From 0d6f55403a47b317c0d9511a80545c19ab0ef52f Mon Sep 17 00:00:00 2001
From: John Ogness <john.ogness@linutronix.de>
Date: Thu, 9 Jul 2020 15:29:41 +0206
Subject: crash: add VMCOREINFO macro to define offset in a struct declared by
 typedef

The existing macro VMCOREINFO_OFFSET() can't be used for structures
declared via typedef because "struct" is not part of type definition.

Create another macro for this purpose.

Signed-off-by: John Ogness <john.ogness@linutronix.de>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Acked-by: Baoquan He <bhe@redhat.com>
Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Signed-off-by: Petr Mladek <pmladek@suse.com>
Link: https://lore.kernel.org/r/20200709132344.760-2-john.ogness@linutronix.de
---
 include/linux/crash_core.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h
index 525510a9f965..43b51c9df571 100644
--- a/include/linux/crash_core.h
+++ b/include/linux/crash_core.h
@@ -53,6 +53,9 @@ phys_addr_t paddr_vmcoreinfo_note(void);
 #define VMCOREINFO_OFFSET(name, field) \
 	vmcoreinfo_append_str("OFFSET(%s.%s)=%lu\n", #name, #field, \
 			      (unsigned long)offsetof(struct name, field))
+#define VMCOREINFO_TYPE_OFFSET(name, field) \
+	vmcoreinfo_append_str("OFFSET(%s.%s)=%lu\n", #name, #field, \
+			      (unsigned long)offsetof(name, field))
 #define VMCOREINFO_LENGTH(name, value) \
 	vmcoreinfo_append_str("LENGTH(%s)=%lu\n", #name, (unsigned long)value)
 #define VMCOREINFO_NUMBER(name) \
-- 
cgit v1.2.3


From 7d8365771ffb0edc336f2cd45e96ef8214a83dca Mon Sep 17 00:00:00 2001
From: Paul Menzel <pmenzel@molgen.mpg.de>
Date: Fri, 3 Jul 2020 16:29:38 +0200
Subject: moduleparams: Add hexint type parameter
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For bitmasks printing values in hex is more convenient.

Prefix with `0x` to make it clear, that it’s a hex value, and pad it
out.

Using the helper for `amdgpu.ppfeaturemask`, it will look like below.

Before:

    $ more /sys/module/amdgpu/parameters/ppfeaturemask
    4294950911

After:

    $ more /sys/module/amdgpu/parameters/ppfeaturemask
    0xffffbfff

Cc: linux-kernel@vger.kernel.org
Cc: amd-gfx@lists.freedesktop.org
Signed-off-by: Paul Menzel <pmenzel@molgen.mpg.de>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/374726/
---
 include/linux/moduleparam.h |  7 ++++++-
 kernel/params.c             | 17 +++++++++--------
 2 files changed, 15 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index 3ef917ff0964..cff7261e98bb 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -118,7 +118,7 @@ struct kparam_array
  * you can create your own by defining those variables.
  *
  * Standard types are:
- *	byte, short, ushort, int, uint, long, ulong
+ *	byte, hexint, short, ushort, int, uint, long, ulong
  *	charp: a character pointer
  *	bool: a bool, values 0/1, y/n, Y/N.
  *	invbool: the above, only sense-reversed (N = true).
@@ -448,6 +448,11 @@ extern int param_set_ullong(const char *val, const struct kernel_param *kp);
 extern int param_get_ullong(char *buffer, const struct kernel_param *kp);
 #define param_check_ullong(name, p) __param_check(name, p, unsigned long long)
 
+extern const struct kernel_param_ops param_ops_hexint;
+extern int param_set_hexint(const char *val, const struct kernel_param *kp);
+extern int param_get_hexint(char *buffer, const struct kernel_param *kp);
+#define param_check_hexint(name, p) param_check_uint(name, p)
+
 extern const struct kernel_param_ops param_ops_charp;
 extern int param_set_charp(const char *val, const struct kernel_param *kp);
 extern int param_get_charp(char *buffer, const struct kernel_param *kp);
diff --git a/kernel/params.c b/kernel/params.c
index 111eee82b999..3835fb82c64b 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -233,14 +233,15 @@ char *parse_args(const char *doing,
 	EXPORT_SYMBOL(param_ops_##name)
 
 
-STANDARD_PARAM_DEF(byte,	unsigned char,		"%hhu",	kstrtou8);
-STANDARD_PARAM_DEF(short,	short,			"%hi",	kstrtos16);
-STANDARD_PARAM_DEF(ushort,	unsigned short,		"%hu",	kstrtou16);
-STANDARD_PARAM_DEF(int,		int,			"%i",	kstrtoint);
-STANDARD_PARAM_DEF(uint,	unsigned int,		"%u",	kstrtouint);
-STANDARD_PARAM_DEF(long,	long,			"%li",	kstrtol);
-STANDARD_PARAM_DEF(ulong,	unsigned long,		"%lu",	kstrtoul);
-STANDARD_PARAM_DEF(ullong,	unsigned long long,	"%llu",	kstrtoull);
+STANDARD_PARAM_DEF(byte,	unsigned char,		"%hhu",		kstrtou8);
+STANDARD_PARAM_DEF(short,	short,			"%hi",		kstrtos16);
+STANDARD_PARAM_DEF(ushort,	unsigned short,		"%hu",		kstrtou16);
+STANDARD_PARAM_DEF(int,		int,			"%i",		kstrtoint);
+STANDARD_PARAM_DEF(uint,	unsigned int,		"%u",		kstrtouint);
+STANDARD_PARAM_DEF(long,	long,			"%li",		kstrtol);
+STANDARD_PARAM_DEF(ulong,	unsigned long,		"%lu",		kstrtoul);
+STANDARD_PARAM_DEF(ullong,	unsigned long long,	"%llu",		kstrtoull);
+STANDARD_PARAM_DEF(hexint,	unsigned int,		"%#08x", 	kstrtouint);
 
 int param_set_charp(const char *val, const struct kernel_param *kp)
 {
-- 
cgit v1.2.3


From 2d05f56af8f52d52dc614ddf4d51c00ea5afb67f Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Wed, 29 Jul 2020 15:41:44 +0200
Subject: fbdev: Remove trailing whitespace

Removes trailing whitespaces in several places.

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20200729134148.6855-2-tzimmermann@suse.de
---
 drivers/video/fbdev/core/fbmem.c | 10 +++++-----
 include/linux/fb.h               | 18 +++++++++---------
 2 files changed, 14 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c
index 30e73ec4ad5c..dd0ccf35f7b7 100644
--- a/drivers/video/fbdev/core/fbmem.c
+++ b/drivers/video/fbdev/core/fbmem.c
@@ -777,7 +777,7 @@ fb_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 
 	if (info->fbops->fb_read)
 		return info->fbops->fb_read(info, buf, count, ppos);
-	
+
 	total_size = info->screen_size;
 
 	if (total_size == 0)
@@ -842,7 +842,7 @@ fb_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
 
 	if (info->fbops->fb_write)
 		return info->fbops->fb_write(info, buf, count, ppos);
-	
+
 	total_size = info->screen_size;
 
 	if (total_size == 0)
@@ -1061,7 +1061,7 @@ EXPORT_SYMBOL(fb_set_var);
 
 int
 fb_blank(struct fb_info *info, int blank)
-{	
+{
 	struct fb_event event;
 	int ret = -EINVAL;
 
@@ -1437,7 +1437,7 @@ out:
 	return res;
 }
 
-static int 
+static int
 fb_release(struct inode *inode, struct file *file)
 __acquires(&info->lock)
 __releases(&info->lock)
@@ -1627,7 +1627,7 @@ static int do_register_framebuffer(struct fb_info *fb_info)
 			fb_info->pixmap.access_align = 32;
 			fb_info->pixmap.flags = FB_PIXMAP_DEFAULT;
 		}
-	}	
+	}
 	fb_info->pixmap.offset = 0;
 
 	if (!fb_info->pixmap.blit_x)
diff --git a/include/linux/fb.h b/include/linux/fb.h
index 2b530e6d86e4..714187bc13ac 100644
--- a/include/linux/fb.h
+++ b/include/linux/fb.h
@@ -124,7 +124,7 @@ struct fb_cursor_user {
  * Register/unregister for framebuffer events
  */
 
-/*	The resolution of the passed in fb_info about to change */ 
+/*	The resolution of the passed in fb_info about to change */
 #define FB_EVENT_MODE_CHANGE		0x01
 
 #ifdef CONFIG_GUMSTIX_AM200EPD
@@ -459,12 +459,12 @@ struct fb_info {
 
 #if IS_ENABLED(CONFIG_FB_BACKLIGHT)
 	/* assigned backlight device */
-	/* set before framebuffer registration, 
+	/* set before framebuffer registration,
 	   remove after unregister */
 	struct backlight_device *bl_dev;
 
 	/* Backlight level curve */
-	struct mutex bl_curve_mutex;	
+	struct mutex bl_curve_mutex;
 	u8 bl_curve[FB_BACKLIGHT_LEVELS];
 #endif
 #ifdef CONFIG_FB_DEFERRED_IO
@@ -483,8 +483,8 @@ struct fb_info {
 		char __iomem *screen_base;	/* Virtual address */
 		char *screen_buffer;
 	};
-	unsigned long screen_size;	/* Amount of ioremapped VRAM or 0 */ 
-	void *pseudo_palette;		/* Fake palette of 16 colors */ 
+	unsigned long screen_size;	/* Amount of ioremapped VRAM or 0 */
+	void *pseudo_palette;		/* Fake palette of 16 colors */
 #define FBINFO_STATE_RUNNING	0
 #define FBINFO_STATE_SUSPENDED	1
 	u32 state;			/* Hardware state i.e suspend */
@@ -587,11 +587,11 @@ static inline struct apertures_struct *alloc_apertures(unsigned int max_num) {
      *  `Generic' versions of the frame buffer device operations
      */
 
-extern int fb_set_var(struct fb_info *info, struct fb_var_screeninfo *var); 
-extern int fb_pan_display(struct fb_info *info, struct fb_var_screeninfo *var); 
+extern int fb_set_var(struct fb_info *info, struct fb_var_screeninfo *var);
+extern int fb_pan_display(struct fb_info *info, struct fb_var_screeninfo *var);
 extern int fb_blank(struct fb_info *info, int blank);
-extern void cfb_fillrect(struct fb_info *info, const struct fb_fillrect *rect); 
-extern void cfb_copyarea(struct fb_info *info, const struct fb_copyarea *area); 
+extern void cfb_fillrect(struct fb_info *info, const struct fb_fillrect *rect);
+extern void cfb_copyarea(struct fb_info *info, const struct fb_copyarea *area);
 extern void cfb_imageblit(struct fb_info *info, const struct fb_image *image);
 /*
  * Drawing operations where framebuffer is in system RAM
-- 
cgit v1.2.3


From e544ea57ac0734bca752eb2d8635fecbe932c356 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Fri, 31 Jul 2020 16:07:46 -0700
Subject: x86/boot/compressed: Force hidden visibility for all symbol
 references

Eliminate all GOT entries in the decompressor binary, by forcing hidden
visibility for all symbol references, which informs the compiler that
such references will be resolved at link time without the need for
allocating GOT entries.

To ensure that no GOT entries will creep back in, add an assertion to
the decompressor linker script that will fire if the .got section has
a non-zero size.

[Arvind: move hidden.h to include/linux instead of making a copy]

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Arvind Sankar <nivedita@alum.mit.edu>
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Nick Desaulniers <ndesaulniers@google.com>
Tested-by: Sedat Dilek <sedat.dilek@gmail.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: Arvind Sankar <nivedita@alum.mit.edu>
Link: https://lore.kernel.org/r/20200731230820.1742553-3-keescook@chromium.org
---
 arch/x86/boot/compressed/Makefile      |  1 +
 arch/x86/boot/compressed/vmlinux.lds.S |  1 +
 drivers/firmware/efi/libstub/Makefile  |  2 +-
 drivers/firmware/efi/libstub/hidden.h  |  6 ------
 include/linux/hidden.h                 | 19 +++++++++++++++++++
 5 files changed, 22 insertions(+), 7 deletions(-)
 delete mode 100644 drivers/firmware/efi/libstub/hidden.h
 create mode 100644 include/linux/hidden.h

(limited to 'include/linux')

diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 3962f592633d..7c687a770537 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -43,6 +43,7 @@ KBUILD_CFLAGS += -Wno-pointer-sign
 KBUILD_CFLAGS += $(call cc-option,-fmacro-prefix-map=$(srctree)/=)
 KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
 KBUILD_CFLAGS += -D__DISABLE_EXPORTS
+KBUILD_CFLAGS += -include $(srctree)/include/linux/hidden.h
 
 KBUILD_AFLAGS  := $(KBUILD_CFLAGS) -D__ASSEMBLY__
 GCOV_PROFILE := n
diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S
index b17d218ccdf9..4bcc943842ab 100644
--- a/arch/x86/boot/compressed/vmlinux.lds.S
+++ b/arch/x86/boot/compressed/vmlinux.lds.S
@@ -81,6 +81,7 @@ SECTIONS
 	DISCARDS
 }
 
+ASSERT(SIZEOF(.got) == 0, "Unexpected GOT entries detected!")
 #ifdef CONFIG_X86_64
 ASSERT(SIZEOF(.got.plt) == 0 || SIZEOF(.got.plt) == 0x18, "Unexpected GOT/PLT entries detected!")
 #else
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index 296b18fbd7a2..5eefd60917df 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -26,7 +26,7 @@ cflags-$(CONFIG_ARM)		:= $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) \
 cflags-$(CONFIG_EFI_GENERIC_STUB) += -I$(srctree)/scripts/dtc/libfdt
 
 KBUILD_CFLAGS			:= $(cflags-y) -Os -DDISABLE_BRANCH_PROFILING \
-				   -include $(srctree)/drivers/firmware/efi/libstub/hidden.h \
+				   -include $(srctree)/include/linux/hidden.h \
 				   -D__NO_FORTIFY \
 				   -ffreestanding \
 				   -fno-stack-protector \
diff --git a/drivers/firmware/efi/libstub/hidden.h b/drivers/firmware/efi/libstub/hidden.h
deleted file mode 100644
index 3493b041f419..000000000000
--- a/drivers/firmware/efi/libstub/hidden.h
+++ /dev/null
@@ -1,6 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * To prevent the compiler from emitting GOT-indirected (and thus absolute)
- * references to any global symbols, override their visibility as 'hidden'
- */
-#pragma GCC visibility push(hidden)
diff --git a/include/linux/hidden.h b/include/linux/hidden.h
new file mode 100644
index 000000000000..49a17b6b5962
--- /dev/null
+++ b/include/linux/hidden.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * When building position independent code with GCC using the -fPIC option,
+ * (or even the -fPIE one on older versions), it will assume that we are
+ * building a dynamic object (either a shared library or an executable) that
+ * may have symbol references that can only be resolved at load time. For a
+ * variety of reasons (ELF symbol preemption, the CoW footprint of the section
+ * that is modified by the loader), this results in all references to symbols
+ * with external linkage to go via entries in the Global Offset Table (GOT),
+ * which carries absolute addresses which need to be fixed up when the
+ * executable image is loaded at an offset which is different from its link
+ * time offset.
+ *
+ * Fortunately, there is a way to inform the compiler that such symbol
+ * references will be satisfied at link time rather than at load time, by
+ * giving them 'hidden' visibility.
+ */
+
+#pragma GCC visibility push(hidden)
-- 
cgit v1.2.3


From e8ee6c8cb61b676f1a2d6b942329e98224bd8ee9 Mon Sep 17 00:00:00 2001
From: Serge Semin <Sergey.Semin@baikalelectronics.ru>
Date: Fri, 31 Jul 2020 23:08:26 +0300
Subject: dmaengine: dw: Add DMA-channels mask cell support

DW DMA IP-core provides a way to synthesize the DMA controller with
channels having different parameters like maximum burst-length,
multi-block support, maximum data width, etc. Those parameters both
explicitly and implicitly affect the channels performance. Since DMA slave
devices might be very demanding to the DMA performance, let's provide a
functionality for the slaves to be assigned with DW DMA channels, which
performance according to the platform engineer fulfill their requirements.
After this patch is applied it can be done by passing the mask of suitable
DMA-channels either directly in the dw_dma_slave structure instance or as
a fifth cell of the DMA DT-property. If mask is zero or not provided, then
there is no limitation on the channels allocation.

For instance Baikal-T1 SoC is equipped with a DW DMAC engine, which first
two channels are synthesized with max burst length of 16, while the rest
of the channels have been created with max-burst-len=4. It would seem that
the first two channels must be faster than the others and should be more
preferable for the time-critical DMA slave devices. In practice it turned
out that the situation is quite the opposite. The channels with
max-burst-len=4 demonstrated a better performance than the channels with
max-burst-len=16 even when they both had been initialized with the same
settings. The performance drop of the first two DMA-channels made them
unsuitable for the DW APB SSI slave device. No matter what settings they
are configured with, full-duplex SPI transfers occasionally experience the
Rx FIFO overflow. It means that the DMA-engine doesn't keep up with
incoming data pace even though the SPI-bus is enabled with speed of 25MHz
while the DW DMA controller is clocked with 50MHz signal. There is no such
problem has been noticed for the channels synthesized with
max-burst-len=4.

Signed-off-by: Serge Semin <Sergey.Semin@baikalelectronics.ru>
Link: https://lore.kernel.org/r/20200731200826.9292-6-Sergey.Semin@baikalelectronics.ru
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/dw/core.c                | 4 ++++
 drivers/dma/dw/of.c                  | 7 +++++--
 include/linux/platform_data/dma-dw.h | 2 ++
 3 files changed, 11 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index 3da0aea9fe25..5f7b9badb965 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -772,6 +772,10 @@ bool dw_dma_filter(struct dma_chan *chan, void *param)
 	if (dws->dma_dev != chan->device->dev)
 		return false;
 
+	/* permit channels in accordance with the channels mask */
+	if (dws->channels && !(dws->channels & dwc->mask))
+		return false;
+
 	/* We have to copy data since dws can be temporary storage */
 	memcpy(&dwc->dws, dws, sizeof(struct dw_dma_slave));
 
diff --git a/drivers/dma/dw/of.c b/drivers/dma/dw/of.c
index 1474b3817ef4..c1cf7675b9d1 100644
--- a/drivers/dma/dw/of.c
+++ b/drivers/dma/dw/of.c
@@ -22,18 +22,21 @@ static struct dma_chan *dw_dma_of_xlate(struct of_phandle_args *dma_spec,
 	};
 	dma_cap_mask_t cap;
 
-	if (dma_spec->args_count != 3)
+	if (dma_spec->args_count < 3 || dma_spec->args_count > 4)
 		return NULL;
 
 	slave.src_id = dma_spec->args[0];
 	slave.dst_id = dma_spec->args[0];
 	slave.m_master = dma_spec->args[1];
 	slave.p_master = dma_spec->args[2];
+	if (dma_spec->args_count >= 4)
+		slave.channels = dma_spec->args[3];
 
 	if (WARN_ON(slave.src_id >= DW_DMA_MAX_NR_REQUESTS ||
 		    slave.dst_id >= DW_DMA_MAX_NR_REQUESTS ||
 		    slave.m_master >= dw->pdata->nr_masters ||
-		    slave.p_master >= dw->pdata->nr_masters))
+		    slave.p_master >= dw->pdata->nr_masters ||
+		    slave.channels >= BIT(dw->pdata->nr_channels)))
 		return NULL;
 
 	dma_cap_zero(cap);
diff --git a/include/linux/platform_data/dma-dw.h b/include/linux/platform_data/dma-dw.h
index fbbeb2f6189b..b34a094b2258 100644
--- a/include/linux/platform_data/dma-dw.h
+++ b/include/linux/platform_data/dma-dw.h
@@ -26,6 +26,7 @@ struct device;
  * @dst_id:	dst request line
  * @m_master:	memory master for transfers on allocated channel
  * @p_master:	peripheral master for transfers on allocated channel
+ * @channels:	mask of the channels permitted for allocation (zero value means any)
  * @hs_polarity:set active low polarity of handshake interface
  */
 struct dw_dma_slave {
@@ -34,6 +35,7 @@ struct dw_dma_slave {
 	u8			dst_id;
 	u8			m_master;
 	u8			p_master;
+	u8			channels;
 	bool			hs_polarity;
 };
 
-- 
cgit v1.2.3


From d92aabca4df182763cd541d342f2d55f8c0a827c Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Sat, 25 Jul 2020 21:15:20 -0700
Subject: firmware: bcm47xx_sprom: Fix -Wmissing-prototypes warnings

bcm47xx_sprom.h did not include a prototype for bcm47xx_fill_sprom()
therefore add one, and make sure we do include that header to fix
-Wmissing-prototypes warnings.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 drivers/firmware/broadcom/bcm47xx_sprom.c |  1 +
 include/linux/bcm47xx_sprom.h             | 10 ++++++++++
 2 files changed, 11 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/firmware/broadcom/bcm47xx_sprom.c b/drivers/firmware/broadcom/bcm47xx_sprom.c
index 4787f86c8ac1..14fbcd11657c 100644
--- a/drivers/firmware/broadcom/bcm47xx_sprom.c
+++ b/drivers/firmware/broadcom/bcm47xx_sprom.c
@@ -27,6 +27,7 @@
  */
 
 #include <linux/bcm47xx_nvram.h>
+#include <linux/bcm47xx_sprom.h>
 #include <linux/bcma/bcma.h>
 #include <linux/etherdevice.h>
 #include <linux/if_ether.h>
diff --git a/include/linux/bcm47xx_sprom.h b/include/linux/bcm47xx_sprom.h
index b0f4424f34fc..f8254fd53e15 100644
--- a/include/linux/bcm47xx_sprom.h
+++ b/include/linux/bcm47xx_sprom.h
@@ -9,9 +9,19 @@
 #include <linux/kernel.h>
 #include <linux/vmalloc.h>
 
+struct ssb_sprom;
+
 #ifdef CONFIG_BCM47XX_SPROM
+void bcm47xx_fill_sprom(struct ssb_sprom *sprom, const char *prefix,
+			bool fallback);
 int bcm47xx_sprom_register_fallbacks(void);
 #else
+static inline void bcm47xx_fill_sprom(struct ssb_sprom *sprom,
+				      const char *prefix,
+				      bool fallback)
+{
+}
+
 static inline int bcm47xx_sprom_register_fallbacks(void)
 {
 	return -ENOTSUPP;
-- 
cgit v1.2.3


From c2fe8ebb332eefb3d0543b248e28dd2992c04793 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Tue, 4 Aug 2020 21:26:42 +0200
Subject: clk: samsung: s3c64xx: declare s3c64xx_clk_init() in shared header

The s3c64xx_clk_init() is defined and used by the clk-s3c64xx driver and
also used in the mach-s3c64xx machine code.  Move the declaration to a
header to fix W=1 build warning:

    drivers/clk/samsung/clk-s3c64xx.c:391:13: warning: no previous prototype for 's3c64xx_clk_init' [-Wmissing-prototypes]
      391 | void __init s3c64xx_clk_init(struct device_node *np, unsigned long xtal_f,

Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Reviewed-by: Tomasz Figa <tomasz.figa@gmail.com>
Acked-by: Chanwoo Choi <cw00.choi@samsung.com>
Reviewed-by: Stephen Boyd <sboyd@kernel.org>
---
 MAINTAINERS                       |  1 +
 arch/arm/mach-s3c64xx/common.c    |  1 +
 arch/arm/mach-s3c64xx/common.h    |  2 --
 drivers/clk/samsung/clk-s3c64xx.c |  1 +
 include/linux/clk/samsung.h       | 24 ++++++++++++++++++++++++
 5 files changed, 27 insertions(+), 2 deletions(-)
 create mode 100644 include/linux/clk/samsung.h

(limited to 'include/linux')

diff --git a/MAINTAINERS b/MAINTAINERS
index 11860c5e15fb..d6abe0cc1a5d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15304,6 +15304,7 @@ F:	Documentation/devicetree/bindings/clock/samsung,s3c*
 F:	Documentation/devicetree/bindings/clock/samsung,s5p*
 F:	drivers/clk/samsung/
 F:	include/dt-bindings/clock/exynos*.h
+F:	include/linux/clk/samsung.h
 
 SAMSUNG SPI DRIVERS
 M:	Kukjin Kim <kgene@kernel.org>
diff --git a/arch/arm/mach-s3c64xx/common.c b/arch/arm/mach-s3c64xx/common.c
index 13e91074308a..a655bf0c7802 100644
--- a/arch/arm/mach-s3c64xx/common.c
+++ b/arch/arm/mach-s3c64xx/common.c
@@ -24,6 +24,7 @@
 #include <linux/platform_device.h>
 #include <linux/reboot.h>
 #include <linux/io.h>
+#include <linux/clk/samsung.h>
 #include <linux/dma-mapping.h>
 #include <linux/irq.h>
 #include <linux/gpio.h>
diff --git a/arch/arm/mach-s3c64xx/common.h b/arch/arm/mach-s3c64xx/common.h
index 03670887a764..f4eca42cdc86 100644
--- a/arch/arm/mach-s3c64xx/common.h
+++ b/arch/arm/mach-s3c64xx/common.h
@@ -22,8 +22,6 @@ void s3c64xx_init_io(struct map_desc *mach_desc, int size);
 void s3c64xx_restart(enum reboot_mode mode, const char *cmd);
 
 struct device_node;
-void s3c64xx_clk_init(struct device_node *np, unsigned long xtal_f,
-	unsigned long xusbxti_f, bool is_s3c6400, void __iomem *reg_base);
 void s3c64xx_set_xtal_freq(unsigned long freq);
 void s3c64xx_set_xusbxti_freq(unsigned long freq);
 
diff --git a/drivers/clk/samsung/clk-s3c64xx.c b/drivers/clk/samsung/clk-s3c64xx.c
index b96d33e5eb45..56f95b63f71f 100644
--- a/drivers/clk/samsung/clk-s3c64xx.c
+++ b/drivers/clk/samsung/clk-s3c64xx.c
@@ -7,6 +7,7 @@
 
 #include <linux/slab.h>
 #include <linux/clk-provider.h>
+#include <linux/clk/samsung.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 
diff --git a/include/linux/clk/samsung.h b/include/linux/clk/samsung.h
new file mode 100644
index 000000000000..7a0824b22eed
--- /dev/null
+++ b/include/linux/clk/samsung.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2020 Krzysztof Kozlowski <krzk@kernel.org>
+ */
+
+#ifndef __LINUX_CLK_SAMSUNG_H_
+#define __LINUX_CLK_SAMSUNG_H_
+
+#include <linux/compiler_types.h>
+
+struct device_node;
+
+#ifdef CONFIG_ARCH_S3C64XX
+void s3c64xx_clk_init(struct device_node *np, unsigned long xtal_f,
+		      unsigned long xusbxti_f, bool s3c6400,
+		      void __iomem *base);
+#else
+static inline void s3c64xx_clk_init(struct device_node *np,
+				    unsigned long xtal_f,
+				    unsigned long xusbxti_f,
+				    bool s3c6400, void __iomem *base) { }
+#endif /* CONFIG_ARCH_S3C64XX */
+
+#endif /* __LINUX_CLK_SAMSUNG_H_ */
-- 
cgit v1.2.3


From 16b17fcf77f2145b98cabbca6bfe6ea13c90bb08 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Tue, 4 Aug 2020 21:26:43 +0200
Subject: clk: samsung: s3c24xx: declare s3c24xx_common_clk_init() in shared
 header

The s3c2410_common_clk_init() and others are defined and used by the
clk-s3c24xx driver and also used in the mach-s3c24xx machine code.  Move
the declaration to a header to fix W=1 build warnings:

    drivers/clk/samsung/clk-s3c2410.c:320:13: warning: no previous prototype for 's3c2410_common_clk_init' [-Wmissing-prototypes]
      320 | void __init s3c2410_common_clk_init(struct device_node *np, unsigned long xti_f,
    drivers/clk/samsung/clk-s3c2412.c:205:13: warning: no previous prototype for 's3c2412_common_clk_init' [-Wmissing-prototypes]
      205 | void __init s3c2412_common_clk_init(struct device_node *np, unsigned long xti_f,
    drivers/clk/samsung/clk-s3c2443.c:341:13: warning: no previous prototype for 's3c2443_common_clk_init' [-Wmissing-prototypes]
      341 | void __init s3c2443_common_clk_init(struct device_node *np, unsigned long xti_f,

Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Acked-by: Chanwoo Choi <cw00.choi@samsung.com>
Reviewed-by: Stephen Boyd <sboyd@kernel.org>
---
 arch/arm/mach-s3c24xx/common.c    |  1 +
 arch/arm/mach-s3c24xx/common.h    | 15 ---------------
 drivers/clk/samsung/clk-s3c2410.c |  1 +
 drivers/clk/samsung/clk-s3c2412.c |  1 +
 drivers/clk/samsung/clk-s3c2443.c |  1 +
 include/linux/clk/samsung.h       | 32 ++++++++++++++++++++++++++++++++
 6 files changed, 36 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/mach-s3c24xx/common.c b/arch/arm/mach-s3c24xx/common.c
index 3dc029c2d2cb..0d55e88ee0a8 100644
--- a/arch/arm/mach-s3c24xx/common.c
+++ b/arch/arm/mach-s3c24xx/common.c
@@ -19,6 +19,7 @@
 #include <linux/io.h>
 #include <linux/platform_data/dma-s3c24xx.h>
 #include <linux/dmaengine.h>
+#include <linux/clk/samsung.h>
 
 #include <mach/hardware.h>
 #include <mach/regs-clock.h>
diff --git a/arch/arm/mach-s3c24xx/common.h b/arch/arm/mach-s3c24xx/common.h
index d087b20e8857..12d2a112eec7 100644
--- a/arch/arm/mach-s3c24xx/common.h
+++ b/arch/arm/mach-s3c24xx/common.h
@@ -108,19 +108,4 @@ extern struct platform_device s3c2443_device_dma;
 
 extern struct platform_device s3c2410_device_dclk;
 
-#ifdef CONFIG_S3C2410_COMMON_CLK
-void __init s3c2410_common_clk_init(struct device_node *np, unsigned long xti_f,
-				    int current_soc,
-				    void __iomem *reg_base);
-#endif
-#ifdef CONFIG_S3C2412_COMMON_CLK
-void __init s3c2412_common_clk_init(struct device_node *np, unsigned long xti_f,
-				unsigned long ext_f, void __iomem *reg_base);
-#endif
-#ifdef CONFIG_S3C2443_COMMON_CLK
-void __init s3c2443_common_clk_init(struct device_node *np, unsigned long xti_f,
-				    int current_soc,
-				    void __iomem *reg_base);
-#endif
-
 #endif /* __ARCH_ARM_MACH_S3C24XX_COMMON_H */
diff --git a/drivers/clk/samsung/clk-s3c2410.c b/drivers/clk/samsung/clk-s3c2410.c
index fcf6764693cc..5831d0606077 100644
--- a/drivers/clk/samsung/clk-s3c2410.c
+++ b/drivers/clk/samsung/clk-s3c2410.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/clk-provider.h>
+#include <linux/clk/samsung.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 
diff --git a/drivers/clk/samsung/clk-s3c2412.c b/drivers/clk/samsung/clk-s3c2412.c
index a95ab5f75163..724ef642f048 100644
--- a/drivers/clk/samsung/clk-s3c2412.c
+++ b/drivers/clk/samsung/clk-s3c2412.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/clk-provider.h>
+#include <linux/clk/samsung.h>
 #include <linux/io.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
diff --git a/drivers/clk/samsung/clk-s3c2443.c b/drivers/clk/samsung/clk-s3c2443.c
index c7aba1e1af70..a827d63766d1 100644
--- a/drivers/clk/samsung/clk-s3c2443.c
+++ b/drivers/clk/samsung/clk-s3c2443.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/clk-provider.h>
+#include <linux/clk/samsung.h>
 #include <linux/io.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
diff --git a/include/linux/clk/samsung.h b/include/linux/clk/samsung.h
index 7a0824b22eed..79097e365f7f 100644
--- a/include/linux/clk/samsung.h
+++ b/include/linux/clk/samsung.h
@@ -21,4 +21,36 @@ static inline void s3c64xx_clk_init(struct device_node *np,
 				    bool s3c6400, void __iomem *base) { }
 #endif /* CONFIG_ARCH_S3C64XX */
 
+#ifdef CONFIG_S3C2410_COMMON_CLK
+void s3c2410_common_clk_init(struct device_node *np, unsigned long xti_f,
+			     int current_soc,
+			     void __iomem *reg_base);
+#else
+static inline void s3c2410_common_clk_init(struct device_node *np,
+					   unsigned long xti_f,
+					   int current_soc,
+					   void __iomem *reg_base) { }
+#endif /* CONFIG_S3C2410_COMMON_CLK */
+
+#ifdef CONFIG_S3C2412_COMMON_CLK
+void s3c2412_common_clk_init(struct device_node *np, unsigned long xti_f,
+			     unsigned long ext_f, void __iomem *reg_base);
+#else
+static inline void s3c2412_common_clk_init(struct device_node *np,
+					   unsigned long xti_f,
+					   unsigned long ext_f,
+					   void __iomem *reg_base) { }
+#endif /* CONFIG_S3C2412_COMMON_CLK */
+
+#ifdef CONFIG_S3C2443_COMMON_CLK
+void s3c2443_common_clk_init(struct device_node *np, unsigned long xti_f,
+			     int current_soc,
+			     void __iomem *reg_base);
+#else
+static inline void s3c2443_common_clk_init(struct device_node *np,
+					   unsigned long xti_f,
+					   int current_soc,
+					   void __iomem *reg_base) { }
+#endif /* CONFIG_S3C2443_COMMON_CLK */
+
 #endif /* __LINUX_CLK_SAMSUNG_H_ */
-- 
cgit v1.2.3


From a0308938ec81cd0dca9d75833ec0dd1b8708917e Mon Sep 17 00:00:00 2001
From: David Stevens <stevensd@chromium.org>
Date: Tue, 18 Aug 2020 16:13:41 +0900
Subject: virtio: add dma-buf support for exported objects

This change adds a new flavor of dma-bufs that can be used by virtio
drivers to share exported objects. A virtio dma-buf can be queried by
virtio drivers to obtain the UUID which identifies the underlying
exported object.

Signed-off-by: David Stevens <stevensd@chromium.org>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20200818071343.3461203-2-stevensd@chromium.org
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
---
 drivers/virtio/Makefile         |  2 +-
 drivers/virtio/virtio.c         |  6 +++
 drivers/virtio/virtio_dma_buf.c | 85 +++++++++++++++++++++++++++++++++++++++++
 include/linux/virtio.h          |  1 +
 include/linux/virtio_dma_buf.h  | 37 ++++++++++++++++++
 5 files changed, 130 insertions(+), 1 deletion(-)
 create mode 100644 drivers/virtio/virtio_dma_buf.c
 create mode 100644 include/linux/virtio_dma_buf.h

(limited to 'include/linux')

diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile
index 4d993791f2d7..49da768ee7fd 100644
--- a/drivers/virtio/Makefile
+++ b/drivers/virtio/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-obj-$(CONFIG_VIRTIO) += virtio.o virtio_ring.o
+obj-$(CONFIG_VIRTIO) += virtio.o virtio_ring.o virtio_dma_buf.o
 obj-$(CONFIG_VIRTIO_MMIO) += virtio_mmio.o
 obj-$(CONFIG_VIRTIO_PCI) += virtio_pci.o
 virtio_pci-y := virtio_pci_modern.o virtio_pci_common.o
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index a977e32a88f2..5d46f0ded92d 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -357,6 +357,12 @@ out:
 }
 EXPORT_SYMBOL_GPL(register_virtio_device);
 
+bool is_virtio_device(struct device *dev)
+{
+	return dev->bus == &virtio_bus;
+}
+EXPORT_SYMBOL_GPL(is_virtio_device);
+
 void unregister_virtio_device(struct virtio_device *dev)
 {
 	int index = dev->index; /* save for after device release */
diff --git a/drivers/virtio/virtio_dma_buf.c b/drivers/virtio/virtio_dma_buf.c
new file mode 100644
index 000000000000..45d6e8647dcf
--- /dev/null
+++ b/drivers/virtio/virtio_dma_buf.c
@@ -0,0 +1,85 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * dma-bufs for virtio exported objects
+ *
+ * Copyright (C) 2020 Google, Inc.
+ */
+
+#include <linux/virtio_dma_buf.h>
+
+/**
+ * virtio_dma_buf_export - Creates a new dma-buf for a virtio exported object
+ * @exp_info: [in] see dma_buf_export(). ops MUST refer to a dma_buf_ops
+ *	struct embedded in a virtio_dma_buf_ops.
+ *
+ * This wraps dma_buf_export() to allow virtio drivers to create a dma-buf
+ * for an virtio exported object that can be queried by other virtio drivers
+ * for the object's UUID.
+ */
+struct dma_buf *virtio_dma_buf_export
+	(const struct dma_buf_export_info *exp_info)
+{
+	const struct virtio_dma_buf_ops *virtio_ops =
+		container_of(exp_info->ops,
+			     const struct virtio_dma_buf_ops, ops);
+
+	if (!exp_info->ops ||
+	    exp_info->ops->attach != &virtio_dma_buf_attach ||
+	    !virtio_ops->get_uuid) {
+		return ERR_PTR(-EINVAL);
+	}
+
+	return dma_buf_export(exp_info);
+}
+EXPORT_SYMBOL(virtio_dma_buf_export);
+
+/**
+ * virtio_dma_buf_attach - mandatory attach callback for virtio dma-bufs
+ */
+int virtio_dma_buf_attach(struct dma_buf *dma_buf,
+			  struct dma_buf_attachment *attach)
+{
+	int ret;
+	const struct virtio_dma_buf_ops *ops =
+		container_of(dma_buf->ops,
+			     const struct virtio_dma_buf_ops, ops);
+
+	if (ops->device_attach) {
+		ret = ops->device_attach(dma_buf, attach);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(virtio_dma_buf_attach);
+
+/**
+ * is_virtio_dma_buf - returns true if the given dma-buf is a virtio dma-buf
+ * @dma_buf: buffer to query
+ */
+bool is_virtio_dma_buf(struct dma_buf *dma_buf)
+{
+	return dma_buf->ops->attach == &virtio_dma_buf_attach;
+}
+EXPORT_SYMBOL(is_virtio_dma_buf);
+
+/**
+ * virtio_dma_buf_get_uuid - gets a virtio dma-buf's exported object's uuid
+ * @dma_buf: [in] buffer to query
+ * @uuid: [out] the uuid
+ *
+ * Returns: 0 on success, negative on failure.
+ */
+int virtio_dma_buf_get_uuid(struct dma_buf *dma_buf,
+			    uuid_t *uuid)
+{
+	const struct virtio_dma_buf_ops *ops =
+		container_of(dma_buf->ops,
+			     const struct virtio_dma_buf_ops, ops);
+
+	if (!is_virtio_dma_buf(dma_buf))
+		return -EINVAL;
+
+	return ops->get_uuid(dma_buf, uuid);
+}
+EXPORT_SYMBOL(virtio_dma_buf_get_uuid);
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index a493eac08393..55ea329fe72a 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -127,6 +127,7 @@ static inline struct virtio_device *dev_to_virtio(struct device *_dev)
 void virtio_add_status(struct virtio_device *dev, unsigned int status);
 int register_virtio_device(struct virtio_device *dev);
 void unregister_virtio_device(struct virtio_device *dev);
+bool is_virtio_device(struct device *dev);
 
 void virtio_break_device(struct virtio_device *dev);
 
diff --git a/include/linux/virtio_dma_buf.h b/include/linux/virtio_dma_buf.h
new file mode 100644
index 000000000000..a2fdf217ac62
--- /dev/null
+++ b/include/linux/virtio_dma_buf.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * dma-bufs for virtio exported objects
+ *
+ * Copyright (C) 2020 Google, Inc.
+ */
+
+#ifndef _LINUX_VIRTIO_DMA_BUF_H
+#define _LINUX_VIRTIO_DMA_BUF_H
+
+#include <linux/dma-buf.h>
+#include <linux/uuid.h>
+#include <linux/virtio.h>
+
+/**
+ * struct virtio_dma_buf_ops - operations possible on exported object dma-buf
+ * @ops: the base dma_buf_ops. ops.attach MUST be virtio_dma_buf_attach.
+ * @device_attach: [optional] callback invoked by virtio_dma_buf_attach during
+ *		   all attach operations.
+ * @get_uid: [required] callback to get the uuid of the exported object.
+ */
+struct virtio_dma_buf_ops {
+	struct dma_buf_ops ops;
+	int (*device_attach)(struct dma_buf *dma_buf,
+			     struct dma_buf_attachment *attach);
+	int (*get_uuid)(struct dma_buf *dma_buf, uuid_t *uuid);
+};
+
+int virtio_dma_buf_attach(struct dma_buf *dma_buf,
+			  struct dma_buf_attachment *attach);
+
+struct dma_buf *virtio_dma_buf_export
+	(const struct dma_buf_export_info *exp_info);
+bool is_virtio_dma_buf(struct dma_buf *dma_buf);
+int virtio_dma_buf_get_uuid(struct dma_buf *dma_buf, uuid_t *uuid);
+
+#endif /* _LINUX_VIRTIO_DMA_BUF_H */
-- 
cgit v1.2.3


From d73568c4ccb01d01e20cd23fefbff8e4a05ddfac Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jslaby@suse.cz>
Date: Tue, 18 Aug 2020 10:56:51 +0200
Subject: vt: make vc_data pointers const in selection.h

There are many functions declared in selection.h which only read from
struct vc_data passed as a parameter. Make all those uses const to hint
the compiler a bit.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Link: https://lore.kernel.org/r/20200818085706.12163-1-jslaby@suse.cz
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/vt/consolemap.c      |  2 +-
 drivers/tty/vt/vt.c              | 15 ++++++++-------
 drivers/video/console/sticon.c   |  2 +-
 drivers/video/fbdev/core/fbcon.c |  2 +-
 include/linux/console.h          |  2 +-
 include/linux/consolemap.h       |  3 ++-
 include/linux/selection.h        | 14 ++++++++------
 7 files changed, 22 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/vt/consolemap.c b/drivers/tty/vt/consolemap.c
index 5947b54d92be..5d5a5fd2dce7 100644
--- a/drivers/tty/vt/consolemap.c
+++ b/drivers/tty/vt/consolemap.c
@@ -268,7 +268,7 @@ unsigned short *set_translate(int m, struct vc_data *vc)
  *    was active.
  * Still, it is now possible to a certain extent to cut and paste non-ASCII.
  */
-u16 inverse_translate(struct vc_data *conp, int glyph, int use_unicode)
+u16 inverse_translate(const struct vc_data *conp, int glyph, int use_unicode)
 {
 	struct uni_pagedir *p;
 	int m;
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index ccb533fd00a2..8f283221330e 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -283,7 +283,8 @@ static inline bool con_should_update(const struct vc_data *vc)
 	return con_is_visible(vc) && !console_blanked;
 }
 
-static inline unsigned short *screenpos(struct vc_data *vc, int offset, int viewed)
+static inline unsigned short *screenpos(const struct vc_data *vc, int offset,
+		int viewed)
 {
 	unsigned short *p;
 	
@@ -543,7 +544,7 @@ int vc_uniscr_check(struct vc_data *vc)
  * This must be preceded by a successful call to vc_uniscr_check() once
  * the console lock has been taken.
  */
-void vc_uniscr_copy_line(struct vc_data *vc, void *dest, int viewed,
+void vc_uniscr_copy_line(const struct vc_data *vc, void *dest, int viewed,
 			 unsigned int row, unsigned int col, unsigned int nr)
 {
 	struct uni_screen *uniscr = get_vc_uniscr(vc);
@@ -4740,7 +4741,7 @@ int con_font_op(struct vc_data *vc, struct console_font_op *op)
  */
 
 /* used by selection */
-u16 screen_glyph(struct vc_data *vc, int offset)
+u16 screen_glyph(const struct vc_data *vc, int offset)
 {
 	u16 w = scr_readw(screenpos(vc, offset, 1));
 	u16 c = w & 0xff;
@@ -4751,7 +4752,7 @@ u16 screen_glyph(struct vc_data *vc, int offset)
 }
 EXPORT_SYMBOL_GPL(screen_glyph);
 
-u32 screen_glyph_unicode(struct vc_data *vc, int n)
+u32 screen_glyph_unicode(const struct vc_data *vc, int n)
 {
 	struct uni_screen *uniscr = get_vc_uniscr(vc);
 
@@ -4762,13 +4763,13 @@ u32 screen_glyph_unicode(struct vc_data *vc, int n)
 EXPORT_SYMBOL_GPL(screen_glyph_unicode);
 
 /* used by vcs - note the word offset */
-unsigned short *screen_pos(struct vc_data *vc, int w_offset, int viewed)
+unsigned short *screen_pos(const struct vc_data *vc, int w_offset, int viewed)
 {
 	return screenpos(vc, 2 * w_offset, viewed);
 }
 EXPORT_SYMBOL_GPL(screen_pos);
 
-void getconsxy(struct vc_data *vc, unsigned char *p)
+void getconsxy(const struct vc_data *vc, unsigned char *p)
 {
 	/* clamp values if they don't fit */
 	p[0] = min(vc->state.x, 0xFFu);
@@ -4782,7 +4783,7 @@ void putconsxy(struct vc_data *vc, unsigned char *p)
 	set_cursor(vc);
 }
 
-u16 vcs_scr_readw(struct vc_data *vc, const u16 *org)
+u16 vcs_scr_readw(const struct vc_data *vc, const u16 *org)
 {
 	if ((unsigned long)org == vc->vc_pos && softcursor_original != -1)
 		return softcursor_original;
diff --git a/drivers/video/console/sticon.c b/drivers/video/console/sticon.c
index 21a5c280c8c9..e21147e8a14e 100644
--- a/drivers/video/console/sticon.c
+++ b/drivers/video/console/sticon.c
@@ -236,7 +236,7 @@ static int sticon_blank(struct vc_data *c, int blank, int mode_switch)
     return 1;
 }
 
-static u16 *sticon_screen_pos(struct vc_data *conp, int offset)
+static u16 *sticon_screen_pos(const struct vc_data *conp, int offset)
 {
     int line;
     unsigned long p;
diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c
index 8a31fc2b2258..6068845d98f2 100644
--- a/drivers/video/fbdev/core/fbcon.c
+++ b/drivers/video/fbdev/core/fbcon.c
@@ -2765,7 +2765,7 @@ static void fbcon_set_palette(struct vc_data *vc, const unsigned char *table)
 	fb_set_cmap(&palette_cmap, info);
 }
 
-static u16 *fbcon_screen_pos(struct vc_data *vc, int offset)
+static u16 *fbcon_screen_pos(const struct vc_data *vc, int offset)
 {
 	unsigned long p;
 	int line;
diff --git a/include/linux/console.h b/include/linux/console.h
index 0670d3491e0e..4b1e26c4cb42 100644
--- a/include/linux/console.h
+++ b/include/linux/console.h
@@ -74,7 +74,7 @@ struct consw {
 			enum vc_intensity intensity,
 			bool blink, bool underline, bool reverse, bool italic);
 	void	(*con_invert_region)(struct vc_data *vc, u16 *p, int count);
-	u16    *(*con_screen_pos)(struct vc_data *vc, int offset);
+	u16    *(*con_screen_pos)(const struct vc_data *vc, int offset);
 	unsigned long (*con_getxy)(struct vc_data *vc, unsigned long position,
 			int *px, int *py);
 	/*
diff --git a/include/linux/consolemap.h b/include/linux/consolemap.h
index 254246673390..bcfce748c9d8 100644
--- a/include/linux/consolemap.h
+++ b/include/linux/consolemap.h
@@ -17,7 +17,8 @@
 #ifdef CONFIG_CONSOLE_TRANSLATIONS
 struct vc_data;
 
-extern u16 inverse_translate(struct vc_data *conp, int glyph, int use_unicode);
+extern u16 inverse_translate(const struct vc_data *conp, int glyph,
+		int use_unicode);
 extern unsigned short *set_translate(int m, struct vc_data *vc);
 extern int conv_uni_to_pc(struct vc_data *conp, long ucs);
 extern u32 conv_8bit_to_uni(unsigned char c);
diff --git a/include/linux/selection.h b/include/linux/selection.h
index 5b890ef5b59f..34404a019ebf 100644
--- a/include/linux/selection.h
+++ b/include/linux/selection.h
@@ -33,21 +33,23 @@ extern unsigned char default_red[];
 extern unsigned char default_grn[];
 extern unsigned char default_blu[];
 
-extern unsigned short *screen_pos(struct vc_data *vc, int w_offset, int viewed);
-extern u16 screen_glyph(struct vc_data *vc, int offset);
-extern u32 screen_glyph_unicode(struct vc_data *vc, int offset);
+extern unsigned short *screen_pos(const struct vc_data *vc, int w_offset,
+		int viewed);
+extern u16 screen_glyph(const struct vc_data *vc, int offset);
+extern u32 screen_glyph_unicode(const struct vc_data *vc, int offset);
 extern void complement_pos(struct vc_data *vc, int offset);
 extern void invert_screen(struct vc_data *vc, int offset, int count, int shift);
 
-extern void getconsxy(struct vc_data *vc, unsigned char *p);
+extern void getconsxy(const struct vc_data *vc, unsigned char *p);
 extern void putconsxy(struct vc_data *vc, unsigned char *p);
 
-extern u16 vcs_scr_readw(struct vc_data *vc, const u16 *org);
+extern u16 vcs_scr_readw(const struct vc_data *vc, const u16 *org);
 extern void vcs_scr_writew(struct vc_data *vc, u16 val, u16 *org);
 extern void vcs_scr_updated(struct vc_data *vc);
 
 extern int vc_uniscr_check(struct vc_data *vc);
-extern void vc_uniscr_copy_line(struct vc_data *vc, void *dest, int viewed,
+extern void vc_uniscr_copy_line(const struct vc_data *vc, void *dest,
+				int viewed,
 				unsigned int row, unsigned int col,
 				unsigned int nr);
 
-- 
cgit v1.2.3


From a5c6bd806dd626103db38dee77796fe758c8df94 Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jslaby@suse.cz>
Date: Tue, 18 Aug 2020 10:56:52 +0200
Subject: vt: declare xy for get/putconsxy properly

That is:
1) call the parameter 'xy' to denote what it really is, not generic 'p'
2) tell the compiler and users that we expect an array:
   * with at least 2 chars (static 2)
   * which we don't modify in putconsxy (const)

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Link: https://lore.kernel.org/r/20200818085706.12163-2-jslaby@suse.cz
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/vt/vt.c       | 10 +++++-----
 include/linux/selection.h |  4 ++--
 2 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 8f283221330e..a0da7771c327 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -4769,17 +4769,17 @@ unsigned short *screen_pos(const struct vc_data *vc, int w_offset, int viewed)
 }
 EXPORT_SYMBOL_GPL(screen_pos);
 
-void getconsxy(const struct vc_data *vc, unsigned char *p)
+void getconsxy(const struct vc_data *vc, unsigned char xy[static 2])
 {
 	/* clamp values if they don't fit */
-	p[0] = min(vc->state.x, 0xFFu);
-	p[1] = min(vc->state.y, 0xFFu);
+	xy[0] = min(vc->state.x, 0xFFu);
+	xy[1] = min(vc->state.y, 0xFFu);
 }
 
-void putconsxy(struct vc_data *vc, unsigned char *p)
+void putconsxy(struct vc_data *vc, unsigned char xy[static const 2])
 {
 	hide_cursor(vc);
-	gotoxy(vc, p[0], p[1]);
+	gotoxy(vc, xy[0], xy[1]);
 	set_cursor(vc);
 }
 
diff --git a/include/linux/selection.h b/include/linux/selection.h
index 34404a019ebf..15e36e7ef869 100644
--- a/include/linux/selection.h
+++ b/include/linux/selection.h
@@ -40,8 +40,8 @@ extern u32 screen_glyph_unicode(const struct vc_data *vc, int offset);
 extern void complement_pos(struct vc_data *vc, int offset);
 extern void invert_screen(struct vc_data *vc, int offset, int count, int shift);
 
-extern void getconsxy(const struct vc_data *vc, unsigned char *p);
-extern void putconsxy(struct vc_data *vc, unsigned char *p);
+extern void getconsxy(const struct vc_data *vc, unsigned char xy[static 2]);
+extern void putconsxy(struct vc_data *vc, unsigned char xy[static const 2]);
 
 extern u16 vcs_scr_readw(const struct vc_data *vc, const u16 *org);
 extern void vcs_scr_writew(struct vc_data *vc, u16 val, u16 *org);
-- 
cgit v1.2.3


From b8209f694f7f4256181deea92d30eedb908d6788 Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jslaby@suse.cz>
Date: Tue, 18 Aug 2020 10:56:53 +0200
Subject: vc: propagate "viewed as bool" from screenpos up

viewed is used as a flag, i.e. bool. So treat is as such in most of the
places. vcs_vc is handled in the next patch.

Note: the last parameter of invert_screen was misnamed in the
declaration since 1.1.92.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Link: https://lore.kernel.org/r/20200818085706.12163-3-jslaby@suse.cz
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/accessibility/speakup/main.c |  4 ++--
 drivers/tty/vt/selection.c           |  2 +-
 drivers/tty/vt/vt.c                  | 18 ++++++++++--------
 include/linux/selection.h            |  6 +++---
 4 files changed, 16 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/accessibility/speakup/main.c b/drivers/accessibility/speakup/main.c
index ddfd12afe3b9..be79b2135fac 100644
--- a/drivers/accessibility/speakup/main.c
+++ b/drivers/accessibility/speakup/main.c
@@ -257,7 +257,7 @@ static struct notifier_block vt_notifier_block = {
 
 static unsigned char get_attributes(struct vc_data *vc, u16 *pos)
 {
-	pos = screen_pos(vc, pos - (u16 *)vc->vc_origin, 1);
+	pos = screen_pos(vc, pos - (u16 *)vc->vc_origin, true);
 	return (scr_readw(pos) & ~vc->vc_hi_font_mask) >> 8;
 }
 
@@ -465,7 +465,7 @@ static u16 get_char(struct vc_data *vc, u16 *pos, u_char *attribs)
 		u16 w;
 		u16 c;
 
-		pos = screen_pos(vc, pos - (u16 *)vc->vc_origin, 1);
+		pos = screen_pos(vc, pos - (u16 *)vc->vc_origin, true);
 		w = scr_readw(pos);
 		c = w & 0xff;
 
diff --git a/drivers/tty/vt/selection.c b/drivers/tty/vt/selection.c
index 8e74654c1b27..f245a5acf7e9 100644
--- a/drivers/tty/vt/selection.c
+++ b/drivers/tty/vt/selection.c
@@ -54,7 +54,7 @@ static struct vc_selection {
 /* set reverse video on characters s-e of console with selection. */
 static inline void highlight(const int s, const int e)
 {
-	invert_screen(vc_sel.cons, s, e-s+2, 1);
+	invert_screen(vc_sel.cons, s, e-s+2, true);
 }
 
 /* use complementary color to show the pointer */
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index a0da7771c327..0f7064d41e92 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -284,7 +284,7 @@ static inline bool con_should_update(const struct vc_data *vc)
 }
 
 static inline unsigned short *screenpos(const struct vc_data *vc, int offset,
-		int viewed)
+		bool viewed)
 {
 	unsigned short *p;
 	
@@ -544,7 +544,7 @@ int vc_uniscr_check(struct vc_data *vc)
  * This must be preceded by a successful call to vc_uniscr_check() once
  * the console lock has been taken.
  */
-void vc_uniscr_copy_line(const struct vc_data *vc, void *dest, int viewed,
+void vc_uniscr_copy_line(const struct vc_data *vc, void *dest, bool viewed,
 			 unsigned int row, unsigned int col, unsigned int nr)
 {
 	struct uni_screen *uniscr = get_vc_uniscr(vc);
@@ -753,7 +753,7 @@ static void update_attr(struct vc_data *vc)
 }
 
 /* Note: inverting the screen twice should revert to the original state */
-void invert_screen(struct vc_data *vc, int offset, int count, int viewed)
+void invert_screen(struct vc_data *vc, int offset, int count, bool viewed)
 {
 	unsigned short *p;
 
@@ -812,7 +812,7 @@ void complement_pos(struct vc_data *vc, int offset)
 
 	if (old_offset != -1 && old_offset >= 0 &&
 	    old_offset < vc->vc_screenbuf_size) {
-		scr_writew(old, screenpos(vc, old_offset, 1));
+		scr_writew(old, screenpos(vc, old_offset, true));
 		if (con_should_update(vc))
 			vc->vc_sw->con_putc(vc, old, oldy, oldx);
 		notify_update(vc);
@@ -824,7 +824,7 @@ void complement_pos(struct vc_data *vc, int offset)
 	    offset < vc->vc_screenbuf_size) {
 		unsigned short new;
 		unsigned short *p;
-		p = screenpos(vc, offset, 1);
+		p = screenpos(vc, offset, true);
 		old = scr_readw(p);
 		new = old ^ vc->vc_complement_mask;
 		scr_writew(new, p);
@@ -1885,7 +1885,9 @@ static void set_mode(struct vc_data *vc, int on_off)
 			case 5:			/* Inverted screen on/off */
 				if (vc->vc_decscnm != on_off) {
 					vc->vc_decscnm = on_off;
-					invert_screen(vc, 0, vc->vc_screenbuf_size, 0);
+					invert_screen(vc, 0,
+							vc->vc_screenbuf_size,
+							false);
 					update_attr(vc);
 				}
 				break;
@@ -4743,7 +4745,7 @@ int con_font_op(struct vc_data *vc, struct console_font_op *op)
 /* used by selection */
 u16 screen_glyph(const struct vc_data *vc, int offset)
 {
-	u16 w = scr_readw(screenpos(vc, offset, 1));
+	u16 w = scr_readw(screenpos(vc, offset, true));
 	u16 c = w & 0xff;
 
 	if (w & vc->vc_hi_font_mask)
@@ -4763,7 +4765,7 @@ u32 screen_glyph_unicode(const struct vc_data *vc, int n)
 EXPORT_SYMBOL_GPL(screen_glyph_unicode);
 
 /* used by vcs - note the word offset */
-unsigned short *screen_pos(const struct vc_data *vc, int w_offset, int viewed)
+unsigned short *screen_pos(const struct vc_data *vc, int w_offset, bool viewed)
 {
 	return screenpos(vc, 2 * w_offset, viewed);
 }
diff --git a/include/linux/selection.h b/include/linux/selection.h
index 15e36e7ef869..170ef28ff26b 100644
--- a/include/linux/selection.h
+++ b/include/linux/selection.h
@@ -34,11 +34,11 @@ extern unsigned char default_grn[];
 extern unsigned char default_blu[];
 
 extern unsigned short *screen_pos(const struct vc_data *vc, int w_offset,
-		int viewed);
+		bool viewed);
 extern u16 screen_glyph(const struct vc_data *vc, int offset);
 extern u32 screen_glyph_unicode(const struct vc_data *vc, int offset);
 extern void complement_pos(struct vc_data *vc, int offset);
-extern void invert_screen(struct vc_data *vc, int offset, int count, int shift);
+extern void invert_screen(struct vc_data *vc, int offset, int count, bool viewed);
 
 extern void getconsxy(const struct vc_data *vc, unsigned char xy[static 2]);
 extern void putconsxy(struct vc_data *vc, unsigned char xy[static const 2]);
@@ -49,7 +49,7 @@ extern void vcs_scr_updated(struct vc_data *vc);
 
 extern int vc_uniscr_check(struct vc_data *vc);
 extern void vc_uniscr_copy_line(const struct vc_data *vc, void *dest,
-				int viewed,
+				bool viewed,
 				unsigned int row, unsigned int col,
 				unsigned int nr);
 
-- 
cgit v1.2.3


From 4524ac56cdcabf77b734ec8021089cba59cac1ac Mon Sep 17 00:00:00 2001
From: Mayulong <mayulong1@huawei.com>
Date: Mon, 17 Aug 2020 09:10:30 +0200
Subject: staging: mfd: add a PMIC driver for HiSilicon 6421 SPMI version

Add the PMIC SPMI driver for the HiSilicon 6421v600.

[mchehab+huawei@kernel.org: keep just the MFD driver on this patch,
 and renamed filenames to better match other upstream drivers]

 The compete patch is at:
	https://github.com/96boards-hikey/linux/commit/08464419fba2

Signed-off-by: Mayulong <mayulong1@huawei.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Link: https://lore.kernel.org/r/4ffb2694244baa47387e39e2c5d71243242c1fc1.1597647359.git.mchehab+huawei@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/hikey9xx/hi6421-spmi-pmic.c | 759 ++++++++++++++++++++++++++++
 include/linux/mfd/hi6421-spmi-pmic.h        | 165 ++++++
 2 files changed, 924 insertions(+)
 create mode 100644 drivers/staging/hikey9xx/hi6421-spmi-pmic.c
 create mode 100644 include/linux/mfd/hi6421-spmi-pmic.h

(limited to 'include/linux')

diff --git a/drivers/staging/hikey9xx/hi6421-spmi-pmic.c b/drivers/staging/hikey9xx/hi6421-spmi-pmic.c
new file mode 100644
index 000000000000..6bb0bc4b203b
--- /dev/null
+++ b/drivers/staging/hikey9xx/hi6421-spmi-pmic.c
@@ -0,0 +1,759 @@
+/*
+ * Device driver for regulators in HISI PMIC IC
+ *
+ * Copyright (c) 2013 Linaro Ltd.
+ * Copyright (c) 2011 Hisilicon.
+ *
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/platform_device.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_device.h>
+#include <linux/of_gpio.h>
+#include <linux/of_irq.h>
+#include <linux/mfd/hisi_pmic.h>
+#include <linux/irq.h>
+#include <linux/spmi.h>
+#ifndef NO_IRQ
+#define NO_IRQ       0
+#endif
+
+/* 8-bit register offset in PMIC */
+#define HISI_MASK_STATE			0xff
+
+#define HISI_IRQ_KEY_NUM		0
+#define HISI_IRQ_KEY_VALUE		0xc0
+#define HISI_IRQ_KEY_DOWN		7
+#define HISI_IRQ_KEY_UP			6
+
+/*#define HISI_NR_IRQ			25*/
+#define HISI_MASK_FIELD		0xFF
+#define HISI_BITS			8
+#define PMIC_FPGA_FLAG          1
+
+/*define the first group interrupt register number*/
+#define HISI_PMIC_FIRST_GROUP_INT_NUM        2
+
+static struct bit_info g_pmic_vbus = {0};
+#ifndef BIT
+#define BIT(x)		(0x1U << (x))
+#endif
+
+static struct hisi_pmic *g_pmic;
+static unsigned int g_extinterrupt_flag  = 0;
+static struct of_device_id of_hisi_pmic_match_tbl[] = {
+	{
+		.compatible = "hisilicon-hisi-pmic-spmi",
+	},
+	{ /* end */ }
+};
+
+/*
+ * The PMIC register is only 8-bit.
+ * Hisilicon SoC use hardware to map PMIC register into SoC mapping.
+ * At here, we are accessing SoC register with 32-bit.
+ */
+u32 hisi_pmic_read(struct hisi_pmic *pmic, int reg)
+{
+	u32 ret;
+	u8 read_value = 0;
+	struct spmi_device *pdev;
+
+	if (NULL == g_pmic) {
+		pr_err(" g_pmic  is NULL\n");
+		return 0;
+	}
+
+	pdev = to_spmi_device(g_pmic->dev);
+	if (NULL == pdev) {
+		pr_err("%s:pdev get failed!\n", __func__);
+		return 0;
+	}
+
+	ret = spmi_ext_register_readl(pdev, reg, (unsigned char*)&read_value, 1);/*lint !e734 !e732 */
+	if (ret) {
+		pr_err("%s:spmi_ext_register_readl failed!\n", __func__);
+		return ret;
+	}
+	return (u32)read_value;
+}
+EXPORT_SYMBOL(hisi_pmic_read);
+
+void hisi_pmic_write(struct hisi_pmic *pmic, int reg, u32 val)
+{
+	u32 ret;
+	struct spmi_device *pdev;
+
+	if (NULL == g_pmic) {
+		pr_err(" g_pmic  is NULL\n");
+		return;
+	}
+
+	pdev = to_spmi_device(g_pmic->dev);
+	if (NULL == pdev) {
+		pr_err("%s:pdev get failed!\n", __func__);
+		return;
+	}
+
+	ret = spmi_ext_register_writel(pdev, reg, (unsigned char*)&val, 1);/*lint !e734 !e732 */
+	if (ret) {
+		pr_err("%s:spmi_ext_register_writel failed!\n", __func__);
+		return ;
+	}
+}
+EXPORT_SYMBOL(hisi_pmic_write);
+
+#ifdef CONFIG_HISI_DIEID
+u32 hisi_pmic_read_sub_pmu(u8 sid, int reg)
+{
+	u32 ret;
+	u8 read_value = 0;
+	struct spmi_device *pdev;
+
+	if(strstr(saved_command_line, "androidboot.swtype=factory"))
+	{
+		if (NULL == g_pmic) {
+			pr_err(" g_pmic  is NULL\n");
+			return -1;/*lint !e570 */
+		}
+
+		pdev = to_spmi_device(g_pmic->dev);
+		if (NULL == pdev) {
+			pr_err("%s:pdev get failed!\n", __func__);
+			return -1;/*lint !e570 */
+		}
+
+		ret = spmi_ext_register_readl(pdev->ctrl, sid, reg, (unsigned char*)&read_value, 1);/*lint !e734 !e732 */
+		if (ret) {
+			pr_err("%s:spmi_ext_register_readl failed!\n", __func__);
+			return ret;
+		}
+		return (u32)read_value;
+	}
+	return  0;
+}
+EXPORT_SYMBOL(hisi_pmic_read_sub_pmu);
+
+void hisi_pmic_write_sub_pmu(u8 sid, int reg, u32 val)
+{
+	u32 ret;
+	struct spmi_device *pdev;
+	if(strstr(saved_command_line, "androidboot.swtype=factory"))
+	{
+		if (NULL == g_pmic) {
+			pr_err(" g_pmic  is NULL\n");
+			return;
+		}
+
+		pdev = to_spmi_device(g_pmic->dev);
+		if (NULL == pdev) {
+			pr_err("%s:pdev get failed!\n", __func__);
+			return;
+		}
+
+		ret = spmi_ext_register_writel(pdev->ctrl, sid, reg, (unsigned char*)&val, 1);/*lint !e734 !e732 */
+		if (ret) {
+			pr_err("%s:spmi_ext_register_writel failed!\n", __func__);
+			return ;
+		}
+	}
+
+	return ;
+}
+EXPORT_SYMBOL(hisi_pmic_write_sub_pmu);
+#endif
+
+void hisi_pmic_rmw(struct hisi_pmic *pmic, int reg,
+		     u32 mask, u32 bits)
+{
+	u32 data;
+	unsigned long flags;
+
+	if (NULL == g_pmic) {
+		pr_err(" g_pmic  is NULL\n");
+		return;
+	}
+
+	spin_lock_irqsave(&g_pmic->lock, flags);
+	data = hisi_pmic_read(pmic, reg) & ~mask;
+	data |= mask & bits;
+	hisi_pmic_write(pmic, reg, data);
+	spin_unlock_irqrestore(&g_pmic->lock, flags);
+}
+EXPORT_SYMBOL(hisi_pmic_rmw);
+
+unsigned int hisi_pmic_reg_read(int addr)
+{
+	return (unsigned int)hisi_pmic_read(g_pmic, addr);
+}
+EXPORT_SYMBOL(hisi_pmic_reg_read);
+
+void hisi_pmic_reg_write(int addr, int val)
+{
+	hisi_pmic_write(g_pmic, addr, val);
+}
+EXPORT_SYMBOL(hisi_pmic_reg_write);
+
+void hisi_pmic_reg_write_lock(int addr, int val)
+{
+	unsigned long flags;
+
+	if (NULL == g_pmic) {
+		pr_err(" g_pmic  is NULL\n");
+		return;
+	}
+
+	spin_lock_irqsave(&g_pmic->lock, flags);
+	hisi_pmic_write(g_pmic, g_pmic->normal_lock.addr, g_pmic->normal_lock.val);
+	hisi_pmic_write(g_pmic, g_pmic->debug_lock.addr, g_pmic->debug_lock.val);
+	hisi_pmic_write(g_pmic, addr, val);
+	hisi_pmic_write(g_pmic, g_pmic->normal_lock.addr, 0);
+	hisi_pmic_write(g_pmic, g_pmic->debug_lock.addr, 0);
+	spin_unlock_irqrestore(&g_pmic->lock, flags);
+}
+
+int hisi_pmic_array_read(int addr, char *buff, unsigned int len)
+{
+	unsigned int i;
+
+	if ((len > 32) || (NULL == buff)) {
+		return -EINVAL;
+	}
+
+	/*
+	 * Here is a bug in the pmu die.
+	 * the coul driver will read 4 bytes,
+	 * but the ssi bus only read 1 byte, and the pmu die
+	 * will make sampling 1/10669us about vol cur,so the driver
+	 * read the data is not the same sampling
+	 */
+	for (i = 0; i < len; i++)
+	{
+		*(buff + i) = hisi_pmic_reg_read(addr+i);
+	}
+
+	return 0;
+}
+
+int hisi_pmic_array_write(int addr, char *buff, unsigned int len)
+{
+    unsigned int i;
+
+	if ((len > 32) || (NULL == buff)) {
+		return -EINVAL;
+	}
+
+	for (i = 0; i < len; i++)
+	{
+		hisi_pmic_reg_write(addr+i, *(buff + i));
+	}
+
+	return 0;
+}
+
+static irqreturn_t hisi_irq_handler(int irq, void *data)
+{
+	struct hisi_pmic *pmic = (struct hisi_pmic *)data;
+	unsigned long pending;
+	int i, offset;
+
+	for (i = 0; i < pmic->irqarray; i++) {
+		pending = hisi_pmic_reg_read((i + pmic->irq_addr.start_addr));
+		pending &= HISI_MASK_FIELD;
+		if (pending != 0) {
+			pr_info("pending[%d]=0x%lx\n\r", i, pending);
+		}
+
+		hisi_pmic_reg_write((i + pmic->irq_addr.start_addr), pending);
+
+		/*solve powerkey order*/
+		if ((HISI_IRQ_KEY_NUM == i) && ((pending & HISI_IRQ_KEY_VALUE) == HISI_IRQ_KEY_VALUE)) {
+			generic_handle_irq(pmic->irqs[HISI_IRQ_KEY_DOWN]);
+			generic_handle_irq(pmic->irqs[HISI_IRQ_KEY_UP]);
+			pending &= (~HISI_IRQ_KEY_VALUE);
+		}
+
+		if (pending) {
+			for_each_set_bit(offset, &pending, HISI_BITS)
+				generic_handle_irq(pmic->irqs[offset + i * HISI_BITS]);/*lint !e679 */
+		}
+	}
+
+	/*Handle the second group irq if analysis the second group irq from dtsi*/
+	if (1 == g_extinterrupt_flag){
+		for (i = 0; i < pmic->irqarray1; i++) {
+			pending = hisi_pmic_reg_read((i + pmic->irq_addr1.start_addr));
+			pending &= HISI_MASK_FIELD;
+			if (pending != 0) {
+				pr_info("pending[%d]=0x%lx\n\r", i, pending);
+			}
+
+			hisi_pmic_reg_write((i + pmic->irq_addr1.start_addr), pending);
+
+			if (pending) {
+				for_each_set_bit(offset, &pending, HISI_BITS)
+					generic_handle_irq(pmic->irqs[offset + (i+HISI_PMIC_FIRST_GROUP_INT_NUM) * HISI_BITS]);/*lint !e679 */
+			}
+		}
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void hisi_irq_mask(struct irq_data *d)
+{
+	struct hisi_pmic *pmic = irq_data_get_irq_chip_data(d);
+	u32 data, offset;
+	unsigned long flags;
+
+	if (NULL == g_pmic) {
+		pr_err(" g_pmic  is NULL\n");
+		return;
+	}
+
+	offset = (irqd_to_hwirq(d) >> 3);
+	if (1==g_extinterrupt_flag){
+		if ( offset < HISI_PMIC_FIRST_GROUP_INT_NUM)
+			offset += pmic->irq_mask_addr.start_addr;
+		else/*Change addr when irq num larger than 16 because interrupt addr is nonsequence*/
+			offset = offset+(pmic->irq_mask_addr1.start_addr)-HISI_PMIC_FIRST_GROUP_INT_NUM;
+	}else{
+		offset += pmic->irq_mask_addr.start_addr;
+	}
+	spin_lock_irqsave(&g_pmic->lock, flags);
+	data = hisi_pmic_reg_read(offset);
+	data |= (1 << (irqd_to_hwirq(d) & 0x07));
+	hisi_pmic_reg_write(offset, data);
+	spin_unlock_irqrestore(&g_pmic->lock, flags);
+}
+
+static void hisi_irq_unmask(struct irq_data *d)
+{
+	struct hisi_pmic *pmic = irq_data_get_irq_chip_data(d);
+	u32 data, offset;
+	unsigned long flags;
+
+	if (NULL == g_pmic) {
+		pr_err(" g_pmic  is NULL\n");
+		return;
+	}
+
+	offset = (irqd_to_hwirq(d) >> 3);
+	if (1==g_extinterrupt_flag){
+		if ( offset < HISI_PMIC_FIRST_GROUP_INT_NUM)
+			offset += pmic->irq_mask_addr.start_addr;
+		else
+			offset = offset+(pmic->irq_mask_addr1.start_addr)-HISI_PMIC_FIRST_GROUP_INT_NUM;
+	}else{
+		offset += pmic->irq_mask_addr.start_addr;
+	}
+	spin_lock_irqsave(&g_pmic->lock, flags);
+	data = hisi_pmic_reg_read(offset);
+	data &= ~(1 << (irqd_to_hwirq(d) & 0x07)); /*lint !e502 */
+	hisi_pmic_reg_write(offset, data);
+	spin_unlock_irqrestore(&g_pmic->lock, flags);
+}
+
+static struct irq_chip hisi_pmu_irqchip = {
+	.name		= "hisi-irq",
+	.irq_mask	= hisi_irq_mask,
+	.irq_unmask	= hisi_irq_unmask,
+	.irq_disable	= hisi_irq_mask,
+	.irq_enable	= hisi_irq_unmask,
+};
+
+static int hisi_irq_map(struct irq_domain *d, unsigned int virq,
+			  irq_hw_number_t hw)
+{
+	struct hisi_pmic *pmic = d->host_data;
+
+	irq_set_chip_and_handler_name(virq, &hisi_pmu_irqchip,
+				      handle_simple_irq, "hisi");
+	irq_set_chip_data(virq, pmic);
+	irq_set_irq_type(virq, IRQ_TYPE_NONE);
+
+	return 0;
+}
+
+static struct irq_domain_ops hisi_domain_ops = {
+	.map	= hisi_irq_map,
+	.xlate	= irq_domain_xlate_twocell,
+};
+
+/*lint -e570 -e64*/
+static int get_pmic_device_tree_data(struct device_node *np, struct hisi_pmic *pmic)
+{
+	int ret = 0;
+
+	/*get pmic irq num*/
+	ret = of_property_read_u32_array(np, "hisilicon,hisi-pmic-irq-num",
+						&(pmic->irqnum), 1);
+	if (ret) {
+		pr_err("no hisilicon,hisi-pmic-irq-num property set\n");
+		ret = -ENODEV;
+		return ret;
+	}
+
+	/*get pmic irq array number*/
+	ret = of_property_read_u32_array(np, "hisilicon,hisi-pmic-irq-array",
+						&(pmic->irqarray), 1);
+	if (ret) {
+		pr_err("no hisilicon,hisi-pmic-irq-array property set\n");
+		ret = -ENODEV;
+		return ret;
+	}
+
+	/*SOC_PMIC_IRQ_MASK_0_ADDR*/
+	ret = of_property_read_u32_array(np, "hisilicon,hisi-pmic-irq-mask-addr",
+						(int *)&pmic->irq_mask_addr, 2);
+	if (ret) {
+		pr_err("no hisilicon,hisi-pmic-irq-mask-addr property set\n");
+		ret = -ENODEV;
+		return ret;
+	}
+
+	/*SOC_PMIC_IRQ0_ADDR*/
+	ret = of_property_read_u32_array(np, "hisilicon,hisi-pmic-irq-addr",
+						(int *)&pmic->irq_addr, 2);
+	if (ret) {
+		pr_err("no hisilicon,hisi-pmic-irq-addr property set\n");
+		ret = -ENODEV;
+		return ret;
+	}
+
+	ret = of_property_read_u32_array(np, "hisilicon,hisi-pmic-vbus",
+						(u32 *)&g_pmic_vbus, 2);
+	if (ret) {
+		pr_err("no hisilicon,hisi-pmic-vbus property\n");
+		ret = -ENODEV;
+		return ret;
+	}
+
+	/*pmic lock*/
+	ret = of_property_read_u32_array(np, "hisilicon,hisi-pmic-lock",
+						(int *)&pmic->normal_lock, 2);
+	if (ret) {
+		pr_err("no hisilicon,hisi-pmic-lock property set\n");
+		ret = -ENODEV;
+		return ret;
+	}
+
+	/*pmic debug lock*/
+	ret = of_property_read_u32_array(np, "hisilicon,hisi-pmic-debug-lock",
+						(int *)&pmic->debug_lock, 2);
+	if (ret) {
+		pr_err("no hisilicon,hisi-pmic-debug-lock property set\n");
+		ret = -ENODEV;
+		return ret;
+	}
+
+	return ret;
+}/*lint -restore*/
+
+
+/*lint -e570 -e64*/
+static int get_pmic_device_tree_data1(struct device_node *np, struct hisi_pmic *pmic)
+{
+	int ret = 0;
+
+	/*get pmic irq num*/
+	ret = of_property_read_u32_array(np, "hisilicon,hisi-pmic-irq-num1",
+						&(pmic->irqnum1), 1);
+	if (ret) {
+		pr_err("no hisilicon,hisi-pmic-irq-num1 property set\n");
+		ret = -ENODEV;
+		pmic->irqnum1 = 0;
+		return ret;
+	}
+
+	/*get pmic irq array number*/
+	ret = of_property_read_u32_array(np, "hisilicon,hisi-pmic-irq-array1",
+						&(pmic->irqarray1), 1);
+	if (ret) {
+		pr_err("no hisilicon,hisi-pmic-irq-array1 property set\n");
+		ret = -ENODEV;
+		return ret;
+	}
+
+	/*SOC_PMIC_IRQ_MASK_0_ADDR*/
+	ret = of_property_read_u32_array(np, "hisilicon,hisi-pmic-irq-mask-addr1",
+						(int *)&pmic->irq_mask_addr1, 2);
+	if (ret) {
+		pr_err("no hisilicon,hisi-pmic-irq-mask-addr1 property set\n");
+		ret = -ENODEV;
+		return ret;
+	}
+
+	/*SOC_PMIC_IRQ0_ADDR*/
+	ret = of_property_read_u32_array(np, "hisilicon,hisi-pmic-irq-addr1",
+						(int *)&pmic->irq_addr1, 2);
+	if (ret) {
+		pr_err("no hisilicon,hisi-pmic-irq-addr1 property set\n");
+		ret = -ENODEV;
+		return ret;
+	}
+
+	g_extinterrupt_flag = 1;
+	return ret;
+}/*lint -restore*/
+
+int hisi_get_pmic_irq_byname(unsigned int pmic_irq_list)
+{
+	if ( NULL == g_pmic ) {
+		pr_err("[%s]g_pmic is NULL\n", __func__);
+		return -1;
+	}
+
+	if (pmic_irq_list > (unsigned int)g_pmic->irqnum) {
+		pr_err("[%s]input pmic irq number is error.\n", __func__);
+		return -1;
+	}
+	pr_info("%s:g_pmic->irqs[%d]=%d\n", __func__, pmic_irq_list, g_pmic->irqs[pmic_irq_list]);
+	return (int)g_pmic->irqs[pmic_irq_list];
+}
+EXPORT_SYMBOL(hisi_get_pmic_irq_byname);
+
+int hisi_pmic_get_vbus_status(void)
+{
+	if (0 == g_pmic_vbus.addr)
+		return -1;
+
+	if (hisi_pmic_reg_read(g_pmic_vbus.addr) & BIT(g_pmic_vbus.bit))
+		return 1;
+
+	return 0;
+}
+EXPORT_SYMBOL(hisi_pmic_get_vbus_status);
+
+static void hisi_pmic_irq_prc(struct hisi_pmic *pmic)
+{
+	int i;
+	for (i = 0 ; i < pmic->irq_mask_addr.array; i++) {
+		hisi_pmic_write(pmic, pmic->irq_mask_addr.start_addr + i, HISI_MASK_STATE);
+	}
+
+	for (i = 0 ; i < pmic->irq_addr.array; i++) {
+		unsigned int pending = hisi_pmic_read(pmic, pmic->irq_addr.start_addr + i);
+		pr_debug("PMU IRQ address value:irq[0x%x] = 0x%x\n", pmic->irq_addr.start_addr + i, pending);
+		hisi_pmic_write(pmic, pmic->irq_addr.start_addr + i, HISI_MASK_STATE);
+	}
+
+}
+
+static void hisi_pmic_irq1_prc(struct hisi_pmic *pmic)
+{
+	int i;
+	if(1 == g_extinterrupt_flag){
+		for (i = 0 ; i < pmic->irq_mask_addr1.array; i++) {
+			hisi_pmic_write(pmic, pmic->irq_mask_addr1.start_addr + i, HISI_MASK_STATE);
+		}
+
+		for (i = 0 ; i < pmic->irq_addr1.array; i++) {
+			unsigned int pending1 = hisi_pmic_read(pmic, pmic->irq_addr1.start_addr + i);
+			pr_debug("PMU IRQ address1 value:irq[0x%x] = 0x%x\n", pmic->irq_addr1.start_addr + i, pending1);
+			hisi_pmic_write(pmic, pmic->irq_addr1.start_addr + i, HISI_MASK_STATE);
+		}
+	}
+}
+
+static int hisi_pmic_probe(struct spmi_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct hisi_pmic *pmic = NULL;
+	enum of_gpio_flags flags;
+	int ret = 0;
+	int i;
+	unsigned int fpga_flag = 0;
+	unsigned int virq;
+
+	pmic = devm_kzalloc(dev, sizeof(*pmic), GFP_KERNEL);
+	if (!pmic) {
+		dev_err(dev, "cannot allocate hisi_pmic device info\n");
+		return -ENOMEM;
+	}
+
+	/*TODO: get pmic dts info*/
+	ret = get_pmic_device_tree_data(np, pmic);
+	if (ret) {
+		dev_err(&pdev->dev, "Error reading hisi pmic dts \n");
+		return ret;
+	}
+
+	/*get pmic dts the second group irq*/
+	ret = get_pmic_device_tree_data1(np, pmic);
+	if (ret) {
+		dev_err(&pdev->dev, "the platform don't support ext-interrupt.\n");
+	}
+
+	/* TODO: get and enable clk request */
+	spin_lock_init(&pmic->lock);
+
+	pmic->dev = dev;
+	g_pmic = pmic;
+	ret = of_property_read_u32_array(np, "hisilicon,pmic_fpga_flag", &fpga_flag, 1);
+	if (ret) {
+		pr_err("no hisilicon,pmic_fpga_flag property set\n");
+	}
+	if (PMIC_FPGA_FLAG == fpga_flag) {
+		goto after_irq_register;
+	}
+
+	pmic->gpio = of_get_gpio_flags(np, 0, &flags);
+	if (pmic->gpio < 0)
+		return pmic->gpio;
+
+	if (!gpio_is_valid(pmic->gpio))
+		return -EINVAL;
+
+	ret = gpio_request_one(pmic->gpio, GPIOF_IN, "pmic");
+	if (ret < 0) {
+		dev_err(dev, "failed to request gpio%d\n", pmic->gpio);
+		return ret;
+	}
+
+	pmic->irq = gpio_to_irq(pmic->gpio);
+
+	/* mask && clear IRQ status */
+	hisi_pmic_irq_prc(pmic);
+	/*clear && mask the new adding irq*/
+	hisi_pmic_irq1_prc(pmic);
+
+	pmic->irqnum += pmic->irqnum1;
+
+	pmic->irqs = (unsigned int *)devm_kmalloc(dev, pmic->irqnum * sizeof(int), GFP_KERNEL);
+	if (!pmic->irqs) {
+		pr_err("%s:Failed to alloc memory for pmic irq number!\n", __func__);
+		goto irq_malloc;
+	}
+	memset(pmic->irqs, 0, pmic->irqnum);
+
+	pmic->domain = irq_domain_add_simple(np, pmic->irqnum, 0,
+					     &hisi_domain_ops, pmic);
+	if (!pmic->domain) {
+		dev_err(dev, "failed irq domain add simple!\n");
+		ret = -ENODEV;
+		goto irq_domain;
+	}
+
+	for (i = 0; i < pmic->irqnum; i++) {
+		virq = irq_create_mapping(pmic->domain, i);
+		if (virq == NO_IRQ) {
+			pr_debug("Failed mapping hwirq\n");
+			ret = -ENOSPC;
+			goto irq_create_mapping;
+		}
+		pmic->irqs[i] = virq;
+		pr_info("[%s]. pmic->irqs[%d] = %d\n", __func__, i, pmic->irqs[i]);
+	}
+
+	ret = request_threaded_irq(pmic->irq, hisi_irq_handler, NULL,
+				IRQF_TRIGGER_LOW | IRQF_SHARED | IRQF_NO_SUSPEND,
+				   "pmic", pmic);
+	if (ret < 0) {
+		dev_err(dev, "could not claim pmic %d\n", ret);
+		ret = -ENODEV;
+		goto request_theaded_irq;
+	}
+
+after_irq_register:
+	return 0;
+
+
+request_theaded_irq:
+irq_create_mapping:
+irq_domain:
+irq_malloc:
+	gpio_free(pmic->gpio);
+	g_pmic = NULL;
+	return ret;
+}
+
+static void hisi_pmic_remove(struct spmi_device *pdev)
+{
+
+	struct hisi_pmic *pmic = dev_get_drvdata(&pdev->dev);
+
+	free_irq(pmic->irq, pmic);
+	gpio_free(pmic->gpio);
+	devm_kfree(&pdev->dev, pmic);
+
+}
+static int hisi_pmic_suspend(struct device *dev, pm_message_t state)
+{
+	struct hisi_pmic *pmic = dev_get_drvdata(dev);
+
+	if (NULL == pmic) {
+		pr_err("%s:pmic is NULL\n", __func__);
+		return -ENOMEM;
+	}
+
+	pr_info("%s:+\n", __func__);
+	pr_info("%s:-\n", __func__);
+
+	return 0;
+}/*lint !e715 */
+
+static int hisi_pmic_resume(struct device *dev)
+{
+	struct hisi_pmic *pmic = dev_get_drvdata(dev);
+
+	if (NULL == pmic) {
+		pr_err("%s:pmic is NULL\n", __func__);
+		return -ENOMEM;
+	}
+
+	pr_info("%s:+\n", __func__);
+	pr_info("%s:-\n", __func__);
+
+	return 0;
+}
+
+MODULE_DEVICE_TABLE(spmi, pmic_spmi_id);
+static struct spmi_driver hisi_pmic_driver = {
+	.driver = {
+		.name	= "hisi_pmic",
+		.owner  = THIS_MODULE,
+		.of_match_table = of_hisi_pmic_match_tbl,
+		.suspend = hisi_pmic_suspend,
+		.resume = hisi_pmic_resume,
+	},
+	.probe	= hisi_pmic_probe,
+	.remove	= hisi_pmic_remove,
+};
+
+static int __init hisi_pmic_init(void)
+{
+	return spmi_driver_register(&hisi_pmic_driver);
+}
+
+static void __exit hisi_pmic_exit(void)
+{
+	spmi_driver_unregister(&hisi_pmic_driver);
+}
+
+
+subsys_initcall_sync(hisi_pmic_init);
+module_exit(hisi_pmic_exit);
+
+MODULE_DESCRIPTION("PMIC driver");
+MODULE_LICENSE("GPL v2");
+
diff --git a/include/linux/mfd/hi6421-spmi-pmic.h b/include/linux/mfd/hi6421-spmi-pmic.h
new file mode 100644
index 000000000000..939b36f617c1
--- /dev/null
+++ b/include/linux/mfd/hi6421-spmi-pmic.h
@@ -0,0 +1,165 @@
+/*
+ * Header file for device driver Hi6421 PMIC
+ *
+ * Copyright (c) 2013 Linaro Ltd.
+ * Copyright (C) 2011 Hisilicon.
+ *
+ * Guodong Xu <guodong.xu@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+ */
+
+#ifndef	__HISI_PMIC_H
+#define	__HISI_PMIC_H
+
+#include <linux/irqdomain.h>
+
+#define HISI_REGS_ENA_PROTECT_TIME	(0) 	/* in microseconds */
+#define HISI_ECO_MODE_ENABLE		(1)
+#define HISI_ECO_MODE_DISABLE		(0)
+
+typedef int (*pmic_ocp_callback)(char *);
+extern int hisi_pmic_special_ocp_register(char *power_name, pmic_ocp_callback handler);
+
+struct irq_mask_info {
+	int start_addr;
+	int array;
+};
+
+struct irq_info {
+	int start_addr;
+	int array;
+};
+
+struct bit_info {
+	int addr;
+	int bit;
+};
+
+struct write_lock {
+	int addr;
+	int val;
+};
+
+struct hisi_pmic {
+	struct resource		*res;
+	struct device		*dev;
+	void __iomem		*regs;
+	spinlock_t		lock;
+	struct irq_domain	*domain;
+	int			irq;
+	int			gpio;
+	unsigned int	*irqs;
+	int			irqnum;
+	int			irqarray;
+	struct irq_mask_info irq_mask_addr;
+	struct irq_info irq_addr;
+	int			irqnum1;
+	int			irqarray1;
+	struct irq_mask_info irq_mask_addr1;
+	struct irq_info irq_addr1;
+	struct write_lock normal_lock;
+	struct write_lock debug_lock;
+};
+
+/* 0:disable; 1:enable */
+unsigned int get_uv_mntn_status(void);
+void clear_uv_mntn_resered_reg_bit(void);
+void set_uv_mntn_resered_reg_bit(void);
+
+#if defined(CONFIG_HISI_PMIC) || defined(CONFIG_HISI_PMIC_PMU_SPMI)
+/* Register Access Helpers */
+u32 hisi_pmic_read(struct hisi_pmic *pmic, int reg);
+void hisi_pmic_write(struct hisi_pmic *pmic, int reg, u32 val);
+void hisi_pmic_rmw(struct hisi_pmic *pmic, int reg, u32 mask, u32 bits);
+unsigned int hisi_pmic_reg_read(int addr);
+void hisi_pmic_reg_write(int addr, int val);
+void hisi_pmic_reg_write_lock(int addr, int val);
+int hisi_pmic_array_read(int addr, char *buff, unsigned int len);
+int hisi_pmic_array_write(int addr, char *buff, unsigned int len);
+extern int hisi_get_pmic_irq_byname(unsigned int pmic_irq_list);
+extern int hisi_pmic_get_vbus_status(void);
+#if defined(CONFIG_HISI_DIEID)
+u32 hisi_pmic_read_sub_pmu(u8 sid ,int reg);
+void hisi_pmic_write_sub_pmu(u8 sid ,int reg, u32 val);
+#endif
+#else
+static inline u32 hisi_pmic_read(struct hisi_pmic *pmic, int reg) { return 0; }
+static inline void hisi_pmic_write(struct hisi_pmic *pmic, int reg, u32 val) {}
+static inline void hisi_pmic_rmw(struct hisi_pmic *pmic, int reg, u32 mask, u32 bits) {}
+static inline unsigned int hisi_pmic_reg_read(int addr) { return 0; }
+static inline void hisi_pmic_reg_write(int addr, int val) {}
+static inline void hisi_pmic_reg_write_lock(int addr, int val) {}
+static inline int hisi_pmic_array_read(int addr, char *buff, unsigned int len) { return 0; }
+static inline int hisi_pmic_array_write(int addr, char *buff, unsigned int len) { return 0; }
+static inline int hisi_get_pmic_irq_byname(unsigned int pmic_irq_list) { return -1; }
+static inline int hisi_pmic_get_vbus_status(void) { return 1; }
+static inline u32 hisi_pmic_read_sub_pmu(u8 sid ,int reg) { return 0; }
+static inline void hisi_pmic_write_sub_pmu(u8 sid ,int reg, u32 val) {}
+#endif
+
+#ifdef CONFIG_HISI_HI6421V500_PMU
+enum pmic_irq_list {
+	POR_D45MR = 0,
+	VBUS_CONNECT,
+	VBUS_DISCONNECT,
+	ALARMON_R,
+	HOLD_6S,
+	HOLD_1S,
+	POWERKEY_UP,
+	POWERKEY_DOWN,
+	OCP_SCP_R,
+	COUL_R,
+	VSYS_OV,
+	VSYS_UV,
+	VSYS_PWROFF_ABS,
+	VSYS_PWROFF_DEB,
+	THSD_OTMP140,
+	THSD_OTMP125,
+	HRESETN,
+	SIM0_HPD_R = 24,
+	SIM0_HPD_F,
+	SIM0_HPD_H,
+	SIM0_HPD_L,
+	SIM1_HPD_R,
+	SIM1_HPD_F,
+	SIM1_HPD_H,
+	SIM1_HPD_L,
+	PMIC_IRQ_LIST_MAX,
+};
+#else
+enum pmic_irq_list {
+	OTMP = 0,
+	VBUS_CONNECT,
+	VBUS_DISCONNECT,
+	ALARMON_R,
+	HOLD_6S,
+	HOLD_1S,
+	POWERKEY_UP,
+	POWERKEY_DOWN,
+	OCP_SCP_R,
+	COUL_R,
+	SIM0_HPD_R,
+	SIM0_HPD_F,
+	SIM1_HPD_R,
+	SIM1_HPD_F,
+	PMIC_IRQ_LIST_MAX,
+};
+#endif
+
+#ifdef CONFIG_HISI_SR_DEBUG
+extern void get_ip_regulator_state(void);
+#endif
+#endif		/* __HISI_PMIC_H */
+
-- 
cgit v1.2.3


From 489b1a36b111b6a3a4ac1acf29de5cf154810887 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Mon, 17 Aug 2020 09:10:31 +0200
Subject: staging: mfd: hi6421-spmi-pmic: get rid of unused code

There are some checks there which could make sense for
downstream builds, but doesn't make much sense for
upstream ones. They came from the official Hikey970 tree
from Linaro, but even there, the commented-out code is not
set via other Kconfig vars.

So, let's just get rid of that. If needed later, this
patch can be (partially?) reversed.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Link: https://lore.kernel.org/r/ecbef801f6c32ba0850ad9e5c534a4304807df3b.1597647359.git.mchehab+huawei@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/hikey9xx/hi6421-spmi-pmic.c | 63 -----------------------------
 include/linux/mfd/hi6421-spmi-pmic.h        | 42 -------------------
 2 files changed, 105 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/staging/hikey9xx/hi6421-spmi-pmic.c b/drivers/staging/hikey9xx/hi6421-spmi-pmic.c
index 6bb0bc4b203b..809381eb6043 100644
--- a/drivers/staging/hikey9xx/hi6421-spmi-pmic.c
+++ b/drivers/staging/hikey9xx/hi6421-spmi-pmic.c
@@ -53,10 +53,6 @@
 #define HISI_PMIC_FIRST_GROUP_INT_NUM        2
 
 static struct bit_info g_pmic_vbus = {0};
-#ifndef BIT
-#define BIT(x)		(0x1U << (x))
-#endif
-
 static struct hisi_pmic *g_pmic;
 static unsigned int g_extinterrupt_flag  = 0;
 static struct of_device_id of_hisi_pmic_match_tbl[] = {
@@ -121,65 +117,6 @@ void hisi_pmic_write(struct hisi_pmic *pmic, int reg, u32 val)
 }
 EXPORT_SYMBOL(hisi_pmic_write);
 
-#ifdef CONFIG_HISI_DIEID
-u32 hisi_pmic_read_sub_pmu(u8 sid, int reg)
-{
-	u32 ret;
-	u8 read_value = 0;
-	struct spmi_device *pdev;
-
-	if(strstr(saved_command_line, "androidboot.swtype=factory"))
-	{
-		if (NULL == g_pmic) {
-			pr_err(" g_pmic  is NULL\n");
-			return -1;/*lint !e570 */
-		}
-
-		pdev = to_spmi_device(g_pmic->dev);
-		if (NULL == pdev) {
-			pr_err("%s:pdev get failed!\n", __func__);
-			return -1;/*lint !e570 */
-		}
-
-		ret = spmi_ext_register_readl(pdev->ctrl, sid, reg, (unsigned char*)&read_value, 1);/*lint !e734 !e732 */
-		if (ret) {
-			pr_err("%s:spmi_ext_register_readl failed!\n", __func__);
-			return ret;
-		}
-		return (u32)read_value;
-	}
-	return  0;
-}
-EXPORT_SYMBOL(hisi_pmic_read_sub_pmu);
-
-void hisi_pmic_write_sub_pmu(u8 sid, int reg, u32 val)
-{
-	u32 ret;
-	struct spmi_device *pdev;
-	if(strstr(saved_command_line, "androidboot.swtype=factory"))
-	{
-		if (NULL == g_pmic) {
-			pr_err(" g_pmic  is NULL\n");
-			return;
-		}
-
-		pdev = to_spmi_device(g_pmic->dev);
-		if (NULL == pdev) {
-			pr_err("%s:pdev get failed!\n", __func__);
-			return;
-		}
-
-		ret = spmi_ext_register_writel(pdev->ctrl, sid, reg, (unsigned char*)&val, 1);/*lint !e734 !e732 */
-		if (ret) {
-			pr_err("%s:spmi_ext_register_writel failed!\n", __func__);
-			return ;
-		}
-	}
-
-	return ;
-}
-EXPORT_SYMBOL(hisi_pmic_write_sub_pmu);
-#endif
 
 void hisi_pmic_rmw(struct hisi_pmic *pmic, int reg,
 		     u32 mask, u32 bits)
diff --git a/include/linux/mfd/hi6421-spmi-pmic.h b/include/linux/mfd/hi6421-spmi-pmic.h
index 939b36f617c1..5be9b4d3f207 100644
--- a/include/linux/mfd/hi6421-spmi-pmic.h
+++ b/include/linux/mfd/hi6421-spmi-pmic.h
@@ -78,7 +78,6 @@ unsigned int get_uv_mntn_status(void);
 void clear_uv_mntn_resered_reg_bit(void);
 void set_uv_mntn_resered_reg_bit(void);
 
-#if defined(CONFIG_HISI_PMIC) || defined(CONFIG_HISI_PMIC_PMU_SPMI)
 /* Register Access Helpers */
 u32 hisi_pmic_read(struct hisi_pmic *pmic, int reg);
 void hisi_pmic_write(struct hisi_pmic *pmic, int reg, u32 val);
@@ -90,11 +89,6 @@ int hisi_pmic_array_read(int addr, char *buff, unsigned int len);
 int hisi_pmic_array_write(int addr, char *buff, unsigned int len);
 extern int hisi_get_pmic_irq_byname(unsigned int pmic_irq_list);
 extern int hisi_pmic_get_vbus_status(void);
-#if defined(CONFIG_HISI_DIEID)
-u32 hisi_pmic_read_sub_pmu(u8 sid ,int reg);
-void hisi_pmic_write_sub_pmu(u8 sid ,int reg, u32 val);
-#endif
-#else
 static inline u32 hisi_pmic_read(struct hisi_pmic *pmic, int reg) { return 0; }
 static inline void hisi_pmic_write(struct hisi_pmic *pmic, int reg, u32 val) {}
 static inline void hisi_pmic_rmw(struct hisi_pmic *pmic, int reg, u32 mask, u32 bits) {}
@@ -107,38 +101,7 @@ static inline int hisi_get_pmic_irq_byname(unsigned int pmic_irq_list) { return
 static inline int hisi_pmic_get_vbus_status(void) { return 1; }
 static inline u32 hisi_pmic_read_sub_pmu(u8 sid ,int reg) { return 0; }
 static inline void hisi_pmic_write_sub_pmu(u8 sid ,int reg, u32 val) {}
-#endif
 
-#ifdef CONFIG_HISI_HI6421V500_PMU
-enum pmic_irq_list {
-	POR_D45MR = 0,
-	VBUS_CONNECT,
-	VBUS_DISCONNECT,
-	ALARMON_R,
-	HOLD_6S,
-	HOLD_1S,
-	POWERKEY_UP,
-	POWERKEY_DOWN,
-	OCP_SCP_R,
-	COUL_R,
-	VSYS_OV,
-	VSYS_UV,
-	VSYS_PWROFF_ABS,
-	VSYS_PWROFF_DEB,
-	THSD_OTMP140,
-	THSD_OTMP125,
-	HRESETN,
-	SIM0_HPD_R = 24,
-	SIM0_HPD_F,
-	SIM0_HPD_H,
-	SIM0_HPD_L,
-	SIM1_HPD_R,
-	SIM1_HPD_F,
-	SIM1_HPD_H,
-	SIM1_HPD_L,
-	PMIC_IRQ_LIST_MAX,
-};
-#else
 enum pmic_irq_list {
 	OTMP = 0,
 	VBUS_CONNECT,
@@ -156,10 +119,5 @@ enum pmic_irq_list {
 	SIM1_HPD_F,
 	PMIC_IRQ_LIST_MAX,
 };
-#endif
-
-#ifdef CONFIG_HISI_SR_DEBUG
-extern void get_ip_regulator_state(void);
-#endif
 #endif		/* __HISI_PMIC_H */
 
-- 
cgit v1.2.3


From 4b5e9b39e7dd9e6b980ad588f1f7a36fe7cda044 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Mon, 17 Aug 2020 09:10:33 +0200
Subject: staging: mfd: hi6421-spmi-pmic: get rid of the static vars

There are several static vars inside this driver.

Get rid of them.

While here, add a SPDX header file.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Link: https://lore.kernel.org/r/19c497fc2bb1d3a95863d92cac89869d5abe3f2e.1597647359.git.mchehab+huawei@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/hikey9xx/hi6421-spmi-pmic.c | 224 ++++++++++++----------------
 include/linux/mfd/hi6421-spmi-pmic.h        |  20 +--
 2 files changed, 97 insertions(+), 147 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/staging/hikey9xx/hi6421-spmi-pmic.c b/drivers/staging/hikey9xx/hi6421-spmi-pmic.c
index 8b87d48b88b5..be42fed16bd2 100644
--- a/drivers/staging/hikey9xx/hi6421-spmi-pmic.c
+++ b/drivers/staging/hikey9xx/hi6421-spmi-pmic.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Device driver for regulators in HISI PMIC IC
  *
@@ -52,10 +53,7 @@
 /*define the first group interrupt register number*/
 #define HISI_PMIC_FIRST_GROUP_INT_NUM        2
 
-static struct bit_info g_pmic_vbus = {0};
-static struct hisi_pmic *g_pmic;
-static unsigned int g_extinterrupt_flag  = 0;
-static struct of_device_id of_hisi_pmic_match_tbl[] = {
+static const struct of_device_id of_hisi_pmic_match_tbl[] = {
 	{
 		.compatible = "hisilicon-hisi-pmic-spmi",
 	},
@@ -73,18 +71,14 @@ u32 hisi_pmic_read(struct hisi_pmic *pmic, int reg)
 	u8 read_value = 0;
 	struct spmi_device *pdev;
 
-	if (!g_pmic) {
-		pr_err("%s: g_pmic is NULL\n", __func__);
-		return 0;
-	}
-
-	pdev = to_spmi_device(g_pmic->dev);
+	pdev = to_spmi_device(pmic->dev);
 	if (!pdev) {
 		pr_err("%s: pdev get failed!\n", __func__);
 		return 0;
 	}
 
-	ret = spmi_ext_register_readl(pdev, reg, (unsigned char*)&read_value, 1);/*lint !e734 !e732 */
+	ret = spmi_ext_register_readl(pdev, reg,
+				      (unsigned char *)&read_value, 1);
 	if (ret) {
 		pr_err("%s: spmi_ext_register_readl failed!\n", __func__);
 		return 0;
@@ -98,18 +92,13 @@ void hisi_pmic_write(struct hisi_pmic *pmic, int reg, u32 val)
 	u32 ret;
 	struct spmi_device *pdev;
 
-	if (!g_pmic) {
-		pr_err("%s: g_pmic is NULL\n", __func__);
-		return;
-	}
-
-	pdev = to_spmi_device(g_pmic->dev);
+	pdev = to_spmi_device(pmic->dev);
 	if (!pdev) {
 		pr_err("%s: pdev get failed!\n", __func__);
 		return;
 	}
 
-	ret = spmi_ext_register_writel(pdev, reg, (unsigned char*)&val, 1);/*lint !e734 !e732 */
+	ret = spmi_ext_register_writel(pdev, reg, (unsigned char *)&val, 1);
 	if (ret) {
 		pr_err("%s: spmi_ext_register_writel failed!\n", __func__);
 		return;
@@ -122,16 +111,11 @@ void hisi_pmic_rmw(struct hisi_pmic *pmic, int reg, u32 mask, u32 bits)
 	u32 data;
 	unsigned long flags;
 
-	if (!g_pmic) {
-		pr_err("%s: g_pmic is NULL\n", __func__);
-		return;
-	}
-
-	spin_lock_irqsave(&g_pmic->lock, flags);
+	spin_lock_irqsave(&pmic->lock, flags);
 	data = hisi_pmic_read(pmic, reg) & ~mask;
 	data |= mask & bits;
 	hisi_pmic_write(pmic, reg, data);
-	spin_unlock_irqrestore(&g_pmic->lock, flags);
+	spin_unlock_irqrestore(&pmic->lock, flags);
 }
 EXPORT_SYMBOL(hisi_pmic_rmw);
 
@@ -142,16 +126,15 @@ static irqreturn_t hisi_irq_handler(int irq, void *data)
 	int i, offset;
 
 	for (i = 0; i < pmic->irqarray; i++) {
-		pending = hisi_pmic_read(g_pmic, (i + pmic->irq_addr.start_addr));
+		pending = hisi_pmic_read(pmic, (i + pmic->irq_addr.start_addr));
 		pending &= HISI_MASK_FIELD;
-		if (pending != 0) {
-			pr_info("pending[%d]=0x%lx\n\r", i, pending);
-		}
+		if (pending != 0)
+			pr_debug("pending[%d]=0x%lx\n\r", i, pending);
 
-		hisi_pmic_write(g_pmic, (i + pmic->irq_addr.start_addr), pending);
+		hisi_pmic_write(pmic, (i + pmic->irq_addr.start_addr), pending);
 
-		/*solve powerkey order*/
-		if ((HISI_IRQ_KEY_NUM == i) && ((pending & HISI_IRQ_KEY_VALUE) == HISI_IRQ_KEY_VALUE)) {
+		/* solve powerkey order */
+		if ((i == HISI_IRQ_KEY_NUM) && ((pending & HISI_IRQ_KEY_VALUE) == HISI_IRQ_KEY_VALUE)) {
 			generic_handle_irq(pmic->irqs[HISI_IRQ_KEY_DOWN]);
 			generic_handle_irq(pmic->irqs[HISI_IRQ_KEY_UP]);
 			pending &= (~HISI_IRQ_KEY_VALUE);
@@ -159,25 +142,25 @@ static irqreturn_t hisi_irq_handler(int irq, void *data)
 
 		if (pending) {
 			for_each_set_bit(offset, &pending, HISI_BITS)
-				generic_handle_irq(pmic->irqs[offset + i * HISI_BITS]);/*lint !e679 */
+				generic_handle_irq(pmic->irqs[offset + i * HISI_BITS]);
 		}
 	}
 
 	/*Handle the second group irq if analysis the second group irq from dtsi*/
-	if (1 == g_extinterrupt_flag){
+	if (pmic->g_extinterrupt_flag == 1) {
 		for (i = 0; i < pmic->irqarray1; i++) {
-			pending = hisi_pmic_read(g_pmic, (i + pmic->irq_addr1.start_addr));
+			pending = hisi_pmic_read(pmic, (i + pmic->irq_addr1.start_addr));
 			pending &= HISI_MASK_FIELD;
-			if (pending != 0) {
-				pr_info("pending[%d]=0x%lx\n\r", i, pending);
-			}
+			if (pending != 0)
+				pr_debug("pending[%d]=0x%lx\n\r", i, pending);
+
+			hisi_pmic_write(pmic, (i + pmic->irq_addr1.start_addr), pending);
 
-			hisi_pmic_write(g_pmic, (i + pmic->irq_addr1.start_addr), pending);
+			if (!pending)
+				continue;
 
-			if (pending) {
-				for_each_set_bit(offset, &pending, HISI_BITS)
-					generic_handle_irq(pmic->irqs[offset + (i+HISI_PMIC_FIRST_GROUP_INT_NUM) * HISI_BITS]);/*lint !e679 */
-			}
+			for_each_set_bit(offset, &pending, HISI_BITS)
+				generic_handle_irq(pmic->irqs[offset + (i + HISI_PMIC_FIRST_GROUP_INT_NUM) * HISI_BITS]);
 		}
 	}
 
@@ -190,25 +173,25 @@ static void hisi_irq_mask(struct irq_data *d)
 	u32 data, offset;
 	unsigned long flags;
 
-	if (NULL == g_pmic) {
-		pr_err(" g_pmic  is NULL\n");
-		return;
-	}
-
 	offset = (irqd_to_hwirq(d) >> 3);
-	if (1==g_extinterrupt_flag){
-		if ( offset < HISI_PMIC_FIRST_GROUP_INT_NUM)
+	if (pmic->g_extinterrupt_flag == 1) {
+		if (offset < HISI_PMIC_FIRST_GROUP_INT_NUM) {
 			offset += pmic->irq_mask_addr.start_addr;
-		else/*Change addr when irq num larger than 16 because interrupt addr is nonsequence*/
-			offset = offset+(pmic->irq_mask_addr1.start_addr)-HISI_PMIC_FIRST_GROUP_INT_NUM;
-	}else{
+		} else {
+			/*
+			 * Change addr when irq num larger than 16 because
+			 * interrupt addr is nonsequence
+			 */
+			offset = offset + (pmic->irq_mask_addr1.start_addr) - HISI_PMIC_FIRST_GROUP_INT_NUM;
+		}
+	} else {
 		offset += pmic->irq_mask_addr.start_addr;
 	}
-	spin_lock_irqsave(&g_pmic->lock, flags);
-	data = hisi_pmic_read(g_pmic, offset);
+	spin_lock_irqsave(&pmic->lock, flags);
+	data = hisi_pmic_read(pmic, offset);
 	data |= (1 << (irqd_to_hwirq(d) & 0x07));
-	hisi_pmic_write(g_pmic, offset, data);
-	spin_unlock_irqrestore(&g_pmic->lock, flags);
+	hisi_pmic_write(pmic, offset, data);
+	spin_unlock_irqrestore(&pmic->lock, flags);
 }
 
 static void hisi_irq_unmask(struct irq_data *d)
@@ -217,25 +200,20 @@ static void hisi_irq_unmask(struct irq_data *d)
 	u32 data, offset;
 	unsigned long flags;
 
-	if (NULL == g_pmic) {
-		pr_err(" g_pmic  is NULL\n");
-		return;
-	}
-
 	offset = (irqd_to_hwirq(d) >> 3);
-	if (1==g_extinterrupt_flag){
-		if ( offset < HISI_PMIC_FIRST_GROUP_INT_NUM)
+	if (pmic->g_extinterrupt_flag == 1) {
+		if (offset < HISI_PMIC_FIRST_GROUP_INT_NUM)
 			offset += pmic->irq_mask_addr.start_addr;
 		else
-			offset = offset+(pmic->irq_mask_addr1.start_addr)-HISI_PMIC_FIRST_GROUP_INT_NUM;
-	}else{
+			offset = offset + (pmic->irq_mask_addr1.start_addr) - HISI_PMIC_FIRST_GROUP_INT_NUM;
+	} else {
 		offset += pmic->irq_mask_addr.start_addr;
 	}
-	spin_lock_irqsave(&g_pmic->lock, flags);
-	data = hisi_pmic_read(g_pmic, offset);
+	spin_lock_irqsave(&pmic->lock, flags);
+	data = hisi_pmic_read(pmic, offset);
 	data &= ~(1 << (irqd_to_hwirq(d) & 0x07));
-	hisi_pmic_write(g_pmic, offset, data);
-	spin_unlock_irqrestore(&g_pmic->lock, flags);
+	hisi_pmic_write(pmic, offset, data);
+	spin_unlock_irqrestore(&pmic->lock, flags);
 }
 
 static struct irq_chip hisi_pmu_irqchip = {
@@ -247,7 +225,7 @@ static struct irq_chip hisi_pmu_irqchip = {
 };
 
 static int hisi_irq_map(struct irq_domain *d, unsigned int virq,
-			  irq_hw_number_t hw)
+			irq_hw_number_t hw)
 {
 	struct hisi_pmic *pmic = d->host_data;
 
@@ -259,19 +237,18 @@ static int hisi_irq_map(struct irq_domain *d, unsigned int virq,
 	return 0;
 }
 
-static struct irq_domain_ops hisi_domain_ops = {
+static const struct irq_domain_ops hisi_domain_ops = {
 	.map	= hisi_irq_map,
 	.xlate	= irq_domain_xlate_twocell,
 };
 
-/*lint -e570 -e64*/
 static int get_pmic_device_tree_data(struct device_node *np, struct hisi_pmic *pmic)
 {
 	int ret = 0;
 
 	/*get pmic irq num*/
 	ret = of_property_read_u32_array(np, "hisilicon,hisi-pmic-irq-num",
-						&(pmic->irqnum), 1);
+					 &pmic->irqnum, 1);
 	if (ret) {
 		pr_err("no hisilicon,hisi-pmic-irq-num property set\n");
 		ret = -ENODEV;
@@ -280,7 +257,7 @@ static int get_pmic_device_tree_data(struct device_node *np, struct hisi_pmic *p
 
 	/*get pmic irq array number*/
 	ret = of_property_read_u32_array(np, "hisilicon,hisi-pmic-irq-array",
-						&(pmic->irqarray), 1);
+					 &pmic->irqarray, 1);
 	if (ret) {
 		pr_err("no hisilicon,hisi-pmic-irq-array property set\n");
 		ret = -ENODEV;
@@ -289,7 +266,7 @@ static int get_pmic_device_tree_data(struct device_node *np, struct hisi_pmic *p
 
 	/*SOC_PMIC_IRQ_MASK_0_ADDR*/
 	ret = of_property_read_u32_array(np, "hisilicon,hisi-pmic-irq-mask-addr",
-						(int *)&pmic->irq_mask_addr, 2);
+					 (int *)&pmic->irq_mask_addr, 2);
 	if (ret) {
 		pr_err("no hisilicon,hisi-pmic-irq-mask-addr property set\n");
 		ret = -ENODEV;
@@ -298,24 +275,16 @@ static int get_pmic_device_tree_data(struct device_node *np, struct hisi_pmic *p
 
 	/*SOC_PMIC_IRQ0_ADDR*/
 	ret = of_property_read_u32_array(np, "hisilicon,hisi-pmic-irq-addr",
-						(int *)&pmic->irq_addr, 2);
+					 (int *)&pmic->irq_addr, 2);
 	if (ret) {
 		pr_err("no hisilicon,hisi-pmic-irq-addr property set\n");
 		ret = -ENODEV;
 		return ret;
 	}
 
-	ret = of_property_read_u32_array(np, "hisilicon,hisi-pmic-vbus",
-						(u32 *)&g_pmic_vbus, 2);
-	if (ret) {
-		pr_err("no hisilicon,hisi-pmic-vbus property\n");
-		ret = -ENODEV;
-		return ret;
-	}
-
 	/*pmic lock*/
 	ret = of_property_read_u32_array(np, "hisilicon,hisi-pmic-lock",
-						(int *)&pmic->normal_lock, 2);
+					 (int *)&pmic->normal_lock, 2);
 	if (ret) {
 		pr_err("no hisilicon,hisi-pmic-lock property set\n");
 		ret = -ENODEV;
@@ -324,7 +293,7 @@ static int get_pmic_device_tree_data(struct device_node *np, struct hisi_pmic *p
 
 	/*pmic debug lock*/
 	ret = of_property_read_u32_array(np, "hisilicon,hisi-pmic-debug-lock",
-						(int *)&pmic->debug_lock, 2);
+					 (int *)&pmic->debug_lock, 2);
 	if (ret) {
 		pr_err("no hisilicon,hisi-pmic-debug-lock property set\n");
 		ret = -ENODEV;
@@ -332,17 +301,15 @@ static int get_pmic_device_tree_data(struct device_node *np, struct hisi_pmic *p
 	}
 
 	return ret;
-}/*lint -restore*/
-
+}
 
-/*lint -e570 -e64*/
 static int get_pmic_device_tree_data1(struct device_node *np, struct hisi_pmic *pmic)
 {
 	int ret = 0;
 
 	/*get pmic irq num*/
 	ret = of_property_read_u32_array(np, "hisilicon,hisi-pmic-irq-num1",
-						&(pmic->irqnum1), 1);
+					 &pmic->irqnum1, 1);
 	if (ret) {
 		pr_err("no hisilicon,hisi-pmic-irq-num1 property set\n");
 		ret = -ENODEV;
@@ -352,7 +319,7 @@ static int get_pmic_device_tree_data1(struct device_node *np, struct hisi_pmic *
 
 	/*get pmic irq array number*/
 	ret = of_property_read_u32_array(np, "hisilicon,hisi-pmic-irq-array1",
-						&(pmic->irqarray1), 1);
+					 &pmic->irqarray1, 1);
 	if (ret) {
 		pr_err("no hisilicon,hisi-pmic-irq-array1 property set\n");
 		ret = -ENODEV;
@@ -361,7 +328,7 @@ static int get_pmic_device_tree_data1(struct device_node *np, struct hisi_pmic *
 
 	/*SOC_PMIC_IRQ_MASK_0_ADDR*/
 	ret = of_property_read_u32_array(np, "hisilicon,hisi-pmic-irq-mask-addr1",
-						(int *)&pmic->irq_mask_addr1, 2);
+					 (int *)&pmic->irq_mask_addr1, 2);
 	if (ret) {
 		pr_err("no hisilicon,hisi-pmic-irq-mask-addr1 property set\n");
 		ret = -ENODEV;
@@ -370,43 +337,48 @@ static int get_pmic_device_tree_data1(struct device_node *np, struct hisi_pmic *
 
 	/*SOC_PMIC_IRQ0_ADDR*/
 	ret = of_property_read_u32_array(np, "hisilicon,hisi-pmic-irq-addr1",
-						(int *)&pmic->irq_addr1, 2);
+					 (int *)&pmic->irq_addr1, 2);
 	if (ret) {
 		pr_err("no hisilicon,hisi-pmic-irq-addr1 property set\n");
 		ret = -ENODEV;
 		return ret;
 	}
 
-	g_extinterrupt_flag = 1;
+	pmic->g_extinterrupt_flag = 1;
 	return ret;
-}/*lint -restore*/
+}
 
 static void hisi_pmic_irq_prc(struct hisi_pmic *pmic)
 {
 	int i;
-	for (i = 0 ; i < pmic->irq_mask_addr.array; i++) {
+
+	for (i = 0 ; i < pmic->irq_mask_addr.array; i++)
 		hisi_pmic_write(pmic, pmic->irq_mask_addr.start_addr + i, HISI_MASK_STATE);
-	}
 
 	for (i = 0 ; i < pmic->irq_addr.array; i++) {
 		unsigned int pending = hisi_pmic_read(pmic, pmic->irq_addr.start_addr + i);
-		pr_debug("PMU IRQ address value:irq[0x%x] = 0x%x\n", pmic->irq_addr.start_addr + i, pending);
+
+		pr_debug("PMU IRQ address value:irq[0x%x] = 0x%x\n",
+			 pmic->irq_addr.start_addr + i, pending);
 		hisi_pmic_write(pmic, pmic->irq_addr.start_addr + i, HISI_MASK_STATE);
 	}
-
 }
 
 static void hisi_pmic_irq1_prc(struct hisi_pmic *pmic)
 {
 	int i;
-	if(1 == g_extinterrupt_flag){
-		for (i = 0 ; i < pmic->irq_mask_addr1.array; i++) {
+	unsigned int pending1;
+
+	if (pmic->g_extinterrupt_flag == 1) {
+		for (i = 0 ; i < pmic->irq_mask_addr1.array; i++)
 			hisi_pmic_write(pmic, pmic->irq_mask_addr1.start_addr + i, HISI_MASK_STATE);
-		}
 
 		for (i = 0 ; i < pmic->irq_addr1.array; i++) {
-			unsigned int pending1 = hisi_pmic_read(pmic, pmic->irq_addr1.start_addr + i);
-			pr_debug("PMU IRQ address1 value:irq[0x%x] = 0x%x\n", pmic->irq_addr1.start_addr + i, pending1);
+			pending1 = hisi_pmic_read(pmic, pmic->irq_addr1.start_addr + i);
+
+			pr_debug("PMU IRQ address1 value:irq[0x%x] = 0x%x\n",
+				 pmic->irq_addr1.start_addr + i, pending1);
+
 			hisi_pmic_write(pmic, pmic->irq_addr1.start_addr + i, HISI_MASK_STATE);
 		}
 	}
@@ -424,36 +396,32 @@ static int hisi_pmic_probe(struct spmi_device *pdev)
 	unsigned int virq;
 
 	pmic = devm_kzalloc(dev, sizeof(*pmic), GFP_KERNEL);
-	if (!pmic) {
-		dev_err(dev, "cannot allocate hisi_pmic device info\n");
+	if (!pmic)
 		return -ENOMEM;
-	}
 
 	/*TODO: get pmic dts info*/
 	ret = get_pmic_device_tree_data(np, pmic);
 	if (ret) {
-		dev_err(&pdev->dev, "Error reading hisi pmic dts \n");
+		dev_err(&pdev->dev, "Error reading hisi pmic dts\n");
 		return ret;
 	}
 
 	/*get pmic dts the second group irq*/
 	ret = get_pmic_device_tree_data1(np, pmic);
-	if (ret) {
+	if (ret)
 		dev_err(&pdev->dev, "the platform don't support ext-interrupt.\n");
-	}
 
 	/* TODO: get and enable clk request */
 	spin_lock_init(&pmic->lock);
 
 	pmic->dev = dev;
-	g_pmic = pmic;
-	ret = of_property_read_u32_array(np, "hisilicon,pmic_fpga_flag", &fpga_flag, 1);
-	if (ret) {
+	ret = of_property_read_u32_array(np, "hisilicon,pmic_fpga_flag",
+					 &fpga_flag, 1);
+	if (ret)
 		pr_err("no hisilicon,pmic_fpga_flag property set\n");
-	}
-	if (PMIC_FPGA_FLAG == fpga_flag) {
+
+	if (fpga_flag == PMIC_FPGA_FLAG)
 		goto after_irq_register;
-	}
 
 	pmic->gpio = of_get_gpio_flags(np, 0, &flags);
 	if (pmic->gpio < 0)
@@ -477,12 +445,9 @@ static int hisi_pmic_probe(struct spmi_device *pdev)
 
 	pmic->irqnum += pmic->irqnum1;
 
-	pmic->irqs = (unsigned int *)devm_kmalloc(dev, pmic->irqnum * sizeof(int), GFP_KERNEL);
-	if (!pmic->irqs) {
-		pr_err("%s:Failed to alloc memory for pmic irq number!\n", __func__);
+	pmic->irqs = devm_kzalloc(dev, pmic->irqnum * sizeof(int), GFP_KERNEL);
+	if (!pmic->irqs)
 		goto irq_malloc;
-	}
-	memset(pmic->irqs, 0, pmic->irqnum);
 
 	pmic->domain = irq_domain_add_simple(np, pmic->irqnum, 0,
 					     &hisi_domain_ops, pmic);
@@ -504,7 +469,7 @@ static int hisi_pmic_probe(struct spmi_device *pdev)
 	}
 
 	ret = request_threaded_irq(pmic->irq, hisi_irq_handler, NULL,
-				IRQF_TRIGGER_LOW | IRQF_SHARED | IRQF_NO_SUSPEND,
+				   IRQF_TRIGGER_LOW | IRQF_SHARED | IRQF_NO_SUSPEND,
 				   "pmic", pmic);
 	if (ret < 0) {
 		dev_err(dev, "could not claim pmic %d\n", ret);
@@ -515,31 +480,28 @@ static int hisi_pmic_probe(struct spmi_device *pdev)
 after_irq_register:
 	return 0;
 
-
 request_theaded_irq:
 irq_create_mapping:
 irq_domain:
 irq_malloc:
 	gpio_free(pmic->gpio);
-	g_pmic = NULL;
 	return ret;
 }
 
 static void hisi_pmic_remove(struct spmi_device *pdev)
 {
-
 	struct hisi_pmic *pmic = dev_get_drvdata(&pdev->dev);
 
 	free_irq(pmic->irq, pmic);
 	gpio_free(pmic->gpio);
 	devm_kfree(&pdev->dev, pmic);
-
 }
+
 static int hisi_pmic_suspend(struct device *dev, pm_message_t state)
 {
 	struct hisi_pmic *pmic = dev_get_drvdata(dev);
 
-	if (NULL == pmic) {
+	if (!pmic) {
 		pr_err("%s:pmic is NULL\n", __func__);
 		return -ENOMEM;
 	}
@@ -548,13 +510,13 @@ static int hisi_pmic_suspend(struct device *dev, pm_message_t state)
 	pr_info("%s:-\n", __func__);
 
 	return 0;
-}/*lint !e715 */
+}
 
 static int hisi_pmic_resume(struct device *dev)
 {
 	struct hisi_pmic *pmic = dev_get_drvdata(dev);
 
-	if (NULL == pmic) {
+	if (!pmic) {
 		pr_err("%s:pmic is NULL\n", __func__);
 		return -ENOMEM;
 	}
@@ -588,10 +550,8 @@ static void __exit hisi_pmic_exit(void)
 	spmi_driver_unregister(&hisi_pmic_driver);
 }
 
-
 subsys_initcall_sync(hisi_pmic_init);
 module_exit(hisi_pmic_exit);
 
 MODULE_DESCRIPTION("PMIC driver");
 MODULE_LICENSE("GPL v2");
-
diff --git a/include/linux/mfd/hi6421-spmi-pmic.h b/include/linux/mfd/hi6421-spmi-pmic.h
index 5be9b4d3f207..e0a8b50f95fc 100644
--- a/include/linux/mfd/hi6421-spmi-pmic.h
+++ b/include/linux/mfd/hi6421-spmi-pmic.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Header file for device driver Hi6421 PMIC
  *
@@ -5,19 +6,6 @@
  * Copyright (C) 2011 Hisilicon.
  *
  * Guodong Xu <guodong.xu@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  */
 
 #ifndef	__HISI_PMIC_H
@@ -25,12 +13,12 @@
 
 #include <linux/irqdomain.h>
 
-#define HISI_REGS_ENA_PROTECT_TIME	(0) 	/* in microseconds */
+#define HISI_REGS_ENA_PROTECT_TIME	(0)	/* in microseconds */
 #define HISI_ECO_MODE_ENABLE		(1)
 #define HISI_ECO_MODE_DISABLE		(0)
 
 typedef int (*pmic_ocp_callback)(char *);
-extern int hisi_pmic_special_ocp_register(char *power_name, pmic_ocp_callback handler);
+int hisi_pmic_special_ocp_register(char *power_name, pmic_ocp_callback handler);
 
 struct irq_mask_info {
 	int start_addr;
@@ -71,6 +59,8 @@ struct hisi_pmic {
 	struct irq_info irq_addr1;
 	struct write_lock normal_lock;
 	struct write_lock debug_lock;
+
+	unsigned int g_extinterrupt_flag;
 };
 
 /* 0:disable; 1:enable */
-- 
cgit v1.2.3


From 4860b39f545fd96805c6400bd185de4fb383a2c7 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Mon, 17 Aug 2020 09:10:34 +0200
Subject: staging: mfd: hi6421-spmi-pmic: cleanup hi6421-spmi-pmic.h header

There are several external vars that are defined there, which
are not needed anymore.

Get rid of them.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Link: https://lore.kernel.org/r/3dbc3f3876275404153da52b84e5dcef09faf644.1597647359.git.mchehab+huawei@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/mfd/hi6421-spmi-pmic.h | 26 --------------------------
 1 file changed, 26 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mfd/hi6421-spmi-pmic.h b/include/linux/mfd/hi6421-spmi-pmic.h
index e0a8b50f95fc..1f986dd5f31c 100644
--- a/include/linux/mfd/hi6421-spmi-pmic.h
+++ b/include/linux/mfd/hi6421-spmi-pmic.h
@@ -63,34 +63,9 @@ struct hisi_pmic {
 	unsigned int g_extinterrupt_flag;
 };
 
-/* 0:disable; 1:enable */
-unsigned int get_uv_mntn_status(void);
-void clear_uv_mntn_resered_reg_bit(void);
-void set_uv_mntn_resered_reg_bit(void);
-
-/* Register Access Helpers */
 u32 hisi_pmic_read(struct hisi_pmic *pmic, int reg);
 void hisi_pmic_write(struct hisi_pmic *pmic, int reg, u32 val);
 void hisi_pmic_rmw(struct hisi_pmic *pmic, int reg, u32 mask, u32 bits);
-unsigned int hisi_pmic_reg_read(int addr);
-void hisi_pmic_reg_write(int addr, int val);
-void hisi_pmic_reg_write_lock(int addr, int val);
-int hisi_pmic_array_read(int addr, char *buff, unsigned int len);
-int hisi_pmic_array_write(int addr, char *buff, unsigned int len);
-extern int hisi_get_pmic_irq_byname(unsigned int pmic_irq_list);
-extern int hisi_pmic_get_vbus_status(void);
-static inline u32 hisi_pmic_read(struct hisi_pmic *pmic, int reg) { return 0; }
-static inline void hisi_pmic_write(struct hisi_pmic *pmic, int reg, u32 val) {}
-static inline void hisi_pmic_rmw(struct hisi_pmic *pmic, int reg, u32 mask, u32 bits) {}
-static inline unsigned int hisi_pmic_reg_read(int addr) { return 0; }
-static inline void hisi_pmic_reg_write(int addr, int val) {}
-static inline void hisi_pmic_reg_write_lock(int addr, int val) {}
-static inline int hisi_pmic_array_read(int addr, char *buff, unsigned int len) { return 0; }
-static inline int hisi_pmic_array_write(int addr, char *buff, unsigned int len) { return 0; }
-static inline int hisi_get_pmic_irq_byname(unsigned int pmic_irq_list) { return -1; }
-static inline int hisi_pmic_get_vbus_status(void) { return 1; }
-static inline u32 hisi_pmic_read_sub_pmu(u8 sid ,int reg) { return 0; }
-static inline void hisi_pmic_write_sub_pmu(u8 sid ,int reg, u32 val) {}
 
 enum pmic_irq_list {
 	OTMP = 0,
@@ -110,4 +85,3 @@ enum pmic_irq_list {
 	PMIC_IRQ_LIST_MAX,
 };
 #endif		/* __HISI_PMIC_H */
-
-- 
cgit v1.2.3


From bd07d62a47290ca3ceee58f373fa05464edc6eb5 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Mon, 17 Aug 2020 09:10:36 +0200
Subject: staging: mfd: hi6421-spmi-pmic: get rid of unused OF properties

There are several OF properties that aren't used by Hikey 970,
and some are not even used inside the driver.

So, drop them, as as this makes easier to document what's
actually used.

If latter needed, those could be re-added later.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Link: https://lore.kernel.org/r/332f96c178b81bf1e9908a1da2127f043909ae0c.1597647359.git.mchehab+huawei@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/hikey9xx/hi6421-spmi-pmic.c | 145 +---------------------------
 include/linux/mfd/hi6421-spmi-pmic.h        |  14 +--
 2 files changed, 7 insertions(+), 152 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/staging/hikey9xx/hi6421-spmi-pmic.c b/drivers/staging/hikey9xx/hi6421-spmi-pmic.c
index 939f7bd5d8ba..f523b2d844b9 100644
--- a/drivers/staging/hikey9xx/hi6421-spmi-pmic.c
+++ b/drivers/staging/hikey9xx/hi6421-spmi-pmic.c
@@ -49,7 +49,6 @@
 /*#define HISI_NR_IRQ			25*/
 #define HISI_MASK_FIELD		0xFF
 #define HISI_BITS			8
-#define PMIC_FPGA_FLAG          1
 
 /*define the first group interrupt register number*/
 #define HISI_PMIC_FIRST_GROUP_INT_NUM        2
@@ -144,24 +143,6 @@ static irqreturn_t hisi_irq_handler(int irq, void *data)
 		}
 	}
 
-	/*Handle the second group irq if analysis the second group irq from dtsi*/
-	if (pmic->g_extinterrupt_flag == 1) {
-		for (i = 0; i < pmic->irqarray1; i++) {
-			pending = hisi_pmic_read(pmic, (i + pmic->irq_addr1.start_addr));
-			pending &= HISI_MASK_FIELD;
-			if (pending != 0)
-				pr_debug("pending[%d]=0x%lx\n\r", i, pending);
-
-			hisi_pmic_write(pmic, (i + pmic->irq_addr1.start_addr), pending);
-
-			if (!pending)
-				continue;
-
-			for_each_set_bit(offset, &pending, HISI_BITS)
-				generic_handle_irq(pmic->irqs[offset + (i + HISI_PMIC_FIRST_GROUP_INT_NUM) * HISI_BITS]);
-		}
-	}
-
 	return IRQ_HANDLED;
 }
 
@@ -172,19 +153,8 @@ static void hisi_irq_mask(struct irq_data *d)
 	unsigned long flags;
 
 	offset = (irqd_to_hwirq(d) >> 3);
-	if (pmic->g_extinterrupt_flag == 1) {
-		if (offset < HISI_PMIC_FIRST_GROUP_INT_NUM) {
-			offset += pmic->irq_mask_addr.start_addr;
-		} else {
-			/*
-			 * Change addr when irq num larger than 16 because
-			 * interrupt addr is nonsequence
-			 */
-			offset = offset + (pmic->irq_mask_addr1.start_addr) - HISI_PMIC_FIRST_GROUP_INT_NUM;
-		}
-	} else {
-		offset += pmic->irq_mask_addr.start_addr;
-	}
+	offset += pmic->irq_mask_addr.start_addr;
+
 	spin_lock_irqsave(&pmic->lock, flags);
 	data = hisi_pmic_read(pmic, offset);
 	data |= (1 << (irqd_to_hwirq(d) & 0x07));
@@ -199,14 +169,8 @@ static void hisi_irq_unmask(struct irq_data *d)
 	unsigned long flags;
 
 	offset = (irqd_to_hwirq(d) >> 3);
-	if (pmic->g_extinterrupt_flag == 1) {
-		if (offset < HISI_PMIC_FIRST_GROUP_INT_NUM)
-			offset += pmic->irq_mask_addr.start_addr;
-		else
-			offset = offset + (pmic->irq_mask_addr1.start_addr) - HISI_PMIC_FIRST_GROUP_INT_NUM;
-	} else {
-		offset += pmic->irq_mask_addr.start_addr;
-	}
+	offset += pmic->irq_mask_addr.start_addr;
+
 	spin_lock_irqsave(&pmic->lock, flags);
 	data = hisi_pmic_read(pmic, offset);
 	data &= ~(1 << (irqd_to_hwirq(d) & 0x07));
@@ -280,69 +244,6 @@ static int get_pmic_device_tree_data(struct device_node *np, struct hisi_pmic *p
 		return ret;
 	}
 
-	/*pmic lock*/
-	ret = of_property_read_u32_array(np, "hisilicon,hisi-pmic-lock",
-					 (int *)&pmic->normal_lock, 2);
-	if (ret) {
-		pr_err("no hisilicon,hisi-pmic-lock property set\n");
-		ret = -ENODEV;
-		return ret;
-	}
-
-	/*pmic debug lock*/
-	ret = of_property_read_u32_array(np, "hisilicon,hisi-pmic-debug-lock",
-					 (int *)&pmic->debug_lock, 2);
-	if (ret) {
-		pr_err("no hisilicon,hisi-pmic-debug-lock property set\n");
-		ret = -ENODEV;
-		return ret;
-	}
-
-	return ret;
-}
-
-static int get_pmic_device_tree_data1(struct device_node *np, struct hisi_pmic *pmic)
-{
-	int ret = 0;
-
-	/*get pmic irq num*/
-	ret = of_property_read_u32_array(np, "hisilicon,hisi-pmic-irq-num1",
-					 &pmic->irqnum1, 1);
-	if (ret) {
-		pr_err("no hisilicon,hisi-pmic-irq-num1 property set\n");
-		ret = -ENODEV;
-		pmic->irqnum1 = 0;
-		return ret;
-	}
-
-	/*get pmic irq array number*/
-	ret = of_property_read_u32_array(np, "hisilicon,hisi-pmic-irq-array1",
-					 &pmic->irqarray1, 1);
-	if (ret) {
-		pr_err("no hisilicon,hisi-pmic-irq-array1 property set\n");
-		ret = -ENODEV;
-		return ret;
-	}
-
-	/*SOC_PMIC_IRQ_MASK_0_ADDR*/
-	ret = of_property_read_u32_array(np, "hisilicon,hisi-pmic-irq-mask-addr1",
-					 (int *)&pmic->irq_mask_addr1, 2);
-	if (ret) {
-		pr_err("no hisilicon,hisi-pmic-irq-mask-addr1 property set\n");
-		ret = -ENODEV;
-		return ret;
-	}
-
-	/*SOC_PMIC_IRQ0_ADDR*/
-	ret = of_property_read_u32_array(np, "hisilicon,hisi-pmic-irq-addr1",
-					 (int *)&pmic->irq_addr1, 2);
-	if (ret) {
-		pr_err("no hisilicon,hisi-pmic-irq-addr1 property set\n");
-		ret = -ENODEV;
-		return ret;
-	}
-
-	pmic->g_extinterrupt_flag = 1;
 	return ret;
 }
 
@@ -362,26 +263,6 @@ static void hisi_pmic_irq_prc(struct hisi_pmic *pmic)
 	}
 }
 
-static void hisi_pmic_irq1_prc(struct hisi_pmic *pmic)
-{
-	int i;
-	unsigned int pending1;
-
-	if (pmic->g_extinterrupt_flag == 1) {
-		for (i = 0 ; i < pmic->irq_mask_addr1.array; i++)
-			hisi_pmic_write(pmic, pmic->irq_mask_addr1.start_addr + i, HISI_MASK_STATE);
-
-		for (i = 0 ; i < pmic->irq_addr1.array; i++) {
-			pending1 = hisi_pmic_read(pmic, pmic->irq_addr1.start_addr + i);
-
-			pr_debug("PMU IRQ address1 value:irq[0x%x] = 0x%x\n",
-				 pmic->irq_addr1.start_addr + i, pending1);
-
-			hisi_pmic_write(pmic, pmic->irq_addr1.start_addr + i, HISI_MASK_STATE);
-		}
-	}
-}
-
 static int hisi_pmic_probe(struct spmi_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -390,7 +271,6 @@ static int hisi_pmic_probe(struct spmi_device *pdev)
 	enum of_gpio_flags flags;
 	int ret = 0;
 	int i;
-	unsigned int fpga_flag = 0;
 	unsigned int virq;
 
 	pmic = devm_kzalloc(dev, sizeof(*pmic), GFP_KERNEL);
@@ -404,22 +284,10 @@ static int hisi_pmic_probe(struct spmi_device *pdev)
 		return ret;
 	}
 
-	/*get pmic dts the second group irq*/
-	ret = get_pmic_device_tree_data1(np, pmic);
-	if (ret)
-		dev_err(&pdev->dev, "the platform don't support ext-interrupt.\n");
-
 	/* TODO: get and enable clk request */
 	spin_lock_init(&pmic->lock);
 
 	pmic->dev = dev;
-	ret = of_property_read_u32_array(np, "hisilicon,pmic_fpga_flag",
-					 &fpga_flag, 1);
-	if (ret)
-		pr_err("no hisilicon,pmic_fpga_flag property set\n");
-
-	if (fpga_flag == PMIC_FPGA_FLAG)
-		goto after_irq_register;
 
 	pmic->gpio = of_get_gpio_flags(np, 0, &flags);
 	if (pmic->gpio < 0)
@@ -438,10 +306,6 @@ static int hisi_pmic_probe(struct spmi_device *pdev)
 
 	/* mask && clear IRQ status */
 	hisi_pmic_irq_prc(pmic);
-	/*clear && mask the new adding irq*/
-	hisi_pmic_irq1_prc(pmic);
-
-	pmic->irqnum += pmic->irqnum1;
 
 	pmic->irqs = devm_kzalloc(dev, pmic->irqnum * sizeof(int), GFP_KERNEL);
 	if (!pmic->irqs)
@@ -491,7 +355,6 @@ static int hisi_pmic_probe(struct spmi_device *pdev)
 		return ret;
 	}
 
-after_irq_register:
 	return 0;
 
 request_theaded_irq:
diff --git a/include/linux/mfd/hi6421-spmi-pmic.h b/include/linux/mfd/hi6421-spmi-pmic.h
index 1f986dd5f31c..41b61de48259 100644
--- a/include/linux/mfd/hi6421-spmi-pmic.h
+++ b/include/linux/mfd/hi6421-spmi-pmic.h
@@ -48,19 +48,11 @@ struct hisi_pmic {
 	struct irq_domain	*domain;
 	int			irq;
 	int			gpio;
-	unsigned int	*irqs;
+	unsigned int		*irqs;
 	int			irqnum;
 	int			irqarray;
-	struct irq_mask_info irq_mask_addr;
-	struct irq_info irq_addr;
-	int			irqnum1;
-	int			irqarray1;
-	struct irq_mask_info irq_mask_addr1;
-	struct irq_info irq_addr1;
-	struct write_lock normal_lock;
-	struct write_lock debug_lock;
-
-	unsigned int g_extinterrupt_flag;
+	struct irq_mask_info 	irq_mask_addr;
+	struct irq_info		irq_addr;
 };
 
 u32 hisi_pmic_read(struct hisi_pmic *pmic, int reg);
-- 
cgit v1.2.3


From 1eb2784a90925d48500f6baac1fa1870085c4121 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Mon, 17 Aug 2020 09:10:38 +0200
Subject: staging: mfd: hi6421-spmi-pmic: change namespace on its functions

Rename the functions used internally inside the driver in
order for them to follow the driver's name.

While here, get rid of some unused definitions at the
header file.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Link: https://lore.kernel.org/r/bfa8bf33f71612b1511d73269ca242d0d4e70940.1597647359.git.mchehab+huawei@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/hikey9xx/hi6421-spmi-pmic.c | 97 +++++++++++++++--------------
 include/linux/mfd/hi6421-spmi-pmic.h        | 51 ++++++---------
 2 files changed, 70 insertions(+), 78 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/staging/hikey9xx/hi6421-spmi-pmic.c b/drivers/staging/hikey9xx/hi6421-spmi-pmic.c
index aed2d3ec2227..09cedfa1e4bb 100644
--- a/drivers/staging/hikey9xx/hi6421-spmi-pmic.c
+++ b/drivers/staging/hikey9xx/hi6421-spmi-pmic.c
@@ -62,7 +62,7 @@ static const struct mfd_cell hi6421v600_devs[] = {
  * Hisilicon SoC use hardware to map PMIC register into SoC mapping.
  * At here, we are accessing SoC register with 32-bit.
  */
-u32 hisi_pmic_read(struct hisi_pmic *pmic, int reg)
+u32 hi6421_spmi_pmic_read(struct hi6421_spmi_pmic *pmic, int reg)
 {
 	u32 ret;
 	u8 read_value = 0;
@@ -82,9 +82,9 @@ u32 hisi_pmic_read(struct hisi_pmic *pmic, int reg)
 	}
 	return (u32)read_value;
 }
-EXPORT_SYMBOL(hisi_pmic_read);
+EXPORT_SYMBOL(hi6421_spmi_pmic_read);
 
-void hisi_pmic_write(struct hisi_pmic *pmic, int reg, u32 val)
+void hi6421_spmi_pmic_write(struct hi6421_spmi_pmic *pmic, int reg, u32 val)
 {
 	u32 ret;
 	struct spmi_device *pdev;
@@ -101,34 +101,36 @@ void hisi_pmic_write(struct hisi_pmic *pmic, int reg, u32 val)
 		return;
 	}
 }
-EXPORT_SYMBOL(hisi_pmic_write);
+EXPORT_SYMBOL(hi6421_spmi_pmic_write);
 
-void hisi_pmic_rmw(struct hisi_pmic *pmic, int reg, u32 mask, u32 bits)
+void hi6421_spmi_pmic_rmw(struct hi6421_spmi_pmic *pmic, int reg,
+			  u32 mask, u32 bits)
 {
 	u32 data;
 	unsigned long flags;
 
 	spin_lock_irqsave(&pmic->lock, flags);
-	data = hisi_pmic_read(pmic, reg) & ~mask;
+	data = hi6421_spmi_pmic_read(pmic, reg) & ~mask;
 	data |= mask & bits;
-	hisi_pmic_write(pmic, reg, data);
+	hi6421_spmi_pmic_write(pmic, reg, data);
 	spin_unlock_irqrestore(&pmic->lock, flags);
 }
-EXPORT_SYMBOL(hisi_pmic_rmw);
+EXPORT_SYMBOL(hi6421_spmi_pmic_rmw);
 
-static irqreturn_t hisi_irq_handler(int irq, void *data)
+static irqreturn_t hi6421_spmi_irq_handler(int irq, void *data)
 {
-	struct hisi_pmic *pmic = (struct hisi_pmic *)data;
+	struct hi6421_spmi_pmic *pmic = (struct hi6421_spmi_pmic *)data;
 	unsigned long pending;
 	int i, offset;
 
 	for (i = 0; i < pmic->irqarray; i++) {
-		pending = hisi_pmic_read(pmic, (i + pmic->irq_addr.start_addr));
+		pending = hi6421_spmi_pmic_read(pmic, (i + pmic->irq_addr.start_addr));
 		pending &= HISI_MASK_FIELD;
 		if (pending != 0)
 			pr_debug("pending[%d]=0x%lx\n\r", i, pending);
 
-		hisi_pmic_write(pmic, (i + pmic->irq_addr.start_addr), pending);
+		hi6421_spmi_pmic_write(pmic, (i + pmic->irq_addr.start_addr),
+				       pending);
 
 		/* solve powerkey order */
 		if ((i == HISI_IRQ_KEY_NUM) && ((pending & HISI_IRQ_KEY_VALUE) == HISI_IRQ_KEY_VALUE)) {
@@ -146,9 +148,9 @@ static irqreturn_t hisi_irq_handler(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static void hisi_irq_mask(struct irq_data *d)
+static void hi6421_spmi_irq_mask(struct irq_data *d)
 {
-	struct hisi_pmic *pmic = irq_data_get_irq_chip_data(d);
+	struct hi6421_spmi_pmic *pmic = irq_data_get_irq_chip_data(d);
 	u32 data, offset;
 	unsigned long flags;
 
@@ -156,15 +158,15 @@ static void hisi_irq_mask(struct irq_data *d)
 	offset += pmic->irq_mask_addr.start_addr;
 
 	spin_lock_irqsave(&pmic->lock, flags);
-	data = hisi_pmic_read(pmic, offset);
+	data = hi6421_spmi_pmic_read(pmic, offset);
 	data |= (1 << (irqd_to_hwirq(d) & 0x07));
-	hisi_pmic_write(pmic, offset, data);
+	hi6421_spmi_pmic_write(pmic, offset, data);
 	spin_unlock_irqrestore(&pmic->lock, flags);
 }
 
-static void hisi_irq_unmask(struct irq_data *d)
+static void hi6421_spmi_irq_unmask(struct irq_data *d)
 {
-	struct hisi_pmic *pmic = irq_data_get_irq_chip_data(d);
+	struct hi6421_spmi_pmic *pmic = irq_data_get_irq_chip_data(d);
 	u32 data, offset;
 	unsigned long flags;
 
@@ -172,26 +174,26 @@ static void hisi_irq_unmask(struct irq_data *d)
 	offset += pmic->irq_mask_addr.start_addr;
 
 	spin_lock_irqsave(&pmic->lock, flags);
-	data = hisi_pmic_read(pmic, offset);
+	data = hi6421_spmi_pmic_read(pmic, offset);
 	data &= ~(1 << (irqd_to_hwirq(d) & 0x07));
-	hisi_pmic_write(pmic, offset, data);
+	hi6421_spmi_pmic_write(pmic, offset, data);
 	spin_unlock_irqrestore(&pmic->lock, flags);
 }
 
-static struct irq_chip hisi_pmu_irqchip = {
+static struct irq_chip hi6421_spmi_pmu_irqchip = {
 	.name		= "hisi-irq",
-	.irq_mask	= hisi_irq_mask,
-	.irq_unmask	= hisi_irq_unmask,
-	.irq_disable	= hisi_irq_mask,
-	.irq_enable	= hisi_irq_unmask,
+	.irq_mask	= hi6421_spmi_irq_mask,
+	.irq_unmask	= hi6421_spmi_irq_unmask,
+	.irq_disable	= hi6421_spmi_irq_mask,
+	.irq_enable	= hi6421_spmi_irq_unmask,
 };
 
-static int hisi_irq_map(struct irq_domain *d, unsigned int virq,
+static int hi6421_spmi_irq_map(struct irq_domain *d, unsigned int virq,
 			irq_hw_number_t hw)
 {
-	struct hisi_pmic *pmic = d->host_data;
+	struct hi6421_spmi_pmic *pmic = d->host_data;
 
-	irq_set_chip_and_handler_name(virq, &hisi_pmu_irqchip,
+	irq_set_chip_and_handler_name(virq, &hi6421_spmi_pmu_irqchip,
 				      handle_simple_irq, "hisi");
 	irq_set_chip_data(virq, pmic);
 	irq_set_irq_type(virq, IRQ_TYPE_NONE);
@@ -199,12 +201,13 @@ static int hisi_irq_map(struct irq_domain *d, unsigned int virq,
 	return 0;
 }
 
-static const struct irq_domain_ops hisi_domain_ops = {
-	.map	= hisi_irq_map,
+static const struct irq_domain_ops hi6421_spmi_domain_ops = {
+	.map	= hi6421_spmi_irq_map,
 	.xlate	= irq_domain_xlate_twocell,
 };
 
-static int get_pmic_device_tree_data(struct device_node *np, struct hisi_pmic *pmic)
+static int get_pmic_device_tree_data(struct device_node *np,
+				     struct hi6421_spmi_pmic *pmic)
 {
 	int ret = 0;
 
@@ -247,27 +250,29 @@ static int get_pmic_device_tree_data(struct device_node *np, struct hisi_pmic *p
 	return ret;
 }
 
-static void hisi_pmic_irq_prc(struct hisi_pmic *pmic)
+static void hi6421_spmi_pmic_irq_prc(struct hi6421_spmi_pmic *pmic)
 {
 	int i;
 
 	for (i = 0 ; i < pmic->irq_mask_addr.array; i++)
-		hisi_pmic_write(pmic, pmic->irq_mask_addr.start_addr + i, HISI_MASK_STATE);
+		hi6421_spmi_pmic_write(pmic, pmic->irq_mask_addr.start_addr + i,
+				       HISI_MASK_STATE);
 
 	for (i = 0 ; i < pmic->irq_addr.array; i++) {
-		unsigned int pending = hisi_pmic_read(pmic, pmic->irq_addr.start_addr + i);
+		unsigned int pending = hi6421_spmi_pmic_read(pmic, pmic->irq_addr.start_addr + i);
 
 		pr_debug("PMU IRQ address value:irq[0x%x] = 0x%x\n",
 			 pmic->irq_addr.start_addr + i, pending);
-		hisi_pmic_write(pmic, pmic->irq_addr.start_addr + i, HISI_MASK_STATE);
+		hi6421_spmi_pmic_write(pmic, pmic->irq_addr.start_addr + i,
+				       HISI_MASK_STATE);
 	}
 }
 
-static int hisi_pmic_probe(struct spmi_device *pdev)
+static int hi6421_spmi_pmic_probe(struct spmi_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct device_node *np = dev->of_node;
-	struct hisi_pmic *pmic = NULL;
+	struct hi6421_spmi_pmic *pmic = NULL;
 	enum of_gpio_flags flags;
 	int ret = 0;
 	int i;
@@ -305,14 +310,14 @@ static int hisi_pmic_probe(struct spmi_device *pdev)
 	pmic->irq = gpio_to_irq(pmic->gpio);
 
 	/* mask && clear IRQ status */
-	hisi_pmic_irq_prc(pmic);
+	hi6421_spmi_pmic_irq_prc(pmic);
 
 	pmic->irqs = devm_kzalloc(dev, pmic->irqnum * sizeof(int), GFP_KERNEL);
 	if (!pmic->irqs)
 		goto irq_malloc;
 
 	pmic->domain = irq_domain_add_simple(np, pmic->irqnum, 0,
-					     &hisi_domain_ops, pmic);
+					     &hi6421_spmi_domain_ops, pmic);
 	if (!pmic->domain) {
 		dev_err(dev, "failed irq domain add simple!\n");
 		ret = -ENODEV;
@@ -330,7 +335,7 @@ static int hisi_pmic_probe(struct spmi_device *pdev)
 		pr_info("[%s]. pmic->irqs[%d] = %d\n", __func__, i, pmic->irqs[i]);
 	}
 
-	ret = request_threaded_irq(pmic->irq, hisi_irq_handler, NULL,
+	ret = request_threaded_irq(pmic->irq, hi6421_spmi_irq_handler, NULL,
 				   IRQF_TRIGGER_LOW | IRQF_SHARED | IRQF_NO_SUSPEND,
 				   "pmic", pmic);
 	if (ret < 0) {
@@ -365,9 +370,9 @@ irq_malloc:
 	return ret;
 }
 
-static void hisi_pmic_remove(struct spmi_device *pdev)
+static void hi6421_spmi_pmic_remove(struct spmi_device *pdev)
 {
-	struct hisi_pmic *pmic = dev_get_drvdata(&pdev->dev);
+	struct hi6421_spmi_pmic *pmic = dev_get_drvdata(&pdev->dev);
 
 	free_irq(pmic->irq, pmic);
 	gpio_free(pmic->gpio);
@@ -380,15 +385,15 @@ static const struct of_device_id pmic_spmi_id_table[] = {
 };
 MODULE_DEVICE_TABLE(of, pmic_spmi_id_table);
 
-static struct spmi_driver hisi_pmic_driver = {
+static struct spmi_driver hi6421_spmi_pmic_driver = {
 	.driver = {
 		.name	= "hi6421-spmi-pmic",
 		.of_match_table = pmic_spmi_id_table,
 	},
-	.probe	= hisi_pmic_probe,
-	.remove	= hisi_pmic_remove,
+	.probe	= hi6421_spmi_pmic_probe,
+	.remove	= hi6421_spmi_pmic_remove,
 };
-module_spmi_driver(hisi_pmic_driver);
+module_spmi_driver(hi6421_spmi_pmic_driver);
 
 MODULE_DESCRIPTION("HiSilicon Hi6421v600 SPMI PMIC driver");
 MODULE_LICENSE("GPL v2");
diff --git a/include/linux/mfd/hi6421-spmi-pmic.h b/include/linux/mfd/hi6421-spmi-pmic.h
index 41b61de48259..d12ad7484018 100644
--- a/include/linux/mfd/hi6421-spmi-pmic.h
+++ b/include/linux/mfd/hi6421-spmi-pmic.h
@@ -17,49 +17,36 @@
 #define HISI_ECO_MODE_ENABLE		(1)
 #define HISI_ECO_MODE_DISABLE		(0)
 
-typedef int (*pmic_ocp_callback)(char *);
-int hisi_pmic_special_ocp_register(char *power_name, pmic_ocp_callback handler);
-
-struct irq_mask_info {
+struct hi6421_spmi_irq_mask_info {
 	int start_addr;
 	int array;
 };
 
-struct irq_info {
+struct hi6421_spmi_irq_info {
 	int start_addr;
 	int array;
 };
 
-struct bit_info {
-	int addr;
-	int bit;
-};
-
-struct write_lock {
-	int addr;
-	int val;
-};
-
-struct hisi_pmic {
-	struct resource		*res;
-	struct device		*dev;
-	void __iomem		*regs;
-	spinlock_t		lock;
-	struct irq_domain	*domain;
-	int			irq;
-	int			gpio;
-	unsigned int		*irqs;
-	int			irqnum;
-	int			irqarray;
-	struct irq_mask_info 	irq_mask_addr;
-	struct irq_info		irq_addr;
+struct hi6421_spmi_pmic {
+	struct resource				*res;
+	struct device				*dev;
+	void __iomem				*regs;
+	spinlock_t				lock;
+	struct irq_domain			*domain;
+	int					irq;
+	int					gpio;
+	unsigned int				*irqs;
+	int					irqnum;
+	int					irqarray;
+	struct hi6421_spmi_irq_mask_info 	irq_mask_addr;
+	struct hi6421_spmi_irq_info		irq_addr;
 };
 
-u32 hisi_pmic_read(struct hisi_pmic *pmic, int reg);
-void hisi_pmic_write(struct hisi_pmic *pmic, int reg, u32 val);
-void hisi_pmic_rmw(struct hisi_pmic *pmic, int reg, u32 mask, u32 bits);
+u32 hi6421_spmi_pmic_read(struct hi6421_spmi_pmic *pmic, int reg);
+void hi6421_spmi_pmic_write(struct hi6421_spmi_pmic *pmic, int reg, u32 val);
+void hi6421_spmi_pmic_rmw(struct hi6421_spmi_pmic *pmic, int reg, u32 mask, u32 bits);
 
-enum pmic_irq_list {
+enum hi6421_spmi_pmic_irq_list {
 	OTMP = 0,
 	VBUS_CONNECT,
 	VBUS_DISCONNECT,
-- 
cgit v1.2.3


From 4d70881afdeb261ee318447ed0232b96946ecabc Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Mon, 17 Aug 2020 09:10:39 +0200
Subject: staging: mfd: hi6421-spmi-pmic: fix some coding style issues

Checkpatch complains about some minor issues inside this
driver that were not addressed by the previous patch.

Address them.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Link: https://lore.kernel.org/r/84b53d20632c84cc60b8dadfe937f3c54b355cef.1597647359.git.mchehab+huawei@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/hikey9xx/hi6421-spmi-pmic.c | 4 ++--
 include/linux/mfd/hi6421-spmi-pmic.h        | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/staging/hikey9xx/hi6421-spmi-pmic.c b/drivers/staging/hikey9xx/hi6421-spmi-pmic.c
index 09cedfa1e4bb..d8b84d64041e 100644
--- a/drivers/staging/hikey9xx/hi6421-spmi-pmic.c
+++ b/drivers/staging/hikey9xx/hi6421-spmi-pmic.c
@@ -189,7 +189,7 @@ static struct irq_chip hi6421_spmi_pmu_irqchip = {
 };
 
 static int hi6421_spmi_irq_map(struct irq_domain *d, unsigned int virq,
-			irq_hw_number_t hw)
+			       irq_hw_number_t hw)
 {
 	struct hi6421_spmi_pmic *pmic = d->host_data;
 
@@ -350,7 +350,7 @@ static int hi6421_spmi_pmic_probe(struct spmi_device *pdev)
 	 * The logic below will rely that the pmic is already stored at
 	 * drvdata.
 	 */
-	dev_dbg(&pdev->dev, "SPMI-PMIC: adding childs for %pOF\n",
+	dev_dbg(&pdev->dev, "SPMI-PMIC: adding children for %pOF\n",
 		pdev->dev.of_node);
 	ret = devm_mfd_add_devices(&pdev->dev, PLATFORM_DEVID_NONE,
 				   hi6421v600_devs, ARRAY_SIZE(hi6421v600_devs),
diff --git a/include/linux/mfd/hi6421-spmi-pmic.h b/include/linux/mfd/hi6421-spmi-pmic.h
index d12ad7484018..403fd8bb45fa 100644
--- a/include/linux/mfd/hi6421-spmi-pmic.h
+++ b/include/linux/mfd/hi6421-spmi-pmic.h
@@ -38,7 +38,7 @@ struct hi6421_spmi_pmic {
 	unsigned int				*irqs;
 	int					irqnum;
 	int					irqarray;
-	struct hi6421_spmi_irq_mask_info 	irq_mask_addr;
+	struct hi6421_spmi_irq_mask_info	irq_mask_addr;
 	struct hi6421_spmi_irq_info		irq_addr;
 };
 
-- 
cgit v1.2.3


From 6b946699252c68b0c792896eded217269c9aa286 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Mon, 17 Aug 2020 09:10:41 +0200
Subject: staging: mfd: hi6421-spmi-pmic: cleanup the code

There are several small cleanups that can be done in order to
make the code more prepared to be upstreamed.

Suggested-by: Jonathan Cameron <Jonathan.Cameron@Huawei.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Link: https://lore.kernel.org/r/823792ba2f69e613629ab52a33e5728d54e2288b.1597647359.git.mchehab+huawei@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/hikey9xx/hi6421-spmi-pmic.c | 151 ++++++++++++----------------
 include/linux/mfd/hi6421-spmi-pmic.h        |  12 ++-
 2 files changed, 74 insertions(+), 89 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/staging/hikey9xx/hi6421-spmi-pmic.c b/drivers/staging/hikey9xx/hi6421-spmi-pmic.c
index d8b84d64041e..9d73458ca65a 100644
--- a/drivers/staging/hikey9xx/hi6421-spmi-pmic.c
+++ b/drivers/staging/hikey9xx/hi6421-spmi-pmic.c
@@ -17,26 +17,23 @@
  *
  */
 
-#include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/device.h>
-#include <linux/module.h>
 #include <linux/err.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
+#include <linux/irq.h>
 #include <linux/mfd/core.h>
-#include <linux/platform_device.h>
-#include <linux/of.h>
+#include <linux/mfd/hi6421-spmi-pmic.h>
+#include <linux/module.h>
 #include <linux/of_address.h>
 #include <linux/of_device.h>
 #include <linux/of_gpio.h>
+#include <linux/of.h>
 #include <linux/of_irq.h>
-#include <linux/mfd/hi6421-spmi-pmic.h>
-#include <linux/irq.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
 #include <linux/spmi.h>
-#ifndef NO_IRQ
-#define NO_IRQ       0
-#endif
 
 /* 8-bit register offset in PMIC */
 #define HISI_MASK_STATE			0xff
@@ -46,12 +43,11 @@
 #define HISI_IRQ_KEY_DOWN		7
 #define HISI_IRQ_KEY_UP			6
 
-/*#define HISI_NR_IRQ			25*/
-#define HISI_MASK_FIELD		0xFF
+#define HISI_MASK_FIELD			0xFF
 #define HISI_BITS			8
 
 /*define the first group interrupt register number*/
-#define HISI_PMIC_FIRST_GROUP_INT_NUM        2
+#define HISI_PMIC_FIRST_GROUP_INT_NUM	2
 
 static const struct mfd_cell hi6421v600_devs[] = {
 	{ .name = "hi6421v600-regulator", },
@@ -62,58 +58,60 @@ static const struct mfd_cell hi6421v600_devs[] = {
  * Hisilicon SoC use hardware to map PMIC register into SoC mapping.
  * At here, we are accessing SoC register with 32-bit.
  */
-u32 hi6421_spmi_pmic_read(struct hi6421_spmi_pmic *pmic, int reg)
+int hi6421_spmi_pmic_read(struct hi6421_spmi_pmic *pmic, int reg)
 {
-	u32 ret;
-	u8 read_value = 0;
 	struct spmi_device *pdev;
+	u8 read_value = 0;
+	u32 ret;
 
 	pdev = to_spmi_device(pmic->dev);
 	if (!pdev) {
 		pr_err("%s: pdev get failed!\n", __func__);
-		return 0;
+		return -ENODEV;
 	}
 
-	ret = spmi_ext_register_readl(pdev, reg,
-				      (unsigned char *)&read_value, 1);
+	ret = spmi_ext_register_readl(pdev, reg, &read_value, 1);
 	if (ret) {
 		pr_err("%s: spmi_ext_register_readl failed!\n", __func__);
-		return 0;
+		return ret;
 	}
-	return (u32)read_value;
+	return read_value;
 }
 EXPORT_SYMBOL(hi6421_spmi_pmic_read);
 
-void hi6421_spmi_pmic_write(struct hi6421_spmi_pmic *pmic, int reg, u32 val)
+int hi6421_spmi_pmic_write(struct hi6421_spmi_pmic *pmic, int reg, u32 val)
 {
-	u32 ret;
 	struct spmi_device *pdev;
+	u32 ret;
 
 	pdev = to_spmi_device(pmic->dev);
 	if (!pdev) {
 		pr_err("%s: pdev get failed!\n", __func__);
-		return;
+		return -ENODEV;
 	}
 
 	ret = spmi_ext_register_writel(pdev, reg, (unsigned char *)&val, 1);
-	if (ret) {
+	if (ret)
 		pr_err("%s: spmi_ext_register_writel failed!\n", __func__);
-		return;
-	}
+
+	return ret;
 }
 EXPORT_SYMBOL(hi6421_spmi_pmic_write);
 
-void hi6421_spmi_pmic_rmw(struct hi6421_spmi_pmic *pmic, int reg,
-			  u32 mask, u32 bits)
+int hi6421_spmi_pmic_rmw(struct hi6421_spmi_pmic *pmic, int reg,
+			 u32 mask, u32 bits)
 {
-	u32 data;
 	unsigned long flags;
+	u32 data;
+	int ret;
 
 	spin_lock_irqsave(&pmic->lock, flags);
 	data = hi6421_spmi_pmic_read(pmic, reg) & ~mask;
 	data |= mask & bits;
-	hi6421_spmi_pmic_write(pmic, reg, data);
+	ret = hi6421_spmi_pmic_write(pmic, reg, data);
 	spin_unlock_irqrestore(&pmic->lock, flags);
+
+	return ret;
 }
 EXPORT_SYMBOL(hi6421_spmi_pmic_rmw);
 
@@ -124,16 +122,16 @@ static irqreturn_t hi6421_spmi_irq_handler(int irq, void *data)
 	int i, offset;
 
 	for (i = 0; i < pmic->irqarray; i++) {
-		pending = hi6421_spmi_pmic_read(pmic, (i + pmic->irq_addr.start_addr));
+		pending = hi6421_spmi_pmic_read(pmic, (i + pmic->irq_addr));
 		pending &= HISI_MASK_FIELD;
 		if (pending != 0)
 			pr_debug("pending[%d]=0x%lx\n\r", i, pending);
 
-		hi6421_spmi_pmic_write(pmic, (i + pmic->irq_addr.start_addr),
-				       pending);
+		hi6421_spmi_pmic_write(pmic, (i + pmic->irq_addr), pending);
 
 		/* solve powerkey order */
-		if ((i == HISI_IRQ_KEY_NUM) && ((pending & HISI_IRQ_KEY_VALUE) == HISI_IRQ_KEY_VALUE)) {
+		if ((i == HISI_IRQ_KEY_NUM) &&
+		    ((pending & HISI_IRQ_KEY_VALUE) == HISI_IRQ_KEY_VALUE)) {
 			generic_handle_irq(pmic->irqs[HISI_IRQ_KEY_DOWN]);
 			generic_handle_irq(pmic->irqs[HISI_IRQ_KEY_UP]);
 			pending &= (~HISI_IRQ_KEY_VALUE);
@@ -155,7 +153,7 @@ static void hi6421_spmi_irq_mask(struct irq_data *d)
 	unsigned long flags;
 
 	offset = (irqd_to_hwirq(d) >> 3);
-	offset += pmic->irq_mask_addr.start_addr;
+	offset += pmic->irq_mask_addr;
 
 	spin_lock_irqsave(&pmic->lock, flags);
 	data = hi6421_spmi_pmic_read(pmic, offset);
@@ -171,7 +169,7 @@ static void hi6421_spmi_irq_unmask(struct irq_data *d)
 	unsigned long flags;
 
 	offset = (irqd_to_hwirq(d) >> 3);
-	offset += pmic->irq_mask_addr.start_addr;
+	offset += pmic->irq_mask_addr;
 
 	spin_lock_irqsave(&pmic->lock, flags);
 	data = hi6421_spmi_pmic_read(pmic, offset);
@@ -211,36 +209,32 @@ static int get_pmic_device_tree_data(struct device_node *np,
 {
 	int ret = 0;
 
-	/*get pmic irq num*/
-	ret = of_property_read_u32_array(np, "irq-num",
-					 &pmic->irqnum, 1);
+	/* IRQ number */
+	ret = of_property_read_u32(np, "irq-num", &pmic->irqnum);
 	if (ret) {
 		pr_err("no irq-num property set\n");
 		ret = -ENODEV;
 		return ret;
 	}
 
-	/*get pmic irq array number*/
-	ret = of_property_read_u32_array(np, "irq-array",
-					 &pmic->irqarray, 1);
+	/* Size of IRQ array */
+	ret = of_property_read_u32(np, "irq-array", &pmic->irqarray);
 	if (ret) {
 		pr_err("no irq-array property set\n");
 		ret = -ENODEV;
 		return ret;
 	}
 
-	/*SOC_PMIC_IRQ_MASK_0_ADDR*/
-	ret = of_property_read_u32_array(np, "irq-mask-addr",
-					 (int *)&pmic->irq_mask_addr, 2);
+	/* SOC_PMIC_IRQ_MASK_0_ADDR */
+	ret = of_property_read_u32(np, "irq-mask-addr", &pmic->irq_mask_addr);
 	if (ret) {
 		pr_err("no irq-mask-addr property set\n");
 		ret = -ENODEV;
 		return ret;
 	}
 
-	/*SOC_PMIC_IRQ0_ADDR*/
-	ret = of_property_read_u32_array(np, "irq-addr",
-					 (int *)&pmic->irq_addr, 2);
+	/* SOC_PMIC_IRQ0_ADDR */
+	ret = of_property_read_u32(np, "irq-addr", &pmic->irq_addr);
 	if (ret) {
 		pr_err("no irq-addr property set\n");
 		ret = -ENODEV;
@@ -252,18 +246,18 @@ static int get_pmic_device_tree_data(struct device_node *np,
 
 static void hi6421_spmi_pmic_irq_prc(struct hi6421_spmi_pmic *pmic)
 {
-	int i;
+	int i, pending;
 
-	for (i = 0 ; i < pmic->irq_mask_addr.array; i++)
-		hi6421_spmi_pmic_write(pmic, pmic->irq_mask_addr.start_addr + i,
+	for (i = 0 ; i < pmic->irqarray; i++)
+		hi6421_spmi_pmic_write(pmic, pmic->irq_mask_addr + i,
 				       HISI_MASK_STATE);
 
-	for (i = 0 ; i < pmic->irq_addr.array; i++) {
-		unsigned int pending = hi6421_spmi_pmic_read(pmic, pmic->irq_addr.start_addr + i);
+	for (i = 0 ; i < pmic->irqarray; i++) {
+		pending = hi6421_spmi_pmic_read(pmic, pmic->irq_addr + i);
 
 		pr_debug("PMU IRQ address value:irq[0x%x] = 0x%x\n",
-			 pmic->irq_addr.start_addr + i, pending);
-		hi6421_spmi_pmic_write(pmic, pmic->irq_addr.start_addr + i,
+			 pmic->irq_addr + i, pending);
+		hi6421_spmi_pmic_write(pmic, pmic->irq_addr + i,
 				       HISI_MASK_STATE);
 	}
 }
@@ -272,36 +266,32 @@ static int hi6421_spmi_pmic_probe(struct spmi_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct device_node *np = dev->of_node;
-	struct hi6421_spmi_pmic *pmic = NULL;
-	enum of_gpio_flags flags;
-	int ret = 0;
-	int i;
+	struct hi6421_spmi_pmic *pmic;
 	unsigned int virq;
+	int ret, i;
 
 	pmic = devm_kzalloc(dev, sizeof(*pmic), GFP_KERNEL);
 	if (!pmic)
 		return -ENOMEM;
 
-	/*TODO: get pmic dts info*/
 	ret = get_pmic_device_tree_data(np, pmic);
 	if (ret) {
-		dev_err(&pdev->dev, "Error reading hisi pmic dts\n");
+		dev_err(dev, "Error reading hisi pmic dts\n");
 		return ret;
 	}
 
-	/* TODO: get and enable clk request */
 	spin_lock_init(&pmic->lock);
 
 	pmic->dev = dev;
 
-	pmic->gpio = of_get_gpio_flags(np, 0, &flags);
+	pmic->gpio = of_get_gpio(np, 0);
 	if (pmic->gpio < 0)
 		return pmic->gpio;
 
 	if (!gpio_is_valid(pmic->gpio))
 		return -EINVAL;
 
-	ret = gpio_request_one(pmic->gpio, GPIOF_IN, "pmic");
+	ret = devm_gpio_request_one(dev, pmic->gpio, GPIOF_IN, "pmic");
 	if (ret < 0) {
 		dev_err(dev, "failed to request gpio%d\n", pmic->gpio);
 		return ret;
@@ -309,7 +299,6 @@ static int hi6421_spmi_pmic_probe(struct spmi_device *pdev)
 
 	pmic->irq = gpio_to_irq(pmic->gpio);
 
-	/* mask && clear IRQ status */
 	hi6421_spmi_pmic_irq_prc(pmic);
 
 	pmic->irqs = devm_kzalloc(dev, pmic->irqnum * sizeof(int), GFP_KERNEL);
@@ -321,27 +310,27 @@ static int hi6421_spmi_pmic_probe(struct spmi_device *pdev)
 	if (!pmic->domain) {
 		dev_err(dev, "failed irq domain add simple!\n");
 		ret = -ENODEV;
-		goto irq_domain;
+		goto irq_malloc;
 	}
 
 	for (i = 0; i < pmic->irqnum; i++) {
 		virq = irq_create_mapping(pmic->domain, i);
-		if (virq == NO_IRQ) {
-			pr_debug("Failed mapping hwirq\n");
+		if (!virq) {
+			dev_err(dev, "Failed mapping hwirq\n");
 			ret = -ENOSPC;
-			goto irq_create_mapping;
+			goto irq_malloc;
 		}
 		pmic->irqs[i] = virq;
-		pr_info("[%s]. pmic->irqs[%d] = %d\n", __func__, i, pmic->irqs[i]);
+		dev_dbg(dev, "%s: pmic->irqs[%d] = %d\n",
+			__func__, i, pmic->irqs[i]);
 	}
 
 	ret = request_threaded_irq(pmic->irq, hi6421_spmi_irq_handler, NULL,
 				   IRQF_TRIGGER_LOW | IRQF_SHARED | IRQF_NO_SUSPEND,
 				   "pmic", pmic);
 	if (ret < 0) {
-		dev_err(dev, "could not claim pmic %d\n", ret);
-		ret = -ENODEV;
-		goto request_theaded_irq;
+		dev_err(dev, "could not claim pmic IRQ: error %d\n", ret);
+		goto irq_malloc;
 	}
 
 	dev_set_drvdata(&pdev->dev, pmic);
@@ -355,18 +344,14 @@ static int hi6421_spmi_pmic_probe(struct spmi_device *pdev)
 	ret = devm_mfd_add_devices(&pdev->dev, PLATFORM_DEVID_NONE,
 				   hi6421v600_devs, ARRAY_SIZE(hi6421v600_devs),
 				   NULL, 0, NULL);
-	if (ret) {
-		dev_err(&pdev->dev, "Failed to add child devices: %d\n", ret);
-		return ret;
-	}
+	if (!ret)
+		return 0;
 
-	return 0;
+	dev_err(dev, "Failed to add child devices: %d\n", ret);
 
-request_theaded_irq:
-irq_create_mapping:
-irq_domain:
 irq_malloc:
-	gpio_free(pmic->gpio);
+	free_irq(pmic->irq, pmic);
+
 	return ret;
 }
 
@@ -375,8 +360,6 @@ static void hi6421_spmi_pmic_remove(struct spmi_device *pdev)
 	struct hi6421_spmi_pmic *pmic = dev_get_drvdata(&pdev->dev);
 
 	free_irq(pmic->irq, pmic);
-	gpio_free(pmic->gpio);
-	devm_kfree(&pdev->dev, pmic);
 }
 
 static const struct of_device_id pmic_spmi_id_table[] = {
diff --git a/include/linux/mfd/hi6421-spmi-pmic.h b/include/linux/mfd/hi6421-spmi-pmic.h
index 403fd8bb45fa..ff3adfa7b3ec 100644
--- a/include/linux/mfd/hi6421-spmi-pmic.h
+++ b/include/linux/mfd/hi6421-spmi-pmic.h
@@ -36,15 +36,17 @@ struct hi6421_spmi_pmic {
 	int					irq;
 	int					gpio;
 	unsigned int				*irqs;
+
 	int					irqnum;
 	int					irqarray;
-	struct hi6421_spmi_irq_mask_info	irq_mask_addr;
-	struct hi6421_spmi_irq_info		irq_addr;
+	int					irq_mask_addr;
+	int					irq_addr;
 };
 
-u32 hi6421_spmi_pmic_read(struct hi6421_spmi_pmic *pmic, int reg);
-void hi6421_spmi_pmic_write(struct hi6421_spmi_pmic *pmic, int reg, u32 val);
-void hi6421_spmi_pmic_rmw(struct hi6421_spmi_pmic *pmic, int reg, u32 mask, u32 bits);
+int hi6421_spmi_pmic_read(struct hi6421_spmi_pmic *pmic, int reg);
+int hi6421_spmi_pmic_write(struct hi6421_spmi_pmic *pmic, int reg, u32 val);
+int hi6421_spmi_pmic_rmw(struct hi6421_spmi_pmic *pmic, int reg,
+			 u32 mask, u32 bits);
 
 enum hi6421_spmi_pmic_irq_list {
 	OTMP = 0,
-- 
cgit v1.2.3


From 9f0c4fa111dc909ca545c45ea20ec84da555ce16 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Thu, 23 Jul 2020 10:11:10 -0700
Subject: perf/core: Add a new PERF_EV_CAP_SIBLING event capability

Current perf assumes that events in a group are independent. Close an
event doesn't impact the value of the other events in the same group.
If the closed event is a member, after the event closure, other events
are still running like a group. If the closed event is a leader, other
events are running as singleton events.

Add PERF_EV_CAP_SIBLING to allow events to indicate they require being
part of a group, and when the leader dies they cannot exist
independently.

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200723171117.9918-8-kan.liang@linux.intel.com
---
 include/linux/perf_event.h |  4 ++++
 kernel/events/core.c       | 38 +++++++++++++++++++++++++++++++++-----
 2 files changed, 37 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 04a49ccc7beb..6048650f8c1d 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -576,9 +576,13 @@ typedef void (*perf_overflow_handler_t)(struct perf_event *,
  * PERF_EV_CAP_SOFTWARE: Is a software event.
  * PERF_EV_CAP_READ_ACTIVE_PKG: A CPU event (or cgroup event) that can be read
  * from any CPU in the package where it is active.
+ * PERF_EV_CAP_SIBLING: An event with this flag must be a group sibling and
+ * cannot be a group leader. If an event with this flag is detached from the
+ * group it is scheduled out and moved into an unrecoverable ERROR state.
  */
 #define PERF_EV_CAP_SOFTWARE		BIT(0)
 #define PERF_EV_CAP_READ_ACTIVE_PKG	BIT(1)
+#define PERF_EV_CAP_SIBLING		BIT(2)
 
 #define SWEVENT_HLIST_BITS		8
 #define SWEVENT_HLIST_SIZE		(1 << SWEVENT_HLIST_BITS)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 5bfe8e3c6e44..57efe3b21e29 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2133,8 +2133,24 @@ static inline struct list_head *get_event_list(struct perf_event *event)
 	return event->attr.pinned ? &ctx->pinned_active : &ctx->flexible_active;
 }
 
+/*
+ * Events that have PERF_EV_CAP_SIBLING require being part of a group and
+ * cannot exist on their own, schedule them out and move them into the ERROR
+ * state. Also see _perf_event_enable(), it will not be able to recover
+ * this ERROR state.
+ */
+static inline void perf_remove_sibling_event(struct perf_event *event)
+{
+	struct perf_event_context *ctx = event->ctx;
+	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
+
+	event_sched_out(event, cpuctx, ctx);
+	perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
+}
+
 static void perf_group_detach(struct perf_event *event)
 {
+	struct perf_event *leader = event->group_leader;
 	struct perf_event *sibling, *tmp;
 	struct perf_event_context *ctx = event->ctx;
 
@@ -2153,7 +2169,7 @@ static void perf_group_detach(struct perf_event *event)
 	/*
 	 * If this is a sibling, remove it from its group.
 	 */
-	if (event->group_leader != event) {
+	if (leader != event) {
 		list_del_init(&event->sibling_list);
 		event->group_leader->nr_siblings--;
 		goto out;
@@ -2166,6 +2182,9 @@ static void perf_group_detach(struct perf_event *event)
 	 */
 	list_for_each_entry_safe(sibling, tmp, &event->sibling_list, sibling_list) {
 
+		if (sibling->event_caps & PERF_EV_CAP_SIBLING)
+			perf_remove_sibling_event(sibling);
+
 		sibling->group_leader = sibling;
 		list_del_init(&sibling->sibling_list);
 
@@ -2183,10 +2202,10 @@ static void perf_group_detach(struct perf_event *event)
 	}
 
 out:
-	perf_event__header_size(event->group_leader);
-
-	for_each_sibling_event(tmp, event->group_leader)
+	for_each_sibling_event(tmp, leader)
 		perf_event__header_size(tmp);
+
+	perf_event__header_size(leader);
 }
 
 static bool is_orphaned_event(struct perf_event *event)
@@ -2979,6 +2998,7 @@ static void _perf_event_enable(struct perf_event *event)
 	raw_spin_lock_irq(&ctx->lock);
 	if (event->state >= PERF_EVENT_STATE_INACTIVE ||
 	    event->state <  PERF_EVENT_STATE_ERROR) {
+out:
 		raw_spin_unlock_irq(&ctx->lock);
 		return;
 	}
@@ -2990,8 +3010,16 @@ static void _perf_event_enable(struct perf_event *event)
 	 * has gone back into error state, as distinct from the task having
 	 * been scheduled away before the cross-call arrived.
 	 */
-	if (event->state == PERF_EVENT_STATE_ERROR)
+	if (event->state == PERF_EVENT_STATE_ERROR) {
+		/*
+		 * Detached SIBLING events cannot leave ERROR state.
+		 */
+		if (event->event_caps & PERF_EV_CAP_SIBLING &&
+		    event->group_leader == event)
+			goto out;
+
 		event->state = PERF_EVENT_STATE_OFF;
+	}
 	raw_spin_unlock_irq(&ctx->lock);
 
 	event_function_call(event, __perf_event_enable, NULL);
-- 
cgit v1.2.3


From 2cb5383b30d47c446ec7d884cd80f93ffcc31817 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Thu, 23 Jul 2020 10:11:14 -0700
Subject: perf/x86/intel: Support per-thread RDPMC TopDown metrics

Starts from Ice Lake, the TopDown metrics are directly available as
fixed counters and do not require generic counters. Also, the TopDown
metrics can be collected per thread. Extend the RDPMC usage to support
per-thread TopDown metrics.

The RDPMC index of the PERF_METRICS will be output if RDPMC users ask
for the RDPMC index of the metrics events.

To support per thread RDPMC TopDown, the metrics and slots counters have
to be saved/restored during the context switching.

The last_period and period_left are not used in the counting mode. Use
the fields for saved_metric and saved_slots.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200723171117.9918-12-kan.liang@linux.intel.com
---
 arch/x86/events/core.c       |  5 ++-
 arch/x86/events/intel/core.c | 90 ++++++++++++++++++++++++++++++++++++++------
 include/linux/perf_event.h   | 29 +++++++++-----
 3 files changed, 102 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index ebf723f33794..0f3d01562ded 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2257,7 +2257,10 @@ static int x86_pmu_event_idx(struct perf_event *event)
 	if (!(hwc->flags & PERF_X86_EVENT_RDPMC_ALLOWED))
 		return 0;
 
-	return hwc->event_base_rdpmc + 1;
+	if (is_metric_idx(hwc->idx))
+		return INTEL_PMC_FIXED_RDPMC_METRICS + 1;
+	else
+		return hwc->event_base_rdpmc + 1;
 }
 
 static ssize_t get_attr_rdpmc(struct device *cdev,
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index db833346c119..c72e4904e056 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2258,7 +2258,13 @@ static int icl_set_topdown_event_period(struct perf_event *event)
 	if (left == x86_pmu.max_period) {
 		wrmsrl(MSR_CORE_PERF_FIXED_CTR3, 0);
 		wrmsrl(MSR_PERF_METRICS, 0);
-		local64_set(&hwc->period_left, 0);
+		hwc->saved_slots = 0;
+		hwc->saved_metric = 0;
+	}
+
+	if ((hwc->saved_slots) && is_slots_event(event)) {
+		wrmsrl(MSR_CORE_PERF_FIXED_CTR3, hwc->saved_slots);
+		wrmsrl(MSR_PERF_METRICS, hwc->saved_metric);
 	}
 
 	perf_event_update_userpage(event);
@@ -2279,7 +2285,7 @@ static inline u64 icl_get_metrics_event_value(u64 metric, u64 slots, int idx)
 	return  mul_u64_u32_div(slots, val, 0xff);
 }
 
-static void __icl_update_topdown_event(struct perf_event *event,
+static u64 icl_get_topdown_value(struct perf_event *event,
 				       u64 slots, u64 metrics)
 {
 	int idx = event->hw.idx;
@@ -2290,7 +2296,50 @@ static void __icl_update_topdown_event(struct perf_event *event,
 	else
 		delta = slots;
 
-	local64_add(delta, &event->count);
+	return delta;
+}
+
+static void __icl_update_topdown_event(struct perf_event *event,
+				       u64 slots, u64 metrics,
+				       u64 last_slots, u64 last_metrics)
+{
+	u64 delta, last = 0;
+
+	delta = icl_get_topdown_value(event, slots, metrics);
+	if (last_slots)
+		last = icl_get_topdown_value(event, last_slots, last_metrics);
+
+	/*
+	 * The 8bit integer fraction of metric may be not accurate,
+	 * especially when the changes is very small.
+	 * For example, if only a few bad_spec happens, the fraction
+	 * may be reduced from 1 to 0. If so, the bad_spec event value
+	 * will be 0 which is definitely less than the last value.
+	 * Avoid update event->count for this case.
+	 */
+	if (delta > last) {
+		delta -= last;
+		local64_add(delta, &event->count);
+	}
+}
+
+static void update_saved_topdown_regs(struct perf_event *event,
+				      u64 slots, u64 metrics)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct perf_event *other;
+	int idx;
+
+	event->hw.saved_slots = slots;
+	event->hw.saved_metric = metrics;
+
+	for_each_set_bit(idx, cpuc->active_mask, INTEL_PMC_IDX_TD_BE_BOUND + 1) {
+		if (!is_topdown_idx(idx))
+			continue;
+		other = cpuc->events[idx];
+		other->hw.saved_slots = slots;
+		other->hw.saved_metric = metrics;
+	}
 }
 
 /*
@@ -2304,6 +2353,7 @@ static u64 icl_update_topdown_event(struct perf_event *event)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct perf_event *other;
 	u64 slots, metrics;
+	bool reset = true;
 	int idx;
 
 	/* read Fixed counter 3 */
@@ -2318,19 +2368,39 @@ static u64 icl_update_topdown_event(struct perf_event *event)
 		if (!is_topdown_idx(idx))
 			continue;
 		other = cpuc->events[idx];
-		__icl_update_topdown_event(other, slots, metrics);
+		__icl_update_topdown_event(other, slots, metrics,
+					   event ? event->hw.saved_slots : 0,
+					   event ? event->hw.saved_metric : 0);
 	}
 
 	/*
 	 * Check and update this event, which may have been cleared
 	 * in active_mask e.g. x86_pmu_stop()
 	 */
-	if (event && !test_bit(event->hw.idx, cpuc->active_mask))
-		__icl_update_topdown_event(event, slots, metrics);
+	if (event && !test_bit(event->hw.idx, cpuc->active_mask)) {
+		__icl_update_topdown_event(event, slots, metrics,
+					   event->hw.saved_slots,
+					   event->hw.saved_metric);
 
-	/* The fixed counter 3 has to be written before the PERF_METRICS. */
-	wrmsrl(MSR_CORE_PERF_FIXED_CTR3, 0);
-	wrmsrl(MSR_PERF_METRICS, 0);
+		/*
+		 * In x86_pmu_stop(), the event is cleared in active_mask first,
+		 * then drain the delta, which indicates context switch for
+		 * counting.
+		 * Save metric and slots for context switch.
+		 * Don't need to reset the PERF_METRICS and Fixed counter 3.
+		 * Because the values will be restored in next schedule in.
+		 */
+		update_saved_topdown_regs(event, slots, metrics);
+		reset = false;
+	}
+
+	if (reset) {
+		/* The fixed counter 3 has to be written before the PERF_METRICS. */
+		wrmsrl(MSR_CORE_PERF_FIXED_CTR3, 0);
+		wrmsrl(MSR_PERF_METRICS, 0);
+		if (event)
+			update_saved_topdown_regs(event, 0, 0);
+	}
 
 	return slots;
 }
@@ -3578,8 +3648,6 @@ static int intel_pmu_hw_config(struct perf_event *event)
 			 */
 			leader->hw.flags |= PERF_X86_EVENT_TOPDOWN;
 			event->hw.flags  |= PERF_X86_EVENT_TOPDOWN;
-
-			event->hw.flags &= ~PERF_X86_EVENT_RDPMC_ALLOWED;
 		}
 	}
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 6048650f8c1d..46a3974eb4fe 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -212,17 +212,26 @@ struct hw_perf_event {
 	 */
 	u64				sample_period;
 
-	/*
-	 * The period we started this sample with.
-	 */
-	u64				last_period;
+	union {
+		struct { /* Sampling */
+			/*
+			 * The period we started this sample with.
+			 */
+			u64				last_period;
 
-	/*
-	 * However much is left of the current period; note that this is
-	 * a full 64bit value and allows for generation of periods longer
-	 * than hardware might allow.
-	 */
-	local64_t			period_left;
+			/*
+			 * However much is left of the current period;
+			 * note that this is a full 64bit value and
+			 * allows for generation of periods longer
+			 * than hardware might allow.
+			 */
+			local64_t			period_left;
+		};
+		struct { /* Topdown events counting for context switch */
+			u64				saved_metric;
+			u64				saved_slots;
+		};
+	};
 
 	/*
 	 * State for throttling the event, see __perf_event_overflow() and
-- 
cgit v1.2.3


From b240d0143bfbc96f610405f978e4753fd663cbfc Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Tue, 18 Aug 2020 16:58:54 +0200
Subject: staging: mfd: hi6421-spmi-pmic: get rid of interrupt properties

Both irqnum and irqarray properties reflect the same thing:
the number of bits and bytes for interrupts at this
chipset. E. g.:

	irqnum = 8 x irqarray

This can be seen by the way pending interrupts are handled:

	/* During probe time */
	pmic->irqs = devm_kzalloc(dev, pmic->irqnum * sizeof(int), GFP_KERNEL);

	/* While handling IRQs */
	for (i = 0; i < pmic->irqarray; i++) {
		pending = hi6421_spmi_pmic_read(pmic, (i + pmic->irq_addr));
		pending &= 0xff;

		for_each_set_bit(offset, &pending, 8)
			generic_handle_irq(pmic->irqs[offset + i * 8]);

	}

Going further, there are some logic at the driver which assumes
that irqarray is 2:

	/* solve powerkey order */
	if ((i == HISI_IRQ_KEY_NUM) &&
	    ((pending & HISI_IRQ_KEY_VALUE) == HISI_IRQ_KEY_VALUE)) {
		generic_handle_irq(pmic->irqs[HISI_IRQ_KEY_DOWN]);
		generic_handle_irq(pmic->irqs[HISI_IRQ_KEY_UP]);
		pending &= (~HISI_IRQ_KEY_VALUE);
	}

As HISI_IRQ_KEY_DOWN and HISI_IRQ_KEY_UP are fixed values
and don't depend on irqnum/irqarray.

The IRQ addr and mask addr seem to be also fixed, based on some
comments at the OF parsing code. So, get rid of them too,
removing the of parsing function completely.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Link: https://lore.kernel.org/r/e231244e42cb5b56240705cac2f987e11a078038.1597762400.git.mchehab+huawei@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/hikey9xx/hi6421-spmi-pmic.c | 80 ++++++++---------------------
 include/linux/mfd/hi6421-spmi-pmic.h        | 15 ------
 2 files changed, 20 insertions(+), 75 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/staging/hikey9xx/hi6421-spmi-pmic.c b/drivers/staging/hikey9xx/hi6421-spmi-pmic.c
index 9d73458ca65a..7817c0637737 100644
--- a/drivers/staging/hikey9xx/hi6421-spmi-pmic.c
+++ b/drivers/staging/hikey9xx/hi6421-spmi-pmic.c
@@ -38,6 +38,12 @@
 /* 8-bit register offset in PMIC */
 #define HISI_MASK_STATE			0xff
 
+#define HISI_IRQ_ARRAY			2
+#define HISI_IRQ_NUM			(HISI_IRQ_ARRAY * 8)
+
+#define SOC_PMIC_IRQ_MASK_0_ADDR	0x0202
+#define SOC_PMIC_IRQ0_ADDR		0x0212
+
 #define HISI_IRQ_KEY_NUM		0
 #define HISI_IRQ_KEY_VALUE		0xc0
 #define HISI_IRQ_KEY_DOWN		7
@@ -121,13 +127,13 @@ static irqreturn_t hi6421_spmi_irq_handler(int irq, void *data)
 	unsigned long pending;
 	int i, offset;
 
-	for (i = 0; i < pmic->irqarray; i++) {
-		pending = hi6421_spmi_pmic_read(pmic, (i + pmic->irq_addr));
+	for (i = 0; i < HISI_IRQ_ARRAY; i++) {
+		pending = hi6421_spmi_pmic_read(pmic, (i + SOC_PMIC_IRQ0_ADDR));
 		pending &= HISI_MASK_FIELD;
 		if (pending != 0)
 			pr_debug("pending[%d]=0x%lx\n\r", i, pending);
 
-		hi6421_spmi_pmic_write(pmic, (i + pmic->irq_addr), pending);
+		hi6421_spmi_pmic_write(pmic, (i + SOC_PMIC_IRQ0_ADDR), pending);
 
 		/* solve powerkey order */
 		if ((i == HISI_IRQ_KEY_NUM) &&
@@ -153,7 +159,7 @@ static void hi6421_spmi_irq_mask(struct irq_data *d)
 	unsigned long flags;
 
 	offset = (irqd_to_hwirq(d) >> 3);
-	offset += pmic->irq_mask_addr;
+	offset += SOC_PMIC_IRQ_MASK_0_ADDR;
 
 	spin_lock_irqsave(&pmic->lock, flags);
 	data = hi6421_spmi_pmic_read(pmic, offset);
@@ -169,7 +175,7 @@ static void hi6421_spmi_irq_unmask(struct irq_data *d)
 	unsigned long flags;
 
 	offset = (irqd_to_hwirq(d) >> 3);
-	offset += pmic->irq_mask_addr;
+	offset += SOC_PMIC_IRQ_MASK_0_ADDR;
 
 	spin_lock_irqsave(&pmic->lock, flags);
 	data = hi6421_spmi_pmic_read(pmic, offset);
@@ -204,60 +210,20 @@ static const struct irq_domain_ops hi6421_spmi_domain_ops = {
 	.xlate	= irq_domain_xlate_twocell,
 };
 
-static int get_pmic_device_tree_data(struct device_node *np,
-				     struct hi6421_spmi_pmic *pmic)
-{
-	int ret = 0;
-
-	/* IRQ number */
-	ret = of_property_read_u32(np, "irq-num", &pmic->irqnum);
-	if (ret) {
-		pr_err("no irq-num property set\n");
-		ret = -ENODEV;
-		return ret;
-	}
-
-	/* Size of IRQ array */
-	ret = of_property_read_u32(np, "irq-array", &pmic->irqarray);
-	if (ret) {
-		pr_err("no irq-array property set\n");
-		ret = -ENODEV;
-		return ret;
-	}
-
-	/* SOC_PMIC_IRQ_MASK_0_ADDR */
-	ret = of_property_read_u32(np, "irq-mask-addr", &pmic->irq_mask_addr);
-	if (ret) {
-		pr_err("no irq-mask-addr property set\n");
-		ret = -ENODEV;
-		return ret;
-	}
-
-	/* SOC_PMIC_IRQ0_ADDR */
-	ret = of_property_read_u32(np, "irq-addr", &pmic->irq_addr);
-	if (ret) {
-		pr_err("no irq-addr property set\n");
-		ret = -ENODEV;
-		return ret;
-	}
-
-	return ret;
-}
-
 static void hi6421_spmi_pmic_irq_prc(struct hi6421_spmi_pmic *pmic)
 {
 	int i, pending;
 
-	for (i = 0 ; i < pmic->irqarray; i++)
-		hi6421_spmi_pmic_write(pmic, pmic->irq_mask_addr + i,
+	for (i = 0 ; i < HISI_IRQ_ARRAY; i++)
+		hi6421_spmi_pmic_write(pmic, SOC_PMIC_IRQ_MASK_0_ADDR + i,
 				       HISI_MASK_STATE);
 
-	for (i = 0 ; i < pmic->irqarray; i++) {
-		pending = hi6421_spmi_pmic_read(pmic, pmic->irq_addr + i);
+	for (i = 0 ; i < HISI_IRQ_ARRAY; i++) {
+		pending = hi6421_spmi_pmic_read(pmic, SOC_PMIC_IRQ0_ADDR + i);
 
 		pr_debug("PMU IRQ address value:irq[0x%x] = 0x%x\n",
-			 pmic->irq_addr + i, pending);
-		hi6421_spmi_pmic_write(pmic, pmic->irq_addr + i,
+			 SOC_PMIC_IRQ0_ADDR + i, pending);
+		hi6421_spmi_pmic_write(pmic, SOC_PMIC_IRQ0_ADDR + i,
 				       HISI_MASK_STATE);
 	}
 }
@@ -274,12 +240,6 @@ static int hi6421_spmi_pmic_probe(struct spmi_device *pdev)
 	if (!pmic)
 		return -ENOMEM;
 
-	ret = get_pmic_device_tree_data(np, pmic);
-	if (ret) {
-		dev_err(dev, "Error reading hisi pmic dts\n");
-		return ret;
-	}
-
 	spin_lock_init(&pmic->lock);
 
 	pmic->dev = dev;
@@ -301,11 +261,11 @@ static int hi6421_spmi_pmic_probe(struct spmi_device *pdev)
 
 	hi6421_spmi_pmic_irq_prc(pmic);
 
-	pmic->irqs = devm_kzalloc(dev, pmic->irqnum * sizeof(int), GFP_KERNEL);
+	pmic->irqs = devm_kzalloc(dev, HISI_IRQ_NUM * sizeof(int), GFP_KERNEL);
 	if (!pmic->irqs)
 		goto irq_malloc;
 
-	pmic->domain = irq_domain_add_simple(np, pmic->irqnum, 0,
+	pmic->domain = irq_domain_add_simple(np, HISI_IRQ_NUM, 0,
 					     &hi6421_spmi_domain_ops, pmic);
 	if (!pmic->domain) {
 		dev_err(dev, "failed irq domain add simple!\n");
@@ -313,7 +273,7 @@ static int hi6421_spmi_pmic_probe(struct spmi_device *pdev)
 		goto irq_malloc;
 	}
 
-	for (i = 0; i < pmic->irqnum; i++) {
+	for (i = 0; i < HISI_IRQ_NUM; i++) {
 		virq = irq_create_mapping(pmic->domain, i);
 		if (!virq) {
 			dev_err(dev, "Failed mapping hwirq\n");
diff --git a/include/linux/mfd/hi6421-spmi-pmic.h b/include/linux/mfd/hi6421-spmi-pmic.h
index ff3adfa7b3ec..2c8896fd852e 100644
--- a/include/linux/mfd/hi6421-spmi-pmic.h
+++ b/include/linux/mfd/hi6421-spmi-pmic.h
@@ -17,16 +17,6 @@
 #define HISI_ECO_MODE_ENABLE		(1)
 #define HISI_ECO_MODE_DISABLE		(0)
 
-struct hi6421_spmi_irq_mask_info {
-	int start_addr;
-	int array;
-};
-
-struct hi6421_spmi_irq_info {
-	int start_addr;
-	int array;
-};
-
 struct hi6421_spmi_pmic {
 	struct resource				*res;
 	struct device				*dev;
@@ -36,11 +26,6 @@ struct hi6421_spmi_pmic {
 	int					irq;
 	int					gpio;
 	unsigned int				*irqs;
-
-	int					irqnum;
-	int					irqarray;
-	int					irq_mask_addr;
-	int					irq_addr;
 };
 
 int hi6421_spmi_pmic_read(struct hi6421_spmi_pmic *pmic, int reg);
-- 
cgit v1.2.3


From a21a4391f20c0ab45db452e22bc3e8afe8b36e46 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Wed, 8 Jul 2020 16:39:24 +0000
Subject: x86/resctrl: Include pid.h

We are about to disturb the header soup. This header uses struct pid
and struct pid_namespace. Include their header.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lkml.kernel.org/r/20200708163929.2783-6-james.morse@arm.com
---
 include/linux/resctrl.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index daf5cf64c6a6..9b05af9b3e28 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -2,6 +2,8 @@
 #ifndef _RESCTRL_H
 #define _RESCTRL_H
 
+#include <linux/pid.h>
+
 #ifdef CONFIG_PROC_CPU_RESCTRL
 
 int proc_resctrl_show(struct seq_file *m,
-- 
cgit v1.2.3


From cfe7ddcbd72dc67ce5749cc6f451a2b0c6aec5b5 Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Mon, 17 Aug 2020 12:29:47 +0100
Subject: ARM, sched/topology: Remove SD_SHARE_POWERDOMAIN

This flag was introduced in 2014 by commit:

  d77b3ed5c9f8 ("sched: Add a new SD_SHARE_POWERDOMAIN for sched_domain")

but AFAIA it was never leveraged by the scheduler. The closest thing I can
think of is EAS caring about frequency domains, and it does that by
leveraging performance domains.

Remove the flag. No change in functionality is expected.

Suggested-by: Morten Rasmussen <morten.rasmussen@arm.com>
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: https://lore.kernel.org/r/20200817113003.20802-2-valentin.schneider@arm.com
---
 arch/arm/kernel/topology.c     |  2 +-
 include/linux/sched/topology.h | 13 ++++++-------
 kernel/sched/topology.c        | 10 +++-------
 3 files changed, 10 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index b5adaf744630..353f3ee660e4 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -243,7 +243,7 @@ topology_populated:
 
 static inline int cpu_corepower_flags(void)
 {
-	return SD_SHARE_PKG_RESOURCES  | SD_SHARE_POWERDOMAIN;
+	return SD_SHARE_PKG_RESOURCES;
 }
 
 static struct sched_domain_topology_level arm_topology[] = {
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 820511289857..6ec7d7c1d1e3 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -18,13 +18,12 @@
 #define SD_WAKE_AFFINE		0x0010	/* Wake task to waking CPU */
 #define SD_ASYM_CPUCAPACITY	0x0020  /* Domain members have different CPU capacities */
 #define SD_SHARE_CPUCAPACITY	0x0040	/* Domain members share CPU capacity */
-#define SD_SHARE_POWERDOMAIN	0x0080	/* Domain members share power domain */
-#define SD_SHARE_PKG_RESOURCES	0x0100	/* Domain members share CPU pkg resources */
-#define SD_SERIALIZE		0x0200	/* Only a single load balancing instance */
-#define SD_ASYM_PACKING		0x0400  /* Place busy groups earlier in the domain */
-#define SD_PREFER_SIBLING	0x0800	/* Prefer to place tasks in a sibling domain */
-#define SD_OVERLAP		0x1000	/* sched_domains of this level overlap */
-#define SD_NUMA			0x2000	/* cross-node balancing */
+#define SD_SHARE_PKG_RESOURCES	0x0080	/* Domain members share CPU pkg resources */
+#define SD_SERIALIZE		0x0100	/* Only a single load balancing instance */
+#define SD_ASYM_PACKING		0x0200  /* Place busy groups earlier in the domain */
+#define SD_PREFER_SIBLING	0x0400	/* Prefer to place tasks in a sibling domain */
+#define SD_OVERLAP		0x0800	/* sched_domains of this level overlap */
+#define SD_NUMA			0x1000	/* cross-node balancing */
 
 #ifdef CONFIG_SCHED_SMT
 static inline int cpu_smt_flags(void)
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 007b0a6b0152..fe0396978fea 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -148,8 +148,7 @@ static int sd_degenerate(struct sched_domain *sd)
 			 SD_BALANCE_EXEC |
 			 SD_SHARE_CPUCAPACITY |
 			 SD_ASYM_CPUCAPACITY |
-			 SD_SHARE_PKG_RESOURCES |
-			 SD_SHARE_POWERDOMAIN)) {
+			 SD_SHARE_PKG_RESOURCES)) {
 		if (sd->groups != sd->groups->next)
 			return 0;
 	}
@@ -180,8 +179,7 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
 			    SD_ASYM_CPUCAPACITY |
 			    SD_SHARE_CPUCAPACITY |
 			    SD_SHARE_PKG_RESOURCES |
-			    SD_PREFER_SIBLING |
-			    SD_SHARE_POWERDOMAIN);
+			    SD_PREFER_SIBLING);
 		if (nr_node_ids == 1)
 			pflags &= ~SD_SERIALIZE;
 	}
@@ -1292,7 +1290,6 @@ int __read_mostly		node_reclaim_distance = RECLAIM_DISTANCE;
  *   SD_SHARE_CPUCAPACITY   - describes SMT topologies
  *   SD_SHARE_PKG_RESOURCES - describes shared caches
  *   SD_NUMA                - describes NUMA topologies
- *   SD_SHARE_POWERDOMAIN   - describes shared power domain
  *
  * Odd one out, which beside describing the topology has a quirk also
  * prescribes the desired behaviour that goes along with it:
@@ -1303,8 +1300,7 @@ int __read_mostly		node_reclaim_distance = RECLAIM_DISTANCE;
 	(SD_SHARE_CPUCAPACITY	|	\
 	 SD_SHARE_PKG_RESOURCES |	\
 	 SD_NUMA		|	\
-	 SD_ASYM_PACKING	|	\
-	 SD_SHARE_POWERDOMAIN)
+	 SD_ASYM_PACKING)
 
 static struct sched_domain *
 sd_init(struct sched_domain_topology_level *tl,
-- 
cgit v1.2.3


From d54a9658a75633b839af7a2c6c758807678b8064 Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Mon, 17 Aug 2020 12:29:49 +0100
Subject: sched/topology: Split out SD_* flags declaration to its own file

To associate the SD flags with some metadata, we need some more structure
in the way they are declared.

Rather than shove that in a free-standing macro list, move the declaration
in a separate file that can be re-imported with different SD_FLAG
definitions. This is inspired by what is done with the syscall
table (see uapi/asm/unistd.h and sys_call_table).

The value assigned to a given SD flag now depends on the order it appears
in sd_flags.h. No change in functionality.

Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: https://lore.kernel.org/r/20200817113003.20802-4-valentin.schneider@arm.com
---
 include/linux/sched/sd_flags.h | 35 +++++++++++++++++++++++++++++++++++
 include/linux/sched/topology.h | 26 +++++++++++++-------------
 2 files changed, 48 insertions(+), 13 deletions(-)
 create mode 100644 include/linux/sched/sd_flags.h

(limited to 'include/linux')

diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h
new file mode 100644
index 000000000000..373dc45c024e
--- /dev/null
+++ b/include/linux/sched/sd_flags.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * sched-domains (multiprocessor balancing) flag declarations.
+ */
+
+#ifndef SD_FLAG
+# error "Incorrect import of SD flags definitions"
+#endif
+
+/* Balance when about to become idle */
+SD_FLAG(SD_BALANCE_NEWIDLE)
+/* Balance on exec */
+SD_FLAG(SD_BALANCE_EXEC)
+/* Balance on fork, clone */
+SD_FLAG(SD_BALANCE_FORK)
+/* Balance on wakeup */
+SD_FLAG(SD_BALANCE_WAKE)
+/* Wake task to waking CPU */
+SD_FLAG(SD_WAKE_AFFINE)
+/* Domain members have different CPU capacities */
+SD_FLAG(SD_ASYM_CPUCAPACITY)
+/* Domain members share CPU capacity */
+SD_FLAG(SD_SHARE_CPUCAPACITY)
+/* Domain members share CPU pkg resources */
+SD_FLAG(SD_SHARE_PKG_RESOURCES)
+/* Only a single load balancing instance */
+SD_FLAG(SD_SERIALIZE)
+/* Place busy groups earlier in the domain */
+SD_FLAG(SD_ASYM_PACKING)
+/* Prefer to place tasks in a sibling domain */
+SD_FLAG(SD_PREFER_SIBLING)
+/* sched_domains of this level overlap */
+SD_FLAG(SD_OVERLAP)
+/* cross-node balancing */
+SD_FLAG(SD_NUMA)
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 6ec7d7c1d1e3..3e41c0401b5f 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -11,19 +11,19 @@
  */
 #ifdef CONFIG_SMP
 
-#define SD_BALANCE_NEWIDLE	0x0001	/* Balance when about to become idle */
-#define SD_BALANCE_EXEC		0x0002	/* Balance on exec */
-#define SD_BALANCE_FORK		0x0004	/* Balance on fork, clone */
-#define SD_BALANCE_WAKE		0x0008  /* Balance on wakeup */
-#define SD_WAKE_AFFINE		0x0010	/* Wake task to waking CPU */
-#define SD_ASYM_CPUCAPACITY	0x0020  /* Domain members have different CPU capacities */
-#define SD_SHARE_CPUCAPACITY	0x0040	/* Domain members share CPU capacity */
-#define SD_SHARE_PKG_RESOURCES	0x0080	/* Domain members share CPU pkg resources */
-#define SD_SERIALIZE		0x0100	/* Only a single load balancing instance */
-#define SD_ASYM_PACKING		0x0200  /* Place busy groups earlier in the domain */
-#define SD_PREFER_SIBLING	0x0400	/* Prefer to place tasks in a sibling domain */
-#define SD_OVERLAP		0x0800	/* sched_domains of this level overlap */
-#define SD_NUMA			0x1000	/* cross-node balancing */
+/* Generate SD flag indexes */
+#define SD_FLAG(name) __##name,
+enum {
+	#include <linux/sched/sd_flags.h>
+	__SD_FLAG_CNT,
+};
+#undef SD_FLAG
+/* Generate SD flag bits */
+#define SD_FLAG(name) name = 1 << __##name,
+enum {
+	#include <linux/sched/sd_flags.h>
+};
+#undef SD_FLAG
 
 #ifdef CONFIG_SCHED_SMT
 static inline int cpu_smt_flags(void)
-- 
cgit v1.2.3


From b6e862f386722e0de6c37f85f1cf438a0efa7f93 Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Mon, 17 Aug 2020 12:29:50 +0100
Subject: sched/topology: Define and assign sched_domain flag metadata

There are some expectations regarding how sched domain flags should be laid
out, but none of them are checked or asserted in
sched_domain_debug_one(). After staring at said flags for a while, I've
come to realize there's two repeating patterns:

- Shared with children: those flags are set from the base CPU domain
  upwards. Any domain that has it set will have it set in its children. It
  hints at "some property holds true / some behaviour is enabled until this
  level".

- Shared with parents: those flags are set from the topmost domain
  downwards. Any domain that has it set will have it set in its parents. It
  hints at "some property isn't visible / some behaviour is disabled until
  this level".

There are two outliers that (currently) do not map to either of these:

o SD_PREFER_SIBLING, which is cleared below levels with
  SD_ASYM_CPUCAPACITY. The change was introduced by commit:

    9c63e84db29b ("sched/core: Disable SD_PREFER_SIBLING on asymmetric CPU capacity domains")

  as it could break misfit migration on some systems. In light of this, we
  might want to change it back to make it fit one of the two categories and
  fix the issue another way.

o SD_ASYM_CPUCAPACITY, which gets set on a single level and isn't
  propagated up nor down. From a topology description point of view, it
  really wants to be SDF_SHARED_PARENT; this will be rectified in a later
  patch.

Tweak the sched_domain flag declaration to assign each flag an expected
layout, and include the rationale for each flag "meta type" assignment as a
comment. Consolidate the flag metadata into an array; the index of a flag's
metadata can easily be found with log2(flag), IOW __ffs(flag).

Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: https://lore.kernel.org/r/20200817113003.20802-5-valentin.schneider@arm.com
---
 include/linux/sched/sd_flags.h | 147 +++++++++++++++++++++++++++++++++--------
 include/linux/sched/topology.h |  15 ++++-
 2 files changed, 134 insertions(+), 28 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h
index 373dc45c024e..c24a45b05fbb 100644
--- a/include/linux/sched/sd_flags.h
+++ b/include/linux/sched/sd_flags.h
@@ -7,29 +7,124 @@
 # error "Incorrect import of SD flags definitions"
 #endif
 
-/* Balance when about to become idle */
-SD_FLAG(SD_BALANCE_NEWIDLE)
-/* Balance on exec */
-SD_FLAG(SD_BALANCE_EXEC)
-/* Balance on fork, clone */
-SD_FLAG(SD_BALANCE_FORK)
-/* Balance on wakeup */
-SD_FLAG(SD_BALANCE_WAKE)
-/* Wake task to waking CPU */
-SD_FLAG(SD_WAKE_AFFINE)
-/* Domain members have different CPU capacities */
-SD_FLAG(SD_ASYM_CPUCAPACITY)
-/* Domain members share CPU capacity */
-SD_FLAG(SD_SHARE_CPUCAPACITY)
-/* Domain members share CPU pkg resources */
-SD_FLAG(SD_SHARE_PKG_RESOURCES)
-/* Only a single load balancing instance */
-SD_FLAG(SD_SERIALIZE)
-/* Place busy groups earlier in the domain */
-SD_FLAG(SD_ASYM_PACKING)
-/* Prefer to place tasks in a sibling domain */
-SD_FLAG(SD_PREFER_SIBLING)
-/* sched_domains of this level overlap */
-SD_FLAG(SD_OVERLAP)
-/* cross-node balancing */
-SD_FLAG(SD_NUMA)
+/*
+ * Expected flag uses
+ *
+ * SHARED_CHILD: These flags are meant to be set from the base domain upwards.
+ * If a domain has this flag set, all of its children should have it set. This
+ * is usually because the flag describes some shared resource (all CPUs in that
+ * domain share the same resource), or because they are tied to a scheduling
+ * behaviour that we want to disable at some point in the hierarchy for
+ * scalability reasons.
+ *
+ * In those cases it doesn't make sense to have the flag set for a domain but
+ * not have it in (some of) its children: sched domains ALWAYS span their child
+ * domains, so operations done with parent domains will cover CPUs in the lower
+ * child domains.
+ *
+ *
+ * SHARED_PARENT: These flags are meant to be set from the highest domain
+ * downwards. If a domain has this flag set, all of its parents should have it
+ * set. This is usually for topology properties that start to appear above a
+ * certain level (e.g. domain starts spanning CPUs outside of the base CPU's
+ * socket).
+ */
+#define SDF_SHARED_CHILD 0x1
+#define SDF_SHARED_PARENT 0x2
+
+/*
+ * Balance when about to become idle
+ *
+ * SHARED_CHILD: Set from the base domain up to cpuset.sched_relax_domain_level.
+ */
+SD_FLAG(SD_BALANCE_NEWIDLE, SDF_SHARED_CHILD)
+
+/*
+ * Balance on exec
+ *
+ * SHARED_CHILD: Set from the base domain up to the NUMA reclaim level.
+ */
+SD_FLAG(SD_BALANCE_EXEC, SDF_SHARED_CHILD)
+
+/*
+ * Balance on fork, clone
+ *
+ * SHARED_CHILD: Set from the base domain up to the NUMA reclaim level.
+ */
+SD_FLAG(SD_BALANCE_FORK, SDF_SHARED_CHILD)
+
+/*
+ * Balance on wakeup
+ *
+ * SHARED_CHILD: Set from the base domain up to cpuset.sched_relax_domain_level.
+ */
+SD_FLAG(SD_BALANCE_WAKE, SDF_SHARED_CHILD)
+
+/*
+ * Consider waking task on waking CPU.
+ *
+ * SHARED_CHILD: Set from the base domain up to the NUMA reclaim level.
+ */
+SD_FLAG(SD_WAKE_AFFINE, SDF_SHARED_CHILD)
+
+/*
+ * Domain members have different CPU capacities
+ */
+SD_FLAG(SD_ASYM_CPUCAPACITY, 0)
+
+/*
+ * Domain members share CPU capacity (i.e. SMT)
+ *
+ * SHARED_CHILD: Set from the base domain up until spanned CPUs no longer share
+ * CPU capacity.
+ */
+SD_FLAG(SD_SHARE_CPUCAPACITY, SDF_SHARED_CHILD)
+
+/*
+ * Domain members share CPU package resources (i.e. caches)
+ *
+ * SHARED_CHILD: Set from the base domain up until spanned CPUs no longer share
+ * the same cache(s).
+ */
+SD_FLAG(SD_SHARE_PKG_RESOURCES, SDF_SHARED_CHILD)
+
+/*
+ * Only a single load balancing instance
+ *
+ * SHARED_PARENT: Set for all NUMA levels above NODE. Could be set from a
+ * different level upwards, but it doesn't change that if a domain has this flag
+ * set, then all of its parents need to have it too (otherwise the serialization
+ * doesn't make sense).
+ */
+SD_FLAG(SD_SERIALIZE, SDF_SHARED_PARENT)
+
+/*
+ * Place busy tasks earlier in the domain
+ *
+ * SHARED_CHILD: Usually set on the SMT level. Technically could be set further
+ * up, but currently assumed to be set from the base domain upwards (see
+ * update_top_cache_domain()).
+ */
+SD_FLAG(SD_ASYM_PACKING, SDF_SHARED_CHILD)
+
+/*
+ * Prefer to place tasks in a sibling domain
+ *
+ * Set up until domains start spanning NUMA nodes. Close to being a SHARED_CHILD
+ * flag, but cleared below domains with SD_ASYM_CPUCAPACITY.
+ */
+SD_FLAG(SD_PREFER_SIBLING, 0)
+
+/*
+ * sched_groups of this level overlap
+ *
+ * SHARED_PARENT: Set for all NUMA levels above NODE.
+ */
+SD_FLAG(SD_OVERLAP, SDF_SHARED_PARENT)
+
+/*
+ * Cross-node balancing
+ *
+ * SHARED_PARENT: Set for all NUMA levels above NODE.
+ */
+SD_FLAG(SD_NUMA, SDF_SHARED_PARENT)
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 3e41c0401b5f..32f602ff37a0 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -12,19 +12,30 @@
 #ifdef CONFIG_SMP
 
 /* Generate SD flag indexes */
-#define SD_FLAG(name) __##name,
+#define SD_FLAG(name, mflags) __##name,
 enum {
 	#include <linux/sched/sd_flags.h>
 	__SD_FLAG_CNT,
 };
 #undef SD_FLAG
 /* Generate SD flag bits */
-#define SD_FLAG(name) name = 1 << __##name,
+#define SD_FLAG(name, mflags) name = 1 << __##name,
 enum {
 	#include <linux/sched/sd_flags.h>
 };
 #undef SD_FLAG
 
+#ifdef CONFIG_SCHED_DEBUG
+#define SD_FLAG(_name, mflags) [__##_name] = { .meta_flags = mflags, .name = #_name },
+static const struct {
+	unsigned int meta_flags;
+	char *name;
+} sd_flag_debug[] = {
+#include <linux/sched/sd_flags.h>
+};
+#undef SD_FLAG
+#endif
+
 #ifdef CONFIG_SCHED_SMT
 static inline int cpu_smt_flags(void)
 {
-- 
cgit v1.2.3


From 4ee4ea443a5dc3fc4d8ae338199676eae9d8ef02 Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Mon, 17 Aug 2020 12:29:53 +0100
Subject: sched/topology: Introduce SD metaflag for flags needing > 1 groups

In preparation of cleaning up the sd_degenerate*() functions, mark flags
used in sd_degenerate() with the new SDF_NEEDS_GROUPS flag. With this,
build a compile-time mask of those SD flags.

Note that sd_parent_degenerate() uses an extra flag in its mask,
SD_PREFER_SIBLING, which remains singled out for now.

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: https://lore.kernel.org/r/20200817113003.20802-8-valentin.schneider@arm.com
---
 include/linux/sched/sd_flags.h | 39 ++++++++++++++++++++++++++++-----------
 include/linux/sched/topology.h |  7 +++++++
 2 files changed, 35 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h
index c24a45b05fbb..ee5cbfc7189f 100644
--- a/include/linux/sched/sd_flags.h
+++ b/include/linux/sched/sd_flags.h
@@ -8,7 +8,7 @@
 #endif
 
 /*
- * Expected flag uses
+ * Hierarchical metaflags
  *
  * SHARED_CHILD: These flags are meant to be set from the base domain upwards.
  * If a domain has this flag set, all of its children should have it set. This
@@ -29,29 +29,42 @@
  * certain level (e.g. domain starts spanning CPUs outside of the base CPU's
  * socket).
  */
-#define SDF_SHARED_CHILD 0x1
-#define SDF_SHARED_PARENT 0x2
+#define SDF_SHARED_CHILD       0x1
+#define SDF_SHARED_PARENT      0x2
+
+/*
+ * Behavioural metaflags
+ *
+ * NEEDS_GROUPS: These flags are only relevant if the domain they are set on has
+ * more than one group. This is usually for balancing flags (load balancing
+ * involves equalizing a metric between groups), or for flags describing some
+ * shared resource (which would be shared between groups).
+ */
+#define SDF_NEEDS_GROUPS       0x4
 
 /*
  * Balance when about to become idle
  *
  * SHARED_CHILD: Set from the base domain up to cpuset.sched_relax_domain_level.
+ * NEEDS_GROUPS: Load balancing flag.
  */
-SD_FLAG(SD_BALANCE_NEWIDLE, SDF_SHARED_CHILD)
+SD_FLAG(SD_BALANCE_NEWIDLE, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
 
 /*
  * Balance on exec
  *
  * SHARED_CHILD: Set from the base domain up to the NUMA reclaim level.
+ * NEEDS_GROUPS: Load balancing flag.
  */
-SD_FLAG(SD_BALANCE_EXEC, SDF_SHARED_CHILD)
+SD_FLAG(SD_BALANCE_EXEC, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
 
 /*
  * Balance on fork, clone
  *
  * SHARED_CHILD: Set from the base domain up to the NUMA reclaim level.
+ * NEEDS_GROUPS: Load balancing flag.
  */
-SD_FLAG(SD_BALANCE_FORK, SDF_SHARED_CHILD)
+SD_FLAG(SD_BALANCE_FORK, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
 
 /*
  * Balance on wakeup
@@ -69,24 +82,28 @@ SD_FLAG(SD_WAKE_AFFINE, SDF_SHARED_CHILD)
 
 /*
  * Domain members have different CPU capacities
+ *
+ * NEEDS_GROUPS: Per-CPU capacity is asymmetric between groups.
  */
-SD_FLAG(SD_ASYM_CPUCAPACITY, 0)
+SD_FLAG(SD_ASYM_CPUCAPACITY, SDF_NEEDS_GROUPS)
 
 /*
  * Domain members share CPU capacity (i.e. SMT)
  *
  * SHARED_CHILD: Set from the base domain up until spanned CPUs no longer share
- * CPU capacity.
+ *               CPU capacity.
+ * NEEDS_GROUPS: Capacity is shared between groups.
  */
-SD_FLAG(SD_SHARE_CPUCAPACITY, SDF_SHARED_CHILD)
+SD_FLAG(SD_SHARE_CPUCAPACITY, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
 
 /*
  * Domain members share CPU package resources (i.e. caches)
  *
  * SHARED_CHILD: Set from the base domain up until spanned CPUs no longer share
- * the same cache(s).
+ *               the same cache(s).
+ * NEEDS_GROUPS: Caches are shared between groups.
  */
-SD_FLAG(SD_SHARE_PKG_RESOURCES, SDF_SHARED_CHILD)
+SD_FLAG(SD_SHARE_PKG_RESOURCES, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
 
 /*
  * Only a single load balancing instance
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 32f602ff37a0..2d59ca77103e 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -25,6 +25,13 @@ enum {
 };
 #undef SD_FLAG
 
+/* Generate a mask of SD flags with the SDF_NEEDS_GROUPS metaflag */
+#define SD_FLAG(name, mflags) (name * !!((mflags) & SDF_NEEDS_GROUPS)) |
+static const unsigned int SD_DEGENERATE_GROUPS_MASK =
+#include <linux/sched/sd_flags.h>
+0;
+#undef SD_FLAG
+
 #ifdef CONFIG_SCHED_DEBUG
 #define SD_FLAG(_name, mflags) [__##_name] = { .meta_flags = mflags, .name = #_name },
 static const struct {
-- 
cgit v1.2.3


From c200191d4c2c1aa2ffb62a984b756ac1f02dc55c Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Mon, 17 Aug 2020 12:29:56 +0100
Subject: sched/topology: Propagate SD_ASYM_CPUCAPACITY upwards

We currently set this flag *only* on domains whose topology level exactly
match the level where we detect asymmetry (as returned by
asym_cpu_capacity_level()). This is rather problematic.

Say there are two clusters in the system, one with a lone big CPU and the
other with a mix of big and LITTLE CPUs (as is allowed by DynamIQ):

  DIE [                ]
  MC  [             ][ ]
       0   1   2   3  4
       L   L   B   B  B

asym_cpu_capacity_level() will figure out that the MC level is the one
where all CPUs can see a CPU of max capacity, and we will thus set
SD_ASYM_CPUCAPACITY at MC level for all CPUs.

That lone big CPU will degenerate its MC domain, since it would be alone in
there, and will end up with just a DIE domain. Since the flag was only set
at MC, this CPU ends up not seeing any SD with the flag set, which is
broken.

Rather than clearing dflags at every topology level, clear it before
entering the topology level loop. This will properly propagate upwards
flags that are set starting from a certain level.

Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Quentin Perret <qperret@google.com>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: https://lore.kernel.org/r/20200817113003.20802-11-valentin.schneider@arm.com
---
 include/linux/sched/sd_flags.h | 4 +++-
 kernel/sched/topology.c        | 3 +--
 2 files changed, 4 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h
index ee5cbfc7189f..40ad0d5c32e3 100644
--- a/include/linux/sched/sd_flags.h
+++ b/include/linux/sched/sd_flags.h
@@ -83,9 +83,11 @@ SD_FLAG(SD_WAKE_AFFINE, SDF_SHARED_CHILD)
 /*
  * Domain members have different CPU capacities
  *
+ * SHARED_PARENT: Set from the topmost domain down to the first domain where
+ *                asymmetry is detected.
  * NEEDS_GROUPS: Per-CPU capacity is asymmetric between groups.
  */
-SD_FLAG(SD_ASYM_CPUCAPACITY, SDF_NEEDS_GROUPS)
+SD_FLAG(SD_ASYM_CPUCAPACITY, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS)
 
 /*
  * Domain members share CPU capacity (i.e. SMT)
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index c662c53736e2..f36ed96f3197 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1988,11 +1988,10 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 	/* Set up domains for CPUs specified by the cpu_map: */
 	for_each_cpu(i, cpu_map) {
 		struct sched_domain_topology_level *tl;
+		int dflags = 0;
 
 		sd = NULL;
 		for_each_sd_topology(tl) {
-			int dflags = 0;
-
 			if (tl == tl_asym) {
 				dflags |= SD_ASYM_CPUCAPACITY;
 				has_asym = true;
-- 
cgit v1.2.3


From 3a6712c7685352a5d71eaf459a4fddfc3589f018 Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Mon, 17 Aug 2020 12:29:57 +0100
Subject: sched/topology: Mark SD_PREFER_SIBLING as SDF_NEEDS_GROUPS

SD_PREFER_SIBLING is currently considered in sd_parent_degenerate() but not
in sd_degenerate(). It too hinges on load balancing, and thus won't have
any effect when set on a domain with a single group. Add it to
SD_DEGENERATE_GROUPS_MASK.

Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: https://lore.kernel.org/r/20200817113003.20802-12-valentin.schneider@arm.com
---
 include/linux/sched/sd_flags.h | 4 +++-
 kernel/sched/topology.c        | 2 +-
 2 files changed, 4 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h
index 40ad0d5c32e3..d28fe67c3098 100644
--- a/include/linux/sched/sd_flags.h
+++ b/include/linux/sched/sd_flags.h
@@ -131,8 +131,10 @@ SD_FLAG(SD_ASYM_PACKING, SDF_SHARED_CHILD)
  *
  * Set up until domains start spanning NUMA nodes. Close to being a SHARED_CHILD
  * flag, but cleared below domains with SD_ASYM_CPUCAPACITY.
+ *
+ * NEEDS_GROUPS: Load balancing flag.
  */
-SD_FLAG(SD_PREFER_SIBLING, 0)
+SD_FLAG(SD_PREFER_SIBLING, SDF_NEEDS_GROUPS)
 
 /*
  * sched_groups of this level overlap
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index f36ed96f3197..c674aaab312c 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -184,7 +184,7 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
 
 	/* Flags needing groups don't count if only 1 group in parent */
 	if (parent->groups == parent->groups->next)
-		pflags &= ~(SD_DEGENERATE_GROUPS_MASK | SD_PREFER_SIBLING);
+		pflags &= ~SD_DEGENERATE_GROUPS_MASK;
 
 	if (~cflags & pflags)
 		return 0;
-- 
cgit v1.2.3


From 94b858fea1f2246a2fb7f7af21840fd14ced028f Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Mon, 17 Aug 2020 12:29:58 +0100
Subject: sched/topology: Mark SD_BALANCE_WAKE as SDF_NEEDS_GROUPS

Even if no mainline topology uses this flag, it is a load balancing flag
just like SD_BALANCE_FORK and requires 2+ groups to have any effect.

Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: https://lore.kernel.org/r/20200817113003.20802-13-valentin.schneider@arm.com
---
 include/linux/sched/sd_flags.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h
index d28fe67c3098..729510a291b2 100644
--- a/include/linux/sched/sd_flags.h
+++ b/include/linux/sched/sd_flags.h
@@ -70,8 +70,9 @@ SD_FLAG(SD_BALANCE_FORK, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
  * Balance on wakeup
  *
  * SHARED_CHILD: Set from the base domain up to cpuset.sched_relax_domain_level.
+ * NEEDS_GROUPS: Load balancing flag.
  */
-SD_FLAG(SD_BALANCE_WAKE, SDF_SHARED_CHILD)
+SD_FLAG(SD_BALANCE_WAKE, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
 
 /*
  * Consider waking task on waking CPU.
-- 
cgit v1.2.3


From bdb7c802cc0a7e21f5223dc3ce41b7ac220c576e Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Mon, 17 Aug 2020 12:29:59 +0100
Subject: sched/topology: Mark SD_SERIALIZE as SDF_NEEDS_GROUPS

There would be no point in preserving a sched_domain with a single group
just because it has this flag set. Add it to SD_DEGENERATE_GROUPS_MASK.

Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: https://lore.kernel.org/r/20200817113003.20802-14-valentin.schneider@arm.com
---
 include/linux/sched/sd_flags.h | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h
index 729510a291b2..b7f4d80e338e 100644
--- a/include/linux/sched/sd_flags.h
+++ b/include/linux/sched/sd_flags.h
@@ -112,11 +112,12 @@ SD_FLAG(SD_SHARE_PKG_RESOURCES, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
  * Only a single load balancing instance
  *
  * SHARED_PARENT: Set for all NUMA levels above NODE. Could be set from a
- * different level upwards, but it doesn't change that if a domain has this flag
- * set, then all of its parents need to have it too (otherwise the serialization
- * doesn't make sense).
+ *                different level upwards, but it doesn't change that if a
+ *                domain has this flag set, then all of its parents need to have
+ *                it too (otherwise the serialization doesn't make sense).
+ * NEEDS_GROUPS: No point in preserving domain if it has a single group.
  */
-SD_FLAG(SD_SERIALIZE, SDF_SHARED_PARENT)
+SD_FLAG(SD_SERIALIZE, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS)
 
 /*
  * Place busy tasks earlier in the domain
-- 
cgit v1.2.3


From 33199b0143daf4778d6301f966cb914d75f122eb Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Mon, 17 Aug 2020 12:30:00 +0100
Subject: sched/topology: Mark SD_ASYM_PACKING as SDF_NEEDS_GROUPS

Being a load-balancing flag, it requires 2+ groups to have any effect.

Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: https://lore.kernel.org/r/20200817113003.20802-15-valentin.schneider@arm.com
---
 include/linux/sched/sd_flags.h | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h
index b7f4d80e338e..2998ece2c18d 100644
--- a/include/linux/sched/sd_flags.h
+++ b/include/linux/sched/sd_flags.h
@@ -123,10 +123,11 @@ SD_FLAG(SD_SERIALIZE, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS)
  * Place busy tasks earlier in the domain
  *
  * SHARED_CHILD: Usually set on the SMT level. Technically could be set further
- * up, but currently assumed to be set from the base domain upwards (see
- * update_top_cache_domain()).
+ *               up, but currently assumed to be set from the base domain
+ *               upwards (see update_top_cache_domain()).
+ * NEEDS_GROUPS: Load balancing flag.
  */
-SD_FLAG(SD_ASYM_PACKING, SDF_SHARED_CHILD)
+SD_FLAG(SD_ASYM_PACKING, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
 
 /*
  * Prefer to place tasks in a sibling domain
-- 
cgit v1.2.3


From 3551e954f5d95faf3dbc340d422da7624658c230 Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Mon, 17 Aug 2020 12:30:01 +0100
Subject: sched/topology: Mark SD_OVERLAP as SDF_NEEDS_GROUPS

A sched_domain can only have overlapping sched_groups if it has more than
one group.

Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: https://lore.kernel.org/r/20200817113003.20802-16-valentin.schneider@arm.com
---
 include/linux/sched/sd_flags.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h
index 2998ece2c18d..29af5f032861 100644
--- a/include/linux/sched/sd_flags.h
+++ b/include/linux/sched/sd_flags.h
@@ -143,8 +143,9 @@ SD_FLAG(SD_PREFER_SIBLING, SDF_NEEDS_GROUPS)
  * sched_groups of this level overlap
  *
  * SHARED_PARENT: Set for all NUMA levels above NODE.
+ * NEEDS_GROUPS: Overlaps can only exist with more than one group.
  */
-SD_FLAG(SD_OVERLAP, SDF_SHARED_PARENT)
+SD_FLAG(SD_OVERLAP, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS)
 
 /*
  * Cross-node balancing
-- 
cgit v1.2.3


From 5f4a1c4ea44728aa80be21dbf3a0469b5ca81d88 Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Mon, 17 Aug 2020 12:30:02 +0100
Subject: sched/topology: Mark SD_NUMA as SDF_NEEDS_GROUPS

There would be no point in preserving a sched_domain with a single group
just because it has this flag set. Add it to SD_DEGENERATE_GROUPS_MASK.

Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: https://lore.kernel.org/r/20200817113003.20802-17-valentin.schneider@arm.com
---
 include/linux/sched/sd_flags.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h
index 29af5f032861..34b21e971d77 100644
--- a/include/linux/sched/sd_flags.h
+++ b/include/linux/sched/sd_flags.h
@@ -151,5 +151,6 @@ SD_FLAG(SD_OVERLAP, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS)
  * Cross-node balancing
  *
  * SHARED_PARENT: Set for all NUMA levels above NODE.
+ * NEEDS_GROUPS: No point in preserving domain if it has a single group.
  */
-SD_FLAG(SD_NUMA, SDF_SHARED_PARENT)
+SD_FLAG(SD_NUMA, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS)
-- 
cgit v1.2.3


From 709c4362725abb5fa1e36fd94893a9b0d049df82 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Wed, 8 Jul 2020 16:39:29 +0000
Subject: cacheinfo: Move resctrl's get_cache_id() to the cacheinfo header file

resctrl/core.c defines get_cache_id() for use in its cpu-hotplug
callbacks. This gets the id attribute of the cache at the corresponding
level of a CPU.

Later rework means this private function needs to be shared. Move
it to the header file.

The name conflicts with a different definition in intel_cacheinfo.c,
name it get_cpu_cacheinfo_id() to show its relation with
get_cpu_cacheinfo().

Now this is visible on other architectures, check the id attribute
has actually been set.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lkml.kernel.org/r/20200708163929.2783-11-james.morse@arm.com
---
 arch/x86/kernel/cpu/resctrl/core.c | 17 ++---------------
 include/linux/cacheinfo.h          | 21 +++++++++++++++++++++
 2 files changed, 23 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index cbbd751bcc38..1c00f2f0bf0c 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -350,19 +350,6 @@ static void rdt_get_cdp_l2_config(void)
 	rdt_get_cdp_config(RDT_RESOURCE_L2, RDT_RESOURCE_L2CODE);
 }
 
-static int get_cache_id(int cpu, int level)
-{
-	struct cpu_cacheinfo *ci = get_cpu_cacheinfo(cpu);
-	int i;
-
-	for (i = 0; i < ci->num_leaves; i++) {
-		if (ci->info_list[i].level == level)
-			return ci->info_list[i].id;
-	}
-
-	return -1;
-}
-
 static void
 mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
 {
@@ -560,7 +547,7 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d)
  */
 static void domain_add_cpu(int cpu, struct rdt_resource *r)
 {
-	int id = get_cache_id(cpu, r->cache_level);
+	int id = get_cpu_cacheinfo_id(cpu, r->cache_level);
 	struct list_head *add_pos = NULL;
 	struct rdt_domain *d;
 
@@ -606,7 +593,7 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 
 static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 {
-	int id = get_cache_id(cpu, r->cache_level);
+	int id = get_cpu_cacheinfo_id(cpu, r->cache_level);
 	struct rdt_domain *d;
 
 	d = rdt_find_domain(r, id, NULL);
diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h
index 46b92cd61d0c..4f72b47973c3 100644
--- a/include/linux/cacheinfo.h
+++ b/include/linux/cacheinfo.h
@@ -3,6 +3,7 @@
 #define _LINUX_CACHEINFO_H
 
 #include <linux/bitops.h>
+#include <linux/cpu.h>
 #include <linux/cpumask.h>
 #include <linux/smp.h>
 
@@ -119,4 +120,24 @@ int acpi_find_last_cache_level(unsigned int cpu);
 
 const struct attribute_group *cache_get_priv_group(struct cacheinfo *this_leaf);
 
+/*
+ * Get the id of the cache associated with @cpu at level @level.
+ * cpuhp lock must be held.
+ */
+static inline int get_cpu_cacheinfo_id(int cpu, int level)
+{
+	struct cpu_cacheinfo *ci = get_cpu_cacheinfo(cpu);
+	int i;
+
+	for (i = 0; i < ci->num_leaves; i++) {
+		if (ci->info_list[i].level == level) {
+			if (ci->info_list[i].attributes & CACHE_ID)
+				return ci->info_list[i].id;
+			return -1;
+		}
+	}
+
+	return -1;
+}
+
 #endif /* _LINUX_CACHEINFO_H */
-- 
cgit v1.2.3


From 2024f91e965f7d7a38364874031c2132dcd11992 Mon Sep 17 00:00:00 2001
From: Christian Brauner <christian.brauner@ubuntu.com>
Date: Wed, 19 Aug 2020 13:47:15 +0200
Subject: ns: Add a common refcount into ns_common

Currently every namespace type has its own lifetime counter which is stored
in the specific namespace struct. The lifetime counters are used
identically for all namespaces types. Namespaces may of course have
additional unrelated counters and these are not altered.

This introduces a common lifetime counter into struct ns_common. The
ns_common struct encompasses information that all namespaces share. That
should include the lifetime counter since its common for all of them.

It also allows us to unify the type of the counters across all namespaces.
Most of them use refcount_t but one uses atomic_t and at least one uses
kref. Especially the last one doesn't make much sense since it's just a
wrapper around refcount_t since 2016 and actually complicates cleanup
operations by having to use container_of() to cast the correct namespace
struct out of struct ns_common.

Having the lifetime counter for the namespaces in one place reduces
maintenance cost. Not just because after switching all namespaces over we
will have removed more code than we added but also because the logic is
more easily understandable and we indicate to the user that the basic
lifetime requirements for all namespaces are currently identical.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
[christian.brauner@ubuntu.com: rewrite commit & split into two patches]
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 include/linux/ns_common.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/ns_common.h b/include/linux/ns_common.h
index 5fbc4000358f..0f1d024bd958 100644
--- a/include/linux/ns_common.h
+++ b/include/linux/ns_common.h
@@ -2,12 +2,15 @@
 #ifndef _LINUX_NS_COMMON_H
 #define _LINUX_NS_COMMON_H
 
+#include <linux/refcount.h>
+
 struct proc_ns_operations;
 
 struct ns_common {
 	atomic_long_t stashed;
 	const struct proc_ns_operations *ops;
 	unsigned int inum;
+	refcount_t count;
 };
 
 #endif
-- 
cgit v1.2.3


From 9a56493f6942c0e2df1579986128721da96e00d8 Mon Sep 17 00:00:00 2001
From: Kirill Tkhai <ktkhai@virtuozzo.com>
Date: Mon, 3 Aug 2020 13:16:21 +0300
Subject: uts: Use generic ns_common::count

Switch over uts namespaces to use the newly introduced common lifetime
counter.

Currently every namespace type has its own lifetime counter which is stored
in the specific namespace struct. The lifetime counters are used
identically for all namespaces types. Namespaces may of course have
additional unrelated counters and these are not altered.

This introduces a common lifetime counter into struct ns_common. The
ns_common struct encompasses information that all namespaces share. That
should include the lifetime counter since its common for all of them.

It also allows us to unify the type of the counters across all namespaces.
Most of them use refcount_t but one uses atomic_t and at least one uses
kref. Especially the last one doesn't make much sense since it's just a
wrapper around refcount_t since 2016 and actually complicates cleanup
operations by having to use container_of() to cast the correct namespace
struct out of struct ns_common.

Having the lifetime counter for the namespaces in one place reduces
maintenance cost. Not just because after switching all namespaces over we
will have removed more code than we added but also because the logic is
more easily understandable and we indicate to the user that the basic
lifetime requirements for all namespaces are currently identical.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Link: https://lore.kernel.org/r/159644978167.604812.1773586504374412107.stgit@localhost.localdomain
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 include/linux/utsname.h | 9 ++++-----
 init/version.c          | 2 +-
 kernel/utsname.c        | 7 ++-----
 3 files changed, 7 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/utsname.h b/include/linux/utsname.h
index 44429d9142ca..2b1737c9b244 100644
--- a/include/linux/utsname.h
+++ b/include/linux/utsname.h
@@ -4,7 +4,6 @@
 
 
 #include <linux/sched.h>
-#include <linux/kref.h>
 #include <linux/nsproxy.h>
 #include <linux/ns_common.h>
 #include <linux/err.h>
@@ -22,7 +21,6 @@ struct user_namespace;
 extern struct user_namespace init_user_ns;
 
 struct uts_namespace {
-	struct kref kref;
 	struct new_utsname name;
 	struct user_namespace *user_ns;
 	struct ucounts *ucounts;
@@ -33,16 +31,17 @@ extern struct uts_namespace init_uts_ns;
 #ifdef CONFIG_UTS_NS
 static inline void get_uts_ns(struct uts_namespace *ns)
 {
-	kref_get(&ns->kref);
+	refcount_inc(&ns->ns.count);
 }
 
 extern struct uts_namespace *copy_utsname(unsigned long flags,
 	struct user_namespace *user_ns, struct uts_namespace *old_ns);
-extern void free_uts_ns(struct kref *kref);
+extern void free_uts_ns(struct uts_namespace *ns);
 
 static inline void put_uts_ns(struct uts_namespace *ns)
 {
-	kref_put(&ns->kref, free_uts_ns);
+	if (refcount_dec_and_test(&ns->ns.count))
+		free_uts_ns(ns);
 }
 
 void uts_ns_init(void);
diff --git a/init/version.c b/init/version.c
index cba341161b58..80d2b7566b39 100644
--- a/init/version.c
+++ b/init/version.c
@@ -25,7 +25,7 @@ int version_string(LINUX_VERSION_CODE);
 #endif
 
 struct uts_namespace init_uts_ns = {
-	.kref = KREF_INIT(2),
+	.ns.count = REFCOUNT_INIT(2),
 	.name = {
 		.sysname	= UTS_SYSNAME,
 		.nodename	= UTS_NODENAME,
diff --git a/kernel/utsname.c b/kernel/utsname.c
index e488d0e2ab45..b1ac3ca870f2 100644
--- a/kernel/utsname.c
+++ b/kernel/utsname.c
@@ -33,7 +33,7 @@ static struct uts_namespace *create_uts_ns(void)
 
 	uts_ns = kmem_cache_alloc(uts_ns_cache, GFP_KERNEL);
 	if (uts_ns)
-		kref_init(&uts_ns->kref);
+		refcount_set(&uts_ns->ns.count, 1);
 	return uts_ns;
 }
 
@@ -103,11 +103,8 @@ struct uts_namespace *copy_utsname(unsigned long flags,
 	return new_ns;
 }
 
-void free_uts_ns(struct kref *kref)
+void free_uts_ns(struct uts_namespace *ns)
 {
-	struct uts_namespace *ns;
-
-	ns = container_of(kref, struct uts_namespace, kref);
 	dec_uts_namespaces(ns->ucounts);
 	put_user_ns(ns->user_ns);
 	ns_free_inum(&ns->ns);
-- 
cgit v1.2.3


From 137ec390fad41928307216ea9f91acf5cf6f4204 Mon Sep 17 00:00:00 2001
From: Kirill Tkhai <ktkhai@virtuozzo.com>
Date: Mon, 3 Aug 2020 13:16:27 +0300
Subject: ipc: Use generic ns_common::count

Switch over ipc namespaces to use the newly introduced common lifetime
counter.

Currently every namespace type has its own lifetime counter which is stored
in the specific namespace struct. The lifetime counters are used
identically for all namespaces types. Namespaces may of course have
additional unrelated counters and these are not altered.

This introduces a common lifetime counter into struct ns_common. The
ns_common struct encompasses information that all namespaces share. That
should include the lifetime counter since its common for all of them.

It also allows us to unify the type of the counters across all namespaces.
Most of them use refcount_t but one uses atomic_t and at least one uses
kref. Especially the last one doesn't make much sense since it's just a
wrapper around refcount_t since 2016 and actually complicates cleanup
operations by having to use container_of() to cast the correct namespace
struct out of struct ns_common.

Having the lifetime counter for the namespaces in one place reduces
maintenance cost. Not just because after switching all namespaces over we
will have removed more code than we added but also because the logic is
more easily understandable and we indicate to the user that the basic
lifetime requirements for all namespaces are currently identical.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Link: https://lore.kernel.org/r/159644978697.604812.16592754423881032385.stgit@localhost.localdomain
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 include/linux/ipc_namespace.h | 3 +--
 ipc/msgutil.c                 | 2 +-
 ipc/namespace.c               | 4 ++--
 3 files changed, 4 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h
index a06a78c67f19..05e22770af51 100644
--- a/include/linux/ipc_namespace.h
+++ b/include/linux/ipc_namespace.h
@@ -27,7 +27,6 @@ struct ipc_ids {
 };
 
 struct ipc_namespace {
-	refcount_t	count;
 	struct ipc_ids	ids[3];
 
 	int		sem_ctls[4];
@@ -128,7 +127,7 @@ extern struct ipc_namespace *copy_ipcs(unsigned long flags,
 static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns)
 {
 	if (ns)
-		refcount_inc(&ns->count);
+		refcount_inc(&ns->ns.count);
 	return ns;
 }
 
diff --git a/ipc/msgutil.c b/ipc/msgutil.c
index 3149b4a379de..d0a0e877cadd 100644
--- a/ipc/msgutil.c
+++ b/ipc/msgutil.c
@@ -26,7 +26,7 @@ DEFINE_SPINLOCK(mq_lock);
  * and not CONFIG_IPC_NS.
  */
 struct ipc_namespace init_ipc_ns = {
-	.count		= REFCOUNT_INIT(1),
+	.ns.count = REFCOUNT_INIT(1),
 	.user_ns = &init_user_ns,
 	.ns.inum = PROC_IPC_INIT_INO,
 #ifdef CONFIG_IPC_NS
diff --git a/ipc/namespace.c b/ipc/namespace.c
index 24e7b45320f7..7bd0766ddc3b 100644
--- a/ipc/namespace.c
+++ b/ipc/namespace.c
@@ -51,7 +51,7 @@ static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns,
 		goto fail_free;
 	ns->ns.ops = &ipcns_operations;
 
-	refcount_set(&ns->count, 1);
+	refcount_set(&ns->ns.count, 1);
 	ns->user_ns = get_user_ns(user_ns);
 	ns->ucounts = ucounts;
 
@@ -164,7 +164,7 @@ static DECLARE_WORK(free_ipc_work, free_ipc);
  */
 void put_ipc_ns(struct ipc_namespace *ns)
 {
-	if (refcount_dec_and_lock(&ns->count, &mq_lock)) {
+	if (refcount_dec_and_lock(&ns->ns.count, &mq_lock)) {
 		mq_clear_sbinfo(ns);
 		spin_unlock(&mq_lock);
 
-- 
cgit v1.2.3


From 8eb71d95f34a009cc22084e05e78eb9686f7ea28 Mon Sep 17 00:00:00 2001
From: Kirill Tkhai <ktkhai@virtuozzo.com>
Date: Mon, 3 Aug 2020 13:16:32 +0300
Subject: pid: Use generic ns_common::count

Switch over pid namespaces to use the newly introduced common lifetime
counter.

Currently every namespace type has its own lifetime counter which is stored
in the specific namespace struct. The lifetime counters are used
identically for all namespaces types. Namespaces may of course have
additional unrelated counters and these are not altered.

This introduces a common lifetime counter into struct ns_common. The
ns_common struct encompasses information that all namespaces share. That
should include the lifetime counter since its common for all of them.

It also allows us to unify the type of the counters across all namespaces.
Most of them use refcount_t but one uses atomic_t and at least one uses
kref. Especially the last one doesn't make much sense since it's just a
wrapper around refcount_t since 2016 and actually complicates cleanup
operations by having to use container_of() to cast the correct namespace
struct out of struct ns_common.

Having the lifetime counter for the namespaces in one place reduces
maintenance cost. Not just because after switching all namespaces over we
will have removed more code than we added but also because the logic is
more easily understandable and we indicate to the user that the basic
lifetime requirements for all namespaces are currently identical.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Link: https://lore.kernel.org/r/159644979226.604812.7512601754841882036.stgit@localhost.localdomain
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 include/linux/pid_namespace.h |  4 +---
 kernel/pid.c                  |  2 +-
 kernel/pid_namespace.c        | 13 +++----------
 3 files changed, 5 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h
index 5a5cb45ac57e..7c7e627503d2 100644
--- a/include/linux/pid_namespace.h
+++ b/include/linux/pid_namespace.h
@@ -8,7 +8,6 @@
 #include <linux/workqueue.h>
 #include <linux/threads.h>
 #include <linux/nsproxy.h>
-#include <linux/kref.h>
 #include <linux/ns_common.h>
 #include <linux/idr.h>
 
@@ -18,7 +17,6 @@
 struct fs_pin;
 
 struct pid_namespace {
-	struct kref kref;
 	struct idr idr;
 	struct rcu_head rcu;
 	unsigned int pid_allocated;
@@ -43,7 +41,7 @@ extern struct pid_namespace init_pid_ns;
 static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns)
 {
 	if (ns != &init_pid_ns)
-		kref_get(&ns->kref);
+		refcount_inc(&ns->ns.count);
 	return ns;
 }
 
diff --git a/kernel/pid.c b/kernel/pid.c
index b2562a7ce525..2b97bedc1d9f 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -72,7 +72,7 @@ int pid_max_max = PID_MAX_LIMIT;
  * the scheme scales to up to 4 million PIDs, runtime.
  */
 struct pid_namespace init_pid_ns = {
-	.kref = KREF_INIT(2),
+	.ns.count = REFCOUNT_INIT(2),
 	.idr = IDR_INIT(init_pid_ns.idr),
 	.pid_allocated = PIDNS_ADDING,
 	.level = 0,
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index ac135bd600eb..166a91cdd387 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -102,7 +102,7 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns
 		goto out_free_idr;
 	ns->ns.ops = &pidns_operations;
 
-	kref_init(&ns->kref);
+	refcount_set(&ns->ns.count, 1);
 	ns->level = level;
 	ns->parent = get_pid_ns(parent_pid_ns);
 	ns->user_ns = get_user_ns(user_ns);
@@ -148,22 +148,15 @@ struct pid_namespace *copy_pid_ns(unsigned long flags,
 	return create_pid_namespace(user_ns, old_ns);
 }
 
-static void free_pid_ns(struct kref *kref)
-{
-	struct pid_namespace *ns;
-
-	ns = container_of(kref, struct pid_namespace, kref);
-	destroy_pid_namespace(ns);
-}
-
 void put_pid_ns(struct pid_namespace *ns)
 {
 	struct pid_namespace *parent;
 
 	while (ns != &init_pid_ns) {
 		parent = ns->parent;
-		if (!kref_put(&ns->kref, free_pid_ns))
+		if (!refcount_dec_and_test(&ns->ns.count))
 			break;
+		destroy_pid_namespace(ns);
 		ns = parent;
 	}
 }
-- 
cgit v1.2.3


From 265cbd62e034cb09a9da7cbff9072c8082f8df65 Mon Sep 17 00:00:00 2001
From: Kirill Tkhai <ktkhai@virtuozzo.com>
Date: Mon, 3 Aug 2020 13:16:37 +0300
Subject: user: Use generic ns_common::count

Switch over user namespaces to use the newly introduced common lifetime
counter.

Currently every namespace type has its own lifetime counter which is stored
in the specific namespace struct. The lifetime counters are used
identically for all namespaces types. Namespaces may of course have
additional unrelated counters and these are not altered.

This introduces a common lifetime counter into struct ns_common. The
ns_common struct encompasses information that all namespaces share. That
should include the lifetime counter since its common for all of them.

It also allows us to unify the type of the counters across all namespaces.
Most of them use refcount_t but one uses atomic_t and at least one uses
kref. Especially the last one doesn't make much sense since it's just a
wrapper around refcount_t since 2016 and actually complicates cleanup
operations by having to use container_of() to cast the correct namespace
struct out of struct ns_common.

Having the lifetime counter for the namespaces in one place reduces
maintenance cost. Not just because after switching all namespaces over we
will have removed more code than we added but also because the logic is
more easily understandable and we indicate to the user that the basic
lifetime requirements for all namespaces are currently identical.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Link: https://lore.kernel.org/r/159644979754.604812.601625186726406922.stgit@localhost.localdomain
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 include/linux/user_namespace.h | 5 ++---
 kernel/user.c                  | 2 +-
 kernel/user_namespace.c        | 4 ++--
 3 files changed, 5 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index 6ef1c7109fc4..64cf8ebdc4ec 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -57,7 +57,6 @@ struct user_namespace {
 	struct uid_gid_map	uid_map;
 	struct uid_gid_map	gid_map;
 	struct uid_gid_map	projid_map;
-	atomic_t		count;
 	struct user_namespace	*parent;
 	int			level;
 	kuid_t			owner;
@@ -109,7 +108,7 @@ void dec_ucount(struct ucounts *ucounts, enum ucount_type type);
 static inline struct user_namespace *get_user_ns(struct user_namespace *ns)
 {
 	if (ns)
-		atomic_inc(&ns->count);
+		refcount_inc(&ns->ns.count);
 	return ns;
 }
 
@@ -119,7 +118,7 @@ extern void __put_user_ns(struct user_namespace *ns);
 
 static inline void put_user_ns(struct user_namespace *ns)
 {
-	if (ns && atomic_dec_and_test(&ns->count))
+	if (ns && refcount_dec_and_test(&ns->ns.count))
 		__put_user_ns(ns);
 }
 
diff --git a/kernel/user.c b/kernel/user.c
index b1635d94a1f2..a2478cddf536 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -55,7 +55,7 @@ struct user_namespace init_user_ns = {
 			},
 		},
 	},
-	.count = ATOMIC_INIT(3),
+	.ns.count = REFCOUNT_INIT(3),
 	.owner = GLOBAL_ROOT_UID,
 	.group = GLOBAL_ROOT_GID,
 	.ns.inum = PROC_USER_INIT_INO,
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 87804e0371fe..7c2bbe8f3e45 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -111,7 +111,7 @@ int create_user_ns(struct cred *new)
 		goto fail_free;
 	ns->ns.ops = &userns_operations;
 
-	atomic_set(&ns->count, 1);
+	refcount_set(&ns->ns.count, 1);
 	/* Leave the new->user_ns reference with the new user namespace. */
 	ns->parent = parent_ns;
 	ns->level = parent_ns->level + 1;
@@ -197,7 +197,7 @@ static void free_user_ns(struct work_struct *work)
 		kmem_cache_free(user_ns_cachep, ns);
 		dec_user_namespaces(ucounts);
 		ns = parent;
-	} while (atomic_dec_and_test(&parent->count));
+	} while (refcount_dec_and_test(&parent->ns.count));
 }
 
 void __put_user_ns(struct user_namespace *ns)
-- 
cgit v1.2.3


From f387882d8d3eda7c7b13e330c73907035569ce4a Mon Sep 17 00:00:00 2001
From: Kirill Tkhai <ktkhai@virtuozzo.com>
Date: Mon, 3 Aug 2020 13:16:50 +0300
Subject: cgroup: Use generic ns_common::count

Switch over cgroup namespaces to use the newly introduced common lifetime
counter.

Currently every namespace type has its own lifetime counter which is stored
in the specific namespace struct. The lifetime counters are used
identically for all namespaces types. Namespaces may of course have
additional unrelated counters and these are not altered.

This introduces a common lifetime counter into struct ns_common. The
ns_common struct encompasses information that all namespaces share. That
should include the lifetime counter since its common for all of them.

It also allows us to unify the type of the counters across all namespaces.
Most of them use refcount_t but one uses atomic_t and at least one uses
kref. Especially the last one doesn't make much sense since it's just a
wrapper around refcount_t since 2016 and actually complicates cleanup
operations by having to use container_of() to cast the correct namespace
struct out of struct ns_common.

Having the lifetime counter for the namespaces in one place reduces
maintenance cost. Not just because after switching all namespaces over we
will have removed more code than we added but also because the logic is
more easily understandable and we indicate to the user that the basic
lifetime requirements for all namespaces are currently identical.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Link: https://lore.kernel.org/r/159644980994.604812.383801057081594972.stgit@localhost.localdomain
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 include/linux/cgroup.h    | 5 ++---
 kernel/cgroup/cgroup.c    | 2 +-
 kernel/cgroup/namespace.c | 2 +-
 3 files changed, 4 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 618838c48313..451c2d26a5db 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -854,7 +854,6 @@ static inline void cgroup_sk_free(struct sock_cgroup_data *skcd) {}
 #endif	/* CONFIG_CGROUP_DATA */
 
 struct cgroup_namespace {
-	refcount_t		count;
 	struct ns_common	ns;
 	struct user_namespace	*user_ns;
 	struct ucounts		*ucounts;
@@ -889,12 +888,12 @@ copy_cgroup_ns(unsigned long flags, struct user_namespace *user_ns,
 static inline void get_cgroup_ns(struct cgroup_namespace *ns)
 {
 	if (ns)
-		refcount_inc(&ns->count);
+		refcount_inc(&ns->ns.count);
 }
 
 static inline void put_cgroup_ns(struct cgroup_namespace *ns)
 {
-	if (ns && refcount_dec_and_test(&ns->count))
+	if (ns && refcount_dec_and_test(&ns->ns.count))
 		free_cgroup_ns(ns);
 }
 
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index dd247747ec14..22e466926853 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -199,7 +199,7 @@ static u16 have_canfork_callback __read_mostly;
 
 /* cgroup namespace for init task */
 struct cgroup_namespace init_cgroup_ns = {
-	.count		= REFCOUNT_INIT(2),
+	.ns.count	= REFCOUNT_INIT(2),
 	.user_ns	= &init_user_ns,
 	.ns.ops		= &cgroupns_operations,
 	.ns.inum	= PROC_CGROUP_INIT_INO,
diff --git a/kernel/cgroup/namespace.c b/kernel/cgroup/namespace.c
index 812a61afd538..f5e8828c109c 100644
--- a/kernel/cgroup/namespace.c
+++ b/kernel/cgroup/namespace.c
@@ -32,7 +32,7 @@ static struct cgroup_namespace *alloc_cgroup_ns(void)
 		kfree(new_ns);
 		return ERR_PTR(ret);
 	}
-	refcount_set(&new_ns->count, 1);
+	refcount_set(&new_ns->ns.count, 1);
 	new_ns->ns.ops = &cgroupns_operations;
 	return new_ns;
 }
-- 
cgit v1.2.3


From 28c41efd08bf97fc64f75304035ee3943995b68e Mon Sep 17 00:00:00 2001
From: Kirill Tkhai <ktkhai@virtuozzo.com>
Date: Mon, 3 Aug 2020 13:17:00 +0300
Subject: time: Use generic ns_common::count

Switch over time namespaces to use the newly introduced common lifetime
counter.

Currently every namespace type has its own lifetime counter which is stored
in the specific namespace struct. The lifetime counters are used
identically for all namespaces types. Namespaces may of course have
additional unrelated counters and these are not altered.

This introduces a common lifetime counter into struct ns_common. The
ns_common struct encompasses information that all namespaces share. That
should include the lifetime counter since its common for all of them.

It also allows us to unify the type of the counters across all namespaces.
Most of them use refcount_t but one uses atomic_t and at least one uses
kref. Especially the last one doesn't make much sense since it's just a
wrapper around refcount_t since 2016 and actually complicates cleanup
operations by having to use container_of() to cast the correct namespace
struct out of struct ns_common.

Having the lifetime counter for the namespaces in one place reduces
maintenance cost. Not just because after switching all namespaces over we
will have removed more code than we added but also because the logic is
more easily understandable and we indicate to the user that the basic
lifetime requirements for all namespaces are currently identical.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Link: https://lore.kernel.org/r/159644982033.604812.9406853013011123238.stgit@localhost.localdomain
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 include/linux/time_namespace.h | 9 ++++-----
 kernel/time/namespace.c        | 9 +++------
 2 files changed, 7 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/time_namespace.h b/include/linux/time_namespace.h
index 5b6031385db0..a51ffc089219 100644
--- a/include/linux/time_namespace.h
+++ b/include/linux/time_namespace.h
@@ -4,7 +4,6 @@
 
 
 #include <linux/sched.h>
-#include <linux/kref.h>
 #include <linux/nsproxy.h>
 #include <linux/ns_common.h>
 #include <linux/err.h>
@@ -18,7 +17,6 @@ struct timens_offsets {
 };
 
 struct time_namespace {
-	struct kref		kref;
 	struct user_namespace	*user_ns;
 	struct ucounts		*ucounts;
 	struct ns_common	ns;
@@ -37,20 +35,21 @@ extern void timens_commit(struct task_struct *tsk, struct time_namespace *ns);
 
 static inline struct time_namespace *get_time_ns(struct time_namespace *ns)
 {
-	kref_get(&ns->kref);
+	refcount_inc(&ns->ns.count);
 	return ns;
 }
 
 struct time_namespace *copy_time_ns(unsigned long flags,
 				    struct user_namespace *user_ns,
 				    struct time_namespace *old_ns);
-void free_time_ns(struct kref *kref);
+void free_time_ns(struct time_namespace *ns);
 int timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk);
 struct vdso_data *arch_get_vdso_data(void *vvar_page);
 
 static inline void put_time_ns(struct time_namespace *ns)
 {
-	kref_put(&ns->kref, free_time_ns);
+	if (refcount_dec_and_test(&ns->ns.count))
+		free_time_ns(ns);
 }
 
 void proc_timens_show_offsets(struct task_struct *p, struct seq_file *m);
diff --git a/kernel/time/namespace.c b/kernel/time/namespace.c
index afc65e6be33e..c4c829eb3511 100644
--- a/kernel/time/namespace.c
+++ b/kernel/time/namespace.c
@@ -92,7 +92,7 @@ static struct time_namespace *clone_time_ns(struct user_namespace *user_ns,
 	if (!ns)
 		goto fail_dec;
 
-	kref_init(&ns->kref);
+	refcount_set(&ns->ns.count, 1);
 
 	ns->vvar_page = alloc_page(GFP_KERNEL | __GFP_ZERO);
 	if (!ns->vvar_page)
@@ -226,11 +226,8 @@ out:
 	mutex_unlock(&offset_lock);
 }
 
-void free_time_ns(struct kref *kref)
+void free_time_ns(struct time_namespace *ns)
 {
-	struct time_namespace *ns;
-
-	ns = container_of(kref, struct time_namespace, kref);
 	dec_time_namespaces(ns->ucounts);
 	put_user_ns(ns->user_ns);
 	ns_free_inum(&ns->ns);
@@ -464,7 +461,7 @@ const struct proc_ns_operations timens_for_children_operations = {
 };
 
 struct time_namespace init_time_ns = {
-	.kref		= KREF_INIT(3),
+	.ns.count	= REFCOUNT_INIT(3),
 	.user_ns	= &init_user_ns,
 	.ns.inum	= PROC_TIME_INIT_INO,
 	.ns.ops		= &timens_operations,
-- 
cgit v1.2.3


From b84e23f5135103c45022b0e4a4ed2459d5398a7e Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Thu, 6 Aug 2020 20:20:23 +0200
Subject: ARM: s3c24xx: pass pointer to clk driver via platform data

Passing pointers directly as platform data is fragile and undocumented.
Better to create a platform data structure which explicitly documents
what is passed to the driver.

Suggested-by: Tomasz Figa <tomasz.figa@gmail.com>
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Stephen Boyd <sboyd@kernel.org>
Link: https://lore.kernel.org/r/20200806182059.2431-6-krzk@kernel.org
---
 MAINTAINERS                               |  1 +
 arch/arm/mach-s3c24xx/common.c            |  7 ++++++-
 drivers/clk/samsung/clk-s3c2410-dclk.c    |  7 ++++++-
 include/linux/platform_data/clk-s3c2410.h | 19 +++++++++++++++++++
 4 files changed, 32 insertions(+), 2 deletions(-)
 create mode 100644 include/linux/platform_data/clk-s3c2410.h

(limited to 'include/linux')

diff --git a/MAINTAINERS b/MAINTAINERS
index d6abe0cc1a5d..45906c58ff4a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15305,6 +15305,7 @@ F:	Documentation/devicetree/bindings/clock/samsung,s5p*
 F:	drivers/clk/samsung/
 F:	include/dt-bindings/clock/exynos*.h
 F:	include/linux/clk/samsung.h
+F:	include/linux/platform_data/clk-s3c2410.h
 
 SAMSUNG SPI DRIVERS
 M:	Kukjin Kim <kgene@kernel.org>
diff --git a/arch/arm/mach-s3c24xx/common.c b/arch/arm/mach-s3c24xx/common.c
index 222238e8acbb..c476a673d07f 100644
--- a/arch/arm/mach-s3c24xx/common.c
+++ b/arch/arm/mach-s3c24xx/common.c
@@ -17,6 +17,7 @@
 #include <linux/platform_device.h>
 #include <linux/delay.h>
 #include <linux/io.h>
+#include <linux/platform_data/clk-s3c2410.h>
 #include <linux/platform_data/dma-s3c24xx.h>
 #include <linux/dmaengine.h>
 #include <linux/clk/samsung.h>
@@ -663,13 +664,17 @@ static struct resource s3c2410_dclk_resource[] = {
 	[0] = DEFINE_RES_MEM(0x56000084, 0x4),
 };
 
+static struct s3c2410_clk_platform_data s3c_clk_platform_data = {
+	.modify_misccr = s3c2410_modify_misccr,
+};
+
 struct platform_device s3c2410_device_dclk = {
 	.name		= "s3c2410-dclk",
 	.id		= 0,
 	.num_resources	= ARRAY_SIZE(s3c2410_dclk_resource),
 	.resource	= s3c2410_dclk_resource,
 	.dev		= {
-		.platform_data = s3c2410_modify_misccr,
+		.platform_data = &s3c_clk_platform_data,
 	},
 };
 #endif
diff --git a/drivers/clk/samsung/clk-s3c2410-dclk.c b/drivers/clk/samsung/clk-s3c2410-dclk.c
index 3e0f23e8ec21..f5e0a6ba2d12 100644
--- a/drivers/clk/samsung/clk-s3c2410-dclk.c
+++ b/drivers/clk/samsung/clk-s3c2410-dclk.c
@@ -11,6 +11,7 @@
 #include <linux/clk-provider.h>
 #include <linux/io.h>
 #include <linux/platform_device.h>
+#include <linux/platform_data/clk-s3c2410.h>
 #include <linux/module.h>
 #include "clk.h"
 
@@ -89,10 +90,14 @@ static struct clk_hw *s3c24xx_register_clkout(struct device *dev,
 		const char *name, const char **parent_names, u8 num_parents,
 		u8 shift, u32 mask)
 {
+	struct s3c2410_clk_platform_data *pdata = dev_get_platdata(dev);
 	struct s3c24xx_clkout *clkout;
 	struct clk_init_data init;
 	int ret;
 
+	if (!pdata)
+		return ERR_PTR(-EINVAL);
+
 	/* allocate the clkout */
 	clkout = kzalloc(sizeof(*clkout), GFP_KERNEL);
 	if (!clkout)
@@ -107,7 +112,7 @@ static struct clk_hw *s3c24xx_register_clkout(struct device *dev,
 	clkout->shift = shift;
 	clkout->mask = mask;
 	clkout->hw.init = &init;
-	clkout->modify_misccr = dev->platform_data;
+	clkout->modify_misccr = pdata->modify_misccr;
 
 	ret = clk_hw_register(dev, &clkout->hw);
 	if (ret)
diff --git a/include/linux/platform_data/clk-s3c2410.h b/include/linux/platform_data/clk-s3c2410.h
new file mode 100644
index 000000000000..7eb1cfa5409b
--- /dev/null
+++ b/include/linux/platform_data/clk-s3c2410.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2020 Krzysztof Kozlowski <krzk@kernel.org>
+ */
+
+#ifndef __LINUX_PLATFORM_DATA_CLK_S3C2410_H_
+#define __LINUX_PLATFORM_DATA_CLK_S3C2410_H_
+
+/**
+ * struct s3c2410_clk_platform_data - platform data for S3C2410 clock driver
+ *
+ * @modify_misccr: Function to modify the MISCCR and return the new value
+ */
+struct s3c2410_clk_platform_data {
+	unsigned int (*modify_misccr)(unsigned int clr, unsigned int chg);
+};
+
+#endif /* __LINUX_PLATFORM_DATA_CLK_S3C2410_H_ */
+
-- 
cgit v1.2.3


From 5f745424761a2a49762625e8616417a8e7694228 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 6 Aug 2020 20:20:26 +0200
Subject: usb: gadget: s3c-hsudc: remove platform header dependency

There is no real phy driver, so s3c-hsudc just pokes the registers
itself. Improve this a little by making it a platform data callback
like we do for gpios.

There is only one board using this driver, and it's unlikely
that another would be added, so this is a minimal workaround.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20200806182059.2431-9-krzk@kernel.org
[krzk: Include regs-s3c2443-clock.h in ifdef to fixup build on s3c6400]
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
---
 .../mach-s3c24xx/include/mach/regs-s3c2443-clock.h | 49 +++++++++++++++++++
 arch/arm/plat-samsung/devs.c                       |  6 +++
 drivers/usb/gadget/udc/s3c-hsudc.c                 | 55 ++--------------------
 include/linux/platform_data/s3c-hsudc.h            |  2 +
 4 files changed, 61 insertions(+), 51 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/mach-s3c24xx/include/mach/regs-s3c2443-clock.h b/arch/arm/mach-s3c24xx/include/mach/regs-s3c2443-clock.h
index 6bf924612b06..682759549e63 100644
--- a/arch/arm/mach-s3c24xx/include/mach/regs-s3c2443-clock.h
+++ b/arch/arm/mach-s3c24xx/include/mach/regs-s3c2443-clock.h
@@ -10,6 +10,8 @@
 #ifndef __ASM_ARM_REGS_S3C2443_CLOCK
 #define __ASM_ARM_REGS_S3C2443_CLOCK
 
+#include <linux/delay.h>
+
 #define S3C2443_CLKREG(x)		((x) + S3C24XX_VA_CLKPWR)
 
 #define S3C2443_PLLCON_MDIVSHIFT	16
@@ -184,5 +186,52 @@ s3c2443_get_epll(unsigned int pllval, unsigned int baseclk)
 	return (unsigned int)fvco;
 }
 
+static inline void s3c_hsudc_init_phy(void)
+{
+	u32 cfg;
+
+	cfg = readl(S3C2443_PWRCFG) | S3C2443_PWRCFG_USBPHY;
+	writel(cfg, S3C2443_PWRCFG);
+
+	cfg = readl(S3C2443_URSTCON);
+	cfg |= (S3C2443_URSTCON_FUNCRST | S3C2443_URSTCON_PHYRST);
+	writel(cfg, S3C2443_URSTCON);
+	mdelay(1);
+
+	cfg = readl(S3C2443_URSTCON);
+	cfg &= ~(S3C2443_URSTCON_FUNCRST | S3C2443_URSTCON_PHYRST);
+	writel(cfg, S3C2443_URSTCON);
+
+	cfg = readl(S3C2443_PHYCTRL);
+	cfg &= ~(S3C2443_PHYCTRL_CLKSEL | S3C2443_PHYCTRL_DSPORT);
+	cfg |= (S3C2443_PHYCTRL_EXTCLK | S3C2443_PHYCTRL_PLLSEL);
+	writel(cfg, S3C2443_PHYCTRL);
+
+	cfg = readl(S3C2443_PHYPWR);
+	cfg &= ~(S3C2443_PHYPWR_FSUSPEND | S3C2443_PHYPWR_PLL_PWRDN |
+		S3C2443_PHYPWR_XO_ON | S3C2443_PHYPWR_PLL_REFCLK |
+		S3C2443_PHYPWR_ANALOG_PD);
+	cfg |= S3C2443_PHYPWR_COMMON_ON;
+	writel(cfg, S3C2443_PHYPWR);
+
+	cfg = readl(S3C2443_UCLKCON);
+	cfg |= (S3C2443_UCLKCON_DETECT_VBUS | S3C2443_UCLKCON_FUNC_CLKEN |
+		S3C2443_UCLKCON_TCLKEN);
+	writel(cfg, S3C2443_UCLKCON);
+}
+
+static inline void s3c_hsudc_uninit_phy(void)
+{
+	u32 cfg;
+
+	cfg = readl(S3C2443_PWRCFG) & ~S3C2443_PWRCFG_USBPHY;
+	writel(cfg, S3C2443_PWRCFG);
+
+	writel(S3C2443_PHYPWR_FSUSPEND, S3C2443_PHYPWR);
+
+	cfg = readl(S3C2443_UCLKCON) & ~S3C2443_UCLKCON_FUNC_CLKEN;
+	writel(cfg, S3C2443_UCLKCON);
+}
+
 #endif /*  __ASM_ARM_REGS_S3C2443_CLOCK */
 
diff --git a/arch/arm/plat-samsung/devs.c b/arch/arm/plat-samsung/devs.c
index 2ed3ef604a25..0607d2984841 100644
--- a/arch/arm/plat-samsung/devs.c
+++ b/arch/arm/plat-samsung/devs.c
@@ -40,6 +40,10 @@
 #include <mach/irqs.h>
 #include <mach/map.h>
 
+#ifdef CONFIG_PLAT_S3C24XX
+#include <mach/regs-s3c2443-clock.h>
+#endif /* CONFIG_PLAT_S3C24XX */
+
 #include <plat/cpu.h>
 #include <plat/devs.h>
 #include <plat/adc.h>
@@ -1037,6 +1041,8 @@ struct platform_device s3c_device_usb_hsudc = {
 void __init s3c24xx_hsudc_set_platdata(struct s3c24xx_hsudc_platdata *pd)
 {
 	s3c_set_platdata(pd, sizeof(*pd), &s3c_device_usb_hsudc);
+	pd->phy_init = s3c_hsudc_init_phy;
+	pd->phy_uninit = s3c_hsudc_uninit_phy;
 }
 #endif /* CONFIG_PLAT_S3C24XX */
 
diff --git a/drivers/usb/gadget/udc/s3c-hsudc.c b/drivers/usb/gadget/udc/s3c-hsudc.c
index aaca1b0a2f59..7bd5182ce3ef 100644
--- a/drivers/usb/gadget/udc/s3c-hsudc.c
+++ b/drivers/usb/gadget/udc/s3c-hsudc.c
@@ -30,8 +30,6 @@
 #include <linux/regulator/consumer.h>
 #include <linux/pm_runtime.h>
 
-#include <mach/regs-s3c2443-clock.h>
-
 #define S3C_HSUDC_REG(x)	(x)
 
 /* Non-Indexed Registers */
@@ -186,53 +184,6 @@ static inline void __orr32(void __iomem *ptr, u32 val)
 	writel(readl(ptr) | val, ptr);
 }
 
-static void s3c_hsudc_init_phy(void)
-{
-	u32 cfg;
-
-	cfg = readl(S3C2443_PWRCFG) | S3C2443_PWRCFG_USBPHY;
-	writel(cfg, S3C2443_PWRCFG);
-
-	cfg = readl(S3C2443_URSTCON);
-	cfg |= (S3C2443_URSTCON_FUNCRST | S3C2443_URSTCON_PHYRST);
-	writel(cfg, S3C2443_URSTCON);
-	mdelay(1);
-
-	cfg = readl(S3C2443_URSTCON);
-	cfg &= ~(S3C2443_URSTCON_FUNCRST | S3C2443_URSTCON_PHYRST);
-	writel(cfg, S3C2443_URSTCON);
-
-	cfg = readl(S3C2443_PHYCTRL);
-	cfg &= ~(S3C2443_PHYCTRL_CLKSEL | S3C2443_PHYCTRL_DSPORT);
-	cfg |= (S3C2443_PHYCTRL_EXTCLK | S3C2443_PHYCTRL_PLLSEL);
-	writel(cfg, S3C2443_PHYCTRL);
-
-	cfg = readl(S3C2443_PHYPWR);
-	cfg &= ~(S3C2443_PHYPWR_FSUSPEND | S3C2443_PHYPWR_PLL_PWRDN |
-		S3C2443_PHYPWR_XO_ON | S3C2443_PHYPWR_PLL_REFCLK |
-		S3C2443_PHYPWR_ANALOG_PD);
-	cfg |= S3C2443_PHYPWR_COMMON_ON;
-	writel(cfg, S3C2443_PHYPWR);
-
-	cfg = readl(S3C2443_UCLKCON);
-	cfg |= (S3C2443_UCLKCON_DETECT_VBUS | S3C2443_UCLKCON_FUNC_CLKEN |
-		S3C2443_UCLKCON_TCLKEN);
-	writel(cfg, S3C2443_UCLKCON);
-}
-
-static void s3c_hsudc_uninit_phy(void)
-{
-	u32 cfg;
-
-	cfg = readl(S3C2443_PWRCFG) & ~S3C2443_PWRCFG_USBPHY;
-	writel(cfg, S3C2443_PWRCFG);
-
-	writel(S3C2443_PHYPWR_FSUSPEND, S3C2443_PHYPWR);
-
-	cfg = readl(S3C2443_UCLKCON) & ~S3C2443_UCLKCON_FUNC_CLKEN;
-	writel(cfg, S3C2443_UCLKCON);
-}
-
 /**
  * s3c_hsudc_complete_request - Complete a transfer request.
  * @hsep: Endpoint to which the request belongs.
@@ -1188,7 +1139,8 @@ static int s3c_hsudc_start(struct usb_gadget *gadget,
 
 	pm_runtime_get_sync(hsudc->dev);
 
-	s3c_hsudc_init_phy();
+	if (hsudc->pd->phy_init)
+		hsudc->pd->phy_init();
 	if (hsudc->pd->gpio_init)
 		hsudc->pd->gpio_init();
 
@@ -1210,7 +1162,8 @@ static int s3c_hsudc_stop(struct usb_gadget *gadget)
 
 	spin_lock_irqsave(&hsudc->lock, flags);
 	hsudc->gadget.speed = USB_SPEED_UNKNOWN;
-	s3c_hsudc_uninit_phy();
+	if (hsudc->pd->phy_uninit)
+		hsudc->pd->phy_uninit();
 
 	pm_runtime_put(hsudc->dev);
 
diff --git a/include/linux/platform_data/s3c-hsudc.h b/include/linux/platform_data/s3c-hsudc.h
index 4dc9b8760166..a170939832d5 100644
--- a/include/linux/platform_data/s3c-hsudc.h
+++ b/include/linux/platform_data/s3c-hsudc.h
@@ -26,6 +26,8 @@ struct s3c24xx_hsudc_platdata {
 	unsigned int	epnum;
 	void		(*gpio_init)(void);
 	void		(*gpio_uninit)(void);
+	void		(*phy_init)(void);
+	void		(*phy_uninit)(void);
 };
 
 #endif	/* __LINUX_USB_S3C_HSUDC_H */
-- 
cgit v1.2.3


From 17132da70eb766785b9b4677bacce18cc11ea442 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 6 Aug 2020 20:20:33 +0200
Subject: ARM: samsung: move pm check code to drivers/soc

This is the only part of plat-samsung that is really
shared between the s3c and s5p ports. Moving it to
drivers/soc/ lets us make them completely independent.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20200806182059.2431-16-krzk@kernel.org
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
---
 arch/arm/mach-s5pv210/Kconfig                  |   1 +
 arch/arm/plat-samsung/Kconfig                  |  49 +-----
 arch/arm/plat-samsung/Makefile                 |   2 -
 arch/arm/plat-samsung/include/plat/pm-common.h |  70 +-------
 arch/arm/plat-samsung/pm-check.c               | 233 -------------------------
 arch/arm/plat-samsung/pm-debug.c               |  80 ---------
 drivers/soc/samsung/Kconfig                    |  48 ++++-
 drivers/soc/samsung/Makefile                   |   3 +
 drivers/soc/samsung/s3c-pm-check.c             | 233 +++++++++++++++++++++++++
 drivers/soc/samsung/s3c-pm-debug.c             |  79 +++++++++
 include/linux/soc/samsung/s3c-pm.h             |  84 +++++++++
 11 files changed, 449 insertions(+), 433 deletions(-)
 delete mode 100644 arch/arm/plat-samsung/pm-check.c
 delete mode 100644 arch/arm/plat-samsung/pm-debug.c
 create mode 100644 drivers/soc/samsung/s3c-pm-check.c
 create mode 100644 drivers/soc/samsung/s3c-pm-debug.c
 create mode 100644 include/linux/soc/samsung/s3c-pm.h

(limited to 'include/linux')

diff --git a/arch/arm/mach-s5pv210/Kconfig b/arch/arm/mach-s5pv210/Kconfig
index b3db1191e437..95d4e8284866 100644
--- a/arch/arm/mach-s5pv210/Kconfig
+++ b/arch/arm/mach-s5pv210/Kconfig
@@ -17,6 +17,7 @@ config ARCH_S5PV210
 	select HAVE_S3C_RTC if RTC_CLASS
 	select PINCTRL
 	select PINCTRL_EXYNOS
+	select SOC_SAMSUNG
 	help
 	  Samsung S5PV210/S5PC110 series based systems
 
diff --git a/arch/arm/plat-samsung/Kconfig b/arch/arm/plat-samsung/Kconfig
index 920931c3fefd..a7cb0db1d5cc 100644
--- a/arch/arm/plat-samsung/Kconfig
+++ b/arch/arm/plat-samsung/Kconfig
@@ -8,6 +8,7 @@ config PLAT_SAMSUNG
 	default y
 	select GENERIC_IRQ_CHIP
 	select NO_IOPORT_MAP
+	select SOC_SAMSUNG
 	help
 	  Base platform code for all Samsung SoC based systems
 
@@ -234,54 +235,6 @@ config SAMSUNG_PM_GPIO
 	  pinctrl-samsung driver.
 endif
 
-comment "Power management"
-
-config SAMSUNG_PM_DEBUG
-	bool "Samsung PM Suspend debug"
-	depends on PM && DEBUG_KERNEL
-	depends on PLAT_S3C24XX || ARCH_S3C64XX || ARCH_S5PV210
-	depends on DEBUG_S3C24XX_UART || DEBUG_S3C2410_UART
-	help
-	  Say Y here if you want verbose debugging from the PM Suspend and
-	  Resume code. See <file:Documentation/arm/samsung-s3c24xx/suspend.rst>
-	  for more information.
-
-config S3C_PM_DEBUG_LED_SMDK
-       bool "SMDK LED suspend/resume debugging"
-       depends on PM && (MACH_SMDK6410)
-       help
-         Say Y here to enable the use of the SMDK LEDs on the baseboard
-	 for debugging of the state of the suspend and resume process.
-
-	 Note, this currently only works for S3C64XX based SMDK boards.
-
-config SAMSUNG_PM_CHECK
-	bool "S3C2410 PM Suspend Memory CRC"
-	depends on PM && (PLAT_S3C24XX || ARCH_S3C64XX || ARCH_S5PV210)
-	select CRC32
-	help
-	  Enable the PM code's memory area checksum over sleep. This option
-	  will generate CRCs of all blocks of memory, and store them before
-	  going to sleep. The blocks are then checked on resume for any
-	  errors.
-
-	  Note, this can take several seconds depending on memory size
-	  and CPU speed.
-
-	  See <file:Documentation/arm/samsung-s3c24xx/suspend.rst>
-
-config SAMSUNG_PM_CHECK_CHUNKSIZE
-	int "S3C2410 PM Suspend CRC Chunksize (KiB)"
-	depends on PM && SAMSUNG_PM_CHECK
-	default 64
-	help
-	  Set the chunksize in Kilobytes of the CRC for checking memory
-	  corruption over suspend and resume. A smaller value will mean that
-	  the CRC data block will take more memory, but will identify any
-	  faults with better precision.
-
-	  See <file:Documentation/arm/samsung-s3c24xx/suspend.rst>
-
 config SAMSUNG_WAKEMASK
 	bool
 	depends on PM
diff --git a/arch/arm/plat-samsung/Makefile b/arch/arm/plat-samsung/Makefile
index d8a80fbcebb3..c47f58ed83e2 100644
--- a/arch/arm/plat-samsung/Makefile
+++ b/arch/arm/plat-samsung/Makefile
@@ -27,7 +27,5 @@ obj-$(CONFIG_GPIO_SAMSUNG)     += gpio-samsung.o
 obj-$(CONFIG_PM_SLEEP)		+= pm-common.o
 obj-$(CONFIG_SAMSUNG_PM)	+= pm.o
 obj-$(CONFIG_SAMSUNG_PM_GPIO)	+= pm-gpio.o
-obj-$(CONFIG_SAMSUNG_PM_CHECK)	+= pm-check.o
-obj-$(CONFIG_SAMSUNG_PM_DEBUG)	+= pm-debug.o
 
 obj-$(CONFIG_SAMSUNG_WAKEMASK)	+= wakeup-mask.o
diff --git a/arch/arm/plat-samsung/include/plat/pm-common.h b/arch/arm/plat-samsung/include/plat/pm-common.h
index 87fa97fd6e8b..18b9607e1e39 100644
--- a/arch/arm/plat-samsung/include/plat/pm-common.h
+++ b/arch/arm/plat-samsung/include/plat/pm-common.h
@@ -11,6 +11,7 @@
 #define __PLAT_SAMSUNG_PM_COMMON_H __FILE__
 
 #include <linux/irq.h>
+#include <linux/soc/samsung/s3c-pm.h>
 
 /* sleep save info */
 
@@ -36,73 +37,4 @@ extern void s3c_pm_do_save(struct sleep_save *ptr, int count);
 extern void s3c_pm_do_restore(const struct sleep_save *ptr, int count);
 extern void s3c_pm_do_restore_core(const struct sleep_save *ptr, int count);
 
-/* PM debug functions */
-
-/**
- * struct pm_uart_save - save block for core UART
- * @ulcon: Save value for S3C2410_ULCON
- * @ucon: Save value for S3C2410_UCON
- * @ufcon: Save value for S3C2410_UFCON
- * @umcon: Save value for S3C2410_UMCON
- * @ubrdiv: Save value for S3C2410_UBRDIV
- *
- * Save block for UART registers to be held over sleep and restored if they
- * are needed (say by debug).
-*/
-struct pm_uart_save {
-	u32	ulcon;
-	u32	ucon;
-	u32	ufcon;
-	u32	umcon;
-	u32	ubrdiv;
-	u32	udivslot;
-};
-
-#ifdef CONFIG_SAMSUNG_PM_DEBUG
-/**
- * s3c_pm_dbg() - low level debug function for use in suspend/resume.
- * @msg: The message to print.
- *
- * This function is used mainly to debug the resume process before the system
- * can rely on printk/console output. It uses the low-level debugging output
- * routine printascii() to do its work.
- */
-extern void s3c_pm_dbg(const char *msg, ...);
-
-#define S3C_PMDBG(fmt...) s3c_pm_dbg(fmt)
-
-extern void s3c_pm_save_uarts(bool is_s3c24xx);
-extern void s3c_pm_restore_uarts(bool is_s3c24xx);
-
-#ifdef CONFIG_ARCH_S3C64XX
-extern void s3c_pm_arch_update_uart(void __iomem *regs,
-				    struct pm_uart_save *save);
-#else
-static inline void
-s3c_pm_arch_update_uart(void __iomem *regs, struct pm_uart_save *save)
-{
-}
-#endif
-
-#else
-#define S3C_PMDBG(fmt...) pr_debug(fmt)
-
-static inline void s3c_pm_save_uarts(bool is_s3c24xx) { }
-static inline void s3c_pm_restore_uarts(bool is_s3c24xx) { }
-#endif
-
-/* suspend memory checking */
-
-#ifdef CONFIG_SAMSUNG_PM_CHECK
-extern void s3c_pm_check_prepare(void);
-extern void s3c_pm_check_restore(void);
-extern void s3c_pm_check_cleanup(void);
-extern void s3c_pm_check_store(void);
-#else
-#define s3c_pm_check_prepare() do { } while (0)
-#define s3c_pm_check_restore() do { } while (0)
-#define s3c_pm_check_cleanup() do { } while (0)
-#define s3c_pm_check_store()   do { } while (0)
-#endif
-
 #endif
diff --git a/arch/arm/plat-samsung/pm-check.c b/arch/arm/plat-samsung/pm-check.c
deleted file mode 100644
index cd2c02c68bc3..000000000000
--- a/arch/arm/plat-samsung/pm-check.c
+++ /dev/null
@@ -1,233 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-//
-// originally in linux/arch/arm/plat-s3c24xx/pm.c
-//
-// Copyright (c) 2004-2008 Simtec Electronics
-//	http://armlinux.simtec.co.uk
-//	Ben Dooks <ben@simtec.co.uk>
-//
-// S3C Power Mangament - suspend/resume memory corruption check.
-
-#include <linux/kernel.h>
-#include <linux/suspend.h>
-#include <linux/init.h>
-#include <linux/crc32.h>
-#include <linux/ioport.h>
-#include <linux/slab.h>
-
-#include <plat/pm-common.h>
-
-#if CONFIG_SAMSUNG_PM_CHECK_CHUNKSIZE < 1
-#error CONFIG_SAMSUNG_PM_CHECK_CHUNKSIZE must be a positive non-zero value
-#endif
-
-/* suspend checking code...
- *
- * this next area does a set of crc checks over all the installed
- * memory, so the system can verify if the resume was ok.
- *
- * CONFIG_SAMSUNG_PM_CHECK_CHUNKSIZE defines the block-size for the CRC,
- * increasing it will mean that the area corrupted will be less easy to spot,
- * and reducing the size will cause the CRC save area to grow
-*/
-
-#define CHECK_CHUNKSIZE (CONFIG_SAMSUNG_PM_CHECK_CHUNKSIZE * 1024)
-
-static u32 crc_size;	/* size needed for the crc block */
-static u32 *crcs;	/* allocated over suspend/resume */
-
-typedef u32 *(run_fn_t)(struct resource *ptr, u32 *arg);
-
-/* s3c_pm_run_res
- *
- * go through the given resource list, and look for system ram
-*/
-
-static void s3c_pm_run_res(struct resource *ptr, run_fn_t fn, u32 *arg)
-{
-	while (ptr != NULL) {
-		if (ptr->child != NULL)
-			s3c_pm_run_res(ptr->child, fn, arg);
-
-		if ((ptr->flags & IORESOURCE_SYSTEM_RAM)
-				== IORESOURCE_SYSTEM_RAM) {
-			S3C_PMDBG("Found system RAM at %08lx..%08lx\n",
-				  (unsigned long)ptr->start,
-				  (unsigned long)ptr->end);
-			arg = (fn)(ptr, arg);
-		}
-
-		ptr = ptr->sibling;
-	}
-}
-
-static void s3c_pm_run_sysram(run_fn_t fn, u32 *arg)
-{
-	s3c_pm_run_res(&iomem_resource, fn, arg);
-}
-
-static u32 *s3c_pm_countram(struct resource *res, u32 *val)
-{
-	u32 size = (u32)resource_size(res);
-
-	size += CHECK_CHUNKSIZE-1;
-	size /= CHECK_CHUNKSIZE;
-
-	S3C_PMDBG("Area %08lx..%08lx, %d blocks\n",
-		  (unsigned long)res->start, (unsigned long)res->end, size);
-
-	*val += size * sizeof(u32);
-	return val;
-}
-
-/* s3c_pm_prepare_check
- *
- * prepare the necessary information for creating the CRCs. This
- * must be done before the final save, as it will require memory
- * allocating, and thus touching bits of the kernel we do not
- * know about.
-*/
-
-void s3c_pm_check_prepare(void)
-{
-	crc_size = 0;
-
-	s3c_pm_run_sysram(s3c_pm_countram, &crc_size);
-
-	S3C_PMDBG("s3c_pm_prepare_check: %u checks needed\n", crc_size);
-
-	crcs = kmalloc(crc_size+4, GFP_KERNEL);
-	if (crcs == NULL)
-		printk(KERN_ERR "Cannot allocated CRC save area\n");
-}
-
-static u32 *s3c_pm_makecheck(struct resource *res, u32 *val)
-{
-	unsigned long addr, left;
-
-	for (addr = res->start; addr < res->end;
-	     addr += CHECK_CHUNKSIZE) {
-		left = res->end - addr;
-
-		if (left > CHECK_CHUNKSIZE)
-			left = CHECK_CHUNKSIZE;
-
-		*val = crc32_le(~0, phys_to_virt(addr), left);
-		val++;
-	}
-
-	return val;
-}
-
-/* s3c_pm_check_store
- *
- * compute the CRC values for the memory blocks before the final
- * sleep.
-*/
-
-void s3c_pm_check_store(void)
-{
-	if (crcs != NULL)
-		s3c_pm_run_sysram(s3c_pm_makecheck, crcs);
-}
-
-/* in_region
- *
- * return TRUE if the area defined by ptr..ptr+size contains the
- * what..what+whatsz
-*/
-
-static inline int in_region(void *ptr, int size, void *what, size_t whatsz)
-{
-	if ((what+whatsz) < ptr)
-		return 0;
-
-	if (what > (ptr+size))
-		return 0;
-
-	return 1;
-}
-
-/**
- * s3c_pm_runcheck() - helper to check a resource on restore.
- * @res: The resource to check
- * @vak: Pointer to list of CRC32 values to check.
- *
- * Called from the s3c_pm_check_restore() via s3c_pm_run_sysram(), this
- * function runs the given memory resource checking it against the stored
- * CRC to ensure that memory is restored. The function tries to skip as
- * many of the areas used during the suspend process.
- */
-static u32 *s3c_pm_runcheck(struct resource *res, u32 *val)
-{
-	unsigned long addr;
-	unsigned long left;
-	void *stkpage;
-	void *ptr;
-	u32 calc;
-
-	stkpage = (void *)((u32)&calc & ~PAGE_MASK);
-
-	for (addr = res->start; addr < res->end;
-	     addr += CHECK_CHUNKSIZE) {
-		left = res->end - addr;
-
-		if (left > CHECK_CHUNKSIZE)
-			left = CHECK_CHUNKSIZE;
-
-		ptr = phys_to_virt(addr);
-
-		if (in_region(ptr, left, stkpage, 4096)) {
-			S3C_PMDBG("skipping %08lx, has stack in\n", addr);
-			goto skip_check;
-		}
-
-		if (in_region(ptr, left, crcs, crc_size)) {
-			S3C_PMDBG("skipping %08lx, has crc block in\n", addr);
-			goto skip_check;
-		}
-
-		/* calculate and check the checksum */
-
-		calc = crc32_le(~0, ptr, left);
-		if (calc != *val) {
-			printk(KERN_ERR "Restore CRC error at "
-			       "%08lx (%08x vs %08x)\n", addr, calc, *val);
-
-			S3C_PMDBG("Restore CRC error at %08lx (%08x vs %08x)\n",
-			    addr, calc, *val);
-		}
-
-	skip_check:
-		val++;
-	}
-
-	return val;
-}
-
-/**
- * s3c_pm_check_restore() - memory check called on resume
- *
- * check the CRCs after the restore event and free the memory used
- * to hold them
-*/
-void s3c_pm_check_restore(void)
-{
-	if (crcs != NULL)
-		s3c_pm_run_sysram(s3c_pm_runcheck, crcs);
-}
-
-/**
- * s3c_pm_check_cleanup() - free memory resources
- *
- * Free the resources that where allocated by the suspend
- * memory check code. We do this separately from the
- * s3c_pm_check_restore() function as we cannot call any
- * functions that might sleep during that resume.
- */
-void s3c_pm_check_cleanup(void)
-{
-	kfree(crcs);
-	crcs = NULL;
-}
-
diff --git a/arch/arm/plat-samsung/pm-debug.c b/arch/arm/plat-samsung/pm-debug.c
deleted file mode 100644
index 482d53753e93..000000000000
--- a/arch/arm/plat-samsung/pm-debug.c
+++ /dev/null
@@ -1,80 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-//
-// Copyright (C) 2013 Samsung Electronics Co., Ltd.
-//	Tomasz Figa <t.figa@samsung.com>
-// Copyright (C) 2008 Openmoko, Inc.
-// Copyright (C) 2004-2008 Simtec Electronics
-//	Ben Dooks <ben@simtec.co.uk>
-//	http://armlinux.simtec.co.uk/
-//
-// Samsung common power management (suspend to RAM) debug support
-
-#include <linux/serial_core.h>
-#include <linux/serial_s3c.h>
-#include <linux/io.h>
-
-#include <asm/mach/map.h>
-
-#include <plat/cpu.h>
-#include <plat/pm-common.h>
-
-static struct pm_uart_save uart_save;
-
-extern void printascii(const char *);
-
-void s3c_pm_dbg(const char *fmt, ...)
-{
-	va_list va;
-	char buff[256];
-
-	va_start(va, fmt);
-	vsnprintf(buff, sizeof(buff), fmt, va);
-	va_end(va);
-
-	printascii(buff);
-}
-
-static inline void __iomem *s3c_pm_uart_base(void)
-{
-	unsigned long paddr;
-	unsigned long vaddr;
-
-	debug_ll_addr(&paddr, &vaddr);
-
-	return (void __iomem *)vaddr;
-}
-
-void s3c_pm_save_uarts(bool is_s3c2410)
-{
-	void __iomem *regs = s3c_pm_uart_base();
-	struct pm_uart_save *save = &uart_save;
-
-	save->ulcon = __raw_readl(regs + S3C2410_ULCON);
-	save->ucon = __raw_readl(regs + S3C2410_UCON);
-	save->ufcon = __raw_readl(regs + S3C2410_UFCON);
-	save->umcon = __raw_readl(regs + S3C2410_UMCON);
-	save->ubrdiv = __raw_readl(regs + S3C2410_UBRDIV);
-
-	if (!is_s3c2410)
-		save->udivslot = __raw_readl(regs + S3C2443_DIVSLOT);
-
-	S3C_PMDBG("UART[%p]: ULCON=%04x, UCON=%04x, UFCON=%04x, UBRDIV=%04x\n",
-		  regs, save->ulcon, save->ucon, save->ufcon, save->ubrdiv);
-}
-
-void s3c_pm_restore_uarts(bool is_s3c2410)
-{
-	void __iomem *regs = s3c_pm_uart_base();
-	struct pm_uart_save *save = &uart_save;
-
-	s3c_pm_arch_update_uart(regs, save);
-
-	__raw_writel(save->ulcon, regs + S3C2410_ULCON);
-	__raw_writel(save->ucon,  regs + S3C2410_UCON);
-	__raw_writel(save->ufcon, regs + S3C2410_UFCON);
-	__raw_writel(save->umcon, regs + S3C2410_UMCON);
-	__raw_writel(save->ubrdiv, regs + S3C2410_UBRDIV);
-
-	if (!is_s3c2410)
-		__raw_writel(save->udivslot, regs + S3C2443_DIVSLOT);
-}
diff --git a/drivers/soc/samsung/Kconfig b/drivers/soc/samsung/Kconfig
index 264185664594..5abe82079d2e 100644
--- a/drivers/soc/samsung/Kconfig
+++ b/drivers/soc/samsung/Kconfig
@@ -35,7 +35,53 @@ config EXYNOS_PMU_ARM_DRIVERS
 
 config EXYNOS_PM_DOMAINS
 	bool "Exynos PM domains" if COMPILE_TEST
-	depends on PM_GENERIC_DOMAINS || COMPILE_TEST
+	depends on (ARCH_EXYNOS && PM_GENERIC_DOMAINS) || COMPILE_TEST
+
+config SAMSUNG_PM_DEBUG
+	bool "Samsung PM Suspend debug"
+	depends on PM && DEBUG_KERNEL
+	depends on PLAT_S3C24XX || ARCH_S3C64XX || ARCH_S5PV210
+	depends on DEBUG_S3C24XX_UART || DEBUG_S3C2410_UART
+	help
+	  Say Y here if you want verbose debugging from the PM Suspend and
+	  Resume code. See <file:Documentation/arm/samsung-s3c24xx/suspend.rst>
+	  for more information.
+
+config S3C_PM_DEBUG_LED_SMDK
+       bool "SMDK LED suspend/resume debugging"
+       depends on PM && (MACH_SMDK6410)
+       help
+         Say Y here to enable the use of the SMDK LEDs on the baseboard
+	 for debugging of the state of the suspend and resume process.
+
+	 Note, this currently only works for S3C64XX based SMDK boards.
+
+config SAMSUNG_PM_CHECK
+	bool "S3C2410 PM Suspend Memory CRC"
+	depends on PM && (PLAT_S3C24XX || ARCH_S3C64XX || ARCH_S5PV210)
+	select CRC32
+	help
+	  Enable the PM code's memory area checksum over sleep. This option
+	  will generate CRCs of all blocks of memory, and store them before
+	  going to sleep. The blocks are then checked on resume for any
+	  errors.
+
+	  Note, this can take several seconds depending on memory size
+	  and CPU speed.
+
+	  See <file:Documentation/arm/samsung-s3c24xx/suspend.rst>
+
+config SAMSUNG_PM_CHECK_CHUNKSIZE
+	int "S3C2410 PM Suspend CRC Chunksize (KiB)"
+	depends on PM && SAMSUNG_PM_CHECK
+	default 64
+	help
+	  Set the chunksize in Kilobytes of the CRC for checking memory
+	  corruption over suspend and resume. A smaller value will mean that
+	  the CRC data block will take more memory, but will identify any
+	  faults with better precision.
+
+	  See <file:Documentation/arm/samsung-s3c24xx/suspend.rst>
 
 config EXYNOS_REGULATOR_COUPLER
 	bool "Exynos SoC Regulator Coupler" if COMPILE_TEST
diff --git a/drivers/soc/samsung/Makefile b/drivers/soc/samsung/Makefile
index ecc3a32f6406..59e8e9453f27 100644
--- a/drivers/soc/samsung/Makefile
+++ b/drivers/soc/samsung/Makefile
@@ -10,3 +10,6 @@ obj-$(CONFIG_EXYNOS_PMU_ARM_DRIVERS)	+= exynos3250-pmu.o exynos4-pmu.o \
 					exynos5250-pmu.o exynos5420-pmu.o
 obj-$(CONFIG_EXYNOS_PM_DOMAINS) += pm_domains.o
 obj-$(CONFIG_EXYNOS_REGULATOR_COUPLER) += exynos-regulator-coupler.o
+
+obj-$(CONFIG_SAMSUNG_PM_CHECK)	+= s3c-pm-check.o
+obj-$(CONFIG_SAMSUNG_PM_DEBUG)	+= s3c-pm-debug.o
diff --git a/drivers/soc/samsung/s3c-pm-check.c b/drivers/soc/samsung/s3c-pm-check.c
new file mode 100644
index 000000000000..ff3e099fc208
--- /dev/null
+++ b/drivers/soc/samsung/s3c-pm-check.c
@@ -0,0 +1,233 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// originally in linux/arch/arm/plat-s3c24xx/pm.c
+//
+// Copyright (c) 2004-2008 Simtec Electronics
+//	http://armlinux.simtec.co.uk
+//	Ben Dooks <ben@simtec.co.uk>
+//
+// S3C Power Mangament - suspend/resume memory corruption check.
+
+#include <linux/kernel.h>
+#include <linux/suspend.h>
+#include <linux/init.h>
+#include <linux/crc32.h>
+#include <linux/ioport.h>
+#include <linux/slab.h>
+
+#include <linux/soc/samsung/s3c-pm.h>
+
+#if CONFIG_SAMSUNG_PM_CHECK_CHUNKSIZE < 1
+#error CONFIG_SAMSUNG_PM_CHECK_CHUNKSIZE must be a positive non-zero value
+#endif
+
+/* suspend checking code...
+ *
+ * this next area does a set of crc checks over all the installed
+ * memory, so the system can verify if the resume was ok.
+ *
+ * CONFIG_SAMSUNG_PM_CHECK_CHUNKSIZE defines the block-size for the CRC,
+ * increasing it will mean that the area corrupted will be less easy to spot,
+ * and reducing the size will cause the CRC save area to grow
+*/
+
+#define CHECK_CHUNKSIZE (CONFIG_SAMSUNG_PM_CHECK_CHUNKSIZE * 1024)
+
+static u32 crc_size;	/* size needed for the crc block */
+static u32 *crcs;	/* allocated over suspend/resume */
+
+typedef u32 *(run_fn_t)(struct resource *ptr, u32 *arg);
+
+/* s3c_pm_run_res
+ *
+ * go through the given resource list, and look for system ram
+*/
+
+static void s3c_pm_run_res(struct resource *ptr, run_fn_t fn, u32 *arg)
+{
+	while (ptr != NULL) {
+		if (ptr->child != NULL)
+			s3c_pm_run_res(ptr->child, fn, arg);
+
+		if ((ptr->flags & IORESOURCE_SYSTEM_RAM)
+				== IORESOURCE_SYSTEM_RAM) {
+			S3C_PMDBG("Found system RAM at %08lx..%08lx\n",
+				  (unsigned long)ptr->start,
+				  (unsigned long)ptr->end);
+			arg = (fn)(ptr, arg);
+		}
+
+		ptr = ptr->sibling;
+	}
+}
+
+static void s3c_pm_run_sysram(run_fn_t fn, u32 *arg)
+{
+	s3c_pm_run_res(&iomem_resource, fn, arg);
+}
+
+static u32 *s3c_pm_countram(struct resource *res, u32 *val)
+{
+	u32 size = (u32)resource_size(res);
+
+	size += CHECK_CHUNKSIZE-1;
+	size /= CHECK_CHUNKSIZE;
+
+	S3C_PMDBG("Area %08lx..%08lx, %d blocks\n",
+		  (unsigned long)res->start, (unsigned long)res->end, size);
+
+	*val += size * sizeof(u32);
+	return val;
+}
+
+/* s3c_pm_prepare_check
+ *
+ * prepare the necessary information for creating the CRCs. This
+ * must be done before the final save, as it will require memory
+ * allocating, and thus touching bits of the kernel we do not
+ * know about.
+*/
+
+void s3c_pm_check_prepare(void)
+{
+	crc_size = 0;
+
+	s3c_pm_run_sysram(s3c_pm_countram, &crc_size);
+
+	S3C_PMDBG("s3c_pm_prepare_check: %u checks needed\n", crc_size);
+
+	crcs = kmalloc(crc_size+4, GFP_KERNEL);
+	if (crcs == NULL)
+		printk(KERN_ERR "Cannot allocated CRC save area\n");
+}
+
+static u32 *s3c_pm_makecheck(struct resource *res, u32 *val)
+{
+	unsigned long addr, left;
+
+	for (addr = res->start; addr < res->end;
+	     addr += CHECK_CHUNKSIZE) {
+		left = res->end - addr;
+
+		if (left > CHECK_CHUNKSIZE)
+			left = CHECK_CHUNKSIZE;
+
+		*val = crc32_le(~0, phys_to_virt(addr), left);
+		val++;
+	}
+
+	return val;
+}
+
+/* s3c_pm_check_store
+ *
+ * compute the CRC values for the memory blocks before the final
+ * sleep.
+*/
+
+void s3c_pm_check_store(void)
+{
+	if (crcs != NULL)
+		s3c_pm_run_sysram(s3c_pm_makecheck, crcs);
+}
+
+/* in_region
+ *
+ * return TRUE if the area defined by ptr..ptr+size contains the
+ * what..what+whatsz
+*/
+
+static inline int in_region(void *ptr, int size, void *what, size_t whatsz)
+{
+	if ((what+whatsz) < ptr)
+		return 0;
+
+	if (what > (ptr+size))
+		return 0;
+
+	return 1;
+}
+
+/**
+ * s3c_pm_runcheck() - helper to check a resource on restore.
+ * @res: The resource to check
+ * @vak: Pointer to list of CRC32 values to check.
+ *
+ * Called from the s3c_pm_check_restore() via s3c_pm_run_sysram(), this
+ * function runs the given memory resource checking it against the stored
+ * CRC to ensure that memory is restored. The function tries to skip as
+ * many of the areas used during the suspend process.
+ */
+static u32 *s3c_pm_runcheck(struct resource *res, u32 *val)
+{
+	unsigned long addr;
+	unsigned long left;
+	void *stkpage;
+	void *ptr;
+	u32 calc;
+
+	stkpage = (void *)((u32)&calc & ~PAGE_MASK);
+
+	for (addr = res->start; addr < res->end;
+	     addr += CHECK_CHUNKSIZE) {
+		left = res->end - addr;
+
+		if (left > CHECK_CHUNKSIZE)
+			left = CHECK_CHUNKSIZE;
+
+		ptr = phys_to_virt(addr);
+
+		if (in_region(ptr, left, stkpage, 4096)) {
+			S3C_PMDBG("skipping %08lx, has stack in\n", addr);
+			goto skip_check;
+		}
+
+		if (in_region(ptr, left, crcs, crc_size)) {
+			S3C_PMDBG("skipping %08lx, has crc block in\n", addr);
+			goto skip_check;
+		}
+
+		/* calculate and check the checksum */
+
+		calc = crc32_le(~0, ptr, left);
+		if (calc != *val) {
+			printk(KERN_ERR "Restore CRC error at "
+			       "%08lx (%08x vs %08x)\n", addr, calc, *val);
+
+			S3C_PMDBG("Restore CRC error at %08lx (%08x vs %08x)\n",
+			    addr, calc, *val);
+		}
+
+	skip_check:
+		val++;
+	}
+
+	return val;
+}
+
+/**
+ * s3c_pm_check_restore() - memory check called on resume
+ *
+ * check the CRCs after the restore event and free the memory used
+ * to hold them
+*/
+void s3c_pm_check_restore(void)
+{
+	if (crcs != NULL)
+		s3c_pm_run_sysram(s3c_pm_runcheck, crcs);
+}
+
+/**
+ * s3c_pm_check_cleanup() - free memory resources
+ *
+ * Free the resources that where allocated by the suspend
+ * memory check code. We do this separately from the
+ * s3c_pm_check_restore() function as we cannot call any
+ * functions that might sleep during that resume.
+ */
+void s3c_pm_check_cleanup(void)
+{
+	kfree(crcs);
+	crcs = NULL;
+}
+
diff --git a/drivers/soc/samsung/s3c-pm-debug.c b/drivers/soc/samsung/s3c-pm-debug.c
new file mode 100644
index 000000000000..b5ce0e9a41e5
--- /dev/null
+++ b/drivers/soc/samsung/s3c-pm-debug.c
@@ -0,0 +1,79 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (C) 2013 Samsung Electronics Co., Ltd.
+//	Tomasz Figa <t.figa@samsung.com>
+// Copyright (C) 2008 Openmoko, Inc.
+// Copyright (C) 2004-2008 Simtec Electronics
+//	Ben Dooks <ben@simtec.co.uk>
+//	http://armlinux.simtec.co.uk/
+//
+// Samsung common power management (suspend to RAM) debug support
+
+#include <linux/serial_core.h>
+#include <linux/serial_s3c.h>
+#include <linux/io.h>
+
+#include <asm/mach/map.h>
+
+#include <linux/soc/samsung/s3c-pm.h>
+
+static struct pm_uart_save uart_save;
+
+extern void printascii(const char *);
+
+void s3c_pm_dbg(const char *fmt, ...)
+{
+	va_list va;
+	char buff[256];
+
+	va_start(va, fmt);
+	vsnprintf(buff, sizeof(buff), fmt, va);
+	va_end(va);
+
+	printascii(buff);
+}
+
+static inline void __iomem *s3c_pm_uart_base(void)
+{
+	unsigned long paddr;
+	unsigned long vaddr;
+
+	debug_ll_addr(&paddr, &vaddr);
+
+	return (void __iomem *)vaddr;
+}
+
+void s3c_pm_save_uarts(bool is_s3c2410)
+{
+	void __iomem *regs = s3c_pm_uart_base();
+	struct pm_uart_save *save = &uart_save;
+
+	save->ulcon = __raw_readl(regs + S3C2410_ULCON);
+	save->ucon = __raw_readl(regs + S3C2410_UCON);
+	save->ufcon = __raw_readl(regs + S3C2410_UFCON);
+	save->umcon = __raw_readl(regs + S3C2410_UMCON);
+	save->ubrdiv = __raw_readl(regs + S3C2410_UBRDIV);
+
+	if (!is_s3c2410)
+		save->udivslot = __raw_readl(regs + S3C2443_DIVSLOT);
+
+	S3C_PMDBG("UART[%p]: ULCON=%04x, UCON=%04x, UFCON=%04x, UBRDIV=%04x\n",
+		  regs, save->ulcon, save->ucon, save->ufcon, save->ubrdiv);
+}
+
+void s3c_pm_restore_uarts(bool is_s3c2410)
+{
+	void __iomem *regs = s3c_pm_uart_base();
+	struct pm_uart_save *save = &uart_save;
+
+	s3c_pm_arch_update_uart(regs, save);
+
+	__raw_writel(save->ulcon, regs + S3C2410_ULCON);
+	__raw_writel(save->ucon,  regs + S3C2410_UCON);
+	__raw_writel(save->ufcon, regs + S3C2410_UFCON);
+	__raw_writel(save->umcon, regs + S3C2410_UMCON);
+	__raw_writel(save->ubrdiv, regs + S3C2410_UBRDIV);
+
+	if (!is_s3c2410)
+		__raw_writel(save->udivslot, regs + S3C2443_DIVSLOT);
+}
diff --git a/include/linux/soc/samsung/s3c-pm.h b/include/linux/soc/samsung/s3c-pm.h
new file mode 100644
index 000000000000..730bd1d3d09a
--- /dev/null
+++ b/include/linux/soc/samsung/s3c-pm.h
@@ -0,0 +1,84 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ *	Tomasz Figa <t.figa@samsung.com>
+ * Copyright (c) 2004 Simtec Electronics
+ *	http://armlinux.simtec.co.uk/
+ *	Written by Ben Dooks, <ben@simtec.co.uk>
+ */
+
+#ifndef __LINUX_SOC_SAMSUNG_S3C_PM_H
+#define __LINUX_SOC_SAMSUNG_S3C_PM_H __FILE__
+
+#include <linux/types.h>
+
+/* PM debug functions */
+
+/**
+ * struct pm_uart_save - save block for core UART
+ * @ulcon: Save value for S3C2410_ULCON
+ * @ucon: Save value for S3C2410_UCON
+ * @ufcon: Save value for S3C2410_UFCON
+ * @umcon: Save value for S3C2410_UMCON
+ * @ubrdiv: Save value for S3C2410_UBRDIV
+ *
+ * Save block for UART registers to be held over sleep and restored if they
+ * are needed (say by debug).
+*/
+struct pm_uart_save {
+	u32	ulcon;
+	u32	ucon;
+	u32	ufcon;
+	u32	umcon;
+	u32	ubrdiv;
+	u32	udivslot;
+};
+
+#ifdef CONFIG_SAMSUNG_PM_DEBUG
+/**
+ * s3c_pm_dbg() - low level debug function for use in suspend/resume.
+ * @msg: The message to print.
+ *
+ * This function is used mainly to debug the resume process before the system
+ * can rely on printk/console output. It uses the low-level debugging output
+ * routine printascii() to do its work.
+ */
+extern void s3c_pm_dbg(const char *msg, ...);
+
+#define S3C_PMDBG(fmt...) s3c_pm_dbg(fmt)
+
+extern void s3c_pm_save_uarts(bool is_s3c24xx);
+extern void s3c_pm_restore_uarts(bool is_s3c24xx);
+
+#ifdef CONFIG_ARCH_S3C64XX
+extern void s3c_pm_arch_update_uart(void __iomem *regs,
+				    struct pm_uart_save *save);
+#else
+static inline void
+s3c_pm_arch_update_uart(void __iomem *regs, struct pm_uart_save *save)
+{
+}
+#endif
+
+#else
+#define S3C_PMDBG(fmt...) pr_debug(fmt)
+
+static inline void s3c_pm_save_uarts(bool is_s3c24xx) { }
+static inline void s3c_pm_restore_uarts(bool is_s3c24xx) { }
+#endif
+
+/* suspend memory checking */
+
+#ifdef CONFIG_SAMSUNG_PM_CHECK
+extern void s3c_pm_check_prepare(void);
+extern void s3c_pm_check_restore(void);
+extern void s3c_pm_check_cleanup(void);
+extern void s3c_pm_check_store(void);
+#else
+#define s3c_pm_check_prepare() do { } while (0)
+#define s3c_pm_check_restore() do { } while (0)
+#define s3c_pm_check_cleanup() do { } while (0)
+#define s3c_pm_check_store()   do { } while (0)
+#endif
+
+#endif
-- 
cgit v1.2.3


From 7dbad03ebcb924cde142f7477d65a54ffb1166a3 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 6 Aug 2020 20:20:39 +0200
Subject: ARM: s3c: adc: move header to linux/soc/samsung

There are multiple drivers using the private adc interface.
It seems unlikely that they would ever get converted to iio,
so make the current state official by making the header file
global.

The s3c2410_ts driver needs a couple of register definitions
as well.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Guenter Roeck <linux@roeck-us.net>
Acked-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Acked-by: Sebastian Reichel <sre@kernel.org>
Link: https://lore.kernel.org/r/20200806182059.2431-22-krzk@kernel.org
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
---
 arch/arm/mach-s3c64xx/mach-crag6410.c    |  2 +-
 arch/arm/mach-s3c64xx/mach-mini6410.c    |  2 +-
 arch/arm/mach-s3c64xx/mach-real6410.c    |  2 +-
 arch/arm/mach-s3c64xx/mach-smdk6410.c    |  2 +-
 arch/arm/plat-samsung/adc.c              |  2 +-
 arch/arm/plat-samsung/devs.c             |  2 +-
 arch/arm/plat-samsung/include/plat/adc.h | 32 ---------------------------
 drivers/hwmon/s3c-hwmon.c                |  2 +-
 drivers/input/touchscreen/s3c2410_ts.c   | 37 ++++++++++++++++++++++++++++++--
 drivers/power/supply/s3c_adc_battery.c   |  2 +-
 include/linux/soc/samsung/s3c-adc.h      | 32 +++++++++++++++++++++++++++
 11 files changed, 75 insertions(+), 42 deletions(-)
 delete mode 100644 arch/arm/plat-samsung/include/plat/adc.h
 create mode 100644 include/linux/soc/samsung/s3c-adc.h

(limited to 'include/linux')

diff --git a/arch/arm/mach-s3c64xx/mach-crag6410.c b/arch/arm/mach-s3c64xx/mach-crag6410.c
index a2fefb2609e7..ca9a346056ed 100644
--- a/arch/arm/mach-s3c64xx/mach-crag6410.c
+++ b/arch/arm/mach-s3c64xx/mach-crag6410.c
@@ -57,7 +57,7 @@
 #include <plat/keypad.h>
 #include <plat/devs.h>
 #include <plat/cpu.h>
-#include <plat/adc.h>
+#include <linux/soc/samsung/s3c-adc.h>
 #include <linux/platform_data/i2c-s3c2410.h>
 #include <plat/pm.h>
 
diff --git a/arch/arm/mach-s3c64xx/mach-mini6410.c b/arch/arm/mach-s3c64xx/mach-mini6410.c
index 636d312add81..cbf6a1696a6d 100644
--- a/arch/arm/mach-s3c64xx/mach-mini6410.c
+++ b/arch/arm/mach-s3c64xx/mach-mini6410.c
@@ -27,7 +27,7 @@
 #include <mach/regs-gpio.h>
 #include <mach/gpio-samsung.h>
 
-#include <plat/adc.h>
+#include <linux/soc/samsung/s3c-adc.h>
 #include <plat/cpu.h>
 #include <plat/devs.h>
 #include <plat/fb.h>
diff --git a/arch/arm/mach-s3c64xx/mach-real6410.c b/arch/arm/mach-s3c64xx/mach-real6410.c
index 56fc21f02c7b..e2aa7c0998bd 100644
--- a/arch/arm/mach-s3c64xx/mach-real6410.c
+++ b/arch/arm/mach-s3c64xx/mach-real6410.c
@@ -29,7 +29,7 @@
 #include <mach/gpio-samsung.h>
 #include <mach/irqs.h>
 
-#include <plat/adc.h>
+#include <linux/soc/samsung/s3c-adc.h>
 #include <plat/cpu.h>
 #include <plat/devs.h>
 #include <plat/fb.h>
diff --git a/arch/arm/mach-s3c64xx/mach-smdk6410.c b/arch/arm/mach-s3c64xx/mach-smdk6410.c
index 7b931e7a7913..febeacc476c8 100644
--- a/arch/arm/mach-s3c64xx/mach-smdk6410.c
+++ b/arch/arm/mach-s3c64xx/mach-smdk6410.c
@@ -60,7 +60,7 @@
 
 #include <plat/devs.h>
 #include <plat/cpu.h>
-#include <plat/adc.h>
+#include <linux/soc/samsung/s3c-adc.h>
 #include <linux/platform_data/touchscreen-s3c2410.h>
 #include <plat/keypad.h>
 
diff --git a/arch/arm/plat-samsung/adc.c b/arch/arm/plat-samsung/adc.c
index 55b1925f65d7..e35e04417cce 100644
--- a/arch/arm/plat-samsung/adc.c
+++ b/arch/arm/plat-samsung/adc.c
@@ -20,7 +20,7 @@
 #include <linux/regulator/consumer.h>
 
 #include <plat/regs-adc.h>
-#include <plat/adc.h>
+#include <linux/soc/samsung/s3c-adc.h>
 
 /* This driver is designed to control the usage of the ADC block between
  * the touchscreen and any other drivers that may need to use it, such as
diff --git a/arch/arm/plat-samsung/devs.c b/arch/arm/plat-samsung/devs.c
index 0ed3a4b9fc12..c42e4a272cc7 100644
--- a/arch/arm/plat-samsung/devs.c
+++ b/arch/arm/plat-samsung/devs.c
@@ -46,7 +46,7 @@
 
 #include <plat/cpu.h>
 #include <plat/devs.h>
-#include <plat/adc.h>
+#include <linux/soc/samsung/s3c-adc.h>
 #include <linux/platform_data/ata-samsung_cf.h>
 #include <plat/fb.h>
 #include <plat/fb-s3c2410.h>
diff --git a/arch/arm/plat-samsung/include/plat/adc.h b/arch/arm/plat-samsung/include/plat/adc.h
deleted file mode 100644
index 74d1a46408c1..000000000000
--- a/arch/arm/plat-samsung/include/plat/adc.h
+++ /dev/null
@@ -1,32 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (c) 2008 Simtec Electronics
- *	http://armlinux.simtec.co.uk/	
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * S3C ADC driver information
- */
-
-#ifndef __ASM_PLAT_ADC_H
-#define __ASM_PLAT_ADC_H __FILE__
-
-struct s3c_adc_client;
-struct platform_device;
-
-extern int s3c_adc_start(struct s3c_adc_client *client,
-			 unsigned int channel, unsigned int nr_samples);
-
-extern int s3c_adc_read(struct s3c_adc_client *client, unsigned int ch);
-
-extern struct s3c_adc_client *
-	s3c_adc_register(struct platform_device *pdev,
-			 void (*select)(struct s3c_adc_client *client,
-					unsigned selected),
-			 void (*conv)(struct s3c_adc_client *client,
-				      unsigned d0, unsigned d1,
-				      unsigned *samples_left),
-			 unsigned int is_ts);
-
-extern void s3c_adc_release(struct s3c_adc_client *client);
-
-#endif /* __ASM_PLAT_ADC_H */
diff --git a/drivers/hwmon/s3c-hwmon.c b/drivers/hwmon/s3c-hwmon.c
index b490fe3d2ee8..f2703c5460d0 100644
--- a/drivers/hwmon/s3c-hwmon.c
+++ b/drivers/hwmon/s3c-hwmon.c
@@ -20,7 +20,7 @@
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
 
-#include <plat/adc.h>
+#include <linux/soc/samsung/s3c-adc.h>
 #include <linux/platform_data/hwmon-s3c.h>
 
 struct s3c_hwmon_attr {
diff --git a/drivers/input/touchscreen/s3c2410_ts.c b/drivers/input/touchscreen/s3c2410_ts.c
index 82920ff46f72..2e70c0b79444 100644
--- a/drivers/input/touchscreen/s3c2410_ts.c
+++ b/drivers/input/touchscreen/s3c2410_ts.c
@@ -20,10 +20,43 @@
 #include <linux/clk.h>
 #include <linux/io.h>
 
-#include <plat/adc.h>
-#include <plat/regs-adc.h>
+#include <linux/soc/samsung/s3c-adc.h>
 #include <linux/platform_data/touchscreen-s3c2410.h>
 
+#define	S3C2410_ADCCON			(0x00)
+#define	S3C2410_ADCTSC			(0x04)
+#define	S3C2410_ADCDLY			(0x08)
+#define	S3C2410_ADCDAT0			(0x0C)
+#define	S3C2410_ADCDAT1			(0x10)
+#define	S3C64XX_ADCUPDN			(0x14)
+#define	S3C2443_ADCMUX			(0x18)
+#define	S3C64XX_ADCCLRINT		(0x18)
+#define	S5P_ADCMUX			(0x1C)
+#define	S3C64XX_ADCCLRINTPNDNUP		(0x20)
+
+/* ADCTSC Register Bits */
+#define S3C2443_ADCTSC_UD_SEN		(1 << 8)
+#define S3C2410_ADCTSC_YM_SEN		(1<<7)
+#define S3C2410_ADCTSC_YP_SEN		(1<<6)
+#define S3C2410_ADCTSC_XM_SEN		(1<<5)
+#define S3C2410_ADCTSC_XP_SEN		(1<<4)
+#define S3C2410_ADCTSC_PULL_UP_DISABLE	(1<<3)
+#define S3C2410_ADCTSC_AUTO_PST		(1<<2)
+#define S3C2410_ADCTSC_XY_PST(x)	(((x)&0x3)<<0)
+
+/* ADCDAT0 Bits */
+#define S3C2410_ADCDAT0_UPDOWN		(1<<15)
+#define S3C2410_ADCDAT0_AUTO_PST	(1<<14)
+#define S3C2410_ADCDAT0_XY_PST		(0x3<<12)
+#define S3C2410_ADCDAT0_XPDATA_MASK	(0x03FF)
+
+/* ADCDAT1 Bits */
+#define S3C2410_ADCDAT1_UPDOWN		(1<<15)
+#define S3C2410_ADCDAT1_AUTO_PST	(1<<14)
+#define S3C2410_ADCDAT1_XY_PST		(0x3<<12)
+#define S3C2410_ADCDAT1_YPDATA_MASK	(0x03FF)
+
+
 #define TSC_SLEEP  (S3C2410_ADCTSC_PULL_UP_DISABLE | S3C2410_ADCTSC_XY_PST(0))
 
 #define INT_DOWN	(0)
diff --git a/drivers/power/supply/s3c_adc_battery.c b/drivers/power/supply/s3c_adc_battery.c
index 3d00b35cafc9..60b7f41ab063 100644
--- a/drivers/power/supply/s3c_adc_battery.c
+++ b/drivers/power/supply/s3c_adc_battery.c
@@ -22,7 +22,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 
-#include <plat/adc.h>
+#include <linux/soc/samsung/s3c-adc.h>
 
 #define BAT_POLL_INTERVAL		10000 /* ms */
 #define JITTER_DELAY			500 /* ms */
diff --git a/include/linux/soc/samsung/s3c-adc.h b/include/linux/soc/samsung/s3c-adc.h
new file mode 100644
index 000000000000..591c94ef957d
--- /dev/null
+++ b/include/linux/soc/samsung/s3c-adc.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2008 Simtec Electronics
+ *	http://armlinux.simtec.co.uk/	
+ *	Ben Dooks <ben@simtec.co.uk>
+ *
+ * S3C ADC driver information
+ */
+
+#ifndef __LINUX_SOC_SAMSUNG_S3C_ADC_H
+#define __LINUX_SOC_SAMSUNG_S3C_ADC_H __FILE__
+
+struct s3c_adc_client;
+struct platform_device;
+
+extern int s3c_adc_start(struct s3c_adc_client *client,
+			 unsigned int channel, unsigned int nr_samples);
+
+extern int s3c_adc_read(struct s3c_adc_client *client, unsigned int ch);
+
+extern struct s3c_adc_client *
+	s3c_adc_register(struct platform_device *pdev,
+			 void (*select)(struct s3c_adc_client *client,
+					unsigned selected),
+			 void (*conv)(struct s3c_adc_client *client,
+				      unsigned d0, unsigned d1,
+				      unsigned *samples_left),
+			 unsigned int is_ts);
+
+extern void s3c_adc_release(struct s3c_adc_client *client);
+
+#endif /* __LINUX_SOC_SAMSUNG_S3C_ADC_H */
-- 
cgit v1.2.3


From f131a4443ea468cd532410c271c229bb39caab08 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 3 Sep 2019 11:31:09 +0200
Subject: ARM: s3c24xx: move spi fiq handler into platform

The fiq handler needs access to some register definitions that
should not be used directly by device drivers.

Since this is closely related to the irqchip driver anyway,
move it into the same place.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
[krzk: Add a header guard in include/linux/spi/s3c24xx-fiq.h, fix
       SPDX comment style, update maintainer's entry]
Co-developed-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Link: https://lore.kernel.org/r/20200806182059.2431-23-krzk%40kernel.org
Acked-by: Mark Brown <broonie@kernel.org>
---
 MAINTAINERS                                     |   1 +
 arch/arm/mach-s3c24xx/Makefile                  |   2 +
 arch/arm/mach-s3c24xx/irq-s3c24xx-fiq-exports.c |   9 ++
 arch/arm/mach-s3c24xx/irq-s3c24xx-fiq.S         | 115 ++++++++++++++++++++++++
 drivers/spi/Makefile                            |   1 -
 drivers/spi/spi-s3c24xx-fiq.S                   | 115 ------------------------
 drivers/spi/spi-s3c24xx-fiq.h                   |  23 -----
 drivers/spi/spi-s3c24xx.c                       |   7 +-
 include/linux/spi/s3c24xx-fiq.h                 |  33 +++++++
 9 files changed, 161 insertions(+), 145 deletions(-)
 create mode 100644 arch/arm/mach-s3c24xx/irq-s3c24xx-fiq-exports.c
 create mode 100644 arch/arm/mach-s3c24xx/irq-s3c24xx-fiq.S
 delete mode 100644 drivers/spi/spi-s3c24xx-fiq.S
 delete mode 100644 drivers/spi/spi-s3c24xx-fiq.h
 create mode 100644 include/linux/spi/s3c24xx-fiq.h

(limited to 'include/linux')

diff --git a/MAINTAINERS b/MAINTAINERS
index 45906c58ff4a..a14144691ca5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15317,6 +15317,7 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/spi/spi-samsung.txt
 F:	drivers/spi/spi-s3c*
 F:	include/linux/platform_data/spi-s3c64xx.h
+F:	include/linux/spi/s3c24xx-fiq.h
 
 SAMSUNG SXGBE DRIVERS
 M:	Byungho An <bh74.an@samsung.com>
diff --git a/arch/arm/mach-s3c24xx/Makefile b/arch/arm/mach-s3c24xx/Makefile
index 3ad297bd6b4a..b69eee24940b 100644
--- a/arch/arm/mach-s3c24xx/Makefile
+++ b/arch/arm/mach-s3c24xx/Makefile
@@ -9,6 +9,8 @@
 
 obj-y				+= common.o
 obj-y				+= irq-s3c24xx.o
+obj-$(CONFIG_SPI_S3C24XX_FIQ)	+= irq-s3c24xx-fiq.o
+obj-$(CONFIG_SPI_S3C24XX_FIQ)	+= irq-s3c24xx-fiq-exports.o
 
 obj-$(CONFIG_CPU_S3C2410)	+= s3c2410.o
 obj-$(CONFIG_S3C2410_PLL)	+= pll-s3c2410.o
diff --git a/arch/arm/mach-s3c24xx/irq-s3c24xx-fiq-exports.c b/arch/arm/mach-s3c24xx/irq-s3c24xx-fiq-exports.c
new file mode 100644
index 000000000000..84cf86376ded
--- /dev/null
+++ b/arch/arm/mach-s3c24xx/irq-s3c24xx-fiq-exports.c
@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/stddef.h>
+#include <linux/export.h>
+#include <linux/spi/s3c24xx-fiq.h>
+
+EXPORT_SYMBOL(s3c24xx_spi_fiq_rx);
+EXPORT_SYMBOL(s3c24xx_spi_fiq_txrx);
+EXPORT_SYMBOL(s3c24xx_spi_fiq_tx);
diff --git a/arch/arm/mach-s3c24xx/irq-s3c24xx-fiq.S b/arch/arm/mach-s3c24xx/irq-s3c24xx-fiq.S
new file mode 100644
index 000000000000..2a84535a14fd
--- /dev/null
+++ b/arch/arm/mach-s3c24xx/irq-s3c24xx-fiq.S
@@ -0,0 +1,115 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* linux/drivers/spi/spi_s3c24xx_fiq.S
+ *
+ * Copyright 2009 Simtec Electronics
+ *	Ben Dooks <ben@simtec.co.uk>
+ *
+ * S3C24XX SPI - FIQ pseudo-DMA transfer code
+*/
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+#include <mach/map.h>
+#include <mach/regs-irq.h>
+
+#include <linux/spi/s3c24xx-fiq.h>
+
+#define S3C2410_SPTDAT           (0x10)
+#define S3C2410_SPRDAT           (0x14)
+
+	.text
+
+	@ entry to these routines is as follows, with the register names
+	@ defined in fiq.h so that they can be shared with the C files which
+	@ setup the calling registers.
+	@
+	@ fiq_rirq	The base of the IRQ registers to find S3C2410_SRCPND
+	@ fiq_rtmp	Temporary register to hold tx/rx data
+	@ fiq_rspi	The base of the SPI register block
+	@ fiq_rtx	The tx buffer pointer
+	@ fiq_rrx	The rx buffer pointer
+	@ fiq_rcount	The number of bytes to move
+
+	@ each entry starts with a word entry of how long it is
+	@ and an offset to the irq acknowledgment word
+
+ENTRY(s3c24xx_spi_fiq_rx)
+s3c24xx_spi_fix_rx:
+	.word	fiq_rx_end - fiq_rx_start
+	.word	fiq_rx_irq_ack - fiq_rx_start
+fiq_rx_start:
+	ldr	fiq_rtmp, fiq_rx_irq_ack
+	str	fiq_rtmp, [ fiq_rirq, # S3C2410_SRCPND - S3C24XX_VA_IRQ ]
+
+	ldrb	fiq_rtmp, [ fiq_rspi, #  S3C2410_SPRDAT ]
+	strb	fiq_rtmp, [ fiq_rrx ], #1
+
+	mov	fiq_rtmp, #0xff
+	strb	fiq_rtmp, [ fiq_rspi, # S3C2410_SPTDAT ]
+
+	subs	fiq_rcount, fiq_rcount, #1
+	subnes	pc, lr, #4		@@ return, still have work to do
+
+	@@ set IRQ controller so that next op will trigger IRQ
+	mov	fiq_rtmp, #0
+	str	fiq_rtmp, [ fiq_rirq, # S3C2410_INTMOD  - S3C24XX_VA_IRQ ]
+	subs	pc, lr, #4
+
+fiq_rx_irq_ack:
+	.word	0
+fiq_rx_end:
+
+ENTRY(s3c24xx_spi_fiq_txrx)
+s3c24xx_spi_fiq_txrx:
+	.word	fiq_txrx_end - fiq_txrx_start
+	.word	fiq_txrx_irq_ack - fiq_txrx_start
+fiq_txrx_start:
+
+	ldrb	fiq_rtmp, [ fiq_rspi, #  S3C2410_SPRDAT ]
+	strb	fiq_rtmp, [ fiq_rrx ], #1
+
+	ldr	fiq_rtmp, fiq_txrx_irq_ack
+	str	fiq_rtmp, [ fiq_rirq, # S3C2410_SRCPND - S3C24XX_VA_IRQ ]
+
+	ldrb	fiq_rtmp, [ fiq_rtx ], #1
+	strb	fiq_rtmp, [ fiq_rspi, # S3C2410_SPTDAT ]
+
+	subs	fiq_rcount, fiq_rcount, #1
+	subnes	pc, lr, #4		@@ return, still have work to do
+
+	mov	fiq_rtmp, #0
+	str	fiq_rtmp, [ fiq_rirq, # S3C2410_INTMOD  - S3C24XX_VA_IRQ ]
+	subs	pc, lr, #4
+
+fiq_txrx_irq_ack:
+	.word	0
+
+fiq_txrx_end:
+
+ENTRY(s3c24xx_spi_fiq_tx)
+s3c24xx_spi_fix_tx:
+	.word	fiq_tx_end - fiq_tx_start
+	.word	fiq_tx_irq_ack - fiq_tx_start
+fiq_tx_start:
+	ldrb	fiq_rtmp, [ fiq_rspi, #  S3C2410_SPRDAT ]
+
+	ldr	fiq_rtmp, fiq_tx_irq_ack
+	str	fiq_rtmp, [ fiq_rirq, # S3C2410_SRCPND - S3C24XX_VA_IRQ ]
+
+	ldrb	fiq_rtmp, [ fiq_rtx ], #1
+	strb	fiq_rtmp, [ fiq_rspi, # S3C2410_SPTDAT ]
+
+	subs	fiq_rcount, fiq_rcount, #1
+	subnes	pc, lr, #4		@@ return, still have work to do
+
+	mov	fiq_rtmp, #0
+	str	fiq_rtmp, [ fiq_rirq, # S3C2410_INTMOD  - S3C24XX_VA_IRQ ]
+	subs	pc, lr, #4
+
+fiq_tx_irq_ack:
+	.word	0
+
+fiq_tx_end:
+
+	.end
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index cf955ea803cd..eba6fb607aa2 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -97,7 +97,6 @@ obj-$(CONFIG_SPI_RPCIF)			+= spi-rpc-if.o
 obj-$(CONFIG_SPI_RSPI)			+= spi-rspi.o
 obj-$(CONFIG_SPI_S3C24XX)		+= spi-s3c24xx-hw.o
 spi-s3c24xx-hw-y			:= spi-s3c24xx.o
-spi-s3c24xx-hw-$(CONFIG_SPI_S3C24XX_FIQ) += spi-s3c24xx-fiq.o
 obj-$(CONFIG_SPI_S3C64XX)		+= spi-s3c64xx.o
 obj-$(CONFIG_SPI_SC18IS602)		+= spi-sc18is602.o
 obj-$(CONFIG_SPI_SH)			+= spi-sh.o
diff --git a/drivers/spi/spi-s3c24xx-fiq.S b/drivers/spi/spi-s3c24xx-fiq.S
deleted file mode 100644
index 9d5f8f1e5e81..000000000000
--- a/drivers/spi/spi-s3c24xx-fiq.S
+++ /dev/null
@@ -1,115 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/* linux/drivers/spi/spi_s3c24xx_fiq.S
- *
- * Copyright 2009 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * S3C24XX SPI - FIQ pseudo-DMA transfer code
-*/
-
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-
-#include <mach/map.h>
-#include <mach/regs-irq.h>
-
-#include "spi-s3c24xx-fiq.h"
-
-#define S3C2410_SPTDAT           (0x10)
-#define S3C2410_SPRDAT           (0x14)
-
-	.text
-
-	@ entry to these routines is as follows, with the register names
-	@ defined in fiq.h so that they can be shared with the C files which
-	@ setup the calling registers.
-	@
-	@ fiq_rirq	The base of the IRQ registers to find S3C2410_SRCPND
-	@ fiq_rtmp	Temporary register to hold tx/rx data
-	@ fiq_rspi	The base of the SPI register block
-	@ fiq_rtx	The tx buffer pointer
-	@ fiq_rrx	The rx buffer pointer
-	@ fiq_rcount	The number of bytes to move
-
-	@ each entry starts with a word entry of how long it is
-	@ and an offset to the irq acknowledgment word
-
-ENTRY(s3c24xx_spi_fiq_rx)
-s3c24xx_spi_fix_rx:
-	.word	fiq_rx_end - fiq_rx_start
-	.word	fiq_rx_irq_ack - fiq_rx_start
-fiq_rx_start:
-	ldr	fiq_rtmp, fiq_rx_irq_ack
-	str	fiq_rtmp, [ fiq_rirq, # S3C2410_SRCPND - S3C24XX_VA_IRQ ]
-
-	ldrb	fiq_rtmp, [ fiq_rspi, #  S3C2410_SPRDAT ]
-	strb	fiq_rtmp, [ fiq_rrx ], #1
-
-	mov	fiq_rtmp, #0xff
-	strb	fiq_rtmp, [ fiq_rspi, # S3C2410_SPTDAT ]
-
-	subs	fiq_rcount, fiq_rcount, #1
-	subnes	pc, lr, #4		@@ return, still have work to do
-
-	@@ set IRQ controller so that next op will trigger IRQ
-	mov	fiq_rtmp, #0
-	str	fiq_rtmp, [ fiq_rirq, # S3C2410_INTMOD  - S3C24XX_VA_IRQ ]
-	subs	pc, lr, #4
-
-fiq_rx_irq_ack:
-	.word	0
-fiq_rx_end:
-
-ENTRY(s3c24xx_spi_fiq_txrx)
-s3c24xx_spi_fiq_txrx:
-	.word	fiq_txrx_end - fiq_txrx_start
-	.word	fiq_txrx_irq_ack - fiq_txrx_start
-fiq_txrx_start:
-
-	ldrb	fiq_rtmp, [ fiq_rspi, #  S3C2410_SPRDAT ]
-	strb	fiq_rtmp, [ fiq_rrx ], #1
-
-	ldr	fiq_rtmp, fiq_txrx_irq_ack
-	str	fiq_rtmp, [ fiq_rirq, # S3C2410_SRCPND - S3C24XX_VA_IRQ ]
-
-	ldrb	fiq_rtmp, [ fiq_rtx ], #1
-	strb	fiq_rtmp, [ fiq_rspi, # S3C2410_SPTDAT ]
-
-	subs	fiq_rcount, fiq_rcount, #1
-	subnes	pc, lr, #4		@@ return, still have work to do
-
-	mov	fiq_rtmp, #0
-	str	fiq_rtmp, [ fiq_rirq, # S3C2410_INTMOD  - S3C24XX_VA_IRQ ]
-	subs	pc, lr, #4
-
-fiq_txrx_irq_ack:
-	.word	0
-
-fiq_txrx_end:
-
-ENTRY(s3c24xx_spi_fiq_tx)
-s3c24xx_spi_fix_tx:
-	.word	fiq_tx_end - fiq_tx_start
-	.word	fiq_tx_irq_ack - fiq_tx_start
-fiq_tx_start:
-	ldrb	fiq_rtmp, [ fiq_rspi, #  S3C2410_SPRDAT ]
-
-	ldr	fiq_rtmp, fiq_tx_irq_ack
-	str	fiq_rtmp, [ fiq_rirq, # S3C2410_SRCPND - S3C24XX_VA_IRQ ]
-
-	ldrb	fiq_rtmp, [ fiq_rtx ], #1
-	strb	fiq_rtmp, [ fiq_rspi, # S3C2410_SPTDAT ]
-
-	subs	fiq_rcount, fiq_rcount, #1
-	subnes	pc, lr, #4		@@ return, still have work to do
-
-	mov	fiq_rtmp, #0
-	str	fiq_rtmp, [ fiq_rirq, # S3C2410_INTMOD  - S3C24XX_VA_IRQ ]
-	subs	pc, lr, #4
-
-fiq_tx_irq_ack:
-	.word	0
-
-fiq_tx_end:
-
-	.end
diff --git a/drivers/spi/spi-s3c24xx-fiq.h b/drivers/spi/spi-s3c24xx-fiq.h
deleted file mode 100644
index 7786b0ea56ec..000000000000
--- a/drivers/spi/spi-s3c24xx-fiq.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/* linux/drivers/spi/spi_s3c24xx_fiq.h
- *
- * Copyright 2009 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * S3C24XX SPI - FIQ pseudo-DMA transfer support
-*/
-
-/* We have R8 through R13 to play with */
-
-#ifdef __ASSEMBLY__
-#define __REG_NR(x)     r##x
-#else
-#define __REG_NR(x)     (x)
-#endif
-
-#define fiq_rspi	__REG_NR(8)
-#define fiq_rtmp	__REG_NR(9)
-#define fiq_rrx		__REG_NR(10)
-#define fiq_rtx		__REG_NR(11)
-#define fiq_rcount	__REG_NR(12)
-#define fiq_rirq	__REG_NR(13)
diff --git a/drivers/spi/spi-s3c24xx.c b/drivers/spi/spi-s3c24xx.c
index 0691248c7c0d..6ac6f0b6f237 100644
--- a/drivers/spi/spi-s3c24xx.c
+++ b/drivers/spi/spi-s3c24xx.c
@@ -19,12 +19,12 @@
 #include <linux/spi/spi.h>
 #include <linux/spi/spi_bitbang.h>
 #include <linux/spi/s3c24xx.h>
+#include <linux/spi/s3c24xx-fiq.h>
 #include <linux/module.h>
 
 #include <asm/fiq.h>
 
 #include "spi-s3c24xx-regs.h"
-#include "spi-s3c24xx-fiq.h"
 
 /**
  * s3c24xx_spi_devstate - per device data
@@ -229,10 +229,6 @@ struct spi_fiq_code {
 	u8	data[];
 };
 
-extern struct spi_fiq_code s3c24xx_spi_fiq_txrx;
-extern struct spi_fiq_code s3c24xx_spi_fiq_tx;
-extern struct spi_fiq_code s3c24xx_spi_fiq_rx;
-
 /**
  * ack_bit - turn IRQ into IRQ acknowledgement bit
  * @irq: The interrupt number
@@ -282,7 +278,6 @@ static void s3c24xx_spi_tryfiq(struct s3c24xx_spi *hw)
 	regs.uregs[fiq_rrx]  = (long)hw->rx;
 	regs.uregs[fiq_rtx]  = (long)hw->tx + 1;
 	regs.uregs[fiq_rcount] = hw->len - 1;
-	regs.uregs[fiq_rirq] = (long)S3C24XX_VA_IRQ;
 
 	set_fiq_regs(&regs);
 
diff --git a/include/linux/spi/s3c24xx-fiq.h b/include/linux/spi/s3c24xx-fiq.h
new file mode 100644
index 000000000000..d2842ac1de27
--- /dev/null
+++ b/include/linux/spi/s3c24xx-fiq.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* linux/drivers/spi/spi_s3c24xx_fiq.h
+ *
+ * Copyright 2009 Simtec Electronics
+ *	Ben Dooks <ben@simtec.co.uk>
+ *
+ * S3C24XX SPI - FIQ pseudo-DMA transfer support
+*/
+
+#ifndef __LINUX_SPI_S3C24XX_FIQ_H
+#define __LINUX_SPI_S3C24XX_FIQ_H __FILE__
+
+/* We have R8 through R13 to play with */
+
+#ifdef __ASSEMBLY__
+#define __REG_NR(x)     r##x
+#else
+
+extern struct spi_fiq_code s3c24xx_spi_fiq_txrx;
+extern struct spi_fiq_code s3c24xx_spi_fiq_tx;
+extern struct spi_fiq_code s3c24xx_spi_fiq_rx;
+
+#define __REG_NR(x)     (x)
+#endif
+
+#define fiq_rspi	__REG_NR(8)
+#define fiq_rtmp	__REG_NR(9)
+#define fiq_rrx		__REG_NR(10)
+#define fiq_rtx		__REG_NR(11)
+#define fiq_rcount	__REG_NR(12)
+#define fiq_rirq	__REG_NR(13)
+
+#endif /* __LINUX_SPI_S3C24XX_FIQ_H */
-- 
cgit v1.2.3


From b558b6c24068d87ffcd95dad3bf0d9bd2ac290e9 Mon Sep 17 00:00:00 2001
From: Maciej Żenczykowski <maze@google.com>
Date: Tue, 18 Aug 2020 18:07:09 -0700
Subject: net-tun: Add type safety to tun_xdp_to_ptr() and tun_ptr_to_xdp()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This reduces likelihood of incorrect use.

Test: builds

Signed-off-by: Maciej Żenczykowski <maze@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200819010710.3959310-1-zenczykowski@gmail.com
---
 drivers/net/tun.c      | 6 +++---
 include/linux/if_tun.h | 8 ++++----
 2 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 3c11a77f5709..5dd7f353eeef 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -225,13 +225,13 @@ bool tun_is_xdp_frame(void *ptr)
 }
 EXPORT_SYMBOL(tun_is_xdp_frame);
 
-void *tun_xdp_to_ptr(void *ptr)
+void *tun_xdp_to_ptr(struct xdp_frame *xdp)
 {
-	return (void *)((unsigned long)ptr | TUN_XDP_FLAG);
+	return (void *)((unsigned long)xdp | TUN_XDP_FLAG);
 }
 EXPORT_SYMBOL(tun_xdp_to_ptr);
 
-void *tun_ptr_to_xdp(void *ptr)
+struct xdp_frame *tun_ptr_to_xdp(void *ptr)
 {
 	return (void *)((unsigned long)ptr & ~TUN_XDP_FLAG);
 }
diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h
index 5bda8cf457b6..6c37e1dbc5df 100644
--- a/include/linux/if_tun.h
+++ b/include/linux/if_tun.h
@@ -28,8 +28,8 @@ struct tun_xdp_hdr {
 struct socket *tun_get_socket(struct file *);
 struct ptr_ring *tun_get_tx_ring(struct file *file);
 bool tun_is_xdp_frame(void *ptr);
-void *tun_xdp_to_ptr(void *ptr);
-void *tun_ptr_to_xdp(void *ptr);
+void *tun_xdp_to_ptr(struct xdp_frame *xdp);
+struct xdp_frame *tun_ptr_to_xdp(void *ptr);
 void tun_ptr_free(void *ptr);
 #else
 #include <linux/err.h>
@@ -48,11 +48,11 @@ static inline bool tun_is_xdp_frame(void *ptr)
 {
 	return false;
 }
-static inline void *tun_xdp_to_ptr(void *ptr)
+static inline void *tun_xdp_to_ptr(struct xdp_frame *xdp)
 {
 	return NULL;
 }
-static inline void *tun_ptr_to_xdp(void *ptr)
+static inline struct xdp_frame *tun_ptr_to_xdp(void *ptr)
 {
 	return NULL;
 }
-- 
cgit v1.2.3


From 596b5ef458f903d4362fb3c69967b6d8a23334bd Mon Sep 17 00:00:00 2001
From: Maciej Żenczykowski <maze@google.com>
Date: Tue, 18 Aug 2020 18:07:10 -0700
Subject: net-tun: Eliminate two tun/xdp related function calls from vhost-net
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This provides a minor performance boost by virtue of inlining
instead of cross module function calls.

Test: builds

Signed-off-by: Maciej Żenczykowski <maze@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200819010710.3959310-2-zenczykowski@gmail.com
---
 drivers/net/tun.c      | 18 ------------------
 include/linux/if_tun.h | 15 ++++++++++++---
 2 files changed, 12 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 5dd7f353eeef..efaef83b8897 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -219,24 +219,6 @@ struct veth {
 	__be16 h_vlan_TCI;
 };
 
-bool tun_is_xdp_frame(void *ptr)
-{
-	return (unsigned long)ptr & TUN_XDP_FLAG;
-}
-EXPORT_SYMBOL(tun_is_xdp_frame);
-
-void *tun_xdp_to_ptr(struct xdp_frame *xdp)
-{
-	return (void *)((unsigned long)xdp | TUN_XDP_FLAG);
-}
-EXPORT_SYMBOL(tun_xdp_to_ptr);
-
-struct xdp_frame *tun_ptr_to_xdp(void *ptr)
-{
-	return (void *)((unsigned long)ptr & ~TUN_XDP_FLAG);
-}
-EXPORT_SYMBOL(tun_ptr_to_xdp);
-
 static int tun_napi_receive(struct napi_struct *napi, int budget)
 {
 	struct tun_file *tfile = container_of(napi, struct tun_file, napi);
diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h
index 6c37e1dbc5df..2a7660843444 100644
--- a/include/linux/if_tun.h
+++ b/include/linux/if_tun.h
@@ -27,9 +27,18 @@ struct tun_xdp_hdr {
 #if defined(CONFIG_TUN) || defined(CONFIG_TUN_MODULE)
 struct socket *tun_get_socket(struct file *);
 struct ptr_ring *tun_get_tx_ring(struct file *file);
-bool tun_is_xdp_frame(void *ptr);
-void *tun_xdp_to_ptr(struct xdp_frame *xdp);
-struct xdp_frame *tun_ptr_to_xdp(void *ptr);
+static inline bool tun_is_xdp_frame(void *ptr)
+{
+       return (unsigned long)ptr & TUN_XDP_FLAG;
+}
+static inline void *tun_xdp_to_ptr(struct xdp_frame *xdp)
+{
+       return (void *)((unsigned long)xdp | TUN_XDP_FLAG);
+}
+static inline struct xdp_frame *tun_ptr_to_xdp(void *ptr)
+{
+       return (void *)((unsigned long)ptr & ~TUN_XDP_FLAG);
+}
 void tun_ptr_free(void *ptr);
 #else
 #include <linux/err.h>
-- 
cgit v1.2.3


From bdfbb63c314a6fb7d27dddd62f5a3e4f062b92bb Mon Sep 17 00:00:00 2001
From: Kurt Kanzenbach <kurt@linutronix.de>
Date: Tue, 18 Aug 2020 12:32:43 +0200
Subject: ptp: Add generic ptp v2 header parsing function

Reason: A lot of the ptp drivers - which implement hardware time stamping - need
specific fields such as the sequence id from the ptp v2 header. Currently all
drivers implement that themselves.

Introduce a generic function to retrieve a pointer to the start of the ptp v2
header.

Suggested-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Kurt Kanzenbach <kurt@linutronix.de>
Reviewed-by: Richard Cochran <richardcochran@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ptp_classify.h | 44 ++++++++++++++++++++++++++++++++++++++++++++
 net/core/ptp_classifier.c    | 30 ++++++++++++++++++++++++++++++
 2 files changed, 74 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h
index dd00fa41f7e7..0a9cc0eb0801 100644
--- a/include/linux/ptp_classify.h
+++ b/include/linux/ptp_classify.h
@@ -44,6 +44,30 @@
 #define OFF_IHL		14
 #define IPV4_HLEN(data) (((struct iphdr *)(data + OFF_IHL))->ihl << 2)
 
+struct clock_identity {
+	u8 id[8];
+} __packed;
+
+struct port_identity {
+	struct clock_identity	clock_identity;
+	__be16			port_number;
+} __packed;
+
+struct ptp_header {
+	u8			tsmt;  /* transportSpecific | messageType */
+	u8			ver;   /* reserved          | versionPTP  */
+	__be16			message_length;
+	u8			domain_number;
+	u8			reserved1;
+	u8			flag_field[2];
+	__be64			correction;
+	__be32			reserved2;
+	struct port_identity	source_port_identity;
+	__be16			sequence_id;
+	u8			control;
+	u8			log_message_interval;
+} __packed;
+
 #if defined(CONFIG_NET_PTP_CLASSIFY)
 /**
  * ptp_classify_raw - classify a PTP packet
@@ -57,6 +81,21 @@
  */
 unsigned int ptp_classify_raw(const struct sk_buff *skb);
 
+/**
+ * ptp_parse_header - Get pointer to the PTP v2 header
+ * @skb: packet buffer
+ * @type: type of the packet (see ptp_classify_raw())
+ *
+ * This function takes care of the VLAN, UDP, IPv4 and IPv6 headers. The length
+ * is checked.
+ *
+ * Note, internally skb_mac_header() is used. Make sure that the @skb is
+ * initialized accordingly.
+ *
+ * Return: Pointer to the ptp v2 header or NULL if not found
+ */
+struct ptp_header *ptp_parse_header(struct sk_buff *skb, unsigned int type);
+
 void __init ptp_classifier_init(void);
 #else
 static inline void ptp_classifier_init(void)
@@ -66,5 +105,10 @@ static inline unsigned int ptp_classify_raw(struct sk_buff *skb)
 {
 	return PTP_CLASS_NONE;
 }
+static inline struct ptp_header *ptp_parse_header(struct sk_buff *skb,
+						  unsigned int type)
+{
+	return NULL;
+}
 #endif
 #endif /* _PTP_CLASSIFY_H_ */
diff --git a/net/core/ptp_classifier.c b/net/core/ptp_classifier.c
index d964a5147f22..e33fde06d528 100644
--- a/net/core/ptp_classifier.c
+++ b/net/core/ptp_classifier.c
@@ -107,6 +107,36 @@ unsigned int ptp_classify_raw(const struct sk_buff *skb)
 }
 EXPORT_SYMBOL_GPL(ptp_classify_raw);
 
+struct ptp_header *ptp_parse_header(struct sk_buff *skb, unsigned int type)
+{
+	u8 *ptr = skb_mac_header(skb);
+
+	if (type & PTP_CLASS_VLAN)
+		ptr += VLAN_HLEN;
+
+	switch (type & PTP_CLASS_PMASK) {
+	case PTP_CLASS_IPV4:
+		ptr += IPV4_HLEN(ptr) + UDP_HLEN;
+		break;
+	case PTP_CLASS_IPV6:
+		ptr += IP6_HLEN + UDP_HLEN;
+		break;
+	case PTP_CLASS_L2:
+		break;
+	default:
+		return NULL;
+	}
+
+	ptr += ETH_HLEN;
+
+	/* Ensure that the entire header is present in this packet. */
+	if (ptr + sizeof(struct ptp_header) > skb->data + skb->len)
+		return NULL;
+
+	return (struct ptp_header *)ptr;
+}
+EXPORT_SYMBOL_GPL(ptp_parse_header);
+
 void __init ptp_classifier_init(void)
 {
 	static struct sock_filter ptp_filter[] __initdata = {
-- 
cgit v1.2.3


From 036c508ba95e573f53bd5bbb79b0c4d71003b319 Mon Sep 17 00:00:00 2001
From: Kurt Kanzenbach <kurt@linutronix.de>
Date: Tue, 18 Aug 2020 12:32:44 +0200
Subject: ptp: Add generic ptp message type function

The message type is located at different offsets within the ptp header depending
on the ptp version (v1 or v2). Therefore, drivers which also deal with ptp v1
have some code for it.

Extract this into a helper function for drivers to be used.

Signed-off-by: Kurt Kanzenbach <kurt@linutronix.de>
Reviewed-by: Richard Cochran <richardcochran@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ptp_classify.h | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h
index 0a9cc0eb0801..cfc6d9152f69 100644
--- a/include/linux/ptp_classify.h
+++ b/include/linux/ptp_classify.h
@@ -96,6 +96,31 @@ unsigned int ptp_classify_raw(const struct sk_buff *skb);
  */
 struct ptp_header *ptp_parse_header(struct sk_buff *skb, unsigned int type);
 
+/**
+ * ptp_get_msgtype - Extract ptp message type from given header
+ * @hdr: ptp header
+ * @type: type of the packet (see ptp_classify_raw())
+ *
+ * This function returns the message type for a given ptp header. It takes care
+ * of the different ptp header versions (v1 or v2).
+ *
+ * Return: The message type
+ */
+static inline u8 ptp_get_msgtype(const struct ptp_header *hdr,
+				 unsigned int type)
+{
+	u8 msgtype;
+
+	if (unlikely(type & PTP_CLASS_V1)) {
+		/* msg type is located at the control field for ptp v1 */
+		msgtype = hdr->control;
+	} else {
+		msgtype = hdr->tsmt & 0x0f;
+	}
+
+	return msgtype;
+}
+
 void __init ptp_classifier_init(void);
 #else
 static inline void ptp_classifier_init(void)
-- 
cgit v1.2.3


From 17060fb5069f2c73a566015ce6e019d5685680b5 Mon Sep 17 00:00:00 2001
From: Kurt Kanzenbach <kurt@linutronix.de>
Date: Tue, 18 Aug 2020 12:32:51 +0200
Subject: ptp: Remove unused macro

The offset for the control field is not needed anymore. Remove it.

Signed-off-by: Kurt Kanzenbach <kurt@linutronix.de>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ptp_classify.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h
index cfc6d9152f69..8437307cca8c 100644
--- a/include/linux/ptp_classify.h
+++ b/include/linux/ptp_classify.h
@@ -36,7 +36,6 @@
 
 #define OFF_PTP_SOURCE_UUID	22 /* PTPv1 only */
 #define OFF_PTP_SEQUENCE_ID	30
-#define OFF_PTP_CONTROL		32 /* PTPv1 only */
 
 /* Below defines should actually be removed at some point in time. */
 #define IP6_HLEN	40
-- 
cgit v1.2.3


From cad6967ac10843a70842cd39c7b53412901dd21f Mon Sep 17 00:00:00 2001
From: Christian Brauner <christian.brauner@ubuntu.com>
Date: Wed, 19 Aug 2020 12:46:45 +0200
Subject: fork: introduce kernel_clone()

The old _do_fork() helper doesn't follow naming conventions of in-kernel
helpers for syscalls. The process creation cleanup in [1] didn't change the
name to something more reasonable mainly because _do_fork() was used in quite a
few places. So sending this as a separate series seemed the better strategy.

This commit does two things:
1. renames _do_fork() to kernel_clone() but keeps _do_fork() as a simple static
   inline wrapper around kernel_clone().
2. Changes the return type from long to pid_t. This aligns kernel_thread() and
   kernel_clone(). Also, the return value from kernel_clone that is surfaced in
   fork(), vfork(), clone(), and clone3() is taken from pid_vrn() which returns
   a pid_t too.

Follow-up patches will switch each caller of _do_fork() and each place where it
is referenced over to kernel_clone(). After all these changes are done, we can
remove _do_fork() completely and will only be left with kernel_clone().

[1]: 9ba27414f2ec ("Merge tag 'fork-v5.9' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux")

Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org>
Link: https://lore.kernel.org/r/20200819104655.436656-2-christian.brauner@ubuntu.com
---
 include/linux/sched/task.h |  6 +++++-
 kernel/fork.c              | 16 ++++++++--------
 2 files changed, 13 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index a98965007eef..d4428039c3c1 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -83,7 +83,11 @@ extern void do_group_exit(int);
 extern void exit_files(struct task_struct *);
 extern void exit_itimers(struct signal_struct *);
 
-extern long _do_fork(struct kernel_clone_args *kargs);
+extern pid_t kernel_clone(struct kernel_clone_args *kargs);
+static inline long _do_fork(struct kernel_clone_args *kargs)
+{
+	return kernel_clone(kargs);
+}
 struct task_struct *fork_idle(int);
 struct mm_struct *copy_init_mm(void);
 extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
diff --git a/kernel/fork.c b/kernel/fork.c
index 4d32190861bd..d822c7a4b9c4 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2384,14 +2384,14 @@ struct mm_struct *copy_init_mm(void)
  *
  * args->exit_signal is expected to be checked for sanity by the caller.
  */
-long _do_fork(struct kernel_clone_args *args)
+pid_t kernel_clone(struct kernel_clone_args *args)
 {
 	u64 clone_flags = args->flags;
 	struct completion vfork;
 	struct pid *pid;
 	struct task_struct *p;
 	int trace = 0;
-	long nr;
+	pid_t nr;
 
 	/*
 	 * For legacy clone() calls, CLONE_PIDFD uses the parent_tid argument
@@ -2477,7 +2477,7 @@ pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
 		.stack_size	= (unsigned long)arg,
 	};
 
-	return _do_fork(&args);
+	return kernel_clone(&args);
 }
 
 #ifdef __ARCH_WANT_SYS_FORK
@@ -2488,7 +2488,7 @@ SYSCALL_DEFINE0(fork)
 		.exit_signal = SIGCHLD,
 	};
 
-	return _do_fork(&args);
+	return kernel_clone(&args);
 #else
 	/* can not support in nommu mode */
 	return -EINVAL;
@@ -2504,7 +2504,7 @@ SYSCALL_DEFINE0(vfork)
 		.exit_signal	= SIGCHLD,
 	};
 
-	return _do_fork(&args);
+	return kernel_clone(&args);
 }
 #endif
 
@@ -2542,7 +2542,7 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
 		.tls		= tls,
 	};
 
-	return _do_fork(&args);
+	return kernel_clone(&args);
 }
 #endif
 
@@ -2700,7 +2700,7 @@ SYSCALL_DEFINE2(clone3, struct clone_args __user *, uargs, size_t, size)
 	if (!clone3_args_valid(&kargs))
 		return -EINVAL;
 
-	return _do_fork(&kargs);
+	return kernel_clone(&kargs);
 }
 #endif
 
@@ -2863,7 +2863,7 @@ int unshare_fd(unsigned long unshare_flags, unsigned int max_fds,
 /*
  * unshare allows a process to 'unshare' part of the process
  * context which was originally shared using clone.  copy_*
- * functions used by _do_fork() cannot be used here directly
+ * functions used by kernel_clone() cannot be used here directly
  * because they modify an inactive task_struct that is being
  * constructed. Here we are modifying the current, active,
  * task_struct.
-- 
cgit v1.2.3


From 06fe45634942dc96c316bbb789049a4b0b692542 Mon Sep 17 00:00:00 2001
From: Christian Brauner <christian.brauner@ubuntu.com>
Date: Wed, 19 Aug 2020 12:46:55 +0200
Subject: sched: remove _do_fork()

Now that all callers of _do_fork() have been switched to kernel_clone() remove
the _do_fork() helper.

Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
Link: https://lore.kernel.org/r/20200819104655.436656-12-christian.brauner@ubuntu.com
---
 include/linux/sched/task.h | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index d4428039c3c1..85fb2f34c59b 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -84,10 +84,6 @@ extern void exit_files(struct task_struct *);
 extern void exit_itimers(struct signal_struct *);
 
 extern pid_t kernel_clone(struct kernel_clone_args *kargs);
-static inline long _do_fork(struct kernel_clone_args *kargs)
-{
-	return kernel_clone(kargs);
-}
 struct task_struct *fork_idle(int);
 struct mm_struct *copy_init_mm(void);
 extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
-- 
cgit v1.2.3


From 005142b8a1f0f32d33fbe04b728464c1b7acfa0e Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Tue, 18 Aug 2020 21:27:56 -0700
Subject: bpf: Factor out bpf_link_by_id() helper.

Refactor the code a bit to extract bpf_link_by_id() helper.
It's similar to existing bpf_prog_by_id().

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20200819042759.51280-2-alexei.starovoitov@gmail.com
---
 include/linux/bpf.h  |  1 +
 kernel/bpf/syscall.c | 46 ++++++++++++++++++++++++++++------------------
 2 files changed, 29 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 55f694b63164..a9b7185a6b37 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1358,6 +1358,7 @@ int btf_check_type_match(struct bpf_verifier_env *env, struct bpf_prog *prog,
 			 struct btf *btf, const struct btf_type *t);
 
 struct bpf_prog *bpf_prog_by_id(u32 id);
+struct bpf_link *bpf_link_by_id(u32 id);
 
 const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id);
 #else /* !CONFIG_BPF_SYSCALL */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 86299a292214..689d736b6904 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -4014,40 +4014,50 @@ static int link_detach(union bpf_attr *attr)
 	return ret;
 }
 
-static int bpf_link_inc_not_zero(struct bpf_link *link)
+static struct bpf_link *bpf_link_inc_not_zero(struct bpf_link *link)
 {
-	return atomic64_fetch_add_unless(&link->refcnt, 1, 0) ? 0 : -ENOENT;
+	return atomic64_fetch_add_unless(&link->refcnt, 1, 0) ? link : ERR_PTR(-ENOENT);
 }
 
-#define BPF_LINK_GET_FD_BY_ID_LAST_FIELD link_id
-
-static int bpf_link_get_fd_by_id(const union bpf_attr *attr)
+struct bpf_link *bpf_link_by_id(u32 id)
 {
 	struct bpf_link *link;
-	u32 id = attr->link_id;
-	int fd, err;
 
-	if (CHECK_ATTR(BPF_LINK_GET_FD_BY_ID))
-		return -EINVAL;
-
-	if (!capable(CAP_SYS_ADMIN))
-		return -EPERM;
+	if (!id)
+		return ERR_PTR(-ENOENT);
 
 	spin_lock_bh(&link_idr_lock);
-	link = idr_find(&link_idr, id);
 	/* before link is "settled", ID is 0, pretend it doesn't exist yet */
+	link = idr_find(&link_idr, id);
 	if (link) {
 		if (link->id)
-			err = bpf_link_inc_not_zero(link);
+			link = bpf_link_inc_not_zero(link);
 		else
-			err = -EAGAIN;
+			link = ERR_PTR(-EAGAIN);
 	} else {
-		err = -ENOENT;
+		link = ERR_PTR(-ENOENT);
 	}
 	spin_unlock_bh(&link_idr_lock);
+	return link;
+}
 
-	if (err)
-		return err;
+#define BPF_LINK_GET_FD_BY_ID_LAST_FIELD link_id
+
+static int bpf_link_get_fd_by_id(const union bpf_attr *attr)
+{
+	struct bpf_link *link;
+	u32 id = attr->link_id;
+	int fd;
+
+	if (CHECK_ATTR(BPF_LINK_GET_FD_BY_ID))
+		return -EINVAL;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	link = bpf_link_by_id(id);
+	if (IS_ERR(link))
+		return PTR_ERR(link);
 
 	fd = bpf_link_new_fd(link);
 	if (fd < 0)
-- 
cgit v1.2.3


From f67f6c00c7f367fe90f2bc01b9a977aa13de870e Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 6 Aug 2020 20:20:46 +0200
Subject: ARM: s3c24xx: move s3cmci pinctrl handling into board files

Rather than call the internal s3c_gpio_cfgall_range() function
through a platform header, move the code into the set_power
callback that is already exported by the board, and add
a default implementation.

In DT mode, the code already does not set the pin config,
so nothing changes there.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Ulf Hansson <ulf.hansson@linaro.org>
Link: https://lore.kernel.org/r/20200806182059.2431-29-krzk@kernel.org
[krzk: Rebase and correct set_power in mach-h1940.c]
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
---
 arch/arm/mach-s3c24xx/include/mach/pm-core.h |  1 +
 arch/arm/mach-s3c24xx/mach-amlm5900.c        | 15 ++++++
 arch/arm/mach-s3c24xx/mach-at2440evb.c       | 10 +++-
 arch/arm/mach-s3c24xx/mach-gta02.c           | 15 ++++++
 arch/arm/mach-s3c24xx/mach-h1940.c           |  9 ++++
 arch/arm/mach-s3c24xx/mach-mini2440.c        |  9 +++-
 arch/arm/mach-s3c24xx/mach-n30.c             |  9 ++++
 arch/arm/mach-s3c24xx/mach-qt2410.c          | 15 ++++++
 arch/arm/mach-s3c24xx/mach-rx1950.c          |  9 ++++
 arch/arm/mach-s3c24xx/mach-tct_hammer.c      | 15 ++++++
 arch/arm/plat-samsung/devs.c                 | 29 ++++++++++++
 drivers/mmc/host/s3cmci.c                    | 71 +++++++---------------------
 include/linux/platform_data/mmc-s3cmci.h     |  2 +
 13 files changed, 153 insertions(+), 56 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/mach-s3c24xx/include/mach/pm-core.h b/arch/arm/mach-s3c24xx/include/mach/pm-core.h
index 8f87606c4cdc..a22b4a37ee57 100644
--- a/arch/arm/mach-s3c24xx/include/mach/pm-core.h
+++ b/arch/arm/mach-s3c24xx/include/mach/pm-core.h
@@ -12,6 +12,7 @@
 
 #include "regs-clock.h"
 #include "regs-irq.h"
+#include <mach/irqs.h>
 
 static inline void s3c_pm_debug_init_uart(void)
 {
diff --git a/arch/arm/mach-s3c24xx/mach-amlm5900.c b/arch/arm/mach-s3c24xx/mach-amlm5900.c
index 6324e608dcda..1a2a9259b4b6 100644
--- a/arch/arm/mach-s3c24xx/mach-amlm5900.c
+++ b/arch/arm/mach-s3c24xx/mach-amlm5900.c
@@ -13,6 +13,7 @@
 #include <linux/list.h>
 #include <linux/timer.h>
 #include <linux/init.h>
+#include <linux/gpio/machine.h>
 #include <linux/gpio.h>
 #include <linux/device.h>
 #include <linux/platform_device.h>
@@ -121,6 +122,19 @@ static struct s3c2410_uartcfg amlm5900_uartcfgs[] = {
 	}
 };
 
+static struct gpiod_lookup_table amlm5900_mmc_gpio_table = {
+	.dev_id = "s3c2410-sdi",
+	.table = {
+		/* bus pins */
+		GPIO_LOOKUP_IDX("GPIOE",  5, "bus", 0, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  6, "bus", 1, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  7, "bus", 2, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  8, "bus", 3, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  9, "bus", 4, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE", 10, "bus", 5, GPIO_ACTIVE_HIGH),
+		{ },
+	},
+};
 
 static struct platform_device *amlm5900_devices[] __initdata = {
 #ifdef CONFIG_FB_S3C2410
@@ -216,6 +230,7 @@ static void __init amlm5900_init(void)
 	s3c24xx_fb_set_platdata(&amlm5900_fb_info);
 #endif
 	s3c_i2c0_set_platdata(NULL);
+	gpiod_add_lookup_table(&amlm5900_mmc_gpio_table);
 	platform_add_devices(amlm5900_devices, ARRAY_SIZE(amlm5900_devices));
 }
 
diff --git a/arch/arm/mach-s3c24xx/mach-at2440evb.c b/arch/arm/mach-s3c24xx/mach-at2440evb.c
index fe8f9f1bdc0a..a2693246b3ca 100644
--- a/arch/arm/mach-s3c24xx/mach-at2440evb.c
+++ b/arch/arm/mach-s3c24xx/mach-at2440evb.c
@@ -134,7 +134,7 @@ static struct platform_device at2440evb_device_eth = {
 };
 
 static struct s3c24xx_mci_pdata at2440evb_mci_pdata __initdata = {
-	/* Intentionally left blank */
+	.set_power	= s3c24xx_mci_def_set_power,
 };
 
 static struct gpiod_lookup_table at2440evb_mci_gpio_table = {
@@ -142,10 +142,18 @@ static struct gpiod_lookup_table at2440evb_mci_gpio_table = {
 	.table = {
 		/* Card detect S3C2410_GPG(10) */
 		GPIO_LOOKUP("GPIOG", 10, "cd", GPIO_ACTIVE_LOW),
+		/* bus pins */
+		GPIO_LOOKUP_IDX("GPIOE",  5, "bus", 0, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  6, "bus", 1, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  7, "bus", 2, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  8, "bus", 3, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  9, "bus", 4, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE", 10, "bus", 5, GPIO_ACTIVE_HIGH),
 		{ },
 	},
 };
 
+
 /* 7" LCD panel */
 
 static struct s3c2410fb_display at2440evb_lcd_cfg __initdata = {
diff --git a/arch/arm/mach-s3c24xx/mach-gta02.c b/arch/arm/mach-s3c24xx/mach-gta02.c
index 3c7f2a3d00a5..c023e261a240 100644
--- a/arch/arm/mach-s3c24xx/mach-gta02.c
+++ b/arch/arm/mach-s3c24xx/mach-gta02.c
@@ -487,6 +487,20 @@ static struct platform_device gta02_audio = {
 	.id = -1,
 };
 
+static struct gpiod_lookup_table gta02_mmc_gpio_table = {
+	.dev_id = "s3c2410-sdi",
+	.table = {
+		/* bus pins */
+		GPIO_LOOKUP_IDX("GPIOE",  5, "bus", 0, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  6, "bus", 1, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  7, "bus", 2, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  8, "bus", 3, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  9, "bus", 4, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE", 10, "bus", 5, GPIO_ACTIVE_HIGH),
+		{ },
+	},
+};
+
 static void __init gta02_map_io(void)
 {
 	s3c24xx_init_io(gta02_iodesc, ARRAY_SIZE(gta02_iodesc));
@@ -543,6 +557,7 @@ static void __init gta02_machine_init(void)
 			      S3C_GPIO_PULL_NONE);
 
 	gpiod_add_lookup_table(&gta02_audio_gpio_table);
+	gpiod_add_lookup_table(&gta02_mmc_gpio_table);
 	platform_add_devices(gta02_devices, ARRAY_SIZE(gta02_devices));
 	pm_power_off = gta02_poweroff;
 
diff --git a/arch/arm/mach-s3c24xx/mach-h1940.c b/arch/arm/mach-s3c24xx/mach-h1940.c
index 1f18ac4e84b2..e9b3b048a96d 100644
--- a/arch/arm/mach-s3c24xx/mach-h1940.c
+++ b/arch/arm/mach-s3c24xx/mach-h1940.c
@@ -445,6 +445,8 @@ static struct platform_device h1940_device_bluetooth = {
 
 static void h1940_set_mmc_power(unsigned char power_mode, unsigned short vdd)
 {
+	s3c24xx_mci_def_set_power(power_mode, vdd);
+
 	switch (power_mode) {
 	case MMC_POWER_OFF:
 		gpio_set_value(H1940_LATCH_SD_POWER, 0);
@@ -470,6 +472,13 @@ static struct gpiod_lookup_table h1940_mmc_gpio_table = {
 		GPIO_LOOKUP("GPIOF", 5, "cd", GPIO_ACTIVE_LOW),
 		/* Write protect S3C2410_GPH(8) */
 		GPIO_LOOKUP("GPIOH", 8, "wp", GPIO_ACTIVE_LOW),
+		/* bus pins */
+		GPIO_LOOKUP_IDX("GPIOE",  5, "bus", 0, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  6, "bus", 1, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  7, "bus", 2, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  8, "bus", 3, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  9, "bus", 4, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE", 10, "bus", 5, GPIO_ACTIVE_HIGH),
 		{ },
 	},
 };
diff --git a/arch/arm/mach-s3c24xx/mach-mini2440.c b/arch/arm/mach-s3c24xx/mach-mini2440.c
index 0bd2746f19a6..d3cc0141f58c 100644
--- a/arch/arm/mach-s3c24xx/mach-mini2440.c
+++ b/arch/arm/mach-s3c24xx/mach-mini2440.c
@@ -234,7 +234,7 @@ static struct s3c2410fb_mach_info mini2440_fb_info __initdata = {
 
 static struct s3c24xx_mci_pdata mini2440_mmc_cfg __initdata = {
 	.wprotect_invert	= 1,
-	.set_power		= NULL,
+	.set_power		= s3c24xx_mci_def_set_power,
 	.ocr_avail		= MMC_VDD_32_33|MMC_VDD_33_34,
 };
 
@@ -245,6 +245,13 @@ static struct gpiod_lookup_table mini2440_mmc_gpio_table = {
 		GPIO_LOOKUP("GPIOG", 8, "cd", GPIO_ACTIVE_LOW),
 		/* Write protect S3C2410_GPH(8) */
 		GPIO_LOOKUP("GPIOH", 8, "wp", GPIO_ACTIVE_HIGH),
+		/* bus pins */
+		GPIO_LOOKUP_IDX("GPIOE",  5, "bus", 0, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  6, "bus", 1, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  7, "bus", 2, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  8, "bus", 3, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  9, "bus", 4, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE", 10, "bus", 5, GPIO_ACTIVE_HIGH),
 		{ },
 	},
 };
diff --git a/arch/arm/mach-s3c24xx/mach-n30.c b/arch/arm/mach-s3c24xx/mach-n30.c
index 9410fcb82340..24e97646b068 100644
--- a/arch/arm/mach-s3c24xx/mach-n30.c
+++ b/arch/arm/mach-s3c24xx/mach-n30.c
@@ -368,6 +368,8 @@ static struct s3c2410fb_mach_info n30_fb_info __initdata = {
 
 static void n30_sdi_set_power(unsigned char power_mode, unsigned short vdd)
 {
+	s3c24xx_mci_def_set_power(power_mode, vdd);
+
 	switch (power_mode) {
 	case MMC_POWER_ON:
 	case MMC_POWER_UP:
@@ -393,6 +395,13 @@ static struct gpiod_lookup_table n30_mci_gpio_table = {
 		/* Write protect S3C2410_GPG(10) */
 		GPIO_LOOKUP("GPIOG", 10, "wp", GPIO_ACTIVE_LOW),
 		{ },
+		/* bus pins */
+		GPIO_LOOKUP_IDX("GPIOE",  5, "bus", 0, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  6, "bus", 1, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  7, "bus", 2, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  8, "bus", 3, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  9, "bus", 4, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE", 10, "bus", 5, GPIO_ACTIVE_HIGH),
 	},
 };
 
diff --git a/arch/arm/mach-s3c24xx/mach-qt2410.c b/arch/arm/mach-s3c24xx/mach-qt2410.c
index 5e33f3da629e..b21f7fbcadf9 100644
--- a/arch/arm/mach-s3c24xx/mach-qt2410.c
+++ b/arch/arm/mach-s3c24xx/mach-qt2410.c
@@ -223,6 +223,20 @@ static struct gpiod_lookup_table qt2410_spi_gpiod_table = {
 	},
 };
 
+static struct gpiod_lookup_table qt2410_mmc_gpiod_table = {
+	.dev_id = "s3c2410-sdi",
+	.table = {
+		/* bus pins */
+		GPIO_LOOKUP_IDX("GPIOE",  5, "bus", 0, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  6, "bus", 1, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  7, "bus", 2, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  8, "bus", 3, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  9, "bus", 4, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE", 10, "bus", 5, GPIO_ACTIVE_HIGH),
+		{ },
+	},
+};
+
 /* Board devices */
 
 static struct platform_device *qt2410_devices[] __initdata = {
@@ -347,6 +361,7 @@ static void __init qt2410_machine_init(void)
 	gpiod_add_lookup_table(&qt2410_spi_gpiod_table);
 	s3c_gpio_setpull(S3C2410_GPB(0), S3C_GPIO_PULL_NONE);
 	gpiod_add_lookup_table(&qt2410_led_gpio_table);
+	gpiod_add_lookup_table(&qt2410_mmc_gpiod_table);
 	platform_add_devices(qt2410_devices, ARRAY_SIZE(qt2410_devices));
 	s3c_pm_init();
 }
diff --git a/arch/arm/mach-s3c24xx/mach-rx1950.c b/arch/arm/mach-s3c24xx/mach-rx1950.c
index 86d348f33972..aa91785a95b5 100644
--- a/arch/arm/mach-s3c24xx/mach-rx1950.c
+++ b/arch/arm/mach-s3c24xx/mach-rx1950.c
@@ -548,6 +548,8 @@ static struct platform_device rx1950_backlight = {
 
 static void rx1950_set_mmc_power(unsigned char power_mode, unsigned short vdd)
 {
+	s3c24xx_mci_def_set_power(power_mode, vdd);
+
 	switch (power_mode) {
 	case MMC_POWER_OFF:
 		gpio_direction_output(S3C2410_GPJ(1), 0);
@@ -573,6 +575,13 @@ static struct gpiod_lookup_table rx1950_mmc_gpio_table = {
 		GPIO_LOOKUP("GPIOF", 5, "cd", GPIO_ACTIVE_LOW),
 		/* Write protect S3C2410_GPH(8) */
 		GPIO_LOOKUP("GPIOH", 8, "wp", GPIO_ACTIVE_LOW),
+		/* bus pins */
+		GPIO_LOOKUP_IDX("GPIOE",  5, "bus", 0, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  6, "bus", 1, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  7, "bus", 2, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  8, "bus", 3, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  9, "bus", 4, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE", 10, "bus", 5, GPIO_ACTIVE_HIGH),
 		{ },
 	},
 };
diff --git a/arch/arm/mach-s3c24xx/mach-tct_hammer.c b/arch/arm/mach-s3c24xx/mach-tct_hammer.c
index fd51a098e443..8092be7b47db 100644
--- a/arch/arm/mach-s3c24xx/mach-tct_hammer.c
+++ b/arch/arm/mach-s3c24xx/mach-tct_hammer.c
@@ -7,6 +7,7 @@
 // derived from linux/arch/arm/mach-s3c2410/mach-bast.c, written by
 // Ben Dooks <ben@simtec.co.uk>
 
+#include <linux/gpio/machine.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/interrupt.h>
@@ -101,6 +102,19 @@ static struct s3c2410_uartcfg tct_hammer_uartcfgs[] = {
 	}
 };
 
+static struct gpiod_lookup_table tct_hammer_mmc_gpio_table = {
+	.dev_id = "s3c2410-sdi",
+	.table = {
+		/* bus pins */
+		GPIO_LOOKUP_IDX("GPIOE",  5, "bus", 0, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  6, "bus", 1, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  7, "bus", 2, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  8, "bus", 3, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE",  9, "bus", 4, GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP_IDX("GPIOE", 10, "bus", 5, GPIO_ACTIVE_HIGH),
+		{ },
+	},
+};
 
 static struct platform_device *tct_hammer_devices[] __initdata = {
 	&s3c_device_adc,
@@ -129,6 +143,7 @@ static void __init tct_hammer_init_time(void)
 static void __init tct_hammer_init(void)
 {
 	s3c_i2c0_set_platdata(NULL);
+	gpiod_add_lookup_table(&tct_hammer_mmc_gpio_table);
 	platform_add_devices(tct_hammer_devices, ARRAY_SIZE(tct_hammer_devices));
 }
 
diff --git a/arch/arm/plat-samsung/devs.c b/arch/arm/plat-samsung/devs.c
index c42e4a272cc7..b16be04c0169 100644
--- a/arch/arm/plat-samsung/devs.c
+++ b/arch/arm/plat-samsung/devs.c
@@ -5,6 +5,7 @@
 //
 // Base Samsung platform device definitions
 
+#include <linux/gpio.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/interrupt.h>
@@ -39,6 +40,7 @@
 
 #include <mach/irqs.h>
 #include <mach/map.h>
+#include <mach/gpio-samsung.h>
 
 #ifdef CONFIG_PLAT_S3C24XX
 #include <mach/regs-s3c2443-clock.h>
@@ -46,6 +48,7 @@
 
 #include <plat/cpu.h>
 #include <plat/devs.h>
+#include <plat/gpio-cfg.h>
 #include <linux/soc/samsung/s3c-adc.h>
 #include <linux/platform_data/ata-samsung_cf.h>
 #include <plat/fb.h>
@@ -835,16 +838,42 @@ struct platform_device s3c_device_rtc = {
 /* SDI */
 
 #ifdef CONFIG_PLAT_S3C24XX
+void s3c24xx_mci_def_set_power(unsigned char power_mode, unsigned short vdd)
+{
+	switch (power_mode) {
+	case MMC_POWER_ON:
+	case MMC_POWER_UP:
+		/* Configure GPE5...GPE10 pins in SD mode */
+		s3c_gpio_cfgall_range(S3C2410_GPE(5), 6, S3C_GPIO_SFN(2),
+				      S3C_GPIO_PULL_NONE);
+		break;
+
+	case MMC_POWER_OFF:
+	default:
+		gpio_direction_output(S3C2410_GPE(5), 0);
+		break;
+	}
+}
+
 static struct resource s3c_sdi_resource[] = {
 	[0] = DEFINE_RES_MEM(S3C24XX_PA_SDI, S3C24XX_SZ_SDI),
 	[1] = DEFINE_RES_IRQ(IRQ_SDI),
 };
 
+static struct s3c24xx_mci_pdata s3cmci_def_pdata = {
+	/* This is currently here to avoid a number of if (host->pdata)
+	 * checks. Any zero fields to ensure reasonable defaults are picked. */
+	.no_wprotect = 1,
+	.no_detect = 1,
+	.set_power = s3c24xx_mci_def_set_power,
+};
+
 struct platform_device s3c_device_sdi = {
 	.name		= "s3c2410-sdi",
 	.id		= -1,
 	.num_resources	= ARRAY_SIZE(s3c_sdi_resource),
 	.resource	= s3c_sdi_resource,
+	.dev.platform_data = &s3cmci_def_pdata,
 };
 
 void __init s3c24xx_mci_set_platdata(struct s3c24xx_mci_pdata *pdata)
diff --git a/drivers/mmc/host/s3cmci.c b/drivers/mmc/host/s3cmci.c
index ee98f1e3a1c7..52d1f5e9d7c7 100644
--- a/drivers/mmc/host/s3cmci.c
+++ b/drivers/mmc/host/s3cmci.c
@@ -24,10 +24,6 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/mmc/slot-gpio.h>
-
-#include <plat/gpio-cfg.h>
-#include <mach/gpio-samsung.h>
-
 #include <linux/platform_data/mmc-s3cmci.h>
 
 #include "s3cmci.h"
@@ -306,7 +302,8 @@ static inline void clear_imask(struct s3cmci_host *host)
 static void s3cmci_check_sdio_irq(struct s3cmci_host *host)
 {
 	if (host->sdio_irqen) {
-		if (gpio_get_value(S3C2410_GPE(8)) == 0) {
+		if (host->pdata->bus[3] &&
+		    gpiod_get_value(host->pdata->bus[3]) == 0) {
 			pr_debug("%s: signalling irq\n", __func__);
 			mmc_signal_sdio_irq(host->mmc);
 		}
@@ -1205,33 +1202,20 @@ static void s3cmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	switch (ios->power_mode) {
 	case MMC_POWER_ON:
 	case MMC_POWER_UP:
-		/* Configure GPE5...GPE10 pins in SD mode */
-		if (!host->pdev->dev.of_node)
-			s3c_gpio_cfgall_range(S3C2410_GPE(5), 6, S3C_GPIO_SFN(2),
-					      S3C_GPIO_PULL_NONE);
-
-		if (host->pdata->set_power)
-			host->pdata->set_power(ios->power_mode, ios->vdd);
-
 		if (!host->is2440)
 			mci_con |= S3C2410_SDICON_FIFORESET;
-
 		break;
 
 	case MMC_POWER_OFF:
 	default:
-		if (!host->pdev->dev.of_node)
-			gpio_direction_output(S3C2410_GPE(5), 0);
-
 		if (host->is2440)
 			mci_con |= S3C2440_SDICON_SDRESET;
-
-		if (host->pdata->set_power)
-			host->pdata->set_power(ios->power_mode, ios->vdd);
-
 		break;
 	}
 
+	if (host->pdata->set_power)
+		host->pdata->set_power(ios->power_mode, ios->vdd);
+
 	s3cmci_set_clk(host, ios);
 
 	/* Set CLOCK_ENABLE */
@@ -1309,13 +1293,6 @@ static const struct mmc_host_ops s3cmci_ops = {
 	.enable_sdio_irq = s3cmci_enable_sdio_irq,
 };
 
-static struct s3c24xx_mci_pdata s3cmci_def_pdata = {
-	/* This is currently here to avoid a number of if (host->pdata)
-	 * checks. Any zero fields to ensure reasonable defaults are picked. */
-	 .no_wprotect = 1,
-	 .no_detect = 1,
-};
-
 #ifdef CONFIG_ARM_S3C24XX_CPUFREQ
 
 static int s3cmci_cpufreq_transition(struct notifier_block *nb,
@@ -1469,24 +1446,21 @@ static int s3cmci_probe_pdata(struct s3cmci_host *host)
 	int i, ret;
 
 	host->is2440 = platform_get_device_id(pdev)->driver_data;
+	pdata = pdev->dev.platform_data;
+	if (!pdata) {
+		dev_err(&pdev->dev, "need platform data");
+		return -ENXIO;
+	}
 
-	for (i = S3C2410_GPE(5); i <= S3C2410_GPE(10); i++) {
-		ret = gpio_request(i, dev_name(&pdev->dev));
-		if (ret) {
+	for (i = 0; i < 6; i++) {
+		pdata->bus[i] = devm_gpiod_get_index(&pdev->dev, "bus", i,
+						     GPIOD_OUT_LOW);
+		if (IS_ERR(pdata->bus[i])) {
 			dev_err(&pdev->dev, "failed to get gpio %d\n", i);
-
-			for (i--; i >= S3C2410_GPE(5); i--)
-				gpio_free(i);
-
-			return ret;
+			return PTR_ERR(pdata->bus[i]);
 		}
 	}
 
-	if (!pdev->dev.platform_data)
-		pdev->dev.platform_data = &s3cmci_def_pdata;
-
-	pdata = pdev->dev.platform_data;
-
 	if (pdata->no_wprotect)
 		mmc->caps2 |= MMC_CAP2_NO_WRITE_PROTECT;
 
@@ -1541,7 +1515,6 @@ static int s3cmci_probe(struct platform_device *pdev)
 	struct s3cmci_host *host;
 	struct mmc_host	*mmc;
 	int ret;
-	int i;
 
 	mmc = mmc_alloc_host(sizeof(struct s3cmci_host), &pdev->dev);
 	if (!mmc) {
@@ -1585,7 +1558,7 @@ static int s3cmci_probe(struct platform_device *pdev)
 			"failed to get io memory region resource.\n");
 
 		ret = -ENOENT;
-		goto probe_free_gpio;
+		goto probe_free_host;
 	}
 
 	host->mem = request_mem_region(host->mem->start,
@@ -1594,7 +1567,7 @@ static int s3cmci_probe(struct platform_device *pdev)
 	if (!host->mem) {
 		dev_err(&pdev->dev, "failed to request io memory region.\n");
 		ret = -ENOENT;
-		goto probe_free_gpio;
+		goto probe_free_host;
 	}
 
 	host->base = ioremap(host->mem->start, resource_size(host->mem));
@@ -1718,11 +1691,6 @@ static int s3cmci_probe(struct platform_device *pdev)
  probe_free_mem_region:
 	release_mem_region(host->mem->start, resource_size(host->mem));
 
- probe_free_gpio:
-	if (!pdev->dev.of_node)
-		for (i = S3C2410_GPE(5); i <= S3C2410_GPE(10); i++)
-			gpio_free(i);
-
  probe_free_host:
 	mmc_free_host(mmc);
 
@@ -1748,7 +1716,6 @@ static int s3cmci_remove(struct platform_device *pdev)
 {
 	struct mmc_host		*mmc  = platform_get_drvdata(pdev);
 	struct s3cmci_host	*host = mmc_priv(mmc);
-	int i;
 
 	s3cmci_shutdown(pdev);
 
@@ -1761,10 +1728,6 @@ static int s3cmci_remove(struct platform_device *pdev)
 
 	free_irq(host->irq, host);
 
-	if (!pdev->dev.of_node)
-		for (i = S3C2410_GPE(5); i <= S3C2410_GPE(10); i++)
-			gpio_free(i);
-
 	iounmap(host->base);
 	release_mem_region(host->mem->start, resource_size(host->mem));
 
diff --git a/include/linux/platform_data/mmc-s3cmci.h b/include/linux/platform_data/mmc-s3cmci.h
index 33310b11cbdd..bacb86db3112 100644
--- a/include/linux/platform_data/mmc-s3cmci.h
+++ b/include/linux/platform_data/mmc-s3cmci.h
@@ -35,6 +35,7 @@ struct s3c24xx_mci_pdata {
 	unsigned long	ocr_avail;
 	void		(*set_power)(unsigned char power_mode,
 				     unsigned short vdd);
+	struct gpio_desc *bus[6];
 };
 
 /**
@@ -44,6 +45,7 @@ struct s3c24xx_mci_pdata {
  * Copy the platform data supplied by @pdata so that this can be marked
  * __initdata.
  */
+extern void s3c24xx_mci_def_set_power(unsigned char power_mode, unsigned short vdd);
 extern void s3c24xx_mci_set_platdata(struct s3c24xx_mci_pdata *pdata);
 
 #endif /* _ARCH_NCI_H */
-- 
cgit v1.2.3


From cd4bd8f9435ddf08a8677f56abf418423f223959 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 6 Aug 2020 20:20:48 +0200
Subject: ARM: s3c24xx: spi: avoid hardcoding fiq number in driver

The IRQ_EINT0 constant is a platform detail that is
defined in mach/irqs.h and not visible to drivers once
that header is made private.

Since the same calculation already happens in s3c24xx_set_fiq,
just return the value from there.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20200806182059.2431-31-krzk@kernel.org
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
---
 arch/arm/mach-s3c24xx/irq-s3c24xx.c | 12 +++++++++---
 drivers/spi/spi-s3c24xx.c           | 18 ++----------------
 include/linux/spi/s3c24xx.h         |  2 +-
 3 files changed, 12 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/mach-s3c24xx/irq-s3c24xx.c b/arch/arm/mach-s3c24xx/irq-s3c24xx.c
index b0e879ee14c1..3965347cacf0 100644
--- a/arch/arm/mach-s3c24xx/irq-s3c24xx.c
+++ b/arch/arm/mach-s3c24xx/irq-s3c24xx.c
@@ -376,14 +376,17 @@ asmlinkage void __exception_irq_entry s3c24xx_handle_irq(struct pt_regs *regs)
 /**
  * s3c24xx_set_fiq - set the FIQ routing
  * @irq: IRQ number to route to FIQ on processor.
+ * @ack_ptr: pointer to a location for storing the bit mask
  * @on: Whether to route @irq to the FIQ, or to remove the FIQ routing.
  *
  * Change the state of the IRQ to FIQ routing depending on @irq and @on. If
  * @on is true, the @irq is checked to see if it can be routed and the
  * interrupt controller updated to route the IRQ. If @on is false, the FIQ
  * routing is cleared, regardless of which @irq is specified.
+ *
+ * returns the mask value for the register.
  */
-int s3c24xx_set_fiq(unsigned int irq, bool on)
+int s3c24xx_set_fiq(unsigned int irq, u32 *ack_ptr, bool on)
 {
 	u32 intmod;
 	unsigned offs;
@@ -391,15 +394,18 @@ int s3c24xx_set_fiq(unsigned int irq, bool on)
 	if (on) {
 		offs = irq - FIQ_START;
 		if (offs > 31)
-			return -EINVAL;
+			return 0;
 
 		intmod = 1 << offs;
 	} else {
 		intmod = 0;
 	}
 
+	if (ack_ptr)
+		*ack_ptr = intmod;
 	writel_relaxed(intmod, S3C2410_INTMOD);
-	return 0;
+
+	return intmod;
 }
 
 EXPORT_SYMBOL_GPL(s3c24xx_set_fiq);
diff --git a/drivers/spi/spi-s3c24xx.c b/drivers/spi/spi-s3c24xx.c
index 6ac6f0b6f237..9138a315aa4f 100644
--- a/drivers/spi/spi-s3c24xx.c
+++ b/drivers/spi/spi-s3c24xx.c
@@ -229,17 +229,6 @@ struct spi_fiq_code {
 	u8	data[];
 };
 
-/**
- * ack_bit - turn IRQ into IRQ acknowledgement bit
- * @irq: The interrupt number
- *
- * Returns the bit to write to the interrupt acknowledge register.
- */
-static inline u32 ack_bit(unsigned int irq)
-{
-	return 1 << (irq - IRQ_EINT0);
-}
-
 /**
  * s3c24xx_spi_tryfiq - attempt to claim and setup FIQ for transfer
  * @hw: The hardware state.
@@ -256,6 +245,7 @@ static void s3c24xx_spi_tryfiq(struct s3c24xx_spi *hw)
 	struct pt_regs regs;
 	enum spi_fiq_mode mode;
 	struct spi_fiq_code *code;
+	u32 *ack_ptr = NULL;
 	int ret;
 
 	if (!hw->fiq_claimed) {
@@ -282,8 +272,6 @@ static void s3c24xx_spi_tryfiq(struct s3c24xx_spi *hw)
 	set_fiq_regs(&regs);
 
 	if (hw->fiq_mode != mode) {
-		u32 *ack_ptr;
-
 		hw->fiq_mode = mode;
 
 		switch (mode) {
@@ -303,12 +291,10 @@ static void s3c24xx_spi_tryfiq(struct s3c24xx_spi *hw)
 		BUG_ON(!code);
 
 		ack_ptr = (u32 *)&code->data[code->ack_offset];
-		*ack_ptr = ack_bit(hw->irq);
-
 		set_fiq_handler(&code->data, code->length);
 	}
 
-	s3c24xx_set_fiq(hw->irq, true);
+	s3c24xx_set_fiq(hw->irq, ack_ptr, true);
 
 	hw->fiq_mode = mode;
 	hw->fiq_inuse = 1;
diff --git a/include/linux/spi/s3c24xx.h b/include/linux/spi/s3c24xx.h
index c91d10b82f08..440a71593162 100644
--- a/include/linux/spi/s3c24xx.h
+++ b/include/linux/spi/s3c24xx.h
@@ -20,6 +20,6 @@ struct s3c2410_spi_info {
 	void (*set_cs)(struct s3c2410_spi_info *spi, int cs, int pol);
 };
 
-extern int s3c24xx_set_fiq(unsigned int irq, bool on);
+extern int s3c24xx_set_fiq(unsigned int irq, u32 *ack_ptr, bool on);
 
 #endif /* __LINUX_SPI_S3C24XX_H */
-- 
cgit v1.2.3


From 81994e0ffc373e67ace4c98797c35f8213f07753 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 2 Sep 2019 22:33:24 +0200
Subject: fbdev: s3c2410fb: remove mach header dependency

The s3c2410fb driver is too deeply intertwined with the s3c24xx
platform code. Change it in a way that avoids the use of platform
header files but having all interface data in a platform_data
header, and the private register definitions next to the driver
itself.

One ugly bit here is that the driver pokes directly into gpio
registers, which are owned by another driver. Passing the
mapped addresses in platform_data is somewhat suboptimal, but
it is a small improvement over the previous version.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20200806182059.2431-33-krzk@kernel.org
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
---
 arch/arm/mach-s3c24xx/include/mach/fb.h         |   2 -
 arch/arm/mach-s3c24xx/include/mach/regs-lcd.h   | 157 ------------------------
 arch/arm/mach-s3c24xx/mach-amlm5900.c           |   7 +-
 arch/arm/mach-s3c24xx/mach-anubis.c             |   1 -
 arch/arm/mach-s3c24xx/mach-at2440evb.c          |   3 +-
 arch/arm/mach-s3c24xx/mach-bast.c               |   3 +-
 arch/arm/mach-s3c24xx/mach-gta02.c              |   2 +-
 arch/arm/mach-s3c24xx/mach-h1940.c              |   7 +-
 arch/arm/mach-s3c24xx/mach-jive.c               |  10 +-
 arch/arm/mach-s3c24xx/mach-mini2440.c           |   9 +-
 arch/arm/mach-s3c24xx/mach-n30.c                |   3 +-
 arch/arm/mach-s3c24xx/mach-osiris.c             |   1 -
 arch/arm/mach-s3c24xx/mach-qt2410.c             |   3 +-
 arch/arm/mach-s3c24xx/mach-rx1950.c             |   8 +-
 arch/arm/mach-s3c24xx/mach-rx3715.c             |   7 +-
 arch/arm/mach-s3c24xx/mach-smdk2413.c           |   3 +-
 arch/arm/mach-s3c24xx/mach-smdk2416.c           |   1 -
 arch/arm/mach-s3c24xx/mach-smdk2440.c           |   8 +-
 arch/arm/mach-s3c24xx/mach-smdk2443.c           |   3 +-
 arch/arm/mach-s3c24xx/mach-vstms.c              |   3 +-
 arch/arm/plat-samsung/devs.c                    |   2 +-
 arch/arm/plat-samsung/include/plat/fb-s3c2410.h |  68 ----------
 drivers/video/fbdev/s3c2410fb-regs-lcd.h        | 143 +++++++++++++++++++++
 drivers/video/fbdev/s3c2410fb.c                 |  16 +--
 include/linux/platform_data/fb-s3c2410.h        |  99 +++++++++++++++
 25 files changed, 301 insertions(+), 268 deletions(-)
 delete mode 100644 arch/arm/mach-s3c24xx/include/mach/fb.h
 delete mode 100644 arch/arm/mach-s3c24xx/include/mach/regs-lcd.h
 delete mode 100644 arch/arm/plat-samsung/include/plat/fb-s3c2410.h
 create mode 100644 drivers/video/fbdev/s3c2410fb-regs-lcd.h
 create mode 100644 include/linux/platform_data/fb-s3c2410.h

(limited to 'include/linux')

diff --git a/arch/arm/mach-s3c24xx/include/mach/fb.h b/arch/arm/mach-s3c24xx/include/mach/fb.h
deleted file mode 100644
index 4e539cb8b884..000000000000
--- a/arch/arm/mach-s3c24xx/include/mach/fb.h
+++ /dev/null
@@ -1,2 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#include <plat/fb-s3c2410.h>
diff --git a/arch/arm/mach-s3c24xx/include/mach/regs-lcd.h b/arch/arm/mach-s3c24xx/include/mach/regs-lcd.h
deleted file mode 100644
index 4c3434f261bb..000000000000
--- a/arch/arm/mach-s3c24xx/include/mach/regs-lcd.h
+++ /dev/null
@@ -1,157 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (c) 2003 Simtec Electronics <linux@simtec.co.uk>
- *		      http://www.simtec.co.uk/products/SWLINUX/
- */
-
-#ifndef ___ASM_ARCH_REGS_LCD_H
-#define ___ASM_ARCH_REGS_LCD_H
-
-#define S3C2410_LCDREG(x)	(x)
-
-/* LCD control registers */
-#define S3C2410_LCDCON1	    S3C2410_LCDREG(0x00)
-#define S3C2410_LCDCON2	    S3C2410_LCDREG(0x04)
-#define S3C2410_LCDCON3	    S3C2410_LCDREG(0x08)
-#define S3C2410_LCDCON4	    S3C2410_LCDREG(0x0C)
-#define S3C2410_LCDCON5	    S3C2410_LCDREG(0x10)
-
-#define S3C2410_LCDCON1_CLKVAL(x)  ((x) << 8)
-#define S3C2410_LCDCON1_MMODE	   (1<<7)
-#define S3C2410_LCDCON1_DSCAN4	   (0<<5)
-#define S3C2410_LCDCON1_STN4	   (1<<5)
-#define S3C2410_LCDCON1_STN8	   (2<<5)
-#define S3C2410_LCDCON1_TFT	   (3<<5)
-
-#define S3C2410_LCDCON1_STN1BPP	   (0<<1)
-#define S3C2410_LCDCON1_STN2GREY   (1<<1)
-#define S3C2410_LCDCON1_STN4GREY   (2<<1)
-#define S3C2410_LCDCON1_STN8BPP	   (3<<1)
-#define S3C2410_LCDCON1_STN12BPP   (4<<1)
-
-#define S3C2410_LCDCON1_TFT1BPP	   (8<<1)
-#define S3C2410_LCDCON1_TFT2BPP	   (9<<1)
-#define S3C2410_LCDCON1_TFT4BPP	   (10<<1)
-#define S3C2410_LCDCON1_TFT8BPP	   (11<<1)
-#define S3C2410_LCDCON1_TFT16BPP   (12<<1)
-#define S3C2410_LCDCON1_TFT24BPP   (13<<1)
-
-#define S3C2410_LCDCON1_ENVID	   (1)
-
-#define S3C2410_LCDCON1_MODEMASK    0x1E
-
-#define S3C2410_LCDCON2_VBPD(x)	    ((x) << 24)
-#define S3C2410_LCDCON2_LINEVAL(x)  ((x) << 14)
-#define S3C2410_LCDCON2_VFPD(x)	    ((x) << 6)
-#define S3C2410_LCDCON2_VSPW(x)	    ((x) << 0)
-
-#define S3C2410_LCDCON2_GET_VBPD(x) ( ((x) >> 24) & 0xFF)
-#define S3C2410_LCDCON2_GET_VFPD(x) ( ((x) >>  6) & 0xFF)
-#define S3C2410_LCDCON2_GET_VSPW(x) ( ((x) >>  0) & 0x3F)
-
-#define S3C2410_LCDCON3_HBPD(x)	    ((x) << 19)
-#define S3C2410_LCDCON3_WDLY(x)	    ((x) << 19)
-#define S3C2410_LCDCON3_HOZVAL(x)   ((x) << 8)
-#define S3C2410_LCDCON3_HFPD(x)	    ((x) << 0)
-#define S3C2410_LCDCON3_LINEBLANK(x)((x) << 0)
-
-#define S3C2410_LCDCON3_GET_HBPD(x) ( ((x) >> 19) & 0x7F)
-#define S3C2410_LCDCON3_GET_HFPD(x) ( ((x) >>  0) & 0xFF)
-
-/* LDCCON4 changes for STN mode on the S3C2412 */
-
-#define S3C2410_LCDCON4_MVAL(x)	    ((x) << 8)
-#define S3C2410_LCDCON4_HSPW(x)	    ((x) << 0)
-#define S3C2410_LCDCON4_WLH(x)	    ((x) << 0)
-
-#define S3C2410_LCDCON4_GET_HSPW(x) ( ((x) >>  0) & 0xFF)
-
-#define S3C2410_LCDCON5_BPP24BL	    (1<<12)
-#define S3C2410_LCDCON5_FRM565	    (1<<11)
-#define S3C2410_LCDCON5_INVVCLK	    (1<<10)
-#define S3C2410_LCDCON5_INVVLINE    (1<<9)
-#define S3C2410_LCDCON5_INVVFRAME   (1<<8)
-#define S3C2410_LCDCON5_INVVD	    (1<<7)
-#define S3C2410_LCDCON5_INVVDEN	    (1<<6)
-#define S3C2410_LCDCON5_INVPWREN    (1<<5)
-#define S3C2410_LCDCON5_INVLEND	    (1<<4)
-#define S3C2410_LCDCON5_PWREN	    (1<<3)
-#define S3C2410_LCDCON5_ENLEND	    (1<<2)
-#define S3C2410_LCDCON5_BSWP	    (1<<1)
-#define S3C2410_LCDCON5_HWSWP	    (1<<0)
-
-/* framebuffer start addressed */
-#define S3C2410_LCDSADDR1   S3C2410_LCDREG(0x14)
-#define S3C2410_LCDSADDR2   S3C2410_LCDREG(0x18)
-#define S3C2410_LCDSADDR3   S3C2410_LCDREG(0x1C)
-
-#define S3C2410_LCDBANK(x)	((x) << 21)
-#define S3C2410_LCDBASEU(x)	(x)
-
-#define S3C2410_OFFSIZE(x)	((x) << 11)
-#define S3C2410_PAGEWIDTH(x)	(x)
-
-/* colour lookup and miscellaneous controls */
-
-#define S3C2410_REDLUT	   S3C2410_LCDREG(0x20)
-#define S3C2410_GREENLUT   S3C2410_LCDREG(0x24)
-#define S3C2410_BLUELUT	   S3C2410_LCDREG(0x28)
-
-#define S3C2410_DITHMODE   S3C2410_LCDREG(0x4C)
-#define S3C2410_TPAL	   S3C2410_LCDREG(0x50)
-
-#define S3C2410_TPAL_EN		(1<<24)
-
-/* interrupt info */
-#define S3C2410_LCDINTPND  S3C2410_LCDREG(0x54)
-#define S3C2410_LCDSRCPND  S3C2410_LCDREG(0x58)
-#define S3C2410_LCDINTMSK  S3C2410_LCDREG(0x5C)
-#define S3C2410_LCDINT_FIWSEL	(1<<2)
-#define	S3C2410_LCDINT_FRSYNC	(1<<1)
-#define S3C2410_LCDINT_FICNT	(1<<0)
-
-/* s3c2442 extra stn registers */
-
-#define S3C2442_REDLUT		S3C2410_LCDREG(0x20)
-#define S3C2442_GREENLUT	S3C2410_LCDREG(0x24)
-#define S3C2442_BLUELUT		S3C2410_LCDREG(0x28)
-#define S3C2442_DITHMODE	S3C2410_LCDREG(0x20)
-
-#define S3C2410_LPCSEL	   S3C2410_LCDREG(0x60)
-
-#define S3C2410_TFTPAL(x)  S3C2410_LCDREG((0x400 + (x)*4))
-
-/* S3C2412 registers */
-
-#define S3C2412_TPAL		S3C2410_LCDREG(0x20)
-
-#define S3C2412_LCDINTPND	S3C2410_LCDREG(0x24)
-#define S3C2412_LCDSRCPND	S3C2410_LCDREG(0x28)
-#define S3C2412_LCDINTMSK	S3C2410_LCDREG(0x2C)
-
-#define S3C2412_TCONSEL		S3C2410_LCDREG(0x30)
-
-#define S3C2412_LCDCON6		S3C2410_LCDREG(0x34)
-#define S3C2412_LCDCON7		S3C2410_LCDREG(0x38)
-#define S3C2412_LCDCON8		S3C2410_LCDREG(0x3C)
-#define S3C2412_LCDCON9		S3C2410_LCDREG(0x40)
-
-#define S3C2412_REDLUT(x)	S3C2410_LCDREG(0x44 + ((x)*4))
-#define S3C2412_GREENLUT(x)	S3C2410_LCDREG(0x60 + ((x)*4))
-#define S3C2412_BLUELUT(x)	S3C2410_LCDREG(0x98 + ((x)*4))
-
-#define S3C2412_FRCPAT(x)	S3C2410_LCDREG(0xB4 + ((x)*4))
-
-/* general registers */
-
-/* base of the LCD registers, where INTPND, INTSRC and then INTMSK
- * are available. */
-
-#define S3C2410_LCDINTBASE	S3C2410_LCDREG(0x54)
-#define S3C2412_LCDINTBASE	S3C2410_LCDREG(0x24)
-
-#define S3C24XX_LCDINTPND	(0x00)
-#define S3C24XX_LCDSRCPND	(0x04)
-#define S3C24XX_LCDINTMSK	(0x08)
-
-#endif /* ___ASM_ARCH_REGS_LCD_H */
diff --git a/arch/arm/mach-s3c24xx/mach-amlm5900.c b/arch/arm/mach-s3c24xx/mach-amlm5900.c
index 1a2a9259b4b6..f04eb9aa29ac 100644
--- a/arch/arm/mach-s3c24xx/mach-amlm5900.c
+++ b/arch/arm/mach-s3c24xx/mach-amlm5900.c
@@ -29,9 +29,8 @@
 
 #include <asm/irq.h>
 #include <asm/mach-types.h>
-#include <mach/fb.h>
+#include <linux/platform_data/fb-s3c2410.h>
 
-#include <mach/regs-lcd.h>
 #include <mach/regs-gpio.h>
 #include <mach/gpio-samsung.h>
 
@@ -191,13 +190,17 @@ static struct s3c2410fb_mach_info __initdata amlm5900_fb_info = {
 
 	.gpccon =	0xaaaaaaaa,
 	.gpccon_mask =	0xffffffff,
+	.gpccon_reg =	S3C2410_GPCCON,
 	.gpcup =	0x0000ffff,
 	.gpcup_mask =	0xffffffff,
+	.gpcup_reg =	S3C2410_GPCUP,
 
 	.gpdcon =	0xaaaaaaaa,
 	.gpdcon_mask =	0xffffffff,
+	.gpdcon_reg =	S3C2410_GPDCON,
 	.gpdup =	0x0000ffff,
 	.gpdup_mask =	0xffffffff,
+	.gpdup_reg =	S3C2410_GPDUP,
 };
 #endif
 
diff --git a/arch/arm/mach-s3c24xx/mach-anubis.c b/arch/arm/mach-s3c24xx/mach-anubis.c
index 753a314f4493..15cab0976941 100644
--- a/arch/arm/mach-s3c24xx/mach-anubis.c
+++ b/arch/arm/mach-s3c24xx/mach-anubis.c
@@ -28,7 +28,6 @@
 #include <asm/mach-types.h>
 
 #include <mach/regs-gpio.h>
-#include <mach/regs-lcd.h>
 #include <mach/gpio-samsung.h>
 #include <linux/platform_data/mtd-nand-s3c2410.h>
 #include <linux/platform_data/i2c-s3c2410.h>
diff --git a/arch/arm/mach-s3c24xx/mach-at2440evb.c b/arch/arm/mach-s3c24xx/mach-at2440evb.c
index a2693246b3ca..7fcb24a49ad8 100644
--- a/arch/arm/mach-s3c24xx/mach-at2440evb.c
+++ b/arch/arm/mach-s3c24xx/mach-at2440evb.c
@@ -24,12 +24,11 @@
 #include <asm/mach/map.h>
 #include <asm/mach/irq.h>
 
-#include <mach/fb.h>
+#include <linux/platform_data/fb-s3c2410.h>
 #include <asm/irq.h>
 #include <asm/mach-types.h>
 
 #include <mach/regs-gpio.h>
-#include <mach/regs-lcd.h>
 #include <mach/gpio-samsung.h>
 #include <linux/platform_data/mtd-nand-s3c2410.h>
 #include <linux/platform_data/i2c-s3c2410.h>
diff --git a/arch/arm/mach-s3c24xx/mach-bast.c b/arch/arm/mach-s3c24xx/mach-bast.c
index 9eef0f80175f..306891235f73 100644
--- a/arch/arm/mach-s3c24xx/mach-bast.c
+++ b/arch/arm/mach-s3c24xx/mach-bast.c
@@ -40,9 +40,8 @@
 #include <asm/mach/irq.h>
 #include <asm/mach-types.h>
 
-#include <mach/fb.h>
+#include <linux/platform_data/fb-s3c2410.h>
 #include <mach/regs-gpio.h>
-#include <mach/regs-lcd.h>
 #include <mach/gpio-samsung.h>
 
 #include <plat/cpu.h>
diff --git a/arch/arm/mach-s3c24xx/mach-gta02.c b/arch/arm/mach-s3c24xx/mach-gta02.c
index c023e261a240..a28e92142b04 100644
--- a/arch/arm/mach-s3c24xx/mach-gta02.c
+++ b/arch/arm/mach-s3c24xx/mach-gta02.c
@@ -57,8 +57,8 @@
 #include <linux/platform_data/touchscreen-s3c2410.h>
 #include <linux/platform_data/usb-ohci-s3c2410.h>
 #include <linux/platform_data/usb-s3c2410_udc.h>
+#include <linux/platform_data/fb-s3c2410.h>
 
-#include <mach/fb.h>
 #include <mach/regs-gpio.h>
 #include <mach/regs-irq.h>
 #include <mach/gpio-samsung.h>
diff --git a/arch/arm/mach-s3c24xx/mach-h1940.c b/arch/arm/mach-s3c24xx/mach-h1940.c
index e9b3b048a96d..d45825898835 100644
--- a/arch/arm/mach-s3c24xx/mach-h1940.c
+++ b/arch/arm/mach-s3c24xx/mach-h1940.c
@@ -47,11 +47,10 @@
 
 #include <sound/uda1380.h>
 
-#include <mach/fb.h>
+#include <linux/platform_data/fb-s3c2410.h>
 #include <mach/hardware.h>
 #include <mach/regs-clock.h>
 #include <mach/regs-gpio.h>
-#include <mach/regs-lcd.h>
 #include <mach/gpio-samsung.h>
 
 #include <plat/cpu.h>
@@ -210,12 +209,16 @@ static struct s3c2410fb_mach_info h1940_fb_info __initdata = {
 	.lpcsel =	0x02,
 	.gpccon =	0xaa940659,
 	.gpccon_mask =	0xffffc0f0,
+	.gpccon_reg =	S3C2410_GPCCON,
 	.gpcup =	0x0000ffff,
 	.gpcup_mask =	0xffffffff,
+	.gpcup_reg =	S3C2410_GPCUP,
 	.gpdcon =	0xaa84aaa0,
 	.gpdcon_mask =	0xffffffff,
+	.gpdcon_reg =	S3C2410_GPDCON,
 	.gpdup =	0x0000faff,
 	.gpdup_mask =	0xffffffff,
+	.gpdup_reg =	S3C2410_GPDUP,
 };
 
 static int power_supply_init(struct device *dev)
diff --git a/arch/arm/mach-s3c24xx/mach-jive.c b/arch/arm/mach-s3c24xx/mach-jive.c
index 2c630ade08bb..ec6c40ea8f86 100644
--- a/arch/arm/mach-s3c24xx/mach-jive.c
+++ b/arch/arm/mach-s3c24xx/mach-jive.c
@@ -32,8 +32,7 @@
 #include <linux/platform_data/i2c-s3c2410.h>
 
 #include <mach/regs-gpio.h>
-#include <mach/regs-lcd.h>
-#include <mach/fb.h>
+#include <linux/platform_data/fb-s3c2410.h>
 #include <mach/gpio-samsung.h>
 
 #include <asm/mach-types.h>
@@ -320,6 +319,7 @@ static struct s3c2410fb_mach_info jive_lcd_config = {
 	 * data. */
 
 	.gpcup		= (0xf << 1) | (0x3f << 10),
+	.gpcup_reg	= S3C2410_GPCUP,
 
 	.gpccon		= (S3C2410_GPC1_VCLK   | S3C2410_GPC2_VLINE |
 			   S3C2410_GPC3_VFRAME | S3C2410_GPC4_VM |
@@ -333,8 +333,12 @@ static struct s3c2410fb_mach_info jive_lcd_config = {
 			   S3C2410_GPCCON_MASK(12) | S3C2410_GPCCON_MASK(13) |
 			   S3C2410_GPCCON_MASK(14) | S3C2410_GPCCON_MASK(15)),
 
+	.gpccon_reg	= S3C2410_GPCCON,
+
 	.gpdup		= (0x3f << 2) | (0x3f << 10),
 
+	.gpdup_reg	= S3C2410_GPDUP,
+
 	.gpdcon		= (S3C2410_GPD2_VD10  | S3C2410_GPD3_VD11 |
 			   S3C2410_GPD4_VD12  | S3C2410_GPD5_VD13 |
 			   S3C2410_GPD6_VD14  | S3C2410_GPD7_VD15 |
@@ -348,6 +352,8 @@ static struct s3c2410fb_mach_info jive_lcd_config = {
 			   S3C2410_GPDCON_MASK(10) | S3C2410_GPDCON_MASK(11)|
 			   S3C2410_GPDCON_MASK(12) | S3C2410_GPDCON_MASK(13)|
 			   S3C2410_GPDCON_MASK(14) | S3C2410_GPDCON_MASK(15)),
+
+	.gpdcon_reg	= S3C2410_GPDCON,
 };
 
 /* ILI9320 support. */
diff --git a/arch/arm/mach-s3c24xx/mach-mini2440.c b/arch/arm/mach-s3c24xx/mach-mini2440.c
index d3cc0141f58c..6f58a3404b36 100644
--- a/arch/arm/mach-s3c24xx/mach-mini2440.c
+++ b/arch/arm/mach-s3c24xx/mach-mini2440.c
@@ -30,12 +30,11 @@
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 
-#include <mach/fb.h>
+#include <linux/platform_data/fb-s3c2410.h>
 #include <asm/mach-types.h>
 
 #include <mach/regs-gpio.h>
 #include <linux/platform_data/leds-s3c24xx.h>
-#include <mach/regs-lcd.h>
 #include <mach/irqs.h>
 #include <mach/gpio-samsung.h>
 #include <linux/platform_data/mtd-nand-s3c2410.h>
@@ -213,6 +212,9 @@ static struct s3c2410fb_mach_info mini2440_fb_info __initdata = {
 			   S3C2410_GPCCON_MASK(12) | S3C2410_GPCCON_MASK(13) |
 			   S3C2410_GPCCON_MASK(14) | S3C2410_GPCCON_MASK(15)),
 
+	.gpccon_reg	= S3C2410_GPCCON,
+	.gpcup_reg	= S3C2410_GPCUP,
+
 	.gpdup		= (0x3f << 2) | (0x3f << 10),
 
 	.gpdcon		= (S3C2410_GPD2_VD10  | S3C2410_GPD3_VD11 |
@@ -228,6 +230,9 @@ static struct s3c2410fb_mach_info mini2440_fb_info __initdata = {
 			   S3C2410_GPDCON_MASK(10) | S3C2410_GPDCON_MASK(11)|
 			   S3C2410_GPDCON_MASK(12) | S3C2410_GPDCON_MASK(13)|
 			   S3C2410_GPDCON_MASK(14) | S3C2410_GPDCON_MASK(15)),
+
+	.gpdcon_reg	= S3C2410_GPDCON,
+	.gpdup_reg	= S3C2410_GPDUP,
 };
 
 /* MMC/SD  */
diff --git a/arch/arm/mach-s3c24xx/mach-n30.c b/arch/arm/mach-s3c24xx/mach-n30.c
index 24e97646b068..a3c1315f5ffb 100644
--- a/arch/arm/mach-s3c24xx/mach-n30.c
+++ b/arch/arm/mach-s3c24xx/mach-n30.c
@@ -31,10 +31,9 @@
 #include <asm/irq.h>
 #include <asm/mach-types.h>
 
-#include <mach/fb.h>
+#include <linux/platform_data/fb-s3c2410.h>
 #include <linux/platform_data/leds-s3c24xx.h>
 #include <mach/regs-gpio.h>
-#include <mach/regs-lcd.h>
 #include <mach/gpio-samsung.h>
 #include <plat/gpio-cfg.h>
 
diff --git a/arch/arm/mach-s3c24xx/mach-osiris.c b/arch/arm/mach-s3c24xx/mach-osiris.c
index 03595144126b..ed10a32e26b8 100644
--- a/arch/arm/mach-s3c24xx/mach-osiris.c
+++ b/arch/arm/mach-s3c24xx/mach-osiris.c
@@ -42,7 +42,6 @@
 #include <plat/gpio-cfg.h>
 
 #include <mach/regs-gpio.h>
-#include <mach/regs-lcd.h>
 #include <mach/gpio-samsung.h>
 
 #include "common.h"
diff --git a/arch/arm/mach-s3c24xx/mach-qt2410.c b/arch/arm/mach-s3c24xx/mach-qt2410.c
index b21f7fbcadf9..1ccad4e9e437 100644
--- a/arch/arm/mach-s3c24xx/mach-qt2410.c
+++ b/arch/arm/mach-s3c24xx/mach-qt2410.c
@@ -32,8 +32,7 @@
 #include <asm/mach-types.h>
 
 #include <linux/platform_data/leds-s3c24xx.h>
-#include <mach/regs-lcd.h>
-#include <mach/fb.h>
+#include <linux/platform_data/fb-s3c2410.h>
 #include <linux/platform_data/mtd-nand-s3c2410.h>
 #include <linux/platform_data/usb-s3c2410_udc.h>
 #include <linux/platform_data/i2c-s3c2410.h>
diff --git a/arch/arm/mach-s3c24xx/mach-rx1950.c b/arch/arm/mach-s3c24xx/mach-rx1950.c
index aa91785a95b5..2513ce7fa026 100644
--- a/arch/arm/mach-s3c24xx/mach-rx1950.c
+++ b/arch/arm/mach-s3c24xx/mach-rx1950.c
@@ -42,12 +42,11 @@
 #include <linux/platform_data/mtd-nand-s3c2410.h>
 #include <linux/platform_data/touchscreen-s3c2410.h>
 #include <linux/platform_data/usb-s3c2410_udc.h>
+#include <linux/platform_data/fb-s3c2410.h>
 
 #include <sound/uda1380.h>
 
-#include <mach/fb.h>
 #include <mach/regs-gpio.h>
-#include <mach/regs-lcd.h>
 #include <mach/gpio-samsung.h>
 
 #include <plat/cpu.h>
@@ -360,14 +359,17 @@ static struct s3c2410fb_mach_info rx1950_lcd_cfg = {
 	.lpcsel = 0x02,
 	.gpccon = 0xaa9556a9,
 	.gpccon_mask = 0xffc003fc,
+	.gpccon_reg = S3C2410_GPCCON,
 	.gpcup = 0x0000ffff,
 	.gpcup_mask = 0xffffffff,
+	.gpcup_reg = S3C2410_GPCUP,
 
 	.gpdcon = 0xaa90aaa1,
 	.gpdcon_mask = 0xffc0fff0,
+	.gpdcon_reg = S3C2410_GPDCON,
 	.gpdup = 0x0000fcfd,
 	.gpdup_mask = 0xffffffff,
-
+	.gpdup_reg = S3C2410_GPDUP,
 };
 
 static struct pwm_lookup rx1950_pwm_lookup[] = {
diff --git a/arch/arm/mach-s3c24xx/mach-rx3715.c b/arch/arm/mach-s3c24xx/mach-rx3715.c
index fc197cee77a0..0eb45f13f0c4 100644
--- a/arch/arm/mach-s3c24xx/mach-rx3715.c
+++ b/arch/arm/mach-s3c24xx/mach-rx3715.c
@@ -30,13 +30,12 @@
 #include <asm/mach/map.h>
 
 #include <linux/platform_data/mtd-nand-s3c2410.h>
+#include <linux/platform_data/fb-s3c2410.h>
 
 #include <asm/irq.h>
 #include <asm/mach-types.h>
 
-#include <mach/fb.h>
 #include <mach/regs-gpio.h>
-#include <mach/regs-lcd.h>
 #include <mach/gpio-samsung.h>
 #include <plat/gpio-cfg.h>
 
@@ -124,13 +123,17 @@ static struct s3c2410fb_mach_info rx3715_fb_info __initdata = {
 
 	.gpccon =	0xaa955699,
 	.gpccon_mask =	0xffc003cc,
+	.gpccon_reg =	S3C2410_GPCCON,
 	.gpcup =	0x0000ffff,
 	.gpcup_mask =	0xffffffff,
+	.gpcup_reg =	S3C2410_GPCUP,
 
 	.gpdcon =	0xaa95aaa1,
 	.gpdcon_mask =	0xffc0fff0,
+	.gpdcon_reg =	S3C2410_GPDCON,
 	.gpdup =	0x0000faff,
 	.gpdup_mask =	0xffffffff,
+	.gpdup_reg =	S3C2410_GPDUP,
 };
 
 static struct mtd_partition __initdata rx3715_nand_part[] = {
diff --git a/arch/arm/mach-s3c24xx/mach-smdk2413.c b/arch/arm/mach-s3c24xx/mach-smdk2413.c
index 287bd502a030..4604ec89f06e 100644
--- a/arch/arm/mach-s3c24xx/mach-smdk2413.c
+++ b/arch/arm/mach-s3c24xx/mach-smdk2413.c
@@ -31,12 +31,11 @@
 
 //#include <asm/debug-ll.h>
 #include <mach/regs-gpio.h>
-#include <mach/regs-lcd.h>
 
 #include <linux/platform_data/usb-s3c2410_udc.h>
 #include <linux/platform_data/i2c-s3c2410.h>
+#include <linux/platform_data/fb-s3c2410.h>
 #include <mach/gpio-samsung.h>
-#include <mach/fb.h>
 #include <plat/gpio-cfg.h>
 
 #include <plat/devs.h>
diff --git a/arch/arm/mach-s3c24xx/mach-smdk2416.c b/arch/arm/mach-s3c24xx/mach-smdk2416.c
index f98feb45568d..217401b2238d 100644
--- a/arch/arm/mach-s3c24xx/mach-smdk2416.c
+++ b/arch/arm/mach-s3c24xx/mach-smdk2416.c
@@ -30,7 +30,6 @@
 #include <asm/mach-types.h>
 
 #include <mach/regs-gpio.h>
-#include <mach/regs-lcd.h>
 #include <mach/regs-s3c2443-clock.h>
 #include <mach/gpio-samsung.h>
 
diff --git a/arch/arm/mach-s3c24xx/mach-smdk2440.c b/arch/arm/mach-s3c24xx/mach-smdk2440.c
index 5939372ecec2..a0116cff6e4e 100644
--- a/arch/arm/mach-s3c24xx/mach-smdk2440.c
+++ b/arch/arm/mach-s3c24xx/mach-smdk2440.c
@@ -27,11 +27,10 @@
 #include <asm/mach-types.h>
 
 #include <mach/regs-gpio.h>
-#include <mach/regs-lcd.h>
 #include <mach/gpio-samsung.h>
 #include <plat/gpio-cfg.h>
 
-#include <mach/fb.h>
+#include <linux/platform_data/fb-s3c2410.h>
 #include <linux/platform_data/i2c-s3c2410.h>
 
 #include <plat/devs.h>
@@ -137,6 +136,11 @@ static struct s3c2410fb_mach_info smdk2440_fb_info __initdata = {
 	.gpdcon_mask	= 0xffffffff,
 	.gpdup		= 0x0000faff,
 	.gpdup_mask	= 0xffffffff,
+
+	.gpccon_reg	= S3C2410_GPCCON,
+	.gpcup_reg	= S3C2410_GPCUP,
+	.gpdcon_reg	= S3C2410_GPDCON,
+	.gpdup_reg	= S3C2410_GPDUP,
 #endif
 
 	.lpcsel		= ((0xCE6) & ~7) | 1<<4,
diff --git a/arch/arm/mach-s3c24xx/mach-smdk2443.c b/arch/arm/mach-s3c24xx/mach-smdk2443.c
index 8a1f2580c6c7..1c2fa7c3feb8 100644
--- a/arch/arm/mach-s3c24xx/mach-smdk2443.c
+++ b/arch/arm/mach-s3c24xx/mach-smdk2443.c
@@ -26,9 +26,8 @@
 #include <asm/mach-types.h>
 
 #include <mach/regs-gpio.h>
-#include <mach/regs-lcd.h>
 
-#include <mach/fb.h>
+#include <linux/platform_data/fb-s3c2410.h>
 #include <linux/platform_data/i2c-s3c2410.h>
 
 #include <plat/devs.h>
diff --git a/arch/arm/mach-s3c24xx/mach-vstms.c b/arch/arm/mach-s3c24xx/mach-vstms.c
index c6e777aab24e..ff3fa0017494 100644
--- a/arch/arm/mach-s3c24xx/mach-vstms.c
+++ b/arch/arm/mach-s3c24xx/mach-vstms.c
@@ -29,11 +29,10 @@
 #include <asm/mach-types.h>
 
 #include <mach/regs-gpio.h>
-#include <mach/regs-lcd.h>
 #include <mach/gpio-samsung.h>
 #include <plat/gpio-cfg.h>
 
-#include <mach/fb.h>
+#include <linux/platform_data/fb-s3c2410.h>
 
 #include <linux/platform_data/i2c-s3c2410.h>
 #include <linux/platform_data/mtd-nand-s3c2410.h>
diff --git a/arch/arm/plat-samsung/devs.c b/arch/arm/plat-samsung/devs.c
index b16be04c0169..e23204132b27 100644
--- a/arch/arm/plat-samsung/devs.c
+++ b/arch/arm/plat-samsung/devs.c
@@ -52,7 +52,7 @@
 #include <linux/soc/samsung/s3c-adc.h>
 #include <linux/platform_data/ata-samsung_cf.h>
 #include <plat/fb.h>
-#include <plat/fb-s3c2410.h>
+#include <linux/platform_data/fb-s3c2410.h>
 #include <linux/platform_data/hwmon-s3c.h>
 #include <linux/platform_data/i2c-s3c2410.h>
 #include <plat/keypad.h>
diff --git a/arch/arm/plat-samsung/include/plat/fb-s3c2410.h b/arch/arm/plat-samsung/include/plat/fb-s3c2410.h
deleted file mode 100644
index 614240d768b4..000000000000
--- a/arch/arm/plat-samsung/include/plat/fb-s3c2410.h
+++ /dev/null
@@ -1,68 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (c) 2004 Arnaud Patard <arnaud.patard@rtp-net.org>
- *
- * Inspired by pxafb.h
-*/
-
-#ifndef __ASM_PLAT_FB_S3C2410_H
-#define __ASM_PLAT_FB_S3C2410_H __FILE__
-
-struct s3c2410fb_hw {
-	unsigned long	lcdcon1;
-	unsigned long	lcdcon2;
-	unsigned long	lcdcon3;
-	unsigned long	lcdcon4;
-	unsigned long	lcdcon5;
-};
-
-/* LCD description */
-struct s3c2410fb_display {
-	/* LCD type */
-	unsigned type;
-
-	/* Screen size */
-	unsigned short width;
-	unsigned short height;
-
-	/* Screen info */
-	unsigned short xres;
-	unsigned short yres;
-	unsigned short bpp;
-
-	unsigned pixclock;		/* pixclock in picoseconds */
-	unsigned short left_margin;  /* value in pixels (TFT) or HCLKs (STN) */
-	unsigned short right_margin; /* value in pixels (TFT) or HCLKs (STN) */
-	unsigned short hsync_len;    /* value in pixels (TFT) or HCLKs (STN) */
-	unsigned short upper_margin;	/* value in lines (TFT) or 0 (STN) */
-	unsigned short lower_margin;	/* value in lines (TFT) or 0 (STN) */
-	unsigned short vsync_len;	/* value in lines (TFT) or 0 (STN) */
-
-	/* lcd configuration registers */
-	unsigned long	lcdcon5;
-};
-
-struct s3c2410fb_mach_info {
-
-	struct s3c2410fb_display *displays;	/* attached displays info */
-	unsigned num_displays;			/* number of defined displays */
-	unsigned default_display;
-
-	/* GPIOs */
-
-	unsigned long	gpcup;
-	unsigned long	gpcup_mask;
-	unsigned long	gpccon;
-	unsigned long	gpccon_mask;
-	unsigned long	gpdup;
-	unsigned long	gpdup_mask;
-	unsigned long	gpdcon;
-	unsigned long	gpdcon_mask;
-
-	/* lpc3600 control register */
-	unsigned long	lpcsel;
-};
-
-extern void __init s3c24xx_fb_set_platdata(struct s3c2410fb_mach_info *);
-
-#endif /* __ASM_PLAT_FB_S3C2410_H */
diff --git a/drivers/video/fbdev/s3c2410fb-regs-lcd.h b/drivers/video/fbdev/s3c2410fb-regs-lcd.h
new file mode 100644
index 000000000000..1e46f7a788e5
--- /dev/null
+++ b/drivers/video/fbdev/s3c2410fb-regs-lcd.h
@@ -0,0 +1,143 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2003 Simtec Electronics <linux@simtec.co.uk>
+ *		      http://www.simtec.co.uk/products/SWLINUX/
+ */
+
+#ifndef ___ASM_ARCH_REGS_LCD_H
+#define ___ASM_ARCH_REGS_LCD_H
+
+/*
+ * a couple of values are used as platform data in
+ * include/linux/platform_data/fb-s3c2410.h and not
+ * duplicated here.
+ */
+#include <linux/platform_data/fb-s3c2410.h>
+
+#define S3C2410_LCDREG(x)	(x)
+
+/* LCD control registers */
+#define S3C2410_LCDCON1	    S3C2410_LCDREG(0x00)
+#define S3C2410_LCDCON2	    S3C2410_LCDREG(0x04)
+#define S3C2410_LCDCON3	    S3C2410_LCDREG(0x08)
+#define S3C2410_LCDCON4	    S3C2410_LCDREG(0x0C)
+#define S3C2410_LCDCON5	    S3C2410_LCDREG(0x10)
+
+#define S3C2410_LCDCON1_CLKVAL(x)  ((x) << 8)
+#define S3C2410_LCDCON1_MMODE	   (1<<7)
+#define S3C2410_LCDCON1_DSCAN4	   (0<<5)
+#define S3C2410_LCDCON1_STN4	   (1<<5)
+#define S3C2410_LCDCON1_STN8	   (2<<5)
+#define S3C2410_LCDCON1_TFT	   (3<<5)
+
+#define S3C2410_LCDCON1_STN1BPP	   (0<<1)
+#define S3C2410_LCDCON1_STN2GREY   (1<<1)
+#define S3C2410_LCDCON1_STN4GREY   (2<<1)
+#define S3C2410_LCDCON1_STN8BPP	   (3<<1)
+#define S3C2410_LCDCON1_STN12BPP   (4<<1)
+
+#define S3C2410_LCDCON1_ENVID	   (1)
+
+#define S3C2410_LCDCON1_MODEMASK    0x1E
+
+#define S3C2410_LCDCON2_VBPD(x)	    ((x) << 24)
+#define S3C2410_LCDCON2_LINEVAL(x)  ((x) << 14)
+#define S3C2410_LCDCON2_VFPD(x)	    ((x) << 6)
+#define S3C2410_LCDCON2_VSPW(x)	    ((x) << 0)
+
+#define S3C2410_LCDCON2_GET_VBPD(x) ( ((x) >> 24) & 0xFF)
+#define S3C2410_LCDCON2_GET_VFPD(x) ( ((x) >>  6) & 0xFF)
+#define S3C2410_LCDCON2_GET_VSPW(x) ( ((x) >>  0) & 0x3F)
+
+#define S3C2410_LCDCON3_HBPD(x)	    ((x) << 19)
+#define S3C2410_LCDCON3_WDLY(x)	    ((x) << 19)
+#define S3C2410_LCDCON3_HOZVAL(x)   ((x) << 8)
+#define S3C2410_LCDCON3_HFPD(x)	    ((x) << 0)
+#define S3C2410_LCDCON3_LINEBLANK(x)((x) << 0)
+
+#define S3C2410_LCDCON3_GET_HBPD(x) ( ((x) >> 19) & 0x7F)
+#define S3C2410_LCDCON3_GET_HFPD(x) ( ((x) >>  0) & 0xFF)
+
+/* LDCCON4 changes for STN mode on the S3C2412 */
+
+#define S3C2410_LCDCON4_MVAL(x)	    ((x) << 8)
+#define S3C2410_LCDCON4_HSPW(x)	    ((x) << 0)
+#define S3C2410_LCDCON4_WLH(x)	    ((x) << 0)
+
+#define S3C2410_LCDCON4_GET_HSPW(x) ( ((x) >>  0) & 0xFF)
+
+/* framebuffer start addressed */
+#define S3C2410_LCDSADDR1   S3C2410_LCDREG(0x14)
+#define S3C2410_LCDSADDR2   S3C2410_LCDREG(0x18)
+#define S3C2410_LCDSADDR3   S3C2410_LCDREG(0x1C)
+
+#define S3C2410_LCDBANK(x)	((x) << 21)
+#define S3C2410_LCDBASEU(x)	(x)
+
+#define S3C2410_OFFSIZE(x)	((x) << 11)
+#define S3C2410_PAGEWIDTH(x)	(x)
+
+/* colour lookup and miscellaneous controls */
+
+#define S3C2410_REDLUT	   S3C2410_LCDREG(0x20)
+#define S3C2410_GREENLUT   S3C2410_LCDREG(0x24)
+#define S3C2410_BLUELUT	   S3C2410_LCDREG(0x28)
+
+#define S3C2410_DITHMODE   S3C2410_LCDREG(0x4C)
+#define S3C2410_TPAL	   S3C2410_LCDREG(0x50)
+
+#define S3C2410_TPAL_EN		(1<<24)
+
+/* interrupt info */
+#define S3C2410_LCDINTPND  S3C2410_LCDREG(0x54)
+#define S3C2410_LCDSRCPND  S3C2410_LCDREG(0x58)
+#define S3C2410_LCDINTMSK  S3C2410_LCDREG(0x5C)
+#define S3C2410_LCDINT_FIWSEL	(1<<2)
+#define	S3C2410_LCDINT_FRSYNC	(1<<1)
+#define S3C2410_LCDINT_FICNT	(1<<0)
+
+/* s3c2442 extra stn registers */
+
+#define S3C2442_REDLUT		S3C2410_LCDREG(0x20)
+#define S3C2442_GREENLUT	S3C2410_LCDREG(0x24)
+#define S3C2442_BLUELUT		S3C2410_LCDREG(0x28)
+#define S3C2442_DITHMODE	S3C2410_LCDREG(0x20)
+
+#define S3C2410_LPCSEL	   S3C2410_LCDREG(0x60)
+
+#define S3C2410_TFTPAL(x)  S3C2410_LCDREG((0x400 + (x)*4))
+
+/* S3C2412 registers */
+
+#define S3C2412_TPAL		S3C2410_LCDREG(0x20)
+
+#define S3C2412_LCDINTPND	S3C2410_LCDREG(0x24)
+#define S3C2412_LCDSRCPND	S3C2410_LCDREG(0x28)
+#define S3C2412_LCDINTMSK	S3C2410_LCDREG(0x2C)
+
+#define S3C2412_TCONSEL		S3C2410_LCDREG(0x30)
+
+#define S3C2412_LCDCON6		S3C2410_LCDREG(0x34)
+#define S3C2412_LCDCON7		S3C2410_LCDREG(0x38)
+#define S3C2412_LCDCON8		S3C2410_LCDREG(0x3C)
+#define S3C2412_LCDCON9		S3C2410_LCDREG(0x40)
+
+#define S3C2412_REDLUT(x)	S3C2410_LCDREG(0x44 + ((x)*4))
+#define S3C2412_GREENLUT(x)	S3C2410_LCDREG(0x60 + ((x)*4))
+#define S3C2412_BLUELUT(x)	S3C2410_LCDREG(0x98 + ((x)*4))
+
+#define S3C2412_FRCPAT(x)	S3C2410_LCDREG(0xB4 + ((x)*4))
+
+/* general registers */
+
+/* base of the LCD registers, where INTPND, INTSRC and then INTMSK
+ * are available. */
+
+#define S3C2410_LCDINTBASE	S3C2410_LCDREG(0x54)
+#define S3C2412_LCDINTBASE	S3C2410_LCDREG(0x24)
+
+#define S3C24XX_LCDINTPND	(0x00)
+#define S3C24XX_LCDSRCPND	(0x04)
+#define S3C24XX_LCDINTMSK	(0x08)
+
+#endif /* ___ASM_ARCH_REGS_LCD_H */
diff --git a/drivers/video/fbdev/s3c2410fb.c b/drivers/video/fbdev/s3c2410fb.c
index 6f8fa501583f..d8ae5258de46 100644
--- a/drivers/video/fbdev/s3c2410fb.c
+++ b/drivers/video/fbdev/s3c2410fb.c
@@ -29,19 +29,18 @@
 #include <linux/clk.h>
 #include <linux/cpufreq.h>
 #include <linux/io.h>
+#include <linux/platform_data/fb-s3c2410.h>
 
 #include <asm/div64.h>
 
 #include <asm/mach/map.h>
-#include <mach/regs-lcd.h>
-#include <mach/regs-gpio.h>
-#include <mach/fb.h>
 
 #ifdef CONFIG_PM
 #include <linux/pm.h>
 #endif
 
 #include "s3c2410fb.h"
+#include "s3c2410fb-regs-lcd.h"
 
 /* Debugging stuff */
 static int debug = IS_BUILTIN(CONFIG_FB_S3C2410_DEBUG);
@@ -672,6 +671,9 @@ static inline void modify_gpio(void __iomem *reg,
 {
 	unsigned long tmp;
 
+	if (!reg)
+		return;
+
 	tmp = readl(reg) & ~mask;
 	writel(tmp | set, reg);
 }
@@ -702,10 +704,10 @@ static int s3c2410fb_init_registers(struct fb_info *info)
 
 	/* modify the gpio(s) with interrupts set (bjd) */
 
-	modify_gpio(S3C2410_GPCUP,  mach_info->gpcup,  mach_info->gpcup_mask);
-	modify_gpio(S3C2410_GPCCON, mach_info->gpccon, mach_info->gpccon_mask);
-	modify_gpio(S3C2410_GPDUP,  mach_info->gpdup,  mach_info->gpdup_mask);
-	modify_gpio(S3C2410_GPDCON, mach_info->gpdcon, mach_info->gpdcon_mask);
+	modify_gpio(mach_info->gpcup_reg,  mach_info->gpcup,  mach_info->gpcup_mask);
+	modify_gpio(mach_info->gpccon_reg, mach_info->gpccon, mach_info->gpccon_mask);
+	modify_gpio(mach_info->gpdup_reg,  mach_info->gpdup,  mach_info->gpdup_mask);
+	modify_gpio(mach_info->gpdcon_reg, mach_info->gpdcon, mach_info->gpdcon_mask);
 
 	local_irq_restore(flags);
 
diff --git a/include/linux/platform_data/fb-s3c2410.h b/include/linux/platform_data/fb-s3c2410.h
new file mode 100644
index 000000000000..10c11e6316d6
--- /dev/null
+++ b/include/linux/platform_data/fb-s3c2410.h
@@ -0,0 +1,99 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2004 Arnaud Patard <arnaud.patard@rtp-net.org>
+ *
+ * Inspired by pxafb.h
+*/
+
+#ifndef __ASM_PLAT_FB_S3C2410_H
+#define __ASM_PLAT_FB_S3C2410_H __FILE__
+
+#include <linux/compiler_types.h>
+
+struct s3c2410fb_hw {
+	unsigned long	lcdcon1;
+	unsigned long	lcdcon2;
+	unsigned long	lcdcon3;
+	unsigned long	lcdcon4;
+	unsigned long	lcdcon5;
+};
+
+/* LCD description */
+struct s3c2410fb_display {
+	/* LCD type */
+	unsigned type;
+#define S3C2410_LCDCON1_DSCAN4	   (0<<5)
+#define S3C2410_LCDCON1_STN4	   (1<<5)
+#define S3C2410_LCDCON1_STN8	   (2<<5)
+#define S3C2410_LCDCON1_TFT	   (3<<5)
+
+#define S3C2410_LCDCON1_TFT1BPP	   (8<<1)
+#define S3C2410_LCDCON1_TFT2BPP	   (9<<1)
+#define S3C2410_LCDCON1_TFT4BPP	   (10<<1)
+#define S3C2410_LCDCON1_TFT8BPP	   (11<<1)
+#define S3C2410_LCDCON1_TFT16BPP   (12<<1)
+#define S3C2410_LCDCON1_TFT24BPP   (13<<1)
+
+	/* Screen size */
+	unsigned short width;
+	unsigned short height;
+
+	/* Screen info */
+	unsigned short xres;
+	unsigned short yres;
+	unsigned short bpp;
+
+	unsigned pixclock;		/* pixclock in picoseconds */
+	unsigned short left_margin;  /* value in pixels (TFT) or HCLKs (STN) */
+	unsigned short right_margin; /* value in pixels (TFT) or HCLKs (STN) */
+	unsigned short hsync_len;    /* value in pixels (TFT) or HCLKs (STN) */
+	unsigned short upper_margin;	/* value in lines (TFT) or 0 (STN) */
+	unsigned short lower_margin;	/* value in lines (TFT) or 0 (STN) */
+	unsigned short vsync_len;	/* value in lines (TFT) or 0 (STN) */
+
+	/* lcd configuration registers */
+	unsigned long	lcdcon5;
+#define S3C2410_LCDCON5_BPP24BL	    (1<<12)
+#define S3C2410_LCDCON5_FRM565	    (1<<11)
+#define S3C2410_LCDCON5_INVVCLK	    (1<<10)
+#define S3C2410_LCDCON5_INVVLINE    (1<<9)
+#define S3C2410_LCDCON5_INVVFRAME   (1<<8)
+#define S3C2410_LCDCON5_INVVD	    (1<<7)
+#define S3C2410_LCDCON5_INVVDEN	    (1<<6)
+#define S3C2410_LCDCON5_INVPWREN    (1<<5)
+#define S3C2410_LCDCON5_INVLEND	    (1<<4)
+#define S3C2410_LCDCON5_PWREN	    (1<<3)
+#define S3C2410_LCDCON5_ENLEND	    (1<<2)
+#define S3C2410_LCDCON5_BSWP	    (1<<1)
+#define S3C2410_LCDCON5_HWSWP	    (1<<0)
+};
+
+struct s3c2410fb_mach_info {
+
+	struct s3c2410fb_display *displays;	/* attached displays info */
+	unsigned num_displays;			/* number of defined displays */
+	unsigned default_display;
+
+	/* GPIOs */
+
+	unsigned long	gpcup;
+	unsigned long	gpcup_mask;
+	unsigned long	gpccon;
+	unsigned long	gpccon_mask;
+	unsigned long	gpdup;
+	unsigned long	gpdup_mask;
+	unsigned long	gpdcon;
+	unsigned long	gpdcon_mask;
+
+	void __iomem *  gpccon_reg;
+	void __iomem *  gpcup_reg;
+	void __iomem *  gpdcon_reg;
+	void __iomem *  gpdup_reg;
+
+	/* lpc3600 control register */
+	unsigned long	lpcsel;
+};
+
+extern void s3c24xx_fb_set_platdata(struct s3c2410fb_mach_info *);
+
+#endif /* __ASM_PLAT_FB_S3C2410_H */
-- 
cgit v1.2.3


From 81b11a6a09964cfea4c525d22548790a1d92d38f Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 6 Aug 2020 20:20:52 +0200
Subject: ARM: s3c: remove cpufreq header dependencies

The cpufreq drivers are split between the machine directory
and the drivers/cpufreq directory. In order to share header
files after we convert s3c to multiplatform, those headers
have to live in a different global location.

Move them to linux/soc/samsung/ in lack of a better place.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Link: https://lore.kernel.org/r/20200806182059.2431-35-krzk@kernel.org
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
---
 arch/arm/mach-s3c24xx/common.c                     |   1 -
 arch/arm/mach-s3c24xx/cpufreq-utils.c              |   2 +-
 arch/arm/mach-s3c24xx/iotiming-s3c2410.c           |   2 +-
 arch/arm/mach-s3c24xx/iotiming-s3c2412.c           |   2 +-
 arch/arm/mach-s3c24xx/mach-bast.c                  |   2 +-
 arch/arm/mach-s3c24xx/mach-osiris-dvs.c            |   2 +-
 arch/arm/mach-s3c24xx/mach-osiris.c                |   2 +-
 arch/arm/mach-s3c24xx/pll-s3c2410.c                |   4 +-
 arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c       |   4 +-
 arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c       |   4 +-
 arch/arm/mach-s3c24xx/s3c2410.c                    |   1 -
 arch/arm/mach-s3c24xx/s3c2412.c                    |   1 -
 arch/arm/mach-s3c24xx/s3c244x.c                    |   2 -
 arch/arm/mach-s3c64xx/s3c6400.c                    |   1 -
 arch/arm/mach-s3c64xx/s3c6410.c                    |   2 +-
 arch/arm/plat-samsung/include/plat/cpu-freq-core.h | 287 --------------------
 arch/arm/plat-samsung/include/plat/cpu-freq.h      | 141 ----------
 arch/arm/plat-samsung/include/plat/cpu.h           |   9 -
 drivers/cpufreq/s3c2410-cpufreq.c                  |   5 +-
 drivers/cpufreq/s3c2412-cpufreq.c                  |   5 +-
 drivers/cpufreq/s3c2440-cpufreq.c                  |   5 +-
 drivers/cpufreq/s3c24xx-cpufreq-debugfs.c          |   2 +-
 drivers/cpufreq/s3c24xx-cpufreq.c                  |   5 +-
 include/linux/soc/samsung/s3c-cpu-freq.h           | 145 ++++++++++
 include/linux/soc/samsung/s3c-cpufreq-core.h       | 291 +++++++++++++++++++++
 include/linux/soc/samsung/s3c-pm.h                 |  10 +
 26 files changed, 468 insertions(+), 469 deletions(-)
 delete mode 100644 arch/arm/plat-samsung/include/plat/cpu-freq-core.h
 delete mode 100644 arch/arm/plat-samsung/include/plat/cpu-freq.h
 create mode 100644 include/linux/soc/samsung/s3c-cpu-freq.h
 create mode 100644 include/linux/soc/samsung/s3c-cpufreq-core.h

(limited to 'include/linux')

diff --git a/arch/arm/mach-s3c24xx/common.c b/arch/arm/mach-s3c24xx/common.c
index c476a673d07f..f987de1a61c2 100644
--- a/arch/arm/mach-s3c24xx/common.c
+++ b/arch/arm/mach-s3c24xx/common.c
@@ -37,7 +37,6 @@
 
 #include <plat/cpu.h>
 #include <plat/devs.h>
-#include <plat/cpu-freq.h>
 #include <plat/pwm-core.h>
 
 #include "common.h"
diff --git a/arch/arm/mach-s3c24xx/cpufreq-utils.c b/arch/arm/mach-s3c24xx/cpufreq-utils.c
index 1a7f38d085dd..43ab714eaa9e 100644
--- a/arch/arm/mach-s3c24xx/cpufreq-utils.c
+++ b/arch/arm/mach-s3c24xx/cpufreq-utils.c
@@ -15,7 +15,7 @@
 #include <mach/map.h>
 #include <mach/regs-clock.h>
 
-#include <plat/cpu-freq-core.h>
+#include <linux/soc/samsung/s3c-cpufreq-core.h>
 
 #include "regs-mem.h"
 
diff --git a/arch/arm/mach-s3c24xx/iotiming-s3c2410.c b/arch/arm/mach-s3c24xx/iotiming-s3c2410.c
index 39081c41958c..5d85c259f328 100644
--- a/arch/arm/mach-s3c24xx/iotiming-s3c2410.c
+++ b/arch/arm/mach-s3c24xx/iotiming-s3c2410.c
@@ -17,7 +17,7 @@
 #include <mach/map.h>
 #include <mach/regs-clock.h>
 
-#include <plat/cpu-freq-core.h>
+#include <linux/soc/samsung/s3c-cpufreq-core.h>
 
 #include "regs-mem.h"
 
diff --git a/arch/arm/mach-s3c24xx/iotiming-s3c2412.c b/arch/arm/mach-s3c24xx/iotiming-s3c2412.c
index 59356d10fbcf..a22b5611697d 100644
--- a/arch/arm/mach-s3c24xx/iotiming-s3c2412.c
+++ b/arch/arm/mach-s3c24xx/iotiming-s3c2412.c
@@ -24,7 +24,7 @@
 #include <asm/mach/map.h>
 
 #include <plat/cpu.h>
-#include <plat/cpu-freq-core.h>
+#include <linux/soc/samsung/s3c-cpufreq-core.h>
 
 #include <mach/s3c2412.h>
 
diff --git a/arch/arm/mach-s3c24xx/mach-bast.c b/arch/arm/mach-s3c24xx/mach-bast.c
index 306891235f73..7e3ce48539c4 100644
--- a/arch/arm/mach-s3c24xx/mach-bast.c
+++ b/arch/arm/mach-s3c24xx/mach-bast.c
@@ -45,7 +45,7 @@
 #include <mach/gpio-samsung.h>
 
 #include <plat/cpu.h>
-#include <plat/cpu-freq.h>
+#include <linux/soc/samsung/s3c-cpu-freq.h>
 #include <plat/devs.h>
 #include <plat/gpio-cfg.h>
 
diff --git a/arch/arm/mach-s3c24xx/mach-osiris-dvs.c b/arch/arm/mach-s3c24xx/mach-osiris-dvs.c
index 5d819b6ea428..1250520b3bcc 100644
--- a/arch/arm/mach-s3c24xx/mach-osiris-dvs.c
+++ b/arch/arm/mach-s3c24xx/mach-osiris-dvs.c
@@ -14,7 +14,7 @@
 
 #include <linux/mfd/tps65010.h>
 
-#include <plat/cpu-freq.h>
+#include <linux/soc/samsung/s3c-cpu-freq.h>
 #include <mach/gpio-samsung.h>
 
 #define OSIRIS_GPIO_DVS	S3C2410_GPB(5)
diff --git a/arch/arm/mach-s3c24xx/mach-osiris.c b/arch/arm/mach-s3c24xx/mach-osiris.c
index ed10a32e26b8..258850c1bbb2 100644
--- a/arch/arm/mach-s3c24xx/mach-osiris.c
+++ b/arch/arm/mach-s3c24xx/mach-osiris.c
@@ -37,7 +37,7 @@
 #include <linux/mtd/partitions.h>
 
 #include <plat/cpu.h>
-#include <plat/cpu-freq.h>
+#include <linux/soc/samsung/s3c-cpu-freq.h>
 #include <plat/devs.h>
 #include <plat/gpio-cfg.h>
 
diff --git a/arch/arm/mach-s3c24xx/pll-s3c2410.c b/arch/arm/mach-s3c24xx/pll-s3c2410.c
index 0561f79ddce8..3fbc99eaa4a2 100644
--- a/arch/arm/mach-s3c24xx/pll-s3c2410.c
+++ b/arch/arm/mach-s3c24xx/pll-s3c2410.c
@@ -15,8 +15,8 @@
 #include <linux/clk.h>
 #include <linux/err.h>
 
-#include <plat/cpu.h>
-#include <plat/cpu-freq-core.h>
+#include <linux/soc/samsung/s3c-cpufreq-core.h>
+#include <linux/soc/samsung/s3c-pm.h>
 
 /* This array should be sorted in ascending order of the frequencies */
 static struct cpufreq_frequency_table pll_vals_12MHz[] = {
diff --git a/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c b/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c
index 2ec3a2f9a6a5..fdb8e8c2fe3b 100644
--- a/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c
+++ b/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c
@@ -13,8 +13,8 @@
 #include <linux/clk.h>
 #include <linux/err.h>
 
-#include <plat/cpu.h>
-#include <plat/cpu-freq-core.h>
+#include <linux/soc/samsung/s3c-cpufreq-core.h>
+#include <linux/soc/samsung/s3c-pm.h>
 
 /* This array should be sorted in ascending order of the frequencies */
 static struct cpufreq_frequency_table s3c2440_plls_12[] = {
diff --git a/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c b/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c
index 4b3d9e36c6bb..438b6fc099a4 100644
--- a/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c
+++ b/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c
@@ -13,8 +13,8 @@
 #include <linux/clk.h>
 #include <linux/err.h>
 
-#include <plat/cpu.h>
-#include <plat/cpu-freq-core.h>
+#include <linux/soc/samsung/s3c-cpufreq-core.h>
+#include <linux/soc/samsung/s3c-pm.h>
 
 /* This array should be sorted in ascending order of the frequencies */
 static struct cpufreq_frequency_table s3c2440_plls_169344[] = {
diff --git a/arch/arm/mach-s3c24xx/s3c2410.c b/arch/arm/mach-s3c24xx/s3c2410.c
index 21fd5404bc98..8427c150dd22 100644
--- a/arch/arm/mach-s3c24xx/s3c2410.c
+++ b/arch/arm/mach-s3c24xx/s3c2410.c
@@ -30,7 +30,6 @@
 #include <asm/irq.h>
 #include <asm/system_misc.h>
 
-#include <plat/cpu-freq.h>
 
 #include <mach/regs-clock.h>
 
diff --git a/arch/arm/mach-s3c24xx/s3c2412.c b/arch/arm/mach-s3c24xx/s3c2412.c
index c3fb3e6c0dd8..209f952a6c98 100644
--- a/arch/arm/mach-s3c24xx/s3c2412.c
+++ b/arch/arm/mach-s3c24xx/s3c2412.c
@@ -34,7 +34,6 @@
 #include <mach/regs-gpio.h>
 
 #include <plat/cpu.h>
-#include <plat/cpu-freq.h>
 #include <plat/devs.h>
 #include <plat/pm.h>
 
diff --git a/arch/arm/mach-s3c24xx/s3c244x.c b/arch/arm/mach-s3c24xx/s3c244x.c
index a75f588b9d45..f5bd489bac85 100644
--- a/arch/arm/mach-s3c24xx/s3c244x.c
+++ b/arch/arm/mach-s3c24xx/s3c244x.c
@@ -28,8 +28,6 @@
 #include <mach/hardware.h>
 #include <asm/irq.h>
 
-#include <plat/cpu-freq.h>
-
 #include <mach/regs-clock.h>
 #include <mach/regs-gpio.h>
 
diff --git a/arch/arm/mach-s3c64xx/s3c6400.c b/arch/arm/mach-s3c64xx/s3c6400.c
index 81233495d548..d18af724c807 100644
--- a/arch/arm/mach-s3c64xx/s3c6400.c
+++ b/arch/arm/mach-s3c64xx/s3c6400.c
@@ -28,7 +28,6 @@
 
 #include <asm/irq.h>
 
-#include <plat/cpu-freq.h>
 #include <mach/regs-clock.h>
 
 #include <plat/cpu.h>
diff --git a/arch/arm/mach-s3c64xx/s3c6410.c b/arch/arm/mach-s3c64xx/s3c6410.c
index 9465a6e0f068..b1d725e55cd2 100644
--- a/arch/arm/mach-s3c64xx/s3c6410.c
+++ b/arch/arm/mach-s3c64xx/s3c6410.c
@@ -29,7 +29,7 @@
 
 #include <asm/irq.h>
 
-#include <plat/cpu-freq.h>
+#include <linux/soc/samsung/s3c-pm.h>
 #include <mach/regs-clock.h>
 
 #include <plat/cpu.h>
diff --git a/arch/arm/plat-samsung/include/plat/cpu-freq-core.h b/arch/arm/plat-samsung/include/plat/cpu-freq-core.h
deleted file mode 100644
index 2c7cf2665634..000000000000
--- a/arch/arm/plat-samsung/include/plat/cpu-freq-core.h
+++ /dev/null
@@ -1,287 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (c) 2006-2009 Simtec Electronics
- *	http://armlinux.simtec.co.uk/
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * S3C CPU frequency scaling support - core support
- */
-
-#include <plat/cpu-freq.h>
-
-struct seq_file;
-
-#define MAX_BANKS (8)
-#define S3C2412_MAX_IO	(8)
-
-/**
- * struct s3c2410_iobank_timing - IO bank timings for S3C2410 style timings
- * @bankcon: The cached version of settings in this structure.
- * @tacp:
- * @tacs: Time from address valid to nCS asserted.
- * @tcos: Time from nCS asserted to nOE or nWE asserted.
- * @tacc: Time that nOE or nWE is asserted.
- * @tcoh: Time nCS is held after nOE or nWE are released.
- * @tcah: Time address is held for after
- * @nwait_en: Whether nWAIT is enabled for this bank.
- *
- * This structure represents the IO timings for a S3C2410 style IO bank
- * used by the CPU frequency support if it needs to change the settings
- * of the IO.
- */
-struct s3c2410_iobank_timing {
-	unsigned long	bankcon;
-	unsigned int	tacp;
-	unsigned int	tacs;
-	unsigned int	tcos;
-	unsigned int	tacc;
-	unsigned int	tcoh;		/* nCS hold after nOE/nWE */
-	unsigned int	tcah;		/* Address hold after nCS */
-	unsigned char	nwait_en;	/* nWait enabled for bank. */
-};
-
-/**
- * struct s3c2412_iobank_timing - io timings for PL092 (S3C2412) style IO
- * @idcy: The idle cycle time between transactions.
- * @wstrd: nCS release to end of read cycle.
- * @wstwr: nCS release to end of write cycle.
- * @wstoen: nCS assertion to nOE assertion time.
- * @wstwen: nCS assertion to nWE assertion time.
- * @wstbrd: Burst ready delay.
- * @smbidcyr: Register cache for smbidcyr value.
- * @smbwstrd: Register cache for smbwstrd value.
- * @smbwstwr: Register cache for smbwstwr value.
- * @smbwstoen: Register cache for smbwstoen value.
- * @smbwstwen: Register cache for smbwstwen value.
- * @smbwstbrd: Register cache for smbwstbrd value.
- *
- * Timing information for a IO bank on an S3C2412 or similar system which
- * uses a PL093 block.
- */
-struct s3c2412_iobank_timing {
-	unsigned int	idcy;
-	unsigned int	wstrd;
-	unsigned int	wstwr;
-	unsigned int	wstoen;
-	unsigned int	wstwen;
-	unsigned int	wstbrd;
-
-	/* register cache */
-	unsigned char	smbidcyr;
-	unsigned char	smbwstrd;
-	unsigned char	smbwstwr;
-	unsigned char	smbwstoen;
-	unsigned char	smbwstwen;
-	unsigned char	smbwstbrd;
-};
-
-union s3c_iobank {
-	struct s3c2410_iobank_timing	*io_2410;
-	struct s3c2412_iobank_timing	*io_2412;
-};
-
-/**
- * struct s3c_iotimings - Chip IO timings holder
- * @bank: The timings for each IO bank.
- */
-struct s3c_iotimings {
-	union s3c_iobank	bank[MAX_BANKS];
-};
-
-/**
- * struct s3c_plltab - PLL table information.
- * @vals: List of PLL values.
- * @size: Size of the PLL table @vals.
- */
-struct s3c_plltab {
-	struct s3c_pllval	*vals;
-	int			 size;
-};
-
-/**
- * struct s3c_cpufreq_config - current cpu frequency configuration
- * @freq: The current settings for the core clocks.
- * @max: Maxium settings, derived from core, board and user settings.
- * @pll: The PLL table entry for the current PLL settings.
- * @divs: The divisor settings for the core clocks.
- * @info: The current core driver information.
- * @board: The information for the board we are running on.
- * @lock_pll: Set if the PLL settings cannot be changed.
- *
- * This is for the core drivers that need to know information about
- * the current settings and values. It should not be needed by any
- * device drivers.
-*/
-struct s3c_cpufreq_config {
-	struct s3c_freq		freq;
-	struct s3c_freq		max;
-	struct clk		*mpll;
-	struct cpufreq_frequency_table pll;
-	struct s3c_clkdivs	divs;
-	struct s3c_cpufreq_info *info;	/* for core, not drivers */
-	struct s3c_cpufreq_board *board;
-
-	unsigned int	lock_pll:1;
-};
-
-/**
- * struct s3c_cpufreq_info - Information for the CPU frequency driver.
- * @name: The name of this implementation.
- * @max: The maximum frequencies for the system.
- * @latency: Transition latency to give to cpufreq.
- * @locktime_m: The lock-time in uS for the MPLL.
- * @locktime_u: The lock-time in uS for the UPLL.
- * @locttime_bits: The number of bits each LOCKTIME field.
- * @need_pll: Set if this driver needs to change the PLL values to achieve
- *	any frequency changes. This is really only need by devices like the
- *	S3C2410 where there is no or limited divider between the PLL and the
- *	ARMCLK.
- * @get_iotiming: Get the current IO timing data, mainly for use at start.
- * @set_iotiming: Update the IO timings from the cached copies calculated
- *	from the @calc_iotiming entry when changing the frequency.
- * @calc_iotiming: Calculate and update the cached copies of the IO timings
- *	from the newly calculated frequencies.
- * @calc_freqtable: Calculate (fill in) the given frequency table from the
- *	current frequency configuration. If the table passed in is NULL,
- *	then the return is the number of elements to be filled for allocation
- *	of the table.
- * @set_refresh: Set the memory refresh configuration.
- * @set_fvco: Set the PLL frequencies.
- * @set_divs: Update the clock divisors.
- * @calc_divs: Calculate the clock divisors.
- */
-struct s3c_cpufreq_info {
-	const char		*name;
-	struct s3c_freq		max;
-
-	unsigned int		latency;
-
-	unsigned int		locktime_m;
-	unsigned int		locktime_u;
-	unsigned char		locktime_bits;
-
-	unsigned int		need_pll:1;
-
-	/* driver routines */
-
-	int		(*get_iotiming)(struct s3c_cpufreq_config *cfg,
-					struct s3c_iotimings *timings);
-
-	void		(*set_iotiming)(struct s3c_cpufreq_config *cfg,
-					struct s3c_iotimings *timings);
-
-	int		(*calc_iotiming)(struct s3c_cpufreq_config *cfg,
-					 struct s3c_iotimings *timings);
-
-	int		(*calc_freqtable)(struct s3c_cpufreq_config *cfg,
-					  struct cpufreq_frequency_table *t,
-					  size_t table_size);
-
-	void		(*debug_io_show)(struct seq_file *seq,
-					 struct s3c_cpufreq_config *cfg,
-					 union s3c_iobank *iob);
-
-	void		(*set_refresh)(struct s3c_cpufreq_config *cfg);
-	void		(*set_fvco)(struct s3c_cpufreq_config *cfg);
-	void		(*set_divs)(struct s3c_cpufreq_config *cfg);
-	int		(*calc_divs)(struct s3c_cpufreq_config *cfg);
-};
-
-extern int s3c_cpufreq_register(struct s3c_cpufreq_info *info);
-
-extern int s3c_plltab_register(struct cpufreq_frequency_table *plls,
-			       unsigned int plls_no);
-
-/* exports and utilities for debugfs */
-extern struct s3c_cpufreq_config *s3c_cpufreq_getconfig(void);
-extern struct s3c_iotimings *s3c_cpufreq_getiotimings(void);
-
-#ifdef CONFIG_ARM_S3C24XX_CPUFREQ_DEBUGFS
-#define s3c_cpufreq_debugfs_call(x) x
-#else
-#define s3c_cpufreq_debugfs_call(x) NULL
-#endif
-
-/* Useful utility functions. */
-
-extern struct clk *s3c_cpufreq_clk_get(struct device *, const char *);
-
-/* S3C2410 and compatible exported functions */
-
-extern void s3c2410_cpufreq_setrefresh(struct s3c_cpufreq_config *cfg);
-extern void s3c2410_set_fvco(struct s3c_cpufreq_config *cfg);
-
-#ifdef CONFIG_S3C2410_IOTIMING
-extern void s3c2410_iotiming_debugfs(struct seq_file *seq,
-				     struct s3c_cpufreq_config *cfg,
-				     union s3c_iobank *iob);
-
-extern int s3c2410_iotiming_calc(struct s3c_cpufreq_config *cfg,
-				 struct s3c_iotimings *iot);
-
-extern int s3c2410_iotiming_get(struct s3c_cpufreq_config *cfg,
-				struct s3c_iotimings *timings);
-
-extern void s3c2410_iotiming_set(struct s3c_cpufreq_config *cfg,
-				 struct s3c_iotimings *iot);
-#else
-#define s3c2410_iotiming_debugfs NULL
-#define s3c2410_iotiming_calc NULL
-#define s3c2410_iotiming_get NULL
-#define s3c2410_iotiming_set NULL
-#endif /* CONFIG_S3C2410_IOTIMING */
-
-/* S3C2412 compatible routines */
-
-#ifdef CONFIG_S3C2412_IOTIMING
-extern void s3c2412_iotiming_debugfs(struct seq_file *seq,
-				     struct s3c_cpufreq_config *cfg,
-				     union s3c_iobank *iob);
-
-extern int s3c2412_iotiming_get(struct s3c_cpufreq_config *cfg,
-				struct s3c_iotimings *timings);
-
-extern int s3c2412_iotiming_calc(struct s3c_cpufreq_config *cfg,
-				 struct s3c_iotimings *iot);
-
-extern void s3c2412_iotiming_set(struct s3c_cpufreq_config *cfg,
-				 struct s3c_iotimings *iot);
-#else
-#define s3c2412_iotiming_debugfs NULL
-#define s3c2412_iotiming_calc NULL
-#define s3c2412_iotiming_get NULL
-#define s3c2412_iotiming_set NULL
-#endif /* CONFIG_S3C2412_IOTIMING */
-
-#ifdef CONFIG_ARM_S3C24XX_CPUFREQ_DEBUG
-#define s3c_freq_dbg(x...) printk(KERN_INFO x)
-#else
-#define s3c_freq_dbg(x...) do { if (0) printk(x); } while (0)
-#endif /* CONFIG_ARM_S3C24XX_CPUFREQ_DEBUG */
-
-#ifdef CONFIG_ARM_S3C24XX_CPUFREQ_IODEBUG
-#define s3c_freq_iodbg(x...) printk(KERN_INFO x)
-#else
-#define s3c_freq_iodbg(x...) do { if (0) printk(x); } while (0)
-#endif /* CONFIG_ARM_S3C24XX_CPUFREQ_IODEBUG */
-
-static inline int s3c_cpufreq_addfreq(struct cpufreq_frequency_table *table,
-				      int index, size_t table_size,
-				      unsigned int freq)
-{
-	if (index < 0)
-		return index;
-
-	if (table) {
-		if (index >= table_size)
-			return -ENOMEM;
-
-		s3c_freq_dbg("%s: { %d = %u kHz }\n",
-			     __func__, index, freq);
-
-		table[index].driver_data = index;
-		table[index].frequency = freq;
-	}
-
-	return index + 1;
-}
diff --git a/arch/arm/plat-samsung/include/plat/cpu-freq.h b/arch/arm/plat-samsung/include/plat/cpu-freq.h
deleted file mode 100644
index 558892bcf9b6..000000000000
--- a/arch/arm/plat-samsung/include/plat/cpu-freq.h
+++ /dev/null
@@ -1,141 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (c) 2006-2007 Simtec Electronics
- *	http://armlinux.simtec.co.uk/
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * S3C CPU frequency scaling support - driver and board
- */
-
-#include <linux/cpufreq.h>
-
-struct s3c_cpufreq_info;
-struct s3c_cpufreq_board;
-struct s3c_iotimings;
-
-/**
- * struct s3c_freq - frequency information (mainly for core drivers)
- * @fclk: The FCLK frequency in Hz.
- * @armclk: The ARMCLK frequency in Hz.
- * @hclk_tns: HCLK cycle time in 10ths of nano-seconds.
- * @hclk: The HCLK frequency in Hz.
- * @pclk: The PCLK frequency in Hz.
- *
- * This contains the frequency information about the current configuration
- * mainly for the core drivers to ensure we do not end up passing about
- * a large number of parameters.
- *
- * The @hclk_tns field is a useful cache for the parts of the drivers that
- * need to calculate IO timings and suchlike.
- */
-struct s3c_freq {
-	unsigned long	fclk;
-	unsigned long	armclk;
-	unsigned long	hclk_tns;	/* in 10ths of ns */
-	unsigned long	hclk;
-	unsigned long	pclk;
-};
-
-/**
- * struct s3c_cpufreq_freqs - s3c cpufreq notification information.
- * @freqs: The cpufreq setting information.
- * @old: The old clock settings.
- * @new: The new clock settings.
- * @pll_changing: Set if the PLL is changing.
- *
- * Wrapper 'struct cpufreq_freqs' so that any drivers receiving the
- * notification can use this information that is not provided by just
- * having the core frequency alone.
- *
- * The pll_changing flag is used to indicate if the PLL itself is
- * being set during this change. This is important as the clocks
- * will temporarily be set to the XTAL clock during this time, so
- * drivers may want to close down their output during this time.
- *
- * Note, this is not being used by any current drivers and therefore
- * may be removed in the future.
- */
-struct s3c_cpufreq_freqs {
-	struct cpufreq_freqs	freqs;
-	struct s3c_freq		old;
-	struct s3c_freq		new;
-
-	unsigned int		pll_changing:1;
-};
-
-#define to_s3c_cpufreq(_cf) container_of(_cf, struct s3c_cpufreq_freqs, freqs)
-
-/**
- * struct s3c_clkdivs - clock divisor information
- * @p_divisor: Divisor from FCLK to PCLK.
- * @h_divisor: Divisor from FCLK to HCLK.
- * @arm_divisor: Divisor from FCLK to ARMCLK (not all CPUs).
- * @dvs: Non-zero if using DVS mode for ARMCLK.
- *
- * Divisor settings for the core clocks.
- */
-struct s3c_clkdivs {
-	int		p_divisor;
-	int		h_divisor;
-	int		arm_divisor;
-	unsigned char	dvs;
-};
-
-#define PLLVAL(_m, _p, _s) (((_m) << 12) | ((_p) << 4) | (_s))
-
-/**
- * struct s3c_pllval - PLL value entry.
- * @freq: The frequency for this entry in Hz.
- * @pll_reg: The PLL register setting for this PLL value.
- */
-struct s3c_pllval {
-	unsigned long		freq;
-	unsigned long		pll_reg;
-};
-
-/**
- * struct s3c_cpufreq_board - per-board cpu frequency informatin
- * @refresh: The SDRAM refresh period in nanoseconds.
- * @auto_io: Set if the IO timing settings should be generated from the
- *	initialisation time hardware registers.
- * @need_io: Set if the board has external IO on any of the chipselect
- *	lines that will require the hardware timing registers to be
- *	updated on a clock change.
- * @max: The maxium frequency limits for the system. Any field that
- *	is left at zero will use the CPU's settings.
- *
- * This contains the board specific settings that affect how the CPU
- * drivers chose settings. These include the memory refresh and IO
- * timing information.
- *
- * Registration depends on the driver being used, the ARMCLK only
- * implementation does not currently need this but the older style
- * driver requires this to be available.
- */
-struct s3c_cpufreq_board {
-	unsigned int	refresh;
-	unsigned int	auto_io:1;	/* automatically init io timings. */
-	unsigned int	need_io:1;	/* set if needs io timing support. */
-
-	/* any non-zero field in here is taken as an upper limit. */
-	struct s3c_freq	max;	/* frequency limits */
-};
-
-/* Things depending on frequency scaling. */
-#ifdef CONFIG_ARM_S3C_CPUFREQ
-#define __init_or_cpufreq
-#else
-#define __init_or_cpufreq __init
-#endif
-
-/* Board functions */
-
-#ifdef CONFIG_ARM_S3C_CPUFREQ
-extern int s3c_cpufreq_setboard(struct s3c_cpufreq_board *board);
-#else
-
-static inline int s3c_cpufreq_setboard(struct s3c_cpufreq_board *board)
-{
-	return 0;
-}
-#endif  /* CONFIG_ARM_S3C_CPUFREQ */
diff --git a/arch/arm/plat-samsung/include/plat/cpu.h b/arch/arm/plat-samsung/include/plat/cpu.h
index 93ecd7127831..20ff98d05c53 100644
--- a/arch/arm/plat-samsung/include/plat/cpu.h
+++ b/arch/arm/plat-samsung/include/plat/cpu.h
@@ -123,15 +123,6 @@ extern struct syscore_ops s3c2412_pm_syscore_ops;
 extern struct syscore_ops s3c2416_pm_syscore_ops;
 extern struct syscore_ops s3c244x_pm_syscore_ops;
 
-/* system device subsystems */
-
-extern struct bus_type s3c2410_subsys;
-extern struct bus_type s3c2410a_subsys;
-extern struct bus_type s3c2412_subsys;
-extern struct bus_type s3c2416_subsys;
-extern struct bus_type s3c2440_subsys;
-extern struct bus_type s3c2442_subsys;
-extern struct bus_type s3c2443_subsys;
 extern struct bus_type s3c6410_subsys;
 
 #endif
diff --git a/drivers/cpufreq/s3c2410-cpufreq.c b/drivers/cpufreq/s3c2410-cpufreq.c
index 5c6cb590b63f..9c2f29cacdd0 100644
--- a/drivers/cpufreq/s3c2410-cpufreq.c
+++ b/drivers/cpufreq/s3c2410-cpufreq.c
@@ -16,13 +16,12 @@
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/io.h>
+#include <linux/soc/samsung/s3c-cpufreq-core.h>
+#include <linux/soc/samsung/s3c-pm.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 
-#include <plat/cpu.h>
-#include <plat/cpu-freq-core.h>
-
 #include <mach/map.h>
 
 #define S3C2410_CLKREG(x) ((x) + S3C24XX_VA_CLKPWR)
diff --git a/drivers/cpufreq/s3c2412-cpufreq.c b/drivers/cpufreq/s3c2412-cpufreq.c
index d922d0d47c80..38dc9e6db633 100644
--- a/drivers/cpufreq/s3c2412-cpufreq.c
+++ b/drivers/cpufreq/s3c2412-cpufreq.c
@@ -19,15 +19,14 @@
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/io.h>
+#include <linux/soc/samsung/s3c-cpufreq-core.h>
+#include <linux/soc/samsung/s3c-pm.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 
 #include <mach/s3c2412.h>
 
-#include <plat/cpu.h>
-#include <plat/cpu-freq-core.h>
-
 #include <mach/map.h>
 
 #define S3C2410_CLKREG(x) ((x) + S3C24XX_VA_CLKPWR)
diff --git a/drivers/cpufreq/s3c2440-cpufreq.c b/drivers/cpufreq/s3c2440-cpufreq.c
index 5fe7a891fa13..442abdccb9c1 100644
--- a/drivers/cpufreq/s3c2440-cpufreq.c
+++ b/drivers/cpufreq/s3c2440-cpufreq.c
@@ -20,13 +20,12 @@
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/io.h>
+#include <linux/soc/samsung/s3c-cpufreq-core.h>
+#include <linux/soc/samsung/s3c-pm.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 
-#include <plat/cpu.h>
-#include <plat/cpu-freq-core.h>
-
 #include <mach/map.h>
 
 #define S3C2410_CLKREG(x) ((x) + S3C24XX_VA_CLKPWR)
diff --git a/drivers/cpufreq/s3c24xx-cpufreq-debugfs.c b/drivers/cpufreq/s3c24xx-cpufreq-debugfs.c
index 290e3539d03e..93971dfe7c75 100644
--- a/drivers/cpufreq/s3c24xx-cpufreq-debugfs.c
+++ b/drivers/cpufreq/s3c24xx-cpufreq-debugfs.c
@@ -18,7 +18,7 @@
 #include <linux/seq_file.h>
 #include <linux/err.h>
 
-#include <plat/cpu-freq-core.h>
+#include <linux/soc/samsung/s3c-cpufreq-core.h>
 
 static struct dentry *dbgfs_root;
 static struct dentry *dbgfs_file_io;
diff --git a/drivers/cpufreq/s3c24xx-cpufreq.c b/drivers/cpufreq/s3c24xx-cpufreq.c
index cf0571e8fafb..27111fbca2ff 100644
--- a/drivers/cpufreq/s3c24xx-cpufreq.c
+++ b/drivers/cpufreq/s3c24xx-cpufreq.c
@@ -21,13 +21,12 @@
 #include <linux/device.h>
 #include <linux/sysfs.h>
 #include <linux/slab.h>
+#include <linux/soc/samsung/s3c-cpufreq-core.h>
+#include <linux/soc/samsung/s3c-pm.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 
-#include <plat/cpu.h>
-#include <plat/cpu-freq-core.h>
-
 #include <mach/map.h>
 
 /* note, cpufreq support deals in kHz, no Hz */
diff --git a/include/linux/soc/samsung/s3c-cpu-freq.h b/include/linux/soc/samsung/s3c-cpu-freq.h
new file mode 100644
index 000000000000..63e88fd5dea2
--- /dev/null
+++ b/include/linux/soc/samsung/s3c-cpu-freq.h
@@ -0,0 +1,145 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2006-2007 Simtec Electronics
+ *	http://armlinux.simtec.co.uk/
+ *	Ben Dooks <ben@simtec.co.uk>
+ *
+ * S3C CPU frequency scaling support - driver and board
+ */
+#ifndef __LINUX_SOC_SAMSUNG_S3C_CPU_FREQ_H
+#define __LINUX_SOC_SAMSUNG_S3C_CPU_FREQ_H
+
+#include <linux/cpufreq.h>
+
+struct s3c_cpufreq_info;
+struct s3c_cpufreq_board;
+struct s3c_iotimings;
+
+/**
+ * struct s3c_freq - frequency information (mainly for core drivers)
+ * @fclk: The FCLK frequency in Hz.
+ * @armclk: The ARMCLK frequency in Hz.
+ * @hclk_tns: HCLK cycle time in 10ths of nano-seconds.
+ * @hclk: The HCLK frequency in Hz.
+ * @pclk: The PCLK frequency in Hz.
+ *
+ * This contains the frequency information about the current configuration
+ * mainly for the core drivers to ensure we do not end up passing about
+ * a large number of parameters.
+ *
+ * The @hclk_tns field is a useful cache for the parts of the drivers that
+ * need to calculate IO timings and suchlike.
+ */
+struct s3c_freq {
+	unsigned long	fclk;
+	unsigned long	armclk;
+	unsigned long	hclk_tns;	/* in 10ths of ns */
+	unsigned long	hclk;
+	unsigned long	pclk;
+};
+
+/**
+ * struct s3c_cpufreq_freqs - s3c cpufreq notification information.
+ * @freqs: The cpufreq setting information.
+ * @old: The old clock settings.
+ * @new: The new clock settings.
+ * @pll_changing: Set if the PLL is changing.
+ *
+ * Wrapper 'struct cpufreq_freqs' so that any drivers receiving the
+ * notification can use this information that is not provided by just
+ * having the core frequency alone.
+ *
+ * The pll_changing flag is used to indicate if the PLL itself is
+ * being set during this change. This is important as the clocks
+ * will temporarily be set to the XTAL clock during this time, so
+ * drivers may want to close down their output during this time.
+ *
+ * Note, this is not being used by any current drivers and therefore
+ * may be removed in the future.
+ */
+struct s3c_cpufreq_freqs {
+	struct cpufreq_freqs	freqs;
+	struct s3c_freq		old;
+	struct s3c_freq		new;
+
+	unsigned int		pll_changing:1;
+};
+
+#define to_s3c_cpufreq(_cf) container_of(_cf, struct s3c_cpufreq_freqs, freqs)
+
+/**
+ * struct s3c_clkdivs - clock divisor information
+ * @p_divisor: Divisor from FCLK to PCLK.
+ * @h_divisor: Divisor from FCLK to HCLK.
+ * @arm_divisor: Divisor from FCLK to ARMCLK (not all CPUs).
+ * @dvs: Non-zero if using DVS mode for ARMCLK.
+ *
+ * Divisor settings for the core clocks.
+ */
+struct s3c_clkdivs {
+	int		p_divisor;
+	int		h_divisor;
+	int		arm_divisor;
+	unsigned char	dvs;
+};
+
+#define PLLVAL(_m, _p, _s) (((_m) << 12) | ((_p) << 4) | (_s))
+
+/**
+ * struct s3c_pllval - PLL value entry.
+ * @freq: The frequency for this entry in Hz.
+ * @pll_reg: The PLL register setting for this PLL value.
+ */
+struct s3c_pllval {
+	unsigned long		freq;
+	unsigned long		pll_reg;
+};
+
+/**
+ * struct s3c_cpufreq_board - per-board cpu frequency informatin
+ * @refresh: The SDRAM refresh period in nanoseconds.
+ * @auto_io: Set if the IO timing settings should be generated from the
+ *	initialisation time hardware registers.
+ * @need_io: Set if the board has external IO on any of the chipselect
+ *	lines that will require the hardware timing registers to be
+ *	updated on a clock change.
+ * @max: The maxium frequency limits for the system. Any field that
+ *	is left at zero will use the CPU's settings.
+ *
+ * This contains the board specific settings that affect how the CPU
+ * drivers chose settings. These include the memory refresh and IO
+ * timing information.
+ *
+ * Registration depends on the driver being used, the ARMCLK only
+ * implementation does not currently need this but the older style
+ * driver requires this to be available.
+ */
+struct s3c_cpufreq_board {
+	unsigned int	refresh;
+	unsigned int	auto_io:1;	/* automatically init io timings. */
+	unsigned int	need_io:1;	/* set if needs io timing support. */
+
+	/* any non-zero field in here is taken as an upper limit. */
+	struct s3c_freq	max;	/* frequency limits */
+};
+
+/* Things depending on frequency scaling. */
+#ifdef CONFIG_ARM_S3C_CPUFREQ
+#define __init_or_cpufreq
+#else
+#define __init_or_cpufreq __init
+#endif
+
+/* Board functions */
+
+#ifdef CONFIG_ARM_S3C_CPUFREQ
+extern int s3c_cpufreq_setboard(struct s3c_cpufreq_board *board);
+#else
+
+static inline int s3c_cpufreq_setboard(struct s3c_cpufreq_board *board)
+{
+	return 0;
+}
+#endif  /* CONFIG_ARM_S3C_CPUFREQ */
+
+#endif
diff --git a/include/linux/soc/samsung/s3c-cpufreq-core.h b/include/linux/soc/samsung/s3c-cpufreq-core.h
new file mode 100644
index 000000000000..c578b07ccd5d
--- /dev/null
+++ b/include/linux/soc/samsung/s3c-cpufreq-core.h
@@ -0,0 +1,291 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2006-2009 Simtec Electronics
+ *	http://armlinux.simtec.co.uk/
+ *	Ben Dooks <ben@simtec.co.uk>
+ *
+ * S3C CPU frequency scaling support - core support
+ */
+#ifndef __LINUX_SOC_SAMSUNG_S3C_CPUFREQ_CORE_H
+#define __LINUX_SOC_SAMSUNG_S3C_CPUFREQ_CORE_H
+
+#include <linux/soc/samsung/s3c-cpu-freq.h>
+
+struct seq_file;
+
+#define MAX_BANKS (8)
+#define S3C2412_MAX_IO	(8)
+
+/**
+ * struct s3c2410_iobank_timing - IO bank timings for S3C2410 style timings
+ * @bankcon: The cached version of settings in this structure.
+ * @tacp:
+ * @tacs: Time from address valid to nCS asserted.
+ * @tcos: Time from nCS asserted to nOE or nWE asserted.
+ * @tacc: Time that nOE or nWE is asserted.
+ * @tcoh: Time nCS is held after nOE or nWE are released.
+ * @tcah: Time address is held for after
+ * @nwait_en: Whether nWAIT is enabled for this bank.
+ *
+ * This structure represents the IO timings for a S3C2410 style IO bank
+ * used by the CPU frequency support if it needs to change the settings
+ * of the IO.
+ */
+struct s3c2410_iobank_timing {
+	unsigned long	bankcon;
+	unsigned int	tacp;
+	unsigned int	tacs;
+	unsigned int	tcos;
+	unsigned int	tacc;
+	unsigned int	tcoh;		/* nCS hold after nOE/nWE */
+	unsigned int	tcah;		/* Address hold after nCS */
+	unsigned char	nwait_en;	/* nWait enabled for bank. */
+};
+
+/**
+ * struct s3c2412_iobank_timing - io timings for PL092 (S3C2412) style IO
+ * @idcy: The idle cycle time between transactions.
+ * @wstrd: nCS release to end of read cycle.
+ * @wstwr: nCS release to end of write cycle.
+ * @wstoen: nCS assertion to nOE assertion time.
+ * @wstwen: nCS assertion to nWE assertion time.
+ * @wstbrd: Burst ready delay.
+ * @smbidcyr: Register cache for smbidcyr value.
+ * @smbwstrd: Register cache for smbwstrd value.
+ * @smbwstwr: Register cache for smbwstwr value.
+ * @smbwstoen: Register cache for smbwstoen value.
+ * @smbwstwen: Register cache for smbwstwen value.
+ * @smbwstbrd: Register cache for smbwstbrd value.
+ *
+ * Timing information for a IO bank on an S3C2412 or similar system which
+ * uses a PL093 block.
+ */
+struct s3c2412_iobank_timing {
+	unsigned int	idcy;
+	unsigned int	wstrd;
+	unsigned int	wstwr;
+	unsigned int	wstoen;
+	unsigned int	wstwen;
+	unsigned int	wstbrd;
+
+	/* register cache */
+	unsigned char	smbidcyr;
+	unsigned char	smbwstrd;
+	unsigned char	smbwstwr;
+	unsigned char	smbwstoen;
+	unsigned char	smbwstwen;
+	unsigned char	smbwstbrd;
+};
+
+union s3c_iobank {
+	struct s3c2410_iobank_timing	*io_2410;
+	struct s3c2412_iobank_timing	*io_2412;
+};
+
+/**
+ * struct s3c_iotimings - Chip IO timings holder
+ * @bank: The timings for each IO bank.
+ */
+struct s3c_iotimings {
+	union s3c_iobank	bank[MAX_BANKS];
+};
+
+/**
+ * struct s3c_plltab - PLL table information.
+ * @vals: List of PLL values.
+ * @size: Size of the PLL table @vals.
+ */
+struct s3c_plltab {
+	struct s3c_pllval	*vals;
+	int			 size;
+};
+
+/**
+ * struct s3c_cpufreq_config - current cpu frequency configuration
+ * @freq: The current settings for the core clocks.
+ * @max: Maxium settings, derived from core, board and user settings.
+ * @pll: The PLL table entry for the current PLL settings.
+ * @divs: The divisor settings for the core clocks.
+ * @info: The current core driver information.
+ * @board: The information for the board we are running on.
+ * @lock_pll: Set if the PLL settings cannot be changed.
+ *
+ * This is for the core drivers that need to know information about
+ * the current settings and values. It should not be needed by any
+ * device drivers.
+*/
+struct s3c_cpufreq_config {
+	struct s3c_freq		freq;
+	struct s3c_freq		max;
+	struct clk		*mpll;
+	struct cpufreq_frequency_table pll;
+	struct s3c_clkdivs	divs;
+	struct s3c_cpufreq_info *info;	/* for core, not drivers */
+	struct s3c_cpufreq_board *board;
+
+	unsigned int	lock_pll:1;
+};
+
+/**
+ * struct s3c_cpufreq_info - Information for the CPU frequency driver.
+ * @name: The name of this implementation.
+ * @max: The maximum frequencies for the system.
+ * @latency: Transition latency to give to cpufreq.
+ * @locktime_m: The lock-time in uS for the MPLL.
+ * @locktime_u: The lock-time in uS for the UPLL.
+ * @locttime_bits: The number of bits each LOCKTIME field.
+ * @need_pll: Set if this driver needs to change the PLL values to achieve
+ *	any frequency changes. This is really only need by devices like the
+ *	S3C2410 where there is no or limited divider between the PLL and the
+ *	ARMCLK.
+ * @get_iotiming: Get the current IO timing data, mainly for use at start.
+ * @set_iotiming: Update the IO timings from the cached copies calculated
+ *	from the @calc_iotiming entry when changing the frequency.
+ * @calc_iotiming: Calculate and update the cached copies of the IO timings
+ *	from the newly calculated frequencies.
+ * @calc_freqtable: Calculate (fill in) the given frequency table from the
+ *	current frequency configuration. If the table passed in is NULL,
+ *	then the return is the number of elements to be filled for allocation
+ *	of the table.
+ * @set_refresh: Set the memory refresh configuration.
+ * @set_fvco: Set the PLL frequencies.
+ * @set_divs: Update the clock divisors.
+ * @calc_divs: Calculate the clock divisors.
+ */
+struct s3c_cpufreq_info {
+	const char		*name;
+	struct s3c_freq		max;
+
+	unsigned int		latency;
+
+	unsigned int		locktime_m;
+	unsigned int		locktime_u;
+	unsigned char		locktime_bits;
+
+	unsigned int		need_pll:1;
+
+	/* driver routines */
+
+	int		(*get_iotiming)(struct s3c_cpufreq_config *cfg,
+					struct s3c_iotimings *timings);
+
+	void		(*set_iotiming)(struct s3c_cpufreq_config *cfg,
+					struct s3c_iotimings *timings);
+
+	int		(*calc_iotiming)(struct s3c_cpufreq_config *cfg,
+					 struct s3c_iotimings *timings);
+
+	int		(*calc_freqtable)(struct s3c_cpufreq_config *cfg,
+					  struct cpufreq_frequency_table *t,
+					  size_t table_size);
+
+	void		(*debug_io_show)(struct seq_file *seq,
+					 struct s3c_cpufreq_config *cfg,
+					 union s3c_iobank *iob);
+
+	void		(*set_refresh)(struct s3c_cpufreq_config *cfg);
+	void		(*set_fvco)(struct s3c_cpufreq_config *cfg);
+	void		(*set_divs)(struct s3c_cpufreq_config *cfg);
+	int		(*calc_divs)(struct s3c_cpufreq_config *cfg);
+};
+
+extern int s3c_cpufreq_register(struct s3c_cpufreq_info *info);
+
+extern int s3c_plltab_register(struct cpufreq_frequency_table *plls,
+			       unsigned int plls_no);
+
+/* exports and utilities for debugfs */
+extern struct s3c_cpufreq_config *s3c_cpufreq_getconfig(void);
+extern struct s3c_iotimings *s3c_cpufreq_getiotimings(void);
+
+#ifdef CONFIG_ARM_S3C24XX_CPUFREQ_DEBUGFS
+#define s3c_cpufreq_debugfs_call(x) x
+#else
+#define s3c_cpufreq_debugfs_call(x) NULL
+#endif
+
+/* Useful utility functions. */
+
+extern struct clk *s3c_cpufreq_clk_get(struct device *, const char *);
+
+/* S3C2410 and compatible exported functions */
+
+extern void s3c2410_cpufreq_setrefresh(struct s3c_cpufreq_config *cfg);
+extern void s3c2410_set_fvco(struct s3c_cpufreq_config *cfg);
+
+#ifdef CONFIG_S3C2410_IOTIMING
+extern void s3c2410_iotiming_debugfs(struct seq_file *seq,
+				     struct s3c_cpufreq_config *cfg,
+				     union s3c_iobank *iob);
+
+extern int s3c2410_iotiming_calc(struct s3c_cpufreq_config *cfg,
+				 struct s3c_iotimings *iot);
+
+extern int s3c2410_iotiming_get(struct s3c_cpufreq_config *cfg,
+				struct s3c_iotimings *timings);
+
+extern void s3c2410_iotiming_set(struct s3c_cpufreq_config *cfg,
+				 struct s3c_iotimings *iot);
+#else
+#define s3c2410_iotiming_debugfs NULL
+#define s3c2410_iotiming_calc NULL
+#define s3c2410_iotiming_get NULL
+#define s3c2410_iotiming_set NULL
+#endif /* CONFIG_S3C2410_IOTIMING */
+
+/* S3C2412 compatible routines */
+
+#ifdef CONFIG_S3C2412_IOTIMING
+extern void s3c2412_iotiming_debugfs(struct seq_file *seq,
+				     struct s3c_cpufreq_config *cfg,
+				     union s3c_iobank *iob);
+
+extern int s3c2412_iotiming_get(struct s3c_cpufreq_config *cfg,
+				struct s3c_iotimings *timings);
+
+extern int s3c2412_iotiming_calc(struct s3c_cpufreq_config *cfg,
+				 struct s3c_iotimings *iot);
+
+extern void s3c2412_iotiming_set(struct s3c_cpufreq_config *cfg,
+				 struct s3c_iotimings *iot);
+#else
+#define s3c2412_iotiming_debugfs NULL
+#define s3c2412_iotiming_calc NULL
+#define s3c2412_iotiming_get NULL
+#define s3c2412_iotiming_set NULL
+#endif /* CONFIG_S3C2412_IOTIMING */
+
+#ifdef CONFIG_ARM_S3C24XX_CPUFREQ_DEBUG
+#define s3c_freq_dbg(x...) printk(KERN_INFO x)
+#else
+#define s3c_freq_dbg(x...) do { if (0) printk(x); } while (0)
+#endif /* CONFIG_ARM_S3C24XX_CPUFREQ_DEBUG */
+
+#ifdef CONFIG_ARM_S3C24XX_CPUFREQ_IODEBUG
+#define s3c_freq_iodbg(x...) printk(KERN_INFO x)
+#else
+#define s3c_freq_iodbg(x...) do { if (0) printk(x); } while (0)
+#endif /* CONFIG_ARM_S3C24XX_CPUFREQ_IODEBUG */
+
+static inline int s3c_cpufreq_addfreq(struct cpufreq_frequency_table *table,
+				      int index, size_t table_size,
+				      unsigned int freq)
+{
+	if (index < 0)
+		return index;
+
+	if (table) {
+		if (index >= table_size)
+			return -ENOMEM;
+
+		s3c_freq_dbg("%s: { %d = %u kHz }\n",
+			     __func__, index, freq);
+
+		table[index].driver_data = index;
+		table[index].frequency = freq;
+	}
+
+	return index + 1;
+}
+
+#endif
diff --git a/include/linux/soc/samsung/s3c-pm.h b/include/linux/soc/samsung/s3c-pm.h
index 730bd1d3d09a..f9164559c99f 100644
--- a/include/linux/soc/samsung/s3c-pm.h
+++ b/include/linux/soc/samsung/s3c-pm.h
@@ -81,4 +81,14 @@ extern void s3c_pm_check_store(void);
 #define s3c_pm_check_store()   do { } while (0)
 #endif
 
+/* system device subsystems */
+
+extern struct bus_type s3c2410_subsys;
+extern struct bus_type s3c2410a_subsys;
+extern struct bus_type s3c2412_subsys;
+extern struct bus_type s3c2416_subsys;
+extern struct bus_type s3c2440_subsys;
+extern struct bus_type s3c2442_subsys;
+extern struct bus_type s3c2443_subsys;
+
 #endif
-- 
cgit v1.2.3


From 44c01f5ce1c7518886a87d5522528e30e0b4d9f8 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 6 Aug 2020 20:20:53 +0200
Subject: cpufreq: s3c2412: use global s3c2412_cpufreq_setrefresh

There are two identical copies of the s3c2412_cpufreq_setrefresh
function: a static one in the cpufreq driver and a global
version in iotiming-s3c2412.c.

As the function requires the use of a hardcoded register address
from a header that we want to not be visible to drivers, just
move the existing global function and add a declaration in
one of the cpufreq header files.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Link: https://lore.kernel.org/r/20200806182059.2431-36-krzk@kernel.org
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
---
 drivers/cpufreq/s3c2412-cpufreq.c            | 23 -----------------------
 include/linux/soc/samsung/s3c-cpufreq-core.h |  1 +
 2 files changed, 1 insertion(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/cpufreq/s3c2412-cpufreq.c b/drivers/cpufreq/s3c2412-cpufreq.c
index 38dc9e6db633..a77c63e92e1a 100644
--- a/drivers/cpufreq/s3c2412-cpufreq.c
+++ b/drivers/cpufreq/s3c2412-cpufreq.c
@@ -25,8 +25,6 @@
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 
-#include <mach/s3c2412.h>
-
 #include <mach/map.h>
 
 #define S3C2410_CLKREG(x) ((x) + S3C24XX_VA_CLKPWR)
@@ -156,27 +154,6 @@ static void s3c2412_cpufreq_setdivs(struct s3c_cpufreq_config *cfg)
 	clk_set_parent(armclk, cfg->divs.dvs ? hclk : fclk);
 }
 
-static void s3c2412_cpufreq_setrefresh(struct s3c_cpufreq_config *cfg)
-{
-	struct s3c_cpufreq_board *board = cfg->board;
-	unsigned long refresh;
-
-	s3c_freq_dbg("%s: refresh %u ns, hclk %lu\n", __func__,
-		     board->refresh, cfg->freq.hclk);
-
-	/* Reduce both the refresh time (in ns) and the frequency (in MHz)
-	 * by 10 each to ensure that we do not overflow 32 bit numbers. This
-	 * should work for HCLK up to 133MHz and refresh period up to 30usec.
-	 */
-
-	refresh = (board->refresh / 10);
-	refresh *= (cfg->freq.hclk / 100);
-	refresh /= (1 * 1000 * 1000);	/* 10^6 */
-
-	s3c_freq_dbg("%s: setting refresh 0x%08lx\n", __func__, refresh);
-	__raw_writel(refresh, S3C2412_REFRESH);
-}
-
 /* set the default cpu frequency information, based on an 200MHz part
  * as we have no other way of detecting the speed rating in software.
  */
diff --git a/include/linux/soc/samsung/s3c-cpufreq-core.h b/include/linux/soc/samsung/s3c-cpufreq-core.h
index c578b07ccd5d..e0c7217a0f53 100644
--- a/include/linux/soc/samsung/s3c-cpufreq-core.h
+++ b/include/linux/soc/samsung/s3c-cpufreq-core.h
@@ -248,6 +248,7 @@ extern int s3c2412_iotiming_calc(struct s3c_cpufreq_config *cfg,
 
 extern void s3c2412_iotiming_set(struct s3c_cpufreq_config *cfg,
 				 struct s3c_iotimings *iot);
+extern void s3c2412_cpufreq_setrefresh(struct s3c_cpufreq_config *cfg);
 #else
 #define s3c2412_iotiming_debugfs NULL
 #define s3c2412_iotiming_calc NULL
-- 
cgit v1.2.3


From c38758e3d574380ccfa583793be14c1cc8a322ff Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 6 Aug 2020 20:20:54 +0200
Subject: cpufreq: s3c24xx: move low-level clk reg access into platform code

Rather than have the cpufreq drivers touch include the
common headers to get the constants, add a small indirection.
This is still not the proper way that would do this through
the common clk API, but it lets us kill off the header file
usage.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Link: https://lore.kernel.org/r/20200806182059.2431-37-krzk@kernel.org
[krzk: Rebase and fix -Wold-style-definition]
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
---
 arch/arm/mach-s3c24xx/Kconfig                |  7 ------
 arch/arm/mach-s3c24xx/Makefile               |  2 +-
 arch/arm/mach-s3c24xx/cpufreq-utils.c        | 32 ++++++++++++++++++++++++++++
 drivers/cpufreq/Kconfig.arm                  |  2 --
 drivers/cpufreq/s3c2410-cpufreq.c            |  8 +------
 drivers/cpufreq/s3c2412-cpufreq.c            | 10 ++-------
 drivers/cpufreq/s3c2440-cpufreq.c            | 16 +++++---------
 drivers/cpufreq/s3c24xx-cpufreq.c            | 12 +++--------
 include/linux/soc/samsung/s3c-cpufreq-core.h |  7 ++++++
 9 files changed, 51 insertions(+), 45 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/mach-s3c24xx/Kconfig b/arch/arm/mach-s3c24xx/Kconfig
index eaea567fcbfe..000e3e234f71 100644
--- a/arch/arm/mach-s3c24xx/Kconfig
+++ b/arch/arm/mach-s3c24xx/Kconfig
@@ -132,13 +132,6 @@ config S3C2410_IOTIMING
 	  Internal node to select io timing code that is common to the s3c2410
 	  and s3c2440/s3c2442 cpu frequency support.
 
-config S3C2410_CPUFREQ_UTILS
-       bool
-       depends on ARM_S3C24XX_CPUFREQ
-       help
-         Internal node to select timing code that is common to the s3c2410
-         and s3c2440/s3c244 cpu frequency support.
-
 # cpu frequency support common to s3c2412, s3c2413 and s3c2442
 
 config S3C2412_IOTIMING
diff --git a/arch/arm/mach-s3c24xx/Makefile b/arch/arm/mach-s3c24xx/Makefile
index b69eee24940b..68e583c94679 100644
--- a/arch/arm/mach-s3c24xx/Makefile
+++ b/arch/arm/mach-s3c24xx/Makefile
@@ -38,7 +38,7 @@ obj-$(CONFIG_PM_SLEEP)		+= irq-pm.o sleep.o
 
 # common code
 
-obj-$(CONFIG_S3C2410_CPUFREQ_UTILS) += cpufreq-utils.o
+obj-$(CONFIG_ARM_S3C24XX_CPUFREQ) += cpufreq-utils.o
 
 obj-$(CONFIG_S3C2410_IOTIMING)	+= iotiming-s3c2410.o
 obj-$(CONFIG_S3C2412_IOTIMING)	+= iotiming-s3c2412.o
diff --git a/arch/arm/mach-s3c24xx/cpufreq-utils.c b/arch/arm/mach-s3c24xx/cpufreq-utils.c
index 43ab714eaa9e..3bc374dd0b2d 100644
--- a/arch/arm/mach-s3c24xx/cpufreq-utils.c
+++ b/arch/arm/mach-s3c24xx/cpufreq-utils.c
@@ -60,3 +60,35 @@ void s3c2410_set_fvco(struct s3c_cpufreq_config *cfg)
 	if (!IS_ERR(cfg->mpll))
 		clk_set_rate(cfg->mpll, cfg->pll.frequency);
 }
+
+#if defined(CONFIG_CPU_S3C2440) || defined(CONFIG_CPU_S3C2442)
+u32 s3c2440_read_camdivn(void)
+{
+	return __raw_readl(S3C2440_CAMDIVN);
+}
+
+void s3c2440_write_camdivn(u32 camdiv)
+{
+	__raw_writel(camdiv, S3C2440_CAMDIVN);
+}
+#endif
+
+u32 s3c24xx_read_clkdivn(void)
+{
+	return __raw_readl(S3C2410_CLKDIVN);
+}
+
+void s3c24xx_write_clkdivn(u32 clkdiv)
+{
+	__raw_writel(clkdiv, S3C2410_CLKDIVN);
+}
+
+u32 s3c24xx_read_mpllcon(void)
+{
+	return __raw_readl(S3C2410_MPLLCON);
+}
+
+void s3c24xx_write_locktime(u32 locktime)
+{
+	return __raw_writel(locktime, S3C2410_LOCKTIME);
+}
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index cb72fb507d57..6514a39981e1 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -196,7 +196,6 @@ config ARM_S3C24XX_CPUFREQ_DEBUGFS
 config ARM_S3C2410_CPUFREQ
 	bool
 	depends on ARM_S3C24XX_CPUFREQ && CPU_S3C2410
-	select S3C2410_CPUFREQ_UTILS
 	help
 	  CPU Frequency scaling support for S3C2410
 
@@ -233,7 +232,6 @@ config ARM_S3C2416_CPUFREQ_VCORESCALE
 config ARM_S3C2440_CPUFREQ
 	bool "S3C2440/S3C2442 CPU Frequency scaling support"
 	depends on ARM_S3C24XX_CPUFREQ && (CPU_S3C2440 || CPU_S3C2442)
-	select S3C2410_CPUFREQ_UTILS
 	default y
 	help
 	  CPU Frequency scaling support for S3C2440 and S3C2442 SoC CPUs.
diff --git a/drivers/cpufreq/s3c2410-cpufreq.c b/drivers/cpufreq/s3c2410-cpufreq.c
index 9c2f29cacdd0..5dcfbf0bfb74 100644
--- a/drivers/cpufreq/s3c2410-cpufreq.c
+++ b/drivers/cpufreq/s3c2410-cpufreq.c
@@ -22,12 +22,6 @@
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 
-#include <mach/map.h>
-
-#define S3C2410_CLKREG(x) ((x) + S3C24XX_VA_CLKPWR)
-
-#define S3C2410_CLKDIVN	    S3C2410_CLKREG(0x14)
-
 #define S3C2410_CLKDIVN_PDIVN	     (1<<0)
 #define S3C2410_CLKDIVN_HDIVN	     (1<<1)
 
@@ -43,7 +37,7 @@ static void s3c2410_cpufreq_setdivs(struct s3c_cpufreq_config *cfg)
 	if (cfg->divs.p_divisor != cfg->divs.h_divisor)
 		clkdiv |= S3C2410_CLKDIVN_PDIVN;
 
-	__raw_writel(clkdiv, S3C2410_CLKDIVN);
+	s3c24xx_write_clkdivn(clkdiv);
 }
 
 static int s3c2410_cpufreq_calcdivs(struct s3c_cpufreq_config *cfg)
diff --git a/drivers/cpufreq/s3c2412-cpufreq.c b/drivers/cpufreq/s3c2412-cpufreq.c
index a77c63e92e1a..5945945ead7c 100644
--- a/drivers/cpufreq/s3c2412-cpufreq.c
+++ b/drivers/cpufreq/s3c2412-cpufreq.c
@@ -25,12 +25,6 @@
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 
-#include <mach/map.h>
-
-#define S3C2410_CLKREG(x) ((x) + S3C24XX_VA_CLKPWR)
-
-#define S3C2410_CLKDIVN	    S3C2410_CLKREG(0x14)
-
 #define S3C2412_CLKDIVN_PDIVN		(1<<2)
 #define S3C2412_CLKDIVN_HDIVN_MASK	(3<<0)
 #define S3C2412_CLKDIVN_ARMDIVN		(1<<3)
@@ -132,7 +126,7 @@ static void s3c2412_cpufreq_setdivs(struct s3c_cpufreq_config *cfg)
 	unsigned long clkdiv;
 	unsigned long olddiv;
 
-	olddiv = clkdiv = __raw_readl(S3C2410_CLKDIVN);
+	olddiv = clkdiv = s3c24xx_read_clkdivn();
 
 	/* clear off current clock info */
 
@@ -149,7 +143,7 @@ static void s3c2412_cpufreq_setdivs(struct s3c_cpufreq_config *cfg)
 		clkdiv |= S3C2412_CLKDIVN_PDIVN;
 
 	s3c_freq_dbg("%s: div %08lx => %08lx\n", __func__, olddiv, clkdiv);
-	__raw_writel(clkdiv, S3C2410_CLKDIVN);
+	s3c24xx_write_clkdivn(clkdiv);
 
 	clk_set_parent(armclk, cfg->divs.dvs ? hclk : fclk);
 }
diff --git a/drivers/cpufreq/s3c2440-cpufreq.c b/drivers/cpufreq/s3c2440-cpufreq.c
index 442abdccb9c1..148e8aedefa9 100644
--- a/drivers/cpufreq/s3c2440-cpufreq.c
+++ b/drivers/cpufreq/s3c2440-cpufreq.c
@@ -26,12 +26,6 @@
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 
-#include <mach/map.h>
-
-#define S3C2410_CLKREG(x) ((x) + S3C24XX_VA_CLKPWR)
-#define S3C2410_CLKDIVN	    S3C2410_CLKREG(0x14)
-#define S3C2440_CAMDIVN	    S3C2410_CLKREG(0x18)
-
 #define S3C2440_CLKDIVN_PDIVN	     (1<<0)
 #define S3C2440_CLKDIVN_HDIVN_MASK   (3<<1)
 #define S3C2440_CLKDIVN_HDIVN_1      (0<<1)
@@ -162,8 +156,8 @@ static void s3c2440_cpufreq_setdivs(struct s3c_cpufreq_config *cfg)
 	s3c_freq_dbg("%s: divisors: h=%d, p=%d\n", __func__,
 		     cfg->divs.h_divisor, cfg->divs.p_divisor);
 
-	clkdiv = __raw_readl(S3C2410_CLKDIVN);
-	camdiv = __raw_readl(S3C2440_CAMDIVN);
+	clkdiv = s3c24xx_read_clkdivn();
+	camdiv = s3c2440_read_camdivn();
 
 	clkdiv &= ~(S3C2440_CLKDIVN_HDIVN_MASK | S3C2440_CLKDIVN_PDIVN);
 	camdiv &= ~CAMDIVN_HCLK_HALF;
@@ -203,11 +197,11 @@ static void s3c2440_cpufreq_setdivs(struct s3c_cpufreq_config *cfg)
 	 * then make a short delay and remove the hclk halving if necessary.
 	 */
 
-	__raw_writel(camdiv | CAMDIVN_HCLK_HALF, S3C2440_CAMDIVN);
-	__raw_writel(clkdiv, S3C2410_CLKDIVN);
+	s3c2440_write_camdivn(camdiv | CAMDIVN_HCLK_HALF);
+	s3c24xx_write_clkdivn(clkdiv);
 
 	ndelay(20);
-	__raw_writel(camdiv, S3C2440_CAMDIVN);
+	s3c2440_write_camdivn(camdiv);
 
 	clk_set_parent(armclk, cfg->divs.dvs ? hclk : fclk);
 }
diff --git a/drivers/cpufreq/s3c24xx-cpufreq.c b/drivers/cpufreq/s3c24xx-cpufreq.c
index 27111fbca2ff..37efc0dc3f91 100644
--- a/drivers/cpufreq/s3c24xx-cpufreq.c
+++ b/drivers/cpufreq/s3c24xx-cpufreq.c
@@ -27,13 +27,7 @@
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 
-#include <mach/map.h>
-
 /* note, cpufreq support deals in kHz, no Hz */
-#define S3C2410_CLKREG(x) ((x) + S3C24XX_VA_CLKPWR)
-#define S3C2410_LOCKTIME    S3C2410_CLKREG(0x00)
-#define S3C2410_MPLLCON     S3C2410_CLKREG(0x04)
-
 static struct cpufreq_driver s3c24xx_driver;
 static struct s3c_cpufreq_config cpu_cur;
 static struct s3c_iotimings s3c24xx_iotiming;
@@ -70,7 +64,7 @@ static void s3c_cpufreq_getcur(struct s3c_cpufreq_config *cfg)
 	cfg->freq.pclk = pclk = clk_get_rate(clk_pclk);
 	cfg->freq.armclk = armclk = clk_get_rate(clk_arm);
 
-	cfg->pll.driver_data = __raw_readl(S3C2410_MPLLCON);
+	cfg->pll.driver_data = s3c24xx_read_mpllcon();
 	cfg->pll.frequency = fclk;
 
 	cfg->freq.hclk_tns = 1000000000 / (cfg->freq.hclk / 10);
@@ -388,7 +382,7 @@ static unsigned int suspend_freq;
 static int s3c_cpufreq_suspend(struct cpufreq_policy *policy)
 {
 	suspend_pll.frequency = clk_get_rate(_clk_mpll);
-	suspend_pll.driver_data = __raw_readl(S3C2410_MPLLCON);
+	suspend_pll.driver_data = s3c24xx_read_mpllcon();
 	suspend_freq = clk_get_rate(clk_arm);
 
 	return 0;
@@ -549,7 +543,7 @@ static void s3c_cpufreq_update_loctkime(void)
 	val |= calc_locktime(rate, cpu_cur.info->locktime_m);
 
 	pr_info("%s: new locktime is 0x%08x\n", __func__, val);
-	__raw_writel(val, S3C2410_LOCKTIME);
+	s3c24xx_write_locktime(val);
 }
 
 static int s3c_cpufreq_build_freq(void)
diff --git a/include/linux/soc/samsung/s3c-cpufreq-core.h b/include/linux/soc/samsung/s3c-cpufreq-core.h
index e0c7217a0f53..3b278afb769b 100644
--- a/include/linux/soc/samsung/s3c-cpufreq-core.h
+++ b/include/linux/soc/samsung/s3c-cpufreq-core.h
@@ -289,4 +289,11 @@ static inline int s3c_cpufreq_addfreq(struct cpufreq_frequency_table *table,
 	return index + 1;
 }
 
+u32 s3c2440_read_camdivn(void);
+void s3c2440_write_camdivn(u32 camdiv);
+u32 s3c24xx_read_clkdivn(void);
+void s3c24xx_write_clkdivn(u32 clkdiv);
+u32 s3c24xx_read_mpllcon(void);
+void s3c24xx_write_locktime(u32 locktime);
+
 #endif
-- 
cgit v1.2.3


From 8d5930dfb7edbf136f2d9900be34ca7af4ba38c1 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 10 Jul 2020 20:07:10 -0400
Subject: skb_copy_and_csum_bits(): don't bother with the last argument

it's always 0

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/net/ethernet/sun/sunvnet_common.c |  2 +-
 include/linux/skbuff.h                    |  2 +-
 net/core/skbuff.c                         | 11 ++++++-----
 net/ipv4/icmp.c                           |  2 +-
 net/ipv4/ip_output.c                      |  4 ++--
 net/ipv6/icmp.c                           |  4 ++--
 net/ipv6/ip6_output.c                     |  2 +-
 net/sunrpc/socklib.c                      |  2 +-
 8 files changed, 15 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/sun/sunvnet_common.c b/drivers/net/ethernet/sun/sunvnet_common.c
index 8dc6c9ff22e1..80fde5f06fce 100644
--- a/drivers/net/ethernet/sun/sunvnet_common.c
+++ b/drivers/net/ethernet/sun/sunvnet_common.c
@@ -1168,7 +1168,7 @@ static inline struct sk_buff *vnet_skb_shape(struct sk_buff *skb, int ncookies)
 			*(__sum16 *)(skb->data + offset) = 0;
 			csum = skb_copy_and_csum_bits(skb, start,
 						      nskb->data + start,
-						      skb->len - start, 0);
+						      skb->len - start);
 
 			/* add in the header checksums */
 			if (skb->protocol == htons(ETH_P_IP)) {
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 46881d902124..31a6d2fce071 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3535,7 +3535,7 @@ int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags);
 int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len);
 int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len);
 __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8 *to,
-			      int len, __wsum csum);
+			      int len);
 int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset,
 		    struct pipe_inode_info *pipe, unsigned int len,
 		    unsigned int flags);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 7e2e502ef519..6e806da2913e 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2723,19 +2723,20 @@ EXPORT_SYMBOL(skb_checksum);
 /* Both of above in one bottle. */
 
 __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset,
-				    u8 *to, int len, __wsum csum)
+				    u8 *to, int len)
 {
 	int start = skb_headlen(skb);
 	int i, copy = start - offset;
 	struct sk_buff *frag_iter;
 	int pos = 0;
+	__wsum csum = 0;
 
 	/* Copy header. */
 	if (copy > 0) {
 		if (copy > len)
 			copy = len;
 		csum = csum_partial_copy_nocheck(skb->data + offset, to,
-						 copy, csum);
+						 copy, 0);
 		if ((len -= copy) == 0)
 			return csum;
 		offset += copy;
@@ -2791,7 +2792,7 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset,
 				copy = len;
 			csum2 = skb_copy_and_csum_bits(frag_iter,
 						       offset - start,
-						       to, copy, 0);
+						       to, copy);
 			csum = csum_block_add(csum, csum2, pos);
 			if ((len -= copy) == 0)
 				return csum;
@@ -3011,7 +3012,7 @@ void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to)
 	csum = 0;
 	if (csstart != skb->len)
 		csum = skb_copy_and_csum_bits(skb, csstart, to + csstart,
-					      skb->len - csstart, 0);
+					      skb->len - csstart);
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		long csstuff = csstart + skb->csum_offset;
@@ -3932,7 +3933,7 @@ normal:
 					skb_copy_and_csum_bits(head_skb, offset,
 							       skb_put(nskb,
 								       len),
-							       len, 0);
+							       len);
 				SKB_GSO_CB(nskb)->csum_start =
 					skb_headroom(nskb) + doffset;
 			} else {
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index cf36f955bfe6..d15f78053ef4 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -352,7 +352,7 @@ static int icmp_glue_bits(void *from, char *to, int offset, int len, int odd,
 
 	csum = skb_copy_and_csum_bits(icmp_param->skb,
 				      icmp_param->offset + offset,
-				      to, len, 0);
+				      to, len);
 
 	skb->csum = csum_block_add(skb->csum, csum, odd);
 	if (icmp_pointers[icmp_param->data.icmph.type].error)
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 61f802d5350c..5bd059853376 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1126,7 +1126,7 @@ alloc_new_skb:
 			if (fraggap) {
 				skb->csum = skb_copy_and_csum_bits(
 					skb_prev, maxfraglen,
-					data + transhdrlen, fraggap, 0);
+					data + transhdrlen, fraggap);
 				skb_prev->csum = csum_sub(skb_prev->csum,
 							  skb->csum);
 				data += fraggap;
@@ -1411,7 +1411,7 @@ ssize_t	ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
 				skb->csum = skb_copy_and_csum_bits(skb_prev,
 								   maxfraglen,
 						    skb_transport_header(skb),
-								   fraggap, 0);
+								   fraggap);
 				skb_prev->csum = csum_sub(skb_prev->csum,
 							  skb->csum);
 				pskb_trim_unique(skb_prev, maxfraglen);
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index a4e4912ad607..83b251151b5c 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -314,10 +314,10 @@ static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, st
 {
 	struct icmpv6_msg *msg = (struct icmpv6_msg *) from;
 	struct sk_buff *org_skb = msg->skb;
-	__wsum csum = 0;
+	__wsum csum;
 
 	csum = skb_copy_and_csum_bits(org_skb, msg->offset + offset,
-				      to, len, csum);
+				      to, len);
 	skb->csum = csum_block_add(skb->csum, csum, odd);
 	if (!(msg->type & ICMPV6_INFOMSG_MASK))
 		nf_ct_attach(skb, org_skb);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index c78e67d7747f..2689498157d1 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1615,7 +1615,7 @@ alloc_new_skb:
 			if (fraggap) {
 				skb->csum = skb_copy_and_csum_bits(
 					skb_prev, maxfraglen,
-					data + transhdrlen, fraggap, 0);
+					data + transhdrlen, fraggap);
 				skb_prev->csum = csum_sub(skb_prev->csum,
 							  skb->csum);
 				data += fraggap;
diff --git a/net/sunrpc/socklib.c b/net/sunrpc/socklib.c
index 3fc8af8bb961..d52313af82bc 100644
--- a/net/sunrpc/socklib.c
+++ b/net/sunrpc/socklib.c
@@ -70,7 +70,7 @@ static size_t xdr_skb_read_and_csum_bits(struct xdr_skb_reader *desc, void *to,
 	if (len > desc->count)
 		len = desc->count;
 	pos = desc->offset;
-	csum2 = skb_copy_and_csum_bits(desc->skb, pos, to, len, 0);
+	csum2 = skb_copy_and_csum_bits(desc->skb, pos, to, len);
 	desc->csum = csum_block_add(desc->csum, csum2, pos);
 	desc->count -= len;
 	desc->offset += len;
-- 
cgit v1.2.3


From ba171d3f0850003216fd1a85190d17b1feddb961 Mon Sep 17 00:00:00 2001
From: Cedric Neveux <cedric.neveux@nxp.com>
Date: Mon, 4 Mar 2019 08:54:23 +0100
Subject: driver: tee: Handle NULL pointer indication from client

TEE Client introduce a new capability "TEE_GEN_CAP_MEMREF_NULL"
to handle the support of the shared memory buffer with a NULL pointer.

This capability depends on TEE Capabilities and driver support.
Driver and TEE exchange capabilities at driver initialization.

Signed-off-by: Michael Whitfield <michael.whitfield@nxp.com>
Signed-off-by: Cedric Neveux <cedric.neveux@nxp.com>
Reviewed-by: Joakim Bech <joakim.bech@linaro.org>
Tested-by: Joakim Bech <joakim.bech@linaro.org> (QEMU)
Signed-off-by: Jens Wiklander <jens.wiklander@linaro.org>
---
 drivers/tee/optee/core.c      |  7 +++++++
 drivers/tee/optee/optee_smc.h |  3 +++
 drivers/tee/tee_core.c        | 49 +++++++++++++++++++++++++++----------------
 include/linux/tee_drv.h       |  3 +++
 include/uapi/linux/tee.h      | 13 ++++++++++++
 5 files changed, 57 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tee/optee/core.c b/drivers/tee/optee/core.c
index b373b1b08b6d..cf4718c6d35d 100644
--- a/drivers/tee/optee/core.c
+++ b/drivers/tee/optee/core.c
@@ -216,6 +216,8 @@ static void optee_get_version(struct tee_device *teedev,
 
 	if (optee->sec_caps & OPTEE_SMC_SEC_CAP_DYNAMIC_SHM)
 		v.gen_caps |= TEE_GEN_CAP_REG_MEM;
+	if (optee->sec_caps & OPTEE_SMC_SEC_CAP_MEMREF_NULL)
+		v.gen_caps |= TEE_GEN_CAP_MEMREF_NULL;
 	*vers = v;
 }
 
@@ -262,6 +264,11 @@ static int optee_open(struct tee_context *ctx)
 	mutex_init(&ctxdata->mutex);
 	INIT_LIST_HEAD(&ctxdata->sess_list);
 
+	if (optee->sec_caps & OPTEE_SMC_SEC_CAP_MEMREF_NULL)
+		ctx->cap_memref_null  = true;
+	else
+		ctx->cap_memref_null = false;
+
 	ctx->data = ctxdata;
 	return 0;
 }
diff --git a/drivers/tee/optee/optee_smc.h b/drivers/tee/optee/optee_smc.h
index c72122d9c997..777ad54d4c2c 100644
--- a/drivers/tee/optee/optee_smc.h
+++ b/drivers/tee/optee/optee_smc.h
@@ -215,6 +215,9 @@ struct optee_smc_get_shm_config_result {
  */
 #define OPTEE_SMC_SEC_CAP_DYNAMIC_SHM		BIT(2)
 
+/* Secure world supports Shared Memory with a NULL buffer reference */
+#define OPTEE_SMC_SEC_CAP_MEMREF_NULL		BIT(4)
+
 #define OPTEE_SMC_FUNCID_EXCHANGE_CAPABILITIES	9
 #define OPTEE_SMC_EXCHANGE_CAPABILITIES \
 	OPTEE_SMC_FAST_CALL_VAL(OPTEE_SMC_FUNCID_EXCHANGE_CAPABILITIES)
diff --git a/drivers/tee/tee_core.c b/drivers/tee/tee_core.c
index 64637e09a095..ce0f0309b6ac 100644
--- a/drivers/tee/tee_core.c
+++ b/drivers/tee/tee_core.c
@@ -383,25 +383,38 @@ static int params_from_user(struct tee_context *ctx, struct tee_param *params,
 		case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT:
 		case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT:
 			/*
-			 * If we fail to get a pointer to a shared memory
-			 * object (and increase the ref count) from an
-			 * identifier we return an error. All pointers that
-			 * has been added in params have an increased ref
-			 * count. It's the callers responibility to do
-			 * tee_shm_put() on all resolved pointers.
+			 * If a NULL pointer is passed to a TA in the TEE,
+			 * the ip.c IOCTL parameters is set to TEE_MEMREF_NULL
+			 * indicating a NULL memory reference.
 			 */
-			shm = tee_shm_get_from_id(ctx, ip.c);
-			if (IS_ERR(shm))
-				return PTR_ERR(shm);
-
-			/*
-			 * Ensure offset + size does not overflow offset
-			 * and does not overflow the size of the referred
-			 * shared memory object.
-			 */
-			if ((ip.a + ip.b) < ip.a ||
-			    (ip.a + ip.b) > shm->size) {
-				tee_shm_put(shm);
+			if (ip.c != TEE_MEMREF_NULL) {
+				/*
+				 * If we fail to get a pointer to a shared
+				 * memory object (and increase the ref count)
+				 * from an identifier we return an error. All
+				 * pointers that has been added in params have
+				 * an increased ref count. It's the callers
+				 * responibility to do tee_shm_put() on all
+				 * resolved pointers.
+				 */
+				shm = tee_shm_get_from_id(ctx, ip.c);
+				if (IS_ERR(shm))
+					return PTR_ERR(shm);
+
+				/*
+				 * Ensure offset + size does not overflow
+				 * offset and does not overflow the size of
+				 * the referred shared memory object.
+				 */
+				if ((ip.a + ip.b) < ip.a ||
+				    (ip.a + ip.b) > shm->size) {
+					tee_shm_put(shm);
+					return -EINVAL;
+				}
+			} else if (ctx->cap_memref_null) {
+				/* Pass NULL pointer to OP-TEE */
+				shm = NULL;
+			} else {
 				return -EINVAL;
 			}
 
diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h
index d074302989dd..cdd049a724b1 100644
--- a/include/linux/tee_drv.h
+++ b/include/linux/tee_drv.h
@@ -47,6 +47,8 @@ struct tee_shm_pool;
  *              and just return with an error code. It is needed for requests
  *              that arises from TEE based kernel drivers that should be
  *              non-blocking in nature.
+ * @cap_memref_null: flag indicating if the TEE Client support shared
+ *                   memory buffer with a NULL pointer.
  */
 struct tee_context {
 	struct tee_device *teedev;
@@ -54,6 +56,7 @@ struct tee_context {
 	struct kref refcount;
 	bool releasing;
 	bool supp_nowait;
+	bool cap_memref_null;
 };
 
 struct tee_param_memref {
diff --git a/include/uapi/linux/tee.h b/include/uapi/linux/tee.h
index b619f37ee03e..d67cadf221fc 100644
--- a/include/uapi/linux/tee.h
+++ b/include/uapi/linux/tee.h
@@ -51,6 +51,9 @@
 #define TEE_GEN_CAP_GP		(1 << 0)/* GlobalPlatform compliant TEE */
 #define TEE_GEN_CAP_PRIVILEGED	(1 << 1)/* Privileged device (for supplicant) */
 #define TEE_GEN_CAP_REG_MEM	(1 << 2)/* Supports registering shared memory */
+#define TEE_GEN_CAP_MEMREF_NULL	(1 << 3)/* NULL MemRef support */
+
+#define TEE_MEMREF_NULL		(__u64)(-1) /* NULL MemRef Buffer */
 
 /*
  * TEE Implementation ID
@@ -200,6 +203,16 @@ struct tee_ioctl_buf_data {
  * a part of a shared memory by specifying an offset (@a) and size (@b) of
  * the object. To supply the entire shared memory object set the offset
  * (@a) to 0 and size (@b) to the previously returned size of the object.
+ *
+ * A client may need to present a NULL pointer in the argument
+ * passed to a trusted application in the TEE.
+ * This is also a requirement in GlobalPlatform Client API v1.0c
+ * (section 3.2.5 memory references), which can be found at
+ * http://www.globalplatform.org/specificationsdevice.asp
+ *
+ * If a NULL pointer is passed to a TA in the TEE, the (@c)
+ * IOCTL parameters value must be set to TEE_MEMREF_NULL indicating a NULL
+ * memory reference.
  */
 struct tee_ioctl_param {
 	__u64 attr;
-- 
cgit v1.2.3


From 6b0a249a301e2af9adda84adbced3a2988248b95 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Fri, 21 Aug 2020 11:44:18 -0700
Subject: bpf: Implement link_query for bpf iterators

This patch implemented bpf_link callback functions
show_fdinfo and fill_link_info to support link_query
interface.

The general interface for show_fdinfo and fill_link_info
will print/fill the target_name. Each targets can
register show_fdinfo and fill_link_info callbacks
to print/fill more target specific information.

For example, the below is a fdinfo result for a bpf
task iterator.
  $ cat /proc/1749/fdinfo/7
  pos:    0
  flags:  02000000
  mnt_id: 14
  link_type:      iter
  link_id:        11
  prog_tag:       990e1f8152f7e54f
  prog_id:        59
  target_name:    task

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200821184418.574122-1-yhs@fb.com
---
 include/linux/bpf.h            |  6 +++++
 include/uapi/linux/bpf.h       |  7 +++++
 kernel/bpf/bpf_iter.c          | 58 ++++++++++++++++++++++++++++++++++++++++++
 tools/include/uapi/linux/bpf.h |  7 +++++
 4 files changed, 78 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index a9b7185a6b37..529e9b183eeb 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1218,12 +1218,18 @@ typedef int (*bpf_iter_attach_target_t)(struct bpf_prog *prog,
 					union bpf_iter_link_info *linfo,
 					struct bpf_iter_aux_info *aux);
 typedef void (*bpf_iter_detach_target_t)(struct bpf_iter_aux_info *aux);
+typedef void (*bpf_iter_show_fdinfo_t) (const struct bpf_iter_aux_info *aux,
+					struct seq_file *seq);
+typedef int (*bpf_iter_fill_link_info_t)(const struct bpf_iter_aux_info *aux,
+					 struct bpf_link_info *info);
 
 #define BPF_ITER_CTX_ARG_MAX 2
 struct bpf_iter_reg {
 	const char *target;
 	bpf_iter_attach_target_t attach_target;
 	bpf_iter_detach_target_t detach_target;
+	bpf_iter_show_fdinfo_t show_fdinfo;
+	bpf_iter_fill_link_info_t fill_link_info;
 	u32 ctx_arg_info_size;
 	struct bpf_ctx_arg_aux ctx_arg_info[BPF_ITER_CTX_ARG_MAX];
 	const struct bpf_iter_seq_info *seq_info;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 0480f893facd..a1bbaff7a0af 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -4071,6 +4071,13 @@ struct bpf_link_info {
 			__u64 cgroup_id;
 			__u32 attach_type;
 		} cgroup;
+		struct {
+			__aligned_u64 target_name; /* in/out: target_name buffer ptr */
+			__u32 target_name_len;	   /* in/out: target_name buffer len */
+			union {
+				__u32 map_id;
+			} map;
+		} iter;
 		struct  {
 			__u32 netns_ino;
 			__u32 attach_type;
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index b6715964b685..aeec7e174188 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -377,10 +377,68 @@ out_unlock:
 	return ret;
 }
 
+static void bpf_iter_link_show_fdinfo(const struct bpf_link *link,
+				      struct seq_file *seq)
+{
+	struct bpf_iter_link *iter_link =
+		container_of(link, struct bpf_iter_link, link);
+	bpf_iter_show_fdinfo_t show_fdinfo;
+
+	seq_printf(seq,
+		   "target_name:\t%s\n",
+		   iter_link->tinfo->reg_info->target);
+
+	show_fdinfo = iter_link->tinfo->reg_info->show_fdinfo;
+	if (show_fdinfo)
+		show_fdinfo(&iter_link->aux, seq);
+}
+
+static int bpf_iter_link_fill_link_info(const struct bpf_link *link,
+					struct bpf_link_info *info)
+{
+	struct bpf_iter_link *iter_link =
+		container_of(link, struct bpf_iter_link, link);
+	char __user *ubuf = u64_to_user_ptr(info->iter.target_name);
+	bpf_iter_fill_link_info_t fill_link_info;
+	u32 ulen = info->iter.target_name_len;
+	const char *target_name;
+	u32 target_len;
+
+	if (!ulen ^ !ubuf)
+		return -EINVAL;
+
+	target_name = iter_link->tinfo->reg_info->target;
+	target_len =  strlen(target_name);
+	info->iter.target_name_len = target_len + 1;
+
+	if (ubuf) {
+		if (ulen >= target_len + 1) {
+			if (copy_to_user(ubuf, target_name, target_len + 1))
+				return -EFAULT;
+		} else {
+			char zero = '\0';
+
+			if (copy_to_user(ubuf, target_name, ulen - 1))
+				return -EFAULT;
+			if (put_user(zero, ubuf + ulen - 1))
+				return -EFAULT;
+			return -ENOSPC;
+		}
+	}
+
+	fill_link_info = iter_link->tinfo->reg_info->fill_link_info;
+	if (fill_link_info)
+		return fill_link_info(&iter_link->aux, info);
+
+	return 0;
+}
+
 static const struct bpf_link_ops bpf_iter_link_lops = {
 	.release = bpf_iter_link_release,
 	.dealloc = bpf_iter_link_dealloc,
 	.update_prog = bpf_iter_link_replace,
+	.show_fdinfo = bpf_iter_link_show_fdinfo,
+	.fill_link_info = bpf_iter_link_fill_link_info,
 };
 
 bool bpf_link_is_iter(struct bpf_link *link)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 0480f893facd..a1bbaff7a0af 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4071,6 +4071,13 @@ struct bpf_link_info {
 			__u64 cgroup_id;
 			__u32 attach_type;
 		} cgroup;
+		struct {
+			__aligned_u64 target_name; /* in/out: target_name buffer ptr */
+			__u32 target_name_len;	   /* in/out: target_name buffer len */
+			union {
+				__u32 map_id;
+			} map;
+		} iter;
 		struct  {
 			__u32 netns_ino;
 			__u32 attach_type;
-- 
cgit v1.2.3


From b76f22269028fb252727a696084c70494d80a52c Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Fri, 21 Aug 2020 11:44:19 -0700
Subject: bpf: Implement link_query callbacks in map element iterators

For bpf_map_elem and bpf_sk_local_storage bpf iterators,
additional map_id should be shown for fdinfo and
userspace query. For example, the following is for
a bpf_map_elem iterator.
  $ cat /proc/1753/fdinfo/9
  pos:    0
  flags:  02000000
  mnt_id: 14
  link_type:      iter
  link_id:        34
  prog_tag:       104be6d3fe45e6aa
  prog_id:        173
  target_name:    bpf_map_elem
  map_id: 127

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200821184419.574240-1-yhs@fb.com
---
 include/linux/bpf.h       |  4 ++++
 kernel/bpf/map_iter.c     | 15 +++++++++++++++
 net/core/bpf_sk_storage.c |  2 ++
 3 files changed, 21 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 529e9b183eeb..30c144af894a 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1256,6 +1256,10 @@ int bpf_iter_new_fd(struct bpf_link *link);
 bool bpf_link_is_iter(struct bpf_link *link);
 struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop);
 int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx);
+void bpf_iter_map_show_fdinfo(const struct bpf_iter_aux_info *aux,
+			      struct seq_file *seq);
+int bpf_iter_map_fill_link_info(const struct bpf_iter_aux_info *aux,
+				struct bpf_link_info *info);
 
 int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value);
 int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value);
diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c
index af86048e5afd..6a9542af4212 100644
--- a/kernel/bpf/map_iter.c
+++ b/kernel/bpf/map_iter.c
@@ -149,6 +149,19 @@ static void bpf_iter_detach_map(struct bpf_iter_aux_info *aux)
 	bpf_map_put_with_uref(aux->map);
 }
 
+void bpf_iter_map_show_fdinfo(const struct bpf_iter_aux_info *aux,
+			      struct seq_file *seq)
+{
+	seq_printf(seq, "map_id:\t%u\n", aux->map->id);
+}
+
+int bpf_iter_map_fill_link_info(const struct bpf_iter_aux_info *aux,
+				struct bpf_link_info *info)
+{
+	info->iter.map.map_id = aux->map->id;
+	return 0;
+}
+
 DEFINE_BPF_ITER_FUNC(bpf_map_elem, struct bpf_iter_meta *meta,
 		     struct bpf_map *map, void *key, void *value)
 
@@ -156,6 +169,8 @@ static const struct bpf_iter_reg bpf_map_elem_reg_info = {
 	.target			= "bpf_map_elem",
 	.attach_target		= bpf_iter_attach_map,
 	.detach_target		= bpf_iter_detach_map,
+	.show_fdinfo		= bpf_iter_map_show_fdinfo,
+	.fill_link_info		= bpf_iter_map_fill_link_info,
 	.ctx_arg_info_size	= 2,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__bpf_map_elem, key),
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index b988f48153a4..281200dc0a01 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -1437,6 +1437,8 @@ static struct bpf_iter_reg bpf_sk_storage_map_reg_info = {
 	.target			= "bpf_sk_storage_map",
 	.attach_target		= bpf_iter_attach_map,
 	.detach_target		= bpf_iter_detach_map,
+	.show_fdinfo		= bpf_iter_map_show_fdinfo,
+	.fill_link_info		= bpf_iter_map_fill_link_info,
 	.ctx_arg_info_size	= 2,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__bpf_sk_storage_map, sk),
-- 
cgit v1.2.3


From 7b219da43f94a3b4d5a8aa4cc52b75b34f0301ec Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@cloudflare.com>
Date: Fri, 21 Aug 2020 11:29:43 +0100
Subject: net: sk_msg: Simplify sk_psock initialization

Initializing psock->sk_proto and other saved callbacks is only
done in sk_psock_update_proto, after sk_psock_init has returned.
The logic for this is difficult to follow, and needlessly complex.

Instead, initialize psock->sk_proto whenever we allocate a new
psock. Additionally, assert the following invariants:

* The SK has no ULP: ULP does it's own finagling of sk->sk_prot
* sk_user_data is unused: we need it to store sk_psock

Protect our access to sk_user_data with sk_callback_lock, which
is what other users like reuseport arrays, etc. do.

The result is that an sk_psock is always fully initialized, and
that psock->sk_proto is always the "original" struct proto.
The latter allows us to use psock->sk_proto when initializing
IPv6 TCP / UDP callbacks for sockmap.

Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20200821102948.21918-2-lmb@cloudflare.com
---
 include/linux/skmsg.h | 17 -----------------
 net/core/skmsg.c      | 34 ++++++++++++++++++++++++++++------
 net/core/sock_map.c   | 14 ++++----------
 net/ipv4/tcp_bpf.c    | 13 +++++--------
 net/ipv4/udp_bpf.c    |  9 ++++-----
 5 files changed, 41 insertions(+), 46 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 1e9ed840b9fc..3119928fc103 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -340,23 +340,6 @@ static inline void sk_psock_update_proto(struct sock *sk,
 					 struct sk_psock *psock,
 					 struct proto *ops)
 {
-	/* Initialize saved callbacks and original proto only once, since this
-	 * function may be called multiple times for a psock, e.g. when
-	 * psock->progs.msg_parser is updated.
-	 *
-	 * Since we've not installed the new proto, psock is not yet in use and
-	 * we can initialize it without synchronization.
-	 */
-	if (!psock->sk_proto) {
-		struct proto *orig = READ_ONCE(sk->sk_prot);
-
-		psock->saved_unhash = orig->unhash;
-		psock->saved_close = orig->close;
-		psock->saved_write_space = sk->sk_write_space;
-
-		psock->sk_proto = orig;
-	}
-
 	/* Pairs with lockless read in sk_clone_lock() */
 	WRITE_ONCE(sk->sk_prot, ops);
 }
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 6a32a1fd34f8..1c81caf9630f 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -494,14 +494,34 @@ end:
 
 struct sk_psock *sk_psock_init(struct sock *sk, int node)
 {
-	struct sk_psock *psock = kzalloc_node(sizeof(*psock),
-					      GFP_ATOMIC | __GFP_NOWARN,
-					      node);
-	if (!psock)
-		return NULL;
+	struct sk_psock *psock;
+	struct proto *prot;
+
+	write_lock_bh(&sk->sk_callback_lock);
+
+	if (inet_csk_has_ulp(sk)) {
+		psock = ERR_PTR(-EINVAL);
+		goto out;
+	}
+
+	if (sk->sk_user_data) {
+		psock = ERR_PTR(-EBUSY);
+		goto out;
+	}
 
+	psock = kzalloc_node(sizeof(*psock), GFP_ATOMIC | __GFP_NOWARN, node);
+	if (!psock) {
+		psock = ERR_PTR(-ENOMEM);
+		goto out;
+	}
+
+	prot = READ_ONCE(sk->sk_prot);
 	psock->sk = sk;
-	psock->eval =  __SK_NONE;
+	psock->eval = __SK_NONE;
+	psock->sk_proto = prot;
+	psock->saved_unhash = prot->unhash;
+	psock->saved_close = prot->close;
+	psock->saved_write_space = sk->sk_write_space;
 
 	INIT_LIST_HEAD(&psock->link);
 	spin_lock_init(&psock->link_lock);
@@ -516,6 +536,8 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node)
 	rcu_assign_sk_user_data_nocopy(sk, psock);
 	sock_hold(sk);
 
+out:
+	write_unlock_bh(&sk->sk_callback_lock);
 	return psock;
 }
 EXPORT_SYMBOL_GPL(sk_psock_init);
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 119f52a99dc1..abe4bac40db9 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -184,8 +184,6 @@ static int sock_map_init_proto(struct sock *sk, struct sk_psock *psock)
 {
 	struct proto *prot;
 
-	sock_owned_by_me(sk);
-
 	switch (sk->sk_type) {
 	case SOCK_STREAM:
 		prot = tcp_bpf_get_proto(sk, psock);
@@ -272,8 +270,8 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs,
 		}
 	} else {
 		psock = sk_psock_init(sk, map->numa_node);
-		if (!psock) {
-			ret = -ENOMEM;
+		if (IS_ERR(psock)) {
+			ret = PTR_ERR(psock);
 			goto out_progs;
 		}
 	}
@@ -322,8 +320,8 @@ static int sock_map_link_no_progs(struct bpf_map *map, struct sock *sk)
 
 	if (!psock) {
 		psock = sk_psock_init(sk, map->numa_node);
-		if (!psock)
-			return -ENOMEM;
+		if (IS_ERR(psock))
+			return PTR_ERR(psock);
 	}
 
 	ret = sock_map_init_proto(sk, psock);
@@ -478,8 +476,6 @@ static int sock_map_update_common(struct bpf_map *map, u32 idx,
 		return -EINVAL;
 	if (unlikely(idx >= map->max_entries))
 		return -E2BIG;
-	if (inet_csk_has_ulp(sk))
-		return -EINVAL;
 
 	link = sk_psock_init_link();
 	if (!link)
@@ -855,8 +851,6 @@ static int sock_hash_update_common(struct bpf_map *map, void *key,
 	WARN_ON_ONCE(!rcu_read_lock_held());
 	if (unlikely(flags > BPF_EXIST))
 		return -EINVAL;
-	if (inet_csk_has_ulp(sk))
-		return -EINVAL;
 
 	link = sk_psock_init_link();
 	if (!link)
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 7aa68f4aae6c..37f4cb2bba5c 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -567,10 +567,9 @@ static void tcp_bpf_rebuild_protos(struct proto prot[TCP_BPF_NUM_CFGS],
 	prot[TCP_BPF_TX].sendpage		= tcp_bpf_sendpage;
 }
 
-static void tcp_bpf_check_v6_needs_rebuild(struct sock *sk, struct proto *ops)
+static void tcp_bpf_check_v6_needs_rebuild(struct proto *ops)
 {
-	if (sk->sk_family == AF_INET6 &&
-	    unlikely(ops != smp_load_acquire(&tcpv6_prot_saved))) {
+	if (unlikely(ops != smp_load_acquire(&tcpv6_prot_saved))) {
 		spin_lock_bh(&tcpv6_prot_lock);
 		if (likely(ops != tcpv6_prot_saved)) {
 			tcp_bpf_rebuild_protos(tcp_bpf_prots[TCP_BPF_IPV6], ops);
@@ -603,13 +602,11 @@ struct proto *tcp_bpf_get_proto(struct sock *sk, struct sk_psock *psock)
 	int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4;
 	int config = psock->progs.msg_parser   ? TCP_BPF_TX   : TCP_BPF_BASE;
 
-	if (!psock->sk_proto) {
-		struct proto *ops = READ_ONCE(sk->sk_prot);
-
-		if (tcp_bpf_assert_proto_ops(ops))
+	if (sk->sk_family == AF_INET6) {
+		if (tcp_bpf_assert_proto_ops(psock->sk_proto))
 			return ERR_PTR(-EINVAL);
 
-		tcp_bpf_check_v6_needs_rebuild(sk, ops);
+		tcp_bpf_check_v6_needs_rebuild(psock->sk_proto);
 	}
 
 	return &tcp_bpf_prots[family][config];
diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c
index eddd973e6575..7a94791efc1a 100644
--- a/net/ipv4/udp_bpf.c
+++ b/net/ipv4/udp_bpf.c
@@ -22,10 +22,9 @@ static void udp_bpf_rebuild_protos(struct proto *prot, const struct proto *base)
 	prot->close  = sock_map_close;
 }
 
-static void udp_bpf_check_v6_needs_rebuild(struct sock *sk, struct proto *ops)
+static void udp_bpf_check_v6_needs_rebuild(struct proto *ops)
 {
-	if (sk->sk_family == AF_INET6 &&
-	    unlikely(ops != smp_load_acquire(&udpv6_prot_saved))) {
+	if (unlikely(ops != smp_load_acquire(&udpv6_prot_saved))) {
 		spin_lock_bh(&udpv6_prot_lock);
 		if (likely(ops != udpv6_prot_saved)) {
 			udp_bpf_rebuild_protos(&udp_bpf_prots[UDP_BPF_IPV6], ops);
@@ -46,8 +45,8 @@ struct proto *udp_bpf_get_proto(struct sock *sk, struct sk_psock *psock)
 {
 	int family = sk->sk_family == AF_INET ? UDP_BPF_IPV4 : UDP_BPF_IPV6;
 
-	if (!psock->sk_proto)
-		udp_bpf_check_v6_needs_rebuild(sk, READ_ONCE(sk->sk_prot));
+	if (sk->sk_family == AF_INET6)
+		udp_bpf_check_v6_needs_rebuild(psock->sk_proto);
 
 	return &udp_bpf_prots[family];
 }
-- 
cgit v1.2.3


From 13b79d3ffbb8add9e2a6d604db2b49f241b97303 Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@cloudflare.com>
Date: Fri, 21 Aug 2020 11:29:45 +0100
Subject: bpf: sockmap: Call sock_map_update_elem directly

Don't go via map->ops to call sock_map_update_elem, since we know
what function to call in bpf_map_update_value. Since we currently
don't allow calling map_update_elem from BPF context, we can remove
ops->map_update_elem and rename the function to sock_map_update_elem_sys.

Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20200821102948.21918-4-lmb@cloudflare.com
---
 include/linux/bpf.h  | 7 +++++++
 kernel/bpf/syscall.c | 5 +++--
 net/core/sock_map.c  | 6 ++----
 3 files changed, 12 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 30c144af894a..81f38e2fda78 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1648,6 +1648,7 @@ int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog,
 			 struct bpf_prog *old, u32 which);
 int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog);
 int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype);
+int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags);
 void sock_map_unhash(struct sock *sk);
 void sock_map_close(struct sock *sk, long timeout);
 #else
@@ -1669,6 +1670,12 @@ static inline int sock_map_prog_detach(const union bpf_attr *attr,
 {
 	return -EOPNOTSUPP;
 }
+
+static inline int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value,
+					   u64 flags)
+{
+	return -EOPNOTSUPP;
+}
 #endif /* CONFIG_BPF_STREAM_PARSER */
 
 #if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 689d736b6904..b46e973faee9 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -157,10 +157,11 @@ static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key,
 	if (bpf_map_is_dev_bound(map)) {
 		return bpf_map_offload_update_elem(map, key, value, flags);
 	} else if (map->map_type == BPF_MAP_TYPE_CPUMAP ||
-		   map->map_type == BPF_MAP_TYPE_SOCKHASH ||
-		   map->map_type == BPF_MAP_TYPE_SOCKMAP ||
 		   map->map_type == BPF_MAP_TYPE_STRUCT_OPS) {
 		return map->ops->map_update_elem(map, key, value, flags);
+	} else if (map->map_type == BPF_MAP_TYPE_SOCKHASH ||
+		   map->map_type == BPF_MAP_TYPE_SOCKMAP) {
+		return sock_map_update_elem_sys(map, key, value, flags);
 	} else if (IS_FD_PROG_ARRAY(map)) {
 		return bpf_fd_array_map_update_elem(map, f.file, key, value,
 						    flags);
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 905e2dd765aa..48e83f93ee66 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -562,8 +562,8 @@ static bool sock_map_sk_state_allowed(const struct sock *sk)
 static int sock_hash_update_common(struct bpf_map *map, void *key,
 				   struct sock *sk, u64 flags);
 
-static int sock_map_update_elem(struct bpf_map *map, void *key,
-				void *value, u64 flags)
+int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value,
+			     u64 flags)
 {
 	struct socket *sock;
 	struct sock *sk;
@@ -687,7 +687,6 @@ const struct bpf_map_ops sock_map_ops = {
 	.map_free		= sock_map_free,
 	.map_get_next_key	= sock_map_get_next_key,
 	.map_lookup_elem_sys_only = sock_map_lookup_sys,
-	.map_update_elem	= sock_map_update_elem,
 	.map_delete_elem	= sock_map_delete_elem,
 	.map_lookup_elem	= sock_map_lookup,
 	.map_release_uref	= sock_map_release_progs,
@@ -1181,7 +1180,6 @@ const struct bpf_map_ops sock_hash_ops = {
 	.map_alloc		= sock_hash_alloc,
 	.map_free		= sock_hash_free,
 	.map_get_next_key	= sock_hash_get_next_key,
-	.map_update_elem	= sock_map_update_elem,
 	.map_delete_elem	= sock_hash_delete_elem,
 	.map_lookup_elem	= sock_hash_lookup,
 	.map_lookup_elem_sys_only = sock_hash_lookup_sys,
-- 
cgit v1.2.3


From 781cb90b0529b5bb84c63691fe42a7c26d197aec Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sat, 18 Jul 2020 17:30:40 -0700
Subject: platform_data: ad7793.h: drop a duplicated word

Drop the repeated word "and" in a comment.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Lars-Peter Clausen <lars@metafoo.de>
Cc: Jonathan Cameron <jic23@kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 include/linux/platform_data/ad7793.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/platform_data/ad7793.h b/include/linux/platform_data/ad7793.h
index 576c7f962c4e..7c697e58f02a 100644
--- a/include/linux/platform_data/ad7793.h
+++ b/include/linux/platform_data/ad7793.h
@@ -40,7 +40,7 @@ enum ad7793_bias_voltage {
  * enum ad7793_refsel - AD7793 reference voltage selection
  * @AD7793_REFSEL_REFIN1: External reference applied between REFIN1(+)
  *	and REFIN1(-).
- * @AD7793_REFSEL_REFIN2: External reference applied between REFIN2(+) and
+ * @AD7793_REFSEL_REFIN2: External reference applied between REFIN2(+)
  *	and REFIN1(-). Only valid for AD7795/AD7796.
  * @AD7793_REFSEL_INTERNAL: Internal 1.17 V reference.
  */
-- 
cgit v1.2.3


From e2d977c9f1abd1d199b412f8f83c1727808b794d Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 14 Aug 2020 12:19:35 +0200
Subject: timekeeping: Provide multi-timestamp accessor to NMI safe timekeeper

printk wants to store various timestamps (MONOTONIC, REALTIME, BOOTTIME) to
make correlation of dmesg from several systems easier.

Provide an interface to retrieve all three timestamps in one go.

There are some caveats:

1) Boot time and late sleep time injection

  Boot time is a racy access on 32bit systems if the sleep time injection
  happens late during resume and not in timekeeping_resume(). That could be
  avoided by expanding struct tk_read_base with boot offset for 32bit and
  adding more overhead to the update. As this is a hard to observe once per
  resume event which can be filtered with reasonable effort using the
  accurate mono/real timestamps, it's probably not worth the trouble.

  Aside of that it might be possible on 32 and 64 bit to observe the
  following when the sleep time injection happens late:

  CPU 0				         CPU 1
  timekeeping_resume()
  ktime_get_fast_timestamps()
    mono, real = __ktime_get_real_fast()
  					 inject_sleep_time()
  					   update boot offset
  	boot = mono + bootoffset;

  That means that boot time already has the sleep time adjustment, but
  real time does not. On the next readout both are in sync again.

  Preventing this for 64bit is not really feasible without destroying the
  careful cache layout of the timekeeper because the sequence count and
  struct tk_read_base would then need two cache lines instead of one.

2) Suspend/resume timestamps

   Access to the time keeper clock source is disabled accross the innermost
   steps of suspend/resume. The accessors still work, but the timestamps
   are frozen until time keeping is resumed which happens very early.

   For regular suspend/resume there is no observable difference vs. sched
   clock, but it might affect some of the nasty low level debug printks.

   OTOH, access to sched clock is not guaranteed accross suspend/resume on
   all systems either so it depends on the hardware in use.

   If that turns out to be a real problem then this could be mitigated by
   using sched clock in a similar way as during early boot. But it's not as
   trivial as on early boot because it needs some careful protection
   against the clock monotonic timestamp jumping backwards on resume.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Petr Mladek <pmladek@suse.com>
Link: https://lore.kernel.org/r/20200814115512.159981360@linutronix.de
---
 include/linux/timekeeping.h | 15 +++++++++
 kernel/time/timekeeping.c   | 76 ++++++++++++++++++++++++++++++++++++++-------
 2 files changed, 80 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index d5471d6fa778..7f7e4a3f4394 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -222,6 +222,18 @@ extern bool timekeeping_rtc_skipresume(void);
 
 extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta);
 
+/*
+ * struct ktime_timestanps - Simultaneous mono/boot/real timestamps
+ * @mono:	Monotonic timestamp
+ * @boot:	Boottime timestamp
+ * @real:	Realtime timestamp
+ */
+struct ktime_timestamps {
+	u64		mono;
+	u64		boot;
+	u64		real;
+};
+
 /**
  * struct system_time_snapshot - simultaneous raw/real time capture with
  *				 counter value
@@ -280,6 +292,9 @@ extern int get_device_system_crosststamp(
  */
 extern void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot);
 
+/* NMI safe mono/boot/realtime timestamps */
+extern void ktime_get_fast_timestamps(struct ktime_timestamps *snap);
+
 /*
  * Persistent clock related interfaces
  */
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 57d064d94cc2..ba7657685e22 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -530,29 +530,29 @@ u64 notrace ktime_get_boot_fast_ns(void)
 }
 EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns);
 
-
 /*
  * See comment for __ktime_get_fast_ns() vs. timestamp ordering
  */
-static __always_inline u64 __ktime_get_real_fast_ns(struct tk_fast *tkf)
+static __always_inline u64 __ktime_get_real_fast(struct tk_fast *tkf, u64 *mono)
 {
 	struct tk_read_base *tkr;
+	u64 basem, baser, delta;
 	unsigned int seq;
-	u64 now;
 
 	do {
 		seq = raw_read_seqcount_latch(&tkf->seq);
 		tkr = tkf->base + (seq & 0x01);
-		now = ktime_to_ns(tkr->base_real);
+		basem = ktime_to_ns(tkr->base);
+		baser = ktime_to_ns(tkr->base_real);
 
-		now += timekeeping_delta_to_ns(tkr,
-				clocksource_delta(
-					tk_clock_read(tkr),
-					tkr->cycle_last,
-					tkr->mask));
+		delta = timekeeping_delta_to_ns(tkr,
+				clocksource_delta(tk_clock_read(tkr),
+				tkr->cycle_last, tkr->mask));
 	} while (read_seqcount_retry(&tkf->seq, seq));
 
-	return now;
+	if (mono)
+		*mono = basem + delta;
+	return baser + delta;
 }
 
 /**
@@ -560,10 +560,64 @@ static __always_inline u64 __ktime_get_real_fast_ns(struct tk_fast *tkf)
  */
 u64 ktime_get_real_fast_ns(void)
 {
-	return __ktime_get_real_fast_ns(&tk_fast_mono);
+	return __ktime_get_real_fast(&tk_fast_mono, NULL);
 }
 EXPORT_SYMBOL_GPL(ktime_get_real_fast_ns);
 
+/**
+ * ktime_get_fast_timestamps: - NMI safe timestamps
+ * @snapshot:	Pointer to timestamp storage
+ *
+ * Stores clock monotonic, boottime and realtime timestamps.
+ *
+ * Boot time is a racy access on 32bit systems if the sleep time injection
+ * happens late during resume and not in timekeeping_resume(). That could
+ * be avoided by expanding struct tk_read_base with boot offset for 32bit
+ * and adding more overhead to the update. As this is a hard to observe
+ * once per resume event which can be filtered with reasonable effort using
+ * the accurate mono/real timestamps, it's probably not worth the trouble.
+ *
+ * Aside of that it might be possible on 32 and 64 bit to observe the
+ * following when the sleep time injection happens late:
+ *
+ * CPU 0				CPU 1
+ * timekeeping_resume()
+ * ktime_get_fast_timestamps()
+ *	mono, real = __ktime_get_real_fast()
+ *					inject_sleep_time()
+ *					   update boot offset
+ *	boot = mono + bootoffset;
+ *
+ * That means that boot time already has the sleep time adjustment, but
+ * real time does not. On the next readout both are in sync again.
+ *
+ * Preventing this for 64bit is not really feasible without destroying the
+ * careful cache layout of the timekeeper because the sequence count and
+ * struct tk_read_base would then need two cache lines instead of one.
+ *
+ * Access to the time keeper clock source is disabled accross the innermost
+ * steps of suspend/resume. The accessors still work, but the timestamps
+ * are frozen until time keeping is resumed which happens very early.
+ *
+ * For regular suspend/resume there is no observable difference vs. sched
+ * clock, but it might affect some of the nasty low level debug printks.
+ *
+ * OTOH, access to sched clock is not guaranteed accross suspend/resume on
+ * all systems either so it depends on the hardware in use.
+ *
+ * If that turns out to be a real problem then this could be mitigated by
+ * using sched clock in a similar way as during early boot. But it's not as
+ * trivial as on early boot because it needs some careful protection
+ * against the clock monotonic timestamp jumping backwards on resume.
+ */
+void ktime_get_fast_timestamps(struct ktime_timestamps *snapshot)
+{
+	struct timekeeper *tk = &tk_core.timekeeper;
+
+	snapshot->real = __ktime_get_real_fast(&tk_fast_mono, &snapshot->mono);
+	snapshot->boot = snapshot->mono + ktime_to_ns(data_race(tk->offs_boot));
+}
+
 /**
  * halt_fast_timekeeper - Prevent fast timekeeper from accessing clocksource.
  * @tk: Timekeeper to snapshot.
-- 
cgit v1.2.3


From 2152fbbd47c06c4f50ad265ec1b0c43673bee3e8 Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Fri, 3 Jul 2020 09:07:29 -0700
Subject: soc: ti: pm33xx: Simplify RTC usage to prepare to drop platform data

We must re-enable the RTC module clock enabled in RTC+DDR suspend, and
pm33xx has been using platform data callbacks for that. Looks like for
retention suspend the RTC module clock must not be re-enabled.

To remove the legacy platform data callbacks, and eventually be able to
drop the RTC legacy platform data, let's manage the RTC module clock
and register range directly in pm33xx.

Acked-by: Santosh Shilimkar <ssantosh@kernel.org>
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/mach-omap2/pm33xx-core.c    | 25 -------------------
 drivers/soc/ti/pm33xx.c              | 47 ++++++++++++++++++++++++++++++++----
 include/linux/platform_data/pm33xx.h |  3 ---
 3 files changed, 42 insertions(+), 33 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/mach-omap2/pm33xx-core.c b/arch/arm/mach-omap2/pm33xx-core.c
index 58236c7dc83e..87c347e97af8 100644
--- a/arch/arm/mach-omap2/pm33xx-core.c
+++ b/arch/arm/mach-omap2/pm33xx-core.c
@@ -25,7 +25,6 @@
 #include "control.h"
 #include "clockdomain.h"
 #include "iomap.h"
-#include "omap_hwmod.h"
 #include "pm.h"
 #include "powerdomain.h"
 #include "prm33xx.h"
@@ -36,7 +35,6 @@
 static struct powerdomain *cefuse_pwrdm, *gfx_pwrdm, *per_pwrdm, *mpu_pwrdm;
 static struct clockdomain *gfx_l4ls_clkdm;
 static void __iomem *scu_base;
-static struct omap_hwmod *rtc_oh;
 
 static int (*idle_fn)(u32 wfi_flags);
 
@@ -267,13 +265,6 @@ static struct am33xx_pm_sram_addr *amx3_get_sram_addrs(void)
 		return NULL;
 }
 
-static void __iomem *am43xx_get_rtc_base_addr(void)
-{
-	rtc_oh = omap_hwmod_lookup("rtc");
-
-	return omap_hwmod_get_mpu_rt_va(rtc_oh);
-}
-
 static void am43xx_save_context(void)
 {
 }
@@ -297,16 +288,6 @@ static void am43xx_restore_context(void)
 	writel_relaxed(0x0, AM33XX_L4_WK_IO_ADDRESS(0x44df2e14));
 }
 
-static void am43xx_prepare_rtc_suspend(void)
-{
-	omap_hwmod_enable(rtc_oh);
-}
-
-static void am43xx_prepare_rtc_resume(void)
-{
-	omap_hwmod_idle(rtc_oh);
-}
-
 static struct am33xx_pm_platform_data am33xx_ops = {
 	.init = am33xx_suspend_init,
 	.deinit = amx3_suspend_deinit,
@@ -317,10 +298,7 @@ static struct am33xx_pm_platform_data am33xx_ops = {
 	.get_sram_addrs = amx3_get_sram_addrs,
 	.save_context = am33xx_save_context,
 	.restore_context = am33xx_restore_context,
-	.prepare_rtc_suspend = am43xx_prepare_rtc_suspend,
-	.prepare_rtc_resume = am43xx_prepare_rtc_resume,
 	.check_off_mode_enable = am33xx_check_off_mode_enable,
-	.get_rtc_base_addr = am43xx_get_rtc_base_addr,
 };
 
 static struct am33xx_pm_platform_data am43xx_ops = {
@@ -333,10 +311,7 @@ static struct am33xx_pm_platform_data am43xx_ops = {
 	.get_sram_addrs = amx3_get_sram_addrs,
 	.save_context = am43xx_save_context,
 	.restore_context = am43xx_restore_context,
-	.prepare_rtc_suspend = am43xx_prepare_rtc_suspend,
-	.prepare_rtc_resume = am43xx_prepare_rtc_resume,
 	.check_off_mode_enable = am43xx_check_off_mode_enable,
-	.get_rtc_base_addr = am43xx_get_rtc_base_addr,
 };
 
 static struct am33xx_pm_platform_data *am33xx_pm_get_pdata(void)
diff --git a/drivers/soc/ti/pm33xx.c b/drivers/soc/ti/pm33xx.c
index de0123ec8ad6..d2f5e7001a93 100644
--- a/drivers/soc/ti/pm33xx.c
+++ b/drivers/soc/ti/pm33xx.c
@@ -16,6 +16,7 @@
 #include <linux/module.h>
 #include <linux/nvmem-consumer.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/platform_data/pm33xx.h>
 #include <linux/platform_device.h>
 #include <linux/rtc.h>
@@ -39,6 +40,8 @@
 #define GIC_INT_SET_PENDING_BASE 0x200
 #define AM43XX_GIC_DIST_BASE	0x48241000
 
+static void __iomem *rtc_base_virt;
+static struct clk *rtc_fck;
 static u32 rtc_magic_val;
 
 static int (*am33xx_do_wfi_sram)(unsigned long unused);
@@ -90,7 +93,7 @@ static int am33xx_push_sram_idle(void)
 	ro_sram_data.amx3_pm_sram_data_virt = ocmcram_location_data;
 	ro_sram_data.amx3_pm_sram_data_phys =
 		gen_pool_virt_to_phys(sram_pool_data, ocmcram_location_data);
-	ro_sram_data.rtc_base_virt = pm_ops->get_rtc_base_addr();
+	ro_sram_data.rtc_base_virt = rtc_base_virt;
 
 	/* Save physical address to calculate resume offset during pm init */
 	am33xx_do_wfi_sram_phys = gen_pool_virt_to_phys(sram_pool,
@@ -158,7 +161,7 @@ static struct wkup_m3_wakeup_src rtc_wake_src(void)
 {
 	u32 i;
 
-	i = __raw_readl(pm_ops->get_rtc_base_addr() + 0x44) & 0x40;
+	i = __raw_readl(rtc_base_virt + 0x44) & 0x40;
 
 	if (i) {
 		retrigger_irq = rtc_alarm_wakeup.irq_nr;
@@ -177,13 +180,24 @@ static int am33xx_rtc_only_idle(unsigned long wfi_flags)
 	return 0;
 }
 
+/*
+ * Note that the RTC module clock must be re-enabled only for rtc+ddr suspend.
+ * And looks like the module can stay in SYSC_IDLE_SMART_WKUP mode configured
+ * by the interconnect code just fine for both rtc+ddr suspend and retention
+ * suspend.
+ */
 static int am33xx_pm_suspend(suspend_state_t suspend_state)
 {
 	int i, ret = 0;
 
 	if (suspend_state == PM_SUSPEND_MEM &&
 	    pm_ops->check_off_mode_enable()) {
-		pm_ops->prepare_rtc_suspend();
+		ret = clk_prepare_enable(rtc_fck);
+		if (ret) {
+			dev_err(pm33xx_dev, "Failed to enable clock: %i\n", ret);
+			return ret;
+		}
+
 		pm_ops->save_context();
 		suspend_wfi_flags |= WFI_FLAG_RTC_ONLY;
 		clk_save_context();
@@ -236,7 +250,7 @@ static int am33xx_pm_suspend(suspend_state_t suspend_state)
 	}
 
 	if (suspend_state == PM_SUSPEND_MEM && pm_ops->check_off_mode_enable())
-		pm_ops->prepare_rtc_resume();
+		clk_disable_unprepare(rtc_fck);
 
 	return ret;
 }
@@ -425,14 +439,28 @@ static int am33xx_pm_rtc_setup(void)
 	struct device_node *np;
 	unsigned long val = 0;
 	struct nvmem_device *nvmem;
+	int error;
 
 	np = of_find_node_by_name(NULL, "rtc");
 
 	if (of_device_is_available(np)) {
+		/* RTC interconnect target module clock */
+		rtc_fck = of_clk_get_by_name(np->parent, "fck");
+		if (IS_ERR(rtc_fck))
+			return PTR_ERR(rtc_fck);
+
+		rtc_base_virt = of_iomap(np, 0);
+		if (!rtc_base_virt) {
+			pr_warn("PM: could not iomap rtc");
+			error = -ENODEV;
+			goto err_clk_put;
+		}
+
 		omap_rtc = rtc_class_open("rtc0");
 		if (!omap_rtc) {
 			pr_warn("PM: rtc0 not available");
-			return -EPROBE_DEFER;
+			error = -EPROBE_DEFER;
+			goto err_iounmap;
 		}
 
 		nvmem = devm_nvmem_device_get(&omap_rtc->dev,
@@ -454,6 +482,13 @@ static int am33xx_pm_rtc_setup(void)
 	}
 
 	return 0;
+
+err_iounmap:
+	iounmap(rtc_base_virt);
+err_clk_put:
+	clk_put(rtc_fck);
+
+	return error;
 }
 
 static int am33xx_pm_probe(struct platform_device *pdev)
@@ -544,6 +579,8 @@ static int am33xx_pm_remove(struct platform_device *pdev)
 	suspend_set_ops(NULL);
 	wkup_m3_ipc_put(m3_ipc);
 	am33xx_pm_free_sram();
+	iounmap(rtc_base_virt);
+	clk_put(rtc_fck);
 	return 0;
 }
 
diff --git a/include/linux/platform_data/pm33xx.h b/include/linux/platform_data/pm33xx.h
index 644af1d89cfa..7037ba7a53ca 100644
--- a/include/linux/platform_data/pm33xx.h
+++ b/include/linux/platform_data/pm33xx.h
@@ -54,11 +54,8 @@ struct am33xx_pm_platform_data {
 	void    (*begin_suspend)(void);
 	void    (*finish_suspend)(void);
 	struct  am33xx_pm_sram_addr *(*get_sram_addrs)(void);
-	void __iomem *(*get_rtc_base_addr)(void);
 	void (*save_context)(void);
 	void (*restore_context)(void);
-	void (*prepare_rtc_suspend)(void);
-	void (*prepare_rtc_resume)(void);
 	int (*check_off_mode_enable)(void);
 };
 
-- 
cgit v1.2.3


From 70a217f1976f75a6cfe8223e5669ad7b405daaad Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Thu, 20 Aug 2020 12:00:14 -0700
Subject: tcp: Use a struct to represent a saved_syn

The TCP_SAVE_SYN has both the network header and tcp header.
The total length of the saved syn packet is currently stored in
the first 4 bytes (u32) of an array and the actual packet data is
stored after that.

A later patch will add a bpf helper that allows to get the tcp header
alone from the saved syn without the network header.  It will be more
convenient to have a direct offset to a specific header instead of
re-parsing it.  This requires to separately store the network hdrlen.
The total header length (i.e. network + tcp) is still needed for the
current usage in getsockopt.  Although this total length can be obtained
by looking into the tcphdr and then get the (th->doff << 2), this patch
chooses to directly store the tcp hdrlen in the second four bytes of
this newly created "struct saved_syn".  By using a new struct, it can
give a readable name to each individual header length.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20200820190014.2883694-1-kafai@fb.com
---
 include/linux/tcp.h        |  7 ++++++-
 include/net/request_sock.h |  8 +++++++-
 net/core/filter.c          |  4 ++--
 net/ipv4/tcp.c             |  9 +++++----
 net/ipv4/tcp_input.c       | 16 +++++++++-------
 5 files changed, 29 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 14b62d7df942..2088d5a079af 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -406,7 +406,7 @@ struct tcp_sock {
 	 * socket. Used to retransmit SYNACKs etc.
 	 */
 	struct request_sock __rcu *fastopen_rsk;
-	u32	*saved_syn;
+	struct saved_syn *saved_syn;
 };
 
 enum tsq_enum {
@@ -484,6 +484,11 @@ static inline void tcp_saved_syn_free(struct tcp_sock *tp)
 	tp->saved_syn = NULL;
 }
 
+static inline u32 tcp_saved_syn_len(const struct saved_syn *saved_syn)
+{
+	return saved_syn->network_hdrlen + saved_syn->tcp_hdrlen;
+}
+
 struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk,
 					       const struct sk_buff *orig_skb);
 
diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index b2eb8b4ba697..7d9ed99a77bd 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -41,6 +41,12 @@ struct request_sock_ops {
 
 int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req);
 
+struct saved_syn {
+	u32 network_hdrlen;
+	u32 tcp_hdrlen;
+	u8 data[];
+};
+
 /* struct request_sock - mini sock to represent a connection request
  */
 struct request_sock {
@@ -60,7 +66,7 @@ struct request_sock {
 	struct timer_list		rsk_timer;
 	const struct request_sock_ops	*rsk_ops;
 	struct sock			*sk;
-	u32				*saved_syn;
+	struct saved_syn		*saved_syn;
 	u32				secid;
 	u32				peer_secid;
 };
diff --git a/net/core/filter.c b/net/core/filter.c
index b2df52086445..c847b1285acd 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4550,9 +4550,9 @@ static int _bpf_getsockopt(struct sock *sk, int level, int optname,
 			tp = tcp_sk(sk);
 
 			if (optlen <= 0 || !tp->saved_syn ||
-			    optlen > tp->saved_syn[0])
+			    optlen > tcp_saved_syn_len(tp->saved_syn))
 				goto err_clear;
-			memcpy(optval, tp->saved_syn + 1, optlen);
+			memcpy(optval, tp->saved_syn->data, optlen);
 			break;
 		default:
 			goto err_clear;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 31f3b858db81..87d3036d8bd8 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3788,20 +3788,21 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 
 		lock_sock(sk);
 		if (tp->saved_syn) {
-			if (len < tp->saved_syn[0]) {
-				if (put_user(tp->saved_syn[0], optlen)) {
+			if (len < tcp_saved_syn_len(tp->saved_syn)) {
+				if (put_user(tcp_saved_syn_len(tp->saved_syn),
+					     optlen)) {
 					release_sock(sk);
 					return -EFAULT;
 				}
 				release_sock(sk);
 				return -EINVAL;
 			}
-			len = tp->saved_syn[0];
+			len = tcp_saved_syn_len(tp->saved_syn);
 			if (put_user(len, optlen)) {
 				release_sock(sk);
 				return -EFAULT;
 			}
-			if (copy_to_user(optval, tp->saved_syn + 1, len)) {
+			if (copy_to_user(optval, tp->saved_syn->data, len)) {
 				release_sock(sk);
 				return -EFAULT;
 			}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 184ea556f50e..4aaedcf71973 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6599,13 +6599,15 @@ static void tcp_reqsk_record_syn(const struct sock *sk,
 {
 	if (tcp_sk(sk)->save_syn) {
 		u32 len = skb_network_header_len(skb) + tcp_hdrlen(skb);
-		u32 *copy;
-
-		copy = kmalloc(len + sizeof(u32), GFP_ATOMIC);
-		if (copy) {
-			copy[0] = len;
-			memcpy(&copy[1], skb_network_header(skb), len);
-			req->saved_syn = copy;
+		struct saved_syn *saved_syn;
+
+		saved_syn = kmalloc(struct_size(saved_syn, data, len),
+				    GFP_ATOMIC);
+		if (saved_syn) {
+			saved_syn->network_hdrlen = skb_network_header_len(skb);
+			saved_syn->tcp_hdrlen = tcp_hdrlen(skb);
+			memcpy(saved_syn->data, skb_network_header(skb), len);
+			req->saved_syn = saved_syn;
 		}
 	}
 }
-- 
cgit v1.2.3


From 7656d68455891f7fc6689f95415fd59e7a1d629b Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Thu, 20 Aug 2020 12:00:33 -0700
Subject: tcp: Add saw_unknown to struct tcp_options_received

In a later patch, the bpf prog only wants to be called to handle
a header option if that particular header option cannot be handled by
the kernel.  This unknown option could be written by the peer's bpf-prog.
It could also be a new standard option that the running kernel does not
support it while a bpf-prog can handle it.

This patch adds a "saw_unknown" bit to "struct tcp_options_received"
and it uses an existing one byte hole to do that.  "saw_unknown" will
be set in tcp_parse_options() if it sees an option that the kernel
cannot handle.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20200820190033.2884430-1-kafai@fb.com
---
 include/linux/tcp.h  |  2 ++
 net/ipv4/tcp_input.c | 22 ++++++++++++++++------
 2 files changed, 18 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 2088d5a079af..29d166263ae7 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -92,6 +92,8 @@ struct tcp_options_received {
 		smc_ok : 1,	/* SMC seen on SYN packet		*/
 		snd_wscale : 4,	/* Window scaling received from sender	*/
 		rcv_wscale : 4;	/* Window scaling to send to receiver	*/
+	u8	saw_unknown:1,	/* Received unknown option		*/
+		unused:7;
 	u8	num_sacks;	/* Number of SACK blocks		*/
 	u16	user_mss;	/* mss requested by user in ioctl	*/
 	u16	mss_clamp;	/* Maximal mss, negotiated at connection setup */
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 4aaedcf71973..9072d9160df9 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3801,7 +3801,7 @@ static void tcp_parse_fastopen_option(int len, const unsigned char *cookie,
 	foc->exp = exp_opt;
 }
 
-static void smc_parse_options(const struct tcphdr *th,
+static bool smc_parse_options(const struct tcphdr *th,
 			      struct tcp_options_received *opt_rx,
 			      const unsigned char *ptr,
 			      int opsize)
@@ -3810,10 +3810,13 @@ static void smc_parse_options(const struct tcphdr *th,
 	if (static_branch_unlikely(&tcp_have_smc)) {
 		if (th->syn && !(opsize & 1) &&
 		    opsize >= TCPOLEN_EXP_SMC_BASE &&
-		    get_unaligned_be32(ptr) == TCPOPT_SMC_MAGIC)
+		    get_unaligned_be32(ptr) == TCPOPT_SMC_MAGIC) {
 			opt_rx->smc_ok = 1;
+			return true;
+		}
 	}
 #endif
+	return false;
 }
 
 /* Try to parse the MSS option from the TCP header. Return 0 on failure, clamped
@@ -3874,6 +3877,7 @@ void tcp_parse_options(const struct net *net,
 
 	ptr = (const unsigned char *)(th + 1);
 	opt_rx->saw_tstamp = 0;
+	opt_rx->saw_unknown = 0;
 
 	while (length > 0) {
 		int opcode = *ptr++;
@@ -3964,15 +3968,21 @@ void tcp_parse_options(const struct net *net,
 				 */
 				if (opsize >= TCPOLEN_EXP_FASTOPEN_BASE &&
 				    get_unaligned_be16(ptr) ==
-				    TCPOPT_FASTOPEN_MAGIC)
+				    TCPOPT_FASTOPEN_MAGIC) {
 					tcp_parse_fastopen_option(opsize -
 						TCPOLEN_EXP_FASTOPEN_BASE,
 						ptr + 2, th->syn, foc, true);
-				else
-					smc_parse_options(th, opt_rx, ptr,
-							  opsize);
+					break;
+				}
+
+				if (smc_parse_options(th, opt_rx, ptr, opsize))
+					break;
+
+				opt_rx->saw_unknown = 1;
 				break;
 
+			default:
+				opt_rx->saw_unknown = 1;
 			}
 			ptr += opsize-2;
 			length -= opsize;
-- 
cgit v1.2.3


From c9985d09e18965131958102f4b67fa1e742df335 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Thu, 20 Aug 2020 12:00:58 -0700
Subject: bpf: sock_ops: Change some members of sock_ops_kern from u32 to u8

A later patch needs to add a few pointers and a few u8 to
sock_ops_kern.  Hence, this patch saves some spaces by moving
some of the existing members from u32 to u8 so that the later
patch can still fit everything in a cacheline.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200820190058.2885640-1-kafai@fb.com
---
 include/linux/filter.h |  4 ++--
 net/core/filter.c      | 15 ++++++++++-----
 2 files changed, 12 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 0a355b005bf4..c427dfa5f908 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1236,13 +1236,13 @@ struct bpf_sock_addr_kern {
 
 struct bpf_sock_ops_kern {
 	struct	sock *sk;
-	u32	op;
 	union {
 		u32 args[4];
 		u32 reply;
 		u32 replylong[4];
 	};
-	u32	is_fullsock;
+	u8	op;
+	u8	is_fullsock;
 	u64	temp;			/* temp and everything after is not
 					 * initialized to 0 before calling
 					 * the BPF program. New fields that
diff --git a/net/core/filter.c b/net/core/filter.c
index 075ab71b985c..1608f4b3987f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -8465,17 +8465,22 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
 		return insn - insn_buf;
 
 	switch (si->off) {
-	case offsetof(struct bpf_sock_ops, op) ...
+	case offsetof(struct bpf_sock_ops, op):
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern,
+						       op),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct bpf_sock_ops_kern, op));
+		break;
+
+	case offsetof(struct bpf_sock_ops, replylong[0]) ...
 	     offsetof(struct bpf_sock_ops, replylong[3]):
-		BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, op) !=
-			     sizeof_field(struct bpf_sock_ops_kern, op));
 		BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, reply) !=
 			     sizeof_field(struct bpf_sock_ops_kern, reply));
 		BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, replylong) !=
 			     sizeof_field(struct bpf_sock_ops_kern, replylong));
 		off = si->off;
-		off -= offsetof(struct bpf_sock_ops, op);
-		off += offsetof(struct bpf_sock_ops_kern, op);
+		off -= offsetof(struct bpf_sock_ops, replylong[0]);
+		off += offsetof(struct bpf_sock_ops_kern, replylong[0]);
 		if (type == BPF_WRITE)
 			*insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg,
 					      off);
-- 
cgit v1.2.3


From 0813a841566f0962a5551be7749b43c45f0022a0 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Thu, 20 Aug 2020 12:01:04 -0700
Subject: bpf: tcp: Allow bpf prog to write and parse TCP header option
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Note: The TCP changes here is mainly to implement the bpf
  pieces into the bpf_skops_*() functions introduced
  in the earlier patches. ]

The earlier effort in BPF-TCP-CC allows the TCP Congestion Control
algorithm to be written in BPF.  It opens up opportunities to allow
a faster turnaround time in testing/releasing new congestion control
ideas to production environment.

The same flexibility can be extended to writing TCP header option.
It is not uncommon that people want to test new TCP header option
to improve the TCP performance.  Another use case is for data-center
that has a more controlled environment and has more flexibility in
putting header options for internal only use.

For example, we want to test the idea in putting maximum delay
ACK in TCP header option which is similar to a draft RFC proposal [1].

This patch introduces the necessary BPF API and use them in the
TCP stack to allow BPF_PROG_TYPE_SOCK_OPS program to parse
and write TCP header options.  It currently supports most of
the TCP packet except RST.

Supported TCP header option:
───────────────────────────
This patch allows the bpf-prog to write any option kind.
Different bpf-progs can write its own option by calling the new helper
bpf_store_hdr_opt().  The helper will ensure there is no duplicated
option in the header.

By allowing bpf-prog to write any option kind, this gives a lot of
flexibility to the bpf-prog.  Different bpf-prog can write its
own option kind.  It could also allow the bpf-prog to support a
recently standardized option on an older kernel.

Sockops Callback Flags:
──────────────────────
The bpf program will only be called to parse/write tcp header option
if the following newly added callback flags are enabled
in tp->bpf_sock_ops_cb_flags:
BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG
BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG
BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG

A few words on the PARSE CB flags.  When the above PARSE CB flags are
turned on, the bpf-prog will be called on packets received
at a sk that has at least reached the ESTABLISHED state.
The parsing of the SYN-SYNACK-ACK will be discussed in the
"3 Way HandShake" section.

The default is off for all of the above new CB flags, i.e. the bpf prog
will not be called to parse or write bpf hdr option.  There are
details comment on these new cb flags in the UAPI bpf.h.

sock_ops->skb_data and bpf_load_hdr_opt()
─────────────────────────────────────────
sock_ops->skb_data and sock_ops->skb_data_end covers the whole
TCP header and its options.  They are read only.

The new bpf_load_hdr_opt() helps to read a particular option "kind"
from the skb_data.

Please refer to the comment in UAPI bpf.h.  It has details
on what skb_data contains under different sock_ops->op.

3 Way HandShake
───────────────
The bpf-prog can learn if it is sending SYN or SYNACK by reading the
sock_ops->skb_tcp_flags.

* Passive side

When writing SYNACK (i.e. sock_ops->op == BPF_SOCK_OPS_WRITE_HDR_OPT_CB),
the received SYN skb will be available to the bpf prog.  The bpf prog can
use the SYN skb (which may carry the header option sent from the remote bpf
prog) to decide what bpf header option should be written to the outgoing
SYNACK skb.  The SYN packet can be obtained by getsockopt(TCP_BPF_SYN*).
More on this later.  Also, the bpf prog can learn if it is in syncookie
mode (by checking sock_ops->args[0] == BPF_WRITE_HDR_TCP_SYNACK_COOKIE).

The bpf prog can store the received SYN pkt by using the existing
bpf_setsockopt(TCP_SAVE_SYN).  The example in a later patch does it.
[ Note that the fullsock here is a listen sk, bpf_sk_storage
  is not very useful here since the listen sk will be shared
  by many concurrent connection requests.

  Extending bpf_sk_storage support to request_sock will add weight
  to the minisock and it is not necessary better than storing the
  whole ~100 bytes SYN pkt. ]

When the connection is established, the bpf prog will be called
in the existing PASSIVE_ESTABLISHED_CB callback.  At that time,
the bpf prog can get the header option from the saved syn and
then apply the needed operation to the newly established socket.
The later patch will use the max delay ack specified in the SYN
header and set the RTO of this newly established connection
as an example.

The received ACK (that concludes the 3WHS) will also be available to
the bpf prog during PASSIVE_ESTABLISHED_CB through the sock_ops->skb_data.
It could be useful in syncookie scenario.  More on this later.

There is an existing getsockopt "TCP_SAVED_SYN" to return the whole
saved syn pkt which includes the IP[46] header and the TCP header.
A few "TCP_BPF_SYN*" getsockopt has been added to allow specifying where to
start getting from, e.g. starting from TCP header, or from IP[46] header.

The new getsockopt(TCP_BPF_SYN*) will also know where it can get
the SYN's packet from:
  - (a) the just received syn (available when the bpf prog is writing SYNACK)
        and it is the only way to get SYN during syncookie mode.
  or
  - (b) the saved syn (available in PASSIVE_ESTABLISHED_CB and also other
        existing CB).

The bpf prog does not need to know where the SYN pkt is coming from.
The getsockopt(TCP_BPF_SYN*) will hide this details.

Similarly, a flags "BPF_LOAD_HDR_OPT_TCP_SYN" is also added to
bpf_load_hdr_opt() to read a particular header option from the SYN packet.

* Fastopen

Fastopen should work the same as the regular non fastopen case.
This is a test in a later patch.

* Syncookie

For syncookie, the later example patch asks the active
side's bpf prog to resend the header options in ACK.  The server
can use bpf_load_hdr_opt() to look at the options in this
received ACK during PASSIVE_ESTABLISHED_CB.

* Active side

The bpf prog will get a chance to write the bpf header option
in the SYN packet during WRITE_HDR_OPT_CB.  The received SYNACK
pkt will also be available to the bpf prog during the existing
ACTIVE_ESTABLISHED_CB callback through the sock_ops->skb_data
and bpf_load_hdr_opt().

* Turn off header CB flags after 3WHS

If the bpf prog does not need to write/parse header options
beyond the 3WHS, the bpf prog can clear the bpf_sock_ops_cb_flags
to avoid being called for header options.
Or the bpf-prog can select to leave the UNKNOWN_HDR_OPT_CB_FLAG on
so that the kernel will only call it when there is option that
the kernel cannot handle.

[1]: draft-wang-tcpm-low-latency-opt-00
     https://tools.ietf.org/html/draft-wang-tcpm-low-latency-opt-00

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200820190104.2885895-1-kafai@fb.com
---
 include/linux/bpf-cgroup.h     |  25 +++
 include/linux/filter.h         |   4 +
 include/net/tcp.h              |  49 ++++++
 include/uapi/linux/bpf.h       | 300 ++++++++++++++++++++++++++++++++-
 net/core/filter.c              | 365 +++++++++++++++++++++++++++++++++++++++++
 net/ipv4/tcp_input.c           |  20 ++-
 net/ipv4/tcp_minisocks.c       |   1 +
 net/ipv4/tcp_output.c          | 104 +++++++++++-
 tools/include/uapi/linux/bpf.h | 300 ++++++++++++++++++++++++++++++++-
 9 files changed, 1150 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 64f367044e25..2f98d2fce62e 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -279,6 +279,31 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
 #define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr)			\
 	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_UDP6_RECVMSG, NULL)
 
+/* The SOCK_OPS"_SK" macro should be used when sock_ops->sk is not a
+ * fullsock and its parent fullsock cannot be traced by
+ * sk_to_full_sk().
+ *
+ * e.g. sock_ops->sk is a request_sock and it is under syncookie mode.
+ * Its listener-sk is not attached to the rsk_listener.
+ * In this case, the caller holds the listener-sk (unlocked),
+ * set its sock_ops->sk to req_sk, and call this SOCK_OPS"_SK" with
+ * the listener-sk such that the cgroup-bpf-progs of the
+ * listener-sk will be run.
+ *
+ * Regardless of syncookie mode or not,
+ * calling bpf_setsockopt on listener-sk will not make sense anyway,
+ * so passing 'sock_ops->sk == req_sk' to the bpf prog is appropriate here.
+ */
+#define BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(sock_ops, sk)			\
+({									\
+	int __ret = 0;							\
+	if (cgroup_bpf_enabled)						\
+		__ret = __cgroup_bpf_run_filter_sock_ops(sk,		\
+							 sock_ops,	\
+							 BPF_CGROUP_SOCK_OPS); \
+	__ret;								\
+})
+
 #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops)				       \
 ({									       \
 	int __ret = 0;							       \
diff --git a/include/linux/filter.h b/include/linux/filter.h
index c427dfa5f908..995625950cc1 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1241,8 +1241,12 @@ struct bpf_sock_ops_kern {
 		u32 reply;
 		u32 replylong[4];
 	};
+	struct sk_buff	*syn_skb;
+	struct sk_buff	*skb;
+	void	*skb_data_end;
 	u8	op;
 	u8	is_fullsock;
+	u8	remaining_opt_len;
 	u64	temp;			/* temp and everything after is not
 					 * initialized to 0 before calling
 					 * the BPF program. New fields that
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 3e768a6b8264..1f967b4e22f6 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2235,6 +2235,55 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock,
 		      struct msghdr *msg, int len, int flags);
 #endif /* CONFIG_NET_SOCK_MSG */
 
+#ifdef CONFIG_CGROUP_BPF
+/* Copy the listen sk's HDR_OPT_CB flags to its child.
+ *
+ * During 3-Way-HandShake, the synack is usually sent from
+ * the listen sk with the HDR_OPT_CB flags set so that
+ * bpf-prog will be called to write the BPF hdr option.
+ *
+ * In fastopen, the child sk is used to send synack instead
+ * of the listen sk.  Thus, inheriting the HDR_OPT_CB flags
+ * from the listen sk gives the bpf-prog a chance to write
+ * BPF hdr option in the synack pkt during fastopen.
+ *
+ * Both fastopen and non-fastopen child will inherit the
+ * HDR_OPT_CB flags to keep the bpf-prog having a consistent
+ * behavior when deciding to clear this cb flags (or not)
+ * during the PASSIVE_ESTABLISHED_CB.
+ *
+ * In the future, other cb flags could be inherited here also.
+ */
+static inline void bpf_skops_init_child(const struct sock *sk,
+					struct sock *child)
+{
+	tcp_sk(child)->bpf_sock_ops_cb_flags =
+		tcp_sk(sk)->bpf_sock_ops_cb_flags &
+		(BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG |
+		 BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG |
+		 BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG);
+}
+
+static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops,
+				      struct sk_buff *skb,
+				      unsigned int end_offset)
+{
+	skops->skb = skb;
+	skops->skb_data_end = skb->data + end_offset;
+}
+#else
+static inline void bpf_skops_init_child(const struct sock *sk,
+					struct sock *child)
+{
+}
+
+static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops,
+				      struct sk_buff *skb,
+				      unsigned int end_offset)
+{
+}
+#endif
+
 /* Call BPF_SOCK_OPS program that returns an int. If the return value
  * is < 0, then the BPF op failed (for example if the loaded BPF
  * program does not support the chosen operation or there is no BPF
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 18d0e128bc3c..f67ec5d9e57d 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3395,6 +3395,120 @@ union bpf_attr {
  *		A non-negative value equal to or less than *size* on success,
  *		or a negative error in case of failure.
  *
+ * long bpf_load_hdr_opt(struct bpf_sock_ops *skops, void *searchby_res, u32 len, u64 flags)
+ *	Description
+ *		Load header option.  Support reading a particular TCP header
+ *		option for bpf program (BPF_PROG_TYPE_SOCK_OPS).
+ *
+ *		If *flags* is 0, it will search the option from the
+ *		sock_ops->skb_data.  The comment in "struct bpf_sock_ops"
+ *		has details on what skb_data contains under different
+ *		sock_ops->op.
+ *
+ *		The first byte of the *searchby_res* specifies the
+ *		kind that it wants to search.
+ *
+ *		If the searching kind is an experimental kind
+ *		(i.e. 253 or 254 according to RFC6994).  It also
+ *		needs to specify the "magic" which is either
+ *		2 bytes or 4 bytes.  It then also needs to
+ *		specify the size of the magic by using
+ *		the 2nd byte which is "kind-length" of a TCP
+ *		header option and the "kind-length" also
+ *		includes the first 2 bytes "kind" and "kind-length"
+ *		itself as a normal TCP header option also does.
+ *
+ *		For example, to search experimental kind 254 with
+ *		2 byte magic 0xeB9F, the searchby_res should be
+ *		[ 254, 4, 0xeB, 0x9F, 0, 0, .... 0 ].
+ *
+ *		To search for the standard window scale option (3),
+ *		the searchby_res should be [ 3, 0, 0, .... 0 ].
+ *		Note, kind-length must be 0 for regular option.
+ *
+ *		Searching for No-Op (0) and End-of-Option-List (1) are
+ *		not supported.
+ *
+ *		*len* must be at least 2 bytes which is the minimal size
+ *		of a header option.
+ *
+ *		Supported flags:
+ *		* **BPF_LOAD_HDR_OPT_TCP_SYN** to search from the
+ *		  saved_syn packet or the just-received syn packet.
+ *
+ *	Return
+ *		>0 when found, the header option is copied to *searchby_res*.
+ *		The return value is the total length copied.
+ *
+ *		**-EINVAL** If param is invalid
+ *
+ *		**-ENOMSG** The option is not found
+ *
+ *		**-ENOENT** No syn packet available when
+ *			    **BPF_LOAD_HDR_OPT_TCP_SYN** is used
+ *
+ *		**-ENOSPC** Not enough space.  Only *len* number of
+ *			    bytes are copied.
+ *
+ *		**-EFAULT** Cannot parse the header options in the packet
+ *
+ *		**-EPERM** This helper cannot be used under the
+ *			   current sock_ops->op.
+ *
+ * long bpf_store_hdr_opt(struct bpf_sock_ops *skops, const void *from, u32 len, u64 flags)
+ *	Description
+ *		Store header option.  The data will be copied
+ *		from buffer *from* with length *len* to the TCP header.
+ *
+ *		The buffer *from* should have the whole option that
+ *		includes the kind, kind-length, and the actual
+ *		option data.  The *len* must be at least kind-length
+ *		long.  The kind-length does not have to be 4 byte
+ *		aligned.  The kernel will take care of the padding
+ *		and setting the 4 bytes aligned value to th->doff.
+ *
+ *		This helper will check for duplicated option
+ *		by searching the same option in the outgoing skb.
+ *
+ *		This helper can only be called during
+ *		BPF_SOCK_OPS_WRITE_HDR_OPT_CB.
+ *
+ *	Return
+ *		0 on success, or negative error in case of failure:
+ *
+ *		**-EINVAL** If param is invalid
+ *
+ *		**-ENOSPC** Not enough space in the header.
+ *			    Nothing has been written
+ *
+ *		**-EEXIST** The option has already existed
+ *
+ *		**-EFAULT** Cannot parse the existing header options
+ *
+ *		**-EPERM** This helper cannot be used under the
+ *			   current sock_ops->op.
+ *
+ * long bpf_reserve_hdr_opt(struct bpf_sock_ops *skops, u32 len, u64 flags)
+ *	Description
+ *		Reserve *len* bytes for the bpf header option.  The
+ *		space will be used by bpf_store_hdr_opt() later in
+ *		BPF_SOCK_OPS_WRITE_HDR_OPT_CB.
+ *
+ *		If bpf_reserve_hdr_opt() is called multiple times,
+ *		the total number of bytes will be reserved.
+ *
+ *		This helper can only be called during
+ *		BPF_SOCK_OPS_HDR_OPT_LEN_CB.
+ *
+ *	Return
+ *		0 on success, or negative error in case of failure:
+ *
+ *		**-EINVAL** if param is invalid
+ *
+ *		**-ENOSPC** Not enough space in the header.
+ *
+ *		**-EPERM** This helper cannot be used under the
+ *			   current sock_ops->op.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3539,6 +3653,9 @@ union bpf_attr {
 	FN(skc_to_tcp_request_sock),	\
 	FN(skc_to_udp6_sock),		\
 	FN(get_task_stack),		\
+	FN(load_hdr_opt),		\
+	FN(store_hdr_opt),		\
+	FN(reserve_hdr_opt),
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -4165,6 +4282,36 @@ struct bpf_sock_ops {
 	__u64 bytes_received;
 	__u64 bytes_acked;
 	__bpf_md_ptr(struct bpf_sock *, sk);
+	/* [skb_data, skb_data_end) covers the whole TCP header.
+	 *
+	 * BPF_SOCK_OPS_PARSE_HDR_OPT_CB: The packet received
+	 * BPF_SOCK_OPS_HDR_OPT_LEN_CB:   Not useful because the
+	 *                                header has not been written.
+	 * BPF_SOCK_OPS_WRITE_HDR_OPT_CB: The header and options have
+	 *				  been written so far.
+	 * BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:  The SYNACK that concludes
+	 *					the 3WHS.
+	 * BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: The ACK that concludes
+	 *					the 3WHS.
+	 *
+	 * bpf_load_hdr_opt() can also be used to read a particular option.
+	 */
+	__bpf_md_ptr(void *, skb_data);
+	__bpf_md_ptr(void *, skb_data_end);
+	__u32 skb_len;		/* The total length of a packet.
+				 * It includes the header, options,
+				 * and payload.
+				 */
+	__u32 skb_tcp_flags;	/* tcp_flags of the header.  It provides
+				 * an easy way to check for tcp_flags
+				 * without parsing skb_data.
+				 *
+				 * In particular, the skb_tcp_flags
+				 * will still be available in
+				 * BPF_SOCK_OPS_HDR_OPT_LEN even though
+				 * the outgoing header has not
+				 * been written yet.
+				 */
 };
 
 /* Definitions for bpf_sock_ops_cb_flags */
@@ -4173,8 +4320,48 @@ enum {
 	BPF_SOCK_OPS_RETRANS_CB_FLAG	= (1<<1),
 	BPF_SOCK_OPS_STATE_CB_FLAG	= (1<<2),
 	BPF_SOCK_OPS_RTT_CB_FLAG	= (1<<3),
-	BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG  = (1<<4),
+	/* Call bpf for all received TCP headers.  The bpf prog will be
+	 * called under sock_ops->op == BPF_SOCK_OPS_PARSE_HDR_OPT_CB
+	 *
+	 * Please refer to the comment in BPF_SOCK_OPS_PARSE_HDR_OPT_CB
+	 * for the header option related helpers that will be useful
+	 * to the bpf programs.
+	 *
+	 * It could be used at the client/active side (i.e. connect() side)
+	 * when the server told it that the server was in syncookie
+	 * mode and required the active side to resend the bpf-written
+	 * options.  The active side can keep writing the bpf-options until
+	 * it received a valid packet from the server side to confirm
+	 * the earlier packet (and options) has been received.  The later
+	 * example patch is using it like this at the active side when the
+	 * server is in syncookie mode.
+	 *
+	 * The bpf prog will usually turn this off in the common cases.
+	 */
+	BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG	= (1<<4),
+	/* Call bpf when kernel has received a header option that
+	 * the kernel cannot handle.  The bpf prog will be called under
+	 * sock_ops->op == BPF_SOCK_OPS_PARSE_HDR_OPT_CB.
+	 *
+	 * Please refer to the comment in BPF_SOCK_OPS_PARSE_HDR_OPT_CB
+	 * for the header option related helpers that will be useful
+	 * to the bpf programs.
+	 */
 	BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG = (1<<5),
+	/* Call bpf when the kernel is writing header options for the
+	 * outgoing packet.  The bpf prog will first be called
+	 * to reserve space in a skb under
+	 * sock_ops->op == BPF_SOCK_OPS_HDR_OPT_LEN_CB.  Then
+	 * the bpf prog will be called to write the header option(s)
+	 * under sock_ops->op == BPF_SOCK_OPS_WRITE_HDR_OPT_CB.
+	 *
+	 * Please refer to the comment in BPF_SOCK_OPS_HDR_OPT_LEN_CB
+	 * and BPF_SOCK_OPS_WRITE_HDR_OPT_CB for the header option
+	 * related helpers that will be useful to the bpf programs.
+	 *
+	 * The kernel gets its chance to reserve space and write
+	 * options first before the BPF program does.
+	 */
 	BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG = (1<<6),
 /* Mask of all currently supported cb flags */
 	BPF_SOCK_OPS_ALL_CB_FLAGS       = 0x7F,
@@ -4233,6 +4420,63 @@ enum {
 					 */
 	BPF_SOCK_OPS_RTT_CB,		/* Called on every RTT.
 					 */
+	BPF_SOCK_OPS_PARSE_HDR_OPT_CB,	/* Parse the header option.
+					 * It will be called to handle
+					 * the packets received at
+					 * an already established
+					 * connection.
+					 *
+					 * sock_ops->skb_data:
+					 * Referring to the received skb.
+					 * It covers the TCP header only.
+					 *
+					 * bpf_load_hdr_opt() can also
+					 * be used to search for a
+					 * particular option.
+					 */
+	BPF_SOCK_OPS_HDR_OPT_LEN_CB,	/* Reserve space for writing the
+					 * header option later in
+					 * BPF_SOCK_OPS_WRITE_HDR_OPT_CB.
+					 * Arg1: bool want_cookie. (in
+					 *       writing SYNACK only)
+					 *
+					 * sock_ops->skb_data:
+					 * Not available because no header has
+					 * been	written yet.
+					 *
+					 * sock_ops->skb_tcp_flags:
+					 * The tcp_flags of the
+					 * outgoing skb. (e.g. SYN, ACK, FIN).
+					 *
+					 * bpf_reserve_hdr_opt() should
+					 * be used to reserve space.
+					 */
+	BPF_SOCK_OPS_WRITE_HDR_OPT_CB,	/* Write the header options
+					 * Arg1: bool want_cookie. (in
+					 *       writing SYNACK only)
+					 *
+					 * sock_ops->skb_data:
+					 * Referring to the outgoing skb.
+					 * It covers the TCP header
+					 * that has already been written
+					 * by the kernel and the
+					 * earlier bpf-progs.
+					 *
+					 * sock_ops->skb_tcp_flags:
+					 * The tcp_flags of the outgoing
+					 * skb. (e.g. SYN, ACK, FIN).
+					 *
+					 * bpf_store_hdr_opt() should
+					 * be used to write the
+					 * option.
+					 *
+					 * bpf_load_hdr_opt() can also
+					 * be used to search for a
+					 * particular option that
+					 * has already been written
+					 * by the kernel or the
+					 * earlier bpf-progs.
+					 */
 };
 
 /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
@@ -4262,6 +4506,60 @@ enum {
 	TCP_BPF_SNDCWND_CLAMP	= 1002,	/* Set sndcwnd_clamp */
 	TCP_BPF_DELACK_MAX	= 1003, /* Max delay ack in usecs */
 	TCP_BPF_RTO_MIN		= 1004, /* Min delay ack in usecs */
+	/* Copy the SYN pkt to optval
+	 *
+	 * BPF_PROG_TYPE_SOCK_OPS only.  It is similar to the
+	 * bpf_getsockopt(TCP_SAVED_SYN) but it does not limit
+	 * to only getting from the saved_syn.  It can either get the
+	 * syn packet from:
+	 *
+	 * 1. the just-received SYN packet (only available when writing the
+	 *    SYNACK).  It will be useful when it is not necessary to
+	 *    save the SYN packet for latter use.  It is also the only way
+	 *    to get the SYN during syncookie mode because the syn
+	 *    packet cannot be saved during syncookie.
+	 *
+	 * OR
+	 *
+	 * 2. the earlier saved syn which was done by
+	 *    bpf_setsockopt(TCP_SAVE_SYN).
+	 *
+	 * The bpf_getsockopt(TCP_BPF_SYN*) option will hide where the
+	 * SYN packet is obtained.
+	 *
+	 * If the bpf-prog does not need the IP[46] header,  the
+	 * bpf-prog can avoid parsing the IP header by using
+	 * TCP_BPF_SYN.  Otherwise, the bpf-prog can get both
+	 * IP[46] and TCP header by using TCP_BPF_SYN_IP.
+	 *
+	 *      >0: Total number of bytes copied
+	 * -ENOSPC: Not enough space in optval. Only optlen number of
+	 *          bytes is copied.
+	 * -ENOENT: The SYN skb is not available now and the earlier SYN pkt
+	 *	    is not saved by setsockopt(TCP_SAVE_SYN).
+	 */
+	TCP_BPF_SYN		= 1005, /* Copy the TCP header */
+	TCP_BPF_SYN_IP		= 1006, /* Copy the IP[46] and TCP header */
+};
+
+enum {
+	BPF_LOAD_HDR_OPT_TCP_SYN = (1ULL << 0),
+};
+
+/* args[0] value during BPF_SOCK_OPS_HDR_OPT_LEN_CB and
+ * BPF_SOCK_OPS_WRITE_HDR_OPT_CB.
+ */
+enum {
+	BPF_WRITE_HDR_TCP_CURRENT_MSS = 1,	/* Kernel is finding the
+						 * total option spaces
+						 * required for an established
+						 * sk in order to calculate the
+						 * MSS.  No skb is actually
+						 * sent.
+						 */
+	BPF_WRITE_HDR_TCP_SYNACK_COOKIE = 2,	/* Kernel is in syncookie mode
+						 * when sending a SYN.
+						 */
 };
 
 struct bpf_perf_event_value {
diff --git a/net/core/filter.c b/net/core/filter.c
index 1608f4b3987f..ab5603d5b62a 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4669,9 +4669,82 @@ static const struct bpf_func_proto bpf_sock_ops_setsockopt_proto = {
 	.arg5_type	= ARG_CONST_SIZE,
 };
 
+static int bpf_sock_ops_get_syn(struct bpf_sock_ops_kern *bpf_sock,
+				int optname, const u8 **start)
+{
+	struct sk_buff *syn_skb = bpf_sock->syn_skb;
+	const u8 *hdr_start;
+	int ret;
+
+	if (syn_skb) {
+		/* sk is a request_sock here */
+
+		if (optname == TCP_BPF_SYN) {
+			hdr_start = syn_skb->data;
+			ret = tcp_hdrlen(syn_skb);
+		} else {
+			/* optname == TCP_BPF_SYN_IP */
+			hdr_start = skb_network_header(syn_skb);
+			ret = skb_network_header_len(syn_skb) +
+				tcp_hdrlen(syn_skb);
+		}
+	} else {
+		struct sock *sk = bpf_sock->sk;
+		struct saved_syn *saved_syn;
+
+		if (sk->sk_state == TCP_NEW_SYN_RECV)
+			/* synack retransmit. bpf_sock->syn_skb will
+			 * not be available.  It has to resort to
+			 * saved_syn (if it is saved).
+			 */
+			saved_syn = inet_reqsk(sk)->saved_syn;
+		else
+			saved_syn = tcp_sk(sk)->saved_syn;
+
+		if (!saved_syn)
+			return -ENOENT;
+
+		if (optname == TCP_BPF_SYN) {
+			hdr_start = saved_syn->data +
+				saved_syn->network_hdrlen;
+			ret = saved_syn->tcp_hdrlen;
+		} else {
+			/* optname == TCP_BPF_SYN_IP */
+			hdr_start = saved_syn->data;
+			ret = saved_syn->network_hdrlen +
+				saved_syn->tcp_hdrlen;
+		}
+	}
+
+	*start = hdr_start;
+	return ret;
+}
+
 BPF_CALL_5(bpf_sock_ops_getsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 	   int, level, int, optname, char *, optval, int, optlen)
 {
+	if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP &&
+	    optname >= TCP_BPF_SYN && optname <= TCP_BPF_SYN_IP) {
+		int ret, copy_len = 0;
+		const u8 *start;
+
+		ret = bpf_sock_ops_get_syn(bpf_sock, optname, &start);
+		if (ret > 0) {
+			copy_len = ret;
+			if (optlen < copy_len) {
+				copy_len = optlen;
+				ret = -ENOSPC;
+			}
+
+			memcpy(optval, start, copy_len);
+		}
+
+		/* Zero out unused buffer at the end */
+		memset(optval + copy_len, 0, optlen - copy_len);
+
+		return ret;
+	}
+
 	return _bpf_getsockopt(bpf_sock->sk, level, optname, optval, optlen);
 }
 
@@ -6165,6 +6238,232 @@ static const struct bpf_func_proto bpf_sk_assign_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
+static const u8 *bpf_search_tcp_opt(const u8 *op, const u8 *opend,
+				    u8 search_kind, const u8 *magic,
+				    u8 magic_len, bool *eol)
+{
+	u8 kind, kind_len;
+
+	*eol = false;
+
+	while (op < opend) {
+		kind = op[0];
+
+		if (kind == TCPOPT_EOL) {
+			*eol = true;
+			return ERR_PTR(-ENOMSG);
+		} else if (kind == TCPOPT_NOP) {
+			op++;
+			continue;
+		}
+
+		if (opend - op < 2 || opend - op < op[1] || op[1] < 2)
+			/* Something is wrong in the received header.
+			 * Follow the TCP stack's tcp_parse_options()
+			 * and just bail here.
+			 */
+			return ERR_PTR(-EFAULT);
+
+		kind_len = op[1];
+		if (search_kind == kind) {
+			if (!magic_len)
+				return op;
+
+			if (magic_len > kind_len - 2)
+				return ERR_PTR(-ENOMSG);
+
+			if (!memcmp(&op[2], magic, magic_len))
+				return op;
+		}
+
+		op += kind_len;
+	}
+
+	return ERR_PTR(-ENOMSG);
+}
+
+BPF_CALL_4(bpf_sock_ops_load_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock,
+	   void *, search_res, u32, len, u64, flags)
+{
+	bool eol, load_syn = flags & BPF_LOAD_HDR_OPT_TCP_SYN;
+	const u8 *op, *opend, *magic, *search = search_res;
+	u8 search_kind, search_len, copy_len, magic_len;
+	int ret;
+
+	/* 2 byte is the minimal option len except TCPOPT_NOP and
+	 * TCPOPT_EOL which are useless for the bpf prog to learn
+	 * and this helper disallow loading them also.
+	 */
+	if (len < 2 || flags & ~BPF_LOAD_HDR_OPT_TCP_SYN)
+		return -EINVAL;
+
+	search_kind = search[0];
+	search_len = search[1];
+
+	if (search_len > len || search_kind == TCPOPT_NOP ||
+	    search_kind == TCPOPT_EOL)
+		return -EINVAL;
+
+	if (search_kind == TCPOPT_EXP || search_kind == 253) {
+		/* 16 or 32 bit magic.  +2 for kind and kind length */
+		if (search_len != 4 && search_len != 6)
+			return -EINVAL;
+		magic = &search[2];
+		magic_len = search_len - 2;
+	} else {
+		if (search_len)
+			return -EINVAL;
+		magic = NULL;
+		magic_len = 0;
+	}
+
+	if (load_syn) {
+		ret = bpf_sock_ops_get_syn(bpf_sock, TCP_BPF_SYN, &op);
+		if (ret < 0)
+			return ret;
+
+		opend = op + ret;
+		op += sizeof(struct tcphdr);
+	} else {
+		if (!bpf_sock->skb ||
+		    bpf_sock->op == BPF_SOCK_OPS_HDR_OPT_LEN_CB)
+			/* This bpf_sock->op cannot call this helper */
+			return -EPERM;
+
+		opend = bpf_sock->skb_data_end;
+		op = bpf_sock->skb->data + sizeof(struct tcphdr);
+	}
+
+	op = bpf_search_tcp_opt(op, opend, search_kind, magic, magic_len,
+				&eol);
+	if (IS_ERR(op))
+		return PTR_ERR(op);
+
+	copy_len = op[1];
+	ret = copy_len;
+	if (copy_len > len) {
+		ret = -ENOSPC;
+		copy_len = len;
+	}
+
+	memcpy(search_res, op, copy_len);
+	return ret;
+}
+
+static const struct bpf_func_proto bpf_sock_ops_load_hdr_opt_proto = {
+	.func		= bpf_sock_ops_load_hdr_opt,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+	.arg4_type	= ARG_ANYTHING,
+};
+
+BPF_CALL_4(bpf_sock_ops_store_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock,
+	   const void *, from, u32, len, u64, flags)
+{
+	u8 new_kind, new_kind_len, magic_len = 0, *opend;
+	const u8 *op, *new_op, *magic = NULL;
+	struct sk_buff *skb;
+	bool eol;
+
+	if (bpf_sock->op != BPF_SOCK_OPS_WRITE_HDR_OPT_CB)
+		return -EPERM;
+
+	if (len < 2 || flags)
+		return -EINVAL;
+
+	new_op = from;
+	new_kind = new_op[0];
+	new_kind_len = new_op[1];
+
+	if (new_kind_len > len || new_kind == TCPOPT_NOP ||
+	    new_kind == TCPOPT_EOL)
+		return -EINVAL;
+
+	if (new_kind_len > bpf_sock->remaining_opt_len)
+		return -ENOSPC;
+
+	/* 253 is another experimental kind */
+	if (new_kind == TCPOPT_EXP || new_kind == 253)  {
+		if (new_kind_len < 4)
+			return -EINVAL;
+		/* Match for the 2 byte magic also.
+		 * RFC 6994: the magic could be 2 or 4 bytes.
+		 * Hence, matching by 2 byte only is on the
+		 * conservative side but it is the right
+		 * thing to do for the 'search-for-duplication'
+		 * purpose.
+		 */
+		magic = &new_op[2];
+		magic_len = 2;
+	}
+
+	/* Check for duplication */
+	skb = bpf_sock->skb;
+	op = skb->data + sizeof(struct tcphdr);
+	opend = bpf_sock->skb_data_end;
+
+	op = bpf_search_tcp_opt(op, opend, new_kind, magic, magic_len,
+				&eol);
+	if (!IS_ERR(op))
+		return -EEXIST;
+
+	if (PTR_ERR(op) != -ENOMSG)
+		return PTR_ERR(op);
+
+	if (eol)
+		/* The option has been ended.  Treat it as no more
+		 * header option can be written.
+		 */
+		return -ENOSPC;
+
+	/* No duplication found.  Store the header option. */
+	memcpy(opend, from, new_kind_len);
+
+	bpf_sock->remaining_opt_len -= new_kind_len;
+	bpf_sock->skb_data_end += new_kind_len;
+
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_sock_ops_store_hdr_opt_proto = {
+	.func		= bpf_sock_ops_store_hdr_opt,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+	.arg4_type	= ARG_ANYTHING,
+};
+
+BPF_CALL_3(bpf_sock_ops_reserve_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock,
+	   u32, len, u64, flags)
+{
+	if (bpf_sock->op != BPF_SOCK_OPS_HDR_OPT_LEN_CB)
+		return -EPERM;
+
+	if (flags || len < 2)
+		return -EINVAL;
+
+	if (len > bpf_sock->remaining_opt_len)
+		return -ENOSPC;
+
+	bpf_sock->remaining_opt_len -= len;
+
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_sock_ops_reserve_hdr_opt_proto = {
+	.func		= bpf_sock_ops_reserve_hdr_opt,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_ANYTHING,
+};
+
 #endif /* CONFIG_INET */
 
 bool bpf_helper_changes_pkt_data(void *func)
@@ -6193,6 +6492,9 @@ bool bpf_helper_changes_pkt_data(void *func)
 	    func == bpf_lwt_seg6_store_bytes ||
 	    func == bpf_lwt_seg6_adjust_srh ||
 	    func == bpf_lwt_seg6_action ||
+#endif
+#ifdef CONFIG_INET
+	    func == bpf_sock_ops_store_hdr_opt ||
 #endif
 	    func == bpf_lwt_in_push_encap ||
 	    func == bpf_lwt_xmit_push_encap)
@@ -6565,6 +6867,12 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_sk_storage_delete:
 		return &bpf_sk_storage_delete_proto;
 #ifdef CONFIG_INET
+	case BPF_FUNC_load_hdr_opt:
+		return &bpf_sock_ops_load_hdr_opt_proto;
+	case BPF_FUNC_store_hdr_opt:
+		return &bpf_sock_ops_store_hdr_opt_proto;
+	case BPF_FUNC_reserve_hdr_opt:
+		return &bpf_sock_ops_reserve_hdr_opt_proto;
 	case BPF_FUNC_tcp_sock:
 		return &bpf_tcp_sock_proto;
 #endif /* CONFIG_INET */
@@ -7364,6 +7672,20 @@ static bool sock_ops_is_valid_access(int off, int size,
 				return false;
 			info->reg_type = PTR_TO_SOCKET_OR_NULL;
 			break;
+		case offsetof(struct bpf_sock_ops, skb_data):
+			if (size != sizeof(__u64))
+				return false;
+			info->reg_type = PTR_TO_PACKET;
+			break;
+		case offsetof(struct bpf_sock_ops, skb_data_end):
+			if (size != sizeof(__u64))
+				return false;
+			info->reg_type = PTR_TO_PACKET_END;
+			break;
+		case offsetof(struct bpf_sock_ops, skb_tcp_flags):
+			bpf_ctx_record_field_size(info, size_default);
+			return bpf_ctx_narrow_access_ok(off, size,
+							size_default);
 		default:
 			if (size != size_default)
 				return false;
@@ -8701,6 +9023,49 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
 	case offsetof(struct bpf_sock_ops, sk):
 		SOCK_OPS_GET_SK();
 		break;
+	case offsetof(struct bpf_sock_ops, skb_data_end):
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern,
+						       skb_data_end),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct bpf_sock_ops_kern,
+					       skb_data_end));
+		break;
+	case offsetof(struct bpf_sock_ops, skb_data):
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern,
+						       skb),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct bpf_sock_ops_kern,
+					       skb));
+		*insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1);
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data),
+				      si->dst_reg, si->dst_reg,
+				      offsetof(struct sk_buff, data));
+		break;
+	case offsetof(struct bpf_sock_ops, skb_len):
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern,
+						       skb),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct bpf_sock_ops_kern,
+					       skb));
+		*insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1);
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, len),
+				      si->dst_reg, si->dst_reg,
+				      offsetof(struct sk_buff, len));
+		break;
+	case offsetof(struct bpf_sock_ops, skb_tcp_flags):
+		off = offsetof(struct sk_buff, cb);
+		off += offsetof(struct tcp_skb_cb, tcp_flags);
+		*target_size = sizeof_field(struct tcp_skb_cb, tcp_flags);
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern,
+						       skb),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct bpf_sock_ops_kern,
+					       skb));
+		*insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1);
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct tcp_skb_cb,
+						       tcp_flags),
+				      si->dst_reg, si->dst_reg, off);
+		break;
 	}
 	return insn - insn_buf;
 }
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 8c9da4b65dae..319cc7fd5117 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -146,6 +146,7 @@ static void bpf_skops_parse_hdr(struct sock *sk, struct sk_buff *skb)
 				       BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG);
 	bool parse_all_opt = BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk),
 						    BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG);
+	struct bpf_sock_ops_kern sock_ops;
 
 	if (likely(!unknown_opt && !parse_all_opt))
 		return;
@@ -161,12 +162,15 @@ static void bpf_skops_parse_hdr(struct sock *sk, struct sk_buff *skb)
 		return;
 	}
 
-	/* BPF prog will have access to the sk and skb.
-	 *
-	 * The bpf running context preparation and the actual bpf prog
-	 * calling will be implemented in a later PATCH together with
-	 * other bpf pieces.
-	 */
+	sock_owned_by_me(sk);
+
+	memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
+	sock_ops.op = BPF_SOCK_OPS_PARSE_HDR_OPT_CB;
+	sock_ops.is_fullsock = 1;
+	sock_ops.sk = sk;
+	bpf_skops_init_skb(&sock_ops, skb, tcp_hdrlen(skb));
+
+	BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops);
 }
 
 static void bpf_skops_established(struct sock *sk, int bpf_op,
@@ -180,7 +184,9 @@ static void bpf_skops_established(struct sock *sk, int bpf_op,
 	sock_ops.op = bpf_op;
 	sock_ops.is_fullsock = 1;
 	sock_ops.sk = sk;
-	/* skb will be passed to the bpf prog in a later patch. */
+	/* sk with TCP_REPAIR_ON does not have skb in tcp_finish_connect */
+	if (skb)
+		bpf_skops_init_skb(&sock_ops, skb, tcp_hdrlen(skb));
 
 	BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops);
 }
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 495dda2449fe..56c306e3cd2f 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -548,6 +548,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 	newtp->fastopen_req = NULL;
 	RCU_INIT_POINTER(newtp->fastopen_rsk, NULL);
 
+	bpf_skops_init_child(sk, newsk);
 	tcp_bpf_clone(sk, newsk);
 
 	__TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 673db6879e46..ab79d36ed07f 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -454,6 +454,18 @@ static void mptcp_options_write(__be32 *ptr, struct tcp_out_options *opts)
 }
 
 #ifdef CONFIG_CGROUP_BPF
+static int bpf_skops_write_hdr_opt_arg0(struct sk_buff *skb,
+					enum tcp_synack_type synack_type)
+{
+	if (unlikely(!skb))
+		return BPF_WRITE_HDR_TCP_CURRENT_MSS;
+
+	if (unlikely(synack_type == TCP_SYNACK_COOKIE))
+		return BPF_WRITE_HDR_TCP_SYNACK_COOKIE;
+
+	return 0;
+}
+
 /* req, syn_skb and synack_type are used when writing synack */
 static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb,
 				  struct request_sock *req,
@@ -462,15 +474,60 @@ static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb,
 				  struct tcp_out_options *opts,
 				  unsigned int *remaining)
 {
+	struct bpf_sock_ops_kern sock_ops;
+	int err;
+
 	if (likely(!BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk),
 					   BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG)) ||
 	    !*remaining)
 		return;
 
-	/* The bpf running context preparation and the actual bpf prog
-	 * calling will be implemented in a later PATCH together with
-	 * other bpf pieces.
-	 */
+	/* *remaining has already been aligned to 4 bytes, so *remaining >= 4 */
+
+	/* init sock_ops */
+	memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
+
+	sock_ops.op = BPF_SOCK_OPS_HDR_OPT_LEN_CB;
+
+	if (req) {
+		/* The listen "sk" cannot be passed here because
+		 * it is not locked.  It would not make too much
+		 * sense to do bpf_setsockopt(listen_sk) based
+		 * on individual connection request also.
+		 *
+		 * Thus, "req" is passed here and the cgroup-bpf-progs
+		 * of the listen "sk" will be run.
+		 *
+		 * "req" is also used here for fastopen even the "sk" here is
+		 * a fullsock "child" sk.  It is to keep the behavior
+		 * consistent between fastopen and non-fastopen on
+		 * the bpf programming side.
+		 */
+		sock_ops.sk = (struct sock *)req;
+		sock_ops.syn_skb = syn_skb;
+	} else {
+		sock_owned_by_me(sk);
+
+		sock_ops.is_fullsock = 1;
+		sock_ops.sk = sk;
+	}
+
+	sock_ops.args[0] = bpf_skops_write_hdr_opt_arg0(skb, synack_type);
+	sock_ops.remaining_opt_len = *remaining;
+	/* tcp_current_mss() does not pass a skb */
+	if (skb)
+		bpf_skops_init_skb(&sock_ops, skb, 0);
+
+	err = BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(&sock_ops, sk);
+
+	if (err || sock_ops.remaining_opt_len == *remaining)
+		return;
+
+	opts->bpf_opt_len = *remaining - sock_ops.remaining_opt_len;
+	/* round up to 4 bytes */
+	opts->bpf_opt_len = (opts->bpf_opt_len + 3) & ~3;
+
+	*remaining -= opts->bpf_opt_len;
 }
 
 static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb,
@@ -479,13 +536,42 @@ static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb,
 				    enum tcp_synack_type synack_type,
 				    struct tcp_out_options *opts)
 {
-	if (likely(!opts->bpf_opt_len))
+	u8 first_opt_off, nr_written, max_opt_len = opts->bpf_opt_len;
+	struct bpf_sock_ops_kern sock_ops;
+	int err;
+
+	if (likely(!max_opt_len))
 		return;
 
-	/* The bpf running context preparation and the actual bpf prog
-	 * calling will be implemented in a later PATCH together with
-	 * other bpf pieces.
-	 */
+	memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
+
+	sock_ops.op = BPF_SOCK_OPS_WRITE_HDR_OPT_CB;
+
+	if (req) {
+		sock_ops.sk = (struct sock *)req;
+		sock_ops.syn_skb = syn_skb;
+	} else {
+		sock_owned_by_me(sk);
+
+		sock_ops.is_fullsock = 1;
+		sock_ops.sk = sk;
+	}
+
+	sock_ops.args[0] = bpf_skops_write_hdr_opt_arg0(skb, synack_type);
+	sock_ops.remaining_opt_len = max_opt_len;
+	first_opt_off = tcp_hdrlen(skb) - max_opt_len;
+	bpf_skops_init_skb(&sock_ops, skb, first_opt_off);
+
+	err = BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(&sock_ops, sk);
+
+	if (err)
+		nr_written = 0;
+	else
+		nr_written = max_opt_len - sock_ops.remaining_opt_len;
+
+	if (nr_written < max_opt_len)
+		memset(skb->data + first_opt_off + nr_written, TCPOPT_NOP,
+		       max_opt_len - nr_written);
 }
 #else
 static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb,
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 18d0e128bc3c..f67ec5d9e57d 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3395,6 +3395,120 @@ union bpf_attr {
  *		A non-negative value equal to or less than *size* on success,
  *		or a negative error in case of failure.
  *
+ * long bpf_load_hdr_opt(struct bpf_sock_ops *skops, void *searchby_res, u32 len, u64 flags)
+ *	Description
+ *		Load header option.  Support reading a particular TCP header
+ *		option for bpf program (BPF_PROG_TYPE_SOCK_OPS).
+ *
+ *		If *flags* is 0, it will search the option from the
+ *		sock_ops->skb_data.  The comment in "struct bpf_sock_ops"
+ *		has details on what skb_data contains under different
+ *		sock_ops->op.
+ *
+ *		The first byte of the *searchby_res* specifies the
+ *		kind that it wants to search.
+ *
+ *		If the searching kind is an experimental kind
+ *		(i.e. 253 or 254 according to RFC6994).  It also
+ *		needs to specify the "magic" which is either
+ *		2 bytes or 4 bytes.  It then also needs to
+ *		specify the size of the magic by using
+ *		the 2nd byte which is "kind-length" of a TCP
+ *		header option and the "kind-length" also
+ *		includes the first 2 bytes "kind" and "kind-length"
+ *		itself as a normal TCP header option also does.
+ *
+ *		For example, to search experimental kind 254 with
+ *		2 byte magic 0xeB9F, the searchby_res should be
+ *		[ 254, 4, 0xeB, 0x9F, 0, 0, .... 0 ].
+ *
+ *		To search for the standard window scale option (3),
+ *		the searchby_res should be [ 3, 0, 0, .... 0 ].
+ *		Note, kind-length must be 0 for regular option.
+ *
+ *		Searching for No-Op (0) and End-of-Option-List (1) are
+ *		not supported.
+ *
+ *		*len* must be at least 2 bytes which is the minimal size
+ *		of a header option.
+ *
+ *		Supported flags:
+ *		* **BPF_LOAD_HDR_OPT_TCP_SYN** to search from the
+ *		  saved_syn packet or the just-received syn packet.
+ *
+ *	Return
+ *		>0 when found, the header option is copied to *searchby_res*.
+ *		The return value is the total length copied.
+ *
+ *		**-EINVAL** If param is invalid
+ *
+ *		**-ENOMSG** The option is not found
+ *
+ *		**-ENOENT** No syn packet available when
+ *			    **BPF_LOAD_HDR_OPT_TCP_SYN** is used
+ *
+ *		**-ENOSPC** Not enough space.  Only *len* number of
+ *			    bytes are copied.
+ *
+ *		**-EFAULT** Cannot parse the header options in the packet
+ *
+ *		**-EPERM** This helper cannot be used under the
+ *			   current sock_ops->op.
+ *
+ * long bpf_store_hdr_opt(struct bpf_sock_ops *skops, const void *from, u32 len, u64 flags)
+ *	Description
+ *		Store header option.  The data will be copied
+ *		from buffer *from* with length *len* to the TCP header.
+ *
+ *		The buffer *from* should have the whole option that
+ *		includes the kind, kind-length, and the actual
+ *		option data.  The *len* must be at least kind-length
+ *		long.  The kind-length does not have to be 4 byte
+ *		aligned.  The kernel will take care of the padding
+ *		and setting the 4 bytes aligned value to th->doff.
+ *
+ *		This helper will check for duplicated option
+ *		by searching the same option in the outgoing skb.
+ *
+ *		This helper can only be called during
+ *		BPF_SOCK_OPS_WRITE_HDR_OPT_CB.
+ *
+ *	Return
+ *		0 on success, or negative error in case of failure:
+ *
+ *		**-EINVAL** If param is invalid
+ *
+ *		**-ENOSPC** Not enough space in the header.
+ *			    Nothing has been written
+ *
+ *		**-EEXIST** The option has already existed
+ *
+ *		**-EFAULT** Cannot parse the existing header options
+ *
+ *		**-EPERM** This helper cannot be used under the
+ *			   current sock_ops->op.
+ *
+ * long bpf_reserve_hdr_opt(struct bpf_sock_ops *skops, u32 len, u64 flags)
+ *	Description
+ *		Reserve *len* bytes for the bpf header option.  The
+ *		space will be used by bpf_store_hdr_opt() later in
+ *		BPF_SOCK_OPS_WRITE_HDR_OPT_CB.
+ *
+ *		If bpf_reserve_hdr_opt() is called multiple times,
+ *		the total number of bytes will be reserved.
+ *
+ *		This helper can only be called during
+ *		BPF_SOCK_OPS_HDR_OPT_LEN_CB.
+ *
+ *	Return
+ *		0 on success, or negative error in case of failure:
+ *
+ *		**-EINVAL** if param is invalid
+ *
+ *		**-ENOSPC** Not enough space in the header.
+ *
+ *		**-EPERM** This helper cannot be used under the
+ *			   current sock_ops->op.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3539,6 +3653,9 @@ union bpf_attr {
 	FN(skc_to_tcp_request_sock),	\
 	FN(skc_to_udp6_sock),		\
 	FN(get_task_stack),		\
+	FN(load_hdr_opt),		\
+	FN(store_hdr_opt),		\
+	FN(reserve_hdr_opt),
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -4165,6 +4282,36 @@ struct bpf_sock_ops {
 	__u64 bytes_received;
 	__u64 bytes_acked;
 	__bpf_md_ptr(struct bpf_sock *, sk);
+	/* [skb_data, skb_data_end) covers the whole TCP header.
+	 *
+	 * BPF_SOCK_OPS_PARSE_HDR_OPT_CB: The packet received
+	 * BPF_SOCK_OPS_HDR_OPT_LEN_CB:   Not useful because the
+	 *                                header has not been written.
+	 * BPF_SOCK_OPS_WRITE_HDR_OPT_CB: The header and options have
+	 *				  been written so far.
+	 * BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:  The SYNACK that concludes
+	 *					the 3WHS.
+	 * BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: The ACK that concludes
+	 *					the 3WHS.
+	 *
+	 * bpf_load_hdr_opt() can also be used to read a particular option.
+	 */
+	__bpf_md_ptr(void *, skb_data);
+	__bpf_md_ptr(void *, skb_data_end);
+	__u32 skb_len;		/* The total length of a packet.
+				 * It includes the header, options,
+				 * and payload.
+				 */
+	__u32 skb_tcp_flags;	/* tcp_flags of the header.  It provides
+				 * an easy way to check for tcp_flags
+				 * without parsing skb_data.
+				 *
+				 * In particular, the skb_tcp_flags
+				 * will still be available in
+				 * BPF_SOCK_OPS_HDR_OPT_LEN even though
+				 * the outgoing header has not
+				 * been written yet.
+				 */
 };
 
 /* Definitions for bpf_sock_ops_cb_flags */
@@ -4173,8 +4320,48 @@ enum {
 	BPF_SOCK_OPS_RETRANS_CB_FLAG	= (1<<1),
 	BPF_SOCK_OPS_STATE_CB_FLAG	= (1<<2),
 	BPF_SOCK_OPS_RTT_CB_FLAG	= (1<<3),
-	BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG  = (1<<4),
+	/* Call bpf for all received TCP headers.  The bpf prog will be
+	 * called under sock_ops->op == BPF_SOCK_OPS_PARSE_HDR_OPT_CB
+	 *
+	 * Please refer to the comment in BPF_SOCK_OPS_PARSE_HDR_OPT_CB
+	 * for the header option related helpers that will be useful
+	 * to the bpf programs.
+	 *
+	 * It could be used at the client/active side (i.e. connect() side)
+	 * when the server told it that the server was in syncookie
+	 * mode and required the active side to resend the bpf-written
+	 * options.  The active side can keep writing the bpf-options until
+	 * it received a valid packet from the server side to confirm
+	 * the earlier packet (and options) has been received.  The later
+	 * example patch is using it like this at the active side when the
+	 * server is in syncookie mode.
+	 *
+	 * The bpf prog will usually turn this off in the common cases.
+	 */
+	BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG	= (1<<4),
+	/* Call bpf when kernel has received a header option that
+	 * the kernel cannot handle.  The bpf prog will be called under
+	 * sock_ops->op == BPF_SOCK_OPS_PARSE_HDR_OPT_CB.
+	 *
+	 * Please refer to the comment in BPF_SOCK_OPS_PARSE_HDR_OPT_CB
+	 * for the header option related helpers that will be useful
+	 * to the bpf programs.
+	 */
 	BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG = (1<<5),
+	/* Call bpf when the kernel is writing header options for the
+	 * outgoing packet.  The bpf prog will first be called
+	 * to reserve space in a skb under
+	 * sock_ops->op == BPF_SOCK_OPS_HDR_OPT_LEN_CB.  Then
+	 * the bpf prog will be called to write the header option(s)
+	 * under sock_ops->op == BPF_SOCK_OPS_WRITE_HDR_OPT_CB.
+	 *
+	 * Please refer to the comment in BPF_SOCK_OPS_HDR_OPT_LEN_CB
+	 * and BPF_SOCK_OPS_WRITE_HDR_OPT_CB for the header option
+	 * related helpers that will be useful to the bpf programs.
+	 *
+	 * The kernel gets its chance to reserve space and write
+	 * options first before the BPF program does.
+	 */
 	BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG = (1<<6),
 /* Mask of all currently supported cb flags */
 	BPF_SOCK_OPS_ALL_CB_FLAGS       = 0x7F,
@@ -4233,6 +4420,63 @@ enum {
 					 */
 	BPF_SOCK_OPS_RTT_CB,		/* Called on every RTT.
 					 */
+	BPF_SOCK_OPS_PARSE_HDR_OPT_CB,	/* Parse the header option.
+					 * It will be called to handle
+					 * the packets received at
+					 * an already established
+					 * connection.
+					 *
+					 * sock_ops->skb_data:
+					 * Referring to the received skb.
+					 * It covers the TCP header only.
+					 *
+					 * bpf_load_hdr_opt() can also
+					 * be used to search for a
+					 * particular option.
+					 */
+	BPF_SOCK_OPS_HDR_OPT_LEN_CB,	/* Reserve space for writing the
+					 * header option later in
+					 * BPF_SOCK_OPS_WRITE_HDR_OPT_CB.
+					 * Arg1: bool want_cookie. (in
+					 *       writing SYNACK only)
+					 *
+					 * sock_ops->skb_data:
+					 * Not available because no header has
+					 * been	written yet.
+					 *
+					 * sock_ops->skb_tcp_flags:
+					 * The tcp_flags of the
+					 * outgoing skb. (e.g. SYN, ACK, FIN).
+					 *
+					 * bpf_reserve_hdr_opt() should
+					 * be used to reserve space.
+					 */
+	BPF_SOCK_OPS_WRITE_HDR_OPT_CB,	/* Write the header options
+					 * Arg1: bool want_cookie. (in
+					 *       writing SYNACK only)
+					 *
+					 * sock_ops->skb_data:
+					 * Referring to the outgoing skb.
+					 * It covers the TCP header
+					 * that has already been written
+					 * by the kernel and the
+					 * earlier bpf-progs.
+					 *
+					 * sock_ops->skb_tcp_flags:
+					 * The tcp_flags of the outgoing
+					 * skb. (e.g. SYN, ACK, FIN).
+					 *
+					 * bpf_store_hdr_opt() should
+					 * be used to write the
+					 * option.
+					 *
+					 * bpf_load_hdr_opt() can also
+					 * be used to search for a
+					 * particular option that
+					 * has already been written
+					 * by the kernel or the
+					 * earlier bpf-progs.
+					 */
 };
 
 /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
@@ -4262,6 +4506,60 @@ enum {
 	TCP_BPF_SNDCWND_CLAMP	= 1002,	/* Set sndcwnd_clamp */
 	TCP_BPF_DELACK_MAX	= 1003, /* Max delay ack in usecs */
 	TCP_BPF_RTO_MIN		= 1004, /* Min delay ack in usecs */
+	/* Copy the SYN pkt to optval
+	 *
+	 * BPF_PROG_TYPE_SOCK_OPS only.  It is similar to the
+	 * bpf_getsockopt(TCP_SAVED_SYN) but it does not limit
+	 * to only getting from the saved_syn.  It can either get the
+	 * syn packet from:
+	 *
+	 * 1. the just-received SYN packet (only available when writing the
+	 *    SYNACK).  It will be useful when it is not necessary to
+	 *    save the SYN packet for latter use.  It is also the only way
+	 *    to get the SYN during syncookie mode because the syn
+	 *    packet cannot be saved during syncookie.
+	 *
+	 * OR
+	 *
+	 * 2. the earlier saved syn which was done by
+	 *    bpf_setsockopt(TCP_SAVE_SYN).
+	 *
+	 * The bpf_getsockopt(TCP_BPF_SYN*) option will hide where the
+	 * SYN packet is obtained.
+	 *
+	 * If the bpf-prog does not need the IP[46] header,  the
+	 * bpf-prog can avoid parsing the IP header by using
+	 * TCP_BPF_SYN.  Otherwise, the bpf-prog can get both
+	 * IP[46] and TCP header by using TCP_BPF_SYN_IP.
+	 *
+	 *      >0: Total number of bytes copied
+	 * -ENOSPC: Not enough space in optval. Only optlen number of
+	 *          bytes is copied.
+	 * -ENOENT: The SYN skb is not available now and the earlier SYN pkt
+	 *	    is not saved by setsockopt(TCP_SAVE_SYN).
+	 */
+	TCP_BPF_SYN		= 1005, /* Copy the TCP header */
+	TCP_BPF_SYN_IP		= 1006, /* Copy the IP[46] and TCP header */
+};
+
+enum {
+	BPF_LOAD_HDR_OPT_TCP_SYN = (1ULL << 0),
+};
+
+/* args[0] value during BPF_SOCK_OPS_HDR_OPT_LEN_CB and
+ * BPF_SOCK_OPS_WRITE_HDR_OPT_CB.
+ */
+enum {
+	BPF_WRITE_HDR_TCP_CURRENT_MSS = 1,	/* Kernel is finding the
+						 * total option spaces
+						 * required for an established
+						 * sk in order to calculate the
+						 * MSS.  No skb is actually
+						 * sent.
+						 */
+	BPF_WRITE_HDR_TCP_SYNACK_COOKIE = 2,	/* Kernel is in syncookie mode
+						 * when sending a SYN.
+						 */
 };
 
 struct bpf_perf_event_value {
-- 
cgit v1.2.3


From 267cf9fa43d1c9d525d5d818a8651f2900e3aa9e Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Thu, 20 Aug 2020 12:01:23 -0700
Subject: tcp: bpf: Optionally store mac header in TCP_SAVE_SYN

This patch is adapted from Eric's patch in an earlier discussion [1].

The TCP_SAVE_SYN currently only stores the network header and
tcp header.  This patch allows it to optionally store
the mac header also if the setsockopt's optval is 2.

It requires one more bit for the "save_syn" bit field in tcp_sock.
This patch achieves this by moving the syn_smc bit next to the is_mptcp.
The syn_smc is currently used with the TCP experimental option.  Since
syn_smc is only used when CONFIG_SMC is enabled, this patch also puts
the "IS_ENABLED(CONFIG_SMC)" around it like the is_mptcp did
with "IS_ENABLED(CONFIG_MPTCP)".

The mac_hdrlen is also stored in the "struct saved_syn"
to allow a quick offset from the bpf prog if it chooses to start
getting from the network header or the tcp header.

[1]: https://lore.kernel.org/netdev/CANn89iLJNWh6bkH7DNhy_kmcAexuUCccqERqe7z2QsvPhGrYPQ@mail.gmail.com/

Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/bpf/20200820190123.2886935-1-kafai@fb.com
---
 include/linux/tcp.h            | 13 ++++++++-----
 include/net/request_sock.h     |  1 +
 include/uapi/linux/bpf.h       |  1 +
 net/core/filter.c              | 27 ++++++++++++++++++++++-----
 net/ipv4/tcp.c                 |  3 ++-
 net/ipv4/tcp_input.c           | 14 +++++++++++++-
 tools/include/uapi/linux/bpf.h |  1 +
 7 files changed, 48 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 29d166263ae7..56ff2952edaf 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -239,14 +239,13 @@ struct tcp_sock {
 		repair      : 1,
 		frto        : 1;/* F-RTO (RFC5682) activated in CA_Loss */
 	u8	repair_queue;
-	u8	syn_data:1,	/* SYN includes data */
+	u8	save_syn:2,	/* Save headers of SYN packet */
+		syn_data:1,	/* SYN includes data */
 		syn_fastopen:1,	/* SYN includes Fast Open option */
 		syn_fastopen_exp:1,/* SYN includes Fast Open exp. option */
 		syn_fastopen_ch:1, /* Active TFO re-enabling probe */
 		syn_data_acked:1,/* data in SYN is acked by SYN-ACK */
-		save_syn:1,	/* Save headers of SYN packet */
-		is_cwnd_limited:1,/* forward progress limited by snd_cwnd? */
-		syn_smc:1;	/* SYN includes SMC */
+		is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */
 	u32	tlp_high_seq;	/* snd_nxt at the time of TLP */
 
 	u32	tcp_tx_delay;	/* delay (in usec) added to TX packets */
@@ -393,6 +392,9 @@ struct tcp_sock {
 #if IS_ENABLED(CONFIG_MPTCP)
 	bool	is_mptcp;
 #endif
+#if IS_ENABLED(CONFIG_SMC)
+	bool	syn_smc;	/* SYN includes SMC */
+#endif
 
 #ifdef CONFIG_TCP_MD5SIG
 /* TCP AF-Specific parts; only used by MD5 Signature support so far */
@@ -488,7 +490,8 @@ static inline void tcp_saved_syn_free(struct tcp_sock *tp)
 
 static inline u32 tcp_saved_syn_len(const struct saved_syn *saved_syn)
 {
-	return saved_syn->network_hdrlen + saved_syn->tcp_hdrlen;
+	return saved_syn->mac_hdrlen + saved_syn->network_hdrlen +
+		saved_syn->tcp_hdrlen;
 }
 
 struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk,
diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index 7d9ed99a77bd..29e41ff3ec93 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -42,6 +42,7 @@ struct request_sock_ops {
 int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req);
 
 struct saved_syn {
+	u32 mac_hdrlen;
 	u32 network_hdrlen;
 	u32 tcp_hdrlen;
 	u8 data[];
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index f67ec5d9e57d..544b89a64918 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -4540,6 +4540,7 @@ enum {
 	 */
 	TCP_BPF_SYN		= 1005, /* Copy the TCP header */
 	TCP_BPF_SYN_IP		= 1006, /* Copy the IP[46] and TCP header */
+	TCP_BPF_SYN_MAC         = 1007, /* Copy the MAC, IP[46], and TCP header */
 };
 
 enum {
diff --git a/net/core/filter.c b/net/core/filter.c
index ab5603d5b62a..47eef9a0be6a 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4682,11 +4682,16 @@ static int bpf_sock_ops_get_syn(struct bpf_sock_ops_kern *bpf_sock,
 		if (optname == TCP_BPF_SYN) {
 			hdr_start = syn_skb->data;
 			ret = tcp_hdrlen(syn_skb);
-		} else {
-			/* optname == TCP_BPF_SYN_IP */
+		} else if (optname == TCP_BPF_SYN_IP) {
 			hdr_start = skb_network_header(syn_skb);
 			ret = skb_network_header_len(syn_skb) +
 				tcp_hdrlen(syn_skb);
+		} else {
+			/* optname == TCP_BPF_SYN_MAC */
+			hdr_start = skb_mac_header(syn_skb);
+			ret = skb_mac_header_len(syn_skb) +
+				skb_network_header_len(syn_skb) +
+				tcp_hdrlen(syn_skb);
 		}
 	} else {
 		struct sock *sk = bpf_sock->sk;
@@ -4706,12 +4711,24 @@ static int bpf_sock_ops_get_syn(struct bpf_sock_ops_kern *bpf_sock,
 
 		if (optname == TCP_BPF_SYN) {
 			hdr_start = saved_syn->data +
+				saved_syn->mac_hdrlen +
 				saved_syn->network_hdrlen;
 			ret = saved_syn->tcp_hdrlen;
+		} else if (optname == TCP_BPF_SYN_IP) {
+			hdr_start = saved_syn->data +
+				saved_syn->mac_hdrlen;
+			ret = saved_syn->network_hdrlen +
+				saved_syn->tcp_hdrlen;
 		} else {
-			/* optname == TCP_BPF_SYN_IP */
+			/* optname == TCP_BPF_SYN_MAC */
+
+			/* TCP_SAVE_SYN may not have saved the mac hdr */
+			if (!saved_syn->mac_hdrlen)
+				return -ENOENT;
+
 			hdr_start = saved_syn->data;
-			ret = saved_syn->network_hdrlen +
+			ret = saved_syn->mac_hdrlen +
+				saved_syn->network_hdrlen +
 				saved_syn->tcp_hdrlen;
 		}
 	}
@@ -4724,7 +4741,7 @@ BPF_CALL_5(bpf_sock_ops_getsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 	   int, level, int, optname, char *, optval, int, optlen)
 {
 	if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP &&
-	    optname >= TCP_BPF_SYN && optname <= TCP_BPF_SYN_IP) {
+	    optname >= TCP_BPF_SYN && optname <= TCP_BPF_SYN_MAC) {
 		int ret, copy_len = 0;
 		const u8 *start;
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 6075cb091a20..57a568875539 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3211,7 +3211,8 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case TCP_SAVE_SYN:
-		if (val < 0 || val > 1)
+		/* 0: disable, 1: enable, 2: start from ether_header */
+		if (val < 0 || val > 2)
 			err = -EINVAL;
 		else
 			tp->save_syn = val;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 319cc7fd5117..4337841faeff 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6676,13 +6676,25 @@ static void tcp_reqsk_record_syn(const struct sock *sk,
 	if (tcp_sk(sk)->save_syn) {
 		u32 len = skb_network_header_len(skb) + tcp_hdrlen(skb);
 		struct saved_syn *saved_syn;
+		u32 mac_hdrlen;
+		void *base;
+
+		if (tcp_sk(sk)->save_syn == 2) {  /* Save full header. */
+			base = skb_mac_header(skb);
+			mac_hdrlen = skb_mac_header_len(skb);
+			len += mac_hdrlen;
+		} else {
+			base = skb_network_header(skb);
+			mac_hdrlen = 0;
+		}
 
 		saved_syn = kmalloc(struct_size(saved_syn, data, len),
 				    GFP_ATOMIC);
 		if (saved_syn) {
+			saved_syn->mac_hdrlen = mac_hdrlen;
 			saved_syn->network_hdrlen = skb_network_header_len(skb);
 			saved_syn->tcp_hdrlen = tcp_hdrlen(skb);
-			memcpy(saved_syn->data, skb_network_header(skb), len);
+			memcpy(saved_syn->data, base, len);
 			req->saved_syn = saved_syn;
 		}
 	}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index f67ec5d9e57d..544b89a64918 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4540,6 +4540,7 @@ enum {
 	 */
 	TCP_BPF_SYN		= 1005, /* Copy the TCP header */
 	TCP_BPF_SYN_IP		= 1006, /* Copy the IP[46] and TCP header */
+	TCP_BPF_SYN_MAC         = 1007, /* Copy the MAC, IP[46], and TCP header */
 };
 
 enum {
-- 
cgit v1.2.3


From 14e2ac8de0f91f12122a49f09897b0cd05256460 Mon Sep 17 00:00:00 2001
From: Marco Elver <elver@google.com>
Date: Fri, 24 Jul 2020 09:00:01 +0200
Subject: kcsan: Support compounded read-write instrumentation

Add support for compounded read-write instrumentation if supported by
the compiler. Adds the necessary instrumentation functions, and a new
type which is used to generate a more descriptive report.

Furthermore, such compounded memory access instrumentation is excluded
from the "assume aligned writes up to word size are atomic" rule,
because we cannot assume that the compiler emits code that is atomic for
compound ops.

LLVM/Clang added support for the feature in:
https://github.com/llvm/llvm-project/commit/785d41a261d136b64ab6c15c5d35f2adc5ad53e3

The new instrumentation is emitted for sets of memory accesses in the
same basic block to the same address with at least one read appearing
before a write. These typically result from compound operations such as
++, --, +=, -=, |=, &=, etc. but also equivalent forms such as "var =
var + 1". Where the compiler determines that it is equivalent to emit a
call to a single __tsan_read_write instead of separate __tsan_read and
__tsan_write, we can then benefit from improved performance and better
reporting for such access patterns.

The new reports now show that the ops are both reads and writes, for
example:

	read-write to 0xffffffff90548a38 of 8 bytes by task 143 on cpu 3:
	 test_kernel_rmw_array+0x45/0xa0
	 access_thread+0x71/0xb0
	 kthread+0x21e/0x240
	 ret_from_fork+0x22/0x30

	read-write to 0xffffffff90548a38 of 8 bytes by task 144 on cpu 2:
	 test_kernel_rmw_array+0x45/0xa0
	 access_thread+0x71/0xb0
	 kthread+0x21e/0x240
	 ret_from_fork+0x22/0x30

Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Marco Elver <elver@google.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/kcsan-checks.h | 45 +++++++++++++++++++++++++++++---------------
 kernel/kcsan/core.c          | 23 +++++++++++++++++-----
 kernel/kcsan/report.c        |  4 ++++
 scripts/Makefile.kcsan       |  2 +-
 4 files changed, 53 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kcsan-checks.h b/include/linux/kcsan-checks.h
index c5f6c1dcf7e3..cf14840609ce 100644
--- a/include/linux/kcsan-checks.h
+++ b/include/linux/kcsan-checks.h
@@ -7,19 +7,13 @@
 #include <linux/compiler_attributes.h>
 #include <linux/types.h>
 
-/*
- * ACCESS TYPE MODIFIERS
- *
- *   <none>: normal read access;
- *   WRITE : write access;
- *   ATOMIC: access is atomic;
- *   ASSERT: access is not a regular access, but an assertion;
- *   SCOPED: access is a scoped access;
- */
-#define KCSAN_ACCESS_WRITE  0x1
-#define KCSAN_ACCESS_ATOMIC 0x2
-#define KCSAN_ACCESS_ASSERT 0x4
-#define KCSAN_ACCESS_SCOPED 0x8
+/* Access types -- if KCSAN_ACCESS_WRITE is not set, the access is a read. */
+#define KCSAN_ACCESS_WRITE	(1 << 0) /* Access is a write. */
+#define KCSAN_ACCESS_COMPOUND	(1 << 1) /* Compounded read-write instrumentation. */
+#define KCSAN_ACCESS_ATOMIC	(1 << 2) /* Access is atomic. */
+/* The following are special, and never due to compiler instrumentation. */
+#define KCSAN_ACCESS_ASSERT	(1 << 3) /* Access is an assertion. */
+#define KCSAN_ACCESS_SCOPED	(1 << 4) /* Access is a scoped access. */
 
 /*
  * __kcsan_*: Always calls into the runtime when KCSAN is enabled. This may be used
@@ -204,6 +198,15 @@ static inline void __kcsan_disable_current(void) { }
 #define __kcsan_check_write(ptr, size)                                         \
 	__kcsan_check_access(ptr, size, KCSAN_ACCESS_WRITE)
 
+/**
+ * __kcsan_check_read_write - check regular read-write access for races
+ *
+ * @ptr: address of access
+ * @size: size of access
+ */
+#define __kcsan_check_read_write(ptr, size)                                    \
+	__kcsan_check_access(ptr, size, KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE)
+
 /**
  * kcsan_check_read - check regular read access for races
  *
@@ -221,18 +224,30 @@ static inline void __kcsan_disable_current(void) { }
 #define kcsan_check_write(ptr, size)                                           \
 	kcsan_check_access(ptr, size, KCSAN_ACCESS_WRITE)
 
+/**
+ * kcsan_check_read_write - check regular read-write access for races
+ *
+ * @ptr: address of access
+ * @size: size of access
+ */
+#define kcsan_check_read_write(ptr, size)                                      \
+	kcsan_check_access(ptr, size, KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE)
+
 /*
  * Check for atomic accesses: if atomic accesses are not ignored, this simply
  * aliases to kcsan_check_access(), otherwise becomes a no-op.
  */
 #ifdef CONFIG_KCSAN_IGNORE_ATOMICS
-#define kcsan_check_atomic_read(...)	do { } while (0)
-#define kcsan_check_atomic_write(...)	do { } while (0)
+#define kcsan_check_atomic_read(...)		do { } while (0)
+#define kcsan_check_atomic_write(...)		do { } while (0)
+#define kcsan_check_atomic_read_write(...)	do { } while (0)
 #else
 #define kcsan_check_atomic_read(ptr, size)                                     \
 	kcsan_check_access(ptr, size, KCSAN_ACCESS_ATOMIC)
 #define kcsan_check_atomic_write(ptr, size)                                    \
 	kcsan_check_access(ptr, size, KCSAN_ACCESS_ATOMIC | KCSAN_ACCESS_WRITE)
+#define kcsan_check_atomic_read_write(ptr, size)                               \
+	kcsan_check_access(ptr, size, KCSAN_ACCESS_ATOMIC | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_COMPOUND)
 #endif
 
 /**
diff --git a/kernel/kcsan/core.c b/kernel/kcsan/core.c
index 682d9fd76733..4c8b40b14314 100644
--- a/kernel/kcsan/core.c
+++ b/kernel/kcsan/core.c
@@ -223,7 +223,7 @@ is_atomic(const volatile void *ptr, size_t size, int type, struct kcsan_ctx *ctx
 
 	if (IS_ENABLED(CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC) &&
 	    (type & KCSAN_ACCESS_WRITE) && size <= sizeof(long) &&
-	    IS_ALIGNED((unsigned long)ptr, size))
+	    !(type & KCSAN_ACCESS_COMPOUND) && IS_ALIGNED((unsigned long)ptr, size))
 		return true; /* Assume aligned writes up to word size are atomic. */
 
 	if (ctx->atomic_next > 0) {
@@ -793,7 +793,17 @@ EXPORT_SYMBOL(__kcsan_check_access);
 	EXPORT_SYMBOL(__tsan_write##size);                                     \
 	void __tsan_unaligned_write##size(void *ptr)                           \
 		__alias(__tsan_write##size);                                   \
-	EXPORT_SYMBOL(__tsan_unaligned_write##size)
+	EXPORT_SYMBOL(__tsan_unaligned_write##size);                           \
+	void __tsan_read_write##size(void *ptr);                               \
+	void __tsan_read_write##size(void *ptr)                                \
+	{                                                                      \
+		check_access(ptr, size,                                        \
+			     KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE);      \
+	}                                                                      \
+	EXPORT_SYMBOL(__tsan_read_write##size);                                \
+	void __tsan_unaligned_read_write##size(void *ptr)                      \
+		__alias(__tsan_read_write##size);                              \
+	EXPORT_SYMBOL(__tsan_unaligned_read_write##size)
 
 DEFINE_TSAN_READ_WRITE(1);
 DEFINE_TSAN_READ_WRITE(2);
@@ -916,7 +926,8 @@ EXPORT_SYMBOL(__tsan_init);
 	u##bits __tsan_atomic##bits##_##op(u##bits *ptr, u##bits v, int memorder);                 \
 	u##bits __tsan_atomic##bits##_##op(u##bits *ptr, u##bits v, int memorder)                  \
 	{                                                                                          \
-		check_access(ptr, bits / BITS_PER_BYTE, KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC); \
+		check_access(ptr, bits / BITS_PER_BYTE,                                            \
+			     KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC);    \
 		return __atomic_##op##suffix(ptr, v, memorder);                                    \
 	}                                                                                          \
 	EXPORT_SYMBOL(__tsan_atomic##bits##_##op)
@@ -944,7 +955,8 @@ EXPORT_SYMBOL(__tsan_init);
 	int __tsan_atomic##bits##_compare_exchange_##strength(u##bits *ptr, u##bits *exp,          \
 							      u##bits val, int mo, int fail_mo)    \
 	{                                                                                          \
-		check_access(ptr, bits / BITS_PER_BYTE, KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC); \
+		check_access(ptr, bits / BITS_PER_BYTE,                                            \
+			     KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC);    \
 		return __atomic_compare_exchange_n(ptr, exp, val, weak, mo, fail_mo);              \
 	}                                                                                          \
 	EXPORT_SYMBOL(__tsan_atomic##bits##_compare_exchange_##strength)
@@ -955,7 +967,8 @@ EXPORT_SYMBOL(__tsan_init);
 	u##bits __tsan_atomic##bits##_compare_exchange_val(u##bits *ptr, u##bits exp, u##bits val, \
 							   int mo, int fail_mo)                    \
 	{                                                                                          \
-		check_access(ptr, bits / BITS_PER_BYTE, KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC); \
+		check_access(ptr, bits / BITS_PER_BYTE,                                            \
+			     KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC);    \
 		__atomic_compare_exchange_n(ptr, &exp, val, 0, mo, fail_mo);                       \
 		return exp;                                                                        \
 	}                                                                                          \
diff --git a/kernel/kcsan/report.c b/kernel/kcsan/report.c
index 9d07e175de0f..3e83a69239fa 100644
--- a/kernel/kcsan/report.c
+++ b/kernel/kcsan/report.c
@@ -228,6 +228,10 @@ static const char *get_access_type(int type)
 		return "write";
 	case KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC:
 		return "write (marked)";
+	case KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE:
+		return "read-write";
+	case KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC:
+		return "read-write (marked)";
 	case KCSAN_ACCESS_SCOPED:
 		return "read (scoped)";
 	case KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_ATOMIC:
diff --git a/scripts/Makefile.kcsan b/scripts/Makefile.kcsan
index c50f27b3ac56..c37f9518d5d9 100644
--- a/scripts/Makefile.kcsan
+++ b/scripts/Makefile.kcsan
@@ -11,5 +11,5 @@ endif
 # of some options does not break KCSAN nor causes false positive reports.
 CFLAGS_KCSAN := -fsanitize=thread \
 	$(call cc-option,$(call cc-param,tsan-instrument-func-entry-exit=0) -fno-optimize-sibling-calls) \
-	$(call cc-option,$(call cc-param,tsan-instrument-read-before-write=1)) \
+	$(call cc-option,$(call cc-param,tsan-compound-read-before-write=1),$(call cc-option,$(call cc-param,tsan-instrument-read-before-write=1))) \
 	$(call cc-param,tsan-distinguish-volatile=1)
-- 
cgit v1.2.3


From 00047c2e6d7c576c1a847f7db07ef0fc58085f22 Mon Sep 17 00:00:00 2001
From: Marco Elver <elver@google.com>
Date: Fri, 24 Jul 2020 09:00:06 +0200
Subject: instrumented.h: Introduce read-write instrumentation hooks

Introduce read-write instrumentation hooks, to more precisely denote an
operation's behaviour.

KCSAN is able to distinguish compound instrumentation, and with the new
instrumentation we then benefit from improved reporting. More
importantly, read-write compound operations should not implicitly be
treated as atomic, if they aren't actually atomic.

Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Marco Elver <elver@google.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/instrumented.h | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/instrumented.h b/include/linux/instrumented.h
index 43e6ea591975..42faebbaa202 100644
--- a/include/linux/instrumented.h
+++ b/include/linux/instrumented.h
@@ -42,6 +42,21 @@ static __always_inline void instrument_write(const volatile void *v, size_t size
 	kcsan_check_write(v, size);
 }
 
+/**
+ * instrument_read_write - instrument regular read-write access
+ *
+ * Instrument a regular write access. The instrumentation should be inserted
+ * before the actual write happens.
+ *
+ * @ptr address of access
+ * @size size of access
+ */
+static __always_inline void instrument_read_write(const volatile void *v, size_t size)
+{
+	kasan_check_write(v, size);
+	kcsan_check_read_write(v, size);
+}
+
 /**
  * instrument_atomic_read - instrument atomic read access
  *
@@ -72,6 +87,21 @@ static __always_inline void instrument_atomic_write(const volatile void *v, size
 	kcsan_check_atomic_write(v, size);
 }
 
+/**
+ * instrument_atomic_read_write - instrument atomic read-write access
+ *
+ * Instrument an atomic read-write access. The instrumentation should be
+ * inserted before the actual write happens.
+ *
+ * @ptr address of access
+ * @size size of access
+ */
+static __always_inline void instrument_atomic_read_write(const volatile void *v, size_t size)
+{
+	kasan_check_write(v, size);
+	kcsan_check_atomic_read_write(v, size);
+}
+
 /**
  * instrument_copy_to_user - instrument reads of copy_to_user
  *
-- 
cgit v1.2.3


From 583bbf0624dfd8fc45f1049be1d4980be59451ff Mon Sep 17 00:00:00 2001
From: Luke Hsiao <lukehsiao@google.com>
Date: Fri, 21 Aug 2020 21:41:04 -0700
Subject: io_uring: allow tcp ancillary data for __sys_recvmsg_sock()

For TCP tx zero-copy, the kernel notifies the process of completions by
queuing completion notifications on the socket error queue. This patch
allows reading these notifications via recvmsg to support TCP tx
zero-copy.

Ancillary data was originally disallowed due to privilege escalation
via io_uring's offloading of sendmsg() onto a kernel thread with kernel
credentials (https://crbug.com/project-zero/1975). So, we must ensure
that the socket type is one where the ancillary data types that are
delivered on recvmsg are plain data (no file descriptors or values that
are translated based on the identity of the calling process).

This was tested by using io_uring to call recvmsg on the MSG_ERRQUEUE
with tx zero-copy enabled. Before this patch, we received -EINVALID from
this specific code path. After this patch, we could read tcp tx
zero-copy completion notifications from the MSG_ERRQUEUE.

Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: Arjun Roy <arjunroy@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jann Horn <jannh@google.com>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Luke Hsiao <lukehsiao@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/net.h | 3 +++
 net/ipv4/af_inet.c  | 1 +
 net/ipv6/af_inet6.c | 1 +
 net/socket.c        | 8 +++++---
 4 files changed, 10 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/net.h b/include/linux/net.h
index d48ff1180879..7657c6432a69 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -41,6 +41,8 @@ struct net;
 #define SOCK_PASSCRED		3
 #define SOCK_PASSSEC		4
 
+#define PROTO_CMSG_DATA_ONLY	0x0001
+
 #ifndef ARCH_HAS_SOCKET_TYPES
 /**
  * enum sock_type - Socket types
@@ -135,6 +137,7 @@ typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *,
 
 struct proto_ops {
 	int		family;
+	unsigned int	flags;
 	struct module	*owner;
 	int		(*release)   (struct socket *sock);
 	int		(*bind)	     (struct socket *sock,
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 4307503a6f0b..b7260c8cef2e 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1017,6 +1017,7 @@ static int inet_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned lon
 
 const struct proto_ops inet_stream_ops = {
 	.family		   = PF_INET,
+	.flags		   = PROTO_CMSG_DATA_ONLY,
 	.owner		   = THIS_MODULE,
 	.release	   = inet_release,
 	.bind		   = inet_bind,
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 0306509ab063..d9a14935f402 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -661,6 +661,7 @@ int inet6_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 
 const struct proto_ops inet6_stream_ops = {
 	.family		   = PF_INET6,
+	.flags		   = PROTO_CMSG_DATA_ONLY,
 	.owner		   = THIS_MODULE,
 	.release	   = inet6_release,
 	.bind		   = inet6_bind,
diff --git a/net/socket.c b/net/socket.c
index dbbe8ea7d395..e84a8e281b4c 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2628,9 +2628,11 @@ long __sys_recvmsg_sock(struct socket *sock, struct msghdr *msg,
 			struct user_msghdr __user *umsg,
 			struct sockaddr __user *uaddr, unsigned int flags)
 {
-	/* disallow ancillary data requests from this path */
-	if (msg->msg_control || msg->msg_controllen)
-		return -EINVAL;
+	if (msg->msg_control || msg->msg_controllen) {
+		/* disallow ancillary data reqs unless cmsg is plain data */
+		if (!(sock->ops->flags & PROTO_CMSG_DATA_ONLY))
+			return -EINVAL;
+	}
 
 	return ____sys_recvmsg(sock, msg, umsg, uaddr, flags, 0);
 }
-- 
cgit v1.2.3


From 755f982bb1ff469a181df3eaf8dd5d769267ab8e Mon Sep 17 00:00:00 2001
From: Igor Russkikh <irusskikh@marvell.com>
Date: Sun, 23 Aug 2020 14:19:26 +0300
Subject: qed/qede: make devlink survive recovery

Devlink instance lifecycle was linked to qed_dev object,
that caused devlink to be recreated on each recovery.

Changing it by making higher level driver (qede) responsible for its
life. This way devlink now survives recoveries.

qede now stores devlink structure pointer as a part of its device
object, devlink private data contains a linkage structure,
qed_devlink.

Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed.h         |  1 -
 drivers/net/ethernet/qlogic/qed/qed_devlink.c | 40 +++++++++++----------------
 drivers/net/ethernet/qlogic/qed/qed_devlink.h |  4 +--
 drivers/net/ethernet/qlogic/qed/qed_main.c    | 10 ++-----
 drivers/net/ethernet/qlogic/qede/qede.h       |  1 +
 drivers/net/ethernet/qlogic/qede/qede_main.c  | 18 ++++++++++++
 include/linux/qed/qed_if.h                    |  9 ++++++
 7 files changed, 48 insertions(+), 35 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index b2a7b53ee760..b6ce1488abcc 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -849,7 +849,6 @@ struct qed_dev {
 	u32 rdma_max_srq_sge;
 	u16 tunn_feature_mask;
 
-	struct devlink			*dl;
 	bool				iwarp_cmt;
 };
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_devlink.c b/drivers/net/ethernet/qlogic/qed/qed_devlink.c
index eb693787c99e..a62c47c61edf 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_devlink.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_devlink.c
@@ -5,6 +5,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/qed/qed_if.h>
 #include "qed.h"
 #include "qed_devlink.h"
 
@@ -13,17 +14,12 @@ enum qed_devlink_param_id {
 	QED_DEVLINK_PARAM_ID_IWARP_CMT,
 };
 
-struct qed_devlink {
-	struct qed_dev *cdev;
-};
-
 static int qed_dl_param_get(struct devlink *dl, u32 id,
 			    struct devlink_param_gset_ctx *ctx)
 {
-	struct qed_devlink *qed_dl;
+	struct qed_devlink *qed_dl = devlink_priv(dl);
 	struct qed_dev *cdev;
 
-	qed_dl = devlink_priv(dl);
 	cdev = qed_dl->cdev;
 	ctx->val.vbool = cdev->iwarp_cmt;
 
@@ -33,10 +29,9 @@ static int qed_dl_param_get(struct devlink *dl, u32 id,
 static int qed_dl_param_set(struct devlink *dl, u32 id,
 			    struct devlink_param_gset_ctx *ctx)
 {
-	struct qed_devlink *qed_dl;
+	struct qed_devlink *qed_dl = devlink_priv(dl);
 	struct qed_dev *cdev;
 
-	qed_dl = devlink_priv(dl);
 	cdev = qed_dl->cdev;
 	cdev->iwarp_cmt = ctx->val.vbool;
 
@@ -52,21 +47,19 @@ static const struct devlink_param qed_devlink_params[] = {
 
 static const struct devlink_ops qed_dl_ops;
 
-int qed_devlink_register(struct qed_dev *cdev)
+struct devlink *qed_devlink_register(struct qed_dev *cdev)
 {
 	union devlink_param_value value;
-	struct qed_devlink *qed_dl;
+	struct qed_devlink *qdevlink;
 	struct devlink *dl;
 	int rc;
 
-	dl = devlink_alloc(&qed_dl_ops, sizeof(*qed_dl));
+	dl = devlink_alloc(&qed_dl_ops, sizeof(struct qed_devlink));
 	if (!dl)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
-	qed_dl = devlink_priv(dl);
-
-	cdev->dl = dl;
-	qed_dl->cdev = cdev;
+	qdevlink = devlink_priv(dl);
+	qdevlink->cdev = cdev;
 
 	rc = devlink_register(dl, &cdev->pdev->dev);
 	if (rc)
@@ -85,26 +78,25 @@ int qed_devlink_register(struct qed_dev *cdev)
 	devlink_params_publish(dl);
 	cdev->iwarp_cmt = false;
 
-	return 0;
+	return dl;
 
 err_unregister:
 	devlink_unregister(dl);
 
 err_free:
-	cdev->dl = NULL;
 	devlink_free(dl);
 
-	return rc;
+	return ERR_PTR(rc);
 }
 
-void qed_devlink_unregister(struct qed_dev *cdev)
+void qed_devlink_unregister(struct devlink *devlink)
 {
-	if (!cdev->dl)
+	if (!devlink)
 		return;
 
-	devlink_params_unregister(cdev->dl, qed_devlink_params,
+	devlink_params_unregister(devlink, qed_devlink_params,
 				  ARRAY_SIZE(qed_devlink_params));
 
-	devlink_unregister(cdev->dl);
-	devlink_free(cdev->dl);
+	devlink_unregister(devlink);
+	devlink_free(devlink);
 }
diff --git a/drivers/net/ethernet/qlogic/qed/qed_devlink.h b/drivers/net/ethernet/qlogic/qed/qed_devlink.h
index b94c40e9b7c1..c79dc6bfa194 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_devlink.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_devlink.h
@@ -9,7 +9,7 @@
 #include <linux/qed/qed_if.h>
 #include <net/devlink.h>
 
-int qed_devlink_register(struct qed_dev *cdev);
-void qed_devlink_unregister(struct qed_dev *cdev);
+struct devlink *qed_devlink_register(struct qed_dev *cdev);
+void qed_devlink_unregister(struct devlink *devlink);
 
 #endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index 8751355d9ef7..d6f76421379b 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -539,12 +539,6 @@ static struct qed_dev *qed_probe(struct pci_dev *pdev,
 	}
 	DP_INFO(cdev, "PCI init completed successfully\n");
 
-	rc = qed_devlink_register(cdev);
-	if (rc) {
-		DP_INFO(cdev, "Failed to register devlink.\n");
-		goto err2;
-	}
-
 	rc = qed_hw_prepare(cdev, QED_PCI_DEFAULT);
 	if (rc) {
 		DP_ERR(cdev, "hw prepare failed\n");
@@ -574,8 +568,6 @@ static void qed_remove(struct qed_dev *cdev)
 
 	qed_set_power_state(cdev, PCI_D3hot);
 
-	qed_devlink_unregister(cdev);
-
 	qed_free_cdev(cdev);
 }
 
@@ -3012,6 +3004,8 @@ const struct qed_common_ops qed_common_ops_pass = {
 	.get_link = &qed_get_current_link,
 	.drain = &qed_drain,
 	.update_msglvl = &qed_init_dp,
+	.devlink_register = qed_devlink_register,
+	.devlink_unregister = qed_devlink_unregister,
 	.dbg_all_data = &qed_dbg_all_data,
 	.dbg_all_data_size = &qed_dbg_all_data_size,
 	.chain_alloc = &qed_chain_alloc,
diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index 803c1fcca8ad..1f0e7505a973 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -172,6 +172,7 @@ struct qede_dev {
 	struct qed_dev			*cdev;
 	struct net_device		*ndev;
 	struct pci_dev			*pdev;
+	struct devlink			*devlink;
 
 	u32				dp_module;
 	u8				dp_level;
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 140a392a81bb..4cd8412e5ed0 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -1170,10 +1170,23 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level,
 			rc = -ENOMEM;
 			goto err2;
 		}
+
+		edev->devlink = qed_ops->common->devlink_register(cdev);
+		if (IS_ERR(edev->devlink)) {
+			DP_NOTICE(edev, "Cannot register devlink\n");
+			edev->devlink = NULL;
+			/* Go on, we can live without devlink */
+		}
 	} else {
 		struct net_device *ndev = pci_get_drvdata(pdev);
 
 		edev = netdev_priv(ndev);
+
+		if (edev->devlink) {
+			struct qed_devlink *qdl = devlink_priv(edev->devlink);
+
+			qdl->cdev = cdev;
+		}
 		edev->cdev = cdev;
 		memset(&edev->stats, 0, sizeof(edev->stats));
 		memcpy(&edev->dev_info, &dev_info, sizeof(dev_info));
@@ -1296,6 +1309,11 @@ static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode)
 	qed_ops->common->slowpath_stop(cdev);
 	if (system_state == SYSTEM_POWER_OFF)
 		return;
+
+	if (mode != QEDE_REMOVE_RECOVERY && edev->devlink) {
+		qed_ops->common->devlink_unregister(edev->devlink);
+		edev->devlink = NULL;
+	}
 	qed_ops->common->remove(cdev);
 	edev->cdev = NULL;
 
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index cd6a5c7e56eb..d8368e1770df 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -21,6 +21,7 @@
 #include <linux/qed/common_hsi.h>
 #include <linux/qed/qed_chain.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
+#include <net/devlink.h>
 
 enum dcbx_protocol_type {
 	DCBX_PROTOCOL_ISCSI,
@@ -779,6 +780,10 @@ enum qed_nvm_flash_cmd {
 	QED_NVM_FLASH_CMD_NVM_MAX,
 };
 
+struct qed_devlink {
+	struct qed_dev *cdev;
+};
+
 struct qed_common_cb_ops {
 	void (*arfs_filter_op)(void *dev, void *fltr, u8 fw_rc);
 	void (*link_update)(void *dev, struct qed_link_output *link);
@@ -1137,6 +1142,10 @@ struct qed_common_ops {
  *
  */
 	int (*set_grc_config)(struct qed_dev *cdev, u32 cfg_id, u32 val);
+
+	struct devlink* (*devlink_register)(struct qed_dev *cdev);
+
+	void (*devlink_unregister)(struct devlink *devlink);
 };
 
 #define MASK_FIELD(_name, _value) \
-- 
cgit v1.2.3


From 9524067b9a91dce2a096a0de7727c217495e3d2e Mon Sep 17 00:00:00 2001
From: Igor Russkikh <irusskikh@marvell.com>
Date: Sun, 23 Aug 2020 14:19:29 +0300
Subject: qed: health reporter init deinit seq

Here we declare health reporter ops (empty for now)
and register these in qed probe and remove callbacks.

This way we get devlink attached to all kind of qed* PCI
device entities: networking or storage offload entity.

Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_devlink.c | 34 +++++++++++++++++++++++++++
 drivers/net/ethernet/qlogic/qed/qed_devlink.h |  3 +++
 include/linux/qed/qed_if.h                    |  1 +
 3 files changed, 38 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/qlogic/qed/qed_devlink.c b/drivers/net/ethernet/qlogic/qed/qed_devlink.c
index 47d54a96cbb9..8b2c72fa8c44 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_devlink.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_devlink.c
@@ -14,6 +14,36 @@ enum qed_devlink_param_id {
 	QED_DEVLINK_PARAM_ID_IWARP_CMT,
 };
 
+static const struct devlink_health_reporter_ops qed_fw_fatal_reporter_ops = {
+		.name = "fw_fatal",
+};
+
+#define QED_REPORTER_FW_GRACEFUL_PERIOD 1200000
+
+void qed_fw_reporters_create(struct devlink *devlink)
+{
+	struct qed_devlink *dl = devlink_priv(devlink);
+
+	dl->fw_reporter = devlink_health_reporter_create(devlink, &qed_fw_fatal_reporter_ops,
+							 QED_REPORTER_FW_GRACEFUL_PERIOD, dl);
+	if (IS_ERR(dl->fw_reporter)) {
+		DP_NOTICE(dl->cdev, "Failed to create fw reporter, err = %ld\n",
+			  PTR_ERR(dl->fw_reporter));
+		dl->fw_reporter = NULL;
+	}
+}
+
+void qed_fw_reporters_destroy(struct devlink *devlink)
+{
+	struct qed_devlink *dl = devlink_priv(devlink);
+	struct devlink_health_reporter *rep;
+
+	rep = dl->fw_reporter;
+
+	if (!IS_ERR_OR_NULL(rep))
+		devlink_health_reporter_destroy(rep);
+}
+
 static int qed_dl_param_get(struct devlink *dl, u32 id,
 			    struct devlink_param_gset_ctx *ctx)
 {
@@ -126,6 +156,8 @@ struct devlink *qed_devlink_register(struct qed_dev *cdev)
 	devlink_params_publish(dl);
 	cdev->iwarp_cmt = false;
 
+	qed_fw_reporters_create(dl);
+
 	return dl;
 
 err_unregister:
@@ -142,6 +174,8 @@ void qed_devlink_unregister(struct devlink *devlink)
 	if (!devlink)
 		return;
 
+	qed_fw_reporters_destroy(devlink);
+
 	devlink_params_unregister(devlink, qed_devlink_params,
 				  ARRAY_SIZE(qed_devlink_params));
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_devlink.h b/drivers/net/ethernet/qlogic/qed/qed_devlink.h
index c79dc6bfa194..c68ecf778826 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_devlink.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_devlink.h
@@ -12,4 +12,7 @@
 struct devlink *qed_devlink_register(struct qed_dev *cdev);
 void qed_devlink_unregister(struct devlink *devlink);
 
+void qed_fw_reporters_create(struct devlink *devlink);
+void qed_fw_reporters_destroy(struct devlink *devlink);
+
 #endif
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index d8368e1770df..30fe06fe06a0 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -782,6 +782,7 @@ enum qed_nvm_flash_cmd {
 
 struct qed_devlink {
 	struct qed_dev *cdev;
+	struct devlink_health_reporter *fw_reporter;
 };
 
 struct qed_common_cb_ops {
-- 
cgit v1.2.3


From 4f5a8db27eb926616500f827d9b81dc40595b0ef Mon Sep 17 00:00:00 2001
From: Igor Russkikh <irusskikh@marvell.com>
Date: Sun, 23 Aug 2020 14:19:30 +0300
Subject: qed: use devlink logic to report errors

Use devlink_health_report to push error indications.
We implement this in qede via callback function to make it possible
to reuse the same for other drivers sitting on top of qed in future.

Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_devlink.c | 18 ++++++++++++++++++
 drivers/net/ethernet/qlogic/qed/qed_devlink.h |  2 ++
 drivers/net/ethernet/qlogic/qed/qed_main.c    |  1 +
 drivers/net/ethernet/qlogic/qede/qede.h       |  1 +
 drivers/net/ethernet/qlogic/qede/qede_main.c  |  4 ++++
 include/linux/qed/qed_if.h                    |  3 +++
 6 files changed, 29 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/qlogic/qed/qed_devlink.c b/drivers/net/ethernet/qlogic/qed/qed_devlink.c
index 8b2c72fa8c44..4de786d4261b 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_devlink.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_devlink.c
@@ -14,6 +14,24 @@ enum qed_devlink_param_id {
 	QED_DEVLINK_PARAM_ID_IWARP_CMT,
 };
 
+struct qed_fw_fatal_ctx {
+	enum qed_hw_err_type err_type;
+};
+
+int qed_report_fatal_error(struct devlink *devlink, enum qed_hw_err_type err_type)
+{
+	struct qed_devlink *qdl = devlink_priv(devlink);
+	struct qed_fw_fatal_ctx fw_fatal_ctx = {
+		.err_type = err_type,
+	};
+
+	if (qdl->fw_reporter)
+		devlink_health_report(qdl->fw_reporter,
+				      "Fatal error occurred", &fw_fatal_ctx);
+
+	return 0;
+}
+
 static const struct devlink_health_reporter_ops qed_fw_fatal_reporter_ops = {
 		.name = "fw_fatal",
 };
diff --git a/drivers/net/ethernet/qlogic/qed/qed_devlink.h b/drivers/net/ethernet/qlogic/qed/qed_devlink.h
index c68ecf778826..ccc7d1d1bfd4 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_devlink.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_devlink.h
@@ -15,4 +15,6 @@ void qed_devlink_unregister(struct devlink *devlink);
 void qed_fw_reporters_create(struct devlink *devlink);
 void qed_fw_reporters_destroy(struct devlink *devlink);
 
+int qed_report_fatal_error(struct devlink *dl, enum qed_hw_err_type err_type);
+
 #endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index d1a559ccf516..a64d594f9294 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -3007,6 +3007,7 @@ const struct qed_common_ops qed_common_ops_pass = {
 	.update_msglvl = &qed_init_dp,
 	.devlink_register = qed_devlink_register,
 	.devlink_unregister = qed_devlink_unregister,
+	.report_fatal_error = qed_report_fatal_error,
 	.dbg_all_data = &qed_dbg_all_data,
 	.dbg_all_data_size = &qed_dbg_all_data_size,
 	.chain_alloc = &qed_chain_alloc,
diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index 1f0e7505a973..3efc5899f656 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -264,6 +264,7 @@ struct qede_dev {
 
 	struct bpf_prog			*xdp_prog;
 
+	enum qed_hw_err_type		last_err_type;
 	unsigned long			err_flags;
 #define QEDE_ERR_IS_HANDLED		31
 #define QEDE_ERR_ATTN_CLR_EN		0
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 4cd8412e5ed0..bafdf46a9b1f 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -2601,6 +2601,9 @@ static void qede_generic_hw_err_handler(struct qede_dev *edev)
 		  "Generic sleepable HW error handling started - err_flags 0x%lx\n",
 		  edev->err_flags);
 
+	if (edev->devlink)
+		edev->ops->common->report_fatal_error(edev->devlink, edev->last_err_type);
+
 	/* Trigger a recovery process.
 	 * This is placed in the sleep requiring section just to make
 	 * sure it is the last one, and that all the other operations
@@ -2661,6 +2664,7 @@ static void qede_schedule_hw_err_handler(void *dev,
 		return;
 	}
 
+	edev->last_err_type = err_type;
 	qede_set_hw_err_flags(edev, err_type);
 	qede_atomic_hw_err_handler(edev);
 	set_bit(QEDE_SP_HW_ERR, &edev->sp_flags);
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index 30fe06fe06a0..a75533de9186 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -906,6 +906,9 @@ struct qed_common_ops {
 
 	int (*dbg_all_data_size) (struct qed_dev *cdev);
 
+	int (*report_fatal_error)(struct devlink *devlink,
+				  enum qed_hw_err_type err_type);
+
 /**
  * @brief can_link_change - can the instance change the link or not
  *
-- 
cgit v1.2.3


From c5c642c55e2fd43fcf42262fd1e87271d413fb42 Mon Sep 17 00:00:00 2001
From: Igor Russkikh <irusskikh@marvell.com>
Date: Sun, 23 Aug 2020 14:19:33 +0300
Subject: qed: align adjacent indent

Remove extra indent on some of adjacent declarations.

Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/qed/qed_if.h | 69 ++++++++++++++++++++++------------------------
 1 file changed, 33 insertions(+), 36 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index a75533de9186..56fa55841d39 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -850,10 +850,9 @@ struct qed_common_ops {
 	struct qed_dev*	(*probe)(struct pci_dev *dev,
 				 struct qed_probe_params *params);
 
-	void		(*remove)(struct qed_dev *cdev);
+	void (*remove)(struct qed_dev *cdev);
 
-	int		(*set_power_state)(struct qed_dev *cdev,
-					   pci_power_t state);
+	int (*set_power_state)(struct qed_dev *cdev, pci_power_t state);
 
 	void (*set_name) (struct qed_dev *cdev, char name[]);
 
@@ -861,50 +860,48 @@ struct qed_common_ops {
 	 * PF params required for the call before slowpath_start is
 	 * documented within the qed_pf_params structure definition.
 	 */
-	void		(*update_pf_params)(struct qed_dev *cdev,
-					    struct qed_pf_params *params);
-	int		(*slowpath_start)(struct qed_dev *cdev,
-					  struct qed_slowpath_params *params);
+	void (*update_pf_params)(struct qed_dev *cdev,
+				 struct qed_pf_params *params);
 
-	int		(*slowpath_stop)(struct qed_dev *cdev);
+	int (*slowpath_start)(struct qed_dev *cdev,
+			      struct qed_slowpath_params *params);
+
+	int (*slowpath_stop)(struct qed_dev *cdev);
 
 	/* Requests to use `cnt' interrupts for fastpath.
 	 * upon success, returns number of interrupts allocated for fastpath.
 	 */
-	int		(*set_fp_int)(struct qed_dev *cdev,
-				      u16 cnt);
+	int (*set_fp_int)(struct qed_dev *cdev, u16 cnt);
 
 	/* Fills `info' with pointers required for utilizing interrupts */
-	int		(*get_fp_int)(struct qed_dev *cdev,
-				      struct qed_int_info *info);
-
-	u32		(*sb_init)(struct qed_dev *cdev,
-				   struct qed_sb_info *sb_info,
-				   void *sb_virt_addr,
-				   dma_addr_t sb_phy_addr,
-				   u16 sb_id,
-				   enum qed_sb_type type);
-
-	u32		(*sb_release)(struct qed_dev *cdev,
-				      struct qed_sb_info *sb_info,
-				      u16 sb_id,
-				      enum qed_sb_type type);
-
-	void		(*simd_handler_config)(struct qed_dev *cdev,
-					       void *token,
-					       int index,
-					       void (*handler)(void *));
-
-	void		(*simd_handler_clean)(struct qed_dev *cdev,
-					      int index);
-	int (*dbg_grc)(struct qed_dev *cdev,
-		       void *buffer, u32 *num_dumped_bytes);
+	int (*get_fp_int)(struct qed_dev *cdev, struct qed_int_info *info);
+
+	u32 (*sb_init)(struct qed_dev *cdev,
+		       struct qed_sb_info *sb_info,
+		       void *sb_virt_addr,
+		       dma_addr_t sb_phy_addr,
+		       u16 sb_id,
+		       enum qed_sb_type type);
+
+	u32 (*sb_release)(struct qed_dev *cdev,
+			  struct qed_sb_info *sb_info,
+			  u16 sb_id,
+			  enum qed_sb_type type);
+
+	void (*simd_handler_config)(struct qed_dev *cdev,
+				    void *token,
+				    int index,
+				    void (*handler)(void *));
+
+	void (*simd_handler_clean)(struct qed_dev *cdev, int index);
+
+	int (*dbg_grc)(struct qed_dev *cdev, void *buffer, u32 *num_dumped_bytes);
 
 	int (*dbg_grc_size)(struct qed_dev *cdev);
 
-	int (*dbg_all_data) (struct qed_dev *cdev, void *buffer);
+	int (*dbg_all_data)(struct qed_dev *cdev, void *buffer);
 
-	int (*dbg_all_data_size) (struct qed_dev *cdev);
+	int (*dbg_all_data_size)(struct qed_dev *cdev);
 
 	int (*report_fatal_error)(struct devlink *devlink,
 				  enum qed_hw_err_type err_type);
-- 
cgit v1.2.3


From 000601bb62330f18dc8f5d2d0b82e9aec3e207c4 Mon Sep 17 00:00:00 2001
From: Tobias Klauser <tklauser@distanz.ch>
Date: Thu, 9 Jul 2020 15:05:59 +0200
Subject: rcu: Fix kerneldoc comments in rcupdate.h

This commit fixes the kerneldoc comments for rcu_read_unlock_bh(),
rcu_read_unlock_sched() and rcu_head_after_call_rcu() so they e.g. get
properly linked in the API documentation. Also add parenthesis after
function names to match the notation used in other kerneldoc comments in
the same file.

Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/rcupdate.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index d15d46db61f7..b47d6b66665e 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -709,8 +709,8 @@ static inline void rcu_read_lock_bh(void)
 			 "rcu_read_lock_bh() used illegally while idle");
 }
 
-/*
- * rcu_read_unlock_bh - marks the end of a softirq-only RCU critical section
+/**
+ * rcu_read_unlock_bh() - marks the end of a softirq-only RCU critical section
  *
  * See rcu_read_lock_bh() for more information.
  */
@@ -751,10 +751,10 @@ static inline notrace void rcu_read_lock_sched_notrace(void)
 	__acquire(RCU_SCHED);
 }
 
-/*
- * rcu_read_unlock_sched - marks the end of a RCU-classic critical section
+/**
+ * rcu_read_unlock_sched() - marks the end of a RCU-classic critical section
  *
- * See rcu_read_lock_sched for more information.
+ * See rcu_read_lock_sched() for more information.
  */
 static inline void rcu_read_unlock_sched(void)
 {
@@ -945,7 +945,7 @@ static inline void rcu_head_init(struct rcu_head *rhp)
 }
 
 /**
- * rcu_head_after_call_rcu - Has this rcu_head been passed to call_rcu()?
+ * rcu_head_after_call_rcu() - Has this rcu_head been passed to call_rcu()?
  * @rhp: The rcu_head structure to test.
  * @f: The function passed to call_rcu() along with @rhp.
  *
-- 
cgit v1.2.3


From ae2212a7216b674633bdc3bd2e24947a0665efb8 Mon Sep 17 00:00:00 2001
From: Madhuparna Bhowmik <madhuparnabhowmik10@gmail.com>
Date: Sun, 12 Jul 2020 18:40:02 +0530
Subject: rculist: Introduce list/hlist_for_each_entry_srcu() macros

list/hlist_for_each_entry_rcu() provides an optional cond argument
to specify the lock held in the updater side.
However for SRCU read side, not providing the cond argument results
into false positive as whether srcu_read_lock is held or not is not
checked implicitly. Therefore, on read side the lockdep expression
srcu_read_lock_held(srcu struct) can solve this issue.

However, the function still fails to check the cases where srcu
protected list is traversed with rcu_read_lock() instead of
srcu_read_lock(). Therefore, to remove the false negative,
this patch introduces two new list traversal primitives :
list_for_each_entry_srcu() and hlist_for_each_entry_srcu().

Both of the functions have non-optional cond argument
as it is required for both read and update side, and simply checks
if the cond is true. For regular read side the lockdep expression
srcu_read_lock_head() can be passed as the cond argument to
list/hlist_for_each_entry_srcu().

Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Tested-by: Suraj Upadhyay <usuraj35@gmail.com>
Tested-by: Naresh Kamboju <naresh.kamboju@linaro.org>
[ paulmck: Add "true" per kbuild test robot feedback. ]
Signed-off-by: Madhuparna Bhowmik <madhuparnabhowmik10@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/rculist.h | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index 7a6fc9956510..f8633d37e358 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -63,9 +63,17 @@ static inline void INIT_LIST_HEAD_RCU(struct list_head *list)
 	RCU_LOCKDEP_WARN(!(cond) && !rcu_read_lock_any_held(),		\
 			 "RCU-list traversed in non-reader section!");	\
 	})
+
+#define __list_check_srcu(cond)					 \
+	({								 \
+	RCU_LOCKDEP_WARN(!(cond),					 \
+		"RCU-list traversed without holding the required lock!");\
+	})
 #else
 #define __list_check_rcu(dummy, cond, extra...)				\
 	({ check_arg_count_one(extra); })
+
+#define __list_check_srcu(cond) ({ })
 #endif
 
 /*
@@ -385,6 +393,25 @@ static inline void list_splice_tail_init_rcu(struct list_head *list,
 		&pos->member != (head);					\
 		pos = list_entry_rcu(pos->member.next, typeof(*pos), member))
 
+/**
+ * list_for_each_entry_srcu	-	iterate over rcu list of given type
+ * @pos:	the type * to use as a loop cursor.
+ * @head:	the head for your list.
+ * @member:	the name of the list_head within the struct.
+ * @cond:	lockdep expression for the lock required to traverse the list.
+ *
+ * This list-traversal primitive may safely run concurrently with
+ * the _rcu list-mutation primitives such as list_add_rcu()
+ * as long as the traversal is guarded by srcu_read_lock().
+ * The lockdep expression srcu_read_lock_held() can be passed as the
+ * cond argument from read side.
+ */
+#define list_for_each_entry_srcu(pos, head, member, cond)		\
+	for (__list_check_srcu(cond),					\
+	     pos = list_entry_rcu((head)->next, typeof(*pos), member);	\
+		&pos->member != (head);					\
+		pos = list_entry_rcu(pos->member.next, typeof(*pos), member))
+
 /**
  * list_entry_lockless - get the struct for this entry
  * @ptr:        the &struct list_head pointer.
@@ -683,6 +710,27 @@ static inline void hlist_add_behind_rcu(struct hlist_node *n,
 		pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(\
 			&(pos)->member)), typeof(*(pos)), member))
 
+/**
+ * hlist_for_each_entry_srcu - iterate over rcu list of given type
+ * @pos:	the type * to use as a loop cursor.
+ * @head:	the head for your list.
+ * @member:	the name of the hlist_node within the struct.
+ * @cond:	lockdep expression for the lock required to traverse the list.
+ *
+ * This list-traversal primitive may safely run concurrently with
+ * the _rcu list-mutation primitives such as hlist_add_head_rcu()
+ * as long as the traversal is guarded by srcu_read_lock().
+ * The lockdep expression srcu_read_lock_held() can be passed as the
+ * cond argument from read side.
+ */
+#define hlist_for_each_entry_srcu(pos, head, member, cond)		\
+	for (__list_check_srcu(cond),					\
+	     pos = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),\
+			typeof(*(pos)), member);			\
+		pos;							\
+		pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(\
+			&(pos)->member)), typeof(*(pos)), member))
+
 /**
  * hlist_for_each_entry_rcu_notrace - iterate over rcu list of given type (for tracing)
  * @pos:	the type * to use as a loop cursor.
-- 
cgit v1.2.3


From 7f2a53c231fe5d9522c3b695ab454203904031ac Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Mon, 17 Aug 2020 10:37:22 -0700
Subject: rcu: Remove unused __rcu_is_watching() function

The x86/entry work removed all uses of __rcu_is_watching(), therefore
this commit removes it entirely.

Cc: Andy Lutomirski <luto@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <x86@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/rcutiny.h | 1 -
 include/linux/rcutree.h | 1 -
 kernel/entry/common.c   | 2 +-
 kernel/rcu/tree.c       | 5 -----
 4 files changed, 1 insertion(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 5cc9637cac16..7c1ecdb356d8 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -103,7 +103,6 @@ static inline void rcu_scheduler_starting(void) { }
 static inline void rcu_end_inkernel_boot(void) { }
 static inline bool rcu_inkernel_boot_has_ended(void) { return true; }
 static inline bool rcu_is_watching(void) { return true; }
-static inline bool __rcu_is_watching(void) { return true; }
 static inline void rcu_momentary_dyntick_idle(void) { }
 static inline void kfree_rcu_scheduler_running(void) { }
 static inline bool rcu_gp_might_be_stalled(void) { return false; }
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index d2f4064ebd1d..59eb5cd567d7 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -64,7 +64,6 @@ extern int rcu_scheduler_active __read_mostly;
 void rcu_end_inkernel_boot(void);
 bool rcu_inkernel_boot_has_ended(void);
 bool rcu_is_watching(void);
-bool __rcu_is_watching(void);
 #ifndef CONFIG_PREEMPTION
 void rcu_all_qs(void);
 #endif
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 9852e0d62d95..ad794a10fa80 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -278,7 +278,7 @@ noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
 	 * terminate a grace period, if and only if the timer interrupt is
 	 * not nested into another interrupt.
 	 *
-	 * Checking for __rcu_is_watching() here would prevent the nesting
+	 * Checking for rcu_is_watching() here would prevent the nesting
 	 * interrupt to invoke rcu_irq_enter(). If that nested interrupt is
 	 * the tick then rcu_flavor_sched_clock_irq() would wrongfully
 	 * assume that it is the first interupt and eventually claim
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 396abe0e0d01..232362293678 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1077,11 +1077,6 @@ static void rcu_disable_urgency_upon_qs(struct rcu_data *rdp)
 	}
 }
 
-noinstr bool __rcu_is_watching(void)
-{
-	return !rcu_dynticks_curr_cpu_in_eqs();
-}
-
 /**
  * rcu_is_watching - see if RCU thinks that the current CPU is not idle
  *
-- 
cgit v1.2.3


From aa40c138cc8f36e2f5c721fd1bdb823a1ef1a237 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Mon, 10 Aug 2020 09:58:03 -0700
Subject: rcu: Report QS for outermost PREEMPT=n rcu_read_unlock() for strict
 GPs

The CONFIG_PREEMPT=n instance of rcu_read_unlock is even more
aggressively than that of CONFIG_PREEMPT=y in deferring reporting
quiescent states to the RCU core.  This is just what is wanted in normal
use because it reduces overhead, but the resulting delay is not what
is wanted for kernels built with CONFIG_RCU_STRICT_GRACE_PERIOD=y.
This commit therefore adds an rcu_read_unlock_strict() function that
checks for exceptional conditions, and reports the newly started
quiescent state if it is safe to do so, also doing a spin-delay if
requested via rcutree.rcu_unlock_delay.  This commit also adds a call
to rcu_read_unlock_strict() from the CONFIG_PREEMPT=n instance of
__rcu_read_unlock().

[ paulmck: Fixed bug located by kernel test robot <lkp@intel.com> ]
Reported-by Jann Horn <jannh@google.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/rcupdate.h |  7 +++++++
 kernel/rcu/tree.c        |  6 ++++++
 kernel/rcu/tree_plugin.h | 24 ++++++++++++++++++------
 3 files changed, 31 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index d15d46db61f7..522529a13786 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -55,6 +55,12 @@ void __rcu_read_unlock(void);
 
 #else /* #ifdef CONFIG_PREEMPT_RCU */
 
+#ifdef CONFIG_TINY_RCU
+#define rcu_read_unlock_strict() do { } while (0)
+#else
+void rcu_read_unlock_strict(void);
+#endif
+
 static inline void __rcu_read_lock(void)
 {
 	preempt_disable();
@@ -63,6 +69,7 @@ static inline void __rcu_read_lock(void)
 static inline void __rcu_read_unlock(void)
 {
 	preempt_enable();
+	rcu_read_unlock_strict();
 }
 
 static inline int rcu_preempt_depth(void)
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 31995b3f0ed9..a295cadf7c2f 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -178,6 +178,12 @@ module_param(gp_init_delay, int, 0444);
 static int gp_cleanup_delay;
 module_param(gp_cleanup_delay, int, 0444);
 
+// Add delay to rcu_read_unlock() for strict grace periods.
+static int rcu_unlock_delay;
+#ifdef CONFIG_RCU_STRICT_GRACE_PERIOD
+module_param(rcu_unlock_delay, int, 0444);
+#endif
+
 /*
  * This rcu parameter is runtime-read-only. It reflects
  * a minimum allowed number of objects which can be cached
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 3f3a4ffd4df2..25a676dff5de 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -430,12 +430,6 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp)
 	return !list_empty(&rnp->blkd_tasks);
 }
 
-// Add delay to rcu_read_unlock() for strict grace periods.
-static int rcu_unlock_delay;
-#ifdef CONFIG_RCU_STRICT_GRACE_PERIOD
-module_param(rcu_unlock_delay, int, 0444);
-#endif
-
 /*
  * Report deferred quiescent states.  The deferral time can
  * be quite short, for example, in the case of the call from
@@ -784,6 +778,24 @@ dump_blkd_tasks(struct rcu_node *rnp, int ncheck)
 
 #else /* #ifdef CONFIG_PREEMPT_RCU */
 
+/*
+ * If strict grace periods are enabled, and if the calling
+ * __rcu_read_unlock() marks the beginning of a quiescent state, immediately
+ * report that quiescent state and, if requested, spin for a bit.
+ */
+void rcu_read_unlock_strict(void)
+{
+	struct rcu_data *rdp;
+
+	if (!IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD) ||
+	   irqs_disabled() || preempt_count() || !rcu_state.gp_kthread)
+		return;
+	rdp = this_cpu_ptr(&rcu_data);
+	rcu_report_qs_rdp(rdp->cpu, rdp);
+	udelay(rcu_unlock_delay);
+}
+EXPORT_SYMBOL_GPL(rcu_read_unlock_strict);
+
 /*
  * Tell them what RCU they are running.
  */
-- 
cgit v1.2.3


From 00cda13e339c9f4956a6f036675df2ca5b5a552e Mon Sep 17 00:00:00 2001
From: Dmitry Osipenko <digetx@gmail.com>
Date: Fri, 14 Aug 2020 00:34:02 +0300
Subject: power: supply: Support battery temperature device-tree properties

The generic battery temperature properties are already supported by the
power-supply core. Let's support parsing of the common battery temperature
properties from a device-tree.

Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/power_supply_core.c | 19 +++++++++++++++++++
 include/linux/power_supply.h             |  6 ++++++
 2 files changed, 25 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c
index ccbad435ed12..38e3aa642131 100644
--- a/drivers/power/supply/power_supply_core.c
+++ b/drivers/power/supply/power_supply_core.c
@@ -579,6 +579,12 @@ int power_supply_get_battery_info(struct power_supply *psy,
 	info->charge_term_current_ua         = -EINVAL;
 	info->constant_charge_current_max_ua = -EINVAL;
 	info->constant_charge_voltage_max_uv = -EINVAL;
+	info->temp_ambient_alert_min         = INT_MIN;
+	info->temp_ambient_alert_max         = INT_MAX;
+	info->temp_alert_min                 = INT_MIN;
+	info->temp_alert_max                 = INT_MAX;
+	info->temp_min                       = INT_MIN;
+	info->temp_max                       = INT_MAX;
 	info->factory_internal_resistance_uohm  = -EINVAL;
 	info->resist_table = NULL;
 
@@ -639,6 +645,19 @@ int power_supply_get_battery_info(struct power_supply *psy,
 	of_property_read_u32(battery_np, "factory-internal-resistance-micro-ohms",
 			     &info->factory_internal_resistance_uohm);
 
+	of_property_read_u32_index(battery_np, "ambient-celsius",
+				   0, &info->temp_ambient_alert_min);
+	of_property_read_u32_index(battery_np, "ambient-celsius",
+				   1, &info->temp_ambient_alert_max);
+	of_property_read_u32_index(battery_np, "alert-celsius",
+				   0, &info->temp_alert_min);
+	of_property_read_u32_index(battery_np, "alert-celsius",
+				   1, &info->temp_alert_max);
+	of_property_read_u32_index(battery_np, "operating-range-celsius",
+				   0, &info->temp_min);
+	of_property_read_u32_index(battery_np, "operating-range-celsius",
+				   1, &info->temp_max);
+
 	len = of_property_count_u32_elems(battery_np, "ocv-capacity-celsius");
 	if (len < 0 && len != -EINVAL) {
 		err = len;
diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h
index 97cc4b85bf61..d0684362a392 100644
--- a/include/linux/power_supply.h
+++ b/include/linux/power_supply.h
@@ -365,6 +365,12 @@ struct power_supply_battery_info {
 	int constant_charge_voltage_max_uv; /* microVolts */
 	int factory_internal_resistance_uohm;   /* microOhms */
 	int ocv_temp[POWER_SUPPLY_OCV_TEMP_MAX];/* celsius */
+	int temp_ambient_alert_min;             /* celsius */
+	int temp_ambient_alert_max;             /* celsius */
+	int temp_alert_min;                     /* celsius */
+	int temp_alert_max;                     /* celsius */
+	int temp_min;                           /* celsius */
+	int temp_max;                           /* celsius */
 	struct power_supply_battery_ocv_table *ocv_table[POWER_SUPPLY_OCV_TEMP_MAX];
 	int ocv_table_size[POWER_SUPPLY_OCV_TEMP_MAX];
 	struct power_supply_resistance_temp_table *resist_table;
-- 
cgit v1.2.3


From f836a56e84ffc9f1a1cd73f77e10404ca46a4616 Mon Sep 17 00:00:00 2001
From: KP Singh <kpsingh@google.com>
Date: Tue, 25 Aug 2020 20:29:15 +0200
Subject: bpf: Generalize bpf_sk_storage

Refactor the functionality in bpf_sk_storage.c so that concept of
storage linked to kernel objects can be extended to other objects like
inode, task_struct etc.

Each new local storage will still be a separate map and provide its own
set of helpers. This allows for future object specific extensions and
still share a lot of the underlying implementation.

This includes the changes suggested by Martin in:

  https://lore.kernel.org/bpf/20200725013047.4006241-1-kafai@fb.com/

adding new map operations to support bpf_local_storage maps:

* storages for different kernel objects to optionally have different
  memory charging strategy (map_local_storage_charge,
  map_local_storage_uncharge)
* Functionality to extract the storage pointer from a pointer to the
  owning object (map_owner_storage_ptr)

Co-developed-by: Martin KaFai Lau <kafai@fb.com>

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: KP Singh <kpsingh@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200825182919.1118197-4-kpsingh@chromium.org
---
 include/linux/bpf.h            |   8 ++
 include/net/bpf_sk_storage.h   |  52 +++++++++
 include/uapi/linux/bpf.h       |   8 +-
 net/core/bpf_sk_storage.c      | 238 +++++++++++++++++++++++++++--------------
 tools/include/uapi/linux/bpf.h |   8 +-
 5 files changed, 228 insertions(+), 86 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 81f38e2fda78..8c443b93ac11 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -34,6 +34,8 @@ struct btf_type;
 struct exception_table_entry;
 struct seq_operations;
 struct bpf_iter_aux_info;
+struct bpf_local_storage;
+struct bpf_local_storage_map;
 
 extern struct idr btf_idr;
 extern spinlock_t btf_idr_lock;
@@ -104,6 +106,12 @@ struct bpf_map_ops {
 	__poll_t (*map_poll)(struct bpf_map *map, struct file *filp,
 			     struct poll_table_struct *pts);
 
+	/* Functions called by bpf_local_storage maps */
+	int (*map_local_storage_charge)(struct bpf_local_storage_map *smap,
+					void *owner, u32 size);
+	void (*map_local_storage_uncharge)(struct bpf_local_storage_map *smap,
+					   void *owner, u32 size);
+	struct bpf_local_storage __rcu ** (*map_owner_storage_ptr)(void *owner);
 	/* BTF name and id of struct allocated by map_alloc */
 	const char * const map_btf_name;
 	int *map_btf_id;
diff --git a/include/net/bpf_sk_storage.h b/include/net/bpf_sk_storage.h
index 950c5aaba15e..9e631b5466e3 100644
--- a/include/net/bpf_sk_storage.h
+++ b/include/net/bpf_sk_storage.h
@@ -3,8 +3,15 @@
 #ifndef _BPF_SK_STORAGE_H
 #define _BPF_SK_STORAGE_H
 
+#include <linux/rculist.h>
+#include <linux/list.h>
+#include <linux/hash.h>
 #include <linux/types.h>
 #include <linux/spinlock.h>
+#include <linux/bpf.h>
+#include <net/sock.h>
+#include <uapi/linux/sock_diag.h>
+#include <uapi/linux/btf.h>
 
 struct sock;
 
@@ -13,6 +20,7 @@ void bpf_sk_storage_free(struct sock *sk);
 extern const struct bpf_func_proto bpf_sk_storage_get_proto;
 extern const struct bpf_func_proto bpf_sk_storage_delete_proto;
 
+struct bpf_local_storage_elem;
 struct bpf_sk_storage_diag;
 struct sk_buff;
 struct nlattr;
@@ -34,6 +42,50 @@ u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache);
 void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache,
 				      u16 idx);
 
+/* Helper functions for bpf_local_storage */
+int bpf_local_storage_map_alloc_check(union bpf_attr *attr);
+
+struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr);
+
+struct bpf_local_storage_data *
+bpf_local_storage_lookup(struct bpf_local_storage *local_storage,
+			 struct bpf_local_storage_map *smap,
+			 bool cacheit_lockit);
+
+void bpf_local_storage_map_free(struct bpf_local_storage_map *smap);
+
+int bpf_local_storage_map_check_btf(const struct bpf_map *map,
+				    const struct btf *btf,
+				    const struct btf_type *key_type,
+				    const struct btf_type *value_type);
+
+void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage,
+				   struct bpf_local_storage_elem *selem);
+
+bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage,
+				     struct bpf_local_storage_elem *selem,
+				     bool uncharge_omem);
+
+void bpf_selem_unlink(struct bpf_local_storage_elem *selem);
+
+void bpf_selem_link_map(struct bpf_local_storage_map *smap,
+			struct bpf_local_storage_elem *selem);
+
+void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem);
+
+struct bpf_local_storage_elem *
+bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, void *value,
+		bool charge_mem);
+
+int
+bpf_local_storage_alloc(void *owner,
+			struct bpf_local_storage_map *smap,
+			struct bpf_local_storage_elem *first_selem);
+
+struct bpf_local_storage_data *
+bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
+			 void *value, u64 map_flags);
+
 #ifdef CONFIG_BPF_SYSCALL
 int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk);
 struct bpf_sk_storage_diag *
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 544b89a64918..2cbd137eed86 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3765,9 +3765,13 @@ enum {
 	BPF_F_SYSCTL_BASE_NAME		= (1ULL << 0),
 };
 
-/* BPF_FUNC_sk_storage_get flags */
+/* BPF_FUNC_<kernel_obj>_storage_get flags */
 enum {
-	BPF_SK_STORAGE_GET_F_CREATE	= (1ULL << 0),
+	BPF_LOCAL_STORAGE_GET_F_CREATE	= (1ULL << 0),
+	/* BPF_SK_STORAGE_GET_F_CREATE is only kept for backward compatibility
+	 * and BPF_LOCAL_STORAGE_GET_F_CREATE must be used instead.
+	 */
+	BPF_SK_STORAGE_GET_F_CREATE  = BPF_LOCAL_STORAGE_GET_F_CREATE,
 };
 
 /* BPF_FUNC_read_branch_records flags. */
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index ec61ee7c7ee4..cd8b7017913b 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -84,7 +84,7 @@ struct bpf_local_storage_elem {
 struct bpf_local_storage {
 	struct bpf_local_storage_data __rcu *cache[BPF_LOCAL_STORAGE_CACHE_SIZE];
 	struct hlist_head list; /* List of bpf_local_storage_elem */
-	struct sock *owner;	/* The object that owns the above "list" of
+	void *owner;		/* The object that owns the above "list" of
 				 * bpf_local_storage_elem.
 				 */
 	struct rcu_head rcu;
@@ -110,6 +110,33 @@ static int omem_charge(struct sock *sk, unsigned int size)
 	return -ENOMEM;
 }
 
+static int mem_charge(struct bpf_local_storage_map *smap, void *owner, u32 size)
+{
+	struct bpf_map *map = &smap->map;
+
+	if (!map->ops->map_local_storage_charge)
+		return 0;
+
+	return map->ops->map_local_storage_charge(smap, owner, size);
+}
+
+static void mem_uncharge(struct bpf_local_storage_map *smap, void *owner,
+			 u32 size)
+{
+	struct bpf_map *map = &smap->map;
+
+	if (map->ops->map_local_storage_uncharge)
+		map->ops->map_local_storage_uncharge(smap, owner, size);
+}
+
+static struct bpf_local_storage __rcu **
+owner_storage(struct bpf_local_storage_map *smap, void *owner)
+{
+	struct bpf_map *map = &smap->map;
+
+	return map->ops->map_owner_storage_ptr(owner);
+}
+
 static bool selem_linked_to_storage(const struct bpf_local_storage_elem *selem)
 {
 	return !hlist_unhashed(&selem->snode);
@@ -120,13 +147,13 @@ static bool selem_linked_to_map(const struct bpf_local_storage_elem *selem)
 	return !hlist_unhashed(&selem->map_node);
 }
 
-static struct bpf_local_storage_elem *
-bpf_selem_alloc(struct bpf_local_storage_map *smap, struct sock *sk,
-		void *value, bool charge_omem)
+struct bpf_local_storage_elem *
+bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner,
+		void *value, bool charge_mem)
 {
 	struct bpf_local_storage_elem *selem;
 
-	if (charge_omem && omem_charge(sk, smap->elem_size))
+	if (charge_mem && mem_charge(smap, owner, smap->elem_size))
 		return NULL;
 
 	selem = kzalloc(smap->elem_size, GFP_ATOMIC | __GFP_NOWARN);
@@ -136,8 +163,8 @@ bpf_selem_alloc(struct bpf_local_storage_map *smap, struct sock *sk,
 		return selem;
 	}
 
-	if (charge_omem)
-		atomic_sub(smap->elem_size, &sk->sk_omem_alloc);
+	if (charge_mem)
+		mem_uncharge(smap, owner, smap->elem_size);
 
 	return NULL;
 }
@@ -146,32 +173,32 @@ bpf_selem_alloc(struct bpf_local_storage_map *smap, struct sock *sk,
  * The caller must ensure selem->smap is still valid to be
  * dereferenced for its smap->elem_size and smap->cache_idx.
  */
-static bool
-bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage,
-				struct bpf_local_storage_elem *selem,
-				bool uncharge_omem)
+bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage,
+				     struct bpf_local_storage_elem *selem,
+				     bool uncharge_mem)
 {
 	struct bpf_local_storage_map *smap;
 	bool free_local_storage;
-	struct sock *sk;
+	void *owner;
 
 	smap = rcu_dereference(SDATA(selem)->smap);
-	sk = local_storage->owner;
+	owner = local_storage->owner;
 
 	/* All uncharging on the owner must be done first.
 	 * The owner may be freed once the last selem is unlinked
 	 * from local_storage.
 	 */
-	if (uncharge_omem)
-		atomic_sub(smap->elem_size, &sk->sk_omem_alloc);
+	if (uncharge_mem)
+		mem_uncharge(smap, owner, smap->elem_size);
 
 	free_local_storage = hlist_is_singular_node(&selem->snode,
 						    &local_storage->list);
 	if (free_local_storage) {
-		atomic_sub(sizeof(struct bpf_local_storage), &sk->sk_omem_alloc);
+		mem_uncharge(smap, owner, sizeof(struct bpf_local_storage));
 		local_storage->owner = NULL;
-		/* After this RCU_INIT, sk may be freed and cannot be used */
-		RCU_INIT_POINTER(sk->sk_bpf_storage, NULL);
+
+		/* After this RCU_INIT, owner may be freed and cannot be used */
+		RCU_INIT_POINTER(*owner_storage(smap, owner), NULL);
 
 		/* local_storage is not freed now.  local_storage->lock is
 		 * still held and raw_spin_unlock_bh(&local_storage->lock)
@@ -209,23 +236,22 @@ static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem)
 	local_storage = rcu_dereference(selem->local_storage);
 	raw_spin_lock_bh(&local_storage->lock);
 	if (likely(selem_linked_to_storage(selem)))
-		free_local_storage =
-			bpf_selem_unlink_storage_nolock(local_storage, selem, true);
+		free_local_storage = bpf_selem_unlink_storage_nolock(
+			local_storage, selem, true);
 	raw_spin_unlock_bh(&local_storage->lock);
 
 	if (free_local_storage)
 		kfree_rcu(local_storage, rcu);
 }
 
-static void
-bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage,
-			      struct bpf_local_storage_elem *selem)
+void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage,
+				   struct bpf_local_storage_elem *selem)
 {
 	RCU_INIT_POINTER(selem->local_storage, local_storage);
 	hlist_add_head(&selem->snode, &local_storage->list);
 }
 
-static void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem)
+void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem)
 {
 	struct bpf_local_storage_map *smap;
 	struct bpf_local_storage_map_bucket *b;
@@ -242,8 +268,8 @@ static void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem)
 	raw_spin_unlock_bh(&b->lock);
 }
 
-static void bpf_selem_link_map(struct bpf_local_storage_map *smap,
-			       struct bpf_local_storage_elem *selem)
+void bpf_selem_link_map(struct bpf_local_storage_map *smap,
+			struct bpf_local_storage_elem *selem)
 {
 	struct bpf_local_storage_map_bucket *b = select_bucket(smap, selem);
 
@@ -253,7 +279,7 @@ static void bpf_selem_link_map(struct bpf_local_storage_map *smap,
 	raw_spin_unlock_bh(&b->lock);
 }
 
-static void bpf_selem_unlink(struct bpf_local_storage_elem *selem)
+void bpf_selem_unlink(struct bpf_local_storage_elem *selem)
 {
 	/* Always unlink from map before unlinking from local_storage
 	 * because selem will be freed after successfully unlinked from
@@ -263,7 +289,7 @@ static void bpf_selem_unlink(struct bpf_local_storage_elem *selem)
 	__bpf_selem_unlink_storage(selem);
 }
 
-static struct bpf_local_storage_data *
+struct bpf_local_storage_data *
 bpf_local_storage_lookup(struct bpf_local_storage *local_storage,
 			 struct bpf_local_storage_map *smap,
 			 bool cacheit_lockit)
@@ -329,40 +355,45 @@ static int check_flags(const struct bpf_local_storage_data *old_sdata,
 	return 0;
 }
 
-static int sk_storage_alloc(struct sock *sk,
+int bpf_local_storage_alloc(void *owner,
 			    struct bpf_local_storage_map *smap,
 			    struct bpf_local_storage_elem *first_selem)
 {
-	struct bpf_local_storage *prev_sk_storage, *sk_storage;
+	struct bpf_local_storage *prev_storage, *storage;
+	struct bpf_local_storage **owner_storage_ptr;
 	int err;
 
-	err = omem_charge(sk, sizeof(*sk_storage));
+	err = mem_charge(smap, owner, sizeof(*storage));
 	if (err)
 		return err;
 
-	sk_storage = kzalloc(sizeof(*sk_storage), GFP_ATOMIC | __GFP_NOWARN);
-	if (!sk_storage) {
+	storage = kzalloc(sizeof(*storage), GFP_ATOMIC | __GFP_NOWARN);
+	if (!storage) {
 		err = -ENOMEM;
 		goto uncharge;
 	}
-	INIT_HLIST_HEAD(&sk_storage->list);
-	raw_spin_lock_init(&sk_storage->lock);
-	sk_storage->owner = sk;
 
-	bpf_selem_link_storage_nolock(sk_storage, first_selem);
+	INIT_HLIST_HEAD(&storage->list);
+	raw_spin_lock_init(&storage->lock);
+	storage->owner = owner;
+
+	bpf_selem_link_storage_nolock(storage, first_selem);
 	bpf_selem_link_map(smap, first_selem);
-	/* Publish sk_storage to sk.  sk->sk_lock cannot be acquired.
-	 * Hence, atomic ops is used to set sk->sk_bpf_storage
-	 * from NULL to the newly allocated sk_storage ptr.
+
+	owner_storage_ptr =
+		(struct bpf_local_storage **)owner_storage(smap, owner);
+	/* Publish storage to the owner.
+	 * Instead of using any lock of the kernel object (i.e. owner),
+	 * cmpxchg will work with any kernel object regardless what
+	 * the running context is, bh, irq...etc.
 	 *
-	 * From now on, the sk->sk_bpf_storage pointer is protected
-	 * by the sk_storage->lock.  Hence,  when freeing
-	 * the sk->sk_bpf_storage, the sk_storage->lock must
-	 * be held before setting sk->sk_bpf_storage to NULL.
+	 * From now on, the owner->storage pointer (e.g. sk->sk_bpf_storage)
+	 * is protected by the storage->lock.  Hence, when freeing
+	 * the owner->storage, the storage->lock must be held before
+	 * setting owner->storage ptr to NULL.
 	 */
-	prev_sk_storage = cmpxchg((struct bpf_local_storage **)&sk->sk_bpf_storage,
-				  NULL, sk_storage);
-	if (unlikely(prev_sk_storage)) {
+	prev_storage = cmpxchg(owner_storage_ptr, NULL, storage);
+	if (unlikely(prev_storage)) {
 		bpf_selem_unlink_map(first_selem);
 		err = -EAGAIN;
 		goto uncharge;
@@ -380,8 +411,8 @@ static int sk_storage_alloc(struct sock *sk,
 	return 0;
 
 uncharge:
-	kfree(sk_storage);
-	atomic_sub(sizeof(*sk_storage), &sk->sk_omem_alloc);
+	kfree(storage);
+	mem_uncharge(smap, owner, sizeof(*storage));
 	return err;
 }
 
@@ -390,38 +421,37 @@ uncharge:
  * Otherwise, it will become a leak (and other memory issues
  * during map destruction).
  */
-static struct bpf_local_storage_data *
-bpf_local_storage_update(struct sock *sk, struct bpf_map *map, void *value,
-			 u64 map_flags)
+struct bpf_local_storage_data *
+bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
+			 void *value, u64 map_flags)
 {
 	struct bpf_local_storage_data *old_sdata = NULL;
 	struct bpf_local_storage_elem *selem;
 	struct bpf_local_storage *local_storage;
-	struct bpf_local_storage_map *smap;
 	int err;
 
 	/* BPF_EXIST and BPF_NOEXIST cannot be both set */
 	if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST) ||
 	    /* BPF_F_LOCK can only be used in a value with spin_lock */
-	    unlikely((map_flags & BPF_F_LOCK) && !map_value_has_spin_lock(map)))
+	    unlikely((map_flags & BPF_F_LOCK) &&
+		     !map_value_has_spin_lock(&smap->map)))
 		return ERR_PTR(-EINVAL);
 
-	smap = (struct bpf_local_storage_map *)map;
-	local_storage = rcu_dereference(sk->sk_bpf_storage);
+	local_storage = rcu_dereference(*owner_storage(smap, owner));
 	if (!local_storage || hlist_empty(&local_storage->list)) {
 		/* Very first elem for the owner */
 		err = check_flags(NULL, map_flags);
 		if (err)
 			return ERR_PTR(err);
 
-		selem = bpf_selem_alloc(smap, sk, value, true);
+		selem = bpf_selem_alloc(smap, owner, value, true);
 		if (!selem)
 			return ERR_PTR(-ENOMEM);
 
-		err = sk_storage_alloc(sk, smap, selem);
+		err = bpf_local_storage_alloc(owner, smap, selem);
 		if (err) {
 			kfree(selem);
-			atomic_sub(smap->elem_size, &sk->sk_omem_alloc);
+			mem_uncharge(smap, owner, smap->elem_size);
 			return ERR_PTR(err);
 		}
 
@@ -439,7 +469,7 @@ bpf_local_storage_update(struct sock *sk, struct bpf_map *map, void *value,
 		if (err)
 			return ERR_PTR(err);
 		if (old_sdata && selem_linked_to_storage(SELEM(old_sdata))) {
-			copy_map_value_locked(map, old_sdata->data,
+			copy_map_value_locked(&smap->map, old_sdata->data,
 					      value, false);
 			return old_sdata;
 		}
@@ -464,7 +494,8 @@ bpf_local_storage_update(struct sock *sk, struct bpf_map *map, void *value,
 		goto unlock_err;
 
 	if (old_sdata && (map_flags & BPF_F_LOCK)) {
-		copy_map_value_locked(map, old_sdata->data, value, false);
+		copy_map_value_locked(&smap->map, old_sdata->data, value,
+				      false);
 		selem = SELEM(old_sdata);
 		goto unlock;
 	}
@@ -478,7 +509,7 @@ bpf_local_storage_update(struct sock *sk, struct bpf_map *map, void *value,
 	 * old_sdata will not be uncharged later during
 	 * bpf_selem_unlink_storage_nolock().
 	 */
-	selem = bpf_selem_alloc(smap, sk, value, !old_sdata);
+	selem = bpf_selem_alloc(smap, owner, value, !old_sdata);
 	if (!selem) {
 		err = -ENOMEM;
 		goto unlock_err;
@@ -591,17 +622,12 @@ void bpf_sk_storage_free(struct sock *sk)
 		kfree_rcu(sk_storage, rcu);
 }
 
-static void bpf_local_storage_map_free(struct bpf_map *map)
+void bpf_local_storage_map_free(struct bpf_local_storage_map *smap)
 {
 	struct bpf_local_storage_elem *selem;
-	struct bpf_local_storage_map *smap;
 	struct bpf_local_storage_map_bucket *b;
 	unsigned int i;
 
-	smap = (struct bpf_local_storage_map *)map;
-
-	bpf_local_storage_cache_idx_free(&sk_cache, smap->cache_idx);
-
 	/* Note that this map might be concurrently cloned from
 	 * bpf_sk_storage_clone. Wait for any existing bpf_sk_storage_clone
 	 * RCU read section to finish before proceeding. New RCU
@@ -646,7 +672,16 @@ static void bpf_local_storage_map_free(struct bpf_map *map)
 	synchronize_rcu();
 
 	kvfree(smap->buckets);
-	kfree(map);
+	kfree(smap);
+}
+
+static void sk_storage_map_free(struct bpf_map *map)
+{
+	struct bpf_local_storage_map *smap;
+
+	smap = (struct bpf_local_storage_map *)map;
+	bpf_local_storage_cache_idx_free(&sk_cache, smap->cache_idx);
+	bpf_local_storage_map_free(smap);
 }
 
 /* U16_MAX is much more than enough for sk local storage
@@ -658,7 +693,7 @@ static void bpf_local_storage_map_free(struct bpf_map *map)
 	       sizeof(struct bpf_local_storage_elem)),			\
 	      (U16_MAX - sizeof(struct bpf_local_storage_elem)))
 
-static int bpf_local_storage_map_alloc_check(union bpf_attr *attr)
+int bpf_local_storage_map_alloc_check(union bpf_attr *attr)
 {
 	if (attr->map_flags & ~BPF_LOCAL_STORAGE_CREATE_FLAG_MASK ||
 	    !(attr->map_flags & BPF_F_NO_PREALLOC) ||
@@ -677,7 +712,7 @@ static int bpf_local_storage_map_alloc_check(union bpf_attr *attr)
 	return 0;
 }
 
-static struct bpf_map *bpf_local_storage_map_alloc(union bpf_attr *attr)
+struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr)
 {
 	struct bpf_local_storage_map *smap;
 	unsigned int i;
@@ -717,8 +752,19 @@ static struct bpf_map *bpf_local_storage_map_alloc(union bpf_attr *attr)
 
 	smap->elem_size =
 		sizeof(struct bpf_local_storage_elem) + attr->value_size;
-	smap->cache_idx = bpf_local_storage_cache_idx_get(&sk_cache);
 
+	return smap;
+}
+
+static struct bpf_map *sk_storage_map_alloc(union bpf_attr *attr)
+{
+	struct bpf_local_storage_map *smap;
+
+	smap = bpf_local_storage_map_alloc(attr);
+	if (IS_ERR(smap))
+		return ERR_CAST(smap);
+
+	smap->cache_idx = bpf_local_storage_cache_idx_get(&sk_cache);
 	return &smap->map;
 }
 
@@ -728,10 +774,10 @@ static int notsupp_get_next_key(struct bpf_map *map, void *key,
 	return -ENOTSUPP;
 }
 
-static int bpf_local_storage_map_check_btf(const struct bpf_map *map,
-					   const struct btf *btf,
-					   const struct btf_type *key_type,
-					   const struct btf_type *value_type)
+int bpf_local_storage_map_check_btf(const struct bpf_map *map,
+				    const struct btf *btf,
+				    const struct btf_type *key_type,
+				    const struct btf_type *value_type)
 {
 	u32 int_data;
 
@@ -772,8 +818,9 @@ static int bpf_fd_sk_storage_update_elem(struct bpf_map *map, void *key,
 	fd = *(int *)key;
 	sock = sockfd_lookup(fd, &err);
 	if (sock) {
-		sdata = bpf_local_storage_update(sock->sk, map, value,
-						 map_flags);
+		sdata = bpf_local_storage_update(
+			sock->sk, (struct bpf_local_storage_map *)map, value,
+			map_flags);
 		sockfd_put(sock);
 		return PTR_ERR_OR_ZERO(sdata);
 	}
@@ -862,7 +909,7 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk)
 			bpf_selem_link_map(smap, copy_selem);
 			bpf_selem_link_storage_nolock(new_sk_storage, copy_selem);
 		} else {
-			ret = sk_storage_alloc(newsk, smap, copy_selem);
+			ret = bpf_local_storage_alloc(newsk, smap, copy_selem);
 			if (ret) {
 				kfree(copy_selem);
 				atomic_sub(smap->elem_size,
@@ -906,7 +953,9 @@ BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk,
 	     *  destruction).
 	     */
 	    refcount_inc_not_zero(&sk->sk_refcnt)) {
-		sdata = bpf_local_storage_update(sk, map, value, BPF_NOEXIST);
+		sdata = bpf_local_storage_update(
+			sk, (struct bpf_local_storage_map *)map, value,
+			BPF_NOEXIST);
 		/* sk must be a fullsock (guaranteed by verifier),
 		 * so sock_gen_put() is unnecessary.
 		 */
@@ -931,11 +980,33 @@ BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk)
 	return -ENOENT;
 }
 
+static int sk_storage_charge(struct bpf_local_storage_map *smap,
+			     void *owner, u32 size)
+{
+	return omem_charge(owner, size);
+}
+
+static void sk_storage_uncharge(struct bpf_local_storage_map *smap,
+				void *owner, u32 size)
+{
+	struct sock *sk = owner;
+
+	atomic_sub(size, &sk->sk_omem_alloc);
+}
+
+static struct bpf_local_storage __rcu **
+sk_storage_ptr(void *owner)
+{
+	struct sock *sk = owner;
+
+	return &sk->sk_bpf_storage;
+}
+
 static int sk_storage_map_btf_id;
 const struct bpf_map_ops sk_storage_map_ops = {
 	.map_alloc_check = bpf_local_storage_map_alloc_check,
-	.map_alloc = bpf_local_storage_map_alloc,
-	.map_free = bpf_local_storage_map_free,
+	.map_alloc = sk_storage_map_alloc,
+	.map_free = sk_storage_map_free,
 	.map_get_next_key = notsupp_get_next_key,
 	.map_lookup_elem = bpf_fd_sk_storage_lookup_elem,
 	.map_update_elem = bpf_fd_sk_storage_update_elem,
@@ -943,6 +1014,9 @@ const struct bpf_map_ops sk_storage_map_ops = {
 	.map_check_btf = bpf_local_storage_map_check_btf,
 	.map_btf_name = "bpf_local_storage_map",
 	.map_btf_id = &sk_storage_map_btf_id,
+	.map_local_storage_charge = sk_storage_charge,
+	.map_local_storage_uncharge = sk_storage_uncharge,
+	.map_owner_storage_ptr = sk_storage_ptr,
 };
 
 const struct bpf_func_proto bpf_sk_storage_get_proto = {
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 544b89a64918..2cbd137eed86 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3765,9 +3765,13 @@ enum {
 	BPF_F_SYSCTL_BASE_NAME		= (1ULL << 0),
 };
 
-/* BPF_FUNC_sk_storage_get flags */
+/* BPF_FUNC_<kernel_obj>_storage_get flags */
 enum {
-	BPF_SK_STORAGE_GET_F_CREATE	= (1ULL << 0),
+	BPF_LOCAL_STORAGE_GET_F_CREATE	= (1ULL << 0),
+	/* BPF_SK_STORAGE_GET_F_CREATE is only kept for backward compatibility
+	 * and BPF_LOCAL_STORAGE_GET_F_CREATE must be used instead.
+	 */
+	BPF_SK_STORAGE_GET_F_CREATE  = BPF_LOCAL_STORAGE_GET_F_CREATE,
 };
 
 /* BPF_FUNC_read_branch_records flags. */
-- 
cgit v1.2.3


From 450af8d0f6be2e7dd2a528a3fb054bb726bf1747 Mon Sep 17 00:00:00 2001
From: KP Singh <kpsingh@google.com>
Date: Tue, 25 Aug 2020 20:29:16 +0200
Subject: bpf: Split bpf_local_storage to bpf_sk_storage

A purely mechanical change:

	bpf_sk_storage.c = bpf_sk_storage.c + bpf_local_storage.c
	bpf_sk_storage.h = bpf_sk_storage.h + bpf_local_storage.h

Signed-off-by: KP Singh <kpsingh@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200825182919.1118197-5-kpsingh@chromium.org
---
 include/linux/bpf_local_storage.h | 163 +++++++++
 include/net/bpf_sk_storage.h      |  61 +---
 kernel/bpf/Makefile               |   1 +
 kernel/bpf/bpf_local_storage.c    | 600 ++++++++++++++++++++++++++++++++++
 net/core/bpf_sk_storage.c         | 672 +-------------------------------------
 5 files changed, 766 insertions(+), 731 deletions(-)
 create mode 100644 include/linux/bpf_local_storage.h
 create mode 100644 kernel/bpf/bpf_local_storage.c

(limited to 'include/linux')

diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h
new file mode 100644
index 000000000000..b2c9463f36a1
--- /dev/null
+++ b/include/linux/bpf_local_storage.h
@@ -0,0 +1,163 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2019 Facebook
+ * Copyright 2020 Google LLC.
+ */
+
+#ifndef _BPF_LOCAL_STORAGE_H
+#define _BPF_LOCAL_STORAGE_H
+
+#include <linux/bpf.h>
+#include <linux/rculist.h>
+#include <linux/list.h>
+#include <linux/hash.h>
+#include <linux/types.h>
+#include <uapi/linux/btf.h>
+
+#define BPF_LOCAL_STORAGE_CACHE_SIZE	16
+
+struct bpf_local_storage_map_bucket {
+	struct hlist_head list;
+	raw_spinlock_t lock;
+};
+
+/* Thp map is not the primary owner of a bpf_local_storage_elem.
+ * Instead, the container object (eg. sk->sk_bpf_storage) is.
+ *
+ * The map (bpf_local_storage_map) is for two purposes
+ * 1. Define the size of the "local storage".  It is
+ *    the map's value_size.
+ *
+ * 2. Maintain a list to keep track of all elems such
+ *    that they can be cleaned up during the map destruction.
+ *
+ * When a bpf local storage is being looked up for a
+ * particular object,  the "bpf_map" pointer is actually used
+ * as the "key" to search in the list of elem in
+ * the respective bpf_local_storage owned by the object.
+ *
+ * e.g. sk->sk_bpf_storage is the mini-map with the "bpf_map" pointer
+ * as the searching key.
+ */
+struct bpf_local_storage_map {
+	struct bpf_map map;
+	/* Lookup elem does not require accessing the map.
+	 *
+	 * Updating/Deleting requires a bucket lock to
+	 * link/unlink the elem from the map.  Having
+	 * multiple buckets to improve contention.
+	 */
+	struct bpf_local_storage_map_bucket *buckets;
+	u32 bucket_log;
+	u16 elem_size;
+	u16 cache_idx;
+};
+
+struct bpf_local_storage_data {
+	/* smap is used as the searching key when looking up
+	 * from the object's bpf_local_storage.
+	 *
+	 * Put it in the same cacheline as the data to minimize
+	 * the number of cachelines access during the cache hit case.
+	 */
+	struct bpf_local_storage_map __rcu *smap;
+	u8 data[] __aligned(8);
+};
+
+/* Linked to bpf_local_storage and bpf_local_storage_map */
+struct bpf_local_storage_elem {
+	struct hlist_node map_node;	/* Linked to bpf_local_storage_map */
+	struct hlist_node snode;	/* Linked to bpf_local_storage */
+	struct bpf_local_storage __rcu *local_storage;
+	struct rcu_head rcu;
+	/* 8 bytes hole */
+	/* The data is stored in aother cacheline to minimize
+	 * the number of cachelines access during a cache hit.
+	 */
+	struct bpf_local_storage_data sdata ____cacheline_aligned;
+};
+
+struct bpf_local_storage {
+	struct bpf_local_storage_data __rcu *cache[BPF_LOCAL_STORAGE_CACHE_SIZE];
+	struct hlist_head list; /* List of bpf_local_storage_elem */
+	void *owner;		/* The object that owns the above "list" of
+				 * bpf_local_storage_elem.
+				 */
+	struct rcu_head rcu;
+	raw_spinlock_t lock;	/* Protect adding/removing from the "list" */
+};
+
+/* U16_MAX is much more than enough for sk local storage
+ * considering a tcp_sock is ~2k.
+ */
+#define BPF_LOCAL_STORAGE_MAX_VALUE_SIZE				       \
+	min_t(u32,                                                             \
+	      (KMALLOC_MAX_SIZE - MAX_BPF_STACK -                              \
+	       sizeof(struct bpf_local_storage_elem)),                         \
+	      (U16_MAX - sizeof(struct bpf_local_storage_elem)))
+
+#define SELEM(_SDATA)                                                          \
+	container_of((_SDATA), struct bpf_local_storage_elem, sdata)
+#define SDATA(_SELEM) (&(_SELEM)->sdata)
+
+#define BPF_LOCAL_STORAGE_CACHE_SIZE	16
+
+struct bpf_local_storage_cache {
+	spinlock_t idx_lock;
+	u64 idx_usage_counts[BPF_LOCAL_STORAGE_CACHE_SIZE];
+};
+
+#define DEFINE_BPF_STORAGE_CACHE(name)				\
+static struct bpf_local_storage_cache name = {			\
+	.idx_lock = __SPIN_LOCK_UNLOCKED(name.idx_lock),	\
+}
+
+u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache);
+void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache,
+				      u16 idx);
+
+/* Helper functions for bpf_local_storage */
+int bpf_local_storage_map_alloc_check(union bpf_attr *attr);
+
+struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr);
+
+struct bpf_local_storage_data *
+bpf_local_storage_lookup(struct bpf_local_storage *local_storage,
+			 struct bpf_local_storage_map *smap,
+			 bool cacheit_lockit);
+
+void bpf_local_storage_map_free(struct bpf_local_storage_map *smap);
+
+int bpf_local_storage_map_check_btf(const struct bpf_map *map,
+				    const struct btf *btf,
+				    const struct btf_type *key_type,
+				    const struct btf_type *value_type);
+
+void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage,
+				   struct bpf_local_storage_elem *selem);
+
+bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage,
+				     struct bpf_local_storage_elem *selem,
+				     bool uncharge_omem);
+
+void bpf_selem_unlink(struct bpf_local_storage_elem *selem);
+
+void bpf_selem_link_map(struct bpf_local_storage_map *smap,
+			struct bpf_local_storage_elem *selem);
+
+void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem);
+
+struct bpf_local_storage_elem *
+bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, void *value,
+		bool charge_mem);
+
+int
+bpf_local_storage_alloc(void *owner,
+			struct bpf_local_storage_map *smap,
+			struct bpf_local_storage_elem *first_selem);
+
+struct bpf_local_storage_data *
+bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
+			 void *value, u64 map_flags);
+
+#endif /* _BPF_LOCAL_STORAGE_H */
diff --git a/include/net/bpf_sk_storage.h b/include/net/bpf_sk_storage.h
index 9e631b5466e3..3c516dd07caf 100644
--- a/include/net/bpf_sk_storage.h
+++ b/include/net/bpf_sk_storage.h
@@ -12,6 +12,7 @@
 #include <net/sock.h>
 #include <uapi/linux/sock_diag.h>
 #include <uapi/linux/btf.h>
+#include <linux/bpf_local_storage.h>
 
 struct sock;
 
@@ -26,66 +27,6 @@ struct sk_buff;
 struct nlattr;
 struct sock;
 
-#define BPF_LOCAL_STORAGE_CACHE_SIZE	16
-
-struct bpf_local_storage_cache {
-	spinlock_t idx_lock;
-	u64 idx_usage_counts[BPF_LOCAL_STORAGE_CACHE_SIZE];
-};
-
-#define DEFINE_BPF_STORAGE_CACHE(name)				\
-static struct bpf_local_storage_cache name = {			\
-	.idx_lock = __SPIN_LOCK_UNLOCKED(name.idx_lock),	\
-}
-
-u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache);
-void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache,
-				      u16 idx);
-
-/* Helper functions for bpf_local_storage */
-int bpf_local_storage_map_alloc_check(union bpf_attr *attr);
-
-struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr);
-
-struct bpf_local_storage_data *
-bpf_local_storage_lookup(struct bpf_local_storage *local_storage,
-			 struct bpf_local_storage_map *smap,
-			 bool cacheit_lockit);
-
-void bpf_local_storage_map_free(struct bpf_local_storage_map *smap);
-
-int bpf_local_storage_map_check_btf(const struct bpf_map *map,
-				    const struct btf *btf,
-				    const struct btf_type *key_type,
-				    const struct btf_type *value_type);
-
-void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage,
-				   struct bpf_local_storage_elem *selem);
-
-bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage,
-				     struct bpf_local_storage_elem *selem,
-				     bool uncharge_omem);
-
-void bpf_selem_unlink(struct bpf_local_storage_elem *selem);
-
-void bpf_selem_link_map(struct bpf_local_storage_map *smap,
-			struct bpf_local_storage_elem *selem);
-
-void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem);
-
-struct bpf_local_storage_elem *
-bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, void *value,
-		bool charge_mem);
-
-int
-bpf_local_storage_alloc(void *owner,
-			struct bpf_local_storage_map *smap,
-			struct bpf_local_storage_elem *first_selem);
-
-struct bpf_local_storage_data *
-bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
-			 void *value, u64 map_flags);
-
 #ifdef CONFIG_BPF_SYSCALL
 int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk);
 struct bpf_sk_storage_diag *
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 19e137aae40e..6961ff400cba 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -12,6 +12,7 @@ obj-$(CONFIG_BPF_JIT) += dispatcher.o
 ifeq ($(CONFIG_NET),y)
 obj-$(CONFIG_BPF_SYSCALL) += devmap.o
 obj-$(CONFIG_BPF_SYSCALL) += cpumap.o
+obj-$(CONFIG_BPF_SYSCALL) += bpf_local_storage.o
 obj-$(CONFIG_BPF_SYSCALL) += offload.o
 obj-$(CONFIG_BPF_SYSCALL) += net_namespace.o
 endif
diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
new file mode 100644
index 000000000000..ffa7d11fc2bd
--- /dev/null
+++ b/kernel/bpf/bpf_local_storage.c
@@ -0,0 +1,600 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook  */
+#include <linux/rculist.h>
+#include <linux/list.h>
+#include <linux/hash.h>
+#include <linux/types.h>
+#include <linux/spinlock.h>
+#include <linux/bpf.h>
+#include <linux/btf_ids.h>
+#include <linux/bpf_local_storage.h>
+#include <net/sock.h>
+#include <uapi/linux/sock_diag.h>
+#include <uapi/linux/btf.h>
+
+#define BPF_LOCAL_STORAGE_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_CLONE)
+
+static struct bpf_local_storage_map_bucket *
+select_bucket(struct bpf_local_storage_map *smap,
+	      struct bpf_local_storage_elem *selem)
+{
+	return &smap->buckets[hash_ptr(selem, smap->bucket_log)];
+}
+
+static int mem_charge(struct bpf_local_storage_map *smap, void *owner, u32 size)
+{
+	struct bpf_map *map = &smap->map;
+
+	if (!map->ops->map_local_storage_charge)
+		return 0;
+
+	return map->ops->map_local_storage_charge(smap, owner, size);
+}
+
+static void mem_uncharge(struct bpf_local_storage_map *smap, void *owner,
+			 u32 size)
+{
+	struct bpf_map *map = &smap->map;
+
+	if (map->ops->map_local_storage_uncharge)
+		map->ops->map_local_storage_uncharge(smap, owner, size);
+}
+
+static struct bpf_local_storage __rcu **
+owner_storage(struct bpf_local_storage_map *smap, void *owner)
+{
+	struct bpf_map *map = &smap->map;
+
+	return map->ops->map_owner_storage_ptr(owner);
+}
+
+static bool selem_linked_to_storage(const struct bpf_local_storage_elem *selem)
+{
+	return !hlist_unhashed(&selem->snode);
+}
+
+static bool selem_linked_to_map(const struct bpf_local_storage_elem *selem)
+{
+	return !hlist_unhashed(&selem->map_node);
+}
+
+struct bpf_local_storage_elem *
+bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner,
+		void *value, bool charge_mem)
+{
+	struct bpf_local_storage_elem *selem;
+
+	if (charge_mem && mem_charge(smap, owner, smap->elem_size))
+		return NULL;
+
+	selem = kzalloc(smap->elem_size, GFP_ATOMIC | __GFP_NOWARN);
+	if (selem) {
+		if (value)
+			memcpy(SDATA(selem)->data, value, smap->map.value_size);
+		return selem;
+	}
+
+	if (charge_mem)
+		mem_uncharge(smap, owner, smap->elem_size);
+
+	return NULL;
+}
+
+/* local_storage->lock must be held and selem->local_storage == local_storage.
+ * The caller must ensure selem->smap is still valid to be
+ * dereferenced for its smap->elem_size and smap->cache_idx.
+ */
+bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage,
+				     struct bpf_local_storage_elem *selem,
+				     bool uncharge_mem)
+{
+	struct bpf_local_storage_map *smap;
+	bool free_local_storage;
+	void *owner;
+
+	smap = rcu_dereference(SDATA(selem)->smap);
+	owner = local_storage->owner;
+
+	/* All uncharging on the owner must be done first.
+	 * The owner may be freed once the last selem is unlinked
+	 * from local_storage.
+	 */
+	if (uncharge_mem)
+		mem_uncharge(smap, owner, smap->elem_size);
+
+	free_local_storage = hlist_is_singular_node(&selem->snode,
+						    &local_storage->list);
+	if (free_local_storage) {
+		mem_uncharge(smap, owner, sizeof(struct bpf_local_storage));
+		local_storage->owner = NULL;
+
+		/* After this RCU_INIT, owner may be freed and cannot be used */
+		RCU_INIT_POINTER(*owner_storage(smap, owner), NULL);
+
+		/* local_storage is not freed now.  local_storage->lock is
+		 * still held and raw_spin_unlock_bh(&local_storage->lock)
+		 * will be done by the caller.
+		 *
+		 * Although the unlock will be done under
+		 * rcu_read_lock(),  it is more intutivie to
+		 * read if kfree_rcu(local_storage, rcu) is done
+		 * after the raw_spin_unlock_bh(&local_storage->lock).
+		 *
+		 * Hence, a "bool free_local_storage" is returned
+		 * to the caller which then calls the kfree_rcu()
+		 * after unlock.
+		 */
+	}
+	hlist_del_init_rcu(&selem->snode);
+	if (rcu_access_pointer(local_storage->cache[smap->cache_idx]) ==
+	    SDATA(selem))
+		RCU_INIT_POINTER(local_storage->cache[smap->cache_idx], NULL);
+
+	kfree_rcu(selem, rcu);
+
+	return free_local_storage;
+}
+
+static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem)
+{
+	struct bpf_local_storage *local_storage;
+	bool free_local_storage = false;
+
+	if (unlikely(!selem_linked_to_storage(selem)))
+		/* selem has already been unlinked from sk */
+		return;
+
+	local_storage = rcu_dereference(selem->local_storage);
+	raw_spin_lock_bh(&local_storage->lock);
+	if (likely(selem_linked_to_storage(selem)))
+		free_local_storage = bpf_selem_unlink_storage_nolock(
+			local_storage, selem, true);
+	raw_spin_unlock_bh(&local_storage->lock);
+
+	if (free_local_storage)
+		kfree_rcu(local_storage, rcu);
+}
+
+void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage,
+				   struct bpf_local_storage_elem *selem)
+{
+	RCU_INIT_POINTER(selem->local_storage, local_storage);
+	hlist_add_head(&selem->snode, &local_storage->list);
+}
+
+void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem)
+{
+	struct bpf_local_storage_map *smap;
+	struct bpf_local_storage_map_bucket *b;
+
+	if (unlikely(!selem_linked_to_map(selem)))
+		/* selem has already be unlinked from smap */
+		return;
+
+	smap = rcu_dereference(SDATA(selem)->smap);
+	b = select_bucket(smap, selem);
+	raw_spin_lock_bh(&b->lock);
+	if (likely(selem_linked_to_map(selem)))
+		hlist_del_init_rcu(&selem->map_node);
+	raw_spin_unlock_bh(&b->lock);
+}
+
+void bpf_selem_link_map(struct bpf_local_storage_map *smap,
+			struct bpf_local_storage_elem *selem)
+{
+	struct bpf_local_storage_map_bucket *b = select_bucket(smap, selem);
+
+	raw_spin_lock_bh(&b->lock);
+	RCU_INIT_POINTER(SDATA(selem)->smap, smap);
+	hlist_add_head_rcu(&selem->map_node, &b->list);
+	raw_spin_unlock_bh(&b->lock);
+}
+
+void bpf_selem_unlink(struct bpf_local_storage_elem *selem)
+{
+	/* Always unlink from map before unlinking from local_storage
+	 * because selem will be freed after successfully unlinked from
+	 * the local_storage.
+	 */
+	bpf_selem_unlink_map(selem);
+	__bpf_selem_unlink_storage(selem);
+}
+
+struct bpf_local_storage_data *
+bpf_local_storage_lookup(struct bpf_local_storage *local_storage,
+			 struct bpf_local_storage_map *smap,
+			 bool cacheit_lockit)
+{
+	struct bpf_local_storage_data *sdata;
+	struct bpf_local_storage_elem *selem;
+
+	/* Fast path (cache hit) */
+	sdata = rcu_dereference(local_storage->cache[smap->cache_idx]);
+	if (sdata && rcu_access_pointer(sdata->smap) == smap)
+		return sdata;
+
+	/* Slow path (cache miss) */
+	hlist_for_each_entry_rcu(selem, &local_storage->list, snode)
+		if (rcu_access_pointer(SDATA(selem)->smap) == smap)
+			break;
+
+	if (!selem)
+		return NULL;
+
+	sdata = SDATA(selem);
+	if (cacheit_lockit) {
+		/* spinlock is needed to avoid racing with the
+		 * parallel delete.  Otherwise, publishing an already
+		 * deleted sdata to the cache will become a use-after-free
+		 * problem in the next bpf_local_storage_lookup().
+		 */
+		raw_spin_lock_bh(&local_storage->lock);
+		if (selem_linked_to_storage(selem))
+			rcu_assign_pointer(local_storage->cache[smap->cache_idx],
+					   sdata);
+		raw_spin_unlock_bh(&local_storage->lock);
+	}
+
+	return sdata;
+}
+
+static int check_flags(const struct bpf_local_storage_data *old_sdata,
+		       u64 map_flags)
+{
+	if (old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST)
+		/* elem already exists */
+		return -EEXIST;
+
+	if (!old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_EXIST)
+		/* elem doesn't exist, cannot update it */
+		return -ENOENT;
+
+	return 0;
+}
+
+int bpf_local_storage_alloc(void *owner,
+			    struct bpf_local_storage_map *smap,
+			    struct bpf_local_storage_elem *first_selem)
+{
+	struct bpf_local_storage *prev_storage, *storage;
+	struct bpf_local_storage **owner_storage_ptr;
+	int err;
+
+	err = mem_charge(smap, owner, sizeof(*storage));
+	if (err)
+		return err;
+
+	storage = kzalloc(sizeof(*storage), GFP_ATOMIC | __GFP_NOWARN);
+	if (!storage) {
+		err = -ENOMEM;
+		goto uncharge;
+	}
+
+	INIT_HLIST_HEAD(&storage->list);
+	raw_spin_lock_init(&storage->lock);
+	storage->owner = owner;
+
+	bpf_selem_link_storage_nolock(storage, first_selem);
+	bpf_selem_link_map(smap, first_selem);
+
+	owner_storage_ptr =
+		(struct bpf_local_storage **)owner_storage(smap, owner);
+	/* Publish storage to the owner.
+	 * Instead of using any lock of the kernel object (i.e. owner),
+	 * cmpxchg will work with any kernel object regardless what
+	 * the running context is, bh, irq...etc.
+	 *
+	 * From now on, the owner->storage pointer (e.g. sk->sk_bpf_storage)
+	 * is protected by the storage->lock.  Hence, when freeing
+	 * the owner->storage, the storage->lock must be held before
+	 * setting owner->storage ptr to NULL.
+	 */
+	prev_storage = cmpxchg(owner_storage_ptr, NULL, storage);
+	if (unlikely(prev_storage)) {
+		bpf_selem_unlink_map(first_selem);
+		err = -EAGAIN;
+		goto uncharge;
+
+		/* Note that even first_selem was linked to smap's
+		 * bucket->list, first_selem can be freed immediately
+		 * (instead of kfree_rcu) because
+		 * bpf_local_storage_map_free() does a
+		 * synchronize_rcu() before walking the bucket->list.
+		 * Hence, no one is accessing selem from the
+		 * bucket->list under rcu_read_lock().
+		 */
+	}
+
+	return 0;
+
+uncharge:
+	kfree(storage);
+	mem_uncharge(smap, owner, sizeof(*storage));
+	return err;
+}
+
+/* sk cannot be going away because it is linking new elem
+ * to sk->sk_bpf_storage. (i.e. sk->sk_refcnt cannot be 0).
+ * Otherwise, it will become a leak (and other memory issues
+ * during map destruction).
+ */
+struct bpf_local_storage_data *
+bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
+			 void *value, u64 map_flags)
+{
+	struct bpf_local_storage_data *old_sdata = NULL;
+	struct bpf_local_storage_elem *selem;
+	struct bpf_local_storage *local_storage;
+	int err;
+
+	/* BPF_EXIST and BPF_NOEXIST cannot be both set */
+	if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST) ||
+	    /* BPF_F_LOCK can only be used in a value with spin_lock */
+	    unlikely((map_flags & BPF_F_LOCK) &&
+		     !map_value_has_spin_lock(&smap->map)))
+		return ERR_PTR(-EINVAL);
+
+	local_storage = rcu_dereference(*owner_storage(smap, owner));
+	if (!local_storage || hlist_empty(&local_storage->list)) {
+		/* Very first elem for the owner */
+		err = check_flags(NULL, map_flags);
+		if (err)
+			return ERR_PTR(err);
+
+		selem = bpf_selem_alloc(smap, owner, value, true);
+		if (!selem)
+			return ERR_PTR(-ENOMEM);
+
+		err = bpf_local_storage_alloc(owner, smap, selem);
+		if (err) {
+			kfree(selem);
+			mem_uncharge(smap, owner, smap->elem_size);
+			return ERR_PTR(err);
+		}
+
+		return SDATA(selem);
+	}
+
+	if ((map_flags & BPF_F_LOCK) && !(map_flags & BPF_NOEXIST)) {
+		/* Hoping to find an old_sdata to do inline update
+		 * such that it can avoid taking the local_storage->lock
+		 * and changing the lists.
+		 */
+		old_sdata =
+			bpf_local_storage_lookup(local_storage, smap, false);
+		err = check_flags(old_sdata, map_flags);
+		if (err)
+			return ERR_PTR(err);
+		if (old_sdata && selem_linked_to_storage(SELEM(old_sdata))) {
+			copy_map_value_locked(&smap->map, old_sdata->data,
+					      value, false);
+			return old_sdata;
+		}
+	}
+
+	raw_spin_lock_bh(&local_storage->lock);
+
+	/* Recheck local_storage->list under local_storage->lock */
+	if (unlikely(hlist_empty(&local_storage->list))) {
+		/* A parallel del is happening and local_storage is going
+		 * away.  It has just been checked before, so very
+		 * unlikely.  Return instead of retry to keep things
+		 * simple.
+		 */
+		err = -EAGAIN;
+		goto unlock_err;
+	}
+
+	old_sdata = bpf_local_storage_lookup(local_storage, smap, false);
+	err = check_flags(old_sdata, map_flags);
+	if (err)
+		goto unlock_err;
+
+	if (old_sdata && (map_flags & BPF_F_LOCK)) {
+		copy_map_value_locked(&smap->map, old_sdata->data, value,
+				      false);
+		selem = SELEM(old_sdata);
+		goto unlock;
+	}
+
+	/* local_storage->lock is held.  Hence, we are sure
+	 * we can unlink and uncharge the old_sdata successfully
+	 * later.  Hence, instead of charging the new selem now
+	 * and then uncharge the old selem later (which may cause
+	 * a potential but unnecessary charge failure),  avoid taking
+	 * a charge at all here (the "!old_sdata" check) and the
+	 * old_sdata will not be uncharged later during
+	 * bpf_selem_unlink_storage_nolock().
+	 */
+	selem = bpf_selem_alloc(smap, owner, value, !old_sdata);
+	if (!selem) {
+		err = -ENOMEM;
+		goto unlock_err;
+	}
+
+	/* First, link the new selem to the map */
+	bpf_selem_link_map(smap, selem);
+
+	/* Second, link (and publish) the new selem to local_storage */
+	bpf_selem_link_storage_nolock(local_storage, selem);
+
+	/* Third, remove old selem, SELEM(old_sdata) */
+	if (old_sdata) {
+		bpf_selem_unlink_map(SELEM(old_sdata));
+		bpf_selem_unlink_storage_nolock(local_storage, SELEM(old_sdata),
+						false);
+	}
+
+unlock:
+	raw_spin_unlock_bh(&local_storage->lock);
+	return SDATA(selem);
+
+unlock_err:
+	raw_spin_unlock_bh(&local_storage->lock);
+	return ERR_PTR(err);
+}
+
+u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache)
+{
+	u64 min_usage = U64_MAX;
+	u16 i, res = 0;
+
+	spin_lock(&cache->idx_lock);
+
+	for (i = 0; i < BPF_LOCAL_STORAGE_CACHE_SIZE; i++) {
+		if (cache->idx_usage_counts[i] < min_usage) {
+			min_usage = cache->idx_usage_counts[i];
+			res = i;
+
+			/* Found a free cache_idx */
+			if (!min_usage)
+				break;
+		}
+	}
+	cache->idx_usage_counts[res]++;
+
+	spin_unlock(&cache->idx_lock);
+
+	return res;
+}
+
+void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache,
+				      u16 idx)
+{
+	spin_lock(&cache->idx_lock);
+	cache->idx_usage_counts[idx]--;
+	spin_unlock(&cache->idx_lock);
+}
+
+void bpf_local_storage_map_free(struct bpf_local_storage_map *smap)
+{
+	struct bpf_local_storage_elem *selem;
+	struct bpf_local_storage_map_bucket *b;
+	unsigned int i;
+
+	/* Note that this map might be concurrently cloned from
+	 * bpf_sk_storage_clone. Wait for any existing bpf_sk_storage_clone
+	 * RCU read section to finish before proceeding. New RCU
+	 * read sections should be prevented via bpf_map_inc_not_zero.
+	 */
+	synchronize_rcu();
+
+	/* bpf prog and the userspace can no longer access this map
+	 * now.  No new selem (of this map) can be added
+	 * to the owner->storage or to the map bucket's list.
+	 *
+	 * The elem of this map can be cleaned up here
+	 * or when the storage is freed e.g.
+	 * by bpf_sk_storage_free() during __sk_destruct().
+	 */
+	for (i = 0; i < (1U << smap->bucket_log); i++) {
+		b = &smap->buckets[i];
+
+		rcu_read_lock();
+		/* No one is adding to b->list now */
+		while ((selem = hlist_entry_safe(
+				rcu_dereference_raw(hlist_first_rcu(&b->list)),
+				struct bpf_local_storage_elem, map_node))) {
+			bpf_selem_unlink(selem);
+			cond_resched_rcu();
+		}
+		rcu_read_unlock();
+	}
+
+	/* While freeing the storage we may still need to access the map.
+	 *
+	 * e.g. when bpf_sk_storage_free() has unlinked selem from the map
+	 * which then made the above while((selem = ...)) loop
+	 * exit immediately.
+	 *
+	 * However, while freeing the storage one still needs to access the
+	 * smap->elem_size to do the uncharging in
+	 * bpf_selem_unlink_storage_nolock().
+	 *
+	 * Hence, wait another rcu grace period for the storage to be freed.
+	 */
+	synchronize_rcu();
+
+	kvfree(smap->buckets);
+	kfree(smap);
+}
+
+int bpf_local_storage_map_alloc_check(union bpf_attr *attr)
+{
+	if (attr->map_flags & ~BPF_LOCAL_STORAGE_CREATE_FLAG_MASK ||
+	    !(attr->map_flags & BPF_F_NO_PREALLOC) ||
+	    attr->max_entries ||
+	    attr->key_size != sizeof(int) || !attr->value_size ||
+	    /* Enforce BTF for userspace sk dumping */
+	    !attr->btf_key_type_id || !attr->btf_value_type_id)
+		return -EINVAL;
+
+	if (!bpf_capable())
+		return -EPERM;
+
+	if (attr->value_size > BPF_LOCAL_STORAGE_MAX_VALUE_SIZE)
+		return -E2BIG;
+
+	return 0;
+}
+
+struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr)
+{
+	struct bpf_local_storage_map *smap;
+	unsigned int i;
+	u32 nbuckets;
+	u64 cost;
+	int ret;
+
+	smap = kzalloc(sizeof(*smap), GFP_USER | __GFP_NOWARN);
+	if (!smap)
+		return ERR_PTR(-ENOMEM);
+	bpf_map_init_from_attr(&smap->map, attr);
+
+	nbuckets = roundup_pow_of_two(num_possible_cpus());
+	/* Use at least 2 buckets, select_bucket() is undefined behavior with 1 bucket */
+	nbuckets = max_t(u32, 2, nbuckets);
+	smap->bucket_log = ilog2(nbuckets);
+	cost = sizeof(*smap->buckets) * nbuckets + sizeof(*smap);
+
+	ret = bpf_map_charge_init(&smap->map.memory, cost);
+	if (ret < 0) {
+		kfree(smap);
+		return ERR_PTR(ret);
+	}
+
+	smap->buckets = kvcalloc(sizeof(*smap->buckets), nbuckets,
+				 GFP_USER | __GFP_NOWARN);
+	if (!smap->buckets) {
+		bpf_map_charge_finish(&smap->map.memory);
+		kfree(smap);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	for (i = 0; i < nbuckets; i++) {
+		INIT_HLIST_HEAD(&smap->buckets[i].list);
+		raw_spin_lock_init(&smap->buckets[i].lock);
+	}
+
+	smap->elem_size =
+		sizeof(struct bpf_local_storage_elem) + attr->value_size;
+
+	return smap;
+}
+
+int bpf_local_storage_map_check_btf(const struct bpf_map *map,
+				    const struct btf *btf,
+				    const struct btf_type *key_type,
+				    const struct btf_type *value_type)
+{
+	u32 int_data;
+
+	if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
+		return -EINVAL;
+
+	int_data = *(u32 *)(key_type + 1);
+	if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data))
+		return -EINVAL;
+
+	return 0;
+}
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index cd8b7017913b..f29d9a9b4ea4 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -7,97 +7,14 @@
 #include <linux/spinlock.h>
 #include <linux/bpf.h>
 #include <linux/btf_ids.h>
+#include <linux/bpf_local_storage.h>
 #include <net/bpf_sk_storage.h>
 #include <net/sock.h>
 #include <uapi/linux/sock_diag.h>
 #include <uapi/linux/btf.h>
 
-#define BPF_LOCAL_STORAGE_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_CLONE)
-
 DEFINE_BPF_STORAGE_CACHE(sk_cache);
 
-struct bpf_local_storage_map_bucket {
-	struct hlist_head list;
-	raw_spinlock_t lock;
-};
-
-/* Thp map is not the primary owner of a bpf_local_storage_elem.
- * Instead, the container object (eg. sk->sk_bpf_storage) is.
- *
- * The map (bpf_local_storage_map) is for two purposes
- * 1. Define the size of the "local storage".  It is
- *    the map's value_size.
- *
- * 2. Maintain a list to keep track of all elems such
- *    that they can be cleaned up during the map destruction.
- *
- * When a bpf local storage is being looked up for a
- * particular object,  the "bpf_map" pointer is actually used
- * as the "key" to search in the list of elem in
- * the respective bpf_local_storage owned by the object.
- *
- * e.g. sk->sk_bpf_storage is the mini-map with the "bpf_map" pointer
- * as the searching key.
- */
-struct bpf_local_storage_map {
-	struct bpf_map map;
-	/* Lookup elem does not require accessing the map.
-	 *
-	 * Updating/Deleting requires a bucket lock to
-	 * link/unlink the elem from the map.  Having
-	 * multiple buckets to improve contention.
-	 */
-	struct bpf_local_storage_map_bucket *buckets;
-	u32 bucket_log;
-	u16 elem_size;
-	u16 cache_idx;
-};
-
-struct bpf_local_storage_data {
-	/* smap is used as the searching key when looking up
-	 * from the object's bpf_local_storage.
-	 *
-	 * Put it in the same cacheline as the data to minimize
-	 * the number of cachelines access during the cache hit case.
-	 */
-	struct bpf_local_storage_map __rcu *smap;
-	u8 data[] __aligned(8);
-};
-
-/* Linked to bpf_local_storage and bpf_local_storage_map */
-struct bpf_local_storage_elem {
-	struct hlist_node map_node;	/* Linked to bpf_local_storage_map */
-	struct hlist_node snode;	/* Linked to bpf_local_storage */
-	struct bpf_local_storage __rcu *local_storage;
-	struct rcu_head rcu;
-	/* 8 bytes hole */
-	/* The data is stored in aother cacheline to minimize
-	 * the number of cachelines access during a cache hit.
-	 */
-	struct bpf_local_storage_data sdata ____cacheline_aligned;
-};
-
-#define SELEM(_SDATA)							\
-	container_of((_SDATA), struct bpf_local_storage_elem, sdata)
-#define SDATA(_SELEM) (&(_SELEM)->sdata)
-
-struct bpf_local_storage {
-	struct bpf_local_storage_data __rcu *cache[BPF_LOCAL_STORAGE_CACHE_SIZE];
-	struct hlist_head list; /* List of bpf_local_storage_elem */
-	void *owner;		/* The object that owns the above "list" of
-				 * bpf_local_storage_elem.
-				 */
-	struct rcu_head rcu;
-	raw_spinlock_t lock;	/* Protect adding/removing from the "list" */
-};
-
-static struct bpf_local_storage_map_bucket *
-select_bucket(struct bpf_local_storage_map *smap,
-	      struct bpf_local_storage_elem *selem)
-{
-	return &smap->buckets[hash_ptr(selem, smap->bucket_log)];
-}
-
 static int omem_charge(struct sock *sk, unsigned int size)
 {
 	/* same check as in sock_kmalloc() */
@@ -110,223 +27,6 @@ static int omem_charge(struct sock *sk, unsigned int size)
 	return -ENOMEM;
 }
 
-static int mem_charge(struct bpf_local_storage_map *smap, void *owner, u32 size)
-{
-	struct bpf_map *map = &smap->map;
-
-	if (!map->ops->map_local_storage_charge)
-		return 0;
-
-	return map->ops->map_local_storage_charge(smap, owner, size);
-}
-
-static void mem_uncharge(struct bpf_local_storage_map *smap, void *owner,
-			 u32 size)
-{
-	struct bpf_map *map = &smap->map;
-
-	if (map->ops->map_local_storage_uncharge)
-		map->ops->map_local_storage_uncharge(smap, owner, size);
-}
-
-static struct bpf_local_storage __rcu **
-owner_storage(struct bpf_local_storage_map *smap, void *owner)
-{
-	struct bpf_map *map = &smap->map;
-
-	return map->ops->map_owner_storage_ptr(owner);
-}
-
-static bool selem_linked_to_storage(const struct bpf_local_storage_elem *selem)
-{
-	return !hlist_unhashed(&selem->snode);
-}
-
-static bool selem_linked_to_map(const struct bpf_local_storage_elem *selem)
-{
-	return !hlist_unhashed(&selem->map_node);
-}
-
-struct bpf_local_storage_elem *
-bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner,
-		void *value, bool charge_mem)
-{
-	struct bpf_local_storage_elem *selem;
-
-	if (charge_mem && mem_charge(smap, owner, smap->elem_size))
-		return NULL;
-
-	selem = kzalloc(smap->elem_size, GFP_ATOMIC | __GFP_NOWARN);
-	if (selem) {
-		if (value)
-			memcpy(SDATA(selem)->data, value, smap->map.value_size);
-		return selem;
-	}
-
-	if (charge_mem)
-		mem_uncharge(smap, owner, smap->elem_size);
-
-	return NULL;
-}
-
-/* local_storage->lock must be held and selem->local_storage == local_storage.
- * The caller must ensure selem->smap is still valid to be
- * dereferenced for its smap->elem_size and smap->cache_idx.
- */
-bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage,
-				     struct bpf_local_storage_elem *selem,
-				     bool uncharge_mem)
-{
-	struct bpf_local_storage_map *smap;
-	bool free_local_storage;
-	void *owner;
-
-	smap = rcu_dereference(SDATA(selem)->smap);
-	owner = local_storage->owner;
-
-	/* All uncharging on the owner must be done first.
-	 * The owner may be freed once the last selem is unlinked
-	 * from local_storage.
-	 */
-	if (uncharge_mem)
-		mem_uncharge(smap, owner, smap->elem_size);
-
-	free_local_storage = hlist_is_singular_node(&selem->snode,
-						    &local_storage->list);
-	if (free_local_storage) {
-		mem_uncharge(smap, owner, sizeof(struct bpf_local_storage));
-		local_storage->owner = NULL;
-
-		/* After this RCU_INIT, owner may be freed and cannot be used */
-		RCU_INIT_POINTER(*owner_storage(smap, owner), NULL);
-
-		/* local_storage is not freed now.  local_storage->lock is
-		 * still held and raw_spin_unlock_bh(&local_storage->lock)
-		 * will be done by the caller.
-		 *
-		 * Although the unlock will be done under
-		 * rcu_read_lock(),  it is more intutivie to
-		 * read if kfree_rcu(local_storage, rcu) is done
-		 * after the raw_spin_unlock_bh(&local_storage->lock).
-		 *
-		 * Hence, a "bool free_local_storage" is returned
-		 * to the caller which then calls the kfree_rcu()
-		 * after unlock.
-		 */
-	}
-	hlist_del_init_rcu(&selem->snode);
-	if (rcu_access_pointer(local_storage->cache[smap->cache_idx]) ==
-	    SDATA(selem))
-		RCU_INIT_POINTER(local_storage->cache[smap->cache_idx], NULL);
-
-	kfree_rcu(selem, rcu);
-
-	return free_local_storage;
-}
-
-static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem)
-{
-	struct bpf_local_storage *local_storage;
-	bool free_local_storage = false;
-
-	if (unlikely(!selem_linked_to_storage(selem)))
-		/* selem has already been unlinked from sk */
-		return;
-
-	local_storage = rcu_dereference(selem->local_storage);
-	raw_spin_lock_bh(&local_storage->lock);
-	if (likely(selem_linked_to_storage(selem)))
-		free_local_storage = bpf_selem_unlink_storage_nolock(
-			local_storage, selem, true);
-	raw_spin_unlock_bh(&local_storage->lock);
-
-	if (free_local_storage)
-		kfree_rcu(local_storage, rcu);
-}
-
-void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage,
-				   struct bpf_local_storage_elem *selem)
-{
-	RCU_INIT_POINTER(selem->local_storage, local_storage);
-	hlist_add_head(&selem->snode, &local_storage->list);
-}
-
-void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem)
-{
-	struct bpf_local_storage_map *smap;
-	struct bpf_local_storage_map_bucket *b;
-
-	if (unlikely(!selem_linked_to_map(selem)))
-		/* selem has already be unlinked from smap */
-		return;
-
-	smap = rcu_dereference(SDATA(selem)->smap);
-	b = select_bucket(smap, selem);
-	raw_spin_lock_bh(&b->lock);
-	if (likely(selem_linked_to_map(selem)))
-		hlist_del_init_rcu(&selem->map_node);
-	raw_spin_unlock_bh(&b->lock);
-}
-
-void bpf_selem_link_map(struct bpf_local_storage_map *smap,
-			struct bpf_local_storage_elem *selem)
-{
-	struct bpf_local_storage_map_bucket *b = select_bucket(smap, selem);
-
-	raw_spin_lock_bh(&b->lock);
-	RCU_INIT_POINTER(SDATA(selem)->smap, smap);
-	hlist_add_head_rcu(&selem->map_node, &b->list);
-	raw_spin_unlock_bh(&b->lock);
-}
-
-void bpf_selem_unlink(struct bpf_local_storage_elem *selem)
-{
-	/* Always unlink from map before unlinking from local_storage
-	 * because selem will be freed after successfully unlinked from
-	 * the local_storage.
-	 */
-	bpf_selem_unlink_map(selem);
-	__bpf_selem_unlink_storage(selem);
-}
-
-struct bpf_local_storage_data *
-bpf_local_storage_lookup(struct bpf_local_storage *local_storage,
-			 struct bpf_local_storage_map *smap,
-			 bool cacheit_lockit)
-{
-	struct bpf_local_storage_data *sdata;
-	struct bpf_local_storage_elem *selem;
-
-	/* Fast path (cache hit) */
-	sdata = rcu_dereference(local_storage->cache[smap->cache_idx]);
-	if (sdata && rcu_access_pointer(sdata->smap) == smap)
-		return sdata;
-
-	/* Slow path (cache miss) */
-	hlist_for_each_entry_rcu(selem, &local_storage->list, snode)
-		if (rcu_access_pointer(SDATA(selem)->smap) == smap)
-			break;
-
-	if (!selem)
-		return NULL;
-
-	sdata = SDATA(selem);
-	if (cacheit_lockit) {
-		/* spinlock is needed to avoid racing with the
-		 * parallel delete.  Otherwise, publishing an already
-		 * deleted sdata to the cache will become a use-after-free
-		 * problem in the next bpf_local_storage_lookup().
-		 */
-		raw_spin_lock_bh(&local_storage->lock);
-		if (selem_linked_to_storage(selem))
-			rcu_assign_pointer(local_storage->cache[smap->cache_idx],
-					   sdata);
-		raw_spin_unlock_bh(&local_storage->lock);
-	}
-
-	return sdata;
-}
-
 static struct bpf_local_storage_data *
 sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit)
 {
@@ -341,202 +41,6 @@ sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit)
 	return bpf_local_storage_lookup(sk_storage, smap, cacheit_lockit);
 }
 
-static int check_flags(const struct bpf_local_storage_data *old_sdata,
-		       u64 map_flags)
-{
-	if (old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST)
-		/* elem already exists */
-		return -EEXIST;
-
-	if (!old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_EXIST)
-		/* elem doesn't exist, cannot update it */
-		return -ENOENT;
-
-	return 0;
-}
-
-int bpf_local_storage_alloc(void *owner,
-			    struct bpf_local_storage_map *smap,
-			    struct bpf_local_storage_elem *first_selem)
-{
-	struct bpf_local_storage *prev_storage, *storage;
-	struct bpf_local_storage **owner_storage_ptr;
-	int err;
-
-	err = mem_charge(smap, owner, sizeof(*storage));
-	if (err)
-		return err;
-
-	storage = kzalloc(sizeof(*storage), GFP_ATOMIC | __GFP_NOWARN);
-	if (!storage) {
-		err = -ENOMEM;
-		goto uncharge;
-	}
-
-	INIT_HLIST_HEAD(&storage->list);
-	raw_spin_lock_init(&storage->lock);
-	storage->owner = owner;
-
-	bpf_selem_link_storage_nolock(storage, first_selem);
-	bpf_selem_link_map(smap, first_selem);
-
-	owner_storage_ptr =
-		(struct bpf_local_storage **)owner_storage(smap, owner);
-	/* Publish storage to the owner.
-	 * Instead of using any lock of the kernel object (i.e. owner),
-	 * cmpxchg will work with any kernel object regardless what
-	 * the running context is, bh, irq...etc.
-	 *
-	 * From now on, the owner->storage pointer (e.g. sk->sk_bpf_storage)
-	 * is protected by the storage->lock.  Hence, when freeing
-	 * the owner->storage, the storage->lock must be held before
-	 * setting owner->storage ptr to NULL.
-	 */
-	prev_storage = cmpxchg(owner_storage_ptr, NULL, storage);
-	if (unlikely(prev_storage)) {
-		bpf_selem_unlink_map(first_selem);
-		err = -EAGAIN;
-		goto uncharge;
-
-		/* Note that even first_selem was linked to smap's
-		 * bucket->list, first_selem can be freed immediately
-		 * (instead of kfree_rcu) because
-		 * bpf_local_storage_map_free() does a
-		 * synchronize_rcu() before walking the bucket->list.
-		 * Hence, no one is accessing selem from the
-		 * bucket->list under rcu_read_lock().
-		 */
-	}
-
-	return 0;
-
-uncharge:
-	kfree(storage);
-	mem_uncharge(smap, owner, sizeof(*storage));
-	return err;
-}
-
-/* sk cannot be going away because it is linking new elem
- * to sk->sk_bpf_storage. (i.e. sk->sk_refcnt cannot be 0).
- * Otherwise, it will become a leak (and other memory issues
- * during map destruction).
- */
-struct bpf_local_storage_data *
-bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
-			 void *value, u64 map_flags)
-{
-	struct bpf_local_storage_data *old_sdata = NULL;
-	struct bpf_local_storage_elem *selem;
-	struct bpf_local_storage *local_storage;
-	int err;
-
-	/* BPF_EXIST and BPF_NOEXIST cannot be both set */
-	if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST) ||
-	    /* BPF_F_LOCK can only be used in a value with spin_lock */
-	    unlikely((map_flags & BPF_F_LOCK) &&
-		     !map_value_has_spin_lock(&smap->map)))
-		return ERR_PTR(-EINVAL);
-
-	local_storage = rcu_dereference(*owner_storage(smap, owner));
-	if (!local_storage || hlist_empty(&local_storage->list)) {
-		/* Very first elem for the owner */
-		err = check_flags(NULL, map_flags);
-		if (err)
-			return ERR_PTR(err);
-
-		selem = bpf_selem_alloc(smap, owner, value, true);
-		if (!selem)
-			return ERR_PTR(-ENOMEM);
-
-		err = bpf_local_storage_alloc(owner, smap, selem);
-		if (err) {
-			kfree(selem);
-			mem_uncharge(smap, owner, smap->elem_size);
-			return ERR_PTR(err);
-		}
-
-		return SDATA(selem);
-	}
-
-	if ((map_flags & BPF_F_LOCK) && !(map_flags & BPF_NOEXIST)) {
-		/* Hoping to find an old_sdata to do inline update
-		 * such that it can avoid taking the local_storage->lock
-		 * and changing the lists.
-		 */
-		old_sdata =
-			bpf_local_storage_lookup(local_storage, smap, false);
-		err = check_flags(old_sdata, map_flags);
-		if (err)
-			return ERR_PTR(err);
-		if (old_sdata && selem_linked_to_storage(SELEM(old_sdata))) {
-			copy_map_value_locked(&smap->map, old_sdata->data,
-					      value, false);
-			return old_sdata;
-		}
-	}
-
-	raw_spin_lock_bh(&local_storage->lock);
-
-	/* Recheck local_storage->list under local_storage->lock */
-	if (unlikely(hlist_empty(&local_storage->list))) {
-		/* A parallel del is happening and local_storage is going
-		 * away.  It has just been checked before, so very
-		 * unlikely.  Return instead of retry to keep things
-		 * simple.
-		 */
-		err = -EAGAIN;
-		goto unlock_err;
-	}
-
-	old_sdata = bpf_local_storage_lookup(local_storage, smap, false);
-	err = check_flags(old_sdata, map_flags);
-	if (err)
-		goto unlock_err;
-
-	if (old_sdata && (map_flags & BPF_F_LOCK)) {
-		copy_map_value_locked(&smap->map, old_sdata->data, value,
-				      false);
-		selem = SELEM(old_sdata);
-		goto unlock;
-	}
-
-	/* local_storage->lock is held.  Hence, we are sure
-	 * we can unlink and uncharge the old_sdata successfully
-	 * later.  Hence, instead of charging the new selem now
-	 * and then uncharge the old selem later (which may cause
-	 * a potential but unnecessary charge failure),  avoid taking
-	 * a charge at all here (the "!old_sdata" check) and the
-	 * old_sdata will not be uncharged later during
-	 * bpf_selem_unlink_storage_nolock().
-	 */
-	selem = bpf_selem_alloc(smap, owner, value, !old_sdata);
-	if (!selem) {
-		err = -ENOMEM;
-		goto unlock_err;
-	}
-
-	/* First, link the new selem to the map */
-	bpf_selem_link_map(smap, selem);
-
-	/* Second, link (and publish) the new selem to local_storage */
-	bpf_selem_link_storage_nolock(local_storage, selem);
-
-	/* Third, remove old selem, SELEM(old_sdata) */
-	if (old_sdata) {
-		bpf_selem_unlink_map(SELEM(old_sdata));
-		bpf_selem_unlink_storage_nolock(local_storage, SELEM(old_sdata),
-						false);
-	}
-
-unlock:
-	raw_spin_unlock_bh(&local_storage->lock);
-	return SDATA(selem);
-
-unlock_err:
-	raw_spin_unlock_bh(&local_storage->lock);
-	return ERR_PTR(err);
-}
-
 static int sk_storage_delete(struct sock *sk, struct bpf_map *map)
 {
 	struct bpf_local_storage_data *sdata;
@@ -550,38 +54,6 @@ static int sk_storage_delete(struct sock *sk, struct bpf_map *map)
 	return 0;
 }
 
-u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache)
-{
-	u64 min_usage = U64_MAX;
-	u16 i, res = 0;
-
-	spin_lock(&cache->idx_lock);
-
-	for (i = 0; i < BPF_LOCAL_STORAGE_CACHE_SIZE; i++) {
-		if (cache->idx_usage_counts[i] < min_usage) {
-			min_usage = cache->idx_usage_counts[i];
-			res = i;
-
-			/* Found a free cache_idx */
-			if (!min_usage)
-				break;
-		}
-	}
-	cache->idx_usage_counts[res]++;
-
-	spin_unlock(&cache->idx_lock);
-
-	return res;
-}
-
-void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache,
-				      u16 idx)
-{
-	spin_lock(&cache->idx_lock);
-	cache->idx_usage_counts[idx]--;
-	spin_unlock(&cache->idx_lock);
-}
-
 /* Called by __sk_destruct() & bpf_sk_storage_clone() */
 void bpf_sk_storage_free(struct sock *sk)
 {
@@ -622,59 +94,6 @@ void bpf_sk_storage_free(struct sock *sk)
 		kfree_rcu(sk_storage, rcu);
 }
 
-void bpf_local_storage_map_free(struct bpf_local_storage_map *smap)
-{
-	struct bpf_local_storage_elem *selem;
-	struct bpf_local_storage_map_bucket *b;
-	unsigned int i;
-
-	/* Note that this map might be concurrently cloned from
-	 * bpf_sk_storage_clone. Wait for any existing bpf_sk_storage_clone
-	 * RCU read section to finish before proceeding. New RCU
-	 * read sections should be prevented via bpf_map_inc_not_zero.
-	 */
-	synchronize_rcu();
-
-	/* bpf prog and the userspace can no longer access this map
-	 * now.  No new selem (of this map) can be added
-	 * to the owner->storage or to the map bucket's list.
-	 *
-	 * The elem of this map can be cleaned up here
-	 * or when the storage is freed e.g.
-	 * by bpf_sk_storage_free() during __sk_destruct().
-	 */
-	for (i = 0; i < (1U << smap->bucket_log); i++) {
-		b = &smap->buckets[i];
-
-		rcu_read_lock();
-		/* No one is adding to b->list now */
-		while ((selem = hlist_entry_safe(
-				rcu_dereference_raw(hlist_first_rcu(&b->list)),
-				struct bpf_local_storage_elem, map_node))) {
-			bpf_selem_unlink(selem);
-			cond_resched_rcu();
-		}
-		rcu_read_unlock();
-	}
-
-	/* While freeing the storage we may still need to access the map.
-	 *
-	 * e.g. when bpf_sk_storage_free() has unlinked selem from the map
-	 * which then made the above while((selem = ...)) loop
-	 * exit immediately.
-	 *
-	 * However, while freeing the storage one still needs to access the
-	 * smap->elem_size to do the uncharging in
-	 * bpf_selem_unlink_storage_nolock().
-	 *
-	 * Hence, wait another rcu grace period for the storage to be freed.
-	 */
-	synchronize_rcu();
-
-	kvfree(smap->buckets);
-	kfree(smap);
-}
-
 static void sk_storage_map_free(struct bpf_map *map)
 {
 	struct bpf_local_storage_map *smap;
@@ -684,78 +103,6 @@ static void sk_storage_map_free(struct bpf_map *map)
 	bpf_local_storage_map_free(smap);
 }
 
-/* U16_MAX is much more than enough for sk local storage
- * considering a tcp_sock is ~2k.
- */
-#define BPF_LOCAL_STORAGE_MAX_VALUE_SIZE				\
-	min_t(u32,							\
-	      (KMALLOC_MAX_SIZE - MAX_BPF_STACK -			\
-	       sizeof(struct bpf_local_storage_elem)),			\
-	      (U16_MAX - sizeof(struct bpf_local_storage_elem)))
-
-int bpf_local_storage_map_alloc_check(union bpf_attr *attr)
-{
-	if (attr->map_flags & ~BPF_LOCAL_STORAGE_CREATE_FLAG_MASK ||
-	    !(attr->map_flags & BPF_F_NO_PREALLOC) ||
-	    attr->max_entries ||
-	    attr->key_size != sizeof(int) || !attr->value_size ||
-	    /* Enforce BTF for userspace sk dumping */
-	    !attr->btf_key_type_id || !attr->btf_value_type_id)
-		return -EINVAL;
-
-	if (!bpf_capable())
-		return -EPERM;
-
-	if (attr->value_size > BPF_LOCAL_STORAGE_MAX_VALUE_SIZE)
-		return -E2BIG;
-
-	return 0;
-}
-
-struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr)
-{
-	struct bpf_local_storage_map *smap;
-	unsigned int i;
-	u32 nbuckets;
-	u64 cost;
-	int ret;
-
-	smap = kzalloc(sizeof(*smap), GFP_USER | __GFP_NOWARN);
-	if (!smap)
-		return ERR_PTR(-ENOMEM);
-	bpf_map_init_from_attr(&smap->map, attr);
-
-	nbuckets = roundup_pow_of_two(num_possible_cpus());
-	/* Use at least 2 buckets, select_bucket() is undefined behavior with 1 bucket */
-	nbuckets = max_t(u32, 2, nbuckets);
-	smap->bucket_log = ilog2(nbuckets);
-	cost = sizeof(*smap->buckets) * nbuckets + sizeof(*smap);
-
-	ret = bpf_map_charge_init(&smap->map.memory, cost);
-	if (ret < 0) {
-		kfree(smap);
-		return ERR_PTR(ret);
-	}
-
-	smap->buckets = kvcalloc(sizeof(*smap->buckets), nbuckets,
-				 GFP_USER | __GFP_NOWARN);
-	if (!smap->buckets) {
-		bpf_map_charge_finish(&smap->map.memory);
-		kfree(smap);
-		return ERR_PTR(-ENOMEM);
-	}
-
-	for (i = 0; i < nbuckets; i++) {
-		INIT_HLIST_HEAD(&smap->buckets[i].list);
-		raw_spin_lock_init(&smap->buckets[i].lock);
-	}
-
-	smap->elem_size =
-		sizeof(struct bpf_local_storage_elem) + attr->value_size;
-
-	return smap;
-}
-
 static struct bpf_map *sk_storage_map_alloc(union bpf_attr *attr)
 {
 	struct bpf_local_storage_map *smap;
@@ -774,23 +121,6 @@ static int notsupp_get_next_key(struct bpf_map *map, void *key,
 	return -ENOTSUPP;
 }
 
-int bpf_local_storage_map_check_btf(const struct bpf_map *map,
-				    const struct btf *btf,
-				    const struct btf_type *key_type,
-				    const struct btf_type *value_type)
-{
-	u32 int_data;
-
-	if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
-		return -EINVAL;
-
-	int_data = *(u32 *)(key_type + 1);
-	if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data))
-		return -EINVAL;
-
-	return 0;
-}
-
 static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_local_storage_data *sdata;
-- 
cgit v1.2.3


From 8ea636848aca35b9f97c5b5dee30225cf2dd0fe6 Mon Sep 17 00:00:00 2001
From: KP Singh <kpsingh@google.com>
Date: Tue, 25 Aug 2020 20:29:17 +0200
Subject: bpf: Implement bpf_local_storage for inodes

Similar to bpf_local_storage for sockets, add local storage for inodes.
The life-cycle of storage is managed with the life-cycle of the inode.
i.e. the storage is destroyed along with the owning inode.

The BPF LSM allocates an __rcu pointer to the bpf_local_storage in the
security blob which are now stackable and can co-exist with other LSMs.

Signed-off-by: KP Singh <kpsingh@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200825182919.1118197-6-kpsingh@chromium.org
---
 include/linux/bpf_lsm.h                         |  29 +++
 include/linux/bpf_types.h                       |   3 +
 include/uapi/linux/bpf.h                        |  40 +++-
 kernel/bpf/Makefile                             |   1 +
 kernel/bpf/bpf_inode_storage.c                  | 273 ++++++++++++++++++++++++
 kernel/bpf/syscall.c                            |   3 +-
 kernel/bpf/verifier.c                           |  10 +
 security/bpf/hooks.c                            |   6 +
 tools/bpf/bpftool/Documentation/bpftool-map.rst |   2 +-
 tools/bpf/bpftool/bash-completion/bpftool       |   3 +-
 tools/bpf/bpftool/map.c                         |   3 +-
 tools/include/uapi/linux/bpf.h                  |  40 +++-
 tools/lib/bpf/libbpf_probes.c                   |   5 +-
 13 files changed, 410 insertions(+), 8 deletions(-)
 create mode 100644 kernel/bpf/bpf_inode_storage.c

(limited to 'include/linux')

diff --git a/include/linux/bpf_lsm.h b/include/linux/bpf_lsm.h
index af74712af585..aaacb6aafc87 100644
--- a/include/linux/bpf_lsm.h
+++ b/include/linux/bpf_lsm.h
@@ -17,9 +17,28 @@
 #include <linux/lsm_hook_defs.h>
 #undef LSM_HOOK
 
+struct bpf_storage_blob {
+	struct bpf_local_storage __rcu *storage;
+};
+
+extern struct lsm_blob_sizes bpf_lsm_blob_sizes;
+
 int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog,
 			const struct bpf_prog *prog);
 
+static inline struct bpf_storage_blob *bpf_inode(
+	const struct inode *inode)
+{
+	if (unlikely(!inode->i_security))
+		return NULL;
+
+	return inode->i_security + bpf_lsm_blob_sizes.lbs_inode;
+}
+
+extern const struct bpf_func_proto bpf_inode_storage_get_proto;
+extern const struct bpf_func_proto bpf_inode_storage_delete_proto;
+void bpf_inode_storage_free(struct inode *inode);
+
 #else /* !CONFIG_BPF_LSM */
 
 static inline int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog,
@@ -28,6 +47,16 @@ static inline int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog,
 	return -EOPNOTSUPP;
 }
 
+static inline struct bpf_storage_blob *bpf_inode(
+	const struct inode *inode)
+{
+	return NULL;
+}
+
+static inline void bpf_inode_storage_free(struct inode *inode)
+{
+}
+
 #endif /* CONFIG_BPF_LSM */
 
 #endif /* _LINUX_BPF_LSM_H */
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index a52a5688418e..2e6f568377f1 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -107,6 +107,9 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_SK_STORAGE, sk_storage_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKHASH, sock_hash_ops)
 #endif
+#ifdef CONFIG_BPF_LSM
+BPF_MAP_TYPE(BPF_MAP_TYPE_INODE_STORAGE, inode_storage_map_ops)
+#endif
 BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops)
 #if defined(CONFIG_XDP_SOCKETS)
 BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 2cbd137eed86..b6bfcd085a76 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -155,6 +155,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_DEVMAP_HASH,
 	BPF_MAP_TYPE_STRUCT_OPS,
 	BPF_MAP_TYPE_RINGBUF,
+	BPF_MAP_TYPE_INODE_STORAGE,
 };
 
 /* Note that tracing related programs such as
@@ -3509,6 +3510,41 @@ union bpf_attr {
  *
  *		**-EPERM** This helper cannot be used under the
  *			   current sock_ops->op.
+ * void *bpf_inode_storage_get(struct bpf_map *map, void *inode, void *value, u64 flags)
+ *	Description
+ *		Get a bpf_local_storage from an *inode*.
+ *
+ *		Logically, it could be thought of as getting the value from
+ *		a *map* with *inode* as the **key**.  From this
+ *		perspective,  the usage is not much different from
+ *		**bpf_map_lookup_elem**\ (*map*, **&**\ *inode*) except this
+ *		helper enforces the key must be an inode and the map must also
+ *		be a **BPF_MAP_TYPE_INODE_STORAGE**.
+ *
+ *		Underneath, the value is stored locally at *inode* instead of
+ *		the *map*.  The *map* is used as the bpf-local-storage
+ *		"type". The bpf-local-storage "type" (i.e. the *map*) is
+ *		searched against all bpf_local_storage residing at *inode*.
+ *
+ *		An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be
+ *		used such that a new bpf_local_storage will be
+ *		created if one does not exist.  *value* can be used
+ *		together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify
+ *		the initial value of a bpf_local_storage.  If *value* is
+ *		**NULL**, the new bpf_local_storage will be zero initialized.
+ *	Return
+ *		A bpf_local_storage pointer is returned on success.
+ *
+ *		**NULL** if not found or there was an error in adding
+ *		a new bpf_local_storage.
+ *
+ * int bpf_inode_storage_delete(struct bpf_map *map, void *inode)
+ *	Description
+ *		Delete a bpf_local_storage from an *inode*.
+ *	Return
+ *		0 on success.
+ *
+ *		**-ENOENT** if the bpf_local_storage cannot be found.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3655,7 +3691,9 @@ union bpf_attr {
 	FN(get_task_stack),		\
 	FN(load_hdr_opt),		\
 	FN(store_hdr_opt),		\
-	FN(reserve_hdr_opt),
+	FN(reserve_hdr_opt),		\
+	FN(inode_storage_get),		\
+	FN(inode_storage_delete),	\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 6961ff400cba..bdc8cd1b6767 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -5,6 +5,7 @@ CFLAGS_core.o += $(call cc-disable-warning, override-init)
 obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o prog_iter.o
 obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
 obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o
+obj-${CONFIG_BPF_LSM}	  += bpf_inode_storage.o
 obj-$(CONFIG_BPF_SYSCALL) += disasm.o
 obj-$(CONFIG_BPF_JIT) += trampoline.o
 obj-$(CONFIG_BPF_SYSCALL) += btf.o
diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c
new file mode 100644
index 000000000000..f3a44e929447
--- /dev/null
+++ b/kernel/bpf/bpf_inode_storage.c
@@ -0,0 +1,273 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2019 Facebook
+ * Copyright 2020 Google LLC.
+ */
+
+#include <linux/rculist.h>
+#include <linux/list.h>
+#include <linux/hash.h>
+#include <linux/types.h>
+#include <linux/spinlock.h>
+#include <linux/bpf.h>
+#include <linux/bpf_local_storage.h>
+#include <net/sock.h>
+#include <uapi/linux/sock_diag.h>
+#include <uapi/linux/btf.h>
+#include <linux/bpf_lsm.h>
+#include <linux/btf_ids.h>
+#include <linux/fdtable.h>
+
+DEFINE_BPF_STORAGE_CACHE(inode_cache);
+
+static struct bpf_local_storage __rcu **
+inode_storage_ptr(void *owner)
+{
+	struct inode *inode = owner;
+	struct bpf_storage_blob *bsb;
+
+	bsb = bpf_inode(inode);
+	if (!bsb)
+		return NULL;
+	return &bsb->storage;
+}
+
+static struct bpf_local_storage_data *inode_storage_lookup(struct inode *inode,
+							   struct bpf_map *map,
+							   bool cacheit_lockit)
+{
+	struct bpf_local_storage *inode_storage;
+	struct bpf_local_storage_map *smap;
+	struct bpf_storage_blob *bsb;
+
+	bsb = bpf_inode(inode);
+	if (!bsb)
+		return NULL;
+
+	inode_storage = rcu_dereference(bsb->storage);
+	if (!inode_storage)
+		return NULL;
+
+	smap = (struct bpf_local_storage_map *)map;
+	return bpf_local_storage_lookup(inode_storage, smap, cacheit_lockit);
+}
+
+void bpf_inode_storage_free(struct inode *inode)
+{
+	struct bpf_local_storage_elem *selem;
+	struct bpf_local_storage *local_storage;
+	bool free_inode_storage = false;
+	struct bpf_storage_blob *bsb;
+	struct hlist_node *n;
+
+	bsb = bpf_inode(inode);
+	if (!bsb)
+		return;
+
+	rcu_read_lock();
+
+	local_storage = rcu_dereference(bsb->storage);
+	if (!local_storage) {
+		rcu_read_unlock();
+		return;
+	}
+
+	/* Netiher the bpf_prog nor the bpf-map's syscall
+	 * could be modifying the local_storage->list now.
+	 * Thus, no elem can be added-to or deleted-from the
+	 * local_storage->list by the bpf_prog or by the bpf-map's syscall.
+	 *
+	 * It is racing with bpf_local_storage_map_free() alone
+	 * when unlinking elem from the local_storage->list and
+	 * the map's bucket->list.
+	 */
+	raw_spin_lock_bh(&local_storage->lock);
+	hlist_for_each_entry_safe(selem, n, &local_storage->list, snode) {
+		/* Always unlink from map before unlinking from
+		 * local_storage.
+		 */
+		bpf_selem_unlink_map(selem);
+		free_inode_storage = bpf_selem_unlink_storage_nolock(
+			local_storage, selem, false);
+	}
+	raw_spin_unlock_bh(&local_storage->lock);
+	rcu_read_unlock();
+
+	/* free_inoode_storage should always be true as long as
+	 * local_storage->list was non-empty.
+	 */
+	if (free_inode_storage)
+		kfree_rcu(local_storage, rcu);
+}
+
+static void *bpf_fd_inode_storage_lookup_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_local_storage_data *sdata;
+	struct file *f;
+	int fd;
+
+	fd = *(int *)key;
+	f = fget_raw(fd);
+	if (!f)
+		return NULL;
+
+	sdata = inode_storage_lookup(f->f_inode, map, true);
+	fput(f);
+	return sdata ? sdata->data : NULL;
+}
+
+static int bpf_fd_inode_storage_update_elem(struct bpf_map *map, void *key,
+					 void *value, u64 map_flags)
+{
+	struct bpf_local_storage_data *sdata;
+	struct file *f;
+	int fd;
+
+	fd = *(int *)key;
+	f = fget_raw(fd);
+	if (!f || !inode_storage_ptr(f->f_inode))
+		return -EBADF;
+
+	sdata = bpf_local_storage_update(f->f_inode,
+					 (struct bpf_local_storage_map *)map,
+					 value, map_flags);
+	fput(f);
+	return PTR_ERR_OR_ZERO(sdata);
+}
+
+static int inode_storage_delete(struct inode *inode, struct bpf_map *map)
+{
+	struct bpf_local_storage_data *sdata;
+
+	sdata = inode_storage_lookup(inode, map, false);
+	if (!sdata)
+		return -ENOENT;
+
+	bpf_selem_unlink(SELEM(sdata));
+
+	return 0;
+}
+
+static int bpf_fd_inode_storage_delete_elem(struct bpf_map *map, void *key)
+{
+	struct file *f;
+	int fd, err;
+
+	fd = *(int *)key;
+	f = fget_raw(fd);
+	if (!f)
+		return -EBADF;
+
+	err = inode_storage_delete(f->f_inode, map);
+	fput(f);
+	return err;
+}
+
+BPF_CALL_4(bpf_inode_storage_get, struct bpf_map *, map, struct inode *, inode,
+	   void *, value, u64, flags)
+{
+	struct bpf_local_storage_data *sdata;
+
+	if (flags & ~(BPF_LOCAL_STORAGE_GET_F_CREATE))
+		return (unsigned long)NULL;
+
+	/* explicitly check that the inode_storage_ptr is not
+	 * NULL as inode_storage_lookup returns NULL in this case and
+	 * bpf_local_storage_update expects the owner to have a
+	 * valid storage pointer.
+	 */
+	if (!inode_storage_ptr(inode))
+		return (unsigned long)NULL;
+
+	sdata = inode_storage_lookup(inode, map, true);
+	if (sdata)
+		return (unsigned long)sdata->data;
+
+	/* This helper must only called from where the inode is gurranteed
+	 * to have a refcount and cannot be freed.
+	 */
+	if (flags & BPF_LOCAL_STORAGE_GET_F_CREATE) {
+		sdata = bpf_local_storage_update(
+			inode, (struct bpf_local_storage_map *)map, value,
+			BPF_NOEXIST);
+		return IS_ERR(sdata) ? (unsigned long)NULL :
+					     (unsigned long)sdata->data;
+	}
+
+	return (unsigned long)NULL;
+}
+
+BPF_CALL_2(bpf_inode_storage_delete,
+	   struct bpf_map *, map, struct inode *, inode)
+{
+	/* This helper must only called from where the inode is gurranteed
+	 * to have a refcount and cannot be freed.
+	 */
+	return inode_storage_delete(inode, map);
+}
+
+static int notsupp_get_next_key(struct bpf_map *map, void *key,
+				void *next_key)
+{
+	return -ENOTSUPP;
+}
+
+static struct bpf_map *inode_storage_map_alloc(union bpf_attr *attr)
+{
+	struct bpf_local_storage_map *smap;
+
+	smap = bpf_local_storage_map_alloc(attr);
+	if (IS_ERR(smap))
+		return ERR_CAST(smap);
+
+	smap->cache_idx = bpf_local_storage_cache_idx_get(&inode_cache);
+	return &smap->map;
+}
+
+static void inode_storage_map_free(struct bpf_map *map)
+{
+	struct bpf_local_storage_map *smap;
+
+	smap = (struct bpf_local_storage_map *)map;
+	bpf_local_storage_cache_idx_free(&inode_cache, smap->cache_idx);
+	bpf_local_storage_map_free(smap);
+}
+
+static int inode_storage_map_btf_id;
+const struct bpf_map_ops inode_storage_map_ops = {
+	.map_alloc_check = bpf_local_storage_map_alloc_check,
+	.map_alloc = inode_storage_map_alloc,
+	.map_free = inode_storage_map_free,
+	.map_get_next_key = notsupp_get_next_key,
+	.map_lookup_elem = bpf_fd_inode_storage_lookup_elem,
+	.map_update_elem = bpf_fd_inode_storage_update_elem,
+	.map_delete_elem = bpf_fd_inode_storage_delete_elem,
+	.map_check_btf = bpf_local_storage_map_check_btf,
+	.map_btf_name = "bpf_local_storage_map",
+	.map_btf_id = &inode_storage_map_btf_id,
+	.map_owner_storage_ptr = inode_storage_ptr,
+};
+
+BTF_ID_LIST(bpf_inode_storage_btf_ids)
+BTF_ID_UNUSED
+BTF_ID(struct, inode)
+
+const struct bpf_func_proto bpf_inode_storage_get_proto = {
+	.func		= bpf_inode_storage_get,
+	.gpl_only	= false,
+	.ret_type	= RET_PTR_TO_MAP_VALUE_OR_NULL,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_PTR_TO_BTF_ID,
+	.arg3_type	= ARG_PTR_TO_MAP_VALUE_OR_NULL,
+	.arg4_type	= ARG_ANYTHING,
+	.btf_id		= bpf_inode_storage_btf_ids,
+};
+
+const struct bpf_func_proto bpf_inode_storage_delete_proto = {
+	.func		= bpf_inode_storage_delete,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_PTR_TO_BTF_ID,
+	.btf_id		= bpf_inode_storage_btf_ids,
+};
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index b46e973faee9..5443cea86cef 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -769,7 +769,8 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
 		if (map->map_type != BPF_MAP_TYPE_HASH &&
 		    map->map_type != BPF_MAP_TYPE_ARRAY &&
 		    map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE &&
-		    map->map_type != BPF_MAP_TYPE_SK_STORAGE)
+		    map->map_type != BPF_MAP_TYPE_SK_STORAGE &&
+		    map->map_type != BPF_MAP_TYPE_INODE_STORAGE)
 			return -ENOTSUPP;
 		if (map->spin_lock_off + sizeof(struct bpf_spin_lock) >
 		    map->value_size) {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index dd24503ab3d3..38748794518e 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4311,6 +4311,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		    func_id != BPF_FUNC_sk_storage_delete)
 			goto error;
 		break;
+	case BPF_MAP_TYPE_INODE_STORAGE:
+		if (func_id != BPF_FUNC_inode_storage_get &&
+		    func_id != BPF_FUNC_inode_storage_delete)
+			goto error;
+		break;
 	default:
 		break;
 	}
@@ -4384,6 +4389,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		if (map->map_type != BPF_MAP_TYPE_SK_STORAGE)
 			goto error;
 		break;
+	case BPF_FUNC_inode_storage_get:
+	case BPF_FUNC_inode_storage_delete:
+		if (map->map_type != BPF_MAP_TYPE_INODE_STORAGE)
+			goto error;
+		break;
 	default:
 		break;
 	}
diff --git a/security/bpf/hooks.c b/security/bpf/hooks.c
index 32d32d485451..788667d582ae 100644
--- a/security/bpf/hooks.c
+++ b/security/bpf/hooks.c
@@ -11,6 +11,7 @@ static struct security_hook_list bpf_lsm_hooks[] __lsm_ro_after_init = {
 	LSM_HOOK_INIT(NAME, bpf_lsm_##NAME),
 	#include <linux/lsm_hook_defs.h>
 	#undef LSM_HOOK
+	LSM_HOOK_INIT(inode_free_security, bpf_inode_storage_free),
 };
 
 static int __init bpf_lsm_init(void)
@@ -20,7 +21,12 @@ static int __init bpf_lsm_init(void)
 	return 0;
 }
 
+struct lsm_blob_sizes bpf_lsm_blob_sizes __lsm_ro_after_init = {
+	.lbs_inode = sizeof(struct bpf_storage_blob),
+};
+
 DEFINE_LSM(bpf) = {
 	.name = "bpf",
 	.init = bpf_lsm_init,
+	.blobs = &bpf_lsm_blob_sizes
 };
diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst
index 41e2a74252d0..083db6c2fc67 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-map.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst
@@ -49,7 +49,7 @@ MAP COMMANDS
 |		| **lru_percpu_hash** | **lpm_trie** | **array_of_maps** | **hash_of_maps**
 |		| **devmap** | **devmap_hash** | **sockmap** | **cpumap** | **xskmap** | **sockhash**
 |		| **cgroup_storage** | **reuseport_sockarray** | **percpu_cgroup_storage**
-|		| **queue** | **stack** | **sk_storage** | **struct_ops** | **ringbuf** }
+|		| **queue** | **stack** | **sk_storage** | **struct_ops** | **ringbuf** | **inode_storage** }
 
 DESCRIPTION
 ===========
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index f53ed2f1a4aa..7b68e3c0a5fb 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -704,7 +704,8 @@ _bpftool()
                                 lru_percpu_hash lpm_trie array_of_maps \
                                 hash_of_maps devmap devmap_hash sockmap cpumap \
                                 xskmap sockhash cgroup_storage reuseport_sockarray \
-                                percpu_cgroup_storage queue stack' -- \
+                                percpu_cgroup_storage queue stack sk_storage \
+                                struct_ops inode_storage' -- \
                                                    "$cur" ) )
                             return 0
                             ;;
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index 3a27d31a1856..bc0071228f88 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -50,6 +50,7 @@ const char * const map_type_name[] = {
 	[BPF_MAP_TYPE_SK_STORAGE]		= "sk_storage",
 	[BPF_MAP_TYPE_STRUCT_OPS]		= "struct_ops",
 	[BPF_MAP_TYPE_RINGBUF]			= "ringbuf",
+	[BPF_MAP_TYPE_INODE_STORAGE]		= "inode_storage",
 };
 
 const size_t map_type_name_size = ARRAY_SIZE(map_type_name);
@@ -1442,7 +1443,7 @@ static int do_help(int argc, char **argv)
 		"                 lru_percpu_hash | lpm_trie | array_of_maps | hash_of_maps |\n"
 		"                 devmap | devmap_hash | sockmap | cpumap | xskmap | sockhash |\n"
 		"                 cgroup_storage | reuseport_sockarray | percpu_cgroup_storage |\n"
-		"                 queue | stack | sk_storage | struct_ops | ringbuf }\n"
+		"                 queue | stack | sk_storage | struct_ops | ringbuf | inode_storage }\n"
 		"       " HELP_SPEC_OPTIONS "\n"
 		"",
 		bin_name, argv[-2]);
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 2cbd137eed86..b6bfcd085a76 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -155,6 +155,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_DEVMAP_HASH,
 	BPF_MAP_TYPE_STRUCT_OPS,
 	BPF_MAP_TYPE_RINGBUF,
+	BPF_MAP_TYPE_INODE_STORAGE,
 };
 
 /* Note that tracing related programs such as
@@ -3509,6 +3510,41 @@ union bpf_attr {
  *
  *		**-EPERM** This helper cannot be used under the
  *			   current sock_ops->op.
+ * void *bpf_inode_storage_get(struct bpf_map *map, void *inode, void *value, u64 flags)
+ *	Description
+ *		Get a bpf_local_storage from an *inode*.
+ *
+ *		Logically, it could be thought of as getting the value from
+ *		a *map* with *inode* as the **key**.  From this
+ *		perspective,  the usage is not much different from
+ *		**bpf_map_lookup_elem**\ (*map*, **&**\ *inode*) except this
+ *		helper enforces the key must be an inode and the map must also
+ *		be a **BPF_MAP_TYPE_INODE_STORAGE**.
+ *
+ *		Underneath, the value is stored locally at *inode* instead of
+ *		the *map*.  The *map* is used as the bpf-local-storage
+ *		"type". The bpf-local-storage "type" (i.e. the *map*) is
+ *		searched against all bpf_local_storage residing at *inode*.
+ *
+ *		An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be
+ *		used such that a new bpf_local_storage will be
+ *		created if one does not exist.  *value* can be used
+ *		together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify
+ *		the initial value of a bpf_local_storage.  If *value* is
+ *		**NULL**, the new bpf_local_storage will be zero initialized.
+ *	Return
+ *		A bpf_local_storage pointer is returned on success.
+ *
+ *		**NULL** if not found or there was an error in adding
+ *		a new bpf_local_storage.
+ *
+ * int bpf_inode_storage_delete(struct bpf_map *map, void *inode)
+ *	Description
+ *		Delete a bpf_local_storage from an *inode*.
+ *	Return
+ *		0 on success.
+ *
+ *		**-ENOENT** if the bpf_local_storage cannot be found.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3655,7 +3691,9 @@ union bpf_attr {
 	FN(get_task_stack),		\
 	FN(load_hdr_opt),		\
 	FN(store_hdr_opt),		\
-	FN(reserve_hdr_opt),
+	FN(reserve_hdr_opt),		\
+	FN(inode_storage_get),		\
+	FN(inode_storage_delete),	\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c
index 010c9a76fd2b..5482a9b7ae2d 100644
--- a/tools/lib/bpf/libbpf_probes.c
+++ b/tools/lib/bpf/libbpf_probes.c
@@ -170,7 +170,7 @@ int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
 	return btf_fd;
 }
 
-static int load_sk_storage_btf(void)
+static int load_local_storage_btf(void)
 {
 	const char strs[] = "\0bpf_spin_lock\0val\0cnt\0l";
 	/* struct bpf_spin_lock {
@@ -229,12 +229,13 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
 		key_size	= 0;
 		break;
 	case BPF_MAP_TYPE_SK_STORAGE:
+	case BPF_MAP_TYPE_INODE_STORAGE:
 		btf_key_type_id = 1;
 		btf_value_type_id = 3;
 		value_size = 8;
 		max_entries = 0;
 		map_flags = BPF_F_NO_PREALLOC;
-		btf_fd = load_sk_storage_btf();
+		btf_fd = load_local_storage_btf();
 		if (btf_fd < 0)
 			return false;
 		break;
-- 
cgit v1.2.3


From 6298399bfc101f8e8cf35a916f26aa32bdf04278 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Tue, 25 Aug 2020 21:21:13 +0200
Subject: bpf: Move btf_resolve_size into __btf_resolve_size

Moving btf_resolve_size into __btf_resolve_size and
keeping btf_resolve_size public with just first 3
arguments, because the rest of the arguments are not
used by outside callers.

Following changes are adding more arguments, which
are not useful to outside callers. They will be added
to the __btf_resolve_size function.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200825192124.710397-4-jolsa@kernel.org
---
 include/linux/btf.h         |  3 +--
 kernel/bpf/bpf_struct_ops.c |  6 ++----
 kernel/bpf/btf.c            | 21 ++++++++++++++-------
 3 files changed, 17 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/btf.h b/include/linux/btf.h
index 8b81fbb4497c..a9af5e7a7ece 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -64,8 +64,7 @@ const struct btf_type *btf_type_resolve_func_ptr(const struct btf *btf,
 						 u32 id, u32 *res_id);
 const struct btf_type *
 btf_resolve_size(const struct btf *btf, const struct btf_type *type,
-		 u32 *type_size, const struct btf_type **elem_type,
-		 u32 *total_nelems);
+		 u32 *type_size);
 
 #define for_each_member(i, struct_type, member)			\
 	for (i = 0, member = btf_type_member(struct_type);	\
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index 969c5d47f81f..4c3b543bb33b 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -298,8 +298,7 @@ static int check_zero_holes(const struct btf_type *t, void *data)
 			return -EINVAL;
 
 		mtype = btf_type_by_id(btf_vmlinux, member->type);
-		mtype = btf_resolve_size(btf_vmlinux, mtype, &msize,
-					 NULL, NULL);
+		mtype = btf_resolve_size(btf_vmlinux, mtype, &msize);
 		if (IS_ERR(mtype))
 			return PTR_ERR(mtype);
 		prev_mend = moff + msize;
@@ -396,8 +395,7 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 			u32 msize;
 
 			mtype = btf_type_by_id(btf_vmlinux, member->type);
-			mtype = btf_resolve_size(btf_vmlinux, mtype, &msize,
-						 NULL, NULL);
+			mtype = btf_resolve_size(btf_vmlinux, mtype, &msize);
 			if (IS_ERR(mtype)) {
 				err = PTR_ERR(mtype);
 				goto reset_unlock;
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 91afdd4c82e3..6ed4ecc60381 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -1088,10 +1088,10 @@ static const struct resolve_vertex *env_stack_peak(struct btf_verifier_env *env)
  * *elem_type: same as return type ("struct X")
  * *total_nelems: 1
  */
-const struct btf_type *
-btf_resolve_size(const struct btf *btf, const struct btf_type *type,
-		 u32 *type_size, const struct btf_type **elem_type,
-		 u32 *total_nelems)
+static const struct btf_type *
+__btf_resolve_size(const struct btf *btf, const struct btf_type *type,
+		   u32 *type_size, const struct btf_type **elem_type,
+		   u32 *total_nelems)
 {
 	const struct btf_type *array_type = NULL;
 	const struct btf_array *array;
@@ -1150,6 +1150,13 @@ resolved:
 	return array_type ? : type;
 }
 
+const struct btf_type *
+btf_resolve_size(const struct btf *btf, const struct btf_type *type,
+		 u32 *type_size)
+{
+	return __btf_resolve_size(btf, type, type_size, NULL, NULL);
+}
+
 /* The input param "type_id" must point to a needs_resolve type */
 static const struct btf_type *btf_type_id_resolve(const struct btf *btf,
 						  u32 *type_id)
@@ -3976,8 +3983,8 @@ error:
 		mtype = btf_type_by_id(btf_vmlinux, member->type);
 		mname = __btf_name_by_offset(btf_vmlinux, member->name_off);
 
-		mtype = btf_resolve_size(btf_vmlinux, mtype, &msize,
-					 &elem_type, &total_nelems);
+		mtype = __btf_resolve_size(btf_vmlinux, mtype, &msize,
+					   &elem_type, &total_nelems);
 		if (IS_ERR(mtype)) {
 			bpf_log(log, "field %s doesn't have size\n", mname);
 			return -EFAULT;
@@ -3991,7 +3998,7 @@ error:
 		if (btf_type_is_array(mtype)) {
 			u32 elem_idx;
 
-			/* btf_resolve_size() above helps to
+			/* __btf_resolve_size() above helps to
 			 * linearize a multi-dimensional array.
 			 *
 			 * The logic here is treating an array
-- 
cgit v1.2.3


From faaf4a790d93794b46d67e2fd69b8e5c8cae2d41 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Tue, 25 Aug 2020 21:21:18 +0200
Subject: bpf: Add btf_struct_ids_match function

Adding btf_struct_ids_match function to check if given address provided
by BTF object + offset is also address of another nested BTF object.

This allows to pass an argument to helper, which is defined via parent
BTF object + offset, like for bpf_d_path (added in following changes):

  SEC("fentry/filp_close")
  int BPF_PROG(prog_close, struct file *file, void *id)
  {
    ...
    ret = bpf_d_path(&file->f_path, ...

The first bpf_d_path argument is hold by verifier as BTF file object
plus offset of f_path member.

The btf_struct_ids_match function will walk the struct file object and
check if there's nested struct path object on the given offset.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200825192124.710397-9-jolsa@kernel.org
---
 include/linux/bpf.h   |  2 ++
 kernel/bpf/btf.c      | 31 +++++++++++++++++++++++++++++++
 kernel/bpf/verifier.c | 17 +++++++++++------
 3 files changed, 44 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 8c443b93ac11..540f5e6c3788 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1358,6 +1358,8 @@ int btf_struct_access(struct bpf_verifier_log *log,
 		      const struct btf_type *t, int off, int size,
 		      enum bpf_access_type atype,
 		      u32 *next_btf_id);
+bool btf_struct_ids_match(struct bpf_verifier_log *log,
+			  int off, u32 id, u32 need_type_id);
 int btf_resolve_helper_id(struct bpf_verifier_log *log,
 			  const struct bpf_func_proto *fn, int);
 
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index d8d64201c4e0..df966acaaeb1 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -4160,6 +4160,37 @@ int btf_struct_access(struct bpf_verifier_log *log,
 	return -EINVAL;
 }
 
+bool btf_struct_ids_match(struct bpf_verifier_log *log,
+			  int off, u32 id, u32 need_type_id)
+{
+	const struct btf_type *type;
+	int err;
+
+	/* Are we already done? */
+	if (need_type_id == id && off == 0)
+		return true;
+
+again:
+	type = btf_type_by_id(btf_vmlinux, id);
+	if (!type)
+		return false;
+	err = btf_struct_walk(log, type, off, 1, &id);
+	if (err != WALK_STRUCT)
+		return false;
+
+	/* We found nested struct object. If it matches
+	 * the requested ID, we're done. Otherwise let's
+	 * continue the search with offset 0 in the new
+	 * type.
+	 */
+	if (need_type_id != id) {
+		off = 0;
+		goto again;
+	}
+
+	return true;
+}
+
 int btf_resolve_helper_id(struct bpf_verifier_log *log,
 			  const struct bpf_func_proto *fn, int arg)
 {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 38748794518e..f003cee75d22 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3995,16 +3995,21 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 				goto err_type;
 		}
 	} else if (arg_type == ARG_PTR_TO_BTF_ID) {
+		bool ids_match = false;
+
 		expected_type = PTR_TO_BTF_ID;
 		if (type != expected_type)
 			goto err_type;
 		if (!fn->check_btf_id) {
 			if (reg->btf_id != meta->btf_id) {
-				verbose(env, "Helper has type %s got %s in R%d\n",
-					kernel_type_name(meta->btf_id),
-					kernel_type_name(reg->btf_id), regno);
-
-				return -EACCES;
+				ids_match = btf_struct_ids_match(&env->log, reg->off, reg->btf_id,
+								 meta->btf_id);
+				if (!ids_match) {
+					verbose(env, "Helper has type %s got %s in R%d\n",
+						kernel_type_name(meta->btf_id),
+						kernel_type_name(reg->btf_id), regno);
+					return -EACCES;
+				}
 			}
 		} else if (!fn->check_btf_id(reg->btf_id, arg)) {
 			verbose(env, "Helper does not support %s in R%d\n",
@@ -4012,7 +4017,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 
 			return -EACCES;
 		}
-		if (!tnum_is_const(reg->var_off) || reg->var_off.value || reg->off) {
+		if ((reg->off && !ids_match) || !tnum_is_const(reg->var_off) || reg->var_off.value) {
 			verbose(env, "R%d is a pointer to in-kernel struct with non-zero offset\n",
 				regno);
 			return -EACCES;
-- 
cgit v1.2.3


From eae2e83e62633a2659e3bc690facba1c2fc9c45b Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Tue, 25 Aug 2020 21:21:19 +0200
Subject: bpf: Add BTF_SET_START/END macros

Adding support to define sorted set of BTF ID values.

Following defines sorted set of BTF ID values:

  BTF_SET_START(btf_allowlist_d_path)
  BTF_ID(func, vfs_truncate)
  BTF_ID(func, vfs_fallocate)
  BTF_ID(func, dentry_open)
  BTF_ID(func, vfs_getattr)
  BTF_ID(func, filp_close)
  BTF_SET_END(btf_allowlist_d_path)

It defines following 'struct btf_id_set' variable to access
values and count:

  struct btf_id_set btf_allowlist_d_path;

Adding 'allowed' callback to struct bpf_func_proto, to allow
verifier the check on allowed callers.

Adding btf_id_set_contains function, which will be used by
allowed callbacks to verify the caller's BTF ID value is
within allowed set.

Also removing extra '\' in __BTF_ID_LIST macro.

Added BTF_SET_START_GLOBAL macro for global sets.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200825192124.710397-10-jolsa@kernel.org
---
 include/linux/bpf.h           |  4 ++++
 include/linux/btf_ids.h       | 51 ++++++++++++++++++++++++++++++++++++++++++-
 kernel/bpf/btf.c              | 14 ++++++++++++
 kernel/bpf/verifier.c         |  5 +++++
 tools/include/linux/btf_ids.h | 51 ++++++++++++++++++++++++++++++++++++++++++-
 5 files changed, 123 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 540f5e6c3788..a6131d95e31e 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -317,6 +317,7 @@ struct bpf_func_proto {
 						    * for this argument.
 						    */
 	int *ret_btf_id; /* return value btf_id */
+	bool (*allowed)(const struct bpf_prog *prog);
 };
 
 /* bpf_context is intentionally undefined structure. Pointer to bpf_context is
@@ -1878,4 +1879,7 @@ enum bpf_text_poke_type {
 int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 		       void *addr1, void *addr2);
 
+struct btf_id_set;
+bool btf_id_set_contains(struct btf_id_set *set, u32 id);
+
 #endif /* _LINUX_BPF_H */
diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h
index 4867d549e3c1..210b086188a3 100644
--- a/include/linux/btf_ids.h
+++ b/include/linux/btf_ids.h
@@ -3,6 +3,11 @@
 #ifndef _LINUX_BTF_IDS_H
 #define _LINUX_BTF_IDS_H
 
+struct btf_id_set {
+	u32 cnt;
+	u32 ids[];
+};
+
 #ifdef CONFIG_DEBUG_INFO_BTF
 
 #include <linux/compiler.h> /* for __PASTE */
@@ -62,7 +67,7 @@ asm(							\
 ".pushsection " BTF_IDS_SECTION ",\"a\";       \n"	\
 "." #scope " " #name ";                        \n"	\
 #name ":;                                      \n"	\
-".popsection;                                  \n");	\
+".popsection;                                  \n");
 
 #define BTF_ID_LIST(name)				\
 __BTF_ID_LIST(name, local)				\
@@ -88,12 +93,56 @@ asm(							\
 ".zero 4                                       \n"	\
 ".popsection;                                  \n");
 
+/*
+ * The BTF_SET_START/END macros pair defines sorted list of
+ * BTF IDs plus its members count, with following layout:
+ *
+ * BTF_SET_START(list)
+ * BTF_ID(type1, name1)
+ * BTF_ID(type2, name2)
+ * BTF_SET_END(list)
+ *
+ * __BTF_ID__set__list:
+ * .zero 4
+ * list:
+ * __BTF_ID__type1__name1__3:
+ * .zero 4
+ * __BTF_ID__type2__name2__4:
+ * .zero 4
+ *
+ */
+#define __BTF_SET_START(name, scope)			\
+asm(							\
+".pushsection " BTF_IDS_SECTION ",\"a\";       \n"	\
+"." #scope " __BTF_ID__set__" #name ";         \n"	\
+"__BTF_ID__set__" #name ":;                    \n"	\
+".zero 4                                       \n"	\
+".popsection;                                  \n");
+
+#define BTF_SET_START(name)				\
+__BTF_ID_LIST(name, local)				\
+__BTF_SET_START(name, local)
+
+#define BTF_SET_START_GLOBAL(name)			\
+__BTF_ID_LIST(name, globl)				\
+__BTF_SET_START(name, globl)
+
+#define BTF_SET_END(name)				\
+asm(							\
+".pushsection " BTF_IDS_SECTION ",\"a\";      \n"	\
+".size __BTF_ID__set__" #name ", .-" #name "  \n"	\
+".popsection;                                 \n");	\
+extern struct btf_id_set name;
+
 #else
 
 #define BTF_ID_LIST(name) static u32 name[5];
 #define BTF_ID(prefix, name)
 #define BTF_ID_UNUSED
 #define BTF_ID_LIST_GLOBAL(name) u32 name[1];
+#define BTF_SET_START(name) static struct btf_id_set name = { 0 };
+#define BTF_SET_START_GLOBAL(name) static struct btf_id_set name = { 0 };
+#define BTF_SET_END(name)
 
 #endif /* CONFIG_DEBUG_INFO_BTF */
 
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index df966acaaeb1..f9ac6935ab3c 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -21,6 +21,8 @@
 #include <linux/btf_ids.h>
 #include <linux/skmsg.h>
 #include <linux/perf_event.h>
+#include <linux/bsearch.h>
+#include <linux/btf_ids.h>
 #include <net/sock.h>
 
 /* BTF (BPF Type Format) is the meta data format which describes
@@ -4762,3 +4764,15 @@ u32 btf_id(const struct btf *btf)
 {
 	return btf->id;
 }
+
+static int btf_id_cmp_func(const void *a, const void *b)
+{
+	const int *pa = a, *pb = b;
+
+	return *pa - *pb;
+}
+
+bool btf_id_set_contains(struct btf_id_set *set, u32 id)
+{
+	return bsearch(&id, set->ids, set->cnt, sizeof(u32), btf_id_cmp_func) != NULL;
+}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index f003cee75d22..7e5908b83ec7 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4859,6 +4859,11 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 		return -EINVAL;
 	}
 
+	if (fn->allowed && !fn->allowed(env->prog)) {
+		verbose(env, "helper call is not allowed in probe\n");
+		return -EINVAL;
+	}
+
 	/* With LD_ABS/IND some JITs save/restore skb from r1. */
 	changes_data = bpf_helper_changes_pkt_data(fn->func);
 	if (changes_data && fn->arg1_type != ARG_PTR_TO_CTX) {
diff --git a/tools/include/linux/btf_ids.h b/tools/include/linux/btf_ids.h
index 4867d549e3c1..210b086188a3 100644
--- a/tools/include/linux/btf_ids.h
+++ b/tools/include/linux/btf_ids.h
@@ -3,6 +3,11 @@
 #ifndef _LINUX_BTF_IDS_H
 #define _LINUX_BTF_IDS_H
 
+struct btf_id_set {
+	u32 cnt;
+	u32 ids[];
+};
+
 #ifdef CONFIG_DEBUG_INFO_BTF
 
 #include <linux/compiler.h> /* for __PASTE */
@@ -62,7 +67,7 @@ asm(							\
 ".pushsection " BTF_IDS_SECTION ",\"a\";       \n"	\
 "." #scope " " #name ";                        \n"	\
 #name ":;                                      \n"	\
-".popsection;                                  \n");	\
+".popsection;                                  \n");
 
 #define BTF_ID_LIST(name)				\
 __BTF_ID_LIST(name, local)				\
@@ -88,12 +93,56 @@ asm(							\
 ".zero 4                                       \n"	\
 ".popsection;                                  \n");
 
+/*
+ * The BTF_SET_START/END macros pair defines sorted list of
+ * BTF IDs plus its members count, with following layout:
+ *
+ * BTF_SET_START(list)
+ * BTF_ID(type1, name1)
+ * BTF_ID(type2, name2)
+ * BTF_SET_END(list)
+ *
+ * __BTF_ID__set__list:
+ * .zero 4
+ * list:
+ * __BTF_ID__type1__name1__3:
+ * .zero 4
+ * __BTF_ID__type2__name2__4:
+ * .zero 4
+ *
+ */
+#define __BTF_SET_START(name, scope)			\
+asm(							\
+".pushsection " BTF_IDS_SECTION ",\"a\";       \n"	\
+"." #scope " __BTF_ID__set__" #name ";         \n"	\
+"__BTF_ID__set__" #name ":;                    \n"	\
+".zero 4                                       \n"	\
+".popsection;                                  \n");
+
+#define BTF_SET_START(name)				\
+__BTF_ID_LIST(name, local)				\
+__BTF_SET_START(name, local)
+
+#define BTF_SET_START_GLOBAL(name)			\
+__BTF_ID_LIST(name, globl)				\
+__BTF_SET_START(name, globl)
+
+#define BTF_SET_END(name)				\
+asm(							\
+".pushsection " BTF_IDS_SECTION ",\"a\";      \n"	\
+".size __BTF_ID__set__" #name ", .-" #name "  \n"	\
+".popsection;                                 \n");	\
+extern struct btf_id_set name;
+
 #else
 
 #define BTF_ID_LIST(name) static u32 name[5];
 #define BTF_ID(prefix, name)
 #define BTF_ID_UNUSED
 #define BTF_ID_LIST_GLOBAL(name) u32 name[1];
+#define BTF_SET_START(name) static struct btf_id_set name = { 0 };
+#define BTF_SET_START_GLOBAL(name) static struct btf_id_set name = { 0 };
+#define BTF_SET_END(name)
 
 #endif /* CONFIG_DEBUG_INFO_BTF */
 
-- 
cgit v1.2.3


From 01ccf592362a984534371b3596d4c953da6a7bb2 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Wed, 19 Aug 2020 21:55:05 +0200
Subject: sched: Bring the PF_IO_WORKER and PF_WQ_WORKER bits closer together

The bits PF_IO_WORKER and PF_WQ_WORKER are tested together in
sched_submit_work() which is considered to be a hot path.
If the two bits cross the 8 or 16 bit boundary then most architecture
require multiple load instructions in order to create the constant
value. Also, such a value can not be encoded within the compare opcode.

By moving the bit definition within the same block, the compiler can
create/use one immediate value.

For some reason gcc-10 on ARM64 requires both bits to be next to each
other in order to issue "tst reg, val; bne label". Otherwise the result
is "mov reg1, val; tst reg, reg1; bne label".

Move PF_VCPU out of the way so that PF_IO_WORKER can be next to
PF_WQ_WORKER.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200819195505.y3fxk72sotnrkczi@linutronix.de
---
 include/linux/sched.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 93ecd930efd3..2bf0af19a62a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1489,9 +1489,10 @@ extern struct pid *cad_pid;
 /*
  * Per process flags
  */
+#define PF_VCPU			0x00000001	/* I'm a virtual CPU */
 #define PF_IDLE			0x00000002	/* I am an IDLE thread */
 #define PF_EXITING		0x00000004	/* Getting shut down */
-#define PF_VCPU			0x00000010	/* I'm a virtual CPU */
+#define PF_IO_WORKER		0x00000010	/* Task is an IO worker */
 #define PF_WQ_WORKER		0x00000020	/* I'm a workqueue worker */
 #define PF_FORKNOEXEC		0x00000040	/* Forked but didn't exec */
 #define PF_MCE_PROCESS		0x00000080      /* Process policy on mce errors */
@@ -1515,7 +1516,6 @@ extern struct pid *cad_pid;
 #define PF_NO_SETAFFINITY	0x04000000	/* Userland is not allowed to meddle with cpus_mask */
 #define PF_MCE_EARLY		0x08000000      /* Early kill for mce process policy */
 #define PF_MEMALLOC_NOCMA	0x10000000	/* All allocation request will have _GFP_MOVABLE cleared */
-#define PF_IO_WORKER		0x20000000	/* Task is an IO worker */
 #define PF_FREEZER_SKIP		0x40000000	/* Freezer should not count it as freezable */
 #define PF_SUSPEND_TASK		0x80000000      /* This thread called freeze_processes() and should not be frozen */
 
-- 
cgit v1.2.3


From 8fca9494d4b4d6b57b1398cd473feb308df656db Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Tue, 25 Aug 2020 14:32:15 +0100
Subject: sched/topology: Move sd_flag_debug out of linux/sched/topology.h

Defining an array in a header imported all over the place clearly is a daft
idea, that still didn't stop me from doing it.

Leave a declaration of sd_flag_debug in topology.h and move its definition
to sched/debug.c.

Fixes: b6e862f38672 ("sched/topology: Define and assign sched_domain flag metadata")
Reported-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200825133216.9163-1-valentin.schneider@arm.com
---
 include/linux/sched/topology.h | 9 ++++-----
 kernel/sched/debug.c           | 6 ++++++
 2 files changed, 10 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 2d59ca77103e..b9b0dab4d067 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -33,14 +33,13 @@ static const unsigned int SD_DEGENERATE_GROUPS_MASK =
 #undef SD_FLAG
 
 #ifdef CONFIG_SCHED_DEBUG
-#define SD_FLAG(_name, mflags) [__##_name] = { .meta_flags = mflags, .name = #_name },
-static const struct {
+
+struct sd_flag_debug {
 	unsigned int meta_flags;
 	char *name;
-} sd_flag_debug[] = {
-#include <linux/sched/sd_flags.h>
 };
-#undef SD_FLAG
+extern const struct sd_flag_debug sd_flag_debug[];
+
 #endif
 
 #ifdef CONFIG_SCHED_SMT
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 0655524700d2..0d7896d2a0b2 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -245,6 +245,12 @@ set_table_entry(struct ctl_table *entry,
 	entry->proc_handler = proc_handler;
 }
 
+#define SD_FLAG(_name, mflags) [__##_name] = { .meta_flags = mflags, .name = #_name },
+const struct sd_flag_debug sd_flag_debug[] = {
+#include <linux/sched/sd_flags.h>
+};
+#undef SD_FLAG
+
 static int sd_ctl_doflags(struct ctl_table *table, int write,
 			  void *buffer, size_t *lenp, loff_t *ppos)
 {
-- 
cgit v1.2.3


From 4fc472f1214ef75e5450f207e23ff13af6eecad4 Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Tue, 25 Aug 2020 14:32:16 +0100
Subject: sched/topology: Move SD_DEGENERATE_GROUPS_MASK out of
 linux/sched/topology.h

SD_DEGENERATE_GROUPS_MASK is only useful for sched/topology.c, but still
gets defined for anyone who imports topology.h, leading to a flurry of
unused variable warnings.

Move it out of the header and place it next to the SD degeneration
functions in sched/topology.c.

Fixes: 4ee4ea443a5d ("sched/topology: Introduce SD metaflag for flags needing > 1 groups")
Reported-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200825133216.9163-2-valentin.schneider@arm.com
---
 include/linux/sched/topology.h | 7 -------
 kernel/sched/topology.c        | 7 +++++++
 2 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index b9b0dab4d067..9ef7bf686a9f 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -25,13 +25,6 @@ enum {
 };
 #undef SD_FLAG
 
-/* Generate a mask of SD flags with the SDF_NEEDS_GROUPS metaflag */
-#define SD_FLAG(name, mflags) (name * !!((mflags) & SDF_NEEDS_GROUPS)) |
-static const unsigned int SD_DEGENERATE_GROUPS_MASK =
-#include <linux/sched/sd_flags.h>
-0;
-#undef SD_FLAG
-
 #ifdef CONFIG_SCHED_DEBUG
 
 struct sd_flag_debug {
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index c674aaab312c..aa1676abc544 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -154,6 +154,13 @@ static inline bool sched_debug(void)
 }
 #endif /* CONFIG_SCHED_DEBUG */
 
+/* Generate a mask of SD flags with the SDF_NEEDS_GROUPS metaflag */
+#define SD_FLAG(name, mflags) (name * !!((mflags) & SDF_NEEDS_GROUPS)) |
+static const unsigned int SD_DEGENERATE_GROUPS_MASK =
+#include <linux/sched/sd_flags.h>
+0;
+#undef SD_FLAG
+
 static int sd_degenerate(struct sched_domain *sd)
 {
 	if (cpumask_weight(sched_domain_span(sd)) == 1)
-- 
cgit v1.2.3


From a435b9a14356587cf512ea6473368a579373c74c Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 29 Jul 2020 13:00:57 +0200
Subject: locking/refcount: Provide __refcount API to obtain the old value

David requested means to obtain the old/previous value from the
refcount API for tracing purposes.

Duplicate (most of) the API as __refcount*() with an additional
'int *' argument into which, if !NULL, the old value will be stored.

Requested-by: David Howells <dhowells@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lkml.kernel.org/r/20200729111120.GA2638@hirez.programming.kicks-ass.net
---
 include/linux/refcount.h | 65 ++++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 57 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/refcount.h b/include/linux/refcount.h
index 0e3ee25eb156..7fabb1af18e0 100644
--- a/include/linux/refcount.h
+++ b/include/linux/refcount.h
@@ -165,7 +165,7 @@ static inline unsigned int refcount_read(const refcount_t *r)
  *
  * Return: false if the passed refcount is 0, true otherwise
  */
-static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r)
+static inline __must_check bool __refcount_add_not_zero(int i, refcount_t *r, int *oldp)
 {
 	int old = refcount_read(r);
 
@@ -174,12 +174,20 @@ static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r)
 			break;
 	} while (!atomic_try_cmpxchg_relaxed(&r->refs, &old, old + i));
 
+	if (oldp)
+		*oldp = old;
+
 	if (unlikely(old < 0 || old + i < 0))
 		refcount_warn_saturate(r, REFCOUNT_ADD_NOT_ZERO_OVF);
 
 	return old;
 }
 
+static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r)
+{
+	return __refcount_add_not_zero(i, r, NULL);
+}
+
 /**
  * refcount_add - add a value to a refcount
  * @i: the value to add to the refcount
@@ -196,16 +204,24 @@ static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r)
  * cases, refcount_inc(), or one of its variants, should instead be used to
  * increment a reference count.
  */
-static inline void refcount_add(int i, refcount_t *r)
+static inline void __refcount_add(int i, refcount_t *r, int *oldp)
 {
 	int old = atomic_fetch_add_relaxed(i, &r->refs);
 
+	if (oldp)
+		*oldp = old;
+
 	if (unlikely(!old))
 		refcount_warn_saturate(r, REFCOUNT_ADD_UAF);
 	else if (unlikely(old < 0 || old + i < 0))
 		refcount_warn_saturate(r, REFCOUNT_ADD_OVF);
 }
 
+static inline void refcount_add(int i, refcount_t *r)
+{
+	__refcount_add(i, r, NULL);
+}
+
 /**
  * refcount_inc_not_zero - increment a refcount unless it is 0
  * @r: the refcount to increment
@@ -219,9 +235,14 @@ static inline void refcount_add(int i, refcount_t *r)
  *
  * Return: true if the increment was successful, false otherwise
  */
+static inline __must_check bool __refcount_inc_not_zero(refcount_t *r, int *oldp)
+{
+	return __refcount_add_not_zero(1, r, oldp);
+}
+
 static inline __must_check bool refcount_inc_not_zero(refcount_t *r)
 {
-	return refcount_add_not_zero(1, r);
+	return __refcount_inc_not_zero(r, NULL);
 }
 
 /**
@@ -236,9 +257,14 @@ static inline __must_check bool refcount_inc_not_zero(refcount_t *r)
  * Will WARN if the refcount is 0, as this represents a possible use-after-free
  * condition.
  */
+static inline void __refcount_inc(refcount_t *r, int *oldp)
+{
+	__refcount_add(1, r, oldp);
+}
+
 static inline void refcount_inc(refcount_t *r)
 {
-	refcount_add(1, r);
+	__refcount_inc(r, NULL);
 }
 
 /**
@@ -261,10 +287,13 @@ static inline void refcount_inc(refcount_t *r)
  *
  * Return: true if the resulting refcount is 0, false otherwise
  */
-static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r)
+static inline __must_check bool __refcount_sub_and_test(int i, refcount_t *r, int *oldp)
 {
 	int old = atomic_fetch_sub_release(i, &r->refs);
 
+	if (oldp)
+		*oldp = old;
+
 	if (old == i) {
 		smp_acquire__after_ctrl_dep();
 		return true;
@@ -276,6 +305,11 @@ static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r)
 	return false;
 }
 
+static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r)
+{
+	return __refcount_sub_and_test(i, r, NULL);
+}
+
 /**
  * refcount_dec_and_test - decrement a refcount and test if it is 0
  * @r: the refcount
@@ -289,9 +323,14 @@ static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r)
  *
  * Return: true if the resulting refcount is 0, false otherwise
  */
+static inline __must_check bool __refcount_dec_and_test(refcount_t *r, int *oldp)
+{
+	return __refcount_sub_and_test(1, r, oldp);
+}
+
 static inline __must_check bool refcount_dec_and_test(refcount_t *r)
 {
-	return refcount_sub_and_test(1, r);
+	return __refcount_dec_and_test(r, NULL);
 }
 
 /**
@@ -304,12 +343,22 @@ static inline __must_check bool refcount_dec_and_test(refcount_t *r)
  * Provides release memory ordering, such that prior loads and stores are done
  * before.
  */
-static inline void refcount_dec(refcount_t *r)
+static inline void __refcount_dec(refcount_t *r, int *oldp)
 {
-	if (unlikely(atomic_fetch_sub_release(1, &r->refs) <= 1))
+	int old = atomic_fetch_sub_release(1, &r->refs);
+
+	if (oldp)
+		*oldp = old;
+
+	if (unlikely(old <= 1))
 		refcount_warn_saturate(r, REFCOUNT_DEC_LEAK);
 }
 
+static inline void refcount_dec(refcount_t *r)
+{
+	__refcount_dec(r, NULL);
+}
+
 extern __must_check bool refcount_dec_if_one(refcount_t *r);
 extern __must_check bool refcount_dec_not_one(refcount_t *r);
 extern __must_check bool refcount_dec_and_mutex_lock(refcount_t *r, struct mutex *lock);
-- 
cgit v1.2.3


From a28e884b966e713da29caefbb347efea77367d22 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sun, 16 Aug 2020 17:02:00 -0700
Subject: seqlock: Fix multiple kernel-doc warnings

Fix kernel-doc warnings in <linux/seqlock.h>.

../include/linux/seqlock.h:152: warning: Incorrect use of kernel-doc format:  * seqcount_LOCKNAME_init() - runtime initializer for seqcount_LOCKNAME_t
../include/linux/seqlock.h:164: warning: Incorrect use of kernel-doc format:  * SEQCOUNT_LOCKTYPE() - Instantiate seqcount_LOCKNAME_t and helpers
../include/linux/seqlock.h:229: warning: Function parameter or member 'seq_name' not described in 'SEQCOUNT_LOCKTYPE_ZERO'
../include/linux/seqlock.h:229: warning: Function parameter or member 'assoc_lock' not described in 'SEQCOUNT_LOCKTYPE_ZERO'
../include/linux/seqlock.h:229: warning: Excess function parameter 'name' description in 'SEQCOUNT_LOCKTYPE_ZERO'
../include/linux/seqlock.h:229: warning: Excess function parameter 'lock' description in 'SEQCOUNT_LOCKTYPE_ZERO'
../include/linux/seqlock.h:695: warning: duplicate section name 'NOTE'

Demote kernel-doc notation for the macros "seqcount_LOCKNAME_init()" and
"SEQCOUNT_LOCKTYPE()"; scripts/kernel-doc does not handle them correctly.

Rename function parameters in SEQCNT_LOCKNAME_ZERO() documentation
to match the macro's argument names. Change the macro name in the
documentation to SEQCOUNT_LOCKTYPE_ZERO() to match the macro's name.

For raw_write_seqcount_latch(), rename the second NOTE: to NOTE2:
to prevent a kernel-doc warning. However, the generated output is not
quite as nice as it could be for this.

Fix a typo: s/LOCKTYPR/LOCKTYPE/

Fixes: 0efc94c5d15c ("seqcount: Compress SEQCNT_LOCKNAME_ZERO()")
Fixes: e4e9ab3f9f91 ("seqlock: Fold seqcount_LOCKNAME_init() definition")
Fixes: a8772dccb2ec ("seqlock: Fold seqcount_LOCKNAME_t definition")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200817000200.20993-1-rdunlap@infradead.org
---
 include/linux/seqlock.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 962d9768945f..300cbf312546 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -138,7 +138,7 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
 #endif
 
 /**
- * typedef seqcount_LOCKNAME_t - sequence counter with LOCKTYPR associated
+ * typedef seqcount_LOCKNAME_t - sequence counter with LOCKTYPE associated
  * @seqcount:	The real sequence counter
  * @lock:	Pointer to the associated spinlock
  *
@@ -148,7 +148,7 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
  * that the write side critical section is properly serialized.
  */
 
-/**
+/*
  * seqcount_LOCKNAME_init() - runtime initializer for seqcount_LOCKNAME_t
  * @s:		Pointer to the seqcount_LOCKNAME_t instance
  * @lock:	Pointer to the associated LOCKTYPE
@@ -217,7 +217,7 @@ SEQCOUNT_LOCKTYPE(rwlock_t,		rwlock,		false,	s->lock)
 SEQCOUNT_LOCKTYPE(struct mutex,		mutex,		true,	s->lock)
 SEQCOUNT_LOCKTYPE(struct ww_mutex,	ww_mutex,	true,	&s->lock->base)
 
-/**
+/*
  * SEQCNT_LOCKNAME_ZERO - static initializer for seqcount_LOCKNAME_t
  * @name:	Name of the seqcount_LOCKNAME_t instance
  * @lock:	Pointer to the associated LOCKTYPE
@@ -688,7 +688,7 @@ static inline int raw_read_seqcount_t_latch(seqcount_t *s)
  *	to miss an entire modification sequence, once it resumes it might
  *	observe the new entry.
  *
- * NOTE:
+ * NOTE2:
  *
  *	When data is a dynamic data structure; one should use regular RCU
  *	patterns to manage the lifetimes of the objects within.
-- 
cgit v1.2.3


From e918188611f073063415f40fae568fa4d86d9044 Mon Sep 17 00:00:00 2001
From: Boqun Feng <boqun.feng@gmail.com>
Date: Fri, 7 Aug 2020 15:42:20 +0800
Subject: locking: More accurate annotations for read_lock()

On the archs using QUEUED_RWLOCKS, read_lock() is not always a recursive
read lock, actually it's only recursive if in_interrupt() is true. So
change the annotation accordingly to catch more deadlocks.

Note we used to treat read_lock() as pure recursive read locks in
lib/locking-seftest.c, and this is useful, especially for the lockdep
development selftest, so we keep this via a variable to force switching
lock annotation for read_lock().

Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200807074238.1632519-2-boqun.feng@gmail.com
---
 include/linux/lockdep.h  | 23 ++++++++++++++++++++++-
 kernel/locking/lockdep.c | 14 ++++++++++++++
 lib/locking-selftest.c   | 11 +++++++++++
 3 files changed, 47 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 6a584b3e5c74..7cae5ea00d59 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -469,6 +469,20 @@ static inline void print_irqtrace_events(struct task_struct *curr)
 }
 #endif
 
+/* Variable used to make lockdep treat read_lock() as recursive in selftests */
+#ifdef CONFIG_DEBUG_LOCKING_API_SELFTESTS
+extern unsigned int force_read_lock_recursive;
+#else /* CONFIG_DEBUG_LOCKING_API_SELFTESTS */
+#define force_read_lock_recursive 0
+#endif /* CONFIG_DEBUG_LOCKING_API_SELFTESTS */
+
+#ifdef CONFIG_LOCKDEP
+extern bool read_lock_is_recursive(void);
+#else /* CONFIG_LOCKDEP */
+/* If !LOCKDEP, the value is meaningless */
+#define read_lock_is_recursive() 0
+#endif
+
 /*
  * For trivial one-depth nesting of a lock-class, the following
  * global define can be used. (Subsystems with multiple levels
@@ -490,7 +504,14 @@ static inline void print_irqtrace_events(struct task_struct *curr)
 #define spin_release(l, i)			lock_release(l, i)
 
 #define rwlock_acquire(l, s, t, i)		lock_acquire_exclusive(l, s, t, NULL, i)
-#define rwlock_acquire_read(l, s, t, i)		lock_acquire_shared_recursive(l, s, t, NULL, i)
+#define rwlock_acquire_read(l, s, t, i)					\
+do {									\
+	if (read_lock_is_recursive())					\
+		lock_acquire_shared_recursive(l, s, t, NULL, i);	\
+	else								\
+		lock_acquire_shared(l, s, t, NULL, i);			\
+} while (0)
+
 #define rwlock_release(l, i)			lock_release(l, i)
 
 #define seqcount_acquire(l, s, t, i)		lock_acquire_exclusive(l, s, t, NULL, i)
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 54b74fabf40c..77cd9e6520c4 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -4967,6 +4967,20 @@ static bool lockdep_nmi(void)
 	return true;
 }
 
+/*
+ * read_lock() is recursive if:
+ * 1. We force lockdep think this way in selftests or
+ * 2. The implementation is not queued read/write lock or
+ * 3. The locker is at an in_interrupt() context.
+ */
+bool read_lock_is_recursive(void)
+{
+	return force_read_lock_recursive ||
+	       !IS_ENABLED(CONFIG_QUEUED_RWLOCKS) ||
+	       in_interrupt();
+}
+EXPORT_SYMBOL_GPL(read_lock_is_recursive);
+
 /*
  * We are not always called with irqs disabled - do that here,
  * and also avoid lockdep recursion:
diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c
index 14f44f59e733..caadc4dd3368 100644
--- a/lib/locking-selftest.c
+++ b/lib/locking-selftest.c
@@ -28,6 +28,7 @@
  * Change this to 1 if you want to see the failure printouts:
  */
 static unsigned int debug_locks_verbose;
+unsigned int force_read_lock_recursive;
 
 static DEFINE_WD_CLASS(ww_lockdep);
 
@@ -1978,6 +1979,11 @@ void locking_selftest(void)
 		return;
 	}
 
+	/*
+	 * treats read_lock() as recursive read locks for testing purpose
+	 */
+	force_read_lock_recursive = 1;
+
 	/*
 	 * Run the testsuite:
 	 */
@@ -2073,6 +2079,11 @@ void locking_selftest(void)
 
 	ww_tests();
 
+	force_read_lock_recursive = 0;
+	/*
+	 * queued_read_lock() specific test cases can be put here
+	 */
+
 	if (unexpected_testcase_failures) {
 		printk("-----------------------------------------------------------------\n");
 		debug_locks = 0;
-- 
cgit v1.2.3


From bd76eca10de2eb9998d5125b08e8997cbf5508d5 Mon Sep 17 00:00:00 2001
From: Boqun Feng <boqun.feng@gmail.com>
Date: Fri, 7 Aug 2020 15:42:24 +0800
Subject: lockdep: Reduce the size of lock_list::distance

lock_list::distance is always not greater than MAX_LOCK_DEPTH (which
is 48 right now), so a u16 will fit. This patch reduces the size of
lock_list::distance to save space, so that we can introduce other fields
to help detect recursive read lock deadlocks without increasing the size
of lock_list structure.

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200807074238.1632519-6-boqun.feng@gmail.com
---
 include/linux/lockdep.h  | 2 +-
 kernel/locking/lockdep.c | 6 +++---
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 7cae5ea00d59..22750102b5fe 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -54,7 +54,7 @@ struct lock_list {
 	struct lock_class		*class;
 	struct lock_class		*links_to;
 	const struct lock_trace		*trace;
-	int				distance;
+	u16				distance;
 
 	/*
 	 * The parent field is used to implement breadth-first search, and the
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 150686a71be0..668a983d6405 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -1320,7 +1320,7 @@ static struct lock_list *alloc_list_entry(void)
  */
 static int add_lock_to_list(struct lock_class *this,
 			    struct lock_class *links_to, struct list_head *head,
-			    unsigned long ip, int distance,
+			    unsigned long ip, u16 distance,
 			    const struct lock_trace *trace)
 {
 	struct lock_list *entry;
@@ -2489,7 +2489,7 @@ check_deadlock(struct task_struct *curr, struct held_lock *next)
  */
 static int
 check_prev_add(struct task_struct *curr, struct held_lock *prev,
-	       struct held_lock *next, int distance,
+	       struct held_lock *next, u16 distance,
 	       struct lock_trace **const trace)
 {
 	struct lock_list *entry;
@@ -2622,7 +2622,7 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next)
 		goto out_bug;
 
 	for (;;) {
-		int distance = curr->lockdep_depth - depth + 1;
+		u16 distance = curr->lockdep_depth - depth + 1;
 		hlock = curr->held_locks + depth - 1;
 
 		/*
-- 
cgit v1.2.3


From 3454a36d6a39186de508dd43df590a6363364176 Mon Sep 17 00:00:00 2001
From: Boqun Feng <boqun.feng@gmail.com>
Date: Fri, 7 Aug 2020 15:42:25 +0800
Subject: lockdep: Introduce lock_list::dep

To add recursive read locks into the dependency graph, we need to store
the types of dependencies for the BFS later. There are four types of
dependencies:

*	Exclusive -> Non-recursive dependencies: EN
	e.g. write_lock(prev) held and try to acquire write_lock(next)
	or non-recursive read_lock(next), which can be represented as
	"prev -(EN)-> next"

*	Shared -> Non-recursive dependencies: SN
	e.g. read_lock(prev) held and try to acquire write_lock(next) or
	non-recursive read_lock(next), which can be represented as
	"prev -(SN)-> next"

*	Exclusive -> Recursive dependencies: ER
	e.g. write_lock(prev) held and try to acquire recursive
	read_lock(next), which can be represented as "prev -(ER)-> next"

*	Shared -> Recursive dependencies: SR
	e.g. read_lock(prev) held and try to acquire recursive
	read_lock(next), which can be represented as "prev -(SR)-> next"

So we use 4 bits for the presence of each type in lock_list::dep. Helper
functions and macros are also introduced to convert a pair of locks into
lock_list::dep bit and maintain the addition of different types of
dependencies.

Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200807074238.1632519-7-boqun.feng@gmail.com
---
 include/linux/lockdep.h  |  2 ++
 kernel/locking/lockdep.c | 92 +++++++++++++++++++++++++++++++++++++++++++++---
 2 files changed, 90 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 22750102b5fe..35c8bb0108dd 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -55,6 +55,8 @@ struct lock_list {
 	struct lock_class		*links_to;
 	const struct lock_trace		*trace;
 	u16				distance;
+	/* bitmap of different dependencies from head to this */
+	u8				dep;
 
 	/*
 	 * The parent field is used to implement breadth-first search, and the
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 668a983d6405..16ad1b74aa30 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -1320,7 +1320,7 @@ static struct lock_list *alloc_list_entry(void)
  */
 static int add_lock_to_list(struct lock_class *this,
 			    struct lock_class *links_to, struct list_head *head,
-			    unsigned long ip, u16 distance,
+			    unsigned long ip, u16 distance, u8 dep,
 			    const struct lock_trace *trace)
 {
 	struct lock_list *entry;
@@ -1334,6 +1334,7 @@ static int add_lock_to_list(struct lock_class *this,
 
 	entry->class = this;
 	entry->links_to = links_to;
+	entry->dep = dep;
 	entry->distance = distance;
 	entry->trace = trace;
 	/*
@@ -1498,6 +1499,57 @@ static inline bool bfs_error(enum bfs_result res)
 	return res < 0;
 }
 
+/*
+ * DEP_*_BIT in lock_list::dep
+ *
+ * For dependency @prev -> @next:
+ *
+ *   SR: @prev is shared reader (->read != 0) and @next is recursive reader
+ *       (->read == 2)
+ *   ER: @prev is exclusive locker (->read == 0) and @next is recursive reader
+ *   SN: @prev is shared reader and @next is non-recursive locker (->read != 2)
+ *   EN: @prev is exclusive locker and @next is non-recursive locker
+ *
+ * Note that we define the value of DEP_*_BITs so that:
+ *   bit0 is prev->read == 0
+ *   bit1 is next->read != 2
+ */
+#define DEP_SR_BIT (0 + (0 << 1)) /* 0 */
+#define DEP_ER_BIT (1 + (0 << 1)) /* 1 */
+#define DEP_SN_BIT (0 + (1 << 1)) /* 2 */
+#define DEP_EN_BIT (1 + (1 << 1)) /* 3 */
+
+#define DEP_SR_MASK (1U << (DEP_SR_BIT))
+#define DEP_ER_MASK (1U << (DEP_ER_BIT))
+#define DEP_SN_MASK (1U << (DEP_SN_BIT))
+#define DEP_EN_MASK (1U << (DEP_EN_BIT))
+
+static inline unsigned int
+__calc_dep_bit(struct held_lock *prev, struct held_lock *next)
+{
+	return (prev->read == 0) + ((next->read != 2) << 1);
+}
+
+static inline u8 calc_dep(struct held_lock *prev, struct held_lock *next)
+{
+	return 1U << __calc_dep_bit(prev, next);
+}
+
+/*
+ * calculate the dep_bit for backwards edges. We care about whether @prev is
+ * shared and whether @next is recursive.
+ */
+static inline unsigned int
+__calc_dep_bitb(struct held_lock *prev, struct held_lock *next)
+{
+	return (next->read != 2) + ((prev->read == 0) << 1);
+}
+
+static inline u8 calc_depb(struct held_lock *prev, struct held_lock *next)
+{
+	return 1U << __calc_dep_bitb(prev, next);
+}
+
 /*
  * Forward- or backward-dependency search, used for both circular dependency
  * checking and hardirq-unsafe/softirq-unsafe checking.
@@ -2552,7 +2604,35 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 		if (entry->class == hlock_class(next)) {
 			if (distance == 1)
 				entry->distance = 1;
-			return 1;
+			entry->dep |= calc_dep(prev, next);
+
+			/*
+			 * Also, update the reverse dependency in @next's
+			 * ->locks_before list.
+			 *
+			 *  Here we reuse @entry as the cursor, which is fine
+			 *  because we won't go to the next iteration of the
+			 *  outer loop:
+			 *
+			 *  For normal cases, we return in the inner loop.
+			 *
+			 *  If we fail to return, we have inconsistency, i.e.
+			 *  <prev>::locks_after contains <next> while
+			 *  <next>::locks_before doesn't contain <prev>. In
+			 *  that case, we return after the inner and indicate
+			 *  something is wrong.
+			 */
+			list_for_each_entry(entry, &hlock_class(next)->locks_before, entry) {
+				if (entry->class == hlock_class(prev)) {
+					if (distance == 1)
+						entry->distance = 1;
+					entry->dep |= calc_depb(prev, next);
+					return 1;
+				}
+			}
+
+			/* <prev> is not found in <next>::locks_before */
+			return 0;
 		}
 	}
 
@@ -2579,14 +2659,18 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 	 */
 	ret = add_lock_to_list(hlock_class(next), hlock_class(prev),
 			       &hlock_class(prev)->locks_after,
-			       next->acquire_ip, distance, *trace);
+			       next->acquire_ip, distance,
+			       calc_dep(prev, next),
+			       *trace);
 
 	if (!ret)
 		return 0;
 
 	ret = add_lock_to_list(hlock_class(prev), hlock_class(next),
 			       &hlock_class(next)->locks_before,
-			       next->acquire_ip, distance, *trace);
+			       next->acquire_ip, distance,
+			       calc_depb(prev, next),
+			       *trace);
 	if (!ret)
 		return 0;
 
-- 
cgit v1.2.3


From 6971c0f345620aae5e6172207a57b7524603a34e Mon Sep 17 00:00:00 2001
From: Boqun Feng <boqun.feng@gmail.com>
Date: Fri, 7 Aug 2020 15:42:26 +0800
Subject: lockdep: Extend __bfs() to work with multiple types of dependencies

Now we have four types of dependencies in the dependency graph, and not
all the pathes carry real dependencies (the dependencies that may cause
a deadlock), for example:

	Given lock A and B, if we have:

	CPU1			CPU2
	=============		==============
	write_lock(A);		read_lock(B);
	read_lock(B);		write_lock(A);

	(assuming read_lock(B) is a recursive reader)

	then we have dependencies A -(ER)-> B, and B -(SN)-> A, and a
	dependency path A -(ER)-> B -(SN)-> A.

	In lockdep w/o recursive locks, a dependency path from A to A
	means a deadlock. However, the above case is obviously not a
	deadlock, because no one holds B exclusively, therefore no one
	waits for the other to release B, so who get A first in CPU1 and
	CPU2 will run non-blockingly.

	As a result, dependency path A -(ER)-> B -(SN)-> A is not a
	real/strong dependency that could cause a deadlock.

From the observation above, we know that for a dependency path to be
real/strong, no two adjacent dependencies can be as -(*R)-> -(S*)->.

Now our mission is to make __bfs() traverse only the strong dependency
paths, which is simple: we record whether we only have -(*R)-> for the
previous lock_list of the path in lock_list::only_xr, and when we pick a
dependency in the traverse, we 1) filter out -(S*)-> dependency if the
previous lock_list only has -(*R)-> dependency (i.e. ->only_xr is true)
and 2) set the next lock_list::only_xr to true if we only have -(*R)->
left after we filter out dependencies based on 1), otherwise, set it to
false.

With this extension for __bfs(), we now need to initialize the root of
__bfs() properly (with a correct ->only_xr), to do so, we introduce some
helper functions, which also cleans up a little bit for the __bfs() root
initialization code.

Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200807074238.1632519-8-boqun.feng@gmail.com
---
 include/linux/lockdep.h  |   2 +
 kernel/locking/lockdep.c | 113 +++++++++++++++++++++++++++++++++++++++--------
 2 files changed, 96 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 35c8bb0108dd..57d642d378c7 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -57,6 +57,8 @@ struct lock_list {
 	u16				distance;
 	/* bitmap of different dependencies from head to this */
 	u8				dep;
+	/* used by BFS to record whether "prev -> this" only has -(*R)-> */
+	u8				only_xr;
 
 	/*
 	 * The parent field is used to implement breadth-first search, and the
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 16ad1b74aa30..5abc227db0e9 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -1551,8 +1551,72 @@ static inline u8 calc_depb(struct held_lock *prev, struct held_lock *next)
 }
 
 /*
- * Forward- or backward-dependency search, used for both circular dependency
- * checking and hardirq-unsafe/softirq-unsafe checking.
+ * Initialize a lock_list entry @lock belonging to @class as the root for a BFS
+ * search.
+ */
+static inline void __bfs_init_root(struct lock_list *lock,
+				   struct lock_class *class)
+{
+	lock->class = class;
+	lock->parent = NULL;
+	lock->only_xr = 0;
+}
+
+/*
+ * Initialize a lock_list entry @lock based on a lock acquisition @hlock as the
+ * root for a BFS search.
+ *
+ * ->only_xr of the initial lock node is set to @hlock->read == 2, to make sure
+ * that <prev> -> @hlock and @hlock -> <whatever __bfs() found> is not -(*R)->
+ * and -(S*)->.
+ */
+static inline void bfs_init_root(struct lock_list *lock,
+				 struct held_lock *hlock)
+{
+	__bfs_init_root(lock, hlock_class(hlock));
+	lock->only_xr = (hlock->read == 2);
+}
+
+/*
+ * Similar to bfs_init_root() but initialize the root for backwards BFS.
+ *
+ * ->only_xr of the initial lock node is set to @hlock->read != 0, to make sure
+ * that <next> -> @hlock and @hlock -> <whatever backwards BFS found> is not
+ * -(*S)-> and -(R*)-> (reverse order of -(*R)-> and -(S*)->).
+ */
+static inline void bfs_init_rootb(struct lock_list *lock,
+				  struct held_lock *hlock)
+{
+	__bfs_init_root(lock, hlock_class(hlock));
+	lock->only_xr = (hlock->read != 0);
+}
+
+/*
+ * Breadth-First Search to find a strong path in the dependency graph.
+ *
+ * @source_entry: the source of the path we are searching for.
+ * @data: data used for the second parameter of @match function
+ * @match: match function for the search
+ * @target_entry: pointer to the target of a matched path
+ * @offset: the offset to struct lock_class to determine whether it is
+ *          locks_after or locks_before
+ *
+ * We may have multiple edges (considering different kinds of dependencies,
+ * e.g. ER and SN) between two nodes in the dependency graph. But
+ * only the strong dependency path in the graph is relevant to deadlocks. A
+ * strong dependency path is a dependency path that doesn't have two adjacent
+ * dependencies as -(*R)-> -(S*)->, please see:
+ *
+ *         Documentation/locking/lockdep-design.rst
+ *
+ * for more explanation of the definition of strong dependency paths
+ *
+ * In __bfs(), we only traverse in the strong dependency path:
+ *
+ *     In lock_list::only_xr, we record whether the previous dependency only
+ *     has -(*R)-> in the search, and if it does (prev only has -(*R)->), we
+ *     filter out any -(S*)-> in the current dependency and after that, the
+ *     ->only_xr is set according to whether we only have -(*R)-> left.
  */
 static enum bfs_result __bfs(struct lock_list *source_entry,
 			     void *data,
@@ -1582,6 +1646,7 @@ static enum bfs_result __bfs(struct lock_list *source_entry,
 	__cq_enqueue(cq, source_entry);
 
 	while ((lock = __cq_dequeue(cq))) {
+		bool prev_only_xr;
 
 		if (!lock->class) {
 			ret = BFS_EINVALIDNODE;
@@ -1602,10 +1667,26 @@ static enum bfs_result __bfs(struct lock_list *source_entry,
 
 		head = get_dep_list(lock, offset);
 
-		DEBUG_LOCKS_WARN_ON(!irqs_disabled());
+		prev_only_xr = lock->only_xr;
 
 		list_for_each_entry_rcu(entry, head, entry) {
 			unsigned int cq_depth;
+			u8 dep = entry->dep;
+
+			/*
+			 * Mask out all -(S*)-> if we only have *R in previous
+			 * step, because -(*R)-> -(S*)-> don't make up a strong
+			 * dependency.
+			 */
+			if (prev_only_xr)
+				dep &= ~(DEP_SR_MASK | DEP_SN_MASK);
+
+			/* If nothing left, we skip */
+			if (!dep)
+				continue;
+
+			/* If there are only -(*R)-> left, set that for the next step */
+			entry->only_xr = !(dep & (DEP_SN_MASK | DEP_EN_MASK));
 
 			visit_lock_entry(entry, lock);
 			if (match(entry, data)) {
@@ -1827,8 +1908,7 @@ unsigned long lockdep_count_forward_deps(struct lock_class *class)
 	unsigned long ret, flags;
 	struct lock_list this;
 
-	this.parent = NULL;
-	this.class = class;
+	__bfs_init_root(&this, class);
 
 	raw_local_irq_save(flags);
 	lockdep_lock();
@@ -1854,8 +1934,7 @@ unsigned long lockdep_count_backward_deps(struct lock_class *class)
 	unsigned long ret, flags;
 	struct lock_list this;
 
-	this.parent = NULL;
-	this.class = class;
+	__bfs_init_root(&this, class);
 
 	raw_local_irq_save(flags);
 	lockdep_lock();
@@ -1898,10 +1977,9 @@ check_noncircular(struct held_lock *src, struct held_lock *target,
 {
 	enum bfs_result ret;
 	struct lock_list *target_entry;
-	struct lock_list src_entry = {
-		.class = hlock_class(src),
-		.parent = NULL,
-	};
+	struct lock_list src_entry;
+
+	bfs_init_root(&src_entry, src);
 
 	debug_atomic_inc(nr_cyclic_checks);
 
@@ -1937,10 +2015,9 @@ check_redundant(struct held_lock *src, struct held_lock *target)
 {
 	enum bfs_result ret;
 	struct lock_list *target_entry;
-	struct lock_list src_entry = {
-		.class = hlock_class(src),
-		.parent = NULL,
-	};
+	struct lock_list src_entry;
+
+	bfs_init_root(&src_entry, src);
 
 	debug_atomic_inc(nr_redundant_checks);
 
@@ -3556,8 +3633,7 @@ check_usage_forwards(struct task_struct *curr, struct held_lock *this,
 	struct lock_list root;
 	struct lock_list *target_entry;
 
-	root.parent = NULL;
-	root.class = hlock_class(this);
+	bfs_init_root(&root, this);
 	ret = find_usage_forwards(&root, lock_flag(bit), &target_entry);
 	if (bfs_error(ret)) {
 		print_bfs_bug(ret);
@@ -3583,8 +3659,7 @@ check_usage_backwards(struct task_struct *curr, struct held_lock *this,
 	struct lock_list root;
 	struct lock_list *target_entry;
 
-	root.parent = NULL;
-	root.class = hlock_class(this);
+	bfs_init_rootb(&root, this);
 	ret = find_usage_backwards(&root, lock_flag(bit), &target_entry);
 	if (bfs_error(ret)) {
 		print_bfs_bug(ret);
-- 
cgit v1.2.3


From a2bee00cccf4f2a80412d38328b92f448fd66935 Mon Sep 17 00:00:00 2001
From: Cezary Rojewski <cezary.rojewski@intel.com>
Date: Tue, 25 Aug 2020 22:17:43 +0200
Subject: spi: pxa2xx: Add SSC2 and SSPSP2 SSP registers

Update list of SSP registers with SSC2 and SSPSP2. These registers are
utilized by LPT/WPT AudioDSP architecture.

While SSC2 shares the same offset (0x40) as SSACDD, description of this
register for SSP device present on mentioned AudioDSP is different so
define separate constant to avoid any ambiguity.

Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Cezary Rojewski <cezary.rojewski@intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20200825201743.4926-1-cezary.rojewski@intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/pxa2xx_ssp.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h
index 6facf27865f9..1608c760fe91 100644
--- a/include/linux/pxa2xx_ssp.h
+++ b/include/linux/pxa2xx_ssp.h
@@ -186,6 +186,10 @@
 #define SSIRF			0x48		/* RX FIFO trigger level */
 #define SSIRF_RxThresh(x)	((x) - 1)
 
+/* LPT/WPT SSP */
+#define SSCR2		(0x40)	/* SSP Command / Status 2 */
+#define SSPSP2		(0x44)	/* SSP Programmable Serial Protocol 2 */
+
 enum pxa_ssp_type {
 	SSP_UNDEFINED = 0,
 	PXA25x_SSP,  /* pxa 210, 250, 255, 26x */
-- 
cgit v1.2.3


From 24da79902efc4a8443fae09e6c8e25b515bd8db2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 26 Aug 2020 06:50:16 -0700
Subject: inet: remove inet_sk_copy_descendant()

This is no longer used, SCTP now uses a private helper.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ipv6.h    | 11 -----------
 include/net/inet_sock.h |  7 -------
 2 files changed, 18 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index a44789d027cc..bac8f4fffbd6 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -345,17 +345,6 @@ static inline struct raw6_sock *raw6_sk(const struct sock *sk)
 	return (struct raw6_sock *)sk;
 }
 
-static inline void inet_sk_copy_descendant(struct sock *sk_to,
-					   const struct sock *sk_from)
-{
-	int ancestor_size = sizeof(struct inet_sock);
-
-	if (sk_from->sk_family == PF_INET6)
-		ancestor_size += sizeof(struct ipv6_pinfo);
-
-	__inet_sk_copy_descendant(sk_to, sk_from, ancestor_size);
-}
-
 #define __ipv6_only_sock(sk)	(sk->sk_ipv6only)
 #define ipv6_only_sock(sk)	(__ipv6_only_sock(sk))
 #define ipv6_sk_rxinfo(sk)	((sk)->sk_family == PF_INET6 && \
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index a3702d1d4875..89163ef8cf4b 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -296,13 +296,6 @@ static inline void __inet_sk_copy_descendant(struct sock *sk_to,
 	memcpy(inet_sk(sk_to) + 1, inet_sk(sk_from) + 1,
 	       sk_from->sk_prot->obj_size - ancestor_size);
 }
-#if !(IS_ENABLED(CONFIG_IPV6))
-static inline void inet_sk_copy_descendant(struct sock *sk_to,
-					   const struct sock *sk_from)
-{
-	__inet_sk_copy_descendant(sk_to, sk_from, sizeof(struct inet_sock));
-}
-#endif
 
 int inet_sk_rebuild_header(struct sock *sk);
 
-- 
cgit v1.2.3


From 5ca937fb5d6870735341d8fdacdd2b49618c35dc Mon Sep 17 00:00:00 2001
From: Subbaraman Narayanamurthy <subbaram@codeaurora.org>
Date: Thu, 13 Aug 2020 11:34:08 -0700
Subject: power: supply: add wireless type

Currently, power_supply framework supports only Battery, UPS,
Mains and USB power_supply_type. Add wireless power_supply_type
so that the drivers which supports wireless can register a power
supply class device with POWER_SUPPLY_TYPE_WIRELESS.

Signed-off-by: Subbaraman Narayanamurthy <subbaram@codeaurora.org>
Signed-off-by: Guru Das Srinagesh <gurus@codeaurora.org>
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 Documentation/ABI/testing/sysfs-class-power | 2 +-
 drivers/power/supply/power_supply_sysfs.c   | 1 +
 include/linux/power_supply.h                | 1 +
 3 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/Documentation/ABI/testing/sysfs-class-power b/Documentation/ABI/testing/sysfs-class-power
index 40213c73bc9c..651599fb18f8 100644
--- a/Documentation/ABI/testing/sysfs-class-power
+++ b/Documentation/ABI/testing/sysfs-class-power
@@ -34,7 +34,7 @@ Description:
 		Describes the main type of the supply.
 
 		Access: Read
-		Valid values: "Battery", "UPS", "Mains", "USB"
+		Valid values: "Battery", "UPS", "Mains", "USB", "Wireless"
 
 ===== Battery Properties =====
 
diff --git a/drivers/power/supply/power_supply_sysfs.c b/drivers/power/supply/power_supply_sysfs.c
index 3d383086018c..a616b9d8f43c 100644
--- a/drivers/power/supply/power_supply_sysfs.c
+++ b/drivers/power/supply/power_supply_sysfs.c
@@ -56,6 +56,7 @@ static const char * const POWER_SUPPLY_TYPE_TEXT[] = {
 	[POWER_SUPPLY_TYPE_USB_PD]		= "USB_PD",
 	[POWER_SUPPLY_TYPE_USB_PD_DRP]		= "USB_PD_DRP",
 	[POWER_SUPPLY_TYPE_APPLE_BRICK_ID]	= "BrickID",
+	[POWER_SUPPLY_TYPE_WIRELESS]		= "Wireless",
 };
 
 static const char * const POWER_SUPPLY_USB_TYPE_TEXT[] = {
diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h
index d0684362a392..81a55e974feb 100644
--- a/include/linux/power_supply.h
+++ b/include/linux/power_supply.h
@@ -186,6 +186,7 @@ enum power_supply_type {
 	POWER_SUPPLY_TYPE_USB_PD,		/* Power Delivery Port */
 	POWER_SUPPLY_TYPE_USB_PD_DRP,		/* PD Dual Role Port */
 	POWER_SUPPLY_TYPE_APPLE_BRICK_ID,	/* Apple Charging Method */
+	POWER_SUPPLY_TYPE_WIRELESS,		/* Wireless */
 };
 
 enum power_supply_usb_type {
-- 
cgit v1.2.3


From 7f9fb67358a2bcaacbdfeee12e0f19e98c8bdf55 Mon Sep 17 00:00:00 2001
From: Xu Yilun <yilun.xu@intel.com>
Date: Wed, 19 Aug 2020 15:34:56 +0800
Subject: regmap: add Intel SPI Slave to AVMM Bus Bridge support

This patch add support for regmap APIs that are intended to be used by
the drivers of some SPI slave chips which integrate the "SPI slave to
Avalon Master Bridge" (spi-avmm) IP.

The spi-avmm IP acts as a bridge to convert encoded streams of bytes
from the host to the chip's internal register read/write on Avalon bus.
The driver implements the register read/write operations for a generic
SPI master to access the sub devices behind spi-avmm bridge.

Signed-off-by: Xu Yilun <yilun.xu@intel.com>
Signed-off-by: Wu Hao <hao.wu@intel.com>
Signed-off-by: Matthew Gerlach <matthew.gerlach@linux.intel.com>
Signed-off-by: Russ Weight <russell.h.weight@intel.com>
Reviewed-by: Tom Rix <trix@redhat.com>
Reviewed-by: Luis Claudio R. Goncalves <lgoncalv@redhat.com>
Link: https://lore.kernel.org/r/1597822497-25107-2-git-send-email-yilun.xu@intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/base/regmap/Kconfig           |   6 +-
 drivers/base/regmap/Makefile          |   1 +
 drivers/base/regmap/regmap-spi-avmm.c | 719 ++++++++++++++++++++++++++++++++++
 include/linux/regmap.h                |  36 ++
 4 files changed, 761 insertions(+), 1 deletion(-)
 create mode 100644 drivers/base/regmap/regmap-spi-avmm.c

(limited to 'include/linux')

diff --git a/drivers/base/regmap/Kconfig b/drivers/base/regmap/Kconfig
index 1d1d26b0d279..bcb90d8c3960 100644
--- a/drivers/base/regmap/Kconfig
+++ b/drivers/base/regmap/Kconfig
@@ -4,7 +4,7 @@
 # subsystems should select the appropriate symbols.
 
 config REGMAP
-	default y if (REGMAP_I2C || REGMAP_SPI || REGMAP_SPMI || REGMAP_W1 || REGMAP_AC97 || REGMAP_MMIO || REGMAP_IRQ || REGMAP_SOUNDWIRE || REGMAP_SCCB || REGMAP_I3C)
+	default y if (REGMAP_I2C || REGMAP_SPI || REGMAP_SPMI || REGMAP_W1 || REGMAP_AC97 || REGMAP_MMIO || REGMAP_IRQ || REGMAP_SOUNDWIRE || REGMAP_SCCB || REGMAP_I3C || REGMAP_SPI_AVMM)
 	select IRQ_DOMAIN if REGMAP_IRQ
 	bool
 
@@ -53,3 +53,7 @@ config REGMAP_SCCB
 config REGMAP_I3C
 	tristate
 	depends on I3C
+
+config REGMAP_SPI_AVMM
+	tristate
+	depends on SPI
diff --git a/drivers/base/regmap/Makefile b/drivers/base/regmap/Makefile
index ff6c7d8ec1cd..ac1b69ee4051 100644
--- a/drivers/base/regmap/Makefile
+++ b/drivers/base/regmap/Makefile
@@ -17,3 +17,4 @@ obj-$(CONFIG_REGMAP_W1) += regmap-w1.o
 obj-$(CONFIG_REGMAP_SOUNDWIRE) += regmap-sdw.o
 obj-$(CONFIG_REGMAP_SCCB) += regmap-sccb.o
 obj-$(CONFIG_REGMAP_I3C) += regmap-i3c.o
+obj-$(CONFIG_REGMAP_SPI_AVMM) += regmap-spi-avmm.o
diff --git a/drivers/base/regmap/regmap-spi-avmm.c b/drivers/base/regmap/regmap-spi-avmm.c
new file mode 100644
index 000000000000..ad1da83e849f
--- /dev/null
+++ b/drivers/base/regmap/regmap-spi-avmm.c
@@ -0,0 +1,719 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Register map access API - SPI AVMM support
+//
+// Copyright (C) 2018-2020 Intel Corporation. All rights reserved.
+
+#include <linux/module.h>
+#include <linux/regmap.h>
+#include <linux/spi/spi.h>
+
+/*
+ * This driver implements the regmap operations for a generic SPI
+ * master to access the registers of the spi slave chip which has an
+ * Avalone bus in it.
+ *
+ * The "SPI slave to Avalon Master Bridge" (spi-avmm) IP should be integrated
+ * in the spi slave chip. The IP acts as a bridge to convert encoded streams of
+ * bytes from the host to the internal register read/write on Avalon bus. In
+ * order to issue register access requests to the slave chip, the host should
+ * send formatted bytes that conform to the transfer protocol.
+ * The transfer protocol contains 3 layers: transaction layer, packet layer
+ * and physical layer.
+ *
+ * Reference Documents could be found at:
+ * https://www.intel.com/content/www/us/en/programmable/documentation/sfo1400787952932.html
+ *
+ * Chapter "SPI Slave/JTAG to Avalon Master Bridge Cores" is a general
+ * introduction to the protocol.
+ *
+ * Chapter "Avalon Packets to Transactions Converter Core" describes
+ * the transaction layer.
+ *
+ * Chapter "Avalon-ST Bytes to Packets and Packets to Bytes Converter Cores"
+ * describes the packet layer.
+ *
+ * Chapter "Avalon-ST Serial Peripheral Interface Core" describes the
+ * physical layer.
+ *
+ *
+ * When host issues a regmap read/write, the driver will transform the request
+ * to byte stream layer by layer. It formats the register addr, value and
+ * length to the transaction layer request, then converts the request to packet
+ * layer bytes stream and then to physical layer bytes stream. Finally the
+ * driver sends the formatted byte stream over SPI bus to the slave chip.
+ *
+ * The spi-avmm IP on the slave chip decodes the byte stream and initiates
+ * register read/write on its internal Avalon bus, and then encodes the
+ * response to byte stream and sends back to host.
+ *
+ * The driver receives the byte stream, reverses the 3 layers transformation,
+ * and finally gets the response value (read out data for register read,
+ * successful written size for register write).
+ */
+
+#define PKT_SOP			0x7a
+#define PKT_EOP			0x7b
+#define PKT_CHANNEL		0x7c
+#define PKT_ESC			0x7d
+
+#define PHY_IDLE		0x4a
+#define PHY_ESC			0x4d
+
+#define TRANS_CODE_WRITE	0x0
+#define TRANS_CODE_SEQ_WRITE	0x4
+#define TRANS_CODE_READ		0x10
+#define TRANS_CODE_SEQ_READ	0x14
+#define TRANS_CODE_NO_TRANS	0x7f
+
+#define SPI_AVMM_XFER_TIMEOUT	(msecs_to_jiffies(200))
+
+/* slave's register addr is 32 bits */
+#define SPI_AVMM_REG_SIZE		4UL
+/* slave's register value is 32 bits */
+#define SPI_AVMM_VAL_SIZE		4UL
+
+/*
+ * max rx size could be larger. But considering the buffer consuming,
+ * it is proper that we limit 1KB xfer at max.
+ */
+#define MAX_READ_CNT		256UL
+#define MAX_WRITE_CNT		1UL
+
+struct trans_req_header {
+	u8 code;
+	u8 rsvd;
+	__be16 size;
+	__be32 addr;
+} __packed;
+
+struct trans_resp_header {
+	u8 r_code;
+	u8 rsvd;
+	__be16 size;
+} __packed;
+
+#define TRANS_REQ_HD_SIZE	(sizeof(struct trans_req_header))
+#define TRANS_RESP_HD_SIZE	(sizeof(struct trans_resp_header))
+
+/*
+ * In transaction layer,
+ * the write request format is: Transaction request header + data
+ * the read request format is: Transaction request header
+ * the write response format is: Transaction response header
+ * the read response format is: pure data, no Transaction response header
+ */
+#define TRANS_WR_TX_SIZE(n)	(TRANS_REQ_HD_SIZE + SPI_AVMM_VAL_SIZE * (n))
+#define TRANS_RD_TX_SIZE	TRANS_REQ_HD_SIZE
+#define TRANS_TX_MAX		TRANS_WR_TX_SIZE(MAX_WRITE_CNT)
+
+#define TRANS_RD_RX_SIZE(n)	(SPI_AVMM_VAL_SIZE * (n))
+#define TRANS_WR_RX_SIZE	TRANS_RESP_HD_SIZE
+#define TRANS_RX_MAX		TRANS_RD_RX_SIZE(MAX_READ_CNT)
+
+/* tx & rx share one transaction layer buffer */
+#define TRANS_BUF_SIZE		((TRANS_TX_MAX > TRANS_RX_MAX) ?	\
+				 TRANS_TX_MAX : TRANS_RX_MAX)
+
+/*
+ * In tx phase, the host prepares all the phy layer bytes of a request in the
+ * phy buffer and sends them in a batch.
+ *
+ * The packet layer and physical layer defines several special chars for
+ * various purpose, when a transaction layer byte hits one of these special
+ * chars, it should be escaped. The escape rule is, "Escape char first,
+ * following the byte XOR'ed with 0x20".
+ *
+ * This macro defines the max possible length of the phy data. In the worst
+ * case, all transaction layer bytes need to be escaped (so the data length
+ * doubles), plus 4 special chars (SOP, CHANNEL, CHANNEL_NUM, EOP). Finally
+ * we should make sure the length is aligned to SPI BPW.
+ */
+#define PHY_TX_MAX		ALIGN(2 * TRANS_TX_MAX + 4, 4)
+
+/*
+ * Unlike tx, phy rx is affected by possible PHY_IDLE bytes from slave, the max
+ * length of the rx bit stream is unpredictable. So the driver reads the words
+ * one by one, and parses each word immediately into transaction layer buffer.
+ * Only one word length of phy buffer is used for rx.
+ */
+#define PHY_BUF_SIZE		PHY_TX_MAX
+
+/**
+ * struct spi_avmm_bridge - SPI slave to AVMM bus master bridge
+ *
+ * @spi: spi slave associated with this bridge.
+ * @word_len: bytes of word for spi transfer.
+ * @trans_len: length of valid data in trans_buf.
+ * @phy_len: length of valid data in phy_buf.
+ * @trans_buf: the bridge buffer for transaction layer data.
+ * @phy_buf: the bridge buffer for physical layer data.
+ * @swap_words: the word swapping cb for phy data. NULL if not needed.
+ *
+ * As a device's registers are implemented on the AVMM bus address space, it
+ * requires the driver to issue formatted requests to spi slave to AVMM bus
+ * master bridge to perform register access.
+ */
+struct spi_avmm_bridge {
+	struct spi_device *spi;
+	unsigned char word_len;
+	unsigned int trans_len;
+	unsigned int phy_len;
+	/* bridge buffer used in translation between protocol layers */
+	char trans_buf[TRANS_BUF_SIZE];
+	char phy_buf[PHY_BUF_SIZE];
+	void (*swap_words)(char *buf, unsigned int len);
+};
+
+static void br_swap_words_32(char *buf, unsigned int len)
+{
+	u32 *p = (u32 *)buf;
+	unsigned int count;
+
+	count = len / 4;
+	while (count--) {
+		*p = swab32p(p);
+		p++;
+	}
+}
+
+/*
+ * Format transaction layer data in br->trans_buf according to the register
+ * access request, Store valid transaction layer data length in br->trans_len.
+ */
+static int br_trans_tx_prepare(struct spi_avmm_bridge *br, bool is_read, u32 reg,
+			       u32 *wr_val, u32 count)
+{
+	struct trans_req_header *header;
+	unsigned int trans_len;
+	u8 code;
+	__le32 *data;
+	int i;
+
+	if (is_read) {
+		if (count == 1)
+			code = TRANS_CODE_READ;
+		else
+			code = TRANS_CODE_SEQ_READ;
+	} else {
+		if (count == 1)
+			code = TRANS_CODE_WRITE;
+		else
+			code = TRANS_CODE_SEQ_WRITE;
+	}
+
+	header = (struct trans_req_header *)br->trans_buf;
+	header->code = code;
+	header->rsvd = 0;
+	header->size = cpu_to_be16((u16)count * SPI_AVMM_VAL_SIZE);
+	header->addr = cpu_to_be32(reg);
+
+	trans_len = TRANS_REQ_HD_SIZE;
+
+	if (!is_read) {
+		trans_len += SPI_AVMM_VAL_SIZE * count;
+		if (trans_len > sizeof(br->trans_buf))
+			return -ENOMEM;
+
+		data = (__le32 *)(br->trans_buf + TRANS_REQ_HD_SIZE);
+
+		for (i = 0; i < count; i++)
+			*data++ = cpu_to_le32(*wr_val++);
+	}
+
+	/* Store valid trans data length for next layer */
+	br->trans_len = trans_len;
+
+	return 0;
+}
+
+/*
+ * Convert transaction layer data (in br->trans_buf) to phy layer data, store
+ * them in br->phy_buf. Pad the phy_buf aligned with SPI's BPW. Store valid phy
+ * layer data length in br->phy_len.
+ *
+ * phy_buf len should be aligned with SPI's BPW. Spare bytes should be padded
+ * with PHY_IDLE, then the slave will just drop them.
+ *
+ * The driver will not simply pad 4a at the tail. The concern is that driver
+ * will not store MISO data during tx phase, if the driver pads 4a at the tail,
+ * it is possible that if the slave is fast enough to response at the padding
+ * time. As a result these rx bytes are lost. In the following case, 7a,7c,00
+ * will lost.
+ * MOSI ...|7a|7c|00|10| |00|00|04|02| |4b|7d|5a|7b| |40|4a|4a|4a| |XX|XX|...
+ * MISO ...|4a|4a|4a|4a| |4a|4a|4a|4a| |4a|4a|4a|4a| |4a|7a|7c|00| |78|56|...
+ *
+ * So the driver moves EOP and bytes after EOP to the end of the aligned size,
+ * then fill the hole with PHY_IDLE. As following:
+ * before pad ...|7a|7c|00|10| |00|00|04|02| |4b|7d|5a|7b| |40|
+ * after pad  ...|7a|7c|00|10| |00|00|04|02| |4b|7d|5a|4a| |4a|4a|7b|40|
+ * Then if the slave will not get the entire packet before the tx phase is
+ * over, it can't responsed to anything either.
+ */
+static int br_pkt_phy_tx_prepare(struct spi_avmm_bridge *br)
+{
+	char *tb, *tb_end, *pb, *pb_limit, *pb_eop = NULL;
+	unsigned int aligned_phy_len, move_size;
+	bool need_esc = false;
+
+	tb = br->trans_buf;
+	tb_end = tb + br->trans_len;
+	pb = br->phy_buf;
+	pb_limit = pb + ARRAY_SIZE(br->phy_buf);
+
+	*pb++ = PKT_SOP;
+
+	/*
+	 * The driver doesn't support multiple channels so the channel number
+	 * is always 0.
+	 */
+	*pb++ = PKT_CHANNEL;
+	*pb++ = 0x0;
+
+	for (; pb < pb_limit && tb < tb_end; pb++) {
+		if (need_esc) {
+			*pb = *tb++ ^ 0x20;
+			need_esc = false;
+			continue;
+		}
+
+		/* EOP should be inserted before the last valid char */
+		if (tb == tb_end - 1 && !pb_eop) {
+			*pb = PKT_EOP;
+			pb_eop = pb;
+			continue;
+		}
+
+		/*
+		 * insert an ESCAPE char if the data value equals any special
+		 * char.
+		 */
+		switch (*tb) {
+		case PKT_SOP:
+		case PKT_EOP:
+		case PKT_CHANNEL:
+		case PKT_ESC:
+			*pb = PKT_ESC;
+			need_esc = true;
+			break;
+		case PHY_IDLE:
+		case PHY_ESC:
+			*pb = PHY_ESC;
+			need_esc = true;
+			break;
+		default:
+			*pb = *tb++;
+			break;
+		}
+	}
+
+	/* The phy buffer is used out but transaction layer data remains */
+	if (tb < tb_end)
+		return -ENOMEM;
+
+	/* Store valid phy data length for spi transfer */
+	br->phy_len = pb - br->phy_buf;
+
+	if (br->word_len == 1)
+		return 0;
+
+	/* Do phy buf padding if word_len > 1 byte. */
+	aligned_phy_len = ALIGN(br->phy_len, br->word_len);
+	if (aligned_phy_len > sizeof(br->phy_buf))
+		return -ENOMEM;
+
+	if (aligned_phy_len == br->phy_len)
+		return 0;
+
+	/* move EOP and bytes after EOP to the end of aligned size */
+	move_size = pb - pb_eop;
+	memmove(&br->phy_buf[aligned_phy_len - move_size], pb_eop, move_size);
+
+	/* fill the hole with PHY_IDLEs */
+	memset(pb_eop, PHY_IDLE, aligned_phy_len - br->phy_len);
+
+	/* update the phy data length */
+	br->phy_len = aligned_phy_len;
+
+	return 0;
+}
+
+/*
+ * In tx phase, the slave only returns PHY_IDLE (0x4a). So the driver will
+ * ignore rx in tx phase.
+ */
+static int br_do_tx(struct spi_avmm_bridge *br)
+{
+	/* reorder words for spi transfer */
+	if (br->swap_words)
+		br->swap_words(br->phy_buf, br->phy_len);
+
+	/* send all data in phy_buf  */
+	return spi_write(br->spi, br->phy_buf, br->phy_len);
+}
+
+/*
+ * This function read the rx byte stream from SPI word by word and convert
+ * them to transaction layer data in br->trans_buf. It also stores the length
+ * of rx transaction layer data in br->trans_len
+ *
+ * The slave may send an unknown number of PHY_IDLEs in rx phase, so we cannot
+ * prepare a fixed length buffer to receive all of the rx data in a batch. We
+ * have to read word by word and convert them to transaction layer data at
+ * once.
+ */
+static int br_do_rx_and_pkt_phy_parse(struct spi_avmm_bridge *br)
+{
+	bool eop_found = false, channel_found = false, esc_found = false;
+	bool valid_word = false, last_try = false;
+	struct device *dev = &br->spi->dev;
+	char *pb, *tb_limit, *tb = NULL;
+	unsigned long poll_timeout;
+	int ret, i;
+
+	tb_limit = br->trans_buf + ARRAY_SIZE(br->trans_buf);
+	pb = br->phy_buf;
+	poll_timeout = jiffies + SPI_AVMM_XFER_TIMEOUT;
+	while (tb < tb_limit) {
+		ret = spi_read(br->spi, pb, br->word_len);
+		if (ret)
+			return ret;
+
+		/* reorder the word back */
+		if (br->swap_words)
+			br->swap_words(pb, br->word_len);
+
+		valid_word = false;
+		for (i = 0; i < br->word_len; i++) {
+			/* drop everything before first SOP */
+			if (!tb && pb[i] != PKT_SOP)
+				continue;
+
+			/* drop PHY_IDLE */
+			if (pb[i] == PHY_IDLE)
+				continue;
+
+			valid_word = true;
+
+			/*
+			 * We don't support multiple channels, so error out if
+			 * a non-zero channel number is found.
+			 */
+			if (channel_found) {
+				if (pb[i] != 0) {
+					dev_err(dev, "%s channel num != 0\n",
+						__func__);
+					return -EFAULT;
+				}
+
+				channel_found = false;
+				continue;
+			}
+
+			switch (pb[i]) {
+			case PKT_SOP:
+				/*
+				 * reset the parsing if a second SOP appears.
+				 */
+				tb = br->trans_buf;
+				eop_found = false;
+				channel_found = false;
+				esc_found = false;
+				break;
+			case PKT_EOP:
+				/*
+				 * No special char is expected after ESC char.
+				 * No special char (except ESC & PHY_IDLE) is
+				 * expected after EOP char.
+				 *
+				 * The special chars are all dropped.
+				 */
+				if (esc_found || eop_found)
+					return -EFAULT;
+
+				eop_found = true;
+				break;
+			case PKT_CHANNEL:
+				if (esc_found || eop_found)
+					return -EFAULT;
+
+				channel_found = true;
+				break;
+			case PKT_ESC:
+			case PHY_ESC:
+				if (esc_found)
+					return -EFAULT;
+
+				esc_found = true;
+				break;
+			default:
+				/* Record the normal byte in trans_buf. */
+				if (esc_found) {
+					*tb++ = pb[i] ^ 0x20;
+					esc_found = false;
+				} else {
+					*tb++ = pb[i];
+				}
+
+				/*
+				 * We get the last normal byte after EOP, it is
+				 * time we finish. Normally the function should
+				 * return here.
+				 */
+				if (eop_found) {
+					br->trans_len = tb - br->trans_buf;
+					return 0;
+				}
+			}
+		}
+
+		if (valid_word) {
+			/* update poll timeout when we get valid word */
+			poll_timeout = jiffies + SPI_AVMM_XFER_TIMEOUT;
+			last_try = false;
+		} else {
+			/*
+			 * We timeout when rx keeps invalid for some time. But
+			 * it is possible we are scheduled out for long time
+			 * after a spi_read. So when we are scheduled in, a SW
+			 * timeout happens. But actually HW may have worked fine and
+			 * has been ready long time ago. So we need to do an extra
+			 * read, if we get a valid word then we could continue rx,
+			 * otherwise real a HW issue happens.
+			 */
+			if (last_try)
+				return -ETIMEDOUT;
+
+			if (time_after(jiffies, poll_timeout))
+				last_try = true;
+		}
+	}
+
+	/*
+	 * We have used out all transfer layer buffer but cannot find the end
+	 * of the byte stream.
+	 */
+	dev_err(dev, "%s transfer buffer is full but rx doesn't end\n",
+		__func__);
+
+	return -EFAULT;
+}
+
+/*
+ * For read transactions, the avmm bus will directly return register values
+ * without transaction response header.
+ */
+static int br_rd_trans_rx_parse(struct spi_avmm_bridge *br,
+				u32 *val, unsigned int expected_count)
+{
+	unsigned int i, trans_len = br->trans_len;
+	__le32 *data;
+
+	if (expected_count * SPI_AVMM_VAL_SIZE != trans_len)
+		return -EFAULT;
+
+	data = (__le32 *)br->trans_buf;
+	for (i = 0; i < expected_count; i++)
+		*val++ = le32_to_cpu(*data++);
+
+	return 0;
+}
+
+/*
+ * For write transactions, the slave will return a transaction response
+ * header.
+ */
+static int br_wr_trans_rx_parse(struct spi_avmm_bridge *br,
+				unsigned int expected_count)
+{
+	unsigned int trans_len = br->trans_len;
+	struct trans_resp_header *resp;
+	u8 code;
+	u16 val_len;
+
+	if (trans_len != TRANS_RESP_HD_SIZE)
+		return -EFAULT;
+
+	resp = (struct trans_resp_header *)br->trans_buf;
+
+	code = resp->r_code ^ 0x80;
+	val_len = be16_to_cpu(resp->size);
+	if (!val_len || val_len != expected_count * SPI_AVMM_VAL_SIZE)
+		return -EFAULT;
+
+	/* error out if the trans code doesn't align with the val size */
+	if ((val_len == SPI_AVMM_VAL_SIZE && code != TRANS_CODE_WRITE) ||
+	    (val_len > SPI_AVMM_VAL_SIZE && code != TRANS_CODE_SEQ_WRITE))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int do_reg_access(void *context, bool is_read, unsigned int reg,
+			 unsigned int *value, unsigned int count)
+{
+	struct spi_avmm_bridge *br = context;
+	int ret;
+
+	/* invalidate bridge buffers first */
+	br->trans_len = 0;
+	br->phy_len = 0;
+
+	ret = br_trans_tx_prepare(br, is_read, reg, value, count);
+	if (ret)
+		return ret;
+
+	ret = br_pkt_phy_tx_prepare(br);
+	if (ret)
+		return ret;
+
+	ret = br_do_tx(br);
+	if (ret)
+		return ret;
+
+	ret = br_do_rx_and_pkt_phy_parse(br);
+	if (ret)
+		return ret;
+
+	if (is_read)
+		return br_rd_trans_rx_parse(br, value, count);
+	else
+		return br_wr_trans_rx_parse(br, count);
+}
+
+static int regmap_spi_avmm_gather_write(void *context,
+					const void *reg_buf, size_t reg_len,
+					const void *val_buf, size_t val_len)
+{
+	if (reg_len != SPI_AVMM_REG_SIZE)
+		return -EINVAL;
+
+	if (!IS_ALIGNED(val_len, SPI_AVMM_VAL_SIZE))
+		return -EINVAL;
+
+	return do_reg_access(context, false, *(u32 *)reg_buf, (u32 *)val_buf,
+			     val_len / SPI_AVMM_VAL_SIZE);
+}
+
+static int regmap_spi_avmm_write(void *context, const void *data, size_t bytes)
+{
+	if (bytes < SPI_AVMM_REG_SIZE + SPI_AVMM_VAL_SIZE)
+		return -EINVAL;
+
+	return regmap_spi_avmm_gather_write(context, data, SPI_AVMM_REG_SIZE,
+					    data + SPI_AVMM_REG_SIZE,
+					    bytes - SPI_AVMM_REG_SIZE);
+}
+
+static int regmap_spi_avmm_read(void *context,
+				const void *reg_buf, size_t reg_len,
+				void *val_buf, size_t val_len)
+{
+	if (reg_len != SPI_AVMM_REG_SIZE)
+		return -EINVAL;
+
+	if (!IS_ALIGNED(val_len, SPI_AVMM_VAL_SIZE))
+		return -EINVAL;
+
+	return do_reg_access(context, true, *(u32 *)reg_buf, val_buf,
+			     (val_len / SPI_AVMM_VAL_SIZE));
+}
+
+static struct spi_avmm_bridge *
+spi_avmm_bridge_ctx_gen(struct spi_device *spi)
+{
+	struct spi_avmm_bridge *br;
+
+	if (!spi)
+		return ERR_PTR(-ENODEV);
+
+	/* Only support BPW == 8 or 32 now. Try 32 BPW first. */
+	spi->mode = SPI_MODE_1;
+	spi->bits_per_word = 32;
+	if (spi_setup(spi)) {
+		spi->bits_per_word = 8;
+		if (spi_setup(spi))
+			return ERR_PTR(-EINVAL);
+	}
+
+	br = kzalloc(sizeof(*br), GFP_KERNEL);
+	if (!br)
+		return ERR_PTR(-ENOMEM);
+
+	br->spi = spi;
+	br->word_len = spi->bits_per_word / 8;
+	if (br->word_len == 4) {
+		/*
+		 * The protocol requires little endian byte order but MSB
+		 * first. So driver needs to swap the byte order word by word
+		 * if word length > 1.
+		 */
+		br->swap_words = br_swap_words_32;
+	}
+
+	return br;
+}
+
+static void spi_avmm_bridge_ctx_free(void *context)
+{
+	kfree(context);
+}
+
+static const struct regmap_bus regmap_spi_avmm_bus = {
+	.write = regmap_spi_avmm_write,
+	.gather_write = regmap_spi_avmm_gather_write,
+	.read = regmap_spi_avmm_read,
+	.reg_format_endian_default = REGMAP_ENDIAN_NATIVE,
+	.val_format_endian_default = REGMAP_ENDIAN_NATIVE,
+	.max_raw_read = SPI_AVMM_VAL_SIZE * MAX_READ_CNT,
+	.max_raw_write = SPI_AVMM_VAL_SIZE * MAX_WRITE_CNT,
+	.free_context = spi_avmm_bridge_ctx_free,
+};
+
+struct regmap *__regmap_init_spi_avmm(struct spi_device *spi,
+				      const struct regmap_config *config,
+				      struct lock_class_key *lock_key,
+				      const char *lock_name)
+{
+	struct spi_avmm_bridge *bridge;
+	struct regmap *map;
+
+	bridge = spi_avmm_bridge_ctx_gen(spi);
+	if (IS_ERR(bridge))
+		return ERR_CAST(bridge);
+
+	map = __regmap_init(&spi->dev, &regmap_spi_avmm_bus,
+			    bridge, config, lock_key, lock_name);
+	if (IS_ERR(map)) {
+		spi_avmm_bridge_ctx_free(bridge);
+		return ERR_CAST(map);
+	}
+
+	return map;
+}
+EXPORT_SYMBOL_GPL(__regmap_init_spi_avmm);
+
+struct regmap *__devm_regmap_init_spi_avmm(struct spi_device *spi,
+					   const struct regmap_config *config,
+					   struct lock_class_key *lock_key,
+					   const char *lock_name)
+{
+	struct spi_avmm_bridge *bridge;
+	struct regmap *map;
+
+	bridge = spi_avmm_bridge_ctx_gen(spi);
+	if (IS_ERR(bridge))
+		return ERR_CAST(bridge);
+
+	map = __devm_regmap_init(&spi->dev, &regmap_spi_avmm_bus,
+				 bridge, config, lock_key, lock_name);
+	if (IS_ERR(map)) {
+		spi_avmm_bridge_ctx_free(bridge);
+		return ERR_CAST(map);
+	}
+
+	return map;
+}
+EXPORT_SYMBOL_GPL(__devm_regmap_init_spi_avmm);
+
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index 1970ed59d49f..d865d8fea535 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -567,6 +567,10 @@ struct regmap *__regmap_init_sdw(struct sdw_slave *sdw,
 				 const struct regmap_config *config,
 				 struct lock_class_key *lock_key,
 				 const char *lock_name);
+struct regmap *__regmap_init_spi_avmm(struct spi_device *spi,
+				      const struct regmap_config *config,
+				      struct lock_class_key *lock_key,
+				      const char *lock_name);
 
 struct regmap *__devm_regmap_init(struct device *dev,
 				  const struct regmap_bus *bus,
@@ -620,6 +624,10 @@ struct regmap *__devm_regmap_init_i3c(struct i3c_device *i3c,
 				 const struct regmap_config *config,
 				 struct lock_class_key *lock_key,
 				 const char *lock_name);
+struct regmap *__devm_regmap_init_spi_avmm(struct spi_device *spi,
+					   const struct regmap_config *config,
+					   struct lock_class_key *lock_key,
+					   const char *lock_name);
 /*
  * Wrapper for regmap_init macros to include a unique lockdep key and name
  * for each call. No-op if CONFIG_LOCKDEP is not set.
@@ -806,6 +814,19 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg);
 	__regmap_lockdep_wrapper(__regmap_init_sdw, #config,		\
 				sdw, config)
 
+/**
+ * regmap_init_spi_avmm() - Initialize register map for Intel SPI Slave
+ * to AVMM Bus Bridge
+ *
+ * @spi: Device that will be interacted with
+ * @config: Configuration for register map
+ *
+ * The return value will be an ERR_PTR() on error or a valid pointer
+ * to a struct regmap.
+ */
+#define regmap_init_spi_avmm(spi, config)					\
+	__regmap_lockdep_wrapper(__regmap_init_spi_avmm, #config,		\
+				 spi, config)
 
 /**
  * devm_regmap_init() - Initialise managed register map
@@ -993,6 +1014,21 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg);
 	__regmap_lockdep_wrapper(__devm_regmap_init_i3c, #config,	\
 				i3c, config)
 
+/**
+ * devm_regmap_init_spi_avmm() - Initialize register map for Intel SPI Slave
+ * to AVMM Bus Bridge
+ *
+ * @spi: Device that will be interacted with
+ * @config: Configuration for register map
+ *
+ * The return value will be an ERR_PTR() on error or a valid pointer
+ * to a struct regmap.  The map will be automatically freed by the
+ * device management code.
+ */
+#define devm_regmap_init_spi_avmm(spi, config)				\
+	__regmap_lockdep_wrapper(__devm_regmap_init_spi_avmm, #config,	\
+				 spi, config)
+
 int regmap_mmio_attach_clk(struct regmap *map, struct clk *clk);
 void regmap_mmio_detach_clk(struct regmap *map);
 void regmap_exit(struct regmap *map);
-- 
cgit v1.2.3


From e7aaf8748897d88fd1d17bfa461df84cf233d5a9 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 26 Aug 2020 18:14:53 +0300
Subject: spi: pxa2xx: Update header block in pxa2xx_ssp.h

We have direct users of some headers that are missed and
have header included when forward declarations are enough.

Update header block in pxa2xx_ssp.h to align with actual usage.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20200826151455.55970-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/pxa2xx_ssp.h | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h
index 1608c760fe91..ae65fe635934 100644
--- a/include/linux/pxa2xx_ssp.h
+++ b/include/linux/pxa2xx_ssp.h
@@ -16,10 +16,15 @@
 #ifndef __LINUX_SSP_H
 #define __LINUX_SSP_H
 
-#include <linux/list.h>
+#include <linux/compiler_types.h>
 #include <linux/io.h>
-#include <linux/of.h>
+#include <linux/kconfig.h>
+#include <linux/list.h>
+#include <linux/types.h>
 
+struct clk;
+struct device;
+struct device_node;
 
 /*
  * SSP Serial Port Registers
-- 
cgit v1.2.3


From 410f4cf79f64b1831e207b89f3c7ab08e36aa646 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 26 Aug 2020 18:14:54 +0300
Subject: spi: pxa2xx: Switch to use BIT() and GENMASK() in pxa2xx_ssp.h

Switch pxa2xx_ssp.h header to use BIT() and GENMASK().
It's better to read and understand. While here, correct ordering
of some definitions.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20200826151455.55970-2-andriy.shevchenko@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/pxa2xx_ssp.h | 150 ++++++++++++++++++++++-----------------------
 1 file changed, 75 insertions(+), 75 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h
index ae65fe635934..3f0f275bd630 100644
--- a/include/linux/pxa2xx_ssp.h
+++ b/include/linux/pxa2xx_ssp.h
@@ -16,6 +16,7 @@
 #ifndef __LINUX_SSP_H
 #define __LINUX_SSP_H
 
+#include <linux/bits.h>
 #include <linux/compiler_types.h>
 #include <linux/io.h>
 #include <linux/kconfig.h>
@@ -48,130 +49,127 @@ struct device_node;
 #define SSACDD		(0x40)	/* SSP Audio Clock Dither Divider */
 
 /* Common PXA2xx bits first */
-#define SSCR0_DSS	(0x0000000f)	/* Data Size Select (mask) */
+#define SSCR0_DSS	GENMASK(3, 0)	/* Data Size Select (mask) */
 #define SSCR0_DataSize(x)  ((x) - 1)	/* Data Size Select [4..16] */
-#define SSCR0_FRF	(0x00000030)	/* FRame Format (mask) */
+#define SSCR0_FRF	GENMASK(5, 4)	/* FRame Format (mask) */
 #define SSCR0_Motorola	(0x0 << 4)	/* Motorola's Serial Peripheral Interface (SPI) */
 #define SSCR0_TI	(0x1 << 4)	/* Texas Instruments' Synchronous Serial Protocol (SSP) */
 #define SSCR0_National	(0x2 << 4)	/* National Microwire */
-#define SSCR0_ECS	(1 << 6)	/* External clock select */
-#define SSCR0_SSE	(1 << 7)	/* Synchronous Serial Port Enable */
+#define SSCR0_ECS	BIT(6)		/* External clock select */
+#define SSCR0_SSE	BIT(7)		/* Synchronous Serial Port Enable */
 #define SSCR0_SCR(x)	((x) << 8)	/* Serial Clock Rate (mask) */
 
 /* PXA27x, PXA3xx */
-#define SSCR0_EDSS	(1 << 20)	/* Extended data size select */
-#define SSCR0_NCS	(1 << 21)	/* Network clock select */
-#define SSCR0_RIM	(1 << 22)	/* Receive FIFO overrrun interrupt mask */
-#define SSCR0_TUM	(1 << 23)	/* Transmit FIFO underrun interrupt mask */
-#define SSCR0_FRDC	(0x07000000)	/* Frame rate divider control (mask) */
+#define SSCR0_EDSS	BIT(20)		/* Extended data size select */
+#define SSCR0_NCS	BIT(21)		/* Network clock select */
+#define SSCR0_RIM	BIT(22)		/* Receive FIFO overrrun interrupt mask */
+#define SSCR0_TUM	BIT(23)		/* Transmit FIFO underrun interrupt mask */
+#define SSCR0_FRDC	GENMASK(26, 24)	/* Frame rate divider control (mask) */
 #define SSCR0_SlotsPerFrm(x) (((x) - 1) << 24)	/* Time slots per frame [1..8] */
-#define SSCR0_FPCKE	(1 << 29)	/* FIFO packing enable */
-#define SSCR0_ACS	(1 << 30)	/* Audio clock select */
-#define SSCR0_MOD	(1 << 31)	/* Mode (normal or network) */
-
-
-#define SSCR1_RIE	(1 << 0)	/* Receive FIFO Interrupt Enable */
-#define SSCR1_TIE	(1 << 1)	/* Transmit FIFO Interrupt Enable */
-#define SSCR1_LBM	(1 << 2)	/* Loop-Back Mode */
-#define SSCR1_SPO	(1 << 3)	/* Motorola SPI SSPSCLK polarity setting */
-#define SSCR1_SPH	(1 << 4)	/* Motorola SPI SSPSCLK phase setting */
-#define SSCR1_MWDS	(1 << 5)	/* Microwire Transmit Data Size */
-
-#define SSSR_ALT_FRM_MASK	3	/* Masks the SFRM signal number */
-#define SSSR_TNF	(1 << 2)	/* Transmit FIFO Not Full */
-#define SSSR_RNE	(1 << 3)	/* Receive FIFO Not Empty */
-#define SSSR_BSY	(1 << 4)	/* SSP Busy */
-#define SSSR_TFS	(1 << 5)	/* Transmit FIFO Service Request */
-#define SSSR_RFS	(1 << 6)	/* Receive FIFO Service Request */
-#define SSSR_ROR	(1 << 7)	/* Receive FIFO Overrun */
+#define SSCR0_FPCKE	BIT(29)		/* FIFO packing enable */
+#define SSCR0_ACS	BIT(30)		/* Audio clock select */
+#define SSCR0_MOD	BIT(31)		/* Mode (normal or network) */
+
+#define SSCR1_RIE	BIT(0)		/* Receive FIFO Interrupt Enable */
+#define SSCR1_TIE	BIT(1)		/* Transmit FIFO Interrupt Enable */
+#define SSCR1_LBM	BIT(2)		/* Loop-Back Mode */
+#define SSCR1_SPO	BIT(3)		/* Motorola SPI SSPSCLK polarity setting */
+#define SSCR1_SPH	BIT(4)		/* Motorola SPI SSPSCLK phase setting */
+#define SSCR1_MWDS	BIT(5)		/* Microwire Transmit Data Size */
+
+#define SSSR_ALT_FRM_MASK	GENMASK(1, 0)	/* Masks the SFRM signal number */
+#define SSSR_TNF		BIT(2)		/* Transmit FIFO Not Full */
+#define SSSR_RNE		BIT(3)		/* Receive FIFO Not Empty */
+#define SSSR_BSY		BIT(4)		/* SSP Busy */
+#define SSSR_TFS		BIT(5)		/* Transmit FIFO Service Request */
+#define SSSR_RFS		BIT(6)		/* Receive FIFO Service Request */
+#define SSSR_ROR		BIT(7)		/* Receive FIFO Overrun */
 
 #define RX_THRESH_DFLT	8
 #define TX_THRESH_DFLT	8
 
-#define SSSR_TFL_MASK	(0xf << 8)	/* Transmit FIFO Level mask */
-#define SSSR_RFL_MASK	(0xf << 12)	/* Receive FIFO Level mask */
+#define SSSR_TFL_MASK	GENMASK(11, 8)	/* Transmit FIFO Level mask */
+#define SSSR_RFL_MASK	GENMASK(15, 12)	/* Receive FIFO Level mask */
 
-#define SSCR1_TFT	(0x000003c0)	/* Transmit FIFO Threshold (mask) */
+#define SSCR1_TFT	GENMASK(9, 6)	/* Transmit FIFO Threshold (mask) */
 #define SSCR1_TxTresh(x) (((x) - 1) << 6)	/* level [1..16] */
-#define SSCR1_RFT	(0x00003c00)	/* Receive FIFO Threshold (mask) */
+#define SSCR1_RFT	GENMASK(13, 10)	/* Receive FIFO Threshold (mask) */
 #define SSCR1_RxTresh(x) (((x) - 1) << 10)	/* level [1..16] */
 
 #define RX_THRESH_CE4100_DFLT	2
 #define TX_THRESH_CE4100_DFLT	2
 
-#define CE4100_SSSR_TFL_MASK	(0x3 << 8)	/* Transmit FIFO Level mask */
-#define CE4100_SSSR_RFL_MASK	(0x3 << 12)	/* Receive FIFO Level mask */
+#define CE4100_SSSR_TFL_MASK	GENMASK(9, 8)	/* Transmit FIFO Level mask */
+#define CE4100_SSSR_RFL_MASK	GENMASK(13, 12)	/* Receive FIFO Level mask */
 
-#define CE4100_SSCR1_TFT	(0x000000c0)	/* Transmit FIFO Threshold (mask) */
+#define CE4100_SSCR1_TFT	GENMASK(7, 6)	/* Transmit FIFO Threshold (mask) */
 #define CE4100_SSCR1_TxTresh(x) (((x) - 1) << 6)	/* level [1..4] */
-#define CE4100_SSCR1_RFT	(0x00000c00)	/* Receive FIFO Threshold (mask) */
+#define CE4100_SSCR1_RFT	GENMASK(11, 10)	/* Receive FIFO Threshold (mask) */
 #define CE4100_SSCR1_RxTresh(x) (((x) - 1) << 10)	/* level [1..4] */
 
 /* QUARK_X1000 SSCR0 bit definition */
-#define QUARK_X1000_SSCR0_DSS		(0x1F << 0)	/* Data Size Select (mask) */
+#define QUARK_X1000_SSCR0_DSS		GENMASK(4, 0)	/* Data Size Select (mask) */
 #define QUARK_X1000_SSCR0_DataSize(x)	((x) - 1)	/* Data Size Select [4..32] */
-#define QUARK_X1000_SSCR0_FRF		(0x3 << 5)	/* FRame Format (mask) */
+#define QUARK_X1000_SSCR0_FRF		GENMASK(6, 5)	/* FRame Format (mask) */
 #define QUARK_X1000_SSCR0_Motorola	(0x0 << 5)	/* Motorola's Serial Peripheral Interface (SPI) */
 
 #define RX_THRESH_QUARK_X1000_DFLT	1
 #define TX_THRESH_QUARK_X1000_DFLT	16
 
-#define QUARK_X1000_SSSR_TFL_MASK	(0x1F << 8)	/* Transmit FIFO Level mask */
-#define QUARK_X1000_SSSR_RFL_MASK	(0x1F << 13)	/* Receive FIFO Level mask */
+#define QUARK_X1000_SSSR_TFL_MASK	GENMASK(12, 8)	/* Transmit FIFO Level mask */
+#define QUARK_X1000_SSSR_RFL_MASK	GENMASK(17, 13)	/* Receive FIFO Level mask */
 
-#define QUARK_X1000_SSCR1_TFT	(0x1F << 6)	/* Transmit FIFO Threshold (mask) */
+#define QUARK_X1000_SSCR1_TFT	GENMASK(10, 6)	/* Transmit FIFO Threshold (mask) */
 #define QUARK_X1000_SSCR1_TxTresh(x) (((x) - 1) << 6)	/* level [1..32] */
-#define QUARK_X1000_SSCR1_RFT	(0x1F << 11)	/* Receive FIFO Threshold (mask) */
+#define QUARK_X1000_SSCR1_RFT	GENMASK(15, 11)	/* Receive FIFO Threshold (mask) */
 #define QUARK_X1000_SSCR1_RxTresh(x) (((x) - 1) << 11)	/* level [1..32] */
-#define QUARK_X1000_SSCR1_STRF	(1 << 17)	/* Select FIFO or EFWR */
-#define QUARK_X1000_SSCR1_EFWR	(1 << 16)	/* Enable FIFO Write/Read */
+#define QUARK_X1000_SSCR1_EFWR	BIT(16)		/* Enable FIFO Write/Read */
+#define QUARK_X1000_SSCR1_STRF	BIT(17)		/* Select FIFO or EFWR */
 
 /* extra bits in PXA255, PXA26x and PXA27x SSP ports */
 #define SSCR0_TISSP		(1 << 4)	/* TI Sync Serial Protocol */
 #define SSCR0_PSP		(3 << 4)	/* PSP - Programmable Serial Protocol */
-#define SSCR1_TTELP		(1 << 31)	/* TXD Tristate Enable Last Phase */
-#define SSCR1_TTE		(1 << 30)	/* TXD Tristate Enable */
-#define SSCR1_EBCEI		(1 << 29)	/* Enable Bit Count Error interrupt */
-#define SSCR1_SCFR		(1 << 28)	/* Slave Clock free Running */
-#define SSCR1_ECRA		(1 << 27)	/* Enable Clock Request A */
-#define SSCR1_ECRB		(1 << 26)	/* Enable Clock request B */
-#define SSCR1_SCLKDIR		(1 << 25)	/* Serial Bit Rate Clock Direction */
-#define SSCR1_SFRMDIR		(1 << 24)	/* Frame Direction */
-#define SSCR1_RWOT		(1 << 23)	/* Receive Without Transmit */
-#define SSCR1_TRAIL		(1 << 22)	/* Trailing Byte */
-#define SSCR1_TSRE		(1 << 21)	/* Transmit Service Request Enable */
-#define SSCR1_RSRE		(1 << 20)	/* Receive Service Request Enable */
-#define SSCR1_TINTE		(1 << 19)	/* Receiver Time-out Interrupt enable */
-#define SSCR1_PINTE		(1 << 18)	/* Peripheral Trailing Byte Interrupt Enable */
-#define SSCR1_IFS		(1 << 16)	/* Invert Frame Signal */
-#define SSCR1_STRF		(1 << 15)	/* Select FIFO or EFWR */
-#define SSCR1_EFWR		(1 << 14)	/* Enable FIFO Write/Read */
-
-#define SSSR_BCE		(1 << 23)	/* Bit Count Error */
-#define SSSR_CSS		(1 << 22)	/* Clock Synchronisation Status */
-#define SSSR_TUR		(1 << 21)	/* Transmit FIFO Under Run */
-#define SSSR_EOC		(1 << 20)	/* End Of Chain */
-#define SSSR_TINT		(1 << 19)	/* Receiver Time-out Interrupt */
-#define SSSR_PINT		(1 << 18)	/* Peripheral Trailing Byte Interrupt */
 
+#define SSCR1_EFWR		BIT(14)		/* Enable FIFO Write/Read */
+#define SSCR1_STRF		BIT(15)		/* Select FIFO or EFWR */
+#define SSCR1_IFS		BIT(16)		/* Invert Frame Signal */
+#define SSCR1_PINTE		BIT(18)		/* Peripheral Trailing Byte Interrupt Enable */
+#define SSCR1_TINTE		BIT(19)		/* Receiver Time-out Interrupt enable */
+#define SSCR1_RSRE		BIT(20)		/* Receive Service Request Enable */
+#define SSCR1_TSRE		BIT(21)		/* Transmit Service Request Enable */
+#define SSCR1_TRAIL		BIT(22)		/* Trailing Byte */
+#define SSCR1_RWOT		BIT(23)		/* Receive Without Transmit */
+#define SSCR1_SFRMDIR		BIT(24)		/* Frame Direction */
+#define SSCR1_SCLKDIR		BIT(25)		/* Serial Bit Rate Clock Direction */
+#define SSCR1_ECRB		BIT(26)		/* Enable Clock request B */
+#define SSCR1_ECRA		BIT(27)		/* Enable Clock Request A */
+#define SSCR1_SCFR		BIT(28)		/* Slave Clock free Running */
+#define SSCR1_EBCEI		BIT(29)		/* Enable Bit Count Error interrupt */
+#define SSCR1_TTE		BIT(30)		/* TXD Tristate Enable */
+#define SSCR1_TTELP		BIT(31)		/* TXD Tristate Enable Last Phase */
+
+#define SSSR_PINT		BIT(18)		/* Peripheral Trailing Byte Interrupt */
+#define SSSR_TINT		BIT(19)		/* Receiver Time-out Interrupt */
+#define SSSR_EOC		BIT(20)		/* End Of Chain */
+#define SSSR_TUR		BIT(21)		/* Transmit FIFO Under Run */
+#define SSSR_CSS		BIT(22)		/* Clock Synchronisation Status */
+#define SSSR_BCE		BIT(23)		/* Bit Count Error */
 
 #define SSPSP_SCMODE(x)		((x) << 0)	/* Serial Bit Rate Clock Mode */
-#define SSPSP_SFRMP		(1 << 2)	/* Serial Frame Polarity */
-#define SSPSP_ETDS		(1 << 3)	/* End of Transfer data State */
+#define SSPSP_SFRMP		BIT(2)		/* Serial Frame Polarity */
+#define SSPSP_ETDS		BIT(3)		/* End of Transfer data State */
 #define SSPSP_STRTDLY(x)	((x) << 4)	/* Start Delay */
 #define SSPSP_DMYSTRT(x)	((x) << 7)	/* Dummy Start */
 #define SSPSP_SFRMDLY(x)	((x) << 9)	/* Serial Frame Delay */
 #define SSPSP_SFRMWDTH(x)	((x) << 16)	/* Serial Frame Width */
 #define SSPSP_DMYSTOP(x)	((x) << 23)	/* Dummy Stop */
-#define SSPSP_FSRT		(1 << 25)	/* Frame Sync Relative Timing */
+#define SSPSP_FSRT		BIT(25)		/* Frame Sync Relative Timing */
 
 /* PXA3xx */
 #define SSPSP_EDMYSTRT(x)	((x) << 26)     /* Extended Dummy Start */
 #define SSPSP_EDMYSTOP(x)	((x) << 28)     /* Extended Dummy Stop */
 #define SSPSP_TIMING_MASK	(0x7f8001f0)
 
-#define SSACD_SCDB		(1 << 3)	/* SSPSYSCLK Divider Bypass */
-#define SSACD_ACPS(x)		((x) << 4)	/* Audio clock PLL select */
 #define SSACD_ACDS(x)		((x) << 0)	/* Audio clock divider select */
 #define SSACD_ACDS_1		(0)
 #define SSACD_ACDS_2		(1)
@@ -179,14 +177,16 @@ struct device_node;
 #define SSACD_ACDS_8		(3)
 #define SSACD_ACDS_16		(4)
 #define SSACD_ACDS_32		(5)
+#define SSACD_SCDB		BIT(3)		/* SSPSYSCLK Divider Bypass */
 #define SSACD_SCDB_4X		(0)
 #define SSACD_SCDB_1X		(1)
-#define SSACD_SCDX8		(1 << 7)	/* SYSCLK division ratio select */
+#define SSACD_ACPS(x)		((x) << 4)	/* Audio clock PLL select */
+#define SSACD_SCDX8		BIT(7)		/* SYSCLK division ratio select */
 
 /* LPSS SSP */
 #define SSITF			0x44		/* TX FIFO trigger level */
+#define SSITF_TxHiThresh(x)	(((x) - 1) << 0)
 #define SSITF_TxLoThresh(x)	(((x) - 1) << 8)
-#define SSITF_TxHiThresh(x)	((x) - 1)
 
 #define SSIRF			0x48		/* RX FIFO trigger level */
 #define SSIRF_RxThresh(x)	((x) - 1)
-- 
cgit v1.2.3


From 3a2fd4011a1ecec361498301a27d79d5fef255de Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 26 Aug 2020 18:14:55 +0300
Subject: spi: pxa2xx: Drop useless comment in the pxa2xx_ssp.h

No need to have file name inside file.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20200826151455.55970-3-andriy.shevchenko@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/pxa2xx_ssp.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h
index 3f0f275bd630..7f73b26ed22e 100644
--- a/include/linux/pxa2xx_ssp.h
+++ b/include/linux/pxa2xx_ssp.h
@@ -1,7 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- *  pxa2xx_ssp.h
- *
  *  Copyright (C) 2003 Russell King, All Rights Reserved.
  *
  * This driver supports the following PXA CPU/SSP ports:-
-- 
cgit v1.2.3


From f468f21b7af0fa472ff8ff70f10b9b4995ef7eb3 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Wed, 26 Aug 2020 15:54:16 +0300
Subject: net: Take common prefetch code structure into a function

Many device drivers use the same prefetch code structure to
deal with small L1 cacheline size.
Take this code into a function and call it from the drivers.

Suggested-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb3/sge.c          |  5 +----
 drivers/net/ethernet/hisilicon/hns/hns_enet.c     |  5 +----
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c   |  5 +----
 drivers/net/ethernet/intel/fm10k/fm10k_main.c     |  5 +----
 drivers/net/ethernet/intel/i40e/i40e_txrx.c       | 12 ++++--------
 drivers/net/ethernet/intel/iavf/iavf_txrx.c       | 11 +++--------
 drivers/net/ethernet/intel/ice/ice_txrx.c         | 10 ++--------
 drivers/net/ethernet/intel/igb/igb_main.c         | 10 ++--------
 drivers/net/ethernet/intel/igc/igc_main.c         | 10 ++--------
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c     | 11 +++--------
 drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 11 +++--------
 include/linux/netdevice.h                         | 16 ++++++++++++++++
 12 files changed, 39 insertions(+), 72 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/chelsio/cxgb3/sge.c b/drivers/net/ethernet/chelsio/cxgb3/sge.c
index 6dabbf1502c7..ee6188dea705 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/sge.c
@@ -2372,10 +2372,7 @@ no_mem:
 			if (fl->use_pages) {
 				void *addr = fl->sdesc[fl->cidx].pg_chunk.va;
 
-				prefetch(addr);
-#if L1_CACHE_BYTES < 128
-				prefetch(addr + L1_CACHE_BYTES);
-#endif
+				net_prefetch(addr);
 				__refill_fl(adap, fl);
 				if (lro > 0) {
 					lro_add_page(adap, qs, fl,
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index 23f278e46975..3af33ade7b60 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -557,10 +557,7 @@ static int hns_nic_poll_rx_skb(struct hns_nic_ring_data *ring_data,
 	va = (unsigned char *)desc_cb->buf + desc_cb->page_offset;
 
 	/* prefetch first cache line of first page */
-	prefetch(va);
-#if L1_CACHE_BYTES < 128
-	prefetch(va + L1_CACHE_BYTES);
-#endif
+	net_prefetch(va);
 
 	skb = *out_skb = napi_alloc_skb(&ring_data->napi,
 					HNS_RX_HEAD_SIZE);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 87776ce3539b..1a1ba6a41bfe 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -3091,10 +3091,7 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring)
 	 * lines. In such a case, single fetch would suffice to cache in the
 	 * relevant part of the header.
 	 */
-	prefetch(ring->va);
-#if L1_CACHE_BYTES < 128
-	prefetch(ring->va + L1_CACHE_BYTES);
-#endif
+	net_prefetch(ring->va);
 
 	if (!skb) {
 		ret = hns3_alloc_skb(ring, length, ring->va);
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
index d88dd41a9442..99b8252eb969 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
@@ -310,10 +310,7 @@ static struct sk_buff *fm10k_fetch_rx_buffer(struct fm10k_ring *rx_ring,
 				  rx_buffer->page_offset;
 
 		/* prefetch first cache line of first page */
-		prefetch(page_addr);
-#if L1_CACHE_BYTES < 128
-		prefetch((void *)((u8 *)page_addr + L1_CACHE_BYTES));
-#endif
+		net_prefetch(page_addr);
 
 		/* allocate a skb to store the frags */
 		skb = napi_alloc_skb(&rx_ring->q_vector->napi,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 3e5c566ceb01..432a984ac335 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -1992,10 +1992,8 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring,
 	struct sk_buff *skb;
 
 	/* prefetch first cache line of first page */
-	prefetch(xdp->data);
-#if L1_CACHE_BYTES < 128
-	prefetch(xdp->data + L1_CACHE_BYTES);
-#endif
+	net_prefetch(xdp->data);
+
 	/* Note, we get here by enabling legacy-rx via:
 	 *
 	 *    ethtool --set-priv-flags <dev> legacy-rx on
@@ -2078,10 +2076,8 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring,
 	 * likely have a consumer accessing first few bytes of meta
 	 * data, and then actual data.
 	 */
-	prefetch(xdp->data_meta);
-#if L1_CACHE_BYTES < 128
-	prefetch(xdp->data_meta + L1_CACHE_BYTES);
-#endif
+	net_prefetch(xdp->data_meta);
+
 	/* build an skb around the page buffer */
 	skb = build_skb(xdp->data_hard_start, truesize);
 	if (unlikely(!skb))
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
index ca041b39ffda..256fa07d54d5 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
@@ -1309,10 +1309,7 @@ static struct sk_buff *iavf_construct_skb(struct iavf_ring *rx_ring,
 		return NULL;
 	/* prefetch first cache line of first page */
 	va = page_address(rx_buffer->page) + rx_buffer->page_offset;
-	prefetch(va);
-#if L1_CACHE_BYTES < 128
-	prefetch(va + L1_CACHE_BYTES);
-#endif
+	net_prefetch(va);
 
 	/* allocate a skb to store the frags */
 	skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
@@ -1376,10 +1373,8 @@ static struct sk_buff *iavf_build_skb(struct iavf_ring *rx_ring,
 		return NULL;
 	/* prefetch first cache line of first page */
 	va = page_address(rx_buffer->page) + rx_buffer->page_offset;
-	prefetch(va);
-#if L1_CACHE_BYTES < 128
-	prefetch(va + L1_CACHE_BYTES);
-#endif
+	net_prefetch(va);
+
 	/* build an skb around the page buffer */
 	skb = build_skb(va - IAVF_SKB_PAD, truesize);
 	if (unlikely(!skb))
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 9d0d6b0025cf..d2fca4a52f51 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -919,10 +919,7 @@ ice_build_skb(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf,
 	 * likely have a consumer accessing first few bytes of meta
 	 * data, and then actual data.
 	 */
-	prefetch(xdp->data_meta);
-#if L1_CACHE_BYTES < 128
-	prefetch((void *)(xdp->data + L1_CACHE_BYTES));
-#endif
+	net_prefetch(xdp->data_meta);
 	/* build an skb around the page buffer */
 	skb = build_skb(xdp->data_hard_start, truesize);
 	if (unlikely(!skb))
@@ -964,10 +961,7 @@ ice_construct_skb(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf,
 	struct sk_buff *skb;
 
 	/* prefetch first cache line of first page */
-	prefetch(xdp->data);
-#if L1_CACHE_BYTES < 128
-	prefetch((void *)(xdp->data + L1_CACHE_BYTES));
-#endif /* L1_CACHE_BYTES */
+	net_prefetch(xdp->data);
 
 	/* allocate a skb to store the frags */
 	skb = __napi_alloc_skb(&rx_ring->q_vector->napi, ICE_RX_HDR_SIZE,
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 4f05f6efe6af..698bb6a4b088 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -8047,10 +8047,7 @@ static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring,
 	struct sk_buff *skb;
 
 	/* prefetch first cache line of first page */
-	prefetch(va);
-#if L1_CACHE_BYTES < 128
-	prefetch(va + L1_CACHE_BYTES);
-#endif
+	net_prefetch(va);
 
 	/* allocate a skb to store the frags */
 	skb = napi_alloc_skb(&rx_ring->q_vector->napi, IGB_RX_HDR_LEN);
@@ -8104,10 +8101,7 @@ static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring,
 	struct sk_buff *skb;
 
 	/* prefetch first cache line of first page */
-	prefetch(va);
-#if L1_CACHE_BYTES < 128
-	prefetch(va + L1_CACHE_BYTES);
-#endif
+	net_prefetch(va);
 
 	/* build an skb around the page buffer */
 	skb = build_skb(va - IGB_SKB_PAD, truesize);
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 9593aa4eea36..c6968fdb6caa 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -1550,10 +1550,7 @@ static struct sk_buff *igc_build_skb(struct igc_ring *rx_ring,
 	struct sk_buff *skb;
 
 	/* prefetch first cache line of first page */
-	prefetch(va);
-#if L1_CACHE_BYTES < 128
-	prefetch(va + L1_CACHE_BYTES);
-#endif
+	net_prefetch(va);
 
 	/* build an skb around the page buffer */
 	skb = build_skb(va - IGC_SKB_PAD, truesize);
@@ -1589,10 +1586,7 @@ static struct sk_buff *igc_construct_skb(struct igc_ring *rx_ring,
 	struct sk_buff *skb;
 
 	/* prefetch first cache line of first page */
-	prefetch(va);
-#if L1_CACHE_BYTES < 128
-	prefetch(va + L1_CACHE_BYTES);
-#endif
+	net_prefetch(va);
 
 	/* allocate a skb to store the frags */
 	skb = napi_alloc_skb(&rx_ring->q_vector->napi, IGC_RX_HDR_LEN);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 2f8a4cfc5fa1..f4f2198f388b 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2095,10 +2095,8 @@ static struct sk_buff *ixgbe_construct_skb(struct ixgbe_ring *rx_ring,
 	struct sk_buff *skb;
 
 	/* prefetch first cache line of first page */
-	prefetch(xdp->data);
-#if L1_CACHE_BYTES < 128
-	prefetch(xdp->data + L1_CACHE_BYTES);
-#endif
+	net_prefetch(xdp->data);
+
 	/* Note, we get here by enabling legacy-rx via:
 	 *
 	 *    ethtool --set-priv-flags <dev> legacy-rx on
@@ -2161,10 +2159,7 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring,
 	 * likely have a consumer accessing first few bytes of meta
 	 * data, and then actual data.
 	 */
-	prefetch(xdp->data_meta);
-#if L1_CACHE_BYTES < 128
-	prefetch(xdp->data_meta + L1_CACHE_BYTES);
-#endif
+	net_prefetch(xdp->data_meta);
 
 	/* build an skb to around the page buffer */
 	skb = build_skb(xdp->data_hard_start, truesize);
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index a428113e6d54..50afec43e001 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -866,10 +866,8 @@ struct sk_buff *ixgbevf_construct_skb(struct ixgbevf_ring *rx_ring,
 	struct sk_buff *skb;
 
 	/* prefetch first cache line of first page */
-	prefetch(xdp->data);
-#if L1_CACHE_BYTES < 128
-	prefetch(xdp->data + L1_CACHE_BYTES);
-#endif
+	net_prefetch(xdp->data);
+
 	/* Note, we get here by enabling legacy-rx via:
 	 *
 	 *    ethtool --set-priv-flags <dev> legacy-rx on
@@ -947,10 +945,7 @@ static struct sk_buff *ixgbevf_build_skb(struct ixgbevf_ring *rx_ring,
 	 * have a consumer accessing first few bytes of meta data,
 	 * and then actual data.
 	 */
-	prefetch(xdp->data_meta);
-#if L1_CACHE_BYTES < 128
-	prefetch(xdp->data_meta + L1_CACHE_BYTES);
-#endif
+	net_prefetch(xdp->data_meta);
 
 	/* build an skb around the page buffer */
 	skb = build_skb(xdp->data_hard_start, truesize);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index b0e303f6603f..b8abe1d7aa0b 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2193,6 +2193,22 @@ int netdev_get_num_tc(struct net_device *dev)
 	return dev->num_tc;
 }
 
+static inline void net_prefetch(void *p)
+{
+	prefetch(p);
+#if L1_CACHE_BYTES < 128
+	prefetch((u8 *)p + L1_CACHE_BYTES);
+#endif
+}
+
+static inline void net_prefetchw(void *p)
+{
+	prefetchw(p);
+#if L1_CACHE_BYTES < 128
+	prefetchw((u8 *)p + L1_CACHE_BYTES);
+#endif
+}
+
 void netdev_unbind_sb_channel(struct net_device *dev,
 			      struct net_device *sb_dev);
 int netdev_bind_sb_channel_queue(struct net_device *dev,
-- 
cgit v1.2.3


From f9f890ba2b13ea9ccfffd0e7354c7b64d9109790 Mon Sep 17 00:00:00 2001
From: Serge Semin <Sergey.Semin@baikalelectronics.ru>
Date: Thu, 30 Jul 2020 18:28:01 +0300
Subject: gpio: dwapb: Add max GPIOs macro

Add a new macro DWAPB_MAX_GPIOS which defines the maximum possible number
of GPIO lines corresponding to the maximum DW APB GPIO controller port
width. Use the new macro instead of number literal 32 where it's
applicable.

Suggested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Serge Semin <Sergey.Semin@baikalelectronics.ru>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20200730152808.2955-5-Sergey.Semin@baikalelectronics.ru
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-dwapb.c                | 8 ++++----
 include/linux/platform_data/gpio-dwapb.h | 4 +++-
 2 files changed, 7 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c
index 3081213247d8..f34001152850 100644
--- a/drivers/gpio/gpio-dwapb.c
+++ b/drivers/gpio/gpio-dwapb.c
@@ -162,7 +162,7 @@ static struct dwapb_gpio_port *dwapb_offs_to_port(struct dwapb_gpio *gpio, unsig
 
 	for (i = 0; i < gpio->nr_ports; i++) {
 		port = &gpio->ports[i];
-		if (port->idx == offs / 32)
+		if (port->idx == offs / DWAPB_MAX_GPIOS)
 			return port;
 	}
 
@@ -182,7 +182,7 @@ static void dwapb_toggle_trigger(struct dwapb_gpio *gpio, unsigned int offs)
 
 	pol = dwapb_read(gpio, GPIO_INT_POLARITY);
 	/* Just read the current value right out of the data register */
-	val = gc->get(gc, offs % 32);
+	val = gc->get(gc, offs % DWAPB_MAX_GPIOS);
 	if (val)
 		pol &= ~BIT(offs);
 	else
@@ -197,7 +197,7 @@ static u32 dwapb_do_irq(struct dwapb_gpio *gpio)
 	irq_hw_number_t hwirq;
 
 	irq_status = dwapb_read(gpio, GPIO_INTSTATUS);
-	for_each_set_bit(hwirq, &irq_status, 32) {
+	for_each_set_bit(hwirq, &irq_status, DWAPB_MAX_GPIOS) {
 		int gpio_irq = irq_find_mapping(gpio->domain, hwirq);
 		u32 irq_type = irq_get_trigger_type(gpio_irq);
 
@@ -599,7 +599,7 @@ static struct dwapb_platform_data *dwapb_gpio_get_pdata(struct device *dev)
 			dev_info(dev,
 				 "failed to get number of gpios for port%d\n",
 				 i);
-			pp->ngpio = 32;
+			pp->ngpio = DWAPB_MAX_GPIOS;
 		}
 
 		pp->irq_shared	= false;
diff --git a/include/linux/platform_data/gpio-dwapb.h b/include/linux/platform_data/gpio-dwapb.h
index ff1be737bad6..0aa5c6720259 100644
--- a/include/linux/platform_data/gpio-dwapb.h
+++ b/include/linux/platform_data/gpio-dwapb.h
@@ -6,12 +6,14 @@
 #ifndef GPIO_DW_APB_H
 #define GPIO_DW_APB_H
 
+#define DWAPB_MAX_GPIOS		32
+
 struct dwapb_port_property {
 	struct fwnode_handle *fwnode;
 	unsigned int	idx;
 	unsigned int	ngpio;
 	unsigned int	gpio_base;
-	int		irq[32];
+	int		irq[DWAPB_MAX_GPIOS];
 	bool		irq_shared;
 };
 
-- 
cgit v1.2.3


From 2da45b8f069644604e8e05ccb03b2b66ada611d5 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Thu, 27 Aug 2020 10:51:49 +0200
Subject: mtd: rawnand: Add a kernel doc to the ECC algorithm enumeration

Before moving it to the generic raw NAND core, ensure the enumeration
is properly described.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-2-miquel.raynal@bootlin.com
---
 include/linux/mtd/rawnand.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index a725b620aca2..1495f22b60cb 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -92,6 +92,13 @@ enum nand_ecc_mode {
 	NAND_ECC_ON_DIE,
 };
 
+/**
+ * enum nand_ecc_algo - NAND ECC algorithm
+ * @NAND_ECC_UNKNOWN: Unknown algorithm
+ * @NAND_ECC_HAMMING: Hamming algorithm
+ * @NAND_ECC_BCH: Bose-Chaudhuri-Hocquenghem algorithm
+ * @NAND_ECC_RS: Reed-Solomon algorithm
+ */
 enum nand_ecc_algo {
 	NAND_ECC_UNKNOWN,
 	NAND_ECC_HAMMING,
-- 
cgit v1.2.3


From e0a564ae0a4bc1bcf156d468955b27d3606e8253 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Thu, 27 Aug 2020 10:51:50 +0200
Subject: mtd: rawnand: Rename the ECC algorithm enumeration items

NAND_ECC_ is not a meaningful prefix, use NAND_ECC_ALGO_ instead.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-3-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/raw/ams-delta.c              |  2 +-
 drivers/mtd/nand/raw/arasan-nand-controller.c |  2 +-
 drivers/mtd/nand/raw/atmel/nand-controller.c  |  2 +-
 drivers/mtd/nand/raw/au1550nd.c               |  2 +-
 drivers/mtd/nand/raw/brcmnand/brcmnand.c      | 12 ++++++------
 drivers/mtd/nand/raw/davinci_nand.c           |  8 ++++----
 drivers/mtd/nand/raw/fsl_elbc_nand.c          |  2 +-
 drivers/mtd/nand/raw/fsl_ifc_nand.c           |  2 +-
 drivers/mtd/nand/raw/fsl_upm.c                |  2 +-
 drivers/mtd/nand/raw/fsmc_nand.c              |  2 +-
 drivers/mtd/nand/raw/gpio.c                   |  2 +-
 drivers/mtd/nand/raw/marvell_nand.c           | 10 +++++-----
 drivers/mtd/nand/raw/mpc5121_nfc.c            |  2 +-
 drivers/mtd/nand/raw/mxc_nand.c               |  2 +-
 drivers/mtd/nand/raw/nand_base.c              | 26 +++++++++++++-------------
 drivers/mtd/nand/raw/nand_micron.c            |  2 +-
 drivers/mtd/nand/raw/nandsim.c                |  4 ++--
 drivers/mtd/nand/raw/omap2.c                  |  2 +-
 drivers/mtd/nand/raw/orion_nand.c             |  2 +-
 drivers/mtd/nand/raw/pasemi_nand.c            |  2 +-
 drivers/mtd/nand/raw/plat_nand.c              |  2 +-
 drivers/mtd/nand/raw/s3c2410.c                |  4 ++--
 drivers/mtd/nand/raw/sh_flctl.c               |  2 +-
 drivers/mtd/nand/raw/socrates_nand.c          |  2 +-
 drivers/mtd/nand/raw/tango_nand.c             |  2 +-
 drivers/mtd/nand/raw/tegra_nand.c             | 20 ++++++++++----------
 drivers/mtd/nand/raw/xway_nand.c              |  2 +-
 include/linux/mtd/rawnand.h                   | 16 ++++++++--------
 28 files changed, 70 insertions(+), 70 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/raw/ams-delta.c b/drivers/mtd/nand/raw/ams-delta.c
index fdba155416d2..21199d9ae9be 100644
--- a/drivers/mtd/nand/raw/ams-delta.c
+++ b/drivers/mtd/nand/raw/ams-delta.c
@@ -261,7 +261,7 @@ static int gpio_nand_probe(struct platform_device *pdev)
 	}
 
 	this->ecc.mode = NAND_ECC_SOFT;
-	this->ecc.algo = NAND_ECC_HAMMING;
+	this->ecc.algo = NAND_ECC_ALGO_HAMMING;
 
 	platform_set_drvdata(pdev, priv);
 
diff --git a/drivers/mtd/nand/raw/arasan-nand-controller.c b/drivers/mtd/nand/raw/arasan-nand-controller.c
index 12c643e97c85..b0616a95340d 100644
--- a/drivers/mtd/nand/raw/arasan-nand-controller.c
+++ b/drivers/mtd/nand/raw/arasan-nand-controller.c
@@ -983,7 +983,7 @@ static int anfc_init_hw_ecc_controller(struct arasan_nfc *nfc,
 	mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
 
 	ecc->steps = mtd->writesize / ecc->size;
-	ecc->algo = NAND_ECC_BCH;
+	ecc->algo = NAND_ECC_ALGO_BCH;
 	anand->ecc_bits = bch_gf_mag * ecc->strength;
 	ecc->bytes = DIV_ROUND_UP(anand->ecc_bits, 8);
 	anand->ecc_total = DIV_ROUND_UP(anand->ecc_bits * ecc->steps, 8);
diff --git a/drivers/mtd/nand/raw/atmel/nand-controller.c b/drivers/mtd/nand/raw/atmel/nand-controller.c
index c9818f548d07..8999571bfa5d 100644
--- a/drivers/mtd/nand/raw/atmel/nand-controller.c
+++ b/drivers/mtd/nand/raw/atmel/nand-controller.c
@@ -1099,7 +1099,7 @@ static int atmel_nand_pmecc_init(struct nand_chip *chip)
 	if (IS_ERR(nand->pmecc))
 		return PTR_ERR(nand->pmecc);
 
-	chip->ecc.algo = NAND_ECC_BCH;
+	chip->ecc.algo = NAND_ECC_ALGO_BCH;
 	chip->ecc.size = req.ecc.sectorsize;
 	chip->ecc.bytes = req.ecc.bytes / req.ecc.nsectors;
 	chip->ecc.strength = req.ecc.strength;
diff --git a/drivers/mtd/nand/raw/au1550nd.c b/drivers/mtd/nand/raw/au1550nd.c
index d865200ccd08..ec2d90ad87de 100644
--- a/drivers/mtd/nand/raw/au1550nd.c
+++ b/drivers/mtd/nand/raw/au1550nd.c
@@ -295,7 +295,7 @@ static int au1550nd_probe(struct platform_device *pdev)
 	ctx->controller.ops = &au1550nd_ops;
 	this->controller = &ctx->controller;
 	this->ecc.mode = NAND_ECC_SOFT;
-	this->ecc.algo = NAND_ECC_HAMMING;
+	this->ecc.algo = NAND_ECC_ALGO_HAMMING;
 
 	if (pd->devwidth)
 		this->options |= NAND_BUSWIDTH_16;
diff --git a/drivers/mtd/nand/raw/brcmnand/brcmnand.c b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
index a4033d32a710..39f1bf327592 100644
--- a/drivers/mtd/nand/raw/brcmnand/brcmnand.c
+++ b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
@@ -2571,17 +2571,17 @@ static int brcmnand_setup_dev(struct brcmnand_host *host)
 		return -EINVAL;
 	}
 
-	if (chip->ecc.algo == NAND_ECC_UNKNOWN) {
+	if (chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) {
 		if (chip->ecc.strength == 1 && chip->ecc.size == 512)
 			/* Default to Hamming for 1-bit ECC, if unspecified */
-			chip->ecc.algo = NAND_ECC_HAMMING;
+			chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
 		else
 			/* Otherwise, BCH */
-			chip->ecc.algo = NAND_ECC_BCH;
+			chip->ecc.algo = NAND_ECC_ALGO_BCH;
 	}
 
-	if (chip->ecc.algo == NAND_ECC_HAMMING && (chip->ecc.strength != 1 ||
-						   chip->ecc.size != 512)) {
+	if (chip->ecc.algo == NAND_ECC_ALGO_HAMMING &&
+	    (chip->ecc.strength != 1 || chip->ecc.size != 512)) {
 		dev_err(ctrl->dev, "invalid Hamming params: %d bits per %d bytes\n",
 			chip->ecc.strength, chip->ecc.size);
 		return -EINVAL;
@@ -2600,7 +2600,7 @@ static int brcmnand_setup_dev(struct brcmnand_host *host)
 
 	switch (chip->ecc.size) {
 	case 512:
-		if (chip->ecc.algo == NAND_ECC_HAMMING)
+		if (chip->ecc.algo == NAND_ECC_ALGO_HAMMING)
 			cfg->ecc_level = 15;
 		else
 			cfg->ecc_level = chip->ecc.strength;
diff --git a/drivers/mtd/nand/raw/davinci_nand.c b/drivers/mtd/nand/raw/davinci_nand.c
index d975a62caaa5..551515c223bb 100644
--- a/drivers/mtd/nand/raw/davinci_nand.c
+++ b/drivers/mtd/nand/raw/davinci_nand.c
@@ -593,11 +593,11 @@ static int davinci_nand_attach_chip(struct nand_chip *chip)
 		pdata->ecc_bits = 0;
 		/*
 		 * This driver expects Hamming based ECC when ecc_mode is set
-		 * to NAND_ECC_SOFT. Force ecc.algo to NAND_ECC_HAMMING to
+		 * to NAND_ECC_SOFT. Force ecc.algo to NAND_ECC_ALGO_HAMMING to
 		 * avoid adding an extra ->ecc_algo field to
 		 * davinci_nand_pdata.
 		 */
-		info->chip.ecc.algo = NAND_ECC_HAMMING;
+		info->chip.ecc.algo = NAND_ECC_ALGO_HAMMING;
 		break;
 	case NAND_ECC_HW:
 		if (pdata->ecc_bits == 4) {
@@ -629,7 +629,7 @@ static int davinci_nand_attach_chip(struct nand_chip *chip)
 			info->chip.ecc.hwctl = nand_davinci_hwctl_4bit;
 			info->chip.ecc.bytes = 10;
 			info->chip.ecc.options = NAND_ECC_GENERIC_ERASED_CHECK;
-			info->chip.ecc.algo = NAND_ECC_BCH;
+			info->chip.ecc.algo = NAND_ECC_ALGO_BCH;
 
 			/*
 			 * Update ECC layout if needed ... for 1-bit HW ECC, the
@@ -656,7 +656,7 @@ static int davinci_nand_attach_chip(struct nand_chip *chip)
 			info->chip.ecc.correct = nand_davinci_correct_1bit;
 			info->chip.ecc.hwctl = nand_davinci_hwctl_1bit;
 			info->chip.ecc.bytes = 3;
-			info->chip.ecc.algo = NAND_ECC_HAMMING;
+			info->chip.ecc.algo = NAND_ECC_ALGO_HAMMING;
 		}
 		info->chip.ecc.size = 512;
 		info->chip.ecc.strength = pdata->ecc_bits;
diff --git a/drivers/mtd/nand/raw/fsl_elbc_nand.c b/drivers/mtd/nand/raw/fsl_elbc_nand.c
index 088692b2e27a..da89389faaae 100644
--- a/drivers/mtd/nand/raw/fsl_elbc_nand.c
+++ b/drivers/mtd/nand/raw/fsl_elbc_nand.c
@@ -748,7 +748,7 @@ static int fsl_elbc_attach_chip(struct nand_chip *chip)
 		} else {
 			/* otherwise fall back to default software ECC */
 			chip->ecc.mode = NAND_ECC_SOFT;
-			chip->ecc.algo = NAND_ECC_HAMMING;
+			chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
 		}
 		break;
 
diff --git a/drivers/mtd/nand/raw/fsl_ifc_nand.c b/drivers/mtd/nand/raw/fsl_ifc_nand.c
index 00ae7a910b03..b2ae759dd14e 100644
--- a/drivers/mtd/nand/raw/fsl_ifc_nand.c
+++ b/drivers/mtd/nand/raw/fsl_ifc_nand.c
@@ -926,7 +926,7 @@ static int fsl_ifc_chip_init(struct fsl_ifc_mtd *priv)
 		}
 	} else {
 		chip->ecc.mode = NAND_ECC_SOFT;
-		chip->ecc.algo = NAND_ECC_HAMMING;
+		chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
 	}
 
 	ret = fsl_ifc_sram_init(priv);
diff --git a/drivers/mtd/nand/raw/fsl_upm.c b/drivers/mtd/nand/raw/fsl_upm.c
index 197850aeb261..04cf7d14082a 100644
--- a/drivers/mtd/nand/raw/fsl_upm.c
+++ b/drivers/mtd/nand/raw/fsl_upm.c
@@ -48,7 +48,7 @@ static int fun_chip_init(struct fsl_upm_nand *fun,
 	struct device_node *flash_np;
 
 	fun->chip.ecc.mode = NAND_ECC_SOFT;
-	fun->chip.ecc.algo = NAND_ECC_HAMMING;
+	fun->chip.ecc.algo = NAND_ECC_ALGO_HAMMING;
 	fun->chip.controller = &fun->base;
 	mtd->dev.parent = fun->dev;
 
diff --git a/drivers/mtd/nand/raw/fsmc_nand.c b/drivers/mtd/nand/raw/fsmc_nand.c
index 92ddc41d0ff0..580b9fe8ca42 100644
--- a/drivers/mtd/nand/raw/fsmc_nand.c
+++ b/drivers/mtd/nand/raw/fsmc_nand.c
@@ -911,7 +911,7 @@ static int fsmc_nand_attach_chip(struct nand_chip *nand)
 		break;
 
 	case NAND_ECC_SOFT:
-		if (nand->ecc.algo == NAND_ECC_BCH) {
+		if (nand->ecc.algo == NAND_ECC_ALGO_BCH) {
 			dev_info(host->dev,
 				 "Using 4-bit SW BCH ECC scheme\n");
 			break;
diff --git a/drivers/mtd/nand/raw/gpio.c b/drivers/mtd/nand/raw/gpio.c
index 3bd847ccc3f3..c8f498eaabeb 100644
--- a/drivers/mtd/nand/raw/gpio.c
+++ b/drivers/mtd/nand/raw/gpio.c
@@ -343,7 +343,7 @@ static int gpio_nand_probe(struct platform_device *pdev)
 
 	nand_set_flash_node(chip, pdev->dev.of_node);
 	chip->ecc.mode		= NAND_ECC_SOFT;
-	chip->ecc.algo		= NAND_ECC_HAMMING;
+	chip->ecc.algo		= NAND_ECC_ALGO_HAMMING;
 	chip->options		= gpiomtd->plat.options;
 	chip->controller	= &gpiomtd->base;
 
diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c
index 8482d3bd8b1f..b2200aa787f2 100644
--- a/drivers/mtd/nand/raw/marvell_nand.c
+++ b/drivers/mtd/nand/raw/marvell_nand.c
@@ -780,7 +780,7 @@ static void marvell_nfc_enable_hw_ecc(struct nand_chip *chip)
 		 * When enabling BCH, set threshold to 0 to always know the
 		 * number of corrected bitflips.
 		 */
-		if (chip->ecc.algo == NAND_ECC_BCH)
+		if (chip->ecc.algo == NAND_ECC_ALGO_BCH)
 			writel_relaxed(NDECCCTRL_BCH_EN, nfc->regs + NDECCCTRL);
 	}
 }
@@ -792,7 +792,7 @@ static void marvell_nfc_disable_hw_ecc(struct nand_chip *chip)
 
 	if (ndcr & NDCR_ECC_EN) {
 		writel_relaxed(ndcr & ~NDCR_ECC_EN, nfc->regs + NDCR);
-		if (chip->ecc.algo == NAND_ECC_BCH)
+		if (chip->ecc.algo == NAND_ECC_ALGO_BCH)
 			writel_relaxed(0, nfc->regs + NDECCCTRL);
 	}
 }
@@ -966,7 +966,7 @@ static int marvell_nfc_hw_ecc_check_bitflips(struct nand_chip *chip,
 	if (ndsr & NDSR_CORERR) {
 		writel_relaxed(ndsr, nfc->regs + NDSR);
 
-		if (chip->ecc.algo == NAND_ECC_BCH)
+		if (chip->ecc.algo == NAND_ECC_ALGO_BCH)
 			bf = NDSR_ERRCNT(ndsr);
 		else
 			bf = 1;
@@ -2218,7 +2218,7 @@ static int marvell_nand_hw_ecc_controller_init(struct mtd_info *mtd,
 	ecc->size = l->data_bytes;
 
 	if (ecc->strength == 1) {
-		chip->ecc.algo = NAND_ECC_HAMMING;
+		chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
 		ecc->read_page_raw = marvell_nfc_hw_ecc_hmg_read_page_raw;
 		ecc->read_page = marvell_nfc_hw_ecc_hmg_read_page;
 		ecc->read_oob_raw = marvell_nfc_hw_ecc_hmg_read_oob_raw;
@@ -2228,7 +2228,7 @@ static int marvell_nand_hw_ecc_controller_init(struct mtd_info *mtd,
 		ecc->write_oob_raw = marvell_nfc_hw_ecc_hmg_write_oob_raw;
 		ecc->write_oob = ecc->write_oob_raw;
 	} else {
-		chip->ecc.algo = NAND_ECC_BCH;
+		chip->ecc.algo = NAND_ECC_ALGO_BCH;
 		ecc->strength = 16;
 		ecc->read_page_raw = marvell_nfc_hw_ecc_bch_read_page_raw;
 		ecc->read_page = marvell_nfc_hw_ecc_bch_read_page;
diff --git a/drivers/mtd/nand/raw/mpc5121_nfc.c b/drivers/mtd/nand/raw/mpc5121_nfc.c
index 18ecb096a32d..a67eded226db 100644
--- a/drivers/mtd/nand/raw/mpc5121_nfc.c
+++ b/drivers/mtd/nand/raw/mpc5121_nfc.c
@@ -689,7 +689,7 @@ static int mpc5121_nfc_probe(struct platform_device *op)
 	chip->legacy.get_features = nand_get_set_features_notsupp;
 	chip->bbt_options = NAND_BBT_USE_FLASH;
 	chip->ecc.mode = NAND_ECC_SOFT;
-	chip->ecc.algo = NAND_ECC_HAMMING;
+	chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
 
 	/* Support external chip-select logic on ADS5121 board */
 	if (of_machine_is_compatible("fsl,mpc5121ads")) {
diff --git a/drivers/mtd/nand/raw/mxc_nand.c b/drivers/mtd/nand/raw/mxc_nand.c
index a043d76b48cb..65448fb223b8 100644
--- a/drivers/mtd/nand/raw/mxc_nand.c
+++ b/drivers/mtd/nand/raw/mxc_nand.c
@@ -1846,7 +1846,7 @@ static int mxcnd_probe(struct platform_device *pdev)
 		this->ecc.mode = NAND_ECC_HW;
 	} else {
 		this->ecc.mode = NAND_ECC_SOFT;
-		this->ecc.algo = NAND_ECC_HAMMING;
+		this->ecc.algo = NAND_ECC_ALGO_HAMMING;
 	}
 
 	/* NAND bus width determines access functions used by upper layer */
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 0c768cb88f96..e22a7f9986b1 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -5066,9 +5066,9 @@ static int of_get_nand_ecc_mode(struct device_node *np)
 }
 
 static const char * const nand_ecc_algos[] = {
-	[NAND_ECC_HAMMING]	= "hamming",
-	[NAND_ECC_BCH]		= "bch",
-	[NAND_ECC_RS]		= "rs",
+	[NAND_ECC_ALGO_HAMMING]	= "hamming",
+	[NAND_ECC_ALGO_BCH]	= "bch",
+	[NAND_ECC_ALGO_RS]	= "rs",
 };
 
 static enum nand_ecc_algo of_get_nand_ecc_algo(struct device_node *np)
@@ -5079,7 +5079,7 @@ static enum nand_ecc_algo of_get_nand_ecc_algo(struct device_node *np)
 
 	err = of_property_read_string(np, "nand-ecc-algo", &pm);
 	if (!err) {
-		for (ecc_algo = NAND_ECC_HAMMING;
+		for (ecc_algo = NAND_ECC_ALGO_HAMMING;
 		     ecc_algo < ARRAY_SIZE(nand_ecc_algos);
 		     ecc_algo++) {
 			if (!strcasecmp(pm, nand_ecc_algos[ecc_algo]))
@@ -5094,12 +5094,12 @@ static enum nand_ecc_algo of_get_nand_ecc_algo(struct device_node *np)
 	err = of_property_read_string(np, "nand-ecc-mode", &pm);
 	if (!err) {
 		if (!strcasecmp(pm, "soft"))
-			return NAND_ECC_HAMMING;
+			return NAND_ECC_ALGO_HAMMING;
 		else if (!strcasecmp(pm, "soft_bch"))
-			return NAND_ECC_BCH;
+			return NAND_ECC_ALGO_BCH;
 	}
 
-	return NAND_ECC_UNKNOWN;
+	return NAND_ECC_ALGO_UNKNOWN;
 }
 
 static int of_get_nand_ecc_step_size(struct device_node *np)
@@ -5167,7 +5167,7 @@ static int nand_dt_init(struct nand_chip *chip)
 	if (ecc_mode >= 0)
 		chip->ecc.mode = ecc_mode;
 
-	if (ecc_algo != NAND_ECC_UNKNOWN)
+	if (ecc_algo != NAND_ECC_ALGO_UNKNOWN)
 		chip->ecc.algo = ecc_algo;
 
 	if (ecc_strength >= 0)
@@ -5291,7 +5291,7 @@ static int nand_set_ecc_soft_ops(struct nand_chip *chip)
 		return -EINVAL;
 
 	switch (ecc->algo) {
-	case NAND_ECC_HAMMING:
+	case NAND_ECC_ALGO_HAMMING:
 		ecc->calculate = nand_calculate_ecc;
 		ecc->correct = nand_correct_data;
 		ecc->read_page = nand_read_page_swecc;
@@ -5312,7 +5312,7 @@ static int nand_set_ecc_soft_ops(struct nand_chip *chip)
 			ecc->options |= NAND_ECC_SOFT_HAMMING_SM_ORDER;
 
 		return 0;
-	case NAND_ECC_BCH:
+	case NAND_ECC_ALGO_BCH:
 		if (!mtd_nand_has_bch()) {
 			WARN(1, "CONFIG_MTD_NAND_ECC_SW_BCH not enabled\n");
 			return -EINVAL;
@@ -5752,7 +5752,7 @@ static int nand_scan_tail(struct nand_chip *chip)
 	 * If no default placement scheme is given, select an appropriate one.
 	 */
 	if (!mtd->ooblayout &&
-	    !(ecc->mode == NAND_ECC_SOFT && ecc->algo == NAND_ECC_BCH)) {
+	    !(ecc->mode == NAND_ECC_SOFT && ecc->algo == NAND_ECC_ALGO_BCH)) {
 		switch (mtd->oobsize) {
 		case 8:
 		case 16:
@@ -5843,7 +5843,7 @@ static int nand_scan_tail(struct nand_chip *chip)
 		pr_warn("%d byte HW ECC not possible on %d byte page size, fallback to SW ECC\n",
 			ecc->size, mtd->writesize);
 		ecc->mode = NAND_ECC_SOFT;
-		ecc->algo = NAND_ECC_HAMMING;
+		ecc->algo = NAND_ECC_ALGO_HAMMING;
 		fallthrough;
 	case NAND_ECC_SOFT:
 		ret = nand_set_ecc_soft_ops(chip);
@@ -6102,7 +6102,7 @@ EXPORT_SYMBOL(nand_scan_with_ids);
 void nand_cleanup(struct nand_chip *chip)
 {
 	if (chip->ecc.mode == NAND_ECC_SOFT &&
-	    chip->ecc.algo == NAND_ECC_BCH)
+	    chip->ecc.algo == NAND_ECC_ALGO_BCH)
 		nand_bch_free((struct nand_bch_control *)chip->ecc.priv);
 
 	nanddev_cleanup(&chip->base);
diff --git a/drivers/mtd/nand/raw/nand_micron.c b/drivers/mtd/nand/raw/nand_micron.c
index 4385092a9325..2d54a3aa15b1 100644
--- a/drivers/mtd/nand/raw/nand_micron.c
+++ b/drivers/mtd/nand/raw/nand_micron.c
@@ -543,7 +543,7 @@ static int micron_nand_init(struct nand_chip *chip)
 		chip->ecc.bytes = chip->base.eccreq.strength * 2;
 		chip->ecc.size = 512;
 		chip->ecc.strength = chip->base.eccreq.strength;
-		chip->ecc.algo = NAND_ECC_BCH;
+		chip->ecc.algo = NAND_ECC_ALGO_BCH;
 		chip->ecc.read_page = micron_nand_read_page_on_die_ecc;
 		chip->ecc.write_page = micron_nand_write_page_on_die_ecc;
 
diff --git a/drivers/mtd/nand/raw/nandsim.c b/drivers/mtd/nand/raw/nandsim.c
index f5a53aac3c5f..1ab849ccaa96 100644
--- a/drivers/mtd/nand/raw/nandsim.c
+++ b/drivers/mtd/nand/raw/nandsim.c
@@ -2235,7 +2235,7 @@ static int ns_attach_chip(struct nand_chip *chip)
 	}
 
 	chip->ecc.mode = NAND_ECC_SOFT;
-	chip->ecc.algo = NAND_ECC_BCH;
+	chip->ecc.algo = NAND_ECC_ALGO_BCH;
 	chip->ecc.size = 512;
 	chip->ecc.strength = bch;
 	chip->ecc.bytes = eccbytes;
@@ -2275,7 +2275,7 @@ static int __init ns_init_module(void)
 	nand_set_controller_data(chip, (void *)ns);
 
 	chip->ecc.mode   = NAND_ECC_SOFT;
-	chip->ecc.algo   = NAND_ECC_HAMMING;
+	chip->ecc.algo   = NAND_ECC_ALGO_HAMMING;
 	/* The NAND_SKIP_BBTSCAN option is necessary for 'overridesize' */
 	/* and 'badblocks' parameters to work */
 	chip->options   |= NAND_SKIP_BBTSCAN;
diff --git a/drivers/mtd/nand/raw/omap2.c b/drivers/mtd/nand/raw/omap2.c
index eb7fcfd9276b..967ddbda1c48 100644
--- a/drivers/mtd/nand/raw/omap2.c
+++ b/drivers/mtd/nand/raw/omap2.c
@@ -2011,7 +2011,7 @@ static int omap_nand_attach_chip(struct nand_chip *chip)
 	 */
 	if (info->ecc_opt == OMAP_ECC_HAM1_CODE_SW) {
 		chip->ecc.mode = NAND_ECC_SOFT;
-		chip->ecc.algo = NAND_ECC_HAMMING;
+		chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
 		return 0;
 	}
 
diff --git a/drivers/mtd/nand/raw/orion_nand.c b/drivers/mtd/nand/raw/orion_nand.c
index 880b54ca1b41..7a5cfa3d883f 100644
--- a/drivers/mtd/nand/raw/orion_nand.c
+++ b/drivers/mtd/nand/raw/orion_nand.c
@@ -140,7 +140,7 @@ static int __init orion_nand_probe(struct platform_device *pdev)
 	nc->legacy.cmd_ctrl = orion_nand_cmd_ctrl;
 	nc->legacy.read_buf = orion_nand_read_buf;
 	nc->ecc.mode = NAND_ECC_SOFT;
-	nc->ecc.algo = NAND_ECC_HAMMING;
+	nc->ecc.algo = NAND_ECC_ALGO_HAMMING;
 
 	if (board->chip_delay)
 		nc->legacy.chip_delay = board->chip_delay;
diff --git a/drivers/mtd/nand/raw/pasemi_nand.c b/drivers/mtd/nand/raw/pasemi_nand.c
index d8eca8c3fdcd..3eddc284614d 100644
--- a/drivers/mtd/nand/raw/pasemi_nand.c
+++ b/drivers/mtd/nand/raw/pasemi_nand.c
@@ -133,7 +133,7 @@ static int pasemi_nand_probe(struct platform_device *ofdev)
 	chip->legacy.write_buf = pasemi_write_buf;
 	chip->legacy.chip_delay = 0;
 	chip->ecc.mode = NAND_ECC_SOFT;
-	chip->ecc.algo = NAND_ECC_HAMMING;
+	chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
 
 	/* Enable the following for a flash based bad block table */
 	chip->bbt_options = NAND_BBT_USE_FLASH;
diff --git a/drivers/mtd/nand/raw/plat_nand.c b/drivers/mtd/nand/raw/plat_nand.c
index 556182f26057..dbc089c8872f 100644
--- a/drivers/mtd/nand/raw/plat_nand.c
+++ b/drivers/mtd/nand/raw/plat_nand.c
@@ -67,7 +67,7 @@ static int plat_nand_probe(struct platform_device *pdev)
 	data->chip.bbt_options |= pdata->chip.bbt_options;
 
 	data->chip.ecc.mode = NAND_ECC_SOFT;
-	data->chip.ecc.algo = NAND_ECC_HAMMING;
+	data->chip.ecc.algo = NAND_ECC_ALGO_HAMMING;
 
 	platform_set_drvdata(pdev, data);
 
diff --git a/drivers/mtd/nand/raw/s3c2410.c b/drivers/mtd/nand/raw/s3c2410.c
index 105522205979..5a39002d67ef 100644
--- a/drivers/mtd/nand/raw/s3c2410.c
+++ b/drivers/mtd/nand/raw/s3c2410.c
@@ -938,11 +938,11 @@ static int s3c2410_nand_attach_chip(struct nand_chip *chip)
 	case NAND_ECC_SOFT:
 		/*
 		 * This driver expects Hamming based ECC when ecc_mode is set
-		 * to NAND_ECC_SOFT. Force ecc.algo to NAND_ECC_HAMMING to
+		 * to NAND_ECC_SOFT. Force ecc.algo to NAND_ECC_ALGO_HAMMING to
 		 * avoid adding an extra ecc_algo field to
 		 * s3c2410_platform_nand.
 		 */
-		chip->ecc.algo = NAND_ECC_HAMMING;
+		chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
 		dev_info(info->device, "soft ECC\n");
 		break;
 
diff --git a/drivers/mtd/nand/raw/sh_flctl.c b/drivers/mtd/nand/raw/sh_flctl.c
index a661b8bb2dd5..9dbd6fdbe264 100644
--- a/drivers/mtd/nand/raw/sh_flctl.c
+++ b/drivers/mtd/nand/raw/sh_flctl.c
@@ -1045,7 +1045,7 @@ static int flctl_chip_attach_chip(struct nand_chip *chip)
 		flctl->flcmncr_base |= _4ECCEN;
 	} else {
 		chip->ecc.mode = NAND_ECC_SOFT;
-		chip->ecc.algo = NAND_ECC_HAMMING;
+		chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
 	}
 
 	return 0;
diff --git a/drivers/mtd/nand/raw/socrates_nand.c b/drivers/mtd/nand/raw/socrates_nand.c
index 243b34cfbc1b..72a3a7f98282 100644
--- a/drivers/mtd/nand/raw/socrates_nand.c
+++ b/drivers/mtd/nand/raw/socrates_nand.c
@@ -154,7 +154,7 @@ static int socrates_nand_probe(struct platform_device *ofdev)
 	nand_chip->legacy.dev_ready = socrates_nand_device_ready;
 
 	nand_chip->ecc.mode = NAND_ECC_SOFT;	/* enable ECC */
-	nand_chip->ecc.algo = NAND_ECC_HAMMING;
+	nand_chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
 
 	/* TODO: I have no idea what real delay is. */
 	nand_chip->legacy.chip_delay = 20;	/* 20us command delay time */
diff --git a/drivers/mtd/nand/raw/tango_nand.c b/drivers/mtd/nand/raw/tango_nand.c
index bdb965ae7a4a..021ceef4ad0a 100644
--- a/drivers/mtd/nand/raw/tango_nand.c
+++ b/drivers/mtd/nand/raw/tango_nand.c
@@ -550,7 +550,7 @@ static int tango_attach_chip(struct nand_chip *chip)
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
 
 	ecc->mode = NAND_ECC_HW;
-	ecc->algo = NAND_ECC_BCH;
+	ecc->algo = NAND_ECC_ALGO_BCH;
 	ecc->bytes = DIV_ROUND_UP(ecc->strength * FIELD_ORDER, BITS_PER_BYTE);
 
 	ecc->read_page_raw = tango_read_page_raw;
diff --git a/drivers/mtd/nand/raw/tegra_nand.c b/drivers/mtd/nand/raw/tegra_nand.c
index 6b6212ffa01c..0d6f3c6d6e11 100644
--- a/drivers/mtd/nand/raw/tegra_nand.c
+++ b/drivers/mtd/nand/raw/tegra_nand.c
@@ -479,7 +479,7 @@ static void tegra_nand_hw_ecc(struct tegra_nand_controller *ctrl,
 {
 	struct tegra_nand_chip *nand = to_tegra_chip(chip);
 
-	if (chip->ecc.algo == NAND_ECC_BCH && enable)
+	if (chip->ecc.algo == NAND_ECC_ALGO_BCH && enable)
 		writel_relaxed(nand->bch_config, ctrl->regs + BCH_CONFIG);
 	else
 		writel_relaxed(0, ctrl->regs + BCH_CONFIG);
@@ -877,7 +877,7 @@ static int tegra_nand_select_strength(struct nand_chip *chip, int oobsize)
 	int strength_len, bits_per_step;
 
 	switch (chip->ecc.algo) {
-	case NAND_ECC_RS:
+	case NAND_ECC_ALGO_RS:
 		bits_per_step = BITS_PER_STEP_RS;
 		if (chip->options & NAND_IS_BOOT_MEDIUM) {
 			strength = rs_strength_bootable;
@@ -887,7 +887,7 @@ static int tegra_nand_select_strength(struct nand_chip *chip, int oobsize)
 			strength_len = ARRAY_SIZE(rs_strength);
 		}
 		break;
-	case NAND_ECC_BCH:
+	case NAND_ECC_ALGO_BCH:
 		bits_per_step = BITS_PER_STEP_BCH;
 		if (chip->options & NAND_IS_BOOT_MEDIUM) {
 			strength = bch_strength_bootable;
@@ -935,14 +935,14 @@ static int tegra_nand_attach_chip(struct nand_chip *chip)
 	if (chip->options & NAND_BUSWIDTH_16)
 		nand->config |= CONFIG_BUS_WIDTH_16;
 
-	if (chip->ecc.algo == NAND_ECC_UNKNOWN) {
+	if (chip->ecc.algo == NAND_ECC_ALGO_UNKNOWN) {
 		if (mtd->writesize < 2048)
-			chip->ecc.algo = NAND_ECC_RS;
+			chip->ecc.algo = NAND_ECC_ALGO_RS;
 		else
-			chip->ecc.algo = NAND_ECC_BCH;
+			chip->ecc.algo = NAND_ECC_ALGO_BCH;
 	}
 
-	if (chip->ecc.algo == NAND_ECC_BCH && mtd->writesize < 2048) {
+	if (chip->ecc.algo == NAND_ECC_ALGO_BCH && mtd->writesize < 2048) {
 		dev_err(ctrl->dev, "BCH supports 2K or 4K page size only\n");
 		return -EINVAL;
 	}
@@ -963,7 +963,7 @@ static int tegra_nand_attach_chip(struct nand_chip *chip)
 			   CONFIG_SKIP_SPARE_SIZE_4;
 
 	switch (chip->ecc.algo) {
-	case NAND_ECC_RS:
+	case NAND_ECC_ALGO_RS:
 		bits_per_step = BITS_PER_STEP_RS * chip->ecc.strength;
 		mtd_set_ooblayout(mtd, &tegra_nand_oob_rs_ops);
 		nand->config_ecc |= CONFIG_HW_ECC | CONFIG_ECC_SEL |
@@ -984,7 +984,7 @@ static int tegra_nand_attach_chip(struct nand_chip *chip)
 			return -EINVAL;
 		}
 		break;
-	case NAND_ECC_BCH:
+	case NAND_ECC_ALGO_BCH:
 		bits_per_step = BITS_PER_STEP_BCH * chip->ecc.strength;
 		mtd_set_ooblayout(mtd, &tegra_nand_oob_bch_ops);
 		nand->bch_config = BCH_ENABLE;
@@ -1013,7 +1013,7 @@ static int tegra_nand_attach_chip(struct nand_chip *chip)
 	}
 
 	dev_info(ctrl->dev, "Using %s with strength %d per 512 byte step\n",
-		 chip->ecc.algo == NAND_ECC_BCH ? "BCH" : "RS",
+		 chip->ecc.algo == NAND_ECC_ALGO_BCH ? "BCH" : "RS",
 		 chip->ecc.strength);
 
 	chip->ecc.bytes = DIV_ROUND_UP(bits_per_step, BITS_PER_BYTE);
diff --git a/drivers/mtd/nand/raw/xway_nand.c b/drivers/mtd/nand/raw/xway_nand.c
index 29255476afdb..b279ed143b8f 100644
--- a/drivers/mtd/nand/raw/xway_nand.c
+++ b/drivers/mtd/nand/raw/xway_nand.c
@@ -181,7 +181,7 @@ static int xway_nand_probe(struct platform_device *pdev)
 	data->chip.legacy.chip_delay = 30;
 
 	data->chip.ecc.mode = NAND_ECC_SOFT;
-	data->chip.ecc.algo = NAND_ECC_HAMMING;
+	data->chip.ecc.algo = NAND_ECC_ALGO_HAMMING;
 
 	platform_set_drvdata(pdev, data);
 	nand_set_controller_data(&data->chip, data);
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 1495f22b60cb..8174c0c331a1 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -94,16 +94,16 @@ enum nand_ecc_mode {
 
 /**
  * enum nand_ecc_algo - NAND ECC algorithm
- * @NAND_ECC_UNKNOWN: Unknown algorithm
- * @NAND_ECC_HAMMING: Hamming algorithm
- * @NAND_ECC_BCH: Bose-Chaudhuri-Hocquenghem algorithm
- * @NAND_ECC_RS: Reed-Solomon algorithm
+ * @NAND_ECC_ALGO_UNKNOWN: Unknown algorithm
+ * @NAND_ECC_ALGO_HAMMING: Hamming algorithm
+ * @NAND_ECC_ALGO_BCH: Bose-Chaudhuri-Hocquenghem algorithm
+ * @NAND_ECC_ALGO_RS: Reed-Solomon algorithm
  */
 enum nand_ecc_algo {
-	NAND_ECC_UNKNOWN,
-	NAND_ECC_HAMMING,
-	NAND_ECC_BCH,
-	NAND_ECC_RS,
+	NAND_ECC_ALGO_UNKNOWN,
+	NAND_ECC_ALGO_HAMMING,
+	NAND_ECC_ALGO_BCH,
+	NAND_ECC_ALGO_RS,
 };
 
 /*
-- 
cgit v1.2.3


From f2f64c1e924131878179da64794d9cb18ee5c827 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Thu, 27 Aug 2020 10:51:51 +0200
Subject: mtd: rawnand: Move the nand_ecc_algo enum to the generic NAND layer

This enumeration is generic and will be reused NAND-wide.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-4-miquel.raynal@bootlin.com
---
 include/linux/mtd/nand.h    | 14 ++++++++++++++
 include/linux/mtd/rawnand.h | 14 --------------
 2 files changed, 14 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index af99041ceaa9..986c7de83326 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -115,6 +115,20 @@ struct nand_page_io_req {
 	int mode;
 };
 
+/**
+ * enum nand_ecc_algo - NAND ECC algorithm
+ * @NAND_ECC_ALGO_UNKNOWN: Unknown algorithm
+ * @NAND_ECC_ALGO_HAMMING: Hamming algorithm
+ * @NAND_ECC_ALGO_BCH: Bose-Chaudhuri-Hocquenghem algorithm
+ * @NAND_ECC_ALGO_RS: Reed-Solomon algorithm
+ */
+enum nand_ecc_algo {
+	NAND_ECC_ALGO_UNKNOWN,
+	NAND_ECC_ALGO_HAMMING,
+	NAND_ECC_ALGO_BCH,
+	NAND_ECC_ALGO_RS,
+};
+
 /**
  * struct nand_ecc_props - NAND ECC properties
  * @strength: ECC strength
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 8174c0c331a1..10bbfbf4ad7f 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -92,20 +92,6 @@ enum nand_ecc_mode {
 	NAND_ECC_ON_DIE,
 };
 
-/**
- * enum nand_ecc_algo - NAND ECC algorithm
- * @NAND_ECC_ALGO_UNKNOWN: Unknown algorithm
- * @NAND_ECC_ALGO_HAMMING: Hamming algorithm
- * @NAND_ECC_ALGO_BCH: Bose-Chaudhuri-Hocquenghem algorithm
- * @NAND_ECC_ALGO_RS: Reed-Solomon algorithm
- */
-enum nand_ecc_algo {
-	NAND_ECC_ALGO_UNKNOWN,
-	NAND_ECC_ALGO_HAMMING,
-	NAND_ECC_ALGO_BCH,
-	NAND_ECC_ALGO_RS,
-};
-
 /*
  * Constants for Hardware ECC
  */
-- 
cgit v1.2.3


From 701981cab01696584a12e5f0e7c2ad931a326059 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Thu, 27 Aug 2020 10:51:52 +0200
Subject: mtd: nand: Add a NAND page I/O request type

Use an enum to differentiate the type of I/O (reading or writing a
page). Also update the request iterator.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-5-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/spi/core.c |  4 ++--
 include/linux/mtd/nand.h    | 18 ++++++++++++++++--
 2 files changed, 18 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c
index e2c382ffc5b6..4725d390c87c 100644
--- a/drivers/mtd/nand/spi/core.c
+++ b/drivers/mtd/nand/spi/core.c
@@ -497,7 +497,7 @@ static int spinand_mtd_read(struct mtd_info *mtd, loff_t from,
 
 	mutex_lock(&spinand->lock);
 
-	nanddev_io_for_each_page(nand, from, ops, &iter) {
+	nanddev_io_for_each_page(nand, NAND_PAGE_READ, from, ops, &iter) {
 		ret = spinand_select_target(spinand, iter.req.pos.target);
 		if (ret)
 			break;
@@ -545,7 +545,7 @@ static int spinand_mtd_write(struct mtd_info *mtd, loff_t to,
 
 	mutex_lock(&spinand->lock);
 
-	nanddev_io_for_each_page(nand, to, ops, &iter) {
+	nanddev_io_for_each_page(nand, NAND_PAGE_WRITE, to, ops, &iter) {
 		ret = spinand_select_target(spinand, iter.req.pos.target);
 		if (ret)
 			break;
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 986c7de83326..e754a6fc8a4b 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -82,8 +82,19 @@ struct nand_pos {
 	unsigned int page;
 };
 
+/**
+ * enum nand_page_io_req_type - Direction of an I/O request
+ * @NAND_PAGE_READ: from the chip, to the controller
+ * @NAND_PAGE_WRITE: from the controller, to the chip
+ */
+enum nand_page_io_req_type {
+	NAND_PAGE_READ = 0,
+	NAND_PAGE_WRITE,
+};
+
 /**
  * struct nand_page_io_req - NAND I/O request object
+ * @type: the type of page I/O: read or write
  * @pos: the position this I/O request is targeting
  * @dataoffs: the offset within the page
  * @datalen: number of data bytes to read from/write to this page
@@ -99,6 +110,7 @@ struct nand_pos {
  * specific commands/operations.
  */
 struct nand_page_io_req {
+	enum nand_page_io_req_type type;
 	struct nand_pos pos;
 	unsigned int dataoffs;
 	unsigned int datalen;
@@ -638,11 +650,13 @@ static inline void nanddev_pos_next_page(struct nand_device *nand,
  * layer.
  */
 static inline void nanddev_io_iter_init(struct nand_device *nand,
+					enum nand_page_io_req_type reqtype,
 					loff_t offs, struct mtd_oob_ops *req,
 					struct nand_io_iter *iter)
 {
 	struct mtd_info *mtd = nanddev_to_mtd(nand);
 
+	iter->req.type = reqtype;
 	iter->req.mode = req->mode;
 	iter->req.dataoffs = nanddev_offs_to_pos(nand, offs, &iter->req.pos);
 	iter->req.ooboffs = req->ooboffs;
@@ -712,8 +726,8 @@ static inline bool nanddev_io_iter_end(struct nand_device *nand,
  *
  * Should be used for iterate over pages that are contained in an MTD request.
  */
-#define nanddev_io_for_each_page(nand, start, req, iter)		\
-	for (nanddev_io_iter_init(nand, start, req, iter);		\
+#define nanddev_io_for_each_page(nand, type, start, req, iter)		\
+	for (nanddev_io_iter_init(nand, type, start, req, iter);	\
 	     !nanddev_io_iter_end(nand, iter);				\
 	     nanddev_io_iter_next_page(nand, iter))
 
-- 
cgit v1.2.3


From 7c4b1ab9f16732fb921b3f11cd127fa65f26ad5c Mon Sep 17 00:00:00 2001
From: Mark Zhang <markz@mellanox.com>
Date: Tue, 18 Aug 2020 14:52:45 +0300
Subject: IB/mlx5: Add DCT RoCE LAG support

When DCT QPs work in RoCE LAG mode:
 1. DCT creation is allowed only when it is supported
 2. The "port" of a DCT QP is assigned in a round-robin way

Link: https://lore.kernel.org/r/20200818115245.700581-3-leon@kernel.org
Signed-off-by: Mark Zhang <markz@mellanox.com>
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/hw/mlx5/qp.c | 9 ++++++++-
 include/linux/mlx5/mlx5_ifc.h   | 3 ++-
 2 files changed, 10 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 214d401ed3d2..e51df89e4440 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -2409,6 +2409,9 @@ static int create_dct(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 	u32 uidx = params->uidx;
 	void *dctc;
 
+	if (mlx5_lag_is_active(dev->mdev) && !MLX5_CAP_GEN(dev->mdev, lag_dct))
+		return -EOPNOTSUPP;
+
 	qp->dct.in = kzalloc(MLX5_ST_SZ_BYTES(create_dct_in), GFP_KERNEL);
 	if (!qp->dct.in)
 		return -ENOMEM;
@@ -4183,7 +4186,11 @@ static int mlx5_ib_modify_dct(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 			MLX5_SET(dctc, dctc, rae, 1);
 		}
 		MLX5_SET(dctc, dctc, pkey_index, attr->pkey_index);
-		MLX5_SET(dctc, dctc, port, attr->port_num);
+		if (mlx5_lag_is_active(dev->mdev))
+			MLX5_SET(dctc, dctc, port,
+				 get_tx_affinity_rr(dev, udata));
+		else
+			MLX5_SET(dctc, dctc, port, attr->port_num);
 
 		set_id = mlx5_ib_get_counters_id(dev, attr->port_num - 1);
 		MLX5_SET(dctc, dctc, counter_set_id, set_id);
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index de1ffb4804d6..aee25e4fb2cc 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1430,7 +1430,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 	u8         log_bf_reg_size[0x5];
 
-	u8         reserved_at_270[0x8];
+	u8         reserved_at_270[0x6];
+	u8         lag_dct[0x2];
 	u8         lag_tx_port_affinity[0x1];
 	u8         reserved_at_279[0x2];
 	u8         lag_master[0x1];
-- 
cgit v1.2.3


From 1c9c02bb22684f6949d2e7ddc0a3ff364fd5a6fc Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 27 Apr 2020 14:50:37 -0500
Subject: mtd: lpddr: Fix bad logic in print_drs_error

Update logic for broken test. Use a more common logging style.

It appears the logic in this function is broken for the
consecutive tests of

        if (prog_status & 0x3)
                ...
        else if (prog_status & 0x2)
                ...
        else (prog_status & 0x1)
                ...

Likely the first test should be

        if ((prog_status & 0x3) == 0x3)

Found by inspection of include files using printk.

Fixes: eb3db27507f7 ("[MTD] LPDDR PFOW definition")
Cc: stable@vger.kernel.org
Reported-by: Joe Perches <joe@perches.com>
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Acked-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/3fb0e29f5b601db8be2938a01d974b00c8788501.1588016644.git.gustavo@embeddedor.com
---
 include/linux/mtd/pfow.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/mtd/pfow.h b/include/linux/mtd/pfow.h
index 6166e7c60869..b8da6f8e854b 100644
--- a/include/linux/mtd/pfow.h
+++ b/include/linux/mtd/pfow.h
@@ -128,7 +128,7 @@ static inline void print_drs_error(unsigned dsr)
 
 	if (!(dsr & DSR_AVAILABLE))
 		printk(KERN_NOTICE"DSR.15: (0) Device not Available\n");
-	if (prog_status & 0x03)
+	if ((prog_status & 0x03) == 0x03)
 		printk(KERN_NOTICE"DSR.9,8: (11) Attempt to program invalid "
 						"half with 41h command\n");
 	else if (prog_status & 0x02)
-- 
cgit v1.2.3


From 518693abe6e3f57606ec18892e9135abbc04b361 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 27 Apr 2020 14:54:13 -0500
Subject: mtd: lpddr: Replace printk with pr_notice

pr_notice is preferred over printk.

Also, coalesce formats as coalescing is part of coding-style:
"never break user-visible strings such as printk messages"

Suggested-by: Joe Perches <joe@perches.com>
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/ff48ce07ef208ba65b858f09279a3b36031d64d2.1588016644.git.gustavo@embeddedor.com
---
 include/linux/mtd/pfow.h | 27 +++++++++++----------------
 1 file changed, 11 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mtd/pfow.h b/include/linux/mtd/pfow.h
index b8da6f8e854b..1c0f6113f230 100644
--- a/include/linux/mtd/pfow.h
+++ b/include/linux/mtd/pfow.h
@@ -127,31 +127,26 @@ static inline void print_drs_error(unsigned dsr)
 	int prog_status = (dsr & DSR_RPS) >> 8;
 
 	if (!(dsr & DSR_AVAILABLE))
-		printk(KERN_NOTICE"DSR.15: (0) Device not Available\n");
+		pr_notice("DSR.15: (0) Device not Available\n");
 	if ((prog_status & 0x03) == 0x03)
-		printk(KERN_NOTICE"DSR.9,8: (11) Attempt to program invalid "
-						"half with 41h command\n");
+		pr_notice("DSR.9,8: (11) Attempt to program invalid half with 41h command\n");
 	else if (prog_status & 0x02)
-		printk(KERN_NOTICE"DSR.9,8: (10) Object Mode Program attempt "
-					"in region with Control Mode data\n");
+		pr_notice("DSR.9,8: (10) Object Mode Program attempt in region with Control Mode data\n");
 	else if (prog_status &  0x01)
-		printk(KERN_NOTICE"DSR.9,8: (01) Program attempt in region "
-						"with Object Mode data\n");
+		pr_notice("DSR.9,8: (01) Program attempt in region with Object Mode data\n");
 	if (!(dsr & DSR_READY_STATUS))
-		printk(KERN_NOTICE"DSR.7: (0) Device is Busy\n");
+		pr_notice("DSR.7: (0) Device is Busy\n");
 	if (dsr & DSR_ESS)
-		printk(KERN_NOTICE"DSR.6: (1) Erase Suspended\n");
+		pr_notice("DSR.6: (1) Erase Suspended\n");
 	if (dsr & DSR_ERASE_STATUS)
-		printk(KERN_NOTICE"DSR.5: (1) Erase/Blank check error\n");
+		pr_notice("DSR.5: (1) Erase/Blank check error\n");
 	if (dsr & DSR_PROGRAM_STATUS)
-		printk(KERN_NOTICE"DSR.4: (1) Program Error\n");
+		pr_notice("DSR.4: (1) Program Error\n");
 	if (dsr & DSR_VPPS)
-		printk(KERN_NOTICE"DSR.3: (1) Vpp low detect, operation "
-					"aborted\n");
+		pr_notice("DSR.3: (1) Vpp low detect, operation aborted\n");
 	if (dsr & DSR_PSS)
-		printk(KERN_NOTICE"DSR.2: (1) Program suspended\n");
+		pr_notice("DSR.2: (1) Program suspended\n");
 	if (dsr & DSR_DPS)
-		printk(KERN_NOTICE"DSR.1: (1) Aborted Erase/Program attempt "
-					"on locked block\n");
+		pr_notice("DSR.1: (1) Aborted Erase/Program attempt on locked block\n");
 }
 #endif /* __LINUX_MTD_PFOW_H */
-- 
cgit v1.2.3


From 1a64026eda1642c81425e48550fd4bd3f73d0ab5 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 27 Apr 2020 14:56:08 -0500
Subject: mtd: lpddr: Move function print_drs_error to lpddr_cmds.c

Function print_drs_error is only used in drivers/mtd/lpddr/lpddr_cmds.c
so, better to move it there.

Also, notice that there's no need for inline as the function is used
once.  Lastly, fix the following checkpatch warning:

WARNING: Prefer 'unsigned int' to bare use of 'unsigned'
+static void print_drs_error(unsigned dsr)

Suggested-by: Joe Perches <joe@perches.com>
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/e0063cbd65f3b47be1db34efc494ea3047634d88.1588016644.git.gustavo@embeddedor.com
---
 drivers/mtd/lpddr/lpddr_cmds.c | 28 ++++++++++++++++++++++++++++
 include/linux/mtd/pfow.h       | 28 ----------------------------
 2 files changed, 28 insertions(+), 28 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/lpddr/lpddr_cmds.c b/drivers/mtd/lpddr/lpddr_cmds.c
index fb1cbc9a2870..ee063baed136 100644
--- a/drivers/mtd/lpddr/lpddr_cmds.c
+++ b/drivers/mtd/lpddr/lpddr_cmds.c
@@ -94,6 +94,34 @@ struct mtd_info *lpddr_cmdset(struct map_info *map)
 }
 EXPORT_SYMBOL(lpddr_cmdset);
 
+static void print_drs_error(unsigned int dsr)
+{
+	int prog_status = (dsr & DSR_RPS) >> 8;
+
+	if (!(dsr & DSR_AVAILABLE))
+		pr_notice("DSR.15: (0) Device not Available\n");
+	if ((prog_status & 0x03) == 0x03)
+		pr_notice("DSR.9,8: (11) Attempt to program invalid half with 41h command\n");
+	else if (prog_status & 0x02)
+		pr_notice("DSR.9,8: (10) Object Mode Program attempt in region with Control Mode data\n");
+	else if (prog_status &  0x01)
+		pr_notice("DSR.9,8: (01) Program attempt in region with Object Mode data\n");
+	if (!(dsr & DSR_READY_STATUS))
+		pr_notice("DSR.7: (0) Device is Busy\n");
+	if (dsr & DSR_ESS)
+		pr_notice("DSR.6: (1) Erase Suspended\n");
+	if (dsr & DSR_ERASE_STATUS)
+		pr_notice("DSR.5: (1) Erase/Blank check error\n");
+	if (dsr & DSR_PROGRAM_STATUS)
+		pr_notice("DSR.4: (1) Program Error\n");
+	if (dsr & DSR_VPPS)
+		pr_notice("DSR.3: (1) Vpp low detect, operation aborted\n");
+	if (dsr & DSR_PSS)
+		pr_notice("DSR.2: (1) Program suspended\n");
+	if (dsr & DSR_DPS)
+		pr_notice("DSR.1: (1) Aborted Erase/Program attempt on locked block\n");
+}
+
 static int wait_for_ready(struct map_info *map, struct flchip *chip,
 		unsigned int chip_op_time)
 {
diff --git a/include/linux/mtd/pfow.h b/include/linux/mtd/pfow.h
index 1c0f6113f230..146413d4bdb7 100644
--- a/include/linux/mtd/pfow.h
+++ b/include/linux/mtd/pfow.h
@@ -121,32 +121,4 @@ static inline void send_pfow_command(struct map_info *map,
 	map_write(map, CMD(LPDDR_START_EXECUTION),
 			map->pfow_base + PFOW_COMMAND_EXECUTE);
 }
-
-static inline void print_drs_error(unsigned dsr)
-{
-	int prog_status = (dsr & DSR_RPS) >> 8;
-
-	if (!(dsr & DSR_AVAILABLE))
-		pr_notice("DSR.15: (0) Device not Available\n");
-	if ((prog_status & 0x03) == 0x03)
-		pr_notice("DSR.9,8: (11) Attempt to program invalid half with 41h command\n");
-	else if (prog_status & 0x02)
-		pr_notice("DSR.9,8: (10) Object Mode Program attempt in region with Control Mode data\n");
-	else if (prog_status &  0x01)
-		pr_notice("DSR.9,8: (01) Program attempt in region with Object Mode data\n");
-	if (!(dsr & DSR_READY_STATUS))
-		pr_notice("DSR.7: (0) Device is Busy\n");
-	if (dsr & DSR_ESS)
-		pr_notice("DSR.6: (1) Erase Suspended\n");
-	if (dsr & DSR_ERASE_STATUS)
-		pr_notice("DSR.5: (1) Erase/Blank check error\n");
-	if (dsr & DSR_PROGRAM_STATUS)
-		pr_notice("DSR.4: (1) Program Error\n");
-	if (dsr & DSR_VPPS)
-		pr_notice("DSR.3: (1) Vpp low detect, operation aborted\n");
-	if (dsr & DSR_PSS)
-		pr_notice("DSR.2: (1) Program suspended\n");
-	if (dsr & DSR_DPS)
-		pr_notice("DSR.1: (1) Aborted Erase/Program attempt on locked block\n");
-}
 #endif /* __LINUX_MTD_PFOW_H */
-- 
cgit v1.2.3


From 2fa4e4b799e191530edbae4b96b85d4486e55053 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Thu, 27 Aug 2020 04:00:28 +0200
Subject: net: pcs: Move XPCS into new PCS subdirectory

Create drivers/net/pcs and move the Synopsys DesignWare XPCS into the
new directory. Move the header file into a subdirectory
include/linux/pcs

Start a naming convention of all PCS files use the prefix pcs-, and
rename the XPCS files to fit.

v2:
Add include/linux/pcs

v4:
Fix include path in stmmac.
Remove PCS_DEVICES to avoid new prompts

Cc: Jose Abreu <Jose.Abreu@synopsys.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS                                  |   5 +-
 drivers/net/Kconfig                          |   2 +
 drivers/net/Makefile                         |   1 +
 drivers/net/ethernet/stmicro/stmmac/Kconfig  |   2 +-
 drivers/net/ethernet/stmicro/stmmac/common.h |   2 +-
 drivers/net/pcs/Kconfig                      |  16 +
 drivers/net/pcs/Makefile                     |   4 +
 drivers/net/pcs/pcs-xpcs.c                   | 716 +++++++++++++++++++++++++++
 drivers/net/phy/Kconfig                      |   6 -
 drivers/net/phy/Makefile                     |   1 -
 drivers/net/phy/mdio-xpcs.c                  | 716 ---------------------------
 include/linux/mdio-xpcs.h                    |  41 --
 include/linux/pcs/pcs-xpcs.h                 |  41 ++
 13 files changed, 785 insertions(+), 768 deletions(-)
 create mode 100644 drivers/net/pcs/Kconfig
 create mode 100644 drivers/net/pcs/Makefile
 create mode 100644 drivers/net/pcs/pcs-xpcs.c
 delete mode 100644 drivers/net/phy/mdio-xpcs.c
 delete mode 100644 include/linux/mdio-xpcs.h
 create mode 100644 include/linux/pcs/pcs-xpcs.h

(limited to 'include/linux')

diff --git a/MAINTAINERS b/MAINTAINERS
index 36ec0bd50a8f..347ed6904fdf 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6513,6 +6513,7 @@ F:	Documentation/devicetree/bindings/net/ethernet-phy.yaml
 F:	Documentation/devicetree/bindings/net/mdio*
 F:	Documentation/devicetree/bindings/net/qca,ar803x.yaml
 F:	Documentation/networking/phy.rst
+F:	drivers/net/pcs/
 F:	drivers/net/phy/
 F:	drivers/of/of_mdio.c
 F:	drivers/of/of_net.c
@@ -16730,8 +16731,8 @@ SYNOPSYS DESIGNWARE ETHERNET XPCS DRIVER
 M:	Jose Abreu <Jose.Abreu@synopsys.com>
 L:	netdev@vger.kernel.org
 S:	Supported
-F:	drivers/net/phy/mdio-xpcs.c
-F:	include/linux/mdio-xpcs.h
+F:	drivers/net/pcs/pcs-xpcs.c
+F:	include/linux/pcs/pcs-xpcs.h
 
 SYNOPSYS DESIGNWARE I2C DRIVER
 M:	Jarkko Nikula <jarkko.nikula@linux.intel.com>
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 1368d1d6a114..2b07566de78c 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -473,6 +473,8 @@ config NET_SB1000
 
 source "drivers/net/phy/Kconfig"
 
+source "drivers/net/pcs/Kconfig"
+
 source "drivers/net/plip/Kconfig"
 
 source "drivers/net/ppp/Kconfig"
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index 94b60800887a..f7402d766b67 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -21,6 +21,7 @@ obj-$(CONFIG_MDIO) += mdio.o
 obj-$(CONFIG_NET) += Space.o loopback.o
 obj-$(CONFIG_NETCONSOLE) += netconsole.o
 obj-y += phy/
+obj-y += pcs/
 obj-$(CONFIG_RIONET) += rionet.o
 obj-$(CONFIG_NET_TEAM) += team/
 obj-$(CONFIG_TUN) += tun.o
diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig
index 7572cea9d59e..53f14c5a9e02 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Kconfig
+++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig
@@ -3,7 +3,7 @@ config STMMAC_ETH
 	tristate "STMicroelectronics Multi-Gigabit Ethernet driver"
 	depends on HAS_IOMEM && HAS_DMA
 	select MII
-	select MDIO_XPCS
+	select PCS_XPCS
 	select PAGE_POOL
 	select PHYLINK
 	select CRC32
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 127f75862962..acc5e3fc1c2f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -15,7 +15,7 @@
 #include <linux/netdevice.h>
 #include <linux/stmmac.h>
 #include <linux/phy.h>
-#include <linux/mdio-xpcs.h>
+#include <linux/pcs/pcs-xpcs.h>
 #include <linux/module.h>
 #if IS_ENABLED(CONFIG_VLAN_8021Q)
 #define STMMAC_VLAN_TAG_USED
diff --git a/drivers/net/pcs/Kconfig b/drivers/net/pcs/Kconfig
new file mode 100644
index 000000000000..9d6e2be32060
--- /dev/null
+++ b/drivers/net/pcs/Kconfig
@@ -0,0 +1,16 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# PCS Layer Configuration
+#
+
+menu "PCS device drivers"
+
+config PCS_XPCS
+	tristate "Synopsys DesignWare XPCS controller"
+	select MDIO_BUS
+	depends on MDIO_DEVICE
+	help
+	  This module provides helper functions for Synopsys DesignWare XPCS
+	  controllers.
+
+endmenu
diff --git a/drivers/net/pcs/Makefile b/drivers/net/pcs/Makefile
new file mode 100644
index 000000000000..f0480afc7157
--- /dev/null
+++ b/drivers/net/pcs/Makefile
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
+# Makefile for Linux PCS drivers
+
+obj-$(CONFIG_PCS_XPCS)		+= pcs-xpcs.o
diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c
new file mode 100644
index 000000000000..1aa9903d602e
--- /dev/null
+++ b/drivers/net/pcs/pcs-xpcs.c
@@ -0,0 +1,716 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2020 Synopsys, Inc. and/or its affiliates.
+ * Synopsys DesignWare XPCS helpers
+ *
+ * Author: Jose Abreu <Jose.Abreu@synopsys.com>
+ */
+
+#include <linux/delay.h>
+#include <linux/pcs/pcs-xpcs.h>
+#include <linux/mdio.h>
+#include <linux/phylink.h>
+#include <linux/workqueue.h>
+
+#define SYNOPSYS_XPCS_USXGMII_ID	0x7996ced0
+#define SYNOPSYS_XPCS_10GKR_ID		0x7996ced0
+#define SYNOPSYS_XPCS_XLGMII_ID		0x7996ced0
+#define SYNOPSYS_XPCS_MASK		0xffffffff
+
+/* Vendor regs access */
+#define DW_VENDOR			BIT(15)
+
+/* VR_XS_PCS */
+#define DW_USXGMII_RST			BIT(10)
+#define DW_USXGMII_EN			BIT(9)
+#define DW_VR_XS_PCS_DIG_STS		0x0010
+#define DW_RXFIFO_ERR			GENMASK(6, 5)
+
+/* SR_MII */
+#define DW_USXGMII_FULL			BIT(8)
+#define DW_USXGMII_SS_MASK		(BIT(13) | BIT(6) | BIT(5))
+#define DW_USXGMII_10000		(BIT(13) | BIT(6))
+#define DW_USXGMII_5000			(BIT(13) | BIT(5))
+#define DW_USXGMII_2500			(BIT(5))
+#define DW_USXGMII_1000			(BIT(6))
+#define DW_USXGMII_100			(BIT(13))
+#define DW_USXGMII_10			(0)
+
+/* SR_AN */
+#define DW_SR_AN_ADV1			0x10
+#define DW_SR_AN_ADV2			0x11
+#define DW_SR_AN_ADV3			0x12
+#define DW_SR_AN_LP_ABL1		0x13
+#define DW_SR_AN_LP_ABL2		0x14
+#define DW_SR_AN_LP_ABL3		0x15
+
+/* Clause 73 Defines */
+/* AN_LP_ABL1 */
+#define DW_C73_PAUSE			BIT(10)
+#define DW_C73_ASYM_PAUSE		BIT(11)
+#define DW_C73_AN_ADV_SF		0x1
+/* AN_LP_ABL2 */
+#define DW_C73_1000KX			BIT(5)
+#define DW_C73_10000KX4			BIT(6)
+#define DW_C73_10000KR			BIT(7)
+/* AN_LP_ABL3 */
+#define DW_C73_2500KX			BIT(0)
+#define DW_C73_5000KR			BIT(1)
+
+static const int xpcs_usxgmii_features[] = {
+	ETHTOOL_LINK_MODE_Pause_BIT,
+	ETHTOOL_LINK_MODE_Asym_Pause_BIT,
+	ETHTOOL_LINK_MODE_Autoneg_BIT,
+	ETHTOOL_LINK_MODE_1000baseKX_Full_BIT,
+	ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT,
+	ETHTOOL_LINK_MODE_10000baseKR_Full_BIT,
+	ETHTOOL_LINK_MODE_2500baseX_Full_BIT,
+	__ETHTOOL_LINK_MODE_MASK_NBITS,
+};
+
+static const int xpcs_10gkr_features[] = {
+	ETHTOOL_LINK_MODE_Pause_BIT,
+	ETHTOOL_LINK_MODE_Asym_Pause_BIT,
+	ETHTOOL_LINK_MODE_10000baseKR_Full_BIT,
+	__ETHTOOL_LINK_MODE_MASK_NBITS,
+};
+
+static const int xpcs_xlgmii_features[] = {
+	ETHTOOL_LINK_MODE_Pause_BIT,
+	ETHTOOL_LINK_MODE_Asym_Pause_BIT,
+	ETHTOOL_LINK_MODE_25000baseCR_Full_BIT,
+	ETHTOOL_LINK_MODE_25000baseKR_Full_BIT,
+	ETHTOOL_LINK_MODE_25000baseSR_Full_BIT,
+	ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT,
+	ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT,
+	ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT,
+	ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT,
+	ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT,
+	ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT,
+	ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT,
+	ETHTOOL_LINK_MODE_50000baseKR_Full_BIT,
+	ETHTOOL_LINK_MODE_50000baseSR_Full_BIT,
+	ETHTOOL_LINK_MODE_50000baseCR_Full_BIT,
+	ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT,
+	ETHTOOL_LINK_MODE_50000baseDR_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseKR2_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseSR2_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseCR2_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseLR2_ER2_FR2_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseDR2_Full_BIT,
+	__ETHTOOL_LINK_MODE_MASK_NBITS,
+};
+
+static const phy_interface_t xpcs_usxgmii_interfaces[] = {
+	PHY_INTERFACE_MODE_USXGMII,
+	PHY_INTERFACE_MODE_MAX,
+};
+
+static const phy_interface_t xpcs_10gkr_interfaces[] = {
+	PHY_INTERFACE_MODE_10GKR,
+	PHY_INTERFACE_MODE_MAX,
+};
+
+static const phy_interface_t xpcs_xlgmii_interfaces[] = {
+	PHY_INTERFACE_MODE_XLGMII,
+	PHY_INTERFACE_MODE_MAX,
+};
+
+static struct xpcs_id {
+	u32 id;
+	u32 mask;
+	const int *supported;
+	const phy_interface_t *interface;
+} xpcs_id_list[] = {
+	{
+		.id = SYNOPSYS_XPCS_USXGMII_ID,
+		.mask = SYNOPSYS_XPCS_MASK,
+		.supported = xpcs_usxgmii_features,
+		.interface = xpcs_usxgmii_interfaces,
+	}, {
+		.id = SYNOPSYS_XPCS_10GKR_ID,
+		.mask = SYNOPSYS_XPCS_MASK,
+		.supported = xpcs_10gkr_features,
+		.interface = xpcs_10gkr_interfaces,
+	}, {
+		.id = SYNOPSYS_XPCS_XLGMII_ID,
+		.mask = SYNOPSYS_XPCS_MASK,
+		.supported = xpcs_xlgmii_features,
+		.interface = xpcs_xlgmii_interfaces,
+	},
+};
+
+static int xpcs_read(struct mdio_xpcs_args *xpcs, int dev, u32 reg)
+{
+	u32 reg_addr = MII_ADDR_C45 | dev << 16 | reg;
+
+	return mdiobus_read(xpcs->bus, xpcs->addr, reg_addr);
+}
+
+static int xpcs_write(struct mdio_xpcs_args *xpcs, int dev, u32 reg, u16 val)
+{
+	u32 reg_addr = MII_ADDR_C45 | dev << 16 | reg;
+
+	return mdiobus_write(xpcs->bus, xpcs->addr, reg_addr, val);
+}
+
+static int xpcs_read_vendor(struct mdio_xpcs_args *xpcs, int dev, u32 reg)
+{
+	return xpcs_read(xpcs, dev, DW_VENDOR | reg);
+}
+
+static int xpcs_write_vendor(struct mdio_xpcs_args *xpcs, int dev, int reg,
+			     u16 val)
+{
+	return xpcs_write(xpcs, dev, DW_VENDOR | reg, val);
+}
+
+static int xpcs_read_vpcs(struct mdio_xpcs_args *xpcs, int reg)
+{
+	return xpcs_read_vendor(xpcs, MDIO_MMD_PCS, reg);
+}
+
+static int xpcs_write_vpcs(struct mdio_xpcs_args *xpcs, int reg, u16 val)
+{
+	return xpcs_write_vendor(xpcs, MDIO_MMD_PCS, reg, val);
+}
+
+static int xpcs_poll_reset(struct mdio_xpcs_args *xpcs, int dev)
+{
+	/* Poll until the reset bit clears (50ms per retry == 0.6 sec) */
+	unsigned int retries = 12;
+	int ret;
+
+	do {
+		msleep(50);
+		ret = xpcs_read(xpcs, dev, MDIO_CTRL1);
+		if (ret < 0)
+			return ret;
+	} while (ret & MDIO_CTRL1_RESET && --retries);
+
+	return (ret & MDIO_CTRL1_RESET) ? -ETIMEDOUT : 0;
+}
+
+static int xpcs_soft_reset(struct mdio_xpcs_args *xpcs, int dev)
+{
+	int ret;
+
+	ret = xpcs_write(xpcs, dev, MDIO_CTRL1, MDIO_CTRL1_RESET);
+	if (ret < 0)
+		return ret;
+
+	return xpcs_poll_reset(xpcs, dev);
+}
+
+#define xpcs_warn(__xpcs, __state, __args...) \
+({ \
+	if ((__state)->link) \
+		dev_warn(&(__xpcs)->bus->dev, ##__args); \
+})
+
+static int xpcs_read_fault(struct mdio_xpcs_args *xpcs,
+			   struct phylink_link_state *state)
+{
+	int ret;
+
+	ret = xpcs_read(xpcs, MDIO_MMD_PCS, MDIO_STAT1);
+	if (ret < 0)
+		return ret;
+
+	if (ret & MDIO_STAT1_FAULT) {
+		xpcs_warn(xpcs, state, "Link fault condition detected!\n");
+		return -EFAULT;
+	}
+
+	ret = xpcs_read(xpcs, MDIO_MMD_PCS, MDIO_STAT2);
+	if (ret < 0)
+		return ret;
+
+	if (ret & MDIO_STAT2_RXFAULT)
+		xpcs_warn(xpcs, state, "Receiver fault detected!\n");
+	if (ret & MDIO_STAT2_TXFAULT)
+		xpcs_warn(xpcs, state, "Transmitter fault detected!\n");
+
+	ret = xpcs_read_vendor(xpcs, MDIO_MMD_PCS, DW_VR_XS_PCS_DIG_STS);
+	if (ret < 0)
+		return ret;
+
+	if (ret & DW_RXFIFO_ERR) {
+		xpcs_warn(xpcs, state, "FIFO fault condition detected!\n");
+		return -EFAULT;
+	}
+
+	ret = xpcs_read(xpcs, MDIO_MMD_PCS, MDIO_PCS_10GBRT_STAT1);
+	if (ret < 0)
+		return ret;
+
+	if (!(ret & MDIO_PCS_10GBRT_STAT1_BLKLK))
+		xpcs_warn(xpcs, state, "Link is not locked!\n");
+
+	ret = xpcs_read(xpcs, MDIO_MMD_PCS, MDIO_PCS_10GBRT_STAT2);
+	if (ret < 0)
+		return ret;
+
+	if (ret & MDIO_PCS_10GBRT_STAT2_ERR) {
+		xpcs_warn(xpcs, state, "Link has errors!\n");
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+static int xpcs_read_link(struct mdio_xpcs_args *xpcs, bool an)
+{
+	bool link = true;
+	int ret;
+
+	ret = xpcs_read(xpcs, MDIO_MMD_PCS, MDIO_STAT1);
+	if (ret < 0)
+		return ret;
+
+	if (!(ret & MDIO_STAT1_LSTATUS))
+		link = false;
+
+	if (an) {
+		ret = xpcs_read(xpcs, MDIO_MMD_AN, MDIO_STAT1);
+		if (ret < 0)
+			return ret;
+
+		if (!(ret & MDIO_STAT1_LSTATUS))
+			link = false;
+	}
+
+	return link;
+}
+
+static int xpcs_get_max_usxgmii_speed(const unsigned long *supported)
+{
+	int max = SPEED_UNKNOWN;
+
+	if (phylink_test(supported, 1000baseKX_Full))
+		max = SPEED_1000;
+	if (phylink_test(supported, 2500baseX_Full))
+		max = SPEED_2500;
+	if (phylink_test(supported, 10000baseKX4_Full))
+		max = SPEED_10000;
+	if (phylink_test(supported, 10000baseKR_Full))
+		max = SPEED_10000;
+
+	return max;
+}
+
+static int xpcs_config_usxgmii(struct mdio_xpcs_args *xpcs, int speed)
+{
+	int ret, speed_sel;
+
+	switch (speed) {
+	case SPEED_10:
+		speed_sel = DW_USXGMII_10;
+		break;
+	case SPEED_100:
+		speed_sel = DW_USXGMII_100;
+		break;
+	case SPEED_1000:
+		speed_sel = DW_USXGMII_1000;
+		break;
+	case SPEED_2500:
+		speed_sel = DW_USXGMII_2500;
+		break;
+	case SPEED_5000:
+		speed_sel = DW_USXGMII_5000;
+		break;
+	case SPEED_10000:
+		speed_sel = DW_USXGMII_10000;
+		break;
+	default:
+		/* Nothing to do here */
+		return -EINVAL;
+	}
+
+	ret = xpcs_read_vpcs(xpcs, MDIO_CTRL1);
+	if (ret < 0)
+		return ret;
+
+	ret = xpcs_write_vpcs(xpcs, MDIO_CTRL1, ret | DW_USXGMII_EN);
+	if (ret < 0)
+		return ret;
+
+	ret = xpcs_read(xpcs, MDIO_MMD_VEND2, MDIO_CTRL1);
+	if (ret < 0)
+		return ret;
+
+	ret &= ~DW_USXGMII_SS_MASK;
+	ret |= speed_sel | DW_USXGMII_FULL;
+
+	ret = xpcs_write(xpcs, MDIO_MMD_VEND2, MDIO_CTRL1, ret);
+	if (ret < 0)
+		return ret;
+
+	ret = xpcs_read_vpcs(xpcs, MDIO_CTRL1);
+	if (ret < 0)
+		return ret;
+
+	return xpcs_write_vpcs(xpcs, MDIO_CTRL1, ret | DW_USXGMII_RST);
+}
+
+static int xpcs_config_aneg_c73(struct mdio_xpcs_args *xpcs)
+{
+	int ret, adv;
+
+	/* By default, in USXGMII mode XPCS operates at 10G baud and
+	 * replicates data to achieve lower speeds. Hereby, in this
+	 * default configuration we need to advertise all supported
+	 * modes and not only the ones we want to use.
+	 */
+
+	/* SR_AN_ADV3 */
+	adv = 0;
+	if (phylink_test(xpcs->supported, 2500baseX_Full))
+		adv |= DW_C73_2500KX;
+
+	/* TODO: 5000baseKR */
+
+	ret = xpcs_write(xpcs, MDIO_MMD_AN, DW_SR_AN_ADV3, adv);
+	if (ret < 0)
+		return ret;
+
+	/* SR_AN_ADV2 */
+	adv = 0;
+	if (phylink_test(xpcs->supported, 1000baseKX_Full))
+		adv |= DW_C73_1000KX;
+	if (phylink_test(xpcs->supported, 10000baseKX4_Full))
+		adv |= DW_C73_10000KX4;
+	if (phylink_test(xpcs->supported, 10000baseKR_Full))
+		adv |= DW_C73_10000KR;
+
+	ret = xpcs_write(xpcs, MDIO_MMD_AN, DW_SR_AN_ADV2, adv);
+	if (ret < 0)
+		return ret;
+
+	/* SR_AN_ADV1 */
+	adv = DW_C73_AN_ADV_SF;
+	if (phylink_test(xpcs->supported, Pause))
+		adv |= DW_C73_PAUSE;
+	if (phylink_test(xpcs->supported, Asym_Pause))
+		adv |= DW_C73_ASYM_PAUSE;
+
+	return xpcs_write(xpcs, MDIO_MMD_AN, DW_SR_AN_ADV1, adv);
+}
+
+static int xpcs_config_aneg(struct mdio_xpcs_args *xpcs)
+{
+	int ret;
+
+	ret = xpcs_config_aneg_c73(xpcs);
+	if (ret < 0)
+		return ret;
+
+	ret = xpcs_read(xpcs, MDIO_MMD_AN, MDIO_CTRL1);
+	if (ret < 0)
+		return ret;
+
+	ret |= MDIO_AN_CTRL1_ENABLE | MDIO_AN_CTRL1_RESTART;
+
+	return xpcs_write(xpcs, MDIO_MMD_AN, MDIO_CTRL1, ret);
+}
+
+static int xpcs_aneg_done(struct mdio_xpcs_args *xpcs,
+			  struct phylink_link_state *state)
+{
+	int ret;
+
+	ret = xpcs_read(xpcs, MDIO_MMD_AN, MDIO_STAT1);
+	if (ret < 0)
+		return ret;
+
+	if (ret & MDIO_AN_STAT1_COMPLETE) {
+		ret = xpcs_read(xpcs, MDIO_MMD_AN, DW_SR_AN_LP_ABL1);
+		if (ret < 0)
+			return ret;
+
+		/* Check if Aneg outcome is valid */
+		if (!(ret & DW_C73_AN_ADV_SF)) {
+			xpcs_config_aneg(xpcs);
+			return 0;
+		}
+
+		return 1;
+	}
+
+	return 0;
+}
+
+static int xpcs_read_lpa(struct mdio_xpcs_args *xpcs,
+			 struct phylink_link_state *state)
+{
+	int ret;
+
+	ret = xpcs_read(xpcs, MDIO_MMD_AN, MDIO_STAT1);
+	if (ret < 0)
+		return ret;
+
+	if (!(ret & MDIO_AN_STAT1_LPABLE)) {
+		phylink_clear(state->lp_advertising, Autoneg);
+		return 0;
+	}
+
+	phylink_set(state->lp_advertising, Autoneg);
+
+	/* Clause 73 outcome */
+	ret = xpcs_read(xpcs, MDIO_MMD_AN, DW_SR_AN_LP_ABL3);
+	if (ret < 0)
+		return ret;
+
+	if (ret & DW_C73_2500KX)
+		phylink_set(state->lp_advertising, 2500baseX_Full);
+
+	ret = xpcs_read(xpcs, MDIO_MMD_AN, DW_SR_AN_LP_ABL2);
+	if (ret < 0)
+		return ret;
+
+	if (ret & DW_C73_1000KX)
+		phylink_set(state->lp_advertising, 1000baseKX_Full);
+	if (ret & DW_C73_10000KX4)
+		phylink_set(state->lp_advertising, 10000baseKX4_Full);
+	if (ret & DW_C73_10000KR)
+		phylink_set(state->lp_advertising, 10000baseKR_Full);
+
+	ret = xpcs_read(xpcs, MDIO_MMD_AN, DW_SR_AN_LP_ABL1);
+	if (ret < 0)
+		return ret;
+
+	if (ret & DW_C73_PAUSE)
+		phylink_set(state->lp_advertising, Pause);
+	if (ret & DW_C73_ASYM_PAUSE)
+		phylink_set(state->lp_advertising, Asym_Pause);
+
+	linkmode_and(state->lp_advertising, state->lp_advertising,
+		     state->advertising);
+	return 0;
+}
+
+static void xpcs_resolve_lpa(struct mdio_xpcs_args *xpcs,
+			     struct phylink_link_state *state)
+{
+	int max_speed = xpcs_get_max_usxgmii_speed(state->lp_advertising);
+
+	state->pause = MLO_PAUSE_TX | MLO_PAUSE_RX;
+	state->speed = max_speed;
+	state->duplex = DUPLEX_FULL;
+}
+
+static int xpcs_get_max_xlgmii_speed(struct mdio_xpcs_args *xpcs,
+				     struct phylink_link_state *state)
+{
+	unsigned long *adv = state->advertising;
+	int speed = SPEED_UNKNOWN;
+	int bit;
+
+	for_each_set_bit(bit, adv, __ETHTOOL_LINK_MODE_MASK_NBITS) {
+		int new_speed = SPEED_UNKNOWN;
+
+		switch (bit) {
+		case ETHTOOL_LINK_MODE_25000baseCR_Full_BIT:
+		case ETHTOOL_LINK_MODE_25000baseKR_Full_BIT:
+		case ETHTOOL_LINK_MODE_25000baseSR_Full_BIT:
+			new_speed = SPEED_25000;
+			break;
+		case ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT:
+		case ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT:
+		case ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT:
+		case ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT:
+			new_speed = SPEED_40000;
+			break;
+		case ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT:
+		case ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT:
+		case ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT:
+		case ETHTOOL_LINK_MODE_50000baseKR_Full_BIT:
+		case ETHTOOL_LINK_MODE_50000baseSR_Full_BIT:
+		case ETHTOOL_LINK_MODE_50000baseCR_Full_BIT:
+		case ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT:
+		case ETHTOOL_LINK_MODE_50000baseDR_Full_BIT:
+			new_speed = SPEED_50000;
+			break;
+		case ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT:
+		case ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT:
+		case ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT:
+		case ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT:
+		case ETHTOOL_LINK_MODE_100000baseKR2_Full_BIT:
+		case ETHTOOL_LINK_MODE_100000baseSR2_Full_BIT:
+		case ETHTOOL_LINK_MODE_100000baseCR2_Full_BIT:
+		case ETHTOOL_LINK_MODE_100000baseLR2_ER2_FR2_Full_BIT:
+		case ETHTOOL_LINK_MODE_100000baseDR2_Full_BIT:
+			new_speed = SPEED_100000;
+			break;
+		default:
+			continue;
+		}
+
+		if (new_speed > speed)
+			speed = new_speed;
+	}
+
+	return speed;
+}
+
+static void xpcs_resolve_pma(struct mdio_xpcs_args *xpcs,
+			     struct phylink_link_state *state)
+{
+	state->pause = MLO_PAUSE_TX | MLO_PAUSE_RX;
+	state->duplex = DUPLEX_FULL;
+
+	switch (state->interface) {
+	case PHY_INTERFACE_MODE_10GKR:
+		state->speed = SPEED_10000;
+		break;
+	case PHY_INTERFACE_MODE_XLGMII:
+		state->speed = xpcs_get_max_xlgmii_speed(xpcs, state);
+		break;
+	default:
+		state->speed = SPEED_UNKNOWN;
+		break;
+	}
+}
+
+static int xpcs_validate(struct mdio_xpcs_args *xpcs,
+			 unsigned long *supported,
+			 struct phylink_link_state *state)
+{
+	linkmode_and(supported, supported, xpcs->supported);
+	linkmode_and(state->advertising, state->advertising, xpcs->supported);
+	return 0;
+}
+
+static int xpcs_config(struct mdio_xpcs_args *xpcs,
+		       const struct phylink_link_state *state)
+{
+	int ret;
+
+	if (state->an_enabled) {
+		ret = xpcs_config_aneg(xpcs);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int xpcs_get_state(struct mdio_xpcs_args *xpcs,
+			  struct phylink_link_state *state)
+{
+	int ret;
+
+	/* Link needs to be read first ... */
+	state->link = xpcs_read_link(xpcs, state->an_enabled) > 0 ? 1 : 0;
+
+	/* ... and then we check the faults. */
+	ret = xpcs_read_fault(xpcs, state);
+	if (ret) {
+		ret = xpcs_soft_reset(xpcs, MDIO_MMD_PCS);
+		if (ret)
+			return ret;
+
+		state->link = 0;
+
+		return xpcs_config(xpcs, state);
+	}
+
+	if (state->an_enabled && xpcs_aneg_done(xpcs, state)) {
+		state->an_complete = true;
+		xpcs_read_lpa(xpcs, state);
+		xpcs_resolve_lpa(xpcs, state);
+	} else if (state->an_enabled) {
+		state->link = 0;
+	} else if (state->link) {
+		xpcs_resolve_pma(xpcs, state);
+	}
+
+	return 0;
+}
+
+static int xpcs_link_up(struct mdio_xpcs_args *xpcs, int speed,
+			phy_interface_t interface)
+{
+	if (interface == PHY_INTERFACE_MODE_USXGMII)
+		return xpcs_config_usxgmii(xpcs, speed);
+
+	return 0;
+}
+
+static u32 xpcs_get_id(struct mdio_xpcs_args *xpcs)
+{
+	int ret;
+	u32 id;
+
+	ret = xpcs_read(xpcs, MDIO_MMD_PCS, MII_PHYSID1);
+	if (ret < 0)
+		return 0xffffffff;
+
+	id = ret << 16;
+
+	ret = xpcs_read(xpcs, MDIO_MMD_PCS, MII_PHYSID2);
+	if (ret < 0)
+		return 0xffffffff;
+
+	return id | ret;
+}
+
+static bool xpcs_check_features(struct mdio_xpcs_args *xpcs,
+				struct xpcs_id *match,
+				phy_interface_t interface)
+{
+	int i;
+
+	for (i = 0; match->interface[i] != PHY_INTERFACE_MODE_MAX; i++) {
+		if (match->interface[i] == interface)
+			break;
+	}
+
+	if (match->interface[i] == PHY_INTERFACE_MODE_MAX)
+		return false;
+
+	for (i = 0; match->supported[i] != __ETHTOOL_LINK_MODE_MASK_NBITS; i++)
+		set_bit(match->supported[i], xpcs->supported);
+
+	return true;
+}
+
+static int xpcs_probe(struct mdio_xpcs_args *xpcs, phy_interface_t interface)
+{
+	u32 xpcs_id = xpcs_get_id(xpcs);
+	struct xpcs_id *match = NULL;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(xpcs_id_list); i++) {
+		struct xpcs_id *entry = &xpcs_id_list[i];
+
+		if ((xpcs_id & entry->mask) == entry->id) {
+			match = entry;
+
+			if (xpcs_check_features(xpcs, match, interface))
+				return xpcs_soft_reset(xpcs, MDIO_MMD_PCS);
+		}
+	}
+
+	return -ENODEV;
+}
+
+static struct mdio_xpcs_ops xpcs_ops = {
+	.validate = xpcs_validate,
+	.config = xpcs_config,
+	.get_state = xpcs_get_state,
+	.link_up = xpcs_link_up,
+	.probe = xpcs_probe,
+};
+
+struct mdio_xpcs_ops *mdio_xpcs_get_ops(void)
+{
+	return &xpcs_ops;
+}
+EXPORT_SYMBOL_GPL(mdio_xpcs_get_ops);
+
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 726e4b240e7e..c69cc806f064 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -234,12 +234,6 @@ config MDIO_XGENE
 	  This module provides a driver for the MDIO busses found in the
 	  APM X-Gene SoC's.
 
-config MDIO_XPCS
-	tristate "Synopsys DesignWare XPCS controller"
-	help
-	  This module provides helper functions for Synopsys DesignWare XPCS
-	  controllers.
-
 endif
 endif
 
diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
index d84bab489a53..7cd8a0d1c0d0 100644
--- a/drivers/net/phy/Makefile
+++ b/drivers/net/phy/Makefile
@@ -47,7 +47,6 @@ obj-$(CONFIG_MDIO_OCTEON)	+= mdio-octeon.o
 obj-$(CONFIG_MDIO_SUN4I)	+= mdio-sun4i.o
 obj-$(CONFIG_MDIO_THUNDER)	+= mdio-thunder.o
 obj-$(CONFIG_MDIO_XGENE)	+= mdio-xgene.o
-obj-$(CONFIG_MDIO_XPCS)		+= mdio-xpcs.o
 
 obj-$(CONFIG_NETWORK_PHY_TIMESTAMPING) += mii_timestamper.o
 
diff --git a/drivers/net/phy/mdio-xpcs.c b/drivers/net/phy/mdio-xpcs.c
deleted file mode 100644
index 0d66a8ba7eb6..000000000000
--- a/drivers/net/phy/mdio-xpcs.c
+++ /dev/null
@@ -1,716 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (c) 2020 Synopsys, Inc. and/or its affiliates.
- * Synopsys DesignWare XPCS helpers
- *
- * Author: Jose Abreu <Jose.Abreu@synopsys.com>
- */
-
-#include <linux/delay.h>
-#include <linux/mdio.h>
-#include <linux/mdio-xpcs.h>
-#include <linux/phylink.h>
-#include <linux/workqueue.h>
-
-#define SYNOPSYS_XPCS_USXGMII_ID	0x7996ced0
-#define SYNOPSYS_XPCS_10GKR_ID		0x7996ced0
-#define SYNOPSYS_XPCS_XLGMII_ID		0x7996ced0
-#define SYNOPSYS_XPCS_MASK		0xffffffff
-
-/* Vendor regs access */
-#define DW_VENDOR			BIT(15)
-
-/* VR_XS_PCS */
-#define DW_USXGMII_RST			BIT(10)
-#define DW_USXGMII_EN			BIT(9)
-#define DW_VR_XS_PCS_DIG_STS		0x0010
-#define DW_RXFIFO_ERR			GENMASK(6, 5)
-
-/* SR_MII */
-#define DW_USXGMII_FULL			BIT(8)
-#define DW_USXGMII_SS_MASK		(BIT(13) | BIT(6) | BIT(5))
-#define DW_USXGMII_10000		(BIT(13) | BIT(6))
-#define DW_USXGMII_5000			(BIT(13) | BIT(5))
-#define DW_USXGMII_2500			(BIT(5))
-#define DW_USXGMII_1000			(BIT(6))
-#define DW_USXGMII_100			(BIT(13))
-#define DW_USXGMII_10			(0)
-
-/* SR_AN */
-#define DW_SR_AN_ADV1			0x10
-#define DW_SR_AN_ADV2			0x11
-#define DW_SR_AN_ADV3			0x12
-#define DW_SR_AN_LP_ABL1		0x13
-#define DW_SR_AN_LP_ABL2		0x14
-#define DW_SR_AN_LP_ABL3		0x15
-
-/* Clause 73 Defines */
-/* AN_LP_ABL1 */
-#define DW_C73_PAUSE			BIT(10)
-#define DW_C73_ASYM_PAUSE		BIT(11)
-#define DW_C73_AN_ADV_SF		0x1
-/* AN_LP_ABL2 */
-#define DW_C73_1000KX			BIT(5)
-#define DW_C73_10000KX4			BIT(6)
-#define DW_C73_10000KR			BIT(7)
-/* AN_LP_ABL3 */
-#define DW_C73_2500KX			BIT(0)
-#define DW_C73_5000KR			BIT(1)
-
-static const int xpcs_usxgmii_features[] = {
-	ETHTOOL_LINK_MODE_Pause_BIT,
-	ETHTOOL_LINK_MODE_Asym_Pause_BIT,
-	ETHTOOL_LINK_MODE_Autoneg_BIT,
-	ETHTOOL_LINK_MODE_1000baseKX_Full_BIT,
-	ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT,
-	ETHTOOL_LINK_MODE_10000baseKR_Full_BIT,
-	ETHTOOL_LINK_MODE_2500baseX_Full_BIT,
-	__ETHTOOL_LINK_MODE_MASK_NBITS,
-};
-
-static const int xpcs_10gkr_features[] = {
-	ETHTOOL_LINK_MODE_Pause_BIT,
-	ETHTOOL_LINK_MODE_Asym_Pause_BIT,
-	ETHTOOL_LINK_MODE_10000baseKR_Full_BIT,
-	__ETHTOOL_LINK_MODE_MASK_NBITS,
-};
-
-static const int xpcs_xlgmii_features[] = {
-	ETHTOOL_LINK_MODE_Pause_BIT,
-	ETHTOOL_LINK_MODE_Asym_Pause_BIT,
-	ETHTOOL_LINK_MODE_25000baseCR_Full_BIT,
-	ETHTOOL_LINK_MODE_25000baseKR_Full_BIT,
-	ETHTOOL_LINK_MODE_25000baseSR_Full_BIT,
-	ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT,
-	ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT,
-	ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT,
-	ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT,
-	ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT,
-	ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT,
-	ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT,
-	ETHTOOL_LINK_MODE_50000baseKR_Full_BIT,
-	ETHTOOL_LINK_MODE_50000baseSR_Full_BIT,
-	ETHTOOL_LINK_MODE_50000baseCR_Full_BIT,
-	ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT,
-	ETHTOOL_LINK_MODE_50000baseDR_Full_BIT,
-	ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT,
-	ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT,
-	ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT,
-	ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT,
-	ETHTOOL_LINK_MODE_100000baseKR2_Full_BIT,
-	ETHTOOL_LINK_MODE_100000baseSR2_Full_BIT,
-	ETHTOOL_LINK_MODE_100000baseCR2_Full_BIT,
-	ETHTOOL_LINK_MODE_100000baseLR2_ER2_FR2_Full_BIT,
-	ETHTOOL_LINK_MODE_100000baseDR2_Full_BIT,
-	__ETHTOOL_LINK_MODE_MASK_NBITS,
-};
-
-static const phy_interface_t xpcs_usxgmii_interfaces[] = {
-	PHY_INTERFACE_MODE_USXGMII,
-	PHY_INTERFACE_MODE_MAX,
-};
-
-static const phy_interface_t xpcs_10gkr_interfaces[] = {
-	PHY_INTERFACE_MODE_10GKR,
-	PHY_INTERFACE_MODE_MAX,
-};
-
-static const phy_interface_t xpcs_xlgmii_interfaces[] = {
-	PHY_INTERFACE_MODE_XLGMII,
-	PHY_INTERFACE_MODE_MAX,
-};
-
-static struct xpcs_id {
-	u32 id;
-	u32 mask;
-	const int *supported;
-	const phy_interface_t *interface;
-} xpcs_id_list[] = {
-	{
-		.id = SYNOPSYS_XPCS_USXGMII_ID,
-		.mask = SYNOPSYS_XPCS_MASK,
-		.supported = xpcs_usxgmii_features,
-		.interface = xpcs_usxgmii_interfaces,
-	}, {
-		.id = SYNOPSYS_XPCS_10GKR_ID,
-		.mask = SYNOPSYS_XPCS_MASK,
-		.supported = xpcs_10gkr_features,
-		.interface = xpcs_10gkr_interfaces,
-	}, {
-		.id = SYNOPSYS_XPCS_XLGMII_ID,
-		.mask = SYNOPSYS_XPCS_MASK,
-		.supported = xpcs_xlgmii_features,
-		.interface = xpcs_xlgmii_interfaces,
-	},
-};
-
-static int xpcs_read(struct mdio_xpcs_args *xpcs, int dev, u32 reg)
-{
-	u32 reg_addr = MII_ADDR_C45 | dev << 16 | reg;
-
-	return mdiobus_read(xpcs->bus, xpcs->addr, reg_addr);
-}
-
-static int xpcs_write(struct mdio_xpcs_args *xpcs, int dev, u32 reg, u16 val)
-{
-	u32 reg_addr = MII_ADDR_C45 | dev << 16 | reg;
-
-	return mdiobus_write(xpcs->bus, xpcs->addr, reg_addr, val);
-}
-
-static int xpcs_read_vendor(struct mdio_xpcs_args *xpcs, int dev, u32 reg)
-{
-	return xpcs_read(xpcs, dev, DW_VENDOR | reg);
-}
-
-static int xpcs_write_vendor(struct mdio_xpcs_args *xpcs, int dev, int reg,
-			     u16 val)
-{
-	return xpcs_write(xpcs, dev, DW_VENDOR | reg, val);
-}
-
-static int xpcs_read_vpcs(struct mdio_xpcs_args *xpcs, int reg)
-{
-	return xpcs_read_vendor(xpcs, MDIO_MMD_PCS, reg);
-}
-
-static int xpcs_write_vpcs(struct mdio_xpcs_args *xpcs, int reg, u16 val)
-{
-	return xpcs_write_vendor(xpcs, MDIO_MMD_PCS, reg, val);
-}
-
-static int xpcs_poll_reset(struct mdio_xpcs_args *xpcs, int dev)
-{
-	/* Poll until the reset bit clears (50ms per retry == 0.6 sec) */
-	unsigned int retries = 12;
-	int ret;
-
-	do {
-		msleep(50);
-		ret = xpcs_read(xpcs, dev, MDIO_CTRL1);
-		if (ret < 0)
-			return ret;
-	} while (ret & MDIO_CTRL1_RESET && --retries);
-
-	return (ret & MDIO_CTRL1_RESET) ? -ETIMEDOUT : 0;
-}
-
-static int xpcs_soft_reset(struct mdio_xpcs_args *xpcs, int dev)
-{
-	int ret;
-
-	ret = xpcs_write(xpcs, dev, MDIO_CTRL1, MDIO_CTRL1_RESET);
-	if (ret < 0)
-		return ret;
-
-	return xpcs_poll_reset(xpcs, dev);
-}
-
-#define xpcs_warn(__xpcs, __state, __args...) \
-({ \
-	if ((__state)->link) \
-		dev_warn(&(__xpcs)->bus->dev, ##__args); \
-})
-
-static int xpcs_read_fault(struct mdio_xpcs_args *xpcs,
-			   struct phylink_link_state *state)
-{
-	int ret;
-
-	ret = xpcs_read(xpcs, MDIO_MMD_PCS, MDIO_STAT1);
-	if (ret < 0)
-		return ret;
-
-	if (ret & MDIO_STAT1_FAULT) {
-		xpcs_warn(xpcs, state, "Link fault condition detected!\n");
-		return -EFAULT;
-	}
-
-	ret = xpcs_read(xpcs, MDIO_MMD_PCS, MDIO_STAT2);
-	if (ret < 0)
-		return ret;
-
-	if (ret & MDIO_STAT2_RXFAULT)
-		xpcs_warn(xpcs, state, "Receiver fault detected!\n");
-	if (ret & MDIO_STAT2_TXFAULT)
-		xpcs_warn(xpcs, state, "Transmitter fault detected!\n");
-
-	ret = xpcs_read_vendor(xpcs, MDIO_MMD_PCS, DW_VR_XS_PCS_DIG_STS);
-	if (ret < 0)
-		return ret;
-
-	if (ret & DW_RXFIFO_ERR) {
-		xpcs_warn(xpcs, state, "FIFO fault condition detected!\n");
-		return -EFAULT;
-	}
-
-	ret = xpcs_read(xpcs, MDIO_MMD_PCS, MDIO_PCS_10GBRT_STAT1);
-	if (ret < 0)
-		return ret;
-
-	if (!(ret & MDIO_PCS_10GBRT_STAT1_BLKLK))
-		xpcs_warn(xpcs, state, "Link is not locked!\n");
-
-	ret = xpcs_read(xpcs, MDIO_MMD_PCS, MDIO_PCS_10GBRT_STAT2);
-	if (ret < 0)
-		return ret;
-
-	if (ret & MDIO_PCS_10GBRT_STAT2_ERR) {
-		xpcs_warn(xpcs, state, "Link has errors!\n");
-		return -EFAULT;
-	}
-
-	return 0;
-}
-
-static int xpcs_read_link(struct mdio_xpcs_args *xpcs, bool an)
-{
-	bool link = true;
-	int ret;
-
-	ret = xpcs_read(xpcs, MDIO_MMD_PCS, MDIO_STAT1);
-	if (ret < 0)
-		return ret;
-
-	if (!(ret & MDIO_STAT1_LSTATUS))
-		link = false;
-
-	if (an) {
-		ret = xpcs_read(xpcs, MDIO_MMD_AN, MDIO_STAT1);
-		if (ret < 0)
-			return ret;
-
-		if (!(ret & MDIO_STAT1_LSTATUS))
-			link = false;
-	}
-
-	return link;
-}
-
-static int xpcs_get_max_usxgmii_speed(const unsigned long *supported)
-{
-	int max = SPEED_UNKNOWN;
-
-	if (phylink_test(supported, 1000baseKX_Full))
-		max = SPEED_1000;
-	if (phylink_test(supported, 2500baseX_Full))
-		max = SPEED_2500;
-	if (phylink_test(supported, 10000baseKX4_Full))
-		max = SPEED_10000;
-	if (phylink_test(supported, 10000baseKR_Full))
-		max = SPEED_10000;
-
-	return max;
-}
-
-static int xpcs_config_usxgmii(struct mdio_xpcs_args *xpcs, int speed)
-{
-	int ret, speed_sel;
-
-	switch (speed) {
-	case SPEED_10:
-		speed_sel = DW_USXGMII_10;
-		break;
-	case SPEED_100:
-		speed_sel = DW_USXGMII_100;
-		break;
-	case SPEED_1000:
-		speed_sel = DW_USXGMII_1000;
-		break;
-	case SPEED_2500:
-		speed_sel = DW_USXGMII_2500;
-		break;
-	case SPEED_5000:
-		speed_sel = DW_USXGMII_5000;
-		break;
-	case SPEED_10000:
-		speed_sel = DW_USXGMII_10000;
-		break;
-	default:
-		/* Nothing to do here */
-		return -EINVAL;
-	}
-
-	ret = xpcs_read_vpcs(xpcs, MDIO_CTRL1);
-	if (ret < 0)
-		return ret;
-
-	ret = xpcs_write_vpcs(xpcs, MDIO_CTRL1, ret | DW_USXGMII_EN);
-	if (ret < 0)
-		return ret;
-
-	ret = xpcs_read(xpcs, MDIO_MMD_VEND2, MDIO_CTRL1);
-	if (ret < 0)
-		return ret;
-
-	ret &= ~DW_USXGMII_SS_MASK;
-	ret |= speed_sel | DW_USXGMII_FULL;
-
-	ret = xpcs_write(xpcs, MDIO_MMD_VEND2, MDIO_CTRL1, ret);
-	if (ret < 0)
-		return ret;
-
-	ret = xpcs_read_vpcs(xpcs, MDIO_CTRL1);
-	if (ret < 0)
-		return ret;
-
-	return xpcs_write_vpcs(xpcs, MDIO_CTRL1, ret | DW_USXGMII_RST);
-}
-
-static int xpcs_config_aneg_c73(struct mdio_xpcs_args *xpcs)
-{
-	int ret, adv;
-
-	/* By default, in USXGMII mode XPCS operates at 10G baud and
-	 * replicates data to achieve lower speeds. Hereby, in this
-	 * default configuration we need to advertise all supported
-	 * modes and not only the ones we want to use.
-	 */
-
-	/* SR_AN_ADV3 */
-	adv = 0;
-	if (phylink_test(xpcs->supported, 2500baseX_Full))
-		adv |= DW_C73_2500KX;
-
-	/* TODO: 5000baseKR */
-
-	ret = xpcs_write(xpcs, MDIO_MMD_AN, DW_SR_AN_ADV3, adv);
-	if (ret < 0)
-		return ret;
-
-	/* SR_AN_ADV2 */
-	adv = 0;
-	if (phylink_test(xpcs->supported, 1000baseKX_Full))
-		adv |= DW_C73_1000KX;
-	if (phylink_test(xpcs->supported, 10000baseKX4_Full))
-		adv |= DW_C73_10000KX4;
-	if (phylink_test(xpcs->supported, 10000baseKR_Full))
-		adv |= DW_C73_10000KR;
-
-	ret = xpcs_write(xpcs, MDIO_MMD_AN, DW_SR_AN_ADV2, adv);
-	if (ret < 0)
-		return ret;
-
-	/* SR_AN_ADV1 */
-	adv = DW_C73_AN_ADV_SF;
-	if (phylink_test(xpcs->supported, Pause))
-		adv |= DW_C73_PAUSE;
-	if (phylink_test(xpcs->supported, Asym_Pause))
-		adv |= DW_C73_ASYM_PAUSE;
-
-	return xpcs_write(xpcs, MDIO_MMD_AN, DW_SR_AN_ADV1, adv);
-}
-
-static int xpcs_config_aneg(struct mdio_xpcs_args *xpcs)
-{
-	int ret;
-
-	ret = xpcs_config_aneg_c73(xpcs);
-	if (ret < 0)
-		return ret;
-
-	ret = xpcs_read(xpcs, MDIO_MMD_AN, MDIO_CTRL1);
-	if (ret < 0)
-		return ret;
-
-	ret |= MDIO_AN_CTRL1_ENABLE | MDIO_AN_CTRL1_RESTART;
-
-	return xpcs_write(xpcs, MDIO_MMD_AN, MDIO_CTRL1, ret);
-}
-
-static int xpcs_aneg_done(struct mdio_xpcs_args *xpcs,
-			  struct phylink_link_state *state)
-{
-	int ret;
-
-	ret = xpcs_read(xpcs, MDIO_MMD_AN, MDIO_STAT1);
-	if (ret < 0)
-		return ret;
-
-	if (ret & MDIO_AN_STAT1_COMPLETE) {
-		ret = xpcs_read(xpcs, MDIO_MMD_AN, DW_SR_AN_LP_ABL1);
-		if (ret < 0)
-			return ret;
-
-		/* Check if Aneg outcome is valid */
-		if (!(ret & DW_C73_AN_ADV_SF)) {
-			xpcs_config_aneg(xpcs);
-			return 0;
-		}
-
-		return 1;
-	}
-
-	return 0;
-}
-
-static int xpcs_read_lpa(struct mdio_xpcs_args *xpcs,
-			 struct phylink_link_state *state)
-{
-	int ret;
-
-	ret = xpcs_read(xpcs, MDIO_MMD_AN, MDIO_STAT1);
-	if (ret < 0)
-		return ret;
-
-	if (!(ret & MDIO_AN_STAT1_LPABLE)) {
-		phylink_clear(state->lp_advertising, Autoneg);
-		return 0;
-	}
-
-	phylink_set(state->lp_advertising, Autoneg);
-
-	/* Clause 73 outcome */
-	ret = xpcs_read(xpcs, MDIO_MMD_AN, DW_SR_AN_LP_ABL3);
-	if (ret < 0)
-		return ret;
-
-	if (ret & DW_C73_2500KX)
-		phylink_set(state->lp_advertising, 2500baseX_Full);
-
-	ret = xpcs_read(xpcs, MDIO_MMD_AN, DW_SR_AN_LP_ABL2);
-	if (ret < 0)
-		return ret;
-
-	if (ret & DW_C73_1000KX)
-		phylink_set(state->lp_advertising, 1000baseKX_Full);
-	if (ret & DW_C73_10000KX4)
-		phylink_set(state->lp_advertising, 10000baseKX4_Full);
-	if (ret & DW_C73_10000KR)
-		phylink_set(state->lp_advertising, 10000baseKR_Full);
-
-	ret = xpcs_read(xpcs, MDIO_MMD_AN, DW_SR_AN_LP_ABL1);
-	if (ret < 0)
-		return ret;
-
-	if (ret & DW_C73_PAUSE)
-		phylink_set(state->lp_advertising, Pause);
-	if (ret & DW_C73_ASYM_PAUSE)
-		phylink_set(state->lp_advertising, Asym_Pause);
-
-	linkmode_and(state->lp_advertising, state->lp_advertising,
-		     state->advertising);
-	return 0;
-}
-
-static void xpcs_resolve_lpa(struct mdio_xpcs_args *xpcs,
-			     struct phylink_link_state *state)
-{
-	int max_speed = xpcs_get_max_usxgmii_speed(state->lp_advertising);
-
-	state->pause = MLO_PAUSE_TX | MLO_PAUSE_RX;
-	state->speed = max_speed;
-	state->duplex = DUPLEX_FULL;
-}
-
-static int xpcs_get_max_xlgmii_speed(struct mdio_xpcs_args *xpcs,
-				     struct phylink_link_state *state)
-{
-	unsigned long *adv = state->advertising;
-	int speed = SPEED_UNKNOWN;
-	int bit;
-
-	for_each_set_bit(bit, adv, __ETHTOOL_LINK_MODE_MASK_NBITS) {
-		int new_speed = SPEED_UNKNOWN;
-
-		switch (bit) {
-		case ETHTOOL_LINK_MODE_25000baseCR_Full_BIT:
-		case ETHTOOL_LINK_MODE_25000baseKR_Full_BIT:
-		case ETHTOOL_LINK_MODE_25000baseSR_Full_BIT:
-			new_speed = SPEED_25000;
-			break;
-		case ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT:
-		case ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT:
-		case ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT:
-		case ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT:
-			new_speed = SPEED_40000;
-			break;
-		case ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT:
-		case ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT:
-		case ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT:
-		case ETHTOOL_LINK_MODE_50000baseKR_Full_BIT:
-		case ETHTOOL_LINK_MODE_50000baseSR_Full_BIT:
-		case ETHTOOL_LINK_MODE_50000baseCR_Full_BIT:
-		case ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT:
-		case ETHTOOL_LINK_MODE_50000baseDR_Full_BIT:
-			new_speed = SPEED_50000;
-			break;
-		case ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT:
-		case ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT:
-		case ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT:
-		case ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT:
-		case ETHTOOL_LINK_MODE_100000baseKR2_Full_BIT:
-		case ETHTOOL_LINK_MODE_100000baseSR2_Full_BIT:
-		case ETHTOOL_LINK_MODE_100000baseCR2_Full_BIT:
-		case ETHTOOL_LINK_MODE_100000baseLR2_ER2_FR2_Full_BIT:
-		case ETHTOOL_LINK_MODE_100000baseDR2_Full_BIT:
-			new_speed = SPEED_100000;
-			break;
-		default:
-			continue;
-		}
-
-		if (new_speed > speed)
-			speed = new_speed;
-	}
-
-	return speed;
-}
-
-static void xpcs_resolve_pma(struct mdio_xpcs_args *xpcs,
-			     struct phylink_link_state *state)
-{
-	state->pause = MLO_PAUSE_TX | MLO_PAUSE_RX;
-	state->duplex = DUPLEX_FULL;
-
-	switch (state->interface) {
-	case PHY_INTERFACE_MODE_10GKR:
-		state->speed = SPEED_10000;
-		break;
-	case PHY_INTERFACE_MODE_XLGMII:
-		state->speed = xpcs_get_max_xlgmii_speed(xpcs, state);
-		break;
-	default:
-		state->speed = SPEED_UNKNOWN;
-		break;
-	}
-}
-
-static int xpcs_validate(struct mdio_xpcs_args *xpcs,
-			 unsigned long *supported,
-			 struct phylink_link_state *state)
-{
-	linkmode_and(supported, supported, xpcs->supported);
-	linkmode_and(state->advertising, state->advertising, xpcs->supported);
-	return 0;
-}
-
-static int xpcs_config(struct mdio_xpcs_args *xpcs,
-		       const struct phylink_link_state *state)
-{
-	int ret;
-
-	if (state->an_enabled) {
-		ret = xpcs_config_aneg(xpcs);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-
-static int xpcs_get_state(struct mdio_xpcs_args *xpcs,
-			  struct phylink_link_state *state)
-{
-	int ret;
-
-	/* Link needs to be read first ... */
-	state->link = xpcs_read_link(xpcs, state->an_enabled) > 0 ? 1 : 0;
-
-	/* ... and then we check the faults. */
-	ret = xpcs_read_fault(xpcs, state);
-	if (ret) {
-		ret = xpcs_soft_reset(xpcs, MDIO_MMD_PCS);
-		if (ret)
-			return ret;
-
-		state->link = 0;
-
-		return xpcs_config(xpcs, state);
-	}
-
-	if (state->an_enabled && xpcs_aneg_done(xpcs, state)) {
-		state->an_complete = true;
-		xpcs_read_lpa(xpcs, state);
-		xpcs_resolve_lpa(xpcs, state);
-	} else if (state->an_enabled) {
-		state->link = 0;
-	} else if (state->link) {
-		xpcs_resolve_pma(xpcs, state);
-	}
-
-	return 0;
-}
-
-static int xpcs_link_up(struct mdio_xpcs_args *xpcs, int speed,
-			phy_interface_t interface)
-{
-	if (interface == PHY_INTERFACE_MODE_USXGMII)
-		return xpcs_config_usxgmii(xpcs, speed);
-
-	return 0;
-}
-
-static u32 xpcs_get_id(struct mdio_xpcs_args *xpcs)
-{
-	int ret;
-	u32 id;
-
-	ret = xpcs_read(xpcs, MDIO_MMD_PCS, MII_PHYSID1);
-	if (ret < 0)
-		return 0xffffffff;
-
-	id = ret << 16;
-
-	ret = xpcs_read(xpcs, MDIO_MMD_PCS, MII_PHYSID2);
-	if (ret < 0)
-		return 0xffffffff;
-
-	return id | ret;
-}
-
-static bool xpcs_check_features(struct mdio_xpcs_args *xpcs,
-				struct xpcs_id *match,
-				phy_interface_t interface)
-{
-	int i;
-
-	for (i = 0; match->interface[i] != PHY_INTERFACE_MODE_MAX; i++) {
-		if (match->interface[i] == interface)
-			break;
-	}
-
-	if (match->interface[i] == PHY_INTERFACE_MODE_MAX)
-		return false;
-
-	for (i = 0; match->supported[i] != __ETHTOOL_LINK_MODE_MASK_NBITS; i++)
-		set_bit(match->supported[i], xpcs->supported);
-
-	return true;
-}
-
-static int xpcs_probe(struct mdio_xpcs_args *xpcs, phy_interface_t interface)
-{
-	u32 xpcs_id = xpcs_get_id(xpcs);
-	struct xpcs_id *match = NULL;
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(xpcs_id_list); i++) {
-		struct xpcs_id *entry = &xpcs_id_list[i];
-
-		if ((xpcs_id & entry->mask) == entry->id) {
-			match = entry;
-
-			if (xpcs_check_features(xpcs, match, interface))
-				return xpcs_soft_reset(xpcs, MDIO_MMD_PCS);
-		}
-	}
-
-	return -ENODEV;
-}
-
-static struct mdio_xpcs_ops xpcs_ops = {
-	.validate = xpcs_validate,
-	.config = xpcs_config,
-	.get_state = xpcs_get_state,
-	.link_up = xpcs_link_up,
-	.probe = xpcs_probe,
-};
-
-struct mdio_xpcs_ops *mdio_xpcs_get_ops(void)
-{
-	return &xpcs_ops;
-}
-EXPORT_SYMBOL_GPL(mdio_xpcs_get_ops);
-
-MODULE_LICENSE("GPL v2");
diff --git a/include/linux/mdio-xpcs.h b/include/linux/mdio-xpcs.h
deleted file mode 100644
index 9a841aa5982d..000000000000
--- a/include/linux/mdio-xpcs.h
+++ /dev/null
@@ -1,41 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (c) 2020 Synopsys, Inc. and/or its affiliates.
- * Synopsys DesignWare XPCS helpers
- */
-
-#ifndef __LINUX_MDIO_XPCS_H
-#define __LINUX_MDIO_XPCS_H
-
-#include <linux/phy.h>
-#include <linux/phylink.h>
-
-struct mdio_xpcs_args {
-	__ETHTOOL_DECLARE_LINK_MODE_MASK(supported);
-	struct mii_bus *bus;
-	int addr;
-};
-
-struct mdio_xpcs_ops {
-	int (*validate)(struct mdio_xpcs_args *xpcs,
-			unsigned long *supported,
-			struct phylink_link_state *state);
-	int (*config)(struct mdio_xpcs_args *xpcs,
-		      const struct phylink_link_state *state);
-	int (*get_state)(struct mdio_xpcs_args *xpcs,
-			 struct phylink_link_state *state);
-	int (*link_up)(struct mdio_xpcs_args *xpcs, int speed,
-		       phy_interface_t interface);
-	int (*probe)(struct mdio_xpcs_args *xpcs, phy_interface_t interface);
-};
-
-#if IS_ENABLED(CONFIG_MDIO_XPCS)
-struct mdio_xpcs_ops *mdio_xpcs_get_ops(void);
-#else
-static inline struct mdio_xpcs_ops *mdio_xpcs_get_ops(void)
-{
-	return NULL;
-}
-#endif
-
-#endif /* __LINUX_MDIO_XPCS_H */
diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h
new file mode 100644
index 000000000000..351c1c9aedc5
--- /dev/null
+++ b/include/linux/pcs/pcs-xpcs.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2020 Synopsys, Inc. and/or its affiliates.
+ * Synopsys DesignWare XPCS helpers
+ */
+
+#ifndef __LINUX_PCS_XPCS_H
+#define __LINUX_PCS_XPCS_H
+
+#include <linux/phy.h>
+#include <linux/phylink.h>
+
+struct mdio_xpcs_args {
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(supported);
+	struct mii_bus *bus;
+	int addr;
+};
+
+struct mdio_xpcs_ops {
+	int (*validate)(struct mdio_xpcs_args *xpcs,
+			unsigned long *supported,
+			struct phylink_link_state *state);
+	int (*config)(struct mdio_xpcs_args *xpcs,
+		      const struct phylink_link_state *state);
+	int (*get_state)(struct mdio_xpcs_args *xpcs,
+			 struct phylink_link_state *state);
+	int (*link_up)(struct mdio_xpcs_args *xpcs, int speed,
+		       phy_interface_t interface);
+	int (*probe)(struct mdio_xpcs_args *xpcs, phy_interface_t interface);
+};
+
+#if IS_ENABLED(CONFIG_PCS_XPCS)
+struct mdio_xpcs_ops *mdio_xpcs_get_ops(void);
+#else
+static inline struct mdio_xpcs_ops *mdio_xpcs_get_ops(void)
+{
+	return NULL;
+}
+#endif
+
+#endif /* __LINUX_PCS_XPCS_H */
-- 
cgit v1.2.3


From fcba68bd75bb1d42b3aec7f471d382a9e639a672 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Thu, 27 Aug 2020 04:00:29 +0200
Subject: net/phy/mdio-i2c: Move header file to include/linux/mdio

In preparation for moving all MDIO drivers into drivers/net/mdio, move
the mdio-i2c header file into include/linux/mdio so it can be used by
both the MDIO driver and the SFP code which instantiates I2C MDIO
busses.

v2:
Add include/linux/mdio

Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS                   |  1 +
 drivers/net/phy/mdio-i2c.c    |  3 +--
 drivers/net/phy/mdio-i2c.h    | 16 ----------------
 drivers/net/phy/sfp.c         |  2 +-
 include/linux/mdio/mdio-i2c.h | 16 ++++++++++++++++
 5 files changed, 19 insertions(+), 19 deletions(-)
 delete mode 100644 drivers/net/phy/mdio-i2c.h
 create mode 100644 include/linux/mdio/mdio-i2c.h

(limited to 'include/linux')

diff --git a/MAINTAINERS b/MAINTAINERS
index 347ed6904fdf..af25e8d003e7 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15647,6 +15647,7 @@ L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/phy/phylink.c
 F:	drivers/net/phy/sfp*
+F:	include/linux/mdio/mdio-i2c.h
 F:	include/linux/phylink.h
 F:	include/linux/sfp.h
 K:	phylink\.h|struct\s+phylink|\.phylink|>phylink_|phylink_(autoneg|clear|connect|create|destroy|disconnect|ethtool|helper|mac|mii|of|set|start|stop|test|validate)
diff --git a/drivers/net/phy/mdio-i2c.c b/drivers/net/phy/mdio-i2c.c
index 0746e2cc39ae..09200a70b315 100644
--- a/drivers/net/phy/mdio-i2c.c
+++ b/drivers/net/phy/mdio-i2c.c
@@ -10,10 +10,9 @@
  * of their settings.
  */
 #include <linux/i2c.h>
+#include <linux/mdio/mdio-i2c.h>
 #include <linux/phy.h>
 
-#include "mdio-i2c.h"
-
 /*
  * I2C bus addresses 0x50 and 0x51 are normally an EEPROM, which is
  * specified to be present in SFP modules.  These correspond with PHY
diff --git a/drivers/net/phy/mdio-i2c.h b/drivers/net/phy/mdio-i2c.h
deleted file mode 100644
index b1d27f7cd23f..000000000000
--- a/drivers/net/phy/mdio-i2c.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * MDIO I2C bridge
- *
- * Copyright (C) 2015 Russell King
- */
-#ifndef MDIO_I2C_H
-#define MDIO_I2C_H
-
-struct device;
-struct i2c_adapter;
-struct mii_bus;
-
-struct mii_bus *mdio_i2c_alloc(struct device *parent, struct i2c_adapter *i2c);
-
-#endif
diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index c24b0e83dd32..5250dcdf46a4 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -7,6 +7,7 @@
 #include <linux/i2c.h>
 #include <linux/interrupt.h>
 #include <linux/jiffies.h>
+#include <linux/mdio/mdio-i2c.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/of.h>
@@ -16,7 +17,6 @@
 #include <linux/slab.h>
 #include <linux/workqueue.h>
 
-#include "mdio-i2c.h"
 #include "sfp.h"
 #include "swphy.h"
 
diff --git a/include/linux/mdio/mdio-i2c.h b/include/linux/mdio/mdio-i2c.h
new file mode 100644
index 000000000000..b1d27f7cd23f
--- /dev/null
+++ b/include/linux/mdio/mdio-i2c.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * MDIO I2C bridge
+ *
+ * Copyright (C) 2015 Russell King
+ */
+#ifndef MDIO_I2C_H
+#define MDIO_I2C_H
+
+struct device;
+struct i2c_adapter;
+struct mii_bus;
+
+struct mii_bus *mdio_i2c_alloc(struct device *parent, struct i2c_adapter *i2c);
+
+#endif
-- 
cgit v1.2.3


From 232e15e1d7ddb191c28248cb681f4544c0ff1c54 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Thu, 27 Aug 2020 04:00:30 +0200
Subject: net: xgene: Move shared header file into include/linux

This header file is currently included into the ethernet driver via a
relative path into the PHY subsystem. This is bad practice, and causes
issues for the upcoming move of the MDIO driver. Move the header file
into include/linux to clean this up.

v2:
Move header to include/linux/mdio

Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/apm/xgene/xgene_enet_main.h |   2 +-
 drivers/net/phy/mdio-xgene.c                     |   2 +-
 drivers/net/phy/mdio-xgene.h                     | 130 -----------------------
 include/linux/mdio/mdio-xgene.h                  | 130 +++++++++++++++++++++++
 4 files changed, 132 insertions(+), 132 deletions(-)
 delete mode 100644 drivers/net/phy/mdio-xgene.h
 create mode 100644 include/linux/mdio/mdio-xgene.h

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h
index d35a338120cf..643f5e646740 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h
@@ -18,6 +18,7 @@
 #include <linux/of_platform.h>
 #include <linux/of_net.h>
 #include <linux/of_mdio.h>
+#include <linux/mdio/mdio-xgene.h>
 #include <linux/module.h>
 #include <net/ip.h>
 #include <linux/prefetch.h>
@@ -26,7 +27,6 @@
 #include "xgene_enet_hw.h"
 #include "xgene_enet_cle.h"
 #include "xgene_enet_ring2.h"
-#include "../../../phy/mdio-xgene.h"
 
 #define ETHER_MIN_PACKET	64
 #define ETHER_STD_PACKET	1518
diff --git a/drivers/net/phy/mdio-xgene.c b/drivers/net/phy/mdio-xgene.c
index 34990eaa3298..461207cdf5d6 100644
--- a/drivers/net/phy/mdio-xgene.c
+++ b/drivers/net/phy/mdio-xgene.c
@@ -11,6 +11,7 @@
 #include <linux/efi.h>
 #include <linux/if_vlan.h>
 #include <linux/io.h>
+#include <linux/mdio/mdio-xgene.h>
 #include <linux/module.h>
 #include <linux/of_platform.h>
 #include <linux/of_net.h>
@@ -18,7 +19,6 @@
 #include <linux/prefetch.h>
 #include <linux/phy.h>
 #include <net/ip.h>
-#include "mdio-xgene.h"
 
 static bool xgene_mdio_status;
 
diff --git a/drivers/net/phy/mdio-xgene.h b/drivers/net/phy/mdio-xgene.h
deleted file mode 100644
index 8af93ada8b64..000000000000
--- a/drivers/net/phy/mdio-xgene.h
+++ /dev/null
@@ -1,130 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0+ */
-/* Applied Micro X-Gene SoC MDIO Driver
- *
- * Copyright (c) 2016, Applied Micro Circuits Corporation
- * Author: Iyappan Subramanian <isubramanian@apm.com>
- */
-
-#ifndef __MDIO_XGENE_H__
-#define __MDIO_XGENE_H__
-
-#define BLOCK_XG_MDIO_CSR_OFFSET	0x5000
-#define BLOCK_DIAG_CSR_OFFSET		0xd000
-#define XGENET_CONFIG_REG_ADDR		0x20
-
-#define MAC_ADDR_REG_OFFSET		0x00
-#define MAC_COMMAND_REG_OFFSET		0x04
-#define MAC_WRITE_REG_OFFSET		0x08
-#define MAC_READ_REG_OFFSET		0x0c
-#define MAC_COMMAND_DONE_REG_OFFSET	0x10
-
-#define CLKEN_OFFSET			0x08
-#define SRST_OFFSET			0x00
-
-#define MENET_CFG_MEM_RAM_SHUTDOWN_ADDR	0x70
-#define MENET_BLOCK_MEM_RDY_ADDR	0x74
-
-#define MAC_CONFIG_1_ADDR		0x00
-#define MII_MGMT_COMMAND_ADDR		0x24
-#define MII_MGMT_ADDRESS_ADDR		0x28
-#define MII_MGMT_CONTROL_ADDR		0x2c
-#define MII_MGMT_STATUS_ADDR		0x30
-#define MII_MGMT_INDICATORS_ADDR	0x34
-#define SOFT_RESET			BIT(31)
-
-#define MII_MGMT_CONFIG_ADDR            0x20
-#define MII_MGMT_COMMAND_ADDR           0x24
-#define MII_MGMT_ADDRESS_ADDR           0x28
-#define MII_MGMT_CONTROL_ADDR           0x2c
-#define MII_MGMT_STATUS_ADDR            0x30
-#define MII_MGMT_INDICATORS_ADDR        0x34
-
-#define MIIM_COMMAND_ADDR               0x20
-#define MIIM_FIELD_ADDR                 0x24
-#define MIIM_CONFIGURATION_ADDR         0x28
-#define MIIM_LINKFAILVECTOR_ADDR        0x2c
-#define MIIM_INDICATOR_ADDR             0x30
-#define MIIMRD_FIELD_ADDR               0x34
-
-#define MDIO_CSR_OFFSET			0x5000
-
-#define REG_ADDR_POS			0
-#define REG_ADDR_LEN			5
-#define PHY_ADDR_POS			8
-#define PHY_ADDR_LEN			5
-
-#define HSTMIIMWRDAT_POS		0
-#define HSTMIIMWRDAT_LEN		16
-#define HSTPHYADX_POS			23
-#define HSTPHYADX_LEN			5
-#define HSTREGADX_POS			18
-#define HSTREGADX_LEN			5
-#define HSTLDCMD			BIT(3)
-#define HSTMIIMCMD_POS			0
-#define HSTMIIMCMD_LEN			3
-
-#define BUSY_MASK			BIT(0)
-#define READ_CYCLE_MASK			BIT(0)
-
-enum xgene_enet_cmd {
-	XGENE_ENET_WR_CMD = BIT(31),
-	XGENE_ENET_RD_CMD = BIT(30)
-};
-
-enum {
-	MIIM_CMD_IDLE,
-	MIIM_CMD_LEGACY_WRITE,
-	MIIM_CMD_LEGACY_READ,
-};
-
-enum xgene_mdio_id {
-	XGENE_MDIO_RGMII = 1,
-	XGENE_MDIO_XFI
-};
-
-struct xgene_mdio_pdata {
-	struct clk *clk;
-	struct device *dev;
-	void __iomem *mac_csr_addr;
-	void __iomem *diag_csr_addr;
-	void __iomem *mdio_csr_addr;
-	struct mii_bus *mdio_bus;
-	int mdio_id;
-	spinlock_t mac_lock; /* mac lock */
-};
-
-/* Set the specified value into a bit-field defined by its starting position
- * and length within a single u64.
- */
-static inline u64 xgene_enet_set_field_value(int pos, int len, u64 val)
-{
-	return (val & ((1ULL << len) - 1)) << pos;
-}
-
-#define SET_VAL(field, val) \
-		xgene_enet_set_field_value(field ## _POS, field ## _LEN, val)
-
-#define SET_BIT(field) \
-		xgene_enet_set_field_value(field ## _POS, 1, 1)
-
-/* Get the value from a bit-field defined by its starting position
- * and length within the specified u64.
- */
-static inline u64 xgene_enet_get_field_value(int pos, int len, u64 src)
-{
-	return (src >> pos) & ((1ULL << len) - 1);
-}
-
-#define GET_VAL(field, src) \
-		xgene_enet_get_field_value(field ## _POS, field ## _LEN, src)
-
-#define GET_BIT(field, src) \
-		xgene_enet_get_field_value(field ## _POS, 1, src)
-
-u32 xgene_mdio_rd_mac(struct xgene_mdio_pdata *pdata, u32 rd_addr);
-void xgene_mdio_wr_mac(struct xgene_mdio_pdata *pdata, u32 wr_addr, u32 data);
-int xgene_mdio_rgmii_read(struct mii_bus *bus, int phy_id, int reg);
-int xgene_mdio_rgmii_write(struct mii_bus *bus, int phy_id, int reg, u16 data);
-struct phy_device *xgene_enet_phy_register(struct mii_bus *bus, int phy_addr);
-
-#endif  /* __MDIO_XGENE_H__ */
diff --git a/include/linux/mdio/mdio-xgene.h b/include/linux/mdio/mdio-xgene.h
new file mode 100644
index 000000000000..8af93ada8b64
--- /dev/null
+++ b/include/linux/mdio/mdio-xgene.h
@@ -0,0 +1,130 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/* Applied Micro X-Gene SoC MDIO Driver
+ *
+ * Copyright (c) 2016, Applied Micro Circuits Corporation
+ * Author: Iyappan Subramanian <isubramanian@apm.com>
+ */
+
+#ifndef __MDIO_XGENE_H__
+#define __MDIO_XGENE_H__
+
+#define BLOCK_XG_MDIO_CSR_OFFSET	0x5000
+#define BLOCK_DIAG_CSR_OFFSET		0xd000
+#define XGENET_CONFIG_REG_ADDR		0x20
+
+#define MAC_ADDR_REG_OFFSET		0x00
+#define MAC_COMMAND_REG_OFFSET		0x04
+#define MAC_WRITE_REG_OFFSET		0x08
+#define MAC_READ_REG_OFFSET		0x0c
+#define MAC_COMMAND_DONE_REG_OFFSET	0x10
+
+#define CLKEN_OFFSET			0x08
+#define SRST_OFFSET			0x00
+
+#define MENET_CFG_MEM_RAM_SHUTDOWN_ADDR	0x70
+#define MENET_BLOCK_MEM_RDY_ADDR	0x74
+
+#define MAC_CONFIG_1_ADDR		0x00
+#define MII_MGMT_COMMAND_ADDR		0x24
+#define MII_MGMT_ADDRESS_ADDR		0x28
+#define MII_MGMT_CONTROL_ADDR		0x2c
+#define MII_MGMT_STATUS_ADDR		0x30
+#define MII_MGMT_INDICATORS_ADDR	0x34
+#define SOFT_RESET			BIT(31)
+
+#define MII_MGMT_CONFIG_ADDR            0x20
+#define MII_MGMT_COMMAND_ADDR           0x24
+#define MII_MGMT_ADDRESS_ADDR           0x28
+#define MII_MGMT_CONTROL_ADDR           0x2c
+#define MII_MGMT_STATUS_ADDR            0x30
+#define MII_MGMT_INDICATORS_ADDR        0x34
+
+#define MIIM_COMMAND_ADDR               0x20
+#define MIIM_FIELD_ADDR                 0x24
+#define MIIM_CONFIGURATION_ADDR         0x28
+#define MIIM_LINKFAILVECTOR_ADDR        0x2c
+#define MIIM_INDICATOR_ADDR             0x30
+#define MIIMRD_FIELD_ADDR               0x34
+
+#define MDIO_CSR_OFFSET			0x5000
+
+#define REG_ADDR_POS			0
+#define REG_ADDR_LEN			5
+#define PHY_ADDR_POS			8
+#define PHY_ADDR_LEN			5
+
+#define HSTMIIMWRDAT_POS		0
+#define HSTMIIMWRDAT_LEN		16
+#define HSTPHYADX_POS			23
+#define HSTPHYADX_LEN			5
+#define HSTREGADX_POS			18
+#define HSTREGADX_LEN			5
+#define HSTLDCMD			BIT(3)
+#define HSTMIIMCMD_POS			0
+#define HSTMIIMCMD_LEN			3
+
+#define BUSY_MASK			BIT(0)
+#define READ_CYCLE_MASK			BIT(0)
+
+enum xgene_enet_cmd {
+	XGENE_ENET_WR_CMD = BIT(31),
+	XGENE_ENET_RD_CMD = BIT(30)
+};
+
+enum {
+	MIIM_CMD_IDLE,
+	MIIM_CMD_LEGACY_WRITE,
+	MIIM_CMD_LEGACY_READ,
+};
+
+enum xgene_mdio_id {
+	XGENE_MDIO_RGMII = 1,
+	XGENE_MDIO_XFI
+};
+
+struct xgene_mdio_pdata {
+	struct clk *clk;
+	struct device *dev;
+	void __iomem *mac_csr_addr;
+	void __iomem *diag_csr_addr;
+	void __iomem *mdio_csr_addr;
+	struct mii_bus *mdio_bus;
+	int mdio_id;
+	spinlock_t mac_lock; /* mac lock */
+};
+
+/* Set the specified value into a bit-field defined by its starting position
+ * and length within a single u64.
+ */
+static inline u64 xgene_enet_set_field_value(int pos, int len, u64 val)
+{
+	return (val & ((1ULL << len) - 1)) << pos;
+}
+
+#define SET_VAL(field, val) \
+		xgene_enet_set_field_value(field ## _POS, field ## _LEN, val)
+
+#define SET_BIT(field) \
+		xgene_enet_set_field_value(field ## _POS, 1, 1)
+
+/* Get the value from a bit-field defined by its starting position
+ * and length within the specified u64.
+ */
+static inline u64 xgene_enet_get_field_value(int pos, int len, u64 src)
+{
+	return (src >> pos) & ((1ULL << len) - 1);
+}
+
+#define GET_VAL(field, src) \
+		xgene_enet_get_field_value(field ## _POS, field ## _LEN, src)
+
+#define GET_BIT(field, src) \
+		xgene_enet_get_field_value(field ## _POS, 1, src)
+
+u32 xgene_mdio_rd_mac(struct xgene_mdio_pdata *pdata, u32 rd_addr);
+void xgene_mdio_wr_mac(struct xgene_mdio_pdata *pdata, u32 wr_addr, u32 data);
+int xgene_mdio_rgmii_read(struct mii_bus *bus, int phy_id, int reg);
+int xgene_mdio_rgmii_write(struct mii_bus *bus, int phy_id, int reg, u16 data);
+struct phy_device *xgene_enet_phy_register(struct mii_bus *bus, int phy_addr);
+
+#endif  /* __MDIO_XGENE_H__ */
-- 
cgit v1.2.3


From 17529bcf0ae20f1ac6d7846762bf0c6ad91dbb7f Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Thu, 27 Aug 2020 10:48:28 +0200
Subject: power: supply: gpio-charger: Convert to GPIO descriptors

This converts the GPIO charger to use exclusively GPIO
descriptors, moving the two remaining platforms passing
global GPIO numbers over to using a GPIO descriptor table.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Cc: Robert Jarzmik <robert.jarzmik@free.fr>
Cc: Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 arch/arm/mach-pxa/tosa.c            | 12 ++++++++++--
 arch/arm/mach-sa1100/collie.c       | 14 ++++++++++++--
 drivers/power/supply/gpio-charger.c | 26 +-------------------------
 include/linux/power/gpio-charger.h  |  6 ------
 4 files changed, 23 insertions(+), 35 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/mach-pxa/tosa.c b/arch/arm/mach-pxa/tosa.c
index 3d2c108e911e..431709725d02 100644
--- a/arch/arm/mach-pxa/tosa.c
+++ b/arch/arm/mach-pxa/tosa.c
@@ -369,6 +369,15 @@ static struct pxaficp_platform_data tosa_ficp_platform_data = {
 /*
  * Tosa AC IN
  */
+static struct gpiod_lookup_table tosa_power_gpiod_table = {
+	.dev_id = "gpio-charger",
+	.table = {
+		GPIO_LOOKUP("gpio-pxa", TOSA_GPIO_AC_IN,
+			    NULL, GPIO_ACTIVE_LOW),
+		{ },
+	},
+};
+
 static char *tosa_ac_supplied_to[] = {
 	"main-battery",
 	"backup-battery",
@@ -378,8 +387,6 @@ static char *tosa_ac_supplied_to[] = {
 static struct gpio_charger_platform_data tosa_power_data = {
 	.name			= "charger",
 	.type			= POWER_SUPPLY_TYPE_MAINS,
-	.gpio			= TOSA_GPIO_AC_IN,
-	.gpio_active_low	= 1,
 	.supplied_to		= tosa_ac_supplied_to,
 	.num_supplicants	= ARRAY_SIZE(tosa_ac_supplied_to),
 };
@@ -951,6 +958,7 @@ static void __init tosa_init(void)
 	clk_add_alias("CLK_CK3P6MI", tc6393xb_device.name, "GPIO11_CLK", NULL);
 
 	gpiod_add_lookup_table(&tosa_udc_gpiod_table);
+	gpiod_add_lookup_table(&tosa_power_gpiod_table);
 	platform_add_devices(devices, ARRAY_SIZE(devices));
 }
 
diff --git a/arch/arm/mach-sa1100/collie.c b/arch/arm/mach-sa1100/collie.c
index 3cc2b71e16f0..bd3a52fd09ce 100644
--- a/arch/arm/mach-sa1100/collie.c
+++ b/arch/arm/mach-sa1100/collie.c
@@ -30,6 +30,7 @@
 #include <linux/gpio_keys.h>
 #include <linux/input.h>
 #include <linux/gpio.h>
+#include <linux/gpio/machine.h>
 #include <linux/power/gpio-charger.h>
 
 #include <video/sa1100fb.h>
@@ -131,16 +132,23 @@ static struct irda_platform_data collie_ir_data = {
 /*
  * Collie AC IN
  */
+static struct gpiod_lookup_table collie_power_gpiod_table = {
+	.dev_id = "gpio-charger",
+	.table = {
+		GPIO_LOOKUP("gpio", COLLIE_GPIO_AC_IN,
+			    NULL, GPIO_ACTIVE_HIGH),
+		{ },
+	},
+};
+
 static char *collie_ac_supplied_to[] = {
 	"main-battery",
 	"backup-battery",
 };
 
-
 static struct gpio_charger_platform_data collie_power_data = {
 	.name			= "charger",
 	.type			= POWER_SUPPLY_TYPE_MAINS,
-	.gpio			= COLLIE_GPIO_AC_IN,
 	.supplied_to		= collie_ac_supplied_to,
 	.num_supplicants	= ARRAY_SIZE(collie_ac_supplied_to),
 };
@@ -386,6 +394,8 @@ static void __init collie_init(void)
 
 	platform_scoop_config = &collie_pcmcia_config;
 
+	gpiod_add_lookup_table(&collie_power_gpiod_table);
+
 	ret = platform_add_devices(devices, ARRAY_SIZE(devices));
 	if (ret) {
 		printk(KERN_WARNING "collie: Unable to register LoCoMo device\n");
diff --git a/drivers/power/supply/gpio-charger.c b/drivers/power/supply/gpio-charger.c
index 875735d50716..ae778f110101 100644
--- a/drivers/power/supply/gpio-charger.c
+++ b/drivers/power/supply/gpio-charger.c
@@ -5,7 +5,6 @@
  */
 
 #include <linux/device.h>
-#include <linux/gpio.h> /* For legacy platform data */
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
@@ -131,7 +130,6 @@ static int gpio_charger_probe(struct platform_device *pdev)
 	struct power_supply_desc *charger_desc;
 	struct gpio_desc *charge_status;
 	int charge_status_irq;
-	unsigned long flags;
 	int ret;
 	int num_props = 0;
 
@@ -149,29 +147,7 @@ static int gpio_charger_probe(struct platform_device *pdev)
 	 * boardfile descriptor tables. It's good to try this first.
 	 */
 	gpio_charger->gpiod = devm_gpiod_get_optional(dev, NULL, GPIOD_IN);
-
-	/*
-	 * Fallback to legacy platform data method, if no GPIO is specified
-	 * using boardfile descriptor tables.
-	 */
-	if (!gpio_charger->gpiod && pdata) {
-		/* Non-DT: use legacy GPIO numbers */
-		if (!gpio_is_valid(pdata->gpio)) {
-			dev_err(dev, "Invalid gpio pin in pdata\n");
-			return -EINVAL;
-		}
-		flags = GPIOF_IN;
-		if (pdata->gpio_active_low)
-			flags |= GPIOF_ACTIVE_LOW;
-		ret = devm_gpio_request_one(dev, pdata->gpio, flags,
-					    dev_name(dev));
-		if (ret) {
-			dev_err(dev, "Failed to request gpio pin: %d\n", ret);
-			return ret;
-		}
-		/* Then convert this to gpiod for now */
-		gpio_charger->gpiod = gpio_to_desc(pdata->gpio);
-	} else if (IS_ERR(gpio_charger->gpiod)) {
+	if (IS_ERR(gpio_charger->gpiod)) {
 		/* Just try again if this happens */
 		if (PTR_ERR(gpio_charger->gpiod) == -EPROBE_DEFER)
 			return -EPROBE_DEFER;
diff --git a/include/linux/power/gpio-charger.h b/include/linux/power/gpio-charger.h
index 5a5a8de98181..c0b7657ac1df 100644
--- a/include/linux/power/gpio-charger.h
+++ b/include/linux/power/gpio-charger.h
@@ -13,18 +13,12 @@
  * struct gpio_charger_platform_data - platform_data for gpio_charger devices
  * @name:		Name for the chargers power_supply device
  * @type:		Type of the charger
- * @gpio:		GPIO which is used to indicate the chargers status
- * @gpio_active_low:	Should be set to 1 if the GPIO is active low otherwise 0
  * @supplied_to:	Array of battery names to which this chargers supplies power
  * @num_supplicants:	Number of entries in the supplied_to array
  */
 struct gpio_charger_platform_data {
 	const char *name;
 	enum power_supply_type type;
-
-	int gpio;
-	int gpio_active_low;
-
 	char **supplied_to;
 	size_t num_supplicants;
 };
-- 
cgit v1.2.3


From dab741e0e02bd3c4f5e2e97be74b39df2523fc6e Mon Sep 17 00:00:00 2001
From: Mattias Nissler <mnissler@chromium.org>
Date: Thu, 27 Aug 2020 11:09:46 -0600
Subject: Add a "nosymfollow" mount option.

For mounts that have the new "nosymfollow" option, don't follow symlinks
when resolving paths. The new option is similar in spirit to the
existing "nodev", "noexec", and "nosuid" options, as well as to the
LOOKUP_NO_SYMLINKS resolve flag in the openat2(2) syscall. Various BSD
variants have been supporting the "nosymfollow" mount option for a long
time with equivalent implementations.

Note that symlinks may still be created on file systems mounted with
the "nosymfollow" option present. readlink() remains functional, so
user space code that is aware of symlinks can still choose to follow
them explicitly.

Setting the "nosymfollow" mount option helps prevent privileged
writers from modifying files unintentionally in case there is an
unexpected link along the accessed path. The "nosymfollow" option is
thus useful as a defensive measure for systems that need to deal with
untrusted file systems in privileged contexts.

More information on the history and motivation for this patch can be
found here:

https://sites.google.com/a/chromium.org/dev/chromium-os/chromiumos-design-docs/hardening-against-malicious-stateful-data#TOC-Restricting-symlink-traversal

Signed-off-by: Mattias Nissler <mnissler@chromium.org>
Signed-off-by: Ross Zwisler <zwisler@google.com>
Reviewed-by: Aleksa Sarai <cyphar@cyphar.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c                 | 3 ++-
 fs/namespace.c             | 2 ++
 fs/proc_namespace.c        | 1 +
 fs/statfs.c                | 2 ++
 include/linux/mount.h      | 3 ++-
 include/linux/statfs.h     | 1 +
 include/uapi/linux/mount.h | 1 +
 7 files changed, 11 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/fs/namei.c b/fs/namei.c
index e99e2a9da0f7..33e8c79bc761 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1626,7 +1626,8 @@ static const char *pick_link(struct nameidata *nd, struct path *link,
 			return ERR_PTR(error);
 	}
 
-	if (unlikely(nd->flags & LOOKUP_NO_SYMLINKS))
+	if (unlikely(nd->flags & LOOKUP_NO_SYMLINKS) ||
+			unlikely(link->mnt->mnt_flags & MNT_NOSYMFOLLOW))
 		return ERR_PTR(-ELOOP);
 
 	if (!(nd->flags & LOOKUP_RCU)) {
diff --git a/fs/namespace.c b/fs/namespace.c
index bae0e95b3713..6408788a649e 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -3160,6 +3160,8 @@ int path_mount(const char *dev_name, struct path *path,
 		mnt_flags &= ~(MNT_RELATIME | MNT_NOATIME);
 	if (flags & MS_RDONLY)
 		mnt_flags |= MNT_READONLY;
+	if (flags & MS_NOSYMFOLLOW)
+		mnt_flags |= MNT_NOSYMFOLLOW;
 
 	/* The default atime for remount is preservation */
 	if ((flags & MS_REMOUNT) &&
diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c
index 3059a9394c2d..e59d4bb3a89e 100644
--- a/fs/proc_namespace.c
+++ b/fs/proc_namespace.c
@@ -70,6 +70,7 @@ static void show_mnt_opts(struct seq_file *m, struct vfsmount *mnt)
 		{ MNT_NOATIME, ",noatime" },
 		{ MNT_NODIRATIME, ",nodiratime" },
 		{ MNT_RELATIME, ",relatime" },
+		{ MNT_NOSYMFOLLOW, ",nosymfollow" },
 		{ 0, NULL }
 	};
 	const struct proc_fs_opts *fs_infop;
diff --git a/fs/statfs.c b/fs/statfs.c
index 2616424012ea..59f33752c131 100644
--- a/fs/statfs.c
+++ b/fs/statfs.c
@@ -29,6 +29,8 @@ static int flags_by_mnt(int mnt_flags)
 		flags |= ST_NODIRATIME;
 	if (mnt_flags & MNT_RELATIME)
 		flags |= ST_RELATIME;
+	if (mnt_flags & MNT_NOSYMFOLLOW)
+		flags |= ST_NOSYMFOLLOW;
 	return flags;
 }
 
diff --git a/include/linux/mount.h b/include/linux/mount.h
index de657bd211fa..aaf343b38671 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -30,6 +30,7 @@ struct fs_context;
 #define MNT_NODIRATIME	0x10
 #define MNT_RELATIME	0x20
 #define MNT_READONLY	0x40	/* does the user want this to be r/o? */
+#define MNT_NOSYMFOLLOW	0x80
 
 #define MNT_SHRINKABLE	0x100
 #define MNT_WRITE_HOLD	0x200
@@ -46,7 +47,7 @@ struct fs_context;
 #define MNT_SHARED_MASK	(MNT_UNBINDABLE)
 #define MNT_USER_SETTABLE_MASK  (MNT_NOSUID | MNT_NODEV | MNT_NOEXEC \
 				 | MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME \
-				 | MNT_READONLY)
+				 | MNT_READONLY | MNT_NOSYMFOLLOW)
 #define MNT_ATIME_MASK (MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME )
 
 #define MNT_INTERNAL_FLAGS (MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | \
diff --git a/include/linux/statfs.h b/include/linux/statfs.h
index 9bc69edb8f18..fac4356ea1bf 100644
--- a/include/linux/statfs.h
+++ b/include/linux/statfs.h
@@ -40,6 +40,7 @@ struct kstatfs {
 #define ST_NOATIME	0x0400	/* do not update access times */
 #define ST_NODIRATIME	0x0800	/* do not update directory access times */
 #define ST_RELATIME	0x1000	/* update atime relative to mtime/ctime */
+#define ST_NOSYMFOLLOW	0x2000	/* do not follow symlinks */
 
 struct dentry;
 extern int vfs_get_fsid(struct dentry *dentry, __kernel_fsid_t *fsid);
diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h
index 96a0240f23fe..dd8306ea336c 100644
--- a/include/uapi/linux/mount.h
+++ b/include/uapi/linux/mount.h
@@ -16,6 +16,7 @@
 #define MS_REMOUNT	32	/* Alter flags of a mounted FS */
 #define MS_MANDLOCK	64	/* Allow mandatory locks on an FS */
 #define MS_DIRSYNC	128	/* Directory modifications are synchronous */
+#define MS_NOSYMFOLLOW	256	/* Do not follow symlinks */
 #define MS_NOATIME	1024	/* Do not update access times. */
 #define MS_NODIRATIME	2048	/* Do not update directory access times */
 #define MS_BIND		4096
-- 
cgit v1.2.3


From 6bbe2a90a0bb4af8dd99c3565e907fe9b5e7fd88 Mon Sep 17 00:00:00 2001
From: Badhri Jagan Sridharan <badhri@google.com>
Date: Mon, 17 Aug 2020 11:38:27 -0700
Subject: usb: typec: tcpm: During PR_SWAP, source caps should be sent only
 after tSwapSourceStart

The patch addresses the compliance test failures while running
TD.PD.CP.E3, TD.PD.CP.E4, TD.PD.CP.E5 of the "Deterministic PD
Compliance MOI" test plan published in https://www.usb.org/usbc.
For a product to be Type-C compliant, it's expected that these tests
are run on usb.org certified Type-C compliance tester as mentioned in
https://www.usb.org/usbc.

The purpose of the tests TD.PD.CP.E3, TD.PD.CP.E4, TD.PD.CP.E5 is to
verify the PR_SWAP response of the device. While doing so, the test
asserts that Source Capabilities message is NOT received from the test
device within tSwapSourceStart min (20 ms) from the time the last bit
of GoodCRC corresponding to the RS_RDY message sent by the UUT was
sent. If it does then the test fails.

This is in line with the requirements from the USB Power Delivery
Specification Revision 3.0, Version 1.2:
"6.6.8.1 SwapSourceStartTimer
The SwapSourceStartTimer Shall be used by the new Source, after a
Power Role Swap or Fast Role Swap, to ensure that it does not send
Source_Capabilities Message before the new Sink is ready to receive
the
Source_Capabilities Message. The new Source Shall Not send the
Source_Capabilities Message earlier than tSwapSourceStart after the
last bit of the EOP of GoodCRC Message sent in response to the PS_RDY
Message sent by the new Source indicating that its power supply is
ready."

The patch makes sure that TCPM does not send the Source_Capabilities
Message within tSwapSourceStart(20ms) by transitioning into
SRC_STARTUP only after  tSwapSourceStart(20ms).

Signed-off-by: Badhri Jagan Sridharan <badhri@google.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20200817183828.1895015-1-badhri@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/tcpm.c | 2 +-
 include/linux/usb/pd.h        | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 3ef37202ee37..d38347bd3335 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -3555,7 +3555,7 @@ static void run_state_machine(struct tcpm_port *port)
 		 */
 		tcpm_set_pwr_role(port, TYPEC_SOURCE);
 		tcpm_pd_send_control(port, PD_CTRL_PS_RDY);
-		tcpm_set_state(port, SRC_STARTUP, 0);
+		tcpm_set_state(port, SRC_STARTUP, PD_T_SWAP_SRC_START);
 		break;
 
 	case VCONN_SWAP_ACCEPT:
diff --git a/include/linux/usb/pd.h b/include/linux/usb/pd.h
index b6c233e79bd4..1df895e4680b 100644
--- a/include/linux/usb/pd.h
+++ b/include/linux/usb/pd.h
@@ -473,6 +473,7 @@ static inline unsigned int rdo_max_power(u32 rdo)
 #define PD_T_ERROR_RECOVERY	100	/* minimum 25 is insufficient */
 #define PD_T_SRCSWAPSTDBY      625     /* Maximum of 650ms */
 #define PD_T_NEWSRC            250     /* Maximum of 275ms */
+#define PD_T_SWAP_SRC_START	20	/* Minimum of 20ms */
 
 #define PD_T_DRP_TRY		100	/* 75 - 150 ms */
 #define PD_T_DRP_TRYWAIT	600	/* 400 - 800 ms */
-- 
cgit v1.2.3


From aefc66afe42bcae01743c0b3c5addd089263801b Mon Sep 17 00:00:00 2001
From: Badhri Jagan Sridharan <badhri@google.com>
Date: Mon, 17 Aug 2020 11:38:28 -0700
Subject: usb: typec: pd: Fix formatting in pd.h header

Replacing spaces with tabs for PD_T_* constants.

Signed-off-by: Badhri Jagan Sridharan <badhri@google.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20200817183828.1895015-2-badhri@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/usb/pd.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/usb/pd.h b/include/linux/usb/pd.h
index 1df895e4680b..f842e4589bd2 100644
--- a/include/linux/usb/pd.h
+++ b/include/linux/usb/pd.h
@@ -471,9 +471,10 @@ static inline unsigned int rdo_max_power(u32 rdo)
 #define PD_T_VCONN_SOURCE_ON	100
 #define PD_T_SINK_REQUEST	100	/* 100 ms minimum */
 #define PD_T_ERROR_RECOVERY	100	/* minimum 25 is insufficient */
-#define PD_T_SRCSWAPSTDBY      625     /* Maximum of 650ms */
-#define PD_T_NEWSRC            250     /* Maximum of 275ms */
+#define PD_T_SRCSWAPSTDBY	625	/* Maximum of 650ms */
+#define PD_T_NEWSRC		250	/* Maximum of 275ms */
 #define PD_T_SWAP_SRC_START	20	/* Minimum of 20ms */
+#define PD_T_BIST_CONT_MODE	50	/* 30 - 60 ms */
 
 #define PD_T_DRP_TRY		100	/* 75 - 150 ms */
 #define PD_T_DRP_TRYWAIT	600	/* 400 - 800 ms */
@@ -484,5 +485,4 @@ static inline unsigned int rdo_max_power(u32 rdo)
 #define PD_N_CAPS_COUNT		(PD_T_NO_RESPONSE / PD_T_SEND_SOURCE_CAP)
 #define PD_N_HARD_RESET_COUNT	2
 
-#define PD_T_BIST_CONT_MODE	50 /* 30 - 60 ms */
 #endif /* __LINUX_USB_PD_H */
-- 
cgit v1.2.3


From d3cd0071a89a085a2d578b6a9e31db10469501c6 Mon Sep 17 00:00:00 2001
From: Christian Eggers <ceggers@arri.de>
Date: Mon, 27 Jul 2020 13:12:18 +0200
Subject: eeprom: at25: allow page sizes greater than 16 bit

Storage technologies like FRAM have no "write pages", the whole chip can
be written within one SPI transfer. For these chips, the page size can
be set equal to the device size. Currently available devices are already
bigger than 64 kiB.

Signed-off-by: Christian Eggers <ceggers@arri.de>
Link: https://lore.kernel.org/r/20200727111218.26926-1-ceggers@arri.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/eeprom/at25.c | 2 +-
 include/linux/spi/eeprom.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/misc/eeprom/at25.c b/drivers/misc/eeprom/at25.c
index cde9a2fc1325..0e7c8dc01195 100644
--- a/drivers/misc/eeprom/at25.c
+++ b/drivers/misc/eeprom/at25.c
@@ -261,7 +261,7 @@ static int at25_fw_to_chip(struct device *dev, struct spi_eeprom *chip)
 
 	if (device_property_read_u32(dev, "pagesize", &val) == 0 ||
 	    device_property_read_u32(dev, "at25,page-size", &val) == 0) {
-		chip->page_size = (u16)val;
+		chip->page_size = val;
 	} else {
 		dev_err(dev, "Error: missing \"pagesize\" property\n");
 		return -ENODEV;
diff --git a/include/linux/spi/eeprom.h b/include/linux/spi/eeprom.h
index aceccf9c71fb..1cca3dd5a748 100644
--- a/include/linux/spi/eeprom.h
+++ b/include/linux/spi/eeprom.h
@@ -14,7 +14,7 @@
 struct spi_eeprom {
 	u32		byte_len;
 	char		name[10];
-	u16		page_size;		/* for writes */
+	u32		page_size;		/* for writes */
 	u16		flags;
 #define	EE_ADDR1	0x0001			/*  8 bit addrs */
 #define	EE_ADDR2	0x0002			/* 16 bit addrs */
-- 
cgit v1.2.3


From 145fbd1e82e6654398ace321432e3a803b8a2be4 Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@ti.com>
Date: Fri, 28 Aug 2020 11:41:41 +0300
Subject: dmaengine: Remove unused define for
 dma_request_slave_channel_reason()

No users left in the kernel, it can be removed.

Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Link: https://lore.kernel.org/r/20200828084141.14902-1-peter.ujfalusi@ti.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/dmaengine.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 6fbd5c99e30c..011371b7f081 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -1527,8 +1527,6 @@ static inline int dma_get_slave_caps(struct dma_chan *chan,
 }
 #endif
 
-#define dma_request_slave_channel_reason(dev, name) dma_request_chan(dev, name)
-
 static inline int dmaengine_desc_set_reuse(struct dma_async_tx_descriptor *tx)
 {
 	struct dma_slave_caps caps;
-- 
cgit v1.2.3


From 31b4b3bff2c217c61bb99db76f24c4886e74a1a5 Mon Sep 17 00:00:00 2001
From: Sebastian Fricke <sebastian.fricke.linux@gmail.com>
Date: Mon, 3 Aug 2020 07:43:45 +0200
Subject: include/linux/miscdevice.h - Fix typo/grammar

Improve the clarity and grammar of descriptive comment on top of the
minor number assignments.

Fix a typo within 2 comments for macros.
s/This helps in eleminating of boilerplate code.
 /This helps to eliminate boilerplate code./

Signed-off-by: Sebastian Fricke <sebastian.fricke.linux@gmail.com>
Link: https://lore.kernel.org/r/20200803054346.4285-1-sebastian.fricke.linux@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/miscdevice.h | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h
index c7a93002a3c1..0676f18093f9 100644
--- a/include/linux/miscdevice.h
+++ b/include/linux/miscdevice.h
@@ -7,9 +7,9 @@
 #include <linux/device.h>
 
 /*
- *	These allocations are managed by device@lanana.org. If you use an
- *	entry that is not in assigned your entry may well be moved and
- *	reassigned, or set dynamic if a fixed value is not justified.
+ *	These allocations are managed by device@lanana.org. If you need
+ *	an entry that is not assigned here, it can be moved and
+ *	reassigned or dynamically set if a fixed value is not justified.
  */
 
 #define PSMOUSE_MINOR		1
@@ -93,14 +93,14 @@ extern void misc_deregister(struct miscdevice *misc);
 
 /*
  * Helper macro for drivers that don't do anything special in the initcall.
- * This helps in eleminating of boilerplate code.
+ * This helps to eliminate boilerplate code.
  */
 #define builtin_misc_device(__misc_device) \
 	builtin_driver(__misc_device, misc_register)
 
 /*
  * Helper macro for drivers that don't do anything special in module init / exit
- * call. This helps in eleminating of boilerplate code.
+ * call. This helps to eliminate boilerplate code.
  */
 #define module_misc_device(__misc_device) \
 	module_driver(__misc_device, misc_register, misc_deregister)
-- 
cgit v1.2.3


From cf5153e4338c4cca655a4a4eff6d54c6a0adcdb7 Mon Sep 17 00:00:00 2001
From: Sowjanya Komatineni <skomatineni@nvidia.com>
Date: Wed, 12 Aug 2020 02:27:19 +0200
Subject: media: gpu: host1x: mipi: Keep MIPI clock enabled and mutex locked
 till calibration done

With the split of MIPI calibration into tegra_mipi_calibrate() and
tegra_mipi_wait(), MIPI clock is not kept enabled and mutex is not locked
till the calibration is done.

So, this patch keeps MIPI clock enabled and mutex locked after triggering
start of calibration till its done.

To let calibration process go through its finite sequence codes before
calibration logic waiting for pads idle state added wait time of 75usec
to make sure it sees idle state to apply the results.

This patch renames tegra_mipi_calibrate() as tegra_mipi_start_calibration()
and tegra_mipi_wait() as tegra_mipi_finish_calibration() to be inline
with their usage.

Reviewed-by: Dmitry Osipenko <digetx@gmail.com>
Signed-off-by: Sowjanya Komatineni <skomatineni@nvidia.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 drivers/gpu/drm/tegra/dsi.c |  4 ++--
 drivers/gpu/host1x/mipi.c   | 22 ++++++++++------------
 include/linux/host1x.h      |  4 ++--
 3 files changed, 14 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/tegra/dsi.c b/drivers/gpu/drm/tegra/dsi.c
index 3820e8dff14b..a7864e91fc0b 100644
--- a/drivers/gpu/drm/tegra/dsi.c
+++ b/drivers/gpu/drm/tegra/dsi.c
@@ -694,11 +694,11 @@ static int tegra_dsi_pad_calibrate(struct tegra_dsi *dsi)
 		DSI_PAD_PREEMP_PD(0x03) | DSI_PAD_PREEMP_PU(0x3);
 	tegra_dsi_writel(dsi, value, DSI_PAD_CONTROL_3);
 
-	err = tegra_mipi_calibrate(dsi->mipi);
+	err = tegra_mipi_start_calibration(dsi->mipi);
 	if (err < 0)
 		return err;
 
-	return tegra_mipi_wait(dsi->mipi);
+	return tegra_mipi_finish_calibration(dsi->mipi);
 }
 
 static void tegra_dsi_set_timeout(struct tegra_dsi *dsi, unsigned long bclk,
diff --git a/drivers/gpu/host1x/mipi.c b/drivers/gpu/host1x/mipi.c
index e606464aa43c..2efe12dde8bc 100644
--- a/drivers/gpu/host1x/mipi.c
+++ b/drivers/gpu/host1x/mipi.c
@@ -293,19 +293,13 @@ int tegra_mipi_disable(struct tegra_mipi_device *dev)
 }
 EXPORT_SYMBOL(tegra_mipi_disable);
 
-int tegra_mipi_wait(struct tegra_mipi_device *device)
+int tegra_mipi_finish_calibration(struct tegra_mipi_device *device)
 {
 	struct tegra_mipi *mipi = device->mipi;
 	void __iomem *status_reg = mipi->regs + (MIPI_CAL_STATUS << 2);
 	u32 value;
 	int err;
 
-	err = clk_enable(device->mipi->clk);
-	if (err < 0)
-		return err;
-
-	mutex_lock(&device->mipi->lock);
-
 	err = readl_relaxed_poll_timeout(status_reg, value,
 					 !(value & MIPI_CAL_STATUS_ACTIVE) &&
 					 (value & MIPI_CAL_STATUS_DONE), 50,
@@ -315,9 +309,9 @@ int tegra_mipi_wait(struct tegra_mipi_device *device)
 
 	return err;
 }
-EXPORT_SYMBOL(tegra_mipi_wait);
+EXPORT_SYMBOL(tegra_mipi_finish_calibration);
 
-int tegra_mipi_calibrate(struct tegra_mipi_device *device)
+int tegra_mipi_start_calibration(struct tegra_mipi_device *device)
 {
 	const struct tegra_mipi_soc *soc = device->mipi->soc;
 	unsigned int i;
@@ -381,12 +375,16 @@ int tegra_mipi_calibrate(struct tegra_mipi_device *device)
 	value |= MIPI_CAL_CTRL_START;
 	tegra_mipi_writel(device->mipi, value, MIPI_CAL_CTRL);
 
-	mutex_unlock(&device->mipi->lock);
-	clk_disable(device->mipi->clk);
+	/*
+	 * Wait for min 72uS to let calibration logic finish calibration
+	 * sequence codes before waiting for pads idle state to apply the
+	 * results.
+	 */
+	usleep_range(75, 80);
 
 	return 0;
 }
-EXPORT_SYMBOL(tegra_mipi_calibrate);
+EXPORT_SYMBOL(tegra_mipi_start_calibration);
 
 static const struct tegra_mipi_pad tegra114_mipi_pads[] = {
 	{ .data = MIPI_CAL_CONFIG_CSIA },
diff --git a/include/linux/host1x.h b/include/linux/host1x.h
index 20c885d0bddc..ce59a6a6a008 100644
--- a/include/linux/host1x.h
+++ b/include/linux/host1x.h
@@ -333,7 +333,7 @@ struct tegra_mipi_device *tegra_mipi_request(struct device *device,
 void tegra_mipi_free(struct tegra_mipi_device *device);
 int tegra_mipi_enable(struct tegra_mipi_device *device);
 int tegra_mipi_disable(struct tegra_mipi_device *device);
-int tegra_mipi_calibrate(struct tegra_mipi_device *device);
-int tegra_mipi_wait(struct tegra_mipi_device *device);
+int tegra_mipi_start_calibration(struct tegra_mipi_device *device);
+int tegra_mipi_finish_calibration(struct tegra_mipi_device *device);
 
 #endif
-- 
cgit v1.2.3


From b6f3e21b928a8ae7959a0d79203b80bd70120768 Mon Sep 17 00:00:00 2001
From: Sebastian Reichel <sebastian.reichel@collabora.com>
Date: Wed, 26 Aug 2020 16:41:58 +0200
Subject: power: supply: smb347-charger: Drop pdata support

There are no platforms using the pdata support, so let's
drop it to simplify the driver.

Reviewed-by: Dmitry Osipenko <digetx@gmail.com>
Tested-by: Dmitry Osipenko <digetx@gmail.com>
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/smb347-charger.c | 287 +++++++++++++++++++---------------
 include/linux/power/smb347-charger.h  | 114 --------------
 2 files changed, 159 insertions(+), 242 deletions(-)
 delete mode 100644 include/linux/power/smb347-charger.h

(limited to 'include/linux')

diff --git a/drivers/power/supply/smb347-charger.c b/drivers/power/supply/smb347-charger.c
index ec68ab2bce27..b182727dfc90 100644
--- a/drivers/power/supply/smb347-charger.c
+++ b/drivers/power/supply/smb347-charger.c
@@ -17,9 +17,16 @@
 #include <linux/interrupt.h>
 #include <linux/i2c.h>
 #include <linux/power_supply.h>
-#include <linux/power/smb347-charger.h>
 #include <linux/regmap.h>
 
+#include <dt-bindings/power/summit,smb347-charger.h>
+
+/* Use the default compensation method */
+#define SMB3XX_SOFT_TEMP_COMPENSATE_DEFAULT -1
+
+/* Use default factory programmed value for hard/soft temperature limit */
+#define SMB3XX_TEMP_USE_DEFAULT		-273
+
 /*
  * Configuration registers. These are mirrored to volatile RAM and can be
  * written once %CMD_A_ALLOW_WRITE is set in %CMD_A register. They will be
@@ -129,7 +136,52 @@
  * @mains_online: is AC/DC input connected
  * @usb_online: is USB input connected
  * @charging_enabled: is charging enabled
- * @pdata: pointer to platform data
+ * @max_charge_current: maximum current (in uA) the battery can be charged
+ * @max_charge_voltage: maximum voltage (in uV) the battery can be charged
+ * @pre_charge_current: current (in uA) to use in pre-charging phase
+ * @termination_current: current (in uA) used to determine when the
+ *			 charging cycle terminates
+ * @pre_to_fast_voltage: voltage (in uV) treshold used for transitioning to
+ *			 pre-charge to fast charge mode
+ * @mains_current_limit: maximum input current drawn from AC/DC input (in uA)
+ * @usb_hc_current_limit: maximum input high current (in uA) drawn from USB
+ *			  input
+ * @chip_temp_threshold: die temperature where device starts limiting charge
+ *			 current [%100 - %130] (in degree C)
+ * @soft_cold_temp_limit: soft cold temperature limit [%0 - %15] (in degree C),
+ *			  granularity is 5 deg C.
+ * @soft_hot_temp_limit: soft hot temperature limit [%40 - %55] (in degree  C),
+ *			 granularity is 5 deg C.
+ * @hard_cold_temp_limit: hard cold temperature limit [%-5 - %10] (in degree C),
+ *			  granularity is 5 deg C.
+ * @hard_hot_temp_limit: hard hot temperature limit [%50 - %65] (in degree C),
+ *			 granularity is 5 deg C.
+ * @suspend_on_hard_temp_limit: suspend charging when hard limit is hit
+ * @soft_temp_limit_compensation: compensation method when soft temperature
+ *				  limit is hit
+ * @charge_current_compensation: current (in uA) for charging compensation
+ *				 current when temperature hits soft limits
+ * @use_mains: AC/DC input can be used
+ * @use_usb: USB input can be used
+ * @use_usb_otg: USB OTG output can be used (not implemented yet)
+ * @enable_control: how charging enable/disable is controlled
+ *		    (driver/pin controls)
+ *
+ * @use_main, @use_usb, and @use_usb_otg are means to enable/disable
+ * hardware support for these. This is useful when we want to have for
+ * example OTG charging controlled via OTG transceiver driver and not by
+ * the SMB347 hardware.
+ *
+ * Hard and soft temperature limit values are given as described in the
+ * device data sheet and assuming NTC beta value is %3750. Even if this is
+ * not the case, these values should be used. They can be mapped to the
+ * corresponding NTC beta values with the help of table %2 in the data
+ * sheet. So for example if NTC beta is %3375 and we want to program hard
+ * hot limit to be %53 deg C, @hard_hot_temp_limit should be set to %50.
+ *
+ * If zero value is given in any of the current and voltage values, the
+ * factory programmed default will be used. For soft/hard temperature
+ * values, pass in %SMB3XX_TEMP_USE_DEFAULT instead.
  */
 struct smb347_charger {
 	struct device		*dev;
@@ -140,7 +192,26 @@ struct smb347_charger {
 	bool			mains_online;
 	bool			usb_online;
 	bool			charging_enabled;
-	const struct smb347_charger_platform_data *pdata;
+
+	unsigned int		max_charge_current;
+	unsigned int		max_charge_voltage;
+	unsigned int		pre_charge_current;
+	unsigned int		termination_current;
+	unsigned int		pre_to_fast_voltage;
+	unsigned int		mains_current_limit;
+	unsigned int		usb_hc_current_limit;
+	unsigned int		chip_temp_threshold;
+	int			soft_cold_temp_limit;
+	int			soft_hot_temp_limit;
+	int			hard_cold_temp_limit;
+	int			hard_hot_temp_limit;
+	bool			suspend_on_hard_temp_limit;
+	unsigned int		soft_temp_limit_compensation;
+	unsigned int		charge_current_compensation;
+	bool			use_mains;
+	bool			use_usb;
+	bool			use_usb_otg;
+	unsigned int		enable_control;
 };
 
 enum smb_charger_chipid {
@@ -235,9 +306,9 @@ static int smb347_update_ps_status(struct smb347_charger *smb)
 	 * Dc and usb are set depending on whether they are enabled in
 	 * platform data _and_ whether corresponding undervoltage is set.
 	 */
-	if (smb->pdata->use_mains)
+	if (smb->use_mains)
 		dc = !(val & IRQSTAT_E_DCIN_UV_STAT);
-	if (smb->pdata->use_usb)
+	if (smb->use_usb)
 		usb = !(val & IRQSTAT_E_USBIN_UV_STAT);
 
 	ret = smb->mains_online != dc || smb->usb_online != usb;
@@ -287,7 +358,7 @@ static int smb347_charging_set(struct smb347_charger *smb, bool enable)
 {
 	int ret = 0;
 
-	if (smb->pdata->enable_control != SMB347_CHG_ENABLE_SW) {
+	if (smb->enable_control != SMB3XX_CHG_ENABLE_SW) {
 		dev_dbg(smb->dev, "charging enable/disable in SW disabled\n");
 		return 0;
 	}
@@ -339,9 +410,9 @@ static int smb347_set_charge_current(struct smb347_charger *smb)
 	unsigned int id = smb->id;
 	int ret;
 
-	if (smb->pdata->max_charge_current) {
+	if (smb->max_charge_current) {
 		ret = current_to_hw(fcc_tbl[id], ARRAY_SIZE(fcc_tbl[id]),
-				    smb->pdata->max_charge_current);
+				    smb->max_charge_current);
 		if (ret < 0)
 			return ret;
 
@@ -352,9 +423,9 @@ static int smb347_set_charge_current(struct smb347_charger *smb)
 			return ret;
 	}
 
-	if (smb->pdata->pre_charge_current) {
+	if (smb->pre_charge_current) {
 		ret = current_to_hw(pcc_tbl[id], ARRAY_SIZE(pcc_tbl[id]),
-				    smb->pdata->pre_charge_current);
+				    smb->pre_charge_current);
 		if (ret < 0)
 			return ret;
 
@@ -365,9 +436,9 @@ static int smb347_set_charge_current(struct smb347_charger *smb)
 			return ret;
 	}
 
-	if (smb->pdata->termination_current) {
+	if (smb->termination_current) {
 		ret = current_to_hw(tc_tbl[id], ARRAY_SIZE(tc_tbl[id]),
-				    smb->pdata->termination_current);
+				    smb->termination_current);
 		if (ret < 0)
 			return ret;
 
@@ -385,9 +456,9 @@ static int smb347_set_current_limits(struct smb347_charger *smb)
 	unsigned int id = smb->id;
 	int ret;
 
-	if (smb->pdata->mains_current_limit) {
+	if (smb->mains_current_limit) {
 		ret = current_to_hw(icl_tbl[id], ARRAY_SIZE(icl_tbl[id]),
-				    smb->pdata->mains_current_limit);
+				    smb->mains_current_limit);
 		if (ret < 0)
 			return ret;
 
@@ -398,9 +469,9 @@ static int smb347_set_current_limits(struct smb347_charger *smb)
 			return ret;
 	}
 
-	if (smb->pdata->usb_hc_current_limit) {
+	if (smb->usb_hc_current_limit) {
 		ret = current_to_hw(icl_tbl[id], ARRAY_SIZE(icl_tbl[id]),
-				    smb->pdata->usb_hc_current_limit);
+				    smb->usb_hc_current_limit);
 		if (ret < 0)
 			return ret;
 
@@ -417,8 +488,8 @@ static int smb347_set_voltage_limits(struct smb347_charger *smb)
 {
 	int ret;
 
-	if (smb->pdata->pre_to_fast_voltage) {
-		ret = smb->pdata->pre_to_fast_voltage;
+	if (smb->pre_to_fast_voltage) {
+		ret = smb->pre_to_fast_voltage;
 
 		/* uV */
 		ret = clamp_val(ret, 2400000, 3000000) - 2400000;
@@ -431,8 +502,8 @@ static int smb347_set_voltage_limits(struct smb347_charger *smb)
 			return ret;
 	}
 
-	if (smb->pdata->max_charge_voltage) {
-		ret = smb->pdata->max_charge_voltage;
+	if (smb->max_charge_voltage) {
+		ret = smb->max_charge_voltage;
 
 		/* uV */
 		ret = clamp_val(ret, 3500000, 4500000) - 3500000;
@@ -454,8 +525,8 @@ static int smb347_set_temp_limits(struct smb347_charger *smb)
 	int ret = 0;
 	int val;
 
-	if (smb->pdata->chip_temp_threshold) {
-		val = smb->pdata->chip_temp_threshold;
+	if (smb->chip_temp_threshold) {
+		val = smb->chip_temp_threshold;
 
 		/* degree C */
 		val = clamp_val(val, 100, 130) - 100;
@@ -468,8 +539,8 @@ static int smb347_set_temp_limits(struct smb347_charger *smb)
 			return ret;
 	}
 
-	if (smb->pdata->soft_cold_temp_limit != SMB347_TEMP_USE_DEFAULT) {
-		val = smb->pdata->soft_cold_temp_limit;
+	if (smb->soft_cold_temp_limit != SMB3XX_TEMP_USE_DEFAULT) {
+		val = smb->soft_cold_temp_limit;
 
 		val = clamp_val(val, 0, 15);
 		val /= 5;
@@ -485,8 +556,8 @@ static int smb347_set_temp_limits(struct smb347_charger *smb)
 		enable_therm_monitor = true;
 	}
 
-	if (smb->pdata->soft_hot_temp_limit != SMB347_TEMP_USE_DEFAULT) {
-		val = smb->pdata->soft_hot_temp_limit;
+	if (smb->soft_hot_temp_limit != SMB3XX_TEMP_USE_DEFAULT) {
+		val = smb->soft_hot_temp_limit;
 
 		val = clamp_val(val, 40, 55) - 40;
 		val /= 5;
@@ -500,8 +571,8 @@ static int smb347_set_temp_limits(struct smb347_charger *smb)
 		enable_therm_monitor = true;
 	}
 
-	if (smb->pdata->hard_cold_temp_limit != SMB347_TEMP_USE_DEFAULT) {
-		val = smb->pdata->hard_cold_temp_limit;
+	if (smb->hard_cold_temp_limit != SMB3XX_TEMP_USE_DEFAULT) {
+		val = smb->hard_cold_temp_limit;
 
 		val = clamp_val(val, -5, 10) + 5;
 		val /= 5;
@@ -517,8 +588,8 @@ static int smb347_set_temp_limits(struct smb347_charger *smb)
 		enable_therm_monitor = true;
 	}
 
-	if (smb->pdata->hard_hot_temp_limit != SMB347_TEMP_USE_DEFAULT) {
-		val = smb->pdata->hard_hot_temp_limit;
+	if (smb->hard_hot_temp_limit != SMB3XX_TEMP_USE_DEFAULT) {
+		val = smb->hard_hot_temp_limit;
 
 		val = clamp_val(val, 50, 65) - 50;
 		val /= 5;
@@ -549,16 +620,16 @@ static int smb347_set_temp_limits(struct smb347_charger *smb)
 			return ret;
 	}
 
-	if (smb->pdata->suspend_on_hard_temp_limit) {
+	if (smb->suspend_on_hard_temp_limit) {
 		ret = regmap_update_bits(smb->regmap, CFG_SYSOK,
 				 CFG_SYSOK_SUSPEND_HARD_LIMIT_DISABLED, 0);
 		if (ret < 0)
 			return ret;
 	}
 
-	if (smb->pdata->soft_temp_limit_compensation !=
-	    SMB347_SOFT_TEMP_COMPENSATE_DEFAULT) {
-		val = smb->pdata->soft_temp_limit_compensation & 0x3;
+	if (smb->soft_temp_limit_compensation !=
+	    SMB3XX_SOFT_TEMP_COMPENSATE_DEFAULT) {
+		val = smb->soft_temp_limit_compensation & 0x3;
 
 		ret = regmap_update_bits(smb->regmap, CFG_THERM,
 				 CFG_THERM_SOFT_HOT_COMPENSATION_MASK,
@@ -573,9 +644,9 @@ static int smb347_set_temp_limits(struct smb347_charger *smb)
 			return ret;
 	}
 
-	if (smb->pdata->charge_current_compensation) {
+	if (smb->charge_current_compensation) {
 		val = current_to_hw(ccc_tbl[id], ARRAY_SIZE(ccc_tbl[id]),
-				    smb->pdata->charge_current_compensation);
+				    smb->charge_current_compensation);
 		if (val < 0)
 			return val;
 
@@ -634,7 +705,7 @@ static int smb347_hw_init(struct smb347_charger *smb)
 		goto fail;
 
 	/* If USB charging is disabled we put the USB in suspend mode */
-	if (!smb->pdata->use_usb) {
+	if (!smb->use_usb) {
 		ret = regmap_update_bits(smb->regmap, CMD_A,
 					 CMD_A_SUSPEND_ENABLED,
 					 CMD_A_SUSPEND_ENABLED);
@@ -647,7 +718,7 @@ static int smb347_hw_init(struct smb347_charger *smb)
 	 * support for driving VBUS. Otherwise we disable it.
 	 */
 	ret = regmap_update_bits(smb->regmap, CFG_OTHER, CFG_OTHER_RID_MASK,
-		smb->pdata->use_usb_otg ? CFG_OTHER_RID_ENABLED_AUTO_OTG : 0);
+		smb->use_usb_otg ? CFG_OTHER_RID_ENABLED_AUTO_OTG : 0);
 	if (ret < 0)
 		goto fail;
 
@@ -656,11 +727,11 @@ static int smb347_hw_init(struct smb347_charger *smb)
 	 * command register unless pin control is specified in the platform
 	 * data.
 	 */
-	switch (smb->pdata->enable_control) {
-	case SMB347_CHG_ENABLE_PIN_ACTIVE_LOW:
+	switch (smb->enable_control) {
+	case SMB3XX_CHG_ENABLE_PIN_ACTIVE_LOW:
 		val = CFG_PIN_EN_CTRL_ACTIVE_LOW;
 		break;
-	case SMB347_CHG_ENABLE_PIN_ACTIVE_HIGH:
+	case SMB3XX_CHG_ENABLE_PIN_ACTIVE_HIGH:
 		val = CFG_PIN_EN_CTRL_ACTIVE_HIGH;
 		break;
 	default:
@@ -729,9 +800,9 @@ static irqreturn_t smb347_interrupt(int irq, void *data)
 	 */
 	if (stat_c & STAT_C_CHARGER_ERROR) {
 		dev_err(smb->dev, "charging stopped due to charger error\n");
-		if (smb->pdata->use_mains)
+		if (smb->use_mains)
 			power_supply_changed(smb->mains);
-		if (smb->pdata->use_usb)
+		if (smb->use_usb)
 			power_supply_changed(smb->usb);
 		handled = true;
 	}
@@ -743,9 +814,9 @@ static irqreturn_t smb347_interrupt(int irq, void *data)
 	 */
 	if (irqstat_c & (IRQSTAT_C_TERMINATION_IRQ | IRQSTAT_C_TAPER_IRQ)) {
 		if (irqstat_c & IRQSTAT_C_TERMINATION_STAT) {
-			if (smb->pdata->use_mains)
+			if (smb->use_mains)
 				power_supply_changed(smb->mains);
-			if (smb->pdata->use_usb)
+			if (smb->use_usb)
 				power_supply_changed(smb->usb);
 		}
 		dev_dbg(smb->dev, "going to HW maintenance mode\n");
@@ -761,9 +832,9 @@ static irqreturn_t smb347_interrupt(int irq, void *data)
 
 		if (irqstat_d & IRQSTAT_D_CHARGE_TIMEOUT_STAT)
 			dev_warn(smb->dev, "charging stopped due to timeout\n");
-		if (smb->pdata->use_mains)
+		if (smb->use_mains)
 			power_supply_changed(smb->mains);
-		if (smb->pdata->use_usb)
+		if (smb->use_usb)
 			power_supply_changed(smb->usb);
 		handled = true;
 	}
@@ -775,9 +846,9 @@ static irqreturn_t smb347_interrupt(int irq, void *data)
 	if (irqstat_e & (IRQSTAT_E_USBIN_UV_IRQ | IRQSTAT_E_DCIN_UV_IRQ)) {
 		if (smb347_update_ps_status(smb) > 0) {
 			smb347_start_stop_charging(smb);
-			if (smb->pdata->use_mains)
+			if (smb->use_mains)
 				power_supply_changed(smb->mains);
-			if (smb->pdata->use_usb)
+			if (smb->use_usb)
 				power_supply_changed(smb->usb);
 		}
 		handled = true;
@@ -832,25 +903,10 @@ static inline int smb347_irq_disable(struct smb347_charger *smb)
 static int smb347_irq_init(struct smb347_charger *smb,
 			   struct i2c_client *client)
 {
-	const struct smb347_charger_platform_data *pdata = smb->pdata;
-	unsigned long irqflags = IRQF_ONESHOT;
 	int ret;
 
-	/* Requesting GPIO for IRQ is only needed in non-DT way */
-	if (!client->irq) {
-		int irq = gpio_to_irq(pdata->irq_gpio);
-
-		ret = devm_gpio_request_one(smb->dev, pdata->irq_gpio,
-					    GPIOF_IN, client->name);
-		if (ret < 0)
-			return ret;
-
-		irqflags |= IRQF_TRIGGER_FALLING;
-		client->irq = irq;
-	}
-
 	ret = devm_request_threaded_irq(smb->dev, client->irq, NULL,
-					smb347_interrupt, irqflags,
+					smb347_interrupt, IRQF_ONESHOT,
 					client->name, smb);
 	if (ret < 0)
 		return ret;
@@ -1118,56 +1174,52 @@ static bool smb347_readable_reg(struct device *dev, unsigned int reg)
 	return smb347_volatile_reg(dev, reg);
 }
 
-static void smb347_dt_parse_pdata(struct device_node *np,
-				  struct smb347_charger_platform_data *pdata)
+static void smb347_dt_parse_dev_info(struct smb347_charger *smb)
 {
-	pdata->soft_temp_limit_compensation =
-					SMB347_SOFT_TEMP_COMPENSATE_DEFAULT;
+	struct device_node *np = smb->dev->of_node;
+
+	smb->soft_temp_limit_compensation =
+					SMB3XX_SOFT_TEMP_COMPENSATE_DEFAULT;
 	/*
 	 * These properties come from the battery info, still we need to
 	 * pre-initialize the values. See smb347_get_battery_info() below.
 	 */
-	pdata->soft_cold_temp_limit = SMB347_TEMP_USE_DEFAULT;
-	pdata->hard_cold_temp_limit = SMB347_TEMP_USE_DEFAULT;
-	pdata->soft_hot_temp_limit  = SMB347_TEMP_USE_DEFAULT;
-	pdata->hard_hot_temp_limit  = SMB347_TEMP_USE_DEFAULT;
+	smb->soft_cold_temp_limit = SMB3XX_TEMP_USE_DEFAULT;
+	smb->hard_cold_temp_limit = SMB3XX_TEMP_USE_DEFAULT;
+	smb->soft_hot_temp_limit  = SMB3XX_TEMP_USE_DEFAULT;
+	smb->hard_hot_temp_limit  = SMB3XX_TEMP_USE_DEFAULT;
 
 	/* Charging constraints */
 	of_property_read_u32(np, "summit,fast-voltage-threshold-microvolt",
-			     &pdata->pre_to_fast_voltage);
+			     &smb->pre_to_fast_voltage);
 	of_property_read_u32(np, "summit,mains-current-limit-microamp",
-			     &pdata->mains_current_limit);
+			     &smb->mains_current_limit);
 	of_property_read_u32(np, "summit,usb-current-limit-microamp",
-			     &pdata->usb_hc_current_limit);
+			     &smb->usb_hc_current_limit);
 
 	/* For thermometer monitoring */
 	of_property_read_u32(np, "summit,chip-temperature-threshold-celsius",
-			     &pdata->chip_temp_threshold);
+			     &smb->chip_temp_threshold);
 	of_property_read_u32(np, "summit,soft-compensation-method",
-			     &pdata->soft_temp_limit_compensation);
+			     &smb->soft_temp_limit_compensation);
 	of_property_read_u32(np, "summit,charge-current-compensation-microamp",
-			     &pdata->charge_current_compensation);
+			     &smb->charge_current_compensation);
 
 	/* Supported charging mode */
-	pdata->use_mains =
+	smb->use_mains =
 		of_property_read_bool(np, "summit,enable-mains-charging");
-	pdata->use_usb =
+	smb->use_usb =
 		of_property_read_bool(np, "summit,enable-usb-charging");
-	pdata->use_usb_otg =
+	smb->use_usb_otg =
 		of_property_read_bool(np, "summit,enable-otg-charging");
 
 	/* Select charging control */
 	of_property_read_u32(np, "summit,enable-charge-control",
-			     &pdata->enable_control);
-
-	/* Interrupt support is optional */
-	if (!of_find_property(np, "interrupts", NULL))
-		pdata->irq_gpio = -1;
+			     &smb->enable_control);
 }
 
 static int smb347_get_battery_info(struct smb347_charger *smb)
 {
-	struct smb347_charger_platform_data *pdata = (void *)smb->pdata;
 	struct power_supply_battery_info info = {};
 	struct power_supply *supply;
 	int err;
@@ -1184,53 +1236,37 @@ static int smb347_get_battery_info(struct smb347_charger *smb)
 		return err;
 
 	if (info.constant_charge_current_max_ua != -EINVAL)
-		pdata->max_charge_current = info.constant_charge_current_max_ua;
+		smb->max_charge_current = info.constant_charge_current_max_ua;
 
 	if (info.constant_charge_voltage_max_uv != -EINVAL)
-		pdata->max_charge_voltage = info.constant_charge_voltage_max_uv;
+		smb->max_charge_voltage = info.constant_charge_voltage_max_uv;
 
 	if (info.precharge_current_ua != -EINVAL)
-		pdata->pre_charge_current = info.precharge_current_ua;
+		smb->pre_charge_current = info.precharge_current_ua;
 
 	if (info.charge_term_current_ua != -EINVAL)
-		pdata->termination_current = info.charge_term_current_ua;
+		smb->termination_current = info.charge_term_current_ua;
 
 	if (info.temp_alert_min != INT_MIN)
-		pdata->soft_cold_temp_limit = info.temp_alert_min;
+		smb->soft_cold_temp_limit = info.temp_alert_min;
 
 	if (info.temp_alert_max != INT_MAX)
-		pdata->soft_hot_temp_limit = info.temp_alert_max;
+		smb->soft_hot_temp_limit = info.temp_alert_max;
 
 	if (info.temp_min != INT_MIN)
-		pdata->hard_cold_temp_limit = info.temp_min;
+		smb->hard_cold_temp_limit = info.temp_min;
 
 	if (info.temp_max != INT_MAX)
-		pdata->hard_hot_temp_limit = info.temp_max;
+		smb->hard_hot_temp_limit = info.temp_max;
 
 	/* Suspend when battery temperature is outside hard limits */
-	if (pdata->hard_cold_temp_limit != SMB347_TEMP_USE_DEFAULT ||
-	    pdata->hard_hot_temp_limit != SMB347_TEMP_USE_DEFAULT)
-		pdata->suspend_on_hard_temp_limit = true;
+	if (smb->hard_cold_temp_limit != SMB3XX_TEMP_USE_DEFAULT ||
+	    smb->hard_hot_temp_limit != SMB3XX_TEMP_USE_DEFAULT)
+		smb->suspend_on_hard_temp_limit = true;
 
 	return 0;
 }
 
-static struct smb347_charger_platform_data
-			*smb347_get_platdata(struct device *dev)
-{
-	struct smb347_charger_platform_data *pdata;
-
-	if (dev->of_node) {
-		pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL);
-		if (pdata)
-			smb347_dt_parse_pdata(dev->of_node, pdata);
-	} else {
-		pdata = dev_get_platdata(dev);
-	}
-
-	return pdata;
-}
-
 static const struct regmap_config smb347_regmap = {
 	.reg_bits	= 8,
 	.val_bits	= 8,
@@ -1266,18 +1302,13 @@ static int smb347_probe(struct i2c_client *client,
 	smb = devm_kzalloc(dev, sizeof(*smb), GFP_KERNEL);
 	if (!smb)
 		return -ENOMEM;
-
-	smb->pdata = smb347_get_platdata(dev);
-	if (!smb->pdata)
-		return -ENODEV;
-
-	if (!smb->pdata->use_mains && !smb->pdata->use_usb)
-		return -EINVAL;
-
-	i2c_set_clientdata(client, smb);
-
 	smb->dev = &client->dev;
 	smb->id = id->driver_data;
+	i2c_set_clientdata(client, smb);
+
+	smb347_dt_parse_dev_info(smb);
+	if (!smb->use_mains && !smb->use_usb)
+		return -EINVAL;
 
 	smb->regmap = devm_regmap_init_i2c(client, &smb347_regmap);
 	if (IS_ERR(smb->regmap))
@@ -1285,14 +1316,14 @@ static int smb347_probe(struct i2c_client *client,
 
 	mains_usb_cfg.drv_data = smb;
 	mains_usb_cfg.of_node = dev->of_node;
-	if (smb->pdata->use_mains) {
+	if (smb->use_mains) {
 		smb->mains = devm_power_supply_register(dev, &smb347_mains_desc,
 							&mains_usb_cfg);
 		if (IS_ERR(smb->mains))
 			return PTR_ERR(smb->mains);
 	}
 
-	if (smb->pdata->use_usb) {
+	if (smb->use_usb) {
 		smb->usb = devm_power_supply_register(dev, &smb347_usb_desc,
 						      &mains_usb_cfg);
 		if (IS_ERR(smb->usb))
@@ -1311,7 +1342,7 @@ static int smb347_probe(struct i2c_client *client,
 	 * Interrupt pin is optional. If it is connected, we setup the
 	 * interrupt support here.
 	 */
-	if (smb->pdata->irq_gpio >= 0) {
+	if (client->irq) {
 		ret = smb347_irq_init(smb, client);
 		if (ret < 0) {
 			dev_warn(dev, "failed to initialize IRQ: %d\n", ret);
diff --git a/include/linux/power/smb347-charger.h b/include/linux/power/smb347-charger.h
deleted file mode 100644
index e0b687a4d20c..000000000000
--- a/include/linux/power/smb347-charger.h
+++ /dev/null
@@ -1,114 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Summit Microelectronics SMB347 Battery Charger Driver
- *
- * Copyright (C) 2011, Intel Corporation
- *
- * Authors: Bruce E. Robertson <bruce.e.robertson@intel.com>
- *          Mika Westerberg <mika.westerberg@linux.intel.com>
- */
-
-#ifndef SMB347_CHARGER_H
-#define SMB347_CHARGER_H
-
-#include <linux/types.h>
-#include <linux/power_supply.h>
-
-enum {
-	/* use the default compensation method */
-	SMB347_SOFT_TEMP_COMPENSATE_DEFAULT = -1,
-
-	SMB347_SOFT_TEMP_COMPENSATE_NONE,
-	SMB347_SOFT_TEMP_COMPENSATE_CURRENT,
-	SMB347_SOFT_TEMP_COMPENSATE_VOLTAGE,
-};
-
-/* Use default factory programmed value for hard/soft temperature limit */
-#define SMB347_TEMP_USE_DEFAULT		-273
-
-/*
- * Charging enable can be controlled by software (via i2c) by
- * smb347-charger driver or by EN pin (active low/high).
- */
-enum smb347_chg_enable {
-	SMB347_CHG_ENABLE_SW,
-	SMB347_CHG_ENABLE_PIN_ACTIVE_LOW,
-	SMB347_CHG_ENABLE_PIN_ACTIVE_HIGH,
-};
-
-/**
- * struct smb347_charger_platform_data - platform data for SMB347 charger
- * @battery_info: Information about the battery
- * @max_charge_current: maximum current (in uA) the battery can be charged
- * @max_charge_voltage: maximum voltage (in uV) the battery can be charged
- * @pre_charge_current: current (in uA) to use in pre-charging phase
- * @termination_current: current (in uA) used to determine when the
- *			 charging cycle terminates
- * @pre_to_fast_voltage: voltage (in uV) treshold used for transitioning to
- *			 pre-charge to fast charge mode
- * @mains_current_limit: maximum input current drawn from AC/DC input (in uA)
- * @usb_hc_current_limit: maximum input high current (in uA) drawn from USB
- *			  input
- * @chip_temp_threshold: die temperature where device starts limiting charge
- *			 current [%100 - %130] (in degree C)
- * @soft_cold_temp_limit: soft cold temperature limit [%0 - %15] (in degree C),
- *			  granularity is 5 deg C.
- * @soft_hot_temp_limit: soft hot temperature limit [%40 - %55] (in degree  C),
- *			 granularity is 5 deg C.
- * @hard_cold_temp_limit: hard cold temperature limit [%-5 - %10] (in degree C),
- *			  granularity is 5 deg C.
- * @hard_hot_temp_limit: hard hot temperature limit [%50 - %65] (in degree C),
- *			 granularity is 5 deg C.
- * @suspend_on_hard_temp_limit: suspend charging when hard limit is hit
- * @soft_temp_limit_compensation: compensation method when soft temperature
- *				  limit is hit
- * @charge_current_compensation: current (in uA) for charging compensation
- *				 current when temperature hits soft limits
- * @use_mains: AC/DC input can be used
- * @use_usb: USB input can be used
- * @use_usb_otg: USB OTG output can be used (not implemented yet)
- * @irq_gpio: GPIO number used for interrupts (%-1 if not used)
- * @enable_control: how charging enable/disable is controlled
- *		    (driver/pin controls)
- *
- * @use_main, @use_usb, and @use_usb_otg are means to enable/disable
- * hardware support for these. This is useful when we want to have for
- * example OTG charging controlled via OTG transceiver driver and not by
- * the SMB347 hardware.
- *
- * Hard and soft temperature limit values are given as described in the
- * device data sheet and assuming NTC beta value is %3750. Even if this is
- * not the case, these values should be used. They can be mapped to the
- * corresponding NTC beta values with the help of table %2 in the data
- * sheet. So for example if NTC beta is %3375 and we want to program hard
- * hot limit to be %53 deg C, @hard_hot_temp_limit should be set to %50.
- *
- * If zero value is given in any of the current and voltage values, the
- * factory programmed default will be used. For soft/hard temperature
- * values, pass in %SMB347_TEMP_USE_DEFAULT instead.
- */
-struct smb347_charger_platform_data {
-	struct power_supply_info battery_info;
-	unsigned int	max_charge_current;
-	unsigned int	max_charge_voltage;
-	unsigned int	pre_charge_current;
-	unsigned int	termination_current;
-	unsigned int	pre_to_fast_voltage;
-	unsigned int	mains_current_limit;
-	unsigned int	usb_hc_current_limit;
-	unsigned int	chip_temp_threshold;
-	int		soft_cold_temp_limit;
-	int		soft_hot_temp_limit;
-	int		hard_cold_temp_limit;
-	int		hard_hot_temp_limit;
-	bool		suspend_on_hard_temp_limit;
-	unsigned int	soft_temp_limit_compensation;
-	unsigned int	charge_current_compensation;
-	bool		use_mains;
-	bool		use_usb;
-	bool		use_usb_otg;
-	int		irq_gpio;
-	enum smb347_chg_enable enable_control;
-};
-
-#endif /* SMB347_CHARGER_H */
-- 
cgit v1.2.3


From f4d05259213ff1e91f767c91dcab455f68308fac Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Thu, 27 Aug 2020 18:18:06 -0700
Subject: bpf: Add map_meta_equal map ops

Some properties of the inner map is used in the verification time.
When an inner map is inserted to an outer map at runtime,
bpf_map_meta_equal() is currently used to ensure those properties
of the inserting inner map stays the same as the verification
time.

In particular, the current bpf_map_meta_equal() checks max_entries which
turns out to be too restrictive for most of the maps which do not use
max_entries during the verification time.  It limits the use case that
wants to replace a smaller inner map with a larger inner map.  There are
some maps do use max_entries during verification though.  For example,
the map_gen_lookup in array_map_ops uses the max_entries to generate
the inline lookup code.

To accommodate differences between maps, the map_meta_equal is added
to bpf_map_ops.  Each map-type can decide what to check when its
map is used as an inner map during runtime.

Also, some map types cannot be used as an inner map and they are
currently black listed in bpf_map_meta_alloc() in map_in_map.c.
It is not unusual that the new map types may not aware that such
blacklist exists.  This patch enforces an explicit opt-in
and only allows a map to be used as an inner map if it has
implemented the map_meta_equal ops.  It is based on the
discussion in [1].

All maps that support inner map has its map_meta_equal points
to bpf_map_meta_equal in this patch.  A later patch will
relax the max_entries check for most maps.  bpf_types.h
counts 28 map types.  This patch adds 23 ".map_meta_equal"
by using coccinelle.  -5 for
	BPF_MAP_TYPE_PROG_ARRAY
	BPF_MAP_TYPE_(PERCPU)_CGROUP_STORAGE
	BPF_MAP_TYPE_STRUCT_OPS
	BPF_MAP_TYPE_ARRAY_OF_MAPS
	BPF_MAP_TYPE_HASH_OF_MAPS

The "if (inner_map->inner_map_meta)" check in bpf_map_meta_alloc()
is moved such that the same error is returned.

[1]: https://lore.kernel.org/bpf/20200522022342.899756-1-kafai@fb.com/

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20200828011806.1970400-1-kafai@fb.com
---
 include/linux/bpf.h            | 16 ++++++++++++++++
 kernel/bpf/arraymap.c          |  9 +++++++++
 kernel/bpf/bpf_inode_storage.c |  1 +
 kernel/bpf/cpumap.c            |  1 +
 kernel/bpf/devmap.c            |  2 ++
 kernel/bpf/hashtab.c           |  4 ++++
 kernel/bpf/lpm_trie.c          |  1 +
 kernel/bpf/map_in_map.c        | 21 ++++++++-------------
 kernel/bpf/map_in_map.h        |  2 --
 kernel/bpf/queue_stack_maps.c  |  2 ++
 kernel/bpf/reuseport_array.c   |  1 +
 kernel/bpf/ringbuf.c           |  1 +
 kernel/bpf/stackmap.c          |  1 +
 kernel/bpf/syscall.c           |  1 +
 net/core/bpf_sk_storage.c      |  1 +
 net/core/sock_map.c            |  2 ++
 net/xdp/xskmap.c               |  1 +
 17 files changed, 52 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index a6131d95e31e..dbba82a80087 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -112,6 +112,19 @@ struct bpf_map_ops {
 	void (*map_local_storage_uncharge)(struct bpf_local_storage_map *smap,
 					   void *owner, u32 size);
 	struct bpf_local_storage __rcu ** (*map_owner_storage_ptr)(void *owner);
+
+	/* map_meta_equal must be implemented for maps that can be
+	 * used as an inner map.  It is a runtime check to ensure
+	 * an inner map can be inserted to an outer map.
+	 *
+	 * Some properties of the inner map has been used during the
+	 * verification time.  When inserting an inner map at the runtime,
+	 * map_meta_equal has to ensure the inserting map has the same
+	 * properties that the verifier has used earlier.
+	 */
+	bool (*map_meta_equal)(const struct bpf_map *meta0,
+			       const struct bpf_map *meta1);
+
 	/* BTF name and id of struct allocated by map_alloc */
 	const char * const map_btf_name;
 	int *map_btf_id;
@@ -235,6 +248,9 @@ int map_check_no_btf(const struct bpf_map *map,
 		     const struct btf_type *key_type,
 		     const struct btf_type *value_type);
 
+bool bpf_map_meta_equal(const struct bpf_map *meta0,
+			const struct bpf_map *meta1);
+
 extern const struct bpf_map_ops bpf_map_offload_ops;
 
 /* function argument constraints */
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 8ff419b632a6..40d1f7f94307 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -625,6 +625,7 @@ static const struct bpf_iter_seq_info iter_seq_info = {
 
 static int array_map_btf_id;
 const struct bpf_map_ops array_map_ops = {
+	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = array_map_alloc_check,
 	.map_alloc = array_map_alloc,
 	.map_free = array_map_free,
@@ -647,6 +648,7 @@ const struct bpf_map_ops array_map_ops = {
 
 static int percpu_array_map_btf_id;
 const struct bpf_map_ops percpu_array_map_ops = {
+	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = array_map_alloc_check,
 	.map_alloc = array_map_alloc,
 	.map_free = array_map_free,
@@ -1003,6 +1005,11 @@ static void prog_array_map_free(struct bpf_map *map)
 	fd_array_map_free(map);
 }
 
+/* prog_array->aux->{type,jited} is a runtime binding.
+ * Doing static check alone in the verifier is not enough.
+ * Thus, prog_array_map cannot be used as an inner_map
+ * and map_meta_equal is not implemented.
+ */
 static int prog_array_map_btf_id;
 const struct bpf_map_ops prog_array_map_ops = {
 	.map_alloc_check = fd_array_map_alloc_check,
@@ -1101,6 +1108,7 @@ static void perf_event_fd_array_release(struct bpf_map *map,
 
 static int perf_event_array_map_btf_id;
 const struct bpf_map_ops perf_event_array_map_ops = {
+	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = fd_array_map_alloc_check,
 	.map_alloc = array_map_alloc,
 	.map_free = fd_array_map_free,
@@ -1137,6 +1145,7 @@ static void cgroup_fd_array_free(struct bpf_map *map)
 
 static int cgroup_array_map_btf_id;
 const struct bpf_map_ops cgroup_array_map_ops = {
+	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = fd_array_map_alloc_check,
 	.map_alloc = array_map_alloc,
 	.map_free = cgroup_fd_array_free,
diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c
index f3a44e929447..75be02799c0f 100644
--- a/kernel/bpf/bpf_inode_storage.c
+++ b/kernel/bpf/bpf_inode_storage.c
@@ -235,6 +235,7 @@ static void inode_storage_map_free(struct bpf_map *map)
 
 static int inode_storage_map_btf_id;
 const struct bpf_map_ops inode_storage_map_ops = {
+	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = bpf_local_storage_map_alloc_check,
 	.map_alloc = inode_storage_map_alloc,
 	.map_free = inode_storage_map_free,
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index f1c46529929b..8d2a8623d2a7 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -658,6 +658,7 @@ static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
 
 static int cpu_map_btf_id;
 const struct bpf_map_ops cpu_map_ops = {
+	.map_meta_equal		= bpf_map_meta_equal,
 	.map_alloc		= cpu_map_alloc,
 	.map_free		= cpu_map_free,
 	.map_delete_elem	= cpu_map_delete_elem,
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 10abb06065bb..a42052b85c35 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -751,6 +751,7 @@ static int dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value,
 
 static int dev_map_btf_id;
 const struct bpf_map_ops dev_map_ops = {
+	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc = dev_map_alloc,
 	.map_free = dev_map_free,
 	.map_get_next_key = dev_map_get_next_key,
@@ -764,6 +765,7 @@ const struct bpf_map_ops dev_map_ops = {
 
 static int dev_map_hash_map_btf_id;
 const struct bpf_map_ops dev_map_hash_ops = {
+	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc = dev_map_alloc,
 	.map_free = dev_map_free,
 	.map_get_next_key = dev_map_hash_get_next_key,
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 78dfff6a501b..ad80f45774e7 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -1810,6 +1810,7 @@ static const struct bpf_iter_seq_info iter_seq_info = {
 
 static int htab_map_btf_id;
 const struct bpf_map_ops htab_map_ops = {
+	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = htab_map_alloc_check,
 	.map_alloc = htab_map_alloc,
 	.map_free = htab_map_free,
@@ -1827,6 +1828,7 @@ const struct bpf_map_ops htab_map_ops = {
 
 static int htab_lru_map_btf_id;
 const struct bpf_map_ops htab_lru_map_ops = {
+	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = htab_map_alloc_check,
 	.map_alloc = htab_map_alloc,
 	.map_free = htab_map_free,
@@ -1947,6 +1949,7 @@ static void htab_percpu_map_seq_show_elem(struct bpf_map *map, void *key,
 
 static int htab_percpu_map_btf_id;
 const struct bpf_map_ops htab_percpu_map_ops = {
+	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = htab_map_alloc_check,
 	.map_alloc = htab_map_alloc,
 	.map_free = htab_map_free,
@@ -1963,6 +1966,7 @@ const struct bpf_map_ops htab_percpu_map_ops = {
 
 static int htab_lru_percpu_map_btf_id;
 const struct bpf_map_ops htab_lru_percpu_map_ops = {
+	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = htab_map_alloc_check,
 	.map_alloc = htab_map_alloc,
 	.map_free = htab_map_free,
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index 44474bf3ab7a..00e32f2ec3e6 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -732,6 +732,7 @@ static int trie_check_btf(const struct bpf_map *map,
 
 static int trie_map_btf_id;
 const struct bpf_map_ops trie_map_ops = {
+	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc = trie_alloc,
 	.map_free = trie_free,
 	.map_get_next_key = trie_get_next_key,
diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c
index 17738c93bec8..e97a22dd3232 100644
--- a/kernel/bpf/map_in_map.c
+++ b/kernel/bpf/map_in_map.c
@@ -17,23 +17,17 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd)
 	if (IS_ERR(inner_map))
 		return inner_map;
 
-	/* prog_array->aux->{type,jited} is a runtime binding.
-	 * Doing static check alone in the verifier is not enough.
-	 */
-	if (inner_map->map_type == BPF_MAP_TYPE_PROG_ARRAY ||
-	    inner_map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE ||
-	    inner_map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE ||
-	    inner_map->map_type == BPF_MAP_TYPE_STRUCT_OPS) {
-		fdput(f);
-		return ERR_PTR(-ENOTSUPP);
-	}
-
 	/* Does not support >1 level map-in-map */
 	if (inner_map->inner_map_meta) {
 		fdput(f);
 		return ERR_PTR(-EINVAL);
 	}
 
+	if (!inner_map->ops->map_meta_equal) {
+		fdput(f);
+		return ERR_PTR(-ENOTSUPP);
+	}
+
 	if (map_value_has_spin_lock(inner_map)) {
 		fdput(f);
 		return ERR_PTR(-ENOTSUPP);
@@ -89,7 +83,7 @@ void *bpf_map_fd_get_ptr(struct bpf_map *map,
 			 struct file *map_file /* not used */,
 			 int ufd)
 {
-	struct bpf_map *inner_map;
+	struct bpf_map *inner_map, *inner_map_meta;
 	struct fd f;
 
 	f = fdget(ufd);
@@ -97,7 +91,8 @@ void *bpf_map_fd_get_ptr(struct bpf_map *map,
 	if (IS_ERR(inner_map))
 		return inner_map;
 
-	if (bpf_map_meta_equal(map->inner_map_meta, inner_map))
+	inner_map_meta = map->inner_map_meta;
+	if (inner_map_meta->ops->map_meta_equal(inner_map_meta, inner_map))
 		bpf_map_inc(inner_map);
 	else
 		inner_map = ERR_PTR(-EINVAL);
diff --git a/kernel/bpf/map_in_map.h b/kernel/bpf/map_in_map.h
index a507bf6ef8b9..bcb7534afb3c 100644
--- a/kernel/bpf/map_in_map.h
+++ b/kernel/bpf/map_in_map.h
@@ -11,8 +11,6 @@ struct bpf_map;
 
 struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd);
 void bpf_map_meta_free(struct bpf_map *map_meta);
-bool bpf_map_meta_equal(const struct bpf_map *meta0,
-			const struct bpf_map *meta1);
 void *bpf_map_fd_get_ptr(struct bpf_map *map, struct file *map_file,
 			 int ufd);
 void bpf_map_fd_put_ptr(void *ptr);
diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c
index 44184f82916a..0ee2347ba510 100644
--- a/kernel/bpf/queue_stack_maps.c
+++ b/kernel/bpf/queue_stack_maps.c
@@ -257,6 +257,7 @@ static int queue_stack_map_get_next_key(struct bpf_map *map, void *key,
 
 static int queue_map_btf_id;
 const struct bpf_map_ops queue_map_ops = {
+	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = queue_stack_map_alloc_check,
 	.map_alloc = queue_stack_map_alloc,
 	.map_free = queue_stack_map_free,
@@ -273,6 +274,7 @@ const struct bpf_map_ops queue_map_ops = {
 
 static int stack_map_btf_id;
 const struct bpf_map_ops stack_map_ops = {
+	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = queue_stack_map_alloc_check,
 	.map_alloc = queue_stack_map_alloc,
 	.map_free = queue_stack_map_free,
diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c
index 90b29c5b1da7..5a2ba1182493 100644
--- a/kernel/bpf/reuseport_array.c
+++ b/kernel/bpf/reuseport_array.c
@@ -351,6 +351,7 @@ static int reuseport_array_get_next_key(struct bpf_map *map, void *key,
 
 static int reuseport_array_map_btf_id;
 const struct bpf_map_ops reuseport_array_ops = {
+	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = reuseport_array_alloc_check,
 	.map_alloc = reuseport_array_alloc,
 	.map_free = reuseport_array_free,
diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c
index 002f8a5c9e51..31cb04a4dd2d 100644
--- a/kernel/bpf/ringbuf.c
+++ b/kernel/bpf/ringbuf.c
@@ -287,6 +287,7 @@ static __poll_t ringbuf_map_poll(struct bpf_map *map, struct file *filp,
 
 static int ringbuf_map_btf_id;
 const struct bpf_map_ops ringbuf_map_ops = {
+	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc = ringbuf_map_alloc,
 	.map_free = ringbuf_map_free,
 	.map_mmap = ringbuf_map_mmap,
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index cfed0ac44d38..a2fa006f430e 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -839,6 +839,7 @@ static void stack_map_free(struct bpf_map *map)
 
 static int stack_trace_map_btf_id;
 const struct bpf_map_ops stack_trace_map_ops = {
+	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc = stack_map_alloc,
 	.map_free = stack_map_free,
 	.map_get_next_key = stack_map_get_next_key,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 5443cea86cef..b86b1155b748 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -90,6 +90,7 @@ int bpf_check_uarg_tail_zero(void __user *uaddr,
 }
 
 const struct bpf_map_ops bpf_map_offload_ops = {
+	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc = bpf_map_offload_map_alloc,
 	.map_free = bpf_map_offload_map_free,
 	.map_check_btf = map_check_no_btf,
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index 55fae03b4cc3..a0d1a3265b71 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -335,6 +335,7 @@ sk_storage_ptr(void *owner)
 
 static int sk_storage_map_btf_id;
 const struct bpf_map_ops sk_storage_map_ops = {
+	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = bpf_local_storage_map_alloc_check,
 	.map_alloc = sk_storage_map_alloc,
 	.map_free = sk_storage_map_free,
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index d6c6e1e312fc..078386d7d9a2 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -705,6 +705,7 @@ const struct bpf_func_proto bpf_msg_redirect_map_proto = {
 
 static int sock_map_btf_id;
 const struct bpf_map_ops sock_map_ops = {
+	.map_meta_equal		= bpf_map_meta_equal,
 	.map_alloc		= sock_map_alloc,
 	.map_free		= sock_map_free,
 	.map_get_next_key	= sock_map_get_next_key,
@@ -1200,6 +1201,7 @@ const struct bpf_func_proto bpf_msg_redirect_hash_proto = {
 
 static int sock_hash_map_btf_id;
 const struct bpf_map_ops sock_hash_ops = {
+	.map_meta_equal		= bpf_map_meta_equal,
 	.map_alloc		= sock_hash_alloc,
 	.map_free		= sock_hash_free,
 	.map_get_next_key	= sock_hash_get_next_key,
diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c
index 8367adbbe9df..f45f29f04151 100644
--- a/net/xdp/xskmap.c
+++ b/net/xdp/xskmap.c
@@ -256,6 +256,7 @@ void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
 
 static int xsk_map_btf_id;
 const struct bpf_map_ops xsk_map_ops = {
+	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc = xsk_map_alloc,
 	.map_free = xsk_map_free,
 	.map_get_next_key = xsk_map_get_next_key,
-- 
cgit v1.2.3


From 316cdaa1158af17250397054f92bb339fbd8e282 Mon Sep 17 00:00:00 2001
From: Mahesh Bandewar <maheshb@google.com>
Date: Wed, 26 Aug 2020 09:05:35 -0700
Subject: net: add option to not create fall-back tunnels in root-ns as well

The sysctl that was added  earlier by commit 79134e6ce2c ("net: do
not create fallback tunnels for non-default namespaces") to create
fall-back only in root-ns. This patch enhances that behavior to provide
option not to create fallback tunnels in root-ns as well. Since modules
that create fallback tunnels could be built-in and setting the sysctl
value after booting is pointless, so added a kernel cmdline options to
change this default. The default setting is preseved for backward
compatibility. The kernel command line option of fb_tunnels=initns will
set the sysctl value to 1 and will create fallback tunnels only in initns
while kernel cmdline fb_tunnels=none will set the sysctl value to 2 and
fallback tunnels are skipped in every netns.

Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Maciej Zenczykowski <maze@google.com>
Cc: Jian Yang <jianyang@google.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/admin-guide/kernel-parameters.txt |  5 +++++
 Documentation/admin-guide/sysctl/net.rst        | 20 ++++++++++++++------
 include/linux/netdevice.h                       |  8 ++++++--
 net/core/sysctl_net_core.c                      | 17 +++++++++++++++--
 4 files changed, 40 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index a1068742a6df..8af893ef0d46 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1338,6 +1338,11 @@
 			Format: <interval>,<probability>,<space>,<times>
 			See also Documentation/fault-injection/.
 
+	fb_tunnels=	[NET]
+			Format: { initns | none }
+			See Documentation/admin-guide/sysctl/net.rst for
+			fb_tunnels_only_for_init_ns
+
 	floppy=		[HW]
 			See Documentation/admin-guide/blockdev/floppy.rst.
 
diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst
index 42cd04bca548..57fd6ce68fe0 100644
--- a/Documentation/admin-guide/sysctl/net.rst
+++ b/Documentation/admin-guide/sysctl/net.rst
@@ -300,7 +300,6 @@ Note:
       0:    0     1     2     3     4     5     6     7
   RSS hash key:
   84:50:f4:00:a8:15:d1:a7:e9:7f:1d:60:35:c7:47:25:42:97:74:ca:56:bb:b6:a1:d8:43:e3:c9:0c:fd:17:55:c2:3a:4d:69:ed:f1:42:89
-
 netdev_tstamp_prequeue
 ----------------------
 
@@ -321,11 +320,20 @@ fb_tunnels_only_for_init_net
 ----------------------------
 
 Controls if fallback tunnels (like tunl0, gre0, gretap0, erspan0,
-sit0, ip6tnl0, ip6gre0) are automatically created when a new
-network namespace is created, if corresponding tunnel is present
-in initial network namespace.
-If set to 1, these devices are not automatically created, and
-user space is responsible for creating them if needed.
+sit0, ip6tnl0, ip6gre0) are automatically created. There are 3 possibilities
+(a) value = 0; respective fallback tunnels are created when module is
+loaded in every net namespaces (backward compatible behavior).
+(b) value = 1; [kcmd value: initns] respective fallback tunnels are
+created only in init net namespace and every other net namespace will
+not have them.
+(c) value = 2; [kcmd value: none] fallback tunnels are not created
+when a module is loaded in any of the net namespace. Setting value to
+"2" is pointless after boot if these modules are built-in, so there is
+a kernel command-line option that can change this default. Please refer to
+Documentation/admin-guide/kernel-parameters.txt for additional details.
+
+Not creating fallback tunnels gives control to userspace to create
+whatever is needed only and avoid creating devices which are redundant.
 
 Default : 0  (for compatibility reasons)
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index b8abe1d7aa0b..c0b512e6a02b 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -640,10 +640,14 @@ struct netdev_queue {
 extern int sysctl_fb_tunnels_only_for_init_net;
 extern int sysctl_devconf_inherit_init_net;
 
+/*
+ * sysctl_fb_tunnels_only_for_init_net == 0 : For all netns
+ *                                     == 1 : For initns only
+ *                                     == 2 : For none.
+ */
 static inline bool net_has_fallback_tunnels(const struct net *net)
 {
-	return net == &init_net ||
-	       !IS_ENABLED(CONFIG_SYSCTL) ||
+	return (net == &init_net && sysctl_fb_tunnels_only_for_init_net == 1) ||
 	       !sysctl_fb_tunnels_only_for_init_net;
 }
 
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 6ada114bbcca..d86d8d11cfe4 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -22,7 +22,7 @@
 #include <net/busy_poll.h>
 #include <net/pkt_sched.h>
 
-static int two __maybe_unused = 2;
+static int two = 2;
 static int three = 3;
 static int min_sndbuf = SOCK_MIN_SNDBUF;
 static int min_rcvbuf = SOCK_MIN_RCVBUF;
@@ -546,7 +546,7 @@ static struct ctl_table net_core_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_ONE,
+		.extra2		= &two,
 	},
 	{
 		.procname	= "devconf_inherit_init_net",
@@ -587,6 +587,19 @@ static struct ctl_table netns_core_table[] = {
 	{ }
 };
 
+static int __init fb_tunnels_only_for_init_net_sysctl_setup(char *str)
+{
+	/* fallback tunnels for initns only */
+	if (!strncmp(str, "initns", 6))
+		sysctl_fb_tunnels_only_for_init_net = 1;
+	/* no fallback tunnels anywhere */
+	else if (!strncmp(str, "none", 4))
+		sysctl_fb_tunnels_only_for_init_net = 2;
+
+	return 1;
+}
+__setup("fb_tunnels=", fb_tunnels_only_for_init_net_sysctl_setup);
+
 static __net_init int sysctl_core_net_init(struct net *net)
 {
 	struct ctl_table *tbl;
-- 
cgit v1.2.3


From 9584051f3cf3af181e577960956bb7c085879b67 Mon Sep 17 00:00:00 2001
From: Jonghwa Lee <jonghwa3.lee@samsung.com>
Date: Thu, 14 May 2020 16:04:27 -0700
Subject: power: supply: charger-manager: Remove cm_notify_event function

cm_notify_event() was introduced to get an event associated with the
battery status externally (ie in board files), but no one ever used it.
Moreover it makes charger manager driver more complicated. Drop the
function and all data related to it to simplify the driver.

Signed-off-by: Jonghwa Lee <jonghwa3.lee@samsung.com>
Signed-off-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Signed-off-by: Jonathan Bakker <xc-racer2@live.ca>
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/charger-manager.c | 183 ++-------------------------------
 include/linux/power/charger-manager.h  |  33 ++----
 2 files changed, 16 insertions(+), 200 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/power/supply/charger-manager.c b/drivers/power/supply/charger-manager.c
index 1adaeefd90a4..c18dc8d3ae1c 100644
--- a/drivers/power/supply/charger-manager.c
+++ b/drivers/power/supply/charger-manager.c
@@ -434,25 +434,18 @@ static int try_charger_restart(struct charger_manager *cm)
 
 /**
  * fullbatt_vchk - Check voltage drop some times after "FULL" event.
- * @work: the work_struct appointing the function
  *
- * If a user has designated "fullbatt_vchkdrop_ms/uV" values with
+ * If a user has designated "fullbatt_vchkdrop_uV" values with
  * charger_desc, Charger Manager checks voltage drop after the battery
  * "FULL" event. It checks whether the voltage has dropped more than
  * fullbatt_vchkdrop_uV by calling this function after fullbatt_vchkrop_ms.
  */
-static void fullbatt_vchk(struct work_struct *work)
+static void fullbatt_vchk(struct charger_manager *cm)
 {
-	struct delayed_work *dwork = to_delayed_work(work);
-	struct charger_manager *cm = container_of(dwork,
-			struct charger_manager, fullbatt_vchk_work);
 	struct charger_desc *desc = cm->desc;
 	int batt_uV, err, diff;
 
-	/* remove the appointment for fullbatt_vchk */
-	cm->fullbatt_vchk_jiffies_at = 0;
-
-	if (!desc->fullbatt_vchkdrop_uV || !desc->fullbatt_vchkdrop_ms)
+	if (!desc->fullbatt_vchkdrop_uV)
 		return;
 
 	err = get_batt_uV(cm, &batt_uV);
@@ -588,9 +581,11 @@ static int cm_check_thermal_status(struct charger_manager *cm)
 	}
 
 	if (temp > upper_limit)
-		ret = CM_EVENT_BATT_OVERHEAT;
+		ret = CM_BATT_OVERHEAT;
 	else if (temp < lower_limit)
-		ret = CM_EVENT_BATT_COLD;
+		ret = CM_BATT_COLD;
+	else
+		ret = CM_BATT_OK;
 
 	return ret;
 }
@@ -635,7 +630,7 @@ static bool _cm_monitor(struct charger_manager *cm)
 	 */
 	} else if (!cm->emergency_stop && is_ext_pwr_online(cm) &&
 			!cm->charger_enabled) {
-		fullbatt_vchk(&cm->fullbatt_vchk_work.work);
+		fullbatt_vchk(cm);
 
 	/*
 	 * Check whether fully charged state to protect overcharge
@@ -648,7 +643,7 @@ static bool _cm_monitor(struct charger_manager *cm)
 
 		try_charger_enable(cm, false);
 
-		fullbatt_vchk(&cm->fullbatt_vchk_work.work);
+		fullbatt_vchk(cm);
 	} else {
 		cm->emergency_stop = 0;
 		if (is_ext_pwr_online(cm)) {
@@ -750,66 +745,6 @@ static void cm_monitor_poller(struct work_struct *work)
 	schedule_work(&setup_polling);
 }
 
-/**
- * fullbatt_handler - Event handler for CM_EVENT_BATT_FULL
- * @cm: the Charger Manager representing the battery.
- */
-static void fullbatt_handler(struct charger_manager *cm)
-{
-	struct charger_desc *desc = cm->desc;
-
-	if (!desc->fullbatt_vchkdrop_uV || !desc->fullbatt_vchkdrop_ms)
-		goto out;
-
-	if (cm_suspended)
-		device_set_wakeup_capable(cm->dev, true);
-
-	mod_delayed_work(cm_wq, &cm->fullbatt_vchk_work,
-			 msecs_to_jiffies(desc->fullbatt_vchkdrop_ms));
-	cm->fullbatt_vchk_jiffies_at = jiffies + msecs_to_jiffies(
-				       desc->fullbatt_vchkdrop_ms);
-
-	if (cm->fullbatt_vchk_jiffies_at == 0)
-		cm->fullbatt_vchk_jiffies_at = 1;
-
-out:
-	dev_info(cm->dev, "EVENT_HANDLE: Battery Fully Charged\n");
-	power_supply_changed(cm->charger_psy);
-}
-
-/**
- * battout_handler - Event handler for CM_EVENT_BATT_OUT
- * @cm: the Charger Manager representing the battery.
- */
-static void battout_handler(struct charger_manager *cm)
-{
-	if (cm_suspended)
-		device_set_wakeup_capable(cm->dev, true);
-
-	if (!is_batt_present(cm)) {
-		dev_emerg(cm->dev, "Battery Pulled Out!\n");
-		power_supply_changed(cm->charger_psy);
-	} else {
-		power_supply_changed(cm->charger_psy);
-	}
-}
-
-/**
- * misc_event_handler - Handler for other events
- * @cm: the Charger Manager representing the battery.
- * @type: the Charger Manager representing the battery.
- */
-static void misc_event_handler(struct charger_manager *cm,
-			enum cm_event_types type)
-{
-	if (cm_suspended)
-		device_set_wakeup_capable(cm->dev, true);
-
-	if (is_polling_required(cm) && cm->desc->polling_interval_ms)
-		schedule_work(&setup_polling);
-	power_supply_changed(cm->charger_psy);
-}
-
 static int charger_get_property(struct power_supply *psy,
 		enum power_supply_property psp,
 		union power_supply_propval *val)
@@ -1000,21 +935,6 @@ static bool cm_setup_timer(void)
 
 	mutex_lock(&cm_list_mtx);
 	list_for_each_entry(cm, &cm_list, entry) {
-		unsigned int fbchk_ms = 0;
-
-		/* fullbatt_vchk is required. setup timer for that */
-		if (cm->fullbatt_vchk_jiffies_at) {
-			fbchk_ms = jiffies_to_msecs(cm->fullbatt_vchk_jiffies_at
-						    - jiffies);
-			if (time_is_before_eq_jiffies(
-				cm->fullbatt_vchk_jiffies_at) ||
-				msecs_to_jiffies(fbchk_ms) < CM_JIFFIES_SMALL) {
-				fullbatt_vchk(&cm->fullbatt_vchk_work.work);
-				fbchk_ms = 0;
-			}
-		}
-		CM_MIN_VALID(wakeup_ms, fbchk_ms);
-
 		/* Skip if polling is not required for this CM */
 		if (!is_polling_required(cm) && !cm->emergency_stop)
 			continue;
@@ -1422,8 +1342,6 @@ static struct charger_desc *of_cm_parse_desc(struct device *dev)
 	of_property_read_u32(np, "cm-poll-interval",
 				&desc->polling_interval_ms);
 
-	of_property_read_u32(np, "cm-fullbatt-vchkdrop-ms",
-					&desc->fullbatt_vchkdrop_ms);
 	of_property_read_u32(np, "cm-fullbatt-vchkdrop-volt",
 					&desc->fullbatt_vchkdrop_uV);
 	of_property_read_u32(np, "cm-fullbatt-voltage", &desc->fullbatt_uV);
@@ -1585,9 +1503,8 @@ static int charger_manager_probe(struct platform_device *pdev)
 	if (desc->fullbatt_uV == 0) {
 		dev_info(&pdev->dev, "Ignoring full-battery voltage threshold as it is not supplied\n");
 	}
-	if (!desc->fullbatt_vchkdrop_ms || !desc->fullbatt_vchkdrop_uV) {
+	if (!desc->fullbatt_vchkdrop_uV) {
 		dev_info(&pdev->dev, "Disabling full-battery voltage drop checking mechanism as it is not supplied\n");
-		desc->fullbatt_vchkdrop_ms = 0;
 		desc->fullbatt_vchkdrop_uV = 0;
 	}
 	if (desc->fullbatt_soc == 0) {
@@ -1693,8 +1610,6 @@ static int charger_manager_probe(struct platform_device *pdev)
 	cm->charger_psy_desc.properties = properties;
 	cm->charger_psy_desc.num_properties = num_properties;
 
-	INIT_DELAYED_WORK(&cm->fullbatt_vchk_work, fullbatt_vchk);
-
 	/* Register sysfs entry for charger(regulator) */
 	ret = charger_manager_prepare_sysfs(cm);
 	if (ret < 0) {
@@ -1834,8 +1749,6 @@ static bool cm_need_to_awake(void)
 
 static int cm_suspend_prepare(struct device *dev)
 {
-	struct charger_manager *cm = dev_get_drvdata(dev);
-
 	if (cm_need_to_awake())
 		return -EBUSY;
 
@@ -1847,7 +1760,6 @@ static int cm_suspend_prepare(struct device *dev)
 	if (cm_timer_set) {
 		cancel_work_sync(&setup_polling);
 		cancel_delayed_work_sync(&cm_monitor_work);
-		cancel_delayed_work(&cm->fullbatt_vchk_work);
 	}
 
 	return 0;
@@ -1872,31 +1784,6 @@ static void cm_suspend_complete(struct device *dev)
 
 	_cm_monitor(cm);
 
-	/* Re-enqueue delayed work (fullbatt_vchk_work) */
-	if (cm->fullbatt_vchk_jiffies_at) {
-		unsigned long delay = 0;
-		unsigned long now = jiffies + CM_JIFFIES_SMALL;
-
-		if (time_after_eq(now, cm->fullbatt_vchk_jiffies_at)) {
-			delay = (unsigned long)((long)now
-				- (long)(cm->fullbatt_vchk_jiffies_at));
-			delay = jiffies_to_msecs(delay);
-		} else {
-			delay = 0;
-		}
-
-		/*
-		 * Account for cm_suspend_duration_ms with assuming that
-		 * timer stops in suspend.
-		 */
-		if (delay > cm_suspend_duration_ms)
-			delay -= cm_suspend_duration_ms;
-		else
-			delay = 0;
-
-		queue_delayed_work(cm_wq, &cm->fullbatt_vchk_work,
-				   msecs_to_jiffies(delay));
-	}
 	device_set_wakeup_capable(cm->dev, false);
 }
 
@@ -1938,56 +1825,6 @@ static void __exit charger_manager_cleanup(void)
 }
 module_exit(charger_manager_cleanup);
 
-/**
- * cm_notify_event - charger driver notify Charger Manager of charger event
- * @psy: pointer to instance of charger's power_supply
- * @type: type of charger event
- * @msg: optional message passed to uevent_notify function
- */
-void cm_notify_event(struct power_supply *psy, enum cm_event_types type,
-		     char *msg)
-{
-	struct charger_manager *cm;
-	bool found_power_supply = false;
-
-	if (psy == NULL)
-		return;
-
-	mutex_lock(&cm_list_mtx);
-	list_for_each_entry(cm, &cm_list, entry) {
-		if (match_string(cm->desc->psy_charger_stat, -1,
-				 psy->desc->name) >= 0) {
-			found_power_supply = true;
-			break;
-		}
-	}
-	mutex_unlock(&cm_list_mtx);
-
-	if (!found_power_supply)
-		return;
-
-	switch (type) {
-	case CM_EVENT_BATT_FULL:
-		fullbatt_handler(cm);
-		break;
-	case CM_EVENT_BATT_OUT:
-		battout_handler(cm);
-		break;
-	case CM_EVENT_BATT_IN:
-	case CM_EVENT_EXT_PWR_IN_OUT ... CM_EVENT_CHG_START_STOP:
-		misc_event_handler(cm, type);
-		break;
-	case CM_EVENT_UNKNOWN:
-	case CM_EVENT_OTHERS:
-		power_supply_changed(cm->charger_psy);
-		break;
-	default:
-		dev_err(cm->dev, "%s: type not specified\n", __func__);
-		break;
-	}
-}
-EXPORT_SYMBOL_GPL(cm_notify_event);
-
 MODULE_AUTHOR("MyungJoo Ham <myungjoo.ham@samsung.com>");
 MODULE_DESCRIPTION("Charger Manager");
 MODULE_LICENSE("GPL");
diff --git a/include/linux/power/charger-manager.h b/include/linux/power/charger-manager.h
index ae94dcebd936..3a98837684e3 100644
--- a/include/linux/power/charger-manager.h
+++ b/include/linux/power/charger-manager.h
@@ -31,16 +31,10 @@ enum polling_modes {
 	CM_POLL_CHARGING_ONLY,
 };
 
-enum cm_event_types {
-	CM_EVENT_UNKNOWN = 0,
-	CM_EVENT_BATT_FULL,
-	CM_EVENT_BATT_IN,
-	CM_EVENT_BATT_OUT,
-	CM_EVENT_BATT_OVERHEAT,
-	CM_EVENT_BATT_COLD,
-	CM_EVENT_EXT_PWR_IN_OUT,
-	CM_EVENT_CHG_START_STOP,
-	CM_EVENT_OTHERS,
+enum cm_batt_temp {
+	CM_BATT_OK = 0,
+	CM_BATT_OVERHEAT,
+	CM_BATT_COLD,
 };
 
 /**
@@ -131,11 +125,10 @@ struct charger_regulator {
  * @psy_name: the name of power-supply-class for charger manager
  * @polling_mode:
  *	Determine which polling mode will be used
- * @fullbatt_vchkdrop_ms:
  * @fullbatt_vchkdrop_uV:
  *	Check voltage drop after the battery is fully charged.
- *	If it has dropped more than fullbatt_vchkdrop_uV after
- *	fullbatt_vchkdrop_ms, CM will restart charging.
+ *	If it has dropped more than fullbatt_vchkdrop_uV
+ *	CM will restart charging.
  * @fullbatt_uV: voltage in microvolt
  *	If VBATT >= fullbatt_uV, it is assumed to be full.
  * @fullbatt_soc: state of Charge in %
@@ -172,7 +165,6 @@ struct charger_desc {
 	enum polling_modes polling_mode;
 	unsigned int polling_interval_ms;
 
-	unsigned int fullbatt_vchkdrop_ms;
 	unsigned int fullbatt_vchkdrop_uV;
 	unsigned int fullbatt_uV;
 	unsigned int fullbatt_soc;
@@ -211,9 +203,6 @@ struct charger_desc {
  * @charger_stat: array of power_supply for chargers
  * @tzd_batt : thermal zone device for battery
  * @charger_enabled: the state of charger
- * @fullbatt_vchk_jiffies_at:
- *	jiffies at the time full battery check will occur.
- * @fullbatt_vchk_work: work queue for full battery check
  * @emergency_stop:
  *	When setting true, stop charging
  * @psy_name_buf: the name of power-supply-class for charger manager
@@ -235,9 +224,6 @@ struct charger_manager {
 #endif
 	bool charger_enabled;
 
-	unsigned long fullbatt_vchk_jiffies_at;
-	struct delayed_work fullbatt_vchk_work;
-
 	int emergency_stop;
 
 	char psy_name_buf[PSY_NAME_MAX + 1];
@@ -248,11 +234,4 @@ struct charger_manager {
 	u64 charging_end_time;
 };
 
-#if IS_ENABLED(CONFIG_CHARGER_MANAGER)
-extern void cm_notify_event(struct power_supply *psy,
-				enum cm_event_types type, char *msg);
-#else
-static inline void cm_notify_event(struct power_supply *psy,
-				enum cm_event_types type, char *msg) { }
-#endif
 #endif /* _CHARGER_MANAGER_H */
-- 
cgit v1.2.3


From e132fc6bb89bd307cfcdb8ba24afcd1985261485 Mon Sep 17 00:00:00 2001
From: Jonghwa Lee <jonghwa3.lee@samsung.com>
Date: Thu, 14 May 2020 16:04:31 -0700
Subject: power: supply: charger-manager: Make decisions focussed on battery
 status

cm_monitor(), where charging management starts, checks various charging
condition sequentially to decide next charging operation. However, as it
follows sequential process, cascaded if statements, it does some
jobs which have already done in the previous stage. This results in a
delay in decision making. Moreover, starting point of charging is spread
all around which makes maintain code and debugging difficult.

Both of the problems mentioned above become clean if it manages battery
charging focusing on battery status not following sequential condition
checking.  Now, cm_monitor() moves battery state diagram and does the
optimal operation for current state. As a result, it reduces whole
monitoring time almost in half.

Signed-off-by: Jonghwa Lee <jonghwa3.lee@samsung.com>
Signed-off-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Signed-off-by: Jonathan Bakker <xc-racer2@live.ca>
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/charger-manager.c | 181 +++++++++++----------------------
 include/linux/power/charger-manager.h  |   3 +
 2 files changed, 64 insertions(+), 120 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/power/supply/charger-manager.c b/drivers/power/supply/charger-manager.c
index cc8feb68694d..d10bf89328a0 100644
--- a/drivers/power/supply/charger-manager.c
+++ b/drivers/power/supply/charger-manager.c
@@ -271,6 +271,19 @@ static bool is_full_charged(struct charger_manager *cm)
 	if (!fuel_gauge)
 		return false;
 
+	/* Full, if it's over the fullbatt voltage */
+	if (desc->fullbatt_uV > 0) {
+		ret = get_batt_uV(cm, &uV);
+		if (!ret) {
+			/* Battery is already full, checks voltage drop. */
+			if (cm->battery_status == POWER_SUPPLY_STATUS_FULL
+					&& desc->fullbatt_vchkdrop_uV)
+				uV += desc->fullbatt_vchkdrop_uV;
+			if (uV >= desc->fullbatt_uV)
+				return true;
+		}
+	}
+
 	if (desc->fullbatt_full_capacity > 0) {
 		val.intval = 0;
 
@@ -283,15 +296,6 @@ static bool is_full_charged(struct charger_manager *cm)
 		}
 	}
 
-	/* Full, if it's over the fullbatt voltage */
-	if (desc->fullbatt_uV > 0) {
-		ret = get_batt_uV(cm, &uV);
-		if (!ret && uV >= desc->fullbatt_uV) {
-			is_full = true;
-			goto out;
-		}
-	}
-
 	/* Full, if the capacity is more than fullbatt_soc */
 	if (desc->fullbatt_soc > 0) {
 		val.intval = 0;
@@ -406,66 +410,12 @@ static int try_charger_enable(struct charger_manager *cm, bool enable)
 		}
 	}
 
-	if (!err) {
+	if (!err)
 		cm->charger_enabled = enable;
-		power_supply_changed(cm->charger_psy);
-	}
 
 	return err;
 }
 
-/**
- * try_charger_restart - Restart charging.
- * @cm: the Charger Manager representing the battery.
- *
- * Restart charging by turning off and on the charger.
- */
-static int try_charger_restart(struct charger_manager *cm)
-{
-	int err;
-
-	if (cm->emergency_stop)
-		return -EAGAIN;
-
-	err = try_charger_enable(cm, false);
-	if (err)
-		return err;
-
-	return try_charger_enable(cm, true);
-}
-
-/**
- * fullbatt_vchk - Check voltage drop some times after "FULL" event.
- *
- * If a user has designated "fullbatt_vchkdrop_uV" values with
- * charger_desc, Charger Manager checks voltage drop after the battery
- * "FULL" event. It checks whether the voltage has dropped more than
- * fullbatt_vchkdrop_uV by calling this function after fullbatt_vchkrop_ms.
- */
-static void fullbatt_vchk(struct charger_manager *cm)
-{
-	struct charger_desc *desc = cm->desc;
-	int batt_uV, err, diff;
-
-	if (!desc->fullbatt_vchkdrop_uV)
-		return;
-
-	err = get_batt_uV(cm, &batt_uV);
-	if (err) {
-		dev_err(cm->dev, "%s: get_batt_uV error(%d)\n", __func__, err);
-		return;
-	}
-
-	diff = desc->fullbatt_uV - batt_uV;
-	if (diff < 0)
-		return;
-
-	dev_info(cm->dev, "VBATT dropped %duV after full-batt\n", diff);
-
-	if (diff > desc->fullbatt_vchkdrop_uV)
-		try_charger_restart(cm);
-}
-
 /**
  * check_charging_duration - Monitor charging/discharging duration
  * @cm: the Charger Manager representing the battery.
@@ -493,17 +443,14 @@ static int check_charging_duration(struct charger_manager *cm)
 		if (duration > desc->charging_max_duration_ms) {
 			dev_info(cm->dev, "Charging duration exceed %ums\n",
 				 desc->charging_max_duration_ms);
-			try_charger_enable(cm, false);
 			ret = true;
 		}
-	} else if (is_ext_pwr_online(cm) && !cm->charger_enabled) {
+	} else if (cm->battery_status == POWER_SUPPLY_STATUS_NOT_CHARGING) {
 		duration = curr - cm->charging_end_time;
 
-		if (duration > desc->discharging_max_duration_ms &&
-				is_ext_pwr_online(cm)) {
+		if (duration > desc->charging_max_duration_ms) {
 			dev_info(cm->dev, "Discharging duration exceed %ums\n",
 				 desc->discharging_max_duration_ms);
-			try_charger_enable(cm, true);
 			ret = true;
 		}
 	}
@@ -585,9 +532,46 @@ static int cm_check_thermal_status(struct charger_manager *cm)
 	else
 		ret = CM_BATT_OK;
 
+	cm->emergency_stop = ret;
+
 	return ret;
 }
 
+/**
+ * cm_get_target_status - Check current status and get next target status.
+ * @cm: the Charger Manager representing the battery.
+ */
+static int cm_get_target_status(struct charger_manager *cm)
+{
+	if (!is_ext_pwr_online(cm))
+		return POWER_SUPPLY_STATUS_DISCHARGING;
+
+	if (cm_check_thermal_status(cm)) {
+		/* Check if discharging duration exeeds limit. */
+		if (check_charging_duration(cm))
+			goto charging_ok;
+		return POWER_SUPPLY_STATUS_NOT_CHARGING;
+	}
+
+	switch (cm->battery_status) {
+	case POWER_SUPPLY_STATUS_CHARGING:
+		/* Check if charging duration exeeds limit. */
+		if (check_charging_duration(cm))
+			return POWER_SUPPLY_STATUS_FULL;
+		fallthrough;
+	case POWER_SUPPLY_STATUS_FULL:
+		if (is_full_charged(cm))
+			return POWER_SUPPLY_STATUS_FULL;
+		fallthrough;
+	default:
+		break;
+	}
+
+charging_ok:
+	/* Charging is allowed. */
+	return POWER_SUPPLY_STATUS_CHARGING;
+}
+
 /**
  * _cm_monitor - Monitor the temperature and return true for exceptions.
  * @cm: the Charger Manager representing the battery.
@@ -597,56 +581,18 @@ static int cm_check_thermal_status(struct charger_manager *cm)
  */
 static bool _cm_monitor(struct charger_manager *cm)
 {
-	int temp_alrt;
+	int target;
 
-	temp_alrt = cm_check_thermal_status(cm);
+	target = cm_get_target_status(cm);
 
-	/* It has been stopped already */
-	if (temp_alrt && cm->emergency_stop)
-		return false;
-
-	/*
-	 * Check temperature whether overheat or cold.
-	 * If temperature is out of range normal state, stop charging.
-	 */
-	if (temp_alrt) {
-		cm->emergency_stop = temp_alrt;
-		try_charger_enable(cm, false);
-
-	/*
-	 * Check whole charging duration and discharging duration
-	 * after full-batt.
-	 */
-	} else if (!cm->emergency_stop && check_charging_duration(cm)) {
-		dev_dbg(cm->dev,
-			"Charging/Discharging duration is out of range\n");
-	/*
-	 * Check dropped voltage of battery. If battery voltage is more
-	 * dropped than fullbatt_vchkdrop_uV after fully charged state,
-	 * charger-manager have to recharge battery.
-	 */
-	} else if (!cm->emergency_stop && is_ext_pwr_online(cm) &&
-			!cm->charger_enabled) {
-		fullbatt_vchk(cm);
+	try_charger_enable(cm, (target == POWER_SUPPLY_STATUS_CHARGING));
 
-	/*
-	 * Check whether fully charged state to protect overcharge
-	 * if charger-manager is charging for battery.
-	 */
-	} else if (!cm->emergency_stop && is_full_charged(cm) &&
-			cm->charger_enabled) {
-		dev_info(cm->dev, "EVENT_HANDLE: Battery Fully Charged\n");
-		try_charger_enable(cm, false);
-
-		fullbatt_vchk(cm);
-	} else {
-		cm->emergency_stop = 0;
-		if (is_ext_pwr_online(cm)) {
-			try_charger_enable(cm, true);
-		}
+	if (cm->battery_status != target) {
+		cm->battery_status = target;
+		power_supply_changed(cm->charger_psy);
 	}
 
-	return true;
+	return (cm->battery_status == POWER_SUPPLY_STATUS_NOT_CHARGING);
 }
 
 /**
@@ -751,12 +697,7 @@ static int charger_get_property(struct power_supply *psy,
 
 	switch (psp) {
 	case POWER_SUPPLY_PROP_STATUS:
-		if (is_charging(cm))
-			val->intval = POWER_SUPPLY_STATUS_CHARGING;
-		else if (is_ext_pwr_online(cm))
-			val->intval = POWER_SUPPLY_STATUS_NOT_CHARGING;
-		else
-			val->intval = POWER_SUPPLY_STATUS_DISCHARGING;
+		val->intval = cm->battery_status;
 		break;
 	case POWER_SUPPLY_PROP_HEALTH:
 		if (cm->emergency_stop > 0)
diff --git a/include/linux/power/charger-manager.h b/include/linux/power/charger-manager.h
index 3a98837684e3..c127dbe31e49 100644
--- a/include/linux/power/charger-manager.h
+++ b/include/linux/power/charger-manager.h
@@ -213,6 +213,7 @@ struct charger_desc {
  *	saved status of battery before entering suspend-to-RAM
  * @charging_start_time: saved start time of enabling charging
  * @charging_end_time: saved end time of disabling charging
+ * @battery_status: Current battery status
  */
 struct charger_manager {
 	struct list_head entry;
@@ -232,6 +233,8 @@ struct charger_manager {
 
 	u64 charging_start_time;
 	u64 charging_end_time;
+
+	int battery_status;
 };
 
 #endif /* _CHARGER_MANAGER_H */
-- 
cgit v1.2.3


From c1f73028f75df43689feda4bc70573b7d18a618e Mon Sep 17 00:00:00 2001
From: Jonathan Bakker <xc-racer2@live.ca>
Date: Thu, 14 May 2020 16:04:33 -0700
Subject: power: supply: charger-manager: Update extcon functions

In commit 830ae442202e ("extcon: Remove the deprecated extcon functions")
the function extcon_register_interest became a no-op returning an error,
leading to non-functional behaviour in charger-manager.

Additionally, a translation table is needed between the text representation
of the extcon cable names and their IDs is needed.  In order to retain DT
compatibility, TA and CHARGE-DOWNSTREAM are added as they were present up
until commit 11eecf910bd8 ("extcon: Modify the id and name of external
connector")

Signed-off-by: Jonathan Bakker <xc-racer2@live.ca>
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/charger-manager.c | 82 +++++++++++++++++++++++++---------
 include/linux/power/charger-manager.h  |  5 ++-
 2 files changed, 63 insertions(+), 24 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/power/supply/charger-manager.c b/drivers/power/supply/charger-manager.c
index d3b2ed3ef720..5f536284d2ca 100644
--- a/drivers/power/supply/charger-manager.c
+++ b/drivers/power/supply/charger-manager.c
@@ -26,6 +26,29 @@
 #include <linux/of.h>
 #include <linux/thermal.h>
 
+static struct {
+	const char *name;
+	u64 extcon_type;
+} extcon_mapping[] = {
+	/* Current textual representations */
+	{ "USB", EXTCON_USB },
+	{ "USB-HOST", EXTCON_USB_HOST },
+	{ "SDP", EXTCON_CHG_USB_SDP },
+	{ "DCP", EXTCON_CHG_USB_DCP },
+	{ "CDP", EXTCON_CHG_USB_CDP },
+	{ "ACA", EXTCON_CHG_USB_ACA },
+	{ "FAST-CHARGER", EXTCON_CHG_USB_FAST },
+	{ "SLOW-CHARGER", EXTCON_CHG_USB_SLOW },
+	{ "WPT", EXTCON_CHG_WPT },
+	{ "PD", EXTCON_CHG_USB_PD },
+	{ "DOCK", EXTCON_DOCK },
+	{ "JIG", EXTCON_JIG },
+	{ "MECHANICAL", EXTCON_MECHANICAL },
+	/* Deprecated textual representations */
+	{ "TA", EXTCON_CHG_USB_SDP },
+	{ "CHARGE-DOWNSTREAM", EXTCON_CHG_USB_CDP },
+};
+
 /*
  * Default temperature threshold for charging.
  * Every temperature units are in tenth of centigrade.
@@ -950,7 +973,8 @@ static int charger_extcon_notifier(struct notifier_block *self,
 static int charger_extcon_init(struct charger_manager *cm,
 		struct charger_cable *cable)
 {
-	int ret;
+	int ret, i;
+	u64 extcon_type = EXTCON_NONE;
 
 	/*
 	 * Charger manager use Extcon framework to identify
@@ -959,14 +983,39 @@ static int charger_extcon_init(struct charger_manager *cm,
 	 */
 	INIT_WORK(&cable->wq, charger_extcon_work);
 	cable->nb.notifier_call = charger_extcon_notifier;
-	ret = extcon_register_interest(&cable->extcon_dev,
-			cable->extcon_name, cable->name, &cable->nb);
+
+	cable->extcon_dev = extcon_get_extcon_dev(cable->extcon_name);
+	if (IS_ERR_OR_NULL(cable->extcon_dev)) {
+		pr_err("Cannot find extcon_dev for %s (cable: %s)\n",
+			cable->extcon_name, cable->name);
+		if (cable->extcon_dev == NULL)
+			return -EPROBE_DEFER;
+		else
+			return PTR_ERR(cable->extcon_dev);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(extcon_mapping); i++) {
+		if (!strcmp(cable->name, extcon_mapping[i].name)) {
+			extcon_type = extcon_mapping[i].extcon_type;
+			break;
+		}
+	}
+	if (extcon_type == EXTCON_NONE) {
+		pr_err("Cannot find cable for type %s", cable->name);
+		return -EINVAL;
+	}
+
+	cable->extcon_type = extcon_type;
+
+	ret = devm_extcon_register_notifier(cm->dev, cable->extcon_dev,
+		cable->extcon_type, &cable->nb);
 	if (ret < 0) {
-		pr_info("Cannot register extcon_dev for %s(cable: %s)\n",
+		pr_err("Cannot register extcon_dev for %s (cable: %s)\n",
 			cable->extcon_name, cable->name);
+		return ret;
 	}
 
-	return ret;
+	return 0;
 }
 
 /**
@@ -983,6 +1032,7 @@ static int charger_manager_register_extcon(struct charger_manager *cm)
 {
 	struct charger_desc *desc = cm->desc;
 	struct charger_regulator *charger;
+	unsigned long event;
 	int ret;
 	int i;
 	int j;
@@ -1010,6 +1060,11 @@ static int charger_manager_register_extcon(struct charger_manager *cm)
 			}
 			cable->charger = charger;
 			cable->cm = cm;
+
+			event = extcon_get_state(cable->extcon_dev,
+				cable->extcon_type);
+			charger_extcon_notifier(&cable->nb,
+				event, NULL);
 		}
 	}
 
@@ -1370,7 +1425,6 @@ static int charger_manager_probe(struct platform_device *pdev)
 	struct charger_desc *desc = cm_get_drv_data(pdev);
 	struct charger_manager *cm;
 	int ret, i = 0;
-	int j = 0;
 	union power_supply_propval val;
 	struct power_supply *fuel_gauge;
 	enum power_supply_property *properties;
@@ -1572,12 +1626,6 @@ err_reg_extcon:
 		struct charger_regulator *charger;
 
 		charger = &desc->charger_regulators[i];
-		for (j = 0; j < charger->num_cables; j++) {
-			struct charger_cable *cable = &charger->cables[j];
-			/* Remove notifier block if only edev exists */
-			if (cable->extcon_dev.edev)
-				extcon_unregister_interest(&cable->extcon_dev);
-		}
 
 		regulator_put(desc->charger_regulators[i].consumer);
 	}
@@ -1592,7 +1640,6 @@ static int charger_manager_remove(struct platform_device *pdev)
 	struct charger_manager *cm = platform_get_drvdata(pdev);
 	struct charger_desc *desc = cm->desc;
 	int i = 0;
-	int j = 0;
 
 	/* Remove from the list */
 	mutex_lock(&cm_list_mtx);
@@ -1602,15 +1649,6 @@ static int charger_manager_remove(struct platform_device *pdev)
 	cancel_work_sync(&setup_polling);
 	cancel_delayed_work_sync(&cm_monitor_work);
 
-	for (i = 0 ; i < desc->num_charger_regulators ; i++) {
-		struct charger_regulator *charger
-				= &desc->charger_regulators[i];
-		for (j = 0 ; j < charger->num_cables ; j++) {
-			struct charger_cable *cable = &charger->cables[j];
-			extcon_unregister_interest(&cable->extcon_dev);
-		}
-	}
-
 	for (i = 0 ; i < desc->num_charger_regulators ; i++)
 		regulator_put(desc->charger_regulators[i].consumer);
 
diff --git a/include/linux/power/charger-manager.h b/include/linux/power/charger-manager.h
index c127dbe31e49..45e228b353ea 100644
--- a/include/linux/power/charger-manager.h
+++ b/include/linux/power/charger-manager.h
@@ -40,7 +40,7 @@ enum cm_batt_temp {
 /**
  * struct charger_cable
  * @extcon_name: the name of extcon device.
- * @name: the name of charger cable(external connector).
+ * @name: the name of the cable connector
  * @extcon_dev: the extcon device.
  * @wq: the workqueue to control charger according to the state of
  *	charger cable. If charger cable is attached, enable charger.
@@ -56,9 +56,10 @@ enum cm_batt_temp {
 struct charger_cable {
 	const char *extcon_name;
 	const char *name;
+	struct extcon_dev *extcon_dev;
+	u64 extcon_type;
 
 	/* The charger-manager use Extcon framework */
-	struct extcon_specific_cable_nb extcon_dev;
 	struct work_struct wq;
 	struct notifier_block nb;
 
-- 
cgit v1.2.3


From 4afc41dfa5a716e9e7a90c22972583f337c0bcbf Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 26 Aug 2020 00:52:43 +0200
Subject: netfilter: conntrack: remove ignore stats

This counter increments when nf_conntrack_in sees a packet that already
has a conntrack attached or when the packet is marked as UNTRACKED.
Neither is an error.

The former is normal for loopback traffic.  The second happens for
certain ICMPv6 packets or when nftables/ip(6)tables rules are in place.

In case someone needs to count UNTRACKED packets, or packets
that are marked as untracked before conntrack_in this can be done with
both nftables and ip(6)tables rules.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/nf_conntrack_common.h      | 1 -
 include/uapi/linux/netfilter/nfnetlink_conntrack.h | 2 +-
 net/netfilter/nf_conntrack_core.c                  | 4 +---
 net/netfilter/nf_conntrack_netlink.c               | 1 -
 net/netfilter/nf_conntrack_standalone.c            | 2 +-
 5 files changed, 3 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h
index 1db83c931d9c..96b90d7e361f 100644
--- a/include/linux/netfilter/nf_conntrack_common.h
+++ b/include/linux/netfilter/nf_conntrack_common.h
@@ -8,7 +8,6 @@
 struct ip_conntrack_stat {
 	unsigned int found;
 	unsigned int invalid;
-	unsigned int ignore;
 	unsigned int insert;
 	unsigned int insert_failed;
 	unsigned int drop;
diff --git a/include/uapi/linux/netfilter/nfnetlink_conntrack.h b/include/uapi/linux/netfilter/nfnetlink_conntrack.h
index 262881792671..3e471558da82 100644
--- a/include/uapi/linux/netfilter/nfnetlink_conntrack.h
+++ b/include/uapi/linux/netfilter/nfnetlink_conntrack.h
@@ -247,7 +247,7 @@ enum ctattr_stats_cpu {
 	CTA_STATS_FOUND,
 	CTA_STATS_NEW,		/* no longer used */
 	CTA_STATS_INVALID,
-	CTA_STATS_IGNORE,
+	CTA_STATS_IGNORE,	/* no longer used */
 	CTA_STATS_DELETE,	/* no longer used */
 	CTA_STATS_DELETE_LIST,	/* no longer used */
 	CTA_STATS_INSERT,
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 3cfbafdff941..a111bcf1b93c 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1800,10 +1800,8 @@ nf_conntrack_in(struct sk_buff *skb, const struct nf_hook_state *state)
 	if (tmpl || ctinfo == IP_CT_UNTRACKED) {
 		/* Previously seen (loopback or untracked)?  Ignore. */
 		if ((tmpl && !nf_ct_is_template(tmpl)) ||
-		     ctinfo == IP_CT_UNTRACKED) {
-			NF_CT_STAT_INC_ATOMIC(state->net, ignore);
+		     ctinfo == IP_CT_UNTRACKED)
 			return NF_ACCEPT;
-		}
 		skb->_nfct = 0;
 	}
 
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 832eabecfbdd..c64f23a8f373 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -2509,7 +2509,6 @@ ctnetlink_ct_stat_cpu_fill_info(struct sk_buff *skb, u32 portid, u32 seq,
 
 	if (nla_put_be32(skb, CTA_STATS_FOUND, htonl(st->found)) ||
 	    nla_put_be32(skb, CTA_STATS_INVALID, htonl(st->invalid)) ||
-	    nla_put_be32(skb, CTA_STATS_IGNORE, htonl(st->ignore)) ||
 	    nla_put_be32(skb, CTA_STATS_INSERT, htonl(st->insert)) ||
 	    nla_put_be32(skb, CTA_STATS_INSERT_FAILED,
 				htonl(st->insert_failed)) ||
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index a604f43e3e6b..b673a03624d2 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -439,7 +439,7 @@ static int ct_cpu_seq_show(struct seq_file *seq, void *v)
 		   st->found,
 		   0,
 		   st->invalid,
-		   st->ignore,
+		   0,
 		   0,
 		   0,
 		   st->insert,
-- 
cgit v1.2.3


From bc92470413f3af152db0d8f90ef3eb13f8cc417a Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 26 Aug 2020 00:52:44 +0200
Subject: netfilter: conntrack: add clash resolution stat counter

There is a misconception about what "insert_failed" means.

We increment this even when a clash got resolved, so it might not indicate
a problem.

Add a dedicated counter for clash resolution and only increment
insert_failed if a clash cannot be resolved.

For the old /proc interface, export this in place of an older stat
that got removed a while back.
For ctnetlink, export this with a new attribute.

Also correct an outdated comment that implies we add a duplicate tuple --
we only add the (unique) reply direction.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/nf_conntrack_common.h      | 1 +
 include/uapi/linux/netfilter/nfnetlink_conntrack.h | 1 +
 net/netfilter/nf_conntrack_core.c                  | 9 +++++----
 net/netfilter/nf_conntrack_netlink.c               | 4 +++-
 net/netfilter/nf_conntrack_standalone.c            | 2 +-
 5 files changed, 11 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h
index 96b90d7e361f..0c7d8d1e945d 100644
--- a/include/linux/netfilter/nf_conntrack_common.h
+++ b/include/linux/netfilter/nf_conntrack_common.h
@@ -10,6 +10,7 @@ struct ip_conntrack_stat {
 	unsigned int invalid;
 	unsigned int insert;
 	unsigned int insert_failed;
+	unsigned int clash_resolve;
 	unsigned int drop;
 	unsigned int early_drop;
 	unsigned int error;
diff --git a/include/uapi/linux/netfilter/nfnetlink_conntrack.h b/include/uapi/linux/netfilter/nfnetlink_conntrack.h
index 3e471558da82..d8484be72fdc 100644
--- a/include/uapi/linux/netfilter/nfnetlink_conntrack.h
+++ b/include/uapi/linux/netfilter/nfnetlink_conntrack.h
@@ -256,6 +256,7 @@ enum ctattr_stats_cpu {
 	CTA_STATS_EARLY_DROP,
 	CTA_STATS_ERROR,
 	CTA_STATS_SEARCH_RESTART,
+	CTA_STATS_CLASH_RESOLVE,
 	__CTA_STATS_MAX,
 };
 #define CTA_STATS_MAX (__CTA_STATS_MAX - 1)
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index a111bcf1b93c..93e77ca0efad 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -859,7 +859,6 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct)
 
 out:
 	nf_conntrack_double_unlock(hash, reply_hash);
-	NF_CT_STAT_INC(net, insert_failed);
 	local_bh_enable();
 	return -EEXIST;
 }
@@ -934,7 +933,7 @@ static int __nf_ct_resolve_clash(struct sk_buff *skb,
 		nf_conntrack_put(&loser_ct->ct_general);
 		nf_ct_set(skb, ct, ctinfo);
 
-		NF_CT_STAT_INC(net, insert_failed);
+		NF_CT_STAT_INC(net, clash_resolve);
 		return NF_ACCEPT;
 	}
 
@@ -998,6 +997,8 @@ static int nf_ct_resolve_clash_harder(struct sk_buff *skb, u32 repl_idx)
 
 	hlist_nulls_add_head_rcu(&loser_ct->tuplehash[IP_CT_DIR_REPLY].hnnode,
 				 &nf_conntrack_hash[repl_idx]);
+
+	NF_CT_STAT_INC(net, clash_resolve);
 	return NF_ACCEPT;
 }
 
@@ -1027,10 +1028,10 @@ static int nf_ct_resolve_clash_harder(struct sk_buff *skb, u32 repl_idx)
  *
  * Failing that, the new, unconfirmed conntrack is still added to the table
  * provided that the collision only occurs in the ORIGINAL direction.
- * The new entry will be added after the existing one in the hash list,
+ * The new entry will be added only in the non-clashing REPLY direction,
  * so packets in the ORIGINAL direction will continue to match the existing
  * entry.  The new entry will also have a fixed timeout so it expires --
- * due to the collision, it will not see bidirectional traffic.
+ * due to the collision, it will only see reply traffic.
  *
  * Returns NF_DROP if the clash could not be resolved.
  */
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index c64f23a8f373..89d99f6dfd0a 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -2516,7 +2516,9 @@ ctnetlink_ct_stat_cpu_fill_info(struct sk_buff *skb, u32 portid, u32 seq,
 	    nla_put_be32(skb, CTA_STATS_EARLY_DROP, htonl(st->early_drop)) ||
 	    nla_put_be32(skb, CTA_STATS_ERROR, htonl(st->error)) ||
 	    nla_put_be32(skb, CTA_STATS_SEARCH_RESTART,
-				htonl(st->search_restart)))
+				htonl(st->search_restart)) ||
+	    nla_put_be32(skb, CTA_STATS_CLASH_RESOLVE,
+				htonl(st->clash_resolve)))
 		goto nla_put_failure;
 
 	nlmsg_end(skb, nlh);
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index b673a03624d2..0ff39740797d 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -435,7 +435,7 @@ static int ct_cpu_seq_show(struct seq_file *seq, void *v)
 	seq_printf(seq, "%08x  %08x %08x %08x %08x %08x %08x %08x "
 			"%08x %08x %08x %08x %08x  %08x %08x %08x %08x\n",
 		   nr_conntracks,
-		   0,
+		   st->clash_resolve, /* was: searched */
 		   st->found,
 		   0,
 		   st->invalid,
-- 
cgit v1.2.3


From 1e6c62a8821557720a9b2ea9617359b264f2f67c Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Thu, 27 Aug 2020 15:01:11 -0700
Subject: bpf: Introduce sleepable BPF programs

Introduce sleepable BPF programs that can request such property for themselves
via BPF_F_SLEEPABLE flag at program load time. In such case they will be able
to use helpers like bpf_copy_from_user() that might sleep. At present only
fentry/fexit/fmod_ret and lsm programs can request to be sleepable and only
when they are attached to kernel functions that are known to allow sleeping.

The non-sleepable programs are relying on implicit rcu_read_lock() and
migrate_disable() to protect life time of programs, maps that they use and
per-cpu kernel structures used to pass info between bpf programs and the
kernel. The sleepable programs cannot be enclosed into rcu_read_lock().
migrate_disable() maps to preempt_disable() in non-RT kernels, so the progs
should not be enclosed in migrate_disable() as well. Therefore
rcu_read_lock_trace is used to protect the life time of sleepable progs.

There are many networking and tracing program types. In many cases the
'struct bpf_prog *' pointer itself is rcu protected within some other kernel
data structure and the kernel code is using rcu_dereference() to load that
program pointer and call BPF_PROG_RUN() on it. All these cases are not touched.
Instead sleepable bpf programs are allowed with bpf trampoline only. The
program pointers are hard-coded into generated assembly of bpf trampoline and
synchronize_rcu_tasks_trace() is used to protect the life time of the program.
The same trampoline can hold both sleepable and non-sleepable progs.

When rcu_read_lock_trace is held it means that some sleepable bpf program is
running from bpf trampoline. Those programs can use bpf arrays and preallocated
hash/lru maps. These map types are waiting on programs to complete via
synchronize_rcu_tasks_trace();

Updates to trampoline now has to do synchronize_rcu_tasks_trace() and
synchronize_rcu_tasks() to wait for sleepable progs to finish and for
trampoline assembly to finish.

This is the first step of introducing sleepable progs. Eventually dynamically
allocated hash maps can be allowed and networking program types can become
sleepable too.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: KP Singh <kpsingh@google.com>
Link: https://lore.kernel.org/bpf/20200827220114.69225-3-alexei.starovoitov@gmail.com
---
 arch/x86/net/bpf_jit_comp.c    | 32 +++++++++++------
 include/linux/bpf.h            |  3 ++
 include/uapi/linux/bpf.h       |  8 +++++
 init/Kconfig                   |  1 +
 kernel/bpf/arraymap.c          |  1 +
 kernel/bpf/hashtab.c           | 12 +++----
 kernel/bpf/syscall.c           | 13 +++++--
 kernel/bpf/trampoline.c        | 28 +++++++++++++--
 kernel/bpf/verifier.c          | 81 ++++++++++++++++++++++++++++++++++++++++--
 tools/include/uapi/linux/bpf.h |  8 +++++
 10 files changed, 162 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 42b6709e6dc7..7d9ea7b41c71 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1379,10 +1379,15 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 	u8 *prog = *pprog;
 	int cnt = 0;
 
-	if (emit_call(&prog, __bpf_prog_enter, prog))
-		return -EINVAL;
-	/* remember prog start time returned by __bpf_prog_enter */
-	emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0);
+	if (p->aux->sleepable) {
+		if (emit_call(&prog, __bpf_prog_enter_sleepable, prog))
+			return -EINVAL;
+	} else {
+		if (emit_call(&prog, __bpf_prog_enter, prog))
+			return -EINVAL;
+		/* remember prog start time returned by __bpf_prog_enter */
+		emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0);
+	}
 
 	/* arg1: lea rdi, [rbp - stack_size] */
 	EMIT4(0x48, 0x8D, 0x7D, -stack_size);
@@ -1402,13 +1407,18 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 	if (mod_ret)
 		emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8);
 
-	/* arg1: mov rdi, progs[i] */
-	emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32,
-		       (u32) (long) p);
-	/* arg2: mov rsi, rbx <- start time in nsec */
-	emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6);
-	if (emit_call(&prog, __bpf_prog_exit, prog))
-		return -EINVAL;
+	if (p->aux->sleepable) {
+		if (emit_call(&prog, __bpf_prog_exit_sleepable, prog))
+			return -EINVAL;
+	} else {
+		/* arg1: mov rdi, progs[i] */
+		emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32,
+			       (u32) (long) p);
+		/* arg2: mov rsi, rbx <- start time in nsec */
+		emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6);
+		if (emit_call(&prog, __bpf_prog_exit, prog))
+			return -EINVAL;
+	}
 
 	*pprog = prog;
 	return 0;
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index dbba82a80087..4dd7e927621d 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -539,6 +539,8 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end,
 /* these two functions are called from generated trampoline */
 u64 notrace __bpf_prog_enter(void);
 void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start);
+void notrace __bpf_prog_enter_sleepable(void);
+void notrace __bpf_prog_exit_sleepable(void);
 
 struct bpf_ksym {
 	unsigned long		 start;
@@ -734,6 +736,7 @@ struct bpf_prog_aux {
 	bool offload_requested;
 	bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */
 	bool func_proto_unreliable;
+	bool sleepable;
 	enum bpf_tramp_prog_type trampoline_prog_type;
 	struct bpf_trampoline *trampoline;
 	struct hlist_node tramp_hlist;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index ef7af384f5ee..6e8b706aeb05 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -346,6 +346,14 @@ enum bpf_link_type {
 /* The verifier internal test flag. Behavior is undefined */
 #define BPF_F_TEST_STATE_FREQ	(1U << 3)
 
+/* If BPF_F_SLEEPABLE is used in BPF_PROG_LOAD command, the verifier will
+ * restrict map and helper usage for such programs. Sleepable BPF programs can
+ * only be attached to hooks where kernel execution context allows sleeping.
+ * Such programs are allowed to use helpers that may sleep like
+ * bpf_copy_from_user().
+ */
+#define BPF_F_SLEEPABLE		(1U << 4)
+
 /* When BPF ldimm64's insn[0].src_reg != 0 then this can have
  * two extensions:
  *
diff --git a/init/Kconfig b/init/Kconfig
index fc10f7ede5f6..6ecc00e130ff 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1691,6 +1691,7 @@ config BPF_SYSCALL
 	bool "Enable bpf() system call"
 	select BPF
 	select IRQ_WORK
+	select TASKS_TRACE_RCU
 	default n
 	help
 	  Enable the bpf() system call that allows to manipulate eBPF
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index d851ebbcf302..e046fb7d17cd 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -10,6 +10,7 @@
 #include <linux/filter.h>
 #include <linux/perf_event.h>
 #include <uapi/linux/btf.h>
+#include <linux/rcupdate_trace.h>
 
 #include "map_in_map.h"
 
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index ad80f45774e7..fe0e06284d33 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -9,6 +9,7 @@
 #include <linux/rculist_nulls.h>
 #include <linux/random.h>
 #include <uapi/linux/btf.h>
+#include <linux/rcupdate_trace.h>
 #include "percpu_freelist.h"
 #include "bpf_lru_list.h"
 #include "map_in_map.h"
@@ -577,8 +578,7 @@ static void *__htab_map_lookup_elem(struct bpf_map *map, void *key)
 	struct htab_elem *l;
 	u32 hash, key_size;
 
-	/* Must be called with rcu_read_lock. */
-	WARN_ON_ONCE(!rcu_read_lock_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held());
 
 	key_size = map->key_size;
 
@@ -941,7 +941,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
 		/* unknown flags */
 		return -EINVAL;
 
-	WARN_ON_ONCE(!rcu_read_lock_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held());
 
 	key_size = map->key_size;
 
@@ -1032,7 +1032,7 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value,
 		/* unknown flags */
 		return -EINVAL;
 
-	WARN_ON_ONCE(!rcu_read_lock_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held());
 
 	key_size = map->key_size;
 
@@ -1220,7 +1220,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key)
 	u32 hash, key_size;
 	int ret = -ENOENT;
 
-	WARN_ON_ONCE(!rcu_read_lock_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held());
 
 	key_size = map->key_size;
 
@@ -1252,7 +1252,7 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key)
 	u32 hash, key_size;
 	int ret = -ENOENT;
 
-	WARN_ON_ONCE(!rcu_read_lock_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held());
 
 	key_size = map->key_size;
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index b86b1155b748..4108ef3b828b 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -29,6 +29,7 @@
 #include <linux/bpf_lsm.h>
 #include <linux/poll.h>
 #include <linux/bpf-netns.h>
+#include <linux/rcupdate_trace.h>
 
 #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
 			  (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \
@@ -1731,10 +1732,14 @@ static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred)
 	btf_put(prog->aux->btf);
 	bpf_prog_free_linfo(prog);
 
-	if (deferred)
-		call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu);
-	else
+	if (deferred) {
+		if (prog->aux->sleepable)
+			call_rcu_tasks_trace(&prog->aux->rcu, __bpf_prog_put_rcu);
+		else
+			call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu);
+	} else {
 		__bpf_prog_put_rcu(&prog->aux->rcu);
+	}
 }
 
 static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
@@ -2104,6 +2109,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 	if (attr->prog_flags & ~(BPF_F_STRICT_ALIGNMENT |
 				 BPF_F_ANY_ALIGNMENT |
 				 BPF_F_TEST_STATE_FREQ |
+				 BPF_F_SLEEPABLE |
 				 BPF_F_TEST_RND_HI32))
 		return -EINVAL;
 
@@ -2159,6 +2165,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 	}
 
 	prog->aux->offload_requested = !!attr->prog_ifindex;
+	prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE;
 
 	err = security_bpf_prog_alloc(prog->aux);
 	if (err)
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 9be85aa4ec5f..c2b76545153c 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -7,6 +7,8 @@
 #include <linux/rbtree_latch.h>
 #include <linux/perf_event.h>
 #include <linux/btf.h>
+#include <linux/rcupdate_trace.h>
+#include <linux/rcupdate_wait.h>
 
 /* dummy _ops. The verifier will operate on target program's ops. */
 const struct bpf_verifier_ops bpf_extension_verifier_ops = {
@@ -210,9 +212,12 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr)
 	 * updates to trampoline would change the code from underneath the
 	 * preempted task. Hence wait for tasks to voluntarily schedule or go
 	 * to userspace.
+	 * The same trampoline can hold both sleepable and non-sleepable progs.
+	 * synchronize_rcu_tasks_trace() is needed to make sure all sleepable
+	 * programs finish executing.
+	 * Wait for these two grace periods together.
 	 */
-
-	synchronize_rcu_tasks();
+	synchronize_rcu_mult(call_rcu_tasks, call_rcu_tasks_trace);
 
 	err = arch_prepare_bpf_trampoline(new_image, new_image + PAGE_SIZE / 2,
 					  &tr->func.model, flags, tprogs,
@@ -344,7 +349,14 @@ void bpf_trampoline_put(struct bpf_trampoline *tr)
 	if (WARN_ON_ONCE(!hlist_empty(&tr->progs_hlist[BPF_TRAMP_FEXIT])))
 		goto out;
 	bpf_image_ksym_del(&tr->ksym);
-	/* wait for tasks to get out of trampoline before freeing it */
+	/* This code will be executed when all bpf progs (both sleepable and
+	 * non-sleepable) went through
+	 * bpf_prog_put()->call_rcu[_tasks_trace]()->bpf_prog_free_deferred().
+	 * Hence no need for another synchronize_rcu_tasks_trace() here,
+	 * but synchronize_rcu_tasks() is still needed, since trampoline
+	 * may not have had any sleepable programs and we need to wait
+	 * for tasks to get out of trampoline code before freeing it.
+	 */
 	synchronize_rcu_tasks();
 	bpf_jit_free_exec(tr->image);
 	hlist_del(&tr->hlist);
@@ -394,6 +406,16 @@ void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start)
 	rcu_read_unlock();
 }
 
+void notrace __bpf_prog_enter_sleepable(void)
+{
+	rcu_read_lock_trace();
+}
+
+void notrace __bpf_prog_exit_sleepable(void)
+{
+	rcu_read_unlock_trace();
+}
+
 int __weak
 arch_prepare_bpf_trampoline(void *image, void *image_end,
 			    const struct btf_func_model *m, u32 flags,
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 6f5a9f51cc03..3ebfdb7bd427 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -21,6 +21,7 @@
 #include <linux/ctype.h>
 #include <linux/error-injection.h>
 #include <linux/bpf_lsm.h>
+#include <linux/btf_ids.h>
 
 #include "disasm.h"
 
@@ -9367,6 +9368,23 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env,
 		return -EINVAL;
 	}
 
+	if (prog->aux->sleepable)
+		switch (map->map_type) {
+		case BPF_MAP_TYPE_HASH:
+		case BPF_MAP_TYPE_LRU_HASH:
+		case BPF_MAP_TYPE_ARRAY:
+			if (!is_preallocated_map(map)) {
+				verbose(env,
+					"Sleepable programs can only use preallocated hash maps\n");
+				return -EINVAL;
+			}
+			break;
+		default:
+			verbose(env,
+				"Sleepable programs can only use array and hash maps\n");
+			return -EINVAL;
+		}
+
 	return 0;
 }
 
@@ -10985,6 +11003,36 @@ static int check_attach_modify_return(struct bpf_prog *prog, unsigned long addr)
 	return -EINVAL;
 }
 
+/* non exhaustive list of sleepable bpf_lsm_*() functions */
+BTF_SET_START(btf_sleepable_lsm_hooks)
+#ifdef CONFIG_BPF_LSM
+BTF_ID(func, bpf_lsm_file_mprotect)
+BTF_ID(func, bpf_lsm_bprm_committed_creds)
+#endif
+BTF_SET_END(btf_sleepable_lsm_hooks)
+
+static int check_sleepable_lsm_hook(u32 btf_id)
+{
+	return btf_id_set_contains(&btf_sleepable_lsm_hooks, btf_id);
+}
+
+/* list of non-sleepable functions that are otherwise on
+ * ALLOW_ERROR_INJECTION list
+ */
+BTF_SET_START(btf_non_sleepable_error_inject)
+/* Three functions below can be called from sleepable and non-sleepable context.
+ * Assume non-sleepable from bpf safety point of view.
+ */
+BTF_ID(func, __add_to_page_cache_locked)
+BTF_ID(func, should_fail_alloc_page)
+BTF_ID(func, should_failslab)
+BTF_SET_END(btf_non_sleepable_error_inject)
+
+static int check_non_sleepable_error_inject(u32 btf_id)
+{
+	return btf_id_set_contains(&btf_non_sleepable_error_inject, btf_id);
+}
+
 static int check_attach_btf_id(struct bpf_verifier_env *env)
 {
 	struct bpf_prog *prog = env->prog;
@@ -11002,6 +11050,12 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 	long addr;
 	u64 key;
 
+	if (prog->aux->sleepable && prog->type != BPF_PROG_TYPE_TRACING &&
+	    prog->type != BPF_PROG_TYPE_LSM) {
+		verbose(env, "Only fentry/fexit/fmod_ret and lsm programs can be sleepable\n");
+		return -EINVAL;
+	}
+
 	if (prog->type == BPF_PROG_TYPE_STRUCT_OPS)
 		return check_struct_ops_btf_id(env);
 
@@ -11210,13 +11264,36 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 			}
 		}
 
-		if (prog->expected_attach_type == BPF_MODIFY_RETURN) {
+		if (prog->aux->sleepable) {
+			ret = -EINVAL;
+			switch (prog->type) {
+			case BPF_PROG_TYPE_TRACING:
+				/* fentry/fexit/fmod_ret progs can be sleepable only if they are
+				 * attached to ALLOW_ERROR_INJECTION and are not in denylist.
+				 */
+				if (!check_non_sleepable_error_inject(btf_id) &&
+				    within_error_injection_list(addr))
+					ret = 0;
+				break;
+			case BPF_PROG_TYPE_LSM:
+				/* LSM progs check that they are attached to bpf_lsm_*() funcs.
+				 * Only some of them are sleepable.
+				 */
+				if (check_sleepable_lsm_hook(btf_id))
+					ret = 0;
+				break;
+			default:
+				break;
+			}
+			if (ret)
+				verbose(env, "%s is not sleepable\n",
+					prog->aux->attach_func_name);
+		} else if (prog->expected_attach_type == BPF_MODIFY_RETURN) {
 			ret = check_attach_modify_return(prog, addr);
 			if (ret)
 				verbose(env, "%s() is not modifiable\n",
 					prog->aux->attach_func_name);
 		}
-
 		if (ret)
 			goto out;
 		tr->func.addr = (void *)addr;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index ef7af384f5ee..6e8b706aeb05 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -346,6 +346,14 @@ enum bpf_link_type {
 /* The verifier internal test flag. Behavior is undefined */
 #define BPF_F_TEST_STATE_FREQ	(1U << 3)
 
+/* If BPF_F_SLEEPABLE is used in BPF_PROG_LOAD command, the verifier will
+ * restrict map and helper usage for such programs. Sleepable BPF programs can
+ * only be attached to hooks where kernel execution context allows sleeping.
+ * Such programs are allowed to use helpers that may sleep like
+ * bpf_copy_from_user().
+ */
+#define BPF_F_SLEEPABLE		(1U << 4)
+
 /* When BPF ldimm64's insn[0].src_reg != 0 then this can have
  * two extensions:
  *
-- 
cgit v1.2.3


From 07be4c4a3e7a0db148e44b16c5190e753d1c8569 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Thu, 27 Aug 2020 15:01:12 -0700
Subject: bpf: Add bpf_copy_from_user() helper.

Sleepable BPF programs can now use copy_from_user() to access user memory.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: KP Singh <kpsingh@google.com>
Link: https://lore.kernel.org/bpf/20200827220114.69225-4-alexei.starovoitov@gmail.com
---
 include/linux/bpf.h            |  1 +
 include/uapi/linux/bpf.h       |  8 ++++++++
 kernel/bpf/helpers.c           | 22 ++++++++++++++++++++++
 kernel/trace/bpf_trace.c       |  2 ++
 tools/include/uapi/linux/bpf.h |  8 ++++++++
 5 files changed, 41 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 4dd7e927621d..c6d9f2c444f4 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1784,6 +1784,7 @@ extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto;
 extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto;
 extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto;
 extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto;
+extern const struct bpf_func_proto bpf_copy_from_user_proto;
 
 const struct bpf_func_proto *bpf_tracing_func_proto(
 	enum bpf_func_id func_id, const struct bpf_prog *prog);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 6e8b706aeb05..a613750d5515 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3569,6 +3569,13 @@ union bpf_attr {
  *		On success, the strictly positive length of the string,
  *		including the trailing NUL character. On error, a negative
  *		value.
+ *
+ * long bpf_copy_from_user(void *dst, u32 size, const void *user_ptr)
+ * 	Description
+ * 		Read *size* bytes from user space address *user_ptr* and store
+ * 		the data in *dst*. This is a wrapper of copy_from_user().
+ * 	Return
+ * 		0 on success, or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3719,6 +3726,7 @@ union bpf_attr {
 	FN(inode_storage_get),		\
 	FN(inode_storage_delete),	\
 	FN(d_path),			\
+	FN(copy_from_user),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index be43ab3e619f..5cc7425ee476 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -601,6 +601,28 @@ const struct bpf_func_proto bpf_event_output_data_proto =  {
 	.arg5_type      = ARG_CONST_SIZE_OR_ZERO,
 };
 
+BPF_CALL_3(bpf_copy_from_user, void *, dst, u32, size,
+	   const void __user *, user_ptr)
+{
+	int ret = copy_from_user(dst, user_ptr, size);
+
+	if (unlikely(ret)) {
+		memset(dst, 0, size);
+		ret = -EFAULT;
+	}
+
+	return ret;
+}
+
+const struct bpf_func_proto bpf_copy_from_user_proto = {
+	.func		= bpf_copy_from_user,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
+	.arg3_type	= ARG_ANYTHING,
+};
+
 const struct bpf_func_proto bpf_get_current_task_proto __weak;
 const struct bpf_func_proto bpf_probe_read_user_proto __weak;
 const struct bpf_func_proto bpf_probe_read_user_str_proto __weak;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index d973d891f2e2..b2a5380eb187 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1228,6 +1228,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_jiffies64_proto;
 	case BPF_FUNC_get_task_stack:
 		return &bpf_get_task_stack_proto;
+	case BPF_FUNC_copy_from_user:
+		return prog->aux->sleepable ? &bpf_copy_from_user_proto : NULL;
 	default:
 		return NULL;
 	}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 6e8b706aeb05..a613750d5515 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3569,6 +3569,13 @@ union bpf_attr {
  *		On success, the strictly positive length of the string,
  *		including the trailing NUL character. On error, a negative
  *		value.
+ *
+ * long bpf_copy_from_user(void *dst, u32 size, const void *user_ptr)
+ * 	Description
+ * 		Read *size* bytes from user space address *user_ptr* and store
+ * 		the data in *dst*. This is a wrapper of copy_from_user().
+ * 	Return
+ * 		0 on success, or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3719,6 +3726,7 @@ union bpf_attr {
 	FN(inode_storage_get),		\
 	FN(inode_storage_delete),	\
 	FN(d_path),			\
+	FN(copy_from_user),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
-- 
cgit v1.2.3


From 9667305c6374df8672be46bc496f52f040999531 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Mon, 31 Aug 2020 08:51:55 -0700
Subject: bpf: Fix build without BPF_SYSCALL, but with BPF_JIT.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When CONFIG_BPF_SYSCALL is not set, but CONFIG_BPF_JIT=y
the kernel build fails:
In file included from ../kernel/bpf/trampoline.c:11:
../kernel/bpf/trampoline.c: In function ‘bpf_trampoline_update’:
../kernel/bpf/trampoline.c:220:39: error: ‘call_rcu_tasks_trace’ undeclared
../kernel/bpf/trampoline.c: In function ‘__bpf_prog_enter_sleepable’:
../kernel/bpf/trampoline.c:411:2: error: implicit declaration of function ‘rcu_read_lock_trace’
../kernel/bpf/trampoline.c: In function ‘__bpf_prog_exit_sleepable’:
../kernel/bpf/trampoline.c:416:2: error: implicit declaration of function ‘rcu_read_unlock_trace’

This is due to:
obj-$(CONFIG_BPF_JIT) += trampoline.o
obj-$(CONFIG_BPF_JIT) += dispatcher.o
There is a number of functions that arch/x86/net/bpf_jit_comp.c is
using from these two files, but none of them will be used when
only cBPF is on (which is the case for BPF_SYSCALL=n BPF_JIT=y).

Add rcu_trace functions to rcupdate_trace.h. The JITed code won't execute them
and BPF trampoline logic won't be used without BPF_SYSCALL.

Fixes: 1e6c62a88215 ("bpf: Introduce sleepable BPF programs")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Paul E. McKenney <paulmck@kernel.org>
Link: https://lore.kernel.org/bpf/20200831155155.62754-1-alexei.starovoitov@gmail.com
---
 include/linux/rcupdate_trace.h | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/rcupdate_trace.h b/include/linux/rcupdate_trace.h
index d9015aac78c6..aaaac8ac927c 100644
--- a/include/linux/rcupdate_trace.h
+++ b/include/linux/rcupdate_trace.h
@@ -82,7 +82,14 @@ static inline void rcu_read_unlock_trace(void)
 void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func);
 void synchronize_rcu_tasks_trace(void);
 void rcu_barrier_tasks_trace(void);
-
+#else
+/*
+ * The BPF JIT forms these addresses even when it doesn't call these
+ * functions, so provide definitions that result in runtime errors.
+ */
+static inline void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func) { BUG(); }
+static inline void rcu_read_lock_trace(void) { BUG(); }
+static inline void rcu_read_unlock_trace(void) { BUG(); }
 #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
 
 #endif /* __LINUX_RCUPDATE_TRACE_H */
-- 
cgit v1.2.3


From 1742b3d528690ae7773cf7bf2f01a90ee1de2fe0 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Fri, 28 Aug 2020 10:26:15 +0200
Subject: xsk: i40e: ice: ixgbe: mlx5: Pass buffer pool to driver instead of
 umem
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Replace the explicit umem reference passed to the driver in AF_XDP
zero-copy mode with the buffer pool instead. This in preparation for
extending the functionality of the zero-copy mode so that umems can be
shared between queues on the same netdev and also between netdevs. In
this commit, only an umem reference has been added to the buffer pool
struct. But later commits will add other entities to it. These are
going to be entities that are different between different queue ids
and netdevs even though the umem is shared between them.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Link: https://lore.kernel.org/bpf/1598603189-32145-2-git-send-email-magnus.karlsson@intel.com
---
 drivers/net/ethernet/intel/i40e/i40e_ethtool.c     |   2 +-
 drivers/net/ethernet/intel/i40e/i40e_main.c        |  29 +--
 drivers/net/ethernet/intel/i40e/i40e_txrx.c        |  10 +-
 drivers/net/ethernet/intel/i40e/i40e_txrx.h        |   2 +-
 drivers/net/ethernet/intel/i40e/i40e_xsk.c         |  81 ++++----
 drivers/net/ethernet/intel/i40e/i40e_xsk.h         |   4 +-
 drivers/net/ethernet/intel/ice/ice.h               |  18 +-
 drivers/net/ethernet/intel/ice/ice_base.c          |  16 +-
 drivers/net/ethernet/intel/ice/ice_lib.c           |   2 +-
 drivers/net/ethernet/intel/ice/ice_main.c          |  10 +-
 drivers/net/ethernet/intel/ice/ice_txrx.c          |   8 +-
 drivers/net/ethernet/intel/ice/ice_txrx.h          |   2 +-
 drivers/net/ethernet/intel/ice/ice_xsk.c           | 136 ++++++-------
 drivers/net/ethernet/intel/ice/ice_xsk.h           |   7 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe.h           |   2 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c      |  34 ++--
 .../net/ethernet/intel/ixgbe/ixgbe_txrx_common.h   |   7 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c       |  61 +++---
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   |   2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |  19 +-
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c   |   5 +-
 .../net/ethernet/mellanox/mlx5/core/en/xsk/pool.c  | 217 +++++++++++++++++++++
 .../net/ethernet/mellanox/mlx5/core/en/xsk/pool.h  |  27 +++
 .../net/ethernet/mellanox/mlx5/core/en/xsk/rx.h    |  10 +-
 .../net/ethernet/mellanox/mlx5/core/en/xsk/setup.c |  12 +-
 .../net/ethernet/mellanox/mlx5/core/en/xsk/setup.h |   2 +-
 .../net/ethernet/mellanox/mlx5/core/en/xsk/tx.c    |  14 +-
 .../net/ethernet/mellanox/mlx5/core/en/xsk/tx.h    |   6 +-
 .../net/ethernet/mellanox/mlx5/core/en/xsk/umem.c  | 217 ---------------------
 .../net/ethernet/mellanox/mlx5/core/en/xsk/umem.h  |  29 ---
 .../net/ethernet/mellanox/mlx5/core/en_ethtool.c   |   2 +-
 .../ethernet/mellanox/mlx5/core/en_fs_ethtool.c    |   2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  |  49 ++---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c    |  16 +-
 include/linux/netdevice.h                          |  10 +-
 include/net/xdp_sock_drv.h                         |   7 +-
 include/net/xsk_buff_pool.h                        |   4 +-
 net/ethtool/channels.c                             |   2 +-
 net/ethtool/ioctl.c                                |   2 +-
 net/xdp/xdp_umem.c                                 |  45 ++---
 net/xdp/xsk_buff_pool.c                            |   5 +-
 41 files changed, 575 insertions(+), 560 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.h
 delete mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.c
 delete mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.h

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 825c104ecba1..dc1577156bb6 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -1967,7 +1967,7 @@ static int i40e_set_ringparam(struct net_device *netdev,
 	    (new_rx_count == vsi->rx_rings[0]->count))
 		return 0;
 
-	/* If there is a AF_XDP UMEM attached to any of Rx rings,
+	/* If there is a AF_XDP page pool attached to any of Rx rings,
 	 * disallow changing the number of descriptors -- regardless
 	 * if the netdev is running or not.
 	 */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 2e433fdbf2c3..cbf2a4454499 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -3122,12 +3122,12 @@ static void i40e_config_xps_tx_ring(struct i40e_ring *ring)
 }
 
 /**
- * i40e_xsk_umem - Retrieve the AF_XDP ZC if XDP and ZC is enabled
+ * i40e_xsk_pool - Retrieve the AF_XDP buffer pool if XDP and ZC is enabled
  * @ring: The Tx or Rx ring
  *
- * Returns the UMEM or NULL.
+ * Returns the AF_XDP buffer pool or NULL.
  **/
-static struct xdp_umem *i40e_xsk_umem(struct i40e_ring *ring)
+static struct xsk_buff_pool *i40e_xsk_pool(struct i40e_ring *ring)
 {
 	bool xdp_on = i40e_enabled_xdp_vsi(ring->vsi);
 	int qid = ring->queue_index;
@@ -3138,7 +3138,7 @@ static struct xdp_umem *i40e_xsk_umem(struct i40e_ring *ring)
 	if (!xdp_on || !test_bit(qid, ring->vsi->af_xdp_zc_qps))
 		return NULL;
 
-	return xdp_get_umem_from_qid(ring->vsi->netdev, qid);
+	return xdp_get_xsk_pool_from_qid(ring->vsi->netdev, qid);
 }
 
 /**
@@ -3157,7 +3157,7 @@ static int i40e_configure_tx_ring(struct i40e_ring *ring)
 	u32 qtx_ctl = 0;
 
 	if (ring_is_xdp(ring))
-		ring->xsk_umem = i40e_xsk_umem(ring);
+		ring->xsk_pool = i40e_xsk_pool(ring);
 
 	/* some ATR related tx ring init */
 	if (vsi->back->flags & I40E_FLAG_FD_ATR_ENABLED) {
@@ -3280,12 +3280,13 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 		xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
 
 	kfree(ring->rx_bi);
-	ring->xsk_umem = i40e_xsk_umem(ring);
-	if (ring->xsk_umem) {
+	ring->xsk_pool = i40e_xsk_pool(ring);
+	if (ring->xsk_pool) {
 		ret = i40e_alloc_rx_bi_zc(ring);
 		if (ret)
 			return ret;
-		ring->rx_buf_len = xsk_umem_get_rx_frame_size(ring->xsk_umem);
+		ring->rx_buf_len =
+		  xsk_umem_get_rx_frame_size(ring->xsk_pool->umem);
 		/* For AF_XDP ZC, we disallow packets to span on
 		 * multiple buffers, thus letting us skip that
 		 * handling in the fast-path.
@@ -3368,8 +3369,8 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 	ring->tail = hw->hw_addr + I40E_QRX_TAIL(pf_q);
 	writel(0, ring->tail);
 
-	if (ring->xsk_umem) {
-		xsk_buff_set_rxq_info(ring->xsk_umem, &ring->xdp_rxq);
+	if (ring->xsk_pool) {
+		xsk_buff_set_rxq_info(ring->xsk_pool->umem, &ring->xdp_rxq);
 		ok = i40e_alloc_rx_buffers_zc(ring, I40E_DESC_UNUSED(ring));
 	} else {
 		ok = !i40e_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring));
@@ -3380,7 +3381,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 		 */
 		dev_info(&vsi->back->pdev->dev,
 			 "Failed to allocate some buffers on %sRx ring %d (pf_q %d)\n",
-			 ring->xsk_umem ? "UMEM enabled " : "",
+			 ring->xsk_pool ? "AF_XDP ZC enabled " : "",
 			 ring->queue_index, pf_q);
 	}
 
@@ -12644,7 +12645,7 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi,
 	 */
 	if (need_reset && prog)
 		for (i = 0; i < vsi->num_queue_pairs; i++)
-			if (vsi->xdp_rings[i]->xsk_umem)
+			if (vsi->xdp_rings[i]->xsk_pool)
 				(void)i40e_xsk_wakeup(vsi->netdev, i,
 						      XDP_WAKEUP_RX);
 
@@ -12923,8 +12924,8 @@ static int i40e_xdp(struct net_device *dev,
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return i40e_xdp_setup(vsi, xdp->prog);
-	case XDP_SETUP_XSK_UMEM:
-		return i40e_xsk_umem_setup(vsi, xdp->xsk.umem,
+	case XDP_SETUP_XSK_POOL:
+		return i40e_xsk_pool_setup(vsi, xdp->xsk.pool,
 					   xdp->xsk.queue_id);
 	default:
 		return -EINVAL;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 3e5c566ceb01..f14bfc33844c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -636,7 +636,7 @@ void i40e_clean_tx_ring(struct i40e_ring *tx_ring)
 	unsigned long bi_size;
 	u16 i;
 
-	if (ring_is_xdp(tx_ring) && tx_ring->xsk_umem) {
+	if (ring_is_xdp(tx_ring) && tx_ring->xsk_pool) {
 		i40e_xsk_clean_tx_ring(tx_ring);
 	} else {
 		/* ring already cleared, nothing to do */
@@ -1335,7 +1335,7 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring)
 		rx_ring->skb = NULL;
 	}
 
-	if (rx_ring->xsk_umem) {
+	if (rx_ring->xsk_pool) {
 		i40e_xsk_clean_rx_ring(rx_ring);
 		goto skip_free;
 	}
@@ -1369,7 +1369,7 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring)
 	}
 
 skip_free:
-	if (rx_ring->xsk_umem)
+	if (rx_ring->xsk_pool)
 		i40e_clear_rx_bi_zc(rx_ring);
 	else
 		i40e_clear_rx_bi(rx_ring);
@@ -2579,7 +2579,7 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
 	 * budget and be more aggressive about cleaning up the Tx descriptors.
 	 */
 	i40e_for_each_ring(ring, q_vector->tx) {
-		bool wd = ring->xsk_umem ?
+		bool wd = ring->xsk_pool ?
 			  i40e_clean_xdp_tx_irq(vsi, ring) :
 			  i40e_clean_tx_irq(vsi, ring, budget);
 
@@ -2607,7 +2607,7 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
 		budget_per_ring = budget;
 
 	i40e_for_each_ring(ring, q_vector->rx) {
-		int cleaned = ring->xsk_umem ?
+		int cleaned = ring->xsk_pool ?
 			      i40e_clean_rx_irq_zc(ring, budget_per_ring) :
 			      i40e_clean_rx_irq(ring, budget_per_ring);
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index 4036893d6825..703b644fd71f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -388,7 +388,7 @@ struct i40e_ring {
 
 	struct i40e_channel *ch;
 	struct xdp_rxq_info xdp_rxq;
-	struct xdp_umem *xsk_umem;
+	struct xsk_buff_pool *xsk_pool;
 } ____cacheline_internodealigned_in_smp;
 
 static inline bool ring_uses_build_skb(struct i40e_ring *ring)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index 8ce57b507a21..00e9fe6394f2 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -29,14 +29,16 @@ static struct xdp_buff **i40e_rx_bi(struct i40e_ring *rx_ring, u32 idx)
 }
 
 /**
- * i40e_xsk_umem_enable - Enable/associate a UMEM to a certain ring/qid
+ * i40e_xsk_pool_enable - Enable/associate an AF_XDP buffer pool to a
+ * certain ring/qid
  * @vsi: Current VSI
- * @umem: UMEM
- * @qid: Rx ring to associate UMEM to
+ * @pool: buffer pool
+ * @qid: Rx ring to associate buffer pool with
  *
  * Returns 0 on success, <0 on failure
  **/
-static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem,
+static int i40e_xsk_pool_enable(struct i40e_vsi *vsi,
+				struct xsk_buff_pool *pool,
 				u16 qid)
 {
 	struct net_device *netdev = vsi->netdev;
@@ -53,7 +55,8 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem,
 	    qid >= netdev->real_num_tx_queues)
 		return -EINVAL;
 
-	err = xsk_buff_dma_map(umem, &vsi->back->pdev->dev, I40E_RX_DMA_ATTR);
+	err = xsk_buff_dma_map(pool->umem, &vsi->back->pdev->dev,
+			       I40E_RX_DMA_ATTR);
 	if (err)
 		return err;
 
@@ -80,21 +83,22 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem,
 }
 
 /**
- * i40e_xsk_umem_disable - Disassociate a UMEM from a certain ring/qid
+ * i40e_xsk_pool_disable - Disassociate an AF_XDP buffer pool from a
+ * certain ring/qid
  * @vsi: Current VSI
- * @qid: Rx ring to associate UMEM to
+ * @qid: Rx ring to associate buffer pool with
  *
  * Returns 0 on success, <0 on failure
  **/
-static int i40e_xsk_umem_disable(struct i40e_vsi *vsi, u16 qid)
+static int i40e_xsk_pool_disable(struct i40e_vsi *vsi, u16 qid)
 {
 	struct net_device *netdev = vsi->netdev;
-	struct xdp_umem *umem;
+	struct xsk_buff_pool *pool;
 	bool if_running;
 	int err;
 
-	umem = xdp_get_umem_from_qid(netdev, qid);
-	if (!umem)
+	pool = xdp_get_xsk_pool_from_qid(netdev, qid);
+	if (!pool)
 		return -EINVAL;
 
 	if_running = netif_running(vsi->netdev) && i40e_enabled_xdp_vsi(vsi);
@@ -106,7 +110,7 @@ static int i40e_xsk_umem_disable(struct i40e_vsi *vsi, u16 qid)
 	}
 
 	clear_bit(qid, vsi->af_xdp_zc_qps);
-	xsk_buff_dma_unmap(umem, I40E_RX_DMA_ATTR);
+	xsk_buff_dma_unmap(pool->umem, I40E_RX_DMA_ATTR);
 
 	if (if_running) {
 		err = i40e_queue_pair_enable(vsi, qid);
@@ -118,20 +122,21 @@ static int i40e_xsk_umem_disable(struct i40e_vsi *vsi, u16 qid)
 }
 
 /**
- * i40e_xsk_umem_setup - Enable/disassociate a UMEM to/from a ring/qid
+ * i40e_xsk_pool_setup - Enable/disassociate an AF_XDP buffer pool to/from
+ * a ring/qid
  * @vsi: Current VSI
- * @umem: UMEM to enable/associate to a ring, or NULL to disable
- * @qid: Rx ring to (dis)associate UMEM (from)to
+ * @pool: Buffer pool to enable/associate to a ring, or NULL to disable
+ * @qid: Rx ring to (dis)associate buffer pool (from)to
  *
- * This function enables or disables a UMEM to a certain ring.
+ * This function enables or disables a buffer pool to a certain ring.
  *
  * Returns 0 on success, <0 on failure
  **/
-int i40e_xsk_umem_setup(struct i40e_vsi *vsi, struct xdp_umem *umem,
+int i40e_xsk_pool_setup(struct i40e_vsi *vsi, struct xsk_buff_pool *pool,
 			u16 qid)
 {
-	return umem ? i40e_xsk_umem_enable(vsi, umem, qid) :
-		i40e_xsk_umem_disable(vsi, qid);
+	return pool ? i40e_xsk_pool_enable(vsi, pool, qid) :
+		i40e_xsk_pool_disable(vsi, qid);
 }
 
 /**
@@ -191,7 +196,7 @@ bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count)
 	rx_desc = I40E_RX_DESC(rx_ring, ntu);
 	bi = i40e_rx_bi(rx_ring, ntu);
 	do {
-		xdp = xsk_buff_alloc(rx_ring->xsk_umem);
+		xdp = xsk_buff_alloc(rx_ring->xsk_pool->umem);
 		if (!xdp) {
 			ok = false;
 			goto no_buffers;
@@ -358,11 +363,11 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 	i40e_finalize_xdp_rx(rx_ring, xdp_xmit);
 	i40e_update_rx_stats(rx_ring, total_rx_bytes, total_rx_packets);
 
-	if (xsk_umem_uses_need_wakeup(rx_ring->xsk_umem)) {
+	if (xsk_umem_uses_need_wakeup(rx_ring->xsk_pool->umem)) {
 		if (failure || rx_ring->next_to_clean == rx_ring->next_to_use)
-			xsk_set_rx_need_wakeup(rx_ring->xsk_umem);
+			xsk_set_rx_need_wakeup(rx_ring->xsk_pool->umem);
 		else
-			xsk_clear_rx_need_wakeup(rx_ring->xsk_umem);
+			xsk_clear_rx_need_wakeup(rx_ring->xsk_pool->umem);
 
 		return (int)total_rx_packets;
 	}
@@ -385,11 +390,12 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget)
 	dma_addr_t dma;
 
 	while (budget-- > 0) {
-		if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &desc))
+		if (!xsk_umem_consume_tx(xdp_ring->xsk_pool->umem, &desc))
 			break;
 
-		dma = xsk_buff_raw_get_dma(xdp_ring->xsk_umem, desc.addr);
-		xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_umem, dma,
+		dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool->umem,
+					   desc.addr);
+		xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool->umem, dma,
 						 desc.len);
 
 		tx_bi = &xdp_ring->tx_bi[xdp_ring->next_to_use];
@@ -416,7 +422,7 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget)
 						 I40E_TXD_QW1_CMD_SHIFT);
 		i40e_xdp_ring_update_tail(xdp_ring);
 
-		xsk_umem_consume_tx_done(xdp_ring->xsk_umem);
+		xsk_umem_consume_tx_done(xdp_ring->xsk_pool->umem);
 		i40e_update_tx_stats(xdp_ring, sent_frames, total_bytes);
 	}
 
@@ -448,7 +454,7 @@ static void i40e_clean_xdp_tx_buffer(struct i40e_ring *tx_ring,
  **/
 bool i40e_clean_xdp_tx_irq(struct i40e_vsi *vsi, struct i40e_ring *tx_ring)
 {
-	struct xdp_umem *umem = tx_ring->xsk_umem;
+	struct xsk_buff_pool *bp = tx_ring->xsk_pool;
 	u32 i, completed_frames, xsk_frames = 0;
 	u32 head_idx = i40e_get_head(tx_ring);
 	struct i40e_tx_buffer *tx_bi;
@@ -488,13 +494,13 @@ skip:
 		tx_ring->next_to_clean -= tx_ring->count;
 
 	if (xsk_frames)
-		xsk_umem_complete_tx(umem, xsk_frames);
+		xsk_umem_complete_tx(bp->umem, xsk_frames);
 
 	i40e_arm_wb(tx_ring, vsi, completed_frames);
 
 out_xmit:
-	if (xsk_umem_uses_need_wakeup(tx_ring->xsk_umem))
-		xsk_set_tx_need_wakeup(tx_ring->xsk_umem);
+	if (xsk_umem_uses_need_wakeup(tx_ring->xsk_pool->umem))
+		xsk_set_tx_need_wakeup(tx_ring->xsk_pool->umem);
 
 	return i40e_xmit_zc(tx_ring, I40E_DESC_UNUSED(tx_ring));
 }
@@ -526,7 +532,7 @@ int i40e_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags)
 	if (queue_id >= vsi->num_queue_pairs)
 		return -ENXIO;
 
-	if (!vsi->xdp_rings[queue_id]->xsk_umem)
+	if (!vsi->xdp_rings[queue_id]->xsk_pool)
 		return -ENXIO;
 
 	ring = vsi->xdp_rings[queue_id];
@@ -565,7 +571,7 @@ void i40e_xsk_clean_rx_ring(struct i40e_ring *rx_ring)
 void i40e_xsk_clean_tx_ring(struct i40e_ring *tx_ring)
 {
 	u16 ntc = tx_ring->next_to_clean, ntu = tx_ring->next_to_use;
-	struct xdp_umem *umem = tx_ring->xsk_umem;
+	struct xsk_buff_pool *bp = tx_ring->xsk_pool;
 	struct i40e_tx_buffer *tx_bi;
 	u32 xsk_frames = 0;
 
@@ -585,14 +591,15 @@ void i40e_xsk_clean_tx_ring(struct i40e_ring *tx_ring)
 	}
 
 	if (xsk_frames)
-		xsk_umem_complete_tx(umem, xsk_frames);
+		xsk_umem_complete_tx(bp->umem, xsk_frames);
 }
 
 /**
- * i40e_xsk_any_rx_ring_enabled - Checks if Rx rings have AF_XDP UMEM attached
+ * i40e_xsk_any_rx_ring_enabled - Checks if Rx rings have an AF_XDP
+ * buffer pool attached
  * @vsi: vsi
  *
- * Returns true if any of the Rx rings has an AF_XDP UMEM attached
+ * Returns true if any of the Rx rings has an AF_XDP buffer pool attached
  **/
 bool i40e_xsk_any_rx_ring_enabled(struct i40e_vsi *vsi)
 {
@@ -600,7 +607,7 @@ bool i40e_xsk_any_rx_ring_enabled(struct i40e_vsi *vsi)
 	int i;
 
 	for (i = 0; i < vsi->num_queue_pairs; i++) {
-		if (xdp_get_umem_from_qid(netdev, i))
+		if (xdp_get_xsk_pool_from_qid(netdev, i))
 			return true;
 	}
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h
index c524c142127f..7adfd8539247 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.h
@@ -5,12 +5,12 @@
 #define _I40E_XSK_H_
 
 struct i40e_vsi;
-struct xdp_umem;
+struct xsk_buff_pool;
 struct zero_copy_allocator;
 
 int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair);
 int i40e_queue_pair_enable(struct i40e_vsi *vsi, int queue_pair);
-int i40e_xsk_umem_setup(struct i40e_vsi *vsi, struct xdp_umem *umem,
+int i40e_xsk_pool_setup(struct i40e_vsi *vsi, struct xsk_buff_pool *pool,
 			u16 qid);
 bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 cleaned_count);
 int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget);
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index fe140ff38f74..65583f0a1797 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -321,9 +321,9 @@ struct ice_vsi {
 	struct ice_ring **xdp_rings;	 /* XDP ring array */
 	u16 num_xdp_txq;		 /* Used XDP queues */
 	u8 xdp_mapping_mode;		 /* ICE_MAP_MODE_[CONTIG|SCATTER] */
-	struct xdp_umem **xsk_umems;
-	u16 num_xsk_umems_used;
-	u16 num_xsk_umems;
+	struct xsk_buff_pool **xsk_pools;
+	u16 num_xsk_pools_used;
+	u16 num_xsk_pools;
 } ____cacheline_internodealigned_in_smp;
 
 /* struct that defines an interrupt vector */
@@ -507,25 +507,25 @@ static inline void ice_set_ring_xdp(struct ice_ring *ring)
 }
 
 /**
- * ice_xsk_umem - get XDP UMEM bound to a ring
+ * ice_xsk_pool - get XSK buffer pool bound to a ring
  * @ring - ring to use
  *
- * Returns a pointer to xdp_umem structure if there is an UMEM present,
+ * Returns a pointer to xdp_umem structure if there is a buffer pool present,
  * NULL otherwise.
  */
-static inline struct xdp_umem *ice_xsk_umem(struct ice_ring *ring)
+static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_ring *ring)
 {
-	struct xdp_umem **umems = ring->vsi->xsk_umems;
+	struct xsk_buff_pool **pools = ring->vsi->xsk_pools;
 	u16 qid = ring->q_index;
 
 	if (ice_ring_is_xdp(ring))
 		qid -= ring->vsi->num_xdp_txq;
 
-	if (qid >= ring->vsi->num_xsk_umems || !umems || !umems[qid] ||
+	if (qid >= ring->vsi->num_xsk_pools || !pools || !pools[qid] ||
 	    !ice_is_xdp_ena_vsi(ring->vsi))
 		return NULL;
 
-	return umems[qid];
+	return pools[qid];
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 87008476d8fe..3c92448e2554 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -308,12 +308,12 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 			xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
 					 ring->q_index);
 
-		ring->xsk_umem = ice_xsk_umem(ring);
-		if (ring->xsk_umem) {
+		ring->xsk_pool = ice_xsk_pool(ring);
+		if (ring->xsk_pool) {
 			xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
 
 			ring->rx_buf_len =
-				xsk_umem_get_rx_frame_size(ring->xsk_umem);
+				xsk_umem_get_rx_frame_size(ring->xsk_pool->umem);
 			/* For AF_XDP ZC, we disallow packets to span on
 			 * multiple buffers, thus letting us skip that
 			 * handling in the fast-path.
@@ -324,7 +324,7 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 							 NULL);
 			if (err)
 				return err;
-			xsk_buff_set_rxq_info(ring->xsk_umem, &ring->xdp_rxq);
+			xsk_buff_set_rxq_info(ring->xsk_pool->umem, &ring->xdp_rxq);
 
 			dev_info(dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n",
 				 ring->q_index);
@@ -417,9 +417,9 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 	ring->tail = hw->hw_addr + QRX_TAIL(pf_q);
 	writel(0, ring->tail);
 
-	if (ring->xsk_umem) {
-		if (!xsk_buff_can_alloc(ring->xsk_umem, num_bufs)) {
-			dev_warn(dev, "UMEM does not provide enough addresses to fill %d buffers on Rx ring %d\n",
+	if (ring->xsk_pool) {
+		if (!xsk_buff_can_alloc(ring->xsk_pool->umem, num_bufs)) {
+			dev_warn(dev, "XSK buffer pool does not provide enough addresses to fill %d buffers on Rx ring %d\n",
 				 num_bufs, ring->q_index);
 			dev_warn(dev, "Change Rx ring/fill queue size to avoid performance issues\n");
 
@@ -428,7 +428,7 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 
 		err = ice_alloc_rx_bufs_zc(ring, num_bufs);
 		if (err)
-			dev_info(dev, "Failed to allocate some buffers on UMEM enabled Rx ring %d (pf_q %d)\n",
+			dev_info(dev, "Failed to allocate some buffers on XSK buffer pool enabled Rx ring %d (pf_q %d)\n",
 				 ring->q_index, pf_q);
 		return 0;
 	}
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index f2682776f8c8..feeb5cdccdc5 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -1743,7 +1743,7 @@ int ice_vsi_cfg_xdp_txqs(struct ice_vsi *vsi)
 		return ret;
 
 	for (i = 0; i < vsi->num_xdp_txq; i++)
-		vsi->xdp_rings[i]->xsk_umem = ice_xsk_umem(vsi->xdp_rings[i]);
+		vsi->xdp_rings[i]->xsk_pool = ice_xsk_pool(vsi->xdp_rings[i]);
 
 	return ret;
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 4634b48949bb..2297ee7dba26 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2273,7 +2273,7 @@ static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi)
 		if (ice_setup_tx_ring(xdp_ring))
 			goto free_xdp_rings;
 		ice_set_ring_xdp(xdp_ring);
-		xdp_ring->xsk_umem = ice_xsk_umem(xdp_ring);
+		xdp_ring->xsk_pool = ice_xsk_pool(xdp_ring);
 	}
 
 	return 0;
@@ -2517,13 +2517,13 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
 	if (if_running)
 		ret = ice_up(vsi);
 
-	if (!ret && prog && vsi->xsk_umems) {
+	if (!ret && prog && vsi->xsk_pools) {
 		int i;
 
 		ice_for_each_rxq(vsi, i) {
 			struct ice_ring *rx_ring = vsi->rx_rings[i];
 
-			if (rx_ring->xsk_umem)
+			if (rx_ring->xsk_pool)
 				napi_schedule(&rx_ring->q_vector->napi);
 		}
 	}
@@ -2549,8 +2549,8 @@ static int ice_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return ice_xdp_setup_prog(vsi, xdp->prog, xdp->extack);
-	case XDP_SETUP_XSK_UMEM:
-		return ice_xsk_umem_setup(vsi, xdp->xsk.umem,
+	case XDP_SETUP_XSK_POOL:
+		return ice_xsk_pool_setup(vsi, xdp->xsk.pool,
 					  xdp->xsk.queue_id);
 	default:
 		return -EINVAL;
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 9d0d6b0025cf..b061dc10703d 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -145,7 +145,7 @@ void ice_clean_tx_ring(struct ice_ring *tx_ring)
 {
 	u16 i;
 
-	if (ice_ring_is_xdp(tx_ring) && tx_ring->xsk_umem) {
+	if (ice_ring_is_xdp(tx_ring) && tx_ring->xsk_pool) {
 		ice_xsk_clean_xdp_ring(tx_ring);
 		goto tx_skip_free;
 	}
@@ -375,7 +375,7 @@ void ice_clean_rx_ring(struct ice_ring *rx_ring)
 	if (!rx_ring->rx_buf)
 		return;
 
-	if (rx_ring->xsk_umem) {
+	if (rx_ring->xsk_pool) {
 		ice_xsk_clean_rx_ring(rx_ring);
 		goto rx_skip_free;
 	}
@@ -1616,7 +1616,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 	 * budget and be more aggressive about cleaning up the Tx descriptors.
 	 */
 	ice_for_each_ring(ring, q_vector->tx) {
-		bool wd = ring->xsk_umem ?
+		bool wd = ring->xsk_pool ?
 			  ice_clean_tx_irq_zc(ring, budget) :
 			  ice_clean_tx_irq(ring, budget);
 
@@ -1646,7 +1646,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 		 * comparison in the irq context instead of many inside the
 		 * ice_clean_rx_irq function and makes the codebase cleaner.
 		 */
-		cleaned = ring->xsk_umem ?
+		cleaned = ring->xsk_pool ?
 			  ice_clean_rx_irq_zc(ring, budget_per_ring) :
 			  ice_clean_rx_irq(ring, budget_per_ring);
 		work_done += cleaned;
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index 51b4df7a59d2..e9f60d550fcb 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -295,7 +295,7 @@ struct ice_ring {
 
 	struct rcu_head rcu;		/* to avoid race on free */
 	struct bpf_prog *xdp_prog;
-	struct xdp_umem *xsk_umem;
+	struct xsk_buff_pool *xsk_pool;
 	/* CL3 - 3rd cacheline starts here */
 	struct xdp_rxq_info xdp_rxq;
 	/* CLX - the below items are only accessed infrequently and should be
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 20ac5fca68c6..8b70e8c5bc3a 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -236,7 +236,7 @@ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx)
 		if (err)
 			goto free_buf;
 		ice_set_ring_xdp(xdp_ring);
-		xdp_ring->xsk_umem = ice_xsk_umem(xdp_ring);
+		xdp_ring->xsk_pool = ice_xsk_pool(xdp_ring);
 	}
 
 	err = ice_setup_rx_ctx(rx_ring);
@@ -260,21 +260,21 @@ free_buf:
 }
 
 /**
- * ice_xsk_alloc_umems - allocate a UMEM region for an XDP socket
- * @vsi: VSI to allocate the UMEM on
+ * ice_xsk_alloc_pools - allocate a buffer pool for an XDP socket
+ * @vsi: VSI to allocate the buffer pool on
  *
  * Returns 0 on success, negative on error
  */
-static int ice_xsk_alloc_umems(struct ice_vsi *vsi)
+static int ice_xsk_alloc_pools(struct ice_vsi *vsi)
 {
-	if (vsi->xsk_umems)
+	if (vsi->xsk_pools)
 		return 0;
 
-	vsi->xsk_umems = kcalloc(vsi->num_xsk_umems, sizeof(*vsi->xsk_umems),
+	vsi->xsk_pools = kcalloc(vsi->num_xsk_pools, sizeof(*vsi->xsk_pools),
 				 GFP_KERNEL);
 
-	if (!vsi->xsk_umems) {
-		vsi->num_xsk_umems = 0;
+	if (!vsi->xsk_pools) {
+		vsi->num_xsk_pools = 0;
 		return -ENOMEM;
 	}
 
@@ -282,73 +282,73 @@ static int ice_xsk_alloc_umems(struct ice_vsi *vsi)
 }
 
 /**
- * ice_xsk_remove_umem - Remove an UMEM for a certain ring/qid
+ * ice_xsk_remove_pool - Remove an buffer pool for a certain ring/qid
  * @vsi: VSI from which the VSI will be removed
- * @qid: Ring/qid associated with the UMEM
+ * @qid: Ring/qid associated with the buffer pool
  */
-static void ice_xsk_remove_umem(struct ice_vsi *vsi, u16 qid)
+static void ice_xsk_remove_pool(struct ice_vsi *vsi, u16 qid)
 {
-	vsi->xsk_umems[qid] = NULL;
-	vsi->num_xsk_umems_used--;
+	vsi->xsk_pools[qid] = NULL;
+	vsi->num_xsk_pools_used--;
 
-	if (vsi->num_xsk_umems_used == 0) {
-		kfree(vsi->xsk_umems);
-		vsi->xsk_umems = NULL;
-		vsi->num_xsk_umems = 0;
+	if (vsi->num_xsk_pools_used == 0) {
+		kfree(vsi->xsk_pools);
+		vsi->xsk_pools = NULL;
+		vsi->num_xsk_pools = 0;
 	}
 }
 
 /**
- * ice_xsk_umem_disable - disable a UMEM region
+ * ice_xsk_pool_disable - disable a buffer pool region
  * @vsi: Current VSI
  * @qid: queue ID
  *
  * Returns 0 on success, negative on failure
  */
-static int ice_xsk_umem_disable(struct ice_vsi *vsi, u16 qid)
+static int ice_xsk_pool_disable(struct ice_vsi *vsi, u16 qid)
 {
-	if (!vsi->xsk_umems || qid >= vsi->num_xsk_umems ||
-	    !vsi->xsk_umems[qid])
+	if (!vsi->xsk_pools || qid >= vsi->num_xsk_pools ||
+	    !vsi->xsk_pools[qid])
 		return -EINVAL;
 
-	xsk_buff_dma_unmap(vsi->xsk_umems[qid], ICE_RX_DMA_ATTR);
-	ice_xsk_remove_umem(vsi, qid);
+	xsk_buff_dma_unmap(vsi->xsk_pools[qid]->umem, ICE_RX_DMA_ATTR);
+	ice_xsk_remove_pool(vsi, qid);
 
 	return 0;
 }
 
 /**
- * ice_xsk_umem_enable - enable a UMEM region
+ * ice_xsk_pool_enable - enable a buffer pool region
  * @vsi: Current VSI
- * @umem: pointer to a requested UMEM region
+ * @pool: pointer to a requested buffer pool region
  * @qid: queue ID
  *
  * Returns 0 on success, negative on failure
  */
 static int
-ice_xsk_umem_enable(struct ice_vsi *vsi, struct xdp_umem *umem, u16 qid)
+ice_xsk_pool_enable(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid)
 {
 	int err;
 
 	if (vsi->type != ICE_VSI_PF)
 		return -EINVAL;
 
-	if (!vsi->num_xsk_umems)
-		vsi->num_xsk_umems = min_t(u16, vsi->num_rxq, vsi->num_txq);
-	if (qid >= vsi->num_xsk_umems)
+	if (!vsi->num_xsk_pools)
+		vsi->num_xsk_pools = min_t(u16, vsi->num_rxq, vsi->num_txq);
+	if (qid >= vsi->num_xsk_pools)
 		return -EINVAL;
 
-	err = ice_xsk_alloc_umems(vsi);
+	err = ice_xsk_alloc_pools(vsi);
 	if (err)
 		return err;
 
-	if (vsi->xsk_umems && vsi->xsk_umems[qid])
+	if (vsi->xsk_pools && vsi->xsk_pools[qid])
 		return -EBUSY;
 
-	vsi->xsk_umems[qid] = umem;
-	vsi->num_xsk_umems_used++;
+	vsi->xsk_pools[qid] = pool;
+	vsi->num_xsk_pools_used++;
 
-	err = xsk_buff_dma_map(vsi->xsk_umems[qid], ice_pf_to_dev(vsi->back),
+	err = xsk_buff_dma_map(vsi->xsk_pools[qid]->umem, ice_pf_to_dev(vsi->back),
 			       ICE_RX_DMA_ATTR);
 	if (err)
 		return err;
@@ -357,17 +357,17 @@ ice_xsk_umem_enable(struct ice_vsi *vsi, struct xdp_umem *umem, u16 qid)
 }
 
 /**
- * ice_xsk_umem_setup - enable/disable a UMEM region depending on its state
+ * ice_xsk_pool_setup - enable/disable a buffer pool region depending on its state
  * @vsi: Current VSI
- * @umem: UMEM to enable/associate to a ring, NULL to disable
+ * @pool: buffer pool to enable/associate to a ring, NULL to disable
  * @qid: queue ID
  *
  * Returns 0 on success, negative on failure
  */
-int ice_xsk_umem_setup(struct ice_vsi *vsi, struct xdp_umem *umem, u16 qid)
+int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid)
 {
-	bool if_running, umem_present = !!umem;
-	int ret = 0, umem_failure = 0;
+	bool if_running, pool_present = !!pool;
+	int ret = 0, pool_failure = 0;
 
 	if_running = netif_running(vsi->netdev) && ice_is_xdp_ena_vsi(vsi);
 
@@ -375,26 +375,26 @@ int ice_xsk_umem_setup(struct ice_vsi *vsi, struct xdp_umem *umem, u16 qid)
 		ret = ice_qp_dis(vsi, qid);
 		if (ret) {
 			netdev_err(vsi->netdev, "ice_qp_dis error = %d\n", ret);
-			goto xsk_umem_if_up;
+			goto xsk_pool_if_up;
 		}
 	}
 
-	umem_failure = umem_present ? ice_xsk_umem_enable(vsi, umem, qid) :
-				      ice_xsk_umem_disable(vsi, qid);
+	pool_failure = pool_present ? ice_xsk_pool_enable(vsi, pool, qid) :
+				      ice_xsk_pool_disable(vsi, qid);
 
-xsk_umem_if_up:
+xsk_pool_if_up:
 	if (if_running) {
 		ret = ice_qp_ena(vsi, qid);
-		if (!ret && umem_present)
+		if (!ret && pool_present)
 			napi_schedule(&vsi->xdp_rings[qid]->q_vector->napi);
 		else if (ret)
 			netdev_err(vsi->netdev, "ice_qp_ena error = %d\n", ret);
 	}
 
-	if (umem_failure) {
-		netdev_err(vsi->netdev, "Could not %sable UMEM, error = %d\n",
-			   umem_present ? "en" : "dis", umem_failure);
-		return umem_failure;
+	if (pool_failure) {
+		netdev_err(vsi->netdev, "Could not %sable buffer pool, error = %d\n",
+			   pool_present ? "en" : "dis", pool_failure);
+		return pool_failure;
 	}
 
 	return ret;
@@ -425,7 +425,7 @@ bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count)
 	rx_buf = &rx_ring->rx_buf[ntu];
 
 	do {
-		rx_buf->xdp = xsk_buff_alloc(rx_ring->xsk_umem);
+		rx_buf->xdp = xsk_buff_alloc(rx_ring->xsk_pool->umem);
 		if (!rx_buf->xdp) {
 			ret = true;
 			break;
@@ -645,11 +645,11 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget)
 	ice_finalize_xdp_rx(rx_ring, xdp_xmit);
 	ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes);
 
-	if (xsk_umem_uses_need_wakeup(rx_ring->xsk_umem)) {
+	if (xsk_umem_uses_need_wakeup(rx_ring->xsk_pool->umem)) {
 		if (failure || rx_ring->next_to_clean == rx_ring->next_to_use)
-			xsk_set_rx_need_wakeup(rx_ring->xsk_umem);
+			xsk_set_rx_need_wakeup(rx_ring->xsk_pool->umem);
 		else
-			xsk_clear_rx_need_wakeup(rx_ring->xsk_umem);
+			xsk_clear_rx_need_wakeup(rx_ring->xsk_pool->umem);
 
 		return (int)total_rx_packets;
 	}
@@ -682,11 +682,11 @@ static bool ice_xmit_zc(struct ice_ring *xdp_ring, int budget)
 
 		tx_buf = &xdp_ring->tx_buf[xdp_ring->next_to_use];
 
-		if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &desc))
+		if (!xsk_umem_consume_tx(xdp_ring->xsk_pool->umem, &desc))
 			break;
 
-		dma = xsk_buff_raw_get_dma(xdp_ring->xsk_umem, desc.addr);
-		xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_umem, dma,
+		dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool->umem, desc.addr);
+		xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool->umem, dma,
 						 desc.len);
 
 		tx_buf->bytecount = desc.len;
@@ -703,7 +703,7 @@ static bool ice_xmit_zc(struct ice_ring *xdp_ring, int budget)
 
 	if (tx_desc) {
 		ice_xdp_ring_update_tail(xdp_ring);
-		xsk_umem_consume_tx_done(xdp_ring->xsk_umem);
+		xsk_umem_consume_tx_done(xdp_ring->xsk_pool->umem);
 	}
 
 	return budget > 0 && work_done;
@@ -777,10 +777,10 @@ bool ice_clean_tx_irq_zc(struct ice_ring *xdp_ring, int budget)
 	xdp_ring->next_to_clean = ntc;
 
 	if (xsk_frames)
-		xsk_umem_complete_tx(xdp_ring->xsk_umem, xsk_frames);
+		xsk_umem_complete_tx(xdp_ring->xsk_pool->umem, xsk_frames);
 
-	if (xsk_umem_uses_need_wakeup(xdp_ring->xsk_umem))
-		xsk_set_tx_need_wakeup(xdp_ring->xsk_umem);
+	if (xsk_umem_uses_need_wakeup(xdp_ring->xsk_pool->umem))
+		xsk_set_tx_need_wakeup(xdp_ring->xsk_pool->umem);
 
 	ice_update_tx_ring_stats(xdp_ring, total_packets, total_bytes);
 	xmit_done = ice_xmit_zc(xdp_ring, ICE_DFLT_IRQ_WORK);
@@ -814,7 +814,7 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id,
 	if (queue_id >= vsi->num_txq)
 		return -ENXIO;
 
-	if (!vsi->xdp_rings[queue_id]->xsk_umem)
+	if (!vsi->xdp_rings[queue_id]->xsk_pool)
 		return -ENXIO;
 
 	ring = vsi->xdp_rings[queue_id];
@@ -833,20 +833,20 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id,
 }
 
 /**
- * ice_xsk_any_rx_ring_ena - Checks if Rx rings have AF_XDP UMEM attached
+ * ice_xsk_any_rx_ring_ena - Checks if Rx rings have AF_XDP buff pool attached
  * @vsi: VSI to be checked
  *
- * Returns true if any of the Rx rings has an AF_XDP UMEM attached
+ * Returns true if any of the Rx rings has an AF_XDP buff pool attached
  */
 bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi)
 {
 	int i;
 
-	if (!vsi->xsk_umems)
+	if (!vsi->xsk_pools)
 		return false;
 
-	for (i = 0; i < vsi->num_xsk_umems; i++) {
-		if (vsi->xsk_umems[i])
+	for (i = 0; i < vsi->num_xsk_pools; i++) {
+		if (vsi->xsk_pools[i])
 			return true;
 	}
 
@@ -854,7 +854,7 @@ bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi)
 }
 
 /**
- * ice_xsk_clean_rx_ring - clean UMEM queues connected to a given Rx ring
+ * ice_xsk_clean_rx_ring - clean buffer pool queues connected to a given Rx ring
  * @rx_ring: ring to be cleaned
  */
 void ice_xsk_clean_rx_ring(struct ice_ring *rx_ring)
@@ -872,7 +872,7 @@ void ice_xsk_clean_rx_ring(struct ice_ring *rx_ring)
 }
 
 /**
- * ice_xsk_clean_xdp_ring - Clean the XDP Tx ring and its UMEM queues
+ * ice_xsk_clean_xdp_ring - Clean the XDP Tx ring and its buffer pool queues
  * @xdp_ring: XDP_Tx ring
  */
 void ice_xsk_clean_xdp_ring(struct ice_ring *xdp_ring)
@@ -896,5 +896,5 @@ void ice_xsk_clean_xdp_ring(struct ice_ring *xdp_ring)
 	}
 
 	if (xsk_frames)
-		xsk_umem_complete_tx(xdp_ring->xsk_umem, xsk_frames);
+		xsk_umem_complete_tx(xdp_ring->xsk_pool->umem, xsk_frames);
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.h b/drivers/net/ethernet/intel/ice/ice_xsk.h
index fc1a06b4df36..fad783690134 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.h
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.h
@@ -9,7 +9,8 @@
 struct ice_vsi;
 
 #ifdef CONFIG_XDP_SOCKETS
-int ice_xsk_umem_setup(struct ice_vsi *vsi, struct xdp_umem *umem, u16 qid);
+int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool,
+		       u16 qid);
 int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget);
 bool ice_clean_tx_irq_zc(struct ice_ring *xdp_ring, int budget);
 int ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, u32 flags);
@@ -19,8 +20,8 @@ void ice_xsk_clean_rx_ring(struct ice_ring *rx_ring);
 void ice_xsk_clean_xdp_ring(struct ice_ring *xdp_ring);
 #else
 static inline int
-ice_xsk_umem_setup(struct ice_vsi __always_unused *vsi,
-		   struct xdp_umem __always_unused *umem,
+ice_xsk_pool_setup(struct ice_vsi __always_unused *vsi,
+		   struct xsk_buff_pool __always_unused *pool,
 		   u16 __always_unused qid)
 {
 	return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index 1e8a809233a0..de0fc6ecf491 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -350,7 +350,7 @@ struct ixgbe_ring {
 		struct ixgbe_rx_queue_stats rx_stats;
 	};
 	struct xdp_rxq_info xdp_rxq;
-	struct xdp_umem *xsk_umem;
+	struct xsk_buff_pool *xsk_pool;
 	u16 ring_idx;		/* {rx,tx,xdp}_ring back reference idx */
 	u16 rx_buf_len;
 } ____cacheline_internodealigned_in_smp;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 2f8a4cfc5fa1..c498465b3000 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -3156,7 +3156,7 @@ int ixgbe_poll(struct napi_struct *napi, int budget)
 #endif
 
 	ixgbe_for_each_ring(ring, q_vector->tx) {
-		bool wd = ring->xsk_umem ?
+		bool wd = ring->xsk_pool ?
 			  ixgbe_clean_xdp_tx_irq(q_vector, ring, budget) :
 			  ixgbe_clean_tx_irq(q_vector, ring, budget);
 
@@ -3176,7 +3176,7 @@ int ixgbe_poll(struct napi_struct *napi, int budget)
 		per_ring_budget = budget;
 
 	ixgbe_for_each_ring(ring, q_vector->rx) {
-		int cleaned = ring->xsk_umem ?
+		int cleaned = ring->xsk_pool ?
 			      ixgbe_clean_rx_irq_zc(q_vector, ring,
 						    per_ring_budget) :
 			      ixgbe_clean_rx_irq(q_vector, ring,
@@ -3471,9 +3471,9 @@ void ixgbe_configure_tx_ring(struct ixgbe_adapter *adapter,
 	u32 txdctl = IXGBE_TXDCTL_ENABLE;
 	u8 reg_idx = ring->reg_idx;
 
-	ring->xsk_umem = NULL;
+	ring->xsk_pool = NULL;
 	if (ring_is_xdp(ring))
-		ring->xsk_umem = ixgbe_xsk_umem(adapter, ring);
+		ring->xsk_pool = ixgbe_xsk_pool(adapter, ring);
 
 	/* disable queue to avoid issues while updating state */
 	IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), 0);
@@ -3713,8 +3713,8 @@ static void ixgbe_configure_srrctl(struct ixgbe_adapter *adapter,
 	srrctl = IXGBE_RX_HDR_SIZE << IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT;
 
 	/* configure the packet buffer length */
-	if (rx_ring->xsk_umem) {
-		u32 xsk_buf_len = xsk_umem_get_rx_frame_size(rx_ring->xsk_umem);
+	if (rx_ring->xsk_pool) {
+		u32 xsk_buf_len = xsk_umem_get_rx_frame_size(rx_ring->xsk_pool->umem);
 
 		/* If the MAC support setting RXDCTL.RLPML, the
 		 * SRRCTL[n].BSIZEPKT is set to PAGE_SIZE and
@@ -4059,12 +4059,12 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter,
 	u8 reg_idx = ring->reg_idx;
 
 	xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
-	ring->xsk_umem = ixgbe_xsk_umem(adapter, ring);
-	if (ring->xsk_umem) {
+	ring->xsk_pool = ixgbe_xsk_pool(adapter, ring);
+	if (ring->xsk_pool) {
 		WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
 						   MEM_TYPE_XSK_BUFF_POOL,
 						   NULL));
-		xsk_buff_set_rxq_info(ring->xsk_umem, &ring->xdp_rxq);
+		xsk_buff_set_rxq_info(ring->xsk_pool->umem, &ring->xdp_rxq);
 	} else {
 		WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
 						   MEM_TYPE_PAGE_SHARED, NULL));
@@ -4119,8 +4119,8 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter,
 #endif
 	}
 
-	if (ring->xsk_umem && hw->mac.type != ixgbe_mac_82599EB) {
-		u32 xsk_buf_len = xsk_umem_get_rx_frame_size(ring->xsk_umem);
+	if (ring->xsk_pool && hw->mac.type != ixgbe_mac_82599EB) {
+		u32 xsk_buf_len = xsk_umem_get_rx_frame_size(ring->xsk_pool->umem);
 
 		rxdctl &= ~(IXGBE_RXDCTL_RLPMLMASK |
 			    IXGBE_RXDCTL_RLPML_EN);
@@ -4142,7 +4142,7 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter,
 	IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl);
 
 	ixgbe_rx_desc_queue_enable(adapter, ring);
-	if (ring->xsk_umem)
+	if (ring->xsk_pool)
 		ixgbe_alloc_rx_buffers_zc(ring, ixgbe_desc_unused(ring));
 	else
 		ixgbe_alloc_rx_buffers(ring, ixgbe_desc_unused(ring));
@@ -5292,7 +5292,7 @@ static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring)
 	u16 i = rx_ring->next_to_clean;
 	struct ixgbe_rx_buffer *rx_buffer = &rx_ring->rx_buffer_info[i];
 
-	if (rx_ring->xsk_umem) {
+	if (rx_ring->xsk_pool) {
 		ixgbe_xsk_clean_rx_ring(rx_ring);
 		goto skip_free;
 	}
@@ -5984,7 +5984,7 @@ static void ixgbe_clean_tx_ring(struct ixgbe_ring *tx_ring)
 	u16 i = tx_ring->next_to_clean;
 	struct ixgbe_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i];
 
-	if (tx_ring->xsk_umem) {
+	if (tx_ring->xsk_pool) {
 		ixgbe_xsk_clean_tx_ring(tx_ring);
 		goto out;
 	}
@@ -10146,7 +10146,7 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
 	 */
 	if (need_reset && prog)
 		for (i = 0; i < adapter->num_rx_queues; i++)
-			if (adapter->xdp_ring[i]->xsk_umem)
+			if (adapter->xdp_ring[i]->xsk_pool)
 				(void)ixgbe_xsk_wakeup(adapter->netdev, i,
 						       XDP_WAKEUP_RX);
 
@@ -10160,8 +10160,8 @@ static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return ixgbe_xdp_setup(dev, xdp->prog);
-	case XDP_SETUP_XSK_UMEM:
-		return ixgbe_xsk_umem_setup(adapter, xdp->xsk.umem,
+	case XDP_SETUP_XSK_POOL:
+		return ixgbe_xsk_pool_setup(adapter, xdp->xsk.pool,
 					    xdp->xsk.queue_id);
 
 	default:
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h
index 7887ae4aaf4f..2aeec78029bc 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h
@@ -28,9 +28,10 @@ void ixgbe_irq_rearm_queues(struct ixgbe_adapter *adapter, u64 qmask);
 void ixgbe_txrx_ring_disable(struct ixgbe_adapter *adapter, int ring);
 void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring);
 
-struct xdp_umem *ixgbe_xsk_umem(struct ixgbe_adapter *adapter,
-				struct ixgbe_ring *ring);
-int ixgbe_xsk_umem_setup(struct ixgbe_adapter *adapter, struct xdp_umem *umem,
+struct xsk_buff_pool *ixgbe_xsk_pool(struct ixgbe_adapter *adapter,
+				     struct ixgbe_ring *ring);
+int ixgbe_xsk_pool_setup(struct ixgbe_adapter *adapter,
+			 struct xsk_buff_pool *pool,
 			 u16 qid);
 
 void ixgbe_zca_free(struct zero_copy_allocator *alloc, unsigned long handle);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
index ec7121f352e2..8ad954fcdc38 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
@@ -8,8 +8,8 @@
 #include "ixgbe.h"
 #include "ixgbe_txrx_common.h"
 
-struct xdp_umem *ixgbe_xsk_umem(struct ixgbe_adapter *adapter,
-				struct ixgbe_ring *ring)
+struct xsk_buff_pool *ixgbe_xsk_pool(struct ixgbe_adapter *adapter,
+				     struct ixgbe_ring *ring)
 {
 	bool xdp_on = READ_ONCE(adapter->xdp_prog);
 	int qid = ring->ring_idx;
@@ -17,11 +17,11 @@ struct xdp_umem *ixgbe_xsk_umem(struct ixgbe_adapter *adapter,
 	if (!xdp_on || !test_bit(qid, adapter->af_xdp_zc_qps))
 		return NULL;
 
-	return xdp_get_umem_from_qid(adapter->netdev, qid);
+	return xdp_get_xsk_pool_from_qid(adapter->netdev, qid);
 }
 
-static int ixgbe_xsk_umem_enable(struct ixgbe_adapter *adapter,
-				 struct xdp_umem *umem,
+static int ixgbe_xsk_pool_enable(struct ixgbe_adapter *adapter,
+				 struct xsk_buff_pool *pool,
 				 u16 qid)
 {
 	struct net_device *netdev = adapter->netdev;
@@ -35,7 +35,7 @@ static int ixgbe_xsk_umem_enable(struct ixgbe_adapter *adapter,
 	    qid >= netdev->real_num_tx_queues)
 		return -EINVAL;
 
-	err = xsk_buff_dma_map(umem, &adapter->pdev->dev, IXGBE_RX_DMA_ATTR);
+	err = xsk_buff_dma_map(pool->umem, &adapter->pdev->dev, IXGBE_RX_DMA_ATTR);
 	if (err)
 		return err;
 
@@ -59,13 +59,13 @@ static int ixgbe_xsk_umem_enable(struct ixgbe_adapter *adapter,
 	return 0;
 }
 
-static int ixgbe_xsk_umem_disable(struct ixgbe_adapter *adapter, u16 qid)
+static int ixgbe_xsk_pool_disable(struct ixgbe_adapter *adapter, u16 qid)
 {
-	struct xdp_umem *umem;
+	struct xsk_buff_pool *pool;
 	bool if_running;
 
-	umem = xdp_get_umem_from_qid(adapter->netdev, qid);
-	if (!umem)
+	pool = xdp_get_xsk_pool_from_qid(adapter->netdev, qid);
+	if (!pool)
 		return -EINVAL;
 
 	if_running = netif_running(adapter->netdev) &&
@@ -75,7 +75,7 @@ static int ixgbe_xsk_umem_disable(struct ixgbe_adapter *adapter, u16 qid)
 		ixgbe_txrx_ring_disable(adapter, qid);
 
 	clear_bit(qid, adapter->af_xdp_zc_qps);
-	xsk_buff_dma_unmap(umem, IXGBE_RX_DMA_ATTR);
+	xsk_buff_dma_unmap(pool->umem, IXGBE_RX_DMA_ATTR);
 
 	if (if_running)
 		ixgbe_txrx_ring_enable(adapter, qid);
@@ -83,11 +83,12 @@ static int ixgbe_xsk_umem_disable(struct ixgbe_adapter *adapter, u16 qid)
 	return 0;
 }
 
-int ixgbe_xsk_umem_setup(struct ixgbe_adapter *adapter, struct xdp_umem *umem,
+int ixgbe_xsk_pool_setup(struct ixgbe_adapter *adapter,
+			 struct xsk_buff_pool *pool,
 			 u16 qid)
 {
-	return umem ? ixgbe_xsk_umem_enable(adapter, umem, qid) :
-		ixgbe_xsk_umem_disable(adapter, qid);
+	return pool ? ixgbe_xsk_pool_enable(adapter, pool, qid) :
+		ixgbe_xsk_pool_disable(adapter, qid);
 }
 
 static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter,
@@ -149,7 +150,7 @@ bool ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 count)
 	i -= rx_ring->count;
 
 	do {
-		bi->xdp = xsk_buff_alloc(rx_ring->xsk_umem);
+		bi->xdp = xsk_buff_alloc(rx_ring->xsk_pool->umem);
 		if (!bi->xdp) {
 			ok = false;
 			break;
@@ -344,11 +345,11 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector,
 	q_vector->rx.total_packets += total_rx_packets;
 	q_vector->rx.total_bytes += total_rx_bytes;
 
-	if (xsk_umem_uses_need_wakeup(rx_ring->xsk_umem)) {
+	if (xsk_umem_uses_need_wakeup(rx_ring->xsk_pool->umem)) {
 		if (failure || rx_ring->next_to_clean == rx_ring->next_to_use)
-			xsk_set_rx_need_wakeup(rx_ring->xsk_umem);
+			xsk_set_rx_need_wakeup(rx_ring->xsk_pool->umem);
 		else
-			xsk_clear_rx_need_wakeup(rx_ring->xsk_umem);
+			xsk_clear_rx_need_wakeup(rx_ring->xsk_pool->umem);
 
 		return (int)total_rx_packets;
 	}
@@ -373,6 +374,7 @@ void ixgbe_xsk_clean_rx_ring(struct ixgbe_ring *rx_ring)
 
 static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget)
 {
+	struct xsk_buff_pool *pool = xdp_ring->xsk_pool;
 	union ixgbe_adv_tx_desc *tx_desc = NULL;
 	struct ixgbe_tx_buffer *tx_bi;
 	bool work_done = true;
@@ -387,12 +389,11 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget)
 			break;
 		}
 
-		if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &desc))
+		if (!xsk_umem_consume_tx(pool->umem, &desc))
 			break;
 
-		dma = xsk_buff_raw_get_dma(xdp_ring->xsk_umem, desc.addr);
-		xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_umem, dma,
-						 desc.len);
+		dma = xsk_buff_raw_get_dma(pool->umem, desc.addr);
+		xsk_buff_raw_dma_sync_for_device(pool->umem, dma, desc.len);
 
 		tx_bi = &xdp_ring->tx_buffer_info[xdp_ring->next_to_use];
 		tx_bi->bytecount = desc.len;
@@ -418,7 +419,7 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget)
 
 	if (tx_desc) {
 		ixgbe_xdp_ring_update_tail(xdp_ring);
-		xsk_umem_consume_tx_done(xdp_ring->xsk_umem);
+		xsk_umem_consume_tx_done(pool->umem);
 	}
 
 	return !!budget && work_done;
@@ -439,7 +440,7 @@ bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector,
 {
 	u16 ntc = tx_ring->next_to_clean, ntu = tx_ring->next_to_use;
 	unsigned int total_packets = 0, total_bytes = 0;
-	struct xdp_umem *umem = tx_ring->xsk_umem;
+	struct xsk_buff_pool *pool = tx_ring->xsk_pool;
 	union ixgbe_adv_tx_desc *tx_desc;
 	struct ixgbe_tx_buffer *tx_bi;
 	u32 xsk_frames = 0;
@@ -484,10 +485,10 @@ bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector,
 	q_vector->tx.total_packets += total_packets;
 
 	if (xsk_frames)
-		xsk_umem_complete_tx(umem, xsk_frames);
+		xsk_umem_complete_tx(pool->umem, xsk_frames);
 
-	if (xsk_umem_uses_need_wakeup(tx_ring->xsk_umem))
-		xsk_set_tx_need_wakeup(tx_ring->xsk_umem);
+	if (xsk_umem_uses_need_wakeup(pool->umem))
+		xsk_set_tx_need_wakeup(pool->umem);
 
 	return ixgbe_xmit_zc(tx_ring, q_vector->tx.work_limit);
 }
@@ -511,7 +512,7 @@ int ixgbe_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags)
 	if (test_bit(__IXGBE_TX_DISABLED, &ring->state))
 		return -ENETDOWN;
 
-	if (!ring->xsk_umem)
+	if (!ring->xsk_pool)
 		return -ENXIO;
 
 	if (!napi_if_scheduled_mark_missed(&ring->q_vector->napi)) {
@@ -526,7 +527,7 @@ int ixgbe_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags)
 void ixgbe_xsk_clean_tx_ring(struct ixgbe_ring *tx_ring)
 {
 	u16 ntc = tx_ring->next_to_clean, ntu = tx_ring->next_to_use;
-	struct xdp_umem *umem = tx_ring->xsk_umem;
+	struct xsk_buff_pool *pool = tx_ring->xsk_pool;
 	struct ixgbe_tx_buffer *tx_bi;
 	u32 xsk_frames = 0;
 
@@ -546,5 +547,5 @@ void ixgbe_xsk_clean_tx_ring(struct ixgbe_ring *tx_ring)
 	}
 
 	if (xsk_frames)
-		xsk_umem_complete_tx(umem, xsk_frames);
+		xsk_umem_complete_tx(pool->umem, xsk_frames);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 10e6886c96ba..0b3eaa102751 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -24,7 +24,7 @@ mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
 mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
 		en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \
 		en_selftest.o en/port.o en/monitor_stats.o en/health.o \
-		en/reporter_tx.o en/reporter_rx.o en/params.o en/xsk/umem.o \
+		en/reporter_tx.o en/reporter_rx.o en/params.o en/xsk/pool.o \
 		en/xsk/setup.o en/xsk/rx.o en/xsk/tx.o en/devlink.o
 
 #
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 0cc2080fd847..4f33658da25a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -442,7 +442,7 @@ struct mlx5e_xdpsq {
 	struct mlx5e_cq            cq;
 
 	/* read only */
-	struct xdp_umem           *umem;
+	struct xsk_buff_pool      *xsk_pool;
 	struct mlx5_wq_cyc         wq;
 	struct mlx5e_xdpsq_stats  *stats;
 	mlx5e_fp_xmit_xdp_frame_check xmit_xdp_frame_check;
@@ -606,7 +606,7 @@ struct mlx5e_rq {
 	struct page_pool      *page_pool;
 
 	/* AF_XDP zero-copy */
-	struct xdp_umem       *umem;
+	struct xsk_buff_pool  *xsk_pool;
 
 	struct work_struct     recover_work;
 
@@ -729,12 +729,13 @@ struct mlx5e_hv_vhca_stats_agent {
 #endif
 
 struct mlx5e_xsk {
-	/* UMEMs are stored separately from channels, because we don't want to
-	 * lose them when channels are recreated. The kernel also stores UMEMs,
-	 * but it doesn't distinguish between zero-copy and non-zero-copy UMEMs,
-	 * so rely on our mechanism.
+	/* XSK buffer pools are stored separately from channels,
+	 * because we don't want to lose them when channels are
+	 * recreated. The kernel also stores buffer pool, but it doesn't
+	 * distinguish between zero-copy and non-zero-copy UMEMs, so
+	 * rely on our mechanism.
 	 */
-	struct xdp_umem **umems;
+	struct xsk_buff_pool **pools;
 	u16 refcnt;
 	bool ever_used;
 };
@@ -893,7 +894,7 @@ struct mlx5e_xsk_param;
 struct mlx5e_rq_param;
 int mlx5e_open_rq(struct mlx5e_channel *c, struct mlx5e_params *params,
 		  struct mlx5e_rq_param *param, struct mlx5e_xsk_param *xsk,
-		  struct xdp_umem *umem, struct mlx5e_rq *rq);
+		  struct xsk_buff_pool *xsk_pool, struct mlx5e_rq *rq);
 int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time);
 void mlx5e_deactivate_rq(struct mlx5e_rq *rq);
 void mlx5e_close_rq(struct mlx5e_rq *rq);
@@ -903,7 +904,7 @@ int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params,
 		     struct mlx5e_sq_param *param, struct mlx5e_icosq *sq);
 void mlx5e_close_icosq(struct mlx5e_icosq *sq);
 int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params,
-		     struct mlx5e_sq_param *param, struct xdp_umem *umem,
+		     struct mlx5e_sq_param *param, struct xsk_buff_pool *xsk_pool,
 		     struct mlx5e_xdpsq *sq, bool is_redirect);
 void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 0e6946fc121f..c9f0d2be6dd1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -445,7 +445,7 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
 	} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
 
 	if (xsk_frames)
-		xsk_umem_complete_tx(sq->umem, xsk_frames);
+		xsk_umem_complete_tx(sq->xsk_pool->umem, xsk_frames);
 
 	sq->stats->cqes += i;
 
@@ -475,7 +475,7 @@ void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq)
 	}
 
 	if (xsk_frames)
-		xsk_umem_complete_tx(sq->umem, xsk_frames);
+		xsk_umem_complete_tx(sq->xsk_pool->umem, xsk_frames);
 }
 
 int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
@@ -563,4 +563,3 @@ void mlx5e_set_xmit_fp(struct mlx5e_xdpsq *sq, bool is_mpw)
 	sq->xmit_xdp_frame = is_mpw ?
 		mlx5e_xmit_xdp_frame_mpwqe : mlx5e_xmit_xdp_frame;
 }
-
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c
new file mode 100644
index 000000000000..8ccd9203ee25
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c
@@ -0,0 +1,217 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019-2020, Mellanox Technologies inc. All rights reserved. */
+
+#include <net/xdp_sock_drv.h>
+#include "pool.h"
+#include "setup.h"
+#include "en/params.h"
+
+static int mlx5e_xsk_map_pool(struct mlx5e_priv *priv,
+			      struct xsk_buff_pool *pool)
+{
+	struct device *dev = priv->mdev->device;
+
+	return xsk_buff_dma_map(pool->umem, dev, 0);
+}
+
+static void mlx5e_xsk_unmap_pool(struct mlx5e_priv *priv,
+				 struct xsk_buff_pool *pool)
+{
+	return xsk_buff_dma_unmap(pool->umem, 0);
+}
+
+static int mlx5e_xsk_get_pools(struct mlx5e_xsk *xsk)
+{
+	if (!xsk->pools) {
+		xsk->pools = kcalloc(MLX5E_MAX_NUM_CHANNELS,
+				     sizeof(*xsk->pools), GFP_KERNEL);
+		if (unlikely(!xsk->pools))
+			return -ENOMEM;
+	}
+
+	xsk->refcnt++;
+	xsk->ever_used = true;
+
+	return 0;
+}
+
+static void mlx5e_xsk_put_pools(struct mlx5e_xsk *xsk)
+{
+	if (!--xsk->refcnt) {
+		kfree(xsk->pools);
+		xsk->pools = NULL;
+	}
+}
+
+static int mlx5e_xsk_add_pool(struct mlx5e_xsk *xsk, struct xsk_buff_pool *pool, u16 ix)
+{
+	int err;
+
+	err = mlx5e_xsk_get_pools(xsk);
+	if (unlikely(err))
+		return err;
+
+	xsk->pools[ix] = pool;
+	return 0;
+}
+
+static void mlx5e_xsk_remove_pool(struct mlx5e_xsk *xsk, u16 ix)
+{
+	xsk->pools[ix] = NULL;
+
+	mlx5e_xsk_put_pools(xsk);
+}
+
+static bool mlx5e_xsk_is_pool_sane(struct xsk_buff_pool *pool)
+{
+	return xsk_umem_get_headroom(pool->umem) <= 0xffff &&
+		xsk_umem_get_chunk_size(pool->umem) <= 0xffff;
+}
+
+void mlx5e_build_xsk_param(struct xsk_buff_pool *pool, struct mlx5e_xsk_param *xsk)
+{
+	xsk->headroom = xsk_umem_get_headroom(pool->umem);
+	xsk->chunk_size = xsk_umem_get_chunk_size(pool->umem);
+}
+
+static int mlx5e_xsk_enable_locked(struct mlx5e_priv *priv,
+				   struct xsk_buff_pool *pool, u16 ix)
+{
+	struct mlx5e_params *params = &priv->channels.params;
+	struct mlx5e_xsk_param xsk;
+	struct mlx5e_channel *c;
+	int err;
+
+	if (unlikely(mlx5e_xsk_get_pool(&priv->channels.params, &priv->xsk, ix)))
+		return -EBUSY;
+
+	if (unlikely(!mlx5e_xsk_is_pool_sane(pool)))
+		return -EINVAL;
+
+	err = mlx5e_xsk_map_pool(priv, pool);
+	if (unlikely(err))
+		return err;
+
+	err = mlx5e_xsk_add_pool(&priv->xsk, pool, ix);
+	if (unlikely(err))
+		goto err_unmap_pool;
+
+	mlx5e_build_xsk_param(pool, &xsk);
+
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+		/* XSK objects will be created on open. */
+		goto validate_closed;
+	}
+
+	if (!params->xdp_prog) {
+		/* XSK objects will be created when an XDP program is set,
+		 * and the channels are reopened.
+		 */
+		goto validate_closed;
+	}
+
+	c = priv->channels.c[ix];
+
+	err = mlx5e_open_xsk(priv, params, &xsk, pool, c);
+	if (unlikely(err))
+		goto err_remove_pool;
+
+	mlx5e_activate_xsk(c);
+
+	/* Don't wait for WQEs, because the newer xdpsock sample doesn't provide
+	 * any Fill Ring entries at the setup stage.
+	 */
+
+	err = mlx5e_xsk_redirect_rqt_to_channel(priv, priv->channels.c[ix]);
+	if (unlikely(err))
+		goto err_deactivate;
+
+	return 0;
+
+err_deactivate:
+	mlx5e_deactivate_xsk(c);
+	mlx5e_close_xsk(c);
+
+err_remove_pool:
+	mlx5e_xsk_remove_pool(&priv->xsk, ix);
+
+err_unmap_pool:
+	mlx5e_xsk_unmap_pool(priv, pool);
+
+	return err;
+
+validate_closed:
+	/* Check the configuration in advance, rather than fail at a later stage
+	 * (in mlx5e_xdp_set or on open) and end up with no channels.
+	 */
+	if (!mlx5e_validate_xsk_param(params, &xsk, priv->mdev)) {
+		err = -EINVAL;
+		goto err_remove_pool;
+	}
+
+	return 0;
+}
+
+static int mlx5e_xsk_disable_locked(struct mlx5e_priv *priv, u16 ix)
+{
+	struct xsk_buff_pool *pool = mlx5e_xsk_get_pool(&priv->channels.params,
+						   &priv->xsk, ix);
+	struct mlx5e_channel *c;
+
+	if (unlikely(!pool))
+		return -EINVAL;
+
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+		goto remove_pool;
+
+	/* XSK RQ and SQ are only created if XDP program is set. */
+	if (!priv->channels.params.xdp_prog)
+		goto remove_pool;
+
+	c = priv->channels.c[ix];
+	mlx5e_xsk_redirect_rqt_to_drop(priv, ix);
+	mlx5e_deactivate_xsk(c);
+	mlx5e_close_xsk(c);
+
+remove_pool:
+	mlx5e_xsk_remove_pool(&priv->xsk, ix);
+	mlx5e_xsk_unmap_pool(priv, pool);
+
+	return 0;
+}
+
+static int mlx5e_xsk_enable_pool(struct mlx5e_priv *priv, struct xsk_buff_pool *pool,
+				 u16 ix)
+{
+	int err;
+
+	mutex_lock(&priv->state_lock);
+	err = mlx5e_xsk_enable_locked(priv, pool, ix);
+	mutex_unlock(&priv->state_lock);
+
+	return err;
+}
+
+static int mlx5e_xsk_disable_pool(struct mlx5e_priv *priv, u16 ix)
+{
+	int err;
+
+	mutex_lock(&priv->state_lock);
+	err = mlx5e_xsk_disable_locked(priv, ix);
+	mutex_unlock(&priv->state_lock);
+
+	return err;
+}
+
+int mlx5e_xsk_setup_pool(struct net_device *dev, struct xsk_buff_pool *pool, u16 qid)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5e_params *params = &priv->channels.params;
+	u16 ix;
+
+	if (unlikely(!mlx5e_qid_get_ch_if_in_group(params, qid, MLX5E_RQ_GROUP_XSK, &ix)))
+		return -EINVAL;
+
+	return pool ? mlx5e_xsk_enable_pool(priv, pool, ix) :
+		      mlx5e_xsk_disable_pool(priv, ix);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.h
new file mode 100644
index 000000000000..dca0010a0866
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019-2020, Mellanox Technologies inc. All rights reserved. */
+
+#ifndef __MLX5_EN_XSK_POOL_H__
+#define __MLX5_EN_XSK_POOL_H__
+
+#include "en.h"
+
+static inline struct xsk_buff_pool *mlx5e_xsk_get_pool(struct mlx5e_params *params,
+						       struct mlx5e_xsk *xsk, u16 ix)
+{
+	if (!xsk || !xsk->pools)
+		return NULL;
+
+	if (unlikely(ix >= params->num_channels))
+		return NULL;
+
+	return xsk->pools[ix];
+}
+
+struct mlx5e_xsk_param;
+void mlx5e_build_xsk_param(struct xsk_buff_pool *pool, struct mlx5e_xsk_param *xsk);
+
+/* .ndo_bpf callback. */
+int mlx5e_xsk_setup_pool(struct net_device *dev, struct xsk_buff_pool *pool, u16 qid);
+
+#endif /* __MLX5_EN_XSK_POOL_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h
index d147b2f13b54..3dd056a11bae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h
@@ -19,10 +19,10 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
 					      struct mlx5e_wqe_frag_info *wi,
 					      u32 cqe_bcnt);
 
-static inline int mlx5e_xsk_page_alloc_umem(struct mlx5e_rq *rq,
+static inline int mlx5e_xsk_page_alloc_pool(struct mlx5e_rq *rq,
 					    struct mlx5e_dma_info *dma_info)
 {
-	dma_info->xsk = xsk_buff_alloc(rq->umem);
+	dma_info->xsk = xsk_buff_alloc(rq->xsk_pool->umem);
 	if (!dma_info->xsk)
 		return -ENOMEM;
 
@@ -38,13 +38,13 @@ static inline int mlx5e_xsk_page_alloc_umem(struct mlx5e_rq *rq,
 
 static inline bool mlx5e_xsk_update_rx_wakeup(struct mlx5e_rq *rq, bool alloc_err)
 {
-	if (!xsk_umem_uses_need_wakeup(rq->umem))
+	if (!xsk_umem_uses_need_wakeup(rq->xsk_pool->umem))
 		return alloc_err;
 
 	if (unlikely(alloc_err))
-		xsk_set_rx_need_wakeup(rq->umem);
+		xsk_set_rx_need_wakeup(rq->xsk_pool->umem);
 	else
-		xsk_clear_rx_need_wakeup(rq->umem);
+		xsk_clear_rx_need_wakeup(rq->xsk_pool->umem);
 
 	return false;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
index dd9df519d383..662a1dafeaad 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
@@ -45,7 +45,7 @@ static void mlx5e_build_xsk_cparam(struct mlx5e_priv *priv,
 }
 
 int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params,
-		   struct mlx5e_xsk_param *xsk, struct xdp_umem *umem,
+		   struct mlx5e_xsk_param *xsk, struct xsk_buff_pool *pool,
 		   struct mlx5e_channel *c)
 {
 	struct mlx5e_channel_param *cparam;
@@ -64,7 +64,7 @@ int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params,
 	if (unlikely(err))
 		goto err_free_cparam;
 
-	err = mlx5e_open_rq(c, params, &cparam->rq, xsk, umem, &c->xskrq);
+	err = mlx5e_open_rq(c, params, &cparam->rq, xsk, pool, &c->xskrq);
 	if (unlikely(err))
 		goto err_close_rx_cq;
 
@@ -72,13 +72,13 @@ int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params,
 	if (unlikely(err))
 		goto err_close_rq;
 
-	/* Create a separate SQ, so that when the UMEM is disabled, we could
+	/* Create a separate SQ, so that when the buff pool is disabled, we could
 	 * close this SQ safely and stop receiving CQEs. In other case, e.g., if
-	 * the XDPSQ was used instead, we might run into trouble when the UMEM
+	 * the XDPSQ was used instead, we might run into trouble when the buff pool
 	 * is disabled and then reenabled, but the SQ continues receiving CQEs
-	 * from the old UMEM.
+	 * from the old buff pool.
 	 */
-	err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, umem, &c->xsksq, true);
+	err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, pool, &c->xsksq, true);
 	if (unlikely(err))
 		goto err_close_tx_cq;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.h
index 0dd11b81c046..ca20f1ff5e39 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.h
@@ -12,7 +12,7 @@ bool mlx5e_validate_xsk_param(struct mlx5e_params *params,
 			      struct mlx5e_xsk_param *xsk,
 			      struct mlx5_core_dev *mdev);
 int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params,
-		   struct mlx5e_xsk_param *xsk, struct xdp_umem *umem,
+		   struct mlx5e_xsk_param *xsk, struct xsk_buff_pool *pool,
 		   struct mlx5e_channel *c);
 void mlx5e_close_xsk(struct mlx5e_channel *c);
 void mlx5e_activate_xsk(struct mlx5e_channel *c);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
index 4d892f6cecb3..5f9470207bb0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
@@ -2,7 +2,7 @@
 /* Copyright (c) 2019 Mellanox Technologies. */
 
 #include "tx.h"
-#include "umem.h"
+#include "pool.h"
 #include "en/xdp.h"
 #include "en/params.h"
 #include <net/xdp_sock_drv.h>
@@ -66,7 +66,7 @@ static void mlx5e_xsk_tx_post_err(struct mlx5e_xdpsq *sq,
 
 bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget)
 {
-	struct xdp_umem *umem = sq->umem;
+	struct xsk_buff_pool *pool = sq->xsk_pool;
 	struct mlx5e_xdp_info xdpi;
 	struct mlx5e_xdp_xmit_data xdptxd;
 	bool work_done = true;
@@ -87,7 +87,7 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget)
 			break;
 		}
 
-		if (!xsk_umem_consume_tx(umem, &desc)) {
+		if (!xsk_umem_consume_tx(pool->umem, &desc)) {
 			/* TX will get stuck until something wakes it up by
 			 * triggering NAPI. Currently it's expected that the
 			 * application calls sendto() if there are consumed, but
@@ -96,11 +96,11 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget)
 			break;
 		}
 
-		xdptxd.dma_addr = xsk_buff_raw_get_dma(umem, desc.addr);
-		xdptxd.data = xsk_buff_raw_get_data(umem, desc.addr);
+		xdptxd.dma_addr = xsk_buff_raw_get_dma(pool->umem, desc.addr);
+		xdptxd.data = xsk_buff_raw_get_data(pool->umem, desc.addr);
 		xdptxd.len = desc.len;
 
-		xsk_buff_raw_dma_sync_for_device(umem, xdptxd.dma_addr, xdptxd.len);
+		xsk_buff_raw_dma_sync_for_device(pool->umem, xdptxd.dma_addr, xdptxd.len);
 
 		ret = INDIRECT_CALL_2(sq->xmit_xdp_frame, mlx5e_xmit_xdp_frame_mpwqe,
 				      mlx5e_xmit_xdp_frame, sq, &xdptxd, &xdpi, check_result);
@@ -119,7 +119,7 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget)
 			mlx5e_xdp_mpwqe_complete(sq);
 		mlx5e_xmit_xdp_doorbell(sq);
 
-		xsk_umem_consume_tx_done(umem);
+		xsk_umem_consume_tx_done(pool->umem);
 	}
 
 	return !(budget && work_done);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h
index 39fa0a705856..ddb61d5bc2db 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h
@@ -15,13 +15,13 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget);
 
 static inline void mlx5e_xsk_update_tx_wakeup(struct mlx5e_xdpsq *sq)
 {
-	if (!xsk_umem_uses_need_wakeup(sq->umem))
+	if (!xsk_umem_uses_need_wakeup(sq->xsk_pool->umem))
 		return;
 
 	if (sq->pc != sq->cc)
-		xsk_clear_tx_need_wakeup(sq->umem);
+		xsk_clear_tx_need_wakeup(sq->xsk_pool->umem);
 	else
-		xsk_set_tx_need_wakeup(sq->umem);
+		xsk_set_tx_need_wakeup(sq->xsk_pool->umem);
 }
 
 #endif /* __MLX5_EN_XSK_TX_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.c
deleted file mode 100644
index 331ca2b0f8a4..000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.c
+++ /dev/null
@@ -1,217 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
-/* Copyright (c) 2019 Mellanox Technologies. */
-
-#include <net/xdp_sock_drv.h>
-#include "umem.h"
-#include "setup.h"
-#include "en/params.h"
-
-static int mlx5e_xsk_map_umem(struct mlx5e_priv *priv,
-			      struct xdp_umem *umem)
-{
-	struct device *dev = priv->mdev->device;
-
-	return xsk_buff_dma_map(umem, dev, 0);
-}
-
-static void mlx5e_xsk_unmap_umem(struct mlx5e_priv *priv,
-				 struct xdp_umem *umem)
-{
-	return xsk_buff_dma_unmap(umem, 0);
-}
-
-static int mlx5e_xsk_get_umems(struct mlx5e_xsk *xsk)
-{
-	if (!xsk->umems) {
-		xsk->umems = kcalloc(MLX5E_MAX_NUM_CHANNELS,
-				     sizeof(*xsk->umems), GFP_KERNEL);
-		if (unlikely(!xsk->umems))
-			return -ENOMEM;
-	}
-
-	xsk->refcnt++;
-	xsk->ever_used = true;
-
-	return 0;
-}
-
-static void mlx5e_xsk_put_umems(struct mlx5e_xsk *xsk)
-{
-	if (!--xsk->refcnt) {
-		kfree(xsk->umems);
-		xsk->umems = NULL;
-	}
-}
-
-static int mlx5e_xsk_add_umem(struct mlx5e_xsk *xsk, struct xdp_umem *umem, u16 ix)
-{
-	int err;
-
-	err = mlx5e_xsk_get_umems(xsk);
-	if (unlikely(err))
-		return err;
-
-	xsk->umems[ix] = umem;
-	return 0;
-}
-
-static void mlx5e_xsk_remove_umem(struct mlx5e_xsk *xsk, u16 ix)
-{
-	xsk->umems[ix] = NULL;
-
-	mlx5e_xsk_put_umems(xsk);
-}
-
-static bool mlx5e_xsk_is_umem_sane(struct xdp_umem *umem)
-{
-	return xsk_umem_get_headroom(umem) <= 0xffff &&
-		xsk_umem_get_chunk_size(umem) <= 0xffff;
-}
-
-void mlx5e_build_xsk_param(struct xdp_umem *umem, struct mlx5e_xsk_param *xsk)
-{
-	xsk->headroom = xsk_umem_get_headroom(umem);
-	xsk->chunk_size = xsk_umem_get_chunk_size(umem);
-}
-
-static int mlx5e_xsk_enable_locked(struct mlx5e_priv *priv,
-				   struct xdp_umem *umem, u16 ix)
-{
-	struct mlx5e_params *params = &priv->channels.params;
-	struct mlx5e_xsk_param xsk;
-	struct mlx5e_channel *c;
-	int err;
-
-	if (unlikely(mlx5e_xsk_get_umem(&priv->channels.params, &priv->xsk, ix)))
-		return -EBUSY;
-
-	if (unlikely(!mlx5e_xsk_is_umem_sane(umem)))
-		return -EINVAL;
-
-	err = mlx5e_xsk_map_umem(priv, umem);
-	if (unlikely(err))
-		return err;
-
-	err = mlx5e_xsk_add_umem(&priv->xsk, umem, ix);
-	if (unlikely(err))
-		goto err_unmap_umem;
-
-	mlx5e_build_xsk_param(umem, &xsk);
-
-	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
-		/* XSK objects will be created on open. */
-		goto validate_closed;
-	}
-
-	if (!params->xdp_prog) {
-		/* XSK objects will be created when an XDP program is set,
-		 * and the channels are reopened.
-		 */
-		goto validate_closed;
-	}
-
-	c = priv->channels.c[ix];
-
-	err = mlx5e_open_xsk(priv, params, &xsk, umem, c);
-	if (unlikely(err))
-		goto err_remove_umem;
-
-	mlx5e_activate_xsk(c);
-
-	/* Don't wait for WQEs, because the newer xdpsock sample doesn't provide
-	 * any Fill Ring entries at the setup stage.
-	 */
-
-	err = mlx5e_xsk_redirect_rqt_to_channel(priv, priv->channels.c[ix]);
-	if (unlikely(err))
-		goto err_deactivate;
-
-	return 0;
-
-err_deactivate:
-	mlx5e_deactivate_xsk(c);
-	mlx5e_close_xsk(c);
-
-err_remove_umem:
-	mlx5e_xsk_remove_umem(&priv->xsk, ix);
-
-err_unmap_umem:
-	mlx5e_xsk_unmap_umem(priv, umem);
-
-	return err;
-
-validate_closed:
-	/* Check the configuration in advance, rather than fail at a later stage
-	 * (in mlx5e_xdp_set or on open) and end up with no channels.
-	 */
-	if (!mlx5e_validate_xsk_param(params, &xsk, priv->mdev)) {
-		err = -EINVAL;
-		goto err_remove_umem;
-	}
-
-	return 0;
-}
-
-static int mlx5e_xsk_disable_locked(struct mlx5e_priv *priv, u16 ix)
-{
-	struct xdp_umem *umem = mlx5e_xsk_get_umem(&priv->channels.params,
-						   &priv->xsk, ix);
-	struct mlx5e_channel *c;
-
-	if (unlikely(!umem))
-		return -EINVAL;
-
-	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
-		goto remove_umem;
-
-	/* XSK RQ and SQ are only created if XDP program is set. */
-	if (!priv->channels.params.xdp_prog)
-		goto remove_umem;
-
-	c = priv->channels.c[ix];
-	mlx5e_xsk_redirect_rqt_to_drop(priv, ix);
-	mlx5e_deactivate_xsk(c);
-	mlx5e_close_xsk(c);
-
-remove_umem:
-	mlx5e_xsk_remove_umem(&priv->xsk, ix);
-	mlx5e_xsk_unmap_umem(priv, umem);
-
-	return 0;
-}
-
-static int mlx5e_xsk_enable_umem(struct mlx5e_priv *priv, struct xdp_umem *umem,
-				 u16 ix)
-{
-	int err;
-
-	mutex_lock(&priv->state_lock);
-	err = mlx5e_xsk_enable_locked(priv, umem, ix);
-	mutex_unlock(&priv->state_lock);
-
-	return err;
-}
-
-static int mlx5e_xsk_disable_umem(struct mlx5e_priv *priv, u16 ix)
-{
-	int err;
-
-	mutex_lock(&priv->state_lock);
-	err = mlx5e_xsk_disable_locked(priv, ix);
-	mutex_unlock(&priv->state_lock);
-
-	return err;
-}
-
-int mlx5e_xsk_setup_umem(struct net_device *dev, struct xdp_umem *umem, u16 qid)
-{
-	struct mlx5e_priv *priv = netdev_priv(dev);
-	struct mlx5e_params *params = &priv->channels.params;
-	u16 ix;
-
-	if (unlikely(!mlx5e_qid_get_ch_if_in_group(params, qid, MLX5E_RQ_GROUP_XSK, &ix)))
-		return -EINVAL;
-
-	return umem ? mlx5e_xsk_enable_umem(priv, umem, ix) :
-		      mlx5e_xsk_disable_umem(priv, ix);
-}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.h
deleted file mode 100644
index bada94973586..000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
-/* Copyright (c) 2019 Mellanox Technologies. */
-
-#ifndef __MLX5_EN_XSK_UMEM_H__
-#define __MLX5_EN_XSK_UMEM_H__
-
-#include "en.h"
-
-static inline struct xdp_umem *mlx5e_xsk_get_umem(struct mlx5e_params *params,
-						  struct mlx5e_xsk *xsk, u16 ix)
-{
-	if (!xsk || !xsk->umems)
-		return NULL;
-
-	if (unlikely(ix >= params->num_channels))
-		return NULL;
-
-	return xsk->umems[ix];
-}
-
-struct mlx5e_xsk_param;
-void mlx5e_build_xsk_param(struct xdp_umem *umem, struct mlx5e_xsk_param *xsk);
-
-/* .ndo_bpf callback. */
-int mlx5e_xsk_setup_umem(struct net_device *dev, struct xdp_umem *umem, u16 qid);
-
-int mlx5e_xsk_resize_reuseq(struct xdp_umem *umem, u32 nentries);
-
-#endif /* __MLX5_EN_XSK_UMEM_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 08270987c506..5cb1e4839eb7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -32,7 +32,7 @@
 
 #include "en.h"
 #include "en/port.h"
-#include "en/xsk/umem.h"
+#include "en/xsk/pool.h"
 #include "lib/clock.h"
 
 void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index 83c9b2bbc4af..b416a8ee2eed 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -33,7 +33,7 @@
 #include <linux/mlx5/fs.h>
 #include "en.h"
 #include "en/params.h"
-#include "en/xsk/umem.h"
+#include "en/xsk/pool.h"
 
 struct mlx5e_ethtool_rule {
 	struct list_head             list;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index aebcf73f8546..f598683dc906 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -57,7 +57,7 @@
 #include "en/monitor_stats.h"
 #include "en/health.h"
 #include "en/params.h"
-#include "en/xsk/umem.h"
+#include "en/xsk/pool.h"
 #include "en/xsk/setup.h"
 #include "en/xsk/rx.h"
 #include "en/xsk/tx.h"
@@ -363,7 +363,7 @@ static void mlx5e_rq_err_cqe_work(struct work_struct *recover_work)
 static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 			  struct mlx5e_params *params,
 			  struct mlx5e_xsk_param *xsk,
-			  struct xdp_umem *umem,
+			  struct xsk_buff_pool *xsk_pool,
 			  struct mlx5e_rq_param *rqp,
 			  struct mlx5e_rq *rq)
 {
@@ -389,9 +389,9 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	rq->mdev    = mdev;
 	rq->hw_mtu  = MLX5E_SW2HW_MTU(params, params->sw_mtu);
 	rq->xdpsq   = &c->rq_xdpsq;
-	rq->umem    = umem;
+	rq->xsk_pool = xsk_pool;
 
-	if (rq->umem)
+	if (rq->xsk_pool)
 		rq->stats = &c->priv->channel_stats[c->ix].xskrq;
 	else
 		rq->stats = &c->priv->channel_stats[c->ix].rq;
@@ -477,7 +477,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	if (xsk) {
 		err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq,
 						 MEM_TYPE_XSK_BUFF_POOL, NULL);
-		xsk_buff_set_rxq_info(rq->umem, &rq->xdp_rxq);
+		xsk_buff_set_rxq_info(rq->xsk_pool->umem, &rq->xdp_rxq);
 	} else {
 		/* Create a page_pool and register it with rxq */
 		pp_params.order     = 0;
@@ -816,11 +816,11 @@ void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
 
 int mlx5e_open_rq(struct mlx5e_channel *c, struct mlx5e_params *params,
 		  struct mlx5e_rq_param *param, struct mlx5e_xsk_param *xsk,
-		  struct xdp_umem *umem, struct mlx5e_rq *rq)
+		  struct xsk_buff_pool *xsk_pool, struct mlx5e_rq *rq)
 {
 	int err;
 
-	err = mlx5e_alloc_rq(c, params, xsk, umem, param, rq);
+	err = mlx5e_alloc_rq(c, params, xsk, xsk_pool, param, rq);
 	if (err)
 		return err;
 
@@ -925,7 +925,7 @@ static int mlx5e_alloc_xdpsq_db(struct mlx5e_xdpsq *sq, int numa)
 
 static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c,
 			     struct mlx5e_params *params,
-			     struct xdp_umem *umem,
+			     struct xsk_buff_pool *xsk_pool,
 			     struct mlx5e_sq_param *param,
 			     struct mlx5e_xdpsq *sq,
 			     bool is_redirect)
@@ -941,9 +941,9 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c,
 	sq->uar_map   = mdev->mlx5e_res.bfreg.map;
 	sq->min_inline_mode = params->tx_min_inline_mode;
 	sq->hw_mtu    = MLX5E_SW2HW_MTU(params, params->sw_mtu);
-	sq->umem      = umem;
+	sq->xsk_pool  = xsk_pool;
 
-	sq->stats = sq->umem ?
+	sq->stats = sq->xsk_pool ?
 		&c->priv->channel_stats[c->ix].xsksq :
 		is_redirect ?
 			&c->priv->channel_stats[c->ix].xdpsq :
@@ -1408,13 +1408,13 @@ void mlx5e_close_icosq(struct mlx5e_icosq *sq)
 }
 
 int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params,
-		     struct mlx5e_sq_param *param, struct xdp_umem *umem,
+		     struct mlx5e_sq_param *param, struct xsk_buff_pool *xsk_pool,
 		     struct mlx5e_xdpsq *sq, bool is_redirect)
 {
 	struct mlx5e_create_sq_param csp = {};
 	int err;
 
-	err = mlx5e_alloc_xdpsq(c, params, umem, param, sq, is_redirect);
+	err = mlx5e_alloc_xdpsq(c, params, xsk_pool, param, sq, is_redirect);
 	if (err)
 		return err;
 
@@ -1907,7 +1907,7 @@ static u8 mlx5e_enumerate_lag_port(struct mlx5_core_dev *mdev, int ix)
 static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 			      struct mlx5e_params *params,
 			      struct mlx5e_channel_param *cparam,
-			      struct xdp_umem *umem,
+			      struct xsk_buff_pool *xsk_pool,
 			      struct mlx5e_channel **cp)
 {
 	int cpu = cpumask_first(mlx5_comp_irq_get_affinity_mask(priv->mdev, ix));
@@ -1946,9 +1946,9 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	if (unlikely(err))
 		goto err_napi_del;
 
-	if (umem) {
-		mlx5e_build_xsk_param(umem, &xsk);
-		err = mlx5e_open_xsk(priv, params, &xsk, umem, c);
+	if (xsk_pool) {
+		mlx5e_build_xsk_param(xsk_pool, &xsk);
+		err = mlx5e_open_xsk(priv, params, &xsk, xsk_pool, c);
 		if (unlikely(err))
 			goto err_close_queues;
 	}
@@ -2309,12 +2309,12 @@ int mlx5e_open_channels(struct mlx5e_priv *priv,
 
 	mlx5e_build_channel_param(priv, &chs->params, cparam);
 	for (i = 0; i < chs->num; i++) {
-		struct xdp_umem *umem = NULL;
+		struct xsk_buff_pool *xsk_pool = NULL;
 
 		if (chs->params.xdp_prog)
-			umem = mlx5e_xsk_get_umem(&chs->params, chs->params.xsk, i);
+			xsk_pool = mlx5e_xsk_get_pool(&chs->params, chs->params.xsk, i);
 
-		err = mlx5e_open_channel(priv, i, &chs->params, cparam, umem, &chs->c[i]);
+		err = mlx5e_open_channel(priv, i, &chs->params, cparam, xsk_pool, &chs->c[i]);
 		if (err)
 			goto err_close_channels;
 	}
@@ -3892,13 +3892,14 @@ static bool mlx5e_xsk_validate_mtu(struct net_device *netdev,
 	u16 ix;
 
 	for (ix = 0; ix < chs->params.num_channels; ix++) {
-		struct xdp_umem *umem = mlx5e_xsk_get_umem(&chs->params, chs->params.xsk, ix);
+		struct xsk_buff_pool *xsk_pool =
+			mlx5e_xsk_get_pool(&chs->params, chs->params.xsk, ix);
 		struct mlx5e_xsk_param xsk;
 
-		if (!umem)
+		if (!xsk_pool)
 			continue;
 
-		mlx5e_build_xsk_param(umem, &xsk);
+		mlx5e_build_xsk_param(xsk_pool, &xsk);
 
 		if (!mlx5e_validate_xsk_param(new_params, &xsk, mdev)) {
 			u32 hr = mlx5e_get_linear_rq_headroom(new_params, &xsk);
@@ -4423,8 +4424,8 @@ static int mlx5e_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return mlx5e_xdp_set(dev, xdp->prog);
-	case XDP_SETUP_XSK_UMEM:
-		return mlx5e_xsk_setup_umem(dev, xdp->xsk.umem,
+	case XDP_SETUP_XSK_POOL:
+		return mlx5e_xsk_setup_pool(dev, xdp->xsk.pool,
 					    xdp->xsk.queue_id);
 	default:
 		return -EINVAL;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 65828af120b7..b33f9f21848f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -281,8 +281,8 @@ static inline int mlx5e_page_alloc_pool(struct mlx5e_rq *rq,
 static inline int mlx5e_page_alloc(struct mlx5e_rq *rq,
 				   struct mlx5e_dma_info *dma_info)
 {
-	if (rq->umem)
-		return mlx5e_xsk_page_alloc_umem(rq, dma_info);
+	if (rq->xsk_pool)
+		return mlx5e_xsk_page_alloc_pool(rq, dma_info);
 	else
 		return mlx5e_page_alloc_pool(rq, dma_info);
 }
@@ -313,7 +313,7 @@ static inline void mlx5e_page_release(struct mlx5e_rq *rq,
 				      struct mlx5e_dma_info *dma_info,
 				      bool recycle)
 {
-	if (rq->umem)
+	if (rq->xsk_pool)
 		/* The `recycle` parameter is ignored, and the page is always
 		 * put into the Reuse Ring, because there is no way to return
 		 * the page to the userspace when the interface goes down.
@@ -400,14 +400,14 @@ static int mlx5e_alloc_rx_wqes(struct mlx5e_rq *rq, u16 ix, u8 wqe_bulk)
 	int err;
 	int i;
 
-	if (rq->umem) {
+	if (rq->xsk_pool) {
 		int pages_desired = wqe_bulk << rq->wqe.info.log_num_frags;
 
 		/* Check in advance that we have enough frames, instead of
 		 * allocating one-by-one, failing and moving frames to the
 		 * Reuse Ring.
 		 */
-		if (unlikely(!xsk_buff_can_alloc(rq->umem, pages_desired)))
+		if (unlikely(!xsk_buff_can_alloc(rq->xsk_pool->umem, pages_desired)))
 			return -ENOMEM;
 	}
 
@@ -505,8 +505,8 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 	/* Check in advance that we have enough frames, instead of allocating
 	 * one-by-one, failing and moving frames to the Reuse Ring.
 	 */
-	if (rq->umem &&
-	    unlikely(!xsk_buff_can_alloc(rq->umem, MLX5_MPWRQ_PAGES_PER_WQE))) {
+	if (rq->xsk_pool &&
+	    unlikely(!xsk_buff_can_alloc(rq->xsk_pool->umem, MLX5_MPWRQ_PAGES_PER_WQE))) {
 		err = -ENOMEM;
 		goto err;
 	}
@@ -754,7 +754,7 @@ INDIRECT_CALLABLE_SCOPE bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq)
 	 * the driver when it refills the Fill Ring.
 	 * 2. Otherwise, busy poll by rescheduling the NAPI poll.
 	 */
-	if (unlikely(alloc_err == -ENOMEM && rq->umem))
+	if (unlikely(alloc_err == -ENOMEM && rq->xsk_pool))
 		return true;
 
 	return false;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index b0e303f6603f..d088dd866825 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -618,7 +618,7 @@ struct netdev_queue {
 	/* Subordinate device that the queue has been assigned to */
 	struct net_device	*sb_dev;
 #ifdef CONFIG_XDP_SOCKETS
-	struct xdp_umem         *umem;
+	struct xsk_buff_pool    *pool;
 #endif
 /*
  * write-mostly part
@@ -751,7 +751,7 @@ struct netdev_rx_queue {
 	struct net_device		*dev;
 	struct xdp_rxq_info		xdp_rxq;
 #ifdef CONFIG_XDP_SOCKETS
-	struct xdp_umem                 *umem;
+	struct xsk_buff_pool            *pool;
 #endif
 } ____cacheline_aligned_in_smp;
 
@@ -879,7 +879,7 @@ enum bpf_netdev_command {
 	/* BPF program for offload callbacks, invoked at program load time. */
 	BPF_OFFLOAD_MAP_ALLOC,
 	BPF_OFFLOAD_MAP_FREE,
-	XDP_SETUP_XSK_UMEM,
+	XDP_SETUP_XSK_POOL,
 };
 
 struct bpf_prog_offload_ops;
@@ -913,9 +913,9 @@ struct netdev_bpf {
 		struct {
 			struct bpf_offloaded_map *offmap;
 		};
-		/* XDP_SETUP_XSK_UMEM */
+		/* XDP_SETUP_XSK_POOL */
 		struct {
-			struct xdp_umem *umem;
+			struct xsk_buff_pool *pool;
 			u16 queue_id;
 		} xsk;
 	};
diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index ccf848f7efa4..5dc8d3c0dcd4 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -14,7 +14,8 @@
 void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries);
 bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc);
 void xsk_umem_consume_tx_done(struct xdp_umem *umem);
-struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev, u16 queue_id);
+struct xsk_buff_pool *xdp_get_xsk_pool_from_qid(struct net_device *dev,
+						u16 queue_id);
 void xsk_set_rx_need_wakeup(struct xdp_umem *umem);
 void xsk_set_tx_need_wakeup(struct xdp_umem *umem);
 void xsk_clear_rx_need_wakeup(struct xdp_umem *umem);
@@ -125,8 +126,8 @@ static inline void xsk_umem_consume_tx_done(struct xdp_umem *umem)
 {
 }
 
-static inline struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev,
-						     u16 queue_id)
+static inline struct xsk_buff_pool *
+xdp_get_xsk_pool_from_qid(struct net_device *dev, u16 queue_id)
 {
 	return NULL;
 }
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index 6842990e2712..f851b0a68324 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -13,6 +13,7 @@ struct xsk_buff_pool;
 struct xdp_rxq_info;
 struct xsk_queue;
 struct xdp_desc;
+struct xdp_umem;
 struct device;
 struct page;
 
@@ -42,13 +43,14 @@ struct xsk_buff_pool {
 	u32 frame_len;
 	bool dma_need_sync;
 	bool unaligned;
+	struct xdp_umem *umem;
 	void *addrs;
 	struct device *dev;
 	struct xdp_buff_xsk *free_heads[];
 };
 
 /* AF_XDP core. */
-struct xsk_buff_pool *xp_create(struct page **pages, u32 nr_pages, u32 chunks,
+struct xsk_buff_pool *xp_create(struct xdp_umem *umem, u32 chunks,
 				u32 chunk_size, u32 headroom, u64 size,
 				bool unaligned);
 void xp_set_fq(struct xsk_buff_pool *pool, struct xsk_queue *fq);
diff --git a/net/ethtool/channels.c b/net/ethtool/channels.c
index 9ef54cdcf662..78d990bfb90f 100644
--- a/net/ethtool/channels.c
+++ b/net/ethtool/channels.c
@@ -223,7 +223,7 @@ int ethnl_set_channels(struct sk_buff *skb, struct genl_info *info)
 	from_channel = channels.combined_count +
 		       min(channels.rx_count, channels.tx_count);
 	for (i = from_channel; i < old_total; i++)
-		if (xdp_get_umem_from_qid(dev, i)) {
+		if (xdp_get_xsk_pool_from_qid(dev, i)) {
 			GENL_SET_ERR_MSG(info, "requested channel counts are too low for existing zerocopy AF_XDP sockets");
 			return -EINVAL;
 		}
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 441794e0034f..2e6a678df741 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -1706,7 +1706,7 @@ static noinline_for_stack int ethtool_set_channels(struct net_device *dev,
 		min(channels.rx_count, channels.tx_count);
 	to_channel = curr.combined_count + max(curr.rx_count, curr.tx_count);
 	for (i = from_channel; i < to_channel; i++)
-		if (xdp_get_umem_from_qid(dev, i))
+		if (xdp_get_xsk_pool_from_qid(dev, i))
 			return -EINVAL;
 
 	ret = dev->ethtool_ops->set_channels(dev, &channels);
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index e97db37354e4..0b5f3b04216f 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -51,8 +51,9 @@ void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs)
  * not know if the device has more tx queues than rx, or the opposite.
  * This might also change during run time.
  */
-static int xdp_reg_umem_at_qid(struct net_device *dev, struct xdp_umem *umem,
-			       u16 queue_id)
+static int xdp_reg_xsk_pool_at_qid(struct net_device *dev,
+				   struct xsk_buff_pool *pool,
+				   u16 queue_id)
 {
 	if (queue_id >= max_t(unsigned int,
 			      dev->real_num_rx_queues,
@@ -60,31 +61,31 @@ static int xdp_reg_umem_at_qid(struct net_device *dev, struct xdp_umem *umem,
 		return -EINVAL;
 
 	if (queue_id < dev->real_num_rx_queues)
-		dev->_rx[queue_id].umem = umem;
+		dev->_rx[queue_id].pool = pool;
 	if (queue_id < dev->real_num_tx_queues)
-		dev->_tx[queue_id].umem = umem;
+		dev->_tx[queue_id].pool = pool;
 
 	return 0;
 }
 
-struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev,
-				       u16 queue_id)
+struct xsk_buff_pool *xdp_get_xsk_pool_from_qid(struct net_device *dev,
+						u16 queue_id)
 {
 	if (queue_id < dev->real_num_rx_queues)
-		return dev->_rx[queue_id].umem;
+		return dev->_rx[queue_id].pool;
 	if (queue_id < dev->real_num_tx_queues)
-		return dev->_tx[queue_id].umem;
+		return dev->_tx[queue_id].pool;
 
 	return NULL;
 }
-EXPORT_SYMBOL(xdp_get_umem_from_qid);
+EXPORT_SYMBOL(xdp_get_xsk_pool_from_qid);
 
-static void xdp_clear_umem_at_qid(struct net_device *dev, u16 queue_id)
+static void xdp_clear_xsk_pool_at_qid(struct net_device *dev, u16 queue_id)
 {
 	if (queue_id < dev->real_num_rx_queues)
-		dev->_rx[queue_id].umem = NULL;
+		dev->_rx[queue_id].pool = NULL;
 	if (queue_id < dev->real_num_tx_queues)
-		dev->_tx[queue_id].umem = NULL;
+		dev->_tx[queue_id].pool = NULL;
 }
 
 int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
@@ -102,10 +103,10 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
 	if (force_zc && force_copy)
 		return -EINVAL;
 
-	if (xdp_get_umem_from_qid(dev, queue_id))
+	if (xdp_get_xsk_pool_from_qid(dev, queue_id))
 		return -EBUSY;
 
-	err = xdp_reg_umem_at_qid(dev, umem, queue_id);
+	err = xdp_reg_xsk_pool_at_qid(dev, umem->pool, queue_id);
 	if (err)
 		return err;
 
@@ -132,8 +133,8 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
 		goto err_unreg_umem;
 	}
 
-	bpf.command = XDP_SETUP_XSK_UMEM;
-	bpf.xsk.umem = umem;
+	bpf.command = XDP_SETUP_XSK_POOL;
+	bpf.xsk.pool = umem->pool;
 	bpf.xsk.queue_id = queue_id;
 
 	err = dev->netdev_ops->ndo_bpf(dev, &bpf);
@@ -147,7 +148,7 @@ err_unreg_umem:
 	if (!force_zc)
 		err = 0; /* fallback to copy mode */
 	if (err)
-		xdp_clear_umem_at_qid(dev, queue_id);
+		xdp_clear_xsk_pool_at_qid(dev, queue_id);
 	return err;
 }
 
@@ -162,8 +163,8 @@ void xdp_umem_clear_dev(struct xdp_umem *umem)
 		return;
 
 	if (umem->zc) {
-		bpf.command = XDP_SETUP_XSK_UMEM;
-		bpf.xsk.umem = NULL;
+		bpf.command = XDP_SETUP_XSK_POOL;
+		bpf.xsk.pool = NULL;
 		bpf.xsk.queue_id = umem->queue_id;
 
 		err = umem->dev->netdev_ops->ndo_bpf(umem->dev, &bpf);
@@ -172,7 +173,7 @@ void xdp_umem_clear_dev(struct xdp_umem *umem)
 			WARN(1, "failed to disable umem!\n");
 	}
 
-	xdp_clear_umem_at_qid(umem->dev, umem->queue_id);
+	xdp_clear_xsk_pool_at_qid(umem->dev, umem->queue_id);
 
 	dev_put(umem->dev);
 	umem->dev = NULL;
@@ -373,8 +374,8 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 	if (err)
 		goto out_account;
 
-	umem->pool = xp_create(umem->pgs, umem->npgs, chunks, chunk_size,
-			       headroom, size, unaligned_chunks);
+	umem->pool = xp_create(umem, chunks, chunk_size, headroom, size,
+			       unaligned_chunks);
 	if (!umem->pool) {
 		err = -ENOMEM;
 		goto out_pin;
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index a2044c245215..f3df3cba3d73 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -29,7 +29,7 @@ void xp_destroy(struct xsk_buff_pool *pool)
 	kvfree(pool);
 }
 
-struct xsk_buff_pool *xp_create(struct page **pages, u32 nr_pages, u32 chunks,
+struct xsk_buff_pool *xp_create(struct xdp_umem *umem, u32 chunks,
 				u32 chunk_size, u32 headroom, u64 size,
 				bool unaligned)
 {
@@ -54,6 +54,7 @@ struct xsk_buff_pool *xp_create(struct page **pages, u32 nr_pages, u32 chunks,
 	pool->chunk_size = chunk_size;
 	pool->unaligned = unaligned;
 	pool->frame_len = chunk_size - headroom - XDP_PACKET_HEADROOM;
+	pool->umem = umem;
 	INIT_LIST_HEAD(&pool->free_list);
 
 	for (i = 0; i < pool->free_heads_cnt; i++) {
@@ -63,7 +64,7 @@ struct xsk_buff_pool *xp_create(struct page **pages, u32 nr_pages, u32 chunks,
 		pool->free_heads[i] = xskb;
 	}
 
-	err = xp_addr_map(pool, pages, nr_pages);
+	err = xp_addr_map(pool, umem->pgs, umem->npgs);
 	if (!err)
 		return pool;
 
-- 
cgit v1.2.3


From afd6220999d4932616322f8a893371f8d0567a2a Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Sun, 30 Aug 2020 11:33:58 +0300
Subject: net: phylink: add helper function to decode USXGMII word

With the new addition of the USXGMII link partner ability constants we
can now introduce a phylink helper that decodes the USXGMII word and
populates the appropriate fields in the phylink_link_state structure
based on them.

Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Reviewed-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phylink.c | 43 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/phylink.h   |  3 +++
 2 files changed, 46 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 5e4cb12972eb..4adc904ad5c1 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -2320,6 +2320,49 @@ static void phylink_decode_sgmii_word(struct phylink_link_state *state,
 		state->duplex = DUPLEX_HALF;
 }
 
+/**
+ * phylink_decode_usxgmii_word() - decode the USXGMII word from a MAC PCS
+ * @state: a pointer to a struct phylink_link_state.
+ * @lpa: a 16 bit value which stores the USXGMII auto-negotiation word
+ *
+ * Helper for MAC PCS supporting the USXGMII protocol and the auto-negotiation
+ * code word.  Decode the USXGMII code word and populate the corresponding fields
+ * (speed, duplex) into the phylink_link_state structure.
+ */
+void phylink_decode_usxgmii_word(struct phylink_link_state *state,
+				 uint16_t lpa)
+{
+	switch (lpa & MDIO_USXGMII_SPD_MASK) {
+	case MDIO_USXGMII_10:
+		state->speed = SPEED_10;
+		break;
+	case MDIO_USXGMII_100:
+		state->speed = SPEED_100;
+		break;
+	case MDIO_USXGMII_1000:
+		state->speed = SPEED_1000;
+		break;
+	case MDIO_USXGMII_2500:
+		state->speed = SPEED_2500;
+		break;
+	case MDIO_USXGMII_5000:
+		state->speed = SPEED_5000;
+		break;
+	case MDIO_USXGMII_10G:
+		state->speed = SPEED_10000;
+		break;
+	default:
+		state->link = false;
+		return;
+	}
+
+	if (lpa & MDIO_USXGMII_FULL_DUPLEX)
+		state->duplex = DUPLEX_FULL;
+	else
+		state->duplex = DUPLEX_HALF;
+}
+EXPORT_SYMBOL_GPL(phylink_decode_usxgmii_word);
+
 /**
  * phylink_mii_c22_pcs_get_state() - read the MAC PCS state
  * @pcs: a pointer to a &struct mdio_device.
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index c36fb41a7d90..d81a714cfbbd 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -490,4 +490,7 @@ void phylink_mii_c22_pcs_an_restart(struct mdio_device *pcs);
 
 void phylink_mii_c45_pcs_get_state(struct mdio_device *pcs,
 				   struct phylink_link_state *state);
+
+void phylink_decode_usxgmii_word(struct phylink_link_state *state,
+				 uint16_t lpa);
 #endif
-- 
cgit v1.2.3


From 2dab432c5ae4f9c8eab3132ac0e9facf498ead92 Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Sun, 30 Aug 2020 11:34:00 +0300
Subject: net: mdiobus: add clause 45 mdiobus write accessor

Add the locked variant of the clause 45 mdiobus write accessor -
mdiobus_c45_write().

Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Reviewed-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/mdio.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/mdio.h b/include/linux/mdio.h
index 898cbf00332a..3a88b699b758 100644
--- a/include/linux/mdio.h
+++ b/include/linux/mdio.h
@@ -358,6 +358,12 @@ static inline int mdiobus_c45_read(struct mii_bus *bus, int prtad, int devad,
 	return mdiobus_read(bus, prtad, mdiobus_c45_addr(devad, regnum));
 }
 
+static inline int mdiobus_c45_write(struct mii_bus *bus, int prtad, int devad,
+				    u16 regnum, u16 val)
+{
+	return mdiobus_write(bus, prtad, mdiobus_c45_addr(devad, regnum), val);
+}
+
 int mdiobus_register_device(struct mdio_device *mdiodev);
 int mdiobus_unregister_device(struct mdio_device *mdiodev);
 bool mdiobus_is_registered_device(struct mii_bus *bus, int addr);
-- 
cgit v1.2.3


From 0da4c3d393e40e41e3c6b9f1cebaa498512c2abb Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Sun, 30 Aug 2020 11:34:01 +0300
Subject: net: phy: add Lynx PCS module

Add a Lynx PCS module which exposes the necessary operations to drive
the PCS using phylink.

The majority of the code is extracted from the Felix DSA driver, which
will be also modified in a later patch, and exposed as a separate module
for code reusability purposes.
As such, this aims at feature and bug parity with the existing Felix DSA
driver, and thus USXGMII, SGMII, QSGMII and 2500Base-X (only w/o in-band
AN) are supported by the Lynx PCS module since these were also supported
by Felix.

The module can only be enabled by the drivers in need and not user
selectable.

Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS                |   7 +
 drivers/net/pcs/Kconfig    |   6 +
 drivers/net/pcs/Makefile   |   1 +
 drivers/net/pcs/pcs-lynx.c | 312 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/pcs-lynx.h   |  21 +++
 5 files changed, 347 insertions(+)
 create mode 100644 drivers/net/pcs/pcs-lynx.c
 create mode 100644 include/linux/pcs-lynx.h

(limited to 'include/linux')

diff --git a/MAINTAINERS b/MAINTAINERS
index b0e909937499..a1c15b6714a0 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10293,6 +10293,13 @@ S:	Maintained
 W:	http://linux-test-project.github.io/
 T:	git git://github.com/linux-test-project/ltp.git
 
+LYNX PCS MODULE
+M:	Ioana Ciornei <ioana.ciornei@nxp.com>
+L:	netdev@vger.kernel.org
+S:	Supported
+F:	drivers/net/phy/pcs-lynx.c
+F:	include/linux/pcs-lynx.h
+
 M68K ARCHITECTURE
 M:	Geert Uytterhoeven <geert@linux-m68k.org>
 L:	linux-m68k@lists.linux-m68k.org
diff --git a/drivers/net/pcs/Kconfig b/drivers/net/pcs/Kconfig
index 9d6e2be32060..074fb3f5db18 100644
--- a/drivers/net/pcs/Kconfig
+++ b/drivers/net/pcs/Kconfig
@@ -13,4 +13,10 @@ config PCS_XPCS
 	  This module provides helper functions for Synopsys DesignWare XPCS
 	  controllers.
 
+config PCS_LYNX
+	tristate
+	help
+	  This module provides helpers to phylink for managing the Lynx PCS
+	  which is part of the Layerscape and QorIQ Ethernet SERDES.
+
 endmenu
diff --git a/drivers/net/pcs/Makefile b/drivers/net/pcs/Makefile
index f0480afc7157..c23146755972 100644
--- a/drivers/net/pcs/Makefile
+++ b/drivers/net/pcs/Makefile
@@ -2,3 +2,4 @@
 # Makefile for Linux PCS drivers
 
 obj-$(CONFIG_PCS_XPCS)		+= pcs-xpcs.o
+obj-$(CONFIG_PCS_LYNX)		+= pcs-lynx.o
diff --git a/drivers/net/pcs/pcs-lynx.c b/drivers/net/pcs/pcs-lynx.c
new file mode 100644
index 000000000000..c43d97682083
--- /dev/null
+++ b/drivers/net/pcs/pcs-lynx.c
@@ -0,0 +1,312 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+/* Copyright 2020 NXP
+ * Lynx PCS MDIO helpers
+ */
+
+#include <linux/mdio.h>
+#include <linux/phylink.h>
+#include <linux/pcs-lynx.h>
+
+#define SGMII_CLOCK_PERIOD_NS		8 /* PCS is clocked at 125 MHz */
+#define LINK_TIMER_VAL(ns)		((u32)((ns) / SGMII_CLOCK_PERIOD_NS))
+
+#define SGMII_AN_LINK_TIMER_NS		1600000 /* defined by SGMII spec */
+
+#define LINK_TIMER_LO			0x12
+#define LINK_TIMER_HI			0x13
+#define IF_MODE				0x14
+#define IF_MODE_SGMII_EN		BIT(0)
+#define IF_MODE_USE_SGMII_AN		BIT(1)
+#define IF_MODE_SPEED(x)		(((x) << 2) & GENMASK(3, 2))
+#define IF_MODE_SPEED_MSK		GENMASK(3, 2)
+#define IF_MODE_HALF_DUPLEX		BIT(4)
+
+enum sgmii_speed {
+	SGMII_SPEED_10		= 0,
+	SGMII_SPEED_100		= 1,
+	SGMII_SPEED_1000	= 2,
+	SGMII_SPEED_2500	= 2,
+};
+
+#define phylink_pcs_to_lynx(pl_pcs) container_of((pl_pcs), struct lynx_pcs, pcs)
+
+static void lynx_pcs_get_state_usxgmii(struct mdio_device *pcs,
+				       struct phylink_link_state *state)
+{
+	struct mii_bus *bus = pcs->bus;
+	int addr = pcs->addr;
+	int status, lpa;
+
+	status = mdiobus_c45_read(bus, addr, MDIO_MMD_VEND2, MII_BMSR);
+	if (status < 0)
+		return;
+
+	state->link = !!(status & MDIO_STAT1_LSTATUS);
+	state->an_complete = !!(status & MDIO_AN_STAT1_COMPLETE);
+	if (!state->link || !state->an_complete)
+		return;
+
+	lpa = mdiobus_c45_read(bus, addr, MDIO_MMD_VEND2, MII_LPA);
+	if (lpa < 0)
+		return;
+
+	phylink_decode_usxgmii_word(state, lpa);
+}
+
+static void lynx_pcs_get_state_2500basex(struct mdio_device *pcs,
+					 struct phylink_link_state *state)
+{
+	struct mii_bus *bus = pcs->bus;
+	int addr = pcs->addr;
+	int bmsr, lpa;
+
+	bmsr = mdiobus_read(bus, addr, MII_BMSR);
+	lpa = mdiobus_read(bus, addr, MII_LPA);
+	if (bmsr < 0 || lpa < 0) {
+		state->link = false;
+		return;
+	}
+
+	state->link = !!(bmsr & BMSR_LSTATUS);
+	state->an_complete = !!(bmsr & BMSR_ANEGCOMPLETE);
+	if (!state->link)
+		return;
+
+	state->speed = SPEED_2500;
+	state->pause |= MLO_PAUSE_TX | MLO_PAUSE_RX;
+	state->duplex = DUPLEX_FULL;
+}
+
+static void lynx_pcs_get_state(struct phylink_pcs *pcs,
+			       struct phylink_link_state *state)
+{
+	struct lynx_pcs *lynx = phylink_pcs_to_lynx(pcs);
+
+	switch (state->interface) {
+	case PHY_INTERFACE_MODE_SGMII:
+	case PHY_INTERFACE_MODE_QSGMII:
+		phylink_mii_c22_pcs_get_state(lynx->mdio, state);
+		break;
+	case PHY_INTERFACE_MODE_2500BASEX:
+		lynx_pcs_get_state_2500basex(lynx->mdio, state);
+		break;
+	case PHY_INTERFACE_MODE_USXGMII:
+		lynx_pcs_get_state_usxgmii(lynx->mdio, state);
+		break;
+	default:
+		break;
+	}
+
+	dev_dbg(&lynx->mdio->dev,
+		"mode=%s/%s/%s link=%u an_enabled=%u an_complete=%u\n",
+		phy_modes(state->interface),
+		phy_speed_to_str(state->speed),
+		phy_duplex_to_str(state->duplex),
+		state->link, state->an_enabled, state->an_complete);
+}
+
+static int lynx_pcs_config_sgmii(struct mdio_device *pcs, unsigned int mode,
+				 const unsigned long *advertising)
+{
+	struct mii_bus *bus = pcs->bus;
+	int addr = pcs->addr;
+	u16 if_mode;
+	int err;
+
+	if_mode = IF_MODE_SGMII_EN;
+	if (mode == MLO_AN_INBAND) {
+		u32 link_timer;
+
+		if_mode |= IF_MODE_USE_SGMII_AN;
+
+		/* Adjust link timer for SGMII */
+		link_timer = LINK_TIMER_VAL(SGMII_AN_LINK_TIMER_NS);
+		mdiobus_write(bus, addr, LINK_TIMER_LO, link_timer & 0xffff);
+		mdiobus_write(bus, addr, LINK_TIMER_HI, link_timer >> 16);
+	}
+	err = mdiobus_modify(bus, addr, IF_MODE,
+			     IF_MODE_SGMII_EN | IF_MODE_USE_SGMII_AN,
+			     if_mode);
+	if (err)
+		return err;
+
+	return phylink_mii_c22_pcs_config(pcs, mode, PHY_INTERFACE_MODE_SGMII,
+					 advertising);
+}
+
+static int lynx_pcs_config_usxgmii(struct mdio_device *pcs, unsigned int mode,
+				   const unsigned long *advertising)
+{
+	struct mii_bus *bus = pcs->bus;
+	int addr = pcs->addr;
+
+	if (!phylink_autoneg_inband(mode)) {
+		dev_err(&pcs->dev, "USXGMII only supports in-band AN for now\n");
+		return -EOPNOTSUPP;
+	}
+
+	/* Configure device ability for the USXGMII Replicator */
+	return mdiobus_c45_write(bus, addr, MDIO_MMD_VEND2, MII_ADVERTISE,
+				 MDIO_USXGMII_10G | MDIO_USXGMII_LINK |
+				 MDIO_USXGMII_FULL_DUPLEX |
+				 ADVERTISE_SGMII | ADVERTISE_LPACK);
+}
+
+static int lynx_pcs_config(struct phylink_pcs *pcs, unsigned int mode,
+			   phy_interface_t ifmode,
+			   const unsigned long *advertising,
+			   bool permit)
+{
+	struct lynx_pcs *lynx = phylink_pcs_to_lynx(pcs);
+
+	switch (ifmode) {
+	case PHY_INTERFACE_MODE_SGMII:
+	case PHY_INTERFACE_MODE_QSGMII:
+		return lynx_pcs_config_sgmii(lynx->mdio, mode, advertising);
+	case PHY_INTERFACE_MODE_2500BASEX:
+		if (phylink_autoneg_inband(mode)) {
+			dev_err(&lynx->mdio->dev,
+				"AN not supported on 3.125GHz SerDes lane\n");
+			return -EOPNOTSUPP;
+		}
+		break;
+	case PHY_INTERFACE_MODE_USXGMII:
+		return lynx_pcs_config_usxgmii(lynx->mdio, mode, advertising);
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static void lynx_pcs_link_up_sgmii(struct mdio_device *pcs, unsigned int mode,
+				   int speed, int duplex)
+{
+	struct mii_bus *bus = pcs->bus;
+	u16 if_mode = 0, sgmii_speed;
+	int addr = pcs->addr;
+
+	/* The PCS needs to be configured manually only
+	 * when not operating on in-band mode
+	 */
+	if (mode == MLO_AN_INBAND)
+		return;
+
+	if (duplex == DUPLEX_HALF)
+		if_mode |= IF_MODE_HALF_DUPLEX;
+
+	switch (speed) {
+	case SPEED_1000:
+		sgmii_speed = SGMII_SPEED_1000;
+		break;
+	case SPEED_100:
+		sgmii_speed = SGMII_SPEED_100;
+		break;
+	case SPEED_10:
+		sgmii_speed = SGMII_SPEED_10;
+		break;
+	case SPEED_UNKNOWN:
+		/* Silently don't do anything */
+		return;
+	default:
+		dev_err(&pcs->dev, "Invalid PCS speed %d\n", speed);
+		return;
+	}
+	if_mode |= IF_MODE_SPEED(sgmii_speed);
+
+	mdiobus_modify(bus, addr, IF_MODE,
+		       IF_MODE_HALF_DUPLEX | IF_MODE_SPEED_MSK,
+		       if_mode);
+}
+
+/* 2500Base-X is SerDes protocol 7 on Felix and 6 on ENETC. It is a SerDes lane
+ * clocked at 3.125 GHz which encodes symbols with 8b/10b and does not have
+ * auto-negotiation of any link parameters. Electrically it is compatible with
+ * a single lane of XAUI.
+ * The hardware reference manual wants to call this mode SGMII, but it isn't
+ * really, since the fundamental features of SGMII:
+ * - Downgrading the link speed by duplicating symbols
+ * - Auto-negotiation
+ * are not there.
+ * The speed is configured at 1000 in the IF_MODE because the clock frequency
+ * is actually given by a PLL configured in the Reset Configuration Word (RCW).
+ * Since there is no difference between fixed speed SGMII w/o AN and 802.3z w/o
+ * AN, we call this PHY interface type 2500Base-X. In case a PHY negotiates a
+ * lower link speed on line side, the system-side interface remains fixed at
+ * 2500 Mbps and we do rate adaptation through pause frames.
+ */
+static void lynx_pcs_link_up_2500basex(struct mdio_device *pcs,
+				       unsigned int mode,
+				       int speed, int duplex)
+{
+	struct mii_bus *bus = pcs->bus;
+	int addr = pcs->addr;
+	u16 if_mode = 0;
+
+	if (mode == MLO_AN_INBAND) {
+		dev_err(&pcs->dev, "AN not supported for 2500BaseX\n");
+		return;
+	}
+
+	if (duplex == DUPLEX_HALF)
+		if_mode |= IF_MODE_HALF_DUPLEX;
+	if_mode |= IF_MODE_SPEED(SGMII_SPEED_2500);
+
+	mdiobus_modify(bus, addr, IF_MODE,
+		       IF_MODE_HALF_DUPLEX | IF_MODE_SPEED_MSK,
+		       if_mode);
+}
+
+static void lynx_pcs_link_up(struct phylink_pcs *pcs, unsigned int mode,
+			     phy_interface_t interface,
+			     int speed, int duplex)
+{
+	struct lynx_pcs *lynx = phylink_pcs_to_lynx(pcs);
+
+	switch (interface) {
+	case PHY_INTERFACE_MODE_SGMII:
+	case PHY_INTERFACE_MODE_QSGMII:
+		lynx_pcs_link_up_sgmii(lynx->mdio, mode, speed, duplex);
+		break;
+	case PHY_INTERFACE_MODE_2500BASEX:
+		lynx_pcs_link_up_2500basex(lynx->mdio, mode, speed, duplex);
+		break;
+	case PHY_INTERFACE_MODE_USXGMII:
+		/* At the moment, only in-band AN is supported for USXGMII
+		 * so nothing to do in link_up
+		 */
+		break;
+	default:
+		break;
+	}
+}
+
+static const struct phylink_pcs_ops lynx_pcs_phylink_ops = {
+	.pcs_get_state = lynx_pcs_get_state,
+	.pcs_config = lynx_pcs_config,
+	.pcs_link_up = lynx_pcs_link_up,
+};
+
+struct lynx_pcs *lynx_pcs_create(struct mdio_device *mdio)
+{
+	struct lynx_pcs *lynx_pcs;
+
+	lynx_pcs = kzalloc(sizeof(*lynx_pcs), GFP_KERNEL);
+	if (!lynx_pcs)
+		return NULL;
+
+	lynx_pcs->mdio = mdio;
+	lynx_pcs->pcs.ops = &lynx_pcs_phylink_ops;
+	lynx_pcs->pcs.poll = true;
+
+	return lynx_pcs;
+}
+EXPORT_SYMBOL(lynx_pcs_create);
+
+void lynx_pcs_destroy(struct lynx_pcs *pcs)
+{
+	kfree(pcs);
+}
+EXPORT_SYMBOL(lynx_pcs_destroy);
+
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/include/linux/pcs-lynx.h b/include/linux/pcs-lynx.h
new file mode 100644
index 000000000000..a6440d6ebe95
--- /dev/null
+++ b/include/linux/pcs-lynx.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */
+/* Copyright 2020 NXP
+ * Lynx PCS helpers
+ */
+
+#ifndef __LINUX_PCS_LYNX_H
+#define __LINUX_PCS_LYNX_H
+
+#include <linux/mdio.h>
+#include <linux/phylink.h>
+
+struct lynx_pcs {
+	struct phylink_pcs pcs;
+	struct mdio_device *mdio;
+};
+
+struct lynx_pcs *lynx_pcs_create(struct mdio_device *mdio);
+
+void lynx_pcs_destroy(struct lynx_pcs *pcs);
+
+#endif /* __LINUX_PCS_LYNX_H */
-- 
cgit v1.2.3


From 3f7d820bad6cace3ecb859bf3fa5bc56fe8bb1c6 Mon Sep 17 00:00:00 2001
From: Miaohe Lin <linmiaohe@huawei.com>
Date: Mon, 31 Aug 2020 02:26:10 -0400
Subject: net: ipv6: remove unused arg exact_dif in compute_score

The arg exact_dif is not used anymore, remove it. inet6_exact_dif_match()
is no longer needed after the above is removed, remove it too.

Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ipv6.h        | 11 -----------
 net/ipv6/inet6_hashtables.c |  6 ++----
 2 files changed, 2 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index bac8f4fffbd6..dda61d150a13 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -177,17 +177,6 @@ static inline int inet6_sdif(const struct sk_buff *skb)
 	return 0;
 }
 
-/* can not be used in TCP layer after tcp_v6_fill_cb */
-static inline bool inet6_exact_dif_match(struct net *net, struct sk_buff *skb)
-{
-#if defined(CONFIG_NET_L3_MASTER_DEV)
-	if (!net->ipv4.sysctl_tcp_l3mdev_accept &&
-	    skb && ipv6_l3mdev_skb(IP6CB(skb)->flags))
-		return true;
-#endif
-	return false;
-}
-
 struct tcp6_request_sock {
 	struct tcp_request_sock	  tcp6rsk_tcp;
 };
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 2d3add9e6116..55c290d55605 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -94,7 +94,7 @@ EXPORT_SYMBOL(__inet6_lookup_established);
 static inline int compute_score(struct sock *sk, struct net *net,
 				const unsigned short hnum,
 				const struct in6_addr *daddr,
-				const int dif, const int sdif, bool exact_dif)
+				const int dif, const int sdif)
 {
 	int score = -1;
 
@@ -138,15 +138,13 @@ static struct sock *inet6_lhash2_lookup(struct net *net,
 		const __be16 sport, const struct in6_addr *daddr,
 		const unsigned short hnum, const int dif, const int sdif)
 {
-	bool exact_dif = inet6_exact_dif_match(net, skb);
 	struct inet_connection_sock *icsk;
 	struct sock *sk, *result = NULL;
 	int score, hiscore = 0;
 
 	inet_lhash2_for_each_icsk_rcu(icsk, &ilb2->head) {
 		sk = (struct sock *)icsk;
-		score = compute_score(sk, net, hnum, daddr, dif, sdif,
-				      exact_dif);
+		score = compute_score(sk, net, hnum, daddr, dif, sdif);
 		if (score > hiscore) {
 			result = lookup_reuseport(net, sk, skb, doff,
 						  saddr, sport, daddr, hnum);
-- 
cgit v1.2.3


From b7176c261cdbced87bed9562577333150ed05b01 Mon Sep 17 00:00:00 2001
From: Barry Song <song.bao.hua@hisilicon.com>
Date: Mon, 24 Aug 2020 11:03:07 +1200
Subject: dma-contiguous: provide the ability to reserve per-numa CMA

Right now, drivers like ARM SMMU are using dma_alloc_coherent() to get
coherent DMA buffers to save their command queues and page tables. As
there is only one default CMA in the whole system, SMMUs on nodes other
than node0 will get remote memory. This leads to significant latency.

This patch provides per-numa CMA so that drivers like SMMU can get local
memory. Tests show localizing CMA can decrease dma_unmap latency much.
For instance, before this patch, SMMU on node2  has to wait for more than
560ns for the completion of CMD_SYNC in an empty command queue; with this
patch, it needs 240ns only.

A positive side effect of this patch would be improving performance even
further for those users who are worried about performance more than DMA
security and use iommu.passthrough=1 to skip IOMMU. With local CMA, all
drivers can get local coherent DMA buffers.

Also, this patch changes the default CONFIG_CMA_AREAS to 19 in NUMA. As
1+CONFIG_CMA_AREAS should be quite enough for most servers on the market
even they enable both hugetlb_cma and pernuma_cma.
2 numa nodes: 2(hugetlb) + 2(pernuma) + 1(default global cma) = 5
4 numa nodes: 4(hugetlb) + 4(pernuma) + 1(default global cma) = 9
8 numa nodes: 8(hugetlb) + 8(pernuma) + 1(default global cma) = 17

Signed-off-by: Barry Song <song.bao.hua@hisilicon.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 Documentation/admin-guide/kernel-parameters.txt |  11 +++
 include/linux/dma-contiguous.h                  |   6 ++
 kernel/dma/Kconfig                              |  11 +++
 kernel/dma/contiguous.c                         | 100 +++++++++++++++++++++---
 mm/Kconfig                                      |   3 +-
 5 files changed, 120 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index a1068742a6df..e464cf0b5025 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -599,6 +599,17 @@
 			altogether. For more information, see
 			include/linux/dma-contiguous.h
 
+	cma_pernuma=nn[MG]
+			[ARM64,KNL]
+			Sets the size of kernel per-numa memory area for
+			contiguous memory allocations. A value of 0 disables
+			per-numa CMA altogether. And If this option is not
+			specificed, the default value is 0.
+			With per-numa CMA enabled, DMA users on node nid will
+			first try to allocate buffer from the pernuma area
+			which is located in node nid, if the allocation fails,
+			they will fallback to the global default memory area.
+
 	cmo_free_hint=	[PPC] Format: { yes | no }
 			Specify whether pages are marked as being inactive
 			when they are freed.  This is used in CMO environments
diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h
index 03f8e98e3bcc..fe55e004f1f4 100644
--- a/include/linux/dma-contiguous.h
+++ b/include/linux/dma-contiguous.h
@@ -171,6 +171,12 @@ static inline void dma_free_contiguous(struct device *dev, struct page *page,
 
 #endif
 
+#ifdef CONFIG_DMA_PERNUMA_CMA
+void dma_pernuma_cma_reserve(void);
+#else
+static inline void dma_pernuma_cma_reserve(void) { }
+#endif
+
 #endif
 
 #endif
diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index 847a9d1fa634..0ddfb5510fe4 100644
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@ -118,6 +118,17 @@ config DMA_CMA
 	  If unsure, say "n".
 
 if  DMA_CMA
+
+config DMA_PERNUMA_CMA
+	bool "Enable separate DMA Contiguous Memory Area for each NUMA Node"
+	default NUMA && ARM64
+	help
+	  Enable this option to get pernuma CMA areas so that devices like
+	  ARM64 SMMU can get local memory by DMA coherent APIs.
+
+	  You can set the size of pernuma CMA by specifying "cma_pernuma=size"
+	  on the kernel's command line.
+
 comment "Default contiguous memory area size:"
 
 config CMA_SIZE_MBYTES
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index cff7e60968b9..aa53384fd7dc 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -69,6 +69,19 @@ static int __init early_cma(char *p)
 }
 early_param("cma", early_cma);
 
+#ifdef CONFIG_DMA_PERNUMA_CMA
+
+static struct cma *dma_contiguous_pernuma_area[MAX_NUMNODES];
+static phys_addr_t pernuma_size_bytes __initdata;
+
+static int __init early_cma_pernuma(char *p)
+{
+	pernuma_size_bytes = memparse(p, &p);
+	return 0;
+}
+early_param("cma_pernuma", early_cma_pernuma);
+#endif
+
 #ifdef CONFIG_CMA_SIZE_PERCENTAGE
 
 static phys_addr_t __init __maybe_unused cma_early_percent_memory(void)
@@ -96,6 +109,34 @@ static inline __maybe_unused phys_addr_t cma_early_percent_memory(void)
 
 #endif
 
+#ifdef CONFIG_DMA_PERNUMA_CMA
+void __init dma_pernuma_cma_reserve(void)
+{
+	int nid;
+
+	if (!pernuma_size_bytes)
+		return;
+
+	for_each_online_node(nid) {
+		int ret;
+		char name[20];
+		struct cma **cma = &dma_contiguous_pernuma_area[nid];
+
+		snprintf(name, sizeof(name), "pernuma%d", nid);
+		ret = cma_declare_contiguous_nid(0, pernuma_size_bytes, 0, 0,
+						 0, false, name, cma, nid);
+		if (ret) {
+			pr_warn("%s: reservation failed: err %d, node %d", __func__,
+				ret, nid);
+			continue;
+		}
+
+		pr_debug("%s: reserved %llu MiB on node %d\n", __func__,
+			(unsigned long long)pernuma_size_bytes / SZ_1M, nid);
+	}
+}
+#endif
+
 /**
  * dma_contiguous_reserve() - reserve area(s) for contiguous memory handling
  * @limit: End address of the reserved memory (optional, 0 for any).
@@ -228,23 +269,44 @@ static struct page *cma_alloc_aligned(struct cma *cma, size_t size, gfp_t gfp)
  * @size:  Requested allocation size.
  * @gfp:   Allocation flags.
  *
- * This function allocates contiguous memory buffer for specified device. It
- * tries to use device specific contiguous memory area if available, or the
- * default global one.
+ * tries to use device specific contiguous memory area if available, or it
+ * tries to use per-numa cma, if the allocation fails, it will fallback to
+ * try default global one.
  *
- * Note that it byapss one-page size of allocations from the global area as
- * the addresses within one page are always contiguous, so there is no need
- * to waste CMA pages for that kind; it also helps reduce fragmentations.
+ * Note that it bypass one-page size of allocations from the per-numa and
+ * global area as the addresses within one page are always contiguous, so
+ * there is no need to waste CMA pages for that kind; it also helps reduce
+ * fragmentations.
  */
 struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp)
 {
+#ifdef CONFIG_DMA_PERNUMA_CMA
+	int nid = dev_to_node(dev);
+#endif
+
 	/* CMA can be used only in the context which permits sleeping */
 	if (!gfpflags_allow_blocking(gfp))
 		return NULL;
 	if (dev->cma_area)
 		return cma_alloc_aligned(dev->cma_area, size, gfp);
-	if (size <= PAGE_SIZE || !dma_contiguous_default_area)
+	if (size <= PAGE_SIZE)
+		return NULL;
+
+#ifdef CONFIG_DMA_PERNUMA_CMA
+	if (nid != NUMA_NO_NODE && !(gfp & (GFP_DMA | GFP_DMA32))) {
+		struct cma *cma = dma_contiguous_pernuma_area[nid];
+		struct page *page;
+
+		if (cma) {
+			page = cma_alloc_aligned(cma, size, gfp);
+			if (page)
+				return page;
+		}
+	}
+#endif
+	if (!dma_contiguous_default_area)
 		return NULL;
+
 	return cma_alloc_aligned(dma_contiguous_default_area, size, gfp);
 }
 
@@ -261,9 +323,27 @@ struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp)
  */
 void dma_free_contiguous(struct device *dev, struct page *page, size_t size)
 {
-	if (!cma_release(dev_get_cma_area(dev), page,
-			 PAGE_ALIGN(size) >> PAGE_SHIFT))
-		__free_pages(page, get_order(size));
+	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+
+	/* if dev has its own cma, free page from there */
+	if (dev->cma_area) {
+		if (cma_release(dev->cma_area, page, count))
+			return;
+	} else {
+		/*
+		 * otherwise, page is from either per-numa cma or default cma
+		 */
+#ifdef CONFIG_DMA_PERNUMA_CMA
+		if (cma_release(dma_contiguous_pernuma_area[page_to_nid(page)],
+					page, count))
+			return;
+#endif
+		if (cma_release(dma_contiguous_default_area, page, count))
+			return;
+	}
+
+	/* not in any cma, free from buddy */
+	__free_pages(page, get_order(size));
 }
 
 /*
diff --git a/mm/Kconfig b/mm/Kconfig
index 6c974888f86f..d75a0107f61f 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -516,13 +516,14 @@ config CMA_DEBUGFS
 config CMA_AREAS
 	int "Maximum count of the CMA areas"
 	depends on CMA
+	default 19 if NUMA
 	default 7
 	help
 	  CMA allows to create CMA areas for particular purpose, mainly,
 	  used as device private area. This parameter sets the maximum
 	  number of CMA area in the system.
 
-	  If unsure, leave the default value "7".
+	  If unsure, leave the default value "7" in UMA and "19" in NUMA.
 
 config MEM_SOFT_DIRTY
 	bool "Track memory changes"
-- 
cgit v1.2.3


From 2281f797f5524abb8fff66bf8540b4f4687332a2 Mon Sep 17 00:00:00 2001
From: Barry Song <song.bao.hua@hisilicon.com>
Date: Mon, 24 Aug 2020 11:03:09 +1200
Subject: mm: cma: use CMA_MAX_NAME to define the length of cma name array

CMA_MAX_NAME should be visible to CMA's users as they might need it to set
the name of CMA areas and avoid hardcoding the size locally.
So this patch moves CMA_MAX_NAME from local header file to include/linux
header file and removes the hardcode in both hugetlb.c and contiguous.c.

Signed-off-by: Barry Song <song.bao.hua@hisilicon.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/cma.h     | 2 ++
 kernel/dma/contiguous.c | 2 +-
 mm/cma.h                | 2 --
 mm/hugetlb.c            | 4 ++--
 4 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cma.h b/include/linux/cma.h
index 6ff79fefd01f..217999c8a762 100644
--- a/include/linux/cma.h
+++ b/include/linux/cma.h
@@ -18,6 +18,8 @@
 
 #endif
 
+#define CMA_MAX_NAME 64
+
 struct cma;
 
 extern unsigned long totalcma_pages;
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index aa53384fd7dc..f4c150810fd2 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -119,7 +119,7 @@ void __init dma_pernuma_cma_reserve(void)
 
 	for_each_online_node(nid) {
 		int ret;
-		char name[20];
+		char name[CMA_MAX_NAME];
 		struct cma **cma = &dma_contiguous_pernuma_area[nid];
 
 		snprintf(name, sizeof(name), "pernuma%d", nid);
diff --git a/mm/cma.h b/mm/cma.h
index 20f6e24bc477..42ae082cb067 100644
--- a/mm/cma.h
+++ b/mm/cma.h
@@ -4,8 +4,6 @@
 
 #include <linux/debugfs.h>
 
-#define CMA_MAX_NAME 64
-
 struct cma {
 	unsigned long   base_pfn;
 	unsigned long   count;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a301c2d672bf..9eec0ea9ba68 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5683,12 +5683,12 @@ void __init hugetlb_cma_reserve(int order)
 	reserved = 0;
 	for_each_node_state(nid, N_ONLINE) {
 		int res;
-		char name[20];
+		char name[CMA_MAX_NAME];
 
 		size = min(per_node, hugetlb_cma_size - reserved);
 		size = round_up(size, PAGE_SIZE << order);
 
-		snprintf(name, 20, "hugetlb%d", nid);
+		snprintf(name, sizeof(name), "hugetlb%d", nid);
 		res = cma_declare_contiguous_nid(0, size, 0, PAGE_SIZE << order,
 						 0, false, name,
 						 &hugetlb_cma[nid], nid);
-- 
cgit v1.2.3


From 70d932985757fbe978024db313001218e9f8fe5c Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 18 Aug 2020 15:57:36 +0200
Subject: notifier: Fix broken error handling pattern

The current notifiers have the following error handling pattern all
over the place:

	int err, nr;

	err = __foo_notifier_call_chain(&chain, val_up, v, -1, &nr);
	if (err & NOTIFIER_STOP_MASK)
		__foo_notifier_call_chain(&chain, val_down, v, nr-1, NULL)

And aside from the endless repetition thereof, it is broken. Consider
blocking notifiers; both calls take and drop the rwsem, this means
that the notifier list can change in between the two calls, making @nr
meaningless.

Fix this by replacing all the __foo_notifier_call_chain() functions
with foo_notifier_call_chain_robust() that embeds the above pattern,
but ensures it is inside a single lock region.

Note: I switched atomic_notifier_call_chain_robust() to use
      the spinlock, since RCU cannot provide the guarantee
      required for the recovery.

Note: software_resume() error handling was broken afaict.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lore.kernel.org/r/20200818135804.325626653@infradead.org
---
 include/linux/notifier.h           |  15 ++--
 kernel/cpu_pm.c                    |  48 +++++--------
 kernel/notifier.c                  | 144 ++++++++++++++++++++++---------------
 kernel/power/hibernate.c           |  39 +++++-----
 kernel/power/main.c                |   8 +--
 kernel/power/power.h               |   3 +-
 kernel/power/suspend.c             |  14 ++--
 kernel/power/user.c                |  14 ++--
 tools/power/pm-graph/sleepgraph.py |   2 +-
 9 files changed, 147 insertions(+), 140 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/notifier.h b/include/linux/notifier.h
index 018947611483..2fb373a5c1ed 100644
--- a/include/linux/notifier.h
+++ b/include/linux/notifier.h
@@ -161,20 +161,19 @@ extern int srcu_notifier_chain_unregister(struct srcu_notifier_head *nh,
 
 extern int atomic_notifier_call_chain(struct atomic_notifier_head *nh,
 		unsigned long val, void *v);
-extern int __atomic_notifier_call_chain(struct atomic_notifier_head *nh,
-	unsigned long val, void *v, int nr_to_call, int *nr_calls);
 extern int blocking_notifier_call_chain(struct blocking_notifier_head *nh,
 		unsigned long val, void *v);
-extern int __blocking_notifier_call_chain(struct blocking_notifier_head *nh,
-	unsigned long val, void *v, int nr_to_call, int *nr_calls);
 extern int raw_notifier_call_chain(struct raw_notifier_head *nh,
 		unsigned long val, void *v);
-extern int __raw_notifier_call_chain(struct raw_notifier_head *nh,
-	unsigned long val, void *v, int nr_to_call, int *nr_calls);
 extern int srcu_notifier_call_chain(struct srcu_notifier_head *nh,
 		unsigned long val, void *v);
-extern int __srcu_notifier_call_chain(struct srcu_notifier_head *nh,
-	unsigned long val, void *v, int nr_to_call, int *nr_calls);
+
+extern int atomic_notifier_call_chain_robust(struct atomic_notifier_head *nh,
+		unsigned long val_up, unsigned long val_down, void *v);
+extern int blocking_notifier_call_chain_robust(struct blocking_notifier_head *nh,
+		unsigned long val_up, unsigned long val_down, void *v);
+extern int raw_notifier_call_chain_robust(struct raw_notifier_head *nh,
+		unsigned long val_up, unsigned long val_down, void *v);
 
 #define NOTIFY_DONE		0x0000		/* Don't care */
 #define NOTIFY_OK		0x0001		/* Suits me */
diff --git a/kernel/cpu_pm.c b/kernel/cpu_pm.c
index 44a259338e33..f7e1d0eccdbc 100644
--- a/kernel/cpu_pm.c
+++ b/kernel/cpu_pm.c
@@ -15,18 +15,28 @@
 
 static ATOMIC_NOTIFIER_HEAD(cpu_pm_notifier_chain);
 
-static int cpu_pm_notify(enum cpu_pm_event event, int nr_to_call, int *nr_calls)
+static int cpu_pm_notify(enum cpu_pm_event event)
 {
 	int ret;
 
 	/*
-	 * __atomic_notifier_call_chain has a RCU read critical section, which
+	 * atomic_notifier_call_chain has a RCU read critical section, which
 	 * could be disfunctional in cpu idle. Copy RCU_NONIDLE code to let
 	 * RCU know this.
 	 */
 	rcu_irq_enter_irqson();
-	ret = __atomic_notifier_call_chain(&cpu_pm_notifier_chain, event, NULL,
-		nr_to_call, nr_calls);
+	ret = atomic_notifier_call_chain(&cpu_pm_notifier_chain, event, NULL);
+	rcu_irq_exit_irqson();
+
+	return notifier_to_errno(ret);
+}
+
+static int cpu_pm_notify_robust(enum cpu_pm_event event_up, enum cpu_pm_event event_down)
+{
+	int ret;
+
+	rcu_irq_enter_irqson();
+	ret = atomic_notifier_call_chain_robust(&cpu_pm_notifier_chain, event_up, event_down, NULL);
 	rcu_irq_exit_irqson();
 
 	return notifier_to_errno(ret);
@@ -80,18 +90,7 @@ EXPORT_SYMBOL_GPL(cpu_pm_unregister_notifier);
  */
 int cpu_pm_enter(void)
 {
-	int nr_calls = 0;
-	int ret = 0;
-
-	ret = cpu_pm_notify(CPU_PM_ENTER, -1, &nr_calls);
-	if (ret)
-		/*
-		 * Inform listeners (nr_calls - 1) about failure of CPU PM
-		 * PM entry who are notified earlier to prepare for it.
-		 */
-		cpu_pm_notify(CPU_PM_ENTER_FAILED, nr_calls - 1, NULL);
-
-	return ret;
+	return cpu_pm_notify_robust(CPU_PM_ENTER, CPU_PM_ENTER_FAILED);
 }
 EXPORT_SYMBOL_GPL(cpu_pm_enter);
 
@@ -109,7 +108,7 @@ EXPORT_SYMBOL_GPL(cpu_pm_enter);
  */
 int cpu_pm_exit(void)
 {
-	return cpu_pm_notify(CPU_PM_EXIT, -1, NULL);
+	return cpu_pm_notify(CPU_PM_EXIT);
 }
 EXPORT_SYMBOL_GPL(cpu_pm_exit);
 
@@ -131,18 +130,7 @@ EXPORT_SYMBOL_GPL(cpu_pm_exit);
  */
 int cpu_cluster_pm_enter(void)
 {
-	int nr_calls = 0;
-	int ret = 0;
-
-	ret = cpu_pm_notify(CPU_CLUSTER_PM_ENTER, -1, &nr_calls);
-	if (ret)
-		/*
-		 * Inform listeners (nr_calls - 1) about failure of CPU cluster
-		 * PM entry who are notified earlier to prepare for it.
-		 */
-		cpu_pm_notify(CPU_CLUSTER_PM_ENTER_FAILED, nr_calls - 1, NULL);
-
-	return ret;
+	return cpu_pm_notify_robust(CPU_CLUSTER_PM_ENTER, CPU_CLUSTER_PM_ENTER_FAILED);
 }
 EXPORT_SYMBOL_GPL(cpu_cluster_pm_enter);
 
@@ -163,7 +151,7 @@ EXPORT_SYMBOL_GPL(cpu_cluster_pm_enter);
  */
 int cpu_cluster_pm_exit(void)
 {
-	return cpu_pm_notify(CPU_CLUSTER_PM_EXIT, -1, NULL);
+	return cpu_pm_notify(CPU_CLUSTER_PM_EXIT);
 }
 EXPORT_SYMBOL_GPL(cpu_cluster_pm_exit);
 
diff --git a/kernel/notifier.c b/kernel/notifier.c
index 84c987dfbe03..1b019cbca594 100644
--- a/kernel/notifier.c
+++ b/kernel/notifier.c
@@ -94,6 +94,34 @@ static int notifier_call_chain(struct notifier_block **nl,
 }
 NOKPROBE_SYMBOL(notifier_call_chain);
 
+/**
+ * notifier_call_chain_robust - Inform the registered notifiers about an event
+ *                              and rollback on error.
+ * @nl:		Pointer to head of the blocking notifier chain
+ * @val_up:	Value passed unmodified to the notifier function
+ * @val_down:	Value passed unmodified to the notifier function when recovering
+ *              from an error on @val_up
+ * @v		Pointer passed unmodified to the notifier function
+ *
+ * NOTE:	It is important the @nl chain doesn't change between the two
+ *		invocations of notifier_call_chain() such that we visit the
+ *		exact same notifier callbacks; this rules out any RCU usage.
+ *
+ * Returns:	the return value of the @val_up call.
+ */
+static int notifier_call_chain_robust(struct notifier_block **nl,
+				     unsigned long val_up, unsigned long val_down,
+				     void *v)
+{
+	int ret, nr = 0;
+
+	ret = notifier_call_chain(nl, val_up, v, -1, &nr);
+	if (ret & NOTIFY_STOP_MASK)
+		notifier_call_chain(nl, val_down, v, nr-1, NULL);
+
+	return ret;
+}
+
 /*
  *	Atomic notifier chain routines.  Registration and unregistration
  *	use a spinlock, and call_chain is synchronized by RCU (no locks).
@@ -144,13 +172,30 @@ int atomic_notifier_chain_unregister(struct atomic_notifier_head *nh,
 }
 EXPORT_SYMBOL_GPL(atomic_notifier_chain_unregister);
 
+int atomic_notifier_call_chain_robust(struct atomic_notifier_head *nh,
+		unsigned long val_up, unsigned long val_down, void *v)
+{
+	unsigned long flags;
+	int ret;
+
+	/*
+	 * Musn't use RCU; because then the notifier list can
+	 * change between the up and down traversal.
+	 */
+	spin_lock_irqsave(&nh->lock, flags);
+	ret = notifier_call_chain_robust(&nh->head, val_up, val_down, v);
+	spin_unlock_irqrestore(&nh->lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(atomic_notifier_call_chain_robust);
+NOKPROBE_SYMBOL(atomic_notifier_call_chain_robust);
+
 /**
- *	__atomic_notifier_call_chain - Call functions in an atomic notifier chain
+ *	atomic_notifier_call_chain - Call functions in an atomic notifier chain
  *	@nh: Pointer to head of the atomic notifier chain
  *	@val: Value passed unmodified to notifier function
  *	@v: Pointer passed unmodified to notifier function
- *	@nr_to_call: See the comment for notifier_call_chain.
- *	@nr_calls: See the comment for notifier_call_chain.
  *
  *	Calls each function in a notifier chain in turn.  The functions
  *	run in an atomic context, so they must not block.
@@ -163,24 +208,16 @@ EXPORT_SYMBOL_GPL(atomic_notifier_chain_unregister);
  *	Otherwise the return value is the return value
  *	of the last notifier function called.
  */
-int __atomic_notifier_call_chain(struct atomic_notifier_head *nh,
-				 unsigned long val, void *v,
-				 int nr_to_call, int *nr_calls)
+int atomic_notifier_call_chain(struct atomic_notifier_head *nh,
+			       unsigned long val, void *v)
 {
 	int ret;
 
 	rcu_read_lock();
-	ret = notifier_call_chain(&nh->head, val, v, nr_to_call, nr_calls);
+	ret = notifier_call_chain(&nh->head, val, v, -1, NULL);
 	rcu_read_unlock();
-	return ret;
-}
-EXPORT_SYMBOL_GPL(__atomic_notifier_call_chain);
-NOKPROBE_SYMBOL(__atomic_notifier_call_chain);
 
-int atomic_notifier_call_chain(struct atomic_notifier_head *nh,
-			       unsigned long val, void *v)
-{
-	return __atomic_notifier_call_chain(nh, val, v, -1, NULL);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(atomic_notifier_call_chain);
 NOKPROBE_SYMBOL(atomic_notifier_call_chain);
@@ -250,13 +287,30 @@ int blocking_notifier_chain_unregister(struct blocking_notifier_head *nh,
 }
 EXPORT_SYMBOL_GPL(blocking_notifier_chain_unregister);
 
+int blocking_notifier_call_chain_robust(struct blocking_notifier_head *nh,
+		unsigned long val_up, unsigned long val_down, void *v)
+{
+	int ret = NOTIFY_DONE;
+
+	/*
+	 * We check the head outside the lock, but if this access is
+	 * racy then it does not matter what the result of the test
+	 * is, we re-check the list after having taken the lock anyway:
+	 */
+	if (rcu_access_pointer(nh->head)) {
+		down_read(&nh->rwsem);
+		ret = notifier_call_chain_robust(&nh->head, val_up, val_down, v);
+		up_read(&nh->rwsem);
+	}
+	return ret;
+}
+EXPORT_SYMBOL_GPL(blocking_notifier_call_chain_robust);
+
 /**
- *	__blocking_notifier_call_chain - Call functions in a blocking notifier chain
+ *	blocking_notifier_call_chain - Call functions in a blocking notifier chain
  *	@nh: Pointer to head of the blocking notifier chain
  *	@val: Value passed unmodified to notifier function
  *	@v: Pointer passed unmodified to notifier function
- *	@nr_to_call: See comment for notifier_call_chain.
- *	@nr_calls: See comment for notifier_call_chain.
  *
  *	Calls each function in a notifier chain in turn.  The functions
  *	run in a process context, so they are allowed to block.
@@ -268,9 +322,8 @@ EXPORT_SYMBOL_GPL(blocking_notifier_chain_unregister);
  *	Otherwise the return value is the return value
  *	of the last notifier function called.
  */
-int __blocking_notifier_call_chain(struct blocking_notifier_head *nh,
-				   unsigned long val, void *v,
-				   int nr_to_call, int *nr_calls)
+int blocking_notifier_call_chain(struct blocking_notifier_head *nh,
+		unsigned long val, void *v)
 {
 	int ret = NOTIFY_DONE;
 
@@ -281,19 +334,11 @@ int __blocking_notifier_call_chain(struct blocking_notifier_head *nh,
 	 */
 	if (rcu_access_pointer(nh->head)) {
 		down_read(&nh->rwsem);
-		ret = notifier_call_chain(&nh->head, val, v, nr_to_call,
-					nr_calls);
+		ret = notifier_call_chain(&nh->head, val, v, -1, NULL);
 		up_read(&nh->rwsem);
 	}
 	return ret;
 }
-EXPORT_SYMBOL_GPL(__blocking_notifier_call_chain);
-
-int blocking_notifier_call_chain(struct blocking_notifier_head *nh,
-		unsigned long val, void *v)
-{
-	return __blocking_notifier_call_chain(nh, val, v, -1, NULL);
-}
 EXPORT_SYMBOL_GPL(blocking_notifier_call_chain);
 
 /*
@@ -335,13 +380,18 @@ int raw_notifier_chain_unregister(struct raw_notifier_head *nh,
 }
 EXPORT_SYMBOL_GPL(raw_notifier_chain_unregister);
 
+int raw_notifier_call_chain_robust(struct raw_notifier_head *nh,
+		unsigned long val_up, unsigned long val_down, void *v)
+{
+	return notifier_call_chain_robust(&nh->head, val_up, val_down, v);
+}
+EXPORT_SYMBOL_GPL(raw_notifier_call_chain_robust);
+
 /**
- *	__raw_notifier_call_chain - Call functions in a raw notifier chain
+ *	raw_notifier_call_chain - Call functions in a raw notifier chain
  *	@nh: Pointer to head of the raw notifier chain
  *	@val: Value passed unmodified to notifier function
  *	@v: Pointer passed unmodified to notifier function
- *	@nr_to_call: See comment for notifier_call_chain.
- *	@nr_calls: See comment for notifier_call_chain
  *
  *	Calls each function in a notifier chain in turn.  The functions
  *	run in an undefined context.
@@ -354,18 +404,10 @@ EXPORT_SYMBOL_GPL(raw_notifier_chain_unregister);
  *	Otherwise the return value is the return value
  *	of the last notifier function called.
  */
-int __raw_notifier_call_chain(struct raw_notifier_head *nh,
-			      unsigned long val, void *v,
-			      int nr_to_call, int *nr_calls)
-{
-	return notifier_call_chain(&nh->head, val, v, nr_to_call, nr_calls);
-}
-EXPORT_SYMBOL_GPL(__raw_notifier_call_chain);
-
 int raw_notifier_call_chain(struct raw_notifier_head *nh,
 		unsigned long val, void *v)
 {
-	return __raw_notifier_call_chain(nh, val, v, -1, NULL);
+	return notifier_call_chain(&nh->head, val, v, -1, NULL);
 }
 EXPORT_SYMBOL_GPL(raw_notifier_call_chain);
 
@@ -437,12 +479,10 @@ int srcu_notifier_chain_unregister(struct srcu_notifier_head *nh,
 EXPORT_SYMBOL_GPL(srcu_notifier_chain_unregister);
 
 /**
- *	__srcu_notifier_call_chain - Call functions in an SRCU notifier chain
+ *	srcu_notifier_call_chain - Call functions in an SRCU notifier chain
  *	@nh: Pointer to head of the SRCU notifier chain
  *	@val: Value passed unmodified to notifier function
  *	@v: Pointer passed unmodified to notifier function
- *	@nr_to_call: See comment for notifier_call_chain.
- *	@nr_calls: See comment for notifier_call_chain
  *
  *	Calls each function in a notifier chain in turn.  The functions
  *	run in a process context, so they are allowed to block.
@@ -454,25 +494,17 @@ EXPORT_SYMBOL_GPL(srcu_notifier_chain_unregister);
  *	Otherwise the return value is the return value
  *	of the last notifier function called.
  */
-int __srcu_notifier_call_chain(struct srcu_notifier_head *nh,
-			       unsigned long val, void *v,
-			       int nr_to_call, int *nr_calls)
+int srcu_notifier_call_chain(struct srcu_notifier_head *nh,
+		unsigned long val, void *v)
 {
 	int ret;
 	int idx;
 
 	idx = srcu_read_lock(&nh->srcu);
-	ret = notifier_call_chain(&nh->head, val, v, nr_to_call, nr_calls);
+	ret = notifier_call_chain(&nh->head, val, v, -1, NULL);
 	srcu_read_unlock(&nh->srcu, idx);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(__srcu_notifier_call_chain);
-
-int srcu_notifier_call_chain(struct srcu_notifier_head *nh,
-		unsigned long val, void *v)
-{
-	return __srcu_notifier_call_chain(nh, val, v, -1, NULL);
-}
 EXPORT_SYMBOL_GPL(srcu_notifier_call_chain);
 
 /**
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index e7aa57fb2fdc..1dee70815f3c 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -706,8 +706,8 @@ static int load_image_and_restore(void)
  */
 int hibernate(void)
 {
-	int error, nr_calls = 0;
 	bool snapshot_test = false;
+	int error;
 
 	if (!hibernation_available()) {
 		pm_pr_dbg("Hibernation not available.\n");
@@ -723,11 +723,9 @@ int hibernate(void)
 
 	pr_info("hibernation entry\n");
 	pm_prepare_console();
-	error = __pm_notifier_call_chain(PM_HIBERNATION_PREPARE, -1, &nr_calls);
-	if (error) {
-		nr_calls--;
-		goto Exit;
-	}
+	error = pm_notifier_call_chain_robust(PM_HIBERNATION_PREPARE, PM_POST_HIBERNATION);
+	if (error)
+		goto Restore;
 
 	ksys_sync_helper();
 
@@ -785,7 +783,8 @@ int hibernate(void)
 	/* Don't bother checking whether freezer_test_done is true */
 	freezer_test_done = false;
  Exit:
-	__pm_notifier_call_chain(PM_POST_HIBERNATION, nr_calls, NULL);
+	pm_notifier_call_chain(PM_POST_HIBERNATION);
+ Restore:
 	pm_restore_console();
 	hibernate_release();
  Unlock:
@@ -804,7 +803,7 @@ int hibernate(void)
  */
 int hibernate_quiet_exec(int (*func)(void *data), void *data)
 {
-	int error, nr_calls = 0;
+	int error;
 
 	lock_system_sleep();
 
@@ -815,11 +814,9 @@ int hibernate_quiet_exec(int (*func)(void *data), void *data)
 
 	pm_prepare_console();
 
-	error = __pm_notifier_call_chain(PM_HIBERNATION_PREPARE, -1, &nr_calls);
-	if (error) {
-		nr_calls--;
-		goto exit;
-	}
+	error = pm_notifier_call_chain_robust(PM_HIBERNATION_PREPARE, PM_POST_HIBERNATION);
+	if (error)
+		goto restore;
 
 	error = freeze_processes();
 	if (error)
@@ -880,8 +877,9 @@ thaw:
 	thaw_processes();
 
 exit:
-	__pm_notifier_call_chain(PM_POST_HIBERNATION, nr_calls, NULL);
+	pm_notifier_call_chain(PM_POST_HIBERNATION);
 
+restore:
 	pm_restore_console();
 
 	hibernate_release();
@@ -910,7 +908,7 @@ EXPORT_SYMBOL_GPL(hibernate_quiet_exec);
  */
 static int software_resume(void)
 {
-	int error, nr_calls = 0;
+	int error;
 
 	/*
 	 * If the user said "noresume".. bail out early.
@@ -997,11 +995,9 @@ static int software_resume(void)
 
 	pr_info("resume from hibernation\n");
 	pm_prepare_console();
-	error = __pm_notifier_call_chain(PM_RESTORE_PREPARE, -1, &nr_calls);
-	if (error) {
-		nr_calls--;
-		goto Close_Finish;
-	}
+	error = pm_notifier_call_chain_robust(PM_RESTORE_PREPARE, PM_POST_RESTORE);
+	if (error)
+		goto Restore;
 
 	pm_pr_dbg("Preparing processes for hibernation restore.\n");
 	error = freeze_processes();
@@ -1017,7 +1013,8 @@ static int software_resume(void)
 	error = load_image_and_restore();
 	thaw_processes();
  Finish:
-	__pm_notifier_call_chain(PM_POST_RESTORE, nr_calls, NULL);
+	pm_notifier_call_chain(PM_POST_RESTORE);
+ Restore:
 	pm_restore_console();
 	pr_info("resume failed (%d)\n", error);
 	hibernate_release();
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 40f86ec4ab30..0aefd6f57e0a 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -80,18 +80,18 @@ int unregister_pm_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL_GPL(unregister_pm_notifier);
 
-int __pm_notifier_call_chain(unsigned long val, int nr_to_call, int *nr_calls)
+int pm_notifier_call_chain_robust(unsigned long val_up, unsigned long val_down)
 {
 	int ret;
 
-	ret = __blocking_notifier_call_chain(&pm_chain_head, val, NULL,
-						nr_to_call, nr_calls);
+	ret = blocking_notifier_call_chain_robust(&pm_chain_head, val_up, val_down, NULL);
 
 	return notifier_to_errno(ret);
 }
+
 int pm_notifier_call_chain(unsigned long val)
 {
-	return __pm_notifier_call_chain(val, -1, NULL);
+	return blocking_notifier_call_chain(&pm_chain_head, val, NULL);
 }
 
 /* If set, devices may be suspended and resumed asynchronously. */
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 32fc89ac96c3..24f12d534515 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -210,8 +210,7 @@ static inline void suspend_test_finish(const char *label) {}
 
 #ifdef CONFIG_PM_SLEEP
 /* kernel/power/main.c */
-extern int __pm_notifier_call_chain(unsigned long val, int nr_to_call,
-				    int *nr_calls);
+extern int pm_notifier_call_chain_robust(unsigned long val_up, unsigned long val_down);
 extern int pm_notifier_call_chain(unsigned long val);
 #endif
 
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 8b1bb5ee7e5d..32391acc806b 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -342,18 +342,16 @@ static int suspend_test(int level)
  */
 static int suspend_prepare(suspend_state_t state)
 {
-	int error, nr_calls = 0;
+	int error;
 
 	if (!sleep_state_supported(state))
 		return -EPERM;
 
 	pm_prepare_console();
 
-	error = __pm_notifier_call_chain(PM_SUSPEND_PREPARE, -1, &nr_calls);
-	if (error) {
-		nr_calls--;
-		goto Finish;
-	}
+	error = pm_notifier_call_chain_robust(PM_SUSPEND_PREPARE, PM_POST_SUSPEND);
+	if (error)
+		goto Restore;
 
 	trace_suspend_resume(TPS("freeze_processes"), 0, true);
 	error = suspend_freeze_processes();
@@ -363,8 +361,8 @@ static int suspend_prepare(suspend_state_t state)
 
 	suspend_stats.failed_freeze++;
 	dpm_save_failed_step(SUSPEND_FREEZE);
- Finish:
-	__pm_notifier_call_chain(PM_POST_SUSPEND, nr_calls, NULL);
+	pm_notifier_call_chain(PM_POST_SUSPEND);
+ Restore:
 	pm_restore_console();
 	return error;
 }
diff --git a/kernel/power/user.c b/kernel/power/user.c
index d5eedc2baa2a..047f598f89a5 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -46,7 +46,7 @@ int is_hibernate_resume_dev(const struct inode *bd_inode)
 static int snapshot_open(struct inode *inode, struct file *filp)
 {
 	struct snapshot_data *data;
-	int error, nr_calls = 0;
+	int error;
 
 	if (!hibernation_available())
 		return -EPERM;
@@ -73,9 +73,7 @@ static int snapshot_open(struct inode *inode, struct file *filp)
 			swap_type_of(swsusp_resume_device, 0, NULL) : -1;
 		data->mode = O_RDONLY;
 		data->free_bitmaps = false;
-		error = __pm_notifier_call_chain(PM_HIBERNATION_PREPARE, -1, &nr_calls);
-		if (error)
-			__pm_notifier_call_chain(PM_POST_HIBERNATION, --nr_calls, NULL);
+		error = pm_notifier_call_chain_robust(PM_HIBERNATION_PREPARE, PM_POST_HIBERNATION);
 	} else {
 		/*
 		 * Resuming.  We may need to wait for the image device to
@@ -85,15 +83,11 @@ static int snapshot_open(struct inode *inode, struct file *filp)
 
 		data->swap = -1;
 		data->mode = O_WRONLY;
-		error = __pm_notifier_call_chain(PM_RESTORE_PREPARE, -1, &nr_calls);
+		error = pm_notifier_call_chain_robust(PM_RESTORE_PREPARE, PM_POST_RESTORE);
 		if (!error) {
 			error = create_basic_memory_bitmaps();
 			data->free_bitmaps = !error;
-		} else
-			nr_calls--;
-
-		if (error)
-			__pm_notifier_call_chain(PM_POST_RESTORE, nr_calls, NULL);
+		}
 	}
 	if (error)
 		hibernate_release();
diff --git a/tools/power/pm-graph/sleepgraph.py b/tools/power/pm-graph/sleepgraph.py
index 46ff97e909c6..1bc36a1db14f 100755
--- a/tools/power/pm-graph/sleepgraph.py
+++ b/tools/power/pm-graph/sleepgraph.py
@@ -171,7 +171,7 @@ class SystemValues:
 	tracefuncs = {
 		'sys_sync': {},
 		'ksys_sync': {},
-		'__pm_notifier_call_chain': {},
+		'pm_notifier_call_chain_robust': {},
 		'pm_prepare_console': {},
 		'pm_notifier_call_chain': {},
 		'freeze_processes': {},
-- 
cgit v1.2.3


From 563a02b0c9704f69c0364befedd451f57fe88092 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Tue, 18 Aug 2020 15:57:40 +0200
Subject: compiler.h: Make __ADDRESSABLE() symbol truly unique

The __ADDRESSABLE() macro uses the __LINE__ macro to create a temporary
symbol which has a unique name.  However, if the macro is used multiple
times from within another macro, the line number will always be the
same, resulting in duplicate symbols.

Make the temporary symbols truly unique by using __UNIQUE_ID instead of
__LINE__.

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Link: https://lore.kernel.org/r/20200818135804.564436253@infradead.org
---
 include/linux/compiler.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 6810d80acb0b..92ef163a7479 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -207,7 +207,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
  */
 #define __ADDRESSABLE(sym) \
 	static void * __section(.discard.addressable) __used \
-		__PASTE(__addressable_##sym, __LINE__) = (void *)&sym;
+		__UNIQUE_ID(__PASTE(__addressable_,sym)) = (void *)&sym;
 
 /**
  * offset_to_ptr - convert a relative memory offset to an absolute pointer
-- 
cgit v1.2.3


From 115284d89a436e9b66da0c6c4f6efded806874b2 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Tue, 18 Aug 2020 15:57:41 +0200
Subject: static_call: Add basic static call infrastructure

Static calls are a replacement for global function pointers.  They use
code patching to allow direct calls to be used instead of indirect
calls.  They give the flexibility of function pointers, but with
improved performance.  This is especially important for cases where
retpolines would otherwise be used, as retpolines can significantly
impact performance.

The concept and code are an extension of previous work done by Ard
Biesheuvel and Steven Rostedt:

  https://lkml.kernel.org/r/20181005081333.15018-1-ard.biesheuvel@linaro.org
  https://lkml.kernel.org/r/20181006015110.653946300@goodmis.org

There are two implementations, depending on arch support:

 1) out-of-line: patched trampolines (CONFIG_HAVE_STATIC_CALL)
 2) basic function pointers

For more details, see the comments in include/linux/static_call.h.

[peterz: simplified interface]

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20200818135804.623259796@infradead.org
---
 arch/Kconfig                      |   3 +
 include/linux/static_call.h       | 156 ++++++++++++++++++++++++++++++++++++++
 include/linux/static_call_types.h |  15 ++++
 3 files changed, 174 insertions(+)
 create mode 100644 include/linux/static_call.h
 create mode 100644 include/linux/static_call_types.h

(limited to 'include/linux')

diff --git a/arch/Kconfig b/arch/Kconfig
index af14a567b493..806e6df7b47c 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -975,6 +975,9 @@ config HAVE_SPARSE_SYSCALL_NR
 config ARCH_HAS_VDSO_DATA
 	bool
 
+config HAVE_STATIC_CALL
+	bool
+
 source "kernel/gcov/Kconfig"
 
 source "scripts/gcc-plugins/Kconfig"
diff --git a/include/linux/static_call.h b/include/linux/static_call.h
new file mode 100644
index 000000000000..d8892dff2e91
--- /dev/null
+++ b/include/linux/static_call.h
@@ -0,0 +1,156 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_STATIC_CALL_H
+#define _LINUX_STATIC_CALL_H
+
+/*
+ * Static call support
+ *
+ * Static calls use code patching to hard-code function pointers into direct
+ * branch instructions. They give the flexibility of function pointers, but
+ * with improved performance. This is especially important for cases where
+ * retpolines would otherwise be used, as retpolines can significantly impact
+ * performance.
+ *
+ *
+ * API overview:
+ *
+ *   DECLARE_STATIC_CALL(name, func);
+ *   DEFINE_STATIC_CALL(name, func);
+ *   static_call(name)(args...);
+ *   static_call_update(name, func);
+ *
+ * Usage example:
+ *
+ *   # Start with the following functions (with identical prototypes):
+ *   int func_a(int arg1, int arg2);
+ *   int func_b(int arg1, int arg2);
+ *
+ *   # Define a 'my_name' reference, associated with func_a() by default
+ *   DEFINE_STATIC_CALL(my_name, func_a);
+ *
+ *   # Call func_a()
+ *   static_call(my_name)(arg1, arg2);
+ *
+ *   # Update 'my_name' to point to func_b()
+ *   static_call_update(my_name, &func_b);
+ *
+ *   # Call func_b()
+ *   static_call(my_name)(arg1, arg2);
+ *
+ *
+ * Implementation details:
+ *
+ *   This requires some arch-specific code (CONFIG_HAVE_STATIC_CALL).
+ *   Otherwise basic indirect calls are used (with function pointers).
+ *
+ *   Each static_call() site calls into a trampoline associated with the name.
+ *   The trampoline has a direct branch to the default function.  Updates to a
+ *   name will modify the trampoline's branch destination.
+ *
+ *   If the arch has CONFIG_HAVE_STATIC_CALL_INLINE, then the call sites
+ *   themselves will be patched at runtime to call the functions directly,
+ *   rather than calling through the trampoline.  This requires objtool or a
+ *   compiler plugin to detect all the static_call() sites and annotate them
+ *   in the .static_call_sites section.
+ */
+
+#include <linux/types.h>
+#include <linux/cpu.h>
+#include <linux/static_call_types.h>
+
+#ifdef CONFIG_HAVE_STATIC_CALL
+#include <asm/static_call.h>
+
+/*
+ * Either @site or @tramp can be NULL.
+ */
+extern void arch_static_call_transform(void *site, void *tramp, void *func);
+
+#define STATIC_CALL_TRAMP_ADDR(name) &STATIC_CALL_TRAMP(name)
+
+/*
+ * __ADDRESSABLE() is used to ensure the key symbol doesn't get stripped from
+ * the symbol table so that objtool can reference it when it generates the
+ * .static_call_sites section.
+ */
+#define __static_call(name)						\
+({									\
+	__ADDRESSABLE(STATIC_CALL_KEY(name));				\
+	&STATIC_CALL_TRAMP(name);					\
+})
+
+#else
+#define STATIC_CALL_TRAMP_ADDR(name) NULL
+#endif
+
+
+#define DECLARE_STATIC_CALL(name, func)					\
+	extern struct static_call_key STATIC_CALL_KEY(name);		\
+	extern typeof(func) STATIC_CALL_TRAMP(name);
+
+#define static_call_update(name, func)					\
+({									\
+	BUILD_BUG_ON(!__same_type(*(func), STATIC_CALL_TRAMP(name)));	\
+	__static_call_update(&STATIC_CALL_KEY(name),			\
+			     STATIC_CALL_TRAMP_ADDR(name), func);	\
+})
+
+#if defined(CONFIG_HAVE_STATIC_CALL)
+
+struct static_call_key {
+	void *func;
+};
+
+#define DEFINE_STATIC_CALL(name, _func)					\
+	DECLARE_STATIC_CALL(name, _func);				\
+	struct static_call_key STATIC_CALL_KEY(name) = {		\
+		.func = _func,						\
+	};								\
+	ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func)
+
+#define static_call(name)	__static_call(name)
+
+static inline
+void __static_call_update(struct static_call_key *key, void *tramp, void *func)
+{
+	cpus_read_lock();
+	WRITE_ONCE(key->func, func);
+	arch_static_call_transform(NULL, tramp, func);
+	cpus_read_unlock();
+}
+
+#define EXPORT_STATIC_CALL(name)					\
+	EXPORT_SYMBOL(STATIC_CALL_KEY(name));				\
+	EXPORT_SYMBOL(STATIC_CALL_TRAMP(name))
+
+#define EXPORT_STATIC_CALL_GPL(name)					\
+	EXPORT_SYMBOL_GPL(STATIC_CALL_KEY(name));			\
+	EXPORT_SYMBOL_GPL(STATIC_CALL_TRAMP(name))
+
+#else /* Generic implementation */
+
+struct static_call_key {
+	void *func;
+};
+
+#define DEFINE_STATIC_CALL(name, _func)					\
+	DECLARE_STATIC_CALL(name, _func);				\
+	struct static_call_key STATIC_CALL_KEY(name) = {		\
+		.func = _func,						\
+	}
+
+#define static_call(name)						\
+	((typeof(STATIC_CALL_TRAMP(name))*)(STATIC_CALL_KEY(name).func))
+
+static inline
+void __static_call_update(struct static_call_key *key, void *tramp, void *func)
+{
+	WRITE_ONCE(key->func, func);
+}
+
+#define EXPORT_STATIC_CALL(name)	EXPORT_SYMBOL(STATIC_CALL_KEY(name))
+#define EXPORT_STATIC_CALL_GPL(name)	EXPORT_SYMBOL_GPL(STATIC_CALL_KEY(name))
+
+#endif /* CONFIG_HAVE_STATIC_CALL */
+
+#endif /* _LINUX_STATIC_CALL_H */
diff --git a/include/linux/static_call_types.h b/include/linux/static_call_types.h
new file mode 100644
index 000000000000..5ed249dc47d3
--- /dev/null
+++ b/include/linux/static_call_types.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _STATIC_CALL_TYPES_H
+#define _STATIC_CALL_TYPES_H
+
+#include <linux/stringify.h>
+
+#define STATIC_CALL_KEY_PREFIX		__SCK__
+#define STATIC_CALL_KEY(name)		__PASTE(STATIC_CALL_KEY_PREFIX, name)
+
+#define STATIC_CALL_TRAMP_PREFIX	__SCT__
+#define STATIC_CALL_TRAMP_PREFIX_STR	__stringify(STATIC_CALL_TRAMP_PREFIX)
+#define STATIC_CALL_TRAMP(name)		__PASTE(STATIC_CALL_TRAMP_PREFIX, name)
+#define STATIC_CALL_TRAMP_STR(name)	__stringify(STATIC_CALL_TRAMP(name))
+
+#endif /* _STATIC_CALL_TYPES_H */
-- 
cgit v1.2.3


From 9183c3f9ed710a8edf1a61e8a96d497258d26e08 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Tue, 18 Aug 2020 15:57:42 +0200
Subject: static_call: Add inline static call infrastructure

Add infrastructure for an arch-specific CONFIG_HAVE_STATIC_CALL_INLINE
option, which is a faster version of CONFIG_HAVE_STATIC_CALL.  At
runtime, the static call sites are patched directly, rather than using
the out-of-line trampolines.

Compared to out-of-line static calls, the performance benefits are more
modest, but still measurable.  Steven Rostedt did some tracepoint
measurements:

  https://lkml.kernel.org/r/20181126155405.72b4f718@gandalf.local.home

This code is heavily inspired by the jump label code (aka "static
jumps"), as some of the concepts are very similar.

For more details, see the comments in include/linux/static_call.h.

[peterz: simplified interface; merged trampolines]

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20200818135804.684334440@infradead.org
---
 arch/Kconfig                      |   4 +
 include/asm-generic/vmlinux.lds.h |   7 +
 include/linux/module.h            |   5 +
 include/linux/static_call.h       |  36 ++++-
 include/linux/static_call_types.h |  13 ++
 kernel/Makefile                   |   1 +
 kernel/module.c                   |   5 +
 kernel/static_call.c              | 303 ++++++++++++++++++++++++++++++++++++++
 8 files changed, 373 insertions(+), 1 deletion(-)
 create mode 100644 kernel/static_call.c

(limited to 'include/linux')

diff --git a/arch/Kconfig b/arch/Kconfig
index 806e6df7b47c..2c4936ac620a 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -978,6 +978,10 @@ config ARCH_HAS_VDSO_DATA
 config HAVE_STATIC_CALL
 	bool
 
+config HAVE_STATIC_CALL_INLINE
+	bool
+	depends on HAVE_STATIC_CALL
+
 source "kernel/gcov/Kconfig"
 
 source "scripts/gcc-plugins/Kconfig"
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 5430febd34be..0088a5cd6a40 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -388,6 +388,12 @@
 	KEEP(*(__jump_table))						\
 	__stop___jump_table = .;
 
+#define STATIC_CALL_DATA						\
+	. = ALIGN(8);							\
+	__start_static_call_sites = .;					\
+	KEEP(*(.static_call_sites))					\
+	__stop_static_call_sites = .;
+
 /*
  * Allow architectures to handle ro_after_init data on their
  * own by defining an empty RO_AFTER_INIT_DATA.
@@ -398,6 +404,7 @@
 	__start_ro_after_init = .;					\
 	*(.data..ro_after_init)						\
 	JUMP_TABLE_DATA							\
+	STATIC_CALL_DATA						\
 	__end_ro_after_init = .;
 #endif
 
diff --git a/include/linux/module.h b/include/linux/module.h
index e30ed5fa33a7..a29187f7c360 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -25,6 +25,7 @@
 #include <linux/error-injection.h>
 #include <linux/tracepoint-defs.h>
 #include <linux/srcu.h>
+#include <linux/static_call_types.h>
 
 #include <linux/percpu.h>
 #include <asm/module.h>
@@ -498,6 +499,10 @@ struct module {
 	unsigned long *kprobe_blacklist;
 	unsigned int num_kprobe_blacklist;
 #endif
+#ifdef CONFIG_HAVE_STATIC_CALL_INLINE
+	int num_static_call_sites;
+	struct static_call_site *static_call_sites;
+#endif
 
 #ifdef CONFIG_LIVEPATCH
 	bool klp; /* Is this a livepatch module? */
diff --git a/include/linux/static_call.h b/include/linux/static_call.h
index d8892dff2e91..0d7f9efaa3b2 100644
--- a/include/linux/static_call.h
+++ b/include/linux/static_call.h
@@ -95,7 +95,41 @@ extern void arch_static_call_transform(void *site, void *tramp, void *func);
 			     STATIC_CALL_TRAMP_ADDR(name), func);	\
 })
 
-#if defined(CONFIG_HAVE_STATIC_CALL)
+#ifdef CONFIG_HAVE_STATIC_CALL_INLINE
+
+struct static_call_mod {
+	struct static_call_mod *next;
+	struct module *mod; /* for vmlinux, mod == NULL */
+	struct static_call_site *sites;
+};
+
+struct static_call_key {
+	void *func;
+	struct static_call_mod *mods;
+};
+
+extern void __static_call_update(struct static_call_key *key, void *tramp, void *func);
+extern int static_call_mod_init(struct module *mod);
+
+#define DEFINE_STATIC_CALL(name, _func)					\
+	DECLARE_STATIC_CALL(name, _func);				\
+	struct static_call_key STATIC_CALL_KEY(name) = {		\
+		.func = _func,						\
+		.mods = NULL,						\
+	};								\
+	ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func)
+
+#define static_call(name)	__static_call(name)
+
+#define EXPORT_STATIC_CALL(name)					\
+	EXPORT_SYMBOL(STATIC_CALL_KEY(name));				\
+	EXPORT_SYMBOL(STATIC_CALL_TRAMP(name))
+
+#define EXPORT_STATIC_CALL_GPL(name)					\
+	EXPORT_SYMBOL_GPL(STATIC_CALL_KEY(name));			\
+	EXPORT_SYMBOL_GPL(STATIC_CALL_TRAMP(name))
+
+#elif defined(CONFIG_HAVE_STATIC_CALL)
 
 struct static_call_key {
 	void *func;
diff --git a/include/linux/static_call_types.h b/include/linux/static_call_types.h
index 5ed249dc47d3..408d345d83e1 100644
--- a/include/linux/static_call_types.h
+++ b/include/linux/static_call_types.h
@@ -2,14 +2,27 @@
 #ifndef _STATIC_CALL_TYPES_H
 #define _STATIC_CALL_TYPES_H
 
+#include <linux/types.h>
 #include <linux/stringify.h>
 
 #define STATIC_CALL_KEY_PREFIX		__SCK__
+#define STATIC_CALL_KEY_PREFIX_STR	__stringify(STATIC_CALL_KEY_PREFIX)
+#define STATIC_CALL_KEY_PREFIX_LEN	(sizeof(STATIC_CALL_KEY_PREFIX_STR) - 1)
 #define STATIC_CALL_KEY(name)		__PASTE(STATIC_CALL_KEY_PREFIX, name)
 
 #define STATIC_CALL_TRAMP_PREFIX	__SCT__
 #define STATIC_CALL_TRAMP_PREFIX_STR	__stringify(STATIC_CALL_TRAMP_PREFIX)
+#define STATIC_CALL_TRAMP_PREFIX_LEN	(sizeof(STATIC_CALL_TRAMP_PREFIX_STR) - 1)
 #define STATIC_CALL_TRAMP(name)		__PASTE(STATIC_CALL_TRAMP_PREFIX, name)
 #define STATIC_CALL_TRAMP_STR(name)	__stringify(STATIC_CALL_TRAMP(name))
 
+/*
+ * The static call site table needs to be created by external tooling (objtool
+ * or a compiler plugin).
+ */
+struct static_call_site {
+	s32 addr;
+	s32 key;
+};
+
 #endif /* _STATIC_CALL_TYPES_H */
diff --git a/kernel/Makefile b/kernel/Makefile
index 9a20016d4900..b74820d8b264 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -111,6 +111,7 @@ obj-$(CONFIG_CPU_PM) += cpu_pm.o
 obj-$(CONFIG_BPF) += bpf/
 obj-$(CONFIG_KCSAN) += kcsan/
 obj-$(CONFIG_SHADOW_CALL_STACK) += scs.o
+obj-$(CONFIG_HAVE_STATIC_CALL_INLINE) += static_call.o
 
 obj-$(CONFIG_PERF_EVENTS) += events/
 
diff --git a/kernel/module.c b/kernel/module.c
index 3c465cf31d08..c075a18103fb 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -3274,6 +3274,11 @@ static int find_module_sections(struct module *mod, struct load_info *info)
 	mod->kprobe_blacklist = section_objs(info, "_kprobe_blacklist",
 						sizeof(unsigned long),
 						&mod->num_kprobe_blacklist);
+#endif
+#ifdef CONFIG_HAVE_STATIC_CALL_INLINE
+	mod->static_call_sites = section_objs(info, ".static_call_sites",
+					      sizeof(*mod->static_call_sites),
+					      &mod->num_static_call_sites);
 #endif
 	mod->extable = section_objs(info, "__ex_table",
 				    sizeof(*mod->extable), &mod->num_exentries);
diff --git a/kernel/static_call.c b/kernel/static_call.c
new file mode 100644
index 000000000000..d24349244675
--- /dev/null
+++ b/kernel/static_call.c
@@ -0,0 +1,303 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/init.h>
+#include <linux/static_call.h>
+#include <linux/bug.h>
+#include <linux/smp.h>
+#include <linux/sort.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/cpu.h>
+#include <linux/processor.h>
+#include <asm/sections.h>
+
+extern struct static_call_site __start_static_call_sites[],
+			       __stop_static_call_sites[];
+
+static bool static_call_initialized;
+
+#define STATIC_CALL_INIT 1UL
+
+/* mutex to protect key modules/sites */
+static DEFINE_MUTEX(static_call_mutex);
+
+static void static_call_lock(void)
+{
+	mutex_lock(&static_call_mutex);
+}
+
+static void static_call_unlock(void)
+{
+	mutex_unlock(&static_call_mutex);
+}
+
+static inline void *static_call_addr(struct static_call_site *site)
+{
+	return (void *)((long)site->addr + (long)&site->addr);
+}
+
+
+static inline struct static_call_key *static_call_key(const struct static_call_site *site)
+{
+	return (struct static_call_key *)
+		(((long)site->key + (long)&site->key) & ~STATIC_CALL_INIT);
+}
+
+/* These assume the key is word-aligned. */
+static inline bool static_call_is_init(struct static_call_site *site)
+{
+	return ((long)site->key + (long)&site->key) & STATIC_CALL_INIT;
+}
+
+static inline void static_call_set_init(struct static_call_site *site)
+{
+	site->key = ((long)static_call_key(site) | STATIC_CALL_INIT) -
+		    (long)&site->key;
+}
+
+static int static_call_site_cmp(const void *_a, const void *_b)
+{
+	const struct static_call_site *a = _a;
+	const struct static_call_site *b = _b;
+	const struct static_call_key *key_a = static_call_key(a);
+	const struct static_call_key *key_b = static_call_key(b);
+
+	if (key_a < key_b)
+		return -1;
+
+	if (key_a > key_b)
+		return 1;
+
+	return 0;
+}
+
+static void static_call_site_swap(void *_a, void *_b, int size)
+{
+	long delta = (unsigned long)_a - (unsigned long)_b;
+	struct static_call_site *a = _a;
+	struct static_call_site *b = _b;
+	struct static_call_site tmp = *a;
+
+	a->addr = b->addr  - delta;
+	a->key  = b->key   - delta;
+
+	b->addr = tmp.addr + delta;
+	b->key  = tmp.key  + delta;
+}
+
+static inline void static_call_sort_entries(struct static_call_site *start,
+					    struct static_call_site *stop)
+{
+	sort(start, stop - start, sizeof(struct static_call_site),
+	     static_call_site_cmp, static_call_site_swap);
+}
+
+void __static_call_update(struct static_call_key *key, void *tramp, void *func)
+{
+	struct static_call_site *site, *stop;
+	struct static_call_mod *site_mod;
+
+	cpus_read_lock();
+	static_call_lock();
+
+	if (key->func == func)
+		goto done;
+
+	key->func = func;
+
+	arch_static_call_transform(NULL, tramp, func);
+
+	/*
+	 * If uninitialized, we'll not update the callsites, but they still
+	 * point to the trampoline and we just patched that.
+	 */
+	if (WARN_ON_ONCE(!static_call_initialized))
+		goto done;
+
+	for (site_mod = key->mods; site_mod; site_mod = site_mod->next) {
+		struct module *mod = site_mod->mod;
+
+		if (!site_mod->sites) {
+			/*
+			 * This can happen if the static call key is defined in
+			 * a module which doesn't use it.
+			 */
+			continue;
+		}
+
+		stop = __stop_static_call_sites;
+
+#ifdef CONFIG_MODULES
+		if (mod) {
+			stop = mod->static_call_sites +
+			       mod->num_static_call_sites;
+		}
+#endif
+
+		for (site = site_mod->sites;
+		     site < stop && static_call_key(site) == key; site++) {
+			void *site_addr = static_call_addr(site);
+
+			if (static_call_is_init(site)) {
+				/*
+				 * Don't write to call sites which were in
+				 * initmem and have since been freed.
+				 */
+				if (!mod && system_state >= SYSTEM_RUNNING)
+					continue;
+				if (mod && !within_module_init((unsigned long)site_addr, mod))
+					continue;
+			}
+
+			if (!kernel_text_address((unsigned long)site_addr)) {
+				WARN_ONCE(1, "can't patch static call site at %pS",
+					  site_addr);
+				continue;
+			}
+
+			arch_static_call_transform(site_addr, NULL, func);
+		}
+	}
+
+done:
+	static_call_unlock();
+	cpus_read_unlock();
+}
+EXPORT_SYMBOL_GPL(__static_call_update);
+
+static int __static_call_init(struct module *mod,
+			      struct static_call_site *start,
+			      struct static_call_site *stop)
+{
+	struct static_call_site *site;
+	struct static_call_key *key, *prev_key = NULL;
+	struct static_call_mod *site_mod;
+
+	if (start == stop)
+		return 0;
+
+	static_call_sort_entries(start, stop);
+
+	for (site = start; site < stop; site++) {
+		void *site_addr = static_call_addr(site);
+
+		if ((mod && within_module_init((unsigned long)site_addr, mod)) ||
+		    (!mod && init_section_contains(site_addr, 1)))
+			static_call_set_init(site);
+
+		key = static_call_key(site);
+		if (key != prev_key) {
+			prev_key = key;
+
+			site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL);
+			if (!site_mod)
+				return -ENOMEM;
+
+			site_mod->mod = mod;
+			site_mod->sites = site;
+			site_mod->next = key->mods;
+			key->mods = site_mod;
+		}
+
+		arch_static_call_transform(site_addr, NULL, key->func);
+	}
+
+	return 0;
+}
+
+#ifdef CONFIG_MODULES
+
+static int static_call_add_module(struct module *mod)
+{
+	return __static_call_init(mod, mod->static_call_sites,
+				  mod->static_call_sites + mod->num_static_call_sites);
+}
+
+static void static_call_del_module(struct module *mod)
+{
+	struct static_call_site *start = mod->static_call_sites;
+	struct static_call_site *stop = mod->static_call_sites +
+					mod->num_static_call_sites;
+	struct static_call_key *key, *prev_key = NULL;
+	struct static_call_mod *site_mod, **prev;
+	struct static_call_site *site;
+
+	for (site = start; site < stop; site++) {
+		key = static_call_key(site);
+		if (key == prev_key)
+			continue;
+
+		prev_key = key;
+
+		for (prev = &key->mods, site_mod = key->mods;
+		     site_mod && site_mod->mod != mod;
+		     prev = &site_mod->next, site_mod = site_mod->next)
+			;
+
+		if (!site_mod)
+			continue;
+
+		*prev = site_mod->next;
+		kfree(site_mod);
+	}
+}
+
+static int static_call_module_notify(struct notifier_block *nb,
+				     unsigned long val, void *data)
+{
+	struct module *mod = data;
+	int ret = 0;
+
+	cpus_read_lock();
+	static_call_lock();
+
+	switch (val) {
+	case MODULE_STATE_COMING:
+		ret = static_call_add_module(mod);
+		if (ret) {
+			WARN(1, "Failed to allocate memory for static calls");
+			static_call_del_module(mod);
+		}
+		break;
+	case MODULE_STATE_GOING:
+		static_call_del_module(mod);
+		break;
+	}
+
+	static_call_unlock();
+	cpus_read_unlock();
+
+	return notifier_from_errno(ret);
+}
+
+static struct notifier_block static_call_module_nb = {
+	.notifier_call = static_call_module_notify,
+};
+
+#endif /* CONFIG_MODULES */
+
+static void __init static_call_init(void)
+{
+	int ret;
+
+	if (static_call_initialized)
+		return;
+
+	cpus_read_lock();
+	static_call_lock();
+	ret = __static_call_init(NULL, __start_static_call_sites,
+				 __stop_static_call_sites);
+	static_call_unlock();
+	cpus_read_unlock();
+
+	if (ret) {
+		pr_err("Failed to allocate memory for static_call!\n");
+		BUG();
+	}
+
+	static_call_initialized = true;
+
+#ifdef CONFIG_MODULES
+	register_module_notifier(&static_call_module_nb);
+#endif
+}
+early_initcall(static_call_init);
-- 
cgit v1.2.3


From 6333e8f73b834f54e395a056e6002403f0862c51 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 18 Aug 2020 15:57:43 +0200
Subject: static_call: Avoid kprobes on inline static_call()s

Similar to how we disallow kprobes on any other dynamic text
(ftrace/jump_label) also disallow kprobes on inline static_call()s.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20200818135804.744920586@infradead.org
---
 arch/x86/kernel/kprobes/opt.c |  4 ++-
 include/linux/static_call.h   | 11 +++++++
 kernel/kprobes.c              |  2 ++
 kernel/static_call.c          | 68 +++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 84 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 40f380461e6d..c068e21c2c40 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -18,6 +18,7 @@
 #include <linux/ftrace.h>
 #include <linux/frame.h>
 #include <linux/pgtable.h>
+#include <linux/static_call.h>
 
 #include <asm/text-patching.h>
 #include <asm/cacheflush.h>
@@ -210,7 +211,8 @@ static int copy_optimized_instructions(u8 *dest, u8 *src, u8 *real)
 	/* Check whether the address range is reserved */
 	if (ftrace_text_reserved(src, src + len - 1) ||
 	    alternatives_text_reserved(src, src + len - 1) ||
-	    jump_label_text_reserved(src, src + len - 1))
+	    jump_label_text_reserved(src, src + len - 1) ||
+	    static_call_text_reserved(src, src + len - 1))
 		return -EBUSY;
 
 	return len;
diff --git a/include/linux/static_call.h b/include/linux/static_call.h
index 0d7f9efaa3b2..6f62ceda7dd9 100644
--- a/include/linux/static_call.h
+++ b/include/linux/static_call.h
@@ -110,6 +110,7 @@ struct static_call_key {
 
 extern void __static_call_update(struct static_call_key *key, void *tramp, void *func);
 extern int static_call_mod_init(struct module *mod);
+extern int static_call_text_reserved(void *start, void *end);
 
 #define DEFINE_STATIC_CALL(name, _func)					\
 	DECLARE_STATIC_CALL(name, _func);				\
@@ -153,6 +154,11 @@ void __static_call_update(struct static_call_key *key, void *tramp, void *func)
 	cpus_read_unlock();
 }
 
+static inline int static_call_text_reserved(void *start, void *end)
+{
+	return 0;
+}
+
 #define EXPORT_STATIC_CALL(name)					\
 	EXPORT_SYMBOL(STATIC_CALL_KEY(name));				\
 	EXPORT_SYMBOL(STATIC_CALL_TRAMP(name))
@@ -182,6 +188,11 @@ void __static_call_update(struct static_call_key *key, void *tramp, void *func)
 	WRITE_ONCE(key->func, func);
 }
 
+static inline int static_call_text_reserved(void *start, void *end)
+{
+	return 0;
+}
+
 #define EXPORT_STATIC_CALL(name)	EXPORT_SYMBOL(STATIC_CALL_KEY(name))
 #define EXPORT_STATIC_CALL_GPL(name)	EXPORT_SYMBOL_GPL(STATIC_CALL_KEY(name))
 
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 287b263c9cb9..67e6a8c18007 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -36,6 +36,7 @@
 #include <linux/cpu.h>
 #include <linux/jump_label.h>
 #include <linux/perf_event.h>
+#include <linux/static_call.h>
 
 #include <asm/sections.h>
 #include <asm/cacheflush.h>
@@ -1634,6 +1635,7 @@ static int check_kprobe_address_safe(struct kprobe *p,
 	if (!kernel_text_address((unsigned long) p->addr) ||
 	    within_kprobe_blacklist((unsigned long) p->addr) ||
 	    jump_label_text_reserved(p->addr, p->addr) ||
+	    static_call_text_reserved(p->addr, p->addr) ||
 	    find_bug((unsigned long)p->addr)) {
 		ret = -EINVAL;
 		goto out;
diff --git a/kernel/static_call.c b/kernel/static_call.c
index d24349244675..753b2f1b4fb8 100644
--- a/kernel/static_call.c
+++ b/kernel/static_call.c
@@ -204,8 +204,58 @@ static int __static_call_init(struct module *mod,
 	return 0;
 }
 
+static int addr_conflict(struct static_call_site *site, void *start, void *end)
+{
+	unsigned long addr = (unsigned long)static_call_addr(site);
+
+	if (addr <= (unsigned long)end &&
+	    addr + CALL_INSN_SIZE > (unsigned long)start)
+		return 1;
+
+	return 0;
+}
+
+static int __static_call_text_reserved(struct static_call_site *iter_start,
+				       struct static_call_site *iter_stop,
+				       void *start, void *end)
+{
+	struct static_call_site *iter = iter_start;
+
+	while (iter < iter_stop) {
+		if (addr_conflict(iter, start, end))
+			return 1;
+		iter++;
+	}
+
+	return 0;
+}
+
 #ifdef CONFIG_MODULES
 
+static int __static_call_mod_text_reserved(void *start, void *end)
+{
+	struct module *mod;
+	int ret;
+
+	preempt_disable();
+	mod = __module_text_address((unsigned long)start);
+	WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod);
+	if (!try_module_get(mod))
+		mod = NULL;
+	preempt_enable();
+
+	if (!mod)
+		return 0;
+
+	ret = __static_call_text_reserved(mod->static_call_sites,
+			mod->static_call_sites + mod->num_static_call_sites,
+			start, end);
+
+	module_put(mod);
+
+	return ret;
+}
+
 static int static_call_add_module(struct module *mod)
 {
 	return __static_call_init(mod, mod->static_call_sites,
@@ -273,8 +323,26 @@ static struct notifier_block static_call_module_nb = {
 	.notifier_call = static_call_module_notify,
 };
 
+#else
+
+static inline int __static_call_mod_text_reserved(void *start, void *end)
+{
+	return 0;
+}
+
 #endif /* CONFIG_MODULES */
 
+int static_call_text_reserved(void *start, void *end)
+{
+	int ret = __static_call_text_reserved(__start_static_call_sites,
+			__stop_static_call_sites, start, end);
+
+	if (ret)
+		return ret;
+
+	return __static_call_mod_text_reserved(start, end);
+}
+
 static void __init static_call_init(void)
 {
 	int ret;
-- 
cgit v1.2.3


From 452cddbff74b6a15b9354505671011700fe03710 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 18 Aug 2020 15:57:48 +0200
Subject: static_call: Add static_call_cond()

Extend the static_call infrastructure to optimize the following common
pattern:

	if (func_ptr)
		func_ptr(args...)

For the trampoline (which is in effect a tail-call), we patch the
JMP.d32 into a RET, which then directly consumes the trampoline call.

For the in-line sites we replace the CALL with a NOP5.

NOTE: this is 'obviously' limited to functions with a 'void' return type.

NOTE: DEFINE_STATIC_COND_CALL() only requires a typename, as opposed
      to a full function.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20200818135805.042977182@infradead.org
---
 arch/x86/include/asm/static_call.h | 12 ++++--
 arch/x86/kernel/static_call.c      | 42 ++++++++++++++-----
 include/linux/static_call.h        | 86 ++++++++++++++++++++++++++++++++++++++
 3 files changed, 127 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h
index 33469ae3612c..c37f11999d0c 100644
--- a/arch/x86/include/asm/static_call.h
+++ b/arch/x86/include/asm/static_call.h
@@ -20,15 +20,21 @@
  * it does tail-call optimization on the call; since you cannot compute the
  * relative displacement across sections.
  */
-#define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func)			\
+
+#define __ARCH_DEFINE_STATIC_CALL_TRAMP(name, insns)			\
 	asm(".pushsection .static_call.text, \"ax\"		\n"	\
 	    ".align 4						\n"	\
 	    ".globl " STATIC_CALL_TRAMP_STR(name) "		\n"	\
 	    STATIC_CALL_TRAMP_STR(name) ":			\n"	\
-	    "	.byte 0xe9 # jmp.d32				\n"	\
-	    "	.long " #func " - (. + 4)			\n"	\
+	    insns "						\n"	\
 	    ".type " STATIC_CALL_TRAMP_STR(name) ", @function	\n"	\
 	    ".size " STATIC_CALL_TRAMP_STR(name) ", . - " STATIC_CALL_TRAMP_STR(name) " \n" \
 	    ".popsection					\n")
 
+#define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func)			\
+	__ARCH_DEFINE_STATIC_CALL_TRAMP(name, ".byte 0xe9; .long " #func " - (. + 4)")
+
+#define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)			\
+	__ARCH_DEFINE_STATIC_CALL_TRAMP(name, "ret; nop; nop; nop; nop")
+
 #endif /* _ASM_STATIC_CALL_H */
diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
index 5ff2b639a1a6..ead6726fb06d 100644
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -4,19 +4,41 @@
 #include <linux/bug.h>
 #include <asm/text-patching.h>
 
-static void __static_call_transform(void *insn, u8 opcode, void *func)
+enum insn_type {
+	CALL = 0, /* site call */
+	NOP = 1,  /* site cond-call */
+	JMP = 2,  /* tramp / site tail-call */
+	RET = 3,  /* tramp / site cond-tail-call */
+};
+
+static void __static_call_transform(void *insn, enum insn_type type, void *func)
 {
-	const void *code = text_gen_insn(opcode, insn, func);
+	int size = CALL_INSN_SIZE;
+	const void *code;
 
-	if (WARN_ONCE(*(u8 *)insn != opcode,
-		      "unexpected static call insn opcode 0x%x at %pS\n",
-		      opcode, insn))
-		return;
+	switch (type) {
+	case CALL:
+		code = text_gen_insn(CALL_INSN_OPCODE, insn, func);
+		break;
+
+	case NOP:
+		code = ideal_nops[NOP_ATOMIC5];
+		break;
+
+	case JMP:
+		code = text_gen_insn(JMP32_INSN_OPCODE, insn, func);
+		break;
+
+	case RET:
+		code = text_gen_insn(RET_INSN_OPCODE, insn, func);
+		size = RET_INSN_SIZE;
+		break;
+	}
 
-	if (memcmp(insn, code, CALL_INSN_SIZE) == 0)
+	if (memcmp(insn, code, size) == 0)
 		return;
 
-	text_poke_bp(insn, code, CALL_INSN_SIZE, NULL);
+	text_poke_bp(insn, code, size, NULL);
 }
 
 void arch_static_call_transform(void *site, void *tramp, void *func)
@@ -24,10 +46,10 @@ void arch_static_call_transform(void *site, void *tramp, void *func)
 	mutex_lock(&text_mutex);
 
 	if (tramp)
-		__static_call_transform(tramp, JMP32_INSN_OPCODE, func);
+		__static_call_transform(tramp, func ? JMP : RET, func);
 
 	if (IS_ENABLED(CONFIG_HAVE_STATIC_CALL_INLINE) && site)
-		__static_call_transform(site, CALL_INSN_OPCODE, func);
+		__static_call_transform(site, func ? CALL : NOP, func);
 
 	mutex_unlock(&text_mutex);
 }
diff --git a/include/linux/static_call.h b/include/linux/static_call.h
index 6f62ceda7dd9..0f74581e0e2f 100644
--- a/include/linux/static_call.h
+++ b/include/linux/static_call.h
@@ -16,7 +16,9 @@
  *
  *   DECLARE_STATIC_CALL(name, func);
  *   DEFINE_STATIC_CALL(name, func);
+ *   DEFINE_STATIC_CALL_NULL(name, typename);
  *   static_call(name)(args...);
+ *   static_call_cond(name)(args...);
  *   static_call_update(name, func);
  *
  * Usage example:
@@ -52,6 +54,43 @@
  *   rather than calling through the trampoline.  This requires objtool or a
  *   compiler plugin to detect all the static_call() sites and annotate them
  *   in the .static_call_sites section.
+ *
+ *
+ * Notes on NULL function pointers:
+ *
+ *   Static_call()s support NULL functions, with many of the caveats that
+ *   regular function pointers have.
+ *
+ *   Clearly calling a NULL function pointer is 'BAD', so too for
+ *   static_call()s (although when HAVE_STATIC_CALL it might not be immediately
+ *   fatal). A NULL static_call can be the result of:
+ *
+ *     DECLARE_STATIC_CALL_NULL(my_static_call, void (*)(int));
+ *
+ *   which is equivalent to declaring a NULL function pointer with just a
+ *   typename:
+ *
+ *     void (*my_func_ptr)(int arg1) = NULL;
+ *
+ *   or using static_call_update() with a NULL function. In both cases the
+ *   HAVE_STATIC_CALL implementation will patch the trampoline with a RET
+ *   instruction, instead of an immediate tail-call JMP. HAVE_STATIC_CALL_INLINE
+ *   architectures can patch the trampoline call to a NOP.
+ *
+ *   In all cases, any argument evaluation is unconditional. Unlike a regular
+ *   conditional function pointer call:
+ *
+ *     if (my_func_ptr)
+ *         my_func_ptr(arg1)
+ *
+ *   where the argument evaludation also depends on the pointer value.
+ *
+ *   When calling a static_call that can be NULL, use:
+ *
+ *     static_call_cond(name)(arg1);
+ *
+ *   which will include the required value tests to avoid NULL-pointer
+ *   dereferences.
  */
 
 #include <linux/types.h>
@@ -120,7 +159,16 @@ extern int static_call_text_reserved(void *start, void *end);
 	};								\
 	ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func)
 
+#define DEFINE_STATIC_CALL_NULL(name, _func)				\
+	DECLARE_STATIC_CALL(name, _func);				\
+	struct static_call_key STATIC_CALL_KEY(name) = {		\
+		.func = NULL,						\
+		.type = 1,						\
+	};								\
+	ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)
+
 #define static_call(name)	__static_call(name)
+#define static_call_cond(name)	(void)__static_call(name)
 
 #define EXPORT_STATIC_CALL(name)					\
 	EXPORT_SYMBOL(STATIC_CALL_KEY(name));				\
@@ -143,7 +191,15 @@ struct static_call_key {
 	};								\
 	ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func)
 
+#define DEFINE_STATIC_CALL_NULL(name, _func)				\
+	DECLARE_STATIC_CALL(name, _func);				\
+	struct static_call_key STATIC_CALL_KEY(name) = {		\
+		.func = NULL,						\
+	};								\
+	ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)
+
 #define static_call(name)	__static_call(name)
+#define static_call_cond(name)	(void)__static_call(name)
 
 static inline
 void __static_call_update(struct static_call_key *key, void *tramp, void *func)
@@ -179,9 +235,39 @@ struct static_call_key {
 		.func = _func,						\
 	}
 
+#define DEFINE_STATIC_CALL_NULL(name, _func)				\
+	DECLARE_STATIC_CALL(name, _func);				\
+	struct static_call_key STATIC_CALL_KEY(name) = {		\
+		.func = NULL,						\
+	}
+
 #define static_call(name)						\
 	((typeof(STATIC_CALL_TRAMP(name))*)(STATIC_CALL_KEY(name).func))
 
+static inline void __static_call_nop(void) { }
+
+/*
+ * This horrific hack takes care of two things:
+ *
+ *  - it ensures the compiler will only load the function pointer ONCE,
+ *    which avoids a reload race.
+ *
+ *  - it ensures the argument evaluation is unconditional, similar
+ *    to the HAVE_STATIC_CALL variant.
+ *
+ * Sadly current GCC/Clang (10 for both) do not optimize this properly
+ * and will emit an indirect call for the NULL case :-(
+ */
+#define __static_call_cond(name)					\
+({									\
+	void *func = READ_ONCE(STATIC_CALL_KEY(name).func);		\
+	if (!func)							\
+		func = &__static_call_nop;				\
+	(typeof(STATIC_CALL_TRAMP(name))*)func;				\
+})
+
+#define static_call_cond(name)	(void)__static_call_cond(name)
+
 static inline
 void __static_call_update(struct static_call_key *key, void *tramp, void *func)
 {
-- 
cgit v1.2.3


From 5b06fd3bb9cdce4f3e731c48eb5b74c4acc47997 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 18 Aug 2020 15:57:49 +0200
Subject: static_call: Handle tail-calls

GCC can turn our static_call(name)(args...) into a tail call, in which
case we get a JMP.d32 into the trampoline (which then does a further
tail-call).

Teach objtool to recognise and mark these in .static_call_sites and
adjust the code patching to deal with this.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20200818135805.101186767@infradead.org
---
 arch/x86/kernel/static_call.c           | 21 ++++++++++++++++++---
 include/linux/static_call.h             |  4 ++--
 include/linux/static_call_types.h       |  7 +++++++
 kernel/static_call.c                    | 21 +++++++++++++--------
 tools/include/linux/static_call_types.h |  7 +++++++
 tools/objtool/check.c                   | 18 +++++++++++++-----
 6 files changed, 60 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
index ead6726fb06d..60a325c731df 100644
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -41,15 +41,30 @@ static void __static_call_transform(void *insn, enum insn_type type, void *func)
 	text_poke_bp(insn, code, size, NULL);
 }
 
-void arch_static_call_transform(void *site, void *tramp, void *func)
+static inline enum insn_type __sc_insn(bool null, bool tail)
+{
+	/*
+	 * Encode the following table without branches:
+	 *
+	 *	tail	null	insn
+	 *	-----+-------+------
+	 *	  0  |   0   |  CALL
+	 *	  0  |   1   |  NOP
+	 *	  1  |   0   |  JMP
+	 *	  1  |   1   |  RET
+	 */
+	return 2*tail + null;
+}
+
+void arch_static_call_transform(void *site, void *tramp, void *func, bool tail)
 {
 	mutex_lock(&text_mutex);
 
 	if (tramp)
-		__static_call_transform(tramp, func ? JMP : RET, func);
+		__static_call_transform(tramp, __sc_insn(!func, true), func);
 
 	if (IS_ENABLED(CONFIG_HAVE_STATIC_CALL_INLINE) && site)
-		__static_call_transform(site, func ? CALL : NOP, func);
+		__static_call_transform(site, __sc_insn(!func, tail), func);
 
 	mutex_unlock(&text_mutex);
 }
diff --git a/include/linux/static_call.h b/include/linux/static_call.h
index 0f74581e0e2f..519bd666e096 100644
--- a/include/linux/static_call.h
+++ b/include/linux/static_call.h
@@ -103,7 +103,7 @@
 /*
  * Either @site or @tramp can be NULL.
  */
-extern void arch_static_call_transform(void *site, void *tramp, void *func);
+extern void arch_static_call_transform(void *site, void *tramp, void *func, bool tail);
 
 #define STATIC_CALL_TRAMP_ADDR(name) &STATIC_CALL_TRAMP(name)
 
@@ -206,7 +206,7 @@ void __static_call_update(struct static_call_key *key, void *tramp, void *func)
 {
 	cpus_read_lock();
 	WRITE_ONCE(key->func, func);
-	arch_static_call_transform(NULL, tramp, func);
+	arch_static_call_transform(NULL, tramp, func, false);
 	cpus_read_unlock();
 }
 
diff --git a/include/linux/static_call_types.h b/include/linux/static_call_types.h
index 408d345d83e1..89135bb35bf7 100644
--- a/include/linux/static_call_types.h
+++ b/include/linux/static_call_types.h
@@ -16,6 +16,13 @@
 #define STATIC_CALL_TRAMP(name)		__PASTE(STATIC_CALL_TRAMP_PREFIX, name)
 #define STATIC_CALL_TRAMP_STR(name)	__stringify(STATIC_CALL_TRAMP(name))
 
+/*
+ * Flags in the low bits of static_call_site::key.
+ */
+#define STATIC_CALL_SITE_TAIL 1UL	/* tail call */
+#define STATIC_CALL_SITE_INIT 2UL	/* init section */
+#define STATIC_CALL_SITE_FLAGS 3UL
+
 /*
  * The static call site table needs to be created by external tooling (objtool
  * or a compiler plugin).
diff --git a/kernel/static_call.c b/kernel/static_call.c
index 97142cb6bfa6..d98e0e4272c1 100644
--- a/kernel/static_call.c
+++ b/kernel/static_call.c
@@ -15,8 +15,6 @@ extern struct static_call_site __start_static_call_sites[],
 
 static bool static_call_initialized;
 
-#define STATIC_CALL_INIT 1UL
-
 /* mutex to protect key modules/sites */
 static DEFINE_MUTEX(static_call_mutex);
 
@@ -39,18 +37,23 @@ static inline void *static_call_addr(struct static_call_site *site)
 static inline struct static_call_key *static_call_key(const struct static_call_site *site)
 {
 	return (struct static_call_key *)
-		(((long)site->key + (long)&site->key) & ~STATIC_CALL_INIT);
+		(((long)site->key + (long)&site->key) & ~STATIC_CALL_SITE_FLAGS);
 }
 
 /* These assume the key is word-aligned. */
 static inline bool static_call_is_init(struct static_call_site *site)
 {
-	return ((long)site->key + (long)&site->key) & STATIC_CALL_INIT;
+	return ((long)site->key + (long)&site->key) & STATIC_CALL_SITE_INIT;
+}
+
+static inline bool static_call_is_tail(struct static_call_site *site)
+{
+	return ((long)site->key + (long)&site->key) & STATIC_CALL_SITE_TAIL;
 }
 
 static inline void static_call_set_init(struct static_call_site *site)
 {
-	site->key = ((long)static_call_key(site) | STATIC_CALL_INIT) -
+	site->key = ((long)static_call_key(site) | STATIC_CALL_SITE_INIT) -
 		    (long)&site->key;
 }
 
@@ -104,7 +107,7 @@ void __static_call_update(struct static_call_key *key, void *tramp, void *func)
 
 	key->func = func;
 
-	arch_static_call_transform(NULL, tramp, func);
+	arch_static_call_transform(NULL, tramp, func, false);
 
 	/*
 	 * If uninitialized, we'll not update the callsites, but they still
@@ -154,7 +157,8 @@ void __static_call_update(struct static_call_key *key, void *tramp, void *func)
 				continue;
 			}
 
-			arch_static_call_transform(site_addr, NULL, func);
+			arch_static_call_transform(site_addr, NULL, func,
+				static_call_is_tail(site));
 		}
 	}
 
@@ -198,7 +202,8 @@ static int __static_call_init(struct module *mod,
 			key->mods = site_mod;
 		}
 
-		arch_static_call_transform(site_addr, NULL, key->func);
+		arch_static_call_transform(site_addr, NULL, key->func,
+				static_call_is_tail(site));
 	}
 
 	return 0;
diff --git a/tools/include/linux/static_call_types.h b/tools/include/linux/static_call_types.h
index 408d345d83e1..89135bb35bf7 100644
--- a/tools/include/linux/static_call_types.h
+++ b/tools/include/linux/static_call_types.h
@@ -16,6 +16,13 @@
 #define STATIC_CALL_TRAMP(name)		__PASTE(STATIC_CALL_TRAMP_PREFIX, name)
 #define STATIC_CALL_TRAMP_STR(name)	__stringify(STATIC_CALL_TRAMP(name))
 
+/*
+ * Flags in the low bits of static_call_site::key.
+ */
+#define STATIC_CALL_SITE_TAIL 1UL	/* tail call */
+#define STATIC_CALL_SITE_INIT 2UL	/* init section */
+#define STATIC_CALL_SITE_FLAGS 3UL
+
 /*
  * The static call site table needs to be created by external tooling (objtool
  * or a compiler plugin).
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index f8f7a40c6ef3..75d0cd2f9044 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -516,7 +516,7 @@ static int create_static_call_sections(struct objtool_file *file)
 		}
 		memset(reloc, 0, sizeof(*reloc));
 		reloc->sym = key_sym;
-		reloc->addend = 0;
+		reloc->addend = is_sibling_call(insn) ? STATIC_CALL_SITE_TAIL : 0;
 		reloc->type = R_X86_64_PC32;
 		reloc->offset = idx * sizeof(struct static_call_site) + 4;
 		reloc->sec = reloc_sec;
@@ -747,6 +747,10 @@ static int add_jump_destinations(struct objtool_file *file)
 		} else {
 			/* external sibling call */
 			insn->call_dest = reloc->sym;
+			if (insn->call_dest->static_call_tramp) {
+				list_add_tail(&insn->static_call_node,
+					      &file->static_call_list);
+			}
 			continue;
 		}
 
@@ -798,6 +802,10 @@ static int add_jump_destinations(struct objtool_file *file)
 
 				/* internal sibling call */
 				insn->call_dest = insn->jump_dest->func;
+				if (insn->call_dest->static_call_tramp) {
+					list_add_tail(&insn->static_call_node,
+						      &file->static_call_list);
+				}
 			}
 		}
 	}
@@ -1684,6 +1692,10 @@ static int decode_sections(struct objtool_file *file)
 	if (ret)
 		return ret;
 
+	ret = read_static_call_tramps(file);
+	if (ret)
+		return ret;
+
 	ret = add_jump_destinations(file);
 	if (ret)
 		return ret;
@@ -1716,10 +1728,6 @@ static int decode_sections(struct objtool_file *file)
 	if (ret)
 		return ret;
 
-	ret = read_static_call_tramps(file);
-	if (ret)
-		return ret;
-
 	return 0;
 }
 
-- 
cgit v1.2.3


From a945c8345ec0decb2f1a7f19a8c5e60bcb1dd1eb Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 18 Aug 2020 15:57:51 +0200
Subject: static_call: Allow early init

In order to use static_call() to wire up x86_pmu, we need to
initialize earlier, specifically before memory allocation works; copy
some of the tricks from jump_label to enable this.

Primarily we overload key->next to store a sites pointer when there
are no modules, this avoids having to use kmalloc() to initialize the
sites and allows us to run much earlier.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Link: https://lore.kernel.org/r/20200818135805.220737930@infradead.org
---
 arch/x86/kernel/setup.c       |  2 ++
 arch/x86/kernel/static_call.c |  5 +++-
 include/linux/static_call.h   | 15 ++++++++--
 kernel/static_call.c          | 70 ++++++++++++++++++++++++++++++++++++++++---
 4 files changed, 85 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 3511736fbc74..799a6de439ea 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -19,6 +19,7 @@
 #include <linux/hugetlb.h>
 #include <linux/tboot.h>
 #include <linux/usb/xhci-dbgp.h>
+#include <linux/static_call.h>
 
 #include <uapi/linux/mount.h>
 
@@ -849,6 +850,7 @@ void __init setup_arch(char **cmdline_p)
 	early_cpu_init();
 	arch_init_ideal_nops();
 	jump_label_init();
+	static_call_init();
 	early_ioremap_init();
 
 	setup_olpc_ofw_pgd();
diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
index 55140d8db106..ca9a380d9c0b 100644
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -11,7 +11,7 @@ enum insn_type {
 	RET = 3,  /* tramp / site cond-tail-call */
 };
 
-static void __static_call_transform(void *insn, enum insn_type type, void *func)
+static void __ref __static_call_transform(void *insn, enum insn_type type, void *func)
 {
 	int size = CALL_INSN_SIZE;
 	const void *code;
@@ -38,6 +38,9 @@ static void __static_call_transform(void *insn, enum insn_type type, void *func)
 	if (memcmp(insn, code, size) == 0)
 		return;
 
+	if (unlikely(system_state == SYSTEM_BOOTING))
+		return text_poke_early(insn, code, size);
+
 	text_poke_bp(insn, code, size, NULL);
 }
 
diff --git a/include/linux/static_call.h b/include/linux/static_call.h
index 519bd666e096..bfa2ba39be57 100644
--- a/include/linux/static_call.h
+++ b/include/linux/static_call.h
@@ -136,6 +136,8 @@ extern void arch_static_call_transform(void *site, void *tramp, void *func, bool
 
 #ifdef CONFIG_HAVE_STATIC_CALL_INLINE
 
+extern void __init static_call_init(void);
+
 struct static_call_mod {
 	struct static_call_mod *next;
 	struct module *mod; /* for vmlinux, mod == NULL */
@@ -144,7 +146,12 @@ struct static_call_mod {
 
 struct static_call_key {
 	void *func;
-	struct static_call_mod *mods;
+	union {
+		/* bit 0: 0 = mods, 1 = sites */
+		unsigned long type;
+		struct static_call_mod *mods;
+		struct static_call_site *sites;
+	};
 };
 
 extern void __static_call_update(struct static_call_key *key, void *tramp, void *func);
@@ -155,7 +162,7 @@ extern int static_call_text_reserved(void *start, void *end);
 	DECLARE_STATIC_CALL(name, _func);				\
 	struct static_call_key STATIC_CALL_KEY(name) = {		\
 		.func = _func,						\
-		.mods = NULL,						\
+		.type = 1,						\
 	};								\
 	ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func)
 
@@ -180,6 +187,8 @@ extern int static_call_text_reserved(void *start, void *end);
 
 #elif defined(CONFIG_HAVE_STATIC_CALL)
 
+static inline void static_call_init(void) { }
+
 struct static_call_key {
 	void *func;
 };
@@ -225,6 +234,8 @@ static inline int static_call_text_reserved(void *start, void *end)
 
 #else /* Generic implementation */
 
+static inline void static_call_init(void) { }
+
 struct static_call_key {
 	void *func;
 };
diff --git a/kernel/static_call.c b/kernel/static_call.c
index d98e0e4272c1..f8362b3f8fd5 100644
--- a/kernel/static_call.c
+++ b/kernel/static_call.c
@@ -94,10 +94,31 @@ static inline void static_call_sort_entries(struct static_call_site *start,
 	     static_call_site_cmp, static_call_site_swap);
 }
 
+static inline bool static_call_key_has_mods(struct static_call_key *key)
+{
+	return !(key->type & 1);
+}
+
+static inline struct static_call_mod *static_call_key_next(struct static_call_key *key)
+{
+	if (!static_call_key_has_mods(key))
+		return NULL;
+
+	return key->mods;
+}
+
+static inline struct static_call_site *static_call_key_sites(struct static_call_key *key)
+{
+	if (static_call_key_has_mods(key))
+		return NULL;
+
+	return (struct static_call_site *)(key->type & ~1);
+}
+
 void __static_call_update(struct static_call_key *key, void *tramp, void *func)
 {
 	struct static_call_site *site, *stop;
-	struct static_call_mod *site_mod;
+	struct static_call_mod *site_mod, first;
 
 	cpus_read_lock();
 	static_call_lock();
@@ -116,13 +137,22 @@ void __static_call_update(struct static_call_key *key, void *tramp, void *func)
 	if (WARN_ON_ONCE(!static_call_initialized))
 		goto done;
 
-	for (site_mod = key->mods; site_mod; site_mod = site_mod->next) {
+	first = (struct static_call_mod){
+		.next = static_call_key_next(key),
+		.mod = NULL,
+		.sites = static_call_key_sites(key),
+	};
+
+	for (site_mod = &first; site_mod; site_mod = site_mod->next) {
 		struct module *mod = site_mod->mod;
 
 		if (!site_mod->sites) {
 			/*
 			 * This can happen if the static call key is defined in
 			 * a module which doesn't use it.
+			 *
+			 * It also happens in the has_mods case, where the
+			 * 'first' entry has no sites associated with it.
 			 */
 			continue;
 		}
@@ -192,16 +222,48 @@ static int __static_call_init(struct module *mod,
 		if (key != prev_key) {
 			prev_key = key;
 
+			/*
+			 * For vmlinux (!mod) avoid the allocation by storing
+			 * the sites pointer in the key itself. Also see
+			 * __static_call_update()'s @first.
+			 *
+			 * This allows architectures (eg. x86) to call
+			 * static_call_init() before memory allocation works.
+			 */
+			if (!mod) {
+				key->sites = site;
+				key->type |= 1;
+				goto do_transform;
+			}
+
 			site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL);
 			if (!site_mod)
 				return -ENOMEM;
 
+			/*
+			 * When the key has a direct sites pointer, extract
+			 * that into an explicit struct static_call_mod, so we
+			 * can have a list of modules.
+			 */
+			if (static_call_key_sites(key)) {
+				site_mod->mod = NULL;
+				site_mod->next = NULL;
+				site_mod->sites = static_call_key_sites(key);
+
+				key->mods = site_mod;
+
+				site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL);
+				if (!site_mod)
+					return -ENOMEM;
+			}
+
 			site_mod->mod = mod;
 			site_mod->sites = site;
-			site_mod->next = key->mods;
+			site_mod->next = static_call_key_next(key);
 			key->mods = site_mod;
 		}
 
+do_transform:
 		arch_static_call_transform(site_addr, NULL, key->func,
 				static_call_is_tail(site));
 	}
@@ -348,7 +410,7 @@ int static_call_text_reserved(void *start, void *end)
 	return __static_call_mod_text_reserved(start, end);
 }
 
-static void __init static_call_init(void)
+void __init static_call_init(void)
 {
 	int ret;
 
-- 
cgit v1.2.3


From d25e37d89dd2f41d7acae0429039d2f0ae8b4a07 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Tue, 18 Aug 2020 15:57:52 +0200
Subject: tracepoint: Optimize using static_call()

Currently the tracepoint site will iterate a vector and issue indirect
calls to however many handlers are registered (ie. the vector is
long).

Using static_call() it is possible to optimize this for the common
case of only having a single handler registered. In this case the
static_call() can directly call this handler. Otherwise, if the vector
is longer than 1, call a function that iterates the whole vector like
the current code.

[peterz: updated to new interface]

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20200818135805.279421092@infradead.org
---
 include/linux/tracepoint-defs.h |  5 +++
 include/linux/tracepoint.h      | 86 +++++++++++++++++++++++++++++------------
 include/trace/define_trace.h    | 14 +++----
 kernel/tracepoint.c             | 25 ++++++++++--
 4 files changed, 94 insertions(+), 36 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/tracepoint-defs.h b/include/linux/tracepoint-defs.h
index b29950a19205..de97450cf190 100644
--- a/include/linux/tracepoint-defs.h
+++ b/include/linux/tracepoint-defs.h
@@ -11,6 +11,8 @@
 #include <linux/atomic.h>
 #include <linux/static_key.h>
 
+struct static_call_key;
+
 struct trace_print_flags {
 	unsigned long		mask;
 	const char		*name;
@@ -30,6 +32,9 @@ struct tracepoint_func {
 struct tracepoint {
 	const char *name;		/* Tracepoint name */
 	struct static_key key;
+	struct static_call_key *static_call_key;
+	void *static_call_tramp;
+	void *iterator;
 	int (*regfunc)(void);
 	void (*unregfunc)(void);
 	struct tracepoint_func __rcu *funcs;
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 598fec9f9dbf..3722a10fc46d 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -19,6 +19,7 @@
 #include <linux/cpumask.h>
 #include <linux/rcupdate.h>
 #include <linux/tracepoint-defs.h>
+#include <linux/static_call.h>
 
 struct module;
 struct tracepoint;
@@ -92,7 +93,9 @@ extern int syscall_regfunc(void);
 extern void syscall_unregfunc(void);
 #endif /* CONFIG_HAVE_SYSCALL_TRACEPOINTS */
 
+#ifndef PARAMS
 #define PARAMS(args...) args
+#endif
 
 #define TRACE_DEFINE_ENUM(x)
 #define TRACE_DEFINE_SIZEOF(x)
@@ -148,6 +151,12 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 
 #ifdef TRACEPOINTS_ENABLED
 
+#ifdef CONFIG_HAVE_STATIC_CALL
+#define __DO_TRACE_CALL(name)	static_call(tp_func_##name)
+#else
+#define __DO_TRACE_CALL(name)	__tracepoint_iter_##name
+#endif /* CONFIG_HAVE_STATIC_CALL */
+
 /*
  * it_func[0] is never NULL because there is at least one element in the array
  * when the array itself is non NULL.
@@ -157,12 +166,11 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
  * has a "void" prototype, then it is invalid to declare a function
  * as "(void *, void)".
  */
-#define __DO_TRACE(tp, proto, args, cond, rcuidle)			\
+#define __DO_TRACE(name, proto, args, cond, rcuidle)			\
 	do {								\
 		struct tracepoint_func *it_func_ptr;			\
-		void *it_func;						\
-		void *__data;						\
 		int __maybe_unused __idx = 0;				\
+		void *__data;						\
 									\
 		if (!(cond))						\
 			return;						\
@@ -182,14 +190,11 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 			rcu_irq_enter_irqson();				\
 		}							\
 									\
-		it_func_ptr = rcu_dereference_raw((tp)->funcs);		\
-									\
+		it_func_ptr =						\
+			rcu_dereference_raw((&__tracepoint_##name)->funcs); \
 		if (it_func_ptr) {					\
-			do {						\
-				it_func = (it_func_ptr)->func;		\
-				__data = (it_func_ptr)->data;		\
-				((void(*)(proto))(it_func))(args);	\
-			} while ((++it_func_ptr)->func);		\
+			__data = (it_func_ptr)->data;			\
+			__DO_TRACE_CALL(name)(args);			\
 		}							\
 									\
 		if (rcuidle) {						\
@@ -205,7 +210,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 	static inline void trace_##name##_rcuidle(proto)		\
 	{								\
 		if (static_key_false(&__tracepoint_##name.key))		\
-			__DO_TRACE(&__tracepoint_##name,		\
+			__DO_TRACE(name,				\
 				TP_PROTO(data_proto),			\
 				TP_ARGS(data_args),			\
 				TP_CONDITION(cond), 1);			\
@@ -227,11 +232,13 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
  * poking RCU a bit.
  */
 #define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \
+	extern int __tracepoint_iter_##name(data_proto);		\
+	DECLARE_STATIC_CALL(tp_func_##name, __tracepoint_iter_##name); \
 	extern struct tracepoint __tracepoint_##name;			\
 	static inline void trace_##name(proto)				\
 	{								\
 		if (static_key_false(&__tracepoint_##name.key))		\
-			__DO_TRACE(&__tracepoint_##name,		\
+			__DO_TRACE(name,				\
 				TP_PROTO(data_proto),			\
 				TP_ARGS(data_args),			\
 				TP_CONDITION(cond), 0);			\
@@ -277,21 +284,50 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
  * structures, so we create an array of pointers that will be used for iteration
  * on the tracepoints.
  */
-#define DEFINE_TRACE_FN(name, reg, unreg)				 \
-	static const char __tpstrtab_##name[]				 \
-	__section(__tracepoints_strings) = #name;			 \
-	struct tracepoint __tracepoint_##name __used			 \
-	__section(__tracepoints) =					 \
-		{ __tpstrtab_##name, STATIC_KEY_INIT_FALSE, reg, unreg, NULL };\
-	__TRACEPOINT_ENTRY(name);
+#define DEFINE_TRACE_FN(_name, _reg, _unreg, proto, args)		\
+	static const char __tpstrtab_##_name[]				\
+	__section(__tracepoints_strings) = #_name;			\
+	extern struct static_call_key STATIC_CALL_KEY(tp_func_##_name);	\
+	int __tracepoint_iter_##_name(void *__data, proto);		\
+	struct tracepoint __tracepoint_##_name	__used			\
+	__section(__tracepoints) = {					\
+		.name = __tpstrtab_##_name,				\
+		.key = STATIC_KEY_INIT_FALSE,				\
+		.static_call_key = &STATIC_CALL_KEY(tp_func_##_name),	\
+		.static_call_tramp = STATIC_CALL_TRAMP_ADDR(tp_func_##_name), \
+		.iterator = &__tracepoint_iter_##_name,			\
+		.regfunc = _reg,					\
+		.unregfunc = _unreg,					\
+		.funcs = NULL };					\
+	__TRACEPOINT_ENTRY(_name);					\
+	int __tracepoint_iter_##_name(void *__data, proto)		\
+	{								\
+		struct tracepoint_func *it_func_ptr;			\
+		void *it_func;						\
+									\
+		it_func_ptr =						\
+			rcu_dereference_raw((&__tracepoint_##_name)->funcs); \
+		do {							\
+			it_func = (it_func_ptr)->func;			\
+			__data = (it_func_ptr)->data;			\
+			((void(*)(void *, proto))(it_func))(__data, args); \
+		} while ((++it_func_ptr)->func);			\
+		return 0;						\
+	}								\
+	DEFINE_STATIC_CALL(tp_func_##_name, __tracepoint_iter_##_name);
 
-#define DEFINE_TRACE(name)						\
-	DEFINE_TRACE_FN(name, NULL, NULL);
+#define DEFINE_TRACE(name, proto, args)		\
+	DEFINE_TRACE_FN(name, NULL, NULL, PARAMS(proto), PARAMS(args));
 
 #define EXPORT_TRACEPOINT_SYMBOL_GPL(name)				\
-	EXPORT_SYMBOL_GPL(__tracepoint_##name)
+	EXPORT_SYMBOL_GPL(__tracepoint_##name);				\
+	EXPORT_SYMBOL_GPL(__tracepoint_iter_##name);			\
+	EXPORT_STATIC_CALL_GPL(tp_func_##name)
 #define EXPORT_TRACEPOINT_SYMBOL(name)					\
-	EXPORT_SYMBOL(__tracepoint_##name)
+	EXPORT_SYMBOL(__tracepoint_##name);				\
+	EXPORT_SYMBOL(__tracepoint_iter_##name);			\
+	EXPORT_STATIC_CALL(tp_func_##name)
+
 
 #else /* !TRACEPOINTS_ENABLED */
 #define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \
@@ -320,8 +356,8 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 		return false;						\
 	}
 
-#define DEFINE_TRACE_FN(name, reg, unreg)
-#define DEFINE_TRACE(name)
+#define DEFINE_TRACE_FN(name, reg, unreg, proto, args)
+#define DEFINE_TRACE(name, proto, args)
 #define EXPORT_TRACEPOINT_SYMBOL_GPL(name)
 #define EXPORT_TRACEPOINT_SYMBOL(name)
 
diff --git a/include/trace/define_trace.h b/include/trace/define_trace.h
index bd75f97867b9..00723935dcc7 100644
--- a/include/trace/define_trace.h
+++ b/include/trace/define_trace.h
@@ -25,7 +25,7 @@
 
 #undef TRACE_EVENT
 #define TRACE_EVENT(name, proto, args, tstruct, assign, print)	\
-	DEFINE_TRACE(name)
+	DEFINE_TRACE(name, PARAMS(proto), PARAMS(args))
 
 #undef TRACE_EVENT_CONDITION
 #define TRACE_EVENT_CONDITION(name, proto, args, cond, tstruct, assign, print) \
@@ -39,12 +39,12 @@
 #undef TRACE_EVENT_FN
 #define TRACE_EVENT_FN(name, proto, args, tstruct,		\
 		assign, print, reg, unreg)			\
-	DEFINE_TRACE_FN(name, reg, unreg)
+	DEFINE_TRACE_FN(name, reg, unreg, PARAMS(proto), PARAMS(args))
 
 #undef TRACE_EVENT_FN_COND
 #define TRACE_EVENT_FN_COND(name, proto, args, cond, tstruct,		\
 		assign, print, reg, unreg)			\
-	DEFINE_TRACE_FN(name, reg, unreg)
+	DEFINE_TRACE_FN(name, reg, unreg, PARAMS(proto), PARAMS(args))
 
 #undef TRACE_EVENT_NOP
 #define TRACE_EVENT_NOP(name, proto, args, struct, assign, print)
@@ -54,15 +54,15 @@
 
 #undef DEFINE_EVENT
 #define DEFINE_EVENT(template, name, proto, args) \
-	DEFINE_TRACE(name)
+	DEFINE_TRACE(name, PARAMS(proto), PARAMS(args))
 
 #undef DEFINE_EVENT_FN
 #define DEFINE_EVENT_FN(template, name, proto, args, reg, unreg) \
-	DEFINE_TRACE_FN(name, reg, unreg)
+	DEFINE_TRACE_FN(name, reg, unreg, PARAMS(proto), PARAMS(args))
 
 #undef DEFINE_EVENT_PRINT
 #define DEFINE_EVENT_PRINT(template, name, proto, args, print)	\
-	DEFINE_TRACE(name)
+	DEFINE_TRACE(name, PARAMS(proto), PARAMS(args))
 
 #undef DEFINE_EVENT_CONDITION
 #define DEFINE_EVENT_CONDITION(template, name, proto, args, cond) \
@@ -70,7 +70,7 @@
 
 #undef DECLARE_TRACE
 #define DECLARE_TRACE(name, proto, args)	\
-	DEFINE_TRACE(name)
+	DEFINE_TRACE(name, PARAMS(proto), PARAMS(args))
 
 #undef TRACE_INCLUDE
 #undef __TRACE_INCLUDE
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 8e05ed2cd39e..e92f3fb8887a 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -221,6 +221,20 @@ static void *func_remove(struct tracepoint_func **funcs,
 	return old;
 }
 
+static void tracepoint_update_call(struct tracepoint *tp, struct tracepoint_func *tp_funcs)
+{
+	void *func = tp->iterator;
+
+	/* Synthetic events do not have static call sites */
+	if (!tp->static_call_key)
+		return;
+
+	if (!tp_funcs[1].func)
+		func = tp_funcs[0].func;
+
+	__static_call_update(tp->static_call_key, tp->static_call_tramp, func);
+}
+
 /*
  * Add the probe function to a tracepoint.
  */
@@ -251,8 +265,9 @@ static int tracepoint_add_func(struct tracepoint *tp,
 	 * include/linux/tracepoint.h using rcu_dereference_sched().
 	 */
 	rcu_assign_pointer(tp->funcs, tp_funcs);
-	if (!static_key_enabled(&tp->key))
-		static_key_slow_inc(&tp->key);
+	tracepoint_update_call(tp, tp_funcs);
+	static_key_enable(&tp->key);
+
 	release_probes(old);
 	return 0;
 }
@@ -281,9 +296,11 @@ static int tracepoint_remove_func(struct tracepoint *tp,
 		if (tp->unregfunc && static_key_enabled(&tp->key))
 			tp->unregfunc();
 
-		if (static_key_enabled(&tp->key))
-			static_key_slow_dec(&tp->key);
+		static_key_disable(&tp->key);
+	} else {
+		tracepoint_update_call(tp, tp_funcs);
 	}
+
 	rcu_assign_pointer(tp->funcs, tp_funcs);
 	release_probes(old);
 	return 0;
-- 
cgit v1.2.3


From f53fa968a7344970b8f8a5707c39cdcf17a6f367 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Tue, 5 May 2020 15:42:35 +0200
Subject: scif: Fix spelling of EACCES

As per POSIX, the correct spelling is EACCES:

include/uapi/asm-generic/errno-base.h:#define EACCES 13 /* Permission denied */

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 include/linux/scif.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/scif.h b/include/linux/scif.h
index eeb250b73c4b..329e695b8fe5 100644
--- a/include/linux/scif.h
+++ b/include/linux/scif.h
@@ -657,7 +657,7 @@ int scif_unregister(scif_epd_t epd, off_t offset, size_t len);
  * the negative of one of the following errors is returned.
  *
  * Errors:
- * EACCESS - Attempt to write to a read-only range
+ * EACCES - Attempt to write to a read-only range
  * EBADF, ENOTTY - epd is not a valid endpoint descriptor
  * ECONNRESET - Connection reset by peer
  * EINVAL - rma_flags is invalid
@@ -733,7 +733,7 @@ int scif_readfrom(scif_epd_t epd, off_t loffset, size_t len, off_t
  * the negative of one of the following errors is returned.
  *
  * Errors:
- * EACCESS - Attempt to write to a read-only range
+ * EACCES - Attempt to write to a read-only range
  * EBADF, ENOTTY - epd is not a valid endpoint descriptor
  * ECONNRESET - Connection reset by peer
  * EINVAL - rma_flags is invalid
@@ -815,7 +815,7 @@ int scif_writeto(scif_epd_t epd, off_t loffset, size_t len, off_t
  * the negative of one of the following errors is returned.
  *
  * Errors:
- * EACCESS - Attempt to write to a read-only range
+ * EACCES - Attempt to write to a read-only range
  * EBADF, ENOTTY - epd is not a valid endpoint descriptor
  * ECONNRESET - Connection reset by peer
  * EINVAL - rma_flags is invalid
@@ -895,7 +895,7 @@ int scif_vreadfrom(scif_epd_t epd, void *addr, size_t len, off_t roffset,
  * the negative of one of the following errors is returned.
  *
  * Errors:
- * EACCESS - Attempt to write to a read-only range
+ * EACCES - Attempt to write to a read-only range
  * EBADF, ENOTTY - epd is not a valid endpoint descriptor
  * ECONNRESET - Connection reset by peer
  * EINVAL - rma_flags is invalid
-- 
cgit v1.2.3


From db04e18dbb0146d3c753dc05f7233350375bbc48 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Wed, 19 Aug 2020 14:34:03 +0200
Subject: block: Make request_queue.rpm_status an enum

request_queue.rpm_status is assigned values of the rpm_status enum only,
so reflect that in its type.

Note that including <linux/pm.h> is (currently) a no-op, as it is
already included through <linux/genhd.h> and <linux/device.h>, but it is
better to play it safe.

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blkdev.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index bb5636cc17b9..0a1730b30ad2 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -24,6 +24,7 @@
 #include <linux/percpu-refcount.h>
 #include <linux/scatterlist.h>
 #include <linux/blkzoned.h>
+#include <linux/pm.h>
 
 struct module;
 struct scsi_ioctl_command;
@@ -458,7 +459,7 @@ struct request_queue {
 
 #ifdef CONFIG_PM
 	struct device		*dev;
-	int			rpm_status;
+	enum rpm_status		rpm_status;
 	unsigned int		nr_pending;
 #endif
 
-- 
cgit v1.2.3


From 611bee526b4a89d49f1b9914a770bfdc101d5fb5 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 23 Aug 2020 11:10:41 +0200
Subject: block: replace bd_set_size with bd_set_nr_sectors

Replace bd_set_size with a version that takes the number of sectors
instead, as that fits most of the current and future callers much better.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/loop.c     |  4 ++--
 drivers/block/nbd.c      |  7 ++++---
 drivers/block/pktcdvd.c  |  2 +-
 drivers/nvme/host/nvme.h |  2 +-
 fs/block_dev.c           | 10 +++++-----
 include/linux/genhd.h    |  2 +-
 6 files changed, 14 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index d3394191e168..cb1191d6e945 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -253,7 +253,7 @@ static void loop_set_size(struct loop_device *lo, loff_t size)
 {
 	struct block_device *bdev = lo->lo_device;
 
-	bd_set_size(bdev, size << SECTOR_SHIFT);
+	bd_set_nr_sectors(bdev, size);
 
 	set_capacity_revalidate_and_notify(lo->lo_disk, size, false);
 }
@@ -1251,7 +1251,7 @@ static int __loop_clr_fd(struct loop_device *lo, bool release)
 	set_capacity(lo->lo_disk, 0);
 	loop_sysfs_exit(lo);
 	if (bdev) {
-		bd_set_size(bdev, 0);
+		bd_set_nr_sectors(bdev, 0);
 		/* let user-space know about this change */
 		kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE);
 	}
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index edf8b632e3d2..a54f2d155a31 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -300,6 +300,7 @@ static void nbd_size_update(struct nbd_device *nbd)
 {
 	struct nbd_config *config = nbd->config;
 	struct block_device *bdev = bdget_disk(nbd->disk, 0);
+	sector_t nr_sectors = config->bytesize >> 9;
 
 	if (config->flags & NBD_FLAG_SEND_TRIM) {
 		nbd->disk->queue->limits.discard_granularity = config->blksize;
@@ -308,10 +309,10 @@ static void nbd_size_update(struct nbd_device *nbd)
 	}
 	blk_queue_logical_block_size(nbd->disk->queue, config->blksize);
 	blk_queue_physical_block_size(nbd->disk->queue, config->blksize);
-	set_capacity(nbd->disk, config->bytesize >> 9);
+	set_capacity(nbd->disk, nr_sectors);
 	if (bdev) {
 		if (bdev->bd_disk) {
-			bd_set_size(bdev, config->bytesize);
+			bd_set_nr_sectors(bdev, nr_sectors);
 			set_blocksize(bdev, config->blksize);
 		} else
 			bdev->bd_invalidated = 1;
@@ -1138,7 +1139,7 @@ static void nbd_bdev_reset(struct block_device *bdev)
 {
 	if (bdev->bd_openers > 1)
 		return;
-	bd_set_size(bdev, 0);
+	bd_set_nr_sectors(bdev, 0);
 }
 
 static void nbd_parse_flags(struct nbd_device *nbd)
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 1034e445680c..17f2e6ff1223 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -2192,7 +2192,7 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write)
 
 	set_capacity(pd->disk, lba << 2);
 	set_capacity(pd->bdev->bd_disk, lba << 2);
-	bd_set_size(pd->bdev, (loff_t)lba << 11);
+	bd_set_nr_sectors(pd->bdev, lba << 2);
 
 	q = bdev_get_queue(pd->bdev);
 	if (write) {
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 2910f6caab7d..aab130f31e25 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -688,7 +688,7 @@ static inline void nvme_mpath_update_disk_size(struct gendisk *disk)
 	struct block_device *bdev = bdget_disk(disk, 0);
 
 	if (bdev) {
-		bd_set_size(bdev, get_capacity(disk) << SECTOR_SHIFT);
+		bd_set_nr_sectors(bdev, get_capacity(disk));
 		bdput(bdev);
 	}
 }
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 8ae833e00443..f52597172c8b 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1371,13 +1371,13 @@ int check_disk_change(struct block_device *bdev)
 
 EXPORT_SYMBOL(check_disk_change);
 
-void bd_set_size(struct block_device *bdev, loff_t size)
+void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors)
 {
 	inode_lock(bdev->bd_inode);
-	i_size_write(bdev->bd_inode, size);
+	i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT);
 	inode_unlock(bdev->bd_inode);
 }
-EXPORT_SYMBOL(bd_set_size);
+EXPORT_SYMBOL(bd_set_nr_sectors);
 
 static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
 
@@ -1514,7 +1514,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder,
 			}
 
 			if (!ret) {
-				bd_set_size(bdev,(loff_t)get_capacity(disk)<<9);
+				bd_set_nr_sectors(bdev, get_capacity(disk));
 				set_init_blocksize(bdev);
 			}
 
@@ -1542,7 +1542,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder,
 				ret = -ENXIO;
 				goto out_clear;
 			}
-			bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9);
+			bd_set_nr_sectors(bdev, bdev->bd_part->nr_sects);
 			set_init_blocksize(bdev);
 		}
 
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 4ab853461dff..39025dc0397c 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -375,7 +375,7 @@ void unregister_blkdev(unsigned int major, const char *name);
 int revalidate_disk(struct gendisk *disk);
 int check_disk_change(struct block_device *bdev);
 int __invalidate_device(struct block_device *bdev, bool kill_dirty);
-void bd_set_size(struct block_device *bdev, loff_t size);
+void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors);
 
 /* for drivers/char/raw.c: */
 int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long);
-- 
cgit v1.2.3


From c2b4bb8cb3741c0bacf3683e4c1ecd04c977ada3 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 23 Aug 2020 11:10:42 +0200
Subject: block: fix locking for struct block_device size updates

Two different callers use two different mutexes for updating the
block device size, which obviously doesn't help to actually protect
against concurrent updates from the different callers.  In addition
one of the locks, bd_mutex is rather prone to deadlocks with other
parts of the block stack that use it for high level synchronization.

Switch to using a new spinlock protecting just the size updates, as
that is all we need, and make sure everyone does the update through
the proper helper.

This fixes a bug reported with the nvme revalidating disks during a
hot removal operation, which can currently deadlock on bd_mutex.

Reported-by: Xianting Tian <xianting_tian@126.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/partitions/core.c         |  4 ++--
 drivers/block/aoe/aoecmd.c      |  4 +---
 drivers/md/dm.c                 | 15 ++-------------
 drivers/s390/block/dasd_ioctl.c |  9 ++-------
 fs/block_dev.c                  | 25 ++++++++++++++-----------
 include/linux/blk_types.h       |  1 +
 6 files changed, 22 insertions(+), 36 deletions(-)

(limited to 'include/linux')

diff --git a/block/partitions/core.c b/block/partitions/core.c
index 5b4869c08fb3..b1c0b50ca92d 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -592,8 +592,8 @@ int bdev_resize_partition(struct block_device *bdev, int partno,
 	if (partition_overlaps(bdev->bd_disk, start, length, partno))
 		goto out_unlock;
 
-	part_nr_sects_write(part, (sector_t)length);
-	i_size_write(bdevp->bd_inode, length << SECTOR_SHIFT);
+	part_nr_sects_write(part, length);
+	bd_set_nr_sectors(bdevp, length);
 
 	ret = 0;
 out_unlock:
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index 6dba41395155..313f0b946fe2 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -900,9 +900,7 @@ aoecmd_sleepwork(struct work_struct *work)
 		ssize = get_capacity(d->gd);
 		bd = bdget_disk(d->gd, 0);
 		if (bd) {
-			inode_lock(bd->bd_inode);
-			i_size_write(bd->bd_inode, (loff_t)ssize<<9);
-			inode_unlock(bd->bd_inode);
+			bd_set_nr_sectors(bd, ssize);
 			bdput(bd);
 		}
 		spin_lock_irq(&d->lock);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index fb0255d25e4b..3dedd9cc4fb6 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -2097,18 +2097,6 @@ static void event_callback(void *context)
 	dm_issue_global_event();
 }
 
-/*
- * Protected by md->suspend_lock obtained by dm_swap_table().
- */
-static void __set_size(struct mapped_device *md, sector_t size)
-{
-	lockdep_assert_held(&md->suspend_lock);
-
-	set_capacity(md->disk, size);
-
-	i_size_write(md->bdev->bd_inode, (loff_t)size << SECTOR_SHIFT);
-}
-
 /*
  * Returns old map, which caller must destroy.
  */
@@ -2131,7 +2119,8 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
 	if (size != dm_get_size(md))
 		memset(&md->geometry, 0, sizeof(md->geometry));
 
-	__set_size(md, size);
+	set_capacity(md->disk, size);
+	bd_set_nr_sectors(md->bdev, size);
 
 	dm_table_event_callback(t, event_callback, md);
 
diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c
index 777734d1b4e5..faaf5596e31c 100644
--- a/drivers/s390/block/dasd_ioctl.c
+++ b/drivers/s390/block/dasd_ioctl.c
@@ -55,10 +55,7 @@ dasd_ioctl_enable(struct block_device *bdev)
 
 	dasd_enable_device(base);
 	/* Formatting the dasd device can change the capacity. */
-	mutex_lock(&bdev->bd_mutex);
-	i_size_write(bdev->bd_inode,
-		     (loff_t)get_capacity(base->block->gdp) << 9);
-	mutex_unlock(&bdev->bd_mutex);
+	bd_set_nr_sectors(bdev, get_capacity(base->block->gdp));
 	dasd_put_device(base);
 	return 0;
 }
@@ -91,9 +88,7 @@ dasd_ioctl_disable(struct block_device *bdev)
 	 * Set i_size to zero, since read, write, etc. check against this
 	 * value.
 	 */
-	mutex_lock(&bdev->bd_mutex);
-	i_size_write(bdev->bd_inode, 0);
-	mutex_unlock(&bdev->bd_mutex);
+	bd_set_nr_sectors(bdev, 0);
 	dasd_put_device(base);
 	return 0;
 }
diff --git a/fs/block_dev.c b/fs/block_dev.c
index f52597172c8b..08158bb2e76c 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -876,6 +876,7 @@ struct block_device *bdget(dev_t dev)
 	bdev = &BDEV_I(inode)->bdev;
 
 	if (inode->i_state & I_NEW) {
+		spin_lock_init(&bdev->bd_size_lock);
 		bdev->bd_contains = NULL;
 		bdev->bd_super = NULL;
 		bdev->bd_inode = inode;
@@ -1290,6 +1291,7 @@ static void check_disk_size_change(struct gendisk *disk,
 {
 	loff_t disk_size, bdev_size;
 
+	spin_lock(&bdev->bd_size_lock);
 	disk_size = (loff_t)get_capacity(disk) << 9;
 	bdev_size = i_size_read(bdev->bd_inode);
 	if (disk_size != bdev_size) {
@@ -1299,11 +1301,15 @@ static void check_disk_size_change(struct gendisk *disk,
 			       disk->disk_name, bdev_size, disk_size);
 		}
 		i_size_write(bdev->bd_inode, disk_size);
-		if (bdev_size > disk_size && __invalidate_device(bdev, false))
+	}
+	bdev->bd_invalidated = 0;
+	spin_unlock(&bdev->bd_size_lock);
+
+	if (bdev_size > disk_size) {
+		if (__invalidate_device(bdev, false))
 			pr_warn("VFS: busy inodes on resized disk %s\n",
 				disk->disk_name);
 	}
-	bdev->bd_invalidated = 0;
 }
 
 /**
@@ -1328,13 +1334,10 @@ int revalidate_disk(struct gendisk *disk)
 	if (!(disk->flags & GENHD_FL_HIDDEN)) {
 		struct block_device *bdev = bdget_disk(disk, 0);
 
-		if (!bdev)
-			return ret;
-
-		mutex_lock(&bdev->bd_mutex);
-		check_disk_size_change(disk, bdev, ret == 0);
-		mutex_unlock(&bdev->bd_mutex);
-		bdput(bdev);
+		if (bdev) {
+			check_disk_size_change(disk, bdev, ret == 0);
+			bdput(bdev);
+		}
 	}
 	return ret;
 }
@@ -1373,9 +1376,9 @@ EXPORT_SYMBOL(check_disk_change);
 
 void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors)
 {
-	inode_lock(bdev->bd_inode);
+	spin_lock(&bdev->bd_size_lock);
 	i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT);
-	inode_unlock(bdev->bd_inode);
+	spin_unlock(&bdev->bd_size_lock);
 }
 EXPORT_SYMBOL(bd_set_nr_sectors);
 
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 4ecf4fed171f..5accc2549d22 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -38,6 +38,7 @@ struct block_device {
 	/* number of times partitions within this device have been opened. */
 	unsigned		bd_part_count;
 	int			bd_invalidated;
+	spinlock_t		bd_size_lock; /* for bd_inode->i_size updates */
 	struct gendisk *	bd_disk;
 	struct backing_dev_info *bd_bdi;
 
-- 
cgit v1.2.3


From f3256075ba49d80835b601bfbff350a2140b2924 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 27 Aug 2020 17:37:45 +0200
Subject: block: remove the BIO_NULL_MAPPED flag

We can simply use a boolean flag in the bio_map_data data structure
instead.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-map.c           | 9 +++++----
 include/linux/blk_types.h | 1 -
 2 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-map.c b/block/blk-map.c
index 6e804892d5ec..51e6195f878d 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -12,7 +12,8 @@
 #include "blk.h"
 
 struct bio_map_data {
-	int is_our_pages;
+	bool is_our_pages : 1;
+	bool is_null_mapped : 1;
 	struct iov_iter iter;
 	struct iovec iov[];
 };
@@ -108,7 +109,7 @@ static int bio_uncopy_user(struct bio *bio)
 	struct bio_map_data *bmd = bio->bi_private;
 	int ret = 0;
 
-	if (!bio_flagged(bio, BIO_NULL_MAPPED)) {
+	if (!bmd || !bmd->is_null_mapped) {
 		/*
 		 * if we're in a workqueue, the request is orphaned, so
 		 * don't copy into a random user address space, just free
@@ -158,7 +159,7 @@ static struct bio *bio_copy_user_iov(struct request_queue *q,
 	 * The caller provided iov might point to an on-stack or otherwise
 	 * shortlived one.
 	 */
-	bmd->is_our_pages = map_data ? 0 : 1;
+	bmd->is_our_pages = !map_data;
 
 	nr_pages = DIV_ROUND_UP(offset + len, PAGE_SIZE);
 	if (nr_pages > BIO_MAX_PAGES)
@@ -234,7 +235,7 @@ static struct bio *bio_copy_user_iov(struct request_queue *q,
 
 	bio->bi_private = bmd;
 	if (map_data && map_data->null_mapped)
-		bio_set_flag(bio, BIO_NULL_MAPPED);
+		bmd->is_null_mapped = true;
 	return bio;
 cleanup:
 	if (!map_data)
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 5accc2549d22..78b073956884 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -257,7 +257,6 @@ enum {
 	BIO_CLONED,		/* doesn't own data */
 	BIO_BOUNCED,		/* bio is a bounce bio */
 	BIO_USER_MAPPED,	/* contains user pages */
-	BIO_NULL_MAPPED,	/* contains invalid user pages */
 	BIO_WORKINGSET,		/* contains userspace workingset pages */
 	BIO_QUIET,		/* Make BIO Quiet */
 	BIO_CHAIN,		/* chained bio, ->bi_remaining in effect */
-- 
cgit v1.2.3


From 3310eebafe6f9a872c1f757b3d822dafae9c0cd8 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 27 Aug 2020 17:37:48 +0200
Subject: block: remove the BIO_USER_MAPPED flag

Just check if there is private data, in which case the bio must have
originated from bio_copy_user_iov.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-map.c           | 10 ++++------
 include/linux/blk_types.h |  1 -
 2 files changed, 4 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-map.c b/block/blk-map.c
index 427962ac2f67..be118926ccf4 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -109,7 +109,7 @@ static int bio_uncopy_user(struct bio *bio)
 	struct bio_map_data *bmd = bio->bi_private;
 	int ret = 0;
 
-	if (!bmd || !bmd->is_null_mapped) {
+	if (!bmd->is_null_mapped) {
 		/*
 		 * if we're in a workqueue, the request is orphaned, so
 		 * don't copy into a random user address space, just free
@@ -307,8 +307,6 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
 			break;
 	}
 
-	bio_set_flag(bio, BIO_USER_MAPPED);
-
 	/*
 	 * Subtle: if we end up needing to bounce a bio, it would normally
 	 * disappear when its bi_end_io is run.  However, we need the original
@@ -654,12 +652,12 @@ int blk_rq_unmap_user(struct bio *bio)
 		if (unlikely(bio_flagged(bio, BIO_BOUNCED)))
 			mapped_bio = bio->bi_private;
 
-		if (bio_flagged(mapped_bio, BIO_USER_MAPPED)) {
-			bio_unmap_user(mapped_bio);
-		} else {
+		if (bio->bi_private) {
 			ret2 = bio_uncopy_user(mapped_bio);
 			if (ret2 && !ret)
 				ret = ret2;
+		} else {
+			bio_unmap_user(mapped_bio);
 		}
 
 		mapped_bio = bio;
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 78b073956884..63a39e47fc60 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -256,7 +256,6 @@ enum {
 	BIO_NO_PAGE_REF,	/* don't put release vec pages */
 	BIO_CLONED,		/* doesn't own data */
 	BIO_BOUNCED,		/* bio is a bounce bio */
-	BIO_USER_MAPPED,	/* contains user pages */
 	BIO_WORKINGSET,		/* contains userspace workingset pages */
 	BIO_QUIET,		/* Make BIO Quiet */
 	BIO_CHAIN,		/* chained bio, ->bi_remaining in effect */
-- 
cgit v1.2.3


From bdc6a287bc98e8f32bf52c9cb2d1bdf75975f5a0 Mon Sep 17 00:00:00 2001
From: Baolin Wang <baolin.wang@linux.alibaba.com>
Date: Fri, 28 Aug 2020 10:52:55 +0800
Subject: block: Move blk_mq_bio_list_merge() into blk-merge.c

Move the blk_mq_bio_list_merge() into blk-merge.c and
rename it as a generic name.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-merge.c      | 44 ++++++++++++++++++++++++++++++++++++++++++++
 block/blk-mq-sched.c   | 46 +---------------------------------------------
 block/blk.h            |  2 ++
 block/kyber-iosched.c  |  2 +-
 include/linux/blk-mq.h |  2 --
 5 files changed, 48 insertions(+), 48 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-merge.c b/block/blk-merge.c
index 3aa2de57b57f..b09e9fc44236 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -1052,3 +1052,47 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 
 	return false;
 }
+
+/*
+ * Iterate list of requests and see if we can merge this bio with any
+ * of them.
+ */
+bool blk_bio_list_merge(struct request_queue *q, struct list_head *list,
+			struct bio *bio, unsigned int nr_segs)
+{
+	struct request *rq;
+	int checked = 8;
+
+	list_for_each_entry_reverse(rq, list, queuelist) {
+		bool merged = false;
+
+		if (!checked--)
+			break;
+
+		if (!blk_rq_merge_ok(rq, bio))
+			continue;
+
+		switch (blk_try_merge(rq, bio)) {
+		case ELEVATOR_BACK_MERGE:
+			if (blk_mq_sched_allow_merge(q, rq, bio))
+				merged = bio_attempt_back_merge(rq, bio,
+						nr_segs);
+			break;
+		case ELEVATOR_FRONT_MERGE:
+			if (blk_mq_sched_allow_merge(q, rq, bio))
+				merged = bio_attempt_front_merge(rq, bio,
+						nr_segs);
+			break;
+		case ELEVATOR_DISCARD_MERGE:
+			merged = bio_attempt_discard_merge(q, rq, bio);
+			break;
+		default:
+			continue;
+		}
+
+		return merged;
+	}
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(blk_bio_list_merge);
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index d2790e5b06d1..82acff96c093 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -391,50 +391,6 @@ bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
 }
 EXPORT_SYMBOL_GPL(blk_mq_sched_try_merge);
 
-/*
- * Iterate list of requests and see if we can merge this bio with any
- * of them.
- */
-bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list,
-			   struct bio *bio, unsigned int nr_segs)
-{
-	struct request *rq;
-	int checked = 8;
-
-	list_for_each_entry_reverse(rq, list, queuelist) {
-		bool merged = false;
-
-		if (!checked--)
-			break;
-
-		if (!blk_rq_merge_ok(rq, bio))
-			continue;
-
-		switch (blk_try_merge(rq, bio)) {
-		case ELEVATOR_BACK_MERGE:
-			if (blk_mq_sched_allow_merge(q, rq, bio))
-				merged = bio_attempt_back_merge(rq, bio,
-						nr_segs);
-			break;
-		case ELEVATOR_FRONT_MERGE:
-			if (blk_mq_sched_allow_merge(q, rq, bio))
-				merged = bio_attempt_front_merge(rq, bio,
-						nr_segs);
-			break;
-		case ELEVATOR_DISCARD_MERGE:
-			merged = bio_attempt_discard_merge(q, rq, bio);
-			break;
-		default:
-			continue;
-		}
-
-		return merged;
-	}
-
-	return false;
-}
-EXPORT_SYMBOL_GPL(blk_mq_bio_list_merge);
-
 /*
  * Reverse check our software queue for entries that we could potentially
  * merge with. Currently includes a hand-wavy stop count of 8, to not spend
@@ -449,7 +405,7 @@ static bool blk_mq_attempt_merge(struct request_queue *q,
 
 	lockdep_assert_held(&ctx->lock);
 
-	if (blk_mq_bio_list_merge(q, &ctx->rq_lists[type], bio, nr_segs)) {
+	if (blk_bio_list_merge(q, &ctx->rq_lists[type], bio, nr_segs)) {
 		ctx->rq_merged++;
 		return true;
 	}
diff --git a/block/blk.h b/block/blk.h
index 49e2928a1632..d6152d20d4e2 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -177,6 +177,8 @@ bool bio_attempt_discard_merge(struct request_queue *q, struct request *req,
 		struct bio *bio);
 bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 		unsigned int nr_segs, struct request **same_queue_rq);
+bool blk_bio_list_merge(struct request_queue *q, struct list_head *list,
+			struct bio *bio, unsigned int nr_segs);
 
 void blk_account_io_start(struct request *req);
 void blk_account_io_done(struct request *req, u64 now);
diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c
index a38c5ab103d1..6d4ba0e9688e 100644
--- a/block/kyber-iosched.c
+++ b/block/kyber-iosched.c
@@ -573,7 +573,7 @@ static bool kyber_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio,
 	bool merged;
 
 	spin_lock(&kcq->lock);
-	merged = blk_mq_bio_list_merge(hctx->queue, rq_list, bio, nr_segs);
+	merged = blk_bio_list_merge(hctx->queue, rq_list, bio, nr_segs);
 	spin_unlock(&kcq->lock);
 
 	return merged;
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 9d2d5ad367a4..21a02e0577dd 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -489,8 +489,6 @@ void blk_mq_kick_requeue_list(struct request_queue *q);
 void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs);
 void blk_mq_complete_request(struct request *rq);
 bool blk_mq_complete_request_remote(struct request *rq);
-bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list,
-			   struct bio *bio, unsigned int nr_segs);
 bool blk_mq_queue_stopped(struct request_queue *q);
 void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx);
 void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx);
-- 
cgit v1.2.3


From 7b8917f5e29c377be1db5680249fe30e038cb3eb Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 31 Aug 2020 20:02:33 +0200
Subject: block: remove the alignment_offset field from struct hd_struct

The alignment offset is only used in slow path callers, so just calculate
it on the fly.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/partitions/core.c | 7 ++++---
 include/linux/blkdev.h  | 5 ++---
 include/linux/genhd.h   | 1 -
 3 files changed, 6 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/block/partitions/core.c b/block/partitions/core.c
index b1c0b50ca92d..94c2fb39e602 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -199,7 +199,10 @@ static ssize_t part_alignment_offset_show(struct device *dev,
 					  struct device_attribute *attr, char *buf)
 {
 	struct hd_struct *p = dev_to_part(dev);
-	return sprintf(buf, "%llu\n", (unsigned long long)p->alignment_offset);
+
+	return sprintf(buf, "%u\n",
+		queue_limit_alignment_offset(&part_to_disk(p)->queue->limits,
+				p->start_sect));
 }
 
 static ssize_t part_discard_alignment_show(struct device *dev,
@@ -405,8 +408,6 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 	pdev = part_to_dev(p);
 
 	p->start_sect = start;
-	p->alignment_offset =
-		queue_limit_alignment_offset(&disk->queue->limits, start);
 	p->discard_alignment =
 		queue_limit_discard_alignment(&disk->queue->limits, start);
 	p->nr_sects = len;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 0a1730b30ad2..ba1f5f5e11c6 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1456,10 +1456,9 @@ static inline int bdev_alignment_offset(struct block_device *bdev)
 
 	if (q->limits.misaligned)
 		return -1;
-
 	if (bdev != bdev->bd_contains)
-		return bdev->bd_part->alignment_offset;
-
+		return queue_limit_alignment_offset(&q->limits,
+				bdev->bd_part->start_sect);
 	return q->limits.alignment_offset;
 }
 
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 39025dc0397c..bfa411c80dbb 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -65,7 +65,6 @@ struct hd_struct {
 	struct disk_stats __percpu *dkstats;
 	struct percpu_ref ref;
 
-	sector_t alignment_offset;
 	unsigned int discard_alignment;
 	struct device __dev;
 	struct kobject *holder_dir;
-- 
cgit v1.2.3


From 7cf34d97ab45203b975396393ded9d3867dfa8bf Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 31 Aug 2020 20:02:34 +0200
Subject: block: remove the discard_alignment field from struct hd_struct

The alignment offset is only used in slow path callers, so just calculate
it on the fly.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/partitions/core.c | 7 ++++---
 include/linux/blkdev.h  | 4 ++--
 include/linux/genhd.h   | 1 -
 3 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/block/partitions/core.c b/block/partitions/core.c
index 94c2fb39e602..e596a85bba1e 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -209,7 +209,10 @@ static ssize_t part_discard_alignment_show(struct device *dev,
 					   struct device_attribute *attr, char *buf)
 {
 	struct hd_struct *p = dev_to_part(dev);
-	return sprintf(buf, "%u\n", p->discard_alignment);
+
+	return sprintf(buf, "%u\n",
+		queue_limit_discard_alignment(&part_to_disk(p)->queue->limits,
+				p->start_sect));
 }
 
 static DEVICE_ATTR(partition, 0444, part_partition_show, NULL);
@@ -408,8 +411,6 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 	pdev = part_to_dev(p);
 
 	p->start_sect = start;
-	p->discard_alignment =
-		queue_limit_discard_alignment(&disk->queue->limits, start);
 	p->nr_sects = len;
 	p->partno = partno;
 	p->policy = get_disk_ro(disk);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index ba1f5f5e11c6..d0d61bc81615 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1498,8 +1498,8 @@ static inline int bdev_discard_alignment(struct block_device *bdev)
 	struct request_queue *q = bdev_get_queue(bdev);
 
 	if (bdev != bdev->bd_contains)
-		return bdev->bd_part->discard_alignment;
-
+		return queue_limit_discard_alignment(&q->limits,
+				bdev->bd_part->start_sect);
 	return q->limits.discard_alignment;
 }
 
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index bfa411c80dbb..9ea2ca31c278 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -65,7 +65,6 @@ struct hd_struct {
 	struct disk_stats __percpu *dkstats;
 	struct percpu_ref ref;
 
-	unsigned int discard_alignment;
 	struct device __dev;
 	struct kobject *holder_dir;
 	int policy, partno;
-- 
cgit v1.2.3


From 46d40cfad13ccbd0739019d754d46d8f93e1d5aa Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 31 Aug 2020 20:02:35 +0200
Subject: block: remove an outdated comment on the bd_dev field

kdev_t is long gone, so we don't need to comment a field isn't one..

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blk_types.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 63a39e47fc60..59d9150165c4 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -20,7 +20,7 @@ typedef void (bio_end_io_t) (struct bio *);
 struct bio_crypt_ctx;
 
 struct block_device {
-	dev_t			bd_dev;  /* not a kdev_t - it's a search key */
+	dev_t			bd_dev;
 	int			bd_openers;
 	struct inode *		bd_inode;	/* will die */
 	struct super_block *	bd_super;
-- 
cgit v1.2.3


From a8c7ffdb5fdde3a57c0b654f66f4d81325abe69f Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Thu, 27 Aug 2020 10:51:56 +0200
Subject: mtd: nand: Introduce the ECC engine framework

Create a generic ECC engine framework. This is a base to instantiate ECC
engine objects.

If we really want to be generic, bindings must evolve, so here is the
new logic. The following three properties are mutually exclusive:
- The nand-no-ecc-engine boolean property is set and there is no
  ECC engine to retrieve.
- The nand-use-soft-ecc-engine boolean property is set and the core
  will force using the use of software correction.
- There is a nand-ecc-engine property pointing at a node which will
  act as ECC engine.

It the later case, the property may reference:
- The NAND chip node itself (for the on-die ECC case).
- The parent node if the NAND controller embeds an ECC engine.
- Any other node being an external ECC controller as well.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-9-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/Kconfig  |   8 +
 drivers/mtd/nand/Makefile |   2 +
 drivers/mtd/nand/ecc.c    | 484 ++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/mtd/nand.h  | 114 +++++++++++
 4 files changed, 608 insertions(+)
 create mode 100644 drivers/mtd/nand/ecc.c

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig
index c1a45b071165..4a9aed4f0104 100644
--- a/drivers/mtd/nand/Kconfig
+++ b/drivers/mtd/nand/Kconfig
@@ -9,4 +9,12 @@ source "drivers/mtd/nand/onenand/Kconfig"
 source "drivers/mtd/nand/raw/Kconfig"
 source "drivers/mtd/nand/spi/Kconfig"
 
+menu "ECC engine support"
+
+config MTD_NAND_ECC
+       bool
+       depends on MTD_NAND_CORE
+
+endmenu
+
 endmenu
diff --git a/drivers/mtd/nand/Makefile b/drivers/mtd/nand/Makefile
index 7ecd80c0a66e..981372953b56 100644
--- a/drivers/mtd/nand/Makefile
+++ b/drivers/mtd/nand/Makefile
@@ -6,3 +6,5 @@ obj-$(CONFIG_MTD_NAND_CORE) += nandcore.o
 obj-y	+= onenand/
 obj-y	+= raw/
 obj-y	+= spi/
+
+nandcore-$(CONFIG_MTD_NAND_ECC) += ecc.o
diff --git a/drivers/mtd/nand/ecc.c b/drivers/mtd/nand/ecc.c
new file mode 100644
index 000000000000..4a56e6c0da67
--- /dev/null
+++ b/drivers/mtd/nand/ecc.c
@@ -0,0 +1,484 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Generic Error-Correcting Code (ECC) engine
+ *
+ * Copyright (C) 2019 Macronix
+ * Author:
+ *     Miquèl RAYNAL <miquel.raynal@bootlin.com>
+ *
+ *
+ * This file describes the abstraction of any NAND ECC engine. It has been
+ * designed to fit most cases, including parallel NANDs and SPI-NANDs.
+ *
+ * There are three main situations where instantiating this ECC engine makes
+ * sense:
+ *   - external: The ECC engine is outside the NAND pipeline, typically this
+ *               is a software ECC engine, or an hardware engine that is
+ *               outside the NAND controller pipeline.
+ *   - pipelined: The ECC engine is inside the NAND pipeline, ie. on the
+ *                controller's side. This is the case of most of the raw NAND
+ *                controllers. In the pipeline case, the ECC bytes are
+ *                generated/data corrected on the fly when a page is
+ *                written/read.
+ *   - ondie: The ECC engine is inside the NAND pipeline, on the chip's side.
+ *            Some NAND chips can correct themselves the data.
+ *
+ * Besides the initial setup and final cleanups, the interfaces are rather
+ * simple:
+ *   - prepare: Prepare an I/O request. Enable/disable the ECC engine based on
+ *              the I/O request type. In case of software correction or external
+ *              engine, this step may involve to derive the ECC bytes and place
+ *              them in the OOB area before a write.
+ *   - finish: Finish an I/O request. Correct the data in case of a read
+ *             request and report the number of corrected bits/uncorrectable
+ *             errors. Most likely empty for write operations, unless you have
+ *             hardware specific stuff to do, like shutting down the engine to
+ *             save power.
+ *
+ * The I/O request should be enclosed in a prepare()/finish() pair of calls
+ * and will behave differently depending on the requested I/O type:
+ *   - raw: Correction disabled
+ *   - ecc: Correction enabled
+ *
+ * The request direction is impacting the logic as well:
+ *   - read: Load data from the NAND chip
+ *   - write: Store data in the NAND chip
+ *
+ * Mixing all this combinations together gives the following behavior.
+ * Those are just examples, drivers are free to add custom steps in their
+ * prepare/finish hook.
+ *
+ * [external ECC engine]
+ *   - external + prepare + raw + read: do nothing
+ *   - external + finish  + raw + read: do nothing
+ *   - external + prepare + raw + write: do nothing
+ *   - external + finish  + raw + write: do nothing
+ *   - external + prepare + ecc + read: do nothing
+ *   - external + finish  + ecc + read: calculate expected ECC bytes, extract
+ *                                      ECC bytes from OOB buffer, correct
+ *                                      and report any bitflip/error
+ *   - external + prepare + ecc + write: calculate ECC bytes and store them at
+ *                                       the right place in the OOB buffer based
+ *                                       on the OOB layout
+ *   - external + finish  + ecc + write: do nothing
+ *
+ * [pipelined ECC engine]
+ *   - pipelined + prepare + raw + read: disable the controller's ECC engine if
+ *                                       activated
+ *   - pipelined + finish  + raw + read: do nothing
+ *   - pipelined + prepare + raw + write: disable the controller's ECC engine if
+ *                                        activated
+ *   - pipelined + finish  + raw + write: do nothing
+ *   - pipelined + prepare + ecc + read: enable the controller's ECC engine if
+ *                                       deactivated
+ *   - pipelined + finish  + ecc + read: check the status, report any
+ *                                       error/bitflip
+ *   - pipelined + prepare + ecc + write: enable the controller's ECC engine if
+ *                                        deactivated
+ *   - pipelined + finish  + ecc + write: do nothing
+ *
+ * [ondie ECC engine]
+ *   - ondie + prepare + raw + read: send commands to disable the on-chip ECC
+ *                                   engine if activated
+ *   - ondie + finish  + raw + read: do nothing
+ *   - ondie + prepare + raw + write: send commands to disable the on-chip ECC
+ *                                    engine if activated
+ *   - ondie + finish  + raw + write: do nothing
+ *   - ondie + prepare + ecc + read: send commands to enable the on-chip ECC
+ *                                   engine if deactivated
+ *   - ondie + finish  + ecc + read: send commands to check the status, report
+ *                                   any error/bitflip
+ *   - ondie + prepare + ecc + write: send commands to enable the on-chip ECC
+ *                                    engine if deactivated
+ *   - ondie + finish  + ecc + write: do nothing
+ */
+
+#include <linux/module.h>
+#include <linux/mtd/nand.h>
+
+/**
+ * nand_ecc_init_ctx - Init the ECC engine context
+ * @nand: the NAND device
+ *
+ * On success, the caller is responsible of calling @nand_ecc_cleanup_ctx().
+ */
+int nand_ecc_init_ctx(struct nand_device *nand)
+{
+	if (!nand->ecc.engine->ops->init_ctx)
+		return 0;
+
+	return nand->ecc.engine->ops->init_ctx(nand);
+}
+EXPORT_SYMBOL(nand_ecc_init_ctx);
+
+/**
+ * nand_ecc_cleanup_ctx - Cleanup the ECC engine context
+ * @nand: the NAND device
+ */
+void nand_ecc_cleanup_ctx(struct nand_device *nand)
+{
+	if (nand->ecc.engine->ops->cleanup_ctx)
+		nand->ecc.engine->ops->cleanup_ctx(nand);
+}
+EXPORT_SYMBOL(nand_ecc_cleanup_ctx);
+
+/**
+ * nand_ecc_prepare_io_req - Prepare an I/O request
+ * @nand: the NAND device
+ * @req: the I/O request
+ */
+int nand_ecc_prepare_io_req(struct nand_device *nand,
+			    struct nand_page_io_req *req)
+{
+	if (!nand->ecc.engine->ops->prepare_io_req)
+		return 0;
+
+	return nand->ecc.engine->ops->prepare_io_req(nand, req);
+}
+EXPORT_SYMBOL(nand_ecc_prepare_io_req);
+
+/**
+ * nand_ecc_finish_io_req - Finish an I/O request
+ * @nand: the NAND device
+ * @req: the I/O request
+ */
+int nand_ecc_finish_io_req(struct nand_device *nand,
+			   struct nand_page_io_req *req)
+{
+	if (!nand->ecc.engine->ops->finish_io_req)
+		return 0;
+
+	return nand->ecc.engine->ops->finish_io_req(nand, req);
+}
+EXPORT_SYMBOL(nand_ecc_finish_io_req);
+
+/* Define default OOB placement schemes for large and small page devices */
+static int nand_ooblayout_ecc_sp(struct mtd_info *mtd, int section,
+				 struct mtd_oob_region *oobregion)
+{
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	unsigned int total_ecc_bytes = nand->ecc.ctx.total;
+
+	if (section > 1)
+		return -ERANGE;
+
+	if (!section) {
+		oobregion->offset = 0;
+		if (mtd->oobsize == 16)
+			oobregion->length = 4;
+		else
+			oobregion->length = 3;
+	} else {
+		if (mtd->oobsize == 8)
+			return -ERANGE;
+
+		oobregion->offset = 6;
+		oobregion->length = total_ecc_bytes - 4;
+	}
+
+	return 0;
+}
+
+static int nand_ooblayout_free_sp(struct mtd_info *mtd, int section,
+				  struct mtd_oob_region *oobregion)
+{
+	if (section > 1)
+		return -ERANGE;
+
+	if (mtd->oobsize == 16) {
+		if (section)
+			return -ERANGE;
+
+		oobregion->length = 8;
+		oobregion->offset = 8;
+	} else {
+		oobregion->length = 2;
+		if (!section)
+			oobregion->offset = 3;
+		else
+			oobregion->offset = 6;
+	}
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops nand_ooblayout_sp_ops = {
+	.ecc = nand_ooblayout_ecc_sp,
+	.free = nand_ooblayout_free_sp,
+};
+
+const struct mtd_ooblayout_ops *nand_get_small_page_ooblayout(void)
+{
+	return &nand_ooblayout_sp_ops;
+}
+EXPORT_SYMBOL_GPL(nand_get_small_page_ooblayout);
+
+static int nand_ooblayout_ecc_lp(struct mtd_info *mtd, int section,
+				 struct mtd_oob_region *oobregion)
+{
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	unsigned int total_ecc_bytes = nand->ecc.ctx.total;
+
+	if (section || !total_ecc_bytes)
+		return -ERANGE;
+
+	oobregion->length = total_ecc_bytes;
+	oobregion->offset = mtd->oobsize - oobregion->length;
+
+	return 0;
+}
+
+static int nand_ooblayout_free_lp(struct mtd_info *mtd, int section,
+				  struct mtd_oob_region *oobregion)
+{
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	unsigned int total_ecc_bytes = nand->ecc.ctx.total;
+
+	if (section)
+		return -ERANGE;
+
+	oobregion->length = mtd->oobsize - total_ecc_bytes - 2;
+	oobregion->offset = 2;
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops nand_ooblayout_lp_ops = {
+	.ecc = nand_ooblayout_ecc_lp,
+	.free = nand_ooblayout_free_lp,
+};
+
+const struct mtd_ooblayout_ops *nand_get_large_page_ooblayout(void)
+{
+	return &nand_ooblayout_lp_ops;
+}
+EXPORT_SYMBOL_GPL(nand_get_large_page_ooblayout);
+
+/*
+ * Support the old "large page" layout used for 1-bit Hamming ECC where ECC
+ * are placed at a fixed offset.
+ */
+static int nand_ooblayout_ecc_lp_hamming(struct mtd_info *mtd, int section,
+					 struct mtd_oob_region *oobregion)
+{
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	unsigned int total_ecc_bytes = nand->ecc.ctx.total;
+
+	if (section)
+		return -ERANGE;
+
+	switch (mtd->oobsize) {
+	case 64:
+		oobregion->offset = 40;
+		break;
+	case 128:
+		oobregion->offset = 80;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	oobregion->length = total_ecc_bytes;
+	if (oobregion->offset + oobregion->length > mtd->oobsize)
+		return -ERANGE;
+
+	return 0;
+}
+
+static int nand_ooblayout_free_lp_hamming(struct mtd_info *mtd, int section,
+					  struct mtd_oob_region *oobregion)
+{
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	unsigned int total_ecc_bytes = nand->ecc.ctx.total;
+	int ecc_offset = 0;
+
+	if (section < 0 || section > 1)
+		return -ERANGE;
+
+	switch (mtd->oobsize) {
+	case 64:
+		ecc_offset = 40;
+		break;
+	case 128:
+		ecc_offset = 80;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (section == 0) {
+		oobregion->offset = 2;
+		oobregion->length = ecc_offset - 2;
+	} else {
+		oobregion->offset = ecc_offset + total_ecc_bytes;
+		oobregion->length = mtd->oobsize - oobregion->offset;
+	}
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops nand_ooblayout_lp_hamming_ops = {
+	.ecc = nand_ooblayout_ecc_lp_hamming,
+	.free = nand_ooblayout_free_lp_hamming,
+};
+
+const struct mtd_ooblayout_ops *nand_get_large_page_hamming_ooblayout(void)
+{
+	return &nand_ooblayout_lp_hamming_ops;
+}
+EXPORT_SYMBOL_GPL(nand_get_large_page_hamming_ooblayout);
+
+static enum nand_ecc_engine_type
+of_get_nand_ecc_engine_type(struct device_node *np)
+{
+	struct device_node *eng_np;
+
+	if (of_property_read_bool(np, "nand-no-ecc-engine"))
+		return NAND_ECC_ENGINE_TYPE_NONE;
+
+	if (of_property_read_bool(np, "nand-use-soft-ecc-engine"))
+		return NAND_ECC_ENGINE_TYPE_SOFT;
+
+	eng_np = of_parse_phandle(np, "nand-ecc-engine", 0);
+	of_node_put(eng_np);
+
+	if (eng_np) {
+		if (eng_np == np)
+			return NAND_ECC_ENGINE_TYPE_ON_DIE;
+		else
+			return NAND_ECC_ENGINE_TYPE_ON_HOST;
+	}
+
+	return NAND_ECC_ENGINE_TYPE_INVALID;
+}
+
+static const char * const nand_ecc_placement[] = {
+	[NAND_ECC_PLACEMENT_OOB] = "oob",
+	[NAND_ECC_PLACEMENT_INTERLEAVED] = "interleaved",
+};
+
+static enum nand_ecc_placement of_get_nand_ecc_placement(struct device_node *np)
+{
+	enum nand_ecc_placement placement;
+	const char *pm;
+	int err;
+
+	err = of_property_read_string(np, "nand-ecc-placement", &pm);
+	if (!err) {
+		for (placement = NAND_ECC_PLACEMENT_OOB;
+		     placement < ARRAY_SIZE(nand_ecc_placement); placement++) {
+			if (!strcasecmp(pm, nand_ecc_placement[placement]))
+				return placement;
+		}
+	}
+
+	return NAND_ECC_PLACEMENT_UNKNOWN;
+}
+
+static const char * const nand_ecc_algos[] = {
+	[NAND_ECC_ALGO_HAMMING] = "hamming",
+	[NAND_ECC_ALGO_BCH] = "bch",
+	[NAND_ECC_ALGO_RS] = "rs",
+};
+
+static enum nand_ecc_algo of_get_nand_ecc_algo(struct device_node *np)
+{
+	enum nand_ecc_algo ecc_algo;
+	const char *pm;
+	int err;
+
+	err = of_property_read_string(np, "nand-ecc-algo", &pm);
+	if (!err) {
+		for (ecc_algo = NAND_ECC_ALGO_HAMMING;
+		     ecc_algo < ARRAY_SIZE(nand_ecc_algos);
+		     ecc_algo++) {
+			if (!strcasecmp(pm, nand_ecc_algos[ecc_algo]))
+				return ecc_algo;
+		}
+	}
+
+	return NAND_ECC_ALGO_UNKNOWN;
+}
+
+static int of_get_nand_ecc_step_size(struct device_node *np)
+{
+	int ret;
+	u32 val;
+
+	ret = of_property_read_u32(np, "nand-ecc-step-size", &val);
+	return ret ? ret : val;
+}
+
+static int of_get_nand_ecc_strength(struct device_node *np)
+{
+	int ret;
+	u32 val;
+
+	ret = of_property_read_u32(np, "nand-ecc-strength", &val);
+	return ret ? ret : val;
+}
+
+void of_get_nand_ecc_user_config(struct nand_device *nand)
+{
+	struct device_node *dn = nanddev_get_of_node(nand);
+	int strength, size;
+
+	nand->ecc.user_conf.engine_type = of_get_nand_ecc_engine_type(dn);
+	nand->ecc.user_conf.algo = of_get_nand_ecc_algo(dn);
+	nand->ecc.user_conf.placement = of_get_nand_ecc_placement(dn);
+
+	strength = of_get_nand_ecc_strength(dn);
+	if (strength >= 0)
+		nand->ecc.user_conf.strength = strength;
+
+	size = of_get_nand_ecc_step_size(dn);
+	if (size >= 0)
+		nand->ecc.user_conf.step_size = size;
+
+	if (of_property_read_bool(dn, "nand-ecc-maximize"))
+		nand->ecc.user_conf.flags |= NAND_ECC_MAXIMIZE_STRENGTH;
+}
+EXPORT_SYMBOL(of_get_nand_ecc_user_config);
+
+/**
+ * nand_ecc_is_strong_enough - Check if the chip configuration meets the
+ *                             datasheet requirements.
+ *
+ * @nand: Device to check
+ *
+ * If our configuration corrects A bits per B bytes and the minimum
+ * required correction level is X bits per Y bytes, then we must ensure
+ * both of the following are true:
+ *
+ * (1) A / B >= X / Y
+ * (2) A >= X
+ *
+ * Requirement (1) ensures we can correct for the required bitflip density.
+ * Requirement (2) ensures we can correct even when all bitflips are clumped
+ * in the same sector.
+ */
+bool nand_ecc_is_strong_enough(struct nand_device *nand)
+{
+	const struct nand_ecc_props *reqs = nanddev_get_ecc_requirements(nand);
+	const struct nand_ecc_props *conf = nanddev_get_ecc_conf(nand);
+	struct mtd_info *mtd = nanddev_to_mtd(nand);
+	int corr, ds_corr;
+
+	if (conf->step_size == 0 || reqs->step_size == 0)
+		/* Not enough information */
+		return true;
+
+	/*
+	 * We get the number of corrected bits per page to compare
+	 * the correction density.
+	 */
+	corr = (mtd->writesize * conf->strength) / conf->step_size;
+	ds_corr = (mtd->writesize * reqs->strength) / reqs->step_size;
+
+	return corr >= ds_corr && conf->strength >= reqs->strength;
+}
+EXPORT_SYMBOL(nand_ecc_is_strong_enough);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Miquel Raynal <miquel.raynal@bootlin.com>");
+MODULE_DESCRIPTION("Generic ECC engine");
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index e754a6fc8a4b..8cf5bdbea782 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -127,6 +127,40 @@ struct nand_page_io_req {
 	int mode;
 };
 
+const struct mtd_ooblayout_ops *nand_get_small_page_ooblayout(void);
+const struct mtd_ooblayout_ops *nand_get_large_page_ooblayout(void);
+const struct mtd_ooblayout_ops *nand_get_large_page_hamming_ooblayout(void);
+
+/**
+ * enum nand_ecc_engine_type - NAND ECC engine type
+ * @NAND_ECC_ENGINE_TYPE_INVALID: Invalid value
+ * @NAND_ECC_ENGINE_TYPE_NONE: No ECC correction
+ * @NAND_ECC_ENGINE_TYPE_SOFT: Software ECC correction
+ * @NAND_ECC_ENGINE_TYPE_ON_HOST: On host hardware ECC correction
+ * @NAND_ECC_ENGINE_TYPE_ON_DIE: On chip hardware ECC correction
+ */
+enum nand_ecc_engine_type {
+	NAND_ECC_ENGINE_TYPE_INVALID,
+	NAND_ECC_ENGINE_TYPE_NONE,
+	NAND_ECC_ENGINE_TYPE_SOFT,
+	NAND_ECC_ENGINE_TYPE_ON_HOST,
+	NAND_ECC_ENGINE_TYPE_ON_DIE,
+};
+
+/**
+ * enum nand_ecc_placement - NAND ECC bytes placement
+ * @NAND_ECC_PLACEMENT_UNKNOWN: The actual position of the ECC bytes is unknown
+ * @NAND_ECC_PLACEMENT_OOB: The ECC bytes are located in the OOB area
+ * @NAND_ECC_PLACEMENT_INTERLEAVED: Syndrome layout, there are ECC bytes
+ *                                  interleaved with regular data in the main
+ *                                  area
+ */
+enum nand_ecc_placement {
+	NAND_ECC_PLACEMENT_UNKNOWN,
+	NAND_ECC_PLACEMENT_OOB,
+	NAND_ECC_PLACEMENT_INTERLEAVED,
+};
+
 /**
  * enum nand_ecc_algo - NAND ECC algorithm
  * @NAND_ECC_ALGO_UNKNOWN: Unknown algorithm
@@ -143,16 +177,27 @@ enum nand_ecc_algo {
 
 /**
  * struct nand_ecc_props - NAND ECC properties
+ * @engine_type: ECC engine type
+ * @placement: OOB placement (if relevant)
+ * @algo: ECC algorithm (if relevant)
  * @strength: ECC strength
  * @step_size: Number of bytes per step
+ * @flags: Misc properties
  */
 struct nand_ecc_props {
+	enum nand_ecc_engine_type engine_type;
+	enum nand_ecc_placement placement;
+	enum nand_ecc_algo algo;
 	unsigned int strength;
 	unsigned int step_size;
+	unsigned int flags;
 };
 
 #define NAND_ECCREQ(str, stp) { .strength = (str), .step_size = (stp) }
 
+/* NAND ECC misc flags */
+#define NAND_ECC_MAXIMIZE_STRENGTH BIT(0)
+
 /**
  * struct nand_bbt - bad block table object
  * @cache: in memory BBT cache
@@ -183,6 +228,75 @@ struct nand_ops {
 	bool (*isbad)(struct nand_device *nand, const struct nand_pos *pos);
 };
 
+/**
+ * struct nand_ecc_context - Context for the ECC engine
+ * @conf: basic ECC engine parameters
+ * @total: total number of bytes used for storing ECC codes, this is used by
+ *         generic OOB layouts
+ * @priv: ECC engine driver private data
+ */
+struct nand_ecc_context {
+	struct nand_ecc_props conf;
+	unsigned int total;
+	void *priv;
+};
+
+/**
+ * struct nand_ecc_engine_ops - ECC engine operations
+ * @init_ctx: given a desired user configuration for the pointed NAND device,
+ *            requests the ECC engine driver to setup a configuration with
+ *            values it supports.
+ * @cleanup_ctx: clean the context initialized by @init_ctx.
+ * @prepare_io_req: is called before reading/writing a page to prepare the I/O
+ *                  request to be performed with ECC correction.
+ * @finish_io_req: is called after reading/writing a page to terminate the I/O
+ *                 request and ensure proper ECC correction.
+ */
+struct nand_ecc_engine_ops {
+	int (*init_ctx)(struct nand_device *nand);
+	void (*cleanup_ctx)(struct nand_device *nand);
+	int (*prepare_io_req)(struct nand_device *nand,
+			      struct nand_page_io_req *req);
+	int (*finish_io_req)(struct nand_device *nand,
+			     struct nand_page_io_req *req);
+};
+
+/**
+ * struct nand_ecc_engine - ECC engine abstraction for NAND devices
+ * @ops: ECC engine operations
+ */
+struct nand_ecc_engine {
+	struct nand_ecc_engine_ops *ops;
+};
+
+void of_get_nand_ecc_user_config(struct nand_device *nand);
+int nand_ecc_init_ctx(struct nand_device *nand);
+void nand_ecc_cleanup_ctx(struct nand_device *nand);
+int nand_ecc_prepare_io_req(struct nand_device *nand,
+			    struct nand_page_io_req *req);
+int nand_ecc_finish_io_req(struct nand_device *nand,
+			   struct nand_page_io_req *req);
+bool nand_ecc_is_strong_enough(struct nand_device *nand);
+
+/**
+ * struct nand_ecc - Information relative to the ECC
+ * @defaults: Default values, depend on the underlying subsystem
+ * @requirements: ECC requirements from the NAND chip perspective
+ * @user_conf: User desires in terms of ECC parameters
+ * @ctx: ECC context for the ECC engine, derived from the device @requirements
+ *       the @user_conf and the @defaults
+ * @ondie_engine: On-die ECC engine reference, if any
+ * @engine: ECC engine actually bound
+ */
+struct nand_ecc {
+	struct nand_ecc_props defaults;
+	struct nand_ecc_props requirements;
+	struct nand_ecc_props user_conf;
+	struct nand_ecc_context ctx;
+	struct nand_ecc_engine *ondie_engine;
+	struct nand_ecc_engine *engine;
+};
+
 /**
  * struct nand_device - NAND device
  * @mtd: MTD instance attached to the NAND device
-- 
cgit v1.2.3


From 0f50257f5348751bf5b93d052885de23b2367cd2 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sun, 30 Aug 2020 21:16:55 -0700
Subject: dma-buf: fix kernel-doc warning in <linux/dma-buf.h>
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix kernel-doc warning in <linux/dma-buf.h>:

../include/linux/dma-buf.h:330: warning: Function parameter or member 'name_lock' not described in 'dma_buf'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Sumit Semwal <sumit.semwal@linaro.org>
Cc: Gustavo Padovan <gustavo@padovan.org>
Cc: Christian König <christian.koenig@amd.com>
Cc: linux-media@vger.kernel.org
Cc: dri-devel@lists.freedesktop.org
Reviewed-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/388523/
Signed-off-by: Christian König <christian.koenig@amd.com>
---
 include/linux/dma-buf.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index a2ca294eaebe..957b398d30e5 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -283,6 +283,7 @@ struct dma_buf_ops {
  * @exp_name: name of the exporter; useful for debugging.
  * @name: userspace-provided name; useful for accounting and debugging,
  *        protected by @resv.
+ * @name_lock: spinlock to protect name access
  * @owner: pointer to exporter module; used for refcounting when exporter is a
  *         kernel module.
  * @list_node: node for dma_buf accounting and debugging.
@@ -311,7 +312,7 @@ struct dma_buf {
 	void *vmap_ptr;
 	const char *exp_name;
 	const char *name;
-	spinlock_t name_lock; /* spinlock to protect name access */
+	spinlock_t name_lock;
 	struct module *owner;
 	struct list_head list_node;
 	void *priv;
-- 
cgit v1.2.3


From f4ad06f2bb8476548b08f89919ee65abc4e40212 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 1 Sep 2020 17:57:42 +0200
Subject: block: rename bd_invalidated

Replace bd_invalidate with a new BDEV_NEED_PART_SCAN flag in a bd_flags
variable to better describe the condition.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/genhd.c             |  2 +-
 drivers/block/nbd.c       |  8 ++++----
 fs/block_dev.c            | 10 +++++-----
 include/linux/blk_types.h |  4 +++-
 4 files changed, 13 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/block/genhd.c b/block/genhd.c
index 5fc6d82e6c68..a36be970b767 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -732,7 +732,7 @@ static void register_disk(struct device *parent, struct gendisk *disk,
 	if (!bdev)
 		goto exit;
 
-	bdev->bd_invalidated = 1;
+	set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
 	err = blkdev_get(bdev, FMODE_READ, NULL);
 	if (err < 0)
 		goto exit;
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index a54f2d155a31..15eed210feef 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -315,7 +315,7 @@ static void nbd_size_update(struct nbd_device *nbd)
 			bd_set_nr_sectors(bdev, nr_sectors);
 			set_blocksize(bdev, config->blksize);
 		} else
-			bdev->bd_invalidated = 1;
+			set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
 		bdput(bdev);
 	}
 	kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE);
@@ -1322,7 +1322,7 @@ static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *b
 		return ret;
 
 	if (max_part)
-		bdev->bd_invalidated = 1;
+		set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
 	mutex_unlock(&nbd->config_lock);
 	ret = wait_event_interruptible(config->recv_wq,
 					 atomic_read(&config->recv_threads) == 0);
@@ -1500,9 +1500,9 @@ static int nbd_open(struct block_device *bdev, fmode_t mode)
 		refcount_set(&nbd->config_refs, 1);
 		refcount_inc(&nbd->refs);
 		mutex_unlock(&nbd->config_lock);
-		bdev->bd_invalidated = 1;
+		set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
 	} else if (nbd_disconnected(nbd->config)) {
-		bdev->bd_invalidated = 1;
+		set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
 	}
 out:
 	mutex_unlock(&nbd_index_mutex);
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 7e32398608c6..1e6441dbe840 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -881,7 +881,7 @@ struct block_device *bdget(dev_t dev)
 		bdev->bd_super = NULL;
 		bdev->bd_inode = inode;
 		bdev->bd_part_count = 0;
-		bdev->bd_invalidated = 0;
+		bdev->bd_flags = 0;
 		inode->i_mode = S_IFBLK;
 		inode->i_rdev = dev;
 		inode->i_bdev = bdev;
@@ -1365,7 +1365,7 @@ int check_disk_change(struct block_device *bdev)
 	if (__invalidate_device(bdev, true))
 		pr_warn("VFS: busy inodes on changed media %s\n",
 			disk->disk_name);
-	bdev->bd_invalidated = 1;
+	set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
 	if (bdops->revalidate_disk)
 		bdops->revalidate_disk(bdev->bd_disk);
 	return 1;
@@ -1390,7 +1390,7 @@ int bdev_disk_changed(struct block_device *bdev, bool invalidate)
 
 	lockdep_assert_held(&bdev->bd_mutex);
 
-	bdev->bd_invalidated = 0;
+	clear_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
 
 rescan:
 	ret = blk_drop_partitions(bdev);
@@ -1514,7 +1514,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder,
 			 * The latter is necessary to prevent ghost
 			 * partitions on a removed medium.
 			 */
-			if (bdev->bd_invalidated &&
+			if (test_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags) &&
 			    (!ret || ret == -ENOMEDIUM))
 				bdev_disk_changed(bdev, ret == -ENOMEDIUM);
 
@@ -1544,7 +1544,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder,
 			if (bdev->bd_disk->fops->open)
 				ret = bdev->bd_disk->fops->open(bdev, mode);
 			/* the same as first opener case, read comment there */
-			if (bdev->bd_invalidated &&
+			if (test_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags) &&
 			    (!ret || ret == -ENOMEDIUM))
 				bdev_disk_changed(bdev, ret == -ENOMEDIUM);
 			if (ret)
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 59d9150165c4..6ffa783e1633 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -19,6 +19,8 @@ struct cgroup_subsys_state;
 typedef void (bio_end_io_t) (struct bio *);
 struct bio_crypt_ctx;
 
+#define BDEV_NEED_PART_SCAN		0
+
 struct block_device {
 	dev_t			bd_dev;
 	int			bd_openers;
@@ -37,7 +39,7 @@ struct block_device {
 	struct hd_struct *	bd_part;
 	/* number of times partitions within this device have been opened. */
 	unsigned		bd_part_count;
-	int			bd_invalidated;
+	unsigned long		bd_flags;
 	spinlock_t		bd_size_lock; /* for bd_inode->i_size updates */
 	struct gendisk *	bd_disk;
 	struct backing_dev_info *bd_bdi;
-- 
cgit v1.2.3


From 659e56ba864d37b7ee0a49cd432205b2a5ca815e Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 1 Sep 2020 17:57:43 +0200
Subject: block: add a new revalidate_disk_size helper

revalidate_disk is a relative awkward helper for driver use, as it first
calls an optional driver method and then updates the block device size,
while most callers either don't need the method call at all, or want to
keep state between the caller and the called method.

Add a revalidate_disk_size helper that just performs the update of the
block device size from the gendisk one, and switch all drivers that do
not implement ->revalidate_disk to use the new helper instead of
revalidate_disk()

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Acked-by: Song Liu <song@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/rbd.c           |  2 +-
 drivers/block/rnbd/rnbd-clt.c | 10 ++--------
 drivers/block/virtio_blk.c    |  2 +-
 drivers/block/zram/zram_drv.c |  4 ++--
 drivers/md/dm-raid.c          |  2 +-
 drivers/md/md-cluster.c       |  6 +++---
 drivers/md/md-linear.c        |  2 +-
 drivers/md/md.c               | 10 +++++-----
 fs/block_dev.c                | 42 +++++++++++++++++++++++++++++-------------
 include/linux/genhd.h         |  1 +
 10 files changed, 46 insertions(+), 35 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 011539039693..5d3923c0997c 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -4921,7 +4921,7 @@ static void rbd_dev_update_size(struct rbd_device *rbd_dev)
 		size = (sector_t)rbd_dev->mapping.size / SECTOR_SIZE;
 		dout("setting size to %llu sectors", (unsigned long long)size);
 		set_capacity(rbd_dev->disk, size);
-		revalidate_disk(rbd_dev->disk);
+		revalidate_disk_size(rbd_dev->disk, true);
 	}
 }
 
diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c
index cc6a4e2587ae..157538fc8be5 100644
--- a/drivers/block/rnbd/rnbd-clt.c
+++ b/drivers/block/rnbd/rnbd-clt.c
@@ -102,18 +102,12 @@ static int rnbd_clt_set_dev_attr(struct rnbd_clt_dev *dev,
 static int rnbd_clt_change_capacity(struct rnbd_clt_dev *dev,
 				    size_t new_nsectors)
 {
-	int err = 0;
-
 	rnbd_clt_info(dev, "Device size changed from %zu to %zu sectors\n",
 		       dev->nsectors, new_nsectors);
 	dev->nsectors = new_nsectors;
 	set_capacity(dev->gd, dev->nsectors);
-	err = revalidate_disk(dev->gd);
-	if (err)
-		rnbd_clt_err(dev,
-			      "Failed to change device size from %zu to %zu, err: %d\n",
-			      dev->nsectors, new_nsectors, err);
-	return err;
+	revalidate_disk_size(dev->gd, true);
+	return 0;
 }
 
 static int process_msg_open_rsp(struct rnbd_clt_dev *dev,
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index ca63a41059d6..a314b9382442 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -598,7 +598,7 @@ static void virtblk_update_cache_mode(struct virtio_device *vdev)
 	struct virtio_blk *vblk = vdev->priv;
 
 	blk_queue_write_cache(vblk->disk->queue, writeback, false);
-	revalidate_disk(vblk->disk);
+	revalidate_disk_size(vblk->disk, true);
 }
 
 static const char *const virtblk_cache_types[] = {
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 9100ac36670a..a356275605b1 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -1739,7 +1739,7 @@ static ssize_t disksize_store(struct device *dev,
 	zram->disksize = disksize;
 	set_capacity(zram->disk, zram->disksize >> SECTOR_SHIFT);
 
-	revalidate_disk(zram->disk);
+	revalidate_disk_size(zram->disk, true);
 	up_write(&zram->init_lock);
 
 	return len;
@@ -1786,7 +1786,7 @@ static ssize_t reset_store(struct device *dev,
 	/* Make sure all the pending I/O are finished */
 	fsync_bdev(bdev);
 	zram_reset_device(zram);
-	revalidate_disk(zram->disk);
+	revalidate_disk_size(zram->disk, true);
 	bdput(bdev);
 
 	mutex_lock(&bdev->bd_mutex);
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 8d2b835d7a10..56b723d012ac 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -701,7 +701,7 @@ static void rs_set_capacity(struct raid_set *rs)
 	struct gendisk *gendisk = dm_disk(dm_table_get_md(rs->ti->table));
 
 	set_capacity(gendisk, rs->md.array_sectors);
-	revalidate_disk(gendisk);
+	revalidate_disk_size(gendisk, true);
 }
 
 /*
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index d50737ec4039..0580b51a156a 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -582,7 +582,7 @@ static int process_recvd_msg(struct mddev *mddev, struct cluster_msg *msg)
 		break;
 	case CHANGE_CAPACITY:
 		set_capacity(mddev->gendisk, mddev->array_sectors);
-		revalidate_disk(mddev->gendisk);
+		revalidate_disk_size(mddev->gendisk, true);
 		break;
 	case RESYNCING:
 		set_bit(MD_RESYNCING_REMOTE, &mddev->recovery);
@@ -1296,12 +1296,12 @@ static void update_size(struct mddev *mddev, sector_t old_dev_sectors)
 			pr_err("%s:%d: failed to send CHANGE_CAPACITY msg\n",
 			       __func__, __LINE__);
 		set_capacity(mddev->gendisk, mddev->array_sectors);
-		revalidate_disk(mddev->gendisk);
+		revalidate_disk_size(mddev->gendisk, true);
 	} else {
 		/* revert to previous sectors */
 		ret = mddev->pers->resize(mddev, old_dev_sectors);
 		if (!ret)
-			revalidate_disk(mddev->gendisk);
+			revalidate_disk_size(mddev->gendisk, true);
 		ret = __sendmsg(cinfo, &cmsg);
 		if (ret)
 			pr_err("%s:%d: failed to send METADATA_UPDATED msg\n",
diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c
index c2ae9125c4c3..5ab22069b5be 100644
--- a/drivers/md/md-linear.c
+++ b/drivers/md/md-linear.c
@@ -202,7 +202,7 @@ static int linear_add(struct mddev *mddev, struct md_rdev *rdev)
 	md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
 	set_capacity(mddev->gendisk, mddev->array_sectors);
 	mddev_resume(mddev);
-	revalidate_disk(mddev->gendisk);
+	revalidate_disk_size(mddev->gendisk, true);
 	kfree_rcu(oldconf, rcu);
 	return 0;
 }
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 607278207023..9562ef598ae1 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5358,7 +5358,7 @@ array_size_store(struct mddev *mddev, const char *buf, size_t len)
 		mddev->array_sectors = sectors;
 		if (mddev->pers) {
 			set_capacity(mddev->gendisk, mddev->array_sectors);
-			revalidate_disk(mddev->gendisk);
+			revalidate_disk_size(mddev->gendisk, true);
 		}
 	}
 	mddev_unlock(mddev);
@@ -6109,7 +6109,7 @@ int do_md_run(struct mddev *mddev)
 	md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
 
 	set_capacity(mddev->gendisk, mddev->array_sectors);
-	revalidate_disk(mddev->gendisk);
+	revalidate_disk_size(mddev->gendisk, true);
 	clear_bit(MD_NOT_READY, &mddev->flags);
 	mddev->changed = 1;
 	kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE);
@@ -6427,7 +6427,7 @@ static int do_md_stop(struct mddev *mddev, int mode,
 		set_capacity(disk, 0);
 		mutex_unlock(&mddev->open_mutex);
 		mddev->changed = 1;
-		revalidate_disk(disk);
+		revalidate_disk_size(disk, true);
 
 		if (mddev->ro)
 			mddev->ro = 0;
@@ -7259,7 +7259,7 @@ static int update_size(struct mddev *mddev, sector_t num_sectors)
 			md_cluster_ops->update_size(mddev, old_dev_sectors);
 		else if (mddev->queue) {
 			set_capacity(mddev->gendisk, mddev->array_sectors);
-			revalidate_disk(mddev->gendisk);
+			revalidate_disk_size(mddev->gendisk, true);
 		}
 	}
 	return rv;
@@ -9018,7 +9018,7 @@ void md_do_sync(struct md_thread *thread)
 		mddev_unlock(mddev);
 		if (!mddev_is_clustered(mddev)) {
 			set_capacity(mddev->gendisk, mddev->array_sectors);
-			revalidate_disk(mddev->gendisk);
+			revalidate_disk_size(mddev->gendisk, true);
 		}
 	}
 
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 1e6441dbe840..9bfe37f394bd 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1311,6 +1311,34 @@ static void check_disk_size_change(struct gendisk *disk,
 	}
 }
 
+/**
+ * revalidate_disk_size - checks for disk size change and adjusts bdev size.
+ * @disk: struct gendisk to check
+ * @verbose: if %true log a message about a size change if there is any
+ *
+ * This routine checks to see if the bdev size does not match the disk size
+ * and adjusts it if it differs. When shrinking the bdev size, its all caches
+ * are freed.
+ */
+void revalidate_disk_size(struct gendisk *disk, bool verbose)
+{
+	struct block_device *bdev;
+
+	/*
+	 * Hidden disks don't have associated bdev so there's no point in
+	 * revalidating them.
+	 */
+	if (disk->flags & GENHD_FL_HIDDEN)
+		return;
+
+	bdev = bdget_disk(disk, 0);
+	if (bdev) {
+		check_disk_size_change(disk, bdev, verbose);
+		bdput(bdev);
+	}
+}
+EXPORT_SYMBOL(revalidate_disk_size);
+
 /**
  * revalidate_disk - wrapper for lower-level driver's revalidate_disk call-back
  * @disk: struct gendisk to be revalidated
@@ -1325,19 +1353,7 @@ int revalidate_disk(struct gendisk *disk)
 
 	if (disk->fops->revalidate_disk)
 		ret = disk->fops->revalidate_disk(disk);
-
-	/*
-	 * Hidden disks don't have associated bdev so there's no point in
-	 * revalidating it.
-	 */
-	if (!(disk->flags & GENHD_FL_HIDDEN)) {
-		struct block_device *bdev = bdget_disk(disk, 0);
-
-		if (bdev) {
-			check_disk_size_change(disk, bdev, ret == 0);
-			bdput(bdev);
-		}
-	}
+	revalidate_disk_size(disk, ret == 0);
 	return ret;
 }
 EXPORT_SYMBOL(revalidate_disk);
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 9ea2ca31c278..f76c8baf6b7d 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -371,6 +371,7 @@ int register_blkdev(unsigned int major, const char *name);
 void unregister_blkdev(unsigned int major, const char *name);
 
 int revalidate_disk(struct gendisk *disk);
+void revalidate_disk_size(struct gendisk *disk, bool verbose);
 int check_disk_change(struct block_device *bdev);
 int __invalidate_device(struct block_device *bdev, bool kill_dirty);
 void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors);
-- 
cgit v1.2.3


From b8086d3f5a0e88b1912d55a158b8a6a43ad6604b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 1 Sep 2020 17:57:44 +0200
Subject: block: use revalidate_disk_size in set_capacity_revalidate_and_notify

Only virtio_blk and xen-blkfront set the revalidate argument to true,
and both do not implement the ->revalidate_disk method.  So switch
to the helper that just updates the size instead.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/genhd.c         | 7 +++----
 include/linux/genhd.h | 4 ++--
 2 files changed, 5 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/block/genhd.c b/block/genhd.c
index a36be970b767..081f1039d936 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -50,14 +50,13 @@ static void disk_release_events(struct gendisk *disk);
  * zero and will not be set to zero
  */
 void set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size,
-					bool revalidate)
+					bool update_bdev)
 {
 	sector_t capacity = get_capacity(disk);
 
 	set_capacity(disk, size);
-
-	if (revalidate)
-		revalidate_disk(disk);
+	if (update_bdev)
+		revalidate_disk_size(disk, true);
 
 	if (capacity != size && capacity != 0 && size != 0) {
 		char *envp[] = { "RESIZE=1", NULL };
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index f76c8baf6b7d..02a73198b289 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -313,8 +313,8 @@ static inline int get_disk_ro(struct gendisk *disk)
 extern void disk_block_events(struct gendisk *disk);
 extern void disk_unblock_events(struct gendisk *disk);
 extern void disk_flush_events(struct gendisk *disk, unsigned int mask);
-extern void set_capacity_revalidate_and_notify(struct gendisk *disk,
-			sector_t size, bool revalidate);
+void set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size,
+		bool update_bdev);
 extern unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask);
 
 /* drivers/char/random.c */
-- 
cgit v1.2.3


From de09077c89183cbc627d9393706343662da7f5a3 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 1 Sep 2020 17:57:48 +0200
Subject: block: remove revalidate_disk()

Remove the now unused helper.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Acked-by: Song Liu <song@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/md.h       |  2 +-
 fs/block_dev.c        | 19 -------------------
 include/linux/genhd.h |  1 -
 3 files changed, 1 insertion(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/md/md.h b/drivers/md/md.h
index d9c4e6b7e939..f9e2ccdd22c4 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -397,7 +397,7 @@ struct mddev {
 	 * These locks are separate due to conflicting interactions
 	 * with bdev->bd_mutex.
 	 * Lock ordering is:
-	 *  reconfig_mutex -> bd_mutex : e.g. do_md_run -> revalidate_disk
+	 *  reconfig_mutex -> bd_mutex
 	 *  bd_mutex -> open_mutex:  e.g. __blkdev_get -> md_open
 	 */
 	struct mutex			open_mutex;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 9bfe37f394bd..9cb205405f9d 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1339,25 +1339,6 @@ void revalidate_disk_size(struct gendisk *disk, bool verbose)
 }
 EXPORT_SYMBOL(revalidate_disk_size);
 
-/**
- * revalidate_disk - wrapper for lower-level driver's revalidate_disk call-back
- * @disk: struct gendisk to be revalidated
- *
- * This routine is a wrapper for lower-level driver's revalidate_disk
- * call-backs.  It is used to do common pre and post operations needed
- * for all revalidate_disk operations.
- */
-int revalidate_disk(struct gendisk *disk)
-{
-	int ret = 0;
-
-	if (disk->fops->revalidate_disk)
-		ret = disk->fops->revalidate_disk(disk);
-	revalidate_disk_size(disk, ret == 0);
-	return ret;
-}
-EXPORT_SYMBOL(revalidate_disk);
-
 /*
  * This routine checks whether a removable media has been changed,
  * and invalidates all buffer-cache-entries in that case. This
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 02a73198b289..c618b27292fc 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -370,7 +370,6 @@ extern void blk_unregister_region(dev_t devt, unsigned long range);
 int register_blkdev(unsigned int major, const char *name);
 void unregister_blkdev(unsigned int major, const char *name);
 
-int revalidate_disk(struct gendisk *disk);
 void revalidate_disk_size(struct gendisk *disk, bool verbose);
 int check_disk_change(struct block_device *bdev);
 int __invalidate_device(struct block_device *bdev, bool kill_dirty);
-- 
cgit v1.2.3


From 21f8e4828c44da39b0670c5d99d5728b739542a1 Mon Sep 17 00:00:00 2001
From: Dmitry Osipenko <digetx@gmail.com>
Date: Wed, 2 Sep 2020 17:18:43 +0300
Subject: regmap: Add can_sleep configuration option

Regmap can't sleep if spinlock is used for the locking protection.
This patch fixes regression caused by a previous commit that switched
regmap to use fsleep() and this broke Amlogic S922X platform.

This patch adds new configuration option for regmap users, allowing to
specify whether regmap operations can sleep and assuming that sleep is
allowed if mutex is used for the regmap locking protection.

Reported-by: Marek Szyprowski <m.szyprowski@samsung.com>
Fixes: 2b32d2f7ce0a ("regmap: Use flexible sleep")
Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Tested-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20200902141843.6591-1-digetx@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/base/regmap/internal.h |  3 +++
 drivers/base/regmap/regmap.c   | 19 +++++++++++++++----
 include/linux/regmap.h         |  3 +++
 3 files changed, 21 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h
index 3d80c4b43f72..8a59359e145f 100644
--- a/drivers/base/regmap/internal.h
+++ b/drivers/base/regmap/internal.h
@@ -161,6 +161,9 @@ struct regmap {
 	void *selector_work_buf;	/* Scratch buffer used for selector */
 
 	struct hwspinlock *hwlock;
+
+	/* if set, the regmap core can sleep */
+	bool can_sleep;
 };
 
 struct regcache_ops {
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index a417cb1a11dc..2807e544658e 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -697,11 +697,13 @@ struct regmap *__regmap_init(struct device *dev,
 
 	if (config->disable_locking) {
 		map->lock = map->unlock = regmap_lock_unlock_none;
+		map->can_sleep = config->can_sleep;
 		regmap_debugfs_disable(map);
 	} else if (config->lock && config->unlock) {
 		map->lock = config->lock;
 		map->unlock = config->unlock;
 		map->lock_arg = config->lock_arg;
+		map->can_sleep = config->can_sleep;
 	} else if (config->use_hwlock) {
 		map->hwlock = hwspin_lock_request_specific(config->hwlock_id);
 		if (!map->hwlock) {
@@ -737,6 +739,7 @@ struct regmap *__regmap_init(struct device *dev,
 			mutex_init(&map->mutex);
 			map->lock = regmap_lock_mutex;
 			map->unlock = regmap_unlock_mutex;
+			map->can_sleep = true;
 			lockdep_set_class_and_name(&map->mutex,
 						   lock_key, lock_name);
 		}
@@ -2230,8 +2233,12 @@ static int _regmap_range_multi_paged_reg_write(struct regmap *map,
 				if (ret != 0)
 					return ret;
 
-				if (regs[i].delay_us)
-					fsleep(regs[i].delay_us);
+				if (regs[i].delay_us) {
+					if (map->can_sleep)
+						fsleep(regs[i].delay_us);
+					else
+						udelay(regs[i].delay_us);
+				}
 
 				base += n;
 				n = 0;
@@ -2267,8 +2274,12 @@ static int _regmap_multi_reg_write(struct regmap *map,
 			if (ret != 0)
 				return ret;
 
-			if (regs[i].delay_us)
-				fsleep(regs[i].delay_us);
+			if (regs[i].delay_us) {
+				if (map->can_sleep)
+					fsleep(regs[i].delay_us);
+				else
+					udelay(regs[i].delay_us);
+			}
 		}
 		return 0;
 	}
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index d865d8fea535..0c49d59168b5 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -342,6 +342,7 @@ typedef void (*regmap_unlock)(void *);
  * @hwlock_id: Specify the hardware spinlock id.
  * @hwlock_mode: The hardware spinlock mode, should be HWLOCK_IRQSTATE,
  *		 HWLOCK_IRQ or 0.
+ * @can_sleep: Optional, specifies whether regmap operations can sleep.
  */
 struct regmap_config {
 	const char *name;
@@ -398,6 +399,8 @@ struct regmap_config {
 	bool use_hwlock;
 	unsigned int hwlock_id;
 	unsigned int hwlock_mode;
+
+	bool can_sleep;
 };
 
 /**
-- 
cgit v1.2.3


From 7547dbd3b198f309aaff54e3528898a8a196faff Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@ti.com>
Date: Fri, 28 Aug 2020 14:05:07 +0300
Subject: dmaengine: Mark dma_request_slave_channel() deprecated

New drivers should use dma_request_chan() instead
dma_request_slave_channel()

dma_request_slave_channel() is a simple wrapper for dma_request_chan()
eating up the error code for channel request failure and makes deferred
probing impossible.

Move the dma_request_slave_channel() into the header as inline function,
mark it as deprecated.

Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20200828110507.22407-1-peter.ujfalusi@ti.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/dmaengine.c   | 18 ------------------
 include/linux/dmaengine.h | 15 +++++++++------
 2 files changed, 9 insertions(+), 24 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index a53e71d2bbd4..ac8ef6cf7626 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -871,24 +871,6 @@ found:
 }
 EXPORT_SYMBOL_GPL(dma_request_chan);
 
-/**
- * dma_request_slave_channel - try to allocate an exclusive slave channel
- * @dev:	pointer to client device structure
- * @name:	slave channel name
- *
- * Returns pointer to appropriate DMA channel on success or NULL.
- */
-struct dma_chan *dma_request_slave_channel(struct device *dev,
-					   const char *name)
-{
-	struct dma_chan *ch = dma_request_chan(dev, name);
-	if (IS_ERR(ch))
-		return NULL;
-
-	return ch;
-}
-EXPORT_SYMBOL_GPL(dma_request_slave_channel);
-
 /**
  * dma_request_chan_by_mask - allocate a channel satisfying certain capabilities
  * @mask:	capabilities that the channel must satisfy
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 011371b7f081..dd357a747780 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -1472,7 +1472,6 @@ void dma_issue_pending_all(void);
 struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask,
 				       dma_filter_fn fn, void *fn_param,
 				       struct device_node *np);
-struct dma_chan *dma_request_slave_channel(struct device *dev, const char *name);
 
 struct dma_chan *dma_request_chan(struct device *dev, const char *name);
 struct dma_chan *dma_request_chan_by_mask(const dma_cap_mask_t *mask);
@@ -1502,11 +1501,6 @@ static inline struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask,
 {
 	return NULL;
 }
-static inline struct dma_chan *dma_request_slave_channel(struct device *dev,
-							 const char *name)
-{
-	return NULL;
-}
 static inline struct dma_chan *dma_request_chan(struct device *dev,
 						const char *name)
 {
@@ -1575,6 +1569,15 @@ void dma_run_dependencies(struct dma_async_tx_descriptor *tx);
 #define dma_request_channel(mask, x, y) \
 	__dma_request_channel(&(mask), x, y, NULL)
 
+/* Deprecated, please use dma_request_chan() directly */
+static inline struct dma_chan * __deprecated
+dma_request_slave_channel(struct device *dev, const char *name)
+{
+	struct dma_chan *ch = dma_request_chan(dev, name);
+
+	return IS_ERR(ch) ? NULL : ch;
+}
+
 static inline struct dma_chan
 *dma_request_slave_channel_compat(const dma_cap_mask_t mask,
 				  dma_filter_fn fn, void *fn_param,
-- 
cgit v1.2.3


From 63642595a78da42f841fabcc3f309f4c1362dc40 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Mon, 31 Aug 2020 21:43:17 +0800
Subject: soundwire: add definition for maximum number of ports

A Device may have at most 15 physical ports (DP0, DP1..DP14).

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Rander Wang <rander.wang@linux.intel.com>
Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Link: https://lore.kernel.org/r/20200831134318.11443-3-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/soundwire/sdw.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 76052f12c9f7..0aa4c6af7554 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -38,7 +38,8 @@ struct sdw_slave;
 #define SDW_FRAME_CTRL_BITS		48
 #define SDW_MAX_DEVICES			11
 
-#define SDW_VALID_PORT_RANGE(n)		((n) <= 14 && (n) >= 1)
+#define SDW_MAX_PORTS			15
+#define SDW_VALID_PORT_RANGE(n)		((n) < SDW_MAX_PORTS && (n) >= 1)
 
 enum {
 	SDW_PORT_DIRN_SINK = 0,
-- 
cgit v1.2.3


From 6073755886a463a7a7aecdd0abb32a1d38bdb7e6 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Mon, 31 Aug 2020 21:43:18 +0800
Subject: soundwire: fix port_ready[] dynamic allocation in mipi_disco

The existing code allocates memory for the total number of ports.
This only works if the ports are contiguous, but will break if e.g. a
Devices uses port0, 1, and 14. The port_ready[] array would contain 3
elements, which would lead to an out-of-bounds access. Conversely in
other cases, the wrong port index would be used leading to timeouts on
prepare.

This can be fixed by allocating for the worst-case of 15
ports (DP0..DP14). In addition since the number is now fixed, we can
use an array instead of a dynamic allocation.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Rander Wang <rander.wang@linux.intel.com>
Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Link: https://lore.kernel.org/r/20200831134318.11443-4-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/mipi_disco.c | 18 +-----------------
 drivers/soundwire/slave.c      |  4 ++++
 include/linux/soundwire/sdw.h  |  2 +-
 3 files changed, 6 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/soundwire/mipi_disco.c b/drivers/soundwire/mipi_disco.c
index 4ae62b452b8c..55a9c51c84c1 100644
--- a/drivers/soundwire/mipi_disco.c
+++ b/drivers/soundwire/mipi_disco.c
@@ -289,7 +289,7 @@ int sdw_slave_read_prop(struct sdw_slave *slave)
 	struct sdw_slave_prop *prop = &slave->prop;
 	struct device *dev = &slave->dev;
 	struct fwnode_handle *port;
-	int num_of_ports, nval, i, dp0 = 0;
+	int nval;
 
 	device_property_read_u32(dev, "mipi-sdw-sw-interface-revision",
 				 &prop->mipi_revision);
@@ -352,7 +352,6 @@ int sdw_slave_read_prop(struct sdw_slave *slave)
 			return -ENOMEM;
 
 		sdw_slave_read_dp0(slave, port, prop->dp0_prop);
-		dp0 = 1;
 	}
 
 	/*
@@ -383,21 +382,6 @@ int sdw_slave_read_prop(struct sdw_slave *slave)
 	sdw_slave_read_dpn(slave, prop->sink_dpn_prop, nval,
 			   prop->sink_ports, "sink");
 
-	/* some ports are bidirectional so check total ports by ORing */
-	nval = prop->source_ports | prop->sink_ports;
-	num_of_ports = hweight32(nval) + dp0; /* add DP0 */
-
-	/* Allocate port_ready based on num_of_ports */
-	slave->port_ready = devm_kcalloc(&slave->dev, num_of_ports,
-					 sizeof(*slave->port_ready),
-					 GFP_KERNEL);
-	if (!slave->port_ready)
-		return -ENOMEM;
-
-	/* Initialize completion */
-	for (i = 0; i < num_of_ports; i++)
-		init_completion(&slave->port_ready[i]);
-
 	return 0;
 }
 EXPORT_SYMBOL(sdw_slave_read_prop);
diff --git a/drivers/soundwire/slave.c b/drivers/soundwire/slave.c
index 0839445ee07b..a762ee24e6fa 100644
--- a/drivers/soundwire/slave.c
+++ b/drivers/soundwire/slave.c
@@ -25,6 +25,7 @@ static int sdw_slave_add(struct sdw_bus *bus,
 {
 	struct sdw_slave *slave;
 	int ret;
+	int i;
 
 	slave = kzalloc(sizeof(*slave), GFP_KERNEL);
 	if (!slave)
@@ -58,6 +59,9 @@ static int sdw_slave_add(struct sdw_bus *bus,
 	init_completion(&slave->probe_complete);
 	slave->probed = false;
 
+	for (i = 0; i < SDW_MAX_PORTS; i++)
+		init_completion(&slave->port_ready[i]);
+
 	mutex_lock(&bus->bus_lock);
 	list_add_tail(&slave->node, &bus->slaves);
 	mutex_unlock(&bus->bus_lock);
diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 0aa4c6af7554..63e71645fd13 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -619,7 +619,7 @@ struct sdw_slave {
 	struct dentry *debugfs;
 #endif
 	struct list_head node;
-	struct completion *port_ready;
+	struct completion port_ready[SDW_MAX_PORTS];
 	enum sdw_clk_stop_mode curr_clk_stop_mode;
 	u16 dev_num;
 	u16 dev_num_sticky;
-- 
cgit v1.2.3


From 88d7c71ea5b29b322d9c72103a196234cb5040db Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Tue, 1 Sep 2020 23:05:51 +0800
Subject: soundwire: bus: update multi-link definition with hw sync details

Hardware-based synchronization is typically required when the
bus->multi_link flag is set.

On Intel platforms, when the Cadence IP is configured in 'Multi Master
Mode', the hardware synchronization is required even when a stream
only uses a single segment. The existing code only deal with hardware
synchronization when a stream uses more than one segment so to remain
backwards compatible we add a configuration threshold. For Intel cases
this threshold will be set to one, other platforms may be able to use
the SSP-based sync in those cases.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20200901150556.19432-6-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/soundwire/sdw.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 63e71645fd13..78f52cdeb2c9 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -828,6 +828,11 @@ struct sdw_master_ops {
  * @multi_link: Store bus property that indicates if multi links
  * are supported. This flag is populated by drivers after reading
  * appropriate firmware (ACPI/DT).
+ * @hw_sync_min_links: Number of links used by a stream above which
+ * hardware-based synchronization is required. This value is only
+ * meaningful if multi_link is set. If set to 1, hardware-based
+ * synchronization will be used even if a stream only uses a single
+ * SoundWire segment.
  */
 struct sdw_bus {
 	struct device *dev;
@@ -851,6 +856,7 @@ struct sdw_bus {
 	unsigned int clk_stop_timeout;
 	u32 bank_switch_timeout;
 	bool multi_link;
+	int hw_sync_min_links;
 };
 
 int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent,
-- 
cgit v1.2.3


From 1e9d90dbed120ec98517428ffff4dacd9797e39d Mon Sep 17 00:00:00 2001
From: Nicolin Chen <nicoleotsuka@gmail.com>
Date: Tue, 1 Sep 2020 15:16:45 -0700
Subject: dma-mapping: introduce dma_get_seg_boundary_nr_pages()

We found that callers of dma_get_seg_boundary mostly do an ALIGN
with page mask and then do a page shift to get number of pages:
    ALIGN(boundary + 1, 1 << shift) >> shift

However, the boundary might be as large as ULONG_MAX, which means
that a device has no specific boundary limit. So either "+ 1" or
passing it to ALIGN() would potentially overflow.

According to kernel defines:
    #define ALIGN_MASK(x, mask) (((x) + (mask)) & ~(mask))
    #define ALIGN(x, a)	ALIGN_MASK(x, (typeof(x))(a) - 1)

We can simplify the logic here into a helper function doing:
  ALIGN(boundary + 1, 1 << shift) >> shift
= ALIGN_MASK(b + 1, (1 << s) - 1) >> s
= {[b + 1 + (1 << s) - 1] & ~[(1 << s) - 1]} >> s
= [b + 1 + (1 << s) - 1] >> s
= [b + (1 << s)] >> s
= (b >> s) + 1

This patch introduces and applies dma_get_seg_boundary_nr_pages()
as an overflow-free helper for the dma_get_seg_boundary() callers
to get numbers of pages. It also takes care of the NULL dev case
for non-DMA API callers.

Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicolin Chen <nicoleotsuka@gmail.com>
Acked-by: Niklas Schnelle <schnelle@linux.ibm.com>
Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc)
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 arch/alpha/kernel/pci_iommu.c    |  7 +------
 arch/ia64/hp/common/sba_iommu.c  |  3 +--
 arch/powerpc/kernel/iommu.c      | 11 ++---------
 arch/s390/pci/pci_dma.c          |  6 ++----
 arch/sparc/kernel/iommu-common.c | 10 +++-------
 arch/sparc/kernel/iommu.c        |  3 +--
 arch/sparc/kernel/pci_sun4v.c    |  3 +--
 arch/x86/kernel/amd_gart_64.c    |  3 +--
 drivers/parisc/ccio-dma.c        |  3 +--
 drivers/parisc/sba_iommu.c       |  3 +--
 include/linux/dma-mapping.h      | 19 +++++++++++++++++++
 11 files changed, 33 insertions(+), 38 deletions(-)

(limited to 'include/linux')

diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c
index 81037907268d..6f7de4f4e191 100644
--- a/arch/alpha/kernel/pci_iommu.c
+++ b/arch/alpha/kernel/pci_iommu.c
@@ -141,12 +141,7 @@ iommu_arena_find_pages(struct device *dev, struct pci_iommu_arena *arena,
 	unsigned long boundary_size;
 
 	base = arena->dma_base >> PAGE_SHIFT;
-	if (dev) {
-		boundary_size = dma_get_seg_boundary(dev) + 1;
-		boundary_size >>= PAGE_SHIFT;
-	} else {
-		boundary_size = 1UL << (32 - PAGE_SHIFT);
-	}
+	boundary_size = dma_get_seg_boundary_nr_pages(dev, PAGE_SHIFT);
 
 	/* Search forward for the first mask-aligned sequence of N free ptes */
 	ptes = arena->ptes;
diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c
index 656a4888c300..b49b73a95067 100644
--- a/arch/ia64/hp/common/sba_iommu.c
+++ b/arch/ia64/hp/common/sba_iommu.c
@@ -485,8 +485,7 @@ sba_search_bitmap(struct ioc *ioc, struct device *dev,
 	ASSERT(((unsigned long) ioc->res_hint & (sizeof(unsigned long) - 1UL)) == 0);
 	ASSERT(res_ptr < res_end);
 
-	boundary_size = (unsigned long long)dma_get_seg_boundary(dev) + 1;
-	boundary_size = ALIGN(boundary_size, 1ULL << iovp_shift) >> iovp_shift;
+	boundary_size = dma_get_seg_boundary_nr_pages(dev, iovp_shift);
 
 	BUG_ON(ioc->ibase & ~iovp_mask);
 	shift = ioc->ibase >> iovp_shift;
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 9704f3f76e63..5b69a6a72a0e 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -172,7 +172,6 @@ static unsigned long iommu_range_alloc(struct device *dev,
 	int largealloc = npages > 15;
 	int pass = 0;
 	unsigned long align_mask;
-	unsigned long boundary_size;
 	unsigned long flags;
 	unsigned int pool_nr;
 	struct iommu_pool *pool;
@@ -236,15 +235,9 @@ again:
 		}
 	}
 
-	if (dev)
-		boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
-				      1 << tbl->it_page_shift);
-	else
-		boundary_size = ALIGN(1UL << 32, 1 << tbl->it_page_shift);
-	/* 4GB boundary for iseries_hv_alloc and iseries_hv_map */
-
 	n = iommu_area_alloc(tbl->it_map, limit, start, npages, tbl->it_offset,
-			     boundary_size >> tbl->it_page_shift, align_mask);
+			dma_get_seg_boundary_nr_pages(dev, tbl->it_page_shift),
+			align_mask);
 	if (n == -1) {
 		if (likely(pass == 0)) {
 			/* First try the pool from the start */
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index 64b1399a73f0..4a37d8f4de9d 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -261,13 +261,11 @@ static unsigned long __dma_alloc_iommu(struct device *dev,
 				       unsigned long start, int size)
 {
 	struct zpci_dev *zdev = to_zpci(to_pci_dev(dev));
-	unsigned long boundary_size;
 
-	boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
-			      PAGE_SIZE) >> PAGE_SHIFT;
 	return iommu_area_alloc(zdev->iommu_bitmap, zdev->iommu_pages,
 				start, size, zdev->start_dma >> PAGE_SHIFT,
-				boundary_size, 0);
+				dma_get_seg_boundary_nr_pages(dev, PAGE_SHIFT),
+				0);
 }
 
 static dma_addr_t dma_alloc_address(struct device *dev, int size)
diff --git a/arch/sparc/kernel/iommu-common.c b/arch/sparc/kernel/iommu-common.c
index 59cb16691322..23ca75f09277 100644
--- a/arch/sparc/kernel/iommu-common.c
+++ b/arch/sparc/kernel/iommu-common.c
@@ -166,13 +166,6 @@ unsigned long iommu_tbl_range_alloc(struct device *dev,
 		}
 	}
 
-	if (dev)
-		boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
-				      1 << iommu->table_shift);
-	else
-		boundary_size = ALIGN(1ULL << 32, 1 << iommu->table_shift);
-
-	boundary_size = boundary_size >> iommu->table_shift;
 	/*
 	 * if the skip_span_boundary_check had been set during init, we set
 	 * things up so that iommu_is_span_boundary() merely checks if the
@@ -181,6 +174,9 @@ unsigned long iommu_tbl_range_alloc(struct device *dev,
 	if ((iommu->flags & IOMMU_NO_SPAN_BOUND) != 0) {
 		shift = 0;
 		boundary_size = iommu->poolsize * iommu->nr_pools;
+	} else {
+		boundary_size = dma_get_seg_boundary_nr_pages(dev,
+					iommu->table_shift);
 	}
 	n = iommu_area_alloc(iommu->map, limit, start, npages, shift,
 			     boundary_size, align_mask);
diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c
index 4ae7388b1bff..c3e4e2df26a8 100644
--- a/arch/sparc/kernel/iommu.c
+++ b/arch/sparc/kernel/iommu.c
@@ -472,8 +472,7 @@ static int dma_4u_map_sg(struct device *dev, struct scatterlist *sglist,
 	outs->dma_length = 0;
 
 	max_seg_size = dma_get_max_seg_size(dev);
-	seg_boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
-				  IO_PAGE_SIZE) >> IO_PAGE_SHIFT;
+	seg_boundary_size = dma_get_seg_boundary_nr_pages(dev, IO_PAGE_SHIFT);
 	base_shift = iommu->tbl.table_map_base >> IO_PAGE_SHIFT;
 	for_each_sg(sglist, s, nelems, i) {
 		unsigned long paddr, npages, entry, out_entry = 0, slen;
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index 14b93c5564e3..6b92dd51c002 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
@@ -508,8 +508,7 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
 	iommu_batch_start(dev, prot, ~0UL);
 
 	max_seg_size = dma_get_max_seg_size(dev);
-	seg_boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
-				  IO_PAGE_SIZE) >> IO_PAGE_SHIFT;
+	seg_boundary_size = dma_get_seg_boundary_nr_pages(dev, IO_PAGE_SHIFT);
 
 	mask = *dev->dma_mask;
 	if (!iommu_use_atu(iommu, mask))
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index e89031e9c847..bccc5357bffd 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -96,8 +96,7 @@ static unsigned long alloc_iommu(struct device *dev, int size,
 
 	base_index = ALIGN(iommu_bus_base & dma_get_seg_boundary(dev),
 			   PAGE_SIZE) >> PAGE_SHIFT;
-	boundary_size = ALIGN((u64)dma_get_seg_boundary(dev) + 1,
-			      PAGE_SIZE) >> PAGE_SHIFT;
+	boundary_size = dma_get_seg_boundary_nr_pages(dev, PAGE_SHIFT);
 
 	spin_lock_irqsave(&iommu_bitmap_lock, flags);
 	offset = iommu_area_alloc(iommu_gart_bitmap, iommu_pages, next_bit,
diff --git a/drivers/parisc/ccio-dma.c b/drivers/parisc/ccio-dma.c
index a5507f75b524..ba16b7f8f806 100644
--- a/drivers/parisc/ccio-dma.c
+++ b/drivers/parisc/ccio-dma.c
@@ -356,8 +356,7 @@ ccio_alloc_range(struct ioc *ioc, struct device *dev, size_t size)
 	** ggg sacrifices another 710 to the computer gods.
 	*/
 
-	boundary_size = ALIGN((unsigned long long)dma_get_seg_boundary(dev) + 1,
-			      1ULL << IOVP_SHIFT) >> IOVP_SHIFT;
+	boundary_size = dma_get_seg_boundary_nr_pages(dev, IOVP_SHIFT);
 
 	if (pages_needed <= 8) {
 		/*
diff --git a/drivers/parisc/sba_iommu.c b/drivers/parisc/sba_iommu.c
index d4314fba0269..959bda193b96 100644
--- a/drivers/parisc/sba_iommu.c
+++ b/drivers/parisc/sba_iommu.c
@@ -342,8 +342,7 @@ sba_search_bitmap(struct ioc *ioc, struct device *dev,
 	unsigned long shift;
 	int ret;
 
-	boundary_size = ALIGN((unsigned long long)dma_get_seg_boundary(dev) + 1,
-			      1ULL << IOVP_SHIFT) >> IOVP_SHIFT;
+	boundary_size = dma_get_seg_boundary_nr_pages(dev, IOVP_SHIFT);
 
 #if defined(ZX1_SUPPORT)
 	BUG_ON(ioc->ibase & ~IOVP_MASK);
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 52635e91143b..faab0a8210b9 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -632,6 +632,25 @@ static inline unsigned long dma_get_seg_boundary(struct device *dev)
 	return DMA_BIT_MASK(32);
 }
 
+/**
+ * dma_get_seg_boundary_nr_pages - return the segment boundary in "page" units
+ * @dev: device to guery the boundary for
+ * @page_shift: ilog() of the IOMMU page size
+ *
+ * Return the segment boundary in IOMMU page units (which may be different from
+ * the CPU page size) for the passed in device.
+ *
+ * If @dev is NULL a boundary of U32_MAX is assumed, this case is just for
+ * non-DMA API callers.
+ */
+static inline unsigned long dma_get_seg_boundary_nr_pages(struct device *dev,
+		unsigned int page_shift)
+{
+	if (!dev)
+		return (U32_MAX >> page_shift) + 1;
+	return (dma_get_seg_boundary(dev) >> page_shift) + 1;
+}
+
 static inline int dma_set_seg_boundary(struct device *dev, unsigned long mask)
 {
 	if (dev->dma_parms) {
-- 
cgit v1.2.3


From 135ba11a7a07b4ce9197d9fa4b196329a57f1e06 Mon Sep 17 00:00:00 2001
From: Nicolin Chen <nicoleotsuka@gmail.com>
Date: Tue, 1 Sep 2020 15:16:46 -0700
Subject: dma-mapping: set default segment_boundary_mask to ULONG_MAX

The default segment_boundary_mask was set to DMA_BIT_MAKS(32)
a decade ago by referencing SCSI/block subsystem, as a 32-bit
mask was good enough for most of the devices.

Now more and more drivers set dma_masks above DMA_BIT_MAKS(32)
while only a handful of them call dma_set_seg_boundary(). This
means that most drivers have a 4GB segmention boundary because
DMA API returns a 32-bit default value, though they might not
really have such a limit.

The default segment_boundary_mask should mean "no limit" since
the device doesn't explicitly set the mask. But a 32-bit mask
certainly limits those devices capable of 32+ bits addressing.

So this patch sets default segment_boundary_mask to ULONG_MAX.

Signed-off-by: Nicolin Chen <nicoleotsuka@gmail.com>
Acked-by: Niklas Schnelle <schnelle@linux.ibm.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/dma-mapping.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index faab0a8210b9..df0bff2ea750 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -629,7 +629,7 @@ static inline unsigned long dma_get_seg_boundary(struct device *dev)
 {
 	if (dev->dma_parms && dev->dma_parms->segment_boundary_mask)
 		return dev->dma_parms->segment_boundary_mask;
-	return DMA_BIT_MASK(32);
+	return ULONG_MAX;
 }
 
 /**
-- 
cgit v1.2.3


From 51db1c37ee166159c5753ce8d64d6bacf113e0f0 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Wed, 19 Aug 2020 23:20:19 +0800
Subject: blk-mq: Rename BLK_MQ_F_TAG_SHARED as BLK_MQ_F_TAG_QUEUE_SHARED

BLK_MQ_F_TAG_SHARED actually means that tags is shared among request
queues, all of which should belong to LUNs attached to same HBA.

So rename it to make the point explicitly.

[jpg: rebase a few times, add rnbd-clt.c change]

Suggested-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Tested-by: Douglas Gilbert <dgilbert@interlog.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq-debugfs.c        |  2 +-
 block/blk-mq-tag.h            |  6 +++---
 block/blk-mq.c                | 20 ++++++++++----------
 drivers/block/rnbd/rnbd-clt.c |  2 +-
 include/linux/blk-mq.h        |  2 +-
 5 files changed, 16 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 3f09bcb8a6fd..a4597febff69 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -240,7 +240,7 @@ static const char *const alloc_policy_name[] = {
 #define HCTX_FLAG_NAME(name) [ilog2(BLK_MQ_F_##name)] = #name
 static const char *const hctx_flag_name[] = {
 	HCTX_FLAG_NAME(SHOULD_MERGE),
-	HCTX_FLAG_NAME(TAG_SHARED),
+	HCTX_FLAG_NAME(TAG_QUEUE_SHARED),
 	HCTX_FLAG_NAME(BLOCKING),
 	HCTX_FLAG_NAME(NO_SCHED),
 	HCTX_FLAG_NAME(STACKING),
diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h
index b1acac518c4e..918e2cee4f43 100644
--- a/block/blk-mq-tag.h
+++ b/block/blk-mq-tag.h
@@ -56,7 +56,7 @@ extern void __blk_mq_tag_idle(struct blk_mq_hw_ctx *);
 
 static inline bool blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
 {
-	if (!(hctx->flags & BLK_MQ_F_TAG_SHARED))
+	if (!(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED))
 		return false;
 
 	return __blk_mq_tag_busy(hctx);
@@ -64,7 +64,7 @@ static inline bool blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
 
 static inline void blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx)
 {
-	if (!(hctx->flags & BLK_MQ_F_TAG_SHARED))
+	if (!(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED))
 		return;
 
 	__blk_mq_tag_idle(hctx);
@@ -79,7 +79,7 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
 {
 	unsigned int depth, users;
 
-	if (!hctx || !(hctx->flags & BLK_MQ_F_TAG_SHARED))
+	if (!hctx || !(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED))
 		return true;
 	if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
 		return true;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index b3d2785eefe9..75031fa1709c 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1124,7 +1124,7 @@ static bool blk_mq_get_driver_tag(struct request *rq)
 	if (rq->tag == BLK_MQ_NO_TAG && !__blk_mq_get_driver_tag(rq))
 		return false;
 
-	if ((hctx->flags & BLK_MQ_F_TAG_SHARED) &&
+	if ((hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) &&
 			!(rq->rq_flags & RQF_MQ_INFLIGHT)) {
 		rq->rq_flags |= RQF_MQ_INFLIGHT;
 		atomic_inc(&hctx->nr_active);
@@ -1168,7 +1168,7 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
 	wait_queue_entry_t *wait;
 	bool ret;
 
-	if (!(hctx->flags & BLK_MQ_F_TAG_SHARED)) {
+	if (!(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) {
 		blk_mq_sched_mark_restart_hctx(hctx);
 
 		/*
@@ -1420,7 +1420,7 @@ out:
 		bool needs_restart;
 		/* For non-shared tags, the RESTART check will suffice */
 		bool no_tag = prep == PREP_DISPATCH_NO_TAG &&
-                        (hctx->flags & BLK_MQ_F_TAG_SHARED);
+			(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED);
 		bool no_budget_avail = prep == PREP_DISPATCH_NO_BUDGET;
 
 		blk_mq_release_budgets(q, nr_budgets);
@@ -2668,7 +2668,7 @@ blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set,
 	spin_lock_init(&hctx->lock);
 	INIT_LIST_HEAD(&hctx->dispatch);
 	hctx->queue = q;
-	hctx->flags = set->flags & ~BLK_MQ_F_TAG_SHARED;
+	hctx->flags = set->flags & ~BLK_MQ_F_TAG_QUEUE_SHARED;
 
 	INIT_LIST_HEAD(&hctx->hctx_list);
 
@@ -2885,9 +2885,9 @@ static void queue_set_hctx_shared(struct request_queue *q, bool shared)
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (shared)
-			hctx->flags |= BLK_MQ_F_TAG_SHARED;
+			hctx->flags |= BLK_MQ_F_TAG_QUEUE_SHARED;
 		else
-			hctx->flags &= ~BLK_MQ_F_TAG_SHARED;
+			hctx->flags &= ~BLK_MQ_F_TAG_QUEUE_SHARED;
 	}
 }
 
@@ -2913,7 +2913,7 @@ static void blk_mq_del_queue_tag_set(struct request_queue *q)
 	list_del(&q->tag_set_list);
 	if (list_is_singular(&set->tag_list)) {
 		/* just transitioned to unshared */
-		set->flags &= ~BLK_MQ_F_TAG_SHARED;
+		set->flags &= ~BLK_MQ_F_TAG_QUEUE_SHARED;
 		/* update existing queue */
 		blk_mq_update_tag_set_depth(set, false);
 	}
@@ -2930,12 +2930,12 @@ static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set,
 	 * Check to see if we're transitioning to shared (from 1 to 2 queues).
 	 */
 	if (!list_empty(&set->tag_list) &&
-	    !(set->flags & BLK_MQ_F_TAG_SHARED)) {
-		set->flags |= BLK_MQ_F_TAG_SHARED;
+	    !(set->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) {
+		set->flags |= BLK_MQ_F_TAG_QUEUE_SHARED;
 		/* update existing queue */
 		blk_mq_update_tag_set_depth(set, true);
 	}
-	if (set->flags & BLK_MQ_F_TAG_SHARED)
+	if (set->flags & BLK_MQ_F_TAG_QUEUE_SHARED)
 		queue_set_hctx_shared(q, true);
 	list_add_tail(&q->tag_set_list, &set->tag_list);
 
diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c
index 157538fc8be5..d7a69741c0f6 100644
--- a/drivers/block/rnbd/rnbd-clt.c
+++ b/drivers/block/rnbd/rnbd-clt.c
@@ -1174,7 +1174,7 @@ static int setup_mq_tags(struct rnbd_clt_session *sess)
 	tag_set->queue_depth	= sess->queue_depth;
 	tag_set->numa_node		= NUMA_NO_NODE;
 	tag_set->flags		= BLK_MQ_F_SHOULD_MERGE |
-				  BLK_MQ_F_TAG_SHARED;
+				  BLK_MQ_F_TAG_QUEUE_SHARED;
 	tag_set->cmd_size		= sizeof(struct rnbd_iu);
 	tag_set->nr_hw_queues	= num_online_cpus();
 
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 21a02e0577dd..982c4f92b63c 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -378,7 +378,7 @@ struct blk_mq_ops {
 
 enum {
 	BLK_MQ_F_SHOULD_MERGE	= 1 << 0,
-	BLK_MQ_F_TAG_SHARED	= 1 << 1,
+	BLK_MQ_F_TAG_QUEUE_SHARED = 1 << 1,
 	/*
 	 * Set when this device requires underlying blk-mq device for
 	 * completing IO:
-- 
cgit v1.2.3


From 32bc15afed04bd73e29d713d8db47818d6aa89af Mon Sep 17 00:00:00 2001
From: John Garry <john.garry@huawei.com>
Date: Wed, 19 Aug 2020 23:20:24 +0800
Subject: blk-mq: Facilitate a shared sbitmap per tagset

Some SCSI HBAs (such as HPSA, megaraid, mpt3sas, hisi_sas_v3 ..) support
multiple reply queues with single hostwide tags.

In addition, these drivers want to use interrupt assignment in
pci_alloc_irq_vectors(PCI_IRQ_AFFINITY). However, as discussed in [0],
CPU hotplug may cause in-flight IO completion to not be serviced when an
interrupt is shutdown. That problem is solved in commit bf0beec0607d
("blk-mq: drain I/O when all CPUs in a hctx are offline").

However, to take advantage of that blk-mq feature, the HBA HW queuess are
required to be mapped to that of the blk-mq hctx's; to do that, the HBA HW
queues need to be exposed to the upper layer.

In making that transition, the per-SCSI command request tags are no
longer unique per Scsi host - they are just unique per hctx. As such, the
HBA LLDD would have to generate this tag internally, which has a certain
performance overhead.

However another problem is that blk-mq assumes the host may accept
(Scsi_host.can_queue * #hw queue) commands. In commit 6eb045e092ef ("scsi:
 core: avoid host-wide host_busy counter for scsi_mq"), the Scsi host busy
counter was removed, which would stop the LLDD being sent more than
.can_queue commands; however, it should still be ensured that the block
layer does not issue more than .can_queue commands to the Scsi host.

To solve this problem, introduce a shared sbitmap per blk_mq_tag_set,
which may be requested at init time.

New flag BLK_MQ_F_TAG_HCTX_SHARED should be set when requesting the
tagset to indicate whether the shared sbitmap should be used.

Even when BLK_MQ_F_TAG_HCTX_SHARED is set, a full set of tags and requests
are still allocated per hctx; the reason for this is that if tags and
requests were only allocated for a single hctx - like hctx0 - it may break
block drivers which expect a request be associated with a specific hctx,
i.e. not always hctx0. This will introduce extra memory usage.

This change is based on work originally from Ming Lei in [1] and from
Bart's suggestion in [2].

[0] https://lore.kernel.org/linux-block/alpine.DEB.2.21.1904051331270.1802@nanos.tec.linutronix.de/
[1] https://lore.kernel.org/linux-block/20190531022801.10003-1-ming.lei@redhat.com/
[2] https://lore.kernel.org/linux-block/ff77beff-5fd9-9f05-12b6-826922bace1f@huawei.com/T/#m3db0a602f095cbcbff27e9c884d6b4ae826144be

Signed-off-by: John Garry <john.garry@huawei.com>
Tested-by: Don Brace<don.brace@microsemi.com> #SCSI resv cmds patches used
Tested-by: Douglas Gilbert <dgilbert@interlog.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq-sched.c   |  8 +++++---
 block/blk-mq-tag.c     | 51 ++++++++++++++++++++++++++++++++++++++++++++++----
 block/blk-mq-tag.h     |  7 +++++++
 block/blk-mq.c         | 15 +++++++++++++++
 block/blk-mq.h         |  5 +++++
 include/linux/blk-mq.h |  6 ++++++
 6 files changed, 85 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index edfc8ea805bc..86d5545342ff 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -560,7 +560,7 @@ static void blk_mq_sched_free_tags(struct blk_mq_tag_set *set,
 				   struct blk_mq_hw_ctx *hctx,
 				   unsigned int hctx_idx)
 {
-	unsigned int flags = set->flags;
+	unsigned int flags = set->flags & ~BLK_MQ_F_TAG_HCTX_SHARED;
 
 	if (hctx->sched_tags) {
 		blk_mq_free_rqs(set, hctx->sched_tags, hctx_idx);
@@ -574,7 +574,8 @@ static int blk_mq_sched_alloc_tags(struct request_queue *q,
 				   unsigned int hctx_idx)
 {
 	struct blk_mq_tag_set *set = q->tag_set;
-	unsigned int flags = set->flags;
+	/* Clear HCTX_SHARED so tags are init'ed */
+	unsigned int flags = set->flags & ~BLK_MQ_F_TAG_HCTX_SHARED;
 	int ret;
 
 	hctx->sched_tags = blk_mq_alloc_rq_map(set, hctx_idx, q->nr_requests,
@@ -596,7 +597,8 @@ static void blk_mq_sched_tags_teardown(struct request_queue *q)
 	int i;
 
 	queue_for_each_hw_ctx(q, hctx, i) {
-		unsigned int flags = hctx->flags;
+		/* Clear HCTX_SHARED so tags are freed */
+		unsigned int flags = hctx->flags & ~BLK_MQ_F_TAG_HCTX_SHARED;
 
 		if (hctx->sched_tags) {
 			blk_mq_free_rq_map(hctx->sched_tags, flags);
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 77fbeae05745..c6d7ebc62bdb 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -197,7 +197,7 @@ static bool bt_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
 	 * We can hit rq == NULL here, because the tagging functions
 	 * test and set the bit before assigning ->rqs[].
 	 */
-	if (rq && rq->q == hctx->queue)
+	if (rq && rq->q == hctx->queue && rq->mq_hctx == hctx)
 		return iter_data->fn(hctx, rq, iter_data->data, reserved);
 	return true;
 }
@@ -450,6 +450,38 @@ free_bitmap_tags:
 	return -ENOMEM;
 }
 
+int blk_mq_init_shared_sbitmap(struct blk_mq_tag_set *set, unsigned int flags)
+{
+	unsigned int depth = set->queue_depth - set->reserved_tags;
+	int alloc_policy = BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags);
+	bool round_robin = alloc_policy == BLK_TAG_ALLOC_RR;
+	int i, node = set->numa_node;
+
+	if (bt_alloc(&set->__bitmap_tags, depth, round_robin, node))
+		return -ENOMEM;
+	if (bt_alloc(&set->__breserved_tags, set->reserved_tags,
+		     round_robin, node))
+		goto free_bitmap_tags;
+
+	for (i = 0; i < set->nr_hw_queues; i++) {
+		struct blk_mq_tags *tags = set->tags[i];
+
+		tags->bitmap_tags = &set->__bitmap_tags;
+		tags->breserved_tags = &set->__breserved_tags;
+	}
+
+	return 0;
+free_bitmap_tags:
+	sbitmap_queue_free(&set->__bitmap_tags);
+	return -ENOMEM;
+}
+
+void blk_mq_exit_shared_sbitmap(struct blk_mq_tag_set *set)
+{
+	sbitmap_queue_free(&set->__bitmap_tags);
+	sbitmap_queue_free(&set->__breserved_tags);
+}
+
 struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
 				     unsigned int reserved_tags,
 				     int node, unsigned int flags)
@@ -469,6 +501,9 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
 	tags->nr_tags = total_tags;
 	tags->nr_reserved_tags = reserved_tags;
 
+	if (flags & BLK_MQ_F_TAG_HCTX_SHARED)
+		return tags;
+
 	if (blk_mq_init_bitmap_tags(tags, node, alloc_policy) < 0) {
 		kfree(tags);
 		return NULL;
@@ -478,8 +513,10 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
 
 void blk_mq_free_tags(struct blk_mq_tags *tags, unsigned int flags)
 {
-	sbitmap_queue_free(&tags->__bitmap_tags);
-	sbitmap_queue_free(&tags->__breserved_tags);
+	if (!(flags & BLK_MQ_F_TAG_HCTX_SHARED)) {
+		sbitmap_queue_free(tags->bitmap_tags);
+		sbitmap_queue_free(tags->breserved_tags);
+	}
 	kfree(tags);
 }
 
@@ -498,7 +535,8 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
 	 */
 	if (tdepth > tags->nr_tags) {
 		struct blk_mq_tag_set *set = hctx->queue->tag_set;
-		unsigned int flags = set->flags;
+		/* Only sched tags can grow, so clear HCTX_SHARED flag  */
+		unsigned int flags = set->flags & ~BLK_MQ_F_TAG_HCTX_SHARED;
 		struct blk_mq_tags *new;
 		bool ret;
 
@@ -537,6 +575,11 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
 	return 0;
 }
 
+void blk_mq_tag_resize_shared_sbitmap(struct blk_mq_tag_set *set, unsigned int size)
+{
+	sbitmap_queue_resize(&set->__bitmap_tags, size - set->reserved_tags);
+}
+
 /**
  * blk_mq_unique_tag() - return a tag that is unique queue-wide
  * @rq: request for which to compute a unique tag
diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h
index 5b6f25bd1966..8f4cce52ba2d 100644
--- a/block/blk-mq-tag.h
+++ b/block/blk-mq-tag.h
@@ -29,12 +29,19 @@ extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags,
 					int node, unsigned int flags);
 extern void blk_mq_free_tags(struct blk_mq_tags *tags, unsigned int flags);
 
+extern int blk_mq_init_shared_sbitmap(struct blk_mq_tag_set *set,
+				      unsigned int flags);
+extern void blk_mq_exit_shared_sbitmap(struct blk_mq_tag_set *set);
+
 extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data);
 extern void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx,
 			   unsigned int tag);
 extern int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
 					struct blk_mq_tags **tags,
 					unsigned int depth, bool can_grow);
+extern void blk_mq_tag_resize_shared_sbitmap(struct blk_mq_tag_set *set,
+					     unsigned int size);
+
 extern void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool);
 void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
 		void *priv);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 4982bb1d75db..5e8fe795edf1 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -3441,11 +3441,21 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 	if (ret)
 		goto out_free_mq_map;
 
+	if (blk_mq_is_sbitmap_shared(set->flags)) {
+		if (blk_mq_init_shared_sbitmap(set, set->flags)) {
+			ret = -ENOMEM;
+			goto out_free_mq_rq_maps;
+		}
+	}
+
 	mutex_init(&set->tag_list_lock);
 	INIT_LIST_HEAD(&set->tag_list);
 
 	return 0;
 
+out_free_mq_rq_maps:
+	for (i = 0; i < set->nr_hw_queues; i++)
+		blk_mq_free_map_and_requests(set, i);
 out_free_mq_map:
 	for (i = 0; i < set->nr_maps; i++) {
 		kfree(set->map[i].mq_map);
@@ -3464,6 +3474,9 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set)
 	for (i = 0; i < set->nr_hw_queues; i++)
 		blk_mq_free_map_and_requests(set, i);
 
+	if (blk_mq_is_sbitmap_shared(set->flags))
+		blk_mq_exit_shared_sbitmap(set);
+
 	for (j = 0; j < set->nr_maps; j++) {
 		kfree(set->map[j].mq_map);
 		set->map[j].mq_map = NULL;
@@ -3500,6 +3513,8 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
 		if (!hctx->sched_tags) {
 			ret = blk_mq_tag_update_depth(hctx, &hctx->tags, nr,
 							false);
+			if (!ret && blk_mq_is_sbitmap_shared(set->flags))
+				blk_mq_tag_resize_shared_sbitmap(set, nr);
 		} else {
 			ret = blk_mq_tag_update_depth(hctx, &hctx->sched_tags,
 							nr, true);
diff --git a/block/blk-mq.h b/block/blk-mq.h
index b86e7fe47789..3acdb56065e1 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -159,6 +159,11 @@ struct blk_mq_alloc_data {
 	struct blk_mq_hw_ctx *hctx;
 };
 
+static inline bool blk_mq_is_sbitmap_shared(unsigned int flags)
+{
+	return flags & BLK_MQ_F_TAG_HCTX_SHARED;
+}
+
 static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data *data)
 {
 	if (data->q->elevator)
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 982c4f92b63c..df7b903ce7ae 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -231,6 +231,9 @@ enum hctx_type {
  * @flags:	   Zero or more BLK_MQ_F_* flags.
  * @driver_data:   Pointer to data owned by the block driver that created this
  *		   tag set.
+ * @__bitmap_tags: A shared tags sbitmap, used over all hctx's
+ * @__breserved_tags:
+ *		   A shared reserved tags sbitmap, used over all hctx's
  * @tags:	   Tag sets. One tag set per hardware queue. Has @nr_hw_queues
  *		   elements.
  * @tag_list_lock: Serializes tag_list accesses.
@@ -250,6 +253,8 @@ struct blk_mq_tag_set {
 	unsigned int		flags;
 	void			*driver_data;
 
+	struct sbitmap_queue	__bitmap_tags;
+	struct sbitmap_queue	__breserved_tags;
 	struct blk_mq_tags	**tags;
 
 	struct mutex		tag_list_lock;
@@ -384,6 +389,7 @@ enum {
 	 * completing IO:
 	 */
 	BLK_MQ_F_STACKING	= 1 << 2,
+	BLK_MQ_F_TAG_HCTX_SHARED = 1 << 3,
 	BLK_MQ_F_BLOCKING	= 1 << 5,
 	BLK_MQ_F_NO_SCHED	= 1 << 6,
 	BLK_MQ_F_ALLOC_POLICY_START_BIT = 8,
-- 
cgit v1.2.3


From bccf5e26d99c28980bd6ced474422a1b18402263 Mon Sep 17 00:00:00 2001
From: John Garry <john.garry@huawei.com>
Date: Wed, 19 Aug 2020 23:20:26 +0800
Subject: blk-mq: Record nr_active_requests per queue for when using shared
 sbitmap

The per-hctx nr_active value can no longer be used to fairly assign a share
of tag depth per request queue for when using a shared sbitmap, as it does
not consider that the tags are shared tags over all hctx's.

For this case, record the nr_active_requests per request_queue, and make
the judgement based on that value.

Co-developed-with: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Tested-by: Don Brace<don.brace@microsemi.com> #SCSI resv cmds patches used
Tested-by: Douglas Gilbert <dgilbert@interlog.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c       |  2 ++
 block/blk-mq.c         |  4 ++--
 block/blk-mq.h         | 26 ++++++++++++++++++++++++--
 include/linux/blkdev.h |  2 ++
 4 files changed, 30 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-core.c b/block/blk-core.c
index 9f2a99abeeb9..093649bd252e 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -543,6 +543,8 @@ struct request_queue *blk_alloc_queue(int node_id)
 	q->backing_dev_info->capabilities = BDI_CAP_CGROUP_WRITEBACK;
 	q->node = node_id;
 
+	atomic_set(&q->nr_active_requests_shared_sbitmap, 0);
+
 	timer_setup(&q->backing_dev_info->laptop_mode_wb_timer,
 		    laptop_mode_timer_fn, 0);
 	timer_setup(&q->timeout, blk_rq_timed_out_timer, 0);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 5e8fe795edf1..ffc5ad0c91b7 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -519,7 +519,7 @@ void blk_mq_free_request(struct request *rq)
 
 	ctx->rq_completed[rq_is_sync(rq)]++;
 	if (rq->rq_flags & RQF_MQ_INFLIGHT)
-		atomic_dec(&hctx->nr_active);
+		__blk_mq_dec_active_requests(hctx);
 
 	if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq)))
 		laptop_io_completion(q->backing_dev_info);
@@ -1127,7 +1127,7 @@ static bool blk_mq_get_driver_tag(struct request *rq)
 	if ((hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) &&
 			!(rq->rq_flags & RQF_MQ_INFLIGHT)) {
 		rq->rq_flags |= RQF_MQ_INFLIGHT;
-		atomic_inc(&hctx->nr_active);
+		__blk_mq_inc_active_requests(hctx);
 	}
 	hctx->tags->rqs[rq->tag] = rq;
 	return true;
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 56dc37c21908..25ec73078e95 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -199,6 +199,28 @@ static inline bool blk_mq_get_dispatch_budget(struct request_queue *q)
 	return true;
 }
 
+static inline void __blk_mq_inc_active_requests(struct blk_mq_hw_ctx *hctx)
+{
+	if (blk_mq_is_sbitmap_shared(hctx->flags))
+		atomic_inc(&hctx->queue->nr_active_requests_shared_sbitmap);
+	else
+		atomic_inc(&hctx->nr_active);
+}
+
+static inline void __blk_mq_dec_active_requests(struct blk_mq_hw_ctx *hctx)
+{
+	if (blk_mq_is_sbitmap_shared(hctx->flags))
+		atomic_dec(&hctx->queue->nr_active_requests_shared_sbitmap);
+	else
+		atomic_dec(&hctx->nr_active);
+}
+
+static inline int __blk_mq_active_requests(struct blk_mq_hw_ctx *hctx)
+{
+	if (blk_mq_is_sbitmap_shared(hctx->flags))
+		return atomic_read(&hctx->queue->nr_active_requests_shared_sbitmap);
+	return atomic_read(&hctx->nr_active);
+}
 static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
 					   struct request *rq)
 {
@@ -207,7 +229,7 @@ static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
 
 	if (rq->rq_flags & RQF_MQ_INFLIGHT) {
 		rq->rq_flags &= ~RQF_MQ_INFLIGHT;
-		atomic_dec(&hctx->nr_active);
+		__blk_mq_dec_active_requests(hctx);
 	}
 }
 
@@ -287,7 +309,7 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
 	 * Allow at least some tags
 	 */
 	depth = max((bt->sb.depth + users - 1) / users, 4U);
-	return atomic_read(&hctx->nr_active) < depth;
+	return __blk_mq_active_requests(hctx) < depth;
 }
 
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index d0d61bc81615..6277aee2aeaa 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -485,6 +485,8 @@ struct request_queue {
 	struct timer_list	timeout;
 	struct work_struct	timeout_work;
 
+	atomic_t		nr_active_requests_shared_sbitmap;
+
 	struct list_head	icq_list;
 #ifdef CONFIG_BLK_CGROUP
 	DECLARE_BITMAP		(blkcg_pols, BLKCG_MAX_POLS);
-- 
cgit v1.2.3


From f1b49fdc1c64db110aa1315831e5fe0f8599fa56 Mon Sep 17 00:00:00 2001
From: John Garry <john.garry@huawei.com>
Date: Wed, 19 Aug 2020 23:20:27 +0800
Subject: blk-mq: Record active_queues_shared_sbitmap per tag_set for when
 using shared sbitmap

For when using a shared sbitmap, no longer should the number of active
request queues per hctx be relied on for when judging how to share the tag
bitmap.

Instead maintain the number of active request queues per tag_set, and make
the judgement based on that.

Originally-from: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Tested-by: Don Brace<don.brace@microsemi.com> #SCSI resv cmds patches used
Tested-by: Douglas Gilbert <dgilbert@interlog.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq-tag.c     | 33 +++++++++++++++++++++++++--------
 block/blk-mq.c         |  2 ++
 block/blk-mq.h         | 16 +++++++++++++---
 include/linux/blk-mq.h |  1 +
 include/linux/blkdev.h |  1 +
 5 files changed, 42 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index c6d7ebc62bdb..c31c4a0478a5 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -23,9 +23,18 @@
  */
 bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
 {
-	if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state) &&
-	    !test_and_set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
-		atomic_inc(&hctx->tags->active_queues);
+	if (blk_mq_is_sbitmap_shared(hctx->flags)) {
+		struct request_queue *q = hctx->queue;
+		struct blk_mq_tag_set *set = q->tag_set;
+
+		if (!test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags) &&
+		    !test_and_set_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags))
+			atomic_inc(&set->active_queues_shared_sbitmap);
+	} else {
+		if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state) &&
+		    !test_and_set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
+			atomic_inc(&hctx->tags->active_queues);
+	}
 
 	return true;
 }
@@ -47,11 +56,19 @@ void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool include_reserve)
 void __blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx)
 {
 	struct blk_mq_tags *tags = hctx->tags;
-
-	if (!test_and_clear_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
-		return;
-
-	atomic_dec(&tags->active_queues);
+	struct request_queue *q = hctx->queue;
+	struct blk_mq_tag_set *set = q->tag_set;
+
+	if (blk_mq_is_sbitmap_shared(hctx->flags)) {
+		if (!test_and_clear_bit(QUEUE_FLAG_HCTX_ACTIVE,
+					&q->queue_flags))
+			return;
+		atomic_dec(&set->active_queues_shared_sbitmap);
+	} else {
+		if (!test_and_clear_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
+			return;
+		atomic_dec(&tags->active_queues);
+	}
 
 	blk_mq_tag_wakeup_all(tags, false);
 }
diff --git a/block/blk-mq.c b/block/blk-mq.c
index ffc5ad0c91b7..eff9d987f85b 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -3442,6 +3442,8 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 		goto out_free_mq_map;
 
 	if (blk_mq_is_sbitmap_shared(set->flags)) {
+		atomic_set(&set->active_queues_shared_sbitmap, 0);
+
 		if (blk_mq_init_shared_sbitmap(set, set->flags)) {
 			ret = -ENOMEM;
 			goto out_free_mq_rq_maps;
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 25ec73078e95..a52703c98b77 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -292,8 +292,6 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
 
 	if (!hctx || !(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED))
 		return true;
-	if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
-		return true;
 
 	/*
 	 * Don't try dividing an ant
@@ -301,7 +299,19 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
 	if (bt->sb.depth == 1)
 		return true;
 
-	users = atomic_read(&hctx->tags->active_queues);
+	if (blk_mq_is_sbitmap_shared(hctx->flags)) {
+		struct request_queue *q = hctx->queue;
+		struct blk_mq_tag_set *set = q->tag_set;
+
+		if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &q->queue_flags))
+			return true;
+		users = atomic_read(&set->active_queues_shared_sbitmap);
+	} else {
+		if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
+			return true;
+		users = atomic_read(&hctx->tags->active_queues);
+	}
+
 	if (!users)
 		return true;
 
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index df7b903ce7ae..8279c807e1f3 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -252,6 +252,7 @@ struct blk_mq_tag_set {
 	unsigned int		timeout;
 	unsigned int		flags;
 	void			*driver_data;
+	atomic_t		active_queues_shared_sbitmap;
 
 	struct sbitmap_queue	__bitmap_tags;
 	struct sbitmap_queue	__breserved_tags;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 6277aee2aeaa..7d82959e7b86 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -618,6 +618,7 @@ struct request_queue {
 #define QUEUE_FLAG_PCI_P2PDMA	25	/* device supports PCI p2p requests */
 #define QUEUE_FLAG_ZONE_RESETALL 26	/* supports Zone Reset All */
 #define QUEUE_FLAG_RQ_ALLOC_TIME 27	/* record rq->alloc_time_ns */
+#define QUEUE_FLAG_HCTX_ACTIVE 28	/* at least one blk-mq hctx is active */
 
 #define QUEUE_FLAG_MQ_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_SAME_COMP))
-- 
cgit v1.2.3


From b445547ec1bbd3e7bf4b1c142550942f70527d95 Mon Sep 17 00:00:00 2001
From: Kashyap Desai <kashyap.desai@broadcom.com>
Date: Wed, 19 Aug 2020 23:20:28 +0800
Subject: blk-mq, elevator: Count requests per hctx to improve performance

High CPU utilization on "native_queued_spin_lock_slowpath" due to lock
contention is possible for mq-deadline and bfq IO schedulers
when nr_hw_queues is more than one.

It is because kblockd work queue can submit IO from all online CPUs
(through blk_mq_run_hw_queues()) even though only one hctx has pending
commands.

The elevator callback .has_work for mq-deadline and bfq scheduler considers
pending work if there are any IOs on request queue but it does not account
hctx context.

Add a per-hctx 'elevator_queued' count to the hctx to avoid triggering
the elevator even though there are no requests queued.

[jpg: Relocated atomic_dec() in dd_dispatch_request(), update commit message per Kashyap]

Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: John Garry <john.garry@huawei.com>
Tested-by: Douglas Gilbert <dgilbert@interlog.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bfq-iosched.c    | 5 +++++
 block/blk-mq.c         | 1 +
 block/mq-deadline.c    | 6 ++++++
 include/linux/blk-mq.h | 4 ++++
 4 files changed, 16 insertions(+)

(limited to 'include/linux')

diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 418ffd4b5552..a251b80d8ee5 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -4640,6 +4640,9 @@ static bool bfq_has_work(struct blk_mq_hw_ctx *hctx)
 {
 	struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
 
+	if (!atomic_read(&hctx->elevator_queued))
+		return false;
+
 	/*
 	 * Avoiding lock: a race on bfqd->busy_queues should cause at
 	 * most a call to dispatch for nothing
@@ -5554,6 +5557,7 @@ static void bfq_insert_requests(struct blk_mq_hw_ctx *hctx,
 		rq = list_first_entry(list, struct request, queuelist);
 		list_del_init(&rq->queuelist);
 		bfq_insert_request(hctx, rq, at_head);
+		atomic_inc(&hctx->elevator_queued);
 	}
 }
 
@@ -5933,6 +5937,7 @@ static void bfq_finish_requeue_request(struct request *rq)
 
 		bfq_completed_request(bfqq, bfqd);
 		bfq_finish_requeue_request_body(bfqq);
+		atomic_dec(&rq->mq_hctx->elevator_queued);
 
 		spin_unlock_irqrestore(&bfqd->lock, flags);
 	} else {
diff --git a/block/blk-mq.c b/block/blk-mq.c
index eff9d987f85b..4abb71459f94 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2660,6 +2660,7 @@ blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set,
 		goto free_hctx;
 
 	atomic_set(&hctx->nr_active, 0);
+	atomic_set(&hctx->elevator_queued, 0);
 	if (node == NUMA_NO_NODE)
 		node = set->numa_node;
 	hctx->numa_node = node;
diff --git a/block/mq-deadline.c b/block/mq-deadline.c
index b57470e154c8..800ac902809b 100644
--- a/block/mq-deadline.c
+++ b/block/mq-deadline.c
@@ -386,6 +386,8 @@ static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
 	spin_lock(&dd->lock);
 	rq = __dd_dispatch_request(dd);
 	spin_unlock(&dd->lock);
+	if (rq)
+		atomic_dec(&rq->mq_hctx->elevator_queued);
 
 	return rq;
 }
@@ -533,6 +535,7 @@ static void dd_insert_requests(struct blk_mq_hw_ctx *hctx,
 		rq = list_first_entry(list, struct request, queuelist);
 		list_del_init(&rq->queuelist);
 		dd_insert_request(hctx, rq, at_head);
+		atomic_inc(&hctx->elevator_queued);
 	}
 	spin_unlock(&dd->lock);
 }
@@ -579,6 +582,9 @@ static bool dd_has_work(struct blk_mq_hw_ctx *hctx)
 {
 	struct deadline_data *dd = hctx->queue->elevator->elevator_data;
 
+	if (!atomic_read(&hctx->elevator_queued))
+		return false;
+
 	return !list_empty_careful(&dd->dispatch) ||
 		!list_empty_careful(&dd->fifo_list[0]) ||
 		!list_empty_careful(&dd->fifo_list[1]);
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 8279c807e1f3..b23eeca4d677 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -139,6 +139,10 @@ struct blk_mq_hw_ctx {
 	 * shared across request queues.
 	 */
 	atomic_t		nr_active;
+	/**
+	 * @elevator_queued: Number of queued requests on hctx.
+	 */
+	atomic_t                elevator_queued;
 
 	/** @cpuhp_online: List to store request if CPU is going to die */
 	struct hlist_node	cpuhp_online;
-- 
cgit v1.2.3


From c1077616142907bb6ee987ecd136d6857ffd8787 Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Tue, 1 Sep 2020 15:10:08 -0700
Subject: ip: expose inet sockopts through inet_diag

Expose all exisiting inet sockopt bits through inet_diag for debug purpose.
Corresponding changes in iproute2 ss will be submitted to output all
these values.

Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/inet_diag.h      |  2 ++
 include/uapi/linux/inet_diag.h | 18 ++++++++++++++++++
 net/ipv4/inet_diag.c           | 17 +++++++++++++++++
 3 files changed, 37 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h
index 0ef2d800fda7..84abb30a3fbb 100644
--- a/include/linux/inet_diag.h
+++ b/include/linux/inet_diag.h
@@ -75,6 +75,8 @@ static inline size_t inet_diag_msg_attrs_size(void)
 #ifdef CONFIG_SOCK_CGROUP_DATA
 		+ nla_total_size_64bit(sizeof(u64))  /* INET_DIAG_CGROUP_ID */
 #endif
+		+ nla_total_size(sizeof(struct inet_diag_sockopt))
+						     /* INET_DIAG_SOCKOPT */
 		;
 }
 int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h
index 5ba122c1949a..20ee93f0f876 100644
--- a/include/uapi/linux/inet_diag.h
+++ b/include/uapi/linux/inet_diag.h
@@ -160,6 +160,7 @@ enum {
 	INET_DIAG_ULP_INFO,
 	INET_DIAG_SK_BPF_STORAGES,
 	INET_DIAG_CGROUP_ID,
+	INET_DIAG_SOCKOPT,
 	__INET_DIAG_MAX,
 };
 
@@ -183,6 +184,23 @@ struct inet_diag_meminfo {
 	__u32	idiag_tmem;
 };
 
+/* INET_DIAG_SOCKOPT */
+
+struct inet_diag_sockopt {
+	__u8	recverr:1,
+		is_icsk:1,
+		freebind:1,
+		hdrincl:1,
+		mc_loop:1,
+		transparent:1,
+		mc_all:1,
+		nodefrag:1;
+	__u8	bind_address_no_port:1,
+		recverr_rfc4884:1,
+		defer_connect:1,
+		unused:5;
+};
+
 /* INET_DIAG_VEGASINFO */
 
 struct tcpvegas_info {
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 4a98dd736270..93816d47e55a 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -125,6 +125,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
 			     bool net_admin)
 {
 	const struct inet_sock *inet = inet_sk(sk);
+	struct inet_diag_sockopt inet_sockopt;
 
 	if (nla_put_u8(skb, INET_DIAG_SHUTDOWN, sk->sk_shutdown))
 		goto errout;
@@ -180,6 +181,22 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
 	r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk));
 	r->idiag_inode = sock_i_ino(sk);
 
+	memset(&inet_sockopt, 0, sizeof(inet_sockopt));
+	inet_sockopt.recverr	= inet->recverr;
+	inet_sockopt.is_icsk	= inet->is_icsk;
+	inet_sockopt.freebind	= inet->freebind;
+	inet_sockopt.hdrincl	= inet->hdrincl;
+	inet_sockopt.mc_loop	= inet->mc_loop;
+	inet_sockopt.transparent = inet->transparent;
+	inet_sockopt.mc_all	= inet->mc_all;
+	inet_sockopt.nodefrag	= inet->nodefrag;
+	inet_sockopt.bind_address_no_port = inet->bind_address_no_port;
+	inet_sockopt.recverr_rfc4884 = inet->recverr_rfc4884;
+	inet_sockopt.defer_connect = inet->defer_connect;
+	if (nla_put(skb, INET_DIAG_SOCKOPT, sizeof(inet_sockopt),
+		    &inet_sockopt))
+		goto errout;
+
 	return 0;
 errout:
 	return 1;
-- 
cgit v1.2.3


From fd5a13f4893c8df2a5a3af8599adecb52d05fe89 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 3 Sep 2020 16:22:31 +0200
Subject: proc: add a read_iter method to proc proc_ops

This will allow proc files to implement iter read semantics.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/proc/inode.c         | 53 ++++++++++++++++++++++++++++++++++++++++++++++---
 include/linux/proc_fs.h |  1 +
 2 files changed, 51 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 93dd20457375..58c075e2a452 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -297,6 +297,21 @@ static loff_t proc_reg_llseek(struct file *file, loff_t offset, int whence)
 	return rv;
 }
 
+static ssize_t proc_reg_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct proc_dir_entry *pde = PDE(file_inode(iocb->ki_filp));
+	ssize_t ret;
+
+	if (pde_is_permanent(pde))
+		return pde->proc_ops->proc_read_iter(iocb, iter);
+
+	if (!use_pde(pde))
+		return -EIO;
+	ret = pde->proc_ops->proc_read_iter(iocb, iter);
+	unuse_pde(pde);
+	return ret;
+}
+
 static ssize_t pde_read(struct proc_dir_entry *pde, struct file *file, char __user *buf, size_t count, loff_t *ppos)
 {
 	typeof_member(struct proc_ops, proc_read) read;
@@ -578,6 +593,18 @@ static const struct file_operations proc_reg_file_ops = {
 	.release	= proc_reg_release,
 };
 
+static const struct file_operations proc_iter_file_ops = {
+	.llseek		= proc_reg_llseek,
+	.read_iter	= proc_reg_read_iter,
+	.write		= proc_reg_write,
+	.poll		= proc_reg_poll,
+	.unlocked_ioctl	= proc_reg_unlocked_ioctl,
+	.mmap		= proc_reg_mmap,
+	.get_unmapped_area = proc_reg_get_unmapped_area,
+	.open		= proc_reg_open,
+	.release	= proc_reg_release,
+};
+
 #ifdef CONFIG_COMPAT
 static const struct file_operations proc_reg_file_ops_compat = {
 	.llseek		= proc_reg_llseek,
@@ -591,6 +618,19 @@ static const struct file_operations proc_reg_file_ops_compat = {
 	.open		= proc_reg_open,
 	.release	= proc_reg_release,
 };
+
+static const struct file_operations proc_iter_file_ops_compat = {
+	.llseek		= proc_reg_llseek,
+	.read_iter	= proc_reg_read_iter,
+	.write		= proc_reg_write,
+	.poll		= proc_reg_poll,
+	.unlocked_ioctl	= proc_reg_unlocked_ioctl,
+	.compat_ioctl	= proc_reg_compat_ioctl,
+	.mmap		= proc_reg_mmap,
+	.get_unmapped_area = proc_reg_get_unmapped_area,
+	.open		= proc_reg_open,
+	.release	= proc_reg_release,
+};
 #endif
 
 static void proc_put_link(void *p)
@@ -642,10 +682,17 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
 
 	if (S_ISREG(inode->i_mode)) {
 		inode->i_op = de->proc_iops;
-		inode->i_fop = &proc_reg_file_ops;
+		if (de->proc_ops->proc_read_iter)
+			inode->i_fop = &proc_iter_file_ops;
+		else
+			inode->i_fop = &proc_reg_file_ops;
 #ifdef CONFIG_COMPAT
-		if (de->proc_ops->proc_compat_ioctl)
-			inode->i_fop = &proc_reg_file_ops_compat;
+		if (de->proc_ops->proc_compat_ioctl) {
+			if (de->proc_ops->proc_read_iter)
+				inode->i_fop = &proc_iter_file_ops_compat;
+			else
+				inode->i_fop = &proc_reg_file_ops_compat;
+		}
 #endif
 	} else if (S_ISDIR(inode->i_mode)) {
 		inode->i_op = de->proc_iops;
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index 2df965cd0974..270cab43ca3d 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -30,6 +30,7 @@ struct proc_ops {
 	unsigned int proc_flags;
 	int	(*proc_open)(struct inode *, struct file *);
 	ssize_t	(*proc_read)(struct file *, char __user *, size_t, loff_t *);
+	ssize_t (*proc_read_iter)(struct kiocb *, struct iov_iter *);
 	ssize_t	(*proc_write)(struct file *, const char __user *, size_t, loff_t *);
 	loff_t	(*proc_lseek)(struct file *, loff_t, int);
 	int	(*proc_release)(struct inode *, struct file *);
-- 
cgit v1.2.3


From aae4c8e27bd7567132bb931488e2faf1a57c66e9 Mon Sep 17 00:00:00 2001
From: Tom Murphy <murphyt7@tcd.ie>
Date: Mon, 17 Aug 2020 22:00:49 +0100
Subject: iommu: Rename iommu_tlb_* functions to iommu_iotlb_*

To keep naming consistent we should stick with *iotlb*. This patch
renames a few remaining functions.

Signed-off-by: Tom Murphy <murphyt7@tcd.ie>
Link: https://lore.kernel.org/r/20200817210051.13546-1-murphyt7@tcd.ie
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/dma-iommu.c       |  2 +-
 drivers/iommu/iommu.c           |  4 ++--
 drivers/vfio/vfio_iommu_type1.c |  2 +-
 include/linux/io-pgtable.h      |  2 +-
 include/linux/iommu.h           | 10 +++++-----
 5 files changed, 10 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 5141d49a046b..3afd076e9f36 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -471,7 +471,7 @@ static void __iommu_dma_unmap(struct device *dev, dma_addr_t dma_addr,
 	WARN_ON(unmapped != size);
 
 	if (!cookie->fq_domain)
-		iommu_tlb_sync(domain, &iotlb_gather);
+		iommu_iotlb_sync(domain, &iotlb_gather);
 	iommu_dma_free_iova(cookie, dma_addr, size);
 }
 
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 609bd25bf154..6c14c88cd525 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -762,7 +762,7 @@ static int iommu_create_device_direct_mappings(struct iommu_group *group,
 
 	}
 
-	iommu_flush_tlb_all(domain);
+	iommu_flush_iotlb_all(domain);
 
 out:
 	iommu_put_resv_regions(dev, &mappings);
@@ -2316,7 +2316,7 @@ size_t iommu_unmap(struct iommu_domain *domain,
 
 	iommu_iotlb_gather_init(&iotlb_gather);
 	ret = __iommu_unmap(domain, iova, size, &iotlb_gather);
-	iommu_tlb_sync(domain, &iotlb_gather);
+	iommu_iotlb_sync(domain, &iotlb_gather);
 
 	return ret;
 }
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 5fbf0c1f7433..c255a6683f31 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -774,7 +774,7 @@ static long vfio_sync_unpin(struct vfio_dma *dma, struct vfio_domain *domain,
 	long unlocked = 0;
 	struct vfio_regions *entry, *next;
 
-	iommu_tlb_sync(domain->domain, iotlb_gather);
+	iommu_iotlb_sync(domain->domain, iotlb_gather);
 
 	list_for_each_entry_safe(entry, next, regions, list) {
 		unlocked += vfio_unpin_pages_remote(dma,
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 23285ba645db..4cde111e425b 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -31,7 +31,7 @@ enum io_pgtable_fmt {
  *                  single page.  IOMMUs that cannot batch TLB invalidation
  *                  operations efficiently will typically issue them here, but
  *                  others may decide to update the iommu_iotlb_gather structure
- *                  and defer the invalidation until iommu_tlb_sync() instead.
+ *                  and defer the invalidation until iommu_iotlb_sync() instead.
  *
  * Note that these can all be called in atomic context and must therefore
  * not block.
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index fee209efb756..2ad26d8b4ab9 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -514,13 +514,13 @@ extern void iommu_domain_window_disable(struct iommu_domain *domain, u32 wnd_nr)
 extern int report_iommu_fault(struct iommu_domain *domain, struct device *dev,
 			      unsigned long iova, int flags);
 
-static inline void iommu_flush_tlb_all(struct iommu_domain *domain)
+static inline void iommu_flush_iotlb_all(struct iommu_domain *domain)
 {
 	if (domain->ops->flush_iotlb_all)
 		domain->ops->flush_iotlb_all(domain);
 }
 
-static inline void iommu_tlb_sync(struct iommu_domain *domain,
+static inline void iommu_iotlb_sync(struct iommu_domain *domain,
 				  struct iommu_iotlb_gather *iotlb_gather)
 {
 	if (domain->ops->iotlb_sync)
@@ -543,7 +543,7 @@ static inline void iommu_iotlb_gather_add_page(struct iommu_domain *domain,
 	if (gather->pgsize != size ||
 	    end < gather->start || start > gather->end) {
 		if (gather->pgsize)
-			iommu_tlb_sync(domain, gather);
+			iommu_iotlb_sync(domain, gather);
 		gather->pgsize = size;
 	}
 
@@ -725,11 +725,11 @@ static inline size_t iommu_map_sg_atomic(struct iommu_domain *domain,
 	return 0;
 }
 
-static inline void iommu_flush_tlb_all(struct iommu_domain *domain)
+static inline void iommu_flush_iotlb_all(struct iommu_domain *domain)
 {
 }
 
-static inline void iommu_tlb_sync(struct iommu_domain *domain,
+static inline void iommu_iotlb_sync(struct iommu_domain *domain,
 				  struct iommu_iotlb_gather *iotlb_gather)
 {
 }
-- 
cgit v1.2.3


From 25e804926da39f1de7ae486920bfe65b099195f1 Mon Sep 17 00:00:00 2001
From: Vinod Koul <vkoul@kernel.org>
Date: Thu, 3 Sep 2020 17:14:56 +0530
Subject: soundwire: define and use addr bit masks

Soundwire addr is a 52bit value encoding link, version, unique id,
mfg id, part id and class id. Define bit masks for these and use
FIELD_GET() to extract these fields.

Signed-off-by: Vinod Koul <vkoul@kernel.org>
Tested-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20200903114504.1202143-2-vkoul@kernel.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/soundwire/sdw.h | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 78f52cdeb2c9..1e9010c139f0 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -5,6 +5,7 @@
 #define __SOUNDWIRE_H
 
 #include <linux/mod_devicetable.h>
+#include <linux/bitfield.h>
 
 struct sdw_bus;
 struct sdw_slave;
@@ -456,13 +457,19 @@ struct sdw_slave_id {
  *
  * The MIPI DisCo for SoundWire defines in addition the link_id as bits 51:48
  */
-
-#define SDW_DISCO_LINK_ID(adr)	(((adr) >> 48) & GENMASK(3, 0))
-#define SDW_VERSION(adr)	(((adr) >> 44) & GENMASK(3, 0))
-#define SDW_UNIQUE_ID(adr)	(((adr) >> 40) & GENMASK(3, 0))
-#define SDW_MFG_ID(adr)		(((adr) >> 24) & GENMASK(15, 0))
-#define SDW_PART_ID(adr)	(((adr) >> 8) & GENMASK(15, 0))
-#define SDW_CLASS_ID(adr)	((adr) & GENMASK(7, 0))
+#define SDW_DISCO_LINK_ID_MASK	GENMASK_ULL(51, 48)
+#define SDW_VERSION_MASK	GENMASK_ULL(47, 44)
+#define SDW_UNIQUE_ID_MASK	GENMASK_ULL(43, 40)
+#define SDW_MFG_ID_MASK		GENMASK_ULL(39, 24)
+#define SDW_PART_ID_MASK	GENMASK_ULL(23, 8)
+#define SDW_CLASS_ID_MASK	GENMASK_ULL(7, 0)
+
+#define SDW_DISCO_LINK_ID(addr)	FIELD_GET(SDW_DISCO_LINK_ID_MASK, addr)
+#define SDW_VERSION(addr)	FIELD_GET(SDW_VERSION_MASK, addr)
+#define SDW_UNIQUE_ID(addr)	FIELD_GET(SDW_UNIQUE_ID_MASK, addr)
+#define SDW_MFG_ID(addr)	FIELD_GET(SDW_MFG_ID_MASK, addr)
+#define SDW_PART_ID(addr)	FIELD_GET(SDW_PART_ID_MASK, addr)
+#define SDW_CLASS_ID(addr)	FIELD_GET(SDW_CLASS_ID_MASK, addr)
 
 /**
  * struct sdw_slave_intr_status - Slave interrupt status
-- 
cgit v1.2.3


From 8be2f84acf2317068c93fea291d823ac30d172d6 Mon Sep 17 00:00:00 2001
From: Vinod Koul <vkoul@kernel.org>
Date: Thu, 3 Sep 2020 17:15:04 +0530
Subject: soundwire: remove SDW_REG_SHIFT()

soundwire had defined SDW_REG_SHIFT to calculate shift values for
bitmasks, but now that we have better things in bitfield.h, remove this.

Signed-off-by: Vinod Koul <vkoul@kernel.org>
Tested-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20200903114504.1202143-10-vkoul@kernel.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/soundwire/sdw_registers.h | 7 -------
 1 file changed, 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/soundwire/sdw_registers.h b/include/linux/soundwire/sdw_registers.h
index 5d3c271af7d1..f420e8059779 100644
--- a/include/linux/soundwire/sdw_registers.h
+++ b/include/linux/soundwire/sdw_registers.h
@@ -4,13 +4,6 @@
 #ifndef __SDW_REGISTERS_H
 #define __SDW_REGISTERS_H
 
-/*
- * typically we define register and shifts but if one observes carefully,
- * the shift can be generated from MASKS using few bit primitaives like ffs
- * etc, so we use that and avoid defining shifts
- */
-#define SDW_REG_SHIFT(n)			(ffs(n) - 1)
-
 /*
  * SDW registers as defined by MIPI 1.2 Spec
  */
-- 
cgit v1.2.3


From c7eb900f5f45eeab1ea1bed997a2a12d8b5907bc Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 28 Aug 2020 19:12:11 +0300
Subject: iommu/vt-d: Move intel_iommu_gfx_mapped to Intel IOMMU header

Static analyzer is not happy about intel_iommu_gfx_mapped declaration:

.../drivers/iommu/intel/iommu.c:364:5: warning: symbol 'intel_iommu_gfx_mapped' was not declared. Should it be static?

Move its declaration to Intel IOMMU header file.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20200828161212.71294-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 include/drm/intel-gtt.h     | 5 +----
 include/linux/intel-iommu.h | 1 +
 2 files changed, 2 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/drm/intel-gtt.h b/include/drm/intel-gtt.h
index 71d81923e6b0..abfefaaf897a 100644
--- a/include/drm/intel-gtt.h
+++ b/include/drm/intel-gtt.h
@@ -5,6 +5,7 @@
 #define	_DRM_INTEL_GTT_H
 
 #include <linux/agp_backend.h>
+#include <linux/intel-iommu.h>
 #include <linux/kernel.h>
 
 void intel_gtt_get(u64 *gtt_total,
@@ -33,8 +34,4 @@ void intel_gtt_clear_range(unsigned int first_entry, unsigned int num_entries);
 /* flag for GFDT type */
 #define AGP_USER_CACHED_MEMORY_GFDT (1 << 3)
 
-#ifdef CONFIG_INTEL_IOMMU
-extern int intel_iommu_gfx_mapped;
-#endif
-
 #endif
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index b1ed2f25f7c0..6a3ddaabf3f5 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -792,6 +792,7 @@ extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu);
 extern int dmar_disabled;
 extern int intel_iommu_enabled;
 extern int intel_iommu_tboot_noforce;
+extern int intel_iommu_gfx_mapped;
 #else
 static inline int iommu_calculate_agaw(struct intel_iommu *iommu)
 {
-- 
cgit v1.2.3


From c2c59456e1fcad3f464761c5839399176e3a934a Mon Sep 17 00:00:00 2001
From: Miles Chen <miles.chen@mediatek.com>
Date: Fri, 4 Sep 2020 18:40:38 +0800
Subject: iommu/mediatek: Check 4GB mode by reading infracfg

In previous discussion [1] and [2], we found that it is risky to
use max_pfn or totalram_pages to tell if 4GB mode is enabled.

Check 4GB mode by reading infracfg register, remove the usage
of the un-exported symbol max_pfn.

This is a step towards building mtk_iommu as a kernel module.

[1] https://lore.kernel.org/lkml/20200603161132.2441-1-miles.chen@mediatek.com/
[2] https://lore.kernel.org/lkml/20200604080120.2628-1-miles.chen@mediatek.com/
[3] https://lore.kernel.org/lkml/20200715205120.GA778876@bogus/

Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Yong Wu <yong.wu@mediatek.com>
Cc: Yingjoe Chen <yingjoe.chen@mediatek.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Rob Herring <robh@kernel.org>
Cc: Matthias Brugger <matthias.bgg@gmail.com>
Cc: Joerg Roedel <joro@8bytes.org>
Reviewed-by: Matthias Brugger <matthias.bgg@gmail.com>
Signed-off-by: Miles Chen <miles.chen@mediatek.com>
Link: https://lore.kernel.org/r/20200904104038.4979-1-miles.chen@mediatek.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/mtk_iommu.c             | 33 ++++++++++++++++++++++++++++-----
 include/linux/soc/mediatek/infracfg.h |  3 +++
 2 files changed, 31 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index b99c2b4b48ca..94f676659ed5 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -3,7 +3,6 @@
  * Copyright (c) 2015-2016 MediaTek Inc.
  * Author: Yong Wu <yong.wu@mediatek.com>
  */
-#include <linux/memblock.h>
 #include <linux/bug.h>
 #include <linux/clk.h>
 #include <linux/component.h>
@@ -15,13 +14,16 @@
 #include <linux/iommu.h>
 #include <linux/iopoll.h>
 #include <linux/list.h>
+#include <linux/mfd/syscon.h>
 #include <linux/of_address.h>
 #include <linux/of_iommu.h>
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
 #include <linux/platform_device.h>
+#include <linux/regmap.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/soc/mediatek/infracfg.h>
 #include <asm/barrier.h>
 #include <soc/mediatek/smi.h>
 
@@ -640,8 +642,11 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 	struct resource         *res;
 	resource_size_t		ioaddr;
 	struct component_match  *match = NULL;
+	struct regmap		*infracfg;
 	void                    *protect;
 	int                     i, larb_nr, ret;
+	u32			val;
+	char                    *p;
 
 	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
 	if (!data)
@@ -655,10 +660,28 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	data->protect_base = ALIGN(virt_to_phys(protect), MTK_PROTECT_PA_ALIGN);
 
-	/* Whether the current dram is over 4GB */
-	data->enable_4GB = !!(max_pfn > (BIT_ULL(32) >> PAGE_SHIFT));
-	if (!MTK_IOMMU_HAS_FLAG(data->plat_data, HAS_4GB_MODE))
-		data->enable_4GB = false;
+	if (MTK_IOMMU_HAS_FLAG(data->plat_data, HAS_4GB_MODE)) {
+		switch (data->plat_data->m4u_plat) {
+		case M4U_MT2712:
+			p = "mediatek,mt2712-infracfg";
+			break;
+		case M4U_MT8173:
+			p = "mediatek,mt8173-infracfg";
+			break;
+		default:
+			p = NULL;
+		}
+
+		infracfg = syscon_regmap_lookup_by_compatible(p);
+
+		if (IS_ERR(infracfg))
+			return PTR_ERR(infracfg);
+
+		ret = regmap_read(infracfg, REG_INFRA_MISC, &val);
+		if (ret)
+			return ret;
+		data->enable_4GB = !!(val & F_DDR_4GB_SUPPORT_EN);
+	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	data->base = devm_ioremap_resource(dev, res);
diff --git a/include/linux/soc/mediatek/infracfg.h b/include/linux/soc/mediatek/infracfg.h
index fd25f0148566..233463d789c6 100644
--- a/include/linux/soc/mediatek/infracfg.h
+++ b/include/linux/soc/mediatek/infracfg.h
@@ -32,6 +32,9 @@
 #define MT7622_TOP_AXI_PROT_EN_WB		(BIT(2) | BIT(6) | \
 						 BIT(7) | BIT(8))
 
+#define REG_INFRA_MISC				0xf00
+#define F_DDR_4GB_SUPPORT_EN			BIT(13)
+
 int mtk_infracfg_set_bus_protection(struct regmap *infracfg, u32 mask,
 		bool reg_update);
 int mtk_infracfg_clear_bus_protection(struct regmap *infracfg, u32 mask,
-- 
cgit v1.2.3


From 4beba9486abd2f86d125271d6946f7c38ed0fe77 Mon Sep 17 00:00:00 2001
From: Steven Price <steven.price@arm.com>
Date: Wed, 22 Apr 2020 15:25:27 +0100
Subject: mm: Add PG_arch_2 page flag

For arm64 MTE support it is necessary to be able to mark pages that
contain user space visible tags that will need to be saved/restored e.g.
when swapped out.

To support this add a new arch specific flag (PG_arch_2). This flag is
only available on 64-bit architectures due to the limited number of
spare page flags on the 32-bit ones.

Signed-off-by: Steven Price <steven.price@arm.com>
[catalin.marinas@arm.com: use CONFIG_64BIT for guarding this new flag]
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
---
 fs/proc/page.c                    | 3 +++
 include/linux/kernel-page-flags.h | 1 +
 include/linux/page-flags.h        | 3 +++
 include/trace/events/mmflags.h    | 9 ++++++++-
 tools/vm/page-types.c             | 2 ++
 5 files changed, 17 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/fs/proc/page.c b/fs/proc/page.c
index f909243d4a66..9f1077d94cde 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -217,6 +217,9 @@ u64 stable_page_flags(struct page *page)
 	u |= kpf_copy_bit(k, KPF_PRIVATE_2,	PG_private_2);
 	u |= kpf_copy_bit(k, KPF_OWNER_PRIVATE,	PG_owner_priv_1);
 	u |= kpf_copy_bit(k, KPF_ARCH,		PG_arch_1);
+#ifdef CONFIG_64BIT
+	u |= kpf_copy_bit(k, KPF_ARCH_2,	PG_arch_2);
+#endif
 
 	return u;
 };
diff --git a/include/linux/kernel-page-flags.h b/include/linux/kernel-page-flags.h
index abd20ef93c98..eee1877a354e 100644
--- a/include/linux/kernel-page-flags.h
+++ b/include/linux/kernel-page-flags.h
@@ -17,5 +17,6 @@
 #define KPF_ARCH		38
 #define KPF_UNCACHED		39
 #define KPF_SOFTDIRTY		40
+#define KPF_ARCH_2		41
 
 #endif /* LINUX_KERNEL_PAGE_FLAGS_H */
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 6be1aa559b1e..276140c94f4a 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -135,6 +135,9 @@ enum pageflags {
 #if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT)
 	PG_young,
 	PG_idle,
+#endif
+#ifdef CONFIG_64BIT
+	PG_arch_2,
 #endif
 	__NR_PAGEFLAGS,
 
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index 5fb752034386..67018d367b9f 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -79,6 +79,12 @@
 #define IF_HAVE_PG_IDLE(flag,string)
 #endif
 
+#ifdef CONFIG_64BIT
+#define IF_HAVE_PG_ARCH_2(flag,string) ,{1UL << flag, string}
+#else
+#define IF_HAVE_PG_ARCH_2(flag,string)
+#endif
+
 #define __def_pageflag_names						\
 	{1UL << PG_locked,		"locked"	},		\
 	{1UL << PG_waiters,		"waiters"	},		\
@@ -105,7 +111,8 @@ IF_HAVE_PG_MLOCK(PG_mlocked,		"mlocked"	)		\
 IF_HAVE_PG_UNCACHED(PG_uncached,	"uncached"	)		\
 IF_HAVE_PG_HWPOISON(PG_hwpoison,	"hwpoison"	)		\
 IF_HAVE_PG_IDLE(PG_young,		"young"		)		\
-IF_HAVE_PG_IDLE(PG_idle,		"idle"		)
+IF_HAVE_PG_IDLE(PG_idle,		"idle"		)		\
+IF_HAVE_PG_ARCH_2(PG_arch_2,		"arch_2"	)
 
 #define show_page_flags(flags)						\
 	(flags) ? __print_flags(flags, "|",				\
diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c
index 58c0eab71bca..0517c744b04e 100644
--- a/tools/vm/page-types.c
+++ b/tools/vm/page-types.c
@@ -78,6 +78,7 @@
 #define KPF_ARCH		38
 #define KPF_UNCACHED		39
 #define KPF_SOFTDIRTY		40
+#define KPF_ARCH_2		41
 
 /* [48-] take some arbitrary free slots for expanding overloaded flags
  * not part of kernel API
@@ -135,6 +136,7 @@ static const char * const page_flag_names[] = {
 	[KPF_ARCH]		= "h:arch",
 	[KPF_UNCACHED]		= "c:uncached",
 	[KPF_SOFTDIRTY]		= "f:softdirty",
+	[KPF_ARCH_2]		= "H:arch_2",
 
 	[KPF_READAHEAD]		= "I:readahead",
 	[KPF_SLOB_FREE]		= "P:slob_free",
-- 
cgit v1.2.3


From b3fbbea4c00220f62e6f7e2514466e6ee81f7f60 Mon Sep 17 00:00:00 2001
From: Kevin Brodsky <Kevin.Brodsky@arm.com>
Date: Mon, 25 Nov 2019 17:27:06 +0000
Subject: mm: Introduce arch_calc_vm_flag_bits()

Similarly to arch_calc_vm_prot_bits(), introduce a dummy
arch_calc_vm_flag_bits() invoked from calc_vm_flag_bits(). This macro
can be overridden by architectures to insert specific VM_* flags derived
from the mmap() MAP_* flags.

Signed-off-by: Kevin Brodsky <Kevin.Brodsky@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mman.h | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mman.h b/include/linux/mman.h
index 6f34c33075f9..6fa15c9b12af 100644
--- a/include/linux/mman.h
+++ b/include/linux/mman.h
@@ -78,13 +78,18 @@ static inline void vm_unacct_memory(long pages)
 }
 
 /*
- * Allow architectures to handle additional protection bits
+ * Allow architectures to handle additional protection and flag bits. The
+ * overriding macros must be defined in the arch-specific asm/mman.h file.
  */
 
 #ifndef arch_calc_vm_prot_bits
 #define arch_calc_vm_prot_bits(prot, pkey) 0
 #endif
 
+#ifndef arch_calc_vm_flag_bits
+#define arch_calc_vm_flag_bits(flags) 0
+#endif
+
 #ifndef arch_vm_get_page_prot
 #define arch_vm_get_page_prot(vm_flags) __pgprot(0)
 #endif
@@ -135,7 +140,8 @@ calc_vm_flag_bits(unsigned long flags)
 	return _calc_vm_trans(flags, MAP_GROWSDOWN,  VM_GROWSDOWN ) |
 	       _calc_vm_trans(flags, MAP_DENYWRITE,  VM_DENYWRITE ) |
 	       _calc_vm_trans(flags, MAP_LOCKED,     VM_LOCKED    ) |
-	       _calc_vm_trans(flags, MAP_SYNC,	     VM_SYNC      );
+	       _calc_vm_trans(flags, MAP_SYNC,	     VM_SYNC      ) |
+	       arch_calc_vm_flag_bits(flags);
 }
 
 unsigned long vm_commit_limit(void);
-- 
cgit v1.2.3


From 9f3419315f3cdc41a7318e4d50ba18a592b30c8c Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Wed, 27 Nov 2019 10:00:27 +0000
Subject: arm64: mte: Add PROT_MTE support to mmap() and mprotect()

To enable tagging on a memory range, the user must explicitly opt in via
a new PROT_MTE flag passed to mmap() or mprotect(). Since this is a new
memory type in the AttrIndx field of a pte, simplify the or'ing of these
bits over the protection_map[] attributes by making MT_NORMAL index 0.

There are two conditions for arch_vm_get_page_prot() to return the
MT_NORMAL_TAGGED memory type: (1) the user requested it via PROT_MTE,
registered as VM_MTE in the vm_flags, and (2) the vma supports MTE,
decided during the mmap() call (only) and registered as VM_MTE_ALLOWED.

arch_calc_vm_prot_bits() is responsible for registering the user request
as VM_MTE. The newly introduced arch_calc_vm_flag_bits() sets
VM_MTE_ALLOWED if the mapping is MAP_ANONYMOUS. An MTE-capable
filesystem (RAM-based) may be able to set VM_MTE_ALLOWED during its
mmap() file ops call.

In addition, update VM_DATA_DEFAULT_FLAGS to allow mprotect(PROT_MTE) on
stack or brk area.

The Linux mmap() syscall currently ignores unknown PROT_* flags. In the
presence of MTE, an mmap(PROT_MTE) on a file which does not support MTE
will not report an error and the memory will not be mapped as Normal
Tagged. For consistency, mprotect(PROT_MTE) will not report an error
either if the memory range does not support MTE. Two subsequent patches
in the series will propose tightening of this behaviour.

Co-developed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Signed-off-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/memory.h    | 18 ++++++++++------
 arch/arm64/include/asm/mman.h      | 44 +++++++++++++++++++++++++++++++++++---
 arch/arm64/include/asm/page.h      |  2 +-
 arch/arm64/include/asm/pgtable.h   |  7 +++++-
 arch/arm64/include/uapi/asm/mman.h |  1 +
 fs/proc/task_mmu.c                 |  4 ++++
 include/linux/mm.h                 |  8 +++++++
 7 files changed, 72 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 1e0a78266410..e424fc3a68cb 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -126,14 +126,18 @@
 
 /*
  * Memory types available.
+ *
+ * IMPORTANT: MT_NORMAL must be index 0 since vm_get_page_prot() may 'or' in
+ *	      the MT_NORMAL_TAGGED memory type for PROT_MTE mappings. Note
+ *	      that protection_map[] only contains MT_NORMAL attributes.
  */
-#define MT_DEVICE_nGnRnE	0
-#define MT_DEVICE_nGnRE		1
-#define MT_DEVICE_GRE		2
-#define MT_NORMAL_NC		3
-#define MT_NORMAL		4
-#define MT_NORMAL_WT		5
-#define MT_NORMAL_TAGGED	6
+#define MT_NORMAL		0
+#define MT_NORMAL_TAGGED	1
+#define MT_NORMAL_NC		2
+#define MT_NORMAL_WT		3
+#define MT_DEVICE_nGnRnE	4
+#define MT_DEVICE_nGnRE		5
+#define MT_DEVICE_GRE		6
 
 /*
  * Memory types for Stage-2 translation
diff --git a/arch/arm64/include/asm/mman.h b/arch/arm64/include/asm/mman.h
index 081ec8de9ea6..b01051be7750 100644
--- a/arch/arm64/include/asm/mman.h
+++ b/arch/arm64/include/asm/mman.h
@@ -9,16 +9,51 @@
 static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot,
 	unsigned long pkey __always_unused)
 {
+	unsigned long ret = 0;
+
 	if (system_supports_bti() && (prot & PROT_BTI))
-		return VM_ARM64_BTI;
+		ret |= VM_ARM64_BTI;
 
-	return 0;
+	if (system_supports_mte() && (prot & PROT_MTE))
+		ret |= VM_MTE;
+
+	return ret;
 }
 #define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey)
 
+static inline unsigned long arch_calc_vm_flag_bits(unsigned long flags)
+{
+	/*
+	 * Only allow MTE on anonymous mappings as these are guaranteed to be
+	 * backed by tags-capable memory. The vm_flags may be overridden by a
+	 * filesystem supporting MTE (RAM-based).
+	 */
+	if (system_supports_mte() && (flags & MAP_ANONYMOUS))
+		return VM_MTE_ALLOWED;
+
+	return 0;
+}
+#define arch_calc_vm_flag_bits(flags) arch_calc_vm_flag_bits(flags)
+
 static inline pgprot_t arch_vm_get_page_prot(unsigned long vm_flags)
 {
-	return (vm_flags & VM_ARM64_BTI) ? __pgprot(PTE_GP) : __pgprot(0);
+	pteval_t prot = 0;
+
+	if (vm_flags & VM_ARM64_BTI)
+		prot |= PTE_GP;
+
+	/*
+	 * There are two conditions required for returning a Normal Tagged
+	 * memory type: (1) the user requested it via PROT_MTE passed to
+	 * mmap() or mprotect() and (2) the corresponding vma supports MTE. We
+	 * register (1) as VM_MTE in the vma->vm_flags and (2) as
+	 * VM_MTE_ALLOWED. Note that the latter can only be set during the
+	 * mmap() call since mprotect() does not accept MAP_* flags.
+	 */
+	if ((vm_flags & VM_MTE) && (vm_flags & VM_MTE_ALLOWED))
+		prot |= PTE_ATTRINDX(MT_NORMAL_TAGGED);
+
+	return __pgprot(prot);
 }
 #define arch_vm_get_page_prot(vm_flags) arch_vm_get_page_prot(vm_flags)
 
@@ -30,6 +65,9 @@ static inline bool arch_validate_prot(unsigned long prot,
 	if (system_supports_bti())
 		supported |= PROT_BTI;
 
+	if (system_supports_mte())
+		supported |= PROT_MTE;
+
 	return (prot & ~supported) == 0;
 }
 #define arch_validate_prot(prot, addr) arch_validate_prot(prot, addr)
diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h
index d918cb1d83a6..012cffc574e8 100644
--- a/arch/arm64/include/asm/page.h
+++ b/arch/arm64/include/asm/page.h
@@ -43,7 +43,7 @@ extern int pfn_valid(unsigned long);
 
 #endif /* !__ASSEMBLY__ */
 
-#define VM_DATA_DEFAULT_FLAGS	VM_DATA_FLAGS_TSK_EXEC
+#define VM_DATA_DEFAULT_FLAGS	(VM_DATA_FLAGS_TSK_EXEC | VM_MTE_ALLOWED)
 
 #include <asm-generic/getorder.h>
 
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 0a205a8e91b2..057c40b6f5e0 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -681,8 +681,13 @@ static inline unsigned long p4d_page_vaddr(p4d_t p4d)
 
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
+	/*
+	 * Normal and Normal-Tagged are two different memory types and indices
+	 * in MAIR_EL1. The mask below has to include PTE_ATTRINDX_MASK.
+	 */
 	const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY |
-			      PTE_PROT_NONE | PTE_VALID | PTE_WRITE | PTE_GP;
+			      PTE_PROT_NONE | PTE_VALID | PTE_WRITE | PTE_GP |
+			      PTE_ATTRINDX_MASK;
 	/* preserve the hardware dirty information */
 	if (pte_hw_dirty(pte))
 		pte = pte_mkdirty(pte);
diff --git a/arch/arm64/include/uapi/asm/mman.h b/arch/arm64/include/uapi/asm/mman.h
index 6fdd71eb644f..1e6482a838e1 100644
--- a/arch/arm64/include/uapi/asm/mman.h
+++ b/arch/arm64/include/uapi/asm/mman.h
@@ -5,5 +5,6 @@
 #include <asm-generic/mman.h>
 
 #define PROT_BTI	0x10		/* BTI guarded page */
+#define PROT_MTE	0x20		/* Normal Tagged mapping */
 
 #endif /* ! _UAPI__ASM_MMAN_H */
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 5066b0251ed8..35172a91148e 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -653,6 +653,10 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
 		[ilog2(VM_MERGEABLE)]	= "mg",
 		[ilog2(VM_UFFD_MISSING)]= "um",
 		[ilog2(VM_UFFD_WP)]	= "uw",
+#ifdef CONFIG_ARM64_MTE
+		[ilog2(VM_MTE)]		= "mt",
+		[ilog2(VM_MTE_ALLOWED)]	= "",
+#endif
 #ifdef CONFIG_ARCH_HAS_PKEYS
 		/* These come out via ProtectionKey: */
 		[ilog2(VM_PKEY_BIT0)]	= "",
diff --git a/include/linux/mm.h b/include/linux/mm.h
index ca6e6a81576b..4312c6c808e9 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -340,6 +340,14 @@ extern unsigned int kobjsize(const void *objp);
 # define VM_MAPPED_COPY	VM_ARCH_1	/* T if mapped copy of data (nommu mmap) */
 #endif
 
+#if defined(CONFIG_ARM64_MTE)
+# define VM_MTE		VM_HIGH_ARCH_0	/* Use Tagged memory for access control */
+# define VM_MTE_ALLOWED	VM_HIGH_ARCH_1	/* Tagged memory permitted */
+#else
+# define VM_MTE		VM_NONE
+# define VM_MTE_ALLOWED	VM_NONE
+#endif
+
 #ifndef VM_GROWSUP
 # define VM_GROWSUP	VM_NONE
 #endif
-- 
cgit v1.2.3


From c462ac288f2c97e0c1d9ff6a65955317e799f958 Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Mon, 25 Nov 2019 17:27:06 +0000
Subject: mm: Introduce arch_validate_flags()

Similarly to arch_validate_prot() called from do_mprotect_pkey(), an
architecture may need to sanity-check the new vm_flags.

Define a dummy function always returning true. In addition to
do_mprotect_pkey(), also invoke it from mmap_region() prior to updating
vma->vm_page_prot to allow the architecture code to veto potentially
inconsistent vm_flags.

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mman.h | 13 +++++++++++++
 mm/mmap.c            |  9 +++++++++
 mm/mprotect.c        |  6 ++++++
 3 files changed, 28 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/mman.h b/include/linux/mman.h
index 6fa15c9b12af..629cefc4ecba 100644
--- a/include/linux/mman.h
+++ b/include/linux/mman.h
@@ -108,6 +108,19 @@ static inline bool arch_validate_prot(unsigned long prot, unsigned long addr)
 #define arch_validate_prot arch_validate_prot
 #endif
 
+#ifndef arch_validate_flags
+/*
+ * This is called from mmap() and mprotect() with the updated vma->vm_flags.
+ *
+ * Returns true if the VM_* flags are valid.
+ */
+static inline bool arch_validate_flags(unsigned long flags)
+{
+	return true;
+}
+#define arch_validate_flags arch_validate_flags
+#endif
+
 /*
  * Optimisation macro.  It is equivalent to:
  *      (x & bit1) ? bit2 : 0
diff --git a/mm/mmap.c b/mm/mmap.c
index 40248d84ad5f..eed30b096667 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1812,6 +1812,15 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 		vma_set_anonymous(vma);
 	}
 
+	/* Allow architectures to sanity-check the vm_flags */
+	if (!arch_validate_flags(vma->vm_flags)) {
+		error = -EINVAL;
+		if (file)
+			goto unmap_and_free_vma;
+		else
+			goto free_vma;
+	}
+
 	vma_link(mm, vma, prev, rb_link, rb_parent);
 	/* Once vma denies write, undo our temporary denial count */
 	if (file) {
diff --git a/mm/mprotect.c b/mm/mprotect.c
index ce8b8a5eacbb..56c02beb6041 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -603,6 +603,12 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
 			goto out;
 		}
 
+		/* Allow architectures to sanity-check the new flags */
+		if (!arch_validate_flags(newflags)) {
+			error = -EINVAL;
+			goto out;
+		}
+
 		error = security_file_mprotect(vma, reqprot, prot);
 		if (error)
 			goto out;
-- 
cgit v1.2.3


From 8a84802e2a2b1a682761a31c2685506b9f4e1840 Mon Sep 17 00:00:00 2001
From: Steven Price <steven.price@arm.com>
Date: Wed, 13 May 2020 16:37:49 +0100
Subject: mm: Add arch hooks for saving/restoring tags

Arm's Memory Tagging Extension (MTE) adds some metadata (tags) to
every physical page, when swapping pages out to disk it is necessary to
save these tags, and later restore them when reading the pages back.

Add some hooks along with dummy implementations to enable the
arch code to handle this.

Three new hooks are added to the swap code:
 * arch_prepare_to_swap() and
 * arch_swap_invalidate_page() / arch_swap_invalidate_area().
One new hook is added to shmem:
 * arch_swap_restore()

Signed-off-by: Steven Price <steven.price@arm.com>
[catalin.marinas@arm.com: add unlock_page() on the error path]
[catalin.marinas@arm.com: dropped the _tags suffix]
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/pgtable.h | 28 ++++++++++++++++++++++++++++
 mm/page_io.c            | 10 ++++++++++
 mm/shmem.c              |  6 ++++++
 mm/swapfile.c           |  2 ++
 4 files changed, 46 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index e8cbc2e795d5..dc3b74129fbc 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -633,6 +633,34 @@ static inline int arch_unmap_one(struct mm_struct *mm,
 }
 #endif
 
+/*
+ * Allow architectures to preserve additional metadata associated with
+ * swapped-out pages. The corresponding __HAVE_ARCH_SWAP_* macros and function
+ * prototypes must be defined in the arch-specific asm/pgtable.h file.
+ */
+#ifndef __HAVE_ARCH_PREPARE_TO_SWAP
+static inline int arch_prepare_to_swap(struct page *page)
+{
+	return 0;
+}
+#endif
+
+#ifndef __HAVE_ARCH_SWAP_INVALIDATE
+static inline void arch_swap_invalidate_page(int type, pgoff_t offset)
+{
+}
+
+static inline void arch_swap_invalidate_area(int type)
+{
+}
+#endif
+
+#ifndef __HAVE_ARCH_SWAP_RESTORE
+static inline void arch_swap_restore(swp_entry_t entry, struct page *page)
+{
+}
+#endif
+
 #ifndef __HAVE_ARCH_PGD_OFFSET_GATE
 #define pgd_offset_gate(mm, addr)	pgd_offset(mm, addr)
 #endif
diff --git a/mm/page_io.c b/mm/page_io.c
index e485a6e8a6cd..4ca28aad0d94 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -252,6 +252,16 @@ int swap_writepage(struct page *page, struct writeback_control *wbc)
 		unlock_page(page);
 		goto out;
 	}
+	/*
+	 * Arch code may have to preserve more data than just the page
+	 * contents, e.g. memory tags.
+	 */
+	ret = arch_prepare_to_swap(page);
+	if (ret) {
+		set_page_dirty(page);
+		unlock_page(page);
+		goto out;
+	}
 	if (frontswap_store(page) == 0) {
 		set_page_writeback(page);
 		unlock_page(page);
diff --git a/mm/shmem.c b/mm/shmem.c
index ec94f4c7851e..e57d3314dc4b 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1734,6 +1734,12 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index,
 	}
 	wait_on_page_writeback(page);
 
+	/*
+	 * Some architectures may have to restore extra metadata to the
+	 * physical page after reading from swap.
+	 */
+	arch_swap_restore(swap, page);
+
 	if (shmem_should_replace_page(page, gfp)) {
 		error = shmem_replace_page(&page, gfp, info, index);
 		if (error)
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 12f59e641b5e..4b1d1a04e327 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -717,6 +717,7 @@ static void swap_range_free(struct swap_info_struct *si, unsigned long offset,
 	else
 		swap_slot_free_notify = NULL;
 	while (offset <= end) {
+		arch_swap_invalidate_page(si->type, offset);
 		frontswap_invalidate_page(si->type, offset);
 		if (swap_slot_free_notify)
 			swap_slot_free_notify(si->bdev, offset);
@@ -2682,6 +2683,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	frontswap_map = frontswap_map_get(p);
 	spin_unlock(&p->lock);
 	spin_unlock(&swap_lock);
+	arch_swap_invalidate_area(p->type);
 	frontswap_invalidate_area(p->type);
 	frontswap_map_set(p, NULL);
 	mutex_unlock(&swapon_mutex);
-- 
cgit v1.2.3


From e48c15b796d412ede883bb2ef7779b2a142f7962 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Mon, 29 Jun 2020 17:21:32 -0700
Subject: smp: Add source and destination CPUs to __call_single_data

This commit adds a destination CPU to __call_single_data, and is inspired
by an earlier commit by Peter Zijlstra.  This version adds #ifdef to
permit use by 32-bit systems and supplying the destination CPU for all
smp_call_function*() requests, not just smp_call_function_single().

If need be, 32-bit systems could be accommodated by shrinking the flags
field to 16 bits (the atomic_t variant is currently unused) and by
providing only eight bits for CPU on such systems.

It is not clear that the addition of the fields to __call_single_node
are really needed.

[ paulmck: Apply Boqun Feng feedback on 32-bit builds. ]
Link: https://lore.kernel.org/lkml/20200615164048.GC2531@hirez.programming.kicks-ass.net/
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/smp.h       | 3 +++
 include/linux/smp_types.h | 3 +++
 kernel/smp.c              | 6 ++++++
 3 files changed, 12 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/smp.h b/include/linux/smp.h
index 80d557ef8a11..9f13966d3d92 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -26,6 +26,9 @@ struct __call_single_data {
 		struct {
 			struct llist_node llist;
 			unsigned int flags;
+#ifdef CONFIG_64BIT
+			u16 src, dst;
+#endif
 		};
 	};
 	smp_call_func_t func;
diff --git a/include/linux/smp_types.h b/include/linux/smp_types.h
index 364b3ae3e41d..2e8461af8df6 100644
--- a/include/linux/smp_types.h
+++ b/include/linux/smp_types.h
@@ -61,6 +61,9 @@ struct __call_single_node {
 		unsigned int	u_flags;
 		atomic_t	a_flags;
 	};
+#ifdef CONFIG_64BIT
+	u16 src, dst;
+#endif
 };
 
 #endif /* __LINUX_SMP_TYPES_H */
diff --git a/kernel/smp.c b/kernel/smp.c
index d0ae8eb6bf8b..865a876f83ce 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -375,6 +375,9 @@ int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
 
 	csd->func = func;
 	csd->info = info;
+#ifdef CONFIG_64BIT
+	csd->dst = cpu;
+#endif
 
 	err = generic_exec_single(cpu, csd);
 
@@ -540,6 +543,9 @@ static void smp_call_function_many_cond(const struct cpumask *mask,
 			csd->flags |= CSD_TYPE_SYNC;
 		csd->func = func;
 		csd->info = info;
+#ifdef CONFIG_64BIT
+		csd->dst = cpu;
+#endif
 		if (llist_add(&csd->llist, &per_cpu(call_single_queue, cpu)))
 			__cpumask_set_cpu(cpu, cfd->cpumask_ipi);
 	}
-- 
cgit v1.2.3


From 0f7c5317b89058e432d3e97efa19467ff4c3b86b Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 4 Sep 2020 14:37:29 -0700
Subject: of: Export of_remove_property() to modules

We will need to remove some OF properties in drivers/net/dsa/bcm_sf2.c
with a subsequent commit. Export of_remove_property() to modules so we
can keep bcm_sf2 modular and provide an empty stub for when CONFIG_OF is
disabled to maintain the ability to compile test.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/of/base.c  | 1 +
 include/linux/of.h | 5 +++++
 2 files changed, 6 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/of/base.c b/drivers/of/base.c
index ea44fea99813..161a23631472 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -1869,6 +1869,7 @@ int of_remove_property(struct device_node *np, struct property *prop)
 
 	return rc;
 }
+EXPORT_SYMBOL_GPL(of_remove_property);
 
 int __of_update_property(struct device_node *np, struct property *newprop,
 		struct property **oldpropp)
diff --git a/include/linux/of.h b/include/linux/of.h
index 5cf7ae0465d1..481ec0467285 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -929,6 +929,11 @@ static inline int of_machine_is_compatible(const char *compat)
 	return 0;
 }
 
+static inline int of_remove_property(struct device_node *np, struct property *prop)
+{
+	return 0;
+}
+
 static inline bool of_console_check(const struct device_node *dn, const char *name, int index)
 {
 	return false;
-- 
cgit v1.2.3


From 78366e9cbd7892ac3d321e62c4be7a7fe79a69ed Mon Sep 17 00:00:00 2001
From: Pali Rohár <pali@kernel.org>
Date: Mon, 27 Jul 2020 15:38:35 +0200
Subject: mmc: sdio: Parse CISTPL_VERS_1 major and minor revision numbers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

They should indicate compliance of standard.

Signed-off-by: Pali Rohár <pali@kernel.org>
Link: https://lore.kernel.org/r/20200727133837.19086-3-pali@kernel.org
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/core/sdio_cis.c   | 8 ++++++++
 include/linux/mmc/card.h      | 2 ++
 include/linux/mmc/sdio_func.h | 2 ++
 3 files changed, 12 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/mmc/core/sdio_cis.c b/drivers/mmc/core/sdio_cis.c
index 3efaa9534a77..44bea5e4aeda 100644
--- a/drivers/mmc/core/sdio_cis.c
+++ b/drivers/mmc/core/sdio_cis.c
@@ -23,12 +23,16 @@
 static int cistpl_vers_1(struct mmc_card *card, struct sdio_func *func,
 			 const unsigned char *buf, unsigned size)
 {
+	u8 major_rev, minor_rev;
 	unsigned i, nr_strings;
 	char **buffer, *string;
 
 	if (size < 2)
 		return 0;
 
+	major_rev = buf[0];
+	minor_rev = buf[1];
+
 	/* Find all null-terminated (including zero length) strings in
 	   the TPLLV1_INFO field. Trailing garbage is ignored. */
 	buf += 2;
@@ -60,9 +64,13 @@ static int cistpl_vers_1(struct mmc_card *card, struct sdio_func *func,
 	}
 
 	if (func) {
+		func->major_rev = major_rev;
+		func->minor_rev = minor_rev;
 		func->num_info = nr_strings;
 		func->info = (const char**)buffer;
 	} else {
+		card->major_rev = major_rev;
+		card->minor_rev = minor_rev;
 		card->num_info = nr_strings;
 		card->info = (const char**)buffer;
 	}
diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
index 7d46411ffaa2..42df06c6b19c 100644
--- a/include/linux/mmc/card.h
+++ b/include/linux/mmc/card.h
@@ -297,6 +297,8 @@ struct mmc_card {
 	struct sdio_cis		cis;		/* common tuple info */
 	struct sdio_func	*sdio_func[SDIO_MAX_FUNCS]; /* SDIO functions (devices) */
 	struct sdio_func	*sdio_single_irq; /* SDIO function when only one IRQ active */
+	u8			major_rev;	/* major revision number */
+	u8			minor_rev;	/* minor revision number */
 	unsigned		num_info;	/* number of info strings */
 	const char		**info;		/* info strings */
 	struct sdio_func_tuple	*tuples;	/* unknown common tuples */
diff --git a/include/linux/mmc/sdio_func.h b/include/linux/mmc/sdio_func.h
index fa2aaab5e57a..478855b8e406 100644
--- a/include/linux/mmc/sdio_func.h
+++ b/include/linux/mmc/sdio_func.h
@@ -51,6 +51,8 @@ struct sdio_func {
 
 	u8			*tmpbuf;	/* DMA:able scratch buffer */
 
+	u8			major_rev;	/* major revision number */
+	u8			minor_rev;	/* minor revision number */
 	unsigned		num_info;	/* number of info strings */
 	const char		**info;		/* info strings */
 
-- 
cgit v1.2.3


From 6932794192f63c5e105eade19fba26b8ef29ec79 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Fri, 21 Aug 2020 08:35:33 +0200
Subject: mmc: core: Improve documentation of MMC_CAP_HW_RESET

MMC_CAP_HW_RESET means that the controller is capable of resetting the eMMC
device via RST_n signal, not a reset of the controller. Two drivers got
this wrong, so let's make it more clear.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Link: https://lore.kernel.org/r/20200821063533.3771-1-wsa+renesas@sang-engineering.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 include/linux/mmc/host.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index c5b6e97cb21a..799e23b0a23c 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -163,6 +163,7 @@ struct mmc_host_ops {
 	int	(*select_drive_strength)(struct mmc_card *card,
 					 unsigned int max_dtr, int host_drv,
 					 int card_drv, int *drv_type);
+	/* Reset the eMMC card via RST_n */
 	void	(*hw_reset)(struct mmc_host *host);
 	void	(*card_event)(struct mmc_host *host);
 
@@ -346,7 +347,7 @@ struct mmc_host {
 #define MMC_CAP_CD_WAKE		(1 << 28)	/* Enable card detect wake */
 #define MMC_CAP_CMD_DURING_TFR	(1 << 29)	/* Commands during data transfer */
 #define MMC_CAP_CMD23		(1 << 30)	/* CMD23 supported. */
-#define MMC_CAP_HW_RESET	(1 << 31)	/* Hardware reset */
+#define MMC_CAP_HW_RESET	(1 << 31)	/* Reset the eMMC card via RST_n */
 
 	u32			caps2;		/* More host capabilities */
 
-- 
cgit v1.2.3


From 97a7d87e96b02fc5b3944d7735e0f6b8446d07da Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Tue, 1 Sep 2020 17:02:48 +0200
Subject: mmc: core: add a 'doing_init_tune' flag and a 'mmc_doing_tune' helper

Our driver needs to know when tuning is in progress. 'doing_retune' only
covers re-tuning, not the initial tuning. Add another flag to detect the
initial tuning state and add a helper which tells us if any kind of
tuning is going on. Only implemented for MMC currently because that's
where we need it. SD can be added later if it becomes necessary.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Reviewed-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Tested-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Link: https://lore.kernel.org/r/20200901150250.26236-3-wsa+renesas@sang-engineering.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/core/mmc.c   | 4 ++++
 include/linux/mmc/host.h | 6 ++++++
 2 files changed, 10 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index ba2852b684b1..216bd1aed373 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -1763,6 +1763,8 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
 		goto free_card;
 
 	if (mmc_card_hs200(card)) {
+		host->doing_init_tune = 1;
+
 		err = mmc_hs200_tuning(card);
 		if (err)
 			goto free_card;
@@ -1770,6 +1772,8 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
 		err = mmc_select_hs400(card);
 		if (err)
 			goto free_card;
+
+		host->doing_init_tune = 0;
 	} else if (!mmc_card_hs400es(card)) {
 		/* Select the desired bus width optionally */
 		err = mmc_select_bus_width(card);
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 799e23b0a23c..c079b932330f 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -400,6 +400,7 @@ struct mmc_host {
 	unsigned int		use_spi_crc:1;
 	unsigned int		claimed:1;	/* host exclusively claimed */
 	unsigned int		bus_dead:1;	/* bus has been released */
+	unsigned int		doing_init_tune:1; /* initial tuning in progress */
 	unsigned int		can_retune:1;	/* re-tuning can be used */
 	unsigned int		doing_retune:1;	/* re-tuning in progress */
 	unsigned int		retune_now:1;	/* do re-tuning at next req */
@@ -595,6 +596,11 @@ static inline bool mmc_doing_retune(struct mmc_host *host)
 	return host->doing_retune == 1;
 }
 
+static inline bool mmc_doing_tune(struct mmc_host *host)
+{
+	return host->doing_retune == 1 || host->doing_init_tune == 1;
+}
+
 static inline enum dma_data_direction mmc_get_dma_dir(struct mmc_data *data)
 {
 	return data->flags & MMC_DATA_WRITE ? DMA_TO_DEVICE : DMA_FROM_DEVICE;
-- 
cgit v1.2.3


From 180c284ce4d66d2fb386b81bea59f01bc7be150a Mon Sep 17 00:00:00 2001
From: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Date: Fri, 4 Sep 2020 15:51:20 +0300
Subject: device connection: Remove device_connection_find()

There are no users for that function.

Signed-off-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20200904125123.83725-2-heikki.krogerus@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/devcon.c  | 73 --------------------------------------------------
 include/linux/device.h |  2 --
 2 files changed, 75 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/devcon.c b/drivers/base/devcon.c
index 14e2178e09f8..51ad546303dd 100644
--- a/drivers/base/devcon.c
+++ b/drivers/base/devcon.c
@@ -133,79 +133,6 @@ void *device_connection_find_match(struct device *dev, const char *con_id,
 }
 EXPORT_SYMBOL_GPL(device_connection_find_match);
 
-extern struct bus_type platform_bus_type;
-extern struct bus_type pci_bus_type;
-extern struct bus_type i2c_bus_type;
-extern struct bus_type spi_bus_type;
-
-static struct bus_type *generic_match_buses[] = {
-	&platform_bus_type,
-#ifdef CONFIG_PCI
-	&pci_bus_type,
-#endif
-#ifdef CONFIG_I2C
-	&i2c_bus_type,
-#endif
-#ifdef CONFIG_SPI_MASTER
-	&spi_bus_type,
-#endif
-	NULL,
-};
-
-static void *device_connection_fwnode_match(struct device_connection *con)
-{
-	struct bus_type *bus;
-	struct device *dev;
-
-	for (bus = generic_match_buses[0]; bus; bus++) {
-		dev = bus_find_device_by_fwnode(bus, con->fwnode);
-		if (dev && !strncmp(dev_name(dev), con->id, strlen(con->id)))
-			return dev;
-
-		put_device(dev);
-	}
-	return NULL;
-}
-
-/* This tries to find the device from the most common bus types by name. */
-static void *generic_match(struct device_connection *con, int ep, void *data)
-{
-	struct bus_type *bus;
-	struct device *dev;
-
-	if (con->fwnode)
-		return device_connection_fwnode_match(con);
-
-	for (bus = generic_match_buses[0]; bus; bus++) {
-		dev = bus_find_device_by_name(bus, NULL, con->endpoint[ep]);
-		if (dev)
-			return dev;
-	}
-
-	/*
-	 * We only get called if a connection was found, tell the caller to
-	 * wait for the other device to show up.
-	 */
-	return ERR_PTR(-EPROBE_DEFER);
-}
-
-/**
- * device_connection_find - Find two devices connected together
- * @dev: Device with the connection
- * @con_id: Identifier for the connection
- *
- * Find a connection with unique identifier @con_id between @dev and
- * another device. On success returns handle to the device that is connected
- * to @dev, with the reference count for the found device incremented. Returns
- * NULL if no matching connection was found, or ERR_PTR(-EPROBE_DEFER) when a
- * connection was found but the other device has not been enumerated yet.
- */
-struct device *device_connection_find(struct device *dev, const char *con_id)
-{
-	return device_connection_find_match(dev, con_id, NULL, generic_match);
-}
-EXPORT_SYMBOL_GPL(device_connection_find);
-
 /**
  * device_connection_add - Register a connection description
  * @con: The connection description to be registered
diff --git a/include/linux/device.h b/include/linux/device.h
index ca18da4768e3..0704461e8aad 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -319,8 +319,6 @@ void *fwnode_connection_find_match(struct fwnode_handle *fwnode,
 void *device_connection_find_match(struct device *dev, const char *con_id,
 				   void *data, devcon_match_fn_t match);
 
-struct device *device_connection_find(struct device *dev, const char *con_id);
-
 void device_connection_add(struct device_connection *con);
 void device_connection_remove(struct device_connection *con);
 
-- 
cgit v1.2.3


From 87ea5926247f7e15f0b5bc5b36cb210536177d77 Mon Sep 17 00:00:00 2001
From: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Date: Fri, 4 Sep 2020 15:51:21 +0300
Subject: device connection: Remove device_connection_add()

All the users of that API have now been converted to use
software fwnodes instead.

Signed-off-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20200904125123.83725-3-heikki.krogerus@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/devcon.c  | 59 +-------------------------------------------------
 include/linux/device.h | 29 -------------------------
 2 files changed, 1 insertion(+), 87 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/devcon.c b/drivers/base/devcon.c
index 51ad546303dd..94ab22a451ce 100644
--- a/drivers/base/devcon.c
+++ b/drivers/base/devcon.c
@@ -9,9 +9,6 @@
 #include <linux/device.h>
 #include <linux/property.h>
 
-static DEFINE_MUTEX(devcon_lock);
-static LIST_HEAD(devcon_list);
-
 static void *
 fwnode_graph_devcon_match(struct fwnode_handle *fwnode, const char *con_id,
 			  void *data, devcon_match_fn_t match)
@@ -99,60 +96,6 @@ EXPORT_SYMBOL_GPL(fwnode_connection_find_match);
 void *device_connection_find_match(struct device *dev, const char *con_id,
 				   void *data, devcon_match_fn_t match)
 {
-	struct fwnode_handle *fwnode = dev_fwnode(dev);
-	const char *devname = dev_name(dev);
-	struct device_connection *con;
-	void *ret = NULL;
-	int ep;
-
-	if (!match)
-		return NULL;
-
-	ret = fwnode_connection_find_match(fwnode, con_id, data, match);
-	if (ret)
-		return ret;
-
-	mutex_lock(&devcon_lock);
-
-	list_for_each_entry(con, &devcon_list, list) {
-		ep = match_string(con->endpoint, 2, devname);
-		if (ep < 0)
-			continue;
-
-		if (con_id && strcmp(con->id, con_id))
-			continue;
-
-		ret = match(con, !ep, data);
-		if (ret)
-			break;
-	}
-
-	mutex_unlock(&devcon_lock);
-
-	return ret;
+	return fwnode_connection_find_match(dev_fwnode(dev), con_id, data, match);
 }
 EXPORT_SYMBOL_GPL(device_connection_find_match);
-
-/**
- * device_connection_add - Register a connection description
- * @con: The connection description to be registered
- */
-void device_connection_add(struct device_connection *con)
-{
-	mutex_lock(&devcon_lock);
-	list_add_tail(&con->list, &devcon_list);
-	mutex_unlock(&devcon_lock);
-}
-EXPORT_SYMBOL_GPL(device_connection_add);
-
-/**
- * device_connections_remove - Unregister connection description
- * @con: The connection description to be unregistered
- */
-void device_connection_remove(struct device_connection *con)
-{
-	mutex_lock(&devcon_lock);
-	list_del(&con->list);
-	mutex_unlock(&devcon_lock);
-}
-EXPORT_SYMBOL_GPL(device_connection_remove);
diff --git a/include/linux/device.h b/include/linux/device.h
index 0704461e8aad..ea37debb0a98 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -297,7 +297,6 @@ struct device_dma_parameters {
  * @fwnode: The device node of the connected device
  * @endpoint: The names of the two devices connected together
  * @id: Unique identifier for the connection
- * @list: List head, private, for internal use only
  *
  * NOTE: @fwnode is not used together with @endpoint. @fwnode is used when
  * platform firmware defines the connection. When the connection is registered
@@ -307,7 +306,6 @@ struct device_connection {
 	struct fwnode_handle	*fwnode;
 	const char		*endpoint[2];
 	const char		*id;
-	struct list_head	list;
 };
 
 typedef void *(*devcon_match_fn_t)(struct device_connection *con, int ep,
@@ -319,33 +317,6 @@ void *fwnode_connection_find_match(struct fwnode_handle *fwnode,
 void *device_connection_find_match(struct device *dev, const char *con_id,
 				   void *data, devcon_match_fn_t match);
 
-void device_connection_add(struct device_connection *con);
-void device_connection_remove(struct device_connection *con);
-
-/**
- * device_connections_add - Add multiple device connections at once
- * @cons: Zero terminated array of device connection descriptors
- */
-static inline void device_connections_add(struct device_connection *cons)
-{
-	struct device_connection *c;
-
-	for (c = cons; c->endpoint[0]; c++)
-		device_connection_add(c);
-}
-
-/**
- * device_connections_remove - Remove multiple device connections at once
- * @cons: Zero terminated array of device connection descriptors
- */
-static inline void device_connections_remove(struct device_connection *cons)
-{
-	struct device_connection *c;
-
-	for (c = cons; c->endpoint[0]; c++)
-		device_connection_remove(c);
-}
-
 /**
  * enum device_link_state - Device link states.
  * @DL_STATE_NONE: The presence of the drivers is not being tracked.
-- 
cgit v1.2.3


From f5514c91e9f72b719bfec64af6acac5ad41df7b5 Mon Sep 17 00:00:00 2001
From: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Date: Fri, 4 Sep 2020 15:51:22 +0300
Subject: device connection: Remove struct device_connection

Since the connection descriptors can't be stored into the
list anymore, there is no need for the data structure.

Signed-off-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20200904125123.83725-4-heikki.krogerus@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/devcon.c     | 20 ++++++++++----------
 drivers/usb/roles/class.c | 12 ++++--------
 drivers/usb/typec/mux.c   | 19 ++++++++++---------
 include/linux/device.h    | 18 +-----------------
 4 files changed, 25 insertions(+), 44 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/devcon.c b/drivers/base/devcon.c
index 94ab22a451ce..1790e84dbe7c 100644
--- a/drivers/base/devcon.c
+++ b/drivers/base/devcon.c
@@ -13,17 +13,17 @@ static void *
 fwnode_graph_devcon_match(struct fwnode_handle *fwnode, const char *con_id,
 			  void *data, devcon_match_fn_t match)
 {
-	struct device_connection con = { .id = con_id };
+	struct fwnode_handle *node;
 	struct fwnode_handle *ep;
 	void *ret;
 
 	fwnode_graph_for_each_endpoint(fwnode, ep) {
-		con.fwnode = fwnode_graph_get_remote_port_parent(ep);
-		if (!fwnode_device_is_available(con.fwnode))
+		node = fwnode_graph_get_remote_port_parent(ep);
+		if (!fwnode_device_is_available(node))
 			continue;
 
-		ret = match(&con, -1, data);
-		fwnode_handle_put(con.fwnode);
+		ret = match(node, con_id, data);
+		fwnode_handle_put(node);
 		if (ret) {
 			fwnode_handle_put(ep);
 			return ret;
@@ -36,17 +36,17 @@ static void *
 fwnode_devcon_match(struct fwnode_handle *fwnode, const char *con_id,
 		    void *data, devcon_match_fn_t match)
 {
-	struct device_connection con = { };
+	struct fwnode_handle *node;
 	void *ret;
 	int i;
 
 	for (i = 0; ; i++) {
-		con.fwnode = fwnode_find_reference(fwnode, con_id, i);
-		if (IS_ERR(con.fwnode))
+		node = fwnode_find_reference(fwnode, con_id, i);
+		if (IS_ERR(node))
 			break;
 
-		ret = match(&con, -1, data);
-		fwnode_handle_put(con.fwnode);
+		ret = match(node, NULL, data);
+		fwnode_handle_put(node);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/usb/roles/class.c b/drivers/usb/roles/class.c
index 27d92af29635..97f37077b7f9 100644
--- a/drivers/usb/roles/class.c
+++ b/drivers/usb/roles/class.c
@@ -87,19 +87,15 @@ enum usb_role usb_role_switch_get_role(struct usb_role_switch *sw)
 }
 EXPORT_SYMBOL_GPL(usb_role_switch_get_role);
 
-static void *usb_role_switch_match(struct device_connection *con, int ep,
+static void *usb_role_switch_match(struct fwnode_handle *fwnode, const char *id,
 				   void *data)
 {
 	struct device *dev;
 
-	if (con->fwnode) {
-		if (con->id && !fwnode_property_present(con->fwnode, con->id))
-			return NULL;
+	if (id && !fwnode_property_present(fwnode, id))
+		return NULL;
 
-		dev = class_find_device_by_fwnode(role_class, con->fwnode);
-	} else {
-		dev = class_find_device_by_name(role_class, con->endpoint[ep]);
-	}
+	dev = class_find_device_by_fwnode(role_class, fwnode);
 
 	return dev ? to_role_switch(dev) : ERR_PTR(-EPROBE_DEFER);
 }
diff --git a/drivers/usb/typec/mux.c b/drivers/usb/typec/mux.c
index 52ad277e4565..b069a5122aaa 100644
--- a/drivers/usb/typec/mux.c
+++ b/drivers/usb/typec/mux.c
@@ -34,15 +34,15 @@ static int switch_fwnode_match(struct device *dev, const void *fwnode)
 	return dev_fwnode(dev) == fwnode && dev_name_ends_with(dev, "-switch");
 }
 
-static void *typec_switch_match(struct device_connection *con, int ep,
+static void *typec_switch_match(struct fwnode_handle *fwnode, const char *id,
 				void *data)
 {
 	struct device *dev;
 
-	if (con->id && !fwnode_property_present(con->fwnode, con->id))
+	if (id && !fwnode_property_present(fwnode, id))
 		return NULL;
 
-	dev = class_find_device(&typec_mux_class, NULL, con->fwnode,
+	dev = class_find_device(&typec_mux_class, NULL, fwnode,
 				switch_fwnode_match);
 
 	return dev ? to_typec_switch(dev) : ERR_PTR(-EPROBE_DEFER);
@@ -183,7 +183,8 @@ static int mux_fwnode_match(struct device *dev, const void *fwnode)
 	return dev_fwnode(dev) == fwnode && dev_name_ends_with(dev, "-mux");
 }
 
-static void *typec_mux_match(struct device_connection *con, int ep, void *data)
+static void *typec_mux_match(struct fwnode_handle *fwnode, const char *id,
+			     void *data)
 {
 	const struct typec_altmode_desc *desc = data;
 	struct device *dev;
@@ -196,20 +197,20 @@ static void *typec_mux_match(struct device_connection *con, int ep, void *data)
 	 * Check has the identifier already been "consumed". If it
 	 * has, no need to do any extra connection identification.
 	 */
-	match = !con->id;
+	match = !id;
 	if (match)
 		goto find_mux;
 
 	/* Accessory Mode muxes */
 	if (!desc) {
-		match = fwnode_property_present(con->fwnode, "accessory");
+		match = fwnode_property_present(fwnode, "accessory");
 		if (match)
 			goto find_mux;
 		return NULL;
 	}
 
 	/* Alternate Mode muxes */
-	nval = fwnode_property_count_u16(con->fwnode, "svid");
+	nval = fwnode_property_count_u16(fwnode, "svid");
 	if (nval <= 0)
 		return NULL;
 
@@ -217,7 +218,7 @@ static void *typec_mux_match(struct device_connection *con, int ep, void *data)
 	if (!val)
 		return ERR_PTR(-ENOMEM);
 
-	nval = fwnode_property_read_u16_array(con->fwnode, "svid", val, nval);
+	nval = fwnode_property_read_u16_array(fwnode, "svid", val, nval);
 	if (nval < 0) {
 		kfree(val);
 		return ERR_PTR(nval);
@@ -234,7 +235,7 @@ static void *typec_mux_match(struct device_connection *con, int ep, void *data)
 	return NULL;
 
 find_mux:
-	dev = class_find_device(&typec_mux_class, NULL, con->fwnode,
+	dev = class_find_device(&typec_mux_class, NULL, fwnode,
 				mux_fwnode_match);
 
 	return dev ? to_typec_switch(dev) : ERR_PTR(-EPROBE_DEFER);
diff --git a/include/linux/device.h b/include/linux/device.h
index ea37debb0a98..d4612efaab82 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -292,23 +292,7 @@ struct device_dma_parameters {
 	unsigned long segment_boundary_mask;
 };
 
-/**
- * struct device_connection - Device Connection Descriptor
- * @fwnode: The device node of the connected device
- * @endpoint: The names of the two devices connected together
- * @id: Unique identifier for the connection
- *
- * NOTE: @fwnode is not used together with @endpoint. @fwnode is used when
- * platform firmware defines the connection. When the connection is registered
- * with device_connection_add() @endpoint is used instead.
- */
-struct device_connection {
-	struct fwnode_handle	*fwnode;
-	const char		*endpoint[2];
-	const char		*id;
-};
-
-typedef void *(*devcon_match_fn_t)(struct device_connection *con, int ep,
+typedef void *(*devcon_match_fn_t)(struct fwnode_handle *fwnode, const char *id,
 				   void *data);
 
 void *fwnode_connection_find_match(struct fwnode_handle *fwnode,
-- 
cgit v1.2.3


From 07e292950b9368518c659c4d5f1dca4bf55779bd Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Thu, 20 Aug 2020 21:53:41 -0600
Subject: PCI: Allow root and child buses to have different pci_ops

PCI host bridges often have different ways to access the root and child
bus config spaces. The host bridge drivers have invented their own
abstractions to handle this. Let's support having different root and
child bus pci_ops so these per driver abstractions can be removed.

Link: https://lore.kernel.org/r/20200821035420.380495-2-robh@kernel.org
Signed-off-by: Rob Herring <robh@kernel.org>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/probe.c | 8 +++++++-
 include/linux/pci.h | 1 +
 2 files changed, 8 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 03d37128a24f..0c9ebc72532e 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -1036,6 +1036,7 @@ static struct pci_bus *pci_alloc_child_bus(struct pci_bus *parent,
 					   struct pci_dev *bridge, int busnr)
 {
 	struct pci_bus *child;
+	struct pci_host_bridge *host;
 	int i;
 	int ret;
 
@@ -1045,11 +1046,16 @@ static struct pci_bus *pci_alloc_child_bus(struct pci_bus *parent,
 		return NULL;
 
 	child->parent = parent;
-	child->ops = parent->ops;
 	child->msi = parent->msi;
 	child->sysdata = parent->sysdata;
 	child->bus_flags = parent->bus_flags;
 
+	host = pci_find_host_bridge(parent);
+	if (host->child_ops)
+		child->ops = host->child_ops;
+	else
+		child->ops = parent->ops;
+
 	/*
 	 * Initialize some portions of the bus device, but don't register
 	 * it now as the parent is not properly set up yet.
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 835530605c0d..1fbe95a7d386 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -523,6 +523,7 @@ struct pci_host_bridge {
 	struct device	dev;
 	struct pci_bus	*bus;		/* Root bus */
 	struct pci_ops	*ops;
+	struct pci_ops	*child_ops;
 	void		*sysdata;
 	int		busnr;
 	struct list_head windows;	/* resource_entry */
-- 
cgit v1.2.3


From e1f82a0dcf388d98bcc7ad195c03bd812405e6b2 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 26 Aug 2020 13:44:59 +0300
Subject: driver core: Annotate dev_err_probe() with __must_check

We have got already new users of this API which interpret it differently
and miss the opportunity to optimize their code.

In order to avoid similar cases in the future, annotate dev_err_probe()
with __must_check.

Fixes: a787e5400a1c ("driver core: add device probe log helper")
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20200826104459.81979-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/device.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/device.h b/include/linux/device.h
index d4612efaab82..0b3dc72f64b2 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -931,7 +931,7 @@ void device_links_supplier_sync_state_pause(void);
 void device_links_supplier_sync_state_resume(void);
 
 extern __printf(3, 4)
-int dev_err_probe(const struct device *dev, int err, const char *fmt, ...);
+int __must_check dev_err_probe(const struct device *dev, int err, const char *fmt, ...);
 
 /* Create alias, so I can be autoloaded. */
 #define MODULE_ALIAS_CHARDEV(major,minor) \
-- 
cgit v1.2.3


From 82894c1d397f16c2208a35dbb1310559f31980bb Mon Sep 17 00:00:00 2001
From: Rikard Falkeborn <rikard.falkeborn@gmail.com>
Date: Mon, 7 Sep 2020 01:04:51 +0200
Subject: firmware: arm_scmi: Constify ops pointers in scmi_handle

These are never modified, so make them const to allow drivers to make
them const.

Link: https://lore.kernel.org/r/20200906230452.33410-3-rikard.falkeborn@gmail.com
Signed-off-by: Rikard Falkeborn <rikard.falkeborn@gmail.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 include/linux/scmi_protocol.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h
index 7e5dd7d1e221..05570afc7f74 100644
--- a/include/linux/scmi_protocol.h
+++ b/include/linux/scmi_protocol.h
@@ -279,12 +279,12 @@ struct scmi_notify_ops {
 struct scmi_handle {
 	struct device *dev;
 	struct scmi_revision_info *version;
-	struct scmi_perf_ops *perf_ops;
-	struct scmi_clk_ops *clk_ops;
-	struct scmi_power_ops *power_ops;
-	struct scmi_sensor_ops *sensor_ops;
-	struct scmi_reset_ops *reset_ops;
-	struct scmi_notify_ops *notify_ops;
+	const struct scmi_perf_ops *perf_ops;
+	const struct scmi_clk_ops *clk_ops;
+	const struct scmi_power_ops *power_ops;
+	const struct scmi_sensor_ops *sensor_ops;
+	const struct scmi_reset_ops *reset_ops;
+	const struct scmi_notify_ops *notify_ops;
 	/* for protocol internal use */
 	void *perf_priv;
 	void *clk_priv;
-- 
cgit v1.2.3


From 8b10fe68985278de4926daa56ad6af701839e40a Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Mon, 10 Aug 2020 10:21:39 -0400
Subject: fscrypt: drop unused inode argument from fscrypt_fname_alloc_buffer

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Link: https://lore.kernel.org/r/20200810142139.487631-1-jlayton@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 fs/crypto/fname.c       | 5 +----
 fs/crypto/hooks.c       | 2 +-
 fs/ext4/dir.c           | 2 +-
 fs/ext4/namei.c         | 7 +++----
 fs/f2fs/dir.c           | 2 +-
 fs/ubifs/dir.c          | 2 +-
 include/linux/fscrypt.h | 5 ++---
 7 files changed, 10 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c
index 011830f84d8d..47bcfddb278b 100644
--- a/fs/crypto/fname.c
+++ b/fs/crypto/fname.c
@@ -260,8 +260,6 @@ bool fscrypt_fname_encrypted_size(const struct inode *inode, u32 orig_len,
 
 /**
  * fscrypt_fname_alloc_buffer() - allocate a buffer for presented filenames
- * @inode: inode of the parent directory (for regular filenames)
- *	   or of the symlink (for symlink targets)
  * @max_encrypted_len: maximum length of encrypted filenames the buffer will be
  *		       used to present
  * @crypto_str: (output) buffer to allocate
@@ -271,8 +269,7 @@ bool fscrypt_fname_encrypted_size(const struct inode *inode, u32 orig_len,
  *
  * Return: 0 on success, -errno on failure
  */
-int fscrypt_fname_alloc_buffer(const struct inode *inode,
-			       u32 max_encrypted_len,
+int fscrypt_fname_alloc_buffer(u32 max_encrypted_len,
 			       struct fscrypt_str *crypto_str)
 {
 	const u32 max_encoded_len = BASE64_CHARS(FSCRYPT_NOKEY_NAME_MAX);
diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c
index 09fb8aa0f2e9..491b252843eb 100644
--- a/fs/crypto/hooks.c
+++ b/fs/crypto/hooks.c
@@ -319,7 +319,7 @@ const char *fscrypt_get_symlink(struct inode *inode, const void *caddr,
 	if (cstr.len + sizeof(*sd) - 1 > max_size)
 		return ERR_PTR(-EUCLEAN);
 
-	err = fscrypt_fname_alloc_buffer(inode, cstr.len, &pstr);
+	err = fscrypt_fname_alloc_buffer(cstr.len, &pstr);
 	if (err)
 		return ERR_PTR(err);
 
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 1d82336b1cd4..efe77cffc322 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -148,7 +148,7 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 	}
 
 	if (IS_ENCRYPTED(inode)) {
-		err = fscrypt_fname_alloc_buffer(inode, EXT4_NAME_LEN, &fstr);
+		err = fscrypt_fname_alloc_buffer(EXT4_NAME_LEN, &fstr);
 		if (err < 0)
 			return err;
 	}
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 153a9fbe1dd0..0d74615fcce3 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -663,8 +663,7 @@ static struct stats dx_show_leaf(struct inode *dir,
 
 					/* Directory is encrypted */
 					res = fscrypt_fname_alloc_buffer(
-						dir, len,
-						&fname_crypto_str);
+						len, &fname_crypto_str);
 					if (res)
 						printk(KERN_WARNING "Error "
 							"allocating crypto "
@@ -1016,8 +1015,8 @@ static int htree_dirblock_to_tree(struct file *dir_file,
 			brelse(bh);
 			return err;
 		}
-		err = fscrypt_fname_alloc_buffer(dir, EXT4_NAME_LEN,
-						     &fname_crypto_str);
+		err = fscrypt_fname_alloc_buffer(EXT4_NAME_LEN,
+						 &fname_crypto_str);
 		if (err < 0) {
 			brelse(bh);
 			return err;
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 069f498af1e3..b2530b9507bd 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -1032,7 +1032,7 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
 		if (err)
 			goto out;
 
-		err = fscrypt_fname_alloc_buffer(inode, F2FS_NAME_LEN, &fstr);
+		err = fscrypt_fname_alloc_buffer(F2FS_NAME_LEN, &fstr);
 		if (err < 0)
 			goto out;
 	}
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index 9d042942d8b2..a9c1f5a9c9bd 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -515,7 +515,7 @@ static int ubifs_readdir(struct file *file, struct dir_context *ctx)
 		if (err)
 			return err;
 
-		err = fscrypt_fname_alloc_buffer(dir, UBIFS_MAX_NLEN, &fstr);
+		err = fscrypt_fname_alloc_buffer(UBIFS_MAX_NLEN, &fstr);
 		if (err)
 			return err;
 
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index 991ff8575d0e..eaf16eb55788 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -197,7 +197,7 @@ static inline void fscrypt_free_filename(struct fscrypt_name *fname)
 	kfree(fname->crypto_buf.name);
 }
 
-int fscrypt_fname_alloc_buffer(const struct inode *inode, u32 max_encrypted_len,
+int fscrypt_fname_alloc_buffer(u32 max_encrypted_len,
 			       struct fscrypt_str *crypto_str);
 void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str);
 int fscrypt_fname_disk_to_usr(const struct inode *inode,
@@ -428,8 +428,7 @@ static inline void fscrypt_free_filename(struct fscrypt_name *fname)
 	return;
 }
 
-static inline int fscrypt_fname_alloc_buffer(const struct inode *inode,
-					     u32 max_encrypted_len,
+static inline int fscrypt_fname_alloc_buffer(u32 max_encrypted_len,
 					     struct fscrypt_str *crypto_str)
 {
 	return -EOPNOTSUPP;
-- 
cgit v1.2.3


From 384d87ef2c954fc58e6c5fd8253e4a1984f5fe02 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Fri, 4 Sep 2020 10:58:52 +0200
Subject: block: Do not discard buffers under a mounted filesystem

Discarding blocks and buffers under a mounted filesystem is hardly
anything admin wants to do. Usually it will confuse the filesystem and
sometimes the loss of buffer_head state (including b_private field) can
even cause crashes like:

BUG: unable to handle kernel NULL pointer dereference at 0000000000000008
PGD 0 P4D 0
Oops: 0002 [#1] SMP PTI
CPU: 4 PID: 203778 Comm: jbd2/dm-3-8 Kdump: loaded Tainted: G O     --------- -  - 4.18.0-147.5.0.5.h126.eulerosv2r9.x86_64 #1
Hardware name: Huawei RH2288H V3/BC11HGSA0, BIOS 1.57 08/11/2015
RIP: 0010:jbd2_journal_grab_journal_head+0x1b/0x40 [jbd2]
...
Call Trace:
 __jbd2_journal_insert_checkpoint+0x23/0x70 [jbd2]
 jbd2_journal_commit_transaction+0x155f/0x1b60 [jbd2]
 kjournald2+0xbd/0x270 [jbd2]

So if we don't have block device open with O_EXCL already, claim the
block device while we truncate buffer cache. This makes sure any
exclusive block device user (such as filesystem) cannot operate on the
device while we are discarding buffer cache.

Reported-by: Ye Bin <yebin10@huawei.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Reviewed-by: Christoph Hellwig <hch@lst.de>
[axboe: fix !CONFIG_BLOCK error in truncate_bdev_range()]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/ioctl.c          | 16 ++++++++++------
 fs/block_dev.c         | 37 +++++++++++++++++++++++++++++++++----
 include/linux/blkdev.h |  7 +++++++
 3 files changed, 50 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/block/ioctl.c b/block/ioctl.c
index bdb3bbb253d9..ae74d0409afa 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -112,8 +112,7 @@ static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode,
 	uint64_t range[2];
 	uint64_t start, len;
 	struct request_queue *q = bdev_get_queue(bdev);
-	struct address_space *mapping = bdev->bd_inode->i_mapping;
-
+	int err;
 
 	if (!(mode & FMODE_WRITE))
 		return -EBADF;
@@ -134,7 +133,11 @@ static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode,
 
 	if (start + len > i_size_read(bdev->bd_inode))
 		return -EINVAL;
-	truncate_inode_pages_range(mapping, start, start + len - 1);
+
+	err = truncate_bdev_range(bdev, mode, start, start + len - 1);
+	if (err)
+		return err;
+
 	return blkdev_issue_discard(bdev, start >> 9, len >> 9,
 				    GFP_KERNEL, flags);
 }
@@ -143,8 +146,8 @@ static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode,
 		unsigned long arg)
 {
 	uint64_t range[2];
-	struct address_space *mapping;
 	uint64_t start, end, len;
+	int err;
 
 	if (!(mode & FMODE_WRITE))
 		return -EBADF;
@@ -166,8 +169,9 @@ static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode,
 		return -EINVAL;
 
 	/* Invalidate the page cache, including dirty pages */
-	mapping = bdev->bd_inode->i_mapping;
-	truncate_inode_pages_range(mapping, start, end);
+	err = truncate_bdev_range(bdev, mode, start, end);
+	if (err)
+		return err;
 
 	return blkdev_issue_zeroout(bdev, start >> 9, len >> 9, GFP_KERNEL,
 			BLKDEV_ZERO_NOUNMAP);
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 9cb205405f9d..c70c41ecba48 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -103,6 +103,35 @@ void invalidate_bdev(struct block_device *bdev)
 }
 EXPORT_SYMBOL(invalidate_bdev);
 
+/*
+ * Drop all buffers & page cache for given bdev range. This function bails
+ * with error if bdev has other exclusive owner (such as filesystem).
+ */
+int truncate_bdev_range(struct block_device *bdev, fmode_t mode,
+			loff_t lstart, loff_t lend)
+{
+	struct block_device *claimed_bdev = NULL;
+	int err;
+
+	/*
+	 * If we don't hold exclusive handle for the device, upgrade to it
+	 * while we discard the buffer cache to avoid discarding buffers
+	 * under live filesystem.
+	 */
+	if (!(mode & FMODE_EXCL)) {
+		claimed_bdev = bdev->bd_contains;
+		err = bd_prepare_to_claim(bdev, claimed_bdev,
+					  truncate_bdev_range);
+		if (err)
+			return err;
+	}
+	truncate_inode_pages_range(bdev->bd_inode->i_mapping, lstart, lend);
+	if (claimed_bdev)
+		bd_abort_claiming(bdev, claimed_bdev, truncate_bdev_range);
+	return 0;
+}
+EXPORT_SYMBOL(truncate_bdev_range);
+
 static void set_init_blocksize(struct block_device *bdev)
 {
 	bdev->bd_inode->i_blkbits = blksize_bits(bdev_logical_block_size(bdev));
@@ -1968,7 +1997,6 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
 			     loff_t len)
 {
 	struct block_device *bdev = I_BDEV(bdev_file_inode(file));
-	struct address_space *mapping;
 	loff_t end = start + len - 1;
 	loff_t isize;
 	int error;
@@ -1996,8 +2024,9 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
 		return -EINVAL;
 
 	/* Invalidate the page cache, including dirty pages. */
-	mapping = bdev->bd_inode->i_mapping;
-	truncate_inode_pages_range(mapping, start, end);
+	error = truncate_bdev_range(bdev, file->f_mode, start, end);
+	if (error)
+		return error;
 
 	switch (mode) {
 	case FALLOC_FL_ZERO_RANGE:
@@ -2024,7 +2053,7 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
 	 * the caller will be given -EBUSY.  The third argument is
 	 * inclusive, so the rounding here is safe.
 	 */
-	return invalidate_inode_pages2_range(mapping,
+	return invalidate_inode_pages2_range(bdev->bd_inode->i_mapping,
 					     start >> PAGE_SHIFT,
 					     end >> PAGE_SHIFT);
 }
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 7d82959e7b86..37ec5a73d027 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1987,11 +1987,18 @@ void bdput(struct block_device *);
 
 #ifdef CONFIG_BLOCK
 void invalidate_bdev(struct block_device *bdev);
+int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart,
+			loff_t lend);
 int sync_blockdev(struct block_device *bdev);
 #else
 static inline void invalidate_bdev(struct block_device *bdev)
 {
 }
+static inline int truncate_bdev_range(struct block_device *bdev, fmode_t mode,
+				      loff_t lstart, loff_t lend)
+{
+	return 0;
+}
 static inline int sync_blockdev(struct block_device *bdev)
 {
 	return 0;
-- 
cgit v1.2.3


From 66ada2ccae4ed4dd07ba91df3b5fdb4c11335bd1 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Sat, 29 Aug 2020 22:00:01 +0900
Subject: kprobes: Add generic kretprobe trampoline handler

Add a generic kretprobe trampoline handler for unifying
the all cloned /arch/* kretprobe trampoline handlers.

The generic kretprobe trampoline handler is based on the
x86 implementation, because it is the latest implementation.
It has frame pointer checking, kprobe_busy_begin/end and
return address fixup for user handlers.

[ mingo: Minor edits. ]

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/159870600138.1229682.3424065380448088833.stgit@devnote2
---
 include/linux/kprobes.h | 32 ++++++++++++++--
 kernel/kprobes.c        | 98 +++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 126 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 9be1bff4f586..72142ae5df3e 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -187,10 +187,38 @@ static inline int kprobes_built_in(void)
 	return 1;
 }
 
+extern struct kprobe kprobe_busy;
+extern void kprobe_busy_begin(void);
+extern void kprobe_busy_end(void);
+
 #ifdef CONFIG_KRETPROBES
 extern void arch_prepare_kretprobe(struct kretprobe_instance *ri,
 				   struct pt_regs *regs);
 extern int arch_trampoline_kprobe(struct kprobe *p);
+
+/* If the trampoline handler called from a kprobe, use this version */
+unsigned long __kretprobe_trampoline_handler(struct pt_regs *regs,
+				void *trampoline_address,
+				void *frame_pointer);
+
+static nokprobe_inline
+unsigned long kretprobe_trampoline_handler(struct pt_regs *regs,
+				void *trampoline_address,
+				void *frame_pointer)
+{
+	unsigned long ret;
+	/*
+	 * Set a dummy kprobe for avoiding kretprobe recursion.
+	 * Since kretprobe never runs in kprobe handler, no kprobe must
+	 * be running at this point.
+	 */
+	kprobe_busy_begin();
+	ret = __kretprobe_trampoline_handler(regs, trampoline_address, frame_pointer);
+	kprobe_busy_end();
+
+	return ret;
+}
+
 #else /* CONFIG_KRETPROBES */
 static inline void arch_prepare_kretprobe(struct kretprobe *rp,
 					struct pt_regs *regs)
@@ -354,10 +382,6 @@ static inline struct kprobe_ctlblk *get_kprobe_ctlblk(void)
 	return this_cpu_ptr(&kprobe_ctlblk);
 }
 
-extern struct kprobe kprobe_busy;
-void kprobe_busy_begin(void);
-void kprobe_busy_end(void);
-
 kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset);
 int register_kprobe(struct kprobe *p);
 void unregister_kprobe(struct kprobe *p);
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 287b263c9cb9..a0afaa79024e 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1927,6 +1927,104 @@ unsigned long __weak arch_deref_entry_point(void *entry)
 }
 
 #ifdef CONFIG_KRETPROBES
+
+unsigned long __kretprobe_trampoline_handler(struct pt_regs *regs,
+					     void *trampoline_address,
+					     void *frame_pointer)
+{
+	struct kretprobe_instance *ri = NULL, *last = NULL;
+	struct hlist_head *head, empty_rp;
+	struct hlist_node *tmp;
+	unsigned long flags;
+	kprobe_opcode_t *correct_ret_addr = NULL;
+	bool skipped = false;
+
+	INIT_HLIST_HEAD(&empty_rp);
+	kretprobe_hash_lock(current, &head, &flags);
+
+	/*
+	 * It is possible to have multiple instances associated with a given
+	 * task either because multiple functions in the call path have
+	 * return probes installed on them, and/or more than one
+	 * return probe was registered for a target function.
+	 *
+	 * We can handle this because:
+	 *     - instances are always pushed into the head of the list
+	 *     - when multiple return probes are registered for the same
+	 *	 function, the (chronologically) first instance's ret_addr
+	 *	 will be the real return address, and all the rest will
+	 *	 point to kretprobe_trampoline.
+	 */
+	hlist_for_each_entry(ri, head, hlist) {
+		if (ri->task != current)
+			/* another task is sharing our hash bucket */
+			continue;
+		/*
+		 * Return probes must be pushed on this hash list correct
+		 * order (same as return order) so that it can be popped
+		 * correctly. However, if we find it is pushed it incorrect
+		 * order, this means we find a function which should not be
+		 * probed, because the wrong order entry is pushed on the
+		 * path of processing other kretprobe itself.
+		 */
+		if (ri->fp != frame_pointer) {
+			if (!skipped)
+				pr_warn("kretprobe is stacked incorrectly. Trying to fixup.\n");
+			skipped = true;
+			continue;
+		}
+
+		correct_ret_addr = ri->ret_addr;
+		if (skipped)
+			pr_warn("%ps must be blacklisted because of incorrect kretprobe order\n",
+				ri->rp->kp.addr);
+
+		if (correct_ret_addr != trampoline_address)
+			/*
+			 * This is the real return address. Any other
+			 * instances associated with this task are for
+			 * other calls deeper on the call stack
+			 */
+			break;
+	}
+
+	kretprobe_assert(ri, (unsigned long)correct_ret_addr,
+			     (unsigned long)trampoline_address);
+	last = ri;
+
+	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
+		if (ri->task != current)
+			/* another task is sharing our hash bucket */
+			continue;
+		if (ri->fp != frame_pointer)
+			continue;
+
+		if (ri->rp && ri->rp->handler) {
+			struct kprobe *prev = kprobe_running();
+
+			__this_cpu_write(current_kprobe, &ri->rp->kp);
+			ri->ret_addr = correct_ret_addr;
+			ri->rp->handler(ri, regs);
+			__this_cpu_write(current_kprobe, prev);
+		}
+
+		recycle_rp_inst(ri, &empty_rp);
+
+		if (ri == last)
+			break;
+	}
+
+	kretprobe_hash_unlock(current, &flags);
+
+	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
+		hlist_del(&ri->hlist);
+		kfree(ri);
+	}
+
+	return (unsigned long)correct_ret_addr;
+}
+NOKPROBE_SYMBOL(__kretprobe_trampoline_handler)
+
 /*
  * This kprobe pre_handler is registered with every kretprobe. When probe
  * hits it will set up the return probe.
-- 
cgit v1.2.3


From b338817807538c893540e393856b79cbbdf777ea Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Sat, 29 Aug 2020 22:02:47 +0900
Subject: kprobes: Free kretprobe_instance with RCU callback

Free kretprobe_instance with RCU callback instead of directly
freeing the object in the kretprobe handler context.

This will make kretprobe run safer in NMI context.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/159870616685.1229682.11978742048709542226.stgit@devnote2
---
 include/linux/kprobes.h |  6 ++++--
 kernel/kprobes.c        | 25 ++++++-------------------
 2 files changed, 10 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 72142ae5df3e..3389067d88b1 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -156,7 +156,10 @@ struct kretprobe {
 };
 
 struct kretprobe_instance {
-	struct hlist_node hlist;
+	union {
+		struct hlist_node hlist;
+		struct rcu_head rcu;
+	};
 	struct kretprobe *rp;
 	kprobe_opcode_t *ret_addr;
 	struct task_struct *task;
@@ -395,7 +398,6 @@ int register_kretprobes(struct kretprobe **rps, int num);
 void unregister_kretprobes(struct kretprobe **rps, int num);
 
 void kprobe_flush_task(struct task_struct *tk);
-void recycle_rp_inst(struct kretprobe_instance *ri, struct hlist_head *head);
 
 int disable_kprobe(struct kprobe *kp);
 int enable_kprobe(struct kprobe *kp);
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 211138225fa5..0676868f1ac2 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1223,8 +1223,7 @@ void kprobes_inc_nmissed_count(struct kprobe *p)
 }
 NOKPROBE_SYMBOL(kprobes_inc_nmissed_count);
 
-void recycle_rp_inst(struct kretprobe_instance *ri,
-		     struct hlist_head *head)
+static void recycle_rp_inst(struct kretprobe_instance *ri)
 {
 	struct kretprobe *rp = ri->rp;
 
@@ -1236,8 +1235,7 @@ void recycle_rp_inst(struct kretprobe_instance *ri,
 		hlist_add_head(&ri->hlist, &rp->free_instances);
 		raw_spin_unlock(&rp->lock);
 	} else
-		/* Unregistering */
-		hlist_add_head(&ri->hlist, head);
+		kfree_rcu(ri, rcu);
 }
 NOKPROBE_SYMBOL(recycle_rp_inst);
 
@@ -1313,7 +1311,7 @@ void kprobe_busy_end(void)
 void kprobe_flush_task(struct task_struct *tk)
 {
 	struct kretprobe_instance *ri;
-	struct hlist_head *head, empty_rp;
+	struct hlist_head *head;
 	struct hlist_node *tmp;
 	unsigned long hash, flags = 0;
 
@@ -1323,19 +1321,14 @@ void kprobe_flush_task(struct task_struct *tk)
 
 	kprobe_busy_begin();
 
-	INIT_HLIST_HEAD(&empty_rp);
 	hash = hash_ptr(tk, KPROBE_HASH_BITS);
 	head = &kretprobe_inst_table[hash];
 	kretprobe_table_lock(hash, &flags);
 	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
 		if (ri->task == tk)
-			recycle_rp_inst(ri, &empty_rp);
+			recycle_rp_inst(ri);
 	}
 	kretprobe_table_unlock(hash, &flags);
-	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
-		hlist_del(&ri->hlist);
-		kfree(ri);
-	}
 
 	kprobe_busy_end();
 }
@@ -1936,13 +1929,12 @@ unsigned long __kretprobe_trampoline_handler(struct pt_regs *regs,
 					     void *frame_pointer)
 {
 	struct kretprobe_instance *ri = NULL, *last = NULL;
-	struct hlist_head *head, empty_rp;
+	struct hlist_head *head;
 	struct hlist_node *tmp;
 	unsigned long flags;
 	kprobe_opcode_t *correct_ret_addr = NULL;
 	bool skipped = false;
 
-	INIT_HLIST_HEAD(&empty_rp);
 	kretprobe_hash_lock(current, &head, &flags);
 
 	/*
@@ -2011,7 +2003,7 @@ unsigned long __kretprobe_trampoline_handler(struct pt_regs *regs,
 			__this_cpu_write(current_kprobe, prev);
 		}
 
-		recycle_rp_inst(ri, &empty_rp);
+		recycle_rp_inst(ri);
 
 		if (ri == last)
 			break;
@@ -2019,11 +2011,6 @@ unsigned long __kretprobe_trampoline_handler(struct pt_regs *regs,
 
 	kretprobe_hash_unlock(current, &flags);
 
-	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
-		hlist_del(&ri->hlist);
-		kfree(ri);
-	}
-
 	return (unsigned long)correct_ret_addr;
 }
 NOKPROBE_SYMBOL(__kretprobe_trampoline_handler)
-- 
cgit v1.2.3


From 319f0ce284fff8e4f95167cb144acc905d0584c7 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Sat, 29 Aug 2020 22:03:02 +0900
Subject: kprobes: Make local functions static

Since we unified the kretprobe trampoline handler from arch/* code,
some functions and objects do not need to be exported anymore.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/159870618256.1229682.8692046612635810882.stgit@devnote2
---
 include/linux/kprobes.h | 15 ---------------
 kernel/kprobes.c        |  9 ++++-----
 2 files changed, 4 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 3389067d88b1..5c8c271fa1e9 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -190,7 +190,6 @@ static inline int kprobes_built_in(void)
 	return 1;
 }
 
-extern struct kprobe kprobe_busy;
 extern void kprobe_busy_begin(void);
 extern void kprobe_busy_end(void);
 
@@ -235,16 +234,6 @@ static inline int arch_trampoline_kprobe(struct kprobe *p)
 
 extern struct kretprobe_blackpoint kretprobe_blacklist[];
 
-static inline void kretprobe_assert(struct kretprobe_instance *ri,
-	unsigned long orig_ret_address, unsigned long trampoline_address)
-{
-	if (!orig_ret_address || (orig_ret_address == trampoline_address)) {
-		printk("kretprobe BUG!: Processing kretprobe %p @ %p\n",
-				ri->rp, ri->rp->kp.addr);
-		BUG();
-	}
-}
-
 #ifdef CONFIG_KPROBES_SANITY_TEST
 extern int init_test_probes(void);
 #else
@@ -364,10 +353,6 @@ int arch_check_ftrace_location(struct kprobe *p);
 
 /* Get the kprobe at this addr (if any) - called with preemption disabled */
 struct kprobe *get_kprobe(void *addr);
-void kretprobe_hash_lock(struct task_struct *tsk,
-			 struct hlist_head **head, unsigned long *flags);
-void kretprobe_hash_unlock(struct task_struct *tsk, unsigned long *flags);
-struct hlist_head * kretprobe_inst_table_head(struct task_struct *tsk);
 
 /* kprobe_running() will just return the current_kprobe on this CPU */
 static inline struct kprobe *kprobe_running(void)
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 0676868f1ac2..732a70163584 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1239,7 +1239,7 @@ static void recycle_rp_inst(struct kretprobe_instance *ri)
 }
 NOKPROBE_SYMBOL(recycle_rp_inst);
 
-void kretprobe_hash_lock(struct task_struct *tsk,
+static void kretprobe_hash_lock(struct task_struct *tsk,
 			 struct hlist_head **head, unsigned long *flags)
 __acquires(hlist_lock)
 {
@@ -1261,7 +1261,7 @@ __acquires(hlist_lock)
 }
 NOKPROBE_SYMBOL(kretprobe_table_lock);
 
-void kretprobe_hash_unlock(struct task_struct *tsk,
+static void kretprobe_hash_unlock(struct task_struct *tsk,
 			   unsigned long *flags)
 __releases(hlist_lock)
 {
@@ -1282,7 +1282,7 @@ __releases(hlist_lock)
 }
 NOKPROBE_SYMBOL(kretprobe_table_unlock);
 
-struct kprobe kprobe_busy = {
+static struct kprobe kprobe_busy = {
 	.addr = (void *) get_kprobe,
 };
 
@@ -1983,8 +1983,7 @@ unsigned long __kretprobe_trampoline_handler(struct pt_regs *regs,
 			break;
 	}
 
-	kretprobe_assert(ri, (unsigned long)correct_ret_addr,
-			     (unsigned long)trampoline_address);
+	BUG_ON(!correct_ret_addr || (correct_ret_addr == trampoline_address));
 	last = ri;
 
 	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
-- 
cgit v1.2.3


From d7cf5590393132993f2e6d2618fd23a20a6342ca Mon Sep 17 00:00:00 2001
From: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Date: Mon, 7 Sep 2020 15:05:31 +0300
Subject: device property: Move fwnode_connection_find_match() under
 drivers/base/property.c

The function is now only a helper that searches the
connection from device graph and then by checking if the
supplied connection identifier matches a property that
contains reference.

Signed-off-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20200907120532.37611-2-heikki.krogerus@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/Makefile    |   2 +-
 drivers/base/devcon.c    | 101 -----------------------------------------------
 drivers/base/property.c  |  73 ++++++++++++++++++++++++++++++++++
 include/linux/device.h   |   9 -----
 include/linux/property.h |  14 +++++++
 5 files changed, 88 insertions(+), 111 deletions(-)
 delete mode 100644 drivers/base/devcon.c

(limited to 'include/linux')

diff --git a/drivers/base/Makefile b/drivers/base/Makefile
index 157452080f3d..41369fc7004f 100644
--- a/drivers/base/Makefile
+++ b/drivers/base/Makefile
@@ -6,7 +6,7 @@ obj-y			:= component.o core.o bus.o dd.o syscore.o \
 			   cpu.o firmware.o init.o map.o devres.o \
 			   attribute_container.o transport_class.o \
 			   topology.o container.o property.o cacheinfo.o \
-			   devcon.o swnode.o
+			   swnode.o
 obj-$(CONFIG_DEVTMPFS)	+= devtmpfs.o
 obj-y			+= power/
 obj-$(CONFIG_ISA_BUS_API)	+= isa.o
diff --git a/drivers/base/devcon.c b/drivers/base/devcon.c
deleted file mode 100644
index 1790e84dbe7c..000000000000
--- a/drivers/base/devcon.c
+++ /dev/null
@@ -1,101 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/**
- * Device connections
- *
- * Copyright (C) 2018 Intel Corporation
- * Author: Heikki Krogerus <heikki.krogerus@linux.intel.com>
- */
-
-#include <linux/device.h>
-#include <linux/property.h>
-
-static void *
-fwnode_graph_devcon_match(struct fwnode_handle *fwnode, const char *con_id,
-			  void *data, devcon_match_fn_t match)
-{
-	struct fwnode_handle *node;
-	struct fwnode_handle *ep;
-	void *ret;
-
-	fwnode_graph_for_each_endpoint(fwnode, ep) {
-		node = fwnode_graph_get_remote_port_parent(ep);
-		if (!fwnode_device_is_available(node))
-			continue;
-
-		ret = match(node, con_id, data);
-		fwnode_handle_put(node);
-		if (ret) {
-			fwnode_handle_put(ep);
-			return ret;
-		}
-	}
-	return NULL;
-}
-
-static void *
-fwnode_devcon_match(struct fwnode_handle *fwnode, const char *con_id,
-		    void *data, devcon_match_fn_t match)
-{
-	struct fwnode_handle *node;
-	void *ret;
-	int i;
-
-	for (i = 0; ; i++) {
-		node = fwnode_find_reference(fwnode, con_id, i);
-		if (IS_ERR(node))
-			break;
-
-		ret = match(node, NULL, data);
-		fwnode_handle_put(node);
-		if (ret)
-			return ret;
-	}
-
-	return NULL;
-}
-
-/**
- * fwnode_connection_find_match - Find connection from a device node
- * @fwnode: Device node with the connection
- * @con_id: Identifier for the connection
- * @data: Data for the match function
- * @match: Function to check and convert the connection description
- *
- * Find a connection with unique identifier @con_id between @fwnode and another
- * device node. @match will be used to convert the connection description to
- * data the caller is expecting to be returned.
- */
-void *fwnode_connection_find_match(struct fwnode_handle *fwnode,
-				   const char *con_id, void *data,
-				   devcon_match_fn_t match)
-{
-	void *ret;
-
-	if (!fwnode || !match)
-		return NULL;
-
-	ret = fwnode_graph_devcon_match(fwnode, con_id, data, match);
-	if (ret)
-		return ret;
-
-	return fwnode_devcon_match(fwnode, con_id, data, match);
-}
-EXPORT_SYMBOL_GPL(fwnode_connection_find_match);
-
-/**
- * device_connection_find_match - Find physical connection to a device
- * @dev: Device with the connection
- * @con_id: Identifier for the connection
- * @data: Data for the match function
- * @match: Function to check and convert the connection description
- *
- * Find a connection with unique identifier @con_id between @dev and another
- * device. @match will be used to convert the connection description to data the
- * caller is expecting to be returned.
- */
-void *device_connection_find_match(struct device *dev, const char *con_id,
-				   void *data, devcon_match_fn_t match)
-{
-	return fwnode_connection_find_match(dev_fwnode(dev), con_id, data, match);
-}
-EXPORT_SYMBOL_GPL(device_connection_find_match);
diff --git a/drivers/base/property.c b/drivers/base/property.c
index d58aa98fe964..4c43d30145c6 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -1184,3 +1184,76 @@ const void *device_get_match_data(struct device *dev)
 	return fwnode_call_ptr_op(dev_fwnode(dev), device_get_match_data, dev);
 }
 EXPORT_SYMBOL_GPL(device_get_match_data);
+
+static void *
+fwnode_graph_devcon_match(struct fwnode_handle *fwnode, const char *con_id,
+			  void *data, devcon_match_fn_t match)
+{
+	struct fwnode_handle *node;
+	struct fwnode_handle *ep;
+	void *ret;
+
+	fwnode_graph_for_each_endpoint(fwnode, ep) {
+		node = fwnode_graph_get_remote_port_parent(ep);
+		if (!fwnode_device_is_available(node))
+			continue;
+
+		ret = match(node, con_id, data);
+		fwnode_handle_put(node);
+		if (ret) {
+			fwnode_handle_put(ep);
+			return ret;
+		}
+	}
+	return NULL;
+}
+
+static void *
+fwnode_devcon_match(struct fwnode_handle *fwnode, const char *con_id,
+		    void *data, devcon_match_fn_t match)
+{
+	struct fwnode_handle *node;
+	void *ret;
+	int i;
+
+	for (i = 0; ; i++) {
+		node = fwnode_find_reference(fwnode, con_id, i);
+		if (IS_ERR(node))
+			break;
+
+		ret = match(node, NULL, data);
+		fwnode_handle_put(node);
+		if (ret)
+			return ret;
+	}
+
+	return NULL;
+}
+
+/**
+ * fwnode_connection_find_match - Find connection from a device node
+ * @fwnode: Device node with the connection
+ * @con_id: Identifier for the connection
+ * @data: Data for the match function
+ * @match: Function to check and convert the connection description
+ *
+ * Find a connection with unique identifier @con_id between @fwnode and another
+ * device node. @match will be used to convert the connection description to
+ * data the caller is expecting to be returned.
+ */
+void *fwnode_connection_find_match(struct fwnode_handle *fwnode,
+				   const char *con_id, void *data,
+				   devcon_match_fn_t match)
+{
+	void *ret;
+
+	if (!fwnode || !match)
+		return NULL;
+
+	ret = fwnode_graph_devcon_match(fwnode, con_id, data, match);
+	if (ret)
+		return ret;
+
+	return fwnode_devcon_match(fwnode, con_id, data, match);
+}
+EXPORT_SYMBOL_GPL(fwnode_connection_find_match);
diff --git a/include/linux/device.h b/include/linux/device.h
index 0b3dc72f64b2..bf480dbe3375 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -292,15 +292,6 @@ struct device_dma_parameters {
 	unsigned long segment_boundary_mask;
 };
 
-typedef void *(*devcon_match_fn_t)(struct fwnode_handle *fwnode, const char *id,
-				   void *data);
-
-void *fwnode_connection_find_match(struct fwnode_handle *fwnode,
-				   const char *con_id, void *data,
-				   devcon_match_fn_t match);
-void *device_connection_find_match(struct device *dev, const char *con_id,
-				   void *data, devcon_match_fn_t match);
-
 /**
  * enum device_link_state - Device link states.
  * @DL_STATE_NONE: The presence of the drivers is not being tracked.
diff --git a/include/linux/property.h b/include/linux/property.h
index 9f805c442819..aedae94dcf41 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -418,6 +418,20 @@ fwnode_graph_get_endpoint_by_id(const struct fwnode_handle *fwnode,
 int fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode,
 				struct fwnode_endpoint *endpoint);
 
+typedef void *(*devcon_match_fn_t)(struct fwnode_handle *fwnode, const char *id,
+				   void *data);
+
+void *fwnode_connection_find_match(struct fwnode_handle *fwnode,
+				   const char *con_id, void *data,
+				   devcon_match_fn_t match);
+
+static inline void *device_connection_find_match(struct device *dev,
+						 const char *con_id, void *data,
+						 devcon_match_fn_t match)
+{
+	return fwnode_connection_find_match(dev_fwnode(dev), con_id, data, match);
+}
+
 /* -------------------------------------------------------------------------- */
 /* Software fwnode support - when HW description is incomplete or missing */
 
-- 
cgit v1.2.3


From 18efb2f9e897ac65e7a1b2892f4a53e404534eba Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Wed, 29 Jul 2020 10:58:29 -0700
Subject: test_firmware: Test platform fw loading on non-EFI systems

On non-EFI systems, it wasn't possible to test the platform firmware
loader because it will have never set "checked_fw" during __init.
Instead, allow the test code to override this check. Additionally split
the declarations into a private header file so it there is greater
enforcement of the symbol visibility.

Fixes: 548193cba2a7 ("test_firmware: add support for firmware_request_platform")
Cc: stable@vger.kernel.org
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Acked-by: Scott Branden <scott.branden@broadcom.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20200729175845.1745471-2-keescook@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/efi/embedded-firmware.c | 21 ++++++++++++++++-----
 drivers/firmware/efi/embedded-firmware.h | 21 +++++++++++++++++++++
 include/linux/efi_embedded_fw.h          | 13 -------------
 lib/test_firmware.c                      |  5 +++++
 4 files changed, 42 insertions(+), 18 deletions(-)
 create mode 100644 drivers/firmware/efi/embedded-firmware.h

(limited to 'include/linux')

diff --git a/drivers/firmware/efi/embedded-firmware.c b/drivers/firmware/efi/embedded-firmware.c
index e97a9c9d010c..f1330f55f7f4 100644
--- a/drivers/firmware/efi/embedded-firmware.c
+++ b/drivers/firmware/efi/embedded-firmware.c
@@ -14,11 +14,22 @@
 #include <linux/vmalloc.h>
 #include <crypto/sha.h>
 
+#include "embedded-firmware.h"
+
+#ifdef CONFIG_TEST_FIRMWARE
+# define EFI_EMBEDDED_FW_VISIBILITY
+#else
+# define EFI_EMBEDDED_FW_VISIBILITY static
+#endif
+
+EFI_EMBEDDED_FW_VISIBILITY LIST_HEAD(efi_embedded_fw_list);
+EFI_EMBEDDED_FW_VISIBILITY bool efi_embedded_fw_checked;
+
 /* Exported for use by lib/test_firmware.c only */
-LIST_HEAD(efi_embedded_fw_list);
+#ifdef CONFIG_TEST_FIRMWARE
 EXPORT_SYMBOL_GPL(efi_embedded_fw_list);
-
-static bool checked_for_fw;
+EXPORT_SYMBOL_GPL(efi_embedded_fw_checked);
+#endif
 
 static const struct dmi_system_id * const embedded_fw_table[] = {
 #ifdef CONFIG_TOUCHSCREEN_DMI
@@ -116,14 +127,14 @@ void __init efi_check_for_embedded_firmwares(void)
 		}
 	}
 
-	checked_for_fw = true;
+	efi_embedded_fw_checked = true;
 }
 
 int efi_get_embedded_fw(const char *name, const u8 **data, size_t *size)
 {
 	struct efi_embedded_fw *iter, *fw = NULL;
 
-	if (!checked_for_fw) {
+	if (!efi_embedded_fw_checked) {
 		pr_warn("Warning %s called while we did not check for embedded fw\n",
 			__func__);
 		return -ENOENT;
diff --git a/drivers/firmware/efi/embedded-firmware.h b/drivers/firmware/efi/embedded-firmware.h
new file mode 100644
index 000000000000..bb894eae0906
--- /dev/null
+++ b/drivers/firmware/efi/embedded-firmware.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _EFI_EMBEDDED_FW_INTERNAL_H_
+#define _EFI_EMBEDDED_FW_INTERNAL_H_
+
+/*
+ * This struct and efi_embedded_fw_list are private to the efi-embedded fw
+ * implementation they only in separate header for use by lib/test_firmware.c.
+ */
+struct efi_embedded_fw {
+	struct list_head list;
+	const char *name;
+	const u8 *data;
+	size_t length;
+};
+
+#ifdef CONFIG_TEST_FIRMWARE
+extern struct list_head efi_embedded_fw_list;
+extern bool efi_embedded_fw_checked;
+#endif
+
+#endif /* _EFI_EMBEDDED_FW_INTERNAL_H_ */
diff --git a/include/linux/efi_embedded_fw.h b/include/linux/efi_embedded_fw.h
index 57eac5241303..4ad5db9f5312 100644
--- a/include/linux/efi_embedded_fw.h
+++ b/include/linux/efi_embedded_fw.h
@@ -7,19 +7,6 @@
 
 #define EFI_EMBEDDED_FW_PREFIX_LEN		8
 
-/*
- * This struct and efi_embedded_fw_list are private to the efi-embedded fw
- * implementation they are in this header for use by lib/test_firmware.c only!
- */
-struct efi_embedded_fw {
-	struct list_head list;
-	const char *name;
-	const u8 *data;
-	size_t length;
-};
-
-extern struct list_head efi_embedded_fw_list;
-
 /**
  * struct efi_embedded_fw_desc - This struct is used by the EFI embedded-fw
  *                               code to search for embedded firmwares.
diff --git a/lib/test_firmware.c b/lib/test_firmware.c
index 9fee2b93a8d1..62af792e151c 100644
--- a/lib/test_firmware.c
+++ b/lib/test_firmware.c
@@ -489,6 +489,7 @@ out:
 static DEVICE_ATTR_WO(trigger_request);
 
 #ifdef CONFIG_EFI_EMBEDDED_FIRMWARE
+#include "../drivers/firmware/efi/embedded-firmware.h"
 static ssize_t trigger_request_platform_store(struct device *dev,
 					      struct device_attribute *attr,
 					      const char *buf, size_t count)
@@ -501,6 +502,7 @@ static ssize_t trigger_request_platform_store(struct device *dev,
 	};
 	struct efi_embedded_fw efi_embedded_fw;
 	const struct firmware *firmware = NULL;
+	bool saved_efi_embedded_fw_checked;
 	char *name;
 	int rc;
 
@@ -513,6 +515,8 @@ static ssize_t trigger_request_platform_store(struct device *dev,
 	efi_embedded_fw.data = (void *)test_data;
 	efi_embedded_fw.length = sizeof(test_data);
 	list_add(&efi_embedded_fw.list, &efi_embedded_fw_list);
+	saved_efi_embedded_fw_checked = efi_embedded_fw_checked;
+	efi_embedded_fw_checked = true;
 
 	pr_info("loading '%s'\n", name);
 	rc = firmware_request_platform(&firmware, name, dev);
@@ -530,6 +534,7 @@ static ssize_t trigger_request_platform_store(struct device *dev,
 	rc = count;
 
 out:
+	efi_embedded_fw_checked = saved_efi_embedded_fw_checked;
 	release_firmware(firmware);
 	list_del(&efi_embedded_fw.list);
 	kfree(name);
-- 
cgit v1.2.3


From f82485722e5de5ebb08d3a1dd7302203346dbff9 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Mon, 24 Aug 2020 19:38:57 +0200
Subject: devres: provide devm_krealloc()

Implement the managed variant of krealloc(). This function works with
all memory allocated by devm_kmalloc() (or devres functions using it
implicitly like devm_kmemdup(), devm_kstrdup() etc.).

Managed realloc'ed chunks can be manually released with devm_kfree().

Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20200824173859.4910-2-brgl@bgdev.pl
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/driver-api/driver-model/devres.rst |   1 +
 drivers/base/devres.c                            | 105 +++++++++++++++++++++++
 include/linux/device.h                           |   2 +
 3 files changed, 108 insertions(+)

(limited to 'include/linux')

diff --git a/Documentation/driver-api/driver-model/devres.rst b/Documentation/driver-api/driver-model/devres.rst
index eaaaafc21134..f318a5c0033c 100644
--- a/Documentation/driver-api/driver-model/devres.rst
+++ b/Documentation/driver-api/driver-model/devres.rst
@@ -354,6 +354,7 @@ MEM
   devm_kmalloc()
   devm_kmalloc_array()
   devm_kmemdup()
+  devm_krealloc()
   devm_kstrdup()
   devm_kvasprintf()
   devm_kzalloc()
diff --git a/drivers/base/devres.c b/drivers/base/devres.c
index ed615d3b9cf1..586e9a75c840 100644
--- a/drivers/base/devres.c
+++ b/drivers/base/devres.c
@@ -126,6 +126,14 @@ static void add_dr(struct device *dev, struct devres_node *node)
 	list_add_tail(&node->entry, &dev->devres_head);
 }
 
+static void replace_dr(struct device *dev,
+		       struct devres_node *old, struct devres_node *new)
+{
+	devres_log(dev, old, "REPLACE");
+	BUG_ON(!list_empty(&new->entry));
+	list_replace(&old->entry, &new->entry);
+}
+
 #ifdef CONFIG_DEBUG_DEVRES
 void * __devres_alloc_node(dr_release_t release, size_t size, gfp_t gfp, int nid,
 		      const char *name)
@@ -837,6 +845,103 @@ void *devm_kmalloc(struct device *dev, size_t size, gfp_t gfp)
 }
 EXPORT_SYMBOL_GPL(devm_kmalloc);
 
+/**
+ * devm_krealloc - Resource-managed krealloc()
+ * @dev: Device to re-allocate memory for
+ * @ptr: Pointer to the memory chunk to re-allocate
+ * @new_size: New allocation size
+ * @gfp: Allocation gfp flags
+ *
+ * Managed krealloc(). Resizes the memory chunk allocated with devm_kmalloc().
+ * Behaves similarly to regular krealloc(): if @ptr is NULL or ZERO_SIZE_PTR,
+ * it's the equivalent of devm_kmalloc(). If new_size is zero, it frees the
+ * previously allocated memory and returns ZERO_SIZE_PTR. This function doesn't
+ * change the order in which the release callback for the re-alloc'ed devres
+ * will be called (except when falling back to devm_kmalloc() or when freeing
+ * resources when new_size is zero). The contents of the memory are preserved
+ * up to the lesser of new and old sizes.
+ */
+void *devm_krealloc(struct device *dev, void *ptr, size_t new_size, gfp_t gfp)
+{
+	size_t total_new_size, total_old_size;
+	struct devres *old_dr, *new_dr;
+	unsigned long flags;
+
+	if (unlikely(!new_size)) {
+		devm_kfree(dev, ptr);
+		return ZERO_SIZE_PTR;
+	}
+
+	if (unlikely(ZERO_OR_NULL_PTR(ptr)))
+		return devm_kmalloc(dev, new_size, gfp);
+
+	if (WARN_ON(is_kernel_rodata((unsigned long)ptr)))
+		/*
+		 * We cannot reliably realloc a const string returned by
+		 * devm_kstrdup_const().
+		 */
+		return NULL;
+
+	if (!check_dr_size(new_size, &total_new_size))
+		return NULL;
+
+	total_old_size = ksize(container_of(ptr, struct devres, data));
+	if (total_old_size == 0) {
+		WARN(1, "Pointer doesn't point to dynamically allocated memory.");
+		return NULL;
+	}
+
+	/*
+	 * If new size is smaller or equal to the actual number of bytes
+	 * allocated previously - just return the same pointer.
+	 */
+	if (total_new_size <= total_old_size)
+		return ptr;
+
+	/*
+	 * Otherwise: allocate new, larger chunk. We need to allocate before
+	 * taking the lock as most probably the caller uses GFP_KERNEL.
+	 */
+	new_dr = alloc_dr(devm_kmalloc_release,
+			  total_new_size, gfp, dev_to_node(dev));
+	if (!new_dr)
+		return NULL;
+
+	/*
+	 * The spinlock protects the linked list against concurrent
+	 * modifications but not the resource itself.
+	 */
+	spin_lock_irqsave(&dev->devres_lock, flags);
+
+	old_dr = find_dr(dev, devm_kmalloc_release, devm_kmalloc_match, ptr);
+	if (!old_dr) {
+		spin_unlock_irqrestore(&dev->devres_lock, flags);
+		kfree(new_dr);
+		WARN(1, "Memory chunk not managed or managed by a different device.");
+		return NULL;
+	}
+
+	replace_dr(dev, &old_dr->node, &new_dr->node);
+
+	spin_unlock_irqrestore(&dev->devres_lock, flags);
+
+	/*
+	 * We can copy the memory contents after releasing the lock as we're
+	 * no longer modyfing the list links.
+	 */
+	memcpy(new_dr->data, old_dr->data,
+	       total_old_size - offsetof(struct devres, data));
+	/*
+	 * Same for releasing the old devres - it's now been removed from the
+	 * list. This is also the reason why we must not use devm_kfree() - the
+	 * links are no longer valid.
+	 */
+	kfree(old_dr);
+
+	return new_dr->data;
+}
+EXPORT_SYMBOL_GPL(devm_krealloc);
+
 /**
  * devm_kstrdup - Allocate resource managed space and
  *                copy an existing string into that.
diff --git a/include/linux/device.h b/include/linux/device.h
index bf480dbe3375..85d5c28bed93 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -206,6 +206,8 @@ int devres_release_group(struct device *dev, void *id);
 
 /* managed devm_k.alloc/kfree for device drivers */
 void *devm_kmalloc(struct device *dev, size_t size, gfp_t gfp) __malloc;
+void *devm_krealloc(struct device *dev, void *ptr, size_t size,
+		    gfp_t gfp) __must_check;
 __printf(3, 0) char *devm_kvasprintf(struct device *dev, gfp_t gfp,
 				     const char *fmt, va_list ap) __malloc;
 __printf(3, 4) char *devm_kasprintf(struct device *dev, gfp_t gfp,
-- 
cgit v1.2.3


From ab5fe88aef4b4837bc2f92fc9f6f9c9b75ef633b Mon Sep 17 00:00:00 2001
From: Vaibhav Gupta <vaibhavgupta40@gmail.com>
Date: Thu, 20 Aug 2020 00:26:45 +0530
Subject: fbdev: via-core: use generic power management

Drivers should do only device-specific jobs. But in general, drivers using
legacy PCI PM framework for .suspend()/.resume() have to manage many PCI
PM-related tasks themselves which can be done by PCI Core itself. This
brings extra load on the driver and it directly calls PCI helper functions
to handle them.

Switch to the new generic framework by updating function signatures and
define a "struct dev_pm_ops" variable to bind PM callbacks.

The via_suspend() is designed to function only in the case of Suspend.
Thus, the code checked for "if (state.event != PM_EVENT_SUSPEND)". This is
because, in the legacy framework, this callback was invoked even in the
event of Freeze and Hibernate. Hence, added the load of unnecessary
function-calls.

The goal can be achieved by binding the callback with only
"via_pm_ops.suspend" in the new framework. This also avoids the step of
checking "if (state.event != PM_EVENT_SUSPEND)" every time the callback is
invoked.

Signed-off-by: Vaibhav Gupta <vaibhavgupta40@gmail.com>
Cc: Bjorn Helgaas <helgaas@kernel.org>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Bjorn Helgaas <bjorn@helgaas.com>
Cc: Vaibhav Gupta <vaibhav.varodek@gmail.com>
Cc: Sam Ravnborg <sam@ravnborg.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Andres Salomon <dilinger@queued.net>
CC: Antonino Daplas <adaplas@gmail.com>
Cc: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200819185654.151170-4-vaibhavgupta40@gmail.com
---
 drivers/video/fbdev/via/via-core.c | 39 ++++++++++++++++----------------------
 include/linux/via-core.h           |  2 --
 2 files changed, 16 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/video/fbdev/via/via-core.c b/drivers/video/fbdev/via/via-core.c
index 703ddee9a244..89d75079b730 100644
--- a/drivers/video/fbdev/via/via-core.c
+++ b/drivers/video/fbdev/via/via-core.c
@@ -558,9 +558,8 @@ static void via_teardown_subdevs(void)
 /*
  * Power management functions
  */
-#ifdef CONFIG_PM
-static LIST_HEAD(viafb_pm_hooks);
-static DEFINE_MUTEX(viafb_pm_hooks_lock);
+static __maybe_unused LIST_HEAD(viafb_pm_hooks);
+static __maybe_unused DEFINE_MUTEX(viafb_pm_hooks_lock);
 
 void viafb_pm_register(struct viafb_pm_hooks *hooks)
 {
@@ -580,12 +579,10 @@ void viafb_pm_unregister(struct viafb_pm_hooks *hooks)
 }
 EXPORT_SYMBOL_GPL(viafb_pm_unregister);
 
-static int via_suspend(struct pci_dev *pdev, pm_message_t state)
+static int __maybe_unused via_suspend(struct device *dev)
 {
 	struct viafb_pm_hooks *hooks;
 
-	if (state.event != PM_EVENT_SUSPEND)
-		return 0;
 	/*
 	 * "I've occasionally hit a few drivers that caused suspend
 	 * failures, and each and every time it was a driver bug, and
@@ -600,24 +597,13 @@ static int via_suspend(struct pci_dev *pdev, pm_message_t state)
 		hooks->suspend(hooks->private);
 	mutex_unlock(&viafb_pm_hooks_lock);
 
-	pci_save_state(pdev);
-	pci_disable_device(pdev);
-	pci_set_power_state(pdev, pci_choose_state(pdev, state));
 	return 0;
 }
 
-static int via_resume(struct pci_dev *pdev)
+static int __maybe_unused via_resume(struct device *dev)
 {
 	struct viafb_pm_hooks *hooks;
 
-	/* Get the bus side powered up */
-	pci_set_power_state(pdev, PCI_D0);
-	pci_restore_state(pdev);
-	if (pci_enable_device(pdev))
-		return 0;
-
-	pci_set_master(pdev);
-
 	/* Now bring back any subdevs */
 	mutex_lock(&viafb_pm_hooks_lock);
 	list_for_each_entry(hooks, &viafb_pm_hooks, list)
@@ -626,7 +612,6 @@ static int via_resume(struct pci_dev *pdev)
 
 	return 0;
 }
-#endif /* CONFIG_PM */
 
 static int via_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
@@ -712,15 +697,23 @@ static const struct pci_device_id via_pci_table[] = {
 };
 MODULE_DEVICE_TABLE(pci, via_pci_table);
 
+static const struct dev_pm_ops via_pm_ops = {
+#ifdef CONFIG_PM_SLEEP
+	.suspend	= via_suspend,
+	.resume		= via_resume,
+	.freeze		= NULL,
+	.thaw		= via_resume,
+	.poweroff	= NULL,
+	.restore	= via_resume,
+#endif
+};
+
 static struct pci_driver via_driver = {
 	.name		= "viafb",
 	.id_table	= via_pci_table,
 	.probe		= via_pci_probe,
 	.remove		= via_pci_remove,
-#ifdef CONFIG_PM
-	.suspend	= via_suspend,
-	.resume		= via_resume,
-#endif
+	.driver.pm	= &via_pm_ops,
 };
 
 static int __init via_core_init(void)
diff --git a/include/linux/via-core.h b/include/linux/via-core.h
index 9e802deedb2d..8737599b9148 100644
--- a/include/linux/via-core.h
+++ b/include/linux/via-core.h
@@ -47,7 +47,6 @@ struct via_port_cfg {
 /*
  * Allow subdevs to register suspend/resume hooks.
  */
-#ifdef CONFIG_PM
 struct viafb_pm_hooks {
 	struct list_head list;
 	int (*suspend)(void *private);
@@ -57,7 +56,6 @@ struct viafb_pm_hooks {
 
 void viafb_pm_register(struct viafb_pm_hooks *hooks);
 void viafb_pm_unregister(struct viafb_pm_hooks *hooks);
-#endif /* CONFIG_PM */
 
 /*
  * This is the global viafb "device" containing stuff needed by
-- 
cgit v1.2.3


From e2028c8e6bf9a12dfe83fc12ce6d5d9ab1628b0b Mon Sep 17 00:00:00 2001
From: Sven Schneider <s.schneider@arkona-technologies.de>
Date: Thu, 20 Aug 2020 10:21:37 +0200
Subject: lib/fonts: add font 6x8 for OLED display

This font is derived from lib/fonts/font_6x10.c and is useful for small
OLED displays

Signed-off-by: Sven Schneider <s.schneider@arkona-technologies.de>
Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200820082137.5907-1-s.hauer@pengutronix.de
---
 include/linux/font.h |    4 +-
 lib/fonts/Kconfig    |    7 +
 lib/fonts/Makefile   |    1 +
 lib/fonts/font_6x8.c | 2576 ++++++++++++++++++++++++++++++++++++++++++++++++++
 lib/fonts/fonts.c    |    3 +
 5 files changed, 2590 insertions(+), 1 deletion(-)
 create mode 100644 lib/fonts/font_6x8.c

(limited to 'include/linux')

diff --git a/include/linux/font.h b/include/linux/font.h
index 51b91c8b69d5..4a3f8741bb7e 100644
--- a/include/linux/font.h
+++ b/include/linux/font.h
@@ -33,6 +33,7 @@ struct font_desc {
 #define	MINI4x6_IDX	9
 #define FONT6x10_IDX	10
 #define TER16x32_IDX	11
+#define FONT6x8_IDX	12
 
 extern const struct font_desc	font_vga_8x8,
 			font_vga_8x16,
@@ -45,7 +46,8 @@ extern const struct font_desc	font_vga_8x8,
 			font_acorn_8x8,
 			font_mini_4x6,
 			font_6x10,
-			font_ter_16x32;
+			font_ter_16x32,
+			font_6x8;
 
 /* Find a font with a specific name */
 
diff --git a/lib/fonts/Kconfig b/lib/fonts/Kconfig
index 37baa79cdd71..c035fde66aeb 100644
--- a/lib/fonts/Kconfig
+++ b/lib/fonts/Kconfig
@@ -119,6 +119,12 @@ config FONT_TER16x32
 	  This is the high resolution, large version for use with HiDPI screens.
 	  If the standard font is unreadable for you, say Y, otherwise say N.
 
+config FONT_6x8
+	bool "OLED 6x8 font" if FONTS
+	depends on FRAMEBUFFER_CONSOLE
+	help
+	  This font is useful for small displays (OLED).
+
 config FONT_AUTOSELECT
 	def_bool y
 	depends on !FONT_8x8
@@ -132,6 +138,7 @@ config FONT_AUTOSELECT
 	depends on !FONT_SUN12x22
 	depends on !FONT_10x18
 	depends on !FONT_TER16x32
+	depends on !FONT_6x8
 	select FONT_8x16
 
 endif # FONT_SUPPORT
diff --git a/lib/fonts/Makefile b/lib/fonts/Makefile
index ed95070860de..e16f68492174 100644
--- a/lib/fonts/Makefile
+++ b/lib/fonts/Makefile
@@ -15,6 +15,7 @@ font-objs-$(CONFIG_FONT_ACORN_8x8) += font_acorn_8x8.o
 font-objs-$(CONFIG_FONT_MINI_4x6)  += font_mini_4x6.o
 font-objs-$(CONFIG_FONT_6x10)      += font_6x10.o
 font-objs-$(CONFIG_FONT_TER16x32)  += font_ter16x32.o
+font-objs-$(CONFIG_FONT_6x8)       += font_6x8.o
 
 font-objs += $(font-objs-y)
 
diff --git a/lib/fonts/font_6x8.c b/lib/fonts/font_6x8.c
new file mode 100644
index 000000000000..e06447788418
--- /dev/null
+++ b/lib/fonts/font_6x8.c
@@ -0,0 +1,2576 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/font.h>
+
+#define FONTDATAMAX 2048
+
+static const unsigned char fontdata_6x8[FONTDATAMAX] = {
+
+	/* 0 0x00 '^@' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 1 0x01 '^A' */
+	0x78, /* 011110 */
+	0x84, /* 100001 */
+	0xCC, /* 110011 */
+	0x84, /* 100001 */
+	0xCC, /* 110011 */
+	0xB4, /* 101101 */
+	0x78, /* 011110 */
+	0x00, /* 000000 */
+
+	/* 2 0x02 '^B' */
+	0x78, /* 011110 */
+	0xFC, /* 111111 */
+	0xB4, /* 101101 */
+	0xFC, /* 111111 */
+	0xB4, /* 101101 */
+	0xCC, /* 110011 */
+	0x78, /* 011110 */
+	0x00, /* 000000 */
+
+	/* 3 0x03 '^C' */
+	0x00, /* 000000 */
+	0x28, /* 001010 */
+	0x7C, /* 011111 */
+	0x7C, /* 011111 */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 4 0x04 '^D' */
+	0x00, /* 000000 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x7C, /* 011111 */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 5 0x05 '^E' */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x38, /* 001110 */
+	0x6C, /* 011011 */
+	0x6C, /* 011011 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 6 0x06 '^F' */
+	0x00, /* 000000 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x7C, /* 011111 */
+	0x7C, /* 011111 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 7 0x07 '^G' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x30, /* 001100 */
+	0x78, /* 011110 */
+	0x30, /* 001100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 8 0x08 '^H' */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+	0xCC, /* 110011 */
+	0x84, /* 100001 */
+	0xCC, /* 110011 */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+
+	/* 9 0x09 '^I' */
+	0x00, /* 000000 */
+	0x30, /* 001100 */
+	0x48, /* 010010 */
+	0x84, /* 100001 */
+	0x48, /* 010010 */
+	0x30, /* 001100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 10 0x0A '^J' */
+	0xFC, /* 111111 */
+	0xCC, /* 110011 */
+	0xB4, /* 101101 */
+	0x78, /* 011110 */
+	0xB4, /* 101101 */
+	0xCC, /* 110011 */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+
+	/* 11 0x0B '^K' */
+	0x3C, /* 001111 */
+	0x14, /* 000101 */
+	0x20, /* 001000 */
+	0x78, /* 011110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 12 0x0C '^L' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 13 0x0D '^M' */
+	0x18, /* 000110 */
+	0x14, /* 000101 */
+	0x14, /* 000101 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x70, /* 011100 */
+	0x60, /* 011000 */
+	0x00, /* 000000 */
+
+	/* 14 0x0E '^N' */
+	0x3C, /* 001111 */
+	0x24, /* 001001 */
+	0x3C, /* 001111 */
+	0x24, /* 001001 */
+	0x24, /* 001001 */
+	0x6C, /* 011011 */
+	0x6C, /* 011011 */
+	0x00, /* 000000 */
+
+	/* 15 0x0F '^O' */
+	0x10, /* 000100 */
+	0x54, /* 010101 */
+	0x38, /* 001110 */
+	0x6C, /* 011011 */
+	0x38, /* 001110 */
+	0x54, /* 010101 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 16 0x10 '^P' */
+	0x40, /* 010000 */
+	0x60, /* 011000 */
+	0x70, /* 011100 */
+	0x78, /* 011110 */
+	0x70, /* 011100 */
+	0x60, /* 011000 */
+	0x40, /* 010000 */
+	0x00, /* 000000 */
+
+	/* 17 0x11 '^Q' */
+	0x04, /* 000001 */
+	0x0C, /* 000011 */
+	0x1C, /* 000111 */
+	0x3C, /* 001111 */
+	0x1C, /* 000111 */
+	0x0C, /* 000011 */
+	0x04, /* 000001 */
+	0x00, /* 000000 */
+
+	/* 18 0x12 '^R' */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x54, /* 010101 */
+	0x10, /* 000100 */
+	0x54, /* 010101 */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 19 0x13 '^S' */
+	0x48, /* 010010 */
+	0x48, /* 010010 */
+	0x48, /* 010010 */
+	0x48, /* 010010 */
+	0x48, /* 010010 */
+	0x00, /* 000000 */
+	0x48, /* 010010 */
+	0x00, /* 000000 */
+
+	/* 20 0x14 '^T' */
+	0x3C, /* 001111 */
+	0x54, /* 010101 */
+	0x54, /* 010101 */
+	0x3C, /* 001111 */
+	0x14, /* 000101 */
+	0x14, /* 000101 */
+	0x14, /* 000101 */
+	0x00, /* 000000 */
+
+	/* 21 0x15 '^U' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x30, /* 001100 */
+	0x28, /* 001010 */
+	0x14, /* 000101 */
+	0x0C, /* 000011 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+
+	/* 22 0x16 '^V' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0xF8, /* 111110 */
+	0xF8, /* 111110 */
+	0xF8, /* 111110 */
+	0x00, /* 000000 */
+
+	/* 23 0x17 '^W' */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x54, /* 010101 */
+	0x10, /* 000100 */
+	0x54, /* 010101 */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+	0x7C, /* 011111 */
+
+	/* 24 0x18 '^X' */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x54, /* 010101 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 25 0x19 '^Y' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x54, /* 010101 */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 26 0x1A '^Z' */
+	0x00, /* 000000 */
+	0x10, /* 000100 */
+	0x08, /* 000010 */
+	0x7C, /* 011111 */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 27 0x1B '^[' */
+	0x00, /* 000000 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+	0x7C, /* 011111 */
+	0x20, /* 001000 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 28 0x1C '^\' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x78, /* 011110 */
+	0x00, /* 000000 */
+
+	/* 29 0x1D '^]' */
+	0x00, /* 000000 */
+	0x48, /* 010010 */
+	0x84, /* 100001 */
+	0xFC, /* 111111 */
+	0x84, /* 100001 */
+	0x48, /* 010010 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 30 0x1E '^^' */
+	0x00, /* 000000 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x38, /* 001110 */
+	0x7C, /* 011111 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+
+	/* 31 0x1F '^_' */
+	0x00, /* 000000 */
+	0x7C, /* 011111 */
+	0x7C, /* 011111 */
+	0x38, /* 001110 */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 32 0x20 ' ' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 33 0x21 '!' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 34 0x22 '"' */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 35 0x23 '#' */
+	0x00, /* 000000 */
+	0x28, /* 001010 */
+	0x7C, /* 011111 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x7C, /* 011111 */
+	0x28, /* 001010 */
+	0x00, /* 000000 */
+
+	/* 36 0x24 '$' */
+	0x10, /* 000000 */
+	0x38, /* 001000 */
+	0x40, /* 010000 */
+	0x30, /* 001000 */
+	0x08, /* 000000 */
+	0x70, /* 011000 */
+	0x20, /* 001000 */
+	0x00, /* 000000 */
+
+	/* 37 0x25 '%' */
+	0x64, /* 011001 */
+	0x64, /* 011001 */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+	0x4C, /* 010011 */
+	0x4C, /* 010011 */
+	0x00, /* 000000 */
+
+	/* 38 0x26 '&' */
+	0x30, /* 001100 */
+	0x48, /* 010010 */
+	0x50, /* 010100 */
+	0x20, /* 001000 */
+	0x54, /* 010101 */
+	0x48, /* 010010 */
+	0x34, /* 001101 */
+	0x00, /* 000000 */
+
+	/* 39 0x27 ''' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 40 0x28 '(' */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+	0x20, /* 001000 */
+	0x20, /* 001000 */
+	0x10, /* 000100 */
+	0x08, /* 000010 */
+	0x00, /* 000000 */
+
+	/* 41 0x29 ')' */
+	0x20, /* 001000 */
+	0x10, /* 000100 */
+	0x08, /* 000010 */
+	0x08, /* 000010 */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+	0x00, /* 000000 */
+
+	/* 42 0x2A '*' */
+	0x10, /* 000100 */
+	0x54, /* 010101 */
+	0x38, /* 001110 */
+	0x54, /* 010101 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 43 0x2B '+' */
+	0x00, /* 000000 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x7C, /* 011111 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 44 0x2C ',' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x30, /* 001100 */
+	0x30, /* 001100 */
+	0x20, /* 001000 */
+
+	/* 45 0x2D '-' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 46 0x2E '.' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x18, /* 000110 */
+	0x18, /* 000110 */
+	0x00, /* 000000 */
+
+	/* 47 0x2F '/' */
+	0x04, /* 000001 */
+	0x08, /* 000010 */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+	0x20, /* 001000 */
+	0x40, /* 010000 */
+
+	/* 48 0x30 '0' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x4C, /* 010011 */
+	0x54, /* 010101 */
+	0x64, /* 011001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 49 0x31 '1' */
+	0x10, /* 000100 */
+	0x30, /* 001100 */
+	0x50, /* 010100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+
+	/* 50 0x32 '2' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x04, /* 000001 */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+
+	/* 51 0x33 '3' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x04, /* 000001 */
+	0x18, /* 000110 */
+	0x04, /* 000001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 52 0x34 '4' */
+	0x08, /* 000010 */
+	0x18, /* 000110 */
+	0x28, /* 001010 */
+	0x48, /* 010010 */
+	0x7C, /* 011111 */
+	0x08, /* 000010 */
+	0x08, /* 000010 */
+	0x00, /* 000000 */
+
+	/* 53 0x35 '5' */
+	0x7C, /* 011111 */
+	0x40, /* 010000 */
+	0x78, /* 011110 */
+	0x04, /* 000001 */
+	0x04, /* 000001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 54 0x36 '6' */
+	0x18, /* 000110 */
+	0x20, /* 001000 */
+	0x40, /* 010000 */
+	0x78, /* 011110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 55 0x37 '7' */
+	0x7C, /* 011111 */
+	0x04, /* 000001 */
+	0x04, /* 000001 */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 56 0x38 '8' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 57 0x39 '9' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x3C, /* 001111 */
+	0x04, /* 000001 */
+	0x08, /* 000010 */
+	0x30, /* 001100 */
+	0x00, /* 000000 */
+
+	/* 58 0x3A ':' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x18, /* 000110 */
+	0x18, /* 000110 */
+	0x00, /* 000000 */
+	0x18, /* 000110 */
+	0x18, /* 000110 */
+	0x00, /* 000000 */
+
+	/* 59 0x3B ';' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x30, /* 001100 */
+	0x30, /* 001100 */
+	0x00, /* 000000 */
+	0x30, /* 001100 */
+	0x30, /* 001100 */
+	0x20, /* 001000 */
+
+	/* 60 0x3C '<' */
+	0x04, /* 000001 */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+	0x10, /* 000100 */
+	0x08, /* 000010 */
+	0x04, /* 000001 */
+	0x00, /* 000000 */
+
+	/* 61 0x3D '=' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 62 0x3E '>' */
+	0x20, /* 001000 */
+	0x10, /* 000100 */
+	0x08, /* 000010 */
+	0x04, /* 000001 */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+	0x00, /* 000000 */
+
+	/* 63 0x3F '?' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x04, /* 000001 */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 64 0x40 '@' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x5C, /* 010111 */
+	0x54, /* 010101 */
+	0x5C, /* 010111 */
+	0x40, /* 010000 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 65 0x41 'A' */
+	0x10, /* 000100 */
+	0x28, /* 001010 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x7C, /* 011111 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 66 0x42 'B' */
+	0x78, /* 011110 */
+	0x24, /* 001001 */
+	0x24, /* 001001 */
+	0x38, /* 001110 */
+	0x24, /* 001001 */
+	0x24, /* 001001 */
+	0x78, /* 011110 */
+	0x00, /* 000000 */
+
+	/* 67 0x43 'C' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 68 0x44 'D' */
+	0x78, /* 011110 */
+	0x24, /* 001001 */
+	0x24, /* 001001 */
+	0x24, /* 001001 */
+	0x24, /* 001001 */
+	0x24, /* 001001 */
+	0x78, /* 011110 */
+	0x00, /* 000000 */
+
+	/* 69 0x45 'E' */
+	0x7C, /* 011111 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x78, /* 011110 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+
+	/* 70 0x46 'F' */
+	0x7C, /* 011111 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x78, /* 011110 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x00, /* 000000 */
+
+	/* 71 0x47 'G' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x40, /* 010000 */
+	0x5C, /* 010111 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 72 0x48 'H' */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x7C, /* 011111 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 73 0x49 'I' */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 74 0x4A 'J' */
+	0x1C, /* 000111 */
+	0x08, /* 000010 */
+	0x08, /* 000010 */
+	0x08, /* 000010 */
+	0x48, /* 010010 */
+	0x48, /* 010010 */
+	0x30, /* 001100 */
+	0x00, /* 000000 */
+
+	/* 75 0x4B 'K' */
+	0x44, /* 010001 */
+	0x48, /* 010010 */
+	0x50, /* 010100 */
+	0x60, /* 011000 */
+	0x50, /* 010100 */
+	0x48, /* 010010 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 76 0x4C 'L' */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+
+	/* 77 0x4D 'M' */
+	0x44, /* 010001 */
+	0x6C, /* 011011 */
+	0x54, /* 010101 */
+	0x54, /* 010101 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 78 0x4E 'N' */
+	0x44, /* 010001 */
+	0x64, /* 011001 */
+	0x54, /* 010101 */
+	0x4C, /* 010011 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 79 0x4F 'O' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 80 0x50 'P' */
+	0x78, /* 011110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x78, /* 011110 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x00, /* 000000 */
+
+	/* 81 0x51 'Q' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x54, /* 010101 */
+	0x48, /* 010010 */
+	0x34, /* 001101 */
+	0x00, /* 000000 */
+
+	/* 82 0x52 'R' */
+	0x78, /* 011110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x78, /* 011110 */
+	0x50, /* 010100 */
+	0x48, /* 010010 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 83 0x53 'S' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x40, /* 010000 */
+	0x38, /* 001110 */
+	0x04, /* 000001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 84 0x54 'T' */
+	0x7C, /* 011111 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 85 0x55 'U' */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 86 0x56 'V' */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x28, /* 001010 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 87 0x57 'W' */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x54, /* 010101 */
+	0x54, /* 010101 */
+	0x6C, /* 011011 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 88 0x58 'X' */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x28, /* 001010 */
+	0x10, /* 000100 */
+	0x28, /* 001010 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 89 0x59 'Y' */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x28, /* 001010 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 90 0x5A 'Z' */
+	0x7C, /* 011111 */
+	0x04, /* 000001 */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+	0x40, /* 010000 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+
+	/* 91 0x5B '[' */
+	0x18, /* 000110 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x18, /* 000110 */
+	0x00, /* 000000 */
+
+	/* 92 0x5C '\' */
+	0x40, /* 010000 */
+	0x20, /* 001000 */
+	0x20, /* 001000 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x08, /* 000010 */
+	0x08, /* 000010 */
+	0x04, /* 000001 */
+
+	/* 93 0x5D ']' */
+	0x30, /* 001100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x30, /* 001100 */
+	0x00, /* 000000 */
+
+	/* 94 0x5E '^' */
+	0x10, /* 000100 */
+	0x28, /* 001010 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 95 0x5F '_' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x7C, /* 011111 */
+
+	/* 96 0x60 '`' */
+	0x20, /* 001000 */
+	0x10, /* 000100 */
+	0x08, /* 000010 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 97 0x61 'a' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x04, /* 000001 */
+	0x3C, /* 001111 */
+	0x44, /* 010001 */
+	0x3C, /* 001111 */
+	0x00, /* 000000 */
+
+	/* 98 0x62 'b' */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x58, /* 010110 */
+	0x64, /* 011001 */
+	0x44, /* 010001 */
+	0x64, /* 011001 */
+	0x58, /* 010110 */
+	0x00, /* 000000 */
+
+	/* 99 0x63 'c' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x40, /* 010000 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 100 0x64 'd' */
+	0x04, /* 000001 */
+	0x04, /* 000001 */
+	0x34, /* 001101 */
+	0x4C, /* 010011 */
+	0x44, /* 010001 */
+	0x4C, /* 010011 */
+	0x34, /* 001101 */
+	0x00, /* 000000 */
+
+	/* 101 0x65 'e' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x7C, /* 011111 */
+	0x40, /* 010000 */
+	0x3C, /* 001111 */
+	0x00, /* 000000 */
+
+	/* 102 0x66 'f' */
+	0x0C, /* 000011 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 103 0x67 'g' */
+	0x00, /* 000000 */
+	0x34, /* 001101 */
+	0x4C, /* 010011 */
+	0x44, /* 010001 */
+	0x4C, /* 010011 */
+	0x34, /* 001101 */
+	0x04, /* 000001 */
+	0x38, /* 001110 */
+
+	/* 104 0x68 'h' */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x78, /* 011110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 105 0x69 'i' */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x30, /* 001100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 106 0x6A 'j' */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x30, /* 001100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x60, /* 011000 */
+
+	/* 107 0x6B 'k' */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x48, /* 010010 */
+	0x50, /* 010100 */
+	0x70, /* 011100 */
+	0x48, /* 010010 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 108 0x6C 'l' */
+	0x30, /* 001100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 109 0x6D 'm' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x68, /* 011010 */
+	0x54, /* 010101 */
+	0x54, /* 010101 */
+	0x54, /* 010101 */
+	0x54, /* 010101 */
+	0x00, /* 000000 */
+
+	/* 110 0x6E 'n' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x58, /* 010110 */
+	0x64, /* 011001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 111 0x6F 'o' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 112 0x70 'p' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x78, /* 011110 */
+	0x44, /* 010001 */
+	0x64, /* 011001 */
+	0x58, /* 010110 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+
+	/* 113 0x71 'q' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x3C, /* 001111 */
+	0x44, /* 010001 */
+	0x4C, /* 010011 */
+	0x34, /* 001101 */
+	0x04, /* 000001 */
+	0x04, /* 000001 */
+
+	/* 114 0x72 'r' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x58, /* 010110 */
+	0x64, /* 011001 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x00, /* 000000 */
+
+	/* 115 0x73 's' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x3C, /* 001111 */
+	0x40, /* 010000 */
+	0x38, /* 001110 */
+	0x04, /* 000001 */
+	0x78, /* 011110 */
+	0x00, /* 000000 */
+
+	/* 116 0x74 't' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x0C, /* 000011 */
+	0x00, /* 000000 */
+
+	/* 117 0x75 'u' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x4C, /* 010011 */
+	0x34, /* 001101 */
+	0x00, /* 000000 */
+
+	/* 118 0x76 'v' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x28, /* 001010 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 119 0x77 'w' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x54, /* 010101 */
+	0x54, /* 010101 */
+	0x54, /* 010101 */
+	0x54, /* 010101 */
+	0x28, /* 001010 */
+	0x00, /* 000000 */
+
+	/* 120 0x78 'x' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x44, /* 010001 */
+	0x28, /* 001010 */
+	0x10, /* 000100 */
+	0x28, /* 001010 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 121 0x79 'y' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x3C, /* 001111 */
+	0x04, /* 000001 */
+	0x38, /* 001110 */
+
+	/* 122 0x7A 'z' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x7C, /* 011111 */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+
+	/* 123 0x7B '{' */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x08, /* 000010 */
+	0x00, /* 000000 */
+
+	/* 124 0x7C '|' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 125 0x7D '}' */
+	0x20, /* 001000 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+	0x00, /* 000000 */
+
+	/* 126 0x7E '~' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x20, /* 001000 */
+	0x54, /* 010101 */
+	0x08, /* 000010 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 127 0x7F '' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x10, /* 000100 */
+	0x28, /* 001010 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+
+	/* 128 0x80 '\200' */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x40, /* 010000 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+
+	/* 129 0x81 '\201' */
+	0x00, /* 000000 */
+	0x28, /* 001010 */
+	0x00, /* 000000 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x4C, /* 010011 */
+	0x34, /* 001101 */
+	0x00, /* 000000 */
+
+	/* 130 0x82 '\202' */
+	0x18, /* 000110 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x7C, /* 011111 */
+	0x40, /* 010000 */
+	0x3C, /* 001111 */
+	0x00, /* 000000 */
+
+	/* 131 0x83 '\203' */
+	0x18, /* 000110 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x04, /* 000001 */
+	0x3C, /* 001111 */
+	0x44, /* 010001 */
+	0x3C, /* 001111 */
+	0x00, /* 000000 */
+
+	/* 132 0x84 '\204' */
+	0x28, /* 001010 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x04, /* 000001 */
+	0x3C, /* 001111 */
+	0x44, /* 010001 */
+	0x3C, /* 001111 */
+	0x00, /* 000000 */
+
+	/* 133 0x85 '\205' */
+	0x18, /* 000110 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x04, /* 000001 */
+	0x3C, /* 001111 */
+	0x44, /* 010001 */
+	0x3C, /* 001111 */
+	0x00, /* 000000 */
+
+	/* 134 0x86 '\206' */
+	0x3C, /* 001111 */
+	0x18, /* 000110 */
+	0x38, /* 001110 */
+	0x04, /* 000001 */
+	0x3C, /* 001111 */
+	0x44, /* 010001 */
+	0x3C, /* 001111 */
+	0x00, /* 000000 */
+
+	/* 135 0x87 '\207' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x40, /* 010000 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+
+	/* 136 0x88 '\210' */
+	0x18, /* 000110 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x7C, /* 011111 */
+	0x40, /* 010000 */
+	0x3C, /* 001111 */
+	0x00, /* 000000 */
+
+	/* 137 0x89 '\211' */
+	0x28, /* 001010 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x7C, /* 011111 */
+	0x40, /* 010000 */
+	0x3C, /* 001111 */
+	0x00, /* 000000 */
+
+	/* 138 0x8A '\212' */
+	0x18, /* 000110 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x7C, /* 011111 */
+	0x40, /* 010000 */
+	0x3C, /* 001111 */
+	0x00, /* 000000 */
+
+	/* 139 0x8B '\213' */
+	0x28, /* 001010 */
+	0x00, /* 000000 */
+	0x30, /* 001100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 140 0x8C '\214' */
+	0x18, /* 000110 */
+	0x00, /* 000000 */
+	0x30, /* 001100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 141 0x8D '\215' */
+	0x18, /* 000110 */
+	0x00, /* 000000 */
+	0x30, /* 001100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 142 0x8E '\216' */
+	0x44, /* 010001 */
+	0x10, /* 000100 */
+	0x28, /* 001010 */
+	0x44, /* 010001 */
+	0x7C, /* 011111 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 143 0x8F '\217' */
+	0x30, /* 001100 */
+	0x48, /* 010010 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x7C, /* 011111 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 144 0x90 '\220' */
+	0x10, /* 000100 */
+	0x7C, /* 011111 */
+	0x40, /* 010000 */
+	0x78, /* 011110 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+
+	/* 145 0x91 '\221' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x78, /* 011110 */
+	0x14, /* 000101 */
+	0x7C, /* 011111 */
+	0x50, /* 010100 */
+	0x3C, /* 001111 */
+	0x00, /* 000000 */
+
+	/* 146 0x92 '\222' */
+	0x3C, /* 001111 */
+	0x50, /* 010100 */
+	0x50, /* 010100 */
+	0x78, /* 011110 */
+	0x50, /* 010100 */
+	0x50, /* 010100 */
+	0x5C, /* 010111 */
+	0x00, /* 000000 */
+
+	/* 147 0x93 '\223' */
+	0x18, /* 000110 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 148 0x94 '\224' */
+	0x28, /* 001010 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 149 0x95 '\225' */
+	0x18, /* 000110 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 150 0x96 '\226' */
+	0x10, /* 000100 */
+	0x28, /* 001010 */
+	0x00, /* 000000 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x4C, /* 010011 */
+	0x34, /* 001101 */
+	0x00, /* 000000 */
+
+	/* 151 0x97 '\227' */
+	0x20, /* 001000 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x4C, /* 010011 */
+	0x34, /* 001101 */
+	0x00, /* 000000 */
+
+	/* 152 0x98 '\230' */
+	0x28, /* 001010 */
+	0x00, /* 000000 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x3C, /* 001111 */
+	0x04, /* 000001 */
+	0x38, /* 001110 */
+
+	/* 153 0x99 '\231' */
+	0x84, /* 100001 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 154 0x9A '\232' */
+	0x88, /* 100010 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 155 0x9B '\233' */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x54, /* 010101 */
+	0x50, /* 010100 */
+	0x54, /* 010101 */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 156 0x9C '\234' */
+	0x30, /* 001100 */
+	0x48, /* 010010 */
+	0x40, /* 010000 */
+	0x70, /* 011100 */
+	0x40, /* 010000 */
+	0x44, /* 010001 */
+	0x78, /* 011110 */
+	0x00, /* 000000 */
+
+	/* 157 0x9D '\235' */
+	0x44, /* 010001 */
+	0x28, /* 001010 */
+	0x7C, /* 011111 */
+	0x10, /* 000100 */
+	0x7C, /* 011111 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 158 0x9E '\236' */
+	0x70, /* 011100 */
+	0x48, /* 010010 */
+	0x70, /* 011100 */
+	0x48, /* 010010 */
+	0x5C, /* 010111 */
+	0x48, /* 010010 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 159 0x9F '\237' */
+	0x0C, /* 000011 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x60, /* 011000 */
+	0x00, /* 000000 */
+
+	/* 160 0xA0 '\240' */
+	0x18, /* 000110 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x04, /* 000001 */
+	0x3C, /* 001111 */
+	0x44, /* 010001 */
+	0x3C, /* 001111 */
+	0x00, /* 000000 */
+
+	/* 161 0xA1 '\241' */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x30, /* 001100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 162 0xA2 '\242' */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 163 0xA3 '\243' */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x4C, /* 010011 */
+	0x34, /* 001101 */
+	0x00, /* 000000 */
+
+	/* 164 0xA4 '\244' */
+	0x34, /* 001101 */
+	0x58, /* 010110 */
+	0x00, /* 000000 */
+	0x58, /* 010110 */
+	0x64, /* 011001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 165 0xA5 '\245' */
+	0x58, /* 010110 */
+	0x44, /* 010001 */
+	0x64, /* 011001 */
+	0x54, /* 010101 */
+	0x4C, /* 010011 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 166 0xA6 '\246' */
+	0x38, /* 001110 */
+	0x04, /* 000001 */
+	0x3C, /* 001111 */
+	0x44, /* 010001 */
+	0x3C, /* 001111 */
+	0x00, /* 000000 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+
+	/* 167 0xA7 '\247' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+
+	/* 168 0xA8 '\250' */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+	0x40, /* 010000 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 169 0xA9 '\251' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x7C, /* 011111 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 170 0xAA '\252' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x7C, /* 011111 */
+	0x04, /* 000001 */
+	0x04, /* 000001 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 171 0xAB '\253' */
+	0x20, /* 001000 */
+	0x24, /* 001001 */
+	0x28, /* 001010 */
+	0x10, /* 000100 */
+	0x28, /* 001010 */
+	0x44, /* 010001 */
+	0x08, /* 000010 */
+	0x1C, /* 000111 */
+
+	/* 172 0xAC '\254' */
+	0x20, /* 001000 */
+	0x24, /* 001001 */
+	0x28, /* 001010 */
+	0x10, /* 000100 */
+	0x28, /* 001010 */
+	0x58, /* 010110 */
+	0x3C, /* 001111 */
+	0x08, /* 000010 */
+
+	/* 173 0xAD '\255' */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 174 0xAE '\256' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x24, /* 001001 */
+	0x48, /* 010010 */
+	0x90, /* 100100 */
+	0x48, /* 010010 */
+	0x24, /* 001001 */
+	0x00, /* 000000 */
+
+	/* 175 0xAF '\257' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x90, /* 100100 */
+	0x48, /* 010010 */
+	0x24, /* 001001 */
+	0x48, /* 010010 */
+	0x90, /* 100100 */
+	0x00, /* 000000 */
+
+	/* 176 0xB0 '\260' */
+	0x10, /* 000100 */
+	0x44, /* 010001 */
+	0x10, /* 000100 */
+	0x44, /* 010001 */
+	0x10, /* 000100 */
+	0x44, /* 010001 */
+	0x10, /* 000100 */
+	0x44, /* 010001 */
+
+	/* 177 0xB1 '\261' */
+	0xA8, /* 101010 */
+	0x54, /* 010101 */
+	0xA8, /* 101010 */
+	0x54, /* 010101 */
+	0xA8, /* 101010 */
+	0x54, /* 010101 */
+	0xA8, /* 101010 */
+	0x54, /* 010101 */
+
+	/* 178 0xB2 '\262' */
+	0xDC, /* 110111 */
+	0x74, /* 011101 */
+	0xDC, /* 110111 */
+	0x74, /* 011101 */
+	0xDC, /* 110111 */
+	0x74, /* 011101 */
+	0xDC, /* 110111 */
+	0x74, /* 011101 */
+
+	/* 179 0xB3 '\263' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+
+	/* 180 0xB4 '\264' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0xF0, /* 111100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+
+	/* 181 0xB5 '\265' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0xF0, /* 111100 */
+	0x10, /* 000100 */
+	0xF0, /* 111100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+
+	/* 182 0xB6 '\266' */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0xE8, /* 111010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+
+	/* 183 0xB7 '\267' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0xF8, /* 111110 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+
+	/* 184 0xB8 '\270' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0xF0, /* 111100 */
+	0x10, /* 000100 */
+	0xF0, /* 111100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+
+	/* 185 0xB9 '\271' */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0xE8, /* 111010 */
+	0x08, /* 000010 */
+	0xE8, /* 111010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+
+	/* 186 0xBA '\272' */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+
+	/* 187 0xBB '\273' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0xF8, /* 111110 */
+	0x08, /* 000010 */
+	0xE8, /* 111010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+
+	/* 188 0xBC '\274' */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0xE8, /* 111010 */
+	0x08, /* 000010 */
+	0xF8, /* 111110 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 189 0xBD '\275' */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0xF8, /* 111110 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 190 0xBE '\276' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0xF0, /* 111100 */
+	0x10, /* 000100 */
+	0xF0, /* 111100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 191 0xBF '\277' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0xF0, /* 111100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+
+	/* 192 0xC0 '\300' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x1C, /* 000111 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 193 0xC1 '\301' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0xFC, /* 111111 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 194 0xC2 '\302' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0xFC, /* 111111 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+
+	/* 195 0xC3 '\303' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x1C, /* 000111 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+
+	/* 196 0xC4 '\304' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0xFC, /* 111111 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 197 0xC5 '\305' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0xFC, /* 111111 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+
+	/* 198 0xC6 '\306' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x1C, /* 000111 */
+	0x10, /* 000100 */
+	0x1C, /* 000111 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+
+	/* 199 0xC7 '\307' */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x2C, /* 001011 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+
+	/* 200 0xC8 '\310' */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x2C, /* 001011 */
+	0x20, /* 001000 */
+	0x3C, /* 001111 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 201 0xC9 '\311' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x3C, /* 001111 */
+	0x20, /* 001000 */
+	0x2C, /* 001011 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+
+	/* 202 0xCA '\312' */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0xEC, /* 111011 */
+	0x00, /* 000000 */
+	0xFC, /* 111111 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 203 0xCB '\313' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0xFC, /* 111111 */
+	0x00, /* 000000 */
+	0xEC, /* 111011 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+
+	/* 204 0xCC '\314' */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x2C, /* 001011 */
+	0x20, /* 001000 */
+	0x2C, /* 001011 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+
+	/* 205 0xCD '\315' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0xFC, /* 111111 */
+	0x00, /* 000000 */
+	0xFC, /* 111111 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 206 0xCE '\316' */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0xEC, /* 111011 */
+	0x00, /* 000000 */
+	0xEC, /* 111011 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+
+	/* 207 0xCF '\317' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0xFC, /* 111111 */
+	0x00, /* 000000 */
+	0xFC, /* 111111 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 208 0xD0 '\320' */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0xFC, /* 111111 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 209 0xD1 '\321' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0xFC, /* 111111 */
+	0x00, /* 000000 */
+	0xFC, /* 111111 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+
+	/* 210 0xD2 '\322' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0xFC, /* 111111 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+
+	/* 211 0xD3 '\323' */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x3C, /* 001111 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 212 0xD4 '\324' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x1C, /* 000111 */
+	0x10, /* 000100 */
+	0x1C, /* 000111 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 213 0xD5 '\325' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x1C, /* 000111 */
+	0x10, /* 000100 */
+	0x1C, /* 000111 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+
+	/* 214 0xD6 '\326' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x3C, /* 001111 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+
+	/* 215 0xD7 '\327' */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0xFC, /* 111111 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+
+	/* 216 0xD8 '\330' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0xFC, /* 111111 */
+	0x10, /* 000100 */
+	0xFC, /* 111111 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+
+	/* 217 0xD9 '\331' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0xF0, /* 111100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 218 0xDA '\332' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x1C, /* 000111 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+
+	/* 219 0xDB '\333' */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+
+	/* 220 0xDC '\334' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+
+	/* 221 0xDD '\335' */
+	0xE0, /* 111000 */
+	0xE0, /* 111000 */
+	0xE0, /* 111000 */
+	0xE0, /* 111000 */
+	0xE0, /* 111000 */
+	0xE0, /* 111000 */
+	0xE0, /* 111000 */
+	0xE0, /* 111000 */
+
+	/* 222 0xDE '\336' */
+	0x1C, /* 000111 */
+	0x1C, /* 000111 */
+	0x1C, /* 000111 */
+	0x1C, /* 000111 */
+	0x1C, /* 000111 */
+	0x1C, /* 000111 */
+	0x1C, /* 000111 */
+	0x1C, /* 000111 */
+
+	/* 223 0xDF '\337' */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 224 0xE0 '\340' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x34, /* 001101 */
+	0x48, /* 010010 */
+	0x48, /* 010010 */
+	0x48, /* 010010 */
+	0x34, /* 001101 */
+	0x00, /* 000000 */
+
+	/* 225 0xE1 '\341' */
+	0x24, /* 001001 */
+	0x44, /* 010001 */
+	0x48, /* 010010 */
+	0x48, /* 010010 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x58, /* 010110 */
+	0x40, /* 010000 */
+
+	/* 226 0xE2 '\342' */
+	0x7C, /* 011111 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x00, /* 000000 */
+
+	/* 227 0xE3 '\343' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x7C, /* 011111 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x00, /* 000000 */
+
+	/* 228 0xE4 '\344' */
+	0x7C, /* 011111 */
+	0x24, /* 001001 */
+	0x10, /* 000100 */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x24, /* 001001 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+
+	/* 229 0xE5 '\345' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x3C, /* 001111 */
+	0x48, /* 010010 */
+	0x48, /* 010010 */
+	0x48, /* 010010 */
+	0x30, /* 001100 */
+	0x00, /* 000000 */
+
+	/* 230 0xE6 '\346' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x48, /* 010010 */
+	0x48, /* 010010 */
+	0x48, /* 010010 */
+	0x48, /* 010010 */
+	0x74, /* 011101 */
+	0x40, /* 010000 */
+
+	/* 231 0xE7 '\347' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x7C, /* 011111 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x0C, /* 000011 */
+	0x00, /* 000000 */
+
+	/* 232 0xE8 '\350' */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 233 0xE9 '\351' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x7C, /* 011111 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 234 0xEA '\352' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x28, /* 001010 */
+	0x6C, /* 011011 */
+	0x00, /* 000000 */
+
+	/* 235 0xEB '\353' */
+	0x18, /* 000110 */
+	0x20, /* 001000 */
+	0x18, /* 000110 */
+	0x24, /* 001001 */
+	0x24, /* 001001 */
+	0x24, /* 001001 */
+	0x18, /* 000110 */
+	0x00, /* 000000 */
+
+	/* 236 0xEC '\354' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x54, /* 010101 */
+	0x54, /* 010101 */
+	0x54, /* 010101 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 237 0xED '\355' */
+	0x00, /* 000000 */
+	0x04, /* 000001 */
+	0x38, /* 001110 */
+	0x54, /* 010101 */
+	0x54, /* 010101 */
+	0x38, /* 001110 */
+	0x40, /* 010000 */
+	0x00, /* 000000 */
+
+	/* 238 0xEE '\356' */
+	0x3C, /* 001111 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x38, /* 001110 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x3C, /* 001111 */
+	0x00, /* 000000 */
+
+	/* 239 0xEF '\357' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 240 0xF0 '\360' */
+	0x00, /* 000000 */
+	0xFC, /* 111111 */
+	0x00, /* 000000 */
+	0xFC, /* 111111 */
+	0x00, /* 000000 */
+	0xFC, /* 111111 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 241 0xF1 '\361' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x7C, /* 011111 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+
+	/* 242 0xF2 '\362' */
+	0x20, /* 001000 */
+	0x10, /* 000100 */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 243 0xF3 '\363' */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+	0x10, /* 000100 */
+	0x08, /* 000010 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 244 0xF4 '\364' */
+	0x0C, /* 000011 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+
+	/* 245 0xF5 '\365' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x60, /* 011000 */
+
+	/* 246 0xF6 '\366' */
+	0x00, /* 000000 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 247 0xF7 '\367' */
+	0x00, /* 000000 */
+	0x20, /* 001000 */
+	0x54, /* 010101 */
+	0x08, /* 000010 */
+	0x20, /* 001000 */
+	0x54, /* 010101 */
+	0x08, /* 000010 */
+	0x00, /* 000000 */
+
+	/* 248 0xF8 '\370' */
+	0x30, /* 001100 */
+	0x48, /* 010010 */
+	0x48, /* 010010 */
+	0x30, /* 001100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 249 0xF9 '\371' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 250 0xFA '\372' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 251 0xFB '\373' */
+	0x04, /* 000001 */
+	0x08, /* 000010 */
+	0x08, /* 000010 */
+	0x50, /* 010100 */
+	0x50, /* 010100 */
+	0x20, /* 001000 */
+	0x20, /* 001000 */
+	0x00, /* 000000 */
+
+	/* 252 0xFC '\374' */
+	0x60, /* 011000 */
+	0x50, /* 010100 */
+	0x50, /* 010100 */
+	0x50, /* 010100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 253 0xFD '\375' */
+	0x60, /* 011000 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+	0x70, /* 011100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 254 0xFE '\376' */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x38, /* 001110 */
+	0x38, /* 001110 */
+	0x38, /* 001110 */
+	0x38, /* 001110 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 255 0xFF '\377' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+};
+
+const struct font_desc font_6x8 = {
+	.idx	= FONT6x8_IDX,
+	.name	= "6x8",
+	.width	= 6,
+	.height	= 8,
+	.data	= fontdata_6x8,
+	.pref	= 0,
+};
diff --git a/lib/fonts/fonts.c b/lib/fonts/fonts.c
index e7258d8c252b..5f4b07b56cd9 100644
--- a/lib/fonts/fonts.c
+++ b/lib/fonts/fonts.c
@@ -57,6 +57,9 @@ static const struct font_desc *fonts[] = {
 #ifdef CONFIG_FONT_TER16x32
 	&font_ter_16x32,
 #endif
+#ifdef CONFIG_FONT_6x8
+	&font_6x8,
+#endif
 };
 
 #define num_fonts ARRAY_SIZE(fonts)
-- 
cgit v1.2.3


From de394e7568ce2cdb4643ed230169f484f25f9442 Mon Sep 17 00:00:00 2001
From: "peterz@infradead.org" <peterz@infradead.org>
Date: Tue, 8 Sep 2020 12:57:43 +0200
Subject: tracepoint: Fix overly long tracepoint names

Stephen Rothwell reported:

> Exported symbols need to be <= (64 - sizeof(Elf_Addr)) long.  This is
> presumably 56 on 64 bit arches and the above symbol (including the '.')
> is 56 characters long.

Shorten the tracepoint symbol name.

Fixes: d25e37d89dd2 ("tracepoint: Optimize using static_call()")
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20200908105743.GW2674@hirez.programming.kicks-ass.net
---
 include/linux/tracepoint.h | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 3722a10fc46d..81fa0b2f271e 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -154,7 +154,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 #ifdef CONFIG_HAVE_STATIC_CALL
 #define __DO_TRACE_CALL(name)	static_call(tp_func_##name)
 #else
-#define __DO_TRACE_CALL(name)	__tracepoint_iter_##name
+#define __DO_TRACE_CALL(name)	__traceiter_##name
 #endif /* CONFIG_HAVE_STATIC_CALL */
 
 /*
@@ -232,8 +232,8 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
  * poking RCU a bit.
  */
 #define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \
-	extern int __tracepoint_iter_##name(data_proto);		\
-	DECLARE_STATIC_CALL(tp_func_##name, __tracepoint_iter_##name); \
+	extern int __traceiter_##name(data_proto);			\
+	DECLARE_STATIC_CALL(tp_func_##name, __traceiter_##name);	\
 	extern struct tracepoint __tracepoint_##name;			\
 	static inline void trace_##name(proto)				\
 	{								\
@@ -288,19 +288,19 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 	static const char __tpstrtab_##_name[]				\
 	__section(__tracepoints_strings) = #_name;			\
 	extern struct static_call_key STATIC_CALL_KEY(tp_func_##_name);	\
-	int __tracepoint_iter_##_name(void *__data, proto);		\
+	int __traceiter_##_name(void *__data, proto);			\
 	struct tracepoint __tracepoint_##_name	__used			\
 	__section(__tracepoints) = {					\
 		.name = __tpstrtab_##_name,				\
 		.key = STATIC_KEY_INIT_FALSE,				\
 		.static_call_key = &STATIC_CALL_KEY(tp_func_##_name),	\
 		.static_call_tramp = STATIC_CALL_TRAMP_ADDR(tp_func_##_name), \
-		.iterator = &__tracepoint_iter_##_name,			\
+		.iterator = &__traceiter_##_name,			\
 		.regfunc = _reg,					\
 		.unregfunc = _unreg,					\
 		.funcs = NULL };					\
 	__TRACEPOINT_ENTRY(_name);					\
-	int __tracepoint_iter_##_name(void *__data, proto)		\
+	int __traceiter_##_name(void *__data, proto)			\
 	{								\
 		struct tracepoint_func *it_func_ptr;			\
 		void *it_func;						\
@@ -314,18 +314,18 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 		} while ((++it_func_ptr)->func);			\
 		return 0;						\
 	}								\
-	DEFINE_STATIC_CALL(tp_func_##_name, __tracepoint_iter_##_name);
+	DEFINE_STATIC_CALL(tp_func_##_name, __traceiter_##_name);
 
 #define DEFINE_TRACE(name, proto, args)		\
 	DEFINE_TRACE_FN(name, NULL, NULL, PARAMS(proto), PARAMS(args));
 
 #define EXPORT_TRACEPOINT_SYMBOL_GPL(name)				\
 	EXPORT_SYMBOL_GPL(__tracepoint_##name);				\
-	EXPORT_SYMBOL_GPL(__tracepoint_iter_##name);			\
+	EXPORT_SYMBOL_GPL(__traceiter_##name);				\
 	EXPORT_STATIC_CALL_GPL(tp_func_##name)
 #define EXPORT_TRACEPOINT_SYMBOL(name)					\
 	EXPORT_SYMBOL(__tracepoint_##name);				\
-	EXPORT_SYMBOL(__tracepoint_iter_##name);			\
+	EXPORT_SYMBOL(__traceiter_##name);				\
 	EXPORT_STATIC_CALL(tp_func_##name)
 
 
-- 
cgit v1.2.3


From b41b0ce5982693e27307cfe0aaf49bc8e3a20900 Mon Sep 17 00:00:00 2001
From: Georgi Djakov <georgi.djakov@linaro.org>
Date: Wed, 29 Jul 2020 15:34:39 +0300
Subject: interconnect: Add bulk API helpers

There are drivers which just need to get multiple interconnect paths,
request some predefined amounts of bandwidth and then just toggle the
paths between enabled/disabled state.

The aim of this patch is simplify the above and to allow drivers to put
all the path names and bandwidth data into a single static icc_bulk_data
table and call the icc_bulk_* functions on that table in order to scale
all the interconnect paths in parallel.

Suggested-by: Evan Green <evgreen@chromium.org>
Suggested-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Link: https://lore.kernel.org/r/20200729123439.9961-1-georgi.djakov@linaro.org
Signed-off-by: Georgi Djakov <georgi.djakov@linaro.org>
---
 drivers/interconnect/Makefile |   2 +-
 drivers/interconnect/bulk.c   | 117 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/interconnect.h  |  22 ++++++++
 3 files changed, 140 insertions(+), 1 deletion(-)
 create mode 100644 drivers/interconnect/bulk.c

(limited to 'include/linux')

diff --git a/drivers/interconnect/Makefile b/drivers/interconnect/Makefile
index 4825c287ca13..d203520b0a56 100644
--- a/drivers/interconnect/Makefile
+++ b/drivers/interconnect/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 
 CFLAGS_core.o				:= -I$(src)
-icc-core-objs				:= core.o
+icc-core-objs				:= core.o bulk.o
 
 obj-$(CONFIG_INTERCONNECT)		+= icc-core.o
 obj-$(CONFIG_INTERCONNECT_IMX)		+= imx/
diff --git a/drivers/interconnect/bulk.c b/drivers/interconnect/bulk.c
new file mode 100644
index 000000000000..73e2c8d0a412
--- /dev/null
+++ b/drivers/interconnect/bulk.c
@@ -0,0 +1,117 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/interconnect-provider.h>
+#include <linux/device.h>
+#include <linux/export.h>
+
+/**
+ * of_icc_bulk_get() - get interconnect paths
+ * @dev: the device requesting the path
+ * @num_paths: the number of icc_bulk_data
+ * @paths: the table with the paths we want to get
+ *
+ * Returns 0 on success or negative errno otherwise.
+ */
+int __must_check of_icc_bulk_get(struct device *dev, int num_paths,
+				 struct icc_bulk_data *paths)
+{
+	int ret, i;
+
+	for (i = 0; i < num_paths; i++) {
+		paths[i].path = of_icc_get(dev, paths[i].name);
+		if (IS_ERR(paths[i].path)) {
+			ret = PTR_ERR(paths[i].path);
+			if (ret != -EPROBE_DEFER)
+				dev_err(dev, "of_icc_get() failed on path %s (%d)\n",
+					paths[i].name, ret);
+			paths[i].path = NULL;
+			goto err;
+		}
+	}
+
+	return 0;
+
+err:
+	icc_bulk_put(i, paths);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(of_icc_bulk_get);
+
+/**
+ * icc_bulk_put() - put a list of interconnect paths
+ * @num_paths: the number of icc_bulk_data
+ * @paths: the icc_bulk_data table with the paths being put
+ */
+void icc_bulk_put(int num_paths, struct icc_bulk_data *paths)
+{
+	while (--num_paths >= 0) {
+		icc_put(paths[num_paths].path);
+		paths[num_paths].path = NULL;
+	}
+}
+EXPORT_SYMBOL_GPL(icc_bulk_put);
+
+/**
+ * icc_bulk_set() - set bandwidth to a set of paths
+ * @num_paths: the number of icc_bulk_data
+ * @paths: the icc_bulk_data table containing the paths and bandwidth
+ *
+ * Returns 0 on success or negative errno otherwise.
+ */
+int icc_bulk_set_bw(int num_paths, const struct icc_bulk_data *paths)
+{
+	int ret = 0;
+	int i;
+
+	for (i = 0; i < num_paths; i++) {
+		ret = icc_set_bw(paths[i].path, paths[i].avg_bw, paths[i].peak_bw);
+		if (ret) {
+			pr_err("icc_set_bw() failed on path %s (%d)\n", paths[i].name, ret);
+			return ret;
+		}
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(icc_bulk_set_bw);
+
+/**
+ * icc_bulk_enable() - enable a previously disabled set of paths
+ * @num_paths: the number of icc_bulk_data
+ * @paths: the icc_bulk_data table containing the paths and bandwidth
+ *
+ * Returns 0 on success or negative errno otherwise.
+ */
+int icc_bulk_enable(int num_paths, const struct icc_bulk_data *paths)
+{
+	int ret, i;
+
+	for (i = 0; i < num_paths; i++) {
+		ret = icc_enable(paths[i].path);
+		if (ret) {
+			pr_err("icc_enable() failed on path %s (%d)\n", paths[i].name, ret);
+			goto err;
+		}
+	}
+
+	return 0;
+
+err:
+	icc_bulk_disable(i, paths);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(icc_bulk_enable);
+
+/**
+ * icc_bulk_disable() - disable a set of interconnect paths
+ * @num_paths: the number of icc_bulk_data
+ * @paths: the icc_bulk_data table containing the paths and bandwidth
+ */
+void icc_bulk_disable(int num_paths, const struct icc_bulk_data *paths)
+{
+	while (--num_paths >= 0)
+		icc_disable(paths[num_paths].path);
+}
+EXPORT_SYMBOL_GPL(icc_bulk_disable);
diff --git a/include/linux/interconnect.h b/include/linux/interconnect.h
index 3a63d98613fc..f2dd2fc8d3cd 100644
--- a/include/linux/interconnect.h
+++ b/include/linux/interconnect.h
@@ -23,6 +23,28 @@
 struct icc_path;
 struct device;
 
+/**
+ * struct icc_bulk_data - Data used for bulk icc operations.
+ *
+ * @path: reference to the interconnect path (internal use)
+ * @name: the name from the "interconnect-names" DT property
+ * @avg_bw: average bandwidth in icc units
+ * @peak_bw: peak bandwidth in icc units
+ */
+struct icc_bulk_data {
+	struct icc_path	*path;
+	const char *name;
+	u32 avg_bw;
+	u32 peak_bw;
+};
+
+int __must_check of_icc_bulk_get(struct device *dev, int num_paths,
+				 struct icc_bulk_data *paths);
+void icc_bulk_put(int num_paths, struct icc_bulk_data *paths);
+int icc_bulk_set_bw(int num_paths, const struct icc_bulk_data *paths);
+int icc_bulk_enable(int num_paths, const struct icc_bulk_data *paths);
+void icc_bulk_disable(int num_paths, const struct icc_bulk_data *paths);
+
 #if IS_ENABLED(CONFIG_INTERCONNECT)
 
 struct icc_path *icc_get(struct device *dev, const int src_id,
-- 
cgit v1.2.3


From 1521e22bfa12db6225002ba3b040572a78dff996 Mon Sep 17 00:00:00 2001
From: Georgi Djakov <georgi.djakov@linaro.org>
Date: Thu, 3 Sep 2020 16:31:28 +0300
Subject: interconnect: Introduce xlate_extended() callback

Currently there is the xlate() callback, which is used by providers for
mapping the nodes from phandle arguments. That's fine for simple mappings,
but the phandle arguments could contain an additional data, such as tag
information. Let's create another callback xlate_extended() for the cases
where providers want also populate the path tag data.

Tested-by: Sibi Sankar <sibis@codeaurora.org>
Reviewed-by: Sibi Sankar <sibis@codeaurora.org>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
Tested-by: Matthias Kaehlcke <mka@chromium.org>
Link: https://lore.kernel.org/r/20200903133134.17201-2-georgi.djakov@linaro.org
Signed-off-by: Georgi Djakov <georgi.djakov@linaro.org>
---
 drivers/interconnect/core.c           | 73 ++++++++++++++++++++++++-----------
 include/linux/interconnect-provider.h | 17 +++++++-
 2 files changed, 65 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c
index cf07491b7415..7642f3601dbf 100644
--- a/drivers/interconnect/core.c
+++ b/drivers/interconnect/core.c
@@ -342,12 +342,13 @@ EXPORT_SYMBOL_GPL(of_icc_xlate_onecell);
  * Looks for interconnect provider under the node specified by @spec and if
  * found, uses xlate function of the provider to map phandle args to node.
  *
- * Returns a valid pointer to struct icc_node on success or ERR_PTR()
+ * Returns a valid pointer to struct icc_node_data on success or ERR_PTR()
  * on failure.
  */
-struct icc_node *of_icc_get_from_provider(struct of_phandle_args *spec)
+struct icc_node_data *of_icc_get_from_provider(struct of_phandle_args *spec)
 {
 	struct icc_node *node = ERR_PTR(-EPROBE_DEFER);
+	struct icc_node_data *data = NULL;
 	struct icc_provider *provider;
 
 	if (!spec)
@@ -355,14 +356,33 @@ struct icc_node *of_icc_get_from_provider(struct of_phandle_args *spec)
 
 	mutex_lock(&icc_lock);
 	list_for_each_entry(provider, &icc_providers, provider_list) {
-		if (provider->dev->of_node == spec->np)
-			node = provider->xlate(spec, provider->data);
-		if (!IS_ERR(node))
-			break;
+		if (provider->dev->of_node == spec->np) {
+			if (provider->xlate_extended) {
+				data = provider->xlate_extended(spec, provider->data);
+				if (!IS_ERR(data)) {
+					node = data->node;
+					break;
+				}
+			} else {
+				node = provider->xlate(spec, provider->data);
+				if (!IS_ERR(node))
+					break;
+			}
+		}
 	}
 	mutex_unlock(&icc_lock);
 
-	return node;
+	if (IS_ERR(node))
+		return ERR_CAST(node);
+
+	if (!data) {
+		data = kzalloc(sizeof(*data), GFP_KERNEL);
+		if (!data)
+			return ERR_PTR(-ENOMEM);
+		data->node = node;
+	}
+
+	return data;
 }
 EXPORT_SYMBOL_GPL(of_icc_get_from_provider);
 
@@ -409,7 +429,7 @@ EXPORT_SYMBOL_GPL(devm_of_icc_get);
 struct icc_path *of_icc_get_by_index(struct device *dev, int idx)
 {
 	struct icc_path *path;
-	struct icc_node *src_node, *dst_node;
+	struct icc_node_data *src_data, *dst_data;
 	struct device_node *np;
 	struct of_phandle_args src_args, dst_args;
 	int ret;
@@ -447,39 +467,46 @@ struct icc_path *of_icc_get_by_index(struct device *dev, int idx)
 
 	of_node_put(dst_args.np);
 
-	src_node = of_icc_get_from_provider(&src_args);
+	src_data = of_icc_get_from_provider(&src_args);
 
-	if (IS_ERR(src_node)) {
-		if (PTR_ERR(src_node) != -EPROBE_DEFER)
+	if (IS_ERR(src_data)) {
+		if (PTR_ERR(src_data) != -EPROBE_DEFER)
 			dev_err(dev, "error finding src node: %ld\n",
-				PTR_ERR(src_node));
-		return ERR_CAST(src_node);
+				PTR_ERR(src_data));
+		return ERR_CAST(src_data);
 	}
 
-	dst_node = of_icc_get_from_provider(&dst_args);
+	dst_data = of_icc_get_from_provider(&dst_args);
 
-	if (IS_ERR(dst_node)) {
-		if (PTR_ERR(dst_node) != -EPROBE_DEFER)
+	if (IS_ERR(dst_data)) {
+		if (PTR_ERR(dst_data) != -EPROBE_DEFER)
 			dev_err(dev, "error finding dst node: %ld\n",
-				PTR_ERR(dst_node));
-		return ERR_CAST(dst_node);
+				PTR_ERR(dst_data));
+		kfree(src_data);
+		return ERR_CAST(dst_data);
 	}
 
 	mutex_lock(&icc_lock);
-	path = path_find(dev, src_node, dst_node);
+	path = path_find(dev, src_data->node, dst_data->node);
 	mutex_unlock(&icc_lock);
 	if (IS_ERR(path)) {
 		dev_err(dev, "%s: invalid path=%ld\n", __func__, PTR_ERR(path));
-		return path;
+		goto free_icc_data;
 	}
 
+	if (src_data->tag && src_data->tag == dst_data->tag)
+		icc_set_tag(path, src_data->tag);
+
 	path->name = kasprintf(GFP_KERNEL, "%s-%s",
-			       src_node->name, dst_node->name);
+			       src_data->node->name, dst_data->node->name);
 	if (!path->name) {
 		kfree(path);
-		return ERR_PTR(-ENOMEM);
+		path = ERR_PTR(-ENOMEM);
 	}
 
+free_icc_data:
+	kfree(src_data);
+	kfree(dst_data);
 	return path;
 }
 EXPORT_SYMBOL_GPL(of_icc_get_by_index);
@@ -981,7 +1008,7 @@ int icc_provider_add(struct icc_provider *provider)
 {
 	if (WARN_ON(!provider->set))
 		return -EINVAL;
-	if (WARN_ON(!provider->xlate))
+	if (WARN_ON(!provider->xlate && !provider->xlate_extended))
 		return -EINVAL;
 
 	mutex_lock(&icc_lock);
diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h
index 4735518de515..4d535fddd5d3 100644
--- a/include/linux/interconnect-provider.h
+++ b/include/linux/interconnect-provider.h
@@ -14,6 +14,17 @@
 struct icc_node;
 struct of_phandle_args;
 
+/**
+ * struct icc_node_data - icc node data
+ *
+ * @node: icc node
+ * @tag: tag
+ */
+struct icc_node_data {
+	struct icc_node *node;
+	u32 tag;
+};
+
 /**
  * struct icc_onecell_data - driver data for onecell interconnect providers
  *
@@ -39,6 +50,7 @@ struct icc_node *of_icc_xlate_onecell(struct of_phandle_args *spec,
  * @pre_aggregate: pointer to device specific function that is called
  *		   before the aggregation begins (optional)
  * @xlate: provider-specific callback for mapping nodes from phandle arguments
+ * @xlate_extended: vendor-specific callback for mapping node data from phandle arguments
  * @dev: the device this interconnect provider belongs to
  * @users: count of active users
  * @inter_set: whether inter-provider pairs will be configured with @set
@@ -52,6 +64,7 @@ struct icc_provider {
 			 u32 peak_bw, u32 *agg_avg, u32 *agg_peak);
 	void (*pre_aggregate)(struct icc_node *node);
 	struct icc_node* (*xlate)(struct of_phandle_args *spec, void *data);
+	struct icc_node_data* (*xlate_extended)(struct of_phandle_args *spec, void *data);
 	struct device		*dev;
 	int			users;
 	bool			inter_set;
@@ -105,7 +118,7 @@ void icc_node_del(struct icc_node *node);
 int icc_nodes_remove(struct icc_provider *provider);
 int icc_provider_add(struct icc_provider *provider);
 int icc_provider_del(struct icc_provider *provider);
-struct icc_node *of_icc_get_from_provider(struct of_phandle_args *spec);
+struct icc_node_data *of_icc_get_from_provider(struct of_phandle_args *spec);
 
 #else
 
@@ -157,7 +170,7 @@ static inline int icc_provider_del(struct icc_provider *provider)
 	return -ENOTSUPP;
 }
 
-static inline struct icc_node *of_icc_get_from_provider(struct of_phandle_args *spec)
+static inline struct icc_node_data *of_icc_get_from_provider(struct of_phandle_args *spec)
 {
 	return ERR_PTR(-ENOTSUPP);
 }
-- 
cgit v1.2.3


From a8803055127afb87640974adedac60435592b86d Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Mon, 7 Sep 2020 18:46:55 +0100
Subject: firmware: arm_scmi: Add system power protocol support

Add bare protocol support for SCMI system power protocol as needed by
an OSPM agent: basic initialization and SYSTEM_POWER_STATE_NOTIFIER
core notification support.

No event-handling logic is attached to such notification..

Link: https://lore.kernel.org/r/20200907174657.32466-2-cristian.marussi@arm.com
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_scmi/Makefile |   2 +-
 drivers/firmware/arm_scmi/system.c | 136 +++++++++++++++++++++++++++++++++++++
 include/linux/scmi_protocol.h      |  18 +++++
 3 files changed, 155 insertions(+), 1 deletion(-)
 create mode 100644 drivers/firmware/arm_scmi/system.c

(limited to 'include/linux')

diff --git a/drivers/firmware/arm_scmi/Makefile b/drivers/firmware/arm_scmi/Makefile
index 6f9cbc4aef22..643f2320f976 100644
--- a/drivers/firmware/arm_scmi/Makefile
+++ b/drivers/firmware/arm_scmi/Makefile
@@ -5,5 +5,5 @@ scmi-driver-y = driver.o notify.o
 scmi-transport-y = shmem.o
 scmi-transport-$(CONFIG_MAILBOX) += mailbox.o
 scmi-transport-$(CONFIG_HAVE_ARM_SMCCC_DISCOVERY) += smc.o
-scmi-protocols-y = base.o clock.o perf.o power.o reset.o sensors.o
+scmi-protocols-y = base.o clock.o perf.o power.o reset.o sensors.o system.o
 obj-$(CONFIG_ARM_SCMI_POWER_DOMAIN) += scmi_pm_domain.o
diff --git a/drivers/firmware/arm_scmi/system.c b/drivers/firmware/arm_scmi/system.c
new file mode 100644
index 000000000000..aa1e74f066a0
--- /dev/null
+++ b/drivers/firmware/arm_scmi/system.c
@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * System Control and Management Interface (SCMI) System Power Protocol
+ *
+ * Copyright (C) 2020 ARM Ltd.
+ */
+
+#define pr_fmt(fmt) "SCMI Notifications SYSTEM - " fmt
+
+#include <linux/scmi_protocol.h>
+
+#include "common.h"
+#include "notify.h"
+
+#define SCMI_SYSTEM_NUM_SOURCES		1
+
+enum scmi_system_protocol_cmd {
+	SYSTEM_POWER_STATE_NOTIFY = 0x5,
+};
+
+struct scmi_system_power_state_notify {
+	__le32 notify_enable;
+};
+
+struct scmi_system_power_state_notifier_payld {
+	__le32 agent_id;
+	__le32 flags;
+	__le32 system_state;
+};
+
+struct scmi_system_info {
+	u32 version;
+};
+
+static int scmi_system_request_notify(const struct scmi_handle *handle,
+				      bool enable)
+{
+	int ret;
+	struct scmi_xfer *t;
+	struct scmi_system_power_state_notify *notify;
+
+	ret = scmi_xfer_get_init(handle, SYSTEM_POWER_STATE_NOTIFY,
+				 SCMI_PROTOCOL_SYSTEM, sizeof(*notify), 0, &t);
+	if (ret)
+		return ret;
+
+	notify = t->tx.buf;
+	notify->notify_enable = enable ? cpu_to_le32(BIT(0)) : 0;
+
+	ret = scmi_do_xfer(handle, t);
+
+	scmi_xfer_put(handle, t);
+	return ret;
+}
+
+static int scmi_system_set_notify_enabled(const struct scmi_handle *handle,
+					  u8 evt_id, u32 src_id, bool enable)
+{
+	int ret;
+
+	ret = scmi_system_request_notify(handle, enable);
+	if (ret)
+		pr_debug("FAIL_ENABLE - evt[%X] - ret:%d\n", evt_id, ret);
+
+	return ret;
+}
+
+static void *scmi_system_fill_custom_report(const struct scmi_handle *handle,
+					    u8 evt_id, ktime_t timestamp,
+					    const void *payld, size_t payld_sz,
+					    void *report, u32 *src_id)
+{
+	const struct scmi_system_power_state_notifier_payld *p = payld;
+	struct scmi_system_power_state_notifier_report *r = report;
+
+	if (evt_id != SCMI_EVENT_SYSTEM_POWER_STATE_NOTIFIER ||
+	    sizeof(*p) != payld_sz)
+		return NULL;
+
+	r->timestamp = timestamp;
+	r->agent_id = le32_to_cpu(p->agent_id);
+	r->flags = le32_to_cpu(p->flags);
+	r->system_state = le32_to_cpu(p->system_state);
+	*src_id = 0;
+
+	return r;
+}
+
+static const struct scmi_event system_events[] = {
+	{
+		.id = SCMI_EVENT_SYSTEM_POWER_STATE_NOTIFIER,
+		.max_payld_sz =
+			sizeof(struct scmi_system_power_state_notifier_payld),
+		.max_report_sz =
+			sizeof(struct scmi_system_power_state_notifier_report),
+	},
+};
+
+static const struct scmi_event_ops system_event_ops = {
+	.set_notify_enabled = scmi_system_set_notify_enabled,
+	.fill_custom_report = scmi_system_fill_custom_report,
+};
+
+static int scmi_system_protocol_init(struct scmi_handle *handle)
+{
+	u32 version;
+	struct scmi_system_info *pinfo;
+
+	scmi_version_get(handle, SCMI_PROTOCOL_SYSTEM, &version);
+
+	dev_dbg(handle->dev, "System Power Version %d.%d\n",
+		PROTOCOL_REV_MAJOR(version), PROTOCOL_REV_MINOR(version));
+
+	pinfo = devm_kzalloc(handle->dev, sizeof(*pinfo), GFP_KERNEL);
+	if (!pinfo)
+		return -ENOMEM;
+
+	scmi_register_protocol_events(handle,
+				      SCMI_PROTOCOL_SYSTEM, SCMI_PROTO_QUEUE_SZ,
+				      &system_event_ops,
+				      system_events,
+				      ARRAY_SIZE(system_events),
+				      SCMI_SYSTEM_NUM_SOURCES);
+
+	pinfo->version = version;
+	handle->system_priv = pinfo;
+
+	return 0;
+}
+
+static int __init scmi_system_init(void)
+{
+	return scmi_protocol_register(SCMI_PROTOCOL_SYSTEM,
+				      &scmi_system_protocol_init);
+}
+subsys_initcall(scmi_system_init);
diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h
index 05570afc7f74..4b10093ad671 100644
--- a/include/linux/scmi_protocol.h
+++ b/include/linux/scmi_protocol.h
@@ -292,6 +292,7 @@ struct scmi_handle {
 	void *sensor_priv;
 	void *reset_priv;
 	void *notify_priv;
+	void *system_priv;
 };
 
 enum scmi_std_protocol {
@@ -304,6 +305,15 @@ enum scmi_std_protocol {
 	SCMI_PROTOCOL_RESET = 0x16,
 };
 
+enum scmi_system_events {
+	SCMI_SYSTEM_SHUTDOWN,
+	SCMI_SYSTEM_COLDRESET,
+	SCMI_SYSTEM_WARMRESET,
+	SCMI_SYSTEM_POWERUP,
+	SCMI_SYSTEM_SUSPEND,
+	SCMI_SYSTEM_MAX
+};
+
 struct scmi_device {
 	u32 id;
 	u8 protocol_id;
@@ -378,6 +388,7 @@ enum scmi_notification_events {
 	SCMI_EVENT_SENSOR_TRIP_POINT_EVENT = 0x0,
 	SCMI_EVENT_RESET_ISSUED = 0x0,
 	SCMI_EVENT_BASE_ERROR_EVENT = 0x0,
+	SCMI_EVENT_SYSTEM_POWER_STATE_NOTIFIER = 0x0,
 };
 
 struct scmi_power_state_changed_report {
@@ -387,6 +398,13 @@ struct scmi_power_state_changed_report {
 	unsigned int	power_state;
 };
 
+struct scmi_system_power_state_notifier_report {
+	ktime_t		timestamp;
+	unsigned int	agent_id;
+	unsigned int	flags;
+	unsigned int	system_state;
+};
+
 struct scmi_perf_limits_report {
 	ktime_t		timestamp;
 	unsigned int	agent_id;
-- 
cgit v1.2.3


From 4bd6a7353ee14697fea645e941354976d2c4a452 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 3 Sep 2020 16:22:32 +0200
Subject: sysctl: Convert to iter interfaces

Using the read_iter/write_iter interfaces allows for in-kernel users
to set sysctls without using set_fs().  Also, the buffer is a string,
so give it the real type of 'char *', not void *.

[AV: Christoph's fixup folded in]

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/proc/proc_sysctl.c      | 48 +++++++++++++++++++++++-----------------------
 include/linux/bpf-cgroup.h |  2 +-
 kernel/bpf/cgroup.c        |  2 +-
 3 files changed, 26 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 6c1166ccdaea..317899222d7f 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -12,6 +12,7 @@
 #include <linux/cred.h>
 #include <linux/namei.h>
 #include <linux/mm.h>
+#include <linux/uio.h>
 #include <linux/module.h>
 #include <linux/bpf-cgroup.h>
 #include <linux/mount.h>
@@ -540,13 +541,14 @@ out:
 	return err;
 }
 
-static ssize_t proc_sys_call_handler(struct file *filp, void __user *ubuf,
-		size_t count, loff_t *ppos, int write)
+static ssize_t proc_sys_call_handler(struct kiocb *iocb, struct iov_iter *iter,
+		int write)
 {
-	struct inode *inode = file_inode(filp);
+	struct inode *inode = file_inode(iocb->ki_filp);
 	struct ctl_table_header *head = grab_header(inode);
 	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
-	void *kbuf;
+	size_t count = iov_iter_count(iter);
+	char *kbuf;
 	ssize_t error;
 
 	if (IS_ERR(head))
@@ -569,32 +571,30 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *ubuf,
 	error = -ENOMEM;
 	if (count >= KMALLOC_MAX_SIZE)
 		goto out;
+	kbuf = kzalloc(count + 1, GFP_KERNEL);
+	if (!kbuf)
+		goto out;
 
 	if (write) {
-		kbuf = memdup_user_nul(ubuf, count);
-		if (IS_ERR(kbuf)) {
-			error = PTR_ERR(kbuf);
-			goto out;
-		}
-	} else {
-		kbuf = kzalloc(count, GFP_KERNEL);
-		if (!kbuf)
-			goto out;
+		error = -EFAULT;
+		if (!copy_from_iter_full(kbuf, count, iter))
+			goto out_free_buf;
+		kbuf[count] = '\0';
 	}
 
 	error = BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, &kbuf, &count,
-					   ppos);
+					   &iocb->ki_pos);
 	if (error)
 		goto out_free_buf;
 
 	/* careful: calling conventions are nasty here */
-	error = table->proc_handler(table, write, kbuf, &count, ppos);
+	error = table->proc_handler(table, write, kbuf, &count, &iocb->ki_pos);
 	if (error)
 		goto out_free_buf;
 
 	if (!write) {
 		error = -EFAULT;
-		if (copy_to_user(ubuf, kbuf, count))
+		if (copy_to_iter(kbuf, count, iter) < count)
 			goto out_free_buf;
 	}
 
@@ -607,16 +607,14 @@ out:
 	return error;
 }
 
-static ssize_t proc_sys_read(struct file *filp, char __user *buf,
-				size_t count, loff_t *ppos)
+static ssize_t proc_sys_read(struct kiocb *iocb, struct iov_iter *iter)
 {
-	return proc_sys_call_handler(filp, (void __user *)buf, count, ppos, 0);
+	return proc_sys_call_handler(iocb, iter, 0);
 }
 
-static ssize_t proc_sys_write(struct file *filp, const char __user *buf,
-				size_t count, loff_t *ppos)
+static ssize_t proc_sys_write(struct kiocb *iocb, struct iov_iter *iter)
 {
-	return proc_sys_call_handler(filp, (void __user *)buf, count, ppos, 1);
+	return proc_sys_call_handler(iocb, iter, 1);
 }
 
 static int proc_sys_open(struct inode *inode, struct file *filp)
@@ -853,8 +851,10 @@ static int proc_sys_getattr(const struct path *path, struct kstat *stat,
 static const struct file_operations proc_sys_file_operations = {
 	.open		= proc_sys_open,
 	.poll		= proc_sys_poll,
-	.read		= proc_sys_read,
-	.write		= proc_sys_write,
+	.read_iter	= proc_sys_read,
+	.write_iter	= proc_sys_write,
+	.splice_read	= generic_file_splice_read,
+	.splice_write	= iter_file_splice_write,
 	.llseek		= default_llseek,
 };
 
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 64f367044e25..82b26a1386d8 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -136,7 +136,7 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
 
 int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 				   struct ctl_table *table, int write,
-				   void **buf, size_t *pcount, loff_t *ppos,
+				   char **buf, size_t *pcount, loff_t *ppos,
 				   enum bpf_attach_type type);
 
 int __cgroup_bpf_run_filter_setsockopt(struct sock *sock, int *level,
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 83ff127ef7ae..226299352a76 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1226,7 +1226,7 @@ const struct bpf_verifier_ops cg_dev_verifier_ops = {
  */
 int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 				   struct ctl_table *table, int write,
-				   void **buf, size_t *pcount, loff_t *ppos,
+				   char **buf, size_t *pcount, loff_t *ppos,
 				   enum bpf_attach_type type)
 {
 	struct bpf_sysctl_kern ctx = {
-- 
cgit v1.2.3


From 36e2c7421f02a22f71c9283e55fdb672a9eb58e7 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 3 Sep 2020 16:22:34 +0200
Subject: fs: don't allow splice read/write without explicit ops

default_file_splice_write is the last piece of generic code that uses
set_fs to make the uaccess routines operate on kernel pointers.  It
implements a "fallback loop" for splicing from files that do not actually
provide a proper splice_read method.  The usual file systems and other
high bandwidth instances all provide a ->splice_read, so this just removes
support for various device drivers and procfs/debugfs files.  If splice
support for any of those turns out to be important it can be added back
by switching them to the iter ops and using generic_file_splice_read.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/read_write.c    |   2 +-
 fs/splice.c        | 130 ++++++-----------------------------------------------
 include/linux/fs.h |   2 -
 3 files changed, 15 insertions(+), 119 deletions(-)

(limited to 'include/linux')

diff --git a/fs/read_write.c b/fs/read_write.c
index 702c4301d9eb..8c61f67453e3 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1077,7 +1077,7 @@ ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos,
 }
 EXPORT_SYMBOL(vfs_iter_write);
 
-ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
+static ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
 		  unsigned long vlen, loff_t *pos, rwf_t flags)
 {
 	struct iovec iovstack[UIO_FASTIOV];
diff --git a/fs/splice.c b/fs/splice.c
index d7c8a7c4db07..412df7b48f9e 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -342,89 +342,6 @@ const struct pipe_buf_operations nosteal_pipe_buf_ops = {
 };
 EXPORT_SYMBOL(nosteal_pipe_buf_ops);
 
-static ssize_t kernel_readv(struct file *file, const struct kvec *vec,
-			    unsigned long vlen, loff_t offset)
-{
-	mm_segment_t old_fs;
-	loff_t pos = offset;
-	ssize_t res;
-
-	old_fs = get_fs();
-	set_fs(KERNEL_DS);
-	/* The cast to a user pointer is valid due to the set_fs() */
-	res = vfs_readv(file, (const struct iovec __user *)vec, vlen, &pos, 0);
-	set_fs(old_fs);
-
-	return res;
-}
-
-static ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
-				 struct pipe_inode_info *pipe, size_t len,
-				 unsigned int flags)
-{
-	struct kvec *vec, __vec[PIPE_DEF_BUFFERS];
-	struct iov_iter to;
-	struct page **pages;
-	unsigned int nr_pages;
-	unsigned int mask;
-	size_t offset, base, copied = 0;
-	ssize_t res;
-	int i;
-
-	if (pipe_full(pipe->head, pipe->tail, pipe->max_usage))
-		return -EAGAIN;
-
-	/*
-	 * Try to keep page boundaries matching to source pagecache ones -
-	 * it probably won't be much help, but...
-	 */
-	offset = *ppos & ~PAGE_MASK;
-
-	iov_iter_pipe(&to, READ, pipe, len + offset);
-
-	res = iov_iter_get_pages_alloc(&to, &pages, len + offset, &base);
-	if (res <= 0)
-		return -ENOMEM;
-
-	nr_pages = DIV_ROUND_UP(res + base, PAGE_SIZE);
-
-	vec = __vec;
-	if (nr_pages > PIPE_DEF_BUFFERS) {
-		vec = kmalloc_array(nr_pages, sizeof(struct kvec), GFP_KERNEL);
-		if (unlikely(!vec)) {
-			res = -ENOMEM;
-			goto out;
-		}
-	}
-
-	mask = pipe->ring_size - 1;
-	pipe->bufs[to.head & mask].offset = offset;
-	pipe->bufs[to.head & mask].len -= offset;
-
-	for (i = 0; i < nr_pages; i++) {
-		size_t this_len = min_t(size_t, len, PAGE_SIZE - offset);
-		vec[i].iov_base = page_address(pages[i]) + offset;
-		vec[i].iov_len = this_len;
-		len -= this_len;
-		offset = 0;
-	}
-
-	res = kernel_readv(in, vec, nr_pages, *ppos);
-	if (res > 0) {
-		copied = res;
-		*ppos += res;
-	}
-
-	if (vec != __vec)
-		kfree(vec);
-out:
-	for (i = 0; i < nr_pages; i++)
-		put_page(pages[i]);
-	kvfree(pages);
-	iov_iter_advance(&to, copied);	/* truncates and discards */
-	return res;
-}
-
 /*
  * Send 'sd->len' bytes to socket from 'sd->file' at position 'sd->pos'
  * using sendpage(). Return the number of bytes sent.
@@ -788,33 +705,6 @@ done:
 
 EXPORT_SYMBOL(iter_file_splice_write);
 
-static int write_pipe_buf(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
-			  struct splice_desc *sd)
-{
-	int ret;
-	void *data;
-	loff_t tmp = sd->pos;
-
-	data = kmap(buf->page);
-	ret = __kernel_write(sd->u.file, data + buf->offset, sd->len, &tmp);
-	kunmap(buf->page);
-
-	return ret;
-}
-
-static ssize_t default_file_splice_write(struct pipe_inode_info *pipe,
-					 struct file *out, loff_t *ppos,
-					 size_t len, unsigned int flags)
-{
-	ssize_t ret;
-
-	ret = splice_from_pipe(pipe, out, ppos, len, flags, write_pipe_buf);
-	if (ret > 0)
-		*ppos += ret;
-
-	return ret;
-}
-
 /**
  * generic_splice_sendpage - splice data from a pipe to a socket
  * @pipe:	pipe to splice from
@@ -836,15 +726,23 @@ ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe, struct file *out,
 
 EXPORT_SYMBOL(generic_splice_sendpage);
 
+static int warn_unsupported(struct file *file, const char *op)
+{
+	pr_debug_ratelimited(
+		"splice %s not supported for file %pD4 (pid: %d comm: %.20s)\n",
+		op, file, current->pid, current->comm);
+	return -EINVAL;
+}
+
 /*
  * Attempt to initiate a splice from pipe to file.
  */
 static long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
 			   loff_t *ppos, size_t len, unsigned int flags)
 {
-	if (out->f_op->splice_write)
-		return out->f_op->splice_write(pipe, out, ppos, len, flags);
-	return default_file_splice_write(pipe, out, ppos, len, flags);
+	if (unlikely(!out->f_op->splice_write))
+		return warn_unsupported(out, "write");
+	return out->f_op->splice_write(pipe, out, ppos, len, flags);
 }
 
 /*
@@ -866,9 +764,9 @@ static long do_splice_to(struct file *in, loff_t *ppos,
 	if (unlikely(len > MAX_RW_COUNT))
 		len = MAX_RW_COUNT;
 
-	if (in->f_op->splice_read)
-		return in->f_op->splice_read(in, ppos, pipe, len, flags);
-	return default_file_splice_read(in, ppos, pipe, len, flags);
+	if (unlikely(!in->f_op->splice_read))
+		return warn_unsupported(in, "read");
+	return in->f_op->splice_read(in, ppos, pipe, len, flags);
 }
 
 /**
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e019ea2f1347..d33cc3e8ed41 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1894,8 +1894,6 @@ ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
 
 extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *);
 extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);
-extern ssize_t vfs_readv(struct file *, const struct iovec __user *,
-		unsigned long, loff_t *, rwf_t);
 extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *,
 				   loff_t, size_t, unsigned int);
 extern ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in,
-- 
cgit v1.2.3


From 5e6e9852d6f76e01b2e6803c74258afa5b432bc5 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 3 Sep 2020 16:22:35 +0200
Subject: uaccess: add infrastructure for kernel builds with set_fs()

Add a CONFIG_SET_FS option that is selected by architecturess that
implement set_fs, which is all of them initially.  If the option is not
set stubs for routines related to overriding the address space are
provided so that architectures can start to opt out of providing set_fs.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/Kconfig            |  3 +++
 arch/alpha/Kconfig      |  1 +
 arch/arc/Kconfig        |  1 +
 arch/arm/Kconfig        |  1 +
 arch/arm64/Kconfig      |  1 +
 arch/c6x/Kconfig        |  1 +
 arch/csky/Kconfig       |  1 +
 arch/h8300/Kconfig      |  1 +
 arch/hexagon/Kconfig    |  1 +
 arch/ia64/Kconfig       |  1 +
 arch/m68k/Kconfig       |  1 +
 arch/microblaze/Kconfig |  1 +
 arch/mips/Kconfig       |  1 +
 arch/nds32/Kconfig      |  1 +
 arch/nios2/Kconfig      |  1 +
 arch/openrisc/Kconfig   |  1 +
 arch/parisc/Kconfig     |  1 +
 arch/powerpc/Kconfig    |  1 +
 arch/riscv/Kconfig      |  1 +
 arch/s390/Kconfig       |  1 +
 arch/sh/Kconfig         |  1 +
 arch/sparc/Kconfig      |  1 +
 arch/um/Kconfig         |  1 +
 arch/x86/Kconfig        |  1 +
 arch/xtensa/Kconfig     |  1 +
 include/linux/uaccess.h | 18 ++++++++++++++++++
 26 files changed, 45 insertions(+)

(limited to 'include/linux')

diff --git a/arch/Kconfig b/arch/Kconfig
index af14a567b493..3fab619a6aa5 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -24,6 +24,9 @@ config KEXEC_ELF
 config HAVE_IMA_KEXEC
 	bool
 
+config SET_FS
+	bool
+
 config HOTPLUG_SMT
 	bool
 
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index 9c5f06e8eb9b..d6e9fc7a7b19 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -39,6 +39,7 @@ config ALPHA
 	select OLD_SIGSUSPEND
 	select CPU_NO_EFFICIENT_FFS if !ALPHA_EV67
 	select MMU_GATHER_NO_RANGE
+	select SET_FS
 	help
 	  The Alpha is a 64-bit general-purpose processor designed and
 	  marketed by the Digital Equipment Corporation of blessed memory,
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index ba00c4e1e1c2..c49f5754a11e 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -48,6 +48,7 @@ config ARC
 	select PCI_SYSCALL if PCI
 	select PERF_USE_VMALLOC if ARC_CACHE_VIPT_ALIASING
 	select HAVE_ARCH_JUMP_LABEL if ISA_ARCV2 && !CPU_ENDIAN_BE32
+	select SET_FS
 
 config ARCH_HAS_CACHE_LINE_SIZE
 	def_bool y
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index e00d94b16658..87e1478a42dc 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -118,6 +118,7 @@ config ARM
 	select PCI_SYSCALL if PCI
 	select PERF_USE_VMALLOC
 	select RTC_LIB
+	select SET_FS
 	select SYS_SUPPORTS_APM_EMULATION
 	# Above selects are sorted alphabetically; please add new ones
 	# according to that.  Thanks.
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 6d232837cbee..fbd9e35bef09 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -192,6 +192,7 @@ config ARM64
 	select PCI_SYSCALL if PCI
 	select POWER_RESET
 	select POWER_SUPPLY
+	select SET_FS
 	select SPARSE_IRQ
 	select SWIOTLB
 	select SYSCTL_EXCEPTION_TRACE
diff --git a/arch/c6x/Kconfig b/arch/c6x/Kconfig
index 6444ebfd06a6..48d66bf0465d 100644
--- a/arch/c6x/Kconfig
+++ b/arch/c6x/Kconfig
@@ -22,6 +22,7 @@ config C6X
 	select GENERIC_CLOCKEVENTS
 	select MODULES_USE_ELF_RELA
 	select MMU_GATHER_NO_RANGE if MMU
+	select SET_FS
 
 config MMU
 	def_bool n
diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig
index 3d5afb5f5685..2836f6e76fdb 100644
--- a/arch/csky/Kconfig
+++ b/arch/csky/Kconfig
@@ -78,6 +78,7 @@ config CSKY
 	select PCI_DOMAINS_GENERIC if PCI
 	select PCI_SYSCALL if PCI
 	select PCI_MSI if PCI
+	select SET_FS
 
 config LOCKDEP_SUPPORT
 	def_bool y
diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig
index d11666d538fe..7945de067e9f 100644
--- a/arch/h8300/Kconfig
+++ b/arch/h8300/Kconfig
@@ -25,6 +25,7 @@ config H8300
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_HASH
 	select CPU_NO_EFFICIENT_FFS
+	select SET_FS
 	select UACCESS_MEMCPY
 
 config CPU_BIG_ENDIAN
diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig
index 667cfc511cf9..f2afabbadd43 100644
--- a/arch/hexagon/Kconfig
+++ b/arch/hexagon/Kconfig
@@ -31,6 +31,7 @@ config HEXAGON
 	select GENERIC_CLOCKEVENTS_BROADCAST
 	select MODULES_USE_ELF_RELA
 	select GENERIC_CPU_DEVICES
+	select SET_FS
 	help
 	  Qualcomm Hexagon is a processor architecture designed for high
 	  performance and low power across a wide variety of applications.
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 5b4ec80bf586..22a6853840e2 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -56,6 +56,7 @@ config IA64
 	select NEED_DMA_MAP_STATE
 	select NEED_SG_DMA_LENGTH
 	select NUMA if !FLATMEM
+	select SET_FS
 	default y
 	help
 	  The Itanium Processor Family is Intel's 64-bit successor to
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index 6f2f38d05772..dcf4ae8c9b21 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -32,6 +32,7 @@ config M68K
 	select OLD_SIGSUSPEND3
 	select OLD_SIGACTION
 	select MMU_GATHER_NO_RANGE if MMU
+	select SET_FS
 
 config CPU_BIG_ENDIAN
 	def_bool y
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index d262ac0c8714..7e3d4583abf3 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -46,6 +46,7 @@ config MICROBLAZE
 	select CPU_NO_EFFICIENT_FFS
 	select MMU_GATHER_NO_RANGE if MMU
 	select SPARSE_IRQ
+	select SET_FS
 
 # Endianness selection
 choice
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index c95fa3a2484c..fbc26391b588 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -87,6 +87,7 @@ config MIPS
 	select MODULES_USE_ELF_RELA if MODULES && 64BIT
 	select PERF_USE_VMALLOC
 	select RTC_LIB
+	select SET_FS
 	select SYSCTL_EXCEPTION_TRACE
 	select VIRT_TO_BUS
 
diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig
index e30298e99e1b..e8e541fd2267 100644
--- a/arch/nds32/Kconfig
+++ b/arch/nds32/Kconfig
@@ -48,6 +48,7 @@ config NDS32
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_DYNAMIC_FTRACE
+	select SET_FS
 	help
 	  Andes(nds32) Linux support.
 
diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig
index c6645141bb2a..c7c6ba6bec9d 100644
--- a/arch/nios2/Kconfig
+++ b/arch/nios2/Kconfig
@@ -27,6 +27,7 @@ config NIOS2
 	select USB_ARCH_HAS_HCD if USB_SUPPORT
 	select CPU_NO_EFFICIENT_FFS
 	select MMU_GATHER_NO_RANGE if MMU
+	select SET_FS
 
 config GENERIC_CSUM
 	def_bool y
diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index 7e94fe37cb2f..6233c6293180 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -39,6 +39,7 @@ config OPENRISC
 	select ARCH_WANT_FRAME_POINTERS
 	select GENERIC_IRQ_MULTI_HANDLER
 	select MMU_GATHER_NO_RANGE if MMU
+	select SET_FS
 
 config CPU_BIG_ENDIAN
 	def_bool y
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index 3b0f53dd70bc..be70af482b5a 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -63,6 +63,7 @@ config PARISC
 	select HAVE_FTRACE_MCOUNT_RECORD if HAVE_DYNAMIC_FTRACE
 	select HAVE_KPROBES_ON_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
+	select SET_FS
 
 	help
 	  The PA-RISC microprocessor is designed by Hewlett-Packard and used
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 1f48bbfb3ce9..3f09d6fdf894 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -249,6 +249,7 @@ config PPC
 	select PCI_SYSCALL			if PCI
 	select PPC_DAWR				if PPC64
 	select RTC_LIB
+	select SET_FS
 	select SPARSE_IRQ
 	select SYSCTL_EXCEPTION_TRACE
 	select THREAD_INFO_IN_TASK
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 7b5905529146..07d53044013e 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -86,6 +86,7 @@ config RISCV
 	select SPARSE_IRQ
 	select SYSCTL_EXCEPTION_TRACE
 	select THREAD_INFO_IN_TASK
+	select SET_FS
 
 config ARCH_MMAP_RND_BITS_MIN
 	default 18 if 64BIT
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 3d86e12e8e3c..fd81385a7787 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -185,6 +185,7 @@ config S390
 	select OLD_SIGSUSPEND3
 	select PCI_DOMAINS		if PCI
 	select PCI_MSI			if PCI
+	select SET_FS
 	select SPARSE_IRQ
 	select SYSCTL_EXCEPTION_TRACE
 	select THREAD_INFO_IN_TASK
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index d20927128fce..2bd1653f3b3f 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -71,6 +71,7 @@ config SUPERH
 	select PERF_EVENTS
 	select PERF_USE_VMALLOC
 	select RTC_LIB
+	select SET_FS
 	select SPARSE_IRQ
 	help
 	  The SuperH is a RISC processor targeted for use in embedded systems
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index efeff2c896a5..3e0cf0319a27 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -49,6 +49,7 @@ config SPARC
 	select LOCKDEP_SMALL if LOCKDEP
 	select NEED_DMA_MAP_STATE
 	select NEED_SG_DMA_LENGTH
+	select SET_FS
 
 config SPARC32
 	def_bool !64BIT
diff --git a/arch/um/Kconfig b/arch/um/Kconfig
index eb51fec75948..3aefcd815668 100644
--- a/arch/um/Kconfig
+++ b/arch/um/Kconfig
@@ -19,6 +19,7 @@ config UML
 	select GENERIC_CPU_DEVICES
 	select GENERIC_CLOCKEVENTS
 	select HAVE_GCC_PLUGINS
+	select SET_FS
 	select TTY # Needed for line.c
 
 config MMU
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 7101ac64bb20..f85c13355732 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -237,6 +237,7 @@ config X86
 	select HAVE_ARCH_KCSAN			if X86_64
 	select X86_FEATURE_NAMES		if PROC_FS
 	select PROC_PID_ARCH_STATUS		if PROC_FS
+	select SET_FS
 	imply IMA_SECURE_AND_OR_TRUSTED_BOOT    if EFI
 
 config INSTRUCTION_DECODER
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index e997e0119c02..94bad4d66b4b 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -41,6 +41,7 @@ config XTENSA
 	select IRQ_DOMAIN
 	select MODULES_USE_ELF_RELA
 	select PERF_USE_VMALLOC
+	select SET_FS
 	select VIRT_TO_BUS
 	help
 	  Xtensa processors are 32-bit RISC machines designed by Tensilica
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 94b285411659..70073c802b48 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -8,6 +8,7 @@
 
 #include <asm/uaccess.h>
 
+#ifdef CONFIG_SET_FS
 /*
  * Force the uaccess routines to be wired up for actual userspace access,
  * overriding any possible set_fs(KERNEL_DS) still lingering around.  Undone
@@ -25,6 +26,23 @@ static inline void force_uaccess_end(mm_segment_t oldfs)
 {
 	set_fs(oldfs);
 }
+#else /* CONFIG_SET_FS */
+typedef struct {
+	/* empty dummy */
+} mm_segment_t;
+
+#define uaccess_kernel()		(false)
+#define user_addr_max()			(TASK_SIZE_MAX)
+
+static inline mm_segment_t force_uaccess_begin(void)
+{
+	return (mm_segment_t) { };
+}
+
+static inline void force_uaccess_end(mm_segment_t oldfs)
+{
+}
+#endif /* CONFIG_SET_FS */
 
 /*
  * Architectures should provide two primitives (raw_copy_{to,from}_user())
-- 
cgit v1.2.3


From 7c69898b86b45842e1c2799df845e203c71a667e Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Wed, 9 Sep 2020 09:25:33 +0200
Subject: Revert "test_firmware: Test platform fw loading on non-EFI systems"

This reverts commit 18efb2f9e897ac65e7a1b2892f4a53e404534eba as it is
reported to break the build:
	https://lore.kernel.org/r/20200909154709.619fe9bb@canb.auug.org.au

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Fixes: 18efb2f9e897 ("test_firmware: Test platform fw loading on non-EFI systems")
Cc: stable@vger.kernel.org
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Scott Branden <scott.branden@broadcom.com>
Cc: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20200909154709.619fe9bb@canb.auug.org.au
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/efi/embedded-firmware.c | 21 +++++----------------
 drivers/firmware/efi/embedded-firmware.h | 21 ---------------------
 include/linux/efi_embedded_fw.h          | 13 +++++++++++++
 lib/test_firmware.c                      |  5 -----
 4 files changed, 18 insertions(+), 42 deletions(-)
 delete mode 100644 drivers/firmware/efi/embedded-firmware.h

(limited to 'include/linux')

diff --git a/drivers/firmware/efi/embedded-firmware.c b/drivers/firmware/efi/embedded-firmware.c
index f1330f55f7f4..e97a9c9d010c 100644
--- a/drivers/firmware/efi/embedded-firmware.c
+++ b/drivers/firmware/efi/embedded-firmware.c
@@ -14,22 +14,11 @@
 #include <linux/vmalloc.h>
 #include <crypto/sha.h>
 
-#include "embedded-firmware.h"
-
-#ifdef CONFIG_TEST_FIRMWARE
-# define EFI_EMBEDDED_FW_VISIBILITY
-#else
-# define EFI_EMBEDDED_FW_VISIBILITY static
-#endif
-
-EFI_EMBEDDED_FW_VISIBILITY LIST_HEAD(efi_embedded_fw_list);
-EFI_EMBEDDED_FW_VISIBILITY bool efi_embedded_fw_checked;
-
 /* Exported for use by lib/test_firmware.c only */
-#ifdef CONFIG_TEST_FIRMWARE
+LIST_HEAD(efi_embedded_fw_list);
 EXPORT_SYMBOL_GPL(efi_embedded_fw_list);
-EXPORT_SYMBOL_GPL(efi_embedded_fw_checked);
-#endif
+
+static bool checked_for_fw;
 
 static const struct dmi_system_id * const embedded_fw_table[] = {
 #ifdef CONFIG_TOUCHSCREEN_DMI
@@ -127,14 +116,14 @@ void __init efi_check_for_embedded_firmwares(void)
 		}
 	}
 
-	efi_embedded_fw_checked = true;
+	checked_for_fw = true;
 }
 
 int efi_get_embedded_fw(const char *name, const u8 **data, size_t *size)
 {
 	struct efi_embedded_fw *iter, *fw = NULL;
 
-	if (!efi_embedded_fw_checked) {
+	if (!checked_for_fw) {
 		pr_warn("Warning %s called while we did not check for embedded fw\n",
 			__func__);
 		return -ENOENT;
diff --git a/drivers/firmware/efi/embedded-firmware.h b/drivers/firmware/efi/embedded-firmware.h
deleted file mode 100644
index bb894eae0906..000000000000
--- a/drivers/firmware/efi/embedded-firmware.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _EFI_EMBEDDED_FW_INTERNAL_H_
-#define _EFI_EMBEDDED_FW_INTERNAL_H_
-
-/*
- * This struct and efi_embedded_fw_list are private to the efi-embedded fw
- * implementation they only in separate header for use by lib/test_firmware.c.
- */
-struct efi_embedded_fw {
-	struct list_head list;
-	const char *name;
-	const u8 *data;
-	size_t length;
-};
-
-#ifdef CONFIG_TEST_FIRMWARE
-extern struct list_head efi_embedded_fw_list;
-extern bool efi_embedded_fw_checked;
-#endif
-
-#endif /* _EFI_EMBEDDED_FW_INTERNAL_H_ */
diff --git a/include/linux/efi_embedded_fw.h b/include/linux/efi_embedded_fw.h
index 4ad5db9f5312..57eac5241303 100644
--- a/include/linux/efi_embedded_fw.h
+++ b/include/linux/efi_embedded_fw.h
@@ -7,6 +7,19 @@
 
 #define EFI_EMBEDDED_FW_PREFIX_LEN		8
 
+/*
+ * This struct and efi_embedded_fw_list are private to the efi-embedded fw
+ * implementation they are in this header for use by lib/test_firmware.c only!
+ */
+struct efi_embedded_fw {
+	struct list_head list;
+	const char *name;
+	const u8 *data;
+	size_t length;
+};
+
+extern struct list_head efi_embedded_fw_list;
+
 /**
  * struct efi_embedded_fw_desc - This struct is used by the EFI embedded-fw
  *                               code to search for embedded firmwares.
diff --git a/lib/test_firmware.c b/lib/test_firmware.c
index 62af792e151c..9fee2b93a8d1 100644
--- a/lib/test_firmware.c
+++ b/lib/test_firmware.c
@@ -489,7 +489,6 @@ out:
 static DEVICE_ATTR_WO(trigger_request);
 
 #ifdef CONFIG_EFI_EMBEDDED_FIRMWARE
-#include "../drivers/firmware/efi/embedded-firmware.h"
 static ssize_t trigger_request_platform_store(struct device *dev,
 					      struct device_attribute *attr,
 					      const char *buf, size_t count)
@@ -502,7 +501,6 @@ static ssize_t trigger_request_platform_store(struct device *dev,
 	};
 	struct efi_embedded_fw efi_embedded_fw;
 	const struct firmware *firmware = NULL;
-	bool saved_efi_embedded_fw_checked;
 	char *name;
 	int rc;
 
@@ -515,8 +513,6 @@ static ssize_t trigger_request_platform_store(struct device *dev,
 	efi_embedded_fw.data = (void *)test_data;
 	efi_embedded_fw.length = sizeof(test_data);
 	list_add(&efi_embedded_fw.list, &efi_embedded_fw_list);
-	saved_efi_embedded_fw_checked = efi_embedded_fw_checked;
-	efi_embedded_fw_checked = true;
 
 	pr_info("loading '%s'\n", name);
 	rc = firmware_request_platform(&firmware, name, dev);
@@ -534,7 +530,6 @@ static ssize_t trigger_request_platform_store(struct device *dev,
 	rc = count;
 
 out:
-	efi_embedded_fw_checked = saved_efi_embedded_fw_checked;
 	release_firmware(firmware);
 	list_del(&efi_embedded_fw.list);
 	kfree(name);
-- 
cgit v1.2.3


From f601e8f37c2c1c52f2923fffc48204a7f7dc023d Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Wed, 9 Sep 2020 09:37:40 +0200
Subject: Revert "driver core: Annotate dev_err_probe() with __must_check"

This reverts commit e1f82a0dcf388d98bcc7ad195c03bd812405e6b2 as it's
already starting to cause build warnings in linux-next for things that
are "obviously correct".

It's up to driver authors do "do the right thing" here with this
function, and if they don't want to call it as the last line of a
function, that's up to them, otherwise code that looks like:
	ret = dev_err_probe(..., ret, ...);
does look really "odd".

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Reported-by: Krzysztof Kozlowski <krzk@kernel.org>
Fixes: e1f82a0dcf38 ("driver core: Annotate dev_err_probe() with __must_check")
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/device.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/device.h b/include/linux/device.h
index 85d5c28bed93..7a0938cf8bd7 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -924,7 +924,7 @@ void device_links_supplier_sync_state_pause(void);
 void device_links_supplier_sync_state_resume(void);
 
 extern __printf(3, 4)
-int __must_check dev_err_probe(const struct device *dev, int err, const char *fmt, ...);
+int dev_err_probe(const struct device *dev, int err, const char *fmt, ...);
 
 /* Create alias, so I can be autoloaded. */
 #define MODULE_ALIAS_CHARDEV(major,minor) \
-- 
cgit v1.2.3


From 2a71593da34d473461f2f5c3dbb53b883596188a Mon Sep 17 00:00:00 2001
From: Alain Volmat <alain.volmat@st.com>
Date: Mon, 3 Aug 2020 07:17:55 +0200
Subject: i2c: smbus: add core function handling SMBus host-notify

SMBus Host-Notify protocol, from the adapter point of view
consist of receiving a message from a client, including the
client address and some other data.

It can be simply handled by creating a new slave device
and registering a callback performing the parsing of the
message received from the client.

This commit introduces two new core functions
  * i2c_new_slave_host_notify_device
  * i2c_free_slave_host_notify_device
that take care of registration of the new slave device and
callback and will call i2c_handle_smbus_host_notify once a
Host-Notify event is received.

Signed-off-by: Alain Volmat <alain.volmat@st.com>
Reviewed-by: Pierre-Yves MORDRET <pierre-yves.mordret@st.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/i2c-smbus.c   | 107 ++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/i2c-smbus.h |  12 ++++++
 2 files changed, 119 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/i2c/i2c-smbus.c b/drivers/i2c/i2c-smbus.c
index dc0108287ccf..d3d06e3b4f3b 100644
--- a/drivers/i2c/i2c-smbus.c
+++ b/drivers/i2c/i2c-smbus.c
@@ -197,6 +197,113 @@ EXPORT_SYMBOL_GPL(i2c_handle_smbus_alert);
 
 module_i2c_driver(smbalert_driver);
 
+#if IS_ENABLED(CONFIG_I2C_SLAVE)
+#define SMBUS_HOST_NOTIFY_LEN	3
+struct i2c_slave_host_notify_status {
+	u8 index;
+	u8 addr;
+};
+
+static int i2c_slave_host_notify_cb(struct i2c_client *client,
+				    enum i2c_slave_event event, u8 *val)
+{
+	struct i2c_slave_host_notify_status *status = client->dev.platform_data;
+
+	switch (event) {
+	case I2C_SLAVE_WRITE_RECEIVED:
+		/* We only retrieve the first byte received (addr)
+		 * since there is currently no support to retrieve the data
+		 * parameter from the client.
+		 */
+		if (status->index == 0)
+			status->addr = *val;
+		if (status->index < U8_MAX)
+			status->index++;
+		break;
+	case I2C_SLAVE_STOP:
+		if (status->index == SMBUS_HOST_NOTIFY_LEN)
+			i2c_handle_smbus_host_notify(client->adapter,
+						     status->addr);
+		fallthrough;
+	case I2C_SLAVE_WRITE_REQUESTED:
+		status->index = 0;
+		break;
+	case I2C_SLAVE_READ_REQUESTED:
+	case I2C_SLAVE_READ_PROCESSED:
+		*val = 0xff;
+		break;
+	}
+
+	return 0;
+}
+
+/**
+ * i2c_new_slave_host_notify_device - get a client for SMBus host-notify support
+ * @adapter: the target adapter
+ * Context: can sleep
+ *
+ * Setup handling of the SMBus host-notify protocol on a given I2C bus segment.
+ *
+ * Handling is done by creating a device and its callback and handling data
+ * received via the SMBus host-notify address (0x8)
+ *
+ * This returns the client, which should be ultimately freed using
+ * i2c_free_slave_host_notify_device(); or an ERRPTR to indicate an error.
+ */
+struct i2c_client *i2c_new_slave_host_notify_device(struct i2c_adapter *adapter)
+{
+	struct i2c_board_info host_notify_board_info = {
+		I2C_BOARD_INFO("smbus_host_notify", 0x08),
+		.flags  = I2C_CLIENT_SLAVE,
+	};
+	struct i2c_slave_host_notify_status *status;
+	struct i2c_client *client;
+	int ret;
+
+	status = kzalloc(sizeof(struct i2c_slave_host_notify_status),
+			 GFP_KERNEL);
+	if (!status)
+		return ERR_PTR(-ENOMEM);
+
+	host_notify_board_info.platform_data = status;
+
+	client = i2c_new_client_device(adapter, &host_notify_board_info);
+	if (IS_ERR(client)) {
+		kfree(status);
+		return client;
+	}
+
+	ret = i2c_slave_register(client, i2c_slave_host_notify_cb);
+	if (ret) {
+		i2c_unregister_device(client);
+		kfree(status);
+		return ERR_PTR(ret);
+	}
+
+	return client;
+}
+EXPORT_SYMBOL_GPL(i2c_new_slave_host_notify_device);
+
+/**
+ * i2c_free_slave_host_notify_device - free the client for SMBus host-notify
+ * support
+ * @client: the client to free
+ * Context: can sleep
+ *
+ * Free the i2c_client allocated via i2c_new_slave_host_notify_device
+ */
+void i2c_free_slave_host_notify_device(struct i2c_client *client)
+{
+	if (IS_ERR_OR_NULL(client))
+		return;
+
+	i2c_slave_unregister(client);
+	kfree(client->dev.platform_data);
+	i2c_unregister_device(client);
+}
+EXPORT_SYMBOL_GPL(i2c_free_slave_host_notify_device);
+#endif
+
 /*
  * SPD is not part of SMBus but we include it here for convenience as the
  * target systems are the same.
diff --git a/include/linux/i2c-smbus.h b/include/linux/i2c-smbus.h
index 1e4e0de4ef8b..1ef421818d3a 100644
--- a/include/linux/i2c-smbus.h
+++ b/include/linux/i2c-smbus.h
@@ -38,6 +38,18 @@ static inline int of_i2c_setup_smbus_alert(struct i2c_adapter *adap)
 	return 0;
 }
 #endif
+#if IS_ENABLED(CONFIG_I2C_SMBUS) && IS_ENABLED(CONFIG_I2C_SLAVE)
+struct i2c_client *i2c_new_slave_host_notify_device(struct i2c_adapter *adapter);
+void i2c_free_slave_host_notify_device(struct i2c_client *client);
+#else
+static inline struct i2c_client *i2c_new_slave_host_notify_device(struct i2c_adapter *adapter)
+{
+	return ERR_PTR(-ENOSYS);
+}
+static inline void i2c_free_slave_host_notify_device(struct i2c_client *client)
+{
+}
+#endif
 
 #if IS_ENABLED(CONFIG_I2C_SMBUS) && IS_ENABLED(CONFIG_DMI)
 void i2c_register_spd(struct i2c_adapter *adap);
-- 
cgit v1.2.3


From d284c16f84c9f8facdde25c9c077cfdcb66163d5 Mon Sep 17 00:00:00 2001
From: dillon min <dillon.minfei@gmail.com>
Date: Thu, 3 Sep 2020 15:30:22 +0800
Subject: gpio: tc35894: Disable Direct KBD interrupts to enable gpio irq

On tc35894, have to disable direct keypad interrupts to make
it as general purpose interrupts functionality work.
if not, after chip reset, IRQST(0x91) will always 0x20,
IRQN always low level, can't be clear.

Configure DIRECTx to enable general purpose gpio mode,
else read GPIOMISx register always zero in irq routine.

verified on tc35894, need more test on other tc3589x.

Signed-off-by: dillon min <dillon.minfei@gmail.com>
Acked-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
---
 drivers/gpio/gpio-tc3589x.c | 18 ++++++++++++++++--
 include/linux/mfd/tc3589x.h |  6 ++++++
 2 files changed, 22 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpio/gpio-tc3589x.c b/drivers/gpio/gpio-tc3589x.c
index 58b0da9eb76f..79d285b845dc 100644
--- a/drivers/gpio/gpio-tc3589x.c
+++ b/drivers/gpio/gpio-tc3589x.c
@@ -19,9 +19,9 @@
  * These registers are modified under the irq bus lock and cached to avoid
  * unnecessary writes in bus_sync_unlock.
  */
-enum { REG_IBE, REG_IEV, REG_IS, REG_IE };
+enum { REG_IBE, REG_IEV, REG_IS, REG_IE, REG_DIRECT };
 
-#define CACHE_NR_REGS	4
+#define CACHE_NR_REGS	5
 #define CACHE_NR_BANKS	3
 
 struct tc3589x_gpio {
@@ -200,6 +200,7 @@ static void tc3589x_gpio_irq_sync_unlock(struct irq_data *d)
 		[REG_IEV]	= TC3589x_GPIOIEV0,
 		[REG_IS]	= TC3589x_GPIOIS0,
 		[REG_IE]	= TC3589x_GPIOIE0,
+		[REG_DIRECT]	= TC3589x_DIRECT0,
 	};
 	int i, j;
 
@@ -228,6 +229,7 @@ static void tc3589x_gpio_irq_mask(struct irq_data *d)
 	int mask = BIT(offset % 8);
 
 	tc3589x_gpio->regs[REG_IE][regoffset] &= ~mask;
+	tc3589x_gpio->regs[REG_DIRECT][regoffset] |= mask;
 }
 
 static void tc3589x_gpio_irq_unmask(struct irq_data *d)
@@ -239,6 +241,7 @@ static void tc3589x_gpio_irq_unmask(struct irq_data *d)
 	int mask = BIT(offset % 8);
 
 	tc3589x_gpio->regs[REG_IE][regoffset] |= mask;
+	tc3589x_gpio->regs[REG_DIRECT][regoffset] &= ~mask;
 }
 
 static struct irq_chip tc3589x_gpio_irq_chip = {
@@ -334,6 +337,17 @@ static int tc3589x_gpio_probe(struct platform_device *pdev)
 	if (ret < 0)
 		return ret;
 
+	 /* For tc35894, have to disable Direct KBD interrupts,
+	  * else IRQST will always be 0x20, IRQN low level, can't
+	  * clear the irq status.
+	  * TODO: need more test on other tc3589x chip.
+	  *
+	  */
+	ret = tc3589x_reg_write(tc3589x, TC3589x_DKBDMSK,
+			TC3589x_DKBDMSK_ELINT | TC3589x_DKBDMSK_EINT);
+	if (ret < 0)
+		return ret;
+
 	ret = devm_request_threaded_irq(&pdev->dev,
 					irq, NULL, tc3589x_gpio_irq,
 					IRQF_ONESHOT, "tc3589x-gpio",
diff --git a/include/linux/mfd/tc3589x.h b/include/linux/mfd/tc3589x.h
index bb2b19599761..b84955410e03 100644
--- a/include/linux/mfd/tc3589x.h
+++ b/include/linux/mfd/tc3589x.h
@@ -19,6 +19,9 @@ enum tx3589x_block {
 #define TC3589x_RSTCTRL_KBDRST	(1 << 1)
 #define TC3589x_RSTCTRL_GPIRST	(1 << 0)
 
+#define TC3589x_DKBDMSK_ELINT	(1 << 1)
+#define TC3589x_DKBDMSK_EINT	(1 << 0)
+
 /* Keyboard Configuration Registers */
 #define TC3589x_KBDSETTLE_REG   0x01
 #define TC3589x_KBDBOUNCE       0x02
@@ -101,6 +104,9 @@ enum tx3589x_block {
 #define TC3589x_GPIOODM2	0xE4
 #define TC3589x_GPIOODE2	0xE5
 
+#define TC3589x_DIRECT0		0xEC
+#define TC3589x_DKBDMSK		0xF3
+
 #define TC3589x_INT_GPIIRQ	0
 #define TC3589x_INT_TI0IRQ	1
 #define TC3589x_INT_TI1IRQ	2
-- 
cgit v1.2.3


From 2acd30b9f6032c6cbefc5e255c17ebbb0718e56a Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Tue, 8 Sep 2020 21:45:15 +0800
Subject: ASoC/soundwire: bus: use property to set interrupt masks

Add a slave-level property and program the SCP_INT1_MASK as desired by
the codec driver. Since there is no DisCo property this has to be an
implementation-specific firmware property or hard-coded in the driver.

The only functionality change is that implementation-defined
interrupts are no longer set for amplifiers - those interrupts are
typically for jack detection or acoustic event detection/hotwording.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Tested-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Reviewed-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Acked-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20200908134521.6781-2-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/bus.c         | 12 ++++++------
 include/linux/soundwire/sdw.h   |  2 ++
 sound/soc/codecs/max98373-sdw.c |  3 +++
 sound/soc/codecs/rt1308-sdw.c   |  2 ++
 sound/soc/codecs/rt5682-sdw.c   |  4 ++++
 sound/soc/codecs/rt700-sdw.c    |  4 ++++
 sound/soc/codecs/rt711-sdw.c    |  4 ++++
 sound/soc/codecs/rt715-sdw.c    |  4 ++++
 sound/soc/codecs/wsa881x.c      |  1 +
 9 files changed, 30 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c
index d808f0256ba0..9f4cc24ccea3 100644
--- a/drivers/soundwire/bus.c
+++ b/drivers/soundwire/bus.c
@@ -1184,13 +1184,13 @@ static int sdw_initialize_slave(struct sdw_slave *slave)
 		return ret;
 
 	/*
-	 * Set bus clash, parity and SCP implementation
-	 * defined interrupt mask
-	 * TODO: Read implementation defined interrupt mask
-	 * from Slave property
+	 * Set SCP_INT1_MASK register, typically bus clash and
+	 * implementation-defined interrupt mask. The Parity detection
+	 * may not always be correct on startup so its use is
+	 * device-dependent, it might e.g. only be enabled in
+	 * steady-state after a couple of frames.
 	 */
-	val = SDW_SCP_INT1_IMPL_DEF | SDW_SCP_INT1_BUS_CLASH |
-					SDW_SCP_INT1_PARITY;
+	val = slave->prop.scp_int1_mask;
 
 	/* Enable SCP interrupts */
 	ret = sdw_update(slave, SDW_SCP_INTMASK1, val, val);
diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 1e9010c139f0..9d94cdf6346f 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -357,6 +357,7 @@ struct sdw_dpn_prop {
  * @dp0_prop: Data Port 0 properties
  * @src_dpn_prop: Source Data Port N properties
  * @sink_dpn_prop: Sink Data Port N properties
+ * @scp_int1_mask: SCP_INT1_MASK desired settings
  */
 struct sdw_slave_prop {
 	u32 mipi_revision;
@@ -378,6 +379,7 @@ struct sdw_slave_prop {
 	struct sdw_dp0_prop *dp0_prop;
 	struct sdw_dpn_prop *src_dpn_prop;
 	struct sdw_dpn_prop *sink_dpn_prop;
+	u8 scp_int1_mask;
 };
 
 /**
diff --git a/sound/soc/codecs/max98373-sdw.c b/sound/soc/codecs/max98373-sdw.c
index a3ec92775ea7..76ddde509a08 100644
--- a/sound/soc/codecs/max98373-sdw.c
+++ b/sound/soc/codecs/max98373-sdw.c
@@ -15,6 +15,7 @@
 #include <linux/of.h>
 #include <linux/soundwire/sdw.h>
 #include <linux/soundwire/sdw_type.h>
+#include <linux/soundwire/sdw_registers.h>
 #include "max98373.h"
 #include "max98373-sdw.h"
 
@@ -287,6 +288,8 @@ static int max98373_read_prop(struct sdw_slave *slave)
 	unsigned long addr;
 	struct sdw_dpn_prop *dpn;
 
+	prop->scp_int1_mask = SDW_SCP_INT1_BUS_CLASH | SDW_SCP_INT1_PARITY;
+
 	/* BITMAP: 00001000  Dataport 3 is active */
 	prop->source_ports = BIT(3);
 	/* BITMAP: 00000010  Dataport 1 is active */
diff --git a/sound/soc/codecs/rt1308-sdw.c b/sound/soc/codecs/rt1308-sdw.c
index 09c69dbab12a..e02b325240df 100644
--- a/sound/soc/codecs/rt1308-sdw.c
+++ b/sound/soc/codecs/rt1308-sdw.c
@@ -123,6 +123,8 @@ static int rt1308_read_prop(struct sdw_slave *slave)
 	unsigned long addr;
 	struct sdw_dpn_prop *dpn;
 
+	prop->scp_int1_mask = SDW_SCP_INT1_BUS_CLASH | SDW_SCP_INT1_PARITY;
+
 	prop->paging_support = true;
 
 	/* first we need to allocate memory for set bits in port lists */
diff --git a/sound/soc/codecs/rt5682-sdw.c b/sound/soc/codecs/rt5682-sdw.c
index b7c97aba7f17..8d4ea46bc6b5 100644
--- a/sound/soc/codecs/rt5682-sdw.c
+++ b/sound/soc/codecs/rt5682-sdw.c
@@ -19,6 +19,7 @@
 #include <linux/mutex.h>
 #include <linux/soundwire/sdw.h>
 #include <linux/soundwire/sdw_type.h>
+#include <linux/soundwire/sdw_registers.h>
 #include <sound/core.h>
 #include <sound/pcm.h>
 #include <sound/pcm_params.h>
@@ -542,6 +543,9 @@ static int rt5682_read_prop(struct sdw_slave *slave)
 	unsigned long addr;
 	struct sdw_dpn_prop *dpn;
 
+	prop->scp_int1_mask = SDW_SCP_INT1_IMPL_DEF | SDW_SCP_INT1_BUS_CLASH |
+		SDW_SCP_INT1_PARITY;
+
 	prop->paging_support = false;
 
 	/* first we need to allocate memory for set bits in port lists */
diff --git a/sound/soc/codecs/rt700-sdw.c b/sound/soc/codecs/rt700-sdw.c
index b19fbcc12c69..8d9678d1f3c7 100644
--- a/sound/soc/codecs/rt700-sdw.c
+++ b/sound/soc/codecs/rt700-sdw.c
@@ -11,6 +11,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/soundwire/sdw.h>
 #include <linux/soundwire/sdw_type.h>
+#include <linux/soundwire/sdw_registers.h>
 #include <linux/module.h>
 #include <linux/regmap.h>
 #include <sound/soc.h>
@@ -338,6 +339,9 @@ static int rt700_read_prop(struct sdw_slave *slave)
 	unsigned long addr;
 	struct sdw_dpn_prop *dpn;
 
+	prop->scp_int1_mask = SDW_SCP_INT1_IMPL_DEF | SDW_SCP_INT1_BUS_CLASH |
+		SDW_SCP_INT1_PARITY;
+
 	prop->paging_support = false;
 
 	/* first we need to allocate memory for set bits in port lists */
diff --git a/sound/soc/codecs/rt711-sdw.c b/sound/soc/codecs/rt711-sdw.c
index dc4a2b482462..d4b3d7716cac 100644
--- a/sound/soc/codecs/rt711-sdw.c
+++ b/sound/soc/codecs/rt711-sdw.c
@@ -11,6 +11,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/soundwire/sdw.h>
 #include <linux/soundwire/sdw_type.h>
+#include <linux/soundwire/sdw_registers.h>
 #include <linux/module.h>
 #include <linux/regmap.h>
 #include <sound/soc.h>
@@ -342,6 +343,9 @@ static int rt711_read_prop(struct sdw_slave *slave)
 	unsigned long addr;
 	struct sdw_dpn_prop *dpn;
 
+	prop->scp_int1_mask = SDW_SCP_INT1_IMPL_DEF | SDW_SCP_INT1_BUS_CLASH |
+		SDW_SCP_INT1_PARITY;
+
 	prop->paging_support = false;
 
 	/* first we need to allocate memory for set bits in port lists */
diff --git a/sound/soc/codecs/rt715-sdw.c b/sound/soc/codecs/rt715-sdw.c
index d8ed07305ffc..0e5c75f85926 100644
--- a/sound/soc/codecs/rt715-sdw.c
+++ b/sound/soc/codecs/rt715-sdw.c
@@ -12,6 +12,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/soundwire/sdw.h>
 #include <linux/soundwire/sdw_type.h>
+#include <linux/soundwire/sdw_registers.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/regmap.h>
@@ -436,6 +437,9 @@ static int rt715_read_prop(struct sdw_slave *slave)
 	unsigned long addr;
 	struct sdw_dpn_prop *dpn;
 
+	prop->scp_int1_mask = SDW_SCP_INT1_IMPL_DEF | SDW_SCP_INT1_BUS_CLASH |
+		SDW_SCP_INT1_PARITY;
+
 	prop->paging_support = false;
 
 	/* first we need to allocate memory for set bits in port lists */
diff --git a/sound/soc/codecs/wsa881x.c b/sound/soc/codecs/wsa881x.c
index d39d479e2378..68e774e69c85 100644
--- a/sound/soc/codecs/wsa881x.c
+++ b/sound/soc/codecs/wsa881x.c
@@ -1112,6 +1112,7 @@ static int wsa881x_probe(struct sdw_slave *pdev,
 	wsa881x->sconfig.type = SDW_STREAM_PDM;
 	pdev->prop.sink_ports = GENMASK(WSA881X_MAX_SWR_PORTS, 0);
 	pdev->prop.sink_dpn_prop = wsa_sink_dpn_prop;
+	pdev->prop.scp_int1_mask = SDW_SCP_INT1_BUS_CLASH | SDW_SCP_INT1_PARITY;
 	gpiod_direction_output(wsa881x->sd_n, 1);
 
 	wsa881x->regmap = devm_regmap_init_sdw(pdev, &wsa881x_regmap_config);
-- 
cgit v1.2.3


From c2819e196b3cc1901a4612f72e66da4821966a5e Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Tue, 8 Sep 2020 21:45:17 +0800
Subject: soundwire: slave: add first_interrupt_done status

Some Slaves report incorrect information in their interrupt status
registers after a master/bus reset, track the initial interrupt
handling so that quirks can be introduced to filter out incorrect
information while keeping interrupts enabled in steady state.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Link: https://lore.kernel.org/r/20200908134521.6781-4-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/bus.c       | 7 ++++++-
 drivers/soundwire/slave.c     | 1 +
 include/linux/soundwire/sdw.h | 3 +++
 3 files changed, 10 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c
index 029818b1f568..30b0bed16630 100644
--- a/drivers/soundwire/bus.c
+++ b/drivers/soundwire/bus.c
@@ -1472,6 +1472,9 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave)
 			goto io_err;
 		}
 
+		/* at this point all initial interrupt sources were handled */
+		slave->first_interrupt_done = true;
+
 		/*
 		 * Read status again to ensure no new interrupts arrived
 		 * while servicing interrupts.
@@ -1674,8 +1677,10 @@ void sdw_clear_slave_status(struct sdw_bus *bus, u32 request)
 		if (!slave)
 			continue;
 
-		if (slave->status != SDW_SLAVE_UNATTACHED)
+		if (slave->status != SDW_SLAVE_UNATTACHED) {
 			sdw_modify_slave_status(slave, SDW_SLAVE_UNATTACHED);
+			slave->first_interrupt_done = false;
+		}
 
 		/* keep track of request, used in pm_runtime resume */
 		slave->unattach_request = request;
diff --git a/drivers/soundwire/slave.c b/drivers/soundwire/slave.c
index 2191dd6e7aa4..4a250d33de5d 100644
--- a/drivers/soundwire/slave.c
+++ b/drivers/soundwire/slave.c
@@ -58,6 +58,7 @@ static int sdw_slave_add(struct sdw_bus *bus,
 	slave->dev_num = 0;
 	init_completion(&slave->probe_complete);
 	slave->probed = false;
+	slave->first_interrupt_done = false;
 
 	for (i = 0; i < SDW_MAX_PORTS; i++)
 		init_completion(&slave->port_ready[i]);
diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 9d94cdf6346f..2b93a8ef7fad 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -616,6 +616,8 @@ struct sdw_slave_ops {
  * between the Master suspending and the codec resuming, and make sure that
  * when the Master triggered a reset the Slave is properly enumerated and
  * initialized
+ * @first_interrupt_done: status flag tracking if the interrupt handling
+ * for a Slave happens for the first time after enumeration
  */
 struct sdw_slave {
 	struct sdw_slave_id id;
@@ -637,6 +639,7 @@ struct sdw_slave {
 	struct completion enumeration_complete;
 	struct completion initialization_complete;
 	u32 unattach_request;
+	bool first_interrupt_done;
 };
 
 #define dev_to_sdw_dev(_dev) container_of(_dev, struct sdw_slave, dev)
-- 
cgit v1.2.3


From 4724f12c1315efa79a0cbf74dfb0c9b98b1a4bff Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Tue, 8 Sep 2020 21:45:18 +0800
Subject: soundwire: bus: use quirk to filter out invalid parity errors

If a Slave device reports with a quirk that its initial parity check
may be incorrect, filter it but keep the parity checks active in
steady state.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Link: https://lore.kernel.org/r/20200908134521.6781-5-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/bus.c       | 8 +++++++-
 include/linux/soundwire/sdw.h | 4 ++++
 2 files changed, 11 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c
index 30b0bed16630..09185e5cfd70 100644
--- a/drivers/soundwire/bus.c
+++ b/drivers/soundwire/bus.c
@@ -1362,6 +1362,8 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave)
 	unsigned long port;
 	bool slave_notify = false;
 	u8 buf, buf2[2], _buf, _buf2[2];
+	bool parity_check;
+	bool parity_quirk;
 
 	sdw_modify_slave_status(slave, SDW_SLAVE_ALERT);
 
@@ -1394,7 +1396,11 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave)
 		 * interrupt
 		 */
 		if (buf & SDW_SCP_INT1_PARITY) {
-			if (slave->prop.scp_int1_mask & SDW_SCP_INT1_PARITY)
+			parity_check = slave->prop.scp_int1_mask & SDW_SCP_INT1_PARITY;
+			parity_quirk = !slave->first_interrupt_done &&
+				(slave->prop.quirks & SDW_SLAVE_QUIRKS_INVALID_INITIAL_PARITY);
+
+			if (parity_check && !parity_quirk)
 				dev_err(&slave->dev, "Parity error detected\n");
 			clear |= SDW_SCP_INT1_PARITY;
 		}
diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 2b93a8ef7fad..790823d2d33b 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -358,6 +358,7 @@ struct sdw_dpn_prop {
  * @src_dpn_prop: Source Data Port N properties
  * @sink_dpn_prop: Sink Data Port N properties
  * @scp_int1_mask: SCP_INT1_MASK desired settings
+ * @quirks: bitmask identifying deltas from the MIPI specification
  */
 struct sdw_slave_prop {
 	u32 mipi_revision;
@@ -380,8 +381,11 @@ struct sdw_slave_prop {
 	struct sdw_dpn_prop *src_dpn_prop;
 	struct sdw_dpn_prop *sink_dpn_prop;
 	u8 scp_int1_mask;
+	u32 quirks;
 };
 
+#define SDW_SLAVE_QUIRKS_INVALID_INITIAL_PARITY	BIT(0)
+
 /**
  * struct sdw_master_prop - Master properties
  * @revision: MIPI spec version of the implementation
-- 
cgit v1.2.3


From 5bfe37ca8ac8e9176bfd923d0a83802b7305d2f5 Mon Sep 17 00:00:00 2001
From: Sebastien Boeuf <sebastien.boeuf@intel.com>
Date: Wed, 19 Aug 2020 18:19:41 -0400
Subject: virtio: Add get_shm_region method

Virtio defines 'shared memory regions' that provide a continuously
shared region between the host and guest.

Provide a method to find a particular region on a device.

Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Cc: kvm@vger.kernel.org
Cc: virtualization@lists.linux-foundation.org
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 include/linux/virtio_config.h | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 8fe857e27ef3..4b8e38c5c4d8 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -11,6 +11,11 @@
 
 struct irq_affinity;
 
+struct virtio_shm_region {
+	u64 addr;
+	u64 len;
+};
+
 /**
  * virtio_config_ops - operations for configuring a virtio device
  * Note: Do not assume that a transport implements all of the operations
@@ -66,6 +71,7 @@ struct irq_affinity;
  *      the caller can then copy.
  * @set_vq_affinity: set the affinity for a virtqueue (optional).
  * @get_vq_affinity: get the affinity for a virtqueue (optional).
+ * @get_shm_region: get a shared memory region based on the index.
  */
 typedef void vq_callback_t(struct virtqueue *);
 struct virtio_config_ops {
@@ -89,6 +95,8 @@ struct virtio_config_ops {
 			       const struct cpumask *cpu_mask);
 	const struct cpumask *(*get_vq_affinity)(struct virtio_device *vdev,
 			int index);
+	bool (*get_shm_region)(struct virtio_device *vdev,
+			       struct virtio_shm_region *region, u8 id);
 };
 
 /* If driver didn't advertise the feature, it will never appear. */
@@ -251,6 +259,15 @@ int virtqueue_set_affinity(struct virtqueue *vq, const struct cpumask *cpu_mask)
 	return 0;
 }
 
+static inline
+bool virtio_get_shm_region(struct virtio_device *vdev,
+			   struct virtio_shm_region *region, u8 id)
+{
+	if (!vdev->config->get_shm_region)
+		return false;
+	return vdev->config->get_shm_region(vdev, region, id);
+}
+
 static inline bool virtio_is_little_endian(struct virtio_device *vdev)
 {
 	return virtio_has_feature(vdev, VIRTIO_F_VERSION_1) ||
-- 
cgit v1.2.3


From 80793c3471d90d4dc2b48deadb6413bdfe39500f Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Thu, 27 Aug 2020 13:40:39 +0200
Subject: seqlock: Introduce seqcount_latch_t

Latch sequence counters are a multiversion concurrency control mechanism
where the seqcount_t counter even/odd value is used to switch between
two copies of protected data. This allows the seqcount_t read path to
safely interrupt its write side critical section (e.g. from NMIs).

Initially, latch sequence counters were implemented as a single write
function above plain seqcount_t: raw_write_seqcount_latch(). The read
side was expected to use plain seqcount_t raw_read_seqcount().

A specialized latch read function, raw_read_seqcount_latch(), was later
added. It became the standardized way for latch read paths.  Due to the
dependent load, it has one read memory barrier less than the plain
seqcount_t raw_read_seqcount() API.

Only raw_write_seqcount_latch() and raw_read_seqcount_latch() should be
used with latch sequence counters. Having *unique* read and write path
APIs means that latch sequence counters are actually a data type of
their own -- just inappropriately overloading plain seqcount_t.

Introduce seqcount_latch_t. This adds type-safety and ensures that only
the correct latch-safe APIs are to be used.

Not to break bisection, let the latch APIs also accept plain seqcount_t
or seqcount_raw_spinlock_t. After converting all call sites to
seqcount_latch_t, only that new data type will be allowed.

References: 9b0fd802e8c0 ("seqcount: Add raw_write_seqcount_latch()")
References: 7fc26327b756 ("seqlock: Introduce raw_read_seqcount_latch()")
References: aadd6e5caaac ("time/sched_clock: Use raw_read_seqcount_latch()")
Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200827114044.11173-4-a.darwish@linutronix.de
---
 Documentation/locking/seqlock.rst |  18 +++++++
 include/linux/seqlock.h           | 104 ++++++++++++++++++++++++++------------
 2 files changed, 91 insertions(+), 31 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/locking/seqlock.rst b/Documentation/locking/seqlock.rst
index 62c5ad98c11c..a334b584f2b3 100644
--- a/Documentation/locking/seqlock.rst
+++ b/Documentation/locking/seqlock.rst
@@ -139,6 +139,24 @@ with the associated LOCKTYPE lock acquired.
 
 Read path: same as in :ref:`seqcount_t`.
 
+
+.. _seqcount_latch_t:
+
+Latch sequence counters (``seqcount_latch_t``)
+----------------------------------------------
+
+Latch sequence counters are a multiversion concurrency control mechanism
+where the embedded seqcount_t counter even/odd value is used to switch
+between two copies of protected data. This allows the sequence counter
+read path to safely interrupt its own write side critical section.
+
+Use seqcount_latch_t when the write side sections cannot be protected
+from interruption by readers. This is typically the case when the read
+side can be invoked from NMI handlers.
+
+Check `raw_write_seqcount_latch()` for more information.
+
+
 .. _seqlock_t:
 
 Sequential locks (``seqlock_t``)
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 300cbf312546..88b917d4ebde 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -587,34 +587,76 @@ static inline void write_seqcount_t_invalidate(seqcount_t *s)
 	kcsan_nestable_atomic_end();
 }
 
-/**
- * raw_read_seqcount_latch() - pick even/odd seqcount_t latch data copy
- * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+/*
+ * Latch sequence counters (seqcount_latch_t)
  *
- * Use seqcount_t latching to switch between two storage places protected
- * by a sequence counter. Doing so allows having interruptible, preemptible,
- * seqcount_t write side critical sections.
+ * A sequence counter variant where the counter even/odd value is used to
+ * switch between two copies of protected data. This allows the read path,
+ * typically NMIs, to safely interrupt the write side critical section.
  *
- * Check raw_write_seqcount_latch() for more details and a full reader and
- * writer usage example.
+ * As the write sections are fully preemptible, no special handling for
+ * PREEMPT_RT is needed.
+ */
+typedef struct {
+	seqcount_t seqcount;
+} seqcount_latch_t;
+
+/**
+ * SEQCNT_LATCH_ZERO() - static initializer for seqcount_latch_t
+ * @seq_name: Name of the seqcount_latch_t instance
+ */
+#define SEQCNT_LATCH_ZERO(seq_name) {					\
+	.seqcount		= SEQCNT_ZERO(seq_name.seqcount),	\
+}
+
+/**
+ * seqcount_latch_init() - runtime initializer for seqcount_latch_t
+ * @s: Pointer to the seqcount_latch_t instance
+ */
+static inline void seqcount_latch_init(seqcount_latch_t *s)
+{
+	seqcount_init(&s->seqcount);
+}
+
+/**
+ * raw_read_seqcount_latch() - pick even/odd latch data copy
+ * @s: Pointer to seqcount_t, seqcount_raw_spinlock_t, or seqcount_latch_t
+ *
+ * See raw_write_seqcount_latch() for details and a full reader/writer
+ * usage example.
  *
  * Return: sequence counter raw value. Use the lowest bit as an index for
- * picking which data copy to read. The full counter value must then be
- * checked with read_seqcount_retry().
+ * picking which data copy to read. The full counter must then be checked
+ * with read_seqcount_latch_retry().
  */
-#define raw_read_seqcount_latch(s)					\
-	raw_read_seqcount_t_latch(__seqcount_ptr(s))
+#define raw_read_seqcount_latch(s)						\
+({										\
+	/*									\
+	 * Pairs with the first smp_wmb() in raw_write_seqcount_latch().	\
+	 * Due to the dependent load, a full smp_rmb() is not needed.		\
+	 */									\
+	_Generic(*(s),								\
+		 seqcount_t:		  READ_ONCE(((seqcount_t *)s)->sequence),			\
+		 seqcount_raw_spinlock_t: READ_ONCE(((seqcount_raw_spinlock_t *)s)->seqcount.sequence),	\
+		 seqcount_latch_t:	  READ_ONCE(((seqcount_latch_t *)s)->seqcount.sequence));	\
+})
 
-static inline int raw_read_seqcount_t_latch(seqcount_t *s)
+/**
+ * read_seqcount_latch_retry() - end a seqcount_latch_t read section
+ * @s:		Pointer to seqcount_latch_t
+ * @start:	count, from raw_read_seqcount_latch()
+ *
+ * Return: true if a read section retry is required, else false
+ */
+static inline int
+read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start)
 {
-	/* Pairs with the first smp_wmb() in raw_write_seqcount_latch() */
-	int seq = READ_ONCE(s->sequence); /* ^^^ */
-	return seq;
+	return read_seqcount_retry(&s->seqcount, start);
 }
 
 /**
- * raw_write_seqcount_latch() - redirect readers to even/odd copy
- * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ * raw_write_seqcount_latch() - redirect latch readers to even/odd copy
+ * @s: Pointer to seqcount_t, seqcount_raw_spinlock_t, or seqcount_latch_t
  *
  * The latch technique is a multiversion concurrency control method that allows
  * queries during non-atomic modifications. If you can guarantee queries never
@@ -633,7 +675,7 @@ static inline int raw_read_seqcount_t_latch(seqcount_t *s)
  * The basic form is a data structure like::
  *
  *	struct latch_struct {
- *		seqcount_t		seq;
+ *		seqcount_latch_t	seq;
  *		struct data_struct	data[2];
  *	};
  *
@@ -643,13 +685,13 @@ static inline int raw_read_seqcount_t_latch(seqcount_t *s)
  *	void latch_modify(struct latch_struct *latch, ...)
  *	{
  *		smp_wmb();	// Ensure that the last data[1] update is visible
- *		latch->seq++;
+ *		latch->seq.sequence++;
  *		smp_wmb();	// Ensure that the seqcount update is visible
  *
  *		modify(latch->data[0], ...);
  *
  *		smp_wmb();	// Ensure that the data[0] update is visible
- *		latch->seq++;
+ *		latch->seq.sequence++;
  *		smp_wmb();	// Ensure that the seqcount update is visible
  *
  *		modify(latch->data[1], ...);
@@ -668,8 +710,8 @@ static inline int raw_read_seqcount_t_latch(seqcount_t *s)
  *			idx = seq & 0x01;
  *			entry = data_query(latch->data[idx], ...);
  *
- *		// read_seqcount_retry() includes needed smp_rmb()
- *		} while (read_seqcount_retry(&latch->seq, seq));
+ *		// This includes needed smp_rmb()
+ *		} while (read_seqcount_latch_retry(&latch->seq, seq));
  *
  *		return entry;
  *	}
@@ -693,14 +735,14 @@ static inline int raw_read_seqcount_t_latch(seqcount_t *s)
  *	When data is a dynamic data structure; one should use regular RCU
  *	patterns to manage the lifetimes of the objects within.
  */
-#define raw_write_seqcount_latch(s)					\
-	raw_write_seqcount_t_latch(__seqcount_ptr(s))
-
-static inline void raw_write_seqcount_t_latch(seqcount_t *s)
-{
-       smp_wmb();      /* prior stores before incrementing "sequence" */
-       s->sequence++;
-       smp_wmb();      /* increment "sequence" before following stores */
+#define raw_write_seqcount_latch(s)						\
+{										\
+       smp_wmb();      /* prior stores before incrementing "sequence" */	\
+       _Generic(*(s),								\
+		seqcount_t:		((seqcount_t *)s)->sequence++,		\
+		seqcount_raw_spinlock_t:((seqcount_raw_spinlock_t *)s)->seqcount.sequence++, \
+		seqcount_latch_t:	((seqcount_latch_t *)s)->seqcount.sequence++); \
+       smp_wmb();      /* increment "sequence" before following stores */	\
 }
 
 /*
-- 
cgit v1.2.3


From 24bf401cebfd630cc9e2c3746e43945e836626f9 Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Thu, 27 Aug 2020 13:40:43 +0200
Subject: rbtree_latch: Use seqcount_latch_t

Latch sequence counters have unique read and write APIs, and thus
seqcount_latch_t was recently introduced at seqlock.h.

Use that new data type instead of plain seqcount_t. This adds the
necessary type-safety and ensures that only latching-safe seqcount APIs
are to be used.

Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200827114044.11173-8-a.darwish@linutronix.de
---
 include/linux/rbtree_latch.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/rbtree_latch.h b/include/linux/rbtree_latch.h
index 7d012faa509a..3d1a9e716b80 100644
--- a/include/linux/rbtree_latch.h
+++ b/include/linux/rbtree_latch.h
@@ -42,8 +42,8 @@ struct latch_tree_node {
 };
 
 struct latch_tree_root {
-	seqcount_t	seq;
-	struct rb_root	tree[2];
+	seqcount_latch_t	seq;
+	struct rb_root		tree[2];
 };
 
 /**
@@ -206,7 +206,7 @@ latch_tree_find(void *key, struct latch_tree_root *root,
 	do {
 		seq = raw_read_seqcount_latch(&root->seq);
 		node = __lt_find(key, root, seq & 1, ops->comp);
-	} while (read_seqcount_retry(&root->seq, seq));
+	} while (read_seqcount_latch_retry(&root->seq, seq));
 
 	return node;
 }
-- 
cgit v1.2.3


From 0c9794c8b6781eb7dad8e19b78c5d4557790597a Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Thu, 27 Aug 2020 13:40:44 +0200
Subject: seqlock: seqcount latch APIs: Only allow seqcount_latch_t

All latch sequence counter call-sites have now been converted from plain
seqcount_t to the new seqcount_latch_t data type.

Enforce type-safety by modifying seqlock.h latch APIs to only accept
seqcount_latch_t.

Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200827114044.11173-9-a.darwish@linutronix.de
---
 include/linux/seqlock.h | 36 +++++++++++++++---------------------
 1 file changed, 15 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 88b917d4ebde..f2a7a467e998 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -620,7 +620,7 @@ static inline void seqcount_latch_init(seqcount_latch_t *s)
 
 /**
  * raw_read_seqcount_latch() - pick even/odd latch data copy
- * @s: Pointer to seqcount_t, seqcount_raw_spinlock_t, or seqcount_latch_t
+ * @s: Pointer to seqcount_latch_t
  *
  * See raw_write_seqcount_latch() for details and a full reader/writer
  * usage example.
@@ -629,17 +629,14 @@ static inline void seqcount_latch_init(seqcount_latch_t *s)
  * picking which data copy to read. The full counter must then be checked
  * with read_seqcount_latch_retry().
  */
-#define raw_read_seqcount_latch(s)						\
-({										\
-	/*									\
-	 * Pairs with the first smp_wmb() in raw_write_seqcount_latch().	\
-	 * Due to the dependent load, a full smp_rmb() is not needed.		\
-	 */									\
-	_Generic(*(s),								\
-		 seqcount_t:		  READ_ONCE(((seqcount_t *)s)->sequence),			\
-		 seqcount_raw_spinlock_t: READ_ONCE(((seqcount_raw_spinlock_t *)s)->seqcount.sequence),	\
-		 seqcount_latch_t:	  READ_ONCE(((seqcount_latch_t *)s)->seqcount.sequence));	\
-})
+static inline unsigned raw_read_seqcount_latch(const seqcount_latch_t *s)
+{
+	/*
+	 * Pairs with the first smp_wmb() in raw_write_seqcount_latch().
+	 * Due to the dependent load, a full smp_rmb() is not needed.
+	 */
+	return READ_ONCE(s->seqcount.sequence);
+}
 
 /**
  * read_seqcount_latch_retry() - end a seqcount_latch_t read section
@@ -656,7 +653,7 @@ read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start)
 
 /**
  * raw_write_seqcount_latch() - redirect latch readers to even/odd copy
- * @s: Pointer to seqcount_t, seqcount_raw_spinlock_t, or seqcount_latch_t
+ * @s: Pointer to seqcount_latch_t
  *
  * The latch technique is a multiversion concurrency control method that allows
  * queries during non-atomic modifications. If you can guarantee queries never
@@ -735,14 +732,11 @@ read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start)
  *	When data is a dynamic data structure; one should use regular RCU
  *	patterns to manage the lifetimes of the objects within.
  */
-#define raw_write_seqcount_latch(s)						\
-{										\
-       smp_wmb();      /* prior stores before incrementing "sequence" */	\
-       _Generic(*(s),								\
-		seqcount_t:		((seqcount_t *)s)->sequence++,		\
-		seqcount_raw_spinlock_t:((seqcount_raw_spinlock_t *)s)->seqcount.sequence++, \
-		seqcount_latch_t:	((seqcount_latch_t *)s)->seqcount.sequence++); \
-       smp_wmb();      /* increment "sequence" before following stores */	\
+static inline void raw_write_seqcount_latch(seqcount_latch_t *s)
+{
+	smp_wmb();	/* prior stores before incrementing "sequence" */
+	s->seqcount.sequence++;
+	smp_wmb();      /* increment "sequence" before following stores */
 }
 
 /*
-- 
cgit v1.2.3


From 6dd699b13d53f26a7603702d8bada3482312df74 Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Fri, 4 Sep 2020 17:32:27 +0200
Subject: seqlock: seqcount_LOCKNAME_t: Standardize naming convention

At seqlock.h, sequence counters with associated locks are either called
seqcount_LOCKNAME_t, seqcount_LOCKTYPE_t, or seqcount_locktype_t.

Standardize on seqcount_LOCKNAME_t for all instances in comments,
kernel-doc, and SEQCOUNT_LOCKNAME() generative macro paramters.

Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200904153231.11994-2-a.darwish@linutronix.de
---
 include/linux/seqlock.h | 79 +++++++++++++++++++++++++------------------------
 1 file changed, 40 insertions(+), 39 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index f2a7a467e998..820ace2f5911 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -53,7 +53,7 @@
  *
  * If the write serialization mechanism is one of the common kernel
  * locking primitives, use a sequence counter with associated lock
- * (seqcount_LOCKTYPE_t) instead.
+ * (seqcount_LOCKNAME_t) instead.
  *
  * If it's desired to automatically handle the sequence counter writer
  * serialization and non-preemptibility requirements, use a sequential
@@ -117,7 +117,7 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
 #define SEQCNT_ZERO(name) { .sequence = 0, SEQCOUNT_DEP_MAP_INIT(name) }
 
 /*
- * Sequence counters with associated locks (seqcount_LOCKTYPE_t)
+ * Sequence counters with associated locks (seqcount_LOCKNAME_t)
  *
  * A sequence counter which associates the lock used for writer
  * serialization at initialization time. This enables lockdep to validate
@@ -138,30 +138,32 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
 #endif
 
 /**
- * typedef seqcount_LOCKNAME_t - sequence counter with LOCKTYPE associated
+ * typedef seqcount_LOCKNAME_t - sequence counter with LOCKNAME associated
  * @seqcount:	The real sequence counter
- * @lock:	Pointer to the associated spinlock
+ * @lock:	Pointer to the associated lock
  *
- * A plain sequence counter with external writer synchronization by a
- * spinlock. The spinlock is associated to the sequence count in the
+ * A plain sequence counter with external writer synchronization by
+ * LOCKNAME @lock. The lock is associated to the sequence counter in the
  * static initializer or init function. This enables lockdep to validate
  * that the write side critical section is properly serialized.
+ *
+ * LOCKNAME:	raw_spinlock, spinlock, rwlock, mutex, or ww_mutex.
  */
 
 /*
  * seqcount_LOCKNAME_init() - runtime initializer for seqcount_LOCKNAME_t
  * @s:		Pointer to the seqcount_LOCKNAME_t instance
- * @lock:	Pointer to the associated LOCKTYPE
+ * @lock:	Pointer to the associated lock
  */
 
 /*
- * SEQCOUNT_LOCKTYPE() - Instantiate seqcount_LOCKNAME_t and helpers
- * @locktype:		actual typename
- * @lockname:		name
- * @preemptible:	preemptibility of above locktype
+ * SEQCOUNT_LOCKNAME() - Instantiate seqcount_LOCKNAME_t and helpers
+ * @lockname:		"LOCKNAME" part of seqcount_LOCKNAME_t
+ * @locktype:		LOCKNAME canonical C data type
+ * @preemptible:	preemptibility of above lockname
  * @lockmember:		argument for lockdep_assert_held()
  */
-#define SEQCOUNT_LOCKTYPE(locktype, lockname, preemptible, lockmember)	\
+#define SEQCOUNT_LOCKNAME(lockname, locktype, preemptible, lockmember)	\
 typedef struct seqcount_##lockname {					\
 	seqcount_t		seqcount;				\
 	__SEQ_LOCK(locktype	*lock);					\
@@ -211,29 +213,28 @@ static inline void __seqcount_assert(seqcount_t *s)
 	lockdep_assert_preemption_disabled();
 }
 
-SEQCOUNT_LOCKTYPE(raw_spinlock_t,	raw_spinlock,	false,	s->lock)
-SEQCOUNT_LOCKTYPE(spinlock_t,		spinlock,	false,	s->lock)
-SEQCOUNT_LOCKTYPE(rwlock_t,		rwlock,		false,	s->lock)
-SEQCOUNT_LOCKTYPE(struct mutex,		mutex,		true,	s->lock)
-SEQCOUNT_LOCKTYPE(struct ww_mutex,	ww_mutex,	true,	&s->lock->base)
+SEQCOUNT_LOCKNAME(raw_spinlock,	raw_spinlock_t,		false,	s->lock)
+SEQCOUNT_LOCKNAME(spinlock,	spinlock_t,		false,	s->lock)
+SEQCOUNT_LOCKNAME(rwlock,	rwlock_t,		false,	s->lock)
+SEQCOUNT_LOCKNAME(mutex,	struct mutex,		true,	s->lock)
+SEQCOUNT_LOCKNAME(ww_mutex,	struct ww_mutex,	true,	&s->lock->base)
 
 /*
  * SEQCNT_LOCKNAME_ZERO - static initializer for seqcount_LOCKNAME_t
  * @name:	Name of the seqcount_LOCKNAME_t instance
- * @lock:	Pointer to the associated LOCKTYPE
+ * @lock:	Pointer to the associated LOCKNAME
  */
 
-#define SEQCOUNT_LOCKTYPE_ZERO(seq_name, assoc_lock) {			\
+#define SEQCOUNT_LOCKNAME_ZERO(seq_name, assoc_lock) {			\
 	.seqcount		= SEQCNT_ZERO(seq_name.seqcount),	\
 	__SEQ_LOCK(.lock	= (assoc_lock))				\
 }
 
-#define SEQCNT_SPINLOCK_ZERO(name, lock)	SEQCOUNT_LOCKTYPE_ZERO(name, lock)
-#define SEQCNT_RAW_SPINLOCK_ZERO(name, lock)	SEQCOUNT_LOCKTYPE_ZERO(name, lock)
-#define SEQCNT_RWLOCK_ZERO(name, lock)		SEQCOUNT_LOCKTYPE_ZERO(name, lock)
-#define SEQCNT_MUTEX_ZERO(name, lock)		SEQCOUNT_LOCKTYPE_ZERO(name, lock)
-#define SEQCNT_WW_MUTEX_ZERO(name, lock) 	SEQCOUNT_LOCKTYPE_ZERO(name, lock)
-
+#define SEQCNT_SPINLOCK_ZERO(name, lock)	SEQCOUNT_LOCKNAME_ZERO(name, lock)
+#define SEQCNT_RAW_SPINLOCK_ZERO(name, lock)	SEQCOUNT_LOCKNAME_ZERO(name, lock)
+#define SEQCNT_RWLOCK_ZERO(name, lock)		SEQCOUNT_LOCKNAME_ZERO(name, lock)
+#define SEQCNT_MUTEX_ZERO(name, lock)		SEQCOUNT_LOCKNAME_ZERO(name, lock)
+#define SEQCNT_WW_MUTEX_ZERO(name, lock) 	SEQCOUNT_LOCKNAME_ZERO(name, lock)
 
 #define __seqprop_case(s, lockname, prop)				\
 	seqcount_##lockname##_t: __seqcount_##lockname##_##prop((void *)(s))
@@ -252,7 +253,7 @@ SEQCOUNT_LOCKTYPE(struct ww_mutex,	ww_mutex,	true,	&s->lock->base)
 
 /**
  * __read_seqcount_begin() - begin a seqcount_t read section w/o barrier
- * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
  *
  * __read_seqcount_begin is like read_seqcount_begin, but has no smp_rmb()
  * barrier. Callers should ensure that smp_rmb() or equivalent ordering is
@@ -283,7 +284,7 @@ repeat:
 
 /**
  * raw_read_seqcount_begin() - begin a seqcount_t read section w/o lockdep
- * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
  *
  * Return: count to be passed to read_seqcount_retry()
  */
@@ -299,7 +300,7 @@ static inline unsigned raw_read_seqcount_t_begin(const seqcount_t *s)
 
 /**
  * read_seqcount_begin() - begin a seqcount_t read critical section
- * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
  *
  * Return: count to be passed to read_seqcount_retry()
  */
@@ -314,7 +315,7 @@ static inline unsigned read_seqcount_t_begin(const seqcount_t *s)
 
 /**
  * raw_read_seqcount() - read the raw seqcount_t counter value
- * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
  *
  * raw_read_seqcount opens a read critical section of the given
  * seqcount_t, without any lockdep checking, and without checking or
@@ -337,7 +338,7 @@ static inline unsigned raw_read_seqcount_t(const seqcount_t *s)
 /**
  * raw_seqcount_begin() - begin a seqcount_t read critical section w/o
  *                        lockdep and w/o counter stabilization
- * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
  *
  * raw_seqcount_begin opens a read critical section of the given
  * seqcount_t. Unlike read_seqcount_begin(), this function will not wait
@@ -365,7 +366,7 @@ static inline unsigned raw_seqcount_t_begin(const seqcount_t *s)
 
 /**
  * __read_seqcount_retry() - end a seqcount_t read section w/o barrier
- * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
  * @start: count, from read_seqcount_begin()
  *
  * __read_seqcount_retry is like read_seqcount_retry, but has no smp_rmb()
@@ -389,7 +390,7 @@ static inline int __read_seqcount_t_retry(const seqcount_t *s, unsigned start)
 
 /**
  * read_seqcount_retry() - end a seqcount_t read critical section
- * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
  * @start: count, from read_seqcount_begin()
  *
  * read_seqcount_retry closes the read critical section of given
@@ -409,7 +410,7 @@ static inline int read_seqcount_t_retry(const seqcount_t *s, unsigned start)
 
 /**
  * raw_write_seqcount_begin() - start a seqcount_t write section w/o lockdep
- * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
  */
 #define raw_write_seqcount_begin(s)					\
 do {									\
@@ -428,7 +429,7 @@ static inline void raw_write_seqcount_t_begin(seqcount_t *s)
 
 /**
  * raw_write_seqcount_end() - end a seqcount_t write section w/o lockdep
- * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
  */
 #define raw_write_seqcount_end(s)					\
 do {									\
@@ -448,7 +449,7 @@ static inline void raw_write_seqcount_t_end(seqcount_t *s)
 /**
  * write_seqcount_begin_nested() - start a seqcount_t write section with
  *                                 custom lockdep nesting level
- * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
  * @subclass: lockdep nesting level
  *
  * See Documentation/locking/lockdep-design.rst
@@ -471,7 +472,7 @@ static inline void write_seqcount_t_begin_nested(seqcount_t *s, int subclass)
 
 /**
  * write_seqcount_begin() - start a seqcount_t write side critical section
- * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
  *
  * write_seqcount_begin opens a write side critical section of the given
  * seqcount_t.
@@ -497,7 +498,7 @@ static inline void write_seqcount_t_begin(seqcount_t *s)
 
 /**
  * write_seqcount_end() - end a seqcount_t write side critical section
- * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
  *
  * The write section must've been opened with write_seqcount_begin().
  */
@@ -517,7 +518,7 @@ static inline void write_seqcount_t_end(seqcount_t *s)
 
 /**
  * raw_write_seqcount_barrier() - do a seqcount_t write barrier
- * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
  *
  * This can be used to provide an ordering guarantee instead of the usual
  * consistency guarantee. It is one wmb cheaper, because it can collapse
@@ -571,7 +572,7 @@ static inline void raw_write_seqcount_t_barrier(seqcount_t *s)
 /**
  * write_seqcount_invalidate() - invalidate in-progress seqcount_t read
  *                               side operations
- * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
  *
  * After write_seqcount_invalidate, no seqcount_t read side operations
  * will complete successfully and see data older than this.
-- 
cgit v1.2.3


From 5cdd25572a29e46f932d3e6eedbd07429de66431 Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Fri, 4 Sep 2020 17:32:28 +0200
Subject: seqlock: Use unique prefix for seqcount_t property accessors

At seqlock.h, the following set of functions:

    - __seqcount_ptr()
    - __seqcount_preemptible()
    - __seqcount_assert()

act as plain seqcount_t "property" accessors. Meanwhile, the following
group:

    - __seqcount_ptr()
    - __seqcount_lock_preemptible()
    - __seqcount_assert_lock_held()

act as the equivalent set, but in the generic form, taking either
seqcount_t or any of the seqcount_LOCKNAME_t variants.

This is quite confusing, especially the first member where it is called
exactly the same in both groups.

Differentiate the first group by using "__seqprop" as prefix, and also
use that same prefix for all of seqcount_LOCKNAME_t property accessors.

While at it, constify the property accessors first parameter when
appropriate.

References: 55f3560df975 ("seqlock: Extend seqcount API with associated locks")
Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200904153231.11994-3-a.darwish@linutronix.de
---
 include/linux/seqlock.h | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 820ace2f5911..0b4a22f33ac3 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -157,7 +157,9 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
  */
 
 /*
- * SEQCOUNT_LOCKNAME() - Instantiate seqcount_LOCKNAME_t and helpers
+ * SEQCOUNT_LOCKNAME()	- Instantiate seqcount_LOCKNAME_t and helpers
+ * seqprop_LOCKNAME_*()	- Property accessors for seqcount_LOCKNAME_t
+ *
  * @lockname:		"LOCKNAME" part of seqcount_LOCKNAME_t
  * @locktype:		LOCKNAME canonical C data type
  * @preemptible:	preemptibility of above lockname
@@ -177,19 +179,19 @@ seqcount_##lockname##_init(seqcount_##lockname##_t *s, locktype *lock)	\
 }									\
 									\
 static __always_inline seqcount_t *					\
-__seqcount_##lockname##_ptr(seqcount_##lockname##_t *s)			\
+__seqprop_##lockname##_ptr(seqcount_##lockname##_t *s)			\
 {									\
 	return &s->seqcount;						\
 }									\
 									\
 static __always_inline bool						\
-__seqcount_##lockname##_preemptible(seqcount_##lockname##_t *s)		\
+__seqprop_##lockname##_preemptible(const seqcount_##lockname##_t *s)	\
 {									\
 	return preemptible;						\
 }									\
 									\
 static __always_inline void						\
-__seqcount_##lockname##_assert(seqcount_##lockname##_t *s)		\
+__seqprop_##lockname##_assert(const seqcount_##lockname##_t *s)		\
 {									\
 	__SEQ_LOCK(lockdep_assert_held(lockmember));			\
 }
@@ -198,17 +200,17 @@ __seqcount_##lockname##_assert(seqcount_##lockname##_t *s)		\
  * __seqprop() for seqcount_t
  */
 
-static inline seqcount_t *__seqcount_ptr(seqcount_t *s)
+static inline seqcount_t *__seqprop_ptr(seqcount_t *s)
 {
 	return s;
 }
 
-static inline bool __seqcount_preemptible(seqcount_t *s)
+static inline bool __seqprop_preemptible(const seqcount_t *s)
 {
 	return false;
 }
 
-static inline void __seqcount_assert(seqcount_t *s)
+static inline void __seqprop_assert(const seqcount_t *s)
 {
 	lockdep_assert_preemption_disabled();
 }
@@ -237,10 +239,10 @@ SEQCOUNT_LOCKNAME(ww_mutex,	struct ww_mutex,	true,	&s->lock->base)
 #define SEQCNT_WW_MUTEX_ZERO(name, lock) 	SEQCOUNT_LOCKNAME_ZERO(name, lock)
 
 #define __seqprop_case(s, lockname, prop)				\
-	seqcount_##lockname##_t: __seqcount_##lockname##_##prop((void *)(s))
+	seqcount_##lockname##_t: __seqprop_##lockname##_##prop((void *)(s))
 
 #define __seqprop(s, prop) _Generic(*(s),				\
-	seqcount_t:		__seqcount_##prop((void *)(s)),		\
+	seqcount_t:		__seqprop_##prop((void *)(s)),		\
 	__seqprop_case((s),	raw_spinlock,	prop),			\
 	__seqprop_case((s),	spinlock,	prop),			\
 	__seqprop_case((s),	rwlock,		prop),			\
-- 
cgit v1.2.3


From 52ac39e5db5148f70392edb654ad882ac8da88a8 Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Fri, 4 Sep 2020 17:32:29 +0200
Subject: seqlock: seqcount_t: Implement all read APIs as statement expressions

The sequence counters read APIs are implemented as CPP macros, so they
can take either seqcount_t or any of the seqcount_LOCKNAME_t variants.
Such macros then get *directly* transformed to internal C functions that
only take plain seqcount_t.

Further commits need access to seqcount_LOCKNAME_t inside of the actual
read APIs code. Thus transform all of the seqcount read APIs to pure GCC
statement expressions instead.

This will not break type-safety: all of the transformed APIs resolve to
a _Generic() selection that does not have a "default" case.

This will also not affect the transformed APIs readability: previously
added kernel-doc above all of seqlock.h functions makes the expectations
quite clear for call-site developers.

Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200904153231.11994-4-a.darwish@linutronix.de
---
 include/linux/seqlock.h | 94 +++++++++++++++++++++++--------------------------
 1 file changed, 45 insertions(+), 49 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 0b4a22f33ac3..f3b78277e26b 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -184,6 +184,12 @@ __seqprop_##lockname##_ptr(seqcount_##lockname##_t *s)			\
 	return &s->seqcount;						\
 }									\
 									\
+static __always_inline unsigned						\
+__seqprop_##lockname##_sequence(const seqcount_##lockname##_t *s)	\
+{									\
+	return READ_ONCE(s->seqcount.sequence);				\
+}									\
+									\
 static __always_inline bool						\
 __seqprop_##lockname##_preemptible(const seqcount_##lockname##_t *s)	\
 {									\
@@ -205,6 +211,11 @@ static inline seqcount_t *__seqprop_ptr(seqcount_t *s)
 	return s;
 }
 
+static inline unsigned __seqprop_sequence(const seqcount_t *s)
+{
+	return READ_ONCE(s->sequence);
+}
+
 static inline bool __seqprop_preemptible(const seqcount_t *s)
 {
 	return false;
@@ -250,6 +261,7 @@ SEQCOUNT_LOCKNAME(ww_mutex,	struct ww_mutex,	true,	&s->lock->base)
 	__seqprop_case((s),	ww_mutex,	prop))
 
 #define __seqcount_ptr(s)		__seqprop(s, ptr)
+#define __seqcount_sequence(s)		__seqprop(s, sequence)
 #define __seqcount_lock_preemptible(s)	__seqprop(s, preemptible)
 #define __seqcount_assert_lock_held(s)	__seqprop(s, assert)
 
@@ -268,21 +280,15 @@ SEQCOUNT_LOCKNAME(ww_mutex,	struct ww_mutex,	true,	&s->lock->base)
  * Return: count to be passed to read_seqcount_retry()
  */
 #define __read_seqcount_begin(s)					\
-	__read_seqcount_t_begin(__seqcount_ptr(s))
-
-static inline unsigned __read_seqcount_t_begin(const seqcount_t *s)
-{
-	unsigned ret;
-
-repeat:
-	ret = READ_ONCE(s->sequence);
-	if (unlikely(ret & 1)) {
-		cpu_relax();
-		goto repeat;
-	}
-	kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX);
-	return ret;
-}
+({									\
+	unsigned seq;							\
+									\
+	while ((seq = __seqcount_sequence(s)) & 1)			\
+		cpu_relax();						\
+									\
+	kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX);			\
+	seq;								\
+})
 
 /**
  * raw_read_seqcount_begin() - begin a seqcount_t read section w/o lockdep
@@ -291,14 +297,12 @@ repeat:
  * Return: count to be passed to read_seqcount_retry()
  */
 #define raw_read_seqcount_begin(s)					\
-	raw_read_seqcount_t_begin(__seqcount_ptr(s))
-
-static inline unsigned raw_read_seqcount_t_begin(const seqcount_t *s)
-{
-	unsigned ret = __read_seqcount_t_begin(s);
-	smp_rmb();
-	return ret;
-}
+({									\
+	unsigned seq = __read_seqcount_begin(s);			\
+									\
+	smp_rmb();							\
+	seq;								\
+})
 
 /**
  * read_seqcount_begin() - begin a seqcount_t read critical section
@@ -307,13 +311,10 @@ static inline unsigned raw_read_seqcount_t_begin(const seqcount_t *s)
  * Return: count to be passed to read_seqcount_retry()
  */
 #define read_seqcount_begin(s)						\
-	read_seqcount_t_begin(__seqcount_ptr(s))
-
-static inline unsigned read_seqcount_t_begin(const seqcount_t *s)
-{
-	seqcount_lockdep_reader_access(s);
-	return raw_read_seqcount_t_begin(s);
-}
+({									\
+	seqcount_lockdep_reader_access(__seqcount_ptr(s));		\
+	raw_read_seqcount_begin(s);					\
+})
 
 /**
  * raw_read_seqcount() - read the raw seqcount_t counter value
@@ -327,15 +328,13 @@ static inline unsigned read_seqcount_t_begin(const seqcount_t *s)
  * Return: count to be passed to read_seqcount_retry()
  */
 #define raw_read_seqcount(s)						\
-	raw_read_seqcount_t(__seqcount_ptr(s))
-
-static inline unsigned raw_read_seqcount_t(const seqcount_t *s)
-{
-	unsigned ret = READ_ONCE(s->sequence);
-	smp_rmb();
-	kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX);
-	return ret;
-}
+({									\
+	unsigned seq = __seqcount_sequence(s);				\
+									\
+	smp_rmb();							\
+	kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX);			\
+	seq;								\
+})
 
 /**
  * raw_seqcount_begin() - begin a seqcount_t read critical section w/o
@@ -355,16 +354,13 @@ static inline unsigned raw_read_seqcount_t(const seqcount_t *s)
  * Return: count to be passed to read_seqcount_retry()
  */
 #define raw_seqcount_begin(s)						\
-	raw_seqcount_t_begin(__seqcount_ptr(s))
-
-static inline unsigned raw_seqcount_t_begin(const seqcount_t *s)
-{
-	/*
-	 * If the counter is odd, let read_seqcount_retry() fail
-	 * by decrementing the counter.
-	 */
-	return raw_read_seqcount_t(s) & ~1;
-}
+({									\
+	/*								\
+	 * If the counter is odd, let read_seqcount_retry() fail	\
+	 * by decrementing the counter.					\
+	 */								\
+	raw_read_seqcount(s) & ~1;					\
+})
 
 /**
  * __read_seqcount_retry() - end a seqcount_t read section w/o barrier
-- 
cgit v1.2.3


From 8117ab508f9c476e0a10b9db7f4818f784cf3176 Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Fri, 4 Sep 2020 17:32:30 +0200
Subject: seqlock: seqcount_LOCKNAME_t: Introduce PREEMPT_RT support

Preemption must be disabled before entering a sequence counter write
side critical section.  Otherwise the read side section can preempt the
write side section and spin for the entire scheduler tick.  If that
reader belongs to a real-time scheduling class, it can spin forever and
the kernel will livelock.

Disabling preemption cannot be done for PREEMPT_RT though: it can lead
to higher latencies, and the write side sections will not be able to
acquire locks which become sleeping locks (e.g. spinlock_t).

To remain preemptible, while avoiding a possible livelock caused by the
reader preempting the writer, use a different technique: let the reader
detect if a seqcount_LOCKNAME_t writer is in progress. If that's the
case, acquire then release the associated LOCKNAME writer serialization
lock. This will allow any possibly-preempted writer to make progress
until the end of its writer serialization lock critical section.

Implement this lock-unlock technique for all seqcount_LOCKNAME_t with
an associated (PREEMPT_RT) sleeping lock.

References: 55f3560df975 ("seqlock: Extend seqcount API with associated locks")
Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200519214547.352050-1-a.darwish@linutronix.de
---
 include/linux/seqlock.h | 61 +++++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 51 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index f3b78277e26b..2bc95104ab1b 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -17,6 +17,7 @@
 #include <linux/kcsan-checks.h>
 #include <linux/lockdep.h>
 #include <linux/mutex.h>
+#include <linux/ww_mutex.h>
 #include <linux/preempt.h>
 #include <linux/spinlock.h>
 
@@ -131,7 +132,23 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
  * See Documentation/locking/seqlock.rst
  */
 
-#ifdef CONFIG_LOCKDEP
+/*
+ * For PREEMPT_RT, seqcount_LOCKNAME_t write side critical sections cannot
+ * disable preemption. It can lead to higher latencies, and the write side
+ * sections will not be able to acquire locks which become sleeping locks
+ * (e.g. spinlock_t).
+ *
+ * To remain preemptible while avoiding a possible livelock caused by the
+ * reader preempting the writer, use a different technique: let the reader
+ * detect if a seqcount_LOCKNAME_t writer is in progress. If that is the
+ * case, acquire then release the associated LOCKNAME writer serialization
+ * lock. This will allow any possibly-preempted writer to make progress
+ * until the end of its writer serialization lock critical section.
+ *
+ * This lock-unlock technique must be implemented for all of PREEMPT_RT
+ * sleeping locks.  See Documentation/locking/locktypes.rst
+ */
+#if defined(CONFIG_LOCKDEP) || defined(CONFIG_PREEMPT_RT)
 #define __SEQ_LOCK(expr)	expr
 #else
 #define __SEQ_LOCK(expr)
@@ -162,10 +179,12 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
  *
  * @lockname:		"LOCKNAME" part of seqcount_LOCKNAME_t
  * @locktype:		LOCKNAME canonical C data type
- * @preemptible:	preemptibility of above lockname
+ * @preemptible:	preemptibility of above locktype
  * @lockmember:		argument for lockdep_assert_held()
+ * @lockbase:		associated lock release function (prefix only)
+ * @lock_acquire:	associated lock acquisition function (full call)
  */
-#define SEQCOUNT_LOCKNAME(lockname, locktype, preemptible, lockmember)	\
+#define SEQCOUNT_LOCKNAME(lockname, locktype, preemptible, lockmember, lockbase, lock_acquire) \
 typedef struct seqcount_##lockname {					\
 	seqcount_t		seqcount;				\
 	__SEQ_LOCK(locktype	*lock);					\
@@ -187,13 +206,33 @@ __seqprop_##lockname##_ptr(seqcount_##lockname##_t *s)			\
 static __always_inline unsigned						\
 __seqprop_##lockname##_sequence(const seqcount_##lockname##_t *s)	\
 {									\
-	return READ_ONCE(s->seqcount.sequence);				\
+	unsigned seq = READ_ONCE(s->seqcount.sequence);			\
+									\
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))				\
+		return seq;						\
+									\
+	if (preemptible && unlikely(seq & 1)) {				\
+		__SEQ_LOCK(lock_acquire);				\
+		__SEQ_LOCK(lockbase##_unlock(s->lock));			\
+									\
+		/*							\
+		 * Re-read the sequence counter since the (possibly	\
+		 * preempted) writer made progress.			\
+		 */							\
+		seq = READ_ONCE(s->seqcount.sequence);			\
+	}								\
+									\
+	return seq;							\
 }									\
 									\
 static __always_inline bool						\
 __seqprop_##lockname##_preemptible(const seqcount_##lockname##_t *s)	\
 {									\
-	return preemptible;						\
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))				\
+		return preemptible;					\
+									\
+	/* PREEMPT_RT relies on the above LOCK+UNLOCK */		\
+	return false;							\
 }									\
 									\
 static __always_inline void						\
@@ -226,11 +265,13 @@ static inline void __seqprop_assert(const seqcount_t *s)
 	lockdep_assert_preemption_disabled();
 }
 
-SEQCOUNT_LOCKNAME(raw_spinlock,	raw_spinlock_t,		false,	s->lock)
-SEQCOUNT_LOCKNAME(spinlock,	spinlock_t,		false,	s->lock)
-SEQCOUNT_LOCKNAME(rwlock,	rwlock_t,		false,	s->lock)
-SEQCOUNT_LOCKNAME(mutex,	struct mutex,		true,	s->lock)
-SEQCOUNT_LOCKNAME(ww_mutex,	struct ww_mutex,	true,	&s->lock->base)
+#define __SEQ_RT	IS_ENABLED(CONFIG_PREEMPT_RT)
+
+SEQCOUNT_LOCKNAME(raw_spinlock, raw_spinlock_t,  false,    s->lock,        raw_spin, raw_spin_lock(s->lock))
+SEQCOUNT_LOCKNAME(spinlock,     spinlock_t,      __SEQ_RT, s->lock,        spin,     spin_lock(s->lock))
+SEQCOUNT_LOCKNAME(rwlock,       rwlock_t,        __SEQ_RT, s->lock,        read,     read_lock(s->lock))
+SEQCOUNT_LOCKNAME(mutex,        struct mutex,    true,     s->lock,        mutex,    mutex_lock(s->lock))
+SEQCOUNT_LOCKNAME(ww_mutex,     struct ww_mutex, true,     &s->lock->base, ww_mutex, ww_mutex_lock(s->lock, NULL))
 
 /*
  * SEQCNT_LOCKNAME_ZERO - static initializer for seqcount_LOCKNAME_t
-- 
cgit v1.2.3


From 1909760f5fc3f123e47b4e24e0ccdc0fc8f3f106 Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Fri, 4 Sep 2020 17:32:31 +0200
Subject: seqlock: PREEMPT_RT: Do not starve seqlock_t writers

On PREEMPT_RT, seqlock_t is transformed to a sleeping lock that do not
disable preemption. A seqlock_t reader can thus preempt its write side
section and spin for the enter scheduler tick. If that reader belongs to
a real-time scheduling class, it can spin forever and the kernel will
livelock.

To break this livelock possibility on PREEMPT_RT, implement seqlock_t in
terms of "seqcount_spinlock_t" instead of plain "seqcount_t".

Beside its pure annotational value, this will leverage the existing
seqcount_LOCKNAME_T PREEMPT_RT anti-livelock mechanisms, without adding
any extra code.

Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200904153231.11994-6-a.darwish@linutronix.de
---
 include/linux/seqlock.h | 32 +++++++++++++++++++++-----------
 1 file changed, 21 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 2bc95104ab1b..f73c7eb68f27 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -790,13 +790,17 @@ static inline void raw_write_seqcount_latch(seqcount_latch_t *s)
  *    - Documentation/locking/seqlock.rst
  */
 typedef struct {
-	struct seqcount seqcount;
+	/*
+	 * Make sure that readers don't starve writers on PREEMPT_RT: use
+	 * seqcount_spinlock_t instead of seqcount_t. Check __SEQ_LOCK().
+	 */
+	seqcount_spinlock_t seqcount;
 	spinlock_t lock;
 } seqlock_t;
 
 #define __SEQLOCK_UNLOCKED(lockname)					\
 	{								\
-		.seqcount = SEQCNT_ZERO(lockname),			\
+		.seqcount = SEQCNT_SPINLOCK_ZERO(lockname, &(lockname).lock), \
 		.lock =	__SPIN_LOCK_UNLOCKED(lockname)			\
 	}
 
@@ -806,8 +810,8 @@ typedef struct {
  */
 #define seqlock_init(sl)						\
 	do {								\
-		seqcount_init(&(sl)->seqcount);				\
 		spin_lock_init(&(sl)->lock);				\
+		seqcount_spinlock_init(&(sl)->seqcount, &(sl)->lock);	\
 	} while (0)
 
 /**
@@ -854,6 +858,12 @@ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start)
 	return read_seqcount_retry(&sl->seqcount, start);
 }
 
+/*
+ * For all seqlock_t write side functions, use write_seqcount_*t*_begin()
+ * instead of the generic write_seqcount_begin(). This way, no redundant
+ * lockdep_assert_held() checks are added.
+ */
+
 /**
  * write_seqlock() - start a seqlock_t write side critical section
  * @sl: Pointer to seqlock_t
@@ -870,7 +880,7 @@ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start)
 static inline void write_seqlock(seqlock_t *sl)
 {
 	spin_lock(&sl->lock);
-	write_seqcount_t_begin(&sl->seqcount);
+	write_seqcount_t_begin(&sl->seqcount.seqcount);
 }
 
 /**
@@ -882,7 +892,7 @@ static inline void write_seqlock(seqlock_t *sl)
  */
 static inline void write_sequnlock(seqlock_t *sl)
 {
-	write_seqcount_t_end(&sl->seqcount);
+	write_seqcount_t_end(&sl->seqcount.seqcount);
 	spin_unlock(&sl->lock);
 }
 
@@ -896,7 +906,7 @@ static inline void write_sequnlock(seqlock_t *sl)
 static inline void write_seqlock_bh(seqlock_t *sl)
 {
 	spin_lock_bh(&sl->lock);
-	write_seqcount_t_begin(&sl->seqcount);
+	write_seqcount_t_begin(&sl->seqcount.seqcount);
 }
 
 /**
@@ -909,7 +919,7 @@ static inline void write_seqlock_bh(seqlock_t *sl)
  */
 static inline void write_sequnlock_bh(seqlock_t *sl)
 {
-	write_seqcount_t_end(&sl->seqcount);
+	write_seqcount_t_end(&sl->seqcount.seqcount);
 	spin_unlock_bh(&sl->lock);
 }
 
@@ -923,7 +933,7 @@ static inline void write_sequnlock_bh(seqlock_t *sl)
 static inline void write_seqlock_irq(seqlock_t *sl)
 {
 	spin_lock_irq(&sl->lock);
-	write_seqcount_t_begin(&sl->seqcount);
+	write_seqcount_t_begin(&sl->seqcount.seqcount);
 }
 
 /**
@@ -935,7 +945,7 @@ static inline void write_seqlock_irq(seqlock_t *sl)
  */
 static inline void write_sequnlock_irq(seqlock_t *sl)
 {
-	write_seqcount_t_end(&sl->seqcount);
+	write_seqcount_t_end(&sl->seqcount.seqcount);
 	spin_unlock_irq(&sl->lock);
 }
 
@@ -944,7 +954,7 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl)
 	unsigned long flags;
 
 	spin_lock_irqsave(&sl->lock, flags);
-	write_seqcount_t_begin(&sl->seqcount);
+	write_seqcount_t_begin(&sl->seqcount.seqcount);
 	return flags;
 }
 
@@ -973,7 +983,7 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl)
 static inline void
 write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags)
 {
-	write_seqcount_t_end(&sl->seqcount);
+	write_seqcount_t_end(&sl->seqcount.seqcount);
 	spin_unlock_irqrestore(&sl->lock, flags);
 }
 
-- 
cgit v1.2.3


From 44fae179ce73a26733d9e2d346da4e1a1cb94647 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Fri, 21 Aug 2020 12:57:53 -0700
Subject: perf/core: Pull pmu::sched_task() into perf_event_context_sched_out()

The pmu::sched_task() is a context switch callback. It passes the
cpuctx->task_ctx as a parameter to the lower code. To find the
cpuctx->task_ctx, the current code iterates a cpuctx list.
The same context will iterated in perf_event_context_sched_out() soon.
Share the cpuctx->task_ctx can avoid the unnecessary iteration of the
cpuctx list.

The pmu::sched_task() is also required for the optimization case for
equivalent contexts.

The task_ctx_sched_out() will eventually disable and reenable the PMU
when schedule out events. Add perf_pmu_disable() and perf_pmu_enable()
around task_ctx_sched_out() don't break anything.

Drop the cpuctx->ctx.lock for the pmu::sched_task(). The lock is for
per-CPU context, which is not necessary for the per-task context
schedule.

No one uses sched_cb_entry, perf_sched_cb_usages, sched_cb_list, and
perf_pmu_sched_task() any more.

Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200821195754.20159-2-kan.liang@linux.intel.com
---
 include/linux/perf_event.h |  1 -
 kernel/events/core.c       | 47 +++++++++++++++++-----------------------------
 2 files changed, 17 insertions(+), 31 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 46a3974eb4fe..0c19d279b97f 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -872,7 +872,6 @@ struct perf_cpu_context {
 	struct list_head		cgrp_cpuctx_entry;
 #endif
 
-	struct list_head		sched_cb_entry;
 	int				sched_cb_usage;
 
 	int				online;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 3f5fec4dcf01..45edb85344a1 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -382,7 +382,6 @@ static DEFINE_MUTEX(perf_sched_mutex);
 static atomic_t perf_sched_count;
 
 static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
-static DEFINE_PER_CPU(int, perf_sched_cb_usages);
 static DEFINE_PER_CPU(struct pmu_event_list, pmu_sb_events);
 
 static atomic_t nr_mmap_events __read_mostly;
@@ -3384,10 +3383,12 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
 	struct perf_event_context *parent, *next_parent;
 	struct perf_cpu_context *cpuctx;
 	int do_switch = 1;
+	struct pmu *pmu;
 
 	if (likely(!ctx))
 		return;
 
+	pmu = ctx->pmu;
 	cpuctx = __get_cpu_context(ctx);
 	if (!cpuctx->task_ctx)
 		return;
@@ -3417,11 +3418,15 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
 		raw_spin_lock(&ctx->lock);
 		raw_spin_lock_nested(&next_ctx->lock, SINGLE_DEPTH_NESTING);
 		if (context_equiv(ctx, next_ctx)) {
-			struct pmu *pmu = ctx->pmu;
 
 			WRITE_ONCE(ctx->task, next);
 			WRITE_ONCE(next_ctx->task, task);
 
+			perf_pmu_disable(pmu);
+
+			if (cpuctx->sched_cb_usage && pmu->sched_task)
+				pmu->sched_task(ctx, false);
+
 			/*
 			 * PMU specific parts of task perf context can require
 			 * additional synchronization. As an example of such
@@ -3433,6 +3438,8 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
 			else
 				swap(ctx->task_ctx_data, next_ctx->task_ctx_data);
 
+			perf_pmu_enable(pmu);
+
 			/*
 			 * RCU_INIT_POINTER here is safe because we've not
 			 * modified the ctx and the above modification of
@@ -3455,21 +3462,22 @@ unlock:
 
 	if (do_switch) {
 		raw_spin_lock(&ctx->lock);
+		perf_pmu_disable(pmu);
+
+		if (cpuctx->sched_cb_usage && pmu->sched_task)
+			pmu->sched_task(ctx, false);
 		task_ctx_sched_out(cpuctx, ctx, EVENT_ALL);
+
+		perf_pmu_enable(pmu);
 		raw_spin_unlock(&ctx->lock);
 	}
 }
 
-static DEFINE_PER_CPU(struct list_head, sched_cb_list);
-
 void perf_sched_cb_dec(struct pmu *pmu)
 {
 	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
 
-	this_cpu_dec(perf_sched_cb_usages);
-
-	if (!--cpuctx->sched_cb_usage)
-		list_del(&cpuctx->sched_cb_entry);
+	--cpuctx->sched_cb_usage;
 }
 
 
@@ -3477,10 +3485,7 @@ void perf_sched_cb_inc(struct pmu *pmu)
 {
 	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
 
-	if (!cpuctx->sched_cb_usage++)
-		list_add(&cpuctx->sched_cb_entry, this_cpu_ptr(&sched_cb_list));
-
-	this_cpu_inc(perf_sched_cb_usages);
+	cpuctx->sched_cb_usage++;
 }
 
 /*
@@ -3509,20 +3514,6 @@ static void __perf_pmu_sched_task(struct perf_cpu_context *cpuctx, bool sched_in
 	perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
 }
 
-static void perf_pmu_sched_task(struct task_struct *prev,
-				struct task_struct *next,
-				bool sched_in)
-{
-	struct perf_cpu_context *cpuctx;
-
-	if (prev == next)
-		return;
-
-	list_for_each_entry(cpuctx, this_cpu_ptr(&sched_cb_list), sched_cb_entry)
-		__perf_pmu_sched_task(cpuctx, sched_in);
-
-}
-
 static void perf_event_switch(struct task_struct *task,
 			      struct task_struct *next_prev, bool sched_in);
 
@@ -3545,9 +3536,6 @@ void __perf_event_task_sched_out(struct task_struct *task,
 {
 	int ctxn;
 
-	if (__this_cpu_read(perf_sched_cb_usages))
-		perf_pmu_sched_task(task, next, false);
-
 	if (atomic_read(&nr_switch_events))
 		perf_event_switch(task, next, false);
 
@@ -12867,7 +12855,6 @@ static void __init perf_event_init_all_cpus(void)
 #ifdef CONFIG_CGROUP_PERF
 		INIT_LIST_HEAD(&per_cpu(cgrp_cpuctx_list, cpu));
 #endif
-		INIT_LIST_HEAD(&per_cpu(sched_cb_list, cpu));
 	}
 }
 
-- 
cgit v1.2.3


From 6bbdd563ee9a6078725727571586c66c8613db64 Mon Sep 17 00:00:00 2001
From: Vivek Goyal <vgoyal@redhat.com>
Date: Tue, 3 Mar 2020 14:58:21 -0500
Subject: dax: Create a range version of dax_layout_busy_page()

virtiofs device has a range of memory which is mapped into file inodes
using dax. This memory is mapped in qemu on host and maps different
sections of real file on host. Size of this memory is limited
(determined by administrator) and depending on filesystem size, we will
soon reach a situation where all the memory is in use and we need to
reclaim some.

As part of reclaim process, we will need to make sure that there are
no active references to pages (taken by get_user_pages()) on the memory
range we are trying to reclaim. I am planning to use
dax_layout_busy_page() for this. But in current form this is per inode
and scans through all the pages of the inode.

We want to reclaim only a portion of memory (say 2MB page). So we want
to make sure that only that 2MB range of pages do not have any
references  (and don't want to unmap all the pages of inode).

Hence, create a range version of this function named
dax_layout_busy_page_range() which can be used to pass a range which
needs to be unmapped.

Cc: Dan Williams <dan.j.williams@intel.com>
Cc: linux-nvdimm@lists.01.org
Cc: Jan Kara <jack@suse.cz>
Cc: Vishal L Verma <vishal.l.verma@intel.com>
Cc: "Weiny, Ira" <ira.weiny@intel.com>
Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/dax.c            | 29 +++++++++++++++++++++++------
 include/linux/dax.h |  6 ++++++
 2 files changed, 29 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/fs/dax.c b/fs/dax.c
index 994ab66a9907..ff9206bfb483 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -559,8 +559,11 @@ fallback:
 }
 
 /**
- * dax_layout_busy_page - find first pinned page in @mapping
+ * dax_layout_busy_page_range - find first pinned page in @mapping
  * @mapping: address space to scan for a page with ref count > 1
+ * @start: Starting offset. Page containing 'start' is included.
+ * @end: End offset. Page containing 'end' is included. If 'end' is LLONG_MAX,
+ *       pages from 'start' till the end of file are included.
  *
  * DAX requires ZONE_DEVICE mapped pages. These pages are never
  * 'onlined' to the page allocator so they are considered idle when
@@ -573,12 +576,15 @@ fallback:
  * to be able to run unmap_mapping_range() and subsequently not race
  * mapping_mapped() becoming true.
  */
-struct page *dax_layout_busy_page(struct address_space *mapping)
+struct page *dax_layout_busy_page_range(struct address_space *mapping,
+					loff_t start, loff_t end)
 {
-	XA_STATE(xas, &mapping->i_pages, 0);
 	void *entry;
 	unsigned int scanned = 0;
 	struct page *page = NULL;
+	pgoff_t start_idx = start >> PAGE_SHIFT;
+	pgoff_t end_idx;
+	XA_STATE(xas, &mapping->i_pages, start_idx);
 
 	/*
 	 * In the 'limited' case get_user_pages() for dax is disabled.
@@ -589,6 +595,11 @@ struct page *dax_layout_busy_page(struct address_space *mapping)
 	if (!dax_mapping(mapping) || !mapping_mapped(mapping))
 		return NULL;
 
+	/* If end == LLONG_MAX, all pages from start to till end of file */
+	if (end == LLONG_MAX)
+		end_idx = ULONG_MAX;
+	else
+		end_idx = end >> PAGE_SHIFT;
 	/*
 	 * If we race get_user_pages_fast() here either we'll see the
 	 * elevated page count in the iteration and wait, or
@@ -596,15 +607,15 @@ struct page *dax_layout_busy_page(struct address_space *mapping)
 	 * against is no longer mapped in the page tables and bail to the
 	 * get_user_pages() slow path.  The slow path is protected by
 	 * pte_lock() and pmd_lock(). New references are not taken without
-	 * holding those locks, and unmap_mapping_range() will not zero the
+	 * holding those locks, and unmap_mapping_pages() will not zero the
 	 * pte or pmd without holding the respective lock, so we are
 	 * guaranteed to either see new references or prevent new
 	 * references from being established.
 	 */
-	unmap_mapping_range(mapping, 0, 0, 0);
+	unmap_mapping_pages(mapping, start_idx, end_idx - start_idx + 1, 0);
 
 	xas_lock_irq(&xas);
-	xas_for_each(&xas, entry, ULONG_MAX) {
+	xas_for_each(&xas, entry, end_idx) {
 		if (WARN_ON_ONCE(!xa_is_value(entry)))
 			continue;
 		if (unlikely(dax_is_locked(entry)))
@@ -625,6 +636,12 @@ struct page *dax_layout_busy_page(struct address_space *mapping)
 	xas_unlock_irq(&xas);
 	return page;
 }
+EXPORT_SYMBOL_GPL(dax_layout_busy_page_range);
+
+struct page *dax_layout_busy_page(struct address_space *mapping)
+{
+	return dax_layout_busy_page_range(mapping, 0, LLONG_MAX);
+}
 EXPORT_SYMBOL_GPL(dax_layout_busy_page);
 
 static int __dax_invalidate_entry(struct address_space *mapping,
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 6904d4e0b2e0..9016929db4c6 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -141,6 +141,7 @@ int dax_writeback_mapping_range(struct address_space *mapping,
 		struct dax_device *dax_dev, struct writeback_control *wbc);
 
 struct page *dax_layout_busy_page(struct address_space *mapping);
+struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t start, loff_t end);
 dax_entry_t dax_lock_page(struct page *page);
 void dax_unlock_page(struct page *page, dax_entry_t cookie);
 #else
@@ -171,6 +172,11 @@ static inline struct page *dax_layout_busy_page(struct address_space *mapping)
 	return NULL;
 }
 
+static inline struct page *dax_layout_busy_page_range(struct address_space *mapping, pgoff_t start, pgoff_t nr_pages)
+{
+	return NULL;
+}
+
 static inline int dax_writeback_mapping_range(struct address_space *mapping,
 		struct dax_device *dax_dev, struct writeback_control *wbc)
 {
-- 
cgit v1.2.3


From 61b82bbf693ecd307550ee64a8af192e8e33c46c Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 2 Sep 2020 20:31:04 +0300
Subject: swiotlb: Declare swiotlb_late_init_with_default_size() in header
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Compiler is not happy about one function prototype:

  CC      kernel/dma/swiotlb.o
  kernel/dma/swiotlb.c:275:1: warning: no previous prototype for ‘swiotlb_late_init_with_default_size’ [-Wmissing-prototypes]
  275 | swiotlb_late_init_with_default_size(size_t default_size)
      | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Since it's used outside of the module, move its declaration to the header
from the user.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 arch/x86/pci/sta2x11-fixup.c | 1 -
 include/linux/swiotlb.h      | 1 +
 2 files changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c
index c313d784efab..11c0e80b9ed4 100644
--- a/arch/x86/pci/sta2x11-fixup.c
+++ b/arch/x86/pci/sta2x11-fixup.c
@@ -15,7 +15,6 @@
 #include <asm/iommu.h>
 
 #define STA2X11_SWIOTLB_SIZE (4*1024*1024)
-extern int swiotlb_late_init_with_default_size(size_t default_size);
 
 /*
  * We build a list of bus numbers that are under the ConneXt. The
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 046bb94bd4d6..513913ff7486 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -34,6 +34,7 @@ int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose);
 extern unsigned long swiotlb_nr_tbl(void);
 unsigned long swiotlb_size_or_default(void);
 extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs);
+extern int swiotlb_late_init_with_default_size(size_t default_size);
 extern void __init swiotlb_update_mem_attributes(void);
 
 /*
-- 
cgit v1.2.3


From 95f6f3a46fc4ee1a2b216a6b46bdf2b450f1877f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 8 Sep 2020 16:53:29 +0200
Subject: block: add a bdev_check_media_change helper

Like check_disk_changed, except that it does not call ->revalidate_disk
but leaves that to the caller.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/genhd.c         | 29 ++++++++++++++++++++++++++++-
 fs/block_dev.c        | 17 +++--------------
 include/linux/genhd.h |  2 +-
 3 files changed, 32 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/block/genhd.c b/block/genhd.c
index 081f1039d936..9d060e79eb31 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -2052,7 +2052,7 @@ void disk_flush_events(struct gendisk *disk, unsigned int mask)
  * CONTEXT:
  * Might sleep.
  */
-unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask)
+static unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask)
 {
 	struct disk_events *ev = disk->ev;
 	unsigned int pending;
@@ -2090,6 +2090,33 @@ unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask)
 	return pending;
 }
 
+/**
+ * bdev_check_media_change - check if a removable media has been changed
+ * @bdev: block device to check
+ *
+ * Check whether a removable media has been changed, and attempt to free all
+ * dentries and inodes and invalidates all block device page cache entries in
+ * that case.
+ *
+ * Returns %true if the block device changed, or %false if not.
+ */
+bool bdev_check_media_change(struct block_device *bdev)
+{
+	unsigned int events;
+
+	events = disk_clear_events(bdev->bd_disk, DISK_EVENT_MEDIA_CHANGE |
+				   DISK_EVENT_EJECT_REQUEST);
+	if (!(events & DISK_EVENT_MEDIA_CHANGE))
+		return false;
+
+	if (__invalidate_device(bdev, true))
+		pr_warn("VFS: busy inodes on changed media %s\n",
+			bdev->bd_disk->disk_name);
+	set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
+	return true;
+}
+EXPORT_SYMBOL(bdev_check_media_change);
+
 /*
  * Separate this part out so that a different pointer for clearing_ptr can be
  * passed in for disk_clear_events.
diff --git a/fs/block_dev.c b/fs/block_dev.c
index c70c41ecba48..c6ac0bd22eca 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1379,21 +1379,10 @@ EXPORT_SYMBOL(revalidate_disk_size);
  */
 int check_disk_change(struct block_device *bdev)
 {
-	struct gendisk *disk = bdev->bd_disk;
-	const struct block_device_operations *bdops = disk->fops;
-	unsigned int events;
-
-	events = disk_clear_events(disk, DISK_EVENT_MEDIA_CHANGE |
-				   DISK_EVENT_EJECT_REQUEST);
-	if (!(events & DISK_EVENT_MEDIA_CHANGE))
+	if (!bdev_check_media_change(bdev))
 		return 0;
-
-	if (__invalidate_device(bdev, true))
-		pr_warn("VFS: busy inodes on changed media %s\n",
-			disk->disk_name);
-	set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
-	if (bdops->revalidate_disk)
-		bdops->revalidate_disk(bdev->bd_disk);
+	if (bdev->bd_disk->fops->revalidate_disk)
+		bdev->bd_disk->fops->revalidate_disk(bdev->bd_disk);
 	return 1;
 }
 
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index c618b27292fc..322d48a20772 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -315,7 +315,6 @@ extern void disk_unblock_events(struct gendisk *disk);
 extern void disk_flush_events(struct gendisk *disk, unsigned int mask);
 void set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size,
 		bool update_bdev);
-extern unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask);
 
 /* drivers/char/random.c */
 extern void add_disk_randomness(struct gendisk *disk) __latent_entropy;
@@ -372,6 +371,7 @@ void unregister_blkdev(unsigned int major, const char *name);
 
 void revalidate_disk_size(struct gendisk *disk, bool verbose);
 int check_disk_change(struct block_device *bdev);
+bool bdev_check_media_change(struct block_device *bdev);
 int __invalidate_device(struct block_device *bdev, bool kill_dirty);
 void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors);
 
-- 
cgit v1.2.3


From fec2cf607ba9305770436b1e5c485963a9f0a7bd Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 8 Sep 2020 16:53:42 +0200
Subject: ide-gd: stop using the disk events mechanism

ide-gd is only using the disk events mechanism to be able to force an
invalidation and partition scan on opening removable media.  Just open
code the logic without invoving the block layer.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/ide/ide-disk.c   |  5 +----
 drivers/ide/ide-floppy.c |  2 --
 drivers/ide/ide-gd.c     | 48 ++++++------------------------------------------
 include/linux/ide.h      |  2 --
 4 files changed, 7 insertions(+), 50 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c
index 1d3407d7e095..34b9441084f8 100644
--- a/drivers/ide/ide-disk.c
+++ b/drivers/ide/ide-disk.c
@@ -739,12 +739,9 @@ static void ide_disk_setup(ide_drive_t *drive)
 	set_wcache(drive, 1);
 
 	if ((drive->dev_flags & IDE_DFLAG_LBA) == 0 &&
-	    (drive->head == 0 || drive->head > 16)) {
+	    (drive->head == 0 || drive->head > 16))
 		printk(KERN_ERR "%s: invalid geometry: %d physical heads?\n",
 			drive->name, drive->head);
-		drive->dev_flags &= ~IDE_DFLAG_ATTACH;
-	} else
-		drive->dev_flags |= IDE_DFLAG_ATTACH;
 }
 
 static void ide_disk_flush(ide_drive_t *drive)
diff --git a/drivers/ide/ide-floppy.c b/drivers/ide/ide-floppy.c
index af7503b47dbe..f5a2870aaf54 100644
--- a/drivers/ide/ide-floppy.c
+++ b/drivers/ide/ide-floppy.c
@@ -516,8 +516,6 @@ static void ide_floppy_setup(ide_drive_t *drive)
 	(void) ide_floppy_get_capacity(drive);
 
 	ide_proc_register_driver(drive, floppy->driver);
-
-	drive->dev_flags |= IDE_DFLAG_ATTACH;
 }
 
 static void ide_floppy_flush(ide_drive_t *drive)
diff --git a/drivers/ide/ide-gd.c b/drivers/ide/ide-gd.c
index 05c26986637b..661e2aa9c967 100644
--- a/drivers/ide/ide-gd.c
+++ b/drivers/ide/ide-gd.c
@@ -225,8 +225,12 @@ static int ide_gd_open(struct block_device *bdev, fmode_t mode)
 		 * and the door_lock is irrelevant at this point.
 		 */
 		drive->disk_ops->set_doorlock(drive, disk, 1);
-		drive->dev_flags |= IDE_DFLAG_MEDIA_CHANGED;
-		check_disk_change(bdev);
+		if (__invalidate_device(bdev, true))
+			pr_warn("VFS: busy inodes on changed media %s\n",
+				bdev->bd_disk->disk_name);
+		drive->disk_ops->get_capacity(drive);
+		set_capacity(disk, ide_gd_capacity(drive));
+		set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
 	} else if (drive->dev_flags & IDE_DFLAG_FORMAT_IN_PROGRESS) {
 		ret = -EBUSY;
 		goto out_put_idkp;
@@ -284,32 +288,6 @@ static int ide_gd_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 	return 0;
 }
 
-static unsigned int ide_gd_check_events(struct gendisk *disk,
-					unsigned int clearing)
-{
-	struct ide_disk_obj *idkp = ide_drv_g(disk, ide_disk_obj);
-	ide_drive_t *drive = idkp->drive;
-	bool ret;
-
-	/* do not scan partitions twice if this is a removable device */
-	if (drive->dev_flags & IDE_DFLAG_ATTACH) {
-		drive->dev_flags &= ~IDE_DFLAG_ATTACH;
-		return 0;
-	}
-
-	/*
-	 * The following is used to force revalidation on the first open on
-	 * removeable devices, and never gets reported to userland as
-	 * DISK_EVENT_FLAG_UEVENT isn't set in genhd->event_flags.
-	 * This is intended as removable ide disk can't really detect
-	 * MEDIA_CHANGE events.
-	 */
-	ret = drive->dev_flags & IDE_DFLAG_MEDIA_CHANGED;
-	drive->dev_flags &= ~IDE_DFLAG_MEDIA_CHANGED;
-
-	return ret ? DISK_EVENT_MEDIA_CHANGE : 0;
-}
-
 static void ide_gd_unlock_native_capacity(struct gendisk *disk)
 {
 	struct ide_disk_obj *idkp = ide_drv_g(disk, ide_disk_obj);
@@ -320,18 +298,6 @@ static void ide_gd_unlock_native_capacity(struct gendisk *disk)
 		disk_ops->unlock_native_capacity(drive);
 }
 
-static int ide_gd_revalidate_disk(struct gendisk *disk)
-{
-	struct ide_disk_obj *idkp = ide_drv_g(disk, ide_disk_obj);
-	ide_drive_t *drive = idkp->drive;
-
-	if (ide_gd_check_events(disk, 0))
-		drive->disk_ops->get_capacity(drive);
-
-	set_capacity(disk, ide_gd_capacity(drive));
-	return 0;
-}
-
 static int ide_gd_ioctl(struct block_device *bdev, fmode_t mode,
 			     unsigned int cmd, unsigned long arg)
 {
@@ -364,9 +330,7 @@ static const struct block_device_operations ide_gd_ops = {
 	.compat_ioctl		= ide_gd_compat_ioctl,
 #endif
 	.getgeo			= ide_gd_getgeo,
-	.check_events		= ide_gd_check_events,
 	.unlock_native_capacity	= ide_gd_unlock_native_capacity,
-	.revalidate_disk	= ide_gd_revalidate_disk
 };
 
 static int ide_gd_probe(ide_drive_t *drive)
diff --git a/include/linux/ide.h b/include/linux/ide.h
index a254841bd315..62653769509f 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -490,8 +490,6 @@ enum {
 	IDE_DFLAG_NOPROBE		= BIT(9),
 	/* need to do check_media_change() */
 	IDE_DFLAG_REMOVABLE		= BIT(10),
-	/* needed for removable devices */
-	IDE_DFLAG_ATTACH		= BIT(11),
 	IDE_DFLAG_FORCED_GEOM		= BIT(12),
 	/* disallow setting unmask bit */
 	IDE_DFLAG_NO_UNMASK		= BIT(13),
-- 
cgit v1.2.3


From b92b53079aedbfb56bbb9ea360e5119fb563a2a1 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 8 Sep 2020 16:53:47 +0200
Subject: block: remove check_disk_change

Remove the now unused check_disk_change helper.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/block_dev.c        | 20 --------------------
 include/linux/genhd.h |  1 -
 2 files changed, 21 deletions(-)

(limited to 'include/linux')

diff --git a/fs/block_dev.c b/fs/block_dev.c
index c6ac0bd22eca..0b34955b9e36 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1368,26 +1368,6 @@ void revalidate_disk_size(struct gendisk *disk, bool verbose)
 }
 EXPORT_SYMBOL(revalidate_disk_size);
 
-/*
- * This routine checks whether a removable media has been changed,
- * and invalidates all buffer-cache-entries in that case. This
- * is a relatively slow routine, so we have to try to minimize using
- * it. Thus it is called only upon a 'mount' or 'open'. This
- * is the best way of combining speed and utility, I think.
- * People changing diskettes in the middle of an operation deserve
- * to lose :-)
- */
-int check_disk_change(struct block_device *bdev)
-{
-	if (!bdev_check_media_change(bdev))
-		return 0;
-	if (bdev->bd_disk->fops->revalidate_disk)
-		bdev->bd_disk->fops->revalidate_disk(bdev->bd_disk);
-	return 1;
-}
-
-EXPORT_SYMBOL(check_disk_change);
-
 void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors)
 {
 	spin_lock(&bdev->bd_size_lock);
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 322d48a20772..1c97cf84f011 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -370,7 +370,6 @@ int register_blkdev(unsigned int major, const char *name);
 void unregister_blkdev(unsigned int major, const char *name);
 
 void revalidate_disk_size(struct gendisk *disk, bool verbose);
-int check_disk_change(struct block_device *bdev);
 bool bdev_check_media_change(struct block_device *bdev);
 int __invalidate_device(struct block_device *bdev, bool kill_dirty);
 void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors);
-- 
cgit v1.2.3


From 00089c048eb4a8250325efb32a2724fd0da68cce Mon Sep 17 00:00:00 2001
From: Julien Thierry <jthierry@redhat.com>
Date: Fri, 4 Sep 2020 16:30:25 +0100
Subject: objtool: Rename frame.h -> objtool.h

Header frame.h is getting more code annotations to help objtool analyze
object files.

Rename the file to objtool.h.

[ jpoimboe: add objtool.h to MAINTAINERS ]

Signed-off-by: Julien Thierry <jthierry@redhat.com>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
---
 MAINTAINERS                          |  1 +
 arch/x86/include/asm/nospec-branch.h |  2 +-
 arch/x86/kernel/kprobes/core.c       |  2 +-
 arch/x86/kernel/kprobes/opt.c        |  2 +-
 arch/x86/kernel/reboot.c             |  2 +-
 arch/x86/kvm/svm/svm.c               |  2 +-
 arch/x86/kvm/vmx/nested.c            |  2 +-
 arch/x86/kvm/vmx/vmx.c               |  2 +-
 arch/x86/xen/enlighten_pv.c          |  2 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_msg.c  |  3 +--
 include/linux/frame.h                | 35 -----------------------------------
 include/linux/objtool.h              | 35 +++++++++++++++++++++++++++++++++++
 kernel/bpf/core.c                    |  2 +-
 kernel/kexec_core.c                  |  2 +-
 14 files changed, 47 insertions(+), 47 deletions(-)
 delete mode 100644 include/linux/frame.h
 create mode 100644 include/linux/objtool.h

(limited to 'include/linux')

diff --git a/MAINTAINERS b/MAINTAINERS
index e4647c84c987..2605a086eb8a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12481,6 +12481,7 @@ M:	Josh Poimboeuf <jpoimboe@redhat.com>
 M:	Peter Zijlstra <peterz@infradead.org>
 S:	Supported
 F:	tools/objtool/
+F:	include/linux/objtool.h
 
 OCELOT ETHERNET SWITCH DRIVER
 M:	Microchip Linux Driver Support <UNGLinuxDriver@microchip.com>
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index e7752b4038ff..86651e86289d 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -4,7 +4,7 @@
 #define _ASM_X86_NOSPEC_BRANCH_H_
 
 #include <linux/static_key.h>
-#include <linux/frame.h>
+#include <linux/objtool.h>
 
 #include <asm/alternative.h>
 #include <asm/alternative-asm.h>
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index fdadc37d72af..ae2488643029 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -38,9 +38,9 @@
 #include <linux/kdebug.h>
 #include <linux/kallsyms.h>
 #include <linux/ftrace.h>
-#include <linux/frame.h>
 #include <linux/kasan.h>
 #include <linux/moduleloader.h>
+#include <linux/objtool.h>
 #include <linux/vmalloc.h>
 #include <linux/pgtable.h>
 
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index c068e21c2c40..9b1cb8f519b0 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -16,7 +16,7 @@
 #include <linux/kdebug.h>
 #include <linux/kallsyms.h>
 #include <linux/ftrace.h>
-#include <linux/frame.h>
+#include <linux/objtool.h>
 #include <linux/pgtable.h>
 #include <linux/static_call.h>
 
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index a515e2d230b7..db115943e8bd 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -10,7 +10,7 @@
 #include <linux/sched.h>
 #include <linux/tboot.h>
 #include <linux/delay.h>
-#include <linux/frame.h>
+#include <linux/objtool.h>
 #include <linux/pgtable.h>
 #include <acpi/reboot.h>
 #include <asm/io.h>
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 0194336b64a4..17ba613de9a9 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -19,7 +19,7 @@
 #include <linux/trace_events.h>
 #include <linux/slab.h>
 #include <linux/hashtable.h>
-#include <linux/frame.h>
+#include <linux/objtool.h>
 #include <linux/psp-sev.h>
 #include <linux/file.h>
 #include <linux/pagemap.h>
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 23b58c28a1c9..ae4ff7c624a4 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#include <linux/frame.h>
+#include <linux/objtool.h>
 #include <linux/percpu.h>
 
 #include <asm/debugreg.h>
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 819c185adf09..df29fb49b43d 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -13,7 +13,6 @@
  *   Yaniv Kamay  <yaniv@qumranet.com>
  */
 
-#include <linux/frame.h>
 #include <linux/highmem.h>
 #include <linux/hrtimer.h>
 #include <linux/kernel.h>
@@ -22,6 +21,7 @@
 #include <linux/moduleparam.h>
 #include <linux/mod_devicetable.h>
 #include <linux/mm.h>
+#include <linux/objtool.h>
 #include <linux/sched.h>
 #include <linux/sched/smt.h>
 #include <linux/slab.h>
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 22e741e0b10c..58382d26f153 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -32,7 +32,7 @@
 #include <linux/pci.h>
 #include <linux/gfp.h>
 #include <linux/edd.h>
-#include <linux/frame.h>
+#include <linux/objtool.h>
 
 #include <xen/xen.h>
 #include <xen/events.h>
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
index e9f448a5ebb3..15b5bde69324 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
@@ -24,7 +24,7 @@
  *
  */
 
-#include <linux/frame.h>
+#include <linux/objtool.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/slab.h>
@@ -599,4 +599,3 @@ out_open:
 
 	return -EINVAL;
 }
-
diff --git a/include/linux/frame.h b/include/linux/frame.h
deleted file mode 100644
index 303cda600e56..000000000000
--- a/include/linux/frame.h
+++ /dev/null
@@ -1,35 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_FRAME_H
-#define _LINUX_FRAME_H
-
-#ifdef CONFIG_STACK_VALIDATION
-/*
- * This macro marks the given function's stack frame as "non-standard", which
- * tells objtool to ignore the function when doing stack metadata validation.
- * It should only be used in special cases where you're 100% sure it won't
- * affect the reliability of frame pointers and kernel stack traces.
- *
- * For more information, see tools/objtool/Documentation/stack-validation.txt.
- */
-#define STACK_FRAME_NON_STANDARD(func) \
-	static void __used __section(.discard.func_stack_frame_non_standard) \
-		*__func_stack_frame_non_standard_##func = func
-
-/*
- * This macro indicates that the following intra-function call is valid.
- * Any non-annotated intra-function call will cause objtool to issue a warning.
- */
-#define ANNOTATE_INTRA_FUNCTION_CALL				\
-	999:							\
-	.pushsection .discard.intra_function_calls;		\
-	.long 999b;						\
-	.popsection;
-
-#else /* !CONFIG_STACK_VALIDATION */
-
-#define STACK_FRAME_NON_STANDARD(func)
-#define ANNOTATE_INTRA_FUNCTION_CALL
-
-#endif /* CONFIG_STACK_VALIDATION */
-
-#endif /* _LINUX_FRAME_H */
diff --git a/include/linux/objtool.h b/include/linux/objtool.h
new file mode 100644
index 000000000000..358175c9c2b5
--- /dev/null
+++ b/include/linux/objtool.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_OBJTOOL_H
+#define _LINUX_OBJTOOL_H
+
+#ifdef CONFIG_STACK_VALIDATION
+/*
+ * This macro marks the given function's stack frame as "non-standard", which
+ * tells objtool to ignore the function when doing stack metadata validation.
+ * It should only be used in special cases where you're 100% sure it won't
+ * affect the reliability of frame pointers and kernel stack traces.
+ *
+ * For more information, see tools/objtool/Documentation/stack-validation.txt.
+ */
+#define STACK_FRAME_NON_STANDARD(func) \
+	static void __used __section(.discard.func_stack_frame_non_standard) \
+		*__func_stack_frame_non_standard_##func = func
+
+/*
+ * This macro indicates that the following intra-function call is valid.
+ * Any non-annotated intra-function call will cause objtool to issue a warning.
+ */
+#define ANNOTATE_INTRA_FUNCTION_CALL				\
+	999:							\
+	.pushsection .discard.intra_function_calls;		\
+	.long 999b;						\
+	.popsection;
+
+#else /* !CONFIG_STACK_VALIDATION */
+
+#define STACK_FRAME_NON_STANDARD(func)
+#define ANNOTATE_INTRA_FUNCTION_CALL
+
+#endif /* CONFIG_STACK_VALIDATION */
+
+#endif /* _LINUX_OBJTOOL_H */
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index ed0b3578867c..03e284873644 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -25,7 +25,7 @@
 #include <linux/moduleloader.h>
 #include <linux/bpf.h>
 #include <linux/btf.h>
-#include <linux/frame.h>
+#include <linux/objtool.h>
 #include <linux/rbtree_latch.h>
 #include <linux/kallsyms.h>
 #include <linux/rcupdate.h>
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index c19c0dad1ebe..c5e5e5a11535 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -36,7 +36,7 @@
 #include <linux/syscore_ops.h>
 #include <linux/compiler.h>
 #include <linux/hugetlb.h>
-#include <linux/frame.h>
+#include <linux/objtool.h>
 
 #include <asm/page.h>
 #include <asm/sections.h>
-- 
cgit v1.2.3


From 5567c6c39f3404e4492c18c0c1abff5556684f6e Mon Sep 17 00:00:00 2001
From: Julien Thierry <jthierry@redhat.com>
Date: Fri, 4 Sep 2020 16:30:26 +0100
Subject: objtool: Only include valid definitions depending on source file type

Header include/linux/objtool.h contains both C and assembly definition that
are visible regardless of the file including them.

Place definition under conditional __ASSEMBLY__.

Reviewed-by: Miroslav Benes <mbenes@suse.cz>
Signed-off-by: Julien Thierry <jthierry@redhat.com>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
---
 include/linux/objtool.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/objtool.h b/include/linux/objtool.h
index 358175c9c2b5..15e9997a9fb4 100644
--- a/include/linux/objtool.h
+++ b/include/linux/objtool.h
@@ -3,6 +3,8 @@
 #define _LINUX_OBJTOOL_H
 
 #ifdef CONFIG_STACK_VALIDATION
+
+#ifndef __ASSEMBLY__
 /*
  * This macro marks the given function's stack frame as "non-standard", which
  * tells objtool to ignore the function when doing stack metadata validation.
@@ -15,6 +17,8 @@
 	static void __used __section(.discard.func_stack_frame_non_standard) \
 		*__func_stack_frame_non_standard_##func = func
 
+#else /* __ASSEMBLY__ */
+
 /*
  * This macro indicates that the following intra-function call is valid.
  * Any non-annotated intra-function call will cause objtool to issue a warning.
@@ -25,6 +29,8 @@
 	.long 999b;						\
 	.popsection;
 
+#endif /* __ASSEMBLY__ */
+
 #else /* !CONFIG_STACK_VALIDATION */
 
 #define STACK_FRAME_NON_STANDARD(func)
-- 
cgit v1.2.3


From ee819aedf34a8f35cd54ee3967c7beb4d1d4a635 Mon Sep 17 00:00:00 2001
From: Julien Thierry <jthierry@redhat.com>
Date: Fri, 4 Sep 2020 16:30:27 +0100
Subject: objtool: Make unwind hint definitions available to other
 architectures

Unwind hints are useful to provide objtool with information about stack
states in non-standard functions/code.

While the type of information being provided might be very arch
specific, the mechanism to provide the information can be useful for
other architectures.

Move the relevant unwint hint definitions for all architectures to
see.

[ jpoimboe: REGS_IRET -> REGS_PARTIAL ]

Signed-off-by: Julien Thierry <jthierry@redhat.com>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
---
 arch/x86/include/asm/orc_types.h       |  34 ---------
 arch/x86/include/asm/unwind_hints.h    |  56 +++-----------
 arch/x86/kernel/unwind_orc.c           |  11 +--
 include/linux/objtool.h                |  88 ++++++++++++++++++++++
 tools/arch/x86/include/asm/orc_types.h |  34 ---------
 tools/include/linux/objtool.h          | 129 +++++++++++++++++++++++++++++++++
 tools/objtool/check.c                  |   4 +-
 tools/objtool/orc_dump.c               |   9 ++-
 tools/objtool/orc_gen.c                |   5 +-
 tools/objtool/sync-check.sh            |   4 +-
 10 files changed, 249 insertions(+), 125 deletions(-)
 create mode 100644 tools/include/linux/objtool.h

(limited to 'include/linux')

diff --git a/arch/x86/include/asm/orc_types.h b/arch/x86/include/asm/orc_types.h
index d25534940bde..fdbffec4cfde 100644
--- a/arch/x86/include/asm/orc_types.h
+++ b/arch/x86/include/asm/orc_types.h
@@ -39,27 +39,6 @@
 #define ORC_REG_SP_INDIRECT		9
 #define ORC_REG_MAX			15
 
-/*
- * ORC_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP (the
- * caller's SP right before it made the call).  Used for all callable
- * functions, i.e. all C code and all callable asm functions.
- *
- * ORC_TYPE_REGS: Used in entry code to indicate that sp_reg+sp_offset points
- * to a fully populated pt_regs from a syscall, interrupt, or exception.
- *
- * ORC_TYPE_REGS_IRET: Used in entry code to indicate that sp_reg+sp_offset
- * points to the iret return frame.
- *
- * The UNWIND_HINT macros are used only for the unwind_hint struct.  They
- * aren't used in struct orc_entry due to size and complexity constraints.
- * Objtool converts them to real types when it converts the hints to orc
- * entries.
- */
-#define ORC_TYPE_CALL			0
-#define ORC_TYPE_REGS			1
-#define ORC_TYPE_REGS_IRET		2
-#define UNWIND_HINT_TYPE_RET_OFFSET	3
-
 #ifndef __ASSEMBLY__
 /*
  * This struct is more or less a vastly simplified version of the DWARF Call
@@ -78,19 +57,6 @@ struct orc_entry {
 	unsigned	end:1;
 } __packed;
 
-/*
- * This struct is used by asm and inline asm code to manually annotate the
- * location of registers on the stack for the ORC unwinder.
- *
- * Type can be either ORC_TYPE_* or UNWIND_HINT_TYPE_*.
- */
-struct unwind_hint {
-	u32		ip;
-	s16		sp_offset;
-	u8		sp_reg;
-	u8		type;
-	u8		end;
-};
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ORC_TYPES_H */
diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h
index 7d903fdb3f43..664d4610d700 100644
--- a/arch/x86/include/asm/unwind_hints.h
+++ b/arch/x86/include/asm/unwind_hints.h
@@ -1,51 +1,17 @@
 #ifndef _ASM_X86_UNWIND_HINTS_H
 #define _ASM_X86_UNWIND_HINTS_H
 
+#include <linux/objtool.h>
+
 #include "orc_types.h"
 
 #ifdef __ASSEMBLY__
 
-/*
- * In asm, there are two kinds of code: normal C-type callable functions and
- * the rest.  The normal callable functions can be called by other code, and
- * don't do anything unusual with the stack.  Such normal callable functions
- * are annotated with the ENTRY/ENDPROC macros.  Most asm code falls in this
- * category.  In this case, no special debugging annotations are needed because
- * objtool can automatically generate the ORC data for the ORC unwinder to read
- * at runtime.
- *
- * Anything which doesn't fall into the above category, such as syscall and
- * interrupt handlers, tends to not be called directly by other functions, and
- * often does unusual non-C-function-type things with the stack pointer.  Such
- * code needs to be annotated such that objtool can understand it.  The
- * following CFI hint macros are for this type of code.
- *
- * These macros provide hints to objtool about the state of the stack at each
- * instruction.  Objtool starts from the hints and follows the code flow,
- * making automatic CFI adjustments when it sees pushes and pops, filling out
- * the debuginfo as necessary.  It will also warn if it sees any
- * inconsistencies.
- */
-.macro UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=0 type=ORC_TYPE_CALL end=0
-#ifdef CONFIG_STACK_VALIDATION
-.Lunwind_hint_ip_\@:
-	.pushsection .discard.unwind_hints
-		/* struct unwind_hint */
-		.long .Lunwind_hint_ip_\@ - .
-		.short \sp_offset
-		.byte \sp_reg
-		.byte \type
-		.byte \end
-		.balign 4
-	.popsection
-#endif
-.endm
-
 .macro UNWIND_HINT_EMPTY
-	UNWIND_HINT sp_reg=ORC_REG_UNDEFINED end=1
+	UNWIND_HINT sp_reg=ORC_REG_UNDEFINED type=UNWIND_HINT_TYPE_CALL end=1
 .endm
 
-.macro UNWIND_HINT_REGS base=%rsp offset=0 indirect=0 extra=1 iret=0
+.macro UNWIND_HINT_REGS base=%rsp offset=0 indirect=0 extra=1 partial=0
 	.if \base == %rsp
 		.if \indirect
 			.set sp_reg, ORC_REG_SP_INDIRECT
@@ -66,24 +32,24 @@
 
 	.set sp_offset, \offset
 
-	.if \iret
-		.set type, ORC_TYPE_REGS_IRET
+	.if \partial
+		.set type, UNWIND_HINT_TYPE_REGS_PARTIAL
 	.elseif \extra == 0
-		.set type, ORC_TYPE_REGS_IRET
+		.set type, UNWIND_HINT_TYPE_REGS_PARTIAL
 		.set sp_offset, \offset + (16*8)
 	.else
-		.set type, ORC_TYPE_REGS
+		.set type, UNWIND_HINT_TYPE_REGS
 	.endif
 
 	UNWIND_HINT sp_reg=sp_reg sp_offset=sp_offset type=type
 .endm
 
 .macro UNWIND_HINT_IRET_REGS base=%rsp offset=0
-	UNWIND_HINT_REGS base=\base offset=\offset iret=1
+	UNWIND_HINT_REGS base=\base offset=\offset partial=1
 .endm
 
 .macro UNWIND_HINT_FUNC sp_offset=8
-	UNWIND_HINT sp_offset=\sp_offset
+	UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=\sp_offset type=UNWIND_HINT_TYPE_CALL
 .endm
 
 /*
@@ -92,7 +58,7 @@
  * initial_func_cfi.
  */
 .macro UNWIND_HINT_RET_OFFSET sp_offset=8
-	UNWIND_HINT type=UNWIND_HINT_TYPE_RET_OFFSET sp_offset=\sp_offset
+	UNWIND_HINT sp_reg=ORC_REG_SP type=UNWIND_HINT_TYPE_RET_OFFSET sp_offset=\sp_offset
 .endm
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index ec88bbe08a32..6a339ce328e0 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
+#include <linux/objtool.h>
 #include <linux/module.h>
 #include <linux/sort.h>
 #include <asm/ptrace.h>
@@ -127,12 +128,12 @@ static struct orc_entry null_orc_entry = {
 	.sp_offset = sizeof(long),
 	.sp_reg = ORC_REG_SP,
 	.bp_reg = ORC_REG_UNDEFINED,
-	.type = ORC_TYPE_CALL
+	.type = UNWIND_HINT_TYPE_CALL
 };
 
 /* Fake frame pointer entry -- used as a fallback for generated code */
 static struct orc_entry orc_fp_entry = {
-	.type		= ORC_TYPE_CALL,
+	.type		= UNWIND_HINT_TYPE_CALL,
 	.sp_reg		= ORC_REG_BP,
 	.sp_offset	= 16,
 	.bp_reg		= ORC_REG_PREV_SP,
@@ -531,7 +532,7 @@ bool unwind_next_frame(struct unwind_state *state)
 
 	/* Find IP, SP and possibly regs: */
 	switch (orc->type) {
-	case ORC_TYPE_CALL:
+	case UNWIND_HINT_TYPE_CALL:
 		ip_p = sp - sizeof(long);
 
 		if (!deref_stack_reg(state, ip_p, &state->ip))
@@ -546,7 +547,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		state->signal = false;
 		break;
 
-	case ORC_TYPE_REGS:
+	case UNWIND_HINT_TYPE_REGS:
 		if (!deref_stack_regs(state, sp, &state->ip, &state->sp)) {
 			orc_warn_current("can't access registers at %pB\n",
 					 (void *)orig_ip);
@@ -559,7 +560,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		state->signal = true;
 		break;
 
-	case ORC_TYPE_REGS_IRET:
+	case UNWIND_HINT_TYPE_REGS_PARTIAL:
 		if (!deref_stack_iret_regs(state, sp, &state->ip, &state->sp)) {
 			orc_warn_current("can't access iret registers at %pB\n",
 					 (void *)orig_ip);
diff --git a/include/linux/objtool.h b/include/linux/objtool.h
index 15e9997a9fb4..ab82c793c897 100644
--- a/include/linux/objtool.h
+++ b/include/linux/objtool.h
@@ -2,9 +2,55 @@
 #ifndef _LINUX_OBJTOOL_H
 #define _LINUX_OBJTOOL_H
 
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+
+/*
+ * This struct is used by asm and inline asm code to manually annotate the
+ * location of registers on the stack.
+ */
+struct unwind_hint {
+	u32		ip;
+	s16		sp_offset;
+	u8		sp_reg;
+	u8		type;
+	u8		end;
+};
+#endif
+
+/*
+ * UNWIND_HINT_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP
+ * (the caller's SP right before it made the call).  Used for all callable
+ * functions, i.e. all C code and all callable asm functions.
+ *
+ * UNWIND_HINT_TYPE_REGS: Used in entry code to indicate that sp_reg+sp_offset
+ * points to a fully populated pt_regs from a syscall, interrupt, or exception.
+ *
+ * UNWIND_HINT_TYPE_REGS_PARTIAL: Used in entry code to indicate that
+ * sp_reg+sp_offset points to the iret return frame.
+ */
+#define UNWIND_HINT_TYPE_CALL		0
+#define UNWIND_HINT_TYPE_REGS		1
+#define UNWIND_HINT_TYPE_REGS_PARTIAL	2
+#define UNWIND_HINT_TYPE_RET_OFFSET	3
+
 #ifdef CONFIG_STACK_VALIDATION
 
 #ifndef __ASSEMBLY__
+
+#define UNWIND_HINT(sp_reg, sp_offset, type, end)		\
+	"987: \n\t"						\
+	".pushsection .discard.unwind_hints\n\t"		\
+	/* struct unwind_hint */				\
+	".long 987b - .\n\t"					\
+	".short " __stringify(sp_offset) "\n\t"			\
+	".byte " __stringify(sp_reg) "\n\t"			\
+	".byte " __stringify(type) "\n\t"			\
+	".byte " __stringify(end) "\n\t"			\
+	".balign 4 \n\t"					\
+	".popsection\n\t"
+
 /*
  * This macro marks the given function's stack frame as "non-standard", which
  * tells objtool to ignore the function when doing stack metadata validation.
@@ -29,12 +75,54 @@
 	.long 999b;						\
 	.popsection;
 
+/*
+ * In asm, there are two kinds of code: normal C-type callable functions and
+ * the rest.  The normal callable functions can be called by other code, and
+ * don't do anything unusual with the stack.  Such normal callable functions
+ * are annotated with the ENTRY/ENDPROC macros.  Most asm code falls in this
+ * category.  In this case, no special debugging annotations are needed because
+ * objtool can automatically generate the ORC data for the ORC unwinder to read
+ * at runtime.
+ *
+ * Anything which doesn't fall into the above category, such as syscall and
+ * interrupt handlers, tends to not be called directly by other functions, and
+ * often does unusual non-C-function-type things with the stack pointer.  Such
+ * code needs to be annotated such that objtool can understand it.  The
+ * following CFI hint macros are for this type of code.
+ *
+ * These macros provide hints to objtool about the state of the stack at each
+ * instruction.  Objtool starts from the hints and follows the code flow,
+ * making automatic CFI adjustments when it sees pushes and pops, filling out
+ * the debuginfo as necessary.  It will also warn if it sees any
+ * inconsistencies.
+ */
+.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0
+.Lunwind_hint_ip_\@:
+	.pushsection .discard.unwind_hints
+		/* struct unwind_hint */
+		.long .Lunwind_hint_ip_\@ - .
+		.short \sp_offset
+		.byte \sp_reg
+		.byte \type
+		.byte \end
+		.balign 4
+	.popsection
+.endm
+
 #endif /* __ASSEMBLY__ */
 
 #else /* !CONFIG_STACK_VALIDATION */
 
+#ifndef __ASSEMBLY__
+
+#define UNWIND_HINT(sp_reg, sp_offset, type, end)	\
+	"\n\t"
 #define STACK_FRAME_NON_STANDARD(func)
+#else
 #define ANNOTATE_INTRA_FUNCTION_CALL
+.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0
+.endm
+#endif
 
 #endif /* CONFIG_STACK_VALIDATION */
 
diff --git a/tools/arch/x86/include/asm/orc_types.h b/tools/arch/x86/include/asm/orc_types.h
index d25534940bde..fdbffec4cfde 100644
--- a/tools/arch/x86/include/asm/orc_types.h
+++ b/tools/arch/x86/include/asm/orc_types.h
@@ -39,27 +39,6 @@
 #define ORC_REG_SP_INDIRECT		9
 #define ORC_REG_MAX			15
 
-/*
- * ORC_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP (the
- * caller's SP right before it made the call).  Used for all callable
- * functions, i.e. all C code and all callable asm functions.
- *
- * ORC_TYPE_REGS: Used in entry code to indicate that sp_reg+sp_offset points
- * to a fully populated pt_regs from a syscall, interrupt, or exception.
- *
- * ORC_TYPE_REGS_IRET: Used in entry code to indicate that sp_reg+sp_offset
- * points to the iret return frame.
- *
- * The UNWIND_HINT macros are used only for the unwind_hint struct.  They
- * aren't used in struct orc_entry due to size and complexity constraints.
- * Objtool converts them to real types when it converts the hints to orc
- * entries.
- */
-#define ORC_TYPE_CALL			0
-#define ORC_TYPE_REGS			1
-#define ORC_TYPE_REGS_IRET		2
-#define UNWIND_HINT_TYPE_RET_OFFSET	3
-
 #ifndef __ASSEMBLY__
 /*
  * This struct is more or less a vastly simplified version of the DWARF Call
@@ -78,19 +57,6 @@ struct orc_entry {
 	unsigned	end:1;
 } __packed;
 
-/*
- * This struct is used by asm and inline asm code to manually annotate the
- * location of registers on the stack for the ORC unwinder.
- *
- * Type can be either ORC_TYPE_* or UNWIND_HINT_TYPE_*.
- */
-struct unwind_hint {
-	u32		ip;
-	s16		sp_offset;
-	u8		sp_reg;
-	u8		type;
-	u8		end;
-};
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ORC_TYPES_H */
diff --git a/tools/include/linux/objtool.h b/tools/include/linux/objtool.h
new file mode 100644
index 000000000000..ab82c793c897
--- /dev/null
+++ b/tools/include/linux/objtool.h
@@ -0,0 +1,129 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_OBJTOOL_H
+#define _LINUX_OBJTOOL_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+
+/*
+ * This struct is used by asm and inline asm code to manually annotate the
+ * location of registers on the stack.
+ */
+struct unwind_hint {
+	u32		ip;
+	s16		sp_offset;
+	u8		sp_reg;
+	u8		type;
+	u8		end;
+};
+#endif
+
+/*
+ * UNWIND_HINT_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP
+ * (the caller's SP right before it made the call).  Used for all callable
+ * functions, i.e. all C code and all callable asm functions.
+ *
+ * UNWIND_HINT_TYPE_REGS: Used in entry code to indicate that sp_reg+sp_offset
+ * points to a fully populated pt_regs from a syscall, interrupt, or exception.
+ *
+ * UNWIND_HINT_TYPE_REGS_PARTIAL: Used in entry code to indicate that
+ * sp_reg+sp_offset points to the iret return frame.
+ */
+#define UNWIND_HINT_TYPE_CALL		0
+#define UNWIND_HINT_TYPE_REGS		1
+#define UNWIND_HINT_TYPE_REGS_PARTIAL	2
+#define UNWIND_HINT_TYPE_RET_OFFSET	3
+
+#ifdef CONFIG_STACK_VALIDATION
+
+#ifndef __ASSEMBLY__
+
+#define UNWIND_HINT(sp_reg, sp_offset, type, end)		\
+	"987: \n\t"						\
+	".pushsection .discard.unwind_hints\n\t"		\
+	/* struct unwind_hint */				\
+	".long 987b - .\n\t"					\
+	".short " __stringify(sp_offset) "\n\t"			\
+	".byte " __stringify(sp_reg) "\n\t"			\
+	".byte " __stringify(type) "\n\t"			\
+	".byte " __stringify(end) "\n\t"			\
+	".balign 4 \n\t"					\
+	".popsection\n\t"
+
+/*
+ * This macro marks the given function's stack frame as "non-standard", which
+ * tells objtool to ignore the function when doing stack metadata validation.
+ * It should only be used in special cases where you're 100% sure it won't
+ * affect the reliability of frame pointers and kernel stack traces.
+ *
+ * For more information, see tools/objtool/Documentation/stack-validation.txt.
+ */
+#define STACK_FRAME_NON_STANDARD(func) \
+	static void __used __section(.discard.func_stack_frame_non_standard) \
+		*__func_stack_frame_non_standard_##func = func
+
+#else /* __ASSEMBLY__ */
+
+/*
+ * This macro indicates that the following intra-function call is valid.
+ * Any non-annotated intra-function call will cause objtool to issue a warning.
+ */
+#define ANNOTATE_INTRA_FUNCTION_CALL				\
+	999:							\
+	.pushsection .discard.intra_function_calls;		\
+	.long 999b;						\
+	.popsection;
+
+/*
+ * In asm, there are two kinds of code: normal C-type callable functions and
+ * the rest.  The normal callable functions can be called by other code, and
+ * don't do anything unusual with the stack.  Such normal callable functions
+ * are annotated with the ENTRY/ENDPROC macros.  Most asm code falls in this
+ * category.  In this case, no special debugging annotations are needed because
+ * objtool can automatically generate the ORC data for the ORC unwinder to read
+ * at runtime.
+ *
+ * Anything which doesn't fall into the above category, such as syscall and
+ * interrupt handlers, tends to not be called directly by other functions, and
+ * often does unusual non-C-function-type things with the stack pointer.  Such
+ * code needs to be annotated such that objtool can understand it.  The
+ * following CFI hint macros are for this type of code.
+ *
+ * These macros provide hints to objtool about the state of the stack at each
+ * instruction.  Objtool starts from the hints and follows the code flow,
+ * making automatic CFI adjustments when it sees pushes and pops, filling out
+ * the debuginfo as necessary.  It will also warn if it sees any
+ * inconsistencies.
+ */
+.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0
+.Lunwind_hint_ip_\@:
+	.pushsection .discard.unwind_hints
+		/* struct unwind_hint */
+		.long .Lunwind_hint_ip_\@ - .
+		.short \sp_offset
+		.byte \sp_reg
+		.byte \type
+		.byte \end
+		.balign 4
+	.popsection
+.endm
+
+#endif /* __ASSEMBLY__ */
+
+#else /* !CONFIG_STACK_VALIDATION */
+
+#ifndef __ASSEMBLY__
+
+#define UNWIND_HINT(sp_reg, sp_offset, type, end)	\
+	"\n\t"
+#define STACK_FRAME_NON_STANDARD(func)
+#else
+#define ANNOTATE_INTRA_FUNCTION_CALL
+.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0
+.endm
+#endif
+
+#endif /* CONFIG_STACK_VALIDATION */
+
+#endif /* _LINUX_OBJTOOL_H */
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index a94ad88d036c..95c6e0d31c0a 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -14,6 +14,7 @@
 #include "warn.h"
 #include "arch_elf.h"
 
+#include <linux/objtool.h>
 #include <linux/hashtable.h>
 #include <linux/kernel.h>
 #include <linux/static_call_types.h>
@@ -1805,7 +1806,8 @@ static int update_cfi_state(struct instruction *insn, struct cfi_state *cfi,
 		return 0;
 	}
 
-	if (cfi->type == ORC_TYPE_REGS || cfi->type == ORC_TYPE_REGS_IRET)
+	if (cfi->type == UNWIND_HINT_TYPE_REGS ||
+	    cfi->type == UNWIND_HINT_TYPE_REGS_PARTIAL)
 		return update_cfi_state_regs(insn, cfi, op);
 
 	switch (op->dest.type) {
diff --git a/tools/objtool/orc_dump.c b/tools/objtool/orc_dump.c
index fca46e006fc2..5e6a95368d35 100644
--- a/tools/objtool/orc_dump.c
+++ b/tools/objtool/orc_dump.c
@@ -4,6 +4,7 @@
  */
 
 #include <unistd.h>
+#include <linux/objtool.h>
 #include <asm/orc_types.h>
 #include "objtool.h"
 #include "warn.h"
@@ -37,12 +38,12 @@ static const char *reg_name(unsigned int reg)
 static const char *orc_type_name(unsigned int type)
 {
 	switch (type) {
-	case ORC_TYPE_CALL:
+	case UNWIND_HINT_TYPE_CALL:
 		return "call";
-	case ORC_TYPE_REGS:
+	case UNWIND_HINT_TYPE_REGS:
 		return "regs";
-	case ORC_TYPE_REGS_IRET:
-		return "iret";
+	case UNWIND_HINT_TYPE_REGS_PARTIAL:
+		return "regs (partial)";
 	default:
 		return "?";
 	}
diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c
index 22fe4398197f..235663b96adc 100644
--- a/tools/objtool/orc_gen.c
+++ b/tools/objtool/orc_gen.c
@@ -6,6 +6,9 @@
 #include <stdlib.h>
 #include <string.h>
 
+#include <linux/objtool.h>
+#include <asm/orc_types.h>
+
 #include "check.h"
 #include "warn.h"
 
@@ -146,7 +149,7 @@ int create_orc_sections(struct objtool_file *file)
 	struct orc_entry empty = {
 		.sp_reg = ORC_REG_UNDEFINED,
 		.bp_reg  = ORC_REG_UNDEFINED,
-		.type    = ORC_TYPE_CALL,
+		.type    = UNWIND_HINT_TYPE_CALL,
 	};
 
 	sec = find_section_by_name(file->elf, ".orc_unwind");
diff --git a/tools/objtool/sync-check.sh b/tools/objtool/sync-check.sh
index cea1c12607b9..606a4b5e929f 100755
--- a/tools/objtool/sync-check.sh
+++ b/tools/objtool/sync-check.sh
@@ -6,8 +6,10 @@ if [ -z "$SRCARCH" ]; then
 	exit 1
 fi
 
+FILES="include/linux/objtool.h"
+
 if [ "$SRCARCH" = "x86" ]; then
-FILES="
+FILES="$FILES
 arch/x86/include/asm/inat_types.h
 arch/x86/include/asm/orc_types.h
 arch/x86/include/asm/emulate_prefix.h
-- 
cgit v1.2.3


From 0feea33d79825d05b5ede30947db4df34722b463 Mon Sep 17 00:00:00 2001
From: Douglas Anderson <dianders@chromium.org>
Date: Wed, 22 Jul 2020 15:01:20 -0700
Subject: soc: qcom-geni-se: Don't use relaxed writes when writing commands

Writing the command is the final step in kicking off a transfer.
Let's use writel() to ensure that any other memory accesses are done
before the command kicks off.  It's expected that this is mostly
relevant if we're in DMA mode but since it doesn't appear to regress
performance in a measurable way [1] even in PIO mode and it's easier
to reason about then let's just always use it.

NOTE: this patch came about due to code inspection.  No actual
problems were observed that this patch fixes.

[1] Tested by timing "flashrom -p ec" on a Chromebook which stresses
GENI SPI a lot.

Reviewed-by: Mukesh Kumar Savaliya <msavaliy@codeaurora.org>
Reviewed-by: Akash Asthana <akashast@codeaurora.org>
Reviewed-by: Stephen Boyd <swboyd@chromium.org>
Suggested-by: Stephen Boyd <swboyd@chromium.org>
Signed-off-by: Douglas Anderson <dianders@chromium.org>
Link: https://lore.kernel.org/r/20200722150113.1.Ia50ab5cb8a6d3a73d302e6bdc25542d48ffd27f4@changeid
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 include/linux/qcom-geni-se.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/qcom-geni-se.h b/include/linux/qcom-geni-se.h
index 8f385fbe5a0e..ae4a8a766b69 100644
--- a/include/linux/qcom-geni-se.h
+++ b/include/linux/qcom-geni-se.h
@@ -296,7 +296,7 @@ static inline void geni_se_setup_m_cmd(struct geni_se *se, u32 cmd, u32 params)
 	u32 m_cmd;
 
 	m_cmd = (cmd << M_OPCODE_SHFT) | (params & M_PARAMS_MSK);
-	writel_relaxed(m_cmd, se->base + SE_GENI_M_CMD0);
+	writel(m_cmd, se->base + SE_GENI_M_CMD0);
 }
 
 /**
@@ -316,7 +316,7 @@ static inline void geni_se_setup_s_cmd(struct geni_se *se, u32 cmd, u32 params)
 	s_cmd &= ~(S_OPCODE_MSK | S_PARAMS_MSK);
 	s_cmd |= (cmd << S_OPCODE_SHFT);
 	s_cmd |= (params & S_PARAMS_MSK);
-	writel_relaxed(s_cmd, se->base + SE_GENI_S_CMD0);
+	writel(s_cmd, se->base + SE_GENI_S_CMD0);
 }
 
 /**
-- 
cgit v1.2.3


From 5198d545dba8ad893f5e5a029ca8d43ee7bcf011 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 9 Sep 2020 10:37:51 -0700
Subject: net: remove napi_hash_del() from driver-facing API

We allow drivers to call napi_hash_del() before calling
netif_napi_del() to batch RCU grace periods. This makes
the API asymmetric and leaks internal implementation details.
Soon we will want the grace period to protect more than just
the NAPI hash table.

Restructure the API and have drivers call a new function -
__netif_napi_del() if they want to take care of RCU waits.

Note that only core was checking the return status from
napi_hash_del() so the new helper does not report if the
NAPI was actually deleted.

Some notes on driver oddness:
 - veth observed the grace period before calling netif_napi_del()
   but that should not matter
 - myri10ge observed normal RCU flavor
 - bnx2x and enic did not actually observe the grace period
   (unless they did so implicitly)
 - virtio_net and enic only unhashed Rx NAPIs

The last two points seem to indicate that the calls to
napi_hash_del() were a left over rather than an optimization.
Regardless, it's easy enough to correct them.

This patch may introduce extra synchronize_net() calls for
interfaces which set NAPI_STATE_NO_BUSY_POLL and depend on
free_netdev() to call netif_napi_del(). This seems inevitable
since we want to use RCU for netpoll dev->napi_list traversal,
and almost no drivers set IFF_DISABLE_NETPOLL.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h  |  8 +++---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c        |  5 ++--
 drivers/net/ethernet/cisco/enic/enic_main.c      | 12 +++++----
 drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c     |  4 +--
 drivers/net/ethernet/myricom/myri10ge/myri10ge.c |  5 ++--
 drivers/net/veth.c                               |  3 +--
 drivers/net/virtio_net.c                         |  7 +++---
 include/linux/netdevice.h                        | 32 ++++++++++++------------
 net/core/dev.c                                   | 19 +++++---------
 9 files changed, 43 insertions(+), 52 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index 7e4c93be4451..d8b1824c334d 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -825,9 +825,9 @@ static inline void bnx2x_del_all_napi_cnic(struct bnx2x *bp)
 	int i;
 
 	for_each_rx_queue_cnic(bp, i) {
-		napi_hash_del(&bnx2x_fp(bp, i, napi));
-		netif_napi_del(&bnx2x_fp(bp, i, napi));
+		__netif_napi_del(&bnx2x_fp(bp, i, napi));
 	}
+	synchronize_net();
 }
 
 static inline void bnx2x_del_all_napi(struct bnx2x *bp)
@@ -835,9 +835,9 @@ static inline void bnx2x_del_all_napi(struct bnx2x *bp)
 	int i;
 
 	for_each_eth_queue(bp, i) {
-		napi_hash_del(&bnx2x_fp(bp, i, napi));
-		netif_napi_del(&bnx2x_fp(bp, i, napi));
+		__netif_napi_del(&bnx2x_fp(bp, i, napi));
 	}
+	synchronize_net();
 }
 
 int bnx2x_set_int_mode(struct bnx2x *bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index b167066af450..53f64ca673c3 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -8634,10 +8634,9 @@ static void bnxt_del_napi(struct bnxt *bp)
 	for (i = 0; i < bp->cp_nr_rings; i++) {
 		struct bnxt_napi *bnapi = bp->bnapi[i];
 
-		napi_hash_del(&bnapi->napi);
-		netif_napi_del(&bnapi->napi);
+		__netif_napi_del(&bnapi->napi);
 	}
-	/* We called napi_hash_del() before netif_napi_del(), we need
+	/* We called __netif_napi_del(), we need
 	 * to respect an RCU grace period before freeing napi structures.
 	 */
 	synchronize_net();
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index a4e307636f5a..4f0329d8778f 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -2529,13 +2529,15 @@ static void enic_dev_deinit(struct enic *enic)
 {
 	unsigned int i;
 
-	for (i = 0; i < enic->rq_count; i++) {
-		napi_hash_del(&enic->napi[i]);
-		netif_napi_del(&enic->napi[i]);
-	}
+	for (i = 0; i < enic->rq_count; i++)
+		__netif_napi_del(&enic->napi[i]);
+
 	if (vnic_dev_get_intr_mode(enic->vdev) == VNIC_DEV_INTR_MODE_MSIX)
 		for (i = 0; i < enic->wq_count; i++)
-			netif_napi_del(&enic->napi[enic_cq_wq(enic, i)]);
+			__netif_napi_del(&enic->napi[enic_cq_wq(enic, i)]);
+
+	/* observe RCU grace period after __netif_napi_del() calls */
+	synchronize_net();
 
 	enic_free_vnic_resources(enic);
 	enic_clear_intr_mode(enic);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
index 2e35c5706cf1..df389a11d3af 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
@@ -1029,10 +1029,10 @@ static void ixgbe_free_q_vector(struct ixgbe_adapter *adapter, int v_idx)
 		WRITE_ONCE(adapter->rx_ring[ring->queue_index], NULL);
 
 	adapter->q_vector[v_idx] = NULL;
-	napi_hash_del(&q_vector->napi);
-	netif_napi_del(&q_vector->napi);
+	__netif_napi_del(&q_vector->napi);
 
 	/*
+	 * after a call to __netif_napi_del() napi may still be used and
 	 * ixgbe_get_stats64() might access the rings on this vector,
 	 * we must wait a grace period before freeing it.
 	 */
diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
index 4a5beafa0493..1634ca6d4a8f 100644
--- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
+++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
@@ -3543,11 +3543,10 @@ static void myri10ge_free_slices(struct myri10ge_priv *mgp)
 					  ss->fw_stats, ss->fw_stats_bus);
 			ss->fw_stats = NULL;
 		}
-		napi_hash_del(&ss->napi);
-		netif_napi_del(&ss->napi);
+		__netif_napi_del(&ss->napi);
 	}
 	/* Wait till napi structs are no longer used, and then free ss. */
-	synchronize_rcu();
+	synchronize_net();
 	kfree(mgp->ss);
 	mgp->ss = NULL;
 }
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 7de8f0ea3f6b..091e5b4ba042 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -897,14 +897,13 @@ static void veth_napi_del(struct net_device *dev)
 		struct veth_rq *rq = &priv->rq[i];
 
 		napi_disable(&rq->xdp_napi);
-		napi_hash_del(&rq->xdp_napi);
+		__netif_napi_del(&rq->xdp_napi);
 	}
 	synchronize_net();
 
 	for (i = 0; i < dev->real_num_rx_queues; i++) {
 		struct veth_rq *rq = &priv->rq[i];
 
-		netif_napi_del(&rq->xdp_napi);
 		rq->rx_notify_masked = false;
 		ptr_ring_cleanup(&rq->xdp_ring, veth_ptr_free);
 	}
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 263b005981bd..7145c83c6c8c 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2604,12 +2604,11 @@ static void virtnet_free_queues(struct virtnet_info *vi)
 	int i;
 
 	for (i = 0; i < vi->max_queue_pairs; i++) {
-		napi_hash_del(&vi->rq[i].napi);
-		netif_napi_del(&vi->rq[i].napi);
-		netif_napi_del(&vi->sq[i].napi);
+		__netif_napi_del(&vi->rq[i].napi);
+		__netif_napi_del(&vi->sq[i].napi);
 	}
 
-	/* We called napi_hash_del() before netif_napi_del(),
+	/* We called __netif_napi_del(),
 	 * we need to respect an RCU grace period before freeing vi->rq
 	 */
 	synchronize_net();
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7f9fcfd15942..74ed95215091 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -70,6 +70,7 @@ struct udp_tunnel_nic;
 struct bpf_prog;
 struct xdp_buff;
 
+void synchronize_net(void);
 void netdev_set_default_ethtool_ops(struct net_device *dev,
 				    const struct ethtool_ops *ops);
 
@@ -488,20 +489,6 @@ static inline bool napi_complete(struct napi_struct *n)
 	return napi_complete_done(n, 0);
 }
 
-/**
- *	napi_hash_del - remove a NAPI from global table
- *	@napi: NAPI context
- *
- * Warning: caller must observe RCU grace period
- * before freeing memory containing @napi, if
- * this function returns true.
- * Note: core networking stack automatically calls it
- * from netif_napi_del().
- * Drivers might want to call this helper to combine all
- * the needed RCU grace periods into a single one.
- */
-bool napi_hash_del(struct napi_struct *napi);
-
 /**
  *	napi_disable - prevent NAPI from scheduling
  *	@n: NAPI context
@@ -2367,13 +2354,27 @@ static inline void netif_tx_napi_add(struct net_device *dev,
 	netif_napi_add(dev, napi, poll, weight);
 }
 
+/**
+ *  __netif_napi_del - remove a NAPI context
+ *  @napi: NAPI context
+ *
+ * Warning: caller must observe RCU grace period before freeing memory
+ * containing @napi. Drivers might want to call this helper to combine
+ * all the needed RCU grace periods into a single one.
+ */
+void __netif_napi_del(struct napi_struct *napi);
+
 /**
  *  netif_napi_del - remove a NAPI context
  *  @napi: NAPI context
  *
  *  netif_napi_del() removes a NAPI context from the network device NAPI list
  */
-void netif_napi_del(struct napi_struct *napi);
+static inline void netif_napi_del(struct napi_struct *napi)
+{
+	__netif_napi_del(napi);
+	synchronize_net();
+}
 
 struct napi_gro_cb {
 	/* Virtual address of skb_shinfo(skb)->frags[0].page + offset. */
@@ -2797,7 +2798,6 @@ static inline void unregister_netdevice(struct net_device *dev)
 int netdev_refcnt_read(const struct net_device *dev);
 void free_netdev(struct net_device *dev);
 void netdev_freemem(struct net_device *dev);
-void synchronize_net(void);
 int init_dummy_netdev(struct net_device *dev);
 
 struct net_device *netdev_get_xmit_slave(struct net_device *dev,
diff --git a/net/core/dev.c b/net/core/dev.c
index 152ad3b578de..205b7339d4ae 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6555,20 +6555,15 @@ static void napi_hash_add(struct napi_struct *napi)
 /* Warning : caller is responsible to make sure rcu grace period
  * is respected before freeing memory containing @napi
  */
-bool napi_hash_del(struct napi_struct *napi)
+static void napi_hash_del(struct napi_struct *napi)
 {
-	bool rcu_sync_needed = false;
-
 	spin_lock(&napi_hash_lock);
 
-	if (test_and_clear_bit(NAPI_STATE_HASHED, &napi->state)) {
-		rcu_sync_needed = true;
+	if (test_and_clear_bit(NAPI_STATE_HASHED, &napi->state))
 		hlist_del_rcu(&napi->napi_hash_node);
-	}
+
 	spin_unlock(&napi_hash_lock);
-	return rcu_sync_needed;
 }
-EXPORT_SYMBOL_GPL(napi_hash_del);
 
 static enum hrtimer_restart napi_watchdog(struct hrtimer *timer)
 {
@@ -6653,18 +6648,16 @@ static void flush_gro_hash(struct napi_struct *napi)
 }
 
 /* Must be called in process context */
-void netif_napi_del(struct napi_struct *napi)
+void __netif_napi_del(struct napi_struct *napi)
 {
-	might_sleep();
-	if (napi_hash_del(napi))
-		synchronize_net();
+	napi_hash_del(napi);
 	list_del_init(&napi->dev_list);
 	napi_free_frags(napi);
 
 	flush_gro_hash(napi);
 	napi->gro_bitmask = 0;
 }
-EXPORT_SYMBOL(netif_napi_del);
+EXPORT_SYMBOL(__netif_napi_del);
 
 static int napi_poll(struct napi_struct *n, struct list_head *repoll)
 {
-- 
cgit v1.2.3


From 4d092dd2041a5f328410ad16d63b8606c24e8604 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 9 Sep 2020 10:37:52 -0700
Subject: net: manage napi add/del idempotence explicitly

To RCUify napi->dev_list we need to replace list_del_init()
with list_del_rcu(). There is no _init() version for RCU for
obvious reasons. Up until now netif_napi_del() was idempotent
so to make sure it remains such add a bit which is set when
NAPI is listed, and cleared when it removed. Since we don't
expect multiple calls to netif_napi_add() to be correct,
add a warning on that side.

Now that napi_hash_add / napi_hash_del are only called by
napi_add / del we can actually steal its bit. We just need
to make sure hash node is initialized correctly.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  4 ++--
 net/core/dev.c            | 13 +++++++++----
 2 files changed, 11 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 74ed95215091..157e0242e9ee 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -355,7 +355,7 @@ enum {
 	NAPI_STATE_MISSED,	/* reschedule a napi */
 	NAPI_STATE_DISABLE,	/* Disable pending */
 	NAPI_STATE_NPSVC,	/* Netpoll - don't dequeue from poll_list */
-	NAPI_STATE_HASHED,	/* In NAPI hash (busy polling possible) */
+	NAPI_STATE_LISTED,	/* NAPI added to system lists */
 	NAPI_STATE_NO_BUSY_POLL,/* Do not add in napi_hash, no busy polling */
 	NAPI_STATE_IN_BUSY_POLL,/* sk_busy_loop() owns this NAPI */
 };
@@ -365,7 +365,7 @@ enum {
 	NAPIF_STATE_MISSED	 = BIT(NAPI_STATE_MISSED),
 	NAPIF_STATE_DISABLE	 = BIT(NAPI_STATE_DISABLE),
 	NAPIF_STATE_NPSVC	 = BIT(NAPI_STATE_NPSVC),
-	NAPIF_STATE_HASHED	 = BIT(NAPI_STATE_HASHED),
+	NAPIF_STATE_LISTED	 = BIT(NAPI_STATE_LISTED),
 	NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL),
 	NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL),
 };
diff --git a/net/core/dev.c b/net/core/dev.c
index 205b7339d4ae..e0a1be986824 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6533,8 +6533,7 @@ EXPORT_SYMBOL(napi_busy_loop);
 
 static void napi_hash_add(struct napi_struct *napi)
 {
-	if (test_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state) ||
-	    test_and_set_bit(NAPI_STATE_HASHED, &napi->state))
+	if (test_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state))
 		return;
 
 	spin_lock(&napi_hash_lock);
@@ -6559,8 +6558,7 @@ static void napi_hash_del(struct napi_struct *napi)
 {
 	spin_lock(&napi_hash_lock);
 
-	if (test_and_clear_bit(NAPI_STATE_HASHED, &napi->state))
-		hlist_del_rcu(&napi->napi_hash_node);
+	hlist_del_init_rcu(&napi->napi_hash_node);
 
 	spin_unlock(&napi_hash_lock);
 }
@@ -6595,7 +6593,11 @@ static void init_gro_hash(struct napi_struct *napi)
 void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
 		    int (*poll)(struct napi_struct *, int), int weight)
 {
+	if (WARN_ON(test_and_set_bit(NAPI_STATE_LISTED, &napi->state)))
+		return;
+
 	INIT_LIST_HEAD(&napi->poll_list);
+	INIT_HLIST_NODE(&napi->napi_hash_node);
 	hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
 	napi->timer.function = napi_watchdog;
 	init_gro_hash(napi);
@@ -6650,6 +6652,9 @@ static void flush_gro_hash(struct napi_struct *napi)
 /* Must be called in process context */
 void __netif_napi_del(struct napi_struct *napi)
 {
+	if (!test_and_clear_bit(NAPI_STATE_LISTED, &napi->state))
+		return;
+
 	napi_hash_del(napi);
 	list_del_init(&napi->dev_list);
 	napi_free_frags(napi);
-- 
cgit v1.2.3


From e9b12edc133b54e15ecd105620d51fb8e8fa8bde Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Wed, 9 Sep 2020 17:50:46 -0700
Subject: tcp: record received TOS value in the request socket

A new field is added to the request sock to record the TOS value
received on the listening socket during 3WHS:
When not under syn flood, it is recording the TOS value sent in SYN.
When under syn flood, it is recording the TOS value sent in the ACK.
This is a preparation patch in order to do TOS reflection in the later
commit.

Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h   | 1 +
 net/ipv4/syncookies.c | 6 +++---
 net/ipv4/tcp_input.c  | 1 +
 3 files changed, 5 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 56ff2952edaf..2f87377e9af7 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -134,6 +134,7 @@ struct tcp_request_sock {
 						  * FastOpen it's the seq#
 						  * after data-in-SYN.
 						  */
+	u8				syn_tos;
 };
 
 static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req)
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index f0794f0232ba..c375c126f436 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -286,11 +286,10 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops,
 					    struct sock *sk,
 					    struct sk_buff *skb)
 {
+	struct tcp_request_sock *treq;
 	struct request_sock *req;
 
 #ifdef CONFIG_MPTCP
-	struct tcp_request_sock *treq;
-
 	if (sk_is_mptcp(sk))
 		ops = &mptcp_subflow_request_sock_ops;
 #endif
@@ -299,8 +298,9 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops,
 	if (!req)
 		return NULL;
 
-#if IS_ENABLED(CONFIG_MPTCP)
 	treq = tcp_rsk(req);
+	treq->syn_tos = TCP_SKB_CB(skb)->ip_dsfield;
+#if IS_ENABLED(CONFIG_MPTCP)
 	treq->is_mptcp = sk_is_mptcp(sk);
 	if (treq->is_mptcp) {
 		int err = mptcp_subflow_init_cookie_req(req, sk, skb);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 4337841faeff..3658ad84f0c6 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6834,6 +6834,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 
 	tcp_rsk(req)->snt_isn = isn;
 	tcp_rsk(req)->txhash = net_tx_rndhash();
+	tcp_rsk(req)->syn_tos = TCP_SKB_CB(skb)->ip_dsfield;
 	tcp_openreq_init_rwin(req, sk, dst);
 	sk_rx_queue_set(req_to_sk(req), skb);
 	if (!want_cookie) {
-- 
cgit v1.2.3


From 3d7bfea8b8378277a25b42b28fe5a2a5ca76a7cf Mon Sep 17 00:00:00 2001
From: Daniel Rosenberg <drosen@google.com>
Date: Wed, 8 Jul 2020 02:12:34 -0700
Subject: unicode: Add utf8_casefold_hash

This adds a case insensitive hash function to allow taking the hash
without needing to allocate a casefolded copy of the string.

The existing d_hash implementations for casefolding allocate memory
within rcu-walk, by avoiding it we can be more efficient and avoid
worrying about a failed allocation.

Signed-off-by: Daniel Rosenberg <drosen@google.com>
Reviewed-by: Gabriel Krisman Bertazi <krisman@collabora.com>
Reviewed-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/unicode/utf8-core.c  | 23 ++++++++++++++++++++++-
 include/linux/unicode.h |  3 +++
 2 files changed, 25 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/fs/unicode/utf8-core.c b/fs/unicode/utf8-core.c
index 2a878b739115..dc25823bfed9 100644
--- a/fs/unicode/utf8-core.c
+++ b/fs/unicode/utf8-core.c
@@ -6,6 +6,7 @@
 #include <linux/parser.h>
 #include <linux/errno.h>
 #include <linux/unicode.h>
+#include <linux/stringhash.h>
 
 #include "utf8n.h"
 
@@ -122,9 +123,29 @@ int utf8_casefold(const struct unicode_map *um, const struct qstr *str,
 	}
 	return -EINVAL;
 }
-
 EXPORT_SYMBOL(utf8_casefold);
 
+int utf8_casefold_hash(const struct unicode_map *um, const void *salt,
+		       struct qstr *str)
+{
+	const struct utf8data *data = utf8nfdicf(um->version);
+	struct utf8cursor cur;
+	int c;
+	unsigned long hash = init_name_hash(salt);
+
+	if (utf8ncursor(&cur, data, str->name, str->len) < 0)
+		return -EINVAL;
+
+	while ((c = utf8byte(&cur))) {
+		if (c < 0)
+			return -EINVAL;
+		hash = partial_name_hash((unsigned char)c, hash);
+	}
+	str->hash = end_name_hash(hash);
+	return 0;
+}
+EXPORT_SYMBOL(utf8_casefold_hash);
+
 int utf8_normalize(const struct unicode_map *um, const struct qstr *str,
 		   unsigned char *dest, size_t dlen)
 {
diff --git a/include/linux/unicode.h b/include/linux/unicode.h
index 990aa97d8049..74484d44c755 100644
--- a/include/linux/unicode.h
+++ b/include/linux/unicode.h
@@ -27,6 +27,9 @@ int utf8_normalize(const struct unicode_map *um, const struct qstr *str,
 int utf8_casefold(const struct unicode_map *um, const struct qstr *str,
 		  unsigned char *dest, size_t dlen);
 
+int utf8_casefold_hash(const struct unicode_map *um, const void *salt,
+		       struct qstr *str);
+
 struct unicode_map *utf8_load(const char *version);
 void utf8_unload(struct unicode_map *um);
 
-- 
cgit v1.2.3


From c843843e714c8f17280d7db009412b1b1baf448b Mon Sep 17 00:00:00 2001
From: Daniel Rosenberg <drosen@google.com>
Date: Wed, 8 Jul 2020 02:12:35 -0700
Subject: fs: Add standard casefolding support

This adds general supporting functions for filesystems that use
utf8 casefolding. It provides standard dentry_operations and adds the
necessary structures in struct super_block to allow this standardization.

The new dentry operations are functionally equivalent to the existing
operations in ext4 and f2fs, apart from the use of utf8_casefold_hash to
avoid an allocation.

By providing a common implementation, all users can benefit from any
optimizations without needing to port over improvements.

Signed-off-by: Daniel Rosenberg <drosen@google.com>
Reviewed-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/libfs.c         | 87 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/fs.h | 16 ++++++++++
 2 files changed, 103 insertions(+)

(limited to 'include/linux')

diff --git a/fs/libfs.c b/fs/libfs.c
index e0d42e977d9a..fc34361c1489 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -20,6 +20,8 @@
 #include <linux/fs_context.h>
 #include <linux/pseudo_fs.h>
 #include <linux/fsnotify.h>
+#include <linux/unicode.h>
+#include <linux/fscrypt.h>
 
 #include <linux/uaccess.h>
 
@@ -1363,3 +1365,88 @@ bool is_empty_dir_inode(struct inode *inode)
 	return (inode->i_fop == &empty_dir_operations) &&
 		(inode->i_op == &empty_dir_inode_operations);
 }
+
+#ifdef CONFIG_UNICODE
+/*
+ * Determine if the name of a dentry should be casefolded.
+ *
+ * Return: if names will need casefolding
+ */
+static bool needs_casefold(const struct inode *dir)
+{
+	return IS_CASEFOLDED(dir) && dir->i_sb->s_encoding;
+}
+
+/**
+ * generic_ci_d_compare - generic d_compare implementation for casefolding filesystems
+ * @dentry:	dentry whose name we are checking against
+ * @len:	len of name of dentry
+ * @str:	str pointer to name of dentry
+ * @name:	Name to compare against
+ *
+ * Return: 0 if names match, 1 if mismatch, or -ERRNO
+ */
+int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
+			  const char *str, const struct qstr *name)
+{
+	const struct dentry *parent = READ_ONCE(dentry->d_parent);
+	const struct inode *dir = READ_ONCE(parent->d_inode);
+	const struct super_block *sb = dentry->d_sb;
+	const struct unicode_map *um = sb->s_encoding;
+	struct qstr qstr = QSTR_INIT(str, len);
+	char strbuf[DNAME_INLINE_LEN];
+	int ret;
+
+	if (!dir || !needs_casefold(dir))
+		goto fallback;
+	/*
+	 * If the dentry name is stored in-line, then it may be concurrently
+	 * modified by a rename.  If this happens, the VFS will eventually retry
+	 * the lookup, so it doesn't matter what ->d_compare() returns.
+	 * However, it's unsafe to call utf8_strncasecmp() with an unstable
+	 * string.  Therefore, we have to copy the name into a temporary buffer.
+	 */
+	if (len <= DNAME_INLINE_LEN - 1) {
+		memcpy(strbuf, str, len);
+		strbuf[len] = 0;
+		qstr.name = strbuf;
+		/* prevent compiler from optimizing out the temporary buffer */
+		barrier();
+	}
+	ret = utf8_strncasecmp(um, name, &qstr);
+	if (ret >= 0)
+		return ret;
+
+	if (sb_has_strict_encoding(sb))
+		return -EINVAL;
+fallback:
+	if (len != name->len)
+		return 1;
+	return !!memcmp(str, name->name, len);
+}
+EXPORT_SYMBOL(generic_ci_d_compare);
+
+/**
+ * generic_ci_d_hash - generic d_hash implementation for casefolding filesystems
+ * @dentry:	dentry of the parent directory
+ * @str:	qstr of name whose hash we should fill in
+ *
+ * Return: 0 if hash was successful or unchanged, and -EINVAL on error
+ */
+int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str)
+{
+	const struct inode *dir = READ_ONCE(dentry->d_inode);
+	struct super_block *sb = dentry->d_sb;
+	const struct unicode_map *um = sb->s_encoding;
+	int ret = 0;
+
+	if (!dir || !needs_casefold(dir))
+		return 0;
+
+	ret = utf8_casefold_hash(um, dentry, str);
+	if (ret < 0 && sb_has_strict_encoding(sb))
+		return -EINVAL;
+	return 0;
+}
+EXPORT_SYMBOL(generic_ci_d_hash);
+#endif
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7519ae003a08..bc5417c61e12 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1371,6 +1371,12 @@ extern int send_sigurg(struct fown_struct *fown);
 #define SB_ACTIVE	(1<<30)
 #define SB_NOUSER	(1<<31)
 
+/* These flags relate to encoding and casefolding */
+#define SB_ENC_STRICT_MODE_FL	(1 << 0)
+
+#define sb_has_strict_encoding(sb) \
+	(sb->s_encoding_flags & SB_ENC_STRICT_MODE_FL)
+
 /*
  *	Umount options
  */
@@ -1440,6 +1446,10 @@ struct super_block {
 #endif
 #ifdef CONFIG_FS_VERITY
 	const struct fsverity_operations *s_vop;
+#endif
+#ifdef CONFIG_UNICODE
+	struct unicode_map *s_encoding;
+	__u16 s_encoding_flags;
 #endif
 	struct hlist_bl_head	s_roots;	/* alternate root dentries for NFS */
 	struct list_head	s_mounts;	/* list of mounts; _not_ for fs use */
@@ -3262,6 +3272,12 @@ extern int generic_file_fsync(struct file *, loff_t, loff_t, int);
 
 extern int generic_check_addressable(unsigned, u64);
 
+#ifdef CONFIG_UNICODE
+extern int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str);
+extern int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
+				const char *str, const struct qstr *name);
+#endif
+
 #ifdef CONFIG_MIGRATION
 extern int buffer_migrate_page(struct address_space *,
 				struct page *, struct page *,
-- 
cgit v1.2.3


From eca4873ee1b63ee051e0eed91099fa42c97b2438 Mon Sep 17 00:00:00 2001
From: Daniel Rosenberg <drosen@google.com>
Date: Wed, 8 Jul 2020 02:12:36 -0700
Subject: f2fs: Use generic casefolding support

This switches f2fs over to the generic support provided in
the previous patch.

Since casefolded dentries behave the same in ext4 and f2fs, we decrease
the maintenance burden by unifying them, and any optimizations will
immediately apply to both.

Signed-off-by: Daniel Rosenberg <drosen@google.com>
Reviewed-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/dir.c           | 84 ++++++-------------------------------------------
 fs/f2fs/f2fs.h          |  4 ---
 fs/f2fs/super.c         | 10 +++---
 fs/f2fs/sysfs.c         | 10 +++---
 include/linux/f2fs_fs.h |  3 --
 5 files changed, 20 insertions(+), 91 deletions(-)

(limited to 'include/linux')

diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 069f498af1e3..a18f839b6fb2 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -75,21 +75,22 @@ int f2fs_init_casefolded_name(const struct inode *dir,
 			      struct f2fs_filename *fname)
 {
 #ifdef CONFIG_UNICODE
-	struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
+	struct super_block *sb = dir->i_sb;
+	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 
 	if (IS_CASEFOLDED(dir)) {
 		fname->cf_name.name = f2fs_kmalloc(sbi, F2FS_NAME_LEN,
 						   GFP_NOFS);
 		if (!fname->cf_name.name)
 			return -ENOMEM;
-		fname->cf_name.len = utf8_casefold(sbi->s_encoding,
+		fname->cf_name.len = utf8_casefold(sb->s_encoding,
 						   fname->usr_fname,
 						   fname->cf_name.name,
 						   F2FS_NAME_LEN);
 		if ((int)fname->cf_name.len <= 0) {
 			kfree(fname->cf_name.name);
 			fname->cf_name.name = NULL;
-			if (f2fs_has_strict_mode(sbi))
+			if (sb_has_strict_encoding(sb))
 				return -EINVAL;
 			/* fall back to treating name as opaque byte sequence */
 		}
@@ -215,8 +216,8 @@ static struct f2fs_dir_entry *find_in_block(struct inode *dir,
 static bool f2fs_match_ci_name(const struct inode *dir, const struct qstr *name,
 			       const u8 *de_name, u32 de_name_len)
 {
-	const struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
-	const struct unicode_map *um = sbi->s_encoding;
+	const struct super_block *sb = dir->i_sb;
+	const struct unicode_map *um = sb->s_encoding;
 	struct qstr entry = QSTR_INIT(de_name, de_name_len);
 	int res;
 
@@ -226,7 +227,7 @@ static bool f2fs_match_ci_name(const struct inode *dir, const struct qstr *name,
 		 * In strict mode, ignore invalid names.  In non-strict mode,
 		 * fall back to treating them as opaque byte sequences.
 		 */
-		if (f2fs_has_strict_mode(sbi) || name->len != entry.len)
+		if (sb_has_strict_encoding(sb) || name->len != entry.len)
 			return false;
 		return !memcmp(name->name, entry.name, name->len);
 	}
@@ -1107,75 +1108,8 @@ const struct file_operations f2fs_dir_operations = {
 };
 
 #ifdef CONFIG_UNICODE
-static int f2fs_d_compare(const struct dentry *dentry, unsigned int len,
-			  const char *str, const struct qstr *name)
-{
-	const struct dentry *parent = READ_ONCE(dentry->d_parent);
-	const struct inode *dir = READ_ONCE(parent->d_inode);
-	const struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
-	struct qstr entry = QSTR_INIT(str, len);
-	char strbuf[DNAME_INLINE_LEN];
-	int res;
-
-	if (!dir || !IS_CASEFOLDED(dir))
-		goto fallback;
-
-	/*
-	 * If the dentry name is stored in-line, then it may be concurrently
-	 * modified by a rename.  If this happens, the VFS will eventually retry
-	 * the lookup, so it doesn't matter what ->d_compare() returns.
-	 * However, it's unsafe to call utf8_strncasecmp() with an unstable
-	 * string.  Therefore, we have to copy the name into a temporary buffer.
-	 */
-	if (len <= DNAME_INLINE_LEN - 1) {
-		memcpy(strbuf, str, len);
-		strbuf[len] = 0;
-		entry.name = strbuf;
-		/* prevent compiler from optimizing out the temporary buffer */
-		barrier();
-	}
-
-	res = utf8_strncasecmp(sbi->s_encoding, name, &entry);
-	if (res >= 0)
-		return res;
-
-	if (f2fs_has_strict_mode(sbi))
-		return -EINVAL;
-fallback:
-	if (len != name->len)
-		return 1;
-	return !!memcmp(str, name->name, len);
-}
-
-static int f2fs_d_hash(const struct dentry *dentry, struct qstr *str)
-{
-	struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
-	const struct unicode_map *um = sbi->s_encoding;
-	const struct inode *inode = READ_ONCE(dentry->d_inode);
-	unsigned char *norm;
-	int len, ret = 0;
-
-	if (!inode || !IS_CASEFOLDED(inode))
-		return 0;
-
-	norm = f2fs_kmalloc(sbi, PATH_MAX, GFP_ATOMIC);
-	if (!norm)
-		return -ENOMEM;
-
-	len = utf8_casefold(um, str, norm, PATH_MAX);
-	if (len < 0) {
-		if (f2fs_has_strict_mode(sbi))
-			ret = -EINVAL;
-		goto out;
-	}
-	str->hash = full_name_hash(dentry, norm, len);
-out:
-	kvfree(norm);
-	return ret;
-}
-
 const struct dentry_operations f2fs_dentry_ops = {
-	.d_hash = f2fs_d_hash,
-	.d_compare = f2fs_d_compare,
+	.d_hash = generic_ci_d_hash,
+	.d_compare = generic_ci_d_compare,
 };
 #endif
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 413d0a3ee78d..7446ca639140 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1414,10 +1414,6 @@ struct f2fs_sb_info {
 	int valid_super_block;			/* valid super block no */
 	unsigned long s_flag;				/* flags for sbi */
 	struct mutex writepages;		/* mutex for writepages() */
-#ifdef CONFIG_UNICODE
-	struct unicode_map *s_encoding;
-	__u16 s_encoding_flags;
-#endif
 
 #ifdef CONFIG_BLK_DEV_ZONED
 	unsigned int blocks_per_blkz;		/* F2FS blocks per zone */
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 17e4008141e6..426d6578d2c9 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1282,7 +1282,7 @@ static void f2fs_put_super(struct super_block *sb)
 	for (i = 0; i < NR_PAGE_TYPE; i++)
 		kvfree(sbi->write_io[i]);
 #ifdef CONFIG_UNICODE
-	utf8_unload(sbi->s_encoding);
+	utf8_unload(sb->s_encoding);
 #endif
 	kfree(sbi);
 }
@@ -3359,7 +3359,7 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 static int f2fs_setup_casefold(struct f2fs_sb_info *sbi)
 {
 #ifdef CONFIG_UNICODE
-	if (f2fs_sb_has_casefold(sbi) && !sbi->s_encoding) {
+	if (f2fs_sb_has_casefold(sbi) && !sbi->sb->s_encoding) {
 		const struct f2fs_sb_encodings *encoding_info;
 		struct unicode_map *encoding;
 		__u16 encoding_flags;
@@ -3390,8 +3390,8 @@ static int f2fs_setup_casefold(struct f2fs_sb_info *sbi)
 			 "%s-%s with flags 0x%hx", encoding_info->name,
 			 encoding_info->version?:"\b", encoding_flags);
 
-		sbi->s_encoding = encoding;
-		sbi->s_encoding_flags = encoding_flags;
+		sbi->sb->s_encoding = encoding;
+		sbi->sb->s_encoding_flags = encoding_flags;
 		sbi->sb->s_d_op = &f2fs_dentry_ops;
 	}
 #else
@@ -3887,7 +3887,7 @@ free_bio_info:
 		kvfree(sbi->write_io[i]);
 
 #ifdef CONFIG_UNICODE
-	utf8_unload(sbi->s_encoding);
+	utf8_unload(sb->s_encoding);
 #endif
 free_options:
 #ifdef CONFIG_QUOTA
diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
index 88ed9969cc86..70ad87d5492f 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -176,12 +176,14 @@ static ssize_t encoding_show(struct f2fs_attr *a,
 		struct f2fs_sb_info *sbi, char *buf)
 {
 #ifdef CONFIG_UNICODE
+	struct super_block *sb = sbi->sb;
+
 	if (f2fs_sb_has_casefold(sbi))
 		return snprintf(buf, PAGE_SIZE, "%s (%d.%d.%d)\n",
-			sbi->s_encoding->charset,
-			(sbi->s_encoding->version >> 16) & 0xff,
-			(sbi->s_encoding->version >> 8) & 0xff,
-			sbi->s_encoding->version & 0xff);
+			sb->s_encoding->charset,
+			(sb->s_encoding->version >> 16) & 0xff,
+			(sb->s_encoding->version >> 8) & 0xff,
+			sb->s_encoding->version & 0xff);
 #endif
 	return sprintf(buf, "(none)");
 }
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index 3c383ddd92dd..a5dbb57a687f 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -38,9 +38,6 @@
 #define F2FS_MAX_QUOTAS		3
 
 #define F2FS_ENC_UTF8_12_1	1
-#define F2FS_ENC_STRICT_MODE_FL	(1 << 0)
-#define f2fs_has_strict_mode(sbi) \
-	(sbi->s_encoding_flags & F2FS_ENC_STRICT_MODE_FL)
 
 #define F2FS_IO_SIZE(sbi)	(1 << F2FS_OPTION(sbi).write_io_size_bits) /* Blocks */
 #define F2FS_IO_SIZE_KB(sbi)	(1 << (F2FS_OPTION(sbi).write_io_size_bits + 2)) /* KB */
-- 
cgit v1.2.3


From d66423fbe11e141206f117b232916aa899d44959 Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@cloudflare.com>
Date: Thu, 10 Sep 2020 12:02:48 +0100
Subject: bpf: Plug hole in struct bpf_sk_lookup_kern

As Alexei points out, struct bpf_sk_lookup_kern has two 4-byte holes.
This leads to suboptimal instructions being generated (IPv4, x86):

    1372                    struct bpf_sk_lookup_kern ctx = {
       0xffffffff81b87f30 <+624>:   xor    %eax,%eax
       0xffffffff81b87f32 <+626>:   mov    $0x6,%ecx
       0xffffffff81b87f37 <+631>:   lea    0x90(%rsp),%rdi
       0xffffffff81b87f3f <+639>:   movl   $0x110002,0x88(%rsp)
       0xffffffff81b87f4a <+650>:   rep stos %rax,%es:(%rdi)
       0xffffffff81b87f4d <+653>:   mov    0x8(%rsp),%eax
       0xffffffff81b87f51 <+657>:   mov    %r13d,0x90(%rsp)
       0xffffffff81b87f59 <+665>:   incl   %gs:0x7e4970a0(%rip)
       0xffffffff81b87f60 <+672>:   mov    %eax,0x8c(%rsp)
       0xffffffff81b87f67 <+679>:   movzwl 0x10(%rsp),%eax
       0xffffffff81b87f6c <+684>:   mov    %ax,0xa8(%rsp)
       0xffffffff81b87f74 <+692>:   movzwl 0x38(%rsp),%eax
       0xffffffff81b87f79 <+697>:   mov    %ax,0xaa(%rsp)

Fix this by moving around sport and dport. pahole confirms there
are no more holes:

    struct bpf_sk_lookup_kern {
        u16                        family;       /*     0     2 */
        u16                        protocol;     /*     2     2 */
        __be16                     sport;        /*     4     2 */
        u16                        dport;        /*     6     2 */
        struct {
                __be32             saddr;        /*     8     4 */
                __be32             daddr;        /*    12     4 */
        } v4;                                    /*     8     8 */
        struct {
                const struct in6_addr  * saddr;  /*    16     8 */
                const struct in6_addr  * daddr;  /*    24     8 */
        } v6;                                    /*    16    16 */
        struct sock *              selected_sk;  /*    32     8 */
        bool                       no_reuseport; /*    40     1 */

        /* size: 48, cachelines: 1, members: 8 */
        /* padding: 7 */
        /* last cacheline: 48 bytes */
    };

The assembly also doesn't contain the pesky rep stos anymore:

    1372                    struct bpf_sk_lookup_kern ctx = {
       0xffffffff81b87f60 <+624>:   movzwl 0x10(%rsp),%eax
       0xffffffff81b87f65 <+629>:   movq   $0x0,0xa8(%rsp)
       0xffffffff81b87f71 <+641>:   movq   $0x0,0xb0(%rsp)
       0xffffffff81b87f7d <+653>:   mov    %ax,0x9c(%rsp)
       0xffffffff81b87f85 <+661>:   movzwl 0x38(%rsp),%eax
       0xffffffff81b87f8a <+666>:   movq   $0x0,0xb8(%rsp)
       0xffffffff81b87f96 <+678>:   mov    %ax,0x9e(%rsp)
       0xffffffff81b87f9e <+686>:   mov    0x8(%rsp),%eax
       0xffffffff81b87fa2 <+690>:   movq   $0x0,0xc0(%rsp)
       0xffffffff81b87fae <+702>:   movl   $0x110002,0x98(%rsp)
       0xffffffff81b87fb9 <+713>:   mov    %eax,0xa0(%rsp)
       0xffffffff81b87fc0 <+720>:   mov    %r13d,0xa4(%rsp)

1: https://lore.kernel.org/bpf/CAADnVQKE6y9h2fwX6OS837v-Uf+aBXnT_JXiN_bbo2gitZQ3tA@mail.gmail.com/

Fixes: e9ddbb7707ff ("bpf: Introduce SK_LOOKUP program type with a dedicated attach point")
Suggested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Link: https://lore.kernel.org/bpf/20200910110248.198326-1-lmb@cloudflare.com
---
 include/linux/filter.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 995625950cc1..e962dd8117d8 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1287,6 +1287,8 @@ int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len);
 struct bpf_sk_lookup_kern {
 	u16		family;
 	u16		protocol;
+	__be16		sport;
+	u16		dport;
 	struct {
 		__be32 saddr;
 		__be32 daddr;
@@ -1295,8 +1297,6 @@ struct bpf_sk_lookup_kern {
 		const struct in6_addr *saddr;
 		const struct in6_addr *daddr;
 	} v6;
-	__be16		sport;
-	u16		dport;
 	struct sock	*selected_sk;
 	bool		no_reuseport;
 };
-- 
cgit v1.2.3


From e33d2a7b3041d7f8cd1f0a2a4ca42a5bc112b14e Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Mon, 31 Aug 2020 18:16:45 +0300
Subject: SUNRPC: remove RC4-HMAC-MD5 support from KerberosV

The RC4-HMAC-MD5 KerberosV algorithm is based on RFC 4757 [0], which
was specifically issued for interoperability with Windows 2000, but was
never intended to receive the same level of support. The RFC says

  The IETF Kerberos community supports publishing this specification as
  an informational document in order to describe this widely
  implemented technology.  However, while these encryption types
  provide the operations necessary to implement the base Kerberos
  specification [RFC4120], they do not provide all the required
  operations in the Kerberos cryptography framework [RFC3961].  As a
  result, it is not generally possible to implement potential
  extensions to Kerberos using these encryption types.  The Kerberos
  encryption type negotiation mechanism [RFC4537] provides one approach
  for using such extensions even when a Kerberos infrastructure uses
  long-term RC4 keys.  Because this specification does not implement
  operations required by RFC 3961 and because of security concerns with
  the use of RC4 and MD4 discussed in Section 8, this specification is
  not appropriate for publication on the standards track.

  The RC4-HMAC encryption types are used to ease upgrade of existing
  Windows NT environments, provide strong cryptography (128-bit key
  lengths), and provide exportable (meet United States government
  export restriction requirements) encryption.  This document describes
  the implementation of those encryption types.

Furthermore, this RFC was re-classified as 'historic' by RFC 8429 [1] in
2018, stating that 'none of the encryption types it specifies should be
used'

Note that other outdated algorithms are left in place (some of which are
guarded by CONFIG_SUNRPC_DISABLE_INSECURE_ENCTYPES), so this should only
adversely affect interoperability with Windows NT/2000 systems that have
not received any updates since 2008 (but are connected to a network
nonetheless)

[0] https://tools.ietf.org/html/rfc4757
[1] https://tools.ietf.org/html/rfc8429

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Acked-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/linux/sunrpc/gss_krb5.h          |  11 --
 include/linux/sunrpc/gss_krb5_enctypes.h |   9 +-
 net/sunrpc/Kconfig                       |   1 -
 net/sunrpc/auth_gss/gss_krb5_crypto.c    | 276 -------------------------------
 net/sunrpc/auth_gss/gss_krb5_mech.c      |  95 -----------
 net/sunrpc/auth_gss/gss_krb5_seal.c      |   1 -
 net/sunrpc/auth_gss/gss_krb5_seqnum.c    |  87 ----------
 net/sunrpc/auth_gss/gss_krb5_unseal.c    |   1 -
 net/sunrpc/auth_gss/gss_krb5_wrap.c      |  65 ++------
 9 files changed, 16 insertions(+), 530 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h
index e8f8ffe7448b..91f43d86879d 100644
--- a/include/linux/sunrpc/gss_krb5.h
+++ b/include/linux/sunrpc/gss_krb5.h
@@ -141,14 +141,12 @@ enum sgn_alg {
 	SGN_ALG_MD2_5 = 0x0001,
 	SGN_ALG_DES_MAC = 0x0002,
 	SGN_ALG_3 = 0x0003,		/* not published */
-	SGN_ALG_HMAC_MD5 = 0x0011,	/* microsoft w2k; no support */
 	SGN_ALG_HMAC_SHA1_DES3_KD = 0x0004
 };
 enum seal_alg {
 	SEAL_ALG_NONE = 0xffff,
 	SEAL_ALG_DES = 0x0000,
 	SEAL_ALG_1 = 0x0001,		/* not published */
-	SEAL_ALG_MICROSOFT_RC4 = 0x0010,/* microsoft w2k; no support */
 	SEAL_ALG_DES3KD = 0x0002
 };
 
@@ -316,14 +314,5 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, u32 len,
 		     struct xdr_buf *buf, u32 *plainoffset,
 		     u32 *plainlen);
 
-int
-krb5_rc4_setup_seq_key(struct krb5_ctx *kctx,
-		       struct crypto_sync_skcipher *cipher,
-		       unsigned char *cksum);
-
-int
-krb5_rc4_setup_enc_key(struct krb5_ctx *kctx,
-		       struct crypto_sync_skcipher *cipher,
-		       s32 seqnum);
 void
 gss_krb5_make_confounder(char *p, u32 conflen);
diff --git a/include/linux/sunrpc/gss_krb5_enctypes.h b/include/linux/sunrpc/gss_krb5_enctypes.h
index 981c89cef19d..87eea679d750 100644
--- a/include/linux/sunrpc/gss_krb5_enctypes.h
+++ b/include/linux/sunrpc/gss_krb5_enctypes.h
@@ -13,15 +13,13 @@
 #ifdef CONFIG_SUNRPC_DISABLE_INSECURE_ENCTYPES
 
 /*
- * NB: This list includes encryption types that were deprecated
- * by RFC 8429 (DES3_CBC_SHA1 and ARCFOUR_HMAC).
+ * NB: This list includes DES3_CBC_SHA1, which was deprecated by RFC 8429.
  *
  * ENCTYPE_AES256_CTS_HMAC_SHA1_96
  * ENCTYPE_AES128_CTS_HMAC_SHA1_96
  * ENCTYPE_DES3_CBC_SHA1
- * ENCTYPE_ARCFOUR_HMAC
  */
-#define KRB5_SUPPORTED_ENCTYPES "18,17,16,23"
+#define KRB5_SUPPORTED_ENCTYPES "18,17,16"
 
 #else	/* CONFIG_SUNRPC_DISABLE_INSECURE_ENCTYPES */
 
@@ -32,12 +30,11 @@
  * ENCTYPE_AES256_CTS_HMAC_SHA1_96
  * ENCTYPE_AES128_CTS_HMAC_SHA1_96
  * ENCTYPE_DES3_CBC_SHA1
- * ENCTYPE_ARCFOUR_HMAC
  * ENCTYPE_DES_CBC_MD5
  * ENCTYPE_DES_CBC_CRC
  * ENCTYPE_DES_CBC_MD4
  */
-#define KRB5_SUPPORTED_ENCTYPES "18,17,16,23,3,1,2"
+#define KRB5_SUPPORTED_ENCTYPES "18,17,16,3,1,2"
 
 #endif	/* CONFIG_SUNRPC_DISABLE_INSECURE_ENCTYPES */
 
diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig
index 3bcf985507be..bbbb5af0af13 100644
--- a/net/sunrpc/Kconfig
+++ b/net/sunrpc/Kconfig
@@ -21,7 +21,6 @@ config RPCSEC_GSS_KRB5
 	depends on SUNRPC && CRYPTO
 	depends on CRYPTO_MD5 && CRYPTO_DES && CRYPTO_CBC && CRYPTO_CTS
 	depends on CRYPTO_ECB && CRYPTO_HMAC && CRYPTO_SHA1 && CRYPTO_AES
-	depends on CRYPTO_ARC4
 	default y
 	select SUNRPC_GSS
 	help
diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c
index 794fb3001880..634b6c6e0dcb 100644
--- a/net/sunrpc/auth_gss/gss_krb5_crypto.c
+++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c
@@ -138,135 +138,6 @@ checksummer(struct scatterlist *sg, void *data)
 	return crypto_ahash_update(req);
 }
 
-static int
-arcfour_hmac_md5_usage_to_salt(unsigned int usage, u8 salt[4])
-{
-	unsigned int ms_usage;
-
-	switch (usage) {
-	case KG_USAGE_SIGN:
-		ms_usage = 15;
-		break;
-	case KG_USAGE_SEAL:
-		ms_usage = 13;
-		break;
-	default:
-		return -EINVAL;
-	}
-	salt[0] = (ms_usage >> 0) & 0xff;
-	salt[1] = (ms_usage >> 8) & 0xff;
-	salt[2] = (ms_usage >> 16) & 0xff;
-	salt[3] = (ms_usage >> 24) & 0xff;
-
-	return 0;
-}
-
-static u32
-make_checksum_hmac_md5(struct krb5_ctx *kctx, char *header, int hdrlen,
-		       struct xdr_buf *body, int body_offset, u8 *cksumkey,
-		       unsigned int usage, struct xdr_netobj *cksumout)
-{
-	struct scatterlist              sg[1];
-	int err = -1;
-	u8 *checksumdata;
-	u8 *rc4salt;
-	struct crypto_ahash *md5;
-	struct crypto_ahash *hmac_md5;
-	struct ahash_request *req;
-
-	if (cksumkey == NULL)
-		return GSS_S_FAILURE;
-
-	if (cksumout->len < kctx->gk5e->cksumlength) {
-		dprintk("%s: checksum buffer length, %u, too small for %s\n",
-			__func__, cksumout->len, kctx->gk5e->name);
-		return GSS_S_FAILURE;
-	}
-
-	rc4salt = kmalloc_array(4, sizeof(*rc4salt), GFP_NOFS);
-	if (!rc4salt)
-		return GSS_S_FAILURE;
-
-	if (arcfour_hmac_md5_usage_to_salt(usage, rc4salt)) {
-		dprintk("%s: invalid usage value %u\n", __func__, usage);
-		goto out_free_rc4salt;
-	}
-
-	checksumdata = kmalloc(GSS_KRB5_MAX_CKSUM_LEN, GFP_NOFS);
-	if (!checksumdata)
-		goto out_free_rc4salt;
-
-	md5 = crypto_alloc_ahash("md5", 0, CRYPTO_ALG_ASYNC);
-	if (IS_ERR(md5))
-		goto out_free_cksum;
-
-	hmac_md5 = crypto_alloc_ahash(kctx->gk5e->cksum_name, 0,
-				      CRYPTO_ALG_ASYNC);
-	if (IS_ERR(hmac_md5))
-		goto out_free_md5;
-
-	req = ahash_request_alloc(md5, GFP_NOFS);
-	if (!req)
-		goto out_free_hmac_md5;
-
-	ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL);
-
-	err = crypto_ahash_init(req);
-	if (err)
-		goto out;
-	sg_init_one(sg, rc4salt, 4);
-	ahash_request_set_crypt(req, sg, NULL, 4);
-	err = crypto_ahash_update(req);
-	if (err)
-		goto out;
-
-	sg_init_one(sg, header, hdrlen);
-	ahash_request_set_crypt(req, sg, NULL, hdrlen);
-	err = crypto_ahash_update(req);
-	if (err)
-		goto out;
-	err = xdr_process_buf(body, body_offset, body->len - body_offset,
-			      checksummer, req);
-	if (err)
-		goto out;
-	ahash_request_set_crypt(req, NULL, checksumdata, 0);
-	err = crypto_ahash_final(req);
-	if (err)
-		goto out;
-
-	ahash_request_free(req);
-	req = ahash_request_alloc(hmac_md5, GFP_NOFS);
-	if (!req)
-		goto out_free_hmac_md5;
-
-	ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL);
-
-	err = crypto_ahash_setkey(hmac_md5, cksumkey, kctx->gk5e->keylength);
-	if (err)
-		goto out;
-
-	sg_init_one(sg, checksumdata, crypto_ahash_digestsize(md5));
-	ahash_request_set_crypt(req, sg, checksumdata,
-				crypto_ahash_digestsize(md5));
-	err = crypto_ahash_digest(req);
-	if (err)
-		goto out;
-
-	memcpy(cksumout->data, checksumdata, kctx->gk5e->cksumlength);
-	cksumout->len = kctx->gk5e->cksumlength;
-out:
-	ahash_request_free(req);
-out_free_hmac_md5:
-	crypto_free_ahash(hmac_md5);
-out_free_md5:
-	crypto_free_ahash(md5);
-out_free_cksum:
-	kfree(checksumdata);
-out_free_rc4salt:
-	kfree(rc4salt);
-	return err ? GSS_S_FAILURE : 0;
-}
-
 /*
  * checksum the plaintext data and hdrlen bytes of the token header
  * The checksum is performed over the first 8 bytes of the
@@ -284,11 +155,6 @@ make_checksum(struct krb5_ctx *kctx, char *header, int hdrlen,
 	u8 *checksumdata;
 	unsigned int checksumlen;
 
-	if (kctx->gk5e->ctype == CKSUMTYPE_HMAC_MD5_ARCFOUR)
-		return make_checksum_hmac_md5(kctx, header, hdrlen,
-					      body, body_offset,
-					      cksumkey, usage, cksumout);
-
 	if (cksumout->len < kctx->gk5e->cksumlength) {
 		dprintk("%s: checksum buffer length, %u, too small for %s\n",
 			__func__, cksumout->len, kctx->gk5e->name);
@@ -942,145 +808,3 @@ out_err:
 		ret = GSS_S_FAILURE;
 	return ret;
 }
-
-/*
- * Compute Kseq given the initial session key and the checksum.
- * Set the key of the given cipher.
- */
-int
-krb5_rc4_setup_seq_key(struct krb5_ctx *kctx,
-		       struct crypto_sync_skcipher *cipher,
-		       unsigned char *cksum)
-{
-	struct crypto_shash *hmac;
-	struct shash_desc *desc;
-	u8 Kseq[GSS_KRB5_MAX_KEYLEN];
-	u32 zeroconstant = 0;
-	int err;
-
-	dprintk("%s: entered\n", __func__);
-
-	hmac = crypto_alloc_shash(kctx->gk5e->cksum_name, 0, 0);
-	if (IS_ERR(hmac)) {
-		dprintk("%s: error %ld, allocating hash '%s'\n",
-			__func__, PTR_ERR(hmac), kctx->gk5e->cksum_name);
-		return PTR_ERR(hmac);
-	}
-
-	desc = kmalloc(sizeof(*desc) + crypto_shash_descsize(hmac),
-		       GFP_NOFS);
-	if (!desc) {
-		dprintk("%s: failed to allocate shash descriptor for '%s'\n",
-			__func__, kctx->gk5e->cksum_name);
-		crypto_free_shash(hmac);
-		return -ENOMEM;
-	}
-
-	desc->tfm = hmac;
-
-	/* Compute intermediate Kseq from session key */
-	err = crypto_shash_setkey(hmac, kctx->Ksess, kctx->gk5e->keylength);
-	if (err)
-		goto out_err;
-
-	err = crypto_shash_digest(desc, (u8 *)&zeroconstant, 4, Kseq);
-	if (err)
-		goto out_err;
-
-	/* Compute final Kseq from the checksum and intermediate Kseq */
-	err = crypto_shash_setkey(hmac, Kseq, kctx->gk5e->keylength);
-	if (err)
-		goto out_err;
-
-	err = crypto_shash_digest(desc, cksum, 8, Kseq);
-	if (err)
-		goto out_err;
-
-	err = crypto_sync_skcipher_setkey(cipher, Kseq, kctx->gk5e->keylength);
-	if (err)
-		goto out_err;
-
-	err = 0;
-
-out_err:
-	kfree_sensitive(desc);
-	crypto_free_shash(hmac);
-	dprintk("%s: returning %d\n", __func__, err);
-	return err;
-}
-
-/*
- * Compute Kcrypt given the initial session key and the plaintext seqnum.
- * Set the key of cipher kctx->enc.
- */
-int
-krb5_rc4_setup_enc_key(struct krb5_ctx *kctx,
-		       struct crypto_sync_skcipher *cipher,
-		       s32 seqnum)
-{
-	struct crypto_shash *hmac;
-	struct shash_desc *desc;
-	u8 Kcrypt[GSS_KRB5_MAX_KEYLEN];
-	u8 zeroconstant[4] = {0};
-	u8 seqnumarray[4];
-	int err, i;
-
-	dprintk("%s: entered, seqnum %u\n", __func__, seqnum);
-
-	hmac = crypto_alloc_shash(kctx->gk5e->cksum_name, 0, 0);
-	if (IS_ERR(hmac)) {
-		dprintk("%s: error %ld, allocating hash '%s'\n",
-			__func__, PTR_ERR(hmac), kctx->gk5e->cksum_name);
-		return PTR_ERR(hmac);
-	}
-
-	desc = kmalloc(sizeof(*desc) + crypto_shash_descsize(hmac),
-		       GFP_NOFS);
-	if (!desc) {
-		dprintk("%s: failed to allocate shash descriptor for '%s'\n",
-			__func__, kctx->gk5e->cksum_name);
-		crypto_free_shash(hmac);
-		return -ENOMEM;
-	}
-
-	desc->tfm = hmac;
-
-	/* Compute intermediate Kcrypt from session key */
-	for (i = 0; i < kctx->gk5e->keylength; i++)
-		Kcrypt[i] = kctx->Ksess[i] ^ 0xf0;
-
-	err = crypto_shash_setkey(hmac, Kcrypt, kctx->gk5e->keylength);
-	if (err)
-		goto out_err;
-
-	err = crypto_shash_digest(desc, zeroconstant, 4, Kcrypt);
-	if (err)
-		goto out_err;
-
-	/* Compute final Kcrypt from the seqnum and intermediate Kcrypt */
-	err = crypto_shash_setkey(hmac, Kcrypt, kctx->gk5e->keylength);
-	if (err)
-		goto out_err;
-
-	seqnumarray[0] = (unsigned char) ((seqnum >> 24) & 0xff);
-	seqnumarray[1] = (unsigned char) ((seqnum >> 16) & 0xff);
-	seqnumarray[2] = (unsigned char) ((seqnum >> 8) & 0xff);
-	seqnumarray[3] = (unsigned char) ((seqnum >> 0) & 0xff);
-
-	err = crypto_shash_digest(desc, seqnumarray, 4, Kcrypt);
-	if (err)
-		goto out_err;
-
-	err = crypto_sync_skcipher_setkey(cipher, Kcrypt,
-					  kctx->gk5e->keylength);
-	if (err)
-		goto out_err;
-
-	err = 0;
-
-out_err:
-	kfree_sensitive(desc);
-	crypto_free_shash(hmac);
-	dprintk("%s: returning %d\n", __func__, err);
-	return err;
-}
diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c
index a84a5b289484..ae9acf3a7389 100644
--- a/net/sunrpc/auth_gss/gss_krb5_mech.c
+++ b/net/sunrpc/auth_gss/gss_krb5_mech.c
@@ -51,27 +51,6 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = {
 	  .keyed_cksum = 0,
 	},
 #endif	/* CONFIG_SUNRPC_DISABLE_INSECURE_ENCTYPES */
-	/*
-	 * RC4-HMAC
-	 */
-	{
-	  .etype = ENCTYPE_ARCFOUR_HMAC,
-	  .ctype = CKSUMTYPE_HMAC_MD5_ARCFOUR,
-	  .name = "rc4-hmac",
-	  .encrypt_name = "ecb(arc4)",
-	  .cksum_name = "hmac(md5)",
-	  .encrypt = krb5_encrypt,
-	  .decrypt = krb5_decrypt,
-	  .mk_key = NULL,
-	  .signalg = SGN_ALG_HMAC_MD5,
-	  .sealalg = SEAL_ALG_MICROSOFT_RC4,
-	  .keybytes = 16,
-	  .keylength = 16,
-	  .blocksize = 1,
-	  .conflen = 8,
-	  .cksumlength = 8,
-	  .keyed_cksum = 1,
-	},
 	/*
 	 * 3DES
 	 */
@@ -401,78 +380,6 @@ out_err:
 	return -EINVAL;
 }
 
-/*
- * Note that RC4 depends on deriving keys using the sequence
- * number or the checksum of a token.  Therefore, the final keys
- * cannot be calculated until the token is being constructed!
- */
-static int
-context_derive_keys_rc4(struct krb5_ctx *ctx)
-{
-	struct crypto_shash *hmac;
-	char sigkeyconstant[] = "signaturekey";
-	int slen = strlen(sigkeyconstant) + 1;	/* include null terminator */
-	struct shash_desc *desc;
-	int err;
-
-	dprintk("RPC:       %s: entered\n", __func__);
-	/*
-	 * derive cksum (aka Ksign) key
-	 */
-	hmac = crypto_alloc_shash(ctx->gk5e->cksum_name, 0, 0);
-	if (IS_ERR(hmac)) {
-		dprintk("%s: error %ld allocating hash '%s'\n",
-			__func__, PTR_ERR(hmac), ctx->gk5e->cksum_name);
-		err = PTR_ERR(hmac);
-		goto out_err;
-	}
-
-	err = crypto_shash_setkey(hmac, ctx->Ksess, ctx->gk5e->keylength);
-	if (err)
-		goto out_err_free_hmac;
-
-
-	desc = kmalloc(sizeof(*desc) + crypto_shash_descsize(hmac), GFP_NOFS);
-	if (!desc) {
-		dprintk("%s: failed to allocate hash descriptor for '%s'\n",
-			__func__, ctx->gk5e->cksum_name);
-		err = -ENOMEM;
-		goto out_err_free_hmac;
-	}
-
-	desc->tfm = hmac;
-
-	err = crypto_shash_digest(desc, sigkeyconstant, slen, ctx->cksum);
-	kfree_sensitive(desc);
-	if (err)
-		goto out_err_free_hmac;
-	/*
-	 * allocate hash, and skciphers for data and seqnum encryption
-	 */
-	ctx->enc = crypto_alloc_sync_skcipher(ctx->gk5e->encrypt_name, 0, 0);
-	if (IS_ERR(ctx->enc)) {
-		err = PTR_ERR(ctx->enc);
-		goto out_err_free_hmac;
-	}
-
-	ctx->seq = crypto_alloc_sync_skcipher(ctx->gk5e->encrypt_name, 0, 0);
-	if (IS_ERR(ctx->seq)) {
-		crypto_free_sync_skcipher(ctx->enc);
-		err = PTR_ERR(ctx->seq);
-		goto out_err_free_hmac;
-	}
-
-	dprintk("RPC:       %s: returning success\n", __func__);
-
-	err = 0;
-
-out_err_free_hmac:
-	crypto_free_shash(hmac);
-out_err:
-	dprintk("RPC:       %s: returning %d\n", __func__, err);
-	return err;
-}
-
 static int
 context_derive_keys_new(struct krb5_ctx *ctx, gfp_t gfp_mask)
 {
@@ -649,8 +556,6 @@ gss_import_v2_context(const void *p, const void *end, struct krb5_ctx *ctx,
 	switch (ctx->enctype) {
 	case ENCTYPE_DES3_CBC_RAW:
 		return context_derive_keys_des3(ctx, gfp_mask);
-	case ENCTYPE_ARCFOUR_HMAC:
-		return context_derive_keys_rc4(ctx);
 	case ENCTYPE_AES128_CTS_HMAC_SHA1_96:
 	case ENCTYPE_AES256_CTS_HMAC_SHA1_96:
 		return context_derive_keys_new(ctx, gfp_mask);
diff --git a/net/sunrpc/auth_gss/gss_krb5_seal.c b/net/sunrpc/auth_gss/gss_krb5_seal.c
index f1d280accf43..33061417ec97 100644
--- a/net/sunrpc/auth_gss/gss_krb5_seal.c
+++ b/net/sunrpc/auth_gss/gss_krb5_seal.c
@@ -214,7 +214,6 @@ gss_get_mic_kerberos(struct gss_ctx *gss_ctx, struct xdr_buf *text,
 		BUG();
 	case ENCTYPE_DES_CBC_RAW:
 	case ENCTYPE_DES3_CBC_RAW:
-	case ENCTYPE_ARCFOUR_HMAC:
 		return gss_get_mic_v1(ctx, text, token);
 	case ENCTYPE_AES128_CTS_HMAC_SHA1_96:
 	case ENCTYPE_AES256_CTS_HMAC_SHA1_96:
diff --git a/net/sunrpc/auth_gss/gss_krb5_seqnum.c b/net/sunrpc/auth_gss/gss_krb5_seqnum.c
index 507105127095..fb117817ff5d 100644
--- a/net/sunrpc/auth_gss/gss_krb5_seqnum.c
+++ b/net/sunrpc/auth_gss/gss_krb5_seqnum.c
@@ -39,42 +39,6 @@
 # define RPCDBG_FACILITY        RPCDBG_AUTH
 #endif
 
-static s32
-krb5_make_rc4_seq_num(struct krb5_ctx *kctx, int direction, s32 seqnum,
-		      unsigned char *cksum, unsigned char *buf)
-{
-	struct crypto_sync_skcipher *cipher;
-	unsigned char *plain;
-	s32 code;
-
-	dprintk("RPC:       %s:\n", __func__);
-	cipher = crypto_alloc_sync_skcipher(kctx->gk5e->encrypt_name, 0, 0);
-	if (IS_ERR(cipher))
-		return PTR_ERR(cipher);
-
-	plain = kmalloc(8, GFP_NOFS);
-	if (!plain)
-		return -ENOMEM;
-
-	plain[0] = (unsigned char) ((seqnum >> 24) & 0xff);
-	plain[1] = (unsigned char) ((seqnum >> 16) & 0xff);
-	plain[2] = (unsigned char) ((seqnum >> 8) & 0xff);
-	plain[3] = (unsigned char) ((seqnum >> 0) & 0xff);
-	plain[4] = direction;
-	plain[5] = direction;
-	plain[6] = direction;
-	plain[7] = direction;
-
-	code = krb5_rc4_setup_seq_key(kctx, cipher, cksum);
-	if (code)
-		goto out;
-
-	code = krb5_encrypt(cipher, cksum, plain, buf, 8);
-out:
-	kfree(plain);
-	crypto_free_sync_skcipher(cipher);
-	return code;
-}
 s32
 krb5_make_seq_num(struct krb5_ctx *kctx,
 		struct crypto_sync_skcipher *key,
@@ -85,10 +49,6 @@ krb5_make_seq_num(struct krb5_ctx *kctx,
 	unsigned char *plain;
 	s32 code;
 
-	if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC)
-		return krb5_make_rc4_seq_num(kctx, direction, seqnum,
-					     cksum, buf);
-
 	plain = kmalloc(8, GFP_NOFS);
 	if (!plain)
 		return -ENOMEM;
@@ -108,50 +68,6 @@ krb5_make_seq_num(struct krb5_ctx *kctx,
 	return code;
 }
 
-static s32
-krb5_get_rc4_seq_num(struct krb5_ctx *kctx, unsigned char *cksum,
-		     unsigned char *buf, int *direction, s32 *seqnum)
-{
-	struct crypto_sync_skcipher *cipher;
-	unsigned char *plain;
-	s32 code;
-
-	dprintk("RPC:       %s:\n", __func__);
-	cipher = crypto_alloc_sync_skcipher(kctx->gk5e->encrypt_name, 0, 0);
-	if (IS_ERR(cipher))
-		return PTR_ERR(cipher);
-
-	code = krb5_rc4_setup_seq_key(kctx, cipher, cksum);
-	if (code)
-		goto out;
-
-	plain = kmalloc(8, GFP_NOFS);
-	if (!plain) {
-		code = -ENOMEM;
-		goto out;
-	}
-
-	code = krb5_decrypt(cipher, cksum, buf, plain, 8);
-	if (code)
-		goto out_plain;
-
-	if ((plain[4] != plain[5]) || (plain[4] != plain[6])
-				   || (plain[4] != plain[7])) {
-		code = (s32)KG_BAD_SEQ;
-		goto out_plain;
-	}
-
-	*direction = plain[4];
-
-	*seqnum = ((plain[0] << 24) | (plain[1] << 16) |
-					(plain[2] << 8) | (plain[3]));
-out_plain:
-	kfree(plain);
-out:
-	crypto_free_sync_skcipher(cipher);
-	return code;
-}
-
 s32
 krb5_get_seq_num(struct krb5_ctx *kctx,
 	       unsigned char *cksum,
@@ -164,9 +80,6 @@ krb5_get_seq_num(struct krb5_ctx *kctx,
 
 	dprintk("RPC:       krb5_get_seq_num:\n");
 
-	if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC)
-		return krb5_get_rc4_seq_num(kctx, cksum, buf,
-					    direction, seqnum);
 	plain = kmalloc(8, GFP_NOFS);
 	if (!plain)
 		return -ENOMEM;
diff --git a/net/sunrpc/auth_gss/gss_krb5_unseal.c b/net/sunrpc/auth_gss/gss_krb5_unseal.c
index aaab91cf24c8..ba04e3ec970a 100644
--- a/net/sunrpc/auth_gss/gss_krb5_unseal.c
+++ b/net/sunrpc/auth_gss/gss_krb5_unseal.c
@@ -218,7 +218,6 @@ gss_verify_mic_kerberos(struct gss_ctx *gss_ctx,
 		BUG();
 	case ENCTYPE_DES_CBC_RAW:
 	case ENCTYPE_DES3_CBC_RAW:
-	case ENCTYPE_ARCFOUR_HMAC:
 		return gss_verify_mic_v1(ctx, message_buffer, read_token);
 	case ENCTYPE_AES128_CTS_HMAC_SHA1_96:
 	case ENCTYPE_AES256_CTS_HMAC_SHA1_96:
diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c
index 90b8329fef82..6be44a7ee4ac 100644
--- a/net/sunrpc/auth_gss/gss_krb5_wrap.c
+++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c
@@ -236,26 +236,9 @@ gss_wrap_kerberos_v1(struct krb5_ctx *kctx, int offset,
 			       seq_send, ptr + GSS_KRB5_TOK_HDR_LEN, ptr + 8)))
 		return GSS_S_FAILURE;
 
-	if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC) {
-		struct crypto_sync_skcipher *cipher;
-		int err;
-		cipher = crypto_alloc_sync_skcipher(kctx->gk5e->encrypt_name,
-						    0, 0);
-		if (IS_ERR(cipher))
-			return GSS_S_FAILURE;
-
-		krb5_rc4_setup_enc_key(kctx, cipher, seq_send);
-
-		err = gss_encrypt_xdr_buf(cipher, buf,
-					  offset + headlen - conflen, pages);
-		crypto_free_sync_skcipher(cipher);
-		if (err)
-			return GSS_S_FAILURE;
-	} else {
-		if (gss_encrypt_xdr_buf(kctx->enc, buf,
-					offset + headlen - conflen, pages))
-			return GSS_S_FAILURE;
-	}
+	if (gss_encrypt_xdr_buf(kctx->enc, buf,
+				offset + headlen - conflen, pages))
+		return GSS_S_FAILURE;
 
 	return (kctx->endtime < now) ? GSS_S_CONTEXT_EXPIRED : GSS_S_COMPLETE;
 }
@@ -316,37 +299,9 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, int len,
 	crypt_offset = ptr + (GSS_KRB5_TOK_HDR_LEN + kctx->gk5e->cksumlength) -
 					(unsigned char *)buf->head[0].iov_base;
 
-	/*
-	 * Need plaintext seqnum to derive encryption key for arcfour-hmac
-	 */
-	if (krb5_get_seq_num(kctx, ptr + GSS_KRB5_TOK_HDR_LEN,
-			     ptr + 8, &direction, &seqnum))
-		return GSS_S_BAD_SIG;
-
-	if ((kctx->initiate && direction != 0xff) ||
-	    (!kctx->initiate && direction != 0))
-		return GSS_S_BAD_SIG;
-
 	buf->len = len;
-	if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC) {
-		struct crypto_sync_skcipher *cipher;
-		int err;
-
-		cipher = crypto_alloc_sync_skcipher(kctx->gk5e->encrypt_name,
-						    0, 0);
-		if (IS_ERR(cipher))
-			return GSS_S_FAILURE;
-
-		krb5_rc4_setup_enc_key(kctx, cipher, seqnum);
-
-		err = gss_decrypt_xdr_buf(cipher, buf, crypt_offset);
-		crypto_free_sync_skcipher(cipher);
-		if (err)
-			return GSS_S_DEFECTIVE_TOKEN;
-	} else {
-		if (gss_decrypt_xdr_buf(kctx->enc, buf, crypt_offset))
-			return GSS_S_DEFECTIVE_TOKEN;
-	}
+	if (gss_decrypt_xdr_buf(kctx->enc, buf, crypt_offset))
+		return GSS_S_DEFECTIVE_TOKEN;
 
 	if (kctx->gk5e->keyed_cksum)
 		cksumkey = kctx->cksum;
@@ -370,6 +325,14 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, int len,
 
 	/* do sequencing checks */
 
+	if (krb5_get_seq_num(kctx, ptr + GSS_KRB5_TOK_HDR_LEN,
+			     ptr + 8, &direction, &seqnum))
+		return GSS_S_BAD_SIG;
+
+	if ((kctx->initiate && direction != 0xff) ||
+	    (!kctx->initiate && direction != 0))
+		return GSS_S_BAD_SIG;
+
 	/* Copy the data back to the right position.  XXX: Would probably be
 	 * better to copy and encrypt at the same time. */
 
@@ -605,7 +568,6 @@ gss_wrap_kerberos(struct gss_ctx *gctx, int offset,
 		BUG();
 	case ENCTYPE_DES_CBC_RAW:
 	case ENCTYPE_DES3_CBC_RAW:
-	case ENCTYPE_ARCFOUR_HMAC:
 		return gss_wrap_kerberos_v1(kctx, offset, buf, pages);
 	case ENCTYPE_AES128_CTS_HMAC_SHA1_96:
 	case ENCTYPE_AES256_CTS_HMAC_SHA1_96:
@@ -624,7 +586,6 @@ gss_unwrap_kerberos(struct gss_ctx *gctx, int offset,
 		BUG();
 	case ENCTYPE_DES_CBC_RAW:
 	case ENCTYPE_DES3_CBC_RAW:
-	case ENCTYPE_ARCFOUR_HMAC:
 		return gss_unwrap_kerberos_v1(kctx, offset, len, buf,
 					      &gctx->slack, &gctx->align);
 	case ENCTYPE_AES128_CTS_HMAC_SHA1_96:
-- 
cgit v1.2.3


From 6d0fd536183034953bf84826fecb37e47779d24b Mon Sep 17 00:00:00 2001
From: Atish Patra <atish.patra@wdc.com>
Date: Fri, 28 Aug 2020 10:20:31 -0700
Subject: include: pe.h: Add RISC-V related PE definition

Define RISC-V related machine types.

Signed-off-by: Atish Patra <atish.patra@wdc.com>
Reviewed-by: Palmer Dabbelt <palmerdabbelt@google.com>
Link: https://lore.kernel.org/r/20200415195422.19866-3-atish.patra@wdc.com
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 include/linux/pe.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/pe.h b/include/linux/pe.h
index 8ad71d763a77..daf09ffffe38 100644
--- a/include/linux/pe.h
+++ b/include/linux/pe.h
@@ -55,6 +55,9 @@
 #define	IMAGE_FILE_MACHINE_POWERPC	0x01f0
 #define	IMAGE_FILE_MACHINE_POWERPCFP	0x01f1
 #define	IMAGE_FILE_MACHINE_R4000	0x0166
+#define	IMAGE_FILE_MACHINE_RISCV32	0x5032
+#define	IMAGE_FILE_MACHINE_RISCV64	0x5064
+#define	IMAGE_FILE_MACHINE_RISCV128	0x5128
 #define	IMAGE_FILE_MACHINE_SH3		0x01a2
 #define	IMAGE_FILE_MACHINE_SH3DSP	0x01a3
 #define	IMAGE_FILE_MACHINE_SH3E		0x01a4
-- 
cgit v1.2.3


From abdaf11ac18925ce8cc229e62e35b342d548ece2 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 17 Aug 2020 16:41:50 +0200
Subject: dma-mapping: add (back) arch_dma_mark_clean for ia64

Add back a hook to optimize dcache flushing after reading executable
code using DMA.  This gets ia64 out of the business of pretending to
be dma incoherent just for this optimization.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 arch/ia64/Kconfig               |  3 +--
 arch/ia64/kernel/dma-mapping.c  | 14 +-------------
 arch/ia64/mm/init.c             |  3 +--
 include/linux/dma-direct.h      |  3 +++
 include/linux/dma-noncoherent.h |  8 ++++++++
 kernel/dma/Kconfig              |  6 ++++++
 kernel/dma/direct.c             |  3 +++
 7 files changed, 23 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 5b4ec80bf586..513ba0c5d336 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -8,6 +8,7 @@ menu "Processor type and features"
 
 config IA64
 	bool
+	select ARCH_HAS_DMA_MARK_CLEAN
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select ACPI
@@ -32,8 +33,6 @@ config IA64
 	select TTY
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_VIRT_CPU_ACCOUNTING
-	select DMA_NONCOHERENT_MMAP
-	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	select VIRT_TO_BUS
 	select GENERIC_IRQ_PROBE
 	select GENERIC_PENDING_IRQ if SMP
diff --git a/arch/ia64/kernel/dma-mapping.c b/arch/ia64/kernel/dma-mapping.c
index 09ef9ce9988d..f640ed6fe1d5 100644
--- a/arch/ia64/kernel/dma-mapping.c
+++ b/arch/ia64/kernel/dma-mapping.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/dma-direct.h>
+#include <linux/dma-mapping.h>
 #include <linux/export.h>
 
 /* Set this to 1 if there is a HW IOMMU in the system */
@@ -7,15 +7,3 @@ int iommu_detected __read_mostly;
 
 const struct dma_map_ops *dma_ops;
 EXPORT_SYMBOL(dma_ops);
-
-void *arch_dma_alloc(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
-{
-	return dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs);
-}
-
-void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
-		dma_addr_t dma_addr, unsigned long attrs)
-{
-	dma_direct_free_pages(dev, size, cpu_addr, dma_addr, attrs);
-}
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 0b3fb4c7af29..02e5aa08294e 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -73,8 +73,7 @@ __ia64_sync_icache_dcache (pte_t pte)
  * DMA can be marked as "clean" so that lazy_mmu_prot_update() doesn't have to
  * flush them when they get mapped into an executable vm-area.
  */
-void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
-		enum dma_data_direction dir)
+void arch_dma_mark_clean(phys_addr_t paddr, size_t size)
 {
 	unsigned long pfn = PHYS_PFN(paddr);
 
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 6e87225600ae..95e3e28bd93f 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -150,6 +150,9 @@ static inline void dma_direct_sync_single_for_cpu(struct device *dev,
 
 	if (unlikely(is_swiotlb_buffer(paddr)))
 		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU);
+
+	if (dir == DMA_FROM_DEVICE)
+		arch_dma_mark_clean(paddr, size);
 }
 
 static inline dma_addr_t dma_direct_map_page(struct device *dev,
diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h
index ca09a4e07d2d..b9bc6c557ea4 100644
--- a/include/linux/dma-noncoherent.h
+++ b/include/linux/dma-noncoherent.h
@@ -108,6 +108,14 @@ static inline void arch_dma_prep_coherent(struct page *page, size_t size)
 }
 #endif /* CONFIG_ARCH_HAS_DMA_PREP_COHERENT */
 
+#ifdef CONFIG_ARCH_HAS_DMA_MARK_CLEAN
+void arch_dma_mark_clean(phys_addr_t paddr, size_t size);
+#else
+static inline void arch_dma_mark_clean(phys_addr_t paddr, size_t size)
+{
+}
+#endif /* ARCH_HAS_DMA_MARK_CLEAN */
+
 void *arch_dma_set_uncached(void *addr, size_t size);
 void arch_dma_clear_uncached(void *addr, size_t size);
 
diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index e7b801649f65..281785feb874 100644
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@ -44,6 +44,12 @@ config ARCH_HAS_DMA_SET_MASK
 config ARCH_HAS_DMA_WRITE_COMBINE
 	bool
 
+#
+# Select if the architectures provides the arch_dma_mark_clean hook
+#
+config ARCH_HAS_DMA_MARK_CLEAN
+	bool
+
 config DMA_DECLARE_COHERENT
 	bool
 
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index db6ef07aec3b..949c1cbf08b2 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -345,6 +345,9 @@ void dma_direct_sync_sg_for_cpu(struct device *dev,
 		if (unlikely(is_swiotlb_buffer(paddr)))
 			swiotlb_tbl_sync_single(dev, paddr, sg->length, dir,
 					SYNC_FOR_CPU);
+
+		if (dir == DMA_FROM_DEVICE)
+			arch_dma_mark_clean(paddr, sg->length);
 	}
 
 	if (!dev_is_dma_coherent(dev))
-- 
cgit v1.2.3


From 2f5388a29be82a62529d146499e70987e856f6f7 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 17 Aug 2020 17:06:40 +0200
Subject: dma-direct: remove dma_direct_{alloc,free}_pages

Just merge these helpers into the main dma_direct_{alloc,free} routines,
as the additional checks are always false for the two callers.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
---
 arch/x86/kernel/amd_gart_64.c |  6 +++---
 include/linux/dma-direct.h    |  4 ----
 kernel/dma/direct.c           | 39 +++++++++++++++------------------------
 kernel/dma/pool.c             |  2 +-
 4 files changed, 19 insertions(+), 32 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index bccc5357bffd..153374b996a2 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -467,7 +467,7 @@ gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr,
 {
 	void *vaddr;
 
-	vaddr = dma_direct_alloc_pages(dev, size, dma_addr, flag, attrs);
+	vaddr = dma_direct_alloc(dev, size, dma_addr, flag, attrs);
 	if (!vaddr ||
 	    !force_iommu || dev->coherent_dma_mask <= DMA_BIT_MASK(24))
 		return vaddr;
@@ -479,7 +479,7 @@ gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr,
 		goto out_free;
 	return vaddr;
 out_free:
-	dma_direct_free_pages(dev, size, vaddr, *dma_addr, attrs);
+	dma_direct_free(dev, size, vaddr, *dma_addr, attrs);
 	return NULL;
 }
 
@@ -489,7 +489,7 @@ gart_free_coherent(struct device *dev, size_t size, void *vaddr,
 		   dma_addr_t dma_addr, unsigned long attrs)
 {
 	gart_unmap_page(dev, dma_addr, size, DMA_BIDIRECTIONAL, 0);
-	dma_direct_free_pages(dev, size, vaddr, dma_addr, attrs);
+	dma_direct_free(dev, size, vaddr, dma_addr, attrs);
 }
 
 static int no_agp;
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 95e3e28bd93f..20eceb2e4f91 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -77,10 +77,6 @@ void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t gfp, unsigned long attrs);
 void dma_direct_free(struct device *dev, size_t size, void *cpu_addr,
 		dma_addr_t dma_addr, unsigned long attrs);
-void *dma_direct_alloc_pages(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs);
-void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
-		dma_addr_t dma_addr, unsigned long attrs);
 int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		unsigned long attrs);
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 949c1cbf08b2..1d564bea5857 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -151,13 +151,18 @@ again:
 	return page;
 }
 
-void *dma_direct_alloc_pages(struct device *dev, size_t size,
+void *dma_direct_alloc(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
 {
 	struct page *page;
 	void *ret;
 	int err;
 
+	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
+	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
+	    dma_alloc_need_uncached(dev, attrs))
+		return arch_dma_alloc(dev, size, dma_handle, gfp, attrs);
+
 	size = PAGE_ALIGN(size);
 
 	if (dma_should_alloc_from_pool(dev, gfp, attrs)) {
@@ -256,11 +261,18 @@ out_free_pages:
 	return NULL;
 }
 
-void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
-		dma_addr_t dma_addr, unsigned long attrs)
+void dma_direct_free(struct device *dev, size_t size,
+		void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs)
 {
 	unsigned int page_order = get_order(size);
 
+	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
+	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
+	    dma_alloc_need_uncached(dev, attrs)) {
+		arch_dma_free(dev, size, cpu_addr, dma_addr, attrs);
+		return;
+	}
+
 	/* If cpu_addr is not from an atomic pool, dma_free_from_pool() fails */
 	if (dma_should_free_from_pool(dev, attrs) &&
 	    dma_free_from_pool(dev, cpu_addr, PAGE_ALIGN(size)))
@@ -284,27 +296,6 @@ void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
 	dma_free_contiguous(dev, dma_direct_to_page(dev, dma_addr), size);
 }
 
-void *dma_direct_alloc(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
-{
-	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
-	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
-	    dma_alloc_need_uncached(dev, attrs))
-		return arch_dma_alloc(dev, size, dma_handle, gfp, attrs);
-	return dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs);
-}
-
-void dma_direct_free(struct device *dev, size_t size,
-		void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs)
-{
-	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
-	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
-	    dma_alloc_need_uncached(dev, attrs))
-		arch_dma_free(dev, size, cpu_addr, dma_addr, attrs);
-	else
-		dma_direct_free_pages(dev, size, cpu_addr, dma_addr, attrs);
-}
-
 #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
     defined(CONFIG_SWIOTLB)
 void dma_direct_sync_sg_for_device(struct device *dev,
diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c
index 1281c0f0442b..fe11643ff9cc 100644
--- a/kernel/dma/pool.c
+++ b/kernel/dma/pool.c
@@ -115,7 +115,7 @@ static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size,
 #endif
 	/*
 	 * Memory in the atomic DMA pools must be unencrypted, the pools do not
-	 * shrink so no re-encryption occurs in dma_direct_free_pages().
+	 * shrink so no re-encryption occurs in dma_direct_free().
 	 */
 	ret = set_memory_decrypted((unsigned long)page_to_virt(page),
 				   1 << order);
-- 
cgit v1.2.3


From 7bc5c428a660d4d1bc95ba54bf4cb6bccf8c3029 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 8 Sep 2020 17:56:22 +0200
Subject: dma-direct: remove __dma_to_phys

There is no harm in just always clearing the SME encryption bit, while
significantly simplifying the interface.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
---
 arch/arm/include/asm/dma-direct.h      |  2 +-
 arch/mips/bmips/dma.c                  |  2 +-
 arch/mips/cavium-octeon/dma-octeon.c   |  2 +-
 arch/mips/include/asm/dma-direct.h     |  2 +-
 arch/mips/loongson2ef/fuloong-2e/dma.c |  2 +-
 arch/mips/loongson2ef/lemote-2f/dma.c  |  2 +-
 arch/mips/loongson64/dma.c             |  2 +-
 arch/mips/pci/pci-ar2315.c             |  2 +-
 arch/mips/pci/pci-xtalk-bridge.c       |  2 +-
 arch/mips/sgi-ip32/ip32-dma.c          |  2 +-
 arch/powerpc/include/asm/dma-direct.h  |  2 +-
 include/linux/dma-direct.h             | 14 +++++---------
 kernel/dma/direct.c                    |  6 +-----
 13 files changed, 17 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/include/asm/dma-direct.h b/arch/arm/include/asm/dma-direct.h
index 7c3001a6a775..a8cee87a93e8 100644
--- a/arch/arm/include/asm/dma-direct.h
+++ b/arch/arm/include/asm/dma-direct.h
@@ -8,7 +8,7 @@ static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return pfn_to_dma(dev, __phys_to_pfn(paddr)) + offset;
 }
 
-static inline phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dev_addr)
+static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr)
 {
 	unsigned int offset = dev_addr & ~PAGE_MASK;
 	return __pfn_to_phys(dma_to_pfn(dev, dev_addr)) + offset;
diff --git a/arch/mips/bmips/dma.c b/arch/mips/bmips/dma.c
index df56bf4179e3..ba2a5d33dfd3 100644
--- a/arch/mips/bmips/dma.c
+++ b/arch/mips/bmips/dma.c
@@ -52,7 +52,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t pa)
 	return pa;
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	struct bmips_dma_range *r;
 
diff --git a/arch/mips/cavium-octeon/dma-octeon.c b/arch/mips/cavium-octeon/dma-octeon.c
index 14ea680d180e..388b13ba2558 100644
--- a/arch/mips/cavium-octeon/dma-octeon.c
+++ b/arch/mips/cavium-octeon/dma-octeon.c
@@ -177,7 +177,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return paddr;
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
 {
 #ifdef CONFIG_PCI
 	if (dev && dev_is_pci(dev))
diff --git a/arch/mips/include/asm/dma-direct.h b/arch/mips/include/asm/dma-direct.h
index 14e352651ce9..8e178651c638 100644
--- a/arch/mips/include/asm/dma-direct.h
+++ b/arch/mips/include/asm/dma-direct.h
@@ -3,6 +3,6 @@
 #define _MIPS_DMA_DIRECT_H 1
 
 dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr);
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr);
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr);
 
 #endif /* _MIPS_DMA_DIRECT_H */
diff --git a/arch/mips/loongson2ef/fuloong-2e/dma.c b/arch/mips/loongson2ef/fuloong-2e/dma.c
index e122292bf666..83fadeb3fd7d 100644
--- a/arch/mips/loongson2ef/fuloong-2e/dma.c
+++ b/arch/mips/loongson2ef/fuloong-2e/dma.c
@@ -6,7 +6,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return paddr | 0x80000000;
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	return dma_addr & 0x7fffffff;
 }
diff --git a/arch/mips/loongson2ef/lemote-2f/dma.c b/arch/mips/loongson2ef/lemote-2f/dma.c
index abf0e39d7e46..302b43a14eee 100644
--- a/arch/mips/loongson2ef/lemote-2f/dma.c
+++ b/arch/mips/loongson2ef/lemote-2f/dma.c
@@ -6,7 +6,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return paddr | 0x80000000;
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	if (dma_addr > 0x8fffffff)
 		return dma_addr;
diff --git a/arch/mips/loongson64/dma.c b/arch/mips/loongson64/dma.c
index dbfe6e82fddd..b3dc5d0bd2b1 100644
--- a/arch/mips/loongson64/dma.c
+++ b/arch/mips/loongson64/dma.c
@@ -13,7 +13,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return ((nid << 44) ^ paddr) | (nid << node_id_offset);
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
 {
 	/* We extract 2bit node id (bit 44~47, only bit 44~45 used now) from
 	 * Loongson-3's 48bit address space and embed it into 40bit */
diff --git a/arch/mips/pci/pci-ar2315.c b/arch/mips/pci/pci-ar2315.c
index 490953f51528..d88395684f48 100644
--- a/arch/mips/pci/pci-ar2315.c
+++ b/arch/mips/pci/pci-ar2315.c
@@ -175,7 +175,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return paddr + ar2315_dev_offset(dev);
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	return dma_addr - ar2315_dev_offset(dev);
 }
diff --git a/arch/mips/pci/pci-xtalk-bridge.c b/arch/mips/pci/pci-xtalk-bridge.c
index 9b3cc775c55e..f1b37f32b553 100644
--- a/arch/mips/pci/pci-xtalk-bridge.c
+++ b/arch/mips/pci/pci-xtalk-bridge.c
@@ -33,7 +33,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return bc->baddr + paddr;
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	return dma_addr & ~(0xffUL << 56);
 }
diff --git a/arch/mips/sgi-ip32/ip32-dma.c b/arch/mips/sgi-ip32/ip32-dma.c
index fa7b17cb5385..160317294d97 100644
--- a/arch/mips/sgi-ip32/ip32-dma.c
+++ b/arch/mips/sgi-ip32/ip32-dma.c
@@ -27,7 +27,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return dma_addr;
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	phys_addr_t paddr = dma_addr & RAM_OFFSET_MASK;
 
diff --git a/arch/powerpc/include/asm/dma-direct.h b/arch/powerpc/include/asm/dma-direct.h
index abc154d784b0..95b09313d2a4 100644
--- a/arch/powerpc/include/asm/dma-direct.h
+++ b/arch/powerpc/include/asm/dma-direct.h
@@ -7,7 +7,7 @@ static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return paddr + dev->archdata.dma_offset;
 }
 
-static inline phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
+static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
 {
 	return daddr - dev->archdata.dma_offset;
 }
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 20eceb2e4f91..f00e262ab6b1 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -24,11 +24,12 @@ static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return dev_addr - ((dma_addr_t)dev->dma_pfn_offset << PAGE_SHIFT);
 }
 
-static inline phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dev_addr)
+static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr)
 {
-	phys_addr_t paddr = (phys_addr_t)dev_addr;
+	phys_addr_t paddr = (phys_addr_t)dev_addr +
+		((phys_addr_t)dev->dma_pfn_offset << PAGE_SHIFT);
 
-	return paddr + ((phys_addr_t)dev->dma_pfn_offset << PAGE_SHIFT);
+	return __sme_clr(paddr);
 }
 #endif /* !CONFIG_ARCH_HAS_PHYS_TO_DMA */
 
@@ -44,7 +45,7 @@ static inline bool force_dma_unencrypted(struct device *dev)
 /*
  * If memory encryption is supported, phys_to_dma will set the memory encryption
  * bit in the DMA address, and dma_to_phys will clear it.  The raw __phys_to_dma
- * and __dma_to_phys versions should only be used on non-encrypted memory for
+ * version should only be used on non-encrypted memory for
  * special occasions like DMA coherent buffers.
  */
 static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
@@ -52,11 +53,6 @@ static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return __sme_set(__phys_to_dma(dev, paddr));
 }
 
-static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
-{
-	return __sme_clr(__dma_to_phys(dev, daddr));
-}
-
 static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size,
 		bool is_ram)
 {
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 57a6e7d7cf8f..bfb479c8a370 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -48,11 +48,6 @@ static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
 {
 	u64 dma_limit = min_not_zero(dma_mask, dev->bus_dma_limit);
 
-	if (force_dma_unencrypted(dev))
-		*phys_limit = __dma_to_phys(dev, dma_limit);
-	else
-		*phys_limit = dma_to_phys(dev, dma_limit);
-
 	/*
 	 * Optimistically try the zone that the physical address mask falls
 	 * into first.  If that returns memory that isn't actually addressable
@@ -61,6 +56,7 @@ static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
 	 * Note that GFP_DMA32 and GFP_DMA are no ops without the corresponding
 	 * zones.
 	 */
+	*phys_limit = dma_to_phys(dev, dma_limit);
 	if (*phys_limit <= DMA_BIT_MASK(zone_dma_bits))
 		return GFP_DMA;
 	if (*phys_limit <= DMA_BIT_MASK(32))
-- 
cgit v1.2.3


From 5ceda74093a5c1c3f42a02b894df031f3bbc9af1 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 17 Aug 2020 17:34:03 +0200
Subject: dma-direct: rename and cleanup __phys_to_dma

The __phys_to_dma vs phys_to_dma distinction isn't exactly obvious.  Try
to improve the situation by renaming __phys_to_dma to
phys_to_dma_unencryped, and not forcing architectures that want to
override phys_to_dma to actually provide __phys_to_dma.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
---
 arch/arm/include/asm/dma-direct.h      |  2 +-
 arch/mips/bmips/dma.c                  |  2 +-
 arch/mips/cavium-octeon/dma-octeon.c   |  2 +-
 arch/mips/include/asm/dma-direct.h     |  2 +-
 arch/mips/loongson2ef/fuloong-2e/dma.c |  2 +-
 arch/mips/loongson2ef/lemote-2f/dma.c  |  2 +-
 arch/mips/loongson64/dma.c             |  2 +-
 arch/mips/pci/pci-ar2315.c             |  2 +-
 arch/mips/pci/pci-xtalk-bridge.c       |  2 +-
 arch/mips/sgi-ip32/ip32-dma.c          |  2 +-
 arch/powerpc/include/asm/dma-direct.h  |  2 +-
 drivers/iommu/intel/iommu.c            |  2 +-
 include/linux/dma-direct.h             | 28 ++++++++++++++++------------
 kernel/dma/direct.c                    |  8 ++++----
 kernel/dma/swiotlb.c                   |  4 ++--
 15 files changed, 34 insertions(+), 30 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/include/asm/dma-direct.h b/arch/arm/include/asm/dma-direct.h
index a8cee87a93e8..bca0de567534 100644
--- a/arch/arm/include/asm/dma-direct.h
+++ b/arch/arm/include/asm/dma-direct.h
@@ -2,7 +2,7 @@
 #ifndef ASM_ARM_DMA_DIRECT_H
 #define ASM_ARM_DMA_DIRECT_H 1
 
-static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	unsigned int offset = paddr & ~PAGE_MASK;
 	return pfn_to_dma(dev, __phys_to_pfn(paddr)) + offset;
diff --git a/arch/mips/bmips/dma.c b/arch/mips/bmips/dma.c
index ba2a5d33dfd3..49061b870680 100644
--- a/arch/mips/bmips/dma.c
+++ b/arch/mips/bmips/dma.c
@@ -40,7 +40,7 @@ static struct bmips_dma_range *bmips_dma_ranges;
 
 #define FLUSH_RAC		0x100
 
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t pa)
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t pa)
 {
 	struct bmips_dma_range *r;
 
diff --git a/arch/mips/cavium-octeon/dma-octeon.c b/arch/mips/cavium-octeon/dma-octeon.c
index 388b13ba2558..232fa1017b1e 100644
--- a/arch/mips/cavium-octeon/dma-octeon.c
+++ b/arch/mips/cavium-octeon/dma-octeon.c
@@ -168,7 +168,7 @@ void __init octeon_pci_dma_init(void)
 }
 #endif /* CONFIG_PCI */
 
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 #ifdef CONFIG_PCI
 	if (dev && dev_is_pci(dev))
diff --git a/arch/mips/include/asm/dma-direct.h b/arch/mips/include/asm/dma-direct.h
index 8e178651c638..9a640118316c 100644
--- a/arch/mips/include/asm/dma-direct.h
+++ b/arch/mips/include/asm/dma-direct.h
@@ -2,7 +2,7 @@
 #ifndef _MIPS_DMA_DIRECT_H
 #define _MIPS_DMA_DIRECT_H 1
 
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr);
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr);
 phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr);
 
 #endif /* _MIPS_DMA_DIRECT_H */
diff --git a/arch/mips/loongson2ef/fuloong-2e/dma.c b/arch/mips/loongson2ef/fuloong-2e/dma.c
index 83fadeb3fd7d..cea167d8aba8 100644
--- a/arch/mips/loongson2ef/fuloong-2e/dma.c
+++ b/arch/mips/loongson2ef/fuloong-2e/dma.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/dma-direct.h>
 
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	return paddr | 0x80000000;
 }
diff --git a/arch/mips/loongson2ef/lemote-2f/dma.c b/arch/mips/loongson2ef/lemote-2f/dma.c
index 302b43a14eee..3c9e99456357 100644
--- a/arch/mips/loongson2ef/lemote-2f/dma.c
+++ b/arch/mips/loongson2ef/lemote-2f/dma.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/dma-direct.h>
 
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	return paddr | 0x80000000;
 }
diff --git a/arch/mips/loongson64/dma.c b/arch/mips/loongson64/dma.c
index b3dc5d0bd2b1..364f2f27c872 100644
--- a/arch/mips/loongson64/dma.c
+++ b/arch/mips/loongson64/dma.c
@@ -4,7 +4,7 @@
 #include <linux/swiotlb.h>
 #include <boot_param.h>
 
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	/* We extract 2bit node id (bit 44~47, only bit 44~45 used now) from
 	 * Loongson-3's 48bit address space and embed it into 40bit */
diff --git a/arch/mips/pci/pci-ar2315.c b/arch/mips/pci/pci-ar2315.c
index d88395684f48..cef4a47ab063 100644
--- a/arch/mips/pci/pci-ar2315.c
+++ b/arch/mips/pci/pci-ar2315.c
@@ -170,7 +170,7 @@ static inline dma_addr_t ar2315_dev_offset(struct device *dev)
 	return 0;
 }
 
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	return paddr + ar2315_dev_offset(dev);
 }
diff --git a/arch/mips/pci/pci-xtalk-bridge.c b/arch/mips/pci/pci-xtalk-bridge.c
index f1b37f32b553..50f7d42cca5a 100644
--- a/arch/mips/pci/pci-xtalk-bridge.c
+++ b/arch/mips/pci/pci-xtalk-bridge.c
@@ -25,7 +25,7 @@
 /*
  * Common phys<->dma mapping for platforms using pci xtalk bridge
  */
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct bridge_controller *bc = BRIDGE_CONTROLLER(pdev->bus);
diff --git a/arch/mips/sgi-ip32/ip32-dma.c b/arch/mips/sgi-ip32/ip32-dma.c
index 160317294d97..20c6da9d76bc 100644
--- a/arch/mips/sgi-ip32/ip32-dma.c
+++ b/arch/mips/sgi-ip32/ip32-dma.c
@@ -18,7 +18,7 @@
 
 #define RAM_OFFSET_MASK 0x3fffffffUL
 
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	dma_addr_t dma_addr = paddr & RAM_OFFSET_MASK;
 
diff --git a/arch/powerpc/include/asm/dma-direct.h b/arch/powerpc/include/asm/dma-direct.h
index 95b09313d2a4..128304cbee1d 100644
--- a/arch/powerpc/include/asm/dma-direct.h
+++ b/arch/powerpc/include/asm/dma-direct.h
@@ -2,7 +2,7 @@
 #ifndef ASM_POWERPC_DMA_DIRECT_H
 #define ASM_POWERPC_DMA_DIRECT_H 1
 
-static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	return paddr + dev->archdata.dma_offset;
 }
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index f8177c59d229..7983c13b9eef 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -3736,7 +3736,7 @@ bounce_map_single(struct device *dev, phys_addr_t paddr, size_t size,
 	 */
 	if (!IS_ALIGNED(paddr | size, VTD_PAGE_SIZE)) {
 		tlb_addr = swiotlb_tbl_map_single(dev,
-				__phys_to_dma(dev, io_tlb_start),
+				phys_to_dma_unencrypted(dev, io_tlb_start),
 				paddr, size, aligned_size, dir, attrs);
 		if (tlb_addr == DMA_MAPPING_ERROR) {
 			goto swiotlb_error;
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index f00e262ab6b1..805010ea5346 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -16,14 +16,29 @@ extern unsigned int zone_dma_bits;
 
 #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA
 #include <asm/dma-direct.h>
+#ifndef phys_to_dma_unencrypted
+#define phys_to_dma_unencrypted		phys_to_dma
+#endif
 #else
-static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+static inline dma_addr_t phys_to_dma_unencrypted(struct device *dev,
+		phys_addr_t paddr)
 {
 	dma_addr_t dev_addr = (dma_addr_t)paddr;
 
 	return dev_addr - ((dma_addr_t)dev->dma_pfn_offset << PAGE_SHIFT);
 }
 
+/*
+ * If memory encryption is supported, phys_to_dma will set the memory encryption
+ * bit in the DMA address, and dma_to_phys will clear it.
+ * phys_to_dma_unencrypted is for use on special unencrypted memory like swiotlb
+ * buffers.
+ */
+static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+	return __sme_set(phys_to_dma_unencrypted(dev, paddr));
+}
+
 static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr)
 {
 	phys_addr_t paddr = (phys_addr_t)dev_addr +
@@ -42,17 +57,6 @@ static inline bool force_dma_unencrypted(struct device *dev)
 }
 #endif /* CONFIG_ARCH_HAS_FORCE_DMA_UNENCRYPTED */
 
-/*
- * If memory encryption is supported, phys_to_dma will set the memory encryption
- * bit in the DMA address, and dma_to_phys will clear it.  The raw __phys_to_dma
- * version should only be used on non-encrypted memory for
- * special occasions like DMA coherent buffers.
- */
-static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
-{
-	return __sme_set(__phys_to_dma(dev, paddr));
-}
-
 static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size,
 		bool is_ram)
 {
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index bfb479c8a370..54db9cfdaecc 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -25,7 +25,7 @@ static inline dma_addr_t phys_to_dma_direct(struct device *dev,
 		phys_addr_t phys)
 {
 	if (force_dma_unencrypted(dev))
-		return __phys_to_dma(dev, phys);
+		return phys_to_dma_unencrypted(dev, phys);
 	return phys_to_dma(dev, phys);
 }
 
@@ -438,13 +438,13 @@ int dma_direct_supported(struct device *dev, u64 mask)
 		return 1;
 
 	/*
-	 * This check needs to be against the actual bit mask value, so
-	 * use __phys_to_dma() here so that the SME encryption mask isn't
+	 * This check needs to be against the actual bit mask value, so use
+	 * phys_to_dma_unencrypted() here so that the SME encryption mask isn't
 	 * part of the check.
 	 */
 	if (IS_ENABLED(CONFIG_ZONE_DMA))
 		min_mask = min_t(u64, min_mask, DMA_BIT_MASK(zone_dma_bits));
-	return mask >= __phys_to_dma(dev, min_mask);
+	return mask >= phys_to_dma_unencrypted(dev, min_mask);
 }
 
 size_t dma_direct_max_mapping_size(struct device *dev)
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index c19379fabd20..4ea72d145cd2 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -670,13 +670,13 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size,
 			      swiotlb_force);
 
 	swiotlb_addr = swiotlb_tbl_map_single(dev,
-			__phys_to_dma(dev, io_tlb_start),
+			phys_to_dma_unencrypted(dev, io_tlb_start),
 			paddr, size, size, dir, attrs);
 	if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR)
 		return DMA_MAPPING_ERROR;
 
 	/* Ensure that the address returned is DMA'ble */
-	dma_addr = __phys_to_dma(dev, swiotlb_addr);
+	dma_addr = phys_to_dma_unencrypted(dev, swiotlb_addr);
 	if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
 		swiotlb_tbl_unmap_single(dev, swiotlb_addr, size, size, dir,
 			attrs | DMA_ATTR_SKIP_CPU_SYNC);
-- 
cgit v1.2.3


From b3003a74456f0c1f614a46c07e16abe33bfdd087 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Fri, 4 Sep 2020 19:41:57 -0300
Subject: RDMA/qedr: Remove fbo and zbva from the MR
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

zbva is always false, so fbo is never read.

A 'zero-based-virtual-address' is simply IOVA == 0, and the driver already
supports this.

Link: https://lore.kernel.org/r/16-v2-270386b7e60b+28f4-umem_1_jgg@nvidia.com
Acked-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/hw/qedr/verbs.c         |  4 ----
 drivers/net/ethernet/qlogic/qed/qed_rdma.c | 12 ++----------
 include/linux/qed/qed_rdma_if.h            |  2 --
 3 files changed, 2 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index 9319778f5df4..f7bfc43f0f5c 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -2882,10 +2882,8 @@ struct ib_mr *qedr_reg_user_mr(struct ib_pd *ibpd, u64 start, u64 len,
 	mr->hw_mr.pbl_two_level = mr->info.pbl_info.two_layered;
 	mr->hw_mr.pbl_page_size_log = ilog2(mr->info.pbl_info.pbl_size);
 	mr->hw_mr.page_size_log = PAGE_SHIFT;
-	mr->hw_mr.fbo = ib_umem_offset(mr->umem);
 	mr->hw_mr.length = len;
 	mr->hw_mr.vaddr = usr_addr;
-	mr->hw_mr.zbva = false;
 	mr->hw_mr.phy_mr = false;
 	mr->hw_mr.dma_mr = false;
 
@@ -2978,10 +2976,8 @@ static struct qedr_mr *__qedr_alloc_mr(struct ib_pd *ibpd,
 	mr->hw_mr.pbl_ptr = 0;
 	mr->hw_mr.pbl_two_level = mr->info.pbl_info.two_layered;
 	mr->hw_mr.pbl_page_size_log = ilog2(mr->info.pbl_info.pbl_size);
-	mr->hw_mr.fbo = 0;
 	mr->hw_mr.length = 0;
 	mr->hw_mr.vaddr = 0;
-	mr->hw_mr.zbva = false;
 	mr->hw_mr.phy_mr = true;
 	mr->hw_mr.dma_mr = false;
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
index 03894584415d..0df6e0587752 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
@@ -1521,7 +1521,7 @@ qed_rdma_register_tid(void *rdma_cxt,
 		  params->pbl_two_level);
 
 	SET_FIELD(flags, RDMA_REGISTER_TID_RAMROD_DATA_ZERO_BASED,
-		  params->zbva);
+		  false);
 
 	SET_FIELD(flags, RDMA_REGISTER_TID_RAMROD_DATA_PHY_MR, params->phy_mr);
 
@@ -1583,15 +1583,7 @@ qed_rdma_register_tid(void *rdma_cxt,
 	p_ramrod->pd = cpu_to_le16(params->pd);
 	p_ramrod->length_hi = (u8)(params->length >> 32);
 	p_ramrod->length_lo = DMA_LO_LE(params->length);
-	if (params->zbva) {
-		/* Lower 32 bits of the registered MR address.
-		 * In case of zero based MR, will hold FBO
-		 */
-		p_ramrod->va.hi = 0;
-		p_ramrod->va.lo = cpu_to_le32(params->fbo);
-	} else {
-		DMA_REGPAIR_LE(p_ramrod->va, params->vaddr);
-	}
+	DMA_REGPAIR_LE(p_ramrod->va, params->vaddr);
 	DMA_REGPAIR_LE(p_ramrod->pbl_base, params->pbl_ptr);
 
 	/* DIF */
diff --git a/include/linux/qed/qed_rdma_if.h b/include/linux/qed/qed_rdma_if.h
index f464d85e88a4..aeb242cefebf 100644
--- a/include/linux/qed/qed_rdma_if.h
+++ b/include/linux/qed/qed_rdma_if.h
@@ -242,10 +242,8 @@ struct qed_rdma_register_tid_in_params {
 	bool pbl_two_level;
 	u8 pbl_page_size_log;
 	u8 page_size_log;
-	u32 fbo;
 	u64 length;
 	u64 vaddr;
-	bool zbva;
 	bool phy_mr;
 	bool dma_mr;
 
-- 
cgit v1.2.3


From 97fb3e33474897c35b7cfe6ff0e16a3e172d9249 Mon Sep 17 00:00:00 2001
From: Michal Kalderon <michal.kalderon@marvell.com>
Date: Wed, 2 Sep 2020 19:57:38 +0300
Subject: qede: Notify qedr when mtu has changed

MTU change on ethtool is currently not supported for iWARP.  Notify qedr
driver so that appropriate logging can take place.

Link: https://lore.kernel.org/r/20200902165741.8355-6-michal.kalderon@marvell.com
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/net/ethernet/qlogic/qede/qede_ethtool.c |  4 +++-
 drivers/net/ethernet/qlogic/qede/qede_rdma.c    | 17 +++++++++++++++++
 include/linux/qed/qede_rdma.h                   |  4 +++-
 3 files changed, 23 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
index b9aa6384563b..bedbb85a179a 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
@@ -1026,7 +1026,9 @@ int qede_change_mtu(struct net_device *ndev, int new_mtu)
 	args.u.mtu = new_mtu;
 	args.func = &qede_update_mtu;
 	qede_reload(edev, &args, false);
-
+#if IS_ENABLED(CONFIG_QED_RDMA)
+	qede_rdma_event_change_mtu(edev);
+#endif
 	edev->ops->common->update_mtu(edev->cdev, new_mtu);
 
 	return 0;
diff --git a/drivers/net/ethernet/qlogic/qede/qede_rdma.c b/drivers/net/ethernet/qlogic/qede/qede_rdma.c
index 769ec2f4d0b7..2f6598086d9b 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_rdma.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_rdma.c
@@ -234,6 +234,15 @@ static void qede_rdma_changeaddr(struct qede_dev *edev)
 		qedr_drv->notify(edev->rdma_info.qedr_dev, QEDE_CHANGE_ADDR);
 }
 
+static void qede_rdma_change_mtu(struct qede_dev *edev)
+{
+	if (qede_rdma_supported(edev)) {
+		if (qedr_drv && edev->rdma_info.qedr_dev && qedr_drv->notify)
+			qedr_drv->notify(edev->rdma_info.qedr_dev,
+					 QEDE_CHANGE_MTU);
+	}
+}
+
 static struct qede_rdma_event_work *
 qede_rdma_get_free_event_node(struct qede_dev *edev)
 {
@@ -287,6 +296,9 @@ static void qede_rdma_handle_event(struct work_struct *work)
 	case QEDE_CHANGE_ADDR:
 		qede_rdma_changeaddr(edev);
 		break;
+	case QEDE_CHANGE_MTU:
+		qede_rdma_change_mtu(edev);
+		break;
 	default:
 		DP_NOTICE(edev, "Invalid rdma event %d", event);
 	}
@@ -338,3 +350,8 @@ void qede_rdma_event_changeaddr(struct qede_dev *edev)
 {
 	qede_rdma_add_event(edev, QEDE_CHANGE_ADDR);
 }
+
+void qede_rdma_event_change_mtu(struct qede_dev *edev)
+{
+	qede_rdma_add_event(edev, QEDE_CHANGE_MTU);
+}
diff --git a/include/linux/qed/qede_rdma.h b/include/linux/qed/qede_rdma.h
index 072da2f6da37..0d5564a59a59 100644
--- a/include/linux/qed/qede_rdma.h
+++ b/include/linux/qed/qede_rdma.h
@@ -20,7 +20,8 @@ enum qede_rdma_event {
 	QEDE_UP,
 	QEDE_DOWN,
 	QEDE_CHANGE_ADDR,
-	QEDE_CLOSE
+	QEDE_CLOSE,
+	QEDE_CHANGE_MTU,
 };
 
 struct qede_rdma_event_work {
@@ -54,6 +55,7 @@ void qede_rdma_dev_event_open(struct qede_dev *dev);
 void qede_rdma_dev_event_close(struct qede_dev *dev);
 void qede_rdma_dev_remove(struct qede_dev *dev, bool recovery);
 void qede_rdma_event_changeaddr(struct qede_dev *edr);
+void qede_rdma_event_change_mtu(struct qede_dev *edev);
 
 #else
 static inline int qede_rdma_dev_add(struct qede_dev *dev,
-- 
cgit v1.2.3


From 78ff97ebd4e9d02a99ca894b643c78c8fda7df5d Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Wed, 9 Sep 2020 16:10:57 +0200
Subject: iio: iio.h: fix a warning at the kernel-doc markup

There's a warning at iio.h kernel-doc markup:

	./include/linux/iio/iio.h:644: WARNING: Unknown target name: "devm".

Because it is using {devm_}foo notation. Well, this is not
a valid kernel-doc notation. Also, it prevents creating hyperlinks
to other documentation functions.

So, replace it to a better notation.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Acked-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/d8f2275c438c459ede4e6fba03ce719cc6ad898b.1599660067.git.mchehab+huawei@kernel.org
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 include/linux/iio/iio.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index e2df67a3b9ab..f1daaba9e706 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -641,7 +641,7 @@ static inline struct iio_dev *iio_device_get(struct iio_dev *indio_dev)
  *
  * This utility must be called between IIO device allocation
  * (via devm_iio_device_alloc()) & IIO device registration
- * (via {devm_}iio_device_register()).
+ * (via iio_device_register() and devm_iio_device_register())).
  * By default, the device allocation will also assign a parent device to
  * the IIO device object. In cases where devm_iio_device_alloc() is used,
  * sometimes the parent device must be different than the device used to
-- 
cgit v1.2.3


From 7b26410b05f8c262688de8a689ba8e5d0c3cff01 Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Mon, 31 Aug 2020 15:27:23 -0700
Subject: block: introduce part_[begin|end]_io_acct

These functions can be used to enable iostat for partitions on devices
like md, bcache.

Signed-off-by: Song Liu <songliubraving@fb.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c       | 39 +++++++++++++++++++++++++++++++++------
 include/linux/blkdev.h |  5 +++++
 2 files changed, 38 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-core.c b/block/blk-core.c
index 093649bd252e..ca3f0f00c943 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1324,10 +1324,9 @@ void blk_account_io_start(struct request *rq)
 	part_stat_unlock();
 }
 
-unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
-		unsigned int op)
+static unsigned long __part_start_io_acct(struct hd_struct *part,
+					  unsigned int sectors, unsigned int op)
 {
-	struct hd_struct *part = &disk->part0;
 	const int sgrp = op_stat_group(op);
 	unsigned long now = READ_ONCE(jiffies);
 
@@ -1340,12 +1339,26 @@ unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
 
 	return now;
 }
+
+unsigned long part_start_io_acct(struct gendisk *disk, struct hd_struct **part,
+				 struct bio *bio)
+{
+	*part = disk_map_sector_rcu(disk, bio->bi_iter.bi_sector);
+
+	return __part_start_io_acct(*part, bio_sectors(bio), bio_op(bio));
+}
+EXPORT_SYMBOL_GPL(part_start_io_acct);
+
+unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
+				 unsigned int op)
+{
+	return __part_start_io_acct(&disk->part0, sectors, op);
+}
 EXPORT_SYMBOL(disk_start_io_acct);
 
-void disk_end_io_acct(struct gendisk *disk, unsigned int op,
-		unsigned long start_time)
+static void __part_end_io_acct(struct hd_struct *part, unsigned int op,
+			       unsigned long start_time)
 {
-	struct hd_struct *part = &disk->part0;
 	const int sgrp = op_stat_group(op);
 	unsigned long now = READ_ONCE(jiffies);
 	unsigned long duration = now - start_time;
@@ -1356,6 +1369,20 @@ void disk_end_io_acct(struct gendisk *disk, unsigned int op,
 	part_stat_local_dec(part, in_flight[op_is_write(op)]);
 	part_stat_unlock();
 }
+
+void part_end_io_acct(struct hd_struct *part, struct bio *bio,
+		      unsigned long start_time)
+{
+	__part_end_io_acct(part, bio_op(bio), start_time);
+	hd_struct_put(part);
+}
+EXPORT_SYMBOL_GPL(part_end_io_acct);
+
+void disk_end_io_acct(struct gendisk *disk, unsigned int op,
+		      unsigned long start_time)
+{
+	__part_end_io_acct(&disk->part0, op, start_time);
+}
 EXPORT_SYMBOL(disk_end_io_acct);
 
 /*
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 37ec5a73d027..5bd96fbab9b4 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1933,6 +1933,11 @@ unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
 void disk_end_io_acct(struct gendisk *disk, unsigned int op,
 		unsigned long start_time);
 
+unsigned long part_start_io_acct(struct gendisk *disk, struct hd_struct **part,
+				 struct bio *bio);
+void part_end_io_acct(struct hd_struct *part, struct bio *bio,
+		      unsigned long start_time);
+
 /**
  * bio_start_io_acct - start I/O accounting for bio based drivers
  * @bio:	bio to start account for
-- 
cgit v1.2.3


From 568a36a69bad4f2efcfa4f94c83aa150a463735c Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 10 Sep 2020 19:48:54 +0300
Subject: net: dsa: tag_8021q: include missing refcount.h

The previous assumption was that the caller would already have this
header file included.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/dsa/8021q.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h
index 311aa04e7520..804750122c66 100644
--- a/include/linux/dsa/8021q.h
+++ b/include/linux/dsa/8021q.h
@@ -5,6 +5,7 @@
 #ifndef _NET_DSA_8021Q_H
 #define _NET_DSA_8021Q_H
 
+#include <linux/refcount.h>
 #include <linux/types.h>
 
 struct dsa_switch;
-- 
cgit v1.2.3


From 7e092af2f3b33694b9117ffd978d42b04ec4f260 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 10 Sep 2020 19:48:55 +0300
Subject: net: dsa: tag_8021q: setup tagging via a single function call

There is no point in calling dsa_port_setup_8021q_tagging for each
individual port. Additionally, it will become more difficult to do that
when we'll have a context structure to tag_8021q (next patch). So
refactor this now.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/sja1105/sja1105_main.c | 15 ++++-----------
 include/linux/dsa/8021q.h              |  6 ++----
 net/dsa/tag_8021q.c                    | 21 +++++++++++++++++++--
 3 files changed, 25 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index 5a28dfb36ec3..508494390e81 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -1934,18 +1934,11 @@ static void sja1105_crosschip_bridge_leave(struct dsa_switch *ds,
 static int sja1105_setup_8021q_tagging(struct dsa_switch *ds, bool enabled)
 {
 	struct sja1105_private *priv = ds->priv;
-	int rc, i;
+	int rc;
 
-	for (i = 0; i < SJA1105_NUM_PORTS; i++) {
-		priv->expect_dsa_8021q = true;
-		rc = dsa_port_setup_8021q_tagging(ds, i, enabled);
-		priv->expect_dsa_8021q = false;
-		if (rc < 0) {
-			dev_err(ds->dev, "Failed to setup VLAN tagging for port %d: %d\n",
-				i, rc);
-			return rc;
-		}
-	}
+	rc = dsa_8021q_setup(priv->ds, enabled);
+	if (rc)
+		return rc;
 
 	dev_info(ds->dev, "%s switch tagging\n",
 		 enabled ? "Enabled" : "Disabled");
diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h
index 804750122c66..8586d8cdf956 100644
--- a/include/linux/dsa/8021q.h
+++ b/include/linux/dsa/8021q.h
@@ -25,8 +25,7 @@ struct dsa_8021q_crosschip_link {
 
 #if IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q)
 
-int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index,
-				 bool enabled);
+int dsa_8021q_setup(struct dsa_switch *ds, bool enabled);
 
 int dsa_8021q_crosschip_bridge_join(struct dsa_switch *ds, int port,
 				    struct dsa_switch *other_ds,
@@ -57,8 +56,7 @@ bool vid_is_dsa_8021q(u16 vid);
 
 #else
 
-int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index,
-				 bool enabled)
+int dsa_8021q_setup(struct dsa_switch *ds, bool enabled)
 {
 	return 0;
 }
diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c
index 780b2a15ac9b..e38fdf5d4d03 100644
--- a/net/dsa/tag_8021q.c
+++ b/net/dsa/tag_8021q.c
@@ -209,7 +209,7 @@ static int dsa_8021q_vid_apply(struct dsa_switch *ds, int port, u16 vid,
  * +-+-----+-+-----+-+-----+-+-----+-+    +-+-----+-+-----+-+-----+-+-----+-+
  *   swp0    swp1    swp2    swp3           swp0    swp1    swp2    swp3
  */
-int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int port, bool enabled)
+static int dsa_8021q_setup_port(struct dsa_switch *ds, int port, bool enabled)
 {
 	int upstream = dsa_upstream_port(ds, port);
 	u16 rx_vid = dsa_8021q_rx_vid(ds, port);
@@ -275,7 +275,24 @@ int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int port, bool enabled)
 
 	return err;
 }
-EXPORT_SYMBOL_GPL(dsa_port_setup_8021q_tagging);
+
+int dsa_8021q_setup(struct dsa_switch *ds, bool enabled)
+{
+	int rc, port;
+
+	for (port = 0; port < ds->num_ports; port++) {
+		rc = dsa_8021q_setup_port(ds, port, enabled);
+		if (rc < 0) {
+			dev_err(ds->dev,
+				"Failed to setup VLAN tagging for port %d: %d\n",
+				port, rc);
+			return rc;
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dsa_8021q_setup);
 
 static int dsa_8021q_crosschip_link_apply(struct dsa_switch *ds, int port,
 					  struct dsa_switch *other_ds,
-- 
cgit v1.2.3


From 5899ee367ab3fec885aa04d9a2b573bf2e464e7f Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 10 Sep 2020 19:48:56 +0300
Subject: net: dsa: tag_8021q: add a context structure

While working on another tag_8021q driver implementation, some things
became apparent:

- It is not mandatory for a DSA driver to offload the tag_8021q VLANs by
  using the VLAN table per se. For example, it can add custom TCAM rules
  that simply encapsulate RX traffic, and redirect & decapsulate rules
  for TX traffic. For such a driver, it makes no sense to receive the
  tag_8021q configuration through the same callback as it receives the
  VLAN configuration from the bridge and the 8021q modules.

- Currently, sja1105 (the only tag_8021q user) sets a
  priv->expect_dsa_8021q variable to distinguish between the bridge
  calling, and tag_8021q calling. That can be improved, to say the
  least.

- The crosschip bridging operations are, in fact, stateful already. The
  list of crosschip_links must be kept by the caller and passed to the
  relevant tag_8021q functions.

So it would be nice if the tag_8021q configuration was more
self-contained. This patch attempts to do that.

Create a struct dsa_8021q_context which encapsulates a struct
dsa_switch, and has 2 function pointers for adding and deleting a VLAN.
These will replace the previous channel to the driver, which was through
the .port_vlan_add and .port_vlan_del callbacks of dsa_switch_ops.

Also put the list of crosschip_links into this dsa_8021q_context.
Drivers that don't support cross-chip bridging can simply omit to
initialize this list, as long as they dont call any cross-chip function.

The sja1105_vlan_add and sja1105_vlan_del functions are refactored into
a smaller sja1105_vlan_add_one, which now has 2 entry points:
- sja1105_vlan_add, from struct dsa_switch_ops
- sja1105_dsa_8021q_vlan_add, from the tag_8021q ops
But even this change is fairly trivial. It just reflects the fact that
for sja1105, the VLANs from these 2 channels end up in the same hardware
table. However that is not necessarily true in the general sense (and
that's the reason for making this change).

The rest of the patch is mostly plain refactoring of "ds" -> "ctx". The
dsa_8021q_context structure needs to be propagated because adding a VLAN
is now done through the ops function pointers inside of it.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/sja1105/sja1105.h      |   3 +-
 drivers/net/dsa/sja1105/sja1105_main.c | 213 +++++++++++++++++++--------------
 include/linux/dsa/8021q.h              |  46 ++++---
 net/dsa/tag_8021q.c                    | 127 ++++++++++----------
 4 files changed, 216 insertions(+), 173 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h
index ba70b40a9a95..a93f580b558a 100644
--- a/drivers/net/dsa/sja1105/sja1105.h
+++ b/drivers/net/dsa/sja1105/sja1105.h
@@ -210,14 +210,13 @@ struct sja1105_private {
 	struct dsa_switch *ds;
 	struct list_head dsa_8021q_vlans;
 	struct list_head bridge_vlans;
-	struct list_head crosschip_links;
 	struct sja1105_flow_block flow_block;
 	struct sja1105_port ports[SJA1105_NUM_PORTS];
 	/* Serializes transmission of management frames so that
 	 * the switch doesn't confuse them with one another.
 	 */
 	struct mutex mgmt_lock;
-	bool expect_dsa_8021q;
+	struct dsa_8021q_context *dsa_8021q_ctx;
 	enum sja1105_vlan_state vlan_state;
 	struct sja1105_cbs_entry *cbs;
 	struct sja1105_tagger_data tagger_data;
diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index 508494390e81..967430e8ceb8 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -1880,19 +1880,17 @@ static int sja1105_crosschip_bridge_join(struct dsa_switch *ds,
 		if (dsa_to_port(ds, port)->bridge_dev != br)
 			continue;
 
-		other_priv->expect_dsa_8021q = true;
-		rc = dsa_8021q_crosschip_bridge_join(ds, port, other_ds,
-						     other_port,
-						     &priv->crosschip_links);
-		other_priv->expect_dsa_8021q = false;
+		rc = dsa_8021q_crosschip_bridge_join(priv->dsa_8021q_ctx,
+						     port,
+						     other_priv->dsa_8021q_ctx,
+						     other_port);
 		if (rc)
 			return rc;
 
-		priv->expect_dsa_8021q = true;
-		rc = dsa_8021q_crosschip_bridge_join(other_ds, other_port, ds,
-						     port,
-						     &other_priv->crosschip_links);
-		priv->expect_dsa_8021q = false;
+		rc = dsa_8021q_crosschip_bridge_join(other_priv->dsa_8021q_ctx,
+						     other_port,
+						     priv->dsa_8021q_ctx,
+						     port);
 		if (rc)
 			return rc;
 	}
@@ -1919,15 +1917,13 @@ static void sja1105_crosschip_bridge_leave(struct dsa_switch *ds,
 		if (dsa_to_port(ds, port)->bridge_dev != br)
 			continue;
 
-		other_priv->expect_dsa_8021q = true;
-		dsa_8021q_crosschip_bridge_leave(ds, port, other_ds, other_port,
-						 &priv->crosschip_links);
-		other_priv->expect_dsa_8021q = false;
+		dsa_8021q_crosschip_bridge_leave(priv->dsa_8021q_ctx, port,
+						 other_priv->dsa_8021q_ctx,
+						 other_port);
 
-		priv->expect_dsa_8021q = true;
-		dsa_8021q_crosschip_bridge_leave(other_ds, other_port, ds, port,
-						 &other_priv->crosschip_links);
-		priv->expect_dsa_8021q = false;
+		dsa_8021q_crosschip_bridge_leave(other_priv->dsa_8021q_ctx,
+						 other_port,
+						 priv->dsa_8021q_ctx, port);
 	}
 }
 
@@ -1936,7 +1932,7 @@ static int sja1105_setup_8021q_tagging(struct dsa_switch *ds, bool enabled)
 	struct sja1105_private *priv = ds->priv;
 	int rc;
 
-	rc = dsa_8021q_setup(priv->ds, enabled);
+	rc = dsa_8021q_setup(priv->dsa_8021q_ctx, enabled);
 	if (rc)
 		return rc;
 
@@ -2142,12 +2138,12 @@ struct sja1105_crosschip_vlan {
 	bool untagged;
 	int port;
 	int other_port;
-	struct dsa_switch *other_ds;
+	struct dsa_8021q_context *other_ctx;
 };
 
 struct sja1105_crosschip_switch {
 	struct list_head list;
-	struct dsa_switch *other_ds;
+	struct dsa_8021q_context *other_ctx;
 };
 
 static int sja1105_commit_pvid(struct sja1105_private *priv)
@@ -2323,8 +2319,8 @@ sja1105_build_crosschip_subvlans(struct sja1105_private *priv,
 
 	INIT_LIST_HEAD(&crosschip_vlans);
 
-	list_for_each_entry(c, &priv->crosschip_links, list) {
-		struct sja1105_private *other_priv = c->other_ds->priv;
+	list_for_each_entry(c, &priv->dsa_8021q_ctx->crosschip_links, list) {
+		struct sja1105_private *other_priv = c->other_ctx->ds->priv;
 
 		if (other_priv->vlan_state == SJA1105_VLAN_FILTERING_FULL)
 			continue;
@@ -2334,7 +2330,7 @@ sja1105_build_crosschip_subvlans(struct sja1105_private *priv,
 		 */
 		if (!dsa_is_user_port(priv->ds, c->port))
 			continue;
-		if (!dsa_is_user_port(c->other_ds, c->other_port))
+		if (!dsa_is_user_port(c->other_ctx->ds, c->other_port))
 			continue;
 
 		/* Search for VLANs on the remote port */
@@ -2369,7 +2365,7 @@ sja1105_build_crosschip_subvlans(struct sja1105_private *priv,
 				    tmp->untagged == v->untagged &&
 				    tmp->port == c->port &&
 				    tmp->other_port == v->port &&
-				    tmp->other_ds == c->other_ds) {
+				    tmp->other_ctx == c->other_ctx) {
 					already_added = true;
 					break;
 				}
@@ -2387,14 +2383,14 @@ sja1105_build_crosschip_subvlans(struct sja1105_private *priv,
 			tmp->vid = v->vid;
 			tmp->port = c->port;
 			tmp->other_port = v->port;
-			tmp->other_ds = c->other_ds;
+			tmp->other_ctx = c->other_ctx;
 			tmp->untagged = v->untagged;
 			list_add(&tmp->list, &crosschip_vlans);
 		}
 	}
 
 	list_for_each_entry(tmp, &crosschip_vlans, list) {
-		struct sja1105_private *other_priv = tmp->other_ds->priv;
+		struct sja1105_private *other_priv = tmp->other_ctx->ds->priv;
 		int upstream = dsa_upstream_port(priv->ds, tmp->port);
 		int match, subvlan;
 		u16 rx_vid;
@@ -2411,7 +2407,7 @@ sja1105_build_crosschip_subvlans(struct sja1105_private *priv,
 			goto out;
 		}
 
-		rx_vid = dsa_8021q_rx_vid_subvlan(tmp->other_ds,
+		rx_vid = dsa_8021q_rx_vid_subvlan(tmp->other_ctx->ds,
 						  tmp->other_port,
 						  subvlan);
 
@@ -2486,11 +2482,11 @@ static int sja1105_notify_crosschip_switches(struct sja1105_private *priv)
 
 	INIT_LIST_HEAD(&crosschip_switches);
 
-	list_for_each_entry(c, &priv->crosschip_links, list) {
+	list_for_each_entry(c, &priv->dsa_8021q_ctx->crosschip_links, list) {
 		bool already_added = false;
 
 		list_for_each_entry(s, &crosschip_switches, list) {
-			if (s->other_ds == c->other_ds) {
+			if (s->other_ctx == c->other_ctx) {
 				already_added = true;
 				break;
 			}
@@ -2505,12 +2501,12 @@ static int sja1105_notify_crosschip_switches(struct sja1105_private *priv)
 			rc = -ENOMEM;
 			goto out;
 		}
-		s->other_ds = c->other_ds;
+		s->other_ctx = c->other_ctx;
 		list_add(&s->list, &crosschip_switches);
 	}
 
 	list_for_each_entry(s, &crosschip_switches, list) {
-		struct sja1105_private *other_priv = s->other_ds->priv;
+		struct sja1105_private *other_priv = s->other_ctx->ds->priv;
 
 		rc = sja1105_build_vlan_table(other_priv, false);
 		if (rc)
@@ -2611,16 +2607,6 @@ out:
 	return rc;
 }
 
-/* Select the list to which we should add this VLAN. */
-static struct list_head *sja1105_classify_vlan(struct sja1105_private *priv,
-					       u16 vid)
-{
-	if (priv->expect_dsa_8021q)
-		return &priv->dsa_8021q_vlans;
-
-	return &priv->bridge_vlans;
-}
-
 static int sja1105_vlan_prepare(struct dsa_switch *ds, int port,
 				const struct switchdev_obj_port_vlan *vlan)
 {
@@ -2635,7 +2621,7 @@ static int sja1105_vlan_prepare(struct dsa_switch *ds, int port,
 	 * configuration done by dsa_8021q.
 	 */
 	for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) {
-		if (!priv->expect_dsa_8021q && vid_is_dsa_8021q(vid)) {
+		if (vid_is_dsa_8021q(vid)) {
 			dev_err(ds->dev, "Range 1024-3071 reserved for dsa_8021q operation\n");
 			return -EBUSY;
 		}
@@ -2755,6 +2741,54 @@ static int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled)
 	return sja1105_setup_8021q_tagging(ds, want_tagging);
 }
 
+/* Returns number of VLANs added (0 or 1) on success,
+ * or a negative error code.
+ */
+static int sja1105_vlan_add_one(struct dsa_switch *ds, int port, u16 vid,
+				u16 flags, struct list_head *vlan_list)
+{
+	bool untagged = flags & BRIDGE_VLAN_INFO_UNTAGGED;
+	bool pvid = flags & BRIDGE_VLAN_INFO_PVID;
+	struct sja1105_bridge_vlan *v;
+
+	list_for_each_entry(v, vlan_list, list)
+		if (v->port == port && v->vid == vid &&
+		    v->untagged == untagged && v->pvid == pvid)
+			/* Already added */
+			return 0;
+
+	v = kzalloc(sizeof(*v), GFP_KERNEL);
+	if (!v) {
+		dev_err(ds->dev, "Out of memory while storing VLAN\n");
+		return -ENOMEM;
+	}
+
+	v->port = port;
+	v->vid = vid;
+	v->untagged = untagged;
+	v->pvid = pvid;
+	list_add(&v->list, vlan_list);
+
+	return 1;
+}
+
+/* Returns number of VLANs deleted (0 or 1) */
+static int sja1105_vlan_del_one(struct dsa_switch *ds, int port, u16 vid,
+				struct list_head *vlan_list)
+{
+	struct sja1105_bridge_vlan *v, *n;
+
+	list_for_each_entry_safe(v, n, vlan_list, list) {
+		if (v->port == port && v->vid == vid) {
+			list_del(&v->list);
+			kfree(v);
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
 static void sja1105_vlan_add(struct dsa_switch *ds, int port,
 			     const struct switchdev_obj_port_vlan *vlan)
 {
@@ -2764,38 +2798,12 @@ static void sja1105_vlan_add(struct dsa_switch *ds, int port,
 	int rc;
 
 	for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) {
-		bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
-		bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
-		struct sja1105_bridge_vlan *v;
-		struct list_head *vlan_list;
-		bool already_added = false;
-
-		vlan_list = sja1105_classify_vlan(priv, vid);
-
-		list_for_each_entry(v, vlan_list, list) {
-			if (v->port == port && v->vid == vid &&
-			    v->untagged == untagged && v->pvid == pvid) {
-				already_added = true;
-				break;
-			}
-		}
-
-		if (already_added)
-			continue;
-
-		v = kzalloc(sizeof(*v), GFP_KERNEL);
-		if (!v) {
-			dev_err(ds->dev, "Out of memory while storing VLAN\n");
+		rc = sja1105_vlan_add_one(ds, port, vid, vlan->flags,
+					  &priv->bridge_vlans);
+		if (rc < 0)
 			return;
-		}
-
-		v->port = port;
-		v->vid = vid;
-		v->untagged = untagged;
-		v->pvid = pvid;
-		list_add(&v->list, vlan_list);
-
-		vlan_table_changed = true;
+		if (rc > 0)
+			vlan_table_changed = true;
 	}
 
 	if (!vlan_table_changed)
@@ -2812,21 +2820,12 @@ static int sja1105_vlan_del(struct dsa_switch *ds, int port,
 	struct sja1105_private *priv = ds->priv;
 	bool vlan_table_changed = false;
 	u16 vid;
+	int rc;
 
 	for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) {
-		struct sja1105_bridge_vlan *v, *n;
-		struct list_head *vlan_list;
-
-		vlan_list = sja1105_classify_vlan(priv, vid);
-
-		list_for_each_entry_safe(v, n, vlan_list, list) {
-			if (v->port == port && v->vid == vid) {
-				list_del(&v->list);
-				kfree(v);
-				vlan_table_changed = true;
-				break;
-			}
-		}
+		rc = sja1105_vlan_del_one(ds, port, vid, &priv->bridge_vlans);
+		if (rc > 0)
+			vlan_table_changed = true;
 	}
 
 	if (!vlan_table_changed)
@@ -2835,6 +2834,36 @@ static int sja1105_vlan_del(struct dsa_switch *ds, int port,
 	return sja1105_build_vlan_table(priv, true);
 }
 
+static int sja1105_dsa_8021q_vlan_add(struct dsa_switch *ds, int port, u16 vid,
+				      u16 flags)
+{
+	struct sja1105_private *priv = ds->priv;
+	int rc;
+
+	rc = sja1105_vlan_add_one(ds, port, vid, flags, &priv->dsa_8021q_vlans);
+	if (rc <= 0)
+		return rc;
+
+	return sja1105_build_vlan_table(priv, true);
+}
+
+static int sja1105_dsa_8021q_vlan_del(struct dsa_switch *ds, int port, u16 vid)
+{
+	struct sja1105_private *priv = ds->priv;
+	int rc;
+
+	rc = sja1105_vlan_del_one(ds, port, vid, &priv->dsa_8021q_vlans);
+	if (!rc)
+		return 0;
+
+	return sja1105_build_vlan_table(priv, true);
+}
+
+static const struct dsa_8021q_ops sja1105_dsa_8021q_ops = {
+	.vlan_add	= sja1105_dsa_8021q_vlan_add,
+	.vlan_del	= sja1105_dsa_8021q_vlan_del,
+};
+
 static int sja1105_best_effort_vlan_filtering_get(struct sja1105_private *priv,
 						  bool *be_vlan)
 {
@@ -3497,7 +3526,15 @@ static int sja1105_probe(struct spi_device *spi)
 	mutex_init(&priv->ptp_data.lock);
 	mutex_init(&priv->mgmt_lock);
 
-	INIT_LIST_HEAD(&priv->crosschip_links);
+	priv->dsa_8021q_ctx = devm_kzalloc(dev, sizeof(*priv->dsa_8021q_ctx),
+					   GFP_KERNEL);
+	if (!priv->dsa_8021q_ctx)
+		return -ENOMEM;
+
+	priv->dsa_8021q_ctx->ops = &sja1105_dsa_8021q_ops;
+	priv->dsa_8021q_ctx->ds = ds;
+
+	INIT_LIST_HEAD(&priv->dsa_8021q_ctx->crosschip_links);
 	INIT_LIST_HEAD(&priv->bridge_vlans);
 	INIT_LIST_HEAD(&priv->dsa_8021q_vlans);
 
diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h
index 8586d8cdf956..2b003ae9fb38 100644
--- a/include/linux/dsa/8021q.h
+++ b/include/linux/dsa/8021q.h
@@ -12,30 +12,40 @@ struct dsa_switch;
 struct sk_buff;
 struct net_device;
 struct packet_type;
+struct dsa_8021q_context;
 
 struct dsa_8021q_crosschip_link {
 	struct list_head list;
 	int port;
-	struct dsa_switch *other_ds;
+	struct dsa_8021q_context *other_ctx;
 	int other_port;
 	refcount_t refcount;
 };
 
+struct dsa_8021q_ops {
+	int (*vlan_add)(struct dsa_switch *ds, int port, u16 vid, u16 flags);
+	int (*vlan_del)(struct dsa_switch *ds, int port, u16 vid);
+};
+
+struct dsa_8021q_context {
+	const struct dsa_8021q_ops *ops;
+	struct dsa_switch *ds;
+	struct list_head crosschip_links;
+};
+
 #define DSA_8021Q_N_SUBVLAN			8
 
 #if IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q)
 
-int dsa_8021q_setup(struct dsa_switch *ds, bool enabled);
+int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled);
 
-int dsa_8021q_crosschip_bridge_join(struct dsa_switch *ds, int port,
-				    struct dsa_switch *other_ds,
-				    int other_port,
-				    struct list_head *crosschip_links);
+int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port,
+				    struct dsa_8021q_context *other_ctx,
+				    int other_port);
 
-int dsa_8021q_crosschip_bridge_leave(struct dsa_switch *ds, int port,
-				     struct dsa_switch *other_ds,
-				     int other_port,
-				     struct list_head *crosschip_links);
+int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port,
+				     struct dsa_8021q_context *other_ctx,
+				     int other_port);
 
 struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev,
 			       u16 tpid, u16 tci);
@@ -56,23 +66,21 @@ bool vid_is_dsa_8021q(u16 vid);
 
 #else
 
-int dsa_8021q_setup(struct dsa_switch *ds, bool enabled)
+int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled)
 {
 	return 0;
 }
 
-int dsa_8021q_crosschip_bridge_join(struct dsa_switch *ds, int port,
-				    struct dsa_switch *other_ds,
-				    int other_port,
-				    struct list_head *crosschip_links)
+int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port,
+				    struct dsa_8021q_context *other_ctx,
+				    int other_port)
 {
 	return 0;
 }
 
-int dsa_8021q_crosschip_bridge_leave(struct dsa_switch *ds, int port,
-				     struct dsa_switch *other_ds,
-				     int other_port,
-				     struct list_head *crosschip_links)
+int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port,
+				     struct dsa_8021q_context *other_ctx,
+				     int other_port)
 {
 	return 0;
 }
diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c
index e38fdf5d4d03..5baeb0893950 100644
--- a/net/dsa/tag_8021q.c
+++ b/net/dsa/tag_8021q.c
@@ -146,15 +146,15 @@ EXPORT_SYMBOL_GPL(vid_is_dsa_8021q);
  * user explicitly configured this @vid through the bridge core, then the @vid
  * is installed again, but this time with the flags from the bridge layer.
  */
-static int dsa_8021q_vid_apply(struct dsa_switch *ds, int port, u16 vid,
+static int dsa_8021q_vid_apply(struct dsa_8021q_context *ctx, int port, u16 vid,
 			       u16 flags, bool enabled)
 {
-	struct dsa_port *dp = dsa_to_port(ds, port);
+	struct dsa_port *dp = dsa_to_port(ctx->ds, port);
 
 	if (enabled)
-		return dsa_port_vid_add(dp, vid, flags);
+		return ctx->ops->vlan_add(ctx->ds, dp->index, vid, flags);
 
-	return dsa_port_vid_del(dp, vid);
+	return ctx->ops->vlan_del(ctx->ds, dp->index, vid);
 }
 
 /* RX VLAN tagging (left) and TX VLAN tagging (right) setup shown for a single
@@ -209,17 +209,18 @@ static int dsa_8021q_vid_apply(struct dsa_switch *ds, int port, u16 vid,
  * +-+-----+-+-----+-+-----+-+-----+-+    +-+-----+-+-----+-+-----+-+-----+-+
  *   swp0    swp1    swp2    swp3           swp0    swp1    swp2    swp3
  */
-static int dsa_8021q_setup_port(struct dsa_switch *ds, int port, bool enabled)
+static int dsa_8021q_setup_port(struct dsa_8021q_context *ctx, int port,
+				bool enabled)
 {
-	int upstream = dsa_upstream_port(ds, port);
-	u16 rx_vid = dsa_8021q_rx_vid(ds, port);
-	u16 tx_vid = dsa_8021q_tx_vid(ds, port);
+	int upstream = dsa_upstream_port(ctx->ds, port);
+	u16 rx_vid = dsa_8021q_rx_vid(ctx->ds, port);
+	u16 tx_vid = dsa_8021q_tx_vid(ctx->ds, port);
 	int i, err;
 
 	/* The CPU port is implicitly configured by
 	 * configuring the front-panel ports
 	 */
-	if (!dsa_is_user_port(ds, port))
+	if (!dsa_is_user_port(ctx->ds, port))
 		return 0;
 
 	/* Add this user port's RX VID to the membership list of all others
@@ -227,7 +228,7 @@ static int dsa_8021q_setup_port(struct dsa_switch *ds, int port, bool enabled)
 	 * L2 forwarding rules still take precedence when there are no VLAN
 	 * restrictions, so there are no concerns about leaking traffic.
 	 */
-	for (i = 0; i < ds->num_ports; i++) {
+	for (i = 0; i < ctx->ds->num_ports; i++) {
 		u16 flags;
 
 		if (i == upstream)
@@ -240,9 +241,10 @@ static int dsa_8021q_setup_port(struct dsa_switch *ds, int port, bool enabled)
 			/* The RX VID is a regular VLAN on all others */
 			flags = BRIDGE_VLAN_INFO_UNTAGGED;
 
-		err = dsa_8021q_vid_apply(ds, i, rx_vid, flags, enabled);
+		err = dsa_8021q_vid_apply(ctx, i, rx_vid, flags, enabled);
 		if (err) {
-			dev_err(ds->dev, "Failed to apply RX VID %d to port %d: %d\n",
+			dev_err(ctx->ds->dev,
+				"Failed to apply RX VID %d to port %d: %d\n",
 				rx_vid, port, err);
 			return err;
 		}
@@ -251,24 +253,27 @@ static int dsa_8021q_setup_port(struct dsa_switch *ds, int port, bool enabled)
 	/* CPU port needs to see this port's RX VID
 	 * as tagged egress.
 	 */
-	err = dsa_8021q_vid_apply(ds, upstream, rx_vid, 0, enabled);
+	err = dsa_8021q_vid_apply(ctx, upstream, rx_vid, 0, enabled);
 	if (err) {
-		dev_err(ds->dev, "Failed to apply RX VID %d to port %d: %d\n",
+		dev_err(ctx->ds->dev,
+			"Failed to apply RX VID %d to port %d: %d\n",
 			rx_vid, port, err);
 		return err;
 	}
 
 	/* Finally apply the TX VID on this port and on the CPU port */
-	err = dsa_8021q_vid_apply(ds, port, tx_vid, BRIDGE_VLAN_INFO_UNTAGGED,
+	err = dsa_8021q_vid_apply(ctx, port, tx_vid, BRIDGE_VLAN_INFO_UNTAGGED,
 				  enabled);
 	if (err) {
-		dev_err(ds->dev, "Failed to apply TX VID %d on port %d: %d\n",
+		dev_err(ctx->ds->dev,
+			"Failed to apply TX VID %d on port %d: %d\n",
 			tx_vid, port, err);
 		return err;
 	}
-	err = dsa_8021q_vid_apply(ds, upstream, tx_vid, 0, enabled);
+	err = dsa_8021q_vid_apply(ctx, upstream, tx_vid, 0, enabled);
 	if (err) {
-		dev_err(ds->dev, "Failed to apply TX VID %d on port %d: %d\n",
+		dev_err(ctx->ds->dev,
+			"Failed to apply TX VID %d on port %d: %d\n",
 			tx_vid, upstream, err);
 		return err;
 	}
@@ -276,14 +281,14 @@ static int dsa_8021q_setup_port(struct dsa_switch *ds, int port, bool enabled)
 	return err;
 }
 
-int dsa_8021q_setup(struct dsa_switch *ds, bool enabled)
+int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled)
 {
 	int rc, port;
 
-	for (port = 0; port < ds->num_ports; port++) {
-		rc = dsa_8021q_setup_port(ds, port, enabled);
+	for (port = 0; port < ctx->ds->num_ports; port++) {
+		rc = dsa_8021q_setup_port(ctx, port, enabled);
 		if (rc < 0) {
-			dev_err(ds->dev,
+			dev_err(ctx->ds->dev,
 				"Failed to setup VLAN tagging for port %d: %d\n",
 				port, rc);
 			return rc;
@@ -294,54 +299,54 @@ int dsa_8021q_setup(struct dsa_switch *ds, bool enabled)
 }
 EXPORT_SYMBOL_GPL(dsa_8021q_setup);
 
-static int dsa_8021q_crosschip_link_apply(struct dsa_switch *ds, int port,
-					  struct dsa_switch *other_ds,
+static int dsa_8021q_crosschip_link_apply(struct dsa_8021q_context *ctx,
+					  int port,
+					  struct dsa_8021q_context *other_ctx,
 					  int other_port, bool enabled)
 {
-	u16 rx_vid = dsa_8021q_rx_vid(ds, port);
+	u16 rx_vid = dsa_8021q_rx_vid(ctx->ds, port);
 
 	/* @rx_vid of local @ds port @port goes to @other_port of
 	 * @other_ds
 	 */
-	return dsa_8021q_vid_apply(other_ds, other_port, rx_vid,
+	return dsa_8021q_vid_apply(other_ctx, other_port, rx_vid,
 				   BRIDGE_VLAN_INFO_UNTAGGED, enabled);
 }
 
-static int dsa_8021q_crosschip_link_add(struct dsa_switch *ds, int port,
-					struct dsa_switch *other_ds,
-					int other_port,
-					struct list_head *crosschip_links)
+static int dsa_8021q_crosschip_link_add(struct dsa_8021q_context *ctx, int port,
+					struct dsa_8021q_context *other_ctx,
+					int other_port)
 {
 	struct dsa_8021q_crosschip_link *c;
 
-	list_for_each_entry(c, crosschip_links, list) {
-		if (c->port == port && c->other_ds == other_ds &&
+	list_for_each_entry(c, &ctx->crosschip_links, list) {
+		if (c->port == port && c->other_ctx == other_ctx &&
 		    c->other_port == other_port) {
 			refcount_inc(&c->refcount);
 			return 0;
 		}
 	}
 
-	dev_dbg(ds->dev, "adding crosschip link from port %d to %s port %d\n",
-		port, dev_name(other_ds->dev), other_port);
+	dev_dbg(ctx->ds->dev,
+		"adding crosschip link from port %d to %s port %d\n",
+		port, dev_name(other_ctx->ds->dev), other_port);
 
 	c = kzalloc(sizeof(*c), GFP_KERNEL);
 	if (!c)
 		return -ENOMEM;
 
 	c->port = port;
-	c->other_ds = other_ds;
+	c->other_ctx = other_ctx;
 	c->other_port = other_port;
 	refcount_set(&c->refcount, 1);
 
-	list_add(&c->list, crosschip_links);
+	list_add(&c->list, &ctx->crosschip_links);
 
 	return 0;
 }
 
-static void dsa_8021q_crosschip_link_del(struct dsa_switch *ds,
+static void dsa_8021q_crosschip_link_del(struct dsa_8021q_context *ctx,
 					 struct dsa_8021q_crosschip_link *c,
-					 struct list_head *crosschip_links,
 					 bool *keep)
 {
 	*keep = !refcount_dec_and_test(&c->refcount);
@@ -349,9 +354,9 @@ static void dsa_8021q_crosschip_link_del(struct dsa_switch *ds,
 	if (*keep)
 		return;
 
-	dev_dbg(ds->dev,
+	dev_dbg(ctx->ds->dev,
 		"deleting crosschip link from port %d to %s port %d\n",
-		c->port, dev_name(c->other_ds->dev), c->other_port);
+		c->port, dev_name(c->other_ctx->ds->dev), c->other_port);
 
 	list_del(&c->list);
 	kfree(c);
@@ -364,64 +369,58 @@ static void dsa_8021q_crosschip_link_del(struct dsa_switch *ds,
  * or untagged: it doesn't matter, since it should never egress a frame having
  * our @rx_vid.
  */
-int dsa_8021q_crosschip_bridge_join(struct dsa_switch *ds, int port,
-				    struct dsa_switch *other_ds,
-				    int other_port,
-				    struct list_head *crosschip_links)
+int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port,
+				    struct dsa_8021q_context *other_ctx,
+				    int other_port)
 {
 	/* @other_upstream is how @other_ds reaches us. If we are part
 	 * of disjoint trees, then we are probably connected through
 	 * our CPU ports. If we're part of the same tree though, we should
 	 * probably use dsa_towards_port.
 	 */
-	int other_upstream = dsa_upstream_port(other_ds, other_port);
+	int other_upstream = dsa_upstream_port(other_ctx->ds, other_port);
 	int rc;
 
-	rc = dsa_8021q_crosschip_link_add(ds, port, other_ds,
-					  other_port, crosschip_links);
+	rc = dsa_8021q_crosschip_link_add(ctx, port, other_ctx, other_port);
 	if (rc)
 		return rc;
 
-	rc = dsa_8021q_crosschip_link_apply(ds, port, other_ds,
+	rc = dsa_8021q_crosschip_link_apply(ctx, port, other_ctx,
 					    other_port, true);
 	if (rc)
 		return rc;
 
-	rc = dsa_8021q_crosschip_link_add(ds, port, other_ds,
-					  other_upstream,
-					  crosschip_links);
+	rc = dsa_8021q_crosschip_link_add(ctx, port, other_ctx, other_upstream);
 	if (rc)
 		return rc;
 
-	return dsa_8021q_crosschip_link_apply(ds, port, other_ds,
+	return dsa_8021q_crosschip_link_apply(ctx, port, other_ctx,
 					      other_upstream, true);
 }
 EXPORT_SYMBOL_GPL(dsa_8021q_crosschip_bridge_join);
 
-int dsa_8021q_crosschip_bridge_leave(struct dsa_switch *ds, int port,
-				     struct dsa_switch *other_ds,
-				     int other_port,
-				     struct list_head *crosschip_links)
+int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port,
+				     struct dsa_8021q_context *other_ctx,
+				     int other_port)
 {
-	int other_upstream = dsa_upstream_port(other_ds, other_port);
+	int other_upstream = dsa_upstream_port(other_ctx->ds, other_port);
 	struct dsa_8021q_crosschip_link *c, *n;
 
-	list_for_each_entry_safe(c, n, crosschip_links, list) {
-		if (c->port == port && c->other_ds == other_ds &&
+	list_for_each_entry_safe(c, n, &ctx->crosschip_links, list) {
+		if (c->port == port && c->other_ctx == other_ctx &&
 		    (c->other_port == other_port ||
 		     c->other_port == other_upstream)) {
-			struct dsa_switch *other_ds = c->other_ds;
+			struct dsa_8021q_context *other_ctx = c->other_ctx;
 			int other_port = c->other_port;
 			bool keep;
 			int rc;
 
-			dsa_8021q_crosschip_link_del(ds, c, crosschip_links,
-						     &keep);
+			dsa_8021q_crosschip_link_del(ctx, c, &keep);
 			if (keep)
 				continue;
 
-			rc = dsa_8021q_crosschip_link_apply(ds, port,
-							    other_ds,
+			rc = dsa_8021q_crosschip_link_apply(ctx, port,
+							    other_ctx,
 							    other_port,
 							    false);
 			if (rc)
-- 
cgit v1.2.3


From 1623ad8ec04c771a54975fb84b22bc21c2dbcac1 Mon Sep 17 00:00:00 2001
From: Divya Koppera <Divya.Koppera@microchip.com>
Date: Fri, 11 Sep 2020 18:48:44 +0530
Subject: net: phy: mchp: Add support for LAN8814 QUAD PHY

LAN8814 is a low-power, quad-port triple-speed (10BASE-T/100BASETX/1000BASE-T)
Ethernet physical layer transceiver (PHY). It supports transmission and
reception of data on standard CAT-5, as well as CAT-5e and CAT-6, unshielded
twisted pair (UTP) cables.

LAN8814 supports industry-standard QSGMII (Quad Serial Gigabit Media
Independent Interface) and Q-USGMII (Quad Universal Serial Gigabit Media
Independent Interface) providing chip-to-chip connection to four Gigabit
Ethernet MACs using a single serialized link (differential pair) in each
direction.

The LAN8814 SKU supports high-accuracy timestamping functions to
support IEEE-1588 solutions using Microchip Ethernet switches, as well as
customer solutions based on SoCs and FPGAs.

The LAN8804 SKU has same features as that of LAN8814 SKU except that it does
not support 1588, SyncE, or Q-USGMII with PCH/MCH.

This adds support for 10BASE-T, 100BASE-TX, and 1000BASE-T,
QSGMII link with the MAC.

Signed-off-by: Divya Koppera<divya.koppera@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/micrel.c   | 14 ++++++++++++++
 include/linux/micrel_phy.h |  1 +
 2 files changed, 15 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 3fe552675dd2..a7f74b3b97af 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -1314,6 +1314,19 @@ static struct phy_driver ksphy_driver[] = {
 	.get_stats	= kszphy_get_stats,
 	.suspend	= genphy_suspend,
 	.resume		= kszphy_resume,
+}, {
+	.phy_id		= PHY_ID_LAN8814,
+	.phy_id_mask	= MICREL_PHY_ID_MASK,
+	.name		= "Microchip INDY Gigabit Quad PHY",
+	.driver_data	= &ksz9021_type,
+	.probe		= kszphy_probe,
+	.soft_reset	= genphy_soft_reset,
+	.read_status	= ksz9031_read_status,
+	.get_sset_count	= kszphy_get_sset_count,
+	.get_strings	= kszphy_get_strings,
+	.get_stats	= kszphy_get_stats,
+	.suspend	= genphy_suspend,
+	.resume		= kszphy_resume,
 }, {
 	.phy_id		= PHY_ID_KSZ9131,
 	.phy_id_mask	= MICREL_PHY_ID_MASK,
@@ -1387,6 +1400,7 @@ static struct mdio_device_id __maybe_unused micrel_tbl[] = {
 	{ PHY_ID_KSZ8081, MICREL_PHY_ID_MASK },
 	{ PHY_ID_KSZ8873MLL, MICREL_PHY_ID_MASK },
 	{ PHY_ID_KSZ886X, MICREL_PHY_ID_MASK },
+	{ PHY_ID_LAN8814, MICREL_PHY_ID_MASK },
 	{ }
 };
 
diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h
index 75f880c25bb8..416ee6dd2574 100644
--- a/include/linux/micrel_phy.h
+++ b/include/linux/micrel_phy.h
@@ -27,6 +27,7 @@
 #define PHY_ID_KSZ8061		0x00221570
 #define PHY_ID_KSZ9031		0x00221620
 #define PHY_ID_KSZ9131		0x00221640
+#define PHY_ID_LAN8814		0x00221660
 
 #define PHY_ID_KSZ886X		0x00221430
 #define PHY_ID_KSZ8863		0x00221435
-- 
cgit v1.2.3


From dc1129564a0147feb459159fd220ae22357e2eb6 Mon Sep 17 00:00:00 2001
From: Suman Anna <s-anna@ti.com>
Date: Fri, 11 Sep 2020 21:43:34 -0700
Subject: soc: ti: pruss: Add a platform driver for PRUSS in TI SoCs

The Programmable Real-Time Unit - Industrial Communication
Subsystem (PRU-ICSS) is present on various TI SoCs such as
AM335x or AM437x or the Keystone 66AK2G. Each SoC can have
one or more PRUSS instances that may or may not be identical.
For example, AM335x SoCs have a single PRUSS, while AM437x has
two PRUSS instances PRUSS1 and PRUSS0, with the PRUSS0 being
a cut-down version of the PRUSS1.

The PRUSS consists of dual 32-bit RISC cores called the
Programmable Real-Time Units (PRUs), some shared, data and
instruction memories, some internal peripheral modules, and
an interrupt controller. The programmable nature of the PRUs
provide flexibility to implement custom peripheral interfaces,
fast real-time responses, or specialized data handling.

The PRU-ICSS functionality is achieved through three different
platform drivers addressing a specific portion of the PRUSS.
Some sub-modules of the PRU-ICSS IP reuse some of the existing
drivers (like davinci mdio driver or the generic syscon driver).
This design provides flexibility in representing the different
modules of PRUSS accordingly, and at the same time allowing the
PRUSS driver to add some instance specific configuration within
an SoC.

The PRUSS platform driver deals with the overall PRUSS and is
used for managing the subsystem level resources like various
memories and the CFG module. It is responsible for the creation
and deletion of the platform devices for the child PRU devices
and other child devices (like Interrupt Controller, MDIO node
and some syscon nodes) so that they can be managed by specific
platform drivers. The PRUSS interrupt controller is managed by
an irqchip driver, while the individual PRU RISC cores are
managed by a PRU remoteproc driver.

The driver currently supports the AM335x SoC, and support for
other TI SoCs will be added in subsequent patches.

Signed-off-by: Suman Anna <s-anna@ti.com>
Signed-off-by: Andrew F. Davis <afd@ti.com>
Signed-off-by: Tero Kristo <t-kristo@ti.com>
Signed-off-by: Grzegorz Jaszczyk <grzegorz.jaszczyk@linaro.org>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
---
 drivers/soc/ti/Kconfig       |  11 ++++
 drivers/soc/ti/Makefile      |   1 +
 drivers/soc/ti/pruss.c       | 147 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/pruss_driver.h |  48 ++++++++++++++
 4 files changed, 207 insertions(+)
 create mode 100644 drivers/soc/ti/pruss.c
 create mode 100644 include/linux/pruss_driver.h

(limited to 'include/linux')

diff --git a/drivers/soc/ti/Kconfig b/drivers/soc/ti/Kconfig
index e192fb788836..b934bc341d26 100644
--- a/drivers/soc/ti/Kconfig
+++ b/drivers/soc/ti/Kconfig
@@ -101,6 +101,17 @@ config TI_K3_SOCINFO
 	  platforms to provide information about the SoC family and
 	  variant to user space.
 
+config TI_PRUSS
+	tristate "TI PRU-ICSS Subsystem Platform drivers"
+	depends on SOC_AM33XX
+	select MFD_SYSCON
+	help
+	  TI PRU-ICSS Subsystem platform specific support.
+
+	  Say Y or M here to support the Programmable Realtime Unit (PRU)
+	  processors on various TI SoCs. It's safe to say N here if you're
+	  not interested in the PRU or if you are unsure.
+
 endif # SOC_TI
 
 config TI_SCI_INTA_MSI_DOMAIN
diff --git a/drivers/soc/ti/Makefile b/drivers/soc/ti/Makefile
index 1110e5c98685..18129aa557df 100644
--- a/drivers/soc/ti/Makefile
+++ b/drivers/soc/ti/Makefile
@@ -12,3 +12,4 @@ obj-$(CONFIG_TI_SCI_PM_DOMAINS)		+= ti_sci_pm_domains.o
 obj-$(CONFIG_TI_SCI_INTA_MSI_DOMAIN)	+= ti_sci_inta_msi.o
 obj-$(CONFIG_TI_K3_RINGACC)		+= k3-ringacc.o
 obj-$(CONFIG_TI_K3_SOCINFO)		+= k3-socinfo.o
+obj-$(CONFIG_TI_PRUSS)			+= pruss.o
diff --git a/drivers/soc/ti/pruss.c b/drivers/soc/ti/pruss.c
new file mode 100644
index 000000000000..c071bb2e1c33
--- /dev/null
+++ b/drivers/soc/ti/pruss.c
@@ -0,0 +1,147 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * PRU-ICSS platform driver for various TI SoCs
+ *
+ * Copyright (C) 2014-2020 Texas Instruments Incorporated - http://www.ti.com/
+ * Author(s):
+ *	Suman Anna <s-anna@ti.com>
+ *	Andrew F. Davis <afd@ti.com>
+ */
+
+#include <linux/dma-mapping.h>
+#include <linux/io.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/pruss_driver.h>
+
+static int pruss_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev_of_node(dev);
+	struct device_node *child;
+	struct pruss *pruss;
+	struct resource res;
+	int ret, i, index;
+	const char *mem_names[PRUSS_MEM_MAX] = { "dram0", "dram1", "shrdram2" };
+
+	ret = dma_set_coherent_mask(dev, DMA_BIT_MASK(32));
+	if (ret) {
+		dev_err(dev, "failed to set the DMA coherent mask");
+		return ret;
+	}
+
+	pruss = devm_kzalloc(dev, sizeof(*pruss), GFP_KERNEL);
+	if (!pruss)
+		return -ENOMEM;
+
+	pruss->dev = dev;
+
+	child = of_get_child_by_name(np, "memories");
+	if (!child) {
+		dev_err(dev, "%pOF is missing its 'memories' node\n", child);
+		return -ENODEV;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(mem_names); i++) {
+		index = of_property_match_string(child, "reg-names",
+						 mem_names[i]);
+		if (index < 0) {
+			of_node_put(child);
+			return index;
+		}
+
+		if (of_address_to_resource(child, index, &res)) {
+			of_node_put(child);
+			return -EINVAL;
+		}
+
+		pruss->mem_regions[i].va = devm_ioremap(dev, res.start,
+							resource_size(&res));
+		if (!pruss->mem_regions[i].va) {
+			dev_err(dev, "failed to parse and map memory resource %d %s\n",
+				i, mem_names[i]);
+			of_node_put(child);
+			return -ENOMEM;
+		}
+		pruss->mem_regions[i].pa = res.start;
+		pruss->mem_regions[i].size = resource_size(&res);
+
+		dev_dbg(dev, "memory %8s: pa %pa size 0x%zx va %pK\n",
+			mem_names[i], &pruss->mem_regions[i].pa,
+			pruss->mem_regions[i].size, pruss->mem_regions[i].va);
+	}
+	of_node_put(child);
+
+	platform_set_drvdata(pdev, pruss);
+
+	pm_runtime_enable(dev);
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0) {
+		dev_err(dev, "couldn't enable module\n");
+		pm_runtime_put_noidle(dev);
+		goto rpm_disable;
+	}
+
+	child = of_get_child_by_name(np, "cfg");
+	if (!child) {
+		dev_err(dev, "%pOF is missing its 'cfg' node\n", child);
+		ret = -ENODEV;
+		goto rpm_put;
+	}
+
+	pruss->cfg_regmap = syscon_node_to_regmap(child);
+	of_node_put(child);
+	if (IS_ERR(pruss->cfg_regmap)) {
+		ret = -ENODEV;
+		goto rpm_put;
+	}
+
+	ret = devm_of_platform_populate(dev);
+	if (ret) {
+		dev_err(dev, "failed to register child devices\n");
+		goto rpm_put;
+	}
+
+	return 0;
+
+rpm_put:
+	pm_runtime_put_sync(dev);
+rpm_disable:
+	pm_runtime_disable(dev);
+	return ret;
+}
+
+static int pruss_remove(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+
+	devm_of_platform_depopulate(dev);
+
+	pm_runtime_put_sync(dev);
+	pm_runtime_disable(dev);
+
+	return 0;
+}
+
+static const struct of_device_id pruss_of_match[] = {
+	{ .compatible = "ti,am3356-pruss" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, pruss_of_match);
+
+static struct platform_driver pruss_driver = {
+	.driver = {
+		.name = "pruss",
+		.of_match_table = pruss_of_match,
+	},
+	.probe  = pruss_probe,
+	.remove = pruss_remove,
+};
+module_platform_driver(pruss_driver);
+
+MODULE_AUTHOR("Suman Anna <s-anna@ti.com>");
+MODULE_DESCRIPTION("PRU-ICSS Subsystem Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/pruss_driver.h b/include/linux/pruss_driver.h
new file mode 100644
index 000000000000..0701fe1953dd
--- /dev/null
+++ b/include/linux/pruss_driver.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * PRU-ICSS sub-system specific definitions
+ *
+ * Copyright (C) 2014-2020 Texas Instruments Incorporated - http://www.ti.com/
+ *	Suman Anna <s-anna@ti.com>
+ */
+
+#ifndef _PRUSS_DRIVER_H_
+#define _PRUSS_DRIVER_H_
+
+#include <linux/types.h>
+
+/*
+ * enum pruss_mem - PRUSS memory range identifiers
+ */
+enum pruss_mem {
+	PRUSS_MEM_DRAM0 = 0,
+	PRUSS_MEM_DRAM1,
+	PRUSS_MEM_SHRD_RAM2,
+	PRUSS_MEM_MAX,
+};
+
+/**
+ * struct pruss_mem_region - PRUSS memory region structure
+ * @va: kernel virtual address of the PRUSS memory region
+ * @pa: physical (bus) address of the PRUSS memory region
+ * @size: size of the PRUSS memory region
+ */
+struct pruss_mem_region {
+	void __iomem *va;
+	phys_addr_t pa;
+	size_t size;
+};
+
+/**
+ * struct pruss - PRUSS parent structure
+ * @dev: pruss device pointer
+ * @cfg_regmap: regmap for config region
+ * @mem_regions: data for each of the PRUSS memory regions
+ */
+struct pruss {
+	struct device *dev;
+	struct regmap *cfg_regmap;
+	struct pruss_mem_region mem_regions[PRUSS_MEM_MAX];
+};
+
+#endif	/* _PRUSS_DRIVER_H_ */
-- 
cgit v1.2.3


From ba59c9b43c86b2c2396acac94e41d946cbaec9fe Mon Sep 17 00:00:00 2001
From: Grzegorz Jaszczyk <grzegorz.jaszczyk@linaro.org>
Date: Fri, 11 Sep 2020 21:47:10 -0700
Subject: soc: ti: pruss: support CORECLK_MUX and IEPCLK_MUX

The IEPCLK_MUX is present on all SoCs whereas the CORECLK_MUX is present
only on AM65x SoCs and J721E. Add support for both these CLK muxes.

This allows the clock rates and clock parents for these to be controlled
through DT leveraging the clk infrastructure for configuring the default
parents and rates.

Signed-off-by: Roger Quadros <rogerq@ti.com>
Signed-off-by: Suman Anna <s-anna@ti.com>
Signed-off-by: Grzegorz Jaszczyk <grzegorz.jaszczyk@linaro.org>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
---
 drivers/soc/ti/pruss.c       | 184 +++++++++++++++++++++++++++++++++++++++++--
 include/linux/pruss_driver.h |   6 ++
 2 files changed, 183 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/soc/ti/pruss.c b/drivers/soc/ti/pruss.c
index 37df543998ef..cc0b4ad7a3d3 100644
--- a/drivers/soc/ti/pruss.c
+++ b/drivers/soc/ti/pruss.c
@@ -8,6 +8,7 @@
  *	Andrew F. Davis <afd@ti.com>
  */
 
+#include <linux/clk-provider.h>
 #include <linux/dma-mapping.h>
 #include <linux/io.h>
 #include <linux/mfd/syscon.h>
@@ -16,13 +17,150 @@
 #include <linux/of_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/pruss_driver.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
 
 /**
  * struct pruss_private_data - PRUSS driver private data
  * @has_no_sharedram: flag to indicate the absence of PRUSS Shared Data RAM
+ * @has_core_mux_clock: flag to indicate the presence of PRUSS core clock
  */
 struct pruss_private_data {
 	bool has_no_sharedram;
+	bool has_core_mux_clock;
+};
+
+static void pruss_of_free_clk_provider(void *data)
+{
+	struct device_node *clk_mux_np = data;
+
+	of_clk_del_provider(clk_mux_np);
+	of_node_put(clk_mux_np);
+}
+
+static int pruss_clk_mux_setup(struct pruss *pruss, struct clk *clk_mux,
+			       char *mux_name, struct device_node *clks_np)
+{
+	struct device_node *clk_mux_np;
+	struct device *dev = pruss->dev;
+	char *clk_mux_name;
+	unsigned int num_parents;
+	const char **parent_names;
+	void __iomem *reg;
+	u32 reg_offset;
+	int ret;
+
+	clk_mux_np = of_get_child_by_name(clks_np, mux_name);
+	if (!clk_mux_np) {
+		dev_err(dev, "%pOF is missing its '%s' node\n", clks_np,
+			mux_name);
+		return -ENODEV;
+	}
+
+	num_parents = of_clk_get_parent_count(clk_mux_np);
+	if (num_parents < 1) {
+		dev_err(dev, "mux-clock %pOF must have parents\n", clk_mux_np);
+		ret = -EINVAL;
+		goto put_clk_mux_np;
+	}
+
+	parent_names = devm_kcalloc(dev, sizeof(*parent_names), num_parents,
+				    GFP_KERNEL);
+	if (!parent_names) {
+		ret = -ENOMEM;
+		goto put_clk_mux_np;
+	}
+
+	of_clk_parent_fill(clk_mux_np, parent_names, num_parents);
+
+	clk_mux_name = devm_kasprintf(dev, GFP_KERNEL, "%s.%pOFn",
+				      dev_name(dev), clk_mux_np);
+	if (!clk_mux_name) {
+		ret = -ENOMEM;
+		goto put_clk_mux_np;
+	}
+
+	ret = of_property_read_u32(clk_mux_np, "reg", &reg_offset);
+	if (ret)
+		goto put_clk_mux_np;
+
+	reg = pruss->cfg_base + reg_offset;
+
+	clk_mux = clk_register_mux(NULL, clk_mux_name, parent_names,
+				   num_parents, 0, reg, 0, 1, 0, NULL);
+	if (IS_ERR(clk_mux)) {
+		ret = PTR_ERR(clk_mux);
+		goto put_clk_mux_np;
+	}
+
+	ret = devm_add_action_or_reset(dev, (void(*)(void *))clk_unregister_mux,
+				       clk_mux);
+	if (ret) {
+		dev_err(dev, "failed to add clkmux unregister action %d", ret);
+		goto put_clk_mux_np;
+	}
+
+	ret = of_clk_add_provider(clk_mux_np, of_clk_src_simple_get, clk_mux);
+	if (ret)
+		goto put_clk_mux_np;
+
+	ret = devm_add_action_or_reset(dev, pruss_of_free_clk_provider,
+				       clk_mux_np);
+	if (ret) {
+		dev_err(dev, "failed to add clkmux free action %d", ret);
+		goto put_clk_mux_np;
+	}
+
+	return 0;
+
+put_clk_mux_np:
+	of_node_put(clk_mux_np);
+	return ret;
+}
+
+static int pruss_clk_init(struct pruss *pruss, struct device_node *cfg_node)
+{
+	const struct pruss_private_data *data;
+	struct device_node *clks_np;
+	struct device *dev = pruss->dev;
+	int ret = 0;
+
+	data = of_device_get_match_data(dev);
+	if (IS_ERR(data))
+		return -ENODEV;
+
+	clks_np = of_get_child_by_name(cfg_node, "clocks");
+	if (!clks_np) {
+		dev_err(dev, "%pOF is missing its 'clocks' node\n", clks_np);
+		return -ENODEV;
+	}
+
+	if (data && data->has_core_mux_clock) {
+		ret = pruss_clk_mux_setup(pruss, pruss->core_clk_mux,
+					  "coreclk-mux", clks_np);
+		if (ret) {
+			dev_err(dev, "failed to setup coreclk-mux\n");
+			goto put_clks_node;
+		}
+	}
+
+	ret = pruss_clk_mux_setup(pruss, pruss->iep_clk_mux, "iepclk-mux",
+				  clks_np);
+	if (ret) {
+		dev_err(dev, "failed to setup iepclk-mux\n");
+		goto put_clks_node;
+	}
+
+put_clks_node:
+	of_node_put(clks_np);
+
+	return ret;
+}
+
+static struct regmap_config regmap_conf = {
+	.reg_bits = 32,
+	.val_bits = 32,
+	.reg_stride = 4,
 };
 
 static int pruss_probe(struct platform_device *pdev)
@@ -114,21 +252,49 @@ static int pruss_probe(struct platform_device *pdev)
 		goto rpm_put;
 	}
 
-	pruss->cfg_regmap = syscon_node_to_regmap(child);
-	of_node_put(child);
+	if (of_address_to_resource(child, 0, &res)) {
+		ret = -ENOMEM;
+		goto node_put;
+	}
+
+	pruss->cfg_base = devm_ioremap(dev, res.start, resource_size(&res));
+	if (!pruss->cfg_base) {
+		ret = -ENOMEM;
+		goto node_put;
+	}
+
+	regmap_conf.name = kasprintf(GFP_KERNEL, "%pOFn@%llx", child,
+				     (u64)res.start);
+	regmap_conf.max_register = resource_size(&res) - 4;
+
+	pruss->cfg_regmap = devm_regmap_init_mmio(dev, pruss->cfg_base,
+						  &regmap_conf);
+	kfree(regmap_conf.name);
 	if (IS_ERR(pruss->cfg_regmap)) {
-		ret = -ENODEV;
-		goto rpm_put;
+		dev_err(dev, "regmap_init_mmio failed for cfg, ret = %ld\n",
+			PTR_ERR(pruss->cfg_regmap));
+		ret = PTR_ERR(pruss->cfg_regmap);
+		goto node_put;
+	}
+
+	ret = pruss_clk_init(pruss, child);
+	if (ret) {
+		dev_err(dev, "failed to setup coreclk-mux\n");
+		goto node_put;
 	}
 
 	ret = devm_of_platform_populate(dev);
 	if (ret) {
 		dev_err(dev, "failed to register child devices\n");
-		goto rpm_put;
+		goto node_put;
 	}
 
+	of_node_put(child);
+
 	return 0;
 
+node_put:
+	of_node_put(child);
 rpm_put:
 	pm_runtime_put_sync(dev);
 rpm_disable:
@@ -157,14 +323,18 @@ static const struct pruss_private_data am437x_pruss0_data = {
 	.has_no_sharedram = true,
 };
 
+static const struct pruss_private_data am65x_j721e_pruss_data = {
+	.has_core_mux_clock = true,
+};
+
 static const struct of_device_id pruss_of_match[] = {
 	{ .compatible = "ti,am3356-pruss" },
 	{ .compatible = "ti,am4376-pruss0", .data = &am437x_pruss0_data, },
 	{ .compatible = "ti,am4376-pruss1", .data = &am437x_pruss1_data, },
 	{ .compatible = "ti,am5728-pruss" },
 	{ .compatible = "ti,k2g-pruss" },
-	{ .compatible = "ti,am654-icssg" },
-	{ .compatible = "ti,j721e-icssg" },
+	{ .compatible = "ti,am654-icssg", .data = &am65x_j721e_pruss_data, },
+	{ .compatible = "ti,j721e-icssg", .data = &am65x_j721e_pruss_data, },
 	{},
 };
 MODULE_DEVICE_TABLE(of, pruss_of_match);
diff --git a/include/linux/pruss_driver.h b/include/linux/pruss_driver.h
index 0701fe1953dd..ecfded30ed05 100644
--- a/include/linux/pruss_driver.h
+++ b/include/linux/pruss_driver.h
@@ -36,13 +36,19 @@ struct pruss_mem_region {
 /**
  * struct pruss - PRUSS parent structure
  * @dev: pruss device pointer
+ * @cfg_base: base iomap for CFG region
  * @cfg_regmap: regmap for config region
  * @mem_regions: data for each of the PRUSS memory regions
+ * @core_clk_mux: clk handle for PRUSS CORE_CLK_MUX
+ * @iep_clk_mux: clk handle for PRUSS IEP_CLK_MUX
  */
 struct pruss {
 	struct device *dev;
+	void __iomem *cfg_base;
 	struct regmap *cfg_regmap;
 	struct pruss_mem_region mem_regions[PRUSS_MEM_MAX];
+	struct clk *core_clk_mux;
+	struct clk *iep_clk_mux;
 };
 
 #endif	/* _PRUSS_DRIVER_H_ */
-- 
cgit v1.2.3


From 2fc7b1561fbe502f7a08f3df7e0d0cecee985966 Mon Sep 17 00:00:00 2001
From: Rob Clark <robdclark@chromium.org>
Date: Mon, 17 Aug 2020 15:01:30 -0700
Subject: drm/msm: Add private interface for adreno-smmu

This interface will be used for drm/msm to coordinate with the
qcom_adreno_smmu_impl to enable/disable TTBR0 translation.

Once TTBR0 translation is enabled, the GPU's CP (Command Processor)
will directly switch TTBR0 pgtables (and do the necessary TLB inv)
synchronized to the GPU's operation.  But help from the SMMU driver
is needed to initially bootstrap TTBR0 translation, which cannot be
done from the GPU.

Since this is a very special case, a private interface is used to
avoid adding highly driver specific things to the public iommu
interface.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Jordan Crouse <jcrouse@codeaurora.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 include/linux/adreno-smmu-priv.h | 36 ++++++++++++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)
 create mode 100644 include/linux/adreno-smmu-priv.h

(limited to 'include/linux')

diff --git a/include/linux/adreno-smmu-priv.h b/include/linux/adreno-smmu-priv.h
new file mode 100644
index 000000000000..a889f28afb42
--- /dev/null
+++ b/include/linux/adreno-smmu-priv.h
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 Google, Inc
+ */
+
+#ifndef __ADRENO_SMMU_PRIV_H
+#define __ADRENO_SMMU_PRIV_H
+
+#include <linux/io-pgtable.h>
+
+/**
+ * struct adreno_smmu_priv - private interface between adreno-smmu and GPU
+ *
+ * @cookie:        An opque token provided by adreno-smmu and passed
+ *                 back into the callbacks
+ * @get_ttbr1_cfg: Get the TTBR1 config for the GPUs context-bank
+ * @set_ttbr0_cfg: Set the TTBR0 config for the GPUs context bank.  A
+ *                 NULL config disables TTBR0 translation, otherwise
+ *                 TTBR0 translation is enabled with the specified cfg
+ *
+ * The GPU driver (drm/msm) and adreno-smmu work together for controlling
+ * the GPU's SMMU instance.  This is by necessity, as the GPU is directly
+ * updating the SMMU for context switches, while on the other hand we do
+ * not want to duplicate all of the initial setup logic from arm-smmu.
+ *
+ * This private interface is used for the two drivers to coordinate.  The
+ * cookie and callback functions are populated when the GPU driver attaches
+ * it's domain.
+ */
+struct adreno_smmu_priv {
+    const void *cookie;
+    const struct io_pgtable_cfg *(*get_ttbr1_cfg)(const void *cookie);
+    int (*set_ttbr0_cfg)(const void *cookie, const struct io_pgtable_cfg *cfg);
+};
+
+#endif /* __ADRENO_SMMU_PRIV_H */
\ No newline at end of file
-- 
cgit v1.2.3


From dde8ceec9e29fe2abf4fabee7d5a0445d0b75b66 Mon Sep 17 00:00:00 2001
From: Crt Mori <cmo@melexis.com>
Date: Sun, 6 Sep 2020 23:02:31 +0200
Subject: iio: temperature: mlx90632: Interface to change object ambient
 temperature

Since object temperature might be different than the sensor temperature
the infrared sensors should provide an interface to inject ambient
temperature. This was in past done via write to ambient temperature
interface (in_temp_ambient_raw), but I think most people did not know
about it. This solution introduces a new iio type of the CALIBAMBIENT
which is hopefully more descriptive and more explicit about the purpose
and capabilities of the sensors.

Signed-off-by: Crt Mori <cmo@melexis.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20200906210231.383976-1-cmo@melexis.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 Documentation/ABI/testing/sysfs-bus-iio | 8 ++++++++
 drivers/iio/industrialio-core.c         | 1 +
 drivers/iio/temperature/mlx90632.c      | 9 +++++++--
 include/linux/iio/types.h               | 1 +
 4 files changed, 17 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio
index c20334454dbf..a9d51810a3ba 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio
+++ b/Documentation/ABI/testing/sysfs-bus-iio
@@ -1758,6 +1758,14 @@ Contact:	linux-iio@vger.kernel.org
 Description:
 		One of the following thermocouple types: B, E, J, K, N, R, S, T.
 
+What:		/sys/bus/iio/devices/iio:deviceX/in_temp_object_calibambient
+What:		/sys/bus/iio/devices/iio:deviceX/in_tempX_object_calibambient
+KernelVersion:	5.10
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Calibrated ambient temperature for object temperature
+		calculation in milli degrees Celsius.
+
 What:		/sys/bus/iio/devices/iio:deviceX/in_intensity_x_raw
 What:		/sys/bus/iio/devices/iio:deviceX/in_intensity_y_raw
 What:		/sys/bus/iio/devices/iio:deviceX/in_intensity_z_raw
diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index 59003dc44e60..8ddc6dfc8ed4 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -166,6 +166,7 @@ static const char * const iio_chan_info_postfix[] = {
 	[IIO_CHAN_INFO_CALIBEMISSIVITY] = "calibemissivity",
 	[IIO_CHAN_INFO_OVERSAMPLING_RATIO] = "oversampling_ratio",
 	[IIO_CHAN_INFO_THERMOCOUPLE_TYPE] = "thermocouple_type",
+	[IIO_CHAN_INFO_CALIBAMBIENT] = "calibambient",
 };
 
 #if defined(CONFIG_DEBUG_FS)
diff --git a/drivers/iio/temperature/mlx90632.c b/drivers/iio/temperature/mlx90632.c
index 472a7fb20615..503fe54a0bb9 100644
--- a/drivers/iio/temperature/mlx90632.c
+++ b/drivers/iio/temperature/mlx90632.c
@@ -761,7 +761,9 @@ static int mlx90632_read_raw(struct iio_dev *indio_dev,
 			*val2 = data->emissivity * 1000;
 		}
 		return IIO_VAL_INT_PLUS_MICRO;
-
+	case IIO_CHAN_INFO_CALIBAMBIENT:
+		*val = data->object_ambient_temperature;
+		return IIO_VAL_INT;
 	default:
 		return -EINVAL;
 	}
@@ -781,6 +783,9 @@ static int mlx90632_write_raw(struct iio_dev *indio_dev,
 			return -EINVAL;
 		data->emissivity = val * 1000 + val2 / 1000;
 		return 0;
+	case IIO_CHAN_INFO_CALIBAMBIENT:
+		data->object_ambient_temperature = val;
+		return 0;
 	default:
 		return -EINVAL;
 	}
@@ -798,7 +803,7 @@ static const struct iio_chan_spec mlx90632_channels[] = {
 		.modified = 1,
 		.channel2 = IIO_MOD_TEMP_OBJECT,
 		.info_mask_separate = BIT(IIO_CHAN_INFO_PROCESSED) |
-			BIT(IIO_CHAN_INFO_CALIBEMISSIVITY),
+			BIT(IIO_CHAN_INFO_CALIBEMISSIVITY) | BIT(IIO_CHAN_INFO_CALIBAMBIENT),
 	},
 };
 
diff --git a/include/linux/iio/types.h b/include/linux/iio/types.h
index e6fd3645963c..1e3ed6f55bca 100644
--- a/include/linux/iio/types.h
+++ b/include/linux/iio/types.h
@@ -59,6 +59,7 @@ enum iio_chan_info_enum {
 	IIO_CHAN_INFO_CALIBEMISSIVITY,
 	IIO_CHAN_INFO_OVERSAMPLING_RATIO,
 	IIO_CHAN_INFO_THERMOCOUPLE_TYPE,
+	IIO_CHAN_INFO_CALIBAMBIENT,
 };
 
 #endif /* _IIO_TYPES_H_ */
-- 
cgit v1.2.3


From c5e5ec033c4ab25c53f1fd217849e75deb0bf7bf Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 19 May 2020 10:41:00 +0100
Subject: genirq: Add fasteoi IPI flow

For irqchips using the fasteoi flow, IPIs are a bit special.
They need to be EOI'd early (before calling the handler), as
funny things may happen in the handler (they do not necessarily
behave like a normal interrupt).

Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 include/linux/irq.h |  1 +
 kernel/irq/chip.c   | 27 +++++++++++++++++++++++++++
 2 files changed, 28 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 1b7f4dfee35b..57205bbf46bf 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -634,6 +634,7 @@ static inline int irq_set_parent(int irq, int parent_irq)
  */
 extern void handle_level_irq(struct irq_desc *desc);
 extern void handle_fasteoi_irq(struct irq_desc *desc);
+extern void handle_percpu_devid_fasteoi_ipi(struct irq_desc *desc);
 extern void handle_edge_irq(struct irq_desc *desc);
 extern void handle_edge_eoi_irq(struct irq_desc *desc);
 extern void handle_simple_irq(struct irq_desc *desc);
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 857f5f4c8098..bed517d5aa4d 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -944,6 +944,33 @@ void handle_percpu_devid_irq(struct irq_desc *desc)
 		chip->irq_eoi(&desc->irq_data);
 }
 
+/**
+ * handle_percpu_devid_fasteoi_ipi - Per CPU local IPI handler with per cpu
+ *				     dev ids
+ * @desc:	the interrupt description structure for this irq
+ *
+ * The biggest difference with the IRQ version is that the interrupt is
+ * EOIed early, as the IPI could result in a context switch, and we need to
+ * make sure the IPI can fire again. We also assume that the arch code has
+ * registered an action. If not, we are positively doomed.
+ */
+void handle_percpu_devid_fasteoi_ipi(struct irq_desc *desc)
+{
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	struct irqaction *action = desc->action;
+	unsigned int irq = irq_desc_get_irq(desc);
+	irqreturn_t res;
+
+	__kstat_incr_irqs_this_cpu(desc);
+
+	if (chip->irq_eoi)
+		chip->irq_eoi(&desc->irq_data);
+
+	trace_irq_handler_entry(irq, action);
+	res = action->handler(irq, raw_cpu_ptr(action->percpu_dev_id));
+	trace_irq_handler_exit(irq, action, res);
+}
+
 /**
  * handle_percpu_devid_fasteoi_nmi - Per CPU local NMI handler with per cpu
  *				     dev ids
-- 
cgit v1.2.3


From 83cfac95c01817819c2a51f0931d798d851f8a08 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 19 May 2020 14:58:13 +0100
Subject: genirq: Allow interrupts to be excluded from /proc/interrupts

A number of architectures implement IPI statistics directly,
duplicating the core kstat_irqs accounting. As we move IPIs to
being actual IRQs, we would end-up with a confusing display
in /proc/interrupts (where the IPIs would appear twice).

In order to solve this, allow interrupts to be flagged as
"hidden", which excludes them from /proc/interrupts.

Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 include/linux/irq.h   | 4 +++-
 kernel/irq/debugfs.c  | 1 +
 kernel/irq/proc.c     | 2 +-
 kernel/irq/settings.h | 7 +++++++
 4 files changed, 12 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 57205bbf46bf..63b9d962ee67 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -71,6 +71,7 @@ enum irqchip_irq_state;
  *				  it from the spurious interrupt detection
  *				  mechanism and from core side polling.
  * IRQ_DISABLE_UNLAZY		- Disable lazy irq disable
+ * IRQ_HIDDEN			- Don't show up in /proc/interrupts
  */
 enum {
 	IRQ_TYPE_NONE		= 0x00000000,
@@ -97,13 +98,14 @@ enum {
 	IRQ_PER_CPU_DEVID	= (1 << 17),
 	IRQ_IS_POLLED		= (1 << 18),
 	IRQ_DISABLE_UNLAZY	= (1 << 19),
+	IRQ_HIDDEN		= (1 << 20),
 };
 
 #define IRQF_MODIFY_MASK	\
 	(IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \
 	 IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL | IRQ_NO_BALANCING | \
 	 IRQ_PER_CPU | IRQ_NESTED_THREAD | IRQ_NOTHREAD | IRQ_PER_CPU_DEVID | \
-	 IRQ_IS_POLLED | IRQ_DISABLE_UNLAZY)
+	 IRQ_IS_POLLED | IRQ_DISABLE_UNLAZY | IRQ_HIDDEN)
 
 #define IRQ_NO_BALANCING_MASK	(IRQ_PER_CPU | IRQ_NO_BALANCING)
 
diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c
index b95ff5d5f4bd..acabc0c0e46b 100644
--- a/kernel/irq/debugfs.c
+++ b/kernel/irq/debugfs.c
@@ -136,6 +136,7 @@ static const struct irq_bit_descr irqdesc_states[] = {
 	BIT_MASK_DESCR(_IRQ_PER_CPU_DEVID),
 	BIT_MASK_DESCR(_IRQ_IS_POLLED),
 	BIT_MASK_DESCR(_IRQ_DISABLE_UNLAZY),
+	BIT_MASK_DESCR(_IRQ_HIDDEN),
 };
 
 static const struct irq_bit_descr irqdesc_istates[] = {
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 32c071d7bc03..72513ed2a5fc 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -485,7 +485,7 @@ int show_interrupts(struct seq_file *p, void *v)
 
 	rcu_read_lock();
 	desc = irq_to_desc(i);
-	if (!desc)
+	if (!desc || irq_settings_is_hidden(desc))
 		goto outsparse;
 
 	if (desc->kstat_irqs)
diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h
index e43795cd2ccf..403378b9947b 100644
--- a/kernel/irq/settings.h
+++ b/kernel/irq/settings.h
@@ -17,6 +17,7 @@ enum {
 	_IRQ_PER_CPU_DEVID	= IRQ_PER_CPU_DEVID,
 	_IRQ_IS_POLLED		= IRQ_IS_POLLED,
 	_IRQ_DISABLE_UNLAZY	= IRQ_DISABLE_UNLAZY,
+	_IRQ_HIDDEN		= IRQ_HIDDEN,
 	_IRQF_MODIFY_MASK	= IRQF_MODIFY_MASK,
 };
 
@@ -31,6 +32,7 @@ enum {
 #define IRQ_PER_CPU_DEVID	GOT_YOU_MORON
 #define IRQ_IS_POLLED		GOT_YOU_MORON
 #define IRQ_DISABLE_UNLAZY	GOT_YOU_MORON
+#define IRQ_HIDDEN		GOT_YOU_MORON
 #undef IRQF_MODIFY_MASK
 #define IRQF_MODIFY_MASK	GOT_YOU_MORON
 
@@ -167,3 +169,8 @@ static inline void irq_settings_clr_disable_unlazy(struct irq_desc *desc)
 {
 	desc->status_use_accessors &= ~_IRQ_DISABLE_UNLAZY;
 }
+
+static inline bool irq_settings_is_hidden(struct irq_desc *desc)
+{
+	return desc->status_use_accessors & _IRQ_HIDDEN;
+}
-- 
cgit v1.2.3


From 66d90f6ecee755e9c19a119c9255e80091165498 Mon Sep 17 00:00:00 2001
From: Sudeep Holla <sudeep.holla@arm.com>
Date: Mon, 7 Sep 2020 12:09:23 +0100
Subject: firmware: arm_scmi: Enable building as a single module

Now, with all the plumbing in place to enable building scmi as a module
instead of built-in modules, let us enable the same.

Link: https://lore.kernel.org/r/20200907195046.56615-5-sudeep.holla@arm.com
Tested-by: Cristian Marussi <cristian.marussi@arm.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/Kconfig           | 2 +-
 drivers/firmware/Makefile          | 2 +-
 drivers/firmware/arm_scmi/Makefile | 4 +++-
 include/linux/scmi_protocol.h      | 2 +-
 4 files changed, 6 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig
index fbd785dd0513..afdbebba628a 100644
--- a/drivers/firmware/Kconfig
+++ b/drivers/firmware/Kconfig
@@ -7,7 +7,7 @@
 menu "Firmware Drivers"
 
 config ARM_SCMI_PROTOCOL
-	bool "ARM System Control and Management Interface (SCMI) Message Protocol"
+	tristate "ARM System Control and Management Interface (SCMI) Message Protocol"
 	depends on ARM || ARM64 || COMPILE_TEST
 	depends on MAILBOX
 	help
diff --git a/drivers/firmware/Makefile b/drivers/firmware/Makefile
index 99510be9f5ed..5e013b6a3692 100644
--- a/drivers/firmware/Makefile
+++ b/drivers/firmware/Makefile
@@ -22,7 +22,7 @@ obj-$(CONFIG_TI_SCI_PROTOCOL)	+= ti_sci.o
 obj-$(CONFIG_TRUSTED_FOUNDATIONS) += trusted_foundations.o
 obj-$(CONFIG_TURRIS_MOX_RWTM)	+= turris-mox-rwtm.o
 
-obj-$(CONFIG_ARM_SCMI_PROTOCOL)	+= arm_scmi/
+obj-y				+= arm_scmi/
 obj-y				+= broadcom/
 obj-y				+= meson/
 obj-$(CONFIG_GOOGLE_FIRMWARE)	+= google/
diff --git a/drivers/firmware/arm_scmi/Makefile b/drivers/firmware/arm_scmi/Makefile
index 643f2320f976..bc0d54f8e861 100644
--- a/drivers/firmware/arm_scmi/Makefile
+++ b/drivers/firmware/arm_scmi/Makefile
@@ -1,9 +1,11 @@
 # SPDX-License-Identifier: GPL-2.0-only
-obj-y	= scmi-bus.o scmi-driver.o scmi-protocols.o scmi-transport.o
 scmi-bus-y = bus.o
 scmi-driver-y = driver.o notify.o
 scmi-transport-y = shmem.o
 scmi-transport-$(CONFIG_MAILBOX) += mailbox.o
 scmi-transport-$(CONFIG_HAVE_ARM_SMCCC_DISCOVERY) += smc.o
 scmi-protocols-y = base.o clock.o perf.o power.o reset.o sensors.o system.o
+scmi-module-objs := $(scmi-bus-y) $(scmi-driver-y) $(scmi-protocols-y) \
+		    $(scmi-transport-y)
+obj-$(CONFIG_ARM_SCMI_PROTOCOL) += scmi-module.o
 obj-$(CONFIG_ARM_SCMI_POWER_DOMAIN) += scmi_pm_domain.o
diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h
index 4b10093ad671..9cd312a1ff92 100644
--- a/include/linux/scmi_protocol.h
+++ b/include/linux/scmi_protocol.h
@@ -345,7 +345,7 @@ struct scmi_driver {
 
 #define to_scmi_driver(d) container_of(d, struct scmi_driver, driver)
 
-#ifdef CONFIG_ARM_SCMI_PROTOCOL
+#if IS_REACHABLE(CONFIG_ARM_SCMI_PROTOCOL)
 int scmi_driver_register(struct scmi_driver *driver,
 			 struct module *owner, const char *mod_name);
 void scmi_driver_unregister(struct scmi_driver *driver);
-- 
cgit v1.2.3


From 6b6ff4acb310a0351005474673f1e09a90020efd Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Wed, 9 Sep 2020 10:54:24 +0200
Subject: device: property: add helpers to count items in string arrays

Instead of doing the following:

    count = device_property_read_string_array(dev, propname, NULL, 0);

Let's provide inline helpers with hardcoded arguments for counting
strings in property arrays.

Suggested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 include/linux/property.h | 13 +++++++++++++
 1 file changed, 13 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/property.h b/include/linux/property.h
index 9f805c442819..75c178055bc9 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -170,6 +170,12 @@ static inline int device_property_count_u64(struct device *dev, const char *prop
 	return device_property_read_u64_array(dev, propname, NULL, 0);
 }
 
+static inline int device_property_string_array_count(struct device *dev,
+						     const char *propname)
+{
+	return device_property_read_string_array(dev, propname, NULL, 0);
+}
+
 static inline bool fwnode_property_read_bool(const struct fwnode_handle *fwnode,
 					     const char *propname)
 {
@@ -224,6 +230,13 @@ static inline int fwnode_property_count_u64(const struct fwnode_handle *fwnode,
 	return fwnode_property_read_u64_array(fwnode, propname, NULL, 0);
 }
 
+static inline int
+fwnode_property_string_array_count(const struct fwnode_handle *fwnode,
+				   const char *propname)
+{
+	return fwnode_property_read_string_array(fwnode, propname, NULL, 0);
+}
+
 struct software_node;
 
 /**
-- 
cgit v1.2.3


From 7cba1a4d5e1628e099728d849918de50dab2e24e Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Wed, 9 Sep 2020 10:54:25 +0200
Subject: gpiolib: generalize devprop_gpiochip_set_names() for device
 properties

devprop_gpiochip_set_names() is overly complicated with taking the
fwnode argument (which requires using dev_fwnode() & of_fwnode_handle()
in ACPI and OF GPIO code respectively). Let's just switch to using the
generic device properties.

This allows us to pull the code setting line names directly into
gpiochip_add_data_with_key() instead of handling it separately for
ACPI and OF.

Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/gpio/gpiolib-acpi.c    |  3 ---
 drivers/gpio/gpiolib-devprop.c | 20 ++++++++++----------
 drivers/gpio/gpiolib-of.c      |  5 -----
 drivers/gpio/gpiolib.c         |  8 ++++----
 include/linux/gpio/driver.h    |  3 +--
 5 files changed, 15 insertions(+), 24 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index 9276051663da..e8dc58f771d8 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -1221,9 +1221,6 @@ void acpi_gpiochip_add(struct gpio_chip *chip)
 		return;
 	}
 
-	if (!chip->names)
-		devprop_gpiochip_set_names(chip, dev_fwnode(chip->parent));
-
 	acpi_gpiochip_request_regions(acpi_gpio);
 	acpi_gpiochip_scan_gpios(acpi_gpio);
 	acpi_walk_dep_device_list(handle);
diff --git a/drivers/gpio/gpiolib-devprop.c b/drivers/gpio/gpiolib-devprop.c
index 26741032fa9e..31599d89a85d 100644
--- a/drivers/gpio/gpiolib-devprop.c
+++ b/drivers/gpio/gpiolib-devprop.c
@@ -17,25 +17,23 @@
 /**
  * devprop_gpiochip_set_names - Set GPIO line names using device properties
  * @chip: GPIO chip whose lines should be named, if possible
- * @fwnode: Property Node containing the gpio-line-names property
  *
  * Looks for device property "gpio-line-names" and if it exists assigns
  * GPIO line names for the chip. The memory allocated for the assigned
- * names belong to the underlying firmware node and should not be released
+ * names belong to the underlying software node and should not be released
  * by the caller.
  */
-void devprop_gpiochip_set_names(struct gpio_chip *chip,
-				const struct fwnode_handle *fwnode)
+int devprop_gpiochip_set_names(struct gpio_chip *chip)
 {
 	struct gpio_device *gdev = chip->gpiodev;
+	struct device *dev = chip->parent;
 	const char **names;
 	int ret, i;
 	int count;
 
-	count = fwnode_property_read_string_array(fwnode, "gpio-line-names",
-						  NULL, 0);
+	count = device_property_string_array_count(dev, "gpio-line-names");
 	if (count < 0)
-		return;
+		return 0;
 
 	if (count > gdev->ngpio) {
 		dev_warn(&gdev->dev, "gpio-line-names is length %d but should be at most length %d",
@@ -45,19 +43,21 @@ void devprop_gpiochip_set_names(struct gpio_chip *chip,
 
 	names = kcalloc(count, sizeof(*names), GFP_KERNEL);
 	if (!names)
-		return;
+		return -ENOMEM;
 
-	ret = fwnode_property_read_string_array(fwnode, "gpio-line-names",
+	ret = device_property_read_string_array(dev, "gpio-line-names",
 						names, count);
 	if (ret < 0) {
 		dev_warn(&gdev->dev, "failed to read GPIO line names\n");
 		kfree(names);
-		return;
+		return ret;
 	}
 
 	for (i = 0; i < count; i++)
 		gdev->descs[i].name = names[i];
 
 	kfree(names);
+
+	return 0;
 }
 EXPORT_SYMBOL_GPL(devprop_gpiochip_set_names);
diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index bd31dd3b6a75..2f895a2b8411 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -1026,11 +1026,6 @@ int of_gpiochip_add(struct gpio_chip *chip)
 	if (ret)
 		return ret;
 
-	/* If the chip defines names itself, these take precedence */
-	if (!chip->names)
-		devprop_gpiochip_set_names(chip,
-					   of_fwnode_handle(chip->of_node));
-
 	of_node_get(chip->of_node);
 
 	ret = of_gpiochip_scan_gpios(chip);
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 03543b8f7ab4..d50e111b0d95 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -340,9 +340,6 @@ static int gpiochip_set_desc_names(struct gpio_chip *gc)
 	struct gpio_device *gdev = gc->gpiodev;
 	int i;
 
-	if (!gc->names)
-		return 0;
-
 	/* First check all names if they are unique */
 	for (i = 0; i != gc->ngpio; ++i) {
 		struct gpio_desc *gpio;
@@ -621,7 +618,10 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data,
 	INIT_LIST_HEAD(&gdev->pin_ranges);
 #endif
 
-	ret = gpiochip_set_desc_names(gc);
+	if (gc->names)
+		ret = gpiochip_set_desc_names(gc);
+	else
+		ret = devprop_gpiochip_set_names(gc);
 	if (ret)
 		goto err_remove_from_list;
 
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index d1cef5c2715c..56485a040b82 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -756,8 +756,7 @@ struct gpio_desc *gpiochip_request_own_desc(struct gpio_chip *gc,
 					    enum gpiod_flags dflags);
 void gpiochip_free_own_desc(struct gpio_desc *desc);
 
-void devprop_gpiochip_set_names(struct gpio_chip *gc,
-				const struct fwnode_handle *fwnode);
+int devprop_gpiochip_set_names(struct gpio_chip *gc);
 
 #ifdef CONFIG_GPIOLIB
 
-- 
cgit v1.2.3


From 32fc5aa2df12c7a95dbd1c2c9ee3eb8d7f920d9e Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Wed, 9 Sep 2020 10:54:26 +0200
Subject: gpiolib: unexport devprop_gpiochip_set_names()

Now that devprop_gpiochip_set_names() is only used in a single place
inside drivers/gpio/gpiolib.c, there's no need anymore for it to be
exported or to even live in its own source file. Pull this function into
the core source file for gpiolib.

Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/gpio/Makefile          |  1 -
 drivers/gpio/gpiolib-devprop.c | 63 ------------------------------------------
 drivers/gpio/gpiolib.c         | 47 +++++++++++++++++++++++++++++++
 include/linux/gpio/driver.h    |  2 --
 4 files changed, 47 insertions(+), 66 deletions(-)
 delete mode 100644 drivers/gpio/gpiolib-devprop.c

(limited to 'include/linux')

diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile
index 4f9abff4f2dc..639275eb4e4d 100644
--- a/drivers/gpio/Makefile
+++ b/drivers/gpio/Makefile
@@ -6,7 +6,6 @@ ccflags-$(CONFIG_DEBUG_GPIO)	+= -DDEBUG
 obj-$(CONFIG_GPIOLIB)		+= gpiolib.o
 obj-$(CONFIG_GPIOLIB)		+= gpiolib-devres.o
 obj-$(CONFIG_GPIOLIB)		+= gpiolib-legacy.o
-obj-$(CONFIG_GPIOLIB)		+= gpiolib-devprop.o
 obj-$(CONFIG_GPIOLIB)		+= gpiolib-cdev.o
 obj-$(CONFIG_OF_GPIO)		+= gpiolib-of.o
 obj-$(CONFIG_GPIO_SYSFS)	+= gpiolib-sysfs.o
diff --git a/drivers/gpio/gpiolib-devprop.c b/drivers/gpio/gpiolib-devprop.c
deleted file mode 100644
index 31599d89a85d..000000000000
--- a/drivers/gpio/gpiolib-devprop.c
+++ /dev/null
@@ -1,63 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Device property helpers for GPIO chips.
- *
- * Copyright (C) 2016, Intel Corporation
- * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
- */
-
-#include <linux/property.h>
-#include <linux/slab.h>
-#include <linux/gpio/consumer.h>
-#include <linux/gpio/driver.h>
-#include <linux/export.h>
-
-#include "gpiolib.h"
-
-/**
- * devprop_gpiochip_set_names - Set GPIO line names using device properties
- * @chip: GPIO chip whose lines should be named, if possible
- *
- * Looks for device property "gpio-line-names" and if it exists assigns
- * GPIO line names for the chip. The memory allocated for the assigned
- * names belong to the underlying software node and should not be released
- * by the caller.
- */
-int devprop_gpiochip_set_names(struct gpio_chip *chip)
-{
-	struct gpio_device *gdev = chip->gpiodev;
-	struct device *dev = chip->parent;
-	const char **names;
-	int ret, i;
-	int count;
-
-	count = device_property_string_array_count(dev, "gpio-line-names");
-	if (count < 0)
-		return 0;
-
-	if (count > gdev->ngpio) {
-		dev_warn(&gdev->dev, "gpio-line-names is length %d but should be at most length %d",
-			 count, gdev->ngpio);
-		count = gdev->ngpio;
-	}
-
-	names = kcalloc(count, sizeof(*names), GFP_KERNEL);
-	if (!names)
-		return -ENOMEM;
-
-	ret = device_property_read_string_array(dev, "gpio-line-names",
-						names, count);
-	if (ret < 0) {
-		dev_warn(&gdev->dev, "failed to read GPIO line names\n");
-		kfree(names);
-		return ret;
-	}
-
-	for (i = 0; i < count; i++)
-		gdev->descs[i].name = names[i];
-
-	kfree(names);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(devprop_gpiochip_set_names);
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index d50e111b0d95..b7b608ef9e6b 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -358,6 +358,53 @@ static int gpiochip_set_desc_names(struct gpio_chip *gc)
 	return 0;
 }
 
+/*
+ * devprop_gpiochip_set_names - Set GPIO line names using device properties
+ * @chip: GPIO chip whose lines should be named, if possible
+ *
+ * Looks for device property "gpio-line-names" and if it exists assigns
+ * GPIO line names for the chip. The memory allocated for the assigned
+ * names belong to the underlying software node and should not be released
+ * by the caller.
+ */
+static int devprop_gpiochip_set_names(struct gpio_chip *chip)
+{
+	struct gpio_device *gdev = chip->gpiodev;
+	struct device *dev = chip->parent;
+	const char **names;
+	int ret, i;
+	int count;
+
+	count = device_property_string_array_count(dev, "gpio-line-names");
+	if (count < 0)
+		return 0;
+
+	if (count > gdev->ngpio) {
+		dev_warn(&gdev->dev, "gpio-line-names is length %d but should be at most length %d",
+			 count, gdev->ngpio);
+		count = gdev->ngpio;
+	}
+
+	names = kcalloc(count, sizeof(*names), GFP_KERNEL);
+	if (!names)
+		return -ENOMEM;
+
+	ret = device_property_read_string_array(dev, "gpio-line-names",
+						names, count);
+	if (ret < 0) {
+		dev_warn(&gdev->dev, "failed to read GPIO line names\n");
+		kfree(names);
+		return ret;
+	}
+
+	for (i = 0; i < count; i++)
+		gdev->descs[i].name = names[i];
+
+	kfree(names);
+
+	return 0;
+}
+
 static unsigned long *gpiochip_allocate_mask(struct gpio_chip *gc)
 {
 	unsigned long *p;
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index 56485a040b82..4a7e295c3640 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -756,8 +756,6 @@ struct gpio_desc *gpiochip_request_own_desc(struct gpio_chip *gc,
 					    enum gpiod_flags dflags);
 void gpiochip_free_own_desc(struct gpio_desc *desc);
 
-int devprop_gpiochip_set_names(struct gpio_chip *gc);
-
 #ifdef CONFIG_GPIOLIB
 
 /* lock/unlock as IRQ */
-- 
cgit v1.2.3


From 6d885330fa3daede6bf24b7422da9d6d9a577eb8 Mon Sep 17 00:00:00 2001
From: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Date: Mon, 17 Aug 2020 10:27:22 +0200
Subject: media: firmware: qcom_scm: Add memory protect virtual address ranges

This adds a new SCM memprotect command to set virtual address ranges.

Signed-off-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Reviewed-by: Elliot Berman <eberman@codeaurora.org>
Acked-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 drivers/firmware/qcom_scm.c | 24 ++++++++++++++++++++++++
 drivers/firmware/qcom_scm.h |  1 +
 include/linux/qcom_scm.h    |  7 +++++++
 3 files changed, 32 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/firmware/qcom_scm.c b/drivers/firmware/qcom_scm.c
index e8bbf2d38ae7..7be48c1bec96 100644
--- a/drivers/firmware/qcom_scm.c
+++ b/drivers/firmware/qcom_scm.c
@@ -756,6 +756,30 @@ int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare)
 }
 EXPORT_SYMBOL(qcom_scm_iommu_secure_ptbl_init);
 
+int qcom_scm_mem_protect_video_var(u32 cp_start, u32 cp_size,
+				   u32 cp_nonpixel_start,
+				   u32 cp_nonpixel_size)
+{
+	int ret;
+	struct qcom_scm_desc desc = {
+		.svc = QCOM_SCM_SVC_MP,
+		.cmd = QCOM_SCM_MP_VIDEO_VAR,
+		.arginfo = QCOM_SCM_ARGS(4, QCOM_SCM_VAL, QCOM_SCM_VAL,
+					 QCOM_SCM_VAL, QCOM_SCM_VAL),
+		.args[0] = cp_start,
+		.args[1] = cp_size,
+		.args[2] = cp_nonpixel_start,
+		.args[3] = cp_nonpixel_size,
+		.owner = ARM_SMCCC_OWNER_SIP,
+	};
+	struct qcom_scm_res res;
+
+	ret = qcom_scm_call(__scm->dev, &desc, &res);
+
+	return ret ? : res.result[0];
+}
+EXPORT_SYMBOL(qcom_scm_mem_protect_video_var);
+
 static int __qcom_scm_assign_mem(struct device *dev, phys_addr_t mem_region,
 				 size_t mem_sz, phys_addr_t src, size_t src_sz,
 				 phys_addr_t dest, size_t dest_sz)
diff --git a/drivers/firmware/qcom_scm.h b/drivers/firmware/qcom_scm.h
index 38ea614d29fe..95cd1ac30ab0 100644
--- a/drivers/firmware/qcom_scm.h
+++ b/drivers/firmware/qcom_scm.h
@@ -97,6 +97,7 @@ extern int scm_legacy_call(struct device *dev, const struct qcom_scm_desc *desc,
 #define QCOM_SCM_MP_RESTORE_SEC_CFG		0x02
 #define QCOM_SCM_MP_IOMMU_SECURE_PTBL_SIZE	0x03
 #define QCOM_SCM_MP_IOMMU_SECURE_PTBL_INIT	0x04
+#define QCOM_SCM_MP_VIDEO_VAR			0x08
 #define QCOM_SCM_MP_ASSIGN			0x16
 
 #define QCOM_SCM_SVC_OCMEM		0x0f
diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h
index 2e1193a3fb5f..0165824c5128 100644
--- a/include/linux/qcom_scm.h
+++ b/include/linux/qcom_scm.h
@@ -84,6 +84,9 @@ extern bool qcom_scm_restore_sec_cfg_available(void);
 extern int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare);
 extern int qcom_scm_iommu_secure_ptbl_size(u32 spare, size_t *size);
 extern int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare);
+extern int qcom_scm_mem_protect_video_var(u32 cp_start, u32 cp_size,
+					  u32 cp_nonpixel_start,
+					  u32 cp_nonpixel_size);
 extern int qcom_scm_assign_mem(phys_addr_t mem_addr, size_t mem_sz,
 			       unsigned int *src,
 			       const struct qcom_scm_vmperm *newvm,
@@ -141,6 +144,10 @@ static inline int qcom_scm_iommu_secure_ptbl_size(u32 spare, size_t *size)
 		{ return -ENODEV; }
 static inline int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare)
 		{ return -ENODEV; }
+extern inline int qcom_scm_mem_protect_video_var(u32 cp_start, u32 cp_size,
+						 u32 cp_nonpixel_start,
+						 u32 cp_nonpixel_size)
+		{ return -ENODEV; }
 static inline int qcom_scm_assign_mem(phys_addr_t mem_addr, size_t mem_sz,
 		unsigned int *src, const struct qcom_scm_vmperm *newvm,
 		unsigned int dest_cnt) { return -ENODEV; }
-- 
cgit v1.2.3


From 1fa5cef283420b3dad93cd6ab04d7125bc1562de Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Tue, 18 Aug 2020 15:07:57 +0800
Subject: i40e: optimise prefetch page refcount

refcount of rx_buffer page will be added here originally, so prefetchw
is needed, but after commit 1793668c3b8c ("i40e/i40evf: Update code to
better handle incrementing page count"), and refcount is not added
every time, so change prefetchw as prefetch.

Now it mainly services page_address(), but which accesses struct page
only when WANT_PAGE_VIRTUAL or HASHED_PAGE_VIRTUAL is defined otherwise
it returns address based on offset, so we prefetch it conditionally.

Jakub suggested to define prefetch_page_address in a common header.

Reported-by: kernel test robot <lkp@intel.com>
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_txrx.c | 2 +-
 include/linux/prefetch.h                    | 8 ++++++++
 2 files changed, 9 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 91ab824926b9..8500e1c1a16b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -1953,7 +1953,7 @@ static struct i40e_rx_buffer *i40e_get_rx_buffer(struct i40e_ring *rx_ring,
 	struct i40e_rx_buffer *rx_buffer;
 
 	rx_buffer = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
-	prefetchw(rx_buffer->page);
+	prefetch_page_address(rx_buffer->page);
 
 	/* we are reusing so sync this buffer for CPU use */
 	dma_sync_single_range_for_cpu(rx_ring->dev,
diff --git a/include/linux/prefetch.h b/include/linux/prefetch.h
index 13eafebf3549..b83a3f944f28 100644
--- a/include/linux/prefetch.h
+++ b/include/linux/prefetch.h
@@ -15,6 +15,7 @@
 #include <asm/processor.h>
 #include <asm/cache.h>
 
+struct page;
 /*
 	prefetch(x) attempts to pre-emptively get the memory pointed to
 	by address "x" into the CPU L1 cache. 
@@ -62,4 +63,11 @@ static inline void prefetch_range(void *addr, size_t len)
 #endif
 }
 
+static inline void prefetch_page_address(struct page *page)
+{
+#if defined(WANT_PAGE_VIRTUAL) || defined(HASHED_PAGE_VIRTUAL)
+	prefetch(page);
+#endif
+}
+
 #endif
-- 
cgit v1.2.3


From 36d818f610f218e9e8711bf498b62a27778dae3f Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 11 Sep 2020 20:02:02 +0300
Subject: kernel.h: Move oops_in_progress to printk.h

The oops_in_progress is defined in printk.c, so it's logical
to move oops_in_progress to printk.h.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Signed-off-by: Petr Mladek <pmladek@suse.com>
Link: https://lore.kernel.org/r/20200911170202.8565-1-andriy.shevchenko@linux.intel.com
---
 include/linux/debug_locks.h | 2 +-
 include/linux/kernel.h      | 1 -
 include/linux/printk.h      | 2 ++
 3 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h
index e7e45f0cc7da..2915f56ad421 100644
--- a/include/linux/debug_locks.h
+++ b/include/linux/debug_locks.h
@@ -2,9 +2,9 @@
 #ifndef __LINUX_DEBUG_LOCKING_H
 #define __LINUX_DEBUG_LOCKING_H
 
-#include <linux/kernel.h>
 #include <linux/atomic.h>
 #include <linux/bug.h>
+#include <linux/printk.h>
 
 struct task_struct;
 
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 82d91547d122..6cef4ca5589c 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -527,7 +527,6 @@ extern unsigned int sysctl_oops_all_cpu_backtrace;
 #endif /* CONFIG_SMP */
 
 extern void bust_spinlocks(int yes);
-extern int oops_in_progress;		/* If set, an oops, panic(), BUG() or die() is in progress */
 extern int panic_timeout;
 extern unsigned long panic_print;
 extern int panic_on_oops;
diff --git a/include/linux/printk.h b/include/linux/printk.h
index 34c1a7be3e01..f749a2c2e7a5 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -12,6 +12,8 @@
 extern const char linux_banner[];
 extern const char linux_proc_banner[];
 
+extern int oops_in_progress;	/* If set, an oops, panic(), BUG() or die() is in progress */
+
 #define PRINTK_MAX_SINGLE_HEADER_LEN 2
 
 static inline int printk_get_level(const char *buffer)
-- 
cgit v1.2.3


From cf6501689012ef346cc835a38cbebb1e398d0834 Mon Sep 17 00:00:00 2001
From: Andrew Scull <ascull@google.com>
Date: Tue, 15 Sep 2020 11:46:39 +0100
Subject: smccc: Define vendor hyp owned service call region

Vendor specific hypervisor services have their own region of function
identifiers reserved by SMCCC. Extend the list of owners to include this
case.

Signed-off-by: Andrew Scull <ascull@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Cc: Sudeep Holla <sudeep.holla@arm.com>
Link: https://lore.kernel.org/r/20200915104643.2543892-16-ascull@google.com
---
 include/linux/arm-smccc.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h
index 15c706fb0a37..ee286f5de239 100644
--- a/include/linux/arm-smccc.h
+++ b/include/linux/arm-smccc.h
@@ -49,6 +49,7 @@
 #define ARM_SMCCC_OWNER_OEM		3
 #define ARM_SMCCC_OWNER_STANDARD	4
 #define ARM_SMCCC_OWNER_STANDARD_HYP	5
+#define ARM_SMCCC_OWNER_VENDOR_HYP	6
 #define ARM_SMCCC_OWNER_TRUSTED_APP	48
 #define ARM_SMCCC_OWNER_TRUSTED_APP_END	49
 #define ARM_SMCCC_OWNER_TRUSTED_OS	50
-- 
cgit v1.2.3


From 0794a974d74dc777a212a3c58dd236f507360348 Mon Sep 17 00:00:00 2001
From: Andrew Scull <ascull@google.com>
Date: Tue, 15 Sep 2020 11:46:40 +0100
Subject: smccc: Use separate variables for args and results

Using the same register-bound variable for both arguments and results
means these values share a type. That type must allow the arguments to
be assigned to it and must also be assignable to the unsigned long
fields of struct arm_smccc_res.

This restriction on types causes compiler warnings when the argument
cannot be implicitly assigned to an unsigned long, for example the
pointers that are used in the KVM hyp interface.

By separating the arguments and results into their own variables, the
type constraint is lifted allowing the arguments to avoid the need for
any type conversion.

Signed-off-by: Andrew Scull <ascull@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Cc: Sudeep Holla <sudeep.holla@arm.com>
Link: https://lore.kernel.org/r/20200915104643.2543892-17-ascull@google.com
---
 include/linux/arm-smccc.h | 73 +++++++++++++++++++----------------------------
 1 file changed, 29 insertions(+), 44 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h
index ee286f5de239..885c9ffc835c 100644
--- a/include/linux/arm-smccc.h
+++ b/include/linux/arm-smccc.h
@@ -228,87 +228,67 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
 #define __count_args(...)						\
 	___count_args(__VA_ARGS__, 7, 6, 5, 4, 3, 2, 1, 0)
 
-#define __constraint_write_0						\
-	"+r" (r0), "=&r" (r1), "=&r" (r2), "=&r" (r3)
-#define __constraint_write_1						\
-	"+r" (r0), "+r" (r1), "=&r" (r2), "=&r" (r3)
-#define __constraint_write_2						\
-	"+r" (r0), "+r" (r1), "+r" (r2), "=&r" (r3)
-#define __constraint_write_3						\
-	"+r" (r0), "+r" (r1), "+r" (r2), "+r" (r3)
-#define __constraint_write_4	__constraint_write_3
-#define __constraint_write_5	__constraint_write_4
-#define __constraint_write_6	__constraint_write_5
-#define __constraint_write_7	__constraint_write_6
-
-#define __constraint_read_0
-#define __constraint_read_1
-#define __constraint_read_2
-#define __constraint_read_3
-#define __constraint_read_4	"r" (r4)
-#define __constraint_read_5	__constraint_read_4, "r" (r5)
-#define __constraint_read_6	__constraint_read_5, "r" (r6)
-#define __constraint_read_7	__constraint_read_6, "r" (r7)
+#define __constraint_read_0	"r" (arg0)
+#define __constraint_read_1	__constraint_read_0, "r" (arg1)
+#define __constraint_read_2	__constraint_read_1, "r" (arg2)
+#define __constraint_read_3	__constraint_read_2, "r" (arg3)
+#define __constraint_read_4	__constraint_read_3, "r" (arg4)
+#define __constraint_read_5	__constraint_read_4, "r" (arg5)
+#define __constraint_read_6	__constraint_read_5, "r" (arg6)
+#define __constraint_read_7	__constraint_read_6, "r" (arg7)
 
 #define __declare_arg_0(a0, res)					\
 	struct arm_smccc_res   *___res = res;				\
-	register unsigned long r0 asm("r0") = (u32)a0;			\
-	register unsigned long r1 asm("r1");				\
-	register unsigned long r2 asm("r2");				\
-	register unsigned long r3 asm("r3")
+	register unsigned long arg0 asm("r0") = (u32)a0
 
 #define __declare_arg_1(a0, a1, res)					\
 	typeof(a1) __a1 = a1;						\
 	struct arm_smccc_res   *___res = res;				\
-	register unsigned long r0 asm("r0") = (u32)a0;			\
-	register unsigned long r1 asm("r1") = __a1;			\
-	register unsigned long r2 asm("r2");				\
-	register unsigned long r3 asm("r3")
+	register unsigned long arg0 asm("r0") = (u32)a0;			\
+	register typeof(a1) arg1 asm("r1") = __a1
 
 #define __declare_arg_2(a0, a1, a2, res)				\
 	typeof(a1) __a1 = a1;						\
 	typeof(a2) __a2 = a2;						\
 	struct arm_smccc_res   *___res = res;				\
-	register unsigned long r0 asm("r0") = (u32)a0;			\
-	register unsigned long r1 asm("r1") = __a1;			\
-	register unsigned long r2 asm("r2") = __a2;			\
-	register unsigned long r3 asm("r3")
+	register unsigned long arg0 asm("r0") = (u32)a0;			\
+	register typeof(a1) arg1 asm("r1") = __a1;			\
+	register typeof(a2) arg2 asm("r2") = __a2
 
 #define __declare_arg_3(a0, a1, a2, a3, res)				\
 	typeof(a1) __a1 = a1;						\
 	typeof(a2) __a2 = a2;						\
 	typeof(a3) __a3 = a3;						\
 	struct arm_smccc_res   *___res = res;				\
-	register unsigned long r0 asm("r0") = (u32)a0;			\
-	register unsigned long r1 asm("r1") = __a1;			\
-	register unsigned long r2 asm("r2") = __a2;			\
-	register unsigned long r3 asm("r3") = __a3
+	register unsigned long arg0 asm("r0") = (u32)a0;			\
+	register typeof(a1) arg1 asm("r1") = __a1;			\
+	register typeof(a2) arg2 asm("r2") = __a2;			\
+	register typeof(a3) arg3 asm("r3") = __a3
 
 #define __declare_arg_4(a0, a1, a2, a3, a4, res)			\
 	typeof(a4) __a4 = a4;						\
 	__declare_arg_3(a0, a1, a2, a3, res);				\
-	register unsigned long r4 asm("r4") = __a4
+	register typeof(a4) arg4 asm("r4") = __a4
 
 #define __declare_arg_5(a0, a1, a2, a3, a4, a5, res)			\
 	typeof(a5) __a5 = a5;						\
 	__declare_arg_4(a0, a1, a2, a3, a4, res);			\
-	register unsigned long r5 asm("r5") = __a5
+	register typeof(a5) arg5 asm("r5") = __a5
 
 #define __declare_arg_6(a0, a1, a2, a3, a4, a5, a6, res)		\
 	typeof(a6) __a6 = a6;						\
 	__declare_arg_5(a0, a1, a2, a3, a4, a5, res);			\
-	register unsigned long r6 asm("r6") = __a6
+	register typeof(a6) arg6 asm("r6") = __a6
 
 #define __declare_arg_7(a0, a1, a2, a3, a4, a5, a6, a7, res)		\
 	typeof(a7) __a7 = a7;						\
 	__declare_arg_6(a0, a1, a2, a3, a4, a5, a6, res);		\
-	register unsigned long r7 asm("r7") = __a7
+	register typeof(a7) arg7 asm("r7") = __a7
 
 #define ___declare_args(count, ...) __declare_arg_ ## count(__VA_ARGS__)
 #define __declare_args(count, ...)  ___declare_args(count, __VA_ARGS__)
 
 #define ___constraints(count)						\
-	: __constraint_write_ ## count					\
 	: __constraint_read_ ## count					\
 	: "memory"
 #define __constraints(count)	___constraints(count)
@@ -320,8 +300,13 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
  */
 #define __arm_smccc_1_1(inst, ...)					\
 	do {								\
+		register unsigned long r0 asm("r0");			\
+		register unsigned long r1 asm("r1");			\
+		register unsigned long r2 asm("r2");			\
+		register unsigned long r3 asm("r3"); 			\
 		__declare_args(__count_args(__VA_ARGS__), __VA_ARGS__);	\
-		asm volatile(inst "\n"					\
+		asm volatile(inst "\n" :				\
+			     "=r" (r0), "=r" (r1), "=r" (r2), "=r" (r3)	\
 			     __constraints(__count_args(__VA_ARGS__)));	\
 		if (___res)						\
 			*___res = (typeof(*___res)){r0, r1, r2, r3};	\
@@ -367,7 +352,7 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
 #define __fail_smccc_1_1(...)						\
 	do {								\
 		__declare_args(__count_args(__VA_ARGS__), __VA_ARGS__);	\
-		asm ("" __constraints(__count_args(__VA_ARGS__)));	\
+		asm ("" : __constraints(__count_args(__VA_ARGS__)));	\
 		if (___res)						\
 			___res->a0 = SMCCC_RET_NOT_SUPPORTED;		\
 	} while (0)
-- 
cgit v1.2.3


From fb609b5112bd74b4ba93c86d7af4089ffd9432c2 Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Wed, 13 May 2020 11:06:47 +0300
Subject: net/mlx5: Always use container_of to find mdev pointer from clock
 struct

Clock struct is part of struct mlx5_core_dev. Code was inconsistent, on
some cases used container_of and on another used clock->mdev.

Align code to use container_of amd remove clock->mdev pointer.
While here, fix reverse xmas tree coding style.

Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/lib/clock.c    | 52 ++++++++++++----------
 include/linux/mlx5/driver.h                        |  1 -
 2 files changed, 29 insertions(+), 24 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index 2d55b7c22c03..a07aeb97d027 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -150,28 +150,30 @@ static void mlx5_pps_out(struct work_struct *work)
 static void mlx5_timestamp_overflow(struct work_struct *work)
 {
 	struct delayed_work *dwork = to_delayed_work(work);
-	struct mlx5_clock *clock = container_of(dwork, struct mlx5_clock,
-						overflow_work);
+	struct mlx5_core_dev *mdev;
+	struct mlx5_clock *clock;
 	unsigned long flags;
 
+	clock = container_of(dwork, struct mlx5_clock, overflow_work);
+	mdev = container_of(clock, struct mlx5_core_dev, clock);
 	write_seqlock_irqsave(&clock->lock, flags);
 	timecounter_read(&clock->tc);
-	mlx5_update_clock_info_page(clock->mdev);
+	mlx5_update_clock_info_page(mdev);
 	write_sequnlock_irqrestore(&clock->lock, flags);
 	schedule_delayed_work(&clock->overflow_work, clock->overflow_period);
 }
 
-static int mlx5_ptp_settime(struct ptp_clock_info *ptp,
-			    const struct timespec64 *ts)
+static int mlx5_ptp_settime(struct ptp_clock_info *ptp, const struct timespec64 *ts)
 {
-	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock,
-						 ptp_info);
+	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
 	u64 ns = timespec64_to_ns(ts);
+	struct mlx5_core_dev *mdev;
 	unsigned long flags;
 
+	mdev = container_of(clock, struct mlx5_core_dev, clock);
 	write_seqlock_irqsave(&clock->lock, flags);
 	timecounter_init(&clock->tc, &clock->cycles, ns);
-	mlx5_update_clock_info_page(clock->mdev);
+	mlx5_update_clock_info_page(mdev);
 	write_sequnlock_irqrestore(&clock->lock, flags);
 
 	return 0;
@@ -180,13 +182,12 @@ static int mlx5_ptp_settime(struct ptp_clock_info *ptp,
 static int mlx5_ptp_gettimex(struct ptp_clock_info *ptp, struct timespec64 *ts,
 			     struct ptp_system_timestamp *sts)
 {
-	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock,
-						ptp_info);
-	struct mlx5_core_dev *mdev = container_of(clock, struct mlx5_core_dev,
-						  clock);
+	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
+	struct mlx5_core_dev *mdev;
 	unsigned long flags;
 	u64 cycles, ns;
 
+	mdev = container_of(clock, struct mlx5_core_dev, clock);
 	write_seqlock_irqsave(&clock->lock, flags);
 	cycles = mlx5_read_internal_timer(mdev, sts);
 	ns = timecounter_cyc2time(&clock->tc, cycles);
@@ -199,13 +200,14 @@ static int mlx5_ptp_gettimex(struct ptp_clock_info *ptp, struct timespec64 *ts,
 
 static int mlx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 {
-	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock,
-						ptp_info);
+	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
+	struct mlx5_core_dev *mdev;
 	unsigned long flags;
 
+	mdev = container_of(clock, struct mlx5_core_dev, clock);
 	write_seqlock_irqsave(&clock->lock, flags);
 	timecounter_adjtime(&clock->tc, delta);
-	mlx5_update_clock_info_page(clock->mdev);
+	mlx5_update_clock_info_page(mdev);
 	write_sequnlock_irqrestore(&clock->lock, flags);
 
 	return 0;
@@ -213,12 +215,13 @@ static int mlx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 
 static int mlx5_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta)
 {
-	u64 adj;
-	u32 diff;
+	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
+	struct mlx5_core_dev *mdev;
 	unsigned long flags;
 	int neg_adj = 0;
-	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock,
-						ptp_info);
+	u32 diff;
+	u64 adj;
+
 
 	if (delta < 0) {
 		neg_adj = 1;
@@ -229,11 +232,12 @@ static int mlx5_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta)
 	adj *= delta;
 	diff = div_u64(adj, 1000000000ULL);
 
+	mdev = container_of(clock, struct mlx5_core_dev, clock);
 	write_seqlock_irqsave(&clock->lock, flags);
 	timecounter_read(&clock->tc);
 	clock->cycles.mult = neg_adj ? clock->nominal_c_mult - diff :
 				       clock->nominal_c_mult + diff;
-	mlx5_update_clock_info_page(clock->mdev);
+	mlx5_update_clock_info_page(mdev);
 	write_sequnlock_irqrestore(&clock->lock, flags);
 
 	return 0;
@@ -465,7 +469,8 @@ static int mlx5_query_mtpps_pin_mode(struct mlx5_core_dev *mdev, u8 pin,
 
 static int mlx5_get_pps_pin_mode(struct mlx5_clock *clock, u8 pin)
 {
-	struct mlx5_core_dev *mdev = clock->mdev;
+	struct mlx5_core_dev *mdev = container_of(clock, struct mlx5_core_dev, clock);
+
 	u32 out[MLX5_ST_SZ_DW(mtpps_reg)] = {};
 	u8 mode;
 	int err;
@@ -538,15 +543,17 @@ static int mlx5_pps_event(struct notifier_block *nb,
 			  unsigned long type, void *data)
 {
 	struct mlx5_clock *clock = mlx5_nb_cof(nb, struct mlx5_clock, pps_nb);
-	struct mlx5_core_dev *mdev = clock->mdev;
 	struct ptp_clock_event ptp_event;
 	u64 cycles_now, cycles_delta;
 	u64 nsec_now, nsec_delta, ns;
 	struct mlx5_eqe *eqe = data;
 	int pin = eqe->data.pps.pin;
+	struct mlx5_core_dev *mdev;
 	struct timespec64 ts;
 	unsigned long flags;
 
+	mdev = container_of(clock, struct mlx5_core_dev, clock);
+
 	switch (clock->ptp_info.pin_config[pin].func) {
 	case PTP_PF_EXTTS:
 		ptp_event.index = pin;
@@ -605,7 +612,6 @@ void mlx5_init_clock(struct mlx5_core_dev *mdev)
 						  clock->cycles.shift);
 	clock->nominal_c_mult = clock->cycles.mult;
 	clock->cycles.mask = CLOCKSOURCE_MASK(41);
-	clock->mdev = mdev;
 
 	timecounter_init(&clock->tc, &clock->cycles,
 			 ktime_to_ns(ktime_get_real()));
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index c145de0473bc..8dc3da6e6480 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -643,7 +643,6 @@ struct mlx5_pps {
 };
 
 struct mlx5_clock {
-	struct mlx5_core_dev      *mdev;
 	struct mlx5_nb             pps_nb;
 	seqlock_t                  lock;
 	struct cyclecounter        cycles;
-- 
cgit v1.2.3


From b7cf0806e8783e38f881cae3c56f0869e70b8da2 Mon Sep 17 00:00:00 2001
From: Ofer Levi <oferle@mellanox.com>
Date: Sun, 17 May 2020 10:16:49 +0300
Subject: net/mlx5e: Add CQE compression support for multi-strides packets

Add CQE compression support for completions of packets that span
multiple strides in a Striding RQ, per the HW capability.
In our memory model, we use small strides (256B as of today) for the
non-linear SKB mode. This feature allows CQE compression to work also
for multiple strides packets. In this case decompressing the mini CQE
array will use stride index provided by HW as part of the mini CQE.
Before this feature, compression was possible only for single-strided
packets, i.e. for packets of size up to 256 bytes when in non-linear
mode, and the index was maintained by SW.
This feature is supported for ConnectX-5 and above.

Feature performance test:
This was whitebox-tested, we reduced the PCI speed from 125Gb/s to
62.5Gb/s to overload pci and manipulated mlx5 driver to drop incoming
packets before building the SKB to achieve low cpu utilization.
Outcome is low cpu utilization and bottleneck on pci only.
Test setup:
Server: Intel(R) Xeon(R) Silver 4108 CPU @ 1.80GHz server, 32 cores
NIC: ConnectX-6 DX.
Sender side generates 300 byte packets at full pci bandwidth.
Receiver side configuration:
Single channel, one cpu processing with one ring allocated. Cpu utilization
is ~20% while pci bandwidth is fully utilized.
For the generated traffic and interface MTU of 4500B (to activate the
non-linear SKB mode), packet rate improvement is about 19% from ~17.6Mpps
to ~21Mpps.
Without this feature, counters show no CQE compression blocks for
this setup, while with the feature, counters show ~20.7Mpps compressed CQEs
in ~500K compression blocks.

Signed-off-by: Ofer Levi <oferle@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      |  1 +
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 12 +++++++++++-
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c   | 11 ++++++++++-
 include/linux/mlx5/device.h                       |  3 ++-
 4 files changed, 24 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 4f33658da25a..95aab8b429cf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -265,6 +265,7 @@ enum {
 	MLX5E_RQ_STATE_NO_CSUM_COMPLETE,
 	MLX5E_RQ_STATE_CSUM_FULL, /* cqe_csum_full hw bit is set */
 	MLX5E_RQ_STATE_FPGA_TLS, /* FPGA TLS enabled */
+	MLX5E_RQ_STATE_MINI_CQE_HW_STRIDX /* set when mini_cqe_resp_stride_index cap is used */
 };
 
 struct mlx5e_cq {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 26834625556d..b057a6c3a6d5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -848,6 +848,13 @@ int mlx5e_open_rq(struct mlx5e_channel *c, struct mlx5e_params *params,
 	if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_NO_CSUM_COMPLETE) || c->xdp)
 		__set_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &c->rq.state);
 
+	/* For CQE compression on striding RQ, use stride index provided by
+	 * HW if capability is supported.
+	 */
+	if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_STRIDING_RQ) &&
+	    MLX5_CAP_GEN(c->mdev, mini_cqe_resp_stride_index))
+		__set_bit(MLX5E_RQ_STATE_MINI_CQE_HW_STRIDX, &c->rq.state);
+
 	return 0;
 
 err_destroy_rq:
@@ -2182,6 +2189,7 @@ void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv,
 			     struct mlx5e_cq_param *param)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
+	bool hw_stridx = false;
 	void *cqc = param->cqc;
 	u8 log_cq_size;
 
@@ -2189,6 +2197,7 @@ void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv,
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
 		log_cq_size = mlx5e_mpwqe_get_log_rq_size(params, xsk) +
 			mlx5e_mpwqe_get_log_num_strides(mdev, params, xsk);
+		hw_stridx = MLX5_CAP_GEN(mdev, mini_cqe_resp_stride_index);
 		break;
 	default: /* MLX5_WQ_TYPE_CYCLIC */
 		log_cq_size = params->log_rq_mtu_frames;
@@ -2196,7 +2205,8 @@ void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv,
 
 	MLX5_SET(cqc, cqc, log_cq_size, log_cq_size);
 	if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS)) {
-		MLX5_SET(cqc, cqc, mini_cqe_res_format, MLX5_CQE_FORMAT_CSUM);
+		MLX5_SET(cqc, cqc, mini_cqe_res_format, hw_stridx ?
+			 MLX5_CQE_FORMAT_CSUM_STRIDX : MLX5_CQE_FORMAT_CSUM);
 		MLX5_SET(cqc, cqc, cqe_comp_en, 1);
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 7aab69e991a5..c9c82b14060a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -137,8 +137,17 @@ static inline void mlx5e_decompress_cqe(struct mlx5e_rq *rq,
 	title->check_sum    = mini_cqe->checksum;
 	title->op_own      &= 0xf0;
 	title->op_own      |= 0x01 & (cqcc >> wq->fbc.log_sz);
-	title->wqe_counter  = cpu_to_be16(cqd->wqe_counter);
 
+	/* state bit set implies linked-list striding RQ wq type and
+	 * HW stride index capability supported
+	 */
+	if (test_bit(MLX5E_RQ_STATE_MINI_CQE_HW_STRIDX, &rq->state)) {
+		title->wqe_counter = mini_cqe->stridx;
+		return;
+	}
+
+	/* HW stride index capability not supported */
+	title->wqe_counter = cpu_to_be16(cqd->wqe_counter);
 	if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
 		cqd->wqe_counter += mpwrq_get_cqe_consumed_strides(title);
 	else
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 4d3376e20f5e..81ca5989009b 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -816,7 +816,7 @@ struct mlx5_mini_cqe8 {
 		__be32 rx_hash_result;
 		struct {
 			__be16 checksum;
-			__be16 rsvd;
+			__be16 stridx;
 		};
 		struct {
 			__be16 wqe_counter;
@@ -836,6 +836,7 @@ enum {
 
 enum {
 	MLX5_CQE_FORMAT_CSUM = 0x1,
+	MLX5_CQE_FORMAT_CSUM_STRIDX = 0x3,
 };
 
 #define MLX5_MINI_CQE_ARRAY_SIZE 8
-- 
cgit v1.2.3


From 9a27a33027f22a716ce362be48d70ae0eb012ab7 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 14 Sep 2020 17:11:52 -0700
Subject: ethtool: add standard pause stats

Currently drivers have to report their pause frames statistics
via ethtool -S, and there is a wide variety of names used for
these statistics.

Add the two statistics defined in IEEE 802.3x to the standard
API. Create a new ethtool request header flag for including
statistics in the response to GET commands.

Always create the ETHTOOL_A_PAUSE_STATS nest in replies when
flag is set. Testing if driver declares the op is not a reliable
way of checking if any stats will actually be included and therefore
we don't want to give the impression that presence of
ETHTOOL_A_PAUSE_STATS indicates driver support.

Note that this patch does not include PFC counters, which may fit
better in dcbnl? But mostly I don't need them/have a setup to test
them so I haven't looked deeply into exposing them :)

v3:
 - add a helper for "uninitializing" stats, rather than a cryptic
   memset() (Andrew)

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ethtool-netlink.rst | 11 +++++
 include/linux/ethtool.h                      | 26 ++++++++++++
 include/uapi/linux/ethtool_netlink.h         | 18 +++++++-
 net/ethtool/pause.c                          | 63 +++++++++++++++++++++++++++-
 4 files changed, 116 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst
index d53bcb31645a..2c8e0ddf548e 100644
--- a/Documentation/networking/ethtool-netlink.rst
+++ b/Documentation/networking/ethtool-netlink.rst
@@ -68,6 +68,7 @@ the flags may not apply to requests. Recognized flags are:
   =================================  ===================================
   ``ETHTOOL_FLAG_COMPACT_BITSETS``   use compact format bitsets in reply
   ``ETHTOOL_FLAG_OMIT_REPLY``        omit optional reply (_SET and _ACT)
+  ``ETHTOOL_FLAG_STATS``             include optional device statistics
   =================================  ===================================
 
 New request flags should follow the general idea that if the flag is not set,
@@ -989,8 +990,18 @@ Kernel response contents:
   ``ETHTOOL_A_PAUSE_AUTONEG``            bool    pause autonegotiation
   ``ETHTOOL_A_PAUSE_RX``                 bool    receive pause frames
   ``ETHTOOL_A_PAUSE_TX``                 bool    transmit pause frames
+  ``ETHTOOL_A_PAUSE_STATS``              nested  pause statistics
   =====================================  ======  ==========================
 
+``ETHTOOL_A_PAUSE_STATS`` are reported if ``ETHTOOL_FLAG_STATS`` was set
+in ``ETHTOOL_A_HEADER_FLAGS``.
+It will be empty if driver did not report any statistics. Drivers fill in
+the statistics in the following structure:
+
+.. kernel-doc:: include/linux/ethtool.h
+    :identifiers: ethtool_pause_stats
+
+Each member has a corresponding attribute defined.
 
 PAUSE_SET
 ============
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 969a80211df6..060b20f0b20f 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -241,6 +241,27 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32,
 	 ETHTOOL_COALESCE_PKT_RATE_LOW | ETHTOOL_COALESCE_PKT_RATE_HIGH | \
 	 ETHTOOL_COALESCE_RATE_SAMPLE_INTERVAL)
 
+#define ETHTOOL_STAT_NOT_SET	(~0ULL)
+
+/**
+ * struct ethtool_pause_stats - statistics for IEEE 802.3x pause frames
+ * @tx_pause_frames: transmitted pause frame count. Reported to user space
+ *	as %ETHTOOL_A_PAUSE_STAT_TX_FRAMES.
+ *
+ *	Equivalent to `30.3.4.2 aPAUSEMACCtrlFramesTransmitted`
+ *	from the standard.
+ *
+ * @rx_pause_frames: received pause frame count. Reported to user space
+ *	as %ETHTOOL_A_PAUSE_STAT_RX_FRAMES. Equivalent to:
+ *
+ *	Equivalent to `30.3.4.3 aPAUSEMACCtrlFramesReceived`
+ *	from the standard.
+ */
+struct ethtool_pause_stats {
+	u64 tx_pause_frames;
+	u64 rx_pause_frames;
+};
+
 /**
  * struct ethtool_ops - optional netdev operations
  * @supported_coalesce_params: supported types of interrupt coalescing.
@@ -282,6 +303,9 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32,
  *	Returns a negative error code or zero.
  * @get_ringparam: Report ring sizes
  * @set_ringparam: Set ring sizes.  Returns a negative error code or zero.
+ * @get_pause_stats: Report pause frame statistics. Drivers must not zero
+ *	statistics which they don't report. The stats structure is initialized
+ *	to ETHTOOL_STAT_NOT_SET indicating driver does not report statistics.
  * @get_pauseparam: Report pause parameters
  * @set_pauseparam: Set pause parameters.  Returns a negative error code
  *	or zero.
@@ -418,6 +442,8 @@ struct ethtool_ops {
 				 struct ethtool_ringparam *);
 	int	(*set_ringparam)(struct net_device *,
 				 struct ethtool_ringparam *);
+	void	(*get_pause_stats)(struct net_device *dev,
+				   struct ethtool_pause_stats *pause_stats);
 	void	(*get_pauseparam)(struct net_device *,
 				  struct ethtool_pauseparam*);
 	int	(*set_pauseparam)(struct net_device *,
diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h
index 5dcd24cb33ea..9cee6df01a10 100644
--- a/include/uapi/linux/ethtool_netlink.h
+++ b/include/uapi/linux/ethtool_netlink.h
@@ -91,9 +91,12 @@ enum {
 #define ETHTOOL_FLAG_COMPACT_BITSETS	(1 << 0)
 /* provide optional reply for SET or ACT requests */
 #define ETHTOOL_FLAG_OMIT_REPLY	(1 << 1)
+/* request statistics, if supported by the driver */
+#define ETHTOOL_FLAG_STATS		(1 << 2)
 
 #define ETHTOOL_FLAG_ALL (ETHTOOL_FLAG_COMPACT_BITSETS | \
-			  ETHTOOL_FLAG_OMIT_REPLY)
+			  ETHTOOL_FLAG_OMIT_REPLY | \
+			  ETHTOOL_FLAG_STATS)
 
 enum {
 	ETHTOOL_A_HEADER_UNSPEC,
@@ -376,12 +379,25 @@ enum {
 	ETHTOOL_A_PAUSE_AUTONEG,			/* u8 */
 	ETHTOOL_A_PAUSE_RX,				/* u8 */
 	ETHTOOL_A_PAUSE_TX,				/* u8 */
+	ETHTOOL_A_PAUSE_STATS,				/* nest - _PAUSE_STAT_* */
 
 	/* add new constants above here */
 	__ETHTOOL_A_PAUSE_CNT,
 	ETHTOOL_A_PAUSE_MAX = (__ETHTOOL_A_PAUSE_CNT - 1)
 };
 
+enum {
+	ETHTOOL_A_PAUSE_STAT_UNSPEC,
+	ETHTOOL_A_PAUSE_STAT_PAD,
+
+	ETHTOOL_A_PAUSE_STAT_TX_FRAMES,
+	ETHTOOL_A_PAUSE_STAT_RX_FRAMES,
+
+	/* add new constants above here */
+	__ETHTOOL_A_PAUSE_STAT_CNT,
+	ETHTOOL_A_PAUSE_STAT_MAX = (__ETHTOOL_A_PAUSE_STAT_CNT - 1)
+};
+
 /* EEE */
 
 enum {
diff --git a/net/ethtool/pause.c b/net/ethtool/pause.c
index 7aea35d1e8a5..1980aa7eb2b6 100644
--- a/net/ethtool/pause.c
+++ b/net/ethtool/pause.c
@@ -10,6 +10,7 @@ struct pause_req_info {
 struct pause_reply_data {
 	struct ethnl_reply_data		base;
 	struct ethtool_pauseparam	pauseparam;
+	struct ethtool_pause_stats	pausestat;
 };
 
 #define PAUSE_REPDATA(__reply_base) \
@@ -22,8 +23,15 @@ pause_get_policy[ETHTOOL_A_PAUSE_MAX + 1] = {
 	[ETHTOOL_A_PAUSE_AUTONEG]		= { .type = NLA_REJECT },
 	[ETHTOOL_A_PAUSE_RX]			= { .type = NLA_REJECT },
 	[ETHTOOL_A_PAUSE_TX]			= { .type = NLA_REJECT },
+	[ETHTOOL_A_PAUSE_STATS]			= { .type = NLA_REJECT },
 };
 
+static void ethtool_stats_init(u64 *stats, unsigned int n)
+{
+	while (n--)
+		stats[n] = ETHTOOL_STAT_NOT_SET;
+}
+
 static int pause_prepare_data(const struct ethnl_req_info *req_base,
 			      struct ethnl_reply_data *reply_base,
 			      struct genl_info *info)
@@ -34,10 +42,17 @@ static int pause_prepare_data(const struct ethnl_req_info *req_base,
 
 	if (!dev->ethtool_ops->get_pauseparam)
 		return -EOPNOTSUPP;
+
 	ret = ethnl_ops_begin(dev);
 	if (ret < 0)
 		return ret;
 	dev->ethtool_ops->get_pauseparam(dev, &data->pauseparam);
+	if (req_base->flags & ETHTOOL_FLAG_STATS &&
+	    dev->ethtool_ops->get_pause_stats) {
+		ethtool_stats_init((u64 *)&data->pausestat,
+				   sizeof(data->pausestat) / 8);
+		dev->ethtool_ops->get_pause_stats(dev, &data->pausestat);
+	}
 	ethnl_ops_complete(dev);
 
 	return 0;
@@ -46,9 +61,50 @@ static int pause_prepare_data(const struct ethnl_req_info *req_base,
 static int pause_reply_size(const struct ethnl_req_info *req_base,
 			    const struct ethnl_reply_data *reply_base)
 {
-	return nla_total_size(sizeof(u8)) +	/* _PAUSE_AUTONEG */
+	int n = nla_total_size(sizeof(u8)) +	/* _PAUSE_AUTONEG */
 		nla_total_size(sizeof(u8)) +	/* _PAUSE_RX */
 		nla_total_size(sizeof(u8));	/* _PAUSE_TX */
+
+	if (req_base->flags & ETHTOOL_FLAG_STATS)
+		n += nla_total_size(0) +	/* _PAUSE_STATS */
+			nla_total_size_64bit(sizeof(u64)) *
+				(ETHTOOL_A_PAUSE_STAT_MAX - 2);
+	return n;
+}
+
+static int ethtool_put_stat(struct sk_buff *skb, u64 val, u16 attrtype,
+			    u16 padtype)
+{
+	if (val == ETHTOOL_STAT_NOT_SET)
+		return 0;
+	if (nla_put_u64_64bit(skb, attrtype, val, padtype))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+static int pause_put_stats(struct sk_buff *skb,
+			   const struct ethtool_pause_stats *pause_stats)
+{
+	const u16 pad = ETHTOOL_A_PAUSE_STAT_PAD;
+	struct nlattr *nest;
+
+	nest = nla_nest_start(skb, ETHTOOL_A_PAUSE_STATS);
+	if (!nest)
+		return -EMSGSIZE;
+
+	if (ethtool_put_stat(skb, pause_stats->tx_pause_frames,
+			     ETHTOOL_A_PAUSE_STAT_TX_FRAMES, pad) ||
+	    ethtool_put_stat(skb, pause_stats->rx_pause_frames,
+			     ETHTOOL_A_PAUSE_STAT_RX_FRAMES, pad))
+		goto err_cancel;
+
+	nla_nest_end(skb, nest);
+	return 0;
+
+err_cancel:
+	nla_nest_cancel(skb, nest);
+	return -EMSGSIZE;
 }
 
 static int pause_fill_reply(struct sk_buff *skb,
@@ -63,6 +119,10 @@ static int pause_fill_reply(struct sk_buff *skb,
 	    nla_put_u8(skb, ETHTOOL_A_PAUSE_TX, !!pauseparam->tx_pause))
 		return -EMSGSIZE;
 
+	if (req_base->flags & ETHTOOL_FLAG_STATS &&
+	    pause_put_stats(skb, &data->pausestat))
+		return -EMSGSIZE;
+
 	return 0;
 }
 
@@ -89,6 +149,7 @@ pause_set_policy[ETHTOOL_A_PAUSE_MAX + 1] = {
 	[ETHTOOL_A_PAUSE_AUTONEG]		= { .type = NLA_U8 },
 	[ETHTOOL_A_PAUSE_RX]			= { .type = NLA_U8 },
 	[ETHTOOL_A_PAUSE_TX]			= { .type = NLA_U8 },
+	[ETHTOOL_A_PAUSE_STATS]			= { .type = NLA_REJECT },
 };
 
 int ethnl_set_pause(struct sk_buff *skb, struct genl_info *info)
-- 
cgit v1.2.3


From 984fe94f94756dacb3c8cc52904a23adf9e04da1 Mon Sep 17 00:00:00 2001
From: YiFei Zhu <zhuyifei@google.com>
Date: Tue, 15 Sep 2020 16:45:39 -0700
Subject: bpf: Mutex protect used_maps array and count

To support modifying the used_maps array, we use a mutex to protect
the use of the counter and the array. The mutex is initialized right
after the prog aux is allocated, and destroyed right before prog
aux is freed. This way we guarantee it's initialized for both cBPF
and eBPF.

Signed-off-by: YiFei Zhu <zhuyifei@google.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Cc: YiFei Zhu <zhuyifei1999@gmail.com>
Link: https://lore.kernel.org/bpf/20200915234543.3220146-2-sdf@google.com
---
 drivers/net/ethernet/netronome/nfp/bpf/offload.c | 18 ++++++++++++------
 include/linux/bpf.h                              |  1 +
 kernel/bpf/core.c                                | 15 +++++++++++----
 kernel/bpf/syscall.c                             | 16 ++++++++++++----
 net/core/dev.c                                   | 11 ++++++++---
 5 files changed, 44 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index ac02369174a9..53851853562c 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -111,7 +111,9 @@ static int
 nfp_map_ptrs_record(struct nfp_app_bpf *bpf, struct nfp_prog *nfp_prog,
 		    struct bpf_prog *prog)
 {
-	int i, cnt, err;
+	int i, cnt, err = 0;
+
+	mutex_lock(&prog->aux->used_maps_mutex);
 
 	/* Quickly count the maps we will have to remember */
 	cnt = 0;
@@ -119,13 +121,15 @@ nfp_map_ptrs_record(struct nfp_app_bpf *bpf, struct nfp_prog *nfp_prog,
 		if (bpf_map_offload_neutral(prog->aux->used_maps[i]))
 			cnt++;
 	if (!cnt)
-		return 0;
+		goto out;
 
 	nfp_prog->map_records = kmalloc_array(cnt,
 					      sizeof(nfp_prog->map_records[0]),
 					      GFP_KERNEL);
-	if (!nfp_prog->map_records)
-		return -ENOMEM;
+	if (!nfp_prog->map_records) {
+		err = -ENOMEM;
+		goto out;
+	}
 
 	for (i = 0; i < prog->aux->used_map_cnt; i++)
 		if (bpf_map_offload_neutral(prog->aux->used_maps[i])) {
@@ -133,12 +137,14 @@ nfp_map_ptrs_record(struct nfp_app_bpf *bpf, struct nfp_prog *nfp_prog,
 						 prog->aux->used_maps[i]);
 			if (err) {
 				nfp_map_ptrs_forget(bpf, nfp_prog);
-				return err;
+				goto out;
 			}
 		}
 	WARN_ON(cnt != nfp_prog->map_records_cnt);
 
-	return 0;
+out:
+	mutex_unlock(&prog->aux->used_maps_mutex);
+	return err;
 }
 
 static int
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index c6d9f2c444f4..5dcce0364634 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -751,6 +751,7 @@ struct bpf_prog_aux {
 	struct bpf_ksym ksym;
 	const struct bpf_prog_ops *ops;
 	struct bpf_map **used_maps;
+	struct mutex used_maps_mutex; /* mutex for used_maps and used_map_cnt */
 	struct bpf_prog *prog;
 	struct user_struct *user;
 	u64 load_time; /* ns since boottime */
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index ed0b3578867c..2a20c2833996 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -98,6 +98,7 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag
 	fp->jit_requested = ebpf_jit_enabled();
 
 	INIT_LIST_HEAD_RCU(&fp->aux->ksym.lnode);
+	mutex_init(&fp->aux->used_maps_mutex);
 
 	return fp;
 }
@@ -253,6 +254,7 @@ struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
 void __bpf_prog_free(struct bpf_prog *fp)
 {
 	if (fp->aux) {
+		mutex_destroy(&fp->aux->used_maps_mutex);
 		free_percpu(fp->aux->stats);
 		kfree(fp->aux->poke_tab);
 		kfree(fp->aux);
@@ -1747,8 +1749,9 @@ bool bpf_prog_array_compatible(struct bpf_array *array,
 static int bpf_check_tail_call(const struct bpf_prog *fp)
 {
 	struct bpf_prog_aux *aux = fp->aux;
-	int i;
+	int i, ret = 0;
 
+	mutex_lock(&aux->used_maps_mutex);
 	for (i = 0; i < aux->used_map_cnt; i++) {
 		struct bpf_map *map = aux->used_maps[i];
 		struct bpf_array *array;
@@ -1757,11 +1760,15 @@ static int bpf_check_tail_call(const struct bpf_prog *fp)
 			continue;
 
 		array = container_of(map, struct bpf_array, map);
-		if (!bpf_prog_array_compatible(array, fp))
-			return -EINVAL;
+		if (!bpf_prog_array_compatible(array, fp)) {
+			ret = -EINVAL;
+			goto out;
+		}
 	}
 
-	return 0;
+out:
+	mutex_unlock(&aux->used_maps_mutex);
+	return ret;
 }
 
 static void bpf_prog_select_func(struct bpf_prog *fp)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 4108ef3b828b..a67b8c6746be 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3162,21 +3162,25 @@ static const struct bpf_map *bpf_map_from_imm(const struct bpf_prog *prog,
 	const struct bpf_map *map;
 	int i;
 
+	mutex_lock(&prog->aux->used_maps_mutex);
 	for (i = 0, *off = 0; i < prog->aux->used_map_cnt; i++) {
 		map = prog->aux->used_maps[i];
 		if (map == (void *)addr) {
 			*type = BPF_PSEUDO_MAP_FD;
-			return map;
+			goto out;
 		}
 		if (!map->ops->map_direct_value_meta)
 			continue;
 		if (!map->ops->map_direct_value_meta(map, addr, off)) {
 			*type = BPF_PSEUDO_MAP_VALUE;
-			return map;
+			goto out;
 		}
 	}
+	map = NULL;
 
-	return NULL;
+out:
+	mutex_unlock(&prog->aux->used_maps_mutex);
+	return map;
 }
 
 static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog,
@@ -3294,6 +3298,7 @@ static int bpf_prog_get_info_by_fd(struct file *file,
 	memcpy(info.tag, prog->tag, sizeof(prog->tag));
 	memcpy(info.name, prog->aux->name, sizeof(prog->aux->name));
 
+	mutex_lock(&prog->aux->used_maps_mutex);
 	ulen = info.nr_map_ids;
 	info.nr_map_ids = prog->aux->used_map_cnt;
 	ulen = min_t(u32, info.nr_map_ids, ulen);
@@ -3303,9 +3308,12 @@ static int bpf_prog_get_info_by_fd(struct file *file,
 
 		for (i = 0; i < ulen; i++)
 			if (put_user(prog->aux->used_maps[i]->id,
-				     &user_map_ids[i]))
+				     &user_map_ids[i])) {
+				mutex_unlock(&prog->aux->used_maps_mutex);
 				return -EFAULT;
+			}
 	}
+	mutex_unlock(&prog->aux->used_maps_mutex);
 
 	err = set_info_rec_size(&info);
 	if (err)
diff --git a/net/core/dev.c b/net/core/dev.c
index d42c9ea0c3c0..75d7f91337d9 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5441,15 +5441,20 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp)
 	if (new) {
 		u32 i;
 
+		mutex_lock(&new->aux->used_maps_mutex);
+
 		/* generic XDP does not work with DEVMAPs that can
 		 * have a bpf_prog installed on an entry
 		 */
 		for (i = 0; i < new->aux->used_map_cnt; i++) {
-			if (dev_map_can_have_prog(new->aux->used_maps[i]))
-				return -EINVAL;
-			if (cpu_map_prog_allowed(new->aux->used_maps[i]))
+			if (dev_map_can_have_prog(new->aux->used_maps[i]) ||
+			    cpu_map_prog_allowed(new->aux->used_maps[i])) {
+				mutex_unlock(&new->aux->used_maps_mutex);
 				return -EINVAL;
+			}
 		}
+
+		mutex_unlock(&new->aux->used_maps_mutex);
 	}
 
 	switch (xdp->command) {
-- 
cgit v1.2.3


From fcc2cc1f35613c016e1de25bb001bfdd9eaa25f9 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 14 Sep 2020 17:37:46 +0200
Subject: USB: move snd_usb_pipe_sanity_check into the USB core

snd_usb_pipe_sanity_check() is a great function, so let's move it into
the USB core so that other parts of the kernel, including the USB core,
can call it.

Name it usb_pipe_type_check() to match the existing
usb_urb_ep_type_check() call, which now uses this function.

Cc: Jaroslav Kysela <perex@perex.cz>
Cc: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Cc: Eli Billauer <eli.billauer@gmail.com>
Cc: Emiliano Ingrassia <ingrassia@epigenesys.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Alexander Tsoy <alexander@tsoy.me>
Cc: "Geoffrey D. Bennett" <g@b4.vu>
Cc: Jussi Laako <jussi@sonarnerd.net>
Cc: Nick Kossifidis <mickflemm@gmail.com>
Cc: Dmitry Panchenko <dmitry@d-systems.ee>
Cc: Chris Wulff <crwulff@gmail.com>
Cc: Jesus Ramos <jesus-ramos@live.com>
Reviewed-by: Takashi Iwai <tiwai@suse.de>
Link: https://lore.kernel.org/r/20200914153756.3412156-2-gregkh@linuxfoundation.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/urb.c          | 31 +++++++++++++++++++++++--------
 include/linux/usb.h             |  1 +
 sound/usb/helper.c              | 16 +---------------
 sound/usb/helper.h              |  1 -
 sound/usb/mixer_scarlett_gen2.c |  2 +-
 sound/usb/quirks.c              | 12 ++++++------
 6 files changed, 32 insertions(+), 31 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/usb/core/urb.c b/drivers/usb/core/urb.c
index 27e83e55a590..357b149b20d3 100644
--- a/drivers/usb/core/urb.c
+++ b/drivers/usb/core/urb.c
@@ -192,24 +192,39 @@ static const int pipetypes[4] = {
 };
 
 /**
- * usb_urb_ep_type_check - sanity check of endpoint in the given urb
- * @urb: urb to be checked
+ * usb_pipe_type_check - sanity check of a specific pipe for a usb device
+ * @dev: struct usb_device to be checked
+ * @pipe: pipe to check
  *
  * This performs a light-weight sanity check for the endpoint in the
- * given urb.  It returns 0 if the urb contains a valid endpoint, otherwise
- * a negative error code.
+ * given usb device.  It returns 0 if the pipe is valid for the specific usb
+ * device, otherwise a negative error code.
  */
-int usb_urb_ep_type_check(const struct urb *urb)
+int usb_pipe_type_check(struct usb_device *dev, unsigned int pipe)
 {
 	const struct usb_host_endpoint *ep;
 
-	ep = usb_pipe_endpoint(urb->dev, urb->pipe);
+	ep = usb_pipe_endpoint(dev, pipe);
 	if (!ep)
 		return -EINVAL;
-	if (usb_pipetype(urb->pipe) != pipetypes[usb_endpoint_type(&ep->desc)])
+	if (usb_pipetype(pipe) != pipetypes[usb_endpoint_type(&ep->desc)])
 		return -EINVAL;
 	return 0;
 }
+EXPORT_SYMBOL_GPL(usb_pipe_type_check);
+
+/**
+ * usb_urb_ep_type_check - sanity check of endpoint in the given urb
+ * @urb: urb to be checked
+ *
+ * This performs a light-weight sanity check for the endpoint in the
+ * given urb.  It returns 0 if the urb contains a valid endpoint, otherwise
+ * a negative error code.
+ */
+int usb_urb_ep_type_check(const struct urb *urb)
+{
+	return usb_pipe_type_check(urb->dev, urb->pipe);
+}
 EXPORT_SYMBOL_GPL(usb_urb_ep_type_check);
 
 /**
@@ -474,7 +489,7 @@ int usb_submit_urb(struct urb *urb, gfp_t mem_flags)
 	 */
 
 	/* Check that the pipe's type matches the endpoint's type */
-	if (usb_urb_ep_type_check(urb))
+	if (usb_pipe_type_check(urb->dev, urb->pipe))
 		dev_WARN(&dev->dev, "BOGUS urb xfer, pipe %x != type %x\n",
 			usb_pipetype(urb->pipe), pipetypes[xfertype]);
 
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 20c555db4621..0b3963d7ec38 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1764,6 +1764,7 @@ static inline int usb_urb_dir_out(struct urb *urb)
 	return (urb->transfer_flags & URB_DIR_MASK) == URB_DIR_OUT;
 }
 
+int usb_pipe_type_check(struct usb_device *dev, unsigned int pipe);
 int usb_urb_ep_type_check(const struct urb *urb);
 
 void *usb_alloc_coherent(struct usb_device *dev, size_t size,
diff --git a/sound/usb/helper.c b/sound/usb/helper.c
index 4c12cc5b53fd..cf92d7110773 100644
--- a/sound/usb/helper.c
+++ b/sound/usb/helper.c
@@ -63,20 +63,6 @@ void *snd_usb_find_csint_desc(void *buffer, int buflen, void *after, u8 dsubtype
 	return NULL;
 }
 
-/* check the validity of pipe and EP types */
-int snd_usb_pipe_sanity_check(struct usb_device *dev, unsigned int pipe)
-{
-	static const int pipetypes[4] = {
-		PIPE_CONTROL, PIPE_ISOCHRONOUS, PIPE_BULK, PIPE_INTERRUPT
-	};
-	struct usb_host_endpoint *ep;
-
-	ep = usb_pipe_endpoint(dev, pipe);
-	if (!ep || usb_pipetype(pipe) != pipetypes[usb_endpoint_type(&ep->desc)])
-		return -EINVAL;
-	return 0;
-}
-
 /*
  * Wrapper for usb_control_msg().
  * Allocates a temp buffer to prevent dmaing from/to the stack.
@@ -89,7 +75,7 @@ int snd_usb_ctl_msg(struct usb_device *dev, unsigned int pipe, __u8 request,
 	void *buf = NULL;
 	int timeout;
 
-	if (snd_usb_pipe_sanity_check(dev, pipe))
+	if (usb_pipe_type_check(dev, pipe))
 		return -EINVAL;
 
 	if (size > 0) {
diff --git a/sound/usb/helper.h b/sound/usb/helper.h
index 5e8a18b4e7b9..f5b4c6647e4d 100644
--- a/sound/usb/helper.h
+++ b/sound/usb/helper.h
@@ -7,7 +7,6 @@ unsigned int snd_usb_combine_bytes(unsigned char *bytes, int size);
 void *snd_usb_find_desc(void *descstart, int desclen, void *after, u8 dtype);
 void *snd_usb_find_csint_desc(void *descstart, int desclen, void *after, u8 dsubtype);
 
-int snd_usb_pipe_sanity_check(struct usb_device *dev, unsigned int pipe);
 int snd_usb_ctl_msg(struct usb_device *dev, unsigned int pipe,
 		    __u8 request, __u8 requesttype, __u16 value, __u16 index,
 		    void *data, __u16 size);
diff --git a/sound/usb/mixer_scarlett_gen2.c b/sound/usb/mixer_scarlett_gen2.c
index 0ffff7640892..9609c6d9655c 100644
--- a/sound/usb/mixer_scarlett_gen2.c
+++ b/sound/usb/mixer_scarlett_gen2.c
@@ -1978,7 +1978,7 @@ static int scarlett2_mixer_status_create(struct usb_mixer_interface *mixer)
 		return 0;
 	}
 
-	if (snd_usb_pipe_sanity_check(dev, pipe))
+	if (usb_pipe_type_check(dev, pipe))
 		return -EINVAL;
 
 	mixer->urb = usb_alloc_urb(0, GFP_KERNEL);
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 75bbdc691243..1b482848e73b 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -856,7 +856,7 @@ static int snd_usb_accessmusic_boot_quirk(struct usb_device *dev)
 	static const u8 seq[] = { 0x4e, 0x73, 0x52, 0x01 };
 	void *buf;
 
-	if (snd_usb_pipe_sanity_check(dev, usb_sndintpipe(dev, 0x05)))
+	if (usb_pipe_type_check(dev, usb_sndintpipe(dev, 0x05)))
 		return -EINVAL;
 	buf = kmemdup(seq, ARRAY_SIZE(seq), GFP_KERNEL);
 	if (!buf)
@@ -885,7 +885,7 @@ static int snd_usb_nativeinstruments_boot_quirk(struct usb_device *dev)
 {
 	int ret;
 
-	if (snd_usb_pipe_sanity_check(dev, usb_sndctrlpipe(dev, 0)))
+	if (usb_pipe_type_check(dev, usb_sndctrlpipe(dev, 0)))
 		return -EINVAL;
 	ret = usb_control_msg(dev, usb_sndctrlpipe(dev, 0),
 				  0xaf, USB_TYPE_VENDOR | USB_RECIP_DEVICE,
@@ -994,7 +994,7 @@ static int snd_usb_axefx3_boot_quirk(struct usb_device *dev)
 
 	dev_dbg(&dev->dev, "Waiting for Axe-Fx III to boot up...\n");
 
-	if (snd_usb_pipe_sanity_check(dev, usb_sndctrlpipe(dev, 0)))
+	if (usb_pipe_type_check(dev, usb_sndctrlpipe(dev, 0)))
 		return -EINVAL;
 	/* If the Axe-Fx III has not fully booted, it will timeout when trying
 	 * to enable the audio streaming interface. A more generous timeout is
@@ -1028,7 +1028,7 @@ static int snd_usb_motu_microbookii_communicate(struct usb_device *dev, u8 *buf,
 {
 	int err, actual_length;
 
-	if (snd_usb_pipe_sanity_check(dev, usb_sndintpipe(dev, 0x01)))
+	if (usb_pipe_type_check(dev, usb_sndintpipe(dev, 0x01)))
 		return -EINVAL;
 	err = usb_interrupt_msg(dev, usb_sndintpipe(dev, 0x01), buf, *length,
 				&actual_length, 1000);
@@ -1040,7 +1040,7 @@ static int snd_usb_motu_microbookii_communicate(struct usb_device *dev, u8 *buf,
 
 	memset(buf, 0, buf_size);
 
-	if (snd_usb_pipe_sanity_check(dev, usb_rcvintpipe(dev, 0x82)))
+	if (usb_pipe_type_check(dev, usb_rcvintpipe(dev, 0x82)))
 		return -EINVAL;
 	err = usb_interrupt_msg(dev, usb_rcvintpipe(dev, 0x82), buf, buf_size,
 				&actual_length, 1000);
@@ -1127,7 +1127,7 @@ static int snd_usb_motu_m_series_boot_quirk(struct usb_device *dev)
 {
 	int ret;
 
-	if (snd_usb_pipe_sanity_check(dev, usb_sndctrlpipe(dev, 0)))
+	if (usb_pipe_type_check(dev, usb_sndctrlpipe(dev, 0)))
 		return -EINVAL;
 	ret = usb_control_msg(dev, usb_sndctrlpipe(dev, 0),
 			      1, USB_TYPE_VENDOR | USB_RECIP_DEVICE,
-- 
cgit v1.2.3


From 719b8f2850d3d9b863cc5e4f08e9ef0206e45b26 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 14 Sep 2020 17:37:47 +0200
Subject: USB: add usb_control_msg_send() and usb_control_msg_recv()

New core functions to make sending/receiving USB control messages easier
and saner.

In discussions, it turns out that the large majority of users of
usb_control_msg() do so in potentially incorrect ways.  The most common
issue is where a "short" message is received, yet never detected
properly due to "incorrect" error handling.

Handle all of this in the USB core with two new functions to try to make
working with USB control messages simpler.

No more need for dynamic data, messages can be on the stack, and only
"complete" send/receive will work without causing an error.

Link: https://lore.kernel.org/r/20200914153756.3412156-3-gregkh@linuxfoundation.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/message.c | 133 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/usb.h        |   6 ++
 2 files changed, 139 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c
index ae1de9cc4b09..1dc53b12a26a 100644
--- a/drivers/usb/core/message.c
+++ b/drivers/usb/core/message.c
@@ -162,6 +162,139 @@ int usb_control_msg(struct usb_device *dev, unsigned int pipe, __u8 request,
 }
 EXPORT_SYMBOL_GPL(usb_control_msg);
 
+/**
+ * usb_control_msg_send - Builds a control "send" message, sends it off and waits for completion
+ * @dev: pointer to the usb device to send the message to
+ * @endpoint: endpoint to send the message to
+ * @request: USB message request value
+ * @requesttype: USB message request type value
+ * @value: USB message value
+ * @index: USB message index value
+ * @driver_data: pointer to the data to send
+ * @size: length in bytes of the data to send
+ * @timeout: time in msecs to wait for the message to complete before timing
+ *	out (if 0 the wait is forever)
+ *
+ * Context: !in_interrupt ()
+ *
+ * This function sends a control message to a specified endpoint that is not
+ * expected to fill in a response (i.e. a "send message") and waits for the
+ * message to complete, or timeout.
+ *
+ * Do not use this function from within an interrupt context. If you need
+ * an asynchronous message, or need to send a message from within interrupt
+ * context, use usb_submit_urb(). If a thread in your driver uses this call,
+ * make sure your disconnect() method can wait for it to complete. Since you
+ * don't have a handle on the URB used, you can't cancel the request.
+ *
+ * The data pointer can be made to a reference on the stack, or anywhere else,
+ * as it will not be modified at all.  This does not have the restriction that
+ * usb_control_msg() has where the data pointer must be to dynamically allocated
+ * memory (i.e. memory that can be successfully DMAed to a device).
+ *
+ * Return: If successful, 0 is returned, Otherwise, a negative error number.
+ */
+int usb_control_msg_send(struct usb_device *dev, __u8 endpoint, __u8 request,
+			 __u8 requesttype, __u16 value, __u16 index,
+			 const void *driver_data, __u16 size, int timeout)
+{
+	unsigned int pipe = usb_sndctrlpipe(dev, endpoint);
+	int ret;
+	u8 *data = NULL;
+
+	if (usb_pipe_type_check(dev, pipe))
+		return -EINVAL;
+
+	if (size) {
+		data = kmemdup(driver_data, size, GFP_KERNEL);
+		if (!data)
+			return -ENOMEM;
+	}
+
+	ret = usb_control_msg(dev, pipe, request, requesttype, value, index,
+			      data, size, timeout);
+	kfree(data);
+
+	if (ret < 0)
+		return ret;
+	if (ret == size)
+		return 0;
+	return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(usb_control_msg_send);
+
+/**
+ * usb_control_msg_recv - Builds a control "receive" message, sends it off and waits for completion
+ * @dev: pointer to the usb device to send the message to
+ * @endpoint: endpoint to send the message to
+ * @request: USB message request value
+ * @requesttype: USB message request type value
+ * @value: USB message value
+ * @index: USB message index value
+ * @driver_data: pointer to the data to be filled in by the message
+ * @size: length in bytes of the data to be received
+ * @timeout: time in msecs to wait for the message to complete before timing
+ *	out (if 0 the wait is forever)
+ *
+ * Context: !in_interrupt ()
+ *
+ * This function sends a control message to a specified endpoint that is
+ * expected to fill in a response (i.e. a "receive message") and waits for the
+ * message to complete, or timeout.
+ *
+ * Do not use this function from within an interrupt context. If you need
+ * an asynchronous message, or need to send a message from within interrupt
+ * context, use usb_submit_urb(). If a thread in your driver uses this call,
+ * make sure your disconnect() method can wait for it to complete. Since you
+ * don't have a handle on the URB used, you can't cancel the request.
+ *
+ * The data pointer can be made to a reference on the stack, or anywhere else
+ * that can be successfully written to.  This function does not have the
+ * restriction that usb_control_msg() has where the data pointer must be to
+ * dynamically allocated memory (i.e. memory that can be successfully DMAed to a
+ * device).
+ *
+ * The "whole" message must be properly received from the device in order for
+ * this function to be successful.  If a device returns less than the expected
+ * amount of data, then the function will fail.  Do not use this for messages
+ * where a variable amount of data might be returned.
+ *
+ * Return: If successful, 0 is returned, Otherwise, a negative error number.
+ */
+int usb_control_msg_recv(struct usb_device *dev, __u8 endpoint, __u8 request,
+			 __u8 requesttype, __u16 value, __u16 index,
+			 void *driver_data, __u16 size, int timeout)
+{
+	unsigned int pipe = usb_rcvctrlpipe(dev, endpoint);
+	int ret;
+	u8 *data;
+
+	if (!size || !driver_data || usb_pipe_type_check(dev, pipe))
+		return -EINVAL;
+
+	data = kmalloc(size, GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	ret = usb_control_msg(dev, pipe, request, requesttype, value, index,
+			      data, size, timeout);
+
+	if (ret < 0)
+		goto exit;
+
+	if (ret == size) {
+		memcpy(driver_data, data, size);
+		ret = 0;
+	} else {
+		ret = -EINVAL;
+	}
+
+exit:
+	kfree(data);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(usb_control_msg_recv);
+
 /**
  * usb_interrupt_msg - Builds an interrupt urb, sends it off and waits for completion
  * @usb_dev: pointer to the usb device to send the message to
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 0b3963d7ec38..a5460f08126e 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1802,6 +1802,12 @@ extern int usb_bulk_msg(struct usb_device *usb_dev, unsigned int pipe,
 	int timeout);
 
 /* wrappers around usb_control_msg() for the most common standard requests */
+int usb_control_msg_send(struct usb_device *dev, __u8 endpoint, __u8 request,
+			 __u8 requesttype, __u16 value, __u16 index,
+			 const void *data, __u16 size, int timeout);
+int usb_control_msg_recv(struct usb_device *dev, __u8 endpoint, __u8 request,
+			 __u8 requesttype, __u16 value, __u16 index,
+			 void *data, __u16 size, int timeout);
 extern int usb_get_descriptor(struct usb_device *dev, unsigned char desctype,
 	unsigned char descindex, void *buf, int size);
 extern int usb_get_status(struct usb_device *dev,
-- 
cgit v1.2.3


From 3babbe447d76ac2919ec4d0eb3b0adfb22f5b03c Mon Sep 17 00:00:00 2001
From: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Date: Fri, 7 Aug 2020 13:15:16 +0530
Subject: sched/topology: Allow archs to override cpu_smt_mask

cpu_smt_mask tracks topology_sibling_cpumask. This would be good for
most architectures. One of the users of cpu_smt_mask(), would be to
identify idle-cores. On Power9, a pair of SMT4 cores can be presented
by the firmware as a SMT8 core for backward compatibility reasons.

powerpc allows LPARs to be live migrated from Power8 to Power9. Do
note Power8 had only SMT8 cores. Existing software which has been
developed/configured for Power8 would expect to see SMT8 core.
Maintaining the illusion of SMT8 core is a requirement to make that
work.

In order to maintain above userspace backward compatibility with
previous versions of processor, Power9 onwards there is option to the
firmware to advertise a pair of SMT4 cores as a fused cores aka SMT8
core. On Power9 this pair shares the L2 cache as well. However, from
the scheduler's point of view, a core should be determined by SMT4,
since its a completely independent unit of compute. Hence allow
powerpc architecture to override the default cpu_smt_mask() to point
to the SMT4 cores in a SMT8 mode.

This will ensure the scheduler is always given the right information.

Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200807074517.27957-1-srikar@linux.vnet.ibm.com
---
 include/linux/topology.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/topology.h b/include/linux/topology.h
index 608fa4aadf0e..ad03df1cc266 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -198,7 +198,7 @@ static inline int cpu_to_mem(int cpu)
 #define topology_die_cpumask(cpu)		cpumask_of(cpu)
 #endif
 
-#ifdef CONFIG_SCHED_SMT
+#if defined(CONFIG_SCHED_SMT) && !defined(cpu_smt_mask)
 static inline const struct cpumask *cpu_smt_mask(int cpu)
 {
 	return topology_sibling_cpumask(cpu);
-- 
cgit v1.2.3


From a25536e8d57dd6fdd70b07219fc2c38e3b8c6503 Mon Sep 17 00:00:00 2001
From: Swapnil Jakhade <sjakhade@cadence.com>
Date: Fri, 11 Sep 2020 08:18:33 +0200
Subject: phy: Add new PHY attribute max_link_rate

Add new PHY attribute max_link_rate to struct phy_attrs. This indicates
maximum link rate supported by PHY (in Mbps).

Signed-off-by: Yuti Amonkar <yamonkar@cadence.com>
Signed-off-by: Swapnil Jakhade <sjakhade@cadence.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Acked-by: Kishon Vijay Abraham I <kishon@ti.com>
Link: https://lore.kernel.org/r/1599805114-22063-2-git-send-email-sjakhade@cadence.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/phy/phy.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h
index bcee8eba62b3..e435bdb0bab3 100644
--- a/include/linux/phy/phy.h
+++ b/include/linux/phy/phy.h
@@ -115,10 +115,12 @@ struct phy_ops {
 /**
  * struct phy_attrs - represents phy attributes
  * @bus_width: Data path width implemented by PHY
+ * @max_link_rate: Maximum link rate supported by PHY (in Mbps)
  * @mode: PHY mode
  */
 struct phy_attrs {
 	u32			bus_width;
+	u32			max_link_rate;
 	enum phy_mode		mode;
 };
 
-- 
cgit v1.2.3


From 42d8a346c5c06689f4f25aecfa287a5aca501a55 Mon Sep 17 00:00:00 2001
From: Xianting Tian <tian.xianting@h3c.com>
Date: Wed, 16 Sep 2020 14:21:29 +0800
Subject: ipmi: add retry in try_get_dev_id()

Use a retry machanism to give the BMC more opportunities to correctly
respond when we receive specific completion codes.

This is similar to what is done in __get_device_id().

Signed-off-by: Xianting Tian <tian.xianting@h3c.com>
Message-Id: <20200916062129.26129-1-tian.xianting@h3c.com>
[Moved GET_DEVICE_ID_MAX_RETRY to include/linux/ipmi.h, reworded some
 text.]
Signed-off-by: Corey Minyard <cminyard@mvista.com>
---
 drivers/char/ipmi/ipmi_msghandler.c |  2 --
 drivers/char/ipmi/ipmi_si_intf.c    | 17 +++++++++++++++++
 include/linux/ipmi.h                |  2 ++
 3 files changed, 19 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index e56409659459..555c3b1e4926 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -62,8 +62,6 @@ enum ipmi_panic_event_op {
 #define IPMI_PANIC_DEFAULT IPMI_SEND_PANIC_EVENT_NONE
 #endif
 
-#define GET_DEVICE_ID_MAX_RETRY	5
-
 static enum ipmi_panic_event_op ipmi_send_panic_event = IPMI_PANIC_DEFAULT;
 
 static int panic_op_write_handler(const char *val,
diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index 77b8d551ae7f..164f85007080 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -1316,6 +1316,7 @@ static int try_get_dev_id(struct smi_info *smi_info)
 	unsigned char         *resp;
 	unsigned long         resp_len;
 	int                   rv = 0;
+	unsigned int          retry_count = 0;
 
 	resp = kmalloc(IPMI_MAX_MSG_LENGTH, GFP_KERNEL);
 	if (!resp)
@@ -1327,6 +1328,8 @@ static int try_get_dev_id(struct smi_info *smi_info)
 	 */
 	msg[0] = IPMI_NETFN_APP_REQUEST << 2;
 	msg[1] = IPMI_GET_DEVICE_ID_CMD;
+
+retry:
 	smi_info->handlers->start_transaction(smi_info->si_sm, msg, 2);
 
 	rv = wait_for_msg_done(smi_info);
@@ -1339,6 +1342,20 @@ static int try_get_dev_id(struct smi_info *smi_info)
 	/* Check and record info from the get device id, in case we need it. */
 	rv = ipmi_demangle_device_id(resp[0] >> 2, resp[1],
 			resp + 2, resp_len - 2, &smi_info->device_id);
+	if (rv) {
+		/* record completion code */
+		char cc = *(resp + 2);
+
+		if ((cc == IPMI_DEVICE_IN_FW_UPDATE_ERR
+		    || cc == IPMI_DEVICE_IN_INIT_ERR
+		    || cc == IPMI_NOT_IN_MY_STATE_ERR)
+		    && ++retry_count <= GET_DEVICE_ID_MAX_RETRY) {
+			dev_warn(smi_info->io.dev,
+			    "BMC returned 0x%2.2x, retry get bmc device id\n",
+			    cc);
+			goto retry;
+		}
+	}
 
 out:
 	kfree(resp);
diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h
index ef61676cfe05..52850a02a3d0 100644
--- a/include/linux/ipmi.h
+++ b/include/linux/ipmi.h
@@ -333,4 +333,6 @@ struct ipmi_smi_info {
 /* This is to get the private info of struct ipmi_smi */
 extern int ipmi_get_smi_info(int if_num, struct ipmi_smi_info *data);
 
+#define GET_DEVICE_ID_MAX_RETRY		5
+
 #endif /* __LINUX_IPMI_H */
-- 
cgit v1.2.3


From 267580db047ef428a70bef8287ca62c5a450c139 Mon Sep 17 00:00:00 2001
From: "peterz@infradead.org" <peterz@infradead.org>
Date: Tue, 15 Sep 2020 16:30:28 +0200
Subject: seqlock: Unbreak lockdep

seqcount_LOCKNAME_init() needs to be a macro due to the lockdep
annotation in seqcount_init(). Since a macro cannot define another
macro, we need to effectively revert commit: e4e9ab3f9f91 ("seqlock:
Fold seqcount_LOCKNAME_init() definition").

Fixes: e4e9ab3f9f91 ("seqlock: Fold seqcount_LOCKNAME_init() definition")
Reported-by: Qian Cai <cai@redhat.com>
Debugged-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Qian Cai <cai@redhat.com>
Link: https://lkml.kernel.org/r/20200915143028.GB2674@hirez.programming.kicks-ass.net
---
 include/linux/seqlock.h | 22 ++++++++++++++--------
 1 file changed, 14 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index f73c7eb68f27..76e44e6c0100 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -173,6 +173,19 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
  * @lock:	Pointer to the associated lock
  */
 
+#define seqcount_LOCKNAME_init(s, _lock, lockname)			\
+	do {								\
+		seqcount_##lockname##_t *____s = (s);			\
+		seqcount_init(&____s->seqcount);			\
+		__SEQ_LOCK(____s->lock = (_lock));			\
+	} while (0)
+
+#define seqcount_raw_spinlock_init(s, lock)	seqcount_LOCKNAME_init(s, lock, raw_spinlock)
+#define seqcount_spinlock_init(s, lock)		seqcount_LOCKNAME_init(s, lock, spinlock)
+#define seqcount_rwlock_init(s, lock)		seqcount_LOCKNAME_init(s, lock, rwlock);
+#define seqcount_mutex_init(s, lock)		seqcount_LOCKNAME_init(s, lock, mutex);
+#define seqcount_ww_mutex_init(s, lock)		seqcount_LOCKNAME_init(s, lock, ww_mutex);
+
 /*
  * SEQCOUNT_LOCKNAME()	- Instantiate seqcount_LOCKNAME_t and helpers
  * seqprop_LOCKNAME_*()	- Property accessors for seqcount_LOCKNAME_t
@@ -190,13 +203,6 @@ typedef struct seqcount_##lockname {					\
 	__SEQ_LOCK(locktype	*lock);					\
 } seqcount_##lockname##_t;						\
 									\
-static __always_inline void						\
-seqcount_##lockname##_init(seqcount_##lockname##_t *s, locktype *lock)	\
-{									\
-	seqcount_init(&s->seqcount);					\
-	__SEQ_LOCK(s->lock = lock);					\
-}									\
-									\
 static __always_inline seqcount_t *					\
 __seqprop_##lockname##_ptr(seqcount_##lockname##_t *s)			\
 {									\
@@ -284,8 +290,8 @@ SEQCOUNT_LOCKNAME(ww_mutex,     struct ww_mutex, true,     &s->lock->base, ww_mu
 	__SEQ_LOCK(.lock	= (assoc_lock))				\
 }
 
-#define SEQCNT_SPINLOCK_ZERO(name, lock)	SEQCOUNT_LOCKNAME_ZERO(name, lock)
 #define SEQCNT_RAW_SPINLOCK_ZERO(name, lock)	SEQCOUNT_LOCKNAME_ZERO(name, lock)
+#define SEQCNT_SPINLOCK_ZERO(name, lock)	SEQCOUNT_LOCKNAME_ZERO(name, lock)
 #define SEQCNT_RWLOCK_ZERO(name, lock)		SEQCOUNT_LOCKNAME_ZERO(name, lock)
 #define SEQCNT_MUTEX_ZERO(name, lock)		SEQCOUNT_LOCKNAME_ZERO(name, lock)
 #define SEQCNT_WW_MUTEX_ZERO(name, lock) 	SEQCOUNT_LOCKNAME_ZERO(name, lock)
-- 
cgit v1.2.3


From dfb9eb7cf6cd0c0b0f2a1111fcc47b0a297b097d Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 26 Aug 2020 13:16:45 +0200
Subject: PCI/MSI: Rework pci_msi_domain_calc_hwirq()

Retrieve the PCI device from the msi descriptor instead of doing so at the
call sites.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200826112332.352583299@linutronix.de
---
 arch/x86/kernel/apic/msi.c | 2 +-
 drivers/pci/msi.c          | 9 ++++-----
 include/linux/msi.h        | 3 +--
 3 files changed, 6 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index ebf57dba111f..6d7655b07f84 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -231,7 +231,7 @@ EXPORT_SYMBOL_GPL(pci_msi_prepare);
 
 void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc)
 {
-	arg->msi_hwirq = pci_msi_domain_calc_hwirq(arg->msi_dev, desc);
+	arg->msi_hwirq = pci_msi_domain_calc_hwirq(desc);
 }
 EXPORT_SYMBOL_GPL(pci_msi_set_desc);
 
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 30ae4ffda5c1..9af58a2ab277 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -1346,14 +1346,14 @@ void pci_msi_domain_write_msg(struct irq_data *irq_data, struct msi_msg *msg)
 
 /**
  * pci_msi_domain_calc_hwirq - Generate a unique ID for an MSI source
- * @dev:	Pointer to the PCI device
  * @desc:	Pointer to the MSI descriptor
  *
  * The ID number is only used within the irqdomain.
  */
-irq_hw_number_t pci_msi_domain_calc_hwirq(struct pci_dev *dev,
-					  struct msi_desc *desc)
+irq_hw_number_t pci_msi_domain_calc_hwirq(struct msi_desc *desc)
 {
+	struct pci_dev *dev = msi_desc_to_pci_dev(desc);
+
 	return (irq_hw_number_t)desc->msi_attrib.entry_nr |
 		pci_dev_id(dev) << 11 |
 		(pci_domain_nr(dev->bus) & 0xFFFFFFFF) << 27;
@@ -1406,8 +1406,7 @@ static void pci_msi_domain_set_desc(msi_alloc_info_t *arg,
 				    struct msi_desc *desc)
 {
 	arg->desc = desc;
-	arg->hwirq = pci_msi_domain_calc_hwirq(msi_desc_to_pci_dev(desc),
-					       desc);
+	arg->hwirq = pci_msi_domain_calc_hwirq(desc);
 }
 #else
 #define pci_msi_domain_set_desc		NULL
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 8ad679e9d9c0..d360cc7c4f94 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -369,8 +369,7 @@ void pci_msi_domain_write_msg(struct irq_data *irq_data, struct msi_msg *msg);
 struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode,
 					     struct msi_domain_info *info,
 					     struct irq_domain *parent);
-irq_hw_number_t pci_msi_domain_calc_hwirq(struct pci_dev *dev,
-					  struct msi_desc *desc);
+irq_hw_number_t pci_msi_domain_calc_hwirq(struct msi_desc *desc);
 int pci_msi_domain_check_cap(struct irq_domain *domain,
 			     struct msi_domain_info *info, struct device *dev);
 u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev);
-- 
cgit v1.2.3


From 9006c133a422f474d7d8e10a8baae179f70c22f5 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 26 Aug 2020 13:16:47 +0200
Subject: x86/msi: Use generic MSI domain ops

pci_msi_get_hwirq() and pci_msi_set_desc are not longer special. Enable the
generic MSI domain ops in the core and PCI MSI code unconditionally and get
rid of the x86 specific implementations in the X86 MSI code and in the
hyperv PCI driver.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200826112332.564274859@linutronix.de
---
 arch/x86/include/asm/msi.h          |  2 --
 arch/x86/kernel/apic/msi.c          | 30 +-----------------------------
 drivers/pci/controller/pci-hyperv.c |  8 --------
 drivers/pci/msi.c                   |  6 +-----
 include/linux/msi.h                 |  1 -
 kernel/irq/msi.c                    |  6 ------
 6 files changed, 2 insertions(+), 51 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/include/asm/msi.h b/arch/x86/include/asm/msi.h
index 25ddd0916bb2..cd30013d15d3 100644
--- a/arch/x86/include/asm/msi.h
+++ b/arch/x86/include/asm/msi.h
@@ -9,6 +9,4 @@ typedef struct irq_alloc_info msi_alloc_info_t;
 int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec,
 		    msi_alloc_info_t *arg);
 
-void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc);
-
 #endif /* _ASM_X86_MSI_H */
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index 6b490d9a2537..378c692a4170 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -203,12 +203,6 @@ void native_teardown_msi_irq(unsigned int irq)
 	irq_domain_free_irqs(irq, 1);
 }
 
-static irq_hw_number_t pci_msi_get_hwirq(struct msi_domain_info *info,
-					 msi_alloc_info_t *arg)
-{
-	return arg->hwirq;
-}
-
 int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec,
 		    msi_alloc_info_t *arg)
 {
@@ -227,17 +221,8 @@ int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec,
 }
 EXPORT_SYMBOL_GPL(pci_msi_prepare);
 
-void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc)
-{
-	arg->desc = desc;
-	arg->hwirq = pci_msi_domain_calc_hwirq(desc);
-}
-EXPORT_SYMBOL_GPL(pci_msi_set_desc);
-
 static struct msi_domain_ops pci_msi_domain_ops = {
-	.get_hwirq	= pci_msi_get_hwirq,
 	.msi_prepare	= pci_msi_prepare,
-	.set_desc	= pci_msi_set_desc,
 };
 
 static struct msi_domain_info pci_msi_domain_info = {
@@ -322,12 +307,6 @@ static struct irq_chip dmar_msi_controller = {
 	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
-static irq_hw_number_t dmar_msi_get_hwirq(struct msi_domain_info *info,
-					  msi_alloc_info_t *arg)
-{
-	return arg->hwirq;
-}
-
 static int dmar_msi_init(struct irq_domain *domain,
 			 struct msi_domain_info *info, unsigned int virq,
 			 irq_hw_number_t hwirq, msi_alloc_info_t *arg)
@@ -339,7 +318,6 @@ static int dmar_msi_init(struct irq_domain *domain,
 }
 
 static struct msi_domain_ops dmar_msi_domain_ops = {
-	.get_hwirq	= dmar_msi_get_hwirq,
 	.msi_init	= dmar_msi_init,
 };
 
@@ -381,6 +359,7 @@ int dmar_alloc_hwirq(int id, int node, void *arg)
 	init_irq_alloc_info(&info, NULL);
 	info.type = X86_IRQ_ALLOC_TYPE_DMAR;
 	info.devid = id;
+	info.hwirq = id;
 	info.data = arg;
 
 	return irq_domain_alloc_irqs(domain, 1, node, &info);
@@ -419,12 +398,6 @@ static struct irq_chip hpet_msi_controller __ro_after_init = {
 	.flags = IRQCHIP_SKIP_SET_WAKE,
 };
 
-static irq_hw_number_t hpet_msi_get_hwirq(struct msi_domain_info *info,
-					  msi_alloc_info_t *arg)
-{
-	return arg->hwirq;
-}
-
 static int hpet_msi_init(struct irq_domain *domain,
 			 struct msi_domain_info *info, unsigned int virq,
 			 irq_hw_number_t hwirq, msi_alloc_info_t *arg)
@@ -443,7 +416,6 @@ static void hpet_msi_free(struct irq_domain *domain,
 }
 
 static struct msi_domain_ops hpet_msi_domain_ops = {
-	.get_hwirq	= hpet_msi_get_hwirq,
 	.msi_init	= hpet_msi_init,
 	.msi_free	= hpet_msi_free,
 };
diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index f6cc49ba6e80..25b4c9023bfa 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -1531,16 +1531,8 @@ static struct irq_chip hv_msi_irq_chip = {
 	.irq_unmask		= hv_irq_unmask,
 };
 
-static irq_hw_number_t hv_msi_domain_ops_get_hwirq(struct msi_domain_info *info,
-						   msi_alloc_info_t *arg)
-{
-	return arg->hwirq;
-}
-
 static struct msi_domain_ops hv_msi_ops = {
-	.get_hwirq	= hv_msi_domain_ops_get_hwirq,
 	.msi_prepare	= pci_msi_prepare,
-	.set_desc	= pci_msi_set_desc,
 	.msi_free	= hv_msi_free,
 };
 
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 9af58a2ab277..744a1a4d2b32 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -1350,7 +1350,7 @@ void pci_msi_domain_write_msg(struct irq_data *irq_data, struct msi_msg *msg)
  *
  * The ID number is only used within the irqdomain.
  */
-irq_hw_number_t pci_msi_domain_calc_hwirq(struct msi_desc *desc)
+static irq_hw_number_t pci_msi_domain_calc_hwirq(struct msi_desc *desc)
 {
 	struct pci_dev *dev = msi_desc_to_pci_dev(desc);
 
@@ -1401,16 +1401,12 @@ static int pci_msi_domain_handle_error(struct irq_domain *domain,
 	return error;
 }
 
-#ifdef GENERIC_MSI_DOMAIN_OPS
 static void pci_msi_domain_set_desc(msi_alloc_info_t *arg,
 				    struct msi_desc *desc)
 {
 	arg->desc = desc;
 	arg->hwirq = pci_msi_domain_calc_hwirq(desc);
 }
-#else
-#define pci_msi_domain_set_desc		NULL
-#endif
 
 static struct msi_domain_ops pci_msi_domain_ops_default = {
 	.set_desc	= pci_msi_domain_set_desc,
diff --git a/include/linux/msi.h b/include/linux/msi.h
index d360cc7c4f94..5aa126b7820b 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -369,7 +369,6 @@ void pci_msi_domain_write_msg(struct irq_data *irq_data, struct msi_msg *msg);
 struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode,
 					     struct msi_domain_info *info,
 					     struct irq_domain *parent);
-irq_hw_number_t pci_msi_domain_calc_hwirq(struct msi_desc *desc);
 int pci_msi_domain_check_cap(struct irq_domain *domain,
 			     struct msi_domain_info *info, struct device *dev);
 u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev);
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index eb95f6106a1e..640668e3f870 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -187,7 +187,6 @@ static const struct irq_domain_ops msi_domain_ops = {
 	.deactivate	= msi_domain_deactivate,
 };
 
-#ifdef GENERIC_MSI_DOMAIN_OPS
 static irq_hw_number_t msi_domain_ops_get_hwirq(struct msi_domain_info *info,
 						msi_alloc_info_t *arg)
 {
@@ -206,11 +205,6 @@ static void msi_domain_ops_set_desc(msi_alloc_info_t *arg,
 {
 	arg->desc = desc;
 }
-#else
-#define msi_domain_ops_get_hwirq	NULL
-#define msi_domain_ops_prepare		NULL
-#define msi_domain_ops_set_desc		NULL
-#endif /* !GENERIC_MSI_DOMAIN_OPS */
 
 static int msi_domain_ops_init(struct irq_domain *domain,
 			       struct msi_domain_info *info,
-- 
cgit v1.2.3


From c6c9e2838c5f0b94773511586123bcb125757f2a Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 26 Aug 2020 13:16:51 +0200
Subject: irqdomain/msi: Provide DOMAIN_BUS_VMD_MSI

PCI devices behind a VMD bus are not subject to interrupt remapping, but
the irq domain for VMD MSI cannot be distinguished from a regular PCI/MSI
irq domain.

Add a new domain bus token and allow it in the bus token check in
msi_check_reservation_mode() to keep the functionality the same once VMD
uses this token.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Marc Zyngier <maz@kernel.org>
Acked-by: Jon Derrick <jonathan.derrick@intel.com>
Link: https://lore.kernel.org/r/20200826112332.954409970@linutronix.de
---
 include/linux/irqdomain.h | 1 +
 kernel/irq/msi.c          | 7 ++++++-
 2 files changed, 7 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index b37350c4fe37..44445d9de881 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -84,6 +84,7 @@ enum irq_domain_bus_token {
 	DOMAIN_BUS_FSL_MC_MSI,
 	DOMAIN_BUS_TI_SCI_INTA_MSI,
 	DOMAIN_BUS_WAKEUP,
+	DOMAIN_BUS_VMD_MSI,
 };
 
 /**
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 640668e3f870..616b9583cfbb 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -364,8 +364,13 @@ static bool msi_check_reservation_mode(struct irq_domain *domain,
 {
 	struct msi_desc *desc;
 
-	if (domain->bus_token != DOMAIN_BUS_PCI_MSI)
+	switch(domain->bus_token) {
+	case DOMAIN_BUS_PCI_MSI:
+	case DOMAIN_BUS_VMD_MSI:
+		break;
+	default:
 		return false;
+	}
 
 	if (!(info->flags & MSI_FLAG_MUST_REACTIVATE))
 		return false;
-- 
cgit v1.2.3


From 2fd602669ee6d749a7dc47b84b87cef1a5075999 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 26 Aug 2020 13:16:53 +0200
Subject: PCI/MSI: Provide pci_dev_has_special_msi_domain() helper

Provide a helper function to check whether a PCI device is handled by a
non-standard PCI/MSI domain. This will be used to exclude such devices
which hang of a special bus, e.g. VMD, to be excluded from the irq domain
override in irq remapping.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://lore.kernel.org/r/20200826112333.139387358@linutronix.de
---
 drivers/pci/msi.c   | 22 ++++++++++++++++++++++
 include/linux/msi.h |  1 +
 2 files changed, 23 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 744a1a4d2b32..a2f00d181016 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -1553,4 +1553,26 @@ struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev)
 					     DOMAIN_BUS_PCI_MSI);
 	return dom;
 }
+
+/**
+ * pci_dev_has_special_msi_domain - Check whether the device is handled by
+ *				    a non-standard PCI-MSI domain
+ * @pdev:	The PCI device to check.
+ *
+ * Returns: True if the device irqdomain or the bus irqdomain is
+ * non-standard PCI/MSI.
+ */
+bool pci_dev_has_special_msi_domain(struct pci_dev *pdev)
+{
+	struct irq_domain *dom = dev_get_msi_domain(&pdev->dev);
+
+	if (!dom)
+		dom = dev_get_msi_domain(&pdev->bus->dev);
+
+	if (!dom)
+		return true;
+
+	return dom->bus_token != DOMAIN_BUS_PCI_MSI;
+}
+
 #endif /* CONFIG_PCI_MSI_IRQ_DOMAIN */
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 5aa126b7820b..a65cc47d0610 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -373,6 +373,7 @@ int pci_msi_domain_check_cap(struct irq_domain *domain,
 			     struct msi_domain_info *info, struct device *dev);
 u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev);
 struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev);
+bool pci_dev_has_special_msi_domain(struct pci_dev *pdev);
 #else
 static inline struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev)
 {
-- 
cgit v1.2.3


From 43e9e705dd57c466c4bfe32ab8c17db537b89297 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 26 Aug 2020 13:16:57 +0200
Subject: irqdomain/msi: Allow to override msi_domain_alloc/free_irqs()

To support MSI irq domains which do not fit at all into the regular MSI
irqdomain scheme, like the XEN MSI interrupt management for PV/HVM/DOM0,
it's necessary to allow to override the alloc/free implementation.

This is a preperatory step to switch X86 away from arch_*_msi_irqs() and
store the irq domain pointer right in struct device.

No functional change for existing MSI irq domain users.

Aside of the evil XEN wrapper this is also useful for special MSI domains
which need to do extra alloc/free work before/after calling the generic
core function. Work like allocating/freeing MSI descriptors, MSI storage
space etc.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200826112333.526797548@linutronix.de
---
 include/linux/msi.h | 27 +++++++++++++++++++++
 kernel/irq/msi.c    | 70 ++++++++++++++++++++++++++++++++++++-----------------
 2 files changed, 75 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/msi.h b/include/linux/msi.h
index a65cc47d0610..0180534b5428 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -241,6 +241,10 @@ struct msi_domain_info;
  * @msi_finish:		Optional callback to finalize the allocation
  * @set_desc:		Set the msi descriptor for an interrupt
  * @handle_error:	Optional error handler if the allocation fails
+ * @domain_alloc_irqs:	Optional function to override the default allocation
+ *			function.
+ * @domain_free_irqs:	Optional function to override the default free
+ *			function.
  *
  * @get_hwirq, @msi_init and @msi_free are callbacks used by
  * msi_create_irq_domain() and related interfaces
@@ -248,6 +252,22 @@ struct msi_domain_info;
  * @msi_check, @msi_prepare, @msi_finish, @set_desc and @handle_error
  * are callbacks used by msi_domain_alloc_irqs() and related
  * interfaces which are based on msi_desc.
+ *
+ * @domain_alloc_irqs, @domain_free_irqs can be used to override the
+ * default allocation/free functions (__msi_domain_alloc/free_irqs). This
+ * is initially for a wrapper around XENs seperate MSI universe which can't
+ * be wrapped into the regular irq domains concepts by mere mortals.  This
+ * allows to universally use msi_domain_alloc/free_irqs without having to
+ * special case XEN all over the place.
+ *
+ * Contrary to other operations @domain_alloc_irqs and @domain_free_irqs
+ * are set to the default implementation if NULL and even when
+ * MSI_FLAG_USE_DEF_DOM_OPS is not set to avoid breaking existing users and
+ * because these callbacks are obviously mandatory.
+ *
+ * This is NOT meant to be abused, but it can be useful to build wrappers
+ * for specialized MSI irq domains which need extra work before and after
+ * calling __msi_domain_alloc_irqs()/__msi_domain_free_irqs().
  */
 struct msi_domain_ops {
 	irq_hw_number_t	(*get_hwirq)(struct msi_domain_info *info,
@@ -270,6 +290,10 @@ struct msi_domain_ops {
 				    struct msi_desc *desc);
 	int		(*handle_error)(struct irq_domain *domain,
 					struct msi_desc *desc, int error);
+	int		(*domain_alloc_irqs)(struct irq_domain *domain,
+					     struct device *dev, int nvec);
+	void		(*domain_free_irqs)(struct irq_domain *domain,
+					    struct device *dev);
 };
 
 /**
@@ -327,8 +351,11 @@ int msi_domain_set_affinity(struct irq_data *data, const struct cpumask *mask,
 struct irq_domain *msi_create_irq_domain(struct fwnode_handle *fwnode,
 					 struct msi_domain_info *info,
 					 struct irq_domain *parent);
+int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
+			    int nvec);
 int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
 			  int nvec);
+void __msi_domain_free_irqs(struct irq_domain *domain, struct device *dev);
 void msi_domain_free_irqs(struct irq_domain *domain, struct device *dev);
 struct msi_domain_info *msi_get_domain_info(struct irq_domain *domain);
 
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 616b9583cfbb..2c0c4d6d0f83 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -229,11 +229,13 @@ static int msi_domain_ops_check(struct irq_domain *domain,
 }
 
 static struct msi_domain_ops msi_domain_ops_default = {
-	.get_hwirq	= msi_domain_ops_get_hwirq,
-	.msi_init	= msi_domain_ops_init,
-	.msi_check	= msi_domain_ops_check,
-	.msi_prepare	= msi_domain_ops_prepare,
-	.set_desc	= msi_domain_ops_set_desc,
+	.get_hwirq		= msi_domain_ops_get_hwirq,
+	.msi_init		= msi_domain_ops_init,
+	.msi_check		= msi_domain_ops_check,
+	.msi_prepare		= msi_domain_ops_prepare,
+	.set_desc		= msi_domain_ops_set_desc,
+	.domain_alloc_irqs	= __msi_domain_alloc_irqs,
+	.domain_free_irqs	= __msi_domain_free_irqs,
 };
 
 static void msi_domain_update_dom_ops(struct msi_domain_info *info)
@@ -245,6 +247,14 @@ static void msi_domain_update_dom_ops(struct msi_domain_info *info)
 		return;
 	}
 
+	if (ops->domain_alloc_irqs == NULL)
+		ops->domain_alloc_irqs = msi_domain_ops_default.domain_alloc_irqs;
+	if (ops->domain_free_irqs == NULL)
+		ops->domain_free_irqs = msi_domain_ops_default.domain_free_irqs;
+
+	if (!(info->flags & MSI_FLAG_USE_DEF_DOM_OPS))
+		return;
+
 	if (ops->get_hwirq == NULL)
 		ops->get_hwirq = msi_domain_ops_default.get_hwirq;
 	if (ops->msi_init == NULL)
@@ -278,8 +288,7 @@ struct irq_domain *msi_create_irq_domain(struct fwnode_handle *fwnode,
 {
 	struct irq_domain *domain;
 
-	if (info->flags & MSI_FLAG_USE_DEF_DOM_OPS)
-		msi_domain_update_dom_ops(info);
+	msi_domain_update_dom_ops(info);
 	if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS)
 		msi_domain_update_chip_ops(info);
 
@@ -386,17 +395,8 @@ static bool msi_check_reservation_mode(struct irq_domain *domain,
 	return desc->msi_attrib.is_msix || desc->msi_attrib.maskbit;
 }
 
-/**
- * msi_domain_alloc_irqs - Allocate interrupts from a MSI interrupt domain
- * @domain:	The domain to allocate from
- * @dev:	Pointer to device struct of the device for which the interrupts
- *		are allocated
- * @nvec:	The number of interrupts to allocate
- *
- * Returns 0 on success or an error code.
- */
-int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
-			  int nvec)
+int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
+			    int nvec)
 {
 	struct msi_domain_info *info = domain->host_data;
 	struct msi_domain_ops *ops = info->ops;
@@ -490,12 +490,24 @@ cleanup:
 }
 
 /**
- * msi_domain_free_irqs - Free interrupts from a MSI interrupt @domain associated tp @dev
- * @domain:	The domain to managing the interrupts
+ * msi_domain_alloc_irqs - Allocate interrupts from a MSI interrupt domain
+ * @domain:	The domain to allocate from
  * @dev:	Pointer to device struct of the device for which the interrupts
- *		are free
+ *		are allocated
+ * @nvec:	The number of interrupts to allocate
+ *
+ * Returns 0 on success or an error code.
  */
-void msi_domain_free_irqs(struct irq_domain *domain, struct device *dev)
+int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
+			  int nvec)
+{
+	struct msi_domain_info *info = domain->host_data;
+	struct msi_domain_ops *ops = info->ops;
+
+	return ops->domain_alloc_irqs(domain, dev, nvec);
+}
+
+void __msi_domain_free_irqs(struct irq_domain *domain, struct device *dev)
 {
 	struct msi_desc *desc;
 
@@ -512,6 +524,20 @@ void msi_domain_free_irqs(struct irq_domain *domain, struct device *dev)
 	}
 }
 
+/**
+ * __msi_domain_free_irqs - Free interrupts from a MSI interrupt @domain associated tp @dev
+ * @domain:	The domain to managing the interrupts
+ * @dev:	Pointer to device struct of the device for which the interrupts
+ *		are free
+ */
+void msi_domain_free_irqs(struct irq_domain *domain, struct device *dev)
+{
+	struct msi_domain_info *info = domain->host_data;
+	struct msi_domain_ops *ops = info->ops;
+
+	return ops->domain_free_irqs(domain, dev);
+}
+
 /**
  * msi_get_domain_info - Get the MSI interrupt domain info for @domain
  * @domain:	The interrupt domain to retrieve data from
-- 
cgit v1.2.3


From 85a8dfc57a0b96785881735e09a61a0fde911ca4 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 26 Aug 2020 13:16:59 +0200
Subject: iommm/vt-d: Store irq domain in struct device

As a first step to make X86 utilize the direct MSI irq domain operations
store the irq domain pointer in the device struct when a device is probed.

This is done from dmar_pci_bus_add_dev() because it has to work even when
DMA remapping is disabled. It only overrides the irqdomain of devices which
are handled by a regular PCI/MSI irq domain which protects PCI devices
behind special busses like VMD which have their own irq domain.

No functional change. It just avoids the redirection through
arch_*_msi_irqs() and allows the PCI/MSI core to directly invoke the irq
domain alloc/free functions instead of having to look up the irq domain for
every single MSI interupt.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Joerg Roedel <jroedel@suse.de>
Link: https://lore.kernel.org/r/20200826112333.714566121@linutronix.de
---
 drivers/iommu/intel/dmar.c          |  3 +++
 drivers/iommu/intel/irq_remapping.c | 16 ++++++++++++++++
 include/linux/intel-iommu.h         |  7 +++++++
 3 files changed, 26 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
index 93e6345f3414..4dc09edef744 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -316,6 +316,9 @@ static int dmar_pci_bus_add_dev(struct dmar_pci_notify_info *info)
 	if (ret < 0 && dmar_dev_scope_status == 0)
 		dmar_dev_scope_status = ret;
 
+	if (ret >= 0)
+		intel_irq_remap_add_device(info);
+
 	return ret;
 }
 
diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c
index d9db2f37b831..68692a4188db 100644
--- a/drivers/iommu/intel/irq_remapping.c
+++ b/drivers/iommu/intel/irq_remapping.c
@@ -1092,6 +1092,22 @@ error:
 	return -1;
 }
 
+/*
+ * Store the MSI remapping domain pointer in the device if enabled.
+ *
+ * This is called from dmar_pci_bus_add_dev() so it works even when DMA
+ * remapping is disabled. Only update the pointer if the device is not
+ * already handled by a non default PCI/MSI interrupt domain. This protects
+ * e.g. VMD devices.
+ */
+void intel_irq_remap_add_device(struct dmar_pci_notify_info *info)
+{
+	if (!irq_remapping_enabled || pci_dev_has_special_msi_domain(info->dev))
+		return;
+
+	dev_set_msi_domain(&info->dev->dev, map_dev_to_ir(info->dev));
+}
+
 static void prepare_irte(struct irte *irte, int vector, unsigned int dest)
 {
 	memset(irte, 0, sizeof(*irte));
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index b1ed2f25f7c0..46f5aaaa66ff 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -425,6 +425,8 @@ struct q_inval {
 	int             free_cnt;
 };
 
+struct dmar_pci_notify_info;
+
 #ifdef CONFIG_IRQ_REMAP
 /* 1MB - maximum possible interrupt remapping table size */
 #define INTR_REMAP_PAGE_ORDER	8
@@ -439,6 +441,11 @@ struct ir_table {
 	struct irte *base;
 	unsigned long *bitmap;
 };
+
+void intel_irq_remap_add_device(struct dmar_pci_notify_info *info);
+#else
+static inline void
+intel_irq_remap_add_device(struct dmar_pci_notify_info *info) { }
 #endif
 
 struct iommu_flush {
-- 
cgit v1.2.3


From 077ee78e392869e46ae6bdc6ba2a3c4249d0b5e1 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 26 Aug 2020 13:17:02 +0200
Subject: PCI/MSI: Make arch_.*_msi_irq[s] fallbacks selectable

The arch_.*_msi_irq[s] fallbacks are compiled in whether an architecture
requires them or not. Architectures which are fully utilizing hierarchical
irq domains should never call into that code.

It's not only architectures which depend on that by implementing one or
more of the weak functions, there is also a bunch of drivers which relies
on the weak functions which invoke msi_controller::setup_irq[s] and
msi_controller::teardown_irq.

Make the architectures and drivers which rely on them select them in Kconfig
and if not selected replace them by stub functions which emit a warning and
fail the PCI/MSI interrupt allocation.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20200826112333.992429909@linutronix.de
---
 arch/ia64/Kconfig              |  1 +
 arch/mips/Kconfig              |  1 +
 arch/powerpc/Kconfig           |  1 +
 arch/s390/Kconfig              |  1 +
 arch/sparc/Kconfig             |  1 +
 arch/x86/Kconfig               |  1 +
 drivers/pci/Kconfig            |  3 +++
 drivers/pci/controller/Kconfig |  3 +++
 drivers/pci/msi.c              |  3 ++-
 include/linux/msi.h            | 31 ++++++++++++++++++++++++++-----
 10 files changed, 40 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 5b4ec80bf586..7ff5b3bbf160 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -56,6 +56,7 @@ config IA64
 	select NEED_DMA_MAP_STATE
 	select NEED_SG_DMA_LENGTH
 	select NUMA if !FLATMEM
+	select PCI_MSI_ARCH_FALLBACKS
 	default y
 	help
 	  The Itanium Processor Family is Intel's 64-bit successor to
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index c95fa3a2484c..3690582eb61f 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -86,6 +86,7 @@ config MIPS
 	select MODULES_USE_ELF_REL if MODULES
 	select MODULES_USE_ELF_RELA if MODULES && 64BIT
 	select PERF_USE_VMALLOC
+	select PCI_MSI_ARCH_FALLBACKS
 	select RTC_LIB
 	select SYSCTL_EXCEPTION_TRACE
 	select VIRT_TO_BUS
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 65bed1fdeaad..9e66ca1376af 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -246,6 +246,7 @@ config PPC
 	select OLD_SIGACTION			if PPC32
 	select OLD_SIGSUSPEND
 	select PCI_DOMAINS			if PCI
+	select PCI_MSI_ARCH_FALLBACKS
 	select PCI_SYSCALL			if PCI
 	select PPC_DAWR				if PPC64
 	select RTC_LIB
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index b29fcc66ec39..63dd5a0aa252 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -185,6 +185,7 @@ config S390
 	select OLD_SIGSUSPEND3
 	select PCI_DOMAINS		if PCI
 	select PCI_MSI			if PCI
+	select PCI_MSI_ARCH_FALLBACKS
 	select SPARSE_IRQ
 	select SYSCTL_EXCEPTION_TRACE
 	select THREAD_INFO_IN_TASK
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index efeff2c896a5..21a3239870c0 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -43,6 +43,7 @@ config SPARC
 	select GENERIC_STRNLEN_USER
 	select MODULES_USE_ELF_RELA
 	select PCI_SYSCALL if PCI
+	select PCI_MSI_ARCH_FALLBACKS
 	select ODD_RT_SIGACTION
 	select OLD_SIGSUSPEND
 	select CPU_NO_EFFICIENT_FFS
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 7101ac64bb20..196e0688ec3c 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -225,6 +225,7 @@ config X86
 	select NEED_SG_DMA_LENGTH
 	select PCI_DOMAINS			if PCI
 	select PCI_LOCKLESS_CONFIG		if PCI
+	select PCI_MSI_ARCH_FALLBACKS
 	select PERF_EVENTS
 	select RTC_LIB
 	select RTC_MC146818_LIB
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index 4bef5c2bae9f..438a792d2cf7 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -56,6 +56,9 @@ config PCI_MSI_IRQ_DOMAIN
 	depends on PCI_MSI
 	select GENERIC_MSI_IRQ_DOMAIN
 
+config PCI_MSI_ARCH_FALLBACKS
+	bool
+
 config PCI_QUIRKS
 	default y
 	bool "Enable PCI quirk workarounds" if EXPERT
diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig
index f18c3725ef80..4a7afbe189f8 100644
--- a/drivers/pci/controller/Kconfig
+++ b/drivers/pci/controller/Kconfig
@@ -41,6 +41,7 @@ config PCI_TEGRA
 	bool "NVIDIA Tegra PCIe controller"
 	depends on ARCH_TEGRA || COMPILE_TEST
 	depends on PCI_MSI_IRQ_DOMAIN
+	select PCI_MSI_ARCH_FALLBACKS
 	help
 	  Say Y here if you want support for the PCIe host controller found
 	  on NVIDIA Tegra SoCs.
@@ -67,6 +68,7 @@ config PCIE_RCAR_HOST
 	bool "Renesas R-Car PCIe host controller"
 	depends on ARCH_RENESAS || COMPILE_TEST
 	depends on PCI_MSI_IRQ_DOMAIN
+	select PCI_MSI_ARCH_FALLBACKS
 	help
 	  Say Y here if you want PCIe controller support on R-Car SoCs in host
 	  mode.
@@ -95,6 +97,7 @@ config PCI_HOST_GENERIC
 config PCIE_XILINX
 	bool "Xilinx AXI PCIe host bridge support"
 	depends on OF || COMPILE_TEST
+	select PCI_MSI_ARCH_FALLBACKS
 	help
 	  Say 'Y' here if you want kernel to support the Xilinx AXI PCIe
 	  Host Bridge driver.
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index a2f00d181016..d52d118979a6 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -58,8 +58,8 @@ static void pci_msi_teardown_msi_irqs(struct pci_dev *dev)
 #define pci_msi_teardown_msi_irqs	arch_teardown_msi_irqs
 #endif
 
+#ifdef CONFIG_PCI_MSI_ARCH_FALLBACKS
 /* Arch hooks */
-
 int __weak arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc)
 {
 	struct msi_controller *chip = dev->bus->msi;
@@ -132,6 +132,7 @@ void __weak arch_teardown_msi_irqs(struct pci_dev *dev)
 {
 	return default_teardown_msi_irqs(dev);
 }
+#endif /* CONFIG_PCI_MSI_ARCH_FALLBACKS */
 
 static void default_restore_msi_irq(struct pci_dev *dev, int irq)
 {
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 0180534b5428..6b584cc4757c 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -193,17 +193,38 @@ void pci_msi_mask_irq(struct irq_data *data);
 void pci_msi_unmask_irq(struct irq_data *data);
 
 /*
- * The arch hooks to setup up msi irqs. Those functions are
- * implemented as weak symbols so that they /can/ be overriden by
- * architecture specific code if needed.
+ * The arch hooks to setup up msi irqs. Default functions are implemented
+ * as weak symbols so that they /can/ be overriden by architecture specific
+ * code if needed. These hooks must be enabled by the architecture or by
+ * drivers which depend on them via msi_controller based MSI handling.
+ *
+ * If CONFIG_PCI_MSI_ARCH_FALLBACKS is not selected they are replaced by
+ * stubs with warnings.
  */
+#ifdef CONFIG_PCI_MSI_ARCH_FALLBACKS
 int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc);
 void arch_teardown_msi_irq(unsigned int irq);
 int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type);
 void arch_teardown_msi_irqs(struct pci_dev *dev);
-void arch_restore_msi_irqs(struct pci_dev *dev);
-
 void default_teardown_msi_irqs(struct pci_dev *dev);
+#else
+static inline int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+	WARN_ON_ONCE(1);
+	return -ENODEV;
+}
+
+static inline void arch_teardown_msi_irqs(struct pci_dev *dev)
+{
+	WARN_ON_ONCE(1);
+}
+#endif
+
+/*
+ * The restore hooks are still available as they are useful even
+ * for fully irq domain based setups. Courtesy to XEN/X86.
+ */
+void arch_restore_msi_irqs(struct pci_dev *dev);
 void default_restore_msi_irqs(struct pci_dev *dev);
 
 struct msi_controller {
-- 
cgit v1.2.3


From 58c909022a5a56cd1d9e89c8c5461fd1f6a27bb5 Mon Sep 17 00:00:00 2001
From: Lenny Szubowicz <lszubowi@redhat.com>
Date: Fri, 4 Sep 2020 21:31:05 -0400
Subject: efi: Support for MOK variable config table

Because of system-specific EFI firmware limitations, EFI volatile
variables may not be capable of holding the required contents of
the Machine Owner Key (MOK) certificate store when the certificate
list grows above some size. Therefore, an EFI boot loader may pass
the MOK certs via a EFI configuration table created specifically for
this purpose to avoid this firmware limitation.

An EFI configuration table is a much more primitive mechanism
compared to EFI variables and is well suited for one-way passage
of static information from a pre-OS environment to the kernel.

This patch adds initial kernel support to recognize, parse,
and validate the EFI MOK configuration table, where named
entries contain the same data that would otherwise be provided
in similarly named EFI variables.

Additionally, this patch creates a sysfs binary file for each
EFI MOK configuration table entry found. These files are read-only
to root and are provided for use by user space utilities such as
mokutil.

A subsequent patch will load MOK certs into the trusted platform
key ring using this infrastructure.

Signed-off-by: Lenny Szubowicz <lszubowi@redhat.com>
Link: https://lore.kernel.org/r/20200905013107.10457-2-lszubowi@redhat.com
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 arch/x86/kernel/setup.c             |   1 +
 arch/x86/platform/efi/efi.c         |   3 +
 drivers/firmware/efi/Makefile       |   1 +
 drivers/firmware/efi/efi-init.c     |   1 +
 drivers/firmware/efi/efi.c          |   6 +
 drivers/firmware/efi/mokvar-table.c | 360 ++++++++++++++++++++++++++++++++++++
 include/linux/efi.h                 |  34 ++++
 7 files changed, 406 insertions(+)
 create mode 100644 drivers/firmware/efi/mokvar-table.c

(limited to 'include/linux')

diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 3511736fbc74..d41be0df72f8 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1077,6 +1077,7 @@ void __init setup_arch(char **cmdline_p)
 	efi_fake_memmap();
 	efi_find_mirror();
 	efi_esrt_init();
+	efi_mokvar_table_init();
 
 	/*
 	 * The EFI specification says that boot service code won't be
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index f6ea8f1a9d57..6961bedc6503 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -91,6 +91,9 @@ static const unsigned long * const efi_tables[] = {
 	&efi.tpm_log,
 	&efi.tpm_final_log,
 	&efi_rng_seed,
+#ifdef CONFIG_LOAD_UEFI_KEYS
+	&efi.mokvar_table,
+#endif
 };
 
 u64 efi_setup;		/* efi setup_data physical address */
diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile
index 61fd1e8b26fb..e8da782280b6 100644
--- a/drivers/firmware/efi/Makefile
+++ b/drivers/firmware/efi/Makefile
@@ -28,6 +28,7 @@ obj-$(CONFIG_EFI_DEV_PATH_PARSER)	+= dev-path-parser.o
 obj-$(CONFIG_APPLE_PROPERTIES)		+= apple-properties.o
 obj-$(CONFIG_EFI_RCI2_TABLE)		+= rci2-table.o
 obj-$(CONFIG_EFI_EMBEDDED_FIRMWARE)	+= embedded-firmware.o
+obj-$(CONFIG_LOAD_UEFI_KEYS)		+= mokvar-table.o
 
 fake_map-y				+= fake_mem.o
 fake_map-$(CONFIG_X86)			+= x86_fake_mem.o
diff --git a/drivers/firmware/efi/efi-init.c b/drivers/firmware/efi/efi-init.c
index 71c445d20258..f55a92ff12c0 100644
--- a/drivers/firmware/efi/efi-init.c
+++ b/drivers/firmware/efi/efi-init.c
@@ -236,6 +236,7 @@ void __init efi_init(void)
 
 	reserve_regions();
 	efi_esrt_init();
+	efi_mokvar_table_init();
 
 	memblock_reserve(data.phys_map & PAGE_MASK,
 			 PAGE_ALIGN(data.size + (data.phys_map & ~PAGE_MASK)));
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index fdd1db025dbf..820f5b1dfba3 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -43,6 +43,9 @@ struct efi __read_mostly efi = {
 	.esrt			= EFI_INVALID_TABLE_ADDR,
 	.tpm_log		= EFI_INVALID_TABLE_ADDR,
 	.tpm_final_log		= EFI_INVALID_TABLE_ADDR,
+#ifdef CONFIG_LOAD_UEFI_KEYS
+	.mokvar_table		= EFI_INVALID_TABLE_ADDR,
+#endif
 };
 EXPORT_SYMBOL(efi);
 
@@ -516,6 +519,9 @@ static const efi_config_table_type_t common_tables[] __initconst = {
 	{EFI_RT_PROPERTIES_TABLE_GUID,		&rt_prop,		"RTPROP"	},
 #ifdef CONFIG_EFI_RCI2_TABLE
 	{DELLEMC_EFI_RCI2_TABLE_GUID,		&rci2_table_phys			},
+#endif
+#ifdef CONFIG_LOAD_UEFI_KEYS
+	{LINUX_EFI_MOK_VARIABLE_TABLE_GUID,	&efi.mokvar_table,	"MOKvar"	},
 #endif
 	{},
 };
diff --git a/drivers/firmware/efi/mokvar-table.c b/drivers/firmware/efi/mokvar-table.c
new file mode 100644
index 000000000000..b1cd49893d4d
--- /dev/null
+++ b/drivers/firmware/efi/mokvar-table.c
@@ -0,0 +1,360 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * mokvar-table.c
+ *
+ * Copyright (c) 2020 Red Hat
+ * Author: Lenny Szubowicz <lszubowi@redhat.com>
+ *
+ * This module contains the kernel support for the Linux EFI Machine
+ * Owner Key (MOK) variable configuration table, which is identified by
+ * the LINUX_EFI_MOK_VARIABLE_TABLE_GUID.
+ *
+ * This EFI configuration table provides a more robust alternative to
+ * EFI volatile variables by which an EFI boot loader can pass the
+ * contents of the Machine Owner Key (MOK) certificate stores to the
+ * kernel during boot. If both the EFI MOK config table and corresponding
+ * EFI MOK variables are present, the table should be considered as
+ * more authoritative.
+ *
+ * This module includes code that validates and maps the EFI MOK table,
+ * if it's presence was detected very early in boot.
+ *
+ * Kernel interface routines are provided to walk through all the
+ * entries in the MOK config table or to search for a specific named
+ * entry.
+ *
+ * The contents of the individual named MOK config table entries are
+ * made available to user space via read-only sysfs binary files under:
+ *
+ * /sys/firmware/efi/mok-variables/
+ *
+ */
+#define pr_fmt(fmt) "mokvar: " fmt
+
+#include <linux/capability.h>
+#include <linux/efi.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/kobject.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+
+/*
+ * The LINUX_EFI_MOK_VARIABLE_TABLE_GUID config table is a packed
+ * sequence of struct efi_mokvar_table_entry, one for each named
+ * MOK variable. The sequence is terminated by an entry with a
+ * completely NULL name and 0 data size.
+ *
+ * efi_mokvar_table_size is set to the computed size of the
+ * MOK config table by efi_mokvar_table_init(). This will be
+ * non-zero if and only if the table if present and has been
+ * validated by efi_mokvar_table_init().
+ */
+static size_t efi_mokvar_table_size;
+
+/*
+ * efi_mokvar_table_va is the kernel virtual address at which the
+ * EFI MOK config table has been mapped by efi_mokvar_sysfs_init().
+ */
+static struct efi_mokvar_table_entry *efi_mokvar_table_va;
+
+/*
+ * Each /sys/firmware/efi/mok-variables/ sysfs file is represented by
+ * an instance of struct efi_mokvar_sysfs_attr on efi_mokvar_sysfs_list.
+ * bin_attr.private points to the associated EFI MOK config table entry.
+ *
+ * This list is created during boot and then remains unchanged.
+ * So no synchronization is currently required to walk the list.
+ */
+struct efi_mokvar_sysfs_attr {
+	struct bin_attribute bin_attr;
+	struct list_head node;
+};
+
+static LIST_HEAD(efi_mokvar_sysfs_list);
+static struct kobject *mokvar_kobj;
+
+/*
+ * efi_mokvar_table_init() - Early boot validation of EFI MOK config table
+ *
+ * If present, validate and compute the size of the EFI MOK variable
+ * configuration table. This table may be provided by an EFI boot loader
+ * as an alternative to ordinary EFI variables, due to platform-dependent
+ * limitations. The memory occupied by this table is marked as reserved.
+ *
+ * This routine must be called before efi_free_boot_services() in order
+ * to guarantee that it can mark the table as reserved.
+ *
+ * Implicit inputs:
+ * efi.mokvar_table:	Physical address of EFI MOK variable config table
+ *			or special value that indicates no such table.
+ *
+ * Implicit outputs:
+ * efi_mokvar_table_size: Computed size of EFI MOK variable config table.
+ *			The table is considered present and valid if this
+ *			is non-zero.
+ */
+void __init efi_mokvar_table_init(void)
+{
+	efi_memory_desc_t md;
+	u64 end_pa;
+	void *va = NULL;
+	size_t cur_offset = 0;
+	size_t offset_limit;
+	size_t map_size = 0;
+	size_t map_size_needed = 0;
+	size_t size;
+	struct efi_mokvar_table_entry *mokvar_entry;
+	int err = -EINVAL;
+
+	if (!efi_enabled(EFI_MEMMAP))
+		return;
+
+	if (efi.mokvar_table == EFI_INVALID_TABLE_ADDR)
+		return;
+	/*
+	 * The EFI MOK config table must fit within a single EFI memory
+	 * descriptor range.
+	 */
+	err = efi_mem_desc_lookup(efi.mokvar_table, &md);
+	if (err) {
+		pr_warn("EFI MOKvar config table is not within the EFI memory map\n");
+		return;
+	}
+	end_pa = efi_mem_desc_end(&md);
+	if (efi.mokvar_table >= end_pa) {
+		pr_err("EFI memory descriptor containing MOKvar config table is invalid\n");
+		return;
+	}
+	offset_limit = end_pa - efi.mokvar_table;
+	/*
+	 * Validate the MOK config table. Since there is no table header
+	 * from which we could get the total size of the MOK config table,
+	 * we compute the total size as we validate each variably sized
+	 * entry, remapping as necessary.
+	 */
+	while (cur_offset + sizeof(*mokvar_entry) <= offset_limit) {
+		mokvar_entry = va + cur_offset;
+		map_size_needed = cur_offset + sizeof(*mokvar_entry);
+		if (map_size_needed > map_size) {
+			if (va)
+				early_memunmap(va, map_size);
+			/*
+			 * Map a little more than the fixed size entry
+			 * header, anticipating some data. It's safe to
+			 * do so as long as we stay within current memory
+			 * descriptor.
+			 */
+			map_size = min(map_size_needed + 2*EFI_PAGE_SIZE,
+				       offset_limit);
+			va = early_memremap(efi.mokvar_table, map_size);
+			if (!va) {
+				pr_err("Failed to map EFI MOKvar config table pa=0x%lx, size=%zu.\n",
+				       efi.mokvar_table, map_size);
+				return;
+			}
+			mokvar_entry = va + cur_offset;
+		}
+
+		/* Check for last sentinel entry */
+		if (mokvar_entry->name[0] == '\0') {
+			if (mokvar_entry->data_size != 0)
+				break;
+			err = 0;
+			break;
+		}
+
+		/* Sanity check that the name is null terminated */
+		size = strnlen(mokvar_entry->name,
+			       sizeof(mokvar_entry->name));
+		if (size >= sizeof(mokvar_entry->name))
+			break;
+
+		/* Advance to the next entry */
+		cur_offset = map_size_needed + mokvar_entry->data_size;
+	}
+
+	if (va)
+		early_memunmap(va, map_size);
+	if (err) {
+		pr_err("EFI MOKvar config table is not valid\n");
+		return;
+	}
+	efi_mem_reserve(efi.mokvar_table, map_size_needed);
+	efi_mokvar_table_size = map_size_needed;
+}
+
+/*
+ * efi_mokvar_entry_next() - Get next entry in the EFI MOK config table
+ *
+ * mokvar_entry:	Pointer to current EFI MOK config table entry
+ *			or null. Null indicates get first entry.
+ *			Passed by reference. This is updated to the
+ *			same value as the return value.
+ *
+ * Returns:		Pointer to next EFI MOK config table entry
+ *			or null, if there are no more entries.
+ *			Same value is returned in the mokvar_entry
+ *			parameter.
+ *
+ * This routine depends on the EFI MOK config table being entirely
+ * mapped with it's starting virtual address in efi_mokvar_table_va.
+ */
+struct efi_mokvar_table_entry *efi_mokvar_entry_next(
+			struct efi_mokvar_table_entry **mokvar_entry)
+{
+	struct efi_mokvar_table_entry *mokvar_cur;
+	struct efi_mokvar_table_entry *mokvar_next;
+	size_t size_cur;
+
+	mokvar_cur = *mokvar_entry;
+	*mokvar_entry = NULL;
+
+	if (efi_mokvar_table_va == NULL)
+		return NULL;
+
+	if (mokvar_cur == NULL) {
+		mokvar_next = efi_mokvar_table_va;
+	} else {
+		if (mokvar_cur->name[0] == '\0')
+			return NULL;
+		size_cur = sizeof(*mokvar_cur) + mokvar_cur->data_size;
+		mokvar_next = (void *)mokvar_cur + size_cur;
+	}
+
+	if (mokvar_next->name[0] == '\0')
+		return NULL;
+
+	*mokvar_entry = mokvar_next;
+	return mokvar_next;
+}
+
+/*
+ * efi_mokvar_entry_find() - Find EFI MOK config entry by name
+ *
+ * name:	Name of the entry to look for.
+ *
+ * Returns:	Pointer to EFI MOK config table entry if found;
+ *		null otherwise.
+ *
+ * This routine depends on the EFI MOK config table being entirely
+ * mapped with it's starting virtual address in efi_mokvar_table_va.
+ */
+struct efi_mokvar_table_entry *efi_mokvar_entry_find(const char *name)
+{
+	struct efi_mokvar_table_entry *mokvar_entry = NULL;
+
+	while (efi_mokvar_entry_next(&mokvar_entry)) {
+		if (!strncmp(name, mokvar_entry->name,
+			     sizeof(mokvar_entry->name)))
+			return mokvar_entry;
+	}
+	return NULL;
+}
+
+/*
+ * efi_mokvar_sysfs_read() - sysfs binary file read routine
+ *
+ * Returns:	Count of bytes read.
+ *
+ * Copy EFI MOK config table entry data for this mokvar sysfs binary file
+ * to the supplied buffer, starting at the specified offset into mokvar table
+ * entry data, for the specified count bytes. The copy is limited by the
+ * amount of data in this mokvar config table entry.
+ */
+static ssize_t efi_mokvar_sysfs_read(struct file *file, struct kobject *kobj,
+				 struct bin_attribute *bin_attr, char *buf,
+				 loff_t off, size_t count)
+{
+	struct efi_mokvar_table_entry *mokvar_entry = bin_attr->private;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return 0;
+
+	if (off >= mokvar_entry->data_size)
+		return 0;
+	if (count >  mokvar_entry->data_size - off)
+		count = mokvar_entry->data_size - off;
+
+	memcpy(buf, mokvar_entry->data + off, count);
+	return count;
+}
+
+/*
+ * efi_mokvar_sysfs_init() - Map EFI MOK config table and create sysfs
+ *
+ * Map the EFI MOK variable config table for run-time use by the kernel
+ * and create the sysfs entries in /sys/firmware/efi/mok-variables/
+ *
+ * This routine just returns if a valid EFI MOK variable config table
+ * was not found earlier during boot.
+ *
+ * This routine must be called during a "middle" initcall phase, i.e.
+ * after efi_mokvar_table_init() but before UEFI certs are loaded
+ * during late init.
+ *
+ * Implicit inputs:
+ * efi.mokvar_table:	Physical address of EFI MOK variable config table
+ *			or special value that indicates no such table.
+ *
+ * efi_mokvar_table_size: Computed size of EFI MOK variable config table.
+ *			The table is considered present and valid if this
+ *			is non-zero.
+ *
+ * Implicit outputs:
+ * efi_mokvar_table_va:	Start virtual address of the EFI MOK config table.
+ */
+static int __init efi_mokvar_sysfs_init(void)
+{
+	void *config_va;
+	struct efi_mokvar_table_entry *mokvar_entry = NULL;
+	struct efi_mokvar_sysfs_attr *mokvar_sysfs = NULL;
+	int err = 0;
+
+	if (efi_mokvar_table_size == 0)
+		return -ENOENT;
+
+	config_va = memremap(efi.mokvar_table, efi_mokvar_table_size,
+			     MEMREMAP_WB);
+	if (!config_va) {
+		pr_err("Failed to map EFI MOKvar config table\n");
+		return -ENOMEM;
+	}
+	efi_mokvar_table_va = config_va;
+
+	mokvar_kobj = kobject_create_and_add("mok-variables", efi_kobj);
+	if (!mokvar_kobj) {
+		pr_err("Failed to create EFI mok-variables sysfs entry\n");
+		return -ENOMEM;
+	}
+
+	while (efi_mokvar_entry_next(&mokvar_entry)) {
+		mokvar_sysfs = kzalloc(sizeof(*mokvar_sysfs), GFP_KERNEL);
+		if (!mokvar_sysfs) {
+			err = -ENOMEM;
+			break;
+		}
+
+		sysfs_bin_attr_init(&mokvar_sysfs->bin_attr);
+		mokvar_sysfs->bin_attr.private = mokvar_entry;
+		mokvar_sysfs->bin_attr.attr.name = mokvar_entry->name;
+		mokvar_sysfs->bin_attr.attr.mode = 0400;
+		mokvar_sysfs->bin_attr.size = mokvar_entry->data_size;
+		mokvar_sysfs->bin_attr.read = efi_mokvar_sysfs_read;
+
+		err = sysfs_create_bin_file(mokvar_kobj,
+					   &mokvar_sysfs->bin_attr);
+		if (err)
+			break;
+
+		list_add_tail(&mokvar_sysfs->node, &efi_mokvar_sysfs_list);
+	}
+
+	if (err) {
+		pr_err("Failed to create some EFI mok-variables sysfs entries\n");
+		kfree(mokvar_sysfs);
+	}
+	return err;
+}
+device_initcall(efi_mokvar_sysfs_init);
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 73db1ae04cef..4a2332f146eb 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -357,6 +357,7 @@ void efi_native_runtime_setup(void);
 #define LINUX_EFI_TPM_FINAL_LOG_GUID		EFI_GUID(0x1e2ed096, 0x30e2, 0x4254,  0xbd, 0x89, 0x86, 0x3b, 0xbe, 0xf8, 0x23, 0x25)
 #define LINUX_EFI_MEMRESERVE_TABLE_GUID		EFI_GUID(0x888eb0c6, 0x8ede, 0x4ff5,  0xa8, 0xf0, 0x9a, 0xee, 0x5c, 0xb9, 0x77, 0xc2)
 #define LINUX_EFI_INITRD_MEDIA_GUID		EFI_GUID(0x5568e427, 0x68fc, 0x4f3d,  0xac, 0x74, 0xca, 0x55, 0x52, 0x31, 0xcc, 0x68)
+#define LINUX_EFI_MOK_VARIABLE_TABLE_GUID	EFI_GUID(0xc451ed2b, 0x9694, 0x45d3,  0xba, 0xba, 0xed, 0x9f, 0x89, 0x88, 0xa3, 0x89)
 
 /* OEM GUIDs */
 #define DELLEMC_EFI_RCI2_TABLE_GUID		EFI_GUID(0x2d9f28a2, 0xa886, 0x456a,  0x97, 0xa8, 0xf1, 0x1e, 0xf2, 0x4f, 0xf4, 0x55)
@@ -546,6 +547,7 @@ extern struct efi {
 	unsigned long			esrt;			/* ESRT table */
 	unsigned long			tpm_log;		/* TPM2 Event Log table */
 	unsigned long			tpm_final_log;		/* TPM2 Final Events Log table */
+	unsigned long			mokvar_table;		/* MOK variable config table */
 
 	efi_get_time_t			*get_time;
 	efi_set_time_t			*set_time;
@@ -1252,4 +1254,36 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size);
 
 char *efi_systab_show_arch(char *str);
 
+/*
+ * The LINUX_EFI_MOK_VARIABLE_TABLE_GUID config table can be provided
+ * to the kernel by an EFI boot loader. The table contains a packed
+ * sequence of these entries, one for each named MOK variable.
+ * The sequence is terminated by an entry with a completely NULL
+ * name and 0 data size.
+ */
+struct efi_mokvar_table_entry {
+	char name[256];
+	u64 data_size;
+	u8 data[];
+} __attribute((packed));
+
+#ifdef CONFIG_LOAD_UEFI_KEYS
+extern void __init efi_mokvar_table_init(void);
+extern struct efi_mokvar_table_entry *efi_mokvar_entry_next(
+			struct efi_mokvar_table_entry **mokvar_entry);
+extern struct efi_mokvar_table_entry *efi_mokvar_entry_find(const char *name);
+#else
+static inline void efi_mokvar_table_init(void) { }
+static inline struct efi_mokvar_table_entry *efi_mokvar_entry_next(
+			struct efi_mokvar_table_entry **mokvar_entry)
+{
+	return NULL;
+}
+static inline struct efi_mokvar_table_entry *efi_mokvar_entry_find(
+			const char *name)
+{
+	return NULL;
+}
+#endif
+
 #endif /* _LINUX_EFI_H */
-- 
cgit v1.2.3


From d8f0cd76684e679d4a8ec4929fcdf6c3a030a007 Mon Sep 17 00:00:00 2001
From: Nuno Sá <nuno.sa@analog.com>
Date: Tue, 15 Sep 2020 14:02:58 +0200
Subject: iio: adis: Drop non Managed device functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Drop `adis_setup_buffer_and_trigger()`. All users were updated to use
the devm version of this function. This avoids having almost the same
code repeated.

Signed-off-by: Nuno Sá <nuno.sa@analog.com>
Link: https://lore.kernel.org/r/20200915120258.161587-11-nuno.sa@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/imu/adis_buffer.c  | 64 +++---------------------------------------
 drivers/iio/imu/adis_trigger.c | 60 ---------------------------------------
 include/linux/iio/imu/adis.h   | 27 ------------------
 3 files changed, 4 insertions(+), 147 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iio/imu/adis_buffer.c b/drivers/iio/imu/adis_buffer.c
index 5b4225ee09b9..df6144285470 100644
--- a/drivers/iio/imu/adis_buffer.c
+++ b/drivers/iio/imu/adis_buffer.c
@@ -169,48 +169,6 @@ static void adis_buffer_cleanup(void *arg)
 	kfree(adis->xfer);
 }
 
-/**
- * adis_setup_buffer_and_trigger() - Sets up buffer and trigger for the adis device
- * @adis: The adis device.
- * @indio_dev: The IIO device.
- * @trigger_handler: Optional trigger handler, may be NULL.
- *
- * Returns 0 on success, a negative error code otherwise.
- *
- * This function sets up the buffer and trigger for a adis devices.  If
- * 'trigger_handler' is NULL the default trigger handler will be used. The
- * default trigger handler will simply read the registers assigned to the
- * currently active channels.
- *
- * adis_cleanup_buffer_and_trigger() should be called to free the resources
- * allocated by this function.
- */
-int adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev,
-	irqreturn_t (*trigger_handler)(int, void *))
-{
-	int ret;
-
-	if (!trigger_handler)
-		trigger_handler = adis_trigger_handler;
-
-	ret = iio_triggered_buffer_setup(indio_dev, &iio_pollfunc_store_time,
-		trigger_handler, NULL);
-	if (ret)
-		return ret;
-
-	if (adis->spi->irq) {
-		ret = adis_probe_trigger(adis, indio_dev);
-		if (ret)
-			goto error_buffer_cleanup;
-	}
-	return 0;
-
-error_buffer_cleanup:
-	iio_triggered_buffer_cleanup(indio_dev);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(adis_setup_buffer_and_trigger);
-
 /**
  * devm_adis_setup_buffer_and_trigger() - Sets up buffer and trigger for
  *					  the managed adis device
@@ -220,7 +178,10 @@ EXPORT_SYMBOL_GPL(adis_setup_buffer_and_trigger);
  *
  * Returns 0 on success, a negative error code otherwise.
  *
- * This function perfoms exactly the same as adis_setup_buffer_and_trigger()
+ * This function sets up the buffer and trigger for a adis devices.  If
+ * 'trigger_handler' is NULL the default trigger handler will be used. The
+ * default trigger handler will simply read the registers assigned to the
+ * currently active channels.
  */
 int
 devm_adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev,
@@ -248,20 +209,3 @@ devm_adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev,
 }
 EXPORT_SYMBOL_GPL(devm_adis_setup_buffer_and_trigger);
 
-/**
- * adis_cleanup_buffer_and_trigger() - Free buffer and trigger resources
- * @adis: The adis device.
- * @indio_dev: The IIO device.
- *
- * Frees resources allocated by adis_setup_buffer_and_trigger()
- */
-void adis_cleanup_buffer_and_trigger(struct adis *adis,
-	struct iio_dev *indio_dev)
-{
-	if (adis->spi->irq)
-		adis_remove_trigger(adis);
-	kfree(adis->buffer);
-	kfree(adis->xfer);
-	iio_triggered_buffer_cleanup(indio_dev);
-}
-EXPORT_SYMBOL_GPL(adis_cleanup_buffer_and_trigger);
diff --git a/drivers/iio/imu/adis_trigger.c b/drivers/iio/imu/adis_trigger.c
index 8afe71947c00..64e0ba51cb18 100644
--- a/drivers/iio/imu/adis_trigger.c
+++ b/drivers/iio/imu/adis_trigger.c
@@ -55,53 +55,6 @@ static int adis_validate_irq_flag(struct adis *adis)
 
 	return 0;
 }
-/**
- * adis_probe_trigger() - Sets up trigger for a adis device
- * @adis: The adis device
- * @indio_dev: The IIO device
- *
- * Returns 0 on success or a negative error code
- *
- * adis_remove_trigger() should be used to free the trigger.
- */
-int adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev)
-{
-	int ret;
-
-	adis->trig = iio_trigger_alloc("%s-dev%d", indio_dev->name,
-					indio_dev->id);
-	if (adis->trig == NULL)
-		return -ENOMEM;
-
-	adis_trigger_setup(adis);
-
-	ret = adis_validate_irq_flag(adis);
-	if (ret)
-		return ret;
-
-	ret = request_irq(adis->spi->irq,
-			  &iio_trigger_generic_data_rdy_poll,
-			  adis->irq_flag,
-			  indio_dev->name,
-			  adis->trig);
-	if (ret)
-		goto error_free_trig;
-
-	ret = iio_trigger_register(adis->trig);
-
-	indio_dev->trig = iio_trigger_get(adis->trig);
-	if (ret)
-		goto error_free_irq;
-
-	return 0;
-
-error_free_irq:
-	free_irq(adis->spi->irq, adis->trig);
-error_free_trig:
-	iio_trigger_free(adis->trig);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(adis_probe_trigger);
 
 /**
  * devm_adis_probe_trigger() - Sets up trigger for a managed adis device
@@ -137,16 +90,3 @@ int devm_adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev)
 }
 EXPORT_SYMBOL_GPL(devm_adis_probe_trigger);
 
-/**
- * adis_remove_trigger() - Remove trigger for a adis devices
- * @adis: The adis device
- *
- * Removes the trigger previously registered with adis_probe_trigger().
- */
-void adis_remove_trigger(struct adis *adis)
-{
-	iio_trigger_unregister(adis->trig);
-	free_irq(adis->spi->irq, adis->trig);
-	iio_trigger_free(adis->trig);
-}
-EXPORT_SYMBOL_GPL(adis_remove_trigger);
diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h
index 2df67448f0d1..01ba691da2f3 100644
--- a/include/linux/iio/imu/adis.h
+++ b/include/linux/iio/imu/adis.h
@@ -517,14 +517,8 @@ struct adis_burst {
 int
 devm_adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev,
 				   irq_handler_t trigger_handler);
-int adis_setup_buffer_and_trigger(struct adis *adis,
-	struct iio_dev *indio_dev, irqreturn_t (*trigger_handler)(int, void *));
-void adis_cleanup_buffer_and_trigger(struct adis *adis,
-	struct iio_dev *indio_dev);
 
 int devm_adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev);
-int adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev);
-void adis_remove_trigger(struct adis *adis);
 
 int adis_update_scan_mode(struct iio_dev *indio_dev,
 	const unsigned long *scan_mask);
@@ -538,33 +532,12 @@ devm_adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev,
 	return 0;
 }
 
-static inline int adis_setup_buffer_and_trigger(struct adis *adis,
-	struct iio_dev *indio_dev, irqreturn_t (*trigger_handler)(int, void *))
-{
-	return 0;
-}
-
-static inline void adis_cleanup_buffer_and_trigger(struct adis *adis,
-	struct iio_dev *indio_dev)
-{
-}
-
 static inline int devm_adis_probe_trigger(struct adis *adis,
 					  struct iio_dev *indio_dev)
 {
 	return 0;
 }
 
-static inline int adis_probe_trigger(struct adis *adis,
-	struct iio_dev *indio_dev)
-{
-	return 0;
-}
-
-static inline void adis_remove_trigger(struct adis *adis)
-{
-}
-
 #define adis_update_scan_mode NULL
 
 #endif /* CONFIG_IIO_BUFFER */
-- 
cgit v1.2.3


From aabf59432c51be174994ecfe280f75ac139b5550 Mon Sep 17 00:00:00 2001
From: Krzysztof Wilczyński <kw@linux.com>
Date: Sun, 6 Sep 2020 22:39:49 +0000
Subject: fs: Remove duplicated flag O_NDELAY occurring twice in
 VALID_OPEN_FLAGS
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The O_NDELAY flag occurs twice in the VALID_OPEN_FLAGS definition, this
change removes the duplicate.  There is no change to the functionality.

Note, that the flags O_NONBLOCK and O_NDELAY are not duplicates, as
values of these flags are platform dependent, and on platforms like
Sparc O_NONBLOCK and O_NDELAY are not the same.

This has been done that way to maintain the ABI compatibility with
Solaris since the Sparc port was first introduced.

This change resolves the following Coccinelle warning:

  include/linux/fcntl.h:11:13-21: duplicated argument to & or |

Signed-off-by: Krzysztof Wilczyński <kw@linux.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/fcntl.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h
index 7bcdcf4f6ab2..921e750843e6 100644
--- a/include/linux/fcntl.h
+++ b/include/linux/fcntl.h
@@ -8,7 +8,7 @@
 /* List of all valid flags for the open/openat flags argument: */
 #define VALID_OPEN_FLAGS \
 	(O_RDONLY | O_WRONLY | O_RDWR | O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC | \
-	 O_APPEND | O_NDELAY | O_NONBLOCK | O_NDELAY | __O_SYNC | O_DSYNC | \
+	 O_APPEND | O_NDELAY | O_NONBLOCK | __O_SYNC | O_DSYNC | \
 	 FASYNC	| O_DIRECT | O_LARGEFILE | O_DIRECTORY | O_NOFOLLOW | \
 	 O_NOATIME | O_CLOEXEC | O_PATH | __O_TMPFILE)
 
-- 
cgit v1.2.3


From ba3a86e47232ad9f76160929f33ac9c64e4d0567 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Mon, 14 Sep 2020 15:44:37 -0700
Subject: rcu-tasks: Fix grace-period/unlock race in RCU Tasks Trace

The more intense grace-period processing resulting from the 50x RCU
Tasks Trace grace-period speedups exposed the following race condition:

o	Task A running on CPU 0 executes rcu_read_lock_trace(),
	entering a read-side critical section.

o	When Task A eventually invokes rcu_read_unlock_trace()
	to exit its read-side critical section, this function
	notes that the ->trc_reader_special.s flag is zero and
	and therefore invoke wil set ->trc_reader_nesting to zero
	using WRITE_ONCE().  But before that happens...

o	The RCU Tasks Trace grace-period kthread running on some other
	CPU interrogates Task A, but this fails because this task is
	currently running.  This kthread therefore sends an IPI to CPU 0.

o	CPU 0 receives the IPI, and thus invokes trc_read_check_handler().
	Because Task A has not yet cleared its ->trc_reader_nesting
	counter, this function sees that Task A is still within its
	read-side critical section.  This function therefore sets the
	->trc_reader_nesting.b.need_qs flag, AKA the .need_qs flag.

	Except that Task A has already checked the .need_qs flag, which
	is part of the ->trc_reader_special.s flag.  The .need_qs flag
	therefore remains set until Task A's next rcu_read_unlock_trace().

o	Task A now invokes synchronize_rcu_tasks_trace(), which cannot
	start a new grace period until the current grace period completes.
	And thus cannot return until after that time.

	But Task A's .need_qs flag is still set, which prevents the current
	grace period from completing.  And because Task A is blocked, it
	will never execute rcu_read_unlock_trace() until its call to
	synchronize_rcu_tasks_trace() returns.

	We are therefore deadlocked.

This race is improbable, but 80 hours of rcutorture made it happen twice.
The race was possible before the grace-period speedup, but roughly 50x
less probable.  Several thousand hours of rcutorture would have been
necessary to have a reasonable chance of making this happen before this
50x speedup.

This commit therefore eliminates this deadlock by setting
->trc_reader_nesting to a large negative number before checking the
.need_qs and zeroing (or decrementing with respect to its initial
value) ->trc_reader_nesting.  For its part, the IPI handler's
trc_read_check_handler() function adds a check for negative values,
deferring evaluation of the task in this case.  Taken together, these
changes avoid this deadlock scenario.

Fixes: 276c410448db ("rcu-tasks: Split ->trc_reader_need_end")
Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: <bpf@vger.kernel.org>
Cc: <stable@vger.kernel.org> # 5.7.x
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/rcupdate_trace.h | 4 ++++
 kernel/rcu/tasks.h             | 6 ++++++
 2 files changed, 10 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/rcupdate_trace.h b/include/linux/rcupdate_trace.h
index d9015aac78c6..a6a6a3acab5a 100644
--- a/include/linux/rcupdate_trace.h
+++ b/include/linux/rcupdate_trace.h
@@ -50,6 +50,7 @@ static inline void rcu_read_lock_trace(void)
 	struct task_struct *t = current;
 
 	WRITE_ONCE(t->trc_reader_nesting, READ_ONCE(t->trc_reader_nesting) + 1);
+	barrier();
 	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) &&
 	    t->trc_reader_special.b.need_mb)
 		smp_mb(); // Pairs with update-side barriers
@@ -72,6 +73,9 @@ static inline void rcu_read_unlock_trace(void)
 
 	rcu_lock_release(&rcu_trace_lock_map);
 	nesting = READ_ONCE(t->trc_reader_nesting) - 1;
+	barrier(); // Critical section before disabling.
+	// Disable IPI-based setting of .need_qs.
+	WRITE_ONCE(t->trc_reader_nesting, INT_MIN);
 	if (likely(!READ_ONCE(t->trc_reader_special.s)) || nesting) {
 		WRITE_ONCE(t->trc_reader_nesting, nesting);
 		return;  // We assume shallow reader nesting.
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index a0eaed522277..e583a2d47374 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -830,6 +830,12 @@ static void trc_read_check_handler(void *t_in)
 		WRITE_ONCE(t->trc_reader_checked, true);
 		goto reset_ipi;
 	}
+	// If we are racing with an rcu_read_unlock_trace(), try again later.
+	if (unlikely(t->trc_reader_nesting < 0)) {
+		if (WARN_ON_ONCE(atomic_dec_and_test(&trc_n_readers_need_end)))
+			wake_up(&trc_wait);
+		goto reset_ipi;
+	}
 	WRITE_ONCE(t->trc_reader_checked, true);
 
 	// Get here if the task is in a read-side critical section.  Set
-- 
cgit v1.2.3


From 9baf68cc4544056f33797b78ec09388f54ecc8f0 Mon Sep 17 00:00:00 2001
From: Alex Kluver <alex.kluver@hpe.com>
Date: Wed, 19 Aug 2020 09:35:43 -0500
Subject: edac,ghes,cper: Add Row Extension to Memory Error Record

Memory errors could be printed with incorrect row values since the DIMM
size has outgrown the 16 bit row field in the CPER structure. UEFI
Specification Version 2.8 has increased the size of row by allowing it to
use the first 2 bits from a previously reserved space within the structure.

When needed, add the extension bits to the row value printed.

Based on UEFI 2.8 Table 299. Memory Error Record

Signed-off-by: Alex Kluver <alex.kluver@hpe.com>
Tested-by: Russ Anderson <russ.anderson@hpe.com>
Reviewed-by: Steve Wahl <steve.wahl@hpe.com>
Reviewed-by: Kyle Meyer <kyle.meyer@hpe.com>
Acked-by: Borislav Petkov <bp@suse.de>
Link: https://lore.kernel.org/r/20200819143544.155096-2-alex.kluver@hpe.com
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/edac/ghes_edac.c    |  8 ++++++--
 drivers/firmware/efi/cper.c |  9 +++++++--
 include/linux/cper.h        | 16 ++++++++++++++--
 3 files changed, 27 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c
index da60c29468a7..741e7609e511 100644
--- a/drivers/edac/ghes_edac.c
+++ b/drivers/edac/ghes_edac.c
@@ -372,8 +372,12 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
 		p += sprintf(p, "rank:%d ", mem_err->rank);
 	if (mem_err->validation_bits & CPER_MEM_VALID_BANK)
 		p += sprintf(p, "bank:%d ", mem_err->bank);
-	if (mem_err->validation_bits & CPER_MEM_VALID_ROW)
-		p += sprintf(p, "row:%d ", mem_err->row);
+	if (mem_err->validation_bits & (CPER_MEM_VALID_ROW | CPER_MEM_VALID_ROW_EXT)) {
+		u32 row = mem_err->row;
+
+		row |= cper_get_mem_extension(mem_err->validation_bits, mem_err->extended);
+		p += sprintf(p, "row:%d ", row);
+	}
 	if (mem_err->validation_bits & CPER_MEM_VALID_COLUMN)
 		p += sprintf(p, "col:%d ", mem_err->column);
 	if (mem_err->validation_bits & CPER_MEM_VALID_BIT_POSITION)
diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index f564e15fbc7e..a60acd17bcaa 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -234,8 +234,12 @@ static int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg)
 		n += scnprintf(msg + n, len - n, "bank: %d ", mem->bank);
 	if (mem->validation_bits & CPER_MEM_VALID_DEVICE)
 		n += scnprintf(msg + n, len - n, "device: %d ", mem->device);
-	if (mem->validation_bits & CPER_MEM_VALID_ROW)
-		n += scnprintf(msg + n, len - n, "row: %d ", mem->row);
+	if (mem->validation_bits & (CPER_MEM_VALID_ROW | CPER_MEM_VALID_ROW_EXT)) {
+		u32 row = mem->row;
+
+		row |= cper_get_mem_extension(mem->validation_bits, mem->extended);
+		n += scnprintf(msg + n, len - n, "row: %d ", row);
+	}
 	if (mem->validation_bits & CPER_MEM_VALID_COLUMN)
 		n += scnprintf(msg + n, len - n, "column: %d ", mem->column);
 	if (mem->validation_bits & CPER_MEM_VALID_BIT_POSITION)
@@ -292,6 +296,7 @@ void cper_mem_err_pack(const struct cper_sec_mem_err *mem,
 	cmem->requestor_id = mem->requestor_id;
 	cmem->responder_id = mem->responder_id;
 	cmem->target_id = mem->target_id;
+	cmem->extended = mem->extended;
 	cmem->rank = mem->rank;
 	cmem->mem_array_handle = mem->mem_array_handle;
 	cmem->mem_dev_handle = mem->mem_dev_handle;
diff --git a/include/linux/cper.h b/include/linux/cper.h
index 8537e9282a65..bd2d8a77a784 100644
--- a/include/linux/cper.h
+++ b/include/linux/cper.h
@@ -230,6 +230,10 @@ enum {
 #define CPER_MEM_VALID_RANK_NUMBER		0x8000
 #define CPER_MEM_VALID_CARD_HANDLE		0x10000
 #define CPER_MEM_VALID_MODULE_HANDLE		0x20000
+#define CPER_MEM_VALID_ROW_EXT			0x40000
+
+#define CPER_MEM_EXT_ROW_MASK			0x3
+#define CPER_MEM_EXT_ROW_SHIFT			16
 
 #define CPER_PCIE_VALID_PORT_TYPE		0x0001
 #define CPER_PCIE_VALID_VERSION			0x0002
@@ -443,7 +447,7 @@ struct cper_sec_mem_err_old {
 	u8	error_type;
 };
 
-/* Memory Error Section (UEFI >= v2.3), UEFI v2.7 sec N.2.5 */
+/* Memory Error Section (UEFI >= v2.3), UEFI v2.8 sec N.2.5 */
 struct cper_sec_mem_err {
 	u64	validation_bits;
 	u64	error_status;
@@ -461,7 +465,7 @@ struct cper_sec_mem_err {
 	u64	responder_id;
 	u64	target_id;
 	u8	error_type;
-	u8	reserved;
+	u8	extended;
 	u16	rank;
 	u16	mem_array_handle;	/* "card handle" in UEFI 2.4 */
 	u16	mem_dev_handle;		/* "module handle" in UEFI 2.4 */
@@ -483,8 +487,16 @@ struct cper_mem_err_compact {
 	u16	rank;
 	u16	mem_array_handle;
 	u16	mem_dev_handle;
+	u8      extended;
 };
 
+static inline u32 cper_get_mem_extension(u64 mem_valid, u8 mem_extended)
+{
+	if (!(mem_valid & CPER_MEM_VALID_ROW_EXT))
+		return 0;
+	return (mem_extended & CPER_MEM_EXT_ROW_MASK) << CPER_MEM_EXT_ROW_SHIFT;
+}
+
 /* PCI Express Error Section, UEFI v2.7 sec N.2.7 */
 struct cper_sec_pcie {
 	u64		validation_bits;
-- 
cgit v1.2.3


From 612b5d506d066cdf0a739963e7cd28642d500ec1 Mon Sep 17 00:00:00 2001
From: Alex Kluver <alex.kluver@hpe.com>
Date: Wed, 19 Aug 2020 09:35:44 -0500
Subject: cper,edac,efi: Memory Error Record: bank group/address and chip id

Updates to the UEFI 2.8 Memory Error Record allow splitting the bank field
into bank address and bank group, and using the last 3 bits of the extended
field as a chip identifier.

When needed, print correct version of bank field, bank group, and chip
identification.

Based on UEFI 2.8 Table 299. Memory Error Record.

Signed-off-by: Alex Kluver <alex.kluver@hpe.com>
Reviewed-by: Russ Anderson <russ.anderson@hpe.com>
Reviewed-by: Kyle Meyer <kyle.meyer@hpe.com>
Reviewed-by: Steve Wahl <steve.wahl@hpe.com>
Acked-by: Borislav Petkov <bp@suse.de>
Link: https://lore.kernel.org/r/20200819143544.155096-3-alex.kluver@hpe.com
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/edac/ghes_edac.c    | 9 +++++++++
 drivers/firmware/efi/cper.c | 9 +++++++++
 include/linux/cper.h        | 8 ++++++++
 3 files changed, 26 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c
index 741e7609e511..8a44f32db849 100644
--- a/drivers/edac/ghes_edac.c
+++ b/drivers/edac/ghes_edac.c
@@ -372,6 +372,12 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
 		p += sprintf(p, "rank:%d ", mem_err->rank);
 	if (mem_err->validation_bits & CPER_MEM_VALID_BANK)
 		p += sprintf(p, "bank:%d ", mem_err->bank);
+	if (mem_err->validation_bits & CPER_MEM_VALID_BANK_GROUP)
+		p += sprintf(p, "bank_group:%d ",
+			     mem_err->bank >> CPER_MEM_BANK_GROUP_SHIFT);
+	if (mem_err->validation_bits & CPER_MEM_VALID_BANK_ADDRESS)
+		p += sprintf(p, "bank_address:%d ",
+			     mem_err->bank & CPER_MEM_BANK_ADDRESS_MASK);
 	if (mem_err->validation_bits & (CPER_MEM_VALID_ROW | CPER_MEM_VALID_ROW_EXT)) {
 		u32 row = mem_err->row;
 
@@ -399,6 +405,9 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
 			strcpy(e->label, dimm->label);
 		}
 	}
+	if (mem_err->validation_bits & CPER_MEM_VALID_CHIP_ID)
+		p += sprintf(p, "chipID: %d ",
+			     mem_err->extended >> CPER_MEM_CHIP_ID_SHIFT);
 	if (p > e->location)
 		*(p - 1) = '\0';
 
diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index a60acd17bcaa..e15d484b6a5a 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -232,6 +232,12 @@ static int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg)
 		n += scnprintf(msg + n, len - n, "rank: %d ", mem->rank);
 	if (mem->validation_bits & CPER_MEM_VALID_BANK)
 		n += scnprintf(msg + n, len - n, "bank: %d ", mem->bank);
+	if (mem->validation_bits & CPER_MEM_VALID_BANK_GROUP)
+		n += scnprintf(msg + n, len - n, "bank_group: %d ",
+			       mem->bank >> CPER_MEM_BANK_GROUP_SHIFT);
+	if (mem->validation_bits & CPER_MEM_VALID_BANK_ADDRESS)
+		n += scnprintf(msg + n, len - n, "bank_address: %d ",
+			       mem->bank & CPER_MEM_BANK_ADDRESS_MASK);
 	if (mem->validation_bits & CPER_MEM_VALID_DEVICE)
 		n += scnprintf(msg + n, len - n, "device: %d ", mem->device);
 	if (mem->validation_bits & (CPER_MEM_VALID_ROW | CPER_MEM_VALID_ROW_EXT)) {
@@ -254,6 +260,9 @@ static int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg)
 	if (mem->validation_bits & CPER_MEM_VALID_TARGET_ID)
 		scnprintf(msg + n, len - n, "target_id: 0x%016llx ",
 			  mem->target_id);
+	if (mem->validation_bits & CPER_MEM_VALID_CHIP_ID)
+		scnprintf(msg + n, len - n, "chip_id: %d ",
+			  mem->extended >> CPER_MEM_CHIP_ID_SHIFT);
 
 	msg[n] = '\0';
 	return n;
diff --git a/include/linux/cper.h b/include/linux/cper.h
index bd2d8a77a784..6a511a1078ca 100644
--- a/include/linux/cper.h
+++ b/include/linux/cper.h
@@ -231,10 +231,18 @@ enum {
 #define CPER_MEM_VALID_CARD_HANDLE		0x10000
 #define CPER_MEM_VALID_MODULE_HANDLE		0x20000
 #define CPER_MEM_VALID_ROW_EXT			0x40000
+#define CPER_MEM_VALID_BANK_GROUP		0x80000
+#define CPER_MEM_VALID_BANK_ADDRESS		0x100000
+#define CPER_MEM_VALID_CHIP_ID			0x200000
 
 #define CPER_MEM_EXT_ROW_MASK			0x3
 #define CPER_MEM_EXT_ROW_SHIFT			16
 
+#define CPER_MEM_BANK_ADDRESS_MASK		0xff
+#define CPER_MEM_BANK_GROUP_SHIFT		8
+
+#define CPER_MEM_CHIP_ID_SHIFT			5
+
 #define CPER_PCIE_VALID_PORT_TYPE		0x0001
 #define CPER_PCIE_VALID_VERSION			0x0002
 #define CPER_PCIE_VALID_COMMAND_STATUS		0x0004
-- 
cgit v1.2.3


From 639bf4415cadff4c18e13aa5cb0dba2d443e3aa7 Mon Sep 17 00:00:00 2001
From: Aharon Landau <aharonl@mellanox.com>
Date: Thu, 17 Sep 2020 12:02:21 +0300
Subject: net/mlx5: Refactor query port speed functions

The functions mlx5_query_port_link_width_oper and
mlx5_query_port_ib_proto_oper are always called together, so combine them
to a new function called mlx5_query_port_oper to avoid duplication.

And while the mlx5i_get_port_settings is the same as
mlx5_query_port_oper therefore let's remove it.

According to the IB spec link_width_oper and ib_proto_oper should be u16
and not as written u8, so perform casting as a preparation to cross-RDMA
patch which will fix that type for all drivers in the RDMA subsystem.

Fixes: ada68c31ba9c ("net/mlx5: Introduce a new header file for physical port functions")
Signed-off-by: Aharon Landau <aharonl@mellanox.com>
Reviewed-by: Michael Guralnik <michaelgur@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/infiniband/hw/mlx5/main.c                  | 27 +++++++++++-----------
 .../ethernet/mellanox/mlx5/core/ipoib/ethtool.c    | 23 ++++--------------
 drivers/net/ethernet/mellanox/mlx5/core/port.c     | 23 ++++--------------
 include/linux/mlx5/port.h                          |  7 +++---
 4 files changed, 25 insertions(+), 55 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index d60d63221b14..631ca360057f 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -326,8 +326,8 @@ out:
 	spin_unlock(&port->mp.mpi_lock);
 }
 
-static int translate_eth_legacy_proto_oper(u32 eth_proto_oper, u8 *active_speed,
-					   u8 *active_width)
+static int translate_eth_legacy_proto_oper(u32 eth_proto_oper,
+					   u16 *active_speed, u8 *active_width)
 {
 	switch (eth_proto_oper) {
 	case MLX5E_PROT_MASK(MLX5E_1000BASE_CX_SGMII):
@@ -384,7 +384,7 @@ static int translate_eth_legacy_proto_oper(u32 eth_proto_oper, u8 *active_speed,
 	return 0;
 }
 
-static int translate_eth_ext_proto_oper(u32 eth_proto_oper, u8 *active_speed,
+static int translate_eth_ext_proto_oper(u32 eth_proto_oper, u16 *active_speed,
 					u8 *active_width)
 {
 	switch (eth_proto_oper) {
@@ -436,7 +436,7 @@ static int translate_eth_ext_proto_oper(u32 eth_proto_oper, u8 *active_speed,
 	return 0;
 }
 
-static int translate_eth_proto_oper(u32 eth_proto_oper, u8 *active_speed,
+static int translate_eth_proto_oper(u32 eth_proto_oper, u16 *active_speed,
 				    u8 *active_width, bool ext)
 {
 	return ext ?
@@ -457,6 +457,7 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num,
 	bool put_mdev = true;
 	u16 qkey_viol_cntr;
 	u32 eth_prot_oper;
+	u16 active_speed;
 	u8 mdev_port_num;
 	bool ext;
 	int err;
@@ -490,9 +491,12 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num,
 	props->active_width     = IB_WIDTH_4X;
 	props->active_speed     = IB_SPEED_QDR;
 
-	translate_eth_proto_oper(eth_prot_oper, &props->active_speed,
+	translate_eth_proto_oper(eth_prot_oper, &active_speed,
 				 &props->active_width, ext);
 
+	WARN_ON_ONCE(active_speed & ~0xFF);
+	props->active_speed = (u8)active_speed;
+
 	props->port_cap_flags |= IB_PORT_CM_SUP;
 	props->ip_gids = true;
 
@@ -1183,8 +1187,8 @@ enum mlx5_ib_width {
 	MLX5_IB_WIDTH_12X	= 1 << 4
 };
 
-static void translate_active_width(struct ib_device *ibdev, u8 active_width,
-				  u8 *ib_width)
+static void translate_active_width(struct ib_device *ibdev, u16 active_width,
+				   u8 *ib_width)
 {
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
 
@@ -1277,7 +1281,7 @@ static int mlx5_query_hca_port(struct ib_device *ibdev, u8 port,
 	u16 max_mtu;
 	u16 oper_mtu;
 	int err;
-	u8 ib_link_width_oper;
+	u16 ib_link_width_oper;
 	u8 vl_hw_cap;
 
 	rep = kzalloc(sizeof(*rep), GFP_KERNEL);
@@ -1310,16 +1314,13 @@ static int mlx5_query_hca_port(struct ib_device *ibdev, u8 port,
 	if (props->port_cap_flags & IB_PORT_CAP_MASK2_SUP)
 		props->port_cap_flags2 = rep->cap_mask2;
 
-	err = mlx5_query_port_link_width_oper(mdev, &ib_link_width_oper, port);
+	err = mlx5_query_ib_port_oper(mdev, &ib_link_width_oper,
+				      (u16 *)&props->active_speed, port);
 	if (err)
 		goto out;
 
 	translate_active_width(ibdev, ib_link_width_oper, &props->active_width);
 
-	err = mlx5_query_port_ib_proto_oper(mdev, &props->active_speed, port);
-	if (err)
-		goto out;
-
 	mlx5_query_port_max_mtu(mdev, &max_mtu, port);
 
 	props->max_mtu = mlx5_mtu_to_ib_mtu(max_mtu);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
index 1eef66ee849e..17f5be801d2f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
@@ -174,24 +174,6 @@ static inline int mlx5_ptys_rate_enum_to_int(enum mlx5_ptys_rate rate)
 	}
 }
 
-static int mlx5i_get_port_settings(struct net_device *netdev,
-				   u16 *ib_link_width_oper, u16 *ib_proto_oper)
-{
-	struct mlx5e_priv *priv    = mlx5i_epriv(netdev);
-	struct mlx5_core_dev *mdev = priv->mdev;
-	u32 out[MLX5_ST_SZ_DW(ptys_reg)] = {0};
-	int ret;
-
-	ret = mlx5_query_port_ptys(mdev, out, sizeof(out), MLX5_PTYS_IB, 1);
-	if (ret)
-		return ret;
-
-	*ib_link_width_oper = MLX5_GET(ptys_reg, out, ib_link_width_oper);
-	*ib_proto_oper      = MLX5_GET(ptys_reg, out, ib_proto_oper);
-
-	return 0;
-}
-
 static int mlx5i_get_speed_settings(u16 ib_link_width_oper, u16 ib_proto_oper)
 {
 	int rate, width;
@@ -209,11 +191,14 @@ static int mlx5i_get_speed_settings(u16 ib_link_width_oper, u16 ib_proto_oper)
 static int mlx5i_get_link_ksettings(struct net_device *netdev,
 				    struct ethtool_link_ksettings *link_ksettings)
 {
+	struct mlx5e_priv *priv = mlx5i_epriv(netdev);
+	struct mlx5_core_dev *mdev = priv->mdev;
 	u16 ib_link_width_oper;
 	u16 ib_proto_oper;
 	int speed, ret;
 
-	ret = mlx5i_get_port_settings(netdev, &ib_link_width_oper, &ib_proto_oper);
+	ret = mlx5_query_ib_port_oper(mdev, &ib_link_width_oper, &ib_proto_oper,
+				      1);
 	if (ret)
 		return ret;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index e4186e84b3ff..4bb219565c58 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -154,24 +154,8 @@ int mlx5_set_port_beacon(struct mlx5_core_dev *dev, u16 beacon_duration)
 				    sizeof(out), MLX5_REG_MLCR, 0, 1);
 }
 
-int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev,
-				    u8 *link_width_oper, u8 local_port)
-{
-	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
-	int err;
-
-	err = mlx5_query_port_ptys(dev, out, sizeof(out), MLX5_PTYS_IB, local_port);
-	if (err)
-		return err;
-
-	*link_width_oper = MLX5_GET(ptys_reg, out, ib_link_width_oper);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(mlx5_query_port_link_width_oper);
-
-int mlx5_query_port_ib_proto_oper(struct mlx5_core_dev *dev,
-				  u8 *proto_oper, u8 local_port)
+int mlx5_query_ib_port_oper(struct mlx5_core_dev *dev, u16 *link_width_oper,
+			    u16 *proto_oper, u8 local_port)
 {
 	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
 	int err;
@@ -181,11 +165,12 @@ int mlx5_query_port_ib_proto_oper(struct mlx5_core_dev *dev,
 	if (err)
 		return err;
 
+	*link_width_oper = MLX5_GET(ptys_reg, out, ib_link_width_oper);
 	*proto_oper = MLX5_GET(ptys_reg, out, ib_proto_oper);
 
 	return 0;
 }
-EXPORT_SYMBOL(mlx5_query_port_ib_proto_oper);
+EXPORT_SYMBOL(mlx5_query_ib_port_oper);
 
 /* This function should be used after setting a port register only */
 void mlx5_toggle_port_link(struct mlx5_core_dev *dev)
diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h
index 2d45a6af52a4..4d33ae0c2d97 100644
--- a/include/linux/mlx5/port.h
+++ b/include/linux/mlx5/port.h
@@ -133,10 +133,9 @@ enum mlx5e_connector_type {
 int mlx5_set_port_caps(struct mlx5_core_dev *dev, u8 port_num, u32 caps);
 int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys,
 			 int ptys_size, int proto_mask, u8 local_port);
-int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev,
-				    u8 *link_width_oper, u8 local_port);
-int mlx5_query_port_ib_proto_oper(struct mlx5_core_dev *dev,
-				  u8 *proto_oper, u8 local_port);
+
+int mlx5_query_ib_port_oper(struct mlx5_core_dev *dev, u16 *link_width_oper,
+			    u16 *proto_oper, u8 local_port);
 void mlx5_toggle_port_link(struct mlx5_core_dev *dev);
 int mlx5_set_port_admin_status(struct mlx5_core_dev *dev,
 			       enum mlx5_port_status status);
-- 
cgit v1.2.3


From e27014bdb47eb435f78573685f4196c07329f1f7 Mon Sep 17 00:00:00 2001
From: Aharon Landau <aharonl@mellanox.com>
Date: Thu, 17 Sep 2020 12:02:22 +0300
Subject: RDMA/mlx5: Delete duplicated mlx5_ptys_width enum

Combine two same enums to avoid duplication.

Signed-off-by: Aharon Landau <aharonl@mellanox.com>
Reviewed-by: Michael Guralnik <michaelgur@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/infiniband/hw/mlx5/main.c                    | 20 ++++++--------------
 .../net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c  |  8 --------
 include/linux/mlx5/port.h                            |  8 ++++++++
 3 files changed, 14 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 631ca360057f..2dbacf0ebda3 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1179,32 +1179,24 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 	return 0;
 }
 
-enum mlx5_ib_width {
-	MLX5_IB_WIDTH_1X	= 1 << 0,
-	MLX5_IB_WIDTH_2X	= 1 << 1,
-	MLX5_IB_WIDTH_4X	= 1 << 2,
-	MLX5_IB_WIDTH_8X	= 1 << 3,
-	MLX5_IB_WIDTH_12X	= 1 << 4
-};
-
 static void translate_active_width(struct ib_device *ibdev, u16 active_width,
 				   u8 *ib_width)
 {
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
 
-	if (active_width & MLX5_IB_WIDTH_1X)
+	if (active_width & MLX5_PTYS_WIDTH_1X)
 		*ib_width = IB_WIDTH_1X;
-	else if (active_width & MLX5_IB_WIDTH_2X)
+	else if (active_width & MLX5_PTYS_WIDTH_2X)
 		*ib_width = IB_WIDTH_2X;
-	else if (active_width & MLX5_IB_WIDTH_4X)
+	else if (active_width & MLX5_PTYS_WIDTH_4X)
 		*ib_width = IB_WIDTH_4X;
-	else if (active_width & MLX5_IB_WIDTH_8X)
+	else if (active_width & MLX5_PTYS_WIDTH_8X)
 		*ib_width = IB_WIDTH_8X;
-	else if (active_width & MLX5_IB_WIDTH_12X)
+	else if (active_width & MLX5_PTYS_WIDTH_12X)
 		*ib_width = IB_WIDTH_12X;
 	else {
 		mlx5_ib_dbg(dev, "Invalid active_width %d, setting width to default value: 4x\n",
-			    (int)active_width);
+			    active_width);
 		*ib_width = IB_WIDTH_4X;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
index 17f5be801d2f..cac8f085b16d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
@@ -130,14 +130,6 @@ static int mlx5i_flash_device(struct net_device *netdev,
 	return mlx5e_ethtool_flash_device(priv, flash);
 }
 
-enum mlx5_ptys_width {
-	MLX5_PTYS_WIDTH_1X	= 1 << 0,
-	MLX5_PTYS_WIDTH_2X	= 1 << 1,
-	MLX5_PTYS_WIDTH_4X	= 1 << 2,
-	MLX5_PTYS_WIDTH_8X	= 1 << 3,
-	MLX5_PTYS_WIDTH_12X	= 1 << 4,
-};
-
 static inline int mlx5_ptys_width_enum_to_int(enum mlx5_ptys_width width)
 {
 	switch (width) {
diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h
index 4d33ae0c2d97..23edd2db4803 100644
--- a/include/linux/mlx5/port.h
+++ b/include/linux/mlx5/port.h
@@ -125,6 +125,14 @@ enum mlx5e_connector_type {
 	MLX5E_CONNECTOR_TYPE_NUMBER,
 };
 
+enum mlx5_ptys_width {
+	MLX5_PTYS_WIDTH_1X	= 1 << 0,
+	MLX5_PTYS_WIDTH_2X	= 1 << 1,
+	MLX5_PTYS_WIDTH_4X	= 1 << 2,
+	MLX5_PTYS_WIDTH_8X	= 1 << 3,
+	MLX5_PTYS_WIDTH_12X	= 1 << 4,
+};
+
 #define MLX5E_PROT_MASK(link_mode) (1 << link_mode)
 #define MLX5_GET_ETH_PROTO(reg, out, ext, field)	\
 	(ext ? MLX5_GET(reg, out, ext_##field) :	\
-- 
cgit v1.2.3


From f959dcd6ddfd29235030e8026471ac1b022ad2b0 Mon Sep 17 00:00:00 2001
From: Thomas Tai <thomas.tai@oracle.com>
Date: Thu, 17 Sep 2020 18:43:03 +0200
Subject: dma-direct: Fix potential NULL pointer dereference

When booting the kernel v5.9-rc4 on a VM, the kernel would panic when
printing a warning message in swiotlb_map(). The dev->dma_mask must not
be a NULL pointer when calling the dma mapping layer. A NULL pointer
check can potentially avoid the panic.

Signed-off-by: Thomas Tai <thomas.tai@oracle.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/dma-direct.h |  3 ---
 kernel/dma/mapping.c       | 11 +++++++++++
 2 files changed, 11 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 805010ea5346..2929685e88aa 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -62,9 +62,6 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size,
 {
 	dma_addr_t end = addr + size - 1;
 
-	if (!dev->dma_mask)
-		return false;
-
 	if (is_ram && !IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT) &&
 	    min(addr, end) < phys_to_dma(dev, PFN_PHYS(min_low_pfn)))
 		return false;
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 848c95c27d79..9a045e51df17 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -144,6 +144,10 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
 	dma_addr_t addr;
 
 	BUG_ON(!valid_dma_direction(dir));
+
+	if (WARN_ON_ONCE(!dev->dma_mask))
+		return DMA_MAPPING_ERROR;
+
 	if (dma_map_direct(dev, ops))
 		addr = dma_direct_map_page(dev, page, offset, size, dir, attrs);
 	else
@@ -179,6 +183,10 @@ int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, int nents,
 	int ents;
 
 	BUG_ON(!valid_dma_direction(dir));
+
+	if (WARN_ON_ONCE(!dev->dma_mask))
+		return 0;
+
 	if (dma_map_direct(dev, ops))
 		ents = dma_direct_map_sg(dev, sg, nents, dir, attrs);
 	else
@@ -213,6 +221,9 @@ dma_addr_t dma_map_resource(struct device *dev, phys_addr_t phys_addr,
 
 	BUG_ON(!valid_dma_direction(dir));
 
+	if (WARN_ON_ONCE(!dev->dma_mask))
+		return DMA_MAPPING_ERROR;
+
 	/* Don't allow RAM to be mapped */
 	if (WARN_ON_ONCE(pfn_valid(PHYS_PFN(phys_addr))))
 		return DMA_MAPPING_ERROR;
-- 
cgit v1.2.3


From e0d072782c734d27f5af062c62266f2598f68542 Mon Sep 17 00:00:00 2001
From: Jim Quinlan <james.quinlan@broadcom.com>
Date: Thu, 17 Sep 2020 18:43:40 +0200
Subject: dma-mapping: introduce DMA range map, supplanting dma_pfn_offset

The new field 'dma_range_map' in struct device is used to facilitate the
use of single or multiple offsets between mapping regions of cpu addrs and
dma addrs.  It subsumes the role of "dev->dma_pfn_offset" which was only
capable of holding a single uniform offset and had no region bounds
checking.

The function of_dma_get_range() has been modified so that it takes a single
argument -- the device node -- and returns a map, NULL, or an error code.
The map is an array that holds the information regarding the DMA regions.
Each range entry contains the address offset, the cpu_start address, the
dma_start address, and the size of the region.

of_dma_configure() is the typical manner to set range offsets but there are
a number of ad hoc assignments to "dev->dma_pfn_offset" in the kernel
driver code.  These cases now invoke the function
dma_direct_set_offset(dev, cpu_addr, dma_addr, size).

Signed-off-by: Jim Quinlan <james.quinlan@broadcom.com>
[hch: various interface cleanups]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Tested-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Tested-by: Nathan Chancellor <natechancellor@gmail.com>
---
 arch/arm/include/asm/dma-direct.h                  |  9 ++-
 arch/arm/mach-keystone/keystone.c                  | 17 +++--
 arch/arm/mach-omap1/include/mach/memory.h          |  4 ++
 arch/sh/drivers/pci/pcie-sh7786.c                  |  9 +--
 arch/x86/pci/sta2x11-fixup.c                       |  6 +-
 drivers/acpi/arm64/iort.c                          |  6 +-
 drivers/base/core.c                                |  2 +
 drivers/gpu/drm/sun4i/sun4i_backend.c              |  8 ++-
 drivers/iommu/io-pgtable-arm.c                     |  2 +-
 drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c |  9 ++-
 drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c | 11 +++-
 drivers/of/address.c                               | 73 ++++++++++------------
 drivers/of/device.c                                | 44 ++++++++-----
 drivers/of/of_private.h                            | 11 ++--
 drivers/of/unittest.c                              | 34 +++++++---
 drivers/remoteproc/remoteproc_core.c               | 24 ++++++-
 drivers/staging/media/sunxi/cedrus/cedrus_hw.c     | 10 ++-
 include/linux/device.h                             |  4 +-
 include/linux/dma-direct.h                         | 53 ++++++++++++++--
 include/linux/dma-mapping.h                        |  9 ++-
 kernel/dma/coherent.c                              |  7 +--
 kernel/dma/direct.c                                | 51 ++++++++++++++-
 22 files changed, 285 insertions(+), 118 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/include/asm/dma-direct.h b/arch/arm/include/asm/dma-direct.h
index fbcf4367b5cb..436544aeb834 100644
--- a/arch/arm/include/asm/dma-direct.h
+++ b/arch/arm/include/asm/dma-direct.h
@@ -12,8 +12,8 @@
 #ifndef __arch_pfn_to_dma
 static inline dma_addr_t pfn_to_dma(struct device *dev, unsigned long pfn)
 {
-	if (dev)
-		pfn -= dev->dma_pfn_offset;
+	if (dev && dev->dma_range_map)
+		pfn = PFN_DOWN(translate_phys_to_dma(dev, PFN_PHYS(pfn)));
 	return (dma_addr_t)__pfn_to_bus(pfn);
 }
 
@@ -21,9 +21,8 @@ static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr)
 {
 	unsigned long pfn = __bus_to_pfn(addr);
 
-	if (dev)
-		pfn += dev->dma_pfn_offset;
-
+	if (dev && dev->dma_range_map)
+		pfn = PFN_DOWN(translate_dma_to_phys(dev, PFN_PHYS(pfn)));
 	return pfn;
 }
 
diff --git a/arch/arm/mach-keystone/keystone.c b/arch/arm/mach-keystone/keystone.c
index dcd031ba84c2..09a65c2dfd73 100644
--- a/arch/arm/mach-keystone/keystone.c
+++ b/arch/arm/mach-keystone/keystone.c
@@ -8,6 +8,7 @@
  */
 #include <linux/io.h>
 #include <linux/of.h>
+#include <linux/dma-mapping.h>
 #include <linux/init.h>
 #include <linux/of_platform.h>
 #include <linux/of_address.h>
@@ -25,8 +26,6 @@
 #include "keystone.h"
 
 #ifdef CONFIG_ARM_LPAE
-static unsigned long keystone_dma_pfn_offset __read_mostly;
-
 static int keystone_platform_notifier(struct notifier_block *nb,
 				      unsigned long event, void *data)
 {
@@ -39,9 +38,12 @@ static int keystone_platform_notifier(struct notifier_block *nb,
 		return NOTIFY_BAD;
 
 	if (!dev->of_node) {
-		dev->dma_pfn_offset = keystone_dma_pfn_offset;
-		dev_err(dev, "set dma_pfn_offset%08lx\n",
-			dev->dma_pfn_offset);
+		int ret = dma_direct_set_offset(dev, KEYSTONE_HIGH_PHYS_START,
+						KEYSTONE_LOW_PHYS_START,
+						KEYSTONE_HIGH_PHYS_SIZE);
+		dev_err(dev, "set dma_offset%08llx%s\n",
+			KEYSTONE_HIGH_PHYS_START - KEYSTONE_LOW_PHYS_START,
+			ret ? " failed" : "");
 	}
 	return NOTIFY_OK;
 }
@@ -54,11 +56,8 @@ static struct notifier_block platform_nb = {
 static void __init keystone_init(void)
 {
 #ifdef CONFIG_ARM_LPAE
-	if (PHYS_OFFSET >= KEYSTONE_HIGH_PHYS_START) {
-		keystone_dma_pfn_offset = PFN_DOWN(KEYSTONE_HIGH_PHYS_START -
-						   KEYSTONE_LOW_PHYS_START);
+	if (PHYS_OFFSET >= KEYSTONE_HIGH_PHYS_START)
 		bus_register_notifier(&platform_bus_type, &platform_nb);
-	}
 #endif
 	keystone_pm_runtime_init();
 }
diff --git a/arch/arm/mach-omap1/include/mach/memory.h b/arch/arm/mach-omap1/include/mach/memory.h
index e43697c3297b..1142560e0078 100644
--- a/arch/arm/mach-omap1/include/mach/memory.h
+++ b/arch/arm/mach-omap1/include/mach/memory.h
@@ -41,6 +41,10 @@
 	   __phys_to_pfn(__dma);				\
 	})
 
+#define __arch_dma_to_virt(dev, addr)	({ (void *) (is_lbus_device(dev) ? \
+						lbus_to_virt(addr) : \
+						__phys_to_virt(addr)); })
+
 #define __arch_virt_to_dma(dev, addr)	({ unsigned long __addr = (unsigned long)(addr); \
 					   (dma_addr_t) (is_lbus_device(dev) ? \
 						virt_to_lbus(__addr) : \
diff --git a/arch/sh/drivers/pci/pcie-sh7786.c b/arch/sh/drivers/pci/pcie-sh7786.c
index e0b568aaa701..4468289ab2ca 100644
--- a/arch/sh/drivers/pci/pcie-sh7786.c
+++ b/arch/sh/drivers/pci/pcie-sh7786.c
@@ -12,6 +12,7 @@
 #include <linux/io.h>
 #include <linux/async.h>
 #include <linux/delay.h>
+#include <linux/dma-mapping.h>
 #include <linux/slab.h>
 #include <linux/clk.h>
 #include <linux/sh_clk.h>
@@ -31,6 +32,8 @@ struct sh7786_pcie_port {
 static struct sh7786_pcie_port *sh7786_pcie_ports;
 static unsigned int nr_ports;
 static unsigned long dma_pfn_offset;
+size_t memsize;
+u64 memstart;
 
 static struct sh7786_pcie_hwops {
 	int (*core_init)(void);
@@ -301,7 +304,6 @@ static int __init pcie_init(struct sh7786_pcie_port *port)
 	struct pci_channel *chan = port->hose;
 	unsigned int data;
 	phys_addr_t memstart, memend;
-	size_t memsize;
 	int ret, i, win;
 
 	/* Begin initialization */
@@ -368,8 +370,6 @@ static int __init pcie_init(struct sh7786_pcie_port *port)
 	memstart = ALIGN_DOWN(memstart, memsize);
 	memsize = roundup_pow_of_two(memend - memstart);
 
-	dma_pfn_offset = memstart >> PAGE_SHIFT;
-
 	/*
 	 * If there's more than 512MB of memory, we need to roll over to
 	 * LAR1/LAMR1.
@@ -487,7 +487,8 @@ int pcibios_map_platform_irq(const struct pci_dev *pdev, u8 slot, u8 pin)
 
 void pcibios_bus_add_device(struct pci_dev *pdev)
 {
-	pdev->dev.dma_pfn_offset = dma_pfn_offset;
+	dma_direct_set_offset(&pdev->dev, __pa(memory_start),
+			      __pa(memory_start) - memstart, memsize);
 }
 
 static int __init sh7786_pcie_core_init(void)
diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c
index c313d784efab..324a207f9995 100644
--- a/arch/x86/pci/sta2x11-fixup.c
+++ b/arch/x86/pci/sta2x11-fixup.c
@@ -133,7 +133,7 @@ static void sta2x11_map_ep(struct pci_dev *pdev)
 	struct sta2x11_instance *instance = sta2x11_pdev_to_instance(pdev);
 	struct device *dev = &pdev->dev;
 	u32 amba_base, max_amba_addr;
-	int i;
+	int i, ret;
 
 	if (!instance)
 		return;
@@ -141,7 +141,9 @@ static void sta2x11_map_ep(struct pci_dev *pdev)
 	pci_read_config_dword(pdev, AHB_BASE(0), &amba_base);
 	max_amba_addr = amba_base + STA2X11_AMBA_SIZE - 1;
 
-	dev->dma_pfn_offset = PFN_DOWN(-amba_base);
+	ret = dma_direct_set_offset(dev, 0, amba_base, STA2X11_AMBA_SIZE);
+	if (ret)
+		dev_err(dev, "sta2x11: could not set DMA offset\n");
 
 	dev->bus_dma_limit = max_amba_addr;
 	pci_set_consistent_dma_mask(pdev, max_amba_addr);
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index ec782e4a0fe4..de18c07ca02c 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -18,6 +18,7 @@
 #include <linux/pci.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
+#include <linux/dma-mapping.h>
 
 #define IORT_TYPE_MASK(type)	(1 << (type))
 #define IORT_MSI_TYPE		(1 << ACPI_IORT_NODE_ITS_GROUP)
@@ -1184,8 +1185,9 @@ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size)
 	*dma_addr = dmaaddr;
 	*dma_size = size;
 
-	dev->dma_pfn_offset = PFN_DOWN(offset);
-	dev_dbg(dev, "dma_pfn_offset(%#08llx)\n", offset);
+	ret = dma_direct_set_offset(dev, dmaaddr + offset, dmaaddr, size);
+
+	dev_dbg(dev, "dma_offset(%#08llx)%s\n", offset, ret ? " failed!" : "");
 }
 
 static void __init acpi_iort_register_irq(int hwirq, const char *name,
diff --git a/drivers/base/core.c b/drivers/base/core.c
index f6f620aa9408..b893056e3945 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -1792,6 +1792,8 @@ static void device_release(struct kobject *kobj)
 	 */
 	devres_release_all(dev);
 
+	kfree(dev->dma_range_map);
+
 	if (dev->release)
 		dev->release(dev);
 	else if (dev->type && dev->type->release)
diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.c b/drivers/gpu/drm/sun4i/sun4i_backend.c
index 072ea113e6be..05e9f0d28196 100644
--- a/drivers/gpu/drm/sun4i/sun4i_backend.c
+++ b/drivers/gpu/drm/sun4i/sun4i_backend.c
@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <linux/of_device.h>
 #include <linux/of_graph.h>
+#include <linux/dma-mapping.h>
 #include <linux/platform_device.h>
 #include <linux/reset.h>
 
@@ -811,8 +812,13 @@ static int sun4i_backend_bind(struct device *dev, struct device *master,
 		 * because of an old DT, we need to set the DMA offset by hand
 		 * on our device since the RAM mapping is at 0 for the DMA bus,
 		 * unlike the CPU.
+		 *
+		 * XXX(hch): this has no business in a driver and needs to move
+		 * to the device tree.
 		 */
-		drm->dev->dma_pfn_offset = PHYS_PFN_OFFSET;
+		ret = dma_direct_set_offset(drm->dev, PHYS_OFFSET, 0, SZ_4G);
+		if (ret)
+			return ret;
 	}
 
 	backend->engine.node = dev->of_node;
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index dc7bcf858b6d..d77e881516a4 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -751,7 +751,7 @@ arm_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg)
 	if (cfg->oas > ARM_LPAE_MAX_ADDR_BITS)
 		return NULL;
 
-	if (!selftest_running && cfg->iommu_dev->dma_pfn_offset) {
+	if (!selftest_running && cfg->iommu_dev->dma_range_map) {
 		dev_err(cfg->iommu_dev, "Cannot accommodate DMA offset for IOMMU page tables\n");
 		return NULL;
 	}
diff --git a/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c b/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c
index 5319eb1ab309..307997ee7f96 100644
--- a/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c
+++ b/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/clk.h>
+#include <linux/dma-mapping.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
@@ -182,8 +183,14 @@ static int sun4i_csi_probe(struct platform_device *pdev)
 		if (ret)
 			return ret;
 	} else {
+		/*
+		 * XXX(hch): this has no business in a driver and needs to move
+		 * to the device tree.
+		 */
 #ifdef PHYS_PFN_OFFSET
-		csi->dev->dma_pfn_offset = PHYS_PFN_OFFSET;
+		ret = dma_direct_set_offset(csi->dev, PHYS_OFFSET, 0, SZ_4G);
+		if (ret)
+			return ret;
 #endif
 	}
 
diff --git a/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c b/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c
index 28e89340fed9..e69e14379fc6 100644
--- a/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c
+++ b/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c
@@ -899,8 +899,15 @@ static int sun6i_csi_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	sdev->dev = &pdev->dev;
-	/* The DMA bus has the memory mapped at 0 */
-	sdev->dev->dma_pfn_offset = PHYS_OFFSET >> PAGE_SHIFT;
+	/*
+	 * The DMA bus has the memory mapped at 0.
+	 *
+	 * XXX(hch): this has no business in a driver and needs to move
+	 * to the device tree.
+	 */
+	ret = dma_direct_set_offset(sdev->dev, PHYS_OFFSET, 0, SZ_4G);
+	if (ret)
+		return ret;
 
 	ret = sun6i_csi_resource_request(sdev, pdev);
 	if (ret)
diff --git a/drivers/of/address.c b/drivers/of/address.c
index da4f7341323f..eb9ab4f1e80b 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -13,6 +13,7 @@
 #include <linux/sizes.h>
 #include <linux/slab.h>
 #include <linux/string.h>
+#include <linux/dma-direct.h> /* for bus_dma_region */
 
 #include "of_private.h"
 
@@ -937,33 +938,33 @@ void __iomem *of_io_request_and_map(struct device_node *np, int index,
 }
 EXPORT_SYMBOL(of_io_request_and_map);
 
+#ifdef CONFIG_HAS_DMA
 /**
- * of_dma_get_range - Get DMA range info
+ * of_dma_get_range - Get DMA range info and put it into a map array
  * @np:		device node to get DMA range info
- * @dma_addr:	pointer to store initial DMA address of DMA range
- * @paddr:	pointer to store initial CPU address of DMA range
- * @size:	pointer to store size of DMA range
+ * @map:	dma range structure to return
  *
  * Look in bottom up direction for the first "dma-ranges" property
- * and parse it.
- *  dma-ranges format:
+ * and parse it.  Put the information into a DMA offset map array.
+ *
+ * dma-ranges format:
  *	DMA addr (dma_addr)	: naddr cells
  *	CPU addr (phys_addr_t)	: pna cells
  *	size			: nsize cells
  *
- * It returns -ENODEV if "dma-ranges" property was not found
- * for this device in DT.
+ * It returns -ENODEV if "dma-ranges" property was not found for this
+ * device in the DT.
  */
-int of_dma_get_range(struct device_node *np, u64 *dma_addr, u64 *paddr, u64 *size)
+int of_dma_get_range(struct device_node *np, const struct bus_dma_region **map)
 {
 	struct device_node *node = of_node_get(np);
 	const __be32 *ranges = NULL;
-	int len;
-	int ret = 0;
 	bool found_dma_ranges = false;
 	struct of_range_parser parser;
 	struct of_range range;
-	u64 dma_start = U64_MAX, dma_end = 0, dma_offset = 0;
+	struct bus_dma_region *r;
+	int len, num_ranges = 0;
+	int ret = 0;
 
 	while (node) {
 		ranges = of_get_property(node, "dma-ranges", &len);
@@ -989,49 +990,39 @@ int of_dma_get_range(struct device_node *np, u64 *dma_addr, u64 *paddr, u64 *siz
 	}
 
 	of_dma_range_parser_init(&parser, node);
+	for_each_of_range(&parser, &range)
+		num_ranges++;
+
+	r = kcalloc(num_ranges + 1, sizeof(*r), GFP_KERNEL);
+	if (!r) {
+		ret = -ENOMEM;
+		goto out;
+	}
 
+	/*
+	 * Record all info in the generic DMA ranges array for struct device.
+	 */
+	*map = r;
+	of_dma_range_parser_init(&parser, node);
 	for_each_of_range(&parser, &range) {
 		pr_debug("dma_addr(%llx) cpu_addr(%llx) size(%llx)\n",
 			 range.bus_addr, range.cpu_addr, range.size);
-
-		if (dma_offset && range.cpu_addr - range.bus_addr != dma_offset) {
-			pr_warn("Can't handle multiple dma-ranges with different offsets on node(%pOF)\n", node);
-			/* Don't error out as we'd break some existing DTs */
-			continue;
-		}
 		if (range.cpu_addr == OF_BAD_ADDR) {
 			pr_err("translation of DMA address(%llx) to CPU address failed node(%pOF)\n",
 			       range.bus_addr, node);
 			continue;
 		}
-		dma_offset = range.cpu_addr - range.bus_addr;
-
-		/* Take lower and upper limits */
-		if (range.bus_addr < dma_start)
-			dma_start = range.bus_addr;
-		if (range.bus_addr + range.size > dma_end)
-			dma_end = range.bus_addr + range.size;
-	}
-
-	if (dma_start >= dma_end) {
-		ret = -EINVAL;
-		pr_debug("Invalid DMA ranges configuration on node(%pOF)\n",
-			 node);
-		goto out;
+		r->cpu_start = range.cpu_addr;
+		r->dma_start = range.bus_addr;
+		r->size = range.size;
+		r->offset = range.cpu_addr - range.bus_addr;
+		r++;
 	}
-
-	*dma_addr = dma_start;
-	*size = dma_end - dma_start;
-	*paddr = dma_start + dma_offset;
-
-	pr_debug("final: dma_addr(%llx) cpu_addr(%llx) size(%llx)\n",
-		 *dma_addr, *paddr, *size);
-
 out:
 	of_node_put(node);
-
 	return ret;
 }
+#endif /* CONFIG_HAS_DMA */
 
 /**
  * of_dma_is_coherent - Check if device is coherent
diff --git a/drivers/of/device.c b/drivers/of/device.c
index b439c1e05434..6e3ae7ebc33e 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -5,7 +5,7 @@
 #include <linux/of_device.h>
 #include <linux/of_address.h>
 #include <linux/of_iommu.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-direct.h> /* for bus_dma_region */
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mod_devicetable.h>
@@ -90,14 +90,14 @@ int of_device_add(struct platform_device *ofdev)
 int of_dma_configure_id(struct device *dev, struct device_node *np,
 			bool force_dma, const u32 *id)
 {
-	u64 dma_addr, paddr, size = 0;
-	int ret;
-	bool coherent;
-	unsigned long offset;
 	const struct iommu_ops *iommu;
-	u64 mask, end;
+	const struct bus_dma_region *map = NULL;
+	dma_addr_t dma_start = 0;
+	u64 mask, end, size = 0;
+	bool coherent;
+	int ret;
 
-	ret = of_dma_get_range(np, &dma_addr, &paddr, &size);
+	ret = of_dma_get_range(np, &map);
 	if (ret < 0) {
 		/*
 		 * For legacy reasons, we have to assume some devices need
@@ -106,26 +106,35 @@ int of_dma_configure_id(struct device *dev, struct device_node *np,
 		 */
 		if (!force_dma)
 			return ret == -ENODEV ? 0 : ret;
-
-		dma_addr = offset = 0;
 	} else {
-		offset = PFN_DOWN(paddr - dma_addr);
+		const struct bus_dma_region *r = map;
+		dma_addr_t dma_end = 0;
+
+		/* Determine the overall bounds of all DMA regions */
+		for (dma_start = ~(dma_addr_t)0; r->size; r++) {
+			/* Take lower and upper limits */
+			if (r->dma_start < dma_start)
+				dma_start = r->dma_start;
+			if (r->dma_start + r->size > dma_end)
+				dma_end = r->dma_start + r->size;
+		}
+		size = dma_end - dma_start;
 
 		/*
 		 * Add a work around to treat the size as mask + 1 in case
 		 * it is defined in DT as a mask.
 		 */
 		if (size & 1) {
-			dev_warn(dev, "Invalid size 0x%llx for dma-range\n",
+			dev_warn(dev, "Invalid size 0x%llx for dma-range(s)\n",
 				 size);
 			size = size + 1;
 		}
 
 		if (!size) {
 			dev_err(dev, "Adjusted size 0x%llx invalid\n", size);
+			kfree(map);
 			return -EINVAL;
 		}
-		dev_dbg(dev, "dma_pfn_offset(%#08lx)\n", offset);
 	}
 
 	/*
@@ -144,13 +153,11 @@ int of_dma_configure_id(struct device *dev, struct device_node *np,
 	else if (!size)
 		size = 1ULL << 32;
 
-	dev->dma_pfn_offset = offset;
-
 	/*
 	 * Limit coherent and dma mask based on size and default mask
 	 * set by the driver.
 	 */
-	end = dma_addr + size - 1;
+	end = dma_start + size - 1;
 	mask = DMA_BIT_MASK(ilog2(end) + 1);
 	dev->coherent_dma_mask &= mask;
 	*dev->dma_mask &= mask;
@@ -163,14 +170,17 @@ int of_dma_configure_id(struct device *dev, struct device_node *np,
 		coherent ? " " : " not ");
 
 	iommu = of_iommu_configure(dev, np, id);
-	if (PTR_ERR(iommu) == -EPROBE_DEFER)
+	if (PTR_ERR(iommu) == -EPROBE_DEFER) {
+		kfree(map);
 		return -EPROBE_DEFER;
+	}
 
 	dev_dbg(dev, "device is%sbehind an iommu\n",
 		iommu ? " " : " not ");
 
-	arch_setup_dma_ops(dev, dma_addr, size, iommu, coherent);
+	arch_setup_dma_ops(dev, dma_start, size, iommu, coherent);
 
+	dev->dma_range_map = map;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(of_dma_configure_id);
diff --git a/drivers/of/of_private.h b/drivers/of/of_private.h
index edc682249c00..d9e6a324de0a 100644
--- a/drivers/of/of_private.h
+++ b/drivers/of/of_private.h
@@ -157,12 +157,13 @@ extern void __of_sysfs_remove_bin_file(struct device_node *np,
 extern int of_bus_n_addr_cells(struct device_node *np);
 extern int of_bus_n_size_cells(struct device_node *np);
 
-#ifdef CONFIG_OF_ADDRESS
-extern int of_dma_get_range(struct device_node *np, u64 *dma_addr,
-			    u64 *paddr, u64 *size);
+struct bus_dma_region;
+#if defined(CONFIG_OF_ADDRESS) && defined(CONFIG_HAS_DMA)
+int of_dma_get_range(struct device_node *np,
+		const struct bus_dma_region **map);
 #else
-static inline int of_dma_get_range(struct device_node *np, u64 *dma_addr,
-				   u64 *paddr, u64 *size)
+static inline int of_dma_get_range(struct device_node *np,
+		const struct bus_dma_region **map)
 {
 	return -ENODEV;
 }
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index 9b7e84bdc7d4..06cc988faf78 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -7,6 +7,7 @@
 
 #include <linux/memblock.h>
 #include <linux/clk.h>
+#include <linux/dma-direct.h> /* to test phys_to_dma/dma_to_phys */
 #include <linux/err.h>
 #include <linux/errno.h>
 #include <linux/hashtable.h>
@@ -869,10 +870,11 @@ static void __init of_unittest_changeset(void)
 }
 
 static void __init of_unittest_dma_ranges_one(const char *path,
-		u64 expect_dma_addr, u64 expect_paddr, u64 expect_size)
+		u64 expect_dma_addr, u64 expect_paddr)
 {
+#ifdef CONFIG_HAS_DMA
 	struct device_node *np;
-	u64 dma_addr, paddr, size;
+	const struct bus_dma_region *map = NULL;
 	int rc;
 
 	np = of_find_node_by_path(path);
@@ -881,28 +883,40 @@ static void __init of_unittest_dma_ranges_one(const char *path,
 		return;
 	}
 
-	rc = of_dma_get_range(np, &dma_addr, &paddr, &size);
+	rc = of_dma_get_range(np, &map);
 
 	unittest(!rc, "of_dma_get_range failed on node %pOF rc=%i\n", np, rc);
+
 	if (!rc) {
-		unittest(size == expect_size,
-			 "of_dma_get_range wrong size on node %pOF size=%llx\n", np, size);
+		phys_addr_t	paddr;
+		dma_addr_t	dma_addr;
+		struct device	dev_bogus;
+
+		dev_bogus.dma_range_map = map;
+		paddr = dma_to_phys(&dev_bogus, expect_dma_addr);
+		dma_addr = phys_to_dma(&dev_bogus, expect_paddr);
+
 		unittest(paddr == expect_paddr,
-			 "of_dma_get_range wrong phys addr (%llx) on node %pOF", paddr, np);
+			 "of_dma_get_range: wrong phys addr %pap (expecting %llx) on node %pOF\n",
+			 &paddr, expect_paddr, np);
 		unittest(dma_addr == expect_dma_addr,
-			 "of_dma_get_range wrong DMA addr (%llx) on node %pOF", dma_addr, np);
+			 "of_dma_get_range: wrong DMA addr %pad (expecting %llx) on node %pOF\n",
+			 &dma_addr, expect_dma_addr, np);
+
+		kfree(map);
 	}
 	of_node_put(np);
+#endif
 }
 
 static void __init of_unittest_parse_dma_ranges(void)
 {
 	of_unittest_dma_ranges_one("/testcase-data/address-tests/device@70000000",
-		0x0, 0x20000000, 0x40000000);
+		0x0, 0x20000000);
 	of_unittest_dma_ranges_one("/testcase-data/address-tests/bus@80000000/device@1000",
-		0x100000000, 0x20000000, 0x2000000000);
+		0x100000000, 0x20000000);
 	of_unittest_dma_ranges_one("/testcase-data/address-tests/pci@90000000",
-		0x80000000, 0x20000000, 0x10000000);
+		0x80000000, 0x20000000);
 }
 
 static void __init of_unittest_pci_dma_ranges(void)
diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c
index 7f90eeea67e2..8157dd491d28 100644
--- a/drivers/remoteproc/remoteproc_core.c
+++ b/drivers/remoteproc/remoteproc_core.c
@@ -23,6 +23,7 @@
 #include <linux/slab.h>
 #include <linux/mutex.h>
 #include <linux/dma-mapping.h>
+#include <linux/dma-direct.h> /* XXX: pokes into bus_dma_range */
 #include <linux/firmware.h>
 #include <linux/string.h>
 #include <linux/debugfs.h>
@@ -458,6 +459,25 @@ static void rproc_rvdev_release(struct device *dev)
 	kfree(rvdev);
 }
 
+static int copy_dma_range_map(struct device *to, struct device *from)
+{
+	const struct bus_dma_region *map = from->dma_range_map, *new_map, *r;
+	int num_ranges = 0;
+
+	if (!map)
+		return 0;
+
+	for (r = map; r->size; r++)
+		num_ranges++;
+
+	new_map = kmemdup(map, array_size(num_ranges + 1, sizeof(*map)),
+			  GFP_KERNEL);
+	if (!new_map)
+		return -ENOMEM;
+	to->dma_range_map = new_map;
+	return 0;
+}
+
 /**
  * rproc_handle_vdev() - handle a vdev fw resource
  * @rproc: the remote processor
@@ -529,7 +549,9 @@ static int rproc_handle_vdev(struct rproc *rproc, struct fw_rsc_vdev *rsc,
 	/* Initialise vdev subdevice */
 	snprintf(name, sizeof(name), "vdev%dbuffer", rvdev->index);
 	rvdev->dev.parent = &rproc->dev;
-	rvdev->dev.dma_pfn_offset = rproc->dev.parent->dma_pfn_offset;
+	ret = copy_dma_range_map(&rvdev->dev, rproc->dev.parent);
+	if (ret)
+		return ret;
 	rvdev->dev.release = rproc_rvdev_release;
 	dev_set_name(&rvdev->dev, "%s#%s", dev_name(rvdev->dev.parent), name);
 	dev_set_drvdata(&rvdev->dev, rvdev);
diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_hw.c b/drivers/staging/media/sunxi/cedrus/cedrus_hw.c
index 1744e6fcc999..bcf050a04ffc 100644
--- a/drivers/staging/media/sunxi/cedrus/cedrus_hw.c
+++ b/drivers/staging/media/sunxi/cedrus/cedrus_hw.c
@@ -227,11 +227,17 @@ int cedrus_hw_probe(struct cedrus_dev *dev)
 	 * the RAM offset to the physcal addresses.
 	 *
 	 * This information will eventually be obtained from device-tree.
+	 *
+	 * XXX(hch): this has no business in a driver and needs to move
+	 * to the device tree.
 	 */
 
 #ifdef PHYS_PFN_OFFSET
-	if (!(variant->quirks & CEDRUS_QUIRK_NO_DMA_OFFSET))
-		dev->dev->dma_pfn_offset = PHYS_PFN_OFFSET;
+	if (!(variant->quirks & CEDRUS_QUIRK_NO_DMA_OFFSET)) {
+		ret = dma_direct_set_offset(dev->dev, PHYS_OFFSET, 0, SZ_4G);
+		if (ret)
+			return ret;
+	}
 #endif
 
 	ret = of_reserved_mem_device_init(dev->dev);
diff --git a/include/linux/device.h b/include/linux/device.h
index ca18da4768e3..1c78621fc3c0 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -466,7 +466,7 @@ struct dev_links_info {
  * 		such descriptors.
  * @bus_dma_limit: Limit of an upstream bridge or bus which imposes a smaller
  *		DMA limit than the device itself supports.
- * @dma_pfn_offset: offset of DMA memory range relatively of RAM
+ * @dma_range_map: map for DMA memory ranges relative to that of RAM
  * @dma_parms:	A low level driver may set these to teach IOMMU code about
  * 		segment limitations.
  * @dma_pools:	Dma pools (if dma'ble device).
@@ -561,7 +561,7 @@ struct device {
 					     64 bit addresses for consistent
 					     allocations such descriptors. */
 	u64		bus_dma_limit;	/* upstream dma constraint */
-	unsigned long	dma_pfn_offset;
+	const struct bus_dma_region *dma_range_map;
 
 	struct device_dma_parameters *dma_parms;
 
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 2929685e88aa..83f797e0cb78 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -14,6 +14,41 @@
 
 extern unsigned int zone_dma_bits;
 
+/*
+ * Record the mapping of CPU physical to DMA addresses for a given region.
+ */
+struct bus_dma_region {
+	phys_addr_t	cpu_start;
+	dma_addr_t	dma_start;
+	u64		size;
+	u64		offset;
+};
+
+static inline dma_addr_t translate_phys_to_dma(struct device *dev,
+		phys_addr_t paddr)
+{
+	const struct bus_dma_region *m;
+
+	for (m = dev->dma_range_map; m->size; m++)
+		if (paddr >= m->cpu_start && paddr - m->cpu_start < m->size)
+			return (dma_addr_t)paddr - m->offset;
+
+	/* make sure dma_capable fails when no translation is available */
+	return DMA_MAPPING_ERROR;
+}
+
+static inline phys_addr_t translate_dma_to_phys(struct device *dev,
+		dma_addr_t dma_addr)
+{
+	const struct bus_dma_region *m;
+
+	for (m = dev->dma_range_map; m->size; m++)
+		if (dma_addr >= m->dma_start && dma_addr - m->dma_start < m->size)
+			return (phys_addr_t)dma_addr + m->offset;
+
+	return (phys_addr_t)-1;
+}
+
 #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA
 #include <asm/dma-direct.h>
 #ifndef phys_to_dma_unencrypted
@@ -23,9 +58,9 @@ extern unsigned int zone_dma_bits;
 static inline dma_addr_t phys_to_dma_unencrypted(struct device *dev,
 		phys_addr_t paddr)
 {
-	dma_addr_t dev_addr = (dma_addr_t)paddr;
-
-	return dev_addr - ((dma_addr_t)dev->dma_pfn_offset << PAGE_SHIFT);
+	if (dev->dma_range_map)
+		return translate_phys_to_dma(dev, paddr);
+	return paddr;
 }
 
 /*
@@ -39,10 +74,14 @@ static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return __sme_set(phys_to_dma_unencrypted(dev, paddr));
 }
 
-static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr)
+static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
-	phys_addr_t paddr = (phys_addr_t)dev_addr +
-		((phys_addr_t)dev->dma_pfn_offset << PAGE_SHIFT);
+	phys_addr_t paddr;
+
+	if (dev->dma_range_map)
+		paddr = translate_dma_to_phys(dev, dma_addr);
+	else
+		paddr = dma_addr;
 
 	return __sme_clr(paddr);
 }
@@ -62,6 +101,8 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size,
 {
 	dma_addr_t end = addr + size - 1;
 
+	if (addr == DMA_MAPPING_ERROR)
+		return false;
 	if (is_ram && !IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT) &&
 	    min(addr, end) < phys_to_dma(dev, PFN_PHYS(min_low_pfn)))
 		return false;
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index df0bff2ea750..bb138ac6f5e6 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -730,4 +730,11 @@ static inline int dma_mmap_wc(struct device *dev,
 #define dma_unmap_len_set(PTR, LEN_NAME, VAL)    do { } while (0)
 #endif
 
-#endif
+/*
+ * Legacy interface to set up the dma offset map.  Drivers really should not
+ * actually use it, but we have a few legacy cases left.
+ */
+int dma_direct_set_offset(struct device *dev, phys_addr_t cpu_start,
+		dma_addr_t dma_start, u64 size);
+
+#endif /* _LINUX_DMA_MAPPING_H */
diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c
index f85d14bbfcbe..c0685196fb6d 100644
--- a/kernel/dma/coherent.c
+++ b/kernel/dma/coherent.c
@@ -7,7 +7,7 @@
 #include <linux/slab.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-direct.h>
 
 struct dma_coherent_mem {
 	void		*virt_base;
@@ -32,9 +32,8 @@ static inline dma_addr_t dma_get_device_base(struct device *dev,
 					     struct dma_coherent_mem * mem)
 {
 	if (mem->use_dev_dma_pfn_offset)
-		return (mem->pfn_base - dev->dma_pfn_offset) << PAGE_SHIFT;
-	else
-		return mem->device_base;
+		return phys_to_dma(dev, PFN_PHYS(mem->pfn_base));
+	return mem->device_base;
 }
 
 static int dma_init_coherent_memory(phys_addr_t phys_addr,
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 54db9cfdaecc..750659f7447c 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -13,6 +13,7 @@
 #include <linux/pfn.h>
 #include <linux/vmalloc.h>
 #include <linux/set_memory.h>
+#include <linux/slab.h>
 
 /*
  * Most architectures use ZONE_DMA for the first 16 Megabytes, but some use it
@@ -66,8 +67,12 @@ static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
 
 static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
 {
-	return phys_to_dma_direct(dev, phys) + size - 1 <=
-			min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
+	dma_addr_t dma_addr = phys_to_dma_direct(dev, phys);
+
+	if (dma_addr == DMA_MAPPING_ERROR)
+		return false;
+	return dma_addr + size - 1 <=
+		min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
 }
 
 /*
@@ -461,3 +466,45 @@ bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr)
 	return !dev_is_dma_coherent(dev) ||
 		is_swiotlb_buffer(dma_to_phys(dev, dma_addr));
 }
+
+/**
+ * dma_direct_set_offset - Assign scalar offset for a single DMA range.
+ * @dev:	device pointer; needed to "own" the alloced memory.
+ * @cpu_start:  beginning of memory region covered by this offset.
+ * @dma_start:  beginning of DMA/PCI region covered by this offset.
+ * @size:	size of the region.
+ *
+ * This is for the simple case of a uniform offset which cannot
+ * be discovered by "dma-ranges".
+ *
+ * It returns -ENOMEM if out of memory, -EINVAL if a map
+ * already exists, 0 otherwise.
+ *
+ * Note: any call to this from a driver is a bug.  The mapping needs
+ * to be described by the device tree or other firmware interfaces.
+ */
+int dma_direct_set_offset(struct device *dev, phys_addr_t cpu_start,
+			 dma_addr_t dma_start, u64 size)
+{
+	struct bus_dma_region *map;
+	u64 offset = (u64)cpu_start - (u64)dma_start;
+
+	if (dev->dma_range_map) {
+		dev_err(dev, "attempt to add DMA range to existing map\n");
+		return -EINVAL;
+	}
+
+	if (!offset)
+		return 0;
+
+	map = kcalloc(2, sizeof(*map), GFP_KERNEL);
+	if (!map)
+		return -ENOMEM;
+	map[0].cpu_start = cpu_start;
+	map[0].dma_start = dma_start;
+	map[0].offset = offset;
+	map[0].size = size;
+	dev->dma_range_map = map;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dma_direct_set_offset);
-- 
cgit v1.2.3


From 527c412519eb63ed354790f4291c3728815d11a6 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 17 Sep 2020 09:41:58 +0200
Subject: compat: add a compat_need_64bit_alignment_fixup() helper

Add a helper to check if the calling syscall needs a fixup for
non-natural 64-bit type alignment in the compat ABI.  This will only
return true for i386 syscalls on x86_64.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/x86/include/asm/compat.h | 1 +
 include/linux/compat.h        | 9 +++++++++
 2 files changed, 10 insertions(+)

(limited to 'include/linux')

diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
index bf547701f41f..0e327a01f50f 100644
--- a/arch/x86/include/asm/compat.h
+++ b/arch/x86/include/asm/compat.h
@@ -209,6 +209,7 @@ static inline bool in_compat_syscall(void)
 	return in_32bit_syscall();
 }
 #define in_compat_syscall in_compat_syscall	/* override the generic impl */
+#define compat_need_64bit_alignment_fixup in_ia32_syscall
 #endif
 
 struct compat_siginfo;
diff --git a/include/linux/compat.h b/include/linux/compat.h
index d38c4d7e83bd..f0026a344482 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -932,6 +932,15 @@ static inline bool in_compat_syscall(void) { return false; }
 
 #endif /* CONFIG_COMPAT */
 
+/*
+ * Some legacy ABIs like the i386 one use less than natural alignment for 64-bit
+ * types, and will need special compat treatment for that.  Most architectures
+ * don't need that special handling even for compat syscalls.
+ */
+#ifndef compat_need_64bit_alignment_fixup
+#define compat_need_64bit_alignment_fixup()		false
+#endif
+
 /*
  * A pointer passed in from user mode. This should not
  * be used for syscall parameters, just declare them
-- 
cgit v1.2.3


From 80bdad3d7e3ec03f812471d9309f5f682e10f52b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 17 Sep 2020 09:41:59 +0200
Subject: quota: simplify the quotactl compat handling

Fold the misaligned u64 workarounds into the main quotactl flow instead
of implementing a separate compat syscall handler.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Jan Kara <jack@suse.cz>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/x86/entry/syscalls/syscall_32.tbl |   2 +-
 fs/quota/Kconfig                       |   5 --
 fs/quota/Makefile                      |   1 -
 fs/quota/compat.c                      | 120 ---------------------------------
 fs/quota/compat.h                      |  34 ++++++++++
 fs/quota/quota.c                       |  73 ++++++++++++++++----
 include/linux/quotaops.h               |   3 -
 kernel/sys_ni.c                        |   1 -
 8 files changed, 94 insertions(+), 145 deletions(-)
 delete mode 100644 fs/quota/compat.c
 create mode 100644 fs/quota/compat.h

(limited to 'include/linux')

diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 9d1102873666..3db3d8823dc8 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -142,7 +142,7 @@
 128	i386	init_module		sys_init_module
 129	i386	delete_module		sys_delete_module
 130	i386	get_kernel_syms
-131	i386	quotactl		sys_quotactl			compat_sys_quotactl32
+131	i386	quotactl		sys_quotactl
 132	i386	getpgid			sys_getpgid
 133	i386	fchdir			sys_fchdir
 134	i386	bdflush			sys_bdflush
diff --git a/fs/quota/Kconfig b/fs/quota/Kconfig
index d1ceb76adb71..b59cd172b5f9 100644
--- a/fs/quota/Kconfig
+++ b/fs/quota/Kconfig
@@ -70,8 +70,3 @@ config QFMT_V2
 config QUOTACTL
 	bool
 	default n
-
-config QUOTACTL_COMPAT
-	bool
-	depends on QUOTACTL && COMPAT_FOR_U64_ALIGNMENT
-	default y
diff --git a/fs/quota/Makefile b/fs/quota/Makefile
index f2b49d0f0287..9160639daffa 100644
--- a/fs/quota/Makefile
+++ b/fs/quota/Makefile
@@ -4,5 +4,4 @@ obj-$(CONFIG_QFMT_V1)		+= quota_v1.o
 obj-$(CONFIG_QFMT_V2)		+= quota_v2.o
 obj-$(CONFIG_QUOTA_TREE)	+= quota_tree.o
 obj-$(CONFIG_QUOTACTL)		+= quota.o kqid.o
-obj-$(CONFIG_QUOTACTL_COMPAT)	+= compat.o
 obj-$(CONFIG_QUOTA_NETLINK_INTERFACE)	+= netlink.o
diff --git a/fs/quota/compat.c b/fs/quota/compat.c
deleted file mode 100644
index c30572857619..000000000000
--- a/fs/quota/compat.c
+++ /dev/null
@@ -1,120 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
-#include <linux/syscalls.h>
-#include <linux/compat.h>
-#include <linux/quotaops.h>
-
-/*
- * This code works only for 32 bit quota tools over 64 bit OS (x86_64, ia64)
- * and is necessary due to alignment problems.
- */
-struct compat_if_dqblk {
-	compat_u64 dqb_bhardlimit;
-	compat_u64 dqb_bsoftlimit;
-	compat_u64 dqb_curspace;
-	compat_u64 dqb_ihardlimit;
-	compat_u64 dqb_isoftlimit;
-	compat_u64 dqb_curinodes;
-	compat_u64 dqb_btime;
-	compat_u64 dqb_itime;
-	compat_uint_t dqb_valid;
-};
-
-/* XFS structures */
-struct compat_fs_qfilestat {
-	compat_u64 dqb_bhardlimit;
-	compat_u64 qfs_nblks;
-	compat_uint_t qfs_nextents;
-};
-
-struct compat_fs_quota_stat {
-	__s8		qs_version;
-	__u16		qs_flags;
-	__s8		qs_pad;
-	struct compat_fs_qfilestat	qs_uquota;
-	struct compat_fs_qfilestat	qs_gquota;
-	compat_uint_t	qs_incoredqs;
-	compat_int_t	qs_btimelimit;
-	compat_int_t	qs_itimelimit;
-	compat_int_t	qs_rtbtimelimit;
-	__u16		qs_bwarnlimit;
-	__u16		qs_iwarnlimit;
-};
-
-COMPAT_SYSCALL_DEFINE4(quotactl32, unsigned int, cmd,
-		       const char __user *, special, qid_t, id,
-		       void __user *, addr)
-{
-	unsigned int cmds;
-	struct if_dqblk __user *dqblk;
-	struct compat_if_dqblk __user *compat_dqblk;
-	struct fs_quota_stat __user *fsqstat;
-	struct compat_fs_quota_stat __user *compat_fsqstat;
-	compat_uint_t data;
-	u16 xdata;
-	long ret;
-
-	cmds = cmd >> SUBCMDSHIFT;
-
-	switch (cmds) {
-	case Q_GETQUOTA:
-		dqblk = compat_alloc_user_space(sizeof(struct if_dqblk));
-		compat_dqblk = addr;
-		ret = kernel_quotactl(cmd, special, id, dqblk);
-		if (ret)
-			break;
-		if (copy_in_user(compat_dqblk, dqblk, sizeof(*compat_dqblk)) ||
-			get_user(data, &dqblk->dqb_valid) ||
-			put_user(data, &compat_dqblk->dqb_valid))
-			ret = -EFAULT;
-		break;
-	case Q_SETQUOTA:
-		dqblk = compat_alloc_user_space(sizeof(struct if_dqblk));
-		compat_dqblk = addr;
-		ret = -EFAULT;
-		if (copy_in_user(dqblk, compat_dqblk, sizeof(*compat_dqblk)) ||
-			get_user(data, &compat_dqblk->dqb_valid) ||
-			put_user(data, &dqblk->dqb_valid))
-			break;
-		ret = kernel_quotactl(cmd, special, id, dqblk);
-		break;
-	case Q_XGETQSTAT:
-		fsqstat = compat_alloc_user_space(sizeof(struct fs_quota_stat));
-		compat_fsqstat = addr;
-		ret = kernel_quotactl(cmd, special, id, fsqstat);
-		if (ret)
-			break;
-		ret = -EFAULT;
-		/* Copying qs_version, qs_flags, qs_pad */
-		if (copy_in_user(compat_fsqstat, fsqstat,
-			offsetof(struct compat_fs_quota_stat, qs_uquota)))
-			break;
-		/* Copying qs_uquota */
-		if (copy_in_user(&compat_fsqstat->qs_uquota,
-			&fsqstat->qs_uquota,
-			sizeof(compat_fsqstat->qs_uquota)) ||
-			get_user(data, &fsqstat->qs_uquota.qfs_nextents) ||
-			put_user(data, &compat_fsqstat->qs_uquota.qfs_nextents))
-			break;
-		/* Copying qs_gquota */
-		if (copy_in_user(&compat_fsqstat->qs_gquota,
-			&fsqstat->qs_gquota,
-			sizeof(compat_fsqstat->qs_gquota)) ||
-			get_user(data, &fsqstat->qs_gquota.qfs_nextents) ||
-			put_user(data, &compat_fsqstat->qs_gquota.qfs_nextents))
-			break;
-		/* Copying the rest */
-		if (copy_in_user(&compat_fsqstat->qs_incoredqs,
-			&fsqstat->qs_incoredqs,
-			sizeof(struct compat_fs_quota_stat) -
-			offsetof(struct compat_fs_quota_stat, qs_incoredqs)) ||
-			get_user(xdata, &fsqstat->qs_iwarnlimit) ||
-			put_user(xdata, &compat_fsqstat->qs_iwarnlimit))
-			break;
-		ret = 0;
-		break;
-	default:
-		ret = kernel_quotactl(cmd, special, id, addr);
-	}
-	return ret;
-}
diff --git a/fs/quota/compat.h b/fs/quota/compat.h
new file mode 100644
index 000000000000..ef7d1e12d650
--- /dev/null
+++ b/fs/quota/compat.h
@@ -0,0 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/compat.h>
+
+struct compat_if_dqblk {
+	compat_u64			dqb_bhardlimit;
+	compat_u64			dqb_bsoftlimit;
+	compat_u64			dqb_curspace;
+	compat_u64			dqb_ihardlimit;
+	compat_u64			dqb_isoftlimit;
+	compat_u64			dqb_curinodes;
+	compat_u64			dqb_btime;
+	compat_u64			dqb_itime;
+	compat_uint_t			dqb_valid;
+};
+
+struct compat_fs_qfilestat {
+	compat_u64			dqb_bhardlimit;
+	compat_u64			qfs_nblks;
+	compat_uint_t			qfs_nextents;
+};
+
+struct compat_fs_quota_stat {
+	__s8				qs_version;
+	__u16				qs_flags;
+	__s8				qs_pad;
+	struct compat_fs_qfilestat	qs_uquota;
+	struct compat_fs_qfilestat	qs_gquota;
+	compat_uint_t			qs_incoredqs;
+	compat_int_t			qs_btimelimit;
+	compat_int_t			qs_itimelimit;
+	compat_int_t			qs_rtbtimelimit;
+	__u16				qs_bwarnlimit;
+	__u16				qs_iwarnlimit;
+};
diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index 5444d3c4d93f..e1e9d05a14c3 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -19,6 +19,7 @@
 #include <linux/types.h>
 #include <linux/writeback.h>
 #include <linux/nospec.h>
+#include "compat.h"
 
 static int check_quotactl_permission(struct super_block *sb, int type, int cmd,
 				     qid_t id)
@@ -211,8 +212,18 @@ static int quota_getquota(struct super_block *sb, int type, qid_t id,
 	if (ret)
 		return ret;
 	copy_to_if_dqblk(&idq, &fdq);
-	if (copy_to_user(addr, &idq, sizeof(idq)))
-		return -EFAULT;
+
+	if (compat_need_64bit_alignment_fixup()) {
+		struct compat_if_dqblk __user *compat_dqblk = addr;
+
+		if (copy_to_user(compat_dqblk, &idq, sizeof(*compat_dqblk)))
+			return -EFAULT;
+		if (put_user(idq.dqb_valid, &compat_dqblk->dqb_valid))
+			return -EFAULT;
+	} else {
+		if (copy_to_user(addr, &idq, sizeof(idq)))
+			return -EFAULT;
+	}
 	return 0;
 }
 
@@ -277,8 +288,16 @@ static int quota_setquota(struct super_block *sb, int type, qid_t id,
 	struct if_dqblk idq;
 	struct kqid qid;
 
-	if (copy_from_user(&idq, addr, sizeof(idq)))
-		return -EFAULT;
+	if (compat_need_64bit_alignment_fixup()) {
+		struct compat_if_dqblk __user *compat_dqblk = addr;
+
+		if (copy_from_user(&idq, compat_dqblk, sizeof(*compat_dqblk)) ||
+		    get_user(idq.dqb_valid, &compat_dqblk->dqb_valid))
+			return -EFAULT;
+	} else {
+		if (copy_from_user(&idq, addr, sizeof(idq)))
+			return -EFAULT;
+	}
 	if (!sb->s_qcop->set_dqblk)
 		return -ENOSYS;
 	qid = make_kqid(current_user_ns(), type, id);
@@ -382,6 +401,33 @@ static int quota_getstate(struct super_block *sb, int type,
 	return 0;
 }
 
+static int compat_copy_fs_qfilestat(struct compat_fs_qfilestat __user *to,
+		struct fs_qfilestat *from)
+{
+	if (copy_to_user(to, from, sizeof(*to)) ||
+	    put_user(from->qfs_nextents, &to->qfs_nextents))
+		return -EFAULT;
+	return 0;
+}
+
+static int compat_copy_fs_quota_stat(struct compat_fs_quota_stat __user *to,
+		struct fs_quota_stat *from)
+{
+	if (put_user(from->qs_version, &to->qs_version) ||
+	    put_user(from->qs_flags, &to->qs_flags) ||
+	    put_user(from->qs_pad, &to->qs_pad) ||
+	    compat_copy_fs_qfilestat(&to->qs_uquota, &from->qs_uquota) ||
+	    compat_copy_fs_qfilestat(&to->qs_gquota, &from->qs_gquota) ||
+	    put_user(from->qs_incoredqs, &to->qs_incoredqs) ||
+	    put_user(from->qs_btimelimit, &to->qs_btimelimit) ||
+	    put_user(from->qs_itimelimit, &to->qs_itimelimit) ||
+	    put_user(from->qs_rtbtimelimit, &to->qs_rtbtimelimit) ||
+	    put_user(from->qs_bwarnlimit, &to->qs_bwarnlimit) ||
+	    put_user(from->qs_iwarnlimit, &to->qs_iwarnlimit))
+		return -EFAULT;
+	return 0;
+}
+
 static int quota_getxstate(struct super_block *sb, int type, void __user *addr)
 {
 	struct fs_quota_stat fqs;
@@ -390,9 +436,14 @@ static int quota_getxstate(struct super_block *sb, int type, void __user *addr)
 	if (!sb->s_qcop->get_state)
 		return -ENOSYS;
 	ret = quota_getstate(sb, type, &fqs);
-	if (!ret && copy_to_user(addr, &fqs, sizeof(fqs)))
+	if (ret)
+		return ret;
+
+	if (compat_need_64bit_alignment_fixup())
+		return compat_copy_fs_quota_stat(addr, &fqs);
+	if (copy_to_user(addr, &fqs, sizeof(fqs)))
 		return -EFAULT;
-	return ret;
+	return 0;
 }
 
 static int quota_getstatev(struct super_block *sb, int type,
@@ -816,8 +867,8 @@ static struct super_block *quotactl_block(const char __user *special, int cmd)
  * calls. Maybe we need to add the process quotas etc. in the future,
  * but we probably should use rlimits for that.
  */
-int kernel_quotactl(unsigned int cmd, const char __user *special,
-		    qid_t id, void __user *addr)
+SYSCALL_DEFINE4(quotactl, unsigned int, cmd, const char __user *, special,
+		qid_t, id, void __user *, addr)
 {
 	uint cmds, type;
 	struct super_block *sb = NULL;
@@ -871,9 +922,3 @@ out:
 		path_put(pathp);
 	return ret;
 }
-
-SYSCALL_DEFINE4(quotactl, unsigned int, cmd, const char __user *, special,
-		qid_t, id, void __user *, addr)
-{
-	return kernel_quotactl(cmd, special, id, addr);
-}
diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h
index 9cf0cd3dc88c..a0f6668924d3 100644
--- a/include/linux/quotaops.h
+++ b/include/linux/quotaops.h
@@ -27,9 +27,6 @@ static inline bool is_quota_modification(struct inode *inode, struct iattr *ia)
 		(ia->ia_valid & ATTR_GID && !gid_eq(ia->ia_gid, inode->i_gid));
 }
 
-int kernel_quotactl(unsigned int cmd, const char __user *special,
-		    qid_t id, void __user *addr);
-
 #if defined(CONFIG_QUOTA)
 
 #define quota_error(sb, fmt, args...) \
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 4d59775ea79c..c925d1e1777e 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -369,7 +369,6 @@ COND_SYSCALL_COMPAT(fanotify_mark);
 /* x86 */
 COND_SYSCALL(vm86old);
 COND_SYSCALL(modify_ldt);
-COND_SYSCALL_COMPAT(quotactl32);
 COND_SYSCALL(vm86);
 COND_SYSCALL(kexec_file_load);
 
-- 
cgit v1.2.3


From c7b6bac9c72c5fcbd6e9e12545bd3022c7f21860 Mon Sep 17 00:00:00 2001
From: Fenghua Yu <fenghua.yu@intel.com>
Date: Tue, 15 Sep 2020 09:30:05 -0700
Subject: drm, iommu: Change type of pasid to u32

PASID is defined as a few different types in iommu including "int",
"u32", and "unsigned int". To be consistent and to match with uapi
definitions, define PASID and its variations (e.g. max PASID) as "u32".
"u32" is also shorter and a little more explicit than "unsigned int".

No PASID type change in uapi although it defines PASID as __u64 in
some places.

Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Joerg Roedel <jroedel@suse.de>
Link: https://lkml.kernel.org/r/1600187413-163670-2-git-send-email-fenghua.yu@intel.com
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h         |  4 +--
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c  |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c  |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c  |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h  |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c   |  4 +--
 drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c            |  6 ++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h            |  4 +--
 drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c            |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c             |  8 +++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h             |  8 +++---
 drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c   |  2 +-
 drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c            |  2 +-
 drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.h            |  2 +-
 .../gpu/drm/amd/amdkfd/kfd_device_queue_manager.c  |  7 +++--
 drivers/gpu/drm/amd/amdkfd/kfd_events.c            |  8 +++---
 drivers/gpu/drm/amd/amdkfd/kfd_events.h            |  4 +--
 drivers/gpu/drm/amd/amdkfd/kfd_iommu.c             |  6 ++---
 drivers/gpu/drm/amd/amdkfd/kfd_pasid.c             |  4 +--
 drivers/gpu/drm/amd/amdkfd/kfd_priv.h              | 20 +++++++-------
 drivers/gpu/drm/amd/amdkfd/kfd_process.c           |  2 +-
 drivers/gpu/drm/amd/include/kgd_kfd_interface.h    |  2 +-
 drivers/iommu/amd/amd_iommu.h                      | 10 +++----
 drivers/iommu/amd/iommu.c                          | 31 +++++++++++-----------
 drivers/iommu/amd/iommu_v2.c                       | 20 +++++++-------
 drivers/iommu/intel/dmar.c                         |  7 ++---
 drivers/iommu/intel/iommu.c                        |  4 +--
 drivers/iommu/intel/pasid.c                        | 31 +++++++++++-----------
 drivers/iommu/intel/pasid.h                        | 24 ++++++++---------
 drivers/iommu/intel/svm.c                          | 12 ++++-----
 drivers/iommu/iommu.c                              |  2 +-
 drivers/misc/uacce/uacce.c                         |  2 +-
 include/linux/amd-iommu.h                          |  8 +++---
 include/linux/intel-iommu.h                        | 12 ++++-----
 include/linux/intel-svm.h                          |  2 +-
 include/linux/iommu.h                              | 10 +++----
 include/linux/uacce.h                              |  2 +-
 38 files changed, 141 insertions(+), 141 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index ffe149aafc39..dfef5a7e0f5a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -207,11 +207,11 @@ uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct kgd_dev *dst, struct kgd_dev *s
 	})
 
 /* GPUVM API */
-int amdgpu_amdkfd_gpuvm_create_process_vm(struct kgd_dev *kgd, unsigned int pasid,
+int amdgpu_amdkfd_gpuvm_create_process_vm(struct kgd_dev *kgd, u32 pasid,
 					void **vm, void **process_info,
 					struct dma_fence **ef);
 int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct kgd_dev *kgd,
-					struct file *filp, unsigned int pasid,
+					struct file *filp, u32 pasid,
 					void **vm, void **process_info,
 					struct dma_fence **ef);
 void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
index bf927f432506..ee531c3988d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
@@ -105,7 +105,7 @@ static void kgd_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid,
 	unlock_srbm(kgd);
 }
 
-static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
+static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, u32 pasid,
 					unsigned int vmid)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
index 744366c7ee85..4d41317b9292 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
@@ -139,7 +139,7 @@ static void kgd_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid,
 	unlock_srbm(kgd);
 }
 
-static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
+static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, u32 pasid,
 					unsigned int vmid)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
index feab4cc6e836..35917d4b50f6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
@@ -96,7 +96,7 @@ static void kgd_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid,
 	unlock_srbm(kgd);
 }
 
-static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
+static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, u32 pasid,
 					unsigned int vmid)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
index 1102de76d876..1abfe63c80fe 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
@@ -110,7 +110,7 @@ void kgd_gfx_v9_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid,
 	unlock_srbm(kgd);
 }
 
-int kgd_gfx_v9_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
+int kgd_gfx_v9_set_pasid_vmid_mapping(struct kgd_dev *kgd, u32 pasid,
 					unsigned int vmid)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h
index aedf67d57449..ff2bc72e6646 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h
@@ -26,7 +26,7 @@ void kgd_gfx_v9_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid,
 		uint32_t sh_mem_config,
 		uint32_t sh_mem_ape1_base, uint32_t sh_mem_ape1_limit,
 		uint32_t sh_mem_bases);
-int kgd_gfx_v9_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
+int kgd_gfx_v9_set_pasid_vmid_mapping(struct kgd_dev *kgd, u32 pasid,
 		unsigned int vmid);
 int kgd_gfx_v9_init_interrupts(struct kgd_dev *kgd, uint32_t pipe_id);
 int kgd_gfx_v9_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index a58af513c952..d02c5c177a98 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -992,7 +992,7 @@ create_evict_fence_fail:
 	return ret;
 }
 
-int amdgpu_amdkfd_gpuvm_create_process_vm(struct kgd_dev *kgd, unsigned int pasid,
+int amdgpu_amdkfd_gpuvm_create_process_vm(struct kgd_dev *kgd, u32 pasid,
 					  void **vm, void **process_info,
 					  struct dma_fence **ef)
 {
@@ -1028,7 +1028,7 @@ amdgpu_vm_init_fail:
 }
 
 int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct kgd_dev *kgd,
-					   struct file *filp, unsigned int pasid,
+					   struct file *filp, u32 pasid,
 					   void **vm, void **process_info,
 					   struct dma_fence **ef)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
index 7521f4ab55de..6e9a9e5dbea0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
@@ -43,7 +43,7 @@ static DEFINE_IDA(amdgpu_pasid_ida);
 /* Helper to free pasid from a fence callback */
 struct amdgpu_pasid_cb {
 	struct dma_fence_cb cb;
-	unsigned int pasid;
+	u32 pasid;
 };
 
 /**
@@ -79,7 +79,7 @@ int amdgpu_pasid_alloc(unsigned int bits)
  * amdgpu_pasid_free - Free a PASID
  * @pasid: PASID to free
  */
-void amdgpu_pasid_free(unsigned int pasid)
+void amdgpu_pasid_free(u32 pasid)
 {
 	trace_amdgpu_pasid_freed(pasid);
 	ida_simple_remove(&amdgpu_pasid_ida, pasid);
@@ -105,7 +105,7 @@ static void amdgpu_pasid_free_cb(struct dma_fence *fence,
  * Free the pasid only after all the fences in resv are signaled.
  */
 void amdgpu_pasid_free_delayed(struct dma_resv *resv,
-			       unsigned int pasid)
+			       u32 pasid)
 {
 	struct dma_fence *fence, **fences;
 	struct amdgpu_pasid_cb *cb;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h
index 8e58325bbca2..0c3b4fa1f936 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h
@@ -71,9 +71,9 @@ struct amdgpu_vmid_mgr {
 };
 
 int amdgpu_pasid_alloc(unsigned int bits);
-void amdgpu_pasid_free(unsigned int pasid);
+void amdgpu_pasid_free(u32 pasid);
 void amdgpu_pasid_free_delayed(struct dma_resv *resv,
-			       unsigned int pasid);
+			       u32 pasid);
 
 bool amdgpu_vmid_had_gpu_reset(struct amdgpu_device *adev,
 			       struct amdgpu_vmid *id);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 414548064648..b403b2a88ee5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -1084,7 +1084,7 @@ void amdgpu_driver_postclose_kms(struct drm_device *dev,
 	struct amdgpu_fpriv *fpriv = file_priv->driver_priv;
 	struct amdgpu_bo_list *list;
 	struct amdgpu_bo *pd;
-	unsigned int pasid;
+	u32 pasid;
 	int handle;
 
 	if (!fpriv)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 71e005cf2952..cb1d7cddebc3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -2785,7 +2785,7 @@ long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout)
  * 0 for success, error for failure.
  */
 int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
-		   int vm_context, unsigned int pasid)
+		   int vm_context, u32 pasid)
 {
 	struct amdgpu_bo_param bp;
 	struct amdgpu_bo *root;
@@ -2956,7 +2956,7 @@ static int amdgpu_vm_check_clean_reserved(struct amdgpu_device *adev,
  * 0 for success, -errno for errors.
  */
 int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm,
-			   unsigned int pasid)
+			   u32 pasid)
 {
 	bool pte_support_ats = (adev->asic_type == CHIP_RAVEN);
 	int r;
@@ -3254,7 +3254,7 @@ int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
  * @pasid: PASID identifier for VM
  * @task_info: task_info to fill.
  */
-void amdgpu_vm_get_task_info(struct amdgpu_device *adev, unsigned int pasid,
+void amdgpu_vm_get_task_info(struct amdgpu_device *adev, u32 pasid,
 			 struct amdgpu_task_info *task_info)
 {
 	struct amdgpu_vm *vm;
@@ -3298,7 +3298,7 @@ void amdgpu_vm_set_task_info(struct amdgpu_vm *vm)
  * Try to gracefully handle a VM fault. Return true if the fault was handled and
  * shouldn't be reported any more.
  */
-bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, unsigned int pasid,
+bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid,
 			    uint64_t addr)
 {
 	struct amdgpu_bo *root;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index 770025a5e500..ffbc0cc87ccf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -372,8 +372,8 @@ void amdgpu_vm_manager_fini(struct amdgpu_device *adev);
 
 long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout);
 int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
-		   int vm_context, unsigned int pasid);
-int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm, unsigned int pasid);
+		   int vm_context, u32 pasid);
+int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm, u32 pasid);
 void amdgpu_vm_release_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm);
 void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm);
 void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm,
@@ -430,9 +430,9 @@ bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring,
 				  struct amdgpu_job *job);
 void amdgpu_vm_check_compute_bug(struct amdgpu_device *adev);
 
-void amdgpu_vm_get_task_info(struct amdgpu_device *adev, unsigned int pasid,
+void amdgpu_vm_get_task_info(struct amdgpu_device *adev, u32 pasid,
 			     struct amdgpu_task_info *task_info);
-bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, unsigned int pasid,
+bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid,
 			    uint64_t addr);
 
 void amdgpu_vm_set_task_info(struct amdgpu_vm *vm);
diff --git a/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c b/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
index 24b471734117..dcb1d89d776e 100644
--- a/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
+++ b/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
@@ -91,7 +91,7 @@ static void cik_event_interrupt_wq(struct kfd_dev *dev,
 			(const struct cik_ih_ring_entry *)ih_ring_entry;
 	uint32_t context_id = ihre->data & 0xfffffff;
 	unsigned int vmid  = (ihre->ring_id & 0x0000ff00) >> 8;
-	unsigned int pasid = (ihre->ring_id & 0xffff0000) >> 16;
+	u32 pasid = (ihre->ring_id & 0xffff0000) >> 16;
 
 	if (pasid == 0)
 		return;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
index 27bcc5b472f6..b258a3dae767 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
@@ -45,7 +45,7 @@ static void dbgdev_address_watch_disable_nodiq(struct kfd_dev *dev)
 }
 
 static int dbgdev_diq_submit_ib(struct kfd_dbgdev *dbgdev,
-				unsigned int pasid, uint64_t vmid0_address,
+				u32 pasid, uint64_t vmid0_address,
 				uint32_t *packet_buff, size_t size_in_bytes)
 {
 	struct pm4__release_mem *rm_packet;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.h b/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.h
index a04a1fe1d0d9..f9c6df1fdc5c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.h
@@ -275,7 +275,7 @@ struct kfd_dbgdev {
 };
 
 struct kfd_dbgmgr {
-	unsigned int pasid;
+	u32 pasid;
 	struct kfd_dev *dev;
 	struct kfd_dbgdev *dbgdev;
 };
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index e0e60b0d0669..1ec2567abbf5 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -40,7 +40,7 @@
 #define CIK_HPD_EOP_BYTES (1U << CIK_HPD_EOP_BYTES_LOG2)
 
 static int set_pasid_vmid_mapping(struct device_queue_manager *dqm,
-					unsigned int pasid, unsigned int vmid);
+				  u32 pasid, unsigned int vmid);
 
 static int execute_queues_cpsch(struct device_queue_manager *dqm,
 				enum kfd_unmap_queues_filter filter,
@@ -948,7 +948,7 @@ out:
 }
 
 static int
-set_pasid_vmid_mapping(struct device_queue_manager *dqm, unsigned int pasid,
+set_pasid_vmid_mapping(struct device_queue_manager *dqm, u32 pasid,
 			unsigned int vmid)
 {
 	return dqm->dev->kfd2kgd->set_pasid_vmid_mapping(
@@ -1979,8 +1979,7 @@ void device_queue_manager_uninit(struct device_queue_manager *dqm)
 	kfree(dqm);
 }
 
-int kfd_process_vm_fault(struct device_queue_manager *dqm,
-			 unsigned int pasid)
+int kfd_process_vm_fault(struct device_queue_manager *dqm, u32 pasid)
 {
 	struct kfd_process_device *pdd;
 	struct kfd_process *p = kfd_lookup_process_by_pasid(pasid);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
index a9583b95fcc1..ba2c2ce0c55a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -460,7 +460,7 @@ static void set_event_from_interrupt(struct kfd_process *p,
 	}
 }
 
-void kfd_signal_event_interrupt(unsigned int pasid, uint32_t partial_id,
+void kfd_signal_event_interrupt(u32 pasid, uint32_t partial_id,
 				uint32_t valid_id_bits)
 {
 	struct kfd_event *ev = NULL;
@@ -872,7 +872,7 @@ static void lookup_events_by_type_and_signal(struct kfd_process *p,
 }
 
 #ifdef KFD_SUPPORT_IOMMU_V2
-void kfd_signal_iommu_event(struct kfd_dev *dev, unsigned int pasid,
+void kfd_signal_iommu_event(struct kfd_dev *dev, u32 pasid,
 		unsigned long address, bool is_write_requested,
 		bool is_execute_requested)
 {
@@ -950,7 +950,7 @@ void kfd_signal_iommu_event(struct kfd_dev *dev, unsigned int pasid,
 }
 #endif /* KFD_SUPPORT_IOMMU_V2 */
 
-void kfd_signal_hw_exception_event(unsigned int pasid)
+void kfd_signal_hw_exception_event(u32 pasid)
 {
 	/*
 	 * Because we are called from arbitrary context (workqueue) as opposed
@@ -971,7 +971,7 @@ void kfd_signal_hw_exception_event(unsigned int pasid)
 	kfd_unref_process(p);
 }
 
-void kfd_signal_vm_fault_event(struct kfd_dev *dev, unsigned int pasid,
+void kfd_signal_vm_fault_event(struct kfd_dev *dev, u32 pasid,
 				struct kfd_vm_fault_info *info)
 {
 	struct kfd_event *ev;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.h b/drivers/gpu/drm/amd/amdkfd/kfd_events.h
index c7ac6c73af86..c8fe5dbdad55 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.h
@@ -79,7 +79,7 @@ struct kfd_event {
 #define KFD_EVENT_TYPE_DEBUG 5
 #define KFD_EVENT_TYPE_MEMORY 8
 
-extern void kfd_signal_event_interrupt(unsigned int pasid, uint32_t partial_id,
-					uint32_t valid_id_bits);
+extern void kfd_signal_event_interrupt(u32 pasid, uint32_t partial_id,
+				       uint32_t valid_id_bits);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
index 7c8786b9eb0a..e8ef3886688b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
@@ -139,7 +139,7 @@ void kfd_iommu_unbind_process(struct kfd_process *p)
 }
 
 /* Callback for process shutdown invoked by the IOMMU driver */
-static void iommu_pasid_shutdown_callback(struct pci_dev *pdev, int pasid)
+static void iommu_pasid_shutdown_callback(struct pci_dev *pdev, u32 pasid)
 {
 	struct kfd_dev *dev = kfd_device_by_pci_dev(pdev);
 	struct kfd_process *p;
@@ -185,8 +185,8 @@ static void iommu_pasid_shutdown_callback(struct pci_dev *pdev, int pasid)
 }
 
 /* This function called by IOMMU driver on PPR failure */
-static int iommu_invalid_ppr_cb(struct pci_dev *pdev, int pasid,
-		unsigned long address, u16 flags)
+static int iommu_invalid_ppr_cb(struct pci_dev *pdev, u32 pasid,
+				unsigned long address, u16 flags)
 {
 	struct kfd_dev *dev;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c b/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c
index 2a07c4f2cd0d..af5816f51e55 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c
@@ -51,7 +51,7 @@ unsigned int kfd_get_pasid_limit(void)
 	return 1U << pasid_bits;
 }
 
-unsigned int kfd_pasid_alloc(void)
+u32 kfd_pasid_alloc(void)
 {
 	int r = amdgpu_pasid_alloc(pasid_bits);
 
@@ -63,7 +63,7 @@ unsigned int kfd_pasid_alloc(void)
 	return 0;
 }
 
-void kfd_pasid_free(unsigned int pasid)
+void kfd_pasid_free(u32 pasid)
 {
 	amdgpu_pasid_free(pasid);
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 6727e9de5b8b..922ae138ab85 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -723,7 +723,7 @@ struct kfd_process {
 	/* We want to receive a notification when the mm_struct is destroyed */
 	struct mmu_notifier mmu_notifier;
 
-	uint16_t pasid;
+	u32 pasid;
 	unsigned int doorbell_index;
 
 	/*
@@ -800,7 +800,7 @@ int kfd_process_create_wq(void);
 void kfd_process_destroy_wq(void);
 struct kfd_process *kfd_create_process(struct file *filep);
 struct kfd_process *kfd_get_process(const struct task_struct *);
-struct kfd_process *kfd_lookup_process_by_pasid(unsigned int pasid);
+struct kfd_process *kfd_lookup_process_by_pasid(u32 pasid);
 struct kfd_process *kfd_lookup_process_by_mm(const struct mm_struct *mm);
 void kfd_unref_process(struct kfd_process *p);
 int kfd_process_evict_queues(struct kfd_process *p);
@@ -841,8 +841,8 @@ int kfd_pasid_init(void);
 void kfd_pasid_exit(void);
 bool kfd_set_pasid_limit(unsigned int new_limit);
 unsigned int kfd_get_pasid_limit(void);
-unsigned int kfd_pasid_alloc(void);
-void kfd_pasid_free(unsigned int pasid);
+u32 kfd_pasid_alloc(void);
+void kfd_pasid_free(u32 pasid);
 
 /* Doorbells */
 size_t kfd_doorbell_process_slice(struct kfd_dev *kfd);
@@ -927,7 +927,7 @@ void device_queue_manager_uninit(struct device_queue_manager *dqm);
 struct kernel_queue *kernel_queue_init(struct kfd_dev *dev,
 					enum kfd_queue_type type);
 void kernel_queue_uninit(struct kernel_queue *kq, bool hanging);
-int kfd_process_vm_fault(struct device_queue_manager *dqm, unsigned int pasid);
+int kfd_process_vm_fault(struct device_queue_manager *dqm, u32 pasid);
 
 /* Process Queue Manager */
 struct process_queue_node {
@@ -1049,12 +1049,12 @@ int kfd_wait_on_events(struct kfd_process *p,
 		       uint32_t num_events, void __user *data,
 		       bool all, uint32_t user_timeout_ms,
 		       uint32_t *wait_result);
-void kfd_signal_event_interrupt(unsigned int pasid, uint32_t partial_id,
+void kfd_signal_event_interrupt(u32 pasid, uint32_t partial_id,
 				uint32_t valid_id_bits);
 void kfd_signal_iommu_event(struct kfd_dev *dev,
-		unsigned int pasid, unsigned long address,
-		bool is_write_requested, bool is_execute_requested);
-void kfd_signal_hw_exception_event(unsigned int pasid);
+			    u32 pasid, unsigned long address,
+			    bool is_write_requested, bool is_execute_requested);
+void kfd_signal_hw_exception_event(u32 pasid);
 int kfd_set_event(struct kfd_process *p, uint32_t event_id);
 int kfd_reset_event(struct kfd_process *p, uint32_t event_id);
 int kfd_event_page_set(struct kfd_process *p, void *kernel_address,
@@ -1065,7 +1065,7 @@ int kfd_event_create(struct file *devkfd, struct kfd_process *p,
 		     uint64_t *event_page_offset, uint32_t *event_slot_index);
 int kfd_event_destroy(struct kfd_process *p, uint32_t event_id);
 
-void kfd_signal_vm_fault_event(struct kfd_dev *dev, unsigned int pasid,
+void kfd_signal_vm_fault_event(struct kfd_dev *dev, u32 pasid,
 				struct kfd_vm_fault_info *info);
 
 void kfd_signal_reset_event(struct kfd_dev *dev);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 40695d52e9a8..627793029033 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -1306,7 +1306,7 @@ void kfd_process_device_remove_obj_handle(struct kfd_process_device *pdd,
 }
 
 /* This increments the process->ref counter. */
-struct kfd_process *kfd_lookup_process_by_pasid(unsigned int pasid)
+struct kfd_process *kfd_lookup_process_by_pasid(u32 pasid)
 {
 	struct kfd_process *p, *ret_p = NULL;
 	unsigned int temp;
diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
index a3c238c39ef5..301de493377a 100644
--- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
@@ -226,7 +226,7 @@ struct kfd2kgd_calls {
 			uint32_t sh_mem_config,	uint32_t sh_mem_ape1_base,
 			uint32_t sh_mem_ape1_limit, uint32_t sh_mem_bases);
 
-	int (*set_pasid_vmid_mapping)(struct kgd_dev *kgd, unsigned int pasid,
+	int (*set_pasid_vmid_mapping)(struct kgd_dev *kgd, u32 pasid,
 					unsigned int vmid);
 
 	int (*init_interrupts)(struct kgd_dev *kgd, uint32_t pipe_id);
diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h
index 57309716fd18..030ee90197a1 100644
--- a/drivers/iommu/amd/amd_iommu.h
+++ b/drivers/iommu/amd/amd_iommu.h
@@ -45,12 +45,12 @@ extern int amd_iommu_register_ppr_notifier(struct notifier_block *nb);
 extern int amd_iommu_unregister_ppr_notifier(struct notifier_block *nb);
 extern void amd_iommu_domain_direct_map(struct iommu_domain *dom);
 extern int amd_iommu_domain_enable_v2(struct iommu_domain *dom, int pasids);
-extern int amd_iommu_flush_page(struct iommu_domain *dom, int pasid,
+extern int amd_iommu_flush_page(struct iommu_domain *dom, u32 pasid,
 				u64 address);
-extern int amd_iommu_flush_tlb(struct iommu_domain *dom, int pasid);
-extern int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, int pasid,
+extern int amd_iommu_flush_tlb(struct iommu_domain *dom, u32 pasid);
+extern int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, u32 pasid,
 				     unsigned long cr3);
-extern int amd_iommu_domain_clear_gcr3(struct iommu_domain *dom, int pasid);
+extern int amd_iommu_domain_clear_gcr3(struct iommu_domain *dom, u32 pasid);
 extern struct iommu_domain *amd_iommu_get_v2_domain(struct pci_dev *pdev);
 
 #ifdef CONFIG_IRQ_REMAP
@@ -66,7 +66,7 @@ static inline int amd_iommu_create_irq_domain(struct amd_iommu *iommu)
 #define PPR_INVALID			0x1
 #define PPR_FAILURE			0xf
 
-extern int amd_iommu_complete_ppr(struct pci_dev *pdev, int pasid,
+extern int amd_iommu_complete_ppr(struct pci_dev *pdev, u32 pasid,
 				  int status, int tag);
 
 static inline bool is_rd890_iommu(struct pci_dev *pdev)
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 07ae8b93887e..a21c717e107d 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -513,10 +513,11 @@ static void amd_iommu_report_page_fault(u16 devid, u16 domain_id,
 static void iommu_print_event(struct amd_iommu *iommu, void *__evt)
 {
 	struct device *dev = iommu->iommu.dev;
-	int type, devid, pasid, flags, tag;
+	int type, devid, flags, tag;
 	volatile u32 *event = __evt;
 	int count = 0;
 	u64 address;
+	u32 pasid;
 
 retry:
 	type    = (event[1] >> EVENT_TYPE_SHIFT)  & EVENT_TYPE_MASK;
@@ -909,7 +910,7 @@ static void build_inv_iotlb_pages(struct iommu_cmd *cmd, u16 devid, int qdep,
 		cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK;
 }
 
-static void build_inv_iommu_pasid(struct iommu_cmd *cmd, u16 domid, int pasid,
+static void build_inv_iommu_pasid(struct iommu_cmd *cmd, u16 domid, u32 pasid,
 				  u64 address, bool size)
 {
 	memset(cmd, 0, sizeof(*cmd));
@@ -927,7 +928,7 @@ static void build_inv_iommu_pasid(struct iommu_cmd *cmd, u16 domid, int pasid,
 	CMD_SET_TYPE(cmd, CMD_INV_IOMMU_PAGES);
 }
 
-static void build_inv_iotlb_pasid(struct iommu_cmd *cmd, u16 devid, int pasid,
+static void build_inv_iotlb_pasid(struct iommu_cmd *cmd, u16 devid, u32 pasid,
 				  int qdep, u64 address, bool size)
 {
 	memset(cmd, 0, sizeof(*cmd));
@@ -947,7 +948,7 @@ static void build_inv_iotlb_pasid(struct iommu_cmd *cmd, u16 devid, int pasid,
 	CMD_SET_TYPE(cmd, CMD_INV_IOTLB_PAGES);
 }
 
-static void build_complete_ppr(struct iommu_cmd *cmd, u16 devid, int pasid,
+static void build_complete_ppr(struct iommu_cmd *cmd, u16 devid, u32 pasid,
 			       int status, int tag, bool gn)
 {
 	memset(cmd, 0, sizeof(*cmd));
@@ -2786,7 +2787,7 @@ out:
 }
 EXPORT_SYMBOL(amd_iommu_domain_enable_v2);
 
-static int __flush_pasid(struct protection_domain *domain, int pasid,
+static int __flush_pasid(struct protection_domain *domain, u32 pasid,
 			 u64 address, bool size)
 {
 	struct iommu_dev_data *dev_data;
@@ -2847,13 +2848,13 @@ out:
 	return ret;
 }
 
-static int __amd_iommu_flush_page(struct protection_domain *domain, int pasid,
+static int __amd_iommu_flush_page(struct protection_domain *domain, u32 pasid,
 				  u64 address)
 {
 	return __flush_pasid(domain, pasid, address, false);
 }
 
-int amd_iommu_flush_page(struct iommu_domain *dom, int pasid,
+int amd_iommu_flush_page(struct iommu_domain *dom, u32 pasid,
 			 u64 address)
 {
 	struct protection_domain *domain = to_pdomain(dom);
@@ -2868,13 +2869,13 @@ int amd_iommu_flush_page(struct iommu_domain *dom, int pasid,
 }
 EXPORT_SYMBOL(amd_iommu_flush_page);
 
-static int __amd_iommu_flush_tlb(struct protection_domain *domain, int pasid)
+static int __amd_iommu_flush_tlb(struct protection_domain *domain, u32 pasid)
 {
 	return __flush_pasid(domain, pasid, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
 			     true);
 }
 
-int amd_iommu_flush_tlb(struct iommu_domain *dom, int pasid)
+int amd_iommu_flush_tlb(struct iommu_domain *dom, u32 pasid)
 {
 	struct protection_domain *domain = to_pdomain(dom);
 	unsigned long flags;
@@ -2888,7 +2889,7 @@ int amd_iommu_flush_tlb(struct iommu_domain *dom, int pasid)
 }
 EXPORT_SYMBOL(amd_iommu_flush_tlb);
 
-static u64 *__get_gcr3_pte(u64 *root, int level, int pasid, bool alloc)
+static u64 *__get_gcr3_pte(u64 *root, int level, u32 pasid, bool alloc)
 {
 	int index;
 	u64 *pte;
@@ -2920,7 +2921,7 @@ static u64 *__get_gcr3_pte(u64 *root, int level, int pasid, bool alloc)
 	return pte;
 }
 
-static int __set_gcr3(struct protection_domain *domain, int pasid,
+static int __set_gcr3(struct protection_domain *domain, u32 pasid,
 		      unsigned long cr3)
 {
 	struct domain_pgtable pgtable;
@@ -2939,7 +2940,7 @@ static int __set_gcr3(struct protection_domain *domain, int pasid,
 	return __amd_iommu_flush_tlb(domain, pasid);
 }
 
-static int __clear_gcr3(struct protection_domain *domain, int pasid)
+static int __clear_gcr3(struct protection_domain *domain, u32 pasid)
 {
 	struct domain_pgtable pgtable;
 	u64 *pte;
@@ -2957,7 +2958,7 @@ static int __clear_gcr3(struct protection_domain *domain, int pasid)
 	return __amd_iommu_flush_tlb(domain, pasid);
 }
 
-int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, int pasid,
+int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, u32 pasid,
 			      unsigned long cr3)
 {
 	struct protection_domain *domain = to_pdomain(dom);
@@ -2972,7 +2973,7 @@ int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, int pasid,
 }
 EXPORT_SYMBOL(amd_iommu_domain_set_gcr3);
 
-int amd_iommu_domain_clear_gcr3(struct iommu_domain *dom, int pasid)
+int amd_iommu_domain_clear_gcr3(struct iommu_domain *dom, u32 pasid)
 {
 	struct protection_domain *domain = to_pdomain(dom);
 	unsigned long flags;
@@ -2986,7 +2987,7 @@ int amd_iommu_domain_clear_gcr3(struct iommu_domain *dom, int pasid)
 }
 EXPORT_SYMBOL(amd_iommu_domain_clear_gcr3);
 
-int amd_iommu_complete_ppr(struct pci_dev *pdev, int pasid,
+int amd_iommu_complete_ppr(struct pci_dev *pdev, u32 pasid,
 			   int status, int tag)
 {
 	struct iommu_dev_data *dev_data;
diff --git a/drivers/iommu/amd/iommu_v2.c b/drivers/iommu/amd/iommu_v2.c
index 0d175aed1d92..5ecc0bc608ec 100644
--- a/drivers/iommu/amd/iommu_v2.c
+++ b/drivers/iommu/amd/iommu_v2.c
@@ -40,7 +40,7 @@ struct pasid_state {
 	struct mmu_notifier mn;                 /* mmu_notifier handle */
 	struct pri_queue pri[PRI_QUEUE_SIZE];	/* PRI tag states */
 	struct device_state *device_state;	/* Link to our device_state */
-	int pasid;				/* PASID index */
+	u32 pasid;				/* PASID index */
 	bool invalid;				/* Used during setup and
 						   teardown of the pasid */
 	spinlock_t lock;			/* Protect pri_queues and
@@ -70,7 +70,7 @@ struct fault {
 	struct mm_struct *mm;
 	u64 address;
 	u16 devid;
-	u16 pasid;
+	u32 pasid;
 	u16 tag;
 	u16 finish;
 	u16 flags;
@@ -150,7 +150,7 @@ static void put_device_state(struct device_state *dev_state)
 
 /* Must be called under dev_state->lock */
 static struct pasid_state **__get_pasid_state_ptr(struct device_state *dev_state,
-						  int pasid, bool alloc)
+						  u32 pasid, bool alloc)
 {
 	struct pasid_state **root, **ptr;
 	int level, index;
@@ -184,7 +184,7 @@ static struct pasid_state **__get_pasid_state_ptr(struct device_state *dev_state
 
 static int set_pasid_state(struct device_state *dev_state,
 			   struct pasid_state *pasid_state,
-			   int pasid)
+			   u32 pasid)
 {
 	struct pasid_state **ptr;
 	unsigned long flags;
@@ -211,7 +211,7 @@ out_unlock:
 	return ret;
 }
 
-static void clear_pasid_state(struct device_state *dev_state, int pasid)
+static void clear_pasid_state(struct device_state *dev_state, u32 pasid)
 {
 	struct pasid_state **ptr;
 	unsigned long flags;
@@ -229,7 +229,7 @@ out_unlock:
 }
 
 static struct pasid_state *get_pasid_state(struct device_state *dev_state,
-					   int pasid)
+					   u32 pasid)
 {
 	struct pasid_state **ptr, *ret = NULL;
 	unsigned long flags;
@@ -594,7 +594,7 @@ static struct notifier_block ppr_nb = {
 	.notifier_call = ppr_notifier,
 };
 
-int amd_iommu_bind_pasid(struct pci_dev *pdev, int pasid,
+int amd_iommu_bind_pasid(struct pci_dev *pdev, u32 pasid,
 			 struct task_struct *task)
 {
 	struct pasid_state *pasid_state;
@@ -615,7 +615,7 @@ int amd_iommu_bind_pasid(struct pci_dev *pdev, int pasid,
 		return -EINVAL;
 
 	ret = -EINVAL;
-	if (pasid < 0 || pasid >= dev_state->max_pasids)
+	if (pasid >= dev_state->max_pasids)
 		goto out;
 
 	ret = -ENOMEM;
@@ -679,7 +679,7 @@ out:
 }
 EXPORT_SYMBOL(amd_iommu_bind_pasid);
 
-void amd_iommu_unbind_pasid(struct pci_dev *pdev, int pasid)
+void amd_iommu_unbind_pasid(struct pci_dev *pdev, u32 pasid)
 {
 	struct pasid_state *pasid_state;
 	struct device_state *dev_state;
@@ -695,7 +695,7 @@ void amd_iommu_unbind_pasid(struct pci_dev *pdev, int pasid)
 	if (dev_state == NULL)
 		return;
 
-	if (pasid < 0 || pasid >= dev_state->max_pasids)
+	if (pasid >= dev_state->max_pasids)
 		goto out;
 
 	pasid_state = get_pasid_state(dev_state, pasid);
diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
index 93e6345f3414..e4cfa7355fc6 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -1482,7 +1482,7 @@ void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid,
 }
 
 void qi_flush_pasid_cache(struct intel_iommu *iommu, u16 did,
-			  u64 granu, int pasid)
+			  u64 granu, u32 pasid)
 {
 	struct qi_desc desc = {.qw1 = 0, .qw2 = 0, .qw3 = 0};
 
@@ -1796,7 +1796,7 @@ void dmar_msi_read(int irq, struct msi_msg *msg)
 }
 
 static int dmar_fault_do_one(struct intel_iommu *iommu, int type,
-		u8 fault_reason, int pasid, u16 source_id,
+		u8 fault_reason, u32 pasid, u16 source_id,
 		unsigned long long addr)
 {
 	const char *reason;
@@ -1846,7 +1846,8 @@ irqreturn_t dmar_fault(int irq, void *dev_id)
 		u8 fault_reason;
 		u16 source_id;
 		u64 guest_addr;
-		int type, pasid;
+		u32 pasid;
+		int type;
 		u32 data;
 		bool pasid_present;
 
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 87b17bac04c2..44bb6fda4755 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -2527,7 +2527,7 @@ dmar_search_domain_by_dev_info(int segment, int bus, int devfn)
 static int domain_setup_first_level(struct intel_iommu *iommu,
 				    struct dmar_domain *domain,
 				    struct device *dev,
-				    int pasid)
+				    u32 pasid)
 {
 	int flags = PASID_FLAG_SUPERVISOR_MODE;
 	struct dma_pte *pgd = domain->pgd;
@@ -5173,7 +5173,7 @@ static int aux_domain_add_dev(struct dmar_domain *domain,
 		return -ENODEV;
 
 	if (domain->default_pasid <= 0) {
-		int pasid;
+		u32 pasid;
 
 		/* No private data needed for the default pasid */
 		pasid = ioasid_alloc(NULL, PASID_MIN,
diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c
index e6faedf42fd4..b92af83b79bd 100644
--- a/drivers/iommu/intel/pasid.c
+++ b/drivers/iommu/intel/pasid.c
@@ -27,7 +27,7 @@
 static DEFINE_SPINLOCK(pasid_lock);
 u32 intel_pasid_max_id = PASID_MAX;
 
-int vcmd_alloc_pasid(struct intel_iommu *iommu, unsigned int *pasid)
+int vcmd_alloc_pasid(struct intel_iommu *iommu, u32 *pasid)
 {
 	unsigned long flags;
 	u8 status_code;
@@ -58,7 +58,7 @@ int vcmd_alloc_pasid(struct intel_iommu *iommu, unsigned int *pasid)
 	return ret;
 }
 
-void vcmd_free_pasid(struct intel_iommu *iommu, unsigned int pasid)
+void vcmd_free_pasid(struct intel_iommu *iommu, u32 pasid)
 {
 	unsigned long flags;
 	u8 status_code;
@@ -146,7 +146,7 @@ int intel_pasid_alloc_table(struct device *dev)
 	struct pasid_table *pasid_table;
 	struct pasid_table_opaque data;
 	struct page *pages;
-	int max_pasid = 0;
+	u32 max_pasid = 0;
 	int ret, order;
 	int size;
 
@@ -168,7 +168,7 @@ int intel_pasid_alloc_table(struct device *dev)
 	INIT_LIST_HEAD(&pasid_table->dev);
 
 	if (info->pasid_supported)
-		max_pasid = min_t(int, pci_max_pasids(to_pci_dev(dev)),
+		max_pasid = min_t(u32, pci_max_pasids(to_pci_dev(dev)),
 				  intel_pasid_max_id);
 
 	size = max_pasid >> (PASID_PDE_SHIFT - 3);
@@ -242,7 +242,7 @@ int intel_pasid_get_dev_max_id(struct device *dev)
 	return info->pasid_table->max_pasid;
 }
 
-struct pasid_entry *intel_pasid_get_entry(struct device *dev, int pasid)
+struct pasid_entry *intel_pasid_get_entry(struct device *dev, u32 pasid)
 {
 	struct device_domain_info *info;
 	struct pasid_table *pasid_table;
@@ -251,8 +251,7 @@ struct pasid_entry *intel_pasid_get_entry(struct device *dev, int pasid)
 	int dir_index, index;
 
 	pasid_table = intel_pasid_get_table(dev);
-	if (WARN_ON(!pasid_table || pasid < 0 ||
-		    pasid >= intel_pasid_get_dev_max_id(dev)))
+	if (WARN_ON(!pasid_table || pasid >= intel_pasid_get_dev_max_id(dev)))
 		return NULL;
 
 	dir = pasid_table->table;
@@ -305,7 +304,7 @@ static inline void pasid_clear_entry_with_fpd(struct pasid_entry *pe)
 }
 
 static void
-intel_pasid_clear_entry(struct device *dev, int pasid, bool fault_ignore)
+intel_pasid_clear_entry(struct device *dev, u32 pasid, bool fault_ignore)
 {
 	struct pasid_entry *pe;
 
@@ -444,7 +443,7 @@ pasid_set_eafe(struct pasid_entry *pe)
 
 static void
 pasid_cache_invalidation_with_pasid(struct intel_iommu *iommu,
-				    u16 did, int pasid)
+				    u16 did, u32 pasid)
 {
 	struct qi_desc desc;
 
@@ -473,7 +472,7 @@ iotlb_invalidation_with_pasid(struct intel_iommu *iommu, u16 did, u32 pasid)
 
 static void
 devtlb_invalidation_with_pasid(struct intel_iommu *iommu,
-			       struct device *dev, int pasid)
+			       struct device *dev, u32 pasid)
 {
 	struct device_domain_info *info;
 	u16 sid, qdep, pfsid;
@@ -499,7 +498,7 @@ devtlb_invalidation_with_pasid(struct intel_iommu *iommu,
 }
 
 void intel_pasid_tear_down_entry(struct intel_iommu *iommu, struct device *dev,
-				 int pasid, bool fault_ignore)
+				 u32 pasid, bool fault_ignore)
 {
 	struct pasid_entry *pte;
 	u16 did;
@@ -524,7 +523,7 @@ void intel_pasid_tear_down_entry(struct intel_iommu *iommu, struct device *dev,
 
 static void pasid_flush_caches(struct intel_iommu *iommu,
 				struct pasid_entry *pte,
-				int pasid, u16 did)
+			       u32 pasid, u16 did)
 {
 	if (!ecap_coherent(iommu->ecap))
 		clflush_cache_range(pte, sizeof(*pte));
@@ -543,7 +542,7 @@ static void pasid_flush_caches(struct intel_iommu *iommu,
  */
 int intel_pasid_setup_first_level(struct intel_iommu *iommu,
 				  struct device *dev, pgd_t *pgd,
-				  int pasid, u16 did, int flags)
+				  u32 pasid, u16 did, int flags)
 {
 	struct pasid_entry *pte;
 
@@ -616,7 +615,7 @@ static inline int iommu_skip_agaw(struct dmar_domain *domain,
  */
 int intel_pasid_setup_second_level(struct intel_iommu *iommu,
 				   struct dmar_domain *domain,
-				   struct device *dev, int pasid)
+				   struct device *dev, u32 pasid)
 {
 	struct pasid_entry *pte;
 	struct dma_pte *pgd;
@@ -674,7 +673,7 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu,
  */
 int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
 				   struct dmar_domain *domain,
-				   struct device *dev, int pasid)
+				   struct device *dev, u32 pasid)
 {
 	u16 did = FLPT_DEFAULT_DID;
 	struct pasid_entry *pte;
@@ -760,7 +759,7 @@ intel_pasid_setup_bind_data(struct intel_iommu *iommu, struct pasid_entry *pte,
  * @addr_width: Address width of the first level (guest)
  */
 int intel_pasid_setup_nested(struct intel_iommu *iommu, struct device *dev,
-			     pgd_t *gpgd, int pasid,
+			     pgd_t *gpgd, u32 pasid,
 			     struct iommu_gpasid_bind_data_vtd *pasid_data,
 			     struct dmar_domain *domain, int addr_width)
 {
diff --git a/drivers/iommu/intel/pasid.h b/drivers/iommu/intel/pasid.h
index c9850766c3a9..97dfcffbf495 100644
--- a/drivers/iommu/intel/pasid.h
+++ b/drivers/iommu/intel/pasid.h
@@ -72,7 +72,7 @@ struct pasid_entry {
 struct pasid_table {
 	void			*table;		/* pasid table pointer */
 	int			order;		/* page order of pasid table */
-	int			max_pasid;	/* max pasid */
+	u32			max_pasid;	/* max pasid */
 	struct list_head	dev;		/* device list */
 };
 
@@ -98,31 +98,31 @@ static inline bool pasid_pte_is_present(struct pasid_entry *pte)
 	return READ_ONCE(pte->val[0]) & PASID_PTE_PRESENT;
 }
 
-extern u32 intel_pasid_max_id;
+extern unsigned int intel_pasid_max_id;
 int intel_pasid_alloc_id(void *ptr, int start, int end, gfp_t gfp);
-void intel_pasid_free_id(int pasid);
-void *intel_pasid_lookup_id(int pasid);
+void intel_pasid_free_id(u32 pasid);
+void *intel_pasid_lookup_id(u32 pasid);
 int intel_pasid_alloc_table(struct device *dev);
 void intel_pasid_free_table(struct device *dev);
 struct pasid_table *intel_pasid_get_table(struct device *dev);
 int intel_pasid_get_dev_max_id(struct device *dev);
-struct pasid_entry *intel_pasid_get_entry(struct device *dev, int pasid);
+struct pasid_entry *intel_pasid_get_entry(struct device *dev, u32 pasid);
 int intel_pasid_setup_first_level(struct intel_iommu *iommu,
 				  struct device *dev, pgd_t *pgd,
-				  int pasid, u16 did, int flags);
+				  u32 pasid, u16 did, int flags);
 int intel_pasid_setup_second_level(struct intel_iommu *iommu,
 				   struct dmar_domain *domain,
-				   struct device *dev, int pasid);
+				   struct device *dev, u32 pasid);
 int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
 				   struct dmar_domain *domain,
-				   struct device *dev, int pasid);
+				   struct device *dev, u32 pasid);
 int intel_pasid_setup_nested(struct intel_iommu *iommu,
-			     struct device *dev, pgd_t *pgd, int pasid,
+			     struct device *dev, pgd_t *pgd, u32 pasid,
 			     struct iommu_gpasid_bind_data_vtd *pasid_data,
 			     struct dmar_domain *domain, int addr_width);
 void intel_pasid_tear_down_entry(struct intel_iommu *iommu,
-				 struct device *dev, int pasid,
+				 struct device *dev, u32 pasid,
 				 bool fault_ignore);
-int vcmd_alloc_pasid(struct intel_iommu *iommu, unsigned int *pasid);
-void vcmd_free_pasid(struct intel_iommu *iommu, unsigned int pasid);
+int vcmd_alloc_pasid(struct intel_iommu *iommu, u32 *pasid);
+void vcmd_free_pasid(struct intel_iommu *iommu, u32 pasid);
 #endif /* __INTEL_PASID_H */
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index 95c3164a2302..e78a74a9c1cf 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -23,7 +23,7 @@
 #include "pasid.h"
 
 static irqreturn_t prq_event_thread(int irq, void *d);
-static void intel_svm_drain_prq(struct device *dev, int pasid);
+static void intel_svm_drain_prq(struct device *dev, u32 pasid);
 
 #define PRQ_ORDER 0
 
@@ -399,7 +399,7 @@ int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev,
 	return ret;
 }
 
-int intel_svm_unbind_gpasid(struct device *dev, int pasid)
+int intel_svm_unbind_gpasid(struct device *dev, u32 pasid)
 {
 	struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL);
 	struct intel_svm_dev *sdev;
@@ -620,7 +620,7 @@ out:
 }
 
 /* Caller must hold pasid_mutex */
-static int intel_svm_unbind_mm(struct device *dev, int pasid)
+static int intel_svm_unbind_mm(struct device *dev, u32 pasid)
 {
 	struct intel_svm_dev *sdev;
 	struct intel_iommu *iommu;
@@ -739,7 +739,7 @@ static bool is_canonical_address(u64 addr)
  * described in VT-d spec CH7.10 to drain all page requests and page
  * responses pending in the hardware.
  */
-static void intel_svm_drain_prq(struct device *dev, int pasid)
+static void intel_svm_drain_prq(struct device *dev, u32 pasid)
 {
 	struct device_domain_info *info;
 	struct dmar_domain *domain;
@@ -1067,10 +1067,10 @@ void intel_svm_unbind(struct iommu_sva *sva)
 	mutex_unlock(&pasid_mutex);
 }
 
-int intel_svm_get_pasid(struct iommu_sva *sva)
+u32 intel_svm_get_pasid(struct iommu_sva *sva)
 {
 	struct intel_svm_dev *sdev;
-	int pasid;
+	u32 pasid;
 
 	mutex_lock(&pasid_mutex);
 	sdev = to_intel_svm_dev(sva);
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 609bd25bf154..0e4fbdc0f5e5 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -2839,7 +2839,7 @@ void iommu_sva_unbind_device(struct iommu_sva *handle)
 }
 EXPORT_SYMBOL_GPL(iommu_sva_unbind_device);
 
-int iommu_sva_get_pasid(struct iommu_sva *handle)
+u32 iommu_sva_get_pasid(struct iommu_sva *handle)
 {
 	const struct iommu_ops *ops = handle->dev->bus->iommu_ops;
 
diff --git a/drivers/misc/uacce/uacce.c b/drivers/misc/uacce/uacce.c
index a5b8dab80c76..4cb7a5b19467 100644
--- a/drivers/misc/uacce/uacce.c
+++ b/drivers/misc/uacce/uacce.c
@@ -93,7 +93,7 @@ static long uacce_fops_compat_ioctl(struct file *filep,
 
 static int uacce_bind_queue(struct uacce_device *uacce, struct uacce_queue *q)
 {
-	int pasid;
+	u32 pasid;
 	struct iommu_sva *handle;
 
 	if (!(uacce->flags & UACCE_DEV_SVA))
diff --git a/include/linux/amd-iommu.h b/include/linux/amd-iommu.h
index 21e950e4ab62..450717299928 100644
--- a/include/linux/amd-iommu.h
+++ b/include/linux/amd-iommu.h
@@ -76,7 +76,7 @@ extern void amd_iommu_free_device(struct pci_dev *pdev);
  *
  * The function returns 0 on success or a negative value on error.
  */
-extern int amd_iommu_bind_pasid(struct pci_dev *pdev, int pasid,
+extern int amd_iommu_bind_pasid(struct pci_dev *pdev, u32 pasid,
 				struct task_struct *task);
 
 /**
@@ -88,7 +88,7 @@ extern int amd_iommu_bind_pasid(struct pci_dev *pdev, int pasid,
  * When this function returns the device is no longer using the PASID
  * and the PASID is no longer bound to its task.
  */
-extern void amd_iommu_unbind_pasid(struct pci_dev *pdev, int pasid);
+extern void amd_iommu_unbind_pasid(struct pci_dev *pdev, u32 pasid);
 
 /**
  * amd_iommu_set_invalid_ppr_cb() - Register a call-back for failed
@@ -114,7 +114,7 @@ extern void amd_iommu_unbind_pasid(struct pci_dev *pdev, int pasid);
 #define AMD_IOMMU_INV_PRI_RSP_FAIL	2
 
 typedef int (*amd_iommu_invalid_ppr_cb)(struct pci_dev *pdev,
-					int pasid,
+					u32 pasid,
 					unsigned long address,
 					u16);
 
@@ -166,7 +166,7 @@ extern int amd_iommu_device_info(struct pci_dev *pdev,
  * @cb: The call-back function
  */
 
-typedef void (*amd_iommu_invalidate_ctx)(struct pci_dev *pdev, int pasid);
+typedef void (*amd_iommu_invalidate_ctx)(struct pci_dev *pdev, u32 pasid);
 
 extern int amd_iommu_set_invalidate_ctx_cb(struct pci_dev *pdev,
 					   amd_iommu_invalidate_ctx cb);
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index b1ed2f25f7c0..7322073f62d0 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -549,7 +549,7 @@ struct dmar_domain {
 					   2 == 1GiB, 3 == 512GiB, 4 == 1TiB */
 	u64		max_addr;	/* maximum mapped address */
 
-	int		default_pasid;	/*
+	u32		default_pasid;	/*
 					 * The default pasid used for non-SVM
 					 * traffic on mediated devices.
 					 */
@@ -708,7 +708,7 @@ void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid,
 			      u32 pasid, u16 qdep, u64 addr,
 			      unsigned int size_order);
 void qi_flush_pasid_cache(struct intel_iommu *iommu, u16 did, u64 granu,
-			  int pasid);
+			  u32 pasid);
 
 int qi_submit_sync(struct intel_iommu *iommu, struct qi_desc *desc,
 		   unsigned int count, unsigned long options);
@@ -737,11 +737,11 @@ extern int intel_svm_enable_prq(struct intel_iommu *iommu);
 extern int intel_svm_finish_prq(struct intel_iommu *iommu);
 int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev,
 			  struct iommu_gpasid_bind_data *data);
-int intel_svm_unbind_gpasid(struct device *dev, int pasid);
+int intel_svm_unbind_gpasid(struct device *dev, u32 pasid);
 struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct *mm,
 				 void *drvdata);
 void intel_svm_unbind(struct iommu_sva *handle);
-int intel_svm_get_pasid(struct iommu_sva *handle);
+u32 intel_svm_get_pasid(struct iommu_sva *handle);
 int intel_svm_page_response(struct device *dev, struct iommu_fault_event *evt,
 			    struct iommu_page_response *msg);
 
@@ -753,7 +753,7 @@ struct intel_svm_dev {
 	struct device *dev;
 	struct svm_dev_ops *ops;
 	struct iommu_sva sva;
-	int pasid;
+	u32 pasid;
 	int users;
 	u16 did;
 	u16 dev_iotlb:1;
@@ -766,7 +766,7 @@ struct intel_svm {
 
 	struct intel_iommu *iommu;
 	int flags;
-	int pasid;
+	u32 pasid;
 	int gpasid; /* In case that guest PASID is different from host PASID */
 	struct list_head devs;
 	struct list_head list;
diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h
index c9e7e601950d..39d368a810b8 100644
--- a/include/linux/intel-svm.h
+++ b/include/linux/intel-svm.h
@@ -11,7 +11,7 @@
 struct device;
 
 struct svm_dev_ops {
-	void (*fault_cb)(struct device *dev, int pasid, u64 address,
+	void (*fault_cb)(struct device *dev, u32 pasid, u64 address,
 			 void *private, int rwxp, int response);
 };
 
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index fee209efb756..e57e819aaf2e 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -286,7 +286,7 @@ struct iommu_ops {
 	struct iommu_sva *(*sva_bind)(struct device *dev, struct mm_struct *mm,
 				      void *drvdata);
 	void (*sva_unbind)(struct iommu_sva *handle);
-	int (*sva_get_pasid)(struct iommu_sva *handle);
+	u32 (*sva_get_pasid)(struct iommu_sva *handle);
 
 	int (*page_response)(struct device *dev,
 			     struct iommu_fault_event *evt,
@@ -296,7 +296,7 @@ struct iommu_ops {
 	int (*sva_bind_gpasid)(struct iommu_domain *domain,
 			struct device *dev, struct iommu_gpasid_bind_data *data);
 
-	int (*sva_unbind_gpasid)(struct device *dev, int pasid);
+	int (*sva_unbind_gpasid)(struct device *dev, u32 pasid);
 
 	int (*def_domain_type)(struct device *dev);
 
@@ -634,7 +634,7 @@ struct iommu_sva *iommu_sva_bind_device(struct device *dev,
 					struct mm_struct *mm,
 					void *drvdata);
 void iommu_sva_unbind_device(struct iommu_sva *handle);
-int iommu_sva_get_pasid(struct iommu_sva *handle);
+u32 iommu_sva_get_pasid(struct iommu_sva *handle);
 
 #else /* CONFIG_IOMMU_API */
 
@@ -1027,7 +1027,7 @@ static inline void iommu_sva_unbind_device(struct iommu_sva *handle)
 {
 }
 
-static inline int iommu_sva_get_pasid(struct iommu_sva *handle)
+static inline u32 iommu_sva_get_pasid(struct iommu_sva *handle)
 {
 	return IOMMU_PASID_INVALID;
 }
@@ -1046,7 +1046,7 @@ static inline int iommu_sva_bind_gpasid(struct iommu_domain *domain,
 }
 
 static inline int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
-					   struct device *dev, int pasid)
+					   struct device *dev, u32 pasid)
 {
 	return -ENODEV;
 }
diff --git a/include/linux/uacce.h b/include/linux/uacce.h
index 454c2f6672d7..48e319f40275 100644
--- a/include/linux/uacce.h
+++ b/include/linux/uacce.h
@@ -81,7 +81,7 @@ struct uacce_queue {
 	struct list_head list;
 	struct uacce_qfile_region *qfrs[UACCE_MAX_REGION];
 	enum uacce_q_state state;
-	int pasid;
+	u32 pasid;
 	struct iommu_sva *handle;
 };
 
-- 
cgit v1.2.3


From 2a5054c6e7b16906984ac36a7363ca46b8d99ade Mon Sep 17 00:00:00 2001
From: Fenghua Yu <fenghua.yu@intel.com>
Date: Tue, 15 Sep 2020 09:30:06 -0700
Subject: iommu/vt-d: Change flags type to unsigned int in binding mm

"flags" passed to intel_svm_bind_mm() is a bit mask and should be
defined as "unsigned int" instead of "int".

Change its type to "unsigned int".

Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Acked-by: Joerg Roedel <jroedel@suse.de>
Link: https://lkml.kernel.org/r/1600187413-163670-3-git-send-email-fenghua.yu@intel.com
---
 drivers/iommu/intel/svm.c   | 7 ++++---
 include/linux/intel-iommu.h | 2 +-
 2 files changed, 5 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index e78a74a9c1cf..fc90a079e228 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -446,7 +446,8 @@ out:
 
 /* Caller must hold pasid_mutex, mm reference */
 static int
-intel_svm_bind_mm(struct device *dev, int flags, struct svm_dev_ops *ops,
+intel_svm_bind_mm(struct device *dev, unsigned int flags,
+		  struct svm_dev_ops *ops,
 		  struct mm_struct *mm, struct intel_svm_dev **sd)
 {
 	struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL);
@@ -1033,7 +1034,7 @@ intel_svm_bind(struct device *dev, struct mm_struct *mm, void *drvdata)
 {
 	struct iommu_sva *sva = ERR_PTR(-EINVAL);
 	struct intel_svm_dev *sdev = NULL;
-	int flags = 0;
+	unsigned int flags = 0;
 	int ret;
 
 	/*
@@ -1042,7 +1043,7 @@ intel_svm_bind(struct device *dev, struct mm_struct *mm, void *drvdata)
 	 * and intel_svm etc.
 	 */
 	if (drvdata)
-		flags = *(int *)drvdata;
+		flags = *(unsigned int *)drvdata;
 	mutex_lock(&pasid_mutex);
 	ret = intel_svm_bind_mm(dev, flags, NULL, mm, &sdev);
 	if (ret)
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 7322073f62d0..9c3e8337442a 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -765,7 +765,7 @@ struct intel_svm {
 	struct mm_struct *mm;
 
 	struct intel_iommu *iommu;
-	int flags;
+	unsigned int flags;
 	u32 pasid;
 	int gpasid; /* In case that guest PASID is different from host PASID */
 	struct list_head devs;
-- 
cgit v1.2.3


From 877c1a5f79c6984bbe3f2924234c08e2f4f1acd5 Mon Sep 17 00:00:00 2001
From: Tuan Phan <tuanphan@os.amperecomputing.com>
Date: Thu, 6 Aug 2020 14:57:34 -0700
Subject: PCI/ACPI: Add Ampere Altra SOC MCFG quirk

Ampere Altra SOC supports only 32-bit ECAM reads.  Add an MCFG quirk for
the platform.

Link: https://lore.kernel.org/r/1596751055-12316-1-git-send-email-tuanphan@os.amperecomputing.com
Signed-off-by: Tuan Phan <tuanphan@os.amperecomputing.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/acpi/pci_mcfg.c  | 20 ++++++++++++++++++++
 drivers/pci/ecam.c       | 10 ++++++++++
 include/linux/pci-ecam.h |  1 +
 3 files changed, 31 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/acpi/pci_mcfg.c b/drivers/acpi/pci_mcfg.c
index c8ef3bb5aa00..7ddd57abadd1 100644
--- a/drivers/acpi/pci_mcfg.c
+++ b/drivers/acpi/pci_mcfg.c
@@ -142,6 +142,26 @@ static struct mcfg_fixup mcfg_quirks[] = {
 	XGENE_V2_ECAM_MCFG(4, 0),
 	XGENE_V2_ECAM_MCFG(4, 1),
 	XGENE_V2_ECAM_MCFG(4, 2),
+
+#define ALTRA_ECAM_QUIRK(rev, seg) \
+	{ "Ampere", "Altra   ", rev, seg, MCFG_BUS_ANY, &pci_32b_read_ops }
+
+	ALTRA_ECAM_QUIRK(1, 0),
+	ALTRA_ECAM_QUIRK(1, 1),
+	ALTRA_ECAM_QUIRK(1, 2),
+	ALTRA_ECAM_QUIRK(1, 3),
+	ALTRA_ECAM_QUIRK(1, 4),
+	ALTRA_ECAM_QUIRK(1, 5),
+	ALTRA_ECAM_QUIRK(1, 6),
+	ALTRA_ECAM_QUIRK(1, 7),
+	ALTRA_ECAM_QUIRK(1, 8),
+	ALTRA_ECAM_QUIRK(1, 9),
+	ALTRA_ECAM_QUIRK(1, 10),
+	ALTRA_ECAM_QUIRK(1, 11),
+	ALTRA_ECAM_QUIRK(1, 12),
+	ALTRA_ECAM_QUIRK(1, 13),
+	ALTRA_ECAM_QUIRK(1, 14),
+	ALTRA_ECAM_QUIRK(1, 15),
 };
 
 static char mcfg_oem_id[ACPI_OEM_ID_SIZE];
diff --git a/drivers/pci/ecam.c b/drivers/pci/ecam.c
index 8f065a42fc1a..b54d32a31669 100644
--- a/drivers/pci/ecam.c
+++ b/drivers/pci/ecam.c
@@ -168,4 +168,14 @@ const struct pci_ecam_ops pci_32b_ops = {
 		.write		= pci_generic_config_write32,
 	}
 };
+
+/* ECAM ops for 32-bit read only (non-compliant) */
+const struct pci_ecam_ops pci_32b_read_ops = {
+	.bus_shift	= 20,
+	.pci_ops	= {
+		.map_bus	= pci_ecam_map_bus,
+		.read		= pci_generic_config_read32,
+		.write		= pci_generic_config_write,
+	}
+};
 #endif
diff --git a/include/linux/pci-ecam.h b/include/linux/pci-ecam.h
index 1af5cb02ef7f..033ce74f02e8 100644
--- a/include/linux/pci-ecam.h
+++ b/include/linux/pci-ecam.h
@@ -51,6 +51,7 @@ extern const struct pci_ecam_ops pci_generic_ecam_ops;
 
 #if defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS)
 extern const struct pci_ecam_ops pci_32b_ops;	/* 32-bit accesses only */
+extern const struct pci_ecam_ops pci_32b_read_ops; /* 32-bit read only */
 extern const struct pci_ecam_ops hisi_pcie_ops;	/* HiSilicon */
 extern const struct pci_ecam_ops thunder_pem_ecam_ops; /* Cavium ThunderX 1.x & 2.x */
 extern const struct pci_ecam_ops pci_thunder_ecam_ops; /* Cavium ThunderX 1.x */
-- 
cgit v1.2.3


From 9d8feb460adb90e89e64101ce2c1cfcd548a6d83 Mon Sep 17 00:00:00 2001
From: Alex Vesker <valex@nvidia.com>
Date: Mon, 31 Aug 2020 10:01:48 +0300
Subject: RDMA/mlx5: Add sw_owner_v2 bit capability

Added sw_owner_v2 which will be enabled for future devices,
replacing sw_owner bit.

Signed-off-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 include/linux/mlx5/mlx5_ifc.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index de1ffb4804d6..3061ceebbaf3 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -420,7 +420,8 @@ struct mlx5_ifc_flow_table_prop_layout_bits {
 	u8         reserved_at_1a[0x2];
 	u8         ipsec_encrypt[0x1];
 	u8         ipsec_decrypt[0x1];
-	u8         reserved_at_1e[0x2];
+	u8         sw_owner_v2[0x1];
+	u8         reserved_at_1f[0x1];
 
 	u8         termination_table_raw_traffic[0x1];
 	u8         reserved_at_21[0x1];
-- 
cgit v1.2.3


From 52ad9bc64c74167466e70e0df4b99ee5ccef0078 Mon Sep 17 00:00:00 2001
From: Fenghua Yu <fenghua.yu@intel.com>
Date: Tue, 15 Sep 2020 09:30:11 -0700
Subject: mm: Add a pasid member to struct mm_struct

A PASID is shared by all threads in a process. So the logical place to
keep track of it is in the mm_struct. Both ARM and x86 would use this
PASID.

 [ bp: Massage commit message. ]

Suggested-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/1600187413-163670-8-git-send-email-fenghua.yu@intel.com
---
 include/linux/mm_types.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 496c3ff97cce..1ff0615ef19f 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -542,6 +542,10 @@ struct mm_struct {
 		atomic_long_t hugetlb_usage;
 #endif
 		struct work_struct async_put_work;
+
+#ifdef CONFIG_IOMMU_SUPPORT
+		u32 pasid;
+#endif
 	} __randomize_layout;
 
 	/*
-- 
cgit v1.2.3


From a748c6975dea325da540610c2ba9b5f332c603e6 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 16 Sep 2020 23:10:05 +0200
Subject: bpf: propagate poke descriptors to subprograms

Previously, there was no need for poke descriptors being present in
subprogram's bpf_prog_aux struct since tailcalls were simply not allowed
in them. Each subprog is JITed independently so in order to enable
JITing subprograms that use tailcalls, do the following:

- in fixup_bpf_calls() store the index of tailcall insn onto the generated
  poke descriptor,
- in case when insn patching occurs, adjust the tailcall insn idx from
  bpf_patch_insn_data,
- then in jit_subprogs() check whether the given poke descriptor belongs
  to the current subprog by checking if that previously stored absolute
  index of tail call insn is in the scope of the insns of given subprog,
- update the insn->imm with new poke descriptor slot so that while JITing
  the proper poke descriptor will be grabbed

This way each of the main program's poke descriptors are distributed
across the subprograms poke descriptor array, so main program's
descriptors can be untracked out of the prog array map.

Add also subprog's aux struct to the BPF map poke_progs list by calling
on it map_poke_track().

In case of any error, call the map_poke_untrack() on subprog's aux
structs that have already been registered to prog array map.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h   |  1 +
 kernel/bpf/verifier.c | 66 ++++++++++++++++++++++++++++++++++++++++++++++++---
 2 files changed, 64 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 5dcce0364634..a23e5eb728c8 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -707,6 +707,7 @@ struct bpf_jit_poke_descriptor {
 	bool ip_stable;
 	u8 adj_off;
 	u16 reason;
+	u32 insn_idx;
 };
 
 /* reg_type info for ctx arguments */
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 814bc6c1ad16..8a18756953de 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -9623,6 +9623,18 @@ static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len
 	}
 }
 
+static void adjust_poke_descs(struct bpf_prog *prog, u32 len)
+{
+	struct bpf_jit_poke_descriptor *tab = prog->aux->poke_tab;
+	int i, sz = prog->aux->size_poke_tab;
+	struct bpf_jit_poke_descriptor *desc;
+
+	for (i = 0; i < sz; i++) {
+		desc = &tab[i];
+		desc->insn_idx += len - 1;
+	}
+}
+
 static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 off,
 					    const struct bpf_insn *patch, u32 len)
 {
@@ -9639,6 +9651,7 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of
 	if (adjust_insn_aux_data(env, new_prog, off, len))
 		return NULL;
 	adjust_subprog_starts(env, off, len);
+	adjust_poke_descs(new_prog, len);
 	return new_prog;
 }
 
@@ -10169,6 +10182,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 {
 	struct bpf_prog *prog = env->prog, **func, *tmp;
 	int i, j, subprog_start, subprog_end = 0, len, subprog;
+	struct bpf_map *map_ptr;
 	struct bpf_insn *insn;
 	void *old_bpf_func;
 	int err, num_exentries;
@@ -10236,6 +10250,31 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		func[i]->aux->btf = prog->aux->btf;
 		func[i]->aux->func_info = prog->aux->func_info;
 
+		for (j = 0; j < prog->aux->size_poke_tab; j++) {
+			u32 insn_idx = prog->aux->poke_tab[j].insn_idx;
+			int ret;
+
+			if (!(insn_idx >= subprog_start &&
+			      insn_idx <= subprog_end))
+				continue;
+
+			ret = bpf_jit_add_poke_descriptor(func[i],
+							  &prog->aux->poke_tab[j]);
+			if (ret < 0) {
+				verbose(env, "adding tail call poke descriptor failed\n");
+				goto out_free;
+			}
+
+			func[i]->insnsi[insn_idx - subprog_start].imm = ret + 1;
+
+			map_ptr = func[i]->aux->poke_tab[ret].tail_call.map;
+			ret = map_ptr->ops->map_poke_track(map_ptr, func[i]->aux);
+			if (ret < 0) {
+				verbose(env, "tracking tail call prog failed\n");
+				goto out_free;
+			}
+		}
+
 		/* Use bpf_prog_F_tag to indicate functions in stack traces.
 		 * Long term would need debug info to populate names
 		 */
@@ -10261,6 +10300,19 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		}
 		cond_resched();
 	}
+
+	/* Untrack main program's aux structs so that during map_poke_run()
+	 * we will not stumble upon the unfilled poke descriptors; each
+	 * of the main program's poke descs got distributed across subprogs
+	 * and got tracked onto map, so we are sure that none of them will
+	 * be missed after the operation below
+	 */
+	for (i = 0; i < prog->aux->size_poke_tab; i++) {
+		map_ptr = prog->aux->poke_tab[i].tail_call.map;
+
+		map_ptr->ops->map_poke_untrack(map_ptr, prog->aux);
+	}
+
 	/* at this point all bpf functions were successfully JITed
 	 * now populate all bpf_calls with correct addresses and
 	 * run last pass of JIT
@@ -10329,9 +10381,16 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 	bpf_prog_free_unused_jited_linfo(prog);
 	return 0;
 out_free:
-	for (i = 0; i < env->subprog_cnt; i++)
-		if (func[i])
-			bpf_jit_free(func[i]);
+	for (i = 0; i < env->subprog_cnt; i++) {
+		if (!func[i])
+			continue;
+
+		for (j = 0; j < func[i]->aux->size_poke_tab; j++) {
+			map_ptr = func[i]->aux->poke_tab[j].tail_call.map;
+			map_ptr->ops->map_poke_untrack(map_ptr, func[i]->aux);
+		}
+		bpf_jit_free(func[i]);
+	}
 	kfree(func);
 out_undo_insn:
 	/* cleanup main prog to be interpreted */
@@ -10549,6 +10608,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 					.reason = BPF_POKE_REASON_TAIL_CALL,
 					.tail_call.map = BPF_MAP_PTR(aux->map_ptr_state),
 					.tail_call.key = bpf_map_key_immediate(aux),
+					.insn_idx = i + delta,
 				};
 
 				ret = bpf_jit_add_poke_descriptor(prog, &desc);
-- 
cgit v1.2.3


From cf71b174d3464c7dc22f86f25d629a8d9d5c3519 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 16 Sep 2020 23:10:06 +0200
Subject: bpf: rename poke descriptor's 'ip' member to 'tailcall_target'

Reflect the actual purpose of poke->ip and rename it to
poke->tailcall_target so that it will not the be confused with another
poke target that will be introduced in next commit.

While at it, do the same thing with poke->ip_stable - rename it to
poke->tailcall_target_stable.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/x86/net/bpf_jit_comp.c | 20 +++++++++++---------
 include/linux/bpf.h         |  4 ++--
 kernel/bpf/arraymap.c       | 17 +++++++++--------
 kernel/bpf/core.c           |  3 ++-
 4 files changed, 24 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 6fb8c9435980..7b0ff169c9a0 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -434,7 +434,7 @@ static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke,
 	EMIT3(0x83, 0xC0, 0x01);                      /* add eax, 1 */
 	EMIT2_off32(0x89, 0x85, -36 - MAX_BPF_STACK); /* mov dword ptr [rbp -548], eax */
 
-	poke->ip = image + (addr - X86_PATCH_SIZE);
+	poke->tailcall_target = image + (addr - X86_PATCH_SIZE);
 	poke->adj_off = PROLOGUE_SIZE;
 
 	memcpy(prog, ideal_nops[NOP_ATOMIC5], X86_PATCH_SIZE);
@@ -453,7 +453,7 @@ static void bpf_tail_call_direct_fixup(struct bpf_prog *prog)
 
 	for (i = 0; i < prog->aux->size_poke_tab; i++) {
 		poke = &prog->aux->poke_tab[i];
-		WARN_ON_ONCE(READ_ONCE(poke->ip_stable));
+		WARN_ON_ONCE(READ_ONCE(poke->tailcall_target_stable));
 
 		if (poke->reason != BPF_POKE_REASON_TAIL_CALL)
 			continue;
@@ -464,18 +464,20 @@ static void bpf_tail_call_direct_fixup(struct bpf_prog *prog)
 		if (target) {
 			/* Plain memcpy is used when image is not live yet
 			 * and still not locked as read-only. Once poke
-			 * location is active (poke->ip_stable), any parallel
-			 * bpf_arch_text_poke() might occur still on the
-			 * read-write image until we finally locked it as
-			 * read-only. Both modifications on the given image
-			 * are under text_mutex to avoid interference.
+			 * location is active (poke->tailcall_target_stable),
+			 * any parallel bpf_arch_text_poke() might occur
+			 * still on the read-write image until we finally
+			 * locked it as read-only. Both modifications on
+			 * the given image are under text_mutex to avoid
+			 * interference.
 			 */
-			ret = __bpf_arch_text_poke(poke->ip, BPF_MOD_JUMP, NULL,
+			ret = __bpf_arch_text_poke(poke->tailcall_target,
+						   BPF_MOD_JUMP, NULL,
 						   (u8 *)target->bpf_func +
 						   poke->adj_off, false);
 			BUG_ON(ret < 0);
 		}
-		WRITE_ONCE(poke->ip_stable, true);
+		WRITE_ONCE(poke->tailcall_target_stable, true);
 		mutex_unlock(&array->aux->poke_mutex);
 	}
 }
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index a23e5eb728c8..f3790c9cf542 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -697,14 +697,14 @@ enum bpf_jit_poke_reason {
 
 /* Descriptor of pokes pointing /into/ the JITed image. */
 struct bpf_jit_poke_descriptor {
-	void *ip;
+	void *tailcall_target;
 	union {
 		struct {
 			struct bpf_map *map;
 			u32 key;
 		} tail_call;
 	};
-	bool ip_stable;
+	bool tailcall_target_stable;
 	u8 adj_off;
 	u16 reason;
 	u32 insn_idx;
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index e046fb7d17cd..60abf7fe12de 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -918,12 +918,13 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 			 *    there could be danger of use after free otherwise.
 			 * 2) Initially when we start tracking aux, the program
 			 *    is not JITed yet and also does not have a kallsyms
-			 *    entry. We skip these as poke->ip_stable is not
-			 *    active yet. The JIT will do the final fixup before
-			 *    setting it stable. The various poke->ip_stable are
-			 *    successively activated, so tail call updates can
-			 *    arrive from here while JIT is still finishing its
-			 *    final fixup for non-activated poke entries.
+			 *    entry. We skip these as poke->tailcall_target_stable
+			 *    is not active yet. The JIT will do the final fixup
+			 *    before setting it stable. The various
+			 *    poke->tailcall_target_stable are successively
+			 *    activated, so tail call updates can arrive from here
+			 *    while JIT is still finishing its final fixup for
+			 *    non-activated poke entries.
 			 * 3) On program teardown, the program's kallsym entry gets
 			 *    removed out of RCU callback, but we can only untrack
 			 *    from sleepable context, therefore bpf_arch_text_poke()
@@ -940,7 +941,7 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 			 * 5) Any other error happening below from bpf_arch_text_poke()
 			 *    is a unexpected bug.
 			 */
-			if (!READ_ONCE(poke->ip_stable))
+			if (!READ_ONCE(poke->tailcall_target_stable))
 				continue;
 			if (poke->reason != BPF_POKE_REASON_TAIL_CALL)
 				continue;
@@ -948,7 +949,7 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 			    poke->tail_call.key != key)
 				continue;
 
-			ret = bpf_arch_text_poke(poke->ip, BPF_MOD_JUMP,
+			ret = bpf_arch_text_poke(poke->tailcall_target, BPF_MOD_JUMP,
 						 old ? (u8 *)old->bpf_func +
 						 poke->adj_off : NULL,
 						 new ? (u8 *)new->bpf_func +
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 2a20c2833996..2e00ac028d38 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -775,7 +775,8 @@ int bpf_jit_add_poke_descriptor(struct bpf_prog *prog,
 
 	if (size > poke_tab_max)
 		return -ENOSPC;
-	if (poke->ip || poke->ip_stable || poke->adj_off)
+	if (poke->tailcall_target || poke->tailcall_target_stable ||
+	    poke->adj_off)
 		return -EINVAL;
 
 	switch (poke->reason) {
-- 
cgit v1.2.3


From 32b313ce9db54991a053da66883289e99d6ad820 Mon Sep 17 00:00:00 2001
From: Gustavo Pimentel <Gustavo.Pimentel@synopsys.com>
Date: Thu, 17 Sep 2020 23:30:27 +0200
Subject: PCI: endpoint: Use "NULL" instead of "0" as a NULL pointer

When returning a NULL pointer, use "NULL" instead of "0".

Fixes sparse warning given by executing "make C=2 drivers/pci/":

  CHECK   drivers/pci/endpoint/pci-epc-core.c
   drivers/pci/endpoint/pci-epc-core.c: note: in included file:
   ./include/linux/pci-ep-cfs.h:22:16: warning:
   Using plain integer as NULL pointer
  CHECK   drivers/pci/endpoint/pci-epf-core.c
   drivers/pci/endpoint/pci-epf-core.c: note: in included file:
   ./include/linux/pci-ep-cfs.h:31:16: warning:
   Using plain integer as NULL pointer

Link: https://lore.kernel.org/r/80895f7465719edb3aa259e907acc4bc3217945c.1600378209.git.gustavo.pimentel@synopsys.com
Reported-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: Kishon Vijay Abraham I <kishon@ti.com>
Cc: Joao Pinto <jpinto@synopsys.com>
---
 include/linux/pci-ep-cfs.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pci-ep-cfs.h b/include/linux/pci-ep-cfs.h
index f42b0fd4b4bc..662881335c7e 100644
--- a/include/linux/pci-ep-cfs.h
+++ b/include/linux/pci-ep-cfs.h
@@ -19,7 +19,7 @@ void pci_ep_cfs_remove_epf_group(struct config_group *group);
 #else
 static inline struct config_group *pci_ep_cfs_add_epc_group(const char *name)
 {
-	return 0;
+	return NULL;
 }
 
 static inline void pci_ep_cfs_remove_epc_group(struct config_group *group)
@@ -28,7 +28,7 @@ static inline void pci_ep_cfs_remove_epc_group(struct config_group *group)
 
 static inline struct config_group *pci_ep_cfs_add_epf_group(const char *name)
 {
-	return 0;
+	return NULL;
 }
 
 static inline void pci_ep_cfs_remove_epf_group(struct config_group *group)
-- 
cgit v1.2.3


From 2492c205d2bbbc01f5c9e49fffe4b2e633c33f38 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Thu, 17 Sep 2020 10:19:10 +0800
Subject: netdev: Remove unused functions

There is no callers in tree, so can remove it.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 10 ----------
 1 file changed, 10 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 157e0242e9ee..909b1fbb0481 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4677,16 +4677,6 @@ int netdev_class_create_file_ns(const struct class_attribute *class_attr,
 void netdev_class_remove_file_ns(const struct class_attribute *class_attr,
 				 const void *ns);
 
-static inline int netdev_class_create_file(const struct class_attribute *class_attr)
-{
-	return netdev_class_create_file_ns(class_attr, NULL);
-}
-
-static inline void netdev_class_remove_file(const struct class_attribute *class_attr)
-{
-	netdev_class_remove_file_ns(class_attr, NULL);
-}
-
 extern const struct kobj_ns_type_operations net_ns_type_operations;
 
 const char *netdev_drivername(const struct net_device *dev);
-- 
cgit v1.2.3


From 7f6e4312e15a5c370e84eaa685879b6bdcc717e4 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 16 Sep 2020 23:10:07 +0200
Subject: bpf: Limit caller's stack depth 256 for subprogs with tailcalls

Protect against potential stack overflow that might happen when bpf2bpf
calls get combined with tailcalls. Limit the caller's stack depth for
such case down to 256 so that the worst case scenario would result in 8k
stack size (32 which is tailcall limit * 256 = 8k).

Suggested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf_verifier.h |  1 +
 kernel/bpf/verifier.c        | 29 +++++++++++++++++++++++++++++
 2 files changed, 30 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 53c7bd568c5d..5026b75db972 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -358,6 +358,7 @@ struct bpf_subprog_info {
 	u32 start; /* insn idx of function entry point */
 	u32 linfo_idx; /* The idx to the main_prog->aux->linfo */
 	u16 stack_depth; /* max. stack depth used by this function */
+	bool has_tail_call;
 };
 
 /* single container for all structs
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 8a18756953de..0958fba48d59 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1490,6 +1490,10 @@ static int check_subprogs(struct bpf_verifier_env *env)
 	for (i = 0; i < insn_cnt; i++) {
 		u8 code = insn[i].code;
 
+		if (code == (BPF_JMP | BPF_CALL) &&
+		    insn[i].imm == BPF_FUNC_tail_call &&
+		    insn[i].src_reg != BPF_PSEUDO_CALL)
+			subprog[cur_subprog].has_tail_call = true;
 		if (BPF_CLASS(code) != BPF_JMP && BPF_CLASS(code) != BPF_JMP32)
 			goto next;
 		if (BPF_OP(code) == BPF_EXIT || BPF_OP(code) == BPF_CALL)
@@ -2983,6 +2987,31 @@ static int check_max_stack_depth(struct bpf_verifier_env *env)
 	int ret_prog[MAX_CALL_FRAMES];
 
 process_func:
+	/* protect against potential stack overflow that might happen when
+	 * bpf2bpf calls get combined with tailcalls. Limit the caller's stack
+	 * depth for such case down to 256 so that the worst case scenario
+	 * would result in 8k stack size (32 which is tailcall limit * 256 =
+	 * 8k).
+	 *
+	 * To get the idea what might happen, see an example:
+	 * func1 -> sub rsp, 128
+	 *  subfunc1 -> sub rsp, 256
+	 *  tailcall1 -> add rsp, 256
+	 *   func2 -> sub rsp, 192 (total stack size = 128 + 192 = 320)
+	 *   subfunc2 -> sub rsp, 64
+	 *   subfunc22 -> sub rsp, 128
+	 *   tailcall2 -> add rsp, 128
+	 *    func3 -> sub rsp, 32 (total stack size 128 + 192 + 64 + 32 = 416)
+	 *
+	 * tailcall will unwind the current stack frame but it will not get rid
+	 * of caller's stack as shown on the example above.
+	 */
+	if (idx && subprog[idx].has_tail_call && depth >= 256) {
+		verbose(env,
+			"tail_calls are not allowed when call stack of previous frames is %d bytes. Too large\n",
+			depth);
+		return -EACCES;
+	}
 	/* round up to 32-bytes, since this is granularity
 	 * of interpreter stack size
 	 */
-- 
cgit v1.2.3


From ebf7d1f508a73871acf3b2bfbfa1323a477acdb3 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 16 Sep 2020 23:10:08 +0200
Subject: bpf, x64: rework pro/epilogue and tailcall handling in JIT
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This commit serves two things:
1) it optimizes BPF prologue/epilogue generation
2) it makes possible to have tailcalls within BPF subprogram

Both points are related to each other since without 1), 2) could not be
achieved.

In [1], Alexei says:
"The prologue will look like:
nop5
xor eax,eax  // two new bytes if bpf_tail_call() is used in this
             // function
push rbp
mov rbp, rsp
sub rsp, rounded_stack_depth
push rax // zero init tail_call counter
variable number of push rbx,r13,r14,r15

Then bpf_tail_call will pop variable number rbx,..
and final 'pop rax'
Then 'add rsp, size_of_current_stack_frame'
jmp to next function and skip over 'nop5; xor eax,eax; push rpb; mov
rbp, rsp'

This way new function will set its own stack size and will init tail
call
counter with whatever value the parent had.

If next function doesn't use bpf_tail_call it won't have 'xor eax,eax'.
Instead it would need to have 'nop2' in there."

Implement that suggestion.

Since the layout of stack is changed, tail call counter handling can not
rely anymore on popping it to rbx just like it have been handled for
constant prologue case and later overwrite of rbx with actual value of
rbx pushed to stack. Therefore, let's use one of the register (%rcx) that
is considered to be volatile/caller-saved and pop the value of tail call
counter in there in the epilogue.

Drop the BUILD_BUG_ON in emit_prologue and in
emit_bpf_tail_call_indirect where instruction layout is not constant
anymore.

Introduce new poke target, 'tailcall_bypass' to poke descriptor that is
dedicated for skipping the register pops and stack unwind that are
generated right before the actual jump to target program.
For case when the target program is not present, BPF program will skip
the pop instructions and nop5 dedicated for jmpq $target. An example of
such state when only R6 of callee saved registers is used by program:

ffffffffc0513aa1:       e9 0e 00 00 00          jmpq   0xffffffffc0513ab4
ffffffffc0513aa6:       5b                      pop    %rbx
ffffffffc0513aa7:       58                      pop    %rax
ffffffffc0513aa8:       48 81 c4 00 00 00 00    add    $0x0,%rsp
ffffffffc0513aaf:       0f 1f 44 00 00          nopl   0x0(%rax,%rax,1)
ffffffffc0513ab4:       48 89 df                mov    %rbx,%rdi

When target program is inserted, the jump that was there to skip
pops/nop5 will become the nop5, so CPU will go over pops and do the
actual tailcall.

One might ask why there simply can not be pushes after the nop5?
In the following example snippet:

ffffffffc037030c:       48 89 fb                mov    %rdi,%rbx
(...)
ffffffffc0370332:       5b                      pop    %rbx
ffffffffc0370333:       58                      pop    %rax
ffffffffc0370334:       48 81 c4 00 00 00 00    add    $0x0,%rsp
ffffffffc037033b:       0f 1f 44 00 00          nopl   0x0(%rax,%rax,1)
ffffffffc0370340:       48 81 ec 00 00 00 00    sub    $0x0,%rsp
ffffffffc0370347:       50                      push   %rax
ffffffffc0370348:       53                      push   %rbx
ffffffffc0370349:       48 89 df                mov    %rbx,%rdi
ffffffffc037034c:       e8 f7 21 00 00          callq  0xffffffffc0372548

There is the bpf2bpf call (at ffffffffc037034c) right after the tailcall
and jump target is not present. ctx is in %rbx register and BPF
subprogram that we will call into on ffffffffc037034c is relying on it,
e.g. it will pick ctx from there. Such code layout is therefore broken
as we would overwrite the content of %rbx with the value that was pushed
on the prologue. That is the reason for the 'bypass' approach.

Special care needs to be taken during the install/update/remove of
tailcall target. In case when target program is not present, the CPU
must not execute the pop instructions that precede the tailcall.

To address that, the following states can be defined:
A nop, unwind, nop
B nop, unwind, tail
C skip, unwind, nop
D skip, unwind, tail

A is forbidden (lead to incorrectness). The state transitions between
tailcall install/update/remove will work as follows:

First install tail call f: C->D->B(f)
 * poke the tailcall, after that get rid of the skip
Update tail call f to f': B(f)->B(f')
 * poke the tailcall (poke->tailcall_target) and do NOT touch the
   poke->tailcall_bypass
Remove tail call: B(f')->C(f')
 * poke->tailcall_bypass is poked back to jump, then we wait the RCU
   grace period so that other programs will finish its execution and
   after that we are safe to remove the poke->tailcall_target
Install new tail call (f''): C(f')->D(f'')->B(f'').
 * same as first step

This way CPU can never be exposed to "unwind, tail" state.

Last but not least, when tailcalls get mixed with bpf2bpf calls, it
would be possible to encounter the endless loop due to clearing the
tailcall counter if for example we would use the tailcall3-like from BPF
selftests program that would be subprogram-based, meaning the tailcall
would be present within the BPF subprogram.

This test, broken down to particular steps, would do:
entry -> set tailcall counter to 0, bump it by 1, tailcall to func0
func0 -> call subprog_tail
(we are NOT skipping the first 11 bytes of prologue and this subprogram
has a tailcall, therefore we clear the counter...)
subprog -> do the same thing as entry

and then loop forever.

To address this, the idea is to go through the call chain of bpf2bpf progs
and look for a tailcall presence throughout whole chain. If we saw a single
tail call then each node in this call chain needs to be marked as a subprog
that can reach the tailcall. We would later feed the JIT with this info
and:
- set eax to 0 only when tailcall is reachable and this is the entry prog
- if tailcall is reachable but there's no tailcall in insns of currently
  JITed prog then push rax anyway, so that it will be possible to
  propagate further down the call chain
- finally if tailcall is reachable, then we need to precede the 'call'
  insn with mov rax, [rbp - (stack_depth + 8)]

Tail call related cases from test_verifier kselftest are also working
fine. Sample BPF programs that utilize tail calls (sockex3, tracex5)
work properly as well.

[1]: https://lore.kernel.org/bpf/20200517043227.2gpq22ifoq37ogst@ast-mbp.dhcp.thefacebook.com/

Suggested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/x86/net/bpf_jit_comp.c  | 237 ++++++++++++++++++++++++++++++++++---------
 include/linux/bpf.h          |   3 +
 include/linux/bpf_verifier.h |   1 +
 kernel/bpf/arraymap.c        |  40 ++++++--
 kernel/bpf/core.c            |   2 +-
 kernel/bpf/verifier.c        |  16 +++
 6 files changed, 244 insertions(+), 55 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 7b0ff169c9a0..26f43279b78b 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -221,14 +221,48 @@ struct jit_context {
 
 /* Number of bytes emit_patch() needs to generate instructions */
 #define X86_PATCH_SIZE		5
+/* Number of bytes that will be skipped on tailcall */
+#define X86_TAIL_CALL_OFFSET	11
 
-#define PROLOGUE_SIZE		25
+static void push_callee_regs(u8 **pprog, bool *callee_regs_used)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+
+	if (callee_regs_used[0])
+		EMIT1(0x53);         /* push rbx */
+	if (callee_regs_used[1])
+		EMIT2(0x41, 0x55);   /* push r13 */
+	if (callee_regs_used[2])
+		EMIT2(0x41, 0x56);   /* push r14 */
+	if (callee_regs_used[3])
+		EMIT2(0x41, 0x57);   /* push r15 */
+	*pprog = prog;
+}
+
+static void pop_callee_regs(u8 **pprog, bool *callee_regs_used)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+
+	if (callee_regs_used[3])
+		EMIT2(0x41, 0x5F);   /* pop r15 */
+	if (callee_regs_used[2])
+		EMIT2(0x41, 0x5E);   /* pop r14 */
+	if (callee_regs_used[1])
+		EMIT2(0x41, 0x5D);   /* pop r13 */
+	if (callee_regs_used[0])
+		EMIT1(0x5B);         /* pop rbx */
+	*pprog = prog;
+}
 
 /*
- * Emit x86-64 prologue code for BPF program and check its size.
- * bpf_tail_call helper will skip it while jumping into another program
+ * Emit x86-64 prologue code for BPF program.
+ * bpf_tail_call helper will skip the first X86_TAIL_CALL_OFFSET bytes
+ * while jumping to another program
  */
-static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
+static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
+			  bool tail_call_reachable, bool is_subprog)
 {
 	u8 *prog = *pprog;
 	int cnt = X86_PATCH_SIZE;
@@ -238,19 +272,18 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
 	 */
 	memcpy(prog, ideal_nops[NOP_ATOMIC5], cnt);
 	prog += cnt;
+	if (!ebpf_from_cbpf) {
+		if (tail_call_reachable && !is_subprog)
+			EMIT2(0x31, 0xC0); /* xor eax, eax */
+		else
+			EMIT2(0x66, 0x90); /* nop2 */
+	}
 	EMIT1(0x55);             /* push rbp */
 	EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
 	/* sub rsp, rounded_stack_depth */
 	EMIT3_off32(0x48, 0x81, 0xEC, round_up(stack_depth, 8));
-	EMIT1(0x53);             /* push rbx */
-	EMIT2(0x41, 0x55);       /* push r13 */
-	EMIT2(0x41, 0x56);       /* push r14 */
-	EMIT2(0x41, 0x57);       /* push r15 */
-	if (!ebpf_from_cbpf) {
-		/* zero init tail_call_cnt */
-		EMIT2(0x6a, 0x00);
-		BUILD_BUG_ON(cnt != PROLOGUE_SIZE);
-	}
+	if (tail_call_reachable)
+		EMIT1(0x50);         /* push rax */
 	*pprog = prog;
 }
 
@@ -314,13 +347,14 @@ static int __bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 	mutex_lock(&text_mutex);
 	if (memcmp(ip, old_insn, X86_PATCH_SIZE))
 		goto out;
+	ret = 1;
 	if (memcmp(ip, new_insn, X86_PATCH_SIZE)) {
 		if (text_live)
 			text_poke_bp(ip, new_insn, X86_PATCH_SIZE, NULL);
 		else
 			memcpy(ip, new_insn, X86_PATCH_SIZE);
+		ret = 0;
 	}
-	ret = 0;
 out:
 	mutex_unlock(&text_mutex);
 	return ret;
@@ -337,6 +371,22 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 	return __bpf_arch_text_poke(ip, t, old_addr, new_addr, true);
 }
 
+static int get_pop_bytes(bool *callee_regs_used)
+{
+	int bytes = 0;
+
+	if (callee_regs_used[3])
+		bytes += 2;
+	if (callee_regs_used[2])
+		bytes += 2;
+	if (callee_regs_used[1])
+		bytes += 2;
+	if (callee_regs_used[0])
+		bytes += 1;
+
+	return bytes;
+}
+
 /*
  * Generate the following code:
  *
@@ -351,12 +401,26 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
  *   goto *(prog->bpf_func + prologue_size);
  * out:
  */
-static void emit_bpf_tail_call_indirect(u8 **pprog)
+static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
+					u32 stack_depth)
 {
+	int tcc_off = -4 - round_up(stack_depth, 8);
 	u8 *prog = *pprog;
-	int label1, label2, label3;
+	int pop_bytes = 0;
+	int off1 = 49;
+	int off2 = 38;
+	int off3 = 16;
 	int cnt = 0;
 
+	/* count the additional bytes used for popping callee regs from stack
+	 * that need to be taken into account for each of the offsets that
+	 * are used for bailing out of the tail call
+	 */
+	pop_bytes = get_pop_bytes(callee_regs_used);
+	off1 += pop_bytes;
+	off2 += pop_bytes;
+	off3 += pop_bytes;
+
 	/*
 	 * rdi - pointer to ctx
 	 * rsi - pointer to bpf_array
@@ -370,21 +434,19 @@ static void emit_bpf_tail_call_indirect(u8 **pprog)
 	EMIT2(0x89, 0xD2);                        /* mov edx, edx */
 	EMIT3(0x39, 0x56,                         /* cmp dword ptr [rsi + 16], edx */
 	      offsetof(struct bpf_array, map.max_entries));
-#define OFFSET1 (41 + RETPOLINE_RCX_BPF_JIT_SIZE) /* Number of bytes to jump */
+#define OFFSET1 (off1 + RETPOLINE_RCX_BPF_JIT_SIZE) /* Number of bytes to jump */
 	EMIT2(X86_JBE, OFFSET1);                  /* jbe out */
-	label1 = cnt;
 
 	/*
 	 * if (tail_call_cnt > MAX_TAIL_CALL_CNT)
 	 *	goto out;
 	 */
-	EMIT2_off32(0x8B, 0x85, -36 - MAX_BPF_STACK); /* mov eax, dword ptr [rbp - 548] */
+	EMIT2_off32(0x8B, 0x85, tcc_off);         /* mov eax, dword ptr [rbp - tcc_off] */
 	EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT);     /* cmp eax, MAX_TAIL_CALL_CNT */
-#define OFFSET2 (30 + RETPOLINE_RCX_BPF_JIT_SIZE)
+#define OFFSET2 (off2 + RETPOLINE_RCX_BPF_JIT_SIZE)
 	EMIT2(X86_JA, OFFSET2);                   /* ja out */
-	label2 = cnt;
 	EMIT3(0x83, 0xC0, 0x01);                  /* add eax, 1 */
-	EMIT2_off32(0x89, 0x85, -36 - MAX_BPF_STACK); /* mov dword ptr [rbp -548], eax */
+	EMIT2_off32(0x89, 0x85, tcc_off);         /* mov dword ptr [rbp - tcc_off], eax */
 
 	/* prog = array->ptrs[index]; */
 	EMIT4_off32(0x48, 0x8B, 0x8C, 0xD6,       /* mov rcx, [rsi + rdx * 8 + offsetof(...)] */
@@ -394,48 +456,84 @@ static void emit_bpf_tail_call_indirect(u8 **pprog)
 	 * if (prog == NULL)
 	 *	goto out;
 	 */
-	EMIT3(0x48, 0x85, 0xC9);		  /* test rcx,rcx */
-#define OFFSET3 (8 + RETPOLINE_RCX_BPF_JIT_SIZE)
+	EMIT3(0x48, 0x85, 0xC9);                  /* test rcx,rcx */
+#define OFFSET3 (off3 + RETPOLINE_RCX_BPF_JIT_SIZE)
 	EMIT2(X86_JE, OFFSET3);                   /* je out */
-	label3 = cnt;
 
-	/* goto *(prog->bpf_func + prologue_size); */
+	*pprog = prog;
+	pop_callee_regs(pprog, callee_regs_used);
+	prog = *pprog;
+
+	EMIT1(0x58);                              /* pop rax */
+	EMIT3_off32(0x48, 0x81, 0xC4,             /* add rsp, sd */
+		    round_up(stack_depth, 8));
+
+	/* goto *(prog->bpf_func + X86_TAIL_CALL_OFFSET); */
 	EMIT4(0x48, 0x8B, 0x49,                   /* mov rcx, qword ptr [rcx + 32] */
 	      offsetof(struct bpf_prog, bpf_func));
-	EMIT4(0x48, 0x83, 0xC1, PROLOGUE_SIZE);   /* add rcx, prologue_size */
-
+	EMIT4(0x48, 0x83, 0xC1,                   /* add rcx, X86_TAIL_CALL_OFFSET */
+	      X86_TAIL_CALL_OFFSET);
 	/*
 	 * Now we're ready to jump into next BPF program
 	 * rdi == ctx (1st arg)
-	 * rcx == prog->bpf_func + prologue_size
+	 * rcx == prog->bpf_func + X86_TAIL_CALL_OFFSET
 	 */
 	RETPOLINE_RCX_BPF_JIT();
 
 	/* out: */
-	BUILD_BUG_ON(cnt - label1 != OFFSET1);
-	BUILD_BUG_ON(cnt - label2 != OFFSET2);
-	BUILD_BUG_ON(cnt - label3 != OFFSET3);
 	*pprog = prog;
 }
 
 static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke,
-				      u8 **pprog, int addr, u8 *image)
+				      u8 **pprog, int addr, u8 *image,
+				      bool *callee_regs_used, u32 stack_depth)
 {
+	int tcc_off = -4 - round_up(stack_depth, 8);
 	u8 *prog = *pprog;
+	int pop_bytes = 0;
+	int off1 = 27;
+	int poke_off;
 	int cnt = 0;
 
+	/* count the additional bytes used for popping callee regs to stack
+	 * that need to be taken into account for jump offset that is used for
+	 * bailing out from of the tail call when limit is reached
+	 */
+	pop_bytes = get_pop_bytes(callee_regs_used);
+	off1 += pop_bytes;
+
+	/*
+	 * total bytes for:
+	 * - nop5/ jmpq $off
+	 * - pop callee regs
+	 * - sub rsp, $val
+	 * - pop rax
+	 */
+	poke_off = X86_PATCH_SIZE + pop_bytes + 7 + 1;
+
 	/*
 	 * if (tail_call_cnt > MAX_TAIL_CALL_CNT)
 	 *	goto out;
 	 */
-	EMIT2_off32(0x8B, 0x85, -36 - MAX_BPF_STACK); /* mov eax, dword ptr [rbp - 548] */
+	EMIT2_off32(0x8B, 0x85, tcc_off);             /* mov eax, dword ptr [rbp - tcc_off] */
 	EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT);         /* cmp eax, MAX_TAIL_CALL_CNT */
-	EMIT2(X86_JA, 14);                            /* ja out */
+	EMIT2(X86_JA, off1);                          /* ja out */
 	EMIT3(0x83, 0xC0, 0x01);                      /* add eax, 1 */
-	EMIT2_off32(0x89, 0x85, -36 - MAX_BPF_STACK); /* mov dword ptr [rbp -548], eax */
+	EMIT2_off32(0x89, 0x85, tcc_off);             /* mov dword ptr [rbp - tcc_off], eax */
 
+	poke->tailcall_bypass = image + (addr - poke_off - X86_PATCH_SIZE);
+	poke->adj_off = X86_TAIL_CALL_OFFSET;
 	poke->tailcall_target = image + (addr - X86_PATCH_SIZE);
-	poke->adj_off = PROLOGUE_SIZE;
+	poke->bypass_addr = (u8 *)poke->tailcall_target + X86_PATCH_SIZE;
+
+	emit_jump(&prog, (u8 *)poke->tailcall_target + X86_PATCH_SIZE,
+		  poke->tailcall_bypass);
+
+	*pprog = prog;
+	pop_callee_regs(pprog, callee_regs_used);
+	prog = *pprog;
+	EMIT1(0x58);                                  /* pop rax */
+	EMIT3_off32(0x48, 0x81, 0xC4, round_up(stack_depth, 8));
 
 	memcpy(prog, ideal_nops[NOP_ATOMIC5], X86_PATCH_SIZE);
 	prog += X86_PATCH_SIZE;
@@ -476,6 +574,11 @@ static void bpf_tail_call_direct_fixup(struct bpf_prog *prog)
 						   (u8 *)target->bpf_func +
 						   poke->adj_off, false);
 			BUG_ON(ret < 0);
+			ret = __bpf_arch_text_poke(poke->tailcall_bypass,
+						   BPF_MOD_JUMP,
+						   (u8 *)poke->tailcall_target +
+						   X86_PATCH_SIZE, NULL, false);
+			BUG_ON(ret < 0);
 		}
 		WRITE_ONCE(poke->tailcall_target_stable, true);
 		mutex_unlock(&array->aux->poke_mutex);
@@ -654,19 +757,49 @@ static bool ex_handler_bpf(const struct exception_table_entry *x,
 	return true;
 }
 
+static void detect_reg_usage(struct bpf_insn *insn, int insn_cnt,
+			     bool *regs_used, bool *tail_call_seen)
+{
+	int i;
+
+	for (i = 1; i <= insn_cnt; i++, insn++) {
+		if (insn->code == (BPF_JMP | BPF_TAIL_CALL))
+			*tail_call_seen = true;
+		if (insn->dst_reg == BPF_REG_6 || insn->src_reg == BPF_REG_6)
+			regs_used[0] = true;
+		if (insn->dst_reg == BPF_REG_7 || insn->src_reg == BPF_REG_7)
+			regs_used[1] = true;
+		if (insn->dst_reg == BPF_REG_8 || insn->src_reg == BPF_REG_8)
+			regs_used[2] = true;
+		if (insn->dst_reg == BPF_REG_9 || insn->src_reg == BPF_REG_9)
+			regs_used[3] = true;
+	}
+}
+
 static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		  int oldproglen, struct jit_context *ctx)
 {
+	bool tail_call_reachable = bpf_prog->aux->tail_call_reachable;
 	struct bpf_insn *insn = bpf_prog->insnsi;
+	bool callee_regs_used[4] = {};
 	int insn_cnt = bpf_prog->len;
+	bool tail_call_seen = false;
 	bool seen_exit = false;
 	u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY];
 	int i, cnt = 0, excnt = 0;
 	int proglen = 0;
 	u8 *prog = temp;
 
+	detect_reg_usage(insn, insn_cnt, callee_regs_used,
+			 &tail_call_seen);
+
+	/* tail call's presence in current prog implies it is reachable */
+	tail_call_reachable |= tail_call_seen;
+
 	emit_prologue(&prog, bpf_prog->aux->stack_depth,
-		      bpf_prog_was_classic(bpf_prog));
+		      bpf_prog_was_classic(bpf_prog), tail_call_reachable,
+		      bpf_prog->aux->func_idx != 0);
+	push_callee_regs(&prog, callee_regs_used);
 	addrs[0] = prog - temp;
 
 	for (i = 1; i <= insn_cnt; i++, insn++) {
@@ -1104,16 +1237,27 @@ xadd:			if (is_imm8(insn->off))
 			/* call */
 		case BPF_JMP | BPF_CALL:
 			func = (u8 *) __bpf_call_base + imm32;
-			if (!imm32 || emit_call(&prog, func, image + addrs[i - 1]))
-				return -EINVAL;
+			if (tail_call_reachable) {
+				EMIT3_off32(0x48, 0x8B, 0x85,
+					    -(bpf_prog->aux->stack_depth + 8));
+				if (!imm32 || emit_call(&prog, func, image + addrs[i - 1] + 7))
+					return -EINVAL;
+			} else {
+				if (!imm32 || emit_call(&prog, func, image + addrs[i - 1]))
+					return -EINVAL;
+			}
 			break;
 
 		case BPF_JMP | BPF_TAIL_CALL:
 			if (imm32)
 				emit_bpf_tail_call_direct(&bpf_prog->aux->poke_tab[imm32 - 1],
-							  &prog, addrs[i], image);
+							  &prog, addrs[i], image,
+							  callee_regs_used,
+							  bpf_prog->aux->stack_depth);
 			else
-				emit_bpf_tail_call_indirect(&prog);
+				emit_bpf_tail_call_indirect(&prog,
+							    callee_regs_used,
+							    bpf_prog->aux->stack_depth);
 			break;
 
 			/* cond jump */
@@ -1296,12 +1440,9 @@ emit_jmp:
 			seen_exit = true;
 			/* Update cleanup_addr */
 			ctx->cleanup_addr = proglen;
-			if (!bpf_prog_was_classic(bpf_prog))
-				EMIT1(0x5B); /* get rid of tail_call_cnt */
-			EMIT2(0x41, 0x5F);   /* pop r15 */
-			EMIT2(0x41, 0x5E);   /* pop r14 */
-			EMIT2(0x41, 0x5D);   /* pop r13 */
-			EMIT1(0x5B);         /* pop rbx */
+			pop_callee_regs(&prog, callee_regs_used);
+			if (tail_call_reachable)
+				EMIT1(0x59); /* pop rcx, get rid of tail_call_cnt */
 			EMIT1(0xC9);         /* leave */
 			EMIT1(0xC3);         /* ret */
 			break;
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f3790c9cf542..d7c5a6ed87e3 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -698,6 +698,8 @@ enum bpf_jit_poke_reason {
 /* Descriptor of pokes pointing /into/ the JITed image. */
 struct bpf_jit_poke_descriptor {
 	void *tailcall_target;
+	void *tailcall_bypass;
+	void *bypass_addr;
 	union {
 		struct {
 			struct bpf_map *map;
@@ -738,6 +740,7 @@ struct bpf_prog_aux {
 	bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */
 	bool func_proto_unreliable;
 	bool sleepable;
+	bool tail_call_reachable;
 	enum bpf_tramp_prog_type trampoline_prog_type;
 	struct bpf_trampoline *trampoline;
 	struct hlist_node tramp_hlist;
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 5026b75db972..fbc964526ba3 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -359,6 +359,7 @@ struct bpf_subprog_info {
 	u32 linfo_idx; /* The idx to the main_prog->aux->linfo */
 	u16 stack_depth; /* max. stack depth used by this function */
 	bool has_tail_call;
+	bool tail_call_reachable;
 };
 
 /* single container for all structs
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 60abf7fe12de..e5fd31268ae0 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -898,6 +898,7 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 				    struct bpf_prog *old,
 				    struct bpf_prog *new)
 {
+	u8 *old_addr, *new_addr, *old_bypass_addr;
 	struct prog_poke_elem *elem;
 	struct bpf_array_aux *aux;
 
@@ -949,12 +950,39 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 			    poke->tail_call.key != key)
 				continue;
 
-			ret = bpf_arch_text_poke(poke->tailcall_target, BPF_MOD_JUMP,
-						 old ? (u8 *)old->bpf_func +
-						 poke->adj_off : NULL,
-						 new ? (u8 *)new->bpf_func +
-						 poke->adj_off : NULL);
-			BUG_ON(ret < 0 && ret != -EINVAL);
+			old_bypass_addr = old ? NULL : poke->bypass_addr;
+			old_addr = old ? (u8 *)old->bpf_func + poke->adj_off : NULL;
+			new_addr = new ? (u8 *)new->bpf_func + poke->adj_off : NULL;
+
+			if (new) {
+				ret = bpf_arch_text_poke(poke->tailcall_target,
+							 BPF_MOD_JUMP,
+							 old_addr, new_addr);
+				BUG_ON(ret < 0 && ret != -EINVAL);
+				if (!old) {
+					ret = bpf_arch_text_poke(poke->tailcall_bypass,
+								 BPF_MOD_JUMP,
+								 poke->bypass_addr,
+								 NULL);
+					BUG_ON(ret < 0 && ret != -EINVAL);
+				}
+			} else {
+				ret = bpf_arch_text_poke(poke->tailcall_bypass,
+							 BPF_MOD_JUMP,
+							 old_bypass_addr,
+							 poke->bypass_addr);
+				BUG_ON(ret < 0 && ret != -EINVAL);
+				/* let other CPUs finish the execution of program
+				 * so that it will not possible to expose them
+				 * to invalid nop, stack unwind, nop state
+				 */
+				if (!ret)
+					synchronize_rcu();
+				ret = bpf_arch_text_poke(poke->tailcall_target,
+							 BPF_MOD_JUMP,
+							 old_addr, NULL);
+				BUG_ON(ret < 0 && ret != -EINVAL);
+			}
 		}
 	}
 }
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 2e00ac028d38..c4811b139caa 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -776,7 +776,7 @@ int bpf_jit_add_poke_descriptor(struct bpf_prog *prog,
 	if (size > poke_tab_max)
 		return -ENOSPC;
 	if (poke->tailcall_target || poke->tailcall_target_stable ||
-	    poke->adj_off)
+	    poke->tailcall_bypass || poke->adj_off || poke->bypass_addr)
 		return -EINVAL;
 
 	switch (poke->reason) {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 0958fba48d59..172e12df9eaa 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2983,8 +2983,10 @@ static int check_max_stack_depth(struct bpf_verifier_env *env)
 	int depth = 0, frame = 0, idx = 0, i = 0, subprog_end;
 	struct bpf_subprog_info *subprog = env->subprog_info;
 	struct bpf_insn *insn = env->prog->insnsi;
+	bool tail_call_reachable = false;
 	int ret_insn[MAX_CALL_FRAMES];
 	int ret_prog[MAX_CALL_FRAMES];
+	int j;
 
 process_func:
 	/* protect against potential stack overflow that might happen when
@@ -3040,6 +3042,10 @@ continue_func:
 				  i);
 			return -EFAULT;
 		}
+
+		if (subprog[idx].has_tail_call)
+			tail_call_reachable = true;
+
 		frame++;
 		if (frame >= MAX_CALL_FRAMES) {
 			verbose(env, "the call stack of %d frames is too deep !\n",
@@ -3048,6 +3054,15 @@ continue_func:
 		}
 		goto process_func;
 	}
+	/* if tail call got detected across bpf2bpf calls then mark each of the
+	 * currently present subprog frames as tail call reachable subprogs;
+	 * this info will be utilized by JIT so that we will be preserving the
+	 * tail call counter throughout bpf2bpf calls combined with tailcalls
+	 */
+	if (tail_call_reachable)
+		for (j = 0; j < frame; j++)
+			subprog[ret_prog[j]].tail_call_reachable = true;
+
 	/* end of for() loop means the last insn of the 'subprog'
 	 * was reached. Doesn't matter whether it was JA or EXIT
 	 */
@@ -10322,6 +10337,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 				num_exentries++;
 		}
 		func[i]->aux->num_exentries = num_exentries;
+		func[i]->aux->tail_call_reachable = env->subprog_info[i].tail_call_reachable;
 		func[i] = bpf_int_jit_compile(func[i]);
 		if (!func[i]->jited) {
 			err = -ENOTSUPP;
-- 
cgit v1.2.3


From 09b28d76eac48e922dc293da1aa2b2b85c32aeee Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Thu, 17 Sep 2020 19:09:18 -0700
Subject: bpf: Add abnormal return checks.

LD_[ABS|IND] instructions may return from the function early. bpf_tail_call
pseudo instruction is either fallthrough or return. Allow them in the
subprograms only when subprograms are BTF annotated and have scalar return
types. Allow ld_abs and tail_call in the main program even if it calls into
subprograms. In the past that was not ok to do for ld_abs, since it was JITed
with special exit sequence. Since bpf_gen_ld_abs() was introduced the ld_abs
looks like normal exit insn from JIT point of view, so it's safe to allow them
in the main program.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf_verifier.h                 |  1 +
 kernel/bpf/verifier.c                        | 67 ++++++++++++++++++++--------
 tools/testing/selftests/bpf/verifier/calls.c |  6 +--
 3 files changed, 52 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index fbc964526ba3..2bb48a2c4d08 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -360,6 +360,7 @@ struct bpf_subprog_info {
 	u16 stack_depth; /* max. stack depth used by this function */
 	bool has_tail_call;
 	bool tail_call_reachable;
+	bool has_ld_abs;
 };
 
 /* single container for all structs
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index d1c009e8c57f..4161b6c406bc 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1494,6 +1494,9 @@ static int check_subprogs(struct bpf_verifier_env *env)
 		    insn[i].imm == BPF_FUNC_tail_call &&
 		    insn[i].src_reg != BPF_PSEUDO_CALL)
 			subprog[cur_subprog].has_tail_call = true;
+		if (BPF_CLASS(code) == BPF_LD &&
+		    (BPF_MODE(code) == BPF_ABS || BPF_MODE(code) == BPF_IND))
+			subprog[cur_subprog].has_ld_abs = true;
 		if (BPF_CLASS(code) != BPF_JMP && BPF_CLASS(code) != BPF_JMP32)
 			goto next;
 		if (BPF_OP(code) == BPF_EXIT || BPF_OP(code) == BPF_CALL)
@@ -7514,18 +7517,6 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
 		return -EINVAL;
 	}
 
-	if (env->subprog_cnt > 1) {
-		/* when program has LD_ABS insn JITs and interpreter assume
-		 * that r1 == ctx == skb which is not the case for callees
-		 * that can have arbitrary arguments. It's problematic
-		 * for main prog as well since JITs would need to analyze
-		 * all functions in order to make proper register save/restore
-		 * decisions in the main prog. Hence disallow LD_ABS with calls
-		 */
-		verbose(env, "BPF_LD_[ABS|IND] instructions cannot be mixed with bpf-to-bpf calls\n");
-		return -EINVAL;
-	}
-
 	if (insn->dst_reg != BPF_REG_0 || insn->off != 0 ||
 	    BPF_SIZE(insn->code) == BPF_DW ||
 	    (mode == BPF_ABS && insn->src_reg != BPF_REG_0)) {
@@ -7936,6 +7927,23 @@ err_free:
 	return ret;
 }
 
+static int check_abnormal_return(struct bpf_verifier_env *env)
+{
+	int i;
+
+	for (i = 1; i < env->subprog_cnt; i++) {
+		if (env->subprog_info[i].has_ld_abs) {
+			verbose(env, "LD_ABS is not allowed in subprogs without BTF\n");
+			return -EINVAL;
+		}
+		if (env->subprog_info[i].has_tail_call) {
+			verbose(env, "tail_call is not allowed in subprogs without BTF\n");
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
 /* The minimum supported BTF func info size */
 #define MIN_BPF_FUNCINFO_SIZE	8
 #define MAX_FUNCINFO_REC_SIZE	252
@@ -7944,20 +7952,24 @@ static int check_btf_func(struct bpf_verifier_env *env,
 			  const union bpf_attr *attr,
 			  union bpf_attr __user *uattr)
 {
+	const struct btf_type *type, *func_proto, *ret_type;
 	u32 i, nfuncs, urec_size, min_size;
 	u32 krec_size = sizeof(struct bpf_func_info);
 	struct bpf_func_info *krecord;
 	struct bpf_func_info_aux *info_aux = NULL;
-	const struct btf_type *type;
 	struct bpf_prog *prog;
 	const struct btf *btf;
 	void __user *urecord;
 	u32 prev_offset = 0;
+	bool scalar_return;
 	int ret = -ENOMEM;
 
 	nfuncs = attr->func_info_cnt;
-	if (!nfuncs)
+	if (!nfuncs) {
+		if (check_abnormal_return(env))
+			return -EINVAL;
 		return 0;
+	}
 
 	if (nfuncs != env->subprog_cnt) {
 		verbose(env, "number of funcs in func_info doesn't match number of subprogs\n");
@@ -8005,25 +8017,23 @@ static int check_btf_func(struct bpf_verifier_env *env,
 		}
 
 		/* check insn_off */
+		ret = -EINVAL;
 		if (i == 0) {
 			if (krecord[i].insn_off) {
 				verbose(env,
 					"nonzero insn_off %u for the first func info record",
 					krecord[i].insn_off);
-				ret = -EINVAL;
 				goto err_free;
 			}
 		} else if (krecord[i].insn_off <= prev_offset) {
 			verbose(env,
 				"same or smaller insn offset (%u) than previous func info record (%u)",
 				krecord[i].insn_off, prev_offset);
-			ret = -EINVAL;
 			goto err_free;
 		}
 
 		if (env->subprog_info[i].start != krecord[i].insn_off) {
 			verbose(env, "func_info BTF section doesn't match subprog layout in BPF program\n");
-			ret = -EINVAL;
 			goto err_free;
 		}
 
@@ -8032,10 +8042,26 @@ static int check_btf_func(struct bpf_verifier_env *env,
 		if (!type || !btf_type_is_func(type)) {
 			verbose(env, "invalid type id %d in func info",
 				krecord[i].type_id);
-			ret = -EINVAL;
 			goto err_free;
 		}
 		info_aux[i].linkage = BTF_INFO_VLEN(type->info);
+
+		func_proto = btf_type_by_id(btf, type->type);
+		if (unlikely(!func_proto || !btf_type_is_func_proto(func_proto)))
+			/* btf_func_check() already verified it during BTF load */
+			goto err_free;
+		ret_type = btf_type_skip_modifiers(btf, func_proto->type, NULL);
+		scalar_return =
+			btf_type_is_small_int(ret_type) || btf_type_is_enum(ret_type);
+		if (i && !scalar_return && env->subprog_info[i].has_ld_abs) {
+			verbose(env, "LD_ABS is only allowed in functions that return 'int'.\n");
+			goto err_free;
+		}
+		if (i && !scalar_return && env->subprog_info[i].has_tail_call) {
+			verbose(env, "tail_call is only allowed in functions that return 'int'.\n");
+			goto err_free;
+		}
+
 		prev_offset = krecord[i].insn_off;
 		urecord += urec_size;
 	}
@@ -8196,8 +8222,11 @@ static int check_btf_info(struct bpf_verifier_env *env,
 	struct btf *btf;
 	int err;
 
-	if (!attr->func_info_cnt && !attr->line_info_cnt)
+	if (!attr->func_info_cnt && !attr->line_info_cnt) {
+		if (check_abnormal_return(env))
+			return -EINVAL;
 		return 0;
+	}
 
 	btf = btf_get_by_fd(attr->prog_btf_fd);
 	if (IS_ERR(btf))
diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c
index 94258c6b5235..c4f5d909e58a 100644
--- a/tools/testing/selftests/bpf/verifier/calls.c
+++ b/tools/testing/selftests/bpf/verifier/calls.c
@@ -647,13 +647,14 @@
 	.result = REJECT,
 },
 {
-	"calls: ld_abs with changing ctx data in callee",
+	"calls: subprog call with ld_abs in main prog",
 	.insns = {
 	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
 	BPF_LD_ABS(BPF_B, 0),
 	BPF_LD_ABS(BPF_H, 0),
 	BPF_LD_ABS(BPF_W, 0),
 	BPF_MOV64_REG(BPF_REG_7, BPF_REG_6),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
 	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 5),
 	BPF_MOV64_REG(BPF_REG_6, BPF_REG_7),
 	BPF_LD_ABS(BPF_B, 0),
@@ -666,8 +667,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.errstr = "BPF_LD_[ABS|IND] instructions cannot be mixed",
-	.result = REJECT,
+	.result = ACCEPT,
 },
 {
 	"calls: two calls with bad fallthrough",
-- 
cgit v1.2.3


From cc80d10d6fcf6f47a2a3efe2c4139e50906a4764 Mon Sep 17 00:00:00 2001
From: Georgi Djakov <georgi.djakov@linaro.org>
Date: Tue, 25 Aug 2020 20:01:50 +0300
Subject: interconnect: Add get_bw() callback

The interconnect controller hardware may support querying the current
bandwidth settings, so add a callback for providers to implement this
functionality if supported.

Link: https://lore.kernel.org/r/20200825170152.6434-2-georgi.djakov@linaro.org
Reviewed-by: Saravana Kannan <saravanak@google.com>
Signed-off-by: Georgi Djakov <georgi.djakov@linaro.org>
---
 include/linux/interconnect-provider.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h
index 4735518de515..520f70fe5a31 100644
--- a/include/linux/interconnect-provider.h
+++ b/include/linux/interconnect-provider.h
@@ -38,6 +38,7 @@ struct icc_node *of_icc_xlate_onecell(struct of_phandle_args *spec,
  * @aggregate: pointer to device specific aggregate operation function
  * @pre_aggregate: pointer to device specific function that is called
  *		   before the aggregation begins (optional)
+ * @get_bw: pointer to device specific function to get current bandwidth
  * @xlate: provider-specific callback for mapping nodes from phandle arguments
  * @dev: the device this interconnect provider belongs to
  * @users: count of active users
@@ -51,6 +52,7 @@ struct icc_provider {
 	int (*aggregate)(struct icc_node *node, u32 tag, u32 avg_bw,
 			 u32 peak_bw, u32 *agg_avg, u32 *agg_peak);
 	void (*pre_aggregate)(struct icc_node *node);
+	int (*get_bw)(struct icc_node *node, u32 *avg, u32 *peak);
 	struct icc_node* (*xlate)(struct of_phandle_args *spec, void *data);
 	struct device		*dev;
 	int			users;
-- 
cgit v1.2.3


From b1d681d8d32499bcf284462d92aeb5f9fe72bf5b Mon Sep 17 00:00:00 2001
From: Georgi Djakov <georgi.djakov@linaro.org>
Date: Tue, 25 Aug 2020 20:01:51 +0300
Subject: interconnect: Add sync state support

The bootloaders often do some initial configuration of the interconnects
in the system and we want to keep this configuration until all consumers
have probed and expressed their bandwidth needs. This is because we don't
want to change the configuration by starting to disable unused paths until
every user had a chance to request the amount of bandwidth it needs.

To accomplish this we will implement an interconnect specific sync_state
callback which will synchronize (aggregate and set) the current bandwidth
settings when all consumers have been probed.

Link: https://lore.kernel.org/r/20200825170152.6434-3-georgi.djakov@linaro.org
Reviewed-by: Saravana Kannan <saravanak@google.com>
Signed-off-by: Georgi Djakov <georgi.djakov@linaro.org>
---
 drivers/interconnect/core.c           | 67 +++++++++++++++++++++++++++++++++++
 include/linux/interconnect-provider.h |  5 +++
 2 files changed, 72 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c
index cf07491b7415..b94c6c2b8ff9 100644
--- a/drivers/interconnect/core.c
+++ b/drivers/interconnect/core.c
@@ -26,6 +26,8 @@
 
 static DEFINE_IDR(icc_idr);
 static LIST_HEAD(icc_providers);
+static int providers_count;
+static bool synced_state;
 static DEFINE_MUTEX(icc_lock);
 static struct dentry *icc_debugfs_dir;
 
@@ -267,6 +269,12 @@ static int aggregate_requests(struct icc_node *node)
 		}
 		p->aggregate(node, r->tag, avg_bw, peak_bw,
 			     &node->avg_bw, &node->peak_bw);
+
+		/* during boot use the initial bandwidth as a floor value */
+		if (!synced_state) {
+			node->avg_bw = max(node->avg_bw, node->init_avg);
+			node->peak_bw = max(node->peak_bw, node->init_peak);
+		}
 	}
 
 	return 0;
@@ -931,6 +939,19 @@ void icc_node_add(struct icc_node *node, struct icc_provider *provider)
 	node->provider = provider;
 	list_add_tail(&node->node_list, &provider->nodes);
 
+	/* get the initial bandwidth values and sync them with hardware */
+	if (provider->get_bw) {
+		provider->get_bw(node, &node->init_avg, &node->init_peak);
+	} else {
+		node->init_avg = INT_MAX;
+		node->init_peak = INT_MAX;
+	}
+	node->avg_bw = node->init_avg;
+	node->peak_bw = node->init_peak;
+	provider->set(node, node);
+	node->avg_bw = 0;
+	node->peak_bw = 0;
+
 	mutex_unlock(&icc_lock);
 }
 EXPORT_SYMBOL_GPL(icc_node_add);
@@ -1026,8 +1047,54 @@ int icc_provider_del(struct icc_provider *provider)
 }
 EXPORT_SYMBOL_GPL(icc_provider_del);
 
+static int of_count_icc_providers(struct device_node *np)
+{
+	struct device_node *child;
+	int count = 0;
+
+	for_each_available_child_of_node(np, child) {
+		if (of_property_read_bool(child, "#interconnect-cells"))
+			count++;
+		count += of_count_icc_providers(child);
+	}
+	of_node_put(np);
+
+	return count;
+}
+
+void icc_sync_state(struct device *dev)
+{
+	struct icc_provider *p;
+	struct icc_node *n;
+	static int count;
+
+	count++;
+
+	if (count < providers_count)
+		return;
+
+	mutex_lock(&icc_lock);
+	synced_state = true;
+	list_for_each_entry(p, &icc_providers, provider_list) {
+		dev_dbg(p->dev, "interconnect provider is in synced state\n");
+		list_for_each_entry(n, &p->nodes, node_list) {
+			if (n->init_avg || n->init_peak) {
+				aggregate_requests(n);
+				p->set(n, n);
+			}
+		}
+	}
+	mutex_unlock(&icc_lock);
+}
+EXPORT_SYMBOL_GPL(icc_sync_state);
+
 static int __init icc_init(void)
 {
+	struct device_node *root = of_find_node_by_path("/");
+
+	providers_count = of_count_icc_providers(root);
+	of_node_put(root);
+
 	icc_debugfs_dir = debugfs_create_dir("interconnect", NULL);
 	debugfs_create_file("interconnect_summary", 0444,
 			    icc_debugfs_dir, NULL, &icc_summary_fops);
diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h
index 520f70fe5a31..f713308b8a8f 100644
--- a/include/linux/interconnect-provider.h
+++ b/include/linux/interconnect-provider.h
@@ -75,6 +75,8 @@ struct icc_provider {
  * @req_list: a list of QoS constraint requests associated with this node
  * @avg_bw: aggregated value of average bandwidth requests from all consumers
  * @peak_bw: aggregated value of peak bandwidth requests from all consumers
+ * @init_avg: average bandwidth value that is read from the hardware during init
+ * @init_peak: peak bandwidth value that is read from the hardware during init
  * @data: pointer to private data
  */
 struct icc_node {
@@ -91,6 +93,8 @@ struct icc_node {
 	struct hlist_head	req_list;
 	u32			avg_bw;
 	u32			peak_bw;
+	u32			init_avg;
+	u32			init_peak;
 	void			*data;
 };
 
@@ -108,6 +112,7 @@ int icc_nodes_remove(struct icc_provider *provider);
 int icc_provider_add(struct icc_provider *provider);
 int icc_provider_del(struct icc_provider *provider);
 struct icc_node *of_icc_get_from_provider(struct of_phandle_args *spec);
+void icc_sync_state(struct device *dev);
 
 #else
 
-- 
cgit v1.2.3


From 37050e3ab0b3f02819e3d70ab01d97addb810b28 Mon Sep 17 00:00:00 2001
From: Thomas Pedersen <thomas@adapt-ip.com>
Date: Tue, 8 Sep 2020 12:03:02 -0700
Subject: ieee80211: redefine S1G bits with GENMASK

The S1G capability fields were defined by ORing BITS()
together, and expecting a custom macro to use the _SHIFT
definitions. Use the Linux kernel GENMASK for the
definitions now, and FIELD_{GET,PREP} to access the fields
in the future.

Take the chance to rename eg. S1G_CAPAB_B0 to the more
compact S1G_CAP0.

Signed-off-by: Thomas Pedersen <thomas@adapt-ip.com>
Link: https://lore.kernel.org/r/20200908190323.15814-2-thomas@adapt-ip.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 156 +++++++++++++++++++++++-----------------------
 1 file changed, 78 insertions(+), 78 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index c47f43e65a2f..53fba39d4ba6 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -2330,84 +2330,84 @@ ieee80211_he_spr_size(const u8 *he_spr_ie)
 }
 
 /* S1G Capabilities Information field */
-#define S1G_CAPAB_B0_S1G_LONG BIT(0)
-#define S1G_CAPAB_B0_SGI_1MHZ BIT(1)
-#define S1G_CAPAB_B0_SGI_2MHZ BIT(2)
-#define S1G_CAPAB_B0_SGI_4MHZ BIT(3)
-#define S1G_CAPAB_B0_SGI_8MHZ BIT(4)
-#define S1G_CAPAB_B0_SGI_16MHZ BIT(5)
-#define S1G_CAPAB_B0_SUPP_CH_WIDTH_MASK (BIT(6) | BIT(7))
-#define S1G_CAPAB_B0_SUPP_CH_WIDTH_SHIFT 6
-
-#define S1G_CAPAB_B1_RX_LDPC BIT(0)
-#define S1G_CAPAB_B1_TX_STBC BIT(1)
-#define S1G_CAPAB_B1_RX_STBC BIT(2)
-#define S1G_CAPAB_B1_SU_BFER BIT(3)
-#define S1G_CAPAB_B1_SU_BFEE BIT(4)
-#define S1G_CAPAB_B1_BFEE_STS_MASK (BIT(5) | BIT(6) | BIT(7))
-#define S1G_CAPAB_B1_BFEE_STS_SHIFT 5
-
-#define S1G_CAPAB_B2_SOUNDING_DIMENSIONS_MASK (BIT(0) | BIT(1) | BIT(2))
-#define S1G_CAPAB_B2_SOUNDING_DIMENSIONS_SHIFT 0
-#define S1G_CAPAB_B2_MU_BFER BIT(3)
-#define S1G_CAPAB_B2_MU_BFEE BIT(4)
-#define S1G_CAPAB_B2_PLUS_HTC_VHT BIT(5)
-#define S1G_CAPAB_B2_TRAVELING_PILOT_MASK (BIT(6) | BIT(7))
-#define S1G_CAPAB_B2_TRAVELING_PILOT_SHIFT 6
-
-#define S1G_CAPAB_B3_RD_RESPONDER BIT(0)
-#define S1G_CAPAB_B3_HT_DELAYED_BA BIT(1)
-#define S1G_CAPAB_B3_MAX_MPDU_LEN BIT(2)
-#define S1G_CAPAB_B3_MAX_AMPDU_LEN_EXP_MASK (BIT(3) | BIT(4))
-#define S1G_CAPAB_B3_MAX_AMPDU_LEN_EXP_SHIFT 3
-#define S1G_CAPAB_B3_MIN_MPDU_START_MASK (BIT(5) | BIT(6) | BIT(7))
-#define S1G_CAPAB_B3_MIN_MPDU_START_SHIFT 5
-
-#define S1G_CAPAB_B4_UPLINK_SYNC BIT(0)
-#define S1G_CAPAB_B4_DYNAMIC_AID BIT(1)
-#define S1G_CAPAB_B4_BAT BIT(2)
-#define S1G_CAPAB_B4_TIME_ADE BIT(3)
-#define S1G_CAPAB_B4_NON_TIM BIT(4)
-#define S1G_CAPAB_B4_GROUP_AID BIT(5)
-#define S1G_CAPAB_B4_STA_TYPE_MASK (BIT(6) | BIT(7))
-#define S1G_CAPAB_B4_STA_TYPE_SHIFT 6
-
-#define S1G_CAPAB_B5_CENT_AUTH_CONTROL BIT(0)
-#define S1G_CAPAB_B5_DIST_AUTH_CONTROL BIT(1)
-#define S1G_CAPAB_B5_AMSDU BIT(2)
-#define S1G_CAPAB_B5_AMPDU BIT(3)
-#define S1G_CAPAB_B5_ASYMMETRIC_BA BIT(4)
-#define S1G_CAPAB_B5_FLOW_CONTROL BIT(5)
-#define S1G_CAPAB_B5_SECTORIZED_BEAM_MASK (BIT(6) | BIT(7))
-#define S1G_CAPAB_B5_SECTORIZED_BEAM_SHIFT 6
-
-#define S1G_CAPAB_B6_OBSS_MITIGATION BIT(0)
-#define S1G_CAPAB_B6_FRAGMENT_BA BIT(1)
-#define S1G_CAPAB_B6_NDP_PS_POLL BIT(2)
-#define S1G_CAPAB_B6_RAW_OPERATION BIT(3)
-#define S1G_CAPAB_B6_PAGE_SLICING BIT(4)
-#define S1G_CAPAB_B6_TXOP_SHARING_IMP_ACK BIT(5)
-#define S1G_CAPAB_B6_VHT_LINK_ADAPT_MASK (BIT(6) | BIT(7))
-#define S1G_CAPAB_B6_VHT_LINK_ADAPT_SHIFT 6
-
-#define S1G_CAPAB_B7_TACK_AS_PS_POLL BIT(0)
-#define S1G_CAPAB_B7_DUP_1MHZ BIT(1)
-#define S1G_CAPAB_B7_MCS_NEGOTIATION BIT(2)
-#define S1G_CAPAB_B7_1MHZ_CTL_RESPONSE_PREAMBLE BIT(3)
-#define S1G_CAPAB_B7_NDP_BFING_REPORT_POLL BIT(4)
-#define S1G_CAPAB_B7_UNSOLICITED_DYN_AID BIT(5)
-#define S1G_CAPAB_B7_SECTOR_TRAINING_OPERATION BIT(6)
-#define S1G_CAPAB_B7_TEMP_PS_MODE_SWITCH BIT(7)
-
-#define S1G_CAPAB_B8_TWT_GROUPING BIT(0)
-#define S1G_CAPAB_B8_BDT BIT(1)
-#define S1G_CAPAB_B8_COLOR_MASK (BIT(2) | BIT(3) | BIT(4))
-#define S1G_CAPAB_B8_COLOR_SHIFT 2
-#define S1G_CAPAB_B8_TWT_REQUEST BIT(5)
-#define S1G_CAPAB_B8_TWT_RESPOND BIT(6)
-#define S1G_CAPAB_B8_PV1_FRAME BIT(7)
-
-#define S1G_CAPAB_B9_LINK_ADAPT_PER_CONTROL_RESPONSE BIT(0)
+#define S1G_CAP0_S1G_LONG	BIT(0)
+#define S1G_CAP0_SGI_1MHZ	BIT(1)
+#define S1G_CAP0_SGI_2MHZ	BIT(2)
+#define S1G_CAP0_SGI_4MHZ	BIT(3)
+#define S1G_CAP0_SGI_8MHZ	BIT(4)
+#define S1G_CAP0_SGI_16MHZ	BIT(5)
+#define S1G_CAP0_SUPP_CH_WIDTH	GENMASK(7, 6)
+
+#define S1G_SUPP_CH_WIDTH_2	0
+#define S1G_SUPP_CH_WIDTH_4	1
+#define S1G_SUPP_CH_WIDTH_8	2
+#define S1G_SUPP_CH_WIDTH_16	3
+#define S1G_SUPP_CH_WIDTH_MAX(cap) ((1 << FIELD_GET(S1G_CAP0_SUPP_CH_WIDTH, \
+						    cap[0])) << 1)
+
+#define S1G_CAP1_RX_LDPC	BIT(0)
+#define S1G_CAP1_TX_STBC	BIT(1)
+#define S1G_CAP1_RX_STBC	BIT(2)
+#define S1G_CAP1_SU_BFER	BIT(3)
+#define S1G_CAP1_SU_BFEE	BIT(4)
+#define S1G_CAP1_BFEE_STS	GENMASK(7, 5)
+
+#define S1G_CAP2_SOUNDING_DIMENSIONS	GENMASK(2, 0)
+#define S1G_CAP2_MU_BFER		BIT(3)
+#define S1G_CAP2_MU_BFEE		BIT(4)
+#define S1G_CAP2_PLUS_HTC_VHT		BIT(5)
+#define S1G_CAP2_TRAVELING_PILOT	GENMASK(7, 6)
+
+#define S1G_CAP3_RD_RESPONDER		BIT(0)
+#define S1G_CAP3_HT_DELAYED_BA		BIT(1)
+#define S1G_CAP3_MAX_MPDU_LEN		BIT(2)
+#define S1G_CAP3_MAX_AMPDU_LEN_EXP	GENMASK(4, 3)
+#define S1G_CAP3_MIN_MPDU_START		GENMASK(7, 5)
+
+#define S1G_CAP4_UPLINK_SYNC	BIT(0)
+#define S1G_CAP4_DYNAMIC_AID	BIT(1)
+#define S1G_CAP4_BAT		BIT(2)
+#define S1G_CAP4_TIME_ADE	BIT(3)
+#define S1G_CAP4_NON_TIM	BIT(4)
+#define S1G_CAP4_GROUP_AID	BIT(5)
+#define S1G_CAP4_STA_TYPE	GENMASK(7, 6)
+
+#define S1G_CAP5_CENT_AUTH_CONTROL	BIT(0)
+#define S1G_CAP5_DIST_AUTH_CONTROL	BIT(1)
+#define S1G_CAP5_AMSDU			BIT(2)
+#define S1G_CAP5_AMPDU			BIT(3)
+#define S1G_CAP5_ASYMMETRIC_BA		BIT(4)
+#define S1G_CAP5_FLOW_CONTROL		BIT(5)
+#define S1G_CAP5_SECTORIZED_BEAM	GENMASK(7, 6)
+
+#define S1G_CAP6_OBSS_MITIGATION	BIT(0)
+#define S1G_CAP6_FRAGMENT_BA		BIT(1)
+#define S1G_CAP6_NDP_PS_POLL		BIT(2)
+#define S1G_CAP6_RAW_OPERATION		BIT(3)
+#define S1G_CAP6_PAGE_SLICING		BIT(4)
+#define S1G_CAP6_TXOP_SHARING_IMP_ACK	BIT(5)
+#define S1G_CAP6_VHT_LINK_ADAPT		GENMASK(7, 6)
+
+#define S1G_CAP7_TACK_AS_PS_POLL		BIT(0)
+#define S1G_CAP7_DUP_1MHZ			BIT(1)
+#define S1G_CAP7_MCS_NEGOTIATION		BIT(2)
+#define S1G_CAP7_1MHZ_CTL_RESPONSE_PREAMBLE	BIT(3)
+#define S1G_CAP7_NDP_BFING_REPORT_POLL		BIT(4)
+#define S1G_CAP7_UNSOLICITED_DYN_AID		BIT(5)
+#define S1G_CAP7_SECTOR_TRAINING_OPERATION	BIT(6)
+#define S1G_CAP7_TEMP_PS_MODE_SWITCH		BIT(7)
+
+#define S1G_CAP8_TWT_GROUPING	BIT(0)
+#define S1G_CAP8_BDT		BIT(1)
+#define S1G_CAP8_COLOR		GENMASK(4, 2)
+#define S1G_CAP8_TWT_REQUEST	BIT(5)
+#define S1G_CAP8_TWT_RESPOND	BIT(6)
+#define S1G_CAP8_PV1_FRAME	BIT(7)
+
+#define S1G_CAP9_LINK_ADAPT_PER_CONTROL_RESPONSE BIT(0)
+
+#define S1G_OPER_CH_WIDTH_PRIMARY_1MHZ	BIT(0)
+#define S1G_OPER_CH_WIDTH_OPER		GENMASK(4, 1)
 
 /* Authentication algorithms */
 #define WLAN_AUTH_OPEN 0
-- 
cgit v1.2.3


From 9026118f20e28f202dab34f219bbb831ffb8c4dc Mon Sep 17 00:00:00 2001
From: Bard Liao <yung-chuan.liao@linux.intel.com>
Date: Tue, 8 Sep 2020 21:15:20 +0800
Subject: soundwire: Add generic bandwidth allocation algorithm

This algorithm computes bus parameters like clock frequency, frame
shape and port transport parameters based on active stream(s) running
on the bus.

Developers can also implement their own .compute_params() callback for
specific resource management algorithm, and set if before calling
sdw_add_bus_master()

Credits: this patch is based on an earlier internal contribution by
Vinod Koul, Sanyog Kale, Shreyas Nc and Hardik Shah. All hard-coded
values were removed from the initial contribution to use BIOS
information instead.

Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Acked-by: Jaroslav Kysela <perex@perex.cz>
Link: https://lore.kernel.org/r/20200908131520.5712-1-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/Kconfig                        |   5 +
 drivers/soundwire/Makefile                       |   3 +
 drivers/soundwire/bus.c                          |   6 +
 drivers/soundwire/bus.h                          |  46 ++-
 drivers/soundwire/generic_bandwidth_allocation.c | 427 +++++++++++++++++++++++
 drivers/soundwire/intel.c                        |   3 +
 drivers/soundwire/stream.c                       |  12 +
 include/linux/soundwire/sdw.h                    |   3 +
 8 files changed, 503 insertions(+), 2 deletions(-)
 create mode 100644 drivers/soundwire/generic_bandwidth_allocation.c

(limited to 'include/linux')

diff --git a/drivers/soundwire/Kconfig b/drivers/soundwire/Kconfig
index f83d02c9c60a..016e74230bb7 100644
--- a/drivers/soundwire/Kconfig
+++ b/drivers/soundwire/Kconfig
@@ -24,6 +24,7 @@ config SOUNDWIRE_CADENCE
 config SOUNDWIRE_INTEL
 	tristate "Intel SoundWire Master driver"
 	select SOUNDWIRE_CADENCE
+	select SOUNDWIRE_GENERIC_ALLOCATION
 	depends on ACPI && SND_SOC
 	help
 	  SoundWire Intel Master driver.
@@ -40,4 +41,8 @@ config SOUNDWIRE_QCOM
 	  If you have an Qualcomm platform which has a SoundWire Master then
 	  enable this config option to get the SoundWire support for that
 	  device
+
+config SOUNDWIRE_GENERIC_ALLOCATION
+	tristate
+
 endif
diff --git a/drivers/soundwire/Makefile b/drivers/soundwire/Makefile
index 7c53ffae9f50..bf1e250d50dd 100644
--- a/drivers/soundwire/Makefile
+++ b/drivers/soundwire/Makefile
@@ -8,6 +8,9 @@ soundwire-bus-y := bus_type.o bus.o master.o slave.o mipi_disco.o stream.o  \
 			sysfs_slave.o sysfs_slave_dpn.o
 obj-$(CONFIG_SOUNDWIRE) += soundwire-bus.o
 
+soundwire-generic-allocation-objs := generic_bandwidth_allocation.o
+obj-$(CONFIG_SOUNDWIRE_GENERIC_ALLOCATION) += soundwire-generic-allocation.o
+
 ifdef CONFIG_DEBUG_FS
 soundwire-bus-y += debugfs.o
 endif
diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c
index 02574b4bb179..340fd1e23e5c 100644
--- a/drivers/soundwire/bus.c
+++ b/drivers/soundwire/bus.c
@@ -61,6 +61,12 @@ int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent,
 		return -EINVAL;
 	}
 
+	if (!bus->compute_params) {
+		dev_err(bus->dev,
+			"Bandwidth allocation not configured, compute_params no set\n");
+		return -EINVAL;
+	}
+
 	mutex_init(&bus->msg_lock);
 	mutex_init(&bus->bus_lock);
 	INIT_LIST_HEAD(&bus->slaves);
diff --git a/drivers/soundwire/bus.h b/drivers/soundwire/bus.h
index c53345fbc4c7..e0703991aad9 100644
--- a/drivers/soundwire/bus.h
+++ b/drivers/soundwire/bus.h
@@ -69,6 +69,7 @@ struct sdw_msg {
 };
 
 #define SDW_DOUBLE_RATE_FACTOR		2
+#define SDW_STRM_RATE_GROUPING		1
 
 extern int sdw_rows[SDW_FRAME_ROWS];
 extern int sdw_cols[SDW_FRAME_COLS];
@@ -154,9 +155,50 @@ int sdw_transfer_defer(struct sdw_bus *bus, struct sdw_msg *msg,
 int sdw_fill_msg(struct sdw_msg *msg, struct sdw_slave *slave,
 		 u32 addr, size_t count, u16 dev_num, u8 flags, u8 *buf);
 
+/* Retrieve and return channel count from channel mask */
+static inline int sdw_ch_mask_to_ch(int ch_mask)
+{
+	int c = 0;
+
+	for (c = 0; ch_mask; ch_mask >>= 1)
+		c += ch_mask & 1;
+
+	return c;
+}
+
+/* Fill transport parameter data structure */
+static inline void sdw_fill_xport_params(struct sdw_transport_params *params,
+					 int port_num, bool grp_ctrl_valid,
+					 int grp_ctrl, int sample_int,
+					 int off1, int off2,
+					 int hstart, int hstop,
+					 int pack_mode, int lane_ctrl)
+{
+	params->port_num = port_num;
+	params->blk_grp_ctrl_valid = grp_ctrl_valid;
+	params->blk_grp_ctrl = grp_ctrl;
+	params->sample_interval = sample_int;
+	params->offset1 = off1;
+	params->offset2 = off2;
+	params->hstart = hstart;
+	params->hstop = hstop;
+	params->blk_pkg_mode = pack_mode;
+	params->lane_ctrl = lane_ctrl;
+}
+
+/* Fill port parameter data structure */
+static inline void sdw_fill_port_params(struct sdw_port_params *params,
+					int port_num, int bps,
+					int flow_mode, int data_mode)
+{
+	params->num = port_num;
+	params->bps = bps;
+	params->flow_mode = flow_mode;
+	params->data_mode = data_mode;
+}
+
 /* Read-Modify-Write Slave register */
-static inline int
-sdw_update(struct sdw_slave *slave, u32 addr, u8 mask, u8 val)
+static inline int sdw_update(struct sdw_slave *slave, u32 addr, u8 mask, u8 val)
 {
 	int tmp;
 
diff --git a/drivers/soundwire/generic_bandwidth_allocation.c b/drivers/soundwire/generic_bandwidth_allocation.c
new file mode 100644
index 000000000000..6088775b67a5
--- /dev/null
+++ b/drivers/soundwire/generic_bandwidth_allocation.c
@@ -0,0 +1,427 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
+// Copyright(c) 2015-2020 Intel Corporation.
+
+/*
+ * Bandwidth management algorithm based on 2^n gears
+ *
+ */
+
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/mod_devicetable.h>
+#include <linux/slab.h>
+#include <linux/soundwire/sdw.h>
+#include "bus.h"
+
+#define SDW_STRM_RATE_GROUPING		1
+
+struct sdw_group_params {
+	unsigned int rate;
+	int full_bw;
+	int payload_bw;
+	int hwidth;
+};
+
+struct sdw_group {
+	unsigned int count;
+	unsigned int max_size;
+	unsigned int *rates;
+};
+
+struct sdw_transport_data {
+	int hstart;
+	int hstop;
+	int block_offset;
+	int sub_block_offset;
+};
+
+static void sdw_compute_slave_ports(struct sdw_master_runtime *m_rt,
+				    struct sdw_transport_data *t_data)
+{
+	struct sdw_slave_runtime *s_rt = NULL;
+	struct sdw_port_runtime *p_rt;
+	int port_bo, sample_int;
+	unsigned int rate, bps, ch = 0;
+	unsigned int slave_total_ch;
+
+	port_bo = t_data->block_offset;
+
+	list_for_each_entry(s_rt, &m_rt->slave_rt_list, m_rt_node) {
+		rate = m_rt->stream->params.rate;
+		bps = m_rt->stream->params.bps;
+		sample_int = (m_rt->bus->params.curr_dr_freq / rate);
+		slave_total_ch = 0;
+
+		list_for_each_entry(p_rt, &s_rt->port_list, port_node) {
+			ch = sdw_ch_mask_to_ch(p_rt->ch_mask);
+
+			sdw_fill_xport_params(&p_rt->transport_params,
+					      p_rt->num, false,
+					      SDW_BLK_GRP_CNT_1,
+					      sample_int, port_bo, port_bo >> 8,
+					      t_data->hstart,
+					      t_data->hstop,
+					      (SDW_BLK_GRP_CNT_1 * ch), 0x0);
+
+			sdw_fill_port_params(&p_rt->port_params,
+					     p_rt->num, bps,
+					     SDW_PORT_FLOW_MODE_ISOCH,
+					     SDW_PORT_DATA_MODE_NORMAL);
+
+			port_bo += bps * ch;
+			slave_total_ch += ch;
+		}
+
+		if (m_rt->direction == SDW_DATA_DIR_TX &&
+		    m_rt->ch_count == slave_total_ch) {
+			/*
+			 * Slave devices were configured to access all channels
+			 * of the stream, which indicates that they operate in
+			 * 'mirror mode'. Make sure we reset the port offset for
+			 * the next device in the list
+			 */
+			port_bo = t_data->block_offset;
+		}
+	}
+}
+
+static void sdw_compute_master_ports(struct sdw_master_runtime *m_rt,
+				     struct sdw_group_params *params,
+				     int port_bo, int hstop)
+{
+	struct sdw_transport_data t_data = {0};
+	struct sdw_port_runtime *p_rt;
+	struct sdw_bus *bus = m_rt->bus;
+	int sample_int, hstart = 0;
+	unsigned int rate, bps, ch, no_ch;
+
+	rate = m_rt->stream->params.rate;
+	bps = m_rt->stream->params.bps;
+	ch = m_rt->ch_count;
+	sample_int = (bus->params.curr_dr_freq / rate);
+
+	if (rate != params->rate)
+		return;
+
+	t_data.hstop = hstop;
+	hstart = hstop - params->hwidth + 1;
+	t_data.hstart = hstart;
+
+	list_for_each_entry(p_rt, &m_rt->port_list, port_node) {
+		no_ch = sdw_ch_mask_to_ch(p_rt->ch_mask);
+
+		sdw_fill_xport_params(&p_rt->transport_params, p_rt->num,
+				      false, SDW_BLK_GRP_CNT_1, sample_int,
+				      port_bo, port_bo >> 8, hstart, hstop,
+				      (SDW_BLK_GRP_CNT_1 * no_ch), 0x0);
+
+		sdw_fill_port_params(&p_rt->port_params,
+				     p_rt->num, bps,
+				     SDW_PORT_FLOW_MODE_ISOCH,
+				     SDW_PORT_DATA_MODE_NORMAL);
+
+		/* Check for first entry */
+		if (!(p_rt == list_first_entry(&m_rt->port_list,
+					       struct sdw_port_runtime,
+					       port_node))) {
+			port_bo += bps * ch;
+			continue;
+		}
+
+		t_data.hstart = hstart;
+		t_data.hstop = hstop;
+		t_data.block_offset = port_bo;
+		t_data.sub_block_offset = 0;
+		port_bo += bps * ch;
+	}
+
+	sdw_compute_slave_ports(m_rt, &t_data);
+}
+
+static void _sdw_compute_port_params(struct sdw_bus *bus,
+				     struct sdw_group_params *params, int count)
+{
+	struct sdw_master_runtime *m_rt = NULL;
+	int hstop = bus->params.col - 1;
+	int block_offset, port_bo, i;
+
+	/* Run loop for all groups to compute transport parameters */
+	for (i = 0; i < count; i++) {
+		port_bo = 1;
+		block_offset = 1;
+
+		list_for_each_entry(m_rt, &bus->m_rt_list, bus_node) {
+			sdw_compute_master_ports(m_rt, &params[i],
+						 port_bo, hstop);
+
+			block_offset += m_rt->ch_count *
+					m_rt->stream->params.bps;
+			port_bo = block_offset;
+		}
+
+		hstop = hstop - params[i].hwidth;
+	}
+}
+
+static int sdw_compute_group_params(struct sdw_bus *bus,
+				    struct sdw_group_params *params,
+				    int *rates, int count)
+{
+	struct sdw_master_runtime *m_rt = NULL;
+	int sel_col = bus->params.col;
+	unsigned int rate, bps, ch;
+	int i, column_needed = 0;
+
+	/* Calculate bandwidth per group */
+	for (i = 0; i < count; i++) {
+		params[i].rate = rates[i];
+		params[i].full_bw = bus->params.curr_dr_freq / params[i].rate;
+	}
+
+	list_for_each_entry(m_rt, &bus->m_rt_list, bus_node) {
+		rate = m_rt->stream->params.rate;
+		bps = m_rt->stream->params.bps;
+		ch = m_rt->ch_count;
+
+		for (i = 0; i < count; i++) {
+			if (rate == params[i].rate)
+				params[i].payload_bw += bps * ch;
+		}
+	}
+
+	for (i = 0; i < count; i++) {
+		params[i].hwidth = (sel_col *
+			params[i].payload_bw + params[i].full_bw - 1) /
+			params[i].full_bw;
+
+		column_needed += params[i].hwidth;
+	}
+
+	if (column_needed > sel_col - 1)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int sdw_add_element_group_count(struct sdw_group *group,
+				       unsigned int rate)
+{
+	int num = group->count;
+	int i;
+
+	for (i = 0; i <= num; i++) {
+		if (rate == group->rates[i])
+			break;
+
+		if (i != num)
+			continue;
+
+		if (group->count >= group->max_size) {
+			unsigned int *rates;
+
+			group->max_size += 1;
+			rates = krealloc(group->rates,
+					 (sizeof(int) * group->max_size),
+					 GFP_KERNEL);
+			if (!rates)
+				return -ENOMEM;
+			group->rates = rates;
+		}
+
+		group->rates[group->count++] = rate;
+	}
+
+	return 0;
+}
+
+static int sdw_get_group_count(struct sdw_bus *bus,
+			       struct sdw_group *group)
+{
+	struct sdw_master_runtime *m_rt;
+	unsigned int rate;
+	int ret = 0;
+
+	group->count = 0;
+	group->max_size = SDW_STRM_RATE_GROUPING;
+	group->rates = kcalloc(group->max_size, sizeof(int), GFP_KERNEL);
+	if (!group->rates)
+		return -ENOMEM;
+
+	list_for_each_entry(m_rt, &bus->m_rt_list, bus_node) {
+		rate = m_rt->stream->params.rate;
+		if (m_rt == list_first_entry(&bus->m_rt_list,
+					     struct sdw_master_runtime,
+					     bus_node)) {
+			group->rates[group->count++] = rate;
+
+		} else {
+			ret = sdw_add_element_group_count(group, rate);
+			if (ret < 0) {
+				kfree(group->rates);
+				return ret;
+			}
+		}
+	}
+
+	return ret;
+}
+
+/**
+ * sdw_compute_port_params: Compute transport and port parameters
+ *
+ * @bus: SDW Bus instance
+ */
+static int sdw_compute_port_params(struct sdw_bus *bus)
+{
+	struct sdw_group_params *params = NULL;
+	struct sdw_group group;
+	int ret;
+
+	ret = sdw_get_group_count(bus, &group);
+	if (ret < 0)
+		return ret;
+
+	if (group.count == 0)
+		goto out;
+
+	params = kcalloc(group.count, sizeof(*params), GFP_KERNEL);
+	if (!params) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	/* Compute transport parameters for grouped streams */
+	ret = sdw_compute_group_params(bus, params,
+				       &group.rates[0], group.count);
+	if (ret < 0)
+		goto free_params;
+
+	_sdw_compute_port_params(bus, params, group.count);
+
+free_params:
+	kfree(params);
+out:
+	kfree(group.rates);
+
+	return ret;
+}
+
+static int sdw_select_row_col(struct sdw_bus *bus, int clk_freq)
+{
+	struct sdw_master_prop *prop = &bus->prop;
+	int frame_int, frame_freq;
+	int r, c;
+
+	for (c = 0; c < SDW_FRAME_COLS; c++) {
+		for (r = 0; r < SDW_FRAME_ROWS; r++) {
+			if (sdw_rows[r] != prop->default_row ||
+			    sdw_cols[c] != prop->default_col)
+				continue;
+
+			frame_int = sdw_rows[r] * sdw_cols[c];
+			frame_freq = clk_freq / frame_int;
+
+			if ((clk_freq - (frame_freq * SDW_FRAME_CTRL_BITS)) <
+			    bus->params.bandwidth)
+				continue;
+
+			bus->params.row = sdw_rows[r];
+			bus->params.col = sdw_cols[c];
+			return 0;
+		}
+	}
+
+	return -EINVAL;
+}
+
+/**
+ * sdw_compute_bus_params: Compute bus parameters
+ *
+ * @bus: SDW Bus instance
+ */
+static int sdw_compute_bus_params(struct sdw_bus *bus)
+{
+	unsigned int max_dr_freq, curr_dr_freq = 0;
+	struct sdw_master_prop *mstr_prop = NULL;
+	int i, clk_values, ret;
+	bool is_gear = false;
+	u32 *clk_buf;
+
+	mstr_prop = &bus->prop;
+	if (!mstr_prop)
+		return -EINVAL;
+
+	if (mstr_prop->num_clk_gears) {
+		clk_values = mstr_prop->num_clk_gears;
+		clk_buf = mstr_prop->clk_gears;
+		is_gear = true;
+	} else if (mstr_prop->num_clk_freq) {
+		clk_values = mstr_prop->num_clk_freq;
+		clk_buf = mstr_prop->clk_freq;
+	} else {
+		clk_values = 1;
+		clk_buf = NULL;
+	}
+
+	max_dr_freq = mstr_prop->max_clk_freq * SDW_DOUBLE_RATE_FACTOR;
+
+	for (i = 0; i < clk_values; i++) {
+		if (!clk_buf)
+			curr_dr_freq = max_dr_freq;
+		else
+			curr_dr_freq = (is_gear) ?
+				(max_dr_freq >>  clk_buf[i]) :
+				clk_buf[i] * SDW_DOUBLE_RATE_FACTOR;
+
+		if (curr_dr_freq <= bus->params.bandwidth)
+			continue;
+
+		break;
+
+		/*
+		 * TODO: Check all the Slave(s) port(s) audio modes and find
+		 * whether given clock rate is supported with glitchless
+		 * transition.
+		 */
+	}
+
+	if (i == clk_values)
+		return -EINVAL;
+
+	ret = sdw_select_row_col(bus, curr_dr_freq);
+	if (ret < 0)
+		return -EINVAL;
+
+	bus->params.curr_dr_freq = curr_dr_freq;
+	return 0;
+}
+
+/**
+ * sdw_compute_params: Compute bus, transport and port parameters
+ *
+ * @bus: SDW Bus instance
+ */
+int sdw_compute_params(struct sdw_bus *bus)
+{
+	int ret;
+
+	/* Computes clock frequency, frame shape and frame frequency */
+	ret = sdw_compute_bus_params(bus);
+	if (ret < 0) {
+		dev_err(bus->dev, "Compute bus params failed: %d", ret);
+		return ret;
+	}
+
+	/* Compute transport and port params */
+	ret = sdw_compute_port_params(bus);
+	if (ret < 0) {
+		dev_err(bus->dev, "Compute transport params failed: %d", ret);
+		return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(sdw_compute_params);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("SoundWire Generic Bandwidth Allocation");
diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c
index e047910d73f5..1211d114ff59 100644
--- a/drivers/soundwire/intel.c
+++ b/drivers/soundwire/intel.c
@@ -1318,6 +1318,9 @@ static int intel_master_probe(struct platform_device *pdev)
 	/* set driver data, accessed by snd_soc_dai_get_drvdata() */
 	dev_set_drvdata(dev, cdns);
 
+	/* use generic bandwidth allocation algorithm */
+	sdw->cdns.bus.compute_params = sdw_compute_params;
+
 	ret = sdw_bus_master_add(bus, dev, dev->fwnode);
 	if (ret) {
 		dev_err(dev, "sdw_bus_master_add fail: %d\n", ret);
diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c
index b8b1973e3ee2..f3219d1fa63b 100644
--- a/drivers/soundwire/stream.c
+++ b/drivers/soundwire/stream.c
@@ -25,8 +25,10 @@
 int sdw_rows[SDW_FRAME_ROWS] = {48, 50, 60, 64, 75, 80, 125, 147,
 			96, 100, 120, 128, 150, 160, 250, 0,
 			192, 200, 240, 256, 72, 144, 90, 180};
+EXPORT_SYMBOL(sdw_rows);
 
 int sdw_cols[SDW_FRAME_COLS] = {2, 4, 6, 8, 10, 12, 14, 16};
+EXPORT_SYMBOL(sdw_cols);
 
 int sdw_find_col_index(int col)
 {
@@ -1782,6 +1784,16 @@ static int _sdw_deprepare_stream(struct sdw_stream_runtime *stream)
 		bus->params.bandwidth -= m_rt->stream->params.rate *
 			m_rt->ch_count * m_rt->stream->params.bps;
 
+		/* Compute params */
+		if (bus->compute_params) {
+			ret = bus->compute_params(bus);
+			if (ret < 0) {
+				dev_err(bus->dev, "Compute params failed: %d",
+					ret);
+				return ret;
+			}
+		}
+
 		/* Program params */
 		ret = sdw_program_params(bus, false);
 		if (ret < 0) {
diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 790823d2d33b..de9ea2ce2d35 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -964,6 +964,9 @@ struct sdw_stream_runtime {
 
 struct sdw_stream_runtime *sdw_alloc_stream(const char *stream_name);
 void sdw_release_stream(struct sdw_stream_runtime *stream);
+
+int sdw_compute_params(struct sdw_bus *bus);
+
 int sdw_stream_add_master(struct sdw_bus *bus,
 		struct sdw_stream_config *stream_config,
 		struct sdw_port_config *port_config,
-- 
cgit v1.2.3


From 264c03a245de7c5b1cc3836db45de6b991f877ca Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Mon, 14 Sep 2020 16:34:07 +0100
Subject: stacktrace: Remove reliable argument from arch_stack_walk() callback

Currently the callback passed to arch_stack_walk() has an argument called
reliable passed to it to indicate if the stack entry is reliable, a comment
says that this is used by some printk() consumers. However in the current
kernel none of the arch_stack_walk() implementations ever set this flag to
true and the only callback implementation we have is in the generic
stacktrace code which ignores the flag. It therefore appears that this
flag is redundant so we can simplify and clarify things by removing it.

Signed-off-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Miroslav Benes <mbenes@suse.cz>
Link: https://lore.kernel.org/r/20200914153409.25097-2-broonie@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/s390/kernel/stacktrace.c |  4 ++--
 arch/x86/kernel/stacktrace.c  | 10 +++++-----
 include/linux/stacktrace.h    |  5 +----
 kernel/stacktrace.c           |  8 +++-----
 4 files changed, 11 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c
index fc5419ac64c8..7f1266c24f6b 100644
--- a/arch/s390/kernel/stacktrace.c
+++ b/arch/s390/kernel/stacktrace.c
@@ -19,7 +19,7 @@ void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
 
 	unwind_for_each_frame(&state, task, regs, 0) {
 		addr = unwind_get_return_address(&state);
-		if (!addr || !consume_entry(cookie, addr, false))
+		if (!addr || !consume_entry(cookie, addr))
 			break;
 	}
 }
@@ -56,7 +56,7 @@ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry,
 			return -EINVAL;
 #endif
 
-		if (!consume_entry(cookie, addr, false))
+		if (!consume_entry(cookie, addr))
 			return -EINVAL;
 	}
 
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 2fd698e28e4d..8627fda8d993 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -18,13 +18,13 @@ void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
 	struct unwind_state state;
 	unsigned long addr;
 
-	if (regs && !consume_entry(cookie, regs->ip, false))
+	if (regs && !consume_entry(cookie, regs->ip))
 		return;
 
 	for (unwind_start(&state, task, regs, NULL); !unwind_done(&state);
 	     unwind_next_frame(&state)) {
 		addr = unwind_get_return_address(&state);
-		if (!addr || !consume_entry(cookie, addr, false))
+		if (!addr || !consume_entry(cookie, addr))
 			break;
 	}
 }
@@ -72,7 +72,7 @@ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry,
 		if (!addr)
 			return -EINVAL;
 
-		if (!consume_entry(cookie, addr, false))
+		if (!consume_entry(cookie, addr))
 			return -EINVAL;
 	}
 
@@ -114,7 +114,7 @@ void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie,
 {
 	const void __user *fp = (const void __user *)regs->bp;
 
-	if (!consume_entry(cookie, regs->ip, false))
+	if (!consume_entry(cookie, regs->ip))
 		return;
 
 	while (1) {
@@ -128,7 +128,7 @@ void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie,
 			break;
 		if (!frame.ret_addr)
 			break;
-		if (!consume_entry(cookie, frame.ret_addr, false))
+		if (!consume_entry(cookie, frame.ret_addr))
 			break;
 		fp = frame.next_fp;
 	}
diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h
index b7af8cc13eda..50e2df30b0aa 100644
--- a/include/linux/stacktrace.h
+++ b/include/linux/stacktrace.h
@@ -29,14 +29,11 @@ unsigned int stack_trace_save_user(unsigned long *store, unsigned int size);
  * stack_trace_consume_fn - Callback for arch_stack_walk()
  * @cookie:	Caller supplied pointer handed back by arch_stack_walk()
  * @addr:	The stack entry address to consume
- * @reliable:	True when the stack entry is reliable. Required by
- *		some printk based consumers.
  *
  * Return:	True, if the entry was consumed or skipped
  *		False, if there is no space left to store
  */
-typedef bool (*stack_trace_consume_fn)(void *cookie, unsigned long addr,
-				       bool reliable);
+typedef bool (*stack_trace_consume_fn)(void *cookie, unsigned long addr);
 /**
  * arch_stack_walk - Architecture specific function to walk the stack
  * @consume_entry:	Callback which is invoked by the architecture code for
diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c
index 946f44a9e86a..9f8117c7cfdd 100644
--- a/kernel/stacktrace.c
+++ b/kernel/stacktrace.c
@@ -78,8 +78,7 @@ struct stacktrace_cookie {
 	unsigned int	len;
 };
 
-static bool stack_trace_consume_entry(void *cookie, unsigned long addr,
-				      bool reliable)
+static bool stack_trace_consume_entry(void *cookie, unsigned long addr)
 {
 	struct stacktrace_cookie *c = cookie;
 
@@ -94,12 +93,11 @@ static bool stack_trace_consume_entry(void *cookie, unsigned long addr,
 	return c->len < c->size;
 }
 
-static bool stack_trace_consume_entry_nosched(void *cookie, unsigned long addr,
-					      bool reliable)
+static bool stack_trace_consume_entry_nosched(void *cookie, unsigned long addr)
 {
 	if (in_sched_functions(addr))
 		return true;
-	return stack_trace_consume_entry(cookie, addr, reliable);
+	return stack_trace_consume_entry(cookie, addr);
 }
 
 /**
-- 
cgit v1.2.3


From 874f635310648a5adcedbd7e02ea0555cfa1da56 Mon Sep 17 00:00:00 2001
From: Ionela Voinescu <ionela.voinescu@arm.com>
Date: Tue, 1 Sep 2020 21:55:47 +0100
Subject: cpufreq: report whether cpufreq supports Frequency Invariance (FI)

Now that the update of the FI scale factor is done in cpufreq core for
selected functions - target(), target_index() and fast_switch(),
we can provide feedback to the task scheduler and architecture code
on whether cpufreq supports FI.

For this purpose provide an external function to expose whether the
cpufreq drivers support FI, by using a static key.

The logic behind the enablement of cpufreq-based invariance is as
follows:
 - cpufreq-based invariance is disabled by default
 - cpufreq-based invariance is enabled if any of the callbacks
   above is implemented while the unsupported setpolicy() is not

The cpufreq_supports_freq_invariance() function only returns whether
cpufreq is instrumented with the arch_set_freq_scale() calls that
result in support for frequency invariance. Due to the lack of knowledge
on whether the implementation of arch_set_freq_scale() actually results
in the setting of a scale factor based on cpufreq information, it is up
to the architecture code to ensure the setting and provision of the
scale factor to the scheduler.

Signed-off-by: Ionela Voinescu <ionela.voinescu@arm.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/cpufreq.c | 16 ++++++++++++++++
 include/linux/cpufreq.h   |  5 +++++
 2 files changed, 21 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 4d5fe777184a..570bf2ebe9d4 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -61,6 +61,12 @@ static struct cpufreq_driver *cpufreq_driver;
 static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data);
 static DEFINE_RWLOCK(cpufreq_driver_lock);
 
+static DEFINE_STATIC_KEY_FALSE(cpufreq_freq_invariance);
+bool cpufreq_supports_freq_invariance(void)
+{
+	return static_branch_likely(&cpufreq_freq_invariance);
+}
+
 /* Flag to suspend/resume CPUFreq governors */
 static bool cpufreq_suspended;
 
@@ -2720,6 +2726,15 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 	cpufreq_driver = driver_data;
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
+	/*
+	 * Mark support for the scheduler's frequency invariance engine for
+	 * drivers that implement target(), target_index() or fast_switch().
+	 */
+	if (!cpufreq_driver->setpolicy) {
+		static_branch_enable_cpuslocked(&cpufreq_freq_invariance);
+		pr_debug("supports frequency invariance");
+	}
+
 	if (driver_data->setpolicy)
 		driver_data->flags |= CPUFREQ_CONST_LOOPS;
 
@@ -2789,6 +2804,7 @@ int cpufreq_unregister_driver(struct cpufreq_driver *driver)
 	cpus_read_lock();
 	subsys_interface_unregister(&cpufreq_interface);
 	remove_boost_sysfs_file();
+	static_branch_disable_cpuslocked(&cpufreq_freq_invariance);
 	cpuhp_remove_state_nocalls_cpuslocked(hp_online);
 
 	write_lock_irqsave(&cpufreq_driver_lock, flags);
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index a911e5d06845..e54767e2a68a 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -217,6 +217,7 @@ void refresh_frequency_limits(struct cpufreq_policy *policy);
 void cpufreq_update_policy(unsigned int cpu);
 void cpufreq_update_limits(unsigned int cpu);
 bool have_governor_per_policy(void);
+bool cpufreq_supports_freq_invariance(void);
 struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy);
 void cpufreq_enable_fast_switch(struct cpufreq_policy *policy);
 void cpufreq_disable_fast_switch(struct cpufreq_policy *policy);
@@ -237,6 +238,10 @@ static inline unsigned int cpufreq_get_hw_max_freq(unsigned int cpu)
 {
 	return 0;
 }
+static inline bool cpufreq_supports_freq_invariance(void)
+{
+	return false;
+}
 static inline void disable_cpufreq(void) { }
 #endif
 
-- 
cgit v1.2.3


From ecddc3a0d5d752071c627aa1a1d4d7b529ddae67 Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Tue, 1 Sep 2020 21:55:48 +0100
Subject: arch_topology, cpufreq: constify arch_* cpumasks

The passed cpumask arguments to arch_set_freq_scale() and
arch_freq_counters_available() are only iterated over, so reflect this
in the prototype. This also allows to pass system cpumasks like
cpu_online_mask without getting a warning.

Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Ionela Voinescu <ionela.voinescu@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 arch/arm64/kernel/topology.c  | 2 +-
 drivers/base/arch_topology.c  | 4 ++--
 drivers/cpufreq/cpufreq.c     | 5 +++--
 include/linux/arch_topology.h | 2 +-
 include/linux/cpufreq.h       | 3 ++-
 5 files changed, 9 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 0801a0f3c156..9a9f2b8dedf5 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -253,7 +253,7 @@ free_valid_mask:
 }
 late_initcall_sync(init_amu_fie);
 
-bool arch_freq_counters_available(struct cpumask *cpus)
+bool arch_freq_counters_available(const struct cpumask *cpus)
 {
 	return amu_freq_invariant() &&
 	       cpumask_subset(cpus, amu_fie_cpus);
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index 42a08ef693ae..91de5331ac8a 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -21,13 +21,13 @@
 #include <linux/sched.h>
 #include <linux/smp.h>
 
-__weak bool arch_freq_counters_available(struct cpumask *cpus)
+__weak bool arch_freq_counters_available(const struct cpumask *cpus)
 {
 	return false;
 }
 DEFINE_PER_CPU(unsigned long, freq_scale) = SCHED_CAPACITY_SCALE;
 
-void arch_set_freq_scale(struct cpumask *cpus, unsigned long cur_freq,
+void arch_set_freq_scale(const struct cpumask *cpus, unsigned long cur_freq,
 			 unsigned long max_freq)
 {
 	unsigned long scale;
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 570bf2ebe9d4..2ea245a6c0c0 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -160,8 +160,9 @@ u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy)
 }
 EXPORT_SYMBOL_GPL(get_cpu_idle_time);
 
-__weak void arch_set_freq_scale(struct cpumask *cpus, unsigned long cur_freq,
-		unsigned long max_freq)
+__weak void arch_set_freq_scale(const struct cpumask *cpus,
+				unsigned long cur_freq,
+				unsigned long max_freq)
 {
 }
 EXPORT_SYMBOL_GPL(arch_set_freq_scale);
diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h
index 69b1dabe39dc..810c83336257 100644
--- a/include/linux/arch_topology.h
+++ b/include/linux/arch_topology.h
@@ -30,7 +30,7 @@ static inline unsigned long topology_get_freq_scale(int cpu)
 	return per_cpu(freq_scale, cpu);
 }
 
-bool arch_freq_counters_available(struct cpumask *cpus);
+bool arch_freq_counters_available(const struct cpumask *cpus);
 
 DECLARE_PER_CPU(unsigned long, thermal_pressure);
 
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index e54767e2a68a..9f779fbdbe7b 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -1011,7 +1011,8 @@ static inline void sched_cpufreq_governor_change(struct cpufreq_policy *policy,
 extern void arch_freq_prepare_all(void);
 extern unsigned int arch_freq_get_on_cpu(int cpu);
 
-extern void arch_set_freq_scale(struct cpumask *cpus, unsigned long cur_freq,
+extern void arch_set_freq_scale(const struct cpumask *cpus,
+				unsigned long cur_freq,
 				unsigned long max_freq);
 
 /* the following are really really optional */
-- 
cgit v1.2.3


From 15e5d5b45b2b7072214af519357a1c0af078c50b Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Tue, 1 Sep 2020 21:55:49 +0100
Subject: arch_topology, arm, arm64: define arch_scale_freq_invariant()

arch_scale_freq_invariant() is used by schedutil to determine whether
the scheduler's load-tracking signals are frequency invariant. Its
definition is overridable, though by default it is hardcoded to 'true'
if arch_scale_freq_capacity() is defined ('false' otherwise).

This behaviour is not overridden on arm, arm64 and other users of the
generic arch topology driver, which is somewhat precarious:
arch_scale_freq_capacity() will always be defined, yet not all cpufreq
drivers are guaranteed to drive the frequency invariance scale factor
setting. In other words, the load-tracking signals may very well *not*
be frequency invariant.

Now that cpufreq can be queried on whether the current driver is driving
the Frequency Invariance (FI) scale setting, the current situation can
be improved. This combines the query of whether cpufreq supports the
setting of the frequency scale factor, with whether all online CPUs are
counter-based FI enabled.

While cpufreq FI enablement applies at system level, for all CPUs,
counter-based FI support could also be used for only a subset of CPUs to
set the invariance scale factor. Therefore, if cpufreq-based FI support
is present, we consider the system to be invariant. If missing, we
require all online CPUs to be counter-based FI enabled in order for the
full system to be considered invariant.

If the system ends up not being invariant, a new condition is needed in
the counter initialization code that disables all scale factor setting
based on counters.

Precedence of counters over cpufreq use is not important here. The
invariant status is only given to the system if all CPUs have at least
one method of setting the frequency scale factor.

Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Ionela Voinescu <ionela.voinescu@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 arch/arm/include/asm/topology.h   | 1 +
 arch/arm64/include/asm/topology.h | 1 +
 arch/arm64/kernel/topology.c      | 7 +++++++
 drivers/base/arch_topology.c      | 6 ++++++
 include/linux/arch_topology.h     | 2 ++
 5 files changed, 17 insertions(+)

(limited to 'include/linux')

diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
index e0593cf095d0..9219e67befbe 100644
--- a/arch/arm/include/asm/topology.h
+++ b/arch/arm/include/asm/topology.h
@@ -9,6 +9,7 @@
 
 /* Replace task scheduler's default frequency-invariant accounting */
 #define arch_scale_freq_capacity topology_get_freq_scale
+#define arch_scale_freq_invariant topology_scale_freq_invariant
 
 /* Replace task scheduler's default cpu-invariant accounting */
 #define arch_scale_cpu_capacity topology_get_cpu_scale
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
index e042f6527981..7cb519473fbd 100644
--- a/arch/arm64/include/asm/topology.h
+++ b/arch/arm64/include/asm/topology.h
@@ -27,6 +27,7 @@ void topology_scale_freq_tick(void);
 
 /* Replace task scheduler's default frequency-invariant accounting */
 #define arch_scale_freq_capacity topology_get_freq_scale
+#define arch_scale_freq_invariant topology_scale_freq_invariant
 
 /* Replace task scheduler's default cpu-invariant accounting */
 #define arch_scale_cpu_capacity topology_get_cpu_scale
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 9a9f2b8dedf5..4064d39bb66d 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -246,6 +246,13 @@ static int __init init_amu_fie(void)
 		static_branch_enable(&amu_fie_key);
 	}
 
+	/*
+	 * If the system is not fully invariant after AMU init, disable
+	 * partial use of counters for frequency invariance.
+	 */
+	if (!topology_scale_freq_invariant())
+		static_branch_disable(&amu_fie_key);
+
 free_valid_mask:
 	free_cpumask_var(valid_cpus);
 
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index 91de5331ac8a..89cae168b076 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -21,6 +21,12 @@
 #include <linux/sched.h>
 #include <linux/smp.h>
 
+bool topology_scale_freq_invariant(void)
+{
+	return cpufreq_supports_freq_invariance() ||
+	       arch_freq_counters_available(cpu_online_mask);
+}
+
 __weak bool arch_freq_counters_available(const struct cpumask *cpus)
 {
 	return false;
diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h
index 810c83336257..083df331a3c9 100644
--- a/include/linux/arch_topology.h
+++ b/include/linux/arch_topology.h
@@ -30,6 +30,8 @@ static inline unsigned long topology_get_freq_scale(int cpu)
 	return per_cpu(freq_scale, cpu);
 }
 
+bool topology_scale_freq_invariant(void);
+
 bool arch_freq_counters_available(const struct cpumask *cpus);
 
 DECLARE_PER_CPU(unsigned long, thermal_pressure);
-- 
cgit v1.2.3


From 6d1349c769ea28543bdde20a658cbc93c3bc936d Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 18 Sep 2020 16:45:50 -0400
Subject: [PATCH] reduce boilerplate in fsid handling

Get rid of boilerplate in most of ->statfs()
instances...

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/9p/vfs_super.c      | 3 +--
 fs/adfs/super.c        | 3 +--
 fs/affs/super.c        | 3 +--
 fs/befs/linuxvfs.c     | 3 +--
 fs/bfs/inode.c         | 3 +--
 fs/ceph/super.c        | 3 +--
 fs/cramfs/inode.c      | 3 +--
 fs/efs/super.c         | 3 +--
 fs/erofs/super.c       | 3 +--
 fs/exfat/super.c       | 3 +--
 fs/ext2/super.c        | 3 +--
 fs/ext4/super.c        | 3 +--
 fs/f2fs/super.c        | 3 +--
 fs/fat/inode.c         | 3 +--
 fs/hfs/super.c         | 3 +--
 fs/hfsplus/super.c     | 3 +--
 fs/hpfs/super.c        | 3 +--
 fs/isofs/inode.c       | 3 +--
 fs/minix/inode.c       | 3 +--
 fs/nilfs2/super.c      | 3 +--
 fs/ntfs/super.c        | 3 +--
 fs/omfs/inode.c        | 3 +--
 fs/qnx4/inode.c        | 3 +--
 fs/qnx6/inode.c        | 3 +--
 fs/romfs/super.c       | 3 +--
 fs/squashfs/super.c    | 3 +--
 fs/sysv/inode.c        | 3 +--
 fs/udf/super.c         | 3 +--
 fs/ufs/super.c         | 3 +--
 fs/xfs/xfs_super.c     | 3 +--
 fs/zonefs/super.c      | 3 +--
 include/linux/statfs.h | 5 +++++
 32 files changed, 36 insertions(+), 62 deletions(-)

(limited to 'include/linux')

diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index 74df32be4c6a..124855b3324d 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -258,8 +258,7 @@ static int v9fs_statfs(struct dentry *dentry, struct kstatfs *buf)
 			buf->f_bavail = rs.bavail;
 			buf->f_files = rs.files;
 			buf->f_ffree = rs.ffree;
-			buf->f_fsid.val[0] = rs.fsid & 0xFFFFFFFFUL;
-			buf->f_fsid.val[1] = (rs.fsid >> 32) & 0xFFFFFFFFUL;
+			buf->f_fsid = u64_to_fsid(rs.fsid);
 			buf->f_namelen = rs.namelen;
 		}
 		if (res != -ENOSYS)
diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index d553bb5bc17a..bdbd26e571ed 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -210,8 +210,7 @@ static int adfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_namelen = sbi->s_namelen;
 	buf->f_bsize   = sb->s_blocksize;
 	buf->f_ffree   = (long)(buf->f_bfree * buf->f_files) / (long)buf->f_blocks;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid    = u64_to_fsid(id);
 
 	return 0;
 }
diff --git a/fs/affs/super.c b/fs/affs/super.c
index 47107c6712a6..890b44874f0f 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -620,8 +620,7 @@ affs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_blocks  = AFFS_SB(sb)->s_partition_size - AFFS_SB(sb)->s_reserved;
 	buf->f_bfree   = free;
 	buf->f_bavail  = free;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid    = u64_to_fsid(id);
 	buf->f_namelen = AFFSNAMEMAX;
 	return 0;
 }
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index 2482032021ca..c1ba13d19024 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -963,8 +963,7 @@ befs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bavail = buf->f_bfree;
 	buf->f_files = 0;	/* UNKNOWN */
 	buf->f_ffree = 0;	/* UNKNOWN */
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 	buf->f_namelen = BEFS_NAME_LEN;
 
 	befs_debug(sb, "<--- %s", __func__);
diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c
index f8ce1368218b..3ac7611ef7ce 100644
--- a/fs/bfs/inode.c
+++ b/fs/bfs/inode.c
@@ -229,8 +229,7 @@ static int bfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bfree = buf->f_bavail = info->si_freeb;
 	buf->f_files = info->si_lasti + 1 - BFS_ROOT_INO;
 	buf->f_ffree = info->si_freei;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 	buf->f_namelen = BFS_NAMELEN;
 	return 0;
 }
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 7ec0e6d03d10..cafb252a9d98 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -104,8 +104,7 @@ static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
 	       le64_to_cpu(*((__le64 *)&monc->monmap->fsid + 1));
 	mutex_unlock(&monc->mutex);
 
-	buf->f_fsid.val[0] = fsid & 0xffffffff;
-	buf->f_fsid.val[1] = fsid >> 32;
+	buf->f_fsid = u64_to_fsid(fsid);
 
 	return 0;
 }
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index 912308600d39..4b90cfd1ec36 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -690,8 +690,7 @@ static int cramfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bavail = 0;
 	buf->f_files = CRAMFS_SB(sb)->files;
 	buf->f_ffree = 0;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 	buf->f_namelen = CRAMFS_MAXPATHLEN;
 	return 0;
 }
diff --git a/fs/efs/super.c b/fs/efs/super.c
index a4a945d0ac6a..62b155b9366b 100644
--- a/fs/efs/super.c
+++ b/fs/efs/super.c
@@ -342,8 +342,7 @@ static int efs_statfs(struct dentry *dentry, struct kstatfs *buf) {
 			sbi->inode_blocks *
 			(EFS_BLOCKSIZE / sizeof(struct efs_dinode));
 	buf->f_ffree   = sbi->inode_free;	/* free inodes */
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid    = u64_to_fsid(id);
 	buf->f_namelen = EFS_MAXNAMELEN;	/* max filename length */
 
 	return 0;
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index ddaa516c008a..744089ab134c 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -563,8 +563,7 @@ static int erofs_statfs(struct dentry *dentry, struct kstatfs *buf)
 
 	buf->f_namelen = EROFS_NAME_LEN;
 
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid    = u64_to_fsid(id);
 	return 0;
 }
 
diff --git a/fs/exfat/super.c b/fs/exfat/super.c
index 3b6a1659892f..ea17e8ed5067 100644
--- a/fs/exfat/super.c
+++ b/fs/exfat/super.c
@@ -89,8 +89,7 @@ static int exfat_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_blocks = sbi->num_clusters - 2; /* clu 0 & 1 */
 	buf->f_bfree = buf->f_blocks - sbi->used_clusters;
 	buf->f_bavail = buf->f_bfree;
-	buf->f_fsid.val[0] = (unsigned int)id;
-	buf->f_fsid.val[1] = (unsigned int)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 	/* Unicode utf16 255 characters */
 	buf->f_namelen = EXFAT_MAX_FILE_LEN * NLS_MAX_CHARSET_SIZE;
 	return 0;
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index dda860562ca3..4911c59679bb 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -1455,8 +1455,7 @@ static int ext2_statfs (struct dentry * dentry, struct kstatfs * buf)
 	buf->f_namelen = EXT2_NAME_LEN;
 	fsid = le64_to_cpup((void *)es->s_uuid) ^
 	       le64_to_cpup((void *)es->s_uuid + sizeof(u64));
-	buf->f_fsid.val[0] = fsid & 0xFFFFFFFFUL;
-	buf->f_fsid.val[1] = (fsid >> 32) & 0xFFFFFFFFUL;
+	buf->f_fsid = u64_to_fsid(fsid);
 	spin_unlock(&sbi->s_lock);
 	return 0;
 }
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 0907f907c47d..eef0a7d81e0d 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -5787,8 +5787,7 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_namelen = EXT4_NAME_LEN;
 	fsid = le64_to_cpup((void *)es->s_uuid) ^
 	       le64_to_cpup((void *)es->s_uuid + sizeof(u64));
-	buf->f_fsid.val[0] = fsid & 0xFFFFFFFFUL;
-	buf->f_fsid.val[1] = (fsid >> 32) & 0xFFFFFFFFUL;
+	buf->f_fsid = u64_to_fsid(fsid);
 
 #ifdef CONFIG_QUOTA
 	if (ext4_test_inode_flag(dentry->d_inode, EXT4_INODE_PROJINHERIT) &&
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index dfa072fa8081..088872f4e568 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1422,8 +1422,7 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	}
 
 	buf->f_namelen = F2FS_NAME_LEN;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid    = u64_to_fsid(id);
 
 #ifdef CONFIG_QUOTA
 	if (is_inode_flag_set(dentry->d_inode, FI_PROJ_INHERIT) &&
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index a0cf99debb1e..bab9b202b496 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -836,8 +836,7 @@ static int fat_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_blocks = sbi->max_cluster - FAT_START_ENT;
 	buf->f_bfree = sbi->free_clusters;
 	buf->f_bavail = sbi->free_clusters;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 	buf->f_namelen =
 		(sbi->options.isvfat ? FAT_LFN_LEN : 12) * NLS_MAX_CHARSET_SIZE;
 
diff --git a/fs/hfs/super.c b/fs/hfs/super.c
index c33324686d89..44d07c9e3a7f 100644
--- a/fs/hfs/super.c
+++ b/fs/hfs/super.c
@@ -104,8 +104,7 @@ static int hfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bavail = buf->f_bfree;
 	buf->f_files = HFS_SB(sb)->fs_ablocks;
 	buf->f_ffree = HFS_SB(sb)->free_ablocks;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 	buf->f_namelen = HFS_NAMELEN;
 
 	return 0;
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 129dca3f4b78..807119ae5adf 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -320,8 +320,7 @@ static int hfsplus_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bavail = buf->f_bfree;
 	buf->f_files = 0xFFFFFFFF;
 	buf->f_ffree = 0xFFFFFFFF - sbi->next_cnid;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 	buf->f_namelen = HFSPLUS_MAX_STRLEN;
 
 	return 0;
diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c
index 0a677a9aaf34..a7dbfc892022 100644
--- a/fs/hpfs/super.c
+++ b/fs/hpfs/super.c
@@ -192,8 +192,7 @@ static int hpfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bavail = sbi->sb_n_free;
 	buf->f_files = sbi->sb_dirband_size / 4;
 	buf->f_ffree = hpfs_get_free_dnodes(s);
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 	buf->f_namelen = 254;
 
 	hpfs_unlock(s);
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index 78f5c96c76f3..ec90773527ee 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -1038,8 +1038,7 @@ static int isofs_statfs (struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bavail = 0;
 	buf->f_files = ISOFS_SB(sb)->s_ninodes;
 	buf->f_ffree = 0;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 	buf->f_namelen = NAME_MAX;
 	return 0;
 }
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index 7b09a9158e40..34f546404aa1 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -383,8 +383,7 @@ static int minix_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_files = sbi->s_ninodes;
 	buf->f_ffree = minix_count_free_inodes(sb);
 	buf->f_namelen = sbi->s_namelen;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 
 	return 0;
 }
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 2eee5fb1a882..4abd928b0bc8 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -651,8 +651,7 @@ static int nilfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_files = nmaxinodes;
 	buf->f_ffree = nfreeinodes;
 	buf->f_namelen = NILFS_NAME_LEN;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 
 	return 0;
 }
diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c
index 7dc3bc604f78..0d7e948cb29c 100644
--- a/fs/ntfs/super.c
+++ b/fs/ntfs/super.c
@@ -2643,8 +2643,7 @@ static int ntfs_statfs(struct dentry *dentry, struct kstatfs *sfs)
 	 * the least significant 32-bits in f_fsid[0] and the most significant
 	 * 32-bits in f_fsid[1].
 	 */
-	sfs->f_fsid.val[0] = vol->serial_no & 0xffffffff;
-	sfs->f_fsid.val[1] = (vol->serial_no >> 32) & 0xffffffff;
+	sfs->f_fsid = u64_to_fsid(vol->serial_no);
 	/* Maximum length of filenames. */
 	sfs->f_namelen	   = NTFS_MAX_NAME_LEN;
 	return 0;
diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c
index b76ec6b88ded..68aa38a48308 100644
--- a/fs/omfs/inode.c
+++ b/fs/omfs/inode.c
@@ -282,8 +282,7 @@ static int omfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_blocks = sbi->s_num_blocks;
 	buf->f_files = sbi->s_num_blocks;
 	buf->f_namelen = OMFS_NAMELEN;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 
 	buf->f_bfree = buf->f_bavail = buf->f_ffree =
 		omfs_count_free(s);
diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c
index e8da1cde87b9..3fb7fc819b4f 100644
--- a/fs/qnx4/inode.c
+++ b/fs/qnx4/inode.c
@@ -137,8 +137,7 @@ static int qnx4_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bfree   = qnx4_count_free_blocks(sb);
 	buf->f_bavail  = buf->f_bfree;
 	buf->f_namelen = QNX4_NAME_MAX;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid    = u64_to_fsid(id);
 
 	return 0;
 }
diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c
index 755293c8c71a..61191f7bdf62 100644
--- a/fs/qnx6/inode.c
+++ b/fs/qnx6/inode.c
@@ -166,8 +166,7 @@ static int qnx6_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_ffree   = fs32_to_cpu(sbi, sbi->sb->sb_free_inodes);
 	buf->f_bavail  = buf->f_bfree;
 	buf->f_namelen = QNX6_LONG_NAME_MAX;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid    = u64_to_fsid(id);
 
 	return 0;
 }
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index e582d001f792..d69c8e4f4973 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -415,8 +415,7 @@ static int romfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bfree = buf->f_bavail = buf->f_ffree;
 	buf->f_blocks =
 		(romfs_maxsize(dentry->d_sb) + ROMBSIZE - 1) >> ROMBSBITS;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 	return 0;
 }
 
diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c
index 0cc4ceec0562..d6c6593ec169 100644
--- a/fs/squashfs/super.c
+++ b/fs/squashfs/super.c
@@ -380,8 +380,7 @@ static int squashfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_files = msblk->inodes;
 	buf->f_ffree = 0;
 	buf->f_namelen = SQUASHFS_NAME_LEN;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 
 	return 0;
 }
diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c
index 02b1d9d0c182..be47263b8605 100644
--- a/fs/sysv/inode.c
+++ b/fs/sysv/inode.c
@@ -98,8 +98,7 @@ static int sysv_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_files = sbi->s_ninodes;
 	buf->f_ffree = sysv_count_free_inodes(sb);
 	buf->f_namelen = SYSV_NAMELEN;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 	return 0;
 }
 
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 1c42f544096d..d40ecaf3c2c2 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -2411,8 +2411,7 @@ static int udf_statfs(struct dentry *dentry, struct kstatfs *buf)
 			+ buf->f_bfree;
 	buf->f_ffree = buf->f_bfree;
 	buf->f_namelen = UDF_NAME_LEN;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 
 	return 0;
 }
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index e3b69fb280e8..983558b572c7 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -1431,8 +1431,7 @@ static int ufs_statfs(struct dentry *dentry, struct kstatfs *buf)
 		? (buf->f_bfree - uspi->s_root_blocks) : 0;
 	buf->f_files = uspi->s_ncg * uspi->s_ipg;
 	buf->f_namelen = UFS_MAXNAMLEN;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 
 	mutex_unlock(&UFS_SB(sb)->s_lock);
 
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 71ac6c1cdc36..2e04dfc373c1 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -794,8 +794,7 @@ xfs_fs_statfs(
 	statp->f_namelen = MAXNAMELEN - 1;
 
 	id = huge_encode_dev(mp->m_ddev_targp->bt_dev);
-	statp->f_fsid.val[0] = (u32)id;
-	statp->f_fsid.val[1] = (u32)(id >> 32);
+	statp->f_fsid = u64_to_fsid(id);
 
 	icount = percpu_counter_sum(&mp->m_icount);
 	ifree = percpu_counter_sum(&mp->m_ifree);
diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index 8ec7c8f109d7..763f48541c68 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -932,8 +932,7 @@ static int zonefs_statfs(struct dentry *dentry, struct kstatfs *buf)
 
 	fsid = le64_to_cpup((void *)sbi->s_uuid.b) ^
 		le64_to_cpup((void *)sbi->s_uuid.b + sizeof(u64));
-	buf->f_fsid.val[0] = (u32)fsid;
-	buf->f_fsid.val[1] = (u32)(fsid >> 32);
+	buf->f_fsid = u64_to_fsid(fsid);
 
 	return 0;
 }
diff --git a/include/linux/statfs.h b/include/linux/statfs.h
index fac4356ea1bf..20f695b90aab 100644
--- a/include/linux/statfs.h
+++ b/include/linux/statfs.h
@@ -45,4 +45,9 @@ struct kstatfs {
 struct dentry;
 extern int vfs_get_fsid(struct dentry *dentry, __kernel_fsid_t *fsid);
 
+static inline __kernel_fsid_t u64_to_fsid(u64 v)
+{
+	return (__kernel_fsid_t){.val = {(u32)v, (u32)(v>>32)}};
+}
+
 #endif
-- 
cgit v1.2.3


From 3753d9779038ab011e01b949253492aaa37bf57a Mon Sep 17 00:00:00 2001
From: Mahesh Bandewar <maheshb@google.com>
Date: Thu, 17 Sep 2020 22:08:32 -0700
Subject: net: fix build without CONFIG_SYSCTL definition

Earlier commit 316cdaa1158a ("net: add option to not create fall-back
tunnels in root-ns as well") removed the CONFIG_SYSCTL to enable the
kernel-commandline to work. However, this variable gets defined only
when CONFIG_SYSCTL option is selected.

With this change the behavior would default to creating fall-back
tunnels in all namespaces when CONFIG_SYSCTL is not selected and
the kernel commandline option will be ignored.

Fixes: 316cdaa1158a ("net: add option to not create fall-back tunnels in root-ns as well")
Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Reported-by: kernel test robot <lkp@intel.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org> # build-tested
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 909b1fbb0481..fef0eb96cf69 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -634,8 +634,9 @@ extern int sysctl_devconf_inherit_init_net;
  */
 static inline bool net_has_fallback_tunnels(const struct net *net)
 {
-	return (net == &init_net && sysctl_fb_tunnels_only_for_init_net == 1) ||
-	       !sysctl_fb_tunnels_only_for_init_net;
+	return !IS_ENABLED(CONFIG_SYSCTL) ||
+	       !sysctl_fb_tunnels_only_for_init_net ||
+	       (net == &init_net && sysctl_fb_tunnels_only_for_init_net == 1);
 }
 
 static inline int netdev_queue_numa_node_read(const struct netdev_queue *q)
-- 
cgit v1.2.3


From 6d23d831e9bd0b1d2bcd9a1ecdc6ac8e6d162c36 Mon Sep 17 00:00:00 2001
From: Yangbo Lu <yangbo.lu@nxp.com>
Date: Fri, 18 Sep 2020 17:48:01 +0800
Subject: ptp_qoriq: support FIPER3

The FIPER3 (fixed interval period pulse generator) is supported on
DPAA2 and ENETC network controller hardware. This patch is to support
it in ptp_qoriq driver.

Signed-off-by: Yangbo Lu <yangbo.lu@nxp.com>
Acked-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/ptp/ptp_qoriq.c       | 20 +++++++++++++++++++-
 include/linux/fsl/ptp_qoriq.h |  3 +++
 2 files changed, 22 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/ptp/ptp_qoriq.c b/drivers/ptp/ptp_qoriq.c
index c09c16be0edf..beb5f74944cd 100644
--- a/drivers/ptp/ptp_qoriq.c
+++ b/drivers/ptp/ptp_qoriq.c
@@ -72,6 +72,10 @@ static void set_fipers(struct ptp_qoriq *ptp_qoriq)
 	set_alarm(ptp_qoriq);
 	ptp_qoriq->write(&regs->fiper_regs->tmr_fiper1, ptp_qoriq->tmr_fiper1);
 	ptp_qoriq->write(&regs->fiper_regs->tmr_fiper2, ptp_qoriq->tmr_fiper2);
+
+	if (ptp_qoriq->fiper3_support)
+		ptp_qoriq->write(&regs->fiper_regs->tmr_fiper3,
+				 ptp_qoriq->tmr_fiper3);
 }
 
 int extts_clean_up(struct ptp_qoriq *ptp_qoriq, int index, bool update_event)
@@ -366,6 +370,7 @@ static u32 ptp_qoriq_nominal_freq(u32 clk_src)
  *   "fsl,tmr-add"
  *   "fsl,tmr-fiper1"
  *   "fsl,tmr-fiper2"
+ *   "fsl,tmr-fiper3" (required only for DPAA2 and ENETC hardware)
  *   "fsl,max-adj"
  *
  * Return 0 if success
@@ -412,6 +417,7 @@ static int ptp_qoriq_auto_config(struct ptp_qoriq *ptp_qoriq,
 	ptp_qoriq->tmr_add = freq_comp;
 	ptp_qoriq->tmr_fiper1 = DEFAULT_FIPER1_PERIOD - ptp_qoriq->tclk_period;
 	ptp_qoriq->tmr_fiper2 = DEFAULT_FIPER2_PERIOD - ptp_qoriq->tclk_period;
+	ptp_qoriq->tmr_fiper3 = DEFAULT_FIPER3_PERIOD - ptp_qoriq->tclk_period;
 
 	/* max_adj = 1000000000 * (freq_ratio - 1.0) - 1
 	 * freq_ratio = reference_clock_freq / nominal_freq
@@ -446,6 +452,10 @@ int ptp_qoriq_init(struct ptp_qoriq *ptp_qoriq, void __iomem *base,
 	else
 		ptp_qoriq->extts_fifo_support = false;
 
+	if (of_device_is_compatible(node, "fsl,dpaa2-ptp") ||
+	    of_device_is_compatible(node, "fsl,enetc-ptp"))
+		ptp_qoriq->fiper3_support = true;
+
 	if (of_property_read_u32(node,
 				 "fsl,tclk-period", &ptp_qoriq->tclk_period) ||
 	    of_property_read_u32(node,
@@ -457,7 +467,10 @@ int ptp_qoriq_init(struct ptp_qoriq *ptp_qoriq, void __iomem *base,
 	    of_property_read_u32(node,
 				 "fsl,tmr-fiper2", &ptp_qoriq->tmr_fiper2) ||
 	    of_property_read_u32(node,
-				 "fsl,max-adj", &ptp_qoriq->caps.max_adj)) {
+				 "fsl,max-adj", &ptp_qoriq->caps.max_adj) ||
+	    (ptp_qoriq->fiper3_support &&
+	     of_property_read_u32(node, "fsl,tmr-fiper3",
+				  &ptp_qoriq->tmr_fiper3))) {
 		pr_warn("device tree node missing required elements, try automatic configuration\n");
 
 		if (ptp_qoriq_auto_config(ptp_qoriq, node))
@@ -502,6 +515,11 @@ int ptp_qoriq_init(struct ptp_qoriq *ptp_qoriq, void __iomem *base,
 	ptp_qoriq->write(&regs->ctrl_regs->tmr_prsc, ptp_qoriq->tmr_prsc);
 	ptp_qoriq->write(&regs->fiper_regs->tmr_fiper1, ptp_qoriq->tmr_fiper1);
 	ptp_qoriq->write(&regs->fiper_regs->tmr_fiper2, ptp_qoriq->tmr_fiper2);
+
+	if (ptp_qoriq->fiper3_support)
+		ptp_qoriq->write(&regs->fiper_regs->tmr_fiper3,
+				 ptp_qoriq->tmr_fiper3);
+
 	set_alarm(ptp_qoriq);
 	ptp_qoriq->write(&regs->ctrl_regs->tmr_ctrl,
 			 tmr_ctrl|FIPERST|RTPE|TE|FRD);
diff --git a/include/linux/fsl/ptp_qoriq.h b/include/linux/fsl/ptp_qoriq.h
index 884b8f8ca06d..01acebe37fab 100644
--- a/include/linux/fsl/ptp_qoriq.h
+++ b/include/linux/fsl/ptp_qoriq.h
@@ -136,6 +136,7 @@ struct ptp_qoriq_registers {
 #define DEFAULT_TMR_PRSC	2
 #define DEFAULT_FIPER1_PERIOD	1000000000
 #define DEFAULT_FIPER2_PERIOD	1000000000
+#define DEFAULT_FIPER3_PERIOD	1000000000
 
 struct ptp_qoriq {
 	void __iomem *base;
@@ -147,6 +148,7 @@ struct ptp_qoriq {
 	struct dentry *debugfs_root;
 	struct device *dev;
 	bool extts_fifo_support;
+	bool fiper3_support;
 	int irq;
 	int phc_index;
 	u32 tclk_period;  /* nanoseconds */
@@ -155,6 +157,7 @@ struct ptp_qoriq {
 	u32 cksel;
 	u32 tmr_fiper1;
 	u32 tmr_fiper2;
+	u32 tmr_fiper3;
 	u32 (*read)(unsigned __iomem *addr);
 	void (*write)(unsigned __iomem *addr, u32 val);
 };
-- 
cgit v1.2.3


From bbed0bbdddaf46260aeb1a8910a3b32941e321a2 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Mon, 21 Sep 2020 03:10:30 +0300
Subject: net: dsa: tag_8021q: add VLANs to the master interface too

The whole purpose of tag_8021q is to send VLAN-tagged traffic to the
CPU, from which the driver can decode the source port and switch id.

Currently this only works if the VLAN filtering on the master is
disabled. Change that by explicitly adding code to tag_8021q.c to add
the VLANs corresponding to the tags to the filter of the master
interface.

Because we now need to call vlan_vid_add, then we also need to hold the
RTNL mutex. Propagate that requirement to the callers of dsa_8021q_setup
and modify the existing call sites as appropriate. Note that one call
path, sja1105_best_effort_vlan_filtering_set -> sja1105_vlan_filtering
-> sja1105_setup_8021q_tagging, was already holding this lock.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/sja1105/sja1105_main.c |  7 ++++++-
 include/linux/dsa/8021q.h              |  2 ++
 net/dsa/tag_8021q.c                    | 20 +++++++++++++++++++-
 3 files changed, 27 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index 967430e8ceb8..4a298729937b 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -3038,7 +3038,11 @@ static int sja1105_setup(struct dsa_switch *ds)
 	 * default, and that means vlan_filtering is 0 since they're not under
 	 * a bridge, so it's safe to set up switch tagging at this time.
 	 */
-	return sja1105_setup_8021q_tagging(ds, true);
+	rtnl_lock();
+	rc = sja1105_setup_8021q_tagging(ds, true);
+	rtnl_unlock();
+
+	return rc;
 }
 
 static void sja1105_teardown(struct dsa_switch *ds)
@@ -3532,6 +3536,7 @@ static int sja1105_probe(struct spi_device *spi)
 		return -ENOMEM;
 
 	priv->dsa_8021q_ctx->ops = &sja1105_dsa_8021q_ops;
+	priv->dsa_8021q_ctx->proto = htons(ETH_P_8021Q);
 	priv->dsa_8021q_ctx->ds = ds;
 
 	INIT_LIST_HEAD(&priv->dsa_8021q_ctx->crosschip_links);
diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h
index 2b003ae9fb38..88cd72dfa4e0 100644
--- a/include/linux/dsa/8021q.h
+++ b/include/linux/dsa/8021q.h
@@ -31,6 +31,8 @@ struct dsa_8021q_context {
 	const struct dsa_8021q_ops *ops;
 	struct dsa_switch *ds;
 	struct list_head crosschip_links;
+	/* EtherType of RX VID, used for filtering on master interface */
+	__be16 proto;
 };
 
 #define DSA_8021Q_N_SUBVLAN			8
diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c
index 5baeb0893950..8e3e8a5b8559 100644
--- a/net/dsa/tag_8021q.c
+++ b/net/dsa/tag_8021q.c
@@ -215,7 +215,8 @@ static int dsa_8021q_setup_port(struct dsa_8021q_context *ctx, int port,
 	int upstream = dsa_upstream_port(ctx->ds, port);
 	u16 rx_vid = dsa_8021q_rx_vid(ctx->ds, port);
 	u16 tx_vid = dsa_8021q_tx_vid(ctx->ds, port);
-	int i, err;
+	struct net_device *master;
+	int i, err, subvlan;
 
 	/* The CPU port is implicitly configured by
 	 * configuring the front-panel ports
@@ -223,6 +224,8 @@ static int dsa_8021q_setup_port(struct dsa_8021q_context *ctx, int port,
 	if (!dsa_is_user_port(ctx->ds, port))
 		return 0;
 
+	master = dsa_to_port(ctx->ds, port)->cpu_dp->master;
+
 	/* Add this user port's RX VID to the membership list of all others
 	 * (including itself). This is so that bridging will not be hindered.
 	 * L2 forwarding rules still take precedence when there are no VLAN
@@ -261,6 +264,19 @@ static int dsa_8021q_setup_port(struct dsa_8021q_context *ctx, int port,
 		return err;
 	}
 
+	/* Add to the master's RX filter not only @rx_vid, but in fact
+	 * the entire subvlan range, just in case this DSA switch might
+	 * want to use sub-VLANs.
+	 */
+	for (subvlan = 0; subvlan < DSA_8021Q_N_SUBVLAN; subvlan++) {
+		u16 vid = dsa_8021q_rx_vid_subvlan(ctx->ds, port, subvlan);
+
+		if (enabled)
+			vlan_vid_add(master, ctx->proto, vid);
+		else
+			vlan_vid_del(master, ctx->proto, vid);
+	}
+
 	/* Finally apply the TX VID on this port and on the CPU port */
 	err = dsa_8021q_vid_apply(ctx, port, tx_vid, BRIDGE_VLAN_INFO_UNTAGGED,
 				  enabled);
@@ -285,6 +301,8 @@ int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled)
 {
 	int rc, port;
 
+	ASSERT_RTNL();
+
 	for (port = 0; port < ctx->ds->num_ports; port++) {
 		rc = dsa_8021q_setup_port(ctx, port, enabled);
 		if (rc < 0) {
-- 
cgit v1.2.3


From 49347755a84052fd1317c3897c7cea954c8f89fe Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Wed, 16 Sep 2020 00:34:53 +0200
Subject: can: include: fix spelling mistakes

This patch fixes spelling erros found by "codespell" in the
include/linux/can subtree.

Link: https://lore.kernel.org/r/20200915223527.1417033-4-mkl@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 include/linux/can/core.h | 2 +-
 include/linux/can/dev.h  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/can/core.h b/include/linux/can/core.h
index e20a0cd09ba5..7da9f1f82e8e 100644
--- a/include/linux/can/core.h
+++ b/include/linux/can/core.h
@@ -2,7 +2,7 @@
 /*
  * linux/can/core.h
  *
- * Protoypes and definitions for CAN protocol modules using the PF_CAN core
+ * Prototypes and definitions for CAN protocol modules using the PF_CAN core
  *
  * Authors: Oliver Hartkopp <oliver.hartkopp@volkswagen.de>
  *          Urs Thuermann   <urs.thuermann@volkswagen.de>
diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h
index 5e3d45525bd3..516892566ac9 100644
--- a/include/linux/can/dev.h
+++ b/include/linux/can/dev.h
@@ -108,7 +108,7 @@ static inline bool can_skb_headroom_valid(struct net_device *dev,
 
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
 
-		/* preform proper loopback on capable devices */
+		/* perform proper loopback on capable devices */
 		if (dev->flags & IFF_ECHO)
 			skb->pkt_type = PACKET_LOOPBACK;
 		else
-- 
cgit v1.2.3


From 80a71815d8cd1be6481ad16fad3167f095045a06 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Wed, 16 Sep 2020 00:35:01 +0200
Subject: can: dev: can_put_echo_skb(): propagate error in case of errors

The function can_put_echo_skb() can fail for several reasons. It may
fail due to OOM, but when it fails it's usually due to locking problems
in the driver.

In order to help developing and debugging of new drivers propagate error
value in case of errors.

Link: https://lore.kernel.org/r/20200915223527.1417033-12-mkl@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/dev.c   | 11 +++++++----
 include/linux/can/dev.h |  4 ++--
 2 files changed, 9 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index dd443e5d8cb7..77a5663693af 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -434,8 +434,8 @@ static void can_flush_echo_skb(struct net_device *dev)
  * of the device driver. The driver must protect access to
  * priv->echo_skb, if necessary.
  */
-void can_put_echo_skb(struct sk_buff *skb, struct net_device *dev,
-		      unsigned int idx)
+int can_put_echo_skb(struct sk_buff *skb, struct net_device *dev,
+		     unsigned int idx)
 {
 	struct can_priv *priv = netdev_priv(dev);
 
@@ -446,13 +446,13 @@ void can_put_echo_skb(struct sk_buff *skb, struct net_device *dev,
 	    (skb->protocol != htons(ETH_P_CAN) &&
 	     skb->protocol != htons(ETH_P_CANFD))) {
 		kfree_skb(skb);
-		return;
+		return 0;
 	}
 
 	if (!priv->echo_skb[idx]) {
 		skb = can_create_echo_skb(skb);
 		if (!skb)
-			return;
+			return -ENOMEM;
 
 		/* make settings for echo to reduce code in irq context */
 		skb->pkt_type = PACKET_BROADCAST;
@@ -465,7 +465,10 @@ void can_put_echo_skb(struct sk_buff *skb, struct net_device *dev,
 		/* locking problem with netif_stop_queue() ?? */
 		netdev_err(dev, "%s: BUG! echo_skb %d is occupied!\n", __func__, idx);
 		kfree_skb(skb);
+		return -EBUSY;
 	}
+
+	return 0;
 }
 EXPORT_SYMBOL_GPL(can_put_echo_skb);
 
diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h
index 516892566ac9..ed0482b2f4b2 100644
--- a/include/linux/can/dev.h
+++ b/include/linux/can/dev.h
@@ -201,8 +201,8 @@ void can_bus_off(struct net_device *dev);
 void can_change_state(struct net_device *dev, struct can_frame *cf,
 		      enum can_state tx_state, enum can_state rx_state);
 
-void can_put_echo_skb(struct sk_buff *skb, struct net_device *dev,
-		      unsigned int idx);
+int can_put_echo_skb(struct sk_buff *skb, struct net_device *dev,
+		     unsigned int idx);
 struct sk_buff *__can_get_echo_skb(struct net_device *dev, unsigned int idx,
 				   u8 *len_ptr);
 unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx);
-- 
cgit v1.2.3


From 728fc9ff73d3f25220f6b8a52aaf063ec51ef294 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Wed, 16 Sep 2020 00:35:22 +0200
Subject: can: rx-offload: can_rx_offload_add_manual(): add new initialization
 function

This patch adds a new initialization function:
can_rx_offload_add_manual()

It should be used to add support rx-offload to a driver, if the callback
mechanism should not be used. Use e.g. can_rx_offload_queue_sorted() to queue
skbs into rx-offload.

Link: https://lore.kernel.org/r/20200915223527.1417033-33-mkl@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/rx-offload.c   | 11 +++++++++++
 include/linux/can/rx-offload.h |  3 +++
 2 files changed, 14 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/net/can/rx-offload.c b/drivers/net/can/rx-offload.c
index e8328910a234..3b180269a92d 100644
--- a/drivers/net/can/rx-offload.c
+++ b/drivers/net/can/rx-offload.c
@@ -351,6 +351,17 @@ int can_rx_offload_add_fifo(struct net_device *dev,
 }
 EXPORT_SYMBOL_GPL(can_rx_offload_add_fifo);
 
+int can_rx_offload_add_manual(struct net_device *dev,
+			      struct can_rx_offload *offload,
+			      unsigned int weight)
+{
+	if (offload->mailbox_read)
+		return -EINVAL;
+
+	return can_rx_offload_init_queue(dev, offload, weight);
+}
+EXPORT_SYMBOL_GPL(can_rx_offload_add_manual);
+
 void can_rx_offload_enable(struct can_rx_offload *offload)
 {
 	napi_enable(&offload->napi);
diff --git a/include/linux/can/rx-offload.h b/include/linux/can/rx-offload.h
index 1b78a0cfb615..f1b38088b765 100644
--- a/include/linux/can/rx-offload.h
+++ b/include/linux/can/rx-offload.h
@@ -35,6 +35,9 @@ int can_rx_offload_add_timestamp(struct net_device *dev,
 int can_rx_offload_add_fifo(struct net_device *dev,
 			    struct can_rx_offload *offload,
 			    unsigned int weight);
+int can_rx_offload_add_manual(struct net_device *dev,
+			      struct can_rx_offload *offload,
+			      unsigned int weight);
 int can_rx_offload_irq_offload_timestamp(struct can_rx_offload *offload,
 					 u64 reg);
 int can_rx_offload_irq_offload_fifo(struct can_rx_offload *offload);
-- 
cgit v1.2.3


From b1d4dc15b2f430a4f541ab6c91e63a71cf230b7d Mon Sep 17 00:00:00 2001
From: Tian Tao <tiantao6@hisilicon.com>
Date: Tue, 15 Sep 2020 09:38:18 +0800
Subject: i2c: Switch to using the new API kobj_to_dev()

Switch to using the new API kobj_to_dev().

Signed-off-by: Tian Tao <tiantao6@hisilicon.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 include/linux/i2c.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index fc55ea41d323..56622658b215 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -344,7 +344,7 @@ const struct i2c_device_id *i2c_match_id(const struct i2c_device_id *id,
 
 static inline struct i2c_client *kobj_to_i2c_client(struct kobject *kobj)
 {
-	struct device * const dev = container_of(kobj, struct device, kobj);
+	struct device * const dev = kobj_to_dev(kobj);
 	return to_i2c_client(dev);
 }
 
-- 
cgit v1.2.3


From 1138ce1cf60954d1c0e2d7b4eba5b4df5813fd86 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 15 Jul 2020 18:31:30 -0700
Subject: sunrpc: fix duplicated word in <linux/sunrpc/cache.h>

Change "time time" to "time expiry_time" to match the field name.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: "J. Bruce Fields" <bfields@fieldses.org>
Cc: Chuck Lever <chuck.lever@oracle.com>
Cc: Trond Myklebust <trond.myklebust@hammerspace.com>
Cc: Anna Schumaker <anna.schumaker@netapp.com>
Cc: linux-nfs@vger.kernel.org
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/linux/sunrpc/cache.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h
index 10891b70fc7b..d0965e2997b0 100644
--- a/include/linux/sunrpc/cache.h
+++ b/include/linux/sunrpc/cache.h
@@ -45,7 +45,8 @@
  */
 struct cache_head {
 	struct hlist_node	cache_list;
-	time64_t	expiry_time;	/* After time time, don't use the data */
+	time64_t	expiry_time;	/* After time expiry_time, don't use
+					 * the data */
 	time64_t	last_refresh;   /* If CACHE_PENDING, this is when upcall was
 					 * sent, else this is when update was
 					 * received, though it is alway set to
-- 
cgit v1.2.3


From 0bdd4cea12a9fd79a7eb7de8493a5fef54d0eea6 Mon Sep 17 00:00:00 2001
From: "Alexander A. Klimov" <grandmaster@al2klimov.de>
Date: Tue, 7 Jul 2020 21:50:12 +0200
Subject: Replace HTTP links with HTTPS ones: NFS, SUNRPC, and LOCKD clients

Rationale:
Reduces attack surface on kernel devs opening the links for MITM
as HTTPS traffic is much harder to manipulate.

Deterministic algorithm:
For each file:
  If not .svg:
    For each line:
      If doesn't contain `\bxmlns\b`:
        For each link, `\bhttp://[^# \t\r\n]*(?:\w|/)`:
          If both the HTTP and HTTPS versions
          return 200 OK and serve the same content:
            Replace HTTP with HTTPS.

Signed-off-by: Alexander A. Klimov <grandmaster@al2klimov.de>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/lockd/mon.c                  | 2 +-
 include/linux/sunrpc/bc_xprt.h  | 2 +-
 include/linux/sunrpc/msg_prot.h | 2 +-
 net/sunrpc/backchannel_rqst.c   | 2 +-
 net/sunrpc/sunrpc.h             | 2 +-
 5 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c
index 1eabd91870e6..1d9488cf0534 100644
--- a/fs/lockd/mon.c
+++ b/fs/lockd/mon.c
@@ -417,7 +417,7 @@ void nsm_release(struct nsm_handle *nsm)
 /*
  * XDR functions for NSM.
  *
- * See http://www.opengroup.org/ for details on the Network
+ * See https://www.opengroup.org/ for details on the Network
  * Status Monitor wire protocol.
  */
 
diff --git a/include/linux/sunrpc/bc_xprt.h b/include/linux/sunrpc/bc_xprt.h
index d796058cdff2..f07c334c599f 100644
--- a/include/linux/sunrpc/bc_xprt.h
+++ b/include/linux/sunrpc/bc_xprt.h
@@ -4,7 +4,7 @@
 
 NetApp provides this source code under the GPL v2 License.
 The GPL v2 license is available at
-http://opensource.org/licenses/gpl-license.php.
+https://opensource.org/licenses/gpl-license.php.
 
 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
diff --git a/include/linux/sunrpc/msg_prot.h b/include/linux/sunrpc/msg_prot.h
index bea40d9f03a1..43f854487539 100644
--- a/include/linux/sunrpc/msg_prot.h
+++ b/include/linux/sunrpc/msg_prot.h
@@ -143,7 +143,7 @@ typedef __be32	rpc_fraghdr;
 /*
  * Well-known netids. See:
  *
- *   http://www.iana.org/assignments/rpc-netids/rpc-netids.xhtml
+ *   https://www.iana.org/assignments/rpc-netids/rpc-netids.xhtml
  */
 #define RPCBIND_NETID_UDP	"udp"
 #define RPCBIND_NETID_TCP	"tcp"
diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c
index 195b40c5dae4..3fecad369592 100644
--- a/net/sunrpc/backchannel_rqst.c
+++ b/net/sunrpc/backchannel_rqst.c
@@ -5,7 +5,7 @@
 
 NetApp provides this source code under the GPL v2 License.
 The GPL v2 license is available at
-http://opensource.org/licenses/gpl-license.php.
+https://opensource.org/licenses/gpl-license.php.
 
 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
diff --git a/net/sunrpc/sunrpc.h b/net/sunrpc/sunrpc.h
index f6fe2e6cd65a..2f59464e6524 100644
--- a/net/sunrpc/sunrpc.h
+++ b/net/sunrpc/sunrpc.h
@@ -4,7 +4,7 @@
 
 NetApp provides this source code under the GPL v2 License.
 The GPL v2 license is available at
-http://opensource.org/licenses/gpl-license.php.
+https://opensource.org/licenses/gpl-license.php.
 
 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
-- 
cgit v1.2.3


From 24addd848a45747bcda68418710c72fdc8e145e4 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Mon, 21 Sep 2020 08:58:39 -0700
Subject: fs: Introduce i_blocks_per_page

This helper is useful for both THPs and for supporting block size larger
than page size.  Convert all users that I could find (we have a few
different ways of writing this idiom, and I may have missed some).

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Acked-by: Dave Kleikamp <dave.kleikamp@oracle.com>
---
 fs/iomap/buffered-io.c  |  8 ++++----
 fs/jfs/jfs_metapage.c   |  2 +-
 fs/xfs/xfs_aops.c       |  2 +-
 include/linux/pagemap.h | 16 ++++++++++++++++
 4 files changed, 22 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index d8013f38a317..dd0739606dce 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -46,7 +46,7 @@ iomap_page_create(struct inode *inode, struct page *page)
 {
 	struct iomap_page *iop = to_iomap_page(page);
 
-	if (iop || i_blocksize(inode) == PAGE_SIZE)
+	if (iop || i_blocks_per_page(inode, page) <= 1)
 		return iop;
 
 	iop = kmalloc(sizeof(*iop), GFP_NOFS | __GFP_NOFAIL);
@@ -147,7 +147,7 @@ iomap_iop_set_range_uptodate(struct page *page, unsigned off, unsigned len)
 	unsigned int i;
 
 	spin_lock_irqsave(&iop->uptodate_lock, flags);
-	for (i = 0; i < PAGE_SIZE / i_blocksize(inode); i++) {
+	for (i = 0; i < i_blocks_per_page(inode, page); i++) {
 		if (i >= first && i <= last)
 			set_bit(i, iop->uptodate);
 		else if (!test_bit(i, iop->uptodate))
@@ -1077,7 +1077,7 @@ iomap_finish_page_writeback(struct inode *inode, struct page *page,
 		mapping_set_error(inode->i_mapping, -EIO);
 	}
 
-	WARN_ON_ONCE(i_blocksize(inode) < PAGE_SIZE && !iop);
+	WARN_ON_ONCE(i_blocks_per_page(inode, page) > 1 && !iop);
 	WARN_ON_ONCE(iop && atomic_read(&iop->write_count) <= 0);
 
 	if (!iop || atomic_dec_and_test(&iop->write_count))
@@ -1373,7 +1373,7 @@ iomap_writepage_map(struct iomap_writepage_ctx *wpc,
 	int error = 0, count = 0, i;
 	LIST_HEAD(submit_list);
 
-	WARN_ON_ONCE(i_blocksize(inode) < PAGE_SIZE && !iop);
+	WARN_ON_ONCE(i_blocks_per_page(inode, page) > 1 && !iop);
 	WARN_ON_ONCE(iop && atomic_read(&iop->write_count) != 0);
 
 	/*
diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c
index a2f5338a5ea1..176580f54af9 100644
--- a/fs/jfs/jfs_metapage.c
+++ b/fs/jfs/jfs_metapage.c
@@ -473,7 +473,7 @@ static int metapage_readpage(struct file *fp, struct page *page)
 	struct inode *inode = page->mapping->host;
 	struct bio *bio = NULL;
 	int block_offset;
-	int blocks_per_page = PAGE_SIZE >> inode->i_blkbits;
+	int blocks_per_page = i_blocks_per_page(inode, page);
 	sector_t page_start;	/* address of page in fs blocks */
 	sector_t pblock;
 	int xlen;
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index b35611882ff9..55d126d4e096 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -544,7 +544,7 @@ xfs_discard_page(
 			page, ip->i_ino, offset);
 
 	error = xfs_bmap_punch_delalloc_range(ip, start_fsb,
-			PAGE_SIZE / i_blocksize(inode));
+			i_blocks_per_page(inode, page));
 	if (error && !XFS_FORCED_SHUTDOWN(mp))
 		xfs_alert(mp, "page discard unable to remove delalloc mapping.");
 out_invalidate:
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 7de11dcd534d..853733286138 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -899,4 +899,20 @@ static inline int page_mkwrite_check_truncate(struct page *page,
 	return offset;
 }
 
+/**
+ * i_blocks_per_page - How many blocks fit in this page.
+ * @inode: The inode which contains the blocks.
+ * @page: The page (head page if the page is a THP).
+ *
+ * If the block size is larger than the size of this page, return zero.
+ *
+ * Context: The caller should hold a refcount on the page to prevent it
+ * from being split.
+ * Return: The number of filesystem blocks covered by this page.
+ */
+static inline
+unsigned int i_blocks_per_page(struct inode *inode, struct page *page)
+{
+	return thp_size(page) >> inode->i_blkbits;
+}
 #endif /* _LINUX_PAGEMAP_H */
-- 
cgit v1.2.3


From 81ee8e52a71c712dbe04994f1430cb4c88b87ad6 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Mon, 21 Sep 2020 08:58:42 -0700
Subject: iomap: Change calling convention for zeroing

Pass the full length to iomap_zero() and dax_iomap_zero(), and have
them return how many bytes they actually handled.  This is preparatory
work for handling THP, although it looks like DAX could actually take
advantage of it if there's a larger contiguous area.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/dax.c               | 13 ++++++-------
 fs/iomap/buffered-io.c | 33 +++++++++++++++------------------
 include/linux/dax.h    |  3 +--
 3 files changed, 22 insertions(+), 27 deletions(-)

(limited to 'include/linux')

diff --git a/fs/dax.c b/fs/dax.c
index 994ab66a9907..6ad346352a8c 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1037,18 +1037,18 @@ static vm_fault_t dax_load_hole(struct xa_state *xas,
 	return ret;
 }
 
-int dax_iomap_zero(loff_t pos, unsigned offset, unsigned size,
-		   struct iomap *iomap)
+s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap)
 {
 	sector_t sector = iomap_sector(iomap, pos & PAGE_MASK);
 	pgoff_t pgoff;
 	long rc, id;
 	void *kaddr;
 	bool page_aligned = false;
-
+	unsigned offset = offset_in_page(pos);
+	unsigned size = min_t(u64, PAGE_SIZE - offset, length);
 
 	if (IS_ALIGNED(sector << SECTOR_SHIFT, PAGE_SIZE) &&
-	    IS_ALIGNED(size, PAGE_SIZE))
+	    (size == PAGE_SIZE))
 		page_aligned = true;
 
 	rc = bdev_dax_pgoff(iomap->bdev, sector, PAGE_SIZE, &pgoff);
@@ -1058,8 +1058,7 @@ int dax_iomap_zero(loff_t pos, unsigned offset, unsigned size,
 	id = dax_read_lock();
 
 	if (page_aligned)
-		rc = dax_zero_page_range(iomap->dax_dev, pgoff,
-					 size >> PAGE_SHIFT);
+		rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1);
 	else
 		rc = dax_direct_access(iomap->dax_dev, pgoff, 1, &kaddr, NULL);
 	if (rc < 0) {
@@ -1072,7 +1071,7 @@ int dax_iomap_zero(loff_t pos, unsigned offset, unsigned size,
 		dax_flush(iomap->dax_dev, kaddr + offset, size);
 	}
 	dax_read_unlock(id);
-	return 0;
+	return size;
 }
 
 static loff_t
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index f26b24f39de4..8b6cca7e34e4 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -898,11 +898,13 @@ iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
 }
 EXPORT_SYMBOL_GPL(iomap_file_unshare);
 
-static int iomap_zero(struct inode *inode, loff_t pos, unsigned offset,
-		unsigned bytes, struct iomap *iomap, struct iomap *srcmap)
+static s64 iomap_zero(struct inode *inode, loff_t pos, u64 length,
+		struct iomap *iomap, struct iomap *srcmap)
 {
 	struct page *page;
 	int status;
+	unsigned offset = offset_in_page(pos);
+	unsigned bytes = min_t(u64, PAGE_SIZE - offset, length);
 
 	status = iomap_write_begin(inode, pos, bytes, 0, &page, iomap, srcmap);
 	if (status)
@@ -914,38 +916,33 @@ static int iomap_zero(struct inode *inode, loff_t pos, unsigned offset,
 	return iomap_write_end(inode, pos, bytes, bytes, page, iomap, srcmap);
 }
 
-static loff_t
-iomap_zero_range_actor(struct inode *inode, loff_t pos, loff_t count,
-		void *data, struct iomap *iomap, struct iomap *srcmap)
+static loff_t iomap_zero_range_actor(struct inode *inode, loff_t pos,
+		loff_t length, void *data, struct iomap *iomap,
+		struct iomap *srcmap)
 {
 	bool *did_zero = data;
 	loff_t written = 0;
-	int status;
 
 	/* already zeroed?  we're done. */
 	if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN)
-		return count;
+		return length;
 
 	do {
-		unsigned offset, bytes;
-
-		offset = offset_in_page(pos);
-		bytes = min_t(loff_t, PAGE_SIZE - offset, count);
+		s64 bytes;
 
 		if (IS_DAX(inode))
-			status = dax_iomap_zero(pos, offset, bytes, iomap);
+			bytes = dax_iomap_zero(pos, length, iomap);
 		else
-			status = iomap_zero(inode, pos, offset, bytes, iomap,
-					srcmap);
-		if (status < 0)
-			return status;
+			bytes = iomap_zero(inode, pos, length, iomap, srcmap);
+		if (bytes < 0)
+			return bytes;
 
 		pos += bytes;
-		count -= bytes;
+		length -= bytes;
 		written += bytes;
 		if (did_zero)
 			*did_zero = true;
-	} while (count > 0);
+	} while (length > 0);
 
 	return written;
 }
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 6904d4e0b2e0..951a851a0481 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -214,8 +214,7 @@ vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf,
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
 int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
 				      pgoff_t index);
-int dax_iomap_zero(loff_t pos, unsigned offset, unsigned size,
-			struct iomap *iomap);
+s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap);
 static inline bool dax_mapping(struct address_space *mapping)
 {
 	return mapping->host && IS_DAX(mapping->host);
-- 
cgit v1.2.3


From c754e137f55e075d6b6ad9b866c32e9aad260a83 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Fri, 18 Sep 2020 15:29:59 -0400
Subject: pNFS/flexfiles: Be consistent about mirror index types

A mirror index is always of type u32.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/flexfilelayout/flexfilelayout.c | 34 +++++++++++++++++-----------------
 include/linux/nfs_xdr.h                |  4 ++--
 2 files changed, 19 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 1edeebd51937..a163533446fa 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -715,7 +715,7 @@ nfs4_ff_layout_stat_io_end_write(struct rpc_task *task,
 }
 
 static void
-ff_layout_mark_ds_unreachable(struct pnfs_layout_segment *lseg, int idx)
+ff_layout_mark_ds_unreachable(struct pnfs_layout_segment *lseg, u32 idx)
 {
 	struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx);
 
@@ -724,7 +724,7 @@ ff_layout_mark_ds_unreachable(struct pnfs_layout_segment *lseg, int idx)
 }
 
 static void
-ff_layout_mark_ds_reachable(struct pnfs_layout_segment *lseg, int idx)
+ff_layout_mark_ds_reachable(struct pnfs_layout_segment *lseg, u32 idx)
 {
 	struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx);
 
@@ -734,14 +734,14 @@ ff_layout_mark_ds_reachable(struct pnfs_layout_segment *lseg, int idx)
 
 static struct nfs4_pnfs_ds *
 ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg,
-			     int start_idx, int *best_idx,
+			     u32 start_idx, u32 *best_idx,
 			     bool check_device)
 {
 	struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg);
 	struct nfs4_ff_layout_mirror *mirror;
 	struct nfs4_pnfs_ds *ds;
 	bool fail_return = false;
-	int idx;
+	u32 idx;
 
 	/* mirrors are initially sorted by efficiency */
 	for (idx = start_idx; idx < fls->mirror_array_cnt; idx++) {
@@ -766,21 +766,21 @@ ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg,
 
 static struct nfs4_pnfs_ds *
 ff_layout_choose_any_ds_for_read(struct pnfs_layout_segment *lseg,
-				 int start_idx, int *best_idx)
+				 u32 start_idx, u32 *best_idx)
 {
 	return ff_layout_choose_ds_for_read(lseg, start_idx, best_idx, false);
 }
 
 static struct nfs4_pnfs_ds *
 ff_layout_choose_valid_ds_for_read(struct pnfs_layout_segment *lseg,
-				   int start_idx, int *best_idx)
+				   u32 start_idx, u32 *best_idx)
 {
 	return ff_layout_choose_ds_for_read(lseg, start_idx, best_idx, true);
 }
 
 static struct nfs4_pnfs_ds *
 ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg,
-				  int start_idx, int *best_idx)
+				  u32 start_idx, u32 *best_idx)
 {
 	struct nfs4_pnfs_ds *ds;
 
@@ -791,7 +791,8 @@ ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg,
 }
 
 static struct nfs4_pnfs_ds *
-ff_layout_get_ds_for_read(struct nfs_pageio_descriptor *pgio, int *best_idx)
+ff_layout_get_ds_for_read(struct nfs_pageio_descriptor *pgio,
+			  u32 *best_idx)
 {
 	struct pnfs_layout_segment *lseg = pgio->pg_lseg;
 	struct nfs4_pnfs_ds *ds;
@@ -837,8 +838,7 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio,
 	struct nfs_pgio_mirror *pgm;
 	struct nfs4_ff_layout_mirror *mirror;
 	struct nfs4_pnfs_ds *ds;
-	int ds_idx;
-	u32 i;
+	u32 ds_idx, i;
 
 retry:
 	ff_layout_pg_check_layout(pgio, req);
@@ -895,7 +895,7 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio,
 	struct nfs4_ff_layout_mirror *mirror;
 	struct nfs_pgio_mirror *pgm;
 	struct nfs4_pnfs_ds *ds;
-	int i;
+	u32 i;
 
 retry:
 	ff_layout_pg_check_layout(pgio, req);
@@ -1039,7 +1039,7 @@ static void ff_layout_reset_write(struct nfs_pgio_header *hdr, bool retry_pnfs)
 static void ff_layout_resend_pnfs_read(struct nfs_pgio_header *hdr)
 {
 	u32 idx = hdr->pgio_mirror_idx + 1;
-	int new_idx = 0;
+	u32 new_idx = 0;
 
 	if (ff_layout_choose_any_ds_for_read(hdr->lseg, idx + 1, &new_idx))
 		ff_layout_send_layouterror(hdr->lseg);
@@ -1076,7 +1076,7 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task,
 					   struct nfs4_state *state,
 					   struct nfs_client *clp,
 					   struct pnfs_layout_segment *lseg,
-					   int idx)
+					   u32 idx)
 {
 	struct pnfs_layout_hdr *lo = lseg->pls_layout;
 	struct inode *inode = lo->plh_inode;
@@ -1150,7 +1150,7 @@ reset:
 /* Retry all errors through either pNFS or MDS except for -EJUKEBOX */
 static int ff_layout_async_handle_error_v3(struct rpc_task *task,
 					   struct pnfs_layout_segment *lseg,
-					   int idx)
+					   u32 idx)
 {
 	struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx);
 
@@ -1185,7 +1185,7 @@ static int ff_layout_async_handle_error(struct rpc_task *task,
 					struct nfs4_state *state,
 					struct nfs_client *clp,
 					struct pnfs_layout_segment *lseg,
-					int idx)
+					u32 idx)
 {
 	int vers = clp->cl_nfs_mod->rpc_vers->number;
 
@@ -1212,7 +1212,7 @@ static int ff_layout_async_handle_error(struct rpc_task *task,
 }
 
 static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg,
-					int idx, u64 offset, u64 length,
+					u32 idx, u64 offset, u64 length,
 					u32 *op_status, int opnum, int error)
 {
 	struct nfs4_ff_layout_mirror *mirror;
@@ -1810,7 +1810,7 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
 	loff_t offset = hdr->args.offset;
 	int vers;
 	struct nfs_fh *fh;
-	int idx = hdr->pgio_mirror_idx;
+	u32 idx = hdr->pgio_mirror_idx;
 
 	mirror = FF_LAYOUT_COMP(lseg, idx);
 	ds = nfs4_ff_layout_prepare_ds(lseg, mirror, true);
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 9408f3252c8e..69cb46f7b8d2 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1611,8 +1611,8 @@ struct nfs_pgio_header {
 	__u64			mds_offset;	/* Filelayout dense stripe */
 	struct nfs_page_array	page_array;
 	struct nfs_client	*ds_clp;	/* pNFS data server */
-	int			ds_commit_idx;	/* ds index if ds_clp is set */
-	int			pgio_mirror_idx;/* mirror index in pgio layer */
+	u32			ds_commit_idx;	/* ds index if ds_clp is set */
+	u32			pgio_mirror_idx;/* mirror index in pgio layer */
 };
 
 struct nfs_mds_commit_info {
-- 
cgit v1.2.3


From 4c9db39361da5dcf0e77f4aeb4817be3bf7d626b Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Sat, 19 Sep 2020 23:28:25 +0200
Subject: regulator: unexport regulator_lock/unlock()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

regulator_lock/unlock() was used only to guard
regulator_notifier_call_chain(). As no users remain, make the functions
internal.

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Link: https://lore.kernel.org/r/d3381aabd2632aff5e7b839d55868bec6e85c811.1600550732.git.mirq-linux@rere.qmqm.pl
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/core.c         | 6 ++----
 include/linux/regulator/driver.h | 3 ---
 2 files changed, 2 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index a9c97c88f50e..6600949d08f8 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -190,11 +190,10 @@ static inline int regulator_lock_nested(struct regulator_dev *rdev,
  * than the one, which initially locked the mutex, it will
  * wait on mutex.
  */
-void regulator_lock(struct regulator_dev *rdev)
+static void regulator_lock(struct regulator_dev *rdev)
 {
 	regulator_lock_nested(rdev, NULL);
 }
-EXPORT_SYMBOL_GPL(regulator_lock);
 
 /**
  * regulator_unlock - unlock a single regulator
@@ -203,7 +202,7 @@ EXPORT_SYMBOL_GPL(regulator_lock);
  * This function unlocks the mutex when the
  * reference counter reaches 0.
  */
-void regulator_unlock(struct regulator_dev *rdev)
+static void regulator_unlock(struct regulator_dev *rdev)
 {
 	mutex_lock(&regulator_nesting_mutex);
 
@@ -216,7 +215,6 @@ void regulator_unlock(struct regulator_dev *rdev)
 
 	mutex_unlock(&regulator_nesting_mutex);
 }
-EXPORT_SYMBOL_GPL(regulator_unlock);
 
 static bool regulator_supply_is_couple(struct regulator_dev *rdev)
 {
diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index 8539f34ae42b..11cade73726c 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -533,9 +533,6 @@ int regulator_set_current_limit_regmap(struct regulator_dev *rdev,
 int regulator_get_current_limit_regmap(struct regulator_dev *rdev);
 void *regulator_get_init_drvdata(struct regulator_init_data *reg_init_data);
 
-void regulator_lock(struct regulator_dev *rdev);
-void regulator_unlock(struct regulator_dev *rdev);
-
 /*
  * Helper functions intended to be used by regulator drivers prior registering
  * their regulators.
-- 
cgit v1.2.3


From cd7798cbd28044a3026619e36993160ba8fa118d Mon Sep 17 00:00:00 2001
From: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Date: Sun, 13 Sep 2020 14:21:14 +0100
Subject: iio: Add __printf() attributes to various allocation functions

A partial set of these was added to IIO a long time back.
This fills in some gaps in coverage highlighted by building
with W=1

Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20200913132115.800131-3-jic23@kernel.org
---
 drivers/iio/industrialio-trigger.c   | 3 ++-
 include/linux/iio/iio.h              | 3 ++-
 include/linux/iio/trigger_consumer.h | 2 +-
 3 files changed, 5 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iio/industrialio-trigger.c b/drivers/iio/industrialio-trigger.c
index 6f16357fd732..583bb51f65a7 100644
--- a/drivers/iio/industrialio-trigger.c
+++ b/drivers/iio/industrialio-trigger.c
@@ -516,7 +516,8 @@ static void iio_trig_subirqunmask(struct irq_data *d)
 	trig->subirqs[d->irq - trig->subirq_base].enabled = true;
 }
 
-static struct iio_trigger *viio_trigger_alloc(const char *fmt, va_list vargs)
+static __printf(1, 0)
+struct iio_trigger *viio_trigger_alloc(const char *fmt, va_list vargs)
 {
 	struct iio_trigger *trig;
 	int i;
diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index e2df67a3b9ab..2e45b3ceafa7 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -691,8 +691,9 @@ static inline void *iio_priv(const struct iio_dev *indio_dev)
 
 void iio_device_free(struct iio_dev *indio_dev);
 struct iio_dev *devm_iio_device_alloc(struct device *parent, int sizeof_priv);
+__printf(2, 3)
 struct iio_trigger *devm_iio_trigger_alloc(struct device *dev,
-						const char *fmt, ...);
+					   const char *fmt, ...);
 /**
  * iio_buffer_enabled() - helper function to test if the buffer is enabled
  * @indio_dev:		IIO device structure for device
diff --git a/include/linux/iio/trigger_consumer.h b/include/linux/iio/trigger_consumer.h
index 3aa2f132dd67..2c05dfad88d7 100644
--- a/include/linux/iio/trigger_consumer.h
+++ b/include/linux/iio/trigger_consumer.h
@@ -38,7 +38,7 @@ struct iio_poll_func {
 };
 
 
-struct iio_poll_func
+__printf(5, 6) struct iio_poll_func
 *iio_alloc_pollfunc(irqreturn_t (*h)(int irq, void *p),
 		    irqreturn_t (*thread)(int irq, void *p),
 		    int type,
-- 
cgit v1.2.3


From 36e322ec5dd24f1d0840061ffe406458669bccf1 Mon Sep 17 00:00:00 2001
From: Nuno Sá <nuno.sa@analog.com>
Date: Thu, 17 Sep 2020 17:52:20 +0200
Subject: iio: adis: Move burst mode into adis_data
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add burst mode variables in the per device specific data structure. As
some drivers support multiple devices with different burst sizes it
makes sense this data to be in `adis_data`. While moving the variables,
there are two main differences:

1. The `en`variable is dropped. If a device supports burst mode, it will
just use it as it will has better performance for almost all real use
cases.
2. Replace `extra_len` by `burst_len`. Users should now explicitly
define the length of the burst buffer as it is typically constant. This
also allows to remove the following line from the library:

```
/* All but the timestamp channel */
burst_length = (indio_dev->num_channels - 1) * sizeof(u16);
```

The library should not assume that a timestamp channel is defined.
Moreover, most parts also include some diagnostic data, crc, etc.. in
the burst buffer that needed to be included in an `extra_len` variable
which is not that nice. On top of this, some devices already start to
have some 32bit size channels ...

This patch is also a move to completely drop the `struct adis_burst`
from the library.

Signed-off-by: Nuno Sá <nuno.sa@analog.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/20200917155223.218500-2-nuno.sa@analog.com
---
 drivers/iio/imu/adis_buffer.c | 12 +++++-------
 include/linux/iio/imu/adis.h  |  9 +++++++++
 2 files changed, 14 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iio/imu/adis_buffer.c b/drivers/iio/imu/adis_buffer.c
index df6144285470..ac354321f63a 100644
--- a/drivers/iio/imu/adis_buffer.c
+++ b/drivers/iio/imu/adis_buffer.c
@@ -26,12 +26,10 @@ static int adis_update_scan_mode_burst(struct iio_dev *indio_dev,
 	unsigned int burst_length, burst_max_length;
 	u8 *tx;
 
-	/* All but the timestamp channel */
-	burst_length = (indio_dev->num_channels - 1) * sizeof(u16);
-	burst_length += adis->burst->extra_len + adis->burst_extra_len;
+	burst_length = adis->data->burst_len + adis->burst_extra_len;
 
-	if (adis->burst->burst_max_len)
-		burst_max_length = adis->burst->burst_max_len;
+	if (adis->data->burst_max_len)
+		burst_max_length = adis->data->burst_max_len;
 	else
 		burst_max_length = burst_length;
 
@@ -47,7 +45,7 @@ static int adis_update_scan_mode_burst(struct iio_dev *indio_dev,
 	}
 
 	tx = adis->buffer + burst_max_length;
-	tx[0] = ADIS_READ_REG(adis->burst->reg_cmd);
+	tx[0] = ADIS_READ_REG(adis->data->burst_reg_cmd);
 	tx[1] = 0;
 
 	adis->xfer[0].tx_buf = tx;
@@ -76,7 +74,7 @@ int adis_update_scan_mode(struct iio_dev *indio_dev,
 	kfree(adis->xfer);
 	kfree(adis->buffer);
 
-	if (adis->burst && adis->burst->en)
+	if (adis->data->burst_len)
 		return adis_update_scan_mode_burst(indio_dev, scan_mask);
 
 	scan_count = indio_dev->scan_bytes / 2;
diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h
index 01ba691da2f3..c502ea3b9199 100644
--- a/include/linux/iio/imu/adis.h
+++ b/include/linux/iio/imu/adis.h
@@ -51,6 +51,11 @@ struct adis_timeout {
  * @timeouts: Chip specific delays
  * @enable_irq: Hook for ADIS devices that have a special IRQ enable/disable
  * @has_paging: True if ADIS device has paged registers
+ * @burst_reg_cmd:	Register command that triggers burst
+ * @burst_len:		Burst size in the SPI RX buffer. If @burst_max_len is defined,
+ *			this should be the minimum size supported by the device.
+ * @burst_max_len:	Holds the maximum burst size when the device supports
+ *			more than one burst mode with different sizes
  */
 struct adis_data {
 	unsigned int read_delay;
@@ -75,6 +80,10 @@ struct adis_data {
 	int (*enable_irq)(struct adis *adis, bool enable);
 
 	bool has_paging;
+
+	unsigned int burst_reg_cmd;
+	unsigned int burst_len;
+	unsigned int burst_max_len;
 };
 
 /**
-- 
cgit v1.2.3


From e8173161746d1d8a8b9dfd8968cf695efaa90d09 Mon Sep 17 00:00:00 2001
From: Nuno Sá <nuno.sa@analog.com>
Date: Thu, 17 Sep 2020 17:52:23 +0200
Subject: iio: adis. Drop adis_burst struct
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

As there are no users anymore of this structure, it can be safely
removed.

Signed-off-by: Nuno Sá <nuno.sa@analog.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/20200917155223.218500-5-nuno.sa@analog.com
---
 include/linux/iio/imu/adis.h | 17 -----------------
 1 file changed, 17 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h
index c502ea3b9199..04e96d688ba9 100644
--- a/include/linux/iio/imu/adis.h
+++ b/include/linux/iio/imu/adis.h
@@ -20,7 +20,6 @@
 #define ADIS_REG_PAGE_ID 0x00
 
 struct adis;
-struct adis_burst;
 
 /**
  * struct adis_timeouts - ADIS chip variant timeouts
@@ -108,7 +107,6 @@ struct adis {
 	struct iio_trigger	*trig;
 
 	const struct adis_data	*data;
-	struct adis_burst	*burst;
 	unsigned int		burst_extra_len;
 	/**
 	 * The state_lock is meant to be used during operations that require
@@ -508,21 +506,6 @@ int adis_single_conversion(struct iio_dev *indio_dev,
 
 #ifdef CONFIG_IIO_ADIS_LIB_BUFFER
 
-/**
- * struct adis_burst - ADIS data for burst transfers
- * @en			burst mode enabled
- * @reg_cmd		register command that triggers burst
- * @extra_len		extra length to account in the SPI RX buffer
- * @burst_max_len	holds the maximum burst size when the device supports
- *			more than one burst mode with different sizes
- */
-struct adis_burst {
-	bool		en;
-	unsigned int	reg_cmd;
-	const u32	extra_len;
-	const u32	burst_max_len;
-};
-
 int
 devm_adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev,
 				   irq_handler_t trigger_handler);
-- 
cgit v1.2.3


From 12856e7acde4702b7c3238c15fcba86ff6aa507f Mon Sep 17 00:00:00 2001
From: Matthew Rosato <mjrosato@linux.ibm.com>
Date: Thu, 10 Sep 2020 10:59:55 -0400
Subject: PCI/IOV: Mark VFs as not implementing PCI_COMMAND_MEMORY

For VFs, the Memory Space Enable bit in the Command Register is
hard-wired to 0.

Add a new bit to signify devices where the Command Register Memory
Space Enable bit does not control the device's response to MMIO
accesses.

Fixes: abafbc551fdd ("vfio-pci: Invalidate mmaps and block MMIO access on disabled memory")
Signed-off-by: Matthew Rosato <mjrosato@linux.ibm.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/pci/iov.c   | 1 +
 include/linux/pci.h | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index b37e08c4f9d1..4afd4ee4f7f0 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -180,6 +180,7 @@ int pci_iov_add_virtfn(struct pci_dev *dev, int id)
 	virtfn->device = iov->vf_device;
 	virtfn->is_virtfn = 1;
 	virtfn->physfn = pci_dev_get(dev);
+	virtfn->no_command_memory = 1;
 
 	if (id == 0)
 		pci_read_vf_config_common(virtfn);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 835530605c0d..3ff723124ca7 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -445,6 +445,7 @@ struct pci_dev {
 	unsigned int	is_probed:1;		/* Device probing in progress */
 	unsigned int	link_active_reporting:1;/* Device capable of reporting link active */
 	unsigned int	no_vf_scan:1;		/* Don't scan for VFs after IOV enablement */
+	unsigned int	no_command_memory:1;	/* No PCI_COMMAND_MEMORY */
 	pci_dev_flags_t dev_flags;
 	atomic_t	enable_cnt;	/* pci_enable_device has been called */
 
-- 
cgit v1.2.3


From 2af30f115d6957f372ce3096c7198763ff253d97 Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@cloudflare.com>
Date: Mon, 21 Sep 2020 13:12:17 +0100
Subject: btf: Make btf_set_contains take a const pointer

bsearch doesn't modify the contents of the array, so we can take a const pointer.

Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200921121227.255763-2-lmb@cloudflare.com
---
 include/linux/bpf.h | 2 +-
 kernel/bpf/btf.c    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index d7c5a6ed87e3..0478b20d335b 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1905,6 +1905,6 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 		       void *addr1, void *addr2);
 
 struct btf_id_set;
-bool btf_id_set_contains(struct btf_id_set *set, u32 id);
+bool btf_id_set_contains(const struct btf_id_set *set, u32 id);
 
 #endif /* _LINUX_BPF_H */
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index f9ac6935ab3c..a2330f6fe2e6 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -4772,7 +4772,7 @@ static int btf_id_cmp_func(const void *a, const void *b)
 	return *pa - *pb;
 }
 
-bool btf_id_set_contains(struct btf_id_set *set, u32 id)
+bool btf_id_set_contains(const struct btf_id_set *set, u32 id)
 {
 	return bsearch(&id, set->ids, set->cnt, sizeof(u32), btf_id_cmp_func) != NULL;
 }
-- 
cgit v1.2.3


From 27774b7073b5d520c80f1fcb8e9993fc139f21bd Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@cloudflare.com>
Date: Mon, 21 Sep 2020 13:12:19 +0100
Subject: btf: Add BTF_ID_LIST_SINGLE macro

Add a convenience macro that allows defining a BTF ID list with
a single item. This lets us cut down on repetitive macros.

Suggested-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200921121227.255763-4-lmb@cloudflare.com
---
 include/linux/btf_ids.h       | 8 ++++++++
 tools/include/linux/btf_ids.h | 8 ++++++++
 2 files changed, 16 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h
index 210b086188a3..57890b357f85 100644
--- a/include/linux/btf_ids.h
+++ b/include/linux/btf_ids.h
@@ -76,6 +76,13 @@ extern u32 name[];
 #define BTF_ID_LIST_GLOBAL(name)			\
 __BTF_ID_LIST(name, globl)
 
+/* The BTF_ID_LIST_SINGLE macro defines a BTF_ID_LIST with
+ * a single entry.
+ */
+#define BTF_ID_LIST_SINGLE(name, prefix, typename)	\
+	BTF_ID_LIST(name) \
+	BTF_ID(prefix, typename)
+
 /*
  * The BTF_ID_UNUSED macro defines 4 zero bytes.
  * It's used when we want to define 'unused' entry
@@ -140,6 +147,7 @@ extern struct btf_id_set name;
 #define BTF_ID(prefix, name)
 #define BTF_ID_UNUSED
 #define BTF_ID_LIST_GLOBAL(name) u32 name[1];
+#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 name[1];
 #define BTF_SET_START(name) static struct btf_id_set name = { 0 };
 #define BTF_SET_START_GLOBAL(name) static struct btf_id_set name = { 0 };
 #define BTF_SET_END(name)
diff --git a/tools/include/linux/btf_ids.h b/tools/include/linux/btf_ids.h
index 210b086188a3..57890b357f85 100644
--- a/tools/include/linux/btf_ids.h
+++ b/tools/include/linux/btf_ids.h
@@ -76,6 +76,13 @@ extern u32 name[];
 #define BTF_ID_LIST_GLOBAL(name)			\
 __BTF_ID_LIST(name, globl)
 
+/* The BTF_ID_LIST_SINGLE macro defines a BTF_ID_LIST with
+ * a single entry.
+ */
+#define BTF_ID_LIST_SINGLE(name, prefix, typename)	\
+	BTF_ID_LIST(name) \
+	BTF_ID(prefix, typename)
+
 /*
  * The BTF_ID_UNUSED macro defines 4 zero bytes.
  * It's used when we want to define 'unused' entry
@@ -140,6 +147,7 @@ extern struct btf_id_set name;
 #define BTF_ID(prefix, name)
 #define BTF_ID_UNUSED
 #define BTF_ID_LIST_GLOBAL(name) u32 name[1];
+#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 name[1];
 #define BTF_SET_START(name) static struct btf_id_set name = { 0 };
 #define BTF_SET_START_GLOBAL(name) static struct btf_id_set name = { 0 };
 #define BTF_SET_END(name)
-- 
cgit v1.2.3


From 9436ef6e862b9ca22e5b12f87b106e07d5af4cae Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@cloudflare.com>
Date: Mon, 21 Sep 2020 13:12:20 +0100
Subject: bpf: Allow specifying a BTF ID per argument in function protos

Function prototypes using ARG_PTR_TO_BTF_ID currently use two ways to signal
which BTF IDs are acceptable. First, bpf_func_proto.btf_id is an array of
IDs, one for each argument. This array is only accessed up to the highest
numbered argument that uses ARG_PTR_TO_BTF_ID and may therefore be less than
five arguments long. It usually points at a BTF_ID_LIST. Second, check_btf_id
is a function pointer that is called by the verifier if present. It gets the
actual BTF ID of the register, and the argument number we're currently checking.
It turns out that the only user check_arg_btf_id ignores the argument, and is
simply used to check whether the BTF ID has a struct sock_common at it's start.

Replace both of these mechanisms with an explicit BTF ID for each argument
in a function proto. Thanks to btf_struct_ids_match this is very flexible:
check_arg_btf_id can be replaced by requiring struct sock_common.

Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200921121227.255763-5-lmb@cloudflare.com
---
 include/linux/bpf.h            | 18 +++++++++--------
 kernel/bpf/bpf_inode_storage.c |  8 +++-----
 kernel/bpf/btf.c               | 13 -------------
 kernel/bpf/stackmap.c          |  5 ++---
 kernel/bpf/verifier.c          | 44 +++++++++++++++++++++---------------------
 kernel/trace/bpf_trace.c       | 15 +++++---------
 net/core/bpf_sk_storage.c      |  8 ++------
 net/core/filter.c              | 31 +++++++++--------------------
 net/ipv4/bpf_tcp_ca.c          | 19 +++++-------------
 9 files changed, 58 insertions(+), 103 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 0478b20d335b..87b0d5dcc1ff 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -326,12 +326,16 @@ struct bpf_func_proto {
 		};
 		enum bpf_arg_type arg_type[5];
 	};
-	int *btf_id; /* BTF ids of arguments */
-	bool (*check_btf_id)(u32 btf_id, u32 arg); /* if the argument btf_id is
-						    * valid. Often used if more
-						    * than one btf id is permitted
-						    * for this argument.
-						    */
+	union {
+		struct {
+			u32 *arg1_btf_id;
+			u32 *arg2_btf_id;
+			u32 *arg3_btf_id;
+			u32 *arg4_btf_id;
+			u32 *arg5_btf_id;
+		};
+		u32 *arg_btf_id[5];
+	};
 	int *ret_btf_id; /* return value btf_id */
 	bool (*allowed)(const struct bpf_prog *prog);
 };
@@ -1385,8 +1389,6 @@ int btf_struct_access(struct bpf_verifier_log *log,
 		      u32 *next_btf_id);
 bool btf_struct_ids_match(struct bpf_verifier_log *log,
 			  int off, u32 id, u32 need_type_id);
-int btf_resolve_helper_id(struct bpf_verifier_log *log,
-			  const struct bpf_func_proto *fn, int);
 
 int btf_distill_func_proto(struct bpf_verifier_log *log,
 			   struct btf *btf,
diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c
index 75be02799c0f..6edff97ad594 100644
--- a/kernel/bpf/bpf_inode_storage.c
+++ b/kernel/bpf/bpf_inode_storage.c
@@ -249,9 +249,7 @@ const struct bpf_map_ops inode_storage_map_ops = {
 	.map_owner_storage_ptr = inode_storage_ptr,
 };
 
-BTF_ID_LIST(bpf_inode_storage_btf_ids)
-BTF_ID_UNUSED
-BTF_ID(struct, inode)
+BTF_ID_LIST_SINGLE(bpf_inode_storage_btf_ids, struct, inode)
 
 const struct bpf_func_proto bpf_inode_storage_get_proto = {
 	.func		= bpf_inode_storage_get,
@@ -259,9 +257,9 @@ const struct bpf_func_proto bpf_inode_storage_get_proto = {
 	.ret_type	= RET_PTR_TO_MAP_VALUE_OR_NULL,
 	.arg1_type	= ARG_CONST_MAP_PTR,
 	.arg2_type	= ARG_PTR_TO_BTF_ID,
+	.arg2_btf_id	= &bpf_inode_storage_btf_ids[0],
 	.arg3_type	= ARG_PTR_TO_MAP_VALUE_OR_NULL,
 	.arg4_type	= ARG_ANYTHING,
-	.btf_id		= bpf_inode_storage_btf_ids,
 };
 
 const struct bpf_func_proto bpf_inode_storage_delete_proto = {
@@ -270,5 +268,5 @@ const struct bpf_func_proto bpf_inode_storage_delete_proto = {
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_CONST_MAP_PTR,
 	.arg2_type	= ARG_PTR_TO_BTF_ID,
-	.btf_id		= bpf_inode_storage_btf_ids,
+	.arg2_btf_id	= &bpf_inode_storage_btf_ids[0],
 };
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index a2330f6fe2e6..5d3c36e13139 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -4193,19 +4193,6 @@ again:
 	return true;
 }
 
-int btf_resolve_helper_id(struct bpf_verifier_log *log,
-			  const struct bpf_func_proto *fn, int arg)
-{
-	int id;
-
-	if (fn->arg_type[arg] != ARG_PTR_TO_BTF_ID || !btf_vmlinux)
-		return -EINVAL;
-	id = fn->btf_id[arg];
-	if (!id || id > btf_vmlinux->nr_types)
-		return -EINVAL;
-	return id;
-}
-
 static int __get_type_size(struct btf *btf, u32 btf_id,
 			   const struct btf_type **bad_type)
 {
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index a2fa006f430e..06065fa27124 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -665,18 +665,17 @@ BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf,
 	return __bpf_get_stack(regs, task, NULL, buf, size, flags);
 }
 
-BTF_ID_LIST(bpf_get_task_stack_btf_ids)
-BTF_ID(struct, task_struct)
+BTF_ID_LIST_SINGLE(bpf_get_task_stack_btf_ids, struct, task_struct)
 
 const struct bpf_func_proto bpf_get_task_stack_proto = {
 	.func		= bpf_get_task_stack,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &bpf_get_task_stack_btf_ids[0],
 	.arg2_type	= ARG_PTR_TO_UNINIT_MEM,
 	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg4_type	= ARG_ANYTHING,
-	.btf_id		= bpf_get_task_stack_btf_ids,
 };
 
 BPF_CALL_4(bpf_get_stack_pe, struct bpf_perf_event_data_kern *, ctx,
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 06238395f244..30da34d9b93b 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -238,7 +238,6 @@ struct bpf_call_arg_meta {
 	u64 msize_max_value;
 	int ref_obj_id;
 	int func_id;
-	u32 btf_id;
 };
 
 struct btf *btf_vmlinux;
@@ -4049,29 +4048,23 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 				goto err_type;
 		}
 	} else if (arg_type == ARG_PTR_TO_BTF_ID) {
-		bool ids_match = false;
+		const u32 *btf_id = fn->arg_btf_id[arg];
 
 		expected_type = PTR_TO_BTF_ID;
 		if (type != expected_type)
 			goto err_type;
-		if (!fn->check_btf_id) {
-			if (reg->btf_id != meta->btf_id) {
-				ids_match = btf_struct_ids_match(&env->log, reg->off, reg->btf_id,
-								 meta->btf_id);
-				if (!ids_match) {
-					verbose(env, "Helper has type %s got %s in R%d\n",
-						kernel_type_name(meta->btf_id),
-						kernel_type_name(reg->btf_id), regno);
-					return -EACCES;
-				}
-			}
-		} else if (!fn->check_btf_id(reg->btf_id, arg)) {
-			verbose(env, "Helper does not support %s in R%d\n",
-				kernel_type_name(reg->btf_id), regno);
 
+		if (!btf_id) {
+			verbose(env, "verifier internal error: missing BTF ID\n");
+			return -EFAULT;
+		}
+
+		if (!btf_struct_ids_match(&env->log, reg->off, reg->btf_id, *btf_id)) {
+			verbose(env, "R%d is of type %s but %s is expected\n",
+				regno, kernel_type_name(reg->btf_id), kernel_type_name(*btf_id));
 			return -EACCES;
 		}
-		if ((reg->off && !ids_match) || !tnum_is_const(reg->var_off) || reg->var_off.value) {
+		if (!tnum_is_const(reg->var_off) || reg->var_off.value) {
 			verbose(env, "R%d is a pointer to in-kernel struct with non-zero offset\n",
 				regno);
 			return -EACCES;
@@ -4545,10 +4538,22 @@ static bool check_refcount_ok(const struct bpf_func_proto *fn, int func_id)
 	return count <= 1;
 }
 
+static bool check_btf_id_ok(const struct bpf_func_proto *fn)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(fn->arg_type); i++)
+		if (fn->arg_type[i] == ARG_PTR_TO_BTF_ID && !fn->arg_btf_id[i])
+			return false;
+
+	return true;
+}
+
 static int check_func_proto(const struct bpf_func_proto *fn, int func_id)
 {
 	return check_raw_mode_ok(fn) &&
 	       check_arg_pair_ok(fn) &&
+	       check_btf_id_ok(fn) &&
 	       check_refcount_ok(fn, func_id) ? 0 : -EINVAL;
 }
 
@@ -4944,11 +4949,6 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 	meta.func_id = func_id;
 	/* check args */
 	for (i = 0; i < 5; i++) {
-		if (!fn->check_btf_id) {
-			err = btf_resolve_helper_id(&env->log, fn, i);
-			if (err > 0)
-				meta.btf_id = err;
-		}
 		err = check_func_arg(env, i, &meta, fn);
 		if (err)
 			return err;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index b2a5380eb187..ebf9be4d0d6a 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -743,19 +743,18 @@ out:
 	return err;
 }
 
-BTF_ID_LIST(bpf_seq_printf_btf_ids)
-BTF_ID(struct, seq_file)
+BTF_ID_LIST_SINGLE(btf_seq_file_ids, struct, seq_file)
 
 static const struct bpf_func_proto bpf_seq_printf_proto = {
 	.func		= bpf_seq_printf,
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &btf_seq_file_ids[0],
 	.arg2_type	= ARG_PTR_TO_MEM,
 	.arg3_type	= ARG_CONST_SIZE,
 	.arg4_type      = ARG_PTR_TO_MEM_OR_NULL,
 	.arg5_type      = ARG_CONST_SIZE_OR_ZERO,
-	.btf_id		= bpf_seq_printf_btf_ids,
 };
 
 BPF_CALL_3(bpf_seq_write, struct seq_file *, m, const void *, data, u32, len)
@@ -763,17 +762,14 @@ BPF_CALL_3(bpf_seq_write, struct seq_file *, m, const void *, data, u32, len)
 	return seq_write(m, data, len) ? -EOVERFLOW : 0;
 }
 
-BTF_ID_LIST(bpf_seq_write_btf_ids)
-BTF_ID(struct, seq_file)
-
 static const struct bpf_func_proto bpf_seq_write_proto = {
 	.func		= bpf_seq_write,
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &btf_seq_file_ids[0],
 	.arg2_type	= ARG_PTR_TO_MEM,
 	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
-	.btf_id		= bpf_seq_write_btf_ids,
 };
 
 static __always_inline int
@@ -1130,17 +1126,16 @@ static bool bpf_d_path_allowed(const struct bpf_prog *prog)
 	return btf_id_set_contains(&btf_allowlist_d_path, prog->aux->attach_btf_id);
 }
 
-BTF_ID_LIST(bpf_d_path_btf_ids)
-BTF_ID(struct, path)
+BTF_ID_LIST_SINGLE(bpf_d_path_btf_ids, struct, path)
 
 static const struct bpf_func_proto bpf_d_path_proto = {
 	.func		= bpf_d_path,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &bpf_d_path_btf_ids[0],
 	.arg2_type	= ARG_PTR_TO_MEM,
 	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
-	.btf_id		= bpf_d_path_btf_ids,
 	.allowed	= bpf_d_path_allowed,
 };
 
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index 4a86ea34f29e..d653a583dbc9 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -378,19 +378,15 @@ const struct bpf_func_proto bpf_sk_storage_delete_proto = {
 	.arg2_type	= ARG_PTR_TO_SOCKET,
 };
 
-BTF_ID_LIST(sk_storage_btf_ids)
-BTF_ID_UNUSED
-BTF_ID(struct, sock)
-
 const struct bpf_func_proto sk_storage_get_btf_proto = {
 	.func		= bpf_sk_storage_get,
 	.gpl_only	= false,
 	.ret_type	= RET_PTR_TO_MAP_VALUE_OR_NULL,
 	.arg1_type	= ARG_CONST_MAP_PTR,
 	.arg2_type	= ARG_PTR_TO_BTF_ID,
+	.arg2_btf_id	= &btf_sock_ids[BTF_SOCK_TYPE_SOCK],
 	.arg3_type	= ARG_PTR_TO_MAP_VALUE_OR_NULL,
 	.arg4_type	= ARG_ANYTHING,
-	.btf_id		= sk_storage_btf_ids,
 };
 
 const struct bpf_func_proto sk_storage_delete_btf_proto = {
@@ -399,7 +395,7 @@ const struct bpf_func_proto sk_storage_delete_btf_proto = {
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_CONST_MAP_PTR,
 	.arg2_type	= ARG_PTR_TO_BTF_ID,
-	.btf_id		= sk_storage_btf_ids,
+	.arg2_btf_id	= &btf_sock_ids[BTF_SOCK_TYPE_SOCK],
 };
 
 struct bpf_sk_storage_diag {
diff --git a/net/core/filter.c b/net/core/filter.c
index d266c6941967..6014e5f40c58 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3803,19 +3803,18 @@ static const struct bpf_func_proto bpf_skb_event_output_proto = {
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 
-BTF_ID_LIST(bpf_skb_output_btf_ids)
-BTF_ID(struct, sk_buff)
+BTF_ID_LIST_SINGLE(bpf_skb_output_btf_ids, struct, sk_buff)
 
 const struct bpf_func_proto bpf_skb_output_proto = {
 	.func		= bpf_skb_event_output,
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &bpf_skb_output_btf_ids[0],
 	.arg2_type	= ARG_CONST_MAP_PTR,
 	.arg3_type	= ARG_ANYTHING,
 	.arg4_type	= ARG_PTR_TO_MEM,
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
-	.btf_id		= bpf_skb_output_btf_ids,
 };
 
 static unsigned short bpf_tunnel_key_af(u64 flags)
@@ -4199,19 +4198,18 @@ static const struct bpf_func_proto bpf_xdp_event_output_proto = {
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 
-BTF_ID_LIST(bpf_xdp_output_btf_ids)
-BTF_ID(struct, xdp_buff)
+BTF_ID_LIST_SINGLE(bpf_xdp_output_btf_ids, struct, xdp_buff)
 
 const struct bpf_func_proto bpf_xdp_output_proto = {
 	.func		= bpf_xdp_event_output,
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &bpf_xdp_output_btf_ids[0],
 	.arg2_type	= ARG_CONST_MAP_PTR,
 	.arg3_type	= ARG_ANYTHING,
 	.arg4_type	= ARG_PTR_TO_MEM,
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
-	.btf_id		= bpf_xdp_output_btf_ids,
 };
 
 BPF_CALL_1(bpf_get_socket_cookie, struct sk_buff *, skb)
@@ -9897,17 +9895,6 @@ BTF_SOCK_TYPE_xxx
 u32 btf_sock_ids[MAX_BTF_SOCK_TYPE];
 #endif
 
-static bool check_arg_btf_id(u32 btf_id, u32 arg)
-{
-	int i;
-
-	/* only one argument, no need to check arg */
-	for (i = 0; i < MAX_BTF_SOCK_TYPE; i++)
-		if (btf_sock_ids[i] == btf_id)
-			return true;
-	return false;
-}
-
 BPF_CALL_1(bpf_skc_to_tcp6_sock, struct sock *, sk)
 {
 	/* tcp6_sock type is not generated in dwarf and hence btf,
@@ -9926,7 +9913,7 @@ const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto = {
 	.gpl_only		= false,
 	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
 	.arg1_type		= ARG_PTR_TO_BTF_ID,
-	.check_btf_id		= check_arg_btf_id,
+	.arg1_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP6],
 };
 
@@ -9943,7 +9930,7 @@ const struct bpf_func_proto bpf_skc_to_tcp_sock_proto = {
 	.gpl_only		= false,
 	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
 	.arg1_type		= ARG_PTR_TO_BTF_ID,
-	.check_btf_id		= check_arg_btf_id,
+	.arg1_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP],
 };
 
@@ -9967,7 +9954,7 @@ const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto = {
 	.gpl_only		= false,
 	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
 	.arg1_type		= ARG_PTR_TO_BTF_ID,
-	.check_btf_id		= check_arg_btf_id,
+	.arg1_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP_TW],
 };
 
@@ -9991,7 +9978,7 @@ const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto = {
 	.gpl_only		= false,
 	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
 	.arg1_type		= ARG_PTR_TO_BTF_ID,
-	.check_btf_id		= check_arg_btf_id,
+	.arg1_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP_REQ],
 };
 
@@ -10013,6 +10000,6 @@ const struct bpf_func_proto bpf_skc_to_udp6_sock_proto = {
 	.gpl_only		= false,
 	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
 	.arg1_type		= ARG_PTR_TO_BTF_ID,
-	.check_btf_id		= check_arg_btf_id,
+	.arg1_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_UDP6],
 };
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index e3939f76b024..74a2ef598c31 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -28,23 +28,18 @@ static u32 unsupported_ops[] = {
 static const struct btf_type *tcp_sock_type;
 static u32 tcp_sock_id, sock_id;
 
-static int btf_sk_storage_get_ids[5];
 static struct bpf_func_proto btf_sk_storage_get_proto __read_mostly;
-
-static int btf_sk_storage_delete_ids[5];
 static struct bpf_func_proto btf_sk_storage_delete_proto __read_mostly;
 
-static void convert_sk_func_proto(struct bpf_func_proto *to, int *to_btf_ids,
-				  const struct bpf_func_proto *from)
+static void convert_sk_func_proto(struct bpf_func_proto *to, const struct bpf_func_proto *from)
 {
 	int i;
 
 	*to = *from;
-	to->btf_id = to_btf_ids;
 	for (i = 0; i < ARRAY_SIZE(to->arg_type); i++) {
 		if (to->arg_type[i] == ARG_PTR_TO_SOCKET) {
 			to->arg_type[i] = ARG_PTR_TO_BTF_ID;
-			to->btf_id[i] = tcp_sock_id;
+			to->arg_btf_id[i] = &tcp_sock_id;
 		}
 	}
 }
@@ -64,12 +59,8 @@ static int bpf_tcp_ca_init(struct btf *btf)
 	tcp_sock_id = type_id;
 	tcp_sock_type = btf_type_by_id(btf, tcp_sock_id);
 
-	convert_sk_func_proto(&btf_sk_storage_get_proto,
-			      btf_sk_storage_get_ids,
-			      &bpf_sk_storage_get_proto);
-	convert_sk_func_proto(&btf_sk_storage_delete_proto,
-			      btf_sk_storage_delete_ids,
-			      &bpf_sk_storage_delete_proto);
+	convert_sk_func_proto(&btf_sk_storage_get_proto, &bpf_sk_storage_get_proto);
+	convert_sk_func_proto(&btf_sk_storage_delete_proto, &bpf_sk_storage_delete_proto);
 
 	return 0;
 }
@@ -185,8 +176,8 @@ static const struct bpf_func_proto bpf_tcp_send_ack_proto = {
 	/* In case we want to report error later */
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &tcp_sock_id,
 	.arg2_type	= ARG_ANYTHING,
-	.btf_id		= &tcp_sock_id,
 };
 
 static const struct bpf_func_proto *
-- 
cgit v1.2.3


From f79e7ea571732a6e16f15c6e2f000c347e2d7431 Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@cloudflare.com>
Date: Mon, 21 Sep 2020 13:12:27 +0100
Subject: bpf: Use a table to drive helper arg type checks

The mapping between bpf_arg_type and bpf_reg_type is encoded in a big
hairy if statement that is hard to follow. The debug output also leaves
to be desired: if a reg_type doesn't match we only print one of the
options, instead printing all the valid ones.

Convert the if statement into a table which is then used to drive type
checking. If none of the reg_types match we print all options, e.g.:

    R2 type=rdonly_buf expected=fp, pkt, pkt_meta, map_value

Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200921121227.255763-12-lmb@cloudflare.com
---
 include/linux/bpf.h   |   1 +
 kernel/bpf/verifier.c | 183 ++++++++++++++++++++++++++++++--------------------
 2 files changed, 110 insertions(+), 74 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 87b0d5dcc1ff..fc5c901c7542 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -292,6 +292,7 @@ enum bpf_arg_type {
 	ARG_PTR_TO_ALLOC_MEM,	/* pointer to dynamically allocated memory */
 	ARG_PTR_TO_ALLOC_MEM_OR_NULL,	/* pointer to dynamically allocated memory or NULL */
 	ARG_CONST_ALLOC_SIZE_OR_ZERO,	/* number of allocated bytes requested */
+	__BPF_ARG_TYPE_MAX,
 };
 
 /* type of values returned from helper functions */
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 129416ea0256..15ab889b0a3f 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3903,12 +3903,6 @@ static bool arg_type_is_mem_size(enum bpf_arg_type type)
 	       type == ARG_CONST_SIZE_OR_ZERO;
 }
 
-static bool arg_type_is_alloc_mem_ptr(enum bpf_arg_type type)
-{
-	return type == ARG_PTR_TO_ALLOC_MEM ||
-	       type == ARG_PTR_TO_ALLOC_MEM_OR_NULL;
-}
-
 static bool arg_type_is_alloc_size(enum bpf_arg_type type)
 {
 	return type == ARG_CONST_ALLOC_SIZE_OR_ZERO;
@@ -3957,14 +3951,115 @@ static int resolve_map_arg_type(struct bpf_verifier_env *env,
 	return 0;
 }
 
+struct bpf_reg_types {
+	const enum bpf_reg_type types[10];
+};
+
+static const struct bpf_reg_types map_key_value_types = {
+	.types = {
+		PTR_TO_STACK,
+		PTR_TO_PACKET,
+		PTR_TO_PACKET_META,
+		PTR_TO_MAP_VALUE,
+	},
+};
+
+static const struct bpf_reg_types sock_types = {
+	.types = {
+		PTR_TO_SOCK_COMMON,
+		PTR_TO_SOCKET,
+		PTR_TO_TCP_SOCK,
+		PTR_TO_XDP_SOCK,
+	},
+};
+
+static const struct bpf_reg_types mem_types = {
+	.types = {
+		PTR_TO_STACK,
+		PTR_TO_PACKET,
+		PTR_TO_PACKET_META,
+		PTR_TO_MAP_VALUE,
+		PTR_TO_MEM,
+		PTR_TO_RDONLY_BUF,
+		PTR_TO_RDWR_BUF,
+	},
+};
+
+static const struct bpf_reg_types int_ptr_types = {
+	.types = {
+		PTR_TO_STACK,
+		PTR_TO_PACKET,
+		PTR_TO_PACKET_META,
+		PTR_TO_MAP_VALUE,
+	},
+};
+
+static const struct bpf_reg_types fullsock_types = { .types = { PTR_TO_SOCKET } };
+static const struct bpf_reg_types scalar_types = { .types = { SCALAR_VALUE } };
+static const struct bpf_reg_types context_types = { .types = { PTR_TO_CTX } };
+static const struct bpf_reg_types alloc_mem_types = { .types = { PTR_TO_MEM } };
+static const struct bpf_reg_types const_map_ptr_types = { .types = { CONST_PTR_TO_MAP } };
+static const struct bpf_reg_types btf_ptr_types = { .types = { PTR_TO_BTF_ID } };
+static const struct bpf_reg_types spin_lock_types = { .types = { PTR_TO_MAP_VALUE } };
+
+static const struct bpf_reg_types *compatible_reg_types[] = {
+	[ARG_PTR_TO_MAP_KEY]		= &map_key_value_types,
+	[ARG_PTR_TO_MAP_VALUE]		= &map_key_value_types,
+	[ARG_PTR_TO_UNINIT_MAP_VALUE]	= &map_key_value_types,
+	[ARG_PTR_TO_MAP_VALUE_OR_NULL]	= &map_key_value_types,
+	[ARG_CONST_SIZE]		= &scalar_types,
+	[ARG_CONST_SIZE_OR_ZERO]	= &scalar_types,
+	[ARG_CONST_ALLOC_SIZE_OR_ZERO]	= &scalar_types,
+	[ARG_CONST_MAP_PTR]		= &const_map_ptr_types,
+	[ARG_PTR_TO_CTX]		= &context_types,
+	[ARG_PTR_TO_CTX_OR_NULL]	= &context_types,
+	[ARG_PTR_TO_SOCK_COMMON]	= &sock_types,
+	[ARG_PTR_TO_SOCKET]		= &fullsock_types,
+	[ARG_PTR_TO_SOCKET_OR_NULL]	= &fullsock_types,
+	[ARG_PTR_TO_BTF_ID]		= &btf_ptr_types,
+	[ARG_PTR_TO_SPIN_LOCK]		= &spin_lock_types,
+	[ARG_PTR_TO_MEM]		= &mem_types,
+	[ARG_PTR_TO_MEM_OR_NULL]	= &mem_types,
+	[ARG_PTR_TO_UNINIT_MEM]		= &mem_types,
+	[ARG_PTR_TO_ALLOC_MEM]		= &alloc_mem_types,
+	[ARG_PTR_TO_ALLOC_MEM_OR_NULL]	= &alloc_mem_types,
+	[ARG_PTR_TO_INT]		= &int_ptr_types,
+	[ARG_PTR_TO_LONG]		= &int_ptr_types,
+	[__BPF_ARG_TYPE_MAX]		= NULL,
+};
+
+static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
+			  const struct bpf_reg_types *compatible)
+{
+	struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
+	enum bpf_reg_type expected, type = reg->type;
+	int i, j;
+
+	for (i = 0; i < ARRAY_SIZE(compatible->types); i++) {
+		expected = compatible->types[i];
+		if (expected == NOT_INIT)
+			break;
+
+		if (type == expected)
+			return 0;
+	}
+
+	verbose(env, "R%d type=%s expected=", regno, reg_type_str[type]);
+	for (j = 0; j + 1 < i; j++)
+		verbose(env, "%s, ", reg_type_str[compatible->types[j]]);
+	verbose(env, "%s\n", reg_type_str[compatible->types[j]]);
+	return -EACCES;
+}
+
 static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 			  struct bpf_call_arg_meta *meta,
 			  const struct bpf_func_proto *fn)
 {
 	u32 regno = BPF_REG_1 + arg;
 	struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
-	enum bpf_reg_type expected_type, type = reg->type;
 	enum bpf_arg_type arg_type = fn->arg_type[arg];
+	const struct bpf_reg_types *compatible;
+	enum bpf_reg_type type = reg->type;
 	int err = 0;
 
 	if (arg_type == ARG_DONTCARE)
@@ -4003,72 +4098,16 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 		 */
 		goto skip_type_check;
 
-	if (arg_type == ARG_PTR_TO_MAP_KEY ||
-	    arg_type == ARG_PTR_TO_MAP_VALUE ||
-	    arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE ||
-	    arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL) {
-		expected_type = PTR_TO_STACK;
-		if (!type_is_pkt_pointer(type) &&
-		    type != PTR_TO_MAP_VALUE &&
-		    type != expected_type)
-			goto err_type;
-	} else if (arg_type == ARG_CONST_SIZE ||
-		   arg_type == ARG_CONST_SIZE_OR_ZERO ||
-		   arg_type == ARG_CONST_ALLOC_SIZE_OR_ZERO) {
-		expected_type = SCALAR_VALUE;
-		if (type != expected_type)
-			goto err_type;
-	} else if (arg_type == ARG_CONST_MAP_PTR) {
-		expected_type = CONST_PTR_TO_MAP;
-		if (type != expected_type)
-			goto err_type;
-	} else if (arg_type == ARG_PTR_TO_CTX ||
-		   arg_type == ARG_PTR_TO_CTX_OR_NULL) {
-		expected_type = PTR_TO_CTX;
-		if (type != expected_type)
-			goto err_type;
-	} else if (arg_type == ARG_PTR_TO_SOCK_COMMON) {
-		expected_type = PTR_TO_SOCK_COMMON;
-		/* Any sk pointer can be ARG_PTR_TO_SOCK_COMMON */
-		if (!type_is_sk_pointer(type))
-			goto err_type;
-	} else if (arg_type == ARG_PTR_TO_SOCKET ||
-		   arg_type == ARG_PTR_TO_SOCKET_OR_NULL) {
-		expected_type = PTR_TO_SOCKET;
-		if (type != expected_type)
-			goto err_type;
-	} else if (arg_type == ARG_PTR_TO_BTF_ID) {
-		expected_type = PTR_TO_BTF_ID;
-		if (type != expected_type)
-			goto err_type;
-	} else if (arg_type == ARG_PTR_TO_SPIN_LOCK) {
-		expected_type = PTR_TO_MAP_VALUE;
-		if (type != expected_type)
-			goto err_type;
-	} else if (arg_type_is_mem_ptr(arg_type)) {
-		expected_type = PTR_TO_STACK;
-		if (!type_is_pkt_pointer(type) &&
-		    type != PTR_TO_MAP_VALUE &&
-		    type != PTR_TO_MEM &&
-		    type != PTR_TO_RDONLY_BUF &&
-		    type != PTR_TO_RDWR_BUF &&
-		    type != expected_type)
-			goto err_type;
-	} else if (arg_type_is_alloc_mem_ptr(arg_type)) {
-		expected_type = PTR_TO_MEM;
-		if (type != expected_type)
-			goto err_type;
-	} else if (arg_type_is_int_ptr(arg_type)) {
-		expected_type = PTR_TO_STACK;
-		if (!type_is_pkt_pointer(type) &&
-		    type != PTR_TO_MAP_VALUE &&
-		    type != expected_type)
-			goto err_type;
-	} else {
-		verbose(env, "unsupported arg_type %d\n", arg_type);
+	compatible = compatible_reg_types[arg_type];
+	if (!compatible) {
+		verbose(env, "verifier internal error: unsupported arg type %d\n", arg_type);
 		return -EFAULT;
 	}
 
+	err = check_reg_type(env, regno, compatible);
+	if (err)
+		return err;
+
 	if (type == PTR_TO_BTF_ID) {
 		const u32 *btf_id = fn->arg_btf_id[arg];
 
@@ -4221,10 +4260,6 @@ skip_type_check:
 	}
 
 	return err;
-err_type:
-	verbose(env, "R%d type=%s expected=%s\n", regno,
-		reg_type_str[type], reg_type_str[expected_type]);
-	return -EACCES;
 }
 
 static bool may_update_sockmap(struct bpf_verifier_env *env, int func_id)
-- 
cgit v1.2.3


From 92ec804f3dbf0d986f8e10850bfff14f316d7aaf Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Mon, 21 Sep 2020 15:10:53 -0700
Subject: net: phy: bcm7xxx: Add an entry for BCM72113

BCM72113 features a 28nm integrated EPHY, add an entry to the driver for
it.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/bcm7xxx.c | 2 ++
 include/linux/brcmphy.h   | 1 +
 2 files changed, 3 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c
index 744c24491d63..15812001b3ff 100644
--- a/drivers/net/phy/bcm7xxx.c
+++ b/drivers/net/phy/bcm7xxx.c
@@ -611,6 +611,7 @@ static void bcm7xxx_28nm_remove(struct phy_device *phydev)
 }
 
 static struct phy_driver bcm7xxx_driver[] = {
+	BCM7XXX_28NM_EPHY(PHY_ID_BCM72113, "Broadcom BCM72113"),
 	BCM7XXX_28NM_GPHY(PHY_ID_BCM7250, "Broadcom BCM7250"),
 	BCM7XXX_28NM_EPHY(PHY_ID_BCM7255, "Broadcom BCM7255"),
 	BCM7XXX_28NM_EPHY(PHY_ID_BCM7260, "Broadcom BCM7260"),
@@ -631,6 +632,7 @@ static struct phy_driver bcm7xxx_driver[] = {
 };
 
 static struct mdio_device_id __maybe_unused bcm7xxx_tbl[] = {
+	{ PHY_ID_BCM72113, 0xfffffff0 },
 	{ PHY_ID_BCM7250, 0xfffffff0, },
 	{ PHY_ID_BCM7255, 0xfffffff0, },
 	{ PHY_ID_BCM7260, 0xfffffff0, },
diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index 6ad4c000661a..d0bd226d6bd9 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -30,6 +30,7 @@
 #define PHY_ID_BCM57780			0x03625d90
 #define PHY_ID_BCM89610			0x03625cd0
 
+#define PHY_ID_BCM72113			0x35905310
 #define PHY_ID_BCM7250			0xae025280
 #define PHY_ID_BCM7255			0xae025120
 #define PHY_ID_BCM7260			0xae025190
-- 
cgit v1.2.3


From 74caba7f2a0685575b3ee5330a118f5922485e02 Mon Sep 17 00:00:00 2001
From: John Ogness <john.ogness@linutronix.de>
Date: Mon, 21 Sep 2020 13:24:45 +0206
Subject: printk: move dictionary keys to dev_printk_info

Dictionaries are only used for SUBSYSTEM and DEVICE properties. The
current implementation stores the property names each time they are
used. This requires more space than otherwise necessary. Also,
because the dictionary entries are currently considered optional,
it cannot be relied upon that they are always available, even if the
writer wanted to store them. These issues will increase should new
dictionary properties be introduced.

Rather than storing the subsystem and device properties in the
dict ring, introduce a struct dev_printk_info with separate fields
to store only the property values. Embed this struct within the
struct printk_info to provide guaranteed availability.

Signed-off-by: John Ogness <john.ogness@linutronix.de>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Signed-off-by: Petr Mladek <pmladek@suse.com>
Link: https://lore.kernel.org/r/87mu1jl6ne.fsf@jogness.linutronix.de
---
 Documentation/admin-guide/kdump/gdbmacros.txt |  73 +++++------
 drivers/base/core.c                           |  46 +++----
 include/linux/dev_printk.h                    |   8 ++
 include/linux/printk.h                        |   6 +-
 kernel/printk/internal.h                      |   4 +-
 kernel/printk/printk.c                        | 166 +++++++++++++-------------
 kernel/printk/printk_ringbuffer.h             |   3 +
 kernel/printk/printk_safe.c                   |   2 +-
 scripts/gdb/linux/dmesg.py                    |  16 ++-
 9 files changed, 164 insertions(+), 160 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/admin-guide/kdump/gdbmacros.txt b/Documentation/admin-guide/kdump/gdbmacros.txt
index 94fabb165abf..82aecdcae8a6 100644
--- a/Documentation/admin-guide/kdump/gdbmacros.txt
+++ b/Documentation/admin-guide/kdump/gdbmacros.txt
@@ -172,13 +172,13 @@ end
 
 define dump_record
 	set var $desc = $arg0
-	if ($argc > 1)
-		set var $prev_flags = $arg1
+	set var $info = $arg1
+	if ($argc > 2)
+		set var $prev_flags = $arg2
 	else
 		set var $prev_flags = 0
 	end
 
-	set var $info = &$desc->info
 	set var $prefix = 1
 	set var $newline = 1
 
@@ -237,44 +237,36 @@ define dump_record
 
 	# handle dictionary data
 
-	set var $begin = $desc->dict_blk_lpos.begin % (1U << prb->dict_data_ring.size_bits)
-	set var $next = $desc->dict_blk_lpos.next % (1U << prb->dict_data_ring.size_bits)
-
-	# handle data-less record
-	if ($begin & 1)
-		set var $dict_len = 0
-		set var $dict = ""
-	else
-		# handle wrapping data block
-		if ($begin > $next)
-			set var $begin = 0
-		end
-
-		# skip over descriptor id
-		set var $begin = $begin + sizeof(long)
-
-		# handle truncated message
-		if ($next - $begin < $info->dict_len)
-			set var $dict_len = $next - $begin
-		else
-			set var $dict_len = $info->dict_len
+	set var $dict = &$info->dev_info.subsystem[0]
+	set var $dict_len = sizeof($info->dev_info.subsystem)
+	if ($dict[0] != '\0')
+		printf " SUBSYSTEM="
+		set var $idx = 0
+		while ($idx < $dict_len)
+			set var $c = $dict[$idx]
+			if ($c == '\0')
+				loop_break
+			else
+				if ($c < ' ' || $c >= 127 || $c == '\\')
+					printf "\\x%02x", $c
+				else
+					printf "%c", $c
+				end
+			end
+			set var $idx = $idx + 1
 		end
-
-		set var $dict = &prb->dict_data_ring.data[$begin]
+		printf "\n"
 	end
 
-	if ($dict_len > 0)
+	set var $dict = &$info->dev_info.device[0]
+	set var $dict_len = sizeof($info->dev_info.device)
+	if ($dict[0] != '\0')
+		printf " DEVICE="
 		set var $idx = 0
-		set var $line = 1
 		while ($idx < $dict_len)
-			if ($line)
-				printf " "
-				set var $line = 0
-			end
 			set var $c = $dict[$idx]
 			if ($c == '\0')
-				printf "\n"
-				set var $line = 1
+				loop_break
 			else
 				if ($c < ' ' || $c >= 127 || $c == '\\')
 					printf "\\x%02x", $c
@@ -288,10 +280,10 @@ define dump_record
 	end
 end
 document dump_record
-	Dump a single record. The first parameter is the descriptor
-	sequence number, the second is optional and specifies the
-	previous record's flags, used for properly formatting
-	continued lines.
+	Dump a single record. The first parameter is the descriptor,
+	the second parameter is the info, the third parameter is
+	optional and specifies the previous record's flags, used for
+	properly formatting continued lines.
 end
 
 define dmesg
@@ -311,12 +303,13 @@ define dmesg
 
 	while (1)
 		set var $desc = &prb->desc_ring.descs[$id % $desc_count]
+		set var $info = &prb->desc_ring.infos[$id % $desc_count]
 
 		# skip non-committed record
 		set var $state = 3 & ($desc->state_var.counter >> $desc_flags_shift)
 		if ($state == $desc_committed || $state == $desc_finalized)
-			dump_record $desc $prev_flags
-			set var $prev_flags = $desc->info.flags
+			dump_record $desc $info $prev_flags
+			set var $prev_flags = $info->flags
 		end
 
 		set var $id = ($id + 1) & $id_mask
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 67d39a90b45c..22d83aedb64e 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -3815,22 +3815,21 @@ void device_shutdown(void)
  */
 
 #ifdef CONFIG_PRINTK
-static int
-create_syslog_header(const struct device *dev, char *hdr, size_t hdrlen)
+static void
+set_dev_info(const struct device *dev, struct dev_printk_info *dev_info)
 {
 	const char *subsys;
-	size_t pos = 0;
+
+	memset(dev_info, 0, sizeof(*dev_info));
 
 	if (dev->class)
 		subsys = dev->class->name;
 	else if (dev->bus)
 		subsys = dev->bus->name;
 	else
-		return 0;
+		return;
 
-	pos += snprintf(hdr + pos, hdrlen - pos, "SUBSYSTEM=%s", subsys);
-	if (pos >= hdrlen)
-		goto overflow;
+	strscpy(dev_info->subsystem, subsys, sizeof(dev_info->subsystem));
 
 	/*
 	 * Add device identifier DEVICE=:
@@ -3846,41 +3845,28 @@ create_syslog_header(const struct device *dev, char *hdr, size_t hdrlen)
 			c = 'b';
 		else
 			c = 'c';
-		pos++;
-		pos += snprintf(hdr + pos, hdrlen - pos,
-				"DEVICE=%c%u:%u",
-				c, MAJOR(dev->devt), MINOR(dev->devt));
+
+		snprintf(dev_info->device, sizeof(dev_info->device),
+			 "%c%u:%u", c, MAJOR(dev->devt), MINOR(dev->devt));
 	} else if (strcmp(subsys, "net") == 0) {
 		struct net_device *net = to_net_dev(dev);
 
-		pos++;
-		pos += snprintf(hdr + pos, hdrlen - pos,
-				"DEVICE=n%u", net->ifindex);
+		snprintf(dev_info->device, sizeof(dev_info->device),
+			 "n%u", net->ifindex);
 	} else {
-		pos++;
-		pos += snprintf(hdr + pos, hdrlen - pos,
-				"DEVICE=+%s:%s", subsys, dev_name(dev));
+		snprintf(dev_info->device, sizeof(dev_info->device),
+			 "+%s:%s", subsys, dev_name(dev));
 	}
-
-	if (pos >= hdrlen)
-		goto overflow;
-
-	return pos;
-
-overflow:
-	dev_WARN(dev, "device/subsystem name too long");
-	return 0;
 }
 
 int dev_vprintk_emit(int level, const struct device *dev,
 		     const char *fmt, va_list args)
 {
-	char hdr[128];
-	size_t hdrlen;
+	struct dev_printk_info dev_info;
 
-	hdrlen = create_syslog_header(dev, hdr, sizeof(hdr));
+	set_dev_info(dev, &dev_info);
 
-	return vprintk_emit(0, level, hdrlen ? hdr : NULL, hdrlen, fmt, args);
+	return vprintk_emit(0, level, &dev_info, fmt, args);
 }
 EXPORT_SYMBOL(dev_vprintk_emit);
 
diff --git a/include/linux/dev_printk.h b/include/linux/dev_printk.h
index 3028b644b4fb..6f009559ee54 100644
--- a/include/linux/dev_printk.h
+++ b/include/linux/dev_printk.h
@@ -21,6 +21,14 @@
 
 struct device;
 
+#define PRINTK_INFO_SUBSYSTEM_LEN	16
+#define PRINTK_INFO_DEVICE_LEN		48
+
+struct dev_printk_info {
+	char subsystem[PRINTK_INFO_SUBSYSTEM_LEN];
+	char device[PRINTK_INFO_DEVICE_LEN];
+};
+
 #ifdef CONFIG_PRINTK
 
 __printf(3, 0) __cold
diff --git a/include/linux/printk.h b/include/linux/printk.h
index fc8f03c54543..071500ee7281 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -158,10 +158,12 @@ static inline void printk_nmi_direct_enter(void) { }
 static inline void printk_nmi_direct_exit(void) { }
 #endif /* PRINTK_NMI */
 
+struct dev_printk_info;
+
 #ifdef CONFIG_PRINTK
-asmlinkage __printf(5, 0)
+asmlinkage __printf(4, 0)
 int vprintk_emit(int facility, int level,
-		 const char *dict, size_t dictlen,
+		 const struct dev_printk_info *dev_info,
 		 const char *fmt, va_list args);
 
 asmlinkage __printf(1, 0)
diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h
index 660f9a6bf73a..3a8fd491758c 100644
--- a/kernel/printk/internal.h
+++ b/kernel/printk/internal.h
@@ -14,9 +14,9 @@
 
 extern raw_spinlock_t logbuf_lock;
 
-__printf(5, 0)
+__printf(4, 0)
 int vprintk_store(int facility, int level,
-		  const char *dict, size_t dictlen,
+		  const struct dev_printk_info *dev_info,
 		  const char *fmt, va_list args);
 
 __printf(1, 0) int vprintk_default(const char *fmt, va_list args);
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 25cfe4fe48af..f1e243cc284a 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -296,8 +296,8 @@ static int console_msg_format = MSG_FORMAT_DEFAULT;
 
 /*
  * The printk log buffer consists of a sequenced collection of records, each
- * containing variable length message and dictionary text. Every record
- * also contains its own meta-data (@info).
+ * containing variable length message text. Every record also contains its
+ * own meta-data (@info).
  *
  * Every record meta-data carries the timestamp in microseconds, as well as
  * the standard userspace syslog level and syslog facility. The usual kernel
@@ -310,9 +310,7 @@ static int console_msg_format = MSG_FORMAT_DEFAULT;
  * terminated.
  *
  * Optionally, a record can carry a dictionary of properties (key/value
- * pairs), to provide userspace with a machine-readable message context. The
- * length of the dictionary is available in @dict_len. The dictionary is not
- * terminated.
+ * pairs), to provide userspace with a machine-readable message context.
  *
  * Examples for well-defined, commonly used property names are:
  *   DEVICE=b12:8               device identifier
@@ -322,21 +320,20 @@ static int console_msg_format = MSG_FORMAT_DEFAULT;
  *                                +sound:card0  subsystem:devname
  *   SUBSYSTEM=pci              driver-core subsystem name
  *
- * Valid characters in property names are [a-zA-Z0-9.-_]. The plain text value
- * follows directly after a '=' character. Every property is terminated by
- * a '\0' character. The last property is not terminated.
+ * Valid characters in property names are [a-zA-Z0-9.-_]. Property names
+ * and values are terminated by a '\0' character.
  *
  * Example of record values:
- *   record.text_buf       = "it's a line" (unterminated)
- *   record.dict_buf       = "DEVICE=b8:2\0DRIVER=bug" (unterminated)
- *   record.info.seq       = 56
- *   record.info.ts_nsec   = 36863
- *   record.info.text_len  = 11
- *   record.info.dict_len  = 22
- *   record.info.facility  = 0 (LOG_KERN)
- *   record.info.flags     = 0
- *   record.info.level     = 3 (LOG_ERR)
- *   record.info.caller_id = 299 (task 299)
+ *   record.text_buf                = "it's a line" (unterminated)
+ *   record.info.seq                = 56
+ *   record.info.ts_nsec            = 36863
+ *   record.info.text_len           = 11
+ *   record.info.facility           = 0 (LOG_KERN)
+ *   record.info.flags              = 0
+ *   record.info.level              = 3 (LOG_ERR)
+ *   record.info.caller_id          = 299 (task 299)
+ *   record.info.dev_info.subsystem = "pci" (terminated)
+ *   record.info.dev_info.device    = "+pci:0000:00:01.0" (terminated)
  *
  * The 'struct printk_info' buffer must never be directly exported to
  * userspace, it is a kernel-private implementation detail that might
@@ -498,19 +495,19 @@ static void truncate_msg(u16 *text_len, u16 *trunc_msg_len)
 /* insert record into the buffer, discard old ones, update heads */
 static int log_store(u32 caller_id, int facility, int level,
 		     enum log_flags flags, u64 ts_nsec,
-		     const char *dict, u16 dict_len,
+		     const struct dev_printk_info *dev_info,
 		     const char *text, u16 text_len)
 {
 	struct prb_reserved_entry e;
 	struct printk_record r;
 	u16 trunc_msg_len = 0;
 
-	prb_rec_init_wr(&r, text_len, dict_len);
+	prb_rec_init_wr(&r, text_len, 0);
 
 	if (!prb_reserve(&e, prb, &r)) {
 		/* truncate the message if it is too long for empty buffer */
 		truncate_msg(&text_len, &trunc_msg_len);
-		prb_rec_init_wr(&r, text_len + trunc_msg_len, dict_len);
+		prb_rec_init_wr(&r, text_len + trunc_msg_len, 0);
 		/* survive when the log buffer is too small for trunc_msg */
 		if (!prb_reserve(&e, prb, &r))
 			return 0;
@@ -521,10 +518,6 @@ static int log_store(u32 caller_id, int facility, int level,
 	if (trunc_msg_len)
 		memcpy(&r.text_buf[text_len], trunc_msg, trunc_msg_len);
 	r.info->text_len = text_len + trunc_msg_len;
-	if (r.dict_buf) {
-		memcpy(&r.dict_buf[0], dict, dict_len);
-		r.info->dict_len = dict_len;
-	}
 	r.info->facility = facility;
 	r.info->level = level & 7;
 	r.info->flags = flags & 0x1f;
@@ -533,6 +526,8 @@ static int log_store(u32 caller_id, int facility, int level,
 	else
 		r.info->ts_nsec = local_clock();
 	r.info->caller_id = caller_id;
+	if (dev_info)
+		memcpy(&r.info->dev_info, dev_info, sizeof(r.info->dev_info));
 
 	/* insert message */
 	if ((flags & LOG_CONT) || !(flags & LOG_NEWLINE))
@@ -613,9 +608,9 @@ static ssize_t info_print_ext_header(char *buf, size_t size,
 			 ts_usec, info->flags & LOG_CONT ? 'c' : '-', caller);
 }
 
-static ssize_t msg_print_ext_body(char *buf, size_t size,
-				  char *dict, size_t dict_len,
-				  char *text, size_t text_len)
+static ssize_t msg_add_ext_text(char *buf, size_t size,
+				const char *text, size_t text_len,
+				unsigned char endc)
 {
 	char *p = buf, *e = buf + size;
 	size_t i;
@@ -629,36 +624,44 @@ static ssize_t msg_print_ext_body(char *buf, size_t size,
 		else
 			append_char(&p, e, c);
 	}
-	append_char(&p, e, '\n');
+	append_char(&p, e, endc);
 
-	if (dict_len) {
-		bool line = true;
+	return p - buf;
+}
 
-		for (i = 0; i < dict_len; i++) {
-			unsigned char c = dict[i];
+static ssize_t msg_add_dict_text(char *buf, size_t size,
+				 const char *key, const char *val)
+{
+	size_t val_len = strlen(val);
+	ssize_t len;
 
-			if (line) {
-				append_char(&p, e, ' ');
-				line = false;
-			}
+	if (!val_len)
+		return 0;
 
-			if (c == '\0') {
-				append_char(&p, e, '\n');
-				line = true;
-				continue;
-			}
+	len = msg_add_ext_text(buf, size, "", 0, ' ');	/* dict prefix */
+	len += msg_add_ext_text(buf + len, size - len, key, strlen(key), '=');
+	len += msg_add_ext_text(buf + len, size - len, val, val_len, '\n');
 
-			if (c < ' ' || c >= 127 || c == '\\') {
-				p += scnprintf(p, e - p, "\\x%02x", c);
-				continue;
-			}
+	return len;
+}
 
-			append_char(&p, e, c);
-		}
-		append_char(&p, e, '\n');
-	}
+static ssize_t msg_print_ext_body(char *buf, size_t size,
+				  char *text, size_t text_len,
+				  struct dev_printk_info *dev_info)
+{
+	ssize_t len;
 
-	return p - buf;
+	len = msg_add_ext_text(buf, size, text, text_len, '\n');
+
+	if (!dev_info)
+		goto out;
+
+	len += msg_add_dict_text(buf + len, size - len, "SUBSYSTEM",
+				 dev_info->subsystem);
+	len += msg_add_dict_text(buf + len, size - len, "DEVICE",
+				 dev_info->device);
+out:
+	return len;
 }
 
 /* /dev/kmsg - userspace message inject/listen interface */
@@ -670,7 +673,6 @@ struct devkmsg_user {
 
 	struct printk_info info;
 	char text_buf[CONSOLE_EXT_LOG_MAX];
-	char dict_buf[CONSOLE_EXT_LOG_MAX];
 	struct printk_record record;
 };
 
@@ -681,7 +683,7 @@ int devkmsg_emit(int facility, int level, const char *fmt, ...)
 	int r;
 
 	va_start(args, fmt);
-	r = vprintk_emit(facility, level, NULL, 0, fmt, args);
+	r = vprintk_emit(facility, level, NULL, fmt, args);
 	va_end(args);
 
 	return r;
@@ -791,8 +793,8 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf,
 
 	len = info_print_ext_header(user->buf, sizeof(user->buf), r->info);
 	len += msg_print_ext_body(user->buf + len, sizeof(user->buf) - len,
-				  &r->dict_buf[0], r->info->dict_len,
-				  &r->text_buf[0], r->info->text_len);
+				  &r->text_buf[0], r->info->text_len,
+				  &r->info->dev_info);
 
 	user->seq = r->info->seq + 1;
 	logbuf_unlock_irq();
@@ -897,7 +899,7 @@ static int devkmsg_open(struct inode *inode, struct file *file)
 
 	prb_rec_init_rd(&user->record, &user->info,
 			&user->text_buf[0], sizeof(user->text_buf),
-			&user->dict_buf[0], sizeof(user->dict_buf));
+			NULL, 0);
 
 	logbuf_lock_irq();
 	user->seq = prb_first_valid_seq(prb);
@@ -941,6 +943,8 @@ const struct file_operations kmsg_fops = {
  */
 void log_buf_vmcoreinfo_setup(void)
 {
+	struct dev_printk_info *dev_info = NULL;
+
 	VMCOREINFO_SYMBOL(prb);
 	VMCOREINFO_SYMBOL(printk_rb_static);
 	VMCOREINFO_SYMBOL(clear_seq);
@@ -978,6 +982,13 @@ void log_buf_vmcoreinfo_setup(void)
 	VMCOREINFO_OFFSET(printk_info, text_len);
 	VMCOREINFO_OFFSET(printk_info, dict_len);
 	VMCOREINFO_OFFSET(printk_info, caller_id);
+	VMCOREINFO_OFFSET(printk_info, dev_info);
+
+	VMCOREINFO_STRUCT_SIZE(dev_printk_info);
+	VMCOREINFO_OFFSET(dev_printk_info, subsystem);
+	VMCOREINFO_LENGTH(printk_info_subsystem, sizeof(dev_info->subsystem));
+	VMCOREINFO_OFFSET(dev_printk_info, device);
+	VMCOREINFO_LENGTH(printk_info_device, sizeof(dev_info->device));
 
 	VMCOREINFO_STRUCT_SIZE(prb_data_ring);
 	VMCOREINFO_OFFSET(prb_data_ring, size_bits);
@@ -1070,22 +1081,19 @@ static unsigned int __init add_to_rb(struct printk_ringbuffer *rb,
 	struct prb_reserved_entry e;
 	struct printk_record dest_r;
 
-	prb_rec_init_wr(&dest_r, r->info->text_len, r->info->dict_len);
+	prb_rec_init_wr(&dest_r, r->info->text_len, 0);
 
 	if (!prb_reserve(&e, rb, &dest_r))
 		return 0;
 
 	memcpy(&dest_r.text_buf[0], &r->text_buf[0], r->info->text_len);
 	dest_r.info->text_len = r->info->text_len;
-	if (dest_r.dict_buf) {
-		memcpy(&dest_r.dict_buf[0], &r->dict_buf[0], r->info->dict_len);
-		dest_r.info->dict_len = r->info->dict_len;
-	}
 	dest_r.info->facility = r->info->facility;
 	dest_r.info->level = r->info->level;
 	dest_r.info->flags = r->info->flags;
 	dest_r.info->ts_nsec = r->info->ts_nsec;
 	dest_r.info->caller_id = r->info->caller_id;
+	memcpy(&dest_r.info->dev_info, &r->info->dev_info, sizeof(dest_r.info->dev_info));
 
 	prb_final_commit(&e);
 
@@ -1093,7 +1101,6 @@ static unsigned int __init add_to_rb(struct printk_ringbuffer *rb,
 }
 
 static char setup_text_buf[CONSOLE_EXT_LOG_MAX] __initdata;
-static char setup_dict_buf[CONSOLE_EXT_LOG_MAX] __initdata;
 
 void __init setup_log_buf(int early)
 {
@@ -1165,7 +1172,7 @@ void __init setup_log_buf(int early)
 
 	prb_rec_init_rd(&r, &info,
 			&setup_text_buf[0], sizeof(setup_text_buf),
-			&setup_dict_buf[0], sizeof(setup_dict_buf));
+			NULL, 0);
 
 	prb_init(&printk_rb_dynamic,
 		 new_log_buf, ilog2(new_log_buf_len),
@@ -1903,7 +1910,9 @@ static inline u32 printk_caller_id(void)
 		0x80000000 + raw_smp_processor_id();
 }
 
-static size_t log_output(int facility, int level, enum log_flags lflags, const char *dict, size_t dictlen, char *text, size_t text_len)
+static size_t log_output(int facility, int level, enum log_flags lflags,
+			 const struct dev_printk_info *dev_info,
+			 char *text, size_t text_len)
 {
 	const u32 caller_id = printk_caller_id();
 
@@ -1927,12 +1936,12 @@ static size_t log_output(int facility, int level, enum log_flags lflags, const c
 
 	/* Store it in the record log */
 	return log_store(caller_id, facility, level, lflags, 0,
-			 dict, dictlen, text, text_len);
+			 dev_info, text, text_len);
 }
 
 /* Must be called under logbuf_lock. */
 int vprintk_store(int facility, int level,
-		  const char *dict, size_t dictlen,
+		  const struct dev_printk_info *dev_info,
 		  const char *fmt, va_list args)
 {
 	static char textbuf[LOG_LINE_MAX];
@@ -1974,15 +1983,14 @@ int vprintk_store(int facility, int level,
 	if (level == LOGLEVEL_DEFAULT)
 		level = default_message_loglevel;
 
-	if (dict)
+	if (dev_info)
 		lflags |= LOG_NEWLINE;
 
-	return log_output(facility, level, lflags,
-			  dict, dictlen, text, text_len);
+	return log_output(facility, level, lflags, dev_info, text, text_len);
 }
 
 asmlinkage int vprintk_emit(int facility, int level,
-			    const char *dict, size_t dictlen,
+			    const struct dev_printk_info *dev_info,
 			    const char *fmt, va_list args)
 {
 	int printed_len;
@@ -2003,7 +2011,7 @@ asmlinkage int vprintk_emit(int facility, int level,
 
 	/* This stops the holder of console_sem just where we want him */
 	logbuf_lock_irqsave(flags);
-	printed_len = vprintk_store(facility, level, dict, dictlen, fmt, args);
+	printed_len = vprintk_store(facility, level, dev_info, fmt, args);
 	logbuf_unlock_irqrestore(flags);
 
 	/* If called from the scheduler, we can not call up(). */
@@ -2037,7 +2045,7 @@ EXPORT_SYMBOL(vprintk);
 
 int vprintk_default(const char *fmt, va_list args)
 {
-	return vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, 0, fmt, args);
+	return vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, fmt, args);
 }
 EXPORT_SYMBOL_GPL(vprintk_default);
 
@@ -2100,8 +2108,8 @@ static ssize_t info_print_ext_header(char *buf, size_t size,
 	return 0;
 }
 static ssize_t msg_print_ext_body(char *buf, size_t size,
-				  char *dict, size_t dict_len,
-				  char *text, size_t text_len) { return 0; }
+				  char *text, size_t text_len,
+				  struct dev_printk_info *dev_info) { return 0; }
 static void console_lock_spinning_enable(void) { }
 static int console_lock_spinning_disable_and_check(void) { return 0; }
 static void call_console_drivers(const char *ext_text, size_t ext_len,
@@ -2390,7 +2398,6 @@ void console_unlock(void)
 {
 	static char ext_text[CONSOLE_EXT_LOG_MAX];
 	static char text[LOG_LINE_MAX + PREFIX_MAX];
-	static char dict[LOG_LINE_MAX];
 	unsigned long flags;
 	bool do_cond_resched, retry;
 	struct printk_info info;
@@ -2401,7 +2408,7 @@ void console_unlock(void)
 		return;
 	}
 
-	prb_rec_init_rd(&r, &info, text, sizeof(text), dict, sizeof(dict));
+	prb_rec_init_rd(&r, &info, text, sizeof(text), NULL, 0);
 
 	/*
 	 * Console drivers are called with interrupts disabled, so
@@ -2473,10 +2480,9 @@ skip:
 						r.info);
 			ext_len += msg_print_ext_body(ext_text + ext_len,
 						sizeof(ext_text) - ext_len,
-						&r.dict_buf[0],
-						r.info->dict_len,
 						&r.text_buf[0],
-						r.info->text_len);
+						r.info->text_len,
+						&r.info->dev_info);
 		}
 		len = record_print_text(&r,
 				console_msg_format & MSG_FORMAT_SYSLOG,
@@ -3055,7 +3061,7 @@ int vprintk_deferred(const char *fmt, va_list args)
 {
 	int r;
 
-	r = vprintk_emit(0, LOGLEVEL_SCHED, NULL, 0, fmt, args);
+	r = vprintk_emit(0, LOGLEVEL_SCHED, NULL, fmt, args);
 	defer_console_output();
 
 	return r;
diff --git a/kernel/printk/printk_ringbuffer.h b/kernel/printk/printk_ringbuffer.h
index 97c8561e74e0..480499ce3c6b 100644
--- a/kernel/printk/printk_ringbuffer.h
+++ b/kernel/printk/printk_ringbuffer.h
@@ -4,6 +4,7 @@
 #define _KERNEL_PRINTK_RINGBUFFER_H
 
 #include <linux/atomic.h>
+#include <linux/dev_printk.h>
 
 /*
  * Meta information about each stored message.
@@ -21,6 +22,8 @@ struct printk_info {
 	u8	flags:5;	/* internal record flags */
 	u8	level:3;	/* syslog level */
 	u32	caller_id;	/* thread id or processor id */
+
+	struct dev_printk_info	dev_info;
 };
 
 /*
diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c
index 50aeae770434..5dbc40160990 100644
--- a/kernel/printk/printk_safe.c
+++ b/kernel/printk/printk_safe.c
@@ -375,7 +375,7 @@ __printf(1, 0) int vprintk_func(const char *fmt, va_list args)
 	    raw_spin_trylock(&logbuf_lock)) {
 		int len;
 
-		len = vprintk_store(0, LOGLEVEL_DEFAULT, NULL, 0, fmt, args);
+		len = vprintk_store(0, LOGLEVEL_DEFAULT, NULL, fmt, args);
 		raw_spin_unlock(&logbuf_lock);
 		defer_console_output();
 		return len;
diff --git a/scripts/gdb/linux/dmesg.py b/scripts/gdb/linux/dmesg.py
index bce14de5f610..a92c55bd8de5 100644
--- a/scripts/gdb/linux/dmesg.py
+++ b/scripts/gdb/linux/dmesg.py
@@ -52,6 +52,12 @@ class LxDmesg(gdb.Command):
         addr = utils.read_ulong(desc_ring, off)
         descs = utils.read_memoryview(inf, addr, desc_sz * desc_ring_count).tobytes()
 
+        # read in info array
+        info_sz = printk_info_type.get_type().sizeof
+        off = prb_desc_ring_type.get_type()['infos'].bitpos // 8
+        addr = utils.read_ulong(desc_ring, off)
+        infos = utils.read_memoryview(inf, addr, info_sz * desc_ring_count).tobytes()
+
         # read in text data ring structure
         off = printk_ringbuffer_type.get_type()['text_data_ring'].bitpos // 8
         addr = prb_addr + off
@@ -73,9 +79,8 @@ class LxDmesg(gdb.Command):
         begin_off = off + (prb_data_blk_lpos_type.get_type()['begin'].bitpos // 8)
         next_off = off + (prb_data_blk_lpos_type.get_type()['next'].bitpos // 8)
 
-        off = prb_desc_type.get_type()['info'].bitpos // 8
-        ts_off = off + printk_info_type.get_type()['ts_nsec'].bitpos // 8
-        len_off = off + printk_info_type.get_type()['text_len'].bitpos // 8
+        ts_off = printk_info_type.get_type()['ts_nsec'].bitpos // 8
+        len_off = printk_info_type.get_type()['text_len'].bitpos // 8
 
         # definitions from kernel/printk/printk_ringbuffer.h
         desc_committed = 1
@@ -95,6 +100,7 @@ class LxDmesg(gdb.Command):
         while True:
             ind = did % desc_ring_count
             desc_off = desc_sz * ind
+            info_off = info_sz * ind
 
             # skip non-committed record
             state = 3 & (utils.read_u64(descs, desc_off + sv_off +
@@ -119,7 +125,7 @@ class LxDmesg(gdb.Command):
                 # skip over descriptor id
                 text_start = begin + utils.get_long_type().sizeof
 
-                text_len = utils.read_u16(descs, desc_off + len_off)
+                text_len = utils.read_u16(infos, info_off + len_off)
 
                 # handle truncated message
                 if end - text_start < text_len:
@@ -128,7 +134,7 @@ class LxDmesg(gdb.Command):
                 text = text_data[text_start:text_start + text_len].decode(
                     encoding='utf8', errors='replace')
 
-            time_stamp = utils.read_u64(descs, desc_off + ts_off)
+            time_stamp = utils.read_u64(infos, info_off + ts_off)
 
             for line in text.splitlines():
                 msg = u"[{time:12.6f}] {line}\n".format(
-- 
cgit v1.2.3


From 15b760c37ad3c3f2b922506eaca4ca8b4292e621 Mon Sep 17 00:00:00 2001
From: Andra Paraschiv <andraprs@amazon.com>
Date: Mon, 21 Sep 2020 15:17:15 +0300
Subject: nitro_enclaves: Add ioctl interface definition

The Nitro Enclaves driver handles the enclave lifetime management. This
includes enclave creation, termination and setting up its resources such
as memory and CPU.

An enclave runs alongside the VM that spawned it. It is abstracted as a
process running in the VM that launched it. The process interacts with
the NE driver, that exposes an ioctl interface for creating an enclave
and setting up its resources.

Changelog

v9 -> v10

* Update commit message to include the changelog before the SoB tag(s).

v8 -> v9

* No changes.

v7 -> v8

* Add NE custom error codes for user space memory regions not backed by
  pages multiple of 2 MiB, invalid flags and enclave CID.
* Add max flag value for enclave image load info.

v6 -> v7

* Clarify in the ioctls documentation that the return value is -1 and
  errno is set on failure.
* Update the error code value for NE_ERR_INVALID_MEM_REGION_SIZE as it
  gets in user space as value 25 (ENOTTY) instead of 515. Update the
  NE custom error codes values range to not be the same as the ones
  defined in include/linux/errno.h, although these are not propagated
  to user space.

v5 -> v6

* Fix typo in the description about the NE CPU pool.
* Update documentation to kernel-doc format.
* Remove the ioctl to query API version.

v4 -> v5

* Add more details about the ioctl calls usage e.g. error codes, file
  descriptors used.
* Update the ioctl to set an enclave vCPU to not return a file
  descriptor.
* Add specific NE error codes.

v3 -> v4

* Decouple NE ioctl interface from KVM API.
* Add NE API version and the corresponding ioctl call.
* Add enclave / image load flags options.

v2 -> v3

* Remove the GPL additional wording as SPDX-License-Identifier is
  already in place.

v1 -> v2

* Add ioctl for getting enclave image load metadata.
* Update NE_ENCLAVE_START ioctl name to NE_START_ENCLAVE.
* Add entry in Documentation/userspace-api/ioctl/ioctl-number.rst for NE
  ioctls.
* Update NE ioctls definition based on the updated ioctl range for major
  and minor.

Reviewed-by: Alexander Graf <graf@amazon.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Alexandru Vasile <lexnv@amazon.com>
Signed-off-by: Andra Paraschiv <andraprs@amazon.com>
Link: https://lore.kernel.org/r/20200921121732.44291-2-andraprs@amazon.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/userspace-api/ioctl/ioctl-number.rst |   5 +-
 include/linux/nitro_enclaves.h                     |  11 +
 include/uapi/linux/nitro_enclaves.h                | 359 +++++++++++++++++++++
 3 files changed, 374 insertions(+), 1 deletion(-)
 create mode 100644 include/linux/nitro_enclaves.h
 create mode 100644 include/uapi/linux/nitro_enclaves.h

(limited to 'include/linux')

diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst
index 2a198838fca9..5f7ff00f394e 100644
--- a/Documentation/userspace-api/ioctl/ioctl-number.rst
+++ b/Documentation/userspace-api/ioctl/ioctl-number.rst
@@ -328,8 +328,11 @@ Code  Seq#    Include File                                           Comments
 0xAC  00-1F  linux/raw.h
 0xAD  00                                                             Netfilter device in development:
                                                                      <mailto:rusty@rustcorp.com.au>
-0xAE  all    linux/kvm.h                                             Kernel-based Virtual Machine
+0xAE  00-1F  linux/kvm.h                                             Kernel-based Virtual Machine
                                                                      <mailto:kvm@vger.kernel.org>
+0xAE  40-FF  linux/kvm.h                                             Kernel-based Virtual Machine
+                                                                     <mailto:kvm@vger.kernel.org>
+0xAE  20-3F  linux/nitro_enclaves.h                                  Nitro Enclaves
 0xAF  00-1F  linux/fsl_hypervisor.h                                  Freescale hypervisor
 0xB0  all                                                            RATIO devices in development:
                                                                      <mailto:vgo@ratio.de>
diff --git a/include/linux/nitro_enclaves.h b/include/linux/nitro_enclaves.h
new file mode 100644
index 000000000000..d91ef2bfdf47
--- /dev/null
+++ b/include/linux/nitro_enclaves.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright 2020 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+ */
+
+#ifndef _LINUX_NITRO_ENCLAVES_H_
+#define _LINUX_NITRO_ENCLAVES_H_
+
+#include <uapi/linux/nitro_enclaves.h>
+
+#endif /* _LINUX_NITRO_ENCLAVES_H_ */
diff --git a/include/uapi/linux/nitro_enclaves.h b/include/uapi/linux/nitro_enclaves.h
new file mode 100644
index 000000000000..b945073fe544
--- /dev/null
+++ b/include/uapi/linux/nitro_enclaves.h
@@ -0,0 +1,359 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright 2020 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+ */
+
+#ifndef _UAPI_LINUX_NITRO_ENCLAVES_H_
+#define _UAPI_LINUX_NITRO_ENCLAVES_H_
+
+#include <linux/types.h>
+
+/**
+ * DOC: Nitro Enclaves (NE) Kernel Driver Interface
+ */
+
+/**
+ * NE_CREATE_VM - The command is used to create a slot that is associated with
+ *		  an enclave VM.
+ *		  The generated unique slot id is an output parameter.
+ *		  The ioctl can be invoked on the /dev/nitro_enclaves fd, before
+ *		  setting any resources, such as memory and vCPUs, for an
+ *		  enclave. Memory and vCPUs are set for the slot mapped to an enclave.
+ *		  A NE CPU pool has to be set before calling this function. The
+ *		  pool can be set after the NE driver load, using
+ *		  /sys/module/nitro_enclaves/parameters/ne_cpus.
+ *		  Its format is the detailed in the cpu-lists section:
+ *		  https://www.kernel.org/doc/html/latest/admin-guide/kernel-parameters.html
+ *		  CPU 0 and its siblings have to remain available for the
+ *		  primary / parent VM, so they cannot be set for enclaves. Full
+ *		  CPU core(s), from the same NUMA node, need(s) to be included
+ *		  in the CPU pool.
+ *
+ * Context: Process context.
+ * Return:
+ * * Enclave file descriptor		- Enclave file descriptor used with
+ *					  ioctl calls to set vCPUs and memory
+ *					  regions, then start the enclave.
+ * *  -1				- There was a failure in the ioctl logic.
+ * On failure, errno is set to:
+ * * EFAULT				- copy_to_user() failure.
+ * * ENOMEM				- Memory allocation failure for internal
+ *					  bookkeeping variables.
+ * * NE_ERR_NO_CPUS_AVAIL_IN_POOL	- No NE CPU pool set / no CPUs available
+ *					  in the pool.
+ * * Error codes from get_unused_fd_flags() and anon_inode_getfile().
+ * * Error codes from the NE PCI device request.
+ */
+#define NE_CREATE_VM			_IOR(0xAE, 0x20, __u64)
+
+/**
+ * NE_ADD_VCPU - The command is used to set a vCPU for an enclave. The vCPU can
+ *		 be auto-chosen from the NE CPU pool or it can be set by the
+ *		 caller, with the note that it needs to be available in the NE
+ *		 CPU pool. Full CPU core(s), from the same NUMA node, need(s) to
+ *		 be associated with an enclave.
+ *		 The vCPU id is an input / output parameter. If its value is 0,
+ *		 then a CPU is chosen from the enclave CPU pool and returned via
+ *		 this parameter.
+ *		 The ioctl can be invoked on the enclave fd, before an enclave
+ *		 is started.
+ *
+ * Context: Process context.
+ * Return:
+ * * 0					- Logic succesfully completed.
+ * *  -1				- There was a failure in the ioctl logic.
+ * On failure, errno is set to:
+ * * EFAULT				- copy_from_user() / copy_to_user() failure.
+ * * ENOMEM				- Memory allocation failure for internal
+ *					  bookkeeping variables.
+ * * EIO				- Current task mm is not the same as the one
+ *					  that created the enclave.
+ * * NE_ERR_NO_CPUS_AVAIL_IN_POOL	- No CPUs available in the NE CPU pool.
+ * * NE_ERR_VCPU_ALREADY_USED		- The provided vCPU is already used.
+ * * NE_ERR_VCPU_NOT_IN_CPU_POOL	- The provided vCPU is not available in the
+ *					  NE CPU pool.
+ * * NE_ERR_VCPU_INVALID_CPU_CORE	- The core id of the provided vCPU is invalid
+ *					  or out of range.
+ * * NE_ERR_NOT_IN_INIT_STATE		- The enclave is not in init state
+ *					  (init = before being started).
+ * * NE_ERR_INVALID_VCPU		- The provided vCPU is not in the available
+ *					  CPUs range.
+ * * Error codes from the NE PCI device request.
+ */
+#define NE_ADD_VCPU			_IOWR(0xAE, 0x21, __u32)
+
+/**
+ * NE_GET_IMAGE_LOAD_INFO - The command is used to get information needed for
+ *			    in-memory enclave image loading e.g. offset in
+ *			    enclave memory to start placing the enclave image.
+ *			    The image load info is an input / output parameter.
+ *			    It includes info provided by the caller - flags -
+ *			    and returns the offset in enclave memory where to
+ *			    start placing the enclave image.
+ *			    The ioctl can be invoked on the enclave fd, before
+ *			    an enclave is started.
+ *
+ * Context: Process context.
+ * Return:
+ * * 0				- Logic succesfully completed.
+ * *  -1			- There was a failure in the ioctl logic.
+ * On failure, errno is set to:
+ * * EFAULT			- copy_from_user() / copy_to_user() failure.
+ * * NE_ERR_NOT_IN_INIT_STATE	- The enclave is not in init state (init =
+ *				  before being started).
+ * * NE_ERR_INVALID_FLAG_VALUE	- The value of the provided flag is invalid.
+ */
+#define NE_GET_IMAGE_LOAD_INFO		_IOWR(0xAE, 0x22, struct ne_image_load_info)
+
+/**
+ * NE_SET_USER_MEMORY_REGION - The command is used to set a memory region for an
+ *			       enclave, given the allocated memory from the
+ *			       userspace. Enclave memory needs to be from the
+ *			       same NUMA node as the enclave CPUs.
+ *			       The user memory region is an input parameter. It
+ *			       includes info provided by the caller - flags,
+ *			       memory size and userspace address.
+ *			       The ioctl can be invoked on the enclave fd,
+ *			       before an enclave is started.
+ *
+ * Context: Process context.
+ * Return:
+ * * 0					- Logic succesfully completed.
+ * *  -1				- There was a failure in the ioctl logic.
+ * On failure, errno is set to:
+ * * EFAULT				- copy_from_user() failure.
+ * * EINVAL				- Invalid physical memory region(s) e.g.
+ *					  unaligned address.
+ * * EIO				- Current task mm is not the same as
+ *					  the one that created the enclave.
+ * * ENOMEM				- Memory allocation failure for internal
+ *					  bookkeeping variables.
+ * * NE_ERR_NOT_IN_INIT_STATE		- The enclave is not in init state
+ *					  (init = before being started).
+ * * NE_ERR_INVALID_MEM_REGION_SIZE	- The memory size of the region is not
+ *					  multiple of 2 MiB.
+ * * NE_ERR_INVALID_MEM_REGION_ADDR	- Invalid user space address given.
+ * * NE_ERR_UNALIGNED_MEM_REGION_ADDR	- Unaligned user space address given.
+ * * NE_ERR_MEM_REGION_ALREADY_USED	- The memory region is already used.
+ * * NE_ERR_MEM_NOT_HUGE_PAGE		- The memory region is not backed by
+ *					  huge pages.
+ * * NE_ERR_MEM_DIFFERENT_NUMA_NODE	- The memory region is not from the same
+ *					  NUMA node as the CPUs.
+ * * NE_ERR_MEM_MAX_REGIONS		- The number of memory regions set for
+ *					  the enclave reached maximum.
+ * * NE_ERR_INVALID_PAGE_SIZE		- The memory region is not backed by
+ *					  pages multiple of 2 MiB.
+ * * NE_ERR_INVALID_FLAG_VALUE		- The value of the provided flag is invalid.
+ * * Error codes from get_user_pages().
+ * * Error codes from the NE PCI device request.
+ */
+#define NE_SET_USER_MEMORY_REGION	_IOW(0xAE, 0x23, struct ne_user_memory_region)
+
+/**
+ * NE_START_ENCLAVE - The command is used to trigger enclave start after the
+ *		      enclave resources, such as memory and CPU, have been set.
+ *		      The enclave start info is an input / output parameter. It
+ *		      includes info provided by the caller - enclave cid and
+ *		      flags - and returns the cid (if input cid is 0).
+ *		      The ioctl can be invoked on the enclave fd, after an
+ *		      enclave slot is created and resources, such as memory and
+ *		      vCPUs are set for an enclave.
+ *
+ * Context: Process context.
+ * Return:
+ * * 0					- Logic succesfully completed.
+ * *  -1				- There was a failure in the ioctl logic.
+ * On failure, errno is set to:
+ * * EFAULT				- copy_from_user() / copy_to_user() failure.
+ * * NE_ERR_NOT_IN_INIT_STATE		- The enclave is not in init state
+ *					  (init = before being started).
+ * * NE_ERR_NO_MEM_REGIONS_ADDED	- No memory regions are set.
+ * * NE_ERR_NO_VCPUS_ADDED		- No vCPUs are set.
+ * *  NE_ERR_FULL_CORES_NOT_USED	- Full core(s) not set for the enclave.
+ * * NE_ERR_ENCLAVE_MEM_MIN_SIZE	- Enclave memory is less than minimum
+ *					  memory size (64 MiB).
+ * * NE_ERR_INVALID_FLAG_VALUE		- The value of the provided flag is invalid.
+ * *  NE_ERR_INVALID_ENCLAVE_CID	- The provided enclave CID is invalid.
+ * * Error codes from the NE PCI device request.
+ */
+#define NE_START_ENCLAVE		_IOWR(0xAE, 0x24, struct ne_enclave_start_info)
+
+/**
+ * DOC: NE specific error codes
+ */
+
+/**
+ * NE_ERR_VCPU_ALREADY_USED - The provided vCPU is already used.
+ */
+#define NE_ERR_VCPU_ALREADY_USED		(256)
+/**
+ * NE_ERR_VCPU_NOT_IN_CPU_POOL - The provided vCPU is not available in the
+ *				 NE CPU pool.
+ */
+#define NE_ERR_VCPU_NOT_IN_CPU_POOL		(257)
+/**
+ * NE_ERR_VCPU_INVALID_CPU_CORE - The core id of the provided vCPU is invalid
+ *				  or out of range of the NE CPU pool.
+ */
+#define NE_ERR_VCPU_INVALID_CPU_CORE		(258)
+/**
+ * NE_ERR_INVALID_MEM_REGION_SIZE - The user space memory region size is not
+ *				    multiple of 2 MiB.
+ */
+#define NE_ERR_INVALID_MEM_REGION_SIZE		(259)
+/**
+ * NE_ERR_INVALID_MEM_REGION_ADDR - The user space memory region address range
+ *				    is invalid.
+ */
+#define NE_ERR_INVALID_MEM_REGION_ADDR		(260)
+/**
+ * NE_ERR_UNALIGNED_MEM_REGION_ADDR - The user space memory region address is
+ *				      not aligned.
+ */
+#define NE_ERR_UNALIGNED_MEM_REGION_ADDR	(261)
+/**
+ * NE_ERR_MEM_REGION_ALREADY_USED - The user space memory region is already used.
+ */
+#define NE_ERR_MEM_REGION_ALREADY_USED		(262)
+/**
+ * NE_ERR_MEM_NOT_HUGE_PAGE - The user space memory region is not backed by
+ *			      contiguous physical huge page(s).
+ */
+#define NE_ERR_MEM_NOT_HUGE_PAGE		(263)
+/**
+ * NE_ERR_MEM_DIFFERENT_NUMA_NODE - The user space memory region is backed by
+ *				    pages from different NUMA nodes than the CPUs.
+ */
+#define NE_ERR_MEM_DIFFERENT_NUMA_NODE		(264)
+/**
+ * NE_ERR_MEM_MAX_REGIONS - The supported max memory regions per enclaves has
+ *			    been reached.
+ */
+#define NE_ERR_MEM_MAX_REGIONS			(265)
+/**
+ * NE_ERR_NO_MEM_REGIONS_ADDED - The command to start an enclave is triggered
+ *				 and no memory regions are added.
+ */
+#define NE_ERR_NO_MEM_REGIONS_ADDED		(266)
+/**
+ * NE_ERR_NO_VCPUS_ADDED - The command to start an enclave is triggered and no
+ *			   vCPUs are added.
+ */
+#define NE_ERR_NO_VCPUS_ADDED			(267)
+/**
+ * NE_ERR_ENCLAVE_MEM_MIN_SIZE - The enclave memory size is lower than the
+ *				 minimum supported.
+ */
+#define NE_ERR_ENCLAVE_MEM_MIN_SIZE		(268)
+/**
+ * NE_ERR_FULL_CORES_NOT_USED - The command to start an enclave is triggered and
+ *				full CPU cores are not set.
+ */
+#define NE_ERR_FULL_CORES_NOT_USED		(269)
+/**
+ * NE_ERR_NOT_IN_INIT_STATE - The enclave is not in init state when setting
+ *			      resources or triggering start.
+ */
+#define NE_ERR_NOT_IN_INIT_STATE		(270)
+/**
+ * NE_ERR_INVALID_VCPU - The provided vCPU is out of range of the available CPUs.
+ */
+#define NE_ERR_INVALID_VCPU			(271)
+/**
+ * NE_ERR_NO_CPUS_AVAIL_IN_POOL - The command to create an enclave is triggered
+ *				  and no CPUs are available in the pool.
+ */
+#define NE_ERR_NO_CPUS_AVAIL_IN_POOL		(272)
+/**
+ * NE_ERR_INVALID_PAGE_SIZE - The user space memory region is not backed by pages
+ *			      multiple of 2 MiB.
+ */
+#define NE_ERR_INVALID_PAGE_SIZE		(273)
+/**
+ * NE_ERR_INVALID_FLAG_VALUE - The provided flag value is invalid.
+ */
+#define NE_ERR_INVALID_FLAG_VALUE		(274)
+/**
+ * NE_ERR_INVALID_ENCLAVE_CID - The provided enclave CID is invalid, either
+ *				being a well-known value or the CID of the
+ *				parent / primary VM.
+ */
+#define NE_ERR_INVALID_ENCLAVE_CID		(275)
+
+/**
+ * DOC: Image load info flags
+ */
+
+/**
+ * NE_EIF_IMAGE - Enclave Image Format (EIF)
+ */
+#define NE_EIF_IMAGE			(0x01)
+
+#define NE_IMAGE_LOAD_MAX_FLAG_VAL	(0x02)
+
+/**
+ * struct ne_image_load_info - Info necessary for in-memory enclave image
+ *			       loading (in / out).
+ * @flags:		Flags to determine the enclave image type
+ *			(e.g. Enclave Image Format - EIF) (in).
+ * @memory_offset:	Offset in enclave memory where to start placing the
+ *			enclave image (out).
+ */
+struct ne_image_load_info {
+	__u64	flags;
+	__u64	memory_offset;
+};
+
+/**
+ * DOC: User memory region flags
+ */
+
+/**
+ * NE_DEFAULT_MEMORY_REGION - Memory region for enclave general usage.
+ */
+#define NE_DEFAULT_MEMORY_REGION	(0x00)
+
+#define NE_MEMORY_REGION_MAX_FLAG_VAL	(0x01)
+
+/**
+ * struct ne_user_memory_region - Memory region to be set for an enclave (in).
+ * @flags:		Flags to determine the usage for the memory region (in).
+ * @memory_size:	The size, in bytes, of the memory region to be set for
+ *			an enclave (in).
+ * @userspace_addr:	The start address of the userspace allocated memory of
+ *			the memory region to set for an enclave (in).
+ */
+struct ne_user_memory_region {
+	__u64	flags;
+	__u64	memory_size;
+	__u64	userspace_addr;
+};
+
+/**
+ * DOC: Enclave start info flags
+ */
+
+/**
+ * NE_ENCLAVE_PRODUCTION_MODE - Start enclave in production mode.
+ */
+#define NE_ENCLAVE_PRODUCTION_MODE	(0x00)
+/**
+ * NE_ENCLAVE_DEBUG_MODE - Start enclave in debug mode.
+ */
+#define NE_ENCLAVE_DEBUG_MODE		(0x01)
+
+#define NE_ENCLAVE_START_MAX_FLAG_VAL	(0x02)
+
+/**
+ * struct ne_enclave_start_info - Setup info necessary for enclave start (in / out).
+ * @flags:		Flags for the enclave to start with (e.g. debug mode) (in).
+ * @enclave_cid:	Context ID (CID) for the enclave vsock device. If 0 as
+ *			input, the CID is autogenerated by the hypervisor and
+ *			returned back as output by the driver (in / out).
+ */
+struct ne_enclave_start_info {
+	__u64	flags;
+	__u64	enclave_cid;
+};
+
+#endif /* _UAPI_LINUX_NITRO_ENCLAVES_H_ */
-- 
cgit v1.2.3


From a992b20cd4ee360dbbe6f69339cb07146e4304d6 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Wed, 16 Sep 2020 21:11:24 -0700
Subject: fscrypt: add fscrypt_prepare_new_inode() and fscrypt_set_context()

fscrypt_get_encryption_info() is intended to be GFP_NOFS-safe.  But
actually it isn't, since it uses functions like crypto_alloc_skcipher()
which aren't GFP_NOFS-safe, even when called under memalloc_nofs_save().
Therefore it can deadlock when called from a context that needs
GFP_NOFS, e.g. during an ext4 transaction or between f2fs_lock_op() and
f2fs_unlock_op().  This happens when creating a new encrypted file.

We can't fix this by just not setting up the key for new inodes right
away, since new symlinks need their key to encrypt the symlink target.

So we need to set up the new inode's key before starting the
transaction.  But just calling fscrypt_get_encryption_info() earlier
doesn't work, since it assumes the encryption context is already set,
and the encryption context can't be set until the transaction.

The recently proposed fscrypt support for the ceph filesystem
(https://lkml.kernel.org/linux-fscrypt/20200821182813.52570-1-jlayton@kernel.org/T/#u)
will have this same ordering problem too, since ceph will need to
encrypt new symlinks before setting their encryption context.

Finally, f2fs can deadlock when the filesystem is mounted with
'-o test_dummy_encryption' and a new file is created in an existing
unencrypted directory.  Similarly, this is caused by holding too many
locks when calling fscrypt_get_encryption_info().

To solve all these problems, add new helper functions:

- fscrypt_prepare_new_inode() sets up a new inode's encryption key
  (fscrypt_info), using the parent directory's encryption policy and a
  new random nonce.  It neither reads nor writes the encryption context.

- fscrypt_set_context() persists the encryption context of a new inode,
  using the information from the fscrypt_info already in memory.  This
  replaces fscrypt_inherit_context().

Temporarily keep fscrypt_inherit_context() around until all filesystems
have been converted to use fscrypt_set_context().

Acked-by: Jeff Layton <jlayton@kernel.org>
Link: https://lore.kernel.org/r/20200917041136.178600-2-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 fs/crypto/fscrypt_private.h |   3 +
 fs/crypto/keysetup.c        | 195 ++++++++++++++++++++++++++++++++++----------
 fs/crypto/policy.c          |  62 ++++++++++++--
 include/linux/fscrypt.h     |  17 ++++
 4 files changed, 223 insertions(+), 54 deletions(-)

(limited to 'include/linux')

diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h
index 8117a61b6f55..355f6d937751 100644
--- a/fs/crypto/fscrypt_private.h
+++ b/fs/crypto/fscrypt_private.h
@@ -572,6 +572,9 @@ int fscrypt_set_per_file_enc_key(struct fscrypt_info *ci, const u8 *raw_key);
 int fscrypt_derive_dirhash_key(struct fscrypt_info *ci,
 			       const struct fscrypt_master_key *mk);
 
+void fscrypt_hash_inode_number(struct fscrypt_info *ci,
+			       const struct fscrypt_master_key *mk);
+
 /* keysetup_v1.c */
 
 void fscrypt_put_direct_key(struct fscrypt_direct_key *dk);
diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c
index fea6226afc2b..615916897214 100644
--- a/fs/crypto/keysetup.c
+++ b/fs/crypto/keysetup.c
@@ -10,6 +10,7 @@
 
 #include <crypto/skcipher.h>
 #include <linux/key.h>
+#include <linux/random.h>
 
 #include "fscrypt_private.h"
 
@@ -222,6 +223,16 @@ int fscrypt_derive_dirhash_key(struct fscrypt_info *ci,
 	return 0;
 }
 
+void fscrypt_hash_inode_number(struct fscrypt_info *ci,
+			       const struct fscrypt_master_key *mk)
+{
+	WARN_ON(ci->ci_inode->i_ino == 0);
+	WARN_ON(!mk->mk_ino_hash_key_initialized);
+
+	ci->ci_hashed_ino = (u32)siphash_1u64(ci->ci_inode->i_ino,
+					      &mk->mk_ino_hash_key);
+}
+
 static int fscrypt_setup_iv_ino_lblk_32_key(struct fscrypt_info *ci,
 					    struct fscrypt_master_key *mk)
 {
@@ -254,13 +265,20 @@ unlock:
 			return err;
 	}
 
-	ci->ci_hashed_ino = (u32)siphash_1u64(ci->ci_inode->i_ino,
-					      &mk->mk_ino_hash_key);
+	/*
+	 * New inodes may not have an inode number assigned yet.
+	 * Hashing their inode number is delayed until later.
+	 */
+	if (ci->ci_inode->i_ino == 0)
+		WARN_ON(!(ci->ci_inode->i_state & I_CREATING));
+	else
+		fscrypt_hash_inode_number(ci, mk);
 	return 0;
 }
 
 static int fscrypt_setup_v2_file_key(struct fscrypt_info *ci,
-				     struct fscrypt_master_key *mk)
+				     struct fscrypt_master_key *mk,
+				     bool need_dirhash_key)
 {
 	int err;
 
@@ -306,7 +324,7 @@ static int fscrypt_setup_v2_file_key(struct fscrypt_info *ci,
 		return err;
 
 	/* Derive a secret dirhash key for directories that need it. */
-	if (S_ISDIR(ci->ci_inode->i_mode) && IS_CASEFOLDED(ci->ci_inode)) {
+	if (need_dirhash_key) {
 		err = fscrypt_derive_dirhash_key(ci, mk);
 		if (err)
 			return err;
@@ -326,6 +344,7 @@ static int fscrypt_setup_v2_file_key(struct fscrypt_info *ci,
  * key being removed with a new inode starting to use it.
  */
 static int setup_file_encryption_key(struct fscrypt_info *ci,
+				     bool need_dirhash_key,
 				     struct key **master_key_ret)
 {
 	struct key *key;
@@ -400,7 +419,7 @@ static int setup_file_encryption_key(struct fscrypt_info *ci,
 		err = fscrypt_setup_v1_file_key(ci, mk->mk_secret.raw);
 		break;
 	case FSCRYPT_POLICY_V2:
-		err = fscrypt_setup_v2_file_key(ci, mk);
+		err = fscrypt_setup_v2_file_key(ci, mk, need_dirhash_key);
 		break;
 	default:
 		WARN_ON(1);
@@ -454,57 +473,28 @@ static void put_crypt_info(struct fscrypt_info *ci)
 	kmem_cache_free(fscrypt_info_cachep, ci);
 }
 
-int fscrypt_get_encryption_info(struct inode *inode)
+static int
+fscrypt_setup_encryption_info(struct inode *inode,
+			      const union fscrypt_policy *policy,
+			      const u8 nonce[FSCRYPT_FILE_NONCE_SIZE],
+			      bool need_dirhash_key)
 {
 	struct fscrypt_info *crypt_info;
-	union fscrypt_context ctx;
 	struct fscrypt_mode *mode;
 	struct key *master_key = NULL;
 	int res;
 
-	if (fscrypt_has_encryption_key(inode))
-		return 0;
-
 	res = fscrypt_initialize(inode->i_sb->s_cop->flags);
 	if (res)
 		return res;
 
-	res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
-	if (res < 0) {
-		const union fscrypt_context *dummy_ctx =
-			fscrypt_get_dummy_context(inode->i_sb);
-
-		if (IS_ENCRYPTED(inode) || !dummy_ctx) {
-			fscrypt_warn(inode,
-				     "Error %d getting encryption context",
-				     res);
-			return res;
-		}
-		/* Fake up a context for an unencrypted directory */
-		res = fscrypt_context_size(dummy_ctx);
-		memcpy(&ctx, dummy_ctx, res);
-	}
-
 	crypt_info = kmem_cache_zalloc(fscrypt_info_cachep, GFP_NOFS);
 	if (!crypt_info)
 		return -ENOMEM;
 
 	crypt_info->ci_inode = inode;
-
-	res = fscrypt_policy_from_context(&crypt_info->ci_policy, &ctx, res);
-	if (res) {
-		fscrypt_warn(inode,
-			     "Unrecognized or corrupt encryption context");
-		goto out;
-	}
-
-	memcpy(crypt_info->ci_nonce, fscrypt_context_nonce(&ctx),
-	       FSCRYPT_FILE_NONCE_SIZE);
-
-	if (!fscrypt_supported_policy(&crypt_info->ci_policy, inode)) {
-		res = -EINVAL;
-		goto out;
-	}
+	crypt_info->ci_policy = *policy;
+	memcpy(crypt_info->ci_nonce, nonce, FSCRYPT_FILE_NONCE_SIZE);
 
 	mode = select_encryption_mode(&crypt_info->ci_policy, inode);
 	if (IS_ERR(mode)) {
@@ -514,13 +504,14 @@ int fscrypt_get_encryption_info(struct inode *inode)
 	WARN_ON(mode->ivsize > FSCRYPT_MAX_IV_SIZE);
 	crypt_info->ci_mode = mode;
 
-	res = setup_file_encryption_key(crypt_info, &master_key);
+	res = setup_file_encryption_key(crypt_info, need_dirhash_key,
+					&master_key);
 	if (res)
 		goto out;
 
 	/*
-	 * Multiple tasks may race to set ->i_crypt_info, so use
-	 * cmpxchg_release().  This pairs with the smp_load_acquire() in
+	 * For existing inodes, multiple tasks may race to set ->i_crypt_info.
+	 * So use cmpxchg_release().  This pairs with the smp_load_acquire() in
 	 * fscrypt_get_info().  I.e., here we publish ->i_crypt_info with a
 	 * RELEASE barrier so that other tasks can ACQUIRE it.
 	 */
@@ -550,13 +541,127 @@ out:
 		up_read(&mk->mk_secret_sem);
 		key_put(master_key);
 	}
+	put_crypt_info(crypt_info);
+	return res;
+}
+
+/**
+ * fscrypt_get_encryption_info() - set up an inode's encryption key
+ * @inode: the inode to set up the key for
+ *
+ * Set up ->i_crypt_info, if it hasn't already been done.
+ *
+ * Note: unless ->i_crypt_info is already set, this isn't %GFP_NOFS-safe.  So
+ * generally this shouldn't be called from within a filesystem transaction.
+ *
+ * Return: 0 if ->i_crypt_info was set or was already set, *or* if the
+ *	   encryption key is unavailable.  (Use fscrypt_has_encryption_key() to
+ *	   distinguish these cases.)  Also can return another -errno code.
+ */
+int fscrypt_get_encryption_info(struct inode *inode)
+{
+	int res;
+	union fscrypt_context ctx;
+	union fscrypt_policy policy;
+
+	if (fscrypt_has_encryption_key(inode))
+		return 0;
+
+	res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
+	if (res < 0) {
+		const union fscrypt_context *dummy_ctx =
+			fscrypt_get_dummy_context(inode->i_sb);
+
+		if (IS_ENCRYPTED(inode) || !dummy_ctx) {
+			fscrypt_warn(inode,
+				     "Error %d getting encryption context",
+				     res);
+			return res;
+		}
+		/* Fake up a context for an unencrypted directory */
+		res = fscrypt_context_size(dummy_ctx);
+		memcpy(&ctx, dummy_ctx, res);
+	}
+
+	res = fscrypt_policy_from_context(&policy, &ctx, res);
+	if (res) {
+		fscrypt_warn(inode,
+			     "Unrecognized or corrupt encryption context");
+		return res;
+	}
+
+	if (!fscrypt_supported_policy(&policy, inode))
+		return -EINVAL;
+
+	res = fscrypt_setup_encryption_info(inode, &policy,
+					    fscrypt_context_nonce(&ctx),
+					    IS_CASEFOLDED(inode) &&
+					    S_ISDIR(inode->i_mode));
 	if (res == -ENOKEY)
 		res = 0;
-	put_crypt_info(crypt_info);
 	return res;
 }
 EXPORT_SYMBOL(fscrypt_get_encryption_info);
 
+/**
+ * fscrypt_prepare_new_inode() - prepare to create a new inode in a directory
+ * @dir: a possibly-encrypted directory
+ * @inode: the new inode.  ->i_mode must be set already.
+ *	   ->i_ino doesn't need to be set yet.
+ * @encrypt_ret: (output) set to %true if the new inode will be encrypted
+ *
+ * If the directory is encrypted, set up its ->i_crypt_info in preparation for
+ * encrypting the name of the new file.  Also, if the new inode will be
+ * encrypted, set up its ->i_crypt_info and set *encrypt_ret=true.
+ *
+ * This isn't %GFP_NOFS-safe, and therefore it should be called before starting
+ * any filesystem transaction to create the inode.  For this reason, ->i_ino
+ * isn't required to be set yet, as the filesystem may not have set it yet.
+ *
+ * This doesn't persist the new inode's encryption context.  That still needs to
+ * be done later by calling fscrypt_set_context().
+ *
+ * Return: 0 on success, -ENOKEY if the encryption key is missing, or another
+ *	   -errno code
+ */
+int fscrypt_prepare_new_inode(struct inode *dir, struct inode *inode,
+			      bool *encrypt_ret)
+{
+	int err;
+	u8 nonce[FSCRYPT_FILE_NONCE_SIZE];
+
+	if (!IS_ENCRYPTED(dir) && fscrypt_get_dummy_context(dir->i_sb) == NULL)
+		return 0;
+
+	err = fscrypt_get_encryption_info(dir);
+	if (err)
+		return err;
+	if (!fscrypt_has_encryption_key(dir))
+		return -ENOKEY;
+
+	if (WARN_ON_ONCE(inode->i_mode == 0))
+		return -EINVAL;
+
+	/*
+	 * Only regular files, directories, and symlinks are encrypted.
+	 * Special files like device nodes and named pipes aren't.
+	 */
+	if (!S_ISREG(inode->i_mode) &&
+	    !S_ISDIR(inode->i_mode) &&
+	    !S_ISLNK(inode->i_mode))
+		return 0;
+
+	*encrypt_ret = true;
+
+	get_random_bytes(nonce, FSCRYPT_FILE_NONCE_SIZE);
+	return fscrypt_setup_encryption_info(inode,
+					     &dir->i_crypt_info->ci_policy,
+					     nonce,
+					     IS_CASEFOLDED(dir) &&
+					     S_ISDIR(inode->i_mode));
+}
+EXPORT_SYMBOL_GPL(fscrypt_prepare_new_inode);
+
 /**
  * fscrypt_put_encryption_info() - free most of an inode's fscrypt data
  * @inode: an inode being evicted
diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
index b92f34523178..7e96953d385e 100644
--- a/fs/crypto/policy.c
+++ b/fs/crypto/policy.c
@@ -236,18 +236,19 @@ bool fscrypt_supported_policy(const union fscrypt_policy *policy_u,
 }
 
 /**
- * fscrypt_new_context_from_policy() - create a new fscrypt_context from
- *				       an fscrypt_policy
+ * fscrypt_new_context() - create a new fscrypt_context
  * @ctx_u: output context
  * @policy_u: input policy
+ * @nonce: nonce to use
  *
  * Create an fscrypt_context for an inode that is being assigned the given
- * encryption policy.  A new nonce is randomly generated.
+ * encryption policy.  @nonce must be a new random nonce.
  *
  * Return: the size of the new context in bytes.
  */
-static int fscrypt_new_context_from_policy(union fscrypt_context *ctx_u,
-					   const union fscrypt_policy *policy_u)
+static int fscrypt_new_context(union fscrypt_context *ctx_u,
+			       const union fscrypt_policy *policy_u,
+			       const u8 nonce[FSCRYPT_FILE_NONCE_SIZE])
 {
 	memset(ctx_u, 0, sizeof(*ctx_u));
 
@@ -265,7 +266,7 @@ static int fscrypt_new_context_from_policy(union fscrypt_context *ctx_u,
 		memcpy(ctx->master_key_descriptor,
 		       policy->master_key_descriptor,
 		       sizeof(ctx->master_key_descriptor));
-		get_random_bytes(ctx->nonce, sizeof(ctx->nonce));
+		memcpy(ctx->nonce, nonce, FSCRYPT_FILE_NONCE_SIZE);
 		return sizeof(*ctx);
 	}
 	case FSCRYPT_POLICY_V2: {
@@ -281,7 +282,7 @@ static int fscrypt_new_context_from_policy(union fscrypt_context *ctx_u,
 		memcpy(ctx->master_key_identifier,
 		       policy->master_key_identifier,
 		       sizeof(ctx->master_key_identifier));
-		get_random_bytes(ctx->nonce, sizeof(ctx->nonce));
+		memcpy(ctx->nonce, nonce, FSCRYPT_FILE_NONCE_SIZE);
 		return sizeof(*ctx);
 	}
 	}
@@ -377,6 +378,7 @@ static int fscrypt_get_policy(struct inode *inode, union fscrypt_policy *policy)
 static int set_encryption_policy(struct inode *inode,
 				 const union fscrypt_policy *policy)
 {
+	u8 nonce[FSCRYPT_FILE_NONCE_SIZE];
 	union fscrypt_context ctx;
 	int ctxsize;
 	int err;
@@ -414,7 +416,8 @@ static int set_encryption_policy(struct inode *inode,
 		return -EINVAL;
 	}
 
-	ctxsize = fscrypt_new_context_from_policy(&ctx, policy);
+	get_random_bytes(nonce, FSCRYPT_FILE_NONCE_SIZE);
+	ctxsize = fscrypt_new_context(&ctx, policy, nonce);
 
 	return inode->i_sb->s_cop->set_context(inode, &ctx, ctxsize, NULL);
 }
@@ -637,6 +640,7 @@ EXPORT_SYMBOL(fscrypt_has_permitted_context);
 int fscrypt_inherit_context(struct inode *parent, struct inode *child,
 						void *fs_data, bool preload)
 {
+	u8 nonce[FSCRYPT_FILE_NONCE_SIZE];
 	union fscrypt_context ctx;
 	int ctxsize;
 	struct fscrypt_info *ci;
@@ -650,7 +654,8 @@ int fscrypt_inherit_context(struct inode *parent, struct inode *child,
 	if (ci == NULL)
 		return -ENOKEY;
 
-	ctxsize = fscrypt_new_context_from_policy(&ctx, &ci->ci_policy);
+	get_random_bytes(nonce, FSCRYPT_FILE_NONCE_SIZE);
+	ctxsize = fscrypt_new_context(&ctx, &ci->ci_policy, nonce);
 
 	BUILD_BUG_ON(sizeof(ctx) != FSCRYPT_SET_CONTEXT_MAX_SIZE);
 	res = parent->i_sb->s_cop->set_context(child, &ctx, ctxsize, fs_data);
@@ -660,6 +665,45 @@ int fscrypt_inherit_context(struct inode *parent, struct inode *child,
 }
 EXPORT_SYMBOL(fscrypt_inherit_context);
 
+/**
+ * fscrypt_set_context() - Set the fscrypt context of a new inode
+ * @inode: a new inode
+ * @fs_data: private data given by FS and passed to ->set_context()
+ *
+ * This should be called after fscrypt_prepare_new_inode(), generally during a
+ * filesystem transaction.  Everything here must be %GFP_NOFS-safe.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int fscrypt_set_context(struct inode *inode, void *fs_data)
+{
+	struct fscrypt_info *ci = inode->i_crypt_info;
+	union fscrypt_context ctx;
+	int ctxsize;
+
+	/* fscrypt_prepare_new_inode() should have set up the key already. */
+	if (WARN_ON_ONCE(!ci))
+		return -ENOKEY;
+
+	BUILD_BUG_ON(sizeof(ctx) != FSCRYPT_SET_CONTEXT_MAX_SIZE);
+	ctxsize = fscrypt_new_context(&ctx, &ci->ci_policy, ci->ci_nonce);
+
+	/*
+	 * This may be the first time the inode number is available, so do any
+	 * delayed key setup that requires the inode number.
+	 */
+	if (ci->ci_policy.version == FSCRYPT_POLICY_V2 &&
+	    (ci->ci_policy.v2.flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32)) {
+		const struct fscrypt_master_key *mk =
+			ci->ci_master_key->payload.data[0];
+
+		fscrypt_hash_inode_number(ci, mk);
+	}
+
+	return inode->i_sb->s_cop->set_context(inode, &ctx, ctxsize, fs_data);
+}
+EXPORT_SYMBOL_GPL(fscrypt_set_context);
+
 /**
  * fscrypt_set_test_dummy_encryption() - handle '-o test_dummy_encryption'
  * @sb: the filesystem on which test_dummy_encryption is being specified
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index eaf16eb55788..9cf7ca90f3ab 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -158,6 +158,7 @@ int fscrypt_ioctl_get_nonce(struct file *filp, void __user *arg);
 int fscrypt_has_permitted_context(struct inode *parent, struct inode *child);
 int fscrypt_inherit_context(struct inode *parent, struct inode *child,
 			    void *fs_data, bool preload);
+int fscrypt_set_context(struct inode *inode, void *fs_data);
 
 struct fscrypt_dummy_context {
 	const union fscrypt_context *ctx;
@@ -184,6 +185,8 @@ int fscrypt_ioctl_get_key_status(struct file *filp, void __user *arg);
 
 /* keysetup.c */
 int fscrypt_get_encryption_info(struct inode *inode);
+int fscrypt_prepare_new_inode(struct inode *dir, struct inode *inode,
+			      bool *encrypt_ret);
 void fscrypt_put_encryption_info(struct inode *inode);
 void fscrypt_free_inode(struct inode *inode);
 int fscrypt_drop_inode(struct inode *inode);
@@ -347,6 +350,11 @@ static inline int fscrypt_inherit_context(struct inode *parent,
 	return -EOPNOTSUPP;
 }
 
+static inline int fscrypt_set_context(struct inode *inode, void *fs_data)
+{
+	return -EOPNOTSUPP;
+}
+
 struct fscrypt_dummy_context {
 };
 
@@ -394,6 +402,15 @@ static inline int fscrypt_get_encryption_info(struct inode *inode)
 	return -EOPNOTSUPP;
 }
 
+static inline int fscrypt_prepare_new_inode(struct inode *dir,
+					    struct inode *inode,
+					    bool *encrypt_ret)
+{
+	if (IS_ENCRYPTED(dir))
+		return -EOPNOTSUPP;
+	return 0;
+}
+
 static inline void fscrypt_put_encryption_info(struct inode *inode)
 {
 	return;
-- 
cgit v1.2.3


From e9d5e31d2fe39825b0fc276b14f2a322faf3c77b Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Wed, 16 Sep 2020 21:11:30 -0700
Subject: fscrypt: remove fscrypt_inherit_context()

Now that all filesystems have been converted to use
fscrypt_prepare_new_inode() and fscrypt_set_context(),
fscrypt_inherit_context() is no longer used.  Remove it.

Acked-by: Jeff Layton <jlayton@kernel.org>
Link: https://lore.kernel.org/r/20200917041136.178600-8-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 fs/crypto/policy.c      | 37 -------------------------------------
 include/linux/fscrypt.h |  9 ---------
 2 files changed, 46 deletions(-)

(limited to 'include/linux')

diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
index 7e96953d385e..4ff893f7b030 100644
--- a/fs/crypto/policy.c
+++ b/fs/crypto/policy.c
@@ -628,43 +628,6 @@ int fscrypt_has_permitted_context(struct inode *parent, struct inode *child)
 }
 EXPORT_SYMBOL(fscrypt_has_permitted_context);
 
-/**
- * fscrypt_inherit_context() - Sets a child context from its parent
- * @parent: Parent inode from which the context is inherited.
- * @child:  Child inode that inherits the context from @parent.
- * @fs_data:  private data given by FS.
- * @preload:  preload child i_crypt_info if true
- *
- * Return: 0 on success, -errno on failure
- */
-int fscrypt_inherit_context(struct inode *parent, struct inode *child,
-						void *fs_data, bool preload)
-{
-	u8 nonce[FSCRYPT_FILE_NONCE_SIZE];
-	union fscrypt_context ctx;
-	int ctxsize;
-	struct fscrypt_info *ci;
-	int res;
-
-	res = fscrypt_get_encryption_info(parent);
-	if (res < 0)
-		return res;
-
-	ci = fscrypt_get_info(parent);
-	if (ci == NULL)
-		return -ENOKEY;
-
-	get_random_bytes(nonce, FSCRYPT_FILE_NONCE_SIZE);
-	ctxsize = fscrypt_new_context(&ctx, &ci->ci_policy, nonce);
-
-	BUILD_BUG_ON(sizeof(ctx) != FSCRYPT_SET_CONTEXT_MAX_SIZE);
-	res = parent->i_sb->s_cop->set_context(child, &ctx, ctxsize, fs_data);
-	if (res)
-		return res;
-	return preload ? fscrypt_get_encryption_info(child): 0;
-}
-EXPORT_SYMBOL(fscrypt_inherit_context);
-
 /**
  * fscrypt_set_context() - Set the fscrypt context of a new inode
  * @inode: a new inode
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index 9cf7ca90f3ab..81d6ded24328 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -156,8 +156,6 @@ int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg);
 int fscrypt_ioctl_get_policy_ex(struct file *filp, void __user *arg);
 int fscrypt_ioctl_get_nonce(struct file *filp, void __user *arg);
 int fscrypt_has_permitted_context(struct inode *parent, struct inode *child);
-int fscrypt_inherit_context(struct inode *parent, struct inode *child,
-			    void *fs_data, bool preload);
 int fscrypt_set_context(struct inode *inode, void *fs_data);
 
 struct fscrypt_dummy_context {
@@ -343,13 +341,6 @@ static inline int fscrypt_has_permitted_context(struct inode *parent,
 	return 0;
 }
 
-static inline int fscrypt_inherit_context(struct inode *parent,
-					  struct inode *child,
-					  void *fs_data, bool preload)
-{
-	return -EOPNOTSUPP;
-}
-
 static inline int fscrypt_set_context(struct inode *inode, void *fs_data)
 {
 	return -EOPNOTSUPP;
-- 
cgit v1.2.3


From 31114726b69364f3bf8dd945c600ceed4c430f4f Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Wed, 16 Sep 2020 21:11:34 -0700
Subject: fscrypt: move fscrypt_prepare_symlink() out-of-line

In preparation for moving the logic for "get the encryption policy
inherited by new files in this directory" to a single place, make
fscrypt_prepare_symlink() a regular function rather than an inline
function that wraps __fscrypt_prepare_symlink().

This way, the new function fscrypt_policy_to_inherit() won't need to be
exported to filesystems.

Acked-by: Jeff Layton <jlayton@kernel.org>
Link: https://lore.kernel.org/r/20200917041136.178600-12-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 fs/crypto/hooks.c       | 39 ++++++++++++++++++++++++++----
 include/linux/fscrypt.h | 63 ++++++++++++-------------------------------------
 2 files changed, 50 insertions(+), 52 deletions(-)

(limited to 'include/linux')

diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c
index 7748db509240..a399c54947f2 100644
--- a/fs/crypto/hooks.c
+++ b/fs/crypto/hooks.c
@@ -166,12 +166,43 @@ int fscrypt_prepare_setflags(struct inode *inode,
 	return 0;
 }
 
-int __fscrypt_prepare_symlink(struct inode *dir, unsigned int len,
-			      unsigned int max_len,
-			      struct fscrypt_str *disk_link)
+/**
+ * fscrypt_prepare_symlink() - prepare to create a possibly-encrypted symlink
+ * @dir: directory in which the symlink is being created
+ * @target: plaintext symlink target
+ * @len: length of @target excluding null terminator
+ * @max_len: space the filesystem has available to store the symlink target
+ * @disk_link: (out) the on-disk symlink target being prepared
+ *
+ * This function computes the size the symlink target will require on-disk,
+ * stores it in @disk_link->len, and validates it against @max_len.  An
+ * encrypted symlink may be longer than the original.
+ *
+ * Additionally, @disk_link->name is set to @target if the symlink will be
+ * unencrypted, but left NULL if the symlink will be encrypted.  For encrypted
+ * symlinks, the filesystem must call fscrypt_encrypt_symlink() to create the
+ * on-disk target later.  (The reason for the two-step process is that some
+ * filesystems need to know the size of the symlink target before creating the
+ * inode, e.g. to determine whether it will be a "fast" or "slow" symlink.)
+ *
+ * Return: 0 on success, -ENAMETOOLONG if the symlink target is too long,
+ * -ENOKEY if the encryption key is missing, or another -errno code if a problem
+ * occurred while setting up the encryption key.
+ */
+int fscrypt_prepare_symlink(struct inode *dir, const char *target,
+			    unsigned int len, unsigned int max_len,
+			    struct fscrypt_str *disk_link)
 {
 	int err;
 
+	if (!IS_ENCRYPTED(dir) && !fscrypt_get_dummy_context(dir->i_sb)) {
+		disk_link->name = (unsigned char *)target;
+		disk_link->len = len + 1;
+		if (disk_link->len > max_len)
+			return -ENAMETOOLONG;
+		return 0;
+	}
+
 	/*
 	 * To calculate the size of the encrypted symlink target we need to know
 	 * the amount of NUL padding, which is determined by the flags set in
@@ -207,7 +238,7 @@ int __fscrypt_prepare_symlink(struct inode *dir, unsigned int len,
 	disk_link->name = NULL;
 	return 0;
 }
-EXPORT_SYMBOL_GPL(__fscrypt_prepare_symlink);
+EXPORT_SYMBOL_GPL(fscrypt_prepare_symlink);
 
 int __fscrypt_encrypt_symlink(struct inode *inode, const char *target,
 			      unsigned int len, struct fscrypt_str *disk_link)
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index 81d6ded24328..39e7397a3f10 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -225,9 +225,9 @@ int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry,
 			     struct fscrypt_name *fname);
 int fscrypt_prepare_setflags(struct inode *inode,
 			     unsigned int oldflags, unsigned int flags);
-int __fscrypt_prepare_symlink(struct inode *dir, unsigned int len,
-			      unsigned int max_len,
-			      struct fscrypt_str *disk_link);
+int fscrypt_prepare_symlink(struct inode *dir, const char *target,
+			    unsigned int len, unsigned int max_len,
+			    struct fscrypt_str *disk_link);
 int __fscrypt_encrypt_symlink(struct inode *inode, const char *target,
 			      unsigned int len, struct fscrypt_str *disk_link);
 const char *fscrypt_get_symlink(struct inode *inode, const void *caddr,
@@ -520,15 +520,21 @@ static inline int fscrypt_prepare_setflags(struct inode *inode,
 	return 0;
 }
 
-static inline int __fscrypt_prepare_symlink(struct inode *dir,
-					    unsigned int len,
-					    unsigned int max_len,
-					    struct fscrypt_str *disk_link)
+static inline int fscrypt_prepare_symlink(struct inode *dir,
+					  const char *target,
+					  unsigned int len,
+					  unsigned int max_len,
+					  struct fscrypt_str *disk_link)
 {
-	return -EOPNOTSUPP;
+	if (IS_ENCRYPTED(dir))
+		return -EOPNOTSUPP;
+	disk_link->name = (unsigned char *)target;
+	disk_link->len = len + 1;
+	if (disk_link->len > max_len)
+		return -ENAMETOOLONG;
+	return 0;
 }
 
-
 static inline int __fscrypt_encrypt_symlink(struct inode *inode,
 					    const char *target,
 					    unsigned int len,
@@ -793,45 +799,6 @@ static inline int fscrypt_prepare_setattr(struct dentry *dentry,
 	return 0;
 }
 
-/**
- * fscrypt_prepare_symlink() - prepare to create a possibly-encrypted symlink
- * @dir: directory in which the symlink is being created
- * @target: plaintext symlink target
- * @len: length of @target excluding null terminator
- * @max_len: space the filesystem has available to store the symlink target
- * @disk_link: (out) the on-disk symlink target being prepared
- *
- * This function computes the size the symlink target will require on-disk,
- * stores it in @disk_link->len, and validates it against @max_len.  An
- * encrypted symlink may be longer than the original.
- *
- * Additionally, @disk_link->name is set to @target if the symlink will be
- * unencrypted, but left NULL if the symlink will be encrypted.  For encrypted
- * symlinks, the filesystem must call fscrypt_encrypt_symlink() to create the
- * on-disk target later.  (The reason for the two-step process is that some
- * filesystems need to know the size of the symlink target before creating the
- * inode, e.g. to determine whether it will be a "fast" or "slow" symlink.)
- *
- * Return: 0 on success, -ENAMETOOLONG if the symlink target is too long,
- * -ENOKEY if the encryption key is missing, or another -errno code if a problem
- * occurred while setting up the encryption key.
- */
-static inline int fscrypt_prepare_symlink(struct inode *dir,
-					  const char *target,
-					  unsigned int len,
-					  unsigned int max_len,
-					  struct fscrypt_str *disk_link)
-{
-	if (IS_ENCRYPTED(dir) || fscrypt_get_dummy_context(dir->i_sb) != NULL)
-		return __fscrypt_prepare_symlink(dir, len, max_len, disk_link);
-
-	disk_link->name = (unsigned char *)target;
-	disk_link->len = len + 1;
-	if (disk_link->len > max_len)
-		return -ENAMETOOLONG;
-	return 0;
-}
-
 /**
  * fscrypt_encrypt_symlink() - encrypt the symlink target if needed
  * @inode: symlink inode
-- 
cgit v1.2.3


From ac4acb1f4b2b6b7e8d913537cccec8789903e164 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Wed, 16 Sep 2020 21:11:35 -0700
Subject: fscrypt: handle test_dummy_encryption in more logical way

The behavior of the test_dummy_encryption mount option is that when a
new file (or directory or symlink) is created in an unencrypted
directory, it's automatically encrypted using a dummy encryption policy.
That's it; in particular, the encryption (or lack thereof) of existing
files (or directories or symlinks) doesn't change.

Unfortunately the implementation of test_dummy_encryption is a bit weird
and confusing.  When test_dummy_encryption is enabled and a file is
being created in an unencrypted directory, we set up an encryption key
(->i_crypt_info) for the directory.  This isn't actually used to do any
encryption, however, since the directory is still unencrypted!  Instead,
->i_crypt_info is only used for inheriting the encryption policy.

One consequence of this is that the filesystem ends up providing a
"dummy context" (policy + nonce) instead of a "dummy policy".  In
commit ed318a6cc0b6 ("fscrypt: support test_dummy_encryption=v2"), I
mistakenly thought this was required.  However, actually the nonce only
ends up being used to derive a key that is never used.

Another consequence of this implementation is that it allows for
'inode->i_crypt_info != NULL && !IS_ENCRYPTED(inode)', which is an edge
case that can be forgotten about.  For example, currently
FS_IOC_GET_ENCRYPTION_POLICY on an unencrypted directory may return the
dummy encryption policy when the filesystem is mounted with
test_dummy_encryption.  That seems like the wrong thing to do, since
again, the directory itself is not actually encrypted.

Therefore, switch to a more logical and maintainable implementation
where the dummy encryption policy inheritance is done without setting up
keys for unencrypted directories.  This involves:

- Adding a function fscrypt_policy_to_inherit() which returns the
  encryption policy to inherit from a directory.  This can be a real
  policy, a dummy policy, or no policy.

- Replacing struct fscrypt_dummy_context, ->get_dummy_context(), etc.
  with struct fscrypt_dummy_policy, ->get_dummy_policy(), etc.

- Making fscrypt_fname_encrypted_size() take an fscrypt_policy instead
  of an inode.

Acked-by: Jaegeuk Kim <jaegeuk@kernel.org>
Acked-by: Jeff Layton <jlayton@kernel.org>
Link: https://lore.kernel.org/r/20200917041136.178600-13-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 fs/crypto/fname.c           |  11 +++--
 fs/crypto/fscrypt_private.h |   6 ++-
 fs/crypto/hooks.c           |  30 +++++-------
 fs/crypto/keysetup.c        |  33 ++++---------
 fs/crypto/policy.c          | 113 +++++++++++++++++++++++++++-----------------
 fs/ext4/ext4.h              |   6 +--
 fs/ext4/super.c             |  16 +++----
 fs/f2fs/f2fs.h              |   2 +-
 fs/f2fs/super.c             |  15 +++---
 include/linux/fscrypt.h     |  40 +++++-----------
 10 files changed, 132 insertions(+), 140 deletions(-)

(limited to 'include/linux')

diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c
index 47bcfddb278b..eb13408b50a7 100644
--- a/fs/crypto/fname.c
+++ b/fs/crypto/fname.c
@@ -242,11 +242,11 @@ static int base64_decode(const char *src, int len, u8 *dst)
 	return cp - dst;
 }
 
-bool fscrypt_fname_encrypted_size(const struct inode *inode, u32 orig_len,
-				  u32 max_len, u32 *encrypted_len_ret)
+bool fscrypt_fname_encrypted_size(const union fscrypt_policy *policy,
+				  u32 orig_len, u32 max_len,
+				  u32 *encrypted_len_ret)
 {
-	const struct fscrypt_info *ci = inode->i_crypt_info;
-	int padding = 4 << (fscrypt_policy_flags(&ci->ci_policy) &
+	int padding = 4 << (fscrypt_policy_flags(policy) &
 			    FSCRYPT_POLICY_FLAGS_PAD_MASK);
 	u32 encrypted_len;
 
@@ -418,7 +418,8 @@ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname,
 		return ret;
 
 	if (fscrypt_has_encryption_key(dir)) {
-		if (!fscrypt_fname_encrypted_size(dir, iname->len,
+		if (!fscrypt_fname_encrypted_size(&dir->i_crypt_info->ci_policy,
+						  iname->len,
 						  dir->i_sb->s_cop->max_namelen,
 						  &fname->crypto_buf.len))
 			return -ENAMETOOLONG;
diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h
index ac3352086ee4..4f5806a3b73d 100644
--- a/fs/crypto/fscrypt_private.h
+++ b/fs/crypto/fscrypt_private.h
@@ -291,8 +291,9 @@ void fscrypt_generate_iv(union fscrypt_iv *iv, u64 lblk_num,
 /* fname.c */
 int fscrypt_fname_encrypt(const struct inode *inode, const struct qstr *iname,
 			  u8 *out, unsigned int olen);
-bool fscrypt_fname_encrypted_size(const struct inode *inode, u32 orig_len,
-				  u32 max_len, u32 *encrypted_len_ret);
+bool fscrypt_fname_encrypted_size(const union fscrypt_policy *policy,
+				  u32 orig_len, u32 max_len,
+				  u32 *encrypted_len_ret);
 extern const struct dentry_operations fscrypt_d_ops;
 
 /* hkdf.c */
@@ -592,5 +593,6 @@ bool fscrypt_supported_policy(const union fscrypt_policy *policy_u,
 int fscrypt_policy_from_context(union fscrypt_policy *policy_u,
 				const union fscrypt_context *ctx_u,
 				int ctx_size);
+const union fscrypt_policy *fscrypt_policy_to_inherit(struct inode *dir);
 
 #endif /* _FSCRYPT_PRIVATE_H */
diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c
index a399c54947f2..42f5ee9f592d 100644
--- a/fs/crypto/hooks.c
+++ b/fs/crypto/hooks.c
@@ -193,30 +193,24 @@ int fscrypt_prepare_symlink(struct inode *dir, const char *target,
 			    unsigned int len, unsigned int max_len,
 			    struct fscrypt_str *disk_link)
 {
-	int err;
+	const union fscrypt_policy *policy;
 
-	if (!IS_ENCRYPTED(dir) && !fscrypt_get_dummy_context(dir->i_sb)) {
+	/*
+	 * To calculate the size of the encrypted symlink target we need to know
+	 * the amount of NUL padding, which is determined by the flags set in
+	 * the encryption policy which will be inherited from the directory.
+	 */
+	policy = fscrypt_policy_to_inherit(dir);
+	if (policy == NULL) {
+		/* Not encrypted */
 		disk_link->name = (unsigned char *)target;
 		disk_link->len = len + 1;
 		if (disk_link->len > max_len)
 			return -ENAMETOOLONG;
 		return 0;
 	}
-
-	/*
-	 * To calculate the size of the encrypted symlink target we need to know
-	 * the amount of NUL padding, which is determined by the flags set in
-	 * the encryption policy which will be inherited from the directory.
-	 * The easiest way to get access to this is to just load the directory's
-	 * fscrypt_info, since we'll need it to create the dir_entry anyway.
-	 *
-	 * Note: in test_dummy_encryption mode, @dir may be unencrypted.
-	 */
-	err = fscrypt_get_encryption_info(dir);
-	if (err)
-		return err;
-	if (!fscrypt_has_encryption_key(dir))
-		return -ENOKEY;
+	if (IS_ERR(policy))
+		return PTR_ERR(policy);
 
 	/*
 	 * Calculate the size of the encrypted symlink and verify it won't
@@ -229,7 +223,7 @@ int fscrypt_prepare_symlink(struct inode *dir, const char *target,
 	 * counting it (even though it is meaningless for ciphertext) is simpler
 	 * for now since filesystems will assume it is there and subtract it.
 	 */
-	if (!fscrypt_fname_encrypted_size(dir, len,
+	if (!fscrypt_fname_encrypted_size(policy, len,
 					  max_len - sizeof(struct fscrypt_symlink_data),
 					  &disk_link->len))
 		return -ENAMETOOLONG;
diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c
index 47f19061ba10..d3c3e5d9b41f 100644
--- a/fs/crypto/keysetup.c
+++ b/fs/crypto/keysetup.c
@@ -547,7 +547,7 @@ out:
 
 /**
  * fscrypt_get_encryption_info() - set up an inode's encryption key
- * @inode: the inode to set up the key for
+ * @inode: the inode to set up the key for.  Must be encrypted.
  *
  * Set up ->i_crypt_info, if it hasn't already been done.
  *
@@ -569,18 +569,8 @@ int fscrypt_get_encryption_info(struct inode *inode)
 
 	res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
 	if (res < 0) {
-		const union fscrypt_context *dummy_ctx =
-			fscrypt_get_dummy_context(inode->i_sb);
-
-		if (IS_ENCRYPTED(inode) || !dummy_ctx) {
-			fscrypt_warn(inode,
-				     "Error %d getting encryption context",
-				     res);
-			return res;
-		}
-		/* Fake up a context for an unencrypted directory */
-		res = fscrypt_context_size(dummy_ctx);
-		memcpy(&ctx, dummy_ctx, res);
+		fscrypt_warn(inode, "Error %d getting encryption context", res);
+		return res;
 	}
 
 	res = fscrypt_policy_from_context(&policy, &ctx, res);
@@ -627,17 +617,14 @@ EXPORT_SYMBOL(fscrypt_get_encryption_info);
 int fscrypt_prepare_new_inode(struct inode *dir, struct inode *inode,
 			      bool *encrypt_ret)
 {
-	int err;
+	const union fscrypt_policy *policy;
 	u8 nonce[FSCRYPT_FILE_NONCE_SIZE];
 
-	if (!IS_ENCRYPTED(dir) && fscrypt_get_dummy_context(dir->i_sb) == NULL)
+	policy = fscrypt_policy_to_inherit(dir);
+	if (policy == NULL)
 		return 0;
-
-	err = fscrypt_get_encryption_info(dir);
-	if (err)
-		return err;
-	if (!fscrypt_has_encryption_key(dir))
-		return -ENOKEY;
+	if (IS_ERR(policy))
+		return PTR_ERR(policy);
 
 	if (WARN_ON_ONCE(inode->i_mode == 0))
 		return -EINVAL;
@@ -654,9 +641,7 @@ int fscrypt_prepare_new_inode(struct inode *dir, struct inode *inode,
 	*encrypt_ret = true;
 
 	get_random_bytes(nonce, FSCRYPT_FILE_NONCE_SIZE);
-	return fscrypt_setup_encryption_info(inode,
-					     &dir->i_crypt_info->ci_policy,
-					     nonce,
+	return fscrypt_setup_encryption_info(inode, policy, nonce,
 					     IS_CASEFOLDED(dir) &&
 					     S_ISDIR(inode->i_mode));
 }
diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
index 4ff893f7b030..97cf07543651 100644
--- a/fs/crypto/policy.c
+++ b/fs/crypto/policy.c
@@ -32,6 +32,14 @@ bool fscrypt_policies_equal(const union fscrypt_policy *policy1,
 	return !memcmp(policy1, policy2, fscrypt_policy_size(policy1));
 }
 
+static const union fscrypt_policy *
+fscrypt_get_dummy_policy(struct super_block *sb)
+{
+	if (!sb->s_cop->get_dummy_policy)
+		return NULL;
+	return sb->s_cop->get_dummy_policy(sb);
+}
+
 static bool fscrypt_valid_enc_modes(u32 contents_mode, u32 filenames_mode)
 {
 	if (contents_mode == FSCRYPT_MODE_AES_256_XTS &&
@@ -628,6 +636,25 @@ int fscrypt_has_permitted_context(struct inode *parent, struct inode *child)
 }
 EXPORT_SYMBOL(fscrypt_has_permitted_context);
 
+/*
+ * Return the encryption policy that new files in the directory will inherit, or
+ * NULL if none, or an ERR_PTR() on error.  If the directory is encrypted, also
+ * ensure that its key is set up, so that the new filename can be encrypted.
+ */
+const union fscrypt_policy *fscrypt_policy_to_inherit(struct inode *dir)
+{
+	int err;
+
+	if (IS_ENCRYPTED(dir)) {
+		err = fscrypt_require_key(dir);
+		if (err)
+			return ERR_PTR(err);
+		return &dir->i_crypt_info->ci_policy;
+	}
+
+	return fscrypt_get_dummy_policy(dir->i_sb);
+}
+
 /**
  * fscrypt_set_context() - Set the fscrypt context of a new inode
  * @inode: a new inode
@@ -672,31 +699,28 @@ EXPORT_SYMBOL_GPL(fscrypt_set_context);
  * @sb: the filesystem on which test_dummy_encryption is being specified
  * @arg: the argument to the test_dummy_encryption option.
  *	 If no argument was specified, then @arg->from == NULL.
- * @dummy_ctx: the filesystem's current dummy context (input/output, see below)
+ * @dummy_policy: the filesystem's current dummy policy (input/output, see
+ *		  below)
  *
  * Handle the test_dummy_encryption mount option by creating a dummy encryption
- * context, saving it in @dummy_ctx, and adding the corresponding dummy
- * encryption key to the filesystem.  If the @dummy_ctx is already set, then
+ * policy, saving it in @dummy_policy, and adding the corresponding dummy
+ * encryption key to the filesystem.  If the @dummy_policy is already set, then
  * instead validate that it matches @arg.  Don't support changing it via
  * remount, as that is difficult to do safely.
  *
- * The reason we use an fscrypt_context rather than an fscrypt_policy is because
- * we mustn't generate a new nonce each time we access a dummy-encrypted
- * directory, as that would change the way filenames are encrypted.
- *
- * Return: 0 on success (dummy context set, or the same context is already set);
- *         -EEXIST if a different dummy context is already set;
+ * Return: 0 on success (dummy policy set, or the same policy is already set);
+ *         -EEXIST if a different dummy policy is already set;
  *         or another -errno value.
  */
 int fscrypt_set_test_dummy_encryption(struct super_block *sb,
 				      const substring_t *arg,
-				      struct fscrypt_dummy_context *dummy_ctx)
+				      struct fscrypt_dummy_policy *dummy_policy)
 {
 	const char *argstr = "v2";
 	const char *argstr_to_free = NULL;
 	struct fscrypt_key_specifier key_spec = { 0 };
 	int version;
-	union fscrypt_context *ctx = NULL;
+	union fscrypt_policy *policy = NULL;
 	int err;
 
 	if (arg->from) {
@@ -706,12 +730,12 @@ int fscrypt_set_test_dummy_encryption(struct super_block *sb,
 	}
 
 	if (!strcmp(argstr, "v1")) {
-		version = FSCRYPT_CONTEXT_V1;
+		version = FSCRYPT_POLICY_V1;
 		key_spec.type = FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR;
 		memset(key_spec.u.descriptor, 0x42,
 		       FSCRYPT_KEY_DESCRIPTOR_SIZE);
 	} else if (!strcmp(argstr, "v2")) {
-		version = FSCRYPT_CONTEXT_V2;
+		version = FSCRYPT_POLICY_V2;
 		key_spec.type = FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER;
 		/* key_spec.u.identifier gets filled in when adding the key */
 	} else {
@@ -719,21 +743,8 @@ int fscrypt_set_test_dummy_encryption(struct super_block *sb,
 		goto out;
 	}
 
-	if (dummy_ctx->ctx) {
-		/*
-		 * Note: if we ever make test_dummy_encryption support
-		 * specifying other encryption settings, such as the encryption
-		 * modes, we'll need to compare those settings here.
-		 */
-		if (dummy_ctx->ctx->version == version)
-			err = 0;
-		else
-			err = -EEXIST;
-		goto out;
-	}
-
-	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
-	if (!ctx) {
+	policy = kzalloc(sizeof(*policy), GFP_KERNEL);
+	if (!policy) {
 		err = -ENOMEM;
 		goto out;
 	}
@@ -742,18 +753,18 @@ int fscrypt_set_test_dummy_encryption(struct super_block *sb,
 	if (err)
 		goto out;
 
-	ctx->version = version;
-	switch (ctx->version) {
-	case FSCRYPT_CONTEXT_V1:
-		ctx->v1.contents_encryption_mode = FSCRYPT_MODE_AES_256_XTS;
-		ctx->v1.filenames_encryption_mode = FSCRYPT_MODE_AES_256_CTS;
-		memcpy(ctx->v1.master_key_descriptor, key_spec.u.descriptor,
+	policy->version = version;
+	switch (policy->version) {
+	case FSCRYPT_POLICY_V1:
+		policy->v1.contents_encryption_mode = FSCRYPT_MODE_AES_256_XTS;
+		policy->v1.filenames_encryption_mode = FSCRYPT_MODE_AES_256_CTS;
+		memcpy(policy->v1.master_key_descriptor, key_spec.u.descriptor,
 		       FSCRYPT_KEY_DESCRIPTOR_SIZE);
 		break;
-	case FSCRYPT_CONTEXT_V2:
-		ctx->v2.contents_encryption_mode = FSCRYPT_MODE_AES_256_XTS;
-		ctx->v2.filenames_encryption_mode = FSCRYPT_MODE_AES_256_CTS;
-		memcpy(ctx->v2.master_key_identifier, key_spec.u.identifier,
+	case FSCRYPT_POLICY_V2:
+		policy->v2.contents_encryption_mode = FSCRYPT_MODE_AES_256_XTS;
+		policy->v2.filenames_encryption_mode = FSCRYPT_MODE_AES_256_CTS;
+		memcpy(policy->v2.master_key_identifier, key_spec.u.identifier,
 		       FSCRYPT_KEY_IDENTIFIER_SIZE);
 		break;
 	default:
@@ -761,11 +772,19 @@ int fscrypt_set_test_dummy_encryption(struct super_block *sb,
 		err = -EINVAL;
 		goto out;
 	}
-	dummy_ctx->ctx = ctx;
-	ctx = NULL;
+
+	if (dummy_policy->policy) {
+		if (fscrypt_policies_equal(policy, dummy_policy->policy))
+			err = 0;
+		else
+			err = -EEXIST;
+		goto out;
+	}
+	dummy_policy->policy = policy;
+	policy = NULL;
 	err = 0;
 out:
-	kfree(ctx);
+	kfree(policy);
 	kfree(argstr_to_free);
 	return err;
 }
@@ -783,10 +802,16 @@ EXPORT_SYMBOL_GPL(fscrypt_set_test_dummy_encryption);
 void fscrypt_show_test_dummy_encryption(struct seq_file *seq, char sep,
 					struct super_block *sb)
 {
-	const union fscrypt_context *ctx = fscrypt_get_dummy_context(sb);
+	const union fscrypt_policy *policy = fscrypt_get_dummy_policy(sb);
+	int vers;
 
-	if (!ctx)
+	if (!policy)
 		return;
-	seq_printf(seq, "%ctest_dummy_encryption=v%d", sep, ctx->version);
+
+	vers = policy->version;
+	if (vers == FSCRYPT_POLICY_V1) /* Handle numbering quirk */
+		vers = 1;
+
+	seq_printf(seq, "%ctest_dummy_encryption=v%d", sep, vers);
 }
 EXPORT_SYMBOL_GPL(fscrypt_show_test_dummy_encryption);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 523e00d7b392..f9a692c0a66c 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1401,7 +1401,7 @@ struct ext4_super_block {
 #define EXT4_MF_FS_ABORTED		0x0002	/* Fatal error detected */
 
 #ifdef CONFIG_FS_ENCRYPTION
-#define DUMMY_ENCRYPTION_ENABLED(sbi) ((sbi)->s_dummy_enc_ctx.ctx != NULL)
+#define DUMMY_ENCRYPTION_ENABLED(sbi) ((sbi)->s_dummy_enc_policy.policy != NULL)
 #else
 #define DUMMY_ENCRYPTION_ENABLED(sbi) (0)
 #endif
@@ -1596,8 +1596,8 @@ struct ext4_sb_info {
 	atomic_t s_warning_count;
 	atomic_t s_msg_count;
 
-	/* Encryption context for '-o test_dummy_encryption' */
-	struct fscrypt_dummy_context s_dummy_enc_ctx;
+	/* Encryption policy for '-o test_dummy_encryption' */
+	struct fscrypt_dummy_policy s_dummy_enc_policy;
 
 	/*
 	 * Barrier between writepages ops and changing any inode's JOURNAL_DATA
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index ea425b49b345..aa6f64badf58 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1104,7 +1104,7 @@ static void ext4_put_super(struct super_block *sb)
 		crypto_free_shash(sbi->s_chksum_driver);
 	kfree(sbi->s_blockgroup_lock);
 	fs_put_dax(sbi->s_daxdev);
-	fscrypt_free_dummy_context(&sbi->s_dummy_enc_ctx);
+	fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy);
 #ifdef CONFIG_UNICODE
 	utf8_unload(sbi->s_encoding);
 #endif
@@ -1392,10 +1392,9 @@ retry:
 	return res;
 }
 
-static const union fscrypt_context *
-ext4_get_dummy_context(struct super_block *sb)
+static const union fscrypt_policy *ext4_get_dummy_policy(struct super_block *sb)
 {
-	return EXT4_SB(sb)->s_dummy_enc_ctx.ctx;
+	return EXT4_SB(sb)->s_dummy_enc_policy.policy;
 }
 
 static bool ext4_has_stable_inodes(struct super_block *sb)
@@ -1414,7 +1413,7 @@ static const struct fscrypt_operations ext4_cryptops = {
 	.key_prefix		= "ext4:",
 	.get_context		= ext4_get_context,
 	.set_context		= ext4_set_context,
-	.get_dummy_context	= ext4_get_dummy_context,
+	.get_dummy_policy	= ext4_get_dummy_policy,
 	.empty_dir		= ext4_empty_dir,
 	.max_namelen		= EXT4_NAME_LEN,
 	.has_stable_inodes	= ext4_has_stable_inodes,
@@ -1888,12 +1887,13 @@ static int ext4_set_test_dummy_encryption(struct super_block *sb,
 	 * needed to allow it to be set or changed during remount.  We do allow
 	 * it to be specified during remount, but only if there is no change.
 	 */
-	if (is_remount && !sbi->s_dummy_enc_ctx.ctx) {
+	if (is_remount && !sbi->s_dummy_enc_policy.policy) {
 		ext4_msg(sb, KERN_WARNING,
 			 "Can't set test_dummy_encryption on remount");
 		return -1;
 	}
-	err = fscrypt_set_test_dummy_encryption(sb, arg, &sbi->s_dummy_enc_ctx);
+	err = fscrypt_set_test_dummy_encryption(sb, arg,
+						&sbi->s_dummy_enc_policy);
 	if (err) {
 		if (err == -EEXIST)
 			ext4_msg(sb, KERN_WARNING,
@@ -4935,7 +4935,7 @@ failed_mount:
 	for (i = 0; i < EXT4_MAXQUOTAS; i++)
 		kfree(get_qf_name(sb, sbi, i));
 #endif
-	fscrypt_free_dummy_context(&sbi->s_dummy_enc_ctx);
+	fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy);
 	ext4_blkdev_remove(sbi);
 	brelse(bh);
 out_fail:
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 0503371f88ed..7c089ff7ff94 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -138,7 +138,7 @@ struct f2fs_mount_info {
 	int fsync_mode;			/* fsync policy */
 	int fs_mode;			/* fs mode: LFS or ADAPTIVE */
 	int bggc_mode;			/* bggc mode: off, on or sync */
-	struct fscrypt_dummy_context dummy_enc_ctx; /* test dummy encryption */
+	struct fscrypt_dummy_policy dummy_enc_policy; /* test dummy encryption */
 	block_t unusable_cap_perc;	/* percentage for cap */
 	block_t unusable_cap;		/* Amount of space allowed to be
 					 * unusable when disabling checkpoint
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index dfa072fa8081..f05ee33f5f26 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -433,12 +433,12 @@ static int f2fs_set_test_dummy_encryption(struct super_block *sb,
 	 * needed to allow it to be set or changed during remount.  We do allow
 	 * it to be specified during remount, but only if there is no change.
 	 */
-	if (is_remount && !F2FS_OPTION(sbi).dummy_enc_ctx.ctx) {
+	if (is_remount && !F2FS_OPTION(sbi).dummy_enc_policy.policy) {
 		f2fs_warn(sbi, "Can't set test_dummy_encryption on remount");
 		return -EINVAL;
 	}
 	err = fscrypt_set_test_dummy_encryption(
-		sb, arg, &F2FS_OPTION(sbi).dummy_enc_ctx);
+		sb, arg, &F2FS_OPTION(sbi).dummy_enc_policy);
 	if (err) {
 		if (err == -EEXIST)
 			f2fs_warn(sbi,
@@ -1275,7 +1275,7 @@ static void f2fs_put_super(struct super_block *sb)
 	for (i = 0; i < MAXQUOTAS; i++)
 		kfree(F2FS_OPTION(sbi).s_qf_names[i]);
 #endif
-	fscrypt_free_dummy_context(&F2FS_OPTION(sbi).dummy_enc_ctx);
+	fscrypt_free_dummy_policy(&F2FS_OPTION(sbi).dummy_enc_policy);
 	destroy_percpu_info(sbi);
 	for (i = 0; i < NR_PAGE_TYPE; i++)
 		kvfree(sbi->write_io[i]);
@@ -2482,10 +2482,9 @@ static int f2fs_set_context(struct inode *inode, const void *ctx, size_t len,
 				ctx, len, fs_data, XATTR_CREATE);
 }
 
-static const union fscrypt_context *
-f2fs_get_dummy_context(struct super_block *sb)
+static const union fscrypt_policy *f2fs_get_dummy_policy(struct super_block *sb)
 {
-	return F2FS_OPTION(F2FS_SB(sb)).dummy_enc_ctx.ctx;
+	return F2FS_OPTION(F2FS_SB(sb)).dummy_enc_policy.policy;
 }
 
 static bool f2fs_has_stable_inodes(struct super_block *sb)
@@ -2523,7 +2522,7 @@ static const struct fscrypt_operations f2fs_cryptops = {
 	.key_prefix		= "f2fs:",
 	.get_context		= f2fs_get_context,
 	.set_context		= f2fs_set_context,
-	.get_dummy_context	= f2fs_get_dummy_context,
+	.get_dummy_policy	= f2fs_get_dummy_policy,
 	.empty_dir		= f2fs_empty_dir,
 	.max_namelen		= F2FS_NAME_LEN,
 	.has_stable_inodes	= f2fs_has_stable_inodes,
@@ -3864,7 +3863,7 @@ free_options:
 	for (i = 0; i < MAXQUOTAS; i++)
 		kfree(F2FS_OPTION(sbi).s_qf_names[i]);
 #endif
-	fscrypt_free_dummy_context(&F2FS_OPTION(sbi).dummy_enc_ctx);
+	fscrypt_free_dummy_policy(&F2FS_OPTION(sbi).dummy_enc_policy);
 	kvfree(options);
 free_sb_buf:
 	kfree(raw_super);
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index 39e7397a3f10..b3b0c5675c6b 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -21,7 +21,7 @@
 
 #define FS_CRYPTO_BLOCK_SIZE		16
 
-union fscrypt_context;
+union fscrypt_policy;
 struct fscrypt_info;
 struct seq_file;
 
@@ -62,8 +62,7 @@ struct fscrypt_operations {
 	int (*get_context)(struct inode *inode, void *ctx, size_t len);
 	int (*set_context)(struct inode *inode, const void *ctx, size_t len,
 			   void *fs_data);
-	const union fscrypt_context *(*get_dummy_context)(
-		struct super_block *sb);
+	const union fscrypt_policy *(*get_dummy_policy)(struct super_block *sb);
 	bool (*empty_dir)(struct inode *inode);
 	unsigned int max_namelen;
 	bool (*has_stable_inodes)(struct super_block *sb);
@@ -101,14 +100,6 @@ static inline bool fscrypt_needs_contents_encryption(const struct inode *inode)
 	return IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode);
 }
 
-static inline const union fscrypt_context *
-fscrypt_get_dummy_context(struct super_block *sb)
-{
-	if (!sb->s_cop->get_dummy_context)
-		return NULL;
-	return sb->s_cop->get_dummy_context(sb);
-}
-
 /*
  * When d_splice_alias() moves a directory's encrypted alias to its decrypted
  * alias as a result of the encryption key being added, DCACHE_ENCRYPTED_NAME
@@ -158,20 +149,21 @@ int fscrypt_ioctl_get_nonce(struct file *filp, void __user *arg);
 int fscrypt_has_permitted_context(struct inode *parent, struct inode *child);
 int fscrypt_set_context(struct inode *inode, void *fs_data);
 
-struct fscrypt_dummy_context {
-	const union fscrypt_context *ctx;
+struct fscrypt_dummy_policy {
+	const union fscrypt_policy *policy;
 };
 
-int fscrypt_set_test_dummy_encryption(struct super_block *sb,
-				      const substring_t *arg,
-				      struct fscrypt_dummy_context *dummy_ctx);
+int fscrypt_set_test_dummy_encryption(
+				struct super_block *sb,
+				const substring_t *arg,
+				struct fscrypt_dummy_policy *dummy_policy);
 void fscrypt_show_test_dummy_encryption(struct seq_file *seq, char sep,
 					struct super_block *sb);
 static inline void
-fscrypt_free_dummy_context(struct fscrypt_dummy_context *dummy_ctx)
+fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy)
 {
-	kfree(dummy_ctx->ctx);
-	dummy_ctx->ctx = NULL;
+	kfree(dummy_policy->policy);
+	dummy_policy->policy = NULL;
 }
 
 /* keyring.c */
@@ -250,12 +242,6 @@ static inline bool fscrypt_needs_contents_encryption(const struct inode *inode)
 	return false;
 }
 
-static inline const union fscrypt_context *
-fscrypt_get_dummy_context(struct super_block *sb)
-{
-	return NULL;
-}
-
 static inline void fscrypt_handle_d_move(struct dentry *dentry)
 {
 }
@@ -346,7 +332,7 @@ static inline int fscrypt_set_context(struct inode *inode, void *fs_data)
 	return -EOPNOTSUPP;
 }
 
-struct fscrypt_dummy_context {
+struct fscrypt_dummy_policy {
 };
 
 static inline void fscrypt_show_test_dummy_encryption(struct seq_file *seq,
@@ -356,7 +342,7 @@ static inline void fscrypt_show_test_dummy_encryption(struct seq_file *seq,
 }
 
 static inline void
-fscrypt_free_dummy_context(struct fscrypt_dummy_context *dummy_ctx)
+fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy)
 {
 }
 
-- 
cgit v1.2.3


From c8c868abc91ff23f6f5c4444c419de7c277d77e1 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Wed, 16 Sep 2020 21:11:36 -0700
Subject: fscrypt: make fscrypt_set_test_dummy_encryption() take a 'const char
 *'

fscrypt_set_test_dummy_encryption() requires that the optional argument
to the test_dummy_encryption mount option be specified as a substring_t.
That doesn't work well with filesystems that use the new mount API,
since the new way of parsing mount options doesn't use substring_t.

Make it take the argument as a 'const char *' instead.

Instead of moving the match_strdup() into the callers in ext4 and f2fs,
make them just use arg->from directly.  Since the pattern is
"test_dummy_encryption=%s", the argument will be null-terminated.

Acked-by: Jeff Layton <jlayton@kernel.org>
Link: https://lore.kernel.org/r/20200917041136.178600-14-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 fs/crypto/policy.c      | 20 ++++++--------------
 fs/ext4/super.c         |  2 +-
 fs/f2fs/super.c         |  2 +-
 include/linux/fscrypt.h |  5 +----
 4 files changed, 9 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
index 97cf07543651..4441d9944b9e 100644
--- a/fs/crypto/policy.c
+++ b/fs/crypto/policy.c
@@ -697,8 +697,7 @@ EXPORT_SYMBOL_GPL(fscrypt_set_context);
 /**
  * fscrypt_set_test_dummy_encryption() - handle '-o test_dummy_encryption'
  * @sb: the filesystem on which test_dummy_encryption is being specified
- * @arg: the argument to the test_dummy_encryption option.
- *	 If no argument was specified, then @arg->from == NULL.
+ * @arg: the argument to the test_dummy_encryption option.  May be NULL.
  * @dummy_policy: the filesystem's current dummy policy (input/output, see
  *		  below)
  *
@@ -712,29 +711,23 @@ EXPORT_SYMBOL_GPL(fscrypt_set_context);
  *         -EEXIST if a different dummy policy is already set;
  *         or another -errno value.
  */
-int fscrypt_set_test_dummy_encryption(struct super_block *sb,
-				      const substring_t *arg,
+int fscrypt_set_test_dummy_encryption(struct super_block *sb, const char *arg,
 				      struct fscrypt_dummy_policy *dummy_policy)
 {
-	const char *argstr = "v2";
-	const char *argstr_to_free = NULL;
 	struct fscrypt_key_specifier key_spec = { 0 };
 	int version;
 	union fscrypt_policy *policy = NULL;
 	int err;
 
-	if (arg->from) {
-		argstr = argstr_to_free = match_strdup(arg);
-		if (!argstr)
-			return -ENOMEM;
-	}
+	if (!arg)
+		arg = "v2";
 
-	if (!strcmp(argstr, "v1")) {
+	if (!strcmp(arg, "v1")) {
 		version = FSCRYPT_POLICY_V1;
 		key_spec.type = FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR;
 		memset(key_spec.u.descriptor, 0x42,
 		       FSCRYPT_KEY_DESCRIPTOR_SIZE);
-	} else if (!strcmp(argstr, "v2")) {
+	} else if (!strcmp(arg, "v2")) {
 		version = FSCRYPT_POLICY_V2;
 		key_spec.type = FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER;
 		/* key_spec.u.identifier gets filled in when adding the key */
@@ -785,7 +778,6 @@ int fscrypt_set_test_dummy_encryption(struct super_block *sb,
 	err = 0;
 out:
 	kfree(policy);
-	kfree(argstr_to_free);
 	return err;
 }
 EXPORT_SYMBOL_GPL(fscrypt_set_test_dummy_encryption);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index aa6f64badf58..8b2736283481 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1892,7 +1892,7 @@ static int ext4_set_test_dummy_encryption(struct super_block *sb,
 			 "Can't set test_dummy_encryption on remount");
 		return -1;
 	}
-	err = fscrypt_set_test_dummy_encryption(sb, arg,
+	err = fscrypt_set_test_dummy_encryption(sb, arg->from,
 						&sbi->s_dummy_enc_policy);
 	if (err) {
 		if (err == -EEXIST)
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index f05ee33f5f26..bef2be3fa3d0 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -438,7 +438,7 @@ static int f2fs_set_test_dummy_encryption(struct super_block *sb,
 		return -EINVAL;
 	}
 	err = fscrypt_set_test_dummy_encryption(
-		sb, arg, &F2FS_OPTION(sbi).dummy_enc_policy);
+		sb, arg->from, &F2FS_OPTION(sbi).dummy_enc_policy);
 	if (err) {
 		if (err == -EEXIST)
 			f2fs_warn(sbi,
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index b3b0c5675c6b..fc67c4cbaa96 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -15,7 +15,6 @@
 
 #include <linux/fs.h>
 #include <linux/mm.h>
-#include <linux/parser.h>
 #include <linux/slab.h>
 #include <uapi/linux/fscrypt.h>
 
@@ -153,9 +152,7 @@ struct fscrypt_dummy_policy {
 	const union fscrypt_policy *policy;
 };
 
-int fscrypt_set_test_dummy_encryption(
-				struct super_block *sb,
-				const substring_t *arg,
+int fscrypt_set_test_dummy_encryption(struct super_block *sb, const char *arg,
 				struct fscrypt_dummy_policy *dummy_policy);
 void fscrypt_show_test_dummy_encryption(struct seq_file *seq, char sep,
 					struct super_block *sb);
-- 
cgit v1.2.3


From 10942019040c5557556ec22aae0f771b2a1a1a6d Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Tue, 1 Sep 2020 16:28:58 +0200
Subject: firmware: psci: Extend psci_set_osi_mode() to allow reset to PC mode

The current user (cpuidle-psci) of psci_set_osi_mode() only needs to enable
the PSCI OSI mode. Although, as subsequent changes shows, there is a need
to be able to reset back into the PSCI PC mode.

Therefore, let's extend psci_set_osi_mode() to take a bool as in-parameter,
to let the user indicate whether to enable OSI or to switch back to PC
mode.

Reviewed-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpuidle/cpuidle-psci-domain.c |  2 +-
 drivers/firmware/psci/psci.c          | 12 +++++++-----
 include/linux/psci.h                  |  2 +-
 3 files changed, 9 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/cpuidle/cpuidle-psci-domain.c b/drivers/cpuidle/cpuidle-psci-domain.c
index b6e9649ab0da..b6ab0415f450 100644
--- a/drivers/cpuidle/cpuidle-psci-domain.c
+++ b/drivers/cpuidle/cpuidle-psci-domain.c
@@ -278,7 +278,7 @@ static int psci_cpuidle_domain_probe(struct platform_device *pdev)
 		goto remove_pd;
 
 	/* Try to enable OSI mode. */
-	ret = psci_set_osi_mode();
+	ret = psci_set_osi_mode(true);
 	if (ret) {
 		pr_warn("failed to enable OSI mode: %d\n", ret);
 		psci_pd_remove_topology(np);
diff --git a/drivers/firmware/psci/psci.c b/drivers/firmware/psci/psci.c
index 92013ecc2d9e..00af99b6f97c 100644
--- a/drivers/firmware/psci/psci.c
+++ b/drivers/firmware/psci/psci.c
@@ -151,12 +151,15 @@ static u32 psci_get_version(void)
 	return invoke_psci_fn(PSCI_0_2_FN_PSCI_VERSION, 0, 0, 0);
 }
 
-int psci_set_osi_mode(void)
+int psci_set_osi_mode(bool enable)
 {
+	unsigned long suspend_mode;
 	int err;
 
-	err = invoke_psci_fn(PSCI_1_0_FN_SET_SUSPEND_MODE,
-			     PSCI_1_0_SUSPEND_MODE_OSI, 0, 0);
+	suspend_mode = enable ? PSCI_1_0_SUSPEND_MODE_OSI :
+			PSCI_1_0_SUSPEND_MODE_PC;
+
+	err = invoke_psci_fn(PSCI_1_0_FN_SET_SUSPEND_MODE, suspend_mode, 0, 0);
 	return psci_to_linux_errno(err);
 }
 
@@ -546,8 +549,7 @@ static int __init psci_1_0_init(struct device_node *np)
 		pr_info("OSI mode supported.\n");
 
 		/* Default to PC mode. */
-		invoke_psci_fn(PSCI_1_0_FN_SET_SUSPEND_MODE,
-			       PSCI_1_0_SUSPEND_MODE_PC, 0, 0);
+		psci_set_osi_mode(false);
 	}
 
 	return 0;
diff --git a/include/linux/psci.h b/include/linux/psci.h
index 14ad9b9ebcd6..2a1bfb890e58 100644
--- a/include/linux/psci.h
+++ b/include/linux/psci.h
@@ -18,7 +18,7 @@ bool psci_tos_resident_on(int cpu);
 
 int psci_cpu_suspend_enter(u32 state);
 bool psci_power_state_is_valid(u32 state);
-int psci_set_osi_mode(void);
+int psci_set_osi_mode(bool enable);
 bool psci_has_osi_support(void);
 
 struct psci_operations {
-- 
cgit v1.2.3


From 900ffe39fec908e0aa26a30612e43ebc7140db79 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Sat, 19 Sep 2020 01:09:36 -0700
Subject: x86/entry: Fix typo in comments for syscall_enter_from_user_mode()

Just to help myself and others with finding the correct function names,
fix a typo for "usermode" vs "user_mode".

Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200919080936.259819-1-keescook@chromium.org
---
 include/linux/entry-common.h | 2 +-
 kernel/entry/common.c        | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index efebbffcd5cc..3b6754d5a604 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -38,7 +38,7 @@
 #endif
 
 /*
- * TIF flags handled in syscall_enter_from_usermode()
+ * TIF flags handled in syscall_enter_from_user_mode()
  */
 #ifndef ARCH_SYSCALL_ENTER_WORK
 # define ARCH_SYSCALL_ENTER_WORK	(0)
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index fcae019158ca..7c7b9d00338a 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -183,7 +183,7 @@ static inline bool report_single_step(unsigned long ti_work)
 /*
  * If TIF_SYSCALL_EMU is set, then the only reason to report is when
  * TIF_SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP).  This syscall
- * instruction has been already reported in syscall_enter_from_usermode().
+ * instruction has been already reported in syscall_enter_from_user_mode().
  */
 #define SYSEMU_STEP	(_TIF_SINGLESTEP | _TIF_SYSCALL_EMU)
 
-- 
cgit v1.2.3


From 028abd9222df0cf5855dab5014a5ebaf06f90565 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 17 Sep 2020 10:22:34 +0200
Subject: fs: remove compat_sys_mount

compat_sys_mount is identical to the regular sys_mount now, so remove it
and use the native version everywhere.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/arm64/include/asm/unistd32.h                  |  2 +-
 arch/mips/kernel/syscalls/syscall_n32.tbl          |  2 +-
 arch/mips/kernel/syscalls/syscall_o32.tbl          |  2 +-
 arch/parisc/kernel/syscalls/syscall.tbl            |  2 +-
 arch/powerpc/kernel/syscalls/syscall.tbl           |  2 +-
 arch/s390/kernel/syscalls/syscall.tbl              |  2 +-
 arch/sparc/kernel/syscalls/syscall.tbl             |  2 +-
 arch/x86/entry/syscalls/syscall_32.tbl             |  2 +-
 fs/Makefile                                        |  1 -
 fs/compat.c                                        | 57 ----------------------
 fs/internal.h                                      |  3 --
 fs/namespace.c                                     |  4 +-
 include/linux/compat.h                             |  6 ---
 include/uapi/asm-generic/unistd.h                  |  2 +-
 tools/include/uapi/asm-generic/unistd.h            |  2 +-
 tools/perf/arch/powerpc/entry/syscalls/syscall.tbl |  2 +-
 tools/perf/arch/s390/entry/syscalls/syscall.tbl    |  2 +-
 17 files changed, 14 insertions(+), 81 deletions(-)
 delete mode 100644 fs/compat.c

(limited to 'include/linux')

diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 734860ac7cf9..5fd095d65450 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -53,7 +53,7 @@ __SYSCALL(__NR_lseek, compat_sys_lseek)
 #define __NR_getpid 20
 __SYSCALL(__NR_getpid, sys_getpid)
 #define __NR_mount 21
-__SYSCALL(__NR_mount, compat_sys_mount)
+__SYSCALL(__NR_mount, sys_mount)
 			/* 22 was sys_umount */
 __SYSCALL(22, sys_ni_syscall)
 #define __NR_setuid 23
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index f9df9edb67a4..61fa9e7013cb 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -167,7 +167,7 @@
 157	n32	sync				sys_sync
 158	n32	acct				sys_acct
 159	n32	settimeofday			compat_sys_settimeofday
-160	n32	mount				compat_sys_mount
+160	n32	mount				sys_mount
 161	n32	umount2				sys_umount
 162	n32	swapon				sys_swapon
 163	n32	swapoff				sys_swapoff
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 195b43cf27c8..b992e89be7ff 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -29,7 +29,7 @@
 18	o32	unused18			sys_ni_syscall
 19	o32	lseek				sys_lseek
 20	o32	getpid				sys_getpid
-21	o32	mount				sys_mount			compat_sys_mount
+21	o32	mount				sys_mount
 22	o32	umount				sys_oldumount
 23	o32	setuid				sys_setuid
 24	o32	getuid				sys_getuid
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index def64d221cd4..07efd978182f 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -29,7 +29,7 @@
 18	common	stat			sys_newstat			compat_sys_newstat
 19	common	lseek			sys_lseek			compat_sys_lseek
 20	common	getpid			sys_getpid
-21	common	mount			sys_mount			compat_sys_mount
+21	common	mount			sys_mount
 22	common	bind			sys_bind
 23	common	setuid			sys_setuid
 24	common	getuid			sys_getuid
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index c2d737ff2e7b..a36ad4fec73c 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -34,7 +34,7 @@
 18	spu	oldstat				sys_ni_syscall
 19	common	lseek				sys_lseek			compat_sys_lseek
 20	common	getpid				sys_getpid
-21	nospu	mount				sys_mount			compat_sys_mount
+21	nospu	mount				sys_mount
 22	32	umount				sys_oldumount
 22	64	umount				sys_ni_syscall
 22	spu	umount				sys_ni_syscall
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 10456bc936fb..4b803dfbee2b 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -26,7 +26,7 @@
 16   32		lchown			-				sys_lchown16
 19   common	lseek			sys_lseek			compat_sys_lseek
 20   common	getpid			sys_getpid			sys_getpid
-21   common	mount			sys_mount			compat_sys_mount
+21   common	mount			sys_mount			sys_mount
 22   common	umount			sys_oldumount			sys_oldumount
 23   32		setuid			-				sys_setuid16
 24   32		getuid			-				sys_getuid16
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index 4af114e84f20..d5ff798fa08f 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -201,7 +201,7 @@
 164	64	utrap_install		sys_utrap_install
 165	common	quotactl		sys_quotactl
 166	common	set_tid_address		sys_set_tid_address
-167	common	mount			sys_mount			compat_sys_mount
+167	common	mount			sys_mount
 168	common	ustat			sys_ustat			compat_sys_ustat
 169	common	setxattr		sys_setxattr
 170	common	lsetxattr		sys_lsetxattr
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 9d1102873666..5a40b226fb7b 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -32,7 +32,7 @@
 18	i386	oldstat			sys_stat
 19	i386	lseek			sys_lseek			compat_sys_lseek
 20	i386	getpid			sys_getpid
-21	i386	mount			sys_mount			compat_sys_mount
+21	i386	mount			sys_mount
 22	i386	umount			sys_oldumount
 23	i386	setuid			sys_setuid16
 24	i386	getuid			sys_getuid16
diff --git a/fs/Makefile b/fs/Makefile
index 1c7b0e3f6daa..d72ee2ce7af0 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -37,7 +37,6 @@ obj-$(CONFIG_FS_DAX)		+= dax.o
 obj-$(CONFIG_FS_ENCRYPTION)	+= crypto/
 obj-$(CONFIG_FS_VERITY)		+= verity/
 obj-$(CONFIG_FILE_LOCKING)      += locks.o
-obj-$(CONFIG_COMPAT)		+= compat.o
 obj-$(CONFIG_BINFMT_AOUT)	+= binfmt_aout.o
 obj-$(CONFIG_BINFMT_EM86)	+= binfmt_em86.o
 obj-$(CONFIG_BINFMT_MISC)	+= binfmt_misc.o
diff --git a/fs/compat.c b/fs/compat.c
deleted file mode 100644
index 9b00523d7fa5..000000000000
--- a/fs/compat.c
+++ /dev/null
@@ -1,57 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- *  linux/fs/compat.c
- *
- *  Kernel compatibililty routines for e.g. 32 bit syscall support
- *  on 64 bit kernels.
- *
- *  Copyright (C) 2002       Stephen Rothwell, IBM Corporation
- *  Copyright (C) 1997-2000  Jakub Jelinek  (jakub@redhat.com)
- *  Copyright (C) 1998       Eddie C. Dost  (ecd@skynet.be)
- *  Copyright (C) 2001,2002  Andi Kleen, SuSE Labs 
- *  Copyright (C) 2003       Pavel Machek (pavel@ucw.cz)
- */
-
-#include <linux/compat.h>
-#include <linux/nfs4_mount.h>
-#include <linux/syscalls.h>
-#include <linux/slab.h>
-#include <linux/uaccess.h>
-#include "internal.h"
-
-COMPAT_SYSCALL_DEFINE5(mount, const char __user *, dev_name,
-		       const char __user *, dir_name,
-		       const char __user *, type, compat_ulong_t, flags,
-		       const void __user *, data)
-{
-	char *kernel_type;
-	void *options;
-	char *kernel_dev;
-	int retval;
-
-	kernel_type = copy_mount_string(type);
-	retval = PTR_ERR(kernel_type);
-	if (IS_ERR(kernel_type))
-		goto out;
-
-	kernel_dev = copy_mount_string(dev_name);
-	retval = PTR_ERR(kernel_dev);
-	if (IS_ERR(kernel_dev))
-		goto out1;
-
-	options = copy_mount_options(data);
-	retval = PTR_ERR(options);
-	if (IS_ERR(options))
-		goto out2;
-
-	retval = do_mount(kernel_dev, dir_name, kernel_type, flags, options);
-
- out3:
-	kfree(options);
- out2:
-	kfree(kernel_dev);
- out1:
-	kfree(kernel_type);
- out:
-	return retval;
-}
diff --git a/fs/internal.h b/fs/internal.h
index 10517ece4516..a7cd0f64faa4 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -82,9 +82,6 @@ int may_linkat(struct path *link);
 /*
  * namespace.c
  */
-extern void *copy_mount_options(const void __user *);
-extern char *copy_mount_string(const void __user *);
-
 extern struct vfsmount *lookup_mnt(const struct path *);
 extern int finish_automount(struct vfsmount *, struct path *);
 
diff --git a/fs/namespace.c b/fs/namespace.c
index bae0e95b3713..12b431b61462 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -3072,7 +3072,7 @@ static void shrink_submounts(struct mount *mnt)
 	}
 }
 
-void *copy_mount_options(const void __user * data)
+static void *copy_mount_options(const void __user * data)
 {
 	char *copy;
 	unsigned size;
@@ -3097,7 +3097,7 @@ void *copy_mount_options(const void __user * data)
 	return copy;
 }
 
-char *copy_mount_string(const void __user *data)
+static char *copy_mount_string(const void __user *data)
 {
 	return data ? strndup_user(data, PATH_MAX) : NULL;
 }
diff --git a/include/linux/compat.h b/include/linux/compat.h
index d38c4d7e83bd..100632280ccc 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -522,12 +522,6 @@ asmlinkage long compat_sys_fcntl64(unsigned int fd, unsigned int cmd,
 asmlinkage long compat_sys_ioctl(unsigned int fd, unsigned int cmd,
 				 compat_ulong_t arg);
 
-/* fs/namespace.c */
-asmlinkage long compat_sys_mount(const char __user *dev_name,
-				 const char __user *dir_name,
-				 const char __user *type, compat_ulong_t flags,
-				 const void __user *data);
-
 /* fs/open.c */
 asmlinkage long compat_sys_statfs(const char __user *pathname,
 				  struct compat_statfs __user *buf);
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 995b36c2ea7d..fc98c9437609 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -140,7 +140,7 @@ __SYSCALL(__NR_renameat, sys_renameat)
 #define __NR_umount2 39
 __SYSCALL(__NR_umount2, sys_umount)
 #define __NR_mount 40
-__SC_COMP(__NR_mount, sys_mount, compat_sys_mount)
+__SYSCALL(__NR_mount, sys_mount)
 #define __NR_pivot_root 41
 __SYSCALL(__NR_pivot_root, sys_pivot_root)
 
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index 995b36c2ea7d..fc98c9437609 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -140,7 +140,7 @@ __SYSCALL(__NR_renameat, sys_renameat)
 #define __NR_umount2 39
 __SYSCALL(__NR_umount2, sys_umount)
 #define __NR_mount 40
-__SC_COMP(__NR_mount, sys_mount, compat_sys_mount)
+__SYSCALL(__NR_mount, sys_mount)
 #define __NR_pivot_root 41
 __SYSCALL(__NR_pivot_root, sys_pivot_root)
 
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index 3ca6fe057a0b..c2866c659650 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -32,7 +32,7 @@
 18	spu	oldstat				sys_ni_syscall
 19	common	lseek				sys_lseek			compat_sys_lseek
 20	common	getpid				sys_getpid
-21	nospu	mount				sys_mount			compat_sys_mount
+21	nospu	mount				sys_mount
 22	32	umount				sys_oldumount
 22	64	umount				sys_ni_syscall
 22	spu	umount				sys_ni_syscall
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index 6a0bbea225db..8e0806f6c38e 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -26,7 +26,7 @@
 16   32		lchown			-				compat_sys_s390_lchown16
 19   common	lseek			sys_lseek			compat_sys_lseek
 20   common	getpid			sys_getpid			sys_getpid
-21   common	mount			sys_mount			compat_sys_mount
+21   common	mount			sys_mount
 22   common	umount			sys_oldumount			compat_sys_oldumount
 23   32		setuid			-				compat_sys_s390_setuid16
 24   32		getuid			-				compat_sys_s390_getuid16
-- 
cgit v1.2.3


From dd87a72ae968f70852cd7a2d939acd9693e76095 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Mon, 21 Sep 2020 03:32:05 +0800
Subject: soundwire: enable Data Port test modes

Test modes are required for all SoundWire IP, and help debug
integration issues. In theory each port can be configured with a
different mode but to simplify this patch only offers separate
configurations for the Master and Slave ports - this covers 99% of the
intended cases during platform integration.

The test mode value is set via platform-specific ways.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Reviewed-by: Rander Wang <rander.wang@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20200920193207.31241-2-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/bus.c                          | 6 ++++++
 drivers/soundwire/generic_bandwidth_allocation.c | 6 ++++--
 drivers/soundwire/stream.c                       | 3 ++-
 include/linux/soundwire/sdw.h                    | 6 ++++++
 4 files changed, 18 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c
index 340fd1e23e5c..e3fe53f38708 100644
--- a/drivers/soundwire/bus.c
+++ b/drivers/soundwire/bus.c
@@ -1099,6 +1099,12 @@ int sdw_configure_dpn_intr(struct sdw_slave *slave,
 	int ret;
 	u8 val = 0;
 
+	if (slave->bus->params.s_data_mode != SDW_PORT_DATA_MODE_NORMAL) {
+		dev_dbg(&slave->dev, "TEST FAIL interrupt %s\n",
+			enable ? "on" : "off");
+		mask |= SDW_DPN_INT_TEST_FAIL;
+	}
+
 	addr = SDW_DPN_INTMASK(port);
 
 	/* Set/Clear port ready interrupt mask */
diff --git a/drivers/soundwire/generic_bandwidth_allocation.c b/drivers/soundwire/generic_bandwidth_allocation.c
index 6088775b67a5..058cb9cd8547 100644
--- a/drivers/soundwire/generic_bandwidth_allocation.c
+++ b/drivers/soundwire/generic_bandwidth_allocation.c
@@ -43,6 +43,7 @@ static void sdw_compute_slave_ports(struct sdw_master_runtime *m_rt,
 	int port_bo, sample_int;
 	unsigned int rate, bps, ch = 0;
 	unsigned int slave_total_ch;
+	struct sdw_bus_params *b_params = &m_rt->bus->params;
 
 	port_bo = t_data->block_offset;
 
@@ -66,7 +67,7 @@ static void sdw_compute_slave_ports(struct sdw_master_runtime *m_rt,
 			sdw_fill_port_params(&p_rt->port_params,
 					     p_rt->num, bps,
 					     SDW_PORT_FLOW_MODE_ISOCH,
-					     SDW_PORT_DATA_MODE_NORMAL);
+					     b_params->s_data_mode);
 
 			port_bo += bps * ch;
 			slave_total_ch += ch;
@@ -92,6 +93,7 @@ static void sdw_compute_master_ports(struct sdw_master_runtime *m_rt,
 	struct sdw_transport_data t_data = {0};
 	struct sdw_port_runtime *p_rt;
 	struct sdw_bus *bus = m_rt->bus;
+	struct sdw_bus_params *b_params = &bus->params;
 	int sample_int, hstart = 0;
 	unsigned int rate, bps, ch, no_ch;
 
@@ -118,7 +120,7 @@ static void sdw_compute_master_ports(struct sdw_master_runtime *m_rt,
 		sdw_fill_port_params(&p_rt->port_params,
 				     p_rt->num, bps,
 				     SDW_PORT_FLOW_MODE_ISOCH,
-				     SDW_PORT_DATA_MODE_NORMAL);
+				     b_params->m_data_mode);
 
 		/* Check for first entry */
 		if (!(p_rt == list_first_entry(&m_rt->port_list,
diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c
index f3219d1fa63b..8608b093abcc 100644
--- a/drivers/soundwire/stream.c
+++ b/drivers/soundwire/stream.c
@@ -443,7 +443,8 @@ static int sdw_prep_deprep_slave_ports(struct sdw_bus *bus,
 
 	prep_ch.bank = bus->params.next_bank;
 
-	if (dpn_prop->imp_def_interrupts || !dpn_prop->simple_ch_prep_sm)
+	if (dpn_prop->imp_def_interrupts || !dpn_prop->simple_ch_prep_sm ||
+	    bus->params.s_data_mode != SDW_PORT_DATA_MODE_NORMAL)
 		intr = true;
 
 	/*
diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index de9ea2ce2d35..41cc1192f9aa 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -554,6 +554,10 @@ enum sdw_port_prep_ops {
  * @bandwidth: Current bandwidth
  * @col: Active columns
  * @row: Active rows
+ * @s_data_mode: NORMAL, STATIC or PRBS mode for all Slave ports
+ * @m_data_mode: NORMAL, STATIC or PRBS mode for all Master ports. The value
+ * should be the same to detect transmission issues, but can be different to
+ * test the interrupt reports
  */
 struct sdw_bus_params {
 	enum sdw_reg_bank curr_bank;
@@ -563,6 +567,8 @@ struct sdw_bus_params {
 	unsigned int bandwidth;
 	unsigned int col;
 	unsigned int row;
+	int s_data_mode;
+	int m_data_mode;
 };
 
 /**
-- 
cgit v1.2.3


From f49735f4978f479b0de4f50ab217d5a56bc83c55 Mon Sep 17 00:00:00 2001
From: Lina Iyer <ilina@codeaurora.org>
Date: Tue, 22 Sep 2020 12:34:16 -0600
Subject: cpuidle: record state entry rejection statistics

CPUs may fail to enter the chosen idle state if there was a
pending interrupt, causing the cpuidle driver to return an error
value.

Record that and export it via sysfs along with the other idle state
statistics.

This could prove useful in understanding behavior of the governor
and the system during usecases that involve multiple CPUs.

Signed-off-by: Lina Iyer <ilina@codeaurora.org>
[ rjw: Changelog and documentation edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/admin-guide/pm/cpuidle.rst | 9 +++++++++
 drivers/cpuidle/cpuidle.c                | 1 +
 drivers/cpuidle/sysfs.c                  | 3 +++
 include/linux/cpuidle.h                  | 1 +
 4 files changed, 14 insertions(+)

(limited to 'include/linux')

diff --git a/Documentation/admin-guide/pm/cpuidle.rst b/Documentation/admin-guide/pm/cpuidle.rst
index a96a423e3779..830868e526f4 100644
--- a/Documentation/admin-guide/pm/cpuidle.rst
+++ b/Documentation/admin-guide/pm/cpuidle.rst
@@ -528,6 +528,10 @@ object corresponding to it, as follows:
 	Total number of times the hardware has been asked by the given CPU to
 	enter this idle state.
 
+``rejected``
+	Total number of times a request to enter this idle state on the given
+	CPU was rejected.
+
 The :file:`desc` and :file:`name` files both contain strings.  The difference
 between them is that the name is expected to be more concise, while the
 description may be longer and it may contain white space or special characters.
@@ -572,6 +576,11 @@ particular case.  For these reasons, the only reliable way to find out how
 much time has been spent by the hardware in different idle states supported by
 it is to use idle state residency counters in the hardware, if available.
 
+Generally, an interrupt received when trying to enter an idle state causes the
+idle state entry request to be rejected, in which case the ``CPUIdle`` driver
+may return an error code to indicate that this was the case. The :file:`usage`
+and :file:`rejected` files report the number of times the given idle state
+was entered successfully or rejected, respectively.
 
 .. _cpu-pm-qos:
 
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 6c7e5621cf9a..0ed5030b89d6 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -307,6 +307,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 		}
 	} else {
 		dev->last_residency_ns = 0;
+		dev->states_usage[index].rejected++;
 	}
 
 	return entered_state;
diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c
index 091d1caceb41..53ec9585ccd4 100644
--- a/drivers/cpuidle/sysfs.c
+++ b/drivers/cpuidle/sysfs.c
@@ -256,6 +256,7 @@ define_show_state_time_function(exit_latency)
 define_show_state_time_function(target_residency)
 define_show_state_function(power_usage)
 define_show_state_ull_function(usage)
+define_show_state_ull_function(rejected)
 define_show_state_str_function(name)
 define_show_state_str_function(desc)
 define_show_state_ull_function(above)
@@ -312,6 +313,7 @@ define_one_state_ro(latency, show_state_exit_latency);
 define_one_state_ro(residency, show_state_target_residency);
 define_one_state_ro(power, show_state_power_usage);
 define_one_state_ro(usage, show_state_usage);
+define_one_state_ro(rejected, show_state_rejected);
 define_one_state_ro(time, show_state_time);
 define_one_state_rw(disable, show_state_disable, store_state_disable);
 define_one_state_ro(above, show_state_above);
@@ -325,6 +327,7 @@ static struct attribute *cpuidle_state_default_attrs[] = {
 	&attr_residency.attr,
 	&attr_power.attr,
 	&attr_usage.attr,
+	&attr_rejected.attr,
 	&attr_time.attr,
 	&attr_disable.attr,
 	&attr_above.attr,
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 6175c77bf25e..ed0da0e58e8b 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -38,6 +38,7 @@ struct cpuidle_state_usage {
 	u64			time_ns;
 	unsigned long long	above; /* Number of times it's been too deep */
 	unsigned long long	below; /* Number of times it's been too shallow */
+	unsigned long long	rejected; /* Number of times idle entry was rejected */
 #ifdef CONFIG_SUSPEND
 	unsigned long long	s2idle_usage;
 	unsigned long long	s2idle_time; /* in US */
-- 
cgit v1.2.3


From 07d098e6bbad04030dab5b3e64149601fcb063ce Mon Sep 17 00:00:00 2001
From: Mike Snitzer <snitzer@redhat.com>
Date: Mon, 21 Sep 2020 22:32:49 -0400
Subject: block: allow 'chunk_sectors' to be non-power-of-2

It is possible, albeit more unlikely, for a block device to have a non
power-of-2 for chunk_sectors (e.g. 10+2 RAID6 with 128K chunk_sectors,
which results in a full-stripe size of 1280K. This causes the RAID6's
io_opt to be advertised as 1280K, and a stacked device _could_ then be
made to use a blocksize, aka chunk_sectors, that matches non power-of-2
io_opt of underlying RAID6 -- resulting in stacked device's
chunk_sectors being a non power-of-2).

Update blk_queue_chunk_sectors() and blk_max_size_offset() to
accommodate drivers that need a non power-of-2 chunk_sectors.

Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-settings.c   | 10 ++++------
 include/linux/blkdev.h | 12 +++++++++---
 2 files changed, 13 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-settings.c b/block/blk-settings.c
index b2e1a929a6db..5ea3de48afba 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -172,15 +172,13 @@ EXPORT_SYMBOL(blk_queue_max_hw_sectors);
  *
  * Description:
  *    If a driver doesn't want IOs to cross a given chunk size, it can set
- *    this limit and prevent merging across chunks. Note that the chunk size
- *    must currently be a power-of-2 in sectors. Also note that the block
- *    layer must accept a page worth of data at any offset. So if the
- *    crossing of chunks is a hard limitation in the driver, it must still be
- *    prepared to split single page bios.
+ *    this limit and prevent merging across chunks. Note that the block layer
+ *    must accept a page worth of data at any offset. So if the crossing of
+ *    chunks is a hard limitation in the driver, it must still be prepared
+ *    to split single page bios.
  **/
 void blk_queue_chunk_sectors(struct request_queue *q, unsigned int chunk_sectors)
 {
-	BUG_ON(!is_power_of_2(chunk_sectors));
 	q->limits.chunk_sectors = chunk_sectors;
 }
 EXPORT_SYMBOL(blk_queue_chunk_sectors);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 5bd96fbab9b4..6e19a7aa1672 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1063,11 +1063,17 @@ static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
 static inline unsigned int blk_max_size_offset(struct request_queue *q,
 					       sector_t offset)
 {
-	if (!q->limits.chunk_sectors)
+	unsigned int chunk_sectors = q->limits.chunk_sectors;
+
+	if (!chunk_sectors)
 		return q->limits.max_sectors;
 
-	return min(q->limits.max_sectors, (unsigned int)(q->limits.chunk_sectors -
-			(offset & (q->limits.chunk_sectors - 1))));
+	if (likely(is_power_of_2(chunk_sectors)))
+		chunk_sectors -= offset & (chunk_sectors - 1);
+	else
+		chunk_sectors -= sector_div(offset, chunk_sectors);
+
+	return min(q->limits.max_sectors, chunk_sectors);
 }
 
 static inline unsigned int blk_rq_get_max_sectors(struct request *rq,
-- 
cgit v1.2.3


From 1967f712677429f52ac3e8896b5ecfecc2372d95 Mon Sep 17 00:00:00 2001
From: Zbigniew Lukwinski <zbigniew.lukwinski@linux.intel.com>
Date: Fri, 31 Jul 2020 21:37:16 +0200
Subject: hwmon: (core) Add support for rated attributes

Adding implementation for new attributes (rated_min/rated_max) for
currentX, inX, powerX, tempX and humidityX.

Tested with OpenBMC stack and simple hwmon driver using
rated_min/rated_max for the following types of sensors: hwmon_temp,
hwmon_in, hwmon_curr, hwmon_power, hwmon_humidity.
For each sensor rated attributes were available and returned
expected values.

Signed-off-by: Zbigniew Lukwinski <zbigniew.lukwinski@linux.intel.com>
Link: https://lore.kernel.org/r/1596224237-32280-3-git-send-email-zbigniew.lukwinski@linux.intel.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/hwmon.c | 10 ++++++++++
 include/linux/hwmon.h | 20 ++++++++++++++++++++
 2 files changed, 30 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c
index 3f596a5328da..6c684058bfdf 100644
--- a/drivers/hwmon/hwmon.c
+++ b/drivers/hwmon/hwmon.c
@@ -431,6 +431,8 @@ static const char * const hwmon_temp_attr_templates[] = {
 	[hwmon_temp_lowest] = "temp%d_lowest",
 	[hwmon_temp_highest] = "temp%d_highest",
 	[hwmon_temp_reset_history] = "temp%d_reset_history",
+	[hwmon_temp_rated_min] = "temp%d_rated_min",
+	[hwmon_temp_rated_max] = "temp%d_rated_max",
 };
 
 static const char * const hwmon_in_attr_templates[] = {
@@ -450,6 +452,8 @@ static const char * const hwmon_in_attr_templates[] = {
 	[hwmon_in_max_alarm] = "in%d_max_alarm",
 	[hwmon_in_lcrit_alarm] = "in%d_lcrit_alarm",
 	[hwmon_in_crit_alarm] = "in%d_crit_alarm",
+	[hwmon_in_rated_min] = "in%d_rated_min",
+	[hwmon_in_rated_max] = "in%d_rated_max",
 };
 
 static const char * const hwmon_curr_attr_templates[] = {
@@ -469,6 +473,8 @@ static const char * const hwmon_curr_attr_templates[] = {
 	[hwmon_curr_max_alarm] = "curr%d_max_alarm",
 	[hwmon_curr_lcrit_alarm] = "curr%d_lcrit_alarm",
 	[hwmon_curr_crit_alarm] = "curr%d_crit_alarm",
+	[hwmon_curr_rated_min] = "curr%d_rated_min",
+	[hwmon_curr_rated_max] = "curr%d_rated_max",
 };
 
 static const char * const hwmon_power_attr_templates[] = {
@@ -501,6 +507,8 @@ static const char * const hwmon_power_attr_templates[] = {
 	[hwmon_power_max_alarm] = "power%d_max_alarm",
 	[hwmon_power_lcrit_alarm] = "power%d_lcrit_alarm",
 	[hwmon_power_crit_alarm] = "power%d_crit_alarm",
+	[hwmon_power_rated_min] = "power%d_rated_min",
+	[hwmon_power_rated_max] = "power%d_rated_max",
 };
 
 static const char * const hwmon_energy_attr_templates[] = {
@@ -519,6 +527,8 @@ static const char * const hwmon_humidity_attr_templates[] = {
 	[hwmon_humidity_max_hyst] = "humidity%d_max_hyst",
 	[hwmon_humidity_alarm] = "humidity%d_alarm",
 	[hwmon_humidity_fault] = "humidity%d_fault",
+	[hwmon_humidity_rated_min] = "humidity%d_rated_min",
+	[hwmon_humidity_rated_max] = "humidity%d_rated_max",
 };
 
 static const char * const hwmon_fan_attr_templates[] = {
diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h
index 363d4a814aa1..1e8d6ea8992e 100644
--- a/include/linux/hwmon.h
+++ b/include/linux/hwmon.h
@@ -85,6 +85,8 @@ enum hwmon_temp_attributes {
 	hwmon_temp_lowest,
 	hwmon_temp_highest,
 	hwmon_temp_reset_history,
+	hwmon_temp_rated_min,
+	hwmon_temp_rated_max,
 };
 
 #define HWMON_T_ENABLE		BIT(hwmon_temp_enable)
@@ -112,6 +114,8 @@ enum hwmon_temp_attributes {
 #define HWMON_T_LOWEST		BIT(hwmon_temp_lowest)
 #define HWMON_T_HIGHEST		BIT(hwmon_temp_highest)
 #define HWMON_T_RESET_HISTORY	BIT(hwmon_temp_reset_history)
+#define HWMON_T_RATED_MIN	BIT(hwmon_temp_rated_min)
+#define HWMON_T_RATED_MAX	BIT(hwmon_temp_rated_max)
 
 enum hwmon_in_attributes {
 	hwmon_in_enable,
@@ -130,6 +134,8 @@ enum hwmon_in_attributes {
 	hwmon_in_max_alarm,
 	hwmon_in_lcrit_alarm,
 	hwmon_in_crit_alarm,
+	hwmon_in_rated_min,
+	hwmon_in_rated_max,
 };
 
 #define HWMON_I_ENABLE		BIT(hwmon_in_enable)
@@ -148,6 +154,8 @@ enum hwmon_in_attributes {
 #define HWMON_I_MAX_ALARM	BIT(hwmon_in_max_alarm)
 #define HWMON_I_LCRIT_ALARM	BIT(hwmon_in_lcrit_alarm)
 #define HWMON_I_CRIT_ALARM	BIT(hwmon_in_crit_alarm)
+#define HWMON_I_RATED_MIN	BIT(hwmon_in_rated_min)
+#define HWMON_I_RATED_MAX	BIT(hwmon_in_rated_max)
 
 enum hwmon_curr_attributes {
 	hwmon_curr_enable,
@@ -166,6 +174,8 @@ enum hwmon_curr_attributes {
 	hwmon_curr_max_alarm,
 	hwmon_curr_lcrit_alarm,
 	hwmon_curr_crit_alarm,
+	hwmon_curr_rated_min,
+	hwmon_curr_rated_max,
 };
 
 #define HWMON_C_ENABLE		BIT(hwmon_curr_enable)
@@ -184,6 +194,8 @@ enum hwmon_curr_attributes {
 #define HWMON_C_MAX_ALARM	BIT(hwmon_curr_max_alarm)
 #define HWMON_C_LCRIT_ALARM	BIT(hwmon_curr_lcrit_alarm)
 #define HWMON_C_CRIT_ALARM	BIT(hwmon_curr_crit_alarm)
+#define HWMON_C_RATED_MIN	BIT(hwmon_curr_rated_min)
+#define HWMON_C_RATED_MAX	BIT(hwmon_curr_rated_max)
 
 enum hwmon_power_attributes {
 	hwmon_power_enable,
@@ -215,6 +227,8 @@ enum hwmon_power_attributes {
 	hwmon_power_max_alarm,
 	hwmon_power_lcrit_alarm,
 	hwmon_power_crit_alarm,
+	hwmon_power_rated_min,
+	hwmon_power_rated_max,
 };
 
 #define HWMON_P_ENABLE			BIT(hwmon_power_enable)
@@ -246,6 +260,8 @@ enum hwmon_power_attributes {
 #define HWMON_P_MAX_ALARM		BIT(hwmon_power_max_alarm)
 #define HWMON_P_LCRIT_ALARM		BIT(hwmon_power_lcrit_alarm)
 #define HWMON_P_CRIT_ALARM		BIT(hwmon_power_crit_alarm)
+#define HWMON_P_RATED_MIN		BIT(hwmon_power_rated_min)
+#define HWMON_P_RATED_MAX		BIT(hwmon_power_rated_max)
 
 enum hwmon_energy_attributes {
 	hwmon_energy_enable,
@@ -267,6 +283,8 @@ enum hwmon_humidity_attributes {
 	hwmon_humidity_max_hyst,
 	hwmon_humidity_alarm,
 	hwmon_humidity_fault,
+	hwmon_humidity_rated_min,
+	hwmon_humidity_rated_max,
 };
 
 #define HWMON_H_ENABLE			BIT(hwmon_humidity_enable)
@@ -278,6 +296,8 @@ enum hwmon_humidity_attributes {
 #define HWMON_H_MAX_HYST		BIT(hwmon_humidity_max_hyst)
 #define HWMON_H_ALARM			BIT(hwmon_humidity_alarm)
 #define HWMON_H_FAULT			BIT(hwmon_humidity_fault)
+#define HWMON_H_RATED_MIN		BIT(hwmon_humidity_rated_min)
+#define HWMON_H_RATED_MAX		BIT(hwmon_humidity_rated_max)
 
 enum hwmon_fan_attributes {
 	hwmon_fan_enable,
-- 
cgit v1.2.3


From 7497d4a66c596fc8312cafe1b8d1e76ad2bc34c3 Mon Sep 17 00:00:00 2001
From: Tim Harvey <tharvey@gateworks.com>
Date: Thu, 27 Aug 2020 13:04:54 -0700
Subject: hwmon: (gsc-hwmon) add fan sensor

Add a fan sensor to report RPM's from a fan tach input.

Signed-off-by: Tim Harvey <tharvey@gateworks.com>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/gsc-hwmon.c               | 32 +++++++++++++++++++++++++++++---
 include/linux/platform_data/gsc_hwmon.h |  1 +
 2 files changed, 30 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/hwmon/gsc-hwmon.c b/drivers/hwmon/gsc-hwmon.c
index c6d4567f3952..1fe37418ff46 100644
--- a/drivers/hwmon/gsc-hwmon.c
+++ b/drivers/hwmon/gsc-hwmon.c
@@ -17,6 +17,7 @@
 
 #define GSC_HWMON_MAX_TEMP_CH	16
 #define GSC_HWMON_MAX_IN_CH	16
+#define GSC_HWMON_MAX_FAN_CH	16
 
 #define GSC_HWMON_RESOLUTION	12
 #define GSC_HWMON_VREF		2500
@@ -27,11 +28,14 @@ struct gsc_hwmon_data {
 	struct regmap *regmap;
 	const struct gsc_hwmon_channel *temp_ch[GSC_HWMON_MAX_TEMP_CH];
 	const struct gsc_hwmon_channel *in_ch[GSC_HWMON_MAX_IN_CH];
+	const struct gsc_hwmon_channel *fan_ch[GSC_HWMON_MAX_FAN_CH];
 	u32 temp_config[GSC_HWMON_MAX_TEMP_CH + 1];
 	u32 in_config[GSC_HWMON_MAX_IN_CH + 1];
+	u32 fan_config[GSC_HWMON_MAX_FAN_CH + 1];
 	struct hwmon_channel_info temp_info;
 	struct hwmon_channel_info in_info;
-	const struct hwmon_channel_info *info[3];
+	struct hwmon_channel_info fan_info;
+	const struct hwmon_channel_info *info[4];
 	struct hwmon_chip_info chip;
 };
 
@@ -155,6 +159,9 @@ gsc_hwmon_read(struct device *dev, enum hwmon_sensor_types type, u32 attr,
 	case hwmon_temp:
 		ch = hwmon->temp_ch[channel];
 		break;
+	case hwmon_fan:
+		ch = hwmon->fan_ch[channel];
+		break;
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -187,6 +194,9 @@ gsc_hwmon_read(struct device *dev, enum hwmon_sensor_types type, u32 attr,
 		/* adjust by uV offset */
 		tmp += ch->mvoffset;
 		break;
+	case mode_fan:
+		tmp *= 30; /* convert to revolutions per minute */
+		break;
 	case mode_voltage_24bit:
 	case mode_voltage_16bit:
 		/* no adjustment needed */
@@ -211,6 +221,9 @@ gsc_hwmon_read_string(struct device *dev, enum hwmon_sensor_types type,
 	case hwmon_temp:
 		*buf = hwmon->temp_ch[channel]->name;
 		break;
+	case hwmon_fan:
+		*buf = hwmon->fan_ch[channel]->name;
+		break;
 	default:
 		return -ENOTSUPP;
 	}
@@ -304,7 +317,7 @@ static int gsc_hwmon_probe(struct platform_device *pdev)
 	struct gsc_hwmon_platform_data *pdata = dev_get_platdata(dev);
 	struct gsc_hwmon_data *hwmon;
 	const struct attribute_group **groups;
-	int i, i_in, i_temp;
+	int i, i_in, i_temp, i_fan;
 
 	if (!pdata) {
 		pdata = gsc_hwmon_get_devtree_pdata(dev);
@@ -324,7 +337,7 @@ static int gsc_hwmon_probe(struct platform_device *pdev)
 	if (IS_ERR(hwmon->regmap))
 		return PTR_ERR(hwmon->regmap);
 
-	for (i = 0, i_in = 0, i_temp = 0; i < hwmon->pdata->nchannels; i++) {
+	for (i = 0, i_in = 0, i_temp = 0, i_fan = 0; i < hwmon->pdata->nchannels; i++) {
 		const struct gsc_hwmon_channel *ch = &pdata->channels[i];
 
 		switch (ch->mode) {
@@ -338,6 +351,16 @@ static int gsc_hwmon_probe(struct platform_device *pdev)
 						     HWMON_T_LABEL;
 			i_temp++;
 			break;
+		case mode_fan:
+			if (i_fan == GSC_HWMON_MAX_FAN_CH) {
+				dev_err(gsc->dev, "too many fan channels\n");
+				return -EINVAL;
+			}
+			hwmon->fan_ch[i_fan] = ch;
+			hwmon->fan_config[i_fan] = HWMON_F_INPUT |
+						   HWMON_F_LABEL;
+			i_fan++;
+			break;
 		case mode_voltage_24bit:
 		case mode_voltage_16bit:
 		case mode_voltage_raw:
@@ -361,10 +384,13 @@ static int gsc_hwmon_probe(struct platform_device *pdev)
 	hwmon->chip.info = hwmon->info;
 	hwmon->info[0] = &hwmon->temp_info;
 	hwmon->info[1] = &hwmon->in_info;
+	hwmon->info[2] = &hwmon->fan_info;
 	hwmon->temp_info.type = hwmon_temp;
 	hwmon->temp_info.config = hwmon->temp_config;
 	hwmon->in_info.type = hwmon_in;
 	hwmon->in_info.config = hwmon->in_config;
+	hwmon->fan_info.type = hwmon_fan;
+	hwmon->fan_info.config = hwmon->fan_config;
 
 	groups = pdata->fan_base ? gsc_hwmon_groups : NULL;
 	hwmon_dev = devm_hwmon_device_register_with_info(dev,
diff --git a/include/linux/platform_data/gsc_hwmon.h b/include/linux/platform_data/gsc_hwmon.h
index 37a8f554da00..281f499eda97 100644
--- a/include/linux/platform_data/gsc_hwmon.h
+++ b/include/linux/platform_data/gsc_hwmon.h
@@ -7,6 +7,7 @@ enum gsc_hwmon_mode {
 	mode_voltage_24bit,
 	mode_voltage_raw,
 	mode_voltage_16bit,
+	mode_fan,
 	mode_max,
 };
 
-- 
cgit v1.2.3


From 38430f0876fa8b9549ec434f569dce03e057c076 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 21 Sep 2020 09:19:45 +0200
Subject: block: move the NEED_PART_SCAN flag to struct gendisk

We can only scan for partitions on the whole disk, so move the flag
from struct block_device to struct gendisk.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/genhd.c             | 4 ++--
 drivers/block/nbd.c       | 8 ++++----
 drivers/ide/ide-gd.c      | 2 +-
 fs/block_dev.c            | 7 +++----
 include/linux/blk_types.h | 4 +---
 include/linux/genhd.h     | 2 ++
 6 files changed, 13 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/block/genhd.c b/block/genhd.c
index 9d060e79eb31..7b56203c90a3 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -731,7 +731,7 @@ static void register_disk(struct device *parent, struct gendisk *disk,
 	if (!bdev)
 		goto exit;
 
-	set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
+	set_bit(GD_NEED_PART_SCAN, &disk->state);
 	err = blkdev_get(bdev, FMODE_READ, NULL);
 	if (err < 0)
 		goto exit;
@@ -2112,7 +2112,7 @@ bool bdev_check_media_change(struct block_device *bdev)
 	if (__invalidate_device(bdev, true))
 		pr_warn("VFS: busy inodes on changed media %s\n",
 			bdev->bd_disk->disk_name);
-	set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
+	set_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state);
 	return true;
 }
 EXPORT_SYMBOL(bdev_check_media_change);
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 15eed210feef..2dca0aab0a9a 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -315,7 +315,7 @@ static void nbd_size_update(struct nbd_device *nbd)
 			bd_set_nr_sectors(bdev, nr_sectors);
 			set_blocksize(bdev, config->blksize);
 		} else
-			set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
+			set_bit(GD_NEED_PART_SCAN, &nbd->disk->state);
 		bdput(bdev);
 	}
 	kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE);
@@ -1322,7 +1322,7 @@ static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *b
 		return ret;
 
 	if (max_part)
-		set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
+		set_bit(GD_NEED_PART_SCAN, &nbd->disk->state);
 	mutex_unlock(&nbd->config_lock);
 	ret = wait_event_interruptible(config->recv_wq,
 					 atomic_read(&config->recv_threads) == 0);
@@ -1500,9 +1500,9 @@ static int nbd_open(struct block_device *bdev, fmode_t mode)
 		refcount_set(&nbd->config_refs, 1);
 		refcount_inc(&nbd->refs);
 		mutex_unlock(&nbd->config_lock);
-		set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
+		set_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state);
 	} else if (nbd_disconnected(nbd->config)) {
-		set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
+		set_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state);
 	}
 out:
 	mutex_unlock(&nbd_index_mutex);
diff --git a/drivers/ide/ide-gd.c b/drivers/ide/ide-gd.c
index 661e2aa9c967..e2b6c82586ce 100644
--- a/drivers/ide/ide-gd.c
+++ b/drivers/ide/ide-gd.c
@@ -230,7 +230,7 @@ static int ide_gd_open(struct block_device *bdev, fmode_t mode)
 				bdev->bd_disk->disk_name);
 		drive->disk_ops->get_capacity(drive);
 		set_capacity(disk, ide_gd_capacity(drive));
-		set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
+		set_bit(GD_NEED_PART_SCAN, &disk->state);
 	} else if (drive->dev_flags & IDE_DFLAG_FORMAT_IN_PROGRESS) {
 		ret = -EBUSY;
 		goto out_put_idkp;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 0b34955b9e36..1a9325f43157 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -910,7 +910,6 @@ struct block_device *bdget(dev_t dev)
 		bdev->bd_super = NULL;
 		bdev->bd_inode = inode;
 		bdev->bd_part_count = 0;
-		bdev->bd_flags = 0;
 		inode->i_mode = S_IFBLK;
 		inode->i_rdev = dev;
 		inode->i_bdev = bdev;
@@ -1385,7 +1384,7 @@ int bdev_disk_changed(struct block_device *bdev, bool invalidate)
 
 	lockdep_assert_held(&bdev->bd_mutex);
 
-	clear_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
+	clear_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state);
 
 rescan:
 	ret = blk_drop_partitions(bdev);
@@ -1509,7 +1508,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder,
 			 * The latter is necessary to prevent ghost
 			 * partitions on a removed medium.
 			 */
-			if (test_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags) &&
+			if (test_bit(GD_NEED_PART_SCAN, &disk->state) &&
 			    (!ret || ret == -ENOMEDIUM))
 				bdev_disk_changed(bdev, ret == -ENOMEDIUM);
 
@@ -1539,7 +1538,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder,
 			if (bdev->bd_disk->fops->open)
 				ret = bdev->bd_disk->fops->open(bdev, mode);
 			/* the same as first opener case, read comment there */
-			if (test_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags) &&
+			if (test_bit(GD_NEED_PART_SCAN, &disk->state) &&
 			    (!ret || ret == -ENOMEDIUM))
 				bdev_disk_changed(bdev, ret == -ENOMEDIUM);
 			if (ret)
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 6ffa783e1633..eb20e28184ab 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -19,8 +19,6 @@ struct cgroup_subsys_state;
 typedef void (bio_end_io_t) (struct bio *);
 struct bio_crypt_ctx;
 
-#define BDEV_NEED_PART_SCAN		0
-
 struct block_device {
 	dev_t			bd_dev;
 	int			bd_openers;
@@ -39,7 +37,7 @@ struct block_device {
 	struct hd_struct *	bd_part;
 	/* number of times partitions within this device have been opened. */
 	unsigned		bd_part_count;
-	unsigned long		bd_flags;
+
 	spinlock_t		bd_size_lock; /* for bd_inode->i_size updates */
 	struct gendisk *	bd_disk;
 	struct backing_dev_info *bd_bdi;
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 1c97cf84f011..38f23d757013 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -191,6 +191,8 @@ struct gendisk {
 	void *private_data;
 
 	int flags;
+	unsigned long state;
+#define GD_NEED_PART_SCAN		0
 	struct rw_semaphore lookup_sem;
 	struct kobject *slave_dir;
 
-- 
cgit v1.2.3


From bb3247a399801ebba20bef101c89e563f5fe7f02 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 21 Sep 2020 09:19:55 +0200
Subject: PM: rewrite is_hibernate_resume_dev to not require an inode

Just check the dev_t to help simplifying the code.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/block_dev.c          |  2 +-
 include/linux/suspend.h |  4 ++--
 kernel/power/user.c     | 12 ++++++------
 3 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 1a9325f43157..2898d69be6b3 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1885,7 +1885,7 @@ ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (bdev_read_only(I_BDEV(bd_inode)))
 		return -EPERM;
 
-	if (IS_SWAPFILE(bd_inode) && !is_hibernate_resume_dev(bd_inode))
+	if (IS_SWAPFILE(bd_inode) && !is_hibernate_resume_dev(bd_inode->i_rdev))
 		return -ETXTBSY;
 
 	if (!iov_iter_count(from))
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index cb9afad82a90..8af13ba60c7e 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -473,9 +473,9 @@ static inline int hibernate_quiet_exec(int (*func)(void *data), void *data) {
 #endif /* CONFIG_HIBERNATION */
 
 #ifdef CONFIG_HIBERNATION_SNAPSHOT_DEV
-int is_hibernate_resume_dev(const struct inode *);
+int is_hibernate_resume_dev(dev_t dev);
 #else
-static inline int is_hibernate_resume_dev(const struct inode *i) { return 0; }
+static inline int is_hibernate_resume_dev(dev_t dev) { return 0; }
 #endif
 
 /* Hibernation and suspend events */
diff --git a/kernel/power/user.c b/kernel/power/user.c
index d5eedc2baa2a..b5815685b944 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -35,12 +35,12 @@ static struct snapshot_data {
 	bool ready;
 	bool platform_support;
 	bool free_bitmaps;
-	struct inode *bd_inode;
+	dev_t dev;
 } snapshot_state;
 
-int is_hibernate_resume_dev(const struct inode *bd_inode)
+int is_hibernate_resume_dev(dev_t dev)
 {
-	return hibernation_available() && snapshot_state.bd_inode == bd_inode;
+	return hibernation_available() && snapshot_state.dev == dev;
 }
 
 static int snapshot_open(struct inode *inode, struct file *filp)
@@ -101,7 +101,7 @@ static int snapshot_open(struct inode *inode, struct file *filp)
 	data->frozen = false;
 	data->ready = false;
 	data->platform_support = false;
-	data->bd_inode = NULL;
+	data->dev = 0;
 
  Unlock:
 	unlock_system_sleep();
@@ -117,7 +117,7 @@ static int snapshot_release(struct inode *inode, struct file *filp)
 
 	swsusp_free();
 	data = filp->private_data;
-	data->bd_inode = NULL;
+	data->dev = 0;
 	free_all_swap_pages(data->swap);
 	if (data->frozen) {
 		pm_restore_gfp_mask();
@@ -245,7 +245,7 @@ static int snapshot_set_swap_area(struct snapshot_data *data,
 	if (data->swap < 0)
 		return -ENODEV;
 
-	data->bd_inode = bdev->bd_inode;
+	data->dev = bdev->bd_dev;
 	bdput(bdev);
 	return 0;
 }
-- 
cgit v1.2.3


From 21bd900572f3708e281ea25f051fc92462eb1193 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 21 Sep 2020 09:19:56 +0200
Subject: mm: split swap_type_of

swap_type_of is used for two entirely different purposes:

 (1) check what swap type a given device/offset corresponds to
 (2) find the first available swap device that can be written to

Mixing both in a single function creates an unreadable mess.  Create two
separate functions instead, and switch both to pass a dev_t instead of
a struct block_device to further simplify the code.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/swap.h |  3 ++-
 kernel/power/swap.c  | 17 ++++++++---------
 kernel/power/user.c  | 16 ++++------------
 mm/swapfile.c        | 39 +++++++++++++++++++++------------------
 4 files changed, 35 insertions(+), 40 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 661046994db4..4340a7b6e7a1 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -467,7 +467,8 @@ extern int swapcache_prepare(swp_entry_t);
 extern void swap_free(swp_entry_t);
 extern void swapcache_free_entries(swp_entry_t *entries, int n);
 extern int free_swap_and_cache(swp_entry_t);
-extern int swap_type_of(dev_t, sector_t, struct block_device **);
+int swap_type_of(dev_t device, sector_t offset);
+int find_first_swap(dev_t *device);
 extern unsigned int count_swap_pages(int, int);
 extern sector_t map_swap_page(struct page *, struct block_device **);
 extern sector_t swapdev_block(int, pgoff_t);
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 01e2858b5fe3..9d3ffbfe08db 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -335,12 +335,17 @@ static int swsusp_swap_check(void)
 {
 	int res;
 
-	res = swap_type_of(swsusp_resume_device, swsusp_resume_block,
-			&hib_resume_bdev);
+	if (swsusp_resume_device)
+		res = swap_type_of(swsusp_resume_device, swsusp_resume_block);
+	else
+		res = find_first_swap(&swsusp_resume_device);
 	if (res < 0)
 		return res;
-
 	root_swap = res;
+
+	hib_resume_bdev = bdget(swsusp_resume_device);
+	if (!hib_resume_bdev)
+		return -ENOMEM;
 	res = blkdev_get(hib_resume_bdev, FMODE_WRITE, NULL);
 	if (res)
 		return res;
@@ -349,12 +354,6 @@ static int swsusp_swap_check(void)
 	if (res < 0)
 		blkdev_put(hib_resume_bdev, FMODE_WRITE);
 
-	/*
-	 * Update the resume device to the one actually used,
-	 * so the test_resume mode can use it in case it is
-	 * invoked from hibernate() to test the snapshot.
-	 */
-	swsusp_resume_device = hib_resume_bdev->bd_dev;
 	return res;
 }
 
diff --git a/kernel/power/user.c b/kernel/power/user.c
index b5815685b944..6510a8f7687f 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -69,8 +69,7 @@ static int snapshot_open(struct inode *inode, struct file *filp)
 	memset(&data->handle, 0, sizeof(struct snapshot_handle));
 	if ((filp->f_flags & O_ACCMODE) == O_RDONLY) {
 		/* Hibernating.  The image device should be accessible. */
-		data->swap = swsusp_resume_device ?
-			swap_type_of(swsusp_resume_device, 0, NULL) : -1;
+		data->swap = swap_type_of(swsusp_resume_device, 0);
 		data->mode = O_RDONLY;
 		data->free_bitmaps = false;
 		error = __pm_notifier_call_chain(PM_HIBERNATION_PREPARE, -1, &nr_calls);
@@ -210,7 +209,6 @@ struct compat_resume_swap_area {
 static int snapshot_set_swap_area(struct snapshot_data *data,
 		void __user *argp)
 {
-	struct block_device *bdev;
 	sector_t offset;
 	dev_t swdev;
 
@@ -237,16 +235,10 @@ static int snapshot_set_swap_area(struct snapshot_data *data,
 	 * User space encodes device types as two-byte values,
 	 * so we need to recode them
 	 */
-	if (!swdev) {
-		data->swap = -1;
-		return -EINVAL;
-	}
-	data->swap = swap_type_of(swdev, offset, &bdev);
+	data->swap = swap_type_of(swdev, offset);
 	if (data->swap < 0)
-		return -ENODEV;
-
-	data->dev = bdev->bd_dev;
-	bdput(bdev);
+		return swdev ? -ENODEV : -EINVAL;
+	data->dev = swdev;
 	return 0;
 }
 
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 7438c4affc75..b90f86920743 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1801,13 +1801,12 @@ int free_swap_and_cache(swp_entry_t entry)
  *
  * This is needed for the suspend to disk (aka swsusp).
  */
-int swap_type_of(dev_t device, sector_t offset, struct block_device **bdev_p)
+int swap_type_of(dev_t device, sector_t offset)
 {
-	struct block_device *bdev = NULL;
 	int type;
 
-	if (device)
-		bdev = bdget(device);
+	if (!device)
+		return -1;
 
 	spin_lock(&swap_lock);
 	for (type = 0; type < nr_swapfiles; type++) {
@@ -1816,30 +1815,34 @@ int swap_type_of(dev_t device, sector_t offset, struct block_device **bdev_p)
 		if (!(sis->flags & SWP_WRITEOK))
 			continue;
 
-		if (!bdev) {
-			if (bdev_p)
-				*bdev_p = bdgrab(sis->bdev);
-
-			spin_unlock(&swap_lock);
-			return type;
-		}
-		if (bdev == sis->bdev) {
+		if (device == sis->bdev->bd_dev) {
 			struct swap_extent *se = first_se(sis);
 
 			if (se->start_block == offset) {
-				if (bdev_p)
-					*bdev_p = bdgrab(sis->bdev);
-
 				spin_unlock(&swap_lock);
-				bdput(bdev);
 				return type;
 			}
 		}
 	}
 	spin_unlock(&swap_lock);
-	if (bdev)
-		bdput(bdev);
+	return -ENODEV;
+}
 
+int find_first_swap(dev_t *device)
+{
+	int type;
+
+	spin_lock(&swap_lock);
+	for (type = 0; type < nr_swapfiles; type++) {
+		struct swap_info_struct *sis = swap_info[type];
+
+		if (!(sis->flags & SWP_WRITEOK))
+			continue;
+		*device = sis->bdev->bd_dev;
+		spin_unlock(&swap_lock);
+		return type;
+	}
+	spin_unlock(&swap_lock);
 	return -ENODEV;
 }
 
-- 
cgit v1.2.3


From 1fb1a2ad75e33e646d33e42b9ed17d879d472859 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 21 Sep 2020 09:19:58 +0200
Subject: block: mark blkdev_get static

There are no users outside the core block code left now.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/block_dev.c         | 3 +--
 include/linux/blkdev.h | 1 -
 2 files changed, 1 insertion(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 2898d69be6b3..6b9d19ffa5af 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1616,7 +1616,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder,
  * RETURNS:
  * 0 on success, -errno on failure.
  */
-int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder)
+static int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder)
 {
 	int ret, perm = 0;
 
@@ -1637,7 +1637,6 @@ bdput:
 	bdput(bdev);
 	return ret;
 }
-EXPORT_SYMBOL(blkdev_get);
 
 /**
  * blkdev_get_by_path - open a block device by name
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 6e19a7aa1672..be5ef6f4ba19 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1981,7 +1981,6 @@ void blkdev_show(struct seq_file *seqf, off_t offset);
 #define BLKDEV_MAJOR_MAX	0
 #endif
 
-int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder);
 struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
 		void *holder);
 struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder);
-- 
cgit v1.2.3


From e1ac11859a057ddcf7d6219bd090c7483541767d Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@nvidia.com>
Date: Tue, 22 Sep 2020 10:30:15 +0300
Subject: net: bridge: add src field to br_ip

Add a new src field to struct br_ip which will be used to lookup S, G
entries. When SSM option is added we will enable full br_ip lookups.

Signed-off-by: Nikolay Aleksandrov <nikolay@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_bridge.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index 6479a38e52fa..4fb9c4954f3a 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -18,6 +18,12 @@ struct br_ip {
 		__be32	ip4;
 #if IS_ENABLED(CONFIG_IPV6)
 		struct in6_addr ip6;
+#endif
+	} src;
+	union {
+		__be32	ip4;
+#if IS_ENABLED(CONFIG_IPV6)
+		struct in6_addr ip6;
 #endif
 	} u;
 	__be16		proto;
-- 
cgit v1.2.3


From eab3227b1240bdcc06c0a01a3fc5bfd2bc12f406 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@nvidia.com>
Date: Tue, 22 Sep 2020 10:30:17 +0300
Subject: net: bridge: mcast: rename br_ip's u member to dst

Since now we have src in br_ip, u no longer makes sense so rename
it to dst. No functional changes.

v2: fix build with CONFIG_BATMAN_ADV_MCAST

CC: Marek Lindner <mareklindner@neomailbox.ch>
CC: Simon Wunderlich <sw@simonwunderlich.de>
CC: Antonio Quartulli <a@unstable.cc>
CC: Sven Eckelmann <sven@narfation.org>
CC: b.a.t.m.a.n@lists.open-mesh.org
Signed-off-by: Nikolay Aleksandrov <nikolay@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_bridge.h  |  2 +-
 net/batman-adv/multicast.c | 14 +++++++-------
 net/bridge/br_mdb.c        | 16 ++++++++--------
 net/bridge/br_multicast.c  | 26 +++++++++++++-------------
 4 files changed, 29 insertions(+), 29 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index 4fb9c4954f3a..556caed00258 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -25,7 +25,7 @@ struct br_ip {
 #if IS_ENABLED(CONFIG_IPV6)
 		struct in6_addr ip6;
 #endif
-	} u;
+	} dst;
 	__be16		proto;
 	__u16           vid;
 };
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index 0746fe2c2c04..9af99c39b9fd 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -221,7 +221,7 @@ static u8 batadv_mcast_mla_rtr_flags_bridge_get(struct batadv_priv *bat_priv,
 		 * address here, only IPv6 ones
 		 */
 		if (br_ip_entry->addr.proto == htons(ETH_P_IPV6) &&
-		    ipv6_addr_is_ll_all_routers(&br_ip_entry->addr.u.ip6))
+		    ipv6_addr_is_ll_all_routers(&br_ip_entry->addr.dst.ip6))
 			flags &= ~BATADV_MCAST_WANT_NO_RTR6;
 
 		list_del(&br_ip_entry->list);
@@ -562,10 +562,10 @@ out:
 static void batadv_mcast_mla_br_addr_cpy(char *dst, const struct br_ip *src)
 {
 	if (src->proto == htons(ETH_P_IP))
-		ip_eth_mc_map(src->u.ip4, dst);
+		ip_eth_mc_map(src->dst.ip4, dst);
 #if IS_ENABLED(CONFIG_IPV6)
 	else if (src->proto == htons(ETH_P_IPV6))
-		ipv6_eth_mc_map(&src->u.ip6, dst);
+		ipv6_eth_mc_map(&src->dst.ip6, dst);
 #endif
 	else
 		eth_zero_addr(dst);
@@ -609,11 +609,11 @@ static int batadv_mcast_mla_bridge_get(struct net_device *dev,
 				continue;
 
 			if (tvlv_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES &&
-			    ipv4_is_local_multicast(br_ip_entry->addr.u.ip4))
+			    ipv4_is_local_multicast(br_ip_entry->addr.dst.ip4))
 				continue;
 
 			if (!(tvlv_flags & BATADV_MCAST_WANT_NO_RTR4) &&
-			    !ipv4_is_local_multicast(br_ip_entry->addr.u.ip4))
+			    !ipv4_is_local_multicast(br_ip_entry->addr.dst.ip4))
 				continue;
 		}
 
@@ -623,11 +623,11 @@ static int batadv_mcast_mla_bridge_get(struct net_device *dev,
 				continue;
 
 			if (tvlv_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES &&
-			    ipv6_addr_is_ll_all_nodes(&br_ip_entry->addr.u.ip6))
+			    ipv6_addr_is_ll_all_nodes(&br_ip_entry->addr.dst.ip6))
 				continue;
 
 			if (!(tvlv_flags & BATADV_MCAST_WANT_NO_RTR6) &&
-			    IPV6_ADDR_MC_SCOPE(&br_ip_entry->addr.u.ip6) >
+			    IPV6_ADDR_MC_SCOPE(&br_ip_entry->addr.dst.ip6) >
 			    IPV6_ADDR_SCOPE_LINKLOCAL)
 				continue;
 		}
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index 269ffd2e549b..a1ff0a372185 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -70,10 +70,10 @@ static void __mdb_entry_to_br_ip(struct br_mdb_entry *entry, struct br_ip *ip)
 	ip->vid = entry->vid;
 	ip->proto = entry->addr.proto;
 	if (ip->proto == htons(ETH_P_IP))
-		ip->u.ip4 = entry->addr.u.ip4;
+		ip->dst.ip4 = entry->addr.u.ip4;
 #if IS_ENABLED(CONFIG_IPV6)
 	else
-		ip->u.ip6 = entry->addr.u.ip6;
+		ip->dst.ip6 = entry->addr.u.ip6;
 #endif
 }
 
@@ -158,10 +158,10 @@ static int __mdb_fill_info(struct sk_buff *skb,
 	e.ifindex = ifindex;
 	e.vid = mp->addr.vid;
 	if (mp->addr.proto == htons(ETH_P_IP))
-		e.addr.u.ip4 = mp->addr.u.ip4;
+		e.addr.u.ip4 = mp->addr.dst.ip4;
 #if IS_ENABLED(CONFIG_IPV6)
 	if (mp->addr.proto == htons(ETH_P_IPV6))
-		e.addr.u.ip6 = mp->addr.u.ip6;
+		e.addr.u.ip6 = mp->addr.dst.ip6;
 #endif
 	e.addr.proto = mp->addr.proto;
 	nest_ent = nla_nest_start_noflag(skb,
@@ -474,10 +474,10 @@ static void br_mdb_switchdev_host_port(struct net_device *dev,
 	};
 
 	if (mp->addr.proto == htons(ETH_P_IP))
-		ip_eth_mc_map(mp->addr.u.ip4, mdb.addr);
+		ip_eth_mc_map(mp->addr.dst.ip4, mdb.addr);
 #if IS_ENABLED(CONFIG_IPV6)
 	else
-		ipv6_eth_mc_map(&mp->addr.u.ip6, mdb.addr);
+		ipv6_eth_mc_map(&mp->addr.dst.ip6, mdb.addr);
 #endif
 
 	mdb.obj.orig_dev = dev;
@@ -520,10 +520,10 @@ void br_mdb_notify(struct net_device *dev,
 
 	if (pg) {
 		if (mp->addr.proto == htons(ETH_P_IP))
-			ip_eth_mc_map(mp->addr.u.ip4, mdb.addr);
+			ip_eth_mc_map(mp->addr.dst.ip4, mdb.addr);
 #if IS_ENABLED(CONFIG_IPV6)
 		else
-			ipv6_eth_mc_map(&mp->addr.u.ip6, mdb.addr);
+			ipv6_eth_mc_map(&mp->addr.dst.ip6, mdb.addr);
 #endif
 		mdb.obj.orig_dev = pg->port->dev;
 		switch (type) {
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index a899c22c8f57..e1fb822b9ddb 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -86,7 +86,7 @@ static struct net_bridge_mdb_entry *br_mdb_ip4_get(struct net_bridge *br,
 	struct br_ip br_dst;
 
 	memset(&br_dst, 0, sizeof(br_dst));
-	br_dst.u.ip4 = dst;
+	br_dst.dst.ip4 = dst;
 	br_dst.proto = htons(ETH_P_IP);
 	br_dst.vid = vid;
 
@@ -101,7 +101,7 @@ static struct net_bridge_mdb_entry *br_mdb_ip6_get(struct net_bridge *br,
 	struct br_ip br_dst;
 
 	memset(&br_dst, 0, sizeof(br_dst));
-	br_dst.u.ip6 = *dst;
+	br_dst.dst.ip6 = *dst;
 	br_dst.proto = htons(ETH_P_IPV6);
 	br_dst.vid = vid;
 
@@ -126,11 +126,11 @@ struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br,
 
 	switch (skb->protocol) {
 	case htons(ETH_P_IP):
-		ip.u.ip4 = ip_hdr(skb)->daddr;
+		ip.dst.ip4 = ip_hdr(skb)->daddr;
 		break;
 #if IS_ENABLED(CONFIG_IPV6)
 	case htons(ETH_P_IPV6):
-		ip.u.ip6 = ipv6_hdr(skb)->daddr;
+		ip.dst.ip6 = ipv6_hdr(skb)->daddr;
 		break;
 #endif
 	default:
@@ -625,9 +625,9 @@ static struct sk_buff *br_multicast_alloc_query(struct net_bridge *br,
 
 	switch (group->proto) {
 	case htons(ETH_P_IP):
-		ip4_dst = ip_dst ? ip_dst->u.ip4 : htonl(INADDR_ALLHOSTS_GROUP);
+		ip4_dst = ip_dst ? ip_dst->dst.ip4 : htonl(INADDR_ALLHOSTS_GROUP);
 		return br_ip4_multicast_alloc_query(br, pg,
-						    ip4_dst, group->u.ip4,
+						    ip4_dst, group->dst.ip4,
 						    with_srcs, over_lmqt,
 						    sflag, igmp_type,
 						    need_rexmit);
@@ -636,13 +636,13 @@ static struct sk_buff *br_multicast_alloc_query(struct net_bridge *br,
 		struct in6_addr ip6_dst;
 
 		if (ip_dst)
-			ip6_dst = ip_dst->u.ip6;
+			ip6_dst = ip_dst->dst.ip6;
 		else
 			ipv6_addr_set(&ip6_dst, htonl(0xff020000), 0, 0,
 				      htonl(1));
 
 		return br_ip6_multicast_alloc_query(br, pg,
-						    &ip6_dst, &group->u.ip6,
+						    &ip6_dst, &group->dst.ip6,
 						    with_srcs, over_lmqt,
 						    sflag, igmp_type,
 						    need_rexmit);
@@ -906,7 +906,7 @@ static int br_ip4_multicast_add_group(struct net_bridge *br,
 		return 0;
 
 	memset(&br_group, 0, sizeof(br_group));
-	br_group.u.ip4 = group;
+	br_group.dst.ip4 = group;
 	br_group.proto = htons(ETH_P_IP);
 	br_group.vid = vid;
 	filter_mode = igmpv2 ? MCAST_EXCLUDE : MCAST_INCLUDE;
@@ -930,7 +930,7 @@ static int br_ip6_multicast_add_group(struct net_bridge *br,
 		return 0;
 
 	memset(&br_group, 0, sizeof(br_group));
-	br_group.u.ip6 = *group;
+	br_group.dst.ip6 = *group;
 	br_group.proto = htons(ETH_P_IPV6);
 	br_group.vid = vid;
 	filter_mode = mldv1 ? MCAST_EXCLUDE : MCAST_INCLUDE;
@@ -1079,7 +1079,7 @@ static void br_multicast_send_query(struct net_bridge *br,
 	    !br_opt_get(br, BROPT_MULTICAST_QUERIER))
 		return;
 
-	memset(&br_group.u, 0, sizeof(br_group.u));
+	memset(&br_group.dst, 0, sizeof(br_group.dst));
 
 	if (port ? (own_query == &port->ip4_own_query) :
 		   (own_query == &br->ip4_own_query)) {
@@ -2506,7 +2506,7 @@ static void br_ip4_multicast_leave_group(struct net_bridge *br,
 	own_query = port ? &port->ip4_own_query : &br->ip4_own_query;
 
 	memset(&br_group, 0, sizeof(br_group));
-	br_group.u.ip4 = group;
+	br_group.dst.ip4 = group;
 	br_group.proto = htons(ETH_P_IP);
 	br_group.vid = vid;
 
@@ -2530,7 +2530,7 @@ static void br_ip6_multicast_leave_group(struct net_bridge *br,
 	own_query = port ? &port->ip6_own_query : &br->ip6_own_query;
 
 	memset(&br_group, 0, sizeof(br_group));
-	br_group.u.ip6 = *group;
+	br_group.dst.ip6 = *group;
 	br_group.proto = htons(ETH_P_IPV6);
 	br_group.vid = vid;
 
-- 
cgit v1.2.3


From 39097ab66dbe89b16438dd6d178d49e75cb922ed Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Wed, 23 Sep 2020 00:29:02 +0200
Subject: net: phy: Fixup kernel doc

Add missing parameter documentation, or fixup wrong parameter names.

Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/mdio.h | 3 ++-
 include/linux/phy.h  | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mdio.h b/include/linux/mdio.h
index 3a88b699b758..dbd69b3d170b 100644
--- a/include/linux/mdio.h
+++ b/include/linux/mdio.h
@@ -306,7 +306,7 @@ static inline u32 linkmode_adv_to_mii_10gbt_adv_t(unsigned long *advertising)
 /**
  * mii_10gbt_stat_mod_linkmode_lpa_t
  * @advertising: target the linkmode advertisement settings
- * @adv: value of the C45 10GBASE-T AN STATUS register
+ * @lpa: value of the C45 10GBASE-T AN STATUS register
  *
  * A small helper function that translates C45 10GBASE-T AN STATUS register bits
  * to linkmode advertisement settings. Other bits in advertising aren't changed.
@@ -371,6 +371,7 @@ struct phy_device *mdiobus_get_phy(struct mii_bus *bus, int addr);
 
 /**
  * mdio_module_driver() - Helper macro for registering mdio drivers
+ * @_mdio_driver: driver to register
  *
  * Helper macro for MDIO drivers which do not do anything special in module
  * init/exit. Each module may only use this macro once, and calling it
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 3a09d2bf69ea..4901b2637059 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1566,8 +1566,9 @@ static inline int mdiobus_register_board_info(const struct mdio_board_info *i,
 
 
 /**
- * module_phy_driver() - Helper macro for registering PHY drivers
+ * phy_module_driver() - Helper macro for registering PHY drivers
  * @__phy_drivers: array of PHY drivers to register
+ * @__count: Numbers of members in array
  *
  * Helper macro for PHY drivers which do not do anything special in module
  * init/exit. Each module may only use this macro once, and calling it
-- 
cgit v1.2.3


From 4069a572d423b73919ae40a500dfc4b10f8a6f32 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Wed, 23 Sep 2020 00:29:03 +0200
Subject: net: phy: Document core PHY structures

Add kerneldoc for the core PHY data structures, a few inline functions
and exported functions which are not already documented.

v2
Typos
g/phy/PHY/s

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/kapi.rst |   9 +
 drivers/net/phy/phy-core.c        |  32 ++-
 drivers/net/phy/phy.c             |  69 ++++++-
 include/linux/phy.h               | 423 ++++++++++++++++++++++++++------------
 4 files changed, 400 insertions(+), 133 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/networking/kapi.rst b/Documentation/networking/kapi.rst
index f03ae64be8bc..d198fa5eaacd 100644
--- a/Documentation/networking/kapi.rst
+++ b/Documentation/networking/kapi.rst
@@ -134,6 +134,15 @@ PHY Support
 .. kernel-doc:: drivers/net/phy/phy.c
    :internal:
 
+.. kernel-doc:: drivers/net/phy/phy-core.c
+   :export:
+
+.. kernel-doc:: drivers/net/phy/phy-c45.c
+   :export:
+
+.. kernel-doc:: include/linux/phy.h
+   :internal:
+
 .. kernel-doc:: drivers/net/phy/phy_device.c
    :export:
 
diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c
index de5b869139d7..8d333d3084ed 100644
--- a/drivers/net/phy/phy-core.c
+++ b/drivers/net/phy/phy-core.c
@@ -6,6 +6,11 @@
 #include <linux/phy.h>
 #include <linux/of.h>
 
+/**
+ * phy_speed_to_str - Return a string representing the PHY link speed
+ *
+ * @speed: Speed of the link
+ */
 const char *phy_speed_to_str(int speed)
 {
 	BUILD_BUG_ON_MSG(__ETHTOOL_LINK_MODE_MASK_NBITS != 92,
@@ -52,6 +57,11 @@ const char *phy_speed_to_str(int speed)
 }
 EXPORT_SYMBOL_GPL(phy_speed_to_str);
 
+/**
+ * phy_duplex_to_str - Return string describing the duplex
+ *
+ * @duplex: Duplex setting to describe
+ */
 const char *phy_duplex_to_str(unsigned int duplex)
 {
 	if (duplex == DUPLEX_HALF)
@@ -252,6 +262,16 @@ static int __set_phy_supported(struct phy_device *phydev, u32 max_speed)
 	return __set_linkmode_max_speed(max_speed, phydev->supported);
 }
 
+/**
+ * phy_set_max_speed - Set the maximum speed the PHY should support
+ *
+ * @phydev: The phy_device struct
+ * @max_speed: Maximum speed
+ *
+ * The PHY might be more capable than the MAC. For example a Fast Ethernet
+ * is connected to a 1G PHY. This function allows the MAC to indicate its
+ * maximum speed, and so limit what the PHY will advertise.
+ */
 int phy_set_max_speed(struct phy_device *phydev, u32 max_speed)
 {
 	int err;
@@ -308,6 +328,16 @@ void of_set_phy_eee_broken(struct phy_device *phydev)
 	phydev->eee_broken_modes = broken;
 }
 
+/**
+ * phy_resolve_aneg_pause - Determine pause autoneg results
+ *
+ * @phydev: The phy_device struct
+ *
+ * Once autoneg has completed the local pause settings can be
+ * resolved.  Determine if pause and asymmetric pause should be used
+ * by the MAC.
+ */
+
 void phy_resolve_aneg_pause(struct phy_device *phydev)
 {
 	if (phydev->duplex == DUPLEX_FULL) {
@@ -321,7 +351,7 @@ void phy_resolve_aneg_pause(struct phy_device *phydev)
 EXPORT_SYMBOL_GPL(phy_resolve_aneg_pause);
 
 /**
- * phy_resolve_aneg_linkmode - resolve the advertisements into phy settings
+ * phy_resolve_aneg_linkmode - resolve the advertisements into PHY settings
  * @phydev: The phy_device struct
  *
  * Resolve our and the link partner advertisements into their corresponding
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 8947d58f2a25..35525a671400 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -456,7 +456,16 @@ int phy_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 }
 EXPORT_SYMBOL(phy_do_ioctl);
 
-/* same as phy_do_ioctl, but ensures that net_device is running */
+/**
+ * phy_do_ioctl_running - generic ndo_do_ioctl implementation but test first
+ *
+ * @dev: the net_device struct
+ * @ifr: &struct ifreq for socket ioctl's
+ * @cmd: ioctl cmd to execute
+ *
+ * Same as phy_do_ioctl, but ensures that net_device is running before
+ * handling the ioctl.
+ */
 int phy_do_ioctl_running(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
 	if (!netif_running(dev))
@@ -466,6 +475,12 @@ int phy_do_ioctl_running(struct net_device *dev, struct ifreq *ifr, int cmd)
 }
 EXPORT_SYMBOL(phy_do_ioctl_running);
 
+/**
+ * phy_queue_state_machine - Trigger the state machine to run soon
+ *
+ * @phydev: the phy_device struct
+ * @jiffies: Run the state machine after these jiffies
+ */
 void phy_queue_state_machine(struct phy_device *phydev, unsigned long jiffies)
 {
 	mod_delayed_work(system_power_efficient_wq, &phydev->state_queue,
@@ -473,6 +488,11 @@ void phy_queue_state_machine(struct phy_device *phydev, unsigned long jiffies)
 }
 EXPORT_SYMBOL(phy_queue_state_machine);
 
+/**
+ * phy_queue_state_machine - Trigger the state machine to run now
+ *
+ * @phydev: the phy_device struct
+ */
 static void phy_trigger_machine(struct phy_device *phydev)
 {
 	phy_queue_state_machine(phydev, 0);
@@ -489,6 +509,12 @@ static void phy_abort_cable_test(struct phy_device *phydev)
 		phydev_err(phydev, "Error while aborting cable test");
 }
 
+/**
+ * phy_ethtool_get_strings - Get the statistic counter names
+ *
+ * @phydev: the phy_device struct
+ * @data: Where to put the strings
+ */
 int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data)
 {
 	if (!phydev->drv)
@@ -502,6 +528,11 @@ int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data)
 }
 EXPORT_SYMBOL(phy_ethtool_get_strings);
 
+/**
+ * phy_ethtool_get_sset_count - Get the number of statistic counters
+ *
+ * @phydev: the phy_device struct
+ */
 int phy_ethtool_get_sset_count(struct phy_device *phydev)
 {
 	int ret;
@@ -523,6 +554,13 @@ int phy_ethtool_get_sset_count(struct phy_device *phydev)
 }
 EXPORT_SYMBOL(phy_ethtool_get_sset_count);
 
+/**
+ * phy_ethtool_get_stats - Get the statistic counters
+ *
+ * @phydev: the phy_device struct
+ * @stats: What counters to get
+ * @data: Where to store the counters
+ */
 int phy_ethtool_get_stats(struct phy_device *phydev,
 			  struct ethtool_stats *stats, u64 *data)
 {
@@ -537,6 +575,12 @@ int phy_ethtool_get_stats(struct phy_device *phydev,
 }
 EXPORT_SYMBOL(phy_ethtool_get_stats);
 
+/**
+ * phy_start_cable_test - Start a cable test
+ *
+ * @phydev: the phy_device struct
+ * @extack: extack for reporting useful error messages
+ */
 int phy_start_cable_test(struct phy_device *phydev,
 			 struct netlink_ext_ack *extack)
 {
@@ -600,6 +644,13 @@ out:
 }
 EXPORT_SYMBOL(phy_start_cable_test);
 
+/**
+ * phy_start_cable_test_tdr - Start a raw TDR cable test
+ *
+ * @phydev: the phy_device struct
+ * @extack: extack for reporting useful error messages
+ * @config: Configuration of the test to run
+ */
 int phy_start_cable_test_tdr(struct phy_device *phydev,
 			     struct netlink_ext_ack *extack,
 			     const struct phy_tdr_config *config)
@@ -1363,6 +1414,12 @@ int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data)
 }
 EXPORT_SYMBOL(phy_ethtool_set_eee);
 
+/**
+ * phy_ethtool_set_wol - Configure Wake On LAN
+ *
+ * @phydev: target phy_device struct
+ * @wol: Configuration requested
+ */
 int phy_ethtool_set_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol)
 {
 	if (phydev->drv && phydev->drv->set_wol)
@@ -1372,6 +1429,12 @@ int phy_ethtool_set_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol)
 }
 EXPORT_SYMBOL(phy_ethtool_set_wol);
 
+/**
+ * phy_ethtool_get_wol - Get the current Wake On LAN configuration
+ *
+ * @phydev: target phy_device struct
+ * @wol: Store the current configuration here
+ */
 void phy_ethtool_get_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol)
 {
 	if (phydev->drv && phydev->drv->get_wol)
@@ -1405,6 +1468,10 @@ int phy_ethtool_set_link_ksettings(struct net_device *ndev,
 }
 EXPORT_SYMBOL(phy_ethtool_set_link_ksettings);
 
+/**
+ * phy_ethtool_nway_reset - Restart auto negotiation
+ * @ndev: Network device to restart autoneg for
+ */
 int phy_ethtool_nway_reset(struct net_device *ndev)
 {
 	struct phy_device *phydev = ndev->phydev;
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 4901b2637059..eb3cb1a98b45 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -82,7 +82,39 @@ extern const int phy_10gbit_features_array[1];
 #define PHY_POLL_CABLE_TEST	0x00000004
 #define MDIO_DEVICE_IS_PHY	0x80000000
 
-/* Interface Mode definitions */
+/**
+ * enum phy_interface_t - Interface Mode definitions
+ *
+ * @PHY_INTERFACE_MODE_NA: Not Applicable - don't touch
+ * @PHY_INTERFACE_MODE_INTERNAL: No interface, MAC and PHY combined
+ * @PHY_INTERFACE_MODE_MII: Median-independent interface
+ * @PHY_INTERFACE_MODE_GMII: Gigabit median-independent interface
+ * @PHY_INTERFACE_MODE_SGMII: Serial gigabit media-independent interface
+ * @PHY_INTERFACE_MODE_TBI: Ten Bit Interface
+ * @PHY_INTERFACE_MODE_REVMII: Reverse Media Independent Interface
+ * @PHY_INTERFACE_MODE_RMII: Reduced Media Independent Interface
+ * @PHY_INTERFACE_MODE_RGMII: Reduced gigabit media-independent interface
+ * @PHY_INTERFACE_MODE_RGMII_ID: RGMII with Internal RX+TX delay
+ * @PHY_INTERFACE_MODE_RGMII_RXID: RGMII with Internal RX delay
+ * @PHY_INTERFACE_MODE_RGMII_TXID: RGMII with Internal RX delay
+ * @PHY_INTERFACE_MODE_RTBI: Reduced TBI
+ * @PHY_INTERFACE_MODE_SMII: ??? MII
+ * @PHY_INTERFACE_MODE_XGMII: 10 gigabit media-independent interface
+ * @PHY_INTERFACE_MODE_XLGMII:40 gigabit media-independent interface
+ * @PHY_INTERFACE_MODE_MOCA: Multimedia over Coax
+ * @PHY_INTERFACE_MODE_QSGMII: Quad SGMII
+ * @PHY_INTERFACE_MODE_TRGMII: Turbo RGMII
+ * @PHY_INTERFACE_MODE_1000BASEX: 1000 BaseX
+ * @PHY_INTERFACE_MODE_2500BASEX: 2500 BaseX
+ * @PHY_INTERFACE_MODE_RXAUI: Reduced XAUI
+ * @PHY_INTERFACE_MODE_XAUI: 10 Gigabit Attachment Unit Interface
+ * @PHY_INTERFACE_MODE_10GBASER: 10G BaseR
+ * @PHY_INTERFACE_MODE_USXGMII:  Universal Serial 10GE MII
+ * @PHY_INTERFACE_MODE_10GKR: 10GBASE-KR - with Clause 73 AN
+ * @PHY_INTERFACE_MODE_MAX: Book keeping
+ *
+ * Describes the interface between the MAC and PHY.
+ */
 typedef enum {
 	PHY_INTERFACE_MODE_NA,
 	PHY_INTERFACE_MODE_INTERNAL,
@@ -116,8 +148,8 @@ typedef enum {
 } phy_interface_t;
 
 /**
- * phy_supported_speeds - return all speeds currently supported by a phy device
- * @phy: The phy device to return supported speeds of.
+ * phy_supported_speeds - return all speeds currently supported by a PHY device
+ * @phy: The PHY device to return supported speeds of.
  * @speeds: buffer to store supported speeds in.
  * @size: size of speeds buffer.
  *
@@ -134,9 +166,9 @@ unsigned int phy_supported_speeds(struct phy_device *phy,
  * phy_modes - map phy_interface_t enum to device tree binding of phy-mode
  * @interface: enum phy_interface_t value
  *
- * Description: maps 'enum phy_interface_t' defined in this file
+ * Description: maps enum &phy_interface_t defined in this file
  * into the device tree binding of 'phy-mode', so that Ethernet
- * device driver can get phy interface from device tree.
+ * device driver can get PHY interface from device tree.
  */
 static inline const char *phy_modes(phy_interface_t interface)
 {
@@ -215,6 +247,14 @@ struct sfp_bus;
 struct sfp_upstream_ops;
 struct sk_buff;
 
+/**
+ * struct mdio_bus_stats - Statistics counters for MDIO busses
+ * @transfers: Total number of transfers, i.e. @writes + @reads
+ * @errors: Number of MDIO transfers that returned an error
+ * @writes: Number of write transfers
+ * @reads: Number of read transfers
+ * @syncp: Synchronisation for incrementing statistics
+ */
 struct mdio_bus_stats {
 	u64_stats_t transfers;
 	u64_stats_t errors;
@@ -224,7 +264,15 @@ struct mdio_bus_stats {
 	struct u64_stats_sync syncp;
 };
 
-/* Represents a shared structure between different phydev's in the same
+/**
+ * struct phy_package_shared - Shared information in PHY packages
+ * @addr: Common PHY address used to combine PHYs in one package
+ * @refcnt: Number of PHYs connected to this shared data
+ * @flags: Initialization of PHY package
+ * @priv_size: Size of the shared private data @priv
+ * @priv: Driver private data shared across a PHY package
+ *
+ * Represents a shared structure between different phydev's in the same
  * package, for example a quad PHY. See phy_package_join() and
  * phy_package_leave().
  */
@@ -247,7 +295,14 @@ struct phy_package_shared {
 #define PHY_SHARED_F_INIT_DONE  0
 #define PHY_SHARED_F_PROBE_DONE 1
 
-/*
+/**
+ * struct mii_bus - Represents an MDIO bus
+ *
+ * @owner: Who owns this device
+ * @name: User friendly name for this MDIO device, or driver name
+ * @id: Unique identifier for this bus, typical from bus hierarchy
+ * @priv: Driver private data
+ *
  * The Bus class for PHYs.  Devices which provide access to
  * PHYs should register using this structure
  */
@@ -256,49 +311,58 @@ struct mii_bus {
 	const char *name;
 	char id[MII_BUS_ID_SIZE];
 	void *priv;
+	/** @read: Perform a read transfer on the bus */
 	int (*read)(struct mii_bus *bus, int addr, int regnum);
+	/** @write: Perform a write transfer on the bus */
 	int (*write)(struct mii_bus *bus, int addr, int regnum, u16 val);
+	/** @reset: Perform a reset of the bus */
 	int (*reset)(struct mii_bus *bus);
+
+	/** @stats: Statistic counters per device on the bus */
 	struct mdio_bus_stats stats[PHY_MAX_ADDR];
 
-	/*
-	 * A lock to ensure that only one thing can read/write
+	/**
+	 * @mdio_lock: A lock to ensure that only one thing can read/write
 	 * the MDIO bus at a time
 	 */
 	struct mutex mdio_lock;
 
+	/** @parent: Parent device of this bus */
 	struct device *parent;
+	/** @state: State of bus structure */
 	enum {
 		MDIOBUS_ALLOCATED = 1,
 		MDIOBUS_REGISTERED,
 		MDIOBUS_UNREGISTERED,
 		MDIOBUS_RELEASED,
 	} state;
+
+	/** @dev: Kernel device representation */
 	struct device dev;
 
-	/* list of all PHYs on bus */
+	/** @mdio_map: list of all MDIO devices on bus */
 	struct mdio_device *mdio_map[PHY_MAX_ADDR];
 
-	/* PHY addresses to be ignored when probing */
+	/** @phy_mask: PHY addresses to be ignored when probing */
 	u32 phy_mask;
 
-	/* PHY addresses to ignore the TA/read failure */
+	/** @phy_ignore_ta_mask: PHY addresses to ignore the TA/read failure */
 	u32 phy_ignore_ta_mask;
 
-	/*
-	 * An array of interrupts, each PHY's interrupt at the index
+	/**
+	 * @irq: An array of interrupts, each PHY's interrupt at the index
 	 * matching its address
 	 */
 	int irq[PHY_MAX_ADDR];
 
-	/* GPIO reset pulse width in microseconds */
+	/** @reset_delay_us: GPIO reset pulse width in microseconds */
 	int reset_delay_us;
-	/* GPIO reset deassert delay in microseconds */
+	/** @reset_post_delay_us: GPIO reset deassert delay in microseconds */
 	int reset_post_delay_us;
-	/* RESET GPIO descriptor pointer */
+	/** @reset_gpiod: Reset GPIO descriptor pointer */
 	struct gpio_desc *reset_gpiod;
 
-	/* bus capabilities, used for probing */
+	/** @probe_capabilities: bus capabilities, used for probing */
 	enum {
 		MDIOBUS_NO_CAP = 0,
 		MDIOBUS_C22,
@@ -306,15 +370,22 @@ struct mii_bus {
 		MDIOBUS_C22_C45,
 	} probe_capabilities;
 
-	/* protect access to the shared element */
+	/** @shared_lock: protect access to the shared element */
 	struct mutex shared_lock;
 
-	/* shared state across different PHYs */
+	/** @shared: shared state across different PHYs */
 	struct phy_package_shared *shared[PHY_MAX_ADDR];
 };
 #define to_mii_bus(d) container_of(d, struct mii_bus, dev)
 
-struct mii_bus *mdiobus_alloc_size(size_t);
+struct mii_bus *mdiobus_alloc_size(size_t size);
+
+/**
+ * mdiobus_alloc - Allocate an MDIO bus structure
+ *
+ * The internal state of the MDIO bus will be set of MDIOBUS_ALLOCATED ready
+ * for the driver to register the bus.
+ */
 static inline struct mii_bus *mdiobus_alloc(void)
 {
 	return mdiobus_alloc_size(0);
@@ -341,40 +412,41 @@ struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr);
 #define PHY_INTERRUPT_DISABLED	false
 #define PHY_INTERRUPT_ENABLED	true
 
-/* PHY state machine states:
+/**
+ * enum phy_state - PHY state machine states:
  *
- * DOWN: PHY device and driver are not ready for anything.  probe
+ * @PHY_DOWN: PHY device and driver are not ready for anything.  probe
  * should be called if and only if the PHY is in this state,
  * given that the PHY device exists.
- * - PHY driver probe function will set the state to READY
+ * - PHY driver probe function will set the state to @PHY_READY
  *
- * READY: PHY is ready to send and receive packets, but the
+ * @PHY_READY: PHY is ready to send and receive packets, but the
  * controller is not.  By default, PHYs which do not implement
  * probe will be set to this state by phy_probe().
  * - start will set the state to UP
  *
- * UP: The PHY and attached device are ready to do work.
+ * @PHY_UP: The PHY and attached device are ready to do work.
  * Interrupts should be started here.
- * - timer moves to NOLINK or RUNNING
+ * - timer moves to @PHY_NOLINK or @PHY_RUNNING
  *
- * NOLINK: PHY is up, but not currently plugged in.
- * - irq or timer will set RUNNING if link comes back
- * - phy_stop moves to HALTED
+ * @PHY_NOLINK: PHY is up, but not currently plugged in.
+ * - irq or timer will set @PHY_RUNNING if link comes back
+ * - phy_stop moves to @PHY_HALTED
  *
- * RUNNING: PHY is currently up, running, and possibly sending
+ * @PHY_RUNNING: PHY is currently up, running, and possibly sending
  * and/or receiving packets
- * - irq or timer will set NOLINK if link goes down
- * - phy_stop moves to HALTED
+ * - irq or timer will set @PHY_NOLINK if link goes down
+ * - phy_stop moves to @PHY_HALTED
  *
- * CABLETEST: PHY is performing a cable test. Packet reception/sending
+ * @PHY_CABLETEST: PHY is performing a cable test. Packet reception/sending
  * is not expected to work, carrier will be indicated as down. PHY will be
  * poll once per second, or on interrupt for it current state.
  * Once complete, move to UP to restart the PHY.
- * - phy_stop aborts the running test and moves to HALTED
+ * - phy_stop aborts the running test and moves to @PHY_HALTED
  *
- * HALTED: PHY is up, but no polling or interrupts are done. Or
+ * @PHY_HALTED: PHY is up, but no polling or interrupts are done. Or
  * PHY is in an error state.
- * - phy_start moves to UP
+ * - phy_start moves to @PHY_UP
  */
 enum phy_state {
 	PHY_DOWN = 0,
@@ -403,34 +475,67 @@ struct phy_c45_device_ids {
 struct macsec_context;
 struct macsec_ops;
 
-/* phy_device: An instance of a PHY
+/**
+ * struct phy_device - An instance of a PHY
  *
- * drv: Pointer to the driver for this PHY instance
- * phy_id: UID for this device found during discovery
- * c45_ids: 802.3-c45 Device Identifers if is_c45.
- * is_c45:  Set to true if this phy uses clause 45 addressing.
- * is_internal: Set to true if this phy is internal to a MAC.
- * is_pseudo_fixed_link: Set to true if this phy is an Ethernet switch, etc.
- * is_gigabit_capable: Set to true if PHY supports 1000Mbps
- * has_fixups: Set to true if this phy has fixups/quirks.
- * suspended: Set to true if this phy has been suspended successfully.
- * suspended_by_mdio_bus: Set to true if this phy was suspended by MDIO bus.
- * sysfs_links: Internal boolean tracking sysfs symbolic links setup/removal.
- * loopback_enabled: Set true if this phy has been loopbacked successfully.
- * downshifted_rate: Set true if link speed has been downshifted.
- * state: state of the PHY for management purposes
- * dev_flags: Device-specific flags used by the PHY driver.
- * irq: IRQ number of the PHY's interrupt (-1 if none)
- * phy_timer: The timer for handling the state machine
- * sfp_bus_attached: flag indicating whether the SFP bus has been attached
- * sfp_bus: SFP bus attached to this PHY's fiber port
- * attached_dev: The attached enet driver's device instance ptr
- * adjust_link: Callback for the enet controller to respond to
- * changes in the link state.
- * macsec_ops: MACsec offloading ops.
+ * @mdio: MDIO bus this PHY is on
+ * @drv: Pointer to the driver for this PHY instance
+ * @phy_id: UID for this device found during discovery
+ * @c45_ids: 802.3-c45 Device Identifiers if is_c45.
+ * @is_c45:  Set to true if this PHY uses clause 45 addressing.
+ * @is_internal: Set to true if this PHY is internal to a MAC.
+ * @is_pseudo_fixed_link: Set to true if this PHY is an Ethernet switch, etc.
+ * @is_gigabit_capable: Set to true if PHY supports 1000Mbps
+ * @has_fixups: Set to true if this PHY has fixups/quirks.
+ * @suspended: Set to true if this PHY has been suspended successfully.
+ * @suspended_by_mdio_bus: Set to true if this PHY was suspended by MDIO bus.
+ * @sysfs_links: Internal boolean tracking sysfs symbolic links setup/removal.
+ * @loopback_enabled: Set true if this PHY has been loopbacked successfully.
+ * @downshifted_rate: Set true if link speed has been downshifted.
+ * @state: State of the PHY for management purposes
+ * @dev_flags: Device-specific flags used by the PHY driver.
+ * @irq: IRQ number of the PHY's interrupt (-1 if none)
+ * @phy_timer: The timer for handling the state machine
+ * @phylink: Pointer to phylink instance for this PHY
+ * @sfp_bus_attached: Flag indicating whether the SFP bus has been attached
+ * @sfp_bus: SFP bus attached to this PHY's fiber port
+ * @attached_dev: The attached enet driver's device instance ptr
+ * @adjust_link: Callback for the enet controller to respond to changes: in the
+ *               link state.
+ * @phy_link_change: Callback for phylink for notification of link change
+ * @macsec_ops: MACsec offloading ops.
  *
- * speed, duplex, pause, supported, advertising, lp_advertising,
- * and autoneg are used like in mii_if_info
+ * @speed: Current link speed
+ * @duplex: Current duplex
+ * @pause: Current pause
+ * @asym_pause: Current asymmetric pause
+ * @supported: Combined MAC/PHY supported linkmodes
+ * @advertising: Currently advertised linkmodes
+ * @adv_old: Saved advertised while power saving for WoL
+ * @lp_advertising: Current link partner advertised linkmodes
+ * @eee_broken_modes: Energy efficient ethernet modes which should be prohibited
+ * @autoneg: Flag autoneg being used
+ * @link: Current link state
+ * @autoneg_complete: Flag auto negotiation of the link has completed
+ * @mdix: Current crossover
+ * @mdix_ctrl: User setting of crossover
+ * @interrupts: Flag interrupts have been enabled
+ * @interface: enum phy_interface_t value
+ * @skb: Netlink message for cable diagnostics
+ * @nest: Netlink nest used for cable diagnostics
+ * @ehdr: nNtlink header for cable diagnostics
+ * @phy_led_triggers: Array of LED triggers
+ * @phy_num_led_triggers: Number of triggers in @phy_led_triggers
+ * @led_link_trigger: LED trigger for link up/down
+ * @last_triggered: last LED trigger for link speed
+ * @master_slave_set: User requested master/slave configuration
+ * @master_slave_get: Current master/slave advertisement
+ * @master_slave_state: Current master/slave configuration
+ * @mii_ts: Pointer to time stamper callbacks
+ * @lock:  Mutex for serialization access to PHY
+ * @state_queue: Work queue for state machine
+ * @shared: Pointer to private data shared by phys in one package
+ * @priv: Pointer to driver private data
  *
  * interrupts currently only supports enabled or disabled,
  * but could be changed in the future to support enabling
@@ -550,9 +655,18 @@ struct phy_device {
 #define to_phy_device(d) container_of(to_mdio_device(d), \
 				      struct phy_device, mdio)
 
-/* A structure containing possible configuration parameters
+/**
+ * struct phy_tdr_config - Configuration of a TDR raw test
+ *
+ * @first: Distance for first data collection point
+ * @last: Distance for last data collection point
+ * @step: Step between data collection points
+ * @pair: Bitmap of cable pairs to collect data for
+ *
+ * A structure containing possible configuration parameters
  * for a TDR cable test. The driver does not need to implement
  * all the parameters, but should report what is actually used.
+ * All distances are in centimeters.
  */
 struct phy_tdr_config {
 	u32 first;
@@ -562,18 +676,20 @@ struct phy_tdr_config {
 };
 #define PHY_PAIR_ALL -1
 
-/* struct phy_driver: Driver structure for a particular PHY type
+/**
+ * struct phy_driver - Driver structure for a particular PHY type
  *
- * driver_data: static driver data
- * phy_id: The result of reading the UID registers of this PHY
+ * @mdiodrv: Data common to all MDIO devices
+ * @phy_id: The result of reading the UID registers of this PHY
  *   type, and ANDing them with the phy_id_mask.  This driver
  *   only works for PHYs with IDs which match this field
- * name: The friendly name of this PHY type
- * phy_id_mask: Defines the important bits of the phy_id
- * features: A mandatory list of features (speed, duplex, etc)
+ * @name: The friendly name of this PHY type
+ * @phy_id_mask: Defines the important bits of the phy_id
+ * @features: A mandatory list of features (speed, duplex, etc)
  *   supported by this PHY
- * flags: A bitfield defining certain other features this PHY
+ * @flags: A bitfield defining certain other features this PHY
  *   supports (like interrupts)
+ * @driver_data: Static driver data
  *
  * All functions are optional. If config_aneg or read_status
  * are not implemented, the phy core uses the genphy versions.
@@ -592,151 +708,178 @@ struct phy_driver {
 	u32 flags;
 	const void *driver_data;
 
-	/*
-	 * Called to issue a PHY software reset
+	/**
+	 * @soft_reset: Called to issue a PHY software reset
 	 */
 	int (*soft_reset)(struct phy_device *phydev);
 
-	/*
-	 * Called to initialize the PHY,
+	/**
+	 * @config_init: Called to initialize the PHY,
 	 * including after a reset
 	 */
 	int (*config_init)(struct phy_device *phydev);
 
-	/*
-	 * Called during discovery.  Used to set
+	/**
+	 * @probe: Called during discovery.  Used to set
 	 * up device-specific structures, if any
 	 */
 	int (*probe)(struct phy_device *phydev);
 
-	/*
-	 * Probe the hardware to determine what abilities it has.
-	 * Should only set phydev->supported.
+	/**
+	 * @get_features: Probe the hardware to determine what
+	 * abilities it has.  Should only set phydev->supported.
 	 */
 	int (*get_features)(struct phy_device *phydev);
 
 	/* PHY Power Management */
+	/** @suspend: Suspend the hardware, saving state if needed */
 	int (*suspend)(struct phy_device *phydev);
+	/** @resume: Resume the hardware, restoring state if needed */
 	int (*resume)(struct phy_device *phydev);
 
-	/*
-	 * Configures the advertisement and resets
+	/**
+	 * @config_aneg: Configures the advertisement and resets
 	 * autonegotiation if phydev->autoneg is on,
 	 * forces the speed to the current settings in phydev
 	 * if phydev->autoneg is off
 	 */
 	int (*config_aneg)(struct phy_device *phydev);
 
-	/* Determines the auto negotiation result */
+	/** @aneg_done: Determines the auto negotiation result */
 	int (*aneg_done)(struct phy_device *phydev);
 
-	/* Determines the negotiated speed and duplex */
+	/** @read_status: Determines the negotiated speed and duplex */
 	int (*read_status)(struct phy_device *phydev);
 
-	/* Clears any pending interrupts */
+	/** @ack_interrupt: Clears any pending interrupts */
 	int (*ack_interrupt)(struct phy_device *phydev);
 
-	/* Enables or disables interrupts */
+	/** @config_intr: Enables or disables interrupts */
 	int (*config_intr)(struct phy_device *phydev);
 
-	/*
-	 * Checks if the PHY generated an interrupt.
+	/**
+	 * @did_interrupt: Checks if the PHY generated an interrupt.
 	 * For multi-PHY devices with shared PHY interrupt pin
 	 * Set interrupt bits have to be cleared.
 	 */
 	int (*did_interrupt)(struct phy_device *phydev);
 
-	/* Override default interrupt handling */
+	/** @handle_interrupt: Override default interrupt handling */
 	irqreturn_t (*handle_interrupt)(struct phy_device *phydev);
 
-	/* Clears up any memory if needed */
+	/** @remove: Clears up any memory if needed */
 	void (*remove)(struct phy_device *phydev);
 
-	/* Returns true if this is a suitable driver for the given
-	 * phydev.  If NULL, matching is based on phy_id and
-	 * phy_id_mask.
+	/**
+	 * @match_phy_device: Returns true if this is a suitable
+	 * driver for the given phydev.	 If NULL, matching is based on
+	 * phy_id and phy_id_mask.
 	 */
 	int (*match_phy_device)(struct phy_device *phydev);
 
-	/* Some devices (e.g. qnap TS-119P II) require PHY register changes to
-	 * enable Wake on LAN, so set_wol is provided to be called in the
-	 * ethernet driver's set_wol function. */
+	/**
+	 * @set_wol: Some devices (e.g. qnap TS-119P II) require PHY
+	 * register changes to enable Wake on LAN, so set_wol is
+	 * provided to be called in the ethernet driver's set_wol
+	 * function.
+	 */
 	int (*set_wol)(struct phy_device *dev, struct ethtool_wolinfo *wol);
 
-	/* See set_wol, but for checking whether Wake on LAN is enabled. */
+	/**
+	 * @get_wol: See set_wol, but for checking whether Wake on LAN
+	 * is enabled.
+	 */
 	void (*get_wol)(struct phy_device *dev, struct ethtool_wolinfo *wol);
 
-	/*
-	 * Called to inform a PHY device driver when the core is about to
-	 * change the link state. This callback is supposed to be used as
-	 * fixup hook for drivers that need to take action when the link
-	 * state changes. Drivers are by no means allowed to mess with the
+	/**
+	 * @link_change_notify: Called to inform a PHY device driver
+	 * when the core is about to change the link state. This
+	 * callback is supposed to be used as fixup hook for drivers
+	 * that need to take action when the link state
+	 * changes. Drivers are by no means allowed to mess with the
 	 * PHY device structure in their implementations.
 	 */
 	void (*link_change_notify)(struct phy_device *dev);
 
-	/*
-	 * Phy specific driver override for reading a MMD register.
-	 * This function is optional for PHY specific drivers.  When
-	 * not provided, the default MMD read function will be used
-	 * by phy_read_mmd(), which will use either a direct read for
-	 * Clause 45 PHYs or an indirect read for Clause 22 PHYs.
-	 *  devnum is the MMD device number within the PHY device,
-	 *  regnum is the register within the selected MMD device.
+	/**
+	 * @read_mmd: PHY specific driver override for reading a MMD
+	 * register.  This function is optional for PHY specific
+	 * drivers.  When not provided, the default MMD read function
+	 * will be used by phy_read_mmd(), which will use either a
+	 * direct read for Clause 45 PHYs or an indirect read for
+	 * Clause 22 PHYs.  devnum is the MMD device number within the
+	 * PHY device, regnum is the register within the selected MMD
+	 * device.
 	 */
 	int (*read_mmd)(struct phy_device *dev, int devnum, u16 regnum);
 
-	/*
-	 * Phy specific driver override for writing a MMD register.
-	 * This function is optional for PHY specific drivers.  When
-	 * not provided, the default MMD write function will be used
-	 * by phy_write_mmd(), which will use either a direct write for
-	 * Clause 45 PHYs, or an indirect write for Clause 22 PHYs.
-	 *  devnum is the MMD device number within the PHY device,
-	 *  regnum is the register within the selected MMD device.
-	 *  val is the value to be written.
+	/**
+	 * @write_mmd: PHY specific driver override for writing a MMD
+	 * register.  This function is optional for PHY specific
+	 * drivers.  When not provided, the default MMD write function
+	 * will be used by phy_write_mmd(), which will use either a
+	 * direct write for Clause 45 PHYs, or an indirect write for
+	 * Clause 22 PHYs.  devnum is the MMD device number within the
+	 * PHY device, regnum is the register within the selected MMD
+	 * device.  val is the value to be written.
 	 */
 	int (*write_mmd)(struct phy_device *dev, int devnum, u16 regnum,
 			 u16 val);
 
+	/** @read_page: Return the current PHY register page number */
 	int (*read_page)(struct phy_device *dev);
+	/** @write_page: Set the current PHY register page number */
 	int (*write_page)(struct phy_device *dev, int page);
 
-	/* Get the size and type of the eeprom contained within a plug-in
-	 * module */
+	/**
+	 * @module_info: Get the size and type of the eeprom contained
+	 * within a plug-in module
+	 */
 	int (*module_info)(struct phy_device *dev,
 			   struct ethtool_modinfo *modinfo);
 
-	/* Get the eeprom information from the plug-in module */
+	/**
+	 * @module_eeprom: Get the eeprom information from the plug-in
+	 * module
+	 */
 	int (*module_eeprom)(struct phy_device *dev,
 			     struct ethtool_eeprom *ee, u8 *data);
 
-	/* Start a cable test */
+	/** @cable_test_start: Start a cable test */
 	int (*cable_test_start)(struct phy_device *dev);
 
-	/* Start a raw TDR cable test */
+	/**  @cable_test_tdr_start: Start a raw TDR cable test */
 	int (*cable_test_tdr_start)(struct phy_device *dev,
 				    const struct phy_tdr_config *config);
 
-	/* Once per second, or on interrupt, request the status of the
-	 * test.
+	/**
+	 * @cable_test_get_status: Once per second, or on interrupt,
+	 * request the status of the test.
 	 */
 	int (*cable_test_get_status)(struct phy_device *dev, bool *finished);
 
-	/* Get statistics from the phy using ethtool */
+	/* Get statistics from the PHY using ethtool */
+	/** @get_sset_count: Number of statistic counters */
 	int (*get_sset_count)(struct phy_device *dev);
+	/** @get_strings: Names of the statistic counters */
 	void (*get_strings)(struct phy_device *dev, u8 *data);
+	/** @get_stats: Return the statistic counter values */
 	void (*get_stats)(struct phy_device *dev,
 			  struct ethtool_stats *stats, u64 *data);
 
 	/* Get and Set PHY tunables */
+	/** @get_tunable: Return the value of a tunable */
 	int (*get_tunable)(struct phy_device *dev,
 			   struct ethtool_tunable *tuna, void *data);
+	/** @set_tunable: Set the value of a tunable */
 	int (*set_tunable)(struct phy_device *dev,
 			    struct ethtool_tunable *tuna,
 			    const void *data);
+	/** @set_loopback: Set the loopback mood of the PHY */
 	int (*set_loopback)(struct phy_device *dev, bool enable);
+	/** @get_sqi: Get the signal quality indication */
 	int (*get_sqi)(struct phy_device *dev);
+	/** @get_sqi_max: Get the maximum signal quality indication */
 	int (*get_sqi_max)(struct phy_device *dev);
 };
 #define to_phy_driver(d) container_of(to_mdio_common_driver(d),		\
@@ -890,6 +1033,24 @@ static inline int __phy_modify_changed(struct phy_device *phydev, u32 regnum,
  */
 int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum);
 
+/**
+ * phy_read_mmd_poll_timeout - Periodically poll a PHY register until a
+ *                             condition is met or a timeout occurs
+ *
+ * @phydev: The phy_device struct
+ * @devaddr: The MMD to read from
+ * @regnum: The register on the MMD to read
+ * @val: Variable to read the register into
+ * @cond: Break condition (usually involving @val)
+ * @sleep_us: Maximum time to sleep between reads in us (0
+ *            tight-loops).  Should be less than ~20ms since usleep_range
+ *            is used (see Documentation/timers/timers-howto.rst).
+ * @timeout_us: Timeout in us, 0 means never timeout
+ * @sleep_before_read: if it is true, sleep @sleep_us before read.
+ * Returns 0 on success and -ETIMEDOUT upon a timeout. In either
+ * case, the last read value at @args is stored in @val. Must not
+ * be called from atomic context if sleep_us or timeout_us are used.
+ */
 #define phy_read_mmd_poll_timeout(phydev, devaddr, regnum, val, cond, \
 				  sleep_us, timeout_us, sleep_before_read) \
 ({ \
@@ -1161,7 +1322,7 @@ static inline bool phy_is_internal(struct phy_device *phydev)
 /**
  * phy_interface_mode_is_rgmii - Convenience function for testing if a
  * PHY interface mode is RGMII (all variants)
- * @mode: the phy_interface_t enum
+ * @mode: the &phy_interface_t enum
  */
 static inline bool phy_interface_mode_is_rgmii(phy_interface_t mode)
 {
@@ -1170,11 +1331,11 @@ static inline bool phy_interface_mode_is_rgmii(phy_interface_t mode)
 };
 
 /**
- * phy_interface_mode_is_8023z() - does the phy interface mode use 802.3z
+ * phy_interface_mode_is_8023z() - does the PHY interface mode use 802.3z
  *   negotiation
  * @mode: one of &enum phy_interface_t
  *
- * Returns true if the phy interface mode uses the 16-bit negotiation
+ * Returns true if the PHY interface mode uses the 16-bit negotiation
  * word as defined in 802.3z. (See 802.3-2015 37.2.1 Config_Reg encoding)
  */
 static inline bool phy_interface_mode_is_8023z(phy_interface_t mode)
@@ -1193,7 +1354,7 @@ static inline bool phy_interface_is_rgmii(struct phy_device *phydev)
 	return phy_interface_mode_is_rgmii(phydev->interface);
 };
 
-/*
+/**
  * phy_is_pseudo_fixed_link - Convenience function for testing if this
  * PHY is the CPU port facing side of an Ethernet switch, or similar.
  * @phydev: the phy_device struct
-- 
cgit v1.2.3


From 70fb2612aab62d47e03f82eaa7384a8d30ca175d Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Wed, 23 Sep 2020 21:26:23 -0700
Subject: fscrypt: don't call no-key names "ciphertext names"

Currently we're using the term "ciphertext name" ambiguously because it
can mean either the actual ciphertext filename, or the encoded filename
that is shown when an encrypted directory is listed without its key.
The latter we're now usually calling the "no-key name"; and while it's
derived from the ciphertext name, it's not the same thing.

To avoid this ambiguity, rename fscrypt_name::is_ciphertext_name to
fscrypt_name::is_nokey_name, and update comments that say "ciphertext
name" (or "encrypted name") to say "no-key name" instead when warranted.

Link: https://lore.kernel.org/r/20200924042624.98439-2-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 fs/crypto/fname.c       | 16 ++++++++--------
 fs/crypto/hooks.c       |  6 +++---
 fs/f2fs/dir.c           |  2 +-
 include/linux/fscrypt.h | 15 +++++++--------
 4 files changed, 19 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c
index f47b581d8a94..391acea4bc96 100644
--- a/fs/crypto/fname.c
+++ b/fs/crypto/fname.c
@@ -382,9 +382,9 @@ EXPORT_SYMBOL(fscrypt_fname_disk_to_usr);
  * directory's encryption key, then @iname is the plaintext, so we encrypt it to
  * get the disk_name.
  *
- * Else, for keyless @lookup operations, @iname is the presented ciphertext, so
- * we decode it to get the fscrypt_nokey_name.  Non-@lookup operations will be
- * impossible in this case, so we fail them with ENOKEY.
+ * Else, for keyless @lookup operations, @iname should be a no-key name, so we
+ * decode it to get the struct fscrypt_nokey_name.  Non-@lookup operations will
+ * be impossible in this case, so we fail them with ENOKEY.
  *
  * If successful, fscrypt_free_filename() must be called later to clean up.
  *
@@ -429,7 +429,7 @@ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname,
 	}
 	if (!lookup)
 		return -ENOKEY;
-	fname->is_ciphertext_name = true;
+	fname->is_nokey_name = true;
 
 	/*
 	 * We don't have the key and we are doing a lookup; decode the
@@ -538,17 +538,17 @@ static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
 
 	/*
 	 * Plaintext names are always valid, since fscrypt doesn't support
-	 * reverting to ciphertext names without evicting the directory's inode
+	 * reverting to no-key names without evicting the directory's inode
 	 * -- which implies eviction of the dentries in the directory.
 	 */
 	if (!(dentry->d_flags & DCACHE_ENCRYPTED_NAME))
 		return 1;
 
 	/*
-	 * Ciphertext name; valid if the directory's key is still unavailable.
+	 * No-key name; valid if the directory's key is still unavailable.
 	 *
-	 * Although fscrypt forbids rename() on ciphertext names, we still must
-	 * use dget_parent() here rather than use ->d_parent directly.  That's
+	 * Although fscrypt forbids rename() on no-key names, we still must use
+	 * dget_parent() here rather than use ->d_parent directly.  That's
 	 * because a corrupted fs image may contain directory hard links, which
 	 * the VFS handles by moving the directory's dentry tree in the dcache
 	 * each time ->lookup() finds the directory and it already has a dentry
diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c
index 42f5ee9f592d..ca996e1c92d9 100644
--- a/fs/crypto/hooks.c
+++ b/fs/crypto/hooks.c
@@ -60,7 +60,7 @@ int __fscrypt_prepare_link(struct inode *inode, struct inode *dir,
 	if (err)
 		return err;
 
-	/* ... in case we looked up ciphertext name before key was added */
+	/* ... in case we looked up no-key name before key was added */
 	if (dentry->d_flags & DCACHE_ENCRYPTED_NAME)
 		return -ENOKEY;
 
@@ -85,7 +85,7 @@ int __fscrypt_prepare_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (err)
 		return err;
 
-	/* ... in case we looked up ciphertext name(s) before key was added */
+	/* ... in case we looked up no-key name(s) before key was added */
 	if ((old_dentry->d_flags | new_dentry->d_flags) &
 	    DCACHE_ENCRYPTED_NAME)
 		return -ENOKEY;
@@ -114,7 +114,7 @@ int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry,
 	if (err && err != -ENOENT)
 		return err;
 
-	if (fname->is_ciphertext_name) {
+	if (fname->is_nokey_name) {
 		spin_lock(&dentry->d_lock);
 		dentry->d_flags |= DCACHE_ENCRYPTED_NAME;
 		spin_unlock(&dentry->d_lock);
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 414bc94fbd54..53fbc4dd6e48 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -111,7 +111,7 @@ static int __f2fs_setup_filename(const struct inode *dir,
 #ifdef CONFIG_FS_ENCRYPTION
 	fname->crypto_buf = crypt_name->crypto_buf;
 #endif
-	if (crypt_name->is_ciphertext_name) {
+	if (crypt_name->is_nokey_name) {
 		/* hash was decoded from the no-key name */
 		fname->hash = cpu_to_le32(crypt_name->hash);
 	} else {
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index fc67c4cbaa96..bc9ec727e993 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -35,7 +35,7 @@ struct fscrypt_name {
 	u32 hash;
 	u32 minor_hash;
 	struct fscrypt_str crypto_buf;
-	bool is_ciphertext_name;
+	bool is_nokey_name;
 };
 
 #define FSTR_INIT(n, l)		{ .name = n, .len = l }
@@ -730,17 +730,16 @@ static inline int fscrypt_prepare_rename(struct inode *old_dir,
  * @fname: (output) the name to use to search the on-disk directory
  *
  * Prepare for ->lookup() in a directory which may be encrypted by determining
- * the name that will actually be used to search the directory on-disk.  Lookups
- * can be done with or without the directory's encryption key; without the key,
- * filenames are presented in encrypted form.  Therefore, we'll try to set up
- * the directory's encryption key, but even without it the lookup can continue.
+ * the name that will actually be used to search the directory on-disk.  If the
+ * directory's encryption key is available, then the lookup is assumed to be by
+ * plaintext name; otherwise, it is assumed to be by no-key name.
  *
  * This also installs a custom ->d_revalidate() method which will invalidate the
  * dentry if it was created without the key and the key is later added.
  *
- * Return: 0 on success; -ENOENT if key is unavailable but the filename isn't a
- * correctly formed encoded ciphertext name, so a negative dentry should be
- * created; or another -errno code.
+ * Return: 0 on success; -ENOENT if the directory's key is unavailable but the
+ * filename isn't a valid no-key name, so a negative dentry should be created;
+ * or another -errno code.
  */
 static inline int fscrypt_prepare_lookup(struct inode *dir,
 					 struct dentry *dentry,
-- 
cgit v1.2.3


From 501e43fbea468fa93c1dff0ee744e69303ef5a43 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Wed, 23 Sep 2020 21:26:24 -0700
Subject: fscrypt: rename DCACHE_ENCRYPTED_NAME to DCACHE_NOKEY_NAME

Originally we used the term "encrypted name" or "ciphertext name" to
mean the encoded filename that is shown when an encrypted directory is
listed without its key.  But these terms are ambiguous since they also
mean the filename stored on-disk.  "Encrypted name" is especially
ambiguous since it could also be understood to mean "this filename is
encrypted on-disk", similar to "encrypted file".

So we've started calling these encoded names "no-key names" instead.

Therefore, rename DCACHE_ENCRYPTED_NAME to DCACHE_NOKEY_NAME to avoid
confusion about what this flag means.

Link: https://lore.kernel.org/r/20200924042624.98439-3-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 fs/crypto/fname.c       |  2 +-
 fs/crypto/hooks.c       |  7 +++----
 include/linux/dcache.h  |  2 +-
 include/linux/fscrypt.h | 12 ++++++------
 4 files changed, 11 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c
index 391acea4bc96..c65979452844 100644
--- a/fs/crypto/fname.c
+++ b/fs/crypto/fname.c
@@ -541,7 +541,7 @@ static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
 	 * reverting to no-key names without evicting the directory's inode
 	 * -- which implies eviction of the dentries in the directory.
 	 */
-	if (!(dentry->d_flags & DCACHE_ENCRYPTED_NAME))
+	if (!(dentry->d_flags & DCACHE_NOKEY_NAME))
 		return 1;
 
 	/*
diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c
index ca996e1c92d9..20b0df47fe6a 100644
--- a/fs/crypto/hooks.c
+++ b/fs/crypto/hooks.c
@@ -61,7 +61,7 @@ int __fscrypt_prepare_link(struct inode *inode, struct inode *dir,
 		return err;
 
 	/* ... in case we looked up no-key name before key was added */
-	if (dentry->d_flags & DCACHE_ENCRYPTED_NAME)
+	if (dentry->d_flags & DCACHE_NOKEY_NAME)
 		return -ENOKEY;
 
 	if (!fscrypt_has_permitted_context(dir, inode))
@@ -86,8 +86,7 @@ int __fscrypt_prepare_rename(struct inode *old_dir, struct dentry *old_dentry,
 		return err;
 
 	/* ... in case we looked up no-key name(s) before key was added */
-	if ((old_dentry->d_flags | new_dentry->d_flags) &
-	    DCACHE_ENCRYPTED_NAME)
+	if ((old_dentry->d_flags | new_dentry->d_flags) & DCACHE_NOKEY_NAME)
 		return -ENOKEY;
 
 	if (old_dir != new_dir) {
@@ -116,7 +115,7 @@ int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry,
 
 	if (fname->is_nokey_name) {
 		spin_lock(&dentry->d_lock);
-		dentry->d_flags |= DCACHE_ENCRYPTED_NAME;
+		dentry->d_flags |= DCACHE_NOKEY_NAME;
 		spin_unlock(&dentry->d_lock);
 		d_set_d_op(dentry, &fscrypt_d_ops);
 	}
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 65d975bf9390..6f95c3300cbb 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -213,7 +213,7 @@ struct dentry_operations {
 
 #define DCACHE_MAY_FREE			0x00800000
 #define DCACHE_FALLTHRU			0x01000000 /* Fall through to lower layer */
-#define DCACHE_ENCRYPTED_NAME		0x02000000 /* Encrypted name (dir key was unavailable) */
+#define DCACHE_NOKEY_NAME		0x02000000 /* Encrypted name encoded without key */
 #define DCACHE_OP_REAL			0x04000000
 
 #define DCACHE_PAR_LOOKUP		0x10000000 /* being looked up (with parent locked shared) */
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index bc9ec727e993..f1757e73162d 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -100,15 +100,15 @@ static inline bool fscrypt_needs_contents_encryption(const struct inode *inode)
 }
 
 /*
- * When d_splice_alias() moves a directory's encrypted alias to its decrypted
- * alias as a result of the encryption key being added, DCACHE_ENCRYPTED_NAME
- * must be cleared.  Note that we don't have to support arbitrary moves of this
- * flag because fscrypt doesn't allow encrypted aliases to be the source or
- * target of a rename().
+ * When d_splice_alias() moves a directory's no-key alias to its plaintext alias
+ * as a result of the encryption key being added, DCACHE_NOKEY_NAME must be
+ * cleared.  Note that we don't have to support arbitrary moves of this flag
+ * because fscrypt doesn't allow no-key names to be the source or target of a
+ * rename().
  */
 static inline void fscrypt_handle_d_move(struct dentry *dentry)
 {
-	dentry->d_flags &= ~DCACHE_ENCRYPTED_NAME;
+	dentry->d_flags &= ~DCACHE_NOKEY_NAME;
 }
 
 /* crypto.c */
-- 
cgit v1.2.3


From fe205d984e7730f4d21f6f8ebc60f0698404ac31 Mon Sep 17 00:00:00 2001
From: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Date: Tue, 18 Aug 2020 22:24:27 +0800
Subject: ACPI: Remove side effect of partly creating a node in
 acpi_map_pxm_to_online_node()

While this function will only return an online node, it can have the side
effect of partially creating a new node.  The existing comments suggest this
is intentional, but the usecases of this function are related to NFIT and
HMAT parsing, neither of which should be able to define new nodes.

One route by which the existing behaviour would cause a crash is to have a
_PXM entry in ACPI DSDT attempt to place a device within this partly
created proximity domain. A subsequent call to devm_kzalloc() or similar
would result in an attempt to allocate memory on a node for which zone
lists have not been set up and a NULL pointer dereference.

Prevent such cases by switching to pxm_to_node() within
acpi_map_pxm_to_online_node() which cannot cause a new node to be
partly created. If one would previously have been created we now
return NO_NUMA_NODE.  Documentation updated to reflect this change.

Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Hanjun Guo <guohanjun@huawei.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/acpi.h | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 1e4cdc6c7ae2..a9fd122ae878 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -430,13 +430,12 @@ int acpi_get_node(acpi_handle handle);
  * ACPI device drivers, which are called after the NUMA initialization has
  * completed in the kernel, can call this interface to obtain their device
  * NUMA topology from ACPI tables.  Such drivers do not have to deal with
- * offline nodes.  A node may be offline when a device proximity ID is
- * unique, SRAT memory entry does not exist, or NUMA is disabled, ex.
- * "numa=off" on x86.
+ * offline nodes.  A node may be offline when SRAT memory entry does not exist,
+ * or NUMA is disabled, ex. "numa=off" on x86.
  */
 static inline int acpi_map_pxm_to_online_node(int pxm)
 {
-	int node = acpi_map_pxm_to_node(pxm);
+	int node = pxm_to_node(pxm);
 
 	return numa_map_to_online_node(node);
 }
-- 
cgit v1.2.3


From 4eb3723f18e9ba4d4b13d82b6f7e68dd50a852ea Mon Sep 17 00:00:00 2001
From: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Date: Tue, 18 Aug 2020 22:24:28 +0800
Subject: ACPI: Rename acpi_map_pxm_to_online_node() to pxm_to_online_node()

As this function is no longer allowed to create new mappings
let us rename it to reflect this.

Note all nodes should already exist before any of the users
of this function are called.

Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Hanjun Guo <guohanjun@huawei.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/nfit/core.c | 3 +--
 drivers/acpi/numa/hmat.c | 2 +-
 include/linux/acpi.h     | 8 ++++----
 3 files changed, 6 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index ea0557cb54f7..8df2f16d1fdf 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -3006,8 +3006,7 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc,
 	ndr_desc->provider_data = nfit_spa;
 	ndr_desc->attr_groups = acpi_nfit_region_attribute_groups;
 	if (spa->flags & ACPI_NFIT_PROXIMITY_VALID) {
-		ndr_desc->numa_node = acpi_map_pxm_to_online_node(
-						spa->proximity_domain);
+		ndr_desc->numa_node = pxm_to_online_node(spa->proximity_domain);
 		ndr_desc->target_node = pxm_to_node(spa->proximity_domain);
 	} else {
 		ndr_desc->numa_node = NUMA_NO_NODE;
diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c
index cf6df2df26cd..e7add2609c03 100644
--- a/drivers/acpi/numa/hmat.c
+++ b/drivers/acpi/numa/hmat.c
@@ -664,7 +664,7 @@ static void hmat_register_target_device(struct memory_target *target,
 		goto out_pdev;
 	}
 
-	pdev->dev.numa_node = acpi_map_pxm_to_online_node(target->memory_pxm);
+	pdev->dev.numa_node = pxm_to_online_node(target->memory_pxm);
 	info = (struct memregion_info) {
 		.target_node = pxm_to_node(target->memory_pxm),
 	};
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index a9fd122ae878..e9f6cd67943e 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -420,10 +420,10 @@ int acpi_map_pxm_to_node(int pxm);
 int acpi_get_node(acpi_handle handle);
 
 /**
- * acpi_map_pxm_to_online_node - Map proximity ID to online node
+ * pxm_to_online_node - Map proximity ID to online node
  * @pxm: ACPI proximity ID
  *
- * This is similar to acpi_map_pxm_to_node(), but always returns an online
+ * This is similar to pxm_to_node(), but always returns an online
  * node.  When the mapped node from a given proximity ID is offline, it
  * looks up the node distance table and returns the nearest online node.
  *
@@ -433,14 +433,14 @@ int acpi_get_node(acpi_handle handle);
  * offline nodes.  A node may be offline when SRAT memory entry does not exist,
  * or NUMA is disabled, ex. "numa=off" on x86.
  */
-static inline int acpi_map_pxm_to_online_node(int pxm)
+static inline int pxm_to_online_node(int pxm)
 {
 	int node = pxm_to_node(pxm);
 
 	return numa_map_to_online_node(node);
 }
 #else
-static inline int acpi_map_pxm_to_online_node(int pxm)
+static inline int pxm_to_online_node(int pxm)
 {
 	return 0;
 }
-- 
cgit v1.2.3


From 76bd5c016ef49683d626a48748ef1764aaf8ba63 Mon Sep 17 00:00:00 2001
From: Olga Kornievskaia <kolga@netapp.com>
Date: Mon, 14 Sep 2020 17:05:08 -0400
Subject: NFSv4: make cache consistency bitmask dynamic

Client uses static bitmask for GETATTR on CLOSE/WRITE/DELEGRETURN
and ignores the fact that it might have some attributes marked
invalid in its cache. Compared to v3 where all attributes are
retrieved in postop attributes, v4's cache is frequently out of
sync and leads to standalone GETATTRs being sent to the server.

Instead, in addition to the minimum cache consistency attributes
also check cache_validity and adjust the GETATTR request accordingly.

Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/nfs4proc.c       | 45 ++++++++++++++++++++++++++++++++++++++++++---
 include/linux/nfs_xdr.h |  6 +++---
 2 files changed, 45 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index aca52e52538f..542961ffa529 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -107,6 +107,9 @@ static int nfs41_test_stateid(struct nfs_server *, nfs4_stateid *,
 static int nfs41_free_stateid(struct nfs_server *, const nfs4_stateid *,
 		const struct cred *, bool);
 #endif
+static void nfs4_bitmask_adjust(__u32 *bitmask, struct inode *inode,
+		struct nfs_server *server,
+		struct nfs4_label *label);
 
 #ifdef CONFIG_NFS_V4_SECURITY_LABEL
 static inline struct nfs4_label *
@@ -3632,9 +3635,10 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
 
 	if (calldata->arg.fmode == 0 || calldata->arg.fmode == FMODE_READ) {
 		/* Close-to-open cache consistency revalidation */
-		if (!nfs4_have_delegation(inode, FMODE_READ))
+		if (!nfs4_have_delegation(inode, FMODE_READ)) {
 			calldata->arg.bitmask = NFS_SERVER(inode)->cache_consistency_bitmask;
-		else
+			nfs4_bitmask_adjust(calldata->arg.bitmask, inode, NFS_SERVER(inode), NULL);
+		} else
 			calldata->arg.bitmask = NULL;
 	}
 
@@ -5360,6 +5364,38 @@ bool nfs4_write_need_cache_consistency_data(struct nfs_pgio_header *hdr)
 	return nfs4_have_delegation(hdr->inode, FMODE_READ) == 0;
 }
 
+static void nfs4_bitmask_adjust(__u32 *bitmask, struct inode *inode,
+				struct nfs_server *server,
+				struct nfs4_label *label)
+{
+
+	unsigned long cache_validity = READ_ONCE(NFS_I(inode)->cache_validity);
+
+	if ((cache_validity & NFS_INO_INVALID_DATA) ||
+		(cache_validity & NFS_INO_REVAL_PAGECACHE) ||
+		(cache_validity & NFS_INO_REVAL_FORCED) ||
+		(cache_validity & NFS_INO_INVALID_OTHER))
+		nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, label), inode);
+
+	if (cache_validity & NFS_INO_INVALID_ATIME)
+		bitmask[1] |= FATTR4_WORD1_TIME_ACCESS;
+	if (cache_validity & NFS_INO_INVALID_ACCESS)
+		bitmask[0] |= FATTR4_WORD1_MODE | FATTR4_WORD1_OWNER |
+				FATTR4_WORD1_OWNER_GROUP;
+	if (cache_validity & NFS_INO_INVALID_ACL)
+		bitmask[0] |= FATTR4_WORD0_ACL;
+	if (cache_validity & NFS_INO_INVALID_LABEL)
+		bitmask[2] |= FATTR4_WORD2_SECURITY_LABEL;
+	if (cache_validity & NFS_INO_INVALID_CTIME)
+		bitmask[0] |= FATTR4_WORD0_CHANGE;
+	if (cache_validity & NFS_INO_INVALID_MTIME)
+		bitmask[1] |= FATTR4_WORD1_TIME_MODIFY;
+	if (cache_validity & NFS_INO_INVALID_SIZE)
+		bitmask[0] |= FATTR4_WORD0_SIZE;
+	if (cache_validity & NFS_INO_INVALID_BLOCKS)
+		bitmask[1] |= FATTR4_WORD1_SPACE_USED;
+}
+
 static void nfs4_proc_write_setup(struct nfs_pgio_header *hdr,
 				  struct rpc_message *msg,
 				  struct rpc_clnt **clnt)
@@ -5369,8 +5405,10 @@ static void nfs4_proc_write_setup(struct nfs_pgio_header *hdr,
 	if (!nfs4_write_need_cache_consistency_data(hdr)) {
 		hdr->args.bitmask = NULL;
 		hdr->res.fattr = NULL;
-	} else
+	} else {
 		hdr->args.bitmask = server->cache_consistency_bitmask;
+		nfs4_bitmask_adjust(hdr->args.bitmask, hdr->inode, server, NULL);
+	}
 
 	if (!hdr->pgio_done_cb)
 		hdr->pgio_done_cb = nfs4_write_done_cb;
@@ -6406,6 +6444,7 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred,
 	data->args.fhandle = &data->fh;
 	data->args.stateid = &data->stateid;
 	data->args.bitmask = server->cache_consistency_bitmask;
+	nfs4_bitmask_adjust(data->args.bitmask, inode, server, NULL);
 	nfs_copy_fh(&data->fh, NFS_FH(inode));
 	nfs4_stateid_copy(&data->stateid, stateid);
 	data->res.fattr = &data->fattr;
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 69cb46f7b8d2..0599efd57eb9 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -525,7 +525,7 @@ struct nfs_closeargs {
 	struct nfs_seqid *	seqid;
 	fmode_t			fmode;
 	u32			share_access;
-	const u32 *		bitmask;
+	u32 *			bitmask;
 	struct nfs4_layoutreturn_args *lr_args;
 };
 
@@ -608,7 +608,7 @@ struct nfs4_delegreturnargs {
 	struct nfs4_sequence_args	seq_args;
 	const struct nfs_fh *fhandle;
 	const nfs4_stateid *stateid;
-	const u32 * bitmask;
+	u32 * bitmask;
 	struct nfs4_layoutreturn_args *lr_args;
 };
 
@@ -648,7 +648,7 @@ struct nfs_pgio_args {
 	union {
 		unsigned int		replen;			/* used by read */
 		struct {
-			const u32 *		bitmask;	/* used by write */
+			u32 *			bitmask;	/* used by write */
 			enum nfs3_stable_how	stable;		/* used by write */
 		};
 	};
-- 
cgit v1.2.3


From 402dd2cf46b177be5bcb138b7d7fd8f38aa130e4 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 24 Sep 2020 08:51:28 +0200
Subject: fs: remove the unused SB_I_MULTIROOT flag

The last user of SB_I_MULTIROOT is disappeared with commit f2aedb713c28
("NFS: Add fs_context support.")

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/namei.c         | 4 ++--
 include/linux/fs.h | 1 -
 2 files changed, 2 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/fs/namei.c b/fs/namei.c
index e99e2a9da0f7..f1eb8ccd2be9 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -568,8 +568,8 @@ static bool path_connected(struct vfsmount *mnt, struct dentry *dentry)
 {
 	struct super_block *sb = mnt->mnt_sb;
 
-	/* Bind mounts and multi-root filesystems can have disconnected paths */
-	if (!(sb->s_iflags & SB_I_MULTIROOT) && (mnt->mnt_root == sb->s_root))
+	/* Bind mounts can have disconnected paths */
+	if (mnt->mnt_root == sb->s_root)
 		return true;
 
 	return is_subdir(dentry, mnt->mnt_root);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7519ae003a08..fbd74df5ce5f 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1385,7 +1385,6 @@ extern int send_sigurg(struct fown_struct *fown);
 #define SB_I_CGROUPWB	0x00000001	/* cgroup-aware writeback enabled */
 #define SB_I_NOEXEC	0x00000002	/* Ignore executables on this fs */
 #define SB_I_NODEV	0x00000004	/* Ignore devices on this fs */
-#define SB_I_MULTIROOT	0x00000008	/* Multiple roots to the dentry tree */
 
 /* sb->s_iflags to limit user namespace mounts */
 #define SB_I_USERNS_VISIBLE		0x00000010 /* fstype already mounted */
-- 
cgit v1.2.3


From c2e4cd57cfa1f627b786c764d185fff85fd12be9 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 24 Sep 2020 08:51:34 +0200
Subject: block: lift setting the readahead size into the block layer

Drivers shouldn't really mess with the readahead size, as that is a VM
concept.  Instead set it based on the optimal I/O size by lifting the
algorithm from the md driver when registering the disk.  Also set
bdi->io_pages there as well by applying the same scheme based on
max_sectors.  To ensure the limits work well for stacking drivers a
new helper is added to update the readahead limits from the block
limits, which is also called from disk_stack_limits.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Mike Snitzer <snitzer@redhat.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Acked-by: Coly Li <colyli@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-settings.c         | 18 ++++++++++++++++--
 block/blk-sysfs.c            |  2 ++
 drivers/block/aoe/aoeblk.c   |  1 -
 drivers/block/drbd/drbd_nl.c | 10 +---------
 drivers/md/bcache/super.c    |  3 ---
 drivers/md/dm-table.c        |  3 +--
 drivers/md/raid0.c           | 16 ----------------
 drivers/md/raid10.c          | 24 +-----------------------
 drivers/md/raid5.c           | 13 +------------
 drivers/nvme/host/core.c     |  1 +
 include/linux/blkdev.h       |  1 +
 11 files changed, 24 insertions(+), 68 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-settings.c b/block/blk-settings.c
index 5ea3de48afba..4f6eb4bb1723 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -372,6 +372,19 @@ void blk_queue_alignment_offset(struct request_queue *q, unsigned int offset)
 }
 EXPORT_SYMBOL(blk_queue_alignment_offset);
 
+void blk_queue_update_readahead(struct request_queue *q)
+{
+	/*
+	 * For read-ahead of large files to be effective, we need to read ahead
+	 * at least twice the optimal I/O size.
+	 */
+	q->backing_dev_info->ra_pages =
+		max(queue_io_opt(q) * 2 / PAGE_SIZE, VM_READAHEAD_PAGES);
+	q->backing_dev_info->io_pages =
+		queue_max_sectors(q) >> (PAGE_SHIFT - 9);
+}
+EXPORT_SYMBOL_GPL(blk_queue_update_readahead);
+
 /**
  * blk_limits_io_min - set minimum request size for a device
  * @limits: the queue limits
@@ -450,6 +463,8 @@ EXPORT_SYMBOL(blk_limits_io_opt);
 void blk_queue_io_opt(struct request_queue *q, unsigned int opt)
 {
 	blk_limits_io_opt(&q->limits, opt);
+	q->backing_dev_info->ra_pages =
+		max(queue_io_opt(q) * 2 / PAGE_SIZE, VM_READAHEAD_PAGES);
 }
 EXPORT_SYMBOL(blk_queue_io_opt);
 
@@ -631,8 +646,7 @@ void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
 		       top, bottom);
 	}
 
-	t->backing_dev_info->io_pages =
-		t->limits.max_sectors >> (PAGE_SHIFT - 9);
+	blk_queue_update_readahead(disk->queue);
 }
 EXPORT_SYMBOL(disk_stack_limits);
 
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 81722cdcf0cb..869ed21a9edc 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -854,6 +854,8 @@ int blk_register_queue(struct gendisk *disk)
 		percpu_ref_switch_to_percpu(&q->q_usage_counter);
 	}
 
+	blk_queue_update_readahead(q);
+
 	ret = blk_trace_init_sysfs(dev);
 	if (ret)
 		return ret;
diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c
index d8cfc233e64b..c34e71b0c4a9 100644
--- a/drivers/block/aoe/aoeblk.c
+++ b/drivers/block/aoe/aoeblk.c
@@ -406,7 +406,6 @@ aoeblk_gdalloc(void *vp)
 	WARN_ON(d->gd);
 	WARN_ON(d->flags & DEVFL_UP);
 	blk_queue_max_hw_sectors(q, BLK_DEF_MAX_SECTORS);
-	q->backing_dev_info->ra_pages = SZ_2M / PAGE_SIZE;
 	blk_queue_io_opt(q, SZ_2M);
 	d->bufpool = mp;
 	d->blkq = gd->queue = q;
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index aaff5bde3915..54a4930c04fe 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -1362,15 +1362,7 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi
 
 	if (b) {
 		blk_stack_limits(&q->limits, &b->limits, 0);
-
-		if (q->backing_dev_info->ra_pages !=
-		    b->backing_dev_info->ra_pages) {
-			drbd_info(device, "Adjusting my ra_pages to backing device's (%lu -> %lu)\n",
-				 q->backing_dev_info->ra_pages,
-				 b->backing_dev_info->ra_pages);
-			q->backing_dev_info->ra_pages =
-						b->backing_dev_info->ra_pages;
-		}
+		blk_queue_update_readahead(q);
 	}
 	fixup_discard_if_not_supported(q);
 	fixup_write_zeroes(device, q);
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 48113005ed86..6bfa77167362 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1427,9 +1427,6 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size)
 	if (ret)
 		return ret;
 
-	dc->disk.disk->queue->backing_dev_info->ra_pages =
-		max(dc->disk.disk->queue->backing_dev_info->ra_pages,
-		    q->backing_dev_info->ra_pages);
 	blk_queue_io_opt(dc->disk.disk->queue,
 		max(queue_io_opt(dc->disk.disk->queue), queue_io_opt(q)));
 
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 5edc3079e7c1..ef2757012f59 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1925,8 +1925,7 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	}
 #endif
 
-	/* Allow reads to exceed readahead limits */
-	q->backing_dev_info->io_pages = limits->max_sectors >> (PAGE_SHIFT - 9);
+	blk_queue_update_readahead(q);
 }
 
 unsigned int dm_table_get_num_targets(struct dm_table *t)
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index f54a449f97aa..aa2d72791768 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -410,22 +410,6 @@ static int raid0_run(struct mddev *mddev)
 		 mdname(mddev),
 		 (unsigned long long)mddev->array_sectors);
 
-	if (mddev->queue) {
-		/* calculate the max read-ahead size.
-		 * For read-ahead of large files to be effective, we need to
-		 * readahead at least twice a whole stripe. i.e. number of devices
-		 * multiplied by chunk size times 2.
-		 * If an individual device has an ra_pages greater than the
-		 * chunk size, then we will not drive that device as hard as it
-		 * wants.  We consider this a configuration error: a larger
-		 * chunksize should be used in that case.
-		 */
-		int stripe = mddev->raid_disks *
-			(mddev->chunk_sectors << 9) / PAGE_SIZE;
-		if (mddev->queue->backing_dev_info->ra_pages < 2* stripe)
-			mddev->queue->backing_dev_info->ra_pages = 2* stripe;
-	}
-
 	dump_zones(mddev);
 
 	ret = md_integrity_register(mddev);
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 9956a04ac13b..5d1bdee313ec 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -3873,19 +3873,6 @@ static int raid10_run(struct mddev *mddev)
 	mddev->resync_max_sectors = size;
 	set_bit(MD_FAILFAST_SUPPORTED, &mddev->flags);
 
-	if (mddev->queue) {
-		int stripe = conf->geo.raid_disks *
-			((mddev->chunk_sectors << 9) / PAGE_SIZE);
-
-		/* Calculate max read-ahead size.
-		 * We need to readahead at least twice a whole stripe....
-		 * maybe...
-		 */
-		stripe /= conf->geo.near_copies;
-		if (mddev->queue->backing_dev_info->ra_pages < 2 * stripe)
-			mddev->queue->backing_dev_info->ra_pages = 2 * stripe;
-	}
-
 	if (md_integrity_register(mddev))
 		goto out_free_conf;
 
@@ -4723,17 +4710,8 @@ static void end_reshape(struct r10conf *conf)
 	conf->reshape_safe = MaxSector;
 	spin_unlock_irq(&conf->device_lock);
 
-	/* read-ahead size must cover two whole stripes, which is
-	 * 2 * (datadisks) * chunksize where 'n' is the number of raid devices
-	 */
-	if (conf->mddev->queue) {
-		int stripe = conf->geo.raid_disks *
-			((conf->mddev->chunk_sectors << 9) / PAGE_SIZE);
-		stripe /= conf->geo.near_copies;
-		if (conf->mddev->queue->backing_dev_info->ra_pages < 2 * stripe)
-			conf->mddev->queue->backing_dev_info->ra_pages = 2 * stripe;
+	if (conf->mddev->queue)
 		raid10_set_io_opt(conf);
-	}
 	conf->fullsync = 0;
 }
 
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 9a7d1250894e..7ace1f76b147 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -7522,8 +7522,6 @@ static int raid5_run(struct mddev *mddev)
 		int data_disks = conf->previous_raid_disks - conf->max_degraded;
 		int stripe = data_disks *
 			((mddev->chunk_sectors << 9) / PAGE_SIZE);
-		if (mddev->queue->backing_dev_info->ra_pages < 2 * stripe)
-			mddev->queue->backing_dev_info->ra_pages = 2 * stripe;
 
 		chunk_size = mddev->chunk_sectors << 9;
 		blk_queue_io_min(mddev->queue, chunk_size);
@@ -8111,17 +8109,8 @@ static void end_reshape(struct r5conf *conf)
 		spin_unlock_irq(&conf->device_lock);
 		wake_up(&conf->wait_for_overlap);
 
-		/* read-ahead size must cover two whole stripes, which is
-		 * 2 * (datadisks) * chunksize where 'n' is the number of raid devices
-		 */
-		if (conf->mddev->queue) {
-			int data_disks = conf->raid_disks - conf->max_degraded;
-			int stripe = data_disks * ((conf->chunk_sectors << 9)
-						   / PAGE_SIZE);
-			if (conf->mddev->queue->backing_dev_info->ra_pages < 2 * stripe)
-				conf->mddev->queue->backing_dev_info->ra_pages = 2 * stripe;
+		if (conf->mddev->queue)
 			raid5_set_io_opt(conf);
-		}
 	}
 }
 
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index ea1fa41fbba8..741c9bfa8e14 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2147,6 +2147,7 @@ static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 		nvme_update_disk_info(ns->head->disk, ns, id);
 		blk_stack_limits(&ns->head->disk->queue->limits,
 				 &ns->queue->limits, 0);
+		blk_queue_update_readahead(ns->head->disk->queue);
 		nvme_update_bdev_size(ns->head->disk);
 	}
 #endif
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index be5ef6f4ba19..282f5ca424f1 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1140,6 +1140,7 @@ extern void blk_queue_max_zone_append_sectors(struct request_queue *q,
 extern void blk_queue_physical_block_size(struct request_queue *, unsigned int);
 extern void blk_queue_alignment_offset(struct request_queue *q,
 				       unsigned int alignment);
+void blk_queue_update_readahead(struct request_queue *q);
 extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min);
 extern void blk_queue_io_min(struct request_queue *q, unsigned int min);
 extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt);
-- 
cgit v1.2.3


From ed7b6b4f6e915cb0bc52d0000bcc63168867b6ac Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 24 Sep 2020 08:51:35 +0200
Subject: bdi: remove BDI_CAP_CGROUP_WRITEBACK

Just checking SB_I_CGROUPWB for cgroup writeback support is enough.
Either the file system allocates its own bdi (e.g. btrfs), in which case
it is known to support cgroup writeback, or the bdi comes from the block
layer, which always supports cgroup writeback.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c            | 1 -
 fs/btrfs/disk-io.c          | 1 -
 include/linux/backing-dev.h | 8 +++-----
 3 files changed, 3 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-core.c b/block/blk-core.c
index 865d39e5be2b..1cc4fa6bc7fe 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -538,7 +538,6 @@ struct request_queue *blk_alloc_queue(int node_id)
 	if (!q->stats)
 		goto fail_stats;
 
-	q->backing_dev_info->capabilities = BDI_CAP_CGROUP_WRITEBACK;
 	q->node = node_id;
 
 	atomic_set(&q->nr_active_requests_shared_sbitmap, 0);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 047934cea25e..e24927bddd58 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3091,7 +3091,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 		goto fail_sb_buffer;
 	}
 
-	sb->s_bdi->capabilities |= BDI_CAP_CGROUP_WRITEBACK;
 	sb->s_bdi->ra_pages *= btrfs_super_num_devices(disk_super);
 	sb->s_bdi->ra_pages = max(sb->s_bdi->ra_pages, SZ_4M / PAGE_SIZE);
 
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 0b06b2d26c9a..52583b6f2ea0 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -123,7 +123,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
  * BDI_CAP_NO_ACCT_WB:     Don't automatically account writeback pages
  * BDI_CAP_STRICTLIMIT:    Keep number of dirty pages below bdi threshold.
  *
- * BDI_CAP_CGROUP_WRITEBACK: Supports cgroup-aware writeback.
  * BDI_CAP_SYNCHRONOUS_IO: Device is so fast that asynchronous IO would be
  *			   inefficient.
  */
@@ -233,9 +232,9 @@ int inode_congested(struct inode *inode, int cong_bits);
  * inode_cgwb_enabled - test whether cgroup writeback is enabled on an inode
  * @inode: inode of interest
  *
- * cgroup writeback requires support from both the bdi and filesystem.
- * Also, both memcg and iocg have to be on the default hierarchy.  Test
- * whether all conditions are met.
+ * Cgroup writeback requires support from the filesystem.  Also, both memcg and
+ * iocg have to be on the default hierarchy.  Test whether all conditions are
+ * met.
  *
  * Note that the test result may change dynamically on the same inode
  * depending on how memcg and iocg are configured.
@@ -247,7 +246,6 @@ static inline bool inode_cgwb_enabled(struct inode *inode)
 	return cgroup_subsys_on_dfl(memory_cgrp_subsys) &&
 		cgroup_subsys_on_dfl(io_cgrp_subsys) &&
 		bdi_cap_account_dirty(bdi) &&
-		(bdi->capabilities & BDI_CAP_CGROUP_WRITEBACK) &&
 		(inode->i_sb->s_iflags & SB_I_CGROUPWB);
 }
 
-- 
cgit v1.2.3


From a8b456d01cd6b37191f14248f3e2bdbe5ce3a89e Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 24 Sep 2020 08:51:36 +0200
Subject: bdi: remove BDI_CAP_SYNCHRONOUS_IO

BDI_CAP_SYNCHRONOUS_IO is only checked in the swap code, and used to
decided if ->rw_page can be used on a block device.  Just check up for
the method instead.  The only complication is that zram needs a second
set of block_device_operations as it can switch between modes that
actually support ->rw_page and those who don't.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/brd.c           |  1 -
 drivers/block/zram/zram_drv.c | 19 +++++++++++++------
 drivers/nvdimm/btt.c          |  2 --
 drivers/nvdimm/pmem.c         |  1 -
 include/linux/backing-dev.h   |  9 ---------
 mm/swapfile.c                 |  2 +-
 6 files changed, 14 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 2723a70eb855..cc49a921339f 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -403,7 +403,6 @@ static struct brd_device *brd_alloc(int i)
 	disk->flags		= GENHD_FL_EXT_DEVT;
 	sprintf(disk->disk_name, "ram%d", i);
 	set_capacity(disk, rd_size * 2);
-	brd->brd_queue->backing_dev_info->capabilities |= BDI_CAP_SYNCHRONOUS_IO;
 
 	/* Tell the block layer that this is not a rotational device */
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, brd->brd_queue);
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 91ccfe444525..e21ca844d7c2 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -52,6 +52,9 @@ static unsigned int num_devices = 1;
  */
 static size_t huge_class_size;
 
+static const struct block_device_operations zram_devops;
+static const struct block_device_operations zram_wb_devops;
+
 static void zram_free_page(struct zram *zram, size_t index);
 static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
 				u32 index, int offset, struct bio *bio);
@@ -408,8 +411,7 @@ static void reset_bdev(struct zram *zram)
 	zram->backing_dev = NULL;
 	zram->old_block_size = 0;
 	zram->bdev = NULL;
-	zram->disk->queue->backing_dev_info->capabilities |=
-				BDI_CAP_SYNCHRONOUS_IO;
+	zram->disk->fops = &zram_devops;
 	kvfree(zram->bitmap);
 	zram->bitmap = NULL;
 }
@@ -529,8 +531,7 @@ static ssize_t backing_dev_store(struct device *dev,
 	 * freely but in fact, IO is going on so finally could cause
 	 * use-after-free when the IO is really done.
 	 */
-	zram->disk->queue->backing_dev_info->capabilities &=
-			~BDI_CAP_SYNCHRONOUS_IO;
+	zram->disk->fops = &zram_wb_devops;
 	up_write(&zram->init_lock);
 
 	pr_info("setup backing device %s\n", file_name);
@@ -1820,6 +1821,13 @@ static const struct block_device_operations zram_devops = {
 	.owner = THIS_MODULE
 };
 
+static const struct block_device_operations zram_wb_devops = {
+	.open = zram_open,
+	.submit_bio = zram_submit_bio,
+	.swap_slot_free_notify = zram_slot_free_notify,
+	.owner = THIS_MODULE
+};
+
 static DEVICE_ATTR_WO(compact);
 static DEVICE_ATTR_RW(disksize);
 static DEVICE_ATTR_RO(initstate);
@@ -1947,8 +1955,7 @@ static int zram_add(void)
 	if (ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE)
 		blk_queue_max_write_zeroes_sectors(zram->disk->queue, UINT_MAX);
 
-	zram->disk->queue->backing_dev_info->capabilities |=
-			(BDI_CAP_STABLE_WRITES | BDI_CAP_SYNCHRONOUS_IO);
+	zram->disk->queue->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
 	device_add_disk(NULL, zram->disk, zram_disk_attr_groups);
 
 	strlcpy(zram->compressor, default_compressor, sizeof(zram->compressor));
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index 0d710140bf93..12ff6f8784ac 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -1537,8 +1537,6 @@ static int btt_blk_init(struct btt *btt)
 	btt->btt_disk->private_data = btt;
 	btt->btt_disk->queue = btt->btt_queue;
 	btt->btt_disk->flags = GENHD_FL_EXT_DEVT;
-	btt->btt_disk->queue->backing_dev_info->capabilities |=
-			BDI_CAP_SYNCHRONOUS_IO;
 
 	blk_queue_logical_block_size(btt->btt_queue, btt->sector_size);
 	blk_queue_max_hw_sectors(btt->btt_queue, UINT_MAX);
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 140cf3b9000c..1711fdfd8d28 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -475,7 +475,6 @@ static int pmem_attach_disk(struct device *dev,
 	disk->queue		= q;
 	disk->flags		= GENHD_FL_EXT_DEVT;
 	disk->private_data	= pmem;
-	disk->queue->backing_dev_info->capabilities |= BDI_CAP_SYNCHRONOUS_IO;
 	nvdimm_namespace_disk_name(ndns, disk->disk_name);
 	set_capacity(disk, (pmem->size - pmem->pfn_pad - pmem->data_offset)
 			/ 512);
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 52583b6f2ea0..860ea33571bc 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -122,9 +122,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
  * BDI_CAP_NO_WRITEBACK:   Don't write pages back
  * BDI_CAP_NO_ACCT_WB:     Don't automatically account writeback pages
  * BDI_CAP_STRICTLIMIT:    Keep number of dirty pages below bdi threshold.
- *
- * BDI_CAP_SYNCHRONOUS_IO: Device is so fast that asynchronous IO would be
- *			   inefficient.
  */
 #define BDI_CAP_NO_ACCT_DIRTY	0x00000001
 #define BDI_CAP_NO_WRITEBACK	0x00000002
@@ -132,7 +129,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
 #define BDI_CAP_STABLE_WRITES	0x00000008
 #define BDI_CAP_STRICTLIMIT	0x00000010
 #define BDI_CAP_CGROUP_WRITEBACK 0x00000020
-#define BDI_CAP_SYNCHRONOUS_IO	0x00000040
 
 #define BDI_CAP_NO_ACCT_AND_WRITEBACK \
 	(BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_ACCT_WB)
@@ -174,11 +170,6 @@ static inline int wb_congested(struct bdi_writeback *wb, int cong_bits)
 long congestion_wait(int sync, long timeout);
 long wait_iff_congested(int sync, long timeout);
 
-static inline bool bdi_cap_synchronous_io(struct backing_dev_info *bdi)
-{
-	return bdi->capabilities & BDI_CAP_SYNCHRONOUS_IO;
-}
-
 static inline bool bdi_cap_stable_pages_required(struct backing_dev_info *bdi)
 {
 	return bdi->capabilities & BDI_CAP_STABLE_WRITES;
diff --git a/mm/swapfile.c b/mm/swapfile.c
index b90f86920743..96a7c47dd533 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -3240,7 +3240,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	if (bdi_cap_stable_pages_required(inode_to_bdi(inode)))
 		p->flags |= SWP_STABLE_WRITES;
 
-	if (bdi_cap_synchronous_io(inode_to_bdi(inode)))
+	if (p->bdev && p->bdev->bd_disk->fops->rw_page)
 		p->flags |= SWP_SYNCHRONOUS_IO;
 
 	if (p->bdev && blk_queue_nonrot(bdev_get_queue(p->bdev))) {
-- 
cgit v1.2.3


From 1cb039f3dc1619eb795c54aad0a98fdb379b4237 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 24 Sep 2020 08:51:38 +0200
Subject: bdi: replace BDI_CAP_STABLE_WRITES with a queue and a sb flag

The BDI_CAP_STABLE_WRITES is one of the few bits of information in the
backing_dev_info shared between the block drivers and the writeback code.
To help untangling the dependency replace it with a queue flag and a
superblock flag derived from it.  This also helps with the case of e.g.
a file system requiring stable writes due to its own checksumming, but
not forcing it on other users of the block device like the swap code.

One downside is that we an't support the stable_pages_required bdi
attribute in sysfs anymore.  It is replaced with a queue attribute which
also is writable for easier testing.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-integrity.c         |  4 ++--
 block/blk-mq-debugfs.c        |  1 +
 block/blk-sysfs.c             |  3 +++
 drivers/block/rbd.c           |  2 +-
 drivers/block/zram/zram_drv.c |  2 +-
 drivers/md/dm-table.c         |  6 +++---
 drivers/md/raid5.c            |  8 ++++----
 drivers/mmc/core/queue.c      |  3 +--
 drivers/nvme/host/core.c      |  3 +--
 drivers/nvme/host/multipath.c | 10 +++-------
 drivers/scsi/iscsi_tcp.c      |  4 ++--
 fs/super.c                    |  2 ++
 include/linux/backing-dev.h   |  6 ------
 include/linux/blkdev.h        |  3 +++
 include/linux/fs.h            |  1 +
 mm/backing-dev.c              |  7 +++----
 mm/page-writeback.c           |  2 +-
 mm/swapfile.c                 |  2 +-
 18 files changed, 33 insertions(+), 36 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index c03705cbb9c9..2b36a8f9b813 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -408,7 +408,7 @@ void blk_integrity_register(struct gendisk *disk, struct blk_integrity *template
 	bi->tuple_size = template->tuple_size;
 	bi->tag_size = template->tag_size;
 
-	disk->queue->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
+	blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, disk->queue);
 
 #ifdef CONFIG_BLK_INLINE_ENCRYPTION
 	if (disk->queue->ksm) {
@@ -428,7 +428,7 @@ EXPORT_SYMBOL(blk_integrity_register);
  */
 void blk_integrity_unregister(struct gendisk *disk)
 {
-	disk->queue->backing_dev_info->capabilities &= ~BDI_CAP_STABLE_WRITES;
+	blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, disk->queue);
 	memset(&disk->queue->integrity, 0, sizeof(struct blk_integrity));
 }
 EXPORT_SYMBOL(blk_integrity_unregister);
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 645b7f800cb8..3094542e12ae 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -116,6 +116,7 @@ static const char *const blk_queue_flag_name[] = {
 	QUEUE_FLAG_NAME(SAME_FORCE),
 	QUEUE_FLAG_NAME(DEAD),
 	QUEUE_FLAG_NAME(INIT_DONE),
+	QUEUE_FLAG_NAME(STABLE_WRITES),
 	QUEUE_FLAG_NAME(POLL),
 	QUEUE_FLAG_NAME(WC),
 	QUEUE_FLAG_NAME(FUA),
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 869ed21a9edc..76b54c7750b0 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -287,6 +287,7 @@ queue_##name##_store(struct request_queue *q, const char *page, size_t count) \
 QUEUE_SYSFS_BIT_FNS(nonrot, NONROT, 1);
 QUEUE_SYSFS_BIT_FNS(random, ADD_RANDOM, 0);
 QUEUE_SYSFS_BIT_FNS(iostats, IO_STAT, 0);
+QUEUE_SYSFS_BIT_FNS(stable_writes, STABLE_WRITES, 0);
 #undef QUEUE_SYSFS_BIT_FNS
 
 static ssize_t queue_zoned_show(struct request_queue *q, char *page)
@@ -613,6 +614,7 @@ static struct queue_sysfs_entry queue_hw_sector_size_entry = {
 QUEUE_RW_ENTRY(queue_nonrot, "rotational");
 QUEUE_RW_ENTRY(queue_iostats, "iostats");
 QUEUE_RW_ENTRY(queue_random, "add_random");
+QUEUE_RW_ENTRY(queue_stable_writes, "stable_writes");
 
 static struct attribute *queue_attrs[] = {
 	&queue_requests_entry.attr,
@@ -645,6 +647,7 @@ static struct attribute *queue_attrs[] = {
 	&queue_nomerges_entry.attr,
 	&queue_rq_affinity_entry.attr,
 	&queue_iostats_entry.attr,
+	&queue_stable_writes_entry.attr,
 	&queue_random_entry.attr,
 	&queue_poll_entry.attr,
 	&queue_wc_entry.attr,
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 5d3923c0997c..cf5b016358cd 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -5022,7 +5022,7 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	}
 
 	if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC))
-		q->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
+		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q);
 
 	/*
 	 * disk_release() expects a queue ref from add_disk() and will
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index e21ca844d7c2..bff3d4021c18 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -1955,7 +1955,7 @@ static int zram_add(void)
 	if (ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE)
 		blk_queue_max_write_zeroes_sectors(zram->disk->queue, UINT_MAX);
 
-	zram->disk->queue->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
+	blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, zram->disk->queue);
 	device_add_disk(NULL, zram->disk, zram_disk_attr_groups);
 
 	strlcpy(zram->compressor, default_compressor, sizeof(zram->compressor));
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index ef2757012f59..405d7cf10eb9 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1815,7 +1815,7 @@ static int device_requires_stable_pages(struct dm_target *ti,
 {
 	struct request_queue *q = bdev_get_queue(dev->bdev);
 
-	return q && bdi_cap_stable_pages_required(q->backing_dev_info);
+	return q && blk_queue_stable_writes(q);
 }
 
 /*
@@ -1900,9 +1900,9 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	 * because they do their own checksumming.
 	 */
 	if (dm_table_requires_stable_pages(t))
-		q->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
+		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q);
 	else
-		q->backing_dev_info->capabilities &= ~BDI_CAP_STABLE_WRITES;
+		blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, q);
 
 	/*
 	 * Determine whether or not this queue's I/O timings contribute
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 7ace1f76b147..d589d26c86ea 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -6638,14 +6638,14 @@ raid5_store_skip_copy(struct mddev *mddev, const char *page, size_t len)
 	if (!conf)
 		err = -ENODEV;
 	else if (new != conf->skip_copy) {
+		struct request_queue *q = mddev->queue;
+
 		mddev_suspend(mddev);
 		conf->skip_copy = new;
 		if (new)
-			mddev->queue->backing_dev_info->capabilities |=
-				BDI_CAP_STABLE_WRITES;
+			blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q);
 		else
-			mddev->queue->backing_dev_info->capabilities &=
-				~BDI_CAP_STABLE_WRITES;
+			blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, q);
 		mddev_resume(mddev);
 	}
 	mddev_unlock(mddev);
diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c
index 6c022ef0f84d..80fe3852ce0f 100644
--- a/drivers/mmc/core/queue.c
+++ b/drivers/mmc/core/queue.c
@@ -472,8 +472,7 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card)
 	}
 
 	if (mmc_host_is_spi(host) && host->use_spi_crc)
-		mq->queue->backing_dev_info->capabilities |=
-			BDI_CAP_STABLE_WRITES;
+		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, mq->queue);
 
 	mq->queue->queuedata = mq;
 	blk_queue_rq_timeout(mq->queue, 60 * HZ);
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 741c9bfa8e14..c190c56bf702 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -3926,8 +3926,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 		goto out_free_ns;
 
 	if (ctrl->opts && ctrl->opts->data_digest)
-		ns->queue->backing_dev_info->capabilities
-			|= BDI_CAP_STABLE_WRITES;
+		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, ns->queue);
 
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, ns->queue);
 	if (ctrl->ops->flags & NVME_F_PCI_P2PDMA)
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index d4ba736c6c89..74896be40c17 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -673,13 +673,9 @@ void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id)
 		nvme_mpath_set_live(ns);
 	}
 
-	if (bdi_cap_stable_pages_required(ns->queue->backing_dev_info)) {
-		struct gendisk *disk = ns->head->disk;
-
-		if (disk)
-			disk->queue->backing_dev_info->capabilities |=
-					BDI_CAP_STABLE_WRITES;
-	}
+	if (blk_queue_stable_writes(ns->queue) && ns->head->disk)
+		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES,
+				   ns->head->disk->queue);
 }
 
 void nvme_mpath_remove_disk(struct nvme_ns_head *head)
diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c
index b5dd1caae5e9..a622f334c933 100644
--- a/drivers/scsi/iscsi_tcp.c
+++ b/drivers/scsi/iscsi_tcp.c
@@ -962,8 +962,8 @@ static int iscsi_sw_tcp_slave_configure(struct scsi_device *sdev)
 	struct iscsi_conn *conn = session->leadconn;
 
 	if (conn->datadgst_en)
-		sdev->request_queue->backing_dev_info->capabilities
-			|= BDI_CAP_STABLE_WRITES;
+		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES,
+				   sdev->request_queue);
 	blk_queue_dma_alignment(sdev->request_queue, 0);
 	return 0;
 }
diff --git a/fs/super.c b/fs/super.c
index 904459b35119..a51c2083cd6b 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1256,6 +1256,8 @@ static int set_bdev_super(struct super_block *s, void *data)
 	s->s_dev = s->s_bdev->bd_dev;
 	s->s_bdi = bdi_get(s->s_bdev->bd_bdi);
 
+	if (blk_queue_stable_writes(s->s_bdev->bd_disk->queue))
+		s->s_iflags |= SB_I_STABLE_WRITES;
 	return 0;
 }
 
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 860ea33571bc..5da4ea3dd0cc 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -126,7 +126,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
 #define BDI_CAP_NO_ACCT_DIRTY	0x00000001
 #define BDI_CAP_NO_WRITEBACK	0x00000002
 #define BDI_CAP_NO_ACCT_WB	0x00000004
-#define BDI_CAP_STABLE_WRITES	0x00000008
 #define BDI_CAP_STRICTLIMIT	0x00000010
 #define BDI_CAP_CGROUP_WRITEBACK 0x00000020
 
@@ -170,11 +169,6 @@ static inline int wb_congested(struct bdi_writeback *wb, int cong_bits)
 long congestion_wait(int sync, long timeout);
 long wait_iff_congested(int sync, long timeout);
 
-static inline bool bdi_cap_stable_pages_required(struct backing_dev_info *bdi)
-{
-	return bdi->capabilities & BDI_CAP_STABLE_WRITES;
-}
-
 static inline bool bdi_cap_writeback_dirty(struct backing_dev_info *bdi)
 {
 	return !(bdi->capabilities & BDI_CAP_NO_WRITEBACK);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 282f5ca424f1..8e77f12de522 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -606,6 +606,7 @@ struct request_queue {
 #define QUEUE_FLAG_SAME_FORCE	12	/* force complete on same CPU */
 #define QUEUE_FLAG_DEAD		13	/* queue tear-down finished */
 #define QUEUE_FLAG_INIT_DONE	14	/* queue is initialized */
+#define QUEUE_FLAG_STABLE_WRITES 15	/* don't modify blks until WB is done */
 #define QUEUE_FLAG_POLL		16	/* IO polling enabled if set */
 #define QUEUE_FLAG_WC		17	/* Write back caching */
 #define QUEUE_FLAG_FUA		18	/* device supports FUA writes */
@@ -635,6 +636,8 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
 #define blk_queue_noxmerges(q)	\
 	test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags)
 #define blk_queue_nonrot(q)	test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags)
+#define blk_queue_stable_writes(q) \
+	test_bit(QUEUE_FLAG_STABLE_WRITES, &(q)->queue_flags)
 #define blk_queue_io_stat(q)	test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags)
 #define blk_queue_add_random(q)	test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags)
 #define blk_queue_discard(q)	test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index fbd74df5ce5f..222465b7cf41 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1385,6 +1385,7 @@ extern int send_sigurg(struct fown_struct *fown);
 #define SB_I_CGROUPWB	0x00000001	/* cgroup-aware writeback enabled */
 #define SB_I_NOEXEC	0x00000002	/* Ignore executables on this fs */
 #define SB_I_NODEV	0x00000004	/* Ignore devices on this fs */
+#define SB_I_STABLE_WRITES 0x00000008	/* don't modify blks until WB is done */
 
 /* sb->s_iflags to limit user namespace mounts */
 #define SB_I_USERNS_VISIBLE		0x00000010 /* fstype already mounted */
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 2dac3be61271..8e3802bf03a9 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -204,10 +204,9 @@ static ssize_t stable_pages_required_show(struct device *dev,
 					  struct device_attribute *attr,
 					  char *page)
 {
-	struct backing_dev_info *bdi = dev_get_drvdata(dev);
-
-	return snprintf(page, PAGE_SIZE-1, "%d\n",
-			bdi_cap_stable_pages_required(bdi) ? 1 : 0);
+	dev_warn_once(dev,
+		"the stable_pages_required attribute has been removed. Use the stable_writes queue attribute instead.\n");
+	return snprintf(page, PAGE_SIZE-1, "%d\n", 0);
 }
 static DEVICE_ATTR_RO(stable_pages_required);
 
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 4e4ddd67b71e..e9c36521461a 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2849,7 +2849,7 @@ EXPORT_SYMBOL_GPL(wait_on_page_writeback);
  */
 void wait_for_stable_page(struct page *page)
 {
-	if (bdi_cap_stable_pages_required(inode_to_bdi(page->mapping->host)))
+	if (page->mapping->host->i_sb->s_iflags & SB_I_STABLE_WRITES)
 		wait_on_page_writeback(page);
 }
 EXPORT_SYMBOL_GPL(wait_for_stable_page);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 96a7c47dd533..65ef407512b5 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -3237,7 +3237,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 		goto bad_swap_unlock_inode;
 	}
 
-	if (bdi_cap_stable_pages_required(inode_to_bdi(inode)))
+	if (p->bdev && blk_queue_stable_writes(p->bdev->bd_disk->queue))
 		p->flags |= SWP_STABLE_WRITES;
 
 	if (p->bdev && p->bdev->bd_disk->fops->rw_page)
-- 
cgit v1.2.3


From 823423ef55f4d9c470b1edc9c5b5c93d06abfaae Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 24 Sep 2020 08:51:39 +0200
Subject: bdi: invert BDI_CAP_NO_ACCT_WB

Replace BDI_CAP_NO_ACCT_WB with a positive BDI_CAP_WRITEBACK_ACCT to
make the checks more obvious.  Also remove the pointless
bdi_cap_account_writeback wrapper that just obsfucates the check.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/fuse/inode.c             |  3 ++-
 include/linux/backing-dev.h | 13 +++----------
 mm/backing-dev.c            |  1 +
 mm/page-writeback.c         |  4 ++--
 4 files changed, 8 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 17b00670fb53..581329203d68 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -1050,7 +1050,8 @@ static int fuse_bdi_init(struct fuse_conn *fc, struct super_block *sb)
 		return err;
 
 	/* fuse does it's own writeback accounting */
-	sb->s_bdi->capabilities = BDI_CAP_NO_ACCT_WB | BDI_CAP_STRICTLIMIT;
+	sb->s_bdi->capabilities &= ~BDI_CAP_WRITEBACK_ACCT;
+	sb->s_bdi->capabilities |= BDI_CAP_STRICTLIMIT;
 
 	/*
 	 * For a single fuse filesystem use max 1% of dirty +
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 5da4ea3dd0cc..b217344a2c63 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -120,17 +120,17 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
  *
  * BDI_CAP_NO_ACCT_DIRTY:  Dirty pages shouldn't contribute to accounting
  * BDI_CAP_NO_WRITEBACK:   Don't write pages back
- * BDI_CAP_NO_ACCT_WB:     Don't automatically account writeback pages
+ * BDI_CAP_WRITEBACK_ACCT: Automatically account writeback pages
  * BDI_CAP_STRICTLIMIT:    Keep number of dirty pages below bdi threshold.
  */
 #define BDI_CAP_NO_ACCT_DIRTY	0x00000001
 #define BDI_CAP_NO_WRITEBACK	0x00000002
-#define BDI_CAP_NO_ACCT_WB	0x00000004
+#define BDI_CAP_WRITEBACK_ACCT	0x00000004
 #define BDI_CAP_STRICTLIMIT	0x00000010
 #define BDI_CAP_CGROUP_WRITEBACK 0x00000020
 
 #define BDI_CAP_NO_ACCT_AND_WRITEBACK \
-	(BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_ACCT_WB)
+	(BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY)
 
 extern struct backing_dev_info noop_backing_dev_info;
 
@@ -179,13 +179,6 @@ static inline bool bdi_cap_account_dirty(struct backing_dev_info *bdi)
 	return !(bdi->capabilities & BDI_CAP_NO_ACCT_DIRTY);
 }
 
-static inline bool bdi_cap_account_writeback(struct backing_dev_info *bdi)
-{
-	/* Paranoia: BDI_CAP_NO_WRITEBACK implies BDI_CAP_NO_ACCT_WB */
-	return !(bdi->capabilities & (BDI_CAP_NO_ACCT_WB |
-				      BDI_CAP_NO_WRITEBACK));
-}
-
 static inline bool mapping_cap_writeback_dirty(struct address_space *mapping)
 {
 	return bdi_cap_writeback_dirty(inode_to_bdi(mapping->host));
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 8e3802bf03a9..df18f0088dd3 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -745,6 +745,7 @@ struct backing_dev_info *bdi_alloc(int node_id)
 		kfree(bdi);
 		return NULL;
 	}
+	bdi->capabilities = BDI_CAP_WRITEBACK_ACCT;
 	bdi->ra_pages = VM_READAHEAD_PAGES;
 	bdi->io_pages = VM_READAHEAD_PAGES;
 	return bdi;
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index e9c36521461a..0139f9622a92 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2738,7 +2738,7 @@ int test_clear_page_writeback(struct page *page)
 		if (ret) {
 			__xa_clear_mark(&mapping->i_pages, page_index(page),
 						PAGECACHE_TAG_WRITEBACK);
-			if (bdi_cap_account_writeback(bdi)) {
+			if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) {
 				struct bdi_writeback *wb = inode_to_wb(inode);
 
 				dec_wb_stat(wb, WB_WRITEBACK);
@@ -2791,7 +2791,7 @@ int __test_set_page_writeback(struct page *page, bool keep_write)
 						   PAGECACHE_TAG_WRITEBACK);
 
 			xas_set_mark(&xas, PAGECACHE_TAG_WRITEBACK);
-			if (bdi_cap_account_writeback(bdi))
+			if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT)
 				inc_wb_stat(inode_to_wb(inode), WB_WRITEBACK);
 
 			/*
-- 
cgit v1.2.3


From f56753ac2a90810726334df04d735e9f8f5a32d9 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 24 Sep 2020 08:51:40 +0200
Subject: bdi: replace BDI_CAP_NO_{WRITEBACK,ACCT_DIRTY} with a single flag

Replace the two negative flags that are always used together with a
single positive flag that indicates the writeback capability instead
of two related non-capabilities.  Also remove the pointless wrappers
to just check the flag.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/9p/vfs_file.c            |  2 +-
 fs/fs-writeback.c           |  7 ++++---
 include/linux/backing-dev.h | 48 ++++++++++-----------------------------------
 mm/backing-dev.c            |  6 ++----
 mm/filemap.c                |  4 ++--
 mm/memcontrol.c             |  2 +-
 mm/memory-failure.c         |  2 +-
 mm/migrate.c                |  2 +-
 mm/mmap.c                   |  2 +-
 mm/page-writeback.c         | 12 ++++++------
 10 files changed, 29 insertions(+), 58 deletions(-)

(limited to 'include/linux')

diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index 3576123d8299..6ecf863bfa2f 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -625,7 +625,7 @@ static void v9fs_mmap_vm_close(struct vm_area_struct *vma)
 
 	inode = file_inode(vma->vm_file);
 
-	if (!mapping_cap_writeback_dirty(inode->i_mapping))
+	if (!mapping_can_writeback(inode->i_mapping))
 		wbc.nr_to_write = 0;
 
 	might_sleep();
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 149227160ff0..d4f84a2fe087 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -2321,7 +2321,7 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 
 			wb = locked_inode_to_wb_and_lock_list(inode);
 
-			WARN(bdi_cap_writeback_dirty(wb->bdi) &&
+			WARN((wb->bdi->capabilities & BDI_CAP_WRITEBACK) &&
 			     !test_bit(WB_registered, &wb->state),
 			     "bdi-%s not registered\n", bdi_dev_name(wb->bdi));
 
@@ -2346,7 +2346,8 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 			 * to make sure background write-back happens
 			 * later.
 			 */
-			if (bdi_cap_writeback_dirty(wb->bdi) && wakeup_bdi)
+			if (wakeup_bdi &&
+			    (wb->bdi->capabilities & BDI_CAP_WRITEBACK))
 				wb_wakeup_delayed(wb);
 			return;
 		}
@@ -2581,7 +2582,7 @@ int write_inode_now(struct inode *inode, int sync)
 		.range_end = LLONG_MAX,
 	};
 
-	if (!mapping_cap_writeback_dirty(inode->i_mapping))
+	if (!mapping_can_writeback(inode->i_mapping))
 		wbc.nr_to_write = 0;
 
 	might_sleep();
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index b217344a2c63..44df4fcef65c 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -110,27 +110,14 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
 /*
  * Flags in backing_dev_info::capability
  *
- * The first three flags control whether dirty pages will contribute to the
- * VM's accounting and whether writepages() should be called for dirty pages
- * (something that would not, for example, be appropriate for ramfs)
- *
- * WARNING: these flags are closely related and should not normally be
- * used separately.  The BDI_CAP_NO_ACCT_AND_WRITEBACK combines these
- * three flags into a single convenience macro.
- *
- * BDI_CAP_NO_ACCT_DIRTY:  Dirty pages shouldn't contribute to accounting
- * BDI_CAP_NO_WRITEBACK:   Don't write pages back
- * BDI_CAP_WRITEBACK_ACCT: Automatically account writeback pages
- * BDI_CAP_STRICTLIMIT:    Keep number of dirty pages below bdi threshold.
+ * BDI_CAP_WRITEBACK:		Supports dirty page writeback, and dirty pages
+ *				should contribute to accounting
+ * BDI_CAP_WRITEBACK_ACCT:	Automatically account writeback pages
+ * BDI_CAP_STRICTLIMIT:		Keep number of dirty pages below bdi threshold
  */
-#define BDI_CAP_NO_ACCT_DIRTY	0x00000001
-#define BDI_CAP_NO_WRITEBACK	0x00000002
-#define BDI_CAP_WRITEBACK_ACCT	0x00000004
-#define BDI_CAP_STRICTLIMIT	0x00000010
-#define BDI_CAP_CGROUP_WRITEBACK 0x00000020
-
-#define BDI_CAP_NO_ACCT_AND_WRITEBACK \
-	(BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY)
+#define BDI_CAP_WRITEBACK		(1 << 0)
+#define BDI_CAP_WRITEBACK_ACCT		(1 << 1)
+#define BDI_CAP_STRICTLIMIT		(1 << 2)
 
 extern struct backing_dev_info noop_backing_dev_info;
 
@@ -169,24 +156,9 @@ static inline int wb_congested(struct bdi_writeback *wb, int cong_bits)
 long congestion_wait(int sync, long timeout);
 long wait_iff_congested(int sync, long timeout);
 
-static inline bool bdi_cap_writeback_dirty(struct backing_dev_info *bdi)
-{
-	return !(bdi->capabilities & BDI_CAP_NO_WRITEBACK);
-}
-
-static inline bool bdi_cap_account_dirty(struct backing_dev_info *bdi)
-{
-	return !(bdi->capabilities & BDI_CAP_NO_ACCT_DIRTY);
-}
-
-static inline bool mapping_cap_writeback_dirty(struct address_space *mapping)
-{
-	return bdi_cap_writeback_dirty(inode_to_bdi(mapping->host));
-}
-
-static inline bool mapping_cap_account_dirty(struct address_space *mapping)
+static inline bool mapping_can_writeback(struct address_space *mapping)
 {
-	return bdi_cap_account_dirty(inode_to_bdi(mapping->host));
+	return inode_to_bdi(mapping->host)->capabilities & BDI_CAP_WRITEBACK;
 }
 
 static inline int bdi_sched_wait(void *word)
@@ -223,7 +195,7 @@ static inline bool inode_cgwb_enabled(struct inode *inode)
 
 	return cgroup_subsys_on_dfl(memory_cgrp_subsys) &&
 		cgroup_subsys_on_dfl(io_cgrp_subsys) &&
-		bdi_cap_account_dirty(bdi) &&
+		(bdi->capabilities & BDI_CAP_WRITEBACK) &&
 		(inode->i_sb->s_iflags & SB_I_CGROUPWB);
 }
 
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index df18f0088dd3..408d5051d05b 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -14,9 +14,7 @@
 #include <linux/device.h>
 #include <trace/events/writeback.h>
 
-struct backing_dev_info noop_backing_dev_info = {
-	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
-};
+struct backing_dev_info noop_backing_dev_info;
 EXPORT_SYMBOL_GPL(noop_backing_dev_info);
 
 static struct class *bdi_class;
@@ -745,7 +743,7 @@ struct backing_dev_info *bdi_alloc(int node_id)
 		kfree(bdi);
 		return NULL;
 	}
-	bdi->capabilities = BDI_CAP_WRITEBACK_ACCT;
+	bdi->capabilities = BDI_CAP_WRITEBACK | BDI_CAP_WRITEBACK_ACCT;
 	bdi->ra_pages = VM_READAHEAD_PAGES;
 	bdi->io_pages = VM_READAHEAD_PAGES;
 	return bdi;
diff --git a/mm/filemap.c b/mm/filemap.c
index 1aaea26556cc..6c2a0139e22f 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -414,7 +414,7 @@ int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
 		.range_end = end,
 	};
 
-	if (!mapping_cap_writeback_dirty(mapping) ||
+	if (!mapping_can_writeback(mapping) ||
 	    !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
 		return 0;
 
@@ -1702,7 +1702,7 @@ repeat:
 no_page:
 	if (!page && (fgp_flags & FGP_CREAT)) {
 		int err;
-		if ((fgp_flags & FGP_WRITE) && mapping_cap_account_dirty(mapping))
+		if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping))
 			gfp_mask |= __GFP_WRITE;
 		if (fgp_flags & FGP_NOFS)
 			gfp_mask &= ~__GFP_FS;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b807952b4d43..d2352f76d651 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5643,7 +5643,7 @@ static int mem_cgroup_move_account(struct page *page,
 		if (PageDirty(page)) {
 			struct address_space *mapping = page_mapping(page);
 
-			if (mapping_cap_account_dirty(mapping)) {
+			if (mapping_can_writeback(mapping)) {
 				__mod_lruvec_state(from_vec, NR_FILE_DIRTY,
 						   -nr_pages);
 				__mod_lruvec_state(to_vec, NR_FILE_DIRTY,
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index f1aa6433f404..a1e73943445e 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1006,7 +1006,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	 */
 	mapping = page_mapping(hpage);
 	if (!(flags & MF_MUST_KILL) && !PageDirty(hpage) && mapping &&
-	    mapping_cap_writeback_dirty(mapping)) {
+	    mapping_can_writeback(mapping)) {
 		if (page_mkclean(hpage)) {
 			SetPageDirty(hpage);
 		} else {
diff --git a/mm/migrate.c b/mm/migrate.c
index 34a842a8eb6a..9d2f42a3a162 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -503,7 +503,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
 			__dec_lruvec_state(old_lruvec, NR_SHMEM);
 			__inc_lruvec_state(new_lruvec, NR_SHMEM);
 		}
-		if (dirty && mapping_cap_account_dirty(mapping)) {
+		if (dirty && mapping_can_writeback(mapping)) {
 			__dec_node_state(oldzone->zone_pgdat, NR_FILE_DIRTY);
 			__dec_zone_state(oldzone, NR_ZONE_WRITE_PENDING);
 			__inc_node_state(newzone->zone_pgdat, NR_FILE_DIRTY);
diff --git a/mm/mmap.c b/mm/mmap.c
index 40248d84ad5f..1fc0e92be4ba 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1666,7 +1666,7 @@ int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot)
 
 	/* Can the mapping track the dirty pages? */
 	return vma->vm_file && vma->vm_file->f_mapping &&
-		mapping_cap_account_dirty(vma->vm_file->f_mapping);
+		mapping_can_writeback(vma->vm_file->f_mapping);
 }
 
 /*
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 0139f9622a92..358d6f28c627 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1882,7 +1882,7 @@ void balance_dirty_pages_ratelimited(struct address_space *mapping)
 	int ratelimit;
 	int *p;
 
-	if (!bdi_cap_account_dirty(bdi))
+	if (!(bdi->capabilities & BDI_CAP_WRITEBACK))
 		return;
 
 	if (inode_cgwb_enabled(inode))
@@ -2423,7 +2423,7 @@ void account_page_dirtied(struct page *page, struct address_space *mapping)
 
 	trace_writeback_dirty_page(page, mapping);
 
-	if (mapping_cap_account_dirty(mapping)) {
+	if (mapping_can_writeback(mapping)) {
 		struct bdi_writeback *wb;
 
 		inode_attach_wb(inode, page);
@@ -2450,7 +2450,7 @@ void account_page_dirtied(struct page *page, struct address_space *mapping)
 void account_page_cleaned(struct page *page, struct address_space *mapping,
 			  struct bdi_writeback *wb)
 {
-	if (mapping_cap_account_dirty(mapping)) {
+	if (mapping_can_writeback(mapping)) {
 		dec_lruvec_page_state(page, NR_FILE_DIRTY);
 		dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
 		dec_wb_stat(wb, WB_RECLAIMABLE);
@@ -2513,7 +2513,7 @@ void account_page_redirty(struct page *page)
 {
 	struct address_space *mapping = page->mapping;
 
-	if (mapping && mapping_cap_account_dirty(mapping)) {
+	if (mapping && mapping_can_writeback(mapping)) {
 		struct inode *inode = mapping->host;
 		struct bdi_writeback *wb;
 		struct wb_lock_cookie cookie = {};
@@ -2625,7 +2625,7 @@ void __cancel_dirty_page(struct page *page)
 {
 	struct address_space *mapping = page_mapping(page);
 
-	if (mapping_cap_account_dirty(mapping)) {
+	if (mapping_can_writeback(mapping)) {
 		struct inode *inode = mapping->host;
 		struct bdi_writeback *wb;
 		struct wb_lock_cookie cookie = {};
@@ -2665,7 +2665,7 @@ int clear_page_dirty_for_io(struct page *page)
 
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 
-	if (mapping && mapping_cap_account_dirty(mapping)) {
+	if (mapping && mapping_can_writeback(mapping)) {
 		struct inode *inode = mapping->host;
 		struct bdi_writeback *wb;
 		struct wb_lock_cookie cookie = {};
-- 
cgit v1.2.3


From aedcade6f4fa9a1e65f327fc42de3fb47660646c Mon Sep 17 00:00:00 2001
From: Stephen Boyd <swboyd@chromium.org>
Date: Fri, 14 Aug 2020 17:40:26 -0700
Subject: debugobjects: Allow debug_obj_descr to be const

The debugobject core could be slightly harder to corrupt if the
debug_obj_descr would be a pointer to const memory.

Depending on the architecture, const data structures are placed into
read-only memory and thus are harder to corrupt or hijack.

This descriptor is used to fix up stuff like timers and workqueues when
core kernel data structures are busted, so moving the descriptors to
read-only memory will make debugobjects more resilient to something going
wrong and then corrupting the function pointers inside struct
debug_obj_descr.

Signed-off-by: Stephen Boyd <swboyd@chromium.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20200815004027.2046113-2-swboyd@chromium.org
---
 include/linux/debugobjects.h | 32 ++++++++++++++++----------------
 lib/debugobjects.c           | 30 +++++++++++++++---------------
 2 files changed, 31 insertions(+), 31 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/debugobjects.h b/include/linux/debugobjects.h
index afc416e5dcab..8d2dde23e9fb 100644
--- a/include/linux/debugobjects.h
+++ b/include/linux/debugobjects.h
@@ -30,7 +30,7 @@ struct debug_obj {
 	enum debug_obj_state	state;
 	unsigned int		astate;
 	void			*object;
-	struct debug_obj_descr	*descr;
+	const struct debug_obj_descr *descr;
 };
 
 /**
@@ -64,14 +64,14 @@ struct debug_obj_descr {
 };
 
 #ifdef CONFIG_DEBUG_OBJECTS
-extern void debug_object_init      (void *addr, struct debug_obj_descr *descr);
+extern void debug_object_init      (void *addr, const struct debug_obj_descr *descr);
 extern void
-debug_object_init_on_stack(void *addr, struct debug_obj_descr *descr);
-extern int debug_object_activate  (void *addr, struct debug_obj_descr *descr);
-extern void debug_object_deactivate(void *addr, struct debug_obj_descr *descr);
-extern void debug_object_destroy   (void *addr, struct debug_obj_descr *descr);
-extern void debug_object_free      (void *addr, struct debug_obj_descr *descr);
-extern void debug_object_assert_init(void *addr, struct debug_obj_descr *descr);
+debug_object_init_on_stack(void *addr, const struct debug_obj_descr *descr);
+extern int debug_object_activate  (void *addr, const struct debug_obj_descr *descr);
+extern void debug_object_deactivate(void *addr, const struct debug_obj_descr *descr);
+extern void debug_object_destroy   (void *addr, const struct debug_obj_descr *descr);
+extern void debug_object_free      (void *addr, const struct debug_obj_descr *descr);
+extern void debug_object_assert_init(void *addr, const struct debug_obj_descr *descr);
 
 /*
  * Active state:
@@ -79,26 +79,26 @@ extern void debug_object_assert_init(void *addr, struct debug_obj_descr *descr);
  * - Must return to 0 before deactivation.
  */
 extern void
-debug_object_active_state(void *addr, struct debug_obj_descr *descr,
+debug_object_active_state(void *addr, const struct debug_obj_descr *descr,
 			  unsigned int expect, unsigned int next);
 
 extern void debug_objects_early_init(void);
 extern void debug_objects_mem_init(void);
 #else
 static inline void
-debug_object_init      (void *addr, struct debug_obj_descr *descr) { }
+debug_object_init      (void *addr, const struct debug_obj_descr *descr) { }
 static inline void
-debug_object_init_on_stack(void *addr, struct debug_obj_descr *descr) { }
+debug_object_init_on_stack(void *addr, const struct debug_obj_descr *descr) { }
 static inline int
-debug_object_activate  (void *addr, struct debug_obj_descr *descr) { return 0; }
+debug_object_activate  (void *addr, const struct debug_obj_descr *descr) { return 0; }
 static inline void
-debug_object_deactivate(void *addr, struct debug_obj_descr *descr) { }
+debug_object_deactivate(void *addr, const struct debug_obj_descr *descr) { }
 static inline void
-debug_object_destroy   (void *addr, struct debug_obj_descr *descr) { }
+debug_object_destroy   (void *addr, const struct debug_obj_descr *descr) { }
 static inline void
-debug_object_free      (void *addr, struct debug_obj_descr *descr) { }
+debug_object_free      (void *addr, const struct debug_obj_descr *descr) { }
 static inline void
-debug_object_assert_init(void *addr, struct debug_obj_descr *descr) { }
+debug_object_assert_init(void *addr, const struct debug_obj_descr *descr) { }
 
 static inline void debug_objects_early_init(void) { }
 static inline void debug_objects_mem_init(void) { }
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index fe4557955d97..e2a3171b6c63 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -90,7 +90,7 @@ static int			debug_objects_pool_size __read_mostly
 				= ODEBUG_POOL_SIZE;
 static int			debug_objects_pool_min_level __read_mostly
 				= ODEBUG_POOL_MIN_LEVEL;
-static struct debug_obj_descr	*descr_test  __read_mostly;
+static const struct debug_obj_descr *descr_test  __read_mostly;
 static struct kmem_cache	*obj_cache __read_mostly;
 
 /*
@@ -223,7 +223,7 @@ static struct debug_obj *__alloc_object(struct hlist_head *list)
  * Must be called with interrupts disabled.
  */
 static struct debug_obj *
-alloc_object(void *addr, struct debug_bucket *b, struct debug_obj_descr *descr)
+alloc_object(void *addr, struct debug_bucket *b, const struct debug_obj_descr *descr)
 {
 	struct debug_percpu_free *percpu_pool = this_cpu_ptr(&percpu_obj_pool);
 	struct debug_obj *obj;
@@ -475,7 +475,7 @@ static struct debug_bucket *get_bucket(unsigned long addr)
 
 static void debug_print_object(struct debug_obj *obj, char *msg)
 {
-	struct debug_obj_descr *descr = obj->descr;
+	const struct debug_obj_descr *descr = obj->descr;
 	static int limit;
 
 	if (limit < 5 && descr != descr_test) {
@@ -529,7 +529,7 @@ static void debug_object_is_on_stack(void *addr, int onstack)
 }
 
 static void
-__debug_object_init(void *addr, struct debug_obj_descr *descr, int onstack)
+__debug_object_init(void *addr, const struct debug_obj_descr *descr, int onstack)
 {
 	enum debug_obj_state state;
 	bool check_stack = false;
@@ -587,7 +587,7 @@ __debug_object_init(void *addr, struct debug_obj_descr *descr, int onstack)
  * @addr:	address of the object
  * @descr:	pointer to an object specific debug description structure
  */
-void debug_object_init(void *addr, struct debug_obj_descr *descr)
+void debug_object_init(void *addr, const struct debug_obj_descr *descr)
 {
 	if (!debug_objects_enabled)
 		return;
@@ -602,7 +602,7 @@ EXPORT_SYMBOL_GPL(debug_object_init);
  * @addr:	address of the object
  * @descr:	pointer to an object specific debug description structure
  */
-void debug_object_init_on_stack(void *addr, struct debug_obj_descr *descr)
+void debug_object_init_on_stack(void *addr, const struct debug_obj_descr *descr)
 {
 	if (!debug_objects_enabled)
 		return;
@@ -617,7 +617,7 @@ EXPORT_SYMBOL_GPL(debug_object_init_on_stack);
  * @descr:	pointer to an object specific debug description structure
  * Returns 0 for success, -EINVAL for check failed.
  */
-int debug_object_activate(void *addr, struct debug_obj_descr *descr)
+int debug_object_activate(void *addr, const struct debug_obj_descr *descr)
 {
 	enum debug_obj_state state;
 	struct debug_bucket *db;
@@ -695,7 +695,7 @@ EXPORT_SYMBOL_GPL(debug_object_activate);
  * @addr:	address of the object
  * @descr:	pointer to an object specific debug description structure
  */
-void debug_object_deactivate(void *addr, struct debug_obj_descr *descr)
+void debug_object_deactivate(void *addr, const struct debug_obj_descr *descr)
 {
 	struct debug_bucket *db;
 	struct debug_obj *obj;
@@ -747,7 +747,7 @@ EXPORT_SYMBOL_GPL(debug_object_deactivate);
  * @addr:	address of the object
  * @descr:	pointer to an object specific debug description structure
  */
-void debug_object_destroy(void *addr, struct debug_obj_descr *descr)
+void debug_object_destroy(void *addr, const struct debug_obj_descr *descr)
 {
 	enum debug_obj_state state;
 	struct debug_bucket *db;
@@ -797,7 +797,7 @@ EXPORT_SYMBOL_GPL(debug_object_destroy);
  * @addr:	address of the object
  * @descr:	pointer to an object specific debug description structure
  */
-void debug_object_free(void *addr, struct debug_obj_descr *descr)
+void debug_object_free(void *addr, const struct debug_obj_descr *descr)
 {
 	enum debug_obj_state state;
 	struct debug_bucket *db;
@@ -838,7 +838,7 @@ EXPORT_SYMBOL_GPL(debug_object_free);
  * @addr:	address of the object
  * @descr:	pointer to an object specific debug description structure
  */
-void debug_object_assert_init(void *addr, struct debug_obj_descr *descr)
+void debug_object_assert_init(void *addr, const struct debug_obj_descr *descr)
 {
 	struct debug_bucket *db;
 	struct debug_obj *obj;
@@ -886,7 +886,7 @@ EXPORT_SYMBOL_GPL(debug_object_assert_init);
  * @next:	state to move to if expected state is found
  */
 void
-debug_object_active_state(void *addr, struct debug_obj_descr *descr,
+debug_object_active_state(void *addr, const struct debug_obj_descr *descr,
 			  unsigned int expect, unsigned int next)
 {
 	struct debug_bucket *db;
@@ -934,7 +934,7 @@ EXPORT_SYMBOL_GPL(debug_object_active_state);
 static void __debug_check_no_obj_freed(const void *address, unsigned long size)
 {
 	unsigned long flags, oaddr, saddr, eaddr, paddr, chunks;
-	struct debug_obj_descr *descr;
+	const struct debug_obj_descr *descr;
 	enum debug_obj_state state;
 	struct debug_bucket *db;
 	struct hlist_node *tmp;
@@ -1052,7 +1052,7 @@ struct self_test {
 	unsigned long	dummy2[3];
 };
 
-static __initdata struct debug_obj_descr descr_type_test;
+static __initconst const struct debug_obj_descr descr_type_test;
 
 static bool __init is_static_object(void *addr)
 {
@@ -1177,7 +1177,7 @@ out:
 	return res;
 }
 
-static __initdata struct debug_obj_descr descr_type_test = {
+static __initconst const struct debug_obj_descr descr_type_test = {
 	.name			= "selftest",
 	.is_static_object	= is_static_object,
 	.fixup_init		= fixup_init,
-- 
cgit v1.2.3


From b952caf2d5ca898cc10d63be7722ae7a5daca696 Mon Sep 17 00:00:00 2001
From: Qianli Zhao <zhaoqianli@xiaomi.com>
Date: Thu, 13 Aug 2020 23:03:14 +0800
Subject: timers: Mask invalid flags in do_init_timer()

do_init_timer() accepts any combination of timer flags handed in by the
caller without a sanity check, but only TIMER_DEFFERABLE, TIMER_PINNED and
TIMER_IRQSAFE are valid.

If the supplied flags have other bits set, this could result in
malfunction. If bits are set in TIMER_CPUMASK the first timer usage could
deference a cpu base which is outside the range of possible CPUs. If
TIMER_MIGRATION is set, then the switch_timer_base() will live lock.

Prevent that with a sanity check which warns when invalid flags are
supplied and masks them out.

[ tglx: Made it WARN_ON_ONCE() and added context to the changelog ]

Signed-off-by: Qianli Zhao <zhaoqianli@xiaomi.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/9d79a8aa4eb56713af7379f99f062dedabcde140.1597326756.git.zhaoqianli@xiaomi.com
---
 include/linux/timer.h | 1 +
 kernel/time/timer.c   | 2 ++
 2 files changed, 3 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/timer.h b/include/linux/timer.h
index 07910ae5ddd9..d10bc7e73b41 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -67,6 +67,7 @@ struct timer_list {
 #define TIMER_DEFERRABLE	0x00080000
 #define TIMER_PINNED		0x00100000
 #define TIMER_IRQSAFE		0x00200000
+#define TIMER_INIT_FLAGS	(TIMER_DEFERRABLE | TIMER_PINNED | TIMER_IRQSAFE)
 #define TIMER_ARRAYSHIFT	22
 #define TIMER_ARRAYMASK		0xFFC00000
 
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index a16764b0116e..25e048d0e660 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -794,6 +794,8 @@ static void do_init_timer(struct timer_list *timer,
 {
 	timer->entry.pprev = NULL;
 	timer->function = func;
+	if (WARN_ON_ONCE(flags & ~TIMER_INIT_FLAGS))
+		flags &= TIMER_INIT_FLAGS;
 	timer->flags = flags | raw_smp_processor_id();
 	lockdep_init_map(&timer->lockdep_map, name, key, 0);
 }
-- 
cgit v1.2.3


From 29bcff787a2593b2126cfaff612c0b4e560022e9 Mon Sep 17 00:00:00 2001
From: Yufen Yu <yuyufen@huawei.com>
Date: Thu, 20 Aug 2020 09:22:08 -0400
Subject: md/raid5: add new xor function to support different page offset

raid5 will call async_xor() and async_xor_val() to compute xor.
For now, both of them require the common src/dst page offset. But,
we want them to support different src/dst page offset for following
shared page.

Here, adding two new function async_xor_offs() and async_xor_val_offs()
respectively for async_xor() and async_xor_val().

Signed-off-by: Yufen Yu <yuyufen@huawei.com>
Signed-off-by: Song Liu <songliubraving@fb.com>
---
 crypto/async_tx/async_xor.c | 120 +++++++++++++++++++++++++++++++++++++-------
 include/linux/async_tx.h    |  11 ++++
 2 files changed, 114 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/crypto/async_tx/async_xor.c b/crypto/async_tx/async_xor.c
index 4e5eebe52e6a..a057ecb1288d 100644
--- a/crypto/async_tx/async_xor.c
+++ b/crypto/async_tx/async_xor.c
@@ -97,7 +97,8 @@ do_async_xor(struct dma_chan *chan, struct dmaengine_unmap_data *unmap,
 }
 
 static void
-do_sync_xor(struct page *dest, struct page **src_list, unsigned int offset,
+do_sync_xor_offs(struct page *dest, unsigned int offset,
+		struct page **src_list, unsigned int *src_offs,
 	    int src_cnt, size_t len, struct async_submit_ctl *submit)
 {
 	int i;
@@ -114,7 +115,8 @@ do_sync_xor(struct page *dest, struct page **src_list, unsigned int offset,
 	/* convert to buffer pointers */
 	for (i = 0; i < src_cnt; i++)
 		if (src_list[i])
-			srcs[xor_src_cnt++] = page_address(src_list[i]) + offset;
+			srcs[xor_src_cnt++] = page_address(src_list[i]) +
+				(src_offs ? src_offs[i] : offset);
 	src_cnt = xor_src_cnt;
 	/* set destination address */
 	dest_buf = page_address(dest) + offset;
@@ -135,11 +137,31 @@ do_sync_xor(struct page *dest, struct page **src_list, unsigned int offset,
 	async_tx_sync_epilog(submit);
 }
 
+static inline bool
+dma_xor_aligned_offsets(struct dma_device *device, unsigned int offset,
+		unsigned int *src_offs, int src_cnt, int len)
+{
+	int i;
+
+	if (!is_dma_xor_aligned(device, offset, 0, len))
+		return false;
+
+	if (!src_offs)
+		return true;
+
+	for (i = 0; i < src_cnt; i++) {
+		if (!is_dma_xor_aligned(device, src_offs[i], 0, len))
+			return false;
+	}
+	return true;
+}
+
 /**
- * async_xor - attempt to xor a set of blocks with a dma engine.
+ * async_xor_offs - attempt to xor a set of blocks with a dma engine.
  * @dest: destination page
+ * @offset: dst offset to start transaction
  * @src_list: array of source pages
- * @offset: common src/dst offset to start transaction
+ * @src_offs: array of source pages offset, NULL means common src/dst offset
  * @src_cnt: number of source pages
  * @len: length in bytes
  * @submit: submission / completion modifiers
@@ -157,8 +179,9 @@ do_sync_xor(struct page *dest, struct page **src_list, unsigned int offset,
  * is not specified.
  */
 struct dma_async_tx_descriptor *
-async_xor(struct page *dest, struct page **src_list, unsigned int offset,
-	  int src_cnt, size_t len, struct async_submit_ctl *submit)
+async_xor_offs(struct page *dest, unsigned int offset,
+		struct page **src_list, unsigned int *src_offs,
+		int src_cnt, size_t len, struct async_submit_ctl *submit)
 {
 	struct dma_chan *chan = async_tx_find_channel(submit, DMA_XOR,
 						      &dest, 1, src_list,
@@ -171,7 +194,8 @@ async_xor(struct page *dest, struct page **src_list, unsigned int offset,
 	if (device)
 		unmap = dmaengine_get_unmap_data(device->dev, src_cnt+1, GFP_NOWAIT);
 
-	if (unmap && is_dma_xor_aligned(device, offset, 0, len)) {
+	if (unmap && dma_xor_aligned_offsets(device, offset,
+				src_offs, src_cnt, len)) {
 		struct dma_async_tx_descriptor *tx;
 		int i, j;
 
@@ -184,7 +208,8 @@ async_xor(struct page *dest, struct page **src_list, unsigned int offset,
 				continue;
 			unmap->to_cnt++;
 			unmap->addr[j++] = dma_map_page(device->dev, src_list[i],
-							offset, len, DMA_TO_DEVICE);
+					src_offs ? src_offs[i] : offset,
+					len, DMA_TO_DEVICE);
 		}
 
 		/* map it bidirectional as it may be re-used as a source */
@@ -213,11 +238,42 @@ async_xor(struct page *dest, struct page **src_list, unsigned int offset,
 		/* wait for any prerequisite operations */
 		async_tx_quiesce(&submit->depend_tx);
 
-		do_sync_xor(dest, src_list, offset, src_cnt, len, submit);
+		do_sync_xor_offs(dest, offset, src_list, src_offs,
+				src_cnt, len, submit);
 
 		return NULL;
 	}
 }
+EXPORT_SYMBOL_GPL(async_xor_offs);
+
+/**
+ * async_xor - attempt to xor a set of blocks with a dma engine.
+ * @dest: destination page
+ * @src_list: array of source pages
+ * @offset: common src/dst offset to start transaction
+ * @src_cnt: number of source pages
+ * @len: length in bytes
+ * @submit: submission / completion modifiers
+ *
+ * honored flags: ASYNC_TX_ACK, ASYNC_TX_XOR_ZERO_DST, ASYNC_TX_XOR_DROP_DST
+ *
+ * xor_blocks always uses the dest as a source so the
+ * ASYNC_TX_XOR_ZERO_DST flag must be set to not include dest data in
+ * the calculation.  The assumption with dma eninges is that they only
+ * use the destination buffer as a source when it is explicity specified
+ * in the source list.
+ *
+ * src_list note: if the dest is also a source it must be at index zero.
+ * The contents of this array will be overwritten if a scribble region
+ * is not specified.
+ */
+struct dma_async_tx_descriptor *
+async_xor(struct page *dest, struct page **src_list, unsigned int offset,
+	  int src_cnt, size_t len, struct async_submit_ctl *submit)
+{
+	return async_xor_offs(dest, offset, src_list, NULL,
+			src_cnt, len, submit);
+}
 EXPORT_SYMBOL_GPL(async_xor);
 
 static int page_is_zero(struct page *p, unsigned int offset, size_t len)
@@ -237,10 +293,11 @@ xor_val_chan(struct async_submit_ctl *submit, struct page *dest,
 }
 
 /**
- * async_xor_val - attempt a xor parity check with a dma engine.
+ * async_xor_val_offs - attempt a xor parity check with a dma engine.
  * @dest: destination page used if the xor is performed synchronously
+ * @offset: des offset in pages to start transaction
  * @src_list: array of source pages
- * @offset: offset in pages to start transaction
+ * @src_offs: array of source pages offset, NULL means common src/det offset
  * @src_cnt: number of source pages
  * @len: length in bytes
  * @result: 0 if sum == 0 else non-zero
@@ -253,9 +310,10 @@ xor_val_chan(struct async_submit_ctl *submit, struct page *dest,
  * is not specified.
  */
 struct dma_async_tx_descriptor *
-async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
-	      int src_cnt, size_t len, enum sum_check_flags *result,
-	      struct async_submit_ctl *submit)
+async_xor_val_offs(struct page *dest, unsigned int offset,
+		struct page **src_list, unsigned int *src_offs,
+		int src_cnt, size_t len, enum sum_check_flags *result,
+		struct async_submit_ctl *submit)
 {
 	struct dma_chan *chan = xor_val_chan(submit, dest, src_list, src_cnt, len);
 	struct dma_device *device = chan ? chan->device : NULL;
@@ -268,7 +326,7 @@ async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
 		unmap = dmaengine_get_unmap_data(device->dev, src_cnt, GFP_NOWAIT);
 
 	if (unmap && src_cnt <= device->max_xor &&
-	    is_dma_xor_aligned(device, offset, 0, len)) {
+	    dma_xor_aligned_offsets(device, offset, src_offs, src_cnt, len)) {
 		unsigned long dma_prep_flags = 0;
 		int i;
 
@@ -281,7 +339,8 @@ async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
 
 		for (i = 0; i < src_cnt; i++) {
 			unmap->addr[i] = dma_map_page(device->dev, src_list[i],
-						      offset, len, DMA_TO_DEVICE);
+					src_offs ? src_offs[i] : offset,
+					len, DMA_TO_DEVICE);
 			unmap->to_cnt++;
 		}
 		unmap->len = len;
@@ -312,7 +371,8 @@ async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
 		submit->flags |= ASYNC_TX_XOR_DROP_DST;
 		submit->flags &= ~ASYNC_TX_ACK;
 
-		tx = async_xor(dest, src_list, offset, src_cnt, len, submit);
+		tx = async_xor_offs(dest, offset, src_list, src_offs,
+				src_cnt, len, submit);
 
 		async_tx_quiesce(&tx);
 
@@ -325,6 +385,32 @@ async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
 
 	return tx;
 }
+EXPORT_SYMBOL_GPL(async_xor_val_offs);
+
+/**
+ * async_xor_val - attempt a xor parity check with a dma engine.
+ * @dest: destination page used if the xor is performed synchronously
+ * @src_list: array of source pages
+ * @offset: offset in pages to start transaction
+ * @src_cnt: number of source pages
+ * @len: length in bytes
+ * @result: 0 if sum == 0 else non-zero
+ * @submit: submission / completion modifiers
+ *
+ * honored flags: ASYNC_TX_ACK
+ *
+ * src_list note: if the dest is also a source it must be at index zero.
+ * The contents of this array will be overwritten if a scribble region
+ * is not specified.
+ */
+struct dma_async_tx_descriptor *
+async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
+	      int src_cnt, size_t len, enum sum_check_flags *result,
+	      struct async_submit_ctl *submit)
+{
+	return async_xor_val_offs(dest, offset, src_list, NULL, src_cnt,
+			len, result, submit);
+}
 EXPORT_SYMBOL_GPL(async_xor_val);
 
 MODULE_AUTHOR("Intel Corporation");
diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h
index 4c328fef403c..8901f3c801ee 100644
--- a/include/linux/async_tx.h
+++ b/include/linux/async_tx.h
@@ -162,11 +162,22 @@ struct dma_async_tx_descriptor *
 async_xor(struct page *dest, struct page **src_list, unsigned int offset,
 	  int src_cnt, size_t len, struct async_submit_ctl *submit);
 
+struct dma_async_tx_descriptor *
+async_xor_offs(struct page *dest, unsigned int offset,
+		struct page **src_list, unsigned int *src_offset,
+		int src_cnt, size_t len, struct async_submit_ctl *submit);
+
 struct dma_async_tx_descriptor *
 async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
 	      int src_cnt, size_t len, enum sum_check_flags *result,
 	      struct async_submit_ctl *submit);
 
+struct dma_async_tx_descriptor *
+async_xor_val_offs(struct page *dest, unsigned int offset,
+		struct page **src_list, unsigned int *src_offset,
+		int src_cnt, size_t len, enum sum_check_flags *result,
+		struct async_submit_ctl *submit);
+
 struct dma_async_tx_descriptor *
 async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset,
 	     unsigned int src_offset, size_t len,
-- 
cgit v1.2.3


From d69454bc9fdfb63e84152e0533454079ea3e38a3 Mon Sep 17 00:00:00 2001
From: Yufen Yu <yuyufen@huawei.com>
Date: Thu, 20 Aug 2020 09:22:10 -0400
Subject: md/raid6: let syndrome computor support different page offset

For now, syndrome compute functions require common offset in the pages
array. However, we expect them to support different offset when try to
use shared page in the following. Simplily covert them by adding page
offset where each page address are referred.

Since the only caller of async_gen_syndrome() and async_syndrome_val()
are in raid6, we don't want to reserve the old interface but modify the
interface directly. After that, replacing old interfaces with new ones
for raid6 and raid6test.

Signed-off-by: Yufen Yu <yuyufen@huawei.com>
Signed-off-by: Song Liu <songliubraving@fb.com>
---
 crypto/async_tx/async_pq.c  | 72 ++++++++++++++++++++++++++++++---------------
 crypto/async_tx/raid6test.c | 24 ++++++++++-----
 drivers/md/raid5.c          | 36 +++++++++++++++--------
 include/linux/async_tx.h    |  6 ++--
 4 files changed, 91 insertions(+), 47 deletions(-)

(limited to 'include/linux')

diff --git a/crypto/async_tx/async_pq.c b/crypto/async_tx/async_pq.c
index 341ece61cf9b..f9cdc5e91664 100644
--- a/crypto/async_tx/async_pq.c
+++ b/crypto/async_tx/async_pq.c
@@ -104,7 +104,7 @@ do_async_gen_syndrome(struct dma_chan *chan,
  * do_sync_gen_syndrome - synchronously calculate a raid6 syndrome
  */
 static void
-do_sync_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
+do_sync_gen_syndrome(struct page **blocks, unsigned int *offsets, int disks,
 		     size_t len, struct async_submit_ctl *submit)
 {
 	void **srcs;
@@ -121,7 +121,8 @@ do_sync_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
 			BUG_ON(i > disks - 3); /* P or Q can't be zero */
 			srcs[i] = (void*)raid6_empty_zero_page;
 		} else {
-			srcs[i] = page_address(blocks[i]) + offset;
+			srcs[i] = page_address(blocks[i]) + offsets[i];
+
 			if (i < disks - 2) {
 				stop = i;
 				if (start == -1)
@@ -138,10 +139,23 @@ do_sync_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
 	async_tx_sync_epilog(submit);
 }
 
+static inline bool
+is_dma_pq_aligned_offs(struct dma_device *dev, unsigned int *offs,
+				     int src_cnt, size_t len)
+{
+	int i;
+
+	for (i = 0; i < src_cnt; i++) {
+		if (!is_dma_pq_aligned(dev, offs[i], 0, len))
+			return false;
+	}
+	return true;
+}
+
 /**
  * async_gen_syndrome - asynchronously calculate a raid6 syndrome
  * @blocks: source blocks from idx 0..disks-3, P @ disks-2 and Q @ disks-1
- * @offset: common offset into each block (src and dest) to start transaction
+ * @offsets: offset array into each block (src and dest) to start transaction
  * @disks: number of blocks (including missing P or Q, see below)
  * @len: length of operation in bytes
  * @submit: submission/completion modifiers
@@ -160,7 +174,7 @@ do_sync_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
  * path.
  */
 struct dma_async_tx_descriptor *
-async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
+async_gen_syndrome(struct page **blocks, unsigned int *offsets, int disks,
 		   size_t len, struct async_submit_ctl *submit)
 {
 	int src_cnt = disks - 2;
@@ -179,7 +193,7 @@ async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
 	if (unmap && !(submit->flags & ASYNC_TX_PQ_XOR_DST) &&
 	    (src_cnt <= dma_maxpq(device, 0) ||
 	     dma_maxpq(device, DMA_PREP_CONTINUE) > 0) &&
-	    is_dma_pq_aligned(device, offset, 0, len)) {
+	    is_dma_pq_aligned_offs(device, offsets, disks, len)) {
 		struct dma_async_tx_descriptor *tx;
 		enum dma_ctrl_flags dma_flags = 0;
 		unsigned char coefs[MAX_DISKS];
@@ -196,8 +210,8 @@ async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
 		for (i = 0, j = 0; i < src_cnt; i++) {
 			if (blocks[i] == NULL)
 				continue;
-			unmap->addr[j] = dma_map_page(device->dev, blocks[i], offset,
-						      len, DMA_TO_DEVICE);
+			unmap->addr[j] = dma_map_page(device->dev, blocks[i],
+						offsets[i], len, DMA_TO_DEVICE);
 			coefs[j] = raid6_gfexp[i];
 			unmap->to_cnt++;
 			j++;
@@ -210,7 +224,8 @@ async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
 		unmap->bidi_cnt++;
 		if (P(blocks, disks))
 			unmap->addr[j++] = dma_map_page(device->dev, P(blocks, disks),
-							offset, len, DMA_BIDIRECTIONAL);
+							P(offsets, disks),
+							len, DMA_BIDIRECTIONAL);
 		else {
 			unmap->addr[j++] = 0;
 			dma_flags |= DMA_PREP_PQ_DISABLE_P;
@@ -219,7 +234,8 @@ async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
 		unmap->bidi_cnt++;
 		if (Q(blocks, disks))
 			unmap->addr[j++] = dma_map_page(device->dev, Q(blocks, disks),
-						       offset, len, DMA_BIDIRECTIONAL);
+							Q(offsets, disks),
+							len, DMA_BIDIRECTIONAL);
 		else {
 			unmap->addr[j++] = 0;
 			dma_flags |= DMA_PREP_PQ_DISABLE_Q;
@@ -240,13 +256,13 @@ async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
 
 	if (!P(blocks, disks)) {
 		P(blocks, disks) = pq_scribble_page;
-		BUG_ON(len + offset > PAGE_SIZE);
+		P(offsets, disks) = 0;
 	}
 	if (!Q(blocks, disks)) {
 		Q(blocks, disks) = pq_scribble_page;
-		BUG_ON(len + offset > PAGE_SIZE);
+		Q(offsets, disks) = 0;
 	}
-	do_sync_gen_syndrome(blocks, offset, disks, len, submit);
+	do_sync_gen_syndrome(blocks, offsets, disks, len, submit);
 
 	return NULL;
 }
@@ -270,6 +286,7 @@ pq_val_chan(struct async_submit_ctl *submit, struct page **blocks, int disks, si
  * @len: length of operation in bytes
  * @pqres: on val failure SUM_CHECK_P_RESULT and/or SUM_CHECK_Q_RESULT are set
  * @spare: temporary result buffer for the synchronous case
+ * @s_off: spare buffer page offset
  * @submit: submission / completion modifiers
  *
  * The same notes from async_gen_syndrome apply to the 'blocks',
@@ -278,9 +295,9 @@ pq_val_chan(struct async_submit_ctl *submit, struct page **blocks, int disks, si
  * specified.
  */
 struct dma_async_tx_descriptor *
-async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
+async_syndrome_val(struct page **blocks, unsigned int *offsets, int disks,
 		   size_t len, enum sum_check_flags *pqres, struct page *spare,
-		   struct async_submit_ctl *submit)
+		   unsigned int s_off, struct async_submit_ctl *submit)
 {
 	struct dma_chan *chan = pq_val_chan(submit, blocks, disks, len);
 	struct dma_device *device = chan ? chan->device : NULL;
@@ -295,7 +312,7 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
 		unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOWAIT);
 
 	if (unmap && disks <= dma_maxpq(device, 0) &&
-	    is_dma_pq_aligned(device, offset, 0, len)) {
+	    is_dma_pq_aligned_offs(device, offsets, disks, len)) {
 		struct device *dev = device->dev;
 		dma_addr_t pq[2];
 		int i, j = 0, src_cnt = 0;
@@ -307,7 +324,7 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
 		for (i = 0; i < disks-2; i++)
 			if (likely(blocks[i])) {
 				unmap->addr[j] = dma_map_page(dev, blocks[i],
-							      offset, len,
+							      offsets[i], len,
 							      DMA_TO_DEVICE);
 				coefs[j] = raid6_gfexp[i];
 				unmap->to_cnt++;
@@ -320,7 +337,7 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
 			dma_flags |= DMA_PREP_PQ_DISABLE_P;
 		} else {
 			pq[0] = dma_map_page(dev, P(blocks, disks),
-					     offset, len,
+					     P(offsets, disks), len,
 					     DMA_TO_DEVICE);
 			unmap->addr[j++] = pq[0];
 			unmap->to_cnt++;
@@ -330,7 +347,7 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
 			dma_flags |= DMA_PREP_PQ_DISABLE_Q;
 		} else {
 			pq[1] = dma_map_page(dev, Q(blocks, disks),
-					     offset, len,
+					     Q(offsets, disks), len,
 					     DMA_TO_DEVICE);
 			unmap->addr[j++] = pq[1];
 			unmap->to_cnt++;
@@ -355,7 +372,9 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
 		async_tx_submit(chan, tx, submit);
 	} else {
 		struct page *p_src = P(blocks, disks);
+		unsigned int p_off = P(offsets, disks);
 		struct page *q_src = Q(blocks, disks);
+		unsigned int q_off = Q(offsets, disks);
 		enum async_tx_flags flags_orig = submit->flags;
 		dma_async_tx_callback cb_fn_orig = submit->cb_fn;
 		void *scribble = submit->scribble;
@@ -381,27 +400,32 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
 		if (p_src) {
 			init_async_submit(submit, ASYNC_TX_XOR_ZERO_DST, NULL,
 					  NULL, NULL, scribble);
-			tx = async_xor(spare, blocks, offset, disks-2, len, submit);
+			tx = async_xor_offs(spare, s_off,
+					blocks, offsets, disks-2, len, submit);
 			async_tx_quiesce(&tx);
-			p = page_address(p_src) + offset;
-			s = page_address(spare) + offset;
+			p = page_address(p_src) + p_off;
+			s = page_address(spare) + s_off;
 			*pqres |= !!memcmp(p, s, len) << SUM_CHECK_P;
 		}
 
 		if (q_src) {
 			P(blocks, disks) = NULL;
 			Q(blocks, disks) = spare;
+			Q(offsets, disks) = s_off;
 			init_async_submit(submit, 0, NULL, NULL, NULL, scribble);
-			tx = async_gen_syndrome(blocks, offset, disks, len, submit);
+			tx = async_gen_syndrome(blocks, offsets, disks,
+					len, submit);
 			async_tx_quiesce(&tx);
-			q = page_address(q_src) + offset;
-			s = page_address(spare) + offset;
+			q = page_address(q_src) + q_off;
+			s = page_address(spare) + s_off;
 			*pqres |= !!memcmp(q, s, len) << SUM_CHECK_Q;
 		}
 
 		/* restore P, Q and submit */
 		P(blocks, disks) = p_src;
+		P(offsets, disks) = p_off;
 		Q(blocks, disks) = q_src;
+		Q(offsets, disks) = q_off;
 
 		submit->cb_fn = cb_fn_orig;
 		submit->cb_param = cb_param_orig;
diff --git a/crypto/async_tx/raid6test.c b/crypto/async_tx/raid6test.c
index 14e73dcd7475..ef4e6e68f759 100644
--- a/crypto/async_tx/raid6test.c
+++ b/crypto/async_tx/raid6test.c
@@ -18,6 +18,7 @@
 #define NDISKS 64 /* Including P and Q */
 
 static struct page *dataptrs[NDISKS];
+unsigned int dataoffs[NDISKS];
 static addr_conv_t addr_conv[NDISKS];
 static struct page *data[NDISKS+3];
 static struct page *spare;
@@ -38,6 +39,7 @@ static void makedata(int disks)
 	for (i = 0; i < disks; i++) {
 		prandom_bytes(page_address(data[i]), PAGE_SIZE);
 		dataptrs[i] = data[i];
+		dataoffs[i] = 0;
 	}
 }
 
@@ -52,7 +54,8 @@ static char disk_type(int d, int disks)
 }
 
 /* Recover two failed blocks. */
-static void raid6_dual_recov(int disks, size_t bytes, int faila, int failb, struct page **ptrs)
+static void raid6_dual_recov(int disks, size_t bytes, int faila, int failb,
+		struct page **ptrs, unsigned int *offs)
 {
 	struct async_submit_ctl submit;
 	struct completion cmp;
@@ -66,7 +69,8 @@ static void raid6_dual_recov(int disks, size_t bytes, int faila, int failb, stru
 		if (faila == disks-2) {
 			/* P+Q failure.  Just rebuild the syndrome. */
 			init_async_submit(&submit, 0, NULL, NULL, NULL, addr_conv);
-			tx = async_gen_syndrome(ptrs, 0, disks, bytes, &submit);
+			tx = async_gen_syndrome(ptrs, offs,
+					disks, bytes, &submit);
 		} else {
 			struct page *blocks[NDISKS];
 			struct page *dest;
@@ -89,22 +93,26 @@ static void raid6_dual_recov(int disks, size_t bytes, int faila, int failb, stru
 			tx = async_xor(dest, blocks, 0, count, bytes, &submit);
 
 			init_async_submit(&submit, 0, tx, NULL, NULL, addr_conv);
-			tx = async_gen_syndrome(ptrs, 0, disks, bytes, &submit);
+			tx = async_gen_syndrome(ptrs, offs,
+					disks, bytes, &submit);
 		}
 	} else {
 		if (failb == disks-2) {
 			/* data+P failure. */
 			init_async_submit(&submit, 0, NULL, NULL, NULL, addr_conv);
-			tx = async_raid6_datap_recov(disks, bytes, faila, ptrs, &submit);
+			tx = async_raid6_datap_recov(disks, bytes,
+					faila, ptrs, &submit);
 		} else {
 			/* data+data failure. */
 			init_async_submit(&submit, 0, NULL, NULL, NULL, addr_conv);
-			tx = async_raid6_2data_recov(disks, bytes, faila, failb, ptrs, &submit);
+			tx = async_raid6_2data_recov(disks, bytes,
+					faila, failb, ptrs, &submit);
 		}
 	}
 	init_completion(&cmp);
 	init_async_submit(&submit, ASYNC_TX_ACK, tx, callback, &cmp, addr_conv);
-	tx = async_syndrome_val(ptrs, 0, disks, bytes, &result, spare, &submit);
+	tx = async_syndrome_val(ptrs, offs,
+			disks, bytes, &result, spare, 0, &submit);
 	async_tx_issue_pending(tx);
 
 	if (wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000)) == 0)
@@ -126,7 +134,7 @@ static int test_disks(int i, int j, int disks)
 	dataptrs[i] = recovi;
 	dataptrs[j] = recovj;
 
-	raid6_dual_recov(disks, PAGE_SIZE, i, j, dataptrs);
+	raid6_dual_recov(disks, PAGE_SIZE, i, j, dataptrs, dataoffs);
 
 	erra = memcmp(page_address(data[i]), page_address(recovi), PAGE_SIZE);
 	errb = memcmp(page_address(data[j]), page_address(recovj), PAGE_SIZE);
@@ -162,7 +170,7 @@ static int test(int disks, int *tests)
 	/* Generate assumed good syndrome */
 	init_completion(&cmp);
 	init_async_submit(&submit, ASYNC_TX_ACK, NULL, callback, &cmp, addr_conv);
-	tx = async_gen_syndrome(dataptrs, 0, disks, PAGE_SIZE, &submit);
+	tx = async_gen_syndrome(dataptrs, dataoffs, disks, PAGE_SIZE, &submit);
 	async_tx_issue_pending(tx);
 
 	if (wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000)) == 0) {
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index f34ddadd4e29..35f0317f0717 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1459,6 +1459,7 @@ ops_run_compute5(struct stripe_head *sh, struct raid5_percpu *percpu)
 
 /* set_syndrome_sources - populate source buffers for gen_syndrome
  * @srcs - (struct page *) array of size sh->disks
+ * @offs - (unsigned int) array of offset for each page
  * @sh - stripe_head to parse
  *
  * Populates srcs in proper layout order for the stripe and returns the
@@ -1467,6 +1468,7 @@ ops_run_compute5(struct stripe_head *sh, struct raid5_percpu *percpu)
  * is recorded in srcs[count+1]].
  */
 static int set_syndrome_sources(struct page **srcs,
+				unsigned int *offs,
 				struct stripe_head *sh,
 				int srctype)
 {
@@ -1497,6 +1499,12 @@ static int set_syndrome_sources(struct page **srcs,
 				srcs[slot] = sh->dev[i].orig_page;
 			else
 				srcs[slot] = sh->dev[i].page;
+			/*
+			 * For R5_InJournal, PAGE_SIZE must be 4KB and will
+			 * not shared page. In that case, dev[i].offset
+			 * is 0.
+			 */
+			offs[slot] = sh->dev[i].offset;
 		}
 		i = raid6_next_disk(i, disks);
 	} while (i != d0_idx);
@@ -1540,13 +1548,13 @@ ops_run_compute6_1(struct stripe_head *sh, struct raid5_percpu *percpu)
 	atomic_inc(&sh->count);
 
 	if (target == qd_idx) {
-		count = set_syndrome_sources(blocks, sh, SYNDROME_SRC_ALL);
+		count = set_syndrome_sources(blocks, offs, sh, SYNDROME_SRC_ALL);
 		blocks[count] = NULL; /* regenerating p is not necessary */
 		BUG_ON(blocks[count+1] != dest); /* q should already be set */
 		init_async_submit(&submit, ASYNC_TX_FENCE, NULL,
 				  ops_complete_compute, sh,
 				  to_addr_conv(sh, percpu, 0));
-		tx = async_gen_syndrome(blocks, 0, count+2,
+		tx = async_gen_syndrome(blocks, offs, count+2,
 				RAID5_STRIPE_SIZE(sh->raid_conf), &submit);
 	} else {
 		/* Compute any data- or p-drive using XOR */
@@ -1628,7 +1636,7 @@ ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu)
 			init_async_submit(&submit, ASYNC_TX_FENCE, NULL,
 					  ops_complete_compute, sh,
 					  to_addr_conv(sh, percpu, 0));
-			return async_gen_syndrome(blocks, 0, syndrome_disks+2,
+			return async_gen_syndrome(blocks, offs, syndrome_disks+2,
 						  RAID5_STRIPE_SIZE(sh->raid_conf),
 						  &submit);
 		} else {
@@ -1660,11 +1668,11 @@ ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu)
 				       RAID5_STRIPE_SIZE(sh->raid_conf),
 				       &submit);
 
-			count = set_syndrome_sources(blocks, sh, SYNDROME_SRC_ALL);
+			count = set_syndrome_sources(blocks, offs, sh, SYNDROME_SRC_ALL);
 			init_async_submit(&submit, ASYNC_TX_FENCE, tx,
 					  ops_complete_compute, sh,
 					  to_addr_conv(sh, percpu, 0));
-			return async_gen_syndrome(blocks, 0, count+2,
+			return async_gen_syndrome(blocks, offs, count+2,
 						  RAID5_STRIPE_SIZE(sh->raid_conf),
 						  &submit);
 		}
@@ -1750,17 +1758,18 @@ ops_run_prexor6(struct stripe_head *sh, struct raid5_percpu *percpu,
 		struct dma_async_tx_descriptor *tx)
 {
 	struct page **blocks = to_addr_page(percpu, 0);
+	unsigned int *offs = to_addr_offs(sh, percpu);
 	int count;
 	struct async_submit_ctl submit;
 
 	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
 
-	count = set_syndrome_sources(blocks, sh, SYNDROME_SRC_WANT_DRAIN);
+	count = set_syndrome_sources(blocks, offs, sh, SYNDROME_SRC_WANT_DRAIN);
 
 	init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_PQ_XOR_DST, tx,
 			  ops_complete_prexor, sh, to_addr_conv(sh, percpu, 0));
-	tx = async_gen_syndrome(blocks, 0, count+2,
+	tx = async_gen_syndrome(blocks, offs, count+2,
 			RAID5_STRIPE_SIZE(sh->raid_conf), &submit);
 
 	return tx;
@@ -1989,6 +1998,7 @@ ops_run_reconstruct6(struct stripe_head *sh, struct raid5_percpu *percpu,
 {
 	struct async_submit_ctl submit;
 	struct page **blocks;
+	unsigned int *offs;
 	int count, i, j = 0;
 	struct stripe_head *head_sh = sh;
 	int last_stripe;
@@ -2013,6 +2023,7 @@ ops_run_reconstruct6(struct stripe_head *sh, struct raid5_percpu *percpu,
 
 again:
 	blocks = to_addr_page(percpu, j);
+	offs = to_addr_offs(sh, percpu);
 
 	if (sh->reconstruct_state == reconstruct_state_prexor_drain_run) {
 		synflags = SYNDROME_SRC_WRITTEN;
@@ -2022,7 +2033,7 @@ again:
 		txflags = ASYNC_TX_ACK;
 	}
 
-	count = set_syndrome_sources(blocks, sh, synflags);
+	count = set_syndrome_sources(blocks, offs, sh, synflags);
 	last_stripe = !head_sh->batch_head ||
 		list_first_entry(&sh->batch_list,
 				 struct stripe_head, batch_list) == head_sh;
@@ -2034,7 +2045,7 @@ again:
 	} else
 		init_async_submit(&submit, 0, tx, NULL, NULL,
 				  to_addr_conv(sh, percpu, j));
-	tx = async_gen_syndrome(blocks, 0, count+2,
+	tx = async_gen_syndrome(blocks, offs, count+2,
 			RAID5_STRIPE_SIZE(sh->raid_conf),  &submit);
 	if (!last_stripe) {
 		j++;
@@ -2100,6 +2111,7 @@ static void ops_run_check_p(struct stripe_head *sh, struct raid5_percpu *percpu)
 static void ops_run_check_pq(struct stripe_head *sh, struct raid5_percpu *percpu, int checkp)
 {
 	struct page **srcs = to_addr_page(percpu, 0);
+	unsigned int *offs = to_addr_offs(sh, percpu);
 	struct async_submit_ctl submit;
 	int count;
 
@@ -2107,16 +2119,16 @@ static void ops_run_check_pq(struct stripe_head *sh, struct raid5_percpu *percpu
 		(unsigned long long)sh->sector, checkp);
 
 	BUG_ON(sh->batch_head);
-	count = set_syndrome_sources(srcs, sh, SYNDROME_SRC_ALL);
+	count = set_syndrome_sources(srcs, offs, sh, SYNDROME_SRC_ALL);
 	if (!checkp)
 		srcs[count] = NULL;
 
 	atomic_inc(&sh->count);
 	init_async_submit(&submit, ASYNC_TX_ACK, NULL, ops_complete_check,
 			  sh, to_addr_conv(sh, percpu, 0));
-	async_syndrome_val(srcs, 0, count+2,
+	async_syndrome_val(srcs, offs, count+2,
 			   RAID5_STRIPE_SIZE(sh->raid_conf),
-			   &sh->ops.zero_sum_result, percpu->spare_page, &submit);
+			   &sh->ops.zero_sum_result, percpu->spare_page, 0, &submit);
 }
 
 static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h
index 8901f3c801ee..efc5510f7d11 100644
--- a/include/linux/async_tx.h
+++ b/include/linux/async_tx.h
@@ -186,13 +186,13 @@ async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset,
 struct dma_async_tx_descriptor *async_trigger_callback(struct async_submit_ctl *submit);
 
 struct dma_async_tx_descriptor *
-async_gen_syndrome(struct page **blocks, unsigned int offset, int src_cnt,
+async_gen_syndrome(struct page **blocks, unsigned int *offsets, int src_cnt,
 		   size_t len, struct async_submit_ctl *submit);
 
 struct dma_async_tx_descriptor *
-async_syndrome_val(struct page **blocks, unsigned int offset, int src_cnt,
+async_syndrome_val(struct page **blocks, unsigned int *offsets, int src_cnt,
 		   size_t len, enum sum_check_flags *pqres, struct page *spare,
-		   struct async_submit_ctl *submit);
+		   unsigned int s_off, struct async_submit_ctl *submit);
 
 struct dma_async_tx_descriptor *
 async_raid6_2data_recov(int src_num, size_t bytes, int faila, int failb,
-- 
cgit v1.2.3


From 4f86ff5580fa692f850f37f948c73814a24a722b Mon Sep 17 00:00:00 2001
From: Yufen Yu <yuyufen@huawei.com>
Date: Thu, 20 Aug 2020 09:22:11 -0400
Subject: md/raid6: let async recovery function support different page offset

For now, asynchronous raid6 recovery calculate functions are require
common offset for pages. But, we expect them to support different page
offset after introducing stripe shared page. Do that by simplily adding
page offset where each page address are referred. Then, replace the
old interface with the new ones in raid6 and raid6test.

Signed-off-by: Yufen Yu <yuyufen@huawei.com>
Signed-off-by: Song Liu <songliubraving@fb.com>
---
 crypto/async_tx/async_raid6_recov.c | 163 ++++++++++++++++++++++++++----------
 crypto/async_tx/raid6test.c         |   4 +-
 drivers/md/raid5.c                  |   4 +-
 include/linux/async_tx.h            |   6 +-
 4 files changed, 128 insertions(+), 49 deletions(-)

(limited to 'include/linux')

diff --git a/crypto/async_tx/async_raid6_recov.c b/crypto/async_tx/async_raid6_recov.c
index f249142ceac4..354b8cd5537f 100644
--- a/crypto/async_tx/async_raid6_recov.c
+++ b/crypto/async_tx/async_raid6_recov.c
@@ -15,8 +15,9 @@
 #include <linux/dmaengine.h>
 
 static struct dma_async_tx_descriptor *
-async_sum_product(struct page *dest, struct page **srcs, unsigned char *coef,
-		  size_t len, struct async_submit_ctl *submit)
+async_sum_product(struct page *dest, unsigned int d_off,
+		struct page **srcs, unsigned int *src_offs, unsigned char *coef,
+		size_t len, struct async_submit_ctl *submit)
 {
 	struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ,
 						      &dest, 1, srcs, 2, len);
@@ -37,11 +38,14 @@ async_sum_product(struct page *dest, struct page **srcs, unsigned char *coef,
 
 		if (submit->flags & ASYNC_TX_FENCE)
 			dma_flags |= DMA_PREP_FENCE;
-		unmap->addr[0] = dma_map_page(dev, srcs[0], 0, len, DMA_TO_DEVICE);
-		unmap->addr[1] = dma_map_page(dev, srcs[1], 0, len, DMA_TO_DEVICE);
+		unmap->addr[0] = dma_map_page(dev, srcs[0], src_offs[0],
+						len, DMA_TO_DEVICE);
+		unmap->addr[1] = dma_map_page(dev, srcs[1], src_offs[1],
+						len, DMA_TO_DEVICE);
 		unmap->to_cnt = 2;
 
-		unmap->addr[2] = dma_map_page(dev, dest, 0, len, DMA_BIDIRECTIONAL);
+		unmap->addr[2] = dma_map_page(dev, dest, d_off,
+						len, DMA_BIDIRECTIONAL);
 		unmap->bidi_cnt = 1;
 		/* engine only looks at Q, but expects it to follow P */
 		pq[1] = unmap->addr[2];
@@ -66,9 +70,9 @@ async_sum_product(struct page *dest, struct page **srcs, unsigned char *coef,
 	async_tx_quiesce(&submit->depend_tx);
 	amul = raid6_gfmul[coef[0]];
 	bmul = raid6_gfmul[coef[1]];
-	a = page_address(srcs[0]);
-	b = page_address(srcs[1]);
-	c = page_address(dest);
+	a = page_address(srcs[0]) + src_offs[0];
+	b = page_address(srcs[1]) + src_offs[1];
+	c = page_address(dest) + d_off;
 
 	while (len--) {
 		ax    = amul[*a++];
@@ -80,8 +84,9 @@ async_sum_product(struct page *dest, struct page **srcs, unsigned char *coef,
 }
 
 static struct dma_async_tx_descriptor *
-async_mult(struct page *dest, struct page *src, u8 coef, size_t len,
-	   struct async_submit_ctl *submit)
+async_mult(struct page *dest, unsigned int d_off, struct page *src,
+		unsigned int s_off, u8 coef, size_t len,
+		struct async_submit_ctl *submit)
 {
 	struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ,
 						      &dest, 1, &src, 1, len);
@@ -101,9 +106,11 @@ async_mult(struct page *dest, struct page *src, u8 coef, size_t len,
 
 		if (submit->flags & ASYNC_TX_FENCE)
 			dma_flags |= DMA_PREP_FENCE;
-		unmap->addr[0] = dma_map_page(dev, src, 0, len, DMA_TO_DEVICE);
+		unmap->addr[0] = dma_map_page(dev, src, s_off,
+						len, DMA_TO_DEVICE);
 		unmap->to_cnt++;
-		unmap->addr[1] = dma_map_page(dev, dest, 0, len, DMA_BIDIRECTIONAL);
+		unmap->addr[1] = dma_map_page(dev, dest, d_off,
+						len, DMA_BIDIRECTIONAL);
 		dma_dest[1] = unmap->addr[1];
 		unmap->bidi_cnt++;
 		unmap->len = len;
@@ -133,8 +140,8 @@ async_mult(struct page *dest, struct page *src, u8 coef, size_t len,
 	 */
 	async_tx_quiesce(&submit->depend_tx);
 	qmul  = raid6_gfmul[coef];
-	d = page_address(dest);
-	s = page_address(src);
+	d = page_address(dest) + d_off;
+	s = page_address(src) + s_off;
 
 	while (len--)
 		*d++ = qmul[*s++];
@@ -144,11 +151,14 @@ async_mult(struct page *dest, struct page *src, u8 coef, size_t len,
 
 static struct dma_async_tx_descriptor *
 __2data_recov_4(int disks, size_t bytes, int faila, int failb,
-		struct page **blocks, struct async_submit_ctl *submit)
+		struct page **blocks, unsigned int *offs,
+		struct async_submit_ctl *submit)
 {
 	struct dma_async_tx_descriptor *tx = NULL;
 	struct page *p, *q, *a, *b;
+	unsigned int p_off, q_off, a_off, b_off;
 	struct page *srcs[2];
+	unsigned int src_offs[2];
 	unsigned char coef[2];
 	enum async_tx_flags flags = submit->flags;
 	dma_async_tx_callback cb_fn = submit->cb_fn;
@@ -156,26 +166,34 @@ __2data_recov_4(int disks, size_t bytes, int faila, int failb,
 	void *scribble = submit->scribble;
 
 	p = blocks[disks-2];
+	p_off = offs[disks-2];
 	q = blocks[disks-1];
+	q_off = offs[disks-1];
 
 	a = blocks[faila];
+	a_off = offs[faila];
 	b = blocks[failb];
+	b_off = offs[failb];
 
 	/* in the 4 disk case P + Pxy == P and Q + Qxy == Q */
 	/* Dx = A*(P+Pxy) + B*(Q+Qxy) */
 	srcs[0] = p;
+	src_offs[0] = p_off;
 	srcs[1] = q;
+	src_offs[1] = q_off;
 	coef[0] = raid6_gfexi[failb-faila];
 	coef[1] = raid6_gfinv[raid6_gfexp[faila]^raid6_gfexp[failb]];
 	init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
-	tx = async_sum_product(b, srcs, coef, bytes, submit);
+	tx = async_sum_product(b, b_off, srcs, src_offs, coef, bytes, submit);
 
 	/* Dy = P+Pxy+Dx */
 	srcs[0] = p;
+	src_offs[0] = p_off;
 	srcs[1] = b;
+	src_offs[1] = b_off;
 	init_async_submit(submit, flags | ASYNC_TX_XOR_ZERO_DST, tx, cb_fn,
 			  cb_param, scribble);
-	tx = async_xor(a, srcs, 0, 2, bytes, submit);
+	tx = async_xor_offs(a, a_off, srcs, src_offs, 2, bytes, submit);
 
 	return tx;
 
@@ -183,11 +201,14 @@ __2data_recov_4(int disks, size_t bytes, int faila, int failb,
 
 static struct dma_async_tx_descriptor *
 __2data_recov_5(int disks, size_t bytes, int faila, int failb,
-		struct page **blocks, struct async_submit_ctl *submit)
+		struct page **blocks, unsigned int *offs,
+		struct async_submit_ctl *submit)
 {
 	struct dma_async_tx_descriptor *tx = NULL;
 	struct page *p, *q, *g, *dp, *dq;
+	unsigned int p_off, q_off, g_off, dp_off, dq_off;
 	struct page *srcs[2];
+	unsigned int src_offs[2];
 	unsigned char coef[2];
 	enum async_tx_flags flags = submit->flags;
 	dma_async_tx_callback cb_fn = submit->cb_fn;
@@ -208,60 +229,77 @@ __2data_recov_5(int disks, size_t bytes, int faila, int failb,
 	BUG_ON(good_srcs > 1);
 
 	p = blocks[disks-2];
+	p_off = offs[disks-2];
 	q = blocks[disks-1];
+	q_off = offs[disks-1];
 	g = blocks[good];
+	g_off = offs[good];
 
 	/* Compute syndrome with zero for the missing data pages
 	 * Use the dead data pages as temporary storage for delta p and
 	 * delta q
 	 */
 	dp = blocks[faila];
+	dp_off = offs[faila];
 	dq = blocks[failb];
+	dq_off = offs[failb];
 
 	init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
-	tx = async_memcpy(dp, g, 0, 0, bytes, submit);
+	tx = async_memcpy(dp, g, dp_off, g_off, bytes, submit);
 	init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
-	tx = async_mult(dq, g, raid6_gfexp[good], bytes, submit);
+	tx = async_mult(dq, dq_off, g, g_off,
+			raid6_gfexp[good], bytes, submit);
 
 	/* compute P + Pxy */
 	srcs[0] = dp;
+	src_offs[0] = dp_off;
 	srcs[1] = p;
+	src_offs[1] = p_off;
 	init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
 			  NULL, NULL, scribble);
-	tx = async_xor(dp, srcs, 0, 2, bytes, submit);
+	tx = async_xor_offs(dp, dp_off, srcs, src_offs, 2, bytes, submit);
 
 	/* compute Q + Qxy */
 	srcs[0] = dq;
+	src_offs[0] = dq_off;
 	srcs[1] = q;
+	src_offs[1] = q_off;
 	init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
 			  NULL, NULL, scribble);
-	tx = async_xor(dq, srcs, 0, 2, bytes, submit);
+	tx = async_xor_offs(dq, dq_off, srcs, src_offs, 2, bytes, submit);
 
 	/* Dx = A*(P+Pxy) + B*(Q+Qxy) */
 	srcs[0] = dp;
+	src_offs[0] = dp_off;
 	srcs[1] = dq;
+	src_offs[1] = dq_off;
 	coef[0] = raid6_gfexi[failb-faila];
 	coef[1] = raid6_gfinv[raid6_gfexp[faila]^raid6_gfexp[failb]];
 	init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
-	tx = async_sum_product(dq, srcs, coef, bytes, submit);
+	tx = async_sum_product(dq, dq_off, srcs, src_offs, coef, bytes, submit);
 
 	/* Dy = P+Pxy+Dx */
 	srcs[0] = dp;
+	src_offs[0] = dp_off;
 	srcs[1] = dq;
+	src_offs[1] = dq_off;
 	init_async_submit(submit, flags | ASYNC_TX_XOR_DROP_DST, tx, cb_fn,
 			  cb_param, scribble);
-	tx = async_xor(dp, srcs, 0, 2, bytes, submit);
+	tx = async_xor_offs(dp, dp_off, srcs, src_offs, 2, bytes, submit);
 
 	return tx;
 }
 
 static struct dma_async_tx_descriptor *
 __2data_recov_n(int disks, size_t bytes, int faila, int failb,
-	      struct page **blocks, struct async_submit_ctl *submit)
+	      struct page **blocks, unsigned int *offs,
+		  struct async_submit_ctl *submit)
 {
 	struct dma_async_tx_descriptor *tx = NULL;
 	struct page *p, *q, *dp, *dq;
+	unsigned int p_off, q_off, dp_off, dq_off;
 	struct page *srcs[2];
+	unsigned int src_offs[2];
 	unsigned char coef[2];
 	enum async_tx_flags flags = submit->flags;
 	dma_async_tx_callback cb_fn = submit->cb_fn;
@@ -269,56 +307,74 @@ __2data_recov_n(int disks, size_t bytes, int faila, int failb,
 	void *scribble = submit->scribble;
 
 	p = blocks[disks-2];
+	p_off = offs[disks-2];
 	q = blocks[disks-1];
+	q_off = offs[disks-1];
 
 	/* Compute syndrome with zero for the missing data pages
 	 * Use the dead data pages as temporary storage for
 	 * delta p and delta q
 	 */
 	dp = blocks[faila];
+	dp_off = offs[faila];
 	blocks[faila] = NULL;
 	blocks[disks-2] = dp;
+	offs[disks-2] = dp_off;
 	dq = blocks[failb];
+	dq_off = offs[failb];
 	blocks[failb] = NULL;
 	blocks[disks-1] = dq;
+	offs[disks-1] = dq_off;
 
 	init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
-	tx = async_gen_syndrome(blocks, 0, disks, bytes, submit);
+	tx = async_gen_syndrome(blocks, offs, disks, bytes, submit);
 
 	/* Restore pointer table */
 	blocks[faila]   = dp;
+	offs[faila] = dp_off;
 	blocks[failb]   = dq;
+	offs[failb] = dq_off;
 	blocks[disks-2] = p;
+	offs[disks-2] = p_off;
 	blocks[disks-1] = q;
+	offs[disks-1] = q_off;
 
 	/* compute P + Pxy */
 	srcs[0] = dp;
+	src_offs[0] = dp_off;
 	srcs[1] = p;
+	src_offs[1] = p_off;
 	init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
 			  NULL, NULL, scribble);
-	tx = async_xor(dp, srcs, 0, 2, bytes, submit);
+	tx = async_xor_offs(dp, dp_off, srcs, src_offs, 2, bytes, submit);
 
 	/* compute Q + Qxy */
 	srcs[0] = dq;
+	src_offs[0] = dq_off;
 	srcs[1] = q;
+	src_offs[1] = q_off;
 	init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
 			  NULL, NULL, scribble);
-	tx = async_xor(dq, srcs, 0, 2, bytes, submit);
+	tx = async_xor_offs(dq, dq_off, srcs, src_offs, 2, bytes, submit);
 
 	/* Dx = A*(P+Pxy) + B*(Q+Qxy) */
 	srcs[0] = dp;
+	src_offs[0] = dp_off;
 	srcs[1] = dq;
+	src_offs[1] = dq_off;
 	coef[0] = raid6_gfexi[failb-faila];
 	coef[1] = raid6_gfinv[raid6_gfexp[faila]^raid6_gfexp[failb]];
 	init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
-	tx = async_sum_product(dq, srcs, coef, bytes, submit);
+	tx = async_sum_product(dq, dq_off, srcs, src_offs, coef, bytes, submit);
 
 	/* Dy = P+Pxy+Dx */
 	srcs[0] = dp;
+	src_offs[0] = dp_off;
 	srcs[1] = dq;
+	src_offs[1] = dq_off;
 	init_async_submit(submit, flags | ASYNC_TX_XOR_DROP_DST, tx, cb_fn,
 			  cb_param, scribble);
-	tx = async_xor(dp, srcs, 0, 2, bytes, submit);
+	tx = async_xor_offs(dp, dp_off, srcs, src_offs, 2, bytes, submit);
 
 	return tx;
 }
@@ -330,11 +386,13 @@ __2data_recov_n(int disks, size_t bytes, int faila, int failb,
  * @faila: first failed drive index
  * @failb: second failed drive index
  * @blocks: array of source pointers where the last two entries are p and q
+ * @offs: array of offset for pages in blocks
  * @submit: submission/completion modifiers
  */
 struct dma_async_tx_descriptor *
 async_raid6_2data_recov(int disks, size_t bytes, int faila, int failb,
-			struct page **blocks, struct async_submit_ctl *submit)
+			struct page **blocks, unsigned int *offs,
+			struct async_submit_ctl *submit)
 {
 	void *scribble = submit->scribble;
 	int non_zero_srcs, i;
@@ -358,7 +416,7 @@ async_raid6_2data_recov(int disks, size_t bytes, int faila, int failb,
 			if (blocks[i] == NULL)
 				ptrs[i] = (void *) raid6_empty_zero_page;
 			else
-				ptrs[i] = page_address(blocks[i]);
+				ptrs[i] = page_address(blocks[i]) + offs[i];
 
 		raid6_2data_recov(disks, bytes, faila, failb, ptrs);
 
@@ -383,16 +441,19 @@ async_raid6_2data_recov(int disks, size_t bytes, int faila, int failb,
 		 * explicitly handle the special case of a 4 disk array with
 		 * both data disks missing.
 		 */
-		return __2data_recov_4(disks, bytes, faila, failb, blocks, submit);
+		return __2data_recov_4(disks, bytes, faila, failb,
+				blocks, offs, submit);
 	case 3:
 		/* dma devices do not uniformly understand a single
 		 * source pq operation (in contrast to the synchronous
 		 * case), so explicitly handle the special case of a 5 disk
 		 * array with 2 of 3 data disks missing.
 		 */
-		return __2data_recov_5(disks, bytes, faila, failb, blocks, submit);
+		return __2data_recov_5(disks, bytes, faila, failb,
+				blocks, offs, submit);
 	default:
-		return __2data_recov_n(disks, bytes, faila, failb, blocks, submit);
+		return __2data_recov_n(disks, bytes, faila, failb,
+				blocks, offs, submit);
 	}
 }
 EXPORT_SYMBOL_GPL(async_raid6_2data_recov);
@@ -403,14 +464,17 @@ EXPORT_SYMBOL_GPL(async_raid6_2data_recov);
  * @bytes: block size
  * @faila: failed drive index
  * @blocks: array of source pointers where the last two entries are p and q
+ * @offs: array of offset for pages in blocks
  * @submit: submission/completion modifiers
  */
 struct dma_async_tx_descriptor *
 async_raid6_datap_recov(int disks, size_t bytes, int faila,
-			struct page **blocks, struct async_submit_ctl *submit)
+			struct page **blocks, unsigned int *offs,
+			struct async_submit_ctl *submit)
 {
 	struct dma_async_tx_descriptor *tx = NULL;
 	struct page *p, *q, *dq;
+	unsigned int p_off, q_off, dq_off;
 	u8 coef;
 	enum async_tx_flags flags = submit->flags;
 	dma_async_tx_callback cb_fn = submit->cb_fn;
@@ -418,6 +482,7 @@ async_raid6_datap_recov(int disks, size_t bytes, int faila,
 	void *scribble = submit->scribble;
 	int good_srcs, good, i;
 	struct page *srcs[2];
+	unsigned int src_offs[2];
 
 	pr_debug("%s: disks: %d len: %zu\n", __func__, disks, bytes);
 
@@ -434,7 +499,7 @@ async_raid6_datap_recov(int disks, size_t bytes, int faila,
 			if (blocks[i] == NULL)
 				ptrs[i] = (void*)raid6_empty_zero_page;
 			else
-				ptrs[i] = page_address(blocks[i]);
+				ptrs[i] = page_address(blocks[i]) + offs[i];
 
 		raid6_datap_recov(disks, bytes, faila, ptrs);
 
@@ -458,55 +523,67 @@ async_raid6_datap_recov(int disks, size_t bytes, int faila,
 	BUG_ON(good_srcs == 0);
 
 	p = blocks[disks-2];
+	p_off = offs[disks-2];
 	q = blocks[disks-1];
+	q_off = offs[disks-1];
 
 	/* Compute syndrome with zero for the missing data page
 	 * Use the dead data page as temporary storage for delta q
 	 */
 	dq = blocks[faila];
+	dq_off = offs[faila];
 	blocks[faila] = NULL;
 	blocks[disks-1] = dq;
+	offs[disks-1] = dq_off;
 
 	/* in the 4-disk case we only need to perform a single source
 	 * multiplication with the one good data block.
 	 */
 	if (good_srcs == 1) {
 		struct page *g = blocks[good];
+		unsigned int g_off = offs[good];
 
 		init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL,
 				  scribble);
-		tx = async_memcpy(p, g, 0, 0, bytes, submit);
+		tx = async_memcpy(p, g, p_off, g_off, bytes, submit);
 
 		init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL,
 				  scribble);
-		tx = async_mult(dq, g, raid6_gfexp[good], bytes, submit);
+		tx = async_mult(dq, dq_off, g, g_off,
+				raid6_gfexp[good], bytes, submit);
 	} else {
 		init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL,
 				  scribble);
-		tx = async_gen_syndrome(blocks, 0, disks, bytes, submit);
+		tx = async_gen_syndrome(blocks, offs, disks, bytes, submit);
 	}
 
 	/* Restore pointer table */
 	blocks[faila]   = dq;
+	offs[faila] = dq_off;
 	blocks[disks-1] = q;
+	offs[disks-1] = q_off;
 
 	/* calculate g^{-faila} */
 	coef = raid6_gfinv[raid6_gfexp[faila]];
 
 	srcs[0] = dq;
+	src_offs[0] = dq_off;
 	srcs[1] = q;
+	src_offs[1] = q_off;
 	init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
 			  NULL, NULL, scribble);
-	tx = async_xor(dq, srcs, 0, 2, bytes, submit);
+	tx = async_xor_offs(dq, dq_off, srcs, src_offs, 2, bytes, submit);
 
 	init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
-	tx = async_mult(dq, dq, coef, bytes, submit);
+	tx = async_mult(dq, dq_off, dq, dq_off, coef, bytes, submit);
 
 	srcs[0] = p;
+	src_offs[0] = p_off;
 	srcs[1] = dq;
+	src_offs[1] = dq_off;
 	init_async_submit(submit, flags | ASYNC_TX_XOR_DROP_DST, tx, cb_fn,
 			  cb_param, scribble);
-	tx = async_xor(p, srcs, 0, 2, bytes, submit);
+	tx = async_xor_offs(p, p_off, srcs, src_offs, 2, bytes, submit);
 
 	return tx;
 }
diff --git a/crypto/async_tx/raid6test.c b/crypto/async_tx/raid6test.c
index ef4e6e68f759..66db82e5a3b1 100644
--- a/crypto/async_tx/raid6test.c
+++ b/crypto/async_tx/raid6test.c
@@ -101,12 +101,12 @@ static void raid6_dual_recov(int disks, size_t bytes, int faila, int failb,
 			/* data+P failure. */
 			init_async_submit(&submit, 0, NULL, NULL, NULL, addr_conv);
 			tx = async_raid6_datap_recov(disks, bytes,
-					faila, ptrs, &submit);
+					faila, ptrs, offs, &submit);
 		} else {
 			/* data+data failure. */
 			init_async_submit(&submit, 0, NULL, NULL, NULL, addr_conv);
 			tx = async_raid6_2data_recov(disks, bytes,
-					faila, failb, ptrs, &submit);
+					faila, failb, ptrs, offs, &submit);
 		}
 	}
 	init_completion(&cmp);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 35f0317f0717..d36b8192940b 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1685,13 +1685,13 @@ ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu)
 			return async_raid6_datap_recov(syndrome_disks+2,
 						RAID5_STRIPE_SIZE(sh->raid_conf),
 						faila,
-						blocks, &submit);
+						blocks, offs, &submit);
 		} else {
 			/* We're missing D+D. */
 			return async_raid6_2data_recov(syndrome_disks+2,
 						RAID5_STRIPE_SIZE(sh->raid_conf),
 						faila, failb,
-						blocks, &submit);
+						blocks, offs, &submit);
 		}
 	}
 }
diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h
index efc5510f7d11..5cc73d7e5b52 100644
--- a/include/linux/async_tx.h
+++ b/include/linux/async_tx.h
@@ -196,11 +196,13 @@ async_syndrome_val(struct page **blocks, unsigned int *offsets, int src_cnt,
 
 struct dma_async_tx_descriptor *
 async_raid6_2data_recov(int src_num, size_t bytes, int faila, int failb,
-			struct page **ptrs, struct async_submit_ctl *submit);
+			struct page **ptrs, unsigned int *offs,
+			struct async_submit_ctl *submit);
 
 struct dma_async_tx_descriptor *
 async_raid6_datap_recov(int src_num, size_t bytes, int faila,
-			struct page **ptrs, struct async_submit_ctl *submit);
+			struct page **ptrs, unsigned int *offs,
+			struct async_submit_ctl *submit);
 
 void async_tx_quiesce(struct dma_async_tx_descriptor **tx);
 #endif /* _ASYNC_TX_H_ */
-- 
cgit v1.2.3


From b5b6775d72e8662b5ea7f892bf06db4831e2c1aa Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Wed, 23 Sep 2020 18:41:22 +0300
Subject: of: add of_mdio_find_device() api

Add a helper function which finds the mdio_device structure given a
device tree node. This is helpful for finding the PCS device based on a
DTS node but managing it as a mdio_device instead of a phy_device.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/of/of_mdio.c    | 38 +++++++++++++++++++++++++++++---------
 include/linux/of_mdio.h |  6 ++++++
 2 files changed, 35 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c
index cb32d7ef4938..4daf94bb56a5 100644
--- a/drivers/of/of_mdio.c
+++ b/drivers/of/of_mdio.c
@@ -337,6 +337,29 @@ unregister:
 }
 EXPORT_SYMBOL(of_mdiobus_register);
 
+/**
+ * of_mdio_find_device - Given a device tree node, find the mdio_device
+ * @np: pointer to the mdio_device's device tree node
+ *
+ * If successful, returns a pointer to the mdio_device with the embedded
+ * struct device refcount incremented by one, or NULL on failure.
+ * The caller should call put_device() on the mdio_device after its use
+ */
+struct mdio_device *of_mdio_find_device(struct device_node *np)
+{
+	struct device *d;
+
+	if (!np)
+		return NULL;
+
+	d = bus_find_device_by_of_node(&mdio_bus_type, np);
+	if (!d)
+		return NULL;
+
+	return to_mdio_device(d);
+}
+EXPORT_SYMBOL(of_mdio_find_device);
+
 /**
  * of_phy_find_device - Give a PHY node, find the phy_device
  * @phy_np: Pointer to the phy's device tree node
@@ -346,19 +369,16 @@ EXPORT_SYMBOL(of_mdiobus_register);
  */
 struct phy_device *of_phy_find_device(struct device_node *phy_np)
 {
-	struct device *d;
 	struct mdio_device *mdiodev;
 
-	if (!phy_np)
+	mdiodev = of_mdio_find_device(phy_np);
+	if (!mdiodev)
 		return NULL;
 
-	d = bus_find_device_by_of_node(&mdio_bus_type, phy_np);
-	if (d) {
-		mdiodev = to_mdio_device(d);
-		if (mdiodev->flags & MDIO_DEVICE_FLAG_PHY)
-			return to_phy_device(d);
-		put_device(d);
-	}
+	if (mdiodev->flags & MDIO_DEVICE_FLAG_PHY)
+		return to_phy_device(&mdiodev->dev);
+
+	put_device(&mdiodev->dev);
 
 	return NULL;
 }
diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h
index 1efb88d9f892..cfe8c607a628 100644
--- a/include/linux/of_mdio.h
+++ b/include/linux/of_mdio.h
@@ -17,6 +17,7 @@ bool of_mdiobus_child_is_phy(struct device_node *child);
 int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np);
 int devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio,
 			     struct device_node *np);
+struct mdio_device *of_mdio_find_device(struct device_node *np);
 struct phy_device *of_phy_find_device(struct device_node *phy_np);
 struct phy_device *
 of_phy_connect(struct net_device *dev, struct device_node *phy_np,
@@ -74,6 +75,11 @@ static inline int of_mdiobus_register(struct mii_bus *mdio, struct device_node *
 	return mdiobus_register(mdio);
 }
 
+static inline struct mdio_device *of_mdio_find_device(struct device_node *np)
+{
+	return NULL;
+}
+
 static inline struct phy_device *of_phy_find_device(struct device_node *phy_np)
 {
 	return NULL;
-- 
cgit v1.2.3


From 7ae10eb903d6ed9b3069fe1dc175b36d86667d09 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 11 Sep 2020 09:29:50 +0200
Subject: dma-mapping: remove DMA_MASK_NONE

This value is only used by a PCMCIA driver and not very useful.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Dominik Brodowski <linux@dominikbrodwski.net>
---
 drivers/pcmcia/ds.c         | 2 +-
 include/linux/dma-mapping.h | 2 --
 2 files changed, 1 insertion(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/pcmcia/ds.c b/drivers/pcmcia/ds.c
index 09d06b082f8b..72114907c0e4 100644
--- a/drivers/pcmcia/ds.c
+++ b/drivers/pcmcia/ds.c
@@ -516,7 +516,7 @@ static struct pcmcia_device *pcmcia_device_add(struct pcmcia_socket *s,
 	p_dev->dev.parent = s->dev.parent;
 	p_dev->dev.release = pcmcia_release_dev;
 	/* by default don't allow DMA */
-	p_dev->dma_mask = DMA_MASK_NONE;
+	p_dev->dma_mask = 0;
 	p_dev->dev.dma_mask = &p_dev->dma_mask;
 	dev_set_name(&p_dev->dev, "%d.%d", p_dev->socket->sock, p_dev->device_no);
 	if (!dev_name(&p_dev->dev))
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index bb138ac6f5e6..e074588d753f 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -138,8 +138,6 @@ extern const struct dma_map_ops dma_dummy_ops;
 
 #define DMA_BIT_MASK(n)	(((n) == 64) ? ~0ULL : ((1ULL<<(n))-1))
 
-#define DMA_MASK_NONE	0x0ULL
-
 static inline int valid_dma_direction(int dma_direction)
 {
 	return ((dma_direction == DMA_BIDIRECTIONAL) ||
-- 
cgit v1.2.3


From db4268f8c575617bacdeff862c7de674dbf65075 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 11 Sep 2020 09:31:32 +0200
Subject: dma-mapping: move valid_dma_direction to dma-direction.h

Move the valid_dma_direction helper to a more suitable header, and
clean it up to use the proper enum as well as removing pointless braces.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/dma-direction.h | 8 +++++++-
 include/linux/dma-mapping.h   | 7 -------
 2 files changed, 7 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/dma-direction.h b/include/linux/dma-direction.h
index 9c96e30e6a0b..a2fe4571bc92 100644
--- a/include/linux/dma-direction.h
+++ b/include/linux/dma-direction.h
@@ -9,4 +9,10 @@ enum dma_data_direction {
 	DMA_NONE = 3,
 };
 
-#endif
+static inline int valid_dma_direction(enum dma_data_direction dir)
+{
+	return dir == DMA_BIDIRECTIONAL || dir == DMA_TO_DEVICE ||
+		dir == DMA_FROM_DEVICE;
+}
+
+#endif /* _LINUX_DMA_DIRECTION_H */
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index e074588d753f..51e93d44b826 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -138,13 +138,6 @@ extern const struct dma_map_ops dma_dummy_ops;
 
 #define DMA_BIT_MASK(n)	(((n) == 64) ? ~0ULL : ((1ULL<<(n))-1))
 
-static inline int valid_dma_direction(int dma_direction)
-{
-	return ((dma_direction == DMA_BIDIRECTIONAL) ||
-		(dma_direction == DMA_TO_DEVICE) ||
-		(dma_direction == DMA_FROM_DEVICE));
-}
-
 #ifdef CONFIG_DMA_DECLARE_COHERENT
 /*
  * These three functions are only for dma allocator.
-- 
cgit v1.2.3


From eba304c6861613a649ba46cfab835b1eddeacd8e Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 11 Sep 2020 09:33:42 +0200
Subject: dma-mapping: better document dma_addr_t and DMA_MAPPING_ERROR

Move the comment documenting dma_addr_t away from the dma_map_ops
definition which isn't very related to it, and toward DMA_MAPPING_ERROR,
which is somewhat related.  Add a little blurb about DMA_MAPPING_ERROR
as well.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/dma-mapping.h | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 51e93d44b826..943479fb77f6 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -67,12 +67,6 @@
  */
 #define DMA_ATTR_PRIVILEGED		(1UL << 9)
 
-/*
- * A dma_addr_t can hold any valid DMA or bus address for the platform.
- * It can be given to a device to use as a DMA source or target.  A CPU cannot
- * reference a dma_addr_t directly because there may be translation between
- * its physical address space and the bus address space.
- */
 struct dma_map_ops {
 	void* (*alloc)(struct device *dev, size_t size,
 				dma_addr_t *dma_handle, gfp_t gfp,
@@ -131,6 +125,16 @@ struct dma_map_ops {
 	unsigned long (*get_merge_boundary)(struct device *dev);
 };
 
+/*
+ * A dma_addr_t can hold any valid DMA or bus address for the platform.  It can
+ * be given to a device to use as a DMA source or target.  It is specific to a
+ * given device and there may be a translation between the CPU physical address
+ * space and the bus address space.
+ *
+ * DMA_MAPPING_ERROR is the magic error code if a mapping failed.  It should not
+ * be used directly in drivers, but checked for using dma_mapping_error()
+ * instead.
+ */
 #define DMA_MAPPING_ERROR		(~(dma_addr_t)0)
 
 extern const struct dma_map_ops dma_virt_ops;
-- 
cgit v1.2.3


From 43ee5b6daa6c45246098493dab2c229d196c9cf6 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 17 Aug 2020 19:17:20 +0200
Subject: mm: turn alloc_pages into an inline function

To prevent a compiler error when a method call alloc_pages is
added (which I plan to for the dma_map_ops).

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/gfp.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 67a0774e080b..dd2577c54071 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -550,8 +550,10 @@ extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order,
 #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \
 	alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true)
 #else
-#define alloc_pages(gfp_mask, order) \
-		alloc_pages_node(numa_node_id(), gfp_mask, order)
+static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order)
+{
+	return alloc_pages_node(numa_node_id(), gfp_mask, order);
+}
 #define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\
 	alloc_pages(gfp_mask, order)
 #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \
-- 
cgit v1.2.3


From 0d71675f87dc406d4c284729b8d36be050ad0d15 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 1 Sep 2020 13:31:30 +0200
Subject: dma-mapping: add a new dma_alloc_noncoherent API

Add a new API to allocate and free memory that is guaranteed to be
addressable by a device, but which potentially is not cache coherent
for DMA.

To transfer ownership to and from the device, the existing streaming
DMA API calls dma_sync_single_for_device and dma_sync_single_for_cpu
must be used.

For now the new calls are implemented on top of dma_alloc_attrs just
like the old-noncoherent API, but once all drivers are switched to
the new API it will be replaced with a better working implementation
that is available on all architectures.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 Documentation/core-api/dma-api.rst | 75 ++++++++++++++++++--------------------
 include/linux/dma-mapping.h        | 12 ++++++
 2 files changed, 48 insertions(+), 39 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/core-api/dma-api.rst b/Documentation/core-api/dma-api.rst
index 90239348b30f..ea0413276ddb 100644
--- a/Documentation/core-api/dma-api.rst
+++ b/Documentation/core-api/dma-api.rst
@@ -516,48 +516,56 @@ routines, e.g.:::
 	}
 
 
-Part II - Advanced dma usage
-----------------------------
+Part II - Non-coherent DMA allocations
+--------------------------------------
 
-Warning: These pieces of the DMA API should not be used in the
-majority of cases, since they cater for unlikely corner cases that
-don't belong in usual drivers.
+These APIs allow to allocate pages in the kernel direct mapping that are
+guaranteed to be DMA addressable.  This means that unlike dma_alloc_coherent,
+virt_to_page can be called on the resulting address, and the resulting
+struct page can be used for everything a struct page is suitable for.
 
-If you don't understand how cache line coherency works between a
-processor and an I/O device, you should not be using this part of the
-API at all.
+If you don't understand how cache line coherency works between a processor and
+an I/O device, you should not be using this part of the API.
 
 ::
 
 	void *
-	dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
-			gfp_t flag, unsigned long attrs)
+	dma_alloc_noncoherent(struct device *dev, size_t size,
+			dma_addr_t *dma_handle, enum dma_data_direction dir,
+			gfp_t gfp)
 
-Identical to dma_alloc_coherent() except that when the
-DMA_ATTR_NON_CONSISTENT flags is passed in the attrs argument, the
-platform will choose to return either consistent or non-consistent memory
-as it sees fit.  By using this API, you are guaranteeing to the platform
-that you have all the correct and necessary sync points for this memory
-in the driver should it choose to return non-consistent memory.
+This routine allocates a region of <size> bytes of consistent memory.  It
+returns a pointer to the allocated region (in the processor's virtual address
+space) or NULL if the allocation failed.  The returned memory may or may not
+be in the kernels direct mapping.  Drivers must not call virt_to_page on
+the returned memory region.
 
-Note: where the platform can return consistent memory, it will
-guarantee that the sync points become nops.
+It also returns a <dma_handle> which may be cast to an unsigned integer the
+same width as the bus and given to the device as the DMA address base of
+the region.
 
-Warning:  Handling non-consistent memory is a real pain.  You should
-only use this API if you positively know your driver will be
-required to work on one of the rare (usually non-PCI) architectures
-that simply cannot make consistent memory.
+The dir parameter specified if data is read and/or written by the device,
+see dma_map_single() for details.
+
+The gfp parameter allows the caller to specify the ``GFP_`` flags (see
+kmalloc()) for the allocation, but rejects flags used to specify a memory
+zone such as GFP_DMA or GFP_HIGHMEM.
+
+Before giving the memory to the device, dma_sync_single_for_device() needs
+to be called, and before reading memory written by the device,
+dma_sync_single_for_cpu(), just like for streaming DMA mappings that are
+reused.
 
 ::
 
 	void
-	dma_free_attrs(struct device *dev, size_t size, void *cpu_addr,
-		       dma_addr_t dma_handle, unsigned long attrs)
+	dma_free_noncoherent(struct device *dev, size_t size, void *cpu_addr,
+			dma_addr_t dma_handle, enum dma_data_direction dir)
 
-Free memory allocated by the dma_alloc_attrs().  All common
-parameters must be identical to those otherwise passed to dma_free_coherent,
-and the attrs argument must be identical to the attrs passed to
-dma_alloc_attrs().
+Free a region of memory previously allocated using dma_alloc_noncoherent().
+dev, size and dma_handle and dir must all be the same as those passed into
+dma_alloc_noncoherent().  cpu_addr must be the virtual address returned by
+the dma_alloc_noncoherent().
 
 ::
 
@@ -575,17 +583,6 @@ memory or doing partial flushes.
 	into the width returned by this call.  It will also always be a power
 	of two for easy alignment.
 
-::
-
-	void
-	dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-		       enum dma_data_direction direction)
-
-Do a partial sync of memory that was allocated by dma_alloc_attrs() with
-the DMA_ATTR_NON_CONSISTENT flag starting at virtual address vaddr and
-continuing on for size.  Again, you *must* observe the cache line
-boundaries when doing this.
-
 
 Part III - Debug drivers use of the DMA-API
 -------------------------------------------
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 943479fb77f6..cb607b381adf 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -384,6 +384,18 @@ static inline unsigned long dma_get_merge_boundary(struct device *dev)
 }
 #endif /* CONFIG_HAS_DMA */
 
+static inline void *dma_alloc_noncoherent(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp)
+{
+	return dma_alloc_attrs(dev, size, dma_handle, gfp,
+			DMA_ATTR_NON_CONSISTENT);
+}
+static inline void dma_free_noncoherent(struct device *dev, size_t size,
+		void *vaddr, dma_addr_t dma_handle, enum dma_data_direction dir)
+{
+	dma_free_attrs(dev, size, vaddr, dma_handle, DMA_ATTR_NON_CONSISTENT);
+}
+
 static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
-- 
cgit v1.2.3


From 5a84292271402cffe0717bc58e2ad9a0c7977272 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 1 Sep 2020 13:28:13 +0200
Subject: dma-mapping: remove dma_cache_sync

All users are gone now, remove the API.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de> (MIPS part)
---
 arch/mips/Kconfig               |  1 -
 arch/mips/jazz/jazzdma.c        |  1 -
 arch/mips/mm/dma-noncoherent.c  |  6 ------
 arch/parisc/Kconfig             |  1 -
 arch/parisc/kernel/pci-dma.c    |  6 ------
 include/linux/dma-mapping.h     |  8 --------
 include/linux/dma-noncoherent.h | 10 ----------
 kernel/dma/Kconfig              |  3 ---
 kernel/dma/mapping.c            | 14 --------------
 9 files changed, 50 deletions(-)

(limited to 'include/linux')

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 8f328298f8cc..92b0fde3d882 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -1135,7 +1135,6 @@ config DMA_NONCOHERENT
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
 	select ARCH_HAS_DMA_SET_UNCACHED
 	select DMA_NONCOHERENT_MMAP
-	select DMA_NONCOHERENT_CACHE_SYNC
 	select NEED_DMA_MAP_STATE
 
 config SYS_HAS_EARLY_PRINTK
diff --git a/arch/mips/jazz/jazzdma.c b/arch/mips/jazz/jazzdma.c
index dab4d058cea9..2bf849caf507 100644
--- a/arch/mips/jazz/jazzdma.c
+++ b/arch/mips/jazz/jazzdma.c
@@ -620,7 +620,6 @@ const struct dma_map_ops jazz_dma_ops = {
 	.sync_single_for_device	= jazz_dma_sync_single_for_device,
 	.sync_sg_for_cpu	= jazz_dma_sync_sg_for_cpu,
 	.sync_sg_for_device	= jazz_dma_sync_sg_for_device,
-	.cache_sync		= arch_dma_cache_sync,
 	.mmap			= dma_common_mmap,
 	.get_sgtable		= dma_common_get_sgtable,
 };
diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c
index 97a14adbafc9..f34ad1f09799 100644
--- a/arch/mips/mm/dma-noncoherent.c
+++ b/arch/mips/mm/dma-noncoherent.c
@@ -137,12 +137,6 @@ void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
 }
 #endif
 
-void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-		enum dma_data_direction direction)
-{
-	dma_sync_virt_for_device(vaddr, size, direction);
-}
-
 #ifdef CONFIG_DMA_PERDEV_COHERENT
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 		const struct iommu_ops *iommu, bool coherent)
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index 3b0f53dd70bc..ed15da1da174 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -195,7 +195,6 @@ config PA11
 	depends on PA7000 || PA7100LC || PA7200 || PA7300LC
 	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
-	select DMA_NONCOHERENT_CACHE_SYNC
 
 config PREFETCH
 	def_bool y
diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c
index 38c68e131bbe..ce38c0b91581 100644
--- a/arch/parisc/kernel/pci-dma.c
+++ b/arch/parisc/kernel/pci-dma.c
@@ -454,9 +454,3 @@ void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
 {
 	flush_kernel_dcache_range((unsigned long)phys_to_virt(paddr), size);
 }
-
-void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-	       enum dma_data_direction direction)
-{
-	flush_kernel_dcache_range((unsigned long)vaddr, size);
-}
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index cb607b381adf..233bb8dcbe02 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -117,8 +117,6 @@ struct dma_map_ops {
 	void (*sync_sg_for_device)(struct device *dev,
 				   struct scatterlist *sg, int nents,
 				   enum dma_data_direction dir);
-	void (*cache_sync)(struct device *dev, void *vaddr, size_t size,
-			enum dma_data_direction direction);
 	int (*dma_supported)(struct device *dev, u64 mask);
 	u64 (*get_required_mask)(struct device *dev);
 	size_t (*max_mapping_size)(struct device *dev);
@@ -249,8 +247,6 @@ void *dmam_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t gfp, unsigned long attrs);
 void dmam_free_coherent(struct device *dev, size_t size, void *vaddr,
 		dma_addr_t dma_handle);
-void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-		enum dma_data_direction dir);
 int dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		unsigned long attrs);
@@ -334,10 +330,6 @@ static inline void dmam_free_coherent(struct device *dev, size_t size,
 		void *vaddr, dma_addr_t dma_handle)
 {
 }
-static inline void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-		enum dma_data_direction dir)
-{
-}
 static inline int dma_get_sgtable_attrs(struct device *dev,
 		struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr,
 		size_t size, unsigned long attrs)
diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h
index b9bc6c557ea4..0888656369a4 100644
--- a/include/linux/dma-noncoherent.h
+++ b/include/linux/dma-noncoherent.h
@@ -62,16 +62,6 @@ static inline pgprot_t dma_pgprot(struct device *dev, pgprot_t prot,
 }
 #endif /* CONFIG_MMU */
 
-#ifdef CONFIG_DMA_NONCOHERENT_CACHE_SYNC
-void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-		enum dma_data_direction direction);
-#else
-static inline void arch_dma_cache_sync(struct device *dev, void *vaddr,
-		size_t size, enum dma_data_direction direction)
-{
-}
-#endif /* CONFIG_DMA_NONCOHERENT_CACHE_SYNC */
-
 #ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE
 void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
 		enum dma_data_direction dir);
diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index 281785feb874..c5f717021f56 100644
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@ -75,9 +75,6 @@ config ARCH_HAS_DMA_PREP_COHERENT
 config ARCH_HAS_FORCE_DMA_UNENCRYPTED
 	bool
 
-config DMA_NONCOHERENT_CACHE_SYNC
-	bool
-
 config DMA_VIRT_OPS
 	bool
 	depends on HAS_DMA
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 9a045e51df17..673ea6759c15 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -529,20 +529,6 @@ int dma_set_coherent_mask(struct device *dev, u64 mask)
 EXPORT_SYMBOL(dma_set_coherent_mask);
 #endif
 
-void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-		enum dma_data_direction dir)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-
-	if (dma_alloc_direct(dev, ops))
-		arch_dma_cache_sync(dev, vaddr, size, dir);
-	else if (ops->cache_sync)
-		ops->cache_sync(dev, vaddr, size, dir);
-}
-EXPORT_SYMBOL(dma_cache_sync);
-
 size_t dma_max_mapping_size(struct device *dev)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
-- 
cgit v1.2.3


From efa70f2fdc842e63a0a13223e0e83cedcc2117f1 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 1 Sep 2020 13:34:33 +0200
Subject: dma-mapping: add a new dma_alloc_pages API

This API is the equivalent of alloc_pages, except that the returned memory
is guaranteed to be DMA addressable by the passed in device.  The
implementation will also be used to provide a more sensible replacement
for DMA_ATTR_NON_CONSISTENT flag.

Additionally dma_alloc_noncoherent is switched over to use dma_alloc_pages
as its backend.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de> (MIPS part)
---
 Documentation/core-api/dma-attributes.rst |  8 ----
 arch/alpha/kernel/pci_iommu.c             |  2 +
 arch/arm/mm/dma-mapping-nommu.c           |  2 +
 arch/arm/mm/dma-mapping.c                 |  4 ++
 arch/ia64/hp/common/sba_iommu.c           |  2 +
 arch/mips/jazz/jazzdma.c                  |  7 +---
 arch/powerpc/kernel/dma-iommu.c           |  2 +
 arch/powerpc/platforms/ps3/system-bus.c   |  4 ++
 arch/powerpc/platforms/pseries/vio.c      |  2 +
 arch/s390/pci/pci_dma.c                   |  2 +
 arch/x86/kernel/amd_gart_64.c             |  2 +
 drivers/iommu/dma-iommu.c                 |  2 +
 drivers/iommu/intel/iommu.c               |  4 ++
 drivers/parisc/ccio-dma.c                 |  2 +
 drivers/parisc/sba_iommu.c                |  2 +
 drivers/xen/swiotlb-xen.c                 |  2 +
 include/linux/dma-direct.h                |  5 +++
 include/linux/dma-mapping.h               | 34 ++++++++---------
 include/linux/dma-noncoherent.h           |  3 --
 kernel/dma/direct.c                       | 52 ++++++++++++++++++++++++-
 kernel/dma/mapping.c                      | 63 +++++++++++++++++++++++++++++--
 kernel/dma/ops_helpers.c                  | 35 +++++++++++++++++
 kernel/dma/virt.c                         |  2 +
 23 files changed, 206 insertions(+), 37 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/core-api/dma-attributes.rst b/Documentation/core-api/dma-attributes.rst
index 29dcbe8826e8..1887d92e8e92 100644
--- a/Documentation/core-api/dma-attributes.rst
+++ b/Documentation/core-api/dma-attributes.rst
@@ -25,14 +25,6 @@ Since it is optional for platforms to implement DMA_ATTR_WRITE_COMBINE,
 those that do not will simply ignore the attribute and exhibit default
 behavior.
 
-DMA_ATTR_NON_CONSISTENT
------------------------
-
-DMA_ATTR_NON_CONSISTENT lets the platform to choose to return either
-consistent or non-consistent memory as it sees fit.  By using this API,
-you are guaranteeing to the platform that you have all the correct and
-necessary sync points for this memory in the driver.
-
 DMA_ATTR_NO_KERNEL_MAPPING
 --------------------------
 
diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c
index 6f7de4f4e191..447e0fd0ed38 100644
--- a/arch/alpha/kernel/pci_iommu.c
+++ b/arch/alpha/kernel/pci_iommu.c
@@ -952,5 +952,7 @@ const struct dma_map_ops alpha_pci_ops = {
 	.dma_supported		= alpha_pci_supported,
 	.mmap			= dma_common_mmap,
 	.get_sgtable		= dma_common_get_sgtable,
+	.alloc_pages		= dma_common_alloc_pages,
+	.free_pages		= dma_common_free_pages,
 };
 EXPORT_SYMBOL(alpha_pci_ops);
diff --git a/arch/arm/mm/dma-mapping-nommu.c b/arch/arm/mm/dma-mapping-nommu.c
index 287ef898a55e..43c6d66b6e73 100644
--- a/arch/arm/mm/dma-mapping-nommu.c
+++ b/arch/arm/mm/dma-mapping-nommu.c
@@ -176,6 +176,8 @@ static void arm_nommu_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist
 const struct dma_map_ops arm_nommu_dma_ops = {
 	.alloc			= arm_nommu_dma_alloc,
 	.free			= arm_nommu_dma_free,
+	.alloc_pages		= dma_direct_alloc_pages,
+	.free_pages		= dma_direct_free_pages,
 	.mmap			= arm_nommu_dma_mmap,
 	.map_page		= arm_nommu_dma_map_page,
 	.unmap_page		= arm_nommu_dma_unmap_page,
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 8a8949174b1c..7738b4d23f69 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -199,6 +199,8 @@ static int arm_dma_supported(struct device *dev, u64 mask)
 const struct dma_map_ops arm_dma_ops = {
 	.alloc			= arm_dma_alloc,
 	.free			= arm_dma_free,
+	.alloc_pages		= dma_direct_alloc_pages,
+	.free_pages		= dma_direct_free_pages,
 	.mmap			= arm_dma_mmap,
 	.get_sgtable		= arm_dma_get_sgtable,
 	.map_page		= arm_dma_map_page,
@@ -226,6 +228,8 @@ static int arm_coherent_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 const struct dma_map_ops arm_coherent_dma_ops = {
 	.alloc			= arm_coherent_dma_alloc,
 	.free			= arm_coherent_dma_free,
+	.alloc_pages		= dma_direct_alloc_pages,
+	.free_pages		= dma_direct_free_pages,
 	.mmap			= arm_coherent_dma_mmap,
 	.get_sgtable		= arm_dma_get_sgtable,
 	.map_page		= arm_coherent_dma_map_page,
diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c
index b49b73a95067..cafbb848a34e 100644
--- a/arch/ia64/hp/common/sba_iommu.c
+++ b/arch/ia64/hp/common/sba_iommu.c
@@ -2070,6 +2070,8 @@ static const struct dma_map_ops sba_dma_ops = {
 	.dma_supported		= sba_dma_supported,
 	.mmap			= dma_common_mmap,
 	.get_sgtable		= dma_common_get_sgtable,
+	.alloc_pages		= dma_common_alloc_pages,
+	.free_pages		= dma_common_free_pages,
 };
 
 static int __init
diff --git a/arch/mips/jazz/jazzdma.c b/arch/mips/jazz/jazzdma.c
index 2bf849caf507..f53bc043334c 100644
--- a/arch/mips/jazz/jazzdma.c
+++ b/arch/mips/jazz/jazzdma.c
@@ -506,9 +506,6 @@ static void *jazz_dma_alloc(struct device *dev, size_t size,
 	*dma_handle = vdma_alloc(virt_to_phys(ret), size);
 	if (*dma_handle == DMA_MAPPING_ERROR)
 		goto out_free_pages;
-
-	if (attrs & DMA_ATTR_NON_CONSISTENT)
-		return ret;
 	arch_dma_prep_coherent(page, size);
 	return (void *)(UNCAC_BASE + __pa(ret));
 
@@ -521,8 +518,6 @@ static void jazz_dma_free(struct device *dev, size_t size, void *vaddr,
 		dma_addr_t dma_handle, unsigned long attrs)
 {
 	vdma_free(dma_handle);
-	if (!(attrs & DMA_ATTR_NON_CONSISTENT))
-		vaddr = __va(vaddr - UNCAC_BASE);
 	__free_pages(virt_to_page(vaddr), get_order(size));
 }
 
@@ -622,5 +617,7 @@ const struct dma_map_ops jazz_dma_ops = {
 	.sync_sg_for_device	= jazz_dma_sync_sg_for_device,
 	.mmap			= dma_common_mmap,
 	.get_sgtable		= dma_common_get_sgtable,
+	.alloc_pages		= dma_common_alloc_pages,
+	.free_pages		= dma_common_free_pages,
 };
 EXPORT_SYMBOL(jazz_dma_ops);
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index 9053fc9d20c7..a1c744194018 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -138,4 +138,6 @@ const struct dma_map_ops dma_iommu_ops = {
 	.get_required_mask	= dma_iommu_get_required_mask,
 	.mmap			= dma_common_mmap,
 	.get_sgtable		= dma_common_get_sgtable,
+	.alloc_pages		= dma_common_alloc_pages,
+	.free_pages		= dma_common_free_pages,
 };
diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c
index 3542b7bd6a46..7bc5f9be3e12 100644
--- a/arch/powerpc/platforms/ps3/system-bus.c
+++ b/arch/powerpc/platforms/ps3/system-bus.c
@@ -696,6 +696,8 @@ static const struct dma_map_ops ps3_sb_dma_ops = {
 	.unmap_page = ps3_unmap_page,
 	.mmap = dma_common_mmap,
 	.get_sgtable = dma_common_get_sgtable,
+	.alloc_pages = dma_common_alloc_pages,
+	.free_pages = dma_common_free_pages,
 };
 
 static const struct dma_map_ops ps3_ioc0_dma_ops = {
@@ -708,6 +710,8 @@ static const struct dma_map_ops ps3_ioc0_dma_ops = {
 	.unmap_page = ps3_unmap_page,
 	.mmap = dma_common_mmap,
 	.get_sgtable = dma_common_get_sgtable,
+	.alloc_pages = dma_common_alloc_pages,
+	.free_pages = dma_common_free_pages,
 };
 
 /**
diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
index 0487b26f6f1a..98ed7b09b3fe 100644
--- a/arch/powerpc/platforms/pseries/vio.c
+++ b/arch/powerpc/platforms/pseries/vio.c
@@ -608,6 +608,8 @@ static const struct dma_map_ops vio_dma_mapping_ops = {
 	.get_required_mask = dma_iommu_get_required_mask,
 	.mmap		   = dma_common_mmap,
 	.get_sgtable	   = dma_common_get_sgtable,
+	.alloc_pages	   = dma_common_alloc_pages,
+	.free_pages	   = dma_common_free_pages,
 };
 
 /**
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index 4a37d8f4de9d..9291023e9469 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -668,6 +668,8 @@ const struct dma_map_ops s390_pci_dma_ops = {
 	.unmap_page	= s390_dma_unmap_pages,
 	.mmap		= dma_common_mmap,
 	.get_sgtable	= dma_common_get_sgtable,
+	.alloc_pages	= dma_common_alloc_pages,
+	.free_pages	= dma_common_free_pages,
 	/* dma_supported is unconditionally true without a callback */
 };
 EXPORT_SYMBOL_GPL(s390_pci_dma_ops);
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index 153374b996a2..c96dcaa572eb 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -677,6 +677,8 @@ static const struct dma_map_ops gart_dma_ops = {
 	.get_sgtable			= dma_common_get_sgtable,
 	.dma_supported			= dma_direct_supported,
 	.get_required_mask		= dma_direct_get_required_mask,
+	.alloc_pages			= dma_direct_alloc_pages,
+	.free_pages			= dma_direct_free_pages,
 };
 
 static void gart_iommu_shutdown(void)
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 5141d49a046b..00a5b49248e3 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -1120,6 +1120,8 @@ static unsigned long iommu_dma_get_merge_boundary(struct device *dev)
 static const struct dma_map_ops iommu_dma_ops = {
 	.alloc			= iommu_dma_alloc,
 	.free			= iommu_dma_free,
+	.alloc_pages		= dma_common_alloc_pages,
+	.free_pages		= dma_common_free_pages,
 	.mmap			= iommu_dma_mmap,
 	.get_sgtable		= iommu_dma_get_sgtable,
 	.map_page		= iommu_dma_map_page,
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index ed5c57e96e8b..2c426dbdf17f 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -3712,6 +3712,8 @@ static const struct dma_map_ops intel_dma_ops = {
 	.dma_supported = dma_direct_supported,
 	.mmap = dma_common_mmap,
 	.get_sgtable = dma_common_get_sgtable,
+	.alloc_pages = dma_common_alloc_pages,
+	.free_pages = dma_common_free_pages,
 	.get_required_mask = intel_get_required_mask,
 };
 
@@ -3965,6 +3967,8 @@ static const struct dma_map_ops bounce_dma_ops = {
 	.sync_sg_for_device	= bounce_sync_sg_for_device,
 	.map_resource		= bounce_map_resource,
 	.unmap_resource		= bounce_unmap_resource,
+	.alloc_pages		= dma_common_alloc_pages,
+	.free_pages		= dma_common_free_pages,
 	.dma_supported		= dma_direct_supported,
 };
 
diff --git a/drivers/parisc/ccio-dma.c b/drivers/parisc/ccio-dma.c
index ba16b7f8f806..8cf0b9c8bdf7 100644
--- a/drivers/parisc/ccio-dma.c
+++ b/drivers/parisc/ccio-dma.c
@@ -1024,6 +1024,8 @@ static const struct dma_map_ops ccio_ops = {
 	.map_sg = 		ccio_map_sg,
 	.unmap_sg = 		ccio_unmap_sg,
 	.get_sgtable =		dma_common_get_sgtable,
+	.alloc_pages =		dma_common_alloc_pages,
+	.free_pages =		dma_common_free_pages,
 };
 
 #ifdef CONFIG_PROC_FS
diff --git a/drivers/parisc/sba_iommu.c b/drivers/parisc/sba_iommu.c
index 959bda193b96..6fcde7980358 100644
--- a/drivers/parisc/sba_iommu.c
+++ b/drivers/parisc/sba_iommu.c
@@ -1076,6 +1076,8 @@ static const struct dma_map_ops sba_ops = {
 	.map_sg =		sba_map_sg,
 	.unmap_sg =		sba_unmap_sg,
 	.get_sgtable =		dma_common_get_sgtable,
+	.alloc_pages =		dma_common_alloc_pages,
+	.free_pages =		dma_common_free_pages,
 };
 
 
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 39a0f2e0847c..030a225624b0 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -578,4 +578,6 @@ const struct dma_map_ops xen_swiotlb_dma_ops = {
 	.dma_supported = xen_swiotlb_dma_supported,
 	.mmap = dma_common_mmap,
 	.get_sgtable = dma_common_get_sgtable,
+	.alloc_pages = dma_common_alloc_pages,
+	.free_pages = dma_common_free_pages,
 };
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 83f797e0cb78..38ed3b55034d 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -115,6 +115,11 @@ void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t gfp, unsigned long attrs);
 void dma_direct_free(struct device *dev, size_t size, void *cpu_addr,
 		dma_addr_t dma_addr, unsigned long attrs);
+struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp);
+void dma_direct_free_pages(struct device *dev, size_t size,
+		struct page *page, dma_addr_t dma_addr,
+		enum dma_data_direction dir);
 int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		unsigned long attrs);
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 233bb8dcbe02..4b9b1d64f5ec 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -27,11 +27,6 @@
  * buffered to improve performance.
  */
 #define DMA_ATTR_WRITE_COMBINE		(1UL << 2)
-/*
- * DMA_ATTR_NON_CONSISTENT: Lets the platform to choose to return either
- * consistent or non-consistent memory as it sees fit.
- */
-#define DMA_ATTR_NON_CONSISTENT		(1UL << 3)
 /*
  * DMA_ATTR_NO_KERNEL_MAPPING: Lets the platform to avoid creating a kernel
  * virtual mapping for the allocated buffer.
@@ -74,6 +69,11 @@ struct dma_map_ops {
 	void (*free)(struct device *dev, size_t size,
 			      void *vaddr, dma_addr_t dma_handle,
 			      unsigned long attrs);
+	struct page *(*alloc_pages)(struct device *dev, size_t size,
+			dma_addr_t *dma_handle, enum dma_data_direction dir,
+			gfp_t gfp);
+	void (*free_pages)(struct device *dev, size_t size, struct page *vaddr,
+			dma_addr_t dma_handle, enum dma_data_direction dir);
 	int (*mmap)(struct device *, struct vm_area_struct *,
 			  void *, dma_addr_t, size_t,
 			  unsigned long attrs);
@@ -376,17 +376,14 @@ static inline unsigned long dma_get_merge_boundary(struct device *dev)
 }
 #endif /* CONFIG_HAS_DMA */
 
-static inline void *dma_alloc_noncoherent(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp)
-{
-	return dma_alloc_attrs(dev, size, dma_handle, gfp,
-			DMA_ATTR_NON_CONSISTENT);
-}
-static inline void dma_free_noncoherent(struct device *dev, size_t size,
-		void *vaddr, dma_addr_t dma_handle, enum dma_data_direction dir)
-{
-	dma_free_attrs(dev, size, vaddr, dma_handle, DMA_ATTR_NON_CONSISTENT);
-}
+struct page *dma_alloc_pages(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp);
+void dma_free_pages(struct device *dev, size_t size, struct page *page,
+		dma_addr_t dma_handle, enum dma_data_direction dir);
+void *dma_alloc_noncoherent(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp);
+void dma_free_noncoherent(struct device *dev, size_t size, void *vaddr,
+		dma_addr_t dma_handle, enum dma_data_direction dir);
 
 static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
@@ -512,7 +509,10 @@ static inline void dma_sync_sgtable_for_device(struct device *dev,
 extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		unsigned long attrs);
-
+struct page *dma_common_alloc_pages(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp);
+void dma_common_free_pages(struct device *dev, size_t size, struct page *vaddr,
+		dma_addr_t dma_handle, enum dma_data_direction dir);
 struct page **dma_common_find_pages(void *cpu_addr);
 void *dma_common_contiguous_remap(struct page *page, size_t size,
 			pgprot_t prot, const void *caller);
diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h
index 0888656369a4..e61283e06576 100644
--- a/include/linux/dma-noncoherent.h
+++ b/include/linux/dma-noncoherent.h
@@ -31,9 +31,6 @@ static __always_inline bool dma_alloc_need_uncached(struct device *dev,
 		return false;
 	if (attrs & DMA_ATTR_NO_KERNEL_MAPPING)
 		return false;
-	if (IS_ENABLED(CONFIG_DMA_NONCOHERENT_CACHE_SYNC) &&
-	    (attrs & DMA_ATTR_NON_CONSISTENT))
-		return false;
 	return true;
 }
 
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 750659f7447c..121a9c1969dd 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright (C) 2018 Christoph Hellwig.
+ * Copyright (C) 2018-2020 Christoph Hellwig.
  *
  * DMA operations that map physical memory directly without using an IOMMU.
  */
@@ -292,6 +292,56 @@ void dma_direct_free(struct device *dev, size_t size,
 	dma_free_contiguous(dev, dma_direct_to_page(dev, dma_addr), size);
 }
 
+struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp)
+{
+	struct page *page;
+	void *ret;
+
+	if (dma_should_alloc_from_pool(dev, gfp, 0)) {
+		page = dma_alloc_from_pool(dev, size, &ret, gfp,
+				dma_coherent_ok);
+		if (!page)
+			return NULL;
+		goto done;
+	}
+
+	page = __dma_direct_alloc_pages(dev, size, gfp);
+	if (!page)
+		return NULL;
+	ret = page_address(page);
+	if (force_dma_unencrypted(dev)) {
+		if (set_memory_decrypted((unsigned long)ret,
+				1 << get_order(size)))
+			goto out_free_pages;
+	}
+	memset(ret, 0, size);
+done:
+	*dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
+	return page;
+out_free_pages:
+	dma_free_contiguous(dev, page, size);
+	return NULL;
+}
+
+void dma_direct_free_pages(struct device *dev, size_t size,
+		struct page *page, dma_addr_t dma_addr,
+		enum dma_data_direction dir)
+{
+	unsigned int page_order = get_order(size);
+	void *vaddr = page_address(page);
+
+	/* If cpu_addr is not from an atomic pool, dma_free_from_pool() fails */
+	if (dma_should_free_from_pool(dev, 0) &&
+	    dma_free_from_pool(dev, vaddr, size))
+		return;
+
+	if (force_dma_unencrypted(dev))
+		set_memory_encrypted((unsigned long)vaddr, 1 << page_order);
+
+	dma_free_contiguous(dev, page, size);
+}
+
 #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
     defined(CONFIG_SWIOTLB)
 void dma_direct_sync_sg_for_device(struct device *dev,
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 673ea6759c15..06115f59f4ff 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -341,9 +341,7 @@ pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs)
 {
 	if (force_dma_unencrypted(dev))
 		prot = pgprot_decrypted(prot);
-	if (dev_is_dma_coherent(dev) ||
-	    (IS_ENABLED(CONFIG_DMA_NONCOHERENT_CACHE_SYNC) &&
-             (attrs & DMA_ATTR_NON_CONSISTENT)))
+	if (dev_is_dma_coherent(dev))
 		return prot;
 #ifdef CONFIG_ARCH_HAS_DMA_WRITE_COMBINE
 	if (attrs & DMA_ATTR_WRITE_COMBINE)
@@ -472,6 +470,65 @@ void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 }
 EXPORT_SYMBOL(dma_free_attrs);
 
+struct page *dma_alloc_pages(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	struct page *page;
+
+	if (WARN_ON_ONCE(!dev->coherent_dma_mask))
+		return NULL;
+	if (WARN_ON_ONCE(gfp & (__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM)))
+		return NULL;
+
+	size = PAGE_ALIGN(size);
+	if (dma_alloc_direct(dev, ops))
+		page = dma_direct_alloc_pages(dev, size, dma_handle, dir, gfp);
+	else if (ops->alloc_pages)
+		page = ops->alloc_pages(dev, size, dma_handle, dir, gfp);
+	else
+		return NULL;
+
+	debug_dma_map_page(dev, page, 0, size, dir, *dma_handle);
+
+	return page;
+}
+EXPORT_SYMBOL_GPL(dma_alloc_pages);
+
+void dma_free_pages(struct device *dev, size_t size, struct page *page,
+		dma_addr_t dma_handle, enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	size = PAGE_ALIGN(size);
+	debug_dma_unmap_page(dev, dma_handle, size, dir);
+
+	if (dma_alloc_direct(dev, ops))
+		dma_direct_free_pages(dev, size, page, dma_handle, dir);
+	else if (ops->free_pages)
+		ops->free_pages(dev, size, page, dma_handle, dir);
+}
+EXPORT_SYMBOL_GPL(dma_free_pages);
+
+void *dma_alloc_noncoherent(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp)
+{
+	struct page *page;
+
+	page = dma_alloc_pages(dev, size, dma_handle, dir, gfp);
+	if (!page)
+		return NULL;
+	return page_address(page);
+}
+EXPORT_SYMBOL_GPL(dma_alloc_noncoherent);
+
+void dma_free_noncoherent(struct device *dev, size_t size, void *vaddr,
+		dma_addr_t dma_handle, enum dma_data_direction dir)
+{
+	dma_free_pages(dev, size, virt_to_page(vaddr), dma_handle, dir);
+}
+EXPORT_SYMBOL_GPL(dma_free_noncoherent);
+
 int dma_supported(struct device *dev, u64 mask)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
diff --git a/kernel/dma/ops_helpers.c b/kernel/dma/ops_helpers.c
index e443c69be429..5828e5e01b79 100644
--- a/kernel/dma/ops_helpers.c
+++ b/kernel/dma/ops_helpers.c
@@ -3,6 +3,7 @@
  * Helpers for DMA ops implementations.  These generally rely on the fact that
  * the allocated memory contains normal pages in the direct kernel mapping.
  */
+#include <linux/dma-contiguous.h>
 #include <linux/dma-noncoherent.h>
 
 /*
@@ -49,3 +50,37 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
 	return -ENXIO;
 #endif /* CONFIG_MMU */
 }
+
+struct page *dma_common_alloc_pages(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	struct page *page;
+
+	page = dma_alloc_contiguous(dev, size, gfp);
+	if (!page)
+		page = alloc_pages_node(dev_to_node(dev), gfp, get_order(size));
+	if (!page)
+		return NULL;
+
+	*dma_handle = ops->map_page(dev, page, 0, size, dir,
+				    DMA_ATTR_SKIP_CPU_SYNC);
+	if (*dma_handle == DMA_MAPPING_ERROR) {
+		dma_free_contiguous(dev, page, size);
+		return NULL;
+	}
+
+	memset(page_address(page), 0, size);
+	return page;
+}
+
+void dma_common_free_pages(struct device *dev, size_t size, struct page *page,
+		dma_addr_t dma_handle, enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (ops->unmap_page)
+		ops->unmap_page(dev, dma_handle, size, dir,
+				DMA_ATTR_SKIP_CPU_SYNC);
+	dma_free_contiguous(dev, page, size);
+}
diff --git a/kernel/dma/virt.c b/kernel/dma/virt.c
index ebe128833af7..6986bf1fd668 100644
--- a/kernel/dma/virt.c
+++ b/kernel/dma/virt.c
@@ -55,5 +55,7 @@ const struct dma_map_ops dma_virt_ops = {
 	.free			= dma_virt_free,
 	.map_page		= dma_virt_map_page,
 	.map_sg			= dma_virt_map_sg,
+	.alloc_pages		= dma_common_alloc_pages,
+	.free_pages		= dma_common_free_pages,
 };
 EXPORT_SYMBOL(dma_virt_ops);
-- 
cgit v1.2.3


From de7cf917768f438aae6d2f4e9bced3739f15f5b6 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 1 Sep 2020 13:59:45 +0200
Subject: dma-mapping: add new {alloc,free}_noncoherent dma_map_ops methods

This will allow IOMMU drivers to allocate non-contigous memory and
return a vmapped virtual address.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/dma-mapping.h |  5 +++++
 kernel/dma/mapping.c        | 33 +++++++++++++++++++++++++++------
 2 files changed, 32 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 4b9b1d64f5ec..7c77cd6f3604 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -74,6 +74,11 @@ struct dma_map_ops {
 			gfp_t gfp);
 	void (*free_pages)(struct device *dev, size_t size, struct page *vaddr,
 			dma_addr_t dma_handle, enum dma_data_direction dir);
+	void* (*alloc_noncoherent)(struct device *dev, size_t size,
+			dma_addr_t *dma_handle, enum dma_data_direction dir,
+			gfp_t gfp);
+	void (*free_noncoherent)(struct device *dev, size_t size, void *vaddr,
+			dma_addr_t dma_handle, enum dma_data_direction dir);
 	int (*mmap)(struct device *, struct vm_area_struct *,
 			  void *, dma_addr_t, size_t,
 			  unsigned long attrs);
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 06115f59f4ff..9669550656a0 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -513,19 +513,40 @@ EXPORT_SYMBOL_GPL(dma_free_pages);
 void *dma_alloc_noncoherent(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp)
 {
-	struct page *page;
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	void *vaddr;
 
-	page = dma_alloc_pages(dev, size, dma_handle, dir, gfp);
-	if (!page)
-		return NULL;
-	return page_address(page);
+	if (!ops || !ops->alloc_noncoherent) {
+		struct page *page;
+
+		page = dma_alloc_pages(dev, size, dma_handle, dir, gfp);
+		if (!page)
+			return NULL;
+		return page_address(page);
+	}
+
+	size = PAGE_ALIGN(size);
+	vaddr = ops->alloc_noncoherent(dev, size, dma_handle, dir, gfp);
+	if (vaddr)
+		debug_dma_map_page(dev, virt_to_page(vaddr), 0, size, dir,
+				   *dma_handle);
+	return vaddr;
 }
 EXPORT_SYMBOL_GPL(dma_alloc_noncoherent);
 
 void dma_free_noncoherent(struct device *dev, size_t size, void *vaddr,
 		dma_addr_t dma_handle, enum dma_data_direction dir)
 {
-	dma_free_pages(dev, size, virt_to_page(vaddr), dma_handle, dir);
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (!ops || !ops->free_noncoherent) {
+		dma_free_pages(dev, size, virt_to_page(vaddr), dma_handle, dir);
+		return;
+	}
+
+	size = PAGE_ALIGN(size);
+	debug_dma_unmap_page(dev, dma_handle, size, dir);
+	ops->free_noncoherent(dev, size, vaddr, dma_handle, dir);
 }
 EXPORT_SYMBOL_GPL(dma_free_noncoherent);
 
-- 
cgit v1.2.3


From a8ea8bdd9df92a0e5db5b43900abb7a288b8a53e Mon Sep 17 00:00:00 2001
From: Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
Date: Mon, 21 Sep 2020 00:20:55 +0800
Subject: lib/mpi: Extend the MPI library

Expand the mpi library based on libgcrypt, and the ECC algorithm of
mpi based on libgcrypt requires these functions.
Some other algorithms will be developed based on mpi ecc, such as SM2.

Signed-off-by: Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
Tested-by: Xufeng Zhang <yunbo.xufeng@linux.alibaba.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/linux/mpi.h    |  87 +++++++++++++
 lib/mpi/Makefile       |   5 +
 lib/mpi/mpi-add.c      | 155 +++++++++++++++++++++++
 lib/mpi/mpi-bit.c      | 251 ++++++++++++++++++++++++++++++++++++
 lib/mpi/mpi-cmp.c      |  46 +++++--
 lib/mpi/mpi-div.c      | 238 +++++++++++++++++++++++++++++++++++
 lib/mpi/mpi-internal.h |  53 ++++++++
 lib/mpi/mpi-inv.c      | 143 +++++++++++++++++++++
 lib/mpi/mpi-mod.c      | 155 +++++++++++++++++++++++
 lib/mpi/mpi-mul.c      |  94 ++++++++++++++
 lib/mpi/mpicoder.c     | 336 +++++++++++++++++++++++++++++++++++++++++++++++++
 lib/mpi/mpih-div.c     | 294 +++++++++++++++++++++++++++++++++++++++++++
 lib/mpi/mpih-mul.c     |  25 ++++
 lib/mpi/mpiutil.c      | 204 ++++++++++++++++++++++++++++++
 14 files changed, 2076 insertions(+), 10 deletions(-)
 create mode 100644 lib/mpi/mpi-add.c
 create mode 100644 lib/mpi/mpi-div.c
 create mode 100644 lib/mpi/mpi-inv.c
 create mode 100644 lib/mpi/mpi-mod.c
 create mode 100644 lib/mpi/mpi-mul.c

(limited to 'include/linux')

diff --git a/include/linux/mpi.h b/include/linux/mpi.h
index 5d906dfbf3ed..3c9e41603cf6 100644
--- a/include/linux/mpi.h
+++ b/include/linux/mpi.h
@@ -40,21 +40,79 @@ struct gcry_mpi {
 typedef struct gcry_mpi *MPI;
 
 #define mpi_get_nlimbs(a)     ((a)->nlimbs)
+#define mpi_has_sign(a)       ((a)->sign)
 
 /*-- mpiutil.c --*/
 MPI mpi_alloc(unsigned nlimbs);
+void mpi_clear(MPI a);
 void mpi_free(MPI a);
 int mpi_resize(MPI a, unsigned nlimbs);
 
+static inline MPI mpi_new(unsigned int nbits)
+{
+	return mpi_alloc((nbits + BITS_PER_MPI_LIMB - 1) / BITS_PER_MPI_LIMB);
+}
+
+MPI mpi_copy(MPI a);
+MPI mpi_alloc_like(MPI a);
+void mpi_snatch(MPI w, MPI u);
+MPI mpi_set(MPI w, MPI u);
+MPI mpi_set_ui(MPI w, unsigned long u);
+MPI mpi_alloc_set_ui(unsigned long u);
+void mpi_swap_cond(MPI a, MPI b, unsigned long swap);
+
+/* Constants used to return constant MPIs.  See mpi_init if you
+ * want to add more constants.
+ */
+#define MPI_NUMBER_OF_CONSTANTS 6
+enum gcry_mpi_constants {
+	MPI_C_ZERO,
+	MPI_C_ONE,
+	MPI_C_TWO,
+	MPI_C_THREE,
+	MPI_C_FOUR,
+	MPI_C_EIGHT
+};
+
+MPI mpi_const(enum gcry_mpi_constants no);
+
 /*-- mpicoder.c --*/
+
+/* Different formats of external big integer representation. */
+enum gcry_mpi_format {
+	GCRYMPI_FMT_NONE = 0,
+	GCRYMPI_FMT_STD = 1,    /* Twos complement stored without length. */
+	GCRYMPI_FMT_PGP = 2,    /* As used by OpenPGP (unsigned only). */
+	GCRYMPI_FMT_SSH = 3,    /* As used by SSH (like STD but with length). */
+	GCRYMPI_FMT_HEX = 4,    /* Hex format. */
+	GCRYMPI_FMT_USG = 5,    /* Like STD but unsigned. */
+	GCRYMPI_FMT_OPAQUE = 8  /* Opaque format (some functions only). */
+};
+
 MPI mpi_read_raw_data(const void *xbuffer, size_t nbytes);
 MPI mpi_read_from_buffer(const void *buffer, unsigned *ret_nread);
+int mpi_fromstr(MPI val, const char *str);
+MPI mpi_scanval(const char *string);
 MPI mpi_read_raw_from_sgl(struct scatterlist *sgl, unsigned int len);
 void *mpi_get_buffer(MPI a, unsigned *nbytes, int *sign);
 int mpi_read_buffer(MPI a, uint8_t *buf, unsigned buf_len, unsigned *nbytes,
 		    int *sign);
 int mpi_write_to_sgl(MPI a, struct scatterlist *sg, unsigned nbytes,
 		     int *sign);
+int mpi_print(enum gcry_mpi_format format, unsigned char *buffer,
+			size_t buflen, size_t *nwritten, MPI a);
+
+/*-- mpi-mod.c --*/
+void mpi_mod(MPI rem, MPI dividend, MPI divisor);
+
+/* Context used with Barrett reduction.  */
+struct barrett_ctx_s;
+typedef struct barrett_ctx_s *mpi_barrett_t;
+
+mpi_barrett_t mpi_barrett_init(MPI m, int copy);
+void mpi_barrett_free(mpi_barrett_t ctx);
+void mpi_mod_barrett(MPI r, MPI x, mpi_barrett_t ctx);
+void mpi_mul_barrett(MPI w, MPI u, MPI v, mpi_barrett_t ctx);
 
 /*-- mpi-pow.c --*/
 int mpi_powm(MPI res, MPI base, MPI exp, MPI mod);
@@ -62,6 +120,7 @@ int mpi_powm(MPI res, MPI base, MPI exp, MPI mod);
 /*-- mpi-cmp.c --*/
 int mpi_cmp_ui(MPI u, ulong v);
 int mpi_cmp(MPI u, MPI v);
+int mpi_cmpabs(MPI u, MPI v);
 
 /*-- mpi-sub-ui.c --*/
 int mpi_sub_ui(MPI w, MPI u, unsigned long vval);
@@ -69,6 +128,34 @@ int mpi_sub_ui(MPI w, MPI u, unsigned long vval);
 /*-- mpi-bit.c --*/
 void mpi_normalize(MPI a);
 unsigned mpi_get_nbits(MPI a);
+int mpi_test_bit(MPI a, unsigned int n);
+void mpi_set_bit(MPI a, unsigned int n);
+void mpi_set_highbit(MPI a, unsigned int n);
+void mpi_clear_highbit(MPI a, unsigned int n);
+void mpi_clear_bit(MPI a, unsigned int n);
+void mpi_rshift_limbs(MPI a, unsigned int count);
+void mpi_rshift(MPI x, MPI a, unsigned int n);
+void mpi_lshift_limbs(MPI a, unsigned int count);
+void mpi_lshift(MPI x, MPI a, unsigned int n);
+
+/*-- mpi-add.c --*/
+void mpi_add_ui(MPI w, MPI u, unsigned long v);
+void mpi_add(MPI w, MPI u, MPI v);
+void mpi_sub(MPI w, MPI u, MPI v);
+void mpi_addm(MPI w, MPI u, MPI v, MPI m);
+void mpi_subm(MPI w, MPI u, MPI v, MPI m);
+
+/*-- mpi-mul.c --*/
+void mpi_mul(MPI w, MPI u, MPI v);
+void mpi_mulm(MPI w, MPI u, MPI v, MPI m);
+
+/*-- mpi-div.c --*/
+void mpi_tdiv_r(MPI rem, MPI num, MPI den);
+void mpi_fdiv_r(MPI rem, MPI dividend, MPI divisor);
+void mpi_fdiv_q(MPI quot, MPI dividend, MPI divisor);
+
+/*-- mpi-inv.c --*/
+int mpi_invm(MPI x, MPI a, MPI n);
 
 /* inline functions */
 
diff --git a/lib/mpi/Makefile b/lib/mpi/Makefile
index 43b8fce14079..477debd7ed50 100644
--- a/lib/mpi/Makefile
+++ b/lib/mpi/Makefile
@@ -14,9 +14,14 @@ mpi-y = \
 	generic_mpih-sub1.o		\
 	generic_mpih-add1.o		\
 	mpicoder.o			\
+	mpi-add.o			\
 	mpi-bit.o			\
 	mpi-cmp.o			\
 	mpi-sub-ui.o			\
+	mpi-div.o			\
+	mpi-inv.o			\
+	mpi-mod.o			\
+	mpi-mul.o			\
 	mpih-cmp.o			\
 	mpih-div.o			\
 	mpih-mul.o			\
diff --git a/lib/mpi/mpi-add.c b/lib/mpi/mpi-add.c
new file mode 100644
index 000000000000..2cdae54c1bd0
--- /dev/null
+++ b/lib/mpi/mpi-add.c
@@ -0,0 +1,155 @@
+/* mpi-add.c  -  MPI functions
+ * Copyright (C) 1994, 1996, 1998, 2001, 2002,
+ *               2003 Free Software Foundation, Inc.
+ *
+ * This file is part of Libgcrypt.
+ *
+ * Note: This code is heavily based on the GNU MP Library.
+ *	 Actually it's the same code with only minor changes in the
+ *	 way the data is stored; this is to support the abstraction
+ *	 of an optional secure memory allocation which may be used
+ *	 to avoid revealing of sensitive data due to paging etc.
+ */
+
+#include "mpi-internal.h"
+
+/****************
+ * Add the unsigned integer V to the mpi-integer U and store the
+ * result in W. U and V may be the same.
+ */
+void mpi_add_ui(MPI w, MPI u, unsigned long v)
+{
+	mpi_ptr_t wp, up;
+	mpi_size_t usize, wsize;
+	int usign, wsign;
+
+	usize = u->nlimbs;
+	usign = u->sign;
+	wsign = 0;
+
+	/* If not space for W (and possible carry), increase space.  */
+	wsize = usize + 1;
+	if (w->alloced < wsize)
+		mpi_resize(w, wsize);
+
+	/* These must be after realloc (U may be the same as W).  */
+	up = u->d;
+	wp = w->d;
+
+	if (!usize) {  /* simple */
+		wp[0] = v;
+		wsize = v ? 1:0;
+	} else if (!usign) {  /* mpi is not negative */
+		mpi_limb_t cy;
+		cy = mpihelp_add_1(wp, up, usize, v);
+		wp[usize] = cy;
+		wsize = usize + cy;
+	} else {
+		/* The signs are different.  Need exact comparison to determine
+		 * which operand to subtract from which.
+		 */
+		if (usize == 1 && up[0] < v) {
+			wp[0] = v - up[0];
+			wsize = 1;
+		} else {
+			mpihelp_sub_1(wp, up, usize, v);
+			/* Size can decrease with at most one limb. */
+			wsize = usize - (wp[usize-1] == 0);
+			wsign = 1;
+		}
+	}
+
+	w->nlimbs = wsize;
+	w->sign   = wsign;
+}
+
+
+void mpi_add(MPI w, MPI u, MPI v)
+{
+	mpi_ptr_t wp, up, vp;
+	mpi_size_t usize, vsize, wsize;
+	int usign, vsign, wsign;
+
+	if (u->nlimbs < v->nlimbs) { /* Swap U and V. */
+		usize = v->nlimbs;
+		usign = v->sign;
+		vsize = u->nlimbs;
+		vsign = u->sign;
+		wsize = usize + 1;
+		RESIZE_IF_NEEDED(w, wsize);
+		/* These must be after realloc (u or v may be the same as w).  */
+		up = v->d;
+		vp = u->d;
+	} else {
+		usize = u->nlimbs;
+		usign = u->sign;
+		vsize = v->nlimbs;
+		vsign = v->sign;
+		wsize = usize + 1;
+		RESIZE_IF_NEEDED(w, wsize);
+		/* These must be after realloc (u or v may be the same as w).  */
+		up = u->d;
+		vp = v->d;
+	}
+	wp = w->d;
+	wsign = 0;
+
+	if (!vsize) {  /* simple */
+		MPN_COPY(wp, up, usize);
+		wsize = usize;
+		wsign = usign;
+	} else if (usign != vsign) { /* different sign */
+		/* This test is right since USIZE >= VSIZE */
+		if (usize != vsize) {
+			mpihelp_sub(wp, up, usize, vp, vsize);
+			wsize = usize;
+			MPN_NORMALIZE(wp, wsize);
+			wsign = usign;
+		} else if (mpihelp_cmp(up, vp, usize) < 0) {
+			mpihelp_sub_n(wp, vp, up, usize);
+			wsize = usize;
+			MPN_NORMALIZE(wp, wsize);
+			if (!usign)
+				wsign = 1;
+		} else {
+			mpihelp_sub_n(wp, up, vp, usize);
+			wsize = usize;
+			MPN_NORMALIZE(wp, wsize);
+			if (usign)
+				wsign = 1;
+		}
+	} else { /* U and V have same sign. Add them. */
+		mpi_limb_t cy = mpihelp_add(wp, up, usize, vp, vsize);
+		wp[usize] = cy;
+		wsize = usize + cy;
+		if (usign)
+			wsign = 1;
+	}
+
+	w->nlimbs = wsize;
+	w->sign = wsign;
+}
+EXPORT_SYMBOL_GPL(mpi_add);
+
+void mpi_sub(MPI w, MPI u, MPI v)
+{
+	MPI vv = mpi_copy(v);
+	vv->sign = !vv->sign;
+	mpi_add(w, u, vv);
+	mpi_free(vv);
+}
+
+
+void mpi_addm(MPI w, MPI u, MPI v, MPI m)
+{
+	mpi_add(w, u, v);
+	mpi_mod(w, w, m);
+}
+EXPORT_SYMBOL_GPL(mpi_addm);
+
+void mpi_subm(MPI w, MPI u, MPI v, MPI m)
+{
+	mpi_sub(w, u, v);
+	mpi_mod(w, w, m);
+}
+EXPORT_SYMBOL_GPL(mpi_subm);
diff --git a/lib/mpi/mpi-bit.c b/lib/mpi/mpi-bit.c
index 503537e08436..a5119a2bcdd4 100644
--- a/lib/mpi/mpi-bit.c
+++ b/lib/mpi/mpi-bit.c
@@ -32,6 +32,7 @@ void mpi_normalize(MPI a)
 	for (; a->nlimbs && !a->d[a->nlimbs - 1]; a->nlimbs--)
 		;
 }
+EXPORT_SYMBOL_GPL(mpi_normalize);
 
 /****************
  * Return the number of bits in A.
@@ -54,3 +55,253 @@ unsigned mpi_get_nbits(MPI a)
 	return n;
 }
 EXPORT_SYMBOL_GPL(mpi_get_nbits);
+
+/****************
+ * Test whether bit N is set.
+ */
+int mpi_test_bit(MPI a, unsigned int n)
+{
+	unsigned int limbno, bitno;
+	mpi_limb_t limb;
+
+	limbno = n / BITS_PER_MPI_LIMB;
+	bitno  = n % BITS_PER_MPI_LIMB;
+
+	if (limbno >= a->nlimbs)
+		return 0; /* too far left: this is a 0 */
+	limb = a->d[limbno];
+	return (limb & (A_LIMB_1 << bitno)) ? 1 : 0;
+}
+EXPORT_SYMBOL_GPL(mpi_test_bit);
+
+/****************
+ * Set bit N of A.
+ */
+void mpi_set_bit(MPI a, unsigned int n)
+{
+	unsigned int i, limbno, bitno;
+
+	limbno = n / BITS_PER_MPI_LIMB;
+	bitno  = n % BITS_PER_MPI_LIMB;
+
+	if (limbno >= a->nlimbs) {
+		for (i = a->nlimbs; i < a->alloced; i++)
+			a->d[i] = 0;
+		mpi_resize(a, limbno+1);
+		a->nlimbs = limbno+1;
+	}
+	a->d[limbno] |= (A_LIMB_1<<bitno);
+}
+
+/****************
+ * Set bit N of A. and clear all bits above
+ */
+void mpi_set_highbit(MPI a, unsigned int n)
+{
+	unsigned int i, limbno, bitno;
+
+	limbno = n / BITS_PER_MPI_LIMB;
+	bitno  = n % BITS_PER_MPI_LIMB;
+
+	if (limbno >= a->nlimbs) {
+		for (i = a->nlimbs; i < a->alloced; i++)
+			a->d[i] = 0;
+		mpi_resize(a, limbno+1);
+		a->nlimbs = limbno+1;
+	}
+	a->d[limbno] |= (A_LIMB_1<<bitno);
+	for (bitno++; bitno < BITS_PER_MPI_LIMB; bitno++)
+		a->d[limbno] &= ~(A_LIMB_1 << bitno);
+	a->nlimbs = limbno+1;
+}
+EXPORT_SYMBOL_GPL(mpi_set_highbit);
+
+/****************
+ * clear bit N of A and all bits above
+ */
+void mpi_clear_highbit(MPI a, unsigned int n)
+{
+	unsigned int limbno, bitno;
+
+	limbno = n / BITS_PER_MPI_LIMB;
+	bitno  = n % BITS_PER_MPI_LIMB;
+
+	if (limbno >= a->nlimbs)
+		return; /* not allocated, therefore no need to clear bits :-) */
+
+	for ( ; bitno < BITS_PER_MPI_LIMB; bitno++)
+		a->d[limbno] &= ~(A_LIMB_1 << bitno);
+	a->nlimbs = limbno+1;
+}
+
+/****************
+ * Clear bit N of A.
+ */
+void mpi_clear_bit(MPI a, unsigned int n)
+{
+	unsigned int limbno, bitno;
+
+	limbno = n / BITS_PER_MPI_LIMB;
+	bitno  = n % BITS_PER_MPI_LIMB;
+
+	if (limbno >= a->nlimbs)
+		return; /* Don't need to clear this bit, it's far too left.  */
+	a->d[limbno] &= ~(A_LIMB_1 << bitno);
+}
+EXPORT_SYMBOL_GPL(mpi_clear_bit);
+
+
+/****************
+ * Shift A by COUNT limbs to the right
+ * This is used only within the MPI library
+ */
+void mpi_rshift_limbs(MPI a, unsigned int count)
+{
+	mpi_ptr_t ap = a->d;
+	mpi_size_t n = a->nlimbs;
+	unsigned int i;
+
+	if (count >= n) {
+		a->nlimbs = 0;
+		return;
+	}
+
+	for (i = 0; i < n - count; i++)
+		ap[i] = ap[i+count];
+	ap[i] = 0;
+	a->nlimbs -= count;
+}
+
+/*
+ * Shift A by N bits to the right.
+ */
+void mpi_rshift(MPI x, MPI a, unsigned int n)
+{
+	mpi_size_t xsize;
+	unsigned int i;
+	unsigned int nlimbs = (n/BITS_PER_MPI_LIMB);
+	unsigned int nbits = (n%BITS_PER_MPI_LIMB);
+
+	if (x == a) {
+		/* In-place operation.  */
+		if (nlimbs >= x->nlimbs) {
+			x->nlimbs = 0;
+			return;
+		}
+
+		if (nlimbs) {
+			for (i = 0; i < x->nlimbs - nlimbs; i++)
+				x->d[i] = x->d[i+nlimbs];
+			x->d[i] = 0;
+			x->nlimbs -= nlimbs;
+		}
+		if (x->nlimbs && nbits)
+			mpihelp_rshift(x->d, x->d, x->nlimbs, nbits);
+	} else if (nlimbs) {
+		/* Copy and shift by more or equal bits than in a limb. */
+		xsize = a->nlimbs;
+		x->sign = a->sign;
+		RESIZE_IF_NEEDED(x, xsize);
+		x->nlimbs = xsize;
+		for (i = 0; i < a->nlimbs; i++)
+			x->d[i] = a->d[i];
+		x->nlimbs = i;
+
+		if (nlimbs >= x->nlimbs) {
+			x->nlimbs = 0;
+			return;
+		}
+
+		if (nlimbs) {
+			for (i = 0; i < x->nlimbs - nlimbs; i++)
+				x->d[i] = x->d[i+nlimbs];
+			x->d[i] = 0;
+			x->nlimbs -= nlimbs;
+		}
+
+		if (x->nlimbs && nbits)
+			mpihelp_rshift(x->d, x->d, x->nlimbs, nbits);
+	} else {
+		/* Copy and shift by less than bits in a limb.  */
+		xsize = a->nlimbs;
+		x->sign = a->sign;
+		RESIZE_IF_NEEDED(x, xsize);
+		x->nlimbs = xsize;
+
+		if (xsize) {
+			if (nbits)
+				mpihelp_rshift(x->d, a->d, x->nlimbs, nbits);
+			else {
+				/* The rshift helper function is not specified for
+				 * NBITS==0, thus we do a plain copy here.
+				 */
+				for (i = 0; i < x->nlimbs; i++)
+					x->d[i] = a->d[i];
+			}
+		}
+	}
+	MPN_NORMALIZE(x->d, x->nlimbs);
+}
+
+/****************
+ * Shift A by COUNT limbs to the left
+ * This is used only within the MPI library
+ */
+void mpi_lshift_limbs(MPI a, unsigned int count)
+{
+	mpi_ptr_t ap;
+	int n = a->nlimbs;
+	int i;
+
+	if (!count || !n)
+		return;
+
+	RESIZE_IF_NEEDED(a, n+count);
+
+	ap = a->d;
+	for (i = n-1; i >= 0; i--)
+		ap[i+count] = ap[i];
+	for (i = 0; i < count; i++)
+		ap[i] = 0;
+	a->nlimbs += count;
+}
+
+/*
+ * Shift A by N bits to the left.
+ */
+void mpi_lshift(MPI x, MPI a, unsigned int n)
+{
+	unsigned int nlimbs = (n/BITS_PER_MPI_LIMB);
+	unsigned int nbits = (n%BITS_PER_MPI_LIMB);
+
+	if (x == a && !n)
+		return;  /* In-place shift with an amount of zero.  */
+
+	if (x != a) {
+		/* Copy A to X.  */
+		unsigned int alimbs = a->nlimbs;
+		int asign = a->sign;
+		mpi_ptr_t xp, ap;
+
+		RESIZE_IF_NEEDED(x, alimbs+nlimbs+1);
+		xp = x->d;
+		ap = a->d;
+		MPN_COPY(xp, ap, alimbs);
+		x->nlimbs = alimbs;
+		x->flags = a->flags;
+		x->sign = asign;
+	}
+
+	if (nlimbs && !nbits) {
+		/* Shift a full number of limbs.  */
+		mpi_lshift_limbs(x, nlimbs);
+	} else if (n) {
+		/* We use a very dump approach: Shift left by the number of
+		 * limbs plus one and than fix it up by an rshift.
+		 */
+		mpi_lshift_limbs(x, nlimbs+1);
+		mpi_rshift(x, x, BITS_PER_MPI_LIMB - nbits);
+	}
+
+	MPN_NORMALIZE(x->d, x->nlimbs);
+}
diff --git a/lib/mpi/mpi-cmp.c b/lib/mpi/mpi-cmp.c
index d25e9e96c310..c4cfa3ff0581 100644
--- a/lib/mpi/mpi-cmp.c
+++ b/lib/mpi/mpi-cmp.c
@@ -41,28 +41,54 @@ int mpi_cmp_ui(MPI u, unsigned long v)
 }
 EXPORT_SYMBOL_GPL(mpi_cmp_ui);
 
-int mpi_cmp(MPI u, MPI v)
+static int do_mpi_cmp(MPI u, MPI v, int absmode)
 {
-	mpi_size_t usize, vsize;
+	mpi_size_t usize;
+	mpi_size_t vsize;
+	int usign;
+	int vsign;
 	int cmp;
 
 	mpi_normalize(u);
 	mpi_normalize(v);
+
 	usize = u->nlimbs;
 	vsize = v->nlimbs;
-	if (!u->sign && v->sign)
+	usign = absmode ? 0 : u->sign;
+	vsign = absmode ? 0 : v->sign;
+
+	/* Compare sign bits.  */
+
+	if (!usign && vsign)
 		return 1;
-	if (u->sign && !v->sign)
+	if (usign && !vsign)
 		return -1;
-	if (usize != vsize && !u->sign && !v->sign)
+
+	/* U and V are either both positive or both negative.  */
+
+	if (usize != vsize && !usign && !vsign)
 		return usize - vsize;
-	if (usize != vsize && u->sign && v->sign)
-		return vsize - usize;
+	if (usize != vsize && usign && vsign)
+		return vsize + usize;
 	if (!usize)
 		return 0;
 	cmp = mpihelp_cmp(u->d, v->d, usize);
-	if (u->sign)
-		return -cmp;
-	return cmp;
+	if (!cmp)
+		return 0;
+	if ((cmp < 0?1:0) == (usign?1:0))
+		return 1;
+
+	return -1;
+}
+
+int mpi_cmp(MPI u, MPI v)
+{
+	return do_mpi_cmp(u, v, 0);
 }
 EXPORT_SYMBOL_GPL(mpi_cmp);
+
+int mpi_cmpabs(MPI u, MPI v)
+{
+	return do_mpi_cmp(u, v, 1);
+}
+EXPORT_SYMBOL_GPL(mpi_cmpabs);
diff --git a/lib/mpi/mpi-div.c b/lib/mpi/mpi-div.c
new file mode 100644
index 000000000000..21332dab97d4
--- /dev/null
+++ b/lib/mpi/mpi-div.c
@@ -0,0 +1,238 @@
+/* mpi-div.c  -  MPI functions
+ * Copyright (C) 1994, 1996, 1998, 2001, 2002,
+ *               2003 Free Software Foundation, Inc.
+ *
+ * This file is part of Libgcrypt.
+ *
+ * Note: This code is heavily based on the GNU MP Library.
+ *	 Actually it's the same code with only minor changes in the
+ *	 way the data is stored; this is to support the abstraction
+ *	 of an optional secure memory allocation which may be used
+ *	 to avoid revealing of sensitive data due to paging etc.
+ */
+
+#include "mpi-internal.h"
+#include "longlong.h"
+
+void mpi_tdiv_qr(MPI quot, MPI rem, MPI num, MPI den);
+void mpi_fdiv_qr(MPI quot, MPI rem, MPI dividend, MPI divisor);
+
+void mpi_fdiv_r(MPI rem, MPI dividend, MPI divisor)
+{
+	int divisor_sign = divisor->sign;
+	MPI temp_divisor = NULL;
+
+	/* We need the original value of the divisor after the remainder has been
+	 * preliminary calculated.	We have to copy it to temporary space if it's
+	 * the same variable as REM.
+	 */
+	if (rem == divisor) {
+		temp_divisor = mpi_copy(divisor);
+		divisor = temp_divisor;
+	}
+
+	mpi_tdiv_r(rem, dividend, divisor);
+
+	if (((divisor_sign?1:0) ^ (dividend->sign?1:0)) && rem->nlimbs)
+		mpi_add(rem, rem, divisor);
+
+	if (temp_divisor)
+		mpi_free(temp_divisor);
+}
+
+void mpi_fdiv_q(MPI quot, MPI dividend, MPI divisor)
+{
+	MPI tmp = mpi_alloc(mpi_get_nlimbs(quot));
+	mpi_fdiv_qr(quot, tmp, dividend, divisor);
+	mpi_free(tmp);
+}
+
+void mpi_fdiv_qr(MPI quot, MPI rem, MPI dividend, MPI divisor)
+{
+	int divisor_sign = divisor->sign;
+	MPI temp_divisor = NULL;
+
+	if (quot == divisor || rem == divisor) {
+		temp_divisor = mpi_copy(divisor);
+		divisor = temp_divisor;
+	}
+
+	mpi_tdiv_qr(quot, rem, dividend, divisor);
+
+	if ((divisor_sign ^ dividend->sign) && rem->nlimbs) {
+		mpi_sub_ui(quot, quot, 1);
+		mpi_add(rem, rem, divisor);
+	}
+
+	if (temp_divisor)
+		mpi_free(temp_divisor);
+}
+
+/* If den == quot, den needs temporary storage.
+ * If den == rem, den needs temporary storage.
+ * If num == quot, num needs temporary storage.
+ * If den has temporary storage, it can be normalized while being copied,
+ *   i.e no extra storage should be allocated.
+ */
+
+void mpi_tdiv_r(MPI rem, MPI num, MPI den)
+{
+	mpi_tdiv_qr(NULL, rem, num, den);
+}
+
+void mpi_tdiv_qr(MPI quot, MPI rem, MPI num, MPI den)
+{
+	mpi_ptr_t np, dp;
+	mpi_ptr_t qp, rp;
+	mpi_size_t nsize = num->nlimbs;
+	mpi_size_t dsize = den->nlimbs;
+	mpi_size_t qsize, rsize;
+	mpi_size_t sign_remainder = num->sign;
+	mpi_size_t sign_quotient = num->sign ^ den->sign;
+	unsigned int normalization_steps;
+	mpi_limb_t q_limb;
+	mpi_ptr_t marker[5];
+	unsigned int marker_nlimbs[5];
+	int markidx = 0;
+
+	/* Ensure space is enough for quotient and remainder.
+	 * We need space for an extra limb in the remainder, because it's
+	 * up-shifted (normalized) below.
+	 */
+	rsize = nsize + 1;
+	mpi_resize(rem, rsize);
+
+	qsize = rsize - dsize;	  /* qsize cannot be bigger than this.	*/
+	if (qsize <= 0) {
+		if (num != rem) {
+			rem->nlimbs = num->nlimbs;
+			rem->sign = num->sign;
+			MPN_COPY(rem->d, num->d, nsize);
+		}
+		if (quot) {
+			/* This needs to follow the assignment to rem, in case the
+			 * numerator and quotient are the same.
+			 */
+			quot->nlimbs = 0;
+			quot->sign = 0;
+		}
+		return;
+	}
+
+	if (quot)
+		mpi_resize(quot, qsize);
+
+	/* Read pointers here, when reallocation is finished.  */
+	np = num->d;
+	dp = den->d;
+	rp = rem->d;
+
+	/* Optimize division by a single-limb divisor.  */
+	if (dsize == 1) {
+		mpi_limb_t rlimb;
+		if (quot) {
+			qp = quot->d;
+			rlimb = mpihelp_divmod_1(qp, np, nsize, dp[0]);
+			qsize -= qp[qsize - 1] == 0;
+			quot->nlimbs = qsize;
+			quot->sign = sign_quotient;
+		} else
+			rlimb = mpihelp_mod_1(np, nsize, dp[0]);
+		rp[0] = rlimb;
+		rsize = rlimb != 0?1:0;
+		rem->nlimbs = rsize;
+		rem->sign = sign_remainder;
+		return;
+	}
+
+
+	if (quot) {
+		qp = quot->d;
+		/* Make sure QP and NP point to different objects.  Otherwise the
+		 * numerator would be gradually overwritten by the quotient limbs.
+		 */
+		if (qp == np) { /* Copy NP object to temporary space.  */
+			marker_nlimbs[markidx] = nsize;
+			np = marker[markidx++] = mpi_alloc_limb_space(nsize);
+			MPN_COPY(np, qp, nsize);
+		}
+	} else /* Put quotient at top of remainder. */
+		qp = rp + dsize;
+
+	normalization_steps = count_leading_zeros(dp[dsize - 1]);
+
+	/* Normalize the denominator, i.e. make its most significant bit set by
+	 * shifting it NORMALIZATION_STEPS bits to the left.  Also shift the
+	 * numerator the same number of steps (to keep the quotient the same!).
+	 */
+	if (normalization_steps) {
+		mpi_ptr_t tp;
+		mpi_limb_t nlimb;
+
+		/* Shift up the denominator setting the most significant bit of
+		 * the most significant word.  Use temporary storage not to clobber
+		 * the original contents of the denominator.
+		 */
+		marker_nlimbs[markidx] = dsize;
+		tp = marker[markidx++] = mpi_alloc_limb_space(dsize);
+		mpihelp_lshift(tp, dp, dsize, normalization_steps);
+		dp = tp;
+
+		/* Shift up the numerator, possibly introducing a new most
+		 * significant word.  Move the shifted numerator in the remainder
+		 * meanwhile.
+		 */
+		nlimb = mpihelp_lshift(rp, np, nsize, normalization_steps);
+		if (nlimb) {
+			rp[nsize] = nlimb;
+			rsize = nsize + 1;
+		} else
+			rsize = nsize;
+	} else {
+		/* The denominator is already normalized, as required.	Copy it to
+		 * temporary space if it overlaps with the quotient or remainder.
+		 */
+		if (dp == rp || (quot && (dp == qp))) {
+			mpi_ptr_t tp;
+
+			marker_nlimbs[markidx] = dsize;
+			tp = marker[markidx++] = mpi_alloc_limb_space(dsize);
+			MPN_COPY(tp, dp, dsize);
+			dp = tp;
+		}
+
+		/* Move the numerator to the remainder.  */
+		if (rp != np)
+			MPN_COPY(rp, np, nsize);
+
+		rsize = nsize;
+	}
+
+	q_limb = mpihelp_divrem(qp, 0, rp, rsize, dp, dsize);
+
+	if (quot) {
+		qsize = rsize - dsize;
+		if (q_limb) {
+			qp[qsize] = q_limb;
+			qsize += 1;
+		}
+
+		quot->nlimbs = qsize;
+		quot->sign = sign_quotient;
+	}
+
+	rsize = dsize;
+	MPN_NORMALIZE(rp, rsize);
+
+	if (normalization_steps && rsize) {
+		mpihelp_rshift(rp, rp, rsize, normalization_steps);
+		rsize -= rp[rsize - 1] == 0?1:0;
+	}
+
+	rem->nlimbs = rsize;
+	rem->sign	= sign_remainder;
+	while (markidx) {
+		markidx--;
+		mpi_free_limb_space(marker[markidx]);
+	}
+}
diff --git a/lib/mpi/mpi-internal.h b/lib/mpi/mpi-internal.h
index 91df5f0b70f2..d29c4537c3a3 100644
--- a/lib/mpi/mpi-internal.h
+++ b/lib/mpi/mpi-internal.h
@@ -52,6 +52,12 @@
 typedef mpi_limb_t *mpi_ptr_t;	/* pointer to a limb */
 typedef int mpi_size_t;		/* (must be a signed type) */
 
+#define RESIZE_IF_NEEDED(a, b)			\
+	do {					\
+		if ((a)->alloced < (b))		\
+			mpi_resize((a), (b));	\
+	} while (0)
+
 /* Copy N limbs from S to D.  */
 #define MPN_COPY(d, s, n) \
 	do {					\
@@ -60,6 +66,14 @@ typedef int mpi_size_t;		/* (must be a signed type) */
 			(d)[_i] = (s)[_i];	\
 	} while (0)
 
+#define MPN_COPY_INCR(d, s, n)		\
+	do {					\
+		mpi_size_t _i;			\
+		for (_i = 0; _i < (n); _i++)	\
+			(d)[_i] = (s)[_i];	\
+	} while (0)
+
+
 #define MPN_COPY_DECR(d, s, n) \
 	do {					\
 		mpi_size_t _i;			\
@@ -92,6 +106,38 @@ typedef int mpi_size_t;		/* (must be a signed type) */
 			mul_n(prodp, up, vp, size, tspace);	\
 	} while (0);
 
+/* Divide the two-limb number in (NH,,NL) by D, with DI being the largest
+ * limb not larger than (2**(2*BITS_PER_MP_LIMB))/D - (2**BITS_PER_MP_LIMB).
+ * If this would yield overflow, DI should be the largest possible number
+ * (i.e., only ones).  For correct operation, the most significant bit of D
+ * has to be set.  Put the quotient in Q and the remainder in R.
+ */
+#define UDIV_QRNND_PREINV(q, r, nh, nl, d, di)				\
+	do {								\
+		mpi_limb_t _ql;						\
+		mpi_limb_t _q, _r;					\
+		mpi_limb_t _xh, _xl;					\
+		umul_ppmm(_q, _ql, (nh), (di));				\
+		_q += (nh);	/* DI is 2**BITS_PER_MPI_LIMB too small */ \
+		umul_ppmm(_xh, _xl, _q, (d));				\
+		sub_ddmmss(_xh, _r, (nh), (nl), _xh, _xl);		\
+		if (_xh) {						\
+			sub_ddmmss(_xh, _r, _xh, _r, 0, (d));		\
+			_q++;						\
+			if (_xh) {					\
+				sub_ddmmss(_xh, _r, _xh, _r, 0, (d));	\
+				_q++;					\
+			}						\
+		}							\
+		if (_r >= (d)) {					\
+			_r -= (d);					\
+			_q++;						\
+		}							\
+		(r) = _r;						\
+		(q) = _q;						\
+	} while (0)
+
+
 /*-- mpiutil.c --*/
 mpi_ptr_t mpi_alloc_limb_space(unsigned nlimbs);
 void mpi_free_limb_space(mpi_ptr_t a);
@@ -135,6 +181,8 @@ int mpihelp_mul(mpi_ptr_t prodp, mpi_ptr_t up, mpi_size_t usize,
 void mpih_sqr_n_basecase(mpi_ptr_t prodp, mpi_ptr_t up, mpi_size_t size);
 void mpih_sqr_n(mpi_ptr_t prodp, mpi_ptr_t up, mpi_size_t size,
 		mpi_ptr_t tspace);
+void mpihelp_mul_n(mpi_ptr_t prodp,
+		mpi_ptr_t up, mpi_ptr_t vp, mpi_size_t size);
 
 int mpihelp_mul_karatsuba_case(mpi_ptr_t prodp,
 			       mpi_ptr_t up, mpi_size_t usize,
@@ -146,9 +194,14 @@ mpi_limb_t mpihelp_mul_1(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr,
 			 mpi_size_t s1_size, mpi_limb_t s2_limb);
 
 /*-- mpih-div.c --*/
+mpi_limb_t mpihelp_mod_1(mpi_ptr_t dividend_ptr, mpi_size_t dividend_size,
+			 mpi_limb_t divisor_limb);
 mpi_limb_t mpihelp_divrem(mpi_ptr_t qp, mpi_size_t qextra_limbs,
 			  mpi_ptr_t np, mpi_size_t nsize,
 			  mpi_ptr_t dp, mpi_size_t dsize);
+mpi_limb_t mpihelp_divmod_1(mpi_ptr_t quot_ptr,
+			    mpi_ptr_t dividend_ptr, mpi_size_t dividend_size,
+			    mpi_limb_t divisor_limb);
 
 /*-- generic_mpih-[lr]shift.c --*/
 mpi_limb_t mpihelp_lshift(mpi_ptr_t wp, mpi_ptr_t up, mpi_size_t usize,
diff --git a/lib/mpi/mpi-inv.c b/lib/mpi/mpi-inv.c
new file mode 100644
index 000000000000..61e37d18f793
--- /dev/null
+++ b/lib/mpi/mpi-inv.c
@@ -0,0 +1,143 @@
+/* mpi-inv.c  -  MPI functions
+ *	Copyright (C) 1998, 2001, 2002, 2003 Free Software Foundation, Inc.
+ *
+ * This file is part of Libgcrypt.
+ *
+ * Libgcrypt is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as
+ * published by the Free Software Foundation; either version 2.1 of
+ * the License, or (at your option) any later version.
+ *
+ * Libgcrypt is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "mpi-internal.h"
+
+/****************
+ * Calculate the multiplicative inverse X of A mod N
+ * That is: Find the solution x for
+ *		1 = (a*x) mod n
+ */
+int mpi_invm(MPI x, MPI a, MPI n)
+{
+	/* Extended Euclid's algorithm (See TAOCP Vol II, 4.5.2, Alg X)
+	 * modified according to Michael Penk's solution for Exercise 35
+	 * with further enhancement
+	 */
+	MPI u, v, u1, u2 = NULL, u3, v1, v2 = NULL, v3, t1, t2 = NULL, t3;
+	unsigned int k;
+	int sign;
+	int odd;
+
+	if (!mpi_cmp_ui(a, 0))
+		return 0; /* Inverse does not exists.  */
+	if (!mpi_cmp_ui(n, 1))
+		return 0; /* Inverse does not exists.  */
+
+	u = mpi_copy(a);
+	v = mpi_copy(n);
+
+	for (k = 0; !mpi_test_bit(u, 0) && !mpi_test_bit(v, 0); k++) {
+		mpi_rshift(u, u, 1);
+		mpi_rshift(v, v, 1);
+	}
+	odd = mpi_test_bit(v, 0);
+
+	u1 = mpi_alloc_set_ui(1);
+	if (!odd)
+		u2 = mpi_alloc_set_ui(0);
+	u3 = mpi_copy(u);
+	v1 = mpi_copy(v);
+	if (!odd) {
+		v2 = mpi_alloc(mpi_get_nlimbs(u));
+		mpi_sub(v2, u1, u); /* U is used as const 1 */
+	}
+	v3 = mpi_copy(v);
+	if (mpi_test_bit(u, 0)) { /* u is odd */
+		t1 = mpi_alloc_set_ui(0);
+		if (!odd) {
+			t2 = mpi_alloc_set_ui(1);
+			t2->sign = 1;
+		}
+		t3 = mpi_copy(v);
+		t3->sign = !t3->sign;
+		goto Y4;
+	} else {
+		t1 = mpi_alloc_set_ui(1);
+		if (!odd)
+			t2 = mpi_alloc_set_ui(0);
+		t3 = mpi_copy(u);
+	}
+
+	do {
+		do {
+			if (!odd) {
+				if (mpi_test_bit(t1, 0) || mpi_test_bit(t2, 0)) {
+					/* one is odd */
+					mpi_add(t1, t1, v);
+					mpi_sub(t2, t2, u);
+				}
+				mpi_rshift(t1, t1, 1);
+				mpi_rshift(t2, t2, 1);
+				mpi_rshift(t3, t3, 1);
+			} else {
+				if (mpi_test_bit(t1, 0))
+					mpi_add(t1, t1, v);
+				mpi_rshift(t1, t1, 1);
+				mpi_rshift(t3, t3, 1);
+			}
+Y4:
+			;
+		} while (!mpi_test_bit(t3, 0)); /* while t3 is even */
+
+		if (!t3->sign) {
+			mpi_set(u1, t1);
+			if (!odd)
+				mpi_set(u2, t2);
+			mpi_set(u3, t3);
+		} else {
+			mpi_sub(v1, v, t1);
+			sign = u->sign; u->sign = !u->sign;
+			if (!odd)
+				mpi_sub(v2, u, t2);
+			u->sign = sign;
+			sign = t3->sign; t3->sign = !t3->sign;
+			mpi_set(v3, t3);
+			t3->sign = sign;
+		}
+		mpi_sub(t1, u1, v1);
+		if (!odd)
+			mpi_sub(t2, u2, v2);
+		mpi_sub(t3, u3, v3);
+		if (t1->sign) {
+			mpi_add(t1, t1, v);
+			if (!odd)
+				mpi_sub(t2, t2, u);
+		}
+	} while (mpi_cmp_ui(t3, 0)); /* while t3 != 0 */
+	/* mpi_lshift( u3, k ); */
+	mpi_set(x, u1);
+
+	mpi_free(u1);
+	mpi_free(v1);
+	mpi_free(t1);
+	if (!odd) {
+		mpi_free(u2);
+		mpi_free(v2);
+		mpi_free(t2);
+	}
+	mpi_free(u3);
+	mpi_free(v3);
+	mpi_free(t3);
+
+	mpi_free(u);
+	mpi_free(v);
+	return 1;
+}
+EXPORT_SYMBOL_GPL(mpi_invm);
diff --git a/lib/mpi/mpi-mod.c b/lib/mpi/mpi-mod.c
new file mode 100644
index 000000000000..47bc59edd4ff
--- /dev/null
+++ b/lib/mpi/mpi-mod.c
@@ -0,0 +1,155 @@
+/* mpi-mod.c -  Modular reduction
+ * Copyright (C) 1998, 1999, 2001, 2002, 2003,
+ *               2007  Free Software Foundation, Inc.
+ *
+ * This file is part of Libgcrypt.
+ */
+
+
+#include "mpi-internal.h"
+#include "longlong.h"
+
+/* Context used with Barrett reduction.  */
+struct barrett_ctx_s {
+	MPI m;   /* The modulus - may not be modified. */
+	int m_copied;   /* If true, M needs to be released.  */
+	int k;
+	MPI y;
+	MPI r1;  /* Helper MPI. */
+	MPI r2;  /* Helper MPI. */
+	MPI r3;  /* Helper MPI allocated on demand. */
+};
+
+
+
+void mpi_mod(MPI rem, MPI dividend, MPI divisor)
+{
+	mpi_fdiv_r(rem, dividend, divisor);
+}
+
+/* This function returns a new context for Barrett based operations on
+ * the modulus M.  This context needs to be released using
+ * _gcry_mpi_barrett_free.  If COPY is true M will be transferred to
+ * the context and the user may change M.  If COPY is false, M may not
+ * be changed until gcry_mpi_barrett_free has been called.
+ */
+mpi_barrett_t mpi_barrett_init(MPI m, int copy)
+{
+	mpi_barrett_t ctx;
+	MPI tmp;
+
+	mpi_normalize(m);
+	ctx = kcalloc(1, sizeof(*ctx), GFP_KERNEL);
+
+	if (copy) {
+		ctx->m = mpi_copy(m);
+		ctx->m_copied = 1;
+	} else
+		ctx->m = m;
+
+	ctx->k = mpi_get_nlimbs(m);
+	tmp = mpi_alloc(ctx->k + 1);
+
+	/* Barrett precalculation: y = floor(b^(2k) / m). */
+	mpi_set_ui(tmp, 1);
+	mpi_lshift_limbs(tmp, 2 * ctx->k);
+	mpi_fdiv_q(tmp, tmp, m);
+
+	ctx->y  = tmp;
+	ctx->r1 = mpi_alloc(2 * ctx->k + 1);
+	ctx->r2 = mpi_alloc(2 * ctx->k + 1);
+
+	return ctx;
+}
+
+void mpi_barrett_free(mpi_barrett_t ctx)
+{
+	if (ctx) {
+		mpi_free(ctx->y);
+		mpi_free(ctx->r1);
+		mpi_free(ctx->r2);
+		if (ctx->r3)
+			mpi_free(ctx->r3);
+		if (ctx->m_copied)
+			mpi_free(ctx->m);
+		kfree(ctx);
+	}
+}
+
+
+/* R = X mod M
+ *
+ * Using Barrett reduction.  Before using this function
+ * _gcry_mpi_barrett_init must have been called to do the
+ * precalculations.  CTX is the context created by this precalculation
+ * and also conveys M.  If the Barret reduction could no be done a
+ * straightforward reduction method is used.
+ *
+ * We assume that these conditions are met:
+ * Input:  x =(x_2k-1 ...x_0)_b
+ *     m =(m_k-1 ....m_0)_b	  with m_k-1 != 0
+ * Output: r = x mod m
+ */
+void mpi_mod_barrett(MPI r, MPI x, mpi_barrett_t ctx)
+{
+	MPI m = ctx->m;
+	int k = ctx->k;
+	MPI y = ctx->y;
+	MPI r1 = ctx->r1;
+	MPI r2 = ctx->r2;
+	int sign;
+
+	mpi_normalize(x);
+	if (mpi_get_nlimbs(x) > 2*k) {
+		mpi_mod(r, x, m);
+		return;
+	}
+
+	sign = x->sign;
+	x->sign = 0;
+
+	/* 1. q1 = floor( x / b^k-1)
+	 *    q2 = q1 * y
+	 *    q3 = floor( q2 / b^k+1 )
+	 * Actually, we don't need qx, we can work direct on r2
+	 */
+	mpi_set(r2, x);
+	mpi_rshift_limbs(r2, k-1);
+	mpi_mul(r2, r2, y);
+	mpi_rshift_limbs(r2, k+1);
+
+	/* 2. r1 = x mod b^k+1
+	 *	r2 = q3 * m mod b^k+1
+	 *	r  = r1 - r2
+	 * 3. if r < 0 then  r = r + b^k+1
+	 */
+	mpi_set(r1, x);
+	if (r1->nlimbs > k+1) /* Quick modulo operation.  */
+		r1->nlimbs = k+1;
+	mpi_mul(r2, r2, m);
+	if (r2->nlimbs > k+1) /* Quick modulo operation. */
+		r2->nlimbs = k+1;
+	mpi_sub(r, r1, r2);
+
+	if (mpi_has_sign(r)) {
+		if (!ctx->r3) {
+			ctx->r3 = mpi_alloc(k + 2);
+			mpi_set_ui(ctx->r3, 1);
+			mpi_lshift_limbs(ctx->r3, k + 1);
+		}
+		mpi_add(r, r, ctx->r3);
+	}
+
+	/* 4. while r >= m do r = r - m */
+	while (mpi_cmp(r, m) >= 0)
+		mpi_sub(r, r, m);
+
+	x->sign = sign;
+}
+
+
+void mpi_mul_barrett(MPI w, MPI u, MPI v, mpi_barrett_t ctx)
+{
+	mpi_mul(w, u, v);
+	mpi_mod_barrett(w, w, ctx);
+}
diff --git a/lib/mpi/mpi-mul.c b/lib/mpi/mpi-mul.c
new file mode 100644
index 000000000000..587e6335cc12
--- /dev/null
+++ b/lib/mpi/mpi-mul.c
@@ -0,0 +1,94 @@
+/* mpi-mul.c  -  MPI functions
+ * Copyright (C) 1994, 1996, 1998, 2001, 2002,
+ *               2003 Free Software Foundation, Inc.
+ *
+ * This file is part of Libgcrypt.
+ *
+ * Note: This code is heavily based on the GNU MP Library.
+ *	 Actually it's the same code with only minor changes in the
+ *	 way the data is stored; this is to support the abstraction
+ *	 of an optional secure memory allocation which may be used
+ *	 to avoid revealing of sensitive data due to paging etc.
+ */
+
+#include "mpi-internal.h"
+
+void mpi_mul(MPI w, MPI u, MPI v)
+{
+	mpi_size_t usize, vsize, wsize;
+	mpi_ptr_t up, vp, wp;
+	mpi_limb_t cy;
+	int usign, vsign, sign_product;
+	int assign_wp = 0;
+	mpi_ptr_t tmp_limb = NULL;
+	unsigned int tmp_limb_nlimbs = 0;
+
+	if (u->nlimbs < v->nlimbs) {
+		/* Swap U and V. */
+		usize = v->nlimbs;
+		usign = v->sign;
+		up    = v->d;
+		vsize = u->nlimbs;
+		vsign = u->sign;
+		vp    = u->d;
+	} else {
+		usize = u->nlimbs;
+		usign = u->sign;
+		up    = u->d;
+		vsize = v->nlimbs;
+		vsign = v->sign;
+		vp    = v->d;
+	}
+	sign_product = usign ^ vsign;
+	wp = w->d;
+
+	/* Ensure W has space enough to store the result.  */
+	wsize = usize + vsize;
+	if (w->alloced < wsize) {
+		if (wp == up || wp == vp) {
+			wp = mpi_alloc_limb_space(wsize);
+			assign_wp = 1;
+		} else {
+			mpi_resize(w, wsize);
+			wp = w->d;
+		}
+	} else { /* Make U and V not overlap with W.	*/
+		if (wp == up) {
+			/* W and U are identical.  Allocate temporary space for U. */
+			tmp_limb_nlimbs = usize;
+			up = tmp_limb = mpi_alloc_limb_space(usize);
+			/* Is V identical too?  Keep it identical with U.  */
+			if (wp == vp)
+				vp = up;
+			/* Copy to the temporary space.  */
+			MPN_COPY(up, wp, usize);
+		} else if (wp == vp) {
+			/* W and V are identical.  Allocate temporary space for V. */
+			tmp_limb_nlimbs = vsize;
+			vp = tmp_limb = mpi_alloc_limb_space(vsize);
+			/* Copy to the temporary space.  */
+			MPN_COPY(vp, wp, vsize);
+		}
+	}
+
+	if (!vsize)
+		wsize = 0;
+	else {
+		mpihelp_mul(wp, up, usize, vp, vsize, &cy);
+		wsize -= cy ? 0:1;
+	}
+
+	if (assign_wp)
+		mpi_assign_limb_space(w, wp, wsize);
+	w->nlimbs = wsize;
+	w->sign = sign_product;
+	if (tmp_limb)
+		mpi_free_limb_space(tmp_limb);
+}
+
+void mpi_mulm(MPI w, MPI u, MPI v, MPI m)
+{
+	mpi_mul(w, u, v);
+	mpi_tdiv_r(w, w, m);
+}
+EXPORT_SYMBOL_GPL(mpi_mulm);
diff --git a/lib/mpi/mpicoder.c b/lib/mpi/mpicoder.c
index eead4b339466..7ea225b2204f 100644
--- a/lib/mpi/mpicoder.c
+++ b/lib/mpi/mpicoder.c
@@ -25,6 +25,7 @@
 #include <linux/string.h>
 #include "mpi-internal.h"
 
+#define MAX_EXTERN_SCAN_BYTES (16*1024*1024)
 #define MAX_EXTERN_MPI_BITS 16384
 
 /**
@@ -109,6 +110,112 @@ MPI mpi_read_from_buffer(const void *xbuffer, unsigned *ret_nread)
 }
 EXPORT_SYMBOL_GPL(mpi_read_from_buffer);
 
+/****************
+ * Fill the mpi VAL from the hex string in STR.
+ */
+int mpi_fromstr(MPI val, const char *str)
+{
+	int sign = 0;
+	int prepend_zero = 0;
+	int i, j, c, c1, c2;
+	unsigned int nbits, nbytes, nlimbs;
+	mpi_limb_t a;
+
+	if (*str == '-') {
+		sign = 1;
+		str++;
+	}
+
+	/* Skip optional hex prefix.  */
+	if (*str == '0' && str[1] == 'x')
+		str += 2;
+
+	nbits = strlen(str);
+	if (nbits > MAX_EXTERN_SCAN_BYTES) {
+		mpi_clear(val);
+		return -EINVAL;
+	}
+	nbits *= 4;
+	if ((nbits % 8))
+		prepend_zero = 1;
+
+	nbytes = (nbits+7) / 8;
+	nlimbs = (nbytes+BYTES_PER_MPI_LIMB-1) / BYTES_PER_MPI_LIMB;
+
+	if (val->alloced < nlimbs)
+		mpi_resize(val, nlimbs);
+
+	i = BYTES_PER_MPI_LIMB - (nbytes % BYTES_PER_MPI_LIMB);
+	i %= BYTES_PER_MPI_LIMB;
+	j = val->nlimbs = nlimbs;
+	val->sign = sign;
+	for (; j > 0; j--) {
+		a = 0;
+		for (; i < BYTES_PER_MPI_LIMB; i++) {
+			if (prepend_zero) {
+				c1 = '0';
+				prepend_zero = 0;
+			} else
+				c1 = *str++;
+
+			if (!c1) {
+				mpi_clear(val);
+				return -EINVAL;
+			}
+			c2 = *str++;
+			if (!c2) {
+				mpi_clear(val);
+				return -EINVAL;
+			}
+			if (c1 >= '0' && c1 <= '9')
+				c = c1 - '0';
+			else if (c1 >= 'a' && c1 <= 'f')
+				c = c1 - 'a' + 10;
+			else if (c1 >= 'A' && c1 <= 'F')
+				c = c1 - 'A' + 10;
+			else {
+				mpi_clear(val);
+				return -EINVAL;
+			}
+			c <<= 4;
+			if (c2 >= '0' && c2 <= '9')
+				c |= c2 - '0';
+			else if (c2 >= 'a' && c2 <= 'f')
+				c |= c2 - 'a' + 10;
+			else if (c2 >= 'A' && c2 <= 'F')
+				c |= c2 - 'A' + 10;
+			else {
+				mpi_clear(val);
+				return -EINVAL;
+			}
+			a <<= 8;
+			a |= c;
+		}
+		i = 0;
+		val->d[j-1] = a;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mpi_fromstr);
+
+MPI mpi_scanval(const char *string)
+{
+	MPI a;
+
+	a = mpi_alloc(0);
+	if (!a)
+		return NULL;
+
+	if (mpi_fromstr(a, string)) {
+		mpi_free(a);
+		return NULL;
+	}
+	mpi_normalize(a);
+	return a;
+}
+EXPORT_SYMBOL_GPL(mpi_scanval);
+
 static int count_lzeros(MPI a)
 {
 	mpi_limb_t alimb;
@@ -413,3 +520,232 @@ MPI mpi_read_raw_from_sgl(struct scatterlist *sgl, unsigned int nbytes)
 	return val;
 }
 EXPORT_SYMBOL_GPL(mpi_read_raw_from_sgl);
+
+/* Perform a two's complement operation on buffer P of size N bytes.  */
+static void twocompl(unsigned char *p, unsigned int n)
+{
+	int i;
+
+	for (i = n-1; i >= 0 && !p[i]; i--)
+		;
+	if (i >= 0) {
+		if ((p[i] & 0x01))
+			p[i] = (((p[i] ^ 0xfe) | 0x01) & 0xff);
+		else if ((p[i] & 0x02))
+			p[i] = (((p[i] ^ 0xfc) | 0x02) & 0xfe);
+		else if ((p[i] & 0x04))
+			p[i] = (((p[i] ^ 0xf8) | 0x04) & 0xfc);
+		else if ((p[i] & 0x08))
+			p[i] = (((p[i] ^ 0xf0) | 0x08) & 0xf8);
+		else if ((p[i] & 0x10))
+			p[i] = (((p[i] ^ 0xe0) | 0x10) & 0xf0);
+		else if ((p[i] & 0x20))
+			p[i] = (((p[i] ^ 0xc0) | 0x20) & 0xe0);
+		else if ((p[i] & 0x40))
+			p[i] = (((p[i] ^ 0x80) | 0x40) & 0xc0);
+		else
+			p[i] = 0x80;
+
+		for (i--; i >= 0; i--)
+			p[i] ^= 0xff;
+	}
+}
+
+int mpi_print(enum gcry_mpi_format format, unsigned char *buffer,
+			size_t buflen, size_t *nwritten, MPI a)
+{
+	unsigned int nbits = mpi_get_nbits(a);
+	size_t len;
+	size_t dummy_nwritten;
+	int negative;
+
+	if (!nwritten)
+		nwritten = &dummy_nwritten;
+
+	/* Libgcrypt does no always care to set clear the sign if the value
+	 * is 0.  For printing this is a bit of a surprise, in particular
+	 * because if some of the formats don't support negative numbers but
+	 * should be able to print a zero.  Thus we need this extra test
+	 * for a negative number.
+	 */
+	if (a->sign && mpi_cmp_ui(a, 0))
+		negative = 1;
+	else
+		negative = 0;
+
+	len = buflen;
+	*nwritten = 0;
+	if (format == GCRYMPI_FMT_STD) {
+		unsigned char *tmp;
+		int extra = 0;
+		unsigned int n;
+
+		tmp = mpi_get_buffer(a, &n, NULL);
+		if (!tmp)
+			return -EINVAL;
+
+		if (negative) {
+			twocompl(tmp, n);
+			if (!(*tmp & 0x80)) {
+				/* Need to extend the sign.  */
+				n++;
+				extra = 2;
+			}
+		} else if (n && (*tmp & 0x80)) {
+			/* Positive but the high bit of the returned buffer is set.
+			 * Thus we need to print an extra leading 0x00 so that the
+			 * output is interpreted as a positive number.
+			 */
+			n++;
+			extra = 1;
+		}
+
+		if (buffer && n > len) {
+			/* The provided buffer is too short. */
+			kfree(tmp);
+			return -E2BIG;
+		}
+		if (buffer) {
+			unsigned char *s = buffer;
+
+			if (extra == 1)
+				*s++ = 0;
+			else if (extra)
+				*s++ = 0xff;
+			memcpy(s, tmp, n-!!extra);
+		}
+		kfree(tmp);
+		*nwritten = n;
+		return 0;
+	} else if (format == GCRYMPI_FMT_USG) {
+		unsigned int n = (nbits + 7)/8;
+
+		/* Note:  We ignore the sign for this format.  */
+		/* FIXME: for performance reasons we should put this into
+		 * mpi_aprint because we can then use the buffer directly.
+		 */
+
+		if (buffer && n > len)
+			return -E2BIG;
+		if (buffer) {
+			unsigned char *tmp;
+
+			tmp = mpi_get_buffer(a, &n, NULL);
+			if (!tmp)
+				return -EINVAL;
+			memcpy(buffer, tmp, n);
+			kfree(tmp);
+		}
+		*nwritten = n;
+		return 0;
+	} else if (format == GCRYMPI_FMT_PGP) {
+		unsigned int n = (nbits + 7)/8;
+
+		/* The PGP format can only handle unsigned integers.  */
+		if (negative)
+			return -EINVAL;
+
+		if (buffer && n+2 > len)
+			return -E2BIG;
+
+		if (buffer) {
+			unsigned char *tmp;
+			unsigned char *s = buffer;
+
+			s[0] = nbits >> 8;
+			s[1] = nbits;
+
+			tmp = mpi_get_buffer(a, &n, NULL);
+			if (!tmp)
+				return -EINVAL;
+			memcpy(s+2, tmp, n);
+			kfree(tmp);
+		}
+		*nwritten = n+2;
+		return 0;
+	} else if (format == GCRYMPI_FMT_SSH) {
+		unsigned char *tmp;
+		int extra = 0;
+		unsigned int n;
+
+		tmp = mpi_get_buffer(a, &n, NULL);
+		if (!tmp)
+			return -EINVAL;
+
+		if (negative) {
+			twocompl(tmp, n);
+			if (!(*tmp & 0x80)) {
+				/* Need to extend the sign.  */
+				n++;
+				extra = 2;
+			}
+		} else if (n && (*tmp & 0x80)) {
+			n++;
+			extra = 1;
+		}
+
+		if (buffer && n+4 > len) {
+			kfree(tmp);
+			return -E2BIG;
+		}
+
+		if (buffer) {
+			unsigned char *s = buffer;
+
+			*s++ = n >> 24;
+			*s++ = n >> 16;
+			*s++ = n >> 8;
+			*s++ = n;
+			if (extra == 1)
+				*s++ = 0;
+			else if (extra)
+				*s++ = 0xff;
+			memcpy(s, tmp, n-!!extra);
+		}
+		kfree(tmp);
+		*nwritten = 4+n;
+		return 0;
+	} else if (format == GCRYMPI_FMT_HEX) {
+		unsigned char *tmp;
+		int i;
+		int extra = 0;
+		unsigned int n = 0;
+
+		tmp = mpi_get_buffer(a, &n, NULL);
+		if (!tmp)
+			return -EINVAL;
+		if (!n || (*tmp & 0x80))
+			extra = 2;
+
+		if (buffer && 2*n + extra + negative + 1 > len) {
+			kfree(tmp);
+			return -E2BIG;
+		}
+		if (buffer) {
+			unsigned char *s = buffer;
+
+			if (negative)
+				*s++ = '-';
+			if (extra) {
+				*s++ = '0';
+				*s++ = '0';
+			}
+
+			for (i = 0; i < n; i++) {
+				unsigned int c = tmp[i];
+
+				*s++ = (c >> 4) < 10 ? '0'+(c>>4) : 'A'+(c>>4)-10;
+				c &= 15;
+				*s++ = c < 10 ? '0'+c : 'A'+c-10;
+			}
+			*s++ = 0;
+			*nwritten = s - buffer;
+		} else {
+			*nwritten = 2*n + extra + negative + 1;
+		}
+		kfree(tmp);
+		return 0;
+	} else
+		return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(mpi_print);
diff --git a/lib/mpi/mpih-div.c b/lib/mpi/mpih-div.c
index 913a519eb005..182a656a1ba0 100644
--- a/lib/mpi/mpih-div.c
+++ b/lib/mpi/mpih-div.c
@@ -24,6 +24,150 @@
 #define UDIV_TIME UMUL_TIME
 #endif
 
+
+mpi_limb_t
+mpihelp_mod_1(mpi_ptr_t dividend_ptr, mpi_size_t dividend_size,
+			mpi_limb_t divisor_limb)
+{
+	mpi_size_t i;
+	mpi_limb_t n1, n0, r;
+	mpi_limb_t dummy;
+
+	/* Botch: Should this be handled at all?  Rely on callers?	*/
+	if (!dividend_size)
+		return 0;
+
+	/* If multiplication is much faster than division, and the
+	 * dividend is large, pre-invert the divisor, and use
+	 * only multiplications in the inner loop.
+	 *
+	 * This test should be read:
+	 *	 Does it ever help to use udiv_qrnnd_preinv?
+	 *	   && Does what we save compensate for the inversion overhead?
+	 */
+	if (UDIV_TIME > (2 * UMUL_TIME + 6)
+			&& (UDIV_TIME - (2 * UMUL_TIME + 6)) * dividend_size > UDIV_TIME) {
+		int normalization_steps;
+
+		normalization_steps = count_leading_zeros(divisor_limb);
+		if (normalization_steps) {
+			mpi_limb_t divisor_limb_inverted;
+
+			divisor_limb <<= normalization_steps;
+
+			/* Compute (2**2N - 2**N * DIVISOR_LIMB) / DIVISOR_LIMB.  The
+			 * result is a (N+1)-bit approximation to 1/DIVISOR_LIMB, with the
+			 * most significant bit (with weight 2**N) implicit.
+			 *
+			 * Special case for DIVISOR_LIMB == 100...000.
+			 */
+			if (!(divisor_limb << 1))
+				divisor_limb_inverted = ~(mpi_limb_t)0;
+			else
+				udiv_qrnnd(divisor_limb_inverted, dummy,
+						-divisor_limb, 0, divisor_limb);
+
+			n1 = dividend_ptr[dividend_size - 1];
+			r = n1 >> (BITS_PER_MPI_LIMB - normalization_steps);
+
+			/* Possible optimization:
+			 * if (r == 0
+			 * && divisor_limb > ((n1 << normalization_steps)
+			 *		       | (dividend_ptr[dividend_size - 2] >> ...)))
+			 * ...one division less...
+			 */
+			for (i = dividend_size - 2; i >= 0; i--) {
+				n0 = dividend_ptr[i];
+				UDIV_QRNND_PREINV(dummy, r, r,
+						((n1 << normalization_steps)
+						 | (n0 >> (BITS_PER_MPI_LIMB - normalization_steps))),
+						divisor_limb, divisor_limb_inverted);
+				n1 = n0;
+			}
+			UDIV_QRNND_PREINV(dummy, r, r,
+					n1 << normalization_steps,
+					divisor_limb, divisor_limb_inverted);
+			return r >> normalization_steps;
+		} else {
+			mpi_limb_t divisor_limb_inverted;
+
+			/* Compute (2**2N - 2**N * DIVISOR_LIMB) / DIVISOR_LIMB.  The
+			 * result is a (N+1)-bit approximation to 1/DIVISOR_LIMB, with the
+			 * most significant bit (with weight 2**N) implicit.
+			 *
+			 * Special case for DIVISOR_LIMB == 100...000.
+			 */
+			if (!(divisor_limb << 1))
+				divisor_limb_inverted = ~(mpi_limb_t)0;
+			else
+				udiv_qrnnd(divisor_limb_inverted, dummy,
+						-divisor_limb, 0, divisor_limb);
+
+			i = dividend_size - 1;
+			r = dividend_ptr[i];
+
+			if (r >= divisor_limb)
+				r = 0;
+			else
+				i--;
+
+			for ( ; i >= 0; i--) {
+				n0 = dividend_ptr[i];
+				UDIV_QRNND_PREINV(dummy, r, r,
+						n0, divisor_limb, divisor_limb_inverted);
+			}
+			return r;
+		}
+	} else {
+		if (UDIV_NEEDS_NORMALIZATION) {
+			int normalization_steps;
+
+			normalization_steps = count_leading_zeros(divisor_limb);
+			if (normalization_steps) {
+				divisor_limb <<= normalization_steps;
+
+				n1 = dividend_ptr[dividend_size - 1];
+				r = n1 >> (BITS_PER_MPI_LIMB - normalization_steps);
+
+				/* Possible optimization:
+				 * if (r == 0
+				 * && divisor_limb > ((n1 << normalization_steps)
+				 *		   | (dividend_ptr[dividend_size - 2] >> ...)))
+				 * ...one division less...
+				 */
+				for (i = dividend_size - 2; i >= 0; i--) {
+					n0 = dividend_ptr[i];
+					udiv_qrnnd(dummy, r, r,
+						((n1 << normalization_steps)
+						 | (n0 >> (BITS_PER_MPI_LIMB - normalization_steps))),
+						divisor_limb);
+					n1 = n0;
+				}
+				udiv_qrnnd(dummy, r, r,
+						n1 << normalization_steps,
+						divisor_limb);
+				return r >> normalization_steps;
+			}
+		}
+		/* No normalization needed, either because udiv_qrnnd doesn't require
+		 * it, or because DIVISOR_LIMB is already normalized.
+		 */
+		i = dividend_size - 1;
+		r = dividend_ptr[i];
+
+		if (r >= divisor_limb)
+			r = 0;
+		else
+			i--;
+
+		for (; i >= 0; i--) {
+			n0 = dividend_ptr[i];
+			udiv_qrnnd(dummy, r, r, n0, divisor_limb);
+		}
+		return r;
+	}
+}
+
 /* Divide num (NP/NSIZE) by den (DP/DSIZE) and write
  * the NSIZE-DSIZE least significant quotient limbs at QP
  * and the DSIZE long remainder at NP.	If QEXTRA_LIMBS is
@@ -221,3 +365,153 @@ q_test:
 
 	return most_significant_q_limb;
 }
+
+/****************
+ * Divide (DIVIDEND_PTR,,DIVIDEND_SIZE) by DIVISOR_LIMB.
+ * Write DIVIDEND_SIZE limbs of quotient at QUOT_PTR.
+ * Return the single-limb remainder.
+ * There are no constraints on the value of the divisor.
+ *
+ * QUOT_PTR and DIVIDEND_PTR might point to the same limb.
+ */
+
+mpi_limb_t
+mpihelp_divmod_1(mpi_ptr_t quot_ptr,
+		mpi_ptr_t dividend_ptr, mpi_size_t dividend_size,
+		mpi_limb_t divisor_limb)
+{
+	mpi_size_t i;
+	mpi_limb_t n1, n0, r;
+	mpi_limb_t dummy;
+
+	if (!dividend_size)
+		return 0;
+
+	/* If multiplication is much faster than division, and the
+	 * dividend is large, pre-invert the divisor, and use
+	 * only multiplications in the inner loop.
+	 *
+	 * This test should be read:
+	 * Does it ever help to use udiv_qrnnd_preinv?
+	 * && Does what we save compensate for the inversion overhead?
+	 */
+	if (UDIV_TIME > (2 * UMUL_TIME + 6)
+			&& (UDIV_TIME - (2 * UMUL_TIME + 6)) * dividend_size > UDIV_TIME) {
+		int normalization_steps;
+
+		normalization_steps = count_leading_zeros(divisor_limb);
+		if (normalization_steps) {
+			mpi_limb_t divisor_limb_inverted;
+
+			divisor_limb <<= normalization_steps;
+
+			/* Compute (2**2N - 2**N * DIVISOR_LIMB) / DIVISOR_LIMB.  The
+			 * result is a (N+1)-bit approximation to 1/DIVISOR_LIMB, with the
+			 * most significant bit (with weight 2**N) implicit.
+			 */
+			/* Special case for DIVISOR_LIMB == 100...000.  */
+			if (!(divisor_limb << 1))
+				divisor_limb_inverted = ~(mpi_limb_t)0;
+			else
+				udiv_qrnnd(divisor_limb_inverted, dummy,
+						-divisor_limb, 0, divisor_limb);
+
+			n1 = dividend_ptr[dividend_size - 1];
+			r = n1 >> (BITS_PER_MPI_LIMB - normalization_steps);
+
+			/* Possible optimization:
+			 * if (r == 0
+			 * && divisor_limb > ((n1 << normalization_steps)
+			 *		       | (dividend_ptr[dividend_size - 2] >> ...)))
+			 * ...one division less...
+			 */
+			for (i = dividend_size - 2; i >= 0; i--) {
+				n0 = dividend_ptr[i];
+				UDIV_QRNND_PREINV(quot_ptr[i + 1], r, r,
+						((n1 << normalization_steps)
+						 | (n0 >> (BITS_PER_MPI_LIMB - normalization_steps))),
+						divisor_limb, divisor_limb_inverted);
+				n1 = n0;
+			}
+			UDIV_QRNND_PREINV(quot_ptr[0], r, r,
+					n1 << normalization_steps,
+					divisor_limb, divisor_limb_inverted);
+			return r >> normalization_steps;
+		} else {
+			mpi_limb_t divisor_limb_inverted;
+
+			/* Compute (2**2N - 2**N * DIVISOR_LIMB) / DIVISOR_LIMB.  The
+			 * result is a (N+1)-bit approximation to 1/DIVISOR_LIMB, with the
+			 * most significant bit (with weight 2**N) implicit.
+			 */
+			/* Special case for DIVISOR_LIMB == 100...000.  */
+			if (!(divisor_limb << 1))
+				divisor_limb_inverted = ~(mpi_limb_t) 0;
+			else
+				udiv_qrnnd(divisor_limb_inverted, dummy,
+						-divisor_limb, 0, divisor_limb);
+
+			i = dividend_size - 1;
+			r = dividend_ptr[i];
+
+			if (r >= divisor_limb)
+				r = 0;
+			else
+				quot_ptr[i--] = 0;
+
+			for ( ; i >= 0; i--) {
+				n0 = dividend_ptr[i];
+				UDIV_QRNND_PREINV(quot_ptr[i], r, r,
+						n0, divisor_limb, divisor_limb_inverted);
+			}
+			return r;
+		}
+	} else {
+		if (UDIV_NEEDS_NORMALIZATION) {
+			int normalization_steps;
+
+			normalization_steps = count_leading_zeros(divisor_limb);
+			if (normalization_steps) {
+				divisor_limb <<= normalization_steps;
+
+				n1 = dividend_ptr[dividend_size - 1];
+				r = n1 >> (BITS_PER_MPI_LIMB - normalization_steps);
+
+				/* Possible optimization:
+				 * if (r == 0
+				 * && divisor_limb > ((n1 << normalization_steps)
+				 *		   | (dividend_ptr[dividend_size - 2] >> ...)))
+				 * ...one division less...
+				 */
+				for (i = dividend_size - 2; i >= 0; i--) {
+					n0 = dividend_ptr[i];
+					udiv_qrnnd(quot_ptr[i + 1], r, r,
+						((n1 << normalization_steps)
+						 | (n0 >> (BITS_PER_MPI_LIMB - normalization_steps))),
+						divisor_limb);
+					n1 = n0;
+				}
+				udiv_qrnnd(quot_ptr[0], r, r,
+						n1 << normalization_steps,
+						divisor_limb);
+				return r >> normalization_steps;
+			}
+		}
+		/* No normalization needed, either because udiv_qrnnd doesn't require
+		 * it, or because DIVISOR_LIMB is already normalized.
+		 */
+		i = dividend_size - 1;
+		r = dividend_ptr[i];
+
+		if (r >= divisor_limb)
+			r = 0;
+		else
+			quot_ptr[i--] = 0;
+
+		for (; i >= 0; i--) {
+			n0 = dividend_ptr[i];
+			udiv_qrnnd(quot_ptr[i], r, r, n0, divisor_limb);
+		}
+		return r;
+	}
+}
diff --git a/lib/mpi/mpih-mul.c b/lib/mpi/mpih-mul.c
index a93647564054..e5f1c84e3c48 100644
--- a/lib/mpi/mpih-mul.c
+++ b/lib/mpi/mpih-mul.c
@@ -317,6 +317,31 @@ mpih_sqr_n(mpi_ptr_t prodp, mpi_ptr_t up, mpi_size_t size, mpi_ptr_t tspace)
 	}
 }
 
+
+void mpihelp_mul_n(mpi_ptr_t prodp,
+		mpi_ptr_t up, mpi_ptr_t vp, mpi_size_t size)
+{
+	if (up == vp) {
+		if (size < KARATSUBA_THRESHOLD)
+			mpih_sqr_n_basecase(prodp, up, size);
+		else {
+			mpi_ptr_t tspace;
+			tspace = mpi_alloc_limb_space(2 * size);
+			mpih_sqr_n(prodp, up, size, tspace);
+			mpi_free_limb_space(tspace);
+		}
+	} else {
+		if (size < KARATSUBA_THRESHOLD)
+			mul_n_basecase(prodp, up, vp, size);
+		else {
+			mpi_ptr_t tspace;
+			tspace = mpi_alloc_limb_space(2 * size);
+			mul_n(prodp, up, vp, size, tspace);
+			mpi_free_limb_space(tspace);
+		}
+	}
+}
+
 int
 mpihelp_mul_karatsuba_case(mpi_ptr_t prodp,
 			   mpi_ptr_t up, mpi_size_t usize,
diff --git a/lib/mpi/mpiutil.c b/lib/mpi/mpiutil.c
index 4cd2b335cb7f..3c63710c20c6 100644
--- a/lib/mpi/mpiutil.c
+++ b/lib/mpi/mpiutil.c
@@ -20,6 +20,63 @@
 
 #include "mpi-internal.h"
 
+/* Constants allocated right away at startup.  */
+static MPI constants[MPI_NUMBER_OF_CONSTANTS];
+
+/* Initialize the MPI subsystem.  This is called early and allows to
+ * do some initialization without taking care of threading issues.
+ */
+static int __init mpi_init(void)
+{
+	int idx;
+	unsigned long value;
+
+	for (idx = 0; idx < MPI_NUMBER_OF_CONSTANTS; idx++) {
+		switch (idx) {
+		case MPI_C_ZERO:
+			value = 0;
+			break;
+		case MPI_C_ONE:
+			value = 1;
+			break;
+		case MPI_C_TWO:
+			value = 2;
+			break;
+		case MPI_C_THREE:
+			value = 3;
+			break;
+		case MPI_C_FOUR:
+			value = 4;
+			break;
+		case MPI_C_EIGHT:
+			value = 8;
+			break;
+		default:
+			pr_err("MPI: invalid mpi_const selector %d\n", idx);
+			return -EFAULT;
+		}
+		constants[idx] = mpi_alloc_set_ui(value);
+		constants[idx]->flags = (16|32);
+	}
+
+	return 0;
+}
+postcore_initcall(mpi_init);
+
+/* Return a constant MPI descripbed by NO which is one of the
+ * MPI_C_xxx macros.  There is no need to copy this returned value; it
+ * may be used directly.
+ */
+MPI mpi_const(enum gcry_mpi_constants no)
+{
+	if ((int)no < 0 || no > MPI_NUMBER_OF_CONSTANTS)
+		pr_err("MPI: invalid mpi_const selector %d\n", no);
+	if (!constants[no])
+		pr_err("MPI: MPI subsystem not initialized\n");
+	return constants[no];
+}
+EXPORT_SYMBOL_GPL(mpi_const);
+
 /****************
  * Note:  It was a bad idea to use the number of limbs to allocate
  *	  because on a alpha the limbs are large but we normally need
@@ -106,6 +163,15 @@ int mpi_resize(MPI a, unsigned nlimbs)
 	return 0;
 }
 
+void mpi_clear(MPI a)
+{
+	if (!a)
+		return;
+	a->nlimbs = 0;
+	a->flags = 0;
+}
+EXPORT_SYMBOL_GPL(mpi_clear);
+
 void mpi_free(MPI a)
 {
 	if (!a)
@@ -122,5 +188,143 @@ void mpi_free(MPI a)
 }
 EXPORT_SYMBOL_GPL(mpi_free);
 
+/****************
+ * Note: This copy function should not interpret the MPI
+ *	 but copy it transparently.
+ */
+MPI mpi_copy(MPI a)
+{
+	int i;
+	MPI b;
+
+	if (a) {
+		b = mpi_alloc(a->nlimbs);
+		b->nlimbs = a->nlimbs;
+		b->sign = a->sign;
+		b->flags = a->flags;
+		b->flags &= ~(16|32); /* Reset the immutable and constant flags. */
+		for (i = 0; i < b->nlimbs; i++)
+			b->d[i] = a->d[i];
+	} else
+		b = NULL;
+	return b;
+}
+
+/****************
+ * This function allocates an MPI which is optimized to hold
+ * a value as large as the one given in the argument and allocates it
+ * with the same flags as A.
+ */
+MPI mpi_alloc_like(MPI a)
+{
+	MPI b;
+
+	if (a) {
+		b = mpi_alloc(a->nlimbs);
+		b->nlimbs = 0;
+		b->sign = 0;
+		b->flags = a->flags;
+	} else
+		b = NULL;
+
+	return b;
+}
+
+
+/* Set U into W and release U.  If W is NULL only U will be released. */
+void mpi_snatch(MPI w, MPI u)
+{
+	if (w) {
+		mpi_assign_limb_space(w, u->d, u->alloced);
+		w->nlimbs = u->nlimbs;
+		w->sign   = u->sign;
+		w->flags  = u->flags;
+		u->alloced = 0;
+		u->nlimbs = 0;
+		u->d = NULL;
+	}
+	mpi_free(u);
+}
+
+
+MPI mpi_set(MPI w, MPI u)
+{
+	mpi_ptr_t wp, up;
+	mpi_size_t usize = u->nlimbs;
+	int usign = u->sign;
+
+	if (!w)
+		w = mpi_alloc(mpi_get_nlimbs(u));
+	RESIZE_IF_NEEDED(w, usize);
+	wp = w->d;
+	up = u->d;
+	MPN_COPY(wp, up, usize);
+	w->nlimbs = usize;
+	w->flags = u->flags;
+	w->flags &= ~(16|32); /* Reset the immutable and constant flags.  */
+	w->sign = usign;
+	return w;
+}
+EXPORT_SYMBOL_GPL(mpi_set);
+
+MPI mpi_set_ui(MPI w, unsigned long u)
+{
+	if (!w)
+		w = mpi_alloc(1);
+	/* FIXME: If U is 0 we have no need to resize and thus possible
+	 * allocating the the limbs.
+	 */
+	RESIZE_IF_NEEDED(w, 1);
+	w->d[0] = u;
+	w->nlimbs = u ? 1 : 0;
+	w->sign = 0;
+	w->flags = 0;
+	return w;
+}
+EXPORT_SYMBOL_GPL(mpi_set_ui);
+
+MPI mpi_alloc_set_ui(unsigned long u)
+{
+	MPI w = mpi_alloc(1);
+	w->d[0] = u;
+	w->nlimbs = u ? 1 : 0;
+	w->sign = 0;
+	return w;
+}
+
+/****************
+ * Swap the value of A and B, when SWAP is 1.
+ * Leave the value when SWAP is 0.
+ * This implementation should be constant-time regardless of SWAP.
+ */
+void mpi_swap_cond(MPI a, MPI b, unsigned long swap)
+{
+	mpi_size_t i;
+	mpi_size_t nlimbs;
+	mpi_limb_t mask = ((mpi_limb_t)0) - swap;
+	mpi_limb_t x;
+
+	if (a->alloced > b->alloced)
+		nlimbs = b->alloced;
+	else
+		nlimbs = a->alloced;
+	if (a->nlimbs > nlimbs || b->nlimbs > nlimbs)
+		return;
+
+	for (i = 0; i < nlimbs; i++) {
+		x = mask & (a->d[i] ^ b->d[i]);
+		a->d[i] = a->d[i] ^ x;
+		b->d[i] = b->d[i] ^ x;
+	}
+
+	x = mask & (a->nlimbs ^ b->nlimbs);
+	a->nlimbs = a->nlimbs ^ x;
+	b->nlimbs = b->nlimbs ^ x;
+
+	x = mask & (a->sign ^ b->sign);
+	a->sign = a->sign ^ x;
+	b->sign = b->sign ^ x;
+}
+
 MODULE_DESCRIPTION("Multiprecision maths library");
 MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From d58bb7e55a8a65894cc02f27c3e2bf9403e7c40f Mon Sep 17 00:00:00 2001
From: Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
Date: Mon, 21 Sep 2020 00:20:56 +0800
Subject: lib/mpi: Introduce ec implementation to MPI library

The implementation of EC is introduced from libgcrypt as the
basic algorithm of elliptic curve, which can be more perfectly
integrated with MPI implementation.
Some other algorithms will be developed based on mpi ecc, such as SM2.

Signed-off-by: Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
Tested-by: Xufeng Zhang <yunbo.xufeng@linux.alibaba.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/linux/mpi.h |  105 ++++
 lib/mpi/Makefile    |    1 +
 lib/mpi/ec.c        | 1509 +++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 1615 insertions(+)
 create mode 100644 lib/mpi/ec.c

(limited to 'include/linux')

diff --git a/include/linux/mpi.h b/include/linux/mpi.h
index 3c9e41603cf6..3e5358f4de2f 100644
--- a/include/linux/mpi.h
+++ b/include/linux/mpi.h
@@ -157,6 +157,111 @@ void mpi_fdiv_q(MPI quot, MPI dividend, MPI divisor);
 /*-- mpi-inv.c --*/
 int mpi_invm(MPI x, MPI a, MPI n);
 
+/*-- ec.c --*/
+
+/* Object to represent a point in projective coordinates */
+struct gcry_mpi_point {
+	MPI x;
+	MPI y;
+	MPI z;
+};
+
+typedef struct gcry_mpi_point *MPI_POINT;
+
+/* Models describing an elliptic curve */
+enum gcry_mpi_ec_models {
+	/* The Short Weierstrass equation is
+	 *      y^2 = x^3 + ax + b
+	 */
+	MPI_EC_WEIERSTRASS = 0,
+	/* The Montgomery equation is
+	 *      by^2 = x^3 + ax^2 + x
+	 */
+	MPI_EC_MONTGOMERY,
+	/* The Twisted Edwards equation is
+	 *      ax^2 + y^2 = 1 + bx^2y^2
+	 * Note that we use 'b' instead of the commonly used 'd'.
+	 */
+	MPI_EC_EDWARDS
+};
+
+/* Dialects used with elliptic curves */
+enum ecc_dialects {
+	ECC_DIALECT_STANDARD = 0,
+	ECC_DIALECT_ED25519,
+	ECC_DIALECT_SAFECURVE
+};
+
+/* This context is used with all our EC functions. */
+struct mpi_ec_ctx {
+	enum gcry_mpi_ec_models model; /* The model describing this curve. */
+	enum ecc_dialects dialect;     /* The ECC dialect used with the curve. */
+	int flags;                     /* Public key flags (not always used). */
+	unsigned int nbits;            /* Number of bits.  */
+
+	/* Domain parameters.  Note that they may not all be set and if set
+	 * the MPIs may be flaged as constant.
+	 */
+	MPI p;         /* Prime specifying the field GF(p).  */
+	MPI a;         /* First coefficient of the Weierstrass equation.  */
+	MPI b;         /* Second coefficient of the Weierstrass equation.  */
+	MPI_POINT G;   /* Base point (generator).  */
+	MPI n;         /* Order of G.  */
+	unsigned int h;       /* Cofactor.  */
+
+	/* The actual key.  May not be set.  */
+	MPI_POINT Q;   /* Public key.   */
+	MPI d;         /* Private key.  */
+
+	const char *name;      /* Name of the curve.  */
+
+	/* This structure is private to mpi/ec.c! */
+	struct {
+		struct {
+			unsigned int a_is_pminus3:1;
+			unsigned int two_inv_p:1;
+		} valid; /* Flags to help setting the helper vars below.  */
+
+		int a_is_pminus3;  /* True if A = P - 3. */
+
+		MPI two_inv_p;
+
+		mpi_barrett_t p_barrett;
+
+		/* Scratch variables.  */
+		MPI scratch[11];
+
+		/* Helper for fast reduction.  */
+		/*   int nist_nbits; /\* If this is a NIST curve, the # of bits. *\/ */
+		/*   MPI s[10]; */
+		/*   MPI c; */
+	} t;
+
+	/* Curve specific computation routines for the field.  */
+	void (*addm)(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx);
+	void (*subm)(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ec);
+	void (*mulm)(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx);
+	void (*pow2)(MPI w, const MPI b, struct mpi_ec_ctx *ctx);
+	void (*mul2)(MPI w, MPI u, struct mpi_ec_ctx *ctx);
+};
+
+void mpi_ec_init(struct mpi_ec_ctx *ctx, enum gcry_mpi_ec_models model,
+			enum ecc_dialects dialect,
+			int flags, MPI p, MPI a, MPI b);
+void mpi_ec_deinit(struct mpi_ec_ctx *ctx);
+MPI_POINT mpi_point_new(unsigned int nbits);
+void mpi_point_release(MPI_POINT p);
+void mpi_point_init(MPI_POINT p);
+void mpi_point_free_parts(MPI_POINT p);
+int mpi_ec_get_affine(MPI x, MPI y, MPI_POINT point, struct mpi_ec_ctx *ctx);
+void mpi_ec_add_points(MPI_POINT result,
+			MPI_POINT p1, MPI_POINT p2,
+			struct mpi_ec_ctx *ctx);
+void mpi_ec_mul_point(MPI_POINT result,
+			MPI scalar, MPI_POINT point,
+			struct mpi_ec_ctx *ctx);
+int mpi_ec_curve_point(MPI_POINT point, struct mpi_ec_ctx *ctx);
+
 /* inline functions */
 
 /**
diff --git a/lib/mpi/Makefile b/lib/mpi/Makefile
index 477debd7ed50..6e6ef9a34fe1 100644
--- a/lib/mpi/Makefile
+++ b/lib/mpi/Makefile
@@ -13,6 +13,7 @@ mpi-y = \
 	generic_mpih-rshift.o		\
 	generic_mpih-sub1.o		\
 	generic_mpih-add1.o		\
+	ec.o				\
 	mpicoder.o			\
 	mpi-add.o			\
 	mpi-bit.o			\
diff --git a/lib/mpi/ec.c b/lib/mpi/ec.c
new file mode 100644
index 000000000000..c21470122dfc
--- /dev/null
+++ b/lib/mpi/ec.c
@@ -0,0 +1,1509 @@
+/* ec.c -  Elliptic Curve functions
+ * Copyright (C) 2007 Free Software Foundation, Inc.
+ * Copyright (C) 2013 g10 Code GmbH
+ *
+ * This file is part of Libgcrypt.
+ *
+ * Libgcrypt is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as
+ * published by the Free Software Foundation; either version 2.1 of
+ * the License, or (at your option) any later version.
+ *
+ * Libgcrypt is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "mpi-internal.h"
+#include "longlong.h"
+
+#define point_init(a)  mpi_point_init((a))
+#define point_free(a)  mpi_point_free_parts((a))
+
+#define log_error(fmt, ...) pr_err(fmt, ##__VA_ARGS__)
+#define log_fatal(fmt, ...) pr_err(fmt, ##__VA_ARGS__)
+
+#define DIM(v) (sizeof(v)/sizeof((v)[0]))
+
+
+/* Create a new point option.  NBITS gives the size in bits of one
+ * coordinate; it is only used to pre-allocate some resources and
+ * might also be passed as 0 to use a default value.
+ */
+MPI_POINT mpi_point_new(unsigned int nbits)
+{
+	MPI_POINT p;
+
+	(void)nbits;  /* Currently not used.  */
+
+	p = kmalloc(sizeof(*p), GFP_KERNEL);
+	if (p)
+		mpi_point_init(p);
+	return p;
+}
+EXPORT_SYMBOL_GPL(mpi_point_new);
+
+/* Release the point object P.  P may be NULL. */
+void mpi_point_release(MPI_POINT p)
+{
+	if (p) {
+		mpi_point_free_parts(p);
+		kfree(p);
+	}
+}
+EXPORT_SYMBOL_GPL(mpi_point_release);
+
+/* Initialize the fields of a point object.  gcry_mpi_point_free_parts
+ * may be used to release the fields.
+ */
+void mpi_point_init(MPI_POINT p)
+{
+	p->x = mpi_new(0);
+	p->y = mpi_new(0);
+	p->z = mpi_new(0);
+}
+EXPORT_SYMBOL_GPL(mpi_point_init);
+
+/* Release the parts of a point object. */
+void mpi_point_free_parts(MPI_POINT p)
+{
+	mpi_free(p->x); p->x = NULL;
+	mpi_free(p->y); p->y = NULL;
+	mpi_free(p->z); p->z = NULL;
+}
+EXPORT_SYMBOL_GPL(mpi_point_free_parts);
+
+/* Set the value from S into D.  */
+static void point_set(MPI_POINT d, MPI_POINT s)
+{
+	mpi_set(d->x, s->x);
+	mpi_set(d->y, s->y);
+	mpi_set(d->z, s->z);
+}
+
+static void point_resize(MPI_POINT p, struct mpi_ec_ctx *ctx)
+{
+	size_t nlimbs = ctx->p->nlimbs;
+
+	mpi_resize(p->x, nlimbs);
+	p->x->nlimbs = nlimbs;
+	mpi_resize(p->z, nlimbs);
+	p->z->nlimbs = nlimbs;
+
+	if (ctx->model != MPI_EC_MONTGOMERY) {
+		mpi_resize(p->y, nlimbs);
+		p->y->nlimbs = nlimbs;
+	}
+}
+
+static void point_swap_cond(MPI_POINT d, MPI_POINT s, unsigned long swap,
+		struct mpi_ec_ctx *ctx)
+{
+	mpi_swap_cond(d->x, s->x, swap);
+	if (ctx->model != MPI_EC_MONTGOMERY)
+		mpi_swap_cond(d->y, s->y, swap);
+	mpi_swap_cond(d->z, s->z, swap);
+}
+
+
+/* W = W mod P.  */
+static void ec_mod(MPI w, struct mpi_ec_ctx *ec)
+{
+	if (ec->t.p_barrett)
+		mpi_mod_barrett(w, w, ec->t.p_barrett);
+	else
+		mpi_mod(w, w, ec->p);
+}
+
+static void ec_addm(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx)
+{
+	mpi_add(w, u, v);
+	ec_mod(w, ctx);
+}
+
+static void ec_subm(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ec)
+{
+	mpi_sub(w, u, v);
+	while (w->sign)
+		mpi_add(w, w, ec->p);
+	/*ec_mod(w, ec);*/
+}
+
+static void ec_mulm(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx)
+{
+	mpi_mul(w, u, v);
+	ec_mod(w, ctx);
+}
+
+/* W = 2 * U mod P.  */
+static void ec_mul2(MPI w, MPI u, struct mpi_ec_ctx *ctx)
+{
+	mpi_lshift(w, u, 1);
+	ec_mod(w, ctx);
+}
+
+static void ec_powm(MPI w, const MPI b, const MPI e,
+		struct mpi_ec_ctx *ctx)
+{
+	mpi_powm(w, b, e, ctx->p);
+	/* mpi_abs(w); */
+}
+
+/* Shortcut for
+ * ec_powm(B, B, mpi_const(MPI_C_TWO), ctx);
+ * for easier optimization.
+ */
+static void ec_pow2(MPI w, const MPI b, struct mpi_ec_ctx *ctx)
+{
+	/* Using mpi_mul is slightly faster (at least on amd64).  */
+	/* mpi_powm(w, b, mpi_const(MPI_C_TWO), ctx->p); */
+	ec_mulm(w, b, b, ctx);
+}
+
+/* Shortcut for
+ * ec_powm(B, B, mpi_const(MPI_C_THREE), ctx);
+ * for easier optimization.
+ */
+static void ec_pow3(MPI w, const MPI b, struct mpi_ec_ctx *ctx)
+{
+	mpi_powm(w, b, mpi_const(MPI_C_THREE), ctx->p);
+}
+
+static void ec_invm(MPI x, MPI a, struct mpi_ec_ctx *ctx)
+{
+	if (!mpi_invm(x, a, ctx->p))
+		log_error("ec_invm: inverse does not exist:\n");
+}
+
+static void mpih_set_cond(mpi_ptr_t wp, mpi_ptr_t up,
+		mpi_size_t usize, unsigned long set)
+{
+	mpi_size_t i;
+	mpi_limb_t mask = ((mpi_limb_t)0) - set;
+	mpi_limb_t x;
+
+	for (i = 0; i < usize; i++) {
+		x = mask & (wp[i] ^ up[i]);
+		wp[i] = wp[i] ^ x;
+	}
+}
+
+/* Routines for 2^255 - 19.  */
+
+#define LIMB_SIZE_25519 ((256+BITS_PER_MPI_LIMB-1)/BITS_PER_MPI_LIMB)
+
+static void ec_addm_25519(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx)
+{
+	mpi_ptr_t wp, up, vp;
+	mpi_size_t wsize = LIMB_SIZE_25519;
+	mpi_limb_t n[LIMB_SIZE_25519];
+	mpi_limb_t borrow;
+
+	if (w->nlimbs != wsize || u->nlimbs != wsize || v->nlimbs != wsize)
+		log_bug("addm_25519: different sizes\n");
+
+	memset(n, 0, sizeof(n));
+	up = u->d;
+	vp = v->d;
+	wp = w->d;
+
+	mpihelp_add_n(wp, up, vp, wsize);
+	borrow = mpihelp_sub_n(wp, wp, ctx->p->d, wsize);
+	mpih_set_cond(n, ctx->p->d, wsize, (borrow != 0UL));
+	mpihelp_add_n(wp, wp, n, wsize);
+	wp[LIMB_SIZE_25519-1] &= ~((mpi_limb_t)1 << (255 % BITS_PER_MPI_LIMB));
+}
+
+static void ec_subm_25519(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx)
+{
+	mpi_ptr_t wp, up, vp;
+	mpi_size_t wsize = LIMB_SIZE_25519;
+	mpi_limb_t n[LIMB_SIZE_25519];
+	mpi_limb_t borrow;
+
+	if (w->nlimbs != wsize || u->nlimbs != wsize || v->nlimbs != wsize)
+		log_bug("subm_25519: different sizes\n");
+
+	memset(n, 0, sizeof(n));
+	up = u->d;
+	vp = v->d;
+	wp = w->d;
+
+	borrow = mpihelp_sub_n(wp, up, vp, wsize);
+	mpih_set_cond(n, ctx->p->d, wsize, (borrow != 0UL));
+	mpihelp_add_n(wp, wp, n, wsize);
+	wp[LIMB_SIZE_25519-1] &= ~((mpi_limb_t)1 << (255 % BITS_PER_MPI_LIMB));
+}
+
+static void ec_mulm_25519(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx)
+{
+	mpi_ptr_t wp, up, vp;
+	mpi_size_t wsize = LIMB_SIZE_25519;
+	mpi_limb_t n[LIMB_SIZE_25519*2];
+	mpi_limb_t m[LIMB_SIZE_25519+1];
+	mpi_limb_t cy;
+	int msb;
+
+	(void)ctx;
+	if (w->nlimbs != wsize || u->nlimbs != wsize || v->nlimbs != wsize)
+		log_bug("mulm_25519: different sizes\n");
+
+	up = u->d;
+	vp = v->d;
+	wp = w->d;
+
+	mpihelp_mul_n(n, up, vp, wsize);
+	memcpy(wp, n, wsize * BYTES_PER_MPI_LIMB);
+	wp[LIMB_SIZE_25519-1] &= ~((mpi_limb_t)1 << (255 % BITS_PER_MPI_LIMB));
+
+	memcpy(m, n+LIMB_SIZE_25519-1, (wsize+1) * BYTES_PER_MPI_LIMB);
+	mpihelp_rshift(m, m, LIMB_SIZE_25519+1, (255 % BITS_PER_MPI_LIMB));
+
+	memcpy(n, m, wsize * BYTES_PER_MPI_LIMB);
+	cy = mpihelp_lshift(m, m, LIMB_SIZE_25519, 4);
+	m[LIMB_SIZE_25519] = cy;
+	cy = mpihelp_add_n(m, m, n, wsize);
+	m[LIMB_SIZE_25519] += cy;
+	cy = mpihelp_add_n(m, m, n, wsize);
+	m[LIMB_SIZE_25519] += cy;
+	cy = mpihelp_add_n(m, m, n, wsize);
+	m[LIMB_SIZE_25519] += cy;
+
+	cy = mpihelp_add_n(wp, wp, m, wsize);
+	m[LIMB_SIZE_25519] += cy;
+
+	memset(m, 0, wsize * BYTES_PER_MPI_LIMB);
+	msb = (wp[LIMB_SIZE_25519-1] >> (255 % BITS_PER_MPI_LIMB));
+	m[0] = (m[LIMB_SIZE_25519] * 2 + msb) * 19;
+	wp[LIMB_SIZE_25519-1] &= ~((mpi_limb_t)1 << (255 % BITS_PER_MPI_LIMB));
+	mpihelp_add_n(wp, wp, m, wsize);
+
+	m[0] = 0;
+	cy = mpihelp_sub_n(wp, wp, ctx->p->d, wsize);
+	mpih_set_cond(m, ctx->p->d, wsize, (cy != 0UL));
+	mpihelp_add_n(wp, wp, m, wsize);
+}
+
+static void ec_mul2_25519(MPI w, MPI u, struct mpi_ec_ctx *ctx)
+{
+	ec_addm_25519(w, u, u, ctx);
+}
+
+static void ec_pow2_25519(MPI w, const MPI b, struct mpi_ec_ctx *ctx)
+{
+	ec_mulm_25519(w, b, b, ctx);
+}
+
+/* Routines for 2^448 - 2^224 - 1.  */
+
+#define LIMB_SIZE_448 ((448+BITS_PER_MPI_LIMB-1)/BITS_PER_MPI_LIMB)
+#define LIMB_SIZE_HALF_448 ((LIMB_SIZE_448+1)/2)
+
+static void ec_addm_448(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx)
+{
+	mpi_ptr_t wp, up, vp;
+	mpi_size_t wsize = LIMB_SIZE_448;
+	mpi_limb_t n[LIMB_SIZE_448];
+	mpi_limb_t cy;
+
+	if (w->nlimbs != wsize || u->nlimbs != wsize || v->nlimbs != wsize)
+		log_bug("addm_448: different sizes\n");
+
+	memset(n, 0, sizeof(n));
+	up = u->d;
+	vp = v->d;
+	wp = w->d;
+
+	cy = mpihelp_add_n(wp, up, vp, wsize);
+	mpih_set_cond(n, ctx->p->d, wsize, (cy != 0UL));
+	mpihelp_sub_n(wp, wp, n, wsize);
+}
+
+static void ec_subm_448(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx)
+{
+	mpi_ptr_t wp, up, vp;
+	mpi_size_t wsize = LIMB_SIZE_448;
+	mpi_limb_t n[LIMB_SIZE_448];
+	mpi_limb_t borrow;
+
+	if (w->nlimbs != wsize || u->nlimbs != wsize || v->nlimbs != wsize)
+		log_bug("subm_448: different sizes\n");
+
+	memset(n, 0, sizeof(n));
+	up = u->d;
+	vp = v->d;
+	wp = w->d;
+
+	borrow = mpihelp_sub_n(wp, up, vp, wsize);
+	mpih_set_cond(n, ctx->p->d, wsize, (borrow != 0UL));
+	mpihelp_add_n(wp, wp, n, wsize);
+}
+
+static void ec_mulm_448(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx)
+{
+	mpi_ptr_t wp, up, vp;
+	mpi_size_t wsize = LIMB_SIZE_448;
+	mpi_limb_t n[LIMB_SIZE_448*2];
+	mpi_limb_t a2[LIMB_SIZE_HALF_448];
+	mpi_limb_t a3[LIMB_SIZE_HALF_448];
+	mpi_limb_t b0[LIMB_SIZE_HALF_448];
+	mpi_limb_t b1[LIMB_SIZE_HALF_448];
+	mpi_limb_t cy;
+	int i;
+#if (LIMB_SIZE_HALF_448 > LIMB_SIZE_448/2)
+	mpi_limb_t b1_rest, a3_rest;
+#endif
+
+	if (w->nlimbs != wsize || u->nlimbs != wsize || v->nlimbs != wsize)
+		log_bug("mulm_448: different sizes\n");
+
+	up = u->d;
+	vp = v->d;
+	wp = w->d;
+
+	mpihelp_mul_n(n, up, vp, wsize);
+
+	for (i = 0; i < (wsize + 1) / 2; i++) {
+		b0[i] = n[i];
+		b1[i] = n[i+wsize/2];
+		a2[i] = n[i+wsize];
+		a3[i] = n[i+wsize+wsize/2];
+	}
+
+#if (LIMB_SIZE_HALF_448 > LIMB_SIZE_448/2)
+	b0[LIMB_SIZE_HALF_448-1] &= ((mpi_limb_t)1UL << 32)-1;
+	a2[LIMB_SIZE_HALF_448-1] &= ((mpi_limb_t)1UL << 32)-1;
+
+	b1_rest = 0;
+	a3_rest = 0;
+
+	for (i = (wsize + 1) / 2 - 1; i >= 0; i--) {
+		mpi_limb_t b1v, a3v;
+		b1v = b1[i];
+		a3v = a3[i];
+		b1[i] = (b1_rest << 32) | (b1v >> 32);
+		a3[i] = (a3_rest << 32) | (a3v >> 32);
+		b1_rest = b1v & (((mpi_limb_t)1UL << 32)-1);
+		a3_rest = a3v & (((mpi_limb_t)1UL << 32)-1);
+	}
+#endif
+
+	cy = mpihelp_add_n(b0, b0, a2, LIMB_SIZE_HALF_448);
+	cy += mpihelp_add_n(b0, b0, a3, LIMB_SIZE_HALF_448);
+	for (i = 0; i < (wsize + 1) / 2; i++)
+		wp[i] = b0[i];
+#if (LIMB_SIZE_HALF_448 > LIMB_SIZE_448/2)
+	wp[LIMB_SIZE_HALF_448-1] &= (((mpi_limb_t)1UL << 32)-1);
+#endif
+
+#if (LIMB_SIZE_HALF_448 > LIMB_SIZE_448/2)
+	cy = b0[LIMB_SIZE_HALF_448-1] >> 32;
+#endif
+
+	cy = mpihelp_add_1(b1, b1, LIMB_SIZE_HALF_448, cy);
+	cy += mpihelp_add_n(b1, b1, a2, LIMB_SIZE_HALF_448);
+	cy += mpihelp_add_n(b1, b1, a3, LIMB_SIZE_HALF_448);
+	cy += mpihelp_add_n(b1, b1, a3, LIMB_SIZE_HALF_448);
+#if (LIMB_SIZE_HALF_448 > LIMB_SIZE_448/2)
+	b1_rest = 0;
+	for (i = (wsize + 1) / 2 - 1; i >= 0; i--) {
+		mpi_limb_t b1v = b1[i];
+		b1[i] = (b1_rest << 32) | (b1v >> 32);
+		b1_rest = b1v & (((mpi_limb_t)1UL << 32)-1);
+	}
+	wp[LIMB_SIZE_HALF_448-1] |= (b1_rest << 32);
+#endif
+	for (i = 0; i < wsize / 2; i++)
+		wp[i+(wsize + 1) / 2] = b1[i];
+
+#if (LIMB_SIZE_HALF_448 > LIMB_SIZE_448/2)
+	cy = b1[LIMB_SIZE_HALF_448-1];
+#endif
+
+	memset(n, 0, wsize * BYTES_PER_MPI_LIMB);
+
+#if (LIMB_SIZE_HALF_448 > LIMB_SIZE_448/2)
+	n[LIMB_SIZE_HALF_448-1] = cy << 32;
+#else
+	n[LIMB_SIZE_HALF_448] = cy;
+#endif
+	n[0] = cy;
+	mpihelp_add_n(wp, wp, n, wsize);
+
+	memset(n, 0, wsize * BYTES_PER_MPI_LIMB);
+	cy = mpihelp_sub_n(wp, wp, ctx->p->d, wsize);
+	mpih_set_cond(n, ctx->p->d, wsize, (cy != 0UL));
+	mpihelp_add_n(wp, wp, n, wsize);
+}
+
+static void ec_mul2_448(MPI w, MPI u, struct mpi_ec_ctx *ctx)
+{
+	ec_addm_448(w, u, u, ctx);
+}
+
+static void ec_pow2_448(MPI w, const MPI b, struct mpi_ec_ctx *ctx)
+{
+	ec_mulm_448(w, b, b, ctx);
+}
+
+struct field_table {
+	const char *p;
+
+	/* computation routines for the field.  */
+	void (*addm)(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx);
+	void (*subm)(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx);
+	void (*mulm)(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx);
+	void (*mul2)(MPI w, MPI u, struct mpi_ec_ctx *ctx);
+	void (*pow2)(MPI w, const MPI b, struct mpi_ec_ctx *ctx);
+};
+
+static const struct field_table field_table[] = {
+	{
+		"0x7FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFED",
+		ec_addm_25519,
+		ec_subm_25519,
+		ec_mulm_25519,
+		ec_mul2_25519,
+		ec_pow2_25519
+	},
+	{
+		"0xFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFE"
+		"FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF",
+		ec_addm_448,
+		ec_subm_448,
+		ec_mulm_448,
+		ec_mul2_448,
+		ec_pow2_448
+	},
+	{ NULL, NULL, NULL, NULL, NULL, NULL },
+};
+
+/* Force recomputation of all helper variables.  */
+static void mpi_ec_get_reset(struct mpi_ec_ctx *ec)
+{
+	ec->t.valid.a_is_pminus3 = 0;
+	ec->t.valid.two_inv_p = 0;
+}
+
+/* Accessor for helper variable.  */
+static int ec_get_a_is_pminus3(struct mpi_ec_ctx *ec)
+{
+	MPI tmp;
+
+	if (!ec->t.valid.a_is_pminus3) {
+		ec->t.valid.a_is_pminus3 = 1;
+		tmp = mpi_alloc_like(ec->p);
+		mpi_sub_ui(tmp, ec->p, 3);
+		ec->t.a_is_pminus3 = !mpi_cmp(ec->a, tmp);
+		mpi_free(tmp);
+	}
+
+	return ec->t.a_is_pminus3;
+}
+
+/* Accessor for helper variable.  */
+static MPI ec_get_two_inv_p(struct mpi_ec_ctx *ec)
+{
+	if (!ec->t.valid.two_inv_p) {
+		ec->t.valid.two_inv_p = 1;
+		if (!ec->t.two_inv_p)
+			ec->t.two_inv_p = mpi_alloc(0);
+		ec_invm(ec->t.two_inv_p, mpi_const(MPI_C_TWO), ec);
+	}
+	return ec->t.two_inv_p;
+}
+
+static const char *const curve25519_bad_points[] = {
+	"0x7fffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffed",
+	"0x0000000000000000000000000000000000000000000000000000000000000000",
+	"0x0000000000000000000000000000000000000000000000000000000000000001",
+	"0x00b8495f16056286fdb1329ceb8d09da6ac49ff1fae35616aeb8413b7c7aebe0",
+	"0x57119fd0dd4e22d8868e1c58c45c44045bef839c55b1d0b1248c50a3bc959c5f",
+	"0x7fffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffec",
+	"0x7fffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffee",
+	NULL
+};
+
+static const char *const curve448_bad_points[] = {
+	"0xfffffffffffffffffffffffffffffffffffffffffffffffffffffffe"
+	"ffffffffffffffffffffffffffffffffffffffffffffffffffffffff",
+	"0x00000000000000000000000000000000000000000000000000000000"
+	"00000000000000000000000000000000000000000000000000000000",
+	"0x00000000000000000000000000000000000000000000000000000000"
+	"00000000000000000000000000000000000000000000000000000001",
+	"0xfffffffffffffffffffffffffffffffffffffffffffffffffffffffe"
+	"fffffffffffffffffffffffffffffffffffffffffffffffffffffffe",
+	"0xffffffffffffffffffffffffffffffffffffffffffffffffffffffff"
+	"00000000000000000000000000000000000000000000000000000000",
+	NULL
+};
+
+static const char *const *bad_points_table[] = {
+	curve25519_bad_points,
+	curve448_bad_points,
+};
+
+static void mpi_ec_coefficient_normalize(MPI a, MPI p)
+{
+	if (a->sign) {
+		mpi_resize(a, p->nlimbs);
+		mpihelp_sub_n(a->d, p->d, a->d, p->nlimbs);
+		a->nlimbs = p->nlimbs;
+		a->sign = 0;
+	}
+}
+
+/* This function initialized a context for elliptic curve based on the
+ * field GF(p).  P is the prime specifying this field, A is the first
+ * coefficient.  CTX is expected to be zeroized.
+ */
+void mpi_ec_init(struct mpi_ec_ctx *ctx, enum gcry_mpi_ec_models model,
+			enum ecc_dialects dialect,
+			int flags, MPI p, MPI a, MPI b)
+{
+	int i;
+	static int use_barrett = -1 /* TODO: 1 or -1 */;
+
+	mpi_ec_coefficient_normalize(a, p);
+	mpi_ec_coefficient_normalize(b, p);
+
+	/* Fixme: Do we want to check some constraints? e.g.  a < p  */
+
+	ctx->model = model;
+	ctx->dialect = dialect;
+	ctx->flags = flags;
+	if (dialect == ECC_DIALECT_ED25519)
+		ctx->nbits = 256;
+	else
+		ctx->nbits = mpi_get_nbits(p);
+	ctx->p = mpi_copy(p);
+	ctx->a = mpi_copy(a);
+	ctx->b = mpi_copy(b);
+
+	ctx->t.p_barrett = use_barrett > 0 ? mpi_barrett_init(ctx->p, 0) : NULL;
+
+	mpi_ec_get_reset(ctx);
+
+	if (model == MPI_EC_MONTGOMERY) {
+		for (i = 0; i < DIM(bad_points_table); i++) {
+			MPI p_candidate = mpi_scanval(bad_points_table[i][0]);
+			int match_p = !mpi_cmp(ctx->p, p_candidate);
+			int j;
+
+			mpi_free(p_candidate);
+			if (!match_p)
+				continue;
+
+			for (j = 0; i < DIM(ctx->t.scratch) && bad_points_table[i][j]; j++)
+				ctx->t.scratch[j] = mpi_scanval(bad_points_table[i][j]);
+		}
+	} else {
+		/* Allocate scratch variables.  */
+		for (i = 0; i < DIM(ctx->t.scratch); i++)
+			ctx->t.scratch[i] = mpi_alloc_like(ctx->p);
+	}
+
+	ctx->addm = ec_addm;
+	ctx->subm = ec_subm;
+	ctx->mulm = ec_mulm;
+	ctx->mul2 = ec_mul2;
+	ctx->pow2 = ec_pow2;
+
+	for (i = 0; field_table[i].p; i++) {
+		MPI f_p;
+
+		f_p = mpi_scanval(field_table[i].p);
+		if (!f_p)
+			break;
+
+		if (!mpi_cmp(p, f_p)) {
+			ctx->addm = field_table[i].addm;
+			ctx->subm = field_table[i].subm;
+			ctx->mulm = field_table[i].mulm;
+			ctx->mul2 = field_table[i].mul2;
+			ctx->pow2 = field_table[i].pow2;
+			mpi_free(f_p);
+
+			mpi_resize(ctx->a, ctx->p->nlimbs);
+			ctx->a->nlimbs = ctx->p->nlimbs;
+
+			mpi_resize(ctx->b, ctx->p->nlimbs);
+			ctx->b->nlimbs = ctx->p->nlimbs;
+
+			for (i = 0; i < DIM(ctx->t.scratch) && ctx->t.scratch[i]; i++)
+				ctx->t.scratch[i]->nlimbs = ctx->p->nlimbs;
+
+			break;
+		}
+
+		mpi_free(f_p);
+	}
+}
+EXPORT_SYMBOL_GPL(mpi_ec_init);
+
+void mpi_ec_deinit(struct mpi_ec_ctx *ctx)
+{
+	int i;
+
+	mpi_barrett_free(ctx->t.p_barrett);
+
+	/* Domain parameter.  */
+	mpi_free(ctx->p);
+	mpi_free(ctx->a);
+	mpi_free(ctx->b);
+	mpi_point_release(ctx->G);
+	mpi_free(ctx->n);
+
+	/* The key.  */
+	mpi_point_release(ctx->Q);
+	mpi_free(ctx->d);
+
+	/* Private data of ec.c.  */
+	mpi_free(ctx->t.two_inv_p);
+
+	for (i = 0; i < DIM(ctx->t.scratch); i++)
+		mpi_free(ctx->t.scratch[i]);
+}
+EXPORT_SYMBOL_GPL(mpi_ec_deinit);
+
+/* Compute the affine coordinates from the projective coordinates in
+ * POINT.  Set them into X and Y.  If one coordinate is not required,
+ * X or Y may be passed as NULL.  CTX is the usual context. Returns: 0
+ * on success or !0 if POINT is at infinity.
+ */
+int mpi_ec_get_affine(MPI x, MPI y, MPI_POINT point, struct mpi_ec_ctx *ctx)
+{
+	if (!mpi_cmp_ui(point->z, 0))
+		return -1;
+
+	switch (ctx->model) {
+	case MPI_EC_WEIERSTRASS: /* Using Jacobian coordinates.  */
+		{
+			MPI z1, z2, z3;
+
+			z1 = mpi_new(0);
+			z2 = mpi_new(0);
+			ec_invm(z1, point->z, ctx);  /* z1 = z^(-1) mod p  */
+			ec_mulm(z2, z1, z1, ctx);    /* z2 = z^(-2) mod p  */
+
+			if (x)
+				ec_mulm(x, point->x, z2, ctx);
+
+			if (y) {
+				z3 = mpi_new(0);
+				ec_mulm(z3, z2, z1, ctx);      /* z3 = z^(-3) mod p */
+				ec_mulm(y, point->y, z3, ctx);
+				mpi_free(z3);
+			}
+
+			mpi_free(z2);
+			mpi_free(z1);
+		}
+		return 0;
+
+	case MPI_EC_MONTGOMERY:
+		{
+			if (x)
+				mpi_set(x, point->x);
+
+			if (y) {
+				log_fatal("%s: Getting Y-coordinate on %s is not supported\n",
+						"mpi_ec_get_affine", "Montgomery");
+				return -1;
+			}
+		}
+		return 0;
+
+	case MPI_EC_EDWARDS:
+		{
+			MPI z;
+
+			z = mpi_new(0);
+			ec_invm(z, point->z, ctx);
+
+			mpi_resize(z, ctx->p->nlimbs);
+			z->nlimbs = ctx->p->nlimbs;
+
+			if (x) {
+				mpi_resize(x, ctx->p->nlimbs);
+				x->nlimbs = ctx->p->nlimbs;
+				ctx->mulm(x, point->x, z, ctx);
+			}
+			if (y) {
+				mpi_resize(y, ctx->p->nlimbs);
+				y->nlimbs = ctx->p->nlimbs;
+				ctx->mulm(y, point->y, z, ctx);
+			}
+
+			mpi_free(z);
+		}
+		return 0;
+
+	default:
+		return -1;
+	}
+}
+EXPORT_SYMBOL_GPL(mpi_ec_get_affine);
+
+/*  RESULT = 2 * POINT  (Weierstrass version). */
+static void dup_point_weierstrass(MPI_POINT result,
+		MPI_POINT point, struct mpi_ec_ctx *ctx)
+{
+#define x3 (result->x)
+#define y3 (result->y)
+#define z3 (result->z)
+#define t1 (ctx->t.scratch[0])
+#define t2 (ctx->t.scratch[1])
+#define t3 (ctx->t.scratch[2])
+#define l1 (ctx->t.scratch[3])
+#define l2 (ctx->t.scratch[4])
+#define l3 (ctx->t.scratch[5])
+
+	if (!mpi_cmp_ui(point->y, 0) || !mpi_cmp_ui(point->z, 0)) {
+		/* P_y == 0 || P_z == 0 => [1:1:0] */
+		mpi_set_ui(x3, 1);
+		mpi_set_ui(y3, 1);
+		mpi_set_ui(z3, 0);
+	} else {
+		if (ec_get_a_is_pminus3(ctx)) {
+			/* Use the faster case.  */
+			/* L1 = 3(X - Z^2)(X + Z^2) */
+			/*                          T1: used for Z^2. */
+			/*                          T2: used for the right term. */
+			ec_pow2(t1, point->z, ctx);
+			ec_subm(l1, point->x, t1, ctx);
+			ec_mulm(l1, l1, mpi_const(MPI_C_THREE), ctx);
+			ec_addm(t2, point->x, t1, ctx);
+			ec_mulm(l1, l1, t2, ctx);
+		} else {
+			/* Standard case. */
+			/* L1 = 3X^2 + aZ^4 */
+			/*                          T1: used for aZ^4. */
+			ec_pow2(l1, point->x, ctx);
+			ec_mulm(l1, l1, mpi_const(MPI_C_THREE), ctx);
+			ec_powm(t1, point->z, mpi_const(MPI_C_FOUR), ctx);
+			ec_mulm(t1, t1, ctx->a, ctx);
+			ec_addm(l1, l1, t1, ctx);
+		}
+		/* Z3 = 2YZ */
+		ec_mulm(z3, point->y, point->z, ctx);
+		ec_mul2(z3, z3, ctx);
+
+		/* L2 = 4XY^2 */
+		/*                              T2: used for Y2; required later. */
+		ec_pow2(t2, point->y, ctx);
+		ec_mulm(l2, t2, point->x, ctx);
+		ec_mulm(l2, l2, mpi_const(MPI_C_FOUR), ctx);
+
+		/* X3 = L1^2 - 2L2 */
+		/*                              T1: used for L2^2. */
+		ec_pow2(x3, l1, ctx);
+		ec_mul2(t1, l2, ctx);
+		ec_subm(x3, x3, t1, ctx);
+
+		/* L3 = 8Y^4 */
+		/*                              T2: taken from above. */
+		ec_pow2(t2, t2, ctx);
+		ec_mulm(l3, t2, mpi_const(MPI_C_EIGHT), ctx);
+
+		/* Y3 = L1(L2 - X3) - L3 */
+		ec_subm(y3, l2, x3, ctx);
+		ec_mulm(y3, y3, l1, ctx);
+		ec_subm(y3, y3, l3, ctx);
+	}
+
+#undef x3
+#undef y3
+#undef z3
+#undef t1
+#undef t2
+#undef t3
+#undef l1
+#undef l2
+#undef l3
+}
+
+/*  RESULT = 2 * POINT  (Montgomery version). */
+static void dup_point_montgomery(MPI_POINT result,
+				MPI_POINT point, struct mpi_ec_ctx *ctx)
+{
+	(void)result;
+	(void)point;
+	(void)ctx;
+	log_fatal("%s: %s not yet supported\n",
+			"mpi_ec_dup_point", "Montgomery");
+}
+
+/*  RESULT = 2 * POINT  (Twisted Edwards version). */
+static void dup_point_edwards(MPI_POINT result,
+		MPI_POINT point, struct mpi_ec_ctx *ctx)
+{
+#define X1 (point->x)
+#define Y1 (point->y)
+#define Z1 (point->z)
+#define X3 (result->x)
+#define Y3 (result->y)
+#define Z3 (result->z)
+#define B (ctx->t.scratch[0])
+#define C (ctx->t.scratch[1])
+#define D (ctx->t.scratch[2])
+#define E (ctx->t.scratch[3])
+#define F (ctx->t.scratch[4])
+#define H (ctx->t.scratch[5])
+#define J (ctx->t.scratch[6])
+
+	/* Compute: (X_3 : Y_3 : Z_3) = 2( X_1 : Y_1 : Z_1 ) */
+
+	/* B = (X_1 + Y_1)^2  */
+	ctx->addm(B, X1, Y1, ctx);
+	ctx->pow2(B, B, ctx);
+
+	/* C = X_1^2 */
+	/* D = Y_1^2 */
+	ctx->pow2(C, X1, ctx);
+	ctx->pow2(D, Y1, ctx);
+
+	/* E = aC */
+	if (ctx->dialect == ECC_DIALECT_ED25519)
+		ctx->subm(E, ctx->p, C, ctx);
+	else
+		ctx->mulm(E, ctx->a, C, ctx);
+
+	/* F = E + D */
+	ctx->addm(F, E, D, ctx);
+
+	/* H = Z_1^2 */
+	ctx->pow2(H, Z1, ctx);
+
+	/* J = F - 2H */
+	ctx->mul2(J, H, ctx);
+	ctx->subm(J, F, J, ctx);
+
+	/* X_3 = (B - C - D) · J */
+	ctx->subm(X3, B, C, ctx);
+	ctx->subm(X3, X3, D, ctx);
+	ctx->mulm(X3, X3, J, ctx);
+
+	/* Y_3 = F · (E - D) */
+	ctx->subm(Y3, E, D, ctx);
+	ctx->mulm(Y3, Y3, F, ctx);
+
+	/* Z_3 = F · J */
+	ctx->mulm(Z3, F, J, ctx);
+
+#undef X1
+#undef Y1
+#undef Z1
+#undef X3
+#undef Y3
+#undef Z3
+#undef B
+#undef C
+#undef D
+#undef E
+#undef F
+#undef H
+#undef J
+}
+
+/*  RESULT = 2 * POINT  */
+static void
+mpi_ec_dup_point(MPI_POINT result, MPI_POINT point, struct mpi_ec_ctx *ctx)
+{
+	switch (ctx->model) {
+	case MPI_EC_WEIERSTRASS:
+		dup_point_weierstrass(result, point, ctx);
+		break;
+	case MPI_EC_MONTGOMERY:
+		dup_point_montgomery(result, point, ctx);
+		break;
+	case MPI_EC_EDWARDS:
+		dup_point_edwards(result, point, ctx);
+		break;
+	}
+}
+
+/* RESULT = P1 + P2  (Weierstrass version).*/
+static void add_points_weierstrass(MPI_POINT result,
+		MPI_POINT p1, MPI_POINT p2,
+		struct mpi_ec_ctx *ctx)
+{
+#define x1 (p1->x)
+#define y1 (p1->y)
+#define z1 (p1->z)
+#define x2 (p2->x)
+#define y2 (p2->y)
+#define z2 (p2->z)
+#define x3 (result->x)
+#define y3 (result->y)
+#define z3 (result->z)
+#define l1 (ctx->t.scratch[0])
+#define l2 (ctx->t.scratch[1])
+#define l3 (ctx->t.scratch[2])
+#define l4 (ctx->t.scratch[3])
+#define l5 (ctx->t.scratch[4])
+#define l6 (ctx->t.scratch[5])
+#define l7 (ctx->t.scratch[6])
+#define l8 (ctx->t.scratch[7])
+#define l9 (ctx->t.scratch[8])
+#define t1 (ctx->t.scratch[9])
+#define t2 (ctx->t.scratch[10])
+
+	if ((!mpi_cmp(x1, x2)) && (!mpi_cmp(y1, y2)) && (!mpi_cmp(z1, z2))) {
+		/* Same point; need to call the duplicate function.  */
+		mpi_ec_dup_point(result, p1, ctx);
+	} else if (!mpi_cmp_ui(z1, 0)) {
+		/* P1 is at infinity.  */
+		mpi_set(x3, p2->x);
+		mpi_set(y3, p2->y);
+		mpi_set(z3, p2->z);
+	} else if (!mpi_cmp_ui(z2, 0)) {
+		/* P2 is at infinity.  */
+		mpi_set(x3, p1->x);
+		mpi_set(y3, p1->y);
+		mpi_set(z3, p1->z);
+	} else {
+		int z1_is_one = !mpi_cmp_ui(z1, 1);
+		int z2_is_one = !mpi_cmp_ui(z2, 1);
+
+		/* l1 = x1 z2^2  */
+		/* l2 = x2 z1^2  */
+		if (z2_is_one)
+			mpi_set(l1, x1);
+		else {
+			ec_pow2(l1, z2, ctx);
+			ec_mulm(l1, l1, x1, ctx);
+		}
+		if (z1_is_one)
+			mpi_set(l2, x2);
+		else {
+			ec_pow2(l2, z1, ctx);
+			ec_mulm(l2, l2, x2, ctx);
+		}
+		/* l3 = l1 - l2 */
+		ec_subm(l3, l1, l2, ctx);
+		/* l4 = y1 z2^3  */
+		ec_powm(l4, z2, mpi_const(MPI_C_THREE), ctx);
+		ec_mulm(l4, l4, y1, ctx);
+		/* l5 = y2 z1^3  */
+		ec_powm(l5, z1, mpi_const(MPI_C_THREE), ctx);
+		ec_mulm(l5, l5, y2, ctx);
+		/* l6 = l4 - l5  */
+		ec_subm(l6, l4, l5, ctx);
+
+		if (!mpi_cmp_ui(l3, 0)) {
+			if (!mpi_cmp_ui(l6, 0)) {
+				/* P1 and P2 are the same - use duplicate function. */
+				mpi_ec_dup_point(result, p1, ctx);
+			} else {
+				/* P1 is the inverse of P2.  */
+				mpi_set_ui(x3, 1);
+				mpi_set_ui(y3, 1);
+				mpi_set_ui(z3, 0);
+			}
+		} else {
+			/* l7 = l1 + l2  */
+			ec_addm(l7, l1, l2, ctx);
+			/* l8 = l4 + l5  */
+			ec_addm(l8, l4, l5, ctx);
+			/* z3 = z1 z2 l3  */
+			ec_mulm(z3, z1, z2, ctx);
+			ec_mulm(z3, z3, l3, ctx);
+			/* x3 = l6^2 - l7 l3^2  */
+			ec_pow2(t1, l6, ctx);
+			ec_pow2(t2, l3, ctx);
+			ec_mulm(t2, t2, l7, ctx);
+			ec_subm(x3, t1, t2, ctx);
+			/* l9 = l7 l3^2 - 2 x3  */
+			ec_mul2(t1, x3, ctx);
+			ec_subm(l9, t2, t1, ctx);
+			/* y3 = (l9 l6 - l8 l3^3)/2  */
+			ec_mulm(l9, l9, l6, ctx);
+			ec_powm(t1, l3, mpi_const(MPI_C_THREE), ctx); /* fixme: Use saved value*/
+			ec_mulm(t1, t1, l8, ctx);
+			ec_subm(y3, l9, t1, ctx);
+			ec_mulm(y3, y3, ec_get_two_inv_p(ctx), ctx);
+		}
+	}
+
+#undef x1
+#undef y1
+#undef z1
+#undef x2
+#undef y2
+#undef z2
+#undef x3
+#undef y3
+#undef z3
+#undef l1
+#undef l2
+#undef l3
+#undef l4
+#undef l5
+#undef l6
+#undef l7
+#undef l8
+#undef l9
+#undef t1
+#undef t2
+}
+
+/* RESULT = P1 + P2  (Montgomery version).*/
+static void add_points_montgomery(MPI_POINT result,
+		MPI_POINT p1, MPI_POINT p2,
+		struct mpi_ec_ctx *ctx)
+{
+	(void)result;
+	(void)p1;
+	(void)p2;
+	(void)ctx;
+	log_fatal("%s: %s not yet supported\n",
+			"mpi_ec_add_points", "Montgomery");
+}
+
+/* RESULT = P1 + P2  (Twisted Edwards version).*/
+static void add_points_edwards(MPI_POINT result,
+		MPI_POINT p1, MPI_POINT p2,
+		struct mpi_ec_ctx *ctx)
+{
+#define X1 (p1->x)
+#define Y1 (p1->y)
+#define Z1 (p1->z)
+#define X2 (p2->x)
+#define Y2 (p2->y)
+#define Z2 (p2->z)
+#define X3 (result->x)
+#define Y3 (result->y)
+#define Z3 (result->z)
+#define A (ctx->t.scratch[0])
+#define B (ctx->t.scratch[1])
+#define C (ctx->t.scratch[2])
+#define D (ctx->t.scratch[3])
+#define E (ctx->t.scratch[4])
+#define F (ctx->t.scratch[5])
+#define G (ctx->t.scratch[6])
+#define tmp (ctx->t.scratch[7])
+
+	point_resize(result, ctx);
+
+	/* Compute: (X_3 : Y_3 : Z_3) = (X_1 : Y_1 : Z_1) + (X_2 : Y_2 : Z_3) */
+
+	/* A = Z1 · Z2 */
+	ctx->mulm(A, Z1, Z2, ctx);
+
+	/* B = A^2 */
+	ctx->pow2(B, A, ctx);
+
+	/* C = X1 · X2 */
+	ctx->mulm(C, X1, X2, ctx);
+
+	/* D = Y1 · Y2 */
+	ctx->mulm(D, Y1, Y2, ctx);
+
+	/* E = d · C · D */
+	ctx->mulm(E, ctx->b, C, ctx);
+	ctx->mulm(E, E, D, ctx);
+
+	/* F = B - E */
+	ctx->subm(F, B, E, ctx);
+
+	/* G = B + E */
+	ctx->addm(G, B, E, ctx);
+
+	/* X_3 = A · F · ((X_1 + Y_1) · (X_2 + Y_2) - C - D) */
+	ctx->addm(tmp, X1, Y1, ctx);
+	ctx->addm(X3, X2, Y2, ctx);
+	ctx->mulm(X3, X3, tmp, ctx);
+	ctx->subm(X3, X3, C, ctx);
+	ctx->subm(X3, X3, D, ctx);
+	ctx->mulm(X3, X3, F, ctx);
+	ctx->mulm(X3, X3, A, ctx);
+
+	/* Y_3 = A · G · (D - aC) */
+	if (ctx->dialect == ECC_DIALECT_ED25519) {
+		ctx->addm(Y3, D, C, ctx);
+	} else {
+		ctx->mulm(Y3, ctx->a, C, ctx);
+		ctx->subm(Y3, D, Y3, ctx);
+	}
+	ctx->mulm(Y3, Y3, G, ctx);
+	ctx->mulm(Y3, Y3, A, ctx);
+
+	/* Z_3 = F · G */
+	ctx->mulm(Z3, F, G, ctx);
+
+
+#undef X1
+#undef Y1
+#undef Z1
+#undef X2
+#undef Y2
+#undef Z2
+#undef X3
+#undef Y3
+#undef Z3
+#undef A
+#undef B
+#undef C
+#undef D
+#undef E
+#undef F
+#undef G
+#undef tmp
+}
+
+/* Compute a step of Montgomery Ladder (only use X and Z in the point).
+ * Inputs:  P1, P2, and x-coordinate of DIF = P1 - P1.
+ * Outputs: PRD = 2 * P1 and  SUM = P1 + P2.
+ */
+static void montgomery_ladder(MPI_POINT prd, MPI_POINT sum,
+		MPI_POINT p1, MPI_POINT p2, MPI dif_x,
+		struct mpi_ec_ctx *ctx)
+{
+	ctx->addm(sum->x, p2->x, p2->z, ctx);
+	ctx->subm(p2->z, p2->x, p2->z, ctx);
+	ctx->addm(prd->x, p1->x, p1->z, ctx);
+	ctx->subm(p1->z, p1->x, p1->z, ctx);
+	ctx->mulm(p2->x, p1->z, sum->x, ctx);
+	ctx->mulm(p2->z, prd->x, p2->z, ctx);
+	ctx->pow2(p1->x, prd->x, ctx);
+	ctx->pow2(p1->z, p1->z, ctx);
+	ctx->addm(sum->x, p2->x, p2->z, ctx);
+	ctx->subm(p2->z, p2->x, p2->z, ctx);
+	ctx->mulm(prd->x, p1->x, p1->z, ctx);
+	ctx->subm(p1->z, p1->x, p1->z, ctx);
+	ctx->pow2(sum->x, sum->x, ctx);
+	ctx->pow2(sum->z, p2->z, ctx);
+	ctx->mulm(prd->z, p1->z, ctx->a, ctx); /* CTX->A: (a-2)/4 */
+	ctx->mulm(sum->z, sum->z, dif_x, ctx);
+	ctx->addm(prd->z, p1->x, prd->z, ctx);
+	ctx->mulm(prd->z, prd->z, p1->z, ctx);
+}
+
+/* RESULT = P1 + P2 */
+void mpi_ec_add_points(MPI_POINT result,
+		MPI_POINT p1, MPI_POINT p2,
+		struct mpi_ec_ctx *ctx)
+{
+	switch (ctx->model) {
+	case MPI_EC_WEIERSTRASS:
+		add_points_weierstrass(result, p1, p2, ctx);
+		break;
+	case MPI_EC_MONTGOMERY:
+		add_points_montgomery(result, p1, p2, ctx);
+		break;
+	case MPI_EC_EDWARDS:
+		add_points_edwards(result, p1, p2, ctx);
+		break;
+	}
+}
+EXPORT_SYMBOL_GPL(mpi_ec_add_points);
+
+/* Scalar point multiplication - the main function for ECC.  If takes
+ * an integer SCALAR and a POINT as well as the usual context CTX.
+ * RESULT will be set to the resulting point.
+ */
+void mpi_ec_mul_point(MPI_POINT result,
+			MPI scalar, MPI_POINT point,
+			struct mpi_ec_ctx *ctx)
+{
+	MPI x1, y1, z1, k, h, yy;
+	unsigned int i, loops;
+	struct gcry_mpi_point p1, p2, p1inv;
+
+	if (ctx->model == MPI_EC_EDWARDS) {
+		/* Simple left to right binary method.  Algorithm 3.27 from
+		 * {author={Hankerson, Darrel and Menezes, Alfred J. and Vanstone, Scott},
+		 *  title = {Guide to Elliptic Curve Cryptography},
+		 *  year = {2003}, isbn = {038795273X},
+		 *  url = {http://www.cacr.math.uwaterloo.ca/ecc/},
+		 *  publisher = {Springer-Verlag New York, Inc.}}
+		 */
+		unsigned int nbits;
+		int j;
+
+		if (mpi_cmp(scalar, ctx->p) >= 0)
+			nbits = mpi_get_nbits(scalar);
+		else
+			nbits = mpi_get_nbits(ctx->p);
+
+		mpi_set_ui(result->x, 0);
+		mpi_set_ui(result->y, 1);
+		mpi_set_ui(result->z, 1);
+		point_resize(point, ctx);
+
+		point_resize(result, ctx);
+		point_resize(point, ctx);
+
+		for (j = nbits-1; j >= 0; j--) {
+			mpi_ec_dup_point(result, result, ctx);
+			if (mpi_test_bit(scalar, j))
+				mpi_ec_add_points(result, result, point, ctx);
+		}
+		return;
+	} else if (ctx->model == MPI_EC_MONTGOMERY) {
+		unsigned int nbits;
+		int j;
+		struct gcry_mpi_point p1_, p2_;
+		MPI_POINT q1, q2, prd, sum;
+		unsigned long sw;
+		mpi_size_t rsize;
+		int scalar_copied = 0;
+
+		/* Compute scalar point multiplication with Montgomery Ladder.
+		 * Note that we don't use Y-coordinate in the points at all.
+		 * RESULT->Y will be filled by zero.
+		 */
+
+		nbits = mpi_get_nbits(scalar);
+		point_init(&p1);
+		point_init(&p2);
+		point_init(&p1_);
+		point_init(&p2_);
+		mpi_set_ui(p1.x, 1);
+		mpi_free(p2.x);
+		p2.x = mpi_copy(point->x);
+		mpi_set_ui(p2.z, 1);
+
+		point_resize(&p1, ctx);
+		point_resize(&p2, ctx);
+		point_resize(&p1_, ctx);
+		point_resize(&p2_, ctx);
+
+		mpi_resize(point->x, ctx->p->nlimbs);
+		point->x->nlimbs = ctx->p->nlimbs;
+
+		q1 = &p1;
+		q2 = &p2;
+		prd = &p1_;
+		sum = &p2_;
+
+		for (j = nbits-1; j >= 0; j--) {
+			MPI_POINT t;
+
+			sw = mpi_test_bit(scalar, j);
+			point_swap_cond(q1, q2, sw, ctx);
+			montgomery_ladder(prd, sum, q1, q2, point->x, ctx);
+			point_swap_cond(prd, sum, sw, ctx);
+			t = q1;  q1 = prd;  prd = t;
+			t = q2;  q2 = sum;  sum = t;
+		}
+
+		mpi_clear(result->y);
+		sw = (nbits & 1);
+		point_swap_cond(&p1, &p1_, sw, ctx);
+
+		rsize = p1.z->nlimbs;
+		MPN_NORMALIZE(p1.z->d, rsize);
+		if (rsize == 0) {
+			mpi_set_ui(result->x, 1);
+			mpi_set_ui(result->z, 0);
+		} else {
+			z1 = mpi_new(0);
+			ec_invm(z1, p1.z, ctx);
+			ec_mulm(result->x, p1.x, z1, ctx);
+			mpi_set_ui(result->z, 1);
+			mpi_free(z1);
+		}
+
+		point_free(&p1);
+		point_free(&p2);
+		point_free(&p1_);
+		point_free(&p2_);
+		if (scalar_copied)
+			mpi_free(scalar);
+		return;
+	}
+
+	x1 = mpi_alloc_like(ctx->p);
+	y1 = mpi_alloc_like(ctx->p);
+	h  = mpi_alloc_like(ctx->p);
+	k  = mpi_copy(scalar);
+	yy = mpi_copy(point->y);
+
+	if (mpi_has_sign(k)) {
+		k->sign = 0;
+		ec_invm(yy, yy, ctx);
+	}
+
+	if (!mpi_cmp_ui(point->z, 1)) {
+		mpi_set(x1, point->x);
+		mpi_set(y1, yy);
+	} else {
+		MPI z2, z3;
+
+		z2 = mpi_alloc_like(ctx->p);
+		z3 = mpi_alloc_like(ctx->p);
+		ec_mulm(z2, point->z, point->z, ctx);
+		ec_mulm(z3, point->z, z2, ctx);
+		ec_invm(z2, z2, ctx);
+		ec_mulm(x1, point->x, z2, ctx);
+		ec_invm(z3, z3, ctx);
+		ec_mulm(y1, yy, z3, ctx);
+		mpi_free(z2);
+		mpi_free(z3);
+	}
+	z1 = mpi_copy(mpi_const(MPI_C_ONE));
+
+	mpi_mul(h, k, mpi_const(MPI_C_THREE)); /* h = 3k */
+	loops = mpi_get_nbits(h);
+	if (loops < 2) {
+		/* If SCALAR is zero, the above mpi_mul sets H to zero and thus
+		 * LOOPs will be zero.  To avoid an underflow of I in the main
+		 * loop we set LOOP to 2 and the result to (0,0,0).
+		 */
+		loops = 2;
+		mpi_clear(result->x);
+		mpi_clear(result->y);
+		mpi_clear(result->z);
+	} else {
+		mpi_set(result->x, point->x);
+		mpi_set(result->y, yy);
+		mpi_set(result->z, point->z);
+	}
+	mpi_free(yy); yy = NULL;
+
+	p1.x = x1; x1 = NULL;
+	p1.y = y1; y1 = NULL;
+	p1.z = z1; z1 = NULL;
+	point_init(&p2);
+	point_init(&p1inv);
+
+	/* Invert point: y = p - y mod p  */
+	point_set(&p1inv, &p1);
+	ec_subm(p1inv.y, ctx->p, p1inv.y, ctx);
+
+	for (i = loops-2; i > 0; i--) {
+		mpi_ec_dup_point(result, result, ctx);
+		if (mpi_test_bit(h, i) == 1 && mpi_test_bit(k, i) == 0) {
+			point_set(&p2, result);
+			mpi_ec_add_points(result, &p2, &p1, ctx);
+		}
+		if (mpi_test_bit(h, i) == 0 && mpi_test_bit(k, i) == 1) {
+			point_set(&p2, result);
+			mpi_ec_add_points(result, &p2, &p1inv, ctx);
+		}
+	}
+
+	point_free(&p1);
+	point_free(&p2);
+	point_free(&p1inv);
+	mpi_free(h);
+	mpi_free(k);
+}
+EXPORT_SYMBOL_GPL(mpi_ec_mul_point);
+
+/* Return true if POINT is on the curve described by CTX.  */
+int mpi_ec_curve_point(MPI_POINT point, struct mpi_ec_ctx *ctx)
+{
+	int res = 0;
+	MPI x, y, w;
+
+	x = mpi_new(0);
+	y = mpi_new(0);
+	w = mpi_new(0);
+
+	/* Check that the point is in range.  This needs to be done here and
+	 * not after conversion to affine coordinates.
+	 */
+	if (mpi_cmpabs(point->x, ctx->p) >= 0)
+		goto leave;
+	if (mpi_cmpabs(point->y, ctx->p) >= 0)
+		goto leave;
+	if (mpi_cmpabs(point->z, ctx->p) >= 0)
+		goto leave;
+
+	switch (ctx->model) {
+	case MPI_EC_WEIERSTRASS:
+		{
+			MPI xxx;
+
+			if (mpi_ec_get_affine(x, y, point, ctx))
+				goto leave;
+
+			xxx = mpi_new(0);
+
+			/* y^2 == x^3 + a·x + b */
+			ec_pow2(y, y, ctx);
+
+			ec_pow3(xxx, x, ctx);
+			ec_mulm(w, ctx->a, x, ctx);
+			ec_addm(w, w, ctx->b, ctx);
+			ec_addm(w, w, xxx, ctx);
+
+			if (!mpi_cmp(y, w))
+				res = 1;
+
+			mpi_free(xxx);
+		}
+		break;
+
+	case MPI_EC_MONTGOMERY:
+		{
+#define xx y
+			/* With Montgomery curve, only X-coordinate is valid. */
+			if (mpi_ec_get_affine(x, NULL, point, ctx))
+				goto leave;
+
+			/* The equation is: b * y^2 == x^3 + a · x^2 + x */
+			/* We check if right hand is quadratic residue or not by
+			 * Euler's criterion.
+			 */
+			/* CTX->A has (a-2)/4 and CTX->B has b^-1 */
+			ec_mulm(w, ctx->a, mpi_const(MPI_C_FOUR), ctx);
+			ec_addm(w, w, mpi_const(MPI_C_TWO), ctx);
+			ec_mulm(w, w, x, ctx);
+			ec_pow2(xx, x, ctx);
+			ec_addm(w, w, xx, ctx);
+			ec_addm(w, w, mpi_const(MPI_C_ONE), ctx);
+			ec_mulm(w, w, x, ctx);
+			ec_mulm(w, w, ctx->b, ctx);
+#undef xx
+			/* Compute Euler's criterion: w^(p-1)/2 */
+#define p_minus1 y
+			ec_subm(p_minus1, ctx->p, mpi_const(MPI_C_ONE), ctx);
+			mpi_rshift(p_minus1, p_minus1, 1);
+			ec_powm(w, w, p_minus1, ctx);
+
+			res = !mpi_cmp_ui(w, 1);
+#undef p_minus1
+		}
+		break;
+
+	case MPI_EC_EDWARDS:
+		{
+			if (mpi_ec_get_affine(x, y, point, ctx))
+				goto leave;
+
+			mpi_resize(w, ctx->p->nlimbs);
+			w->nlimbs = ctx->p->nlimbs;
+
+			/* a · x^2 + y^2 - 1 - b · x^2 · y^2 == 0 */
+			ctx->pow2(x, x, ctx);
+			ctx->pow2(y, y, ctx);
+			if (ctx->dialect == ECC_DIALECT_ED25519)
+				ctx->subm(w, ctx->p, x, ctx);
+			else
+				ctx->mulm(w, ctx->a, x, ctx);
+			ctx->addm(w, w, y, ctx);
+			ctx->mulm(x, x, y, ctx);
+			ctx->mulm(x, x, ctx->b, ctx);
+			ctx->subm(w, w, x, ctx);
+			if (!mpi_cmp_ui(w, 1))
+				res = 1;
+		}
+		break;
+	}
+
+leave:
+	mpi_free(w);
+	mpi_free(x);
+	mpi_free(y);
+
+	return res;
+}
+EXPORT_SYMBOL_GPL(mpi_ec_curve_point);
-- 
cgit v1.2.3


From 254f84f559039b6d6f6e1035fd7645b42671ab48 Mon Sep 17 00:00:00 2001
From: Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
Date: Mon, 21 Sep 2020 00:21:01 +0800
Subject: X.509: support OSCCA certificate parse

The digital certificate format based on SM2 crypto algorithm as
specified in GM/T 0015-2012. It was published by State Encryption
Management Bureau, China.

This patch adds the OID object identifier defined by OSCCA. The
x509 certificate supports SM2-with-SM3 type certificate parsing.
It uses the standard elliptic curve public key, and the sm2
algorithm signs the hash generated by sm3.

Signed-off-by: Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
Tested-by: Xufeng Zhang <yunbo.xufeng@linux.alibaba.com>
Reviewed-by: Vitaly Chikunov <vt@altlinux.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/asymmetric_keys/x509_cert_parser.c | 27 ++++++++++++++++++++++-----
 include/linux/oid_registry.h              |  6 ++++++
 2 files changed, 28 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/crypto/asymmetric_keys/x509_cert_parser.c b/crypto/asymmetric_keys/x509_cert_parser.c
index 26ec20ef4899..52c9b455fc7d 100644
--- a/crypto/asymmetric_keys/x509_cert_parser.c
+++ b/crypto/asymmetric_keys/x509_cert_parser.c
@@ -234,6 +234,10 @@ int x509_note_pkey_algo(void *context, size_t hdrlen,
 	case OID_gost2012Signature512:
 		ctx->cert->sig->hash_algo = "streebog512";
 		goto ecrdsa;
+
+	case OID_SM2_with_SM3:
+		ctx->cert->sig->hash_algo = "sm3";
+		goto sm2;
 	}
 
 rsa_pkcs1:
@@ -246,6 +250,11 @@ ecrdsa:
 	ctx->cert->sig->encoding = "raw";
 	ctx->algo_oid = ctx->last_oid;
 	return 0;
+sm2:
+	ctx->cert->sig->pkey_algo = "sm2";
+	ctx->cert->sig->encoding = "raw";
+	ctx->algo_oid = ctx->last_oid;
+	return 0;
 }
 
 /*
@@ -266,7 +275,8 @@ int x509_note_signature(void *context, size_t hdrlen,
 	}
 
 	if (strcmp(ctx->cert->sig->pkey_algo, "rsa") == 0 ||
-	    strcmp(ctx->cert->sig->pkey_algo, "ecrdsa") == 0) {
+	    strcmp(ctx->cert->sig->pkey_algo, "ecrdsa") == 0 ||
+	    strcmp(ctx->cert->sig->pkey_algo, "sm2") == 0) {
 		/* Discard the BIT STRING metadata */
 		if (vlen < 1 || *(const u8 *)value != 0)
 			return -EBADMSG;
@@ -451,13 +461,20 @@ int x509_extract_key_data(void *context, size_t hdrlen,
 	struct x509_parse_context *ctx = context;
 
 	ctx->key_algo = ctx->last_oid;
-	if (ctx->last_oid == OID_rsaEncryption)
+	switch (ctx->last_oid) {
+	case OID_rsaEncryption:
 		ctx->cert->pub->pkey_algo = "rsa";
-	else if (ctx->last_oid == OID_gost2012PKey256 ||
-		 ctx->last_oid == OID_gost2012PKey512)
+		break;
+	case OID_gost2012PKey256:
+	case OID_gost2012PKey512:
 		ctx->cert->pub->pkey_algo = "ecrdsa";
-	else
+		break;
+	case OID_id_ecPublicKey:
+		ctx->cert->pub->pkey_algo = "sm2";
+		break;
+	default:
 		return -ENOPKG;
+	}
 
 	/* Discard the BIT STRING metadata */
 	if (vlen < 1 || *(const u8 *)value != 0)
diff --git a/include/linux/oid_registry.h b/include/linux/oid_registry.h
index 657d6bf2c064..4462ed2c18cd 100644
--- a/include/linux/oid_registry.h
+++ b/include/linux/oid_registry.h
@@ -107,6 +107,12 @@ enum OID {
 	OID_gostTC26Sign512B,		/* 1.2.643.7.1.2.1.2.2 */
 	OID_gostTC26Sign512C,		/* 1.2.643.7.1.2.1.2.3 */
 
+	/* OSCCA */
+	OID_sm2,			/* 1.2.156.10197.1.301 */
+	OID_sm3,			/* 1.2.156.10197.1.401 */
+	OID_SM2_with_SM3,		/* 1.2.156.10197.1.501 */
+	OID_sm3WithRSAEncryption,	/* 1.2.156.10197.1.504 */
+
 	OID__NR
 };
 
-- 
cgit v1.2.3


From 749626fa099085ca77f3ff05a8efcb3b87721724 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Tue, 1 Sep 2020 14:47:16 +0800
Subject: ACPI: Remove three unused inline functions

There is no callers in tree.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
[ rjw: Subject edit ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/acpi.h | 9 ---------
 1 file changed, 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 1e4cdc6c7ae2..7ce2235f99f9 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -977,8 +977,6 @@ int acpi_subsys_runtime_suspend(struct device *dev);
 int acpi_subsys_runtime_resume(struct device *dev);
 int acpi_dev_pm_attach(struct device *dev, bool power_on);
 #else
-static inline int acpi_dev_runtime_suspend(struct device *dev) { return 0; }
-static inline int acpi_dev_runtime_resume(struct device *dev) { return 0; }
 static inline int acpi_subsys_runtime_suspend(struct device *dev) { return 0; }
 static inline int acpi_subsys_runtime_resume(struct device *dev) { return 0; }
 static inline int acpi_dev_pm_attach(struct device *dev, bool power_on)
@@ -1216,13 +1214,6 @@ static inline int acpi_node_prop_get(const struct fwnode_handle *fwnode,
 	return -ENXIO;
 }
 
-static inline int acpi_dev_prop_get(const struct acpi_device *adev,
-				    const char *propname,
-				    void **valptr)
-{
-	return -ENXIO;
-}
-
 static inline int acpi_dev_prop_read_single(const struct acpi_device *adev,
 					    const char *propname,
 					    enum dev_prop_type proptype,
-- 
cgit v1.2.3


From 2a36ab717e8fe678d98f81c14a0b124712719840 Mon Sep 17 00:00:00 2001
From: Peter Oskolkov <posk@google.com>
Date: Wed, 23 Sep 2020 16:36:16 -0700
Subject: rseq/membarrier: Add MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ

This patchset is based on Google-internal RSEQ work done by Paul
Turner and Andrew Hunter.

When working with per-CPU RSEQ-based memory allocations, it is
sometimes important to make sure that a global memory location is no
longer accessed from RSEQ critical sections. For example, there can be
two per-CPU lists, one is "active" and accessed per-CPU, while another
one is inactive and worked on asynchronously "off CPU" (e.g.  garbage
collection is performed). Then at some point the two lists are
swapped, and a fast RCU-like mechanism is required to make sure that
the previously active list is no longer accessed.

This patch introduces such a mechanism: in short, membarrier() syscall
issues an IPI to a CPU, restarting a potentially active RSEQ critical
section on the CPU.

Signed-off-by: Peter Oskolkov <posk@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lkml.kernel.org/r/20200923233618.2572849-1-posk@google.com
---
 include/linux/sched/mm.h        |   3 +
 include/linux/syscalls.h        |   2 +-
 include/uapi/linux/membarrier.h |  26 ++++++++
 kernel/sched/membarrier.c       | 136 +++++++++++++++++++++++++++++++---------
 4 files changed, 136 insertions(+), 31 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index f889e332912f..15bfb06f2884 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -348,10 +348,13 @@ enum {
 	MEMBARRIER_STATE_GLOBAL_EXPEDITED			= (1U << 3),
 	MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY	= (1U << 4),
 	MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE		= (1U << 5),
+	MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY		= (1U << 6),
+	MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ			= (1U << 7),
 };
 
 enum {
 	MEMBARRIER_FLAG_SYNC_CORE	= (1U << 0),
+	MEMBARRIER_FLAG_RSEQ		= (1U << 1),
 };
 
 #ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 75ac7f8ae93c..06db09875aa4 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -974,7 +974,7 @@ asmlinkage long sys_execveat(int dfd, const char __user *filename,
 			const char __user *const __user *argv,
 			const char __user *const __user *envp, int flags);
 asmlinkage long sys_userfaultfd(int flags);
-asmlinkage long sys_membarrier(int cmd, int flags);
+asmlinkage long sys_membarrier(int cmd, unsigned int flags, int cpu_id);
 asmlinkage long sys_mlock2(unsigned long start, size_t len, int flags);
 asmlinkage long sys_copy_file_range(int fd_in, loff_t __user *off_in,
 				    int fd_out, loff_t __user *off_out,
diff --git a/include/uapi/linux/membarrier.h b/include/uapi/linux/membarrier.h
index 5891d7614c8c..737605897f36 100644
--- a/include/uapi/linux/membarrier.h
+++ b/include/uapi/linux/membarrier.h
@@ -114,6 +114,26 @@
  *                          If this command is not implemented by an
  *                          architecture, -EINVAL is returned.
  *                          Returns 0 on success.
+ * @MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ:
+ *                          Ensure the caller thread, upon return from
+ *                          system call, that all its running thread
+ *                          siblings have any currently running rseq
+ *                          critical sections restarted if @flags
+ *                          parameter is 0; if @flags parameter is
+ *                          MEMBARRIER_CMD_FLAG_CPU,
+ *                          then this operation is performed only
+ *                          on CPU indicated by @cpu_id. If this command is
+ *                          not implemented by an architecture, -EINVAL
+ *                          is returned. A process needs to register its
+ *                          intent to use the private expedited rseq
+ *                          command prior to using it, otherwise
+ *                          this command returns -EPERM.
+ * @MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ:
+ *                          Register the process intent to use
+ *                          MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ.
+ *                          If this command is not implemented by an
+ *                          architecture, -EINVAL is returned.
+ *                          Returns 0 on success.
  * @MEMBARRIER_CMD_SHARED:
  *                          Alias to MEMBARRIER_CMD_GLOBAL. Provided for
  *                          header backward compatibility.
@@ -131,9 +151,15 @@ enum membarrier_cmd {
 	MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED		= (1 << 4),
 	MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE		= (1 << 5),
 	MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE	= (1 << 6),
+	MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ			= (1 << 7),
+	MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ		= (1 << 8),
 
 	/* Alias for header backward compatibility. */
 	MEMBARRIER_CMD_SHARED			= MEMBARRIER_CMD_GLOBAL,
 };
 
+enum membarrier_cmd_flag {
+	MEMBARRIER_CMD_FLAG_CPU		= (1 << 0),
+};
+
 #endif /* _UAPI_LINUX_MEMBARRIER_H */
diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
index 168479a7d61b..e23e74d52db5 100644
--- a/kernel/sched/membarrier.c
+++ b/kernel/sched/membarrier.c
@@ -18,6 +18,14 @@
 #define MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK	0
 #endif
 
+#ifdef CONFIG_RSEQ
+#define MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ_BITMASK		\
+	(MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ			\
+	| MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ_BITMASK)
+#else
+#define MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ_BITMASK	0
+#endif
+
 #define MEMBARRIER_CMD_BITMASK						\
 	(MEMBARRIER_CMD_GLOBAL | MEMBARRIER_CMD_GLOBAL_EXPEDITED	\
 	| MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED			\
@@ -30,6 +38,11 @@ static void ipi_mb(void *info)
 	smp_mb();	/* IPIs should be serializing but paranoid. */
 }
 
+static void ipi_rseq(void *info)
+{
+	rseq_preempt(current);
+}
+
 static void ipi_sync_rq_state(void *info)
 {
 	struct mm_struct *mm = (struct mm_struct *) info;
@@ -129,19 +142,27 @@ static int membarrier_global_expedited(void)
 	return 0;
 }
 
-static int membarrier_private_expedited(int flags)
+static int membarrier_private_expedited(int flags, int cpu_id)
 {
-	int cpu;
 	cpumask_var_t tmpmask;
 	struct mm_struct *mm = current->mm;
+	smp_call_func_t ipi_func = ipi_mb;
 
-	if (flags & MEMBARRIER_FLAG_SYNC_CORE) {
+	if (flags == MEMBARRIER_FLAG_SYNC_CORE) {
 		if (!IS_ENABLED(CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE))
 			return -EINVAL;
 		if (!(atomic_read(&mm->membarrier_state) &
 		      MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY))
 			return -EPERM;
+	} else if (flags == MEMBARRIER_FLAG_RSEQ) {
+		if (!IS_ENABLED(CONFIG_RSEQ))
+			return -EINVAL;
+		if (!(atomic_read(&mm->membarrier_state) &
+		      MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY))
+			return -EPERM;
+		ipi_func = ipi_rseq;
 	} else {
+		WARN_ON_ONCE(flags);
 		if (!(atomic_read(&mm->membarrier_state) &
 		      MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY))
 			return -EPERM;
@@ -156,35 +177,59 @@ static int membarrier_private_expedited(int flags)
 	 */
 	smp_mb();	/* system call entry is not a mb. */
 
-	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
+	if (cpu_id < 0 && !zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
 		return -ENOMEM;
 
 	cpus_read_lock();
-	rcu_read_lock();
-	for_each_online_cpu(cpu) {
+
+	if (cpu_id >= 0) {
 		struct task_struct *p;
 
-		/*
-		 * Skipping the current CPU is OK even through we can be
-		 * migrated at any point. The current CPU, at the point
-		 * where we read raw_smp_processor_id(), is ensured to
-		 * be in program order with respect to the caller
-		 * thread. Therefore, we can skip this CPU from the
-		 * iteration.
-		 */
-		if (cpu == raw_smp_processor_id())
-			continue;
-		p = rcu_dereference(cpu_rq(cpu)->curr);
-		if (p && p->mm == mm)
-			__cpumask_set_cpu(cpu, tmpmask);
+		if (cpu_id >= nr_cpu_ids || !cpu_online(cpu_id))
+			goto out;
+		if (cpu_id == raw_smp_processor_id())
+			goto out;
+		rcu_read_lock();
+		p = rcu_dereference(cpu_rq(cpu_id)->curr);
+		if (!p || p->mm != mm) {
+			rcu_read_unlock();
+			goto out;
+		}
+		rcu_read_unlock();
+	} else {
+		int cpu;
+
+		rcu_read_lock();
+		for_each_online_cpu(cpu) {
+			struct task_struct *p;
+
+			/*
+			 * Skipping the current CPU is OK even through we can be
+			 * migrated at any point. The current CPU, at the point
+			 * where we read raw_smp_processor_id(), is ensured to
+			 * be in program order with respect to the caller
+			 * thread. Therefore, we can skip this CPU from the
+			 * iteration.
+			 */
+			if (cpu == raw_smp_processor_id())
+				continue;
+			p = rcu_dereference(cpu_rq(cpu)->curr);
+			if (p && p->mm == mm)
+				__cpumask_set_cpu(cpu, tmpmask);
+		}
+		rcu_read_unlock();
 	}
-	rcu_read_unlock();
 
 	preempt_disable();
-	smp_call_function_many(tmpmask, ipi_mb, NULL, 1);
+	if (cpu_id >= 0)
+		smp_call_function_single(cpu_id, ipi_func, NULL, 1);
+	else
+		smp_call_function_many(tmpmask, ipi_func, NULL, 1);
 	preempt_enable();
 
-	free_cpumask_var(tmpmask);
+out:
+	if (cpu_id < 0)
+		free_cpumask_var(tmpmask);
 	cpus_read_unlock();
 
 	/*
@@ -283,11 +328,18 @@ static int membarrier_register_private_expedited(int flags)
 	    set_state = MEMBARRIER_STATE_PRIVATE_EXPEDITED,
 	    ret;
 
-	if (flags & MEMBARRIER_FLAG_SYNC_CORE) {
+	if (flags == MEMBARRIER_FLAG_SYNC_CORE) {
 		if (!IS_ENABLED(CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE))
 			return -EINVAL;
 		ready_state =
 			MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY;
+	} else if (flags == MEMBARRIER_FLAG_RSEQ) {
+		if (!IS_ENABLED(CONFIG_RSEQ))
+			return -EINVAL;
+		ready_state =
+			MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY;
+	} else {
+		WARN_ON_ONCE(flags);
 	}
 
 	/*
@@ -299,6 +351,8 @@ static int membarrier_register_private_expedited(int flags)
 		return 0;
 	if (flags & MEMBARRIER_FLAG_SYNC_CORE)
 		set_state |= MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE;
+	if (flags & MEMBARRIER_FLAG_RSEQ)
+		set_state |= MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ;
 	atomic_or(set_state, &mm->membarrier_state);
 	ret = sync_runqueues_membarrier_state(mm);
 	if (ret)
@@ -310,8 +364,15 @@ static int membarrier_register_private_expedited(int flags)
 
 /**
  * sys_membarrier - issue memory barriers on a set of threads
- * @cmd:   Takes command values defined in enum membarrier_cmd.
- * @flags: Currently needs to be 0. For future extensions.
+ * @cmd:    Takes command values defined in enum membarrier_cmd.
+ * @flags:  Currently needs to be 0 for all commands other than
+ *          MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ: in the latter
+ *          case it can be MEMBARRIER_CMD_FLAG_CPU, indicating that @cpu_id
+ *          contains the CPU on which to interrupt (= restart)
+ *          the RSEQ critical section.
+ * @cpu_id: if @flags == MEMBARRIER_CMD_FLAG_CPU, indicates the cpu on which
+ *          RSEQ CS should be interrupted (@cmd must be
+ *          MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ).
  *
  * If this system call is not implemented, -ENOSYS is returned. If the
  * command specified does not exist, not available on the running
@@ -337,10 +398,21 @@ static int membarrier_register_private_expedited(int flags)
  *        smp_mb()           X           O            O
  *        sys_membarrier()   O           O            O
  */
-SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)
+SYSCALL_DEFINE3(membarrier, int, cmd, unsigned int, flags, int, cpu_id)
 {
-	if (unlikely(flags))
-		return -EINVAL;
+	switch (cmd) {
+	case MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ:
+		if (unlikely(flags && flags != MEMBARRIER_CMD_FLAG_CPU))
+			return -EINVAL;
+		break;
+	default:
+		if (unlikely(flags))
+			return -EINVAL;
+	}
+
+	if (!(flags & MEMBARRIER_CMD_FLAG_CPU))
+		cpu_id = -1;
+
 	switch (cmd) {
 	case MEMBARRIER_CMD_QUERY:
 	{
@@ -362,13 +434,17 @@ SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)
 	case MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED:
 		return membarrier_register_global_expedited();
 	case MEMBARRIER_CMD_PRIVATE_EXPEDITED:
-		return membarrier_private_expedited(0);
+		return membarrier_private_expedited(0, cpu_id);
 	case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED:
 		return membarrier_register_private_expedited(0);
 	case MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE:
-		return membarrier_private_expedited(MEMBARRIER_FLAG_SYNC_CORE);
+		return membarrier_private_expedited(MEMBARRIER_FLAG_SYNC_CORE, cpu_id);
 	case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE:
 		return membarrier_register_private_expedited(MEMBARRIER_FLAG_SYNC_CORE);
+	case MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ:
+		return membarrier_private_expedited(MEMBARRIER_FLAG_RSEQ, cpu_id);
+	case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ:
+		return membarrier_register_private_expedited(MEMBARRIER_FLAG_RSEQ);
 	default:
 		return -EINVAL;
 	}
-- 
cgit v1.2.3


From fa01b1e9733fd59ecb8b5b6d85dfb481d2025fbf Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 3 Sep 2020 07:40:57 +0200
Subject: block: add a bdev_is_partition helper

Add a littler helper to make the somewhat arcane bd_contains checks a
little more obvious.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-lib.c                 | 2 +-
 block/ioctl.c                   | 4 ++--
 block/scsi_ioctl.c              | 2 +-
 drivers/ide/ide-ioctls.c        | 4 ++--
 drivers/md/dm-table.c           | 2 +-
 drivers/mmc/core/block.c        | 2 +-
 drivers/s390/block/dasd_ioctl.c | 8 ++++----
 fs/nfsd/blocklayout.c           | 4 ++--
 include/linux/blkdev.h          | 9 +++++++--
 kernel/trace/blktrace.c         | 2 +-
 10 files changed, 22 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-lib.c b/block/blk-lib.c
index 0d1811e57ac7..e90614fd8d6a 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -64,7 +64,7 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		return -EINVAL;
 
 	/* In case the discard request is in a partition */
-	if (bdev->bd_partno)
+	if (bdev_is_partition(bdev))
 		part_offset = bdev->bd_part->start_sect;
 
 	while (nr_sects) {
diff --git a/block/ioctl.c b/block/ioctl.c
index 06262c28f0c6..3fbc382eb926 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -23,7 +23,7 @@ static int blkpg_do_ioctl(struct block_device *bdev,
 		return -EACCES;
 	if (copy_from_user(&p, upart, sizeof(struct blkpg_partition)))
 		return -EFAULT;
-	if (bdev != bdev->bd_contains)
+	if (bdev_is_partition(bdev))
 		return -EINVAL;
 
 	if (p.pno <= 0)
@@ -94,7 +94,7 @@ static int blkdev_reread_part(struct block_device *bdev)
 {
 	int ret;
 
-	if (!disk_part_scan_enabled(bdev->bd_disk) || bdev != bdev->bd_contains)
+	if (!disk_part_scan_enabled(bdev->bd_disk) || bdev_is_partition(bdev))
 		return -EINVAL;
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 4421e61c1af1..d4abd1ed5a2d 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -852,7 +852,7 @@ EXPORT_SYMBOL(scsi_cmd_ioctl);
 
 int scsi_verify_blk_ioctl(struct block_device *bd, unsigned int cmd)
 {
-	if (bd && bd == bd->bd_contains)
+	if (bd && !bdev_is_partition(bd))
 		return 0;
 
 	if (capable(CAP_SYS_RAWIO))
diff --git a/drivers/ide/ide-ioctls.c b/drivers/ide/ide-ioctls.c
index 09491098047b..58994da10c06 100644
--- a/drivers/ide/ide-ioctls.c
+++ b/drivers/ide/ide-ioctls.c
@@ -49,7 +49,7 @@ read_val:
 	return err >= 0 ? put_user_long(err, arg) : err;
 
 set_val:
-	if (bdev != bdev->bd_contains)
+	if (bdev_is_partition(bdev))
 		err = -EINVAL;
 	else {
 		if (!capable(CAP_SYS_ADMIN))
@@ -257,7 +257,7 @@ int generic_ide_ioctl(ide_drive_t *drive, struct block_device *bdev,
 	switch (cmd) {
 	case HDIO_OBSOLETE_IDENTITY:
 	case HDIO_GET_IDENTITY:
-		if (bdev != bdev->bd_contains)
+		if (bdev_is_partition(bdev))
 			return -EINVAL;
 		return ide_get_identity_ioctl(drive, cmd, argp);
 	case HDIO_GET_NICE:
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 405d7cf10eb9..12d909044c10 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -903,7 +903,7 @@ static int device_is_rq_stackable(struct dm_target *ti, struct dm_dev *dev,
 	struct request_queue *q = bdev_get_queue(bdev);
 
 	/* request-based cannot stack on partitions! */
-	if (bdev != bdev->bd_contains)
+	if (bdev_is_partition(bdev))
 		return false;
 
 	return queue_is_mq(q);
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index fa313b634135..8d3df0be0355 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -723,7 +723,7 @@ static int mmc_blk_check_blkdev(struct block_device *bdev)
 	 * whole block device, not on a partition.  This prevents overspray
 	 * between sibling partitions.
 	 */
-	if ((!capable(CAP_SYS_RAWIO)) || (bdev != bdev->bd_contains))
+	if (!capable(CAP_SYS_RAWIO) || bdev_is_partition(bdev))
 		return -EPERM;
 	return 0;
 }
diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c
index faaf5596e31c..cb6427fb9f3d 100644
--- a/drivers/s390/block/dasd_ioctl.c
+++ b/drivers/s390/block/dasd_ioctl.c
@@ -277,7 +277,7 @@ dasd_ioctl_format(struct block_device *bdev, void __user *argp)
 		dasd_put_device(base);
 		return -EFAULT;
 	}
-	if (bdev != bdev->bd_contains) {
+	if (bdev_is_partition(bdev)) {
 		pr_warn("%s: The specified DASD is a partition and cannot be formatted\n",
 			dev_name(&base->cdev->dev));
 		dasd_put_device(base);
@@ -304,7 +304,7 @@ static int dasd_ioctl_check_format(struct block_device *bdev, void __user *argp)
 	base = dasd_device_from_gendisk(bdev->bd_disk);
 	if (!base)
 		return -ENODEV;
-	if (bdev != bdev->bd_contains) {
+	if (bdev_is_partition(bdev)) {
 		pr_warn("%s: The specified DASD is a partition and cannot be checked\n",
 			dev_name(&base->cdev->dev));
 		rc = -EINVAL;
@@ -362,7 +362,7 @@ static int dasd_ioctl_release_space(struct block_device *bdev, void __user *argp
 		rc = -EROFS;
 		goto out_err;
 	}
-	if (bdev != bdev->bd_contains) {
+	if (bdev_is_partition(bdev)) {
 		pr_warn("%s: The specified DASD is a partition and tracks cannot be released\n",
 			dev_name(&base->cdev->dev));
 		rc = -EINVAL;
@@ -540,7 +540,7 @@ dasd_ioctl_set_ro(struct block_device *bdev, void __user *argp)
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
-	if (bdev != bdev->bd_contains)
+	if (bdev_is_partition(bdev))
 		// ro setting is not allowed for partitions
 		return -EINVAL;
 	if (get_user(intval, (int __user *)argp))
diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
index 311e5ce80cfc..a07c39c94bbd 100644
--- a/fs/nfsd/blocklayout.c
+++ b/fs/nfsd/blocklayout.c
@@ -170,7 +170,7 @@ nfsd4_block_proc_getdeviceinfo(struct super_block *sb,
 		struct nfs4_client *clp,
 		struct nfsd4_getdeviceinfo *gdp)
 {
-	if (sb->s_bdev != sb->s_bdev->bd_contains)
+	if (bdev_is_partition(sb->s_bdev))
 		return nfserr_inval;
 	return nfserrno(nfsd4_block_get_device_info_simple(sb, gdp));
 }
@@ -382,7 +382,7 @@ nfsd4_scsi_proc_getdeviceinfo(struct super_block *sb,
 		struct nfs4_client *clp,
 		struct nfsd4_getdeviceinfo *gdp)
 {
-	if (sb->s_bdev != sb->s_bdev->bd_contains)
+	if (bdev_is_partition(sb->s_bdev))
 		return nfserr_inval;
 	return nfserrno(nfsd4_block_get_device_info_scsi(sb, clp, gdp));
 }
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 8e77f12de522..33f283885ba5 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1353,6 +1353,11 @@ static inline int sb_issue_zeroout(struct super_block *sb, sector_t block,
 
 extern int blk_verify_command(unsigned char *cmd, fmode_t mode);
 
+static inline bool bdev_is_partition(struct block_device *bdev)
+{
+	return bdev->bd_partno;
+}
+
 enum blk_default_limits {
 	BLK_MAX_SEGMENTS	= 128,
 	BLK_SAFE_MAX_SECTORS	= 255,
@@ -1469,7 +1474,7 @@ static inline int bdev_alignment_offset(struct block_device *bdev)
 
 	if (q->limits.misaligned)
 		return -1;
-	if (bdev != bdev->bd_contains)
+	if (bdev_is_partition(bdev))
 		return queue_limit_alignment_offset(&q->limits,
 				bdev->bd_part->start_sect);
 	return q->limits.alignment_offset;
@@ -1510,7 +1515,7 @@ static inline int bdev_discard_alignment(struct block_device *bdev)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
 
-	if (bdev != bdev->bd_contains)
+	if (bdev_is_partition(bdev))
 		return queue_limit_discard_alignment(&q->limits,
 				bdev->bd_part->start_sect);
 	return q->limits.discard_alignment;
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index c0887f32f647..ec874ea04092 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -527,7 +527,7 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	 * and scsi-generic block devices we create a temporary new debugfs
 	 * directory that will be removed once the trace ends.
 	 */
-	if (bdev && bdev == bdev->bd_contains)
+	if (bdev && !bdev_is_partition(bdev))
 		dir = q->debugfs_dir;
 	else
 		bt->dir = dir = debugfs_create_dir(buts->name, blk_debugfs_root);
-- 
cgit v1.2.3


From 021a24460dc28e7412aecfae89f60e1847e685c0 Mon Sep 17 00:00:00 2001
From: Mike Snitzer <snitzer@redhat.com>
Date: Wed, 23 Sep 2020 16:06:51 -0400
Subject: block: add QUEUE_FLAG_NOWAIT

Add QUEUE_FLAG_NOWAIT to allow a block device to advertise support for
REQ_NOWAIT. Bio-based devices may set QUEUE_FLAG_NOWAIT where
applicable.

Update QUEUE_FLAG_MQ_DEFAULT to include QUEUE_FLAG_NOWAIT.  Also
update submit_bio_checks() to verify it is set for REQ_NOWAIT bios.

Reported-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c       | 4 ++--
 include/linux/blkdev.h | 7 +++++--
 2 files changed, 7 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-core.c b/block/blk-core.c
index 1cc4fa6bc7fe..4884f1e7451b 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -814,9 +814,9 @@ static noinline_for_stack bool submit_bio_checks(struct bio *bio)
 
 	/*
 	 * For a REQ_NOWAIT based request, return -EOPNOTSUPP
-	 * if queue is not a request based queue.
+	 * if queue does not support NOWAIT.
 	 */
-	if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_mq(q))
+	if ((bio->bi_opf & REQ_NOWAIT) && !blk_queue_nowait(q))
 		goto not_supported;
 
 	if (should_fail_bio(bio))
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 33f283885ba5..d5a3e1a4c2f7 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -619,10 +619,12 @@ struct request_queue {
 #define QUEUE_FLAG_PCI_P2PDMA	25	/* device supports PCI p2p requests */
 #define QUEUE_FLAG_ZONE_RESETALL 26	/* supports Zone Reset All */
 #define QUEUE_FLAG_RQ_ALLOC_TIME 27	/* record rq->alloc_time_ns */
-#define QUEUE_FLAG_HCTX_ACTIVE 28	/* at least one blk-mq hctx is active */
+#define QUEUE_FLAG_HCTX_ACTIVE	28	/* at least one blk-mq hctx is active */
+#define QUEUE_FLAG_NOWAIT       29	/* device supports NOWAIT */
 
 #define QUEUE_FLAG_MQ_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
-				 (1 << QUEUE_FLAG_SAME_COMP))
+				 (1 << QUEUE_FLAG_SAME_COMP) |		\
+				 (1 << QUEUE_FLAG_NOWAIT))
 
 void blk_queue_flag_set(unsigned int flag, struct request_queue *q);
 void blk_queue_flag_clear(unsigned int flag, struct request_queue *q);
@@ -664,6 +666,7 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
 #define blk_queue_pm_only(q)	atomic_read(&(q)->pm_only)
 #define blk_queue_fua(q)	test_bit(QUEUE_FLAG_FUA, &(q)->queue_flags)
 #define blk_queue_registered(q)	test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags)
+#define blk_queue_nowait(q)	test_bit(QUEUE_FLAG_NOWAIT, &(q)->queue_flags)
 
 extern void blk_set_pm_only(struct request_queue *q);
 extern void blk_clear_pm_only(struct request_queue *q);
-- 
cgit v1.2.3


From 6abc49468eeaad2dd481779906aaa29605139087 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Date: Wed, 23 Sep 2020 16:06:52 -0400
Subject: dm: add support for REQ_NOWAIT and enable it for linear target

Add DM target feature flag DM_TARGET_NOWAIT which advertises that
target works with REQ_NOWAIT bios.

Add dm_table_supports_nowait() and update dm_table_set_restrictions()
to set/clear QUEUE_FLAG_NOWAIT accordingly.

Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/dm-linear.c        |  5 +++--
 drivers/md/dm-table.c         | 32 ++++++++++++++++++++++++++++++++
 drivers/md/dm.c               |  4 +++-
 include/linux/device-mapper.h |  6 ++++++
 4 files changed, 44 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index e1db43446327..00774b5d7668 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -228,10 +228,11 @@ static struct target_type linear_target = {
 	.name   = "linear",
 	.version = {1, 4, 0},
 #ifdef CONFIG_BLK_DEV_ZONED
-	.features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_ZONED_HM,
+	.features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_NOWAIT |
+		    DM_TARGET_ZONED_HM,
 	.report_zones = linear_report_zones,
 #else
-	.features = DM_TARGET_PASSES_INTEGRITY,
+	.features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_NOWAIT,
 #endif
 	.module = THIS_MODULE,
 	.ctr    = linear_ctr,
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 12d909044c10..07c319e98581 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1748,6 +1748,33 @@ static bool dm_table_supports_write_zeroes(struct dm_table *t)
 	return true;
 }
 
+static int device_not_nowait_capable(struct dm_target *ti, struct dm_dev *dev,
+				     sector_t start, sector_t len, void *data)
+{
+	struct request_queue *q = bdev_get_queue(dev->bdev);
+
+	return q && !blk_queue_nowait(q);
+}
+
+static bool dm_table_supports_nowait(struct dm_table *t)
+{
+	struct dm_target *ti;
+	unsigned i = 0;
+
+	while (i < dm_table_get_num_targets(t)) {
+		ti = dm_table_get_target(t, i++);
+
+		if (!dm_target_supports_nowait(ti->type))
+			return false;
+
+		if (!ti->type->iterate_devices ||
+		    ti->type->iterate_devices(ti, device_not_nowait_capable, NULL))
+			return false;
+	}
+
+	return true;
+}
+
 static int device_not_discard_capable(struct dm_target *ti, struct dm_dev *dev,
 				      sector_t start, sector_t len, void *data)
 {
@@ -1850,6 +1877,11 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	 */
 	q->limits = *limits;
 
+	if (dm_table_supports_nowait(t))
+		blk_queue_flag_set(QUEUE_FLAG_NOWAIT, q);
+	else
+		blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, q);
+
 	if (!dm_table_supports_discards(t)) {
 		blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q);
 		/* Must also clear discard limits... */
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 3dedd9cc4fb6..59b0687f9235 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1802,7 +1802,9 @@ static blk_qc_t dm_submit_bio(struct bio *bio)
 	if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags))) {
 		dm_put_live_table(md, srcu_idx);
 
-		if (!(bio->bi_opf & REQ_RAHEAD))
+		if (bio->bi_opf & REQ_NOWAIT)
+			bio_wouldblock_error(bio);
+		else if (!(bio->bi_opf & REQ_RAHEAD))
 			queue_io(md, bio);
 		else
 			bio_io_error(bio);
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 93096e524e43..d6f8d4ba8d48 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -252,6 +252,12 @@ struct target_type {
 #define DM_TARGET_ZONED_HM		0x00000040
 #define dm_target_supports_zoned_hm(type) ((type)->features & DM_TARGET_ZONED_HM)
 
+/*
+ * A target handles REQ_NOWAIT
+ */
+#define DM_TARGET_NOWAIT		0x00000080
+#define dm_target_supports_nowait(type) ((type)->features & DM_TARGET_NOWAIT)
+
 struct dm_target {
 	struct dm_table *table;
 	struct target_type *type;
-- 
cgit v1.2.3


From 34d8f7a4627ca59ba915c7ea44fe9d9123875712 Mon Sep 17 00:00:00 2001
From: Chunfeng Yun <chunfeng.yun@mediatek.com>
Date: Mon, 21 Sep 2020 14:13:35 +0800
Subject: iopoll: update kerneldoc of read_poll_timeout_atomic()

Arguments description of read_poll_timeout_atomic() is out of date,
update it.

Cc: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Chunfeng Yun <chunfeng.yun@mediatek.com>
Link: https://lore.kernel.org/r/1600668815-12135-11-git-send-email-chunfeng.yun@mediatek.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/iopoll.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/iopoll.h b/include/linux/iopoll.h
index bc89ac625f26..2c8860e406bd 100644
--- a/include/linux/iopoll.h
+++ b/include/linux/iopoll.h
@@ -60,8 +60,7 @@
 /**
  * read_poll_timeout_atomic - Periodically poll an address until a condition is
  * 				met or a timeout occurs
- * @op: accessor function (takes @addr as its only argument)
- * @addr: Address to poll
+ * @op: accessor function (takes @args as its arguments)
  * @val: Variable to read the value into
  * @cond: Break condition (usually involving @val)
  * @delay_us: Time to udelay between reads in us (0 tight-loops).  Should
@@ -69,6 +68,7 @@
  *            Documentation/timers/timers-howto.rst).
  * @timeout_us: Timeout in us, 0 means never timeout
  * @delay_before_read: if it is true, delay @delay_us before read.
+ * @args: arguments for @op poll
  *
  * Returns 0 on success and -ETIMEDOUT upon a timeout. In either
  * case, the last read value at @args is stored in @val.
-- 
cgit v1.2.3


From ddd1198e3e0935066d6e309180d49f64ef4fa702 Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Wed, 23 Sep 2020 15:43:42 +0200
Subject: USB: correct API of usb_control_msg_send/recv

They need to specify how memory is to be allocated,
as control messages need to work in contexts that require GFP_NOIO.

Signed-off-by: Oliver Neukum <oneukum@suse.com>
Link: https://lore.kernel.org/r/20200923134348.23862-9-oneukum@suse.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/message.c | 25 ++++++++++++++++---------
 include/linux/usb.h        |  6 ++++--
 2 files changed, 20 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c
index 1580694e3b95..f4107b9e8c38 100644
--- a/drivers/usb/core/message.c
+++ b/drivers/usb/core/message.c
@@ -174,6 +174,7 @@ EXPORT_SYMBOL_GPL(usb_control_msg);
  * @size: length in bytes of the data to send
  * @timeout: time in msecs to wait for the message to complete before timing
  *	out (if 0 the wait is forever)
+ * @memflags: the flags for memory allocation for buffers
  *
  * Context: !in_interrupt ()
  *
@@ -196,7 +197,8 @@ EXPORT_SYMBOL_GPL(usb_control_msg);
  */
 int usb_control_msg_send(struct usb_device *dev, __u8 endpoint, __u8 request,
 			 __u8 requesttype, __u16 value, __u16 index,
-			 const void *driver_data, __u16 size, int timeout)
+			 const void *driver_data, __u16 size, int timeout,
+			 gfp_t memflags)
 {
 	unsigned int pipe = usb_sndctrlpipe(dev, endpoint);
 	int ret;
@@ -206,7 +208,7 @@ int usb_control_msg_send(struct usb_device *dev, __u8 endpoint, __u8 request,
 		return -EINVAL;
 
 	if (size) {
-		data = kmemdup(driver_data, size, GFP_KERNEL);
+		data = kmemdup(driver_data, size, memflags);
 		if (!data)
 			return -ENOMEM;
 	}
@@ -235,6 +237,7 @@ EXPORT_SYMBOL_GPL(usb_control_msg_send);
  * @size: length in bytes of the data to be received
  * @timeout: time in msecs to wait for the message to complete before timing
  *	out (if 0 the wait is forever)
+ * @memflags: the flags for memory allocation for buffers
  *
  * Context: !in_interrupt ()
  *
@@ -263,7 +266,8 @@ EXPORT_SYMBOL_GPL(usb_control_msg_send);
  */
 int usb_control_msg_recv(struct usb_device *dev, __u8 endpoint, __u8 request,
 			 __u8 requesttype, __u16 value, __u16 index,
-			 void *driver_data, __u16 size, int timeout)
+			 void *driver_data, __u16 size, int timeout,
+			 gfp_t memflags)
 {
 	unsigned int pipe = usb_rcvctrlpipe(dev, endpoint);
 	int ret;
@@ -272,7 +276,7 @@ int usb_control_msg_recv(struct usb_device *dev, __u8 endpoint, __u8 request,
 	if (!size || !driver_data || usb_pipe_type_check(dev, pipe))
 		return -EINVAL;
 
-	data = kmalloc(size, GFP_KERNEL);
+	data = kmalloc(size, memflags);
 	if (!data)
 		return -ENOMEM;
 
@@ -1085,7 +1089,8 @@ int usb_set_isoch_delay(struct usb_device *dev)
 			USB_REQ_SET_ISOCH_DELAY,
 			USB_DIR_OUT | USB_TYPE_STANDARD | USB_RECIP_DEVICE,
 			dev->hub_delay, 0, NULL, 0,
-			USB_CTRL_SET_TIMEOUT);
+			USB_CTRL_SET_TIMEOUT,
+			GFP_NOIO);
 }
 
 /**
@@ -1206,7 +1211,7 @@ int usb_clear_halt(struct usb_device *dev, int pipe)
 	result = usb_control_msg_send(dev, 0,
 				      USB_REQ_CLEAR_FEATURE, USB_RECIP_ENDPOINT,
 				      USB_ENDPOINT_HALT, endp, NULL, 0,
-				      USB_CTRL_SET_TIMEOUT);
+				      USB_CTRL_SET_TIMEOUT, GFP_NOIO);
 
 	/* don't un-halt or force to DATA0 except on success */
 	if (result)
@@ -1574,7 +1579,8 @@ int usb_set_interface(struct usb_device *dev, int interface, int alternate)
 		ret = usb_control_msg_send(dev, 0,
 					   USB_REQ_SET_INTERFACE,
 					   USB_RECIP_INTERFACE, alternate,
-					   interface, NULL, 0, 5000);
+					   interface, NULL, 0, 5000,
+					   GFP_NOIO);
 
 	/* 9.4.10 says devices don't need this and are free to STALL the
 	 * request if the interface only has one alternate setting.
@@ -1710,7 +1716,8 @@ int usb_reset_configuration(struct usb_device *dev)
 	}
 	retval = usb_control_msg_send(dev, 0, USB_REQ_SET_CONFIGURATION, 0,
 				      config->desc.bConfigurationValue, 0,
-				      NULL, 0, USB_CTRL_SET_TIMEOUT);
+				      NULL, 0, USB_CTRL_SET_TIMEOUT,
+				      GFP_NOIO);
 	if (retval) {
 		usb_hcd_alloc_bandwidth(dev, NULL, NULL, NULL);
 		usb_enable_lpm(dev);
@@ -2098,7 +2105,7 @@ free_interfaces:
 
 	ret = usb_control_msg_send(dev, 0, USB_REQ_SET_CONFIGURATION, 0,
 				   configuration, 0, NULL, 0,
-				   USB_CTRL_SET_TIMEOUT);
+				   USB_CTRL_SET_TIMEOUT, GFP_NOIO);
 	if (ret && cp) {
 		/*
 		 * All the old state is gone, so what else can we do?
diff --git a/include/linux/usb.h b/include/linux/usb.h
index a5460f08126e..7d72c4e0713c 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1804,10 +1804,12 @@ extern int usb_bulk_msg(struct usb_device *usb_dev, unsigned int pipe,
 /* wrappers around usb_control_msg() for the most common standard requests */
 int usb_control_msg_send(struct usb_device *dev, __u8 endpoint, __u8 request,
 			 __u8 requesttype, __u16 value, __u16 index,
-			 const void *data, __u16 size, int timeout);
+			 const void *data, __u16 size, int timeout,
+			 gfp_t memflags);
 int usb_control_msg_recv(struct usb_device *dev, __u8 endpoint, __u8 request,
 			 __u8 requesttype, __u16 value, __u16 index,
-			 void *data, __u16 size, int timeout);
+			 void *data, __u16 size, int timeout,
+			 gfp_t memflags);
 extern int usb_get_descriptor(struct usb_device *dev, unsigned char desctype,
 	unsigned char descindex, void *buf, int size);
 extern int usb_get_status(struct usb_device *dev,
-- 
cgit v1.2.3


From 5f6e560c2dd5be3ae446f20ae97263cbfa309630 Mon Sep 17 00:00:00 2001
From: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Date: Tue, 7 Jul 2020 23:45:07 +0800
Subject: soc: mediatek: cmdq: add write_s function

add write_s function in cmdq helper functions which
writes value contains in internal register to address
with large dma access support.

Signed-off-by: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Link: https://lore.kernel.org/r/1594136714-11650-3-git-send-email-dennis-yc.hsieh@mediatek.com
Signed-off-by: Matthias Brugger <matthias.bgg@gmail.com>
---
 drivers/soc/mediatek/mtk-cmdq-helper.c   | 19 +++++++++++++++++++
 include/linux/mailbox/mtk-cmdq-mailbox.h |  1 +
 include/linux/soc/mediatek/mtk-cmdq.h    | 19 +++++++++++++++++++
 3 files changed, 39 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/soc/mediatek/mtk-cmdq-helper.c b/drivers/soc/mediatek/mtk-cmdq-helper.c
index 9faf78fbed3a..880349b3f16c 100644
--- a/drivers/soc/mediatek/mtk-cmdq-helper.c
+++ b/drivers/soc/mediatek/mtk-cmdq-helper.c
@@ -18,6 +18,10 @@ struct cmdq_instruction {
 	union {
 		u32 value;
 		u32 mask;
+		struct {
+			u16 arg_c;
+			u16 src_reg;
+		};
 	};
 	union {
 		u16 offset;
@@ -223,6 +227,21 @@ int cmdq_pkt_write_mask(struct cmdq_pkt *pkt, u8 subsys,
 }
 EXPORT_SYMBOL(cmdq_pkt_write_mask);
 
+int cmdq_pkt_write_s(struct cmdq_pkt *pkt, u16 high_addr_reg_idx,
+		     u16 addr_low, u16 src_reg_idx)
+{
+	struct cmdq_instruction inst = {};
+
+	inst.op = CMDQ_CODE_WRITE_S;
+	inst.src_t = CMDQ_REG_TYPE;
+	inst.sop = high_addr_reg_idx;
+	inst.offset = addr_low;
+	inst.src_reg = src_reg_idx;
+
+	return cmdq_pkt_append_command(pkt, inst);
+}
+EXPORT_SYMBOL(cmdq_pkt_write_s);
+
 int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event)
 {
 	struct cmdq_instruction inst = { {0} };
diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h
index 05eea1aef5aa..1f76cfedb16d 100644
--- a/include/linux/mailbox/mtk-cmdq-mailbox.h
+++ b/include/linux/mailbox/mtk-cmdq-mailbox.h
@@ -60,6 +60,7 @@ enum cmdq_code {
 	CMDQ_CODE_JUMP = 0x10,
 	CMDQ_CODE_WFE = 0x20,
 	CMDQ_CODE_EOC = 0x40,
+	CMDQ_CODE_WRITE_S = 0x90,
 	CMDQ_CODE_LOGIC = 0xa0,
 };
 
diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h
index 2249ecaf77e4..9b0c57a0063d 100644
--- a/include/linux/soc/mediatek/mtk-cmdq.h
+++ b/include/linux/soc/mediatek/mtk-cmdq.h
@@ -12,6 +12,8 @@
 #include <linux/timer.h>
 
 #define CMDQ_NO_TIMEOUT		0xffffffffu
+#define CMDQ_ADDR_HIGH(addr)	((u32)(((addr) >> 16) & GENMASK(31, 0)))
+#define CMDQ_ADDR_LOW(addr)	((u16)(addr) | BIT(1))
 
 struct cmdq_pkt;
 
@@ -102,6 +104,23 @@ int cmdq_pkt_write(struct cmdq_pkt *pkt, u8 subsys, u16 offset, u32 value);
 int cmdq_pkt_write_mask(struct cmdq_pkt *pkt, u8 subsys,
 			u16 offset, u32 value, u32 mask);
 
+/**
+ * cmdq_pkt_write_s() - append write_s command to the CMDQ packet
+ * @pkt:	the CMDQ packet
+ * @high_addr_reg_idx:	internal register ID which contains high address of pa
+ * @addr_low:	low address of pa
+ * @src_reg_idx:	the CMDQ internal register ID which cache source value
+ *
+ * Return: 0 for success; else the error code is returned
+ *
+ * Support write value to physical address without subsys. Use CMDQ_ADDR_HIGH()
+ * to get high address and call cmdq_pkt_assign() to assign value into internal
+ * reg. Also use CMDQ_ADDR_LOW() to get low address for addr_low parameter when
+ * call to this function.
+ */
+int cmdq_pkt_write_s(struct cmdq_pkt *pkt, u16 high_addr_reg_idx,
+		     u16 addr_low, u16 src_reg_idx);
+
 /**
  * cmdq_pkt_wfe() - append wait for event command to the CMDQ packet
  * @pkt:	the CMDQ packet
-- 
cgit v1.2.3


From 11c7842d41c82eb3551a0606ccba89ac33318b62 Mon Sep 17 00:00:00 2001
From: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Date: Tue, 7 Jul 2020 23:45:08 +0800
Subject: soc: mediatek: cmdq: add write_s_mask function

add write_s_mask function in cmdq helper functions which
writes value contains in internal register to address
with mask and large dma access support.

Signed-off-by: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Link: https://lore.kernel.org/r/1594136714-11650-4-git-send-email-dennis-yc.hsieh@mediatek.com
Signed-off-by: Matthias Brugger <matthias.bgg@gmail.com>
---
 drivers/soc/mediatek/mtk-cmdq-helper.c   | 23 +++++++++++++++++++++++
 include/linux/mailbox/mtk-cmdq-mailbox.h |  1 +
 include/linux/soc/mediatek/mtk-cmdq.h    | 18 ++++++++++++++++++
 3 files changed, 42 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/soc/mediatek/mtk-cmdq-helper.c b/drivers/soc/mediatek/mtk-cmdq-helper.c
index 880349b3f16c..550e9e7e3ff2 100644
--- a/drivers/soc/mediatek/mtk-cmdq-helper.c
+++ b/drivers/soc/mediatek/mtk-cmdq-helper.c
@@ -242,6 +242,29 @@ int cmdq_pkt_write_s(struct cmdq_pkt *pkt, u16 high_addr_reg_idx,
 }
 EXPORT_SYMBOL(cmdq_pkt_write_s);
 
+int cmdq_pkt_write_s_mask(struct cmdq_pkt *pkt, u16 high_addr_reg_idx,
+			  u16 addr_low, u16 src_reg_idx, u32 mask)
+{
+	struct cmdq_instruction inst = {};
+	int err;
+
+	inst.op = CMDQ_CODE_MASK;
+	inst.mask = ~mask;
+	err = cmdq_pkt_append_command(pkt, inst);
+	if (err < 0)
+		return err;
+
+	inst.mask = 0;
+	inst.op = CMDQ_CODE_WRITE_S_MASK;
+	inst.src_t = CMDQ_REG_TYPE;
+	inst.sop = high_addr_reg_idx;
+	inst.offset = addr_low;
+	inst.src_reg = src_reg_idx;
+
+	return cmdq_pkt_append_command(pkt, inst);
+}
+EXPORT_SYMBOL(cmdq_pkt_write_s_mask);
+
 int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event)
 {
 	struct cmdq_instruction inst = { {0} };
diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h
index 1f76cfedb16d..90d1d8e64412 100644
--- a/include/linux/mailbox/mtk-cmdq-mailbox.h
+++ b/include/linux/mailbox/mtk-cmdq-mailbox.h
@@ -61,6 +61,7 @@ enum cmdq_code {
 	CMDQ_CODE_WFE = 0x20,
 	CMDQ_CODE_EOC = 0x40,
 	CMDQ_CODE_WRITE_S = 0x90,
+	CMDQ_CODE_WRITE_S_MASK = 0x91,
 	CMDQ_CODE_LOGIC = 0xa0,
 };
 
diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h
index 9b0c57a0063d..53230341bf94 100644
--- a/include/linux/soc/mediatek/mtk-cmdq.h
+++ b/include/linux/soc/mediatek/mtk-cmdq.h
@@ -121,6 +121,24 @@ int cmdq_pkt_write_mask(struct cmdq_pkt *pkt, u8 subsys,
 int cmdq_pkt_write_s(struct cmdq_pkt *pkt, u16 high_addr_reg_idx,
 		     u16 addr_low, u16 src_reg_idx);
 
+/**
+ * cmdq_pkt_write_s_mask() - append write_s with mask command to the CMDQ packet
+ * @pkt:	the CMDQ packet
+ * @high_addr_reg_idx:	internal register ID which contains high address of pa
+ * @addr_low:	low address of pa
+ * @src_reg_idx:	the CMDQ internal register ID which cache source value
+ * @mask:	the specified target address mask, use U32_MAX if no need
+ *
+ * Return: 0 for success; else the error code is returned
+ *
+ * Support write value to physical address without subsys. Use CMDQ_ADDR_HIGH()
+ * to get high address and call cmdq_pkt_assign() to assign value into internal
+ * reg. Also use CMDQ_ADDR_LOW() to get low address for addr_low parameter when
+ * call to this function.
+ */
+int cmdq_pkt_write_s_mask(struct cmdq_pkt *pkt, u16 high_addr_reg_idx,
+			  u16 addr_low, u16 src_reg_idx, u32 mask);
+
 /**
  * cmdq_pkt_wfe() - append wait for event command to the CMDQ packet
  * @pkt:	the CMDQ packet
-- 
cgit v1.2.3


From d3b04aab06fbc33ddea15725f3ff1667c9717929 Mon Sep 17 00:00:00 2001
From: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Date: Tue, 7 Jul 2020 23:45:09 +0800
Subject: soc: mediatek: cmdq: add read_s function

Add read_s function in cmdq helper functions which support read value from
register or dma physical address into gce internal register.

Signed-off-by: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Link: https://lore.kernel.org/r/1594136714-11650-5-git-send-email-dennis-yc.hsieh@mediatek.com
Signed-off-by: Matthias Brugger <matthias.bgg@gmail.com>
---
 drivers/soc/mediatek/mtk-cmdq-helper.c   | 15 +++++++++++++++
 include/linux/mailbox/mtk-cmdq-mailbox.h |  1 +
 include/linux/soc/mediatek/mtk-cmdq.h    | 12 ++++++++++++
 3 files changed, 28 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/soc/mediatek/mtk-cmdq-helper.c b/drivers/soc/mediatek/mtk-cmdq-helper.c
index 550e9e7e3ff2..ed9f5e63c195 100644
--- a/drivers/soc/mediatek/mtk-cmdq-helper.c
+++ b/drivers/soc/mediatek/mtk-cmdq-helper.c
@@ -227,6 +227,21 @@ int cmdq_pkt_write_mask(struct cmdq_pkt *pkt, u8 subsys,
 }
 EXPORT_SYMBOL(cmdq_pkt_write_mask);
 
+int cmdq_pkt_read_s(struct cmdq_pkt *pkt, u16 high_addr_reg_idx, u16 addr_low,
+		    u16 reg_idx)
+{
+	struct cmdq_instruction inst = {};
+
+	inst.op = CMDQ_CODE_READ_S;
+	inst.dst_t = CMDQ_REG_TYPE;
+	inst.sop = high_addr_reg_idx;
+	inst.reg_dst = reg_idx;
+	inst.src_reg = addr_low;
+
+	return cmdq_pkt_append_command(pkt, inst);
+}
+EXPORT_SYMBOL(cmdq_pkt_read_s);
+
 int cmdq_pkt_write_s(struct cmdq_pkt *pkt, u16 high_addr_reg_idx,
 		     u16 addr_low, u16 src_reg_idx)
 {
diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h
index 90d1d8e64412..efbd8a9eb2d1 100644
--- a/include/linux/mailbox/mtk-cmdq-mailbox.h
+++ b/include/linux/mailbox/mtk-cmdq-mailbox.h
@@ -60,6 +60,7 @@ enum cmdq_code {
 	CMDQ_CODE_JUMP = 0x10,
 	CMDQ_CODE_WFE = 0x20,
 	CMDQ_CODE_EOC = 0x40,
+	CMDQ_CODE_READ_S = 0x80,
 	CMDQ_CODE_WRITE_S = 0x90,
 	CMDQ_CODE_WRITE_S_MASK = 0x91,
 	CMDQ_CODE_LOGIC = 0xa0,
diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h
index 53230341bf94..cd7ec714344e 100644
--- a/include/linux/soc/mediatek/mtk-cmdq.h
+++ b/include/linux/soc/mediatek/mtk-cmdq.h
@@ -104,6 +104,18 @@ int cmdq_pkt_write(struct cmdq_pkt *pkt, u8 subsys, u16 offset, u32 value);
 int cmdq_pkt_write_mask(struct cmdq_pkt *pkt, u8 subsys,
 			u16 offset, u32 value, u32 mask);
 
+/*
+ * cmdq_pkt_read_s() - append read_s command to the CMDQ packet
+ * @pkt:	the CMDQ packet
+ * @high_addr_reg_idx:	internal register ID which contains high address of pa
+ * @addr_low:	low address of pa
+ * @reg_idx:	the CMDQ internal register ID to cache read data
+ *
+ * Return: 0 for success; else the error code is returned
+ */
+int cmdq_pkt_read_s(struct cmdq_pkt *pkt, u16 high_addr_reg_idx, u16 addr_low,
+		    u16 reg_idx);
+
 /**
  * cmdq_pkt_write_s() - append write_s command to the CMDQ packet
  * @pkt:	the CMDQ packet
-- 
cgit v1.2.3


From 1af43fce813ebd74c76d080beb261603bd0853e1 Mon Sep 17 00:00:00 2001
From: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Date: Tue, 7 Jul 2020 23:45:10 +0800
Subject: soc: mediatek: cmdq: add write_s value function

add write_s function in cmdq helper functions which
writes a constant value to address with large dma
access support.

Signed-off-by: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Link: https://lore.kernel.org/r/1594136714-11650-6-git-send-email-dennis-yc.hsieh@mediatek.com
Signed-off-by: Matthias Brugger <matthias.bgg@gmail.com>
---
 drivers/soc/mediatek/mtk-cmdq-helper.c | 14 ++++++++++++++
 include/linux/soc/mediatek/mtk-cmdq.h  | 13 +++++++++++++
 2 files changed, 27 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/soc/mediatek/mtk-cmdq-helper.c b/drivers/soc/mediatek/mtk-cmdq-helper.c
index ed9f5e63c195..4e86b65815fc 100644
--- a/drivers/soc/mediatek/mtk-cmdq-helper.c
+++ b/drivers/soc/mediatek/mtk-cmdq-helper.c
@@ -280,6 +280,20 @@ int cmdq_pkt_write_s_mask(struct cmdq_pkt *pkt, u16 high_addr_reg_idx,
 }
 EXPORT_SYMBOL(cmdq_pkt_write_s_mask);
 
+int cmdq_pkt_write_s_value(struct cmdq_pkt *pkt, u8 high_addr_reg_idx,
+			   u16 addr_low, u32 value)
+{
+	struct cmdq_instruction inst = {};
+
+	inst.op = CMDQ_CODE_WRITE_S;
+	inst.sop = high_addr_reg_idx;
+	inst.offset = addr_low;
+	inst.value = value;
+
+	return cmdq_pkt_append_command(pkt, inst);
+}
+EXPORT_SYMBOL(cmdq_pkt_write_s_value);
+
 int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event)
 {
 	struct cmdq_instruction inst = { {0} };
diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h
index cd7ec714344e..ae73e10da274 100644
--- a/include/linux/soc/mediatek/mtk-cmdq.h
+++ b/include/linux/soc/mediatek/mtk-cmdq.h
@@ -151,6 +151,19 @@ int cmdq_pkt_write_s(struct cmdq_pkt *pkt, u16 high_addr_reg_idx,
 int cmdq_pkt_write_s_mask(struct cmdq_pkt *pkt, u16 high_addr_reg_idx,
 			  u16 addr_low, u16 src_reg_idx, u32 mask);
 
+/**
+ * cmdq_pkt_write_s_value() - append write_s command to the CMDQ packet which
+ *			      write value to a physical address
+ * @pkt:	the CMDQ packet
+ * @high_addr_reg_idx:	internal register ID which contains high address of pa
+ * @addr_low:	low address of pa
+ * @value:	the specified target value
+ *
+ * Return: 0 for success; else the error code is returned
+ */
+int cmdq_pkt_write_s_value(struct cmdq_pkt *pkt, u8 high_addr_reg_idx,
+			   u16 addr_low, u32 value);
+
 /**
  * cmdq_pkt_wfe() - append wait for event command to the CMDQ packet
  * @pkt:	the CMDQ packet
-- 
cgit v1.2.3


From 88a2ffc48d5bc85119ef7961df12369dcd53b4d2 Mon Sep 17 00:00:00 2001
From: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Date: Tue, 7 Jul 2020 23:45:11 +0800
Subject: soc: mediatek: cmdq: add write_s_mask value function

add write_s_mask_value function in cmdq helper functions which
writes a constant value to address with mask and large dma
access support.

Signed-off-by: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Link: https://lore.kernel.org/r/1594136714-11650-7-git-send-email-dennis-yc.hsieh@mediatek.com
Signed-off-by: Matthias Brugger <matthias.bgg@gmail.com>
---
 drivers/soc/mediatek/mtk-cmdq-helper.c | 21 +++++++++++++++++++++
 include/linux/soc/mediatek/mtk-cmdq.h  | 15 +++++++++++++++
 2 files changed, 36 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/soc/mediatek/mtk-cmdq-helper.c b/drivers/soc/mediatek/mtk-cmdq-helper.c
index 4e86b65815fc..b6e25f216605 100644
--- a/drivers/soc/mediatek/mtk-cmdq-helper.c
+++ b/drivers/soc/mediatek/mtk-cmdq-helper.c
@@ -294,6 +294,27 @@ int cmdq_pkt_write_s_value(struct cmdq_pkt *pkt, u8 high_addr_reg_idx,
 }
 EXPORT_SYMBOL(cmdq_pkt_write_s_value);
 
+int cmdq_pkt_write_s_mask_value(struct cmdq_pkt *pkt, u8 high_addr_reg_idx,
+				u16 addr_low, u32 value, u32 mask)
+{
+	struct cmdq_instruction inst = {};
+	int err;
+
+	inst.op = CMDQ_CODE_MASK;
+	inst.mask = ~mask;
+	err = cmdq_pkt_append_command(pkt, inst);
+	if (err < 0)
+		return err;
+
+	inst.op = CMDQ_CODE_WRITE_S_MASK;
+	inst.sop = high_addr_reg_idx;
+	inst.offset = addr_low;
+	inst.value = value;
+
+	return cmdq_pkt_append_command(pkt, inst);
+}
+EXPORT_SYMBOL(cmdq_pkt_write_s_mask_value);
+
 int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event)
 {
 	struct cmdq_instruction inst = { {0} };
diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h
index ae73e10da274..d9390d76ee14 100644
--- a/include/linux/soc/mediatek/mtk-cmdq.h
+++ b/include/linux/soc/mediatek/mtk-cmdq.h
@@ -164,6 +164,21 @@ int cmdq_pkt_write_s_mask(struct cmdq_pkt *pkt, u16 high_addr_reg_idx,
 int cmdq_pkt_write_s_value(struct cmdq_pkt *pkt, u8 high_addr_reg_idx,
 			   u16 addr_low, u32 value);
 
+/**
+ * cmdq_pkt_write_s_mask_value() - append write_s command with mask to the CMDQ
+ *				   packet which write value to a physical
+ *				   address
+ * @pkt:	the CMDQ packet
+ * @high_addr_reg_idx:	internal register ID which contains high address of pa
+ * @addr_low:	low address of pa
+ * @value:	the specified target value
+ * @mask:	the specified target mask
+ *
+ * Return: 0 for success; else the error code is returned
+ */
+int cmdq_pkt_write_s_mask_value(struct cmdq_pkt *pkt, u8 high_addr_reg_idx,
+				u16 addr_low, u32 value, u32 mask);
+
 /**
  * cmdq_pkt_wfe() - append wait for event command to the CMDQ packet
  * @pkt:	the CMDQ packet
-- 
cgit v1.2.3


From 946f1792d3d7942acfbc6afa9a733f608f4622d6 Mon Sep 17 00:00:00 2001
From: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Date: Tue, 7 Jul 2020 23:45:12 +0800
Subject: soc: mediatek: cmdq: add jump function

Add jump function so that client can jump to any address which
contains instruction.

Signed-off-by: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Link: https://lore.kernel.org/r/1594136714-11650-8-git-send-email-dennis-yc.hsieh@mediatek.com
Signed-off-by: Matthias Brugger <matthias.bgg@gmail.com>
---
 drivers/soc/mediatek/mtk-cmdq-helper.c | 13 +++++++++++++
 include/linux/soc/mediatek/mtk-cmdq.h  | 11 +++++++++++
 2 files changed, 24 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/soc/mediatek/mtk-cmdq-helper.c b/drivers/soc/mediatek/mtk-cmdq-helper.c
index b6e25f216605..d55dc3296105 100644
--- a/drivers/soc/mediatek/mtk-cmdq-helper.c
+++ b/drivers/soc/mediatek/mtk-cmdq-helper.c
@@ -13,6 +13,7 @@
 #define CMDQ_POLL_ENABLE_MASK	BIT(0)
 #define CMDQ_EOC_IRQ_EN		BIT(0)
 #define CMDQ_REG_TYPE		1
+#define CMDQ_JUMP_RELATIVE	1
 
 struct cmdq_instruction {
 	union {
@@ -407,6 +408,18 @@ int cmdq_pkt_assign(struct cmdq_pkt *pkt, u16 reg_idx, u32 value)
 }
 EXPORT_SYMBOL(cmdq_pkt_assign);
 
+int cmdq_pkt_jump(struct cmdq_pkt *pkt, dma_addr_t addr)
+{
+	struct cmdq_instruction inst = {};
+
+	inst.op = CMDQ_CODE_JUMP;
+	inst.offset = CMDQ_JUMP_RELATIVE;
+	inst.value = addr >>
+		cmdq_get_shift_pa(((struct cmdq_client *)pkt->cl)->chan);
+	return cmdq_pkt_append_command(pkt, inst);
+}
+EXPORT_SYMBOL(cmdq_pkt_jump);
+
 int cmdq_pkt_finalize(struct cmdq_pkt *pkt)
 {
 	struct cmdq_instruction inst = { {0} };
diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h
index d9390d76ee14..34354e952f60 100644
--- a/include/linux/soc/mediatek/mtk-cmdq.h
+++ b/include/linux/soc/mediatek/mtk-cmdq.h
@@ -252,6 +252,17 @@ int cmdq_pkt_poll_mask(struct cmdq_pkt *pkt, u8 subsys,
  */
 int cmdq_pkt_assign(struct cmdq_pkt *pkt, u16 reg_idx, u32 value);
 
+/**
+ * cmdq_pkt_jump() - Append jump command to the CMDQ packet, ask GCE
+ *		     to execute an instruction that change current thread PC to
+ *		     a physical address which should contains more instruction.
+ * @pkt:        the CMDQ packet
+ * @addr:       physical address of target instruction buffer
+ *
+ * Return: 0 for success; else the error code is returned
+ */
+int cmdq_pkt_jump(struct cmdq_pkt *pkt, dma_addr_t addr);
+
 /**
  * cmdq_pkt_finalize() - Append EOC and jump command to pkt.
  * @pkt:	the CMDQ packet
-- 
cgit v1.2.3


From 23c22299cd290409c6b78f57c42b64f8dfb6dd92 Mon Sep 17 00:00:00 2001
From: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Date: Tue, 7 Jul 2020 23:45:13 +0800
Subject: soc: mediatek: cmdq: add clear option in cmdq_pkt_wfe api

Add clear parameter to let client decide if
event should be clear to 0 after GCE receive it.

Signed-off-by: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Acked-by: Chun-Kuang Hu <chunkuang.hu@kernel.org>
Link: https://lore.kernel.org/r/1594136714-11650-9-git-send-email-dennis-yc.hsieh@mediatek.com
[mb: fix commit message]
Signed-off-by: Matthias Brugger <matthias.bgg@gmail.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_crtc.c  | 2 +-
 drivers/soc/mediatek/mtk-cmdq-helper.c   | 5 +++--
 include/linux/mailbox/mtk-cmdq-mailbox.h | 3 +--
 include/linux/soc/mediatek/mtk-cmdq.h    | 5 +++--
 4 files changed, 8 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
index 3fc5511330b9..2a332e297ebf 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
@@ -481,7 +481,7 @@ static void mtk_drm_crtc_hw_config(struct mtk_drm_crtc *mtk_crtc)
 		mbox_flush(mtk_crtc->cmdq_client->chan, 2000);
 		cmdq_handle = cmdq_pkt_create(mtk_crtc->cmdq_client, PAGE_SIZE);
 		cmdq_pkt_clear_event(cmdq_handle, mtk_crtc->cmdq_event);
-		cmdq_pkt_wfe(cmdq_handle, mtk_crtc->cmdq_event);
+		cmdq_pkt_wfe(cmdq_handle, mtk_crtc->cmdq_event, true);
 		mtk_crtc_ddp_config(crtc, cmdq_handle);
 		cmdq_pkt_finalize(cmdq_handle);
 		cmdq_pkt_flush_async(cmdq_handle, ddp_cmdq_cb, cmdq_handle);
diff --git a/drivers/soc/mediatek/mtk-cmdq-helper.c b/drivers/soc/mediatek/mtk-cmdq-helper.c
index d55dc3296105..505651b0d715 100644
--- a/drivers/soc/mediatek/mtk-cmdq-helper.c
+++ b/drivers/soc/mediatek/mtk-cmdq-helper.c
@@ -316,15 +316,16 @@ int cmdq_pkt_write_s_mask_value(struct cmdq_pkt *pkt, u8 high_addr_reg_idx,
 }
 EXPORT_SYMBOL(cmdq_pkt_write_s_mask_value);
 
-int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event)
+int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event, bool clear)
 {
 	struct cmdq_instruction inst = { {0} };
+	u32 clear_option = clear ? CMDQ_WFE_UPDATE : 0;
 
 	if (event >= CMDQ_MAX_EVENT)
 		return -EINVAL;
 
 	inst.op = CMDQ_CODE_WFE;
-	inst.value = CMDQ_WFE_OPTION;
+	inst.value = CMDQ_WFE_OPTION | clear_option;
 	inst.event = event;
 
 	return cmdq_pkt_append_command(pkt, inst);
diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h
index efbd8a9eb2d1..d5a983d65f05 100644
--- a/include/linux/mailbox/mtk-cmdq-mailbox.h
+++ b/include/linux/mailbox/mtk-cmdq-mailbox.h
@@ -28,8 +28,7 @@
  * bit 16-27: update value
  * bit 31: 1 - update, 0 - no update
  */
-#define CMDQ_WFE_OPTION			(CMDQ_WFE_UPDATE | CMDQ_WFE_WAIT | \
-					CMDQ_WFE_WAIT_VALUE)
+#define CMDQ_WFE_OPTION			(CMDQ_WFE_WAIT | CMDQ_WFE_WAIT_VALUE)
 
 /** cmdq event maximum */
 #define CMDQ_MAX_EVENT			0x3ff
diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h
index 34354e952f60..960704d75994 100644
--- a/include/linux/soc/mediatek/mtk-cmdq.h
+++ b/include/linux/soc/mediatek/mtk-cmdq.h
@@ -182,11 +182,12 @@ int cmdq_pkt_write_s_mask_value(struct cmdq_pkt *pkt, u8 high_addr_reg_idx,
 /**
  * cmdq_pkt_wfe() - append wait for event command to the CMDQ packet
  * @pkt:	the CMDQ packet
- * @event:	the desired event type to "wait and CLEAR"
+ * @event:	the desired event type to wait
+ * @clear:	clear event or not after event arrive
  *
  * Return: 0 for success; else the error code is returned
  */
-int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event);
+int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event, bool clear);
 
 /**
  * cmdq_pkt_clear_event() - append clear event command to the CMDQ packet
-- 
cgit v1.2.3


From ea0c80d1764449acf2f70fdb25aec33800cd0348 Mon Sep 17 00:00:00 2001
From: Zhen Lei <thunder.leizhen@huawei.com>
Date: Thu, 24 Sep 2020 15:17:49 +0800
Subject: genirq: Add stub for set_handle_irq() when !GENERIC_IRQ_MULTI_HANDLER

In order to avoid compilation errors when a driver references set_handle_irq(),
but that the architecture doesn't select GENERIC_IRQ_MULTI_HANDLER,
add a stub function that will just WARN_ON_ONCE() if ever used.

Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
[maz: commit message]
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200924071754.4509-2-thunder.leizhen@huawei.com
---
 include/linux/irq.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 1b7f4dfee35b..b167baef88c0 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -1252,6 +1252,12 @@ int __init set_handle_irq(void (*handle_irq)(struct pt_regs *));
  * top-level IRQ handler.
  */
 extern void (*handle_arch_irq)(struct pt_regs *) __ro_after_init;
+#else
+#define set_handle_irq(handle_irq)		\
+	do {					\
+		(void)handle_irq;		\
+		WARN_ON(1);			\
+	} while (0)
 #endif
 
 #endif /* _LINUX_IRQ_H */
-- 
cgit v1.2.3


From 576d0703a81217f04e3a29ce3403231062ef2877 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 25 Sep 2020 06:51:38 +0200
Subject: compat.h: fix a spelling error in <linux/compat.h>

There is no compat_sys_readv64v2 syscall, only a compat_sys_preadv64v2
one.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/compat.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/compat.h b/include/linux/compat.h
index d38c4d7e83bd..790be5ffc12c 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -812,7 +812,7 @@ asmlinkage ssize_t compat_sys_pwritev2(compat_ulong_t fd,
 		const struct compat_iovec __user *vec,
 		compat_ulong_t vlen, u32 pos_low, u32 pos_high, rwf_t flags);
 #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2
-asmlinkage long  compat_sys_readv64v2(unsigned long fd,
+asmlinkage long  compat_sys_preadv64v2(unsigned long fd,
 		const struct compat_iovec __user *vec,
 		unsigned long vlen, loff_t pos, rwf_t flags);
 #endif
-- 
cgit v1.2.3


From 1df8f55a37bd286a3d40192980050bc3d7d78887 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Thu, 24 Sep 2020 17:03:50 -0700
Subject: bpf: Enable bpf_skc_to_* sock casting helper to networking prog type

There is a constant need to add more fields into the bpf_tcp_sock
for the bpf programs running at tc, sock_ops...etc.

A current workaround could be to use bpf_probe_read_kernel().  However,
other than making another helper call for reading each field and missing
CO-RE, it is also not as intuitive to use as directly reading
"tp->lsndtime" for example.  While already having perfmon cap to do
bpf_probe_read_kernel(), it will be much easier if the bpf prog can
directly read from the tcp_sock.

This patch tries to do that by using the existing casting-helpers
bpf_skc_to_*() whose func_proto returns a btf_id.  For example, the
func_proto of bpf_skc_to_tcp_sock returns the btf_id of the
kernel "struct tcp_sock".

These helpers are also added to is_ptr_cast_function().
It ensures the returning reg (BPF_REF_0) will also carries the ref_obj_id.
That will keep the ref-tracking works properly.

The bpf_skc_to_* helpers are made available to most of the bpf prog
types in filter.c. The bpf_skc_to_* helpers will be limited by
perfmon cap.

This patch adds a ARG_PTR_TO_BTF_ID_SOCK_COMMON.  The helper accepting
this arg can accept a btf-id-ptr (PTR_TO_BTF_ID + &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON])
or a legacy-ctx-convert-skc-ptr (PTR_TO_SOCK_COMMON).  The bpf_skc_to_*()
helpers are changed to take ARG_PTR_TO_BTF_ID_SOCK_COMMON such that
they will accept pointer obtained from skb->sk.

Instead of specifying both arg_type and arg_btf_id in the same func_proto
which is how the current ARG_PTR_TO_BTF_ID does, the arg_btf_id of
the new ARG_PTR_TO_BTF_ID_SOCK_COMMON is specified in the
compatible_reg_types[] in verifier.c.  The reason is the arg_btf_id is
always the same.  Discussion in this thread:
https://lore.kernel.org/bpf/20200922070422.1917351-1-kafai@fb.com/

The ARG_PTR_TO_BTF_ID_ part gives a clear expectation that the helper is
expecting a PTR_TO_BTF_ID which could be NULL.  This is the same
behavior as the existing helper taking ARG_PTR_TO_BTF_ID.

The _SOCK_COMMON part means the helper is also expecting the legacy
SOCK_COMMON pointer.

By excluding the _OR_NULL part, the bpf prog cannot call helper
with a literal NULL which doesn't make sense in most cases.
e.g. bpf_skc_to_tcp_sock(NULL) will be rejected.  All PTR_TO_*_OR_NULL
reg has to do a NULL check first before passing into the helper or else
the bpf prog will be rejected.  This behavior is nothing new and
consistent with the current expectation during bpf-prog-load.

[ ARG_PTR_TO_BTF_ID_SOCK_COMMON will be used to replace
  ARG_PTR_TO_SOCK* of other existing helpers later such that
  those existing helpers can take the PTR_TO_BTF_ID returned by
  the bpf_skc_to_*() helpers.

  The only special case is bpf_sk_lookup_assign() which can accept a
  literal NULL ptr.  It has to be handled specially in another follow
  up patch if there is a need (e.g. by renaming ARG_PTR_TO_SOCKET_OR_NULL
  to ARG_PTR_TO_BTF_ID_SOCK_COMMON_OR_NULL). ]

[ When converting the older helpers that take ARG_PTR_TO_SOCK* in
  the later patch, if the kernel does not support BTF,
  ARG_PTR_TO_BTF_ID_SOCK_COMMON will behave like ARG_PTR_TO_SOCK_COMMON
  because no reg->type could have PTR_TO_BTF_ID in this case.

  It is not a concern for the newer-btf-only helper like the bpf_skc_to_*()
  here though because these helpers must require BTF vmlinux to begin
  with. ]

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20200925000350.3855720-1-kafai@fb.com
---
 include/linux/bpf.h   |  1 +
 kernel/bpf/verifier.c | 34 +++++++++++++++++++++++--
 net/core/filter.c     | 69 ++++++++++++++++++++++++++++++++++++---------------
 3 files changed, 82 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index fc5c901c7542..d0937f1d2980 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -292,6 +292,7 @@ enum bpf_arg_type {
 	ARG_PTR_TO_ALLOC_MEM,	/* pointer to dynamically allocated memory */
 	ARG_PTR_TO_ALLOC_MEM_OR_NULL,	/* pointer to dynamically allocated memory or NULL */
 	ARG_CONST_ALLOC_SIZE_OR_ZERO,	/* number of allocated bytes requested */
+	ARG_PTR_TO_BTF_ID_SOCK_COMMON,	/* pointer to in-kernel sock_common or bpf-mirrored bpf_sock */
 	__BPF_ARG_TYPE_MAX,
 };
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 945fa2b4d096..d4ba29fb17a6 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -486,7 +486,12 @@ static bool is_acquire_function(enum bpf_func_id func_id,
 static bool is_ptr_cast_function(enum bpf_func_id func_id)
 {
 	return func_id == BPF_FUNC_tcp_sock ||
-		func_id == BPF_FUNC_sk_fullsock;
+		func_id == BPF_FUNC_sk_fullsock ||
+		func_id == BPF_FUNC_skc_to_tcp_sock ||
+		func_id == BPF_FUNC_skc_to_tcp6_sock ||
+		func_id == BPF_FUNC_skc_to_udp6_sock ||
+		func_id == BPF_FUNC_skc_to_tcp_timewait_sock ||
+		func_id == BPF_FUNC_skc_to_tcp_request_sock;
 }
 
 /* string representation of 'enum bpf_reg_type' */
@@ -3953,6 +3958,7 @@ static int resolve_map_arg_type(struct bpf_verifier_env *env,
 
 struct bpf_reg_types {
 	const enum bpf_reg_type types[10];
+	u32 *btf_id;
 };
 
 static const struct bpf_reg_types map_key_value_types = {
@@ -3973,6 +3979,17 @@ static const struct bpf_reg_types sock_types = {
 	},
 };
 
+static const struct bpf_reg_types btf_id_sock_common_types = {
+	.types = {
+		PTR_TO_SOCK_COMMON,
+		PTR_TO_SOCKET,
+		PTR_TO_TCP_SOCK,
+		PTR_TO_XDP_SOCK,
+		PTR_TO_BTF_ID,
+	},
+	.btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
+};
+
 static const struct bpf_reg_types mem_types = {
 	.types = {
 		PTR_TO_STACK,
@@ -4014,6 +4031,7 @@ static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = {
 	[ARG_PTR_TO_CTX]		= &context_types,
 	[ARG_PTR_TO_CTX_OR_NULL]	= &context_types,
 	[ARG_PTR_TO_SOCK_COMMON]	= &sock_types,
+	[ARG_PTR_TO_BTF_ID_SOCK_COMMON]	= &btf_id_sock_common_types,
 	[ARG_PTR_TO_SOCKET]		= &fullsock_types,
 	[ARG_PTR_TO_SOCKET_OR_NULL]	= &fullsock_types,
 	[ARG_PTR_TO_BTF_ID]		= &btf_ptr_types,
@@ -4059,6 +4077,14 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
 
 found:
 	if (type == PTR_TO_BTF_ID) {
+		if (!arg_btf_id) {
+			if (!compatible->btf_id) {
+				verbose(env, "verifier internal error: missing arg compatible BTF ID\n");
+				return -EFAULT;
+			}
+			arg_btf_id = compatible->btf_id;
+		}
+
 		if (!btf_struct_ids_match(&env->log, reg->off, reg->btf_id,
 					  *arg_btf_id)) {
 			verbose(env, "R%d is of type %s but %s is expected\n",
@@ -4575,10 +4601,14 @@ static bool check_btf_id_ok(const struct bpf_func_proto *fn)
 {
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(fn->arg_type); i++)
+	for (i = 0; i < ARRAY_SIZE(fn->arg_type); i++) {
 		if (fn->arg_type[i] == ARG_PTR_TO_BTF_ID && !fn->arg_btf_id[i])
 			return false;
 
+		if (fn->arg_type[i] != ARG_PTR_TO_BTF_ID && fn->arg_btf_id[i])
+			return false;
+	}
+
 	return true;
 }
 
diff --git a/net/core/filter.c b/net/core/filter.c
index 706f8db0ccf8..6d1864f2bd51 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -77,6 +77,9 @@
 #include <net/transp_v6.h>
 #include <linux/btf_ids.h>
 
+static const struct bpf_func_proto *
+bpf_sk_base_func_proto(enum bpf_func_id func_id);
+
 int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len)
 {
 	if (in_compat_syscall()) {
@@ -6620,7 +6623,7 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 			return NULL;
 		}
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -6639,7 +6642,7 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_perf_event_output:
 		return &bpf_skb_event_output_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -6800,7 +6803,7 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sk_assign_proto;
 #endif
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -6841,7 +6844,7 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_tcp_gen_syncookie_proto;
 #endif
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -6883,7 +6886,7 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_tcp_sock_proto;
 #endif /* CONFIG_INET */
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -6929,7 +6932,7 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_cgroup_classid_curr_proto;
 #endif
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -6971,7 +6974,7 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_skc_lookup_tcp_proto;
 #endif
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -6982,7 +6985,7 @@ flow_dissector_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_skb_load_bytes:
 		return &bpf_flow_dissector_load_bytes_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -7009,7 +7012,7 @@ lwt_out_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_skb_under_cgroup:
 		return &bpf_skb_under_cgroup_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -9746,7 +9749,7 @@ sk_lookup_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_sk_release:
 		return &bpf_sk_release_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -9913,8 +9916,7 @@ const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto = {
 	.func			= bpf_skc_to_tcp6_sock,
 	.gpl_only		= false,
 	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
-	.arg1_type		= ARG_PTR_TO_BTF_ID,
-	.arg1_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
+	.arg1_type		= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP6],
 };
 
@@ -9930,8 +9932,7 @@ const struct bpf_func_proto bpf_skc_to_tcp_sock_proto = {
 	.func			= bpf_skc_to_tcp_sock,
 	.gpl_only		= false,
 	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
-	.arg1_type		= ARG_PTR_TO_BTF_ID,
-	.arg1_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
+	.arg1_type		= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP],
 };
 
@@ -9954,8 +9955,7 @@ const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto = {
 	.func			= bpf_skc_to_tcp_timewait_sock,
 	.gpl_only		= false,
 	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
-	.arg1_type		= ARG_PTR_TO_BTF_ID,
-	.arg1_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
+	.arg1_type		= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP_TW],
 };
 
@@ -9978,8 +9978,7 @@ const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto = {
 	.func			= bpf_skc_to_tcp_request_sock,
 	.gpl_only		= false,
 	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
-	.arg1_type		= ARG_PTR_TO_BTF_ID,
-	.arg1_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
+	.arg1_type		= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP_REQ],
 };
 
@@ -10000,7 +9999,37 @@ const struct bpf_func_proto bpf_skc_to_udp6_sock_proto = {
 	.func			= bpf_skc_to_udp6_sock,
 	.gpl_only		= false,
 	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
-	.arg1_type		= ARG_PTR_TO_BTF_ID,
-	.arg1_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
+	.arg1_type		= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_UDP6],
 };
+
+static const struct bpf_func_proto *
+bpf_sk_base_func_proto(enum bpf_func_id func_id)
+{
+	const struct bpf_func_proto *func;
+
+	switch (func_id) {
+	case BPF_FUNC_skc_to_tcp6_sock:
+		func = &bpf_skc_to_tcp6_sock_proto;
+		break;
+	case BPF_FUNC_skc_to_tcp_sock:
+		func = &bpf_skc_to_tcp_sock_proto;
+		break;
+	case BPF_FUNC_skc_to_tcp_timewait_sock:
+		func = &bpf_skc_to_tcp_timewait_sock_proto;
+		break;
+	case BPF_FUNC_skc_to_tcp_request_sock:
+		func = &bpf_skc_to_tcp_request_sock_proto;
+		break;
+	case BPF_FUNC_skc_to_udp6_sock:
+		func = &bpf_skc_to_udp6_sock_proto;
+		break;
+	default:
+		return bpf_base_func_proto(func_id);
+	}
+
+	if (!perfmon_capable())
+		return NULL;
+
+	return func;
+}
-- 
cgit v1.2.3


From 6277e374b0b07c1a93c829f0a27e38739b3b7a1b Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Thu, 24 Sep 2020 13:52:24 +0200
Subject: efi: Add definition of EFI_MEMORY_CPU_CRYPTO and ability to report it

Incorporate the definition of EFI_MEMORY_CPU_CRYPTO from the UEFI
specification v2.8, and wire it into our memory map dumping routine
as well.

To make a bit of space in the output buffer, which is provided by
the various callers, shorten the descriptive names of the memory
types.

Reviewed-by: Laszlo Ersek <lersek@redhat.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/efi.c | 47 +++++++++++++++++++++++-----------------------
 include/linux/efi.h        |  1 +
 2 files changed, 25 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 3aa07c3b5136..ebb59e52294f 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -714,7 +714,7 @@ void __init efi_systab_report_header(const efi_table_hdr_t *systab_hdr,
 		vendor);
 }
 
-static __initdata char memory_type_name[][20] = {
+static __initdata char memory_type_name[][13] = {
 	"Reserved",
 	"Loader Code",
 	"Loader Data",
@@ -722,14 +722,14 @@ static __initdata char memory_type_name[][20] = {
 	"Boot Data",
 	"Runtime Code",
 	"Runtime Data",
-	"Conventional Memory",
-	"Unusable Memory",
-	"ACPI Reclaim Memory",
-	"ACPI Memory NVS",
-	"Memory Mapped I/O",
-	"MMIO Port Space",
+	"Conventional",
+	"Unusable",
+	"ACPI Reclaim",
+	"ACPI Mem NVS",
+	"MMIO",
+	"MMIO Port",
 	"PAL Code",
-	"Persistent Memory",
+	"Persistent",
 };
 
 char * __init efi_md_typeattr_format(char *buf, size_t size,
@@ -756,26 +756,27 @@ char * __init efi_md_typeattr_format(char *buf, size_t size,
 	if (attr & ~(EFI_MEMORY_UC | EFI_MEMORY_WC | EFI_MEMORY_WT |
 		     EFI_MEMORY_WB | EFI_MEMORY_UCE | EFI_MEMORY_RO |
 		     EFI_MEMORY_WP | EFI_MEMORY_RP | EFI_MEMORY_XP |
-		     EFI_MEMORY_NV | EFI_MEMORY_SP |
+		     EFI_MEMORY_NV | EFI_MEMORY_SP | EFI_MEMORY_CPU_CRYPTO |
 		     EFI_MEMORY_RUNTIME | EFI_MEMORY_MORE_RELIABLE))
 		snprintf(pos, size, "|attr=0x%016llx]",
 			 (unsigned long long)attr);
 	else
 		snprintf(pos, size,
-			 "|%3s|%2s|%2s|%2s|%2s|%2s|%2s|%2s|%3s|%2s|%2s|%2s|%2s]",
-			 attr & EFI_MEMORY_RUNTIME ? "RUN" : "",
-			 attr & EFI_MEMORY_MORE_RELIABLE ? "MR" : "",
-			 attr & EFI_MEMORY_SP      ? "SP"  : "",
-			 attr & EFI_MEMORY_NV      ? "NV"  : "",
-			 attr & EFI_MEMORY_XP      ? "XP"  : "",
-			 attr & EFI_MEMORY_RP      ? "RP"  : "",
-			 attr & EFI_MEMORY_WP      ? "WP"  : "",
-			 attr & EFI_MEMORY_RO      ? "RO"  : "",
-			 attr & EFI_MEMORY_UCE     ? "UCE" : "",
-			 attr & EFI_MEMORY_WB      ? "WB"  : "",
-			 attr & EFI_MEMORY_WT      ? "WT"  : "",
-			 attr & EFI_MEMORY_WC      ? "WC"  : "",
-			 attr & EFI_MEMORY_UC      ? "UC"  : "");
+			 "|%3s|%2s|%2s|%2s|%2s|%2s|%2s|%2s|%2s|%3s|%2s|%2s|%2s|%2s]",
+			 attr & EFI_MEMORY_RUNTIME		? "RUN" : "",
+			 attr & EFI_MEMORY_MORE_RELIABLE	? "MR"  : "",
+			 attr & EFI_MEMORY_CPU_CRYPTO   	? "CC"  : "",
+			 attr & EFI_MEMORY_SP			? "SP"  : "",
+			 attr & EFI_MEMORY_NV			? "NV"  : "",
+			 attr & EFI_MEMORY_XP			? "XP"  : "",
+			 attr & EFI_MEMORY_RP			? "RP"  : "",
+			 attr & EFI_MEMORY_WP			? "WP"  : "",
+			 attr & EFI_MEMORY_RO			? "RO"  : "",
+			 attr & EFI_MEMORY_UCE			? "UCE" : "",
+			 attr & EFI_MEMORY_WB			? "WB"  : "",
+			 attr & EFI_MEMORY_WT			? "WT"  : "",
+			 attr & EFI_MEMORY_WC			? "WC"  : "",
+			 attr & EFI_MEMORY_UC			? "UC"  : "");
 	return buf;
 }
 
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 73db1ae04cef..f216c029a77b 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -122,6 +122,7 @@ typedef	struct {
 				((u64)0x0000000000010000ULL)	/* higher reliability */
 #define EFI_MEMORY_RO		((u64)0x0000000000020000ULL)	/* read-only */
 #define EFI_MEMORY_SP		((u64)0x0000000000040000ULL)	/* soft reserved */
+#define EFI_MEMORY_CPU_CRYPTO	((u64)0x0000000000080000ULL)	/* supports encryption */
 #define EFI_MEMORY_RUNTIME	((u64)0x8000000000000000ULL)	/* range requires runtime mapping */
 #define EFI_MEMORY_DESCRIPTOR_VERSION	1
 
-- 
cgit v1.2.3


From 403217f30418c808600e3e8e345413ba5cc15676 Mon Sep 17 00:00:00 2001
From: Anna Schumaker <Anna.Schumaker@Netapp.com>
Date: Mon, 17 Aug 2020 12:53:06 -0400
Subject: SUNRPC/NFSD: Implement xdr_reserve_space_vec()

Reserving space for a large READ payload requires special handling when
reserving space in the xdr buffer pages. One problem we can have is use
of the scratch buffer, which is used to get a pointer to a contiguous
region of data up to PAGE_SIZE. When using the scratch buffer, calls to
xdr_commit_encode() shift the data to it's proper alignment in the xdr
buffer. If we've reserved several pages in a vector, then this could
potentially invalidate earlier pointers and result in incorrect READ
data being sent to the client.

I get around this by looking at the amount of space left in the current
page, and never reserve more than that for each entry in the read
vector. This lets us place data directly where it needs to go in the
buffer pages.

Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfsd/nfs4xdr.c          | 28 +++-------------------------
 include/linux/sunrpc/xdr.h |  2 ++
 net/sunrpc/xdr.c           | 45 +++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 50 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 3d263fd20df0..36a54827085b 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -3814,36 +3814,14 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp,
 {
 	struct xdr_stream *xdr = &resp->xdr;
 	u32 eof;
-	int v;
 	int starting_len = xdr->buf->len - 8;
-	long len;
-	int thislen;
 	__be32 nfserr;
 	__be32 tmp;
-	__be32 *p;
 	int pad;
 
-	/*
-	 * svcrdma requires every READ payload to start somewhere
-	 * in xdr->pages.
-	 */
-	if (xdr->iov == xdr->buf->head) {
-		xdr->iov = NULL;
-		xdr->end = xdr->p;
-	}
-
-	len = maxcount;
-	v = 0;
-	while (len) {
-		thislen = min_t(long, len, PAGE_SIZE);
-		p = xdr_reserve_space(xdr, thislen);
-		WARN_ON_ONCE(!p);
-		resp->rqstp->rq_vec[v].iov_base = p;
-		resp->rqstp->rq_vec[v].iov_len = thislen;
-		v++;
-		len -= thislen;
-	}
-	read->rd_vlen = v;
+	read->rd_vlen = xdr_reserve_space_vec(xdr, resp->rqstp->rq_vec, maxcount);
+	if (read->rd_vlen < 0)
+		return nfserr_resource;
 
 	nfserr = nfsd_readv(resp->rqstp, read->rd_fhp, file, read->rd_offset,
 			    resp->rqstp->rq_vec, read->rd_vlen, &maxcount,
diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 5a6a81b7cd9f..6613d96a3029 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -234,6 +234,8 @@ typedef int	(*kxdrdproc_t)(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf,
 			    __be32 *p, struct rpc_rqst *rqst);
 extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes);
+extern int xdr_reserve_space_vec(struct xdr_stream *xdr, struct kvec *vec,
+		size_t nbytes);
 extern void xdr_commit_encode(struct xdr_stream *xdr);
 extern void xdr_truncate_encode(struct xdr_stream *xdr, size_t len);
 extern int xdr_restrict_buflen(struct xdr_stream *xdr, int newbuflen);
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 3bd5bef02996..b45af330f9f3 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -648,6 +648,51 @@ __be32 * xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes)
 }
 EXPORT_SYMBOL_GPL(xdr_reserve_space);
 
+
+/**
+ * xdr_reserve_space_vec - Reserves a large amount of buffer space for sending
+ * @xdr: pointer to xdr_stream
+ * @vec: pointer to a kvec array
+ * @nbytes: number of bytes to reserve
+ *
+ * Reserves enough buffer space to encode 'nbytes' of data and stores the
+ * pointers in 'vec'. The size argument passed to xdr_reserve_space() is
+ * determined based on the number of bytes remaining in the current page to
+ * avoid invalidating iov_base pointers when xdr_commit_encode() is called.
+ */
+int xdr_reserve_space_vec(struct xdr_stream *xdr, struct kvec *vec, size_t nbytes)
+{
+	int thislen;
+	int v = 0;
+	__be32 *p;
+
+	/*
+	 * svcrdma requires every READ payload to start somewhere
+	 * in xdr->pages.
+	 */
+	if (xdr->iov == xdr->buf->head) {
+		xdr->iov = NULL;
+		xdr->end = xdr->p;
+	}
+
+	while (nbytes) {
+		thislen = xdr->buf->page_len % PAGE_SIZE;
+		thislen = min_t(size_t, nbytes, PAGE_SIZE - thislen);
+
+		p = xdr_reserve_space(xdr, thislen);
+		if (!p)
+			return -EIO;
+
+		vec[v].iov_base = p;
+		vec[v].iov_len = thislen;
+		v++;
+		nbytes -= thislen;
+	}
+
+	return v;
+}
+EXPORT_SYMBOL_GPL(xdr_reserve_space_vec);
+
 /**
  * xdr_truncate_encode - truncate an encode buffer
  * @xdr: pointer to xdr_stream
-- 
cgit v1.2.3


From afbe7973173a7ce0a68af8b33e44c967582297be Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Thu, 24 Sep 2020 12:30:20 -0400
Subject: tracepoints: Add helper to test if tracepoint is enabled in a header

As tracepoints are discouraged from being added in a header because it can
cause side effects if other tracepoints are in headers, as well as bloat the
kernel as the trace_<tracepoint>() function is not a small inline, the common
workaround is to add a function call that calls a wrapper function in a
C file that then calls the tracepoint. But as function calls add overhead,
this function should only be called when the tracepoint in question is
enabled. To get around this overhead, a static_branch can be used to only
have the tracepoint wrapper get called when the tracepoint is enabled.

Add a tracepoint_enabled(tp) macro that gets passed the name of the
tracepoint, and this becomes a static_branch that is enabled when the
tracepoint is enabled and is a nop when the tracepoint is disabled.

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 Documentation/trace/tracepoints.rst | 27 +++++++++++++++++++++++++++
 include/linux/tracepoint-defs.h     | 34 ++++++++++++++++++++++++++++++++++
 2 files changed, 61 insertions(+)

(limited to 'include/linux')

diff --git a/Documentation/trace/tracepoints.rst b/Documentation/trace/tracepoints.rst
index 6e3ce3bf3593..0cb8d9ca3d60 100644
--- a/Documentation/trace/tracepoints.rst
+++ b/Documentation/trace/tracepoints.rst
@@ -146,3 +146,30 @@ with jump labels and avoid conditional branches.
       define tracepoints. Check http://lwn.net/Articles/379903,
       http://lwn.net/Articles/381064 and http://lwn.net/Articles/383362
       for a series of articles with more details.
+
+If you require calling a tracepoint from a header file, it is not
+recommended to call one directly or to use the trace_<tracepoint>_enabled()
+function call, as tracepoints in header files can have side effects if a
+header is included from a file that has CREATE_TRACE_POINTS set, as
+well as the trace_<tracepoint>() is not that small of an inline
+and can bloat the kernel if used by other inlined functions. Instead,
+include tracepoint-defs.h and use tracepoint_enabled().
+
+In a C file::
+
+	void do_trace_foo_bar_wrapper(args)
+	{
+		trace_foo_bar(args);
+	}
+
+In the header file::
+
+	DECLARE_TRACEPOINT(foo_bar);
+
+	static inline void some_inline_function()
+	{
+		[..]
+		if (tracepoint_enabled(foo_bar))
+			do_trace_foo_bar_wrapper(args);
+		[..]
+	}
diff --git a/include/linux/tracepoint-defs.h b/include/linux/tracepoint-defs.h
index b29950a19205..60625973faaf 100644
--- a/include/linux/tracepoint-defs.h
+++ b/include/linux/tracepoint-defs.h
@@ -48,4 +48,38 @@ struct bpf_raw_event_map {
 	u32			writable_size;
 } __aligned(32);
 
+/*
+ * If a tracepoint needs to be called from a header file, it is not
+ * recommended to call it directly, as tracepoints in header files
+ * may cause side-effects and bloat the kernel. Instead, use
+ * tracepoint_enabled() to test if the tracepoint is enabled, then if
+ * it is, call a wrapper function defined in a C file that will then
+ * call the tracepoint.
+ *
+ * For "trace_foo_bar()", you would need to create a wrapper function
+ * in a C file to call trace_foo_bar():
+ *   void do_trace_foo_bar(args) { trace_foo_bar(args); }
+ * Then in the header file, declare the tracepoint:
+ *   DECLARE_TRACEPOINT(foo_bar);
+ * And call your wrapper:
+ *   static inline void some_inlined_function() {
+ *            [..]
+ *            if (tracepoint_enabled(foo_bar))
+ *                    do_trace_foo_bar(args);
+ *            [..]
+ *   }
+ *
+ * Note: tracepoint_enabled(foo_bar) is equivalent to trace_foo_bar_enabled()
+ *   but is safe to have in headers, where trace_foo_bar_enabled() is not.
+ */
+#define DECLARE_TRACEPOINT(tp) \
+	extern struct tracepoint __tracepoint_##tp
+
+#ifdef CONFIG_TRACEPOINTS
+# define tracepoint_enabled(tp) \
+	static_key_false(&(__tracepoint_##tp).key)
+#else
+# define tracepoint_enabled(tracepoint) false
+#endif
+
 #endif
-- 
cgit v1.2.3


From c65fc2276f0f022f5ad4a84658add2b28cff7227 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Thu, 24 Sep 2020 12:43:46 -0400
Subject: mm/page_ref: Convert the open coded tracepoint enabled to the new
 helper

As more use cases of checking if a tracepoint is enabled in a header are
coming to fruition, a helper macro, tracepoint_enabled(), has been added to
check if a tracepoint is enabled or not, and can be used with minimal header
requirements (avoid "include hell"). Convert the page_ref logic over to the
new helper macro.

Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/page_ref.h | 42 +++++++++++++++++++++---------------------
 1 file changed, 21 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h
index d27701199a4d..f3318f34fc54 100644
--- a/include/linux/page_ref.h
+++ b/include/linux/page_ref.h
@@ -7,13 +7,13 @@
 #include <linux/page-flags.h>
 #include <linux/tracepoint-defs.h>
 
-extern struct tracepoint __tracepoint_page_ref_set;
-extern struct tracepoint __tracepoint_page_ref_mod;
-extern struct tracepoint __tracepoint_page_ref_mod_and_test;
-extern struct tracepoint __tracepoint_page_ref_mod_and_return;
-extern struct tracepoint __tracepoint_page_ref_mod_unless;
-extern struct tracepoint __tracepoint_page_ref_freeze;
-extern struct tracepoint __tracepoint_page_ref_unfreeze;
+DECLARE_TRACEPOINT(page_ref_set);
+DECLARE_TRACEPOINT(page_ref_mod);
+DECLARE_TRACEPOINT(page_ref_mod_and_test);
+DECLARE_TRACEPOINT(page_ref_mod_and_return);
+DECLARE_TRACEPOINT(page_ref_mod_unless);
+DECLARE_TRACEPOINT(page_ref_freeze);
+DECLARE_TRACEPOINT(page_ref_unfreeze);
 
 #ifdef CONFIG_DEBUG_PAGE_REF
 
@@ -24,7 +24,7 @@ extern struct tracepoint __tracepoint_page_ref_unfreeze;
  *
  * See trace_##name##_enabled(void) in include/linux/tracepoint.h
  */
-#define page_ref_tracepoint_active(t) static_key_false(&(t).key)
+#define page_ref_tracepoint_active(t) tracepoint_enabled(t)
 
 extern void __page_ref_set(struct page *page, int v);
 extern void __page_ref_mod(struct page *page, int v);
@@ -75,7 +75,7 @@ static inline int page_count(struct page *page)
 static inline void set_page_count(struct page *page, int v)
 {
 	atomic_set(&page->_refcount, v);
-	if (page_ref_tracepoint_active(__tracepoint_page_ref_set))
+	if (page_ref_tracepoint_active(page_ref_set))
 		__page_ref_set(page, v);
 }
 
@@ -91,14 +91,14 @@ static inline void init_page_count(struct page *page)
 static inline void page_ref_add(struct page *page, int nr)
 {
 	atomic_add(nr, &page->_refcount);
-	if (page_ref_tracepoint_active(__tracepoint_page_ref_mod))
+	if (page_ref_tracepoint_active(page_ref_mod))
 		__page_ref_mod(page, nr);
 }
 
 static inline void page_ref_sub(struct page *page, int nr)
 {
 	atomic_sub(nr, &page->_refcount);
-	if (page_ref_tracepoint_active(__tracepoint_page_ref_mod))
+	if (page_ref_tracepoint_active(page_ref_mod))
 		__page_ref_mod(page, -nr);
 }
 
@@ -106,7 +106,7 @@ static inline int page_ref_sub_return(struct page *page, int nr)
 {
 	int ret = atomic_sub_return(nr, &page->_refcount);
 
-	if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_return))
+	if (page_ref_tracepoint_active(page_ref_mod_and_return))
 		__page_ref_mod_and_return(page, -nr, ret);
 	return ret;
 }
@@ -114,14 +114,14 @@ static inline int page_ref_sub_return(struct page *page, int nr)
 static inline void page_ref_inc(struct page *page)
 {
 	atomic_inc(&page->_refcount);
-	if (page_ref_tracepoint_active(__tracepoint_page_ref_mod))
+	if (page_ref_tracepoint_active(page_ref_mod))
 		__page_ref_mod(page, 1);
 }
 
 static inline void page_ref_dec(struct page *page)
 {
 	atomic_dec(&page->_refcount);
-	if (page_ref_tracepoint_active(__tracepoint_page_ref_mod))
+	if (page_ref_tracepoint_active(page_ref_mod))
 		__page_ref_mod(page, -1);
 }
 
@@ -129,7 +129,7 @@ static inline int page_ref_sub_and_test(struct page *page, int nr)
 {
 	int ret = atomic_sub_and_test(nr, &page->_refcount);
 
-	if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_test))
+	if (page_ref_tracepoint_active(page_ref_mod_and_test))
 		__page_ref_mod_and_test(page, -nr, ret);
 	return ret;
 }
@@ -138,7 +138,7 @@ static inline int page_ref_inc_return(struct page *page)
 {
 	int ret = atomic_inc_return(&page->_refcount);
 
-	if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_return))
+	if (page_ref_tracepoint_active(page_ref_mod_and_return))
 		__page_ref_mod_and_return(page, 1, ret);
 	return ret;
 }
@@ -147,7 +147,7 @@ static inline int page_ref_dec_and_test(struct page *page)
 {
 	int ret = atomic_dec_and_test(&page->_refcount);
 
-	if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_test))
+	if (page_ref_tracepoint_active(page_ref_mod_and_test))
 		__page_ref_mod_and_test(page, -1, ret);
 	return ret;
 }
@@ -156,7 +156,7 @@ static inline int page_ref_dec_return(struct page *page)
 {
 	int ret = atomic_dec_return(&page->_refcount);
 
-	if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_return))
+	if (page_ref_tracepoint_active(page_ref_mod_and_return))
 		__page_ref_mod_and_return(page, -1, ret);
 	return ret;
 }
@@ -165,7 +165,7 @@ static inline int page_ref_add_unless(struct page *page, int nr, int u)
 {
 	int ret = atomic_add_unless(&page->_refcount, nr, u);
 
-	if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_unless))
+	if (page_ref_tracepoint_active(page_ref_mod_unless))
 		__page_ref_mod_unless(page, nr, ret);
 	return ret;
 }
@@ -174,7 +174,7 @@ static inline int page_ref_freeze(struct page *page, int count)
 {
 	int ret = likely(atomic_cmpxchg(&page->_refcount, count, 0) == count);
 
-	if (page_ref_tracepoint_active(__tracepoint_page_ref_freeze))
+	if (page_ref_tracepoint_active(page_ref_freeze))
 		__page_ref_freeze(page, count, ret);
 	return ret;
 }
@@ -185,7 +185,7 @@ static inline void page_ref_unfreeze(struct page *page, int count)
 	VM_BUG_ON(count == 0);
 
 	atomic_set_release(&page->_refcount, count);
-	if (page_ref_tracepoint_active(__tracepoint_page_ref_unfreeze))
+	if (page_ref_tracepoint_active(page_ref_unfreeze))
 		__page_ref_unfreeze(page, count);
 }
 
-- 
cgit v1.2.3


From e0f9956a3862b32ad73869a8e52a33c84aafa46f Mon Sep 17 00:00:00 2001
From: "Chuah, Kim Tatt" <kim.tatt.chuah@intel.com>
Date: Fri, 25 Sep 2020 17:40:41 +0800
Subject: net: stmmac: Add option for VLAN filter fail queue enable

Add option in plat_stmmacenet_data struct to enable VLAN Filter Fail
Queuing. This option allows packets that fail VLAN filter to be routed
to a specific Rx queue when Receive All is also set.

When this option is enabled:
- Enable VFFQ only when entering promiscuous mode, because Receive All
  will pass up all rx packets that failed address filtering (similar to
  promiscuous mode).
- VLAN-promiscuous mode is never entered to allow rx packet to fail VLAN
  filters and get routed to selected VFFQ Rx queue.

Reviewed-by: Voon Weifeng <weifeng.voon@intel.com>
Reviewed-by: Ong Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: Chuah, Kim Tatt <kim.tatt.chuah@intel.com>
Signed-off-by: Ong Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/common.h      |  2 ++
 drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c |  5 +++++
 drivers/net/ethernet/stmicro/stmmac/dwmac4.h      |  1 +
 drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c | 15 +++++++++++++--
 drivers/net/ethernet/stmicro/stmmac/dwmac5.h      |  6 ++++++
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c |  3 +++
 include/linux/stmmac.h                            |  2 ++
 7 files changed, 32 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index cafa8e3c3573..df7de50497a0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -481,6 +481,8 @@ struct mac_device_info {
 	unsigned int num_vlan;
 	u32 vlan_filter[32];
 	unsigned int promisc;
+	bool vlan_fail_q_en;
+	u8 vlan_fail_q;
 };
 
 struct stmmac_rx_routing {
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index 2ac9dfb3462c..ab0a81e0fea1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -321,6 +321,11 @@ static int intel_mgbe_common_data(struct pci_dev *pdev,
 	/* Set the maxmtu to a default of JUMBO_LEN */
 	plat->maxmtu = JUMBO_LEN;
 
+	plat->vlan_fail_q_en = true;
+
+	/* Use the last Rx queue */
+	plat->vlan_fail_q = plat->rx_queues_to_use - 1;
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
index 61f3249bd724..592b043f9676 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
@@ -76,6 +76,7 @@
 #define GMAC_PACKET_FILTER_HPF		BIT(10)
 #define GMAC_PACKET_FILTER_VTFE		BIT(16)
 #define GMAC_PACKET_FILTER_IPFE		BIT(20)
+#define GMAC_PACKET_FILTER_RA		BIT(31)
 
 #define GMAC_MAX_PERFECT_ADDRESSES	128
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index ecd834e0e121..002791b77356 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -618,7 +618,18 @@ static void dwmac4_set_filter(struct mac_device_info *hw,
 	value &= ~GMAC_PACKET_FILTER_PM;
 	value &= ~GMAC_PACKET_FILTER_PR;
 	if (dev->flags & IFF_PROMISC) {
-		value = GMAC_PACKET_FILTER_PR | GMAC_PACKET_FILTER_PCF;
+		/* VLAN Tag Filter Fail Packets Queuing */
+		if (hw->vlan_fail_q_en) {
+			value = readl(ioaddr + GMAC_RXQ_CTRL4);
+			value &= ~GMAC_RXQCTRL_VFFQ_MASK;
+			value |= GMAC_RXQCTRL_VFFQE |
+				 (hw->vlan_fail_q << GMAC_RXQCTRL_VFFQ_SHIFT);
+			writel(value, ioaddr + GMAC_RXQ_CTRL4);
+			value = GMAC_PACKET_FILTER_PR | GMAC_PACKET_FILTER_RA;
+		} else {
+			value = GMAC_PACKET_FILTER_PR | GMAC_PACKET_FILTER_PCF;
+		}
+
 	} else if ((dev->flags & IFF_ALLMULTI) ||
 		   (netdev_mc_count(dev) > hw->multicast_filter_bins)) {
 		/* Pass all multi */
@@ -680,7 +691,7 @@ static void dwmac4_set_filter(struct mac_device_info *hw,
 
 	writel(value, ioaddr + GMAC_PACKET_FILTER);
 
-	if (dev->flags & IFF_PROMISC) {
+	if (dev->flags & IFF_PROMISC && !hw->vlan_fail_q_en) {
 		if (!hw->promisc) {
 			hw->promisc = 1;
 			dwmac4_vlan_promisc_enable(dev, hw);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h
index 3e8faa96b4d4..56b0762c1276 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h
@@ -92,6 +92,12 @@
 #define TCEIE				BIT(0)
 #define DMA_ECC_INT_STATUS		0x00001088
 
+/* EQoS version 5.xx VLAN Tag Filter Fail Packets Queuing */
+#define GMAC_RXQ_CTRL4			0x00000094
+#define GMAC_RXQCTRL_VFFQ_MASK		GENMASK(19, 17)
+#define GMAC_RXQCTRL_VFFQ_SHIFT		17
+#define GMAC_RXQCTRL_VFFQE		BIT(16)
+
 int dwmac5_safety_feat_config(void __iomem *ioaddr, unsigned int asp);
 int dwmac5_safety_feat_irq_status(struct net_device *ndev,
 		void __iomem *ioaddr, unsigned int asp,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 5e13e6f18dad..4779826b997d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -4713,6 +4713,9 @@ static int stmmac_hw_init(struct stmmac_priv *priv)
 	if (priv->dma_cap.tsoen)
 		dev_info(priv->device, "TSO supported\n");
 
+	priv->hw->vlan_fail_q_en = priv->plat->vlan_fail_q_en;
+	priv->hw->vlan_fail_q = priv->plat->vlan_fail_q;
+
 	/* Run HW quirks, if any */
 	if (priv->hwif_quirks) {
 		ret = priv->hwif_quirks(priv);
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index bd964c31d333..00e83c877496 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -198,5 +198,7 @@ struct plat_stmmacenet_data {
 	int mac_port_sel_speed;
 	bool en_tx_lpi_clockgating;
 	int has_xgmac;
+	bool vlan_fail_q_en;
+	u8 vlan_fail_q;
 };
 #endif
-- 
cgit v1.2.3


From ba5f4cfeac77fca981b199ec7f2396a3616e5216 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Thu, 24 Sep 2020 12:58:40 -0700
Subject: bpf: Add comment to document BTF type PTR_TO_BTF_ID_OR_NULL

The meaning of PTR_TO_BTF_ID_OR_NULL differs slightly from other types
denoted with the *_OR_NULL type. For example the types PTR_TO_SOCKET
and PTR_TO_SOCKET_OR_NULL can be used for branch analysis because the
type PTR_TO_SOCKET is guaranteed to _not_ have a null value.

In contrast PTR_TO_BTF_ID and BTF_TO_BTF_ID_OR_NULL have slightly
different meanings. A PTR_TO_BTF_TO_ID may be a pointer to NULL value,
but it is safe to read this pointer in the program context because
the program context will handle any faults. The fallout is for
PTR_TO_BTF_ID the verifier can assume reads are safe, but can not
use the type in branch analysis. Additionally, authors need to be
extra careful when passing PTR_TO_BTF_ID into helpers. In general
helpers consuming type PTR_TO_BTF_ID will need to assume it may
be null.

Seeing the above is not obvious to readers without the back knowledge
lets add a comment in the type definition.

Editorial comment, as networking and tracing programs get closer
and more tightly merged we may need to consider a new type that we
can ensure is non-null for branch analysis and also passing into
helpers.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Lorenz Bauer <lmb@cloudflare.com>
---
 include/linux/bpf.h | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index d0937f1d2980..79902325bef8 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -383,8 +383,22 @@ enum bpf_reg_type {
 	PTR_TO_TCP_SOCK_OR_NULL, /* reg points to struct tcp_sock or NULL */
 	PTR_TO_TP_BUFFER,	 /* reg points to a writable raw tp's buffer */
 	PTR_TO_XDP_SOCK,	 /* reg points to struct xdp_sock */
-	PTR_TO_BTF_ID,		 /* reg points to kernel struct */
-	PTR_TO_BTF_ID_OR_NULL,	 /* reg points to kernel struct or NULL */
+	/* PTR_TO_BTF_ID points to a kernel struct that does not need
+	 * to be null checked by the BPF program. This does not imply the
+	 * pointer is _not_ null and in practice this can easily be a null
+	 * pointer when reading pointer chains. The assumption is program
+	 * context will handle null pointer dereference typically via fault
+	 * handling. The verifier must keep this in mind and can make no
+	 * assumptions about null or non-null when doing branch analysis.
+	 * Further, when passed into helpers the helpers can not, without
+	 * additional context, assume the value is non-null.
+	 */
+	PTR_TO_BTF_ID,
+	/* PTR_TO_BTF_ID_OR_NULL points to a kernel struct that has not
+	 * been checked for null. Used primarily to inform the verifier
+	 * an explicit null check is required for this struct.
+	 */
+	PTR_TO_BTF_ID_OR_NULL,
 	PTR_TO_MEM,		 /* reg points to valid memory region */
 	PTR_TO_MEM_OR_NULL,	 /* reg points to valid memory region or NULL */
 	PTR_TO_RDONLY_BUF,	 /* reg points to a readonly buffer */
-- 
cgit v1.2.3


From da9aa5d96bfe49e903ce2bc01cfb8a776c2619e9 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 26 Sep 2020 09:03:57 +0200
Subject: fs: remove vfs_statx_fd

vfs_statx_fd is only used to implement vfs_fstat.  Remove vfs_statx_fd
and just implement vfs_fstat directly.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/stat.c          | 22 +++++++---------------
 include/linux/fs.h |  7 +------
 2 files changed, 8 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/fs/stat.c b/fs/stat.c
index 44f8ad346db4..2683a051ce07 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -126,35 +126,27 @@ int vfs_getattr(const struct path *path, struct kstat *stat,
 EXPORT_SYMBOL(vfs_getattr);
 
 /**
- * vfs_statx_fd - Get the enhanced basic attributes by file descriptor
+ * vfs_fstat - Get the basic attributes by file descriptor
  * @fd: The file descriptor referring to the file of interest
  * @stat: The result structure to fill in.
- * @request_mask: STATX_xxx flags indicating what the caller wants
- * @query_flags: Query mode (KSTAT_QUERY_FLAGS)
  *
  * This function is a wrapper around vfs_getattr().  The main difference is
  * that it uses a file descriptor to determine the file location.
  *
  * 0 will be returned on success, and a -ve error code if unsuccessful.
  */
-int vfs_statx_fd(unsigned int fd, struct kstat *stat,
-		 u32 request_mask, unsigned int query_flags)
+int vfs_fstat(int fd, struct kstat *stat)
 {
 	struct fd f;
-	int error = -EBADF;
-
-	if (query_flags & ~KSTAT_QUERY_FLAGS)
-		return -EINVAL;
+	int error;
 
 	f = fdget_raw(fd);
-	if (f.file) {
-		error = vfs_getattr(&f.file->f_path, stat,
-				    request_mask, query_flags);
-		fdput(f);
-	}
+	if (!f.file)
+		return -EBADF;
+	error = vfs_getattr(&f.file->f_path, stat, STATX_BASIC_STATS, 0);
+	fdput(f);
 	return error;
 }
-EXPORT_SYMBOL(vfs_statx_fd);
 
 static inline unsigned vfs_stat_set_lookup_flags(unsigned *lookup_flags,
 						 int flags)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e019ea2f1347..f100d9f711a3 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3163,7 +3163,7 @@ extern const struct inode_operations simple_symlink_inode_operations;
 extern int iterate_dir(struct file *, struct dir_context *);
 
 extern int vfs_statx(int, const char __user *, int, struct kstat *, u32);
-extern int vfs_statx_fd(unsigned int, struct kstat *, u32, unsigned int);
+int vfs_fstat(int fd, struct kstat *stat);
 
 static inline int vfs_stat(const char __user *filename, struct kstat *stat)
 {
@@ -3181,11 +3181,6 @@ static inline int vfs_fstatat(int dfd, const char __user *filename,
 	return vfs_statx(dfd, filename, flags | AT_NO_AUTOMOUNT,
 			 stat, STATX_BASIC_STATS);
 }
-static inline int vfs_fstat(int fd, struct kstat *stat)
-{
-	return vfs_statx_fd(fd, stat, STATX_BASIC_STATS, 0);
-}
-
 
 extern const char *vfs_get_link(struct dentry *, struct delayed_call *);
 extern int vfs_readlink(struct dentry *, char __user *, int);
-- 
cgit v1.2.3


From 0b2c6693b4220595e9cff95d829d5d5bc5d544dc Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 26 Sep 2020 09:03:58 +0200
Subject: fs: implement vfs_stat and vfs_lstat in terms of vfs_fstatat

Go through vfs_fstatat instead of duplicating the *stat to statx mapping
three times.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/fs.h | 16 +++++++---------
 1 file changed, 7 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index f100d9f711a3..b43c9ad7c3c2 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3165,21 +3165,19 @@ extern int iterate_dir(struct file *, struct dir_context *);
 extern int vfs_statx(int, const char __user *, int, struct kstat *, u32);
 int vfs_fstat(int fd, struct kstat *stat);
 
-static inline int vfs_stat(const char __user *filename, struct kstat *stat)
+static inline int vfs_fstatat(int dfd, const char __user *filename,
+			      struct kstat *stat, int flags)
 {
-	return vfs_statx(AT_FDCWD, filename, AT_NO_AUTOMOUNT,
+	return vfs_statx(dfd, filename, flags | AT_NO_AUTOMOUNT,
 			 stat, STATX_BASIC_STATS);
 }
-static inline int vfs_lstat(const char __user *name, struct kstat *stat)
+static inline int vfs_stat(const char __user *filename, struct kstat *stat)
 {
-	return vfs_statx(AT_FDCWD, name, AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT,
-			 stat, STATX_BASIC_STATS);
+	return vfs_fstatat(AT_FDCWD, filename, stat, 0);
 }
-static inline int vfs_fstatat(int dfd, const char __user *filename,
-			      struct kstat *stat, int flags)
+static inline int vfs_lstat(const char __user *name, struct kstat *stat)
 {
-	return vfs_statx(dfd, filename, flags | AT_NO_AUTOMOUNT,
-			 stat, STATX_BASIC_STATS);
+	return vfs_fstatat(AT_FDCWD, name, stat, AT_SYMLINK_NOFOLLOW);
 }
 
 extern const char *vfs_get_link(struct dentry *, struct delayed_call *);
-- 
cgit v1.2.3


From 09f1bde4017e9c34749da2918b3926799c77bce8 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 26 Sep 2020 09:03:59 +0200
Subject: fs: move vfs_fstatat out of line

This allows to keep vfs_statx static in fs/stat.c to prepare for the following
changes.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/stat.c          | 9 +++++++--
 include/linux/fs.h | 9 ++-------
 2 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/fs/stat.c b/fs/stat.c
index 2683a051ce07..ddf0176d4dbc 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -181,7 +181,7 @@ static inline unsigned vfs_stat_set_lookup_flags(unsigned *lookup_flags,
  *
  * 0 will be returned on success, and a -ve error code if unsuccessful.
  */
-int vfs_statx(int dfd, const char __user *filename, int flags,
+static int vfs_statx(int dfd, const char __user *filename, int flags,
 	      struct kstat *stat, u32 request_mask)
 {
 	struct path path;
@@ -209,8 +209,13 @@ retry:
 out:
 	return error;
 }
-EXPORT_SYMBOL(vfs_statx);
 
+int vfs_fstatat(int dfd, const char __user *filename,
+			      struct kstat *stat, int flags)
+{
+	return vfs_statx(dfd, filename, flags | AT_NO_AUTOMOUNT,
+			 stat, STATX_BASIC_STATS);
+}
 
 #ifdef __ARCH_WANT_OLD_STAT
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index b43c9ad7c3c2..1ac68236bc09 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3162,15 +3162,10 @@ extern const struct inode_operations simple_symlink_inode_operations;
 
 extern int iterate_dir(struct file *, struct dir_context *);
 
-extern int vfs_statx(int, const char __user *, int, struct kstat *, u32);
+int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat,
+		int flags);
 int vfs_fstat(int fd, struct kstat *stat);
 
-static inline int vfs_fstatat(int dfd, const char __user *filename,
-			      struct kstat *stat, int flags)
-{
-	return vfs_statx(dfd, filename, flags | AT_NO_AUTOMOUNT,
-			 stat, STATX_BASIC_STATS);
-}
 static inline int vfs_stat(const char __user *filename, struct kstat *stat)
 {
 	return vfs_fstatat(AT_FDCWD, filename, stat, 0);
-- 
cgit v1.2.3


From f2d077ff1b5c17008cff5dc27e7356a694e55462 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 26 Sep 2020 09:04:01 +0200
Subject: fs: remove KSTAT_QUERY_FLAGS

KSTAT_QUERY_FLAGS expands to AT_STATX_SYNC_TYPE, which itself already
is a mask.  Remove the double name, especially given that the prefix
is a little confusing vs the normal AT_* flags.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/stat.c            | 8 ++++----
 include/linux/stat.h | 2 --
 2 files changed, 4 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/fs/stat.c b/fs/stat.c
index 8acc4b14ac24..dacecdda2e79 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -56,7 +56,7 @@ EXPORT_SYMBOL(generic_fillattr);
  * @path: file to get attributes from
  * @stat: structure to return attributes in
  * @request_mask: STATX_xxx flags indicating what the caller wants
- * @query_flags: Query mode (KSTAT_QUERY_FLAGS)
+ * @query_flags: Query mode (AT_STATX_SYNC_TYPE)
  *
  * Get attributes without calling security_inode_getattr.
  *
@@ -71,7 +71,7 @@ int vfs_getattr_nosec(const struct path *path, struct kstat *stat,
 
 	memset(stat, 0, sizeof(*stat));
 	stat->result_mask |= STATX_BASIC_STATS;
-	query_flags &= KSTAT_QUERY_FLAGS;
+	query_flags &= AT_STATX_SYNC_TYPE;
 
 	/* allow the fs to override these if it really wants to */
 	/* SB_NOATIME means filesystem supplies dummy atime value */
@@ -97,7 +97,7 @@ EXPORT_SYMBOL(vfs_getattr_nosec);
  * @path: The file of interest
  * @stat: Where to return the statistics
  * @request_mask: STATX_xxx flags indicating what the caller wants
- * @query_flags: Query mode (KSTAT_QUERY_FLAGS)
+ * @query_flags: Query mode (AT_STATX_SYNC_TYPE)
  *
  * Ask the filesystem for a file's attributes.  The caller must indicate in
  * request_mask and query_flags to indicate what they want.
@@ -171,7 +171,7 @@ static int vfs_statx(int dfd, const char __user *filename, int flags,
 	int error;
 
 	if (flags & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT | AT_EMPTY_PATH |
-		      KSTAT_QUERY_FLAGS))
+		      AT_STATX_SYNC_TYPE))
 		return -EINVAL;
 
 	if (!(flags & AT_SYMLINK_NOFOLLOW))
diff --git a/include/linux/stat.h b/include/linux/stat.h
index 56614af83d4a..fff27e603814 100644
--- a/include/linux/stat.h
+++ b/include/linux/stat.h
@@ -19,8 +19,6 @@
 #include <linux/time.h>
 #include <linux/uidgid.h>
 
-#define KSTAT_QUERY_FLAGS (AT_STATX_SYNC_TYPE)
-
 struct kstat {
 	u32		result_mask;	/* What fields the user got */
 	umode_t		mode;
-- 
cgit v1.2.3


From e622129569963fa3bab976685443756e5da70da9 Mon Sep 17 00:00:00 2001
From: Yangbo Lu <yangbo.lu@nxp.com>
Date: Sun, 27 Sep 2020 16:01:50 +0800
Subject: ptp: add stub function for ptp_get_msgtype()

Added the missing stub function for ptp_get_msgtype().

Fixes: 036c508ba95e ("ptp: Add generic ptp message type function")
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Yangbo Lu <yangbo.lu@nxp.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org> # build-tested
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ptp_classify.h | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h
index 8437307cca8c..c6487b7ab026 100644
--- a/include/linux/ptp_classify.h
+++ b/include/linux/ptp_classify.h
@@ -134,5 +134,13 @@ static inline struct ptp_header *ptp_parse_header(struct sk_buff *skb,
 {
 	return NULL;
 }
+static inline u8 ptp_get_msgtype(const struct ptp_header *hdr,
+				 unsigned int type)
+{
+	/* The return is meaningless. The stub function would not be
+	 * executed since no available header from ptp_parse_header.
+	 */
+	return 0;
+}
 #endif
 #endif /* _PTP_CLASSIFY_H_ */
-- 
cgit v1.2.3


From c1135c7fd0e95740cd4619ce389f43ffce043140 Mon Sep 17 00:00:00 2001
From: Boqun Feng <boqun.feng@gmail.com>
Date: Wed, 16 Sep 2020 11:48:09 +0800
Subject: Drivers: hv: vmbus: Introduce types of GPADL

This patch introduces two types of GPADL: HV_GPADL_{BUFFER, RING}. The
types of GPADL are purely the concept in the guest, IOW the hypervisor
treat them as the same.

The reason of introducing the types for GPADL is to support guests whose
page size is not 4k (the page size of Hyper-V hypervisor). In these
guests, both the headers and the data parts of the ringbuffers need to
be aligned to the PAGE_SIZE, because 1) some of the ringbuffers will be
mapped into userspace and 2) we use "double mapping" mechanism to
support fast wrap-around, and "double mapping" relies on ringbuffers
being page-aligned. However, the Hyper-V hypervisor only uses 4k
(HV_HYP_PAGE_SIZE) headers. Our solution to this is that we always make
the headers of ringbuffers take one guest page and when GPADL is
established between the guest and hypervisor, the only first 4k of
header is used. To handle this special case, we need the types of GPADL
to differ different guest memory usage for GPADL.

Type enum is introduced along with several general interfaces to
describe the differences between normal buffer GPADL and ringbuffer
GPADL.

Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/20200916034817.30282-4-boqun.feng@gmail.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 drivers/hv/channel.c   | 160 ++++++++++++++++++++++++++++++++++++++++++-------
 include/linux/hyperv.h |  48 ++++++++++++++-
 2 files changed, 187 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 1cbe8fc931fc..45267b6d069e 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -35,6 +35,99 @@ static unsigned long virt_to_hvpfn(void *addr)
 	return  paddr >> HV_HYP_PAGE_SHIFT;
 }
 
+/*
+ * hv_gpadl_size - Return the real size of a gpadl, the size that Hyper-V uses
+ *
+ * For BUFFER gpadl, Hyper-V uses the exact same size as the guest does.
+ *
+ * For RING gpadl, in each ring, the guest uses one PAGE_SIZE as the header
+ * (because of the alignment requirement), however, the hypervisor only
+ * uses the first HV_HYP_PAGE_SIZE as the header, therefore leaving a
+ * (PAGE_SIZE - HV_HYP_PAGE_SIZE) gap. And since there are two rings in a
+ * ringbuffer, the total size for a RING gpadl that Hyper-V uses is the
+ * total size that the guest uses minus twice of the gap size.
+ */
+static inline u32 hv_gpadl_size(enum hv_gpadl_type type, u32 size)
+{
+	switch (type) {
+	case HV_GPADL_BUFFER:
+		return size;
+	case HV_GPADL_RING:
+		/* The size of a ringbuffer must be page-aligned */
+		BUG_ON(size % PAGE_SIZE);
+		/*
+		 * Two things to notice here:
+		 * 1) We're processing two ring buffers as a unit
+		 * 2) We're skipping any space larger than HV_HYP_PAGE_SIZE in
+		 * the first guest-size page of each of the two ring buffers.
+		 * So we effectively subtract out two guest-size pages, and add
+		 * back two Hyper-V size pages.
+		 */
+		return size - 2 * (PAGE_SIZE - HV_HYP_PAGE_SIZE);
+	}
+	BUG();
+	return 0;
+}
+
+/*
+ * hv_ring_gpadl_send_hvpgoffset - Calculate the send offset (in unit of
+ *                                 HV_HYP_PAGE) in a ring gpadl based on the
+ *                                 offset in the guest
+ *
+ * @offset: the offset (in bytes) where the send ringbuffer starts in the
+ *               virtual address space of the guest
+ */
+static inline u32 hv_ring_gpadl_send_hvpgoffset(u32 offset)
+{
+
+	/*
+	 * For RING gpadl, in each ring, the guest uses one PAGE_SIZE as the
+	 * header (because of the alignment requirement), however, the
+	 * hypervisor only uses the first HV_HYP_PAGE_SIZE as the header,
+	 * therefore leaving a (PAGE_SIZE - HV_HYP_PAGE_SIZE) gap.
+	 *
+	 * And to calculate the effective send offset in gpadl, we need to
+	 * substract this gap.
+	 */
+	return (offset - (PAGE_SIZE - HV_HYP_PAGE_SIZE)) >> HV_HYP_PAGE_SHIFT;
+}
+
+/*
+ * hv_gpadl_hvpfn - Return the Hyper-V page PFN of the @i th Hyper-V page in
+ *                  the gpadl
+ *
+ * @type: the type of the gpadl
+ * @kbuffer: the pointer to the gpadl in the guest
+ * @size: the total size (in bytes) of the gpadl
+ * @send_offset: the offset (in bytes) where the send ringbuffer starts in the
+ *               virtual address space of the guest
+ * @i: the index
+ */
+static inline u64 hv_gpadl_hvpfn(enum hv_gpadl_type type, void *kbuffer,
+				 u32 size, u32 send_offset, int i)
+{
+	int send_idx = hv_ring_gpadl_send_hvpgoffset(send_offset);
+	unsigned long delta = 0UL;
+
+	switch (type) {
+	case HV_GPADL_BUFFER:
+		break;
+	case HV_GPADL_RING:
+		if (i == 0)
+			delta = 0;
+		else if (i <= send_idx)
+			delta = PAGE_SIZE - HV_HYP_PAGE_SIZE;
+		else
+			delta = 2 * (PAGE_SIZE - HV_HYP_PAGE_SIZE);
+		break;
+	default:
+		BUG();
+		break;
+	}
+
+	return virt_to_hvpfn(kbuffer + delta + (HV_HYP_PAGE_SIZE * i));
+}
+
 /*
  * vmbus_setevent- Trigger an event notification on the specified
  * channel.
@@ -160,7 +253,8 @@ EXPORT_SYMBOL_GPL(vmbus_send_modifychannel);
 /*
  * create_gpadl_header - Creates a gpadl for the specified buffer
  */
-static int create_gpadl_header(void *kbuffer, u32 size,
+static int create_gpadl_header(enum hv_gpadl_type type, void *kbuffer,
+			       u32 size, u32 send_offset,
 			       struct vmbus_channel_msginfo **msginfo)
 {
 	int i;
@@ -173,7 +267,7 @@ static int create_gpadl_header(void *kbuffer, u32 size,
 
 	int pfnsum, pfncount, pfnleft, pfncurr, pfnsize;
 
-	pagecount = size >> HV_HYP_PAGE_SHIFT;
+	pagecount = hv_gpadl_size(type, size) >> HV_HYP_PAGE_SHIFT;
 
 	/* do we need a gpadl body msg */
 	pfnsize = MAX_SIZE_CHANNEL_MESSAGE -
@@ -200,10 +294,10 @@ static int create_gpadl_header(void *kbuffer, u32 size,
 		gpadl_header->range_buflen = sizeof(struct gpa_range) +
 					 pagecount * sizeof(u64);
 		gpadl_header->range[0].byte_offset = 0;
-		gpadl_header->range[0].byte_count = size;
+		gpadl_header->range[0].byte_count = hv_gpadl_size(type, size);
 		for (i = 0; i < pfncount; i++)
-			gpadl_header->range[0].pfn_array[i] = virt_to_hvpfn(
-				kbuffer + HV_HYP_PAGE_SIZE * i);
+			gpadl_header->range[0].pfn_array[i] = hv_gpadl_hvpfn(
+				type, kbuffer, size, send_offset, i);
 		*msginfo = msgheader;
 
 		pfnsum = pfncount;
@@ -254,8 +348,8 @@ static int create_gpadl_header(void *kbuffer, u32 size,
 			 * so the hypervisor guarantees that this is ok.
 			 */
 			for (i = 0; i < pfncurr; i++)
-				gpadl_body->pfn[i] = virt_to_hvpfn(
-					kbuffer + HV_HYP_PAGE_SIZE * (pfnsum + i));
+				gpadl_body->pfn[i] = hv_gpadl_hvpfn(type,
+					kbuffer, size, send_offset, pfnsum + i);
 
 			/* add to msg header */
 			list_add_tail(&msgbody->msglistentry,
@@ -281,10 +375,10 @@ static int create_gpadl_header(void *kbuffer, u32 size,
 		gpadl_header->range_buflen = sizeof(struct gpa_range) +
 					 pagecount * sizeof(u64);
 		gpadl_header->range[0].byte_offset = 0;
-		gpadl_header->range[0].byte_count = size;
+		gpadl_header->range[0].byte_count = hv_gpadl_size(type, size);
 		for (i = 0; i < pagecount; i++)
-			gpadl_header->range[0].pfn_array[i] = virt_to_hvpfn(
-				kbuffer + HV_HYP_PAGE_SIZE * i);
+			gpadl_header->range[0].pfn_array[i] = hv_gpadl_hvpfn(
+				type, kbuffer, size, send_offset, i);
 
 		*msginfo = msgheader;
 	}
@@ -297,15 +391,20 @@ nomem:
 }
 
 /*
- * vmbus_establish_gpadl - Establish a GPADL for the specified buffer
+ * __vmbus_establish_gpadl - Establish a GPADL for a buffer or ringbuffer
  *
  * @channel: a channel
+ * @type: the type of the corresponding GPADL, only meaningful for the guest.
  * @kbuffer: from kmalloc or vmalloc
  * @size: page-size multiple
+ * @send_offset: the offset (in bytes) where the send ring buffer starts,
+ * 		 should be 0 for BUFFER type gpadl
  * @gpadl_handle: some funky thing
  */
-int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer,
-			       u32 size, u32 *gpadl_handle)
+static int __vmbus_establish_gpadl(struct vmbus_channel *channel,
+				   enum hv_gpadl_type type, void *kbuffer,
+				   u32 size, u32 send_offset,
+				   u32 *gpadl_handle)
 {
 	struct vmbus_channel_gpadl_header *gpadlmsg;
 	struct vmbus_channel_gpadl_body *gpadl_body;
@@ -319,7 +418,7 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer,
 	next_gpadl_handle =
 		(atomic_inc_return(&vmbus_connection.next_gpadl_handle) - 1);
 
-	ret = create_gpadl_header(kbuffer, size, &msginfo);
+	ret = create_gpadl_header(type, kbuffer, size, send_offset, &msginfo);
 	if (ret)
 		return ret;
 
@@ -400,6 +499,21 @@ cleanup:
 	kfree(msginfo);
 	return ret;
 }
+
+/*
+ * vmbus_establish_gpadl - Establish a GPADL for the specified buffer
+ *
+ * @channel: a channel
+ * @kbuffer: from kmalloc or vmalloc
+ * @size: page-size multiple
+ * @gpadl_handle: some funky thing
+ */
+int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer,
+			  u32 size, u32 *gpadl_handle)
+{
+	return __vmbus_establish_gpadl(channel, HV_GPADL_BUFFER, kbuffer, size,
+				       0U, gpadl_handle);
+}
 EXPORT_SYMBOL_GPL(vmbus_establish_gpadl);
 
 static int __vmbus_open(struct vmbus_channel *newchannel,
@@ -438,10 +552,11 @@ static int __vmbus_open(struct vmbus_channel *newchannel,
 	/* Establish the gpadl for the ring buffer */
 	newchannel->ringbuffer_gpadlhandle = 0;
 
-	err = vmbus_establish_gpadl(newchannel,
-				    page_address(newchannel->ringbuffer_page),
-				    (send_pages + recv_pages) << PAGE_SHIFT,
-				    &newchannel->ringbuffer_gpadlhandle);
+	err = __vmbus_establish_gpadl(newchannel, HV_GPADL_RING,
+				      page_address(newchannel->ringbuffer_page),
+				      (send_pages + recv_pages) << PAGE_SHIFT,
+				      newchannel->ringbuffer_send_offset << PAGE_SHIFT,
+				      &newchannel->ringbuffer_gpadlhandle);
 	if (err)
 		goto error_clean_ring;
 
@@ -462,7 +577,13 @@ static int __vmbus_open(struct vmbus_channel *newchannel,
 	open_msg->openid = newchannel->offermsg.child_relid;
 	open_msg->child_relid = newchannel->offermsg.child_relid;
 	open_msg->ringbuffer_gpadlhandle = newchannel->ringbuffer_gpadlhandle;
-	open_msg->downstream_ringbuffer_pageoffset = newchannel->ringbuffer_send_offset;
+	/*
+	 * The unit of ->downstream_ringbuffer_pageoffset is HV_HYP_PAGE and
+	 * the unit of ->ringbuffer_send_offset (i.e. send_pages) is PAGE, so
+	 * here we calculate it into HV_HYP_PAGE.
+	 */
+	open_msg->downstream_ringbuffer_pageoffset =
+		hv_ring_gpadl_send_hvpgoffset(send_pages << PAGE_SHIFT);
 	open_msg->target_vp = hv_cpu_number_to_vp_number(newchannel->target_cpu);
 
 	if (userdatalen)
@@ -556,7 +677,6 @@ int vmbus_open(struct vmbus_channel *newchannel,
 }
 EXPORT_SYMBOL_GPL(vmbus_open);
 
-
 /*
  * vmbus_teardown_gpadl -Teardown the specified GPADL handle
  */
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 38100e80360a..9c19149c0e1a 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -29,6 +29,48 @@
 
 #pragma pack(push, 1)
 
+/*
+ * Types for GPADL, decides is how GPADL header is created.
+ *
+ * It doesn't make much difference between BUFFER and RING if PAGE_SIZE is the
+ * same as HV_HYP_PAGE_SIZE.
+ *
+ * If PAGE_SIZE is bigger than HV_HYP_PAGE_SIZE, the headers of ring buffers
+ * will be of PAGE_SIZE, however, only the first HV_HYP_PAGE will be put
+ * into gpadl, therefore the number for HV_HYP_PAGE and the indexes of each
+ * HV_HYP_PAGE will be different between different types of GPADL, for example
+ * if PAGE_SIZE is 64K:
+ *
+ * BUFFER:
+ *
+ * gva:    |--       64k      --|--       64k      --| ... |
+ * gpa:    | 4k | 4k | ... | 4k | 4k | 4k | ... | 4k |
+ * index:  0    1    2     15   16   17   18 .. 31   32 ...
+ *         |    |    ...   |    |    |   ...    |   ...
+ *         v    V          V    V    V          V
+ * gpadl:  | 4k | 4k | ... | 4k | 4k | 4k | ... | 4k | ... |
+ * index:  0    1    2 ... 15   16   17   18 .. 31   32 ...
+ *
+ * RING:
+ *
+ *         | header  |           data           | header  |     data      |
+ * gva:    |-- 64k --|--       64k      --| ... |-- 64k --|-- 64k --| ... |
+ * gpa:    | 4k | .. | 4k | 4k | ... | 4k | ... | 4k | .. | 4k | .. | ... |
+ * index:  0    1    16   17   18    31   ...   n   n+1  n+16 ...         2n
+ *         |         /    /          /          |         /               /
+ *         |        /    /          /           |        /               /
+ *         |       /    /   ...    /    ...     |       /      ...      /
+ *         |      /    /          /             |      /               /
+ *         |     /    /          /              |     /               /
+ *         V    V    V          V               V    V               v
+ * gpadl:  | 4k | 4k |   ...    |    ...        | 4k | 4k |  ...     |
+ * index:  0    1    2   ...    16   ...       n-15 n-14 n-13  ...  2n-30
+ */
+enum hv_gpadl_type {
+	HV_GPADL_BUFFER,
+	HV_GPADL_RING
+};
+
 /* Single-page buffer */
 struct hv_page_buffer {
 	u32 len;
@@ -111,7 +153,7 @@ struct hv_ring_buffer {
 	} feature_bits;
 
 	/* Pad it to PAGE_SIZE so that data starts on page boundary */
-	u8	reserved2[4028];
+	u8	reserved2[PAGE_SIZE - 68];
 
 	/*
 	 * Ring data starts here + RingDataStartOffset
@@ -120,6 +162,10 @@ struct hv_ring_buffer {
 	u8 buffer[];
 } __packed;
 
+/* Calculate the proper size of a ringbuffer, it must be page-aligned */
+#define VMBUS_RING_SIZE(payload_sz) PAGE_ALIGN(sizeof(struct hv_ring_buffer) + \
+					       (payload_sz))
+
 struct hv_ring_buffer_info {
 	struct hv_ring_buffer *ring_buffer;
 	u32 ring_size;			/* Include the shared header */
-- 
cgit v1.2.3


From bca6b91dfdd4347d8fe0bb97377dda0cacd51d82 Mon Sep 17 00:00:00 2001
From: Boqun Feng <boqun.feng@gmail.com>
Date: Wed, 16 Sep 2020 11:48:11 +0800
Subject: Drivers: hv: vmbus: Move virt_to_hvpfn() to hyperv header

There will be more places other than vmbus where we need to calculate
the Hyper-V page PFN from a virtual address, so move virt_to_hvpfn() to
hyperv generic header.

Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/20200916034817.30282-6-boqun.feng@gmail.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 drivers/hv/channel.c   | 13 -------------
 include/linux/hyperv.h | 15 +++++++++++++++
 2 files changed, 15 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 45267b6d069e..fbdda9938039 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -22,19 +22,6 @@
 
 #include "hyperv_vmbus.h"
 
-static unsigned long virt_to_hvpfn(void *addr)
-{
-	phys_addr_t paddr;
-
-	if (is_vmalloc_addr(addr))
-		paddr = page_to_phys(vmalloc_to_page(addr)) +
-					 offset_in_page(addr);
-	else
-		paddr = __pa(addr);
-
-	return  paddr >> HV_HYP_PAGE_SHIFT;
-}
-
 /*
  * hv_gpadl_size - Return the real size of a gpadl, the size that Hyper-V uses
  *
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 9c19149c0e1a..83456dc181a8 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -14,6 +14,7 @@
 
 #include <uapi/linux/hyperv.h>
 
+#include <linux/mm.h>
 #include <linux/types.h>
 #include <linux/scatterlist.h>
 #include <linux/list.h>
@@ -23,6 +24,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/interrupt.h>
 #include <linux/reciprocal_div.h>
+#include <asm/hyperv-tlfs.h>
 
 #define MAX_PAGE_BUFFER_COUNT				32
 #define MAX_MULTIPAGE_BUFFER_COUNT			32 /* 128K */
@@ -1676,4 +1678,17 @@ struct hyperv_pci_block_ops {
 
 extern struct hyperv_pci_block_ops hvpci_block_ops;
 
+static inline unsigned long virt_to_hvpfn(void *addr)
+{
+	phys_addr_t paddr;
+
+	if (is_vmalloc_addr(addr))
+		paddr = page_to_phys(vmalloc_to_page(addr)) +
+				     offset_in_page(addr);
+	else
+		paddr = __pa(addr);
+
+	return  paddr >> HV_HYP_PAGE_SHIFT;
+}
+
 #endif /* _HYPERV_H */
-- 
cgit v1.2.3


From 106dee08408118c5b50387817e74419436e8b651 Mon Sep 17 00:00:00 2001
From: Boqun Feng <boqun.feng@gmail.com>
Date: Wed, 16 Sep 2020 11:48:12 +0800
Subject: hv: hyperv.h: Introduce some hvpfn helper functions

When a guest communicate with the hypervisor, it must use HV_HYP_PAGE to
calculate PFN, so introduce a few hvpfn helper functions as the
counterpart of the page helper functions. This is the preparation for
supporting guest whose PAGE_SIZE is not 4k.

Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/20200916034817.30282-7-boqun.feng@gmail.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 include/linux/hyperv.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 83456dc181a8..1ce131f29f3b 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1691,4 +1691,9 @@ static inline unsigned long virt_to_hvpfn(void *addr)
 	return  paddr >> HV_HYP_PAGE_SHIFT;
 }
 
+#define NR_HV_HYP_PAGES_IN_PAGE	(PAGE_SIZE / HV_HYP_PAGE_SIZE)
+#define offset_in_hvpage(ptr)	((unsigned long)(ptr) & ~HV_HYP_PAGE_MASK)
+#define HVPFN_UP(x)	(((x) + HV_HYP_PAGE_SIZE-1) >> HV_HYP_PAGE_SHIFT)
+#define page_to_hvpfn(page)	(page_to_pfn(page) * NR_HV_HYP_PAGES_IN_PAGE)
+
 #endif /* _HYPERV_H */
-- 
cgit v1.2.3


From f2d10ff4a903813df767a4b56b651a26b938df06 Mon Sep 17 00:00:00 2001
From: Daniel Thompson <daniel.thompson@linaro.org>
Date: Sun, 27 Sep 2020 22:15:29 +0100
Subject: kgdb: Honour the kprobe blocklist when setting breakpoints

Currently kgdb has absolutely no safety rails in place to discourage or
prevent a user from placing a breakpoint in dangerous places such as
the debugger's own trap entry/exit and other places where it is not safe
to take synchronous traps.

Introduce a new config symbol KGDB_HONOUR_BLOCKLIST and modify the
default implementation of kgdb_validate_break_address() so that we use
the kprobe blocklist to prohibit instrumentation of critical functions
if the config symbol is set. The config symbol dependencies are set to
ensure that the blocklist will be enabled by default if we enable KGDB
and are compiling for an architecture where we HAVE_KPROBES.

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org>
Link: https://lore.kernel.org/r/20200927211531.1380577-2-daniel.thompson@linaro.org
Signed-off-by: Daniel Thompson <daniel.thompson@linaro.org>
---
 include/linux/kgdb.h      | 18 ++++++++++++++++++
 kernel/debug/debug_core.c |  4 ++++
 kernel/debug/kdb/kdb_bp.c |  9 +++++++++
 lib/Kconfig.kgdb          | 15 +++++++++++++++
 4 files changed, 46 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h
index 477b8b7c908f..0d6cf64c8bb1 100644
--- a/include/linux/kgdb.h
+++ b/include/linux/kgdb.h
@@ -16,6 +16,7 @@
 #include <linux/linkage.h>
 #include <linux/init.h>
 #include <linux/atomic.h>
+#include <linux/kprobes.h>
 #ifdef CONFIG_HAVE_ARCH_KGDB
 #include <asm/kgdb.h>
 #endif
@@ -335,6 +336,23 @@ extern int kgdb_nmicallin(int cpu, int trapnr, void *regs, int err_code,
 			  atomic_t *snd_rdy);
 extern void gdbstub_exit(int status);
 
+/*
+ * kgdb and kprobes both use the same (kprobe) blocklist (which makes sense
+ * given they are both typically hooked up to the same trap meaning on most
+ * architectures one cannot be used to debug the other)
+ *
+ * However on architectures where kprobes is not (yet) implemented we permit
+ * breakpoints everywhere rather than blocking everything by default.
+ */
+static inline bool kgdb_within_blocklist(unsigned long addr)
+{
+#ifdef CONFIG_KGDB_HONOUR_BLOCKLIST
+	return within_kprobe_blacklist(addr);
+#else
+	return false;
+#endif
+}
+
 extern int			kgdb_single_step;
 extern atomic_t			kgdb_active;
 #define in_dbg_master() \
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index 165e5b0c2083..6b9383fa8278 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -180,6 +180,10 @@ int __weak kgdb_validate_break_address(unsigned long addr)
 {
 	struct kgdb_bkpt tmp;
 	int err;
+
+	if (kgdb_within_blocklist(addr))
+		return -EINVAL;
+
 	/* Validate setting the breakpoint and then removing it.  If the
 	 * remove fails, the kernel needs to emit a bad message because we
 	 * are deep trouble not being able to put things back the way we
diff --git a/kernel/debug/kdb/kdb_bp.c b/kernel/debug/kdb/kdb_bp.c
index d7ebb2c79cb8..ec4940146612 100644
--- a/kernel/debug/kdb/kdb_bp.c
+++ b/kernel/debug/kdb/kdb_bp.c
@@ -306,6 +306,15 @@ static int kdb_bp(int argc, const char **argv)
 	if (!template.bp_addr)
 		return KDB_BADINT;
 
+	/*
+	 * This check is redundant (since the breakpoint machinery should
+	 * be doing the same check during kdb_bp_install) but gives the
+	 * user immediate feedback.
+	 */
+	diag = kgdb_validate_break_address(template.bp_addr);
+	if (diag)
+		return diag;
+
 	/*
 	 * Find an empty bp structure to allocate
 	 */
diff --git a/lib/Kconfig.kgdb b/lib/Kconfig.kgdb
index 256f2486f9bd..05dae05b6cc9 100644
--- a/lib/Kconfig.kgdb
+++ b/lib/Kconfig.kgdb
@@ -24,6 +24,21 @@ menuconfig KGDB
 
 if KGDB
 
+config KGDB_HONOUR_BLOCKLIST
+	bool "KGDB: use kprobe blocklist to prohibit unsafe breakpoints"
+	depends on HAVE_KPROBES
+	depends on MODULES
+	select KPROBES
+	default y
+	help
+	  If set to Y the debug core will use the kprobe blocklist to
+	  identify symbols where it is unsafe to set breakpoints.
+	  In particular this disallows instrumentation of functions
+	  called during debug trap handling and thus makes it very
+	  difficult to inadvertently provoke recursive trap handling.
+
+	  If unsure, say Y.
+
 config KGDB_SERIAL_CONSOLE
 	tristate "KGDB: use kgdb over the serial console"
 	select CONSOLE_POLL
-- 
cgit v1.2.3


From d2b7588a47de8322891de38ec14d15105d66cb1e Mon Sep 17 00:00:00 2001
From: Thomas Pedersen <thomas@adapt-ip.com>
Date: Mon, 21 Sep 2020 19:28:04 -0700
Subject: nl80211: support S1G capability overrides in assoc

NL80211_ATTR_S1G_CAPABILITY can be passed along with
NL80211_ATTR_S1G_CAPABILITY_MASK to NL80211_CMD_ASSOCIATE
to indicate S1G capabilities which should override the
hardware capabilities in eg. the association request.

Signed-off-by: Thomas Pedersen <thomas@adapt-ip.com>
Link: https://lore.kernel.org/r/20200922022818.15855-4-thomas@adapt-ip.com
[johannes: always require both attributes together, commit message]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h    |  2 ++
 include/net/cfg80211.h       |  3 +++
 include/uapi/linux/nl80211.h |  9 +++++++++
 net/wireless/nl80211.c       | 20 ++++++++++++++++++++
 4 files changed, 34 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 53fba39d4ba6..f71cffa18176 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -2330,6 +2330,8 @@ ieee80211_he_spr_size(const u8 *he_spr_ie)
 }
 
 /* S1G Capabilities Information field */
+#define IEEE80211_S1G_CAPABILITY_LEN	15
+
 #define S1G_CAP0_S1G_LONG	BIT(0)
 #define S1G_CAP0_SGI_1MHZ	BIT(1)
 #define S1G_CAP0_SGI_2MHZ	BIT(2)
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 11eb81676e95..bead4b9afeca 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -2556,6 +2556,8 @@ enum cfg80211_assoc_req_flags {
  * @fils_nonces: FILS nonces (part of AAD) for protecting (Re)Association
  *	Request/Response frame or %NULL if FILS is not used. This field starts
  *	with 16 octets of STA Nonce followed by 16 octets of AP Nonce.
+ * @s1g_capa: S1G capability override
+ * @s1g_capa_mask: S1G capability override mask
  */
 struct cfg80211_assoc_request {
 	struct cfg80211_bss *bss;
@@ -2570,6 +2572,7 @@ struct cfg80211_assoc_request {
 	const u8 *fils_kek;
 	size_t fils_kek_len;
 	const u8 *fils_nonces;
+	struct ieee80211_s1g_cap s1g_capa, s1g_capa_mask;
 };
 
 /**
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index c74ceaddb909..05db40b4c56f 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -2521,6 +2521,12 @@ enum nl80211_commands {
  *	unsolicited broadcast probe response. It is a nested attribute, see
  *	&enum nl80211_unsol_bcast_probe_resp_attributes.
  *
+ * @NL80211_ATTR_S1G_CAPABILITY: S1G Capability information element (from
+ *	association request when used with NL80211_CMD_NEW_STATION)
+ * @NL80211_ATTR_S1G_CAPABILITY_MASK: S1G Capability Information element
+ *	override mask. Used with NL80211_ATTR_S1G_CAPABILITY in
+ *	NL80211_CMD_ASSOCIATE or NL80211_CMD_CONNECT.
+ *
  * @NUM_NL80211_ATTR: total number of nl80211_attrs available
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
@@ -3007,6 +3013,9 @@ enum nl80211_attrs {
 
 	NL80211_ATTR_UNSOL_BCAST_PROBE_RESP,
 
+	NL80211_ATTR_S1G_CAPABILITY,
+	NL80211_ATTR_S1G_CAPABILITY_MASK,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index d98db166d5e6..d31451db5407 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -704,6 +704,10 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 		NLA_POLICY_NESTED(nl80211_fils_discovery_policy),
 	[NL80211_ATTR_UNSOL_BCAST_PROBE_RESP] =
 		NLA_POLICY_NESTED(nl80211_unsol_bcast_probe_resp_policy),
+	[NL80211_ATTR_S1G_CAPABILITY] =
+		NLA_POLICY_EXACT_LEN(IEEE80211_S1G_CAPABILITY_LEN),
+	[NL80211_ATTR_S1G_CAPABILITY_MASK] =
+		NLA_POLICY_EXACT_LEN(IEEE80211_S1G_CAPABILITY_LEN),
 };
 
 /* policy for the key attributes */
@@ -9792,6 +9796,22 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info)
 			nla_data(info->attrs[NL80211_ATTR_FILS_NONCES]);
 	}
 
+	if (info->attrs[NL80211_ATTR_S1G_CAPABILITY_MASK]) {
+		if (!info->attrs[NL80211_ATTR_S1G_CAPABILITY])
+			return -EINVAL;
+		memcpy(&req.s1g_capa_mask,
+		       nla_data(info->attrs[NL80211_ATTR_S1G_CAPABILITY_MASK]),
+		       sizeof(req.s1g_capa_mask));
+	}
+
+	if (info->attrs[NL80211_ATTR_S1G_CAPABILITY]) {
+		if (!info->attrs[NL80211_ATTR_S1G_CAPABILITY_MASK])
+			return -EINVAL;
+		memcpy(&req.s1g_capa,
+		       nla_data(info->attrs[NL80211_ATTR_S1G_CAPABILITY]),
+		       sizeof(req.s1g_capa));
+	}
+
 	err = nl80211_crypto_settings(rdev, info, &req.crypto, 1);
 	if (!err) {
 		wdev_lock(dev->ieee80211_ptr);
-- 
cgit v1.2.3


From 9eaffe5078ca0808603cdd15c4eaf0106a996f3a Mon Sep 17 00:00:00 2001
From: Thomas Pedersen <thomas@adapt-ip.com>
Date: Mon, 21 Sep 2020 19:28:06 -0700
Subject: cfg80211: convert S1G beacon to scan results

The S1G beacon is an extension frame as opposed to
management frame for the regular beacon. This means we may
have to occasionally cast the frame buffer to a different
header type. Luckily this isn't too bad as scan results
mostly only care about the IEs.

Signed-off-by: Thomas Pedersen <thomas@adapt-ip.com>
Link: https://lore.kernel.org/r/20200922022818.15855-6-thomas@adapt-ip.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 32 ++++++++++++++++++++++++++
 net/wireless/scan.c       | 57 +++++++++++++++++++++++++++++++++++++++--------
 2 files changed, 80 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index f71cffa18176..1ce0b37441b9 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -151,6 +151,9 @@
 
 #define IEEE80211_ANO_NETTYPE_WILD              15
 
+/* bits unique to S1G beacon */
+#define IEEE80211_S1G_BCN_NEXT_TBTT    0x100
+
 /* control extension - for IEEE80211_FTYPE_CTL | IEEE80211_STYPE_CTL_EXT */
 #define IEEE80211_CTL_EXT_POLL		0x2000
 #define IEEE80211_CTL_EXT_SPR		0x3000
@@ -553,6 +556,28 @@ static inline bool ieee80211_is_s1g_beacon(__le16 fc)
 	       cpu_to_le16(IEEE80211_FTYPE_EXT | IEEE80211_STYPE_S1G_BEACON);
 }
 
+/**
+ * ieee80211_next_tbtt_present - check if IEEE80211_FTYPE_EXT &&
+ * IEEE80211_STYPE_S1G_BEACON && IEEE80211_S1G_BCN_NEXT_TBTT
+ * @fc: frame control bytes in little-endian byteorder
+ */
+static inline bool ieee80211_next_tbtt_present(__le16 fc)
+{
+	return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) ==
+	       cpu_to_le16(IEEE80211_FTYPE_EXT | IEEE80211_STYPE_S1G_BEACON) &&
+	       fc & cpu_to_le16(IEEE80211_S1G_BCN_NEXT_TBTT);
+}
+
+/**
+ * ieee80211_is_s1g_short_beacon - check if next tbtt present bit is set. Only
+ * true for S1G beacons when they're short.
+ * @fc: frame control bytes in little-endian byteorder
+ */
+static inline bool ieee80211_is_s1g_short_beacon(__le16 fc)
+{
+	return ieee80211_is_s1g_beacon(fc) && ieee80211_next_tbtt_present(fc);
+}
+
 /**
  * ieee80211_is_atim - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ATIM
  * @fc: frame control bytes in little-endian byteorder
@@ -1034,6 +1059,13 @@ struct ieee80211_ext {
 			u8 change_seq;
 			u8 variable[0];
 		} __packed s1g_beacon;
+		struct {
+			u8 sa[ETH_ALEN];
+			__le32 timestamp;
+			u8 change_seq;
+			u8 next_tbtt[3];
+			u8 variable[0];
+		} __packed s1g_short_beacon;
 	} u;
 } __packed __aligned(2);
 
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 4fbeb17580d9..777df5751285 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -2294,8 +2294,11 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy,
 	struct cfg80211_bss_ies *ies;
 	struct ieee80211_channel *channel;
 	bool signal_valid;
-	size_t ielen = len - offsetof(struct ieee80211_mgmt,
-				      u.probe_resp.variable);
+	struct ieee80211_ext *ext = NULL;
+	u8 *bssid, *variable;
+	u16 capability, beacon_int;
+	size_t ielen, min_hdr_len = offsetof(struct ieee80211_mgmt,
+					     u.probe_resp.variable);
 	int bss_type;
 
 	BUILD_BUG_ON(offsetof(struct ieee80211_mgmt, u.probe_resp.variable) !=
@@ -2313,21 +2316,57 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy,
 		    (data->signal < 0 || data->signal > 100)))
 		return NULL;
 
-	if (WARN_ON(len < offsetof(struct ieee80211_mgmt, u.probe_resp.variable)))
+	if (ieee80211_is_s1g_beacon(mgmt->frame_control)) {
+		ext = (void *) mgmt;
+		min_hdr_len = offsetof(struct ieee80211_ext, u.s1g_beacon);
+		if (ieee80211_is_s1g_short_beacon(mgmt->frame_control))
+			min_hdr_len = offsetof(struct ieee80211_ext,
+					       u.s1g_short_beacon.variable);
+	}
+
+	if (WARN_ON(len < min_hdr_len))
 		return NULL;
 
-	channel = cfg80211_get_bss_channel(wiphy, mgmt->u.beacon.variable,
+	ielen = len - min_hdr_len;
+	variable = mgmt->u.probe_resp.variable;
+	if (ext) {
+		if (ieee80211_is_s1g_short_beacon(mgmt->frame_control))
+			variable = ext->u.s1g_short_beacon.variable;
+		else
+			variable = ext->u.s1g_beacon.variable;
+	}
+
+	channel = cfg80211_get_bss_channel(wiphy, variable,
 					   ielen, data->chan, data->scan_width);
 	if (!channel)
 		return NULL;
 
+	if (ext) {
+		struct ieee80211_s1g_bcn_compat_ie *compat;
+		u8 *ie;
+
+		ie = (void *)cfg80211_find_ie(WLAN_EID_S1G_BCN_COMPAT,
+					      variable, ielen);
+		if (!ie)
+			return NULL;
+		compat = (void *)(ie + 2);
+		bssid = ext->u.s1g_beacon.sa;
+		capability = le16_to_cpu(compat->compat_info);
+		beacon_int = le16_to_cpu(compat->beacon_int);
+	} else {
+		bssid = mgmt->bssid;
+		beacon_int = le16_to_cpu(mgmt->u.probe_resp.beacon_int);
+		capability = le16_to_cpu(mgmt->u.probe_resp.capab_info);
+	}
+
 	ies = kzalloc(sizeof(*ies) + ielen, gfp);
 	if (!ies)
 		return NULL;
 	ies->len = ielen;
 	ies->tsf = le64_to_cpu(mgmt->u.probe_resp.timestamp);
-	ies->from_beacon = ieee80211_is_beacon(mgmt->frame_control);
-	memcpy(ies->data, mgmt->u.probe_resp.variable, ielen);
+	ies->from_beacon = ieee80211_is_beacon(mgmt->frame_control) ||
+			   ieee80211_is_s1g_beacon(mgmt->frame_control);
+	memcpy(ies->data, variable, ielen);
 
 	if (ieee80211_is_probe_resp(mgmt->frame_control))
 		rcu_assign_pointer(tmp.pub.proberesp_ies, ies);
@@ -2335,12 +2374,12 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy,
 		rcu_assign_pointer(tmp.pub.beacon_ies, ies);
 	rcu_assign_pointer(tmp.pub.ies, ies);
 
-	memcpy(tmp.pub.bssid, mgmt->bssid, ETH_ALEN);
+	memcpy(tmp.pub.bssid, bssid, ETH_ALEN);
+	tmp.pub.beacon_interval = beacon_int;
+	tmp.pub.capability = capability;
 	tmp.pub.channel = channel;
 	tmp.pub.scan_width = data->scan_width;
 	tmp.pub.signal = data->signal;
-	tmp.pub.beacon_interval = le16_to_cpu(mgmt->u.probe_resp.beacon_int);
-	tmp.pub.capability = le16_to_cpu(mgmt->u.probe_resp.capab_info);
 	tmp.ts_boottime = data->boottime_ns;
 	tmp.parent_tsf = data->parent_tsf;
 	tmp.pub.chains = data->chains;
-- 
cgit v1.2.3


From 80ca25711380c8eabe51eed875ca9432b4f8939e Mon Sep 17 00:00:00 2001
From: Thomas Pedersen <thomas@adapt-ip.com>
Date: Mon, 21 Sep 2020 19:28:09 -0700
Subject: cfg80211: handle Association Response from S1G STA

The sending STA type is implicit based on beacon or probe
response content. If sending STA was an S1G STA, adjust
the Information Element location accordingly.

Signed-off-by: Thomas Pedersen <thomas@adapt-ip.com>
Link: https://lore.kernel.org/r/20200922022818.15855-9-thomas@adapt-ip.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h |  5 +++++
 net/wireless/mlme.c       | 14 +++++++++++---
 2 files changed, 16 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 1ce0b37441b9..d0fda8424118 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1100,6 +1100,11 @@ struct ieee80211_mgmt {
 			/* followed by Supported rates */
 			u8 variable[0];
 		} __packed assoc_resp, reassoc_resp;
+		struct {
+			__le16 capab_info;
+			__le16 status_code;
+			u8 variable[0];
+		} __packed s1g_assoc_resp, s1g_reassoc_resp;
 		struct {
 			__le16 capab_info;
 			__le16 listen_interval;
diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c
index db7333e20dd7..0ac820780437 100644
--- a/net/wireless/mlme.c
+++ b/net/wireless/mlme.c
@@ -30,6 +30,15 @@ void cfg80211_rx_assoc_resp(struct net_device *dev, struct cfg80211_bss *bss,
 	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)buf;
 	struct cfg80211_connect_resp_params cr;
+	const u8 *resp_ie = mgmt->u.assoc_resp.variable;
+	size_t resp_ie_len = len - offsetof(struct ieee80211_mgmt,
+					    u.assoc_resp.variable);
+
+	if (bss->channel->band == NL80211_BAND_S1GHZ) {
+		resp_ie = (u8 *)&mgmt->u.s1g_assoc_resp.variable;
+		resp_ie_len = len - offsetof(struct ieee80211_mgmt,
+					     u.s1g_assoc_resp.variable);
+	}
 
 	memset(&cr, 0, sizeof(cr));
 	cr.status = (int)le16_to_cpu(mgmt->u.assoc_resp.status_code);
@@ -37,9 +46,8 @@ void cfg80211_rx_assoc_resp(struct net_device *dev, struct cfg80211_bss *bss,
 	cr.bss = bss;
 	cr.req_ie = req_ies;
 	cr.req_ie_len = req_ies_len;
-	cr.resp_ie = mgmt->u.assoc_resp.variable;
-	cr.resp_ie_len =
-		len - offsetof(struct ieee80211_mgmt, u.assoc_resp.variable);
+	cr.resp_ie = resp_ie;
+	cr.resp_ie_len = resp_ie_len;
 	cr.timeout_reason = NL80211_TIMEOUT_UNSPECIFIED;
 
 	trace_cfg80211_send_rx_assoc(dev, bss);
-- 
cgit v1.2.3


From 05d109576a36fd498e5db2d905eb50c7dd844b83 Mon Sep 17 00:00:00 2001
From: Thomas Pedersen <thomas@adapt-ip.com>
Date: Mon, 21 Sep 2020 19:28:10 -0700
Subject: mac80211: encode listen interval for S1G

S1G allows listen interval up to 2^14 * 10000 beacon
intervals. In order to do this listen interval needs a
scaling factor applied to the lower 14 bits. Calculate
this and properly encode the listen interval for S1G STAs.

See IEEE802.11ah-2016 Table 9-44a for reference.

Signed-off-by: Thomas Pedersen <thomas@adapt-ip.com>
Link: https://lore.kernel.org/r/20200922022818.15855-10-thomas@adapt-ip.com
[move listen_int_usf into function using it]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h  |  7 +++++++
 net/mac80211/ieee80211_i.h |  1 +
 net/mac80211/mlme.c        | 10 ++++++----
 net/mac80211/util.c        | 21 +++++++++++++++++++++
 4 files changed, 35 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index d0fda8424118..7b6af47dd279 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -2448,6 +2448,13 @@ ieee80211_he_spr_size(const u8 *he_spr_ie)
 #define S1G_OPER_CH_WIDTH_PRIMARY_1MHZ	BIT(0)
 #define S1G_OPER_CH_WIDTH_OPER		GENMASK(4, 1)
 
+
+#define LISTEN_INT_USF	GENMASK(15, 14)
+#define LISTEN_INT_UI	GENMASK(13, 0)
+
+#define IEEE80211_MAX_USF	FIELD_MAX(LISTEN_INT_USF)
+#define IEEE80211_MAX_UI	FIELD_MAX(LISTEN_INT_UI)
+
 /* Authentication algorithms */
 #define WLAN_AUTH_OPEN 0
 #define WLAN_AUTH_SHARED_KEY 1
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index f6b209e0b3c7..d4644efc7356 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -2300,6 +2300,7 @@ void ieee80211_tdls_chsw_work(struct work_struct *wk);
 void ieee80211_tdls_handle_disconnect(struct ieee80211_sub_if_data *sdata,
 				      const u8 *peer, u16 reason);
 const char *ieee80211_get_reason_code_string(u16 reason_code);
+u16 ieee80211_encode_usf(int val);
 
 extern const struct ethtool_ops ieee80211_ethtool_ops;
 
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index b69fab1aff2d..70b6f5ee4757 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -696,6 +696,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 	struct ieee80211_chanctx_conf *chanctx_conf;
 	struct ieee80211_channel *chan;
 	u32 rates = 0;
+	__le16 listen_int;
 	struct element *ext_capa = NULL;
 
 	/* we know it's writable, cast away the const */
@@ -784,13 +785,15 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 	memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN);
 	memcpy(mgmt->bssid, assoc_data->bss->bssid, ETH_ALEN);
 
+	listen_int = cpu_to_le16(sband->band == NL80211_BAND_S1GHZ ?
+			ieee80211_encode_usf(local->hw.conf.listen_interval) :
+			local->hw.conf.listen_interval);
 	if (!is_zero_ether_addr(assoc_data->prev_bssid)) {
 		skb_put(skb, 10);
 		mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT |
 						  IEEE80211_STYPE_REASSOC_REQ);
 		mgmt->u.reassoc_req.capab_info = cpu_to_le16(capab);
-		mgmt->u.reassoc_req.listen_interval =
-				cpu_to_le16(local->hw.conf.listen_interval);
+		mgmt->u.reassoc_req.listen_interval = listen_int;
 		memcpy(mgmt->u.reassoc_req.current_ap, assoc_data->prev_bssid,
 		       ETH_ALEN);
 	} else {
@@ -798,8 +801,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 		mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT |
 						  IEEE80211_STYPE_ASSOC_REQ);
 		mgmt->u.assoc_req.capab_info = cpu_to_le16(capab);
-		mgmt->u.assoc_req.listen_interval =
-				cpu_to_le16(local->hw.conf.listen_interval);
+		mgmt->u.assoc_req.listen_interval = listen_int;
 	}
 
 	/* SSID */
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index c34cdac3363f..7bdbff35d28c 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -4383,3 +4383,24 @@ const u8 ieee80211_ac_to_qos_mask[IEEE80211_NUM_ACS] = {
 	IEEE80211_WMM_IE_STA_QOSINFO_AC_BE,
 	IEEE80211_WMM_IE_STA_QOSINFO_AC_BK
 };
+
+u16 ieee80211_encode_usf(int listen_interval)
+{
+	static const int listen_int_usf[] = { 1, 10, 1000, 10000 };
+	u16 ui, usf = 0;
+
+	/* find greatest USF */
+	while (usf < IEEE80211_MAX_USF) {
+		if (listen_interval % listen_int_usf[usf + 1])
+			break;
+		usf += 1;
+	}
+	ui = listen_interval / listen_int_usf[usf];
+
+	/* error if there is a remainder. Should've been checked by user */
+	WARN_ON_ONCE(ui > IEEE80211_MAX_UI);
+	listen_interval = FIELD_PREP(LISTEN_INT_USF, usf) |
+			  FIELD_PREP(LISTEN_INT_UI, ui);
+
+	return (u16) listen_interval;
+}
-- 
cgit v1.2.3


From 1d00ce807efaa0ee3a96de7801be042a06d35873 Mon Sep 17 00:00:00 2001
From: Thomas Pedersen <thomas@adapt-ip.com>
Date: Mon, 21 Sep 2020 19:28:15 -0700
Subject: mac80211: support S1G association

The changes required for associating in S1G are:

- apply S1G BSS channel info before assoc
- mark all S1G STAs as QoS STAs
- include and parse AID request element
- handle new Association Response format
- don't fail assoc if supported rates element is missing

Signed-off-by: Thomas Pedersen <thomas@adapt-ip.com>
Link: https://lore.kernel.org/r/20200922022818.15855-15-thomas@adapt-ip.com
[pass skb to ieee80211_add_aid_request_ie(), remove unused variable 'bss']
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h  | 21 +++++++++++++
 include/net/mac80211.h     |  2 ++
 net/mac80211/cfg.c         |  2 ++
 net/mac80211/ibss.c        |  3 +-
 net/mac80211/ieee80211_i.h |  5 +++
 net/mac80211/mlme.c        | 78 +++++++++++++++++++++++++++++++++++++++-------
 net/mac80211/util.c        | 53 +++++++++++++++++++++++++++++++
 7 files changed, 151 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 7b6af47dd279..f2f56b287aed 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -987,6 +987,25 @@ enum ieee80211_vht_opmode_bits {
 	IEEE80211_OPMODE_NOTIF_RX_NSS_TYPE_BF	= 0x80,
 };
 
+/**
+ * enum ieee80211_s1g_chanwidth
+ * These are defined in IEEE802.11-2016ah Table 10-20
+ * as BSS Channel Width
+ *
+ * @IEEE80211_S1G_CHANWIDTH_1MHZ: 1MHz operating channel
+ * @IEEE80211_S1G_CHANWIDTH_2MHZ: 2MHz operating channel
+ * @IEEE80211_S1G_CHANWIDTH_4MHZ: 4MHz operating channel
+ * @IEEE80211_S1G_CHANWIDTH_8MHZ: 8MHz operating channel
+ * @IEEE80211_S1G_CHANWIDTH_16MHZ: 16MHz operating channel
+ */
+enum ieee80211_s1g_chanwidth {
+	IEEE80211_S1G_CHANWIDTH_1MHZ = 0,
+	IEEE80211_S1G_CHANWIDTH_2MHZ = 1,
+	IEEE80211_S1G_CHANWIDTH_4MHZ = 3,
+	IEEE80211_S1G_CHANWIDTH_8MHZ = 7,
+	IEEE80211_S1G_CHANWIDTH_16MHZ = 15,
+};
+
 #define WLAN_SA_QUERY_TR_ID_LEN 2
 #define WLAN_MEMBERSHIP_LEN 8
 #define WLAN_USER_POSITION_LEN 16
@@ -2854,6 +2873,8 @@ enum ieee80211_eid {
 
 	WLAN_EID_REDUCED_NEIGHBOR_REPORT = 201,
 
+	WLAN_EID_AID_REQUEST = 210,
+	WLAN_EID_AID_RESPONSE = 211,
 	WLAN_EID_S1G_BCN_COMPAT = 213,
 	WLAN_EID_S1G_SHORT_BCN_INTERVAL = 214,
 	WLAN_EID_S1G_CAPABILITIES = 217,
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index de22524e9270..72bc877d2c22 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -627,6 +627,7 @@ struct ieee80211_fils_discovery {
  * @fils_discovery: FILS discovery configuration
  * @unsol_bcast_probe_resp_interval: Unsolicited broadcast probe response
  *	interval.
+ * @s1g: BSS is S1G BSS (affects Association Request format).
  */
 struct ieee80211_bss_conf {
 	const u8 *bssid;
@@ -696,6 +697,7 @@ struct ieee80211_bss_conf {
 	struct cfg80211_he_bss_color he_bss_color;
 	struct ieee80211_fils_discovery fils_discovery;
 	u32 unsol_bcast_probe_resp_interval;
+	bool s1g;
 };
 
 /**
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 8d75a4045d6e..da70f174d629 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1124,6 +1124,8 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
 	       sizeof(struct ieee80211_he_obss_pd));
 	memcpy(&sdata->vif.bss_conf.he_bss_color, &params->he_bss_color,
 	       sizeof(struct ieee80211_he_bss_color));
+	sdata->vif.bss_conf.s1g = params->chandef.chan->band ==
+				  NL80211_BAND_S1GHZ;
 
 	sdata->vif.bss_conf.ssid_len = params->ssid_len;
 	if (params->ssid_len)
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index c0963969a465..1f552f374e97 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -1037,7 +1037,8 @@ static void ieee80211_update_sta_info(struct ieee80211_sub_if_data *sdata,
 	}
 
 	if (sta && !sta->sta.wme &&
-	    elems->wmm_info && local->hw.queues >= IEEE80211_NUM_ACS) {
+	    (elems->wmm_info || elems->s1g_capab) &&
+	    local->hw.queues >= IEEE80211_NUM_ACS) {
 		sta->sta.wme = true;
 		ieee80211_check_fast_xmit(sta);
 	}
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 7b4a16a78fc8..c3e3578574a6 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1538,6 +1538,7 @@ struct ieee802_11_elems {
 	const struct ieee80211_s1g_cap *s1g_capab;
 	const struct ieee80211_s1g_oper_ie *s1g_oper;
 	const struct ieee80211_s1g_bcn_compat_ie *s1g_bcn_compat;
+	const struct ieee80211_aid_response_ie *aid_resp;
 
 	/* length of them, respectively */
 	u8 ext_capab_len;
@@ -2213,6 +2214,8 @@ u8 *ieee80211_add_wmm_info_ie(u8 *buf, u8 qosinfo);
 void ieee80211_add_s1g_capab_ie(struct ieee80211_sub_if_data *sdata,
 				struct ieee80211_sta_s1g_cap *caps,
 				struct sk_buff *skb);
+void ieee80211_add_aid_request_ie(struct ieee80211_sub_if_data *sdata,
+				  struct sk_buff *skb);
 
 /* channel management */
 bool ieee80211_chandef_ht_oper(const struct ieee80211_ht_operation *ht_oper,
@@ -2224,6 +2227,8 @@ bool ieee80211_chandef_vht_oper(struct ieee80211_hw *hw, u32 vht_cap_info,
 bool ieee80211_chandef_he_6ghz_oper(struct ieee80211_sub_if_data *sdata,
 				    const struct ieee80211_he_operation *he_oper,
 				    struct cfg80211_chan_def *chandef);
+bool ieee80211_chandef_s1g_oper(const struct ieee80211_s1g_oper_ie *oper,
+				struct cfg80211_chan_def *chandef);
 u32 ieee80211_chandef_downgrade(struct cfg80211_chan_def *c);
 
 int __must_check
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index fbe64a72eaff..e2df4d54d9df 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -149,6 +149,7 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata,
 			     const struct ieee80211_ht_operation *ht_oper,
 			     const struct ieee80211_vht_operation *vht_oper,
 			     const struct ieee80211_he_operation *he_oper,
+			     const struct ieee80211_s1g_oper_ie *s1g_oper,
 			     struct cfg80211_chan_def *chandef, bool tracking)
 {
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
@@ -176,6 +177,15 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata,
 	memcpy(&sta_ht_cap, &sband->ht_cap, sizeof(sta_ht_cap));
 	ieee80211_apply_htcap_overrides(sdata, &sta_ht_cap);
 
+	if (s1g_oper && sband->band == NL80211_BAND_S1GHZ) {
+		ieee80211_chandef_s1g_oper(s1g_oper, chandef);
+		ret = IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_40MHZ |
+		      IEEE80211_STA_DISABLE_VHT |
+		      IEEE80211_STA_DISABLE_80P80MHZ |
+		      IEEE80211_STA_DISABLE_160MHZ;
+		goto out;
+	}
+
 	if (!ht_oper || !sta_ht_cap.ht_supported) {
 		ret = IEEE80211_STA_DISABLE_HT |
 		      IEEE80211_STA_DISABLE_VHT |
@@ -347,6 +357,7 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata,
 			       const struct ieee80211_ht_operation *ht_oper,
 			       const struct ieee80211_vht_operation *vht_oper,
 			       const struct ieee80211_he_operation *he_oper,
+			       const struct ieee80211_s1g_oper_ie *s1g_oper,
 			       const u8 *bssid, u32 *changed)
 {
 	struct ieee80211_local *local = sdata->local;
@@ -393,7 +404,7 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata,
 	/* calculate new channel (type) based on HT/VHT/HE operation IEs */
 	flags = ieee80211_determine_chantype(sdata, sband, chan, vht_cap_info,
 					     ht_oper, vht_oper, he_oper,
-					     &chandef, true);
+					     s1g_oper, &chandef, true);
 
 	/*
 	 * Downgrade the new channel if we associated with restricted
@@ -811,6 +822,9 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 	*pos++ = assoc_data->ssid_len;
 	memcpy(pos, assoc_data->ssid, assoc_data->ssid_len);
 
+	if (sband->band == NL80211_BAND_S1GHZ)
+		goto skip_rates;
+
 	/* add all rates which were marked to be used above */
 	supp_rates_len = rates_len;
 	if (supp_rates_len > 8)
@@ -846,6 +860,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 		}
 	}
 
+skip_rates:
 	if (capab & WLAN_CAPABILITY_SPECTRUM_MGMT ||
 	    capab & WLAN_CAPABILITY_RADIO_MEASURE) {
 		pos = skb_put(skb, 4);
@@ -1020,8 +1035,10 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 		pos = ieee80211_add_wmm_info_ie(skb_put(skb, 9), qos_info);
 	}
 
-	if (sband->band == NL80211_BAND_S1GHZ)
+	if (sband->band == NL80211_BAND_S1GHZ) {
+		ieee80211_add_aid_request_ie(sdata, skb);
 		ieee80211_add_s1g_capab_ie(sdata, &sband->s1g_cap, skb);
+	}
 
 	/* add any remaining custom (i.e. vendor specific here) IEs */
 	if (assoc_data->ie_len) {
@@ -3250,14 +3267,26 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
 	const struct cfg80211_bss_ies *bss_ies = NULL;
 	struct ieee80211_mgd_assoc_data *assoc_data = ifmgd->assoc_data;
 	bool is_6ghz = cbss->channel->band == NL80211_BAND_6GHZ;
+	bool is_s1g = cbss->channel->band == NL80211_BAND_S1GHZ;
 	u32 changed = 0;
+	u8 *pos;
 	int err;
 	bool ret;
 
 	/* AssocResp and ReassocResp have identical structure */
 
+	pos = mgmt->u.assoc_resp.variable;
 	aid = le16_to_cpu(mgmt->u.assoc_resp.aid);
+	if (is_s1g) {
+		pos = (u8 *) mgmt->u.s1g_assoc_resp.variable;
+		aid = 0; /* TODO */
+	}
 	capab_info = le16_to_cpu(mgmt->u.assoc_resp.capab_info);
+	ieee802_11_parse_elems(pos, len - (pos - (u8 *)mgmt), false, elems,
+			       mgmt->bssid, assoc_data->bss->bssid);
+
+	if (elems->aid_resp)
+		aid = le16_to_cpu(elems->aid_resp->aid);
 
 	/*
 	 * The 5 MSB of the AID field are reserved
@@ -3274,7 +3303,7 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
 		ifmgd->broken_ap = true;
 	}
 
-	if (!elems->supp_rates) {
+	if (!is_s1g && !elems->supp_rates) {
 		sdata_info(sdata, "no SuppRates element in AssocResp\n");
 		return false;
 	}
@@ -3516,7 +3545,8 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
 		sta->sta.mfp = false;
 	}
 
-	sta->sta.wme = elems->wmm_param && local->hw.queues >= IEEE80211_NUM_ACS;
+	sta->sta.wme = (elems->wmm_param || elems->s1g_capab) &&
+		       local->hw.queues >= IEEE80211_NUM_ACS;
 
 	err = sta_info_move_state(sta, IEEE80211_STA_ASSOC);
 	if (!err && !(ifmgd->flags & IEEE80211_STA_CONTROL_PORT))
@@ -3611,7 +3641,7 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 	int ac, uapsd_queues = -1;
 	u8 *pos;
 	bool reassoc;
-	struct cfg80211_bss *bss;
+	struct cfg80211_bss *cbss;
 	struct ieee80211_event event = {
 		.type = MLME_EVENT,
 		.u.mlme.data = ASSOC_EVENT,
@@ -3621,9 +3651,12 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 
 	if (!assoc_data)
 		return;
+
 	if (!ether_addr_equal(assoc_data->bss->bssid, mgmt->bssid))
 		return;
 
+	cbss = assoc_data->bss;
+
 	/*
 	 * AssocResp and ReassocResp have identical structure, so process both
 	 * of them in this function.
@@ -3635,7 +3668,12 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 	reassoc = ieee80211_is_reassoc_resp(mgmt->frame_control);
 	capab_info = le16_to_cpu(mgmt->u.assoc_resp.capab_info);
 	status_code = le16_to_cpu(mgmt->u.assoc_resp.status_code);
+	pos = mgmt->u.assoc_resp.variable;
 	aid = le16_to_cpu(mgmt->u.assoc_resp.aid);
+	if (cbss->channel->band == NL80211_BAND_S1GHZ) {
+		pos = (u8 *) mgmt->u.s1g_assoc_resp.variable;
+		aid = 0; /* TODO */
+	}
 
 	sdata_info(sdata,
 		   "RX %sssocResp from %pM (capab=0x%x status=%d aid=%d)\n",
@@ -3646,7 +3684,6 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 	    fils_decrypt_assoc_resp(sdata, (u8 *)mgmt, &len, assoc_data) < 0)
 		return;
 
-	pos = mgmt->u.assoc_resp.variable;
 	ieee802_11_parse_elems(pos, len - (pos - (u8 *)mgmt), false, &elems,
 			       mgmt->bssid, assoc_data->bss->bssid);
 
@@ -3666,8 +3703,6 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 		return;
 	}
 
-	bss = assoc_data->bss;
-
 	if (status_code != WLAN_STATUS_SUCCESS) {
 		sdata_info(sdata, "%pM denied association (code=%d)\n",
 			   mgmt->sa, status_code);
@@ -3676,10 +3711,10 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 		event.u.mlme.reason = status_code;
 		drv_event_callback(sdata->local, sdata, &event);
 	} else {
-		if (!ieee80211_assoc_success(sdata, bss, mgmt, len, &elems)) {
+		if (!ieee80211_assoc_success(sdata, cbss, mgmt, len, &elems)) {
 			/* oops -- internal error -- send timeout for now */
 			ieee80211_destroy_assoc_data(sdata, false, false);
-			cfg80211_assoc_timeout(sdata->dev, bss);
+			cfg80211_assoc_timeout(sdata->dev, cbss);
 			return;
 		}
 		event.u.mlme.status = MLME_SUCCESS;
@@ -3700,7 +3735,7 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 				uapsd_queues |= ieee80211_ac_to_qos_mask[ac];
 	}
 
-	cfg80211_rx_assoc_resp(sdata->dev, bss, (u8 *)mgmt, len, uapsd_queues,
+	cfg80211_rx_assoc_resp(sdata->dev, cbss, (u8 *)mgmt, len, uapsd_queues,
 			       ifmgd->assoc_req_ies, ifmgd->assoc_req_ies_len);
 }
 
@@ -4149,7 +4184,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 	if (ieee80211_config_bw(sdata, sta, elems.ht_cap_elem,
 				elems.vht_cap_elem, elems.ht_operation,
 				elems.vht_operation, elems.he_operation,
-				bssid, &changed)) {
+				elems.s1g_oper, bssid, &changed)) {
 		mutex_unlock(&local->sta_mtx);
 		sdata_info(sdata,
 			   "failed to follow AP %pM bandwidth change, disconnect\n",
@@ -4902,6 +4937,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 	const struct ieee80211_ht_operation *ht_oper = NULL;
 	const struct ieee80211_vht_operation *vht_oper = NULL;
 	const struct ieee80211_he_operation *he_oper = NULL;
+	const struct ieee80211_s1g_oper_ie *s1g_oper = NULL;
 	struct ieee80211_supported_band *sband;
 	struct cfg80211_chan_def chandef;
 	bool is_6ghz = cbss->channel->band == NL80211_BAND_6GHZ;
@@ -5005,10 +5041,23 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 	if (!have_80mhz)
 		ifmgd->flags |= IEEE80211_STA_DISABLE_VHT;
 
+	if (sband->band == NL80211_BAND_S1GHZ) {
+		const u8 *s1g_oper_ie;
+
+		s1g_oper_ie = ieee80211_bss_get_ie(cbss,
+						   WLAN_EID_S1G_OPERATION);
+		if (s1g_oper_ie && s1g_oper_ie[1] >= sizeof(*s1g_oper))
+			s1g_oper = (void *)(s1g_oper_ie + 2);
+		else
+			sdata_info(sdata,
+				   "AP missing S1G operation element?\n");
+	}
+
 	ifmgd->flags |= ieee80211_determine_chantype(sdata, sband,
 						     cbss->channel,
 						     bss->vht_cap_info,
 						     ht_oper, vht_oper, he_oper,
+						     s1g_oper,
 						     &chandef, false);
 
 	sdata->needed_rx_chains = min(ieee80211_ht_vht_rx_chains(sdata, cbss),
@@ -5135,6 +5184,10 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata,
 		const struct cfg80211_bss_ies *ies;
 		int shift = ieee80211_vif_get_shift(&sdata->vif);
 
+		/* TODO: S1G Basic Rate Set is expressed elsewhere */
+		if (cbss->channel->band == NL80211_BAND_S1GHZ)
+			goto skip_rates;
+
 		ieee80211_get_rates(sband, bss->supp_rates,
 				    bss->supp_rates_len,
 				    &rates, &basic_rates,
@@ -5179,6 +5232,7 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata,
 		else
 			sdata->flags &= ~IEEE80211_SDATA_OPERATING_GMODE;
 
+skip_rates:
 		memcpy(ifmgd->bssid, cbss->bssid, ETH_ALEN);
 
 		/* set timing information */
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 70865f316d89..99d584fe49e8 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1058,6 +1058,7 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action,
 		case WLAN_EID_S1G_BCN_COMPAT:
 		case WLAN_EID_S1G_CAPABILITIES:
 		case WLAN_EID_S1G_OPERATION:
+		case WLAN_EID_AID_RESPONSE:
 		case WLAN_EID_S1G_SHORT_BCN_INTERVAL:
 		/*
 		 * not listing WLAN_EID_CHANNEL_SWITCH_WRAPPER -- it seems possible
@@ -1362,6 +1363,12 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action,
 			else
 				elem_parse_failed = true;
 			break;
+		case WLAN_EID_AID_RESPONSE:
+			if (elen == sizeof(struct ieee80211_aid_response_ie))
+				elems->aid_resp = (void *)pos;
+			else
+				elem_parse_failed = true;
+			break;
 		default:
 			break;
 		}
@@ -3445,6 +3452,42 @@ bool ieee80211_chandef_he_6ghz_oper(struct ieee80211_sub_if_data *sdata,
 
 	*chandef = he_chandef;
 
+	return false;
+}
+
+bool ieee80211_chandef_s1g_oper(const struct ieee80211_s1g_oper_ie *oper,
+				struct cfg80211_chan_def *chandef)
+{
+	u32 oper_freq;
+
+	if (!oper)
+		return false;
+
+	switch (FIELD_GET(S1G_OPER_CH_WIDTH_OPER, oper->ch_width)) {
+	case IEEE80211_S1G_CHANWIDTH_1MHZ:
+		chandef->width = NL80211_CHAN_WIDTH_1;
+		break;
+	case IEEE80211_S1G_CHANWIDTH_2MHZ:
+		chandef->width = NL80211_CHAN_WIDTH_2;
+		break;
+	case IEEE80211_S1G_CHANWIDTH_4MHZ:
+		chandef->width = NL80211_CHAN_WIDTH_4;
+		break;
+	case IEEE80211_S1G_CHANWIDTH_8MHZ:
+		chandef->width = NL80211_CHAN_WIDTH_8;
+		break;
+	case IEEE80211_S1G_CHANWIDTH_16MHZ:
+		chandef->width = NL80211_CHAN_WIDTH_16;
+		break;
+	default:
+		return false;
+	}
+
+	oper_freq = ieee80211_channel_to_freq_khz(oper->oper_ch,
+						  NL80211_BAND_S1GHZ);
+	chandef->center_freq1 = KHZ_TO_MHZ(oper_freq);
+	chandef->freq1_offset = oper_freq % 1000;
+
 	return true;
 }
 
@@ -4393,6 +4436,16 @@ void ieee80211_add_s1g_capab_ie(struct ieee80211_sub_if_data *sdata,
 	memcpy(pos, &s1g_capab, sizeof(s1g_capab));
 }
 
+void ieee80211_add_aid_request_ie(struct ieee80211_sub_if_data *sdata,
+				  struct sk_buff *skb)
+{
+	u8 *pos = skb_put(skb, 3);
+
+	*pos++ = WLAN_EID_AID_REQUEST;
+	*pos++ = 1;
+	*pos++ = 0;
+}
+
 u8 *ieee80211_add_wmm_info_ie(u8 *buf, u8 qosinfo)
 {
 	*buf++ = WLAN_EID_VENDOR_SPECIFIC;
-- 
cgit v1.2.3


From f5bec330e3010450daeb5cb6a94a4a7c54afa306 Mon Sep 17 00:00:00 2001
From: Rajkumar Manoharan <rmanohar@codeaurora.org>
Date: Mon, 28 Sep 2020 00:28:11 -0700
Subject: nl80211: extend support to config spatial reuse parameter set

Allow the user to configure below Spatial Reuse Parameter Set element.
  * Non-SRG OBSS PD Max Offset
  * SRG BSS Color Bitmap
  * SRG Partial BSSID Bitmap

Signed-off-by: Rajkumar Manoharan <rmanohar@codeaurora.org>
Link: https://lore.kernel.org/r/1601278091-20313-2-git-send-email-rmanohar@codeaurora.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h    |  7 +++++--
 include/net/cfg80211.h       | 10 ++++++++++
 include/uapi/linux/nl80211.h | 11 +++++++++++
 net/wireless/nl80211.c       | 25 +++++++++++++++++++++++++
 4 files changed, 51 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index f2f56b287aed..770408b2fdaf 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -2350,8 +2350,11 @@ ieee80211_he_6ghz_oper(const struct ieee80211_he_operation *he_oper)
 }
 
 /* HE Spatial Reuse defines */
-#define IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT			0x4
-#define IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT		0x8
+#define IEEE80211_HE_SPR_PSR_DISALLOWED				BIT(0)
+#define IEEE80211_HE_SPR_NON_SRG_OBSS_PD_SR_DISALLOWED		BIT(1)
+#define IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT			BIT(2)
+#define IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT		BIT(3)
+#define IEEE80211_HE_SPR_HESIGA_SR_VAL15_ALLOWED		BIT(4)
 
 /*
  * ieee80211_he_spr_size - calculate 802.11ax HE Spatial Reuse IE size
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index bead4b9afeca..aee47f2b5709 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -269,13 +269,23 @@ struct ieee80211_rate {
  * struct ieee80211_he_obss_pd - AP settings for spatial reuse
  *
  * @enable: is the feature enabled.
+ * @sr_ctrl: The SR Control field of SRP element.
+ * @non_srg_max_offset: non-SRG maximum tx power offset
  * @min_offset: minimal tx power offset an associated station shall use
  * @max_offset: maximum tx power offset an associated station shall use
+ * @bss_color_bitmap: bitmap that indicates the BSS color values used by
+ *	members of the SRG
+ * @partial_bssid_bitmap: bitmap that indicates the partial BSSID values
+ *	used by members of the SRG
  */
 struct ieee80211_he_obss_pd {
 	bool enable;
+	u8 sr_ctrl;
+	u8 non_srg_max_offset;
 	u8 min_offset;
 	u8 max_offset;
+	u8 bss_color_bitmap[8];
+	u8 partial_bssid_bitmap[8];
 };
 
 /**
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 1e51445f81cd..47700a2b9af9 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -6991,6 +6991,13 @@ enum nl80211_peer_measurement_ftm_resp {
  *
  * @NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET: the OBSS PD minimum tx power offset.
  * @NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET: the OBSS PD maximum tx power offset.
+ * @NL80211_HE_OBSS_PD_ATTR_NON_SRG_MAX_OFFSET: the non-SRG OBSS PD maximum
+ *	tx power offset.
+ * @NL80211_HE_OBSS_PD_ATTR_BSS_COLOR_BITMAP: bitmap that indicates the BSS color
+ *	values used by members of the SRG.
+ * @NL80211_HE_OBSS_PD_ATTR_PARTIAL_BSSID_BITMAP: bitmap that indicates the partial
+ *	BSSID values used by members of the SRG.
+ * @NL80211_HE_OBSS_PD_ATTR_SR_CTRL: The SR Control field of SRP element.
  *
  * @__NL80211_HE_OBSS_PD_ATTR_LAST: Internal
  * @NL80211_HE_OBSS_PD_ATTR_MAX: highest OBSS PD attribute.
@@ -7000,6 +7007,10 @@ enum nl80211_obss_pd_attributes {
 
 	NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET,
 	NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET,
+	NL80211_HE_OBSS_PD_ATTR_NON_SRG_MAX_OFFSET,
+	NL80211_HE_OBSS_PD_ATTR_BSS_COLOR_BITMAP,
+	NL80211_HE_OBSS_PD_ATTR_PARTIAL_BSSID_BITMAP,
+	NL80211_HE_OBSS_PD_ATTR_SR_CTRL,
 
 	/* keep last */
 	__NL80211_HE_OBSS_PD_ATTR_LAST,
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index e501bce86436..d76b8bd0e1d1 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -329,6 +329,13 @@ he_obss_pd_policy[NL80211_HE_OBSS_PD_ATTR_MAX + 1] = {
 		NLA_POLICY_RANGE(NLA_U8, 1, 20),
 	[NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET] =
 		NLA_POLICY_RANGE(NLA_U8, 1, 20),
+	[NL80211_HE_OBSS_PD_ATTR_NON_SRG_MAX_OFFSET] =
+		NLA_POLICY_RANGE(NLA_U8, 1, 20),
+	[NL80211_HE_OBSS_PD_ATTR_BSS_COLOR_BITMAP] =
+		NLA_POLICY_EXACT_LEN(8),
+	[NL80211_HE_OBSS_PD_ATTR_PARTIAL_BSSID_BITMAP] =
+		NLA_POLICY_EXACT_LEN(8),
+	[NL80211_HE_OBSS_PD_ATTR_SR_CTRL] = { .type = NLA_U8 },
 };
 
 static const struct nla_policy
@@ -4857,16 +4864,34 @@ static int nl80211_parse_he_obss_pd(struct nlattr *attrs,
 	if (err)
 		return err;
 
+	if (!tb[NL80211_HE_OBSS_PD_ATTR_SR_CTRL])
+		return -EINVAL;
+
+	he_obss_pd->sr_ctrl = nla_get_u8(tb[NL80211_HE_OBSS_PD_ATTR_SR_CTRL]);
+
 	if (tb[NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET])
 		he_obss_pd->min_offset =
 			nla_get_u8(tb[NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET]);
 	if (tb[NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET])
 		he_obss_pd->max_offset =
 			nla_get_u8(tb[NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET]);
+	if (tb[NL80211_HE_OBSS_PD_ATTR_NON_SRG_MAX_OFFSET])
+		he_obss_pd->non_srg_max_offset =
+			nla_get_u8(tb[NL80211_HE_OBSS_PD_ATTR_NON_SRG_MAX_OFFSET]);
 
 	if (he_obss_pd->min_offset > he_obss_pd->max_offset)
 		return -EINVAL;
 
+	if (tb[NL80211_HE_OBSS_PD_ATTR_BSS_COLOR_BITMAP])
+		memcpy(he_obss_pd->bss_color_bitmap,
+		       nla_data(tb[NL80211_HE_OBSS_PD_ATTR_BSS_COLOR_BITMAP]),
+		       sizeof(he_obss_pd->bss_color_bitmap));
+
+	if (tb[NL80211_HE_OBSS_PD_ATTR_PARTIAL_BSSID_BITMAP])
+		memcpy(he_obss_pd->partial_bssid_bitmap,
+		       nla_data(tb[NL80211_HE_OBSS_PD_ATTR_PARTIAL_BSSID_BITMAP]),
+		       sizeof(he_obss_pd->partial_bssid_bitmap));
+
 	he_obss_pd->enable = true;
 
 	return 0;
-- 
cgit v1.2.3


From f5be3a61fdb5dd11ef60173e2783ccf62685f892 Mon Sep 17 00:00:00 2001
From: Shaokun Zhang <zhangshaokun@hisilicon.com>
Date: Tue, 22 Sep 2020 13:53:45 +0800
Subject: arm64: perf: Add support caps under sysfs

ARMv8.4-PMU introduces the PMMIR_EL1 registers and some new PMU events,
like STALL_SLOT etc, are related to it. Let's add a caps directory to
/sys/bus/event_source/devices/armv8_pmuv3_0/ and support slots from
PMMIR_EL1 registers in this entry. The user programs can get the slots
from sysfs directly.

/sys/bus/event_source/devices/armv8_pmuv3_0/caps/slots is exposed
under sysfs. Both ARMv8.4-PMU and STALL_SLOT event are implemented,
it returns the slots from PMMIR_EL1, otherwise it will return 0.

Signed-off-by: Shaokun Zhang <zhangshaokun@hisilicon.com>
Cc: Will Deacon <will@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Link: https://lore.kernel.org/r/1600754025-53535-1-git-send-email-zhangshaokun@hisilicon.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/perf_event.h |   3 ++
 arch/arm64/include/asm/sysreg.h     |   2 +
 arch/arm64/kernel/perf_event.c      | 103 ++++++++++++++++++++++++------------
 include/linux/perf/arm_pmu.h        |   3 ++
 4 files changed, 78 insertions(+), 33 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
index 2c2d7dbe8a02..60731f602d3e 100644
--- a/arch/arm64/include/asm/perf_event.h
+++ b/arch/arm64/include/asm/perf_event.h
@@ -236,6 +236,9 @@
 #define ARMV8_PMU_USERENR_CR	(1 << 2) /* Cycle counter can be read at EL0 */
 #define ARMV8_PMU_USERENR_ER	(1 << 3) /* Event counter can be read at EL0 */
 
+/* PMMIR_EL1.SLOTS mask */
+#define ARMV8_PMU_SLOTS_MASK	0xff
+
 #ifdef CONFIG_PERF_EVENTS
 struct pt_regs;
 extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 554a7e8ecb07..921773adff5e 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -321,6 +321,8 @@
 #define SYS_PMINTENSET_EL1		sys_reg(3, 0, 9, 14, 1)
 #define SYS_PMINTENCLR_EL1		sys_reg(3, 0, 9, 14, 2)
 
+#define SYS_PMMIR_EL1			sys_reg(3, 0, 9, 14, 6)
+
 #define SYS_MAIR_EL1			sys_reg(3, 0, 10, 2, 0)
 #define SYS_AMAIR_EL1			sys_reg(3, 0, 10, 3, 0)
 
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 04d0ceb72a67..34a7cd3af699 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -305,6 +305,28 @@ static struct attribute_group armv8_pmuv3_format_attr_group = {
 	.attrs = armv8_pmuv3_format_attrs,
 };
 
+static ssize_t slots_show(struct device *dev, struct device_attribute *attr,
+			  char *page)
+{
+	struct pmu *pmu = dev_get_drvdata(dev);
+	struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu);
+	u32 slots = cpu_pmu->reg_pmmir & ARMV8_PMU_SLOTS_MASK;
+
+	return snprintf(page, PAGE_SIZE, "0x%08x\n", slots);
+}
+
+static DEVICE_ATTR_RO(slots);
+
+static struct attribute *armv8_pmuv3_caps_attrs[] = {
+	&dev_attr_slots.attr,
+	NULL,
+};
+
+static struct attribute_group armv8_pmuv3_caps_attr_group = {
+	.name = "caps",
+	.attrs = armv8_pmuv3_caps_attrs,
+};
+
 /*
  * Perf Events' indices
  */
@@ -984,6 +1006,12 @@ static void __armv8pmu_probe_pmu(void *info)
 
 	bitmap_from_arr32(cpu_pmu->pmceid_ext_bitmap,
 			     pmceid, ARMV8_PMUV3_MAX_COMMON_EVENTS);
+
+	/* store PMMIR_EL1 register for sysfs */
+	if (pmuver >= ID_AA64DFR0_PMUVER_8_4 && (pmceid_raw[1] & BIT(31)))
+		cpu_pmu->reg_pmmir = read_cpuid(PMMIR_EL1);
+	else
+		cpu_pmu->reg_pmmir = 0;
 }
 
 static int armv8pmu_probe_pmu(struct arm_pmu *cpu_pmu)
@@ -1006,7 +1034,8 @@ static int armv8pmu_probe_pmu(struct arm_pmu *cpu_pmu)
 static int armv8_pmu_init(struct arm_pmu *cpu_pmu, char *name,
 			  int (*map_event)(struct perf_event *event),
 			  const struct attribute_group *events,
-			  const struct attribute_group *format)
+			  const struct attribute_group *format,
+			  const struct attribute_group *caps)
 {
 	int ret = armv8pmu_probe_pmu(cpu_pmu);
 	if (ret)
@@ -1031,104 +1060,112 @@ static int armv8_pmu_init(struct arm_pmu *cpu_pmu, char *name,
 			events : &armv8_pmuv3_events_attr_group;
 	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = format ?
 			format : &armv8_pmuv3_format_attr_group;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_CAPS] = caps ?
+			caps : &armv8_pmuv3_caps_attr_group;
 
 	return 0;
 }
 
+static int armv8_pmu_init_nogroups(struct arm_pmu *cpu_pmu, char *name,
+				   int (*map_event)(struct perf_event *event))
+{
+	return armv8_pmu_init(cpu_pmu, name, map_event, NULL, NULL, NULL);
+}
+
 static int armv8_pmuv3_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_pmuv3",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_pmuv3",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_a34_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a34",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a34",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_a35_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a35",
-			      armv8_a53_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a35",
+				       armv8_a53_map_event);
 }
 
 static int armv8_a53_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a53",
-			      armv8_a53_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a53",
+				       armv8_a53_map_event);
 }
 
 static int armv8_a55_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a55",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a55",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_a57_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a57",
-			      armv8_a57_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a57",
+				       armv8_a57_map_event);
 }
 
 static int armv8_a65_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a65",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a65",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_a72_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a72",
-			      armv8_a57_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a72",
+				       armv8_a57_map_event);
 }
 
 static int armv8_a73_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a73",
-			      armv8_a73_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a73",
+				       armv8_a73_map_event);
 }
 
 static int armv8_a75_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a75",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a75",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_a76_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a76",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a76",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_a77_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a77",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a77",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_e1_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_neoverse_e1",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_neoverse_e1",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_n1_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_neoverse_n1",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_neoverse_n1",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_thunder_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cavium_thunder",
-			      armv8_thunder_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cavium_thunder",
+				       armv8_thunder_map_event);
 }
 
 static int armv8_vulcan_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_brcm_vulcan",
-			      armv8_vulcan_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_brcm_vulcan",
+				       armv8_vulcan_map_event);
 }
 
 static const struct of_device_id armv8_pmu_of_device_ids[] = {
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index 5b616dde9a4c..505480217cf1 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -73,6 +73,7 @@ enum armpmu_attr_groups {
 	ARMPMU_ATTR_GROUP_COMMON,
 	ARMPMU_ATTR_GROUP_EVENTS,
 	ARMPMU_ATTR_GROUP_FORMATS,
+	ARMPMU_ATTR_GROUP_CAPS,
 	ARMPMU_NR_ATTR_GROUPS
 };
 
@@ -109,6 +110,8 @@ struct arm_pmu {
 	struct notifier_block	cpu_pm_nb;
 	/* the attr_groups array must be NULL-terminated */
 	const struct attribute_group *attr_groups[ARMPMU_NR_ATTR_GROUPS + 1];
+	/* store the PMMIR_EL1 to expose slots */
+	u64		reg_pmmir;
 
 	/* Only to be used by ACPI probing code */
 	unsigned long acpi_cpuid;
-- 
cgit v1.2.3


From ef24f97daac4d9450c956ab165d8337c2feca0e9 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Thu, 27 Aug 2020 10:51:57 +0200
Subject: mtd: rawnand: Separate the ECC engine type and the ECC byte placement

The use of "syndrome" placement should not be encoded in the ECC
engine mode/type.

Create a "placement" field in NAND chip and change all occurrences of
the NAND_ECC_HW_SYNDROME enumeration to be just NAND_ECC_HW and
possibly a placement entry like NAND_ECC_PLACEMENT_INTERLEAVED.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-10-miquel.raynal@bootlin.com
---
 arch/arm/mach-davinci/board-dm355-leopard.c |  3 +-
 drivers/mtd/nand/raw/cafe_nand.c            |  3 +-
 drivers/mtd/nand/raw/davinci_nand.c         |  5 +-
 drivers/mtd/nand/raw/denali.c               |  3 +-
 drivers/mtd/nand/raw/diskonchip.c           |  3 +-
 drivers/mtd/nand/raw/lpc32xx_slc.c          |  3 +-
 drivers/mtd/nand/raw/nand_base.c            | 89 +++++++++++++++++------------
 drivers/mtd/nand/raw/r852.c                 |  3 +-
 include/linux/mtd/rawnand.h                 |  6 +-
 include/linux/platform_data/mtd-davinci.h   |  1 +
 10 files changed, 71 insertions(+), 48 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/mach-davinci/board-dm355-leopard.c b/arch/arm/mach-davinci/board-dm355-leopard.c
index b9e9950dd300..4c8a592754ac 100644
--- a/arch/arm/mach-davinci/board-dm355-leopard.c
+++ b/arch/arm/mach-davinci/board-dm355-leopard.c
@@ -76,7 +76,8 @@ static struct davinci_nand_pdata davinci_nand_data = {
 	.mask_chipsel		= BIT(14),
 	.parts			= davinci_nand_partitions,
 	.nr_parts		= ARRAY_SIZE(davinci_nand_partitions),
-	.ecc_mode		= NAND_ECC_HW_SYNDROME,
+	.ecc_mode		= NAND_HW_ECC_ENGINE,
+	.ecc_placement		= NAND_ECC_PLACEMENT_INTERLEAVED,
 	.ecc_bits		= 4,
 	.bbt_options		= NAND_BBT_USE_FLASH,
 };
diff --git a/drivers/mtd/nand/raw/cafe_nand.c b/drivers/mtd/nand/raw/cafe_nand.c
index 92173790f20b..2bf8ab542e38 100644
--- a/drivers/mtd/nand/raw/cafe_nand.c
+++ b/drivers/mtd/nand/raw/cafe_nand.c
@@ -629,7 +629,8 @@ static int cafe_nand_attach_chip(struct nand_chip *chip)
 		goto out_free_dma;
 	}
 
-	cafe->nand.ecc.mode = NAND_ECC_HW_SYNDROME;
+	cafe->nand.ecc.mode = NAND_ECC_HW;
+	cafe->nand.ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED;
 	cafe->nand.ecc.size = mtd->writesize;
 	cafe->nand.ecc.bytes = 14;
 	cafe->nand.ecc.strength = 4;
diff --git a/drivers/mtd/nand/raw/davinci_nand.c b/drivers/mtd/nand/raw/davinci_nand.c
index 551515c223bb..3640c7e45e15 100644
--- a/drivers/mtd/nand/raw/davinci_nand.c
+++ b/drivers/mtd/nand/raw/davinci_nand.c
@@ -168,7 +168,7 @@ static int nand_davinci_correct_1bit(struct nand_chip *chip, u_char *dat,
 /*
  * 4-bit hardware ECC ... context maintained over entire AEMIF
  *
- * This is a syndrome engine, but we avoid NAND_ECC_HW_SYNDROME
+ * This is a syndrome engine, but we avoid NAND_ECC_PLACEMENT_INTERLEAVED
  * since that forces use of a problematic "infix OOB" layout.
  * Among other things, it trashes manufacturer bad block markers.
  * Also, and specific to this hardware, it ECC-protects the "prepad"
@@ -851,6 +851,7 @@ static int nand_davinci_probe(struct platform_device *pdev)
 
 	/* Use board-specific ECC config */
 	info->chip.ecc.mode	= pdata->ecc_mode;
+	info->chip.ecc.placement = pdata->ecc_placement;
 
 	spin_lock_irq(&davinci_nand_lock);
 
@@ -897,7 +898,7 @@ static int nand_davinci_remove(struct platform_device *pdev)
 	int ret;
 
 	spin_lock_irq(&davinci_nand_lock);
-	if (info->chip.ecc.mode == NAND_ECC_HW_SYNDROME)
+	if (info->chip.ecc.placement == NAND_ECC_PLACEMENT_INTERLEAVED)
 		ecc4_busy = false;
 	spin_unlock_irq(&davinci_nand_lock);
 
diff --git a/drivers/mtd/nand/raw/denali.c b/drivers/mtd/nand/raw/denali.c
index 9d99dade95ce..0e54b8a61cf0 100644
--- a/drivers/mtd/nand/raw/denali.c
+++ b/drivers/mtd/nand/raw/denali.c
@@ -1237,7 +1237,8 @@ int denali_chip_init(struct denali_controller *denali,
 	chip->bbt_options |= NAND_BBT_USE_FLASH;
 	chip->bbt_options |= NAND_BBT_NO_OOB;
 	chip->options |= NAND_NO_SUBPAGE_WRITE;
-	chip->ecc.mode = NAND_ECC_HW_SYNDROME;
+	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED;
 	chip->ecc.read_page = denali_read_page;
 	chip->ecc.write_page = denali_write_page;
 	chip->ecc.read_page_raw = denali_read_page_raw;
diff --git a/drivers/mtd/nand/raw/diskonchip.c b/drivers/mtd/nand/raw/diskonchip.c
index 43721863a0d8..40360352136b 100644
--- a/drivers/mtd/nand/raw/diskonchip.c
+++ b/drivers/mtd/nand/raw/diskonchip.c
@@ -1456,7 +1456,8 @@ static int __init doc_probe(unsigned long physadr)
 	nand->ecc.calculate	= doc200x_calculate_ecc;
 	nand->ecc.correct	= doc200x_correct_data;
 
-	nand->ecc.mode		= NAND_ECC_HW_SYNDROME;
+	nand->ecc.mode		= NAND_ECC_HW;
+	nand->ecc.placement	= NAND_ECC_PLACEMENT_INTERLEAVED;
 	nand->ecc.size		= 512;
 	nand->ecc.bytes		= 6;
 	nand->ecc.strength	= 2;
diff --git a/drivers/mtd/nand/raw/lpc32xx_slc.c b/drivers/mtd/nand/raw/lpc32xx_slc.c
index b151fd000815..ccb189c8e343 100644
--- a/drivers/mtd/nand/raw/lpc32xx_slc.c
+++ b/drivers/mtd/nand/raw/lpc32xx_slc.c
@@ -881,7 +881,8 @@ static int lpc32xx_nand_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, host);
 
 	/* NAND callbacks for LPC32xx SLC hardware */
-	chip->ecc.mode = NAND_ECC_HW_SYNDROME;
+	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED;
 	chip->legacy.read_byte = lpc32xx_nand_read_byte;
 	chip->legacy.read_buf = lpc32xx_nand_read_buf;
 	chip->legacy.write_buf = lpc32xx_nand_write_buf;
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index e22a7f9986b1..172852a29a50 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -5790,47 +5790,59 @@ static int nand_scan_tail(struct nand_chip *chip)
 
 	switch (ecc->mode) {
 	case NAND_ECC_HW:
-		/* Use standard hwecc read page function? */
-		if (!ecc->read_page)
-			ecc->read_page = nand_read_page_hwecc;
-		if (!ecc->write_page)
-			ecc->write_page = nand_write_page_hwecc;
-		if (!ecc->read_page_raw)
-			ecc->read_page_raw = nand_read_page_raw;
-		if (!ecc->write_page_raw)
-			ecc->write_page_raw = nand_write_page_raw;
-		if (!ecc->read_oob)
-			ecc->read_oob = nand_read_oob_std;
-		if (!ecc->write_oob)
-			ecc->write_oob = nand_write_oob_std;
-		if (!ecc->read_subpage)
-			ecc->read_subpage = nand_read_subpage;
-		if (!ecc->write_subpage && ecc->hwctl && ecc->calculate)
-			ecc->write_subpage = nand_write_subpage_hwecc;
-		fallthrough;
-	case NAND_ECC_HW_SYNDROME:
-		if ((!ecc->calculate || !ecc->correct || !ecc->hwctl) &&
-		    (!ecc->read_page ||
-		     ecc->read_page == nand_read_page_hwecc ||
-		     !ecc->write_page ||
-		     ecc->write_page == nand_write_page_hwecc)) {
-			WARN(1, "No ECC functions supplied; hardware ECC not possible\n");
+		switch (ecc->placement) {
+		case NAND_ECC_PLACEMENT_UNKNOWN:
+		case NAND_ECC_PLACEMENT_OOB:
+			/* Use standard hwecc read page function? */
+			if (!ecc->read_page)
+				ecc->read_page = nand_read_page_hwecc;
+			if (!ecc->write_page)
+				ecc->write_page = nand_write_page_hwecc;
+			if (!ecc->read_page_raw)
+				ecc->read_page_raw = nand_read_page_raw;
+			if (!ecc->write_page_raw)
+				ecc->write_page_raw = nand_write_page_raw;
+			if (!ecc->read_oob)
+				ecc->read_oob = nand_read_oob_std;
+			if (!ecc->write_oob)
+				ecc->write_oob = nand_write_oob_std;
+			if (!ecc->read_subpage)
+				ecc->read_subpage = nand_read_subpage;
+			if (!ecc->write_subpage && ecc->hwctl && ecc->calculate)
+				ecc->write_subpage = nand_write_subpage_hwecc;
+			fallthrough;
+
+		case NAND_ECC_PLACEMENT_INTERLEAVED:
+			if ((!ecc->calculate || !ecc->correct || !ecc->hwctl) &&
+			    (!ecc->read_page ||
+			     ecc->read_page == nand_read_page_hwecc ||
+			     !ecc->write_page ||
+			     ecc->write_page == nand_write_page_hwecc)) {
+				WARN(1, "No ECC functions supplied; hardware ECC not possible\n");
+				ret = -EINVAL;
+				goto err_nand_manuf_cleanup;
+			}
+			/* Use standard syndrome read/write page function? */
+			if (!ecc->read_page)
+				ecc->read_page = nand_read_page_syndrome;
+			if (!ecc->write_page)
+				ecc->write_page = nand_write_page_syndrome;
+			if (!ecc->read_page_raw)
+				ecc->read_page_raw = nand_read_page_raw_syndrome;
+			if (!ecc->write_page_raw)
+				ecc->write_page_raw = nand_write_page_raw_syndrome;
+			if (!ecc->read_oob)
+				ecc->read_oob = nand_read_oob_syndrome;
+			if (!ecc->write_oob)
+				ecc->write_oob = nand_write_oob_syndrome;
+			break;
+
+		default:
+			pr_warn("Invalid NAND_ECC_PLACEMENT %d\n",
+				ecc->placement);
 			ret = -EINVAL;
 			goto err_nand_manuf_cleanup;
 		}
-		/* Use standard syndrome read/write page function? */
-		if (!ecc->read_page)
-			ecc->read_page = nand_read_page_syndrome;
-		if (!ecc->write_page)
-			ecc->write_page = nand_write_page_syndrome;
-		if (!ecc->read_page_raw)
-			ecc->read_page_raw = nand_read_page_raw_syndrome;
-		if (!ecc->write_page_raw)
-			ecc->write_page_raw = nand_write_page_raw_syndrome;
-		if (!ecc->read_oob)
-			ecc->read_oob = nand_read_oob_syndrome;
-		if (!ecc->write_oob)
-			ecc->write_oob = nand_write_oob_syndrome;
 
 		if (mtd->writesize >= ecc->size) {
 			if (!ecc->strength) {
@@ -5845,6 +5857,7 @@ static int nand_scan_tail(struct nand_chip *chip)
 		ecc->mode = NAND_ECC_SOFT;
 		ecc->algo = NAND_ECC_ALGO_HAMMING;
 		fallthrough;
+
 	case NAND_ECC_SOFT:
 		ret = nand_set_ecc_soft_ops(chip);
 		if (ret) {
diff --git a/drivers/mtd/nand/raw/r852.c b/drivers/mtd/nand/raw/r852.c
index f865e3a47b01..f0988cda4479 100644
--- a/drivers/mtd/nand/raw/r852.c
+++ b/drivers/mtd/nand/raw/r852.c
@@ -859,7 +859,8 @@ static int  r852_probe(struct pci_dev *pci_dev, const struct pci_device_id *id)
 	chip->legacy.write_buf = r852_write_buf;
 
 	/* ecc */
-	chip->ecc.mode = NAND_ECC_HW_SYNDROME;
+	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED;
 	chip->ecc.size = R852_DMA_LEN;
 	chip->ecc.bytes = SM_OOB_SIZE;
 	chip->ecc.strength = 2;
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 10bbfbf4ad7f..cfd75a12f802 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -304,6 +304,7 @@ static const struct nand_ecc_caps __name = {			\
 /**
  * struct nand_ecc_ctrl - Control structure for ECC
  * @mode:	ECC mode
+ * @placement:	OOB bytes placement
  * @algo:	ECC algorithm
  * @steps:	number of ECC steps per page
  * @size:	data bytes per ECC step
@@ -331,7 +332,7 @@ static const struct nand_ecc_caps __name = {			\
  *			controller and always return contiguous in-band and
  *			out-of-band data even if they're not stored
  *			contiguously on the NAND chip (e.g.
- *			NAND_ECC_HW_SYNDROME interleaves in-band and
+ *			NAND_ECC_PLACEMENT_INTERLEAVED interleaves in-band and
  *			out-of-band data).
  * @write_page_raw:	function to write a raw page without ECC. This function
  *			should hide the specific layout used by the ECC
@@ -339,7 +340,7 @@ static const struct nand_ecc_caps __name = {			\
  *			in-band and out-of-band data. ECC controller is
  *			responsible for doing the appropriate transformations
  *			to adapt to its specific layout (e.g.
- *			NAND_ECC_HW_SYNDROME interleaves in-band and
+ *			NAND_ECC_PLACEMENT_INTERLEAVED interleaves in-band and
  *			out-of-band data).
  * @read_page:	function to read a page according to the ECC generator
  *		requirements; returns maximum number of bitflips corrected in
@@ -356,6 +357,7 @@ static const struct nand_ecc_caps __name = {			\
  */
 struct nand_ecc_ctrl {
 	enum nand_ecc_mode mode;
+	enum nand_ecc_placement placement;
 	enum nand_ecc_algo algo;
 	int steps;
 	int size;
diff --git a/include/linux/platform_data/mtd-davinci.h b/include/linux/platform_data/mtd-davinci.h
index 03e92c71b3fa..6e2b252a4ce6 100644
--- a/include/linux/platform_data/mtd-davinci.h
+++ b/include/linux/platform_data/mtd-davinci.h
@@ -69,6 +69,7 @@ struct davinci_nand_pdata {		/* platform_data */
 	 * using it with large page chips.
 	 */
 	enum nand_ecc_mode	ecc_mode;
+	enum nand_ecc_placement ecc_placement;
 	u8			ecc_bits;
 
 	/* e.g. NAND_BUSWIDTH_16 */
-- 
cgit v1.2.3


From bace41f80f65dc4ba13c892bac783e7e81847379 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Thu, 27 Aug 2020 10:51:58 +0200
Subject: mtd: rawnand: Use the new ECC engine type enumeration

Mechanical switch from the legacy "mode" enumeration to the new
"engine type" enumeration in drivers and board files.

The device tree parsing is also updated to return the new enumeration
from the old strings.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-11-miquel.raynal@bootlin.com
---
 arch/arm/mach-davinci/board-da830-evm.c          |  2 +-
 arch/arm/mach-davinci/board-da850-evm.c          |  2 +-
 arch/arm/mach-davinci/board-dm355-evm.c          |  2 +-
 arch/arm/mach-davinci/board-dm355-leopard.c      |  2 +-
 arch/arm/mach-davinci/board-dm365-evm.c          |  2 +-
 arch/arm/mach-davinci/board-dm644x-evm.c         |  2 +-
 arch/arm/mach-davinci/board-dm646x-evm.c         |  2 +-
 arch/arm/mach-davinci/board-mityomapl138.c       |  2 +-
 arch/arm/mach-davinci/board-neuros-osd2.c        |  2 +-
 arch/arm/mach-davinci/board-omapl138-hawk.c      |  2 +-
 arch/arm/mach-s3c24xx/common-smdk.c              |  2 +-
 arch/arm/mach-s3c24xx/mach-anubis.c              |  2 +-
 arch/arm/mach-s3c24xx/mach-at2440evb.c           |  2 +-
 arch/arm/mach-s3c24xx/mach-bast.c                |  2 +-
 arch/arm/mach-s3c24xx/mach-gta02.c               |  2 +-
 arch/arm/mach-s3c24xx/mach-jive.c                |  2 +-
 arch/arm/mach-s3c24xx/mach-mini2440.c            |  2 +-
 arch/arm/mach-s3c24xx/mach-osiris.c              |  2 +-
 arch/arm/mach-s3c24xx/mach-qt2410.c              |  2 +-
 arch/arm/mach-s3c24xx/mach-rx1950.c              |  2 +-
 arch/arm/mach-s3c24xx/mach-rx3715.c              |  2 +-
 arch/arm/mach-s3c24xx/mach-vstms.c               |  2 +-
 arch/arm/mach-s3c64xx/mach-hmt.c                 |  2 +-
 arch/arm/mach-s3c64xx/mach-mini6410.c            |  2 +-
 arch/arm/mach-s3c64xx/mach-real6410.c            |  2 +-
 drivers/mtd/nand/raw/ams-delta.c                 |  2 +-
 drivers/mtd/nand/raw/arasan-nand-controller.c    | 12 ++--
 drivers/mtd/nand/raw/atmel/nand-controller.c     | 14 ++---
 drivers/mtd/nand/raw/au1550nd.c                  |  2 +-
 drivers/mtd/nand/raw/bcm47xxnflash/ops_bcm4706.c |  3 +-
 drivers/mtd/nand/raw/brcmnand/brcmnand.c         |  8 +--
 drivers/mtd/nand/raw/cadence-nand-controller.c   |  4 +-
 drivers/mtd/nand/raw/cafe_nand.c                 |  2 +-
 drivers/mtd/nand/raw/cs553x_nand.c               |  2 +-
 drivers/mtd/nand/raw/davinci_nand.c              | 24 +++----
 drivers/mtd/nand/raw/denali.c                    |  2 +-
 drivers/mtd/nand/raw/diskonchip.c                |  2 +-
 drivers/mtd/nand/raw/fsl_elbc_nand.c             | 18 +++---
 drivers/mtd/nand/raw/fsl_ifc_nand.c              | 10 +--
 drivers/mtd/nand/raw/fsl_upm.c                   |  2 +-
 drivers/mtd/nand/raw/fsmc_nand.c                 | 12 ++--
 drivers/mtd/nand/raw/gpio.c                      |  2 +-
 drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c       |  2 +-
 drivers/mtd/nand/raw/hisi504_nand.c              |  6 +-
 drivers/mtd/nand/raw/ingenic/ingenic_nand_drv.c  | 14 ++---
 drivers/mtd/nand/raw/lpc32xx_mlc.c               |  2 +-
 drivers/mtd/nand/raw/lpc32xx_slc.c               |  2 +-
 drivers/mtd/nand/raw/marvell_nand.c              | 17 ++---
 drivers/mtd/nand/raw/meson_nand.c                |  2 +-
 drivers/mtd/nand/raw/mpc5121_nfc.c               |  2 +-
 drivers/mtd/nand/raw/mtk_nand.c                  |  6 +-
 drivers/mtd/nand/raw/mxc_nand.c                  | 23 +++----
 drivers/mtd/nand/raw/nand_base.c                 | 80 +++++++++++++++---------
 drivers/mtd/nand/raw/nand_micron.c               |  4 +-
 drivers/mtd/nand/raw/nand_toshiba.c              |  3 +-
 drivers/mtd/nand/raw/nandsim.c                   |  4 +-
 drivers/mtd/nand/raw/ndfc.c                      |  2 +-
 drivers/mtd/nand/raw/omap2.c                     | 20 +++---
 drivers/mtd/nand/raw/orion_nand.c                |  2 +-
 drivers/mtd/nand/raw/pasemi_nand.c               |  2 +-
 drivers/mtd/nand/raw/plat_nand.c                 |  2 +-
 drivers/mtd/nand/raw/qcom_nandc.c                |  2 +-
 drivers/mtd/nand/raw/r852.c                      |  2 +-
 drivers/mtd/nand/raw/s3c2410.c                   | 18 +++---
 drivers/mtd/nand/raw/sh_flctl.c                  |  4 +-
 drivers/mtd/nand/raw/sharpsl.c                   |  2 +-
 drivers/mtd/nand/raw/socrates_nand.c             |  3 +-
 drivers/mtd/nand/raw/stm32_fmc2_nand.c           |  9 +--
 drivers/mtd/nand/raw/sunxi_nand.c                | 18 +++---
 drivers/mtd/nand/raw/tango_nand.c                |  2 +-
 drivers/mtd/nand/raw/tegra_nand.c                |  2 +-
 drivers/mtd/nand/raw/tmio_nand.c                 |  2 +-
 drivers/mtd/nand/raw/txx9ndfmc.c                 |  2 +-
 drivers/mtd/nand/raw/vf610_nfc.c                 |  4 +-
 drivers/mtd/nand/raw/xway_nand.c                 |  2 +-
 include/linux/mtd/rawnand.h                      |  4 +-
 include/linux/platform_data/mtd-davinci.h        |  8 +--
 include/linux/platform_data/mtd-nand-s3c2410.h   |  2 +-
 78 files changed, 239 insertions(+), 213 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/mach-davinci/board-da830-evm.c b/arch/arm/mach-davinci/board-da830-evm.c
index 1076886938b6..a20ba12d876c 100644
--- a/arch/arm/mach-davinci/board-da830-evm.c
+++ b/arch/arm/mach-davinci/board-da830-evm.c
@@ -306,7 +306,7 @@ static struct davinci_nand_pdata da830_evm_nand_pdata = {
 	.core_chipsel	= 1,
 	.parts		= da830_evm_nand_partitions,
 	.nr_parts	= ARRAY_SIZE(da830_evm_nand_partitions),
-	.ecc_mode	= NAND_ECC_HW,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_ON_HOST,
 	.ecc_bits	= 4,
 	.bbt_options	= NAND_BBT_USE_FLASH,
 	.bbt_td		= &da830_evm_nand_bbt_main_descr,
diff --git a/arch/arm/mach-davinci/board-da850-evm.c b/arch/arm/mach-davinci/board-da850-evm.c
index 6751292e5f8f..428012687a80 100644
--- a/arch/arm/mach-davinci/board-da850-evm.c
+++ b/arch/arm/mach-davinci/board-da850-evm.c
@@ -239,7 +239,7 @@ static struct davinci_nand_pdata da850_evm_nandflash_data = {
 	.core_chipsel	= 1,
 	.parts		= da850_evm_nandflash_partition,
 	.nr_parts	= ARRAY_SIZE(da850_evm_nandflash_partition),
-	.ecc_mode	= NAND_ECC_HW,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_ON_HOST,
 	.ecc_bits	= 4,
 	.bbt_options	= NAND_BBT_USE_FLASH,
 	.timing		= &da850_evm_nandflash_timing,
diff --git a/arch/arm/mach-davinci/board-dm355-evm.c b/arch/arm/mach-davinci/board-dm355-evm.c
index 5113273fda69..3c5a9e3c128a 100644
--- a/arch/arm/mach-davinci/board-dm355-evm.c
+++ b/arch/arm/mach-davinci/board-dm355-evm.c
@@ -82,7 +82,7 @@ static struct davinci_nand_pdata davinci_nand_data = {
 	.mask_chipsel		= BIT(14),
 	.parts			= davinci_nand_partitions,
 	.nr_parts		= ARRAY_SIZE(davinci_nand_partitions),
-	.ecc_mode		= NAND_ECC_HW,
+	.engine_type		= NAND_ECC_ENGINE_TYPE_ON_HOST,
 	.bbt_options		= NAND_BBT_USE_FLASH,
 	.ecc_bits		= 4,
 };
diff --git a/arch/arm/mach-davinci/board-dm355-leopard.c b/arch/arm/mach-davinci/board-dm355-leopard.c
index 4c8a592754ac..e475b2113e70 100644
--- a/arch/arm/mach-davinci/board-dm355-leopard.c
+++ b/arch/arm/mach-davinci/board-dm355-leopard.c
@@ -76,7 +76,7 @@ static struct davinci_nand_pdata davinci_nand_data = {
 	.mask_chipsel		= BIT(14),
 	.parts			= davinci_nand_partitions,
 	.nr_parts		= ARRAY_SIZE(davinci_nand_partitions),
-	.ecc_mode		= NAND_HW_ECC_ENGINE,
+	.engine_type		= NAND_ECC_ENGINE_TYPE_ON_HOST,
 	.ecc_placement		= NAND_ECC_PLACEMENT_INTERLEAVED,
 	.ecc_bits		= 4,
 	.bbt_options		= NAND_BBT_USE_FLASH,
diff --git a/arch/arm/mach-davinci/board-dm365-evm.c b/arch/arm/mach-davinci/board-dm365-evm.c
index 2328b15ac067..bdf31eb77620 100644
--- a/arch/arm/mach-davinci/board-dm365-evm.c
+++ b/arch/arm/mach-davinci/board-dm365-evm.c
@@ -146,7 +146,7 @@ static struct davinci_nand_pdata davinci_nand_data = {
 	.mask_chipsel		= BIT(14),
 	.parts			= davinci_nand_partitions,
 	.nr_parts		= ARRAY_SIZE(davinci_nand_partitions),
-	.ecc_mode		= NAND_ECC_HW,
+	.engine_type		= NAND_ECC_ENGINE_TYPE_ON_HOST,
 	.bbt_options		= NAND_BBT_USE_FLASH,
 	.ecc_bits		= 4,
 };
diff --git a/arch/arm/mach-davinci/board-dm644x-evm.c b/arch/arm/mach-davinci/board-dm644x-evm.c
index a5d3708fedf6..bcb3c4070945 100644
--- a/arch/arm/mach-davinci/board-dm644x-evm.c
+++ b/arch/arm/mach-davinci/board-dm644x-evm.c
@@ -162,7 +162,7 @@ static struct davinci_nand_pdata davinci_evm_nandflash_data = {
 	.core_chipsel	= 0,
 	.parts		= davinci_evm_nandflash_partition,
 	.nr_parts	= ARRAY_SIZE(davinci_evm_nandflash_partition),
-	.ecc_mode	= NAND_ECC_HW,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_ON_HOST,
 	.ecc_bits	= 1,
 	.bbt_options	= NAND_BBT_USE_FLASH,
 	.timing		= &davinci_evm_nandflash_timing,
diff --git a/arch/arm/mach-davinci/board-dm646x-evm.c b/arch/arm/mach-davinci/board-dm646x-evm.c
index dd7d60f4139a..8319a6067a68 100644
--- a/arch/arm/mach-davinci/board-dm646x-evm.c
+++ b/arch/arm/mach-davinci/board-dm646x-evm.c
@@ -91,7 +91,7 @@ static struct davinci_nand_pdata davinci_nand_data = {
 	.mask_ale 		= 0x40000,
 	.parts			= davinci_nand_partitions,
 	.nr_parts		= ARRAY_SIZE(davinci_nand_partitions),
-	.ecc_mode		= NAND_ECC_HW,
+	.engine_type		= NAND_ECC_ENGINE_TYPE_ON_HOST,
 	.ecc_bits		= 1,
 	.options		= 0,
 };
diff --git a/arch/arm/mach-davinci/board-mityomapl138.c b/arch/arm/mach-davinci/board-mityomapl138.c
index 3382b93d9a2a..5205008c8061 100644
--- a/arch/arm/mach-davinci/board-mityomapl138.c
+++ b/arch/arm/mach-davinci/board-mityomapl138.c
@@ -432,7 +432,7 @@ static struct davinci_nand_pdata mityomapl138_nandflash_data = {
 	.core_chipsel	= 1,
 	.parts		= mityomapl138_nandflash_partition,
 	.nr_parts	= ARRAY_SIZE(mityomapl138_nandflash_partition),
-	.ecc_mode	= NAND_ECC_HW,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_ON_HOST,
 	.bbt_options	= NAND_BBT_USE_FLASH,
 	.options	= NAND_BUSWIDTH_16,
 	.ecc_bits	= 1, /* 4 bit mode is not supported with 16 bit NAND */
diff --git a/arch/arm/mach-davinci/board-neuros-osd2.c b/arch/arm/mach-davinci/board-neuros-osd2.c
index 6cf46bbc7e1d..b4843f68bb57 100644
--- a/arch/arm/mach-davinci/board-neuros-osd2.c
+++ b/arch/arm/mach-davinci/board-neuros-osd2.c
@@ -90,7 +90,7 @@ static struct davinci_nand_pdata davinci_ntosd2_nandflash_data = {
 	.core_chipsel	= 0,
 	.parts		= davinci_ntosd2_nandflash_partition,
 	.nr_parts	= ARRAY_SIZE(davinci_ntosd2_nandflash_partition),
-	.ecc_mode	= NAND_ECC_HW,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_ON_HOST,
 	.ecc_bits	= 1,
 	.bbt_options	= NAND_BBT_USE_FLASH,
 };
diff --git a/arch/arm/mach-davinci/board-omapl138-hawk.c b/arch/arm/mach-davinci/board-omapl138-hawk.c
index 6c79039002c9..88df8011a4e6 100644
--- a/arch/arm/mach-davinci/board-omapl138-hawk.c
+++ b/arch/arm/mach-davinci/board-omapl138-hawk.c
@@ -206,7 +206,7 @@ static struct davinci_nand_pdata omapl138_hawk_nandflash_data = {
 	.core_chipsel	= 1,
 	.parts		= omapl138_hawk_nandflash_partition,
 	.nr_parts	= ARRAY_SIZE(omapl138_hawk_nandflash_partition),
-	.ecc_mode	= NAND_ECC_HW,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_ON_HOST,
 	.ecc_bits	= 4,
 	.bbt_options	= NAND_BBT_USE_FLASH,
 	.options	= NAND_BUSWIDTH_16,
diff --git a/arch/arm/mach-s3c24xx/common-smdk.c b/arch/arm/mach-s3c24xx/common-smdk.c
index 75064dfaceb1..121646ad1bb1 100644
--- a/arch/arm/mach-s3c24xx/common-smdk.c
+++ b/arch/arm/mach-s3c24xx/common-smdk.c
@@ -191,7 +191,7 @@ static struct s3c2410_platform_nand smdk_nand_info = {
 	.twrph1		= 20,
 	.nr_sets	= ARRAY_SIZE(smdk_nand_sets),
 	.sets		= smdk_nand_sets,
-	.ecc_mode       = NAND_ECC_SOFT,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_SOFT,
 };
 
 /* devices we initialise */
diff --git a/arch/arm/mach-s3c24xx/mach-anubis.c b/arch/arm/mach-s3c24xx/mach-anubis.c
index 072966dcad78..28326241e360 100644
--- a/arch/arm/mach-s3c24xx/mach-anubis.c
+++ b/arch/arm/mach-s3c24xx/mach-anubis.c
@@ -218,7 +218,7 @@ static struct s3c2410_platform_nand __initdata anubis_nand_info = {
 	.nr_sets	= ARRAY_SIZE(anubis_nand_sets),
 	.sets		= anubis_nand_sets,
 	.select_chip	= anubis_nand_select,
-	.ecc_mode       = NAND_ECC_SOFT,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_SOFT,
 };
 
 /* IDE channels */
diff --git a/arch/arm/mach-s3c24xx/mach-at2440evb.c b/arch/arm/mach-s3c24xx/mach-at2440evb.c
index 58c5ef3cf1d7..04dedebdb57c 100644
--- a/arch/arm/mach-s3c24xx/mach-at2440evb.c
+++ b/arch/arm/mach-s3c24xx/mach-at2440evb.c
@@ -109,7 +109,7 @@ static struct s3c2410_platform_nand __initdata at2440evb_nand_info = {
 	.twrph1		= 40,
 	.nr_sets	= ARRAY_SIZE(at2440evb_nand_sets),
 	.sets		= at2440evb_nand_sets,
-	.ecc_mode       = NAND_ECC_SOFT,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_SOFT,
 };
 
 /* DM9000AEP 10/100 ethernet controller */
diff --git a/arch/arm/mach-s3c24xx/mach-bast.c b/arch/arm/mach-s3c24xx/mach-bast.c
index a7c3955ae8f6..6465eab0ab3a 100644
--- a/arch/arm/mach-s3c24xx/mach-bast.c
+++ b/arch/arm/mach-s3c24xx/mach-bast.c
@@ -294,7 +294,7 @@ static struct s3c2410_platform_nand __initdata bast_nand_info = {
 	.nr_sets	= ARRAY_SIZE(bast_nand_sets),
 	.sets		= bast_nand_sets,
 	.select_chip	= bast_nand_select,
-	.ecc_mode       = NAND_ECC_SOFT,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_SOFT,
 };
 
 /* DM9000 */
diff --git a/arch/arm/mach-s3c24xx/mach-gta02.c b/arch/arm/mach-s3c24xx/mach-gta02.c
index 594901f3b8e5..db1b64f6e0a5 100644
--- a/arch/arm/mach-s3c24xx/mach-gta02.c
+++ b/arch/arm/mach-s3c24xx/mach-gta02.c
@@ -416,7 +416,7 @@ static struct s3c2410_platform_nand __initdata gta02_nand_info = {
 	.twrph1		= 15,
 	.nr_sets	= ARRAY_SIZE(gta02_nand_sets),
 	.sets		= gta02_nand_sets,
-	.ecc_mode       = NAND_ECC_SOFT,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_SOFT,
 };
 
 
diff --git a/arch/arm/mach-s3c24xx/mach-jive.c b/arch/arm/mach-s3c24xx/mach-jive.c
index 885e8f12e4b9..8233dcff19e7 100644
--- a/arch/arm/mach-s3c24xx/mach-jive.c
+++ b/arch/arm/mach-s3c24xx/mach-jive.c
@@ -228,7 +228,7 @@ static struct s3c2410_platform_nand __initdata jive_nand_info = {
 	.twrph1		= 40,
 	.sets		= jive_nand_sets,
 	.nr_sets	= ARRAY_SIZE(jive_nand_sets),
-	.ecc_mode       = NAND_ECC_SOFT,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_SOFT,
 };
 
 static int __init jive_mtdset(char *options)
diff --git a/arch/arm/mach-s3c24xx/mach-mini2440.c b/arch/arm/mach-s3c24xx/mach-mini2440.c
index 235749448311..057dcbaf1b22 100644
--- a/arch/arm/mach-s3c24xx/mach-mini2440.c
+++ b/arch/arm/mach-s3c24xx/mach-mini2440.c
@@ -296,7 +296,7 @@ static struct s3c2410_platform_nand mini2440_nand_info __initdata = {
 	.nr_sets	= ARRAY_SIZE(mini2440_nand_sets),
 	.sets		= mini2440_nand_sets,
 	.ignore_unset_ecc = 1,
-	.ecc_mode	= NAND_ECC_HW,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_ON_HOST,
 };
 
 /* DM9000AEP 10/100 ethernet controller */
diff --git a/arch/arm/mach-s3c24xx/mach-osiris.c b/arch/arm/mach-s3c24xx/mach-osiris.c
index ee3630cb236a..157448827f61 100644
--- a/arch/arm/mach-s3c24xx/mach-osiris.c
+++ b/arch/arm/mach-s3c24xx/mach-osiris.c
@@ -234,7 +234,7 @@ static struct s3c2410_platform_nand __initdata osiris_nand_info = {
 	.nr_sets	= ARRAY_SIZE(osiris_nand_sets),
 	.sets		= osiris_nand_sets,
 	.select_chip	= osiris_nand_select,
-	.ecc_mode       = NAND_ECC_SOFT,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_SOFT,
 };
 
 /* PCMCIA control and configuration */
diff --git a/arch/arm/mach-s3c24xx/mach-qt2410.c b/arch/arm/mach-s3c24xx/mach-qt2410.c
index ff9e3197309b..f3131d94e90b 100644
--- a/arch/arm/mach-s3c24xx/mach-qt2410.c
+++ b/arch/arm/mach-s3c24xx/mach-qt2410.c
@@ -287,7 +287,7 @@ static struct s3c2410_platform_nand __initdata qt2410_nand_info = {
 	.twrph1		= 20,
 	.nr_sets	= ARRAY_SIZE(qt2410_nand_sets),
 	.sets		= qt2410_nand_sets,
-	.ecc_mode       = NAND_ECC_SOFT,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_SOFT,
 };
 
 /* UDC */
diff --git a/arch/arm/mach-s3c24xx/mach-rx1950.c b/arch/arm/mach-s3c24xx/mach-rx1950.c
index fde98b175c75..5ecb42e8a028 100644
--- a/arch/arm/mach-s3c24xx/mach-rx1950.c
+++ b/arch/arm/mach-s3c24xx/mach-rx1950.c
@@ -620,7 +620,7 @@ static struct s3c2410_platform_nand rx1950_nand_info = {
 	.twrph1 = 15,
 	.nr_sets = ARRAY_SIZE(rx1950_nand_sets),
 	.sets = rx1950_nand_sets,
-	.ecc_mode = NAND_ECC_SOFT,
+	.engine_type = NAND_ECC_ENGINE_TYPE_SOFT,
 };
 
 static struct s3c2410_udc_mach_info rx1950_udc_cfg __initdata = {
diff --git a/arch/arm/mach-s3c24xx/mach-rx3715.c b/arch/arm/mach-s3c24xx/mach-rx3715.c
index 995f1ff34a1b..017010d67e01 100644
--- a/arch/arm/mach-s3c24xx/mach-rx3715.c
+++ b/arch/arm/mach-s3c24xx/mach-rx3715.c
@@ -158,7 +158,7 @@ static struct s3c2410_platform_nand __initdata rx3715_nand_info = {
 	.twrph1		= 15,
 	.nr_sets	= ARRAY_SIZE(rx3715_nand_sets),
 	.sets		= rx3715_nand_sets,
-	.ecc_mode       = NAND_ECC_SOFT,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_SOFT,
 };
 
 static struct platform_device *rx3715_devices[] __initdata = {
diff --git a/arch/arm/mach-s3c24xx/mach-vstms.c b/arch/arm/mach-s3c24xx/mach-vstms.c
index d76b28b65e65..c5fa215a527e 100644
--- a/arch/arm/mach-s3c24xx/mach-vstms.c
+++ b/arch/arm/mach-s3c24xx/mach-vstms.c
@@ -112,7 +112,7 @@ static struct s3c2410_platform_nand __initdata vstms_nand_info = {
 	.twrph1		= 20,
 	.nr_sets	= ARRAY_SIZE(vstms_nand_sets),
 	.sets		= vstms_nand_sets,
-	.ecc_mode       = NAND_ECC_SOFT,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_SOFT,
 };
 
 static struct platform_device *vstms_devices[] __initdata = {
diff --git a/arch/arm/mach-s3c64xx/mach-hmt.c b/arch/arm/mach-s3c64xx/mach-hmt.c
index e7080215c624..0d9acaf91701 100644
--- a/arch/arm/mach-s3c64xx/mach-hmt.c
+++ b/arch/arm/mach-s3c64xx/mach-hmt.c
@@ -199,7 +199,7 @@ static struct s3c2410_platform_nand hmt_nand_info = {
 	.twrph1		= 40,
 	.nr_sets	= ARRAY_SIZE(hmt_nand_sets),
 	.sets		= hmt_nand_sets,
-	.ecc_mode       = NAND_ECC_SOFT,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_SOFT,
 };
 
 static struct gpio_led hmt_leds[] = {
diff --git a/arch/arm/mach-s3c64xx/mach-mini6410.c b/arch/arm/mach-s3c64xx/mach-mini6410.c
index 0dd36ae49e6a..6fbb57878746 100644
--- a/arch/arm/mach-s3c64xx/mach-mini6410.c
+++ b/arch/arm/mach-s3c64xx/mach-mini6410.c
@@ -136,7 +136,7 @@ static struct s3c2410_platform_nand mini6410_nand_info = {
 	.twrph1		= 40,
 	.nr_sets	= ARRAY_SIZE(mini6410_nand_sets),
 	.sets		= mini6410_nand_sets,
-	.ecc_mode       = NAND_ECC_SOFT,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_SOFT,
 };
 
 static struct s3c_fb_pd_win mini6410_lcd_type0_fb_win = {
diff --git a/arch/arm/mach-s3c64xx/mach-real6410.c b/arch/arm/mach-s3c64xx/mach-real6410.c
index 0ff88b6859c4..1e98e530a6aa 100644
--- a/arch/arm/mach-s3c64xx/mach-real6410.c
+++ b/arch/arm/mach-s3c64xx/mach-real6410.c
@@ -188,7 +188,7 @@ static struct s3c2410_platform_nand real6410_nand_info = {
 	.twrph1		= 40,
 	.nr_sets	= ARRAY_SIZE(real6410_nand_sets),
 	.sets		= real6410_nand_sets,
-	.ecc_mode       = NAND_ECC_SOFT,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_SOFT,
 };
 
 static struct platform_device *real6410_devices[] __initdata = {
diff --git a/drivers/mtd/nand/raw/ams-delta.c b/drivers/mtd/nand/raw/ams-delta.c
index 21199d9ae9be..770d4f1001bb 100644
--- a/drivers/mtd/nand/raw/ams-delta.c
+++ b/drivers/mtd/nand/raw/ams-delta.c
@@ -260,7 +260,7 @@ static int gpio_nand_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	this->ecc.mode = NAND_ECC_SOFT;
+	this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 	this->ecc.algo = NAND_ECC_ALGO_HAMMING;
 
 	platform_set_drvdata(pdev, priv);
diff --git a/drivers/mtd/nand/raw/arasan-nand-controller.c b/drivers/mtd/nand/raw/arasan-nand-controller.c
index b0616a95340d..006bc3d3ce20 100644
--- a/drivers/mtd/nand/raw/arasan-nand-controller.c
+++ b/drivers/mtd/nand/raw/arasan-nand-controller.c
@@ -1056,17 +1056,17 @@ static int anfc_attach_chip(struct nand_chip *chip)
 	chip->ecc.read_page_raw = nand_monolithic_read_page_raw;
 	chip->ecc.write_page_raw = nand_monolithic_write_page_raw;
 
-	switch (chip->ecc.mode) {
-	case NAND_ECC_NONE:
-	case NAND_ECC_SOFT:
-	case NAND_ECC_ON_DIE:
+	switch (chip->ecc.engine_type) {
+	case NAND_ECC_ENGINE_TYPE_NONE:
+	case NAND_ECC_ENGINE_TYPE_SOFT:
+	case NAND_ECC_ENGINE_TYPE_ON_DIE:
 		break;
-	case NAND_ECC_HW:
+	case NAND_ECC_ENGINE_TYPE_ON_HOST:
 		ret = anfc_init_hw_ecc_controller(nfc, chip);
 		break;
 	default:
 		dev_err(nfc->dev, "Unsupported ECC mode: %d\n",
-			chip->ecc.mode);
+			chip->ecc.engine_type);
 		return -EINVAL;
 	}
 
diff --git a/drivers/mtd/nand/raw/atmel/nand-controller.c b/drivers/mtd/nand/raw/atmel/nand-controller.c
index 8999571bfa5d..0d9cd7faf00d 100644
--- a/drivers/mtd/nand/raw/atmel/nand-controller.c
+++ b/drivers/mtd/nand/raw/atmel/nand-controller.c
@@ -1118,15 +1118,15 @@ static int atmel_nand_ecc_init(struct nand_chip *chip)
 
 	nc = to_nand_controller(chip->controller);
 
-	switch (chip->ecc.mode) {
-	case NAND_ECC_NONE:
-	case NAND_ECC_SOFT:
+	switch (chip->ecc.engine_type) {
+	case NAND_ECC_ENGINE_TYPE_NONE:
+	case NAND_ECC_ENGINE_TYPE_SOFT:
 		/*
 		 * Nothing to do, the core will initialize everything for us.
 		 */
 		break;
 
-	case NAND_ECC_HW:
+	case NAND_ECC_ENGINE_TYPE_ON_HOST:
 		ret = atmel_nand_pmecc_init(chip);
 		if (ret)
 			return ret;
@@ -1140,7 +1140,7 @@ static int atmel_nand_ecc_init(struct nand_chip *chip)
 	default:
 		/* Other modes are not supported. */
 		dev_err(nc->dev, "Unsupported ECC mode: %d\n",
-			chip->ecc.mode);
+			chip->ecc.engine_type);
 		return -ENOTSUPP;
 	}
 
@@ -1155,7 +1155,7 @@ static int atmel_hsmc_nand_ecc_init(struct nand_chip *chip)
 	if (ret)
 		return ret;
 
-	if (chip->ecc.mode != NAND_ECC_HW)
+	if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST)
 		return 0;
 
 	/* Adjust the ECC operations for the HSMC IP. */
@@ -1498,7 +1498,7 @@ static void atmel_nand_init(struct atmel_nand_controller *nc,
 
 	/* Default to HW ECC if pmecc is available. */
 	if (nc->pmecc)
-		chip->ecc.mode = NAND_ECC_HW;
+		chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 }
 
 static void atmel_smc_nand_init(struct atmel_nand_controller *nc,
diff --git a/drivers/mtd/nand/raw/au1550nd.c b/drivers/mtd/nand/raw/au1550nd.c
index ec2d90ad87de..79b057400fe9 100644
--- a/drivers/mtd/nand/raw/au1550nd.c
+++ b/drivers/mtd/nand/raw/au1550nd.c
@@ -294,7 +294,7 @@ static int au1550nd_probe(struct platform_device *pdev)
 	nand_controller_init(&ctx->controller);
 	ctx->controller.ops = &au1550nd_ops;
 	this->controller = &ctx->controller;
-	this->ecc.mode = NAND_ECC_SOFT;
+	this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 	this->ecc.algo = NAND_ECC_ALGO_HAMMING;
 
 	if (pd->devwidth)
diff --git a/drivers/mtd/nand/raw/bcm47xxnflash/ops_bcm4706.c b/drivers/mtd/nand/raw/bcm47xxnflash/ops_bcm4706.c
index 591775173034..8bb17c5a66c3 100644
--- a/drivers/mtd/nand/raw/bcm47xxnflash/ops_bcm4706.c
+++ b/drivers/mtd/nand/raw/bcm47xxnflash/ops_bcm4706.c
@@ -391,7 +391,8 @@ int bcm47xxnflash_ops_bcm4706_init(struct bcm47xxnflash *b47n)
 
 	nand_chip->legacy.chip_delay = 50;
 	b47n->nand_chip.bbt_options = NAND_BBT_USE_FLASH;
-	b47n->nand_chip.ecc.mode = NAND_ECC_NONE; /* TODO: implement ECC */
+	/* TODO: implement ECC */
+	b47n->nand_chip.ecc.engine_type = NAND_ECC_ENGINE_TYPE_NONE;
 
 	/* Enable NAND flash access */
 	bcma_cc_set32(b47n->cc, BCMA_CC_4706_FLASHSCFG,
diff --git a/drivers/mtd/nand/raw/brcmnand/brcmnand.c b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
index 39f1bf327592..afe27a27cb93 100644
--- a/drivers/mtd/nand/raw/brcmnand/brcmnand.c
+++ b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
@@ -2565,9 +2565,9 @@ static int brcmnand_setup_dev(struct brcmnand_host *host)
 	cfg->col_adr_bytes = 2;
 	cfg->blk_adr_bytes = get_blk_adr_bytes(mtd->size, mtd->writesize);
 
-	if (chip->ecc.mode != NAND_ECC_HW) {
+	if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST) {
 		dev_err(ctrl->dev, "only HW ECC supported; selected: %d\n",
-			chip->ecc.mode);
+			chip->ecc.engine_type);
 		return -EINVAL;
 	}
 
@@ -2587,7 +2587,7 @@ static int brcmnand_setup_dev(struct brcmnand_host *host)
 		return -EINVAL;
 	}
 
-	if (chip->ecc.mode != NAND_ECC_NONE &&
+	if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_NONE &&
 	    (!chip->ecc.size || !chip->ecc.strength)) {
 		if (chip->base.eccreq.step_size && chip->base.eccreq.strength) {
 			/* use detected ECC parameters */
@@ -2728,7 +2728,7 @@ static int brcmnand_init_cs(struct brcmnand_host *host, struct device_node *dn)
 	chip->legacy.read_buf = brcmnand_read_buf;
 	chip->legacy.write_buf = brcmnand_write_buf;
 
-	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	chip->ecc.read_page = brcmnand_read_page;
 	chip->ecc.write_page = brcmnand_write_page;
 	chip->ecc.read_page_raw = brcmnand_read_page_raw;
diff --git a/drivers/mtd/nand/raw/cadence-nand-controller.c b/drivers/mtd/nand/raw/cadence-nand-controller.c
index 71516af85f23..db29e5e512df 100644
--- a/drivers/mtd/nand/raw/cadence-nand-controller.c
+++ b/drivers/mtd/nand/raw/cadence-nand-controller.c
@@ -2611,7 +2611,7 @@ static int cadence_nand_attach_chip(struct nand_chip *chip)
 
 	chip->bbt_options |= NAND_BBT_USE_FLASH;
 	chip->bbt_options |= NAND_BBT_NO_OOB;
-	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 
 	chip->options |= NAND_NO_SUBPAGE_WRITE;
 
@@ -2757,7 +2757,7 @@ static int cadence_nand_chip_init(struct cdns_nand_ctrl *cdns_ctrl,
 	 * Default to HW ECC engine mode. If the nand-ecc-mode property is given
 	 * in the DT node, this entry will be overwritten in nand_scan_ident().
 	 */
-	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 
 	ret = nand_scan(chip, cdns_chip->nsels);
 	if (ret) {
diff --git a/drivers/mtd/nand/raw/cafe_nand.c b/drivers/mtd/nand/raw/cafe_nand.c
index 2bf8ab542e38..2b94f385a1a8 100644
--- a/drivers/mtd/nand/raw/cafe_nand.c
+++ b/drivers/mtd/nand/raw/cafe_nand.c
@@ -629,7 +629,7 @@ static int cafe_nand_attach_chip(struct nand_chip *chip)
 		goto out_free_dma;
 	}
 
-	cafe->nand.ecc.mode = NAND_ECC_HW;
+	cafe->nand.ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	cafe->nand.ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED;
 	cafe->nand.ecc.size = mtd->writesize;
 	cafe->nand.ecc.bytes = 14;
diff --git a/drivers/mtd/nand/raw/cs553x_nand.c b/drivers/mtd/nand/raw/cs553x_nand.c
index 9472bf798ed5..b7f3f6347761 100644
--- a/drivers/mtd/nand/raw/cs553x_nand.c
+++ b/drivers/mtd/nand/raw/cs553x_nand.c
@@ -286,7 +286,7 @@ static int __init cs553x_init_one(int cs, int mmio, unsigned long adr)
 		goto out_mtd;
 	}
 
-	this->ecc.mode = NAND_ECC_HW;
+	this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	this->ecc.size = 256;
 	this->ecc.bytes = 3;
 	this->ecc.hwctl  = cs_enable_hwecc;
diff --git a/drivers/mtd/nand/raw/davinci_nand.c b/drivers/mtd/nand/raw/davinci_nand.c
index 3640c7e45e15..58966a9706b1 100644
--- a/drivers/mtd/nand/raw/davinci_nand.c
+++ b/drivers/mtd/nand/raw/davinci_nand.c
@@ -530,11 +530,11 @@ static struct davinci_nand_pdata
 		if (!of_property_read_string(pdev->dev.of_node,
 			"ti,davinci-ecc-mode", &mode)) {
 			if (!strncmp("none", mode, 4))
-				pdata->ecc_mode = NAND_ECC_NONE;
+				pdata->engine_type = NAND_ECC_ENGINE_TYPE_NONE;
 			if (!strncmp("soft", mode, 4))
-				pdata->ecc_mode = NAND_ECC_SOFT;
+				pdata->engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 			if (!strncmp("hw", mode, 2))
-				pdata->ecc_mode = NAND_ECC_HW;
+				pdata->engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 		}
 		if (!of_property_read_u32(pdev->dev.of_node,
 			"ti,davinci-ecc-bits", &prop))
@@ -585,21 +585,21 @@ static int davinci_nand_attach_chip(struct nand_chip *chip)
 	if (IS_ERR(pdata))
 		return PTR_ERR(pdata);
 
-	switch (info->chip.ecc.mode) {
-	case NAND_ECC_NONE:
+	switch (info->chip.ecc.engine_type) {
+	case NAND_ECC_ENGINE_TYPE_NONE:
 		pdata->ecc_bits = 0;
 		break;
-	case NAND_ECC_SOFT:
+	case NAND_ECC_ENGINE_TYPE_SOFT:
 		pdata->ecc_bits = 0;
 		/*
-		 * This driver expects Hamming based ECC when ecc_mode is set
-		 * to NAND_ECC_SOFT. Force ecc.algo to NAND_ECC_ALGO_HAMMING to
-		 * avoid adding an extra ->ecc_algo field to
-		 * davinci_nand_pdata.
+		 * This driver expects Hamming based ECC when engine_type is set
+		 * to NAND_ECC_ENGINE_TYPE_SOFT. Force ecc.algo to
+		 * NAND_ECC_ALGO_HAMMING to avoid adding an extra ->ecc_algo
+		 * field to davinci_nand_pdata.
 		 */
 		info->chip.ecc.algo = NAND_ECC_ALGO_HAMMING;
 		break;
-	case NAND_ECC_HW:
+	case NAND_ECC_ENGINE_TYPE_ON_HOST:
 		if (pdata->ecc_bits == 4) {
 			int chunks = mtd->writesize / 512;
 
@@ -850,7 +850,7 @@ static int nand_davinci_probe(struct platform_device *pdev)
 	info->mask_cle		= pdata->mask_cle ? : MASK_CLE;
 
 	/* Use board-specific ECC config */
-	info->chip.ecc.mode	= pdata->ecc_mode;
+	info->chip.ecc.engine_type = pdata->engine_type;
 	info->chip.ecc.placement = pdata->ecc_placement;
 
 	spin_lock_irq(&davinci_nand_lock);
diff --git a/drivers/mtd/nand/raw/denali.c b/drivers/mtd/nand/raw/denali.c
index 0e54b8a61cf0..fa2439cb4daa 100644
--- a/drivers/mtd/nand/raw/denali.c
+++ b/drivers/mtd/nand/raw/denali.c
@@ -1237,7 +1237,7 @@ int denali_chip_init(struct denali_controller *denali,
 	chip->bbt_options |= NAND_BBT_USE_FLASH;
 	chip->bbt_options |= NAND_BBT_NO_OOB;
 	chip->options |= NAND_NO_SUBPAGE_WRITE;
-	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	chip->ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED;
 	chip->ecc.read_page = denali_read_page;
 	chip->ecc.write_page = denali_write_page;
diff --git a/drivers/mtd/nand/raw/diskonchip.c b/drivers/mtd/nand/raw/diskonchip.c
index 40360352136b..94432a453e5e 100644
--- a/drivers/mtd/nand/raw/diskonchip.c
+++ b/drivers/mtd/nand/raw/diskonchip.c
@@ -1456,7 +1456,7 @@ static int __init doc_probe(unsigned long physadr)
 	nand->ecc.calculate	= doc200x_calculate_ecc;
 	nand->ecc.correct	= doc200x_correct_data;
 
-	nand->ecc.mode		= NAND_ECC_HW;
+	nand->ecc.engine_type	= NAND_ECC_ENGINE_TYPE_ON_HOST;
 	nand->ecc.placement	= NAND_ECC_PLACEMENT_INTERLEAVED;
 	nand->ecc.size		= 512;
 	nand->ecc.bytes		= 6;
diff --git a/drivers/mtd/nand/raw/fsl_elbc_nand.c b/drivers/mtd/nand/raw/fsl_elbc_nand.c
index da89389faaae..b2af7f81fdf8 100644
--- a/drivers/mtd/nand/raw/fsl_elbc_nand.c
+++ b/drivers/mtd/nand/raw/fsl_elbc_nand.c
@@ -244,7 +244,7 @@ static int fsl_elbc_run_command(struct mtd_info *mtd)
 		return -EIO;
 	}
 
-	if (chip->ecc.mode != NAND_ECC_HW)
+	if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST)
 		return 0;
 
 	elbc_fcm_ctrl->max_bitflips = 0;
@@ -727,12 +727,12 @@ static int fsl_elbc_attach_chip(struct nand_chip *chip)
 	struct fsl_lbc_regs __iomem *lbc = ctrl->regs;
 	unsigned int al;
 
-	switch (chip->ecc.mode) {
+	switch (chip->ecc.engine_type) {
 	/*
 	 * if ECC was not chosen in DT, decide whether to use HW or SW ECC from
 	 * CS Base Register
 	 */
-	case NAND_ECC_NONE:
+	case NAND_ECC_ENGINE_TYPE_NONE:
 		/* If CS Base Register selects full hardware ECC then use it */
 		if ((in_be32(&lbc->bank[priv->bank].br) & BR_DECC) ==
 		    BR_DECC_CHK_GEN) {
@@ -740,23 +740,23 @@ static int fsl_elbc_attach_chip(struct nand_chip *chip)
 			chip->ecc.write_page = fsl_elbc_write_page;
 			chip->ecc.write_subpage = fsl_elbc_write_subpage;
 
-			chip->ecc.mode = NAND_ECC_HW;
+			chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 			mtd_set_ooblayout(mtd, &fsl_elbc_ooblayout_ops);
 			chip->ecc.size = 512;
 			chip->ecc.bytes = 3;
 			chip->ecc.strength = 1;
 		} else {
 			/* otherwise fall back to default software ECC */
-			chip->ecc.mode = NAND_ECC_SOFT;
+			chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 			chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
 		}
 		break;
 
 	/* if SW ECC was chosen in DT, we do not need to set anything here */
-	case NAND_ECC_SOFT:
+	case NAND_ECC_ENGINE_TYPE_SOFT:
 		break;
 
-	/* should we also implement NAND_ECC_HW to do as the code above? */
+	/* should we also implement *_ECC_ENGINE_CONTROLLER to do as above? */
 	default:
 		return -EINVAL;
 	}
@@ -786,8 +786,8 @@ static int fsl_elbc_attach_chip(struct nand_chip *chip)
 	        chip->page_shift);
 	dev_dbg(priv->dev, "fsl_elbc_init: nand->phys_erase_shift = %d\n",
 	        chip->phys_erase_shift);
-	dev_dbg(priv->dev, "fsl_elbc_init: nand->ecc.mode = %d\n",
-	        chip->ecc.mode);
+	dev_dbg(priv->dev, "fsl_elbc_init: nand->ecc.engine_type = %d\n",
+		chip->ecc.engine_type);
 	dev_dbg(priv->dev, "fsl_elbc_init: nand->ecc.steps = %d\n",
 	        chip->ecc.steps);
 	dev_dbg(priv->dev, "fsl_elbc_init: nand->ecc.bytes = %d\n",
diff --git a/drivers/mtd/nand/raw/fsl_ifc_nand.c b/drivers/mtd/nand/raw/fsl_ifc_nand.c
index b2ae759dd14e..0e7a9b64301e 100644
--- a/drivers/mtd/nand/raw/fsl_ifc_nand.c
+++ b/drivers/mtd/nand/raw/fsl_ifc_nand.c
@@ -309,7 +309,7 @@ static void fsl_ifc_cmdfunc(struct nand_chip *chip, unsigned int command,
 		ifc_nand_ctrl->read_bytes = mtd->writesize + mtd->oobsize;
 		ifc_nand_ctrl->index += column;
 
-		if (chip->ecc.mode == NAND_ECC_HW)
+		if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_ON_HOST)
 			ifc_nand_ctrl->eccread = 1;
 
 		fsl_ifc_do_read(chip, 0, mtd);
@@ -724,8 +724,8 @@ static int fsl_ifc_attach_chip(struct nand_chip *chip)
 							chip->page_shift);
 	dev_dbg(priv->dev, "%s: nand->phys_erase_shift = %d\n", __func__,
 							chip->phys_erase_shift);
-	dev_dbg(priv->dev, "%s: nand->ecc.mode = %d\n", __func__,
-							chip->ecc.mode);
+	dev_dbg(priv->dev, "%s: nand->ecc.engine_type = %d\n", __func__,
+							chip->ecc.engine_type);
 	dev_dbg(priv->dev, "%s: nand->ecc.steps = %d\n", __func__,
 							chip->ecc.steps);
 	dev_dbg(priv->dev, "%s: nand->ecc.bytes = %d\n", __func__,
@@ -912,7 +912,7 @@ static int fsl_ifc_chip_init(struct fsl_ifc_mtd *priv)
 
 	/* Must also set CSOR_NAND_ECC_ENC_EN if DEC_EN set */
 	if (csor & CSOR_NAND_ECC_DEC_EN) {
-		chip->ecc.mode = NAND_ECC_HW;
+		chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 		mtd_set_ooblayout(mtd, &fsl_ifc_ooblayout_ops);
 
 		/* Hardware generates ECC per 512 Bytes */
@@ -925,7 +925,7 @@ static int fsl_ifc_chip_init(struct fsl_ifc_mtd *priv)
 			chip->ecc.strength = 8;
 		}
 	} else {
-		chip->ecc.mode = NAND_ECC_SOFT;
+		chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 		chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
 	}
 
diff --git a/drivers/mtd/nand/raw/fsl_upm.c b/drivers/mtd/nand/raw/fsl_upm.c
index 04cf7d14082a..d5813b9abc8e 100644
--- a/drivers/mtd/nand/raw/fsl_upm.c
+++ b/drivers/mtd/nand/raw/fsl_upm.c
@@ -47,7 +47,7 @@ static int fun_chip_init(struct fsl_upm_nand *fun,
 	int ret;
 	struct device_node *flash_np;
 
-	fun->chip.ecc.mode = NAND_ECC_SOFT;
+	fun->chip.ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 	fun->chip.ecc.algo = NAND_ECC_ALGO_HAMMING;
 	fun->chip.controller = &fun->base;
 	mtd->dev.parent = fun->dev;
diff --git a/drivers/mtd/nand/raw/fsmc_nand.c b/drivers/mtd/nand/raw/fsmc_nand.c
index 580b9fe8ca42..4191831df182 100644
--- a/drivers/mtd/nand/raw/fsmc_nand.c
+++ b/drivers/mtd/nand/raw/fsmc_nand.c
@@ -900,8 +900,8 @@ static int fsmc_nand_attach_chip(struct nand_chip *nand)
 		return 0;
 	}
 
-	switch (nand->ecc.mode) {
-	case NAND_ECC_HW:
+	switch (nand->ecc.engine_type) {
+	case NAND_ECC_ENGINE_TYPE_ON_HOST:
 		dev_info(host->dev, "Using 1-bit HW ECC scheme\n");
 		nand->ecc.calculate = fsmc_read_hwecc_ecc1;
 		nand->ecc.correct = nand_correct_data;
@@ -910,14 +910,14 @@ static int fsmc_nand_attach_chip(struct nand_chip *nand)
 		nand->ecc.options |= NAND_ECC_SOFT_HAMMING_SM_ORDER;
 		break;
 
-	case NAND_ECC_SOFT:
+	case NAND_ECC_ENGINE_TYPE_SOFT:
 		if (nand->ecc.algo == NAND_ECC_ALGO_BCH) {
 			dev_info(host->dev,
 				 "Using 4-bit SW BCH ECC scheme\n");
 			break;
 		}
 
-	case NAND_ECC_ON_DIE:
+	case NAND_ECC_ENGINE_TYPE_ON_DIE:
 		break;
 
 	default:
@@ -929,7 +929,7 @@ static int fsmc_nand_attach_chip(struct nand_chip *nand)
 	 * Don't set layout for BCH4 SW ECC. This will be
 	 * generated later in nand_bch_init() later.
 	 */
-	if (nand->ecc.mode == NAND_ECC_HW) {
+	if (nand->ecc.engine_type == NAND_ECC_ENGINE_TYPE_ON_HOST) {
 		switch (mtd->oobsize) {
 		case 16:
 		case 64:
@@ -1059,7 +1059,7 @@ static int __init fsmc_nand_probe(struct platform_device *pdev)
 	 * Setup default ECC mode. nand_dt_init() called from nand_scan_ident()
 	 * can overwrite this value if the DT provides a different value.
 	 */
-	nand->ecc.mode = NAND_ECC_HW;
+	nand->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	nand->ecc.hwctl = fsmc_enable_hwecc;
 	nand->ecc.size = 512;
 	nand->badblockbits = 7;
diff --git a/drivers/mtd/nand/raw/gpio.c b/drivers/mtd/nand/raw/gpio.c
index c8f498eaabeb..4ec0a1e10867 100644
--- a/drivers/mtd/nand/raw/gpio.c
+++ b/drivers/mtd/nand/raw/gpio.c
@@ -342,7 +342,7 @@ static int gpio_nand_probe(struct platform_device *pdev)
 	gpiomtd->base.ops = &gpio_nand_ops;
 
 	nand_set_flash_node(chip, pdev->dev.of_node);
-	chip->ecc.mode		= NAND_ECC_SOFT;
+	chip->ecc.engine_type	= NAND_ECC_ENGINE_TYPE_SOFT;
 	chip->ecc.algo		= NAND_ECC_ALGO_HAMMING;
 	chip->options		= gpiomtd->plat.options;
 	chip->controller	= &gpiomtd->base;
diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
index 5d4aee46cc55..9b015d360a50 100644
--- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
+++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
@@ -2032,7 +2032,7 @@ static int gpmi_init_last(struct gpmi_nand_data *this)
 	ecc->write_page_raw = gpmi_ecc_write_page_raw;
 	ecc->read_oob_raw = gpmi_ecc_read_oob_raw;
 	ecc->write_oob_raw = gpmi_ecc_write_oob_raw;
-	ecc->mode	= NAND_ECC_HW;
+	ecc->engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	ecc->size	= bch_geo->ecc_chunk_size;
 	ecc->strength	= bch_geo->ecc_strength;
 	mtd_set_ooblayout(mtd, &gpmi_ooblayout_ops);
diff --git a/drivers/mtd/nand/raw/hisi504_nand.c b/drivers/mtd/nand/raw/hisi504_nand.c
index b84238e2268a..8b2122ce6ec3 100644
--- a/drivers/mtd/nand/raw/hisi504_nand.c
+++ b/drivers/mtd/nand/raw/hisi504_nand.c
@@ -186,7 +186,7 @@ static void hisi_nfc_dma_transfer(struct hinfc_host *host, int todev)
 	hinfc_write(host, host->dma_buffer, HINFC504_DMA_ADDR_DATA);
 	hinfc_write(host, host->dma_oob, HINFC504_DMA_ADDR_OOB);
 
-	if (chip->ecc.mode == NAND_ECC_NONE) {
+	if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_NONE) {
 		hinfc_write(host, ((mtd->oobsize & HINFC504_DMA_LEN_OOB_MASK)
 			<< HINFC504_DMA_LEN_OOB_SHIFT), HINFC504_DMA_LEN);
 
@@ -468,7 +468,7 @@ static void hisi_nfc_cmdfunc(struct nand_chip *chip, unsigned command,
 
 	case NAND_CMD_STATUS:
 		flag = hinfc_read(host, HINFC504_CON);
-		if (chip->ecc.mode == NAND_ECC_HW)
+		if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_ON_HOST)
 			hinfc_write(host,
 				    flag & ~(HINFC504_CON_ECCTYPE_MASK <<
 				    HINFC504_CON_ECCTYPE_SHIFT), HINFC504_CON);
@@ -721,7 +721,7 @@ static int hisi_nfc_attach_chip(struct nand_chip *chip)
 	}
 	hinfc_write(host, flag, HINFC504_CON);
 
-	if (chip->ecc.mode == NAND_ECC_HW)
+	if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_ON_HOST)
 		hisi_nfc_ecc_probe(host);
 
 	return 0;
diff --git a/drivers/mtd/nand/raw/ingenic/ingenic_nand_drv.c b/drivers/mtd/nand/raw/ingenic/ingenic_nand_drv.c
index 69423bb29adb..70309f18124c 100644
--- a/drivers/mtd/nand/raw/ingenic/ingenic_nand_drv.c
+++ b/drivers/mtd/nand/raw/ingenic/ingenic_nand_drv.c
@@ -194,8 +194,8 @@ static int ingenic_nand_attach_chip(struct nand_chip *chip)
 				  (chip->ecc.strength / 8);
 	}
 
-	switch (chip->ecc.mode) {
-	case NAND_ECC_HW:
+	switch (chip->ecc.engine_type) {
+	case NAND_ECC_ENGINE_TYPE_ON_HOST:
 		if (!nfc->ecc) {
 			dev_err(nfc->dev, "HW ECC selected, but ECC controller not found\n");
 			return -ENODEV;
@@ -205,22 +205,22 @@ static int ingenic_nand_attach_chip(struct nand_chip *chip)
 		chip->ecc.calculate = ingenic_nand_ecc_calculate;
 		chip->ecc.correct = ingenic_nand_ecc_correct;
 		fallthrough;
-	case NAND_ECC_SOFT:
+	case NAND_ECC_ENGINE_TYPE_SOFT:
 		dev_info(nfc->dev, "using %s (strength %d, size %d, bytes %d)\n",
 			 (nfc->ecc) ? "hardware ECC" : "software ECC",
 			 chip->ecc.strength, chip->ecc.size, chip->ecc.bytes);
 		break;
-	case NAND_ECC_NONE:
+	case NAND_ECC_ENGINE_TYPE_NONE:
 		dev_info(nfc->dev, "not using ECC\n");
 		break;
 	default:
 		dev_err(nfc->dev, "ECC mode %d not supported\n",
-			chip->ecc.mode);
+			chip->ecc.engine_type);
 		return -EINVAL;
 	}
 
 	/* The NAND core will generate the ECC layout for SW ECC */
-	if (chip->ecc.mode != NAND_ECC_HW)
+	if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST)
 		return 0;
 
 	/* Generate ECC layout. ECC codes are right aligned in the OOB area. */
@@ -404,7 +404,7 @@ static int ingenic_nand_init_chip(struct platform_device *pdev,
 	mtd->dev.parent = dev;
 
 	chip->options = NAND_NO_SUBPAGE_WRITE;
-	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	chip->controller = &nfc->controller;
 	nand_set_flash_node(chip, np);
 
diff --git a/drivers/mtd/nand/raw/lpc32xx_mlc.c b/drivers/mtd/nand/raw/lpc32xx_mlc.c
index 7521038af2ef..4940bb2e3c07 100644
--- a/drivers/mtd/nand/raw/lpc32xx_mlc.c
+++ b/drivers/mtd/nand/raw/lpc32xx_mlc.c
@@ -656,7 +656,7 @@ static int lpc32xx_nand_attach_chip(struct nand_chip *chip)
 	if (!host->dummy_buf)
 		return -ENOMEM;
 
-	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	chip->ecc.size = 512;
 	mtd_set_ooblayout(mtd, &lpc32xx_ooblayout_ops);
 	host->mlcsubpages = mtd->writesize / 512;
diff --git a/drivers/mtd/nand/raw/lpc32xx_slc.c b/drivers/mtd/nand/raw/lpc32xx_slc.c
index ccb189c8e343..6db9d2ed6881 100644
--- a/drivers/mtd/nand/raw/lpc32xx_slc.c
+++ b/drivers/mtd/nand/raw/lpc32xx_slc.c
@@ -881,7 +881,7 @@ static int lpc32xx_nand_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, host);
 
 	/* NAND callbacks for LPC32xx SLC hardware */
-	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	chip->ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED;
 	chip->legacy.read_byte = lpc32xx_nand_read_byte;
 	chip->legacy.read_buf = lpc32xx_nand_read_buf;
diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c
index b2200aa787f2..88f8ed051226 100644
--- a/drivers/mtd/nand/raw/marvell_nand.c
+++ b/drivers/mtd/nand/raw/marvell_nand.c
@@ -2250,7 +2250,8 @@ static int marvell_nand_ecc_init(struct mtd_info *mtd,
 	struct marvell_nfc *nfc = to_marvell_nfc(chip->controller);
 	int ret;
 
-	if (ecc->mode != NAND_ECC_NONE && (!ecc->size || !ecc->strength)) {
+	if (ecc->engine_type != NAND_ECC_ENGINE_TYPE_NONE &&
+	    (!ecc->size || !ecc->strength)) {
 		if (chip->base.eccreq.step_size && chip->base.eccreq.strength) {
 			ecc->size = chip->base.eccreq.step_size;
 			ecc->strength = chip->base.eccreq.strength;
@@ -2262,15 +2263,15 @@ static int marvell_nand_ecc_init(struct mtd_info *mtd,
 		}
 	}
 
-	switch (ecc->mode) {
-	case NAND_ECC_HW:
+	switch (ecc->engine_type) {
+	case NAND_ECC_ENGINE_TYPE_ON_HOST:
 		ret = marvell_nand_hw_ecc_controller_init(mtd, ecc);
 		if (ret)
 			return ret;
 		break;
-	case NAND_ECC_NONE:
-	case NAND_ECC_SOFT:
-	case NAND_ECC_ON_DIE:
+	case NAND_ECC_ENGINE_TYPE_NONE:
+	case NAND_ECC_ENGINE_TYPE_SOFT:
+	case NAND_ECC_ENGINE_TYPE_ON_DIE:
 		if (!nfc->caps->is_nfcv2 && mtd->writesize != SZ_512 &&
 		    mtd->writesize != SZ_2K) {
 			dev_err(nfc->dev, "NFCv1 cannot write %d bytes pages\n",
@@ -2467,7 +2468,7 @@ static int marvell_nand_attach_chip(struct nand_chip *chip)
 		return ret;
 	}
 
-	if (chip->ecc.mode == NAND_ECC_HW) {
+	if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_ON_HOST) {
 		/*
 		 * Subpage write not available with hardware ECC, prohibit also
 		 * subpage read as in userspace subpage access would still be
@@ -2642,7 +2643,7 @@ static int marvell_nand_chip_init(struct device *dev, struct marvell_nfc *nfc,
 	 * Default to HW ECC engine mode. If the nand-ecc-mode property is given
 	 * in the DT node, this entry will be overwritten in nand_scan_ident().
 	 */
-	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 
 	/*
 	 * Save a reference value for timing registers before
diff --git a/drivers/mtd/nand/raw/meson_nand.c b/drivers/mtd/nand/raw/meson_nand.c
index 0e5829a2b54f..48e6dac96be6 100644
--- a/drivers/mtd/nand/raw/meson_nand.c
+++ b/drivers/mtd/nand/raw/meson_nand.c
@@ -1197,7 +1197,7 @@ static int meson_nand_attach_chip(struct nand_chip *nand)
 	if (ret)
 		return -EINVAL;
 
-	nand->ecc.mode = NAND_ECC_HW;
+	nand->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	nand->ecc.write_page_raw = meson_nfc_write_page_raw;
 	nand->ecc.write_page = meson_nfc_write_page_hwecc;
 	nand->ecc.write_oob_raw = nand_write_oob_std;
diff --git a/drivers/mtd/nand/raw/mpc5121_nfc.c b/drivers/mtd/nand/raw/mpc5121_nfc.c
index a67eded226db..dfd0d3ed5ed0 100644
--- a/drivers/mtd/nand/raw/mpc5121_nfc.c
+++ b/drivers/mtd/nand/raw/mpc5121_nfc.c
@@ -688,7 +688,7 @@ static int mpc5121_nfc_probe(struct platform_device *op)
 	chip->legacy.set_features = nand_get_set_features_notsupp;
 	chip->legacy.get_features = nand_get_set_features_notsupp;
 	chip->bbt_options = NAND_BBT_USE_FLASH;
-	chip->ecc.mode = NAND_ECC_SOFT;
+	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 	chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
 
 	/* Support external chip-select logic on ADS5121 board */
diff --git a/drivers/mtd/nand/raw/mtk_nand.c b/drivers/mtd/nand/raw/mtk_nand.c
index ad1b55dab211..42966fe22d8b 100644
--- a/drivers/mtd/nand/raw/mtk_nand.c
+++ b/drivers/mtd/nand/raw/mtk_nand.c
@@ -1258,8 +1258,8 @@ static int mtk_nfc_ecc_init(struct device *dev, struct mtd_info *mtd)
 	int free, ret;
 
 	/* support only ecc hw mode */
-	if (nand->ecc.mode != NAND_ECC_HW) {
-		dev_err(dev, "ecc.mode not supported\n");
+	if (nand->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST) {
+		dev_err(dev, "ecc.engine_type not supported\n");
 		return -EINVAL;
 	}
 
@@ -1416,7 +1416,7 @@ static int mtk_nfc_nand_chip_init(struct device *dev, struct mtk_nfc *nfc,
 	nand->options |= NAND_USES_DMA | NAND_SUBPAGE_READ;
 
 	/* set default mode in case dt entry is missing */
-	nand->ecc.mode = NAND_ECC_HW;
+	nand->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 
 	nand->ecc.write_subpage = mtk_nfc_write_subpage_hwecc;
 	nand->ecc.write_page_raw = mtk_nfc_write_page_raw;
diff --git a/drivers/mtd/nand/raw/mxc_nand.c b/drivers/mtd/nand/raw/mxc_nand.c
index 65448fb223b8..d4200eb2ad32 100644
--- a/drivers/mtd/nand/raw/mxc_nand.c
+++ b/drivers/mtd/nand/raw/mxc_nand.c
@@ -669,7 +669,7 @@ static void mxc_nand_enable_hwecc_v1_v2(struct nand_chip *chip, bool enable)
 	struct mxc_nand_host *host = nand_get_controller_data(chip);
 	uint16_t config1;
 
-	if (chip->ecc.mode != NAND_ECC_HW)
+	if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST)
 		return;
 
 	config1 = readw(NFC_V1_V2_CONFIG1);
@@ -687,7 +687,7 @@ static void mxc_nand_enable_hwecc_v3(struct nand_chip *chip, bool enable)
 	struct mxc_nand_host *host = nand_get_controller_data(chip);
 	uint32_t config2;
 
-	if (chip->ecc.mode != NAND_ECC_HW)
+	if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST)
 		return;
 
 	config2 = readl(NFC_V3_CONFIG2);
@@ -1117,7 +1117,8 @@ static void preset_v1(struct mtd_info *mtd)
 	struct mxc_nand_host *host = nand_get_controller_data(nand_chip);
 	uint16_t config1 = 0;
 
-	if (nand_chip->ecc.mode == NAND_ECC_HW && mtd->writesize)
+	if (nand_chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_ON_HOST &&
+	    mtd->writesize)
 		config1 |= NFC_V1_V2_CONFIG1_ECC_EN;
 
 	if (!host->devtype_data->irqpending_quirk)
@@ -1227,7 +1228,7 @@ static void preset_v2(struct mtd_info *mtd)
 	if (mtd->writesize) {
 		uint16_t pages_per_block = mtd->erasesize / mtd->writesize;
 
-		if (nand_chip->ecc.mode == NAND_ECC_HW)
+		if (nand_chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_ON_HOST)
 			config1 |= NFC_V1_V2_CONFIG1_ECC_EN;
 
 		host->eccsize = get_eccsize(mtd);
@@ -1303,7 +1304,7 @@ static void preset_v3(struct mtd_info *mtd)
 	}
 
 	if (mtd->writesize) {
-		if (chip->ecc.mode == NAND_ECC_HW)
+		if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_ON_HOST)
 			config2 |= NFC_V3_CONFIG2_ECC_EN;
 
 		config2 |= NFC_V3_CONFIG2_PPB(
@@ -1680,8 +1681,8 @@ static int mxcnd_attach_chip(struct nand_chip *chip)
 	struct mxc_nand_host *host = nand_get_controller_data(chip);
 	struct device *dev = mtd->dev.parent;
 
-	switch (chip->ecc.mode) {
-	case NAND_ECC_HW:
+	switch (chip->ecc.engine_type) {
+	case NAND_ECC_ENGINE_TYPE_ON_HOST:
 		chip->ecc.read_page = mxc_nand_read_page;
 		chip->ecc.read_page_raw = mxc_nand_read_page_raw;
 		chip->ecc.read_oob = mxc_nand_read_oob;
@@ -1690,7 +1691,7 @@ static int mxcnd_attach_chip(struct nand_chip *chip)
 		chip->ecc.write_oob = mxc_nand_write_oob;
 		break;
 
-	case NAND_ECC_SOFT:
+	case NAND_ECC_ENGINE_TYPE_SOFT:
 		break;
 
 	default:
@@ -1728,7 +1729,7 @@ static int mxcnd_attach_chip(struct nand_chip *chip)
 	 */
 	host->used_oobsize = min(mtd->oobsize, 218U);
 
-	if (chip->ecc.mode == NAND_ECC_HW) {
+	if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_ON_HOST) {
 		if (is_imx21_nfc(host) || is_imx27_nfc(host))
 			chip->ecc.strength = 1;
 		else
@@ -1843,9 +1844,9 @@ static int mxcnd_probe(struct platform_device *pdev)
 	mtd_set_ooblayout(mtd, host->devtype_data->ooblayout);
 
 	if (host->pdata.hw_ecc) {
-		this->ecc.mode = NAND_ECC_HW;
+		this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	} else {
-		this->ecc.mode = NAND_ECC_SOFT;
+		this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 		this->ecc.algo = NAND_ECC_ALGO_HAMMING;
 	}
 
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 172852a29a50..4b406b0f783c 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -5041,28 +5041,45 @@ static const char * const nand_ecc_modes[] = {
 	[NAND_ECC_ON_DIE]	= "on-die",
 };
 
-static int of_get_nand_ecc_mode(struct device_node *np)
+static enum nand_ecc_engine_type
+of_get_nand_ecc_engine_type(struct device_node *np)
 {
+	enum nand_ecc_mode eng_type;
 	const char *pm;
-	int err, i;
+	int err;
 
 	err = of_property_read_string(np, "nand-ecc-mode", &pm);
-	if (err < 0)
-		return err;
-
-	for (i = NAND_ECC_NONE; i < ARRAY_SIZE(nand_ecc_modes); i++)
-		if (!strcasecmp(pm, nand_ecc_modes[i]))
-			return i;
+	if (err)
+		return NAND_ECC_ENGINE_TYPE_INVALID;
+
+	for (eng_type = NAND_ECC_NONE;
+	     eng_type < ARRAY_SIZE(nand_ecc_modes); eng_type++) {
+		if (!strcasecmp(pm, nand_ecc_modes[eng_type])) {
+			switch (eng_type) {
+			case NAND_ECC_NONE:
+				return NAND_ECC_ENGINE_TYPE_NONE;
+			case NAND_ECC_SOFT:
+				return NAND_ECC_ENGINE_TYPE_SOFT;
+			case NAND_ECC_HW:
+			case NAND_ECC_HW_SYNDROME:
+				return NAND_ECC_ENGINE_TYPE_ON_HOST;
+			case NAND_ECC_ON_DIE:
+				return NAND_ECC_ENGINE_TYPE_ON_DIE;
+			default:
+				break;
+			}
+		}
+	}
 
 	/*
 	 * For backward compatibility we support few obsoleted values that don't
-	 * have their mappings into the nand_ecc_mode enum anymore (they were
-	 * merged with other enums).
+	 * have their mappings into the nand_ecc_engine_providers enum anymore
+	 * (they were merged with other enums).
 	 */
 	if (!strcasecmp(pm, "soft_bch"))
-		return NAND_ECC_SOFT;
+		return NAND_ECC_ENGINE_TYPE_SOFT;
 
-	return -ENODEV;
+	return NAND_ECC_ENGINE_TYPE_INVALID;
 }
 
 static const char * const nand_ecc_algos[] = {
@@ -5144,8 +5161,9 @@ static bool of_get_nand_on_flash_bbt(struct device_node *np)
 static int nand_dt_init(struct nand_chip *chip)
 {
 	struct device_node *dn = nand_get_flash_node(chip);
+	enum nand_ecc_engine_type ecc_type;
 	enum nand_ecc_algo ecc_algo;
-	int ecc_mode, ecc_strength, ecc_step;
+	int ecc_strength, ecc_step;
 
 	if (!dn)
 		return 0;
@@ -5159,13 +5177,13 @@ static int nand_dt_init(struct nand_chip *chip)
 	if (of_get_nand_on_flash_bbt(dn))
 		chip->bbt_options |= NAND_BBT_USE_FLASH;
 
-	ecc_mode = of_get_nand_ecc_mode(dn);
+	ecc_type = of_get_nand_ecc_engine_type(dn);
 	ecc_algo = of_get_nand_ecc_algo(dn);
 	ecc_strength = of_get_nand_ecc_strength(dn);
 	ecc_step = of_get_nand_ecc_step_size(dn);
 
-	if (ecc_mode >= 0)
-		chip->ecc.mode = ecc_mode;
+	if (ecc_type != NAND_ECC_ENGINE_TYPE_INVALID)
+		chip->ecc.engine_type = ecc_type;
 
 	if (ecc_algo != NAND_ECC_ALGO_UNKNOWN)
 		chip->ecc.algo = ecc_algo;
@@ -5287,7 +5305,7 @@ static int nand_set_ecc_soft_ops(struct nand_chip *chip)
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
 
-	if (WARN_ON(ecc->mode != NAND_ECC_SOFT))
+	if (WARN_ON(ecc->engine_type != NAND_ECC_ENGINE_TYPE_SOFT))
 		return -EINVAL;
 
 	switch (ecc->algo) {
@@ -5752,7 +5770,8 @@ static int nand_scan_tail(struct nand_chip *chip)
 	 * If no default placement scheme is given, select an appropriate one.
 	 */
 	if (!mtd->ooblayout &&
-	    !(ecc->mode == NAND_ECC_SOFT && ecc->algo == NAND_ECC_ALGO_BCH)) {
+	    !(ecc->engine_type == NAND_ECC_ENGINE_TYPE_SOFT &&
+	      ecc->algo == NAND_ECC_ALGO_BCH)) {
 		switch (mtd->oobsize) {
 		case 8:
 		case 16:
@@ -5770,7 +5789,7 @@ static int nand_scan_tail(struct nand_chip *chip)
 			 * page with ECC layout when ->oobsize <= 128 for
 			 * compatibility reasons.
 			 */
-			if (ecc->mode == NAND_ECC_NONE) {
+			if (ecc->engine_type == NAND_ECC_ENGINE_TYPE_NONE) {
 				mtd_set_ooblayout(mtd,
 						&nand_ooblayout_lp_ops);
 				break;
@@ -5788,8 +5807,9 @@ static int nand_scan_tail(struct nand_chip *chip)
 	 * selected and we have 256 byte pagesize fallback to software ECC
 	 */
 
-	switch (ecc->mode) {
-	case NAND_ECC_HW:
+	switch (ecc->engine_type) {
+	case NAND_ECC_ENGINE_TYPE_ON_HOST:
+
 		switch (ecc->placement) {
 		case NAND_ECC_PLACEMENT_UNKNOWN:
 		case NAND_ECC_PLACEMENT_OOB:
@@ -5854,11 +5874,11 @@ static int nand_scan_tail(struct nand_chip *chip)
 		}
 		pr_warn("%d byte HW ECC not possible on %d byte page size, fallback to SW ECC\n",
 			ecc->size, mtd->writesize);
-		ecc->mode = NAND_ECC_SOFT;
+		ecc->engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 		ecc->algo = NAND_ECC_ALGO_HAMMING;
 		fallthrough;
 
-	case NAND_ECC_SOFT:
+	case NAND_ECC_ENGINE_TYPE_SOFT:
 		ret = nand_set_ecc_soft_ops(chip);
 		if (ret) {
 			ret = -EINVAL;
@@ -5866,7 +5886,7 @@ static int nand_scan_tail(struct nand_chip *chip)
 		}
 		break;
 
-	case NAND_ECC_ON_DIE:
+	case NAND_ECC_ENGINE_TYPE_ON_DIE:
 		if (!ecc->read_page || !ecc->write_page) {
 			WARN(1, "No ECC functions supplied; on-die ECC not possible\n");
 			ret = -EINVAL;
@@ -5878,8 +5898,8 @@ static int nand_scan_tail(struct nand_chip *chip)
 			ecc->write_oob = nand_write_oob_std;
 		break;
 
-	case NAND_ECC_NONE:
-		pr_warn("NAND_ECC_NONE selected by board driver. This is not recommended!\n");
+	case NAND_ECC_ENGINE_TYPE_NONE:
+		pr_warn("NAND_ECC_ENGINE_TYPE_NONE selected by board driver. This is not recommended!\n");
 		ecc->read_page = nand_read_page_raw;
 		ecc->write_page = nand_write_page_raw;
 		ecc->read_oob = nand_read_oob_std;
@@ -5892,7 +5912,7 @@ static int nand_scan_tail(struct nand_chip *chip)
 		break;
 
 	default:
-		WARN(1, "Invalid NAND_ECC_MODE %d\n", ecc->mode);
+		WARN(1, "Invalid NAND_ECC_MODE %d\n", ecc->engine_type);
 		ret = -EINVAL;
 		goto err_nand_manuf_cleanup;
 	}
@@ -5969,8 +5989,8 @@ static int nand_scan_tail(struct nand_chip *chip)
 	chip->pagecache.page = -1;
 
 	/* Large page NAND with SOFT_ECC should support subpage reads */
-	switch (ecc->mode) {
-	case NAND_ECC_SOFT:
+	switch (ecc->engine_type) {
+	case NAND_ECC_ENGINE_TYPE_SOFT:
 		if (chip->page_shift > 9)
 			chip->options |= NAND_SUBPAGE_READ;
 		break;
@@ -6114,7 +6134,7 @@ EXPORT_SYMBOL(nand_scan_with_ids);
  */
 void nand_cleanup(struct nand_chip *chip)
 {
-	if (chip->ecc.mode == NAND_ECC_SOFT &&
+	if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_SOFT &&
 	    chip->ecc.algo == NAND_ECC_ALGO_BCH)
 		nand_bch_free((struct nand_bch_control *)chip->ecc.priv);
 
diff --git a/drivers/mtd/nand/raw/nand_micron.c b/drivers/mtd/nand/raw/nand_micron.c
index 2d54a3aa15b1..c43afaf21482 100644
--- a/drivers/mtd/nand/raw/nand_micron.c
+++ b/drivers/mtd/nand/raw/nand_micron.c
@@ -497,13 +497,13 @@ static int micron_nand_init(struct nand_chip *chip)
 	ondie = micron_supports_on_die_ecc(chip);
 
 	if (ondie == MICRON_ON_DIE_MANDATORY &&
-	    chip->ecc.mode != NAND_ECC_ON_DIE) {
+	    chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_DIE) {
 		pr_err("On-die ECC forcefully enabled, not supported\n");
 		ret = -EINVAL;
 		goto err_free_manuf_data;
 	}
 
-	if (chip->ecc.mode == NAND_ECC_ON_DIE) {
+	if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_ON_DIE) {
 		if (ondie == MICRON_ON_DIE_UNSUPPORTED) {
 			pr_err("On-die ECC selected but not supported\n");
 			ret = -EINVAL;
diff --git a/drivers/mtd/nand/raw/nand_toshiba.c b/drivers/mtd/nand/raw/nand_toshiba.c
index f746c19f3b2c..7ba0516c6247 100644
--- a/drivers/mtd/nand/raw/nand_toshiba.c
+++ b/drivers/mtd/nand/raw/nand_toshiba.c
@@ -273,7 +273,8 @@ static int toshiba_nand_init(struct nand_chip *chip)
 		chip->options |= NAND_BBM_FIRSTPAGE | NAND_BBM_SECONDPAGE;
 
 	/* Check that chip is BENAND and ECC mode is on-die */
-	if (nand_is_slc(chip) && chip->ecc.mode == NAND_ECC_ON_DIE &&
+	if (nand_is_slc(chip) &&
+	    chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_ON_DIE &&
 	    chip->id.data[4] & TOSHIBA_NAND_ID4_IS_BENAND)
 		toshiba_nand_benand_init(chip);
 
diff --git a/drivers/mtd/nand/raw/nandsim.c b/drivers/mtd/nand/raw/nandsim.c
index 1ab849ccaa96..a8048cb8d220 100644
--- a/drivers/mtd/nand/raw/nandsim.c
+++ b/drivers/mtd/nand/raw/nandsim.c
@@ -2234,7 +2234,7 @@ static int ns_attach_chip(struct nand_chip *chip)
 		return -EINVAL;
 	}
 
-	chip->ecc.mode = NAND_ECC_SOFT;
+	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 	chip->ecc.algo = NAND_ECC_ALGO_BCH;
 	chip->ecc.size = 512;
 	chip->ecc.strength = bch;
@@ -2274,7 +2274,7 @@ static int __init ns_init_module(void)
 	nsmtd       = nand_to_mtd(chip);
 	nand_set_controller_data(chip, (void *)ns);
 
-	chip->ecc.mode   = NAND_ECC_SOFT;
+	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 	chip->ecc.algo   = NAND_ECC_ALGO_HAMMING;
 	/* The NAND_SKIP_BBTSCAN option is necessary for 'overridesize' */
 	/* and 'badblocks' parameters to work */
diff --git a/drivers/mtd/nand/raw/ndfc.c b/drivers/mtd/nand/raw/ndfc.c
index ed38338c1383..0fb4ba93c41e 100644
--- a/drivers/mtd/nand/raw/ndfc.c
+++ b/drivers/mtd/nand/raw/ndfc.c
@@ -149,7 +149,7 @@ static int ndfc_chip_init(struct ndfc_controller *ndfc,
 	chip->ecc.correct = nand_correct_data;
 	chip->ecc.hwctl = ndfc_enable_hwecc;
 	chip->ecc.calculate = ndfc_calculate_ecc;
-	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	chip->ecc.size = 256;
 	chip->ecc.bytes = 3;
 	chip->ecc.strength = 1;
diff --git a/drivers/mtd/nand/raw/omap2.c b/drivers/mtd/nand/raw/omap2.c
index 967ddbda1c48..512f60780a50 100644
--- a/drivers/mtd/nand/raw/omap2.c
+++ b/drivers/mtd/nand/raw/omap2.c
@@ -884,8 +884,8 @@ static int omap_correct_data(struct nand_chip *chip, u_char *dat,
 	int stat = 0;
 
 	/* Ex NAND_ECC_HW12_2048 */
-	if ((info->nand.ecc.mode == NAND_ECC_HW) &&
-			(info->nand.ecc.size  == 2048))
+	if (info->nand.ecc.engine_type == NAND_ECC_ENGINE_TYPE_ON_HOST &&
+	    info->nand.ecc.size == 2048)
 		blockCnt = 4;
 	else
 		blockCnt = 1;
@@ -2006,11 +2006,11 @@ static int omap_nand_attach_chip(struct nand_chip *chip)
 		return -EINVAL;
 
 	/*
-	 * Bail out earlier to let NAND_ECC_SOFT code create its own
+	 * Bail out earlier to let NAND_ECC_ENGINE_TYPE_SOFT code create its own
 	 * ooblayout instead of using ours.
 	 */
 	if (info->ecc_opt == OMAP_ECC_HAM1_CODE_SW) {
-		chip->ecc.mode = NAND_ECC_SOFT;
+		chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 		chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
 		return 0;
 	}
@@ -2019,7 +2019,7 @@ static int omap_nand_attach_chip(struct nand_chip *chip)
 	switch (info->ecc_opt) {
 	case OMAP_ECC_HAM1_CODE_HW:
 		dev_info(dev, "nand: using OMAP_ECC_HAM1_CODE_HW\n");
-		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.engine_type	= NAND_ECC_ENGINE_TYPE_ON_HOST;
 		chip->ecc.bytes		= 3;
 		chip->ecc.size		= 512;
 		chip->ecc.strength	= 1;
@@ -2036,7 +2036,7 @@ static int omap_nand_attach_chip(struct nand_chip *chip)
 
 	case OMAP_ECC_BCH4_CODE_HW_DETECTION_SW:
 		pr_info("nand: using OMAP_ECC_BCH4_CODE_HW_DETECTION_SW\n");
-		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.engine_type	= NAND_ECC_ENGINE_TYPE_ON_HOST;
 		chip->ecc.size		= 512;
 		chip->ecc.bytes		= 7;
 		chip->ecc.strength	= 4;
@@ -2056,7 +2056,7 @@ static int omap_nand_attach_chip(struct nand_chip *chip)
 
 	case OMAP_ECC_BCH4_CODE_HW:
 		pr_info("nand: using OMAP_ECC_BCH4_CODE_HW ECC scheme\n");
-		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.engine_type	= NAND_ECC_ENGINE_TYPE_ON_HOST;
 		chip->ecc.size		= 512;
 		/* 14th bit is kept reserved for ROM-code compatibility */
 		chip->ecc.bytes		= 7 + 1;
@@ -2078,7 +2078,7 @@ static int omap_nand_attach_chip(struct nand_chip *chip)
 
 	case OMAP_ECC_BCH8_CODE_HW_DETECTION_SW:
 		pr_info("nand: using OMAP_ECC_BCH8_CODE_HW_DETECTION_SW\n");
-		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.engine_type	= NAND_ECC_ENGINE_TYPE_ON_HOST;
 		chip->ecc.size		= 512;
 		chip->ecc.bytes		= 13;
 		chip->ecc.strength	= 8;
@@ -2098,7 +2098,7 @@ static int omap_nand_attach_chip(struct nand_chip *chip)
 
 	case OMAP_ECC_BCH8_CODE_HW:
 		pr_info("nand: using OMAP_ECC_BCH8_CODE_HW ECC scheme\n");
-		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.engine_type	= NAND_ECC_ENGINE_TYPE_ON_HOST;
 		chip->ecc.size		= 512;
 		/* 14th bit is kept reserved for ROM-code compatibility */
 		chip->ecc.bytes		= 13 + 1;
@@ -2121,7 +2121,7 @@ static int omap_nand_attach_chip(struct nand_chip *chip)
 
 	case OMAP_ECC_BCH16_CODE_HW:
 		pr_info("Using OMAP_ECC_BCH16_CODE_HW ECC scheme\n");
-		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.engine_type	= NAND_ECC_ENGINE_TYPE_ON_HOST;
 		chip->ecc.size		= 512;
 		chip->ecc.bytes		= 26;
 		chip->ecc.strength	= 16;
diff --git a/drivers/mtd/nand/raw/orion_nand.c b/drivers/mtd/nand/raw/orion_nand.c
index 7a5cfa3d883f..df9c0f8e4b4e 100644
--- a/drivers/mtd/nand/raw/orion_nand.c
+++ b/drivers/mtd/nand/raw/orion_nand.c
@@ -139,7 +139,7 @@ static int __init orion_nand_probe(struct platform_device *pdev)
 	nc->legacy.IO_ADDR_R = nc->legacy.IO_ADDR_W = io_base;
 	nc->legacy.cmd_ctrl = orion_nand_cmd_ctrl;
 	nc->legacy.read_buf = orion_nand_read_buf;
-	nc->ecc.mode = NAND_ECC_SOFT;
+	nc->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 	nc->ecc.algo = NAND_ECC_ALGO_HAMMING;
 
 	if (board->chip_delay)
diff --git a/drivers/mtd/nand/raw/pasemi_nand.c b/drivers/mtd/nand/raw/pasemi_nand.c
index 3eddc284614d..155e8c8f61e2 100644
--- a/drivers/mtd/nand/raw/pasemi_nand.c
+++ b/drivers/mtd/nand/raw/pasemi_nand.c
@@ -132,7 +132,7 @@ static int pasemi_nand_probe(struct platform_device *ofdev)
 	chip->legacy.read_buf = pasemi_read_buf;
 	chip->legacy.write_buf = pasemi_write_buf;
 	chip->legacy.chip_delay = 0;
-	chip->ecc.mode = NAND_ECC_SOFT;
+	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 	chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
 
 	/* Enable the following for a flash based bad block table */
diff --git a/drivers/mtd/nand/raw/plat_nand.c b/drivers/mtd/nand/raw/plat_nand.c
index dbc089c8872f..b98c0d5c413f 100644
--- a/drivers/mtd/nand/raw/plat_nand.c
+++ b/drivers/mtd/nand/raw/plat_nand.c
@@ -66,7 +66,7 @@ static int plat_nand_probe(struct platform_device *pdev)
 	data->chip.options |= pdata->chip.options;
 	data->chip.bbt_options |= pdata->chip.bbt_options;
 
-	data->chip.ecc.mode = NAND_ECC_SOFT;
+	data->chip.ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 	data->chip.ecc.algo = NAND_ECC_ALGO_HAMMING;
 
 	platform_set_drvdata(pdev, data);
diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c
index bd7a7251429b..3d616e616b26 100644
--- a/drivers/mtd/nand/raw/qcom_nandc.c
+++ b/drivers/mtd/nand/raw/qcom_nandc.c
@@ -2550,7 +2550,7 @@ static int qcom_nand_attach_chip(struct nand_chip *chip)
 	ecc->write_page_raw	= qcom_nandc_write_page_raw;
 	ecc->write_oob		= qcom_nandc_write_oob;
 
-	ecc->mode = NAND_ECC_HW;
+	ecc->engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 
 	mtd_set_ooblayout(mtd, &qcom_nand_ooblayout_ops);
 
diff --git a/drivers/mtd/nand/raw/r852.c b/drivers/mtd/nand/raw/r852.c
index f0988cda4479..6b7addd2c420 100644
--- a/drivers/mtd/nand/raw/r852.c
+++ b/drivers/mtd/nand/raw/r852.c
@@ -859,7 +859,7 @@ static int  r852_probe(struct pci_dev *pci_dev, const struct pci_device_id *id)
 	chip->legacy.write_buf = r852_write_buf;
 
 	/* ecc */
-	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	chip->ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED;
 	chip->ecc.size = R852_DMA_LEN;
 	chip->ecc.bytes = SM_OOB_SIZE;
diff --git a/drivers/mtd/nand/raw/s3c2410.c b/drivers/mtd/nand/raw/s3c2410.c
index 5a39002d67ef..fbd0fa48e063 100644
--- a/drivers/mtd/nand/raw/s3c2410.c
+++ b/drivers/mtd/nand/raw/s3c2410.c
@@ -904,7 +904,7 @@ static void s3c2410_nand_init_chip(struct s3c2410_nand_info *info,
 	nmtd->info	   = info;
 	nmtd->set	   = set;
 
-	chip->ecc.mode = info->platform->ecc_mode;
+	chip->ecc.engine_type = info->platform->engine_type;
 
 	/*
 	 * If you use u-boot BBT creation code, specifying this flag will
@@ -929,24 +929,24 @@ static int s3c2410_nand_attach_chip(struct nand_chip *chip)
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct s3c2410_nand_info *info = s3c2410_nand_mtd_toinfo(mtd);
 
-	switch (chip->ecc.mode) {
+	switch (chip->ecc.engine_type) {
 
-	case NAND_ECC_NONE:
+	case NAND_ECC_ENGINE_TYPE_NONE:
 		dev_info(info->device, "ECC disabled\n");
 		break;
 
-	case NAND_ECC_SOFT:
+	case NAND_ECC_ENGINE_TYPE_SOFT:
 		/*
-		 * This driver expects Hamming based ECC when ecc_mode is set
-		 * to NAND_ECC_SOFT. Force ecc.algo to NAND_ECC_ALGO_HAMMING to
-		 * avoid adding an extra ecc_algo field to
-		 * s3c2410_platform_nand.
+		 * This driver expects Hamming based ECC when engine_type is set
+		 * to NAND_ECC_ENGINE_TYPE_SOFT. Force ecc.algo to
+		 * NAND_ECC_ALGO_HAMMING to avoid adding an extra ecc_algo field
+		 * to s3c2410_platform_nand.
 		 */
 		chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
 		dev_info(info->device, "soft ECC\n");
 		break;
 
-	case NAND_ECC_HW:
+	case NAND_ECC_ENGINE_TYPE_ON_HOST:
 		chip->ecc.calculate = s3c2410_nand_calculate_ecc;
 		chip->ecc.correct   = s3c2410_nand_correct_data;
 		chip->ecc.strength  = 1;
diff --git a/drivers/mtd/nand/raw/sh_flctl.c b/drivers/mtd/nand/raw/sh_flctl.c
index 9dbd6fdbe264..13df4bdf792a 100644
--- a/drivers/mtd/nand/raw/sh_flctl.c
+++ b/drivers/mtd/nand/raw/sh_flctl.c
@@ -1039,12 +1039,12 @@ static int flctl_chip_attach_chip(struct nand_chip *chip)
 		chip->ecc.strength = 4;
 		chip->ecc.read_page = flctl_read_page_hwecc;
 		chip->ecc.write_page = flctl_write_page_hwecc;
-		chip->ecc.mode = NAND_ECC_HW;
+		chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 
 		/* 4 symbols ECC enabled */
 		flctl->flcmncr_base |= _4ECCEN;
 	} else {
-		chip->ecc.mode = NAND_ECC_SOFT;
+		chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 		chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
 	}
 
diff --git a/drivers/mtd/nand/raw/sharpsl.c b/drivers/mtd/nand/raw/sharpsl.c
index 51286f7acf54..1327bfb3d5d3 100644
--- a/drivers/mtd/nand/raw/sharpsl.c
+++ b/drivers/mtd/nand/raw/sharpsl.c
@@ -157,7 +157,7 @@ static int sharpsl_nand_probe(struct platform_device *pdev)
 	/* 15 us command delay time */
 	this->legacy.chip_delay = 15;
 	/* set eccmode using hardware ECC */
-	this->ecc.mode = NAND_ECC_HW;
+	this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	this->ecc.size = 256;
 	this->ecc.bytes = 3;
 	this->ecc.strength = 1;
diff --git a/drivers/mtd/nand/raw/socrates_nand.c b/drivers/mtd/nand/raw/socrates_nand.c
index 72a3a7f98282..0f63ff6f7fe7 100644
--- a/drivers/mtd/nand/raw/socrates_nand.c
+++ b/drivers/mtd/nand/raw/socrates_nand.c
@@ -153,7 +153,8 @@ static int socrates_nand_probe(struct platform_device *ofdev)
 	nand_chip->legacy.read_buf = socrates_nand_read_buf;
 	nand_chip->legacy.dev_ready = socrates_nand_device_ready;
 
-	nand_chip->ecc.mode = NAND_ECC_SOFT;	/* enable ECC */
+	/* enable ECC */
+	nand_chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 	nand_chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
 
 	/* TODO: I have no idea what real delay is. */
diff --git a/drivers/mtd/nand/raw/stm32_fmc2_nand.c b/drivers/mtd/nand/raw/stm32_fmc2_nand.c
index 7f4546ae9130..ba679d2cc743 100644
--- a/drivers/mtd/nand/raw/stm32_fmc2_nand.c
+++ b/drivers/mtd/nand/raw/stm32_fmc2_nand.c
@@ -1696,14 +1696,15 @@ static int stm32_fmc2_nfc_attach_chip(struct nand_chip *chip)
 	int ret;
 
 	/*
-	 * Only NAND_ECC_HW mode is actually supported
+	 * Only NAND_ECC_ENGINE_TYPE_ON_HOST mode is actually supported
 	 * Hamming => ecc.strength = 1
 	 * BCH4 => ecc.strength = 4
 	 * BCH8 => ecc.strength = 8
 	 * ECC sector size = 512
 	 */
-	if (chip->ecc.mode != NAND_ECC_HW) {
-		dev_err(nfc->dev, "nand_ecc_mode is not well defined in the DT\n");
+	if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST) {
+		dev_err(nfc->dev,
+			"nand_ecc_engine_type is not well defined in the DT\n");
 		return -EINVAL;
 	}
 
@@ -1952,7 +1953,7 @@ static int stm32_fmc2_nfc_probe(struct platform_device *pdev)
 			 NAND_USES_DMA;
 
 	/* Default ECC settings */
-	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	chip->ecc.size = FMC2_ECC_STEP_SIZE;
 	chip->ecc.strength = FMC2_ECC_BCH8;
 
diff --git a/drivers/mtd/nand/raw/sunxi_nand.c b/drivers/mtd/nand/raw/sunxi_nand.c
index 9c50c2b965e1..c78276de7c37 100644
--- a/drivers/mtd/nand/raw/sunxi_nand.c
+++ b/drivers/mtd/nand/raw/sunxi_nand.c
@@ -1575,7 +1575,7 @@ static int sunxi_nand_ooblayout_free(struct mtd_info *mtd, int section,
 	 * only have 2 bytes available in the first user data
 	 * section.
 	 */
-	if (!section && ecc->mode == NAND_ECC_HW) {
+	if (!section && ecc->engine_type == NAND_ECC_ENGINE_TYPE_ON_HOST) {
 		oobregion->offset = 2;
 		oobregion->length = 2;
 
@@ -1720,11 +1720,11 @@ err:
 
 static void sunxi_nand_ecc_cleanup(struct nand_ecc_ctrl *ecc)
 {
-	switch (ecc->mode) {
-	case NAND_ECC_HW:
+	switch (ecc->engine_type) {
+	case NAND_ECC_ENGINE_TYPE_ON_HOST:
 		sunxi_nand_hw_ecc_ctrl_cleanup(ecc);
 		break;
-	case NAND_ECC_NONE:
+	case NAND_ECC_ENGINE_TYPE_NONE:
 	default:
 		break;
 	}
@@ -1752,14 +1752,14 @@ static int sunxi_nand_attach_chip(struct nand_chip *nand)
 	if (!ecc->size || !ecc->strength)
 		return -EINVAL;
 
-	switch (ecc->mode) {
-	case NAND_ECC_HW:
+	switch (ecc->engine_type) {
+	case NAND_ECC_ENGINE_TYPE_ON_HOST:
 		ret = sunxi_nand_hw_ecc_ctrl_init(nand, ecc, np);
 		if (ret)
 			return ret;
 		break;
-	case NAND_ECC_NONE:
-	case NAND_ECC_SOFT:
+	case NAND_ECC_ENGINE_TYPE_NONE:
+	case NAND_ECC_ENGINE_TYPE_SOFT:
 		break;
 	default:
 		return -EINVAL;
@@ -1991,7 +1991,7 @@ static int sunxi_nand_chip_init(struct device *dev, struct sunxi_nfc *nfc,
 	 * Set the ECC mode to the default value in case nothing is specified
 	 * in the DT.
 	 */
-	nand->ecc.mode = NAND_ECC_HW;
+	nand->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	nand_set_flash_node(nand, np);
 
 	mtd = nand_to_mtd(nand);
diff --git a/drivers/mtd/nand/raw/tango_nand.c b/drivers/mtd/nand/raw/tango_nand.c
index 021ceef4ad0a..359187b5a4be 100644
--- a/drivers/mtd/nand/raw/tango_nand.c
+++ b/drivers/mtd/nand/raw/tango_nand.c
@@ -549,7 +549,7 @@ static int tango_attach_chip(struct nand_chip *chip)
 {
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
 
-	ecc->mode = NAND_ECC_HW;
+	ecc->engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	ecc->algo = NAND_ECC_ALGO_BCH;
 	ecc->bytes = DIV_ROUND_UP(ecc->strength * FIELD_ORDER, BITS_PER_BYTE);
 
diff --git a/drivers/mtd/nand/raw/tegra_nand.c b/drivers/mtd/nand/raw/tegra_nand.c
index 0d6f3c6d6e11..cc72a2de8891 100644
--- a/drivers/mtd/nand/raw/tegra_nand.c
+++ b/drivers/mtd/nand/raw/tegra_nand.c
@@ -916,7 +916,7 @@ static int tegra_nand_attach_chip(struct nand_chip *chip)
 	if (chip->bbt_options & NAND_BBT_USE_FLASH)
 		chip->bbt_options |= NAND_BBT_NO_OOB;
 
-	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	chip->ecc.size = 512;
 	chip->ecc.steps = mtd->writesize / chip->ecc.size;
 	if (chip->base.eccreq.step_size != 512) {
diff --git a/drivers/mtd/nand/raw/tmio_nand.c b/drivers/mtd/nand/raw/tmio_nand.c
index 843a8683b737..235a2f7b1bad 100644
--- a/drivers/mtd/nand/raw/tmio_nand.c
+++ b/drivers/mtd/nand/raw/tmio_nand.c
@@ -410,7 +410,7 @@ static int tmio_probe(struct platform_device *dev)
 	nand_chip->legacy.read_buf = tmio_nand_read_buf;
 
 	/* set eccmode using hardware ECC */
-	nand_chip->ecc.mode = NAND_ECC_HW;
+	nand_chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	nand_chip->ecc.size = 512;
 	nand_chip->ecc.bytes = 6;
 	nand_chip->ecc.strength = 2;
diff --git a/drivers/mtd/nand/raw/txx9ndfmc.c b/drivers/mtd/nand/raw/txx9ndfmc.c
index 47d966871445..ef81dce6b5c4 100644
--- a/drivers/mtd/nand/raw/txx9ndfmc.c
+++ b/drivers/mtd/nand/raw/txx9ndfmc.c
@@ -329,7 +329,7 @@ static int __init txx9ndfmc_probe(struct platform_device *dev)
 		chip->ecc.calculate = txx9ndfmc_calculate_ecc;
 		chip->ecc.correct = txx9ndfmc_correct_data;
 		chip->ecc.hwctl = txx9ndfmc_enable_hwecc;
-		chip->ecc.mode = NAND_ECC_HW;
+		chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 		chip->ecc.strength = 1;
 		chip->legacy.chip_delay = 100;
 		chip->controller = &drvdata->controller;
diff --git a/drivers/mtd/nand/raw/vf610_nfc.c b/drivers/mtd/nand/raw/vf610_nfc.c
index 7248c5901183..8ee2c1f539c4 100644
--- a/drivers/mtd/nand/raw/vf610_nfc.c
+++ b/drivers/mtd/nand/raw/vf610_nfc.c
@@ -732,7 +732,7 @@ static void vf610_nfc_init_controller(struct vf610_nfc *nfc)
 	else
 		vf610_nfc_clear(nfc, NFC_FLASH_CONFIG, CONFIG_16BIT);
 
-	if (nfc->chip.ecc.mode == NAND_ECC_HW) {
+	if (nfc->chip.ecc.engine_type == NAND_ECC_ENGINE_TYPE_ON_HOST) {
 		/* Set ECC status offset in SRAM */
 		vf610_nfc_set_field(nfc, NFC_FLASH_CONFIG,
 				    CONFIG_ECC_SRAM_ADDR_MASK,
@@ -761,7 +761,7 @@ static int vf610_nfc_attach_chip(struct nand_chip *chip)
 		return -ENXIO;
 	}
 
-	if (chip->ecc.mode != NAND_ECC_HW)
+	if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST)
 		return 0;
 
 	if (mtd->writesize != PAGE_2K && mtd->oobsize < 64) {
diff --git a/drivers/mtd/nand/raw/xway_nand.c b/drivers/mtd/nand/raw/xway_nand.c
index b279ed143b8f..f2dbd63a5c1f 100644
--- a/drivers/mtd/nand/raw/xway_nand.c
+++ b/drivers/mtd/nand/raw/xway_nand.c
@@ -180,7 +180,7 @@ static int xway_nand_probe(struct platform_device *pdev)
 	data->chip.legacy.read_byte = xway_read_byte;
 	data->chip.legacy.chip_delay = 30;
 
-	data->chip.ecc.mode = NAND_ECC_SOFT;
+	data->chip.ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 	data->chip.ecc.algo = NAND_ECC_ALGO_HAMMING;
 
 	platform_set_drvdata(pdev, data);
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index cfd75a12f802..967b616c50df 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -303,7 +303,7 @@ static const struct nand_ecc_caps __name = {			\
 
 /**
  * struct nand_ecc_ctrl - Control structure for ECC
- * @mode:	ECC mode
+ * @engine_type: ECC engine type
  * @placement:	OOB bytes placement
  * @algo:	ECC algorithm
  * @steps:	number of ECC steps per page
@@ -356,7 +356,7 @@ static const struct nand_ecc_caps __name = {			\
  * @write_oob:	function to write chip OOB data
  */
 struct nand_ecc_ctrl {
-	enum nand_ecc_mode mode;
+	enum nand_ecc_engine_type engine_type;
 	enum nand_ecc_placement placement;
 	enum nand_ecc_algo algo;
 	int steps;
diff --git a/include/linux/platform_data/mtd-davinci.h b/include/linux/platform_data/mtd-davinci.h
index 6e2b252a4ce6..dd474dd44848 100644
--- a/include/linux/platform_data/mtd-davinci.h
+++ b/include/linux/platform_data/mtd-davinci.h
@@ -60,15 +60,15 @@ struct davinci_nand_pdata {		/* platform_data */
 	struct mtd_partition	*parts;
 	unsigned		nr_parts;
 
-	/* none  == NAND_ECC_NONE (strongly *not* advised!!)
-	 * soft  == NAND_ECC_SOFT
-	 * else  == NAND_ECC_HW, according to ecc_bits
+	/* none  == NAND_ECC_ENGINE_TYPE_NONE (strongly *not* advised!!)
+	 * soft  == NAND_ECC_ENGINE_TYPE_SOFT
+	 * else  == NAND_ECC_ENGINE_TYPE_ON_HOST, according to ecc_bits
 	 *
 	 * All DaVinci-family chips support 1-bit hardware ECC.
 	 * Newer ones also support 4-bit ECC, but are awkward
 	 * using it with large page chips.
 	 */
-	enum nand_ecc_mode	ecc_mode;
+	enum nand_ecc_engine_type engine_type;
 	enum nand_ecc_placement ecc_placement;
 	u8			ecc_bits;
 
diff --git a/include/linux/platform_data/mtd-nand-s3c2410.h b/include/linux/platform_data/mtd-nand-s3c2410.h
index 08675b16f9e1..25390fc3e795 100644
--- a/include/linux/platform_data/mtd-nand-s3c2410.h
+++ b/include/linux/platform_data/mtd-nand-s3c2410.h
@@ -49,7 +49,7 @@ struct s3c2410_platform_nand {
 
 	unsigned int	ignore_unset_ecc:1;
 
-	enum nand_ecc_mode	ecc_mode;
+	enum nand_ecc_engine_type engine_type;
 
 	int			nr_sets;
 	struct s3c2410_nand_set *sets;
-- 
cgit v1.2.3


From d193792a26c216cb7db3cf12300c9414990fa603 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Thu, 27 Aug 2020 10:51:59 +0200
Subject: mtd: nand: Create a helper to extract the ECC configuration

Despite its current name, the eccreq field actually encodes both the
NAND requirements and the final ECC configuration. That works fine when
using on-die ECC since those 2 concepts match perfectly, but it starts
being a problem as soon as we use on-host ECC engines, where we're not
guaranteed to have a perfect match.

Let's hide the ECC configuration access behind a helper so we can later
split those 2 concepts.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-12-miquel.raynal@bootlin.com
---
 include/linux/mtd/nand.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 8cf5bdbea782..9cbb41a5541c 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -523,6 +523,16 @@ nanddev_get_memorg(struct nand_device *nand)
 	return &nand->memorg;
 }
 
+/**
+ * nanddev_get_ecc_conf() - Extract the ECC configuration from a NAND device
+ * @nand: NAND device
+ */
+static inline const struct nand_ecc_props *
+nanddev_get_ecc_conf(struct nand_device *nand)
+{
+	return &nand->eccreq;
+}
+
 int nanddev_init(struct nand_device *nand, const struct nand_ops *ops,
 		 struct module *owner);
 void nanddev_cleanup(struct nand_device *nand);
-- 
cgit v1.2.3


From 3316c8e3ad1fcaeefd4ffa93587dd78fb24e8afa Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Thu, 27 Aug 2020 10:52:01 +0200
Subject: mtd: nand: Create helpers to set/extract the ECC requirements

Despite its current name, the eccreq field actually encodes both the
NAND requirements and the final ECC configuration. That works fine when
using on-die ECC since those 2 concepts match perfectly, but it starts
being a problem as soon as we use on-host ECC engines, where we're not
guaranteed to have a perfect match.

Let's hide the ECC requirements access behind helpers so we can later
split those 2 concepts. As the structures have not been clarified yet,
these helpers access the same internal variable as
nanddev_get_ecc_conf() for now.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-14-miquel.raynal@bootlin.com
---
 include/linux/mtd/nand.h | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 9cbb41a5541c..348fb2ad4d90 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -533,6 +533,30 @@ nanddev_get_ecc_conf(struct nand_device *nand)
 	return &nand->eccreq;
 }
 
+/**
+ * nanddev_get_ecc_requirements() - Extract the ECC requirements from a NAND
+ *                                  device
+ * @nand: NAND device
+ */
+static inline const struct nand_ecc_props *
+nanddev_get_ecc_requirements(struct nand_device *nand)
+{
+	return &nand->eccreq;
+}
+
+/**
+ * nanddev_set_ecc_requirements() - Assign the ECC requirements of a NAND
+ *                                  device
+ * @nand: NAND device
+ * @reqs: Requirements
+ */
+static inline void
+nanddev_set_ecc_requirements(struct nand_device *nand,
+			     const struct nand_ecc_props *reqs)
+{
+	nand->eccreq = *reqs;
+}
+
 int nanddev_init(struct nand_device *nand, const struct nand_ops *ops,
 		 struct module *owner);
 void nanddev_cleanup(struct nand_device *nand);
-- 
cgit v1.2.3


From 93ef92f6f42275e3d6070b1c5020bfca0e614fff Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Thu, 27 Aug 2020 10:52:03 +0200
Subject: mtd: nand: Use the new generic ECC object

Embed a generic NAND ECC high-level object in the nand_device
structure to carry all the ECC engine configuration/data.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-16-miquel.raynal@bootlin.com
---
 include/linux/mtd/nand.h | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 348fb2ad4d90..697ea2474a7c 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -301,7 +301,7 @@ struct nand_ecc {
  * struct nand_device - NAND device
  * @mtd: MTD instance attached to the NAND device
  * @memorg: memory layout
- * @eccreq: ECC requirements
+ * @ecc: NAND ECC object attached to the NAND device
  * @rowconv: position to row address converter
  * @bbt: bad block table info
  * @ops: NAND operations attached to the NAND device
@@ -309,8 +309,8 @@ struct nand_ecc {
  * Generic NAND object. Specialized NAND layers (raw NAND, SPI NAND, OneNAND)
  * should declare their own NAND object embedding a nand_device struct (that's
  * how inheritance is done).
- * struct_nand_device->memorg and struct_nand_device->eccreq should be filled
- * at device detection time to reflect the NAND device
+ * struct_nand_device->memorg and struct_nand_device->ecc.requirements should
+ * be filled at device detection time to reflect the NAND device
  * capabilities/requirements. Once this is done nanddev_init() can be called.
  * It will take care of converting NAND information into MTD ones, which means
  * the specialized NAND layers should never manually tweak
@@ -319,7 +319,7 @@ struct nand_ecc {
 struct nand_device {
 	struct mtd_info mtd;
 	struct nand_memory_organization memorg;
-	struct nand_ecc_props eccreq;
+	struct nand_ecc ecc;
 	struct nand_row_converter rowconv;
 	struct nand_bbt bbt;
 	const struct nand_ops *ops;
@@ -530,7 +530,7 @@ nanddev_get_memorg(struct nand_device *nand)
 static inline const struct nand_ecc_props *
 nanddev_get_ecc_conf(struct nand_device *nand)
 {
-	return &nand->eccreq;
+	return &nand->ecc.ctx.conf;
 }
 
 /**
@@ -541,7 +541,7 @@ nanddev_get_ecc_conf(struct nand_device *nand)
 static inline const struct nand_ecc_props *
 nanddev_get_ecc_requirements(struct nand_device *nand)
 {
-	return &nand->eccreq;
+	return &nand->ecc.requirements;
 }
 
 /**
@@ -554,7 +554,7 @@ static inline void
 nanddev_set_ecc_requirements(struct nand_device *nand,
 			     const struct nand_ecc_props *reqs)
 {
-	nand->eccreq = *reqs;
+	nand->ecc.requirements = *reqs;
 }
 
 int nanddev_init(struct nand_device *nand, const struct nand_ops *ops,
-- 
cgit v1.2.3


From 6b61d49a55796dbbc479eeb4465e59fd656c719c Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Fri, 18 Sep 2020 19:55:18 +0300
Subject: PM: runtime: Fix timer_expires data type on 32-bit arches

Commit 8234f6734c5d ("PM-runtime: Switch autosuspend over to using
hrtimers") switched PM runtime autosuspend to use hrtimers and all
related time accounting in ns, but missed to update the timer_expires
data type in struct dev_pm_info to u64.

This causes the timer_expires value to be truncated on 32-bit
architectures when assignment is done from u64 values:

rpm_suspend()
|- dev->power.timer_expires = expires;

Fix it by changing the timer_expires type to u64.

Fixes: 8234f6734c5d ("PM-runtime: Switch autosuspend over to using hrtimers")
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Acked-by: Pavel Machek <pavel@ucw.cz>
Acked-by: Vincent Guittot <vincent.guittot@linaro.org>
Cc: 5.0+ <stable@vger.kernel.org> # 5.0+
[ rjw: Subject and changelog edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/pm.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/pm.h b/include/linux/pm.h
index a30a4b54df52..47aca6bac1d6 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -590,7 +590,7 @@ struct dev_pm_info {
 #endif
 #ifdef CONFIG_PM
 	struct hrtimer		suspend_timer;
-	unsigned long		timer_expires;
+	u64			timer_expires;
 	struct work_struct	work;
 	wait_queue_head_t	wait_queue;
 	struct wake_irq		*wakeirq;
-- 
cgit v1.2.3


From c3d4ed1abecfcfc801199cfadb71f5b80e025d9e Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 28 Sep 2020 08:51:08 -0700
Subject: iomap: Allow filesystem to call iomap_dio_complete without i_rwsem

This is to avoid the deadlock caused in btrfs because of O_DIRECT |
O_DSYNC.

Filesystems such as btrfs require i_rwsem while performing sync on a
file. iomap_dio_rw() is called under i_rw_sem. This leads to a
deadlock because of:

iomap_dio_complete()
  generic_write_sync()
    btrfs_sync_file()

Separate out iomap_dio_complete() from iomap_dio_rw(), so filesystems
can call iomap_dio_complete() after unlocking i_rwsem.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/iomap/direct-io.c  | 35 ++++++++++++++++++++++++++---------
 include/linux/iomap.h |  5 +++++
 2 files changed, 31 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index 024d4bb3028e..b005ef5f554e 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -76,7 +76,7 @@ static void iomap_dio_submit_bio(struct iomap_dio *dio, struct iomap *iomap,
 		dio->submit.cookie = submit_bio(bio);
 }
 
-static ssize_t iomap_dio_complete(struct iomap_dio *dio)
+ssize_t iomap_dio_complete(struct iomap_dio *dio)
 {
 	const struct iomap_dio_ops *dops = dio->dops;
 	struct kiocb *iocb = dio->iocb;
@@ -130,6 +130,7 @@ static ssize_t iomap_dio_complete(struct iomap_dio *dio)
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(iomap_dio_complete);
 
 static void iomap_dio_complete_work(struct work_struct *work)
 {
@@ -416,8 +417,8 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
  * Returns -ENOTBLK In case of a page invalidation invalidation failure for
  * writes.  The callers needs to fall back to buffered I/O in this case.
  */
-ssize_t
-iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
+struct iomap_dio *
+__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
 		bool wait_for_completion)
 {
@@ -431,14 +432,14 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	struct iomap_dio *dio;
 
 	if (!count)
-		return 0;
+		return NULL;
 
 	if (WARN_ON(is_sync_kiocb(iocb) && !wait_for_completion))
-		return -EIO;
+		return ERR_PTR(-EIO);
 
 	dio = kmalloc(sizeof(*dio), GFP_KERNEL);
 	if (!dio)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	dio->iocb = iocb;
 	atomic_set(&dio->ref, 1);
@@ -568,7 +569,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	dio->wait_for_completion = wait_for_completion;
 	if (!atomic_dec_and_test(&dio->ref)) {
 		if (!wait_for_completion)
-			return -EIOCBQUEUED;
+			return ERR_PTR(-EIOCBQUEUED);
 
 		for (;;) {
 			set_current_state(TASK_UNINTERRUPTIBLE);
@@ -584,10 +585,26 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		__set_current_state(TASK_RUNNING);
 	}
 
-	return iomap_dio_complete(dio);
+	return dio;
 
 out_free_dio:
 	kfree(dio);
-	return ret;
+	if (ret)
+		return ERR_PTR(ret);
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(__iomap_dio_rw);
+
+ssize_t
+iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
+		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
+		bool wait_for_completion)
+{
+	struct iomap_dio *dio;
+
+	dio = __iomap_dio_rw(iocb, iter, ops, dops, wait_for_completion);
+	if (IS_ERR_OR_NULL(dio))
+		return PTR_ERR_OR_ZERO(dio);
+	return iomap_dio_complete(dio);
 }
 EXPORT_SYMBOL_GPL(iomap_dio_rw);
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 4d1d3c3469e9..172b3397a1a3 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -13,6 +13,7 @@
 struct address_space;
 struct fiemap_extent_info;
 struct inode;
+struct iomap_dio;
 struct iomap_writepage_ctx;
 struct iov_iter;
 struct kiocb;
@@ -258,6 +259,10 @@ struct iomap_dio_ops {
 ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
 		bool wait_for_completion);
+struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
+		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
+		bool wait_for_completion);
+ssize_t iomap_dio_complete(struct iomap_dio *dio);
 int iomap_dio_iopoll(struct kiocb *kiocb, bool spin);
 
 #ifdef CONFIG_SWAP
-- 
cgit v1.2.3


From b8127113d01e53adba15b41aefd37b90ed83d631 Mon Sep 17 00:00:00 2001
From: Kim Phillips <kim.phillips@arm.com>
Date: Mon, 28 Sep 2020 10:34:51 -0600
Subject: coresight: Use IS_ENABLED for CONFIGs that may be modules

Checking for ifdef CONFIG_x fails if CONFIG_x=m.  Use IS_ENABLED
that is true for both built-ins and modules, instead.  Required
when building coresight components as modules.

Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Suzuki K Poulose <Suzuki.Poulose@arm.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Russell King <linux@armlinux.org.uk>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Kim Phillips <kim.phillips@arm.com>
Signed-off-by: Tingwei Zhang <tingwei@codeaurora.org>
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Link: https://lore.kernel.org/r/20200928163513.70169-4-mathieu.poirier@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/hwtracing/coresight/coresight-etm-perf.h | 2 +-
 drivers/hwtracing/coresight/coresight-priv.h     | 2 +-
 include/linux/coresight.h                        | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.h b/drivers/hwtracing/coresight/coresight-etm-perf.h
index 015213abe00a..05f89723e282 100644
--- a/drivers/hwtracing/coresight/coresight-etm-perf.h
+++ b/drivers/hwtracing/coresight/coresight-etm-perf.h
@@ -57,7 +57,7 @@ struct etm_event_data {
 	struct list_head * __percpu *path;
 };
 
-#ifdef CONFIG_CORESIGHT
+#if IS_ENABLED(CONFIG_CORESIGHT)
 int etm_perf_symlink(struct coresight_device *csdev, bool link);
 int etm_perf_add_symlink_sink(struct coresight_device *csdev);
 void etm_perf_del_symlink_sink(struct coresight_device *csdev);
diff --git a/drivers/hwtracing/coresight/coresight-priv.h b/drivers/hwtracing/coresight/coresight-priv.h
index 5fe773c4d6cc..28695e26e5c6 100644
--- a/drivers/hwtracing/coresight/coresight-priv.h
+++ b/drivers/hwtracing/coresight/coresight-priv.h
@@ -166,7 +166,7 @@ int coresight_make_links(struct coresight_device *orig,
 void coresight_remove_links(struct coresight_device *orig,
 			    struct coresight_connection *conn);
 
-#ifdef CONFIG_CORESIGHT_SOURCE_ETM3X
+#if IS_ENABLED(CONFIG_CORESIGHT_SOURCE_ETM3X)
 extern int etm_readl_cp14(u32 off, unsigned int *val);
 extern int etm_writel_cp14(u32 off, u32 val);
 #else
diff --git a/include/linux/coresight.h b/include/linux/coresight.h
index 58fffdecdbfd..3bb738f9a326 100644
--- a/include/linux/coresight.h
+++ b/include/linux/coresight.h
@@ -324,7 +324,7 @@ struct coresight_ops {
 	const struct coresight_ops_ect *ect_ops;
 };
 
-#ifdef CONFIG_CORESIGHT
+#if IS_ENABLED(CONFIG_CORESIGHT)
 extern struct coresight_device *
 coresight_register(struct coresight_desc *desc);
 extern void coresight_unregister(struct coresight_device *csdev);
-- 
cgit v1.2.3


From f2ccc7b7bfa91b5cad5a4d57b269f6d7bbafd67d Mon Sep 17 00:00:00 2001
From: Tingwei Zhang <tingwei@codeaurora.org>
Date: Mon, 28 Sep 2020 10:35:07 -0600
Subject: coresight: cti: Don't disable ect device if it's not enabled

If associated ect device is not enabled at first place, disable
routine should not be called. Add ect_enabled flag to check whether
ect device is enabled. Fix the issue in below case.  Ect device is
not available when associated coresight device enabled and the
association is established after coresight device is enabled.

Signed-off-by: Mike Leach <mike.leach@linaro.org>
Signed-off-by: Tingwei Zhang <tingwei@codeaurora.org>
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Link: https://lore.kernel.org/r/20200928163513.70169-20-mathieu.poirier@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/hwtracing/coresight/coresight.c | 11 ++++++++---
 include/linux/coresight.h               |  1 +
 2 files changed, 9 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/hwtracing/coresight/coresight.c b/drivers/hwtracing/coresight/coresight.c
index b8b0a20e93c9..711beb92166a 100644
--- a/drivers/hwtracing/coresight/coresight.c
+++ b/drivers/hwtracing/coresight/coresight.c
@@ -244,13 +244,18 @@ coresight_control_assoc_ectdev(struct coresight_device *csdev, bool enable)
 
 	if (!ect_csdev)
 		return 0;
+	if ((!ect_ops(ect_csdev)->enable) || (!ect_ops(ect_csdev)->disable))
+		return 0;
 
 	if (enable) {
-		if (ect_ops(ect_csdev)->enable)
-			ect_ret = ect_ops(ect_csdev)->enable(ect_csdev);
+		ect_ret = ect_ops(ect_csdev)->enable(ect_csdev);
+		if (!ect_ret)
+			csdev->ect_enabled = true;
 	} else {
-		if (ect_ops(ect_csdev)->disable)
+		if (csdev->ect_enabled) {
 			ect_ret = ect_ops(ect_csdev)->disable(ect_csdev);
+			csdev->ect_enabled = false;
+		}
 	}
 
 	/* output warning if ECT enable is preventing trace operation */
diff --git a/include/linux/coresight.h b/include/linux/coresight.h
index 3bb738f9a326..7d3c87e5b97c 100644
--- a/include/linux/coresight.h
+++ b/include/linux/coresight.h
@@ -208,6 +208,7 @@ struct coresight_device {
 	/* sysfs links between components */
 	int nr_links;
 	bool has_conns_grp;
+	bool ect_enabled; /* true only if associated ect device is enabled */
 };
 
 /*
-- 
cgit v1.2.3


From ea470b82f205fc1b0b5276575da519bb7d86db25 Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Fri, 25 Sep 2020 17:48:55 +0100
Subject: regmap: add support to regmap_field_bulk_alloc/free apis

Usage of regmap_field_alloc becomes much overhead when number of fields
exceed more than 3.
QCOM LPASS driver has extensively converted to use regmap_fields.

Using new bulk api to allocate fields makes it much more cleaner code to read!

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Tested-by: Srinivasa Rao Mandadapu <srivasam@codeaurora.org>
Link: https://lore.kernel.org/r/20200925164856.10315-2-srinivas.kandagatla@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/base/regmap/regmap.c | 100 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/regmap.h       |  11 +++++
 2 files changed, 111 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index e93700af7e6e..8fc544aa8c78 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -1227,6 +1227,106 @@ struct regmap_field *devm_regmap_field_alloc(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(devm_regmap_field_alloc);
 
+
+/**
+ * regmap_field_bulk_alloc() - Allocate and initialise a bulk register field.
+ *
+ * @regmap: regmap bank in which this register field is located.
+ * @rm_field: regmap register fields within the bank.
+ * @reg_field: Register fields within the bank.
+ * @num_fields: Number of register fields.
+ *
+ * The return value will be an -ENOMEM on error or zero for success.
+ * Newly allocated regmap_fields should be freed by calling
+ * regmap_field_bulk_free()
+ */
+int regmap_field_bulk_alloc(struct regmap *regmap,
+			    struct regmap_field **rm_field,
+			    struct reg_field *reg_field,
+			    int num_fields)
+{
+	struct regmap_field *rf;
+	int i;
+
+	rf = kcalloc(num_fields, sizeof(*rf), GFP_KERNEL);
+	if (!rf)
+		return -ENOMEM;
+
+	for (i = 0; i < num_fields; i++) {
+		regmap_field_init(&rf[i], regmap, reg_field[i]);
+		rm_field[i] = &rf[i];
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(regmap_field_bulk_alloc);
+
+/**
+ * devm_regmap_field_bulk_alloc() - Allocate and initialise a bulk register
+ * fields.
+ *
+ * @dev: Device that will be interacted with
+ * @regmap: regmap bank in which this register field is located.
+ * @rm_field: regmap register fields within the bank.
+ * @reg_field: Register fields within the bank.
+ * @num_fields: Number of register fields.
+ *
+ * The return value will be an -ENOMEM on error or zero for success.
+ * Newly allocated regmap_fields will be automatically freed by the
+ * device management code.
+ */
+int devm_regmap_field_bulk_alloc(struct device *dev,
+				 struct regmap *regmap,
+				 struct regmap_field **rm_field,
+				 struct reg_field *reg_field,
+				 int num_fields)
+{
+	struct regmap_field *rf;
+	int i;
+
+	rf = devm_kcalloc(dev, num_fields, sizeof(*rf), GFP_KERNEL);
+	if (!rf)
+		return -ENOMEM;
+
+	for (i = 0; i < num_fields; i++) {
+		regmap_field_init(&rf[i], regmap, reg_field[i]);
+		rm_field[i] = &rf[i];
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devm_regmap_field_bulk_alloc);
+
+/**
+ * regmap_field_bulk_free() - Free register field allocated using
+ *                       regmap_field_bulk_alloc.
+ *
+ * @field: regmap fields which should be freed.
+ */
+void regmap_field_bulk_free(struct regmap_field *field)
+{
+	kfree(field);
+}
+EXPORT_SYMBOL_GPL(regmap_field_bulk_free);
+
+/**
+ * devm_regmap_field_bulk_free() - Free a bulk register field allocated using
+ *                            devm_regmap_field_bulk_alloc.
+ *
+ * @dev: Device that will be interacted with
+ * @field: regmap field which should be freed.
+ *
+ * Free register field allocated using devm_regmap_field_bulk_alloc(). Usually
+ * drivers need not call this function, as the memory allocated via devm
+ * will be freed as per device-driver life-cycle.
+ */
+void devm_regmap_field_bulk_free(struct device *dev,
+				 struct regmap_field *field)
+{
+	devm_kfree(dev, field);
+}
+EXPORT_SYMBOL_GPL(devm_regmap_field_bulk_free);
+
 /**
  * devm_regmap_field_free() - Free a register field allocated using
  *                            devm_regmap_field_alloc.
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index 1970ed59d49f..eafe833f0103 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -1150,6 +1150,17 @@ struct regmap_field *devm_regmap_field_alloc(struct device *dev,
 		struct regmap *regmap, struct reg_field reg_field);
 void devm_regmap_field_free(struct device *dev,	struct regmap_field *field);
 
+int regmap_field_bulk_alloc(struct regmap *regmap,
+			     struct regmap_field **rm_field,
+			     struct reg_field *reg_field,
+			     int num_fields);
+void regmap_field_bulk_free(struct regmap_field *field);
+int devm_regmap_field_bulk_alloc(struct device *dev, struct regmap *regmap,
+				 struct regmap_field **field,
+				 struct reg_field *reg_field, int num_fields);
+void devm_regmap_field_bulk_free(struct device *dev,
+				 struct regmap_field *field);
+
 int regmap_field_read(struct regmap_field *field, unsigned int *val);
 int regmap_field_update_bits_base(struct regmap_field *field,
 				  unsigned int mask, unsigned int val,
-- 
cgit v1.2.3


From 1b4d60ec162f82ea29a2e7a907b5c6cc9f926321 Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Fri, 25 Sep 2020 13:54:29 -0700
Subject: bpf: Enable BPF_PROG_TEST_RUN for raw_tracepoint

Add .test_run for raw_tracepoint. Also, introduce a new feature that runs
the target program on a specific CPU. This is achieved by a new flag in
bpf_attr.test, BPF_F_TEST_RUN_ON_CPU. When this flag is set, the program
is triggered on cpu with id bpf_attr.test.cpu. This feature is needed for
BPF programs that handle perf_event and other percpu resources, as the
program can access these resource locally.

Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200925205432.1777-2-songliubraving@fb.com
---
 include/linux/bpf.h            |  3 ++
 include/uapi/linux/bpf.h       |  7 ++++
 kernel/bpf/syscall.c           |  2 +-
 kernel/trace/bpf_trace.c       |  1 +
 net/bpf/test_run.c             | 91 ++++++++++++++++++++++++++++++++++++++++++
 tools/include/uapi/linux/bpf.h |  7 ++++
 6 files changed, 110 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 79902325bef8..db6dcdee7933 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1396,6 +1396,9 @@ int bpf_prog_test_run_tracing(struct bpf_prog *prog,
 int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
 				     const union bpf_attr *kattr,
 				     union bpf_attr __user *uattr);
+int bpf_prog_test_run_raw_tp(struct bpf_prog *prog,
+			     const union bpf_attr *kattr,
+			     union bpf_attr __user *uattr);
 bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 		    const struct bpf_prog *prog,
 		    struct bpf_insn_access_aux *info);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 2d6519a2ed77..82522f05c021 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -424,6 +424,11 @@ enum {
  */
 #define BPF_F_QUERY_EFFECTIVE	(1U << 0)
 
+/* Flags for BPF_PROG_TEST_RUN */
+
+/* If set, run the test on the cpu specified by bpf_attr.test.cpu */
+#define BPF_F_TEST_RUN_ON_CPU	(1U << 0)
+
 /* type for BPF_ENABLE_STATS */
 enum bpf_stats_type {
 	/* enabled run_time_ns and run_cnt */
@@ -566,6 +571,8 @@ union bpf_attr {
 						 */
 		__aligned_u64	ctx_in;
 		__aligned_u64	ctx_out;
+		__u32		flags;
+		__u32		cpu;
 	} test;
 
 	struct { /* anonymous struct used by BPF_*_GET_*_ID */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 2740df19f55e..3bc2ed2e171b 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2979,7 +2979,7 @@ static int bpf_prog_query(const union bpf_attr *attr,
 	}
 }
 
-#define BPF_PROG_TEST_RUN_LAST_FIELD test.ctx_out
+#define BPF_PROG_TEST_RUN_LAST_FIELD test.cpu
 
 static int bpf_prog_test_run(const union bpf_attr *attr,
 			     union bpf_attr __user *uattr)
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 36508f46a8db..2834866d379a 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1678,6 +1678,7 @@ const struct bpf_verifier_ops raw_tracepoint_verifier_ops = {
 };
 
 const struct bpf_prog_ops raw_tracepoint_prog_ops = {
+	.test_run = bpf_prog_test_run_raw_tp,
 };
 
 const struct bpf_verifier_ops tracing_verifier_ops = {
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index a66f211726e7..fde5db93507c 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -11,6 +11,7 @@
 #include <net/sock.h>
 #include <net/tcp.h>
 #include <linux/error-injection.h>
+#include <linux/smp.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/bpf_test_run.h>
@@ -204,6 +205,9 @@ int bpf_prog_test_run_tracing(struct bpf_prog *prog,
 	int b = 2, err = -EFAULT;
 	u32 retval = 0;
 
+	if (kattr->test.flags || kattr->test.cpu)
+		return -EINVAL;
+
 	switch (prog->expected_attach_type) {
 	case BPF_TRACE_FENTRY:
 	case BPF_TRACE_FEXIT:
@@ -236,6 +240,87 @@ out:
 	return err;
 }
 
+struct bpf_raw_tp_test_run_info {
+	struct bpf_prog *prog;
+	void *ctx;
+	u32 retval;
+};
+
+static void
+__bpf_prog_test_run_raw_tp(void *data)
+{
+	struct bpf_raw_tp_test_run_info *info = data;
+
+	rcu_read_lock();
+	migrate_disable();
+	info->retval = BPF_PROG_RUN(info->prog, info->ctx);
+	migrate_enable();
+	rcu_read_unlock();
+}
+
+int bpf_prog_test_run_raw_tp(struct bpf_prog *prog,
+			     const union bpf_attr *kattr,
+			     union bpf_attr __user *uattr)
+{
+	void __user *ctx_in = u64_to_user_ptr(kattr->test.ctx_in);
+	__u32 ctx_size_in = kattr->test.ctx_size_in;
+	struct bpf_raw_tp_test_run_info info;
+	int cpu = kattr->test.cpu, err = 0;
+
+	/* doesn't support data_in/out, ctx_out, duration, or repeat */
+	if (kattr->test.data_in || kattr->test.data_out ||
+	    kattr->test.ctx_out || kattr->test.duration ||
+	    kattr->test.repeat)
+		return -EINVAL;
+
+	if (ctx_size_in < prog->aux->max_ctx_offset)
+		return -EINVAL;
+
+	if ((kattr->test.flags & BPF_F_TEST_RUN_ON_CPU) == 0 && cpu != 0)
+		return -EINVAL;
+
+	if (ctx_size_in) {
+		info.ctx = kzalloc(ctx_size_in, GFP_USER);
+		if (!info.ctx)
+			return -ENOMEM;
+		if (copy_from_user(info.ctx, ctx_in, ctx_size_in)) {
+			err = -EFAULT;
+			goto out;
+		}
+	} else {
+		info.ctx = NULL;
+	}
+
+	info.prog = prog;
+
+	if ((kattr->test.flags & BPF_F_TEST_RUN_ON_CPU) == 0 ||
+	    cpu == smp_processor_id()) {
+		__bpf_prog_test_run_raw_tp(&info);
+	} else {
+		/* smp_call_function_single() also checks cpu_online()
+		 * after csd_lock(). However, since cpu is from user
+		 * space, let's do an extra quick check to filter out
+		 * invalid value before smp_call_function_single().
+		 */
+		if (cpu >= nr_cpu_ids || !cpu_online(cpu)) {
+			err = -ENXIO;
+			goto out;
+		}
+
+		err = smp_call_function_single(cpu, __bpf_prog_test_run_raw_tp,
+					       &info, 1);
+		if (err)
+			goto out;
+	}
+
+	if (copy_to_user(&uattr->test.retval, &info.retval, sizeof(u32)))
+		err = -EFAULT;
+
+out:
+	kfree(info.ctx);
+	return err;
+}
+
 static void *bpf_ctx_init(const union bpf_attr *kattr, u32 max_size)
 {
 	void __user *data_in = u64_to_user_ptr(kattr->test.ctx_in);
@@ -410,6 +495,9 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 	void *data;
 	int ret;
 
+	if (kattr->test.flags || kattr->test.cpu)
+		return -EINVAL;
+
 	data = bpf_test_init(kattr, size, NET_SKB_PAD + NET_IP_ALIGN,
 			     SKB_DATA_ALIGN(sizeof(struct skb_shared_info)));
 	if (IS_ERR(data))
@@ -607,6 +695,9 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
 	if (prog->type != BPF_PROG_TYPE_FLOW_DISSECTOR)
 		return -EINVAL;
 
+	if (kattr->test.flags || kattr->test.cpu)
+		return -EINVAL;
+
 	if (size < ETH_HLEN)
 		return -EINVAL;
 
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 2d6519a2ed77..82522f05c021 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -424,6 +424,11 @@ enum {
  */
 #define BPF_F_QUERY_EFFECTIVE	(1U << 0)
 
+/* Flags for BPF_PROG_TEST_RUN */
+
+/* If set, run the test on the cpu specified by bpf_attr.test.cpu */
+#define BPF_F_TEST_RUN_ON_CPU	(1U << 0)
+
 /* type for BPF_ENABLE_STATS */
 enum bpf_stats_type {
 	/* enabled run_time_ns and run_cnt */
@@ -566,6 +571,8 @@ union bpf_attr {
 						 */
 		__aligned_u64	ctx_in;
 		__aligned_u64	ctx_out;
+		__u32		flags;
+		__u32		cpu;
 	} test;
 
 	struct { /* anonymous struct used by BPF_*_GET_*_ID */
-- 
cgit v1.2.3


From 5b2a828b98ec1872799b1b4d82113c76a12d594f Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Wed, 23 Sep 2020 22:47:21 -0700
Subject: fscrypt: export fscrypt_d_revalidate()

Dentries that represent no-key names must have a dentry_operations that
includes fscrypt_d_revalidate().  Currently, this is handled by
fscrypt_prepare_lookup() installing fscrypt_d_ops.

However, ceph support for encryption
(https://lore.kernel.org/r/20200914191707.380444-1-jlayton@kernel.org)
can't use fscrypt_d_ops, since ceph already has its own
dentry_operations.

Similarly, ext4 and f2fs support for directories that are both encrypted
and casefolded
(https://lore.kernel.org/r/20200923010151.69506-1-drosen@google.com)
can't use fscrypt_d_ops either, since casefolding requires some dentry
operations too.

To satisfy both users, we need to move the responsibility of installing
the dentry_operations to filesystems.

In preparation for this, export fscrypt_d_revalidate() and give it a
!CONFIG_FS_ENCRYPTION stub.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Link: https://lore.kernel.org/r/20200924054721.187797-1-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 fs/crypto/fname.c       | 3 ++-
 include/linux/fscrypt.h | 7 +++++++
 2 files changed, 9 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c
index c65979452844..1fbe6c24d705 100644
--- a/fs/crypto/fname.c
+++ b/fs/crypto/fname.c
@@ -530,7 +530,7 @@ EXPORT_SYMBOL_GPL(fscrypt_fname_siphash);
  * Validate dentries in encrypted directories to make sure we aren't potentially
  * caching stale dentries after a key has been added.
  */
-static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
+int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	struct dentry *dir;
 	int err;
@@ -569,6 +569,7 @@ static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
 
 	return valid;
 }
+EXPORT_SYMBOL_GPL(fscrypt_d_revalidate);
 
 const struct dentry_operations fscrypt_d_ops = {
 	.d_revalidate = fscrypt_d_revalidate,
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index f1757e73162d..a8f7a43f031b 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -197,6 +197,7 @@ int fscrypt_fname_disk_to_usr(const struct inode *inode,
 bool fscrypt_match_name(const struct fscrypt_name *fname,
 			const u8 *de_name, u32 de_name_len);
 u64 fscrypt_fname_siphash(const struct inode *dir, const struct qstr *name);
+int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags);
 
 /* bio.c */
 void fscrypt_decrypt_bio(struct bio *bio);
@@ -454,6 +455,12 @@ static inline u64 fscrypt_fname_siphash(const struct inode *dir,
 	return 0;
 }
 
+static inline int fscrypt_d_revalidate(struct dentry *dentry,
+				       unsigned int flags)
+{
+	return 1;
+}
+
 /* bio.c */
 static inline void fscrypt_decrypt_bio(struct bio *bio)
 {
-- 
cgit v1.2.3


From efc68158c429f37d87fd02ee9a26913c78546fc9 Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@redhat.com>
Date: Fri, 25 Sep 2020 23:25:01 +0200
Subject: bpf: change logging calls from verbose() to bpf_log() and use log
 pointer
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In preparation for moving code around, change a bunch of references to
env->log (and the verbose() logging helper) to use bpf_log() and a direct
pointer to struct bpf_verifier_log. While we're touching the function
signature, mark the 'prog' argument to bpf_check_type_match() as const.

Also enhance the bpf_verifier_log_needed() check to handle NULL pointers
for the log struct so we can re-use the code with logging disabled.

Acked-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h          |  2 +-
 include/linux/bpf_verifier.h |  5 +++--
 kernel/bpf/btf.c             |  6 +++---
 kernel/bpf/verifier.c        | 50 ++++++++++++++++++++++----------------------
 4 files changed, 32 insertions(+), 31 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index db6dcdee7933..5176726f4f03 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1420,7 +1420,7 @@ int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog,
 			     struct bpf_reg_state *regs);
 int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
 			  struct bpf_reg_state *reg);
-int btf_check_type_match(struct bpf_verifier_env *env, struct bpf_prog *prog,
+int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog,
 			 struct btf *btf, const struct btf_type *t);
 
 struct bpf_prog *bpf_prog_by_id(u32 id);
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 2bb48a2c4d08..7bc9276c4ef4 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -347,8 +347,9 @@ static inline bool bpf_verifier_log_full(const struct bpf_verifier_log *log)
 
 static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log)
 {
-	return (log->level && log->ubuf && !bpf_verifier_log_full(log)) ||
-		log->level == BPF_LOG_KERNEL;
+	return log &&
+		((log->level && log->ubuf && !bpf_verifier_log_full(log)) ||
+		 log->level == BPF_LOG_KERNEL);
 }
 
 #define BPF_MAX_SUBPROGS 256
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 5d3c36e13139..868c03a24d0a 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -4388,7 +4388,7 @@ static int btf_check_func_type_match(struct bpf_verifier_log *log,
 }
 
 /* Compare BTFs of given program with BTF of target program */
-int btf_check_type_match(struct bpf_verifier_env *env, struct bpf_prog *prog,
+int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog,
 			 struct btf *btf2, const struct btf_type *t2)
 {
 	struct btf *btf1 = prog->aux->btf;
@@ -4396,7 +4396,7 @@ int btf_check_type_match(struct bpf_verifier_env *env, struct bpf_prog *prog,
 	u32 btf_id = 0;
 
 	if (!prog->aux->func_info) {
-		bpf_log(&env->log, "Program extension requires BTF\n");
+		bpf_log(log, "Program extension requires BTF\n");
 		return -EINVAL;
 	}
 
@@ -4408,7 +4408,7 @@ int btf_check_type_match(struct bpf_verifier_env *env, struct bpf_prog *prog,
 	if (!t1 || !btf_type_is_func(t1))
 		return -EFAULT;
 
-	return btf_check_func_type_match(&env->log, btf1, t1, btf2, t2);
+	return btf_check_func_type_match(log, btf1, t1, btf2, t2);
 }
 
 /* Compare BTF of a function with given bpf_reg_state.
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 52649a5497ce..d93489c1ac65 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -11249,6 +11249,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 	struct bpf_prog *prog = env->prog;
 	bool prog_extension = prog->type == BPF_PROG_TYPE_EXT;
 	struct bpf_prog *tgt_prog = prog->aux->linked_prog;
+	struct bpf_verifier_log *log = &env->log;
 	u32 btf_id = prog->aux->attach_btf_id;
 	const char prefix[] = "btf_trace_";
 	struct btf_func_model fmodel;
@@ -11276,23 +11277,23 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 		return 0;
 
 	if (!btf_id) {
-		verbose(env, "Tracing programs must provide btf_id\n");
+		bpf_log(log, "Tracing programs must provide btf_id\n");
 		return -EINVAL;
 	}
 	btf = bpf_prog_get_target_btf(prog);
 	if (!btf) {
-		verbose(env,
+		bpf_log(log,
 			"FENTRY/FEXIT program can only be attached to another program annotated with BTF\n");
 		return -EINVAL;
 	}
 	t = btf_type_by_id(btf, btf_id);
 	if (!t) {
-		verbose(env, "attach_btf_id %u is invalid\n", btf_id);
+		bpf_log(log, "attach_btf_id %u is invalid\n", btf_id);
 		return -EINVAL;
 	}
 	tname = btf_name_by_offset(btf, t->name_off);
 	if (!tname) {
-		verbose(env, "attach_btf_id %u doesn't have a name\n", btf_id);
+		bpf_log(log, "attach_btf_id %u doesn't have a name\n", btf_id);
 		return -EINVAL;
 	}
 	if (tgt_prog) {
@@ -11304,18 +11305,18 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 				break;
 			}
 		if (subprog == -1) {
-			verbose(env, "Subprog %s doesn't exist\n", tname);
+			bpf_log(log, "Subprog %s doesn't exist\n", tname);
 			return -EINVAL;
 		}
 		conservative = aux->func_info_aux[subprog].unreliable;
 		if (prog_extension) {
 			if (conservative) {
-				verbose(env,
+				bpf_log(log,
 					"Cannot replace static functions\n");
 				return -EINVAL;
 			}
 			if (!prog->jit_requested) {
-				verbose(env,
+				bpf_log(log,
 					"Extension programs should be JITed\n");
 				return -EINVAL;
 			}
@@ -11323,7 +11324,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 			prog->expected_attach_type = tgt_prog->expected_attach_type;
 		}
 		if (!tgt_prog->jited) {
-			verbose(env, "Can attach to only JITed progs\n");
+			bpf_log(log, "Can attach to only JITed progs\n");
 			return -EINVAL;
 		}
 		if (tgt_prog->type == prog->type) {
@@ -11331,7 +11332,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 			 * Cannot attach program extension to another extension.
 			 * It's ok to attach fentry/fexit to extension program.
 			 */
-			verbose(env, "Cannot recursively attach\n");
+			bpf_log(log, "Cannot recursively attach\n");
 			return -EINVAL;
 		}
 		if (tgt_prog->type == BPF_PROG_TYPE_TRACING &&
@@ -11353,13 +11354,13 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 			 * reasonable stack size. Hence extending fentry is not
 			 * allowed.
 			 */
-			verbose(env, "Cannot extend fentry/fexit\n");
+			bpf_log(log, "Cannot extend fentry/fexit\n");
 			return -EINVAL;
 		}
 		key = ((u64)aux->id) << 32 | btf_id;
 	} else {
 		if (prog_extension) {
-			verbose(env, "Cannot replace kernel functions\n");
+			bpf_log(log, "Cannot replace kernel functions\n");
 			return -EINVAL;
 		}
 		key = btf_id;
@@ -11368,17 +11369,17 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 	switch (prog->expected_attach_type) {
 	case BPF_TRACE_RAW_TP:
 		if (tgt_prog) {
-			verbose(env,
+			bpf_log(log,
 				"Only FENTRY/FEXIT progs are attachable to another BPF prog\n");
 			return -EINVAL;
 		}
 		if (!btf_type_is_typedef(t)) {
-			verbose(env, "attach_btf_id %u is not a typedef\n",
+			bpf_log(log, "attach_btf_id %u is not a typedef\n",
 				btf_id);
 			return -EINVAL;
 		}
 		if (strncmp(prefix, tname, sizeof(prefix) - 1)) {
-			verbose(env, "attach_btf_id %u points to wrong type name %s\n",
+			bpf_log(log, "attach_btf_id %u points to wrong type name %s\n",
 				btf_id, tname);
 			return -EINVAL;
 		}
@@ -11401,7 +11402,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 		return 0;
 	case BPF_TRACE_ITER:
 		if (!btf_type_is_func(t)) {
-			verbose(env, "attach_btf_id %u is not a function\n",
+			bpf_log(log, "attach_btf_id %u is not a function\n",
 				btf_id);
 			return -EINVAL;
 		}
@@ -11412,8 +11413,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 		prog->aux->attach_func_proto = t;
 		if (!bpf_iter_prog_supported(prog))
 			return -EINVAL;
-		ret = btf_distill_func_proto(&env->log, btf, t,
-					     tname, &fmodel);
+		ret = btf_distill_func_proto(log, btf, t, tname, &fmodel);
 		return ret;
 	default:
 		if (!prog_extension)
@@ -11425,18 +11425,18 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 	case BPF_TRACE_FEXIT:
 		prog->aux->attach_func_name = tname;
 		if (prog->type == BPF_PROG_TYPE_LSM) {
-			ret = bpf_lsm_verify_prog(&env->log, prog);
+			ret = bpf_lsm_verify_prog(log, prog);
 			if (ret < 0)
 				return ret;
 		}
 
 		if (!btf_type_is_func(t)) {
-			verbose(env, "attach_btf_id %u is not a function\n",
+			bpf_log(log, "attach_btf_id %u is not a function\n",
 				btf_id);
 			return -EINVAL;
 		}
 		if (prog_extension &&
-		    btf_check_type_match(env, prog, btf, t))
+		    btf_check_type_match(log, prog, btf, t))
 			return -EINVAL;
 		t = btf_type_by_id(btf, t->type);
 		if (!btf_type_is_func_proto(t))
@@ -11455,7 +11455,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 			prog->aux->attach_func_proto = NULL;
 			t = NULL;
 		}
-		ret = btf_distill_func_proto(&env->log, btf, t,
+		ret = btf_distill_func_proto(log, btf, t,
 					     tname, &tr->func.model);
 		if (ret < 0)
 			goto out;
@@ -11467,7 +11467,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 		} else {
 			addr = kallsyms_lookup_name(tname);
 			if (!addr) {
-				verbose(env,
+				bpf_log(log,
 					"The address of function %s cannot be found\n",
 					tname);
 				ret = -ENOENT;
@@ -11497,17 +11497,17 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 				break;
 			}
 			if (ret)
-				verbose(env, "%s is not sleepable\n",
+				bpf_log(log, "%s is not sleepable\n",
 					prog->aux->attach_func_name);
 		} else if (prog->expected_attach_type == BPF_MODIFY_RETURN) {
 			if (tgt_prog) {
-				verbose(env, "can't modify return codes of BPF programs\n");
+				bpf_log(log, "can't modify return codes of BPF programs\n");
 				ret = -EINVAL;
 				goto out;
 			}
 			ret = check_attach_modify_return(prog, addr);
 			if (ret)
-				verbose(env, "%s() is not modifiable\n",
+				bpf_log(log, "%s() is not modifiable\n",
 					prog->aux->attach_func_name);
 		}
 		if (ret)
-- 
cgit v1.2.3


From f7b12b6fea00988496b7606d4964cd77beef46a5 Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@redhat.com>
Date: Fri, 25 Sep 2020 23:25:02 +0200
Subject: bpf: verifier: refactor check_attach_btf_id()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The check_attach_btf_id() function really does three things:

1. It performs a bunch of checks on the program to ensure that the
   attachment is valid.

2. It stores a bunch of state about the attachment being requested in
   the verifier environment and struct bpf_prog objects.

3. It allocates a trampoline for the attachment.

This patch splits out (1.) and (3.) into separate functions which will
perform the checks, but return the computed values instead of directly
modifying the environment. This is done in preparation for reusing the
checks when the actual attachment is happening, which will allow tracing
programs to have multiple (compatible) attachments.

This also fixes a bug where a bunch of checks were skipped if a trampoline
already existed for the tracing target.

Fixes: 6ba43b761c41 ("bpf: Attachment verification for BPF_MODIFY_RETURN")
Fixes: 1e6c62a88215 ("bpf: Introduce sleepable BPF programs")
Acked-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h          |  19 +++--
 include/linux/bpf_verifier.h |  13 +++
 kernel/bpf/trampoline.c      |  22 +++++-
 kernel/bpf/verifier.c        | 183 +++++++++++++++++++++++--------------------
 4 files changed, 145 insertions(+), 92 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 5176726f4f03..b89a30764069 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -606,6 +606,13 @@ struct bpf_trampoline {
 	struct bpf_ksym ksym;
 };
 
+struct bpf_attach_target_info {
+	struct btf_func_model fmodel;
+	long tgt_addr;
+	const char *tgt_name;
+	const struct btf_type *tgt_type;
+};
+
 #define BPF_DISPATCHER_MAX 48 /* Fits in 2048B */
 
 struct bpf_dispatcher_prog {
@@ -633,9 +640,10 @@ static __always_inline unsigned int bpf_dispatcher_nop_func(
 	return bpf_func(ctx, insnsi);
 }
 #ifdef CONFIG_BPF_JIT
-struct bpf_trampoline *bpf_trampoline_lookup(u64 key);
 int bpf_trampoline_link_prog(struct bpf_prog *prog);
 int bpf_trampoline_unlink_prog(struct bpf_prog *prog);
+struct bpf_trampoline *bpf_trampoline_get(u64 key,
+					  struct bpf_attach_target_info *tgt_info);
 void bpf_trampoline_put(struct bpf_trampoline *tr);
 #define BPF_DISPATCHER_INIT(_name) {				\
 	.mutex = __MUTEX_INITIALIZER(_name.mutex),		\
@@ -680,10 +688,6 @@ void bpf_image_ksym_del(struct bpf_ksym *ksym);
 void bpf_ksym_add(struct bpf_ksym *ksym);
 void bpf_ksym_del(struct bpf_ksym *ksym);
 #else
-static inline struct bpf_trampoline *bpf_trampoline_lookup(u64 key)
-{
-	return NULL;
-}
 static inline int bpf_trampoline_link_prog(struct bpf_prog *prog)
 {
 	return -ENOTSUPP;
@@ -692,6 +696,11 @@ static inline int bpf_trampoline_unlink_prog(struct bpf_prog *prog)
 {
 	return -ENOTSUPP;
 }
+static inline struct bpf_trampoline *bpf_trampoline_get(u64 key,
+							struct bpf_attach_target_info *tgt_info)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
 static inline void bpf_trampoline_put(struct bpf_trampoline *tr) {}
 #define DEFINE_BPF_DISPATCHER(name)
 #define DECLARE_BPF_DISPATCHER(name)
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 7bc9276c4ef4..363b4f1c562a 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -450,4 +450,17 @@ bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt);
 int check_ctx_reg(struct bpf_verifier_env *env,
 		  const struct bpf_reg_state *reg, int regno);
 
+/* this lives here instead of in bpf.h because it needs to dereference tgt_prog */
+static inline u64 bpf_trampoline_compute_key(const struct bpf_prog *tgt_prog,
+					     u32 btf_id)
+{
+        return tgt_prog ? (((u64)tgt_prog->aux->id) << 32 | btf_id) : btf_id;
+}
+
+int bpf_check_attach_target(struct bpf_verifier_log *log,
+			    const struct bpf_prog *prog,
+			    const struct bpf_prog *tgt_prog,
+			    u32 btf_id,
+			    struct bpf_attach_target_info *tgt_info);
+
 #endif /* _LINUX_BPF_VERIFIER_H */
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 7dd523a7e32d..28c1899949e0 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -65,7 +65,7 @@ static void bpf_trampoline_ksym_add(struct bpf_trampoline *tr)
 	bpf_image_ksym_add(tr->image, ksym);
 }
 
-struct bpf_trampoline *bpf_trampoline_lookup(u64 key)
+static struct bpf_trampoline *bpf_trampoline_lookup(u64 key)
 {
 	struct bpf_trampoline *tr;
 	struct hlist_head *head;
@@ -336,6 +336,26 @@ out:
 	return err;
 }
 
+struct bpf_trampoline *bpf_trampoline_get(u64 key,
+					  struct bpf_attach_target_info *tgt_info)
+{
+	struct bpf_trampoline *tr;
+
+	tr = bpf_trampoline_lookup(key);
+	if (!tr)
+		return NULL;
+
+	mutex_lock(&tr->mutex);
+	if (tr->func.addr)
+		goto out;
+
+	memcpy(&tr->func.model, &tgt_info->fmodel, sizeof(tgt_info->fmodel));
+	tr->func.addr = (void *)tgt_info->tgt_addr;
+out:
+	mutex_unlock(&tr->mutex);
+	return tr;
+}
+
 void bpf_trampoline_put(struct bpf_trampoline *tr)
 {
 	if (!tr)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index d93489c1ac65..7ff05a79984a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -11203,11 +11203,10 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env)
 }
 #define SECURITY_PREFIX "security_"
 
-static int check_attach_modify_return(struct bpf_prog *prog, unsigned long addr)
+static int check_attach_modify_return(unsigned long addr, const char *func_name)
 {
 	if (within_error_injection_list(addr) ||
-	    !strncmp(SECURITY_PREFIX, prog->aux->attach_func_name,
-		     sizeof(SECURITY_PREFIX) - 1))
+	    !strncmp(SECURITY_PREFIX, func_name, sizeof(SECURITY_PREFIX) - 1))
 		return 0;
 
 	return -EINVAL;
@@ -11244,43 +11243,26 @@ static int check_non_sleepable_error_inject(u32 btf_id)
 	return btf_id_set_contains(&btf_non_sleepable_error_inject, btf_id);
 }
 
-static int check_attach_btf_id(struct bpf_verifier_env *env)
+int bpf_check_attach_target(struct bpf_verifier_log *log,
+			    const struct bpf_prog *prog,
+			    const struct bpf_prog *tgt_prog,
+			    u32 btf_id,
+			    struct bpf_attach_target_info *tgt_info)
 {
-	struct bpf_prog *prog = env->prog;
 	bool prog_extension = prog->type == BPF_PROG_TYPE_EXT;
-	struct bpf_prog *tgt_prog = prog->aux->linked_prog;
-	struct bpf_verifier_log *log = &env->log;
-	u32 btf_id = prog->aux->attach_btf_id;
 	const char prefix[] = "btf_trace_";
-	struct btf_func_model fmodel;
 	int ret = 0, subprog = -1, i;
-	struct bpf_trampoline *tr;
 	const struct btf_type *t;
 	bool conservative = true;
 	const char *tname;
 	struct btf *btf;
-	long addr;
-	u64 key;
-
-	if (prog->aux->sleepable && prog->type != BPF_PROG_TYPE_TRACING &&
-	    prog->type != BPF_PROG_TYPE_LSM) {
-		verbose(env, "Only fentry/fexit/fmod_ret and lsm programs can be sleepable\n");
-		return -EINVAL;
-	}
-
-	if (prog->type == BPF_PROG_TYPE_STRUCT_OPS)
-		return check_struct_ops_btf_id(env);
-
-	if (prog->type != BPF_PROG_TYPE_TRACING &&
-	    prog->type != BPF_PROG_TYPE_LSM &&
-	    !prog_extension)
-		return 0;
+	long addr = 0;
 
 	if (!btf_id) {
 		bpf_log(log, "Tracing programs must provide btf_id\n");
 		return -EINVAL;
 	}
-	btf = bpf_prog_get_target_btf(prog);
+	btf = tgt_prog ? tgt_prog->aux->btf : btf_vmlinux;
 	if (!btf) {
 		bpf_log(log,
 			"FENTRY/FEXIT program can only be attached to another program annotated with BTF\n");
@@ -11320,8 +11302,6 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 					"Extension programs should be JITed\n");
 				return -EINVAL;
 			}
-			env->ops = bpf_verifier_ops[tgt_prog->type];
-			prog->expected_attach_type = tgt_prog->expected_attach_type;
 		}
 		if (!tgt_prog->jited) {
 			bpf_log(log, "Can attach to only JITed progs\n");
@@ -11357,13 +11337,11 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 			bpf_log(log, "Cannot extend fentry/fexit\n");
 			return -EINVAL;
 		}
-		key = ((u64)aux->id) << 32 | btf_id;
 	} else {
 		if (prog_extension) {
 			bpf_log(log, "Cannot replace kernel functions\n");
 			return -EINVAL;
 		}
-		key = btf_id;
 	}
 
 	switch (prog->expected_attach_type) {
@@ -11393,13 +11371,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 			/* should never happen in valid vmlinux build */
 			return -EINVAL;
 
-		/* remember two read only pointers that are valid for
-		 * the life time of the kernel
-		 */
-		prog->aux->attach_func_name = tname;
-		prog->aux->attach_func_proto = t;
-		prog->aux->attach_btf_trace = true;
-		return 0;
+		break;
 	case BPF_TRACE_ITER:
 		if (!btf_type_is_func(t)) {
 			bpf_log(log, "attach_btf_id %u is not a function\n",
@@ -11409,12 +11381,10 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 		t = btf_type_by_id(btf, t->type);
 		if (!btf_type_is_func_proto(t))
 			return -EINVAL;
-		prog->aux->attach_func_name = tname;
-		prog->aux->attach_func_proto = t;
-		if (!bpf_iter_prog_supported(prog))
-			return -EINVAL;
-		ret = btf_distill_func_proto(log, btf, t, tname, &fmodel);
-		return ret;
+		ret = btf_distill_func_proto(log, btf, t, tname, &tgt_info->fmodel);
+		if (ret)
+			return ret;
+		break;
 	default:
 		if (!prog_extension)
 			return -EINVAL;
@@ -11423,13 +11393,6 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 	case BPF_LSM_MAC:
 	case BPF_TRACE_FENTRY:
 	case BPF_TRACE_FEXIT:
-		prog->aux->attach_func_name = tname;
-		if (prog->type == BPF_PROG_TYPE_LSM) {
-			ret = bpf_lsm_verify_prog(log, prog);
-			if (ret < 0)
-				return ret;
-		}
-
 		if (!btf_type_is_func(t)) {
 			bpf_log(log, "attach_btf_id %u is not a function\n",
 				btf_id);
@@ -11441,24 +11404,14 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 		t = btf_type_by_id(btf, t->type);
 		if (!btf_type_is_func_proto(t))
 			return -EINVAL;
-		tr = bpf_trampoline_lookup(key);
-		if (!tr)
-			return -ENOMEM;
-		/* t is either vmlinux type or another program's type */
-		prog->aux->attach_func_proto = t;
-		mutex_lock(&tr->mutex);
-		if (tr->func.addr) {
-			prog->aux->trampoline = tr;
-			goto out;
-		}
-		if (tgt_prog && conservative) {
-			prog->aux->attach_func_proto = NULL;
+
+		if (tgt_prog && conservative)
 			t = NULL;
-		}
-		ret = btf_distill_func_proto(log, btf, t,
-					     tname, &tr->func.model);
+
+		ret = btf_distill_func_proto(log, btf, t, tname, &tgt_info->fmodel);
 		if (ret < 0)
-			goto out;
+			return ret;
+
 		if (tgt_prog) {
 			if (subprog == 0)
 				addr = (long) tgt_prog->bpf_func;
@@ -11470,8 +11423,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 				bpf_log(log,
 					"The address of function %s cannot be found\n",
 					tname);
-				ret = -ENOENT;
-				goto out;
+				return -ENOENT;
 			}
 		}
 
@@ -11496,30 +11448,89 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 			default:
 				break;
 			}
-			if (ret)
-				bpf_log(log, "%s is not sleepable\n",
-					prog->aux->attach_func_name);
+			if (ret) {
+				bpf_log(log, "%s is not sleepable\n", tname);
+				return ret;
+			}
 		} else if (prog->expected_attach_type == BPF_MODIFY_RETURN) {
 			if (tgt_prog) {
 				bpf_log(log, "can't modify return codes of BPF programs\n");
-				ret = -EINVAL;
-				goto out;
+				return -EINVAL;
+			}
+			ret = check_attach_modify_return(addr, tname);
+			if (ret) {
+				bpf_log(log, "%s() is not modifiable\n", tname);
+				return ret;
 			}
-			ret = check_attach_modify_return(prog, addr);
-			if (ret)
-				bpf_log(log, "%s() is not modifiable\n",
-					prog->aux->attach_func_name);
 		}
-		if (ret)
-			goto out;
-		tr->func.addr = (void *)addr;
-		prog->aux->trampoline = tr;
-out:
-		mutex_unlock(&tr->mutex);
-		if (ret)
-			bpf_trampoline_put(tr);
+
+		break;
+	}
+	tgt_info->tgt_addr = addr;
+	tgt_info->tgt_name = tname;
+	tgt_info->tgt_type = t;
+	return 0;
+}
+
+static int check_attach_btf_id(struct bpf_verifier_env *env)
+{
+	struct bpf_prog *prog = env->prog;
+	struct bpf_prog *tgt_prog = prog->aux->linked_prog;
+	struct bpf_attach_target_info tgt_info = {};
+	u32 btf_id = prog->aux->attach_btf_id;
+	struct bpf_trampoline *tr;
+	int ret;
+	u64 key;
+
+	if (prog->aux->sleepable && prog->type != BPF_PROG_TYPE_TRACING &&
+	    prog->type != BPF_PROG_TYPE_LSM) {
+		verbose(env, "Only fentry/fexit/fmod_ret and lsm programs can be sleepable\n");
+		return -EINVAL;
+	}
+
+	if (prog->type == BPF_PROG_TYPE_STRUCT_OPS)
+		return check_struct_ops_btf_id(env);
+
+	if (prog->type != BPF_PROG_TYPE_TRACING &&
+	    prog->type != BPF_PROG_TYPE_LSM &&
+	    prog->type != BPF_PROG_TYPE_EXT)
+		return 0;
+
+	ret = bpf_check_attach_target(&env->log, prog, tgt_prog, btf_id, &tgt_info);
+	if (ret)
 		return ret;
+
+	if (tgt_prog && prog->type == BPF_PROG_TYPE_EXT) {
+		env->ops = bpf_verifier_ops[tgt_prog->type];
+		prog->expected_attach_type = tgt_prog->expected_attach_type;
+	}
+
+	/* store info about the attachment target that will be used later */
+	prog->aux->attach_func_proto = tgt_info.tgt_type;
+	prog->aux->attach_func_name = tgt_info.tgt_name;
+
+	if (prog->expected_attach_type == BPF_TRACE_RAW_TP) {
+		prog->aux->attach_btf_trace = true;
+		return 0;
+	} else if (prog->expected_attach_type == BPF_TRACE_ITER) {
+		if (!bpf_iter_prog_supported(prog))
+			return -EINVAL;
+		return 0;
+	}
+
+	if (prog->type == BPF_PROG_TYPE_LSM) {
+		ret = bpf_lsm_verify_prog(&env->log, prog);
+		if (ret < 0)
+			return ret;
 	}
+
+	key = bpf_trampoline_compute_key(tgt_prog, btf_id);
+	tr = bpf_trampoline_get(key, &tgt_info);
+	if (!tr)
+		return -ENOMEM;
+
+	prog->aux->trampoline = tr;
+	return 0;
 }
 
 int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
-- 
cgit v1.2.3


From 76654e67f3a01c50dc13dd6dea75e58943413956 Mon Sep 17 00:00:00 2001
From: Alan Maguire <alan.maguire@oracle.com>
Date: Mon, 28 Sep 2020 12:31:03 +0100
Subject: bpf: Provide function to get vmlinux BTF information

It will be used later for BPF structure display support

Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/1601292670-1616-2-git-send-email-alan.maguire@oracle.com
---
 include/linux/bpf.h   |  2 ++
 kernel/bpf/verifier.c | 18 ++++++++++++------
 2 files changed, 14 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index b89a30764069..e620a4b1290f 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1364,6 +1364,8 @@ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr,
 	      union bpf_attr __user *uattr);
 void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth);
 
+struct btf *bpf_get_btf_vmlinux(void);
+
 /* Map specifics */
 struct xdp_buff;
 struct sk_buff;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 7ff05a79984a..2ee343dda73a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -11533,6 +11533,17 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 	return 0;
 }
 
+struct btf *bpf_get_btf_vmlinux(void)
+{
+	if (!btf_vmlinux && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) {
+		mutex_lock(&bpf_verifier_lock);
+		if (!btf_vmlinux)
+			btf_vmlinux = btf_parse_vmlinux();
+		mutex_unlock(&bpf_verifier_lock);
+	}
+	return btf_vmlinux;
+}
+
 int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 	      union bpf_attr __user *uattr)
 {
@@ -11566,12 +11577,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 	env->ops = bpf_verifier_ops[env->prog->type];
 	is_priv = bpf_capable();
 
-	if (!btf_vmlinux && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) {
-		mutex_lock(&bpf_verifier_lock);
-		if (!btf_vmlinux)
-			btf_vmlinux = btf_parse_vmlinux();
-		mutex_unlock(&bpf_verifier_lock);
-	}
+	bpf_get_btf_vmlinux();
 
 	/* grab the mutex to protect few globals used by verifier */
 	if (!is_priv)
-- 
cgit v1.2.3


From 31d0bc81637d8d974a6dad9827b765b4b70c89d7 Mon Sep 17 00:00:00 2001
From: Alan Maguire <alan.maguire@oracle.com>
Date: Mon, 28 Sep 2020 12:31:04 +0100
Subject: bpf: Move to generic BTF show support, apply it to seq files/strings

generalize the "seq_show" seq file support in btf.c to support
a generic show callback of which we support two instances; the
current seq file show, and a show with snprintf() behaviour which
instead writes the type data to a supplied string.

Both classes of show function call btf_type_show() with different
targets; the seq file or the string to be written.  In the string
case we need to track additional data - length left in string to write
and length to return that we would have written (a la snprintf).

By default show will display type information, field members and
their types and values etc, and the information is indented
based upon structure depth. Zeroed fields are omitted.

Show however supports flags which modify its behaviour:

BTF_SHOW_COMPACT - suppress newline/indent.
BTF_SHOW_NONAME - suppress show of type and member names.
BTF_SHOW_PTR_RAW - do not obfuscate pointer values.
BTF_SHOW_UNSAFE - do not copy data to safe buffer before display.
BTF_SHOW_ZERO - show zeroed values (by default they are not shown).

Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/1601292670-1616-3-git-send-email-alan.maguire@oracle.com
---
 include/linux/btf.h |   36 ++
 kernel/bpf/btf.c    | 1007 +++++++++++++++++++++++++++++++++++++++++++++------
 2 files changed, 941 insertions(+), 102 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/btf.h b/include/linux/btf.h
index a9af5e7a7ece..d0f5d3c9ec3d 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -13,6 +13,7 @@ struct btf;
 struct btf_member;
 struct btf_type;
 union bpf_attr;
+struct btf_show;
 
 extern const struct file_operations btf_fops;
 
@@ -46,8 +47,43 @@ int btf_get_info_by_fd(const struct btf *btf,
 const struct btf_type *btf_type_id_size(const struct btf *btf,
 					u32 *type_id,
 					u32 *ret_size);
+
+/*
+ * Options to control show behaviour.
+ *	- BTF_SHOW_COMPACT: no formatting around type information
+ *	- BTF_SHOW_NONAME: no struct/union member names/types
+ *	- BTF_SHOW_PTR_RAW: show raw (unobfuscated) pointer values;
+ *	  equivalent to %px.
+ *	- BTF_SHOW_ZERO: show zero-valued struct/union members; they
+ *	  are not displayed by default
+ *	- BTF_SHOW_UNSAFE: skip use of bpf_probe_read() to safely read
+ *	  data before displaying it.
+ */
+#define BTF_SHOW_COMPACT	(1ULL << 0)
+#define BTF_SHOW_NONAME		(1ULL << 1)
+#define BTF_SHOW_PTR_RAW	(1ULL << 2)
+#define BTF_SHOW_ZERO		(1ULL << 3)
+#define BTF_SHOW_UNSAFE		(1ULL << 4)
+
 void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
 		       struct seq_file *m);
+
+/*
+ * Copy len bytes of string representation of obj of BTF type_id into buf.
+ *
+ * @btf: struct btf object
+ * @type_id: type id of type obj points to
+ * @obj: pointer to typed data
+ * @buf: buffer to write to
+ * @len: maximum length to write to buf
+ * @flags: show options (see above)
+ *
+ * Return: length that would have been/was copied as per snprintf, or
+ *	   negative error.
+ */
+int btf_type_snprintf_show(const struct btf *btf, u32 type_id, void *obj,
+			   char *buf, int len, u64 flags);
+
 int btf_get_fd_by_id(u32 id);
 u32 btf_id(const struct btf *btf);
 bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 868c03a24d0a..dcdd7109aa29 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -284,6 +284,91 @@ static const char *btf_type_str(const struct btf_type *t)
 	return btf_kind_str[BTF_INFO_KIND(t->info)];
 }
 
+/* Chunk size we use in safe copy of data to be shown. */
+#define BTF_SHOW_OBJ_SAFE_SIZE		32
+
+/*
+ * This is the maximum size of a base type value (equivalent to a
+ * 128-bit int); if we are at the end of our safe buffer and have
+ * less than 16 bytes space we can't be assured of being able
+ * to copy the next type safely, so in such cases we will initiate
+ * a new copy.
+ */
+#define BTF_SHOW_OBJ_BASE_TYPE_SIZE	16
+
+/* Type name size */
+#define BTF_SHOW_NAME_SIZE		80
+
+/*
+ * Common data to all BTF show operations. Private show functions can add
+ * their own data to a structure containing a struct btf_show and consult it
+ * in the show callback.  See btf_type_show() below.
+ *
+ * One challenge with showing nested data is we want to skip 0-valued
+ * data, but in order to figure out whether a nested object is all zeros
+ * we need to walk through it.  As a result, we need to make two passes
+ * when handling structs, unions and arrays; the first path simply looks
+ * for nonzero data, while the second actually does the display.  The first
+ * pass is signalled by show->state.depth_check being set, and if we
+ * encounter a non-zero value we set show->state.depth_to_show to
+ * the depth at which we encountered it.  When we have completed the
+ * first pass, we will know if anything needs to be displayed if
+ * depth_to_show > depth.  See btf_[struct,array]_show() for the
+ * implementation of this.
+ *
+ * Another problem is we want to ensure the data for display is safe to
+ * access.  To support this, the anonymous "struct {} obj" tracks the data
+ * object and our safe copy of it.  We copy portions of the data needed
+ * to the object "copy" buffer, but because its size is limited to
+ * BTF_SHOW_OBJ_COPY_LEN bytes, multiple copies may be required as we
+ * traverse larger objects for display.
+ *
+ * The various data type show functions all start with a call to
+ * btf_show_start_type() which returns a pointer to the safe copy
+ * of the data needed (or if BTF_SHOW_UNSAFE is specified, to the
+ * raw data itself).  btf_show_obj_safe() is responsible for
+ * using copy_from_kernel_nofault() to update the safe data if necessary
+ * as we traverse the object's data.  skbuff-like semantics are
+ * used:
+ *
+ * - obj.head points to the start of the toplevel object for display
+ * - obj.size is the size of the toplevel object
+ * - obj.data points to the current point in the original data at
+ *   which our safe data starts.  obj.data will advance as we copy
+ *   portions of the data.
+ *
+ * In most cases a single copy will suffice, but larger data structures
+ * such as "struct task_struct" will require many copies.  The logic in
+ * btf_show_obj_safe() handles the logic that determines if a new
+ * copy_from_kernel_nofault() is needed.
+ */
+struct btf_show {
+	u64 flags;
+	void *target;	/* target of show operation (seq file, buffer) */
+	void (*showfn)(struct btf_show *show, const char *fmt, va_list args);
+	const struct btf *btf;
+	/* below are used during iteration */
+	struct {
+		u8 depth;
+		u8 depth_to_show;
+		u8 depth_check;
+		u8 array_member:1,
+		   array_terminated:1;
+		u16 array_encoding;
+		u32 type_id;
+		int status;			/* non-zero for error */
+		const struct btf_type *type;
+		const struct btf_member *member;
+		char name[BTF_SHOW_NAME_SIZE];	/* space for member name/type */
+	} state;
+	struct {
+		u32 size;
+		void *head;
+		void *data;
+		u8 safe[BTF_SHOW_OBJ_SAFE_SIZE];
+	} obj;
+};
+
 struct btf_kind_operations {
 	s32 (*check_meta)(struct btf_verifier_env *env,
 			  const struct btf_type *t,
@@ -300,9 +385,9 @@ struct btf_kind_operations {
 				  const struct btf_type *member_type);
 	void (*log_details)(struct btf_verifier_env *env,
 			    const struct btf_type *t);
-	void (*seq_show)(const struct btf *btf, const struct btf_type *t,
+	void (*show)(const struct btf *btf, const struct btf_type *t,
 			 u32 type_id, void *data, u8 bits_offsets,
-			 struct seq_file *m);
+			 struct btf_show *show);
 };
 
 static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS];
@@ -679,6 +764,488 @@ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
 	return true;
 }
 
+/* Similar to btf_type_skip_modifiers() but does not skip typedefs. */
+static const struct btf_type *btf_type_skip_qualifiers(const struct btf *btf,
+						       u32 id)
+{
+	const struct btf_type *t = btf_type_by_id(btf, id);
+
+	while (btf_type_is_modifier(t) &&
+	       BTF_INFO_KIND(t->info) != BTF_KIND_TYPEDEF) {
+		id = t->type;
+		t = btf_type_by_id(btf, t->type);
+	}
+
+	return t;
+}
+
+#define BTF_SHOW_MAX_ITER	10
+
+#define BTF_KIND_BIT(kind)	(1ULL << kind)
+
+/*
+ * Populate show->state.name with type name information.
+ * Format of type name is
+ *
+ * [.member_name = ] (type_name)
+ */
+static const char *btf_show_name(struct btf_show *show)
+{
+	/* BTF_MAX_ITER array suffixes "[]" */
+	const char *array_suffixes = "[][][][][][][][][][]";
+	const char *array_suffix = &array_suffixes[strlen(array_suffixes)];
+	/* BTF_MAX_ITER pointer suffixes "*" */
+	const char *ptr_suffixes = "**********";
+	const char *ptr_suffix = &ptr_suffixes[strlen(ptr_suffixes)];
+	const char *name = NULL, *prefix = "", *parens = "";
+	const struct btf_member *m = show->state.member;
+	const struct btf_type *t = show->state.type;
+	const struct btf_array *array;
+	u32 id = show->state.type_id;
+	const char *member = NULL;
+	bool show_member = false;
+	u64 kinds = 0;
+	int i;
+
+	show->state.name[0] = '\0';
+
+	/*
+	 * Don't show type name if we're showing an array member;
+	 * in that case we show the array type so don't need to repeat
+	 * ourselves for each member.
+	 */
+	if (show->state.array_member)
+		return "";
+
+	/* Retrieve member name, if any. */
+	if (m) {
+		member = btf_name_by_offset(show->btf, m->name_off);
+		show_member = strlen(member) > 0;
+		id = m->type;
+	}
+
+	/*
+	 * Start with type_id, as we have resolved the struct btf_type *
+	 * via btf_modifier_show() past the parent typedef to the child
+	 * struct, int etc it is defined as.  In such cases, the type_id
+	 * still represents the starting type while the struct btf_type *
+	 * in our show->state points at the resolved type of the typedef.
+	 */
+	t = btf_type_by_id(show->btf, id);
+	if (!t)
+		return "";
+
+	/*
+	 * The goal here is to build up the right number of pointer and
+	 * array suffixes while ensuring the type name for a typedef
+	 * is represented.  Along the way we accumulate a list of
+	 * BTF kinds we have encountered, since these will inform later
+	 * display; for example, pointer types will not require an
+	 * opening "{" for struct, we will just display the pointer value.
+	 *
+	 * We also want to accumulate the right number of pointer or array
+	 * indices in the format string while iterating until we get to
+	 * the typedef/pointee/array member target type.
+	 *
+	 * We start by pointing at the end of pointer and array suffix
+	 * strings; as we accumulate pointers and arrays we move the pointer
+	 * or array string backwards so it will show the expected number of
+	 * '*' or '[]' for the type.  BTF_SHOW_MAX_ITER of nesting of pointers
+	 * and/or arrays and typedefs are supported as a precaution.
+	 *
+	 * We also want to get typedef name while proceeding to resolve
+	 * type it points to so that we can add parentheses if it is a
+	 * "typedef struct" etc.
+	 */
+	for (i = 0; i < BTF_SHOW_MAX_ITER; i++) {
+
+		switch (BTF_INFO_KIND(t->info)) {
+		case BTF_KIND_TYPEDEF:
+			if (!name)
+				name = btf_name_by_offset(show->btf,
+							       t->name_off);
+			kinds |= BTF_KIND_BIT(BTF_KIND_TYPEDEF);
+			id = t->type;
+			break;
+		case BTF_KIND_ARRAY:
+			kinds |= BTF_KIND_BIT(BTF_KIND_ARRAY);
+			parens = "[";
+			if (!t)
+				return "";
+			array = btf_type_array(t);
+			if (array_suffix > array_suffixes)
+				array_suffix -= 2;
+			id = array->type;
+			break;
+		case BTF_KIND_PTR:
+			kinds |= BTF_KIND_BIT(BTF_KIND_PTR);
+			if (ptr_suffix > ptr_suffixes)
+				ptr_suffix -= 1;
+			id = t->type;
+			break;
+		default:
+			id = 0;
+			break;
+		}
+		if (!id)
+			break;
+		t = btf_type_skip_qualifiers(show->btf, id);
+	}
+	/* We may not be able to represent this type; bail to be safe */
+	if (i == BTF_SHOW_MAX_ITER)
+		return "";
+
+	if (!name)
+		name = btf_name_by_offset(show->btf, t->name_off);
+
+	switch (BTF_INFO_KIND(t->info)) {
+	case BTF_KIND_STRUCT:
+	case BTF_KIND_UNION:
+		prefix = BTF_INFO_KIND(t->info) == BTF_KIND_STRUCT ?
+			 "struct" : "union";
+		/* if it's an array of struct/union, parens is already set */
+		if (!(kinds & (BTF_KIND_BIT(BTF_KIND_ARRAY))))
+			parens = "{";
+		break;
+	case BTF_KIND_ENUM:
+		prefix = "enum";
+		break;
+	default:
+		break;
+	}
+
+	/* pointer does not require parens */
+	if (kinds & BTF_KIND_BIT(BTF_KIND_PTR))
+		parens = "";
+	/* typedef does not require struct/union/enum prefix */
+	if (kinds & BTF_KIND_BIT(BTF_KIND_TYPEDEF))
+		prefix = "";
+
+	if (!name)
+		name = "";
+
+	/* Even if we don't want type name info, we want parentheses etc */
+	if (show->flags & BTF_SHOW_NONAME)
+		snprintf(show->state.name, sizeof(show->state.name), "%s",
+			 parens);
+	else
+		snprintf(show->state.name, sizeof(show->state.name),
+			 "%s%s%s(%s%s%s%s%s%s)%s",
+			 /* first 3 strings comprise ".member = " */
+			 show_member ? "." : "",
+			 show_member ? member : "",
+			 show_member ? " = " : "",
+			 /* ...next is our prefix (struct, enum, etc) */
+			 prefix,
+			 strlen(prefix) > 0 && strlen(name) > 0 ? " " : "",
+			 /* ...this is the type name itself */
+			 name,
+			 /* ...suffixed by the appropriate '*', '[]' suffixes */
+			 strlen(ptr_suffix) > 0 ? " " : "", ptr_suffix,
+			 array_suffix, parens);
+
+	return show->state.name;
+}
+
+static const char *__btf_show_indent(struct btf_show *show)
+{
+	const char *indents = "                                ";
+	const char *indent = &indents[strlen(indents)];
+
+	if ((indent - show->state.depth) >= indents)
+		return indent - show->state.depth;
+	return indents;
+}
+
+static const char *btf_show_indent(struct btf_show *show)
+{
+	return show->flags & BTF_SHOW_COMPACT ? "" : __btf_show_indent(show);
+}
+
+static const char *btf_show_newline(struct btf_show *show)
+{
+	return show->flags & BTF_SHOW_COMPACT ? "" : "\n";
+}
+
+static const char *btf_show_delim(struct btf_show *show)
+{
+	if (show->state.depth == 0)
+		return "";
+
+	if ((show->flags & BTF_SHOW_COMPACT) && show->state.type &&
+		BTF_INFO_KIND(show->state.type->info) == BTF_KIND_UNION)
+		return "|";
+
+	return ",";
+}
+
+__printf(2, 3) static void btf_show(struct btf_show *show, const char *fmt, ...)
+{
+	va_list args;
+
+	if (!show->state.depth_check) {
+		va_start(args, fmt);
+		show->showfn(show, fmt, args);
+		va_end(args);
+	}
+}
+
+/* Macros are used here as btf_show_type_value[s]() prepends and appends
+ * format specifiers to the format specifier passed in; these do the work of
+ * adding indentation, delimiters etc while the caller simply has to specify
+ * the type value(s) in the format specifier + value(s).
+ */
+#define btf_show_type_value(show, fmt, value)				       \
+	do {								       \
+		if ((value) != 0 || (show->flags & BTF_SHOW_ZERO) ||	       \
+		    show->state.depth == 0) {				       \
+			btf_show(show, "%s%s" fmt "%s%s",		       \
+				 btf_show_indent(show),			       \
+				 btf_show_name(show),			       \
+				 value, btf_show_delim(show),		       \
+				 btf_show_newline(show));		       \
+			if (show->state.depth > show->state.depth_to_show)     \
+				show->state.depth_to_show = show->state.depth; \
+		}							       \
+	} while (0)
+
+#define btf_show_type_values(show, fmt, ...)				       \
+	do {								       \
+		btf_show(show, "%s%s" fmt "%s%s", btf_show_indent(show),       \
+			 btf_show_name(show),				       \
+			 __VA_ARGS__, btf_show_delim(show),		       \
+			 btf_show_newline(show));			       \
+		if (show->state.depth > show->state.depth_to_show)	       \
+			show->state.depth_to_show = show->state.depth;	       \
+	} while (0)
+
+/* How much is left to copy to safe buffer after @data? */
+static int btf_show_obj_size_left(struct btf_show *show, void *data)
+{
+	return show->obj.head + show->obj.size - data;
+}
+
+/* Is object pointed to by @data of @size already copied to our safe buffer? */
+static bool btf_show_obj_is_safe(struct btf_show *show, void *data, int size)
+{
+	return data >= show->obj.data &&
+	       (data + size) < (show->obj.data + BTF_SHOW_OBJ_SAFE_SIZE);
+}
+
+/*
+ * If object pointed to by @data of @size falls within our safe buffer, return
+ * the equivalent pointer to the same safe data.  Assumes
+ * copy_from_kernel_nofault() has already happened and our safe buffer is
+ * populated.
+ */
+static void *__btf_show_obj_safe(struct btf_show *show, void *data, int size)
+{
+	if (btf_show_obj_is_safe(show, data, size))
+		return show->obj.safe + (data - show->obj.data);
+	return NULL;
+}
+
+/*
+ * Return a safe-to-access version of data pointed to by @data.
+ * We do this by copying the relevant amount of information
+ * to the struct btf_show obj.safe buffer using copy_from_kernel_nofault().
+ *
+ * If BTF_SHOW_UNSAFE is specified, just return data as-is; no
+ * safe copy is needed.
+ *
+ * Otherwise we need to determine if we have the required amount
+ * of data (determined by the @data pointer and the size of the
+ * largest base type we can encounter (represented by
+ * BTF_SHOW_OBJ_BASE_TYPE_SIZE). Having that much data ensures
+ * that we will be able to print some of the current object,
+ * and if more is needed a copy will be triggered.
+ * Some objects such as structs will not fit into the buffer;
+ * in such cases additional copies when we iterate over their
+ * members may be needed.
+ *
+ * btf_show_obj_safe() is used to return a safe buffer for
+ * btf_show_start_type(); this ensures that as we recurse into
+ * nested types we always have safe data for the given type.
+ * This approach is somewhat wasteful; it's possible for example
+ * that when iterating over a large union we'll end up copying the
+ * same data repeatedly, but the goal is safety not performance.
+ * We use stack data as opposed to per-CPU buffers because the
+ * iteration over a type can take some time, and preemption handling
+ * would greatly complicate use of the safe buffer.
+ */
+static void *btf_show_obj_safe(struct btf_show *show,
+			       const struct btf_type *t,
+			       void *data)
+{
+	const struct btf_type *rt;
+	int size_left, size;
+	void *safe = NULL;
+
+	if (show->flags & BTF_SHOW_UNSAFE)
+		return data;
+
+	rt = btf_resolve_size(show->btf, t, &size);
+	if (IS_ERR(rt)) {
+		show->state.status = PTR_ERR(rt);
+		return NULL;
+	}
+
+	/*
+	 * Is this toplevel object? If so, set total object size and
+	 * initialize pointers.  Otherwise check if we still fall within
+	 * our safe object data.
+	 */
+	if (show->state.depth == 0) {
+		show->obj.size = size;
+		show->obj.head = data;
+	} else {
+		/*
+		 * If the size of the current object is > our remaining
+		 * safe buffer we _may_ need to do a new copy.  However
+		 * consider the case of a nested struct; it's size pushes
+		 * us over the safe buffer limit, but showing any individual
+		 * struct members does not.  In such cases, we don't need
+		 * to initiate a fresh copy yet; however we definitely need
+		 * at least BTF_SHOW_OBJ_BASE_TYPE_SIZE bytes left
+		 * in our buffer, regardless of the current object size.
+		 * The logic here is that as we resolve types we will
+		 * hit a base type at some point, and we need to be sure
+		 * the next chunk of data is safely available to display
+		 * that type info safely.  We cannot rely on the size of
+		 * the current object here because it may be much larger
+		 * than our current buffer (e.g. task_struct is 8k).
+		 * All we want to do here is ensure that we can print the
+		 * next basic type, which we can if either
+		 * - the current type size is within the safe buffer; or
+		 * - at least BTF_SHOW_OBJ_BASE_TYPE_SIZE bytes are left in
+		 *   the safe buffer.
+		 */
+		safe = __btf_show_obj_safe(show, data,
+					   min(size,
+					       BTF_SHOW_OBJ_BASE_TYPE_SIZE));
+	}
+
+	/*
+	 * We need a new copy to our safe object, either because we haven't
+	 * yet copied and are intializing safe data, or because the data
+	 * we want falls outside the boundaries of the safe object.
+	 */
+	if (!safe) {
+		size_left = btf_show_obj_size_left(show, data);
+		if (size_left > BTF_SHOW_OBJ_SAFE_SIZE)
+			size_left = BTF_SHOW_OBJ_SAFE_SIZE;
+		show->state.status = copy_from_kernel_nofault(show->obj.safe,
+							      data, size_left);
+		if (!show->state.status) {
+			show->obj.data = data;
+			safe = show->obj.safe;
+		}
+	}
+
+	return safe;
+}
+
+/*
+ * Set the type we are starting to show and return a safe data pointer
+ * to be used for showing the associated data.
+ */
+static void *btf_show_start_type(struct btf_show *show,
+				 const struct btf_type *t,
+				 u32 type_id, void *data)
+{
+	show->state.type = t;
+	show->state.type_id = type_id;
+	show->state.name[0] = '\0';
+
+	return btf_show_obj_safe(show, t, data);
+}
+
+static void btf_show_end_type(struct btf_show *show)
+{
+	show->state.type = NULL;
+	show->state.type_id = 0;
+	show->state.name[0] = '\0';
+}
+
+static void *btf_show_start_aggr_type(struct btf_show *show,
+				      const struct btf_type *t,
+				      u32 type_id, void *data)
+{
+	void *safe_data = btf_show_start_type(show, t, type_id, data);
+
+	if (!safe_data)
+		return safe_data;
+
+	btf_show(show, "%s%s%s", btf_show_indent(show),
+		 btf_show_name(show),
+		 btf_show_newline(show));
+	show->state.depth++;
+	return safe_data;
+}
+
+static void btf_show_end_aggr_type(struct btf_show *show,
+				   const char *suffix)
+{
+	show->state.depth--;
+	btf_show(show, "%s%s%s%s", btf_show_indent(show), suffix,
+		 btf_show_delim(show), btf_show_newline(show));
+	btf_show_end_type(show);
+}
+
+static void btf_show_start_member(struct btf_show *show,
+				  const struct btf_member *m)
+{
+	show->state.member = m;
+}
+
+static void btf_show_start_array_member(struct btf_show *show)
+{
+	show->state.array_member = 1;
+	btf_show_start_member(show, NULL);
+}
+
+static void btf_show_end_member(struct btf_show *show)
+{
+	show->state.member = NULL;
+}
+
+static void btf_show_end_array_member(struct btf_show *show)
+{
+	show->state.array_member = 0;
+	btf_show_end_member(show);
+}
+
+static void *btf_show_start_array_type(struct btf_show *show,
+				       const struct btf_type *t,
+				       u32 type_id,
+				       u16 array_encoding,
+				       void *data)
+{
+	show->state.array_encoding = array_encoding;
+	show->state.array_terminated = 0;
+	return btf_show_start_aggr_type(show, t, type_id, data);
+}
+
+static void btf_show_end_array_type(struct btf_show *show)
+{
+	show->state.array_encoding = 0;
+	show->state.array_terminated = 0;
+	btf_show_end_aggr_type(show, "]");
+}
+
+static void *btf_show_start_struct_type(struct btf_show *show,
+					const struct btf_type *t,
+					u32 type_id,
+					void *data)
+{
+	return btf_show_start_aggr_type(show, t, type_id, data);
+}
+
+static void btf_show_end_struct_type(struct btf_show *show)
+{
+	btf_show_end_aggr_type(show, "}");
+}
+
 __printf(2, 3) static void __btf_verifier_log(struct bpf_verifier_log *log,
 					      const char *fmt, ...)
 {
@@ -1268,11 +1835,11 @@ static int btf_df_resolve(struct btf_verifier_env *env,
 	return -EINVAL;
 }
 
-static void btf_df_seq_show(const struct btf *btf, const struct btf_type *t,
-			    u32 type_id, void *data, u8 bits_offsets,
-			    struct seq_file *m)
+static void btf_df_show(const struct btf *btf, const struct btf_type *t,
+			u32 type_id, void *data, u8 bits_offsets,
+			struct btf_show *show)
 {
-	seq_printf(m, "<unsupported kind:%u>", BTF_INFO_KIND(t->info));
+	btf_show(show, "<unsupported kind:%u>", BTF_INFO_KIND(t->info));
 }
 
 static int btf_int_check_member(struct btf_verifier_env *env,
@@ -1445,7 +2012,7 @@ static void btf_int_log(struct btf_verifier_env *env,
 			 btf_int_encoding_str(BTF_INT_ENCODING(int_data)));
 }
 
-static void btf_int128_print(struct seq_file *m, void *data)
+static void btf_int128_print(struct btf_show *show, void *data)
 {
 	/* data points to a __int128 number.
 	 * Suppose
@@ -1464,9 +2031,10 @@ static void btf_int128_print(struct seq_file *m, void *data)
 	lower_num = *(u64 *)data;
 #endif
 	if (upper_num == 0)
-		seq_printf(m, "0x%llx", lower_num);
+		btf_show_type_value(show, "0x%llx", lower_num);
 	else
-		seq_printf(m, "0x%llx%016llx", upper_num, lower_num);
+		btf_show_type_values(show, "0x%llx%016llx", upper_num,
+				     lower_num);
 }
 
 static void btf_int128_shift(u64 *print_num, u16 left_shift_bits,
@@ -1510,8 +2078,8 @@ static void btf_int128_shift(u64 *print_num, u16 left_shift_bits,
 #endif
 }
 
-static void btf_bitfield_seq_show(void *data, u8 bits_offset,
-				  u8 nr_bits, struct seq_file *m)
+static void btf_bitfield_show(void *data, u8 bits_offset,
+			      u8 nr_bits, struct btf_show *show)
 {
 	u16 left_shift_bits, right_shift_bits;
 	u8 nr_copy_bytes;
@@ -1531,14 +2099,14 @@ static void btf_bitfield_seq_show(void *data, u8 bits_offset,
 	right_shift_bits = BITS_PER_U128 - nr_bits;
 
 	btf_int128_shift(print_num, left_shift_bits, right_shift_bits);
-	btf_int128_print(m, print_num);
+	btf_int128_print(show, print_num);
 }
 
 
-static void btf_int_bits_seq_show(const struct btf *btf,
-				  const struct btf_type *t,
-				  void *data, u8 bits_offset,
-				  struct seq_file *m)
+static void btf_int_bits_show(const struct btf *btf,
+			      const struct btf_type *t,
+			      void *data, u8 bits_offset,
+			      struct btf_show *show)
 {
 	u32 int_data = btf_type_int(t);
 	u8 nr_bits = BTF_INT_BITS(int_data);
@@ -1551,55 +2119,77 @@ static void btf_int_bits_seq_show(const struct btf *btf,
 	total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data);
 	data += BITS_ROUNDDOWN_BYTES(total_bits_offset);
 	bits_offset = BITS_PER_BYTE_MASKED(total_bits_offset);
-	btf_bitfield_seq_show(data, bits_offset, nr_bits, m);
+	btf_bitfield_show(data, bits_offset, nr_bits, show);
 }
 
-static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t,
-			     u32 type_id, void *data, u8 bits_offset,
-			     struct seq_file *m)
+static void btf_int_show(const struct btf *btf, const struct btf_type *t,
+			 u32 type_id, void *data, u8 bits_offset,
+			 struct btf_show *show)
 {
 	u32 int_data = btf_type_int(t);
 	u8 encoding = BTF_INT_ENCODING(int_data);
 	bool sign = encoding & BTF_INT_SIGNED;
 	u8 nr_bits = BTF_INT_BITS(int_data);
+	void *safe_data;
+
+	safe_data = btf_show_start_type(show, t, type_id, data);
+	if (!safe_data)
+		return;
 
 	if (bits_offset || BTF_INT_OFFSET(int_data) ||
 	    BITS_PER_BYTE_MASKED(nr_bits)) {
-		btf_int_bits_seq_show(btf, t, data, bits_offset, m);
-		return;
+		btf_int_bits_show(btf, t, safe_data, bits_offset, show);
+		goto out;
 	}
 
 	switch (nr_bits) {
 	case 128:
-		btf_int128_print(m, data);
+		btf_int128_print(show, safe_data);
 		break;
 	case 64:
 		if (sign)
-			seq_printf(m, "%lld", *(s64 *)data);
+			btf_show_type_value(show, "%lld", *(s64 *)safe_data);
 		else
-			seq_printf(m, "%llu", *(u64 *)data);
+			btf_show_type_value(show, "%llu", *(u64 *)safe_data);
 		break;
 	case 32:
 		if (sign)
-			seq_printf(m, "%d", *(s32 *)data);
+			btf_show_type_value(show, "%d", *(s32 *)safe_data);
 		else
-			seq_printf(m, "%u", *(u32 *)data);
+			btf_show_type_value(show, "%u", *(u32 *)safe_data);
 		break;
 	case 16:
 		if (sign)
-			seq_printf(m, "%d", *(s16 *)data);
+			btf_show_type_value(show, "%d", *(s16 *)safe_data);
 		else
-			seq_printf(m, "%u", *(u16 *)data);
+			btf_show_type_value(show, "%u", *(u16 *)safe_data);
 		break;
 	case 8:
+		if (show->state.array_encoding == BTF_INT_CHAR) {
+			/* check for null terminator */
+			if (show->state.array_terminated)
+				break;
+			if (*(char *)data == '\0') {
+				show->state.array_terminated = 1;
+				break;
+			}
+			if (isprint(*(char *)data)) {
+				btf_show_type_value(show, "'%c'",
+						    *(char *)safe_data);
+				break;
+			}
+		}
 		if (sign)
-			seq_printf(m, "%d", *(s8 *)data);
+			btf_show_type_value(show, "%d", *(s8 *)safe_data);
 		else
-			seq_printf(m, "%u", *(u8 *)data);
+			btf_show_type_value(show, "%u", *(u8 *)safe_data);
 		break;
 	default:
-		btf_int_bits_seq_show(btf, t, data, bits_offset, m);
+		btf_int_bits_show(btf, t, safe_data, bits_offset, show);
+		break;
 	}
+out:
+	btf_show_end_type(show);
 }
 
 static const struct btf_kind_operations int_ops = {
@@ -1608,7 +2198,7 @@ static const struct btf_kind_operations int_ops = {
 	.check_member = btf_int_check_member,
 	.check_kflag_member = btf_int_check_kflag_member,
 	.log_details = btf_int_log,
-	.seq_show = btf_int_seq_show,
+	.show = btf_int_show,
 };
 
 static int btf_modifier_check_member(struct btf_verifier_env *env,
@@ -1872,34 +2462,44 @@ static int btf_ptr_resolve(struct btf_verifier_env *env,
 	return 0;
 }
 
-static void btf_modifier_seq_show(const struct btf *btf,
-				  const struct btf_type *t,
-				  u32 type_id, void *data,
-				  u8 bits_offset, struct seq_file *m)
+static void btf_modifier_show(const struct btf *btf,
+			      const struct btf_type *t,
+			      u32 type_id, void *data,
+			      u8 bits_offset, struct btf_show *show)
 {
 	if (btf->resolved_ids)
 		t = btf_type_id_resolve(btf, &type_id);
 	else
 		t = btf_type_skip_modifiers(btf, type_id, NULL);
 
-	btf_type_ops(t)->seq_show(btf, t, type_id, data, bits_offset, m);
+	btf_type_ops(t)->show(btf, t, type_id, data, bits_offset, show);
 }
 
-static void btf_var_seq_show(const struct btf *btf, const struct btf_type *t,
-			     u32 type_id, void *data, u8 bits_offset,
-			     struct seq_file *m)
+static void btf_var_show(const struct btf *btf, const struct btf_type *t,
+			 u32 type_id, void *data, u8 bits_offset,
+			 struct btf_show *show)
 {
 	t = btf_type_id_resolve(btf, &type_id);
 
-	btf_type_ops(t)->seq_show(btf, t, type_id, data, bits_offset, m);
+	btf_type_ops(t)->show(btf, t, type_id, data, bits_offset, show);
 }
 
-static void btf_ptr_seq_show(const struct btf *btf, const struct btf_type *t,
-			     u32 type_id, void *data, u8 bits_offset,
-			     struct seq_file *m)
+static void btf_ptr_show(const struct btf *btf, const struct btf_type *t,
+			 u32 type_id, void *data, u8 bits_offset,
+			 struct btf_show *show)
 {
-	/* It is a hashed value */
-	seq_printf(m, "%p", *(void **)data);
+	void *safe_data;
+
+	safe_data = btf_show_start_type(show, t, type_id, data);
+	if (!safe_data)
+		return;
+
+	/* It is a hashed value unless BTF_SHOW_PTR_RAW is specified */
+	if (show->flags & BTF_SHOW_PTR_RAW)
+		btf_show_type_value(show, "0x%px", *(void **)safe_data);
+	else
+		btf_show_type_value(show, "0x%p", *(void **)safe_data);
+	btf_show_end_type(show);
 }
 
 static void btf_ref_type_log(struct btf_verifier_env *env,
@@ -1914,7 +2514,7 @@ static struct btf_kind_operations modifier_ops = {
 	.check_member = btf_modifier_check_member,
 	.check_kflag_member = btf_modifier_check_kflag_member,
 	.log_details = btf_ref_type_log,
-	.seq_show = btf_modifier_seq_show,
+	.show = btf_modifier_show,
 };
 
 static struct btf_kind_operations ptr_ops = {
@@ -1923,7 +2523,7 @@ static struct btf_kind_operations ptr_ops = {
 	.check_member = btf_ptr_check_member,
 	.check_kflag_member = btf_generic_check_kflag_member,
 	.log_details = btf_ref_type_log,
-	.seq_show = btf_ptr_seq_show,
+	.show = btf_ptr_show,
 };
 
 static s32 btf_fwd_check_meta(struct btf_verifier_env *env,
@@ -1964,7 +2564,7 @@ static struct btf_kind_operations fwd_ops = {
 	.check_member = btf_df_check_member,
 	.check_kflag_member = btf_df_check_kflag_member,
 	.log_details = btf_fwd_type_log,
-	.seq_show = btf_df_seq_show,
+	.show = btf_df_show,
 };
 
 static int btf_array_check_member(struct btf_verifier_env *env,
@@ -2123,28 +2723,90 @@ static void btf_array_log(struct btf_verifier_env *env,
 			 array->type, array->index_type, array->nelems);
 }
 
-static void btf_array_seq_show(const struct btf *btf, const struct btf_type *t,
-			       u32 type_id, void *data, u8 bits_offset,
-			       struct seq_file *m)
+static void __btf_array_show(const struct btf *btf, const struct btf_type *t,
+			     u32 type_id, void *data, u8 bits_offset,
+			     struct btf_show *show)
 {
 	const struct btf_array *array = btf_type_array(t);
 	const struct btf_kind_operations *elem_ops;
 	const struct btf_type *elem_type;
-	u32 i, elem_size, elem_type_id;
+	u32 i, elem_size = 0, elem_type_id;
+	u16 encoding = 0;
 
 	elem_type_id = array->type;
-	elem_type = btf_type_id_size(btf, &elem_type_id, &elem_size);
+	elem_type = btf_type_skip_modifiers(btf, elem_type_id, NULL);
+	if (elem_type && btf_type_has_size(elem_type))
+		elem_size = elem_type->size;
+
+	if (elem_type && btf_type_is_int(elem_type)) {
+		u32 int_type = btf_type_int(elem_type);
+
+		encoding = BTF_INT_ENCODING(int_type);
+
+		/*
+		 * BTF_INT_CHAR encoding never seems to be set for
+		 * char arrays, so if size is 1 and element is
+		 * printable as a char, we'll do that.
+		 */
+		if (elem_size == 1)
+			encoding = BTF_INT_CHAR;
+	}
+
+	if (!btf_show_start_array_type(show, t, type_id, encoding, data))
+		return;
+
+	if (!elem_type)
+		goto out;
 	elem_ops = btf_type_ops(elem_type);
-	seq_puts(m, "[");
+
 	for (i = 0; i < array->nelems; i++) {
-		if (i)
-			seq_puts(m, ",");
 
-		elem_ops->seq_show(btf, elem_type, elem_type_id, data,
-				   bits_offset, m);
+		btf_show_start_array_member(show);
+
+		elem_ops->show(btf, elem_type, elem_type_id, data,
+			       bits_offset, show);
 		data += elem_size;
+
+		btf_show_end_array_member(show);
+
+		if (show->state.array_terminated)
+			break;
 	}
-	seq_puts(m, "]");
+out:
+	btf_show_end_array_type(show);
+}
+
+static void btf_array_show(const struct btf *btf, const struct btf_type *t,
+			   u32 type_id, void *data, u8 bits_offset,
+			   struct btf_show *show)
+{
+	const struct btf_member *m = show->state.member;
+
+	/*
+	 * First check if any members would be shown (are non-zero).
+	 * See comments above "struct btf_show" definition for more
+	 * details on how this works at a high-level.
+	 */
+	if (show->state.depth > 0 && !(show->flags & BTF_SHOW_ZERO)) {
+		if (!show->state.depth_check) {
+			show->state.depth_check = show->state.depth + 1;
+			show->state.depth_to_show = 0;
+		}
+		__btf_array_show(btf, t, type_id, data, bits_offset, show);
+		show->state.member = m;
+
+		if (show->state.depth_check != show->state.depth + 1)
+			return;
+		show->state.depth_check = 0;
+
+		if (show->state.depth_to_show <= show->state.depth)
+			return;
+		/*
+		 * Reaching here indicates we have recursed and found
+		 * non-zero array member(s).
+		 */
+	}
+	__btf_array_show(btf, t, type_id, data, bits_offset, show);
 }
 
 static struct btf_kind_operations array_ops = {
@@ -2153,7 +2815,7 @@ static struct btf_kind_operations array_ops = {
 	.check_member = btf_array_check_member,
 	.check_kflag_member = btf_generic_check_kflag_member,
 	.log_details = btf_array_log,
-	.seq_show = btf_array_seq_show,
+	.show = btf_array_show,
 };
 
 static int btf_struct_check_member(struct btf_verifier_env *env,
@@ -2376,15 +3038,18 @@ int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t)
 	return off;
 }
 
-static void btf_struct_seq_show(const struct btf *btf, const struct btf_type *t,
-				u32 type_id, void *data, u8 bits_offset,
-				struct seq_file *m)
+static void __btf_struct_show(const struct btf *btf, const struct btf_type *t,
+			      u32 type_id, void *data, u8 bits_offset,
+			      struct btf_show *show)
 {
-	const char *seq = BTF_INFO_KIND(t->info) == BTF_KIND_UNION ? "|" : ",";
 	const struct btf_member *member;
+	void *safe_data;
 	u32 i;
 
-	seq_puts(m, "{");
+	safe_data = btf_show_start_struct_type(show, t, type_id, data);
+	if (!safe_data)
+		return;
+
 	for_each_member(i, t, member) {
 		const struct btf_type *member_type = btf_type_by_id(btf,
 								member->type);
@@ -2393,23 +3058,65 @@ static void btf_struct_seq_show(const struct btf *btf, const struct btf_type *t,
 		u32 bytes_offset;
 		u8 bits8_offset;
 
-		if (i)
-			seq_puts(m, seq);
+		btf_show_start_member(show, member);
 
 		member_offset = btf_member_bit_offset(t, member);
 		bitfield_size = btf_member_bitfield_size(t, member);
 		bytes_offset = BITS_ROUNDDOWN_BYTES(member_offset);
 		bits8_offset = BITS_PER_BYTE_MASKED(member_offset);
 		if (bitfield_size) {
-			btf_bitfield_seq_show(data + bytes_offset, bits8_offset,
-					      bitfield_size, m);
+			safe_data = btf_show_start_type(show, member_type,
+							member->type,
+							data + bytes_offset);
+			if (safe_data)
+				btf_bitfield_show(safe_data,
+						  bits8_offset,
+						  bitfield_size, show);
+			btf_show_end_type(show);
 		} else {
 			ops = btf_type_ops(member_type);
-			ops->seq_show(btf, member_type, member->type,
-				      data + bytes_offset, bits8_offset, m);
+			ops->show(btf, member_type, member->type,
+				  data + bytes_offset, bits8_offset, show);
 		}
+
+		btf_show_end_member(show);
 	}
-	seq_puts(m, "}");
+
+	btf_show_end_struct_type(show);
+}
+
+static void btf_struct_show(const struct btf *btf, const struct btf_type *t,
+			    u32 type_id, void *data, u8 bits_offset,
+			    struct btf_show *show)
+{
+	const struct btf_member *m = show->state.member;
+
+	/*
+	 * First check if any members would be shown (are non-zero).
+	 * See comments above "struct btf_show" definition for more
+	 * details on how this works at a high-level.
+	 */
+	if (show->state.depth > 0 && !(show->flags & BTF_SHOW_ZERO)) {
+		if (!show->state.depth_check) {
+			show->state.depth_check = show->state.depth + 1;
+			show->state.depth_to_show = 0;
+		}
+		__btf_struct_show(btf, t, type_id, data, bits_offset, show);
+		/* Restore saved member data here */
+		show->state.member = m;
+		if (show->state.depth_check != show->state.depth + 1)
+			return;
+		show->state.depth_check = 0;
+
+		if (show->state.depth_to_show <= show->state.depth)
+			return;
+		/*
+		 * Reaching here indicates we have recursed and found
+		 * non-zero child values.
+		 */
+	}
+
+	__btf_struct_show(btf, t, type_id, data, bits_offset, show);
 }
 
 static struct btf_kind_operations struct_ops = {
@@ -2418,7 +3125,7 @@ static struct btf_kind_operations struct_ops = {
 	.check_member = btf_struct_check_member,
 	.check_kflag_member = btf_generic_check_kflag_member,
 	.log_details = btf_struct_log,
-	.seq_show = btf_struct_seq_show,
+	.show = btf_struct_show,
 };
 
 static int btf_enum_check_member(struct btf_verifier_env *env,
@@ -2549,24 +3256,35 @@ static void btf_enum_log(struct btf_verifier_env *env,
 	btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t));
 }
 
-static void btf_enum_seq_show(const struct btf *btf, const struct btf_type *t,
-			      u32 type_id, void *data, u8 bits_offset,
-			      struct seq_file *m)
+static void btf_enum_show(const struct btf *btf, const struct btf_type *t,
+			  u32 type_id, void *data, u8 bits_offset,
+			  struct btf_show *show)
 {
 	const struct btf_enum *enums = btf_type_enum(t);
 	u32 i, nr_enums = btf_type_vlen(t);
-	int v = *(int *)data;
+	void *safe_data;
+	int v;
+
+	safe_data = btf_show_start_type(show, t, type_id, data);
+	if (!safe_data)
+		return;
+
+	v = *(int *)safe_data;
 
 	for (i = 0; i < nr_enums; i++) {
-		if (v == enums[i].val) {
-			seq_printf(m, "%s",
-				   __btf_name_by_offset(btf,
-							enums[i].name_off));
-			return;
-		}
+		if (v != enums[i].val)
+			continue;
+
+		btf_show_type_value(show, "%s",
+				    __btf_name_by_offset(btf,
+							 enums[i].name_off));
+
+		btf_show_end_type(show);
+		return;
 	}
 
-	seq_printf(m, "%d", v);
+	btf_show_type_value(show, "%d", v);
+	btf_show_end_type(show);
 }
 
 static struct btf_kind_operations enum_ops = {
@@ -2575,7 +3293,7 @@ static struct btf_kind_operations enum_ops = {
 	.check_member = btf_enum_check_member,
 	.check_kflag_member = btf_enum_check_kflag_member,
 	.log_details = btf_enum_log,
-	.seq_show = btf_enum_seq_show,
+	.show = btf_enum_show,
 };
 
 static s32 btf_func_proto_check_meta(struct btf_verifier_env *env,
@@ -2662,7 +3380,7 @@ static struct btf_kind_operations func_proto_ops = {
 	.check_member = btf_df_check_member,
 	.check_kflag_member = btf_df_check_kflag_member,
 	.log_details = btf_func_proto_log,
-	.seq_show = btf_df_seq_show,
+	.show = btf_df_show,
 };
 
 static s32 btf_func_check_meta(struct btf_verifier_env *env,
@@ -2696,7 +3414,7 @@ static struct btf_kind_operations func_ops = {
 	.check_member = btf_df_check_member,
 	.check_kflag_member = btf_df_check_kflag_member,
 	.log_details = btf_ref_type_log,
-	.seq_show = btf_df_seq_show,
+	.show = btf_df_show,
 };
 
 static s32 btf_var_check_meta(struct btf_verifier_env *env,
@@ -2760,7 +3478,7 @@ static const struct btf_kind_operations var_ops = {
 	.check_member		= btf_df_check_member,
 	.check_kflag_member	= btf_df_check_kflag_member,
 	.log_details		= btf_var_log,
-	.seq_show		= btf_var_seq_show,
+	.show			= btf_var_show,
 };
 
 static s32 btf_datasec_check_meta(struct btf_verifier_env *env,
@@ -2886,24 +3604,28 @@ static void btf_datasec_log(struct btf_verifier_env *env,
 	btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t));
 }
 
-static void btf_datasec_seq_show(const struct btf *btf,
-				 const struct btf_type *t, u32 type_id,
-				 void *data, u8 bits_offset,
-				 struct seq_file *m)
+static void btf_datasec_show(const struct btf *btf,
+			     const struct btf_type *t, u32 type_id,
+			     void *data, u8 bits_offset,
+			     struct btf_show *show)
 {
 	const struct btf_var_secinfo *vsi;
 	const struct btf_type *var;
 	u32 i;
 
-	seq_printf(m, "section (\"%s\") = {", __btf_name_by_offset(btf, t->name_off));
+	if (!btf_show_start_type(show, t, type_id, data))
+		return;
+
+	btf_show_type_value(show, "section (\"%s\") = {",
+			    __btf_name_by_offset(btf, t->name_off));
 	for_each_vsi(i, t, vsi) {
 		var = btf_type_by_id(btf, vsi->type);
 		if (i)
-			seq_puts(m, ",");
-		btf_type_ops(var)->seq_show(btf, var, vsi->type,
-					    data + vsi->offset, bits_offset, m);
+			btf_show(show, ",");
+		btf_type_ops(var)->show(btf, var, vsi->type,
+					data + vsi->offset, bits_offset, show);
 	}
-	seq_puts(m, "}");
+	btf_show_end_type(show);
 }
 
 static const struct btf_kind_operations datasec_ops = {
@@ -2912,7 +3634,7 @@ static const struct btf_kind_operations datasec_ops = {
 	.check_member		= btf_df_check_member,
 	.check_kflag_member	= btf_df_check_kflag_member,
 	.log_details		= btf_datasec_log,
-	.seq_show		= btf_datasec_seq_show,
+	.show			= btf_datasec_show,
 };
 
 static int btf_func_proto_check(struct btf_verifier_env *env,
@@ -4606,12 +5328,93 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
 	return 0;
 }
 
+static void btf_type_show(const struct btf *btf, u32 type_id, void *obj,
+			  struct btf_show *show)
+{
+	const struct btf_type *t = btf_type_by_id(btf, type_id);
+
+	show->btf = btf;
+	memset(&show->state, 0, sizeof(show->state));
+	memset(&show->obj, 0, sizeof(show->obj));
+
+	btf_type_ops(t)->show(btf, t, type_id, obj, 0, show);
+}
+
+static void btf_seq_show(struct btf_show *show, const char *fmt,
+			 va_list args)
+{
+	seq_vprintf((struct seq_file *)show->target, fmt, args);
+}
+
+static int btf_type_seq_show_flags(const struct btf *btf, u32 type_id,
+				   void *obj, struct seq_file *m, u64 flags)
+{
+	struct btf_show sseq;
+
+	sseq.target = m;
+	sseq.showfn = btf_seq_show;
+	sseq.flags = flags;
+
+	btf_type_show(btf, type_id, obj, &sseq);
+
+	return sseq.state.status;
+}
+
 void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
 		       struct seq_file *m)
 {
-	const struct btf_type *t = btf_type_by_id(btf, type_id);
+	(void) btf_type_seq_show_flags(btf, type_id, obj, m,
+				       BTF_SHOW_NONAME | BTF_SHOW_COMPACT |
+				       BTF_SHOW_ZERO | BTF_SHOW_UNSAFE);
+}
+
+struct btf_show_snprintf {
+	struct btf_show show;
+	int len_left;		/* space left in string */
+	int len;		/* length we would have written */
+};
+
+static void btf_snprintf_show(struct btf_show *show, const char *fmt,
+			      va_list args)
+{
+	struct btf_show_snprintf *ssnprintf = (struct btf_show_snprintf *)show;
+	int len;
+
+	len = vsnprintf(show->target, ssnprintf->len_left, fmt, args);
+
+	if (len < 0) {
+		ssnprintf->len_left = 0;
+		ssnprintf->len = len;
+	} else if (len > ssnprintf->len_left) {
+		/* no space, drive on to get length we would have written */
+		ssnprintf->len_left = 0;
+		ssnprintf->len += len;
+	} else {
+		ssnprintf->len_left -= len;
+		ssnprintf->len += len;
+		show->target += len;
+	}
+}
+
+int btf_type_snprintf_show(const struct btf *btf, u32 type_id, void *obj,
+			   char *buf, int len, u64 flags)
+{
+	struct btf_show_snprintf ssnprintf;
+
+	ssnprintf.show.target = buf;
+	ssnprintf.show.flags = flags;
+	ssnprintf.show.showfn = btf_snprintf_show;
+	ssnprintf.len_left = len;
+	ssnprintf.len = 0;
+
+	btf_type_show(btf, type_id, obj, (struct btf_show *)&ssnprintf);
+
+	/* If we encontered an error, return it. */
+	if (ssnprintf.show.state.status)
+		return ssnprintf.show.state.status;
 
-	btf_type_ops(t)->seq_show(btf, t, type_id, obj, 0, m);
+	/* Otherwise return length we would have written */
+	return ssnprintf.len;
 }
 
 #ifdef CONFIG_PROC_FS
-- 
cgit v1.2.3


From c4d0bfb45068d853a478b9067a95969b1886a30f Mon Sep 17 00:00:00 2001
From: Alan Maguire <alan.maguire@oracle.com>
Date: Mon, 28 Sep 2020 12:31:05 +0100
Subject: bpf: Add bpf_snprintf_btf helper

A helper is added to support tracing kernel type information in BPF
using the BPF Type Format (BTF).  Its signature is

long bpf_snprintf_btf(char *str, u32 str_size, struct btf_ptr *ptr,
		      u32 btf_ptr_size, u64 flags);

struct btf_ptr * specifies

- a pointer to the data to be traced
- the BTF id of the type of data pointed to
- a flags field is provided for future use; these flags
  are not to be confused with the BTF_F_* flags
  below that control how the btf_ptr is displayed; the
  flags member of the struct btf_ptr may be used to
  disambiguate types in kernel versus module BTF, etc;
  the main distinction is the flags relate to the type
  and information needed in identifying it; not how it
  is displayed.

For example a BPF program with a struct sk_buff *skb
could do the following:

	static struct btf_ptr b = { };

	b.ptr = skb;
	b.type_id = __builtin_btf_type_id(struct sk_buff, 1);
	bpf_snprintf_btf(str, sizeof(str), &b, sizeof(b), 0, 0);

Default output looks like this:

(struct sk_buff){
 .transport_header = (__u16)65535,
 .mac_header = (__u16)65535,
 .end = (sk_buff_data_t)192,
 .head = (unsigned char *)0x000000007524fd8b,
 .data = (unsigned char *)0x000000007524fd8b,
 .truesize = (unsigned int)768,
 .users = (refcount_t){
  .refs = (atomic_t){
   .counter = (int)1,
  },
 },
}

Flags modifying display are as follows:

- BTF_F_COMPACT:	no formatting around type information
- BTF_F_NONAME:		no struct/union member names/types
- BTF_F_PTR_RAW:	show raw (unobfuscated) pointer values;
			equivalent to %px.
- BTF_F_ZERO:		show zero-valued struct/union members;
			they are not displayed by default

Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/1601292670-1616-4-git-send-email-alan.maguire@oracle.com
---
 include/linux/bpf.h            |  1 +
 include/linux/btf.h            |  9 +++---
 include/uapi/linux/bpf.h       | 67 ++++++++++++++++++++++++++++++++++++++++++
 kernel/bpf/core.c              |  1 +
 kernel/bpf/helpers.c           |  4 +++
 kernel/trace/bpf_trace.c       | 65 ++++++++++++++++++++++++++++++++++++++++
 scripts/bpf_helpers_doc.py     |  2 ++
 tools/include/uapi/linux/bpf.h | 67 ++++++++++++++++++++++++++++++++++++++++++
 8 files changed, 212 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index e620a4b1290f..768b533ba48e 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1822,6 +1822,7 @@ extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto;
 extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto;
 extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto;
 extern const struct bpf_func_proto bpf_copy_from_user_proto;
+extern const struct bpf_func_proto bpf_snprintf_btf_proto;
 
 const struct bpf_func_proto *bpf_tracing_func_proto(
 	enum bpf_func_id func_id, const struct bpf_prog *prog);
diff --git a/include/linux/btf.h b/include/linux/btf.h
index d0f5d3c9ec3d..3e5cdc2ba963 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -6,6 +6,7 @@
 
 #include <linux/types.h>
 #include <uapi/linux/btf.h>
+#include <uapi/linux/bpf.h>
 
 #define BTF_TYPE_EMIT(type) ((void)(type *)0)
 
@@ -59,10 +60,10 @@ const struct btf_type *btf_type_id_size(const struct btf *btf,
  *	- BTF_SHOW_UNSAFE: skip use of bpf_probe_read() to safely read
  *	  data before displaying it.
  */
-#define BTF_SHOW_COMPACT	(1ULL << 0)
-#define BTF_SHOW_NONAME		(1ULL << 1)
-#define BTF_SHOW_PTR_RAW	(1ULL << 2)
-#define BTF_SHOW_ZERO		(1ULL << 3)
+#define BTF_SHOW_COMPACT	BTF_F_COMPACT
+#define BTF_SHOW_NONAME		BTF_F_NONAME
+#define BTF_SHOW_PTR_RAW	BTF_F_PTR_RAW
+#define BTF_SHOW_ZERO		BTF_F_ZERO
 #define BTF_SHOW_UNSAFE		(1ULL << 4)
 
 void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 82522f05c021..cca9eb1b13e5 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3594,6 +3594,42 @@ union bpf_attr {
  * 		the data in *dst*. This is a wrapper of **copy_from_user**\ ().
  * 	Return
  * 		0 on success, or a negative error in case of failure.
+ *
+ * long bpf_snprintf_btf(char *str, u32 str_size, struct btf_ptr *ptr, u32 btf_ptr_size, u64 flags)
+ *	Description
+ *		Use BTF to store a string representation of *ptr*->ptr in *str*,
+ *		using *ptr*->type_id.  This value should specify the type
+ *		that *ptr*->ptr points to. LLVM __builtin_btf_type_id(type, 1)
+ *		can be used to look up vmlinux BTF type ids. Traversing the
+ *		data structure using BTF, the type information and values are
+ *		stored in the first *str_size* - 1 bytes of *str*.  Safe copy of
+ *		the pointer data is carried out to avoid kernel crashes during
+ *		operation.  Smaller types can use string space on the stack;
+ *		larger programs can use map data to store the string
+ *		representation.
+ *
+ *		The string can be subsequently shared with userspace via
+ *		bpf_perf_event_output() or ring buffer interfaces.
+ *		bpf_trace_printk() is to be avoided as it places too small
+ *		a limit on string size to be useful.
+ *
+ *		*flags* is a combination of
+ *
+ *		**BTF_F_COMPACT**
+ *			no formatting around type information
+ *		**BTF_F_NONAME**
+ *			no struct/union member names/types
+ *		**BTF_F_PTR_RAW**
+ *			show raw (unobfuscated) pointer values;
+ *			equivalent to printk specifier %px.
+ *		**BTF_F_ZERO**
+ *			show zero-valued struct/union members; they
+ *			are not displayed by default
+ *
+ *	Return
+ *		The number of bytes that were written (or would have been
+ *		written if output had to be truncated due to string size),
+ *		or a negative error in cases of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3745,6 +3781,7 @@ union bpf_attr {
 	FN(inode_storage_delete),	\
 	FN(d_path),			\
 	FN(copy_from_user),		\
+	FN(snprintf_btf),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -4853,4 +4890,34 @@ struct bpf_sk_lookup {
 	__u32 local_port;	/* Host byte order */
 };
 
+/*
+ * struct btf_ptr is used for typed pointer representation; the
+ * type id is used to render the pointer data as the appropriate type
+ * via the bpf_snprintf_btf() helper described above.  A flags field -
+ * potentially to specify additional details about the BTF pointer
+ * (rather than its mode of display) - is included for future use.
+ * Display flags - BTF_F_* - are passed to bpf_snprintf_btf separately.
+ */
+struct btf_ptr {
+	void *ptr;
+	__u32 type_id;
+	__u32 flags;		/* BTF ptr flags; unused at present. */
+};
+
+/*
+ * Flags to control bpf_snprintf_btf() behaviour.
+ *     - BTF_F_COMPACT: no formatting around type information
+ *     - BTF_F_NONAME: no struct/union member names/types
+ *     - BTF_F_PTR_RAW: show raw (unobfuscated) pointer values;
+ *       equivalent to %px.
+ *     - BTF_F_ZERO: show zero-valued struct/union members; they
+ *       are not displayed by default
+ */
+enum {
+	BTF_F_COMPACT	=	(1ULL << 0),
+	BTF_F_NONAME	=	(1ULL << 1),
+	BTF_F_PTR_RAW	=	(1ULL << 2),
+	BTF_F_ZERO	=	(1ULL << 3),
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index c4811b139caa..403fb2341a86 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2216,6 +2216,7 @@ const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak;
 const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto __weak;
 const struct bpf_func_proto bpf_get_local_storage_proto __weak;
 const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto __weak;
+const struct bpf_func_proto bpf_snprintf_btf_proto __weak;
 
 const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void)
 {
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 5cc7425ee476..e825441781ab 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -683,6 +683,10 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		if (!perfmon_capable())
 			return NULL;
 		return bpf_get_trace_printk_proto();
+	case BPF_FUNC_snprintf_btf:
+		if (!perfmon_capable())
+			return NULL;
+		return &bpf_snprintf_btf_proto;
 	case BPF_FUNC_jiffies64:
 		return &bpf_jiffies64_proto;
 	default:
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 2834866d379a..140e1be9dab6 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -7,6 +7,7 @@
 #include <linux/slab.h>
 #include <linux/bpf.h>
 #include <linux/bpf_perf_event.h>
+#include <linux/btf.h>
 #include <linux/filter.h>
 #include <linux/uaccess.h>
 #include <linux/ctype.h>
@@ -16,6 +17,9 @@
 #include <linux/error-injection.h>
 #include <linux/btf_ids.h>
 
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/btf.h>
+
 #include <asm/tlb.h>
 
 #include "trace_probe.h"
@@ -1147,6 +1151,65 @@ static const struct bpf_func_proto bpf_d_path_proto = {
 	.allowed	= bpf_d_path_allowed,
 };
 
+#define BTF_F_ALL	(BTF_F_COMPACT  | BTF_F_NONAME | \
+			 BTF_F_PTR_RAW | BTF_F_ZERO)
+
+static int bpf_btf_printf_prepare(struct btf_ptr *ptr, u32 btf_ptr_size,
+				  u64 flags, const struct btf **btf,
+				  s32 *btf_id)
+{
+	const struct btf_type *t;
+
+	if (unlikely(flags & ~(BTF_F_ALL)))
+		return -EINVAL;
+
+	if (btf_ptr_size != sizeof(struct btf_ptr))
+		return -EINVAL;
+
+	*btf = bpf_get_btf_vmlinux();
+
+	if (IS_ERR_OR_NULL(*btf))
+		return PTR_ERR(*btf);
+
+	if (ptr->type_id > 0)
+		*btf_id = ptr->type_id;
+	else
+		return -EINVAL;
+
+	if (*btf_id > 0)
+		t = btf_type_by_id(*btf, *btf_id);
+	if (*btf_id <= 0 || !t)
+		return -ENOENT;
+
+	return 0;
+}
+
+BPF_CALL_5(bpf_snprintf_btf, char *, str, u32, str_size, struct btf_ptr *, ptr,
+	   u32, btf_ptr_size, u64, flags)
+{
+	const struct btf *btf;
+	s32 btf_id;
+	int ret;
+
+	ret = bpf_btf_printf_prepare(ptr, btf_ptr_size, flags, &btf, &btf_id);
+	if (ret)
+		return ret;
+
+	return btf_type_snprintf_show(btf, btf_id, ptr->ptr, str, str_size,
+				      flags);
+}
+
+const struct bpf_func_proto bpf_snprintf_btf_proto = {
+	.func		= bpf_snprintf_btf,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_CONST_SIZE,
+	.arg3_type	= ARG_PTR_TO_MEM,
+	.arg4_type	= ARG_CONST_SIZE,
+	.arg5_type	= ARG_ANYTHING,
+};
+
 const struct bpf_func_proto *
 bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
@@ -1233,6 +1296,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_task_stack_proto;
 	case BPF_FUNC_copy_from_user:
 		return prog->aux->sleepable ? &bpf_copy_from_user_proto : NULL;
+	case BPF_FUNC_snprintf_btf:
+		return &bpf_snprintf_btf_proto;
 	default:
 		return NULL;
 	}
diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py
index 08388173973f..7d86fdd190be 100755
--- a/scripts/bpf_helpers_doc.py
+++ b/scripts/bpf_helpers_doc.py
@@ -433,6 +433,7 @@ class PrinterHelpers(Printer):
             'struct sk_msg_md',
             'struct xdp_md',
             'struct path',
+            'struct btf_ptr',
     ]
     known_types = {
             '...',
@@ -474,6 +475,7 @@ class PrinterHelpers(Printer):
             'struct udp6_sock',
             'struct task_struct',
             'struct path',
+            'struct btf_ptr',
     }
     mapped_types = {
             'u8': '__u8',
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 82522f05c021..cca9eb1b13e5 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3594,6 +3594,42 @@ union bpf_attr {
  * 		the data in *dst*. This is a wrapper of **copy_from_user**\ ().
  * 	Return
  * 		0 on success, or a negative error in case of failure.
+ *
+ * long bpf_snprintf_btf(char *str, u32 str_size, struct btf_ptr *ptr, u32 btf_ptr_size, u64 flags)
+ *	Description
+ *		Use BTF to store a string representation of *ptr*->ptr in *str*,
+ *		using *ptr*->type_id.  This value should specify the type
+ *		that *ptr*->ptr points to. LLVM __builtin_btf_type_id(type, 1)
+ *		can be used to look up vmlinux BTF type ids. Traversing the
+ *		data structure using BTF, the type information and values are
+ *		stored in the first *str_size* - 1 bytes of *str*.  Safe copy of
+ *		the pointer data is carried out to avoid kernel crashes during
+ *		operation.  Smaller types can use string space on the stack;
+ *		larger programs can use map data to store the string
+ *		representation.
+ *
+ *		The string can be subsequently shared with userspace via
+ *		bpf_perf_event_output() or ring buffer interfaces.
+ *		bpf_trace_printk() is to be avoided as it places too small
+ *		a limit on string size to be useful.
+ *
+ *		*flags* is a combination of
+ *
+ *		**BTF_F_COMPACT**
+ *			no formatting around type information
+ *		**BTF_F_NONAME**
+ *			no struct/union member names/types
+ *		**BTF_F_PTR_RAW**
+ *			show raw (unobfuscated) pointer values;
+ *			equivalent to printk specifier %px.
+ *		**BTF_F_ZERO**
+ *			show zero-valued struct/union members; they
+ *			are not displayed by default
+ *
+ *	Return
+ *		The number of bytes that were written (or would have been
+ *		written if output had to be truncated due to string size),
+ *		or a negative error in cases of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3745,6 +3781,7 @@ union bpf_attr {
 	FN(inode_storage_delete),	\
 	FN(d_path),			\
 	FN(copy_from_user),		\
+	FN(snprintf_btf),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -4853,4 +4890,34 @@ struct bpf_sk_lookup {
 	__u32 local_port;	/* Host byte order */
 };
 
+/*
+ * struct btf_ptr is used for typed pointer representation; the
+ * type id is used to render the pointer data as the appropriate type
+ * via the bpf_snprintf_btf() helper described above.  A flags field -
+ * potentially to specify additional details about the BTF pointer
+ * (rather than its mode of display) - is included for future use.
+ * Display flags - BTF_F_* - are passed to bpf_snprintf_btf separately.
+ */
+struct btf_ptr {
+	void *ptr;
+	__u32 type_id;
+	__u32 flags;		/* BTF ptr flags; unused at present. */
+};
+
+/*
+ * Flags to control bpf_snprintf_btf() behaviour.
+ *     - BTF_F_COMPACT: no formatting around type information
+ *     - BTF_F_NONAME: no struct/union member names/types
+ *     - BTF_F_PTR_RAW: show raw (unobfuscated) pointer values;
+ *       equivalent to %px.
+ *     - BTF_F_ZERO: show zero-valued struct/union members; they
+ *       are not displayed by default
+ */
+enum {
+	BTF_F_COMPACT	=	(1ULL << 0),
+	BTF_F_NONAME	=	(1ULL << 1),
+	BTF_F_PTR_RAW	=	(1ULL << 2),
+	BTF_F_ZERO	=	(1ULL << 3),
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */
-- 
cgit v1.2.3


From eb411377aed9e27835e77ee0710ee8f4649958f3 Mon Sep 17 00:00:00 2001
From: Alan Maguire <alan.maguire@oracle.com>
Date: Mon, 28 Sep 2020 12:31:09 +0100
Subject: bpf: Add bpf_seq_printf_btf helper

A helper is added to allow seq file writing of kernel data
structures using vmlinux BTF.  Its signature is

long bpf_seq_printf_btf(struct seq_file *m, struct btf_ptr *ptr,
                        u32 btf_ptr_size, u64 flags);

Flags and struct btf_ptr definitions/use are identical to the
bpf_snprintf_btf helper, and the helper returns 0 on success
or a negative error value.

Suggested-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/1601292670-1616-8-git-send-email-alan.maguire@oracle.com
---
 include/linux/btf.h            |  2 ++
 include/uapi/linux/bpf.h       |  9 +++++++++
 kernel/bpf/btf.c               |  4 ++--
 kernel/bpf/core.c              |  1 +
 kernel/trace/bpf_trace.c       | 33 +++++++++++++++++++++++++++++++++
 tools/include/uapi/linux/bpf.h |  9 +++++++++
 6 files changed, 56 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/btf.h b/include/linux/btf.h
index 3e5cdc2ba963..024e16ff7dcc 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -68,6 +68,8 @@ const struct btf_type *btf_type_id_size(const struct btf *btf,
 
 void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
 		       struct seq_file *m);
+int btf_type_seq_show_flags(const struct btf *btf, u32 type_id, void *obj,
+			    struct seq_file *m, u64 flags);
 
 /*
  * Copy len bytes of string representation of obj of BTF type_id into buf.
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index cca9eb1b13e5..96ddb00b91dc 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3630,6 +3630,14 @@ union bpf_attr {
  *		The number of bytes that were written (or would have been
  *		written if output had to be truncated due to string size),
  *		or a negative error in cases of failure.
+ *
+ * long bpf_seq_printf_btf(struct seq_file *m, struct btf_ptr *ptr, u32 ptr_size, u64 flags)
+ *	Description
+ *		Use BTF to write to seq_write a string representation of
+ *		*ptr*->ptr, using *ptr*->type_id as per bpf_snprintf_btf().
+ *		*flags* are identical to those used for bpf_snprintf_btf.
+ *	Return
+ *		0 on success or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3782,6 +3790,7 @@ union bpf_attr {
 	FN(d_path),			\
 	FN(copy_from_user),		\
 	FN(snprintf_btf),		\
+	FN(seq_printf_btf),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index dcdd7109aa29..498e5e553825 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -5346,8 +5346,8 @@ static void btf_seq_show(struct btf_show *show, const char *fmt,
 	seq_vprintf((struct seq_file *)show->target, fmt, args);
 }
 
-static int btf_type_seq_show_flags(const struct btf *btf, u32 type_id,
-				   void *obj, struct seq_file *m, u64 flags)
+int btf_type_seq_show_flags(const struct btf *btf, u32 type_id,
+			    void *obj, struct seq_file *m, u64 flags)
 {
 	struct btf_show sseq;
 
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 403fb2341a86..c4ba45fa4fe1 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2217,6 +2217,7 @@ const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto __weak;
 const struct bpf_func_proto bpf_get_local_storage_proto __weak;
 const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto __weak;
 const struct bpf_func_proto bpf_snprintf_btf_proto __weak;
+const struct bpf_func_proto bpf_seq_printf_btf_proto __weak;
 
 const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void)
 {
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 140e1be9dab6..e118a83439c3 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -71,6 +71,10 @@ static struct bpf_raw_event_map *bpf_get_raw_tracepoint_module(const char *name)
 u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
 u64 bpf_get_stack(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
 
+static int bpf_btf_printf_prepare(struct btf_ptr *ptr, u32 btf_ptr_size,
+				  u64 flags, const struct btf **btf,
+				  s32 *btf_id);
+
 /**
  * trace_call_bpf - invoke BPF program
  * @call: tracepoint event
@@ -776,6 +780,31 @@ static const struct bpf_func_proto bpf_seq_write_proto = {
 	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 
+BPF_CALL_4(bpf_seq_printf_btf, struct seq_file *, m, struct btf_ptr *, ptr,
+	   u32, btf_ptr_size, u64, flags)
+{
+	const struct btf *btf;
+	s32 btf_id;
+	int ret;
+
+	ret = bpf_btf_printf_prepare(ptr, btf_ptr_size, flags, &btf, &btf_id);
+	if (ret)
+		return ret;
+
+	return btf_type_seq_show_flags(btf, btf_id, ptr->ptr, m, flags);
+}
+
+static const struct bpf_func_proto bpf_seq_printf_btf_proto = {
+	.func		= bpf_seq_printf_btf,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &btf_seq_file_ids[0],
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
+	.arg4_type	= ARG_ANYTHING,
+};
+
 static __always_inline int
 get_map_perf_counter(struct bpf_map *map, u64 flags,
 		     u64 *value, u64 *enabled, u64 *running)
@@ -1695,6 +1724,10 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return prog->expected_attach_type == BPF_TRACE_ITER ?
 		       &bpf_seq_write_proto :
 		       NULL;
+	case BPF_FUNC_seq_printf_btf:
+		return prog->expected_attach_type == BPF_TRACE_ITER ?
+		       &bpf_seq_printf_btf_proto :
+		       NULL;
 	case BPF_FUNC_d_path:
 		return &bpf_d_path_proto;
 	default:
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index cca9eb1b13e5..96ddb00b91dc 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3630,6 +3630,14 @@ union bpf_attr {
  *		The number of bytes that were written (or would have been
  *		written if output had to be truncated due to string size),
  *		or a negative error in cases of failure.
+ *
+ * long bpf_seq_printf_btf(struct seq_file *m, struct btf_ptr *ptr, u32 ptr_size, u64 flags)
+ *	Description
+ *		Use BTF to write to seq_write a string representation of
+ *		*ptr*->ptr, using *ptr*->type_id as per bpf_snprintf_btf().
+ *		*flags* are identical to those used for bpf_snprintf_btf.
+ *	Return
+ *		0 on success or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3782,6 +3790,7 @@ union bpf_attr {
 	FN(d_path),			\
 	FN(copy_from_user),		\
 	FN(snprintf_btf),		\
+	FN(seq_printf_btf),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
-- 
cgit v1.2.3


From b4c5f83ae3f3e2b3239751c304e424eace62448b Mon Sep 17 00:00:00 2001
From: Rusaimi Amira Ruslan <rusaimi.amira.rusaimi@intel.com>
Date: Mon, 28 Sep 2020 18:12:12 +0800
Subject: stmmac: intel: Adding ref clock 1us tic for LPI cntr

Adding reference clock (1us tic) for all LPI timer on Intel platforms.
The reference clock is derived from ptp clk. This also enables all LPI
counter.

Signed-off-by: Rusaimi Amira Ruslan <rusaimi.amira.rusaimi@intel.com>
Signed-off-by: Voon Weifeng <weifeng.voon@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c | 9 +++++++++
 drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c      | 9 +++++++++
 include/linux/stmmac.h                                 | 1 +
 3 files changed, 19 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c
index b1323d5c95b5..f61cb997a8f6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c
@@ -11,6 +11,7 @@
 #include <linux/platform_device.h>
 #include <linux/stmmac.h>
 
+#include "dwmac4.h"
 #include "stmmac.h"
 #include "stmmac_platform.h"
 
@@ -146,6 +147,14 @@ static int intel_eth_plat_probe(struct platform_device *pdev)
 	}
 
 	plat_dat->bsp_priv = dwmac;
+	plat_dat->eee_usecs_rate = plat_dat->clk_ptp_rate;
+
+	if (plat_dat->eee_usecs_rate > 0) {
+		u32 tx_lpi_usec;
+
+		tx_lpi_usec = (plat_dat->eee_usecs_rate / 1000000) - 1;
+		writel(tx_lpi_usec, stmmac_res.addr + GMAC_1US_TIC_COUNTER);
+	}
 
 	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
 	if (ret) {
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index ab0a81e0fea1..2af9458be95f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -6,6 +6,7 @@
 #include <linux/pci.h>
 #include <linux/dmi.h>
 #include "dwmac-intel.h"
+#include "dwmac4.h"
 #include "stmmac.h"
 
 struct intel_priv_data {
@@ -295,6 +296,7 @@ static int intel_mgbe_common_data(struct pci_dev *pdev,
 	plat->axi->axi_blen[2] = 16;
 
 	plat->ptp_max_adj = plat->clk_ptp_rate;
+	plat->eee_usecs_rate = plat->clk_ptp_rate;
 
 	/* Set system clock */
 	plat->stmmac_clk = clk_register_fixed_rate(&pdev->dev,
@@ -623,6 +625,13 @@ static int intel_eth_pci_probe(struct pci_dev *pdev,
 	if (ret)
 		return ret;
 
+	if (plat->eee_usecs_rate > 0) {
+		u32 tx_lpi_usec;
+
+		tx_lpi_usec = (plat->eee_usecs_rate / 1000000) - 1;
+		writel(tx_lpi_usec, res.addr + GMAC_1US_TIC_COUNTER);
+	}
+
 	ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES);
 	if (ret < 0)
 		return ret;
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 00e83c877496..628e28903b8b 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -200,5 +200,6 @@ struct plat_stmmacenet_data {
 	int has_xgmac;
 	bool vlan_fail_q_en;
 	u8 vlan_fail_q;
+	unsigned int eee_usecs_rate;
 };
 #endif
-- 
cgit v1.2.3


From 7b38b7b0427df70237e3c9c73f2db6b99be2b4b9 Mon Sep 17 00:00:00 2001
From: Leonard Crestez <leonard.crestez@nxp.com>
Date: Tue, 8 Sep 2020 19:24:45 +0900
Subject: PM / devfreq: Add devfreq_get_devfreq_by_node function

Split off part of devfreq_get_devfreq_by_phandle into a separate
function. This allows callers to fetch devfreq instances by enumerating
devicetree instead of explicit phandles.

Acked-by: Krzysztof Kozlowski <krzk@kernel.org>
Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Leonard Crestez <leonard.crestez@nxp.com>
[cw00.choi: Export devfreq_get_devfreq_by_node function and
 add function to devfreq.h when CONFIG_PM_DEVFREQ is enabled.]
Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
---
 drivers/devfreq/devfreq.c | 46 +++++++++++++++++++++++++++++++++++-----------
 include/linux/devfreq.h   |  6 ++++++
 2 files changed, 41 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 071b59fe84d2..d4424b5d8306 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -983,6 +983,32 @@ struct devfreq *devm_devfreq_add_device(struct device *dev,
 EXPORT_SYMBOL(devm_devfreq_add_device);
 
 #ifdef CONFIG_OF
+/*
+ * devfreq_get_devfreq_by_node - Get the devfreq device from devicetree
+ * @node - pointer to device_node
+ *
+ * return the instance of devfreq device
+ */
+struct devfreq *devfreq_get_devfreq_by_node(struct device_node *node)
+{
+	struct devfreq *devfreq;
+
+	if (!node)
+		return ERR_PTR(-EINVAL);
+
+	mutex_lock(&devfreq_list_lock);
+	list_for_each_entry(devfreq, &devfreq_list, node) {
+		if (devfreq->dev.parent
+			&& devfreq->dev.parent->of_node == node) {
+			mutex_unlock(&devfreq_list_lock);
+			return devfreq;
+		}
+	}
+	mutex_unlock(&devfreq_list_lock);
+
+	return ERR_PTR(-ENODEV);
+}
+
 /*
  * devfreq_get_devfreq_by_phandle - Get the devfreq device from devicetree
  * @dev - instance to the given device
@@ -1005,26 +1031,24 @@ struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev, int index)
 	if (!node)
 		return ERR_PTR(-ENODEV);
 
-	mutex_lock(&devfreq_list_lock);
-	list_for_each_entry(devfreq, &devfreq_list, node) {
-		if (devfreq->dev.parent
-			&& devfreq->dev.parent->of_node == node) {
-			mutex_unlock(&devfreq_list_lock);
-			of_node_put(node);
-			return devfreq;
-		}
-	}
-	mutex_unlock(&devfreq_list_lock);
+	devfreq = devfreq_get_devfreq_by_node(node);
 	of_node_put(node);
 
-	return ERR_PTR(-EPROBE_DEFER);
+	return devfreq;
 }
+
 #else
+struct devfreq *devfreq_get_devfreq_by_node(struct device_node *node)
+{
+	return ERR_PTR(-ENODEV);
+}
+
 struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev, int index)
 {
 	return ERR_PTR(-ENODEV);
 }
 #endif /* CONFIG_OF */
+EXPORT_SYMBOL_GPL(devfreq_get_devfreq_by_node);
 EXPORT_SYMBOL_GPL(devfreq_get_devfreq_by_phandle);
 
 /**
diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index 12782fbb4c25..eb971b8e5051 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -261,6 +261,7 @@ void devm_devfreq_unregister_notifier(struct device *dev,
 				struct devfreq *devfreq,
 				struct notifier_block *nb,
 				unsigned int list);
+struct devfreq *devfreq_get_devfreq_by_node(struct device_node *node);
 struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev, int index);
 
 #if IS_ENABLED(CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND)
@@ -414,6 +415,11 @@ static inline void devm_devfreq_unregister_notifier(struct device *dev,
 {
 }
 
+static inline struct devfreq *devfreq_get_devfreq_by_node(struct device_node *node)
+{
+	return ERR_PTR(-ENODEV);
+}
+
 static inline struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev,
 					int index)
 {
-- 
cgit v1.2.3


From 86d90fd95bbc3b3fdc2ef0507b7324cd1d0a358b Mon Sep 17 00:00:00 2001
From: Chanwoo Choi <cw00.choi@samsung.com>
Date: Tue, 8 Sep 2020 19:24:46 +0900
Subject: PM / devfreq: Change prototype of devfreq_get_devfreq_by_phandle
 function

Previously, devfreq core support 'devfreq' property in order to get
the devfreq device by phandle. But, 'devfreq' property name is not proper
on devicetree binding because this name doesn't mean the any h/w attribute.

The devfreq core hand over the right to decide the property name
for getting the devfreq device on devicetree. Each devfreq driver
will decide the property name on devicetree binding and pass
the their own property name to devfreq_get_devfreq_by_phandle function.

Acked-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
---
 drivers/devfreq/devfreq.c    | 11 +++++++----
 drivers/devfreq/exynos-bus.c |  2 +-
 include/linux/devfreq.h      |  5 +++--
 3 files changed, 11 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index d4424b5d8306..861c100f9fac 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -1012,22 +1012,24 @@ struct devfreq *devfreq_get_devfreq_by_node(struct device_node *node)
 /*
  * devfreq_get_devfreq_by_phandle - Get the devfreq device from devicetree
  * @dev - instance to the given device
+ * @phandle_name - name of property holding a phandle value
  * @index - index into list of devfreq
  *
  * return the instance of devfreq device
  */
-struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev, int index)
+struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev,
+					const char *phandle_name, int index)
 {
 	struct device_node *node;
 	struct devfreq *devfreq;
 
-	if (!dev)
+	if (!dev || !phandle_name)
 		return ERR_PTR(-EINVAL);
 
 	if (!dev->of_node)
 		return ERR_PTR(-EINVAL);
 
-	node = of_parse_phandle(dev->of_node, "devfreq", index);
+	node = of_parse_phandle(dev->of_node, phandle_name, index);
 	if (!node)
 		return ERR_PTR(-ENODEV);
 
@@ -1043,7 +1045,8 @@ struct devfreq *devfreq_get_devfreq_by_node(struct device_node *node)
 	return ERR_PTR(-ENODEV);
 }
 
-struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev, int index)
+struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev,
+					const char *phandle_name, int index)
 {
 	return ERR_PTR(-ENODEV);
 }
diff --git a/drivers/devfreq/exynos-bus.c b/drivers/devfreq/exynos-bus.c
index 8fa8eb541373..58dbf51f0983 100644
--- a/drivers/devfreq/exynos-bus.c
+++ b/drivers/devfreq/exynos-bus.c
@@ -360,7 +360,7 @@ static int exynos_bus_profile_init_passive(struct exynos_bus *bus,
 	profile->exit = exynos_bus_passive_exit;
 
 	/* Get the instance of parent devfreq device */
-	parent_devfreq = devfreq_get_devfreq_by_phandle(dev, 0);
+	parent_devfreq = devfreq_get_devfreq_by_phandle(dev, "devfreq", 0);
 	if (IS_ERR(parent_devfreq))
 		return -EPROBE_DEFER;
 
diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index eb971b8e5051..2f4a74efa6be 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -262,7 +262,8 @@ void devm_devfreq_unregister_notifier(struct device *dev,
 				struct notifier_block *nb,
 				unsigned int list);
 struct devfreq *devfreq_get_devfreq_by_node(struct device_node *node);
-struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev, int index);
+struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev,
+				const char *phandle_name, int index);
 
 #if IS_ENABLED(CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND)
 /**
@@ -421,7 +422,7 @@ static inline struct devfreq *devfreq_get_devfreq_by_node(struct device_node *no
 }
 
 static inline struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev,
-					int index)
+					const char *phandle_name, int index)
 {
 	return ERR_PTR(-ENODEV);
 }
-- 
cgit v1.2.3


From 02bdbf7d09c059b16047e3d4a05e6d584dd993b6 Mon Sep 17 00:00:00 2001
From: Chanwoo Choi <cw00.choi@samsung.com>
Date: Tue, 8 Sep 2020 19:24:47 +0900
Subject: PM / devfreq: event: Change prototype of
 devfreq_event_get_edev_by_phandle function

Previously, devfreq core support 'devfreq-events' property in order to get
the devfreq-event device by phandle. But, 'devfreq-events' property name is
not proper on devicetree binding because this name doesn't mean
the any h/w attribute.

The devfreq-event core hand over the rights to decide the property name
for getting the devfreq-event device on devicetree. Each devfreq-event driver
will decide the property name on devicetree binding and then pass
the their own property name to devfreq_event_get_edev_by_phandle function.

And change the prototype of devfreq_event_get_edev_count function
because of used deprecated 'devfreq-events' property.

Acked-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
---
 drivers/devfreq/devfreq-event.c         | 14 ++++++++------
 drivers/devfreq/exynos-bus.c            |  5 +++--
 drivers/devfreq/rk3399_dmc.c            |  2 +-
 drivers/memory/samsung/exynos5422-dmc.c |  6 ++++--
 include/linux/devfreq-event.h           | 14 ++++++++++----
 5 files changed, 26 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/devfreq/devfreq-event.c b/drivers/devfreq/devfreq-event.c
index 56efbeb7851e..6765c03334bc 100644
--- a/drivers/devfreq/devfreq-event.c
+++ b/drivers/devfreq/devfreq-event.c
@@ -213,20 +213,21 @@ EXPORT_SYMBOL_GPL(devfreq_event_reset_event);
  * devfreq_event_get_edev_by_phandle() - Get the devfreq-event dev from
  *					 devicetree.
  * @dev		: the pointer to the given device
+ * @phandle_name: name of property holding a phandle value
  * @index	: the index into list of devfreq-event device
  *
  * Note that this function return the pointer of devfreq-event device.
  */
 struct devfreq_event_dev *devfreq_event_get_edev_by_phandle(struct device *dev,
-						      int index)
+					const char *phandle_name, int index)
 {
 	struct device_node *node;
 	struct devfreq_event_dev *edev;
 
-	if (!dev->of_node)
+	if (!dev->of_node || !phandle_name)
 		return ERR_PTR(-EINVAL);
 
-	node = of_parse_phandle(dev->of_node, "devfreq-events", index);
+	node = of_parse_phandle(dev->of_node, phandle_name, index);
 	if (!node)
 		return ERR_PTR(-ENODEV);
 
@@ -258,19 +259,20 @@ EXPORT_SYMBOL_GPL(devfreq_event_get_edev_by_phandle);
 /**
  * devfreq_event_get_edev_count() - Get the count of devfreq-event dev
  * @dev		: the pointer to the given device
+ * @phandle_name: name of property holding a phandle value
  *
  * Note that this function return the count of devfreq-event devices.
  */
-int devfreq_event_get_edev_count(struct device *dev)
+int devfreq_event_get_edev_count(struct device *dev, const char *phandle_name)
 {
 	int count;
 
-	if (!dev->of_node) {
+	if (!dev->of_node || !phandle_name) {
 		dev_err(dev, "device does not have a device node entry\n");
 		return -EINVAL;
 	}
 
-	count = of_property_count_elems_of_size(dev->of_node, "devfreq-events",
+	count = of_property_count_elems_of_size(dev->of_node, phandle_name,
 						sizeof(u32));
 	if (count < 0) {
 		dev_err(dev,
diff --git a/drivers/devfreq/exynos-bus.c b/drivers/devfreq/exynos-bus.c
index 58dbf51f0983..1e684a448c9e 100644
--- a/drivers/devfreq/exynos-bus.c
+++ b/drivers/devfreq/exynos-bus.c
@@ -193,7 +193,7 @@ static int exynos_bus_parent_parse_of(struct device_node *np,
 	 * Get the devfreq-event devices to get the current utilization of
 	 * buses. This raw data will be used in devfreq ondemand governor.
 	 */
-	count = devfreq_event_get_edev_count(dev);
+	count = devfreq_event_get_edev_count(dev, "devfreq-events");
 	if (count < 0) {
 		dev_err(dev, "failed to get the count of devfreq-event dev\n");
 		ret = count;
@@ -209,7 +209,8 @@ static int exynos_bus_parent_parse_of(struct device_node *np,
 	}
 
 	for (i = 0; i < count; i++) {
-		bus->edev[i] = devfreq_event_get_edev_by_phandle(dev, i);
+		bus->edev[i] = devfreq_event_get_edev_by_phandle(dev,
+							"devfreq-events", i);
 		if (IS_ERR(bus->edev[i])) {
 			ret = -EPROBE_DEFER;
 			goto err_regulator;
diff --git a/drivers/devfreq/rk3399_dmc.c b/drivers/devfreq/rk3399_dmc.c
index 027769e39f9b..2e912166a993 100644
--- a/drivers/devfreq/rk3399_dmc.c
+++ b/drivers/devfreq/rk3399_dmc.c
@@ -341,7 +341,7 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
 		return PTR_ERR(data->dmc_clk);
 	}
 
-	data->edev = devfreq_event_get_edev_by_phandle(dev, 0);
+	data->edev = devfreq_event_get_edev_by_phandle(dev, "devfreq-events", 0);
 	if (IS_ERR(data->edev))
 		return -EPROBE_DEFER;
 
diff --git a/drivers/memory/samsung/exynos5422-dmc.c b/drivers/memory/samsung/exynos5422-dmc.c
index b9c7956e5031..714d1f6f077c 100644
--- a/drivers/memory/samsung/exynos5422-dmc.c
+++ b/drivers/memory/samsung/exynos5422-dmc.c
@@ -1293,7 +1293,8 @@ static int exynos5_performance_counters_init(struct exynos5_dmc *dmc)
 	int counters_size;
 	int ret, i;
 
-	dmc->num_counters = devfreq_event_get_edev_count(dmc->dev);
+	dmc->num_counters = devfreq_event_get_edev_count(dmc->dev,
+							"devfreq-events");
 	if (dmc->num_counters < 0) {
 		dev_err(dmc->dev, "could not get devfreq-event counters\n");
 		return dmc->num_counters;
@@ -1306,7 +1307,8 @@ static int exynos5_performance_counters_init(struct exynos5_dmc *dmc)
 
 	for (i = 0; i < dmc->num_counters; i++) {
 		dmc->counter[i] =
-			devfreq_event_get_edev_by_phandle(dmc->dev, i);
+			devfreq_event_get_edev_by_phandle(dmc->dev,
+						"devfreq-events", i);
 		if (IS_ERR_OR_NULL(dmc->counter[i]))
 			return -EPROBE_DEFER;
 	}
diff --git a/include/linux/devfreq-event.h b/include/linux/devfreq-event.h
index f14f17f8cb7f..4a50a5c71a5f 100644
--- a/include/linux/devfreq-event.h
+++ b/include/linux/devfreq-event.h
@@ -106,8 +106,11 @@ extern int devfreq_event_get_event(struct devfreq_event_dev *edev,
 				struct devfreq_event_data *edata);
 extern int devfreq_event_reset_event(struct devfreq_event_dev *edev);
 extern struct devfreq_event_dev *devfreq_event_get_edev_by_phandle(
-				struct device *dev, int index);
-extern int devfreq_event_get_edev_count(struct device *dev);
+				struct device *dev,
+				const char *phandle_name,
+				int index);
+extern int devfreq_event_get_edev_count(struct device *dev,
+				const char *phandle_name);
 extern struct devfreq_event_dev *devfreq_event_add_edev(struct device *dev,
 				struct devfreq_event_desc *desc);
 extern int devfreq_event_remove_edev(struct devfreq_event_dev *edev);
@@ -152,12 +155,15 @@ static inline int devfreq_event_reset_event(struct devfreq_event_dev *edev)
 }
 
 static inline struct devfreq_event_dev *devfreq_event_get_edev_by_phandle(
-					struct device *dev, int index)
+					struct device *dev,
+					const char *phandle_name,
+					int index)
 {
 	return ERR_PTR(-EINVAL);
 }
 
-static inline int devfreq_event_get_edev_count(struct device *dev)
+static inline int devfreq_event_get_edev_count(struct device *dev,
+					const char *phandle_name)
 {
 	return -EINVAL;
 }
-- 
cgit v1.2.3


From 01fd30da0474d5528d96a154cb50ce3b0352fd19 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Fri, 25 Sep 2020 13:55:58 +0200
Subject: dma-buf: Add struct dma-buf-map for storing struct dma_buf.vaddr_ptr
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The new type struct dma_buf_map represents a mapping of dma-buf memory
into kernel space. It contains a flag, is_iomem, that signals users to
access the mapped memory with I/O operations instead of regular loads
and stores.

It was assumed that DMA buffer memory can be accessed with regular load
and store operations. Some architectures, such as sparc64, require the
use of I/O operations to access dma-map buffers that are located in I/O
memory. Providing struct dma_buf_map allows drivers to implement this.
This was specifically a problem when refreshing the graphics framebuffer
on such systems. [1]

As the first step, struct dma_buf stores an instance of struct dma_buf_map
internally. Afterwards, dma-buf's vmap and vunmap interfaces are be
converted. Finally, affected drivers can be fixed.

v3:
	* moved documentation into separate patch
	* test for NULL pointers with !<ptr>

[1] https://lore.kernel.org/dri-devel/20200725191012.GA434957@ravnborg.org/

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Acked-by: Sumit Semwal <sumit.semwal@linaro.org>
Acked-by: Sam Ravnborg <sam@ravnborg.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20200925115601.23955-2-tzimmermann@suse.de
---
 drivers/dma-buf/dma-buf.c   | 14 ++++----
 include/linux/dma-buf-map.h | 82 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/dma-buf.h     |  3 +-
 3 files changed, 91 insertions(+), 8 deletions(-)
 create mode 100644 include/linux/dma-buf-map.h

(limited to 'include/linux')

diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index 58564d82a3a2..5e849ca241a0 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -1207,12 +1207,12 @@ void *dma_buf_vmap(struct dma_buf *dmabuf)
 	mutex_lock(&dmabuf->lock);
 	if (dmabuf->vmapping_counter) {
 		dmabuf->vmapping_counter++;
-		BUG_ON(!dmabuf->vmap_ptr);
-		ptr = dmabuf->vmap_ptr;
+		BUG_ON(dma_buf_map_is_null(&dmabuf->vmap_ptr));
+		ptr = dmabuf->vmap_ptr.vaddr;
 		goto out_unlock;
 	}
 
-	BUG_ON(dmabuf->vmap_ptr);
+	BUG_ON(dma_buf_map_is_set(&dmabuf->vmap_ptr));
 
 	ptr = dmabuf->ops->vmap(dmabuf);
 	if (WARN_ON_ONCE(IS_ERR(ptr)))
@@ -1220,7 +1220,7 @@ void *dma_buf_vmap(struct dma_buf *dmabuf)
 	if (!ptr)
 		goto out_unlock;
 
-	dmabuf->vmap_ptr = ptr;
+	dmabuf->vmap_ptr.vaddr = ptr;
 	dmabuf->vmapping_counter = 1;
 
 out_unlock:
@@ -1239,15 +1239,15 @@ void dma_buf_vunmap(struct dma_buf *dmabuf, void *vaddr)
 	if (WARN_ON(!dmabuf))
 		return;
 
-	BUG_ON(!dmabuf->vmap_ptr);
+	BUG_ON(dma_buf_map_is_null(&dmabuf->vmap_ptr));
 	BUG_ON(dmabuf->vmapping_counter == 0);
-	BUG_ON(dmabuf->vmap_ptr != vaddr);
+	BUG_ON(!dma_buf_map_is_vaddr(&dmabuf->vmap_ptr, vaddr));
 
 	mutex_lock(&dmabuf->lock);
 	if (--dmabuf->vmapping_counter == 0) {
 		if (dmabuf->ops->vunmap)
 			dmabuf->ops->vunmap(dmabuf, vaddr);
-		dmabuf->vmap_ptr = NULL;
+		dma_buf_map_clear(&dmabuf->vmap_ptr);
 	}
 	mutex_unlock(&dmabuf->lock);
 }
diff --git a/include/linux/dma-buf-map.h b/include/linux/dma-buf-map.h
new file mode 100644
index 000000000000..00143c88feb6
--- /dev/null
+++ b/include/linux/dma-buf-map.h
@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Pointer to dma-buf-mapped memory, plus helpers.
+ */
+
+#ifndef __DMA_BUF_MAP_H__
+#define __DMA_BUF_MAP_H__
+
+#include <linux/io.h>
+
+/**
+ * struct dma_buf_map - Pointer to vmap'ed dma-buf memory.
+ * @vaddr_iomem:	The buffer's address if in I/O memory
+ * @vaddr:		The buffer's address if in system memory
+ * @is_iomem:		True if the dma-buf memory is located in I/O
+ *			memory, or false otherwise.
+ */
+struct dma_buf_map {
+	union {
+		void __iomem *vaddr_iomem;
+		void *vaddr;
+	};
+	bool is_iomem;
+};
+
+/* API transition helper */
+static inline bool dma_buf_map_is_vaddr(const struct dma_buf_map *map, const void *vaddr)
+{
+	return !map->is_iomem && (map->vaddr == vaddr);
+}
+
+/**
+ * dma_buf_map_is_null - Tests for a dma-buf mapping to be NULL
+ * @map:	The dma-buf mapping structure
+ *
+ * Depending on the state of struct dma_buf_map.is_iomem, tests if the
+ * mapping is NULL.
+ *
+ * Returns:
+ * True if the mapping is NULL, or false otherwise.
+ */
+static inline bool dma_buf_map_is_null(const struct dma_buf_map *map)
+{
+	if (map->is_iomem)
+		return !map->vaddr_iomem;
+	return !map->vaddr;
+}
+
+/**
+ * dma_buf_map_is_set - Tests is the dma-buf mapping has been set
+ * @map:	The dma-buf mapping structure
+ *
+ * Depending on the state of struct dma_buf_map.is_iomem, tests if the
+ * mapping has been set.
+ *
+ * Returns:
+ * True if the mapping is been set, or false otherwise.
+ */
+static inline bool dma_buf_map_is_set(const struct dma_buf_map *map)
+{
+	return !dma_buf_map_is_null(map);
+}
+
+/**
+ * dma_buf_map_clear - Clears a dma-buf mapping structure
+ * @map:	The dma-buf mapping structure
+ *
+ * Clears all fields to zero; including struct dma_buf_map.is_iomem. So
+ * mapping structures that were set to point to I/O memory are reset for
+ * system memory. Pointers are cleared to NULL. This is the default.
+ */
+static inline void dma_buf_map_clear(struct dma_buf_map *map)
+{
+	if (map->is_iomem) {
+		map->vaddr_iomem = NULL;
+		map->is_iomem = false;
+	} else {
+		map->vaddr = NULL;
+	}
+}
+
+#endif /* __DMA_BUF_MAP_H__ */
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index 957b398d30e5..fcc2ddfb6d18 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -13,6 +13,7 @@
 #ifndef __DMA_BUF_H__
 #define __DMA_BUF_H__
 
+#include <linux/dma-buf-map.h>
 #include <linux/file.h>
 #include <linux/err.h>
 #include <linux/scatterlist.h>
@@ -309,7 +310,7 @@ struct dma_buf {
 	const struct dma_buf_ops *ops;
 	struct mutex lock;
 	unsigned vmapping_counter;
-	void *vmap_ptr;
+	struct dma_buf_map vmap_ptr;
 	const char *exp_name;
 	const char *name;
 	spinlock_t name_lock;
-- 
cgit v1.2.3


From 6619ccf1bb1d0ebb071f758111efa83918b216fc Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Fri, 25 Sep 2020 13:55:59 +0200
Subject: dma-buf: Use struct dma_buf_map in dma_buf_vmap() interfaces
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch updates dma_buf_vmap() and dma-buf's vmap callback to use
struct dma_buf_map.

The interfaces used to return a buffer address. This address now gets
stored in an instance of the structure that is given as an additional
argument. The functions return an errno code on errors.

Users of the functions are updated accordingly. This is only an interface
change. It is currently expected that dma-buf memory can be accessed with
system memory load/store operations.

v3:
	* update fastrpc driver (kernel test robot)
v2:
	* always clear map parameter in dma_buf_vmap() (Daniel)
	* include dma-buf-heaps and i915 selftests (kernel test robot)

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Acked-by: Sumit Semwal <sumit.semwal@linaro.org>
Acked-by: Christian König <christian.koenig@amd.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Acked-by: Tomasz Figa <tfiga@chromium.org>
Acked-by: Sam Ravnborg <sam@ravnborg.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20200925115601.23955-3-tzimmermann@suse.de
---
 drivers/dma-buf/dma-buf.c                          | 28 ++++++++++++----------
 drivers/dma-buf/heaps/heap-helpers.c               |  8 +++++--
 drivers/gpu/drm/drm_gem_cma_helper.c               | 13 +++++-----
 drivers/gpu/drm/drm_gem_shmem_helper.c             | 14 +++++++----
 drivers/gpu/drm/drm_prime.c                        |  9 ++++---
 drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c        |  8 ++++++-
 drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c         | 11 +++++++--
 .../gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c   | 12 +++++++---
 drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c   | 10 ++++++--
 drivers/gpu/drm/tegra/gem.c                        | 18 +++++++++-----
 .../media/common/videobuf2/videobuf2-dma-contig.c  | 14 +++++++----
 drivers/media/common/videobuf2/videobuf2-dma-sg.c  | 16 +++++++++----
 drivers/media/common/videobuf2/videobuf2-vmalloc.c | 15 ++++++++----
 drivers/misc/fastrpc.c                             |  6 +++--
 include/drm/drm_prime.h                            |  3 ++-
 include/linux/dma-buf-map.h                        | 13 ++++++++++
 include/linux/dma-buf.h                            |  6 ++---
 17 files changed, 143 insertions(+), 61 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index 5e849ca241a0..61bd24d21b38 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -1186,46 +1186,50 @@ EXPORT_SYMBOL_GPL(dma_buf_mmap);
  * dma_buf_vmap - Create virtual mapping for the buffer object into kernel
  * address space. Same restrictions as for vmap and friends apply.
  * @dmabuf:	[in]	buffer to vmap
+ * @map:	[out]	returns the vmap pointer
  *
  * This call may fail due to lack of virtual mapping address space.
  * These calls are optional in drivers. The intended use for them
  * is for mapping objects linear in kernel space for high use objects.
  * Please attempt to use kmap/kunmap before thinking about these interfaces.
  *
- * Returns NULL on error.
+ * Returns 0 on success, or a negative errno code otherwise.
  */
-void *dma_buf_vmap(struct dma_buf *dmabuf)
+int dma_buf_vmap(struct dma_buf *dmabuf, struct dma_buf_map *map)
 {
-	void *ptr;
+	struct dma_buf_map ptr;
+	int ret = 0;
+
+	dma_buf_map_clear(map);
 
 	if (WARN_ON(!dmabuf))
-		return NULL;
+		return -EINVAL;
 
 	if (!dmabuf->ops->vmap)
-		return NULL;
+		return -EINVAL;
 
 	mutex_lock(&dmabuf->lock);
 	if (dmabuf->vmapping_counter) {
 		dmabuf->vmapping_counter++;
 		BUG_ON(dma_buf_map_is_null(&dmabuf->vmap_ptr));
-		ptr = dmabuf->vmap_ptr.vaddr;
+		*map = dmabuf->vmap_ptr;
 		goto out_unlock;
 	}
 
 	BUG_ON(dma_buf_map_is_set(&dmabuf->vmap_ptr));
 
-	ptr = dmabuf->ops->vmap(dmabuf);
-	if (WARN_ON_ONCE(IS_ERR(ptr)))
-		ptr = NULL;
-	if (!ptr)
+	ret = dmabuf->ops->vmap(dmabuf, &ptr);
+	if (WARN_ON_ONCE(ret))
 		goto out_unlock;
 
-	dmabuf->vmap_ptr.vaddr = ptr;
+	dmabuf->vmap_ptr = ptr;
 	dmabuf->vmapping_counter = 1;
 
+	*map = dmabuf->vmap_ptr;
+
 out_unlock:
 	mutex_unlock(&dmabuf->lock);
-	return ptr;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(dma_buf_vmap);
 
diff --git a/drivers/dma-buf/heaps/heap-helpers.c b/drivers/dma-buf/heaps/heap-helpers.c
index 9f964ca3f59c..27e54d9c120c 100644
--- a/drivers/dma-buf/heaps/heap-helpers.c
+++ b/drivers/dma-buf/heaps/heap-helpers.c
@@ -236,7 +236,7 @@ static int dma_heap_dma_buf_end_cpu_access(struct dma_buf *dmabuf,
 	return 0;
 }
 
-static void *dma_heap_dma_buf_vmap(struct dma_buf *dmabuf)
+static int dma_heap_dma_buf_vmap(struct dma_buf *dmabuf, struct dma_buf_map *map)
 {
 	struct heap_helper_buffer *buffer = dmabuf->priv;
 	void *vaddr;
@@ -245,7 +245,11 @@ static void *dma_heap_dma_buf_vmap(struct dma_buf *dmabuf)
 	vaddr = dma_heap_buffer_vmap_get(buffer);
 	mutex_unlock(&buffer->lock);
 
-	return vaddr;
+	if (!vaddr)
+		return -ENOMEM;
+	dma_buf_map_set_vaddr(map, vaddr);
+
+	return 0;
 }
 
 static void dma_heap_dma_buf_vunmap(struct dma_buf *dmabuf, void *vaddr)
diff --git a/drivers/gpu/drm/drm_gem_cma_helper.c b/drivers/gpu/drm/drm_gem_cma_helper.c
index 1e5b389c435c..eb412e45f896 100644
--- a/drivers/gpu/drm/drm_gem_cma_helper.c
+++ b/drivers/gpu/drm/drm_gem_cma_helper.c
@@ -634,22 +634,23 @@ drm_gem_cma_prime_import_sg_table_vmap(struct drm_device *dev,
 {
 	struct drm_gem_cma_object *cma_obj;
 	struct drm_gem_object *obj;
-	void *vaddr;
+	struct dma_buf_map map;
+	int ret;
 
-	vaddr = dma_buf_vmap(attach->dmabuf);
-	if (!vaddr) {
+	ret = dma_buf_vmap(attach->dmabuf, &map);
+	if (ret) {
 		DRM_ERROR("Failed to vmap PRIME buffer\n");
-		return ERR_PTR(-ENOMEM);
+		return ERR_PTR(ret);
 	}
 
 	obj = drm_gem_cma_prime_import_sg_table(dev, attach, sgt);
 	if (IS_ERR(obj)) {
-		dma_buf_vunmap(attach->dmabuf, vaddr);
+		dma_buf_vunmap(attach->dmabuf, map.vaddr);
 		return obj;
 	}
 
 	cma_obj = to_drm_gem_cma_obj(obj);
-	cma_obj->vaddr = vaddr;
+	cma_obj->vaddr = map.vaddr;
 
 	return obj;
 }
diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c
index 0a952f27c184..ad10a57cfece 100644
--- a/drivers/gpu/drm/drm_gem_shmem_helper.c
+++ b/drivers/gpu/drm/drm_gem_shmem_helper.c
@@ -261,13 +261,16 @@ EXPORT_SYMBOL(drm_gem_shmem_unpin);
 static void *drm_gem_shmem_vmap_locked(struct drm_gem_shmem_object *shmem)
 {
 	struct drm_gem_object *obj = &shmem->base;
-	int ret;
+	struct dma_buf_map map;
+	int ret = 0;
 
 	if (shmem->vmap_use_count++ > 0)
 		return shmem->vaddr;
 
 	if (obj->import_attach) {
-		shmem->vaddr = dma_buf_vmap(obj->import_attach->dmabuf);
+		ret = dma_buf_vmap(obj->import_attach->dmabuf, &map);
+		if (!ret)
+			shmem->vaddr = map.vaddr;
 	} else {
 		pgprot_t prot = PAGE_KERNEL;
 
@@ -279,11 +282,12 @@ static void *drm_gem_shmem_vmap_locked(struct drm_gem_shmem_object *shmem)
 			prot = pgprot_writecombine(prot);
 		shmem->vaddr = vmap(shmem->pages, obj->size >> PAGE_SHIFT,
 				    VM_MAP, prot);
+		if (!shmem->vaddr)
+			ret = -ENOMEM;
 	}
 
-	if (!shmem->vaddr) {
-		DRM_DEBUG_KMS("Failed to vmap pages\n");
-		ret = -ENOMEM;
+	if (ret) {
+		DRM_DEBUG_KMS("Failed to vmap pages, error %d\n", ret);
 		goto err_put_pages;
 	}
 
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 194784a5b344..2d75e58d21fe 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -662,22 +662,25 @@ EXPORT_SYMBOL(drm_gem_unmap_dma_buf);
 /**
  * drm_gem_dmabuf_vmap - dma_buf vmap implementation for GEM
  * @dma_buf: buffer to be mapped
+ * @map: the virtual address of the buffer
  *
  * Sets up a kernel virtual mapping. This can be used as the &dma_buf_ops.vmap
  * callback. Calls into &drm_gem_object_funcs.vmap for device specific handling.
  *
  * Returns the kernel virtual address or NULL on failure.
  */
-void *drm_gem_dmabuf_vmap(struct dma_buf *dma_buf)
+int drm_gem_dmabuf_vmap(struct dma_buf *dma_buf, struct dma_buf_map *map)
 {
 	struct drm_gem_object *obj = dma_buf->priv;
 	void *vaddr;
 
 	vaddr = drm_gem_vmap(obj);
 	if (IS_ERR(vaddr))
-		vaddr = NULL;
+		return PTR_ERR(vaddr);
 
-	return vaddr;
+	dma_buf_map_set_vaddr(map, vaddr);
+
+	return 0;
 }
 EXPORT_SYMBOL(drm_gem_dmabuf_vmap);
 
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c
index 4aa3426a9ba4..80a9fc143bbb 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c
@@ -85,9 +85,15 @@ static void etnaviv_gem_prime_release(struct etnaviv_gem_object *etnaviv_obj)
 
 static void *etnaviv_gem_prime_vmap_impl(struct etnaviv_gem_object *etnaviv_obj)
 {
+	struct dma_buf_map map;
+	int ret;
+
 	lockdep_assert_held(&etnaviv_obj->lock);
 
-	return dma_buf_vmap(etnaviv_obj->base.import_attach->dmabuf);
+	ret = dma_buf_vmap(etnaviv_obj->base.import_attach->dmabuf, &map);
+	if (ret)
+		return NULL;
+	return map.vaddr;
 }
 
 static int etnaviv_gem_prime_mmap_obj(struct etnaviv_gem_object *etnaviv_obj,
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
index 27fddc22a7c6..77b363d3000b 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
@@ -82,11 +82,18 @@ static void i915_gem_unmap_dma_buf(struct dma_buf_attachment *attachment,
 	i915_gem_object_unpin_pages(obj);
 }
 
-static void *i915_gem_dmabuf_vmap(struct dma_buf *dma_buf)
+static int i915_gem_dmabuf_vmap(struct dma_buf *dma_buf, struct dma_buf_map *map)
 {
 	struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf);
+	void *vaddr;
 
-	return i915_gem_object_pin_map(obj, I915_MAP_WB);
+	vaddr = i915_gem_object_pin_map(obj, I915_MAP_WB);
+	if (IS_ERR(vaddr))
+		return PTR_ERR(vaddr);
+
+	dma_buf_map_set_vaddr(map, vaddr);
+
+	return 0;
 }
 
 static void i915_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr)
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
index 0845ce1ae37c..3aad7643b0b7 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
@@ -82,6 +82,7 @@ static int igt_dmabuf_import(void *arg)
 	struct drm_i915_gem_object *obj;
 	struct dma_buf *dmabuf;
 	void *obj_map, *dma_map;
+	struct dma_buf_map map;
 	u32 pattern[] = { 0, 0xaa, 0xcc, 0x55, 0xff };
 	int err, i;
 
@@ -110,7 +111,8 @@ static int igt_dmabuf_import(void *arg)
 		goto out_obj;
 	}
 
-	dma_map = dma_buf_vmap(dmabuf);
+	err = dma_buf_vmap(dmabuf, &map);
+	dma_map = err ? NULL : map.vaddr;
 	if (!dma_map) {
 		pr_err("dma_buf_vmap failed\n");
 		err = -ENOMEM;
@@ -163,6 +165,7 @@ static int igt_dmabuf_import_ownership(void *arg)
 	struct drm_i915_private *i915 = arg;
 	struct drm_i915_gem_object *obj;
 	struct dma_buf *dmabuf;
+	struct dma_buf_map map;
 	void *ptr;
 	int err;
 
@@ -170,7 +173,8 @@ static int igt_dmabuf_import_ownership(void *arg)
 	if (IS_ERR(dmabuf))
 		return PTR_ERR(dmabuf);
 
-	ptr = dma_buf_vmap(dmabuf);
+	err = dma_buf_vmap(dmabuf, &map);
+	ptr = err ? NULL : map.vaddr;
 	if (!ptr) {
 		pr_err("dma_buf_vmap failed\n");
 		err = -ENOMEM;
@@ -212,6 +216,7 @@ static int igt_dmabuf_export_vmap(void *arg)
 	struct drm_i915_private *i915 = arg;
 	struct drm_i915_gem_object *obj;
 	struct dma_buf *dmabuf;
+	struct dma_buf_map map;
 	void *ptr;
 	int err;
 
@@ -228,7 +233,8 @@ static int igt_dmabuf_export_vmap(void *arg)
 	}
 	i915_gem_object_put(obj);
 
-	ptr = dma_buf_vmap(dmabuf);
+	err = dma_buf_vmap(dmabuf, &map);
+	ptr = err ? NULL : map.vaddr;
 	if (!ptr) {
 		pr_err("dma_buf_vmap failed\n");
 		err = -ENOMEM;
diff --git a/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c b/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c
index debaf7b18ab5..dcae46441f7d 100644
--- a/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c
+++ b/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c
@@ -62,11 +62,17 @@ static void mock_dmabuf_release(struct dma_buf *dma_buf)
 	kfree(mock);
 }
 
-static void *mock_dmabuf_vmap(struct dma_buf *dma_buf)
+static int mock_dmabuf_vmap(struct dma_buf *dma_buf, struct dma_buf_map *map)
 {
 	struct mock_dmabuf *mock = to_mock(dma_buf);
+	void *vaddr;
 
-	return vm_map_ram(mock->pages, mock->npages, 0);
+	vaddr = vm_map_ram(mock->pages, mock->npages, 0);
+	if (!vaddr)
+		return -ENOMEM;
+	dma_buf_map_set_vaddr(map, vaddr);
+
+	return 0;
 }
 
 static void mock_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr)
diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c
index d481dea4738d..2b6e06c7a2c5 100644
--- a/drivers/gpu/drm/tegra/gem.c
+++ b/drivers/gpu/drm/tegra/gem.c
@@ -132,14 +132,18 @@ static void tegra_bo_unpin(struct device *dev, struct sg_table *sgt)
 static void *tegra_bo_mmap(struct host1x_bo *bo)
 {
 	struct tegra_bo *obj = host1x_to_tegra_bo(bo);
+	struct dma_buf_map map;
+	int ret;
 
-	if (obj->vaddr)
+	if (obj->vaddr) {
 		return obj->vaddr;
-	else if (obj->gem.import_attach)
-		return dma_buf_vmap(obj->gem.import_attach->dmabuf);
-	else
+	} else if (obj->gem.import_attach) {
+		ret = dma_buf_vmap(obj->gem.import_attach->dmabuf, &map);
+		return ret ? NULL : map.vaddr;
+	} else {
 		return vmap(obj->pages, obj->num_pages, VM_MAP,
 			    pgprot_writecombine(PAGE_KERNEL));
+	}
 }
 
 static void tegra_bo_munmap(struct host1x_bo *bo, void *addr)
@@ -649,12 +653,14 @@ static int tegra_gem_prime_mmap(struct dma_buf *buf, struct vm_area_struct *vma)
 	return __tegra_gem_mmap(gem, vma);
 }
 
-static void *tegra_gem_prime_vmap(struct dma_buf *buf)
+static int tegra_gem_prime_vmap(struct dma_buf *buf, struct dma_buf_map *map)
 {
 	struct drm_gem_object *gem = buf->priv;
 	struct tegra_bo *bo = to_tegra_bo(gem);
 
-	return bo->vaddr;
+	dma_buf_map_set_vaddr(map, bo->vaddr);
+
+	return 0;
 }
 
 static void tegra_gem_prime_vunmap(struct dma_buf *buf, void *vaddr)
diff --git a/drivers/media/common/videobuf2/videobuf2-dma-contig.c b/drivers/media/common/videobuf2/videobuf2-dma-contig.c
index ec3446cc45b8..11428287bdf3 100644
--- a/drivers/media/common/videobuf2/videobuf2-dma-contig.c
+++ b/drivers/media/common/videobuf2/videobuf2-dma-contig.c
@@ -81,9 +81,13 @@ static void *vb2_dc_cookie(void *buf_priv)
 static void *vb2_dc_vaddr(void *buf_priv)
 {
 	struct vb2_dc_buf *buf = buf_priv;
+	struct dma_buf_map map;
+	int ret;
 
-	if (!buf->vaddr && buf->db_attach)
-		buf->vaddr = dma_buf_vmap(buf->db_attach->dmabuf);
+	if (!buf->vaddr && buf->db_attach) {
+		ret = dma_buf_vmap(buf->db_attach->dmabuf, &map);
+		buf->vaddr = ret ? NULL : map.vaddr;
+	}
 
 	return buf->vaddr;
 }
@@ -365,11 +369,13 @@ vb2_dc_dmabuf_ops_end_cpu_access(struct dma_buf *dbuf,
 	return 0;
 }
 
-static void *vb2_dc_dmabuf_ops_vmap(struct dma_buf *dbuf)
+static int vb2_dc_dmabuf_ops_vmap(struct dma_buf *dbuf, struct dma_buf_map *map)
 {
 	struct vb2_dc_buf *buf = dbuf->priv;
 
-	return buf->vaddr;
+	dma_buf_map_set_vaddr(map, buf->vaddr);
+
+	return 0;
 }
 
 static int vb2_dc_dmabuf_ops_mmap(struct dma_buf *dbuf,
diff --git a/drivers/media/common/videobuf2/videobuf2-dma-sg.c b/drivers/media/common/videobuf2/videobuf2-dma-sg.c
index 0a40e00f0d7e..c51170e9c1b9 100644
--- a/drivers/media/common/videobuf2/videobuf2-dma-sg.c
+++ b/drivers/media/common/videobuf2/videobuf2-dma-sg.c
@@ -300,14 +300,18 @@ static void vb2_dma_sg_put_userptr(void *buf_priv)
 static void *vb2_dma_sg_vaddr(void *buf_priv)
 {
 	struct vb2_dma_sg_buf *buf = buf_priv;
+	struct dma_buf_map map;
+	int ret;
 
 	BUG_ON(!buf);
 
 	if (!buf->vaddr) {
-		if (buf->db_attach)
-			buf->vaddr = dma_buf_vmap(buf->db_attach->dmabuf);
-		else
+		if (buf->db_attach) {
+			ret = dma_buf_vmap(buf->db_attach->dmabuf, &map);
+			buf->vaddr = ret ? NULL : map.vaddr;
+		} else {
 			buf->vaddr = vm_map_ram(buf->pages, buf->num_pages, -1);
+		}
 	}
 
 	/* add offset in case userptr is not page-aligned */
@@ -489,11 +493,13 @@ vb2_dma_sg_dmabuf_ops_end_cpu_access(struct dma_buf *dbuf,
 	return 0;
 }
 
-static void *vb2_dma_sg_dmabuf_ops_vmap(struct dma_buf *dbuf)
+static int vb2_dma_sg_dmabuf_ops_vmap(struct dma_buf *dbuf, struct dma_buf_map *map)
 {
 	struct vb2_dma_sg_buf *buf = dbuf->priv;
 
-	return vb2_dma_sg_vaddr(buf);
+	dma_buf_map_set_vaddr(map, buf->vaddr);
+
+	return 0;
 }
 
 static int vb2_dma_sg_dmabuf_ops_mmap(struct dma_buf *dbuf,
diff --git a/drivers/media/common/videobuf2/videobuf2-vmalloc.c b/drivers/media/common/videobuf2/videobuf2-vmalloc.c
index c66fda4a65e4..7b68e2379c65 100644
--- a/drivers/media/common/videobuf2/videobuf2-vmalloc.c
+++ b/drivers/media/common/videobuf2/videobuf2-vmalloc.c
@@ -318,11 +318,13 @@ static void vb2_vmalloc_dmabuf_ops_release(struct dma_buf *dbuf)
 	vb2_vmalloc_put(dbuf->priv);
 }
 
-static void *vb2_vmalloc_dmabuf_ops_vmap(struct dma_buf *dbuf)
+static int vb2_vmalloc_dmabuf_ops_vmap(struct dma_buf *dbuf, struct dma_buf_map *map)
 {
 	struct vb2_vmalloc_buf *buf = dbuf->priv;
 
-	return buf->vaddr;
+	dma_buf_map_set_vaddr(map, buf->vaddr);
+
+	return 0;
 }
 
 static int vb2_vmalloc_dmabuf_ops_mmap(struct dma_buf *dbuf,
@@ -374,10 +376,15 @@ static struct dma_buf *vb2_vmalloc_get_dmabuf(void *buf_priv, unsigned long flag
 static int vb2_vmalloc_map_dmabuf(void *mem_priv)
 {
 	struct vb2_vmalloc_buf *buf = mem_priv;
+	struct dma_buf_map map;
+	int ret;
 
-	buf->vaddr = dma_buf_vmap(buf->dbuf);
+	ret = dma_buf_vmap(buf->dbuf, &map);
+	if (ret)
+		return -EFAULT;
+	buf->vaddr = map.vaddr;
 
-	return buf->vaddr ? 0 : -EFAULT;
+	return 0;
 }
 
 static void vb2_vmalloc_unmap_dmabuf(void *mem_priv)
diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
index 7939c55daceb..b39e198533f0 100644
--- a/drivers/misc/fastrpc.c
+++ b/drivers/misc/fastrpc.c
@@ -581,11 +581,13 @@ static void fastrpc_dma_buf_detatch(struct dma_buf *dmabuf,
 	kfree(a);
 }
 
-static void *fastrpc_vmap(struct dma_buf *dmabuf)
+static int fastrpc_vmap(struct dma_buf *dmabuf, struct dma_buf_map *map)
 {
 	struct fastrpc_buf *buf = dmabuf->priv;
 
-	return buf->virt;
+	dma_buf_map_set_vaddr(map, buf->virt);
+
+	return 0;
 }
 
 static int fastrpc_mmap(struct dma_buf *dmabuf,
diff --git a/include/drm/drm_prime.h b/include/drm/drm_prime.h
index bf141e74a1c2..3ee22639ff77 100644
--- a/include/drm/drm_prime.h
+++ b/include/drm/drm_prime.h
@@ -54,6 +54,7 @@ struct device;
 struct dma_buf_export_info;
 struct dma_buf;
 struct dma_buf_attachment;
+struct dma_buf_map;
 
 enum dma_data_direction;
 
@@ -82,7 +83,7 @@ struct sg_table *drm_gem_map_dma_buf(struct dma_buf_attachment *attach,
 void drm_gem_unmap_dma_buf(struct dma_buf_attachment *attach,
 			   struct sg_table *sgt,
 			   enum dma_data_direction dir);
-void *drm_gem_dmabuf_vmap(struct dma_buf *dma_buf);
+int drm_gem_dmabuf_vmap(struct dma_buf *dma_buf, struct dma_buf_map *map);
 void drm_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr);
 
 int drm_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma);
diff --git a/include/linux/dma-buf-map.h b/include/linux/dma-buf-map.h
index 00143c88feb6..5ae732d373eb 100644
--- a/include/linux/dma-buf-map.h
+++ b/include/linux/dma-buf-map.h
@@ -23,6 +23,19 @@ struct dma_buf_map {
 	bool is_iomem;
 };
 
+/**
+ * dma_buf_map_set_vaddr - Sets a dma-buf mapping structure to an address in system memory
+ * @map:	The dma-buf mapping structure
+ * @vaddr:	A system-memory address
+ *
+ * Sets the address and clears the I/O-memory flag.
+ */
+static inline void dma_buf_map_set_vaddr(struct dma_buf_map *map, void *vaddr)
+{
+	map->vaddr = vaddr;
+	map->is_iomem = false;
+}
+
 /* API transition helper */
 static inline bool dma_buf_map_is_vaddr(const struct dma_buf_map *map, const void *vaddr)
 {
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index fcc2ddfb6d18..7237997cfa38 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -266,7 +266,7 @@ struct dma_buf_ops {
 	 */
 	int (*mmap)(struct dma_buf *, struct vm_area_struct *vma);
 
-	void *(*vmap)(struct dma_buf *);
+	int (*vmap)(struct dma_buf *dmabuf, struct dma_buf_map *map);
 	void (*vunmap)(struct dma_buf *, void *vaddr);
 };
 
@@ -503,6 +503,6 @@ int dma_buf_end_cpu_access(struct dma_buf *dma_buf,
 
 int dma_buf_mmap(struct dma_buf *, struct vm_area_struct *,
 		 unsigned long);
-void *dma_buf_vmap(struct dma_buf *);
-void dma_buf_vunmap(struct dma_buf *, void *vaddr);
+int dma_buf_vmap(struct dma_buf *dmabuf, struct dma_buf_map *map);
+void dma_buf_vunmap(struct dma_buf *dmabuf, void *vaddr);
 #endif /* __DMA_BUF_H__ */
-- 
cgit v1.2.3


From 20e76f1a70596590dec32a5d1f598fba04859526 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Fri, 25 Sep 2020 13:56:00 +0200
Subject: dma-buf: Use struct dma_buf_map in dma_buf_vunmap() interfaces
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch updates dma_buf_vunmap() and dma-buf's vunmap callback to
use struct dma_buf_map. The interfaces used to receive a buffer address.
This address is now given in an instance of the structure.

Users of the functions are updated accordingly. This is only an interface
change. It is currently expected that dma-buf memory can be accessed with
system memory load/store operations.

v2:
	* include dma-buf-heaps and i915 selftests (kernel test robot)
	* initialize cma_obj before using it in drm_gem_cma_free_object()
	  (kernel test robot)

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Acked-by: Sumit Semwal <sumit.semwal@linaro.org>
Acked-by: Christian König <christian.koenig@amd.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Acked-by: Tomasz Figa <tfiga@chromium.org>
Acked-by: Sam Ravnborg <sam@ravnborg.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20200925115601.23955-4-tzimmermann@suse.de
---
 drivers/dma-buf/dma-buf.c                          |  8 +++---
 drivers/dma-buf/heaps/heap-helpers.c               |  2 +-
 drivers/gpu/drm/drm_gem_cma_helper.c               |  9 +++---
 drivers/gpu/drm/drm_gem_shmem_helper.c             |  3 +-
 drivers/gpu/drm/drm_prime.c                        |  6 ++--
 drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c        |  5 ++--
 drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c         |  2 +-
 .../gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c   |  6 ++--
 drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c   |  4 +--
 drivers/gpu/drm/tegra/gem.c                        |  5 ++--
 .../media/common/videobuf2/videobuf2-dma-contig.c  |  3 +-
 drivers/media/common/videobuf2/videobuf2-dma-sg.c  |  3 +-
 drivers/media/common/videobuf2/videobuf2-vmalloc.c |  6 ++--
 include/drm/drm_prime.h                            |  2 +-
 include/linux/dma-buf-map.h                        | 32 ++++++++++++++++++++--
 include/linux/dma-buf.h                            |  4 +--
 16 files changed, 66 insertions(+), 34 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index 61bd24d21b38..a6ba4d598f0e 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -1236,21 +1236,21 @@ EXPORT_SYMBOL_GPL(dma_buf_vmap);
 /**
  * dma_buf_vunmap - Unmap a vmap obtained by dma_buf_vmap.
  * @dmabuf:	[in]	buffer to vunmap
- * @vaddr:	[in]	vmap to vunmap
+ * @map:	[in]	vmap pointer to vunmap
  */
-void dma_buf_vunmap(struct dma_buf *dmabuf, void *vaddr)
+void dma_buf_vunmap(struct dma_buf *dmabuf, struct dma_buf_map *map)
 {
 	if (WARN_ON(!dmabuf))
 		return;
 
 	BUG_ON(dma_buf_map_is_null(&dmabuf->vmap_ptr));
 	BUG_ON(dmabuf->vmapping_counter == 0);
-	BUG_ON(!dma_buf_map_is_vaddr(&dmabuf->vmap_ptr, vaddr));
+	BUG_ON(!dma_buf_map_is_equal(&dmabuf->vmap_ptr, map));
 
 	mutex_lock(&dmabuf->lock);
 	if (--dmabuf->vmapping_counter == 0) {
 		if (dmabuf->ops->vunmap)
-			dmabuf->ops->vunmap(dmabuf, vaddr);
+			dmabuf->ops->vunmap(dmabuf, map);
 		dma_buf_map_clear(&dmabuf->vmap_ptr);
 	}
 	mutex_unlock(&dmabuf->lock);
diff --git a/drivers/dma-buf/heaps/heap-helpers.c b/drivers/dma-buf/heaps/heap-helpers.c
index 27e54d9c120c..e9fb2818f2d4 100644
--- a/drivers/dma-buf/heaps/heap-helpers.c
+++ b/drivers/dma-buf/heaps/heap-helpers.c
@@ -252,7 +252,7 @@ static int dma_heap_dma_buf_vmap(struct dma_buf *dmabuf, struct dma_buf_map *map
 	return 0;
 }
 
-static void dma_heap_dma_buf_vunmap(struct dma_buf *dmabuf, void *vaddr)
+static void dma_heap_dma_buf_vunmap(struct dma_buf *dmabuf, struct dma_buf_map *map)
 {
 	struct heap_helper_buffer *buffer = dmabuf->priv;
 
diff --git a/drivers/gpu/drm/drm_gem_cma_helper.c b/drivers/gpu/drm/drm_gem_cma_helper.c
index eb412e45f896..5e9d29961307 100644
--- a/drivers/gpu/drm/drm_gem_cma_helper.c
+++ b/drivers/gpu/drm/drm_gem_cma_helper.c
@@ -175,13 +175,12 @@ drm_gem_cma_create_with_handle(struct drm_file *file_priv,
  */
 void drm_gem_cma_free_object(struct drm_gem_object *gem_obj)
 {
-	struct drm_gem_cma_object *cma_obj;
-
-	cma_obj = to_drm_gem_cma_obj(gem_obj);
+	struct drm_gem_cma_object *cma_obj = to_drm_gem_cma_obj(gem_obj);
+	struct dma_buf_map map = DMA_BUF_MAP_INIT_VADDR(cma_obj->vaddr);
 
 	if (gem_obj->import_attach) {
 		if (cma_obj->vaddr)
-			dma_buf_vunmap(gem_obj->import_attach->dmabuf, cma_obj->vaddr);
+			dma_buf_vunmap(gem_obj->import_attach->dmabuf, &map);
 		drm_prime_gem_destroy(gem_obj, cma_obj->sgt);
 	} else if (cma_obj->vaddr) {
 		dma_free_wc(gem_obj->dev->dev, cma_obj->base.size,
@@ -645,7 +644,7 @@ drm_gem_cma_prime_import_sg_table_vmap(struct drm_device *dev,
 
 	obj = drm_gem_cma_prime_import_sg_table(dev, attach, sgt);
 	if (IS_ERR(obj)) {
-		dma_buf_vunmap(attach->dmabuf, map.vaddr);
+		dma_buf_vunmap(attach->dmabuf, &map);
 		return obj;
 	}
 
diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c
index ad10a57cfece..3c2e8cde69a8 100644
--- a/drivers/gpu/drm/drm_gem_shmem_helper.c
+++ b/drivers/gpu/drm/drm_gem_shmem_helper.c
@@ -337,6 +337,7 @@ EXPORT_SYMBOL(drm_gem_shmem_vmap);
 static void drm_gem_shmem_vunmap_locked(struct drm_gem_shmem_object *shmem)
 {
 	struct drm_gem_object *obj = &shmem->base;
+	struct dma_buf_map map = DMA_BUF_MAP_INIT_VADDR(shmem->vaddr);
 
 	if (WARN_ON_ONCE(!shmem->vmap_use_count))
 		return;
@@ -345,7 +346,7 @@ static void drm_gem_shmem_vunmap_locked(struct drm_gem_shmem_object *shmem)
 		return;
 
 	if (obj->import_attach)
-		dma_buf_vunmap(obj->import_attach->dmabuf, shmem->vaddr);
+		dma_buf_vunmap(obj->import_attach->dmabuf, &map);
 	else
 		vunmap(shmem->vaddr);
 
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 2d75e58d21fe..4910c446db83 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -687,16 +687,16 @@ EXPORT_SYMBOL(drm_gem_dmabuf_vmap);
 /**
  * drm_gem_dmabuf_vunmap - dma_buf vunmap implementation for GEM
  * @dma_buf: buffer to be unmapped
- * @vaddr: the virtual address of the buffer
+ * @map: the virtual address of the buffer
  *
  * Releases a kernel virtual mapping. This can be used as the
  * &dma_buf_ops.vunmap callback. Calls into &drm_gem_object_funcs.vunmap for device specific handling.
  */
-void drm_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr)
+void drm_gem_dmabuf_vunmap(struct dma_buf *dma_buf, struct dma_buf_map *map)
 {
 	struct drm_gem_object *obj = dma_buf->priv;
 
-	drm_gem_vunmap(obj, vaddr);
+	drm_gem_vunmap(obj, map->vaddr);
 }
 EXPORT_SYMBOL(drm_gem_dmabuf_vunmap);
 
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c
index 80a9fc143bbb..135fbff6fecf 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c
@@ -70,9 +70,10 @@ void etnaviv_gem_prime_unpin(struct drm_gem_object *obj)
 
 static void etnaviv_gem_prime_release(struct etnaviv_gem_object *etnaviv_obj)
 {
+	struct dma_buf_map map = DMA_BUF_MAP_INIT_VADDR(etnaviv_obj->vaddr);
+
 	if (etnaviv_obj->vaddr)
-		dma_buf_vunmap(etnaviv_obj->base.import_attach->dmabuf,
-			       etnaviv_obj->vaddr);
+		dma_buf_vunmap(etnaviv_obj->base.import_attach->dmabuf, &map);
 
 	/* Don't drop the pages for imported dmabuf, as they are not
 	 * ours, just free the array we allocated:
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
index 77b363d3000b..fec0e1e3dc3e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
@@ -96,7 +96,7 @@ static int i915_gem_dmabuf_vmap(struct dma_buf *dma_buf, struct dma_buf_map *map
 	return 0;
 }
 
-static void i915_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr)
+static void i915_gem_dmabuf_vunmap(struct dma_buf *dma_buf, struct dma_buf_map *map)
 {
 	struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf);
 
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
index 3aad7643b0b7..b6d43880b0c1 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
@@ -152,7 +152,7 @@ static int igt_dmabuf_import(void *arg)
 
 	err = 0;
 out_dma_map:
-	dma_buf_vunmap(dmabuf, dma_map);
+	dma_buf_vunmap(dmabuf, &map);
 out_obj:
 	i915_gem_object_put(obj);
 out_dmabuf:
@@ -182,7 +182,7 @@ static int igt_dmabuf_import_ownership(void *arg)
 	}
 
 	memset(ptr, 0xc5, PAGE_SIZE);
-	dma_buf_vunmap(dmabuf, ptr);
+	dma_buf_vunmap(dmabuf, &map);
 
 	obj = to_intel_bo(i915_gem_prime_import(&i915->drm, dmabuf));
 	if (IS_ERR(obj)) {
@@ -250,7 +250,7 @@ static int igt_dmabuf_export_vmap(void *arg)
 	memset(ptr, 0xc5, dmabuf->size);
 
 	err = 0;
-	dma_buf_vunmap(dmabuf, ptr);
+	dma_buf_vunmap(dmabuf, &map);
 out:
 	dma_buf_put(dmabuf);
 	return err;
diff --git a/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c b/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c
index dcae46441f7d..7dfef531f6d4 100644
--- a/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c
+++ b/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c
@@ -75,11 +75,11 @@ static int mock_dmabuf_vmap(struct dma_buf *dma_buf, struct dma_buf_map *map)
 	return 0;
 }
 
-static void mock_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr)
+static void mock_dmabuf_vunmap(struct dma_buf *dma_buf, struct dma_buf_map *map)
 {
 	struct mock_dmabuf *mock = to_mock(dma_buf);
 
-	vm_unmap_ram(vaddr, mock->npages);
+	vm_unmap_ram(map->vaddr, mock->npages);
 }
 
 static int mock_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struct *vma)
diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c
index 2b6e06c7a2c5..5df577682878 100644
--- a/drivers/gpu/drm/tegra/gem.c
+++ b/drivers/gpu/drm/tegra/gem.c
@@ -149,11 +149,12 @@ static void *tegra_bo_mmap(struct host1x_bo *bo)
 static void tegra_bo_munmap(struct host1x_bo *bo, void *addr)
 {
 	struct tegra_bo *obj = host1x_to_tegra_bo(bo);
+	struct dma_buf_map map = DMA_BUF_MAP_INIT_VADDR(addr);
 
 	if (obj->vaddr)
 		return;
 	else if (obj->gem.import_attach)
-		dma_buf_vunmap(obj->gem.import_attach->dmabuf, addr);
+		dma_buf_vunmap(obj->gem.import_attach->dmabuf, &map);
 	else
 		vunmap(addr);
 }
@@ -663,7 +664,7 @@ static int tegra_gem_prime_vmap(struct dma_buf *buf, struct dma_buf_map *map)
 	return 0;
 }
 
-static void tegra_gem_prime_vunmap(struct dma_buf *buf, void *vaddr)
+static void tegra_gem_prime_vunmap(struct dma_buf *buf, struct dma_buf_map *map)
 {
 }
 
diff --git a/drivers/media/common/videobuf2/videobuf2-dma-contig.c b/drivers/media/common/videobuf2/videobuf2-dma-contig.c
index 11428287bdf3..a1eb8279b113 100644
--- a/drivers/media/common/videobuf2/videobuf2-dma-contig.c
+++ b/drivers/media/common/videobuf2/videobuf2-dma-contig.c
@@ -648,6 +648,7 @@ static void vb2_dc_unmap_dmabuf(void *mem_priv)
 {
 	struct vb2_dc_buf *buf = mem_priv;
 	struct sg_table *sgt = buf->dma_sgt;
+	struct dma_buf_map map = DMA_BUF_MAP_INIT_VADDR(buf->vaddr);
 
 	if (WARN_ON(!buf->db_attach)) {
 		pr_err("trying to unpin a not attached buffer\n");
@@ -660,7 +661,7 @@ static void vb2_dc_unmap_dmabuf(void *mem_priv)
 	}
 
 	if (buf->vaddr) {
-		dma_buf_vunmap(buf->db_attach->dmabuf, buf->vaddr);
+		dma_buf_vunmap(buf->db_attach->dmabuf, &map);
 		buf->vaddr = NULL;
 	}
 	dma_buf_unmap_attachment(buf->db_attach, sgt, buf->dma_dir);
diff --git a/drivers/media/common/videobuf2/videobuf2-dma-sg.c b/drivers/media/common/videobuf2/videobuf2-dma-sg.c
index c51170e9c1b9..d5157e903e27 100644
--- a/drivers/media/common/videobuf2/videobuf2-dma-sg.c
+++ b/drivers/media/common/videobuf2/videobuf2-dma-sg.c
@@ -580,6 +580,7 @@ static void vb2_dma_sg_unmap_dmabuf(void *mem_priv)
 {
 	struct vb2_dma_sg_buf *buf = mem_priv;
 	struct sg_table *sgt = buf->dma_sgt;
+	struct dma_buf_map map = DMA_BUF_MAP_INIT_VADDR(buf->vaddr);
 
 	if (WARN_ON(!buf->db_attach)) {
 		pr_err("trying to unpin a not attached buffer\n");
@@ -592,7 +593,7 @@ static void vb2_dma_sg_unmap_dmabuf(void *mem_priv)
 	}
 
 	if (buf->vaddr) {
-		dma_buf_vunmap(buf->db_attach->dmabuf, buf->vaddr);
+		dma_buf_vunmap(buf->db_attach->dmabuf, &map);
 		buf->vaddr = NULL;
 	}
 	dma_buf_unmap_attachment(buf->db_attach, sgt, buf->dma_dir);
diff --git a/drivers/media/common/videobuf2/videobuf2-vmalloc.c b/drivers/media/common/videobuf2/videobuf2-vmalloc.c
index 7b68e2379c65..11ba0eb1315b 100644
--- a/drivers/media/common/videobuf2/videobuf2-vmalloc.c
+++ b/drivers/media/common/videobuf2/videobuf2-vmalloc.c
@@ -390,17 +390,19 @@ static int vb2_vmalloc_map_dmabuf(void *mem_priv)
 static void vb2_vmalloc_unmap_dmabuf(void *mem_priv)
 {
 	struct vb2_vmalloc_buf *buf = mem_priv;
+	struct dma_buf_map map = DMA_BUF_MAP_INIT_VADDR(buf->vaddr);
 
-	dma_buf_vunmap(buf->dbuf, buf->vaddr);
+	dma_buf_vunmap(buf->dbuf, &map);
 	buf->vaddr = NULL;
 }
 
 static void vb2_vmalloc_detach_dmabuf(void *mem_priv)
 {
 	struct vb2_vmalloc_buf *buf = mem_priv;
+	struct dma_buf_map map = DMA_BUF_MAP_INIT_VADDR(buf->vaddr);
 
 	if (buf->vaddr)
-		dma_buf_vunmap(buf->dbuf, buf->vaddr);
+		dma_buf_vunmap(buf->dbuf, &map);
 
 	kfree(buf);
 }
diff --git a/include/drm/drm_prime.h b/include/drm/drm_prime.h
index 3ee22639ff77..093f760cc131 100644
--- a/include/drm/drm_prime.h
+++ b/include/drm/drm_prime.h
@@ -84,7 +84,7 @@ void drm_gem_unmap_dma_buf(struct dma_buf_attachment *attach,
 			   struct sg_table *sgt,
 			   enum dma_data_direction dir);
 int drm_gem_dmabuf_vmap(struct dma_buf *dma_buf, struct dma_buf_map *map);
-void drm_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr);
+void drm_gem_dmabuf_vunmap(struct dma_buf *dma_buf, struct dma_buf_map *map);
 
 int drm_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma);
 int drm_gem_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struct *vma);
diff --git a/include/linux/dma-buf-map.h b/include/linux/dma-buf-map.h
index 5ae732d373eb..c173a4abf4ba 100644
--- a/include/linux/dma-buf-map.h
+++ b/include/linux/dma-buf-map.h
@@ -23,6 +23,16 @@ struct dma_buf_map {
 	bool is_iomem;
 };
 
+/**
+ * DMA_BUF_MAP_INIT_VADDR - Initializes struct dma_buf_map to an address in system memory
+ * @vaddr:	A system-memory address
+ */
+#define DMA_BUF_MAP_INIT_VADDR(vaddr_) \
+	{ \
+		.vaddr = (vaddr_), \
+		.is_iomem = false, \
+	}
+
 /**
  * dma_buf_map_set_vaddr - Sets a dma-buf mapping structure to an address in system memory
  * @map:	The dma-buf mapping structure
@@ -36,10 +46,26 @@ static inline void dma_buf_map_set_vaddr(struct dma_buf_map *map, void *vaddr)
 	map->is_iomem = false;
 }
 
-/* API transition helper */
-static inline bool dma_buf_map_is_vaddr(const struct dma_buf_map *map, const void *vaddr)
+/**
+ * dma_buf_map_is_equal - Compares two dma-buf mapping structures for equality
+ * @lhs:	The dma-buf mapping structure
+ * @rhs:	A dma-buf mapping structure to compare with
+ *
+ * Two dma-buf mapping structures are equal if they both refer to the same type of memory
+ * and to the same address within that memory.
+ *
+ * Returns:
+ * True is both structures are equal, or false otherwise.
+ */
+static inline bool dma_buf_map_is_equal(const struct dma_buf_map *lhs,
+					const struct dma_buf_map *rhs)
 {
-	return !map->is_iomem && (map->vaddr == vaddr);
+	if (lhs->is_iomem != rhs->is_iomem)
+		return false;
+	else if (lhs->is_iomem)
+		return lhs->vaddr_iomem == rhs->vaddr_iomem;
+	else
+		return lhs->vaddr == rhs->vaddr;
 }
 
 /**
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index 7237997cfa38..cf77cc15f4ba 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -267,7 +267,7 @@ struct dma_buf_ops {
 	int (*mmap)(struct dma_buf *, struct vm_area_struct *vma);
 
 	int (*vmap)(struct dma_buf *dmabuf, struct dma_buf_map *map);
-	void (*vunmap)(struct dma_buf *, void *vaddr);
+	void (*vunmap)(struct dma_buf *dmabuf, struct dma_buf_map *map);
 };
 
 /**
@@ -504,5 +504,5 @@ int dma_buf_end_cpu_access(struct dma_buf *dma_buf,
 int dma_buf_mmap(struct dma_buf *, struct vm_area_struct *,
 		 unsigned long);
 int dma_buf_vmap(struct dma_buf *dmabuf, struct dma_buf_map *map);
-void dma_buf_vunmap(struct dma_buf *dmabuf, void *vaddr);
+void dma_buf_vunmap(struct dma_buf *dmabuf, struct dma_buf_map *map);
 #endif /* __DMA_BUF_H__ */
-- 
cgit v1.2.3


From ccc22d41bd9acec58cdc7c3b012e1887aba40af4 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Fri, 25 Sep 2020 13:56:01 +0200
Subject: dma-buf: Document struct dma_buf_map
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch adds struct dma_buf_map and its helpers to the documentation. A
short tutorial is included.

v3:
	* update documentation in a separate patch
	* expand docs (Daniel)
	* carry-over acks from patch 1

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Acked-by: Sumit Semwal <sumit.semwal@linaro.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20200925115601.23955-5-tzimmermann@suse.de
---
 Documentation/driver-api/dma-buf.rst |  9 +++++
 include/linux/dma-buf-map.h          | 72 ++++++++++++++++++++++++++++++++++++
 2 files changed, 81 insertions(+)

(limited to 'include/linux')

diff --git a/Documentation/driver-api/dma-buf.rst b/Documentation/driver-api/dma-buf.rst
index 13ea0cc0a3fa..6dbcc4714b0b 100644
--- a/Documentation/driver-api/dma-buf.rst
+++ b/Documentation/driver-api/dma-buf.rst
@@ -115,6 +115,15 @@ Kernel Functions and Structures Reference
 .. kernel-doc:: include/linux/dma-buf.h
    :internal:
 
+Buffer Mapping Helpers
+~~~~~~~~~~~~~~~~~~~~~~
+
+.. kernel-doc:: include/linux/dma-buf-map.h
+   :doc: overview
+
+.. kernel-doc:: include/linux/dma-buf-map.h
+   :internal:
+
 Reservation Objects
 -------------------
 
diff --git a/include/linux/dma-buf-map.h b/include/linux/dma-buf-map.h
index c173a4abf4ba..fd1aba545fdf 100644
--- a/include/linux/dma-buf-map.h
+++ b/include/linux/dma-buf-map.h
@@ -8,6 +8,78 @@
 
 #include <linux/io.h>
 
+/**
+ * DOC: overview
+ *
+ * Calling dma-buf's vmap operation returns a pointer to the buffer's memory.
+ * Depending on the location of the buffer, users may have to access it with
+ * I/O operations or memory load/store operations. For example, copying to
+ * system memory could be done with memcpy(), copying to I/O memory would be
+ * done with memcpy_toio().
+ *
+ * .. code-block:: c
+ *
+ *	void *vaddr = ...; // pointer to system memory
+ *	memcpy(vaddr, src, len);
+ *
+ *	void *vaddr_iomem = ...; // pointer to I/O memory
+ *	memcpy_toio(vaddr, _iomem, src, len);
+ *
+ * When using dma-buf's vmap operation, the returned pointer is encoded as
+ * :c:type:`struct dma_buf_map <dma_buf_map>`.
+ * :c:type:`struct dma_buf_map <dma_buf_map>` stores the buffer's address in
+ * system or I/O memory and a flag that signals the required method of
+ * accessing the buffer. Use the returned instance and the helper functions
+ * to access the buffer's memory in the correct way.
+ *
+ * Open-coding access to :c:type:`struct dma_buf_map <dma_buf_map>` is
+ * considered bad style. Rather then accessing its fields directly, use one
+ * of the provided helper functions, or implement your own. For example,
+ * instances of :c:type:`struct dma_buf_map <dma_buf_map>` can be initialized
+ * statically with DMA_BUF_MAP_INIT_VADDR(), or at runtime with
+ * dma_buf_map_set_vaddr(). These helpers will set an address in system memory.
+ *
+ * .. code-block:: c
+ *
+ *	struct dma_buf_map map = DMA_BUF_MAP_INIT_VADDR(0xdeadbeaf);
+ *
+ *	dma_buf_map_set_vaddr(&map. 0xdeadbeaf);
+ *
+ * Test if a mapping is valid with either dma_buf_map_is_set() or
+ * dma_buf_map_is_null().
+ *
+ * .. code-block:: c
+ *
+ *	if (dma_buf_map_is_set(&map) != dma_buf_map_is_null(&map))
+ *		// always true
+ *
+ * Instances of :c:type:`struct dma_buf_map <dma_buf_map>` can be compared
+ * for equality with dma_buf_map_is_equal(). Mappings the point to different
+ * memory spaces, system or I/O, are never equal. That's even true if both
+ * spaces are located in the same address space, both mappings contain the
+ * same address value, or both mappings refer to NULL.
+ *
+ * .. code-block:: c
+ *
+ *	struct dma_buf_map sys_map; // refers to system memory
+ *	struct dma_buf_map io_map; // refers to I/O memory
+ *
+ *	if (dma_buf_map_is_equal(&sys_map, &io_map))
+ *		// always false
+ *
+ * Instances of struct dma_buf_map do not have to be cleaned up, but
+ * can be cleared to NULL with dma_buf_map_clear(). Cleared mappings
+ * always refer to system memory.
+ *
+ * The type :c:type:`struct dma_buf_map <dma_buf_map>` and its helpers are
+ * actually independent from the dma-buf infrastructure. When sharing buffers
+ * among devices, drivers have to know the location of the memory to access
+ * the buffers in a safe way. :c:type:`struct dma_buf_map <dma_buf_map>`
+ * solves this problem for dma-buf and its users. If other drivers or
+ * sub-systems require similar functionality, the type could be generalized
+ * and moved to a more prominent header file.
+ */
+
 /**
  * struct dma_buf_map - Pointer to vmap'ed dma-buf memory.
  * @vaddr_iomem:	The buffer's address if in I/O memory
-- 
cgit v1.2.3


From 48404cf57852224c052e2e40d4dc50dd398c7a58 Mon Sep 17 00:00:00 2001
From: Michael Auchter <michael.auchter@ni.com>
Date: Tue, 22 Sep 2020 09:44:20 -0500
Subject: iio: adc: ad7291: convert to device tree

There are no in-tree users of the platform data for this driver, so
remove it and convert the driver to use device tree instead.

Signed-off-by: Michael Auchter <michael.auchter@ni.com>
Link: https://lore.kernel.org/r/20200922144422.542669-1-michael.auchter@ni.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad7291.c             | 35 +++++++++++++++++++++--------------
 include/linux/platform_data/ad7291.h | 13 -------------
 2 files changed, 21 insertions(+), 27 deletions(-)
 delete mode 100644 include/linux/platform_data/ad7291.h

(limited to 'include/linux')

diff --git a/drivers/iio/adc/ad7291.c b/drivers/iio/adc/ad7291.c
index 62fde2aad282..2301a0e27f23 100644
--- a/drivers/iio/adc/ad7291.c
+++ b/drivers/iio/adc/ad7291.c
@@ -20,8 +20,6 @@
 #include <linux/iio/sysfs.h>
 #include <linux/iio/events.h>
 
-#include <linux/platform_data/ad7291.h>
-
 /*
  * Simplified handling
  *
@@ -465,7 +463,6 @@ static const struct iio_info ad7291_info = {
 static int ad7291_probe(struct i2c_client *client,
 			const struct i2c_device_id *id)
 {
-	struct ad7291_platform_data *pdata = client->dev.platform_data;
 	struct ad7291_chip_info *chip;
 	struct iio_dev *indio_dev;
 	int ret;
@@ -475,16 +472,6 @@ static int ad7291_probe(struct i2c_client *client,
 		return -ENOMEM;
 	chip = iio_priv(indio_dev);
 
-	if (pdata && pdata->use_external_ref) {
-		chip->reg = devm_regulator_get(&client->dev, "vref");
-		if (IS_ERR(chip->reg))
-			return PTR_ERR(chip->reg);
-
-		ret = regulator_enable(chip->reg);
-		if (ret)
-			return ret;
-	}
-
 	mutex_init(&chip->state_lock);
 	/* this is only used for device removal purposes */
 	i2c_set_clientdata(client, indio_dev);
@@ -495,8 +482,21 @@ static int ad7291_probe(struct i2c_client *client,
 			AD7291_T_SENSE_MASK | /* Tsense always enabled */
 			AD7291_ALERT_POLARITY; /* set irq polarity low level */
 
-	if (pdata && pdata->use_external_ref)
+	chip->reg = devm_regulator_get_optional(&client->dev, "vref");
+	if (IS_ERR(chip->reg)) {
+		if (PTR_ERR(chip->reg) != -ENODEV)
+			return PTR_ERR(chip->reg);
+
+		chip->reg = NULL;
+	}
+
+	if (chip->reg) {
+		ret = regulator_enable(chip->reg);
+		if (ret)
+			return ret;
+
 		chip->command |= AD7291_EXT_REF;
+	}
 
 	indio_dev->name = id->name;
 	indio_dev->channels = ad7291_channels;
@@ -567,9 +567,16 @@ static const struct i2c_device_id ad7291_id[] = {
 
 MODULE_DEVICE_TABLE(i2c, ad7291_id);
 
+static const struct of_device_id ad7291_of_match[] = {
+	{ .compatible = "adi,ad7291" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, ad7291_of_match);
+
 static struct i2c_driver ad7291_driver = {
 	.driver = {
 		.name = KBUILD_MODNAME,
+		.of_match_table = ad7291_of_match,
 	},
 	.probe = ad7291_probe,
 	.remove = ad7291_remove,
diff --git a/include/linux/platform_data/ad7291.h b/include/linux/platform_data/ad7291.h
deleted file mode 100644
index b1fd1530c9a5..000000000000
--- a/include/linux/platform_data/ad7291.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __IIO_AD7291_H__
-#define __IIO_AD7291_H__
-
-/**
- * struct ad7291_platform_data - AD7291 platform data
- * @use_external_ref: Whether to use an external or internal reference voltage
- */
-struct ad7291_platform_data {
-	bool use_external_ref;
-};
-
-#endif
-- 
cgit v1.2.3


From 25918a9c641c3c73ae94354605860c06fd73a05e Mon Sep 17 00:00:00 2001
From: Alexandru Ardelean <alexandru.ardelean@analog.com>
Date: Wed, 23 Sep 2020 15:18:10 +0300
Subject: iio: buffer-dmaengine: remove non managed alloc/free

This is to encourage the use of devm_iio_dmaengine_buffer_alloc().
Currently the managed version of the DMAEngine buffer alloc is the only
function used from this part of the framework.

Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Link: https://lore.kernel.org/r/20200923121810.944075-1-alexandru.ardelean@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/buffer/industrialio-buffer-dmaengine.c | 6 ++----
 include/linux/iio/buffer-dmaengine.h               | 4 ----
 2 files changed, 2 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iio/buffer/industrialio-buffer-dmaengine.c b/drivers/iio/buffer/industrialio-buffer-dmaengine.c
index 5789bda0745b..93b4e9e6bb55 100644
--- a/drivers/iio/buffer/industrialio-buffer-dmaengine.c
+++ b/drivers/iio/buffer/industrialio-buffer-dmaengine.c
@@ -159,7 +159,7 @@ static const struct attribute *iio_dmaengine_buffer_attrs[] = {
  * Once done using the buffer iio_dmaengine_buffer_free() should be used to
  * release it.
  */
-struct iio_buffer *iio_dmaengine_buffer_alloc(struct device *dev,
+static struct iio_buffer *iio_dmaengine_buffer_alloc(struct device *dev,
 	const char *channel)
 {
 	struct dmaengine_buffer *dmaengine_buffer;
@@ -211,7 +211,6 @@ err_free:
 	kfree(dmaengine_buffer);
 	return ERR_PTR(ret);
 }
-EXPORT_SYMBOL(iio_dmaengine_buffer_alloc);
 
 /**
  * iio_dmaengine_buffer_free() - Free dmaengine buffer
@@ -219,7 +218,7 @@ EXPORT_SYMBOL(iio_dmaengine_buffer_alloc);
  *
  * Frees a buffer previously allocated with iio_dmaengine_buffer_alloc().
  */
-void iio_dmaengine_buffer_free(struct iio_buffer *buffer)
+static void iio_dmaengine_buffer_free(struct iio_buffer *buffer)
 {
 	struct dmaengine_buffer *dmaengine_buffer =
 		iio_buffer_to_dmaengine_buffer(buffer);
@@ -229,7 +228,6 @@ void iio_dmaengine_buffer_free(struct iio_buffer *buffer)
 
 	iio_buffer_put(buffer);
 }
-EXPORT_SYMBOL_GPL(iio_dmaengine_buffer_free);
 
 static void __devm_iio_dmaengine_buffer_free(struct device *dev, void *res)
 {
diff --git a/include/linux/iio/buffer-dmaengine.h b/include/linux/iio/buffer-dmaengine.h
index 0e503db71289..5b502291d6a4 100644
--- a/include/linux/iio/buffer-dmaengine.h
+++ b/include/linux/iio/buffer-dmaengine.h
@@ -10,10 +10,6 @@
 struct iio_buffer;
 struct device;
 
-struct iio_buffer *iio_dmaengine_buffer_alloc(struct device *dev,
-	const char *channel);
-void iio_dmaengine_buffer_free(struct iio_buffer *buffer);
-
 struct iio_buffer *devm_iio_dmaengine_buffer_alloc(struct device *dev,
 						   const char *channel);
 
-- 
cgit v1.2.3


From 2e2366c2d14193d3b95bab1fb484a9377224962b Mon Sep 17 00:00:00 2001
From: Alexandru Ardelean <alexandru.ardelean@analog.com>
Date: Wed, 23 Sep 2020 16:03:39 +0300
Subject: iio: cros_ec: unify hw fifo attributes into the core file

The intent here is to minimize the use of iio_buffer_set_attrs(). Since we
are planning to add support for multiple IIO buffers per IIO device, the
issue has to do with:
1. Accessing 'indio_dev->buffer' directly (as is done with
   'iio_buffer_set_attrs(indio_dev->buffer, <attrs>)').
2. The way that the buffer attributes would get handled or expanded when
   there are more buffers per IIO device. Current a sysfs kobj_type expands
   into a 'device' object that expands into an 'iio_dev' object.
   We will need to change this, so that the sysfs attributes for IIO
   buffers expand into IIO buffers at some point.

Right now, the current IIO framework works fine for the
'1 IIO device == 1 IIO buffer' case (that is now).

Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Reviewed-by: Guenter Roeck <groeck@chromium.org>
Link: https://lore.kernel.org/r/20200923130339.997902-1-alexandru.ardelean@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/accel/cros_ec_accel_legacy.c                  |  2 +-
 drivers/iio/common/cros_ec_sensors/cros_ec_lid_angle.c    |  3 ++-
 drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c      |  5 ++---
 drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c | 11 ++++++++---
 drivers/iio/light/cros_ec_light_prox.c                    |  5 ++---
 drivers/iio/pressure/cros_ec_baro.c                       |  5 ++---
 include/linux/iio/common/cros_ec_sensors_core.h           |  4 ++--
 7 files changed, 19 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iio/accel/cros_ec_accel_legacy.c b/drivers/iio/accel/cros_ec_accel_legacy.c
index b6f3471b62dc..8f1232c38e0d 100644
--- a/drivers/iio/accel/cros_ec_accel_legacy.c
+++ b/drivers/iio/accel/cros_ec_accel_legacy.c
@@ -215,7 +215,7 @@ static int cros_ec_accel_legacy_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	ret = cros_ec_sensors_core_init(pdev, indio_dev, true,
-					cros_ec_sensors_capture, NULL);
+					cros_ec_sensors_capture, NULL, false);
 	if (ret)
 		return ret;
 
diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_lid_angle.c b/drivers/iio/common/cros_ec_sensors/cros_ec_lid_angle.c
index af801e203623..752f59037715 100644
--- a/drivers/iio/common/cros_ec_sensors/cros_ec_lid_angle.c
+++ b/drivers/iio/common/cros_ec_sensors/cros_ec_lid_angle.c
@@ -97,7 +97,8 @@ static int cros_ec_lid_angle_probe(struct platform_device *pdev)
 	if (!indio_dev)
 		return -ENOMEM;
 
-	ret = cros_ec_sensors_core_init(pdev, indio_dev, false, NULL, NULL);
+	ret = cros_ec_sensors_core_init(pdev, indio_dev, false, NULL,
+					NULL, false);
 	if (ret)
 		return ret;
 
diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c
index 130ab8ce0269..57038ca48d93 100644
--- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c
+++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c
@@ -236,12 +236,11 @@ static int cros_ec_sensors_probe(struct platform_device *pdev)
 
 	ret = cros_ec_sensors_core_init(pdev, indio_dev, true,
 					cros_ec_sensors_capture,
-					cros_ec_sensors_push_data);
+					cros_ec_sensors_push_data,
+					true);
 	if (ret)
 		return ret;
 
-	iio_buffer_set_attrs(indio_dev->buffer, cros_ec_sensor_fifo_attributes);
-
 	indio_dev->info = &ec_sensors_info;
 	state = iio_priv(indio_dev);
 	for (channel = state->channels, i = CROS_EC_SENSOR_X;
diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c
index 1bc6efa47316..c62cacc04672 100644
--- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c
+++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c
@@ -177,12 +177,11 @@ static ssize_t hwfifo_watermark_max_show(struct device *dev,
 
 static IIO_DEVICE_ATTR_RO(hwfifo_watermark_max, 0);
 
-const struct attribute *cros_ec_sensor_fifo_attributes[] = {
+static const struct attribute *cros_ec_sensor_fifo_attributes[] = {
 	&iio_dev_attr_hwfifo_timeout.dev_attr.attr,
 	&iio_dev_attr_hwfifo_watermark_max.dev_attr.attr,
 	NULL,
 };
-EXPORT_SYMBOL_GPL(cros_ec_sensor_fifo_attributes);
 
 int cros_ec_sensors_push_data(struct iio_dev *indio_dev,
 			      s16 *data,
@@ -241,6 +240,7 @@ static void cros_ec_sensors_core_clean(void *arg)
  *    for backward compatibility.
  * @push_data:          function to call when cros_ec_sensorhub receives
  *    a sample for that sensor.
+ * @has_hw_fifo:	Set true if this device has/uses a HW FIFO
  *
  * Return: 0 on success, -errno on failure.
  */
@@ -248,7 +248,8 @@ int cros_ec_sensors_core_init(struct platform_device *pdev,
 			      struct iio_dev *indio_dev,
 			      bool physical_device,
 			      cros_ec_sensors_capture_t trigger_capture,
-			      cros_ec_sensorhub_push_data_cb_t push_data)
+			      cros_ec_sensorhub_push_data_cb_t push_data,
+			      bool has_hw_fifo)
 {
 	struct device *dev = &pdev->dev;
 	struct cros_ec_sensors_core_state *state = iio_priv(indio_dev);
@@ -361,6 +362,10 @@ int cros_ec_sensors_core_init(struct platform_device *pdev,
 					NULL);
 			if (ret)
 				return ret;
+
+			if (has_hw_fifo)
+				iio_buffer_set_attrs(indio_dev->buffer,
+						     cros_ec_sensor_fifo_attributes);
 		}
 	}
 
diff --git a/drivers/iio/light/cros_ec_light_prox.c b/drivers/iio/light/cros_ec_light_prox.c
index fed79ba27fda..75d6b5fcf2cc 100644
--- a/drivers/iio/light/cros_ec_light_prox.c
+++ b/drivers/iio/light/cros_ec_light_prox.c
@@ -182,12 +182,11 @@ static int cros_ec_light_prox_probe(struct platform_device *pdev)
 
 	ret = cros_ec_sensors_core_init(pdev, indio_dev, true,
 					cros_ec_sensors_capture,
-					cros_ec_sensors_push_data);
+					cros_ec_sensors_push_data,
+					true);
 	if (ret)
 		return ret;
 
-	iio_buffer_set_attrs(indio_dev->buffer, cros_ec_sensor_fifo_attributes);
-
 	indio_dev->info = &cros_ec_light_prox_info;
 	state = iio_priv(indio_dev);
 	state->core.type = state->core.resp->info.type;
diff --git a/drivers/iio/pressure/cros_ec_baro.c b/drivers/iio/pressure/cros_ec_baro.c
index f0938b6fbba0..aa043cb9ac42 100644
--- a/drivers/iio/pressure/cros_ec_baro.c
+++ b/drivers/iio/pressure/cros_ec_baro.c
@@ -139,12 +139,11 @@ static int cros_ec_baro_probe(struct platform_device *pdev)
 
 	ret = cros_ec_sensors_core_init(pdev, indio_dev, true,
 					cros_ec_sensors_capture,
-					cros_ec_sensors_push_data);
+					cros_ec_sensors_push_data,
+					true);
 	if (ret)
 		return ret;
 
-	iio_buffer_set_attrs(indio_dev->buffer, cros_ec_sensor_fifo_attributes);
-
 	indio_dev->info = &cros_ec_baro_info;
 	state = iio_priv(indio_dev);
 	state->core.type = state->core.resp->info.type;
diff --git a/include/linux/iio/common/cros_ec_sensors_core.h b/include/linux/iio/common/cros_ec_sensors_core.h
index caa8bb279a34..c9b80be82440 100644
--- a/include/linux/iio/common/cros_ec_sensors_core.h
+++ b/include/linux/iio/common/cros_ec_sensors_core.h
@@ -96,7 +96,8 @@ struct platform_device;
 int cros_ec_sensors_core_init(struct platform_device *pdev,
 			      struct iio_dev *indio_dev, bool physical_device,
 			      cros_ec_sensors_capture_t trigger_capture,
-			      cros_ec_sensorhub_push_data_cb_t push_data);
+			      cros_ec_sensorhub_push_data_cb_t push_data,
+			      bool has_hw_fifo);
 
 irqreturn_t cros_ec_sensors_capture(int irq, void *p);
 int cros_ec_sensors_push_data(struct iio_dev *indio_dev,
@@ -125,6 +126,5 @@ extern const struct dev_pm_ops cros_ec_sensors_pm_ops;
 
 /* List of extended channel specification for all sensors. */
 extern const struct iio_chan_spec_ext_info cros_ec_sensors_ext_info[];
-extern const struct attribute *cros_ec_sensor_fifo_attributes[];
 
 #endif  /* __CROS_EC_SENSORS_CORE_H */
-- 
cgit v1.2.3


From 232f4eb6393f42f7f9418560ae9228e747fc6faf Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Wed, 23 Sep 2020 09:56:14 +0200
Subject: efi: pstore: disentangle from deprecated efivars module

The EFI pstore implementation relies on the 'efivars' abstraction,
which encapsulates the EFI variable store in a way that can be
overridden by other backing stores, like the Google SMI one.

On top of that, the EFI pstore implementation also relies on the
efivars.ko module, which is a separate layer built on top of the
'efivars' abstraction that exposes the [deprecated] sysfs entries
for each variable that exists in the backing store.

Since the efivars.ko module is deprecated, and all users appear to
have moved to the efivarfs file system instead, let's prepare for
its removal, by removing EFI pstore's dependency on it.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/Kconfig      |  2 +-
 drivers/firmware/efi/efi-pstore.c | 76 ++++++++++++++++++++++++++++++++++++---
 drivers/firmware/efi/efivars.c    | 41 +--------------------
 include/linux/efi.h               |  4 ---
 4 files changed, 74 insertions(+), 49 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig
index 3939699e62fe..dd8d10817bdf 100644
--- a/drivers/firmware/efi/Kconfig
+++ b/drivers/firmware/efi/Kconfig
@@ -26,7 +26,7 @@ config EFI_ESRT
 
 config EFI_VARS_PSTORE
 	tristate "Register efivars backend for pstore"
-	depends on EFI_VARS && PSTORE
+	depends on PSTORE
 	default y
 	help
 	  Say Y here to enable use efivars as a backend to pstore. This
diff --git a/drivers/firmware/efi/efi-pstore.c b/drivers/firmware/efi/efi-pstore.c
index feb7fe6f2da7..785f5e6b3a41 100644
--- a/drivers/firmware/efi/efi-pstore.c
+++ b/drivers/firmware/efi/efi-pstore.c
@@ -8,6 +8,8 @@
 
 #define DUMP_NAME_LEN 66
 
+#define EFIVARS_DATA_SIZE_MAX 1024
+
 static bool efivars_pstore_disable =
 	IS_ENABLED(CONFIG_EFI_VARS_PSTORE_DEFAULT_DISABLE);
 
@@ -18,6 +20,8 @@ module_param_named(pstore_disable, efivars_pstore_disable, bool, 0644);
 	 EFI_VARIABLE_BOOTSERVICE_ACCESS | \
 	 EFI_VARIABLE_RUNTIME_ACCESS)
 
+static LIST_HEAD(efi_pstore_list);
+
 static int efi_pstore_open(struct pstore_info *psi)
 {
 	psi->data = NULL;
@@ -126,7 +130,7 @@ static inline int __efi_pstore_scan_sysfs_exit(struct efivar_entry *entry,
 	if (entry->deleting) {
 		list_del(&entry->list);
 		efivar_entry_iter_end();
-		efivar_unregister(entry);
+		kfree(entry);
 		if (efivar_entry_iter_begin())
 			return -EINTR;
 	} else if (turn_off_scanning)
@@ -169,7 +173,7 @@ static int efi_pstore_sysfs_entry_iter(struct pstore_record *record)
 {
 	struct efivar_entry **pos = (struct efivar_entry **)&record->psi->data;
 	struct efivar_entry *entry, *n;
-	struct list_head *head = &efivar_sysfs_list;
+	struct list_head *head = &efi_pstore_list;
 	int size = 0;
 	int ret;
 
@@ -314,12 +318,12 @@ static int efi_pstore_erase_name(const char *name)
 	if (efivar_entry_iter_begin())
 		return -EINTR;
 
-	found = __efivar_entry_iter(efi_pstore_erase_func, &efivar_sysfs_list,
+	found = __efivar_entry_iter(efi_pstore_erase_func, &efi_pstore_list,
 				    efi_name, &entry);
 	efivar_entry_iter_end();
 
 	if (found && !entry->scanning)
-		efivar_unregister(entry);
+		kfree(entry);
 
 	return found ? 0 : -ENOENT;
 }
@@ -354,14 +358,76 @@ static struct pstore_info efi_pstore_info = {
 	.erase		= efi_pstore_erase,
 };
 
+static int efi_pstore_callback(efi_char16_t *name, efi_guid_t vendor,
+			       unsigned long name_size, void *data)
+{
+	struct efivar_entry *entry;
+	int ret;
+
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+
+	memcpy(entry->var.VariableName, name, name_size);
+	entry->var.VendorGuid = vendor;
+
+	ret = efivar_entry_add(entry, &efi_pstore_list);
+	if (ret)
+		kfree(entry);
+
+	return ret;
+}
+
+static int efi_pstore_update_entry(efi_char16_t *name, efi_guid_t vendor,
+				   unsigned long name_size, void *data)
+{
+	struct efivar_entry *entry = data;
+
+	if (efivar_entry_find(name, vendor, &efi_pstore_list, false))
+		return 0;
+
+	memcpy(entry->var.VariableName, name, name_size);
+	memcpy(&(entry->var.VendorGuid), &vendor, sizeof(efi_guid_t));
+
+	return 1;
+}
+
+static void efi_pstore_update_entries(struct work_struct *work)
+{
+	struct efivar_entry *entry;
+	int err;
+
+	/* Add new sysfs entries */
+	while (1) {
+		entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+		if (!entry)
+			return;
+
+		err = efivar_init(efi_pstore_update_entry, entry,
+				  false, &efi_pstore_list);
+		if (!err)
+			break;
+
+		efivar_entry_add(entry, &efi_pstore_list);
+	}
+
+	kfree(entry);
+}
+
 static __init int efivars_pstore_init(void)
 {
+	int ret;
+
 	if (!efivars_kobject() || !efivar_supports_writes())
 		return 0;
 
 	if (efivars_pstore_disable)
 		return 0;
 
+	ret = efivar_init(efi_pstore_callback, NULL, true, &efi_pstore_list);
+	if (ret)
+		return ret;
+
 	efi_pstore_info.buf = kmalloc(4096, GFP_KERNEL);
 	if (!efi_pstore_info.buf)
 		return -ENOMEM;
@@ -374,6 +440,8 @@ static __init int efivars_pstore_init(void)
 		efi_pstore_info.bufsize = 0;
 	}
 
+	INIT_WORK(&efivar_work, efi_pstore_update_entries);
+
 	return 0;
 }
 
diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c
index dcea137142b3..f39321dbc29f 100644
--- a/drivers/firmware/efi/efivars.c
+++ b/drivers/firmware/efi/efivars.c
@@ -24,8 +24,7 @@ MODULE_LICENSE("GPL");
 MODULE_VERSION(EFIVARS_VERSION);
 MODULE_ALIAS("platform:efivars");
 
-LIST_HEAD(efivar_sysfs_list);
-EXPORT_SYMBOL_GPL(efivar_sysfs_list);
+static LIST_HEAD(efivar_sysfs_list);
 
 static struct kset *efivars_kset;
 
@@ -591,42 +590,6 @@ out_free:
 	return error;
 }
 
-static int efivar_update_sysfs_entry(efi_char16_t *name, efi_guid_t vendor,
-				     unsigned long name_size, void *data)
-{
-	struct efivar_entry *entry = data;
-
-	if (efivar_entry_find(name, vendor, &efivar_sysfs_list, false))
-		return 0;
-
-	memcpy(entry->var.VariableName, name, name_size);
-	memcpy(&(entry->var.VendorGuid), &vendor, sizeof(efi_guid_t));
-
-	return 1;
-}
-
-static void efivar_update_sysfs_entries(struct work_struct *work)
-{
-	struct efivar_entry *entry;
-	int err;
-
-	/* Add new sysfs entries */
-	while (1) {
-		entry = kzalloc(sizeof(*entry), GFP_KERNEL);
-		if (!entry)
-			return;
-
-		err = efivar_init(efivar_update_sysfs_entry, entry,
-				  false, &efivar_sysfs_list);
-		if (!err)
-			break;
-
-		efivar_create_sysfs_entry(entry);
-	}
-
-	kfree(entry);
-}
-
 static int efivars_sysfs_callback(efi_char16_t *name, efi_guid_t vendor,
 				  unsigned long name_size, void *data)
 {
@@ -701,8 +664,6 @@ int efivars_sysfs_init(void)
 		return error;
 	}
 
-	INIT_WORK(&efivar_work, efivar_update_sysfs_entries);
-
 	return 0;
 }
 EXPORT_SYMBOL_GPL(efivars_sysfs_init);
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 4a2332f146eb..7066c11ab82f 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -986,8 +986,6 @@ struct efivar_entry {
 	bool deleting;
 };
 
-extern struct list_head efivar_sysfs_list;
-
 static inline void
 efivar_unregister(struct efivar_entry *var)
 {
@@ -1045,8 +1043,6 @@ void efivar_run_worker(void);
 #if defined(CONFIG_EFI_VARS) || defined(CONFIG_EFI_VARS_MODULE)
 int efivars_sysfs_init(void);
 
-#define EFIVARS_DATA_SIZE_MAX 1024
-
 #endif /* CONFIG_EFI_VARS */
 extern bool efi_capsule_pending(int *reset_type);
 
-- 
cgit v1.2.3


From c9b51a2dbfe7f47643e133bf48e1bf28f1b85d2a Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Wed, 23 Sep 2020 10:07:49 +0200
Subject: efi: pstore: move workqueue handling out of efivars

The worker thread that gets kicked off to sync the state of the
EFI variable list is only used by the EFI pstore implementation,
and is defined in its source file. So let's move its scheduling
there as well. Since our efivar_init() scan will bail on duplicate
entries, there is no need to disable the workqueue like we did
before, so we can run it unconditionally.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/efi-pstore.c |  7 +++++--
 drivers/firmware/efi/vars.c       | 21 ---------------------
 include/linux/efi.h               |  3 ---
 3 files changed, 5 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/efi/efi-pstore.c b/drivers/firmware/efi/efi-pstore.c
index 785f5e6b3a41..0ef086e43090 100644
--- a/drivers/firmware/efi/efi-pstore.c
+++ b/drivers/firmware/efi/efi-pstore.c
@@ -21,6 +21,7 @@ module_param_named(pstore_disable, efivars_pstore_disable, bool, 0644);
 	 EFI_VARIABLE_RUNTIME_ACCESS)
 
 static LIST_HEAD(efi_pstore_list);
+static DECLARE_WORK(efivar_work, NULL);
 
 static int efi_pstore_open(struct pstore_info *psi)
 {
@@ -267,8 +268,9 @@ static int efi_pstore_write(struct pstore_record *record)
 	ret = efivar_entry_set_safe(efi_name, vendor, PSTORE_EFI_ATTRIBUTES,
 			      preemptible(), record->size, record->psi->buf);
 
-	if (record->reason == KMSG_DUMP_OOPS)
-		efivar_run_worker();
+	if (record->reason == KMSG_DUMP_OOPS && try_module_get(THIS_MODULE))
+		if (!schedule_work(&efivar_work))
+			module_put(THIS_MODULE);
 
 	return ret;
 };
@@ -412,6 +414,7 @@ static void efi_pstore_update_entries(struct work_struct *work)
 	}
 
 	kfree(entry);
+	module_put(THIS_MODULE);
 }
 
 static __init int efivars_pstore_init(void)
diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c
index 973eef234b36..ffb12f6efc97 100644
--- a/drivers/firmware/efi/vars.c
+++ b/drivers/firmware/efi/vars.c
@@ -32,10 +32,6 @@ static struct efivars *__efivars;
  */
 static DEFINE_SEMAPHORE(efivars_lock);
 
-static bool efivar_wq_enabled = true;
-DECLARE_WORK(efivar_work, NULL);
-EXPORT_SYMBOL_GPL(efivar_work);
-
 static bool
 validate_device_path(efi_char16_t *var_name, int match, u8 *buffer,
 		     unsigned long len)
@@ -391,13 +387,6 @@ static void dup_variable_bug(efi_char16_t *str16, efi_guid_t *vendor_guid,
 	size_t i, len8 = len16 / sizeof(efi_char16_t);
 	char *str8;
 
-	/*
-	 * Disable the workqueue since the algorithm it uses for
-	 * detecting new variables won't work with this buggy
-	 * implementation of GetNextVariableName().
-	 */
-	efivar_wq_enabled = false;
-
 	str8 = kzalloc(len8, GFP_KERNEL);
 	if (!str8)
 		return;
@@ -1157,16 +1146,6 @@ struct kobject *efivars_kobject(void)
 }
 EXPORT_SYMBOL_GPL(efivars_kobject);
 
-/**
- * efivar_run_worker - schedule the efivar worker thread
- */
-void efivar_run_worker(void)
-{
-	if (efivar_wq_enabled)
-		schedule_work(&efivar_work);
-}
-EXPORT_SYMBOL_GPL(efivar_run_worker);
-
 /**
  * efivars_register - register an efivars
  * @efivars: efivars to register
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 7066c11ab82f..ab8c80331217 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -1037,9 +1037,6 @@ bool efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data,
 bool efivar_variable_is_removable(efi_guid_t vendor, const char *name,
 				  size_t len);
 
-extern struct work_struct efivar_work;
-void efivar_run_worker(void);
-
 #if defined(CONFIG_EFI_VARS) || defined(CONFIG_EFI_VARS_MODULE)
 int efivars_sysfs_init(void);
 
-- 
cgit v1.2.3


From 5d3c8617ccee6387ba73a5dba77fb9dc21cb85f4 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Wed, 23 Sep 2020 10:13:07 +0200
Subject: efi: efivars: un-export efivars_sysfs_init()

efivars_sysfs_init() is only used locally in the source file that
defines it, so make it static and unexport it.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/efivars.c | 3 +--
 include/linux/efi.h            | 4 ----
 2 files changed, 1 insertion(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c
index f39321dbc29f..a76f50e15e6d 100644
--- a/drivers/firmware/efi/efivars.c
+++ b/drivers/firmware/efi/efivars.c
@@ -638,7 +638,7 @@ static void efivars_sysfs_exit(void)
 	kset_unregister(efivars_kset);
 }
 
-int efivars_sysfs_init(void)
+static int efivars_sysfs_init(void)
 {
 	struct kobject *parent_kobj = efivars_kobject();
 	int error = 0;
@@ -666,7 +666,6 @@ int efivars_sysfs_init(void)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(efivars_sysfs_init);
 
 module_init(efivars_sysfs_init);
 module_exit(efivars_sysfs_exit);
diff --git a/include/linux/efi.h b/include/linux/efi.h
index ab8c80331217..4c8dae0b5c75 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -1037,10 +1037,6 @@ bool efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data,
 bool efivar_variable_is_removable(efi_guid_t vendor, const char *name,
 				  size_t len);
 
-#if defined(CONFIG_EFI_VARS) || defined(CONFIG_EFI_VARS_MODULE)
-int efivars_sysfs_init(void);
-
-#endif /* CONFIG_EFI_VARS */
 extern bool efi_capsule_pending(int *reset_type);
 
 extern int efi_capsule_supported(efi_guid_t guid, u32 flags,
-- 
cgit v1.2.3


From a5d02e901e6dadd7dd60fafb6448a822a47430ff Mon Sep 17 00:00:00 2001
From: Vaibhav Gupta <vaibhavgupta40@gmail.com>
Date: Fri, 31 Jul 2020 01:14:16 +0530
Subject: PCI/PM: Remove unused pcibios_pm_ops

The "struct dev_pm_ops pcibios_pm_ops", declared in include/linux/pci.h and
defined in drivers/pci/pci-driver.c, provided arch-specific hooks when a
PCI device was doing a hibernate transition.

394216275c7d ("s390: remove broken hibernate / power management support")
removed the last use of pcibios_pm_ops, so remove it completely.

[bhelgaas: drop unused "error"]
Link: https://lore.kernel.org/r/20200730194416.1029509-1-vaibhavgupta40@gmail.com
Reported-by: Bjorn Helgaas <helgaas@kernel.org>
Signed-off-by: Vaibhav Gupta <vaibhavgupta40@gmail.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pci-driver.c | 26 --------------------------
 include/linux/pci.h      |  4 ----
 2 files changed, 30 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index 449466f71040..40be221e69cf 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -969,12 +969,6 @@ static int pci_pm_resume(struct device *dev)
 
 #ifdef CONFIG_HIBERNATE_CALLBACKS
 
-/*
- * pcibios_pm_ops - provide arch-specific hooks when a PCI device is doing
- * a hibernate transition
- */
-struct dev_pm_ops __weak pcibios_pm_ops;
-
 static int pci_pm_freeze(struct device *dev)
 {
 	struct pci_dev *pci_dev = to_pci_dev(dev);
@@ -1033,9 +1027,6 @@ static int pci_pm_freeze_noirq(struct device *dev)
 
 	pci_pm_set_unknown_state(pci_dev);
 
-	if (pcibios_pm_ops.freeze_noirq)
-		return pcibios_pm_ops.freeze_noirq(dev);
-
 	return 0;
 }
 
@@ -1043,13 +1034,6 @@ static int pci_pm_thaw_noirq(struct device *dev)
 {
 	struct pci_dev *pci_dev = to_pci_dev(dev);
 	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
-	int error;
-
-	if (pcibios_pm_ops.thaw_noirq) {
-		error = pcibios_pm_ops.thaw_noirq(dev);
-		if (error)
-			return error;
-	}
 
 	/*
 	 * The pm->thaw_noirq() callback assumes the device has been
@@ -1174,9 +1158,6 @@ static int pci_pm_poweroff_noirq(struct device *dev)
 
 	pci_fixup_device(pci_fixup_suspend_late, pci_dev);
 
-	if (pcibios_pm_ops.poweroff_noirq)
-		return pcibios_pm_ops.poweroff_noirq(dev);
-
 	return 0;
 }
 
@@ -1184,13 +1165,6 @@ static int pci_pm_restore_noirq(struct device *dev)
 {
 	struct pci_dev *pci_dev = to_pci_dev(dev);
 	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
-	int error;
-
-	if (pcibios_pm_ops.restore_noirq) {
-		error = pcibios_pm_ops.restore_noirq(dev);
-		if (error)
-			return error;
-	}
 
 	pci_pm_default_resume_early(pci_dev);
 	pci_fixup_device(pci_fixup_resume_early, pci_dev);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 835530605c0d..c9e169c4e216 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -2034,10 +2034,6 @@ int pcibios_alloc_irq(struct pci_dev *dev);
 void pcibios_free_irq(struct pci_dev *dev);
 resource_size_t pcibios_default_alignment(void);
 
-#ifdef CONFIG_HIBERNATE_CALLBACKS
-extern struct dev_pm_ops pcibios_pm_ops;
-#endif
-
 #if defined(CONFIG_PCI_MMCONFIG) || defined(CONFIG_ACPI_MCFG)
 void __init pci_mmcfg_early_init(void);
 void __init pci_mmcfg_late_init(void);
-- 
cgit v1.2.3


From 3789af9a13e5561738c0f2114e3a5e22c843ca3e Mon Sep 17 00:00:00 2001
From: Krzysztof Wilczyński <kw@linux.com>
Date: Thu, 30 Jul 2020 21:08:48 +0000
Subject: PCI/PM: Rename pci_dev.d3_delay to d3hot_delay
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

PCI devices support two variants of the D3 power state: D3hot (main power
present) D3cold (main power removed).  Previously struct pci_dev contained:

  unsigned int    d3_delay;       /* D3->D0 transition time in ms */
  unsigned int    d3cold_delay;   /* D3cold->D0 transition time in ms */

"d3_delay" refers specifically to the D3hot state.  Rename it to
"d3hot_delay" to avoid ambiguity and align with the ACPI "_DSM for
Specifying Device Readiness Durations" in the PCI Firmware spec r3.2,
sec 4.6.9.

There is no change to the functionality.

Link: https://lore.kernel.org/r/20200730210848.1578826-1-kw@linux.com
Signed-off-by: Krzysztof Wilczyński <kw@linux.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 Documentation/power/pci.rst                      |  2 +-
 arch/x86/pci/fixup.c                             |  2 +-
 arch/x86/pci/intel_mid_pci.c                     |  2 +-
 drivers/hid/intel-ish-hid/ipc/ipc.c              |  2 +-
 drivers/net/ethernet/marvell/sky2.c              |  2 +-
 drivers/pci/pci-acpi.c                           |  6 +--
 drivers/pci/pci.c                                | 14 ++---
 drivers/pci/pci.h                                |  4 +-
 drivers/pci/quirks.c                             | 68 ++++++++++++------------
 drivers/staging/media/atomisp/pci/atomisp_v4l2.c |  2 +-
 include/linux/pci.h                              |  2 +-
 include/uapi/linux/pci_regs.h                    |  2 +-
 12 files changed, 54 insertions(+), 54 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/power/pci.rst b/Documentation/power/pci.rst
index 1831e431f725..b04fb18cc4e2 100644
--- a/Documentation/power/pci.rst
+++ b/Documentation/power/pci.rst
@@ -320,7 +320,7 @@ that these callbacks operate on::
 	unsigned int	d2_support:1;	/* Low power state D2 is supported */
 	unsigned int	no_d1d2:1;	/* D1 and D2 are forbidden */
 	unsigned int	wakeup_prepared:1;  /* Device prepared for wake up */
-	unsigned int	d3_delay;	/* D3->D0 transition time in ms */
+	unsigned int	d3hot_delay;	/* D3hot->D0 transition time in ms */
 	...
   };
 
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index b8c9a5b87f37..0a0e168be1cb 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -587,7 +587,7 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0xa26d, pci_invalid_bar);
 static void pci_fixup_amd_ehci_pme(struct pci_dev *dev)
 {
 	dev_info(&dev->dev, "PME# does not work under D3, disabling it\n");
-	dev->pme_support &= ~((PCI_PM_CAP_PME_D3 | PCI_PM_CAP_PME_D3cold)
+	dev->pme_support &= ~((PCI_PM_CAP_PME_D3hot | PCI_PM_CAP_PME_D3cold)
 		>> PCI_PM_CAP_PME_SHIFT);
 }
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x7808, pci_fixup_amd_ehci_pme);
diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c
index 00c62115f39c..979f310b67d4 100644
--- a/arch/x86/pci/intel_mid_pci.c
+++ b/arch/x86/pci/intel_mid_pci.c
@@ -322,7 +322,7 @@ static void pci_d3delay_fixup(struct pci_dev *dev)
 	 */
 	if (type1_access_ok(dev->bus->number, dev->devfn, PCI_DEVICE_ID))
 		return;
-	dev->d3_delay = 0;
+	dev->d3hot_delay = 0;
 }
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_ANY_ID, pci_d3delay_fixup);
 
diff --git a/drivers/hid/intel-ish-hid/ipc/ipc.c b/drivers/hid/intel-ish-hid/ipc/ipc.c
index 8f8dfdf64833..a45ac7fa417b 100644
--- a/drivers/hid/intel-ish-hid/ipc/ipc.c
+++ b/drivers/hid/intel-ish-hid/ipc/ipc.c
@@ -755,7 +755,7 @@ static int _ish_hw_reset(struct ishtp_device *dev)
 	csr |= PCI_D3hot;
 	pci_write_config_word(pdev, pdev->pm_cap + PCI_PM_CTRL, csr);
 
-	mdelay(pdev->d3_delay);
+	mdelay(pdev->d3hot_delay);
 
 	csr &= ~PCI_PM_CTRL_STATE_MASK;
 	csr |= PCI_D0;
diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index cec8124301c7..dd11c06ca7f9 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -5105,7 +5105,7 @@ static int sky2_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	INIT_WORK(&hw->restart_work, sky2_restart);
 
 	pci_set_drvdata(pdev, hw);
-	pdev->d3_delay = 300;
+	pdev->d3hot_delay = 300;
 
 	return 0;
 
diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index d5869a03f748..154db9a47511 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -1167,7 +1167,7 @@ static struct acpi_device *acpi_pci_find_companion(struct device *dev)
  * @pdev: the PCI device whose delay is to be updated
  * @handle: ACPI handle of this device
  *
- * Update the d3_delay and d3cold_delay of a PCI device from the ACPI _DSM
+ * Update the d3hot_delay and d3cold_delay of a PCI device from the ACPI _DSM
  * control method of either the device itself or the PCI host bridge.
  *
  * Function 8, "Reset Delay," applies to the entire hierarchy below a PCI
@@ -1206,8 +1206,8 @@ static void pci_acpi_optimize_delay(struct pci_dev *pdev,
 		}
 		if (elements[3].type == ACPI_TYPE_INTEGER) {
 			value = (int)elements[3].integer.value / 1000;
-			if (value < PCI_PM_D3_WAIT)
-				pdev->d3_delay = value;
+			if (value < PCI_PM_D3HOT_WAIT)
+				pdev->d3hot_delay = value;
 		}
 	}
 	ACPI_FREE(obj);
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index a458c46d7e39..c4a26532a447 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -49,7 +49,7 @@ EXPORT_SYMBOL(isa_dma_bridge_buggy);
 int pci_pci_problems;
 EXPORT_SYMBOL(pci_pci_problems);
 
-unsigned int pci_pm_d3_delay;
+unsigned int pci_pm_d3hot_delay;
 
 static void pci_pme_list_scan(struct work_struct *work);
 
@@ -66,10 +66,10 @@ struct pci_pme_device {
 
 static void pci_dev_d3_sleep(struct pci_dev *dev)
 {
-	unsigned int delay = dev->d3_delay;
+	unsigned int delay = dev->d3hot_delay;
 
-	if (delay < pci_pm_d3_delay)
-		delay = pci_pm_d3_delay;
+	if (delay < pci_pm_d3hot_delay)
+		delay = pci_pm_d3hot_delay;
 
 	if (delay)
 		msleep(delay);
@@ -3013,7 +3013,7 @@ void pci_pm_init(struct pci_dev *dev)
 	}
 
 	dev->pm_cap = pm;
-	dev->d3_delay = PCI_PM_D3_WAIT;
+	dev->d3hot_delay = PCI_PM_D3HOT_WAIT;
 	dev->d3cold_delay = PCI_PM_D3COLD_WAIT;
 	dev->bridge_d3 = pci_bridge_d3_possible(dev);
 	dev->d3cold_allowed = true;
@@ -3038,7 +3038,7 @@ void pci_pm_init(struct pci_dev *dev)
 			 (pmc & PCI_PM_CAP_PME_D0) ? " D0" : "",
 			 (pmc & PCI_PM_CAP_PME_D1) ? " D1" : "",
 			 (pmc & PCI_PM_CAP_PME_D2) ? " D2" : "",
-			 (pmc & PCI_PM_CAP_PME_D3) ? " D3hot" : "",
+			 (pmc & PCI_PM_CAP_PME_D3hot) ? " D3hot" : "",
 			 (pmc & PCI_PM_CAP_PME_D3cold) ? " D3cold" : "");
 		dev->pme_support = pmc >> PCI_PM_CAP_PME_SHIFT;
 		dev->pme_poll = true;
@@ -4621,7 +4621,7 @@ static int pci_af_flr(struct pci_dev *dev, int probe)
  *
  * NOTE: This causes the caller to sleep for twice the device power transition
  * cooldown period, which for the D0->D3hot and D3hot->D0 transitions is 10 ms
- * by default (i.e. unless the @dev's d3_delay field has a different value).
+ * by default (i.e. unless the @dev's d3hot_delay field has a different value).
  * Moreover, only devices in D0 can be reset by this function.
  */
 static int pci_pm_reset(struct pci_dev *dev, int probe)
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index fa12f7cbc1a0..8d492669ecfd 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -44,7 +44,7 @@ int pci_bridge_secondary_bus_reset(struct pci_dev *dev);
 int pci_bus_error_reset(struct pci_dev *dev);
 
 #define PCI_PM_D2_DELAY         200
-#define PCI_PM_D3_WAIT          10
+#define PCI_PM_D3HOT_WAIT       10
 #define PCI_PM_D3COLD_WAIT      100
 #define PCI_PM_BUS_WAIT         50
 
@@ -178,7 +178,7 @@ extern struct mutex pci_slot_mutex;
 
 extern raw_spinlock_t pci_lock;
 
-extern unsigned int pci_pm_d3_delay;
+extern unsigned int pci_pm_d3hot_delay;
 
 #ifdef CONFIG_PCI_MSI
 void pci_no_msi(void);
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index bdf9b52567e0..72b22a35e516 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -1846,7 +1846,7 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_PXHV,	quirk_pci
  */
 static void quirk_intel_pcie_pm(struct pci_dev *dev)
 {
-	pci_pm_d3_delay = 120;
+	pci_pm_d3hot_delay = 120;
 	dev->no_d1d2 = 1;
 }
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x25e2, quirk_intel_pcie_pm);
@@ -1873,12 +1873,12 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x260b, quirk_intel_pcie_pm);
 
 static void quirk_d3hot_delay(struct pci_dev *dev, unsigned int delay)
 {
-	if (dev->d3_delay >= delay)
+	if (dev->d3hot_delay >= delay)
 		return;
 
-	dev->d3_delay = delay;
+	dev->d3hot_delay = delay;
 	pci_info(dev, "extending delay after power-on from D3hot to %d msec\n",
-		 dev->d3_delay);
+		 dev->d3hot_delay);
 }
 
 static void quirk_radeon_pm(struct pci_dev *dev)
@@ -3387,36 +3387,36 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0152, disable_igfx_irq);
  * PCI devices which are on Intel chips can skip the 10ms delay
  * before entering D3 mode.
  */
-static void quirk_remove_d3_delay(struct pci_dev *dev)
-{
-	dev->d3_delay = 0;
-}
-/* C600 Series devices do not need 10ms d3_delay */
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0412, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0c00, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0c0c, quirk_remove_d3_delay);
-/* Lynxpoint-H PCH devices do not need 10ms d3_delay */
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c02, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c18, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c1c, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c20, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c22, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c26, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c2d, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c31, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c3a, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c3d, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c4e, quirk_remove_d3_delay);
-/* Intel Cherrytrail devices do not need 10ms d3_delay */
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x2280, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x2298, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x229c, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x22b0, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x22b5, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x22b7, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x22b8, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x22d8, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x22dc, quirk_remove_d3_delay);
+static void quirk_remove_d3hot_delay(struct pci_dev *dev)
+{
+	dev->d3hot_delay = 0;
+}
+/* C600 Series devices do not need 10ms d3hot_delay */
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0412, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0c00, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0c0c, quirk_remove_d3hot_delay);
+/* Lynxpoint-H PCH devices do not need 10ms d3hot_delay */
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c02, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c18, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c1c, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c20, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c22, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c26, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c2d, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c31, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c3a, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c3d, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c4e, quirk_remove_d3hot_delay);
+/* Intel Cherrytrail devices do not need 10ms d3hot_delay */
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x2280, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x2298, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x229c, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x22b0, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x22b5, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x22b7, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x22b8, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x22d8, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x22dc, quirk_remove_d3hot_delay);
 
 /*
  * Some devices may pass our check in pci_intx_mask_supported() if
diff --git a/drivers/staging/media/atomisp/pci/atomisp_v4l2.c b/drivers/staging/media/atomisp/pci/atomisp_v4l2.c
index a000a1e316f7..beba430a197e 100644
--- a/drivers/staging/media/atomisp/pci/atomisp_v4l2.c
+++ b/drivers/staging/media/atomisp/pci/atomisp_v4l2.c
@@ -1573,7 +1573,7 @@ static int atomisp_pci_probe(struct pci_dev *pdev, const struct pci_device_id *i
 	spin_lock_init(&isp->lock);
 
 	/* This is not a true PCI device on SoC, so the delay is not needed. */
-	pdev->d3_delay = 0;
+	pdev->d3hot_delay = 0;
 
 	pci_set_drvdata(pdev, isp);
 
diff --git a/include/linux/pci.h b/include/linux/pci.h
index c9e169c4e216..bea1a03faab6 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -373,7 +373,7 @@ struct pci_dev {
 						      user sysfs */
 	unsigned int	clear_retrain_link:1;	/* Need to clear Retrain Link
 						   bit manually */
-	unsigned int	d3_delay;	/* D3->D0 transition time in ms */
+	unsigned int	d3hot_delay;	/* D3hot->D0 transition time in ms */
 	unsigned int	d3cold_delay;	/* D3cold->D0 transition time in ms */
 
 #ifdef CONFIG_PCIEASPM
diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index f9701410d3b5..49f15c37e771 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -246,7 +246,7 @@
 #define  PCI_PM_CAP_PME_D0	0x0800	/* PME# from D0 */
 #define  PCI_PM_CAP_PME_D1	0x1000	/* PME# from D1 */
 #define  PCI_PM_CAP_PME_D2	0x2000	/* PME# from D2 */
-#define  PCI_PM_CAP_PME_D3	0x4000	/* PME# from D3 (hot) */
+#define  PCI_PM_CAP_PME_D3hot	0x4000	/* PME# from D3 (hot) */
 #define  PCI_PM_CAP_PME_D3cold	0x8000	/* PME# from D3 (cold) */
 #define  PCI_PM_CAP_PME_SHIFT	11	/* Start of the PME Mask in PMC */
 #define PCI_PM_CTRL		4	/* PM control and status register */
-- 
cgit v1.2.3


From 3aac1ead5eb6b76f3d2b8d111e6de1c2de23fb34 Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@redhat.com>
Date: Tue, 29 Sep 2020 14:45:50 +0200
Subject: bpf: Move prog->aux->linked_prog and trampoline into bpf_link on
 attach
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In preparation for allowing multiple attachments of freplace programs, move
the references to the target program and trampoline into the
bpf_tracing_link structure when that is created. To do this atomically,
introduce a new mutex in prog->aux to protect writing to the two pointers
to target prog and trampoline, and rename the members to make it clear that
they are related.

With this change, it is no longer possible to attach the same tracing
program multiple times (detaching in-between), since the reference from the
tracing program to the target disappears on the first attach. However,
since the next patch will let the caller supply an attach target, that will
also make it possible to attach to the same place multiple times.

Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/160138355059.48470.2503076992210324984.stgit@toke.dk
---
 include/linux/bpf.h                           |  15 +-
 kernel/bpf/btf.c                              |   6 +-
 kernel/bpf/core.c                             |   9 +-
 kernel/bpf/preload/iterators/iterators.bpf.c  |   4 +-
 kernel/bpf/preload/iterators/iterators.skel.h | 444 +++++++++++++-------------
 kernel/bpf/syscall.c                          |  56 +++-
 kernel/bpf/trampoline.c                       |  12 +-
 kernel/bpf/verifier.c                         |  11 +-
 8 files changed, 298 insertions(+), 259 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 768b533ba48e..839dd8670a7a 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -640,8 +640,8 @@ static __always_inline unsigned int bpf_dispatcher_nop_func(
 	return bpf_func(ctx, insnsi);
 }
 #ifdef CONFIG_BPF_JIT
-int bpf_trampoline_link_prog(struct bpf_prog *prog);
-int bpf_trampoline_unlink_prog(struct bpf_prog *prog);
+int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr);
+int bpf_trampoline_unlink_prog(struct bpf_prog *prog, struct bpf_trampoline *tr);
 struct bpf_trampoline *bpf_trampoline_get(u64 key,
 					  struct bpf_attach_target_info *tgt_info);
 void bpf_trampoline_put(struct bpf_trampoline *tr);
@@ -688,11 +688,13 @@ void bpf_image_ksym_del(struct bpf_ksym *ksym);
 void bpf_ksym_add(struct bpf_ksym *ksym);
 void bpf_ksym_del(struct bpf_ksym *ksym);
 #else
-static inline int bpf_trampoline_link_prog(struct bpf_prog *prog)
+static inline int bpf_trampoline_link_prog(struct bpf_prog *prog,
+					   struct bpf_trampoline *tr)
 {
 	return -ENOTSUPP;
 }
-static inline int bpf_trampoline_unlink_prog(struct bpf_prog *prog)
+static inline int bpf_trampoline_unlink_prog(struct bpf_prog *prog,
+					     struct bpf_trampoline *tr)
 {
 	return -ENOTSUPP;
 }
@@ -763,7 +765,9 @@ struct bpf_prog_aux {
 	u32 max_rdonly_access;
 	u32 max_rdwr_access;
 	const struct bpf_ctx_arg_aux *ctx_arg_info;
-	struct bpf_prog *linked_prog;
+	struct mutex dst_mutex; /* protects dst_* pointers below, *after* prog becomes visible */
+	struct bpf_prog *dst_prog;
+	struct bpf_trampoline *dst_trampoline;
 	bool verifier_zext; /* Zero extensions has been inserted by verifier. */
 	bool offload_requested;
 	bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */
@@ -771,7 +775,6 @@ struct bpf_prog_aux {
 	bool sleepable;
 	bool tail_call_reachable;
 	enum bpf_tramp_prog_type trampoline_prog_type;
-	struct bpf_trampoline *trampoline;
 	struct hlist_node tramp_hlist;
 	/* BTF_KIND_FUNC_PROTO for valid attach_btf_id */
 	const struct btf_type *attach_func_proto;
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 498e5e553825..05816471bac6 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -4428,7 +4428,7 @@ errout:
 
 struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog)
 {
-	struct bpf_prog *tgt_prog = prog->aux->linked_prog;
+	struct bpf_prog *tgt_prog = prog->aux->dst_prog;
 
 	if (tgt_prog) {
 		return tgt_prog->aux->btf;
@@ -4455,7 +4455,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 		    struct bpf_insn_access_aux *info)
 {
 	const struct btf_type *t = prog->aux->attach_func_proto;
-	struct bpf_prog *tgt_prog = prog->aux->linked_prog;
+	struct bpf_prog *tgt_prog = prog->aux->dst_prog;
 	struct btf *btf = bpf_prog_get_target_btf(prog);
 	const char *tname = prog->aux->attach_func_name;
 	struct bpf_verifier_log *log = info->log;
@@ -5281,7 +5281,7 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
 		return -EFAULT;
 	}
 	if (prog_type == BPF_PROG_TYPE_EXT)
-		prog_type = prog->aux->linked_prog->type;
+		prog_type = prog->aux->dst_prog->type;
 
 	t = btf_type_by_id(btf, t->type);
 	if (!t || !btf_type_is_func_proto(t)) {
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index c4ba45fa4fe1..cda674f1392f 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -99,6 +99,7 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag
 
 	INIT_LIST_HEAD_RCU(&fp->aux->ksym.lnode);
 	mutex_init(&fp->aux->used_maps_mutex);
+	mutex_init(&fp->aux->dst_mutex);
 
 	return fp;
 }
@@ -255,6 +256,7 @@ void __bpf_prog_free(struct bpf_prog *fp)
 {
 	if (fp->aux) {
 		mutex_destroy(&fp->aux->used_maps_mutex);
+		mutex_destroy(&fp->aux->dst_mutex);
 		free_percpu(fp->aux->stats);
 		kfree(fp->aux->poke_tab);
 		kfree(fp->aux);
@@ -2138,7 +2140,8 @@ static void bpf_prog_free_deferred(struct work_struct *work)
 	if (aux->prog->has_callchain_buf)
 		put_callchain_buffers();
 #endif
-	bpf_trampoline_put(aux->trampoline);
+	if (aux->dst_trampoline)
+		bpf_trampoline_put(aux->dst_trampoline);
 	for (i = 0; i < aux->func_cnt; i++)
 		bpf_jit_free(aux->func[i]);
 	if (aux->func_cnt) {
@@ -2154,8 +2157,8 @@ void bpf_prog_free(struct bpf_prog *fp)
 {
 	struct bpf_prog_aux *aux = fp->aux;
 
-	if (aux->linked_prog)
-		bpf_prog_put(aux->linked_prog);
+	if (aux->dst_prog)
+		bpf_prog_put(aux->dst_prog);
 	INIT_WORK(&aux->work, bpf_prog_free_deferred);
 	schedule_work(&aux->work);
 }
diff --git a/kernel/bpf/preload/iterators/iterators.bpf.c b/kernel/bpf/preload/iterators/iterators.bpf.c
index 5ded550b2ed6..52aa7b38e8b8 100644
--- a/kernel/bpf/preload/iterators/iterators.bpf.c
+++ b/kernel/bpf/preload/iterators/iterators.bpf.c
@@ -42,7 +42,7 @@ struct bpf_prog_aux {
 	__u32 id;
 	char name[16];
 	const char *attach_func_name;
-	struct bpf_prog *linked_prog;
+	struct bpf_prog *dst_prog;
 	struct bpf_func_info *func_info;
 	struct btf *btf;
 };
@@ -108,7 +108,7 @@ int dump_bpf_prog(struct bpf_iter__bpf_prog *ctx)
 
 	BPF_SEQ_PRINTF(seq, "%4u %-16s %s %s\n", aux->id,
 		       get_name(aux->btf, aux->func_info[0].type_id, aux->name),
-		       aux->attach_func_name, aux->linked_prog->aux->name);
+		       aux->attach_func_name, aux->dst_prog->aux->name);
 	return 0;
 }
 char LICENSE[] SEC("license") = "GPL";
diff --git a/kernel/bpf/preload/iterators/iterators.skel.h b/kernel/bpf/preload/iterators/iterators.skel.h
index c3171357dc4f..cf9a6a94b3a4 100644
--- a/kernel/bpf/preload/iterators/iterators.skel.h
+++ b/kernel/bpf/preload/iterators/iterators.skel.h
@@ -47,7 +47,7 @@ iterators_bpf__open_opts(const struct bpf_object_open_opts *opts)
 {
 	struct iterators_bpf *obj;
 
-	obj = (typeof(obj))calloc(1, sizeof(*obj));
+	obj = (struct iterators_bpf *)calloc(1, sizeof(*obj));
 	if (!obj)
 		return NULL;
 	if (iterators_bpf__create_skeleton(obj))
@@ -105,7 +105,7 @@ iterators_bpf__create_skeleton(struct iterators_bpf *obj)
 {
 	struct bpf_object_skeleton *s;
 
-	s = (typeof(s))calloc(1, sizeof(*s));
+	s = (struct bpf_object_skeleton *)calloc(1, sizeof(*s));
 	if (!s)
 		return -1;
 	obj->skeleton = s;
@@ -117,7 +117,7 @@ iterators_bpf__create_skeleton(struct iterators_bpf *obj)
 	/* maps */
 	s->map_cnt = 1;
 	s->map_skel_sz = sizeof(*s->maps);
-	s->maps = (typeof(s->maps))calloc(s->map_cnt, s->map_skel_sz);
+	s->maps = (struct bpf_map_skeleton *)calloc(s->map_cnt, s->map_skel_sz);
 	if (!s->maps)
 		goto err;
 
@@ -128,7 +128,7 @@ iterators_bpf__create_skeleton(struct iterators_bpf *obj)
 	/* programs */
 	s->prog_cnt = 2;
 	s->prog_skel_sz = sizeof(*s->progs);
-	s->progs = (typeof(s->progs))calloc(s->prog_cnt, s->prog_skel_sz);
+	s->progs = (struct bpf_prog_skeleton *)calloc(s->prog_cnt, s->prog_skel_sz);
 	if (!s->progs)
 		goto err;
 
@@ -140,10 +140,10 @@ iterators_bpf__create_skeleton(struct iterators_bpf *obj)
 	s->progs[1].prog = &obj->progs.dump_bpf_prog;
 	s->progs[1].link = &obj->links.dump_bpf_prog;
 
-	s->data_sz = 7128;
+	s->data_sz = 7176;
 	s->data = (void *)"\
 \x7f\x45\x4c\x46\x02\x01\x01\0\0\0\0\0\0\0\0\0\x01\0\xf7\0\x01\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\x18\x18\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\x40\0\x0f\0\
+\0\0\0\0\0\0\0\0\0\0\0\x48\x18\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\x40\0\x0f\0\
 \x0e\0\x79\x12\0\0\0\0\0\0\x79\x26\0\0\0\0\0\0\x79\x17\x08\0\0\0\0\0\x15\x07\
 \x1a\0\0\0\0\0\x79\x21\x10\0\0\0\0\0\x55\x01\x08\0\0\0\0\0\xbf\xa4\0\0\0\0\0\0\
 \x07\x04\0\0\xe8\xff\xff\xff\xbf\x61\0\0\0\0\0\0\x18\x02\0\0\0\0\0\0\0\0\0\0\0\
@@ -164,7 +164,7 @@ iterators_bpf__create_skeleton(struct iterators_bpf *obj)
 \x79\x86\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\x01\0\0\xf8\xff\xff\xff\xb7\x02\0\
 \0\x08\0\0\0\x85\0\0\0\x71\0\0\0\xb7\x01\0\0\0\0\0\0\x79\xa3\xf8\xff\0\0\0\0\
 \x0f\x13\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\x01\0\0\xf4\xff\xff\xff\xb7\x02\0\
-\0\x04\0\0\0\x85\0\0\0\x04\0\0\0\xb7\x03\0\0\x04\0\0\0\x61\xa1\xf4\xff\0\0\0\0\
+\0\x04\0\0\0\x85\0\0\0\x71\0\0\0\xb7\x03\0\0\x04\0\0\0\x61\xa1\xf4\xff\0\0\0\0\
 \x61\x82\x10\0\0\0\0\0\x3d\x21\x02\0\0\0\0\0\x0f\x16\0\0\0\0\0\0\xbf\x69\0\0\0\
 \0\0\0\x7b\x9a\xd8\xff\0\0\0\0\x79\x71\x18\0\0\0\0\0\x7b\x1a\xe0\xff\0\0\0\0\
 \x79\x71\x20\0\0\0\0\0\x79\x11\0\0\0\0\0\0\x0f\x31\0\0\0\0\0\0\x7b\x1a\xe8\xff\
@@ -176,230 +176,232 @@ iterators_bpf__create_skeleton(struct iterators_bpf *obj)
 \x73\x25\x36\x64\x0a\0\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\
 \x20\x20\x20\x20\x20\x20\x20\x20\x61\x74\x74\x61\x63\x68\x65\x64\x0a\0\x25\x34\
 \x75\x20\x25\x2d\x31\x36\x73\x20\x25\x73\x20\x25\x73\x0a\0\x47\x50\x4c\0\x9f\
-\xeb\x01\0\x18\0\0\0\0\0\0\0\x1c\x04\0\0\x1c\x04\0\0\0\x05\0\0\0\0\0\0\0\0\0\
+\xeb\x01\0\x18\0\0\0\0\0\0\0\x1c\x04\0\0\x1c\x04\0\0\x09\x05\0\0\0\0\0\0\0\0\0\
 \x02\x02\0\0\0\x01\0\0\0\x02\0\0\x04\x10\0\0\0\x13\0\0\0\x03\0\0\0\0\0\0\0\x18\
 \0\0\0\x04\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\x02\x08\0\0\0\0\0\0\0\0\0\0\x02\x0d\0\
 \0\0\0\0\0\0\x01\0\0\x0d\x06\0\0\0\x1c\0\0\0\x01\0\0\0\x20\0\0\0\0\0\0\x01\x04\
-\0\0\0\x20\0\0\x01\x24\0\0\0\x01\0\0\x0c\x05\0\0\0\xa3\0\0\0\x03\0\0\x04\x18\0\
-\0\0\xb1\0\0\0\x09\0\0\0\0\0\0\0\xb5\0\0\0\x0b\0\0\0\x40\0\0\0\xc0\0\0\0\x0b\0\
-\0\0\x80\0\0\0\0\0\0\0\0\0\0\x02\x0a\0\0\0\xc8\0\0\0\0\0\0\x07\0\0\0\0\xd1\0\0\
-\0\0\0\0\x08\x0c\0\0\0\xd7\0\0\0\0\0\0\x01\x08\0\0\0\x40\0\0\0\x98\x01\0\0\x03\
-\0\0\x04\x18\0\0\0\xa0\x01\0\0\x0e\0\0\0\0\0\0\0\xa3\x01\0\0\x11\0\0\0\x20\0\0\
-\0\xa8\x01\0\0\x0e\0\0\0\xa0\0\0\0\xb4\x01\0\0\0\0\0\x08\x0f\0\0\0\xba\x01\0\0\
-\0\0\0\x01\x04\0\0\0\x20\0\0\0\xc7\x01\0\0\0\0\0\x01\x01\0\0\0\x08\0\0\x01\0\0\
-\0\0\0\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x10\0\0\0\xcc\x01\0\0\0\0\0\x01\x04\
-\0\0\0\x20\0\0\0\0\0\0\0\0\0\0\x02\x14\0\0\0\x30\x02\0\0\x02\0\0\x04\x10\0\0\0\
-\x13\0\0\0\x03\0\0\0\0\0\0\0\x43\x02\0\0\x15\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\x02\
-\x18\0\0\0\0\0\0\0\x01\0\0\x0d\x06\0\0\0\x1c\0\0\0\x13\0\0\0\x48\x02\0\0\x01\0\
-\0\x0c\x16\0\0\0\x94\x02\0\0\x01\0\0\x04\x08\0\0\0\x9d\x02\0\0\x19\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\x02\x1a\0\0\0\xee\x02\0\0\x06\0\0\x04\x38\0\0\0\xa0\x01\0\0\
-\x0e\0\0\0\0\0\0\0\xa3\x01\0\0\x11\0\0\0\x20\0\0\0\xfb\x02\0\0\x1b\0\0\0\xc0\0\
-\0\0\x0c\x03\0\0\x15\0\0\0\0\x01\0\0\x18\x03\0\0\x1d\0\0\0\x40\x01\0\0\x22\x03\
+\0\0\0\x20\0\0\x01\x24\0\0\0\x01\0\0\x0c\x05\0\0\0\xaf\0\0\0\x03\0\0\x04\x18\0\
+\0\0\xbd\0\0\0\x09\0\0\0\0\0\0\0\xc1\0\0\0\x0b\0\0\0\x40\0\0\0\xcc\0\0\0\x0b\0\
+\0\0\x80\0\0\0\0\0\0\0\0\0\0\x02\x0a\0\0\0\xd4\0\0\0\0\0\0\x07\0\0\0\0\xdd\0\0\
+\0\0\0\0\x08\x0c\0\0\0\xe3\0\0\0\0\0\0\x01\x08\0\0\0\x40\0\0\0\xa4\x01\0\0\x03\
+\0\0\x04\x18\0\0\0\xac\x01\0\0\x0e\0\0\0\0\0\0\0\xaf\x01\0\0\x11\0\0\0\x20\0\0\
+\0\xb4\x01\0\0\x0e\0\0\0\xa0\0\0\0\xc0\x01\0\0\0\0\0\x08\x0f\0\0\0\xc6\x01\0\0\
+\0\0\0\x01\x04\0\0\0\x20\0\0\0\xd3\x01\0\0\0\0\0\x01\x01\0\0\0\x08\0\0\x01\0\0\
+\0\0\0\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x10\0\0\0\xd8\x01\0\0\0\0\0\x01\x04\
+\0\0\0\x20\0\0\0\0\0\0\0\0\0\0\x02\x14\0\0\0\x3c\x02\0\0\x02\0\0\x04\x10\0\0\0\
+\x13\0\0\0\x03\0\0\0\0\0\0\0\x4f\x02\0\0\x15\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\x02\
+\x18\0\0\0\0\0\0\0\x01\0\0\x0d\x06\0\0\0\x1c\0\0\0\x13\0\0\0\x54\x02\0\0\x01\0\
+\0\x0c\x16\0\0\0\xa0\x02\0\0\x01\0\0\x04\x08\0\0\0\xa9\x02\0\0\x19\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\x02\x1a\0\0\0\xfa\x02\0\0\x06\0\0\x04\x38\0\0\0\xac\x01\0\0\
+\x0e\0\0\0\0\0\0\0\xaf\x01\0\0\x11\0\0\0\x20\0\0\0\x07\x03\0\0\x1b\0\0\0\xc0\0\
+\0\0\x18\x03\0\0\x15\0\0\0\0\x01\0\0\x21\x03\0\0\x1d\0\0\0\x40\x01\0\0\x2b\x03\
 \0\0\x1e\0\0\0\x80\x01\0\0\0\0\0\0\0\0\0\x02\x1c\0\0\0\0\0\0\0\0\0\0\x0a\x10\0\
-\0\0\0\0\0\0\0\0\0\x02\x1f\0\0\0\0\0\0\0\0\0\0\x02\x20\0\0\0\x6c\x03\0\0\x02\0\
-\0\x04\x08\0\0\0\x7a\x03\0\0\x0e\0\0\0\0\0\0\0\x83\x03\0\0\x0e\0\0\0\x20\0\0\0\
-\x22\x03\0\0\x03\0\0\x04\x18\0\0\0\x8d\x03\0\0\x1b\0\0\0\0\0\0\0\x95\x03\0\0\
-\x21\0\0\0\x40\0\0\0\x9b\x03\0\0\x23\0\0\0\x80\0\0\0\0\0\0\0\0\0\0\x02\x22\0\0\
-\0\0\0\0\0\0\0\0\x02\x24\0\0\0\x9f\x03\0\0\x01\0\0\x04\x04\0\0\0\xaa\x03\0\0\
-\x0e\0\0\0\0\0\0\0\x13\x04\0\0\x01\0\0\x04\x04\0\0\0\x1c\x04\0\0\x0e\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\x12\0\0\0\x23\0\0\0\x92\x04\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\x02\x1f\0\0\0\0\0\0\0\0\0\0\x02\x20\0\0\0\x75\x03\0\0\x02\0\
+\0\x04\x08\0\0\0\x83\x03\0\0\x0e\0\0\0\0\0\0\0\x8c\x03\0\0\x0e\0\0\0\x20\0\0\0\
+\x2b\x03\0\0\x03\0\0\x04\x18\0\0\0\x96\x03\0\0\x1b\0\0\0\0\0\0\0\x9e\x03\0\0\
+\x21\0\0\0\x40\0\0\0\xa4\x03\0\0\x23\0\0\0\x80\0\0\0\0\0\0\0\0\0\0\x02\x22\0\0\
+\0\0\0\0\0\0\0\0\x02\x24\0\0\0\xa8\x03\0\0\x01\0\0\x04\x04\0\0\0\xb3\x03\0\0\
+\x0e\0\0\0\0\0\0\0\x1c\x04\0\0\x01\0\0\x04\x04\0\0\0\x25\x04\0\0\x0e\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\x12\0\0\0\x23\0\0\0\x9b\x04\0\0\0\0\0\
 \x0e\x25\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\x12\0\0\0\x0e\0\0\0\
-\xa6\x04\0\0\0\0\0\x0e\x27\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\
-\x12\0\0\0\x20\0\0\0\xbc\x04\0\0\0\0\0\x0e\x29\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\
-\0\0\0\0\x1c\0\0\0\x12\0\0\0\x11\0\0\0\xd1\x04\0\0\0\0\0\x0e\x2b\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x04\0\0\0\xe8\x04\0\0\0\0\0\x0e\
-\x2d\0\0\0\x01\0\0\0\xf0\x04\0\0\x04\0\0\x0f\0\0\0\0\x26\0\0\0\0\0\0\0\x23\0\0\
+\xaf\x04\0\0\0\0\0\x0e\x27\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\
+\x12\0\0\0\x20\0\0\0\xc5\x04\0\0\0\0\0\x0e\x29\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\
+\0\0\0\0\x1c\0\0\0\x12\0\0\0\x11\0\0\0\xda\x04\0\0\0\0\0\x0e\x2b\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x04\0\0\0\xf1\x04\0\0\0\0\0\x0e\
+\x2d\0\0\0\x01\0\0\0\xf9\x04\0\0\x04\0\0\x0f\0\0\0\0\x26\0\0\0\0\0\0\0\x23\0\0\
 \0\x28\0\0\0\x23\0\0\0\x0e\0\0\0\x2a\0\0\0\x31\0\0\0\x20\0\0\0\x2c\0\0\0\x51\0\
-\0\0\x11\0\0\0\xf8\x04\0\0\x01\0\0\x0f\0\0\0\0\x2e\0\0\0\0\0\0\0\x04\0\0\0\0\
+\0\0\x11\0\0\0\x01\x05\0\0\x01\0\0\x0f\0\0\0\0\x2e\0\0\0\0\0\0\0\x04\0\0\0\0\
 \x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\x66\x5f\x6d\x61\x70\0\x6d\x65\
 \x74\x61\0\x6d\x61\x70\0\x63\x74\x78\0\x69\x6e\x74\0\x64\x75\x6d\x70\x5f\x62\
 \x70\x66\x5f\x6d\x61\x70\0\x69\x74\x65\x72\x2f\x62\x70\x66\x5f\x6d\x61\x70\0\
-\x30\x3a\x30\0\x2f\x77\x2f\x6e\x65\x74\x2d\x6e\x65\x78\x74\x2f\x6b\x65\x72\x6e\
-\x65\x6c\x2f\x62\x70\x66\x2f\x70\x72\x65\x6c\x6f\x61\x64\x2f\x69\x74\x65\x72\
-\x61\x74\x6f\x72\x73\x2f\x69\x74\x65\x72\x61\x74\x6f\x72\x73\x2e\x62\x70\x66\
-\x2e\x63\0\x09\x73\x74\x72\x75\x63\x74\x20\x73\x65\x71\x5f\x66\x69\x6c\x65\x20\
-\x2a\x73\x65\x71\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\
-\x65\x71\x3b\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x6d\x65\x74\x61\0\x73\x65\
-\x71\0\x73\x65\x73\x73\x69\x6f\x6e\x5f\x69\x64\0\x73\x65\x71\x5f\x6e\x75\x6d\0\
-\x73\x65\x71\x5f\x66\x69\x6c\x65\0\x5f\x5f\x75\x36\x34\0\x6c\x6f\x6e\x67\x20\
-\x6c\x6f\x6e\x67\x20\x75\x6e\x73\x69\x67\x6e\x65\x64\x20\x69\x6e\x74\0\x30\x3a\
-\x31\0\x09\x73\x74\x72\x75\x63\x74\x20\x62\x70\x66\x5f\x6d\x61\x70\x20\x2a\x6d\
-\x61\x70\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x61\x70\x3b\0\x09\x69\x66\x20\x28\
-\x21\x6d\x61\x70\x29\0\x30\x3a\x32\0\x09\x5f\x5f\x75\x36\x34\x20\x73\x65\x71\
-\x5f\x6e\x75\x6d\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\
-\x65\x71\x5f\x6e\x75\x6d\x3b\0\x09\x69\x66\x20\x28\x73\x65\x71\x5f\x6e\x75\x6d\
-\x20\x3d\x3d\x20\x30\x29\0\x09\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\
-\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\
-\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x6d\x61\x78\x5f\x65\x6e\
-\x74\x72\x69\x65\x73\x5c\x6e\x22\x29\x3b\0\x62\x70\x66\x5f\x6d\x61\x70\0\x69\
-\x64\0\x6e\x61\x6d\x65\0\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\0\x5f\x5f\
-\x75\x33\x32\0\x75\x6e\x73\x69\x67\x6e\x65\x64\x20\x69\x6e\x74\0\x63\x68\x61\
-\x72\0\x5f\x5f\x41\x52\x52\x41\x59\x5f\x53\x49\x5a\x45\x5f\x54\x59\x50\x45\x5f\
-\x5f\0\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\
-\x71\x2c\x20\x22\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x25\x36\x64\x5c\x6e\x22\
-\x2c\x20\x6d\x61\x70\x2d\x3e\x69\x64\x2c\x20\x6d\x61\x70\x2d\x3e\x6e\x61\x6d\
-\x65\x2c\x20\x6d\x61\x70\x2d\x3e\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\
-\x29\x3b\0\x7d\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\x66\x5f\x70\
-\x72\x6f\x67\0\x70\x72\x6f\x67\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\
-\x6f\x67\0\x69\x74\x65\x72\x2f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x09\x73\x74\
-\x72\x75\x63\x74\x20\x62\x70\x66\x5f\x70\x72\x6f\x67\x20\x2a\x70\x72\x6f\x67\
-\x20\x3d\x20\x63\x74\x78\x2d\x3e\x70\x72\x6f\x67\x3b\0\x09\x69\x66\x20\x28\x21\
-\x70\x72\x6f\x67\x29\0\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x61\x75\x78\0\x09\x61\
-\x75\x78\x20\x3d\x20\x70\x72\x6f\x67\x2d\x3e\x61\x75\x78\x3b\0\x09\x09\x42\x50\
-\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\
-\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\
-\x20\x20\x20\x61\x74\x74\x61\x63\x68\x65\x64\x5c\x6e\x22\x29\x3b\0\x62\x70\x66\
-\x5f\x70\x72\x6f\x67\x5f\x61\x75\x78\0\x61\x74\x74\x61\x63\x68\x5f\x66\x75\x6e\
-\x63\x5f\x6e\x61\x6d\x65\0\x6c\x69\x6e\x6b\x65\x64\x5f\x70\x72\x6f\x67\0\x66\
-\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\x62\x74\x66\0\x09\x42\x50\x46\x5f\x53\x45\
-\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x25\x34\x75\x20\
-\x25\x2d\x31\x36\x73\x20\x25\x73\x20\x25\x73\x5c\x6e\x22\x2c\x20\x61\x75\x78\
-\x2d\x3e\x69\x64\x2c\0\x30\x3a\x34\0\x30\x3a\x35\0\x09\x69\x66\x20\x28\x21\x62\
-\x74\x66\x29\0\x62\x70\x66\x5f\x66\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\x69\x6e\
-\x73\x6e\x5f\x6f\x66\x66\0\x74\x79\x70\x65\x5f\x69\x64\0\x30\0\x73\x74\x72\x69\
-\x6e\x67\x73\0\x74\x79\x70\x65\x73\0\x68\x64\x72\0\x62\x74\x66\x5f\x68\x65\x61\
-\x64\x65\x72\0\x73\x74\x72\x5f\x6c\x65\x6e\0\x09\x74\x79\x70\x65\x73\x20\x3d\
-\x20\x62\x74\x66\x2d\x3e\x74\x79\x70\x65\x73\x3b\0\x09\x62\x70\x66\x5f\x70\x72\
-\x6f\x62\x65\x5f\x72\x65\x61\x64\x5f\x6b\x65\x72\x6e\x65\x6c\x28\x26\x74\x2c\
-\x20\x73\x69\x7a\x65\x6f\x66\x28\x74\x29\x2c\x20\x74\x79\x70\x65\x73\x20\x2b\
-\x20\x62\x74\x66\x5f\x69\x64\x29\x3b\0\x09\x73\x74\x72\x20\x3d\x20\x62\x74\x66\
-\x2d\x3e\x73\x74\x72\x69\x6e\x67\x73\x3b\0\x62\x74\x66\x5f\x74\x79\x70\x65\0\
-\x6e\x61\x6d\x65\x5f\x6f\x66\x66\0\x09\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\x3d\
-\x20\x42\x50\x46\x5f\x43\x4f\x52\x45\x5f\x52\x45\x41\x44\x28\x74\x2c\x20\x6e\
-\x61\x6d\x65\x5f\x6f\x66\x66\x29\x3b\0\x30\x3a\x32\x3a\x30\0\x09\x69\x66\x20\
-\x28\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\x3e\x3d\x20\x62\x74\x66\x2d\x3e\x68\
-\x64\x72\x2e\x73\x74\x72\x5f\x6c\x65\x6e\x29\0\x09\x72\x65\x74\x75\x72\x6e\x20\
-\x73\x74\x72\x20\x2b\x20\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x3b\0\x30\x3a\x33\0\
-\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\0\
-\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\
-\x2e\x31\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\
-\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\
-\x5f\x66\x6d\x74\x2e\x32\0\x4c\x49\x43\x45\x4e\x53\x45\0\x2e\x72\x6f\x64\x61\
-\x74\x61\0\x6c\x69\x63\x65\x6e\x73\x65\0\x9f\xeb\x01\0\x20\0\0\0\0\0\0\0\x24\0\
-\0\0\x24\0\0\0\x44\x02\0\0\x68\x02\0\0\xa4\x01\0\0\x08\0\0\0\x31\0\0\0\x01\0\0\
-\0\0\0\0\0\x07\0\0\0\x56\x02\0\0\x01\0\0\0\0\0\0\0\x17\0\0\0\x10\0\0\0\x31\0\0\
-\0\x09\0\0\0\0\0\0\0\x42\0\0\0\x7b\0\0\0\x1e\x40\x01\0\x08\0\0\0\x42\0\0\0\x7b\
-\0\0\0\x24\x40\x01\0\x10\0\0\0\x42\0\0\0\xf2\0\0\0\x1d\x48\x01\0\x18\0\0\0\x42\
-\0\0\0\x13\x01\0\0\x06\x50\x01\0\x20\0\0\0\x42\0\0\0\x22\x01\0\0\x1d\x44\x01\0\
-\x28\0\0\0\x42\0\0\0\x47\x01\0\0\x06\x5c\x01\0\x38\0\0\0\x42\0\0\0\x5a\x01\0\0\
-\x03\x60\x01\0\x70\0\0\0\x42\0\0\0\xe0\x01\0\0\x02\x68\x01\0\xf0\0\0\0\x42\0\0\
-\0\x2e\x02\0\0\x01\x70\x01\0\x56\x02\0\0\x1a\0\0\0\0\0\0\0\x42\0\0\0\x7b\0\0\0\
-\x1e\x84\x01\0\x08\0\0\0\x42\0\0\0\x7b\0\0\0\x24\x84\x01\0\x10\0\0\0\x42\0\0\0\
-\x64\x02\0\0\x1f\x8c\x01\0\x18\0\0\0\x42\0\0\0\x88\x02\0\0\x06\x98\x01\0\x20\0\
-\0\0\x42\0\0\0\xa1\x02\0\0\x0e\xa4\x01\0\x28\0\0\0\x42\0\0\0\x22\x01\0\0\x1d\
-\x88\x01\0\x30\0\0\0\x42\0\0\0\x47\x01\0\0\x06\xa8\x01\0\x40\0\0\0\x42\0\0\0\
-\xb3\x02\0\0\x03\xac\x01\0\x80\0\0\0\x42\0\0\0\x26\x03\0\0\x02\xb4\x01\0\xb8\0\
-\0\0\x42\0\0\0\x61\x03\0\0\x06\x08\x01\0\xd0\0\0\0\x42\0\0\0\0\0\0\0\0\0\0\0\
-\xd8\0\0\0\x42\0\0\0\xb2\x03\0\0\x0f\x14\x01\0\xe0\0\0\0\x42\0\0\0\xc7\x03\0\0\
-\x2d\x18\x01\0\xf0\0\0\0\x42\0\0\0\xfe\x03\0\0\x0d\x10\x01\0\0\x01\0\0\x42\0\0\
-\0\0\0\0\0\0\0\0\0\x08\x01\0\0\x42\0\0\0\xc7\x03\0\0\x02\x18\x01\0\x20\x01\0\0\
-\x42\0\0\0\x25\x04\0\0\x0d\x1c\x01\0\x38\x01\0\0\x42\0\0\0\0\0\0\0\0\0\0\0\x40\
-\x01\0\0\x42\0\0\0\x25\x04\0\0\x0d\x1c\x01\0\x58\x01\0\0\x42\0\0\0\x25\x04\0\0\
-\x0d\x1c\x01\0\x60\x01\0\0\x42\0\0\0\x53\x04\0\0\x1b\x20\x01\0\x68\x01\0\0\x42\
-\0\0\0\x53\x04\0\0\x06\x20\x01\0\x70\x01\0\0\x42\0\0\0\x76\x04\0\0\x0d\x28\x01\
-\0\x78\x01\0\0\x42\0\0\0\0\0\0\0\0\0\0\0\x80\x01\0\0\x42\0\0\0\x26\x03\0\0\x02\
-\xb4\x01\0\xf8\x01\0\0\x42\0\0\0\x2e\x02\0\0\x01\xc4\x01\0\x10\0\0\0\x31\0\0\0\
-\x07\0\0\0\0\0\0\0\x02\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\0\x08\0\0\0\x3e\0\0\0\0\
-\0\0\0\x10\0\0\0\x02\0\0\0\xee\0\0\0\0\0\0\0\x20\0\0\0\x08\0\0\0\x1e\x01\0\0\0\
-\0\0\0\x70\0\0\0\x0d\0\0\0\x3e\0\0\0\0\0\0\0\x80\0\0\0\x0d\0\0\0\xee\0\0\0\0\0\
-\0\0\xa0\0\0\0\x0d\0\0\0\x1e\x01\0\0\0\0\0\0\x56\x02\0\0\x12\0\0\0\0\0\0\0\x14\
-\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\0\x08\0\0\0\x3e\0\0\0\0\0\0\0\x10\0\0\0\x14\0\
-\0\0\xee\0\0\0\0\0\0\0\x20\0\0\0\x18\0\0\0\x3e\0\0\0\0\0\0\0\x28\0\0\0\x08\0\0\
-\0\x1e\x01\0\0\0\0\0\0\x80\0\0\0\x1a\0\0\0\x3e\0\0\0\0\0\0\0\x90\0\0\0\x1a\0\0\
-\0\xee\0\0\0\0\0\0\0\xa8\0\0\0\x1a\0\0\0\x59\x03\0\0\0\0\0\0\xb0\0\0\0\x1a\0\0\
-\0\x5d\x03\0\0\0\0\0\0\xc0\0\0\0\x1f\0\0\0\x8b\x03\0\0\0\0\0\0\xd8\0\0\0\x20\0\
-\0\0\xee\0\0\0\0\0\0\0\xf0\0\0\0\x20\0\0\0\x3e\0\0\0\0\0\0\0\x18\x01\0\0\x24\0\
-\0\0\x3e\0\0\0\0\0\0\0\x50\x01\0\0\x1a\0\0\0\xee\0\0\0\0\0\0\0\x60\x01\0\0\x20\
-\0\0\0\x4d\x04\0\0\0\0\0\0\x88\x01\0\0\x1a\0\0\0\x1e\x01\0\0\0\0\0\0\x98\x01\0\
-\0\x1a\0\0\0\x8e\x04\0\0\0\0\0\0\xa0\x01\0\0\x18\0\0\0\x3e\0\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xd6\0\0\0\0\0\x02\0\x70\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\xc8\0\0\0\0\0\x02\0\xf0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\xcf\0\0\0\0\0\x03\0\x78\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xc1\0\0\0\0\0\x03\0\x80\
-\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xba\0\0\0\0\0\x03\0\xf8\x01\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\x14\0\0\0\x01\0\x04\0\0\0\0\0\0\0\0\0\x23\0\0\0\0\0\0\0\xf4\0\0\0\
-\x01\0\x04\0\x23\0\0\0\0\0\0\0\x0e\0\0\0\0\0\0\0\x28\0\0\0\x01\0\x04\0\x31\0\0\
-\0\0\0\0\0\x20\0\0\0\0\0\0\0\xdd\0\0\0\x01\0\x04\0\x51\0\0\0\0\0\0\0\x11\0\0\0\
-\0\0\0\0\0\0\0\0\x03\0\x02\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\x03\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\x04\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\xb2\0\0\0\x11\0\x05\0\0\0\0\0\0\0\0\0\x04\0\0\0\0\0\0\0\x3d\0\0\0\x12\
-\0\x02\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\x5b\0\0\0\x12\0\x03\0\0\0\0\0\0\0\0\
-\0\x08\x02\0\0\0\0\0\0\x48\0\0\0\0\0\0\0\x01\0\0\0\x0c\0\0\0\xc8\0\0\0\0\0\0\0\
-\x01\0\0\0\x0c\0\0\0\x50\0\0\0\0\0\0\0\x01\0\0\0\x0c\0\0\0\xd0\x01\0\0\0\0\0\0\
-\x01\0\0\0\x0c\0\0\0\xf0\x03\0\0\0\0\0\0\x0a\0\0\0\x0c\0\0\0\xfc\x03\0\0\0\0\0\
-\0\x0a\0\0\0\x0c\0\0\0\x08\x04\0\0\0\0\0\0\x0a\0\0\0\x0c\0\0\0\x14\x04\0\0\0\0\
-\0\0\x0a\0\0\0\x0c\0\0\0\x2c\x04\0\0\0\0\0\0\0\0\0\0\x0d\0\0\0\x2c\0\0\0\0\0\0\
-\0\0\0\0\0\x0a\0\0\0\x3c\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x50\0\0\0\0\0\0\0\0\0\
-\0\0\x0a\0\0\0\x60\0\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\x70\0\0\0\0\0\0\0\0\0\0\0\
-\x0a\0\0\0\x80\0\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\x90\0\0\0\0\0\0\0\0\0\0\0\x0a\0\
-\0\0\xa0\0\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\xb0\0\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\
-\xc0\0\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\xd0\0\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\xe8\0\
-\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xf8\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x08\x01\0\0\
-\0\0\0\0\0\0\0\0\x0b\0\0\0\x18\x01\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x28\x01\0\0\0\
-\0\0\0\0\0\0\0\x0b\0\0\0\x38\x01\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x48\x01\0\0\0\0\
-\0\0\0\0\0\0\x0b\0\0\0\x58\x01\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x68\x01\0\0\0\0\0\
-\0\0\0\0\0\x0b\0\0\0\x78\x01\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x88\x01\0\0\0\0\0\0\
-\0\0\0\0\x0b\0\0\0\x98\x01\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xa8\x01\0\0\0\0\0\0\0\
-\0\0\0\x0b\0\0\0\xb8\x01\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xc8\x01\0\0\0\0\0\0\0\0\
-\0\0\x0b\0\0\0\xd8\x01\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xe8\x01\0\0\0\0\0\0\0\0\0\
-\0\x0b\0\0\0\xf8\x01\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x08\x02\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\x18\x02\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x28\x02\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\x38\x02\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x48\x02\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\x58\x02\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x68\x02\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\x78\x02\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x94\x02\0\0\0\0\0\0\0\0\0\0\
-\x0a\0\0\0\xa4\x02\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\xb4\x02\0\0\0\0\0\0\0\0\0\0\
-\x0a\0\0\0\xc4\x02\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\xd4\x02\0\0\0\0\0\0\0\0\0\0\
-\x0a\0\0\0\xe4\x02\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\xf4\x02\0\0\0\0\0\0\0\0\0\0\
-\x0a\0\0\0\x0c\x03\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x1c\x03\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\x2c\x03\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x3c\x03\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\x4c\x03\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x5c\x03\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\x6c\x03\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x7c\x03\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\x8c\x03\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x9c\x03\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\xac\x03\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xbc\x03\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\xcc\x03\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xdc\x03\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\xec\x03\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xfc\x03\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\x0c\x04\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x1c\x04\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\x4e\x4f\x41\x42\x43\x44\x4d\0\x2e\x74\x65\x78\x74\0\x2e\x72\x65\x6c\
-\x2e\x42\x54\x46\x2e\x65\x78\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\
-\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\
-\x6f\x67\x2e\x5f\x5f\x5f\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\
-\x61\x70\0\x2e\x72\x65\x6c\x69\x74\x65\x72\x2f\x62\x70\x66\x5f\x6d\x61\x70\0\
-\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x2e\x72\x65\x6c\x69\x74\
-\x65\x72\x2f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x2e\x6c\x6c\x76\x6d\x5f\x61\x64\
-\x64\x72\x73\x69\x67\0\x6c\x69\x63\x65\x6e\x73\x65\0\x2e\x73\x74\x72\x74\x61\
-\x62\0\x2e\x73\x79\x6d\x74\x61\x62\0\x2e\x72\x6f\x64\x61\x74\x61\0\x2e\x72\x65\
-\x6c\x2e\x42\x54\x46\0\x4c\x49\x43\x45\x4e\x53\x45\0\x4c\x42\x42\x31\x5f\x37\0\
-\x4c\x42\x42\x31\x5f\x36\0\x4c\x42\x42\x30\x5f\x34\0\x4c\x42\x42\x31\x5f\x33\0\
-\x4c\x42\x42\x30\x5f\x33\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\
-\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x32\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\
-\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x31\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\x30\x3a\x30\0\x2f\x68\x6f\x6d\x65\x2f\x61\x6c\x72\x75\x61\x2f\x62\x75\x69\x6c\
+\x64\x2f\x6c\x69\x6e\x75\x78\x2f\x6b\x65\x72\x6e\x65\x6c\x2f\x62\x70\x66\x2f\
+\x70\x72\x65\x6c\x6f\x61\x64\x2f\x69\x74\x65\x72\x61\x74\x6f\x72\x73\x2f\x69\
+\x74\x65\x72\x61\x74\x6f\x72\x73\x2e\x62\x70\x66\x2e\x63\0\x09\x73\x74\x72\x75\
+\x63\x74\x20\x73\x65\x71\x5f\x66\x69\x6c\x65\x20\x2a\x73\x65\x71\x20\x3d\x20\
+\x63\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\x65\x71\x3b\0\x62\x70\x66\x5f\
+\x69\x74\x65\x72\x5f\x6d\x65\x74\x61\0\x73\x65\x71\0\x73\x65\x73\x73\x69\x6f\
+\x6e\x5f\x69\x64\0\x73\x65\x71\x5f\x6e\x75\x6d\0\x73\x65\x71\x5f\x66\x69\x6c\
+\x65\0\x5f\x5f\x75\x36\x34\0\x6c\x6f\x6e\x67\x20\x6c\x6f\x6e\x67\x20\x75\x6e\
+\x73\x69\x67\x6e\x65\x64\x20\x69\x6e\x74\0\x30\x3a\x31\0\x09\x73\x74\x72\x75\
+\x63\x74\x20\x62\x70\x66\x5f\x6d\x61\x70\x20\x2a\x6d\x61\x70\x20\x3d\x20\x63\
+\x74\x78\x2d\x3e\x6d\x61\x70\x3b\0\x09\x69\x66\x20\x28\x21\x6d\x61\x70\x29\0\
+\x30\x3a\x32\0\x09\x5f\x5f\x75\x36\x34\x20\x73\x65\x71\x5f\x6e\x75\x6d\x20\x3d\
+\x20\x63\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\x65\x71\x5f\x6e\x75\x6d\
+\x3b\0\x09\x69\x66\x20\x28\x73\x65\x71\x5f\x6e\x75\x6d\x20\x3d\x3d\x20\x30\x29\
+\0\x09\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\
+\x71\x2c\x20\x22\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\
+\x20\x20\x20\x20\x20\x20\x20\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\x5c\
+\x6e\x22\x29\x3b\0\x62\x70\x66\x5f\x6d\x61\x70\0\x69\x64\0\x6e\x61\x6d\x65\0\
+\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\0\x5f\x5f\x75\x33\x32\0\x75\x6e\
+\x73\x69\x67\x6e\x65\x64\x20\x69\x6e\x74\0\x63\x68\x61\x72\0\x5f\x5f\x41\x52\
+\x52\x41\x59\x5f\x53\x49\x5a\x45\x5f\x54\x59\x50\x45\x5f\x5f\0\x09\x42\x50\x46\
+\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x25\
+\x34\x75\x20\x25\x2d\x31\x36\x73\x25\x36\x64\x5c\x6e\x22\x2c\x20\x6d\x61\x70\
+\x2d\x3e\x69\x64\x2c\x20\x6d\x61\x70\x2d\x3e\x6e\x61\x6d\x65\x2c\x20\x6d\x61\
+\x70\x2d\x3e\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\x29\x3b\0\x7d\0\x62\
+\x70\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x70\x72\
+\x6f\x67\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x69\x74\x65\
+\x72\x2f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x09\x73\x74\x72\x75\x63\x74\x20\x62\
+\x70\x66\x5f\x70\x72\x6f\x67\x20\x2a\x70\x72\x6f\x67\x20\x3d\x20\x63\x74\x78\
+\x2d\x3e\x70\x72\x6f\x67\x3b\0\x09\x69\x66\x20\x28\x21\x70\x72\x6f\x67\x29\0\
+\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x61\x75\x78\0\x09\x61\x75\x78\x20\x3d\x20\
+\x70\x72\x6f\x67\x2d\x3e\x61\x75\x78\x3b\0\x09\x09\x42\x50\x46\x5f\x53\x45\x51\
+\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x20\x20\x69\x64\x20\
+\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x61\x74\
+\x74\x61\x63\x68\x65\x64\x5c\x6e\x22\x29\x3b\0\x62\x70\x66\x5f\x70\x72\x6f\x67\
+\x5f\x61\x75\x78\0\x61\x74\x74\x61\x63\x68\x5f\x66\x75\x6e\x63\x5f\x6e\x61\x6d\
+\x65\0\x64\x73\x74\x5f\x70\x72\x6f\x67\0\x66\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\
+\x62\x74\x66\0\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\
+\x73\x65\x71\x2c\x20\x22\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x20\x25\x73\x20\
+\x25\x73\x5c\x6e\x22\x2c\x20\x61\x75\x78\x2d\x3e\x69\x64\x2c\0\x30\x3a\x34\0\
+\x30\x3a\x35\0\x09\x69\x66\x20\x28\x21\x62\x74\x66\x29\0\x62\x70\x66\x5f\x66\
+\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\x69\x6e\x73\x6e\x5f\x6f\x66\x66\0\x74\x79\
+\x70\x65\x5f\x69\x64\0\x30\0\x73\x74\x72\x69\x6e\x67\x73\0\x74\x79\x70\x65\x73\
+\0\x68\x64\x72\0\x62\x74\x66\x5f\x68\x65\x61\x64\x65\x72\0\x73\x74\x72\x5f\x6c\
+\x65\x6e\0\x09\x74\x79\x70\x65\x73\x20\x3d\x20\x62\x74\x66\x2d\x3e\x74\x79\x70\
+\x65\x73\x3b\0\x09\x62\x70\x66\x5f\x70\x72\x6f\x62\x65\x5f\x72\x65\x61\x64\x5f\
+\x6b\x65\x72\x6e\x65\x6c\x28\x26\x74\x2c\x20\x73\x69\x7a\x65\x6f\x66\x28\x74\
+\x29\x2c\x20\x74\x79\x70\x65\x73\x20\x2b\x20\x62\x74\x66\x5f\x69\x64\x29\x3b\0\
+\x09\x73\x74\x72\x20\x3d\x20\x62\x74\x66\x2d\x3e\x73\x74\x72\x69\x6e\x67\x73\
+\x3b\0\x62\x74\x66\x5f\x74\x79\x70\x65\0\x6e\x61\x6d\x65\x5f\x6f\x66\x66\0\x09\
+\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\x3d\x20\x42\x50\x46\x5f\x43\x4f\x52\x45\
+\x5f\x52\x45\x41\x44\x28\x74\x2c\x20\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x29\x3b\0\
+\x30\x3a\x32\x3a\x30\0\x09\x69\x66\x20\x28\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\
+\x3e\x3d\x20\x62\x74\x66\x2d\x3e\x68\x64\x72\x2e\x73\x74\x72\x5f\x6c\x65\x6e\
+\x29\0\x09\x72\x65\x74\x75\x72\x6e\x20\x73\x74\x72\x20\x2b\x20\x6e\x61\x6d\x65\
+\x5f\x6f\x66\x66\x3b\0\x30\x3a\x33\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\
+\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\
+\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x31\0\x64\x75\x6d\x70\x5f\x62\x70\x66\
+\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\
+\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x32\0\x4c\x49\x43\x45\
+\x4e\x53\x45\0\x2e\x72\x6f\x64\x61\x74\x61\0\x6c\x69\x63\x65\x6e\x73\x65\0\x9f\
+\xeb\x01\0\x20\0\0\0\0\0\0\0\x24\0\0\0\x24\0\0\0\x44\x02\0\0\x68\x02\0\0\xa4\
+\x01\0\0\x08\0\0\0\x31\0\0\0\x01\0\0\0\0\0\0\0\x07\0\0\0\x62\x02\0\0\x01\0\0\0\
+\0\0\0\0\x17\0\0\0\x10\0\0\0\x31\0\0\0\x09\0\0\0\0\0\0\0\x42\0\0\0\x87\0\0\0\
+\x1e\x40\x01\0\x08\0\0\0\x42\0\0\0\x87\0\0\0\x24\x40\x01\0\x10\0\0\0\x42\0\0\0\
+\xfe\0\0\0\x1d\x48\x01\0\x18\0\0\0\x42\0\0\0\x1f\x01\0\0\x06\x50\x01\0\x20\0\0\
+\0\x42\0\0\0\x2e\x01\0\0\x1d\x44\x01\0\x28\0\0\0\x42\0\0\0\x53\x01\0\0\x06\x5c\
+\x01\0\x38\0\0\0\x42\0\0\0\x66\x01\0\0\x03\x60\x01\0\x70\0\0\0\x42\0\0\0\xec\
+\x01\0\0\x02\x68\x01\0\xf0\0\0\0\x42\0\0\0\x3a\x02\0\0\x01\x70\x01\0\x62\x02\0\
+\0\x1a\0\0\0\0\0\0\0\x42\0\0\0\x87\0\0\0\x1e\x84\x01\0\x08\0\0\0\x42\0\0\0\x87\
+\0\0\0\x24\x84\x01\0\x10\0\0\0\x42\0\0\0\x70\x02\0\0\x1f\x8c\x01\0\x18\0\0\0\
+\x42\0\0\0\x94\x02\0\0\x06\x98\x01\0\x20\0\0\0\x42\0\0\0\xad\x02\0\0\x0e\xa4\
+\x01\0\x28\0\0\0\x42\0\0\0\x2e\x01\0\0\x1d\x88\x01\0\x30\0\0\0\x42\0\0\0\x53\
+\x01\0\0\x06\xa8\x01\0\x40\0\0\0\x42\0\0\0\xbf\x02\0\0\x03\xac\x01\0\x80\0\0\0\
+\x42\0\0\0\x2f\x03\0\0\x02\xb4\x01\0\xb8\0\0\0\x42\0\0\0\x6a\x03\0\0\x06\x08\
+\x01\0\xd0\0\0\0\x42\0\0\0\0\0\0\0\0\0\0\0\xd8\0\0\0\x42\0\0\0\xbb\x03\0\0\x0f\
+\x14\x01\0\xe0\0\0\0\x42\0\0\0\xd0\x03\0\0\x2d\x18\x01\0\xf0\0\0\0\x42\0\0\0\
+\x07\x04\0\0\x0d\x10\x01\0\0\x01\0\0\x42\0\0\0\0\0\0\0\0\0\0\0\x08\x01\0\0\x42\
+\0\0\0\xd0\x03\0\0\x02\x18\x01\0\x20\x01\0\0\x42\0\0\0\x2e\x04\0\0\x0d\x1c\x01\
+\0\x38\x01\0\0\x42\0\0\0\0\0\0\0\0\0\0\0\x40\x01\0\0\x42\0\0\0\x2e\x04\0\0\x0d\
+\x1c\x01\0\x58\x01\0\0\x42\0\0\0\x2e\x04\0\0\x0d\x1c\x01\0\x60\x01\0\0\x42\0\0\
+\0\x5c\x04\0\0\x1b\x20\x01\0\x68\x01\0\0\x42\0\0\0\x5c\x04\0\0\x06\x20\x01\0\
+\x70\x01\0\0\x42\0\0\0\x7f\x04\0\0\x0d\x28\x01\0\x78\x01\0\0\x42\0\0\0\0\0\0\0\
+\0\0\0\0\x80\x01\0\0\x42\0\0\0\x2f\x03\0\0\x02\xb4\x01\0\xf8\x01\0\0\x42\0\0\0\
+\x3a\x02\0\0\x01\xc4\x01\0\x10\0\0\0\x31\0\0\0\x07\0\0\0\0\0\0\0\x02\0\0\0\x3e\
+\0\0\0\0\0\0\0\x08\0\0\0\x08\0\0\0\x3e\0\0\0\0\0\0\0\x10\0\0\0\x02\0\0\0\xfa\0\
+\0\0\0\0\0\0\x20\0\0\0\x08\0\0\0\x2a\x01\0\0\0\0\0\0\x70\0\0\0\x0d\0\0\0\x3e\0\
+\0\0\0\0\0\0\x80\0\0\0\x0d\0\0\0\xfa\0\0\0\0\0\0\0\xa0\0\0\0\x0d\0\0\0\x2a\x01\
+\0\0\0\0\0\0\x62\x02\0\0\x12\0\0\0\0\0\0\0\x14\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\
+\0\x08\0\0\0\x3e\0\0\0\0\0\0\0\x10\0\0\0\x14\0\0\0\xfa\0\0\0\0\0\0\0\x20\0\0\0\
+\x18\0\0\0\x3e\0\0\0\0\0\0\0\x28\0\0\0\x08\0\0\0\x2a\x01\0\0\0\0\0\0\x80\0\0\0\
+\x1a\0\0\0\x3e\0\0\0\0\0\0\0\x90\0\0\0\x1a\0\0\0\xfa\0\0\0\0\0\0\0\xa8\0\0\0\
+\x1a\0\0\0\x62\x03\0\0\0\0\0\0\xb0\0\0\0\x1a\0\0\0\x66\x03\0\0\0\0\0\0\xc0\0\0\
+\0\x1f\0\0\0\x94\x03\0\0\0\0\0\0\xd8\0\0\0\x20\0\0\0\xfa\0\0\0\0\0\0\0\xf0\0\0\
+\0\x20\0\0\0\x3e\0\0\0\0\0\0\0\x18\x01\0\0\x24\0\0\0\x3e\0\0\0\0\0\0\0\x50\x01\
+\0\0\x1a\0\0\0\xfa\0\0\0\0\0\0\0\x60\x01\0\0\x20\0\0\0\x56\x04\0\0\0\0\0\0\x88\
+\x01\0\0\x1a\0\0\0\x2a\x01\0\0\0\0\0\0\x98\x01\0\0\x1a\0\0\0\x97\x04\0\0\0\0\0\
+\0\xa0\x01\0\0\x18\0\0\0\x3e\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\x91\0\0\0\x04\0\xf1\xff\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xe6\0\0\
+\0\0\0\x02\0\x70\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xd8\0\0\0\0\0\x02\0\xf0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\0\0\xdf\0\0\0\0\0\x03\0\x78\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\xd1\0\0\0\0\0\x03\0\x80\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xca\0\0\0\0\0\x03\0\
+\xf8\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x14\0\0\0\x01\0\x04\0\0\0\0\0\0\0\0\0\x23\
+\0\0\0\0\0\0\0\x04\x01\0\0\x01\0\x04\0\x23\0\0\0\0\0\0\0\x0e\0\0\0\0\0\0\0\x28\
+\0\0\0\x01\0\x04\0\x31\0\0\0\0\0\0\0\x20\0\0\0\0\0\0\0\xed\0\0\0\x01\0\x04\0\
+\x51\0\0\0\0\0\0\0\x11\0\0\0\0\0\0\0\0\0\0\0\x03\0\x02\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\x03\0\x03\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\
+\x04\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xc2\0\0\0\x11\0\x05\0\0\0\0\0\0\0\0\0\
+\x04\0\0\0\0\0\0\0\x3d\0\0\0\x12\0\x02\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\x5b\
+\0\0\0\x12\0\x03\0\0\0\0\0\0\0\0\0\x08\x02\0\0\0\0\0\0\x48\0\0\0\0\0\0\0\x01\0\
+\0\0\x0d\0\0\0\xc8\0\0\0\0\0\0\0\x01\0\0\0\x0d\0\0\0\x50\0\0\0\0\0\0\0\x01\0\0\
+\0\x0d\0\0\0\xd0\x01\0\0\0\0\0\0\x01\0\0\0\x0d\0\0\0\xf0\x03\0\0\0\0\0\0\x0a\0\
+\0\0\x0d\0\0\0\xfc\x03\0\0\0\0\0\0\x0a\0\0\0\x0d\0\0\0\x08\x04\0\0\0\0\0\0\x0a\
+\0\0\0\x0d\0\0\0\x14\x04\0\0\0\0\0\0\x0a\0\0\0\x0d\0\0\0\x2c\x04\0\0\0\0\0\0\0\
+\0\0\0\x0e\0\0\0\x2c\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x3c\0\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x50\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x60\0\0\0\0\0\0\0\0\0\0\0\x0b\0\
+\0\0\x70\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x80\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\
+\x90\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xa0\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xb0\0\
+\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xc0\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xd0\0\0\0\0\
+\0\0\0\0\0\0\0\x0b\0\0\0\xe8\0\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\xf8\0\0\0\0\0\0\0\
+\0\0\0\0\x0c\0\0\0\x08\x01\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x18\x01\0\0\0\0\0\0\0\
+\0\0\0\x0c\0\0\0\x28\x01\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x38\x01\0\0\0\0\0\0\0\0\
+\0\0\x0c\0\0\0\x48\x01\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x58\x01\0\0\0\0\0\0\0\0\0\
+\0\x0c\0\0\0\x68\x01\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x78\x01\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x88\x01\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x98\x01\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\xa8\x01\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\xb8\x01\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\xc8\x01\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\xd8\x01\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\xe8\x01\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\xf8\x01\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x08\x02\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x18\x02\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x28\x02\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x38\x02\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x48\x02\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x58\x02\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x68\x02\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x78\x02\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x94\x02\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xa4\x02\0\0\0\0\0\0\0\0\0\0\
+\x0b\0\0\0\xb4\x02\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xc4\x02\0\0\0\0\0\0\0\0\0\0\
+\x0b\0\0\0\xd4\x02\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xe4\x02\0\0\0\0\0\0\0\0\0\0\
+\x0b\0\0\0\xf4\x02\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x0c\x03\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x1c\x03\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x2c\x03\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x3c\x03\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x4c\x03\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x5c\x03\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x6c\x03\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x7c\x03\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x8c\x03\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x9c\x03\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\xac\x03\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\xbc\x03\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\xcc\x03\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\xdc\x03\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\xec\x03\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\xfc\x03\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x0c\x04\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x1c\x04\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x4d\x4e\x40\x41\x42\x43\x4c\0\
+\x2e\x74\x65\x78\x74\0\x2e\x72\x65\x6c\x2e\x42\x54\x46\x2e\x65\x78\x74\0\x64\
+\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\0\x64\
+\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\x66\x6d\x74\0\
+\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\0\x2e\x72\x65\x6c\x69\x74\x65\
+\x72\x2f\x62\x70\x66\x5f\x6d\x61\x70\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\
+\x72\x6f\x67\0\x2e\x72\x65\x6c\x69\x74\x65\x72\x2f\x62\x70\x66\x5f\x70\x72\x6f\
+\x67\0\x2e\x6c\x6c\x76\x6d\x5f\x61\x64\x64\x72\x73\x69\x67\0\x6c\x69\x63\x65\
+\x6e\x73\x65\0\x69\x74\x65\x72\x61\x74\x6f\x72\x73\x2e\x62\x70\x66\x2e\x63\0\
+\x2e\x73\x74\x72\x74\x61\x62\0\x2e\x73\x79\x6d\x74\x61\x62\0\x2e\x72\x6f\x64\
+\x61\x74\x61\0\x2e\x72\x65\x6c\x2e\x42\x54\x46\0\x4c\x49\x43\x45\x4e\x53\x45\0\
+\x4c\x42\x42\x31\x5f\x37\0\x4c\x42\x42\x31\x5f\x36\0\x4c\x42\x42\x30\x5f\x34\0\
+\x4c\x42\x42\x31\x5f\x33\0\x4c\x42\x42\x30\x5f\x33\0\x64\x75\x6d\x70\x5f\x62\
+\x70\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x32\0\x64\x75\x6d\
+\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x31\0\0\0\
 \0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\x01\0\0\0\x06\0\0\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x04\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\x4e\0\0\0\x01\0\0\0\x06\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\
-\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\x6d\0\0\0\x01\0\0\0\x06\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x40\x01\0\0\0\0\0\0\x08\
-\x02\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xa1\0\0\0\
-\x01\0\0\0\x02\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x48\x03\0\0\0\0\0\0\x62\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x89\0\0\0\x01\0\0\0\x03\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xaa\x03\0\0\0\0\0\0\x04\0\0\0\0\0\0\0\0\0\0\0\0\
-\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xad\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\xae\x03\0\0\0\0\0\0\x34\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\xe2\x0c\0\0\0\0\0\0\x2c\x04\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\x99\0\0\0\x02\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x10\x11\0\0\0\
-\0\0\0\x80\x01\0\0\0\0\0\0\x0e\0\0\0\x0d\0\0\0\x08\0\0\0\0\0\0\0\x18\0\0\0\0\0\
-\0\0\x4a\0\0\0\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x90\x12\0\0\0\0\0\0\
-\x20\0\0\0\0\0\0\0\x08\0\0\0\x02\0\0\0\x08\0\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\x69\
-\0\0\0\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xb0\x12\0\0\0\0\0\0\x20\0\0\0\
-\0\0\0\0\x08\0\0\0\x03\0\0\0\x08\0\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\xa9\0\0\0\x09\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xd0\x12\0\0\0\0\0\0\x50\0\0\0\0\0\0\0\
-\x08\0\0\0\x06\0\0\0\x08\0\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\x07\0\0\0\x09\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x20\x13\0\0\0\0\0\0\xe0\x03\0\0\0\0\0\0\x08\0\0\
-\0\x07\0\0\0\x08\0\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\x7b\0\0\0\x03\x4c\xff\x6f\0\0\
-\0\x80\0\0\0\0\0\0\0\0\0\0\0\0\0\x17\0\0\0\0\0\0\x07\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x91\0\0\0\x03\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\x07\x17\0\0\0\0\0\0\x0a\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\0";
+\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\x01\0\0\
+\0\x06\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\0\0\0\x04\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x4e\0\0\0\x01\0\0\0\x06\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x08\0\0\
+\0\0\0\0\0\0\0\0\0\0\0\0\0\x6d\0\0\0\x01\0\0\0\x06\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\x40\x01\0\0\0\0\0\0\x08\x02\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\xb1\0\0\0\x01\0\0\0\x02\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x48\x03\0\
+\0\0\0\0\0\x62\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\x89\0\0\0\x01\0\0\0\x03\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xaa\x03\0\0\0\0\0\0\x04\
+\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xbd\0\0\0\x01\
+\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xae\x03\0\0\0\0\0\0\x3d\x09\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x01\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\0\0\0\xeb\x0c\0\0\0\0\0\0\x2c\x04\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xa9\0\0\0\x02\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\0\0\0\0\x18\x11\0\0\0\0\0\0\x98\x01\0\0\0\0\0\0\x0e\0\0\0\x0e\0\0\0\x08\0\0\
+\0\0\0\0\0\x18\0\0\0\0\0\0\0\x4a\0\0\0\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\xb0\x12\0\0\0\0\0\0\x20\0\0\0\0\0\0\0\x08\0\0\0\x02\0\0\0\x08\0\0\0\0\0\0\0\
+\x10\0\0\0\0\0\0\0\x69\0\0\0\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xd0\x12\
+\0\0\0\0\0\0\x20\0\0\0\0\0\0\0\x08\0\0\0\x03\0\0\0\x08\0\0\0\0\0\0\0\x10\0\0\0\
+\0\0\0\0\xb9\0\0\0\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xf0\x12\0\0\0\0\0\
+\0\x50\0\0\0\0\0\0\0\x08\0\0\0\x06\0\0\0\x08\0\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\
+\x07\0\0\0\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x40\x13\0\0\0\0\0\0\xe0\
+\x03\0\0\0\0\0\0\x08\0\0\0\x07\0\0\0\x08\0\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\x7b\0\
+\0\0\x03\x4c\xff\x6f\0\0\0\x80\0\0\0\0\0\0\0\0\0\0\0\0\x20\x17\0\0\0\0\0\0\x07\
+\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xa1\0\0\0\x03\
+\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x27\x17\0\0\0\0\0\0\x1a\x01\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0";
 
 	return 0;
 err:
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 3bc2ed2e171b..e6a0a948e30c 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2154,14 +2154,14 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 	prog->expected_attach_type = attr->expected_attach_type;
 	prog->aux->attach_btf_id = attr->attach_btf_id;
 	if (attr->attach_prog_fd) {
-		struct bpf_prog *tgt_prog;
+		struct bpf_prog *dst_prog;
 
-		tgt_prog = bpf_prog_get(attr->attach_prog_fd);
-		if (IS_ERR(tgt_prog)) {
-			err = PTR_ERR(tgt_prog);
+		dst_prog = bpf_prog_get(attr->attach_prog_fd);
+		if (IS_ERR(dst_prog)) {
+			err = PTR_ERR(dst_prog);
 			goto free_prog_nouncharge;
 		}
-		prog->aux->linked_prog = tgt_prog;
+		prog->aux->dst_prog = dst_prog;
 	}
 
 	prog->aux->offload_requested = !!attr->prog_ifindex;
@@ -2498,11 +2498,23 @@ struct bpf_link *bpf_link_get_from_fd(u32 ufd)
 struct bpf_tracing_link {
 	struct bpf_link link;
 	enum bpf_attach_type attach_type;
+	struct bpf_trampoline *trampoline;
+	struct bpf_prog *tgt_prog;
 };
 
 static void bpf_tracing_link_release(struct bpf_link *link)
 {
-	WARN_ON_ONCE(bpf_trampoline_unlink_prog(link->prog));
+	struct bpf_tracing_link *tr_link =
+		container_of(link, struct bpf_tracing_link, link);
+
+	WARN_ON_ONCE(bpf_trampoline_unlink_prog(link->prog,
+						tr_link->trampoline));
+
+	bpf_trampoline_put(tr_link->trampoline);
+
+	/* tgt_prog is NULL if target is a kernel function */
+	if (tr_link->tgt_prog)
+		bpf_prog_put(tr_link->tgt_prog);
 }
 
 static void bpf_tracing_link_dealloc(struct bpf_link *link)
@@ -2545,7 +2557,9 @@ static const struct bpf_link_ops bpf_tracing_link_lops = {
 static int bpf_tracing_prog_attach(struct bpf_prog *prog)
 {
 	struct bpf_link_primer link_primer;
+	struct bpf_prog *tgt_prog = NULL;
 	struct bpf_tracing_link *link;
+	struct bpf_trampoline *tr;
 	int err;
 
 	switch (prog->type) {
@@ -2583,19 +2597,37 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog)
 		      &bpf_tracing_link_lops, prog);
 	link->attach_type = prog->expected_attach_type;
 
-	err = bpf_link_prime(&link->link, &link_primer);
-	if (err) {
-		kfree(link);
-		goto out_put_prog;
+	mutex_lock(&prog->aux->dst_mutex);
+
+	if (!prog->aux->dst_trampoline) {
+		err = -ENOENT;
+		goto out_unlock;
 	}
+	tr = prog->aux->dst_trampoline;
+	tgt_prog = prog->aux->dst_prog;
+
+	err = bpf_link_prime(&link->link, &link_primer);
+	if (err)
+		goto out_unlock;
 
-	err = bpf_trampoline_link_prog(prog);
+	err = bpf_trampoline_link_prog(prog, tr);
 	if (err) {
 		bpf_link_cleanup(&link_primer);
-		goto out_put_prog;
+		link = NULL;
+		goto out_unlock;
 	}
 
+	link->tgt_prog = tgt_prog;
+	link->trampoline = tr;
+
+	prog->aux->dst_prog = NULL;
+	prog->aux->dst_trampoline = NULL;
+	mutex_unlock(&prog->aux->dst_mutex);
+
 	return bpf_link_settle(&link_primer);
+out_unlock:
+	mutex_unlock(&prog->aux->dst_mutex);
+	kfree(link);
 out_put_prog:
 	bpf_prog_put(prog);
 	return err;
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 28c1899949e0..35c5887d82ff 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -261,14 +261,12 @@ static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(struct bpf_prog *prog)
 	}
 }
 
-int bpf_trampoline_link_prog(struct bpf_prog *prog)
+int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr)
 {
 	enum bpf_tramp_prog_type kind;
-	struct bpf_trampoline *tr;
 	int err = 0;
 	int cnt;
 
-	tr = prog->aux->trampoline;
 	kind = bpf_attach_type_to_tramp(prog);
 	mutex_lock(&tr->mutex);
 	if (tr->extension_prog) {
@@ -301,7 +299,7 @@ int bpf_trampoline_link_prog(struct bpf_prog *prog)
 	}
 	hlist_add_head(&prog->aux->tramp_hlist, &tr->progs_hlist[kind]);
 	tr->progs_cnt[kind]++;
-	err = bpf_trampoline_update(prog->aux->trampoline);
+	err = bpf_trampoline_update(tr);
 	if (err) {
 		hlist_del(&prog->aux->tramp_hlist);
 		tr->progs_cnt[kind]--;
@@ -312,13 +310,11 @@ out:
 }
 
 /* bpf_trampoline_unlink_prog() should never fail. */
-int bpf_trampoline_unlink_prog(struct bpf_prog *prog)
+int bpf_trampoline_unlink_prog(struct bpf_prog *prog, struct bpf_trampoline *tr)
 {
 	enum bpf_tramp_prog_type kind;
-	struct bpf_trampoline *tr;
 	int err;
 
-	tr = prog->aux->trampoline;
 	kind = bpf_attach_type_to_tramp(prog);
 	mutex_lock(&tr->mutex);
 	if (kind == BPF_TRAMP_REPLACE) {
@@ -330,7 +326,7 @@ int bpf_trampoline_unlink_prog(struct bpf_prog *prog)
 	}
 	hlist_del(&prog->aux->tramp_hlist);
 	tr->progs_cnt[kind]--;
-	err = bpf_trampoline_update(prog->aux->trampoline);
+	err = bpf_trampoline_update(tr);
 out:
 	mutex_unlock(&tr->mutex);
 	return err;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 2ee343dda73a..a97a2f2964e3 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2648,8 +2648,7 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno,
 
 static enum bpf_prog_type resolve_prog_type(struct bpf_prog *prog)
 {
-	return prog->aux->linked_prog ? prog->aux->linked_prog->type
-				      : prog->type;
+	return prog->aux->dst_prog ? prog->aux->dst_prog->type : prog->type;
 }
 
 static bool may_access_direct_pkt_data(struct bpf_verifier_env *env,
@@ -11475,7 +11474,7 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
 static int check_attach_btf_id(struct bpf_verifier_env *env)
 {
 	struct bpf_prog *prog = env->prog;
-	struct bpf_prog *tgt_prog = prog->aux->linked_prog;
+	struct bpf_prog *tgt_prog = prog->aux->dst_prog;
 	struct bpf_attach_target_info tgt_info = {};
 	u32 btf_id = prog->aux->attach_btf_id;
 	struct bpf_trampoline *tr;
@@ -11501,6 +11500,10 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 		return ret;
 
 	if (tgt_prog && prog->type == BPF_PROG_TYPE_EXT) {
+		/* to make freplace equivalent to their targets, they need to
+		 * inherit env->ops and expected_attach_type for the rest of the
+		 * verification
+		 */
 		env->ops = bpf_verifier_ops[tgt_prog->type];
 		prog->expected_attach_type = tgt_prog->expected_attach_type;
 	}
@@ -11529,7 +11532,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 	if (!tr)
 		return -ENOMEM;
 
-	prog->aux->trampoline = tr;
+	prog->aux->dst_trampoline = tr;
 	return 0;
 }
 
-- 
cgit v1.2.3


From 4a1e7c0c63e02daad751842b7880f9bbcdfb6e89 Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@redhat.com>
Date: Tue, 29 Sep 2020 14:45:51 +0200
Subject: bpf: Support attaching freplace programs to multiple attach points
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This enables support for attaching freplace programs to multiple attach
points. It does this by amending the UAPI for bpf_link_Create with a target
btf ID that can be used to supply the new attachment point along with the
target program fd. The target must be compatible with the target that was
supplied at program load time.

The implementation reuses the checks that were factored out of
check_attach_btf_id() to ensure compatibility between the BTF types of the
old and new attachment. If these match, a new bpf_tracing_link will be
created for the new attach target, allowing multiple attachments to
co-exist simultaneously.

The code could theoretically support multiple-attach of other types of
tracing programs as well, but since I don't have a use case for any of
those, there is no API support for doing so.

Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/160138355169.48470.17165680973640685368.stgit@toke.dk
---
 include/linux/bpf.h            |   2 +
 include/uapi/linux/bpf.h       |   9 ++-
 kernel/bpf/syscall.c           | 132 ++++++++++++++++++++++++++++++++++++-----
 kernel/bpf/verifier.c          |  10 ++++
 tools/include/uapi/linux/bpf.h |   9 ++-
 5 files changed, 142 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 839dd8670a7a..50e5c4b52bd1 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -768,6 +768,8 @@ struct bpf_prog_aux {
 	struct mutex dst_mutex; /* protects dst_* pointers below, *after* prog becomes visible */
 	struct bpf_prog *dst_prog;
 	struct bpf_trampoline *dst_trampoline;
+	enum bpf_prog_type saved_dst_prog_type;
+	enum bpf_attach_type saved_dst_attach_type;
 	bool verifier_zext; /* Zero extensions has been inserted by verifier. */
 	bool offload_requested;
 	bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 96ddb00b91dc..2b1d3f16cbd1 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -639,8 +639,13 @@ union bpf_attr {
 		};
 		__u32		attach_type;	/* attach type */
 		__u32		flags;		/* extra flags */
-		__aligned_u64	iter_info;	/* extra bpf_iter_link_info */
-		__u32		iter_info_len;	/* iter_info length */
+		union {
+			__u32		target_btf_id;	/* btf_id of target to attach to */
+			struct {
+				__aligned_u64	iter_info;	/* extra bpf_iter_link_info */
+				__u32		iter_info_len;	/* iter_info length */
+			};
+		};
 	} link_create;
 
 	struct { /* struct used by BPF_LINK_UPDATE command */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index e6a0a948e30c..f1528c2a6927 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -4,6 +4,7 @@
 #include <linux/bpf.h>
 #include <linux/bpf_trace.h>
 #include <linux/bpf_lirc.h>
+#include <linux/bpf_verifier.h>
 #include <linux/btf.h>
 #include <linux/syscalls.h>
 #include <linux/slab.h>
@@ -2554,12 +2555,15 @@ static const struct bpf_link_ops bpf_tracing_link_lops = {
 	.fill_link_info = bpf_tracing_link_fill_link_info,
 };
 
-static int bpf_tracing_prog_attach(struct bpf_prog *prog)
+static int bpf_tracing_prog_attach(struct bpf_prog *prog,
+				   int tgt_prog_fd,
+				   u32 btf_id)
 {
 	struct bpf_link_primer link_primer;
 	struct bpf_prog *tgt_prog = NULL;
+	struct bpf_trampoline *tr = NULL;
 	struct bpf_tracing_link *link;
-	struct bpf_trampoline *tr;
+	u64 key = 0;
 	int err;
 
 	switch (prog->type) {
@@ -2588,6 +2592,28 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog)
 		goto out_put_prog;
 	}
 
+	if (!!tgt_prog_fd != !!btf_id) {
+		err = -EINVAL;
+		goto out_put_prog;
+	}
+
+	if (tgt_prog_fd) {
+		/* For now we only allow new targets for BPF_PROG_TYPE_EXT */
+		if (prog->type != BPF_PROG_TYPE_EXT) {
+			err = -EINVAL;
+			goto out_put_prog;
+		}
+
+		tgt_prog = bpf_prog_get(tgt_prog_fd);
+		if (IS_ERR(tgt_prog)) {
+			err = PTR_ERR(tgt_prog);
+			tgt_prog = NULL;
+			goto out_put_prog;
+		}
+
+		key = bpf_trampoline_compute_key(tgt_prog, btf_id);
+	}
+
 	link = kzalloc(sizeof(*link), GFP_USER);
 	if (!link) {
 		err = -ENOMEM;
@@ -2599,12 +2625,58 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog)
 
 	mutex_lock(&prog->aux->dst_mutex);
 
-	if (!prog->aux->dst_trampoline) {
+	/* There are a few possible cases here:
+	 *
+	 * - if prog->aux->dst_trampoline is set, the program was just loaded
+	 *   and not yet attached to anything, so we can use the values stored
+	 *   in prog->aux
+	 *
+	 * - if prog->aux->dst_trampoline is NULL, the program has already been
+         *   attached to a target and its initial target was cleared (below)
+	 *
+	 * - if tgt_prog != NULL, the caller specified tgt_prog_fd +
+	 *   target_btf_id using the link_create API.
+	 *
+	 * - if tgt_prog == NULL when this function was called using the old
+         *   raw_tracepoint_open API, and we need a target from prog->aux
+         *
+         * The combination of no saved target in prog->aux, and no target
+         * specified on load is illegal, and we reject that here.
+	 */
+	if (!prog->aux->dst_trampoline && !tgt_prog) {
 		err = -ENOENT;
 		goto out_unlock;
 	}
-	tr = prog->aux->dst_trampoline;
-	tgt_prog = prog->aux->dst_prog;
+
+	if (!prog->aux->dst_trampoline ||
+	    (key && key != prog->aux->dst_trampoline->key)) {
+		/* If there is no saved target, or the specified target is
+		 * different from the destination specified at load time, we
+		 * need a new trampoline and a check for compatibility
+		 */
+		struct bpf_attach_target_info tgt_info = {};
+
+		err = bpf_check_attach_target(NULL, prog, tgt_prog, btf_id,
+					      &tgt_info);
+		if (err)
+			goto out_unlock;
+
+		tr = bpf_trampoline_get(key, &tgt_info);
+		if (!tr) {
+			err = -ENOMEM;
+			goto out_unlock;
+		}
+	} else {
+		/* The caller didn't specify a target, or the target was the
+		 * same as the destination supplied during program load. This
+		 * means we can reuse the trampoline and reference from program
+		 * load time, and there is no need to allocate a new one. This
+		 * can only happen once for any program, as the saved values in
+		 * prog->aux are cleared below.
+		 */
+		tr = prog->aux->dst_trampoline;
+		tgt_prog = prog->aux->dst_prog;
+	}
 
 	err = bpf_link_prime(&link->link, &link_primer);
 	if (err)
@@ -2620,15 +2692,31 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog)
 	link->tgt_prog = tgt_prog;
 	link->trampoline = tr;
 
+	/* Always clear the trampoline and target prog from prog->aux to make
+	 * sure the original attach destination is not kept alive after a
+	 * program is (re-)attached to another target.
+	 */
+	if (prog->aux->dst_prog &&
+	    (tgt_prog_fd || tr != prog->aux->dst_trampoline))
+		/* got extra prog ref from syscall, or attaching to different prog */
+		bpf_prog_put(prog->aux->dst_prog);
+	if (prog->aux->dst_trampoline && tr != prog->aux->dst_trampoline)
+		/* we allocated a new trampoline, so free the old one */
+		bpf_trampoline_put(prog->aux->dst_trampoline);
+
 	prog->aux->dst_prog = NULL;
 	prog->aux->dst_trampoline = NULL;
 	mutex_unlock(&prog->aux->dst_mutex);
 
 	return bpf_link_settle(&link_primer);
 out_unlock:
+	if (tr && tr != prog->aux->dst_trampoline)
+		bpf_trampoline_put(tr);
 	mutex_unlock(&prog->aux->dst_mutex);
 	kfree(link);
 out_put_prog:
+	if (tgt_prog_fd && tgt_prog)
+		bpf_prog_put(tgt_prog);
 	bpf_prog_put(prog);
 	return err;
 }
@@ -2742,7 +2830,7 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
 			tp_name = prog->aux->attach_func_name;
 			break;
 		}
-		return bpf_tracing_prog_attach(prog);
+		return bpf_tracing_prog_attach(prog, 0, 0);
 	case BPF_PROG_TYPE_RAW_TRACEPOINT:
 	case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
 		if (strncpy_from_user(buf,
@@ -3926,10 +4014,15 @@ err_put:
 
 static int tracing_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 {
-	if (attr->link_create.attach_type == BPF_TRACE_ITER &&
-	    prog->expected_attach_type == BPF_TRACE_ITER)
-		return bpf_iter_link_attach(attr, prog);
+	if (attr->link_create.attach_type != prog->expected_attach_type)
+		return -EINVAL;
 
+	if (prog->expected_attach_type == BPF_TRACE_ITER)
+		return bpf_iter_link_attach(attr, prog);
+	else if (prog->type == BPF_PROG_TYPE_EXT)
+		return bpf_tracing_prog_attach(prog,
+					       attr->link_create.target_fd,
+					       attr->link_create.target_btf_id);
 	return -EINVAL;
 }
 
@@ -3943,18 +4036,25 @@ static int link_create(union bpf_attr *attr)
 	if (CHECK_ATTR(BPF_LINK_CREATE))
 		return -EINVAL;
 
-	ptype = attach_type_to_prog_type(attr->link_create.attach_type);
-	if (ptype == BPF_PROG_TYPE_UNSPEC)
-		return -EINVAL;
-
-	prog = bpf_prog_get_type(attr->link_create.prog_fd, ptype);
+	prog = bpf_prog_get(attr->link_create.prog_fd);
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
 
 	ret = bpf_prog_attach_check_attach_type(prog,
 						attr->link_create.attach_type);
 	if (ret)
-		goto err_out;
+		goto out;
+
+	if (prog->type == BPF_PROG_TYPE_EXT) {
+		ret = tracing_bpf_link_attach(attr, prog);
+		goto out;
+	}
+
+	ptype = attach_type_to_prog_type(attr->link_create.attach_type);
+	if (ptype == BPF_PROG_TYPE_UNSPEC || ptype != prog->type) {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	switch (ptype) {
 	case BPF_PROG_TYPE_CGROUP_SKB:
@@ -3982,7 +4082,7 @@ static int link_create(union bpf_attr *attr)
 		ret = -EINVAL;
 	}
 
-err_out:
+out:
 	if (ret < 0)
 		bpf_prog_put(prog);
 	return ret;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index a97a2f2964e3..015a1c074b6b 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -11404,6 +11404,11 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
 		if (!btf_type_is_func_proto(t))
 			return -EINVAL;
 
+		if ((prog->aux->saved_dst_prog_type || prog->aux->saved_dst_attach_type) &&
+		    (!tgt_prog || prog->aux->saved_dst_prog_type != tgt_prog->type ||
+		     prog->aux->saved_dst_attach_type != tgt_prog->expected_attach_type))
+			return -EINVAL;
+
 		if (tgt_prog && conservative)
 			t = NULL;
 
@@ -11512,6 +11517,11 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 	prog->aux->attach_func_proto = tgt_info.tgt_type;
 	prog->aux->attach_func_name = tgt_info.tgt_name;
 
+	if (tgt_prog) {
+		prog->aux->saved_dst_prog_type = tgt_prog->type;
+		prog->aux->saved_dst_attach_type = tgt_prog->expected_attach_type;
+	}
+
 	if (prog->expected_attach_type == BPF_TRACE_RAW_TP) {
 		prog->aux->attach_btf_trace = true;
 		return 0;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 96ddb00b91dc..2b1d3f16cbd1 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -639,8 +639,13 @@ union bpf_attr {
 		};
 		__u32		attach_type;	/* attach type */
 		__u32		flags;		/* extra flags */
-		__aligned_u64	iter_info;	/* extra bpf_iter_link_info */
-		__u32		iter_info_len;	/* iter_info length */
+		union {
+			__u32		target_btf_id;	/* btf_id of target to attach to */
+			struct {
+				__aligned_u64	iter_info;	/* extra bpf_iter_link_info */
+				__u32		iter_info_len;	/* iter_info length */
+			};
+		};
 	} link_create;
 
 	struct { /* struct used by BPF_LINK_UPDATE command */
-- 
cgit v1.2.3


From c11171a413385c1a72291cdb4a7435cb189762ab Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Tue, 29 Sep 2020 22:25:12 +0200
Subject: net: Add netif_rx_any_context()

Quite some drivers make conditional decisions based on in_interrupt() to
invoke either netif_rx() or netif_rx_ni().

Conditionals based on in_interrupt() or other variants of preempt count
checks in drivers should not exist for various reasons and Linus clearly
requested to either split the code pathes or pass an argument to the
common functions which provides the context.

This is obviously the correct solution, but for some of the affected
drivers this needs a major rewrite due to their convoluted structure.

As in_interrupt() usage in drivers needs to be phased out, provide
netif_rx_any_context() as a stop gap for these drivers.

This confines the in_interrupt() conditional to core code which in turn
allows to remove the access to this check for driver code and provides one
central place to do further modifications once the driver maze is cleaned
up.

Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  1 +
 net/core/dev.c            | 15 +++++++++++++++
 2 files changed, 16 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index a431c3229cbf..28cfa53daf72 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3785,6 +3785,7 @@ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog);
 int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb);
 int netif_rx(struct sk_buff *skb);
 int netif_rx_ni(struct sk_buff *skb);
+int netif_rx_any_context(struct sk_buff *skb);
 int netif_receive_skb(struct sk_buff *skb);
 int netif_receive_skb_core(struct sk_buff *skb);
 void netif_receive_skb_list(struct list_head *head);
diff --git a/net/core/dev.c b/net/core/dev.c
index 873b50ac9668..9d55bf5d1a65 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4841,6 +4841,21 @@ int netif_rx_ni(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(netif_rx_ni);
 
+int netif_rx_any_context(struct sk_buff *skb)
+{
+	/*
+	 * If invoked from contexts which do not invoke bottom half
+	 * processing either at return from interrupt or when softrqs are
+	 * reenabled, use netif_rx_ni() which invokes bottomhalf processing
+	 * directly.
+	 */
+	if (in_interrupt())
+		return netif_rx(skb);
+	else
+		return netif_rx_ni(skb);
+}
+EXPORT_SYMBOL(netif_rx_any_context);
+
 static __latent_entropy void net_tx_action(struct softirq_action *h)
 {
 	struct softnet_data *sd = this_cpu_ptr(&softnet_data);
-- 
cgit v1.2.3


From c9ca43d42ed8d5fd635d327a664ed1d8579eb2af Mon Sep 17 00:00:00 2001
From: Paras Sharma <parashar@codeaurora.org>
Date: Wed, 30 Sep 2020 11:35:26 +0530
Subject: serial: qcom_geni_serial: To correct QUP Version detection logic

For QUP IP versions 2.5 and above the oversampling rate is
halved from 32 to 16.

Commit ce734600545f ("tty: serial: qcom_geni_serial: Update
the oversampling rate") is pushed to handle this scenario.
But the existing logic is failing to classify QUP Version 3.0
into the correct group ( 2.5 and above).

As result Serial Engine clocks are not configured properly for
baud rate and garbage data is sampled to FIFOs from the line.

So, fix the logic to detect QUP with versions 2.5 and above.

Fixes: ce734600545f ("tty: serial: qcom_geni_serial: Update the oversampling rate")
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Paras Sharma <parashar@codeaurora.org>
Reviewed-by: Akash Asthana <akashast@codeaurora.org>
Link: https://lore.kernel.org/r/1601445926-23673-1-git-send-email-parashar@codeaurora.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/qcom_geni_serial.c | 2 +-
 include/linux/qcom-geni-se.h          | 3 +++
 2 files changed, 4 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c
index 8da2eb2d1090..291649f02821 100644
--- a/drivers/tty/serial/qcom_geni_serial.c
+++ b/drivers/tty/serial/qcom_geni_serial.c
@@ -1000,7 +1000,7 @@ static void qcom_geni_serial_set_termios(struct uart_port *uport,
 	sampling_rate = UART_OVERSAMPLING;
 	/* Sampling rate is halved for IP versions >= 2.5 */
 	ver = geni_se_get_qup_hw_version(&port->se);
-	if (GENI_SE_VERSION_MAJOR(ver) >= 2 && GENI_SE_VERSION_MINOR(ver) >= 5)
+	if (ver >= QUP_SE_VERSION_2_5)
 		sampling_rate /= 2;
 
 	clk_rate = get_clk_div_rate(baud, sampling_rate, &clk_div);
diff --git a/include/linux/qcom-geni-se.h b/include/linux/qcom-geni-se.h
index 8f385fbe5a0e..1c31f26ccc7a 100644
--- a/include/linux/qcom-geni-se.h
+++ b/include/linux/qcom-geni-se.h
@@ -248,6 +248,9 @@ struct geni_se {
 #define GENI_SE_VERSION_MINOR(ver) ((ver & HW_VER_MINOR_MASK) >> HW_VER_MINOR_SHFT)
 #define GENI_SE_VERSION_STEP(ver) (ver & HW_VER_STEP_MASK)
 
+/* QUP SE VERSION value for major number 2 and minor number 5 */
+#define QUP_SE_VERSION_2_5                  0x20050000
+
 /*
  * Define bandwidth thresholds that cause the underlying Core 2X interconnect
  * clock to run at the named frequency. These baseline values are recommended
-- 
cgit v1.2.3


From 714fb2fbe7379d0a413be217194f7af9814f2079 Mon Sep 17 00:00:00 2001
From: Vignesh Raghavendra <vigneshr@ti.com>
Date: Thu, 24 Sep 2020 13:42:11 +0530
Subject: mtd: hyperbus: Provide per device private pointer

Provide per device private pointer that can be used by controller
drivers to store device specific private data.

Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com>
Link: https://lore.kernel.org/r/20200924081214.16934-2-vigneshr@ti.com
---
 include/linux/mtd/hyperbus.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/mtd/hyperbus.h b/include/linux/mtd/hyperbus.h
index 2129f7d3b6eb..d8cb1aec826d 100644
--- a/include/linux/mtd/hyperbus.h
+++ b/include/linux/mtd/hyperbus.h
@@ -20,6 +20,7 @@ enum hyperbus_memtype {
  * @mtd: pointer to MTD struct
  * @ctlr: pointer to HyperBus controller struct
  * @memtype: type of memory device: HyperFlash or HyperRAM
+ * @priv: pointer to controller specific per device private data
  */
 
 struct hyperbus_device {
@@ -28,6 +29,7 @@ struct hyperbus_device {
 	struct mtd_info *mtd;
 	struct hyperbus_ctlr *ctlr;
 	enum hyperbus_memtype memtype;
+	void *priv;
 };
 
 /**
-- 
cgit v1.2.3


From 0fd16012adc0a994a7ce980a78e22e4de6220778 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Tue, 29 Sep 2020 12:09:55 +0200
Subject: lib: string_helpers: provide kfree_strarray()

There's a common pattern of dynamically allocating an array of char
pointers and then also dynamically allocating each string in this
array. Provide a helper for freeing such a string array with one call.

Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 include/linux/string_helpers.h |  2 ++
 lib/string_helpers.c           | 23 +++++++++++++++++++++++
 2 files changed, 25 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h
index 86f150c2a6b6..fa06dcdc481e 100644
--- a/include/linux/string_helpers.h
+++ b/include/linux/string_helpers.h
@@ -94,4 +94,6 @@ char *kstrdup_quotable(const char *src, gfp_t gfp);
 char *kstrdup_quotable_cmdline(struct task_struct *task, gfp_t gfp);
 char *kstrdup_quotable_file(struct file *file, gfp_t gfp);
 
+void kfree_strarray(char **array, size_t n);
+
 #endif
diff --git a/lib/string_helpers.c b/lib/string_helpers.c
index 963050c0283e..7f2d5fbaf243 100644
--- a/lib/string_helpers.c
+++ b/lib/string_helpers.c
@@ -649,3 +649,26 @@ char *kstrdup_quotable_file(struct file *file, gfp_t gfp)
 	return pathname;
 }
 EXPORT_SYMBOL_GPL(kstrdup_quotable_file);
+
+/**
+ * kfree_strarray - free a number of dynamically allocated strings contained
+ *                  in an array and the array itself
+ *
+ * @array: Dynamically allocated array of strings to free.
+ * @n: Number of strings (starting from the beginning of the array) to free.
+ *
+ * Passing a non-NULL @array and @n == 0 as well as NULL @array are valid
+ * use-cases. If @array is NULL, the function does nothing.
+ */
+void kfree_strarray(char **array, size_t n)
+{
+	unsigned int i;
+
+	if (!array)
+		return;
+
+	for (i = 0; i < n; i++)
+		kfree(array[i]);
+	kfree(array);
+}
+EXPORT_SYMBOL_GPL(kfree_strarray);
-- 
cgit v1.2.3


From 1e3b37aab958861a9d0c01ff6dbec96a82743701 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Thu, 27 Aug 2020 10:52:05 +0200
Subject: mtd: rawnand: Use the ECC framework OOB layouts

No need to have our own in the raw NAND core.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-18-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/raw/arasan-nand-controller.c   |   2 +-
 drivers/mtd/nand/raw/atmel/nand-controller.c    |   2 +-
 drivers/mtd/nand/raw/davinci_nand.c             |   3 +-
 drivers/mtd/nand/raw/ingenic/ingenic_nand_drv.c |   6 +-
 drivers/mtd/nand/raw/nand_base.c                | 174 ++----------------------
 drivers/mtd/nand/raw/nand_bch.c                 |   1 +
 drivers/mtd/nand/raw/nand_toshiba.c             |   2 +-
 drivers/mtd/nand/raw/vf610_nfc.c                |   2 +-
 include/linux/mtd/rawnand.h                     |   4 +-
 9 files changed, 20 insertions(+), 176 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/raw/arasan-nand-controller.c b/drivers/mtd/nand/raw/arasan-nand-controller.c
index 006bc3d3ce20..fbb4ea751be8 100644
--- a/drivers/mtd/nand/raw/arasan-nand-controller.c
+++ b/drivers/mtd/nand/raw/arasan-nand-controller.c
@@ -980,7 +980,7 @@ static int anfc_init_hw_ecc_controller(struct arasan_nfc *nfc,
 		return -EINVAL;
 	}
 
-	mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
+	mtd_set_ooblayout(mtd, nand_get_large_page_ooblayout());
 
 	ecc->steps = mtd->writesize / ecc->size;
 	ecc->algo = NAND_ECC_ALGO_BCH;
diff --git a/drivers/mtd/nand/raw/atmel/nand-controller.c b/drivers/mtd/nand/raw/atmel/nand-controller.c
index 3d162fdc9ce2..7fcc5e67163e 100644
--- a/drivers/mtd/nand/raw/atmel/nand-controller.c
+++ b/drivers/mtd/nand/raw/atmel/nand-controller.c
@@ -1108,7 +1108,7 @@ static int atmel_nand_pmecc_init(struct nand_chip *chip)
 
 	chip->options |= NAND_NO_SUBPAGE_WRITE;
 
-	mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
+	mtd_set_ooblayout(mtd, nand_get_large_page_ooblayout());
 
 	return 0;
 }
diff --git a/drivers/mtd/nand/raw/davinci_nand.c b/drivers/mtd/nand/raw/davinci_nand.c
index 58966a9706b1..427f320fb79b 100644
--- a/drivers/mtd/nand/raw/davinci_nand.c
+++ b/drivers/mtd/nand/raw/davinci_nand.c
@@ -645,7 +645,8 @@ static int davinci_nand_attach_chip(struct nand_chip *chip)
 				mtd_set_ooblayout(mtd,
 						  &hwecc4_small_ooblayout_ops);
 			} else if (chunks == 4 || chunks == 8) {
-				mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
+				mtd_set_ooblayout(mtd,
+						  nand_get_large_page_ooblayout());
 				info->chip.ecc.read_page = nand_davinci_read_page_hwecc_oob_first;
 			} else {
 				return -EIO;
diff --git a/drivers/mtd/nand/raw/ingenic/ingenic_nand_drv.c b/drivers/mtd/nand/raw/ingenic/ingenic_nand_drv.c
index 70309f18124c..0e9d426fe4f2 100644
--- a/drivers/mtd/nand/raw/ingenic/ingenic_nand_drv.c
+++ b/drivers/mtd/nand/raw/ingenic/ingenic_nand_drv.c
@@ -243,8 +243,10 @@ static int ingenic_nand_attach_chip(struct nand_chip *chip)
 	/* For legacy reasons we use a different layout on the qi,lb60 board. */
 	if (of_machine_is_compatible("qi,lb60"))
 		mtd_set_ooblayout(mtd, &qi_lb60_ooblayout_ops);
-	else
+	else if (nfc->soc_info->oob_layout)
 		mtd_set_ooblayout(mtd, nfc->soc_info->oob_layout);
+	else
+		mtd_set_ooblayout(mtd, nand_get_large_page_ooblayout());
 
 	return 0;
 }
@@ -532,7 +534,6 @@ static const struct jz_soc_info jz4740_soc_info = {
 	.data_offset = 0x00000000,
 	.cmd_offset = 0x00008000,
 	.addr_offset = 0x00010000,
-	.oob_layout = &nand_ooblayout_lp_ops,
 };
 
 static const struct jz_soc_info jz4725b_soc_info = {
@@ -546,7 +547,6 @@ static const struct jz_soc_info jz4780_soc_info = {
 	.data_offset = 0x00000000,
 	.cmd_offset = 0x00400000,
 	.addr_offset = 0x00800000,
-	.oob_layout = &nand_ooblayout_lp_ops,
 };
 
 static const struct of_device_id ingenic_nand_dt_match[] = {
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 2c102aeecdc1..4b41de520d0d 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -46,166 +46,6 @@
 
 #include "internals.h"
 
-/* Define default oob placement schemes for large and small page devices */
-static int nand_ooblayout_ecc_sp(struct mtd_info *mtd, int section,
-				 struct mtd_oob_region *oobregion)
-{
-	struct nand_chip *chip = mtd_to_nand(mtd);
-	struct nand_ecc_ctrl *ecc = &chip->ecc;
-
-	if (section > 1)
-		return -ERANGE;
-
-	if (!section) {
-		oobregion->offset = 0;
-		if (mtd->oobsize == 16)
-			oobregion->length = 4;
-		else
-			oobregion->length = 3;
-	} else {
-		if (mtd->oobsize == 8)
-			return -ERANGE;
-
-		oobregion->offset = 6;
-		oobregion->length = ecc->total - 4;
-	}
-
-	return 0;
-}
-
-static int nand_ooblayout_free_sp(struct mtd_info *mtd, int section,
-				  struct mtd_oob_region *oobregion)
-{
-	if (section > 1)
-		return -ERANGE;
-
-	if (mtd->oobsize == 16) {
-		if (section)
-			return -ERANGE;
-
-		oobregion->length = 8;
-		oobregion->offset = 8;
-	} else {
-		oobregion->length = 2;
-		if (!section)
-			oobregion->offset = 3;
-		else
-			oobregion->offset = 6;
-	}
-
-	return 0;
-}
-
-const struct mtd_ooblayout_ops nand_ooblayout_sp_ops = {
-	.ecc = nand_ooblayout_ecc_sp,
-	.free = nand_ooblayout_free_sp,
-};
-EXPORT_SYMBOL_GPL(nand_ooblayout_sp_ops);
-
-static int nand_ooblayout_ecc_lp(struct mtd_info *mtd, int section,
-				 struct mtd_oob_region *oobregion)
-{
-	struct nand_chip *chip = mtd_to_nand(mtd);
-	struct nand_ecc_ctrl *ecc = &chip->ecc;
-
-	if (section || !ecc->total)
-		return -ERANGE;
-
-	oobregion->length = ecc->total;
-	oobregion->offset = mtd->oobsize - oobregion->length;
-
-	return 0;
-}
-
-static int nand_ooblayout_free_lp(struct mtd_info *mtd, int section,
-				  struct mtd_oob_region *oobregion)
-{
-	struct nand_chip *chip = mtd_to_nand(mtd);
-	struct nand_ecc_ctrl *ecc = &chip->ecc;
-
-	if (section)
-		return -ERANGE;
-
-	oobregion->length = mtd->oobsize - ecc->total - 2;
-	oobregion->offset = 2;
-
-	return 0;
-}
-
-const struct mtd_ooblayout_ops nand_ooblayout_lp_ops = {
-	.ecc = nand_ooblayout_ecc_lp,
-	.free = nand_ooblayout_free_lp,
-};
-EXPORT_SYMBOL_GPL(nand_ooblayout_lp_ops);
-
-/*
- * Support the old "large page" layout used for 1-bit Hamming ECC where ECC
- * are placed at a fixed offset.
- */
-static int nand_ooblayout_ecc_lp_hamming(struct mtd_info *mtd, int section,
-					 struct mtd_oob_region *oobregion)
-{
-	struct nand_chip *chip = mtd_to_nand(mtd);
-	struct nand_ecc_ctrl *ecc = &chip->ecc;
-
-	if (section)
-		return -ERANGE;
-
-	switch (mtd->oobsize) {
-	case 64:
-		oobregion->offset = 40;
-		break;
-	case 128:
-		oobregion->offset = 80;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	oobregion->length = ecc->total;
-	if (oobregion->offset + oobregion->length > mtd->oobsize)
-		return -ERANGE;
-
-	return 0;
-}
-
-static int nand_ooblayout_free_lp_hamming(struct mtd_info *mtd, int section,
-					  struct mtd_oob_region *oobregion)
-{
-	struct nand_chip *chip = mtd_to_nand(mtd);
-	struct nand_ecc_ctrl *ecc = &chip->ecc;
-	int ecc_offset = 0;
-
-	if (section < 0 || section > 1)
-		return -ERANGE;
-
-	switch (mtd->oobsize) {
-	case 64:
-		ecc_offset = 40;
-		break;
-	case 128:
-		ecc_offset = 80;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	if (section == 0) {
-		oobregion->offset = 2;
-		oobregion->length = ecc_offset - 2;
-	} else {
-		oobregion->offset = ecc_offset + ecc->total;
-		oobregion->length = mtd->oobsize - oobregion->offset;
-	}
-
-	return 0;
-}
-
-static const struct mtd_ooblayout_ops nand_ooblayout_lp_hamming_ops = {
-	.ecc = nand_ooblayout_ecc_lp_hamming,
-	.free = nand_ooblayout_free_lp_hamming,
-};
-
 static int nand_pairing_dist3_get_info(struct mtd_info *mtd, int page,
 				       struct mtd_pairing_info *info)
 {
@@ -5372,7 +5212,7 @@ static int nand_set_ecc_soft_ops(struct nand_chip *chip)
 				return -EINVAL;
 			}
 
-			mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
+			mtd_set_ooblayout(mtd, nand_get_large_page_ooblayout());
 
 		}
 
@@ -5381,7 +5221,7 @@ static int nand_set_ecc_soft_ops(struct nand_chip *chip)
 		 * used, otherwise we don't know how many bytes can really be
 		 * used.
 		 */
-		if (mtd->ooblayout == &nand_ooblayout_lp_ops &&
+		if (mtd->ooblayout == nand_get_large_page_ooblayout() &&
 		    ecc->options & NAND_ECC_MAXIMIZE) {
 			int steps, bytes;
 
@@ -5783,11 +5623,12 @@ static int nand_scan_tail(struct nand_chip *chip)
 		switch (mtd->oobsize) {
 		case 8:
 		case 16:
-			mtd_set_ooblayout(mtd, &nand_ooblayout_sp_ops);
+			mtd_set_ooblayout(mtd, nand_get_small_page_ooblayout());
 			break;
 		case 64:
 		case 128:
-			mtd_set_ooblayout(mtd, &nand_ooblayout_lp_hamming_ops);
+			mtd_set_ooblayout(mtd,
+					  nand_get_large_page_hamming_ooblayout());
 			break;
 		default:
 			/*
@@ -5799,7 +5640,7 @@ static int nand_scan_tail(struct nand_chip *chip)
 			 */
 			if (ecc->engine_type == NAND_ECC_ENGINE_TYPE_NONE) {
 				mtd_set_ooblayout(mtd,
-						&nand_ooblayout_lp_ops);
+						  nand_get_large_page_ooblayout());
 				break;
 			}
 
@@ -5954,7 +5795,10 @@ static int nand_scan_tail(struct nand_chip *chip)
 		ret = -EINVAL;
 		goto err_nand_manuf_cleanup;
 	}
+
 	ecc->total = ecc->steps * ecc->bytes;
+	chip->base.ecc.ctx.total = ecc->total;
+
 	if (ecc->total > mtd->oobsize) {
 		WARN(1, "Total number of ECC bytes exceeded oobsize\n");
 		ret = -EINVAL;
diff --git a/drivers/mtd/nand/raw/nand_bch.c b/drivers/mtd/nand/raw/nand_bch.c
index d5af8c5fd02f..9d19ac14c196 100644
--- a/drivers/mtd/nand/raw/nand_bch.c
+++ b/drivers/mtd/nand/raw/nand_bch.c
@@ -165,6 +165,7 @@ struct nand_bch_control *nand_bch_init(struct mtd_info *mtd)
 	 */
 	nand->ecc.steps = eccsteps;
 	nand->ecc.total = eccsteps * eccbytes;
+	nand->base.ecc.ctx.total = nand->ecc.total;
 	if (mtd_ooblayout_count_eccbytes(mtd) != (eccsteps*eccbytes)) {
 		pr_warn("invalid ecc layout\n");
 		goto fail;
diff --git a/drivers/mtd/nand/raw/nand_toshiba.c b/drivers/mtd/nand/raw/nand_toshiba.c
index fb6662337b90..cf4f37959421 100644
--- a/drivers/mtd/nand/raw/nand_toshiba.c
+++ b/drivers/mtd/nand/raw/nand_toshiba.c
@@ -140,7 +140,7 @@ static void toshiba_nand_benand_init(struct nand_chip *chip)
 
 	chip->options |= NAND_SUBPAGE_READ;
 
-	mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
+	mtd_set_ooblayout(mtd, nand_get_large_page_ooblayout());
 }
 
 static void toshiba_nand_decode_id(struct nand_chip *chip)
diff --git a/drivers/mtd/nand/raw/vf610_nfc.c b/drivers/mtd/nand/raw/vf610_nfc.c
index 8ee2c1f539c4..50dc0c93140c 100644
--- a/drivers/mtd/nand/raw/vf610_nfc.c
+++ b/drivers/mtd/nand/raw/vf610_nfc.c
@@ -779,7 +779,7 @@ static int vf610_nfc_attach_chip(struct nand_chip *chip)
 		mtd->oobsize = 64;
 
 	/* Use default large page ECC layout defined in NAND core */
-	mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
+	mtd_set_ooblayout(mtd, nand_get_large_page_ooblayout());
 	if (chip->ecc.strength == 32) {
 		nfc->ecc_mode = ECC_60_BYTE;
 		chip->ecc.bytes = 60;
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 967b616c50df..1bbce6fa1b08 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -14,6 +14,7 @@
 #define __LINUX_MTD_RAWNAND_H
 
 #include <linux/mtd/mtd.h>
+#include <linux/mtd/nand.h>
 #include <linux/mtd/flashchip.h>
 #include <linux/mtd/bbm.h>
 #include <linux/mtd/jedec.h>
@@ -1156,9 +1157,6 @@ struct nand_chip {
 	void *priv;
 };
 
-extern const struct mtd_ooblayout_ops nand_ooblayout_sp_ops;
-extern const struct mtd_ooblayout_ops nand_ooblayout_lp_ops;
-
 static inline struct nand_chip *mtd_to_nand(struct mtd_info *mtd)
 {
 	return container_of(mtd, struct nand_chip, base.mtd);
-- 
cgit v1.2.3


From d7157ff49a5b5845b37b8f2bf31607f0af295ef1 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Thu, 27 Aug 2020 10:52:07 +0200
Subject: mtd: rawnand: Use the ECC framework user input parsing bits

Many helpers are generic to all NAND chips, they should not be
raw-NAND specific, so use the generic ones.

To avoid moving all the raw NAND core "history" into the generic NAND
layer, we keep a part of this parsing in the raw NAND core to ensure
backward compatibility.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-20-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/raw/nand_base.c | 142 +++++++++++++++++++--------------------
 include/linux/mtd/rawnand.h      |  12 ----
 2 files changed, 70 insertions(+), 84 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 9897274a82e4..8bb3e4ee4bfb 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -4877,18 +4877,27 @@ free_detect_allocation:
 	return ret;
 }
 
-static const char * const nand_ecc_modes[] = {
-	[NAND_ECC_NONE]		= "none",
-	[NAND_ECC_SOFT]		= "soft",
-	[NAND_ECC_HW]		= "hw",
-	[NAND_ECC_HW_SYNDROME]	= "hw_syndrome",
-	[NAND_ECC_ON_DIE]	= "on-die",
-};
-
 static enum nand_ecc_engine_type
-of_get_nand_ecc_engine_type(struct device_node *np)
-{
-	enum nand_ecc_mode eng_type;
+of_get_rawnand_ecc_engine_type_legacy(struct device_node *np)
+{
+	enum nand_ecc_legacy_mode {
+		NAND_ECC_INVALID,
+		NAND_ECC_NONE,
+		NAND_ECC_SOFT,
+		NAND_ECC_SOFT_BCH,
+		NAND_ECC_HW,
+		NAND_ECC_HW_SYNDROME,
+		NAND_ECC_ON_DIE,
+	};
+	const char * const nand_ecc_legacy_modes[] = {
+		[NAND_ECC_NONE]		= "none",
+		[NAND_ECC_SOFT]		= "soft",
+		[NAND_ECC_SOFT_BCH]	= "soft_bch",
+		[NAND_ECC_HW]		= "hw",
+		[NAND_ECC_HW_SYNDROME]	= "hw_syndrome",
+		[NAND_ECC_ON_DIE]	= "on-die",
+	};
+	enum nand_ecc_legacy_mode eng_type;
 	const char *pm;
 	int err;
 
@@ -4897,12 +4906,13 @@ of_get_nand_ecc_engine_type(struct device_node *np)
 		return NAND_ECC_ENGINE_TYPE_INVALID;
 
 	for (eng_type = NAND_ECC_NONE;
-	     eng_type < ARRAY_SIZE(nand_ecc_modes); eng_type++) {
-		if (!strcasecmp(pm, nand_ecc_modes[eng_type])) {
+	     eng_type < ARRAY_SIZE(nand_ecc_legacy_modes); eng_type++) {
+		if (!strcasecmp(pm, nand_ecc_legacy_modes[eng_type])) {
 			switch (eng_type) {
 			case NAND_ECC_NONE:
 				return NAND_ECC_ENGINE_TYPE_NONE;
 			case NAND_ECC_SOFT:
+			case NAND_ECC_SOFT_BCH:
 				return NAND_ECC_ENGINE_TYPE_SOFT;
 			case NAND_ECC_HW:
 			case NAND_ECC_HW_SYNDROME:
@@ -4915,43 +4925,29 @@ of_get_nand_ecc_engine_type(struct device_node *np)
 		}
 	}
 
-	/*
-	 * For backward compatibility we support few obsoleted values that don't
-	 * have their mappings into the nand_ecc_engine_providers enum anymore
-	 * (they were merged with other enums).
-	 */
-	if (!strcasecmp(pm, "soft_bch"))
-		return NAND_ECC_ENGINE_TYPE_SOFT;
-
 	return NAND_ECC_ENGINE_TYPE_INVALID;
 }
 
-static const char * const nand_ecc_algos[] = {
-	[NAND_ECC_ALGO_HAMMING]	= "hamming",
-	[NAND_ECC_ALGO_BCH]	= "bch",
-	[NAND_ECC_ALGO_RS]	= "rs",
-};
-
-static enum nand_ecc_algo of_get_nand_ecc_algo(struct device_node *np)
+static enum nand_ecc_placement
+of_get_rawnand_ecc_placement_legacy(struct device_node *np)
 {
-	enum nand_ecc_algo ecc_algo;
 	const char *pm;
 	int err;
 
-	err = of_property_read_string(np, "nand-ecc-algo", &pm);
+	err = of_property_read_string(np, "nand-ecc-mode", &pm);
 	if (!err) {
-		for (ecc_algo = NAND_ECC_ALGO_HAMMING;
-		     ecc_algo < ARRAY_SIZE(nand_ecc_algos);
-		     ecc_algo++) {
-			if (!strcasecmp(pm, nand_ecc_algos[ecc_algo]))
-				return ecc_algo;
-		}
+		if (!strcasecmp(pm, "hw_syndrome"))
+			return NAND_ECC_PLACEMENT_INTERLEAVED;
 	}
 
-	/*
-	 * For backward compatibility we also read "nand-ecc-mode" checking
-	 * for some obsoleted values that were specifying ECC algorithm.
-	 */
+	return NAND_ECC_PLACEMENT_UNKNOWN;
+}
+
+static enum nand_ecc_algo of_get_rawnand_ecc_algo_legacy(struct device_node *np)
+{
+	const char *pm;
+	int err;
+
 	err = of_property_read_string(np, "nand-ecc-mode", &pm);
 	if (!err) {
 		if (!strcasecmp(pm, "soft"))
@@ -4963,22 +4959,19 @@ static enum nand_ecc_algo of_get_nand_ecc_algo(struct device_node *np)
 	return NAND_ECC_ALGO_UNKNOWN;
 }
 
-static int of_get_nand_ecc_step_size(struct device_node *np)
+static void of_get_nand_ecc_legacy_user_config(struct nand_chip *chip)
 {
-	int ret;
-	u32 val;
+	struct device_node *dn = nand_get_flash_node(chip);
+	struct nand_ecc_props *user_conf = &chip->base.ecc.user_conf;
 
-	ret = of_property_read_u32(np, "nand-ecc-step-size", &val);
-	return ret ? ret : val;
-}
+	if (user_conf->engine_type == NAND_ECC_ENGINE_TYPE_INVALID)
+		user_conf->engine_type = of_get_rawnand_ecc_engine_type_legacy(dn);
 
-static int of_get_nand_ecc_strength(struct device_node *np)
-{
-	int ret;
-	u32 val;
+	if (user_conf->algo == NAND_ECC_ALGO_UNKNOWN)
+		user_conf->algo = of_get_rawnand_ecc_algo_legacy(dn);
 
-	ret = of_property_read_u32(np, "nand-ecc-strength", &val);
-	return ret ? ret : val;
+	if (user_conf->placement == NAND_ECC_PLACEMENT_UNKNOWN)
+		user_conf->placement = of_get_rawnand_ecc_placement_legacy(dn);
 }
 
 static int of_get_nand_bus_width(struct device_node *np)
@@ -5002,12 +4995,10 @@ static bool of_get_nand_on_flash_bbt(struct device_node *np)
 	return of_property_read_bool(np, "nand-on-flash-bbt");
 }
 
-static int nand_dt_init(struct nand_chip *chip)
+static int rawnand_dt_init(struct nand_chip *chip)
 {
+	struct nand_device *nand = mtd_to_nanddev(nand_to_mtd(chip));
 	struct device_node *dn = nand_get_flash_node(chip);
-	enum nand_ecc_engine_type ecc_type;
-	enum nand_ecc_algo ecc_algo;
-	int ecc_strength, ecc_step;
 
 	if (!dn)
 		return 0;
@@ -5021,25 +5012,32 @@ static int nand_dt_init(struct nand_chip *chip)
 	if (of_get_nand_on_flash_bbt(dn))
 		chip->bbt_options |= NAND_BBT_USE_FLASH;
 
-	ecc_type = of_get_nand_ecc_engine_type(dn);
-	ecc_algo = of_get_nand_ecc_algo(dn);
-	ecc_strength = of_get_nand_ecc_strength(dn);
-	ecc_step = of_get_nand_ecc_step_size(dn);
-
-	if (ecc_type != NAND_ECC_ENGINE_TYPE_INVALID)
-		chip->ecc.engine_type = ecc_type;
+	if (of_property_read_bool(dn, "nand-ecc-maximize"))
+		chip->ecc.options |= NAND_ECC_MAXIMIZE;
 
-	if (ecc_algo != NAND_ECC_ALGO_UNKNOWN)
-		chip->ecc.algo = ecc_algo;
+	of_get_nand_ecc_user_config(nand);
+	of_get_nand_ecc_legacy_user_config(chip);
 
-	if (ecc_strength >= 0)
-		chip->ecc.strength = ecc_strength;
+	/*
+	 * If neither the user nor the NAND controller have requested a specific
+	 * ECC engine type, we will default to NAND_ECC_ENGINE_TYPE_ON_HOST.
+	 */
+	nand->ecc.defaults.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 
-	if (ecc_step > 0)
-		chip->ecc.size = ecc_step;
+	/*
+	 * Use the user requested engine type, unless there is none, in this
+	 * case default to the NAND controller choice, otherwise fallback to
+	 * the raw NAND default one.
+	 */
+	if (nand->ecc.user_conf.engine_type != NAND_ECC_ENGINE_TYPE_INVALID)
+		chip->ecc.engine_type = nand->ecc.user_conf.engine_type;
+	if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_INVALID)
+		chip->ecc.engine_type = nand->ecc.defaults.engine_type;
 
-	if (of_property_read_bool(dn, "nand-ecc-maximize"))
-		chip->ecc.options |= NAND_ECC_MAXIMIZE;
+	chip->ecc.placement = nand->ecc.user_conf.placement;
+	chip->ecc.algo = nand->ecc.user_conf.algo;
+	chip->ecc.strength = nand->ecc.user_conf.strength;
+	chip->ecc.size = nand->ecc.user_conf.step_size;
 
 	return 0;
 }
@@ -5077,7 +5075,7 @@ static int nand_scan_ident(struct nand_chip *chip, unsigned int maxchips,
 	/* Enforce the right timings for reset/detection */
 	chip->current_interface_config = nand_get_reset_interface_config();
 
-	ret = nand_dt_init(chip);
+	ret = rawnand_dt_init(chip);
 	if (ret)
 		return ret;
 
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 1bbce6fa1b08..671e60948deb 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -81,18 +81,6 @@ struct nand_chip;
 
 #define NAND_DATA_IFACE_CHECK_ONLY	-1
 
-/*
- * Constants for ECC_MODES
- */
-enum nand_ecc_mode {
-	NAND_ECC_INVALID,
-	NAND_ECC_NONE,
-	NAND_ECC_SOFT,
-	NAND_ECC_HW,
-	NAND_ECC_HW_SYNDROME,
-	NAND_ECC_ON_DIE,
-};
-
 /*
  * Constants for Hardware ECC
  */
-- 
cgit v1.2.3


From b5156335ac37f186812090795ed27884a76c3266 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Thu, 27 Aug 2020 10:52:08 +0200
Subject: mtd: rawnand: Use the NAND framework user_conf object for ECC flags

Instead of storing the ECC flags in chip->ecc.options, use
nanddev->ecc.user_conf.flags.

There is currently only one to save: NAND_ECC_MAXIMIZE.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-21-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/raw/atmel/nand-controller.c |  3 ++-
 drivers/mtd/nand/raw/denali_pci.c            |  2 +-
 drivers/mtd/nand/raw/nand_base.c             | 14 +++++++-------
 drivers/mtd/nand/raw/sunxi_nand.c            |  3 ++-
 drivers/mtd/nand/raw/tegra_nand.c            |  5 +++--
 include/linux/mtd/rawnand.h                  |  1 -
 6 files changed, 15 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/raw/atmel/nand-controller.c b/drivers/mtd/nand/raw/atmel/nand-controller.c
index 7fcc5e67163e..c3902e0e0b90 100644
--- a/drivers/mtd/nand/raw/atmel/nand-controller.c
+++ b/drivers/mtd/nand/raw/atmel/nand-controller.c
@@ -1046,6 +1046,7 @@ static int atmel_nand_pmecc_init(struct nand_chip *chip)
 	const struct nand_ecc_props *requirements =
 		nanddev_get_ecc_requirements(&chip->base);
 	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct nand_device *nanddev = mtd_to_nanddev(mtd);
 	struct atmel_nand *nand = to_atmel_nand(chip);
 	struct atmel_nand_controller *nc;
 	struct atmel_pmecc_user_req req;
@@ -1070,7 +1071,7 @@ static int atmel_nand_pmecc_init(struct nand_chip *chip)
 			chip->ecc.size = val;
 	}
 
-	if (chip->ecc.options & NAND_ECC_MAXIMIZE)
+	if (nanddev->ecc.user_conf.flags & NAND_ECC_MAXIMIZE_STRENGTH)
 		req.ecc.strength = ATMEL_PMECC_MAXIMIZE_ECC_STRENGTH;
 	else if (chip->ecc.strength)
 		req.ecc.strength = chip->ecc.strength;
diff --git a/drivers/mtd/nand/raw/denali_pci.c b/drivers/mtd/nand/raw/denali_pci.c
index 2f77ee55e1bf..20c085a30adc 100644
--- a/drivers/mtd/nand/raw/denali_pci.c
+++ b/drivers/mtd/nand/raw/denali_pci.c
@@ -100,7 +100,7 @@ static int denali_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 		goto out_remove_denali;
 	}
 
-	dchip->chip.ecc.options |= NAND_ECC_MAXIMIZE;
+	dchip->chip.base.ecc.user_conf.flags |= NAND_ECC_MAXIMIZE_STRENGTH;
 
 	dchip->nsels = nsels;
 
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 8bb3e4ee4bfb..3af9223e5240 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -5012,9 +5012,6 @@ static int rawnand_dt_init(struct nand_chip *chip)
 	if (of_get_nand_on_flash_bbt(dn))
 		chip->bbt_options |= NAND_BBT_USE_FLASH;
 
-	if (of_property_read_bool(dn, "nand-ecc-maximize"))
-		chip->ecc.options |= NAND_ECC_MAXIMIZE;
-
 	of_get_nand_ecc_user_config(nand);
 	of_get_nand_ecc_legacy_user_config(chip);
 
@@ -5145,6 +5142,7 @@ static void nand_scan_ident_cleanup(struct nand_chip *chip)
 static int nand_set_ecc_soft_ops(struct nand_chip *chip)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct nand_device *nanddev = mtd_to_nanddev(mtd);
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
 
 	if (WARN_ON(ecc->engine_type != NAND_ECC_ENGINE_TYPE_SOFT))
@@ -5220,7 +5218,7 @@ static int nand_set_ecc_soft_ops(struct nand_chip *chip)
 		 * used.
 		 */
 		if (mtd->ooblayout == nand_get_large_page_ooblayout() &&
-		    ecc->options & NAND_ECC_MAXIMIZE) {
+		    nanddev->ecc.user_conf.flags & NAND_ECC_MAXIMIZE_STRENGTH) {
 			int steps, bytes;
 
 			/* Always prefer 1k blocks over 512bytes ones */
@@ -5460,11 +5458,12 @@ nand_maximize_ecc(struct nand_chip *chip,
  * @caps: ECC engine caps info structure
  * @oobavail: OOB size that the ECC engine can use
  *
- * Choose the ECC configuration according to following logic
+ * Choose the ECC configuration according to following logic.
  *
  * 1. If both ECC step size and ECC strength are already set (usually by DT)
  *    then check if it is supported by this controller.
- * 2. If NAND_ECC_MAXIMIZE is set, then select maximum ECC strength.
+ * 2. If the user provided the nand-ecc-maximize property, then select maximum
+ *    ECC strength.
  * 3. Otherwise, try to match the ECC step size and ECC strength closest
  *    to the chip's requirement. If available OOB size can't fit the chip
  *    requirement then fallback to the maximum ECC step size and ECC strength.
@@ -5475,6 +5474,7 @@ int nand_ecc_choose_conf(struct nand_chip *chip,
 			 const struct nand_ecc_caps *caps, int oobavail)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct nand_device *nanddev = mtd_to_nanddev(mtd);
 
 	if (WARN_ON(oobavail < 0 || oobavail > mtd->oobsize))
 		return -EINVAL;
@@ -5482,7 +5482,7 @@ int nand_ecc_choose_conf(struct nand_chip *chip,
 	if (chip->ecc.size && chip->ecc.strength)
 		return nand_check_ecc_caps(chip, caps, oobavail);
 
-	if (chip->ecc.options & NAND_ECC_MAXIMIZE)
+	if (nanddev->ecc.user_conf.flags & NAND_ECC_MAXIMIZE_STRENGTH)
 		return nand_maximize_ecc(chip, caps, oobavail);
 
 	if (!nand_match_ecc_req(chip, caps, oobavail))
diff --git a/drivers/mtd/nand/raw/sunxi_nand.c b/drivers/mtd/nand/raw/sunxi_nand.c
index b7b764ef4b1d..2a7ca3072f35 100644
--- a/drivers/mtd/nand/raw/sunxi_nand.c
+++ b/drivers/mtd/nand/raw/sunxi_nand.c
@@ -1609,12 +1609,13 @@ static int sunxi_nand_hw_ecc_ctrl_init(struct nand_chip *nand,
 	static const u8 strengths[] = { 16, 24, 28, 32, 40, 48, 56, 60, 64 };
 	struct sunxi_nfc *nfc = to_sunxi_nfc(nand->controller);
 	struct mtd_info *mtd = nand_to_mtd(nand);
+	struct nand_device *nanddev = mtd_to_nanddev(mtd);
 	struct sunxi_nand_hw_ecc *data;
 	int nsectors;
 	int ret;
 	int i;
 
-	if (ecc->options & NAND_ECC_MAXIMIZE) {
+	if (nanddev->ecc.user_conf.flags & NAND_ECC_MAXIMIZE_STRENGTH) {
 		int bytes;
 
 		ecc->size = 1024;
diff --git a/drivers/mtd/nand/raw/tegra_nand.c b/drivers/mtd/nand/raw/tegra_nand.c
index 100c18ef8fe8..fbf67722a049 100644
--- a/drivers/mtd/nand/raw/tegra_nand.c
+++ b/drivers/mtd/nand/raw/tegra_nand.c
@@ -840,9 +840,10 @@ static int tegra_nand_get_strength(struct nand_chip *chip, const int *strength,
 				   int strength_len, int bits_per_step,
 				   int oobsize)
 {
+	struct nand_device *base = mtd_to_nanddev(nand_to_mtd(chip));
 	const struct nand_ecc_props *requirements =
-		nanddev_get_ecc_requirements(&chip->base);
-	bool maximize = chip->ecc.options & NAND_ECC_MAXIMIZE;
+		nanddev_get_ecc_requirements(base);
+	bool maximize = base->ecc.user_conf.flags & NAND_ECC_MAXIMIZE_STRENGTH;
 	int i;
 
 	/*
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 671e60948deb..aac07940de09 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -98,7 +98,6 @@ struct nand_chip;
  * pages and you want to rely on the default implementation.
  */
 #define NAND_ECC_GENERIC_ERASED_CHECK	BIT(0)
-#define NAND_ECC_MAXIMIZE		BIT(1)
 
 /*
  * Option constants for bizarre disfunctionality and real
-- 
cgit v1.2.3


From 4b6ec08fd21ee3179cbfccf3605ad13d9f38b623 Mon Sep 17 00:00:00 2001
From: Luca Ceresoli <luca@lucaceresoli.net>
Date: Wed, 2 Sep 2020 16:22:59 +0200
Subject: mfd: lp87565: Add LP87524-Q1 variant

Add support for the LP87524B/J/P-Q1 Four 4-MHz Buck Converter. This is a
variant of the LP87565 having 4 single-phase outputs and up to 10 A of
total output current.

Signed-off-by: Luca Ceresoli <luca@lucaceresoli.net>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/lp87565.c       | 4 ++++
 include/linux/mfd/lp87565.h | 1 +
 2 files changed, 5 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/mfd/lp87565.c b/drivers/mfd/lp87565.c
index 2268be9113f1..9c21483d9653 100644
--- a/drivers/mfd/lp87565.c
+++ b/drivers/mfd/lp87565.c
@@ -26,6 +26,10 @@ static const struct mfd_cell lp87565_cells[] = {
 
 static const struct of_device_id of_lp87565_match_table[] = {
 	{ .compatible = "ti,lp87565", },
+	{
+		.compatible = "ti,lp87524-q1",
+		.data = (void *)LP87565_DEVICE_TYPE_LP87524_Q1,
+	},
 	{
 		.compatible = "ti,lp87565-q1",
 		.data = (void *)LP87565_DEVICE_TYPE_LP87565_Q1,
diff --git a/include/linux/mfd/lp87565.h b/include/linux/mfd/lp87565.h
index 43716aca46fa..d44ddfb6bb63 100644
--- a/include/linux/mfd/lp87565.h
+++ b/include/linux/mfd/lp87565.h
@@ -14,6 +14,7 @@
 
 enum lp87565_device_type {
 	LP87565_DEVICE_TYPE_UNKNOWN	= 0,
+	LP87565_DEVICE_TYPE_LP87524_Q1,
 	LP87565_DEVICE_TYPE_LP87561_Q1,
 	LP87565_DEVICE_TYPE_LP87565_Q1,
 };
-- 
cgit v1.2.3


From 876611c493b10cbb59e0e2143d3e744d0442de63 Mon Sep 17 00:00:00 2001
From: Xu Yilun <yilun.xu@intel.com>
Date: Tue, 15 Sep 2020 11:44:21 +0800
Subject: mfd: intel-m10-bmc: Add Intel MAX 10 BMC chip support for Intel FPGA
 PAC

This patch implements the basic functions of the BMC chip for some Intel
FPGA PCIe Acceleration Cards (PAC). The BMC is implemented using the
Intel MAX 10 CPLD.

This BMC chip is connected to the FPGA by a SPI bus. To provide direct
register access from the FPGA, the "SPI slave to Avalon Master Bridge"
(spi-avmm) IP is integrated in the chip. It converts encoded streams of
bytes from the host to the internal register read/write on the Avalon
bus. So This driver uses the regmap-spi-avmm for register accessing.

Signed-off-by: Xu Yilun <yilun.xu@intel.com>
Signed-off-by: Wu Hao <hao.wu@intel.com>
Signed-off-by: Matthew Gerlach <matthew.gerlach@linux.intel.com>
Signed-off-by: Russ Weight <russell.h.weight@intel.com>
Reviewed-by: Tom Rix <trix@redhat.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 .../ABI/testing/sysfs-driver-intel-m10-bmc         |  15 ++
 drivers/mfd/Kconfig                                |  13 ++
 drivers/mfd/Makefile                               |   1 +
 drivers/mfd/intel-m10-bmc.c                        | 164 +++++++++++++++++++++
 include/linux/mfd/intel-m10-bmc.h                  |  65 ++++++++
 5 files changed, 258 insertions(+)
 create mode 100644 Documentation/ABI/testing/sysfs-driver-intel-m10-bmc
 create mode 100644 drivers/mfd/intel-m10-bmc.c
 create mode 100644 include/linux/mfd/intel-m10-bmc.h

(limited to 'include/linux')

diff --git a/Documentation/ABI/testing/sysfs-driver-intel-m10-bmc b/Documentation/ABI/testing/sysfs-driver-intel-m10-bmc
new file mode 100644
index 000000000000..979a2d62513f
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-driver-intel-m10-bmc
@@ -0,0 +1,15 @@
+What:		/sys/bus/spi/devices/.../bmc_version
+Date:		June 2020
+KernelVersion:	5.10
+Contact:	Xu Yilun <yilun.xu@intel.com>
+Description:	Read only. Returns the hardware build version of Intel
+		MAX10 BMC chip.
+		Format: "0x%x".
+
+What:		/sys/bus/spi/devices/.../bmcfw_version
+Date:		June 2020
+KernelVersion:	5.10
+Contact:	Xu Yilun <yilun.xu@intel.com>
+Description:	Read only. Returns the firmware version of Intel MAX10
+		BMC chip.
+		Format: "0x%x".
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index e1d3bf77b245..2ba269429e25 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -2151,5 +2151,18 @@ config SGI_MFD_IOC3
 	  If you have an SGI Origin, Octane, or a PCI IOC3 card,
 	  then say Y. Otherwise say N.
 
+config MFD_INTEL_M10_BMC
+	tristate "Intel MAX 10 Board Management Controller"
+	depends on SPI_MASTER
+	select REGMAP_SPI_AVMM
+	select MFD_CORE
+	help
+	  Support for the Intel MAX 10 board management controller using the
+	  SPI interface.
+
+	  This driver provides common support for accessing the device,
+	  additional drivers must be enabled in order to use the functionality
+	  of the device.
+
 endmenu
 endif
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index e6c7520ed129..1780019d2474 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -266,3 +266,4 @@ obj-$(CONFIG_MFD_KHADAS_MCU) 	+= khadas-mcu.o
 
 obj-$(CONFIG_SGI_MFD_IOC3)	+= ioc3.o
 obj-$(CONFIG_MFD_SIMPLE_MFD_I2C)	+= simple-mfd-i2c.o
+obj-$(CONFIG_MFD_INTEL_M10_BMC)   += intel-m10-bmc.o
diff --git a/drivers/mfd/intel-m10-bmc.c b/drivers/mfd/intel-m10-bmc.c
new file mode 100644
index 000000000000..b84579b7b4f0
--- /dev/null
+++ b/drivers/mfd/intel-m10-bmc.c
@@ -0,0 +1,164 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel MAX 10 Board Management Controller chip
+ *
+ * Copyright (C) 2018-2020 Intel Corporation. All rights reserved.
+ */
+#include <linux/bitfield.h>
+#include <linux/init.h>
+#include <linux/mfd/core.h>
+#include <linux/mfd/intel-m10-bmc.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/regmap.h>
+#include <linux/spi/spi.h>
+
+enum m10bmc_type {
+	M10_N3000,
+};
+
+static struct mfd_cell m10bmc_pacn3000_subdevs[] = {
+	{ .name = "n3000bmc-hwmon" },
+	{ .name = "n3000bmc-retimer" },
+	{ .name = "n3000bmc-secure" },
+};
+
+static struct regmap_config intel_m10bmc_regmap_config = {
+	.reg_bits = 32,
+	.val_bits = 32,
+	.reg_stride = 4,
+	.max_register = M10BMC_MEM_END,
+};
+
+static ssize_t bmc_version_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct intel_m10bmc *ddata = dev_get_drvdata(dev);
+	unsigned int val;
+	int ret;
+
+	ret = m10bmc_sys_read(ddata, M10BMC_BUILD_VER, &val);
+	if (ret)
+		return ret;
+
+	return sprintf(buf, "0x%x\n", val);
+}
+static DEVICE_ATTR_RO(bmc_version);
+
+static ssize_t bmcfw_version_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	struct intel_m10bmc *ddata = dev_get_drvdata(dev);
+	unsigned int val;
+	int ret;
+
+	ret = m10bmc_sys_read(ddata, NIOS2_FW_VERSION, &val);
+	if (ret)
+		return ret;
+
+	return sprintf(buf, "0x%x\n", val);
+}
+static DEVICE_ATTR_RO(bmcfw_version);
+
+static struct attribute *m10bmc_attrs[] = {
+	&dev_attr_bmc_version.attr,
+	&dev_attr_bmcfw_version.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(m10bmc);
+
+static int check_m10bmc_version(struct intel_m10bmc *ddata)
+{
+	unsigned int v;
+	int ret;
+
+	/*
+	 * This check is to filter out the very old legacy BMC versions,
+	 * M10BMC_LEGACY_SYS_BASE is the offset to this old block of mmio
+	 * registers. In the old BMC chips, the BMC version info is stored
+	 * in this old version register (M10BMC_LEGACY_SYS_BASE +
+	 * M10BMC_BUILD_VER), so its read out value would have not been
+	 * LEGACY_INVALID (0xffffffff). But in new BMC chips that the
+	 * driver supports, the value of this register should be
+	 * LEGACY_INVALID.
+	 */
+	ret = m10bmc_raw_read(ddata,
+			      M10BMC_LEGACY_SYS_BASE + M10BMC_BUILD_VER, &v);
+	if (ret)
+		return -ENODEV;
+
+	if (v != M10BMC_VER_LEGACY_INVALID) {
+		dev_err(ddata->dev, "bad version M10BMC detected\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static int intel_m10_bmc_spi_probe(struct spi_device *spi)
+{
+	const struct spi_device_id *id = spi_get_device_id(spi);
+	struct device *dev = &spi->dev;
+	struct mfd_cell *cells;
+	struct intel_m10bmc *ddata;
+	int ret, n_cell;
+
+	ddata = devm_kzalloc(dev, sizeof(*ddata), GFP_KERNEL);
+	if (!ddata)
+		return -ENOMEM;
+
+	ddata->dev = dev;
+
+	ddata->regmap =
+		devm_regmap_init_spi_avmm(spi, &intel_m10bmc_regmap_config);
+	if (IS_ERR(ddata->regmap)) {
+		ret = PTR_ERR(ddata->regmap);
+		dev_err(dev, "Failed to allocate regmap: %d\n", ret);
+		return ret;
+	}
+
+	spi_set_drvdata(spi, ddata);
+
+	ret = check_m10bmc_version(ddata);
+	if (ret) {
+		dev_err(dev, "Failed to identify m10bmc hardware\n");
+		return ret;
+	}
+
+	switch (id->driver_data) {
+	case M10_N3000:
+		cells = m10bmc_pacn3000_subdevs;
+		n_cell = ARRAY_SIZE(m10bmc_pacn3000_subdevs);
+		break;
+	default:
+		return -ENODEV;
+	}
+
+	ret = devm_mfd_add_devices(dev, PLATFORM_DEVID_AUTO, cells, n_cell,
+				   NULL, 0, NULL);
+	if (ret)
+		dev_err(dev, "Failed to register sub-devices: %d\n", ret);
+
+	return ret;
+}
+
+static const struct spi_device_id m10bmc_spi_id[] = {
+	{ "m10-n3000", M10_N3000 },
+	{ }
+};
+MODULE_DEVICE_TABLE(spi, m10bmc_spi_id);
+
+static struct spi_driver intel_m10bmc_spi_driver = {
+	.driver = {
+		.name = "intel-m10-bmc",
+		.dev_groups = m10bmc_groups,
+	},
+	.probe = intel_m10_bmc_spi_probe,
+	.id_table = m10bmc_spi_id,
+};
+module_spi_driver(intel_m10bmc_spi_driver);
+
+MODULE_DESCRIPTION("Intel MAX 10 BMC Device Driver");
+MODULE_AUTHOR("Intel Corporation");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("spi:intel-m10-bmc");
diff --git a/include/linux/mfd/intel-m10-bmc.h b/include/linux/mfd/intel-m10-bmc.h
new file mode 100644
index 000000000000..c8ef2f1654a4
--- /dev/null
+++ b/include/linux/mfd/intel-m10-bmc.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Intel MAX 10 Board Management Controller chip.
+ *
+ * Copyright (C) 2018-2020 Intel Corporation, Inc.
+ */
+#ifndef __MFD_INTEL_M10_BMC_H
+#define __MFD_INTEL_M10_BMC_H
+
+#include <linux/regmap.h>
+
+#define M10BMC_LEGACY_SYS_BASE		0x300400
+#define M10BMC_SYS_BASE			0x300800
+#define M10BMC_MEM_END			0x200000fc
+
+/* Register offset of system registers */
+#define NIOS2_FW_VERSION		0x0
+#define M10BMC_TEST_REG			0x3c
+#define M10BMC_BUILD_VER		0x68
+#define M10BMC_VER_MAJOR_MSK		GENMASK(23, 16)
+#define M10BMC_VER_PCB_INFO_MSK		GENMASK(31, 24)
+#define M10BMC_VER_LEGACY_INVALID	0xffffffff
+
+/**
+ * struct intel_m10bmc - Intel MAX 10 BMC parent driver data structure
+ * @dev: this device
+ * @regmap: the regmap used to access registers by m10bmc itself
+ */
+struct intel_m10bmc {
+	struct device *dev;
+	struct regmap *regmap;
+};
+
+/*
+ * register access helper functions.
+ *
+ * m10bmc_raw_read - read m10bmc register per addr
+ * m10bmc_sys_read - read m10bmc system register per offset
+ */
+static inline int
+m10bmc_raw_read(struct intel_m10bmc *m10bmc, unsigned int addr,
+		unsigned int *val)
+{
+	int ret;
+
+	ret = regmap_read(m10bmc->regmap, addr, val);
+	if (ret)
+		dev_err(m10bmc->dev, "fail to read raw reg %x: %d\n",
+			addr, ret);
+
+	return ret;
+}
+
+/*
+ * The base of the system registers could be configured by HW developers, and
+ * in HW SPEC, the base is not added to the addresses of the system registers.
+ *
+ * This macro helps to simplify the accessing of the system registers. And if
+ * the base is reconfigured in HW, SW developers could simply change the
+ * M10BMC_SYS_BASE accordingly.
+ */
+#define m10bmc_sys_read(m10bmc, offset, val) \
+	m10bmc_raw_read(m10bmc, M10BMC_SYS_BASE + (offset), val)
+
+#endif /* __MFD_INTEL_M10_BMC_H */
-- 
cgit v1.2.3


From 38b393fec298569c8ec154c750a107299bc8385d Mon Sep 17 00:00:00 2001
From: Marek Behún <marek.behun@nic.cz>
Date: Sun, 20 Sep 2020 00:15:36 +0200
Subject: leds: tca6507: Absorb platform data
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The only in-tree usage of this driver is via device-tree. No on else
includes linux/leds-tca6507.h, so absorb the definition of platdata
structure.

Signed-off-by: Marek Behún <marek.behun@nic.cz>
Cc: NeilBrown <neilb@suse.de>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Tested-by: H. Nikolaus Schaller <hns@goldelico.com>
Signed-off-by: Pavel Machek <pavel@ucw.cz>
---
 drivers/leds/leds-tca6507.c  | 11 ++++++++++-
 include/linux/leds-tca6507.h | 21 ---------------------
 2 files changed, 10 insertions(+), 22 deletions(-)
 delete mode 100644 include/linux/leds-tca6507.h

(limited to 'include/linux')

diff --git a/drivers/leds/leds-tca6507.c b/drivers/leds/leds-tca6507.c
index a7e9fd85b6dd..b5b5bafe2176 100644
--- a/drivers/leds/leds-tca6507.c
+++ b/drivers/leds/leds-tca6507.c
@@ -95,7 +95,6 @@
 #include <linux/i2c.h>
 #include <linux/gpio/driver.h>
 #include <linux/workqueue.h>
-#include <linux/leds-tca6507.h>
 #include <linux/of.h>
 
 /* LED select registers determine the source that drives LED outputs */
@@ -108,6 +107,16 @@
 #define TCA6507_LS_BLINK0	0x6	/* Blink at Bank0 rate */
 #define TCA6507_LS_BLINK1	0x7	/* Blink at Bank1 rate */
 
+struct tca6507_platform_data {
+	struct led_platform_data leds;
+#ifdef CONFIG_GPIOLIB
+	int gpio_base;
+	void (*setup)(unsigned gpio_base, unsigned ngpio);
+#endif
+};
+
+#define	TCA6507_MAKE_GPIO 1
+
 enum {
 	BANK0,
 	BANK1,
diff --git a/include/linux/leds-tca6507.h b/include/linux/leds-tca6507.h
deleted file mode 100644
index 50d330ed1100..000000000000
--- a/include/linux/leds-tca6507.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * TCA6507 LED chip driver.
- *
- * Copyright (C) 2011 Neil Brown <neil@brown.name>
- */
-
-#ifndef __LINUX_TCA6507_H
-#define __LINUX_TCA6507_H
-#include <linux/leds.h>
-
-struct tca6507_platform_data {
-	struct led_platform_data leds;
-#ifdef CONFIG_GPIOLIB
-	int gpio_base;
-	void (*setup)(unsigned gpio_base, unsigned ngpio);
-#endif
-};
-
-#define	TCA6507_MAKE_GPIO 1
-#endif /* __LINUX_TCA6507_H*/
-- 
cgit v1.2.3


From 85fc8efe85d405b80904f73e4e23184a84283753 Mon Sep 17 00:00:00 2001
From: Marek Behún <marek.behun@nic.cz>
Date: Sun, 20 Sep 2020 02:24:59 +0200
Subject: leds: pca963x: register LEDs immediately after parsing, get rid of
 platdata
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Register LEDs immediately after parsing their properties.
This allows us to get rid of platdata, and since no one in tree uses
header linux/platform_data/leds-pca963x.h, remove it.

Signed-off-by: Marek Behún <marek.behun@nic.cz>
Cc: Peter Meerwald <p.meerwald@bct-electronic.com>
Cc: Ricardo Ribalda <ribalda@kernel.org>
Cc: Zahari Petkov <zahari@balena.io>
Signed-off-by: Pavel Machek <pavel@ucw.cz>
---
 drivers/leds/leds-pca963x.c                | 188 +++++++++++------------------
 include/linux/platform_data/leds-pca963x.h |  35 ------
 2 files changed, 71 insertions(+), 152 deletions(-)
 delete mode 100644 include/linux/platform_data/leds-pca963x.h

(limited to 'include/linux')

diff --git a/drivers/leds/leds-pca963x.c b/drivers/leds/leds-pca963x.c
index 73dc00787bee..5083ccce1a51 100644
--- a/drivers/leds/leds-pca963x.c
+++ b/drivers/leds/leds-pca963x.c
@@ -32,7 +32,6 @@
 #include <linux/property.h>
 #include <linux/slab.h>
 #include <linux/of.h>
-#include <linux/platform_data/leds-pca963x.h>
 
 /* LED select registers determine the source that drives LED outputs */
 #define PCA963X_LED_OFF		0x0	/* LED driver off */
@@ -102,7 +101,6 @@ struct pca963x_led {
 	struct pca963x *chip;
 	struct led_classdev led_cdev;
 	int led_num; /* 0 .. 15 potentially */
-	char name[32];
 	u8 gdc;
 	u8 gfrq;
 };
@@ -284,72 +282,85 @@ static int pca963x_blink_set(struct led_classdev *led_cdev,
 	return 0;
 }
 
-static struct pca963x_platform_data *
-pca963x_get_pdata(struct device *dev, struct pca963x_chipdef *chipdef)
+static int pca963x_register_leds(struct i2c_client *client,
+				 struct pca963x *chip)
 {
-	struct pca963x_platform_data *pdata;
-	struct led_info *pca963x_leds;
+	struct pca963x_chipdef *chipdef = chip->chipdef;
+	struct pca963x_led *led = chip->leds;
+	struct device *dev = &client->dev;
 	struct fwnode_handle *child;
-	int count;
+	const char *name;
+	char label[64];
+	bool hw_blink;
+	s32 mode2;
+	u32 reg;
+	int ret;
 
-	count = device_get_child_node_count(dev);
-	if (!count || count > chipdef->n_leds)
-		return ERR_PTR(-ENODEV);
+	if (device_property_read_u32(dev, "nxp,period-scale",
+				     &chipdef->scaling))
+		chipdef->scaling = 1000;
 
-	pca963x_leds = devm_kcalloc(dev, chipdef->n_leds,
-				    sizeof(struct led_info), GFP_KERNEL);
-	if (!pca963x_leds)
-		return ERR_PTR(-ENOMEM);
+	hw_blink = device_property_read_bool(dev, "nxp,hw-blink");
 
-	device_for_each_child_node(dev, child) {
-		struct led_info led = {};
-		u32 reg;
-		int res;
+	mode2 = i2c_smbus_read_byte_data(client, PCA963X_MODE2);
+	if (mode2 < 0)
+		return mode2;
 
-		res = fwnode_property_read_u32(child, "reg", &reg);
-		if ((res != 0) || (reg >= chipdef->n_leds))
-			continue;
+	/* default to open-drain unless totem pole (push-pull) is specified */
+	if (device_property_read_bool(dev, "nxp,totem-pole"))
+		mode2 |= PCA963X_MODE2_OUTDRV;
+	else
+		mode2 &= ~PCA963X_MODE2_OUTDRV;
 
-		res = fwnode_property_read_string(child, "label", &led.name);
-		if ((res != 0) && is_of_node(child))
-			led.name = to_of_node(child)->name;
+	/* default to non-inverted output, unless inverted is specified */
+	if (device_property_read_bool(dev, "nxp,inverted-out"))
+		mode2 |= PCA963X_MODE2_INVRT;
+	else
+		mode2 &= ~PCA963X_MODE2_INVRT;
 
-		fwnode_property_read_string(child, "linux,default-trigger",
-					    &led.default_trigger);
+	ret = i2c_smbus_write_byte_data(client, PCA963X_MODE2, mode2);
+	if (ret < 0)
+		return ret;
 
-		pca963x_leds[reg] = led;
-	}
-	pdata = devm_kzalloc(dev, sizeof(struct pca963x_platform_data),
-			     GFP_KERNEL);
-	if (!pdata)
-		return ERR_PTR(-ENOMEM);
+	device_for_each_child_node(dev, child) {
+		ret = fwnode_property_read_u32(child, "reg", &reg);
+		if (ret || reg >= chipdef->n_leds) {
+			dev_err(dev, "Invalid 'reg' property for node %pfw\n",
+				child);
+			ret = -EINVAL;
+			goto err;
+		}
 
-	pdata->leds.leds = pca963x_leds;
-	pdata->leds.num_leds = chipdef->n_leds;
+		ret = fwnode_property_read_string(child, "label", &name);
+		if (!fwnode_property_read_string(child, "label", &name))
+			snprintf(label, sizeof(label), "pca963x:%s", name);
+		else
+			snprintf(label, sizeof(label), "pca963x::");
 
-	/* default to open-drain unless totem pole (push-pull) is specified */
-	if (device_property_read_bool(dev, "nxp,totem-pole"))
-		pdata->outdrv = PCA963X_TOTEM_POLE;
-	else
-		pdata->outdrv = PCA963X_OPEN_DRAIN;
+		fwnode_property_read_string(child, "linux,default-trigger",
+					    &led->led_cdev.default_trigger);
 
-	/* default to software blinking unless hardware blinking is specified */
-	if (device_property_read_bool(dev, "nxp,hw-blink"))
-		pdata->blink_type = PCA963X_HW_BLINK;
-	else
-		pdata->blink_type = PCA963X_SW_BLINK;
+		led->led_num = reg;
+		led->chip = chip;
+		led->led_cdev.name = label;
+		led->led_cdev.brightness_set_blocking = pca963x_led_set;
+		if (hw_blink)
+			led->led_cdev.blink_set = pca963x_blink_set;
 
-	if (device_property_read_u32(dev, "nxp,period-scale",
-				     &chipdef->scaling))
-		chipdef->scaling = 1000;
+		ret = devm_led_classdev_register(dev, &led->led_cdev);
+		if (ret) {
+			dev_err(dev, "Failed to register LED for node %pfw\n",
+				child);
+			goto err;
+		}
 
-	/* default to non-inverted output, unless inverted is specified */
-	if (device_property_read_bool(dev, "nxp,inverted-out"))
-		pdata->dir = PCA963X_INVERTED;
-	else
-		pdata->dir = PCA963X_NORMAL;
+		++led;
+	}
 
-	return pdata;
+	return 0;
+err:
+	fwnode_handle_put(child);
+	return ret;
 }
 
 static const struct of_device_id of_pca963x_match[] = {
@@ -366,30 +377,19 @@ static int pca963x_probe(struct i2c_client *client,
 {
 	struct device *dev = &client->dev;
 	struct pca963x_chipdef *chipdef;
-	struct pca963x_platform_data *pdata;
 	struct pca963x *chip;
-	int i, err;
+	int i, count;
 
 	chipdef = &pca963x_chipdefs[id->driver_data];
-	pdata = dev_get_platdata(dev);
 
-	if (!pdata) {
-		pdata = pca963x_get_pdata(dev, chipdef);
-		if (IS_ERR(pdata)) {
-			dev_warn(dev, "could not parse configuration\n");
-			pdata = NULL;
-		}
-	}
-
-	if (pdata && (pdata->leds.num_leds < 1 ||
-		      pdata->leds.num_leds > chipdef->n_leds)) {
-		dev_err(dev, "board info must claim 1-%d LEDs",
-			chipdef->n_leds);
+	count = device_get_child_node_count(dev);
+	if (!count || count > chipdef->n_leds) {
+		dev_err(dev, "Node %pfw must define between 1 and %d LEDs\n",
+			dev_fwnode(dev), chipdef->n_leds);
 		return -EINVAL;
 	}
 
-	chip = devm_kzalloc(dev, struct_size(chip, leds, chipdef->n_leds),
-			    GFP_KERNEL);
+	chip = devm_kzalloc(dev, struct_size(chip, leds, count), GFP_KERNEL);
 	if (!chip)
 		return -ENOMEM;
 
@@ -403,56 +403,10 @@ static int pca963x_probe(struct i2c_client *client,
 	for (i = 0; i < chipdef->n_leds / 4; i++)
 		i2c_smbus_write_byte_data(client, chipdef->ledout_base + i, 0x00);
 
-	for (i = 0; i < chipdef->n_leds; i++) {
-		struct pca963x_led *led = &chip->leds[i];
-
-		led->led_num = i;
-		led->chip = chip;
-
-		/* Platform data can specify LED names and default triggers */
-		if (pdata && i < pdata->leds.num_leds) {
-			if (pdata->leds.leds[i].name)
-				snprintf(led->name,
-					 sizeof(led->name), "pca963x:%s",
-					 pdata->leds.leds[i].name);
-			if (pdata->leds.leds[i].default_trigger)
-				led->led_cdev.default_trigger =
-					pdata->leds.leds[i].default_trigger;
-		}
-		if (!pdata || i >= pdata->leds.num_leds ||
-						!pdata->leds.leds[i].name)
-			snprintf(led->name, sizeof(led->name),
-				 "pca963x:%d:%.2x:%d", client->adapter->nr,
-				 client->addr, i);
-
-		led->led_cdev.name = led->name;
-		led->led_cdev.brightness_set_blocking = pca963x_led_set;
-
-		if (pdata && pdata->blink_type == PCA963X_HW_BLINK)
-			led->led_cdev.blink_set = pca963x_blink_set;
-
-		err = devm_led_classdev_register(dev, &led->led_cdev);
-		if (err < 0)
-			return err;
-	}
-
 	/* Disable LED all-call address, and power down initially */
 	i2c_smbus_write_byte_data(client, PCA963X_MODE1, BIT(4));
 
-	if (pdata) {
-		u8 mode2 = i2c_smbus_read_byte_data(client, PCA963X_MODE2);
-		/* Configure output: open-drain or totem pole (push-pull) */
-		if (pdata->outdrv == PCA963X_OPEN_DRAIN)
-			mode2 &= ~PCA963X_MODE2_OUTDRV;
-		else
-			mode2 |= PCA963X_MODE2_OUTDRV;
-		/* Configure direction: normal or inverted */
-		if (pdata->dir == PCA963X_INVERTED)
-			mode2 |= PCA963X_MODE2_INVRT;
-		i2c_smbus_write_byte_data(client, PCA963X_MODE2, mode2);
-	}
-
-	return 0;
+	return pca963x_register_leds(client, chip);
 }
 
 static struct i2c_driver pca963x_driver = {
diff --git a/include/linux/platform_data/leds-pca963x.h b/include/linux/platform_data/leds-pca963x.h
deleted file mode 100644
index 6091337ce4bf..000000000000
--- a/include/linux/platform_data/leds-pca963x.h
+++ /dev/null
@@ -1,35 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * PCA963X LED chip driver.
- *
- * Copyright 2012 bct electronic GmbH
- * Copyright 2013 Qtechnology A/S
- */
-
-#ifndef __LINUX_PCA963X_H
-#define __LINUX_PCA963X_H
-#include <linux/leds.h>
-
-enum pca963x_outdrv {
-	PCA963X_OPEN_DRAIN,
-	PCA963X_TOTEM_POLE, /* aka push-pull */
-};
-
-enum pca963x_blink_type {
-	PCA963X_SW_BLINK,
-	PCA963X_HW_BLINK,
-};
-
-enum pca963x_direction {
-	PCA963X_NORMAL,
-	PCA963X_INVERTED,
-};
-
-struct pca963x_platform_data {
-	struct led_platform_data leds;
-	enum pca963x_outdrv outdrv;
-	enum pca963x_blink_type blink_type;
-	enum pca963x_direction dir;
-};
-
-#endif /* __LINUX_PCA963X_H*/
-- 
cgit v1.2.3


From 92acdc58ab11af66fcaef485433fde61b5e32fac Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 30 Sep 2020 17:18:16 +0200
Subject: bpf, net: Rework cookie generator as per-cpu one

With its use in BPF, the cookie generator can be called very frequently
in particular when used out of cgroup v2 hooks (e.g. connect / sendmsg)
and attached to the root cgroup, for example, when used in v1/v2 mixed
environments. In particular, when there's a high churn on sockets in the
system there can be many parallel requests to the bpf_get_socket_cookie()
and bpf_get_netns_cookie() helpers which then cause contention on the
atomic counter.

As similarly done in f991bd2e1421 ("fs: introduce a per-cpu last_ino
allocator"), add a small helper library that both can use for the 64 bit
counters. Given this can be called from different contexts, we also need
to deal with potential nested calls even though in practice they are
considered extremely rare. One idea as suggested by Eric Dumazet was
to use a reverse counter for this situation since we don't expect 64 bit
overflows anyways; that way, we can avoid bigger gaps in the 64 bit
counter space compared to just batch-wise increase. Even on machines
with small number of cores (e.g. 4) the cookie generation shrinks from
min/max/med/avg (ns) of 22/50/40/38.9 down to 10/35/14/17.3 when run
in parallel from multiple CPUs.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Link: https://lore.kernel.org/bpf/8a80b8d27d3c49f9a14e1d5213c19d8be87d1dc8.1601477936.git.daniel@iogearbox.net
---
 include/linux/cookie.h       | 51 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/sock_diag.h    | 14 +++++++++++-
 include/net/net_namespace.h  |  2 +-
 kernel/bpf/reuseport_array.c |  2 +-
 net/core/filter.c            | 10 ++++-----
 net/core/net_namespace.c     | 12 +++++++----
 net/core/sock_diag.c         |  9 ++++----
 net/core/sock_map.c          |  4 ++--
 8 files changed, 86 insertions(+), 18 deletions(-)
 create mode 100644 include/linux/cookie.h

(limited to 'include/linux')

diff --git a/include/linux/cookie.h b/include/linux/cookie.h
new file mode 100644
index 000000000000..0c159f585109
--- /dev/null
+++ b/include/linux/cookie.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_COOKIE_H
+#define __LINUX_COOKIE_H
+
+#include <linux/atomic.h>
+#include <linux/percpu.h>
+#include <asm/local.h>
+
+struct pcpu_gen_cookie {
+	local_t nesting;
+	u64 last;
+} __aligned(16);
+
+struct gen_cookie {
+	struct pcpu_gen_cookie __percpu *local;
+	atomic64_t forward_last ____cacheline_aligned_in_smp;
+	atomic64_t reverse_last;
+};
+
+#define COOKIE_LOCAL_BATCH	4096
+
+#define DEFINE_COOKIE(name)						\
+	static DEFINE_PER_CPU(struct pcpu_gen_cookie, __##name);	\
+	static struct gen_cookie name = {				\
+		.local		= &__##name,				\
+		.forward_last	= ATOMIC64_INIT(0),			\
+		.reverse_last	= ATOMIC64_INIT(0),			\
+	}
+
+static __always_inline u64 gen_cookie_next(struct gen_cookie *gc)
+{
+	struct pcpu_gen_cookie *local = this_cpu_ptr(gc->local);
+	u64 val;
+
+	if (likely(local_inc_return(&local->nesting) == 1)) {
+		val = local->last;
+		if (__is_defined(CONFIG_SMP) &&
+		    unlikely((val & (COOKIE_LOCAL_BATCH - 1)) == 0)) {
+			s64 next = atomic64_add_return(COOKIE_LOCAL_BATCH,
+						       &gc->forward_last);
+			val = next - COOKIE_LOCAL_BATCH;
+		}
+		local->last = ++val;
+	} else {
+		val = atomic64_dec_return(&gc->reverse_last);
+	}
+	local_dec(&local->nesting);
+	return val;
+}
+
+#endif /* __LINUX_COOKIE_H */
diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h
index 15fe980a27ea..0b9ecd8cf979 100644
--- a/include/linux/sock_diag.h
+++ b/include/linux/sock_diag.h
@@ -25,7 +25,19 @@ void sock_diag_unregister(const struct sock_diag_handler *h);
 void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh));
 void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh));
 
-u64 sock_gen_cookie(struct sock *sk);
+u64 __sock_gen_cookie(struct sock *sk);
+
+static inline u64 sock_gen_cookie(struct sock *sk)
+{
+	u64 cookie;
+
+	preempt_disable();
+	cookie = __sock_gen_cookie(sk);
+	preempt_enable();
+
+	return cookie;
+}
+
 int sock_diag_check_cookie(struct sock *sk, const __u32 *cookie);
 void sock_diag_save_cookie(struct sock *sk, __u32 *cookie);
 
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 2ee5901bec7a..22bc07f4b043 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -230,7 +230,7 @@ extern struct list_head net_namespace_list;
 struct net *get_net_ns_by_pid(pid_t pid);
 struct net *get_net_ns_by_fd(int fd);
 
-u64 net_gen_cookie(struct net *net);
+u64 __net_gen_cookie(struct net *net);
 
 #ifdef CONFIG_SYSCTL
 void ipx_register_sysctl(void);
diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c
index 5a2ba1182493..a55cd542f2ce 100644
--- a/kernel/bpf/reuseport_array.c
+++ b/kernel/bpf/reuseport_array.c
@@ -191,7 +191,7 @@ int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key,
 	rcu_read_lock();
 	sk = reuseport_array_lookup_elem(map, key);
 	if (sk) {
-		*(u64 *)value = sock_gen_cookie(sk);
+		*(u64 *)value = __sock_gen_cookie(sk);
 		err = 0;
 	} else {
 		err = -ENOENT;
diff --git a/net/core/filter.c b/net/core/filter.c
index fa01c697977d..a0776e48dcc9 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4232,7 +4232,7 @@ const struct bpf_func_proto bpf_xdp_output_proto = {
 
 BPF_CALL_1(bpf_get_socket_cookie, struct sk_buff *, skb)
 {
-	return skb->sk ? sock_gen_cookie(skb->sk) : 0;
+	return skb->sk ? __sock_gen_cookie(skb->sk) : 0;
 }
 
 static const struct bpf_func_proto bpf_get_socket_cookie_proto = {
@@ -4244,7 +4244,7 @@ static const struct bpf_func_proto bpf_get_socket_cookie_proto = {
 
 BPF_CALL_1(bpf_get_socket_cookie_sock_addr, struct bpf_sock_addr_kern *, ctx)
 {
-	return sock_gen_cookie(ctx->sk);
+	return __sock_gen_cookie(ctx->sk);
 }
 
 static const struct bpf_func_proto bpf_get_socket_cookie_sock_addr_proto = {
@@ -4256,7 +4256,7 @@ static const struct bpf_func_proto bpf_get_socket_cookie_sock_addr_proto = {
 
 BPF_CALL_1(bpf_get_socket_cookie_sock, struct sock *, ctx)
 {
-	return sock_gen_cookie(ctx);
+	return __sock_gen_cookie(ctx);
 }
 
 static const struct bpf_func_proto bpf_get_socket_cookie_sock_proto = {
@@ -4268,7 +4268,7 @@ static const struct bpf_func_proto bpf_get_socket_cookie_sock_proto = {
 
 BPF_CALL_1(bpf_get_socket_cookie_sock_ops, struct bpf_sock_ops_kern *, ctx)
 {
-	return sock_gen_cookie(ctx->sk);
+	return __sock_gen_cookie(ctx->sk);
 }
 
 static const struct bpf_func_proto bpf_get_socket_cookie_sock_ops_proto = {
@@ -4281,7 +4281,7 @@ static const struct bpf_func_proto bpf_get_socket_cookie_sock_ops_proto = {
 static u64 __bpf_get_netns_cookie(struct sock *sk)
 {
 #ifdef CONFIG_NET_NS
-	return net_gen_cookie(sk ? sk->sk_net.net : &init_net);
+	return __net_gen_cookie(sk ? sk->sk_net.net : &init_net);
 #else
 	return 0;
 #endif
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 944ab214e5ae..dbc66b896287 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -19,6 +19,7 @@
 #include <linux/net_namespace.h>
 #include <linux/sched/task.h>
 #include <linux/uidgid.h>
+#include <linux/cookie.h>
 
 #include <net/sock.h>
 #include <net/netlink.h>
@@ -69,16 +70,16 @@ EXPORT_SYMBOL_GPL(pernet_ops_rwsem);
 
 static unsigned int max_gen_ptrs = INITIAL_NET_GEN_PTRS;
 
-static atomic64_t cookie_gen;
+DEFINE_COOKIE(net_cookie);
 
-u64 net_gen_cookie(struct net *net)
+u64 __net_gen_cookie(struct net *net)
 {
 	while (1) {
 		u64 res = atomic64_read(&net->net_cookie);
 
 		if (res)
 			return res;
-		res = atomic64_inc_return(&cookie_gen);
+		res = gen_cookie_next(&net_cookie);
 		atomic64_cmpxchg(&net->net_cookie, 0, res);
 	}
 }
@@ -1101,7 +1102,10 @@ static int __init net_ns_init(void)
 		panic("Could not allocate generic netns");
 
 	rcu_assign_pointer(init_net.gen, ng);
-	net_gen_cookie(&init_net);
+
+	preempt_disable();
+	__net_gen_cookie(&init_net);
+	preempt_enable();
 
 	down_write(&pernet_ops_rwsem);
 	if (setup_net(&init_net, &init_user_ns))
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index c13ffbd33d8d..c9c45b935f99 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -11,7 +11,7 @@
 #include <linux/tcp.h>
 #include <linux/workqueue.h>
 #include <linux/nospec.h>
-
+#include <linux/cookie.h>
 #include <linux/inet_diag.h>
 #include <linux/sock_diag.h>
 
@@ -19,16 +19,17 @@ static const struct sock_diag_handler *sock_diag_handlers[AF_MAX];
 static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh);
 static DEFINE_MUTEX(sock_diag_table_mutex);
 static struct workqueue_struct *broadcast_wq;
-static atomic64_t cookie_gen;
 
-u64 sock_gen_cookie(struct sock *sk)
+DEFINE_COOKIE(sock_cookie);
+
+u64 __sock_gen_cookie(struct sock *sk)
 {
 	while (1) {
 		u64 res = atomic64_read(&sk->sk_cookie);
 
 		if (res)
 			return res;
-		res = atomic64_inc_return(&cookie_gen);
+		res = gen_cookie_next(&sock_cookie);
 		atomic64_cmpxchg(&sk->sk_cookie, 0, res);
 	}
 }
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 08bc86f51593..e83a80e8f13b 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -401,7 +401,7 @@ static void *sock_map_lookup_sys(struct bpf_map *map, void *key)
 	if (!sk)
 		return ERR_PTR(-ENOENT);
 
-	sock_gen_cookie(sk);
+	__sock_gen_cookie(sk);
 	return &sk->sk_cookie;
 }
 
@@ -1209,7 +1209,7 @@ static void *sock_hash_lookup_sys(struct bpf_map *map, void *key)
 	if (!sk)
 		return ERR_PTR(-ENOENT);
 
-	sock_gen_cookie(sk);
+	__sock_gen_cookie(sk);
 	return &sk->sk_cookie;
 }
 
-- 
cgit v1.2.3


From b4ab31414970a7a03a5d55d75083f2c101a30592 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 30 Sep 2020 17:18:17 +0200
Subject: bpf: Add redirect_neigh helper as redirect drop-in

Add a redirect_neigh() helper as redirect() drop-in replacement
for the xmit side. Main idea for the helper is to be very similar
in semantics to the latter just that the skb gets injected into
the neighboring subsystem in order to let the stack do the work
it knows best anyway to populate the L2 addresses of the packet
and then hand over to dev_queue_xmit() as redirect() does.

This solves two bigger items: i) skbs don't need to go up to the
stack on the host facing veth ingress side for traffic egressing
the container to achieve the same for populating L2 which also
has the huge advantage that ii) the skb->sk won't get orphaned in
ip_rcv_core() when entering the IP routing layer on the host stack.

Given that skb->sk neither gets orphaned when crossing the netns
as per 9c4c325252c5 ("skbuff: preserve sock reference when scrubbing
the skb.") the helper can then push the skbs directly to the phys
device where FQ scheduler can do its work and TCP stack gets proper
backpressure given we hold on to skb->sk as long as skb is still
residing in queues.

With the helper used in BPF data path to then push the skb to the
phys device, I observed a stable/consistent TCP_STREAM improvement
on veth devices for traffic going container -> host -> host ->
container from ~10Gbps to ~15Gbps for a single stream in my test
environment.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: David Ahern <dsahern@gmail.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Cc: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/bpf/f207de81629e1724899b73b8112e0013be782d35.1601477936.git.daniel@iogearbox.net
---
 include/linux/skbuff.h         |   5 +
 include/uapi/linux/bpf.h       |  14 +++
 net/core/filter.c              | 276 ++++++++++++++++++++++++++++++++++++++---
 tools/include/uapi/linux/bpf.h |  14 +++
 4 files changed, 294 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 04a18e01b362..3d0cf3722bb4 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2548,6 +2548,11 @@ static inline int skb_mac_header_was_set(const struct sk_buff *skb)
 	return skb->mac_header != (typeof(skb->mac_header))~0U;
 }
 
+static inline void skb_unset_mac_header(struct sk_buff *skb)
+{
+	skb->mac_header = (typeof(skb->mac_header))~0U;
+}
+
 static inline void skb_reset_mac_header(struct sk_buff *skb)
 {
 	skb->mac_header = skb->data - skb->head;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 6116a7f54c8f..1f17c6752deb 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3652,6 +3652,19 @@ union bpf_attr {
  * 		associated socket instead of the current process.
  * 	Return
  * 		The id is returned or 0 in case the id could not be retrieved.
+ *
+ * long bpf_redirect_neigh(u32 ifindex, u64 flags)
+ * 	Description
+ * 		Redirect the packet to another net device of index *ifindex*
+ * 		and fill in L2 addresses from neighboring subsystem. This helper
+ * 		is somewhat similar to **bpf_redirect**\ (), except that it
+ * 		fills in e.g. MAC addresses based on the L3 information from
+ * 		the packet. This helper is supported for IPv4 and IPv6 protocols.
+ * 		The *flags* argument is reserved and must be 0. The helper is
+ * 		currently only supported for tc BPF program types.
+ * 	Return
+ * 		The helper returns **TC_ACT_REDIRECT** on success or
+ * 		**TC_ACT_SHOT** on error.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3806,6 +3819,7 @@ union bpf_attr {
 	FN(snprintf_btf),		\
 	FN(seq_printf_btf),		\
 	FN(skb_cgroup_classid),		\
+	FN(redirect_neigh),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/net/core/filter.c b/net/core/filter.c
index a0776e48dcc9..3fb6adad1957 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2163,13 +2163,233 @@ static int __bpf_redirect(struct sk_buff *skb, struct net_device *dev,
 		return __bpf_redirect_no_mac(skb, dev, flags);
 }
 
+#if IS_ENABLED(CONFIG_IPV6)
+static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb_dst(skb);
+	struct net_device *dev = dst->dev;
+	u32 hh_len = LL_RESERVED_SPACE(dev);
+	const struct in6_addr *nexthop;
+	struct neighbour *neigh;
+
+	if (dev_xmit_recursion()) {
+		net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n");
+		goto out_drop;
+	}
+
+	skb->dev = dev;
+	skb->tstamp = 0;
+
+	if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) {
+		struct sk_buff *skb2;
+
+		skb2 = skb_realloc_headroom(skb, hh_len);
+		if (unlikely(!skb2)) {
+			kfree_skb(skb);
+			return -ENOMEM;
+		}
+		if (skb->sk)
+			skb_set_owner_w(skb2, skb->sk);
+		consume_skb(skb);
+		skb = skb2;
+	}
+
+	rcu_read_lock_bh();
+	nexthop = rt6_nexthop(container_of(dst, struct rt6_info, dst),
+			      &ipv6_hdr(skb)->daddr);
+	neigh = ip_neigh_gw6(dev, nexthop);
+	if (likely(!IS_ERR(neigh))) {
+		int ret;
+
+		sock_confirm_neigh(skb, neigh);
+		dev_xmit_recursion_inc();
+		ret = neigh_output(neigh, skb, false);
+		dev_xmit_recursion_dec();
+		rcu_read_unlock_bh();
+		return ret;
+	}
+	rcu_read_unlock_bh();
+	IP6_INC_STATS(dev_net(dst->dev),
+		      ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
+out_drop:
+	kfree_skb(skb);
+	return -ENETDOWN;
+}
+
+static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev)
+{
+	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
+	struct net *net = dev_net(dev);
+	int err, ret = NET_XMIT_DROP;
+	struct dst_entry *dst;
+	struct flowi6 fl6 = {
+		.flowi6_flags	= FLOWI_FLAG_ANYSRC,
+		.flowi6_mark	= skb->mark,
+		.flowlabel	= ip6_flowinfo(ip6h),
+		.flowi6_oif	= dev->ifindex,
+		.flowi6_proto	= ip6h->nexthdr,
+		.daddr		= ip6h->daddr,
+		.saddr		= ip6h->saddr,
+	};
+
+	dst = ipv6_stub->ipv6_dst_lookup_flow(net, NULL, &fl6, NULL);
+	if (IS_ERR(dst))
+		goto out_drop;
+
+	skb_dst_set(skb, dst);
+
+	err = bpf_out_neigh_v6(net, skb);
+	if (unlikely(net_xmit_eval(err)))
+		dev->stats.tx_errors++;
+	else
+		ret = NET_XMIT_SUCCESS;
+	goto out_xmit;
+out_drop:
+	dev->stats.tx_errors++;
+	kfree_skb(skb);
+out_xmit:
+	return ret;
+}
+#else
+static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev)
+{
+	kfree_skb(skb);
+	return NET_XMIT_DROP;
+}
+#endif /* CONFIG_IPV6 */
+
+#if IS_ENABLED(CONFIG_INET)
+static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb_dst(skb);
+	struct rtable *rt = container_of(dst, struct rtable, dst);
+	struct net_device *dev = dst->dev;
+	u32 hh_len = LL_RESERVED_SPACE(dev);
+	struct neighbour *neigh;
+	bool is_v6gw = false;
+
+	if (dev_xmit_recursion()) {
+		net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n");
+		goto out_drop;
+	}
+
+	skb->dev = dev;
+	skb->tstamp = 0;
+
+	if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) {
+		struct sk_buff *skb2;
+
+		skb2 = skb_realloc_headroom(skb, hh_len);
+		if (unlikely(!skb2)) {
+			kfree_skb(skb);
+			return -ENOMEM;
+		}
+		if (skb->sk)
+			skb_set_owner_w(skb2, skb->sk);
+		consume_skb(skb);
+		skb = skb2;
+	}
+
+	rcu_read_lock_bh();
+	neigh = ip_neigh_for_gw(rt, skb, &is_v6gw);
+	if (likely(!IS_ERR(neigh))) {
+		int ret;
+
+		sock_confirm_neigh(skb, neigh);
+		dev_xmit_recursion_inc();
+		ret = neigh_output(neigh, skb, is_v6gw);
+		dev_xmit_recursion_dec();
+		rcu_read_unlock_bh();
+		return ret;
+	}
+	rcu_read_unlock_bh();
+out_drop:
+	kfree_skb(skb);
+	return -ENETDOWN;
+}
+
+static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev)
+{
+	const struct iphdr *ip4h = ip_hdr(skb);
+	struct net *net = dev_net(dev);
+	int err, ret = NET_XMIT_DROP;
+	struct rtable *rt;
+	struct flowi4 fl4 = {
+		.flowi4_flags	= FLOWI_FLAG_ANYSRC,
+		.flowi4_mark	= skb->mark,
+		.flowi4_tos	= RT_TOS(ip4h->tos),
+		.flowi4_oif	= dev->ifindex,
+		.flowi4_proto	= ip4h->protocol,
+		.daddr		= ip4h->daddr,
+		.saddr		= ip4h->saddr,
+	};
+
+	rt = ip_route_output_flow(net, &fl4, NULL);
+	if (IS_ERR(rt))
+		goto out_drop;
+	if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) {
+		ip_rt_put(rt);
+		goto out_drop;
+	}
+
+	skb_dst_set(skb, &rt->dst);
+
+	err = bpf_out_neigh_v4(net, skb);
+	if (unlikely(net_xmit_eval(err)))
+		dev->stats.tx_errors++;
+	else
+		ret = NET_XMIT_SUCCESS;
+	goto out_xmit;
+out_drop:
+	dev->stats.tx_errors++;
+	kfree_skb(skb);
+out_xmit:
+	return ret;
+}
+#else
+static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev)
+{
+	kfree_skb(skb);
+	return NET_XMIT_DROP;
+}
+#endif /* CONFIG_INET */
+
+static int __bpf_redirect_neigh(struct sk_buff *skb, struct net_device *dev)
+{
+	struct ethhdr *ethh = eth_hdr(skb);
+
+	if (unlikely(skb->mac_header >= skb->network_header))
+		goto out;
+	bpf_push_mac_rcsum(skb);
+	if (is_multicast_ether_addr(ethh->h_dest))
+		goto out;
+
+	skb_pull(skb, sizeof(*ethh));
+	skb_unset_mac_header(skb);
+	skb_reset_network_header(skb);
+
+	if (skb->protocol == htons(ETH_P_IP))
+		return __bpf_redirect_neigh_v4(skb, dev);
+	else if (skb->protocol == htons(ETH_P_IPV6))
+		return __bpf_redirect_neigh_v6(skb, dev);
+out:
+	kfree_skb(skb);
+	return -ENOTSUPP;
+}
+
+/* Internal, non-exposed redirect flags. */
+enum {
+	BPF_F_NEIGH = (1ULL << 1),
+#define BPF_F_REDIRECT_INTERNAL	(BPF_F_NEIGH)
+};
+
 BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags)
 {
 	struct net_device *dev;
 	struct sk_buff *clone;
 	int ret;
 
-	if (unlikely(flags & ~(BPF_F_INGRESS)))
+	if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL)))
 		return -EINVAL;
 
 	dev = dev_get_by_index_rcu(dev_net(skb->dev), ifindex);
@@ -2206,23 +2426,11 @@ static const struct bpf_func_proto bpf_clone_redirect_proto = {
 DEFINE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info);
 EXPORT_PER_CPU_SYMBOL_GPL(bpf_redirect_info);
 
-BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags)
-{
-	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
-
-	if (unlikely(flags & ~(BPF_F_INGRESS)))
-		return TC_ACT_SHOT;
-
-	ri->flags = flags;
-	ri->tgt_index = ifindex;
-
-	return TC_ACT_REDIRECT;
-}
-
 int skb_do_redirect(struct sk_buff *skb)
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 	struct net_device *dev;
+	u32 flags = ri->flags;
 
 	dev = dev_get_by_index_rcu(dev_net(skb->dev), ri->tgt_index);
 	ri->tgt_index = 0;
@@ -2231,7 +2439,22 @@ int skb_do_redirect(struct sk_buff *skb)
 		return -EINVAL;
 	}
 
-	return __bpf_redirect(skb, dev, ri->flags);
+	return flags & BPF_F_NEIGH ?
+	       __bpf_redirect_neigh(skb, dev) :
+	       __bpf_redirect(skb, dev, flags);
+}
+
+BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags)
+{
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+
+	if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL)))
+		return TC_ACT_SHOT;
+
+	ri->flags = flags;
+	ri->tgt_index = ifindex;
+
+	return TC_ACT_REDIRECT;
 }
 
 static const struct bpf_func_proto bpf_redirect_proto = {
@@ -2242,6 +2465,27 @@ static const struct bpf_func_proto bpf_redirect_proto = {
 	.arg2_type      = ARG_ANYTHING,
 };
 
+BPF_CALL_2(bpf_redirect_neigh, u32, ifindex, u64, flags)
+{
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+
+	if (unlikely(flags))
+		return TC_ACT_SHOT;
+
+	ri->flags = BPF_F_NEIGH;
+	ri->tgt_index = ifindex;
+
+	return TC_ACT_REDIRECT;
+}
+
+static const struct bpf_func_proto bpf_redirect_neigh_proto = {
+	.func		= bpf_redirect_neigh,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_ANYTHING,
+	.arg2_type	= ARG_ANYTHING,
+};
+
 BPF_CALL_2(bpf_msg_apply_bytes, struct sk_msg *, msg, u32, bytes)
 {
 	msg->apply_bytes = bytes;
@@ -6759,6 +7003,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return bpf_get_skb_set_tunnel_proto(func_id);
 	case BPF_FUNC_redirect:
 		return &bpf_redirect_proto;
+	case BPF_FUNC_redirect_neigh:
+		return &bpf_redirect_neigh_proto;
 	case BPF_FUNC_get_route_realm:
 		return &bpf_get_route_realm_proto;
 	case BPF_FUNC_get_hash_recalc:
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 6116a7f54c8f..1f17c6752deb 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3652,6 +3652,19 @@ union bpf_attr {
  * 		associated socket instead of the current process.
  * 	Return
  * 		The id is returned or 0 in case the id could not be retrieved.
+ *
+ * long bpf_redirect_neigh(u32 ifindex, u64 flags)
+ * 	Description
+ * 		Redirect the packet to another net device of index *ifindex*
+ * 		and fill in L2 addresses from neighboring subsystem. This helper
+ * 		is somewhat similar to **bpf_redirect**\ (), except that it
+ * 		fills in e.g. MAC addresses based on the L3 information from
+ * 		the packet. This helper is supported for IPv4 and IPv6 protocols.
+ * 		The *flags* argument is reserved and must be 0. The helper is
+ * 		currently only supported for tc BPF program types.
+ * 	Return
+ * 		The helper returns **TC_ACT_REDIRECT** on success or
+ * 		**TC_ACT_SHOT** on error.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3806,6 +3819,7 @@ union bpf_attr {
 	FN(snprintf_btf),		\
 	FN(seq_printf_btf),		\
 	FN(skb_cgroup_classid),		\
+	FN(redirect_neigh),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
-- 
cgit v1.2.3


From 14c9c014babedc6098bf4cd83c622997867bc0df Mon Sep 17 00:00:00 2001
From: Sean O'Brien <seobrien@chromium.org>
Date: Wed, 9 Sep 2020 15:03:04 -0700
Subject: HID: add vivaldi HID driver

Add vivaldi HID driver. This driver allows us to read and report the top
row layout of keyboards which provide a vendor-defined (Google) HID
usage.

Signed-off-by: Sean O'Brien <seobrien@chromium.org>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/Kconfig       |   9 +++
 drivers/hid/Makefile      |   1 +
 drivers/hid/hid-core.c    |   7 +++
 drivers/hid/hid-vivaldi.c | 144 ++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/hid.h       |   2 +
 5 files changed, 163 insertions(+)
 create mode 100644 drivers/hid/hid-vivaldi.c

(limited to 'include/linux')

diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index 05315b434276..612629678c84 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -397,6 +397,15 @@ config HID_GOOGLE_HAMMER
 	help
 	Say Y here if you have a Google Hammer device.
 
+config HID_VIVALDI
+	tristate "Vivaldi Keyboard"
+	depends on HID
+	help
+	  Say Y here if you want to enable support for Vivaldi keyboards.
+
+	  Vivaldi keyboards use a vendor-specific (Google) HID usage to report
+	  how the keys in the top row are physically ordered.
+
 config HID_GT683R
 	tristate "MSI GT68xR LED support"
 	depends on LEDS_CLASS && USB_HID
diff --git a/drivers/hid/Makefile b/drivers/hid/Makefile
index d8ea4b8c95af..4acb583c92a6 100644
--- a/drivers/hid/Makefile
+++ b/drivers/hid/Makefile
@@ -50,6 +50,7 @@ obj-$(CONFIG_HID_GEMBIRD)	+= hid-gembird.o
 obj-$(CONFIG_HID_GFRM)		+= hid-gfrm.o
 obj-$(CONFIG_HID_GLORIOUS)  += hid-glorious.o
 obj-$(CONFIG_HID_GOOGLE_HAMMER)	+= hid-google-hammer.o
+obj-$(CONFIG_HID_VIVALDI)	+= hid-vivaldi.o
 obj-$(CONFIG_HID_GT683R)	+= hid-gt683r.o
 obj-$(CONFIG_HID_GYRATION)	+= hid-gyration.o
 obj-$(CONFIG_HID_HOLTEK)	+= hid-holtek-kbd.o
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index d2ecc9c45255..6dbd09254c44 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -814,6 +814,13 @@ static void hid_scan_collection(struct hid_parser *parser, unsigned type)
 
 	if ((parser->global.usage_page << 16) >= HID_UP_MSVENDOR)
 		parser->scan_flags |= HID_SCAN_FLAG_VENDOR_SPECIFIC;
+
+	if ((parser->global.usage_page << 16) == HID_UP_GOOGLEVENDOR)
+		for (i = 0; i < parser->local.usage_index; i++)
+			if (parser->local.usage[i] ==
+					(HID_UP_GOOGLEVENDOR | 0x0001))
+				parser->device->group =
+					HID_GROUP_VIVALDI;
 }
 
 static int hid_scan_main(struct hid_parser *parser, struct hid_item *item)
diff --git a/drivers/hid/hid-vivaldi.c b/drivers/hid/hid-vivaldi.c
new file mode 100644
index 000000000000..cd7ada48b1d9
--- /dev/null
+++ b/drivers/hid/hid-vivaldi.c
@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * HID support for Vivaldi Keyboard
+ *
+ * Copyright 2020 Google LLC.
+ * Author: Sean O'Brien <seobrien@chromium.org>
+ */
+
+#include <linux/hid.h>
+#include <linux/module.h>
+
+#define MIN_FN_ROW_KEY	1
+#define MAX_FN_ROW_KEY	24
+#define HID_VD_FN_ROW_PHYSMAP 0x00000001
+#define HID_USAGE_FN_ROW_PHYSMAP (HID_UP_GOOGLEVENDOR | HID_VD_FN_ROW_PHYSMAP)
+
+static struct hid_driver hid_vivaldi;
+
+struct vivaldi_data {
+	u32 function_row_physmap[MAX_FN_ROW_KEY - MIN_FN_ROW_KEY + 1];
+	int max_function_row_key;
+};
+
+static ssize_t function_row_physmap_show(struct device *dev,
+					 struct device_attribute *attr,
+					 char *buf)
+{
+	struct hid_device *hdev = to_hid_device(dev);
+	struct vivaldi_data *drvdata = hid_get_drvdata(hdev);
+	ssize_t size = 0;
+	int i;
+
+	if (!drvdata->max_function_row_key)
+		return 0;
+
+	for (i = 0; i < drvdata->max_function_row_key; i++)
+		size += sprintf(buf + size, "%02X ",
+				drvdata->function_row_physmap[i]);
+	size += sprintf(buf + size, "\n");
+	return size;
+}
+
+DEVICE_ATTR_RO(function_row_physmap);
+static struct attribute *sysfs_attrs[] = {
+	&dev_attr_function_row_physmap.attr,
+	NULL
+};
+
+static const struct attribute_group input_attribute_group = {
+	.attrs = sysfs_attrs
+};
+
+static int vivaldi_probe(struct hid_device *hdev,
+			 const struct hid_device_id *id)
+{
+	struct vivaldi_data *drvdata;
+	int ret;
+
+	drvdata = devm_kzalloc(&hdev->dev, sizeof(*drvdata), GFP_KERNEL);
+	hid_set_drvdata(hdev, drvdata);
+
+	ret = hid_parse(hdev);
+	if (ret)
+		return ret;
+
+	return hid_hw_start(hdev, HID_CONNECT_DEFAULT);
+}
+
+static void vivaldi_feature_mapping(struct hid_device *hdev,
+				    struct hid_field *field,
+				    struct hid_usage *usage)
+{
+	struct vivaldi_data *drvdata = hid_get_drvdata(hdev);
+	int fn_key;
+	int ret;
+	u32 report_len;
+	u8 *buf;
+
+	if (field->logical != HID_USAGE_FN_ROW_PHYSMAP ||
+	    (usage->hid & HID_USAGE_PAGE) != HID_UP_ORDINAL)
+		return;
+
+	fn_key = (usage->hid & HID_USAGE);
+	if (fn_key < MIN_FN_ROW_KEY || fn_key > MAX_FN_ROW_KEY)
+		return;
+	if (fn_key > drvdata->max_function_row_key)
+		drvdata->max_function_row_key = fn_key;
+
+	buf = hid_alloc_report_buf(field->report, GFP_KERNEL);
+	if (!buf)
+		return;
+
+	report_len = hid_report_len(field->report);
+	ret = hid_hw_raw_request(hdev, field->report->id, buf,
+				 report_len, HID_FEATURE_REPORT,
+				 HID_REQ_GET_REPORT);
+	if (ret < 0) {
+		dev_warn(&hdev->dev, "failed to fetch feature %d\n",
+			 field->report->id);
+		goto out;
+	}
+
+	ret = hid_report_raw_event(hdev, HID_FEATURE_REPORT, buf,
+				   report_len, 0);
+	if (ret) {
+		dev_warn(&hdev->dev, "failed to report feature %d\n",
+			 field->report->id);
+		goto out;
+	}
+
+	drvdata->function_row_physmap[fn_key - MIN_FN_ROW_KEY] =
+	    field->value[usage->usage_index];
+
+out:
+	kfree(buf);
+}
+
+static int vivaldi_input_configured(struct hid_device *hdev,
+				    struct hid_input *hidinput)
+{
+	return sysfs_create_group(&hdev->dev.kobj, &input_attribute_group);
+}
+
+static const struct hid_device_id vivaldi_table[] = {
+	{ HID_DEVICE(HID_BUS_ANY, HID_GROUP_VIVALDI, HID_ANY_ID,
+		     HID_ANY_ID) },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(hid, vivaldi_table);
+
+static struct hid_driver hid_vivaldi = {
+	.name = "hid-vivaldi",
+	.id_table = vivaldi_table,
+	.probe = vivaldi_probe,
+	.feature_mapping = vivaldi_feature_mapping,
+	.input_configured = vivaldi_input_configured,
+};
+
+module_hid_driver(hid_vivaldi);
+
+MODULE_AUTHOR("Sean O'Brien");
+MODULE_DESCRIPTION("HID vivaldi driver");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/hid.h b/include/linux/hid.h
index c7044a14200e..58684657960b 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -163,6 +163,7 @@ struct hid_item {
 #define HID_UP_LNVENDOR		0xffa00000
 #define HID_UP_SENSOR		0x00200000
 #define HID_UP_ASUSVENDOR	0xff310000
+#define HID_UP_GOOGLEVENDOR	0xffd10000
 
 #define HID_USAGE		0x0000ffff
 
@@ -371,6 +372,7 @@ struct hid_item {
 #define HID_GROUP_LOGITECH_DJ_DEVICE		0x0102
 #define HID_GROUP_STEAM				0x0103
 #define HID_GROUP_LOGITECH_27MHZ_DEVICE		0x0104
+#define HID_GROUP_VIVALDI			0x0105
 
 /*
  * HID protocol status
-- 
cgit v1.2.3


From 20c168be684a97b084525906eb7ed017b7f9c0b8 Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Wed, 30 Sep 2020 12:50:59 +0200
Subject: net: macb: move pdata to private header

struct macb_platform_data is only used by macb_pci to register the platform
device, move its definition to cadence/macb.h and remove platform_data/macb.h

Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb.h      | 11 +++++++++++
 drivers/net/ethernet/cadence/macb_main.c |  1 -
 drivers/net/ethernet/cadence/macb_pci.c  |  1 -
 include/linux/platform_data/macb.h       | 20 --------------------
 4 files changed, 11 insertions(+), 22 deletions(-)
 delete mode 100644 include/linux/platform_data/macb.h

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index 4f1b41569260..3fd5c6cc23af 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -7,6 +7,7 @@
 #ifndef _MACB_H
 #define _MACB_H
 
+#include <linux/clk.h>
 #include <linux/phylink.h>
 #include <linux/ptp_clock_kernel.h>
 #include <linux/net_tstamp.h>
@@ -1298,4 +1299,14 @@ static inline bool gem_has_ptp(struct macb *bp)
 	return !!(bp->caps & MACB_CAPS_GEM_HAS_PTP);
 }
 
+/**
+ * struct macb_platform_data - platform data for MACB Ethernet used for PCI registration
+ * @pclk:		platform clock
+ * @hclk:		AHB clock
+ */
+struct macb_platform_data {
+	struct clk	*pclk;
+	struct clk	*hclk;
+};
+
 #endif /* _MACB_H */
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index f00ad73ea8e3..4b42b2d6398c 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -23,7 +23,6 @@
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/dma-mapping.h>
-#include <linux/platform_data/macb.h>
 #include <linux/platform_device.h>
 #include <linux/phylink.h>
 #include <linux/of.h>
diff --git a/drivers/net/ethernet/cadence/macb_pci.c b/drivers/net/ethernet/cadence/macb_pci.c
index 35316c91f523..353393dea639 100644
--- a/drivers/net/ethernet/cadence/macb_pci.c
+++ b/drivers/net/ethernet/cadence/macb_pci.c
@@ -13,7 +13,6 @@
 #include <linux/etherdevice.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/platform_data/macb.h>
 #include <linux/platform_device.h>
 #include "macb.h"
 
diff --git a/include/linux/platform_data/macb.h b/include/linux/platform_data/macb.h
deleted file mode 100644
index aa5b5562d6f7..000000000000
--- a/include/linux/platform_data/macb.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- */
-#ifndef __MACB_PDATA_H__
-#define __MACB_PDATA_H__
-
-#include <linux/clk.h>
-
-/**
- * struct macb_platform_data - platform data for MACB Ethernet
- * @pclk:		platform clock
- * @hclk:		AHB clock
- */
-struct macb_platform_data {
-	struct clk	*pclk;
-	struct clk	*hclk;
-};
-
-#endif /* __MACB_PDATA_H__ */
-- 
cgit v1.2.3


From 0f2122045b946241a9e549c2a76cea54fa58a7ff Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Sun, 13 Sep 2020 13:09:39 -0600
Subject: io_uring: don't rely on weak ->files references

Grab actual references to the files_struct. To avoid circular references
issues due to this, we add a per-task note that keeps track of what
io_uring contexts a task has used. When the tasks execs or exits its
assigned files, we cancel requests based on this tracking.

With that, we can grab proper references to the files table, and no
longer need to rely on stashing away ring_fd and ring_file to check
if the ring_fd may have been closed.

Cc: stable@vger.kernel.org # v5.5+
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/exec.c                |   6 +
 fs/file.c                |   2 +
 fs/io_uring.c            | 306 +++++++++++++++++++++++++++++++++++++++++------
 include/linux/io_uring.h |  53 ++++++++
 include/linux/sched.h    |   5 +
 init/init_task.c         |   3 +
 kernel/fork.c            |   6 +
 7 files changed, 344 insertions(+), 37 deletions(-)
 create mode 100644 include/linux/io_uring.h

(limited to 'include/linux')

diff --git a/fs/exec.c b/fs/exec.c
index a91003e28eaa..07910f5032e7 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -62,6 +62,7 @@
 #include <linux/oom.h>
 #include <linux/compat.h>
 #include <linux/vmalloc.h>
+#include <linux/io_uring.h>
 
 #include <linux/uaccess.h>
 #include <asm/mmu_context.h>
@@ -1895,6 +1896,11 @@ static int bprm_execve(struct linux_binprm *bprm,
 	struct files_struct *displaced;
 	int retval;
 
+	/*
+	 * Cancel any io_uring activity across execve
+	 */
+	io_uring_task_cancel();
+
 	retval = unshare_files(&displaced);
 	if (retval)
 		return retval;
diff --git a/fs/file.c b/fs/file.c
index 21c0893f2f1d..4559b5fec3bd 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -21,6 +21,7 @@
 #include <linux/rcupdate.h>
 #include <linux/close_range.h>
 #include <net/sock.h>
+#include <linux/io_uring.h>
 
 unsigned int sysctl_nr_open __read_mostly = 1024*1024;
 unsigned int sysctl_nr_open_min = BITS_PER_LONG;
@@ -452,6 +453,7 @@ void exit_files(struct task_struct *tsk)
 	struct files_struct * files = tsk->files;
 
 	if (files) {
+		io_uring_files_cancel(files);
 		task_lock(tsk);
 		tsk->files = NULL;
 		task_unlock(tsk);
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 046d06266a11..ee75ba7113cf 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -79,6 +79,7 @@
 #include <linux/splice.h>
 #include <linux/task_work.h>
 #include <linux/pagemap.h>
+#include <linux/io_uring.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/io_uring.h>
@@ -284,8 +285,6 @@ struct io_ring_ctx {
 	 */
 	struct fixed_file_data	*file_data;
 	unsigned		nr_user_files;
-	int 			ring_fd;
-	struct file 		*ring_file;
 
 	/* if used, fixed mapped user buffers */
 	unsigned		nr_user_bufs;
@@ -1433,7 +1432,12 @@ static void __io_cqring_fill_event(struct io_kiocb *req, long res, long cflags)
 		WRITE_ONCE(cqe->user_data, req->user_data);
 		WRITE_ONCE(cqe->res, res);
 		WRITE_ONCE(cqe->flags, cflags);
-	} else if (ctx->cq_overflow_flushed) {
+	} else if (ctx->cq_overflow_flushed || req->task->io_uring->in_idle) {
+		/*
+		 * If we're in ring overflow flush mode, or in task cancel mode,
+		 * then we cannot store the request for later flushing, we need
+		 * to drop it on the floor.
+		 */
 		WRITE_ONCE(ctx->rings->cq_overflow,
 				atomic_inc_return(&ctx->cached_cq_overflow));
 	} else {
@@ -1591,8 +1595,12 @@ static bool io_dismantle_req(struct io_kiocb *req)
 
 static void __io_free_req_finish(struct io_kiocb *req)
 {
+	struct io_uring_task *tctx = req->task->io_uring;
 	struct io_ring_ctx *ctx = req->ctx;
 
+	atomic_long_inc(&tctx->req_complete);
+	if (tctx->in_idle)
+		wake_up(&tctx->wait);
 	put_task_struct(req->task);
 
 	if (likely(!io_is_fallback_req(req)))
@@ -1907,6 +1915,7 @@ static void io_req_free_batch_finish(struct io_ring_ctx *ctx,
 	if (rb->to_free)
 		__io_req_free_batch_flush(ctx, rb);
 	if (rb->task) {
+		atomic_long_add(rb->task_refs, &rb->task->io_uring->req_complete);
 		put_task_struct_many(rb->task, rb->task_refs);
 		rb->task = NULL;
 	}
@@ -1922,8 +1931,10 @@ static void io_req_free_batch(struct req_batch *rb, struct io_kiocb *req)
 		io_queue_next(req);
 
 	if (req->task != rb->task) {
-		if (rb->task)
+		if (rb->task) {
+			atomic_long_add(rb->task_refs, &rb->task->io_uring->req_complete);
 			put_task_struct_many(rb->task, rb->task_refs);
+		}
 		rb->task = req->task;
 		rb->task_refs = 0;
 	}
@@ -3978,8 +3989,7 @@ static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		return -EBADF;
 
 	req->close.fd = READ_ONCE(sqe->fd);
-	if ((req->file && req->file->f_op == &io_uring_fops) ||
-	    req->close.fd == req->ctx->ring_fd)
+	if ((req->file && req->file->f_op == &io_uring_fops))
 		return -EBADF;
 
 	req->close.put_file = NULL;
@@ -5667,6 +5677,7 @@ static void io_req_drop_files(struct io_kiocb *req)
 		wake_up(&ctx->inflight_wait);
 	spin_unlock_irqrestore(&ctx->inflight_lock, flags);
 	req->flags &= ~REQ_F_INFLIGHT;
+	put_files_struct(req->work.files);
 	req->work.files = NULL;
 }
 
@@ -6067,34 +6078,20 @@ static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req,
 
 static int io_grab_files(struct io_kiocb *req)
 {
-	int ret = -EBADF;
 	struct io_ring_ctx *ctx = req->ctx;
 
 	io_req_init_async(req);
 
 	if (req->work.files || (req->flags & REQ_F_NO_FILE_TABLE))
 		return 0;
-	if (!ctx->ring_file)
-		return -EBADF;
 
-	rcu_read_lock();
+	req->work.files = get_files_struct(current);
+	req->flags |= REQ_F_INFLIGHT;
+
 	spin_lock_irq(&ctx->inflight_lock);
-	/*
-	 * We use the f_ops->flush() handler to ensure that we can flush
-	 * out work accessing these files if the fd is closed. Check if
-	 * the fd has changed since we started down this path, and disallow
-	 * this operation if it has.
-	 */
-	if (fcheck(ctx->ring_fd) == ctx->ring_file) {
-		list_add(&req->inflight_entry, &ctx->inflight_list);
-		req->flags |= REQ_F_INFLIGHT;
-		req->work.files = current->files;
-		ret = 0;
-	}
+	list_add(&req->inflight_entry, &ctx->inflight_list);
 	spin_unlock_irq(&ctx->inflight_lock);
-	rcu_read_unlock();
-
-	return ret;
+	return 0;
 }
 
 static inline int io_prep_work_files(struct io_kiocb *req)
@@ -6459,6 +6456,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	refcount_set(&req->refs, 2);
 	req->task = current;
 	get_task_struct(req->task);
+	atomic_long_inc(&req->task->io_uring->req_issue);
 	req->result = 0;
 
 	if (unlikely(req->opcode >= IORING_OP_LAST))
@@ -6494,8 +6492,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	return io_req_set_file(state, req, READ_ONCE(sqe->fd));
 }
 
-static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
-			  struct file *ring_file, int ring_fd)
+static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr)
 {
 	struct io_submit_state state;
 	struct io_kiocb *link = NULL;
@@ -6516,9 +6513,6 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
 
 	io_submit_state_start(&state, ctx, nr);
 
-	ctx->ring_fd = ring_fd;
-	ctx->ring_file = ring_file;
-
 	for (i = 0; i < nr; i++) {
 		const struct io_uring_sqe *sqe;
 		struct io_kiocb *req;
@@ -6687,7 +6681,7 @@ static int io_sq_thread(void *data)
 
 		mutex_lock(&ctx->uring_lock);
 		if (likely(!percpu_ref_is_dying(&ctx->refs)))
-			ret = io_submit_sqes(ctx, to_submit, NULL, -1);
+			ret = io_submit_sqes(ctx, to_submit);
 		mutex_unlock(&ctx->uring_lock);
 		timeout = jiffies + ctx->sq_thread_idle;
 	}
@@ -7516,6 +7510,34 @@ out_fput:
 	return ret;
 }
 
+static int io_uring_alloc_task_context(struct task_struct *task)
+{
+	struct io_uring_task *tctx;
+
+	tctx = kmalloc(sizeof(*tctx), GFP_KERNEL);
+	if (unlikely(!tctx))
+		return -ENOMEM;
+
+	xa_init(&tctx->xa);
+	init_waitqueue_head(&tctx->wait);
+	tctx->last = NULL;
+	tctx->in_idle = 0;
+	atomic_long_set(&tctx->req_issue, 0);
+	atomic_long_set(&tctx->req_complete, 0);
+	task->io_uring = tctx;
+	return 0;
+}
+
+void __io_uring_free(struct task_struct *tsk)
+{
+	struct io_uring_task *tctx = tsk->io_uring;
+
+	WARN_ON_ONCE(!xa_empty(&tctx->xa));
+	xa_destroy(&tctx->xa);
+	kfree(tctx);
+	tsk->io_uring = NULL;
+}
+
 static int io_sq_offload_start(struct io_ring_ctx *ctx,
 			       struct io_uring_params *p)
 {
@@ -7551,6 +7573,9 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx,
 			ctx->sqo_thread = NULL;
 			goto err;
 		}
+		ret = io_uring_alloc_task_context(ctx->sqo_thread);
+		if (ret)
+			goto err;
 		wake_up_process(ctx->sqo_thread);
 	} else if (p->flags & IORING_SETUP_SQ_AFF) {
 		/* Can't have SQ_AFF without SQPOLL */
@@ -8063,7 +8088,7 @@ static bool io_wq_files_match(struct io_wq_work *work, void *data)
 {
 	struct files_struct *files = data;
 
-	return work->files == files;
+	return !files || work->files == files;
 }
 
 /*
@@ -8218,7 +8243,7 @@ static bool io_uring_cancel_files(struct io_ring_ctx *ctx,
 
 		spin_lock_irq(&ctx->inflight_lock);
 		list_for_each_entry(req, &ctx->inflight_list, inflight_entry) {
-			if (req->work.files != files)
+			if (files && req->work.files != files)
 				continue;
 			/* req is being completed, ignore */
 			if (!refcount_inc_not_zero(&req->refs))
@@ -8254,18 +8279,217 @@ static bool io_cancel_task_cb(struct io_wq_work *work, void *data)
 	return io_task_match(req, task);
 }
 
+static bool __io_uring_cancel_task_requests(struct io_ring_ctx *ctx,
+					    struct task_struct *task,
+					    struct files_struct *files)
+{
+	bool ret;
+
+	ret = io_uring_cancel_files(ctx, files);
+	if (!files) {
+		enum io_wq_cancel cret;
+
+		cret = io_wq_cancel_cb(ctx->io_wq, io_cancel_task_cb, task, true);
+		if (cret != IO_WQ_CANCEL_NOTFOUND)
+			ret = true;
+
+		/* SQPOLL thread does its own polling */
+		if (!(ctx->flags & IORING_SETUP_SQPOLL)) {
+			while (!list_empty_careful(&ctx->iopoll_list)) {
+				io_iopoll_try_reap_events(ctx);
+				ret = true;
+			}
+		}
+
+		ret |= io_poll_remove_all(ctx, task);
+		ret |= io_kill_timeouts(ctx, task);
+	}
+
+	return ret;
+}
+
+/*
+ * We need to iteratively cancel requests, in case a request has dependent
+ * hard links. These persist even for failure of cancelations, hence keep
+ * looping until none are found.
+ */
+static void io_uring_cancel_task_requests(struct io_ring_ctx *ctx,
+					  struct files_struct *files)
+{
+	struct task_struct *task = current;
+
+	if (ctx->flags & IORING_SETUP_SQPOLL)
+		task = ctx->sqo_thread;
+
+	io_cqring_overflow_flush(ctx, true, task, files);
+
+	while (__io_uring_cancel_task_requests(ctx, task, files)) {
+		io_run_task_work();
+		cond_resched();
+	}
+}
+
+/*
+ * Note that this task has used io_uring. We use it for cancelation purposes.
+ */
+static int io_uring_add_task_file(struct file *file)
+{
+	if (unlikely(!current->io_uring)) {
+		int ret;
+
+		ret = io_uring_alloc_task_context(current);
+		if (unlikely(ret))
+			return ret;
+	}
+	if (current->io_uring->last != file) {
+		XA_STATE(xas, &current->io_uring->xa, (unsigned long) file);
+		void *old;
+
+		rcu_read_lock();
+		old = xas_load(&xas);
+		if (old != file) {
+			get_file(file);
+			xas_lock(&xas);
+			xas_store(&xas, file);
+			xas_unlock(&xas);
+		}
+		rcu_read_unlock();
+		current->io_uring->last = file;
+	}
+
+	return 0;
+}
+
+/*
+ * Remove this io_uring_file -> task mapping.
+ */
+static void io_uring_del_task_file(struct file *file)
+{
+	struct io_uring_task *tctx = current->io_uring;
+	XA_STATE(xas, &tctx->xa, (unsigned long) file);
+
+	if (tctx->last == file)
+		tctx->last = NULL;
+
+	xas_lock(&xas);
+	file = xas_store(&xas, NULL);
+	xas_unlock(&xas);
+
+	if (file)
+		fput(file);
+}
+
+static void __io_uring_attempt_task_drop(struct file *file)
+{
+	XA_STATE(xas, &current->io_uring->xa, (unsigned long) file);
+	struct file *old;
+
+	rcu_read_lock();
+	old = xas_load(&xas);
+	rcu_read_unlock();
+
+	if (old == file)
+		io_uring_del_task_file(file);
+}
+
+/*
+ * Drop task note for this file if we're the only ones that hold it after
+ * pending fput()
+ */
+static void io_uring_attempt_task_drop(struct file *file, bool exiting)
+{
+	if (!current->io_uring)
+		return;
+	/*
+	 * fput() is pending, will be 2 if the only other ref is our potential
+	 * task file note. If the task is exiting, drop regardless of count.
+	 */
+	if (!exiting && atomic_long_read(&file->f_count) != 2)
+		return;
+
+	__io_uring_attempt_task_drop(file);
+}
+
+void __io_uring_files_cancel(struct files_struct *files)
+{
+	struct io_uring_task *tctx = current->io_uring;
+	XA_STATE(xas, &tctx->xa, 0);
+
+	/* make sure overflow events are dropped */
+	tctx->in_idle = true;
+
+	do {
+		struct io_ring_ctx *ctx;
+		struct file *file;
+
+		xas_lock(&xas);
+		file = xas_next_entry(&xas, ULONG_MAX);
+		xas_unlock(&xas);
+
+		if (!file)
+			break;
+
+		ctx = file->private_data;
+
+		io_uring_cancel_task_requests(ctx, files);
+		if (files)
+			io_uring_del_task_file(file);
+	} while (1);
+}
+
+static inline bool io_uring_task_idle(struct io_uring_task *tctx)
+{
+	return atomic_long_read(&tctx->req_issue) ==
+		atomic_long_read(&tctx->req_complete);
+}
+
+/*
+ * Find any io_uring fd that this task has registered or done IO on, and cancel
+ * requests.
+ */
+void __io_uring_task_cancel(void)
+{
+	struct io_uring_task *tctx = current->io_uring;
+	DEFINE_WAIT(wait);
+	long completions;
+
+	/* make sure overflow events are dropped */
+	tctx->in_idle = true;
+
+	while (!io_uring_task_idle(tctx)) {
+		/* read completions before cancelations */
+		completions = atomic_long_read(&tctx->req_complete);
+		__io_uring_files_cancel(NULL);
+
+		prepare_to_wait(&tctx->wait, &wait, TASK_UNINTERRUPTIBLE);
+
+		/*
+		 * If we've seen completions, retry. This avoids a race where
+		 * a completion comes in before we did prepare_to_wait().
+		 */
+		if (completions != atomic_long_read(&tctx->req_complete))
+			continue;
+		if (io_uring_task_idle(tctx))
+			break;
+		schedule();
+	}
+
+	finish_wait(&tctx->wait, &wait);
+	tctx->in_idle = false;
+}
+
 static int io_uring_flush(struct file *file, void *data)
 {
 	struct io_ring_ctx *ctx = file->private_data;
 
-	io_uring_cancel_files(ctx, data);
-
 	/*
 	 * If the task is going away, cancel work it may have pending
 	 */
 	if (fatal_signal_pending(current) || (current->flags & PF_EXITING))
-		io_wq_cancel_cb(ctx->io_wq, io_cancel_task_cb, current, true);
+		data = NULL;
 
+	io_uring_cancel_task_requests(ctx, data);
+	io_uring_attempt_task_drop(file, !data);
 	return 0;
 }
 
@@ -8379,8 +8603,11 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 			wake_up(&ctx->sqo_wait);
 		submitted = to_submit;
 	} else if (to_submit) {
+		ret = io_uring_add_task_file(f.file);
+		if (unlikely(ret))
+			goto out;
 		mutex_lock(&ctx->uring_lock);
-		submitted = io_submit_sqes(ctx, to_submit, f.file, fd);
+		submitted = io_submit_sqes(ctx, to_submit);
 		mutex_unlock(&ctx->uring_lock);
 
 		if (submitted != to_submit)
@@ -8590,6 +8817,7 @@ static int io_uring_get_fd(struct io_ring_ctx *ctx)
 	file = anon_inode_getfile("[io_uring]", &io_uring_fops, ctx,
 					O_RDWR | O_CLOEXEC);
 	if (IS_ERR(file)) {
+err_fd:
 		put_unused_fd(ret);
 		ret = PTR_ERR(file);
 		goto err;
@@ -8598,6 +8826,10 @@ static int io_uring_get_fd(struct io_ring_ctx *ctx)
 #if defined(CONFIG_UNIX)
 	ctx->ring_sock->file = file;
 #endif
+	if (unlikely(io_uring_add_task_file(file))) {
+		file = ERR_PTR(-ENOMEM);
+		goto err_fd;
+	}
 	fd_install(ret, file);
 	return ret;
 err:
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
new file mode 100644
index 000000000000..c09135a1ef13
--- /dev/null
+++ b/include/linux/io_uring.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _LINUX_IO_URING_H
+#define _LINUX_IO_URING_H
+
+#include <linux/sched.h>
+#include <linux/xarray.h>
+#include <linux/percpu-refcount.h>
+
+struct io_uring_task {
+	/* submission side */
+	struct xarray		xa;
+	struct wait_queue_head	wait;
+	struct file		*last;
+	atomic_long_t		req_issue;
+
+	/* completion side */
+	bool			in_idle ____cacheline_aligned_in_smp;
+	atomic_long_t		req_complete;
+};
+
+#if defined(CONFIG_IO_URING)
+void __io_uring_task_cancel(void);
+void __io_uring_files_cancel(struct files_struct *files);
+void __io_uring_free(struct task_struct *tsk);
+
+static inline void io_uring_task_cancel(void)
+{
+	if (current->io_uring && !xa_empty(&current->io_uring->xa))
+		__io_uring_task_cancel();
+}
+static inline void io_uring_files_cancel(struct files_struct *files)
+{
+	if (current->io_uring && !xa_empty(&current->io_uring->xa))
+		__io_uring_files_cancel(files);
+}
+static inline void io_uring_free(struct task_struct *tsk)
+{
+	if (tsk->io_uring)
+		__io_uring_free(tsk);
+}
+#else
+static inline void io_uring_task_cancel(void)
+{
+}
+static inline void io_uring_files_cancel(struct files_struct *files)
+{
+}
+static inline void io_uring_free(struct task_struct *tsk)
+{
+}
+#endif
+
+#endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index afe01e232935..8bf2295ebee4 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -63,6 +63,7 @@ struct sighand_struct;
 struct signal_struct;
 struct task_delay_info;
 struct task_group;
+struct io_uring_task;
 
 /*
  * Task state bitmask. NOTE! These bits are also
@@ -935,6 +936,10 @@ struct task_struct {
 	/* Open file information: */
 	struct files_struct		*files;
 
+#ifdef CONFIG_IO_URING
+	struct io_uring_task		*io_uring;
+#endif
+
 	/* Namespaces: */
 	struct nsproxy			*nsproxy;
 
diff --git a/init/init_task.c b/init/init_task.c
index f6889fce64af..a56f0abb63e9 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -114,6 +114,9 @@ struct task_struct init_task
 	.thread		= INIT_THREAD,
 	.fs		= &init_fs,
 	.files		= &init_files,
+#ifdef CONFIG_IO_URING
+	.io_uring	= NULL,
+#endif
 	.signal		= &init_signals,
 	.sighand	= &init_sighand,
 	.nsproxy	= &init_nsproxy,
diff --git a/kernel/fork.c b/kernel/fork.c
index da8d360fb032..a3795aaaab5c 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -95,6 +95,7 @@
 #include <linux/stackleak.h>
 #include <linux/kasan.h>
 #include <linux/scs.h>
+#include <linux/io_uring.h>
 
 #include <asm/pgalloc.h>
 #include <linux/uaccess.h>
@@ -728,6 +729,7 @@ void __put_task_struct(struct task_struct *tsk)
 	WARN_ON(refcount_read(&tsk->usage));
 	WARN_ON(tsk == current);
 
+	io_uring_free(tsk);
 	cgroup_free(tsk);
 	task_numa_free(tsk, true);
 	security_task_free(tsk);
@@ -1983,6 +1985,10 @@ static __latent_entropy struct task_struct *copy_process(
 	p->vtime.state = VTIME_INACTIVE;
 #endif
 
+#ifdef CONFIG_IO_URING
+	p->io_uring = NULL;
+#endif
+
 #if defined(SPLIT_RSS_COUNTING)
 	memset(&p->rss_stat, 0, sizeof(p->rss_stat));
 #endif
-- 
cgit v1.2.3


From a3ec60054082ca2c2145ba487f9fc4de904e2b03 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Fri, 18 Sep 2020 20:41:00 -0600
Subject: io_uring: move io_uring_get_socket() into io_uring.h

Now we have a io_uring kernel header, move this definition out of fs.h
and into io_uring.h where it belongs.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/fs.h       | 9 ---------
 include/linux/io_uring.h | 5 +++++
 net/unix/scm.c           | 1 +
 3 files changed, 6 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7519ae003a08..1c4068428461 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3514,15 +3514,6 @@ extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len,
 extern int generic_fadvise(struct file *file, loff_t offset, loff_t len,
 			   int advice);
 
-#if defined(CONFIG_IO_URING)
-extern struct sock *io_uring_get_socket(struct file *file);
-#else
-static inline struct sock *io_uring_get_socket(struct file *file)
-{
-	return NULL;
-}
-#endif
-
 int vfs_ioc_setflags_prepare(struct inode *inode, unsigned int oldflags,
 			     unsigned int flags);
 
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index c09135a1ef13..96315cfaf6d1 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -19,6 +19,7 @@ struct io_uring_task {
 };
 
 #if defined(CONFIG_IO_URING)
+struct sock *io_uring_get_socket(struct file *file);
 void __io_uring_task_cancel(void);
 void __io_uring_files_cancel(struct files_struct *files);
 void __io_uring_free(struct task_struct *tsk);
@@ -39,6 +40,10 @@ static inline void io_uring_free(struct task_struct *tsk)
 		__io_uring_free(tsk);
 }
 #else
+static inline struct sock *io_uring_get_socket(struct file *file)
+{
+	return NULL;
+}
 static inline void io_uring_task_cancel(void)
 {
 }
diff --git a/net/unix/scm.c b/net/unix/scm.c
index 8c40f2b32392..052ae709ce28 100644
--- a/net/unix/scm.c
+++ b/net/unix/scm.c
@@ -8,6 +8,7 @@
 #include <net/af_unix.h>
 #include <net/scm.h>
 #include <linux/init.h>
+#include <linux/io_uring.h>
 
 #include "scm.h"
 
-- 
cgit v1.2.3


From ce71bfea207b4d7c21d36f24ec37618ffcea1da8 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Mon, 31 Aug 2020 12:08:10 -0600
Subject: fs: align IOCB_* flags with RWF_* flags

We have a set of flags that are shared between the two and inherired
in kiocb_set_rw_flags(), but we check and set these individually.
Reorder the IOCB flags so that the bottom part of the space is synced
with the RWF flag space, and then we can do them all in one mask and
set operation.

The only exception is RWF_SYNC, which needs to mark IOCB_SYNC and
IOCB_DSYNC. Do that one separately.

This shaves 15 bytes of text from kiocb_set_rw_flags() for me.

Suggested-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/fs.h | 37 +++++++++++++++++++------------------
 1 file changed, 19 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 1c4068428461..4ebc14dee421 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -310,17 +310,20 @@ enum rw_hint {
 	WRITE_LIFE_EXTREME	= RWH_WRITE_LIFE_EXTREME,
 };
 
-#define IOCB_EVENTFD		(1 << 0)
-#define IOCB_APPEND		(1 << 1)
-#define IOCB_DIRECT		(1 << 2)
-#define IOCB_HIPRI		(1 << 3)
-#define IOCB_DSYNC		(1 << 4)
-#define IOCB_SYNC		(1 << 5)
-#define IOCB_WRITE		(1 << 6)
-#define IOCB_NOWAIT		(1 << 7)
+/* Match RWF_* bits to IOCB bits */
+#define IOCB_HIPRI		(__force int) RWF_HIPRI
+#define IOCB_DSYNC		(__force int) RWF_DSYNC
+#define IOCB_SYNC		(__force int) RWF_SYNC
+#define IOCB_NOWAIT		(__force int) RWF_NOWAIT
+#define IOCB_APPEND		(__force int) RWF_APPEND
+
+/* non-RWF related bits - start at 16 */
+#define IOCB_EVENTFD		(1 << 16)
+#define IOCB_DIRECT		(1 << 17)
+#define IOCB_WRITE		(1 << 18)
 /* iocb->ki_waitq is valid */
-#define IOCB_WAITQ		(1 << 8)
-#define IOCB_NOIO		(1 << 9)
+#define IOCB_WAITQ		(1 << 19)
+#define IOCB_NOIO		(1 << 20)
 
 struct kiocb {
 	struct file		*ki_filp;
@@ -3317,6 +3320,9 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags)
 {
 	int kiocb_flags = 0;
 
+	/* make sure there's no overlap between RWF and private IOCB flags */
+	BUILD_BUG_ON((__force int) RWF_SUPPORTED & IOCB_EVENTFD);
+
 	if (!flags)
 		return 0;
 	if (unlikely(flags & ~RWF_SUPPORTED))
@@ -3325,16 +3331,11 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags)
 	if (flags & RWF_NOWAIT) {
 		if (!(ki->ki_filp->f_mode & FMODE_NOWAIT))
 			return -EOPNOTSUPP;
-		kiocb_flags |= IOCB_NOWAIT | IOCB_NOIO;
+		kiocb_flags |= IOCB_NOIO;
 	}
-	if (flags & RWF_HIPRI)
-		kiocb_flags |= IOCB_HIPRI;
-	if (flags & RWF_DSYNC)
-		kiocb_flags |= IOCB_DSYNC;
+	kiocb_flags |= (__force int) (flags & RWF_SUPPORTED);
 	if (flags & RWF_SYNC)
-		kiocb_flags |= (IOCB_DSYNC | IOCB_SYNC);
-	if (flags & RWF_APPEND)
-		kiocb_flags |= IOCB_APPEND;
+		kiocb_flags |= IOCB_DSYNC;
 
 	ki->ki_flags |= kiocb_flags;
 	return 0;
-- 
cgit v1.2.3


From 7cd7becdddb00620fb8deb74e6fe4e5a1522ae5a Mon Sep 17 00:00:00 2001
From: sunils <sunils@nvidia.com>
Date: Fri, 11 Sep 2020 00:13:26 +0300
Subject: net/mlx5: E-switch, Use PF num in metadata reg c0

Currently only 256 vports can be supported as only 8 bits are
reserved for them and 8 bits are reserved for vhca_ids in
metadata reg c0. To support more than 256 vports, replace
vhca_id with a unique shorter 4-bit PF number which covers
upto 16 PF's. Use remaining 12 bits for vports ranging 1-4095.
This will continue to generate unique metadata even if
multiple PCI devices have same switch_id.

Signed-off-by: sunils <sunils@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Vu Pham <vuhuong@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 36 +++++++++++-----------
 include/linux/mlx5/eswitch.h                       | 15 ++++-----
 2 files changed, 26 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index ffd5d540a19e..6b49c0d59099 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -2019,31 +2019,31 @@ esw_check_vport_match_metadata_supported(const struct mlx5_eswitch *esw)
 
 u32 mlx5_esw_match_metadata_alloc(struct mlx5_eswitch *esw)
 {
-	u32 num_vports = GENMASK(ESW_VPORT_BITS - 1, 0) - 1;
-	u32 vhca_id_mask = GENMASK(ESW_VHCA_ID_BITS - 1, 0);
-	u32 vhca_id = MLX5_CAP_GEN(esw->dev, vhca_id);
-	u32 start;
-	u32 end;
+	u32 vport_end_ida = (1 << ESW_VPORT_BITS) - 1;
+	u32 max_pf_num = (1 << ESW_PFNUM_BITS) - 1;
+	u32 pf_num;
 	int id;
 
-	/* Make sure the vhca_id fits the ESW_VHCA_ID_BITS */
-	WARN_ON_ONCE(vhca_id >= BIT(ESW_VHCA_ID_BITS));
-
-	/* Trim vhca_id to ESW_VHCA_ID_BITS */
-	vhca_id &= vhca_id_mask;
-
-	start = (vhca_id << ESW_VPORT_BITS);
-	end = start + num_vports;
-	if (!vhca_id)
-		start += 1; /* zero is reserved/invalid metadata */
-	id = ida_alloc_range(&esw->offloads.vport_metadata_ida, start, end, GFP_KERNEL);
+	/* Only 4 bits of pf_num */
+	pf_num = PCI_FUNC(esw->dev->pdev->devfn);
+	if (pf_num > max_pf_num)
+		return 0;
 
-	return (id < 0) ? 0 : id;
+	/* Metadata is 4 bits of PFNUM and 12 bits of unique id */
+	/* Use only non-zero vport_id (1-4095) for all PF's */
+	id = ida_alloc_range(&esw->offloads.vport_metadata_ida, 1, vport_end_ida, GFP_KERNEL);
+	if (id < 0)
+		return 0;
+	id = (pf_num << ESW_VPORT_BITS) | id;
+	return id;
 }
 
 void mlx5_esw_match_metadata_free(struct mlx5_eswitch *esw, u32 metadata)
 {
-	ida_free(&esw->offloads.vport_metadata_ida, metadata);
+	u32 vport_bit_mask = (1 << ESW_VPORT_BITS) - 1;
+
+	/* Metadata contains only 12 bits of actual ida id */
+	ida_free(&esw->offloads.vport_metadata_ida, metadata & vport_bit_mask);
 }
 
 static int esw_offloads_vport_metadata_setup(struct mlx5_eswitch *esw,
diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h
index c16827eeba9c..b0ae8020f13e 100644
--- a/include/linux/mlx5/eswitch.h
+++ b/include/linux/mlx5/eswitch.h
@@ -74,15 +74,16 @@ bool mlx5_eswitch_reg_c1_loopback_enabled(const struct mlx5_eswitch *esw);
 bool mlx5_eswitch_vport_match_metadata_enabled(const struct mlx5_eswitch *esw);
 
 /* Reg C0 usage:
- * Reg C0 = < ESW_VHCA_ID_BITS(8) | ESW_VPORT BITS(8) | ESW_CHAIN_TAG(16) >
+ * Reg C0 = < ESW_PFNUM_BITS(4) | ESW_VPORT BITS(12) | ESW_CHAIN_TAG(16) >
  *
- * Highest 8 bits of the reg c0 is the vhca_id, next 8 bits is vport_num,
- * the rest (lowest 16 bits) is left for tc chain tag restoration.
- * VHCA_ID + VPORT comprise the SOURCE_PORT matching.
+ * Highest 4 bits of the reg c0 is the PF_NUM (range 0-15), 12 bits of
+ * unique non-zero vport id (range 1-4095). The rest (lowest 16 bits) is left
+ * for tc chain tag restoration.
+ * PFNUM + VPORT comprise the SOURCE_PORT matching.
  */
-#define ESW_VHCA_ID_BITS 8
-#define ESW_VPORT_BITS 8
-#define ESW_SOURCE_PORT_METADATA_BITS (ESW_VHCA_ID_BITS + ESW_VPORT_BITS)
+#define ESW_VPORT_BITS 12
+#define ESW_PFNUM_BITS 4
+#define ESW_SOURCE_PORT_METADATA_BITS (ESW_PFNUM_BITS + ESW_VPORT_BITS)
 #define ESW_SOURCE_PORT_METADATA_OFFSET (32 - ESW_SOURCE_PORT_METADATA_BITS)
 #define ESW_CHAIN_TAG_METADATA_BITS (32 - ESW_SOURCE_PORT_METADATA_BITS)
 #define ESW_CHAIN_TAG_METADATA_MASK GENMASK(ESW_CHAIN_TAG_METADATA_BITS - 1,\
-- 
cgit v1.2.3


From 23cc3493b5e107b8deb697cf3157a07276b5eff7 Mon Sep 17 00:00:00 2001
From: Jacob Pan <jacob.pan.linux@gmail.com>
Date: Fri, 25 Sep 2020 09:32:45 -0700
Subject: iommu/uapi: Rename uapi functions

User APIs such as iommu_sva_unbind_gpasid() may also be used by the
kernel. Since we introduced user pointer to the UAPI functions,
in-kernel callers cannot share the same APIs. In-kernel callers are also
trusted, there is no need to validate the data.

We plan to have two flavors of the same API functions, one called
through ioctls, carrying a user pointer and one called directly with
valid IOMMU UAPI structs. To differentiate both, let's rename existing
functions with an iommu_uapi_ prefix.

Suggested-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Link: https://lore.kernel.org/r/1601051567-54787-5-git-send-email-jacob.jun.pan@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/iommu.c | 18 +++++++++---------
 include/linux/iommu.h | 31 ++++++++++++++++---------------
 2 files changed, 25 insertions(+), 24 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 6c14c88cd525..e412a0abfefa 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -1961,35 +1961,35 @@ out_unlock:
 }
 EXPORT_SYMBOL_GPL(iommu_attach_device);
 
-int iommu_cache_invalidate(struct iommu_domain *domain, struct device *dev,
-			   struct iommu_cache_invalidate_info *inv_info)
+int iommu_uapi_cache_invalidate(struct iommu_domain *domain, struct device *dev,
+				struct iommu_cache_invalidate_info *inv_info)
 {
 	if (unlikely(!domain->ops->cache_invalidate))
 		return -ENODEV;
 
 	return domain->ops->cache_invalidate(domain, dev, inv_info);
 }
-EXPORT_SYMBOL_GPL(iommu_cache_invalidate);
+EXPORT_SYMBOL_GPL(iommu_uapi_cache_invalidate);
 
-int iommu_sva_bind_gpasid(struct iommu_domain *domain,
-			   struct device *dev, struct iommu_gpasid_bind_data *data)
+int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
+			       struct device *dev, struct iommu_gpasid_bind_data *data)
 {
 	if (unlikely(!domain->ops->sva_bind_gpasid))
 		return -ENODEV;
 
 	return domain->ops->sva_bind_gpasid(domain, dev, data);
 }
-EXPORT_SYMBOL_GPL(iommu_sva_bind_gpasid);
+EXPORT_SYMBOL_GPL(iommu_uapi_sva_bind_gpasid);
 
-int iommu_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev,
-			     ioasid_t pasid)
+int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev,
+				 ioasid_t pasid)
 {
 	if (unlikely(!domain->ops->sva_unbind_gpasid))
 		return -ENODEV;
 
 	return domain->ops->sva_unbind_gpasid(dev, pasid);
 }
-EXPORT_SYMBOL_GPL(iommu_sva_unbind_gpasid);
+EXPORT_SYMBOL_GPL(iommu_uapi_sva_unbind_gpasid);
 
 static void __iommu_detach_device(struct iommu_domain *domain,
 				  struct device *dev)
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 2ad26d8b4ab9..d18de2afa6fb 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -424,13 +424,13 @@ extern int iommu_attach_device(struct iommu_domain *domain,
 			       struct device *dev);
 extern void iommu_detach_device(struct iommu_domain *domain,
 				struct device *dev);
-extern int iommu_cache_invalidate(struct iommu_domain *domain,
-				  struct device *dev,
-				  struct iommu_cache_invalidate_info *inv_info);
-extern int iommu_sva_bind_gpasid(struct iommu_domain *domain,
-		struct device *dev, struct iommu_gpasid_bind_data *data);
-extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
-				struct device *dev, ioasid_t pasid);
+extern int iommu_uapi_cache_invalidate(struct iommu_domain *domain,
+				       struct device *dev,
+				       struct iommu_cache_invalidate_info *inv_info);
+extern int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
+				      struct device *dev, struct iommu_gpasid_bind_data *data);
+extern int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain,
+					struct device *dev, ioasid_t pasid);
 extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev);
 extern struct iommu_domain *iommu_get_dma_domain(struct device *dev);
 extern int iommu_map(struct iommu_domain *domain, unsigned long iova,
@@ -1032,21 +1032,22 @@ static inline int iommu_sva_get_pasid(struct iommu_sva *handle)
 	return IOMMU_PASID_INVALID;
 }
 
-static inline int
-iommu_cache_invalidate(struct iommu_domain *domain,
-		       struct device *dev,
-		       struct iommu_cache_invalidate_info *inv_info)
+static inline int iommu_uapi_cache_invalidate(struct iommu_domain *domain,
+					      struct device *dev,
+					      struct iommu_cache_invalidate_info *inv_info)
 {
 	return -ENODEV;
 }
-static inline int iommu_sva_bind_gpasid(struct iommu_domain *domain,
-				struct device *dev, struct iommu_gpasid_bind_data *data)
+
+static inline int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
+					     struct device *dev,
+					     struct iommu_gpasid_bind_data *data)
 {
 	return -ENODEV;
 }
 
-static inline int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
-					   struct device *dev, int pasid)
+static inline int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain,
+					       struct device *dev, int pasid)
 {
 	return -ENODEV;
 }
-- 
cgit v1.2.3


From d90573812eea63c6bc8ab8a38f661b4c27c3cdc0 Mon Sep 17 00:00:00 2001
From: Jacob Pan <jacob.pan.linux@gmail.com>
Date: Fri, 25 Sep 2020 09:32:46 -0700
Subject: iommu/uapi: Handle data and argsz filled by users

IOMMU user APIs are responsible for processing user data. This patch
changes the interface such that user pointers can be passed into IOMMU
code directly. Separate kernel APIs without user pointers are introduced
for in-kernel users of the UAPI functionality.

IOMMU UAPI data has a user filled argsz field which indicates the data
length of the structure. User data is not trusted, argsz must be
validated based on the current kernel data size, mandatory data size,
and feature flags.

User data may also be extended, resulting in possible argsz increase.
Backward compatibility is ensured based on size and flags (or
the functional equivalent fields) checking.

This patch adds sanity checks in the IOMMU layer. In addition to argsz,
reserved/unused fields in padding, flags, and version are also checked.
Details are documented in Documentation/userspace-api/iommu.rst

Signed-off-by: Liu Yi L <yi.l.liu@intel.com>
Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Reviewed-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Link: https://lore.kernel.org/r/1601051567-54787-6-git-send-email-jacob.jun.pan@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/iommu.c      | 194 +++++++++++++++++++++++++++++++++++++++++++--
 include/linux/iommu.h      |  28 ++++---
 include/uapi/linux/iommu.h |   1 +
 3 files changed, 207 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index e412a0abfefa..6d847027d35e 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -1961,34 +1961,214 @@ out_unlock:
 }
 EXPORT_SYMBOL_GPL(iommu_attach_device);
 
+/*
+ * Check flags and other user provided data for valid combinations. We also
+ * make sure no reserved fields or unused flags are set. This is to ensure
+ * not breaking userspace in the future when these fields or flags are used.
+ */
+static int iommu_check_cache_invl_data(struct iommu_cache_invalidate_info *info)
+{
+	u32 mask;
+	int i;
+
+	if (info->version != IOMMU_CACHE_INVALIDATE_INFO_VERSION_1)
+		return -EINVAL;
+
+	mask = (1 << IOMMU_CACHE_INV_TYPE_NR) - 1;
+	if (info->cache & ~mask)
+		return -EINVAL;
+
+	if (info->granularity >= IOMMU_INV_GRANU_NR)
+		return -EINVAL;
+
+	switch (info->granularity) {
+	case IOMMU_INV_GRANU_ADDR:
+		if (info->cache & IOMMU_CACHE_INV_TYPE_PASID)
+			return -EINVAL;
+
+		mask = IOMMU_INV_ADDR_FLAGS_PASID |
+			IOMMU_INV_ADDR_FLAGS_ARCHID |
+			IOMMU_INV_ADDR_FLAGS_LEAF;
+
+		if (info->granu.addr_info.flags & ~mask)
+			return -EINVAL;
+		break;
+	case IOMMU_INV_GRANU_PASID:
+		mask = IOMMU_INV_PASID_FLAGS_PASID |
+			IOMMU_INV_PASID_FLAGS_ARCHID;
+		if (info->granu.pasid_info.flags & ~mask)
+			return -EINVAL;
+
+		break;
+	case IOMMU_INV_GRANU_DOMAIN:
+		if (info->cache & IOMMU_CACHE_INV_TYPE_DEV_IOTLB)
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Check reserved padding fields */
+	for (i = 0; i < sizeof(info->padding); i++) {
+		if (info->padding[i])
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
 int iommu_uapi_cache_invalidate(struct iommu_domain *domain, struct device *dev,
-				struct iommu_cache_invalidate_info *inv_info)
+				void __user *uinfo)
 {
+	struct iommu_cache_invalidate_info inv_info = { 0 };
+	u32 minsz;
+	int ret;
+
 	if (unlikely(!domain->ops->cache_invalidate))
 		return -ENODEV;
 
-	return domain->ops->cache_invalidate(domain, dev, inv_info);
+	/*
+	 * No new spaces can be added before the variable sized union, the
+	 * minimum size is the offset to the union.
+	 */
+	minsz = offsetof(struct iommu_cache_invalidate_info, granu);
+
+	/* Copy minsz from user to get flags and argsz */
+	if (copy_from_user(&inv_info, uinfo, minsz))
+		return -EFAULT;
+
+	/* Fields before the variable size union are mandatory */
+	if (inv_info.argsz < minsz)
+		return -EINVAL;
+
+	/* PASID and address granu require additional info beyond minsz */
+	if (inv_info.granularity == IOMMU_INV_GRANU_PASID &&
+	    inv_info.argsz < offsetofend(struct iommu_cache_invalidate_info, granu.pasid_info))
+		return -EINVAL;
+
+	if (inv_info.granularity == IOMMU_INV_GRANU_ADDR &&
+	    inv_info.argsz < offsetofend(struct iommu_cache_invalidate_info, granu.addr_info))
+		return -EINVAL;
+
+	/*
+	 * User might be using a newer UAPI header which has a larger data
+	 * size, we shall support the existing flags within the current
+	 * size. Copy the remaining user data _after_ minsz but not more
+	 * than the current kernel supported size.
+	 */
+	if (copy_from_user((void *)&inv_info + minsz, uinfo + minsz,
+			   min_t(u32, inv_info.argsz, sizeof(inv_info)) - minsz))
+		return -EFAULT;
+
+	/* Now the argsz is validated, check the content */
+	ret = iommu_check_cache_invl_data(&inv_info);
+	if (ret)
+		return ret;
+
+	return domain->ops->cache_invalidate(domain, dev, &inv_info);
 }
 EXPORT_SYMBOL_GPL(iommu_uapi_cache_invalidate);
 
-int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
-			       struct device *dev, struct iommu_gpasid_bind_data *data)
+static int iommu_check_bind_data(struct iommu_gpasid_bind_data *data)
+{
+	u32 mask;
+	int i;
+
+	if (data->version != IOMMU_GPASID_BIND_VERSION_1)
+		return -EINVAL;
+
+	/* Check the range of supported formats */
+	if (data->format >= IOMMU_PASID_FORMAT_LAST)
+		return -EINVAL;
+
+	/* Check all flags */
+	mask = IOMMU_SVA_GPASID_VAL;
+	if (data->flags & ~mask)
+		return -EINVAL;
+
+	/* Check reserved padding fields */
+	for (i = 0; i < sizeof(data->padding); i++) {
+		if (data->padding[i])
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int iommu_sva_prepare_bind_data(void __user *udata,
+				       struct iommu_gpasid_bind_data *data)
+{
+	u32 minsz;
+
+	/*
+	 * No new spaces can be added before the variable sized union, the
+	 * minimum size is the offset to the union.
+	 */
+	minsz = offsetof(struct iommu_gpasid_bind_data, vendor);
+
+	/* Copy minsz from user to get flags and argsz */
+	if (copy_from_user(data, udata, minsz))
+		return -EFAULT;
+
+	/* Fields before the variable size union are mandatory */
+	if (data->argsz < minsz)
+		return -EINVAL;
+	/*
+	 * User might be using a newer UAPI header, we shall let IOMMU vendor
+	 * driver decide on what size it needs. Since the guest PASID bind data
+	 * can be vendor specific, larger argsz could be the result of extension
+	 * for one vendor but it should not affect another vendor.
+	 * Copy the remaining user data _after_ minsz
+	 */
+	if (copy_from_user((void *)data + minsz, udata + minsz,
+			   min_t(u32, data->argsz, sizeof(*data)) - minsz))
+		return -EFAULT;
+
+	return iommu_check_bind_data(data);
+}
+
+int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain, struct device *dev,
+			       void __user *udata)
 {
+	struct iommu_gpasid_bind_data data = { 0 };
+	int ret;
+
 	if (unlikely(!domain->ops->sva_bind_gpasid))
 		return -ENODEV;
 
-	return domain->ops->sva_bind_gpasid(domain, dev, data);
+	ret = iommu_sva_prepare_bind_data(udata, &data);
+	if (ret)
+		return ret;
+
+	return domain->ops->sva_bind_gpasid(domain, dev, &data);
 }
 EXPORT_SYMBOL_GPL(iommu_uapi_sva_bind_gpasid);
 
-int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev,
-				 ioasid_t pasid)
+int iommu_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev,
+			     ioasid_t pasid)
 {
 	if (unlikely(!domain->ops->sva_unbind_gpasid))
 		return -ENODEV;
 
 	return domain->ops->sva_unbind_gpasid(dev, pasid);
 }
+EXPORT_SYMBOL_GPL(iommu_sva_unbind_gpasid);
+
+int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev,
+				 void __user *udata)
+{
+	struct iommu_gpasid_bind_data data = { 0 };
+	int ret;
+
+	if (unlikely(!domain->ops->sva_bind_gpasid))
+		return -ENODEV;
+
+	ret = iommu_sva_prepare_bind_data(udata, &data);
+	if (ret)
+		return ret;
+
+	return iommu_sva_unbind_gpasid(domain, dev, data.hpasid);
+}
 EXPORT_SYMBOL_GPL(iommu_uapi_sva_unbind_gpasid);
 
 static void __iommu_detach_device(struct iommu_domain *domain,
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index d18de2afa6fb..82876f682367 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -426,11 +426,14 @@ extern void iommu_detach_device(struct iommu_domain *domain,
 				struct device *dev);
 extern int iommu_uapi_cache_invalidate(struct iommu_domain *domain,
 				       struct device *dev,
-				       struct iommu_cache_invalidate_info *inv_info);
+				       void __user *uinfo);
+
 extern int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
-				      struct device *dev, struct iommu_gpasid_bind_data *data);
+				      struct device *dev, void __user *udata);
 extern int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain,
-					struct device *dev, ioasid_t pasid);
+					struct device *dev, void __user *udata);
+extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
+				   struct device *dev, ioasid_t pasid);
 extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev);
 extern struct iommu_domain *iommu_get_dma_domain(struct device *dev);
 extern int iommu_map(struct iommu_domain *domain, unsigned long iova,
@@ -1032,22 +1035,29 @@ static inline int iommu_sva_get_pasid(struct iommu_sva *handle)
 	return IOMMU_PASID_INVALID;
 }
 
-static inline int iommu_uapi_cache_invalidate(struct iommu_domain *domain,
-					      struct device *dev,
-					      struct iommu_cache_invalidate_info *inv_info)
+static inline int
+iommu_uapi_cache_invalidate(struct iommu_domain *domain,
+			    struct device *dev,
+			    struct iommu_cache_invalidate_info *inv_info)
 {
 	return -ENODEV;
 }
 
 static inline int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
-					     struct device *dev,
-					     struct iommu_gpasid_bind_data *data)
+					     struct device *dev, void __user *udata)
 {
 	return -ENODEV;
 }
 
 static inline int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain,
-					       struct device *dev, int pasid)
+					       struct device *dev, void __user *udata)
+{
+	return -ENODEV;
+}
+
+static inline int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
+					  struct device *dev,
+					  ioasid_t pasid)
 {
 	return -ENODEV;
 }
diff --git a/include/uapi/linux/iommu.h b/include/uapi/linux/iommu.h
index 5946779ac1f9..66d4ca40b40f 100644
--- a/include/uapi/linux/iommu.h
+++ b/include/uapi/linux/iommu.h
@@ -322,6 +322,7 @@ struct iommu_gpasid_bind_data {
 #define IOMMU_GPASID_BIND_VERSION_1	1
 	__u32 version;
 #define IOMMU_PASID_FORMAT_INTEL_VTD	1
+#define IOMMU_PASID_FORMAT_LAST		2
 	__u32 format;
 	__u32 addr_width;
 #define IOMMU_SVA_GPASID_VAL	(1 << 0) /* guest PASID valid */
-- 
cgit v1.2.3


From 88451f2cd3cec2abc30debdf129422d2699d1eba Mon Sep 17 00:00:00 2001
From: Zqiang <qiang.zhang@windriver.com>
Date: Tue, 8 Sep 2020 14:27:09 +0800
Subject: debugobjects: Free per CPU pool after CPU unplug

If a CPU is offlined the debug objects per CPU pool is not cleaned up. If
the CPU is never onlined again then the objects in the pool are wasted.

Add a CPU hotplug callback which is invoked after the CPU is dead to free
the pool.

[ tglx: Massaged changelog and added comment about remote access safety ]

Signed-off-by: Zqiang <qiang.zhang@windriver.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Waiman Long <longman@redhat.com>
Link: https://lore.kernel.org/r/20200908062709.11441-1-qiang.zhang@windriver.com
---
 include/linux/cpuhotplug.h |  1 +
 lib/debugobjects.c         | 25 +++++++++++++++++++++++++
 2 files changed, 26 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index bf9181cef444..6f524bbf71a2 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -36,6 +36,7 @@ enum cpuhp_state {
 	CPUHP_X86_MCE_DEAD,
 	CPUHP_VIRT_NET_DEAD,
 	CPUHP_SLUB_DEAD,
+	CPUHP_DEBUG_OBJ_DEAD,
 	CPUHP_MM_WRITEBACK_DEAD,
 	CPUHP_MM_VMSTAT_DEAD,
 	CPUHP_SOFTIRQ_DEAD,
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index e2a3171b6c63..9e14ae02306b 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -19,6 +19,7 @@
 #include <linux/slab.h>
 #include <linux/hash.h>
 #include <linux/kmemleak.h>
+#include <linux/cpu.h>
 
 #define ODEBUG_HASH_BITS	14
 #define ODEBUG_HASH_SIZE	(1 << ODEBUG_HASH_BITS)
@@ -433,6 +434,25 @@ static void free_object(struct debug_obj *obj)
 	}
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
+static int object_cpu_offline(unsigned int cpu)
+{
+	struct debug_percpu_free *percpu_pool;
+	struct hlist_node *tmp;
+	struct debug_obj *obj;
+
+	/* Remote access is safe as the CPU is dead already */
+	percpu_pool = per_cpu_ptr(&percpu_obj_pool, cpu);
+	hlist_for_each_entry_safe(obj, tmp, &percpu_pool->free_objs, node) {
+		hlist_del(&obj->node);
+		kmem_cache_free(obj_cache, obj);
+	}
+	percpu_pool->obj_free = 0;
+
+	return 0;
+}
+#endif
+
 /*
  * We run out of memory. That means we probably have tons of objects
  * allocated.
@@ -1367,6 +1387,11 @@ void __init debug_objects_mem_init(void)
 	} else
 		debug_objects_selftest();
 
+#ifdef CONFIG_HOTPLUG_CPU
+	cpuhp_setup_state_nocalls(CPUHP_DEBUG_OBJ_DEAD, "object:offline", NULL,
+					object_cpu_offline);
+#endif
+
 	/*
 	 * Increase the thresholds for allocating and freeing objects
 	 * according to the number of possible CPUs available in the system.
-- 
cgit v1.2.3


From 6d849653b00f2336efcd371fe85a7eb31bb094e9 Mon Sep 17 00:00:00 2001
From: AngeloGioacchino Del Regno <kholk11@gmail.com>
Date: Sat, 26 Sep 2020 14:55:47 +0200
Subject: regulator: qcom_smd: Add PM660/PM660L regulator support

The PM660 and PM660L are a very very common PMIC combo, found on
boards using the SDM630, SDM636, SDM660 (and SDA variants) SoC.

PM660 provides 6 SMPS and 19 LDOs (of which one is unaccesible),
while PM660L provides 5 SMPS (of which S3 and S4 are combined),
10 LDOs and a Buck-or-Boost (BoB) regulator.

The PM660L IC also provides other regulators that are very
specialized (for example, for the display) and will be managed
in the other appropriate drivers (for example, labibb).

Signed-off-by: AngeloGioacchino Del Regno <kholk11@gmail.com>
Link: https://lore.kernel.org/r/20200926125549.13191-6-kholk11@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/qcom_smd-regulator.c | 113 +++++++++++++++++++++++++++++++++
 include/linux/soc/qcom/smd-rpm.h       |   4 ++
 2 files changed, 117 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/regulator/qcom_smd-regulator.c b/drivers/regulator/qcom_smd-regulator.c
index a87b56bc29fa..faa99690b7b3 100644
--- a/drivers/regulator/qcom_smd-regulator.c
+++ b/drivers/regulator/qcom_smd-regulator.c
@@ -541,6 +541,69 @@ static const struct regulator_desc pmi8998_bob = {
 	.ops = &rpm_bob_ops,
 };
 
+static const struct regulator_desc pm660_ftsmps = {
+	.linear_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(355000, 0, 199, 5000),
+	},
+	.n_linear_ranges = 1,
+	.n_voltages = 200,
+	.ops = &rpm_smps_ldo_ops,
+};
+
+static const struct regulator_desc pm660_hfsmps = {
+	.linear_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(320000, 0, 216, 8000),
+	},
+	.n_linear_ranges = 1,
+	.n_voltages = 217,
+	.ops = &rpm_smps_ldo_ops,
+};
+
+static const struct regulator_desc pm660_ht_nldo = {
+	.linear_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(312000, 0, 124, 8000),
+	},
+	.n_linear_ranges = 1,
+	.n_voltages = 125,
+	.ops = &rpm_smps_ldo_ops,
+};
+
+static const struct regulator_desc pm660_ht_lvpldo = {
+	.linear_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(1504000, 0, 62, 8000),
+	},
+	.n_linear_ranges = 1,
+	.n_voltages = 63,
+	.ops = &rpm_smps_ldo_ops,
+};
+
+static const struct regulator_desc pm660_nldo660 = {
+	.linear_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(320000, 0, 123, 8000),
+	},
+	.n_linear_ranges = 1,
+	.n_voltages = 124,
+	.ops = &rpm_smps_ldo_ops,
+};
+
+static const struct regulator_desc pm660_pldo660 = {
+	.linear_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(1504000, 0, 255, 8000),
+	},
+	.n_linear_ranges = 1,
+	.n_voltages = 256,
+	.ops = &rpm_smps_ldo_ops,
+};
+
+static const struct regulator_desc pm660l_bob = {
+	.linear_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(1800000, 0, 84, 32000),
+	},
+	.n_linear_ranges = 1,
+	.n_voltages = 85,
+	.ops = &rpm_bob_ops,
+};
+
 static const struct regulator_desc pms405_hfsmps3 = {
 	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(320000, 0, 215, 8000),
@@ -902,6 +965,54 @@ static const struct rpm_regulator_data rpm_pmi8998_regulators[] = {
 	{}
 };
 
+static const struct rpm_regulator_data rpm_pm660_regulators[] = {
+	{ "s1", QCOM_SMD_RPM_SMPA, 1, &pm660_ftsmps, "vdd_s1" },
+	{ "s2", QCOM_SMD_RPM_SMPA, 2, &pm660_ftsmps, "vdd_s2" },
+	{ "s3", QCOM_SMD_RPM_SMPA, 3, &pm660_ftsmps, "vdd_s3" },
+	{ "s4", QCOM_SMD_RPM_SMPA, 4, &pm660_hfsmps, "vdd_s4" },
+	{ "s5", QCOM_SMD_RPM_SMPA, 5, &pm660_hfsmps, "vdd_s5" },
+	{ "s6", QCOM_SMD_RPM_SMPA, 6, &pm660_hfsmps, "vdd_s6" },
+	{ "l1", QCOM_SMD_RPM_LDOA, 1, &pm660_nldo660, "vdd_l1_l6_l7" },
+	{ "l2", QCOM_SMD_RPM_LDOA, 2, &pm660_ht_nldo, "vdd_l2_l3" },
+	{ "l3", QCOM_SMD_RPM_LDOA, 3, &pm660_nldo660, "vdd_l2_l3" },
+	/* l4 is unaccessible on PM660 */
+	{ "l5", QCOM_SMD_RPM_LDOA, 5, &pm660_ht_nldo, "vdd_l5" },
+	{ "l6", QCOM_SMD_RPM_LDOA, 6, &pm660_ht_nldo, "vdd_l1_l6_l7" },
+	{ "l7", QCOM_SMD_RPM_LDOA, 7, &pm660_ht_nldo, "vdd_l1_l6_l7" },
+	{ "l8", QCOM_SMD_RPM_LDOA, 8, &pm660_ht_lvpldo, "vdd_l8_l9_l10_l11_l12_l13_l14" },
+	{ "l9", QCOM_SMD_RPM_LDOA, 9, &pm660_ht_lvpldo, "vdd_l8_l9_l10_l11_l12_l13_l14" },
+	{ "l10", QCOM_SMD_RPM_LDOA, 10, &pm660_ht_lvpldo, "vdd_l8_l9_l10_l11_l12_l13_l14" },
+	{ "l11", QCOM_SMD_RPM_LDOA, 11, &pm660_ht_lvpldo, "vdd_l8_l9_l10_l11_l12_l13_l14" },
+	{ "l12", QCOM_SMD_RPM_LDOA, 12, &pm660_ht_lvpldo, "vdd_l8_l9_l10_l11_l12_l13_l14" },
+	{ "l13", QCOM_SMD_RPM_LDOA, 13, &pm660_ht_lvpldo, "vdd_l8_l9_l10_l11_l12_l13_l14" },
+	{ "l14", QCOM_SMD_RPM_LDOA, 14, &pm660_ht_lvpldo, "vdd_l8_l9_l10_l11_l12_l13_l14" },
+	{ "l15", QCOM_SMD_RPM_LDOA, 15, &pm660_pldo660, "vdd_l15_l16_l17_l18_l19" },
+	{ "l16", QCOM_SMD_RPM_LDOA, 16, &pm660_pldo660, "vdd_l15_l16_l17_l18_l19" },
+	{ "l17", QCOM_SMD_RPM_LDOA, 17, &pm660_pldo660, "vdd_l15_l16_l17_l18_l19" },
+	{ "l18", QCOM_SMD_RPM_LDOA, 18, &pm660_pldo660, "vdd_l15_l16_l17_l18_l19" },
+	{ "l19", QCOM_SMD_RPM_LDOA, 19, &pm660_pldo660, "vdd_l15_l16_l17_l18_l19" },
+	{ }
+};
+
+static const struct rpm_regulator_data rpm_pm660l_regulators[] = {
+	{ "s1", QCOM_SMD_RPM_SMPB, 1, &pm660_ftsmps, "vdd_s1" },
+	{ "s2", QCOM_SMD_RPM_SMPB, 2, &pm660_ftsmps, "vdd_s2" },
+	{ "s3", QCOM_SMD_RPM_RWCX, 0, &pm660_ftsmps, "vdd_s3_s4" },
+	{ "s5", QCOM_SMD_RPM_RWMX, 0, &pm660_ftsmps, "vdd_s5" },
+	{ "l1", QCOM_SMD_RPM_LDOB, 1, &pm660_nldo660, "vdd_l1_l9_l10" },
+	{ "l2", QCOM_SMD_RPM_LDOB, 2, &pm660_pldo660, "vdd_l2" },
+	{ "l3", QCOM_SMD_RPM_LDOB, 3, &pm660_pldo660, "vdd_l3_l5_l7_l8" },
+	{ "l4", QCOM_SMD_RPM_LDOB, 4, &pm660_pldo660, "vdd_l4_l6" },
+	{ "l5", QCOM_SMD_RPM_LDOB, 5, &pm660_pldo660, "vdd_l3_l5_l7_l8" },
+	{ "l6", QCOM_SMD_RPM_LDOB, 6, &pm660_pldo660, "vdd_l4_l6" },
+	{ "l7", QCOM_SMD_RPM_LDOB, 7, &pm660_pldo660, "vdd_l3_l5_l7_l8" },
+	{ "l8", QCOM_SMD_RPM_LDOB, 8, &pm660_pldo660, "vdd_l3_l5_l7_l8" },
+	{ "l9", QCOM_SMD_RPM_RWLC, 0, &pm660_ht_nldo, "vdd_l1_l9_l10" },
+	{ "l10", QCOM_SMD_RPM_RWLM, 0, &pm660_ht_nldo, "vdd_l1_l9_l10" },
+	{ "bob", QCOM_SMD_RPM_BOBB, 1, &pm660l_bob, "vdd_bob", },
+	{ }
+};
+
 static const struct rpm_regulator_data rpm_pms405_regulators[] = {
 	{ "s1", QCOM_SMD_RPM_SMPA, 1, &pms405_hfsmps3, "vdd_s1" },
 	{ "s2", QCOM_SMD_RPM_SMPA, 2, &pms405_hfsmps3, "vdd_s2" },
@@ -932,6 +1043,8 @@ static const struct of_device_id rpm_of_match[] = {
 	{ .compatible = "qcom,rpm-pm8950-regulators", .data = &rpm_pm8950_regulators },
 	{ .compatible = "qcom,rpm-pm8994-regulators", .data = &rpm_pm8994_regulators },
 	{ .compatible = "qcom,rpm-pm8998-regulators", .data = &rpm_pm8998_regulators },
+	{ .compatible = "qcom,rpm-pm660-regulators", .data = &rpm_pm660_regulators },
+	{ .compatible = "qcom,rpm-pm660l-regulators", .data = &rpm_pm660l_regulators },
 	{ .compatible = "qcom,rpm-pma8084-regulators", .data = &rpm_pma8084_regulators },
 	{ .compatible = "qcom,rpm-pmi8994-regulators", .data = &rpm_pmi8994_regulators },
 	{ .compatible = "qcom,rpm-pmi8998-regulators", .data = &rpm_pmi8998_regulators },
diff --git a/include/linux/soc/qcom/smd-rpm.h b/include/linux/soc/qcom/smd-rpm.h
index da304ce8c8f7..f2645ec52520 100644
--- a/include/linux/soc/qcom/smd-rpm.h
+++ b/include/linux/soc/qcom/smd-rpm.h
@@ -19,6 +19,10 @@ struct qcom_smd_rpm;
 #define QCOM_SMD_RPM_CLK_BUF_A	0x616B6C63
 #define QCOM_SMD_RPM_LDOA	0x616f646c
 #define QCOM_SMD_RPM_LDOB	0x626F646C
+#define QCOM_SMD_RPM_RWCX	0x78637772
+#define QCOM_SMD_RPM_RWMX	0x786d7772
+#define QCOM_SMD_RPM_RWLC	0x636c7772
+#define QCOM_SMD_RPM_RWLM	0x6d6c7772
 #define QCOM_SMD_RPM_MEM_CLK	0x326b6c63
 #define QCOM_SMD_RPM_MISC_CLK	0x306b6c63
 #define QCOM_SMD_RPM_NCPA	0x6170636E
-- 
cgit v1.2.3


From 41a7431dbaa37533c3b732cdea425a7b8f2d4162 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Sat, 19 Sep 2020 16:04:18 +0200
Subject: power: supply: bq27xxx: add support for TI bq34z100

Add support for new device: the TI bq34z100-G1, a Wide Range Fuel Gauge
for Li-Ion, PbA, NiMH, and NiCd batteries.  The device shares a lot with
other models, although it has its own differences requiring new quirks.

This patch was tested on a system equipped with NiMH batteries.

Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/bq27xxx_battery.c     | 50 +++++++++++++++++++++++++++++-
 drivers/power/supply/bq27xxx_battery_i2c.c |  2 ++
 include/linux/power/bq27xxx_battery.h      |  1 +
 3 files changed, 52 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c
index cda03e1f9586..315e0909e6a4 100644
--- a/drivers/power/supply/bq27xxx_battery.c
+++ b/drivers/power/supply/bq27xxx_battery.c
@@ -38,6 +38,7 @@
  * https://www.ti.com/product/bq27621-g1
  * https://www.ti.com/product/bq27z561
  * https://www.ti.com/product/bq28z610
+ * https://www.ti.com/product/bq34z100-g1
  */
 
 #include <linux/device.h>
@@ -476,6 +477,26 @@ static u8
 		[BQ27XXX_REG_DCAP] = 0x3c,
 		[BQ27XXX_REG_AP] = 0x22,
 		BQ27XXX_DM_REG_ROWS,
+	},
+	bq34z100_regs[BQ27XXX_REG_MAX] = {
+		[BQ27XXX_REG_CTRL] = 0x00,
+		[BQ27XXX_REG_TEMP] = 0x0c,
+		[BQ27XXX_REG_INT_TEMP] = 0x2a,
+		[BQ27XXX_REG_VOLT] = 0x08,
+		[BQ27XXX_REG_AI] = 0x0a,
+		[BQ27XXX_REG_FLAGS] = 0x0e,
+		[BQ27XXX_REG_TTE] = 0x18,
+		[BQ27XXX_REG_TTF] = 0x1a,
+		[BQ27XXX_REG_TTES] = 0x1e,
+		[BQ27XXX_REG_TTECP] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_NAC] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_FCC] = 0x06,
+		[BQ27XXX_REG_CYCT] = 0x2c,
+		[BQ27XXX_REG_AE] = 0x24,
+		[BQ27XXX_REG_SOC] = 0x02,
+		[BQ27XXX_REG_DCAP] = 0x3c,
+		[BQ27XXX_REG_AP] = 0x22,
+		BQ27XXX_DM_REG_ROWS,
 	};
 
 static enum power_supply_property bq27000_props[] = {
@@ -750,6 +771,27 @@ static enum power_supply_property bq28z610_props[] = {
 	POWER_SUPPLY_PROP_MANUFACTURER,
 };
 
+static enum power_supply_property bq34z100_props[] = {
+	POWER_SUPPLY_PROP_STATUS,
+	POWER_SUPPLY_PROP_PRESENT,
+	POWER_SUPPLY_PROP_VOLTAGE_NOW,
+	POWER_SUPPLY_PROP_CURRENT_NOW,
+	POWER_SUPPLY_PROP_CAPACITY,
+	POWER_SUPPLY_PROP_CAPACITY_LEVEL,
+	POWER_SUPPLY_PROP_TEMP,
+	POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW,
+	POWER_SUPPLY_PROP_TIME_TO_EMPTY_AVG,
+	POWER_SUPPLY_PROP_TIME_TO_FULL_NOW,
+	POWER_SUPPLY_PROP_TECHNOLOGY,
+	POWER_SUPPLY_PROP_CHARGE_FULL,
+	POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN,
+	POWER_SUPPLY_PROP_CYCLE_COUNT,
+	POWER_SUPPLY_PROP_ENERGY_NOW,
+	POWER_SUPPLY_PROP_POWER_AVG,
+	POWER_SUPPLY_PROP_HEALTH,
+	POWER_SUPPLY_PROP_MANUFACTURER,
+};
+
 struct bq27xxx_dm_reg {
 	u8 subclass_id;
 	u8 offset;
@@ -857,6 +899,7 @@ static struct bq27xxx_dm_reg bq27621_dm_regs[] = {
 #define BQ27Z561_O_BITS		BIT(5)
 #define BQ27XXX_O_SOC_SI	BIT(6) /* SoC is single register */
 #define BQ27XXX_O_HAS_CI	BIT(7) /* has Capacity Inaccurate flag */
+#define BQ27XXX_O_MUL_CHEM	BIT(8) /* multiple chemistries supported */
 
 #define BQ27XXX_DATA(ref, key, opt) {		\
 	.opts = (opt),				\
@@ -903,6 +946,8 @@ static struct {
 	[BQ27621]   = BQ27XXX_DATA(bq27621,   0x80008000, BQ27XXX_O_UTOT | BQ27XXX_O_CFGUP | BQ27XXX_O_RAM),
 	[BQ27Z561]  = BQ27XXX_DATA(bq27z561,  0         , BQ27Z561_O_BITS),
 	[BQ28Z610]  = BQ27XXX_DATA(bq28z610,  0         , BQ27Z561_O_BITS),
+	[BQ34Z100]  = BQ27XXX_DATA(bq34z100,  0         , BQ27XXX_O_OTDC | BQ27XXX_O_SOC_SI | \
+							  BQ27XXX_O_HAS_CI | BQ27XXX_O_MUL_CHEM),
 };
 
 static DEFINE_MUTEX(bq27xxx_list_lock);
@@ -1914,7 +1959,10 @@ static int bq27xxx_battery_get_property(struct power_supply *psy,
 		ret = bq27xxx_simple_value(di->cache.time_to_full, val);
 		break;
 	case POWER_SUPPLY_PROP_TECHNOLOGY:
-		val->intval = POWER_SUPPLY_TECHNOLOGY_LION;
+		if (di->opts & BQ27XXX_O_MUL_CHEM)
+			val->intval = POWER_SUPPLY_TECHNOLOGY_UNKNOWN;
+		else
+			val->intval = POWER_SUPPLY_TECHNOLOGY_LION;
 		break;
 	case POWER_SUPPLY_PROP_CHARGE_NOW:
 		ret = bq27xxx_simple_value(bq27xxx_battery_read_nac(di), val);
diff --git a/drivers/power/supply/bq27xxx_battery_i2c.c b/drivers/power/supply/bq27xxx_battery_i2c.c
index 765873dfc495..eb4f4284982f 100644
--- a/drivers/power/supply/bq27xxx_battery_i2c.c
+++ b/drivers/power/supply/bq27xxx_battery_i2c.c
@@ -247,6 +247,7 @@ static const struct i2c_device_id bq27xxx_i2c_id_table[] = {
 	{ "bq27621", BQ27621 },
 	{ "bq27z561", BQ27Z561 },
 	{ "bq28z610", BQ28Z610 },
+	{ "bq34z100", BQ34Z100 },
 	{},
 };
 MODULE_DEVICE_TABLE(i2c, bq27xxx_i2c_id_table);
@@ -282,6 +283,7 @@ static const struct of_device_id bq27xxx_battery_i2c_of_match_table[] = {
 	{ .compatible = "ti,bq27621" },
 	{ .compatible = "ti,bq27z561" },
 	{ .compatible = "ti,bq28z610" },
+	{ .compatible = "ti,bq34z100" },
 	{},
 };
 MODULE_DEVICE_TABLE(of, bq27xxx_battery_i2c_of_match_table);
diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h
index 987d9652aa4e..111a40d0d3d5 100644
--- a/include/linux/power/bq27xxx_battery.h
+++ b/include/linux/power/bq27xxx_battery.h
@@ -32,6 +32,7 @@ enum bq27xxx_chip {
 	BQ27621,
 	BQ27Z561,
 	BQ28Z610,
+	BQ34Z100,
 };
 
 struct bq27xxx_device_info;
-- 
cgit v1.2.3


From a4947e84f23474803b62a2759b5808147e4e15f9 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Sun, 13 Sep 2020 13:29:28 +0300
Subject: overflow: Include header file with SIZE_MAX declaration

The various array_size functions use SIZE_MAX define, but missed limits.h
causes to failure to compile code that needs overflow.h.

 In file included from drivers/infiniband/core/uverbs_std_types_device.c:6:
 ./include/linux/overflow.h: In function 'array_size':
 ./include/linux/overflow.h:258:10: error: 'SIZE_MAX' undeclared (first use in this function)
   258 |   return SIZE_MAX;
       |          ^~~~~~~~

Fixes: 610b15c50e86 ("overflow.h: Add allocation size calculation helpers")
Link: https://lore.kernel.org/r/20200913102928.134985-1-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 include/linux/overflow.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/overflow.h b/include/linux/overflow.h
index 93fcef105061..ff3c48f0abc5 100644
--- a/include/linux/overflow.h
+++ b/include/linux/overflow.h
@@ -3,6 +3,7 @@
 #define __LINUX_OVERFLOW_H
 
 #include <linux/compiler.h>
+#include <linux/limits.h>
 
 /*
  * In the fallback code below, we need to compute the minimum and
-- 
cgit v1.2.3


From 3301c215a2bb94b5a0afcb444bbe9bf2a395a65d Mon Sep 17 00:00:00 2001
From: Alan Stern <stern@rowland.harvard.edu>
Date: Fri, 21 Aug 2020 10:55:44 +0800
Subject: USB: UDC: Expand device model API interface

The routines used by the UDC core to interface with the kernel's
device model, namely usb_add_gadget_udc(),
usb_add_gadget_udc_release(), and usb_del_gadget_udc(), provide access
to only a subset of the device model's full API.  They include
functionality equivalent to device_register() and device_unregister()
for gadgets, but they omit device_initialize(), device_add(),
device_del(), get_device(), and put_device().

This patch expands the UDC API by adding usb_initialize_gadget(),
usb_add_gadget(), usb_del_gadget(), usb_get_gadget(), and
usb_put_gadget() to fill in the gap.  It rewrites the existing
routines to call the new ones.

CC: Anton Vasilyev <vasilyev@ispras.ru>
CC: Evgeny Novikov <novikov@ispras.ru>
CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Peter Chen <peter.chen@nxp.com>
Signed-off-by: Felipe Balbi <balbi@kernel.org>
---
 drivers/usb/gadget/udc/core.c | 78 ++++++++++++++++++++++++++++++++++---------
 include/linux/usb/gadget.h    | 27 +++++++++++----
 2 files changed, 84 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c
index 4f82bcd31fd3..2b6770d9fb3f 100644
--- a/drivers/usb/gadget/udc/core.c
+++ b/drivers/usb/gadget/udc/core.c
@@ -1164,21 +1164,18 @@ static int check_pending_gadget_drivers(struct usb_udc *udc)
 }
 
 /**
- * usb_add_gadget_udc_release - adds a new gadget to the udc class driver list
+ * usb_initialize_gadget - initialize a gadget and its embedded struct device
  * @parent: the parent device to this udc. Usually the controller driver's
  * device.
- * @gadget: the gadget to be added to the list.
+ * @gadget: the gadget to be initialized.
  * @release: a gadget release function.
  *
  * Returns zero on success, negative errno otherwise.
  * Calls the gadget release function in the latter case.
  */
-int usb_add_gadget_udc_release(struct device *parent, struct usb_gadget *gadget,
+void usb_initialize_gadget(struct device *parent, struct usb_gadget *gadget,
 		void (*release)(struct device *dev))
 {
-	struct usb_udc		*udc;
-	int			ret = -ENOMEM;
-
 	dev_set_name(&gadget->dev, "gadget");
 	INIT_WORK(&gadget->work, usb_gadget_state_work);
 	gadget->dev.parent = parent;
@@ -1189,17 +1186,32 @@ int usb_add_gadget_udc_release(struct device *parent, struct usb_gadget *gadget,
 		gadget->dev.release = usb_udc_nop_release;
 
 	device_initialize(&gadget->dev);
+}
+EXPORT_SYMBOL_GPL(usb_initialize_gadget);
+
+/**
+ * usb_add_gadget - adds a new gadget to the udc class driver list
+ * @gadget: the gadget to be added to the list.
+ *
+ * Returns zero on success, negative errno otherwise.
+ * Does not do a final usb_put_gadget() if an error occurs.
+ */
+int usb_add_gadget(struct usb_gadget *gadget)
+{
+	struct usb_udc		*udc;
+	int			ret = -ENOMEM;
 
 	udc = kzalloc(sizeof(*udc), GFP_KERNEL);
 	if (!udc)
-		goto err_put_gadget;
+		goto error;
 
 	device_initialize(&udc->dev);
 	udc->dev.release = usb_udc_release;
 	udc->dev.class = udc_class;
 	udc->dev.groups = usb_udc_attr_groups;
-	udc->dev.parent = parent;
-	ret = dev_set_name(&udc->dev, "%s", kobject_name(&parent->kobj));
+	udc->dev.parent = gadget->dev.parent;
+	ret = dev_set_name(&udc->dev, "%s",
+			kobject_name(&gadget->dev.parent->kobj));
 	if (ret)
 		goto err_put_udc;
 
@@ -1242,8 +1254,30 @@ int usb_add_gadget_udc_release(struct device *parent, struct usb_gadget *gadget,
  err_put_udc:
 	put_device(&udc->dev);
 
- err_put_gadget:
-	put_device(&gadget->dev);
+ error:
+	return ret;
+}
+EXPORT_SYMBOL_GPL(usb_add_gadget);
+
+/**
+ * usb_add_gadget_udc_release - adds a new gadget to the udc class driver list
+ * @parent: the parent device to this udc. Usually the controller driver's
+ * device.
+ * @gadget: the gadget to be added to the list.
+ * @release: a gadget release function.
+ *
+ * Returns zero on success, negative errno otherwise.
+ * Calls the gadget release function in the latter case.
+ */
+int usb_add_gadget_udc_release(struct device *parent, struct usb_gadget *gadget,
+		void (*release)(struct device *dev))
+{
+	int	ret;
+
+	usb_initialize_gadget(parent, gadget, release);
+	ret = usb_add_gadget(gadget);
+	if (ret)
+		usb_put_gadget(gadget);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(usb_add_gadget_udc_release);
@@ -1311,13 +1345,14 @@ static void usb_gadget_remove_driver(struct usb_udc *udc)
 }
 
 /**
- * usb_del_gadget_udc - deletes @udc from udc_list
+ * usb_del_gadget - deletes @udc from udc_list
  * @gadget: the gadget to be removed.
  *
- * This, will call usb_gadget_unregister_driver() if
+ * This will call usb_gadget_unregister_driver() if
  * the @udc is still busy.
+ * It will not do a final usb_put_gadget().
  */
-void usb_del_gadget_udc(struct usb_gadget *gadget)
+void usb_del_gadget(struct usb_gadget *gadget)
 {
 	struct usb_udc *udc = gadget->udc;
 
@@ -1340,7 +1375,20 @@ void usb_del_gadget_udc(struct usb_gadget *gadget)
 	kobject_uevent(&udc->dev.kobj, KOBJ_REMOVE);
 	flush_work(&gadget->work);
 	device_unregister(&udc->dev);
-	device_unregister(&gadget->dev);
+	device_del(&gadget->dev);
+}
+EXPORT_SYMBOL_GPL(usb_del_gadget);
+
+/**
+ * usb_del_gadget_udc - deletes @udc from udc_list
+ * @gadget: the gadget to be removed.
+ *
+ * Calls usb_del_gadget() and does a final usb_put_gadget().
+ */
+void usb_del_gadget_udc(struct usb_gadget *gadget)
+{
+	usb_del_gadget(gadget);
+	usb_put_gadget(gadget);
 	memset(&gadget->dev, 0x00, sizeof(gadget->dev));
 }
 EXPORT_SYMBOL_GPL(usb_del_gadget_udc);
diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h
index 52ce1f6b8f83..e7351d64f11f 100644
--- a/include/linux/usb/gadget.h
+++ b/include/linux/usb/gadget.h
@@ -436,6 +436,7 @@ struct usb_gadget {
 };
 #define work_to_gadget(w)	(container_of((w), struct usb_gadget, work))
 
+/* Interface to the device model */
 static inline void set_gadget_data(struct usb_gadget *gadget, void *data)
 	{ dev_set_drvdata(&gadget->dev, data); }
 static inline void *get_gadget_data(struct usb_gadget *gadget)
@@ -444,6 +445,26 @@ static inline struct usb_gadget *dev_to_usb_gadget(struct device *dev)
 {
 	return container_of(dev, struct usb_gadget, dev);
 }
+static inline struct usb_gadget *usb_get_gadget(struct usb_gadget *gadget)
+{
+	get_device(&gadget->dev);
+	return gadget;
+}
+static inline void usb_put_gadget(struct usb_gadget *gadget)
+{
+	put_device(&gadget->dev);
+}
+extern void usb_initialize_gadget(struct device *parent,
+		struct usb_gadget *gadget, void (*release)(struct device *dev));
+extern int usb_add_gadget(struct usb_gadget *gadget);
+extern void usb_del_gadget(struct usb_gadget *gadget);
+
+/* Legacy device-model interface */
+extern int usb_add_gadget_udc_release(struct device *parent,
+		struct usb_gadget *gadget, void (*release)(struct device *dev));
+extern int usb_add_gadget_udc(struct device *parent, struct usb_gadget *gadget);
+extern void usb_del_gadget_udc(struct usb_gadget *gadget);
+extern char *usb_get_gadget_udc_name(void);
 
 /* iterates the non-control endpoints; 'tmp' is a struct usb_ep pointer */
 #define gadget_for_each_ep(tmp, gadget) \
@@ -735,12 +756,6 @@ int usb_gadget_probe_driver(struct usb_gadget_driver *driver);
  */
 int usb_gadget_unregister_driver(struct usb_gadget_driver *driver);
 
-extern int usb_add_gadget_udc_release(struct device *parent,
-		struct usb_gadget *gadget, void (*release)(struct device *dev));
-extern int usb_add_gadget_udc(struct device *parent, struct usb_gadget *gadget);
-extern void usb_del_gadget_udc(struct usb_gadget *gadget);
-extern char *usb_get_gadget_udc_name(void);
-
 /*-------------------------------------------------------------------------*/
 
 /* utility to simplify dealing with string descriptors */
-- 
cgit v1.2.3


From 4d12a897fa1276737724393331d1002962f62940 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 29 Sep 2020 23:22:00 +0530
Subject: bus: mhi: fix doubled words and struct image_info kernel-doc

Drop doubled word "table" in kernel-doc.
Fix syntax for the kernel-doc notation for struct image_info.
Note that the bhi_vec field is private and not part of the kernel-doc.

Drop doubled word "device" in a comment.

Cc: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Cc: Hemant Kumar <hemantk@codeaurora.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
[mani: Added bus: prefix to the commit subject]
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20200929175218.8178-2-manivannan.sadhasivam@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/mhi.h | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mhi.h b/include/linux/mhi.h
index c4a940d98912..0779bc689b3e 100644
--- a/include/linux/mhi.h
+++ b/include/linux/mhi.h
@@ -85,13 +85,15 @@ enum mhi_ch_type {
 };
 
 /**
- * struct image_info - Firmware and RDDM table table
- * @mhi_buf - Buffer for firmware and RDDM table
- * @entries - # of entries in table
+ * struct image_info - Firmware and RDDM table
+ * @mhi_buf: Buffer for firmware and RDDM table
+ * @entries: # of entries in table
  */
 struct image_info {
 	struct mhi_buf *mhi_buf;
+	/* private: from internal.h */
 	struct bhi_vec_entry *bhi_vec;
+	/* public: */
 	u32 entries;
 };
 
@@ -593,7 +595,7 @@ int mhi_async_power_up(struct mhi_controller *mhi_cntrl);
 
 /**
  * mhi_sync_power_up - Start MHI power up sequence and wait till the device
- *                     device enters valid EE state
+ *                     enters valid EE state
  * @mhi_cntrl: MHI controller
  */
 int mhi_sync_power_up(struct mhi_controller *mhi_cntrl);
-- 
cgit v1.2.3


From 5aa93f0576b4e7be60ffcccb674470c59789fd1b Mon Sep 17 00:00:00 2001
From: Bhaumik Bhatt <bbhatt@codeaurora.org>
Date: Tue, 29 Sep 2020 23:22:05 +0530
Subject: bus: mhi: core: Use generic name field for an MHI device

An MHI device is not necessarily associated with only channels as we can
have one associated with the controller itself. Hence, the chan_name
field within the mhi_device structure should instead be replaced with a
generic name to accurately reflect any type of MHI device.

Reviewed-by: Jeffrey Hugo <jhugo@codeaurora.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Bhaumik Bhatt <bbhatt@codeaurora.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20200929175218.8178-7-manivannan.sadhasivam@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/mhi/core/init.c | 5 +++--
 drivers/bus/mhi/core/main.c | 6 +++---
 include/linux/mhi.h         | 8 ++++----
 3 files changed, 10 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/bus/mhi/core/init.c b/drivers/bus/mhi/core/init.c
index e43a190a7a36..e2011ec46b92 100644
--- a/drivers/bus/mhi/core/init.c
+++ b/drivers/bus/mhi/core/init.c
@@ -904,6 +904,7 @@ int mhi_register_controller(struct mhi_controller *mhi_cntrl,
 	mhi_dev->dev_type = MHI_DEVICE_CONTROLLER;
 	mhi_dev->mhi_cntrl = mhi_cntrl;
 	dev_set_name(&mhi_dev->dev, "%s", dev_name(mhi_cntrl->cntrl_dev));
+	mhi_dev->name = dev_name(mhi_cntrl->cntrl_dev);
 
 	/* Init wakeup source */
 	device_init_wakeup(&mhi_dev->dev, true);
@@ -1249,7 +1250,7 @@ static int mhi_uevent(struct device *dev, struct kobj_uevent_env *env)
 	struct mhi_device *mhi_dev = to_mhi_device(dev);
 
 	return add_uevent_var(env, "MODALIAS=" MHI_DEVICE_MODALIAS_FMT,
-					mhi_dev->chan_name);
+					mhi_dev->name);
 }
 
 static int mhi_match(struct device *dev, struct device_driver *drv)
@@ -1266,7 +1267,7 @@ static int mhi_match(struct device *dev, struct device_driver *drv)
 		return 0;
 
 	for (id = mhi_drv->id_table; id->chan[0]; id++)
-		if (!strcmp(mhi_dev->chan_name, id->chan)) {
+		if (!strcmp(mhi_dev->name, id->chan)) {
 			mhi_dev->id = id;
 			return 1;
 		}
diff --git a/drivers/bus/mhi/core/main.c b/drivers/bus/mhi/core/main.c
index 79be18ec2ebf..2cff5ddff225 100644
--- a/drivers/bus/mhi/core/main.c
+++ b/drivers/bus/mhi/core/main.c
@@ -249,7 +249,7 @@ int mhi_destroy_device(struct device *dev, void *data)
 		put_device(&mhi_dev->dl_chan->mhi_dev->dev);
 
 	dev_dbg(&mhi_cntrl->mhi_dev->dev, "destroy device for chan:%s\n",
-		 mhi_dev->chan_name);
+		 mhi_dev->name);
 
 	/* Notify the client and remove the device from MHI bus */
 	device_del(dev);
@@ -327,10 +327,10 @@ void mhi_create_devices(struct mhi_controller *mhi_cntrl)
 		}
 
 		/* Channel name is same for both UL and DL */
-		mhi_dev->chan_name = mhi_chan->name;
+		mhi_dev->name = mhi_chan->name;
 		dev_set_name(&mhi_dev->dev, "%s_%s",
 			     dev_name(mhi_cntrl->cntrl_dev),
-			     mhi_dev->chan_name);
+			     mhi_dev->name);
 
 		/* Init wakeup source if available */
 		if (mhi_dev->dl_chan && mhi_dev->dl_chan->wake_capable)
diff --git a/include/linux/mhi.h b/include/linux/mhi.h
index 0779bc689b3e..bb337d163dda 100644
--- a/include/linux/mhi.h
+++ b/include/linux/mhi.h
@@ -438,10 +438,10 @@ struct mhi_controller {
 };
 
 /**
- * struct mhi_device - Structure representing a MHI device which binds
- *                     to channels
+ * struct mhi_device - Structure representing an MHI device which binds
+ *                     to channels or is associated with controllers
  * @id: Pointer to MHI device ID struct
- * @chan_name: Name of the channel to which the device binds
+ * @name: Name of the associated MHI device
  * @mhi_cntrl: Controller the device belongs to
  * @ul_chan: UL channel for the device
  * @dl_chan: DL channel for the device
@@ -453,7 +453,7 @@ struct mhi_controller {
  */
 struct mhi_device {
 	const struct mhi_device_id *id;
-	const char *chan_name;
+	const char *name;
 	struct mhi_controller *mhi_cntrl;
 	struct mhi_chan *ul_chan;
 	struct mhi_chan *dl_chan;
-- 
cgit v1.2.3


From 601455dae00a853d1d8d6d768b3b79a7d59a5853 Mon Sep 17 00:00:00 2001
From: Bhaumik Bhatt <bbhatt@codeaurora.org>
Date: Tue, 29 Sep 2020 23:22:07 +0530
Subject: bus: mhi: core: Introduce counters to track MHI device state
 transitions

Use counters to track MHI device state transitions such as those
to M0, M2, or M3 states. This can help in better debug, allowing
the user to see the number of transitions to a certain MHI state
when queried using debugfs entries or via other mechanisms.

Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Bhaumik Bhatt <bbhatt@codeaurora.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20200929175218.8178-9-manivannan.sadhasivam@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/mhi/core/pm.c | 4 ++++
 include/linux/mhi.h       | 2 ++
 2 files changed, 6 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/bus/mhi/core/pm.c b/drivers/bus/mhi/core/pm.c
index 27bb471c8f4e..ce4d969818b4 100644
--- a/drivers/bus/mhi/core/pm.c
+++ b/drivers/bus/mhi/core/pm.c
@@ -256,6 +256,7 @@ int mhi_pm_m0_transition(struct mhi_controller *mhi_cntrl)
 		dev_err(dev, "Unable to transition to M0 state\n");
 		return -EIO;
 	}
+	mhi_cntrl->M0++;
 
 	/* Wake up the device */
 	read_lock_bh(&mhi_cntrl->pm_lock);
@@ -326,6 +327,8 @@ void mhi_pm_m1_transition(struct mhi_controller *mhi_cntrl)
 		mhi_cntrl->dev_state = MHI_STATE_M2;
 
 		write_unlock_irq(&mhi_cntrl->pm_lock);
+
+		mhi_cntrl->M2++;
 		wake_up_all(&mhi_cntrl->state_event);
 
 		/* If there are any pending resources, exit M2 immediately */
@@ -362,6 +365,7 @@ int mhi_pm_m3_transition(struct mhi_controller *mhi_cntrl)
 		return -EIO;
 	}
 
+	mhi_cntrl->M3++;
 	wake_up_all(&mhi_cntrl->state_event);
 
 	return 0;
diff --git a/include/linux/mhi.h b/include/linux/mhi.h
index bb337d163dda..c56b4447a4e9 100644
--- a/include/linux/mhi.h
+++ b/include/linux/mhi.h
@@ -328,6 +328,7 @@ struct mhi_controller_config {
  * @dev_state: MHI device state
  * @dev_wake: Device wakeup count
  * @pending_pkts: Pending packets for the controller
+ * @M0, M2, M3: Counters to track number of device MHI state changes
  * @transition_list: List of MHI state transitions
  * @transition_lock: Lock for protecting MHI state transition list
  * @wlock: Lock for protecting device wakeup
@@ -407,6 +408,7 @@ struct mhi_controller {
 	enum mhi_state dev_state;
 	atomic_t dev_wake;
 	atomic_t pending_pkts;
+	u32 M0, M2, M3;
 	struct list_head transition_list;
 	spinlock_t transition_lock;
 	spinlock_t wlock;
-- 
cgit v1.2.3


From 8e3729bfa7be159d1f94d0caab9c1beff8268672 Mon Sep 17 00:00:00 2001
From: Bhaumik Bhatt <bbhatt@codeaurora.org>
Date: Tue, 29 Sep 2020 23:22:08 +0530
Subject: bus: mhi: core: Read and save device hardware information from BHI

Device hardware specific information such as serial number and the OEM
PK hash can be read using BHI and saved on host to identify the
endpoint.

Reviewed-by: Jeffrey Hugo <jhugo@codeaurora.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Bhaumik Bhatt <bbhatt@codeaurora.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20200929175218.8178-10-manivannan.sadhasivam@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/mhi/core/boot.c | 17 ++++++++++++++++-
 include/linux/mhi.h         |  6 ++++++
 2 files changed, 22 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/bus/mhi/core/boot.c b/drivers/bus/mhi/core/boot.c
index 0b38014d040e..24422f5c3d80 100644
--- a/drivers/bus/mhi/core/boot.c
+++ b/drivers/bus/mhi/core/boot.c
@@ -392,13 +392,28 @@ void mhi_fw_load_handler(struct mhi_controller *mhi_cntrl)
 	void *buf;
 	dma_addr_t dma_addr;
 	size_t size;
-	int ret;
+	int i, ret;
 
 	if (MHI_PM_IN_ERROR_STATE(mhi_cntrl->pm_state)) {
 		dev_err(dev, "Device MHI is not in valid state\n");
 		return;
 	}
 
+	/* save hardware info from BHI */
+	ret = mhi_read_reg(mhi_cntrl, mhi_cntrl->bhi, BHI_SERIALNU,
+			   &mhi_cntrl->serial_number);
+	if (ret)
+		dev_err(dev, "Could not capture serial number via BHI\n");
+
+	for (i = 0; i < ARRAY_SIZE(mhi_cntrl->oem_pk_hash); i++) {
+		ret = mhi_read_reg(mhi_cntrl, mhi_cntrl->bhi, BHI_OEMPKHASH(i),
+				   &mhi_cntrl->oem_pk_hash[i]);
+		if (ret) {
+			dev_err(dev, "Could not capture OEM PK HASH via BHI\n");
+			break;
+		}
+	}
+
 	/* If device is in pass through, do reset to ready state transition */
 	if (mhi_cntrl->ee == MHI_EE_PTHRU)
 		goto fw_load_ee_pthru;
diff --git a/include/linux/mhi.h b/include/linux/mhi.h
index c56b4447a4e9..0c97f4bc5fae 100644
--- a/include/linux/mhi.h
+++ b/include/linux/mhi.h
@@ -16,6 +16,8 @@
 #include <linux/wait.h>
 #include <linux/workqueue.h>
 
+#define MHI_MAX_OEM_PK_HASH_SEGMENTS 16
+
 struct mhi_chan;
 struct mhi_event;
 struct mhi_ctxt;
@@ -316,6 +318,8 @@ struct mhi_controller_config {
  * @device_number: MHI controller device number
  * @major_version: MHI controller major revision number
  * @minor_version: MHI controller minor revision number
+ * @serial_number: MHI controller serial number obtained from BHI
+ * @oem_pk_hash: MHI controller OEM PK Hash obtained from BHI
  * @mhi_event: MHI event ring configurations table
  * @mhi_cmd: MHI command ring configurations table
  * @mhi_ctxt: MHI device context, shared memory between host and device
@@ -394,6 +398,8 @@ struct mhi_controller {
 	u32 device_number;
 	u32 major_version;
 	u32 minor_version;
+	u32 serial_number;
+	u32 oem_pk_hash[MHI_MAX_OEM_PK_HASH_SEGMENTS];
 
 	struct mhi_event *mhi_event;
 	struct mhi_cmd *mhi_cmd;
-- 
cgit v1.2.3


From f42dfbe8f712127031e7b9bc938a1c33cec2ff57 Mon Sep 17 00:00:00 2001
From: Bhaumik Bhatt <bbhatt@codeaurora.org>
Date: Tue, 29 Sep 2020 23:22:09 +0530
Subject: bus: mhi: core: Introduce APIs to allocate and free the MHI
 controller

Client devices should use the APIs provided to allocate and free
the MHI controller structure. This will help ensure that the
structure is zero-initialized and there are no false positives
with respect to reading any values such as the serial number or
the OEM PK hash.

Suggested-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Bhaumik Bhatt <bbhatt@codeaurora.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20200929175218.8178-11-manivannan.sadhasivam@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/mhi/core/init.c | 16 ++++++++++++++++
 include/linux/mhi.h         | 12 ++++++++++++
 2 files changed, 28 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/bus/mhi/core/init.c b/drivers/bus/mhi/core/init.c
index e2011ec46b92..f69a2f3d039d 100644
--- a/drivers/bus/mhi/core/init.c
+++ b/drivers/bus/mhi/core/init.c
@@ -954,6 +954,22 @@ void mhi_unregister_controller(struct mhi_controller *mhi_cntrl)
 }
 EXPORT_SYMBOL_GPL(mhi_unregister_controller);
 
+struct mhi_controller *mhi_alloc_controller(void)
+{
+	struct mhi_controller *mhi_cntrl;
+
+	mhi_cntrl = kzalloc(sizeof(*mhi_cntrl), GFP_KERNEL);
+
+	return mhi_cntrl;
+}
+EXPORT_SYMBOL_GPL(mhi_alloc_controller);
+
+void mhi_free_controller(struct mhi_controller *mhi_cntrl)
+{
+	kfree(mhi_cntrl);
+}
+EXPORT_SYMBOL_GPL(mhi_free_controller);
+
 int mhi_prepare_for_power_up(struct mhi_controller *mhi_cntrl)
 {
 	struct device *dev = &mhi_cntrl->mhi_dev->dev;
diff --git a/include/linux/mhi.h b/include/linux/mhi.h
index 0c97f4bc5fae..6b987e8cc438 100644
--- a/include/linux/mhi.h
+++ b/include/linux/mhi.h
@@ -527,6 +527,18 @@ struct mhi_driver {
 #define to_mhi_driver(drv) container_of(drv, struct mhi_driver, driver)
 #define to_mhi_device(dev) container_of(dev, struct mhi_device, dev)
 
+/**
+ * mhi_alloc_controller - Allocate the MHI Controller structure
+ * Allocate the mhi_controller structure using zero initialized memory
+ */
+struct mhi_controller *mhi_alloc_controller(void);
+
+/**
+ * mhi_free_controller - Free the MHI Controller structure
+ * Free the mhi_controller structure which was previously allocated
+ */
+void mhi_free_controller(struct mhi_controller *mhi_cntrl);
+
 /**
  * mhi_register_controller - Register MHI controller
  * @mhi_cntrl: MHI controller to register
-- 
cgit v1.2.3


From f38173a731cae380885e843dace21c8dc4198285 Mon Sep 17 00:00:00 2001
From: Hemant Kumar <hemantk@codeaurora.org>
Date: Tue, 29 Sep 2020 23:22:10 +0530
Subject: bus: mhi: core: Add const qualifier to MHI config information

MHI channel, event and controller config data needs to be
treated read only information. Add const qualifier to make
sure config information passed by MHI controller is not
modified by MHI core driver.

Suggested-by: Kalle Valo <kvalo@codeaurora.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Hemant Kumar <hemantk@codeaurora.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20200929175218.8178-12-manivannan.sadhasivam@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/mhi/core/init.c | 12 ++++++------
 include/linux/mhi.h         |  6 +++---
 2 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/bus/mhi/core/init.c b/drivers/bus/mhi/core/init.c
index f69a2f3d039d..d23293876be8 100644
--- a/drivers/bus/mhi/core/init.c
+++ b/drivers/bus/mhi/core/init.c
@@ -562,10 +562,10 @@ int mhi_init_chan_ctxt(struct mhi_controller *mhi_cntrl,
 }
 
 static int parse_ev_cfg(struct mhi_controller *mhi_cntrl,
-			struct mhi_controller_config *config)
+			const struct mhi_controller_config *config)
 {
 	struct mhi_event *mhi_event;
-	struct mhi_event_config *event_cfg;
+	const struct mhi_event_config *event_cfg;
 	struct device *dev = &mhi_cntrl->mhi_dev->dev;
 	int i, num;
 
@@ -648,9 +648,9 @@ error_ev_cfg:
 }
 
 static int parse_ch_cfg(struct mhi_controller *mhi_cntrl,
-			struct mhi_controller_config *config)
+			const struct mhi_controller_config *config)
 {
-	struct mhi_channel_config *ch_cfg;
+	const struct mhi_channel_config *ch_cfg;
 	struct device *dev = &mhi_cntrl->mhi_dev->dev;
 	int i;
 	u32 chan;
@@ -766,7 +766,7 @@ error_chan_cfg:
 }
 
 static int parse_config(struct mhi_controller *mhi_cntrl,
-			struct mhi_controller_config *config)
+			const struct mhi_controller_config *config)
 {
 	int ret;
 
@@ -803,7 +803,7 @@ error_ev_cfg:
 }
 
 int mhi_register_controller(struct mhi_controller *mhi_cntrl,
-			    struct mhi_controller_config *config)
+			    const struct mhi_controller_config *config)
 {
 	struct mhi_event *mhi_event;
 	struct mhi_chan *mhi_chan;
diff --git a/include/linux/mhi.h b/include/linux/mhi.h
index 6b987e8cc438..b2c0214bfbd6 100644
--- a/include/linux/mhi.h
+++ b/include/linux/mhi.h
@@ -280,9 +280,9 @@ struct mhi_controller_config {
 	u32 timeout_ms;
 	u32 buf_len;
 	u32 num_channels;
-	struct mhi_channel_config *ch_cfg;
+	const struct mhi_channel_config *ch_cfg;
 	u32 num_events;
-	struct mhi_event_config *event_cfg;
+	const struct mhi_event_config *event_cfg;
 	bool use_bounce_buf;
 	bool m2_no_db;
 };
@@ -545,7 +545,7 @@ void mhi_free_controller(struct mhi_controller *mhi_cntrl);
  * @config: Configuration to use for the controller
  */
 int mhi_register_controller(struct mhi_controller *mhi_cntrl,
-			    struct mhi_controller_config *config);
+			const struct mhi_controller_config *config);
 
 /**
  * mhi_unregister_controller - Unregister MHI controller
-- 
cgit v1.2.3


From e1427f32b85010ca0c38104955e234ca89d4cee5 Mon Sep 17 00:00:00 2001
From: Clark Williams <williams@redhat.com>
Date: Tue, 29 Sep 2020 23:22:11 +0530
Subject: bus: mhi: Remove include of rwlock_types.h

rwlock.h should not be included directly. Instead linux/splinlock.h
should be included. Including it directly will break the RT build.

Also there is no point in including _types.h headers directly. There is
no benefit in including the type without the accessor.

Fixes: 0cbf260820fa7 ("bus: mhi: core: Add support for registering MHI controllers")
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Clark Williams <williams@redhat.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20200929175218.8178-13-manivannan.sadhasivam@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/mhi.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mhi.h b/include/linux/mhi.h
index b2c0214bfbd6..008b8f6fa9ff 100644
--- a/include/linux/mhi.h
+++ b/include/linux/mhi.h
@@ -9,10 +9,9 @@
 #include <linux/device.h>
 #include <linux/dma-direction.h>
 #include <linux/mutex.h>
-#include <linux/rwlock_types.h>
 #include <linux/skbuff.h>
 #include <linux/slab.h>
-#include <linux/spinlock_types.h>
+#include <linux/spinlock.h>
 #include <linux/wait.h>
 #include <linux/workqueue.h>
 
-- 
cgit v1.2.3


From c7bd825e52b3d0b9ae519a006b80521d4587f864 Mon Sep 17 00:00:00 2001
From: Bhaumik Bhatt <bbhatt@codeaurora.org>
Date: Tue, 29 Sep 2020 23:22:13 +0530
Subject: bus: mhi: core: Introduce debugfs entries for MHI

Introduce debugfs entries to show state, register, channel, device,
and event rings information. Allow the host to dump registers,
issue device wake, and change the MHI timeout to help in debug.

Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Bhaumik Bhatt <bbhatt@codeaurora.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20200929175218.8178-15-manivannan.sadhasivam@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/mhi/Kconfig         |   8 +
 drivers/bus/mhi/core/Makefile   |   1 +
 drivers/bus/mhi/core/debugfs.c  | 410 ++++++++++++++++++++++++++++++++++++++++
 drivers/bus/mhi/core/init.c     |   7 +
 drivers/bus/mhi/core/internal.h |  24 +++
 include/linux/mhi.h             |   2 +
 6 files changed, 452 insertions(+)
 create mode 100644 drivers/bus/mhi/core/debugfs.c

(limited to 'include/linux')

diff --git a/drivers/bus/mhi/Kconfig b/drivers/bus/mhi/Kconfig
index 6677cccd61f3..e841c1097fb4 100644
--- a/drivers/bus/mhi/Kconfig
+++ b/drivers/bus/mhi/Kconfig
@@ -12,3 +12,11 @@ config MHI_BUS
 	  communication protocol used by the host processors to control
 	  and communicate with modem devices over a high speed peripheral
 	  bus or shared memory.
+
+config MHI_BUS_DEBUG
+	bool "Debugfs support for the MHI bus"
+	depends on MHI_BUS && DEBUG_FS
+	help
+	  Enable debugfs support for use with the MHI transport. Allows
+	  reading and/or modifying some values within the MHI controller
+	  for debug and test purposes.
diff --git a/drivers/bus/mhi/core/Makefile b/drivers/bus/mhi/core/Makefile
index 66e2700c9032..12c57ab3724c 100644
--- a/drivers/bus/mhi/core/Makefile
+++ b/drivers/bus/mhi/core/Makefile
@@ -1,3 +1,4 @@
 obj-$(CONFIG_MHI_BUS) := mhi.o
 
 mhi-y := init.o main.o pm.o boot.o
+mhi-$(CONFIG_MHI_BUS_DEBUG) += debugfs.o
diff --git a/drivers/bus/mhi/core/debugfs.c b/drivers/bus/mhi/core/debugfs.c
new file mode 100644
index 000000000000..f50d73054db4
--- /dev/null
+++ b/drivers/bus/mhi/core/debugfs.c
@@ -0,0 +1,410 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2020, The Linux Foundation. All rights reserved.
+ *
+ */
+
+#include <linux/debugfs.h>
+#include <linux/device.h>
+#include <linux/interrupt.h>
+#include <linux/list.h>
+#include <linux/mhi.h>
+#include <linux/module.h>
+#include "internal.h"
+
+static int mhi_debugfs_states_show(struct seq_file *m, void *d)
+{
+	struct mhi_controller *mhi_cntrl = m->private;
+
+	/* states */
+	seq_printf(m, "PM state: %s Device: %s MHI state: %s EE: %s wake: %s\n",
+		   to_mhi_pm_state_str(mhi_cntrl->pm_state),
+		   mhi_is_active(mhi_cntrl) ? "Active" : "Inactive",
+		   TO_MHI_STATE_STR(mhi_cntrl->dev_state),
+		   TO_MHI_EXEC_STR(mhi_cntrl->ee),
+		   mhi_cntrl->wake_set ? "true" : "false");
+
+	/* counters */
+	seq_printf(m, "M0: %u M2: %u M3: %u", mhi_cntrl->M0, mhi_cntrl->M2,
+		   mhi_cntrl->M3);
+
+	seq_printf(m, " device wake: %u pending packets: %u\n",
+		   atomic_read(&mhi_cntrl->dev_wake),
+		   atomic_read(&mhi_cntrl->pending_pkts));
+
+	return 0;
+}
+
+static int mhi_debugfs_events_show(struct seq_file *m, void *d)
+{
+	struct mhi_controller *mhi_cntrl = m->private;
+	struct mhi_event *mhi_event;
+	struct mhi_event_ctxt *er_ctxt;
+	int i;
+
+	if (!mhi_is_active(mhi_cntrl)) {
+		seq_puts(m, "Device not ready\n");
+		return -ENODEV;
+	}
+
+	er_ctxt = mhi_cntrl->mhi_ctxt->er_ctxt;
+	mhi_event = mhi_cntrl->mhi_event;
+	for (i = 0; i < mhi_cntrl->total_ev_rings;
+						i++, er_ctxt++, mhi_event++) {
+		struct mhi_ring *ring = &mhi_event->ring;
+
+		if (mhi_event->offload_ev) {
+			seq_printf(m, "Index: %d is an offload event ring\n",
+				   i);
+			continue;
+		}
+
+		seq_printf(m, "Index: %d intmod count: %lu time: %lu",
+			   i, (er_ctxt->intmod & EV_CTX_INTMODC_MASK) >>
+			   EV_CTX_INTMODC_SHIFT,
+			   (er_ctxt->intmod & EV_CTX_INTMODT_MASK) >>
+			   EV_CTX_INTMODT_SHIFT);
+
+		seq_printf(m, " base: 0x%0llx len: 0x%llx", er_ctxt->rbase,
+			   er_ctxt->rlen);
+
+		seq_printf(m, " rp: 0x%llx wp: 0x%llx", er_ctxt->rp,
+			   er_ctxt->wp);
+
+		seq_printf(m, " local rp: 0x%pK db: 0x%pad\n", ring->rp,
+			   &mhi_event->db_cfg.db_val);
+	}
+
+	return 0;
+}
+
+static int mhi_debugfs_channels_show(struct seq_file *m, void *d)
+{
+	struct mhi_controller *mhi_cntrl = m->private;
+	struct mhi_chan *mhi_chan;
+	struct mhi_chan_ctxt *chan_ctxt;
+	int i;
+
+	if (!mhi_is_active(mhi_cntrl)) {
+		seq_puts(m, "Device not ready\n");
+		return -ENODEV;
+	}
+
+	mhi_chan = mhi_cntrl->mhi_chan;
+	chan_ctxt = mhi_cntrl->mhi_ctxt->chan_ctxt;
+	for (i = 0; i < mhi_cntrl->max_chan; i++, chan_ctxt++, mhi_chan++) {
+		struct mhi_ring *ring = &mhi_chan->tre_ring;
+
+		if (mhi_chan->offload_ch) {
+			seq_printf(m, "%s(%u) is an offload channel\n",
+				   mhi_chan->name, mhi_chan->chan);
+			continue;
+		}
+
+		if (!mhi_chan->mhi_dev)
+			continue;
+
+		seq_printf(m,
+			   "%s(%u) state: 0x%lx brstmode: 0x%lx pollcfg: 0x%lx",
+			   mhi_chan->name, mhi_chan->chan, (chan_ctxt->chcfg &
+			   CHAN_CTX_CHSTATE_MASK) >> CHAN_CTX_CHSTATE_SHIFT,
+			   (chan_ctxt->chcfg & CHAN_CTX_BRSTMODE_MASK) >>
+			   CHAN_CTX_BRSTMODE_SHIFT, (chan_ctxt->chcfg &
+			   CHAN_CTX_POLLCFG_MASK) >> CHAN_CTX_POLLCFG_SHIFT);
+
+		seq_printf(m, " type: 0x%x event ring: %u", chan_ctxt->chtype,
+			   chan_ctxt->erindex);
+
+		seq_printf(m, " base: 0x%llx len: 0x%llx wp: 0x%llx",
+			   chan_ctxt->rbase, chan_ctxt->rlen, chan_ctxt->wp);
+
+		seq_printf(m, " local rp: 0x%pK local wp: 0x%pK db: 0x%pad\n",
+			   ring->rp, ring->wp,
+			   &mhi_chan->db_cfg.db_val);
+	}
+
+	return 0;
+}
+
+static int mhi_device_info_show(struct device *dev, void *data)
+{
+	struct mhi_device *mhi_dev;
+
+	if (dev->bus != &mhi_bus_type)
+		return 0;
+
+	mhi_dev = to_mhi_device(dev);
+
+	seq_printf((struct seq_file *)data, "%s: type: %s dev_wake: %u",
+		   mhi_dev->name, mhi_dev->dev_type ? "Controller" : "Transfer",
+		   mhi_dev->dev_wake);
+
+	/* for transfer device types only */
+	if (mhi_dev->dev_type == MHI_DEVICE_XFER)
+		seq_printf((struct seq_file *)data, " channels: %u(UL)/%u(DL)",
+			   mhi_dev->ul_chan_id, mhi_dev->dl_chan_id);
+
+	seq_puts((struct seq_file *)data, "\n");
+
+	return 0;
+}
+
+static int mhi_debugfs_devices_show(struct seq_file *m, void *d)
+{
+	struct mhi_controller *mhi_cntrl = m->private;
+
+	if (!mhi_is_active(mhi_cntrl)) {
+		seq_puts(m, "Device not ready\n");
+		return -ENODEV;
+	}
+
+	device_for_each_child(mhi_cntrl->cntrl_dev, m, mhi_device_info_show);
+
+	return 0;
+}
+
+static int mhi_debugfs_regdump_show(struct seq_file *m, void *d)
+{
+	struct mhi_controller *mhi_cntrl = m->private;
+	enum mhi_state state;
+	enum mhi_ee_type ee;
+	int i, ret = -EIO;
+	u32 val;
+	void __iomem *mhi_base = mhi_cntrl->regs;
+	void __iomem *bhi_base = mhi_cntrl->bhi;
+	void __iomem *bhie_base = mhi_cntrl->bhie;
+	void __iomem *wake_db = mhi_cntrl->wake_db;
+	struct {
+		const char *name;
+		int offset;
+		void __iomem *base;
+	} regs[] = {
+		{ "MHI_REGLEN", MHIREGLEN, mhi_base},
+		{ "MHI_VER", MHIVER, mhi_base},
+		{ "MHI_CFG", MHICFG, mhi_base},
+		{ "MHI_CTRL", MHICTRL, mhi_base},
+		{ "MHI_STATUS", MHISTATUS, mhi_base},
+		{ "MHI_WAKE_DB", 0, wake_db},
+		{ "BHI_EXECENV", BHI_EXECENV, bhi_base},
+		{ "BHI_STATUS", BHI_STATUS, bhi_base},
+		{ "BHI_ERRCODE", BHI_ERRCODE, bhi_base},
+		{ "BHI_ERRDBG1", BHI_ERRDBG1, bhi_base},
+		{ "BHI_ERRDBG2", BHI_ERRDBG2, bhi_base},
+		{ "BHI_ERRDBG3", BHI_ERRDBG3, bhi_base},
+		{ "BHIE_TXVEC_DB", BHIE_TXVECDB_OFFS, bhie_base},
+		{ "BHIE_TXVEC_STATUS", BHIE_TXVECSTATUS_OFFS, bhie_base},
+		{ "BHIE_RXVEC_DB", BHIE_RXVECDB_OFFS, bhie_base},
+		{ "BHIE_RXVEC_STATUS", BHIE_RXVECSTATUS_OFFS, bhie_base},
+		{ NULL },
+	};
+
+	if (!MHI_REG_ACCESS_VALID(mhi_cntrl->pm_state))
+		return ret;
+
+	seq_printf(m, "Host PM state: %s Device state: %s EE: %s\n",
+		   to_mhi_pm_state_str(mhi_cntrl->pm_state),
+		   TO_MHI_STATE_STR(mhi_cntrl->dev_state),
+		   TO_MHI_EXEC_STR(mhi_cntrl->ee));
+
+	state = mhi_get_mhi_state(mhi_cntrl);
+	ee = mhi_get_exec_env(mhi_cntrl);
+	seq_printf(m, "Device EE: %s state: %s\n", TO_MHI_EXEC_STR(ee),
+		   TO_MHI_STATE_STR(state));
+
+	for (i = 0; regs[i].name; i++) {
+		if (!regs[i].base)
+			continue;
+		ret = mhi_read_reg(mhi_cntrl, regs[i].base, regs[i].offset,
+				   &val);
+		if (ret)
+			continue;
+
+		seq_printf(m, "%s: 0x%x\n", regs[i].name, val);
+	}
+
+	return 0;
+}
+
+static int mhi_debugfs_device_wake_show(struct seq_file *m, void *d)
+{
+	struct mhi_controller *mhi_cntrl = m->private;
+	struct mhi_device *mhi_dev = mhi_cntrl->mhi_dev;
+
+	if (!mhi_is_active(mhi_cntrl)) {
+		seq_puts(m, "Device not ready\n");
+		return -ENODEV;
+	}
+
+	seq_printf(m,
+		   "Wake count: %d\n%s\n", mhi_dev->dev_wake,
+		   "Usage: echo get/put > device_wake to vote/unvote for M0");
+
+	return 0;
+}
+
+static ssize_t mhi_debugfs_device_wake_write(struct file *file,
+					     const char __user *ubuf,
+					     size_t count, loff_t *ppos)
+{
+	struct seq_file	*m = file->private_data;
+	struct mhi_controller *mhi_cntrl = m->private;
+	struct mhi_device *mhi_dev = mhi_cntrl->mhi_dev;
+	char buf[16];
+	int ret = -EINVAL;
+
+	if (copy_from_user(&buf, ubuf, min_t(size_t, sizeof(buf) - 1, count)))
+		return -EFAULT;
+
+	if (!strncmp(buf, "get", 3)) {
+		ret = mhi_device_get_sync(mhi_dev);
+	} else if (!strncmp(buf, "put", 3)) {
+		mhi_device_put(mhi_dev);
+		ret = 0;
+	}
+
+	return ret ? ret : count;
+}
+
+static int mhi_debugfs_timeout_ms_show(struct seq_file *m, void *d)
+{
+	struct mhi_controller *mhi_cntrl = m->private;
+
+	seq_printf(m, "%u ms\n", mhi_cntrl->timeout_ms);
+
+	return 0;
+}
+
+static ssize_t mhi_debugfs_timeout_ms_write(struct file *file,
+					    const char __user *ubuf,
+					    size_t count, loff_t *ppos)
+{
+	struct seq_file	*m = file->private_data;
+	struct mhi_controller *mhi_cntrl = m->private;
+	u32 timeout_ms;
+
+	if (kstrtou32_from_user(ubuf, count, 0, &timeout_ms))
+		return -EINVAL;
+
+	mhi_cntrl->timeout_ms = timeout_ms;
+
+	return count;
+}
+
+static int mhi_debugfs_states_open(struct inode *inode, struct file *fp)
+{
+	return single_open(fp, mhi_debugfs_states_show, inode->i_private);
+}
+
+static int mhi_debugfs_events_open(struct inode *inode, struct file *fp)
+{
+	return single_open(fp, mhi_debugfs_events_show, inode->i_private);
+}
+
+static int mhi_debugfs_channels_open(struct inode *inode, struct file *fp)
+{
+	return single_open(fp, mhi_debugfs_channels_show, inode->i_private);
+}
+
+static int mhi_debugfs_devices_open(struct inode *inode, struct file *fp)
+{
+	return single_open(fp, mhi_debugfs_devices_show, inode->i_private);
+}
+
+static int mhi_debugfs_regdump_open(struct inode *inode, struct file *fp)
+{
+	return single_open(fp, mhi_debugfs_regdump_show, inode->i_private);
+}
+
+static int mhi_debugfs_device_wake_open(struct inode *inode, struct file *fp)
+{
+	return single_open(fp, mhi_debugfs_device_wake_show, inode->i_private);
+}
+
+static int mhi_debugfs_timeout_ms_open(struct inode *inode, struct file *fp)
+{
+	return single_open(fp, mhi_debugfs_timeout_ms_show, inode->i_private);
+}
+
+static const struct file_operations debugfs_states_fops = {
+	.open = mhi_debugfs_states_open,
+	.release = single_release,
+	.read = seq_read,
+};
+
+static const struct file_operations debugfs_events_fops = {
+	.open = mhi_debugfs_events_open,
+	.release = single_release,
+	.read = seq_read,
+};
+
+static const struct file_operations debugfs_channels_fops = {
+	.open = mhi_debugfs_channels_open,
+	.release = single_release,
+	.read = seq_read,
+};
+
+static const struct file_operations debugfs_devices_fops = {
+	.open = mhi_debugfs_devices_open,
+	.release = single_release,
+	.read = seq_read,
+};
+
+static const struct file_operations debugfs_regdump_fops = {
+	.open = mhi_debugfs_regdump_open,
+	.release = single_release,
+	.read = seq_read,
+};
+
+static const struct file_operations debugfs_device_wake_fops = {
+	.open = mhi_debugfs_device_wake_open,
+	.write = mhi_debugfs_device_wake_write,
+	.release = single_release,
+	.read = seq_read,
+};
+
+static const struct file_operations debugfs_timeout_ms_fops = {
+	.open = mhi_debugfs_timeout_ms_open,
+	.write = mhi_debugfs_timeout_ms_write,
+	.release = single_release,
+	.read = seq_read,
+};
+
+static struct dentry *mhi_debugfs_root;
+
+void mhi_create_debugfs(struct mhi_controller *mhi_cntrl)
+{
+	mhi_cntrl->debugfs_dentry =
+			debugfs_create_dir(dev_name(mhi_cntrl->cntrl_dev),
+					   mhi_debugfs_root);
+
+	debugfs_create_file("states", 0444, mhi_cntrl->debugfs_dentry,
+			    mhi_cntrl, &debugfs_states_fops);
+	debugfs_create_file("events", 0444, mhi_cntrl->debugfs_dentry,
+			    mhi_cntrl, &debugfs_events_fops);
+	debugfs_create_file("channels", 0444, mhi_cntrl->debugfs_dentry,
+			    mhi_cntrl, &debugfs_channels_fops);
+	debugfs_create_file("devices", 0444, mhi_cntrl->debugfs_dentry,
+			    mhi_cntrl, &debugfs_devices_fops);
+	debugfs_create_file("regdump", 0444, mhi_cntrl->debugfs_dentry,
+			    mhi_cntrl, &debugfs_regdump_fops);
+	debugfs_create_file("device_wake", 0644, mhi_cntrl->debugfs_dentry,
+			    mhi_cntrl, &debugfs_device_wake_fops);
+	debugfs_create_file("timeout_ms", 0644, mhi_cntrl->debugfs_dentry,
+			    mhi_cntrl, &debugfs_timeout_ms_fops);
+}
+
+void mhi_destroy_debugfs(struct mhi_controller *mhi_cntrl)
+{
+	debugfs_remove_recursive(mhi_cntrl->debugfs_dentry);
+	mhi_cntrl->debugfs_dentry = NULL;
+}
+
+void mhi_debugfs_init(void)
+{
+	mhi_debugfs_root = debugfs_create_dir(mhi_bus_type.name, NULL);
+}
+
+void mhi_debugfs_exit(void)
+{
+	debugfs_remove_recursive(mhi_debugfs_root);
+}
diff --git a/drivers/bus/mhi/core/init.c b/drivers/bus/mhi/core/init.c
index d23293876be8..61e5885a331a 100644
--- a/drivers/bus/mhi/core/init.c
+++ b/drivers/bus/mhi/core/init.c
@@ -4,6 +4,7 @@
  *
  */
 
+#include <linux/debugfs.h>
 #include <linux/device.h>
 #include <linux/dma-direction.h>
 #include <linux/dma-mapping.h>
@@ -915,6 +916,8 @@ int mhi_register_controller(struct mhi_controller *mhi_cntrl,
 
 	mhi_cntrl->mhi_dev = mhi_dev;
 
+	mhi_create_debugfs(mhi_cntrl);
+
 	return 0;
 
 error_add_dev:
@@ -937,6 +940,8 @@ void mhi_unregister_controller(struct mhi_controller *mhi_cntrl)
 	struct mhi_chan *mhi_chan = mhi_cntrl->mhi_chan;
 	unsigned int i;
 
+	mhi_destroy_debugfs(mhi_cntrl);
+
 	kfree(mhi_cntrl->mhi_cmd);
 	kfree(mhi_cntrl->mhi_event);
 
@@ -1300,11 +1305,13 @@ struct bus_type mhi_bus_type = {
 
 static int __init mhi_init(void)
 {
+	mhi_debugfs_init();
 	return bus_register(&mhi_bus_type);
 }
 
 static void __exit mhi_exit(void)
 {
+	mhi_debugfs_exit();
 	bus_unregister(&mhi_bus_type);
 }
 
diff --git a/drivers/bus/mhi/core/internal.h b/drivers/bus/mhi/core/internal.h
index 5a81a428c4aa..7989269ddd96 100644
--- a/drivers/bus/mhi/core/internal.h
+++ b/drivers/bus/mhi/core/internal.h
@@ -570,6 +570,30 @@ struct mhi_chan {
 /* Default MHI timeout */
 #define MHI_TIMEOUT_MS (1000)
 
+/* debugfs related functions */
+#ifdef CONFIG_MHI_BUS_DEBUG
+void mhi_create_debugfs(struct mhi_controller *mhi_cntrl);
+void mhi_destroy_debugfs(struct mhi_controller *mhi_cntrl);
+void mhi_debugfs_init(void);
+void mhi_debugfs_exit(void);
+#else
+static inline void mhi_create_debugfs(struct mhi_controller *mhi_cntrl)
+{
+}
+
+static inline void mhi_destroy_debugfs(struct mhi_controller *mhi_cntrl)
+{
+}
+
+static inline void mhi_debugfs_init(void)
+{
+}
+
+static inline void mhi_debugfs_exit(void)
+{
+}
+#endif
+
 struct mhi_device *mhi_alloc_device(struct mhi_controller *mhi_cntrl);
 
 int mhi_destroy_device(struct device *dev, void *data);
diff --git a/include/linux/mhi.h b/include/linux/mhi.h
index 008b8f6fa9ff..fb45a0ff9aa3 100644
--- a/include/linux/mhi.h
+++ b/include/linux/mhi.h
@@ -291,6 +291,7 @@ struct mhi_controller_config {
  * @cntrl_dev: Pointer to the struct device of physical bus acting as the MHI
  *            controller (required)
  * @mhi_dev: MHI device instance for the controller
+ * @debugfs_dentry: MHI controller debugfs directory
  * @regs: Base address of MHI MMIO register space (required)
  * @bhi: Points to base of MHI BHI register space
  * @bhie: Points to base of MHI BHIe register space
@@ -370,6 +371,7 @@ struct mhi_controller_config {
 struct mhi_controller {
 	struct device *cntrl_dev;
 	struct mhi_device *mhi_dev;
+	struct dentry *debugfs_dentry;
 	void __iomem *regs;
 	void __iomem *bhi;
 	void __iomem *bhie;
-- 
cgit v1.2.3


From 9654ab011e28ee756d231035c488509dc214fa6f Mon Sep 17 00:00:00 2001
From: Loic Poulain <loic.poulain@linaro.org>
Date: Tue, 29 Sep 2020 23:22:16 +0530
Subject: bus: mhi: Remove unused nr_irqs_req variable

nr_irqs_req is unused in MHI stack.

Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Loic Poulain <loic.poulain@linaro.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20200929175218.8178-18-manivannan.sadhasivam@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/mhi/core/init.c | 3 ---
 include/linux/mhi.h         | 2 --
 2 files changed, 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/bus/mhi/core/init.c b/drivers/bus/mhi/core/init.c
index 103d51f35e28..0ffdebde8265 100644
--- a/drivers/bus/mhi/core/init.c
+++ b/drivers/bus/mhi/core/init.c
@@ -680,9 +680,6 @@ static int parse_ev_cfg(struct mhi_controller *mhi_cntrl,
 		mhi_event++;
 	}
 
-	/* We need IRQ for each event ring + additional one for BHI */
-	mhi_cntrl->nr_irqs_req = mhi_cntrl->total_ev_rings + 1;
-
 	return 0;
 
 error_ev_cfg:
diff --git a/include/linux/mhi.h b/include/linux/mhi.h
index fb45a0ff9aa3..d4841e5a5f45 100644
--- a/include/linux/mhi.h
+++ b/include/linux/mhi.h
@@ -312,7 +312,6 @@ struct mhi_controller_config {
  * @total_ev_rings: Total # of event rings allocated
  * @hw_ev_rings: Number of hardware event rings
  * @sw_ev_rings: Number of software event rings
- * @nr_irqs_req: Number of IRQs required to operate (optional)
  * @nr_irqs: Number of IRQ allocated by bus master (required)
  * @family_number: MHI controller family number
  * @device_number: MHI controller device number
@@ -393,7 +392,6 @@ struct mhi_controller {
 	u32 total_ev_rings;
 	u32 hw_ev_rings;
 	u32 sw_ev_rings;
-	u32 nr_irqs_req;
 	u32 nr_irqs;
 	u32 family_number;
 	u32 device_number;
-- 
cgit v1.2.3


From 2efc459d06f1630001e3984854848a5647086232 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Wed, 16 Sep 2020 13:40:38 -0700
Subject: sysfs: Add sysfs_emit and sysfs_emit_at to format sysfs output

Output defects can exist in sysfs content using sprintf and snprintf.

sprintf does not know the PAGE_SIZE maximum of the temporary buffer
used for outputting sysfs content and it's possible to overrun the
PAGE_SIZE buffer length.

Add a generic sysfs_emit function that knows that the size of the
temporary buffer and ensures that no overrun is done.

Add a generic sysfs_emit_at function that can be used in multiple
call situations that also ensures that no overrun is done.

Validate the output buffer argument to be page aligned.
Validate the offset len argument to be within the PAGE_SIZE buf.

Signed-off-by: Joe Perches <joe@perches.com>
Link: https://lore.kernel.org/r/884235202216d464d61ee975f7465332c86f76b2.1600285923.git.joe@perches.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/filesystems/sysfs.rst |  8 ++----
 fs/sysfs/file.c                     | 55 +++++++++++++++++++++++++++++++++++++
 include/linux/sysfs.h               | 15 ++++++++++
 3 files changed, 73 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/sysfs.rst b/Documentation/filesystems/sysfs.rst
index ab0f7795792b..d44249050f4a 100644
--- a/Documentation/filesystems/sysfs.rst
+++ b/Documentation/filesystems/sysfs.rst
@@ -242,12 +242,10 @@ Other notes:
   is 4096.
 
 - show() methods should return the number of bytes printed into the
-  buffer. This is the return value of scnprintf().
+  buffer.
 
-- show() must not use snprintf() when formatting the value to be
-  returned to user space. If you can guarantee that an overflow
-  will never happen you can use sprintf() otherwise you must use
-  scnprintf().
+- show() should only use sysfs_emit() or sysfs_emit_at() when formatting
+  the value to be returned to user space.
 
 - store() should return the number of bytes used from the buffer. If the
   entire buffer has been used, just return the count argument.
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index eb6897ab78e7..96d0da65e088 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -15,6 +15,7 @@
 #include <linux/list.h>
 #include <linux/mutex.h>
 #include <linux/seq_file.h>
+#include <linux/mm.h>
 
 #include "sysfs.h"
 
@@ -707,3 +708,57 @@ int sysfs_change_owner(struct kobject *kobj, kuid_t kuid, kgid_t kgid)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(sysfs_change_owner);
+
+/**
+ *	sysfs_emit - scnprintf equivalent, aware of PAGE_SIZE buffer.
+ *	@buf:	start of PAGE_SIZE buffer.
+ *	@fmt:	format
+ *	@...:	optional arguments to @format
+ *
+ *
+ * Returns number of characters written to @buf.
+ */
+int sysfs_emit(char *buf, const char *fmt, ...)
+{
+	va_list args;
+	int len;
+
+	if (WARN(!buf || offset_in_page(buf),
+		 "invalid sysfs_emit: buf:%p\n", buf))
+		return 0;
+
+	va_start(args, fmt);
+	len = vscnprintf(buf, PAGE_SIZE, fmt, args);
+	va_end(args);
+
+	return len;
+}
+EXPORT_SYMBOL_GPL(sysfs_emit);
+
+/**
+ *	sysfs_emit_at - scnprintf equivalent, aware of PAGE_SIZE buffer.
+ *	@buf:	start of PAGE_SIZE buffer.
+ *	@at:	offset in @buf to start write in bytes
+ *		@at must be >= 0 && < PAGE_SIZE
+ *	@fmt:	format
+ *	@...:	optional arguments to @fmt
+ *
+ *
+ * Returns number of characters written starting at &@buf[@at].
+ */
+int sysfs_emit_at(char *buf, int at, const char *fmt, ...)
+{
+	va_list args;
+	int len;
+
+	if (WARN(!buf || offset_in_page(buf) || at < 0 || at >= PAGE_SIZE,
+		 "invalid sysfs_emit_at: buf:%p at:%d\n", buf, at))
+		return 0;
+
+	va_start(args, fmt);
+	len = vscnprintf(buf + at, PAGE_SIZE - at, fmt, args);
+	va_end(args);
+
+	return len;
+}
+EXPORT_SYMBOL_GPL(sysfs_emit_at);
diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h
index 34e84122f635..2caa34c1ca1a 100644
--- a/include/linux/sysfs.h
+++ b/include/linux/sysfs.h
@@ -329,6 +329,10 @@ int sysfs_groups_change_owner(struct kobject *kobj,
 int sysfs_group_change_owner(struct kobject *kobj,
 			     const struct attribute_group *groups, kuid_t kuid,
 			     kgid_t kgid);
+__printf(2, 3)
+int sysfs_emit(char *buf, const char *fmt, ...);
+__printf(3, 4)
+int sysfs_emit_at(char *buf, int at, const char *fmt, ...);
 
 #else /* CONFIG_SYSFS */
 
@@ -576,6 +580,17 @@ static inline int sysfs_group_change_owner(struct kobject *kobj,
 	return 0;
 }
 
+__printf(2, 3)
+static inline int sysfs_emit(char *buf, const char *fmt, ...)
+{
+	return 0;
+}
+
+__printf(3, 4)
+static inline int sysfs_emit_at(char *buf, int at, const char *fmt, ...)
+{
+	return 0;
+}
 #endif /* CONFIG_SYSFS */
 
 static inline int __must_check sysfs_create_file(struct kobject *kobj,
-- 
cgit v1.2.3


From 7981593bf083801035b1f1377661849805acb216 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Wed, 16 Sep 2020 13:40:43 -0700
Subject: mm: and drivers core: Convert hugetlb_report_node_meminfo to
 sysfs_emit

Convert the unbound sprintf in hugetlb_report_node_meminfo to use
sysfs_emit_at so that no possible overrun of a PAGE_SIZE buf can occur.

Signed-off-by: Joe Perches <joe@perches.com>
Acked-by: Mike Kravetz <mike.kravetz@oracle.com>
Link: https://lore.kernel.org/r/894b351b82da6013cde7f36ff4b5493cd0ec30d0.1600285923.git.joe@perches.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/node.c     |  2 +-
 include/linux/hugetlb.h |  4 ++--
 mm/hugetlb.c            | 18 ++++++++++--------
 3 files changed, 13 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/node.c b/drivers/base/node.c
index 96d820f979a2..6366f94f8afb 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -473,7 +473,7 @@ static ssize_t node_read_meminfo(struct device *dev,
 				    HPAGE_PMD_NR)
 #endif
 			    );
-	len += hugetlb_report_node_meminfo(nid, buf + len);
+	len += hugetlb_report_node_meminfo(buf, len, nid);
 	return len;
 }
 
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index d5cc5f802dd4..ebca2ef02212 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -129,7 +129,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 				unsigned long start, unsigned long end,
 				struct page *ref_page);
 void hugetlb_report_meminfo(struct seq_file *);
-int hugetlb_report_node_meminfo(int, char *);
+int hugetlb_report_node_meminfo(char *buf, int len, int nid);
 void hugetlb_show_meminfo(void);
 unsigned long hugetlb_total_pages(void);
 vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
@@ -245,7 +245,7 @@ static inline void hugetlb_report_meminfo(struct seq_file *m)
 {
 }
 
-static inline int hugetlb_report_node_meminfo(int nid, char *buf)
+static inline int hugetlb_report_node_meminfo(char *buf, int len, int nid)
 {
 	return 0;
 }
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 67fc6383995b..365ef52a5b29 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3582,18 +3582,20 @@ void hugetlb_report_meminfo(struct seq_file *m)
 	seq_printf(m, "Hugetlb:        %8lu kB\n", total / 1024);
 }
 
-int hugetlb_report_node_meminfo(int nid, char *buf)
+int hugetlb_report_node_meminfo(char *buf, int len, int nid)
 {
 	struct hstate *h = &default_hstate;
+
 	if (!hugepages_supported())
 		return 0;
-	return sprintf(buf,
-		"Node %d HugePages_Total: %5u\n"
-		"Node %d HugePages_Free:  %5u\n"
-		"Node %d HugePages_Surp:  %5u\n",
-		nid, h->nr_huge_pages_node[nid],
-		nid, h->free_huge_pages_node[nid],
-		nid, h->surplus_huge_pages_node[nid]);
+
+	return sysfs_emit_at(buf, len,
+			     "Node %d HugePages_Total: %5u\n"
+			     "Node %d HugePages_Free:  %5u\n"
+			     "Node %d HugePages_Surp:  %5u\n",
+			     nid, h->nr_huge_pages_node[nid],
+			     nid, h->free_huge_pages_node[nid],
+			     nid, h->surplus_huge_pages_node[nid]);
 }
 
 void hugetlb_show_meminfo(void)
-- 
cgit v1.2.3


From 12f3467b0d28369d3add7a0deb65fdac9b503c90 Mon Sep 17 00:00:00 2001
From: Amelie Delaunay <amelie.delaunay@st.com>
Date: Thu, 24 Sep 2020 11:00:45 +0200
Subject: usb: typec: add typec_find_pwr_opmode

This patch adds a function that converts power operation mode string into
power operation mode value.

It is useful to configure power operation mode through device tree
property, as power capabilities may be linked to hardware design.

Acked-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Signed-off-by: Amelie Delaunay <amelie.delaunay@st.com>
Link: https://lore.kernel.org/r/20200924090049.9041-3-amelie.delaunay@st.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/class.c | 15 +++++++++++++++
 include/linux/usb/typec.h |  1 +
 2 files changed, 16 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c
index 02655694f200..35eec707cb51 100644
--- a/drivers/usb/typec/class.c
+++ b/drivers/usb/typec/class.c
@@ -1448,6 +1448,21 @@ void typec_set_pwr_opmode(struct typec_port *port,
 }
 EXPORT_SYMBOL_GPL(typec_set_pwr_opmode);
 
+/**
+ * typec_find_pwr_opmode - Get the typec power operation mode capability
+ * @name: power operation mode string
+ *
+ * This routine is used to find the typec_pwr_opmode by its string @name.
+ *
+ * Returns typec_pwr_opmode if success, otherwise negative error code.
+ */
+int typec_find_pwr_opmode(const char *name)
+{
+	return match_string(typec_pwr_opmodes,
+			    ARRAY_SIZE(typec_pwr_opmodes), name);
+}
+EXPORT_SYMBOL_GPL(typec_find_pwr_opmode);
+
 /**
  * typec_find_orientation - Convert orientation string to enum typec_orientation
  * @name: Orientation string
diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h
index 9cb1bec94b71..6be558045942 100644
--- a/include/linux/usb/typec.h
+++ b/include/linux/usb/typec.h
@@ -268,6 +268,7 @@ int typec_set_mode(struct typec_port *port, int mode);
 
 void *typec_get_drvdata(struct typec_port *port);
 
+int typec_find_pwr_opmode(const char *name);
 int typec_find_orientation(const char *name);
 int typec_find_port_power_role(const char *name);
 int typec_find_power_role(const char *name);
-- 
cgit v1.2.3


From 1f86a00c1159fd77e66b1bd6ff1a183f4d46f34d Mon Sep 17 00:00:00 2001
From: Bharat Bhushan <Bharat.Bhushan@nxp.com>
Date: Tue, 29 Sep 2020 11:54:31 +0300
Subject: bus/fsl-mc: add support for 'driver_override' in the mc-bus

This patch is required for vfio-fsl-mc meta driver to successfully bind
layerscape container devices for device passthrough. This patch adds
a mechanism to allow a layerscape device to specify a driver rather than
a layerscape driver provide a device match.

Example to allow a device (dprc.1) to specifically bind
with driver (vfio-fsl-mc):-
 - echo vfio-fsl-mc > /sys/bus/fsl-mc/devices/dprc.1/driver_override
 - echo dprc.1 > /sys/bus/fsl-mc/drivers/fsl_mc_dprc/unbind
 - echo dprc.1 > /sys/bus/fsl-mc/drivers/vfio-fsl-mc/bind

Reviewed-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Acked-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Signed-off-by: Bharat Bhushan <Bharat.Bhushan@nxp.com>
Signed-off-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Signed-off-by: Diana Craciun <diana.craciun@oss.nxp.com>
Link: https://lore.kernel.org/r/20200929085441.17448-4-diana.craciun@oss.nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/fsl-mc/fsl-mc-bus.c | 54 +++++++++++++++++++++++++++++++++++++++++
 include/linux/fsl/mc.h          |  2 ++
 2 files changed, 56 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c
index 7345ecef93f8..ef2878bfafd2 100644
--- a/drivers/bus/fsl-mc/fsl-mc-bus.c
+++ b/drivers/bus/fsl-mc/fsl-mc-bus.c
@@ -3,6 +3,7 @@
  * Freescale Management Complex (MC) bus driver
  *
  * Copyright (C) 2014-2016 Freescale Semiconductor, Inc.
+ * Copyright 2019-2020 NXP
  * Author: German Rivera <German.Rivera@freescale.com>
  *
  */
@@ -78,6 +79,12 @@ static int fsl_mc_bus_match(struct device *dev, struct device_driver *drv)
 	struct fsl_mc_driver *mc_drv = to_fsl_mc_driver(drv);
 	bool found = false;
 
+	/* When driver_override is set, only bind to the matching driver */
+	if (mc_dev->driver_override) {
+		found = !strcmp(mc_dev->driver_override, mc_drv->driver.name);
+		goto out;
+	}
+
 	if (!mc_drv->match_id_table)
 		goto out;
 
@@ -147,8 +154,52 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_RO(modalias);
 
+static ssize_t driver_override_store(struct device *dev,
+				     struct device_attribute *attr,
+				     const char *buf, size_t count)
+{
+	struct fsl_mc_device *mc_dev = to_fsl_mc_device(dev);
+	char *driver_override, *old = mc_dev->driver_override;
+	char *cp;
+
+	if (WARN_ON(dev->bus != &fsl_mc_bus_type))
+		return -EINVAL;
+
+	if (count >= (PAGE_SIZE - 1))
+		return -EINVAL;
+
+	driver_override = kstrndup(buf, count, GFP_KERNEL);
+	if (!driver_override)
+		return -ENOMEM;
+
+	cp = strchr(driver_override, '\n');
+	if (cp)
+		*cp = '\0';
+
+	if (strlen(driver_override)) {
+		mc_dev->driver_override = driver_override;
+	} else {
+		kfree(driver_override);
+		mc_dev->driver_override = NULL;
+	}
+
+	kfree(old);
+
+	return count;
+}
+
+static ssize_t driver_override_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	struct fsl_mc_device *mc_dev = to_fsl_mc_device(dev);
+
+	return snprintf(buf, PAGE_SIZE, "%s\n", mc_dev->driver_override);
+}
+static DEVICE_ATTR_RW(driver_override);
+
 static struct attribute *fsl_mc_dev_attrs[] = {
 	&dev_attr_modalias.attr,
+	&dev_attr_driver_override.attr,
 	NULL,
 };
 
@@ -748,6 +799,9 @@ EXPORT_SYMBOL_GPL(fsl_mc_device_add);
  */
 void fsl_mc_device_remove(struct fsl_mc_device *mc_dev)
 {
+	kfree(mc_dev->driver_override);
+	mc_dev->driver_override = NULL;
+
 	/*
 	 * The device-specific remove callback will get invoked by device_del()
 	 */
diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h
index a428c61ead6e..3b5f0c98636d 100644
--- a/include/linux/fsl/mc.h
+++ b/include/linux/fsl/mc.h
@@ -161,6 +161,7 @@ struct fsl_mc_obj_desc {
  * @regions: pointer to array of MMIO region entries
  * @irqs: pointer to array of pointers to interrupts allocated to this device
  * @resource: generic resource associated with this MC object device, if any.
+ * @driver_override: driver name to force a match
  *
  * Generic device object for MC object devices that are "attached" to a
  * MC bus.
@@ -194,6 +195,7 @@ struct fsl_mc_device {
 	struct fsl_mc_device_irq **irqs;
 	struct fsl_mc_resource *resource;
 	struct device_link *consumer_link;
+	char   *driver_override;
 };
 
 #define to_fsl_mc_device(_dev) \
-- 
cgit v1.2.3


From e0c171d5537f45185c2e8f97b9ab2e2fdea56fa9 Mon Sep 17 00:00:00 2001
From: Diana Craciun <diana.craciun@oss.nxp.com>
Date: Tue, 29 Sep 2020 11:54:32 +0300
Subject: bus/fsl-mc: Set the QMAN/BMAN region flags

The QMAN region is memory mapped, so it should be of type
IORESOURCE_MEM. The region flags bits were wrongly used to
pass additional information. Use the bus specific bits for
this purpose.

Reviewed-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Acked-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Signed-off-by: Diana Craciun <diana.craciun@oss.nxp.com>
Link: https://lore.kernel.org/r/20200929085441.17448-5-diana.craciun@oss.nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/fsl-mc/fsl-mc-bus.c     | 7 ++-----
 drivers/bus/fsl-mc/fsl-mc-private.h | 6 ------
 include/linux/fsl/mc.h              | 8 ++++++++
 3 files changed, 10 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c
index ef2878bfafd2..c4be4901de68 100644
--- a/drivers/bus/fsl-mc/fsl-mc-bus.c
+++ b/drivers/bus/fsl-mc/fsl-mc-bus.c
@@ -615,11 +615,8 @@ static int fsl_mc_device_get_mmio_regions(struct fsl_mc_device *mc_dev,
 
 		regions[i].end = regions[i].start + region_desc.size - 1;
 		regions[i].name = "fsl-mc object MMIO region";
-		regions[i].flags = IORESOURCE_IO;
-		if (region_desc.flags & DPRC_REGION_CACHEABLE)
-			regions[i].flags |= IORESOURCE_CACHEABLE;
-		if (region_desc.flags & DPRC_REGION_SHAREABLE)
-			regions[i].flags |= IORESOURCE_MEM;
+		regions[i].flags = region_desc.flags & IORESOURCE_BITS;
+		regions[i].flags |= IORESOURCE_MEM;
 	}
 
 	mc_dev->regions = regions;
diff --git a/drivers/bus/fsl-mc/fsl-mc-private.h b/drivers/bus/fsl-mc/fsl-mc-private.h
index 7a46a12eb747..9f200731b274 100644
--- a/drivers/bus/fsl-mc/fsl-mc-private.h
+++ b/drivers/bus/fsl-mc/fsl-mc-private.h
@@ -358,12 +358,6 @@ int dprc_set_obj_irq(struct fsl_mc_io *mc_io,
 		     int obj_id,
 		     u8 irq_index,
 		     struct dprc_irq_cfg *irq_cfg);
-
-/* Region flags */
-/* Cacheable - Indicates that region should be mapped as cacheable */
-#define DPRC_REGION_CACHEABLE	0x00000001
-#define DPRC_REGION_SHAREABLE	0x00000002
-
 /**
  * enum dprc_region_type - Region type
  * @DPRC_REGION_TYPE_MC_PORTAL: MC portal region
diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h
index 3b5f0c98636d..03a5d16dde73 100644
--- a/include/linux/fsl/mc.h
+++ b/include/linux/fsl/mc.h
@@ -3,6 +3,7 @@
  * Freescale Management Complex (MC) bus public interface
  *
  * Copyright (C) 2014-2016 Freescale Semiconductor, Inc.
+ * Copyright 2019-2020 NXP
  * Author: German Rivera <German.Rivera@freescale.com>
  *
  */
@@ -148,6 +149,13 @@ struct fsl_mc_obj_desc {
  */
 #define FSL_MC_IS_DPRC	0x0001
 
+/* Region flags */
+/* Indicates that region can be mapped as cacheable */
+#define FSL_MC_REGION_CACHEABLE	0x00000001
+
+/* Indicates that region can be mapped as shareable */
+#define FSL_MC_REGION_SHAREABLE	0x00000002
+
 /**
  * struct fsl_mc_device - MC object device object
  * @dev: Linux driver model device object
-- 
cgit v1.2.3


From 715b02ce8968bd560d295945520bae6d73707a73 Mon Sep 17 00:00:00 2001
From: Bharat Bhushan <Bharat.Bhushan@nxp.com>
Date: Tue, 29 Sep 2020 11:54:34 +0300
Subject: bus/fsl-mc: Add dprc-reset-container support

DPRC reset is required by VFIO-mc in order to stop a device
to further generate DMA transactions.

Reviewed-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Acked-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Signed-off-by: Bharat Bhushan <Bharat.Bhushan@nxp.com>
Signed-off-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Signed-off-by: Diana Craciun <diana.craciun@oss.nxp.com>
Link: https://lore.kernel.org/r/20200929085441.17448-7-diana.craciun@oss.nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/fsl-mc/dprc.c           | 71 +++++++++++++++++++++++++++++++++++++
 drivers/bus/fsl-mc/fsl-mc-private.h |  7 ++++
 include/linux/fsl/mc.h              |  7 ++++
 3 files changed, 85 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/bus/fsl-mc/dprc.c b/drivers/bus/fsl-mc/dprc.c
index e76f2c76f4c8..2448a723eb28 100644
--- a/drivers/bus/fsl-mc/dprc.c
+++ b/drivers/bus/fsl-mc/dprc.c
@@ -80,6 +80,77 @@ int dprc_close(struct fsl_mc_io *mc_io,
 }
 EXPORT_SYMBOL_GPL(dprc_close);
 
+/**
+ * dprc_reset_container - Reset child container.
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:	Token of DPRC object
+ * @child_container_id:	ID of the container to reset
+ * @options: 32 bit options:
+ *   - 0 (no bits set) - all the objects inside the container are
+ *     reset. The child containers are entered recursively and the
+ *     objects reset. All the objects (including the child containers)
+ *     are closed.
+ *   - bit 0 set - all the objects inside the container are reset.
+ *     However the child containers are not entered recursively.
+ *     This option is supported for API versions >= 6.5
+ * In case a software context crashes or becomes non-responsive, the parent
+ * may wish to reset its resources container before the software context is
+ * restarted.
+ *
+ * This routine informs all objects assigned to the child container that the
+ * container is being reset, so they may perform any cleanup operations that are
+ * needed. All objects handles that were owned by the child container shall be
+ * closed.
+ *
+ * Note that such request may be submitted even if the child software context
+ * has not crashed, but the resulting object cleanup operations will not be
+ * aware of that.
+ *
+ * Return:	'0' on Success; Error code otherwise.
+ */
+int dprc_reset_container(struct fsl_mc_io *mc_io,
+			 u32 cmd_flags,
+			 u16 token,
+			 int child_container_id,
+			 u32 options)
+{
+	struct fsl_mc_command cmd = { 0 };
+	struct dprc_cmd_reset_container *cmd_params;
+	u32 cmdid = DPRC_CMDID_RESET_CONT;
+	int err;
+
+	/*
+	 * If the DPRC object version was not yet cached, cache it now.
+	 * Otherwise use the already cached value.
+	 */
+	if (!dprc_major_ver && !dprc_minor_ver) {
+		err = dprc_get_api_version(mc_io, 0,
+				&dprc_major_ver,
+				&dprc_minor_ver);
+		if (err)
+			return err;
+	}
+
+	/*
+	 * MC API 6.5 introduced a new field in the command used to pass
+	 * some flags.
+	 * Bit 0 indicates that the child containers are not recursively reset.
+	 */
+	if (dprc_major_ver > 6 || (dprc_major_ver == 6 && dprc_minor_ver >= 5))
+		cmdid = DPRC_CMDID_RESET_CONT_V2;
+
+	/* prepare command */
+	cmd.header = mc_encode_cmd_header(cmdid, cmd_flags, token);
+	cmd_params = (struct dprc_cmd_reset_container *)cmd.params;
+	cmd_params->child_container_id = cpu_to_le32(child_container_id);
+	cmd_params->options = cpu_to_le32(options);
+
+	/* send command to mc*/
+	return mc_send_command(mc_io, &cmd);
+}
+EXPORT_SYMBOL_GPL(dprc_reset_container);
+
 /**
  * dprc_set_irq() - Set IRQ information for the DPRC to trigger an interrupt.
  * @mc_io:	Pointer to MC portal's I/O object
diff --git a/drivers/bus/fsl-mc/fsl-mc-private.h b/drivers/bus/fsl-mc/fsl-mc-private.h
index 9f200731b274..5f7e762d517c 100644
--- a/drivers/bus/fsl-mc/fsl-mc-private.h
+++ b/drivers/bus/fsl-mc/fsl-mc-private.h
@@ -91,6 +91,8 @@ int dpmcp_reset(struct fsl_mc_io *mc_io,
 #define DPRC_CMDID_GET_API_VERSION              DPRC_CMD(0xa05)
 
 #define DPRC_CMDID_GET_ATTR                     DPRC_CMD(0x004)
+#define DPRC_CMDID_RESET_CONT                   DPRC_CMD(0x005)
+#define DPRC_CMDID_RESET_CONT_V2                DPRC_CMD_V2(0x005)
 
 #define DPRC_CMDID_SET_IRQ                      DPRC_CMD(0x010)
 #define DPRC_CMDID_SET_IRQ_ENABLE               DPRC_CMD(0x012)
@@ -111,6 +113,11 @@ struct dprc_cmd_open {
 	__le32 container_id;
 };
 
+struct dprc_cmd_reset_container {
+	__le32 child_container_id;
+	__le32 options;
+};
+
 struct dprc_cmd_set_irq {
 	/* cmd word 0 */
 	__le32 irq_val;
diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h
index 03a5d16dde73..1d8800acf21f 100644
--- a/include/linux/fsl/mc.h
+++ b/include/linux/fsl/mc.h
@@ -524,6 +524,13 @@ static inline bool is_fsl_mc_bus_dpdmai(const struct fsl_mc_device *mc_dev)
 	return mc_dev->dev.type == &fsl_mc_bus_dpdmai_type;
 }
 
+#define DPRC_RESET_OPTION_NON_RECURSIVE                0x00000001
+int dprc_reset_container(struct fsl_mc_io *mc_io,
+			 u32 cmd_flags,
+			 u16 token,
+			 int child_container_id,
+			 u32 options);
+
 /*
  * Data Path Buffer Pool (DPBP) API
  * Contains initialization APIs and runtime control APIs for DPBP
-- 
cgit v1.2.3


From 5d781fabe64244ccf8a954617ea8b28737517b1c Mon Sep 17 00:00:00 2001
From: Diana Craciun <diana.craciun@oss.nxp.com>
Date: Tue, 29 Sep 2020 11:54:35 +0300
Subject: bus/fsl-mc: Export dprc_scan/dprc_remove functions to be used by
 multiple entities

Currently the DPRC scan function is used only by the bus driver.
But the same functionality will be needed by the VFIO driver.
To support this, the dprc scan function was exported and a little
bit adjusted to fit both scenarios. Also the scan mutex initialization
is done when the bus object is created, not in dprc_probe in order
to be used by both VFIO and bus driver.
Similarily dprc_remove_devices is exported to be used by VFIO.

Reviewed-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Acked-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Signed-off-by: Diana Craciun <diana.craciun@oss.nxp.com>
Link: https://lore.kernel.org/r/20200929085441.17448-8-diana.craciun@oss.nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/fsl-mc/dprc-driver.c | 26 +++++++++++---------------
 drivers/bus/fsl-mc/fsl-mc-bus.c  |  1 +
 include/linux/fsl/mc.h           |  7 +++++++
 3 files changed, 19 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/bus/fsl-mc/dprc-driver.c b/drivers/bus/fsl-mc/dprc-driver.c
index 3d850515e3e5..dde8fe965e30 100644
--- a/drivers/bus/fsl-mc/dprc-driver.c
+++ b/drivers/bus/fsl-mc/dprc-driver.c
@@ -81,9 +81,9 @@ static int __fsl_mc_device_remove(struct device *dev, void *data)
  * the MC by removing devices that represent MC objects that have
  * been dynamically removed in the physical DPRC.
  */
-static void dprc_remove_devices(struct fsl_mc_device *mc_bus_dev,
-				struct fsl_mc_obj_desc *obj_desc_array,
-				int num_child_objects_in_mc)
+void dprc_remove_devices(struct fsl_mc_device *mc_bus_dev,
+			 struct fsl_mc_obj_desc *obj_desc_array,
+			 int num_child_objects_in_mc)
 {
 	if (num_child_objects_in_mc != 0) {
 		/*
@@ -105,6 +105,7 @@ static void dprc_remove_devices(struct fsl_mc_device *mc_bus_dev,
 				      __fsl_mc_device_remove);
 	}
 }
+EXPORT_SYMBOL_GPL(dprc_remove_devices);
 
 static int __fsl_mc_device_match(struct device *dev, void *data)
 {
@@ -354,9 +355,10 @@ static int dprc_scan_objects(struct fsl_mc_device *mc_bus_dev,
  * bus driver with the actual state of the MC by adding and removing
  * devices as appropriate.
  */
-static int dprc_scan_container(struct fsl_mc_device *mc_bus_dev)
+int dprc_scan_container(struct fsl_mc_device *mc_bus_dev,
+			bool alloc_interrupts)
 {
-	int error;
+	int error = 0;
 	struct fsl_mc_bus *mc_bus = to_fsl_mc_bus(mc_bus_dev);
 
 	fsl_mc_init_all_resource_pools(mc_bus_dev);
@@ -365,16 +367,12 @@ static int dprc_scan_container(struct fsl_mc_device *mc_bus_dev)
 	 * Discover objects in the DPRC:
 	 */
 	mutex_lock(&mc_bus->scan_mutex);
-	error = dprc_scan_objects(mc_bus_dev, true);
+	error = dprc_scan_objects(mc_bus_dev, alloc_interrupts);
 	mutex_unlock(&mc_bus->scan_mutex);
-	if (error < 0) {
-		fsl_mc_cleanup_all_resource_pools(mc_bus_dev);
-		return error;
-	}
 
-	return 0;
+	return error;
 }
-
+EXPORT_SYMBOL_GPL(dprc_scan_container);
 /**
  * dprc_irq0_handler - Regular ISR for DPRC interrupt 0
  *
@@ -683,12 +681,10 @@ static int dprc_probe(struct fsl_mc_device *mc_dev)
 		goto error_cleanup_open;
 	}
 
-	mutex_init(&mc_bus->scan_mutex);
-
 	/*
 	 * Discover MC objects in DPRC object:
 	 */
-	error = dprc_scan_container(mc_dev);
+	error = dprc_scan_container(mc_dev, true);
 	if (error < 0)
 		goto error_cleanup_open;
 
diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c
index c4be4901de68..d53315f42dc2 100644
--- a/drivers/bus/fsl-mc/fsl-mc-bus.c
+++ b/drivers/bus/fsl-mc/fsl-mc-bus.c
@@ -678,6 +678,7 @@ int fsl_mc_device_add(struct fsl_mc_obj_desc *obj_desc,
 		if (!mc_bus)
 			return -ENOMEM;
 
+		mutex_init(&mc_bus->scan_mutex);
 		mc_dev = &mc_bus->mc_dev;
 	} else {
 		/*
diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h
index 1d8800acf21f..da11171bc38f 100644
--- a/include/linux/fsl/mc.h
+++ b/include/linux/fsl/mc.h
@@ -531,6 +531,13 @@ int dprc_reset_container(struct fsl_mc_io *mc_io,
 			 int child_container_id,
 			 u32 options);
 
+int dprc_scan_container(struct fsl_mc_device *mc_bus_dev,
+			bool alloc_interrupts);
+
+void dprc_remove_devices(struct fsl_mc_device *mc_bus_dev,
+			 struct fsl_mc_obj_desc *obj_desc_array,
+			 int num_child_objects_in_mc);
+
 /*
  * Data Path Buffer Pool (DPBP) API
  * Contains initialization APIs and runtime control APIs for DPBP
-- 
cgit v1.2.3


From 46f35b5fbbbb22896839e5dbcc24d020926dca36 Mon Sep 17 00:00:00 2001
From: Diana Craciun <diana.craciun@oss.nxp.com>
Date: Tue, 29 Sep 2020 11:54:36 +0300
Subject: bus/fsl-mc: Export a cleanup function for DPRC

Create and export a cleanup function for DPRC. The function
is used by the DPRC driver, but it will be used by the VFIO
driver as well.

Reviewed-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Acked-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Signed-off-by: Diana Craciun <diana.craciun@oss.nxp.com>
Link: https://lore.kernel.org/r/20200929085441.17448-9-diana.craciun@oss.nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/fsl-mc/dprc-driver.c | 62 ++++++++++++++++++++++++++++++----------
 include/linux/fsl/mc.h           |  2 ++
 2 files changed, 49 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/bus/fsl-mc/dprc-driver.c b/drivers/bus/fsl-mc/dprc-driver.c
index dde8fe965e30..516119c8121a 100644
--- a/drivers/bus/fsl-mc/dprc-driver.c
+++ b/drivers/bus/fsl-mc/dprc-driver.c
@@ -728,33 +728,26 @@ static void dprc_teardown_irq(struct fsl_mc_device *mc_dev)
 }
 
 /**
- * dprc_remove - callback invoked when a DPRC is being unbound from this driver
+ * dprc_cleanup - function that cleanups a DPRC
  *
  * @mc_dev: Pointer to fsl-mc device representing the DPRC
  *
- * It removes the DPRC's child objects from Linux (not from the MC) and
- * closes the DPRC device in the MC.
- * It tears down the interrupts that were configured for the DPRC device.
+ * It closes the DPRC device in the MC.
  * It destroys the interrupt pool associated with this MC bus.
  */
-static int dprc_remove(struct fsl_mc_device *mc_dev)
+
+int dprc_cleanup(struct fsl_mc_device *mc_dev)
 {
 	int error;
 	struct fsl_mc_bus *mc_bus = to_fsl_mc_bus(mc_dev);
 
-	if (!is_fsl_mc_bus_dprc(mc_dev))
-		return -EINVAL;
-	if (!mc_dev->mc_io)
-		return -EINVAL;
 
-	if (!mc_bus->irq_resources)
+	/* this function should be called only for DPRCs, it
+	 * is an error to call it for regular objects
+	 */
+	if (!is_fsl_mc_bus_dprc(mc_dev))
 		return -EINVAL;
 
-	if (dev_get_msi_domain(&mc_dev->dev))
-		dprc_teardown_irq(mc_dev);
-
-	device_for_each_child(&mc_dev->dev, NULL, __fsl_mc_device_remove);
-
 	if (dev_get_msi_domain(&mc_dev->dev)) {
 		fsl_mc_cleanup_irq_pool(mc_bus);
 		dev_set_msi_domain(&mc_dev->dev, NULL);
@@ -762,6 +755,14 @@ static int dprc_remove(struct fsl_mc_device *mc_dev)
 
 	fsl_mc_cleanup_all_resource_pools(mc_dev);
 
+	/* if this step fails we cannot go further with cleanup as there is no way of
+	 * communicating with the firmware
+	 */
+	if (!mc_dev->mc_io) {
+		dev_err(&mc_dev->dev, "mc_io is NULL, tear down cannot be performed in firmware\n");
+		return -EINVAL;
+	}
+
 	error = dprc_close(mc_dev->mc_io, 0, mc_dev->mc_handle);
 	if (error < 0)
 		dev_err(&mc_dev->dev, "dprc_close() failed: %d\n", error);
@@ -771,6 +772,37 @@ static int dprc_remove(struct fsl_mc_device *mc_dev)
 		mc_dev->mc_io = NULL;
 	}
 
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dprc_cleanup);
+
+/**
+ * dprc_remove - callback invoked when a DPRC is being unbound from this driver
+ *
+ * @mc_dev: Pointer to fsl-mc device representing the DPRC
+ *
+ * It removes the DPRC's child objects from Linux (not from the MC) and
+ * closes the DPRC device in the MC.
+ * It tears down the interrupts that were configured for the DPRC device.
+ * It destroys the interrupt pool associated with this MC bus.
+ */
+static int dprc_remove(struct fsl_mc_device *mc_dev)
+{
+	struct fsl_mc_bus *mc_bus = to_fsl_mc_bus(mc_dev);
+
+	if (!is_fsl_mc_bus_dprc(mc_dev))
+		return -EINVAL;
+
+	if (!mc_bus->irq_resources)
+		return -EINVAL;
+
+	if (dev_get_msi_domain(&mc_dev->dev))
+		dprc_teardown_irq(mc_dev);
+
+	device_for_each_child(&mc_dev->dev, NULL, __fsl_mc_device_remove);
+
+	dprc_cleanup(mc_dev);
+
 	dev_info(&mc_dev->dev, "DPRC device unbound from driver");
 	return 0;
 }
diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h
index da11171bc38f..5519a510b8c9 100644
--- a/include/linux/fsl/mc.h
+++ b/include/linux/fsl/mc.h
@@ -538,6 +538,8 @@ void dprc_remove_devices(struct fsl_mc_device *mc_bus_dev,
 			 struct fsl_mc_obj_desc *obj_desc_array,
 			 int num_child_objects_in_mc);
 
+int dprc_cleanup(struct fsl_mc_device *mc_dev);
+
 /*
  * Data Path Buffer Pool (DPBP) API
  * Contains initialization APIs and runtime control APIs for DPBP
-- 
cgit v1.2.3


From 17eaf21320da965c2571a5f029a2becaffe8313f Mon Sep 17 00:00:00 2001
From: Diana Craciun <diana.craciun@oss.nxp.com>
Date: Tue, 29 Sep 2020 11:54:37 +0300
Subject: bus/fsl-mc: Add a container setup function

Both DPRC driver and VFIO driver use the same initialization code
for the DPRC. Introduced a new function which groups this
initialization code. The function is exported and may be
used by VFIO as well.

Reviewed-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Acked-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Signed-off-by: Diana Craciun <diana.craciun@oss.nxp.com>
Link: https://lore.kernel.org/r/20200929085441.17448-10-diana.craciun@oss.nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/fsl-mc/dprc-driver.c | 71 +++++++++++++++++++++++++++-------------
 include/linux/fsl/mc.h           |  2 ++
 2 files changed, 51 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/bus/fsl-mc/dprc-driver.c b/drivers/bus/fsl-mc/dprc-driver.c
index 516119c8121a..9e4088209cfe 100644
--- a/drivers/bus/fsl-mc/dprc-driver.c
+++ b/drivers/bus/fsl-mc/dprc-driver.c
@@ -588,25 +588,24 @@ error_free_irqs:
 }
 
 /**
- * dprc_probe - callback invoked when a DPRC is being bound to this driver
+ * dprc_setup - opens and creates a mc_io for DPRC
  *
  * @mc_dev: Pointer to fsl-mc device representing a DPRC
  *
  * It opens the physical DPRC in the MC.
- * It scans the DPRC to discover the MC objects contained in it.
- * It creates the interrupt pool for the MC bus associated with the DPRC.
- * It configures the interrupts for the DPRC device itself.
+ * It configures the DPRC portal used to communicate with MC
  */
-static int dprc_probe(struct fsl_mc_device *mc_dev)
+
+int dprc_setup(struct fsl_mc_device *mc_dev)
 {
-	int error;
-	size_t region_size;
 	struct device *parent_dev = mc_dev->dev.parent;
 	struct fsl_mc_bus *mc_bus = to_fsl_mc_bus(mc_dev);
+	struct irq_domain *mc_msi_domain;
 	bool mc_io_created = false;
 	bool msi_domain_set = false;
 	u16 major_ver, minor_ver;
-	struct irq_domain *mc_msi_domain;
+	size_t region_size;
+	int error;
 
 	if (!is_fsl_mc_bus_dprc(mc_dev))
 		return -EINVAL;
@@ -681,35 +680,63 @@ static int dprc_probe(struct fsl_mc_device *mc_dev)
 		goto error_cleanup_open;
 	}
 
+	return 0;
+
+error_cleanup_open:
+	(void)dprc_close(mc_dev->mc_io, 0, mc_dev->mc_handle);
+
+error_cleanup_msi_domain:
+	if (msi_domain_set)
+		dev_set_msi_domain(&mc_dev->dev, NULL);
+
+	if (mc_io_created) {
+		fsl_destroy_mc_io(mc_dev->mc_io);
+		mc_dev->mc_io = NULL;
+	}
+
+	return error;
+}
+EXPORT_SYMBOL_GPL(dprc_setup);
+
+/**
+ * dprc_probe - callback invoked when a DPRC is being bound to this driver
+ *
+ * @mc_dev: Pointer to fsl-mc device representing a DPRC
+ *
+ * It opens the physical DPRC in the MC.
+ * It scans the DPRC to discover the MC objects contained in it.
+ * It creates the interrupt pool for the MC bus associated with the DPRC.
+ * It configures the interrupts for the DPRC device itself.
+ */
+static int dprc_probe(struct fsl_mc_device *mc_dev)
+{
+	int error;
+
+	error = dprc_setup(mc_dev);
+	if (error < 0)
+		return error;
+
 	/*
 	 * Discover MC objects in DPRC object:
 	 */
 	error = dprc_scan_container(mc_dev, true);
 	if (error < 0)
-		goto error_cleanup_open;
+		goto dprc_cleanup;
 
 	/*
 	 * Configure interrupt for the DPRC object associated with this MC bus:
 	 */
 	error = dprc_setup_irq(mc_dev);
 	if (error < 0)
-		goto error_cleanup_open;
+		goto scan_cleanup;
 
 	dev_info(&mc_dev->dev, "DPRC device bound to driver");
 	return 0;
 
-error_cleanup_open:
-	(void)dprc_close(mc_dev->mc_io, 0, mc_dev->mc_handle);
-
-error_cleanup_msi_domain:
-	if (msi_domain_set)
-		dev_set_msi_domain(&mc_dev->dev, NULL);
-
-	if (mc_io_created) {
-		fsl_destroy_mc_io(mc_dev->mc_io);
-		mc_dev->mc_io = NULL;
-	}
-
+scan_cleanup:
+	device_for_each_child(&mc_dev->dev, NULL, __fsl_mc_device_remove);
+dprc_cleanup:
+	dprc_cleanup(mc_dev);
 	return error;
 }
 
diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h
index 5519a510b8c9..e99d181ee4cd 100644
--- a/include/linux/fsl/mc.h
+++ b/include/linux/fsl/mc.h
@@ -540,6 +540,8 @@ void dprc_remove_devices(struct fsl_mc_device *mc_bus_dev,
 
 int dprc_cleanup(struct fsl_mc_device *mc_dev);
 
+int dprc_setup(struct fsl_mc_device *mc_dev);
+
 /*
  * Data Path Buffer Pool (DPBP) API
  * Contains initialization APIs and runtime control APIs for DPBP
-- 
cgit v1.2.3


From 0dadd95216d56cec01cef066eebe6354f069ff34 Mon Sep 17 00:00:00 2001
From: Diana Craciun <diana.craciun@oss.nxp.com>
Date: Tue, 29 Sep 2020 11:54:39 +0300
Subject: bus/fsl-mc: Export IRQ pool handling functions to be used by VFIO

The IRQ pool handling functions can be used by both DPRC
driver and VFIO. Adapt and export those functions.

Reviewed-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Acked-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Signed-off-by: Diana Craciun <diana.craciun@oss.nxp.com>
Link: https://lore.kernel.org/r/20200929085441.17448-12-diana.craciun@oss.nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/fsl-mc/dprc-driver.c      |  8 +++-----
 drivers/bus/fsl-mc/fsl-mc-allocator.c | 12 ++++++++----
 drivers/bus/fsl-mc/fsl-mc-private.h   | 10 ----------
 include/linux/fsl/mc.h                | 11 +++++++++++
 4 files changed, 22 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/bus/fsl-mc/dprc-driver.c b/drivers/bus/fsl-mc/dprc-driver.c
index 9e4088209cfe..91dc015963a8 100644
--- a/drivers/bus/fsl-mc/dprc-driver.c
+++ b/drivers/bus/fsl-mc/dprc-driver.c
@@ -327,8 +327,8 @@ static int dprc_scan_objects(struct fsl_mc_device *mc_bus_dev,
 		}
 
 		if (alloc_interrupts && !mc_bus->irq_resources) {
-			error = fsl_mc_populate_irq_pool(mc_bus,
-				FSL_MC_IRQ_POOL_MAX_TOTAL_IRQS);
+			error = fsl_mc_populate_irq_pool(mc_bus_dev,
+					 FSL_MC_IRQ_POOL_MAX_TOTAL_IRQS);
 			if (error < 0)
 				return error;
 		}
@@ -766,8 +766,6 @@ static void dprc_teardown_irq(struct fsl_mc_device *mc_dev)
 int dprc_cleanup(struct fsl_mc_device *mc_dev)
 {
 	int error;
-	struct fsl_mc_bus *mc_bus = to_fsl_mc_bus(mc_dev);
-
 
 	/* this function should be called only for DPRCs, it
 	 * is an error to call it for regular objects
@@ -776,7 +774,7 @@ int dprc_cleanup(struct fsl_mc_device *mc_dev)
 		return -EINVAL;
 
 	if (dev_get_msi_domain(&mc_dev->dev)) {
-		fsl_mc_cleanup_irq_pool(mc_bus);
+		fsl_mc_cleanup_irq_pool(mc_dev);
 		dev_set_msi_domain(&mc_dev->dev, NULL);
 	}
 
diff --git a/drivers/bus/fsl-mc/fsl-mc-allocator.c b/drivers/bus/fsl-mc/fsl-mc-allocator.c
index cc7bb900f524..e71a6f52ea0c 100644
--- a/drivers/bus/fsl-mc/fsl-mc-allocator.c
+++ b/drivers/bus/fsl-mc/fsl-mc-allocator.c
@@ -344,7 +344,7 @@ EXPORT_SYMBOL_GPL(fsl_mc_object_free);
  * Initialize the interrupt pool associated with an fsl-mc bus.
  * It allocates a block of IRQs from the GIC-ITS.
  */
-int fsl_mc_populate_irq_pool(struct fsl_mc_bus *mc_bus,
+int fsl_mc_populate_irq_pool(struct fsl_mc_device *mc_bus_dev,
 			     unsigned int irq_count)
 {
 	unsigned int i;
@@ -352,10 +352,14 @@ int fsl_mc_populate_irq_pool(struct fsl_mc_bus *mc_bus,
 	struct fsl_mc_device_irq *irq_resources;
 	struct fsl_mc_device_irq *mc_dev_irq;
 	int error;
-	struct fsl_mc_device *mc_bus_dev = &mc_bus->mc_dev;
+	struct fsl_mc_bus *mc_bus = to_fsl_mc_bus(mc_bus_dev);
 	struct fsl_mc_resource_pool *res_pool =
 			&mc_bus->resource_pools[FSL_MC_POOL_IRQ];
 
+	/* do nothing if the IRQ pool is already populated */
+	if (mc_bus->irq_resources)
+		return 0;
+
 	if (irq_count == 0 ||
 	    irq_count > FSL_MC_IRQ_POOL_MAX_TOTAL_IRQS)
 		return -EINVAL;
@@ -407,9 +411,9 @@ EXPORT_SYMBOL_GPL(fsl_mc_populate_irq_pool);
  * Teardown the interrupt pool associated with an fsl-mc bus.
  * It frees the IRQs that were allocated to the pool, back to the GIC-ITS.
  */
-void fsl_mc_cleanup_irq_pool(struct fsl_mc_bus *mc_bus)
+void fsl_mc_cleanup_irq_pool(struct fsl_mc_device *mc_bus_dev)
 {
-	struct fsl_mc_device *mc_bus_dev = &mc_bus->mc_dev;
+	struct fsl_mc_bus *mc_bus = to_fsl_mc_bus(mc_bus_dev);
 	struct fsl_mc_resource_pool *res_pool =
 			&mc_bus->resource_pools[FSL_MC_POOL_IRQ];
 
diff --git a/drivers/bus/fsl-mc/fsl-mc-private.h b/drivers/bus/fsl-mc/fsl-mc-private.h
index 5f7e762d517c..ffe709a3f0f8 100644
--- a/drivers/bus/fsl-mc/fsl-mc-private.h
+++ b/drivers/bus/fsl-mc/fsl-mc-private.h
@@ -519,11 +519,6 @@ struct dpcon_cmd_set_notification {
 	__le64 user_ctx;
 };
 
-/**
- * Maximum number of total IRQs that can be pre-allocated for an MC bus'
- * IRQ pool
- */
-#define FSL_MC_IRQ_POOL_MAX_TOTAL_IRQS	256
 
 /**
  * struct fsl_mc_resource_pool - Pool of MC resources of a given
@@ -598,11 +593,6 @@ void fsl_mc_msi_domain_free_irqs(struct device *dev);
 
 struct irq_domain *fsl_mc_find_msi_domain(struct device *dev);
 
-int fsl_mc_populate_irq_pool(struct fsl_mc_bus *mc_bus,
-			     unsigned int irq_count);
-
-void fsl_mc_cleanup_irq_pool(struct fsl_mc_bus *mc_bus);
-
 int __must_check fsl_create_mc_io(struct device *dev,
 				  phys_addr_t mc_portal_phys_addr,
 				  u32 mc_portal_size,
diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h
index e99d181ee4cd..f791fe38c251 100644
--- a/include/linux/fsl/mc.h
+++ b/include/linux/fsl/mc.h
@@ -542,6 +542,17 @@ int dprc_cleanup(struct fsl_mc_device *mc_dev);
 
 int dprc_setup(struct fsl_mc_device *mc_dev);
 
+/**
+ * Maximum number of total IRQs that can be pre-allocated for an MC bus'
+ * IRQ pool
+ */
+#define FSL_MC_IRQ_POOL_MAX_TOTAL_IRQS	256
+
+int fsl_mc_populate_irq_pool(struct fsl_mc_device *mc_bus_dev,
+			     unsigned int irq_count);
+
+void fsl_mc_cleanup_irq_pool(struct fsl_mc_device *mc_bus_dev);
+
 /*
  * Data Path Buffer Pool (DPBP) API
  * Contains initialization APIs and runtime control APIs for DPBP
-- 
cgit v1.2.3


From 273ee53ddf2e7d79565aff0ddc009ea2114d763b Mon Sep 17 00:00:00 2001
From: Bharat Bhushan <Bharat.Bhushan@nxp.com>
Date: Tue, 29 Sep 2020 11:54:40 +0300
Subject: bus/fsl-mc: Extend ICID size from 16bit to 32bit

In virtual machines the device-id range is defined
between 0x10000-0x20000. The reason for using such a
large range is to avoid overlapping with the PCI range.

Reviewed-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Acked-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Signed-off-by: Bharat Bhushan <Bharat.Bhushan@nxp.com>
Signed-off-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Signed-off-by: Diana Craciun <diana.craciun@oss.nxp.com>
Link: https://lore.kernel.org/r/20200929085441.17448-13-diana.craciun@oss.nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/fsl-mc/dprc.c           | 2 +-
 drivers/bus/fsl-mc/fsl-mc-bus.c     | 2 +-
 drivers/bus/fsl-mc/fsl-mc-private.h | 5 ++---
 include/linux/fsl/mc.h              | 2 +-
 4 files changed, 5 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/bus/fsl-mc/dprc.c b/drivers/bus/fsl-mc/dprc.c
index 2448a723eb28..650808799a29 100644
--- a/drivers/bus/fsl-mc/dprc.c
+++ b/drivers/bus/fsl-mc/dprc.c
@@ -360,7 +360,7 @@ int dprc_get_attributes(struct fsl_mc_io *mc_io,
 	/* retrieve response parameters */
 	rsp_params = (struct dprc_rsp_get_attributes *)cmd.params;
 	attr->container_id = le32_to_cpu(rsp_params->container_id);
-	attr->icid = le16_to_cpu(rsp_params->icid);
+	attr->icid = le32_to_cpu(rsp_params->icid);
 	attr->options = le32_to_cpu(rsp_params->options);
 	attr->portal_id = le32_to_cpu(rsp_params->portal_id);
 
diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c
index d53315f42dc2..76a6ee505d33 100644
--- a/drivers/bus/fsl-mc/fsl-mc-bus.c
+++ b/drivers/bus/fsl-mc/fsl-mc-bus.c
@@ -503,7 +503,7 @@ common_cleanup:
 }
 
 static int get_dprc_icid(struct fsl_mc_io *mc_io,
-			 int container_id, u16 *icid)
+			 int container_id, u32 *icid)
 {
 	struct dprc_attributes attr;
 	int error;
diff --git a/drivers/bus/fsl-mc/fsl-mc-private.h b/drivers/bus/fsl-mc/fsl-mc-private.h
index ffe709a3f0f8..3e9f9c778631 100644
--- a/drivers/bus/fsl-mc/fsl-mc-private.h
+++ b/drivers/bus/fsl-mc/fsl-mc-private.h
@@ -159,8 +159,7 @@ struct dprc_cmd_clear_irq_status {
 struct dprc_rsp_get_attributes {
 	/* response word 0 */
 	__le32 container_id;
-	__le16 icid;
-	__le16 pad;
+	__le32 icid;
 	/* response word 1 */
 	__le32 options;
 	__le32 portal_id;
@@ -337,7 +336,7 @@ int dprc_clear_irq_status(struct fsl_mc_io *mc_io,
  */
 struct dprc_attributes {
 	int container_id;
-	u16 icid;
+	u32 icid;
 	int portal_id;
 	u64 options;
 };
diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h
index f791fe38c251..db244874e834 100644
--- a/include/linux/fsl/mc.h
+++ b/include/linux/fsl/mc.h
@@ -195,7 +195,7 @@ struct fsl_mc_device {
 	struct device dev;
 	u64 dma_mask;
 	u16 flags;
-	u16 icid;
+	u32 icid;
 	u16 mc_handle;
 	struct fsl_mc_io *mc_io;
 	struct fsl_mc_obj_desc obj_desc;
-- 
cgit v1.2.3


From 894c26a1c274b8eafbb4b1dad67e70e51a106061 Mon Sep 17 00:00:00 2001
From: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Date: Wed, 30 Sep 2020 22:05:42 +0800
Subject: ACPI: Support Generic Initiator only domains

Generic Initiators are a new ACPI concept that allows for the
description of proximity domains that contain a device which
performs memory access (such as a network card) but neither
host CPU nor Memory.

This patch has the parsing code and provides the infrastructure
for an architecture to associate these new domains with their
nearest memory processing node.

Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/numa/srat.c | 69 +++++++++++++++++++++++++++++++++++++++++++++++-
 drivers/base/node.c      |  3 +++
 include/linux/nodemask.h |  1 +
 3 files changed, 72 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c
index 2c9a66c203ff..979e76b94e54 100644
--- a/drivers/acpi/numa/srat.c
+++ b/drivers/acpi/numa/srat.c
@@ -130,6 +130,36 @@ acpi_table_print_srat_entry(struct acpi_subtable_header *header)
 		}
 		break;
 
+	case ACPI_SRAT_TYPE_GENERIC_AFFINITY:
+	{
+		struct acpi_srat_generic_affinity *p =
+			(struct acpi_srat_generic_affinity *)header;
+
+		if (p->device_handle_type == 0) {
+			/*
+			 * For pci devices this may be the only place they
+			 * are assigned a proximity domain
+			 */
+			pr_debug("SRAT Generic Initiator(Seg:%u BDF:%u) in proximity domain %d %s\n",
+				 *(u16 *)(&p->device_handle[0]),
+				 *(u16 *)(&p->device_handle[2]),
+				 p->proximity_domain,
+				 (p->flags & ACPI_SRAT_GENERIC_AFFINITY_ENABLED) ?
+				"enabled" : "disabled");
+		} else {
+			/*
+			 * In this case we can rely on the device having a
+			 * proximity domain reference
+			 */
+			pr_debug("SRAT Generic Initiator(HID=%.8s UID=%.4s) in proximity domain %d %s\n",
+				(char *)(&p->device_handle[0]),
+				(char *)(&p->device_handle[8]),
+				p->proximity_domain,
+				(p->flags & ACPI_SRAT_GENERIC_AFFINITY_ENABLED) ?
+				"enabled" : "disabled");
+		}
+	}
+	break;
 	default:
 		pr_warn("Found unsupported SRAT entry (type = 0x%x)\n",
 			header->type);
@@ -332,6 +362,41 @@ acpi_parse_gicc_affinity(union acpi_subtable_headers *header,
 	return 0;
 }
 
+#if defined(CONFIG_X86) || defined(CONFIG_ARM64)
+static int __init
+acpi_parse_gi_affinity(union acpi_subtable_headers *header,
+		       const unsigned long end)
+{
+	struct acpi_srat_generic_affinity *gi_affinity;
+	int node;
+
+	gi_affinity = (struct acpi_srat_generic_affinity *)header;
+	if (!gi_affinity)
+		return -EINVAL;
+	acpi_table_print_srat_entry(&header->common);
+
+	if (!(gi_affinity->flags & ACPI_SRAT_GENERIC_AFFINITY_ENABLED))
+		return -EINVAL;
+
+	node = acpi_map_pxm_to_node(gi_affinity->proximity_domain);
+	if (node == NUMA_NO_NODE || node >= MAX_NUMNODES) {
+		pr_err("SRAT: Too many proximity domains.\n");
+		return -EINVAL;
+	}
+	node_set(node, numa_nodes_parsed);
+	node_set_state(node, N_GENERIC_INITIATOR);
+
+	return 0;
+}
+#else
+static int __init
+acpi_parse_gi_affinity(union acpi_subtable_headers *header,
+		       const unsigned long end)
+{
+	return 0;
+}
+#endif /* defined(CONFIG_X86) || defined (CONFIG_ARM64) */
+
 static int __initdata parsed_numa_memblks;
 
 static int __init
@@ -385,7 +450,7 @@ int __init acpi_numa_init(void)
 
 	/* SRAT: System Resource Affinity Table */
 	if (!acpi_table_parse(ACPI_SIG_SRAT, acpi_parse_srat)) {
-		struct acpi_subtable_proc srat_proc[3];
+		struct acpi_subtable_proc srat_proc[4];
 
 		memset(srat_proc, 0, sizeof(srat_proc));
 		srat_proc[0].id = ACPI_SRAT_TYPE_CPU_AFFINITY;
@@ -394,6 +459,8 @@ int __init acpi_numa_init(void)
 		srat_proc[1].handler = acpi_parse_x2apic_affinity;
 		srat_proc[2].id = ACPI_SRAT_TYPE_GICC_AFFINITY;
 		srat_proc[2].handler = acpi_parse_gicc_affinity;
+		srat_proc[3].id = ACPI_SRAT_TYPE_GENERIC_AFFINITY;
+		srat_proc[3].handler = acpi_parse_gi_affinity;
 
 		acpi_table_parse_entries_array(ACPI_SIG_SRAT,
 					sizeof(struct acpi_table_srat),
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 508b80f6329b..53383f1f683c 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -980,6 +980,8 @@ static struct node_attr node_state_attr[] = {
 #endif
 	[N_MEMORY] = _NODE_ATTR(has_memory, N_MEMORY),
 	[N_CPU] = _NODE_ATTR(has_cpu, N_CPU),
+	[N_GENERIC_INITIATOR] = _NODE_ATTR(has_generic_initiator,
+					   N_GENERIC_INITIATOR),
 };
 
 static struct attribute *node_state_attrs[] = {
@@ -991,6 +993,7 @@ static struct attribute *node_state_attrs[] = {
 #endif
 	&node_state_attr[N_MEMORY].attr.attr,
 	&node_state_attr[N_CPU].attr.attr,
+	&node_state_attr[N_GENERIC_INITIATOR].attr.attr,
 	NULL
 };
 
diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
index 27e7fa36f707..3334ce056335 100644
--- a/include/linux/nodemask.h
+++ b/include/linux/nodemask.h
@@ -399,6 +399,7 @@ enum node_states {
 #endif
 	N_MEMORY,		/* The node has memory(regular, high, movable) */
 	N_CPU,		/* The node has one or more cpus */
+	N_GENERIC_INITIATOR,	/* The node has one or more Generic Initiators */
 	NR_NODE_STATES
 };
 
-- 
cgit v1.2.3


From 01aabca2fd545554905321029e6c4c5b2fedb345 Mon Sep 17 00:00:00 2001
From: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Date: Wed, 30 Sep 2020 22:05:44 +0800
Subject: ACPI: Let ACPI know we support Generic Initiator Affinity Structures

Until we tell ACPI that we support generic initiators, it will have
to operate in fall back domain mode and all _PXM entries should
be on existing non GI domains.

This patch sets the relevant OSC bit to make that happen.

Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/bus.c   | 4 ++++
 include/linux/acpi.h | 1 +
 2 files changed, 5 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 54002670cb7a..113c661eb848 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -303,7 +303,11 @@ static void acpi_bus_osc_support(void)
 	capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_HOTPLUG_OST_SUPPORT;
 	capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_PCLPI_SUPPORT;
 
+#ifdef CONFIG_ARM64
+	capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_GENERIC_INITIATOR_SUPPORT;
+#endif
 #ifdef CONFIG_X86
+	capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_GENERIC_INITIATOR_SUPPORT;
 	if (boot_cpu_has(X86_FEATURE_HWP)) {
 		capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_CPC_SUPPORT;
 		capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_CPCV2_SUPPORT;
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index e9f6cd67943e..edbf3c4116b4 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -545,6 +545,7 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context);
 #define OSC_SB_PCLPI_SUPPORT			0x00000080
 #define OSC_SB_OSLPI_SUPPORT			0x00000100
 #define OSC_SB_CPC_DIVERSE_HIGH_SUPPORT		0x00001000
+#define OSC_SB_GENERIC_INITIATOR_SUPPORT	0x00002000
 
 extern bool osc_sb_apei_support_acked;
 extern bool osc_pc_lpi_support_confirmed;
-- 
cgit v1.2.3


From 1e0cb59d5f0a41d1a2b7a1e7d45024fbac62d6e7 Mon Sep 17 00:00:00 2001
From: John Garry <john.garry@huawei.com>
Date: Wed, 30 Sep 2020 13:43:50 +0100
Subject: ACPI: Make acpi_evaluate_dsm() prototype consistent
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When compiling a driver which includes both include/linux/acpi.h and
include/acpi/acpi_bus.h for when CONFIG_ACPI=n for i386, I get this:

/include/acpi/acpi_bus.h:53:20: error: conflicting types for ‘acpi_evaluate_dsm’
 union acpi_object *acpi_evaluate_dsm(acpi_handle handle, const guid_t *guid,
                    ^~~~~~~~~~~~~~~~~
In file included from drivers/scsi/hisi_sas/hisi_sas.h:10:0,
                 from drivers/scsi/hisi_sas/hisi_sas_main.c:7:
./include/linux/acpi.h:866:34: note: previous definition of ‘acpi_evaluate_dsm’ was here
 static inline union acpi_object *acpi_evaluate_dsm(acpi_handle handle,
                                  ^~~~~~~~~~~~~~~~~
Fix by making prototype in include/linux/acpi.h consistent.

Signed-off-by: John Garry <john.garry@huawei.com>
[ rjw: Subject edit ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/acpi.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 7ce2235f99f9..49dbb105084f 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -865,7 +865,7 @@ static inline bool acpi_driver_match_device(struct device *dev,
 
 static inline union acpi_object *acpi_evaluate_dsm(acpi_handle handle,
 						   const guid_t *guid,
-						   int rev, int func,
+						   u64 rev, u64 func,
 						   union acpi_object *argv4)
 {
 	return NULL;
-- 
cgit v1.2.3


From 49f618e1b669ef0e26a8d8d7f8fafc7b8fd31531 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Thu, 24 Sep 2020 13:04:47 +0200
Subject: PM: domains: Rename power state enums for genpd

To clarify the code a bit, let's rename GPD_STATE_ACTIVE into
GENPD_STATE_ON and GPD_STATE_POWER_OFF to GENPD_STATE_OFF.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
[ rjw: Subject edit ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c | 33 ++++++++++++++++-----------------
 include/linux/pm_domain.h   |  4 ++--
 2 files changed, 18 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 2cb5e04cf86c..23aa2feced77 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -123,7 +123,7 @@ static const struct genpd_lock_ops genpd_spin_ops = {
 #define genpd_lock_interruptible(p)	p->lock_ops->lock_interruptible(p)
 #define genpd_unlock(p)			p->lock_ops->unlock(p)
 
-#define genpd_status_on(genpd)		(genpd->status == GPD_STATE_ACTIVE)
+#define genpd_status_on(genpd)		(genpd->status == GENPD_STATE_ON)
 #define genpd_is_irq_safe(genpd)	(genpd->flags & GENPD_FLAG_IRQ_SAFE)
 #define genpd_is_always_on(genpd)	(genpd->flags & GENPD_FLAG_ALWAYS_ON)
 #define genpd_is_active_wakeup(genpd)	(genpd->flags & GENPD_FLAG_ACTIVE_WAKEUP)
@@ -222,7 +222,7 @@ static void genpd_update_accounting(struct generic_pm_domain *genpd)
 	 * out of off and so update the idle time and vice
 	 * versa.
 	 */
-	if (genpd->status == GPD_STATE_ACTIVE) {
+	if (genpd->status == GENPD_STATE_ON) {
 		int state_idx = genpd->state_idx;
 
 		genpd->states[state_idx].idle_time =
@@ -563,7 +563,7 @@ static int genpd_power_off(struct generic_pm_domain *genpd, bool one_dev_on,
 			return ret;
 	}
 
-	genpd->status = GPD_STATE_POWER_OFF;
+	genpd->status = GENPD_STATE_OFF;
 	genpd_update_accounting(genpd);
 
 	list_for_each_entry(link, &genpd->child_links, child_node) {
@@ -616,7 +616,7 @@ static int genpd_power_on(struct generic_pm_domain *genpd, unsigned int depth)
 	if (ret)
 		goto err;
 
-	genpd->status = GPD_STATE_ACTIVE;
+	genpd->status = GENPD_STATE_ON;
 	genpd_update_accounting(genpd);
 
 	return 0;
@@ -961,7 +961,7 @@ static void genpd_sync_power_off(struct generic_pm_domain *genpd, bool use_lock,
 	if (_genpd_power_off(genpd, false))
 		return;
 
-	genpd->status = GPD_STATE_POWER_OFF;
+	genpd->status = GENPD_STATE_OFF;
 
 	list_for_each_entry(link, &genpd->child_links, child_node) {
 		genpd_sd_counter_dec(link->parent);
@@ -1007,8 +1007,7 @@ static void genpd_sync_power_on(struct generic_pm_domain *genpd, bool use_lock,
 	}
 
 	_genpd_power_on(genpd, false);
-
-	genpd->status = GPD_STATE_ACTIVE;
+	genpd->status = GENPD_STATE_ON;
 }
 
 /**
@@ -1287,7 +1286,7 @@ static int genpd_restore_noirq(struct device *dev)
 		 * so make it appear as powered off to genpd_sync_power_on(),
 		 * so that it tries to power it on in case it was really off.
 		 */
-		genpd->status = GPD_STATE_POWER_OFF;
+		genpd->status = GENPD_STATE_OFF;
 
 	genpd_sync_power_on(genpd, true, 0);
 	genpd_unlock(genpd);
@@ -1777,7 +1776,7 @@ int pm_genpd_init(struct generic_pm_domain *genpd,
 	genpd->gov = gov;
 	INIT_WORK(&genpd->power_off_work, genpd_power_off_work_fn);
 	atomic_set(&genpd->sd_count, 0);
-	genpd->status = is_off ? GPD_STATE_POWER_OFF : GPD_STATE_ACTIVE;
+	genpd->status = is_off ? GENPD_STATE_OFF : GENPD_STATE_ON;
 	genpd->device_count = 0;
 	genpd->max_off_time_ns = -1;
 	genpd->max_off_time_changed = true;
@@ -2802,8 +2801,8 @@ static int genpd_summary_one(struct seq_file *s,
 			struct generic_pm_domain *genpd)
 {
 	static const char * const status_lookup[] = {
-		[GPD_STATE_ACTIVE] = "on",
-		[GPD_STATE_POWER_OFF] = "off"
+		[GENPD_STATE_ON] = "on",
+		[GENPD_STATE_OFF] = "off"
 	};
 	struct pm_domain_data *pm_data;
 	const char *kobj_path;
@@ -2881,8 +2880,8 @@ static int summary_show(struct seq_file *s, void *data)
 static int status_show(struct seq_file *s, void *data)
 {
 	static const char * const status_lookup[] = {
-		[GPD_STATE_ACTIVE] = "on",
-		[GPD_STATE_POWER_OFF] = "off"
+		[GENPD_STATE_ON] = "on",
+		[GENPD_STATE_OFF] = "off"
 	};
 
 	struct generic_pm_domain *genpd = s->private;
@@ -2895,7 +2894,7 @@ static int status_show(struct seq_file *s, void *data)
 	if (WARN_ON_ONCE(genpd->status >= ARRAY_SIZE(status_lookup)))
 		goto exit;
 
-	if (genpd->status == GPD_STATE_POWER_OFF)
+	if (genpd->status == GENPD_STATE_OFF)
 		seq_printf(s, "%s-%u\n", status_lookup[genpd->status],
 			genpd->state_idx);
 	else
@@ -2938,7 +2937,7 @@ static int idle_states_show(struct seq_file *s, void *data)
 		ktime_t delta = 0;
 		s64 msecs;
 
-		if ((genpd->status == GPD_STATE_POWER_OFF) &&
+		if ((genpd->status == GENPD_STATE_OFF) &&
 				(genpd->state_idx == i))
 			delta = ktime_sub(ktime_get(), genpd->accounting_time);
 
@@ -2961,7 +2960,7 @@ static int active_time_show(struct seq_file *s, void *data)
 	if (ret)
 		return -ERESTARTSYS;
 
-	if (genpd->status == GPD_STATE_ACTIVE)
+	if (genpd->status == GENPD_STATE_ON)
 		delta = ktime_sub(ktime_get(), genpd->accounting_time);
 
 	seq_printf(s, "%lld ms\n", ktime_to_ms(
@@ -2984,7 +2983,7 @@ static int total_idle_time_show(struct seq_file *s, void *data)
 
 	for (i = 0; i < genpd->state_count; i++) {
 
-		if ((genpd->status == GPD_STATE_POWER_OFF) &&
+		if ((genpd->status == GENPD_STATE_OFF) &&
 				(genpd->state_idx == i))
 			delta = ktime_sub(ktime_get(), genpd->accounting_time);
 
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index ee11502a575b..66f3c5d64d81 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -64,8 +64,8 @@
 #define GENPD_FLAG_RPM_ALWAYS_ON (1U << 5)
 
 enum gpd_status {
-	GPD_STATE_ACTIVE = 0,	/* PM domain is active */
-	GPD_STATE_POWER_OFF,	/* PM domain is off */
+	GENPD_STATE_ON = 0,	/* PM domain is on */
+	GENPD_STATE_OFF,	/* PM domain is off */
 };
 
 struct dev_power_governor {
-- 
cgit v1.2.3


From 69e0ad37c9f32d5aa1beb02aab4ec0cd055be013 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <natechancellor@gmail.com>
Date: Mon, 28 Sep 2020 16:09:39 -0700
Subject: static_call: Fix return type of static_call_init

Functions that are passed to early_initcall should be of type
initcall_t, which expects a return type of int. This is not currently an
error but a patch in the Clang LTO series could change that in the
future.

Fixes: 9183c3f9ed71 ("static_call: Add inline static call infrastructure")
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Link: https://lore.kernel.org/lkml/20200903203053.3411268-17-samitolvanen@google.com/
---
 include/linux/static_call.h | 6 +++---
 kernel/static_call.c        | 5 +++--
 2 files changed, 6 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/static_call.h b/include/linux/static_call.h
index bfa2ba39be57..695da4c9b338 100644
--- a/include/linux/static_call.h
+++ b/include/linux/static_call.h
@@ -136,7 +136,7 @@ extern void arch_static_call_transform(void *site, void *tramp, void *func, bool
 
 #ifdef CONFIG_HAVE_STATIC_CALL_INLINE
 
-extern void __init static_call_init(void);
+extern int __init static_call_init(void);
 
 struct static_call_mod {
 	struct static_call_mod *next;
@@ -187,7 +187,7 @@ extern int static_call_text_reserved(void *start, void *end);
 
 #elif defined(CONFIG_HAVE_STATIC_CALL)
 
-static inline void static_call_init(void) { }
+static inline int static_call_init(void) { return 0; }
 
 struct static_call_key {
 	void *func;
@@ -234,7 +234,7 @@ static inline int static_call_text_reserved(void *start, void *end)
 
 #else /* Generic implementation */
 
-static inline void static_call_init(void) { }
+static inline int static_call_init(void) { return 0; }
 
 struct static_call_key {
 	void *func;
diff --git a/kernel/static_call.c b/kernel/static_call.c
index f8362b3f8fd5..84565c2a41b8 100644
--- a/kernel/static_call.c
+++ b/kernel/static_call.c
@@ -410,12 +410,12 @@ int static_call_text_reserved(void *start, void *end)
 	return __static_call_mod_text_reserved(start, end);
 }
 
-void __init static_call_init(void)
+int __init static_call_init(void)
 {
 	int ret;
 
 	if (static_call_initialized)
-		return;
+		return 0;
 
 	cpus_read_lock();
 	static_call_lock();
@@ -434,6 +434,7 @@ void __init static_call_init(void)
 #ifdef CONFIG_MODULES
 	register_module_notifier(&static_call_module_nb);
 #endif
+	return 0;
 }
 early_initcall(static_call_init);
 
-- 
cgit v1.2.3


From 4976b718c3551faba2c0616ef55ebeb74db1c5ca Mon Sep 17 00:00:00 2001
From: Hao Luo <haoluo@google.com>
Date: Tue, 29 Sep 2020 16:50:44 -0700
Subject: bpf: Introduce pseudo_btf_id

Pseudo_btf_id is a type of ld_imm insn that associates a btf_id to a
ksym so that further dereferences on the ksym can use the BTF info
to validate accesses. Internally, when seeing a pseudo_btf_id ld insn,
the verifier reads the btf_id stored in the insn[0]'s imm field and
marks the dst_reg as PTR_TO_BTF_ID. The btf_id points to a VAR_KIND,
which is encoded in btf_vminux by pahole. If the VAR is not of a struct
type, the dst reg will be marked as PTR_TO_MEM instead of PTR_TO_BTF_ID
and the mem_size is resolved to the size of the VAR's type.

>From the VAR btf_id, the verifier can also read the address of the
ksym's corresponding kernel var from kallsyms and use that to fill
dst_reg.

Therefore, the proper functionality of pseudo_btf_id depends on (1)
kallsyms and (2) the encoding of kernel global VARs in pahole, which
should be available since pahole v1.18.

Signed-off-by: Hao Luo <haoluo@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200929235049.2533242-2-haoluo@google.com
---
 include/linux/bpf_verifier.h   |   7 +++
 include/linux/btf.h            |  15 +++++
 include/uapi/linux/bpf.h       |  36 +++++++++---
 kernel/bpf/btf.c               |  15 -----
 kernel/bpf/verifier.c          | 125 ++++++++++++++++++++++++++++++++++++-----
 tools/include/uapi/linux/bpf.h |  36 +++++++++---
 6 files changed, 188 insertions(+), 46 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 363b4f1c562a..e83ef6f6bf43 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -308,6 +308,13 @@ struct bpf_insn_aux_data {
 			u32 map_index;		/* index into used_maps[] */
 			u32 map_off;		/* offset from value base address */
 		};
+		struct {
+			enum bpf_reg_type reg_type;	/* type of pseudo_btf_id */
+			union {
+				u32 btf_id;	/* btf_id for struct typed var */
+				u32 mem_size;	/* mem_size for non-struct typed var */
+			};
+		} btf_var;
 	};
 	u64 map_key_state; /* constant (32 bit) key tracking for maps */
 	int ctx_field_size; /* the ctx field size for load insn, maybe 0 */
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 024e16ff7dcc..af1244180588 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -145,6 +145,21 @@ static inline bool btf_type_is_func_proto(const struct btf_type *t)
 	return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC_PROTO;
 }
 
+static inline bool btf_type_is_var(const struct btf_type *t)
+{
+	return BTF_INFO_KIND(t->info) == BTF_KIND_VAR;
+}
+
+/* union is only a special case of struct:
+ * all its offsetof(member) == 0
+ */
+static inline bool btf_type_is_struct(const struct btf_type *t)
+{
+	u8 kind = BTF_INFO_KIND(t->info);
+
+	return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION;
+}
+
 static inline u16 btf_type_vlen(const struct btf_type *t)
 {
 	return BTF_INFO_VLEN(t->info);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 4f556cfcbfbe..2aa156af24d6 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -356,18 +356,36 @@ enum bpf_link_type {
 #define BPF_F_SLEEPABLE		(1U << 4)
 
 /* When BPF ldimm64's insn[0].src_reg != 0 then this can have
- * two extensions:
- *
- * insn[0].src_reg:  BPF_PSEUDO_MAP_FD   BPF_PSEUDO_MAP_VALUE
- * insn[0].imm:      map fd              map fd
- * insn[1].imm:      0                   offset into value
- * insn[0].off:      0                   0
- * insn[1].off:      0                   0
- * ldimm64 rewrite:  address of map      address of map[0]+offset
- * verifier type:    CONST_PTR_TO_MAP    PTR_TO_MAP_VALUE
+ * the following extensions:
+ *
+ * insn[0].src_reg:  BPF_PSEUDO_MAP_FD
+ * insn[0].imm:      map fd
+ * insn[1].imm:      0
+ * insn[0].off:      0
+ * insn[1].off:      0
+ * ldimm64 rewrite:  address of map
+ * verifier type:    CONST_PTR_TO_MAP
  */
 #define BPF_PSEUDO_MAP_FD	1
+/* insn[0].src_reg:  BPF_PSEUDO_MAP_VALUE
+ * insn[0].imm:      map fd
+ * insn[1].imm:      offset into value
+ * insn[0].off:      0
+ * insn[1].off:      0
+ * ldimm64 rewrite:  address of map[0]+offset
+ * verifier type:    PTR_TO_MAP_VALUE
+ */
 #define BPF_PSEUDO_MAP_VALUE	2
+/* insn[0].src_reg:  BPF_PSEUDO_BTF_ID
+ * insn[0].imm:      kernel btd id of VAR
+ * insn[1].imm:      0
+ * insn[0].off:      0
+ * insn[1].off:      0
+ * ldimm64 rewrite:  address of the kernel variable
+ * verifier type:    PTR_TO_BTF_ID or PTR_TO_MEM, depending on whether the var
+ *                   is struct/union.
+ */
+#define BPF_PSEUDO_BTF_ID	3
 
 /* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative
  * offset to another bpf function
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 4d0ee7839fdb..00569afe3d0d 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -440,16 +440,6 @@ static bool btf_type_nosize_or_null(const struct btf_type *t)
 	return !t || btf_type_nosize(t);
 }
 
-/* union is only a special case of struct:
- * all its offsetof(member) == 0
- */
-static bool btf_type_is_struct(const struct btf_type *t)
-{
-	u8 kind = BTF_INFO_KIND(t->info);
-
-	return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION;
-}
-
 static bool __btf_type_is_struct(const struct btf_type *t)
 {
 	return BTF_INFO_KIND(t->info) == BTF_KIND_STRUCT;
@@ -460,11 +450,6 @@ static bool btf_type_is_array(const struct btf_type *t)
 	return BTF_INFO_KIND(t->info) == BTF_KIND_ARRAY;
 }
 
-static bool btf_type_is_var(const struct btf_type *t)
-{
-	return BTF_INFO_KIND(t->info) == BTF_KIND_VAR;
-}
-
 static bool btf_type_is_datasec(const struct btf_type *t)
 {
 	return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 015a1c074b6b..fe4965079773 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -7488,6 +7488,7 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
 {
 	struct bpf_insn_aux_data *aux = cur_aux(env);
 	struct bpf_reg_state *regs = cur_regs(env);
+	struct bpf_reg_state *dst_reg;
 	struct bpf_map *map;
 	int err;
 
@@ -7504,25 +7505,44 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
 	if (err)
 		return err;
 
+	dst_reg = &regs[insn->dst_reg];
 	if (insn->src_reg == 0) {
 		u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm;
 
-		regs[insn->dst_reg].type = SCALAR_VALUE;
+		dst_reg->type = SCALAR_VALUE;
 		__mark_reg_known(&regs[insn->dst_reg], imm);
 		return 0;
 	}
 
+	if (insn->src_reg == BPF_PSEUDO_BTF_ID) {
+		mark_reg_known_zero(env, regs, insn->dst_reg);
+
+		dst_reg->type = aux->btf_var.reg_type;
+		switch (dst_reg->type) {
+		case PTR_TO_MEM:
+			dst_reg->mem_size = aux->btf_var.mem_size;
+			break;
+		case PTR_TO_BTF_ID:
+			dst_reg->btf_id = aux->btf_var.btf_id;
+			break;
+		default:
+			verbose(env, "bpf verifier is misconfigured\n");
+			return -EFAULT;
+		}
+		return 0;
+	}
+
 	map = env->used_maps[aux->map_index];
 	mark_reg_known_zero(env, regs, insn->dst_reg);
-	regs[insn->dst_reg].map_ptr = map;
+	dst_reg->map_ptr = map;
 
 	if (insn->src_reg == BPF_PSEUDO_MAP_VALUE) {
-		regs[insn->dst_reg].type = PTR_TO_MAP_VALUE;
-		regs[insn->dst_reg].off = aux->map_off;
+		dst_reg->type = PTR_TO_MAP_VALUE;
+		dst_reg->off = aux->map_off;
 		if (map_value_has_spin_lock(map))
-			regs[insn->dst_reg].id = ++env->id_gen;
+			dst_reg->id = ++env->id_gen;
 	} else if (insn->src_reg == BPF_PSEUDO_MAP_FD) {
-		regs[insn->dst_reg].type = CONST_PTR_TO_MAP;
+		dst_reg->type = CONST_PTR_TO_MAP;
 	} else {
 		verbose(env, "bpf verifier is misconfigured\n");
 		return -EINVAL;
@@ -9424,6 +9444,73 @@ process_bpf_exit:
 	return 0;
 }
 
+/* replace pseudo btf_id with kernel symbol address */
+static int check_pseudo_btf_id(struct bpf_verifier_env *env,
+			       struct bpf_insn *insn,
+			       struct bpf_insn_aux_data *aux)
+{
+	u32 type, id = insn->imm;
+	const struct btf_type *t;
+	const char *sym_name;
+	u64 addr;
+
+	if (!btf_vmlinux) {
+		verbose(env, "kernel is missing BTF, make sure CONFIG_DEBUG_INFO_BTF=y is specified in Kconfig.\n");
+		return -EINVAL;
+	}
+
+	if (insn[1].imm != 0) {
+		verbose(env, "reserved field (insn[1].imm) is used in pseudo_btf_id ldimm64 insn.\n");
+		return -EINVAL;
+	}
+
+	t = btf_type_by_id(btf_vmlinux, id);
+	if (!t) {
+		verbose(env, "ldimm64 insn specifies invalid btf_id %d.\n", id);
+		return -ENOENT;
+	}
+
+	if (!btf_type_is_var(t)) {
+		verbose(env, "pseudo btf_id %d in ldimm64 isn't KIND_VAR.\n",
+			id);
+		return -EINVAL;
+	}
+
+	sym_name = btf_name_by_offset(btf_vmlinux, t->name_off);
+	addr = kallsyms_lookup_name(sym_name);
+	if (!addr) {
+		verbose(env, "ldimm64 failed to find the address for kernel symbol '%s'.\n",
+			sym_name);
+		return -ENOENT;
+	}
+
+	insn[0].imm = (u32)addr;
+	insn[1].imm = addr >> 32;
+
+	type = t->type;
+	t = btf_type_skip_modifiers(btf_vmlinux, type, NULL);
+	if (!btf_type_is_struct(t)) {
+		const struct btf_type *ret;
+		const char *tname;
+		u32 tsize;
+
+		/* resolve the type size of ksym. */
+		ret = btf_resolve_size(btf_vmlinux, t, &tsize);
+		if (IS_ERR(ret)) {
+			tname = btf_name_by_offset(btf_vmlinux, t->name_off);
+			verbose(env, "ldimm64 unable to resolve the size of type '%s': %ld\n",
+				tname, PTR_ERR(ret));
+			return -EINVAL;
+		}
+		aux->btf_var.reg_type = PTR_TO_MEM;
+		aux->btf_var.mem_size = tsize;
+	} else {
+		aux->btf_var.reg_type = PTR_TO_BTF_ID;
+		aux->btf_var.btf_id = type;
+	}
+	return 0;
+}
+
 static int check_map_prealloc(struct bpf_map *map)
 {
 	return (map->map_type != BPF_MAP_TYPE_HASH &&
@@ -9534,10 +9621,14 @@ static bool bpf_map_is_cgroup_storage(struct bpf_map *map)
 		map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE);
 }
 
-/* look for pseudo eBPF instructions that access map FDs and
- * replace them with actual map pointers
+/* find and rewrite pseudo imm in ld_imm64 instructions:
+ *
+ * 1. if it accesses map FD, replace it with actual map pointer.
+ * 2. if it accesses btf_id of a VAR, replace it with pointer to the var.
+ *
+ * NOTE: btf_vmlinux is required for converting pseudo btf_id.
  */
-static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
+static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env)
 {
 	struct bpf_insn *insn = env->prog->insnsi;
 	int insn_cnt = env->prog->len;
@@ -9578,6 +9669,14 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
 				/* valid generic load 64-bit imm */
 				goto next_insn;
 
+			if (insn[0].src_reg == BPF_PSEUDO_BTF_ID) {
+				aux = &env->insn_aux_data[i];
+				err = check_pseudo_btf_id(env, insn, aux);
+				if (err)
+					return err;
+				goto next_insn;
+			}
+
 			/* In final convert_pseudo_ld_imm64() step, this is
 			 * converted into regular 64-bit imm load insn.
 			 */
@@ -11633,10 +11732,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 	if (is_priv)
 		env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ;
 
-	ret = replace_map_fd_with_map_ptr(env);
-	if (ret < 0)
-		goto skip_full_check;
-
 	if (bpf_prog_is_dev_bound(env->prog->aux)) {
 		ret = bpf_prog_offload_verifier_prep(env->prog);
 		if (ret)
@@ -11662,6 +11757,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 	if (ret)
 		goto skip_full_check;
 
+	ret = resolve_pseudo_ldimm64(env);
+	if (ret < 0)
+		goto skip_full_check;
+
 	ret = check_cfg(env);
 	if (ret < 0)
 		goto skip_full_check;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 4f556cfcbfbe..2aa156af24d6 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -356,18 +356,36 @@ enum bpf_link_type {
 #define BPF_F_SLEEPABLE		(1U << 4)
 
 /* When BPF ldimm64's insn[0].src_reg != 0 then this can have
- * two extensions:
- *
- * insn[0].src_reg:  BPF_PSEUDO_MAP_FD   BPF_PSEUDO_MAP_VALUE
- * insn[0].imm:      map fd              map fd
- * insn[1].imm:      0                   offset into value
- * insn[0].off:      0                   0
- * insn[1].off:      0                   0
- * ldimm64 rewrite:  address of map      address of map[0]+offset
- * verifier type:    CONST_PTR_TO_MAP    PTR_TO_MAP_VALUE
+ * the following extensions:
+ *
+ * insn[0].src_reg:  BPF_PSEUDO_MAP_FD
+ * insn[0].imm:      map fd
+ * insn[1].imm:      0
+ * insn[0].off:      0
+ * insn[1].off:      0
+ * ldimm64 rewrite:  address of map
+ * verifier type:    CONST_PTR_TO_MAP
  */
 #define BPF_PSEUDO_MAP_FD	1
+/* insn[0].src_reg:  BPF_PSEUDO_MAP_VALUE
+ * insn[0].imm:      map fd
+ * insn[1].imm:      offset into value
+ * insn[0].off:      0
+ * insn[1].off:      0
+ * ldimm64 rewrite:  address of map[0]+offset
+ * verifier type:    PTR_TO_MAP_VALUE
+ */
 #define BPF_PSEUDO_MAP_VALUE	2
+/* insn[0].src_reg:  BPF_PSEUDO_BTF_ID
+ * insn[0].imm:      kernel btd id of VAR
+ * insn[1].imm:      0
+ * insn[0].off:      0
+ * insn[1].off:      0
+ * ldimm64 rewrite:  address of the kernel variable
+ * verifier type:    PTR_TO_BTF_ID or PTR_TO_MEM, depending on whether the var
+ *                   is struct/union.
+ */
+#define BPF_PSEUDO_BTF_ID	3
 
 /* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative
  * offset to another bpf function
-- 
cgit v1.2.3


From eaa6bcb71ef6ed3dc18fc525ee7e293b06b4882b Mon Sep 17 00:00:00 2001
From: Hao Luo <haoluo@google.com>
Date: Tue, 29 Sep 2020 16:50:47 -0700
Subject: bpf: Introduce bpf_per_cpu_ptr()

Add bpf_per_cpu_ptr() to help bpf programs access percpu vars.
bpf_per_cpu_ptr() has the same semantic as per_cpu_ptr() in the kernel
except that it may return NULL. This happens when the cpu parameter is
out of range. So the caller must check the returned value.

Signed-off-by: Hao Luo <haoluo@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200929235049.2533242-5-haoluo@google.com
---
 include/linux/bpf.h            |  4 +++
 include/linux/btf.h            | 11 ++++++++
 include/uapi/linux/bpf.h       | 18 ++++++++++++
 kernel/bpf/btf.c               | 10 -------
 kernel/bpf/helpers.c           | 18 ++++++++++++
 kernel/bpf/verifier.c          | 64 ++++++++++++++++++++++++++++++++++++++++--
 kernel/trace/bpf_trace.c       |  2 ++
 tools/include/uapi/linux/bpf.h | 18 ++++++++++++
 8 files changed, 132 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 50e5c4b52bd1..9dde15b2479d 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -293,6 +293,7 @@ enum bpf_arg_type {
 	ARG_PTR_TO_ALLOC_MEM_OR_NULL,	/* pointer to dynamically allocated memory or NULL */
 	ARG_CONST_ALLOC_SIZE_OR_ZERO,	/* number of allocated bytes requested */
 	ARG_PTR_TO_BTF_ID_SOCK_COMMON,	/* pointer to in-kernel sock_common or bpf-mirrored bpf_sock */
+	ARG_PTR_TO_PERCPU_BTF_ID,	/* pointer to in-kernel percpu type */
 	__BPF_ARG_TYPE_MAX,
 };
 
@@ -307,6 +308,7 @@ enum bpf_return_type {
 	RET_PTR_TO_SOCK_COMMON_OR_NULL,	/* returns a pointer to a sock_common or NULL */
 	RET_PTR_TO_ALLOC_MEM_OR_NULL,	/* returns a pointer to dynamically allocated memory or NULL */
 	RET_PTR_TO_BTF_ID_OR_NULL,	/* returns a pointer to a btf_id or NULL */
+	RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL, /* returns a pointer to a valid memory or a btf_id or NULL */
 };
 
 /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs
@@ -405,6 +407,7 @@ enum bpf_reg_type {
 	PTR_TO_RDONLY_BUF_OR_NULL, /* reg points to a readonly buffer or NULL */
 	PTR_TO_RDWR_BUF,	 /* reg points to a read/write buffer */
 	PTR_TO_RDWR_BUF_OR_NULL, /* reg points to a read/write buffer or NULL */
+	PTR_TO_PERCPU_BTF_ID,	 /* reg points to a percpu kernel variable */
 };
 
 /* The information passed from prog-specific *_is_valid_access
@@ -1828,6 +1831,7 @@ extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto;
 extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto;
 extern const struct bpf_func_proto bpf_copy_from_user_proto;
 extern const struct bpf_func_proto bpf_snprintf_btf_proto;
+extern const struct bpf_func_proto bpf_per_cpu_ptr_proto;
 
 const struct bpf_func_proto *bpf_tracing_func_proto(
 	enum bpf_func_id func_id, const struct bpf_prog *prog);
diff --git a/include/linux/btf.h b/include/linux/btf.h
index af1244180588..2bf641829664 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -110,6 +110,11 @@ btf_resolve_size(const struct btf *btf, const struct btf_type *type,
 	     i < btf_type_vlen(struct_type);			\
 	     i++, member++)
 
+#define for_each_vsi(i, datasec_type, member)			\
+	for (i = 0, member = btf_type_var_secinfo(datasec_type);	\
+	     i < btf_type_vlen(datasec_type);			\
+	     i++, member++)
+
 static inline bool btf_type_is_ptr(const struct btf_type *t)
 {
 	return BTF_INFO_KIND(t->info) == BTF_KIND_PTR;
@@ -194,6 +199,12 @@ static inline const struct btf_member *btf_type_member(const struct btf_type *t)
 	return (const struct btf_member *)(t + 1);
 }
 
+static inline const struct btf_var_secinfo *btf_type_var_secinfo(
+		const struct btf_type *t)
+{
+	return (const struct btf_var_secinfo *)(t + 1);
+}
+
 #ifdef CONFIG_BPF_SYSCALL
 const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id);
 const char *btf_name_by_offset(const struct btf *btf, u32 offset);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 2aa156af24d6..f3c1b637ab39 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3686,6 +3686,23 @@ union bpf_attr {
  * 	Return
  * 		The helper returns **TC_ACT_REDIRECT** on success or
  * 		**TC_ACT_SHOT** on error.
+ *
+ * void *bpf_per_cpu_ptr(const void *percpu_ptr, u32 cpu)
+ *     Description
+ *             Take a pointer to a percpu ksym, *percpu_ptr*, and return a
+ *             pointer to the percpu kernel variable on *cpu*. A ksym is an
+ *             extern variable decorated with '__ksym'. For ksym, there is a
+ *             global var (either static or global) defined of the same name
+ *             in the kernel. The ksym is percpu if the global var is percpu.
+ *             The returned pointer points to the global percpu var on *cpu*.
+ *
+ *             bpf_per_cpu_ptr() has the same semantic as per_cpu_ptr() in the
+ *             kernel, except that bpf_per_cpu_ptr() may return NULL. This
+ *             happens if *cpu* is larger than nr_cpu_ids. The caller of
+ *             bpf_per_cpu_ptr() must check the returned value.
+ *     Return
+ *             A pointer pointing to the kernel percpu variable on *cpu*, or
+ *             NULL, if *cpu* is invalid.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3841,6 +3858,7 @@ union bpf_attr {
 	FN(seq_printf_btf),		\
 	FN(skb_cgroup_classid),		\
 	FN(redirect_neigh),		\
+	FN(bpf_per_cpu_ptr),            \
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 00569afe3d0d..ed7d02e8bc93 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -188,11 +188,6 @@
 	     i < btf_type_vlen(struct_type);				\
 	     i++, member++)
 
-#define for_each_vsi(i, struct_type, member)			\
-	for (i = 0, member = btf_type_var_secinfo(struct_type);	\
-	     i < btf_type_vlen(struct_type);			\
-	     i++, member++)
-
 #define for_each_vsi_from(i, from, struct_type, member)				\
 	for (i = from, member = btf_type_var_secinfo(struct_type) + from;	\
 	     i < btf_type_vlen(struct_type);					\
@@ -598,11 +593,6 @@ static const struct btf_var *btf_type_var(const struct btf_type *t)
 	return (const struct btf_var *)(t + 1);
 }
 
-static const struct btf_var_secinfo *btf_type_var_secinfo(const struct btf_type *t)
-{
-	return (const struct btf_var_secinfo *)(t + 1);
-}
-
 static const struct btf_kind_operations *btf_type_ops(const struct btf_type *t)
 {
 	return kind_ops[BTF_INFO_KIND(t->info)];
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index e825441781ab..14fe3f64fd82 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -623,6 +623,22 @@ const struct bpf_func_proto bpf_copy_from_user_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_2(bpf_per_cpu_ptr, const void *, ptr, u32, cpu)
+{
+	if (cpu >= nr_cpu_ids)
+		return (unsigned long)NULL;
+
+	return (unsigned long)per_cpu_ptr((const void __percpu *)ptr, cpu);
+}
+
+const struct bpf_func_proto bpf_per_cpu_ptr_proto = {
+	.func		= bpf_per_cpu_ptr,
+	.gpl_only	= false,
+	.ret_type	= RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL,
+	.arg1_type	= ARG_PTR_TO_PERCPU_BTF_ID,
+	.arg2_type	= ARG_ANYTHING,
+};
+
 const struct bpf_func_proto bpf_get_current_task_proto __weak;
 const struct bpf_func_proto bpf_probe_read_user_proto __weak;
 const struct bpf_func_proto bpf_probe_read_user_str_proto __weak;
@@ -689,6 +705,8 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_snprintf_btf_proto;
 	case BPF_FUNC_jiffies64:
 		return &bpf_jiffies64_proto;
+	case BPF_FUNC_bpf_per_cpu_ptr:
+		return &bpf_per_cpu_ptr_proto;
 	default:
 		break;
 	}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index fe4965079773..216b8ece23ce 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -238,6 +238,8 @@ struct bpf_call_arg_meta {
 	u64 msize_max_value;
 	int ref_obj_id;
 	int func_id;
+	u32 btf_id;
+	u32 ret_btf_id;
 };
 
 struct btf *btf_vmlinux;
@@ -517,6 +519,7 @@ static const char * const reg_type_str[] = {
 	[PTR_TO_XDP_SOCK]	= "xdp_sock",
 	[PTR_TO_BTF_ID]		= "ptr_",
 	[PTR_TO_BTF_ID_OR_NULL]	= "ptr_or_null_",
+	[PTR_TO_PERCPU_BTF_ID]	= "percpu_ptr_",
 	[PTR_TO_MEM]		= "mem",
 	[PTR_TO_MEM_OR_NULL]	= "mem_or_null",
 	[PTR_TO_RDONLY_BUF]	= "rdonly_buf",
@@ -583,7 +586,9 @@ static void print_verifier_state(struct bpf_verifier_env *env,
 			/* reg->off should be 0 for SCALAR_VALUE */
 			verbose(env, "%lld", reg->var_off.value + reg->off);
 		} else {
-			if (t == PTR_TO_BTF_ID || t == PTR_TO_BTF_ID_OR_NULL)
+			if (t == PTR_TO_BTF_ID ||
+			    t == PTR_TO_BTF_ID_OR_NULL ||
+			    t == PTR_TO_PERCPU_BTF_ID)
 				verbose(env, "%s", kernel_type_name(reg->btf_id));
 			verbose(env, "(id=%d", reg->id);
 			if (reg_type_may_be_refcounted_or_null(t))
@@ -2204,6 +2209,7 @@ static bool is_spillable_regtype(enum bpf_reg_type type)
 	case PTR_TO_RDONLY_BUF_OR_NULL:
 	case PTR_TO_RDWR_BUF:
 	case PTR_TO_RDWR_BUF_OR_NULL:
+	case PTR_TO_PERCPU_BTF_ID:
 		return true;
 	default:
 		return false;
@@ -4017,6 +4023,7 @@ static const struct bpf_reg_types alloc_mem_types = { .types = { PTR_TO_MEM } };
 static const struct bpf_reg_types const_map_ptr_types = { .types = { CONST_PTR_TO_MAP } };
 static const struct bpf_reg_types btf_ptr_types = { .types = { PTR_TO_BTF_ID } };
 static const struct bpf_reg_types spin_lock_types = { .types = { PTR_TO_MAP_VALUE } };
+static const struct bpf_reg_types percpu_btf_ptr_types = { .types = { PTR_TO_PERCPU_BTF_ID } };
 
 static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = {
 	[ARG_PTR_TO_MAP_KEY]		= &map_key_value_types,
@@ -4042,6 +4049,7 @@ static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = {
 	[ARG_PTR_TO_ALLOC_MEM_OR_NULL]	= &alloc_mem_types,
 	[ARG_PTR_TO_INT]		= &int_ptr_types,
 	[ARG_PTR_TO_LONG]		= &int_ptr_types,
+	[ARG_PTR_TO_PERCPU_BTF_ID]	= &percpu_btf_ptr_types,
 };
 
 static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
@@ -4205,6 +4213,12 @@ skip_type_check:
 		err = check_helper_mem_access(env, regno,
 					      meta->map_ptr->value_size, false,
 					      meta);
+	} else if (arg_type == ARG_PTR_TO_PERCPU_BTF_ID) {
+		if (!reg->btf_id) {
+			verbose(env, "Helper has invalid btf_id in R%d\n", regno);
+			return -EACCES;
+		}
+		meta->ret_btf_id = reg->btf_id;
 	} else if (arg_type == ARG_PTR_TO_SPIN_LOCK) {
 		if (meta->func_id == BPF_FUNC_spin_lock) {
 			if (process_spin_lock(env, regno, true))
@@ -5114,6 +5128,30 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 		regs[BPF_REG_0].type = PTR_TO_MEM_OR_NULL;
 		regs[BPF_REG_0].id = ++env->id_gen;
 		regs[BPF_REG_0].mem_size = meta.mem_size;
+	} else if (fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL) {
+		const struct btf_type *t;
+
+		mark_reg_known_zero(env, regs, BPF_REG_0);
+		t = btf_type_skip_modifiers(btf_vmlinux, meta.ret_btf_id, NULL);
+		if (!btf_type_is_struct(t)) {
+			u32 tsize;
+			const struct btf_type *ret;
+			const char *tname;
+
+			/* resolve the type size of ksym. */
+			ret = btf_resolve_size(btf_vmlinux, t, &tsize);
+			if (IS_ERR(ret)) {
+				tname = btf_name_by_offset(btf_vmlinux, t->name_off);
+				verbose(env, "unable to resolve the size of type '%s': %ld\n",
+					tname, PTR_ERR(ret));
+				return -EINVAL;
+			}
+			regs[BPF_REG_0].type = PTR_TO_MEM_OR_NULL;
+			regs[BPF_REG_0].mem_size = tsize;
+		} else {
+			regs[BPF_REG_0].type = PTR_TO_BTF_ID_OR_NULL;
+			regs[BPF_REG_0].btf_id = meta.ret_btf_id;
+		}
 	} else if (fn->ret_type == RET_PTR_TO_BTF_ID_OR_NULL) {
 		int ret_btf_id;
 
@@ -7523,6 +7561,7 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
 			dst_reg->mem_size = aux->btf_var.mem_size;
 			break;
 		case PTR_TO_BTF_ID:
+		case PTR_TO_PERCPU_BTF_ID:
 			dst_reg->btf_id = aux->btf_var.btf_id;
 			break;
 		default:
@@ -9449,10 +9488,14 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env,
 			       struct bpf_insn *insn,
 			       struct bpf_insn_aux_data *aux)
 {
-	u32 type, id = insn->imm;
+	u32 datasec_id, type, id = insn->imm;
+	const struct btf_var_secinfo *vsi;
+	const struct btf_type *datasec;
 	const struct btf_type *t;
 	const char *sym_name;
+	bool percpu = false;
 	u64 addr;
+	int i;
 
 	if (!btf_vmlinux) {
 		verbose(env, "kernel is missing BTF, make sure CONFIG_DEBUG_INFO_BTF=y is specified in Kconfig.\n");
@@ -9484,12 +9527,27 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env,
 		return -ENOENT;
 	}
 
+	datasec_id = btf_find_by_name_kind(btf_vmlinux, ".data..percpu",
+					   BTF_KIND_DATASEC);
+	if (datasec_id > 0) {
+		datasec = btf_type_by_id(btf_vmlinux, datasec_id);
+		for_each_vsi(i, datasec, vsi) {
+			if (vsi->type == id) {
+				percpu = true;
+				break;
+			}
+		}
+	}
+
 	insn[0].imm = (u32)addr;
 	insn[1].imm = addr >> 32;
 
 	type = t->type;
 	t = btf_type_skip_modifiers(btf_vmlinux, type, NULL);
-	if (!btf_type_is_struct(t)) {
+	if (percpu) {
+		aux->btf_var.reg_type = PTR_TO_PERCPU_BTF_ID;
+		aux->btf_var.btf_id = type;
+	} else if (!btf_type_is_struct(t)) {
 		const struct btf_type *ret;
 		const char *tname;
 		u32 tsize;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index e118a83439c3..364a322e2898 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1327,6 +1327,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return prog->aux->sleepable ? &bpf_copy_from_user_proto : NULL;
 	case BPF_FUNC_snprintf_btf:
 		return &bpf_snprintf_btf_proto;
+	case BPF_FUNC_bpf_per_cpu_ptr:
+		return &bpf_per_cpu_ptr_proto;
 	default:
 		return NULL;
 	}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 2aa156af24d6..f3c1b637ab39 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3686,6 +3686,23 @@ union bpf_attr {
  * 	Return
  * 		The helper returns **TC_ACT_REDIRECT** on success or
  * 		**TC_ACT_SHOT** on error.
+ *
+ * void *bpf_per_cpu_ptr(const void *percpu_ptr, u32 cpu)
+ *     Description
+ *             Take a pointer to a percpu ksym, *percpu_ptr*, and return a
+ *             pointer to the percpu kernel variable on *cpu*. A ksym is an
+ *             extern variable decorated with '__ksym'. For ksym, there is a
+ *             global var (either static or global) defined of the same name
+ *             in the kernel. The ksym is percpu if the global var is percpu.
+ *             The returned pointer points to the global percpu var on *cpu*.
+ *
+ *             bpf_per_cpu_ptr() has the same semantic as per_cpu_ptr() in the
+ *             kernel, except that bpf_per_cpu_ptr() may return NULL. This
+ *             happens if *cpu* is larger than nr_cpu_ids. The caller of
+ *             bpf_per_cpu_ptr() must check the returned value.
+ *     Return
+ *             A pointer pointing to the kernel percpu variable on *cpu*, or
+ *             NULL, if *cpu* is invalid.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3841,6 +3858,7 @@ union bpf_attr {
 	FN(seq_printf_btf),		\
 	FN(skb_cgroup_classid),		\
 	FN(redirect_neigh),		\
+	FN(bpf_per_cpu_ptr),            \
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
-- 
cgit v1.2.3


From 63d9b80dcf2c67bc5ade61cbbaa09d7af21f43f1 Mon Sep 17 00:00:00 2001
From: Hao Luo <haoluo@google.com>
Date: Tue, 29 Sep 2020 16:50:48 -0700
Subject: bpf: Introducte bpf_this_cpu_ptr()

Add bpf_this_cpu_ptr() to help access percpu var on this cpu. This
helper always returns a valid pointer, therefore no need to check
returned value for NULL. Also note that all programs run with
preemption disabled, which means that the returned pointer is stable
during all the execution of the program.

Signed-off-by: Hao Luo <haoluo@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200929235049.2533242-6-haoluo@google.com
---
 include/linux/bpf.h            |  2 ++
 include/uapi/linux/bpf.h       | 13 +++++++++++++
 kernel/bpf/helpers.c           | 14 ++++++++++++++
 kernel/bpf/verifier.c          | 11 ++++++++---
 kernel/trace/bpf_trace.c       |  2 ++
 tools/include/uapi/linux/bpf.h | 13 +++++++++++++
 6 files changed, 52 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 9dde15b2479d..dc63eeed4fd9 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -309,6 +309,7 @@ enum bpf_return_type {
 	RET_PTR_TO_ALLOC_MEM_OR_NULL,	/* returns a pointer to dynamically allocated memory or NULL */
 	RET_PTR_TO_BTF_ID_OR_NULL,	/* returns a pointer to a btf_id or NULL */
 	RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL, /* returns a pointer to a valid memory or a btf_id or NULL */
+	RET_PTR_TO_MEM_OR_BTF_ID,	/* returns a pointer to a valid memory or a btf_id */
 };
 
 /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs
@@ -1832,6 +1833,7 @@ extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto;
 extern const struct bpf_func_proto bpf_copy_from_user_proto;
 extern const struct bpf_func_proto bpf_snprintf_btf_proto;
 extern const struct bpf_func_proto bpf_per_cpu_ptr_proto;
+extern const struct bpf_func_proto bpf_this_cpu_ptr_proto;
 
 const struct bpf_func_proto *bpf_tracing_func_proto(
 	enum bpf_func_id func_id, const struct bpf_prog *prog);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index f3c1b637ab39..c446394135be 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3703,6 +3703,18 @@ union bpf_attr {
  *     Return
  *             A pointer pointing to the kernel percpu variable on *cpu*, or
  *             NULL, if *cpu* is invalid.
+ *
+ * void *bpf_this_cpu_ptr(const void *percpu_ptr)
+ *	Description
+ *		Take a pointer to a percpu ksym, *percpu_ptr*, and return a
+ *		pointer to the percpu kernel variable on this cpu. See the
+ *		description of 'ksym' in **bpf_per_cpu_ptr**\ ().
+ *
+ *		bpf_this_cpu_ptr() has the same semantic as this_cpu_ptr() in
+ *		the kernel. Different from **bpf_per_cpu_ptr**\ (), it would
+ *		never return NULL.
+ *	Return
+ *		A pointer pointing to the kernel percpu variable on this cpu.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3859,6 +3871,7 @@ union bpf_attr {
 	FN(skb_cgroup_classid),		\
 	FN(redirect_neigh),		\
 	FN(bpf_per_cpu_ptr),            \
+	FN(bpf_this_cpu_ptr),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 14fe3f64fd82..25520f5eeaf6 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -639,6 +639,18 @@ const struct bpf_func_proto bpf_per_cpu_ptr_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_1(bpf_this_cpu_ptr, const void *, percpu_ptr)
+{
+	return (unsigned long)this_cpu_ptr((const void __percpu *)percpu_ptr);
+}
+
+const struct bpf_func_proto bpf_this_cpu_ptr_proto = {
+	.func		= bpf_this_cpu_ptr,
+	.gpl_only	= false,
+	.ret_type	= RET_PTR_TO_MEM_OR_BTF_ID,
+	.arg1_type	= ARG_PTR_TO_PERCPU_BTF_ID,
+};
+
 const struct bpf_func_proto bpf_get_current_task_proto __weak;
 const struct bpf_func_proto bpf_probe_read_user_proto __weak;
 const struct bpf_func_proto bpf_probe_read_user_str_proto __weak;
@@ -707,6 +719,8 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_jiffies64_proto;
 	case BPF_FUNC_bpf_per_cpu_ptr:
 		return &bpf_per_cpu_ptr_proto;
+	case BPF_FUNC_bpf_this_cpu_ptr:
+		return &bpf_this_cpu_ptr_proto;
 	default:
 		break;
 	}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 216b8ece23ce..d9dbf271ebab 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5128,7 +5128,8 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 		regs[BPF_REG_0].type = PTR_TO_MEM_OR_NULL;
 		regs[BPF_REG_0].id = ++env->id_gen;
 		regs[BPF_REG_0].mem_size = meta.mem_size;
-	} else if (fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL) {
+	} else if (fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL ||
+		   fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID) {
 		const struct btf_type *t;
 
 		mark_reg_known_zero(env, regs, BPF_REG_0);
@@ -5146,10 +5147,14 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 					tname, PTR_ERR(ret));
 				return -EINVAL;
 			}
-			regs[BPF_REG_0].type = PTR_TO_MEM_OR_NULL;
+			regs[BPF_REG_0].type =
+				fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID ?
+				PTR_TO_MEM : PTR_TO_MEM_OR_NULL;
 			regs[BPF_REG_0].mem_size = tsize;
 		} else {
-			regs[BPF_REG_0].type = PTR_TO_BTF_ID_OR_NULL;
+			regs[BPF_REG_0].type =
+				fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID ?
+				PTR_TO_BTF_ID : PTR_TO_BTF_ID_OR_NULL;
 			regs[BPF_REG_0].btf_id = meta.ret_btf_id;
 		}
 	} else if (fn->ret_type == RET_PTR_TO_BTF_ID_OR_NULL) {
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 364a322e2898..a136a6a63a71 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1329,6 +1329,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_snprintf_btf_proto;
 	case BPF_FUNC_bpf_per_cpu_ptr:
 		return &bpf_per_cpu_ptr_proto;
+	case BPF_FUNC_bpf_this_cpu_ptr:
+		return &bpf_this_cpu_ptr_proto;
 	default:
 		return NULL;
 	}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index f3c1b637ab39..c446394135be 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3703,6 +3703,18 @@ union bpf_attr {
  *     Return
  *             A pointer pointing to the kernel percpu variable on *cpu*, or
  *             NULL, if *cpu* is invalid.
+ *
+ * void *bpf_this_cpu_ptr(const void *percpu_ptr)
+ *	Description
+ *		Take a pointer to a percpu ksym, *percpu_ptr*, and return a
+ *		pointer to the percpu kernel variable on this cpu. See the
+ *		description of 'ksym' in **bpf_per_cpu_ptr**\ ().
+ *
+ *		bpf_this_cpu_ptr() has the same semantic as this_cpu_ptr() in
+ *		the kernel. Different from **bpf_per_cpu_ptr**\ (), it would
+ *		never return NULL.
+ *	Return
+ *		A pointer pointing to the kernel percpu variable on this cpu.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3859,6 +3871,7 @@ union bpf_attr {
 	FN(skb_cgroup_classid),		\
 	FN(redirect_neigh),		\
 	FN(bpf_per_cpu_ptr),            \
+	FN(bpf_this_cpu_ptr),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
-- 
cgit v1.2.3


From bfdc59701d6d100c99c3b987bcffd1c204e393c8 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 25 Sep 2020 06:51:40 +0200
Subject: iov_iter: refactor rw_copy_check_uvector and import_iovec

Split rw_copy_check_uvector into two new helpers with more sensible
calling conventions:

 - iovec_from_user copies a iovec from userspace either into the provided
   stack buffer if it fits, or allocates a new buffer for it.  Returns
   the actually used iovec.  It also verifies that iov_len does fit a
   signed type, and handles compat iovecs if the compat flag is set.
 - __import_iovec consolidates the native and compat versions of
   import_iovec. It calls iovec_from_user, then validates each iovec
   actually points to user addresses, and ensures the total length
   doesn't overflow.

This has two major implications:

 - the access_process_vm case loses the total lenght checking, which
   wasn't required anyway, given that each call receives two iovecs
   for the local and remote side of the operation, and it verifies
   the total length on the local side already.
 - instead of a single loop there now are two loops over the iovecs.
   Given that the iovecs are cache hot this doesn't make a major
   difference

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/compat.h |  16 +--
 include/linux/fs.h     |  13 ---
 include/linux/uio.h    |  12 +-
 lib/iov_iter.c         | 300 +++++++++++++++++++------------------------------
 mm/process_vm_access.c |  34 +++---
 5 files changed, 143 insertions(+), 232 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/compat.h b/include/linux/compat.h
index 790be5ffc12c..cebcaac68aec 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -91,6 +91,11 @@
 	static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
 #endif /* COMPAT_SYSCALL_DEFINEx */
 
+struct compat_iovec {
+	compat_uptr_t	iov_base;
+	compat_size_t	iov_len;
+};
+
 #ifdef CONFIG_COMPAT
 
 #ifndef compat_user_stack_pointer
@@ -248,11 +253,6 @@ typedef struct compat_siginfo {
 	} _sifields;
 } compat_siginfo_t;
 
-struct compat_iovec {
-	compat_uptr_t	iov_base;
-	compat_size_t	iov_len;
-};
-
 struct compat_rlimit {
 	compat_ulong_t	rlim_cur;
 	compat_ulong_t	rlim_max;
@@ -451,12 +451,6 @@ extern long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 
 struct epoll_event;	/* fortunately, this one is fixed-layout */
 
-extern ssize_t compat_rw_copy_check_uvector(int type,
-		const struct compat_iovec __user *uvector,
-		unsigned long nr_segs,
-		unsigned long fast_segs, struct iovec *fast_pointer,
-		struct iovec **ret_pointer);
-
 extern void __user *compat_alloc_user_space(unsigned long len);
 
 int compat_restore_altstack(const compat_stack_t __user *uss);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e019ea2f1347..b9fdac75ba06 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -178,14 +178,6 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 /* File supports async buffered reads */
 #define FMODE_BUF_RASYNC	((__force fmode_t)0x40000000)
 
-/*
- * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector
- * that indicates that they should check the contents of the iovec are
- * valid, but not check the memory that the iovec elements
- * points too.
- */
-#define CHECK_IOVEC_ONLY -1
-
 /*
  * Attribute flags.  These should be or-ed together to figure out what
  * has been changed!
@@ -1887,11 +1879,6 @@ static inline int call_mmap(struct file *file, struct vm_area_struct *vma)
 	return file->f_op->mmap(file, vma);
 }
 
-ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
-			      unsigned long nr_segs, unsigned long fast_segs,
-			      struct iovec *fast_pointer,
-			      struct iovec **ret_pointer);
-
 extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *);
 extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);
 extern ssize_t vfs_readv(struct file *, const struct iovec __user *,
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 3835a8a8e9ea..92c11fe41c62 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -266,9 +266,15 @@ bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct
 size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp,
 		struct iov_iter *i);
 
-ssize_t import_iovec(int type, const struct iovec __user * uvector,
-		 unsigned nr_segs, unsigned fast_segs,
-		 struct iovec **iov, struct iov_iter *i);
+struct iovec *iovec_from_user(const struct iovec __user *uvector,
+		unsigned long nr_segs, unsigned long fast_segs,
+		struct iovec *fast_iov, bool compat);
+ssize_t import_iovec(int type, const struct iovec __user *uvec,
+		 unsigned nr_segs, unsigned fast_segs, struct iovec **iovp,
+		 struct iov_iter *i);
+ssize_t __import_iovec(int type, const struct iovec __user *uvec,
+		 unsigned nr_segs, unsigned fast_segs, struct iovec **iovp,
+		 struct iov_iter *i, bool compat);
 
 #ifdef CONFIG_COMPAT
 struct compat_iovec;
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index ccea9db3f72b..e6cb51da3424 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -7,6 +7,7 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/splice.h>
+#include <linux/compat.h>
 #include <net/checksum.h>
 #include <linux/scatterlist.h>
 #include <linux/instrumented.h>
@@ -1650,107 +1651,133 @@ const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags)
 }
 EXPORT_SYMBOL(dup_iter);
 
-/**
- * rw_copy_check_uvector() - Copy an array of &struct iovec from userspace
- *     into the kernel and check that it is valid.
- *
- * @type: One of %CHECK_IOVEC_ONLY, %READ, or %WRITE.
- * @uvector: Pointer to the userspace array.
- * @nr_segs: Number of elements in userspace array.
- * @fast_segs: Number of elements in @fast_pointer.
- * @fast_pointer: Pointer to (usually small on-stack) kernel array.
- * @ret_pointer: (output parameter) Pointer to a variable that will point to
- *     either @fast_pointer, a newly allocated kernel array, or NULL,
- *     depending on which array was used.
- *
- * This function copies an array of &struct iovec of @nr_segs from
- * userspace into the kernel and checks that each element is valid (e.g.
- * it does not point to a kernel address or cause overflow by being too
- * large, etc.).
- *
- * As an optimization, the caller may provide a pointer to a small
- * on-stack array in @fast_pointer, typically %UIO_FASTIOV elements long
- * (the size of this array, or 0 if unused, should be given in @fast_segs).
- *
- * @ret_pointer will always point to the array that was used, so the
- * caller must take care not to call kfree() on it e.g. in case the
- * @fast_pointer array was used and it was allocated on the stack.
- *
- * Return: The total number of bytes covered by the iovec array on success
- *   or a negative error code on error.
- */
-ssize_t rw_copy_check_uvector(int type, const struct iovec __user *uvector,
-		unsigned long nr_segs, unsigned long fast_segs,
-		struct iovec *fast_pointer, struct iovec **ret_pointer)
+static int copy_compat_iovec_from_user(struct iovec *iov,
+		const struct iovec __user *uvec, unsigned long nr_segs)
+{
+	const struct compat_iovec __user *uiov =
+		(const struct compat_iovec __user *)uvec;
+	int ret = -EFAULT, i;
+
+	if (!user_access_begin(uvec, nr_segs * sizeof(*uvec)))
+		return -EFAULT;
+
+	for (i = 0; i < nr_segs; i++) {
+		compat_uptr_t buf;
+		compat_ssize_t len;
+
+		unsafe_get_user(len, &uiov[i].iov_len, uaccess_end);
+		unsafe_get_user(buf, &uiov[i].iov_base, uaccess_end);
+
+		/* check for compat_size_t not fitting in compat_ssize_t .. */
+		if (len < 0) {
+			ret = -EINVAL;
+			goto uaccess_end;
+		}
+		iov[i].iov_base = compat_ptr(buf);
+		iov[i].iov_len = len;
+	}
+
+	ret = 0;
+uaccess_end:
+	user_access_end();
+	return ret;
+}
+
+static int copy_iovec_from_user(struct iovec *iov,
+		const struct iovec __user *uvec, unsigned long nr_segs)
 {
 	unsigned long seg;
-	ssize_t ret;
-	struct iovec *iov = fast_pointer;
 
-	/*
-	 * SuS says "The readv() function *may* fail if the iovcnt argument
-	 * was less than or equal to 0, or greater than {IOV_MAX}.  Linux has
-	 * traditionally returned zero for zero segments, so...
-	 */
-	if (nr_segs == 0) {
-		ret = 0;
-		goto out;
+	if (copy_from_user(iov, uvec, nr_segs * sizeof(*uvec)))
+		return -EFAULT;
+	for (seg = 0; seg < nr_segs; seg++) {
+		if ((ssize_t)iov[seg].iov_len < 0)
+			return -EINVAL;
 	}
 
+	return 0;
+}
+
+struct iovec *iovec_from_user(const struct iovec __user *uvec,
+		unsigned long nr_segs, unsigned long fast_segs,
+		struct iovec *fast_iov, bool compat)
+{
+	struct iovec *iov = fast_iov;
+	int ret;
+
 	/*
-	 * First get the "struct iovec" from user memory and
-	 * verify all the pointers
+	 * SuS says "The readv() function *may* fail if the iovcnt argument was
+	 * less than or equal to 0, or greater than {IOV_MAX}.  Linux has
+	 * traditionally returned zero for zero segments, so...
 	 */
-	if (nr_segs > UIO_MAXIOV) {
-		ret = -EINVAL;
-		goto out;
-	}
+	if (nr_segs == 0)
+		return iov;
+	if (nr_segs > UIO_MAXIOV)
+		return ERR_PTR(-EINVAL);
 	if (nr_segs > fast_segs) {
 		iov = kmalloc_array(nr_segs, sizeof(struct iovec), GFP_KERNEL);
-		if (iov == NULL) {
-			ret = -ENOMEM;
-			goto out;
-		}
+		if (!iov)
+			return ERR_PTR(-ENOMEM);
 	}
-	if (copy_from_user(iov, uvector, nr_segs*sizeof(*uvector))) {
-		ret = -EFAULT;
-		goto out;
+
+	if (compat)
+		ret = copy_compat_iovec_from_user(iov, uvec, nr_segs);
+	else
+		ret = copy_iovec_from_user(iov, uvec, nr_segs);
+	if (ret) {
+		if (iov != fast_iov)
+			kfree(iov);
+		return ERR_PTR(ret);
+	}
+
+	return iov;
+}
+
+ssize_t __import_iovec(int type, const struct iovec __user *uvec,
+		 unsigned nr_segs, unsigned fast_segs, struct iovec **iovp,
+		 struct iov_iter *i, bool compat)
+{
+	ssize_t total_len = 0;
+	unsigned long seg;
+	struct iovec *iov;
+
+	iov = iovec_from_user(uvec, nr_segs, fast_segs, *iovp, compat);
+	if (IS_ERR(iov)) {
+		*iovp = NULL;
+		return PTR_ERR(iov);
 	}
 
 	/*
-	 * According to the Single Unix Specification we should return EINVAL
-	 * if an element length is < 0 when cast to ssize_t or if the
-	 * total length would overflow the ssize_t return value of the
-	 * system call.
+	 * According to the Single Unix Specification we should return EINVAL if
+	 * an element length is < 0 when cast to ssize_t or if the total length
+	 * would overflow the ssize_t return value of the system call.
 	 *
 	 * Linux caps all read/write calls to MAX_RW_COUNT, and avoids the
 	 * overflow case.
 	 */
-	ret = 0;
 	for (seg = 0; seg < nr_segs; seg++) {
-		void __user *buf = iov[seg].iov_base;
 		ssize_t len = (ssize_t)iov[seg].iov_len;
 
-		/* see if we we're about to use an invalid len or if
-		 * it's about to overflow ssize_t */
-		if (len < 0) {
-			ret = -EINVAL;
-			goto out;
+		if (!access_ok(iov[seg].iov_base, len)) {
+			if (iov != *iovp)
+				kfree(iov);
+			*iovp = NULL;
+			return -EFAULT;
 		}
-		if (type >= 0
-		    && unlikely(!access_ok(buf, len))) {
-			ret = -EFAULT;
-			goto out;
-		}
-		if (len > MAX_RW_COUNT - ret) {
-			len = MAX_RW_COUNT - ret;
+
+		if (len > MAX_RW_COUNT - total_len) {
+			len = MAX_RW_COUNT - total_len;
 			iov[seg].iov_len = len;
 		}
-		ret += len;
+		total_len += len;
 	}
-out:
-	*ret_pointer = iov;
-	return ret;
+
+	iov_iter_init(i, type, iov, nr_segs, total_len);
+	if (iov == *iovp)
+		*iovp = NULL;
+	else
+		*iovp = iov;
+	return total_len;
 }
 
 /**
@@ -1759,10 +1786,10 @@ out:
  *     &struct iov_iter iterator to access it.
  *
  * @type: One of %READ or %WRITE.
- * @uvector: Pointer to the userspace array.
+ * @uvec: Pointer to the userspace array.
  * @nr_segs: Number of elements in userspace array.
  * @fast_segs: Number of elements in @iov.
- * @iov: (input and output parameter) Pointer to pointer to (usually small
+ * @iovp: (input and output parameter) Pointer to pointer to (usually small
  *     on-stack) kernel array.
  * @i: Pointer to iterator that will be initialized on success.
  *
@@ -1775,120 +1802,21 @@ out:
  *
  * Return: Negative error code on error, bytes imported on success
  */
-ssize_t import_iovec(int type, const struct iovec __user * uvector,
+ssize_t import_iovec(int type, const struct iovec __user *uvec,
 		 unsigned nr_segs, unsigned fast_segs,
-		 struct iovec **iov, struct iov_iter *i)
+		 struct iovec **iovp, struct iov_iter *i)
 {
-	ssize_t n;
-	struct iovec *p;
-	n = rw_copy_check_uvector(type, uvector, nr_segs, fast_segs,
-				  *iov, &p);
-	if (n < 0) {
-		if (p != *iov)
-			kfree(p);
-		*iov = NULL;
-		return n;
-	}
-	iov_iter_init(i, type, p, nr_segs, n);
-	*iov = p == *iov ? NULL : p;
-	return n;
+	return __import_iovec(type, uvec, nr_segs, fast_segs, iovp, i, false);
 }
 EXPORT_SYMBOL(import_iovec);
 
 #ifdef CONFIG_COMPAT
-#include <linux/compat.h>
-
-ssize_t compat_rw_copy_check_uvector(int type,
-		const struct compat_iovec __user *uvector,
-		unsigned long nr_segs, unsigned long fast_segs,
-		struct iovec *fast_pointer, struct iovec **ret_pointer)
-{
-	compat_ssize_t tot_len;
-	struct iovec *iov = *ret_pointer = fast_pointer;
-	ssize_t ret = 0;
-	int seg;
-
-	/*
-	 * SuS says "The readv() function *may* fail if the iovcnt argument
-	 * was less than or equal to 0, or greater than {IOV_MAX}.  Linux has
-	 * traditionally returned zero for zero segments, so...
-	 */
-	if (nr_segs == 0)
-		goto out;
-
-	ret = -EINVAL;
-	if (nr_segs > UIO_MAXIOV)
-		goto out;
-	if (nr_segs > fast_segs) {
-		ret = -ENOMEM;
-		iov = kmalloc_array(nr_segs, sizeof(struct iovec), GFP_KERNEL);
-		if (iov == NULL)
-			goto out;
-	}
-	*ret_pointer = iov;
-
-	ret = -EFAULT;
-	if (!access_ok(uvector, nr_segs*sizeof(*uvector)))
-		goto out;
-
-	/*
-	 * Single unix specification:
-	 * We should -EINVAL if an element length is not >= 0 and fitting an
-	 * ssize_t.
-	 *
-	 * In Linux, the total length is limited to MAX_RW_COUNT, there is
-	 * no overflow possibility.
-	 */
-	tot_len = 0;
-	ret = -EINVAL;
-	for (seg = 0; seg < nr_segs; seg++) {
-		compat_uptr_t buf;
-		compat_ssize_t len;
-
-		if (__get_user(len, &uvector->iov_len) ||
-		   __get_user(buf, &uvector->iov_base)) {
-			ret = -EFAULT;
-			goto out;
-		}
-		if (len < 0)	/* size_t not fitting in compat_ssize_t .. */
-			goto out;
-		if (type >= 0 &&
-		    !access_ok(compat_ptr(buf), len)) {
-			ret = -EFAULT;
-			goto out;
-		}
-		if (len > MAX_RW_COUNT - tot_len)
-			len = MAX_RW_COUNT - tot_len;
-		tot_len += len;
-		iov->iov_base = compat_ptr(buf);
-		iov->iov_len = (compat_size_t) len;
-		uvector++;
-		iov++;
-	}
-	ret = tot_len;
-
-out:
-	return ret;
-}
-
-ssize_t compat_import_iovec(int type,
-		const struct compat_iovec __user * uvector,
-		unsigned nr_segs, unsigned fast_segs,
-		struct iovec **iov, struct iov_iter *i)
+ssize_t compat_import_iovec(int type, const struct compat_iovec __user *uvec,
+		unsigned nr_segs, unsigned fast_segs, struct iovec **iovp,
+		struct iov_iter *i)
 {
-	ssize_t n;
-	struct iovec *p;
-	n = compat_rw_copy_check_uvector(type, uvector, nr_segs, fast_segs,
-				  *iov, &p);
-	if (n < 0) {
-		if (p != *iov)
-			kfree(p);
-		*iov = NULL;
-		return n;
-	}
-	iov_iter_init(i, type, p, nr_segs, n);
-	*iov = p == *iov ? NULL : p;
-	return n;
+	return __import_iovec(type, (const struct iovec __user *)uvec, nr_segs,
+			     fast_segs, iovp, i, true);
 }
 EXPORT_SYMBOL(compat_import_iovec);
 #endif
diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c
index 29c052099aff..5e728c20c2be 100644
--- a/mm/process_vm_access.c
+++ b/mm/process_vm_access.c
@@ -276,20 +276,17 @@ static ssize_t process_vm_rw(pid_t pid,
 	if (rc < 0)
 		return rc;
 	if (!iov_iter_count(&iter))
-		goto free_iovecs;
-
-	rc = rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt, UIO_FASTIOV,
-				   iovstack_r, &iov_r);
-	if (rc <= 0)
-		goto free_iovecs;
-
+		goto free_iov_l;
+	iov_r = iovec_from_user(rvec, riovcnt, UIO_FASTIOV, iovstack_r, false);
+	if (IS_ERR(iov_r)) {
+		rc = PTR_ERR(iov_r);
+		goto free_iov_l;
+	}
 	rc = process_vm_rw_core(pid, &iter, iov_r, riovcnt, flags, vm_write);
-
-free_iovecs:
 	if (iov_r != iovstack_r)
 		kfree(iov_r);
+free_iov_l:
 	kfree(iov_l);
-
 	return rc;
 }
 
@@ -333,18 +330,17 @@ compat_process_vm_rw(compat_pid_t pid,
 	if (rc < 0)
 		return rc;
 	if (!iov_iter_count(&iter))
-		goto free_iovecs;
-	rc = compat_rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt,
-					  UIO_FASTIOV, iovstack_r,
-					  &iov_r);
-	if (rc <= 0)
-		goto free_iovecs;
-
+		goto free_iov_l;
+	iov_r = iovec_from_user((const struct iovec __user *)rvec, riovcnt,
+				UIO_FASTIOV, iovstack_r, true);
+	if (IS_ERR(iov_r)) {
+		rc = PTR_ERR(iov_r);
+		goto free_iov_l;
+	}
 	rc = process_vm_rw_core(pid, &iter, iov_r, riovcnt, flags, vm_write);
-
-free_iovecs:
 	if (iov_r != iovstack_r)
 		kfree(iov_r);
+free_iov_l:
 	kfree(iov_l);
 	return rc;
 }
-- 
cgit v1.2.3


From 89cd35c58bc2e36bfdc23dde67a429b08cf4ae03 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 25 Sep 2020 06:51:41 +0200
Subject: iov_iter: transparently handle compat iovecs in import_iovec

Use in compat_syscall to import either native or the compat iovecs, and
remove the now superflous compat_import_iovec.

This removes the need for special compat logic in most callers, and
the remaining ones can still be simplified by using __import_iovec
with a bool compat parameter.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 block/scsi_ioctl.c     | 12 ++----------
 drivers/scsi/sg.c      |  9 +--------
 fs/aio.c               |  8 ++------
 fs/io_uring.c          | 20 ++++++++------------
 fs/read_write.c        |  6 ++++--
 fs/splice.c            |  2 +-
 include/linux/uio.h    |  8 --------
 lib/iov_iter.c         | 14 ++------------
 mm/process_vm_access.c |  3 ++-
 net/compat.c           |  4 ++--
 security/keys/compat.c |  5 ++---
 11 files changed, 26 insertions(+), 65 deletions(-)

(limited to 'include/linux')

diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index ef722f04f88a..e08df86866ee 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -333,16 +333,8 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 		struct iov_iter i;
 		struct iovec *iov = NULL;
 
-#ifdef CONFIG_COMPAT
-		if (in_compat_syscall())
-			ret = compat_import_iovec(rq_data_dir(rq),
-				   hdr->dxferp, hdr->iovec_count,
-				   0, &iov, &i);
-		else
-#endif
-			ret = import_iovec(rq_data_dir(rq),
-				   hdr->dxferp, hdr->iovec_count,
-				   0, &iov, &i);
+		ret = import_iovec(rq_data_dir(rq), hdr->dxferp,
+				   hdr->iovec_count, 0, &iov, &i);
 		if (ret < 0)
 			goto out_free_cdb;
 
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 20472aaaf630..bfa8d77322d7 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -1820,14 +1820,7 @@ sg_start_req(Sg_request *srp, unsigned char *cmd)
 		struct iovec *iov = NULL;
 		struct iov_iter i;
 
-#ifdef CONFIG_COMPAT
-		if (in_compat_syscall())
-			res = compat_import_iovec(rw, hp->dxferp, iov_count,
-						  0, &iov, &i);
-		else
-#endif
-			res = import_iovec(rw, hp->dxferp, iov_count,
-					   0, &iov, &i);
+		res = import_iovec(rw, hp->dxferp, iov_count, 0, &iov, &i);
 		if (res < 0)
 			return res;
 
diff --git a/fs/aio.c b/fs/aio.c
index 5736bff48e9e..247f05533dd5 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1489,12 +1489,8 @@ static ssize_t aio_setup_rw(int rw, const struct iocb *iocb,
 		*iovec = NULL;
 		return ret;
 	}
-#ifdef CONFIG_COMPAT
-	if (compat)
-		return compat_import_iovec(rw, buf, len, UIO_FASTIOV, iovec,
-				iter);
-#endif
-	return import_iovec(rw, buf, len, UIO_FASTIOV, iovec, iter);
+
+	return __import_iovec(rw, buf, len, UIO_FASTIOV, iovec, iter, compat);
 }
 
 static inline void aio_rw_done(struct kiocb *req, ssize_t ret)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 91e2cc8414f9..b75c699b5cb7 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -2846,13 +2846,8 @@ static ssize_t __io_import_iovec(int rw, struct io_kiocb *req,
 		return ret;
 	}
 
-#ifdef CONFIG_COMPAT
-	if (req->ctx->compat)
-		return compat_import_iovec(rw, buf, sqe_len, UIO_FASTIOV,
-						iovec, iter);
-#endif
-
-	return import_iovec(rw, buf, sqe_len, UIO_FASTIOV, iovec, iter);
+	return __import_iovec(rw, buf, sqe_len, UIO_FASTIOV, iovec, iter,
+			      req->ctx->compat);
 }
 
 static ssize_t io_import_iovec(int rw, struct io_kiocb *req,
@@ -4166,8 +4161,9 @@ static int __io_recvmsg_copy_hdr(struct io_kiocb *req,
 				sr->len);
 		iomsg->iov = NULL;
 	} else {
-		ret = import_iovec(READ, uiov, iov_len, UIO_FASTIOV,
-					&iomsg->iov, &iomsg->msg.msg_iter);
+		ret = __import_iovec(READ, uiov, iov_len, UIO_FASTIOV,
+				     &iomsg->iov, &iomsg->msg.msg_iter,
+				     false);
 		if (ret > 0)
 			ret = 0;
 	}
@@ -4207,9 +4203,9 @@ static int __io_compat_recvmsg_copy_hdr(struct io_kiocb *req,
 		sr->len = iomsg->iov[0].iov_len;
 		iomsg->iov = NULL;
 	} else {
-		ret = compat_import_iovec(READ, uiov, len, UIO_FASTIOV,
-						&iomsg->iov,
-						&iomsg->msg.msg_iter);
+		ret = __import_iovec(READ, (struct iovec __user *)uiov, len,
+				   UIO_FASTIOV, &iomsg->iov,
+				   &iomsg->msg.msg_iter, true);
 		if (ret < 0)
 			return ret;
 	}
diff --git a/fs/read_write.c b/fs/read_write.c
index e5e891a88442..0a68037580b4 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1078,7 +1078,8 @@ static size_t compat_readv(struct file *file,
 	struct iov_iter iter;
 	ssize_t ret;
 
-	ret = compat_import_iovec(READ, vec, vlen, UIO_FASTIOV, &iov, &iter);
+	ret = import_iovec(READ, (const struct iovec __user *)vec, vlen,
+			   UIO_FASTIOV, &iov, &iter);
 	if (ret >= 0) {
 		ret = do_iter_read(file, &iter, pos, flags);
 		kfree(iov);
@@ -1186,7 +1187,8 @@ static size_t compat_writev(struct file *file,
 	struct iov_iter iter;
 	ssize_t ret;
 
-	ret = compat_import_iovec(WRITE, vec, vlen, UIO_FASTIOV, &iov, &iter);
+	ret = import_iovec(WRITE, (const struct iovec __user *)vec, vlen,
+			   UIO_FASTIOV, &iov, &iter);
 	if (ret >= 0) {
 		file_start_write(file);
 		ret = do_iter_write(file, &iter, pos, flags);
diff --git a/fs/splice.c b/fs/splice.c
index d7c8a7c4db07..132d42b9871f 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -1387,7 +1387,7 @@ COMPAT_SYSCALL_DEFINE4(vmsplice, int, fd, const struct compat_iovec __user *, io
 	if (error)
 		return error;
 
-	error = compat_import_iovec(type, iov32, nr_segs,
+	error = import_iovec(type, (struct iovec __user *)iov32, nr_segs,
 			     ARRAY_SIZE(iovstack), &iov, &iter);
 	if (error >= 0) {
 		error = do_vmsplice(f.file, &iter, flags);
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 92c11fe41c62..daedc61ad370 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -275,14 +275,6 @@ ssize_t import_iovec(int type, const struct iovec __user *uvec,
 ssize_t __import_iovec(int type, const struct iovec __user *uvec,
 		 unsigned nr_segs, unsigned fast_segs, struct iovec **iovp,
 		 struct iov_iter *i, bool compat);
-
-#ifdef CONFIG_COMPAT
-struct compat_iovec;
-ssize_t compat_import_iovec(int type, const struct compat_iovec __user * uvector,
-		 unsigned nr_segs, unsigned fast_segs,
-		 struct iovec **iov, struct iov_iter *i);
-#endif
-
 int import_single_range(int type, void __user *buf, size_t len,
 		 struct iovec *iov, struct iov_iter *i);
 
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index e6cb51da3424..2e452ce7388b 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -1806,21 +1806,11 @@ ssize_t import_iovec(int type, const struct iovec __user *uvec,
 		 unsigned nr_segs, unsigned fast_segs,
 		 struct iovec **iovp, struct iov_iter *i)
 {
-	return __import_iovec(type, uvec, nr_segs, fast_segs, iovp, i, false);
+	return __import_iovec(type, uvec, nr_segs, fast_segs, iovp, i,
+			      in_compat_syscall());
 }
 EXPORT_SYMBOL(import_iovec);
 
-#ifdef CONFIG_COMPAT
-ssize_t compat_import_iovec(int type, const struct compat_iovec __user *uvec,
-		unsigned nr_segs, unsigned fast_segs, struct iovec **iovp,
-		struct iov_iter *i)
-{
-	return __import_iovec(type, (const struct iovec __user *)uvec, nr_segs,
-			     fast_segs, iovp, i, true);
-}
-EXPORT_SYMBOL(compat_import_iovec);
-#endif
-
 int import_single_range(int rw, void __user *buf, size_t len,
 		 struct iovec *iov, struct iov_iter *i)
 {
diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c
index 5e728c20c2be..3f2156aab442 100644
--- a/mm/process_vm_access.c
+++ b/mm/process_vm_access.c
@@ -326,7 +326,8 @@ compat_process_vm_rw(compat_pid_t pid,
 	if (flags != 0)
 		return -EINVAL;
 
-	rc = compat_import_iovec(dir, lvec, liovcnt, UIO_FASTIOV, &iov_l, &iter);
+	rc = import_iovec(dir, (const struct iovec __user *)lvec, liovcnt,
+			  UIO_FASTIOV, &iov_l, &iter);
 	if (rc < 0)
 		return rc;
 	if (!iov_iter_count(&iter))
diff --git a/net/compat.c b/net/compat.c
index 95ce707a30a3..ddd15af3a283 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -98,8 +98,8 @@ int get_compat_msghdr(struct msghdr *kmsg,
 	if (err)
 		return err;
 
-	err = compat_import_iovec(save_addr ? READ : WRITE, compat_ptr(ptr),
-				   len, UIO_FASTIOV, iov, &kmsg->msg_iter);
+	err = import_iovec(save_addr ? READ : WRITE, compat_ptr(ptr), len,
+			   UIO_FASTIOV, iov, &kmsg->msg_iter);
 	return err < 0 ? err : 0;
 }
 
diff --git a/security/keys/compat.c b/security/keys/compat.c
index 6ee9d8f6a4a5..7ae531db031c 100644
--- a/security/keys/compat.c
+++ b/security/keys/compat.c
@@ -33,9 +33,8 @@ static long compat_keyctl_instantiate_key_iov(
 	if (!_payload_iov)
 		ioc = 0;
 
-	ret = compat_import_iovec(WRITE, _payload_iov, ioc,
-				  ARRAY_SIZE(iovstack), &iov,
-				  &from);
+	ret = import_iovec(WRITE, (const struct iovec __user *)_payload_iov,
+			   ioc, ARRAY_SIZE(iovstack), &iov, &from);
 	if (ret < 0)
 		return ret;
 
-- 
cgit v1.2.3


From 3523a9d45478984169d7f4416a00c83afc964e2a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 25 Sep 2020 06:51:42 +0200
Subject: fs: remove various compat readv/writev helpers

Now that import_iovec handles compat iovecs as well, all the duplicated
code in the compat readv/writev helpers is not needed.  Remove them
and switch the compat syscall handlers to use the native helpers.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/read_write.c        | 179 +++++++++----------------------------------------
 include/linux/compat.h |  20 +++---
 2 files changed, 40 insertions(+), 159 deletions(-)

(limited to 'include/linux')

diff --git a/fs/read_write.c b/fs/read_write.c
index 0a68037580b4..eab427b7cc0a 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1068,226 +1068,107 @@ SYSCALL_DEFINE6(pwritev2, unsigned long, fd, const struct iovec __user *, vec,
 	return do_pwritev(fd, vec, vlen, pos, flags);
 }
 
+/*
+ * Various compat syscalls.  Note that they all pretend to take a native
+ * iovec - import_iovec will properly treat those as compat_iovecs based on
+ * in_compat_syscall().
+ */
 #ifdef CONFIG_COMPAT
-static size_t compat_readv(struct file *file,
-			   const struct compat_iovec __user *vec,
-			   unsigned long vlen, loff_t *pos, rwf_t flags)
-{
-	struct iovec iovstack[UIO_FASTIOV];
-	struct iovec *iov = iovstack;
-	struct iov_iter iter;
-	ssize_t ret;
-
-	ret = import_iovec(READ, (const struct iovec __user *)vec, vlen,
-			   UIO_FASTIOV, &iov, &iter);
-	if (ret >= 0) {
-		ret = do_iter_read(file, &iter, pos, flags);
-		kfree(iov);
-	}
-	if (ret > 0)
-		add_rchar(current, ret);
-	inc_syscr(current);
-	return ret;
-}
-
-static size_t do_compat_readv(compat_ulong_t fd,
-				 const struct compat_iovec __user *vec,
-				 compat_ulong_t vlen, rwf_t flags)
-{
-	struct fd f = fdget_pos(fd);
-	ssize_t ret;
-	loff_t pos;
-
-	if (!f.file)
-		return -EBADF;
-	pos = f.file->f_pos;
-	ret = compat_readv(f.file, vec, vlen, &pos, flags);
-	if (ret >= 0)
-		f.file->f_pos = pos;
-	fdput_pos(f);
-	return ret;
-
-}
-
 COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
-		const struct compat_iovec __user *,vec,
+		const struct iovec __user *, vec,
 		compat_ulong_t, vlen)
 {
-	return do_compat_readv(fd, vec, vlen, 0);
-}
-
-static long do_compat_preadv64(unsigned long fd,
-				  const struct compat_iovec __user *vec,
-				  unsigned long vlen, loff_t pos, rwf_t flags)
-{
-	struct fd f;
-	ssize_t ret;
-
-	if (pos < 0)
-		return -EINVAL;
-	f = fdget(fd);
-	if (!f.file)
-		return -EBADF;
-	ret = -ESPIPE;
-	if (f.file->f_mode & FMODE_PREAD)
-		ret = compat_readv(f.file, vec, vlen, &pos, flags);
-	fdput(f);
-	return ret;
+	return do_readv(fd, vec, vlen, 0);
 }
 
 #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64
 COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd,
-		const struct compat_iovec __user *,vec,
+		const struct iovec __user *, vec,
 		unsigned long, vlen, loff_t, pos)
 {
-	return do_compat_preadv64(fd, vec, vlen, pos, 0);
+	return do_preadv(fd, vec, vlen, pos, 0);
 }
 #endif
 
 COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd,
-		const struct compat_iovec __user *,vec,
+		const struct iovec __user *, vec,
 		compat_ulong_t, vlen, u32, pos_low, u32, pos_high)
 {
 	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
 
-	return do_compat_preadv64(fd, vec, vlen, pos, 0);
+	return do_preadv(fd, vec, vlen, pos, 0);
 }
 
 #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2
 COMPAT_SYSCALL_DEFINE5(preadv64v2, unsigned long, fd,
-		const struct compat_iovec __user *,vec,
+		const struct iovec __user *, vec,
 		unsigned long, vlen, loff_t, pos, rwf_t, flags)
 {
 	if (pos == -1)
-		return do_compat_readv(fd, vec, vlen, flags);
-
-	return do_compat_preadv64(fd, vec, vlen, pos, flags);
+		return do_readv(fd, vec, vlen, flags);
+	return do_preadv(fd, vec, vlen, pos, flags);
 }
 #endif
 
 COMPAT_SYSCALL_DEFINE6(preadv2, compat_ulong_t, fd,
-		const struct compat_iovec __user *,vec,
+		const struct iovec __user *, vec,
 		compat_ulong_t, vlen, u32, pos_low, u32, pos_high,
 		rwf_t, flags)
 {
 	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
 
 	if (pos == -1)
-		return do_compat_readv(fd, vec, vlen, flags);
-
-	return do_compat_preadv64(fd, vec, vlen, pos, flags);
-}
-
-static size_t compat_writev(struct file *file,
-			    const struct compat_iovec __user *vec,
-			    unsigned long vlen, loff_t *pos, rwf_t flags)
-{
-	struct iovec iovstack[UIO_FASTIOV];
-	struct iovec *iov = iovstack;
-	struct iov_iter iter;
-	ssize_t ret;
-
-	ret = import_iovec(WRITE, (const struct iovec __user *)vec, vlen,
-			   UIO_FASTIOV, &iov, &iter);
-	if (ret >= 0) {
-		file_start_write(file);
-		ret = do_iter_write(file, &iter, pos, flags);
-		file_end_write(file);
-		kfree(iov);
-	}
-	if (ret > 0)
-		add_wchar(current, ret);
-	inc_syscw(current);
-	return ret;
-}
-
-static size_t do_compat_writev(compat_ulong_t fd,
-				  const struct compat_iovec __user* vec,
-				  compat_ulong_t vlen, rwf_t flags)
-{
-	struct fd f = fdget_pos(fd);
-	ssize_t ret;
-	loff_t pos;
-
-	if (!f.file)
-		return -EBADF;
-	pos = f.file->f_pos;
-	ret = compat_writev(f.file, vec, vlen, &pos, flags);
-	if (ret >= 0)
-		f.file->f_pos = pos;
-	fdput_pos(f);
-	return ret;
+		return do_readv(fd, vec, vlen, flags);
+	return do_preadv(fd, vec, vlen, pos, flags);
 }
 
 COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
-		const struct compat_iovec __user *, vec,
+		const struct iovec __user *, vec,
 		compat_ulong_t, vlen)
 {
-	return do_compat_writev(fd, vec, vlen, 0);
-}
-
-static long do_compat_pwritev64(unsigned long fd,
-				   const struct compat_iovec __user *vec,
-				   unsigned long vlen, loff_t pos, rwf_t flags)
-{
-	struct fd f;
-	ssize_t ret;
-
-	if (pos < 0)
-		return -EINVAL;
-	f = fdget(fd);
-	if (!f.file)
-		return -EBADF;
-	ret = -ESPIPE;
-	if (f.file->f_mode & FMODE_PWRITE)
-		ret = compat_writev(f.file, vec, vlen, &pos, flags);
-	fdput(f);
-	return ret;
+	return do_writev(fd, vec, vlen, 0);
 }
 
 #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64
 COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd,
-		const struct compat_iovec __user *,vec,
+		const struct iovec __user *, vec,
 		unsigned long, vlen, loff_t, pos)
 {
-	return do_compat_pwritev64(fd, vec, vlen, pos, 0);
+	return do_pwritev(fd, vec, vlen, pos, 0);
 }
 #endif
 
 COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd,
-		const struct compat_iovec __user *,vec,
+		const struct iovec __user *,vec,
 		compat_ulong_t, vlen, u32, pos_low, u32, pos_high)
 {
 	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
 
-	return do_compat_pwritev64(fd, vec, vlen, pos, 0);
+	return do_pwritev(fd, vec, vlen, pos, 0);
 }
 
 #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64V2
 COMPAT_SYSCALL_DEFINE5(pwritev64v2, unsigned long, fd,
-		const struct compat_iovec __user *,vec,
+		const struct iovec __user *, vec,
 		unsigned long, vlen, loff_t, pos, rwf_t, flags)
 {
 	if (pos == -1)
-		return do_compat_writev(fd, vec, vlen, flags);
-
-	return do_compat_pwritev64(fd, vec, vlen, pos, flags);
+		return do_writev(fd, vec, vlen, flags);
+	return do_pwritev(fd, vec, vlen, pos, flags);
 }
 #endif
 
 COMPAT_SYSCALL_DEFINE6(pwritev2, compat_ulong_t, fd,
-		const struct compat_iovec __user *,vec,
+		const struct iovec __user *,vec,
 		compat_ulong_t, vlen, u32, pos_low, u32, pos_high, rwf_t, flags)
 {
 	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
 
 	if (pos == -1)
-		return do_compat_writev(fd, vec, vlen, flags);
-
-	return do_compat_pwritev64(fd, vec, vlen, pos, flags);
+		return do_writev(fd, vec, vlen, flags);
+	return do_pwritev(fd, vec, vlen, pos, flags);
 }
-
-#endif
+#endif /* CONFIG_COMPAT */
 
 static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
 		  	   size_t count, loff_t max)
diff --git a/include/linux/compat.h b/include/linux/compat.h
index cebcaac68aec..36b5842162c7 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -546,25 +546,25 @@ asmlinkage long compat_sys_getdents(unsigned int fd,
 /* fs/read_write.c */
 asmlinkage long compat_sys_lseek(unsigned int, compat_off_t, unsigned int);
 asmlinkage ssize_t compat_sys_readv(compat_ulong_t fd,
-		const struct compat_iovec __user *vec, compat_ulong_t vlen);
+		const struct iovec __user *vec, compat_ulong_t vlen);
 asmlinkage ssize_t compat_sys_writev(compat_ulong_t fd,
-		const struct compat_iovec __user *vec, compat_ulong_t vlen);
+		const struct iovec __user *vec, compat_ulong_t vlen);
 /* No generic prototype for pread64 and pwrite64 */
 asmlinkage ssize_t compat_sys_preadv(compat_ulong_t fd,
-		const struct compat_iovec __user *vec,
+		const struct iovec __user *vec,
 		compat_ulong_t vlen, u32 pos_low, u32 pos_high);
 asmlinkage ssize_t compat_sys_pwritev(compat_ulong_t fd,
-		const struct compat_iovec __user *vec,
+		const struct iovec __user *vec,
 		compat_ulong_t vlen, u32 pos_low, u32 pos_high);
 #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64
 asmlinkage long compat_sys_preadv64(unsigned long fd,
-		const struct compat_iovec __user *vec,
+		const struct iovec __user *vec,
 		unsigned long vlen, loff_t pos);
 #endif
 
 #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64
 asmlinkage long compat_sys_pwritev64(unsigned long fd,
-		const struct compat_iovec __user *vec,
+		const struct iovec __user *vec,
 		unsigned long vlen, loff_t pos);
 #endif
 
@@ -800,20 +800,20 @@ asmlinkage long compat_sys_execveat(int dfd, const char __user *filename,
 		     const compat_uptr_t __user *argv,
 		     const compat_uptr_t __user *envp, int flags);
 asmlinkage ssize_t compat_sys_preadv2(compat_ulong_t fd,
-		const struct compat_iovec __user *vec,
+		const struct iovec __user *vec,
 		compat_ulong_t vlen, u32 pos_low, u32 pos_high, rwf_t flags);
 asmlinkage ssize_t compat_sys_pwritev2(compat_ulong_t fd,
-		const struct compat_iovec __user *vec,
+		const struct iovec __user *vec,
 		compat_ulong_t vlen, u32 pos_low, u32 pos_high, rwf_t flags);
 #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2
 asmlinkage long  compat_sys_preadv64v2(unsigned long fd,
-		const struct compat_iovec __user *vec,
+		const struct iovec __user *vec,
 		unsigned long vlen, loff_t pos, rwf_t flags);
 #endif
 
 #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64V2
 asmlinkage long compat_sys_pwritev64v2(unsigned long fd,
-		const struct compat_iovec __user *vec,
+		const struct iovec __user *vec,
 		unsigned long vlen, loff_t pos, rwf_t flags);
 #endif
 
-- 
cgit v1.2.3


From 5f764d624a89d4d00d282157077878d4e7c69869 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 25 Sep 2020 06:51:43 +0200
Subject: fs: remove the compat readv/writev syscalls

Now that import_iovec handles compat iovecs, the native readv and writev
syscalls can be used for the compat case as well.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/arm64/include/asm/unistd32.h                  |  4 ++--
 arch/mips/kernel/syscalls/syscall_n32.tbl          |  4 ++--
 arch/mips/kernel/syscalls/syscall_o32.tbl          |  4 ++--
 arch/parisc/kernel/syscalls/syscall.tbl            |  4 ++--
 arch/powerpc/kernel/syscalls/syscall.tbl           |  4 ++--
 arch/s390/kernel/syscalls/syscall.tbl              |  4 ++--
 arch/sparc/kernel/syscalls/syscall.tbl             |  4 ++--
 arch/x86/entry/syscall_x32.c                       |  2 ++
 arch/x86/entry/syscalls/syscall_32.tbl             |  4 ++--
 arch/x86/entry/syscalls/syscall_64.tbl             |  4 ++--
 fs/read_write.c                                    | 14 --------------
 include/linux/compat.h                             |  4 ----
 include/uapi/asm-generic/unistd.h                  |  4 ++--
 tools/include/uapi/asm-generic/unistd.h            |  4 ++--
 tools/perf/arch/powerpc/entry/syscalls/syscall.tbl |  4 ++--
 tools/perf/arch/s390/entry/syscalls/syscall.tbl    |  4 ++--
 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl  |  4 ++--
 17 files changed, 30 insertions(+), 46 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 734860ac7cf9..4a236493dca5 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -301,9 +301,9 @@ __SYSCALL(__NR_flock, sys_flock)
 #define __NR_msync 144
 __SYSCALL(__NR_msync, sys_msync)
 #define __NR_readv 145
-__SYSCALL(__NR_readv, compat_sys_readv)
+__SYSCALL(__NR_readv, sys_readv)
 #define __NR_writev 146
-__SYSCALL(__NR_writev, compat_sys_writev)
+__SYSCALL(__NR_writev, sys_writev)
 #define __NR_getsid 147
 __SYSCALL(__NR_getsid, sys_getsid)
 #define __NR_fdatasync 148
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index f9df9edb67a4..c99a92646f8e 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -25,8 +25,8 @@
 15	n32	ioctl				compat_sys_ioctl
 16	n32	pread64				sys_pread64
 17	n32	pwrite64			sys_pwrite64
-18	n32	readv				compat_sys_readv
-19	n32	writev				compat_sys_writev
+18	n32	readv				sys_readv
+19	n32	writev				sys_writev
 20	n32	access				sys_access
 21	n32	pipe				sysm_pipe
 22	n32	_newselect			compat_sys_select
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 195b43cf27c8..075064d10661 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -156,8 +156,8 @@
 142	o32	_newselect			sys_select			compat_sys_select
 143	o32	flock				sys_flock
 144	o32	msync				sys_msync
-145	o32	readv				sys_readv			compat_sys_readv
-146	o32	writev				sys_writev			compat_sys_writev
+145	o32	readv				sys_readv
+146	o32	writev				sys_writev
 147	o32	cacheflush			sys_cacheflush
 148	o32	cachectl			sys_cachectl
 149	o32	sysmips				__sys_sysmips
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index def64d221cd4..192abde0001d 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -159,8 +159,8 @@
 142	common	_newselect		sys_select			compat_sys_select
 143	common	flock			sys_flock
 144	common	msync			sys_msync
-145	common	readv			sys_readv			compat_sys_readv
-146	common	writev			sys_writev			compat_sys_writev
+145	common	readv			sys_readv
+146	common	writev			sys_writev
 147	common	getsid			sys_getsid
 148	common	fdatasync		sys_fdatasync
 149	common	_sysctl			sys_ni_syscall
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index c2d737ff2e7b..6f1e2ecf0eda 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -193,8 +193,8 @@
 142	common	_newselect			sys_select			compat_sys_select
 143	common	flock				sys_flock
 144	common	msync				sys_msync
-145	common	readv				sys_readv			compat_sys_readv
-146	common	writev				sys_writev			compat_sys_writev
+145	common	readv				sys_readv
+146	common	writev				sys_writev
 147	common	getsid				sys_getsid
 148	common	fdatasync			sys_fdatasync
 149	nospu	_sysctl				sys_ni_syscall
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 10456bc936fb..6101cf2e004c 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -134,8 +134,8 @@
 142  64		select			sys_select			-
 143  common	flock			sys_flock			sys_flock
 144  common	msync			sys_msync			sys_msync
-145  common	readv			sys_readv			compat_sys_readv
-146  common	writev			sys_writev			compat_sys_writev
+145  common	readv			sys_readv			sys_readv
+146  common	writev			sys_writev			sys_writev
 147  common	getsid			sys_getsid			sys_getsid
 148  common	fdatasync		sys_fdatasync			sys_fdatasync
 149  common	_sysctl			-				-
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index 4af114e84f20..a87ddb282ab1 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -149,8 +149,8 @@
 117	common	getrusage		sys_getrusage			compat_sys_getrusage
 118	common	getsockopt		sys_getsockopt			sys_getsockopt
 119	common	getcwd			sys_getcwd
-120	common	readv			sys_readv			compat_sys_readv
-121	common	writev			sys_writev			compat_sys_writev
+120	common	readv			sys_readv
+121	common	writev			sys_writev
 122	common	settimeofday		sys_settimeofday		compat_sys_settimeofday
 123	32	fchown			sys_fchown16
 123	64	fchown			sys_fchown
diff --git a/arch/x86/entry/syscall_x32.c b/arch/x86/entry/syscall_x32.c
index 1583831f61a9..aa321444a41f 100644
--- a/arch/x86/entry/syscall_x32.c
+++ b/arch/x86/entry/syscall_x32.c
@@ -12,6 +12,8 @@
  * Reuse the 64-bit entry points for the x32 versions that occupy different
  * slots in the syscall table.
  */
+#define __x32_sys_readv		__x64_sys_readv
+#define __x32_sys_writev	__x64_sys_writev
 #define __x32_sys_getsockopt	__x64_sys_getsockopt
 #define __x32_sys_setsockopt	__x64_sys_setsockopt
 
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 9d1102873666..54ab4beb517f 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -156,8 +156,8 @@
 142	i386	_newselect		sys_select			compat_sys_select
 143	i386	flock			sys_flock
 144	i386	msync			sys_msync
-145	i386	readv			sys_readv			compat_sys_readv
-146	i386	writev			sys_writev			compat_sys_writev
+145	i386	readv			sys_readv
+146	i386	writev			sys_writev
 147	i386	getsid			sys_getsid
 148	i386	fdatasync		sys_fdatasync
 149	i386	_sysctl			sys_ni_syscall
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index f30d6ae9a688..b1e59957c5c5 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -371,8 +371,8 @@
 512	x32	rt_sigaction		compat_sys_rt_sigaction
 513	x32	rt_sigreturn		compat_sys_x32_rt_sigreturn
 514	x32	ioctl			compat_sys_ioctl
-515	x32	readv			compat_sys_readv
-516	x32	writev			compat_sys_writev
+515	x32	readv			sys_readv
+516	x32	writev			sys_writev
 517	x32	recvfrom		compat_sys_recvfrom
 518	x32	sendmsg			compat_sys_sendmsg
 519	x32	recvmsg			compat_sys_recvmsg
diff --git a/fs/read_write.c b/fs/read_write.c
index eab427b7cc0a..6c13f744c34a 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1074,13 +1074,6 @@ SYSCALL_DEFINE6(pwritev2, unsigned long, fd, const struct iovec __user *, vec,
  * in_compat_syscall().
  */
 #ifdef CONFIG_COMPAT
-COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
-		const struct iovec __user *, vec,
-		compat_ulong_t, vlen)
-{
-	return do_readv(fd, vec, vlen, 0);
-}
-
 #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64
 COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd,
 		const struct iovec __user *, vec,
@@ -1122,13 +1115,6 @@ COMPAT_SYSCALL_DEFINE6(preadv2, compat_ulong_t, fd,
 	return do_preadv(fd, vec, vlen, pos, flags);
 }
 
-COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
-		const struct iovec __user *, vec,
-		compat_ulong_t, vlen)
-{
-	return do_writev(fd, vec, vlen, 0);
-}
-
 #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64
 COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd,
 		const struct iovec __user *, vec,
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 36b5842162c7..07268fc8082b 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -545,10 +545,6 @@ asmlinkage long compat_sys_getdents(unsigned int fd,
 
 /* fs/read_write.c */
 asmlinkage long compat_sys_lseek(unsigned int, compat_off_t, unsigned int);
-asmlinkage ssize_t compat_sys_readv(compat_ulong_t fd,
-		const struct iovec __user *vec, compat_ulong_t vlen);
-asmlinkage ssize_t compat_sys_writev(compat_ulong_t fd,
-		const struct iovec __user *vec, compat_ulong_t vlen);
 /* No generic prototype for pread64 and pwrite64 */
 asmlinkage ssize_t compat_sys_preadv(compat_ulong_t fd,
 		const struct iovec __user *vec,
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 995b36c2ea7d..211c9eacbda6 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -207,9 +207,9 @@ __SYSCALL(__NR_read, sys_read)
 #define __NR_write 64
 __SYSCALL(__NR_write, sys_write)
 #define __NR_readv 65
-__SC_COMP(__NR_readv, sys_readv, compat_sys_readv)
+__SC_COMP(__NR_readv, sys_readv, sys_readv)
 #define __NR_writev 66
-__SC_COMP(__NR_writev, sys_writev, compat_sys_writev)
+__SC_COMP(__NR_writev, sys_writev, sys_writev)
 #define __NR_pread64 67
 __SC_COMP(__NR_pread64, sys_pread64, compat_sys_pread64)
 #define __NR_pwrite64 68
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index 995b36c2ea7d..211c9eacbda6 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -207,9 +207,9 @@ __SYSCALL(__NR_read, sys_read)
 #define __NR_write 64
 __SYSCALL(__NR_write, sys_write)
 #define __NR_readv 65
-__SC_COMP(__NR_readv, sys_readv, compat_sys_readv)
+__SC_COMP(__NR_readv, sys_readv, sys_readv)
 #define __NR_writev 66
-__SC_COMP(__NR_writev, sys_writev, compat_sys_writev)
+__SC_COMP(__NR_writev, sys_writev, sys_writev)
 #define __NR_pread64 67
 __SC_COMP(__NR_pread64, sys_pread64, compat_sys_pread64)
 #define __NR_pwrite64 68
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index 3ca6fe057a0b..46be68029587 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -189,8 +189,8 @@
 142	common	_newselect			sys_select			compat_sys_select
 143	common	flock				sys_flock
 144	common	msync				sys_msync
-145	common	readv				sys_readv			compat_sys_readv
-146	common	writev				sys_writev			compat_sys_writev
+145	common	readv				sys_readv
+146	common	writev				sys_writev
 147	common	getsid				sys_getsid
 148	common	fdatasync			sys_fdatasync
 149	nospu	_sysctl				sys_ni_syscall
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index 6a0bbea225db..fb5e61ce9d58 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -134,8 +134,8 @@
 142  64		select			sys_select			-
 143  common	flock			sys_flock			sys_flock
 144  common	msync			sys_msync			compat_sys_msync
-145  common	readv			sys_readv			compat_sys_readv
-146  common	writev			sys_writev			compat_sys_writev
+145  common	readv			sys_readv
+146  common	writev			sys_writev
 147  common	getsid			sys_getsid			sys_getsid
 148  common	fdatasync		sys_fdatasync			sys_fdatasync
 149  common	_sysctl			-				-
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index f30d6ae9a688..b1e59957c5c5 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -371,8 +371,8 @@
 512	x32	rt_sigaction		compat_sys_rt_sigaction
 513	x32	rt_sigreturn		compat_sys_x32_rt_sigreturn
 514	x32	ioctl			compat_sys_ioctl
-515	x32	readv			compat_sys_readv
-516	x32	writev			compat_sys_writev
+515	x32	readv			sys_readv
+516	x32	writev			sys_writev
 517	x32	recvfrom		compat_sys_recvfrom
 518	x32	sendmsg			compat_sys_sendmsg
 519	x32	recvmsg			compat_sys_recvmsg
-- 
cgit v1.2.3


From 598b3cec831fd6ccb3cbe4919a722e868c6364a8 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 25 Sep 2020 06:51:44 +0200
Subject: fs: remove compat_sys_vmsplice

Now that import_iovec handles compat iovecs, the native vmsplice syscall
can be used for the compat case as well.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/arm64/include/asm/unistd32.h                  |  2 +-
 arch/mips/kernel/syscalls/syscall_n32.tbl          |  2 +-
 arch/mips/kernel/syscalls/syscall_o32.tbl          |  2 +-
 arch/parisc/kernel/syscalls/syscall.tbl            |  2 +-
 arch/powerpc/kernel/syscalls/syscall.tbl           |  2 +-
 arch/s390/kernel/syscalls/syscall.tbl              |  2 +-
 arch/sparc/kernel/syscalls/syscall.tbl             |  2 +-
 arch/x86/entry/syscall_x32.c                       |  1 +
 arch/x86/entry/syscalls/syscall_32.tbl             |  2 +-
 arch/x86/entry/syscalls/syscall_64.tbl             |  2 +-
 fs/splice.c                                        | 57 +++++-----------------
 include/linux/compat.h                             |  4 --
 include/uapi/asm-generic/unistd.h                  |  2 +-
 tools/include/uapi/asm-generic/unistd.h            |  2 +-
 tools/perf/arch/powerpc/entry/syscalls/syscall.tbl |  2 +-
 tools/perf/arch/s390/entry/syscalls/syscall.tbl    |  2 +-
 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl  |  2 +-
 17 files changed, 28 insertions(+), 62 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 4a236493dca5..11dfae3a8563 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -697,7 +697,7 @@ __SYSCALL(__NR_sync_file_range2, compat_sys_aarch32_sync_file_range2)
 #define __NR_tee 342
 __SYSCALL(__NR_tee, sys_tee)
 #define __NR_vmsplice 343
-__SYSCALL(__NR_vmsplice, compat_sys_vmsplice)
+__SYSCALL(__NR_vmsplice, sys_vmsplice)
 #define __NR_move_pages 344
 __SYSCALL(__NR_move_pages, compat_sys_move_pages)
 #define __NR_getcpu 345
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index c99a92646f8e..5a39d4de0ac8 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -278,7 +278,7 @@
 267	n32	splice				sys_splice
 268	n32	sync_file_range			sys_sync_file_range
 269	n32	tee				sys_tee
-270	n32	vmsplice			compat_sys_vmsplice
+270	n32	vmsplice			sys_vmsplice
 271	n32	move_pages			compat_sys_move_pages
 272	n32	set_robust_list			compat_sys_set_robust_list
 273	n32	get_robust_list			compat_sys_get_robust_list
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 075064d10661..136efc6b8c54 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -318,7 +318,7 @@
 304	o32	splice				sys_splice
 305	o32	sync_file_range			sys_sync_file_range		sys32_sync_file_range
 306	o32	tee				sys_tee
-307	o32	vmsplice			sys_vmsplice			compat_sys_vmsplice
+307	o32	vmsplice			sys_vmsplice
 308	o32	move_pages			sys_move_pages			compat_sys_move_pages
 309	o32	set_robust_list			sys_set_robust_list		compat_sys_set_robust_list
 310	o32	get_robust_list			sys_get_robust_list		compat_sys_get_robust_list
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index 192abde0001d..a9e184192cae 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -330,7 +330,7 @@
 292	32	sync_file_range		parisc_sync_file_range
 292	64	sync_file_range		sys_sync_file_range
 293	common	tee			sys_tee
-294	common	vmsplice		sys_vmsplice			compat_sys_vmsplice
+294	common	vmsplice		sys_vmsplice
 295	common	move_pages		sys_move_pages			compat_sys_move_pages
 296	common	getcpu			sys_getcpu
 297	common	epoll_pwait		sys_epoll_pwait			compat_sys_epoll_pwait
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index 6f1e2ecf0eda..0d4985919ca3 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -369,7 +369,7 @@
 282	common	unshare				sys_unshare
 283	common	splice				sys_splice
 284	common	tee				sys_tee
-285	common	vmsplice			sys_vmsplice			compat_sys_vmsplice
+285	common	vmsplice			sys_vmsplice
 286	common	openat				sys_openat			compat_sys_openat
 287	common	mkdirat				sys_mkdirat
 288	common	mknodat				sys_mknodat
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 6101cf2e004c..b5495a42814b 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -316,7 +316,7 @@
 306  common	splice			sys_splice			sys_splice
 307  common	sync_file_range		sys_sync_file_range		compat_sys_s390_sync_file_range
 308  common	tee			sys_tee				sys_tee
-309  common	vmsplice		sys_vmsplice			compat_sys_vmsplice
+309  common	vmsplice		sys_vmsplice			sys_vmsplice
 310  common	move_pages		sys_move_pages			compat_sys_move_pages
 311  common	getcpu			sys_getcpu			sys_getcpu
 312  common	epoll_pwait		sys_epoll_pwait			compat_sys_epoll_pwait
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index a87ddb282ab1..f1810c1a35ca 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -38,7 +38,7 @@
 23	64    	setuid			sys_setuid
 24	32	getuid			sys_getuid16
 24	64   	getuid			sys_getuid
-25	common	vmsplice		sys_vmsplice			compat_sys_vmsplice
+25	common	vmsplice		sys_vmsplice
 26	common	ptrace			sys_ptrace			compat_sys_ptrace
 27	common	alarm			sys_alarm
 28	common	sigaltstack		sys_sigaltstack			compat_sys_sigaltstack
diff --git a/arch/x86/entry/syscall_x32.c b/arch/x86/entry/syscall_x32.c
index aa321444a41f..a4840b9d50ad 100644
--- a/arch/x86/entry/syscall_x32.c
+++ b/arch/x86/entry/syscall_x32.c
@@ -16,6 +16,7 @@
 #define __x32_sys_writev	__x64_sys_writev
 #define __x32_sys_getsockopt	__x64_sys_getsockopt
 #define __x32_sys_setsockopt	__x64_sys_setsockopt
+#define __x32_sys_vmsplice	__x64_sys_vmsplice
 
 #define __SYSCALL_64(nr, sym)
 
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 54ab4beb517f..0fb2f172581e 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -327,7 +327,7 @@
 313	i386	splice			sys_splice
 314	i386	sync_file_range		sys_ia32_sync_file_range
 315	i386	tee			sys_tee
-316	i386	vmsplice		sys_vmsplice			compat_sys_vmsplice
+316	i386	vmsplice		sys_vmsplice
 317	i386	move_pages		sys_move_pages			compat_sys_move_pages
 318	i386	getcpu			sys_getcpu
 319	i386	epoll_pwait		sys_epoll_pwait
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index b1e59957c5c5..642af919183d 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -388,7 +388,7 @@
 529	x32	waitid			compat_sys_waitid
 530	x32	set_robust_list		compat_sys_set_robust_list
 531	x32	get_robust_list		compat_sys_get_robust_list
-532	x32	vmsplice		compat_sys_vmsplice
+532	x32	vmsplice		sys_vmsplice
 533	x32	move_pages		compat_sys_move_pages
 534	x32	preadv			compat_sys_preadv64
 535	x32	pwritev			compat_sys_pwritev64
diff --git a/fs/splice.c b/fs/splice.c
index 132d42b9871f..18d84544030b 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -33,7 +33,6 @@
 #include <linux/security.h>
 #include <linux/gfp.h>
 #include <linux/socket.h>
-#include <linux/compat.h>
 #include <linux/sched/signal.h>
 
 #include "internal.h"
@@ -1332,20 +1331,6 @@ static int vmsplice_type(struct fd f, int *type)
  * Currently we punt and implement it as a normal copy, see pipe_to_user().
  *
  */
-static long do_vmsplice(struct file *f, struct iov_iter *iter, unsigned int flags)
-{
-	if (unlikely(flags & ~SPLICE_F_ALL))
-		return -EINVAL;
-
-	if (!iov_iter_count(iter))
-		return 0;
-
-	if (iov_iter_rw(iter) == WRITE)
-		return vmsplice_to_pipe(f, iter, flags);
-	else
-		return vmsplice_to_user(f, iter, flags);
-}
-
 SYSCALL_DEFINE4(vmsplice, int, fd, const struct iovec __user *, uiov,
 		unsigned long, nr_segs, unsigned int, flags)
 {
@@ -1356,6 +1341,9 @@ SYSCALL_DEFINE4(vmsplice, int, fd, const struct iovec __user *, uiov,
 	struct fd f;
 	int type;
 
+	if (unlikely(flags & ~SPLICE_F_ALL))
+		return -EINVAL;
+
 	f = fdget(fd);
 	error = vmsplice_type(f, &type);
 	if (error)
@@ -1363,40 +1351,21 @@ SYSCALL_DEFINE4(vmsplice, int, fd, const struct iovec __user *, uiov,
 
 	error = import_iovec(type, uiov, nr_segs,
 			     ARRAY_SIZE(iovstack), &iov, &iter);
-	if (error >= 0) {
-		error = do_vmsplice(f.file, &iter, flags);
-		kfree(iov);
-	}
-	fdput(f);
-	return error;
-}
+	if (error < 0)
+		goto out_fdput;
 
-#ifdef CONFIG_COMPAT
-COMPAT_SYSCALL_DEFINE4(vmsplice, int, fd, const struct compat_iovec __user *, iov32,
-		    unsigned int, nr_segs, unsigned int, flags)
-{
-	struct iovec iovstack[UIO_FASTIOV];
-	struct iovec *iov = iovstack;
-	struct iov_iter iter;
-	ssize_t error;
-	struct fd f;
-	int type;
-
-	f = fdget(fd);
-	error = vmsplice_type(f, &type);
-	if (error)
-		return error;
+	if (!iov_iter_count(&iter))
+		error = 0;
+	else if (iov_iter_rw(&iter) == WRITE)
+		error = vmsplice_to_pipe(f.file, &iter, flags);
+	else
+		error = vmsplice_to_user(f.file, &iter, flags);
 
-	error = import_iovec(type, (struct iovec __user *)iov32, nr_segs,
-			     ARRAY_SIZE(iovstack), &iov, &iter);
-	if (error >= 0) {
-		error = do_vmsplice(f.file, &iter, flags);
-		kfree(iov);
-	}
+	kfree(iov);
+out_fdput:
 	fdput(f);
 	return error;
 }
-#endif
 
 SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in,
 		int, fd_out, loff_t __user *, off_out,
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 07268fc8082b..7c3e876703cf 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -597,10 +597,6 @@ asmlinkage long compat_sys_signalfd4(int ufd,
 				     const compat_sigset_t __user *sigmask,
 				     compat_size_t sigsetsize, int flags);
 
-/* fs/splice.c */
-asmlinkage long compat_sys_vmsplice(int fd, const struct compat_iovec __user *,
-				    unsigned int nr_segs, unsigned int flags);
-
 /* fs/stat.c */
 asmlinkage long compat_sys_newfstatat(unsigned int dfd,
 				      const char __user *filename,
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 211c9eacbda6..f2dcb0d57030 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -237,7 +237,7 @@ __SC_COMP(__NR_signalfd4, sys_signalfd4, compat_sys_signalfd4)
 
 /* fs/splice.c */
 #define __NR_vmsplice 75
-__SC_COMP(__NR_vmsplice, sys_vmsplice, compat_sys_vmsplice)
+__SYSCALL(__NR_vmsplice, sys_vmsplice)
 #define __NR_splice 76
 __SYSCALL(__NR_splice, sys_splice)
 #define __NR_tee 77
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index 211c9eacbda6..f2dcb0d57030 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -237,7 +237,7 @@ __SC_COMP(__NR_signalfd4, sys_signalfd4, compat_sys_signalfd4)
 
 /* fs/splice.c */
 #define __NR_vmsplice 75
-__SC_COMP(__NR_vmsplice, sys_vmsplice, compat_sys_vmsplice)
+__SYSCALL(__NR_vmsplice, sys_vmsplice)
 #define __NR_splice 76
 __SYSCALL(__NR_splice, sys_splice)
 #define __NR_tee 77
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index 46be68029587..26f0347c1511 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -363,7 +363,7 @@
 282	common	unshare				sys_unshare
 283	common	splice				sys_splice
 284	common	tee				sys_tee
-285	common	vmsplice			sys_vmsplice			compat_sys_vmsplice
+285	common	vmsplice			sys_vmsplice
 286	common	openat				sys_openat			compat_sys_openat
 287	common	mkdirat				sys_mkdirat
 288	common	mknodat				sys_mknodat
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index fb5e61ce9d58..02ad81f69bb7 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -316,7 +316,7 @@
 306  common	splice			sys_splice			compat_sys_splice
 307  common	sync_file_range		sys_sync_file_range		compat_sys_s390_sync_file_range
 308  common	tee			sys_tee				compat_sys_tee
-309  common	vmsplice		sys_vmsplice			compat_sys_vmsplice
+309  common	vmsplice		sys_vmsplice			sys_vmsplice
 310  common	move_pages		sys_move_pages			compat_sys_move_pages
 311  common	getcpu			sys_getcpu			compat_sys_getcpu
 312  common	epoll_pwait		sys_epoll_pwait			compat_sys_epoll_pwait
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index b1e59957c5c5..642af919183d 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -388,7 +388,7 @@
 529	x32	waitid			compat_sys_waitid
 530	x32	set_robust_list		compat_sys_set_robust_list
 531	x32	get_robust_list		compat_sys_get_robust_list
-532	x32	vmsplice		compat_sys_vmsplice
+532	x32	vmsplice		sys_vmsplice
 533	x32	move_pages		compat_sys_move_pages
 534	x32	preadv			compat_sys_preadv64
 535	x32	pwritev			compat_sys_pwritev64
-- 
cgit v1.2.3


From c3973b401ef2b0b8005f8074a10e96e3ea093823 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 25 Sep 2020 06:51:45 +0200
Subject: mm: remove compat_process_vm_{readv,writev}

Now that import_iovec handles compat iovecs, the native syscalls
can be used for the compat case as well.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/arm64/include/asm/unistd32.h                  |  4 +-
 arch/mips/kernel/syscalls/syscall_n32.tbl          |  4 +-
 arch/mips/kernel/syscalls/syscall_o32.tbl          |  4 +-
 arch/parisc/kernel/syscalls/syscall.tbl            |  4 +-
 arch/powerpc/kernel/syscalls/syscall.tbl           |  4 +-
 arch/s390/kernel/syscalls/syscall.tbl              |  4 +-
 arch/sparc/kernel/syscalls/syscall.tbl             |  4 +-
 arch/x86/entry/syscall_x32.c                       |  2 +
 arch/x86/entry/syscalls/syscall_32.tbl             |  4 +-
 arch/x86/entry/syscalls/syscall_64.tbl             |  4 +-
 include/linux/compat.h                             |  8 ---
 include/uapi/asm-generic/unistd.h                  |  6 +-
 mm/process_vm_access.c                             | 69 ----------------------
 tools/include/uapi/asm-generic/unistd.h            |  6 +-
 tools/perf/arch/powerpc/entry/syscalls/syscall.tbl |  4 +-
 tools/perf/arch/s390/entry/syscalls/syscall.tbl    |  4 +-
 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl  |  4 +-
 17 files changed, 30 insertions(+), 109 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 11dfae3a8563..0c280a05f699 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -763,9 +763,9 @@ __SYSCALL(__NR_sendmmsg, compat_sys_sendmmsg)
 #define __NR_setns 375
 __SYSCALL(__NR_setns, sys_setns)
 #define __NR_process_vm_readv 376
-__SYSCALL(__NR_process_vm_readv, compat_sys_process_vm_readv)
+__SYSCALL(__NR_process_vm_readv, sys_process_vm_readv)
 #define __NR_process_vm_writev 377
-__SYSCALL(__NR_process_vm_writev, compat_sys_process_vm_writev)
+__SYSCALL(__NR_process_vm_writev, sys_process_vm_writev)
 #define __NR_kcmp 378
 __SYSCALL(__NR_kcmp, sys_kcmp)
 #define __NR_finit_module 379
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index 5a39d4de0ac8..0bc2e0fcf1ee 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -317,8 +317,8 @@
 306	n32	syncfs				sys_syncfs
 307	n32	sendmmsg			compat_sys_sendmmsg
 308	n32	setns				sys_setns
-309	n32	process_vm_readv		compat_sys_process_vm_readv
-310	n32	process_vm_writev		compat_sys_process_vm_writev
+309	n32	process_vm_readv		sys_process_vm_readv
+310	n32	process_vm_writev		sys_process_vm_writev
 311	n32	kcmp				sys_kcmp
 312	n32	finit_module			sys_finit_module
 313	n32	sched_setattr			sys_sched_setattr
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 136efc6b8c54..b408c13b9342 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -356,8 +356,8 @@
 342	o32	syncfs				sys_syncfs
 343	o32	sendmmsg			sys_sendmmsg			compat_sys_sendmmsg
 344	o32	setns				sys_setns
-345	o32	process_vm_readv		sys_process_vm_readv		compat_sys_process_vm_readv
-346	o32	process_vm_writev		sys_process_vm_writev		compat_sys_process_vm_writev
+345	o32	process_vm_readv		sys_process_vm_readv
+346	o32	process_vm_writev		sys_process_vm_writev
 347	o32	kcmp				sys_kcmp
 348	o32	finit_module			sys_finit_module
 349	o32	sched_setattr			sys_sched_setattr
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index a9e184192cae..2015a5124b78 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -372,8 +372,8 @@
 327	common	syncfs			sys_syncfs
 328	common	setns			sys_setns
 329	common	sendmmsg		sys_sendmmsg			compat_sys_sendmmsg
-330	common	process_vm_readv	sys_process_vm_readv		compat_sys_process_vm_readv
-331	common	process_vm_writev	sys_process_vm_writev		compat_sys_process_vm_writev
+330	common	process_vm_readv	sys_process_vm_readv
+331	common	process_vm_writev	sys_process_vm_writev
 332	common	kcmp			sys_kcmp
 333	common	finit_module		sys_finit_module
 334	common	sched_setattr		sys_sched_setattr
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index 0d4985919ca3..66a472aa635d 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -449,8 +449,8 @@
 348	common	syncfs				sys_syncfs
 349	common	sendmmsg			sys_sendmmsg			compat_sys_sendmmsg
 350	common	setns				sys_setns
-351	nospu	process_vm_readv		sys_process_vm_readv		compat_sys_process_vm_readv
-352	nospu	process_vm_writev		sys_process_vm_writev		compat_sys_process_vm_writev
+351	nospu	process_vm_readv		sys_process_vm_readv
+352	nospu	process_vm_writev		sys_process_vm_writev
 353	nospu	finit_module			sys_finit_module
 354	nospu	kcmp				sys_kcmp
 355	common	sched_setattr			sys_sched_setattr
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index b5495a42814b..7485867a490b 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -347,8 +347,8 @@
 337  common	clock_adjtime		sys_clock_adjtime		sys_clock_adjtime32
 338  common	syncfs			sys_syncfs			sys_syncfs
 339  common	setns			sys_setns			sys_setns
-340  common	process_vm_readv	sys_process_vm_readv		compat_sys_process_vm_readv
-341  common	process_vm_writev	sys_process_vm_writev		compat_sys_process_vm_writev
+340  common	process_vm_readv	sys_process_vm_readv		sys_process_vm_readv
+341  common	process_vm_writev	sys_process_vm_writev		sys_process_vm_writev
 342  common	s390_runtime_instr	sys_s390_runtime_instr		sys_s390_runtime_instr
 343  common	kcmp			sys_kcmp			sys_kcmp
 344  common	finit_module		sys_finit_module		sys_finit_module
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index f1810c1a35ca..4a9365b2e340 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -406,8 +406,8 @@
 335	common	syncfs			sys_syncfs
 336	common	sendmmsg		sys_sendmmsg			compat_sys_sendmmsg
 337	common	setns			sys_setns
-338	common	process_vm_readv	sys_process_vm_readv		compat_sys_process_vm_readv
-339	common	process_vm_writev	sys_process_vm_writev		compat_sys_process_vm_writev
+338	common	process_vm_readv	sys_process_vm_readv
+339	common	process_vm_writev	sys_process_vm_writev
 340	32	kern_features		sys_ni_syscall			sys_kern_features
 340	64	kern_features		sys_kern_features
 341	common	kcmp			sys_kcmp
diff --git a/arch/x86/entry/syscall_x32.c b/arch/x86/entry/syscall_x32.c
index a4840b9d50ad..f2fe0a33bcfd 100644
--- a/arch/x86/entry/syscall_x32.c
+++ b/arch/x86/entry/syscall_x32.c
@@ -17,6 +17,8 @@
 #define __x32_sys_getsockopt	__x64_sys_getsockopt
 #define __x32_sys_setsockopt	__x64_sys_setsockopt
 #define __x32_sys_vmsplice	__x64_sys_vmsplice
+#define __x32_sys_process_vm_readv	__x64_sys_process_vm_readv
+#define __x32_sys_process_vm_writev	__x64_sys_process_vm_writev
 
 #define __SYSCALL_64(nr, sym)
 
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 0fb2f172581e..5fbe10ad8a23 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -358,8 +358,8 @@
 344	i386	syncfs			sys_syncfs
 345	i386	sendmmsg		sys_sendmmsg			compat_sys_sendmmsg
 346	i386	setns			sys_setns
-347	i386	process_vm_readv	sys_process_vm_readv		compat_sys_process_vm_readv
-348	i386	process_vm_writev	sys_process_vm_writev		compat_sys_process_vm_writev
+347	i386	process_vm_readv	sys_process_vm_readv
+348	i386	process_vm_writev	sys_process_vm_writev
 349	i386	kcmp			sys_kcmp
 350	i386	finit_module		sys_finit_module
 351	i386	sched_setattr		sys_sched_setattr
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 642af919183d..347809649ba2 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -395,8 +395,8 @@
 536	x32	rt_tgsigqueueinfo	compat_sys_rt_tgsigqueueinfo
 537	x32	recvmmsg		compat_sys_recvmmsg_time64
 538	x32	sendmmsg		compat_sys_sendmmsg
-539	x32	process_vm_readv	compat_sys_process_vm_readv
-540	x32	process_vm_writev	compat_sys_process_vm_writev
+539	x32	process_vm_readv	sys_process_vm_readv
+540	x32	process_vm_writev	sys_process_vm_writev
 541	x32	setsockopt		sys_setsockopt
 542	x32	getsockopt		sys_getsockopt
 543	x32	io_setup		compat_sys_io_setup
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 7c3e876703cf..3e3d2beafed3 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -780,14 +780,6 @@ asmlinkage long compat_sys_open_by_handle_at(int mountdirfd,
 					     int flags);
 asmlinkage long compat_sys_sendmmsg(int fd, struct compat_mmsghdr __user *mmsg,
 				    unsigned vlen, unsigned int flags);
-asmlinkage ssize_t compat_sys_process_vm_readv(compat_pid_t pid,
-		const struct compat_iovec __user *lvec,
-		compat_ulong_t liovcnt, const struct compat_iovec __user *rvec,
-		compat_ulong_t riovcnt, compat_ulong_t flags);
-asmlinkage ssize_t compat_sys_process_vm_writev(compat_pid_t pid,
-		const struct compat_iovec __user *lvec,
-		compat_ulong_t liovcnt, const struct compat_iovec __user *rvec,
-		compat_ulong_t riovcnt, compat_ulong_t flags);
 asmlinkage long compat_sys_execveat(int dfd, const char __user *filename,
 		     const compat_uptr_t __user *argv,
 		     const compat_uptr_t __user *envp, int flags);
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index f2dcb0d57030..c1dfe99c9c3f 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -727,11 +727,9 @@ __SYSCALL(__NR_setns, sys_setns)
 #define __NR_sendmmsg 269
 __SC_COMP(__NR_sendmmsg, sys_sendmmsg, compat_sys_sendmmsg)
 #define __NR_process_vm_readv 270
-__SC_COMP(__NR_process_vm_readv, sys_process_vm_readv, \
-          compat_sys_process_vm_readv)
+__SYSCALL(__NR_process_vm_readv, sys_process_vm_readv)
 #define __NR_process_vm_writev 271
-__SC_COMP(__NR_process_vm_writev, sys_process_vm_writev, \
-          compat_sys_process_vm_writev)
+__SYSCALL(__NR_process_vm_writev, sys_process_vm_writev)
 #define __NR_kcmp 272
 __SYSCALL(__NR_kcmp, sys_kcmp)
 #define __NR_finit_module 273
diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c
index 3f2156aab442..fd12da80b6f2 100644
--- a/mm/process_vm_access.c
+++ b/mm/process_vm_access.c
@@ -14,10 +14,6 @@
 #include <linux/slab.h>
 #include <linux/syscalls.h>
 
-#ifdef CONFIG_COMPAT
-#include <linux/compat.h>
-#endif
-
 /**
  * process_vm_rw_pages - read/write pages from task specified
  * @pages: array of pointers to pages we want to copy
@@ -304,68 +300,3 @@ SYSCALL_DEFINE6(process_vm_writev, pid_t, pid,
 {
 	return process_vm_rw(pid, lvec, liovcnt, rvec, riovcnt, flags, 1);
 }
-
-#ifdef CONFIG_COMPAT
-
-static ssize_t
-compat_process_vm_rw(compat_pid_t pid,
-		     const struct compat_iovec __user *lvec,
-		     unsigned long liovcnt,
-		     const struct compat_iovec __user *rvec,
-		     unsigned long riovcnt,
-		     unsigned long flags, int vm_write)
-{
-	struct iovec iovstack_l[UIO_FASTIOV];
-	struct iovec iovstack_r[UIO_FASTIOV];
-	struct iovec *iov_l = iovstack_l;
-	struct iovec *iov_r = iovstack_r;
-	struct iov_iter iter;
-	ssize_t rc = -EFAULT;
-	int dir = vm_write ? WRITE : READ;
-
-	if (flags != 0)
-		return -EINVAL;
-
-	rc = import_iovec(dir, (const struct iovec __user *)lvec, liovcnt,
-			  UIO_FASTIOV, &iov_l, &iter);
-	if (rc < 0)
-		return rc;
-	if (!iov_iter_count(&iter))
-		goto free_iov_l;
-	iov_r = iovec_from_user((const struct iovec __user *)rvec, riovcnt,
-				UIO_FASTIOV, iovstack_r, true);
-	if (IS_ERR(iov_r)) {
-		rc = PTR_ERR(iov_r);
-		goto free_iov_l;
-	}
-	rc = process_vm_rw_core(pid, &iter, iov_r, riovcnt, flags, vm_write);
-	if (iov_r != iovstack_r)
-		kfree(iov_r);
-free_iov_l:
-	kfree(iov_l);
-	return rc;
-}
-
-COMPAT_SYSCALL_DEFINE6(process_vm_readv, compat_pid_t, pid,
-		       const struct compat_iovec __user *, lvec,
-		       compat_ulong_t, liovcnt,
-		       const struct compat_iovec __user *, rvec,
-		       compat_ulong_t, riovcnt,
-		       compat_ulong_t, flags)
-{
-	return compat_process_vm_rw(pid, lvec, liovcnt, rvec,
-				    riovcnt, flags, 0);
-}
-
-COMPAT_SYSCALL_DEFINE6(process_vm_writev, compat_pid_t, pid,
-		       const struct compat_iovec __user *, lvec,
-		       compat_ulong_t, liovcnt,
-		       const struct compat_iovec __user *, rvec,
-		       compat_ulong_t, riovcnt,
-		       compat_ulong_t, flags)
-{
-	return compat_process_vm_rw(pid, lvec, liovcnt, rvec,
-				    riovcnt, flags, 1);
-}
-
-#endif
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index f2dcb0d57030..c1dfe99c9c3f 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -727,11 +727,9 @@ __SYSCALL(__NR_setns, sys_setns)
 #define __NR_sendmmsg 269
 __SC_COMP(__NR_sendmmsg, sys_sendmmsg, compat_sys_sendmmsg)
 #define __NR_process_vm_readv 270
-__SC_COMP(__NR_process_vm_readv, sys_process_vm_readv, \
-          compat_sys_process_vm_readv)
+__SYSCALL(__NR_process_vm_readv, sys_process_vm_readv)
 #define __NR_process_vm_writev 271
-__SC_COMP(__NR_process_vm_writev, sys_process_vm_writev, \
-          compat_sys_process_vm_writev)
+__SYSCALL(__NR_process_vm_writev, sys_process_vm_writev)
 #define __NR_kcmp 272
 __SYSCALL(__NR_kcmp, sys_kcmp)
 #define __NR_finit_module 273
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index 26f0347c1511..a188f053cbf9 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -443,8 +443,8 @@
 348	common	syncfs				sys_syncfs
 349	common	sendmmsg			sys_sendmmsg			compat_sys_sendmmsg
 350	common	setns				sys_setns
-351	nospu	process_vm_readv		sys_process_vm_readv		compat_sys_process_vm_readv
-352	nospu	process_vm_writev		sys_process_vm_writev		compat_sys_process_vm_writev
+351	nospu	process_vm_readv		sys_process_vm_readv
+352	nospu	process_vm_writev		sys_process_vm_writev
 353	nospu	finit_module			sys_finit_module
 354	nospu	kcmp				sys_kcmp
 355	common	sched_setattr			sys_sched_setattr
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index 02ad81f69bb7..c44c83032c3a 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -347,8 +347,8 @@
 337  common	clock_adjtime		sys_clock_adjtime		compat_sys_clock_adjtime
 338  common	syncfs			sys_syncfs			sys_syncfs
 339  common	setns			sys_setns			sys_setns
-340  common	process_vm_readv	sys_process_vm_readv		compat_sys_process_vm_readv
-341  common	process_vm_writev	sys_process_vm_writev		compat_sys_process_vm_writev
+340  common	process_vm_readv	sys_process_vm_readv		sys_process_vm_readv
+341  common	process_vm_writev	sys_process_vm_writev		sys_process_vm_writev
 342  common	s390_runtime_instr	sys_s390_runtime_instr		sys_s390_runtime_instr
 343  common	kcmp			sys_kcmp			compat_sys_kcmp
 344  common	finit_module		sys_finit_module		compat_sys_finit_module
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 642af919183d..347809649ba2 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -395,8 +395,8 @@
 536	x32	rt_tgsigqueueinfo	compat_sys_rt_tgsigqueueinfo
 537	x32	recvmmsg		compat_sys_recvmmsg_time64
 538	x32	sendmmsg		compat_sys_sendmmsg
-539	x32	process_vm_readv	compat_sys_process_vm_readv
-540	x32	process_vm_writev	compat_sys_process_vm_writev
+539	x32	process_vm_readv	sys_process_vm_readv
+540	x32	process_vm_writev	sys_process_vm_writev
 541	x32	setsockopt		sys_setsockopt
 542	x32	getsockopt		sys_getsockopt
 543	x32	io_setup		compat_sys_io_setup
-- 
cgit v1.2.3


From 51cf18c90ca1b51d1cb4af3064e85fcf8610b5d2 Mon Sep 17 00:00:00 2001
From: Vincent Donnefort <vincent.donnefort@arm.com>
Date: Fri, 28 Aug 2020 10:00:49 +0100
Subject: sched/debug: Add new tracepoint to track cpu_capacity

rq->cpu_capacity is a key element in several scheduler parts, such as EAS
task placement and load balancing. Tracking this value enables testing
and/or debugging by a toolkit.

Signed-off-by: Vincent Donnefort <vincent.donnefort@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/1598605249-72651-1-git-send-email-vincent.donnefort@arm.com
---
 include/linux/sched.h        |  1 +
 include/trace/events/sched.h |  4 ++++
 kernel/sched/core.c          |  1 +
 kernel/sched/fair.c          | 14 ++++++++++++++
 4 files changed, 20 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 2bf0af19a62a..f516c18eeb20 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2044,6 +2044,7 @@ const struct sched_avg *sched_trace_rq_avg_dl(struct rq *rq);
 const struct sched_avg *sched_trace_rq_avg_irq(struct rq *rq);
 
 int sched_trace_rq_cpu(struct rq *rq);
+int sched_trace_rq_cpu_capacity(struct rq *rq);
 int sched_trace_rq_nr_running(struct rq *rq);
 
 const struct cpumask *sched_trace_rd_span(struct root_domain *rd);
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index fec25b9cfbaf..c96a4337afe6 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -630,6 +630,10 @@ DECLARE_TRACE(pelt_se_tp,
 	TP_PROTO(struct sched_entity *se),
 	TP_ARGS(se));
 
+DECLARE_TRACE(sched_cpu_capacity_tp,
+	TP_PROTO(struct rq *rq),
+	TP_ARGS(rq));
+
 DECLARE_TRACE(sched_overutilized_tp,
 	TP_PROTO(struct root_domain *rd, bool overutilized),
 	TP_ARGS(rd, overutilized));
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index dd32d859ab40..3dc415f58bd7 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -36,6 +36,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_rt_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_dl_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_irq_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_se_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(sched_cpu_capacity_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_overutilized_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_cfs_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_se_tp);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index cec6cf9b2bb3..aa4c6227cd6d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -8108,6 +8108,8 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu)
 		capacity = 1;
 
 	cpu_rq(cpu)->cpu_capacity = capacity;
+	trace_sched_cpu_capacity_tp(cpu_rq(cpu));
+
 	sdg->sgc->capacity = capacity;
 	sdg->sgc->min_capacity = capacity;
 	sdg->sgc->max_capacity = capacity;
@@ -11321,6 +11323,18 @@ int sched_trace_rq_cpu(struct rq *rq)
 }
 EXPORT_SYMBOL_GPL(sched_trace_rq_cpu);
 
+int sched_trace_rq_cpu_capacity(struct rq *rq)
+{
+	return rq ?
+#ifdef CONFIG_SMP
+		rq->cpu_capacity
+#else
+		SCHED_CAPACITY_SCALE
+#endif
+		: -1;
+}
+EXPORT_SYMBOL_GPL(sched_trace_rq_cpu_capacity);
+
 const struct cpumask *sched_trace_rd_span(struct root_domain *rd)
 {
 #ifdef CONFIG_SMP
-- 
cgit v1.2.3


From 8e1b3884eed7d96d4f1210b668611ee6a1803ea5 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Thu, 1 Oct 2020 17:12:50 +0000
Subject: net: remove NETDEV_HW_ADDR_T_SLAVE

NETDEV_HW_ADDR_T_SLAVE is not used anymore, remove it.

Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 28cfa53daf72..0c79d9e56a5e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -212,9 +212,8 @@ struct netdev_hw_addr {
 	unsigned char		type;
 #define NETDEV_HW_ADDR_T_LAN		1
 #define NETDEV_HW_ADDR_T_SAN		2
-#define NETDEV_HW_ADDR_T_SLAVE		3
-#define NETDEV_HW_ADDR_T_UNICAST	4
-#define NETDEV_HW_ADDR_T_MULTICAST	5
+#define NETDEV_HW_ADDR_T_UNICAST	3
+#define NETDEV_HW_ADDR_T_MULTICAST	4
 	bool			global_use;
 	int			sync_cnt;
 	int			refcount;
-- 
cgit v1.2.3


From 19fbcb36a39eefbe8912a13ccc02e937b1c418d6 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Sat, 3 Oct 2020 00:44:28 +0200
Subject: net/sched: act_vlan: Add {POP,PUSH}_ETH actions

Implement TCA_VLAN_ACT_POP_ETH and TCA_VLAN_ACT_PUSH_ETH, to
respectively pop and push a base Ethernet header at the beginning of a
frame.

POP_ETH is just a matter of pulling ETH_HLEN bytes. VLAN tags, if any,
must be stripped before calling POP_ETH.

PUSH_ETH is restricted to skbs with no mac_header, and only the MAC
addresses can be configured. The Ethertype is automatically set from
skb->protocol. These restrictions ensure that all skb's fields remain
consistent, so that this action can't confuse other part of the
networking stack (like GSO).

Since openvswitch already had these actions, consolidate the code in
skbuff.c (like for vlan and mpls push/pop).

Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h              |  3 ++
 include/net/tc_act/tc_vlan.h        |  2 ++
 include/uapi/linux/tc_act/tc_vlan.h |  4 +++
 net/core/skbuff.c                   | 67 +++++++++++++++++++++++++++++++++++++
 net/openvswitch/actions.c           | 28 ++++++----------
 net/sched/act_vlan.c                | 40 ++++++++++++++++++++++
 6 files changed, 126 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 3d0cf3722bb4..42131e325e27 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3573,6 +3573,9 @@ int skb_ensure_writable(struct sk_buff *skb, int write_len);
 int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci);
 int skb_vlan_pop(struct sk_buff *skb);
 int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci);
+int skb_eth_pop(struct sk_buff *skb);
+int skb_eth_push(struct sk_buff *skb, const unsigned char *dst,
+		 const unsigned char *src);
 int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto,
 		  int mac_len, bool ethernet);
 int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len,
diff --git a/include/net/tc_act/tc_vlan.h b/include/net/tc_act/tc_vlan.h
index 4e2502408c31..f051046ba034 100644
--- a/include/net/tc_act/tc_vlan.h
+++ b/include/net/tc_act/tc_vlan.h
@@ -11,6 +11,8 @@
 
 struct tcf_vlan_params {
 	int               tcfv_action;
+	unsigned char     tcfv_push_dst[ETH_ALEN];
+	unsigned char     tcfv_push_src[ETH_ALEN];
 	u16               tcfv_push_vid;
 	__be16            tcfv_push_proto;
 	u8                tcfv_push_prio;
diff --git a/include/uapi/linux/tc_act/tc_vlan.h b/include/uapi/linux/tc_act/tc_vlan.h
index 168995b54a70..5b306fe815cc 100644
--- a/include/uapi/linux/tc_act/tc_vlan.h
+++ b/include/uapi/linux/tc_act/tc_vlan.h
@@ -16,6 +16,8 @@
 #define TCA_VLAN_ACT_POP	1
 #define TCA_VLAN_ACT_PUSH	2
 #define TCA_VLAN_ACT_MODIFY	3
+#define TCA_VLAN_ACT_POP_ETH	4
+#define TCA_VLAN_ACT_PUSH_ETH	5
 
 struct tc_vlan {
 	tc_gen;
@@ -30,6 +32,8 @@ enum {
 	TCA_VLAN_PUSH_VLAN_PROTOCOL,
 	TCA_VLAN_PAD,
 	TCA_VLAN_PUSH_VLAN_PRIORITY,
+	TCA_VLAN_PUSH_ETH_DST,
+	TCA_VLAN_PUSH_ETH_SRC,
 	__TCA_VLAN_MAX,
 };
 #define TCA_VLAN_MAX (__TCA_VLAN_MAX - 1)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index e0774471f56d..75b043accddb 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5558,6 +5558,73 @@ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci)
 }
 EXPORT_SYMBOL(skb_vlan_push);
 
+/**
+ * skb_eth_pop() - Drop the Ethernet header at the head of a packet
+ *
+ * @skb: Socket buffer to modify
+ *
+ * Drop the Ethernet header of @skb.
+ *
+ * Expects that skb->data points to the mac header and that no VLAN tags are
+ * present.
+ *
+ * Returns 0 on success, -errno otherwise.
+ */
+int skb_eth_pop(struct sk_buff *skb)
+{
+	if (!pskb_may_pull(skb, ETH_HLEN) || skb_vlan_tagged(skb) ||
+	    skb_network_offset(skb) < ETH_HLEN)
+		return -EPROTO;
+
+	skb_pull_rcsum(skb, ETH_HLEN);
+	skb_reset_mac_header(skb);
+	skb_reset_mac_len(skb);
+
+	return 0;
+}
+EXPORT_SYMBOL(skb_eth_pop);
+
+/**
+ * skb_eth_push() - Add a new Ethernet header at the head of a packet
+ *
+ * @skb: Socket buffer to modify
+ * @dst: Destination MAC address of the new header
+ * @src: Source MAC address of the new header
+ *
+ * Prepend @skb with a new Ethernet header.
+ *
+ * Expects that skb->data points to the mac header, which must be empty.
+ *
+ * Returns 0 on success, -errno otherwise.
+ */
+int skb_eth_push(struct sk_buff *skb, const unsigned char *dst,
+		 const unsigned char *src)
+{
+	struct ethhdr *eth;
+	int err;
+
+	if (skb_network_offset(skb) || skb_vlan_tag_present(skb))
+		return -EPROTO;
+
+	err = skb_cow_head(skb, sizeof(*eth));
+	if (err < 0)
+		return err;
+
+	skb_push(skb, sizeof(*eth));
+	skb_reset_mac_header(skb);
+	skb_reset_mac_len(skb);
+
+	eth = eth_hdr(skb);
+	ether_addr_copy(eth->h_dest, dst);
+	ether_addr_copy(eth->h_source, src);
+	eth->h_proto = skb->protocol;
+
+	skb_postpush_rcsum(skb, eth, sizeof(*eth));
+
+	return 0;
+}
+EXPORT_SYMBOL(skb_eth_push);
+
 /* Update the ethertype of hdr and the skb csum value if required. */
 static void skb_mod_eth_type(struct sk_buff *skb, struct ethhdr *hdr,
 			     __be16 ethertype)
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 855f2c155956..b87bfc82f44f 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -277,9 +277,11 @@ static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *flow_key,
  */
 static int pop_eth(struct sk_buff *skb, struct sw_flow_key *key)
 {
-	skb_pull_rcsum(skb, ETH_HLEN);
-	skb_reset_mac_header(skb);
-	skb_reset_mac_len(skb);
+	int err;
+
+	err = skb_eth_pop(skb);
+	if (err)
+		return err;
 
 	/* safe right before invalidate_flow_key */
 	key->mac_proto = MAC_PROTO_NONE;
@@ -290,22 +292,12 @@ static int pop_eth(struct sk_buff *skb, struct sw_flow_key *key)
 static int push_eth(struct sk_buff *skb, struct sw_flow_key *key,
 		    const struct ovs_action_push_eth *ethh)
 {
-	struct ethhdr *hdr;
-
-	/* Add the new Ethernet header */
-	if (skb_cow_head(skb, ETH_HLEN) < 0)
-		return -ENOMEM;
-
-	skb_push(skb, ETH_HLEN);
-	skb_reset_mac_header(skb);
-	skb_reset_mac_len(skb);
-
-	hdr = eth_hdr(skb);
-	ether_addr_copy(hdr->h_source, ethh->addresses.eth_src);
-	ether_addr_copy(hdr->h_dest, ethh->addresses.eth_dst);
-	hdr->h_proto = skb->protocol;
+	int err;
 
-	skb_postpush_rcsum(skb, hdr, ETH_HLEN);
+	err = skb_eth_push(skb, ethh->addresses.eth_dst,
+			   ethh->addresses.eth_src);
+	if (err)
+		return err;
 
 	/* safe right before invalidate_flow_key */
 	key->mac_proto = MAC_PROTO_ETHERNET;
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index a5ff9f68ab02..8758bd2a78fa 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -77,6 +77,16 @@ static int tcf_vlan_act(struct sk_buff *skb, const struct tc_action *a,
 		/* put updated tci as hwaccel tag */
 		__vlan_hwaccel_put_tag(skb, p->tcfv_push_proto, tci);
 		break;
+	case TCA_VLAN_ACT_POP_ETH:
+		err = skb_eth_pop(skb);
+		if (err)
+			goto drop;
+		break;
+	case TCA_VLAN_ACT_PUSH_ETH:
+		err = skb_eth_push(skb, p->tcfv_push_dst, p->tcfv_push_src);
+		if (err)
+			goto drop;
+		break;
 	default:
 		BUG();
 	}
@@ -93,10 +103,13 @@ drop:
 }
 
 static const struct nla_policy vlan_policy[TCA_VLAN_MAX + 1] = {
+	[TCA_VLAN_UNSPEC]		= { .strict_start_type = TCA_VLAN_PUSH_ETH_DST },
 	[TCA_VLAN_PARMS]		= { .len = sizeof(struct tc_vlan) },
 	[TCA_VLAN_PUSH_VLAN_ID]		= { .type = NLA_U16 },
 	[TCA_VLAN_PUSH_VLAN_PROTOCOL]	= { .type = NLA_U16 },
 	[TCA_VLAN_PUSH_VLAN_PRIORITY]	= { .type = NLA_U8 },
+	[TCA_VLAN_PUSH_ETH_DST]		= NLA_POLICY_ETH_ADDR,
+	[TCA_VLAN_PUSH_ETH_SRC]		= NLA_POLICY_ETH_ADDR,
 };
 
 static int tcf_vlan_init(struct net *net, struct nlattr *nla,
@@ -179,6 +192,17 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 		if (tb[TCA_VLAN_PUSH_VLAN_PRIORITY])
 			push_prio = nla_get_u8(tb[TCA_VLAN_PUSH_VLAN_PRIORITY]);
 		break;
+	case TCA_VLAN_ACT_POP_ETH:
+		break;
+	case TCA_VLAN_ACT_PUSH_ETH:
+		if (!tb[TCA_VLAN_PUSH_ETH_DST] || !tb[TCA_VLAN_PUSH_ETH_SRC]) {
+			if (exists)
+				tcf_idr_release(*a, bind);
+			else
+				tcf_idr_cleanup(tn, index);
+			return -EINVAL;
+		}
+		break;
 	default:
 		if (exists)
 			tcf_idr_release(*a, bind);
@@ -219,6 +243,13 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 	p->tcfv_push_prio = push_prio;
 	p->tcfv_push_proto = push_proto;
 
+	if (action == TCA_VLAN_ACT_PUSH_ETH) {
+		nla_memcpy(&p->tcfv_push_dst, tb[TCA_VLAN_PUSH_ETH_DST],
+			   ETH_ALEN);
+		nla_memcpy(&p->tcfv_push_src, tb[TCA_VLAN_PUSH_ETH_SRC],
+			   ETH_ALEN);
+	}
+
 	spin_lock_bh(&v->tcf_lock);
 	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
 	p = rcu_replace_pointer(v->vlan_p, p, lockdep_is_held(&v->tcf_lock));
@@ -279,6 +310,15 @@ static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a,
 					      p->tcfv_push_prio))))
 		goto nla_put_failure;
 
+	if (p->tcfv_action == TCA_VLAN_ACT_PUSH_ETH) {
+		if (nla_put(skb, TCA_VLAN_PUSH_ETH_DST, ETH_ALEN,
+			    p->tcfv_push_dst))
+			goto nla_put_failure;
+		if (nla_put(skb, TCA_VLAN_PUSH_ETH_SRC, ETH_ALEN,
+			    p->tcfv_push_src))
+			goto nla_put_failure;
+	}
+
 	tcf_tm_dump(&t, &v->tcf_tm);
 	if (nla_put_64bit(skb, TCA_VLAN_TM, sizeof(t), &t, TCA_VLAN_PAD))
 		goto nla_put_failure;
-- 
cgit v1.2.3


From 24ce66c04a06a678f156cf575128246f3d214b4a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 7 Sep 2020 07:58:18 +0200
Subject: uaccess: provide a generic TASK_SIZE_MAX definition

Define TASK_SIZE_MAX as TASK_SIZE if not otherwise defined.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 include/linux/uaccess.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 70073c802b48..d0e43761c708 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -31,6 +31,10 @@ typedef struct {
 	/* empty dummy */
 } mm_segment_t;
 
+#ifndef TASK_SIZE_MAX
+#define TASK_SIZE_MAX			TASK_SIZE
+#endif
+
 #define uaccess_kernel()		(false)
 #define user_addr_max()			(TASK_SIZE_MAX)
 
-- 
cgit v1.2.3


From 8438f5211479e4b8433f641634362264bc3bbd9e Mon Sep 17 00:00:00 2001
From: Tingwei Zhang <tingwei@codeaurora.org>
Date: Mon, 5 Oct 2020 10:13:13 +0300
Subject: tracing: Add flag to control different traces

More traces like event trace or trace marker will be supported.
Add flag for difference traces, so that they can be controlled
separately. Move current function trace to it's own flag
instead of global ftrace enable flag.

Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Reviewed-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: Tingwei Zhang <tingwei@codeaurora.org>
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Link: https://lore.kernel.org/r/20201005071319.78508-3-alexander.shishkin@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/trace.h |  5 +++++
 kernel/trace/trace.c  | 36 +++++++++++++++++++-----------------
 2 files changed, 24 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/trace.h b/include/linux/trace.h
index 36d255d66f88..c115a5d2269f 100644
--- a/include/linux/trace.h
+++ b/include/linux/trace.h
@@ -3,6 +3,9 @@
 #define _LINUX_TRACE_H
 
 #ifdef CONFIG_TRACING
+
+#define TRACE_EXPORT_FUNCTION	BIT(0)
+
 /*
  * The trace export - an export of Ftrace output. The trace_export
  * can process traces and export them to a registered destination as
@@ -15,10 +18,12 @@
  * next		- pointer to the next trace_export
  * write	- copy traces which have been delt with ->commit() to
  *		  the destination
+ * flags	- which ftrace to be exported
  */
 struct trace_export {
 	struct trace_export __rcu	*next;
 	void (*write)(struct trace_export *, const void *, unsigned int);
+	int flags;
 };
 
 int register_ftrace_export(struct trace_export *export);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index f40d850ebabc..3ca121ad8728 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2744,33 +2744,37 @@ trace_buffer_unlock_commit_nostack(struct trace_buffer *buffer,
 
 static void
 trace_process_export(struct trace_export *export,
-	       struct ring_buffer_event *event)
+	       struct ring_buffer_event *event, int flag)
 {
 	struct trace_entry *entry;
 	unsigned int size = 0;
 
-	entry = ring_buffer_event_data(event);
-	size = ring_buffer_event_length(event);
-	export->write(export, entry, size);
+	if (export->flags & flag) {
+		entry = ring_buffer_event_data(event);
+		size = ring_buffer_event_length(event);
+		export->write(export, entry, size);
+	}
 }
 
 static DEFINE_MUTEX(ftrace_export_lock);
 
 static struct trace_export __rcu *ftrace_exports_list __read_mostly;
 
-static DEFINE_STATIC_KEY_FALSE(ftrace_exports_enabled);
+static DEFINE_STATIC_KEY_FALSE(trace_function_exports_enabled);
 
-static inline void ftrace_exports_enable(void)
+static inline void ftrace_exports_enable(struct trace_export *export)
 {
-	static_branch_enable(&ftrace_exports_enabled);
+	if (export->flags & TRACE_EXPORT_FUNCTION)
+		static_branch_inc(&trace_function_exports_enabled);
 }
 
-static inline void ftrace_exports_disable(void)
+static inline void ftrace_exports_disable(struct trace_export *export)
 {
-	static_branch_disable(&ftrace_exports_enabled);
+	if (export->flags & TRACE_EXPORT_FUNCTION)
+		static_branch_dec(&trace_function_exports_enabled);
 }
 
-static void ftrace_exports(struct ring_buffer_event *event)
+static void ftrace_exports(struct ring_buffer_event *event, int flag)
 {
 	struct trace_export *export;
 
@@ -2778,7 +2782,7 @@ static void ftrace_exports(struct ring_buffer_event *event)
 
 	export = rcu_dereference_raw_check(ftrace_exports_list);
 	while (export) {
-		trace_process_export(export, event);
+		trace_process_export(export, event, flag);
 		export = rcu_dereference_raw_check(export->next);
 	}
 
@@ -2818,8 +2822,7 @@ rm_trace_export(struct trace_export **list, struct trace_export *export)
 static inline void
 add_ftrace_export(struct trace_export **list, struct trace_export *export)
 {
-	if (*list == NULL)
-		ftrace_exports_enable();
+	ftrace_exports_enable(export);
 
 	add_trace_export(list, export);
 }
@@ -2830,8 +2833,7 @@ rm_ftrace_export(struct trace_export **list, struct trace_export *export)
 	int ret;
 
 	ret = rm_trace_export(list, export);
-	if (*list == NULL)
-		ftrace_exports_disable();
+	ftrace_exports_disable(export);
 
 	return ret;
 }
@@ -2884,8 +2886,8 @@ trace_function(struct trace_array *tr,
 	entry->parent_ip		= parent_ip;
 
 	if (!call_filter_check_discard(call, entry, buffer, event)) {
-		if (static_branch_unlikely(&ftrace_exports_enabled))
-			ftrace_exports(event);
+		if (static_branch_unlikely(&trace_function_exports_enabled))
+			ftrace_exports(event, TRACE_EXPORT_FUNCTION);
 		__buffer_unlock_commit(buffer, event);
 	}
 }
-- 
cgit v1.2.3


From 8ab7a2b7055c88c3da5e4684dfa015c6a8987c28 Mon Sep 17 00:00:00 2001
From: Tingwei Zhang <tingwei@codeaurora.org>
Date: Mon, 5 Oct 2020 10:13:14 +0300
Subject: tracing: Add trace_export support for event trace

Only function traces can be exported to other destinations currently.
This patch exports event trace as well. Move trace export related
function to the beginning of file so other trace can call
trace_process_export() to export.

Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Reviewed-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: Tingwei Zhang <tingwei@codeaurora.org>
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Link: https://lore.kernel.org/r/20201005071319.78508-4-alexander.shishkin@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/trace.h |   1 +
 kernel/trace/trace.c  | 259 ++++++++++++++++++++++++++------------------------
 2 files changed, 135 insertions(+), 125 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/trace.h b/include/linux/trace.h
index c115a5d2269f..86033d214972 100644
--- a/include/linux/trace.h
+++ b/include/linux/trace.h
@@ -5,6 +5,7 @@
 #ifdef CONFIG_TRACING
 
 #define TRACE_EXPORT_FUNCTION	BIT(0)
+#define TRACE_EXPORT_EVENT	BIT(1)
 
 /*
  * The trace export - an export of Ftrace output. The trace_export
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 3ca121ad8728..a40ee413123c 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -251,6 +251,138 @@ unsigned long long ns2usecs(u64 nsec)
 	return nsec;
 }
 
+static void
+trace_process_export(struct trace_export *export,
+	       struct ring_buffer_event *event, int flag)
+{
+	struct trace_entry *entry;
+	unsigned int size = 0;
+
+	if (export->flags & flag) {
+		entry = ring_buffer_event_data(event);
+		size = ring_buffer_event_length(event);
+		export->write(export, entry, size);
+	}
+}
+
+static DEFINE_MUTEX(ftrace_export_lock);
+
+static struct trace_export __rcu *ftrace_exports_list __read_mostly;
+
+static DEFINE_STATIC_KEY_FALSE(trace_function_exports_enabled);
+static DEFINE_STATIC_KEY_FALSE(trace_event_exports_enabled);
+
+static inline void ftrace_exports_enable(struct trace_export *export)
+{
+	if (export->flags & TRACE_EXPORT_FUNCTION)
+		static_branch_inc(&trace_function_exports_enabled);
+
+	if (export->flags & TRACE_EXPORT_EVENT)
+		static_branch_inc(&trace_event_exports_enabled);
+}
+
+static inline void ftrace_exports_disable(struct trace_export *export)
+{
+	if (export->flags & TRACE_EXPORT_FUNCTION)
+		static_branch_dec(&trace_function_exports_enabled);
+
+	if (export->flags & TRACE_EXPORT_EVENT)
+		static_branch_dec(&trace_event_exports_enabled);
+}
+
+static void ftrace_exports(struct ring_buffer_event *event, int flag)
+{
+	struct trace_export *export;
+
+	preempt_disable_notrace();
+
+	export = rcu_dereference_raw_check(ftrace_exports_list);
+	while (export) {
+		trace_process_export(export, event, flag);
+		export = rcu_dereference_raw_check(export->next);
+	}
+
+	preempt_enable_notrace();
+}
+
+static inline void
+add_trace_export(struct trace_export **list, struct trace_export *export)
+{
+	rcu_assign_pointer(export->next, *list);
+	/*
+	 * We are entering export into the list but another
+	 * CPU might be walking that list. We need to make sure
+	 * the export->next pointer is valid before another CPU sees
+	 * the export pointer included into the list.
+	 */
+	rcu_assign_pointer(*list, export);
+}
+
+static inline int
+rm_trace_export(struct trace_export **list, struct trace_export *export)
+{
+	struct trace_export **p;
+
+	for (p = list; *p != NULL; p = &(*p)->next)
+		if (*p == export)
+			break;
+
+	if (*p != export)
+		return -1;
+
+	rcu_assign_pointer(*p, (*p)->next);
+
+	return 0;
+}
+
+static inline void
+add_ftrace_export(struct trace_export **list, struct trace_export *export)
+{
+	ftrace_exports_enable(export);
+
+	add_trace_export(list, export);
+}
+
+static inline int
+rm_ftrace_export(struct trace_export **list, struct trace_export *export)
+{
+	int ret;
+
+	ret = rm_trace_export(list, export);
+	ftrace_exports_disable(export);
+
+	return ret;
+}
+
+int register_ftrace_export(struct trace_export *export)
+{
+	if (WARN_ON_ONCE(!export->write))
+		return -1;
+
+	mutex_lock(&ftrace_export_lock);
+
+	add_ftrace_export(&ftrace_exports_list, export);
+
+	mutex_unlock(&ftrace_export_lock);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(register_ftrace_export);
+
+int unregister_ftrace_export(struct trace_export *export)
+{
+	int ret;
+
+	mutex_lock(&ftrace_export_lock);
+
+	ret = rm_ftrace_export(&ftrace_exports_list, export);
+
+	mutex_unlock(&ftrace_export_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(unregister_ftrace_export);
+
 /* trace_flags holds trace_options default values */
 #define TRACE_DEFAULT_FLAGS						\
 	(FUNCTION_DEFAULT_FLAGS |					\
@@ -2699,6 +2831,8 @@ void trace_event_buffer_commit(struct trace_event_buffer *fbuffer)
 	if (static_key_false(&tracepoint_printk_key.key))
 		output_printk(fbuffer);
 
+	if (static_branch_unlikely(&trace_event_exports_enabled))
+		ftrace_exports(fbuffer->event, TRACE_EXPORT_EVENT);
 	event_trigger_unlock_commit_regs(fbuffer->trace_file, fbuffer->buffer,
 				    fbuffer->event, fbuffer->entry,
 				    fbuffer->flags, fbuffer->pc, fbuffer->regs);
@@ -2742,131 +2876,6 @@ trace_buffer_unlock_commit_nostack(struct trace_buffer *buffer,
 	__buffer_unlock_commit(buffer, event);
 }
 
-static void
-trace_process_export(struct trace_export *export,
-	       struct ring_buffer_event *event, int flag)
-{
-	struct trace_entry *entry;
-	unsigned int size = 0;
-
-	if (export->flags & flag) {
-		entry = ring_buffer_event_data(event);
-		size = ring_buffer_event_length(event);
-		export->write(export, entry, size);
-	}
-}
-
-static DEFINE_MUTEX(ftrace_export_lock);
-
-static struct trace_export __rcu *ftrace_exports_list __read_mostly;
-
-static DEFINE_STATIC_KEY_FALSE(trace_function_exports_enabled);
-
-static inline void ftrace_exports_enable(struct trace_export *export)
-{
-	if (export->flags & TRACE_EXPORT_FUNCTION)
-		static_branch_inc(&trace_function_exports_enabled);
-}
-
-static inline void ftrace_exports_disable(struct trace_export *export)
-{
-	if (export->flags & TRACE_EXPORT_FUNCTION)
-		static_branch_dec(&trace_function_exports_enabled);
-}
-
-static void ftrace_exports(struct ring_buffer_event *event, int flag)
-{
-	struct trace_export *export;
-
-	preempt_disable_notrace();
-
-	export = rcu_dereference_raw_check(ftrace_exports_list);
-	while (export) {
-		trace_process_export(export, event, flag);
-		export = rcu_dereference_raw_check(export->next);
-	}
-
-	preempt_enable_notrace();
-}
-
-static inline void
-add_trace_export(struct trace_export **list, struct trace_export *export)
-{
-	rcu_assign_pointer(export->next, *list);
-	/*
-	 * We are entering export into the list but another
-	 * CPU might be walking that list. We need to make sure
-	 * the export->next pointer is valid before another CPU sees
-	 * the export pointer included into the list.
-	 */
-	rcu_assign_pointer(*list, export);
-}
-
-static inline int
-rm_trace_export(struct trace_export **list, struct trace_export *export)
-{
-	struct trace_export **p;
-
-	for (p = list; *p != NULL; p = &(*p)->next)
-		if (*p == export)
-			break;
-
-	if (*p != export)
-		return -1;
-
-	rcu_assign_pointer(*p, (*p)->next);
-
-	return 0;
-}
-
-static inline void
-add_ftrace_export(struct trace_export **list, struct trace_export *export)
-{
-	ftrace_exports_enable(export);
-
-	add_trace_export(list, export);
-}
-
-static inline int
-rm_ftrace_export(struct trace_export **list, struct trace_export *export)
-{
-	int ret;
-
-	ret = rm_trace_export(list, export);
-	ftrace_exports_disable(export);
-
-	return ret;
-}
-
-int register_ftrace_export(struct trace_export *export)
-{
-	if (WARN_ON_ONCE(!export->write))
-		return -1;
-
-	mutex_lock(&ftrace_export_lock);
-
-	add_ftrace_export(&ftrace_exports_list, export);
-
-	mutex_unlock(&ftrace_export_lock);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(register_ftrace_export);
-
-int unregister_ftrace_export(struct trace_export *export)
-{
-	int ret;
-
-	mutex_lock(&ftrace_export_lock);
-
-	ret = rm_ftrace_export(&ftrace_exports_list, export);
-
-	mutex_unlock(&ftrace_export_lock);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(unregister_ftrace_export);
-
 void
 trace_function(struct trace_array *tr,
 	       unsigned long ip, unsigned long parent_ip, unsigned long flags,
-- 
cgit v1.2.3


From 458999c6f67b0ffcc704a4892041dd700adf7d83 Mon Sep 17 00:00:00 2001
From: Tingwei Zhang <tingwei@codeaurora.org>
Date: Mon, 5 Oct 2020 10:13:15 +0300
Subject: tracing: Add trace_export support for trace_marker

Add the support to route trace_marker buffer to other destination
via trace_export.

Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Reviewed-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: Tingwei Zhang <tingwei@codeaurora.org>
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Link: https://lore.kernel.org/r/20201005071319.78508-5-alexander.shishkin@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/trace.h | 1 +
 kernel/trace/trace.c  | 9 +++++++++
 2 files changed, 10 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/trace.h b/include/linux/trace.h
index 86033d214972..886a4ffd9d45 100644
--- a/include/linux/trace.h
+++ b/include/linux/trace.h
@@ -6,6 +6,7 @@
 
 #define TRACE_EXPORT_FUNCTION	BIT(0)
 #define TRACE_EXPORT_EVENT	BIT(1)
+#define TRACE_EXPORT_MARKER	BIT(2)
 
 /*
  * The trace export - an export of Ftrace output. The trace_export
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index a40ee413123c..6048fba2f590 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -271,6 +271,7 @@ static struct trace_export __rcu *ftrace_exports_list __read_mostly;
 
 static DEFINE_STATIC_KEY_FALSE(trace_function_exports_enabled);
 static DEFINE_STATIC_KEY_FALSE(trace_event_exports_enabled);
+static DEFINE_STATIC_KEY_FALSE(trace_marker_exports_enabled);
 
 static inline void ftrace_exports_enable(struct trace_export *export)
 {
@@ -279,6 +280,9 @@ static inline void ftrace_exports_enable(struct trace_export *export)
 
 	if (export->flags & TRACE_EXPORT_EVENT)
 		static_branch_inc(&trace_event_exports_enabled);
+
+	if (export->flags & TRACE_EXPORT_MARKER)
+		static_branch_inc(&trace_marker_exports_enabled);
 }
 
 static inline void ftrace_exports_disable(struct trace_export *export)
@@ -288,6 +292,9 @@ static inline void ftrace_exports_disable(struct trace_export *export)
 
 	if (export->flags & TRACE_EXPORT_EVENT)
 		static_branch_dec(&trace_event_exports_enabled);
+
+	if (export->flags & TRACE_EXPORT_MARKER)
+		static_branch_dec(&trace_marker_exports_enabled);
 }
 
 static void ftrace_exports(struct ring_buffer_event *event, int flag)
@@ -6687,6 +6694,8 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	} else
 		entry->buf[cnt] = '\0';
 
+	if (static_branch_unlikely(&trace_marker_exports_enabled))
+		ftrace_exports(event, TRACE_EXPORT_MARKER);
 	__buffer_unlock_commit(buffer, event);
 
 	if (tt)
-- 
cgit v1.2.3


From 07f8569fbe44f35e53c7a5946fbb348432c68377 Mon Sep 17 00:00:00 2001
From: Rikard Falkeborn <rikard.falkeborn@gmail.com>
Date: Sun, 4 Oct 2020 21:32:00 +0200
Subject: w1: Constify struct w1_family_ops

The fops field in the w1_family struct is never modified. Make it const
to indicate that. Constifying the pointer makes it possible for drivers
to declare static w1_family_ops structs const, which in turn will allow
the compiler to put it in read-only memory.

Reviewed-by: Sebastian Reichel <sebastian.reichel@collabora.com>
Signed-off-by: Rikard Falkeborn <rikard.falkeborn@gmail.com>
Link: https://lore.kernel.org/r/20201004193202.4044-2-rikard.falkeborn@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/w1/w1.c    | 2 +-
 include/linux/w1.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/w1/w1.c b/drivers/w1/w1.c
index e58c7592008d..6bd64bcb6316 100644
--- a/drivers/w1/w1.c
+++ b/drivers/w1/w1.c
@@ -613,7 +613,7 @@ end:
 
 static int w1_family_notify(unsigned long action, struct w1_slave *sl)
 {
-	struct w1_family_ops *fops;
+	const struct w1_family_ops *fops;
 	int err;
 
 	fops = sl->family->fops;
diff --git a/include/linux/w1.h b/include/linux/w1.h
index cebf3464bc03..949d3b10e531 100644
--- a/include/linux/w1.h
+++ b/include/linux/w1.h
@@ -269,7 +269,7 @@ struct w1_family {
 	struct list_head	family_entry;
 	u8			fid;
 
-	struct w1_family_ops	*fops;
+	const struct w1_family_ops *fops;
 
 	const struct of_device_id *of_match_table;
 
-- 
cgit v1.2.3


From c307459b9d1fcb8bbf3ea5a4162979532322ef77 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 2 Oct 2020 10:38:13 -0700
Subject: fs/kernel_read_file: Remove FIRMWARE_PREALLOC_BUFFER enum

FIRMWARE_PREALLOC_BUFFER is a "how", not a "what", and confuses the LSMs
that are interested in filtering between types of things. The "how"
should be an internal detail made uninteresting to the LSMs.

Fixes: a098ecd2fa7d ("firmware: support loading into a pre-allocated buffer")
Fixes: fd90bc559bfb ("ima: based on policy verify firmware signatures (pre-allocated buffer)")
Fixes: 4f0496d8ffa3 ("ima: based on policy warn about loading firmware (pre-allocated buffer)")
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Mimi Zohar <zohar@linux.ibm.com>
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Acked-by: Scott Branden <scott.branden@broadcom.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20201002173828.2099543-2-keescook@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/firmware_loader/main.c | 5 ++---
 fs/exec.c                           | 7 ++++---
 include/linux/fs.h                  | 2 +-
 kernel/module.c                     | 2 +-
 security/integrity/digsig.c         | 2 +-
 security/integrity/ima/ima_fs.c     | 2 +-
 security/integrity/ima/ima_main.c   | 6 ++----
 7 files changed, 12 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c
index 63b9714a0154..b0ec2721f55d 100644
--- a/drivers/base/firmware_loader/main.c
+++ b/drivers/base/firmware_loader/main.c
@@ -470,14 +470,12 @@ fw_get_filesystem_firmware(struct device *device, struct fw_priv *fw_priv,
 	int i, len;
 	int rc = -ENOENT;
 	char *path;
-	enum kernel_read_file_id id = READING_FIRMWARE;
 	size_t msize = INT_MAX;
 	void *buffer = NULL;
 
 	/* Already populated data member means we're loading into a buffer */
 	if (!decompress && fw_priv->data) {
 		buffer = fw_priv->data;
-		id = READING_FIRMWARE_PREALLOC_BUFFER;
 		msize = fw_priv->allocated_size;
 	}
 
@@ -501,7 +499,8 @@ fw_get_filesystem_firmware(struct device *device, struct fw_priv *fw_priv,
 
 		/* load firmware files from the mount namespace of init */
 		rc = kernel_read_file_from_path_initns(path, &buffer,
-						       &size, msize, id);
+						       &size, msize,
+						       READING_FIRMWARE);
 		if (rc) {
 			if (rc != -ENOENT)
 				dev_warn(device, "loading %s failed with error %d\n",
diff --git a/fs/exec.c b/fs/exec.c
index a91003e28eaa..9233cd50dc4c 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -954,6 +954,7 @@ int kernel_read_file(struct file *file, void **buf, loff_t *size,
 {
 	loff_t i_size, pos;
 	ssize_t bytes = 0;
+	void *allocated = NULL;
 	int ret;
 
 	if (!S_ISREG(file_inode(file)->i_mode) || max_size < 0)
@@ -977,8 +978,8 @@ int kernel_read_file(struct file *file, void **buf, loff_t *size,
 		goto out;
 	}
 
-	if (id != READING_FIRMWARE_PREALLOC_BUFFER)
-		*buf = vmalloc(i_size);
+	if (!*buf)
+		*buf = allocated = vmalloc(i_size);
 	if (!*buf) {
 		ret = -ENOMEM;
 		goto out;
@@ -1007,7 +1008,7 @@ int kernel_read_file(struct file *file, void **buf, loff_t *size,
 
 out_free:
 	if (ret < 0) {
-		if (id != READING_FIRMWARE_PREALLOC_BUFFER) {
+		if (allocated) {
 			vfree(*buf);
 			*buf = NULL;
 		}
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7519ae003a08..7336e22d0c5d 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2858,10 +2858,10 @@ static inline void i_readcount_inc(struct inode *inode)
 #endif
 extern int do_pipe_flags(int *, int);
 
+/* This is a list of *what* is being read, not *how*. */
 #define __kernel_read_file_id(id) \
 	id(UNKNOWN, unknown)		\
 	id(FIRMWARE, firmware)		\
-	id(FIRMWARE_PREALLOC_BUFFER, firmware)	\
 	id(FIRMWARE_EFI_EMBEDDED, firmware)	\
 	id(MODULE, kernel-module)		\
 	id(KEXEC_IMAGE, kexec-image)		\
diff --git a/kernel/module.c b/kernel/module.c
index 1c5cff34d9f2..b2808acac46b 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -4035,7 +4035,7 @@ SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags)
 {
 	struct load_info info = { };
 	loff_t size;
-	void *hdr;
+	void *hdr = NULL;
 	int err;
 
 	err = may_init_module();
diff --git a/security/integrity/digsig.c b/security/integrity/digsig.c
index e9cbadade74b..ac02b7632353 100644
--- a/security/integrity/digsig.c
+++ b/security/integrity/digsig.c
@@ -169,7 +169,7 @@ int __init integrity_add_key(const unsigned int id, const void *data,
 
 int __init integrity_load_x509(const unsigned int id, const char *path)
 {
-	void *data;
+	void *data = NULL;
 	loff_t size;
 	int rc;
 	key_perm_t perm;
diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c
index e3fcad871861..15a44c5022f7 100644
--- a/security/integrity/ima/ima_fs.c
+++ b/security/integrity/ima/ima_fs.c
@@ -272,7 +272,7 @@ static const struct file_operations ima_ascii_measurements_ops = {
 
 static ssize_t ima_read_policy(char *path)
 {
-	void *data;
+	void *data = NULL;
 	char *datap;
 	loff_t size;
 	int rc, pathlen = strlen(path);
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index 8a91711ca79b..2f187784c5bc 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -611,19 +611,17 @@ void ima_post_path_mknod(struct dentry *dentry)
 int ima_read_file(struct file *file, enum kernel_read_file_id read_id)
 {
 	/*
-	 * READING_FIRMWARE_PREALLOC_BUFFER
-	 *
 	 * Do devices using pre-allocated memory run the risk of the
 	 * firmware being accessible to the device prior to the completion
 	 * of IMA's signature verification any more than when using two
-	 * buffers?
+	 * buffers? It may be desirable to include the buffer address
+	 * in this API and walk all the dma_map_single() mappings to check.
 	 */
 	return 0;
 }
 
 const int read_idmap[READING_MAX_ID] = {
 	[READING_FIRMWARE] = FIRMWARE_CHECK,
-	[READING_FIRMWARE_PREALLOC_BUFFER] = FIRMWARE_CHECK,
 	[READING_MODULE] = MODULE_CHECK,
 	[READING_KEXEC_IMAGE] = KEXEC_KERNEL_CHECK,
 	[READING_KEXEC_INITRAMFS] = KEXEC_INITRAMFS_CHECK,
-- 
cgit v1.2.3


From 06e67b849ab910a49a629445f43edb074153d0eb Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 2 Oct 2020 10:38:14 -0700
Subject: fs/kernel_read_file: Remove FIRMWARE_EFI_EMBEDDED enum

The "FIRMWARE_EFI_EMBEDDED" enum is a "where", not a "what". It
should not be distinguished separately from just "FIRMWARE", as this
confuses the LSMs about what is being loaded. Additionally, there was
no actual validation of the firmware contents happening.

Fixes: e4c2c0ff00ec ("firmware: Add new platform fallback mechanism and firmware_request_platform()")
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Acked-by: Scott Branden <scott.branden@broadcom.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20201002173828.2099543-3-keescook@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/firmware_loader/fallback_platform.c | 2 +-
 include/linux/fs.h                               | 3 +--
 2 files changed, 2 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/firmware_loader/fallback_platform.c b/drivers/base/firmware_loader/fallback_platform.c
index 685edb7dd05a..6958ab1a8059 100644
--- a/drivers/base/firmware_loader/fallback_platform.c
+++ b/drivers/base/firmware_loader/fallback_platform.c
@@ -17,7 +17,7 @@ int firmware_fallback_platform(struct fw_priv *fw_priv, u32 opt_flags)
 	if (!(opt_flags & FW_OPT_FALLBACK_PLATFORM))
 		return -ENOENT;
 
-	rc = security_kernel_load_data(LOADING_FIRMWARE_EFI_EMBEDDED);
+	rc = security_kernel_load_data(LOADING_FIRMWARE);
 	if (rc)
 		return rc;
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7336e22d0c5d..3fb7af12d033 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2858,11 +2858,10 @@ static inline void i_readcount_inc(struct inode *inode)
 #endif
 extern int do_pipe_flags(int *, int);
 
-/* This is a list of *what* is being read, not *how*. */
+/* This is a list of *what* is being read, not *how* nor *where*. */
 #define __kernel_read_file_id(id) \
 	id(UNKNOWN, unknown)		\
 	id(FIRMWARE, firmware)		\
-	id(FIRMWARE_EFI_EMBEDDED, firmware)	\
 	id(MODULE, kernel-module)		\
 	id(KEXEC_IMAGE, kexec-image)		\
 	id(KEXEC_INITRAMFS, kexec-initramfs)	\
-- 
cgit v1.2.3


From b89999d004931ab2e5123611ace7dab77328f8d6 Mon Sep 17 00:00:00 2001
From: Scott Branden <scott.branden@broadcom.com>
Date: Fri, 2 Oct 2020 10:38:15 -0700
Subject: fs/kernel_read_file: Split into separate include file

Move kernel_read_file* out of linux/fs.h to its own linux/kernel_read_file.h
include file. That header gets pulled in just about everywhere
and doesn't really need functions not related to the general fs interface.

Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Scott Branden <scott.branden@broadcom.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mimi Zohar <zohar@linux.ibm.com>
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: James Morris <jamorris@linux.microsoft.com>
Link: https://lore.kernel.org/r/20200706232309.12010-2-scott.branden@broadcom.com
Link: https://lore.kernel.org/r/20201002173828.2099543-4-keescook@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/firmware_loader/main.c |  1 +
 fs/exec.c                           |  1 +
 include/linux/fs.h                  | 38 ---------------------------
 include/linux/ima.h                 |  1 +
 include/linux/kernel_read_file.h    | 51 +++++++++++++++++++++++++++++++++++++
 include/linux/security.h            |  1 +
 kernel/kexec_file.c                 |  1 +
 kernel/module.c                     |  1 +
 security/integrity/digsig.c         |  1 +
 security/integrity/ima/ima_fs.c     |  1 +
 security/integrity/ima/ima_main.c   |  1 +
 security/integrity/ima/ima_policy.c |  1 +
 security/loadpin/loadpin.c          |  1 +
 security/security.c                 |  1 +
 security/selinux/hooks.c            |  1 +
 15 files changed, 64 insertions(+), 38 deletions(-)
 create mode 100644 include/linux/kernel_read_file.h

(limited to 'include/linux')

diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c
index b0ec2721f55d..8c6ea389afcf 100644
--- a/drivers/base/firmware_loader/main.c
+++ b/drivers/base/firmware_loader/main.c
@@ -12,6 +12,7 @@
 
 #include <linux/capability.h>
 #include <linux/device.h>
+#include <linux/kernel_read_file.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/timer.h>
diff --git a/fs/exec.c b/fs/exec.c
index 9233cd50dc4c..c454af329413 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -23,6 +23,7 @@
  * formats.
  */
 
+#include <linux/kernel_read_file.h>
 #include <linux/slab.h>
 #include <linux/file.h>
 #include <linux/fdtable.h>
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 3fb7af12d033..0885d53afb11 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2858,44 +2858,6 @@ static inline void i_readcount_inc(struct inode *inode)
 #endif
 extern int do_pipe_flags(int *, int);
 
-/* This is a list of *what* is being read, not *how* nor *where*. */
-#define __kernel_read_file_id(id) \
-	id(UNKNOWN, unknown)		\
-	id(FIRMWARE, firmware)		\
-	id(MODULE, kernel-module)		\
-	id(KEXEC_IMAGE, kexec-image)		\
-	id(KEXEC_INITRAMFS, kexec-initramfs)	\
-	id(POLICY, security-policy)		\
-	id(X509_CERTIFICATE, x509-certificate)	\
-	id(MAX_ID, )
-
-#define __fid_enumify(ENUM, dummy) READING_ ## ENUM,
-#define __fid_stringify(dummy, str) #str,
-
-enum kernel_read_file_id {
-	__kernel_read_file_id(__fid_enumify)
-};
-
-static const char * const kernel_read_file_str[] = {
-	__kernel_read_file_id(__fid_stringify)
-};
-
-static inline const char *kernel_read_file_id_str(enum kernel_read_file_id id)
-{
-	if ((unsigned)id >= READING_MAX_ID)
-		return kernel_read_file_str[READING_UNKNOWN];
-
-	return kernel_read_file_str[id];
-}
-
-extern int kernel_read_file(struct file *, void **, loff_t *, loff_t,
-			    enum kernel_read_file_id);
-extern int kernel_read_file_from_path(const char *, void **, loff_t *, loff_t,
-				      enum kernel_read_file_id);
-extern int kernel_read_file_from_path_initns(const char *, void **, loff_t *, loff_t,
-					     enum kernel_read_file_id);
-extern int kernel_read_file_from_fd(int, void **, loff_t *, loff_t,
-				    enum kernel_read_file_id);
 extern ssize_t kernel_read(struct file *, void *, size_t, loff_t *);
 ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos);
 extern ssize_t kernel_write(struct file *, const void *, size_t, loff_t *);
diff --git a/include/linux/ima.h b/include/linux/ima.h
index d15100de6cdd..64804f78408b 100644
--- a/include/linux/ima.h
+++ b/include/linux/ima.h
@@ -7,6 +7,7 @@
 #ifndef _LINUX_IMA_H
 #define _LINUX_IMA_H
 
+#include <linux/kernel_read_file.h>
 #include <linux/fs.h>
 #include <linux/security.h>
 #include <linux/kexec.h>
diff --git a/include/linux/kernel_read_file.h b/include/linux/kernel_read_file.h
new file mode 100644
index 000000000000..78cf3d7dc835
--- /dev/null
+++ b/include/linux/kernel_read_file.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_KERNEL_READ_FILE_H
+#define _LINUX_KERNEL_READ_FILE_H
+
+#include <linux/file.h>
+#include <linux/types.h>
+
+/* This is a list of *what* is being read, not *how* nor *where*. */
+#define __kernel_read_file_id(id) \
+	id(UNKNOWN, unknown)		\
+	id(FIRMWARE, firmware)		\
+	id(MODULE, kernel-module)		\
+	id(KEXEC_IMAGE, kexec-image)		\
+	id(KEXEC_INITRAMFS, kexec-initramfs)	\
+	id(POLICY, security-policy)		\
+	id(X509_CERTIFICATE, x509-certificate)	\
+	id(MAX_ID, )
+
+#define __fid_enumify(ENUM, dummy) READING_ ## ENUM,
+#define __fid_stringify(dummy, str) #str,
+
+enum kernel_read_file_id {
+	__kernel_read_file_id(__fid_enumify)
+};
+
+static const char * const kernel_read_file_str[] = {
+	__kernel_read_file_id(__fid_stringify)
+};
+
+static inline const char *kernel_read_file_id_str(enum kernel_read_file_id id)
+{
+	if ((unsigned int)id >= READING_MAX_ID)
+		return kernel_read_file_str[READING_UNKNOWN];
+
+	return kernel_read_file_str[id];
+}
+
+int kernel_read_file(struct file *file,
+		     void **buf, loff_t *size, loff_t max_size,
+		     enum kernel_read_file_id id);
+int kernel_read_file_from_path(const char *path,
+			       void **buf, loff_t *size, loff_t max_size,
+			       enum kernel_read_file_id id);
+int kernel_read_file_from_path_initns(const char *path,
+				      void **buf, loff_t *size, loff_t max_size,
+				      enum kernel_read_file_id id);
+int kernel_read_file_from_fd(int fd,
+			     void **buf, loff_t *size, loff_t max_size,
+			     enum kernel_read_file_id id);
+
+#endif /* _LINUX_KERNEL_READ_FILE_H */
diff --git a/include/linux/security.h b/include/linux/security.h
index 0a0a03b36a3b..42df0d9b4c37 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -23,6 +23,7 @@
 #ifndef __LINUX_SECURITY_H
 #define __LINUX_SECURITY_H
 
+#include <linux/kernel_read_file.h>
 #include <linux/key.h>
 #include <linux/capability.h>
 #include <linux/fs.h>
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index ca40bef75a61..1cc82557f4c1 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -24,6 +24,7 @@
 #include <linux/elf.h>
 #include <linux/elfcore.h>
 #include <linux/kernel.h>
+#include <linux/kernel_read_file.h>
 #include <linux/syscalls.h>
 #include <linux/vmalloc.h>
 #include "kexec_internal.h"
diff --git a/kernel/module.c b/kernel/module.c
index b2808acac46b..4218abd272ee 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -18,6 +18,7 @@
 #include <linux/fs.h>
 #include <linux/sysfs.h>
 #include <linux/kernel.h>
+#include <linux/kernel_read_file.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/elf.h>
diff --git a/security/integrity/digsig.c b/security/integrity/digsig.c
index ac02b7632353..f8869be45d8f 100644
--- a/security/integrity/digsig.c
+++ b/security/integrity/digsig.c
@@ -10,6 +10,7 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/cred.h>
+#include <linux/kernel_read_file.h>
 #include <linux/key-type.h>
 #include <linux/digsig.h>
 #include <linux/vmalloc.h>
diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c
index 15a44c5022f7..e13ffece3726 100644
--- a/security/integrity/ima/ima_fs.c
+++ b/security/integrity/ima/ima_fs.c
@@ -13,6 +13,7 @@
  */
 
 #include <linux/fcntl.h>
+#include <linux/kernel_read_file.h>
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/seq_file.h>
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index 2f187784c5bc..5f89970c5ab7 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -18,6 +18,7 @@
 #include <linux/module.h>
 #include <linux/file.h>
 #include <linux/binfmts.h>
+#include <linux/kernel_read_file.h>
 #include <linux/mount.h>
 #include <linux/mman.h>
 #include <linux/slab.h>
diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c
index b4de33074b37..3b0b43e18ecf 100644
--- a/security/integrity/ima/ima_policy.c
+++ b/security/integrity/ima/ima_policy.c
@@ -9,6 +9,7 @@
 
 #include <linux/init.h>
 #include <linux/list.h>
+#include <linux/kernel_read_file.h>
 #include <linux/fs.h>
 #include <linux/security.h>
 #include <linux/magic.h>
diff --git a/security/loadpin/loadpin.c b/security/loadpin/loadpin.c
index 670a1aebb8a1..163c48216d13 100644
--- a/security/loadpin/loadpin.c
+++ b/security/loadpin/loadpin.c
@@ -11,6 +11,7 @@
 
 #include <linux/module.h>
 #include <linux/fs.h>
+#include <linux/kernel_read_file.h>
 #include <linux/lsm_hooks.h>
 #include <linux/mount.h>
 #include <linux/blkdev.h>
diff --git a/security/security.c b/security/security.c
index 70a7ad357bc6..19d3150f68f4 100644
--- a/security/security.c
+++ b/security/security.c
@@ -16,6 +16,7 @@
 #include <linux/export.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/kernel_read_file.h>
 #include <linux/lsm_hooks.h>
 #include <linux/integrity.h>
 #include <linux/ima.h>
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index a340986aa92e..96f5f8b3b9f0 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -24,6 +24,7 @@
 #include <linux/init.h>
 #include <linux/kd.h>
 #include <linux/kernel.h>
+#include <linux/kernel_read_file.h>
 #include <linux/tracehook.h>
 #include <linux/errno.h>
 #include <linux/sched/signal.h>
-- 
cgit v1.2.3


From f7a4f689bca6072492626938aad6dd2f32c5bf97 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 2 Oct 2020 10:38:17 -0700
Subject: fs/kernel_read_file: Remove redundant size argument

In preparation for refactoring kernel_read_file*(), remove the redundant
"size" argument which is not needed: it can be included in the return
code, with callers adjusted. (VFS reads already cannot be larger than
INT_MAX.)

Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Mimi Zohar <zohar@linux.ibm.com>
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Reviewed-by: James Morris <jamorris@linux.microsoft.com>
Acked-by: Scott Branden <scott.branden@broadcom.com>
Link: https://lore.kernel.org/r/20201002173828.2099543-6-keescook@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/firmware_loader/main.c | 10 ++++++----
 fs/kernel_read_file.c               | 20 +++++++++-----------
 include/linux/kernel_read_file.h    |  8 ++++----
 kernel/kexec_file.c                 | 14 +++++++-------
 kernel/module.c                     |  7 +++----
 security/integrity/digsig.c         |  5 +++--
 security/integrity/ima/ima_fs.c     |  6 ++++--
 7 files changed, 36 insertions(+), 34 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c
index 8c6ea389afcf..6df1bdcfeb9d 100644
--- a/drivers/base/firmware_loader/main.c
+++ b/drivers/base/firmware_loader/main.c
@@ -467,7 +467,7 @@ fw_get_filesystem_firmware(struct device *device, struct fw_priv *fw_priv,
 					     size_t in_size,
 					     const void *in_buffer))
 {
-	loff_t size;
+	size_t size;
 	int i, len;
 	int rc = -ENOENT;
 	char *path;
@@ -499,10 +499,9 @@ fw_get_filesystem_firmware(struct device *device, struct fw_priv *fw_priv,
 		fw_priv->size = 0;
 
 		/* load firmware files from the mount namespace of init */
-		rc = kernel_read_file_from_path_initns(path, &buffer,
-						       &size, msize,
+		rc = kernel_read_file_from_path_initns(path, &buffer, msize,
 						       READING_FIRMWARE);
-		if (rc) {
+		if (rc < 0) {
 			if (rc != -ENOENT)
 				dev_warn(device, "loading %s failed with error %d\n",
 					 path, rc);
@@ -511,6 +510,9 @@ fw_get_filesystem_firmware(struct device *device, struct fw_priv *fw_priv,
 					 path);
 			continue;
 		}
+		size = rc;
+		rc = 0;
+
 		dev_dbg(device, "Loading firmware from %s\n", path);
 		if (decompress) {
 			dev_dbg(device, "f/w decompressing %s\n",
diff --git a/fs/kernel_read_file.c b/fs/kernel_read_file.c
index 54d972d4befc..dc28a8def597 100644
--- a/fs/kernel_read_file.c
+++ b/fs/kernel_read_file.c
@@ -5,7 +5,7 @@
 #include <linux/security.h>
 #include <linux/vmalloc.h>
 
-int kernel_read_file(struct file *file, void **buf, loff_t *size,
+int kernel_read_file(struct file *file, void **buf,
 		     loff_t max_size, enum kernel_read_file_id id)
 {
 	loff_t i_size, pos;
@@ -29,7 +29,7 @@ int kernel_read_file(struct file *file, void **buf, loff_t *size,
 		ret = -EINVAL;
 		goto out;
 	}
-	if (i_size > SIZE_MAX || (max_size > 0 && i_size > max_size)) {
+	if (i_size > INT_MAX || (max_size > 0 && i_size > max_size)) {
 		ret = -EFBIG;
 		goto out;
 	}
@@ -59,8 +59,6 @@ int kernel_read_file(struct file *file, void **buf, loff_t *size,
 	}
 
 	ret = security_kernel_post_read_file(file, *buf, i_size, id);
-	if (!ret)
-		*size = pos;
 
 out_free:
 	if (ret < 0) {
@@ -72,11 +70,11 @@ out_free:
 
 out:
 	allow_write_access(file);
-	return ret;
+	return ret == 0 ? pos : ret;
 }
 EXPORT_SYMBOL_GPL(kernel_read_file);
 
-int kernel_read_file_from_path(const char *path, void **buf, loff_t *size,
+int kernel_read_file_from_path(const char *path, void **buf,
 			       loff_t max_size, enum kernel_read_file_id id)
 {
 	struct file *file;
@@ -89,14 +87,14 @@ int kernel_read_file_from_path(const char *path, void **buf, loff_t *size,
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	ret = kernel_read_file(file, buf, size, max_size, id);
+	ret = kernel_read_file(file, buf, max_size, id);
 	fput(file);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(kernel_read_file_from_path);
 
 int kernel_read_file_from_path_initns(const char *path, void **buf,
-				      loff_t *size, loff_t max_size,
+				      loff_t max_size,
 				      enum kernel_read_file_id id)
 {
 	struct file *file;
@@ -115,13 +113,13 @@ int kernel_read_file_from_path_initns(const char *path, void **buf,
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	ret = kernel_read_file(file, buf, size, max_size, id);
+	ret = kernel_read_file(file, buf, max_size, id);
 	fput(file);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(kernel_read_file_from_path_initns);
 
-int kernel_read_file_from_fd(int fd, void **buf, loff_t *size, loff_t max_size,
+int kernel_read_file_from_fd(int fd, void **buf, loff_t max_size,
 			     enum kernel_read_file_id id)
 {
 	struct fd f = fdget(fd);
@@ -130,7 +128,7 @@ int kernel_read_file_from_fd(int fd, void **buf, loff_t *size, loff_t max_size,
 	if (!f.file)
 		goto out;
 
-	ret = kernel_read_file(f.file, buf, size, max_size, id);
+	ret = kernel_read_file(f.file, buf, max_size, id);
 out:
 	fdput(f);
 	return ret;
diff --git a/include/linux/kernel_read_file.h b/include/linux/kernel_read_file.h
index 78cf3d7dc835..0ca0bdbed1bd 100644
--- a/include/linux/kernel_read_file.h
+++ b/include/linux/kernel_read_file.h
@@ -36,16 +36,16 @@ static inline const char *kernel_read_file_id_str(enum kernel_read_file_id id)
 }
 
 int kernel_read_file(struct file *file,
-		     void **buf, loff_t *size, loff_t max_size,
+		     void **buf, loff_t max_size,
 		     enum kernel_read_file_id id);
 int kernel_read_file_from_path(const char *path,
-			       void **buf, loff_t *size, loff_t max_size,
+			       void **buf, loff_t max_size,
 			       enum kernel_read_file_id id);
 int kernel_read_file_from_path_initns(const char *path,
-				      void **buf, loff_t *size, loff_t max_size,
+				      void **buf, loff_t max_size,
 				      enum kernel_read_file_id id);
 int kernel_read_file_from_fd(int fd,
-			     void **buf, loff_t *size, loff_t max_size,
+			     void **buf, loff_t max_size,
 			     enum kernel_read_file_id id);
 
 #endif /* _LINUX_KERNEL_READ_FILE_H */
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index 1cc82557f4c1..b20cfde8a01d 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -220,13 +220,12 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd,
 {
 	int ret;
 	void *ldata;
-	loff_t size;
 
 	ret = kernel_read_file_from_fd(kernel_fd, &image->kernel_buf,
-				       &size, INT_MAX, READING_KEXEC_IMAGE);
-	if (ret)
+				       INT_MAX, READING_KEXEC_IMAGE);
+	if (ret < 0)
 		return ret;
-	image->kernel_buf_len = size;
+	image->kernel_buf_len = ret;
 
 	/* Call arch image probe handlers */
 	ret = arch_kexec_kernel_image_probe(image, image->kernel_buf,
@@ -243,11 +242,12 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd,
 	/* It is possible that there no initramfs is being loaded */
 	if (!(flags & KEXEC_FILE_NO_INITRAMFS)) {
 		ret = kernel_read_file_from_fd(initrd_fd, &image->initrd_buf,
-					       &size, INT_MAX,
+					       INT_MAX,
 					       READING_KEXEC_INITRAMFS);
-		if (ret)
+		if (ret < 0)
 			goto out;
-		image->initrd_buf_len = size;
+		image->initrd_buf_len = ret;
+		ret = 0;
 	}
 
 	if (cmdline_len) {
diff --git a/kernel/module.c b/kernel/module.c
index 4218abd272ee..9faa6322f17b 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -4035,7 +4035,6 @@ SYSCALL_DEFINE3(init_module, void __user *, umod,
 SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags)
 {
 	struct load_info info = { };
-	loff_t size;
 	void *hdr = NULL;
 	int err;
 
@@ -4049,12 +4048,12 @@ SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags)
 		      |MODULE_INIT_IGNORE_VERMAGIC))
 		return -EINVAL;
 
-	err = kernel_read_file_from_fd(fd, &hdr, &size, INT_MAX,
+	err = kernel_read_file_from_fd(fd, &hdr, INT_MAX,
 				       READING_MODULE);
-	if (err)
+	if (err < 0)
 		return err;
 	info.hdr = hdr;
-	info.len = size;
+	info.len = err;
 
 	return load_module(&info, uargs, flags);
 }
diff --git a/security/integrity/digsig.c b/security/integrity/digsig.c
index f8869be45d8f..97661ffabc4e 100644
--- a/security/integrity/digsig.c
+++ b/security/integrity/digsig.c
@@ -171,16 +171,17 @@ int __init integrity_add_key(const unsigned int id, const void *data,
 int __init integrity_load_x509(const unsigned int id, const char *path)
 {
 	void *data = NULL;
-	loff_t size;
+	size_t size;
 	int rc;
 	key_perm_t perm;
 
-	rc = kernel_read_file_from_path(path, &data, &size, 0,
+	rc = kernel_read_file_from_path(path, &data, 0,
 					READING_X509_CERTIFICATE);
 	if (rc < 0) {
 		pr_err("Unable to open file: %s (%d)", path, rc);
 		return rc;
 	}
+	size = rc;
 
 	perm = (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW | KEY_USR_READ;
 
diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c
index e13ffece3726..602f52717757 100644
--- a/security/integrity/ima/ima_fs.c
+++ b/security/integrity/ima/ima_fs.c
@@ -275,7 +275,7 @@ static ssize_t ima_read_policy(char *path)
 {
 	void *data = NULL;
 	char *datap;
-	loff_t size;
+	size_t size;
 	int rc, pathlen = strlen(path);
 
 	char *p;
@@ -284,11 +284,13 @@ static ssize_t ima_read_policy(char *path)
 	datap = path;
 	strsep(&datap, "\n");
 
-	rc = kernel_read_file_from_path(path, &data, &size, 0, READING_POLICY);
+	rc = kernel_read_file_from_path(path, &data, 0, READING_POLICY);
 	if (rc < 0) {
 		pr_err("Unable to open file: %s (%d)", path, rc);
 		return rc;
 	}
+	size = rc;
+	rc = 0;
 
 	datap = data;
 	while (size > 0 && (p = strsep(&datap, "\n"))) {
-- 
cgit v1.2.3


From 113eeb517780add2b38932a61d4e4440a73eb72a Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 2 Oct 2020 10:38:18 -0700
Subject: fs/kernel_read_file: Switch buffer size arg to size_t

In preparation for further refactoring of kernel_read_file*(), rename
the "max_size" argument to the more accurate "buf_size", and correct
its type to size_t. Add kerndoc to explain the specifics of how the
arguments will be used. Note that with buf_size now size_t, it can no
longer be negative (and was never called with a negative value). Adjust
callers to use it as a "maximum size" when *buf is NULL.

Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Mimi Zohar <zohar@linux.ibm.com>
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Reviewed-by: James Morris <jamorris@linux.microsoft.com>
Acked-by: Scott Branden <scott.branden@broadcom.com>
Link: https://lore.kernel.org/r/20201002173828.2099543-7-keescook@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/kernel_read_file.c            | 34 +++++++++++++++++++++++++---------
 include/linux/kernel_read_file.h |  8 ++++----
 security/integrity/digsig.c      |  2 +-
 security/integrity/ima/ima_fs.c  |  2 +-
 4 files changed, 31 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/fs/kernel_read_file.c b/fs/kernel_read_file.c
index dc28a8def597..e21a76001fff 100644
--- a/fs/kernel_read_file.c
+++ b/fs/kernel_read_file.c
@@ -5,15 +5,31 @@
 #include <linux/security.h>
 #include <linux/vmalloc.h>
 
+/**
+ * kernel_read_file() - read file contents into a kernel buffer
+ *
+ * @file	file to read from
+ * @buf		pointer to a "void *" buffer for reading into (if
+ *		*@buf is NULL, a buffer will be allocated, and
+ *		@buf_size will be ignored)
+ * @buf_size	size of buf, if already allocated. If @buf not
+ *		allocated, this is the largest size to allocate.
+ * @id		the kernel_read_file_id identifying the type of
+ *		file contents being read (for LSMs to examine)
+ *
+ * Returns number of bytes read (no single read will be bigger
+ * than INT_MAX), or negative on error.
+ *
+ */
 int kernel_read_file(struct file *file, void **buf,
-		     loff_t max_size, enum kernel_read_file_id id)
+		     size_t buf_size, enum kernel_read_file_id id)
 {
 	loff_t i_size, pos;
 	ssize_t bytes = 0;
 	void *allocated = NULL;
 	int ret;
 
-	if (!S_ISREG(file_inode(file)->i_mode) || max_size < 0)
+	if (!S_ISREG(file_inode(file)->i_mode))
 		return -EINVAL;
 
 	ret = deny_write_access(file);
@@ -29,7 +45,7 @@ int kernel_read_file(struct file *file, void **buf,
 		ret = -EINVAL;
 		goto out;
 	}
-	if (i_size > INT_MAX || (max_size > 0 && i_size > max_size)) {
+	if (i_size > INT_MAX || i_size > buf_size) {
 		ret = -EFBIG;
 		goto out;
 	}
@@ -75,7 +91,7 @@ out:
 EXPORT_SYMBOL_GPL(kernel_read_file);
 
 int kernel_read_file_from_path(const char *path, void **buf,
-			       loff_t max_size, enum kernel_read_file_id id)
+			       size_t buf_size, enum kernel_read_file_id id)
 {
 	struct file *file;
 	int ret;
@@ -87,14 +103,14 @@ int kernel_read_file_from_path(const char *path, void **buf,
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	ret = kernel_read_file(file, buf, max_size, id);
+	ret = kernel_read_file(file, buf, buf_size, id);
 	fput(file);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(kernel_read_file_from_path);
 
 int kernel_read_file_from_path_initns(const char *path, void **buf,
-				      loff_t max_size,
+				      size_t buf_size,
 				      enum kernel_read_file_id id)
 {
 	struct file *file;
@@ -113,13 +129,13 @@ int kernel_read_file_from_path_initns(const char *path, void **buf,
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	ret = kernel_read_file(file, buf, max_size, id);
+	ret = kernel_read_file(file, buf, buf_size, id);
 	fput(file);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(kernel_read_file_from_path_initns);
 
-int kernel_read_file_from_fd(int fd, void **buf, loff_t max_size,
+int kernel_read_file_from_fd(int fd, void **buf, size_t buf_size,
 			     enum kernel_read_file_id id)
 {
 	struct fd f = fdget(fd);
@@ -128,7 +144,7 @@ int kernel_read_file_from_fd(int fd, void **buf, loff_t max_size,
 	if (!f.file)
 		goto out;
 
-	ret = kernel_read_file(f.file, buf, max_size, id);
+	ret = kernel_read_file(f.file, buf, buf_size, id);
 out:
 	fdput(f);
 	return ret;
diff --git a/include/linux/kernel_read_file.h b/include/linux/kernel_read_file.h
index 0ca0bdbed1bd..910039e7593e 100644
--- a/include/linux/kernel_read_file.h
+++ b/include/linux/kernel_read_file.h
@@ -36,16 +36,16 @@ static inline const char *kernel_read_file_id_str(enum kernel_read_file_id id)
 }
 
 int kernel_read_file(struct file *file,
-		     void **buf, loff_t max_size,
+		     void **buf, size_t buf_size,
 		     enum kernel_read_file_id id);
 int kernel_read_file_from_path(const char *path,
-			       void **buf, loff_t max_size,
+			       void **buf, size_t buf_size,
 			       enum kernel_read_file_id id);
 int kernel_read_file_from_path_initns(const char *path,
-				      void **buf, loff_t max_size,
+				      void **buf, size_t buf_size,
 				      enum kernel_read_file_id id);
 int kernel_read_file_from_fd(int fd,
-			     void **buf, loff_t max_size,
+			     void **buf, size_t buf_size,
 			     enum kernel_read_file_id id);
 
 #endif /* _LINUX_KERNEL_READ_FILE_H */
diff --git a/security/integrity/digsig.c b/security/integrity/digsig.c
index 97661ffabc4e..04f779c4f5ed 100644
--- a/security/integrity/digsig.c
+++ b/security/integrity/digsig.c
@@ -175,7 +175,7 @@ int __init integrity_load_x509(const unsigned int id, const char *path)
 	int rc;
 	key_perm_t perm;
 
-	rc = kernel_read_file_from_path(path, &data, 0,
+	rc = kernel_read_file_from_path(path, &data, INT_MAX,
 					READING_X509_CERTIFICATE);
 	if (rc < 0) {
 		pr_err("Unable to open file: %s (%d)", path, rc);
diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c
index 602f52717757..692b83e82edf 100644
--- a/security/integrity/ima/ima_fs.c
+++ b/security/integrity/ima/ima_fs.c
@@ -284,7 +284,7 @@ static ssize_t ima_read_policy(char *path)
 	datap = path;
 	strsep(&datap, "\n");
 
-	rc = kernel_read_file_from_path(path, &data, 0, READING_POLICY);
+	rc = kernel_read_file_from_path(path, &data, INT_MAX, READING_POLICY);
 	if (rc < 0) {
 		pr_err("Unable to open file: %s (%d)", path, rc);
 		return rc;
-- 
cgit v1.2.3


From 885352881f11f1f3113d8eb877786bcb6d720544 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 2 Oct 2020 10:38:19 -0700
Subject: fs/kernel_read_file: Add file_size output argument

In preparation for adding partial read support, add an optional output
argument to kernel_read_file*() that reports the file size so callers
can reason more easily about their reading progress.

Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Mimi Zohar <zohar@linux.ibm.com>
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Reviewed-by: James Morris <jamorris@linux.microsoft.com>
Acked-by: Scott Branden <scott.branden@broadcom.com>
Link: https://lore.kernel.org/r/20201002173828.2099543-8-keescook@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/firmware_loader/main.c |  1 +
 fs/kernel_read_file.c               | 19 +++++++++++++------
 include/linux/kernel_read_file.h    |  4 ++++
 kernel/kexec_file.c                 |  4 ++--
 kernel/module.c                     |  2 +-
 security/integrity/digsig.c         |  2 +-
 security/integrity/ima/ima_fs.c     |  2 +-
 7 files changed, 23 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c
index 6df1bdcfeb9d..d9a180148c4b 100644
--- a/drivers/base/firmware_loader/main.c
+++ b/drivers/base/firmware_loader/main.c
@@ -500,6 +500,7 @@ fw_get_filesystem_firmware(struct device *device, struct fw_priv *fw_priv,
 
 		/* load firmware files from the mount namespace of init */
 		rc = kernel_read_file_from_path_initns(path, &buffer, msize,
+						       NULL,
 						       READING_FIRMWARE);
 		if (rc < 0) {
 			if (rc != -ENOENT)
diff --git a/fs/kernel_read_file.c b/fs/kernel_read_file.c
index e21a76001fff..2e29c38eb4df 100644
--- a/fs/kernel_read_file.c
+++ b/fs/kernel_read_file.c
@@ -14,6 +14,8 @@
  *		@buf_size will be ignored)
  * @buf_size	size of buf, if already allocated. If @buf not
  *		allocated, this is the largest size to allocate.
+ * @file_size	if non-NULL, the full size of @file will be
+ *		written here.
  * @id		the kernel_read_file_id identifying the type of
  *		file contents being read (for LSMs to examine)
  *
@@ -22,7 +24,8 @@
  *
  */
 int kernel_read_file(struct file *file, void **buf,
-		     size_t buf_size, enum kernel_read_file_id id)
+		     size_t buf_size, size_t *file_size,
+		     enum kernel_read_file_id id)
 {
 	loff_t i_size, pos;
 	ssize_t bytes = 0;
@@ -49,6 +52,8 @@ int kernel_read_file(struct file *file, void **buf,
 		ret = -EFBIG;
 		goto out;
 	}
+	if (file_size)
+		*file_size = i_size;
 
 	if (!*buf)
 		*buf = allocated = vmalloc(i_size);
@@ -91,7 +96,8 @@ out:
 EXPORT_SYMBOL_GPL(kernel_read_file);
 
 int kernel_read_file_from_path(const char *path, void **buf,
-			       size_t buf_size, enum kernel_read_file_id id)
+			       size_t buf_size, size_t *file_size,
+			       enum kernel_read_file_id id)
 {
 	struct file *file;
 	int ret;
@@ -103,14 +109,14 @@ int kernel_read_file_from_path(const char *path, void **buf,
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	ret = kernel_read_file(file, buf, buf_size, id);
+	ret = kernel_read_file(file, buf, buf_size, file_size, id);
 	fput(file);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(kernel_read_file_from_path);
 
 int kernel_read_file_from_path_initns(const char *path, void **buf,
-				      size_t buf_size,
+				      size_t buf_size, size_t *file_size,
 				      enum kernel_read_file_id id)
 {
 	struct file *file;
@@ -129,13 +135,14 @@ int kernel_read_file_from_path_initns(const char *path, void **buf,
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	ret = kernel_read_file(file, buf, buf_size, id);
+	ret = kernel_read_file(file, buf, buf_size, file_size, id);
 	fput(file);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(kernel_read_file_from_path_initns);
 
 int kernel_read_file_from_fd(int fd, void **buf, size_t buf_size,
+			     size_t *file_size,
 			     enum kernel_read_file_id id)
 {
 	struct fd f = fdget(fd);
@@ -144,7 +151,7 @@ int kernel_read_file_from_fd(int fd, void **buf, size_t buf_size,
 	if (!f.file)
 		goto out;
 
-	ret = kernel_read_file(f.file, buf, buf_size, id);
+	ret = kernel_read_file(f.file, buf, buf_size, file_size, id);
 out:
 	fdput(f);
 	return ret;
diff --git a/include/linux/kernel_read_file.h b/include/linux/kernel_read_file.h
index 910039e7593e..023293eaf948 100644
--- a/include/linux/kernel_read_file.h
+++ b/include/linux/kernel_read_file.h
@@ -37,15 +37,19 @@ static inline const char *kernel_read_file_id_str(enum kernel_read_file_id id)
 
 int kernel_read_file(struct file *file,
 		     void **buf, size_t buf_size,
+		     size_t *file_size,
 		     enum kernel_read_file_id id);
 int kernel_read_file_from_path(const char *path,
 			       void **buf, size_t buf_size,
+			       size_t *file_size,
 			       enum kernel_read_file_id id);
 int kernel_read_file_from_path_initns(const char *path,
 				      void **buf, size_t buf_size,
+				      size_t *file_size,
 				      enum kernel_read_file_id id);
 int kernel_read_file_from_fd(int fd,
 			     void **buf, size_t buf_size,
+			     size_t *file_size,
 			     enum kernel_read_file_id id);
 
 #endif /* _LINUX_KERNEL_READ_FILE_H */
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index b20cfde8a01d..ee51c1028658 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -222,7 +222,7 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd,
 	void *ldata;
 
 	ret = kernel_read_file_from_fd(kernel_fd, &image->kernel_buf,
-				       INT_MAX, READING_KEXEC_IMAGE);
+				       INT_MAX, NULL, READING_KEXEC_IMAGE);
 	if (ret < 0)
 		return ret;
 	image->kernel_buf_len = ret;
@@ -242,7 +242,7 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd,
 	/* It is possible that there no initramfs is being loaded */
 	if (!(flags & KEXEC_FILE_NO_INITRAMFS)) {
 		ret = kernel_read_file_from_fd(initrd_fd, &image->initrd_buf,
-					       INT_MAX,
+					       INT_MAX, NULL,
 					       READING_KEXEC_INITRAMFS);
 		if (ret < 0)
 			goto out;
diff --git a/kernel/module.c b/kernel/module.c
index 9faa6322f17b..0f11eaed047e 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -4048,7 +4048,7 @@ SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags)
 		      |MODULE_INIT_IGNORE_VERMAGIC))
 		return -EINVAL;
 
-	err = kernel_read_file_from_fd(fd, &hdr, INT_MAX,
+	err = kernel_read_file_from_fd(fd, &hdr, INT_MAX, NULL,
 				       READING_MODULE);
 	if (err < 0)
 		return err;
diff --git a/security/integrity/digsig.c b/security/integrity/digsig.c
index 04f779c4f5ed..8a523dfd7fd7 100644
--- a/security/integrity/digsig.c
+++ b/security/integrity/digsig.c
@@ -175,7 +175,7 @@ int __init integrity_load_x509(const unsigned int id, const char *path)
 	int rc;
 	key_perm_t perm;
 
-	rc = kernel_read_file_from_path(path, &data, INT_MAX,
+	rc = kernel_read_file_from_path(path, &data, INT_MAX, NULL,
 					READING_X509_CERTIFICATE);
 	if (rc < 0) {
 		pr_err("Unable to open file: %s (%d)", path, rc);
diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c
index 692b83e82edf..5fc56ccb6678 100644
--- a/security/integrity/ima/ima_fs.c
+++ b/security/integrity/ima/ima_fs.c
@@ -284,7 +284,7 @@ static ssize_t ima_read_policy(char *path)
 	datap = path;
 	strsep(&datap, "\n");
 
-	rc = kernel_read_file_from_path(path, &data, INT_MAX, READING_POLICY);
+	rc = kernel_read_file_from_path(path, &data, INT_MAX, NULL, READING_POLICY);
 	if (rc < 0) {
 		pr_err("Unable to open file: %s (%d)", path, rc);
 		return rc;
-- 
cgit v1.2.3


From b64fcae74b6d6940d14243c963ab0089e8f0d82d Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 2 Oct 2020 10:38:20 -0700
Subject: LSM: Introduce kernel_post_load_data() hook

There are a few places in the kernel where LSMs would like to have
visibility into the contents of a kernel buffer that has been loaded or
read. While security_kernel_post_read_file() (which includes the
buffer) exists as a pairing for security_kernel_read_file(), no such
hook exists to pair with security_kernel_load_data().

Earlier proposals for just using security_kernel_post_read_file() with a
NULL file argument were rejected (i.e. "file" should always be valid for
the security_..._file hooks, but it appears at least one case was
left in the kernel during earlier refactoring. (This will be fixed in
a subsequent patch.)

Since not all cases of security_kernel_load_data() can have a single
contiguous buffer made available to the LSM hook (e.g. kexec image
segments are separately loaded), there needs to be a way for the LSM to
reason about its expectations of the hook coverage. In order to handle
this, add a "contents" argument to the "kernel_load_data" hook that
indicates if the newly added "kernel_post_load_data" hook will be called
with the full contents once loaded. That way, LSMs requiring full contents
can choose to unilaterally reject "kernel_load_data" with contents=false
(which is effectively the existing hook coverage), but when contents=true
they can allow it and later evaluate the "kernel_post_load_data" hook
once the buffer is loaded.

With this change, LSMs can gain coverage over non-file-backed data loads
(e.g. init_module(2) and firmware userspace helper), which will happen
in subsequent patches.

Additionally prepare IMA to start processing these cases.

Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: KP Singh <kpsingh@google.com>
Link: https://lore.kernel.org/r/20201002173828.2099543-9-keescook@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/firmware_loader/fallback.c          |  2 +-
 drivers/base/firmware_loader/fallback_platform.c |  2 +-
 include/linux/ima.h                              | 13 +++++++++++--
 include/linux/lsm_hook_defs.h                    |  4 +++-
 include/linux/lsm_hooks.h                        | 10 ++++++++++
 include/linux/security.h                         | 14 ++++++++++++--
 kernel/kexec.c                                   |  2 +-
 kernel/module.c                                  |  2 +-
 security/integrity/ima/ima_main.c                | 24 +++++++++++++++++++++++-
 security/loadpin/loadpin.c                       |  2 +-
 security/security.c                              | 20 +++++++++++++++++---
 security/selinux/hooks.c                         |  2 +-
 12 files changed, 82 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/firmware_loader/fallback.c b/drivers/base/firmware_loader/fallback.c
index 283ca2de76d4..bff4717cc6b5 100644
--- a/drivers/base/firmware_loader/fallback.c
+++ b/drivers/base/firmware_loader/fallback.c
@@ -613,7 +613,7 @@ static bool fw_run_sysfs_fallback(u32 opt_flags)
 		return false;
 
 	/* Also permit LSMs and IMA to fail firmware sysfs fallback */
-	ret = security_kernel_load_data(LOADING_FIRMWARE);
+	ret = security_kernel_load_data(LOADING_FIRMWARE, false);
 	if (ret < 0)
 		return false;
 
diff --git a/drivers/base/firmware_loader/fallback_platform.c b/drivers/base/firmware_loader/fallback_platform.c
index 6958ab1a8059..a12c79d47efc 100644
--- a/drivers/base/firmware_loader/fallback_platform.c
+++ b/drivers/base/firmware_loader/fallback_platform.c
@@ -17,7 +17,7 @@ int firmware_fallback_platform(struct fw_priv *fw_priv, u32 opt_flags)
 	if (!(opt_flags & FW_OPT_FALLBACK_PLATFORM))
 		return -ENOENT;
 
-	rc = security_kernel_load_data(LOADING_FIRMWARE);
+	rc = security_kernel_load_data(LOADING_FIRMWARE, false);
 	if (rc)
 		return rc;
 
diff --git a/include/linux/ima.h b/include/linux/ima.h
index 64804f78408b..af9fb8c5f16a 100644
--- a/include/linux/ima.h
+++ b/include/linux/ima.h
@@ -20,7 +20,9 @@ extern void ima_post_create_tmpfile(struct inode *inode);
 extern void ima_file_free(struct file *file);
 extern int ima_file_mmap(struct file *file, unsigned long prot);
 extern int ima_file_mprotect(struct vm_area_struct *vma, unsigned long prot);
-extern int ima_load_data(enum kernel_load_data_id id);
+extern int ima_load_data(enum kernel_load_data_id id, bool contents);
+extern int ima_post_load_data(char *buf, loff_t size,
+			      enum kernel_load_data_id id, char *description);
 extern int ima_read_file(struct file *file, enum kernel_read_file_id id);
 extern int ima_post_read_file(struct file *file, void *buf, loff_t size,
 			      enum kernel_read_file_id id);
@@ -78,7 +80,14 @@ static inline int ima_file_mprotect(struct vm_area_struct *vma,
 	return 0;
 }
 
-static inline int ima_load_data(enum kernel_load_data_id id)
+static inline int ima_load_data(enum kernel_load_data_id id, bool contents)
+{
+	return 0;
+}
+
+static inline int ima_post_load_data(char *buf, loff_t size,
+				     enum kernel_load_data_id id,
+				     char *description)
 {
 	return 0;
 }
diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index 2a8c74d99015..83c6f1f5cc1e 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -184,7 +184,9 @@ LSM_HOOK(void, LSM_RET_VOID, cred_getsecid, const struct cred *c, u32 *secid)
 LSM_HOOK(int, 0, kernel_act_as, struct cred *new, u32 secid)
 LSM_HOOK(int, 0, kernel_create_files_as, struct cred *new, struct inode *inode)
 LSM_HOOK(int, 0, kernel_module_request, char *kmod_name)
-LSM_HOOK(int, 0, kernel_load_data, enum kernel_load_data_id id)
+LSM_HOOK(int, 0, kernel_load_data, enum kernel_load_data_id id, bool contents)
+LSM_HOOK(int, 0, kernel_post_load_data, char *buf, loff_t size,
+	 enum kernel_read_file_id id, char *description)
 LSM_HOOK(int, 0, kernel_read_file, struct file *file,
 	 enum kernel_read_file_id id)
 LSM_HOOK(int, 0, kernel_post_read_file, struct file *file, char *buf,
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index 9e2e3e63719d..6bb4f1a0158c 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -635,7 +635,17 @@
  * @kernel_load_data:
  *	Load data provided by userspace.
  *	@id kernel load data identifier
+ *	@contents if a subsequent @kernel_post_load_data will be called.
  *	Return 0 if permission is granted.
+ * @kernel_post_load_data:
+ *	Load data provided by a non-file source (usually userspace buffer).
+ *	@buf pointer to buffer containing the data contents.
+ *	@size length of the data contents.
+ *	@id kernel load data identifier
+ *	@description a text description of what was loaded, @id-specific
+ *	Return 0 if permission is granted.
+ *	This must be paired with a prior @kernel_load_data call that had
+ *	@contents set to true.
  * @kernel_read_file:
  *	Read a file specified by userspace.
  *	@file contains the file structure pointing to the file being read
diff --git a/include/linux/security.h b/include/linux/security.h
index 42df0d9b4c37..51c8e4e6b7cc 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -387,7 +387,10 @@ void security_cred_getsecid(const struct cred *c, u32 *secid);
 int security_kernel_act_as(struct cred *new, u32 secid);
 int security_kernel_create_files_as(struct cred *new, struct inode *inode);
 int security_kernel_module_request(char *kmod_name);
-int security_kernel_load_data(enum kernel_load_data_id id);
+int security_kernel_load_data(enum kernel_load_data_id id, bool contents);
+int security_kernel_post_load_data(char *buf, loff_t size,
+				   enum kernel_load_data_id id,
+				   char *description);
 int security_kernel_read_file(struct file *file, enum kernel_read_file_id id);
 int security_kernel_post_read_file(struct file *file, char *buf, loff_t size,
 				   enum kernel_read_file_id id);
@@ -1014,7 +1017,14 @@ static inline int security_kernel_module_request(char *kmod_name)
 	return 0;
 }
 
-static inline int security_kernel_load_data(enum kernel_load_data_id id)
+static inline int security_kernel_load_data(enum kernel_load_data_id id, bool contents)
+{
+	return 0;
+}
+
+static inline int security_kernel_post_load_data(char *buf, loff_t size,
+						 enum kernel_load_data_id id,
+						 char *description)
 {
 	return 0;
 }
diff --git a/kernel/kexec.c b/kernel/kexec.c
index f977786fe498..c82c6c06f051 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -205,7 +205,7 @@ static inline int kexec_load_check(unsigned long nr_segments,
 		return -EPERM;
 
 	/* Permit LSMs and IMA to fail the kexec */
-	result = security_kernel_load_data(LOADING_KEXEC_IMAGE);
+	result = security_kernel_load_data(LOADING_KEXEC_IMAGE, false);
 	if (result < 0)
 		return result;
 
diff --git a/kernel/module.c b/kernel/module.c
index 0f11eaed047e..f47209e0fde6 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -3014,7 +3014,7 @@ static int copy_module_from_user(const void __user *umod, unsigned long len,
 	if (info->len < sizeof(*(info->hdr)))
 		return -ENOEXEC;
 
-	err = security_kernel_load_data(LOADING_MODULE);
+	err = security_kernel_load_data(LOADING_MODULE, false);
 	if (err)
 		return err;
 
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index 5f89970c5ab7..9dd9c5f4d736 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -676,6 +676,8 @@ int ima_post_read_file(struct file *file, void *buf, loff_t size,
 /**
  * ima_load_data - appraise decision based on policy
  * @id: kernel load data caller identifier
+ * @contents: whether the full contents will be available in a later
+ *	      call to ima_post_load_data().
  *
  * Callers of this LSM hook can not measure, appraise, or audit the
  * data provided by userspace.  Enforce policy rules requring a file
@@ -683,7 +685,7 @@ int ima_post_read_file(struct file *file, void *buf, loff_t size,
  *
  * For permission return 0, otherwise return -EACCES.
  */
-int ima_load_data(enum kernel_load_data_id id)
+int ima_load_data(enum kernel_load_data_id id, bool contents)
 {
 	bool ima_enforce, sig_enforce;
 
@@ -723,6 +725,26 @@ int ima_load_data(enum kernel_load_data_id id)
 	return 0;
 }
 
+/**
+ * ima_post_load_data - appraise decision based on policy
+ * @buf: pointer to in memory file contents
+ * @size: size of in memory file contents
+ * @id: kernel load data caller identifier
+ * @description: @id-specific description of contents
+ *
+ * Measure/appraise/audit in memory buffer based on policy.  Policy rules
+ * are written in terms of a policy identifier.
+ *
+ * On success return 0.  On integrity appraisal error, assuming the file
+ * is in policy and IMA-appraisal is in enforcing mode, return -EACCES.
+ */
+int ima_post_load_data(char *buf, loff_t size,
+		       enum kernel_load_data_id load_id,
+		       char *description)
+{
+	return 0;
+}
+
 /*
  * process_buffer_measurement - Measure the buffer to ima log.
  * @inode: inode associated with the object being measured (NULL for KEY_CHECK)
diff --git a/security/loadpin/loadpin.c b/security/loadpin/loadpin.c
index 163c48216d13..28782412febb 100644
--- a/security/loadpin/loadpin.c
+++ b/security/loadpin/loadpin.c
@@ -177,7 +177,7 @@ static int loadpin_read_file(struct file *file, enum kernel_read_file_id id)
 	return 0;
 }
 
-static int loadpin_load_data(enum kernel_load_data_id id)
+static int loadpin_load_data(enum kernel_load_data_id id, bool contents)
 {
 	return loadpin_read_file(NULL, (enum kernel_read_file_id) id);
 }
diff --git a/security/security.c b/security/security.c
index 19d3150f68f4..531b855826fc 100644
--- a/security/security.c
+++ b/security/security.c
@@ -1695,17 +1695,31 @@ int security_kernel_post_read_file(struct file *file, char *buf, loff_t size,
 }
 EXPORT_SYMBOL_GPL(security_kernel_post_read_file);
 
-int security_kernel_load_data(enum kernel_load_data_id id)
+int security_kernel_load_data(enum kernel_load_data_id id, bool contents)
 {
 	int ret;
 
-	ret = call_int_hook(kernel_load_data, 0, id);
+	ret = call_int_hook(kernel_load_data, 0, id, contents);
 	if (ret)
 		return ret;
-	return ima_load_data(id);
+	return ima_load_data(id, contents);
 }
 EXPORT_SYMBOL_GPL(security_kernel_load_data);
 
+int security_kernel_post_load_data(char *buf, loff_t size,
+				   enum kernel_load_data_id id,
+				   char *description)
+{
+	int ret;
+
+	ret = call_int_hook(kernel_post_load_data, 0, buf, size, id,
+			    description);
+	if (ret)
+		return ret;
+	return ima_post_load_data(buf, size, id, description);
+}
+EXPORT_SYMBOL_GPL(security_kernel_post_load_data);
+
 int security_task_fix_setuid(struct cred *new, const struct cred *old,
 			     int flags)
 {
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 96f5f8b3b9f0..558beee97d8d 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -4018,7 +4018,7 @@ static int selinux_kernel_read_file(struct file *file,
 	return rc;
 }
 
-static int selinux_kernel_load_data(enum kernel_load_data_id id)
+static int selinux_kernel_load_data(enum kernel_load_data_id id, bool contents)
 {
 	int rc = 0;
 
-- 
cgit v1.2.3


From 2039bda1fa8dad3f4275b29eeaffef545bcbc85d Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 2 Oct 2020 10:38:23 -0700
Subject: LSM: Add "contents" flag to kernel_read_file hook

As with the kernel_load_data LSM hook, add a "contents" flag to the
kernel_read_file LSM hook that indicates whether the LSM can expect
a matching call to the kernel_post_read_file LSM hook with the full
contents of the file. With the coming addition of partial file read
support for kernel_read_file*() API, the LSM will no longer be able
to always see the entire contents of a file during the read calls.

For cases where the LSM must read examine the complete file contents,
it will need to do so on its own every time the kernel_read_file
hook is called with contents=false (or reject such cases). Adjust all
existing LSMs to retain existing behavior.

Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Mimi Zohar <zohar@linux.ibm.com>
Link: https://lore.kernel.org/r/20201002173828.2099543-12-keescook@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/kernel_read_file.c             |  2 +-
 include/linux/ima.h               |  6 ++++--
 include/linux/lsm_hook_defs.h     |  2 +-
 include/linux/lsm_hooks.h         |  3 +++
 include/linux/security.h          |  6 ++++--
 security/integrity/ima/ima_main.c | 10 +++++++++-
 security/loadpin/loadpin.c        | 14 ++++++++++++--
 security/security.c               |  7 ++++---
 security/selinux/hooks.c          |  5 +++--
 9 files changed, 41 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/fs/kernel_read_file.c b/fs/kernel_read_file.c
index 2e29c38eb4df..d73bc3fa710a 100644
--- a/fs/kernel_read_file.c
+++ b/fs/kernel_read_file.c
@@ -39,7 +39,7 @@ int kernel_read_file(struct file *file, void **buf,
 	if (ret)
 		return ret;
 
-	ret = security_kernel_read_file(file, id);
+	ret = security_kernel_read_file(file, id, true);
 	if (ret)
 		goto out;
 
diff --git a/include/linux/ima.h b/include/linux/ima.h
index af9fb8c5f16a..8fa7bcfb2da2 100644
--- a/include/linux/ima.h
+++ b/include/linux/ima.h
@@ -23,7 +23,8 @@ extern int ima_file_mprotect(struct vm_area_struct *vma, unsigned long prot);
 extern int ima_load_data(enum kernel_load_data_id id, bool contents);
 extern int ima_post_load_data(char *buf, loff_t size,
 			      enum kernel_load_data_id id, char *description);
-extern int ima_read_file(struct file *file, enum kernel_read_file_id id);
+extern int ima_read_file(struct file *file, enum kernel_read_file_id id,
+			 bool contents);
 extern int ima_post_read_file(struct file *file, void *buf, loff_t size,
 			      enum kernel_read_file_id id);
 extern void ima_post_path_mknod(struct dentry *dentry);
@@ -92,7 +93,8 @@ static inline int ima_post_load_data(char *buf, loff_t size,
 	return 0;
 }
 
-static inline int ima_read_file(struct file *file, enum kernel_read_file_id id)
+static inline int ima_read_file(struct file *file, enum kernel_read_file_id id,
+				bool contents)
 {
 	return 0;
 }
diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index 83c6f1f5cc1e..d67cb3502310 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -188,7 +188,7 @@ LSM_HOOK(int, 0, kernel_load_data, enum kernel_load_data_id id, bool contents)
 LSM_HOOK(int, 0, kernel_post_load_data, char *buf, loff_t size,
 	 enum kernel_read_file_id id, char *description)
 LSM_HOOK(int, 0, kernel_read_file, struct file *file,
-	 enum kernel_read_file_id id)
+	 enum kernel_read_file_id id, bool contents)
 LSM_HOOK(int, 0, kernel_post_read_file, struct file *file, char *buf,
 	 loff_t size, enum kernel_read_file_id id)
 LSM_HOOK(int, 0, task_fix_setuid, struct cred *new, const struct cred *old,
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index 6bb4f1a0158c..8814e3d5952d 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -651,6 +651,7 @@
  *	@file contains the file structure pointing to the file being read
  *	by the kernel.
  *	@id kernel read file identifier
+ *	@contents if a subsequent @kernel_post_read_file will be called.
  *	Return 0 if permission is granted.
  * @kernel_post_read_file:
  *	Read a file specified by userspace.
@@ -659,6 +660,8 @@
  *	@buf pointer to buffer containing the file contents.
  *	@size length of the file contents.
  *	@id kernel read file identifier
+ *	This must be paired with a prior @kernel_read_file call that had
+ *	@contents set to true.
  *	Return 0 if permission is granted.
  * @task_fix_setuid:
  *	Update the module's state after setting one or more of the user
diff --git a/include/linux/security.h b/include/linux/security.h
index 51c8e4e6b7cc..bc2725491560 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -391,7 +391,8 @@ int security_kernel_load_data(enum kernel_load_data_id id, bool contents);
 int security_kernel_post_load_data(char *buf, loff_t size,
 				   enum kernel_load_data_id id,
 				   char *description);
-int security_kernel_read_file(struct file *file, enum kernel_read_file_id id);
+int security_kernel_read_file(struct file *file, enum kernel_read_file_id id,
+			      bool contents);
 int security_kernel_post_read_file(struct file *file, char *buf, loff_t size,
 				   enum kernel_read_file_id id);
 int security_task_fix_setuid(struct cred *new, const struct cred *old,
@@ -1030,7 +1031,8 @@ static inline int security_kernel_post_load_data(char *buf, loff_t size,
 }
 
 static inline int security_kernel_read_file(struct file *file,
-					    enum kernel_read_file_id id)
+					    enum kernel_read_file_id id,
+					    bool contents)
 {
 	return 0;
 }
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index 6f2b8352573a..939f53d02627 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -602,6 +602,7 @@ void ima_post_path_mknod(struct dentry *dentry)
  * ima_read_file - pre-measure/appraise hook decision based on policy
  * @file: pointer to the file to be measured/appraised/audit
  * @read_id: caller identifier
+ * @contents: whether a subsequent call will be made to ima_post_read_file()
  *
  * Permit reading a file based on policy. The policy rules are written
  * in terms of the policy identifier.  Appraising the integrity of
@@ -609,8 +610,15 @@ void ima_post_path_mknod(struct dentry *dentry)
  *
  * For permission return 0, otherwise return -EACCES.
  */
-int ima_read_file(struct file *file, enum kernel_read_file_id read_id)
+int ima_read_file(struct file *file, enum kernel_read_file_id read_id,
+		  bool contents)
 {
+	/* Reject all partial reads during appraisal. */
+	if (!contents) {
+		if (ima_appraise & IMA_APPRAISE_ENFORCE)
+			return -EACCES;
+	}
+
 	/*
 	 * Do devices using pre-allocated memory run the risk of the
 	 * firmware being accessible to the device prior to the completion
diff --git a/security/loadpin/loadpin.c b/security/loadpin/loadpin.c
index 28782412febb..b12f7d986b1e 100644
--- a/security/loadpin/loadpin.c
+++ b/security/loadpin/loadpin.c
@@ -118,11 +118,21 @@ static void loadpin_sb_free_security(struct super_block *mnt_sb)
 	}
 }
 
-static int loadpin_read_file(struct file *file, enum kernel_read_file_id id)
+static int loadpin_read_file(struct file *file, enum kernel_read_file_id id,
+			     bool contents)
 {
 	struct super_block *load_root;
 	const char *origin = kernel_read_file_id_str(id);
 
+	/*
+	 * If we will not know that we'll be seeing the full contents
+	 * then we cannot trust a load will be complete and unchanged
+	 * off disk. Treat all contents=false hooks as if there were
+	 * no associated file struct.
+	 */
+	if (!contents)
+		file = NULL;
+
 	/* If the file id is excluded, ignore the pinning. */
 	if ((unsigned int)id < ARRAY_SIZE(ignore_read_file_id) &&
 	    ignore_read_file_id[id]) {
@@ -179,7 +189,7 @@ static int loadpin_read_file(struct file *file, enum kernel_read_file_id id)
 
 static int loadpin_load_data(enum kernel_load_data_id id, bool contents)
 {
-	return loadpin_read_file(NULL, (enum kernel_read_file_id) id);
+	return loadpin_read_file(NULL, (enum kernel_read_file_id) id, contents);
 }
 
 static struct security_hook_list loadpin_hooks[] __lsm_ro_after_init = {
diff --git a/security/security.c b/security/security.c
index 531b855826fc..a28045dc9e7f 100644
--- a/security/security.c
+++ b/security/security.c
@@ -1672,14 +1672,15 @@ int security_kernel_module_request(char *kmod_name)
 	return integrity_kernel_module_request(kmod_name);
 }
 
-int security_kernel_read_file(struct file *file, enum kernel_read_file_id id)
+int security_kernel_read_file(struct file *file, enum kernel_read_file_id id,
+			      bool contents)
 {
 	int ret;
 
-	ret = call_int_hook(kernel_read_file, 0, file, id);
+	ret = call_int_hook(kernel_read_file, 0, file, id, contents);
 	if (ret)
 		return ret;
-	return ima_read_file(file, id);
+	return ima_read_file(file, id, contents);
 }
 EXPORT_SYMBOL_GPL(security_kernel_read_file);
 
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 558beee97d8d..dec654d52b68 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -4003,13 +4003,14 @@ static int selinux_kernel_module_from_file(struct file *file)
 }
 
 static int selinux_kernel_read_file(struct file *file,
-				    enum kernel_read_file_id id)
+				    enum kernel_read_file_id id,
+				    bool contents)
 {
 	int rc = 0;
 
 	switch (id) {
 	case READING_MODULE:
-		rc = selinux_kernel_module_from_file(file);
+		rc = selinux_kernel_module_from_file(contents ? file : NULL);
 		break;
 	default:
 		break;
-- 
cgit v1.2.3


From 0fa8e084648779eeb8929ae004301b3acf3bad84 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 2 Oct 2020 10:38:25 -0700
Subject: fs/kernel_file_read: Add "offset" arg for partial reads

To perform partial reads, callers of kernel_read_file*() must have a
non-NULL file_size argument and a preallocated buffer. The new "offset"
argument can then be used to seek to specific locations in the file to
fill the buffer to, at most, "buf_size" per call.

Where possible, the LSM hooks can report whether a full file has been
read or not so that the contents can be reasoned about.

Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20201002173828.2099543-14-keescook@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/firmware_loader/main.c |  2 +-
 fs/kernel_read_file.c               | 78 +++++++++++++++++++++++++------------
 include/linux/kernel_read_file.h    |  8 ++--
 kernel/kexec_file.c                 |  4 +-
 kernel/module.c                     |  2 +-
 security/integrity/digsig.c         |  2 +-
 security/integrity/ima/ima_fs.c     |  3 +-
 7 files changed, 65 insertions(+), 34 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c
index d9a180148c4b..79f86466d472 100644
--- a/drivers/base/firmware_loader/main.c
+++ b/drivers/base/firmware_loader/main.c
@@ -499,7 +499,7 @@ fw_get_filesystem_firmware(struct device *device, struct fw_priv *fw_priv,
 		fw_priv->size = 0;
 
 		/* load firmware files from the mount namespace of init */
-		rc = kernel_read_file_from_path_initns(path, &buffer, msize,
+		rc = kernel_read_file_from_path_initns(path, 0, &buffer, msize,
 						       NULL,
 						       READING_FIRMWARE);
 		if (rc < 0) {
diff --git a/fs/kernel_read_file.c b/fs/kernel_read_file.c
index d73bc3fa710a..90d255fbdd9b 100644
--- a/fs/kernel_read_file.c
+++ b/fs/kernel_read_file.c
@@ -9,6 +9,7 @@
  * kernel_read_file() - read file contents into a kernel buffer
  *
  * @file	file to read from
+ * @offset	where to start reading from (see below).
  * @buf		pointer to a "void *" buffer for reading into (if
  *		*@buf is NULL, a buffer will be allocated, and
  *		@buf_size will be ignored)
@@ -19,19 +20,31 @@
  * @id		the kernel_read_file_id identifying the type of
  *		file contents being read (for LSMs to examine)
  *
+ * @offset must be 0 unless both @buf and @file_size are non-NULL
+ * (i.e. the caller must be expecting to read partial file contents
+ * via an already-allocated @buf, in at most @buf_size chunks, and
+ * will be able to determine when the entire file was read by
+ * checking @file_size). This isn't a recommended way to read a
+ * file, though, since it is possible that the contents might
+ * change between calls to kernel_read_file().
+ *
  * Returns number of bytes read (no single read will be bigger
  * than INT_MAX), or negative on error.
  *
  */
-int kernel_read_file(struct file *file, void **buf,
+int kernel_read_file(struct file *file, loff_t offset, void **buf,
 		     size_t buf_size, size_t *file_size,
 		     enum kernel_read_file_id id)
 {
 	loff_t i_size, pos;
-	ssize_t bytes = 0;
+	size_t copied;
 	void *allocated = NULL;
+	bool whole_file;
 	int ret;
 
+	if (offset != 0 && (!*buf || !file_size))
+		return -EINVAL;
+
 	if (!S_ISREG(file_inode(file)->i_mode))
 		return -EINVAL;
 
@@ -39,19 +52,27 @@ int kernel_read_file(struct file *file, void **buf,
 	if (ret)
 		return ret;
 
-	ret = security_kernel_read_file(file, id, true);
-	if (ret)
-		goto out;
-
 	i_size = i_size_read(file_inode(file));
 	if (i_size <= 0) {
 		ret = -EINVAL;
 		goto out;
 	}
-	if (i_size > INT_MAX || i_size > buf_size) {
+	/* The file is too big for sane activities. */
+	if (i_size > INT_MAX) {
+		ret = -EFBIG;
+		goto out;
+	}
+	/* The entire file cannot be read in one buffer. */
+	if (!file_size && offset == 0 && i_size > buf_size) {
 		ret = -EFBIG;
 		goto out;
 	}
+
+	whole_file = (offset == 0 && i_size <= buf_size);
+	ret = security_kernel_read_file(file, id, whole_file);
+	if (ret)
+		goto out;
+
 	if (file_size)
 		*file_size = i_size;
 
@@ -62,9 +83,14 @@ int kernel_read_file(struct file *file, void **buf,
 		goto out;
 	}
 
-	pos = 0;
-	while (pos < i_size) {
-		bytes = kernel_read(file, *buf + pos, i_size - pos, &pos);
+	pos = offset;
+	copied = 0;
+	while (copied < buf_size) {
+		ssize_t bytes;
+		size_t wanted = min_t(size_t, buf_size - copied,
+					      i_size - pos);
+
+		bytes = kernel_read(file, *buf + copied, wanted, &pos);
 		if (bytes < 0) {
 			ret = bytes;
 			goto out_free;
@@ -72,14 +98,17 @@ int kernel_read_file(struct file *file, void **buf,
 
 		if (bytes == 0)
 			break;
+		copied += bytes;
 	}
 
-	if (pos != i_size) {
-		ret = -EIO;
-		goto out_free;
-	}
+	if (whole_file) {
+		if (pos != i_size) {
+			ret = -EIO;
+			goto out_free;
+		}
 
-	ret = security_kernel_post_read_file(file, *buf, i_size, id);
+		ret = security_kernel_post_read_file(file, *buf, i_size, id);
+	}
 
 out_free:
 	if (ret < 0) {
@@ -91,11 +120,11 @@ out_free:
 
 out:
 	allow_write_access(file);
-	return ret == 0 ? pos : ret;
+	return ret == 0 ? copied : ret;
 }
 EXPORT_SYMBOL_GPL(kernel_read_file);
 
-int kernel_read_file_from_path(const char *path, void **buf,
+int kernel_read_file_from_path(const char *path, loff_t offset, void **buf,
 			       size_t buf_size, size_t *file_size,
 			       enum kernel_read_file_id id)
 {
@@ -109,14 +138,15 @@ int kernel_read_file_from_path(const char *path, void **buf,
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	ret = kernel_read_file(file, buf, buf_size, file_size, id);
+	ret = kernel_read_file(file, offset, buf, buf_size, file_size, id);
 	fput(file);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(kernel_read_file_from_path);
 
-int kernel_read_file_from_path_initns(const char *path, void **buf,
-				      size_t buf_size, size_t *file_size,
+int kernel_read_file_from_path_initns(const char *path, loff_t offset,
+				      void **buf, size_t buf_size,
+				      size_t *file_size,
 				      enum kernel_read_file_id id)
 {
 	struct file *file;
@@ -135,14 +165,14 @@ int kernel_read_file_from_path_initns(const char *path, void **buf,
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	ret = kernel_read_file(file, buf, buf_size, file_size, id);
+	ret = kernel_read_file(file, offset, buf, buf_size, file_size, id);
 	fput(file);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(kernel_read_file_from_path_initns);
 
-int kernel_read_file_from_fd(int fd, void **buf, size_t buf_size,
-			     size_t *file_size,
+int kernel_read_file_from_fd(int fd, loff_t offset, void **buf,
+			     size_t buf_size, size_t *file_size,
 			     enum kernel_read_file_id id)
 {
 	struct fd f = fdget(fd);
@@ -151,7 +181,7 @@ int kernel_read_file_from_fd(int fd, void **buf, size_t buf_size,
 	if (!f.file)
 		goto out;
 
-	ret = kernel_read_file(f.file, buf, buf_size, file_size, id);
+	ret = kernel_read_file(f.file, offset, buf, buf_size, file_size, id);
 out:
 	fdput(f);
 	return ret;
diff --git a/include/linux/kernel_read_file.h b/include/linux/kernel_read_file.h
index 023293eaf948..575ffa1031d3 100644
--- a/include/linux/kernel_read_file.h
+++ b/include/linux/kernel_read_file.h
@@ -35,19 +35,19 @@ static inline const char *kernel_read_file_id_str(enum kernel_read_file_id id)
 	return kernel_read_file_str[id];
 }
 
-int kernel_read_file(struct file *file,
+int kernel_read_file(struct file *file, loff_t offset,
 		     void **buf, size_t buf_size,
 		     size_t *file_size,
 		     enum kernel_read_file_id id);
-int kernel_read_file_from_path(const char *path,
+int kernel_read_file_from_path(const char *path, loff_t offset,
 			       void **buf, size_t buf_size,
 			       size_t *file_size,
 			       enum kernel_read_file_id id);
-int kernel_read_file_from_path_initns(const char *path,
+int kernel_read_file_from_path_initns(const char *path, loff_t offset,
 				      void **buf, size_t buf_size,
 				      size_t *file_size,
 				      enum kernel_read_file_id id);
-int kernel_read_file_from_fd(int fd,
+int kernel_read_file_from_fd(int fd, loff_t offset,
 			     void **buf, size_t buf_size,
 			     size_t *file_size,
 			     enum kernel_read_file_id id);
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index ee51c1028658..84f7316792a7 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -221,7 +221,7 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd,
 	int ret;
 	void *ldata;
 
-	ret = kernel_read_file_from_fd(kernel_fd, &image->kernel_buf,
+	ret = kernel_read_file_from_fd(kernel_fd, 0, &image->kernel_buf,
 				       INT_MAX, NULL, READING_KEXEC_IMAGE);
 	if (ret < 0)
 		return ret;
@@ -241,7 +241,7 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd,
 #endif
 	/* It is possible that there no initramfs is being loaded */
 	if (!(flags & KEXEC_FILE_NO_INITRAMFS)) {
-		ret = kernel_read_file_from_fd(initrd_fd, &image->initrd_buf,
+		ret = kernel_read_file_from_fd(initrd_fd, 0, &image->initrd_buf,
 					       INT_MAX, NULL,
 					       READING_KEXEC_INITRAMFS);
 		if (ret < 0)
diff --git a/kernel/module.c b/kernel/module.c
index adfa21dd3842..9c578e44abe7 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -4054,7 +4054,7 @@ SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags)
 		      |MODULE_INIT_IGNORE_VERMAGIC))
 		return -EINVAL;
 
-	err = kernel_read_file_from_fd(fd, &hdr, INT_MAX, NULL,
+	err = kernel_read_file_from_fd(fd, 0, &hdr, INT_MAX, NULL,
 				       READING_MODULE);
 	if (err < 0)
 		return err;
diff --git a/security/integrity/digsig.c b/security/integrity/digsig.c
index 8a523dfd7fd7..0f518dcfde05 100644
--- a/security/integrity/digsig.c
+++ b/security/integrity/digsig.c
@@ -175,7 +175,7 @@ int __init integrity_load_x509(const unsigned int id, const char *path)
 	int rc;
 	key_perm_t perm;
 
-	rc = kernel_read_file_from_path(path, &data, INT_MAX, NULL,
+	rc = kernel_read_file_from_path(path, 0, &data, INT_MAX, NULL,
 					READING_X509_CERTIFICATE);
 	if (rc < 0) {
 		pr_err("Unable to open file: %s (%d)", path, rc);
diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c
index 5fc56ccb6678..ea8ff8a07b36 100644
--- a/security/integrity/ima/ima_fs.c
+++ b/security/integrity/ima/ima_fs.c
@@ -284,7 +284,8 @@ static ssize_t ima_read_policy(char *path)
 	datap = path;
 	strsep(&datap, "\n");
 
-	rc = kernel_read_file_from_path(path, &data, INT_MAX, NULL, READING_POLICY);
+	rc = kernel_read_file_from_path(path, 0, &data, INT_MAX, NULL,
+					READING_POLICY);
 	if (rc < 0) {
 		pr_err("Unable to open file: %s (%d)", path, rc);
 		return rc;
-- 
cgit v1.2.3


From 59cdb23ca2dfef3b93411d1105409dfe9cd1f62f Mon Sep 17 00:00:00 2001
From: Scott Branden <scott.branden@broadcom.com>
Date: Fri, 2 Oct 2020 10:38:27 -0700
Subject: firmware: Add request_partial_firmware_into_buf()

Add request_partial_firmware_into_buf() to allow for portions of a
firmware file to be read into a buffer. This is needed when large firmware
must be loaded in portions from a file on memory constrained systems.

Signed-off-by: Scott Branden <scott.branden@broadcom.com>
Co-developed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20201002173828.2099543-16-keescook@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/firmware_loader/firmware.h |   4 ++
 drivers/base/firmware_loader/main.c     | 101 ++++++++++++++++++++++++++------
 include/linux/firmware.h                |  12 ++++
 3 files changed, 99 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/firmware_loader/firmware.h b/drivers/base/firmware_loader/firmware.h
index f86de5d7e0d7..63bd29fdcb9c 100644
--- a/drivers/base/firmware_loader/firmware.h
+++ b/drivers/base/firmware_loader/firmware.h
@@ -32,6 +32,8 @@
  * @FW_OPT_FALLBACK_PLATFORM: Enable fallback to device fw copy embedded in
  *	the platform's main firmware. If both this fallback and the sysfs
  *      fallback are enabled, then this fallback will be tried first.
+ * @FW_OPT_PARTIAL: Allow partial read of firmware instead of needing to read
+ *	entire file.
  */
 enum fw_opt {
 	FW_OPT_UEVENT			= BIT(0),
@@ -41,6 +43,7 @@ enum fw_opt {
 	FW_OPT_NOCACHE			= BIT(4),
 	FW_OPT_NOFALLBACK_SYSFS		= BIT(5),
 	FW_OPT_FALLBACK_PLATFORM	= BIT(6),
+	FW_OPT_PARTIAL			= BIT(7),
 };
 
 enum fw_status {
@@ -68,6 +71,7 @@ struct fw_priv {
 	void *data;
 	size_t size;
 	size_t allocated_size;
+	size_t offset;
 	u32 opt_flags;
 #ifdef CONFIG_FW_LOADER_PAGED_BUF
 	bool is_paged_buf;
diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c
index 78c8e44c08cb..78355095e00d 100644
--- a/drivers/base/firmware_loader/main.c
+++ b/drivers/base/firmware_loader/main.c
@@ -170,10 +170,19 @@ static struct fw_priv *__allocate_fw_priv(const char *fw_name,
 					  struct firmware_cache *fwc,
 					  void *dbuf,
 					  size_t size,
+					  size_t offset,
 					  u32 opt_flags)
 {
 	struct fw_priv *fw_priv;
 
+	/* For a partial read, the buffer must be preallocated. */
+	if ((opt_flags & FW_OPT_PARTIAL) && !dbuf)
+		return NULL;
+
+	/* Only partial reads are allowed to use an offset. */
+	if (offset != 0 && !(opt_flags & FW_OPT_PARTIAL))
+		return NULL;
+
 	fw_priv = kzalloc(sizeof(*fw_priv), GFP_ATOMIC);
 	if (!fw_priv)
 		return NULL;
@@ -188,6 +197,7 @@ static struct fw_priv *__allocate_fw_priv(const char *fw_name,
 	fw_priv->fwc = fwc;
 	fw_priv->data = dbuf;
 	fw_priv->allocated_size = size;
+	fw_priv->offset = offset;
 	fw_priv->opt_flags = opt_flags;
 	fw_state_init(fw_priv);
 #ifdef CONFIG_FW_LOADER_USER_HELPER
@@ -216,12 +226,17 @@ static int alloc_lookup_fw_priv(const char *fw_name,
 				struct fw_priv **fw_priv,
 				void *dbuf,
 				size_t size,
+				size_t offset,
 				u32 opt_flags)
 {
 	struct fw_priv *tmp;
 
 	spin_lock(&fwc->lock);
-	if (!(opt_flags & FW_OPT_NOCACHE)) {
+	/*
+	 * Do not merge requests that are marked to be non-cached or
+	 * are performing partial reads.
+	 */
+	if (!(opt_flags & (FW_OPT_NOCACHE | FW_OPT_PARTIAL))) {
 		tmp = __lookup_fw_priv(fw_name);
 		if (tmp) {
 			kref_get(&tmp->ref);
@@ -232,7 +247,7 @@ static int alloc_lookup_fw_priv(const char *fw_name,
 		}
 	}
 
-	tmp = __allocate_fw_priv(fw_name, fwc, dbuf, size, opt_flags);
+	tmp = __allocate_fw_priv(fw_name, fwc, dbuf, size, offset, opt_flags);
 	if (tmp) {
 		INIT_LIST_HEAD(&tmp->list);
 		if (!(opt_flags & FW_OPT_NOCACHE))
@@ -490,6 +505,9 @@ fw_get_filesystem_firmware(struct device *device, struct fw_priv *fw_priv,
 		return -ENOMEM;
 
 	for (i = 0; i < ARRAY_SIZE(fw_path); i++) {
+		size_t file_size = 0;
+		size_t *file_size_ptr = NULL;
+
 		/* skip the unset customized path */
 		if (!fw_path[i][0])
 			continue;
@@ -503,9 +521,18 @@ fw_get_filesystem_firmware(struct device *device, struct fw_priv *fw_priv,
 
 		fw_priv->size = 0;
 
+		/*
+		 * The total file size is only examined when doing a partial
+		 * read; the "full read" case needs to fail if the whole
+		 * firmware was not completely loaded.
+		 */
+		if ((fw_priv->opt_flags & FW_OPT_PARTIAL) && buffer)
+			file_size_ptr = &file_size;
+
 		/* load firmware files from the mount namespace of init */
-		rc = kernel_read_file_from_path_initns(path, 0, &buffer, msize,
-						       NULL,
+		rc = kernel_read_file_from_path_initns(path, fw_priv->offset,
+						       &buffer, msize,
+						       file_size_ptr,
 						       READING_FIRMWARE);
 		if (rc < 0) {
 			if (rc != -ENOENT)
@@ -696,7 +723,7 @@ int assign_fw(struct firmware *fw, struct device *device)
 static int
 _request_firmware_prepare(struct firmware **firmware_p, const char *name,
 			  struct device *device, void *dbuf, size_t size,
-			  u32 opt_flags)
+			  size_t offset, u32 opt_flags)
 {
 	struct firmware *firmware;
 	struct fw_priv *fw_priv;
@@ -715,7 +742,7 @@ _request_firmware_prepare(struct firmware **firmware_p, const char *name,
 	}
 
 	ret = alloc_lookup_fw_priv(name, &fw_cache, &fw_priv, dbuf, size,
-				  opt_flags);
+				   offset, opt_flags);
 
 	/*
 	 * bind with 'priv' now to avoid warning in failure path
@@ -762,9 +789,10 @@ static void fw_abort_batch_reqs(struct firmware *fw)
 static int
 _request_firmware(const struct firmware **firmware_p, const char *name,
 		  struct device *device, void *buf, size_t size,
-		  u32 opt_flags)
+		  size_t offset, u32 opt_flags)
 {
 	struct firmware *fw = NULL;
+	bool nondirect = false;
 	int ret;
 
 	if (!firmware_p)
@@ -776,18 +804,22 @@ _request_firmware(const struct firmware **firmware_p, const char *name,
 	}
 
 	ret = _request_firmware_prepare(&fw, name, device, buf, size,
-					opt_flags);
+					offset, opt_flags);
 	if (ret <= 0) /* error or already assigned */
 		goto out;
 
 	ret = fw_get_filesystem_firmware(device, fw->priv, "", NULL);
+
+	/* Only full reads can support decompression, platform, and sysfs. */
+	if (!(opt_flags & FW_OPT_PARTIAL))
+		nondirect = true;
+
 #ifdef CONFIG_FW_LOADER_COMPRESS
-	if (ret == -ENOENT)
+	if (ret == -ENOENT && nondirect)
 		ret = fw_get_filesystem_firmware(device, fw->priv, ".xz",
 						 fw_decompress_xz);
 #endif
-
-	if (ret == -ENOENT)
+	if (ret == -ENOENT && nondirect)
 		ret = firmware_fallback_platform(fw->priv);
 
 	if (ret) {
@@ -795,7 +827,9 @@ _request_firmware(const struct firmware **firmware_p, const char *name,
 			dev_warn(device,
 				 "Direct firmware load for %s failed with error %d\n",
 				 name, ret);
-		ret = firmware_fallback_sysfs(fw, name, device, opt_flags, ret);
+		if (nondirect)
+			ret = firmware_fallback_sysfs(fw, name, device,
+						      opt_flags, ret);
 	} else
 		ret = assign_fw(fw, device);
 
@@ -838,7 +872,7 @@ request_firmware(const struct firmware **firmware_p, const char *name,
 
 	/* Need to pin this module until return */
 	__module_get(THIS_MODULE);
-	ret = _request_firmware(firmware_p, name, device, NULL, 0,
+	ret = _request_firmware(firmware_p, name, device, NULL, 0, 0,
 				FW_OPT_UEVENT);
 	module_put(THIS_MODULE);
 	return ret;
@@ -865,7 +899,7 @@ int firmware_request_nowarn(const struct firmware **firmware, const char *name,
 
 	/* Need to pin this module until return */
 	__module_get(THIS_MODULE);
-	ret = _request_firmware(firmware, name, device, NULL, 0,
+	ret = _request_firmware(firmware, name, device, NULL, 0, 0,
 				FW_OPT_UEVENT | FW_OPT_NO_WARN);
 	module_put(THIS_MODULE);
 	return ret;
@@ -889,7 +923,7 @@ int request_firmware_direct(const struct firmware **firmware_p,
 	int ret;
 
 	__module_get(THIS_MODULE);
-	ret = _request_firmware(firmware_p, name, device, NULL, 0,
+	ret = _request_firmware(firmware_p, name, device, NULL, 0, 0,
 				FW_OPT_UEVENT | FW_OPT_NO_WARN |
 				FW_OPT_NOFALLBACK_SYSFS);
 	module_put(THIS_MODULE);
@@ -914,7 +948,7 @@ int firmware_request_platform(const struct firmware **firmware,
 
 	/* Need to pin this module until return */
 	__module_get(THIS_MODULE);
-	ret = _request_firmware(firmware, name, device, NULL, 0,
+	ret = _request_firmware(firmware, name, device, NULL, 0, 0,
 				FW_OPT_UEVENT | FW_OPT_FALLBACK_PLATFORM);
 	module_put(THIS_MODULE);
 	return ret;
@@ -970,13 +1004,44 @@ request_firmware_into_buf(const struct firmware **firmware_p, const char *name,
 		return -EOPNOTSUPP;
 
 	__module_get(THIS_MODULE);
-	ret = _request_firmware(firmware_p, name, device, buf, size,
+	ret = _request_firmware(firmware_p, name, device, buf, size, 0,
 				FW_OPT_UEVENT | FW_OPT_NOCACHE);
 	module_put(THIS_MODULE);
 	return ret;
 }
 EXPORT_SYMBOL(request_firmware_into_buf);
 
+/**
+ * request_partial_firmware_into_buf() - load partial firmware into a previously allocated buffer
+ * @firmware_p: pointer to firmware image
+ * @name: name of firmware file
+ * @device: device for which firmware is being loaded and DMA region allocated
+ * @buf: address of buffer to load firmware into
+ * @size: size of buffer
+ * @offset: offset into file to read
+ *
+ * This function works pretty much like request_firmware_into_buf except
+ * it allows a partial read of the file.
+ */
+int
+request_partial_firmware_into_buf(const struct firmware **firmware_p,
+				  const char *name, struct device *device,
+				  void *buf, size_t size, size_t offset)
+{
+	int ret;
+
+	if (fw_cache_is_setup(device, name))
+		return -EOPNOTSUPP;
+
+	__module_get(THIS_MODULE);
+	ret = _request_firmware(firmware_p, name, device, buf, size, offset,
+				FW_OPT_UEVENT | FW_OPT_NOCACHE |
+				FW_OPT_PARTIAL);
+	module_put(THIS_MODULE);
+	return ret;
+}
+EXPORT_SYMBOL(request_partial_firmware_into_buf);
+
 /**
  * release_firmware() - release the resource associated with a firmware image
  * @fw: firmware resource to release
@@ -1009,7 +1074,7 @@ static void request_firmware_work_func(struct work_struct *work)
 
 	fw_work = container_of(work, struct firmware_work, work);
 
-	_request_firmware(&fw, fw_work->name, fw_work->device, NULL, 0,
+	_request_firmware(&fw, fw_work->name, fw_work->device, NULL, 0, 0,
 			  fw_work->opt_flags);
 	fw_work->cont(fw, fw_work->context);
 	put_device(fw_work->device); /* taken in request_firmware_nowait() */
diff --git a/include/linux/firmware.h b/include/linux/firmware.h
index cb3e2c06ed8a..c15acadc6cf4 100644
--- a/include/linux/firmware.h
+++ b/include/linux/firmware.h
@@ -53,6 +53,9 @@ int request_firmware_direct(const struct firmware **fw, const char *name,
 			    struct device *device);
 int request_firmware_into_buf(const struct firmware **firmware_p,
 	const char *name, struct device *device, void *buf, size_t size);
+int request_partial_firmware_into_buf(const struct firmware **firmware_p,
+				      const char *name, struct device *device,
+				      void *buf, size_t size, size_t offset);
 
 void release_firmware(const struct firmware *fw);
 #else
@@ -102,6 +105,15 @@ static inline int request_firmware_into_buf(const struct firmware **firmware_p,
 	return -EINVAL;
 }
 
+static inline int request_partial_firmware_into_buf
+					(const struct firmware **firmware_p,
+					 const char *name,
+					 struct device *device,
+					 void *buf, size_t size, size_t offset)
+{
+	return -EINVAL;
+}
+
 #endif
 
 int firmware_request_cache(struct device *device, const char *name);
-- 
cgit v1.2.3


From 10ed16662da9e28a33b6c991c36c6b323b03dd5b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 25 Sep 2020 18:06:18 +0200
Subject: block: add a bdget_part helper

All remaining callers of bdget() outside of fs/block_dev.c want to get a
reference to the struct block_device for a given struct hd_struct.  Add
a helper just for that and then mark bdget static.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/genhd.c           | 2 +-
 block/partitions/core.c | 2 +-
 fs/block_dev.c          | 9 ++++++---
 include/linux/blkdev.h  | 2 +-
 kernel/trace/blktrace.c | 9 ++-------
 5 files changed, 11 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/block/genhd.c b/block/genhd.c
index e5f17f022ec7..0a273211fec2 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1048,7 +1048,7 @@ struct block_device *bdget_disk(struct gendisk *disk, int partno)
 
 	part = disk_get_part(disk, partno);
 	if (part)
-		bdev = bdget(part_devt(part));
+		bdev = bdget_part(part);
 	disk_put_part(part);
 
 	return bdev;
diff --git a/block/partitions/core.c b/block/partitions/core.c
index dd6811422a87..5309e0f44ba3 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -580,7 +580,7 @@ int bdev_resize_partition(struct block_device *bdev, int partno,
 		return -ENXIO;
 
 	ret = -ENOMEM;
-	bdevp = bdget(part_devt(part));
+	bdevp = bdget_part(part);
 	if (!bdevp)
 		goto out_put_part;
 
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 6b9d19ffa5af..9e84b1928b94 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -891,7 +891,7 @@ static int bdev_set(struct inode *inode, void *data)
 	return 0;
 }
 
-struct block_device *bdget(dev_t dev)
+static struct block_device *bdget(dev_t dev)
 {
 	struct block_device *bdev;
 	struct inode *inode;
@@ -920,8 +920,6 @@ struct block_device *bdget(dev_t dev)
 	return bdev;
 }
 
-EXPORT_SYMBOL(bdget);
-
 /**
  * bdgrab -- Grab a reference to an already referenced block device
  * @bdev:	Block device to grab a reference to.
@@ -933,6 +931,11 @@ struct block_device *bdgrab(struct block_device *bdev)
 }
 EXPORT_SYMBOL(bdgrab);
 
+struct block_device *bdget_part(struct hd_struct *part)
+{
+	return bdget(part_devt(part));
+}
+
 long nr_blockdev_pages(void)
 {
 	struct inode *inode;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index d5a3e1a4c2f7..cf80e61b4c5e 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -2003,7 +2003,7 @@ void bd_abort_claiming(struct block_device *bdev, struct block_device *whole,
 void blkdev_put(struct block_device *bdev, fmode_t mode);
 
 struct block_device *I_BDEV(struct inode *inode);
-struct block_device *bdget(dev_t);
+struct block_device *bdget_part(struct hd_struct *part);
 struct block_device *bdgrab(struct block_device *bdev);
 void bdput(struct block_device *);
 
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index ec874ea04092..f1022945e346 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -1827,13 +1827,11 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
 					 struct device_attribute *attr,
 					 char *buf)
 {
-	struct hd_struct *p = dev_to_part(dev);
+	struct block_device *bdev = bdget_part(dev_to_part(dev));
 	struct request_queue *q;
-	struct block_device *bdev;
 	struct blk_trace *bt;
 	ssize_t ret = -ENXIO;
 
-	bdev = bdget(part_devt(p));
 	if (bdev == NULL)
 		goto out;
 
@@ -1875,7 +1873,6 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 {
 	struct block_device *bdev;
 	struct request_queue *q;
-	struct hd_struct *p;
 	struct blk_trace *bt;
 	u64 value;
 	ssize_t ret = -EINVAL;
@@ -1895,9 +1892,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 		goto out;
 
 	ret = -ENXIO;
-
-	p = dev_to_part(dev);
-	bdev = bdget(part_devt(p));
+	bdev = bdget_part(dev_to_part(dev));
 	if (bdev == NULL)
 		goto out;
 
-- 
cgit v1.2.3


From 07560151db960d26b425410d6fd778e6757a5da2 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Tue, 15 Sep 2020 20:53:13 -0700
Subject: block: make bio_crypt_clone() able to fail

bio_crypt_clone() assumes its gfp_mask argument always includes
__GFP_DIRECT_RECLAIM, so that the mempool_alloc() will always succeed.

However, bio_crypt_clone() might be called with GFP_ATOMIC via
setup_clone() in drivers/md/dm-rq.c, or with GFP_NOWAIT via
kcryptd_io_read() in drivers/md/dm-crypt.c.

Neither case is currently reachable with a bio that actually has an
encryption context.  However, it's fragile to rely on this.  Just make
bio_crypt_clone() able to fail, analogous to bio_integrity_clone().

Reported-by: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: Eric Biggers <ebiggers@google.com>
Reviewed-by: Mike Snitzer <snitzer@redhat.com>
Reviewed-by: Satya Tangirala <satyat@google.com>
Cc: Satya Tangirala <satyat@google.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio.c                | 20 +++++++++-----------
 block/blk-crypto.c         |  5 ++++-
 block/bounce.c             | 19 +++++++++----------
 drivers/md/dm.c            |  7 ++++---
 include/linux/blk-crypto.h | 20 ++++++++++++++++----
 5 files changed, 42 insertions(+), 29 deletions(-)

(limited to 'include/linux')

diff --git a/block/bio.c b/block/bio.c
index a9931f23d933..b42e046b12eb 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -713,20 +713,18 @@ struct bio *bio_clone_fast(struct bio *bio, gfp_t gfp_mask, struct bio_set *bs)
 
 	__bio_clone_fast(b, bio);
 
-	bio_crypt_clone(b, bio, gfp_mask);
+	if (bio_crypt_clone(b, bio, gfp_mask) < 0)
+		goto err_put;
 
-	if (bio_integrity(bio)) {
-		int ret;
-
-		ret = bio_integrity_clone(b, bio, gfp_mask);
-
-		if (ret < 0) {
-			bio_put(b);
-			return NULL;
-		}
-	}
+	if (bio_integrity(bio) &&
+	    bio_integrity_clone(b, bio, gfp_mask) < 0)
+		goto err_put;
 
 	return b;
+
+err_put:
+	bio_put(b);
+	return NULL;
 }
 EXPORT_SYMBOL(bio_clone_fast);
 
diff --git a/block/blk-crypto.c b/block/blk-crypto.c
index 2d5e60023b08..a3f27a19067c 100644
--- a/block/blk-crypto.c
+++ b/block/blk-crypto.c
@@ -95,10 +95,13 @@ void __bio_crypt_free_ctx(struct bio *bio)
 	bio->bi_crypt_context = NULL;
 }
 
-void __bio_crypt_clone(struct bio *dst, struct bio *src, gfp_t gfp_mask)
+int __bio_crypt_clone(struct bio *dst, struct bio *src, gfp_t gfp_mask)
 {
 	dst->bi_crypt_context = mempool_alloc(bio_crypt_ctx_pool, gfp_mask);
+	if (!dst->bi_crypt_context)
+		return -ENOMEM;
 	*dst->bi_crypt_context = *src->bi_crypt_context;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(__bio_crypt_clone);
 
diff --git a/block/bounce.c b/block/bounce.c
index 431be88a0240..162a6eee8999 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -267,22 +267,21 @@ static struct bio *bounce_clone_bio(struct bio *bio_src, gfp_t gfp_mask,
 		break;
 	}
 
-	bio_crypt_clone(bio, bio_src, gfp_mask);
+	if (bio_crypt_clone(bio, bio_src, gfp_mask) < 0)
+		goto err_put;
 
-	if (bio_integrity(bio_src)) {
-		int ret;
-
-		ret = bio_integrity_clone(bio, bio_src, gfp_mask);
-		if (ret < 0) {
-			bio_put(bio);
-			return NULL;
-		}
-	}
+	if (bio_integrity(bio_src) &&
+	    bio_integrity_clone(bio, bio_src, gfp_mask) < 0)
+		goto err_put;
 
 	bio_clone_blkg_association(bio, bio_src);
 	blkcg_bio_issue_init(bio);
 
 	return bio;
+
+err_put:
+	bio_put(bio);
+	return NULL;
 }
 
 static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 59b0687f9235..e959cd74cd4b 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1326,14 +1326,15 @@ static int clone_bio(struct dm_target_io *tio, struct bio *bio,
 		     sector_t sector, unsigned len)
 {
 	struct bio *clone = &tio->clone;
+	int r;
 
 	__bio_clone_fast(clone, bio);
 
-	bio_crypt_clone(clone, bio, GFP_NOIO);
+	r = bio_crypt_clone(clone, bio, GFP_NOIO);
+	if (r < 0)
+		return r;
 
 	if (bio_integrity(bio)) {
-		int r;
-
 		if (unlikely(!dm_target_has_integrity(tio->ti->type) &&
 			     !dm_target_passes_integrity(tio->ti->type))) {
 			DMWARN("%s: the target %s doesn't support integrity data.",
diff --git a/include/linux/blk-crypto.h b/include/linux/blk-crypto.h
index e82342907f2b..69b24fe92cbf 100644
--- a/include/linux/blk-crypto.h
+++ b/include/linux/blk-crypto.h
@@ -112,12 +112,24 @@ static inline bool bio_has_crypt_ctx(struct bio *bio)
 
 #endif /* CONFIG_BLK_INLINE_ENCRYPTION */
 
-void __bio_crypt_clone(struct bio *dst, struct bio *src, gfp_t gfp_mask);
-static inline void bio_crypt_clone(struct bio *dst, struct bio *src,
-				   gfp_t gfp_mask)
+int __bio_crypt_clone(struct bio *dst, struct bio *src, gfp_t gfp_mask);
+/**
+ * bio_crypt_clone - clone bio encryption context
+ * @dst: destination bio
+ * @src: source bio
+ * @gfp_mask: memory allocation flags
+ *
+ * If @src has an encryption context, clone it to @dst.
+ *
+ * Return: 0 on success, -ENOMEM if out of memory.  -ENOMEM is only possible if
+ *	   @gfp_mask doesn't include %__GFP_DIRECT_RECLAIM.
+ */
+static inline int bio_crypt_clone(struct bio *dst, struct bio *src,
+				  gfp_t gfp_mask)
 {
 	if (bio_has_crypt_ctx(src))
-		__bio_crypt_clone(dst, src, gfp_mask);
+		return __bio_crypt_clone(dst, src, gfp_mask);
+	return 0;
 }
 
 #endif /* __LINUX_BLK_CRYPTO_H */
-- 
cgit v1.2.3


From 3a6f0fb7b8eb5ef0447da1332225b8c87ee207d0 Mon Sep 17 00:00:00 2001
From: Laxminath Kasam <lkasam@codeaurora.org>
Date: Mon, 5 Oct 2020 19:47:19 +0530
Subject: regmap: irq: Add support to clear ack registers

For particular codec HWs have requirement to toggle interrupt clear
register twice 0->1->0. To accommodate it, need to add one more field
(clear_ack) in the regmap_irq struct and update regmap-irq driver to
support it.

Signed-off-by: Laxminath Kasam <lkasam@codeaurora.org>
Link: https://lore.kernel.org/r/1601907440-13373-1-git-send-email-lkasam@codeaurora.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/base/regmap/regmap-irq.c | 33 ++++++++++++++++++++++++++++++++-
 include/linux/regmap.h           |  2 ++
 2 files changed, 34 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c
index 369a57e6f89d..ad5c2de395d1 100644
--- a/drivers/base/regmap/regmap-irq.c
+++ b/drivers/base/regmap/regmap-irq.c
@@ -168,6 +168,14 @@ static void regmap_irq_sync_unlock(struct irq_data *data)
 				ret = regmap_write(map, reg, ~d->mask_buf[i]);
 			else
 				ret = regmap_write(map, reg, d->mask_buf[i]);
+			if (d->chip->clear_ack) {
+				if (d->chip->ack_invert && !ret)
+					ret = regmap_write(map, reg,
+							   d->mask_buf[i]);
+				else if (!ret)
+					ret = regmap_write(map, reg,
+							   ~d->mask_buf[i]);
+			}
 			if (ret != 0)
 				dev_err(d->map->dev, "Failed to ack 0x%x: %d\n",
 					reg, ret);
@@ -493,7 +501,20 @@ static irqreturn_t regmap_irq_thread(int irq, void *d)
 		if (data->status_buf[i] && (chip->ack_base || chip->use_ack)) {
 			reg = chip->ack_base +
 				(i * map->reg_stride * data->irq_reg_stride);
-			ret = regmap_write(map, reg, data->status_buf[i]);
+			if (chip->ack_invert)
+				ret = regmap_write(map, reg,
+						~data->status_buf[i]);
+			else
+				ret = regmap_write(map, reg,
+						data->status_buf[i]);
+			if (chip->clear_ack) {
+				if (chip->ack_invert && !ret)
+					ret = regmap_write(map, reg,
+							data->status_buf[i]);
+				else if (!ret)
+					ret = regmap_write(map, reg,
+							~data->status_buf[i]);
+			}
 			if (ret != 0)
 				dev_err(map->dev, "Failed to ack 0x%x: %d\n",
 					reg, ret);
@@ -722,6 +743,16 @@ int regmap_add_irq_chip_fwnode(struct fwnode_handle *fwnode,
 			else
 				ret = regmap_write(map, reg,
 					d->status_buf[i] & d->mask_buf[i]);
+			if (chip->clear_ack) {
+				if (chip->ack_invert && !ret)
+					ret = regmap_write(map, reg,
+						(d->status_buf[i] &
+						 d->mask_buf[i]));
+				else if (!ret)
+					ret = regmap_write(map, reg,
+						~(d->status_buf[i] &
+						  d->mask_buf[i]));
+			}
 			if (ret != 0) {
 				dev_err(map->dev, "Failed to ack 0x%x: %d\n",
 					reg, ret);
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index a35ec0a0d6e0..e7834d98207f 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -1355,6 +1355,7 @@ struct regmap_irq_sub_irq_map {
  * @mask_invert: Inverted mask register: cleared bits are masked out.
  * @use_ack:     Use @ack register even if it is zero.
  * @ack_invert:  Inverted ack register: cleared bits for ack.
+ * @clear_ack:  Use this to set 1 and 0 or vice-versa to clear interrupts.
  * @wake_invert: Inverted wake register: cleared bits are wake enabled.
  * @type_invert: Invert the type flags.
  * @type_in_mask: Use the mask registers for controlling irq type. For
@@ -1403,6 +1404,7 @@ struct regmap_irq_chip {
 	bool mask_invert:1;
 	bool use_ack:1;
 	bool ack_invert:1;
+	bool clear_ack:1;
 	bool wake_invert:1;
 	bool runtime_pm:1;
 	bool type_invert:1;
-- 
cgit v1.2.3


From 07da1223ec939982497db3caccd6215b55acc35c Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@nvidia.com>
Date: Sun, 4 Oct 2020 18:43:37 +0300
Subject: lib/scatterlist: Add support in dynamic allocation of SG table from
 pages

Extend __sg_alloc_table_from_pages to support dynamic allocation of
SG table from pages. It should be used by drivers that can't supply
all the pages at one time.

This function returns the last populated SGE in the table. Users should
pass it as an argument to the function from the second call and forward.
As before, nents will be equal to the number of populated SGEs (chunks).

With this new extension, drivers can benefit the optimization of merging
contiguous pages without a need to allocate all pages in advance and
hold them in a large buffer.

E.g. with the Infiniband driver that allocates a single page for hold the
pages. For 1TB memory registration, the temporary buffer would consume only
4KB, instead of 2GB.

Link: https://lore.kernel.org/r/20201004154340.1080481-2-leon@kernel.org
Signed-off-by: Maor Gottlieb <maorg@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/gpu/drm/i915/gem/i915_gem_userptr.c |  12 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c  |  15 ++--
 include/linux/scatterlist.h                 |  38 +++++----
 lib/scatterlist.c                           | 125 ++++++++++++++++++++++------
 tools/testing/scatterlist/main.c            |   9 +-
 5 files changed, 142 insertions(+), 57 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
index 12b30075134a..f2eaed6aca3d 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
@@ -403,6 +403,7 @@ __i915_gem_userptr_alloc_pages(struct drm_i915_gem_object *obj,
 	unsigned int max_segment = i915_sg_segment_size();
 	struct sg_table *st;
 	unsigned int sg_page_sizes;
+	struct scatterlist *sg;
 	int ret;
 
 	st = kmalloc(sizeof(*st), GFP_KERNEL);
@@ -410,13 +411,12 @@ __i915_gem_userptr_alloc_pages(struct drm_i915_gem_object *obj,
 		return ERR_PTR(-ENOMEM);
 
 alloc_table:
-	ret = __sg_alloc_table_from_pages(st, pvec, num_pages,
-					  0, num_pages << PAGE_SHIFT,
-					  max_segment,
-					  GFP_KERNEL);
-	if (ret) {
+	sg = __sg_alloc_table_from_pages(st, pvec, num_pages, 0,
+					 num_pages << PAGE_SHIFT, max_segment,
+					 NULL, 0, GFP_KERNEL);
+	if (IS_ERR(sg)) {
 		kfree(st);
-		return ERR_PTR(ret);
+		return ERR_CAST(sg);
 	}
 
 	ret = i915_gem_gtt_prepare_pages(obj, st);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
index ab524ab3b0b4..f22acd398b1f 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
@@ -419,6 +419,7 @@ static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt)
 	int ret = 0;
 	static size_t sgl_size;
 	static size_t sgt_size;
+	struct scatterlist *sg;
 
 	if (vmw_tt->mapped)
 		return 0;
@@ -441,13 +442,15 @@ static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt)
 		if (unlikely(ret != 0))
 			return ret;
 
-		ret = __sg_alloc_table_from_pages
-			(&vmw_tt->sgt, vsgt->pages, vsgt->num_pages, 0,
-			 (unsigned long) vsgt->num_pages << PAGE_SHIFT,
-			 dma_get_max_seg_size(dev_priv->dev->dev),
-			 GFP_KERNEL);
-		if (unlikely(ret != 0))
+		sg = __sg_alloc_table_from_pages(&vmw_tt->sgt, vsgt->pages,
+				vsgt->num_pages, 0,
+				(unsigned long) vsgt->num_pages << PAGE_SHIFT,
+				dma_get_max_seg_size(dev_priv->dev->dev),
+				NULL, 0, GFP_KERNEL);
+		if (IS_ERR(sg)) {
+			ret = PTR_ERR(sg);
 			goto out_sg_alloc_fail;
+		}
 
 		if (vsgt->num_pages > vmw_tt->sgt.nents) {
 			uint64_t over_alloc =
diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h
index 45cf7b69d852..36c47e7e66a2 100644
--- a/include/linux/scatterlist.h
+++ b/include/linux/scatterlist.h
@@ -165,6 +165,22 @@ static inline void sg_set_buf(struct scatterlist *sg, const void *buf,
 #define for_each_sgtable_dma_sg(sgt, sg, i)	\
 	for_each_sg((sgt)->sgl, sg, (sgt)->nents, i)
 
+static inline void __sg_chain(struct scatterlist *chain_sg,
+			      struct scatterlist *sgl)
+{
+	/*
+	 * offset and length are unused for chain entry. Clear them.
+	 */
+	chain_sg->offset = 0;
+	chain_sg->length = 0;
+
+	/*
+	 * Set lowest bit to indicate a link pointer, and make sure to clear
+	 * the termination bit if it happens to be set.
+	 */
+	chain_sg->page_link = ((unsigned long) sgl | SG_CHAIN) & ~SG_END;
+}
+
 /**
  * sg_chain - Chain two sglists together
  * @prv:	First scatterlist
@@ -178,18 +194,7 @@ static inline void sg_set_buf(struct scatterlist *sg, const void *buf,
 static inline void sg_chain(struct scatterlist *prv, unsigned int prv_nents,
 			    struct scatterlist *sgl)
 {
-	/*
-	 * offset and length are unused for chain entry.  Clear them.
-	 */
-	prv[prv_nents - 1].offset = 0;
-	prv[prv_nents - 1].length = 0;
-
-	/*
-	 * Set lowest bit to indicate a link pointer, and make sure to clear
-	 * the termination bit if it happens to be set.
-	 */
-	prv[prv_nents - 1].page_link = ((unsigned long) sgl | SG_CHAIN)
-					& ~SG_END;
+	__sg_chain(&prv[prv_nents - 1], sgl);
 }
 
 /**
@@ -286,10 +291,11 @@ void sg_free_table(struct sg_table *);
 int __sg_alloc_table(struct sg_table *, unsigned int, unsigned int,
 		     struct scatterlist *, unsigned int, gfp_t, sg_alloc_fn *);
 int sg_alloc_table(struct sg_table *, unsigned int, gfp_t);
-int __sg_alloc_table_from_pages(struct sg_table *sgt, struct page **pages,
-				unsigned int n_pages, unsigned int offset,
-				unsigned long size, unsigned int max_segment,
-				gfp_t gfp_mask);
+struct scatterlist *__sg_alloc_table_from_pages(struct sg_table *sgt,
+		struct page **pages, unsigned int n_pages, unsigned int offset,
+		unsigned long size, unsigned int max_segment,
+		struct scatterlist *prv, unsigned int left_pages,
+		gfp_t gfp_mask);
 int sg_alloc_table_from_pages(struct sg_table *sgt, struct page **pages,
 			      unsigned int n_pages, unsigned int offset,
 			      unsigned long size, gfp_t gfp_mask);
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index 5d63a8857f36..e102fdfaa75b 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -365,6 +365,37 @@ int sg_alloc_table(struct sg_table *table, unsigned int nents, gfp_t gfp_mask)
 }
 EXPORT_SYMBOL(sg_alloc_table);
 
+static struct scatterlist *get_next_sg(struct sg_table *table,
+				       struct scatterlist *cur,
+				       unsigned long needed_sges,
+				       gfp_t gfp_mask)
+{
+	struct scatterlist *new_sg, *next_sg;
+	unsigned int alloc_size;
+
+	if (cur) {
+		next_sg = sg_next(cur);
+		/* Check if last entry should be keeped for chainning */
+		if (!sg_is_last(next_sg) || needed_sges == 1)
+			return next_sg;
+	}
+
+	alloc_size = min_t(unsigned long, needed_sges, SG_MAX_SINGLE_ALLOC);
+	new_sg = sg_kmalloc(alloc_size, gfp_mask);
+	if (!new_sg)
+		return ERR_PTR(-ENOMEM);
+	sg_init_table(new_sg, alloc_size);
+	if (cur) {
+		__sg_chain(next_sg, new_sg);
+		table->orig_nents += alloc_size - 1;
+	} else {
+		table->sgl = new_sg;
+		table->orig_nents = alloc_size;
+		table->nents = 0;
+	}
+	return new_sg;
+}
+
 /**
  * __sg_alloc_table_from_pages - Allocate and initialize an sg table from
  *			         an array of pages
@@ -374,29 +405,63 @@ EXPORT_SYMBOL(sg_alloc_table);
  * @offset:      Offset from start of the first page to the start of a buffer
  * @size:        Number of valid bytes in the buffer (after offset)
  * @max_segment: Maximum size of a scatterlist node in bytes (page aligned)
+ * @prv:	 Last populated sge in sgt
+ * @left_pages:  Left pages caller have to set after this call
  * @gfp_mask:	 GFP allocation mask
  *
- *  Description:
- *    Allocate and initialize an sg table from a list of pages. Contiguous
- *    ranges of the pages are squashed into a single scatterlist node up to the
- *    maximum size specified in @max_segment. An user may provide an offset at a
- *    start and a size of valid data in a buffer specified by the page array.
- *    The returned sg table is released by sg_free_table.
+ * Description:
+ *    If @prv is NULL, allocate and initialize an sg table from a list of pages,
+ *    else reuse the scatterlist passed in at @prv.
+ *    Contiguous ranges of the pages are squashed into a single scatterlist
+ *    entry up to the maximum size specified in @max_segment.  A user may
+ *    provide an offset at a start and a size of valid data in a buffer
+ *    specified by the page array.
  *
  * Returns:
- *   0 on success, negative error on failure
+ *   Last SGE in sgt on success, PTR_ERR on otherwise.
+ *   The allocation in @sgt must be released by sg_free_table.
+ *
+ * Notes:
+ *   If this function returns non-0 (eg failure), the caller must call
+ *   sg_free_table() to cleanup any leftover allocations.
  */
-int __sg_alloc_table_from_pages(struct sg_table *sgt, struct page **pages,
-				unsigned int n_pages, unsigned int offset,
-				unsigned long size, unsigned int max_segment,
-				gfp_t gfp_mask)
+struct scatterlist *__sg_alloc_table_from_pages(struct sg_table *sgt,
+		struct page **pages, unsigned int n_pages, unsigned int offset,
+		unsigned long size, unsigned int max_segment,
+		struct scatterlist *prv, unsigned int left_pages,
+		gfp_t gfp_mask)
 {
-	unsigned int chunks, cur_page, seg_len, i;
-	int ret;
-	struct scatterlist *s;
+	unsigned int chunks, cur_page, seg_len, i, prv_len = 0;
+	unsigned int added_nents = 0;
+	struct scatterlist *s = prv;
 
 	if (WARN_ON(!max_segment || offset_in_page(max_segment)))
-		return -EINVAL;
+		return ERR_PTR(-EINVAL);
+
+	if (IS_ENABLED(CONFIG_ARCH_NO_SG_CHAIN) && prv)
+		return ERR_PTR(-EOPNOTSUPP);
+
+	if (prv) {
+		unsigned long paddr = (page_to_pfn(sg_page(prv)) * PAGE_SIZE +
+				       prv->offset + prv->length) /
+				      PAGE_SIZE;
+
+		if (WARN_ON(offset))
+			return ERR_PTR(-EINVAL);
+
+		/* Merge contiguous pages into the last SG */
+		prv_len = prv->length;
+		while (n_pages && page_to_pfn(pages[0]) == paddr) {
+			if (prv->length + PAGE_SIZE > max_segment)
+				break;
+			prv->length += PAGE_SIZE;
+			paddr++;
+			pages++;
+			n_pages--;
+		}
+		if (!n_pages)
+			goto out;
+	}
 
 	/* compute number of contiguous chunks */
 	chunks = 1;
@@ -410,13 +475,9 @@ int __sg_alloc_table_from_pages(struct sg_table *sgt, struct page **pages,
 		}
 	}
 
-	ret = sg_alloc_table(sgt, chunks, gfp_mask);
-	if (unlikely(ret))
-		return ret;
-
 	/* merging chunks and putting them into the scatterlist */
 	cur_page = 0;
-	for_each_sg(sgt->sgl, s, sgt->orig_nents, i) {
+	for (i = 0; i < chunks; i++) {
 		unsigned int j, chunk_size;
 
 		/* look for the end of the current chunk */
@@ -429,15 +490,30 @@ int __sg_alloc_table_from_pages(struct sg_table *sgt, struct page **pages,
 				break;
 		}
 
+		/* Pass how many chunks might be left */
+		s = get_next_sg(sgt, s, chunks - i + left_pages, gfp_mask);
+		if (IS_ERR(s)) {
+			/*
+			 * Adjust entry length to be as before function was
+			 * called.
+			 */
+			if (prv)
+				prv->length = prv_len;
+			return s;
+		}
 		chunk_size = ((j - cur_page) << PAGE_SHIFT) - offset;
 		sg_set_page(s, pages[cur_page],
 			    min_t(unsigned long, size, chunk_size), offset);
+		added_nents++;
 		size -= chunk_size;
 		offset = 0;
 		cur_page = j;
 	}
-
-	return 0;
+	sgt->nents += added_nents;
+out:
+	if (!left_pages)
+		sg_mark_end(s);
+	return s;
 }
 EXPORT_SYMBOL(__sg_alloc_table_from_pages);
 
@@ -465,8 +541,9 @@ int sg_alloc_table_from_pages(struct sg_table *sgt, struct page **pages,
 			      unsigned int n_pages, unsigned int offset,
 			      unsigned long size, gfp_t gfp_mask)
 {
-	return __sg_alloc_table_from_pages(sgt, pages, n_pages, offset, size,
-					   SCATTERLIST_MAX_SEGMENT, gfp_mask);
+	return PTR_ERR_OR_ZERO(__sg_alloc_table_from_pages(sgt, pages, n_pages,
+			offset, size, SCATTERLIST_MAX_SEGMENT,
+			NULL, 0, gfp_mask));
 }
 EXPORT_SYMBOL(sg_alloc_table_from_pages);
 
diff --git a/tools/testing/scatterlist/main.c b/tools/testing/scatterlist/main.c
index c6db0a1989b2..b2c7e9f7b8d3 100644
--- a/tools/testing/scatterlist/main.c
+++ b/tools/testing/scatterlist/main.c
@@ -79,14 +79,13 @@ int main(void)
 	for (i = 0, test = tests; test->expected_segments; test++, i++) {
 		struct page *pages[MAX_PAGES];
 		struct sg_table st;
-		int ret;
+		struct scatterlist *sg;
 
 		set_pages(pages, test->pfn, test->num_pages);
 
-		ret = __sg_alloc_table_from_pages(&st, pages, test->num_pages,
-						  0, test->size, test->max_seg,
-						  GFP_KERNEL);
-		assert(ret == test->alloc_ret);
+		sg = __sg_alloc_table_from_pages(&st, pages, test->num_pages, 0,
+				test->size, test->max_seg, NULL, 0, GFP_KERNEL);
+		assert(PTR_ERR_OR_ZERO(sg) == test->alloc_ret);
 
 		if (test->alloc_ret)
 			continue;
-- 
cgit v1.2.3


From 0a0f0d8be76dcd4390ff538e7060fda34db79717 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 22 Sep 2020 15:31:03 +0200
Subject: dma-mapping: split <linux/dma-mapping.h>

Split out all the bits that are purely for dma_map_ops implementations
and related code into a new <linux/dma-map-ops.h> header so that they
don't get pulled into all the drivers.  That also means the architecture
specific <asm/dma-mapping.h> is not pulled in by <linux/dma-mapping.h>
any more, which leads to a missing includes that were pulled in by the
x86 or arm versions in a few not overly portable drivers.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 MAINTAINERS                                 |   1 +
 arch/alpha/kernel/pci_iommu.c               |   2 +-
 arch/arc/mm/dma.c                           |   1 +
 arch/arm/common/dmabounce.c                 |   1 +
 arch/arm/mach-highbank/highbank.c           |   2 +-
 arch/arm/mach-imx/mach-imx27_visstrim_m10.c |   2 +-
 arch/arm/mach-imx/mach-mx31moboard.c        |   2 +-
 arch/arm/mach-mvebu/coherency.c             |   2 +-
 arch/arm/mm/dma-mapping-nommu.c             |   1 +
 arch/arm/mm/dma-mapping.c                   |   2 +-
 arch/arm64/mm/dma-mapping.c                 |   1 +
 arch/ia64/hp/common/sba_iommu.c             |   2 +-
 arch/ia64/kernel/dma-mapping.c              |   2 +-
 arch/mips/jazz/jazzdma.c                    |   1 +
 arch/mips/mm/dma-noncoherent.c              |   1 +
 arch/parisc/kernel/drivers.c                |   1 +
 arch/powerpc/include/asm/iommu.h            |   2 +-
 arch/powerpc/include/asm/pci.h              |   2 +-
 arch/powerpc/platforms/ps3/system-bus.c     |   2 +-
 arch/powerpc/platforms/pseries/ibmebus.c    |   2 +-
 arch/powerpc/platforms/pseries/vio.c        |   2 +-
 arch/s390/pci/pci_dma.c                     |   2 +-
 arch/sh/boards/mach-ap325rxa/setup.c        |   1 +
 arch/sh/boards/mach-ecovec24/setup.c        |   1 +
 arch/sh/boards/mach-kfr2r09/setup.c         |   2 +-
 arch/sh/boards/mach-migor/setup.c           |   2 +-
 arch/sh/boards/mach-se/7724/setup.c         |   1 +
 arch/sh/drivers/pci/fixups-dreamcast.c      |   2 +-
 arch/sparc/kernel/iommu.c                   |   2 +-
 arch/sparc/kernel/pci_sun4v.c               |   1 +
 arch/sparc/mm/io-unit.c                     |   2 +-
 arch/sparc/mm/iommu.c                       |   2 +-
 arch/x86/kernel/amd_gart_64.c               |   1 +
 arch/x86/kernel/pci-dma.c                   |   1 +
 arch/x86/kernel/setup.c                     |   2 +
 arch/x86/xen/pci-swiotlb-xen.c              |   2 +-
 drivers/acpi/arm64/iort.c                   |   2 +-
 drivers/acpi/scan.c                         |   2 +-
 drivers/base/dd.c                           |   2 +-
 drivers/gpu/drm/exynos/exynos_drm_dma.c     |   2 +-
 drivers/gpu/drm/msm/msm_gem.c               |   1 +
 drivers/iommu/dma-iommu.c                   |   1 +
 drivers/iommu/intel/iommu.c                 |   2 +-
 drivers/misc/mic/bus/mic_bus.c              |   1 +
 drivers/misc/mic/bus/scif_bus.c             |   2 +-
 drivers/misc/mic/bus/scif_bus.h             |   2 +-
 drivers/misc/mic/bus/vop_bus.c              |   2 +-
 drivers/misc/mic/host/mic_boot.c            |   1 +
 drivers/of/device.c                         |   1 +
 drivers/parisc/ccio-dma.c                   |   1 +
 drivers/parisc/sba_iommu.c                  |   1 +
 drivers/pci/xen-pcifront.c                  |   1 +
 drivers/remoteproc/remoteproc_core.c        |   1 +
 drivers/remoteproc/remoteproc_virtio.c      |   2 +-
 drivers/vdpa/vdpa_sim/vdpa_sim.c            |   2 +-
 drivers/xen/swiotlb-xen.c                   |   1 +
 include/linux/dma-map-ops.h                 | 158 ++++++++++++++++++++++++++
 include/linux/dma-mapping.h                 | 168 +---------------------------
 kernel/dma/coherent.c                       |   1 +
 kernel/dma/direct.c                         |   1 +
 kernel/dma/dummy.c                          |   2 +-
 kernel/dma/mapping.c                        |   2 +-
 kernel/dma/ops_helpers.c                    |   1 +
 kernel/dma/virt.c                           |   2 +-
 64 files changed, 223 insertions(+), 200 deletions(-)
 create mode 100644 include/linux/dma-map-ops.h

(limited to 'include/linux')

diff --git a/MAINTAINERS b/MAINTAINERS
index 190c7fa2ea01..b13fc1794307 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5202,6 +5202,7 @@ T:	git git://git.infradead.org/users/hch/dma-mapping.git
 F:	include/asm-generic/dma-mapping.h
 F:	include/linux/dma-direct.h
 F:	include/linux/dma-mapping.h
+F:	include/linux/dma-map-ops.h
 F:	include/linux/dma-noncoherent.h
 F:	kernel/dma/
 
diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c
index 447e0fd0ed38..d84b19aa8e9d 100644
--- a/arch/alpha/kernel/pci_iommu.c
+++ b/arch/alpha/kernel/pci_iommu.c
@@ -11,7 +11,7 @@
 #include <linux/export.h>
 #include <linux/scatterlist.h>
 #include <linux/log2.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/iommu-helper.h>
 
 #include <asm/io.h>
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index e947572a521e..a8c453e98d75 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -3,6 +3,7 @@
  * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
  */
 
+#include <linux/dma-map-ops.h>
 #include <linux/dma-noncoherent.h>
 #include <asm/cache.h>
 #include <asm/cacheflush.h>
diff --git a/arch/arm/common/dmabounce.c b/arch/arm/common/dmabounce.c
index d3e00ea92088..7996c04393d5 100644
--- a/arch/arm/common/dmabounce.c
+++ b/arch/arm/common/dmabounce.c
@@ -25,6 +25,7 @@
 #include <linux/page-flags.h>
 #include <linux/device.h>
 #include <linux/dma-direct.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dmapool.h>
 #include <linux/list.h>
 #include <linux/scatterlist.h>
diff --git a/arch/arm/mach-highbank/highbank.c b/arch/arm/mach-highbank/highbank.c
index 56bf29523c65..db607955a7e4 100644
--- a/arch/arm/mach-highbank/highbank.c
+++ b/arch/arm/mach-highbank/highbank.c
@@ -5,7 +5,7 @@
 #include <linux/clk.h>
 #include <linux/clkdev.h>
 #include <linux/clocksource.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/input.h>
 #include <linux/io.h>
 #include <linux/irqchip.h>
diff --git a/arch/arm/mach-imx/mach-imx27_visstrim_m10.c b/arch/arm/mach-imx/mach-imx27_visstrim_m10.c
index 3da4c0920198..a329e50928b6 100644
--- a/arch/arm/mach-imx/mach-imx27_visstrim_m10.c
+++ b/arch/arm/mach-imx/mach-imx27_visstrim_m10.c
@@ -16,7 +16,7 @@
 #include <linux/input.h>
 #include <linux/gpio.h>
 #include <linux/delay.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/leds.h>
 #include <linux/platform_data/asoc-mx27vis.h>
 #include <sound/tlv320aic32x4.h>
diff --git a/arch/arm/mach-imx/mach-mx31moboard.c b/arch/arm/mach-imx/mach-mx31moboard.c
index 96845a4eaf57..7f780ad2d459 100644
--- a/arch/arm/mach-imx/mach-mx31moboard.c
+++ b/arch/arm/mach-imx/mach-mx31moboard.c
@@ -4,7 +4,7 @@
  */
 
 #include <linux/delay.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/gfp.h>
 #include <linux/gpio.h>
 #include <linux/init.h>
diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c
index 8f8748a0c84f..49e3c8d20c2f 100644
--- a/arch/arm/mach-mvebu/coherency.c
+++ b/arch/arm/mach-mvebu/coherency.c
@@ -25,7 +25,7 @@
 #include <linux/of_address.h>
 #include <linux/io.h>
 #include <linux/smp.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/mbus.h>
diff --git a/arch/arm/mm/dma-mapping-nommu.c b/arch/arm/mm/dma-mapping-nommu.c
index 43c6d66b6e73..6bfd2b884505 100644
--- a/arch/arm/mm/dma-mapping-nommu.c
+++ b/arch/arm/mm/dma-mapping-nommu.c
@@ -8,6 +8,7 @@
 #include <linux/export.h>
 #include <linux/mm.h>
 #include <linux/dma-direct.h>
+#include <linux/dma-map-ops.h>
 #include <linux/scatterlist.h>
 
 #include <asm/cachetype.h>
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 7738b4d23f69..8bf0bc6bc311 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -15,7 +15,7 @@
 #include <linux/init.h>
 #include <linux/device.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-noncoherent.h>
 #include <linux/dma-contiguous.h>
 #include <linux/highmem.h>
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 6c45350e33aa..3afd3bd659d8 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -6,6 +6,7 @@
 
 #include <linux/gfp.h>
 #include <linux/cache.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-noncoherent.h>
 #include <linux/dma-iommu.h>
 #include <xen/xen.h>
diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c
index cafbb848a34e..9148ddbf02e5 100644
--- a/arch/ia64/hp/common/sba_iommu.c
+++ b/arch/ia64/hp/common/sba_iommu.c
@@ -33,7 +33,7 @@
 #include <linux/bitops.h>         /* hweight64() */
 #include <linux/crash_dump.h>
 #include <linux/iommu-helper.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/prefetch.h>
 #include <linux/swiotlb.h>
 
diff --git a/arch/ia64/kernel/dma-mapping.c b/arch/ia64/kernel/dma-mapping.c
index f640ed6fe1d5..cd0c166bfbc2 100644
--- a/arch/ia64/kernel/dma-mapping.c
+++ b/arch/ia64/kernel/dma-mapping.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/export.h>
 
 /* Set this to 1 if there is a HW IOMMU in the system */
diff --git a/arch/mips/jazz/jazzdma.c b/arch/mips/jazz/jazzdma.c
index f53bc043334c..b8fb42e56da0 100644
--- a/arch/mips/jazz/jazzdma.c
+++ b/arch/mips/jazz/jazzdma.c
@@ -16,6 +16,7 @@
 #include <linux/memblock.h>
 #include <linux/spinlock.h>
 #include <linux/gfp.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-noncoherent.h>
 #include <asm/mipsregs.h>
 #include <asm/jazz.h>
diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c
index f34ad1f09799..f4e8404ee049 100644
--- a/arch/mips/mm/dma-noncoherent.c
+++ b/arch/mips/mm/dma-noncoherent.c
@@ -5,6 +5,7 @@
  * swiped from i386, and cloned for MIPS by Geert, polished by Ralf.
  */
 #include <linux/dma-direct.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-noncoherent.h>
 #include <linux/dma-contiguous.h>
 #include <linux/highmem.h>
diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c
index a5f3e50fe976..80fa0650736b 100644
--- a/arch/parisc/kernel/drivers.c
+++ b/arch/parisc/kernel/drivers.c
@@ -30,6 +30,7 @@
 #include <linux/spinlock.h>
 #include <linux/string.h>
 #include <linux/export.h>
+#include <linux/dma-map-ops.h>
 #include <asm/hardware.h>
 #include <asm/io.h>
 #include <asm/pdc.h>
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 5032f1593299..deef7c94d7b6 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -12,7 +12,7 @@
 #include <linux/compiler.h>
 #include <linux/spinlock.h>
 #include <linux/device.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/bitops.h>
 #include <asm/machdep.h>
 #include <asm/types.h>
diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h
index 63ed7e3b0ba3..6436f0b41539 100644
--- a/arch/powerpc/include/asm/pci.h
+++ b/arch/powerpc/include/asm/pci.h
@@ -9,7 +9,7 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/string.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/scatterlist.h>
 
 #include <asm/machdep.h>
diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c
index 7bc5f9be3e12..c62aaa29a9d5 100644
--- a/arch/powerpc/platforms/ps3/system-bus.c
+++ b/arch/powerpc/platforms/ps3/system-bus.c
@@ -9,7 +9,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/export.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/err.h>
 #include <linux/slab.h>
 
diff --git a/arch/powerpc/platforms/pseries/ibmebus.c b/arch/powerpc/platforms/pseries/ibmebus.c
index a6f101c958e8..8c6e509f6967 100644
--- a/arch/powerpc/platforms/pseries/ibmebus.c
+++ b/arch/powerpc/platforms/pseries/ibmebus.c
@@ -40,7 +40,7 @@
 #include <linux/export.h>
 #include <linux/console.h>
 #include <linux/kobject.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/interrupt.h>
 #include <linux/of.h>
 #include <linux/slab.h>
diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
index 98ed7b09b3fe..b2797cfe4e2b 100644
--- a/arch/powerpc/platforms/pseries/vio.c
+++ b/arch/powerpc/platforms/pseries/vio.c
@@ -20,7 +20,7 @@
 #include <linux/console.h>
 #include <linux/export.h>
 #include <linux/mm.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/kobject.h>
 
 #include <asm/iommu.h>
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index 9291023e9469..ebc9a49523aa 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -10,7 +10,7 @@
 #include <linux/slab.h>
 #include <linux/export.h>
 #include <linux/iommu-helper.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/vmalloc.h>
 #include <linux/pci.h>
 #include <asm/pci_dma.h>
diff --git a/arch/sh/boards/mach-ap325rxa/setup.c b/arch/sh/boards/mach-ap325rxa/setup.c
index 665cad452798..bac8a058ebd7 100644
--- a/arch/sh/boards/mach-ap325rxa/setup.c
+++ b/arch/sh/boards/mach-ap325rxa/setup.c
@@ -13,6 +13,7 @@
 
 #include <cpu/sh7723.h>
 
+#include <linux/dma-map-ops.h>
 #include <linux/clkdev.h>
 #include <linux/delay.h>
 #include <linux/device.h>
diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c
index dd427bac5cde..bab91a99124e 100644
--- a/arch/sh/boards/mach-ecovec24/setup.c
+++ b/arch/sh/boards/mach-ecovec24/setup.c
@@ -36,6 +36,7 @@
 #include <linux/usb/r8a66597.h>
 #include <linux/usb/renesas_usbhs.h>
 #include <linux/videodev2.h>
+#include <linux/dma-map-ops.h>
 
 #include <media/drv-intf/renesas-ceu.h>
 #include <media/i2c/mt9t112.h>
diff --git a/arch/sh/boards/mach-kfr2r09/setup.c b/arch/sh/boards/mach-kfr2r09/setup.c
index 96538ba3aa32..eeb5ce341efd 100644
--- a/arch/sh/boards/mach-kfr2r09/setup.c
+++ b/arch/sh/boards/mach-kfr2r09/setup.c
@@ -14,7 +14,6 @@
 
 #include <linux/clkdev.h>
 #include <linux/delay.h>
-#include <linux/dma-mapping.h>
 #include <linux/gpio.h>
 #include <linux/gpio/machine.h>
 #include <linux/i2c.h>
@@ -33,6 +32,7 @@
 #include <linux/sh_intc.h>
 #include <linux/usb/r8a66597.h>
 #include <linux/videodev2.h>
+#include <linux/dma-map-ops.h>
 
 #include <mach/kfr2r09.h>
 
diff --git a/arch/sh/boards/mach-migor/setup.c b/arch/sh/boards/mach-migor/setup.c
index 9ed369dad62d..6703a2122c0d 100644
--- a/arch/sh/boards/mach-migor/setup.c
+++ b/arch/sh/boards/mach-migor/setup.c
@@ -5,7 +5,7 @@
  * Copyright (C) 2008 Magnus Damm
  */
 #include <linux/clkdev.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/interrupt.h>
diff --git a/arch/sh/boards/mach-se/7724/setup.c b/arch/sh/boards/mach-se/7724/setup.c
index 32f5dd944889..8d6541ba0186 100644
--- a/arch/sh/boards/mach-se/7724/setup.c
+++ b/arch/sh/boards/mach-se/7724/setup.c
@@ -32,6 +32,7 @@
 #include <linux/smc91x.h>
 #include <linux/usb/r8a66597.h>
 #include <linux/videodev2.h>
+#include <linux/dma-map-ops.h>
 
 #include <mach-se/mach/se7724.h>
 #include <media/drv-intf/renesas-ceu.h>
diff --git a/arch/sh/drivers/pci/fixups-dreamcast.c b/arch/sh/drivers/pci/fixups-dreamcast.c
index 7be8694c0d13..41e4daee8f04 100644
--- a/arch/sh/drivers/pci/fixups-dreamcast.c
+++ b/arch/sh/drivers/pci/fixups-dreamcast.c
@@ -19,7 +19,7 @@
 #include <linux/init.h>
 #include <linux/irq.h>
 #include <linux/pci.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 
 #include <asm/io.h>
 #include <asm/irq.h>
diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c
index c3e4e2df26a8..a034f571d869 100644
--- a/arch/sparc/kernel/iommu.c
+++ b/arch/sparc/kernel/iommu.c
@@ -10,7 +10,7 @@
 #include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/device.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/errno.h>
 #include <linux/iommu-helper.h>
 #include <linux/bitmap.h>
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index 6b92dd51c002..9de57e88f7a1 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
@@ -16,6 +16,7 @@
 #include <linux/export.h>
 #include <linux/log2.h>
 #include <linux/of_device.h>
+#include <linux/dma-map-ops.h>
 #include <asm/iommu-common.h>
 
 #include <asm/iommu.h>
diff --git a/arch/sparc/mm/io-unit.c b/arch/sparc/mm/io-unit.c
index 430a47a1b6ae..bf3e6d2fe5d9 100644
--- a/arch/sparc/mm/io-unit.c
+++ b/arch/sparc/mm/io-unit.c
@@ -11,7 +11,7 @@
 #include <linux/spinlock.h>
 #include <linux/mm.h>
 #include <linux/bitops.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
 
diff --git a/arch/sparc/mm/iommu.c b/arch/sparc/mm/iommu.c
index 3a388b1c5d4b..0c0342e5b10d 100644
--- a/arch/sparc/mm/iommu.c
+++ b/arch/sparc/mm/iommu.c
@@ -12,7 +12,7 @@
 #include <linux/init.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
 
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index c96dcaa572eb..9ac696487b13 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -32,6 +32,7 @@
 #include <linux/gfp.h>
 #include <linux/atomic.h>
 #include <linux/dma-direct.h>
+#include <linux/dma-map-ops.h>
 #include <asm/mtrr.h>
 #include <asm/proto.h>
 #include <asm/iommu.h>
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 5dcedad21dff..4892dd043d41 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/dma-map-ops.h>
 #include <linux/dma-direct.h>
 #include <linux/dma-debug.h>
 #include <linux/iommu.h>
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 3511736fbc74..9286fa9d575e 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -7,6 +7,7 @@
  */
 #include <linux/console.h>
 #include <linux/crash_dump.h>
+#include <linux/dma-contiguous.h>
 #include <linux/dmi.h>
 #include <linux/efi.h>
 #include <linux/init_ohci1394_dma.h>
@@ -19,6 +20,7 @@
 #include <linux/hugetlb.h>
 #include <linux/tboot.h>
 #include <linux/usb/xhci-dbgp.h>
+#include <linux/swiotlb.h>
 
 #include <uapi/linux/mount.h>
 
diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c
index 33293ce01d8d..19ae3e4fe4e9 100644
--- a/arch/x86/xen/pci-swiotlb-xen.c
+++ b/arch/x86/xen/pci-swiotlb-xen.c
@@ -2,7 +2,7 @@
 
 /* Glue code to lib/swiotlb-xen.c */
 
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/pci.h>
 #include <xen/swiotlb-xen.h>
 
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index de18c07ca02c..6446b2572f07 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -18,7 +18,7 @@
 #include <linux/pci.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 
 #define IORT_TYPE_MASK(type)	(1 << (type))
 #define IORT_MSI_TYPE		(1 << ACPI_IORT_NODE_ITS_GROUP)
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 2142f1554761..e0b7d7a605b5 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -13,7 +13,7 @@
 #include <linux/kthread.h>
 #include <linux/dmi.h>
 #include <linux/nls.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/platform_data/x86/apple.h>
 #include <linux/pgtable.h>
 
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index 857b0a928e8d..b3d43ace5c2b 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -19,7 +19,7 @@
 #include <linux/debugfs.h>
 #include <linux/device.h>
 #include <linux/delay.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/kthread.h>
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dma.c b/drivers/gpu/drm/exynos/exynos_drm_dma.c
index 58b89ec11b0e..78b8f3403c30 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dma.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dma.c
@@ -5,7 +5,7 @@
 // Author: Andrzej Hajda <a.hajda@samsung.com>
 
 #include <linux/dma-iommu.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/iommu.h>
 #include <linux/platform_device.h>
 
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index b2f49152b4d4..6787ab0d0e43 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -4,6 +4,7 @@
  * Author: Rob Clark <robdclark@gmail.com>
  */
 
+#include <linux/dma-map-ops.h>
 #include <linux/spinlock.h>
 #include <linux/shmem_fs.h>
 #include <linux/dma-buf.h>
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index c12c1dc43d31..d2e3f2622815 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -10,6 +10,7 @@
 
 #include <linux/acpi_iort.h>
 #include <linux/device.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-contiguous.h>
 #include <linux/dma-iommu.h>
 #include <linux/dma-noncoherent.h>
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 2c426dbdf17f..bd3470142b06 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -23,7 +23,7 @@
 #include <linux/spinlock.h>
 #include <linux/pci.h>
 #include <linux/dmar.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/mempool.h>
 #include <linux/memory.h>
 #include <linux/cpu.h>
diff --git a/drivers/misc/mic/bus/mic_bus.c b/drivers/misc/mic/bus/mic_bus.c
index ed9a8351c3bf..a08cb29692a8 100644
--- a/drivers/misc/mic/bus/mic_bus.c
+++ b/drivers/misc/mic/bus/mic_bus.c
@@ -9,6 +9,7 @@
  * This implementation is very similar to the the virtio bus driver
  * implementation @ drivers/virtio/virtio.c
  */
+#include <linux/dma-map-ops.h>
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/idr.h>
diff --git a/drivers/misc/mic/bus/scif_bus.c b/drivers/misc/mic/bus/scif_bus.c
index ae84109649d0..ad7c3604f151 100644
--- a/drivers/misc/mic/bus/scif_bus.c
+++ b/drivers/misc/mic/bus/scif_bus.c
@@ -9,7 +9,7 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/idr.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 
 #include "scif_bus.h"
 
diff --git a/drivers/misc/mic/bus/scif_bus.h b/drivers/misc/mic/bus/scif_bus.h
index 642cd43bcabc..4981eb56f879 100644
--- a/drivers/misc/mic/bus/scif_bus.h
+++ b/drivers/misc/mic/bus/scif_bus.h
@@ -12,7 +12,7 @@
  * Everything a scif driver needs to work with any particular scif
  * hardware abstraction layer.
  */
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 
 #include <linux/mic_common.h>
 #include "../common/mic_dev.h"
diff --git a/drivers/misc/mic/bus/vop_bus.c b/drivers/misc/mic/bus/vop_bus.c
index 3c865534868a..6935ddca1bd5 100644
--- a/drivers/misc/mic/bus/vop_bus.c
+++ b/drivers/misc/mic/bus/vop_bus.c
@@ -9,7 +9,7 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/idr.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 
 #include "vop_bus.h"
 
diff --git a/drivers/misc/mic/host/mic_boot.c b/drivers/misc/mic/host/mic_boot.c
index fb5b3989753d..8cb85b8b3e19 100644
--- a/drivers/misc/mic/host/mic_boot.c
+++ b/drivers/misc/mic/host/mic_boot.c
@@ -10,6 +10,7 @@
 #include <linux/firmware.h>
 #include <linux/pci.h>
 #include <linux/kmod.h>
+#include <linux/dma-map-ops.h>
 #include <linux/mic_common.h>
 #include <linux/mic_bus.h>
 #include "../bus/scif_bus.h"
diff --git a/drivers/of/device.c b/drivers/of/device.c
index 6e3ae7ebc33e..655dee422563 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -6,6 +6,7 @@
 #include <linux/of_address.h>
 #include <linux/of_iommu.h>
 #include <linux/dma-direct.h> /* for bus_dma_region */
+#include <linux/dma-map-ops.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mod_devicetable.h>
diff --git a/drivers/parisc/ccio-dma.c b/drivers/parisc/ccio-dma.c
index 8cf0b9c8bdf7..b5f9ee81a46c 100644
--- a/drivers/parisc/ccio-dma.c
+++ b/drivers/parisc/ccio-dma.c
@@ -39,6 +39,7 @@
 #include <linux/reboot.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
+#include <linux/dma-map-ops.h>
 #include <linux/scatterlist.h>
 #include <linux/iommu-helper.h>
 #include <linux/export.h>
diff --git a/drivers/parisc/sba_iommu.c b/drivers/parisc/sba_iommu.c
index 6fcde7980358..dce4cdf786cd 100644
--- a/drivers/parisc/sba_iommu.c
+++ b/drivers/parisc/sba_iommu.c
@@ -25,6 +25,7 @@
 #include <linux/mm.h>
 #include <linux/string.h>
 #include <linux/pci.h>
+#include <linux/dma-map-ops.h>
 #include <linux/scatterlist.h>
 #include <linux/iommu-helper.h>
 
diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c
index c0e85be598c1..c6fe0cfec0f6 100644
--- a/drivers/pci/xen-pcifront.c
+++ b/drivers/pci/xen-pcifront.c
@@ -22,6 +22,7 @@
 #include <linux/bitops.h>
 #include <linux/time.h>
 #include <linux/ktime.h>
+#include <linux/swiotlb.h>
 #include <xen/platform_pci.h>
 
 #include <asm/xen/swiotlb-xen.h>
diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c
index 8157dd491d28..dab2c0f5caf0 100644
--- a/drivers/remoteproc/remoteproc_core.c
+++ b/drivers/remoteproc/remoteproc_core.c
@@ -22,6 +22,7 @@
 #include <linux/device.h>
 #include <linux/slab.h>
 #include <linux/mutex.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-mapping.h>
 #include <linux/dma-direct.h> /* XXX: pokes into bus_dma_range */
 #include <linux/firmware.h>
diff --git a/drivers/remoteproc/remoteproc_virtio.c b/drivers/remoteproc/remoteproc_virtio.c
index dfd3808c34fd..0cc617f76068 100644
--- a/drivers/remoteproc/remoteproc_virtio.c
+++ b/drivers/remoteproc/remoteproc_virtio.c
@@ -9,7 +9,7 @@
  * Brian Swetland <swetland@google.com>
  */
 
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/export.h>
 #include <linux/of_reserved_mem.h>
 #include <linux/remoteproc.h>
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
index 62d640327145..2629911c29bb 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
@@ -18,7 +18,7 @@
 #include <linux/wait.h>
 #include <linux/uuid.h>
 #include <linux/iommu.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/sysfs.h>
 #include <linux/file.h>
 #include <linux/etherdevice.h>
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 030a225624b0..71ff4bf38073 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -27,6 +27,7 @@
 #define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt
 
 #include <linux/memblock.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-direct.h>
 #include <linux/dma-noncoherent.h>
 #include <linux/export.h>
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
new file mode 100644
index 000000000000..4b4ba5bdcf6a
--- /dev/null
+++ b/include/linux/dma-map-ops.h
@@ -0,0 +1,158 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This header is for implementations of dma_map_ops and related code.
+ * It should not be included in drivers just using the DMA API.
+ */
+#ifndef _LINUX_DMA_MAP_OPS_H
+#define _LINUX_DMA_MAP_OPS_H
+
+#include <linux/dma-mapping.h>
+
+struct dma_map_ops {
+	void *(*alloc)(struct device *dev, size_t size,
+			dma_addr_t *dma_handle, gfp_t gfp,
+			unsigned long attrs);
+	void (*free)(struct device *dev, size_t size, void *vaddr,
+			dma_addr_t dma_handle, unsigned long attrs);
+	struct page *(*alloc_pages)(struct device *dev, size_t size,
+			dma_addr_t *dma_handle, enum dma_data_direction dir,
+			gfp_t gfp);
+	void (*free_pages)(struct device *dev, size_t size, struct page *vaddr,
+			dma_addr_t dma_handle, enum dma_data_direction dir);
+	void *(*alloc_noncoherent)(struct device *dev, size_t size,
+			dma_addr_t *dma_handle, enum dma_data_direction dir,
+			gfp_t gfp);
+	void (*free_noncoherent)(struct device *dev, size_t size, void *vaddr,
+			dma_addr_t dma_handle, enum dma_data_direction dir);
+	int (*mmap)(struct device *, struct vm_area_struct *,
+			void *, dma_addr_t, size_t, unsigned long attrs);
+
+	int (*get_sgtable)(struct device *dev, struct sg_table *sgt,
+			void *cpu_addr, dma_addr_t dma_addr, size_t size,
+			unsigned long attrs);
+
+	dma_addr_t (*map_page)(struct device *dev, struct page *page,
+			unsigned long offset, size_t size,
+			enum dma_data_direction dir, unsigned long attrs);
+	void (*unmap_page)(struct device *dev, dma_addr_t dma_handle,
+			size_t size, enum dma_data_direction dir,
+			unsigned long attrs);
+	/*
+	 * map_sg returns 0 on error and a value > 0 on success.
+	 * It should never return a value < 0.
+	 */
+	int (*map_sg)(struct device *dev, struct scatterlist *sg, int nents,
+			enum dma_data_direction dir, unsigned long attrs);
+	void (*unmap_sg)(struct device *dev, struct scatterlist *sg, int nents,
+			enum dma_data_direction dir, unsigned long attrs);
+	dma_addr_t (*map_resource)(struct device *dev, phys_addr_t phys_addr,
+			size_t size, enum dma_data_direction dir,
+			unsigned long attrs);
+	void (*unmap_resource)(struct device *dev, dma_addr_t dma_handle,
+			size_t size, enum dma_data_direction dir,
+			unsigned long attrs);
+	void (*sync_single_for_cpu)(struct device *dev, dma_addr_t dma_handle,
+			size_t size, enum dma_data_direction dir);
+	void (*sync_single_for_device)(struct device *dev,
+			dma_addr_t dma_handle, size_t size,
+			enum dma_data_direction dir);
+	void (*sync_sg_for_cpu)(struct device *dev, struct scatterlist *sg,
+			int nents, enum dma_data_direction dir);
+	void (*sync_sg_for_device)(struct device *dev, struct scatterlist *sg,
+			int nents, enum dma_data_direction dir);
+	void (*cache_sync)(struct device *dev, void *vaddr, size_t size,
+			enum dma_data_direction direction);
+	int (*dma_supported)(struct device *dev, u64 mask);
+	u64 (*get_required_mask)(struct device *dev);
+	size_t (*max_mapping_size)(struct device *dev);
+	unsigned long (*get_merge_boundary)(struct device *dev);
+};
+
+#ifdef CONFIG_DMA_OPS
+#include <asm/dma-mapping.h>
+
+static inline const struct dma_map_ops *get_dma_ops(struct device *dev)
+{
+	if (dev->dma_ops)
+		return dev->dma_ops;
+	return get_arch_dma_ops(dev->bus);
+}
+
+static inline void set_dma_ops(struct device *dev,
+			       const struct dma_map_ops *dma_ops)
+{
+	dev->dma_ops = dma_ops;
+}
+#else /* CONFIG_DMA_OPS */
+static inline const struct dma_map_ops *get_dma_ops(struct device *dev)
+{
+	return NULL;
+}
+static inline void set_dma_ops(struct device *dev,
+			       const struct dma_map_ops *dma_ops)
+{
+}
+#endif /* CONFIG_DMA_OPS */
+
+#ifdef CONFIG_DMA_DECLARE_COHERENT
+int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
+		dma_addr_t device_addr, size_t size);
+int dma_alloc_from_dev_coherent(struct device *dev, ssize_t size,
+		dma_addr_t *dma_handle, void **ret);
+int dma_release_from_dev_coherent(struct device *dev, int order, void *vaddr);
+int dma_mmap_from_dev_coherent(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, size_t size, int *ret);
+
+void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size,
+		dma_addr_t *dma_handle);
+int dma_release_from_global_coherent(int order, void *vaddr);
+int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *cpu_addr,
+		size_t size, int *ret);
+
+#else
+static inline int dma_declare_coherent_memory(struct device *dev,
+		phys_addr_t phys_addr, dma_addr_t device_addr, size_t size)
+{
+	return -ENOSYS;
+}
+#define dma_alloc_from_dev_coherent(dev, size, handle, ret) (0)
+#define dma_release_from_dev_coherent(dev, order, vaddr) (0)
+#define dma_mmap_from_dev_coherent(dev, vma, vaddr, order, ret) (0)
+
+static inline void *dma_alloc_from_global_coherent(struct device *dev,
+		ssize_t size, dma_addr_t *dma_handle)
+{
+	return NULL;
+}
+static inline int dma_release_from_global_coherent(int order, void *vaddr)
+{
+	return 0;
+}
+static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma,
+		void *cpu_addr, size_t size, int *ret)
+{
+	return 0;
+}
+#endif /* CONFIG_DMA_DECLARE_COHERENT */
+
+#ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS
+void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
+		const struct iommu_ops *iommu, bool coherent);
+#else
+static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base,
+		u64 size, const struct iommu_ops *iommu, bool coherent)
+{
+}
+#endif /* CONFIG_ARCH_HAS_SETUP_DMA_OPS */
+
+#ifdef CONFIG_ARCH_HAS_TEARDOWN_DMA_OPS
+void arch_teardown_dma_ops(struct device *dev);
+#else
+static inline void arch_teardown_dma_ops(struct device *dev)
+{
+}
+#endif /* CONFIG_ARCH_HAS_TEARDOWN_DMA_OPS */
+
+extern const struct dma_map_ops dma_dummy_ops;
+
+#endif /* _LINUX_DMA_MAP_OPS_H */
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 7c77cd6f3604..9591cd482d7c 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -62,72 +62,6 @@
  */
 #define DMA_ATTR_PRIVILEGED		(1UL << 9)
 
-struct dma_map_ops {
-	void* (*alloc)(struct device *dev, size_t size,
-				dma_addr_t *dma_handle, gfp_t gfp,
-				unsigned long attrs);
-	void (*free)(struct device *dev, size_t size,
-			      void *vaddr, dma_addr_t dma_handle,
-			      unsigned long attrs);
-	struct page *(*alloc_pages)(struct device *dev, size_t size,
-			dma_addr_t *dma_handle, enum dma_data_direction dir,
-			gfp_t gfp);
-	void (*free_pages)(struct device *dev, size_t size, struct page *vaddr,
-			dma_addr_t dma_handle, enum dma_data_direction dir);
-	void* (*alloc_noncoherent)(struct device *dev, size_t size,
-			dma_addr_t *dma_handle, enum dma_data_direction dir,
-			gfp_t gfp);
-	void (*free_noncoherent)(struct device *dev, size_t size, void *vaddr,
-			dma_addr_t dma_handle, enum dma_data_direction dir);
-	int (*mmap)(struct device *, struct vm_area_struct *,
-			  void *, dma_addr_t, size_t,
-			  unsigned long attrs);
-
-	int (*get_sgtable)(struct device *dev, struct sg_table *sgt, void *,
-			   dma_addr_t, size_t, unsigned long attrs);
-
-	dma_addr_t (*map_page)(struct device *dev, struct page *page,
-			       unsigned long offset, size_t size,
-			       enum dma_data_direction dir,
-			       unsigned long attrs);
-	void (*unmap_page)(struct device *dev, dma_addr_t dma_handle,
-			   size_t size, enum dma_data_direction dir,
-			   unsigned long attrs);
-	/*
-	 * map_sg returns 0 on error and a value > 0 on success.
-	 * It should never return a value < 0.
-	 */
-	int (*map_sg)(struct device *dev, struct scatterlist *sg,
-		      int nents, enum dma_data_direction dir,
-		      unsigned long attrs);
-	void (*unmap_sg)(struct device *dev,
-			 struct scatterlist *sg, int nents,
-			 enum dma_data_direction dir,
-			 unsigned long attrs);
-	dma_addr_t (*map_resource)(struct device *dev, phys_addr_t phys_addr,
-			       size_t size, enum dma_data_direction dir,
-			       unsigned long attrs);
-	void (*unmap_resource)(struct device *dev, dma_addr_t dma_handle,
-			   size_t size, enum dma_data_direction dir,
-			   unsigned long attrs);
-	void (*sync_single_for_cpu)(struct device *dev,
-				    dma_addr_t dma_handle, size_t size,
-				    enum dma_data_direction dir);
-	void (*sync_single_for_device)(struct device *dev,
-				       dma_addr_t dma_handle, size_t size,
-				       enum dma_data_direction dir);
-	void (*sync_sg_for_cpu)(struct device *dev,
-				struct scatterlist *sg, int nents,
-				enum dma_data_direction dir);
-	void (*sync_sg_for_device)(struct device *dev,
-				   struct scatterlist *sg, int nents,
-				   enum dma_data_direction dir);
-	int (*dma_supported)(struct device *dev, u64 mask);
-	u64 (*get_required_mask)(struct device *dev);
-	size_t (*max_mapping_size)(struct device *dev);
-	unsigned long (*get_merge_boundary)(struct device *dev);
-};
-
 /*
  * A dma_addr_t can hold any valid DMA or bus address for the platform.  It can
  * be given to a device to use as a DMA source or target.  It is specific to a
@@ -140,79 +74,9 @@ struct dma_map_ops {
  */
 #define DMA_MAPPING_ERROR		(~(dma_addr_t)0)
 
-extern const struct dma_map_ops dma_virt_ops;
-extern const struct dma_map_ops dma_dummy_ops;
-
 #define DMA_BIT_MASK(n)	(((n) == 64) ? ~0ULL : ((1ULL<<(n))-1))
 
-#ifdef CONFIG_DMA_DECLARE_COHERENT
-/*
- * These three functions are only for dma allocator.
- * Don't use them in device drivers.
- */
-int dma_alloc_from_dev_coherent(struct device *dev, ssize_t size,
-				       dma_addr_t *dma_handle, void **ret);
-int dma_release_from_dev_coherent(struct device *dev, int order, void *vaddr);
-
-int dma_mmap_from_dev_coherent(struct device *dev, struct vm_area_struct *vma,
-			    void *cpu_addr, size_t size, int *ret);
-
-void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size, dma_addr_t *dma_handle);
-int dma_release_from_global_coherent(int order, void *vaddr);
-int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *cpu_addr,
-				  size_t size, int *ret);
-
-#else
-#define dma_alloc_from_dev_coherent(dev, size, handle, ret) (0)
-#define dma_release_from_dev_coherent(dev, order, vaddr) (0)
-#define dma_mmap_from_dev_coherent(dev, vma, vaddr, order, ret) (0)
-
-static inline void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size,
-						   dma_addr_t *dma_handle)
-{
-	return NULL;
-}
-
-static inline int dma_release_from_global_coherent(int order, void *vaddr)
-{
-	return 0;
-}
-
-static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma,
-						void *cpu_addr, size_t size,
-						int *ret)
-{
-	return 0;
-}
-#endif /* CONFIG_DMA_DECLARE_COHERENT */
-
 #ifdef CONFIG_HAS_DMA
-#include <asm/dma-mapping.h>
-
-#ifdef CONFIG_DMA_OPS
-static inline const struct dma_map_ops *get_dma_ops(struct device *dev)
-{
-	if (dev->dma_ops)
-		return dev->dma_ops;
-	return get_arch_dma_ops(dev->bus);
-}
-
-static inline void set_dma_ops(struct device *dev,
-			       const struct dma_map_ops *dma_ops)
-{
-	dev->dma_ops = dma_ops;
-}
-#else /* CONFIG_DMA_OPS */
-static inline const struct dma_map_ops *get_dma_ops(struct device *dev)
-{
-	return NULL;
-}
-static inline void set_dma_ops(struct device *dev,
-			       const struct dma_map_ops *dma_ops)
-{
-}
-#endif /* CONFIG_DMA_OPS */
-
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
 	debug_dma_mapping_error(dev, dma_addr);
@@ -595,24 +459,6 @@ static inline bool dma_addressing_limited(struct device *dev)
 			    dma_get_required_mask(dev);
 }
 
-#ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS
-void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-		const struct iommu_ops *iommu, bool coherent);
-#else
-static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base,
-		u64 size, const struct iommu_ops *iommu, bool coherent)
-{
-}
-#endif /* CONFIG_ARCH_HAS_SETUP_DMA_OPS */
-
-#ifdef CONFIG_ARCH_HAS_TEARDOWN_DMA_OPS
-void arch_teardown_dma_ops(struct device *dev);
-#else
-static inline void arch_teardown_dma_ops(struct device *dev)
-{
-}
-#endif /* CONFIG_ARCH_HAS_TEARDOWN_DMA_OPS */
-
 static inline unsigned int dma_get_max_seg_size(struct device *dev)
 {
 	if (dev->dma_parms && dev->dma_parms->max_segment_size)
@@ -672,18 +518,6 @@ static inline int dma_get_cache_alignment(void)
 	return 1;
 }
 
-#ifdef CONFIG_DMA_DECLARE_COHERENT
-int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
-				dma_addr_t device_addr, size_t size);
-#else
-static inline int
-dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
-			    dma_addr_t device_addr, size_t size)
-{
-	return -ENOSYS;
-}
-#endif /* CONFIG_DMA_DECLARE_COHERENT */
-
 static inline void *dmam_alloc_coherent(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp)
 {
@@ -741,4 +575,6 @@ static inline int dma_mmap_wc(struct device *dev,
 int dma_direct_set_offset(struct device *dev, phys_addr_t cpu_start,
 		dma_addr_t dma_start, u64 size);
 
+extern const struct dma_map_ops dma_virt_ops;
+
 #endif /* _LINUX_DMA_MAPPING_H */
diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c
index c0685196fb6d..5b5b6c7ec7f2 100644
--- a/kernel/dma/coherent.c
+++ b/kernel/dma/coherent.c
@@ -8,6 +8,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/dma-direct.h>
+#include <linux/dma-map-ops.h>
 
 struct dma_coherent_mem {
 	void		*virt_base;
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 121a9c1969dd..8cf5689a8c40 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -8,6 +8,7 @@
 #include <linux/export.h>
 #include <linux/mm.h>
 #include <linux/dma-direct.h>
+#include <linux/dma-map-ops.h>
 #include <linux/scatterlist.h>
 #include <linux/dma-contiguous.h>
 #include <linux/pfn.h>
diff --git a/kernel/dma/dummy.c b/kernel/dma/dummy.c
index 6974b1bd7d0b..eacd4c5b10bf 100644
--- a/kernel/dma/dummy.c
+++ b/kernel/dma/dummy.c
@@ -2,7 +2,7 @@
 /*
  * Dummy DMA ops that always fail.
  */
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 
 static int dma_dummy_mmap(struct device *dev, struct vm_area_struct *vma,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 9669550656a0..2e13e6d3903f 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -8,7 +8,7 @@
 #include <linux/memblock.h> /* for max_pfn */
 #include <linux/acpi.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/export.h>
 #include <linux/gfp.h>
 #include <linux/of_device.h>
diff --git a/kernel/dma/ops_helpers.c b/kernel/dma/ops_helpers.c
index 5828e5e01b79..60d7b6cdfd8d 100644
--- a/kernel/dma/ops_helpers.c
+++ b/kernel/dma/ops_helpers.c
@@ -4,6 +4,7 @@
  * the allocated memory contains normal pages in the direct kernel mapping.
  */
 #include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-noncoherent.h>
 
 /*
diff --git a/kernel/dma/virt.c b/kernel/dma/virt.c
index 6986bf1fd668..59d32317dd57 100644
--- a/kernel/dma/virt.c
+++ b/kernel/dma/virt.c
@@ -4,7 +4,7 @@
  */
 #include <linux/export.h>
 #include <linux/mm.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/scatterlist.h>
 
 static void *dma_virt_alloc(struct device *dev, size_t size,
-- 
cgit v1.2.3


From 8df4051232152a0520ab3035c2d96f33083c2d6a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 11 Sep 2020 10:29:47 +0200
Subject: dma-contiguous: remove dma_declare_contiguous

dma_declare_contiguous is a trivial wrapper around
dma_contiguous_reserve_area and just has a single caller.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 arch/arm/mach-davinci/devices-da8xx.c | 16 ++++++++++------
 include/linux/dma-contiguous.h        | 32 --------------------------------
 2 files changed, 10 insertions(+), 38 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/mach-davinci/devices-da8xx.c b/arch/arm/mach-davinci/devices-da8xx.c
index feb206bdf6e1..2e2853582b45 100644
--- a/arch/arm/mach-davinci/devices-da8xx.c
+++ b/arch/arm/mach-davinci/devices-da8xx.c
@@ -884,6 +884,7 @@ early_param("rproc_mem", early_rproc_mem);
 
 void __init da8xx_rproc_reserve_cma(void)
 {
+	struct cma *cma;
 	int ret;
 
 	if (!rproc_base || !rproc_size) {
@@ -897,13 +898,16 @@ void __init da8xx_rproc_reserve_cma(void)
 	pr_info("%s: reserving 0x%lx @ 0x%lx...\n",
 		__func__, rproc_size, (unsigned long)rproc_base);
 
-	ret = dma_declare_contiguous(&da8xx_dsp.dev, rproc_size, rproc_base, 0);
-	if (ret)
-		pr_err("%s: dma_declare_contiguous failed %d\n", __func__, ret);
-	else
-		rproc_mem_inited = true;
+	ret = dma_contiguous_reserve_area(rproc_size, rproc_base, 0, &cma,
+			true);
+	if (ret) {
+		pr_err("%s: dma_contiguous_reserve_area failed %d\n",
+			__func__, ret);
+		return;
+	}
+	dev_set_cma_area(&da8xx_dsp.dev, cma);
+	rproc_mem_inited = true;
 }
-
 #else
 
 void __init da8xx_rproc_reserve_cma(void)
diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h
index fe55e004f1f4..62fd55d07235 100644
--- a/include/linux/dma-contiguous.h
+++ b/include/linux/dma-contiguous.h
@@ -83,31 +83,6 @@ int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
 				       phys_addr_t limit, struct cma **res_cma,
 				       bool fixed);
 
-/**
- * dma_declare_contiguous() - reserve area for contiguous memory handling
- *			      for particular device
- * @dev:   Pointer to device structure.
- * @size:  Size of the reserved memory.
- * @base:  Start address of the reserved memory (optional, 0 for any).
- * @limit: End address of the reserved memory (optional, 0 for any).
- *
- * This function reserves memory for specified device. It should be
- * called by board specific code when early allocator (memblock or bootmem)
- * is still activate.
- */
-
-static inline int dma_declare_contiguous(struct device *dev, phys_addr_t size,
-					 phys_addr_t base, phys_addr_t limit)
-{
-	struct cma *cma;
-	int ret;
-	ret = dma_contiguous_reserve_area(size, base, limit, &cma, true);
-	if (ret == 0)
-		dev_set_cma_area(dev, cma);
-
-	return ret;
-}
-
 struct page *dma_alloc_from_contiguous(struct device *dev, size_t count,
 				       unsigned int order, bool no_warn);
 bool dma_release_from_contiguous(struct device *dev, struct page *pages,
@@ -135,13 +110,6 @@ static inline int dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base
 	return -ENOSYS;
 }
 
-static inline
-int dma_declare_contiguous(struct device *dev, phys_addr_t size,
-			   phys_addr_t base, phys_addr_t limit)
-{
-	return -ENOSYS;
-}
-
 static inline
 struct page *dma_alloc_from_contiguous(struct device *dev, size_t count,
 				       unsigned int order, bool no_warn)
-- 
cgit v1.2.3


From 5af638931eb374aa0894d8343cee72f50307ef20 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 11 Sep 2020 10:56:03 +0200
Subject: dma-contiguous: remove dev_set_cma_area

dev_set_cma_area contains a trivial assignment.  It has just three
callers that all have a non-NULL device and depend on CONFIG_DMA_CMA,
so remove the wrapper.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 arch/arm/mach-davinci/devices-da8xx.c | 2 +-
 include/linux/dma-contiguous.h        | 8 --------
 kernel/dma/contiguous.c               | 4 ++--
 3 files changed, 3 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/mach-davinci/devices-da8xx.c b/arch/arm/mach-davinci/devices-da8xx.c
index 2e2853582b45..1207eabe8d1c 100644
--- a/arch/arm/mach-davinci/devices-da8xx.c
+++ b/arch/arm/mach-davinci/devices-da8xx.c
@@ -905,7 +905,7 @@ void __init da8xx_rproc_reserve_cma(void)
 			__func__, ret);
 		return;
 	}
-	dev_set_cma_area(&da8xx_dsp.dev, cma);
+	da8xx_dsp.dev.cma_area = cma;
 	rproc_mem_inited = true;
 }
 #else
diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h
index 62fd55d07235..41ec08d81bc3 100644
--- a/include/linux/dma-contiguous.h
+++ b/include/linux/dma-contiguous.h
@@ -66,12 +66,6 @@ static inline struct cma *dev_get_cma_area(struct device *dev)
 	return dma_contiguous_default_area;
 }
 
-static inline void dev_set_cma_area(struct device *dev, struct cma *cma)
-{
-	if (dev)
-		dev->cma_area = cma;
-}
-
 static inline void dma_contiguous_set_default(struct cma *cma)
 {
 	dma_contiguous_default_area = cma;
@@ -97,8 +91,6 @@ static inline struct cma *dev_get_cma_area(struct device *dev)
 	return NULL;
 }
 
-static inline void dev_set_cma_area(struct device *dev, struct cma *cma) { }
-
 static inline void dma_contiguous_set_default(struct cma *cma) { }
 
 static inline void dma_contiguous_reserve(phys_addr_t limit) { }
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index f4c150810fd2..95adcee972e8 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -359,14 +359,14 @@ void dma_free_contiguous(struct device *dev, struct page *page, size_t size)
 
 static int rmem_cma_device_init(struct reserved_mem *rmem, struct device *dev)
 {
-	dev_set_cma_area(dev, rmem->priv);
+	dev->cma_area = rmem->priv;
 	return 0;
 }
 
 static void rmem_cma_device_release(struct reserved_mem *rmem,
 				    struct device *dev)
 {
-	dev_set_cma_area(dev, NULL);
+	dev->cma_area = NULL;
 }
 
 static const struct reserved_mem_ops rmem_cma_ops = {
-- 
cgit v1.2.3


From 580a0cc9c3f662e0b10136bc8af1e672e472806f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 11 Sep 2020 10:56:40 +0200
Subject: dma-contiguous: remove dma_contiguous_set_default

dma_contiguous_set_default contains a trivial assignment, and has a
single caller that is compiled if CONFIG_CMA_DMA is enabled.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/dma-contiguous.h | 7 -------
 kernel/dma/contiguous.c        | 2 +-
 2 files changed, 1 insertion(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h
index 41ec08d81bc3..f9ce1ee58d41 100644
--- a/include/linux/dma-contiguous.h
+++ b/include/linux/dma-contiguous.h
@@ -66,11 +66,6 @@ static inline struct cma *dev_get_cma_area(struct device *dev)
 	return dma_contiguous_default_area;
 }
 
-static inline void dma_contiguous_set_default(struct cma *cma)
-{
-	dma_contiguous_default_area = cma;
-}
-
 void dma_contiguous_reserve(phys_addr_t addr_limit);
 
 int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
@@ -91,8 +86,6 @@ static inline struct cma *dev_get_cma_area(struct device *dev)
 	return NULL;
 }
 
-static inline void dma_contiguous_set_default(struct cma *cma) { }
-
 static inline void dma_contiguous_reserve(phys_addr_t limit) { }
 
 static inline int dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index 95adcee972e8..bf05ec2256e1 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -407,7 +407,7 @@ static int __init rmem_cma_setup(struct reserved_mem *rmem)
 	dma_contiguous_early_fixup(rmem->base, rmem->size);
 
 	if (default_cma)
-		dma_contiguous_set_default(cma);
+		dma_contiguous_default_area = cma;
 
 	rmem->ops = &rmem_cma_ops;
 	rmem->priv = cma;
-- 
cgit v1.2.3


From 0b1abd1fb7efafc25231c54a67c6fbb3d3127efd Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 11 Sep 2020 10:56:52 +0200
Subject: dma-mapping: merge <linux/dma-contiguous.h> into
 <linux/dma-map-ops.h>

Merge dma-contiguous.h into dma-map-ops.h, after removing the comment
describing the contiguous allocator into kernel/dma/contigous.c.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 Documentation/admin-guide/kernel-parameters.txt |   2 +-
 arch/arm/mach-davinci/devices-da8xx.c           |   2 +-
 arch/arm/mach-shmobile/setup-rcar-gen2.c        |   2 +-
 arch/arm/mm/dma-mapping.c                       |   1 -
 arch/arm/mm/init.c                              |   2 +-
 arch/arm64/mm/init.c                            |   3 +-
 arch/csky/kernel/setup.c                        |   2 +-
 arch/csky/mm/dma-mapping.c                      |   3 +-
 arch/microblaze/mm/init.c                       |   2 +-
 arch/mips/kernel/setup.c                        |   2 +-
 arch/mips/mm/dma-noncoherent.c                  |   1 -
 arch/s390/kernel/setup.c                        |   2 +-
 arch/x86/include/asm/dma-mapping.h              |   1 -
 arch/x86/kernel/setup.c                         |   2 +-
 arch/xtensa/kernel/pci-dma.c                    |   2 +-
 arch/xtensa/mm/init.c                           |   2 +-
 drivers/dma-buf/heaps/cma_heap.c                |   2 +-
 drivers/iommu/amd/iommu.c                       |   3 +-
 drivers/iommu/dma-iommu.c                       |   1 -
 drivers/iommu/intel/iommu.c                     |   2 +-
 drivers/media/platform/exynos4-is/fimc-is.c     |   1 -
 include/linux/dma-contiguous.h                  | 135 ------------------------
 include/linux/dma-map-ops.h                     |  65 ++++++++++++
 kernel/dma/Kconfig                              |   2 +-
 kernel/dma/contiguous.c                         |  30 +++++-
 kernel/dma/direct.c                             |   1 -
 kernel/dma/ops_helpers.c                        |   1 -
 kernel/dma/pool.c                               |   2 +-
 28 files changed, 112 insertions(+), 164 deletions(-)
 delete mode 100644 include/linux/dma-contiguous.h

(limited to 'include/linux')

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index e464cf0b5025..7657e00e83ca 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -597,7 +597,7 @@
 			placement constraint by the physical address range of
 			memory allocations. A value of 0 disables CMA
 			altogether. For more information, see
-			include/linux/dma-contiguous.h
+			kernel/dma/contiguous.c
 
 	cma_pernuma=nn[MG]
 			[ARM64,KNL]
diff --git a/arch/arm/mach-davinci/devices-da8xx.c b/arch/arm/mach-davinci/devices-da8xx.c
index 1207eabe8d1c..bb368938fc49 100644
--- a/arch/arm/mach-davinci/devices-da8xx.c
+++ b/arch/arm/mach-davinci/devices-da8xx.c
@@ -10,7 +10,7 @@
 #include <linux/clk-provider.h>
 #include <linux/clk.h>
 #include <linux/clkdev.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dmaengine.h>
 #include <linux/init.h>
 #include <linux/io.h>
diff --git a/arch/arm/mach-shmobile/setup-rcar-gen2.c b/arch/arm/mach-shmobile/setup-rcar-gen2.c
index c42ff8c314c8..e00f5b3b9293 100644
--- a/arch/arm/mach-shmobile/setup-rcar-gen2.c
+++ b/arch/arm/mach-shmobile/setup-rcar-gen2.c
@@ -9,7 +9,7 @@
 
 #include <linux/clocksource.h>
 #include <linux/device.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
 #include <linux/memblock.h>
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 8bf0bc6bc311..154c24cec94c 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -17,7 +17,6 @@
 #include <linux/dma-direct.h>
 #include <linux/dma-map-ops.h>
 #include <linux/dma-noncoherent.h>
-#include <linux/dma-contiguous.h>
 #include <linux/highmem.h>
 #include <linux/memblock.h>
 #include <linux/slab.h>
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 000c1b48e973..ab1d1931a352 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -18,7 +18,7 @@
 #include <linux/highmem.h>
 #include <linux/gfp.h>
 #include <linux/memblock.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/sizes.h>
 #include <linux/stop_machine.h>
 #include <linux/swiotlb.h>
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index f1c75957ff3c..1b591ddb28b0 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -21,8 +21,7 @@
 #include <linux/of.h>
 #include <linux/of_fdt.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-mapping.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/efi.h>
 #include <linux/swiotlb.h>
 #include <linux/vmalloc.h>
diff --git a/arch/csky/kernel/setup.c b/arch/csky/kernel/setup.c
index 0481f4e34538..e4cab16056d6 100644
--- a/arch/csky/kernel/setup.c
+++ b/arch/csky/kernel/setup.c
@@ -7,7 +7,7 @@
 #include <linux/of.h>
 #include <linux/of_fdt.h>
 #include <linux/start_kernel.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/screen_info.h>
 #include <asm/sections.h>
 #include <asm/mmu_context.h>
diff --git a/arch/csky/mm/dma-mapping.c b/arch/csky/mm/dma-mapping.c
index 8f6571ae27c8..3d9ff26c4bb4 100644
--- a/arch/csky/mm/dma-mapping.c
+++ b/arch/csky/mm/dma-mapping.c
@@ -2,8 +2,7 @@
 // Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
 
 #include <linux/cache.h>
-#include <linux/dma-mapping.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-noncoherent.h>
 #include <linux/genalloc.h>
 #include <linux/highmem.h>
diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c
index 3344d4a1fe89..7659a8b86580 100644
--- a/arch/microblaze/mm/init.c
+++ b/arch/microblaze/mm/init.c
@@ -7,7 +7,7 @@
  * for more details.
  */
 
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/memblock.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index bf5f5acab0a8..464bfd3957ae 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -24,7 +24,7 @@
 #include <linux/kexec.h>
 #include <linux/sizes.h>
 #include <linux/device.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/decompress/generic.h>
 #include <linux/of_fdt.h>
 #include <linux/of_reserved_mem.h>
diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c
index f4e8404ee049..22d99ccc70c8 100644
--- a/arch/mips/mm/dma-noncoherent.c
+++ b/arch/mips/mm/dma-noncoherent.c
@@ -7,7 +7,6 @@
 #include <linux/dma-direct.h>
 #include <linux/dma-map-ops.h>
 #include <linux/dma-noncoherent.h>
-#include <linux/dma-contiguous.h>
 #include <linux/highmem.h>
 
 #include <asm/cache.h>
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index c2c1b4e723ea..151092565a27 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -37,7 +37,7 @@
 #include <linux/root_dev.h>
 #include <linux/console.h>
 #include <linux/kernel_stat.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/device.h>
 #include <linux/notifier.h>
 #include <linux/pfn.h>
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index fed67eafcacc..e0c380b3ec14 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -11,7 +11,6 @@
 #include <linux/dma-debug.h>
 #include <asm/io.h>
 #include <asm/swiotlb.h>
-#include <linux/dma-contiguous.h>
 
 extern int iommu_merge;
 extern int panic_on_overflow;
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 9286fa9d575e..e8155e85bd8f 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -7,7 +7,7 @@
  */
 #include <linux/console.h>
 #include <linux/crash_dump.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dmi.h>
 #include <linux/efi.h>
 #include <linux/init_ohci1394_dma.h>
diff --git a/arch/xtensa/kernel/pci-dma.c b/arch/xtensa/kernel/pci-dma.c
index 17c4384f8495..790dbe022a07 100644
--- a/arch/xtensa/kernel/pci-dma.c
+++ b/arch/xtensa/kernel/pci-dma.c
@@ -11,7 +11,7 @@
  * Joe Taylor <joe@tensilica.com, joetylr@yahoo.com>
  */
 
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-noncoherent.h>
 #include <linux/dma-direct.h>
 #include <linux/gfp.h>
diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c
index a05b306cf371..8079007842ac 100644
--- a/arch/xtensa/mm/init.c
+++ b/arch/xtensa/mm/init.c
@@ -26,7 +26,7 @@
 #include <linux/nodemask.h>
 #include <linux/mm.h>
 #include <linux/of_fdt.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 
 #include <asm/bootparam.h>
 #include <asm/page.h>
diff --git a/drivers/dma-buf/heaps/cma_heap.c b/drivers/dma-buf/heaps/cma_heap.c
index 626cf7fd033a..e55384dc115b 100644
--- a/drivers/dma-buf/heaps/cma_heap.c
+++ b/drivers/dma-buf/heaps/cma_heap.c
@@ -10,7 +10,7 @@
 #include <linux/device.h>
 #include <linux/dma-buf.h>
 #include <linux/dma-heap.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/err.h>
 #include <linux/errno.h>
 #include <linux/highmem.h>
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 10e4200d3552..5396eb8d730b 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -18,7 +18,7 @@
 #include <linux/slab.h>
 #include <linux/debugfs.h>
 #include <linux/scatterlist.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-direct.h>
 #include <linux/dma-iommu.h>
 #include <linux/iommu-helper.h>
@@ -28,7 +28,6 @@
 #include <linux/export.h>
 #include <linux/irq.h>
 #include <linux/msi.h>
-#include <linux/dma-contiguous.h>
 #include <linux/irqdomain.h>
 #include <linux/percpu.h>
 #include <linux/iova.h>
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index d2e3f2622815..22c221bba13e 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -11,7 +11,6 @@
 #include <linux/acpi_iort.h>
 #include <linux/device.h>
 #include <linux/dma-map-ops.h>
-#include <linux/dma-contiguous.h>
 #include <linux/dma-iommu.h>
 #include <linux/dma-noncoherent.h>
 #include <linux/gfp.h>
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index bd3470142b06..0c5b4500ae83 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -37,7 +37,7 @@
 #include <linux/dmi.h>
 #include <linux/pci-ats.h>
 #include <linux/memblock.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-direct.h>
 #include <linux/crash_dump.h>
 #include <linux/numa.h>
diff --git a/drivers/media/platform/exynos4-is/fimc-is.c b/drivers/media/platform/exynos4-is/fimc-is.c
index a474014f0a0f..32f5982afa1a 100644
--- a/drivers/media/platform/exynos4-is/fimc-is.c
+++ b/drivers/media/platform/exynos4-is/fimc-is.c
@@ -12,7 +12,6 @@
 #include <linux/device.h>
 #include <linux/debugfs.h>
 #include <linux/delay.h>
-#include <linux/dma-contiguous.h>
 #include <linux/errno.h>
 #include <linux/firmware.h>
 #include <linux/interrupt.h>
diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h
deleted file mode 100644
index f9ce1ee58d41..000000000000
--- a/include/linux/dma-contiguous.h
+++ /dev/null
@@ -1,135 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-#ifndef __LINUX_CMA_H
-#define __LINUX_CMA_H
-
-/*
- * Contiguous Memory Allocator for DMA mapping framework
- * Copyright (c) 2010-2011 by Samsung Electronics.
- * Written by:
- *	Marek Szyprowski <m.szyprowski@samsung.com>
- *	Michal Nazarewicz <mina86@mina86.com>
- */
-
-/*
- * Contiguous Memory Allocator
- *
- *   The Contiguous Memory Allocator (CMA) makes it possible to
- *   allocate big contiguous chunks of memory after the system has
- *   booted.
- *
- * Why is it needed?
- *
- *   Various devices on embedded systems have no scatter-getter and/or
- *   IO map support and require contiguous blocks of memory to
- *   operate.  They include devices such as cameras, hardware video
- *   coders, etc.
- *
- *   Such devices often require big memory buffers (a full HD frame
- *   is, for instance, more then 2 mega pixels large, i.e. more than 6
- *   MB of memory), which makes mechanisms such as kmalloc() or
- *   alloc_page() ineffective.
- *
- *   At the same time, a solution where a big memory region is
- *   reserved for a device is suboptimal since often more memory is
- *   reserved then strictly required and, moreover, the memory is
- *   inaccessible to page system even if device drivers don't use it.
- *
- *   CMA tries to solve this issue by operating on memory regions
- *   where only movable pages can be allocated from.  This way, kernel
- *   can use the memory for pagecache and when device driver requests
- *   it, allocated pages can be migrated.
- *
- * Driver usage
- *
- *   CMA should not be used by the device drivers directly. It is
- *   only a helper framework for dma-mapping subsystem.
- *
- *   For more information, see kernel-docs in kernel/dma/contiguous.c
- */
-
-#ifdef __KERNEL__
-
-#include <linux/device.h>
-#include <linux/mm.h>
-
-struct cma;
-struct page;
-
-#ifdef CONFIG_DMA_CMA
-
-extern struct cma *dma_contiguous_default_area;
-
-static inline struct cma *dev_get_cma_area(struct device *dev)
-{
-	if (dev && dev->cma_area)
-		return dev->cma_area;
-	return dma_contiguous_default_area;
-}
-
-void dma_contiguous_reserve(phys_addr_t addr_limit);
-
-int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
-				       phys_addr_t limit, struct cma **res_cma,
-				       bool fixed);
-
-struct page *dma_alloc_from_contiguous(struct device *dev, size_t count,
-				       unsigned int order, bool no_warn);
-bool dma_release_from_contiguous(struct device *dev, struct page *pages,
-				 int count);
-struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp);
-void dma_free_contiguous(struct device *dev, struct page *page, size_t size);
-
-#else
-
-static inline struct cma *dev_get_cma_area(struct device *dev)
-{
-	return NULL;
-}
-
-static inline void dma_contiguous_reserve(phys_addr_t limit) { }
-
-static inline int dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
-				       phys_addr_t limit, struct cma **res_cma,
-				       bool fixed)
-{
-	return -ENOSYS;
-}
-
-static inline
-struct page *dma_alloc_from_contiguous(struct device *dev, size_t count,
-				       unsigned int order, bool no_warn)
-{
-	return NULL;
-}
-
-static inline
-bool dma_release_from_contiguous(struct device *dev, struct page *pages,
-				 int count)
-{
-	return false;
-}
-
-/* Use fallback alloc() and free() when CONFIG_DMA_CMA=n */
-static inline struct page *dma_alloc_contiguous(struct device *dev, size_t size,
-		gfp_t gfp)
-{
-	return NULL;
-}
-
-static inline void dma_free_contiguous(struct device *dev, struct page *page,
-		size_t size)
-{
-	__free_pages(page, get_order(size));
-}
-
-#endif
-
-#ifdef CONFIG_DMA_PERNUMA_CMA
-void dma_pernuma_cma_reserve(void);
-#else
-static inline void dma_pernuma_cma_reserve(void) { }
-#endif
-
-#endif
-
-#endif
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 4b4ba5bdcf6a..474fc81bd492 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -8,6 +8,8 @@
 
 #include <linux/dma-mapping.h>
 
+struct cma;
+
 struct dma_map_ops {
 	void *(*alloc)(struct device *dev, size_t size,
 			dma_addr_t *dma_handle, gfp_t gfp,
@@ -94,6 +96,69 @@ static inline void set_dma_ops(struct device *dev,
 }
 #endif /* CONFIG_DMA_OPS */
 
+#ifdef CONFIG_DMA_CMA
+extern struct cma *dma_contiguous_default_area;
+
+static inline struct cma *dev_get_cma_area(struct device *dev)
+{
+	if (dev && dev->cma_area)
+		return dev->cma_area;
+	return dma_contiguous_default_area;
+}
+
+void dma_contiguous_reserve(phys_addr_t addr_limit);
+int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
+		phys_addr_t limit, struct cma **res_cma, bool fixed);
+
+struct page *dma_alloc_from_contiguous(struct device *dev, size_t count,
+				       unsigned int order, bool no_warn);
+bool dma_release_from_contiguous(struct device *dev, struct page *pages,
+				 int count);
+struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp);
+void dma_free_contiguous(struct device *dev, struct page *page, size_t size);
+#else /* CONFIG_DMA_CMA */
+static inline struct cma *dev_get_cma_area(struct device *dev)
+{
+	return NULL;
+}
+static inline void dma_contiguous_reserve(phys_addr_t limit)
+{
+}
+static inline int dma_contiguous_reserve_area(phys_addr_t size,
+		phys_addr_t base, phys_addr_t limit, struct cma **res_cma,
+		bool fixed)
+{
+	return -ENOSYS;
+}
+static inline struct page *dma_alloc_from_contiguous(struct device *dev,
+		size_t count, unsigned int order, bool no_warn)
+{
+	return NULL;
+}
+static inline bool dma_release_from_contiguous(struct device *dev,
+		struct page *pages, int count)
+{
+	return false;
+}
+/* Use fallback alloc() and free() when CONFIG_DMA_CMA=n */
+static inline struct page *dma_alloc_contiguous(struct device *dev, size_t size,
+		gfp_t gfp)
+{
+	return NULL;
+}
+static inline void dma_free_contiguous(struct device *dev, struct page *page,
+		size_t size)
+{
+	__free_pages(page, get_order(size));
+}
+#endif /* CONFIG_DMA_CMA*/
+
+#ifdef CONFIG_DMA_PERNUMA_CMA
+void dma_pernuma_cma_reserve(void);
+#else
+static inline void dma_pernuma_cma_reserve(void) { }
+#endif /* CONFIG_DMA_PERNUMA_CMA */
+
 #ifdef CONFIG_DMA_DECLARE_COHERENT
 int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
 		dma_addr_t device_addr, size_t size);
diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index 647996702bc9..c99de4a21458 100644
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@ -118,7 +118,7 @@ config DMA_CMA
 	  You can disable CMA by specifying "cma=0" on the kernel's command
 	  line.
 
-	  For more information see <include/linux/dma-contiguous.h>.
+	  For more information see <kernel/dma/contiguous.c>.
 	  If unsure, say "n".
 
 if  DMA_CMA
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index bf05ec2256e1..6bfb763fff6f 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -5,6 +5,34 @@
  * Written by:
  *	Marek Szyprowski <m.szyprowski@samsung.com>
  *	Michal Nazarewicz <mina86@mina86.com>
+ *
+ * Contiguous Memory Allocator
+ *
+ *   The Contiguous Memory Allocator (CMA) makes it possible to
+ *   allocate big contiguous chunks of memory after the system has
+ *   booted.
+ *
+ * Why is it needed?
+ *
+ *   Various devices on embedded systems have no scatter-getter and/or
+ *   IO map support and require contiguous blocks of memory to
+ *   operate.  They include devices such as cameras, hardware video
+ *   coders, etc.
+ *
+ *   Such devices often require big memory buffers (a full HD frame
+ *   is, for instance, more then 2 mega pixels large, i.e. more than 6
+ *   MB of memory), which makes mechanisms such as kmalloc() or
+ *   alloc_page() ineffective.
+ *
+ *   At the same time, a solution where a big memory region is
+ *   reserved for a device is suboptimal since often more memory is
+ *   reserved then strictly required and, moreover, the memory is
+ *   inaccessible to page system even if device drivers don't use it.
+ *
+ *   CMA tries to solve this issue by operating on memory regions
+ *   where only movable pages can be allocated from.  This way, kernel
+ *   can use the memory for pagecache and when device driver requests
+ *   it, allocated pages can be migrated.
  */
 
 #define pr_fmt(fmt) "cma: " fmt
@@ -21,7 +49,7 @@
 #include <linux/memblock.h>
 #include <linux/err.h>
 #include <linux/sizes.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/cma.h>
 
 #ifdef CONFIG_CMA_SIZE_MBYTES
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 8cf5689a8c40..87697c86f0b8 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -10,7 +10,6 @@
 #include <linux/dma-direct.h>
 #include <linux/dma-map-ops.h>
 #include <linux/scatterlist.h>
-#include <linux/dma-contiguous.h>
 #include <linux/pfn.h>
 #include <linux/vmalloc.h>
 #include <linux/set_memory.h>
diff --git a/kernel/dma/ops_helpers.c b/kernel/dma/ops_helpers.c
index 60d7b6cdfd8d..bc80fd2648bc 100644
--- a/kernel/dma/ops_helpers.c
+++ b/kernel/dma/ops_helpers.c
@@ -3,7 +3,6 @@
  * Helpers for DMA ops implementations.  These generally rely on the fact that
  * the allocated memory contains normal pages in the direct kernel mapping.
  */
-#include <linux/dma-contiguous.h>
 #include <linux/dma-map-ops.h>
 #include <linux/dma-noncoherent.h>
 
diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c
index fe11643ff9cc..c9fb5c3d8bd0 100644
--- a/kernel/dma/pool.c
+++ b/kernel/dma/pool.c
@@ -5,7 +5,7 @@
  */
 #include <linux/cma.h>
 #include <linux/debugfs.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-direct.h>
 #include <linux/dma-noncoherent.h>
 #include <linux/init.h>
-- 
cgit v1.2.3


From 5db5d93089880c3cc9e83ca8bba68a5502e92dfe Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 11 Sep 2020 11:04:43 +0200
Subject: dma-mapping: remove <asm/dma-contiguous.h>

Just provide a weak default definition of dma_contiguous_early_fixup and
let arm override it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 arch/arm/include/asm/dma-contiguous.h | 15 ---------------
 arch/arm/mm/dma-mapping.c             |  1 -
 include/asm-generic/Kbuild            |  1 -
 include/asm-generic/dma-contiguous.h  | 10 ----------
 include/linux/dma-map-ops.h           |  2 ++
 kernel/dma/contiguous.c               |  6 +++++-
 6 files changed, 7 insertions(+), 28 deletions(-)
 delete mode 100644 arch/arm/include/asm/dma-contiguous.h
 delete mode 100644 include/asm-generic/dma-contiguous.h

(limited to 'include/linux')

diff --git a/arch/arm/include/asm/dma-contiguous.h b/arch/arm/include/asm/dma-contiguous.h
deleted file mode 100644
index d785187a6f8a..000000000000
--- a/arch/arm/include/asm/dma-contiguous.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef ASMARM_DMA_CONTIGUOUS_H
-#define ASMARM_DMA_CONTIGUOUS_H
-
-#ifdef __KERNEL__
-#ifdef CONFIG_DMA_CMA
-
-#include <linux/types.h>
-
-void dma_contiguous_early_fixup(phys_addr_t base, unsigned long size);
-
-#endif
-#endif
-
-#endif
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 154c24cec94c..911fc6ea2607 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -34,7 +34,6 @@
 #include <asm/dma-iommu.h>
 #include <asm/mach/map.h>
 #include <asm/system_info.h>
-#include <asm/dma-contiguous.h>
 #include <xen/swiotlb-xen.h>
 
 #include "dma.h"
diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild
index 74b0612601dd..62ebdc731ee2 100644
--- a/include/asm-generic/Kbuild
+++ b/include/asm-generic/Kbuild
@@ -16,7 +16,6 @@ mandatory-y += current.h
 mandatory-y += delay.h
 mandatory-y += device.h
 mandatory-y += div64.h
-mandatory-y += dma-contiguous.h
 mandatory-y += dma-mapping.h
 mandatory-y += dma.h
 mandatory-y += emergency-restart.h
diff --git a/include/asm-generic/dma-contiguous.h b/include/asm-generic/dma-contiguous.h
deleted file mode 100644
index f24b0f9a4f05..000000000000
--- a/include/asm-generic/dma-contiguous.h
+++ /dev/null
@@ -1,10 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_GENERIC_DMA_CONTIGUOUS_H
-#define _ASM_GENERIC_DMA_CONTIGUOUS_H
-
-#include <linux/types.h>
-
-static inline void
-dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { }
-
-#endif
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 474fc81bd492..7912f5d00ed9 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -116,6 +116,8 @@ bool dma_release_from_contiguous(struct device *dev, struct page *pages,
 				 int count);
 struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp);
 void dma_free_contiguous(struct device *dev, struct page *page, size_t size);
+
+void dma_contiguous_early_fixup(phys_addr_t base, unsigned long size);
 #else /* CONFIG_DMA_CMA */
 static inline struct cma *dev_get_cma_area(struct device *dev)
 {
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index 6bfb763fff6f..a2ee330a3749 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -44,7 +44,6 @@
 #endif
 
 #include <asm/page.h>
-#include <asm/dma-contiguous.h>
 
 #include <linux/memblock.h>
 #include <linux/err.h>
@@ -212,6 +211,11 @@ void __init dma_contiguous_reserve(phys_addr_t limit)
 	}
 }
 
+void __weak
+dma_contiguous_early_fixup(phys_addr_t base, unsigned long size)
+{
+}
+
 /**
  * dma_contiguous_reserve_area() - reserve custom contiguous area
  * @size: Size of the reserved area (in bytes),
-- 
cgit v1.2.3


From a1fd09e8e6ae35228ecc7c1e4bfff1fd725f78a0 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 11 Sep 2020 10:12:44 +0200
Subject: dma-mapping: move dma-debug.h to kernel/dma/

Most of dma-debug.h is not required by anything outside of kernel/dma.
Move the four declarations needed by dma-mappin.h or dma-ops providers
into dma-mapping.h and dma-map-ops.h, and move the remainder of the
file to kernel/dma/debug.h.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 arch/arm/include/asm/dma-iommu.h   |   1 -
 arch/arm/include/asm/dma-mapping.h |   1 -
 arch/microblaze/kernel/dma.c       |   1 -
 arch/sh/drivers/pci/pci.c          |   1 -
 arch/x86/include/asm/dma-mapping.h |   1 -
 arch/x86/kernel/pci-dma.c          |   1 -
 drivers/pci/pci-driver.c           |   1 +
 include/linux/dma-debug.h          | 160 -------------------------------------
 include/linux/dma-map-ops.h        |  12 +++
 include/linux/dma-mapping.h        |  16 +++-
 kernel/dma/debug.c                 |   5 +-
 kernel/dma/debug.h                 | 122 ++++++++++++++++++++++++++++
 kernel/dma/mapping.c               |   1 +
 mm/memory.c                        |   1 -
 14 files changed, 153 insertions(+), 171 deletions(-)
 delete mode 100644 include/linux/dma-debug.h
 create mode 100644 kernel/dma/debug.h

(limited to 'include/linux')

diff --git a/arch/arm/include/asm/dma-iommu.h b/arch/arm/include/asm/dma-iommu.h
index 86405cc81385..fe9ef6f79e9c 100644
--- a/arch/arm/include/asm/dma-iommu.h
+++ b/arch/arm/include/asm/dma-iommu.h
@@ -6,7 +6,6 @@
 
 #include <linux/mm_types.h>
 #include <linux/scatterlist.h>
-#include <linux/dma-debug.h>
 #include <linux/kref.h>
 
 struct dma_iommu_mapping {
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index 0a1a536368c3..77082246a5e1 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -6,7 +6,6 @@
 
 #include <linux/mm_types.h>
 #include <linux/scatterlist.h>
-#include <linux/dma-debug.h>
 
 #include <xen/xen.h>
 #include <asm/xen/hypervisor.h>
diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c
index d7bebd04247b..a564863db06e 100644
--- a/arch/microblaze/kernel/dma.c
+++ b/arch/microblaze/kernel/dma.c
@@ -10,7 +10,6 @@
 #include <linux/device.h>
 #include <linux/dma-noncoherent.h>
 #include <linux/gfp.h>
-#include <linux/dma-debug.h>
 #include <linux/export.h>
 #include <linux/bug.h>
 #include <asm/cacheflush.h>
diff --git a/arch/sh/drivers/pci/pci.c b/arch/sh/drivers/pci/pci.c
index 6ab0b7377f66..a3903304f33f 100644
--- a/arch/sh/drivers/pci/pci.c
+++ b/arch/sh/drivers/pci/pci.c
@@ -13,7 +13,6 @@
 #include <linux/pci.h>
 #include <linux/init.h>
 #include <linux/types.h>
-#include <linux/dma-debug.h>
 #include <linux/io.h>
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index e0c380b3ec14..bb1654fe0ce7 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -8,7 +8,6 @@
  */
 
 #include <linux/scatterlist.h>
-#include <linux/dma-debug.h>
 #include <asm/io.h>
 #include <asm/swiotlb.h>
 
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 4892dd043d41..de234e7a8962 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/dma-map-ops.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-debug.h>
 #include <linux/iommu.h>
 #include <linux/dmar.h>
 #include <linux/export.h>
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index 449466f71040..d1b7169c0684 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -19,6 +19,7 @@
 #include <linux/kexec.h>
 #include <linux/of_device.h>
 #include <linux/acpi.h>
+#include <linux/dma-map-ops.h>
 #include "pci.h"
 #include "pcie/portdrv.h"
 
diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h
deleted file mode 100644
index 7b3b04ba60f3..000000000000
--- a/include/linux/dma-debug.h
+++ /dev/null
@@ -1,160 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2008 Advanced Micro Devices, Inc.
- *
- * Author: Joerg Roedel <joerg.roedel@amd.com>
- */
-
-#ifndef __DMA_DEBUG_H
-#define __DMA_DEBUG_H
-
-#include <linux/types.h>
-
-struct device;
-struct scatterlist;
-struct bus_type;
-
-#ifdef CONFIG_DMA_API_DEBUG
-
-extern void dma_debug_add_bus(struct bus_type *bus);
-
-extern void debug_dma_map_single(struct device *dev, const void *addr,
-				 unsigned long len);
-
-extern void debug_dma_map_page(struct device *dev, struct page *page,
-			       size_t offset, size_t size,
-			       int direction, dma_addr_t dma_addr);
-
-extern void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr);
-
-extern void debug_dma_unmap_page(struct device *dev, dma_addr_t addr,
-				 size_t size, int direction);
-
-extern void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
-			     int nents, int mapped_ents, int direction);
-
-extern void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
-			       int nelems, int dir);
-
-extern void debug_dma_alloc_coherent(struct device *dev, size_t size,
-				     dma_addr_t dma_addr, void *virt);
-
-extern void debug_dma_free_coherent(struct device *dev, size_t size,
-				    void *virt, dma_addr_t addr);
-
-extern void debug_dma_map_resource(struct device *dev, phys_addr_t addr,
-				   size_t size, int direction,
-				   dma_addr_t dma_addr);
-
-extern void debug_dma_unmap_resource(struct device *dev, dma_addr_t dma_addr,
-				     size_t size, int direction);
-
-extern void debug_dma_sync_single_for_cpu(struct device *dev,
-					  dma_addr_t dma_handle, size_t size,
-					  int direction);
-
-extern void debug_dma_sync_single_for_device(struct device *dev,
-					     dma_addr_t dma_handle,
-					     size_t size, int direction);
-
-extern void debug_dma_sync_sg_for_cpu(struct device *dev,
-				      struct scatterlist *sg,
-				      int nelems, int direction);
-
-extern void debug_dma_sync_sg_for_device(struct device *dev,
-					 struct scatterlist *sg,
-					 int nelems, int direction);
-
-extern void debug_dma_dump_mappings(struct device *dev);
-
-#else /* CONFIG_DMA_API_DEBUG */
-
-static inline void dma_debug_add_bus(struct bus_type *bus)
-{
-}
-
-static inline void debug_dma_map_single(struct device *dev, const void *addr,
-					unsigned long len)
-{
-}
-
-static inline void debug_dma_map_page(struct device *dev, struct page *page,
-				      size_t offset, size_t size,
-				      int direction, dma_addr_t dma_addr)
-{
-}
-
-static inline void debug_dma_mapping_error(struct device *dev,
-					  dma_addr_t dma_addr)
-{
-}
-
-static inline void debug_dma_unmap_page(struct device *dev, dma_addr_t addr,
-					size_t size, int direction)
-{
-}
-
-static inline void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
-				    int nents, int mapped_ents, int direction)
-{
-}
-
-static inline void debug_dma_unmap_sg(struct device *dev,
-				      struct scatterlist *sglist,
-				      int nelems, int dir)
-{
-}
-
-static inline void debug_dma_alloc_coherent(struct device *dev, size_t size,
-					    dma_addr_t dma_addr, void *virt)
-{
-}
-
-static inline void debug_dma_free_coherent(struct device *dev, size_t size,
-					   void *virt, dma_addr_t addr)
-{
-}
-
-static inline void debug_dma_map_resource(struct device *dev, phys_addr_t addr,
-					  size_t size, int direction,
-					  dma_addr_t dma_addr)
-{
-}
-
-static inline void debug_dma_unmap_resource(struct device *dev,
-					    dma_addr_t dma_addr, size_t size,
-					    int direction)
-{
-}
-
-static inline void debug_dma_sync_single_for_cpu(struct device *dev,
-						 dma_addr_t dma_handle,
-						 size_t size, int direction)
-{
-}
-
-static inline void debug_dma_sync_single_for_device(struct device *dev,
-						    dma_addr_t dma_handle,
-						    size_t size, int direction)
-{
-}
-
-static inline void debug_dma_sync_sg_for_cpu(struct device *dev,
-					     struct scatterlist *sg,
-					     int nelems, int direction)
-{
-}
-
-static inline void debug_dma_sync_sg_for_device(struct device *dev,
-						struct scatterlist *sg,
-						int nelems, int direction)
-{
-}
-
-static inline void debug_dma_dump_mappings(struct device *dev)
-{
-}
-
-#endif /* CONFIG_DMA_API_DEBUG */
-
-#endif /* __DMA_DEBUG_H */
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 7912f5d00ed9..9891def42da7 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -220,6 +220,18 @@ static inline void arch_teardown_dma_ops(struct device *dev)
 }
 #endif /* CONFIG_ARCH_HAS_TEARDOWN_DMA_OPS */
 
+#ifdef CONFIG_DMA_API_DEBUG
+void dma_debug_add_bus(struct bus_type *bus);
+void debug_dma_dump_mappings(struct device *dev);
+#else
+static inline void dma_debug_add_bus(struct bus_type *bus)
+{
+}
+static inline void debug_dma_dump_mappings(struct device *dev)
+{
+}
+#endif /* CONFIG_DMA_API_DEBUG */
+
 extern const struct dma_map_ops dma_dummy_ops;
 
 #endif /* _LINUX_DMA_MAP_OPS_H */
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 9591cd482d7c..3f029afdc9dc 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -6,7 +6,6 @@
 #include <linux/string.h>
 #include <linux/device.h>
 #include <linux/err.h>
-#include <linux/dma-debug.h>
 #include <linux/dma-direction.h>
 #include <linux/scatterlist.h>
 #include <linux/bug.h>
@@ -76,6 +75,21 @@
 
 #define DMA_BIT_MASK(n)	(((n) == 64) ? ~0ULL : ((1ULL<<(n))-1))
 
+#ifdef CONFIG_DMA_API_DEBUG
+void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr);
+void debug_dma_map_single(struct device *dev, const void *addr,
+		unsigned long len);
+#else
+static inline void debug_dma_mapping_error(struct device *dev,
+		dma_addr_t dma_addr)
+{
+}
+static inline void debug_dma_map_single(struct device *dev, const void *addr,
+		unsigned long len)
+{
+}
+#endif /* CONFIG_DMA_API_DEBUG */
+
 #ifdef CONFIG_HAS_DMA
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index 4211800d9f3e..14de1271463f 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -9,10 +9,9 @@
 
 #include <linux/sched/task_stack.h>
 #include <linux/scatterlist.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/sched/task.h>
 #include <linux/stacktrace.h>
-#include <linux/dma-debug.h>
 #include <linux/spinlock.h>
 #include <linux/vmalloc.h>
 #include <linux/debugfs.h>
@@ -24,8 +23,8 @@
 #include <linux/ctype.h>
 #include <linux/list.h>
 #include <linux/slab.h>
-
 #include <asm/sections.h>
+#include "debug.h"
 
 #define HASH_SIZE       16384ULL
 #define HASH_FN_SHIFT   13
diff --git a/kernel/dma/debug.h b/kernel/dma/debug.h
new file mode 100644
index 000000000000..83643b3010b2
--- /dev/null
+++ b/kernel/dma/debug.h
@@ -0,0 +1,122 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2008 Advanced Micro Devices, Inc.
+ *
+ * Author: Joerg Roedel <joerg.roedel@amd.com>
+ */
+
+#ifndef _KERNEL_DMA_DEBUG_H
+#define _KERNEL_DMA_DEBUG_H
+
+#ifdef CONFIG_DMA_API_DEBUG
+extern void debug_dma_map_page(struct device *dev, struct page *page,
+			       size_t offset, size_t size,
+			       int direction, dma_addr_t dma_addr);
+
+extern void debug_dma_unmap_page(struct device *dev, dma_addr_t addr,
+				 size_t size, int direction);
+
+extern void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
+			     int nents, int mapped_ents, int direction);
+
+extern void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
+			       int nelems, int dir);
+
+extern void debug_dma_alloc_coherent(struct device *dev, size_t size,
+				     dma_addr_t dma_addr, void *virt);
+
+extern void debug_dma_free_coherent(struct device *dev, size_t size,
+				    void *virt, dma_addr_t addr);
+
+extern void debug_dma_map_resource(struct device *dev, phys_addr_t addr,
+				   size_t size, int direction,
+				   dma_addr_t dma_addr);
+
+extern void debug_dma_unmap_resource(struct device *dev, dma_addr_t dma_addr,
+				     size_t size, int direction);
+
+extern void debug_dma_sync_single_for_cpu(struct device *dev,
+					  dma_addr_t dma_handle, size_t size,
+					  int direction);
+
+extern void debug_dma_sync_single_for_device(struct device *dev,
+					     dma_addr_t dma_handle,
+					     size_t size, int direction);
+
+extern void debug_dma_sync_sg_for_cpu(struct device *dev,
+				      struct scatterlist *sg,
+				      int nelems, int direction);
+
+extern void debug_dma_sync_sg_for_device(struct device *dev,
+					 struct scatterlist *sg,
+					 int nelems, int direction);
+#else /* CONFIG_DMA_API_DEBUG */
+static inline void debug_dma_map_page(struct device *dev, struct page *page,
+				      size_t offset, size_t size,
+				      int direction, dma_addr_t dma_addr)
+{
+}
+
+static inline void debug_dma_unmap_page(struct device *dev, dma_addr_t addr,
+					size_t size, int direction)
+{
+}
+
+static inline void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
+				    int nents, int mapped_ents, int direction)
+{
+}
+
+static inline void debug_dma_unmap_sg(struct device *dev,
+				      struct scatterlist *sglist,
+				      int nelems, int dir)
+{
+}
+
+static inline void debug_dma_alloc_coherent(struct device *dev, size_t size,
+					    dma_addr_t dma_addr, void *virt)
+{
+}
+
+static inline void debug_dma_free_coherent(struct device *dev, size_t size,
+					   void *virt, dma_addr_t addr)
+{
+}
+
+static inline void debug_dma_map_resource(struct device *dev, phys_addr_t addr,
+					  size_t size, int direction,
+					  dma_addr_t dma_addr)
+{
+}
+
+static inline void debug_dma_unmap_resource(struct device *dev,
+					    dma_addr_t dma_addr, size_t size,
+					    int direction)
+{
+}
+
+static inline void debug_dma_sync_single_for_cpu(struct device *dev,
+						 dma_addr_t dma_handle,
+						 size_t size, int direction)
+{
+}
+
+static inline void debug_dma_sync_single_for_device(struct device *dev,
+						    dma_addr_t dma_handle,
+						    size_t size, int direction)
+{
+}
+
+static inline void debug_dma_sync_sg_for_cpu(struct device *dev,
+					     struct scatterlist *sg,
+					     int nelems, int direction)
+{
+}
+
+static inline void debug_dma_sync_sg_for_device(struct device *dev,
+						struct scatterlist *sg,
+						int nelems, int direction)
+{
+}
+#endif /* CONFIG_DMA_API_DEBUG */
+#endif /* _KERNEL_DMA_DEBUG_H */
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 2e13e6d3903f..335ba183e095 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -14,6 +14,7 @@
 #include <linux/of_device.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
+#include "debug.h"
 
 /*
  * Managed DMA API
diff --git a/mm/memory.c b/mm/memory.c
index f3eb55975902..7e4e8b81a738 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -65,7 +65,6 @@
 #include <linux/gfp.h>
 #include <linux/migrate.h>
 #include <linux/string.h>
-#include <linux/dma-debug.h>
 #include <linux/debugfs.h>
 #include <linux/userfaultfd_k.h>
 #include <linux/dax.h>
-- 
cgit v1.2.3


From 19c65c3d30bb5a97170e425979d2e44ab2096c7d Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 22 Sep 2020 15:34:22 +0200
Subject: dma-mapping: move large parts of <linux/dma-direct.h> to kernel/dma

Most of the dma_direct symbols should only be used by direct.c and
mapping.c, so move them to kernel/dma.  In fact more of dma-direct.h
should eventually move, but that will require more coordination with
other subsystems.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/dma-direct.h | 106 ----------------------------------------
 kernel/dma/direct.c        |   2 +-
 kernel/dma/direct.h        | 119 +++++++++++++++++++++++++++++++++++++++++++++
 kernel/dma/mapping.c       |   2 +-
 4 files changed, 121 insertions(+), 108 deletions(-)
 create mode 100644 kernel/dma/direct.h

(limited to 'include/linux')

diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 38ed3b55034d..a2d6640c42c0 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -120,114 +120,8 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
 void dma_direct_free_pages(struct device *dev, size_t size,
 		struct page *page, dma_addr_t dma_addr,
 		enum dma_data_direction dir);
-int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt,
-		void *cpu_addr, dma_addr_t dma_addr, size_t size,
-		unsigned long attrs);
-bool dma_direct_can_mmap(struct device *dev);
-int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
-		void *cpu_addr, dma_addr_t dma_addr, size_t size,
-		unsigned long attrs);
 int dma_direct_supported(struct device *dev, u64 mask);
-bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr);
-int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
-		enum dma_data_direction dir, unsigned long attrs);
 dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs);
-size_t dma_direct_max_mapping_size(struct device *dev);
 
-#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
-    defined(CONFIG_SWIOTLB)
-void dma_direct_sync_sg_for_device(struct device *dev, struct scatterlist *sgl,
-		int nents, enum dma_data_direction dir);
-#else
-static inline void dma_direct_sync_sg_for_device(struct device *dev,
-		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
-{
-}
-#endif
-
-#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
-    defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \
-    defined(CONFIG_SWIOTLB)
-void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
-		int nents, enum dma_data_direction dir, unsigned long attrs);
-void dma_direct_sync_sg_for_cpu(struct device *dev,
-		struct scatterlist *sgl, int nents, enum dma_data_direction dir);
-#else
-static inline void dma_direct_unmap_sg(struct device *dev,
-		struct scatterlist *sgl, int nents, enum dma_data_direction dir,
-		unsigned long attrs)
-{
-}
-static inline void dma_direct_sync_sg_for_cpu(struct device *dev,
-		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
-{
-}
-#endif
-
-static inline void dma_direct_sync_single_for_device(struct device *dev,
-		dma_addr_t addr, size_t size, enum dma_data_direction dir)
-{
-	phys_addr_t paddr = dma_to_phys(dev, addr);
-
-	if (unlikely(is_swiotlb_buffer(paddr)))
-		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE);
-
-	if (!dev_is_dma_coherent(dev))
-		arch_sync_dma_for_device(paddr, size, dir);
-}
-
-static inline void dma_direct_sync_single_for_cpu(struct device *dev,
-		dma_addr_t addr, size_t size, enum dma_data_direction dir)
-{
-	phys_addr_t paddr = dma_to_phys(dev, addr);
-
-	if (!dev_is_dma_coherent(dev)) {
-		arch_sync_dma_for_cpu(paddr, size, dir);
-		arch_sync_dma_for_cpu_all();
-	}
-
-	if (unlikely(is_swiotlb_buffer(paddr)))
-		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU);
-
-	if (dir == DMA_FROM_DEVICE)
-		arch_dma_mark_clean(paddr, size);
-}
-
-static inline dma_addr_t dma_direct_map_page(struct device *dev,
-		struct page *page, unsigned long offset, size_t size,
-		enum dma_data_direction dir, unsigned long attrs)
-{
-	phys_addr_t phys = page_to_phys(page) + offset;
-	dma_addr_t dma_addr = phys_to_dma(dev, phys);
-
-	if (unlikely(swiotlb_force == SWIOTLB_FORCE))
-		return swiotlb_map(dev, phys, size, dir, attrs);
-
-	if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
-		if (swiotlb_force != SWIOTLB_NO_FORCE)
-			return swiotlb_map(dev, phys, size, dir, attrs);
-
-		dev_WARN_ONCE(dev, 1,
-			     "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
-			     &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
-		return DMA_MAPPING_ERROR;
-	}
-
-	if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		arch_sync_dma_for_device(phys, size, dir);
-	return dma_addr;
-}
-
-static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
-		size_t size, enum dma_data_direction dir, unsigned long attrs)
-{
-	phys_addr_t phys = dma_to_phys(dev, addr);
-
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		dma_direct_sync_single_for_cpu(dev, addr, size, dir);
-
-	if (unlikely(is_swiotlb_buffer(phys)))
-		swiotlb_tbl_unmap_single(dev, phys, size, size, dir, attrs);
-}
 #endif /* _LINUX_DMA_DIRECT_H */
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 87697c86f0b8..bf9f77623022 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -7,13 +7,13 @@
 #include <linux/memblock.h> /* for max_pfn */
 #include <linux/export.h>
 #include <linux/mm.h>
-#include <linux/dma-direct.h>
 #include <linux/dma-map-ops.h>
 #include <linux/scatterlist.h>
 #include <linux/pfn.h>
 #include <linux/vmalloc.h>
 #include <linux/set_memory.h>
 #include <linux/slab.h>
+#include "direct.h"
 
 /*
  * Most architectures use ZONE_DMA for the first 16 Megabytes, but some use it
diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h
new file mode 100644
index 000000000000..b98615578737
--- /dev/null
+++ b/kernel/dma/direct.h
@@ -0,0 +1,119 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018 Christoph Hellwig.
+ *
+ * DMA operations that map physical memory directly without using an IOMMU.
+ */
+#ifndef _KERNEL_DMA_DIRECT_H
+#define _KERNEL_DMA_DIRECT_H
+
+#include <linux/dma-direct.h>
+
+int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs);
+bool dma_direct_can_mmap(struct device *dev);
+int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs);
+bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr);
+int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
+		enum dma_data_direction dir, unsigned long attrs);
+size_t dma_direct_max_mapping_size(struct device *dev);
+
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
+    defined(CONFIG_SWIOTLB)
+void dma_direct_sync_sg_for_device(struct device *dev, struct scatterlist *sgl,
+		int nents, enum dma_data_direction dir);
+#else
+static inline void dma_direct_sync_sg_for_device(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+}
+#endif
+
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
+    defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \
+    defined(CONFIG_SWIOTLB)
+void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
+		int nents, enum dma_data_direction dir, unsigned long attrs);
+void dma_direct_sync_sg_for_cpu(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir);
+#else
+static inline void dma_direct_unmap_sg(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+}
+static inline void dma_direct_sync_sg_for_cpu(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+}
+#endif
+
+static inline void dma_direct_sync_single_for_device(struct device *dev,
+		dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+	phys_addr_t paddr = dma_to_phys(dev, addr);
+
+	if (unlikely(is_swiotlb_buffer(paddr)))
+		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE);
+
+	if (!dev_is_dma_coherent(dev))
+		arch_sync_dma_for_device(paddr, size, dir);
+}
+
+static inline void dma_direct_sync_single_for_cpu(struct device *dev,
+		dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+	phys_addr_t paddr = dma_to_phys(dev, addr);
+
+	if (!dev_is_dma_coherent(dev)) {
+		arch_sync_dma_for_cpu(paddr, size, dir);
+		arch_sync_dma_for_cpu_all();
+	}
+
+	if (unlikely(is_swiotlb_buffer(paddr)))
+		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU);
+
+	if (dir == DMA_FROM_DEVICE)
+		arch_dma_mark_clean(paddr, size);
+}
+
+static inline dma_addr_t dma_direct_map_page(struct device *dev,
+		struct page *page, unsigned long offset, size_t size,
+		enum dma_data_direction dir, unsigned long attrs)
+{
+	phys_addr_t phys = page_to_phys(page) + offset;
+	dma_addr_t dma_addr = phys_to_dma(dev, phys);
+
+	if (unlikely(swiotlb_force == SWIOTLB_FORCE))
+		return swiotlb_map(dev, phys, size, dir, attrs);
+
+	if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
+		if (swiotlb_force != SWIOTLB_NO_FORCE)
+			return swiotlb_map(dev, phys, size, dir, attrs);
+
+		dev_WARN_ONCE(dev, 1,
+			     "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
+			     &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
+		return DMA_MAPPING_ERROR;
+	}
+
+	if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		arch_sync_dma_for_device(phys, size, dir);
+	return dma_addr;
+}
+
+static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	phys_addr_t phys = dma_to_phys(dev, addr);
+
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		dma_direct_sync_single_for_cpu(dev, addr, size, dir);
+
+	if (unlikely(is_swiotlb_buffer(phys)))
+		swiotlb_tbl_unmap_single(dev, phys, size, size, dir, attrs);
+}
+#endif /* _KERNEL_DMA_DIRECT_H */
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 335ba183e095..51bb8fa8eb89 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -7,7 +7,6 @@
  */
 #include <linux/memblock.h> /* for max_pfn */
 #include <linux/acpi.h>
-#include <linux/dma-direct.h>
 #include <linux/dma-map-ops.h>
 #include <linux/export.h>
 #include <linux/gfp.h>
@@ -15,6 +14,7 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include "debug.h"
+#include "direct.h"
 
 /*
  * Managed DMA API
-- 
cgit v1.2.3


From 9f4df96b8781e40d0cb0e32eb3d1f6d87375adf9 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 22 Sep 2020 15:36:11 +0200
Subject: dma-mapping: merge <linux/dma-noncoherent.h> into
 <linux/dma-map-ops.h>

Move more nitty gritty DMA implementation details into the common
internal header.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 MAINTAINERS                       |   1 -
 arch/arc/mm/dma.c                 |   1 -
 arch/arm/mm/dma-mapping.c         |   1 -
 arch/arm/xen/mm.c                 |   2 +-
 arch/arm64/mm/dma-mapping.c       |   1 -
 arch/c6x/mm/dma-coherent.c        |   2 +-
 arch/csky/mm/dma-mapping.c        |   1 -
 arch/hexagon/kernel/dma.c         |   2 +-
 arch/ia64/mm/init.c               |   2 +-
 arch/m68k/kernel/dma.c            |   2 +-
 arch/microblaze/kernel/dma.c      |   2 +-
 arch/microblaze/mm/consistent.c   |   2 +-
 arch/mips/jazz/jazzdma.c          |   1 -
 arch/mips/mm/dma-noncoherent.c    |   1 -
 arch/nds32/kernel/dma.c           |   2 +-
 arch/openrisc/kernel/dma.c        |   2 +-
 arch/parisc/kernel/pci-dma.c      |   2 +-
 arch/powerpc/mm/dma-noncoherent.c |   2 +-
 arch/sh/kernel/dma-coherent.c     |   2 +-
 arch/sparc/kernel/ioport.c        |   2 +-
 arch/xtensa/kernel/pci-dma.c      |   1 -
 drivers/iommu/dma-iommu.c         |   1 -
 drivers/xen/swiotlb-xen.c         |   3 +-
 include/linux/dma-direct.h        |   2 +-
 include/linux/dma-map-ops.h       | 102 +++++++++++++++++++++++++++++++++++
 include/linux/dma-noncoherent.h   | 109 --------------------------------------
 kernel/dma/ops_helpers.c          |   1 -
 kernel/dma/pool.c                 |   1 -
 kernel/dma/swiotlb.c              |   2 +-
 29 files changed, 118 insertions(+), 137 deletions(-)
 delete mode 100644 include/linux/dma-noncoherent.h

(limited to 'include/linux')

diff --git a/MAINTAINERS b/MAINTAINERS
index b13fc1794307..c0dbe6e9de65 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5203,7 +5203,6 @@ F:	include/asm-generic/dma-mapping.h
 F:	include/linux/dma-direct.h
 F:	include/linux/dma-mapping.h
 F:	include/linux/dma-map-ops.h
-F:	include/linux/dma-noncoherent.h
 F:	kernel/dma/
 
 DMA-BUF HEAPS FRAMEWORK
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index a8c453e98d75..517988e60cfc 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -4,7 +4,6 @@
  */
 
 #include <linux/dma-map-ops.h>
-#include <linux/dma-noncoherent.h>
 #include <asm/cache.h>
 #include <asm/cacheflush.h>
 
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 911fc6ea2607..c4b8df2ad328 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -16,7 +16,6 @@
 #include <linux/device.h>
 #include <linux/dma-direct.h>
 #include <linux/dma-map-ops.h>
-#include <linux/dma-noncoherent.h>
 #include <linux/highmem.h>
 #include <linux/memblock.h>
 #include <linux/slab.h>
diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index 396797ffe2b1..5c80088db13b 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-only
 #include <linux/cpu.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/gfp.h>
 #include <linux/highmem.h>
 #include <linux/export.h>
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 3afd3bd659d8..93e87b287556 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -7,7 +7,6 @@
 #include <linux/gfp.h>
 #include <linux/cache.h>
 #include <linux/dma-map-ops.h>
-#include <linux/dma-noncoherent.h>
 #include <linux/dma-iommu.h>
 #include <xen/xen.h>
 #include <xen/swiotlb-xen.h>
diff --git a/arch/c6x/mm/dma-coherent.c b/arch/c6x/mm/dma-coherent.c
index a5909091cb14..03df07a831fc 100644
--- a/arch/c6x/mm/dma-coherent.c
+++ b/arch/c6x/mm/dma-coherent.c
@@ -15,7 +15,7 @@
 #include <linux/bitops.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/memblock.h>
 
 #include <asm/cacheflush.h>
diff --git a/arch/csky/mm/dma-mapping.c b/arch/csky/mm/dma-mapping.c
index 3d9ff26c4bb4..c3a775a7e8f9 100644
--- a/arch/csky/mm/dma-mapping.c
+++ b/arch/csky/mm/dma-mapping.c
@@ -3,7 +3,6 @@
 
 #include <linux/cache.h>
 #include <linux/dma-map-ops.h>
-#include <linux/dma-noncoherent.h>
 #include <linux/genalloc.h>
 #include <linux/highmem.h>
 #include <linux/io.h>
diff --git a/arch/hexagon/kernel/dma.c b/arch/hexagon/kernel/dma.c
index 25f388d9cfcc..00b9a81075dd 100644
--- a/arch/hexagon/kernel/dma.c
+++ b/arch/hexagon/kernel/dma.c
@@ -5,7 +5,7 @@
  * Copyright (c) 2010-2012, The Linux Foundation. All rights reserved.
  */
 
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/memblock.h>
 #include <linux/genalloc.h>
 #include <linux/module.h>
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 02e5aa08294e..ccba04d12671 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -8,7 +8,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dmar.h>
 #include <linux/efi.h>
 #include <linux/elf.h>
diff --git a/arch/m68k/kernel/dma.c b/arch/m68k/kernel/dma.c
index b1ca3522eccc..1c1b875fadc1 100644
--- a/arch/m68k/kernel/dma.c
+++ b/arch/m68k/kernel/dma.c
@@ -6,7 +6,7 @@
 
 #undef DEBUG
 
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/device.h>
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c
index a564863db06e..04d091ade417 100644
--- a/arch/microblaze/kernel/dma.c
+++ b/arch/microblaze/kernel/dma.c
@@ -8,7 +8,7 @@
  */
 
 #include <linux/device.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/gfp.h>
 #include <linux/export.h>
 #include <linux/bug.h>
diff --git a/arch/microblaze/mm/consistent.c b/arch/microblaze/mm/consistent.c
index e09b66e43cb6..81dffe43b18c 100644
--- a/arch/microblaze/mm/consistent.c
+++ b/arch/microblaze/mm/consistent.c
@@ -11,7 +11,7 @@
 #include <linux/types.h>
 #include <linux/mm.h>
 #include <linux/init.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <asm/cpuinfo.h>
 #include <asm/cacheflush.h>
 
diff --git a/arch/mips/jazz/jazzdma.c b/arch/mips/jazz/jazzdma.c
index b8fb42e56da0..461457b28982 100644
--- a/arch/mips/jazz/jazzdma.c
+++ b/arch/mips/jazz/jazzdma.c
@@ -17,7 +17,6 @@
 #include <linux/spinlock.h>
 #include <linux/gfp.h>
 #include <linux/dma-map-ops.h>
-#include <linux/dma-noncoherent.h>
 #include <asm/mipsregs.h>
 #include <asm/jazz.h>
 #include <asm/io.h>
diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c
index 22d99ccc70c8..38d3d9143b47 100644
--- a/arch/mips/mm/dma-noncoherent.c
+++ b/arch/mips/mm/dma-noncoherent.c
@@ -6,7 +6,6 @@
  */
 #include <linux/dma-direct.h>
 #include <linux/dma-map-ops.h>
-#include <linux/dma-noncoherent.h>
 #include <linux/highmem.h>
 
 #include <asm/cache.h>
diff --git a/arch/nds32/kernel/dma.c b/arch/nds32/kernel/dma.c
index 69d762182d49..2ac8e6c82a61 100644
--- a/arch/nds32/kernel/dma.c
+++ b/arch/nds32/kernel/dma.c
@@ -3,7 +3,7 @@
 
 #include <linux/types.h>
 #include <linux/mm.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/cache.h>
 #include <linux/highmem.h>
 #include <asm/cacheflush.h>
diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c
index 345727638d52..1b16d97e7da7 100644
--- a/arch/openrisc/kernel/dma.c
+++ b/arch/openrisc/kernel/dma.c
@@ -13,7 +13,7 @@
  * DMA mapping callbacks...
  */
 
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/pagewalk.h>
 
 #include <asm/cpuinfo.h>
diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c
index ce38c0b91581..36610a5c029f 100644
--- a/arch/parisc/kernel/pci-dma.c
+++ b/arch/parisc/kernel/pci-dma.c
@@ -26,7 +26,7 @@
 #include <linux/string.h>
 #include <linux/types.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 
 #include <asm/cacheflush.h>
 #include <asm/dma.h>    /* for DMA_CHUNK_SIZE */
diff --git a/arch/powerpc/mm/dma-noncoherent.c b/arch/powerpc/mm/dma-noncoherent.c
index 5ab4f868e919..30260b5d146d 100644
--- a/arch/powerpc/mm/dma-noncoherent.c
+++ b/arch/powerpc/mm/dma-noncoherent.c
@@ -11,7 +11,7 @@
 #include <linux/types.h>
 #include <linux/highmem.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 
 #include <asm/tlbflush.h>
 #include <asm/dma.h>
diff --git a/arch/sh/kernel/dma-coherent.c b/arch/sh/kernel/dma-coherent.c
index cd46a9825e3c..6a44c0e7ba40 100644
--- a/arch/sh/kernel/dma-coherent.c
+++ b/arch/sh/kernel/dma-coherent.c
@@ -3,7 +3,7 @@
  * Copyright (C) 2004 - 2007  Paul Mundt
  */
 #include <linux/mm.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <asm/cacheflush.h>
 #include <asm/addrspace.h>
 
diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c
index d6874c9b639f..8e1d72a16759 100644
--- a/arch/sparc/kernel/ioport.c
+++ b/arch/sparc/kernel/ioport.c
@@ -38,7 +38,7 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/scatterlist.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/of_device.h>
 
 #include <asm/io.h>
diff --git a/arch/xtensa/kernel/pci-dma.c b/arch/xtensa/kernel/pci-dma.c
index 790dbe022a07..94955caa4488 100644
--- a/arch/xtensa/kernel/pci-dma.c
+++ b/arch/xtensa/kernel/pci-dma.c
@@ -12,7 +12,6 @@
  */
 
 #include <linux/dma-map-ops.h>
-#include <linux/dma-noncoherent.h>
 #include <linux/dma-direct.h>
 #include <linux/gfp.h>
 #include <linux/highmem.h>
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 22c221bba13e..3a00fb64477b 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -12,7 +12,6 @@
 #include <linux/device.h>
 #include <linux/dma-map-ops.h>
 #include <linux/dma-iommu.h>
-#include <linux/dma-noncoherent.h>
 #include <linux/gfp.h>
 #include <linux/huge_mm.h>
 #include <linux/iommu.h>
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 71ff4bf38073..71ce1b7a23d1 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -27,9 +27,8 @@
 #define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt
 
 #include <linux/memblock.h>
-#include <linux/dma-map-ops.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/export.h>
 #include <xen/swiotlb-xen.h>
 #include <xen/page.h>
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index a2d6640c42c0..18aade195884 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -7,7 +7,7 @@
 #define _LINUX_DMA_DIRECT_H 1
 
 #include <linux/dma-mapping.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/memblock.h> /* for min_low_pfn */
 #include <linux/mem_encrypt.h>
 #include <linux/swiotlb.h>
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 9891def42da7..33c6e24707a9 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -7,6 +7,7 @@
 #define _LINUX_DMA_MAP_OPS_H
 
 #include <linux/dma-mapping.h>
+#include <linux/pgtable.h>
 
 struct cma;
 
@@ -202,6 +203,107 @@ static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma,
 }
 #endif /* CONFIG_DMA_DECLARE_COHERENT */
 
+#ifdef CONFIG_ARCH_HAS_DMA_COHERENCE_H
+#include <asm/dma-coherence.h>
+#elif defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
+	defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
+	defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL)
+static inline bool dev_is_dma_coherent(struct device *dev)
+{
+	return dev->dma_coherent;
+}
+#else
+static inline bool dev_is_dma_coherent(struct device *dev)
+{
+	return true;
+}
+#endif /* CONFIG_ARCH_HAS_DMA_COHERENCE_H */
+
+/*
+ * Check if an allocation needs to be marked uncached to be coherent.
+ */
+static __always_inline bool dma_alloc_need_uncached(struct device *dev,
+		unsigned long attrs)
+{
+	if (dev_is_dma_coherent(dev))
+		return false;
+	if (attrs & DMA_ATTR_NO_KERNEL_MAPPING)
+		return false;
+	return true;
+}
+
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		gfp_t gfp, unsigned long attrs);
+void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
+		dma_addr_t dma_addr, unsigned long attrs);
+
+#ifdef CONFIG_MMU
+/*
+ * Page protection so that devices that can't snoop CPU caches can use the
+ * memory coherently.  We default to pgprot_noncached which is usually used
+ * for ioremap as a safe bet, but architectures can override this with less
+ * strict semantics if possible.
+ */
+#ifndef pgprot_dmacoherent
+#define pgprot_dmacoherent(prot)	pgprot_noncached(prot)
+#endif
+
+pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs);
+#else
+static inline pgprot_t dma_pgprot(struct device *dev, pgprot_t prot,
+		unsigned long attrs)
+{
+	return prot;	/* no protection bits supported without page tables */
+}
+#endif /* CONFIG_MMU */
+
+#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir);
+#else
+static inline void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
+{
+}
+#endif /* ARCH_HAS_SYNC_DMA_FOR_DEVICE */
+
+#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir);
+#else
+static inline void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
+{
+}
+#endif /* ARCH_HAS_SYNC_DMA_FOR_CPU */
+
+#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL
+void arch_sync_dma_for_cpu_all(void);
+#else
+static inline void arch_sync_dma_for_cpu_all(void)
+{
+}
+#endif /* CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL */
+
+#ifdef CONFIG_ARCH_HAS_DMA_PREP_COHERENT
+void arch_dma_prep_coherent(struct page *page, size_t size);
+#else
+static inline void arch_dma_prep_coherent(struct page *page, size_t size)
+{
+}
+#endif /* CONFIG_ARCH_HAS_DMA_PREP_COHERENT */
+
+#ifdef CONFIG_ARCH_HAS_DMA_MARK_CLEAN
+void arch_dma_mark_clean(phys_addr_t paddr, size_t size);
+#else
+static inline void arch_dma_mark_clean(phys_addr_t paddr, size_t size)
+{
+}
+#endif /* ARCH_HAS_DMA_MARK_CLEAN */
+
+void *arch_dma_set_uncached(void *addr, size_t size);
+void arch_dma_clear_uncached(void *addr, size_t size);
+
 #ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 		const struct iommu_ops *iommu, bool coherent);
diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h
deleted file mode 100644
index e61283e06576..000000000000
--- a/include/linux/dma-noncoherent.h
+++ /dev/null
@@ -1,109 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_DMA_NONCOHERENT_H
-#define _LINUX_DMA_NONCOHERENT_H 1
-
-#include <linux/dma-mapping.h>
-#include <linux/pgtable.h>
-
-#ifdef CONFIG_ARCH_HAS_DMA_COHERENCE_H
-#include <asm/dma-coherence.h>
-#elif defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
-	defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
-	defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL)
-static inline bool dev_is_dma_coherent(struct device *dev)
-{
-	return dev->dma_coherent;
-}
-#else
-static inline bool dev_is_dma_coherent(struct device *dev)
-{
-	return true;
-}
-#endif /* CONFIG_ARCH_HAS_DMA_COHERENCE_H */
-
-/*
- * Check if an allocation needs to be marked uncached to be coherent.
- */
-static __always_inline bool dma_alloc_need_uncached(struct device *dev,
-		unsigned long attrs)
-{
-	if (dev_is_dma_coherent(dev))
-		return false;
-	if (attrs & DMA_ATTR_NO_KERNEL_MAPPING)
-		return false;
-	return true;
-}
-
-void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
-		gfp_t gfp, unsigned long attrs);
-void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
-		dma_addr_t dma_addr, unsigned long attrs);
-
-#ifdef CONFIG_MMU
-/*
- * Page protection so that devices that can't snoop CPU caches can use the
- * memory coherently.  We default to pgprot_noncached which is usually used
- * for ioremap as a safe bet, but architectures can override this with less
- * strict semantics if possible.
- */
-#ifndef pgprot_dmacoherent
-#define pgprot_dmacoherent(prot)	pgprot_noncached(prot)
-#endif
-
-pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs);
-#else
-static inline pgprot_t dma_pgprot(struct device *dev, pgprot_t prot,
-		unsigned long attrs)
-{
-	return prot;	/* no protection bits supported without page tables */
-}
-#endif /* CONFIG_MMU */
-
-#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE
-void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
-		enum dma_data_direction dir);
-#else
-static inline void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
-		enum dma_data_direction dir)
-{
-}
-#endif /* ARCH_HAS_SYNC_DMA_FOR_DEVICE */
-
-#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU
-void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
-		enum dma_data_direction dir);
-#else
-static inline void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
-		enum dma_data_direction dir)
-{
-}
-#endif /* ARCH_HAS_SYNC_DMA_FOR_CPU */
-
-#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL
-void arch_sync_dma_for_cpu_all(void);
-#else
-static inline void arch_sync_dma_for_cpu_all(void)
-{
-}
-#endif /* CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL */
-
-#ifdef CONFIG_ARCH_HAS_DMA_PREP_COHERENT
-void arch_dma_prep_coherent(struct page *page, size_t size);
-#else
-static inline void arch_dma_prep_coherent(struct page *page, size_t size)
-{
-}
-#endif /* CONFIG_ARCH_HAS_DMA_PREP_COHERENT */
-
-#ifdef CONFIG_ARCH_HAS_DMA_MARK_CLEAN
-void arch_dma_mark_clean(phys_addr_t paddr, size_t size);
-#else
-static inline void arch_dma_mark_clean(phys_addr_t paddr, size_t size)
-{
-}
-#endif /* ARCH_HAS_DMA_MARK_CLEAN */
-
-void *arch_dma_set_uncached(void *addr, size_t size);
-void arch_dma_clear_uncached(void *addr, size_t size);
-
-#endif /* _LINUX_DMA_NONCOHERENT_H */
diff --git a/kernel/dma/ops_helpers.c b/kernel/dma/ops_helpers.c
index bc80fd2648bc..910ae69cae77 100644
--- a/kernel/dma/ops_helpers.c
+++ b/kernel/dma/ops_helpers.c
@@ -4,7 +4,6 @@
  * the allocated memory contains normal pages in the direct kernel mapping.
  */
 #include <linux/dma-map-ops.h>
-#include <linux/dma-noncoherent.h>
 
 /*
  * Create scatter-list for the already allocated DMA buffer.
diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c
index c9fb5c3d8bd0..d4637f72239b 100644
--- a/kernel/dma/pool.c
+++ b/kernel/dma/pool.c
@@ -7,7 +7,6 @@
 #include <linux/debugfs.h>
 #include <linux/dma-map-ops.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-noncoherent.h>
 #include <linux/init.h>
 #include <linux/genalloc.h>
 #include <linux/set_memory.h>
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 4ea72d145cd2..2be1e8b34ae3 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -22,7 +22,7 @@
 
 #include <linux/cache.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/mm.h>
 #include <linux/export.h>
 #include <linux/spinlock.h>
-- 
cgit v1.2.3


From 5de15b610f785f0e188fefb707f0b19de156968a Mon Sep 17 00:00:00 2001
From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Date: Sat, 3 Oct 2020 23:23:20 +0300
Subject: mtd: hyperbus: add Renesas RPC-IF driver

Add the HyperFLash driver for the Renesas RPC-IF.  It's the "front end"
driver using the "back end" APIs in the main driver to talk to the real
hardware.

Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com>
Link: https://lore.kernel.org/r/78abb851-2beb-fe7d-87e5-ce58ee877d35@gmail.com
---
 drivers/mtd/hyperbus/Kconfig  |   7 ++
 drivers/mtd/hyperbus/Makefile |   1 +
 drivers/mtd/hyperbus/rpc-if.c | 170 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/mtd/hyperbus.h  |  11 +++
 4 files changed, 189 insertions(+)
 create mode 100644 drivers/mtd/hyperbus/rpc-if.c

(limited to 'include/linux')

diff --git a/drivers/mtd/hyperbus/Kconfig b/drivers/mtd/hyperbus/Kconfig
index a4d8968d133d..35b3ab4c8b94 100644
--- a/drivers/mtd/hyperbus/Kconfig
+++ b/drivers/mtd/hyperbus/Kconfig
@@ -22,4 +22,11 @@ config HBMC_AM654
 	 This is the driver for HyperBus controller on TI's AM65x and
 	 other SoCs
 
+config RPCIF_HYPERBUS
+	tristate "Renesas RPC-IF HyperBus driver"
+	depends on RENESAS_RPCIF || COMPILE_TEST
+	depends on MTD_CFI_BE_BYTE_SWAP
+	help
+	  This option includes Renesas RPC-IF HyperBus support.
+
 endif # MTD_HYPERBUS
diff --git a/drivers/mtd/hyperbus/Makefile b/drivers/mtd/hyperbus/Makefile
index 8a936e066f48..5fc2b5124542 100644
--- a/drivers/mtd/hyperbus/Makefile
+++ b/drivers/mtd/hyperbus/Makefile
@@ -2,3 +2,4 @@
 
 obj-$(CONFIG_MTD_HYPERBUS)	+= hyperbus-core.o
 obj-$(CONFIG_HBMC_AM654)	+= hbmc-am654.o
+obj-$(CONFIG_RPCIF_HYPERBUS)	+= rpc-if.o
diff --git a/drivers/mtd/hyperbus/rpc-if.c b/drivers/mtd/hyperbus/rpc-if.c
new file mode 100644
index 000000000000..ecb050ba95cd
--- /dev/null
+++ b/drivers/mtd/hyperbus/rpc-if.c
@@ -0,0 +1,170 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Linux driver for RPC-IF HyperFlash
+ *
+ * Copyright (C) 2019-2020 Cogent Embedded, Inc.
+ */
+
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mtd/hyperbus.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mux/consumer.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/types.h>
+
+#include <memory/renesas-rpc-if.h>
+
+struct	rpcif_hyperbus {
+	struct rpcif rpc;
+	struct hyperbus_ctlr ctlr;
+	struct hyperbus_device hbdev;
+};
+
+static const struct rpcif_op rpcif_op_tmpl = {
+	.cmd = {
+		.buswidth = 8,
+		.ddr = true,
+	},
+	.ocmd = {
+		.buswidth = 8,
+		.ddr = true,
+	},
+	.addr = {
+		.nbytes = 1,
+		.buswidth = 8,
+		.ddr = true,
+	},
+	.data = {
+		.buswidth = 8,
+		.ddr = true,
+	},
+};
+
+static void rpcif_hb_prepare_read(struct rpcif *rpc, void *to,
+				  unsigned long from, ssize_t len)
+{
+	struct rpcif_op op = rpcif_op_tmpl;
+
+	op.cmd.opcode = HYPERBUS_RW_READ | HYPERBUS_AS_MEM;
+	op.addr.val = from >> 1;
+	op.dummy.buswidth = 1;
+	op.dummy.ncycles = 15;
+	op.data.dir = RPCIF_DATA_IN;
+	op.data.nbytes = len;
+	op.data.buf.in = to;
+
+	rpcif_prepare(rpc, &op, NULL, NULL);
+}
+
+static void rpcif_hb_prepare_write(struct rpcif *rpc, unsigned long to,
+				   void *from, ssize_t len)
+{
+	struct rpcif_op op = rpcif_op_tmpl;
+
+	op.cmd.opcode = HYPERBUS_RW_WRITE | HYPERBUS_AS_MEM;
+	op.addr.val = to >> 1;
+	op.data.dir = RPCIF_DATA_OUT;
+	op.data.nbytes = len;
+	op.data.buf.out = from;
+
+	rpcif_prepare(rpc, &op, NULL, NULL);
+}
+
+static u16 rpcif_hb_read16(struct hyperbus_device *hbdev, unsigned long addr)
+{
+	struct rpcif_hyperbus *hyperbus =
+		container_of(hbdev, struct rpcif_hyperbus, hbdev);
+	map_word data;
+
+	rpcif_hb_prepare_read(&hyperbus->rpc, &data, addr, 2);
+
+	rpcif_manual_xfer(&hyperbus->rpc);
+
+	return data.x[0];
+}
+
+static void rpcif_hb_write16(struct hyperbus_device *hbdev, unsigned long addr,
+			     u16 data)
+{
+	struct rpcif_hyperbus *hyperbus =
+		container_of(hbdev, struct rpcif_hyperbus, hbdev);
+
+	rpcif_hb_prepare_write(&hyperbus->rpc, addr, &data, 2);
+
+	rpcif_manual_xfer(&hyperbus->rpc);
+}
+
+static void rpcif_hb_copy_from(struct hyperbus_device *hbdev, void *to,
+			       unsigned long from, ssize_t len)
+{
+	struct rpcif_hyperbus *hyperbus =
+		container_of(hbdev, struct rpcif_hyperbus, hbdev);
+
+	rpcif_hb_prepare_read(&hyperbus->rpc, to, from, len);
+
+	rpcif_dirmap_read(&hyperbus->rpc, from, len, to);
+}
+
+static const struct hyperbus_ops rpcif_hb_ops = {
+	.read16 = rpcif_hb_read16,
+	.write16 = rpcif_hb_write16,
+	.copy_from = rpcif_hb_copy_from,
+};
+
+static int rpcif_hb_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct rpcif_hyperbus *hyperbus;
+	int error;
+
+	hyperbus = devm_kzalloc(dev, sizeof(*hyperbus), GFP_KERNEL);
+	if (!hyperbus)
+		return -ENOMEM;
+
+	rpcif_sw_init(&hyperbus->rpc, pdev->dev.parent);
+
+	platform_set_drvdata(pdev, hyperbus);
+
+	rpcif_enable_rpm(&hyperbus->rpc);
+
+	rpcif_hw_init(&hyperbus->rpc, true);
+
+	hyperbus->hbdev.map.size = hyperbus->rpc.size;
+	hyperbus->hbdev.map.virt = hyperbus->rpc.dirmap;
+
+	hyperbus->ctlr.dev = dev;
+	hyperbus->ctlr.ops = &rpcif_hb_ops;
+	hyperbus->hbdev.ctlr = &hyperbus->ctlr;
+	hyperbus->hbdev.np = of_get_next_child(pdev->dev.parent->of_node, NULL);
+	error = hyperbus_register_device(&hyperbus->hbdev);
+	if (error)
+		rpcif_disable_rpm(&hyperbus->rpc);
+
+	return error;
+}
+
+static int rpcif_hb_remove(struct platform_device *pdev)
+{
+	struct rpcif_hyperbus *hyperbus = platform_get_drvdata(pdev);
+	int error = hyperbus_unregister_device(&hyperbus->hbdev);
+	struct rpcif *rpc = dev_get_drvdata(pdev->dev.parent);
+
+	rpcif_disable_rpm(rpc);
+	return error;
+}
+
+static struct platform_driver rpcif_platform_driver = {
+	.probe	= rpcif_hb_probe,
+	.remove	= rpcif_hb_remove,
+	.driver	= {
+		.name	= "rpc-if-hyperflash",
+	},
+};
+
+module_platform_driver(rpcif_platform_driver);
+
+MODULE_DESCRIPTION("Renesas RPC-IF HyperFlash driver");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/mtd/hyperbus.h b/include/linux/mtd/hyperbus.h
index d8cb1aec826d..0ce612428aea 100644
--- a/include/linux/mtd/hyperbus.h
+++ b/include/linux/mtd/hyperbus.h
@@ -8,6 +8,17 @@
 
 #include <linux/mtd/map.h>
 
+/* HyperBus command bits */
+#define HYPERBUS_RW	0x80	/* R/W# */
+#define HYPERBUS_RW_WRITE 0
+#define HYPERBUS_RW_READ 0x80
+#define HYPERBUS_AS	0x40	/* Address Space */
+#define HYPERBUS_AS_MEM	0
+#define HYPERBUS_AS_REG	0x40
+#define HYPERBUS_BT	0x20	/* Burst Type */
+#define HYPERBUS_BT_WRAPPED 0
+#define HYPERBUS_BT_LINEAR 0x20
+
 enum hyperbus_memtype {
 	HYPERFLASH,
 	HYPERRAM,
-- 
cgit v1.2.3


From ec6347bb43395cb92126788a1a5b25302543f815 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Mon, 5 Oct 2020 20:40:16 -0700
Subject: x86, powerpc: Rename memcpy_mcsafe() to copy_mc_to_{user, kernel}()

In reaction to a proposal to introduce a memcpy_mcsafe_fast()
implementation Linus points out that memcpy_mcsafe() is poorly named
relative to communicating the scope of the interface. Specifically what
addresses are valid to pass as source, destination, and what faults /
exceptions are handled.

Of particular concern is that even though x86 might be able to handle
the semantics of copy_mc_to_user() with its common copy_user_generic()
implementation other archs likely need / want an explicit path for this
case:

  On Fri, May 1, 2020 at 11:28 AM Linus Torvalds <torvalds@linux-foundation.org> wrote:
  >
  > On Thu, Apr 30, 2020 at 6:21 PM Dan Williams <dan.j.williams@intel.com> wrote:
  > >
  > > However now I see that copy_user_generic() works for the wrong reason.
  > > It works because the exception on the source address due to poison
  > > looks no different than a write fault on the user address to the
  > > caller, it's still just a short copy. So it makes copy_to_user() work
  > > for the wrong reason relative to the name.
  >
  > Right.
  >
  > And it won't work that way on other architectures. On x86, we have a
  > generic function that can take faults on either side, and we use it
  > for both cases (and for the "in_user" case too), but that's an
  > artifact of the architecture oddity.
  >
  > In fact, it's probably wrong even on x86 - because it can hide bugs -
  > but writing those things is painful enough that everybody prefers
  > having just one function.

Replace a single top-level memcpy_mcsafe() with either
copy_mc_to_user(), or copy_mc_to_kernel().

Introduce an x86 copy_mc_fragile() name as the rename for the
low-level x86 implementation formerly named memcpy_mcsafe(). It is used
as the slow / careful backend that is supplanted by a fast
copy_mc_generic() in a follow-on patch.

One side-effect of this reorganization is that separating copy_mc_64.S
to its own file means that perf no longer needs to track dependencies
for its memcpy_64.S benchmarks.

 [ bp: Massage a bit. ]

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Acked-by: Michael Ellerman <mpe@ellerman.id.au>
Cc: <stable@vger.kernel.org>
Link: http://lore.kernel.org/r/CAHk-=wjSqtXAqfUJxFtWNwmguFASTgB0dz1dT3V-78Quiezqbg@mail.gmail.com
Link: https://lkml.kernel.org/r/160195561680.2163339.11574962055305783722.stgit@dwillia2-desk3.amr.corp.intel.com
---
 arch/powerpc/Kconfig                               |   2 +-
 arch/powerpc/include/asm/string.h                  |   2 -
 arch/powerpc/include/asm/uaccess.h                 |  40 ++--
 arch/powerpc/lib/Makefile                          |   2 +-
 arch/powerpc/lib/copy_mc_64.S                      | 242 +++++++++++++++++++++
 arch/powerpc/lib/memcpy_mcsafe_64.S                | 242 ---------------------
 arch/x86/Kconfig                                   |   2 +-
 arch/x86/Kconfig.debug                             |   2 +-
 arch/x86/include/asm/copy_mc_test.h                |  75 +++++++
 arch/x86/include/asm/mce.h                         |   9 +
 arch/x86/include/asm/mcsafe_test.h                 |  75 -------
 arch/x86/include/asm/string_64.h                   |  32 ---
 arch/x86/include/asm/uaccess.h                     |   9 +
 arch/x86/include/asm/uaccess_64.h                  |  20 --
 arch/x86/kernel/cpu/mce/core.c                     |   8 +-
 arch/x86/kernel/quirks.c                           |  10 +-
 arch/x86/lib/Makefile                              |   1 +
 arch/x86/lib/copy_mc.c                             |  82 +++++++
 arch/x86/lib/copy_mc_64.S                          | 127 +++++++++++
 arch/x86/lib/memcpy_64.S                           | 115 ----------
 arch/x86/lib/usercopy_64.c                         |  21 --
 drivers/md/dm-writecache.c                         |  15 +-
 drivers/nvdimm/claim.c                             |   2 +-
 drivers/nvdimm/pmem.c                              |   6 +-
 include/linux/string.h                             |   9 +-
 include/linux/uaccess.h                            |  13 ++
 include/linux/uio.h                                |  10 +-
 lib/Kconfig                                        |   7 +-
 lib/iov_iter.c                                     |  48 ++--
 tools/arch/x86/include/asm/mcsafe_test.h           |  13 --
 tools/arch/x86/lib/memcpy_64.S                     | 115 ----------
 tools/objtool/check.c                              |   4 +-
 tools/perf/bench/Build                             |   1 -
 tools/perf/bench/mem-memcpy-x86-64-lib.c           |  24 --
 tools/testing/nvdimm/test/nfit.c                   |  49 +++--
 .../testing/selftests/powerpc/copyloops/.gitignore |   2 +-
 tools/testing/selftests/powerpc/copyloops/Makefile |   6 +-
 .../selftests/powerpc/copyloops/copy_mc_64.S       |   1 +
 .../selftests/powerpc/copyloops/memcpy_mcsafe_64.S |   1 -
 39 files changed, 673 insertions(+), 771 deletions(-)
 create mode 100644 arch/powerpc/lib/copy_mc_64.S
 delete mode 100644 arch/powerpc/lib/memcpy_mcsafe_64.S
 create mode 100644 arch/x86/include/asm/copy_mc_test.h
 delete mode 100644 arch/x86/include/asm/mcsafe_test.h
 create mode 100644 arch/x86/lib/copy_mc.c
 create mode 100644 arch/x86/lib/copy_mc_64.S
 delete mode 100644 tools/arch/x86/include/asm/mcsafe_test.h
 delete mode 100644 tools/perf/bench/mem-memcpy-x86-64-lib.c
 create mode 120000 tools/testing/selftests/powerpc/copyloops/copy_mc_64.S
 delete mode 120000 tools/testing/selftests/powerpc/copyloops/memcpy_mcsafe_64.S

(limited to 'include/linux')

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 1f48bbfb3ce9..76473eda3426 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -136,7 +136,7 @@ config PPC
 	select ARCH_HAS_STRICT_KERNEL_RWX	if (PPC32 && !HIBERNATION)
 	select ARCH_HAS_TICK_BROADCAST		if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAS_UACCESS_FLUSHCACHE
-	select ARCH_HAS_UACCESS_MCSAFE		if PPC64
+	select ARCH_HAS_COPY_MC			if PPC64
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_KEEP_MEMBLOCK
diff --git a/arch/powerpc/include/asm/string.h b/arch/powerpc/include/asm/string.h
index 283552cd0e58..2aa0e31e6884 100644
--- a/arch/powerpc/include/asm/string.h
+++ b/arch/powerpc/include/asm/string.h
@@ -53,9 +53,7 @@ void *__memmove(void *to, const void *from, __kernel_size_t n);
 #ifndef CONFIG_KASAN
 #define __HAVE_ARCH_MEMSET32
 #define __HAVE_ARCH_MEMSET64
-#define __HAVE_ARCH_MEMCPY_MCSAFE
 
-extern int memcpy_mcsafe(void *dst, const void *src, __kernel_size_t sz);
 extern void *__memset16(uint16_t *, uint16_t v, __kernel_size_t);
 extern void *__memset32(uint32_t *, uint32_t v, __kernel_size_t);
 extern void *__memset64(uint64_t *, uint64_t v, __kernel_size_t);
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index 00699903f1ef..20a35373cafc 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -435,6 +435,32 @@ do {								\
 extern unsigned long __copy_tofrom_user(void __user *to,
 		const void __user *from, unsigned long size);
 
+#ifdef CONFIG_ARCH_HAS_COPY_MC
+unsigned long __must_check
+copy_mc_generic(void *to, const void *from, unsigned long size);
+
+static inline unsigned long __must_check
+copy_mc_to_kernel(void *to, const void *from, unsigned long size)
+{
+	return copy_mc_generic(to, from, size);
+}
+#define copy_mc_to_kernel copy_mc_to_kernel
+
+static inline unsigned long __must_check
+copy_mc_to_user(void __user *to, const void *from, unsigned long n)
+{
+	if (likely(check_copy_size(from, n, true))) {
+		if (access_ok(to, n)) {
+			allow_write_to_user(to, n);
+			n = copy_mc_generic((void *)to, from, n);
+			prevent_write_to_user(to, n);
+		}
+	}
+
+	return n;
+}
+#endif
+
 #ifdef __powerpc64__
 static inline unsigned long
 raw_copy_in_user(void __user *to, const void __user *from, unsigned long n)
@@ -523,20 +549,6 @@ raw_copy_to_user(void __user *to, const void *from, unsigned long n)
 	return ret;
 }
 
-static __always_inline unsigned long __must_check
-copy_to_user_mcsafe(void __user *to, const void *from, unsigned long n)
-{
-	if (likely(check_copy_size(from, n, true))) {
-		if (access_ok(to, n)) {
-			allow_write_to_user(to, n);
-			n = memcpy_mcsafe((void *)to, from, n);
-			prevent_write_to_user(to, n);
-		}
-	}
-
-	return n;
-}
-
 unsigned long __arch_clear_user(void __user *addr, unsigned long size);
 
 static inline unsigned long clear_user(void __user *addr, unsigned long size)
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index d66a645503eb..69a91b571845 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -39,7 +39,7 @@ obj-$(CONFIG_PPC_BOOK3S_64) += copyuser_power7.o copypage_power7.o \
 			       memcpy_power7.o
 
 obj64-y	+= copypage_64.o copyuser_64.o mem_64.o hweight_64.o \
-	   memcpy_64.o memcpy_mcsafe_64.o
+	   memcpy_64.o copy_mc_64.o
 
 ifndef CONFIG_PPC_QUEUED_SPINLOCKS
 obj64-$(CONFIG_SMP)	+= locks.o
diff --git a/arch/powerpc/lib/copy_mc_64.S b/arch/powerpc/lib/copy_mc_64.S
new file mode 100644
index 000000000000..88d46c471493
--- /dev/null
+++ b/arch/powerpc/lib/copy_mc_64.S
@@ -0,0 +1,242 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) IBM Corporation, 2011
+ * Derived from copyuser_power7.s by Anton Blanchard <anton@au.ibm.com>
+ * Author - Balbir Singh <bsingharora@gmail.com>
+ */
+#include <asm/ppc_asm.h>
+#include <asm/errno.h>
+#include <asm/export.h>
+
+	.macro err1
+100:
+	EX_TABLE(100b,.Ldo_err1)
+	.endm
+
+	.macro err2
+200:
+	EX_TABLE(200b,.Ldo_err2)
+	.endm
+
+	.macro err3
+300:	EX_TABLE(300b,.Ldone)
+	.endm
+
+.Ldo_err2:
+	ld	r22,STK_REG(R22)(r1)
+	ld	r21,STK_REG(R21)(r1)
+	ld	r20,STK_REG(R20)(r1)
+	ld	r19,STK_REG(R19)(r1)
+	ld	r18,STK_REG(R18)(r1)
+	ld	r17,STK_REG(R17)(r1)
+	ld	r16,STK_REG(R16)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r14,STK_REG(R14)(r1)
+	addi	r1,r1,STACKFRAMESIZE
+.Ldo_err1:
+	/* Do a byte by byte copy to get the exact remaining size */
+	mtctr	r7
+46:
+err3;	lbz	r0,0(r4)
+	addi	r4,r4,1
+err3;	stb	r0,0(r3)
+	addi	r3,r3,1
+	bdnz	46b
+	li	r3,0
+	blr
+
+.Ldone:
+	mfctr	r3
+	blr
+
+
+_GLOBAL(copy_mc_generic)
+	mr	r7,r5
+	cmpldi	r5,16
+	blt	.Lshort_copy
+
+.Lcopy:
+	/* Get the source 8B aligned */
+	neg	r6,r4
+	mtocrf	0x01,r6
+	clrldi	r6,r6,(64-3)
+
+	bf	cr7*4+3,1f
+err1;	lbz	r0,0(r4)
+	addi	r4,r4,1
+err1;	stb	r0,0(r3)
+	addi	r3,r3,1
+	subi	r7,r7,1
+
+1:	bf	cr7*4+2,2f
+err1;	lhz	r0,0(r4)
+	addi	r4,r4,2
+err1;	sth	r0,0(r3)
+	addi	r3,r3,2
+	subi	r7,r7,2
+
+2:	bf	cr7*4+1,3f
+err1;	lwz	r0,0(r4)
+	addi	r4,r4,4
+err1;	stw	r0,0(r3)
+	addi	r3,r3,4
+	subi	r7,r7,4
+
+3:	sub	r5,r5,r6
+	cmpldi	r5,128
+
+	mflr	r0
+	stdu	r1,-STACKFRAMESIZE(r1)
+	std	r14,STK_REG(R14)(r1)
+	std	r15,STK_REG(R15)(r1)
+	std	r16,STK_REG(R16)(r1)
+	std	r17,STK_REG(R17)(r1)
+	std	r18,STK_REG(R18)(r1)
+	std	r19,STK_REG(R19)(r1)
+	std	r20,STK_REG(R20)(r1)
+	std	r21,STK_REG(R21)(r1)
+	std	r22,STK_REG(R22)(r1)
+	std	r0,STACKFRAMESIZE+16(r1)
+
+	blt	5f
+	srdi	r6,r5,7
+	mtctr	r6
+
+	/* Now do cacheline (128B) sized loads and stores. */
+	.align	5
+4:
+err2;	ld	r0,0(r4)
+err2;	ld	r6,8(r4)
+err2;	ld	r8,16(r4)
+err2;	ld	r9,24(r4)
+err2;	ld	r10,32(r4)
+err2;	ld	r11,40(r4)
+err2;	ld	r12,48(r4)
+err2;	ld	r14,56(r4)
+err2;	ld	r15,64(r4)
+err2;	ld	r16,72(r4)
+err2;	ld	r17,80(r4)
+err2;	ld	r18,88(r4)
+err2;	ld	r19,96(r4)
+err2;	ld	r20,104(r4)
+err2;	ld	r21,112(r4)
+err2;	ld	r22,120(r4)
+	addi	r4,r4,128
+err2;	std	r0,0(r3)
+err2;	std	r6,8(r3)
+err2;	std	r8,16(r3)
+err2;	std	r9,24(r3)
+err2;	std	r10,32(r3)
+err2;	std	r11,40(r3)
+err2;	std	r12,48(r3)
+err2;	std	r14,56(r3)
+err2;	std	r15,64(r3)
+err2;	std	r16,72(r3)
+err2;	std	r17,80(r3)
+err2;	std	r18,88(r3)
+err2;	std	r19,96(r3)
+err2;	std	r20,104(r3)
+err2;	std	r21,112(r3)
+err2;	std	r22,120(r3)
+	addi	r3,r3,128
+	subi	r7,r7,128
+	bdnz	4b
+
+	clrldi	r5,r5,(64-7)
+
+	/* Up to 127B to go */
+5:	srdi	r6,r5,4
+	mtocrf	0x01,r6
+
+6:	bf	cr7*4+1,7f
+err2;	ld	r0,0(r4)
+err2;	ld	r6,8(r4)
+err2;	ld	r8,16(r4)
+err2;	ld	r9,24(r4)
+err2;	ld	r10,32(r4)
+err2;	ld	r11,40(r4)
+err2;	ld	r12,48(r4)
+err2;	ld	r14,56(r4)
+	addi	r4,r4,64
+err2;	std	r0,0(r3)
+err2;	std	r6,8(r3)
+err2;	std	r8,16(r3)
+err2;	std	r9,24(r3)
+err2;	std	r10,32(r3)
+err2;	std	r11,40(r3)
+err2;	std	r12,48(r3)
+err2;	std	r14,56(r3)
+	addi	r3,r3,64
+	subi	r7,r7,64
+
+7:	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
+	ld	r17,STK_REG(R17)(r1)
+	ld	r18,STK_REG(R18)(r1)
+	ld	r19,STK_REG(R19)(r1)
+	ld	r20,STK_REG(R20)(r1)
+	ld	r21,STK_REG(R21)(r1)
+	ld	r22,STK_REG(R22)(r1)
+	addi	r1,r1,STACKFRAMESIZE
+
+	/* Up to 63B to go */
+	bf	cr7*4+2,8f
+err1;	ld	r0,0(r4)
+err1;	ld	r6,8(r4)
+err1;	ld	r8,16(r4)
+err1;	ld	r9,24(r4)
+	addi	r4,r4,32
+err1;	std	r0,0(r3)
+err1;	std	r6,8(r3)
+err1;	std	r8,16(r3)
+err1;	std	r9,24(r3)
+	addi	r3,r3,32
+	subi	r7,r7,32
+
+	/* Up to 31B to go */
+8:	bf	cr7*4+3,9f
+err1;	ld	r0,0(r4)
+err1;	ld	r6,8(r4)
+	addi	r4,r4,16
+err1;	std	r0,0(r3)
+err1;	std	r6,8(r3)
+	addi	r3,r3,16
+	subi	r7,r7,16
+
+9:	clrldi	r5,r5,(64-4)
+
+	/* Up to 15B to go */
+.Lshort_copy:
+	mtocrf	0x01,r5
+	bf	cr7*4+0,12f
+err1;	lwz	r0,0(r4)	/* Less chance of a reject with word ops */
+err1;	lwz	r6,4(r4)
+	addi	r4,r4,8
+err1;	stw	r0,0(r3)
+err1;	stw	r6,4(r3)
+	addi	r3,r3,8
+	subi	r7,r7,8
+
+12:	bf	cr7*4+1,13f
+err1;	lwz	r0,0(r4)
+	addi	r4,r4,4
+err1;	stw	r0,0(r3)
+	addi	r3,r3,4
+	subi	r7,r7,4
+
+13:	bf	cr7*4+2,14f
+err1;	lhz	r0,0(r4)
+	addi	r4,r4,2
+err1;	sth	r0,0(r3)
+	addi	r3,r3,2
+	subi	r7,r7,2
+
+14:	bf	cr7*4+3,15f
+err1;	lbz	r0,0(r4)
+err1;	stb	r0,0(r3)
+
+15:	li	r3,0
+	blr
+
+EXPORT_SYMBOL_GPL(copy_mc_generic);
diff --git a/arch/powerpc/lib/memcpy_mcsafe_64.S b/arch/powerpc/lib/memcpy_mcsafe_64.S
deleted file mode 100644
index cb882d9a6d8a..000000000000
--- a/arch/powerpc/lib/memcpy_mcsafe_64.S
+++ /dev/null
@@ -1,242 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (C) IBM Corporation, 2011
- * Derived from copyuser_power7.s by Anton Blanchard <anton@au.ibm.com>
- * Author - Balbir Singh <bsingharora@gmail.com>
- */
-#include <asm/ppc_asm.h>
-#include <asm/errno.h>
-#include <asm/export.h>
-
-	.macro err1
-100:
-	EX_TABLE(100b,.Ldo_err1)
-	.endm
-
-	.macro err2
-200:
-	EX_TABLE(200b,.Ldo_err2)
-	.endm
-
-	.macro err3
-300:	EX_TABLE(300b,.Ldone)
-	.endm
-
-.Ldo_err2:
-	ld	r22,STK_REG(R22)(r1)
-	ld	r21,STK_REG(R21)(r1)
-	ld	r20,STK_REG(R20)(r1)
-	ld	r19,STK_REG(R19)(r1)
-	ld	r18,STK_REG(R18)(r1)
-	ld	r17,STK_REG(R17)(r1)
-	ld	r16,STK_REG(R16)(r1)
-	ld	r15,STK_REG(R15)(r1)
-	ld	r14,STK_REG(R14)(r1)
-	addi	r1,r1,STACKFRAMESIZE
-.Ldo_err1:
-	/* Do a byte by byte copy to get the exact remaining size */
-	mtctr	r7
-46:
-err3;	lbz	r0,0(r4)
-	addi	r4,r4,1
-err3;	stb	r0,0(r3)
-	addi	r3,r3,1
-	bdnz	46b
-	li	r3,0
-	blr
-
-.Ldone:
-	mfctr	r3
-	blr
-
-
-_GLOBAL(memcpy_mcsafe)
-	mr	r7,r5
-	cmpldi	r5,16
-	blt	.Lshort_copy
-
-.Lcopy:
-	/* Get the source 8B aligned */
-	neg	r6,r4
-	mtocrf	0x01,r6
-	clrldi	r6,r6,(64-3)
-
-	bf	cr7*4+3,1f
-err1;	lbz	r0,0(r4)
-	addi	r4,r4,1
-err1;	stb	r0,0(r3)
-	addi	r3,r3,1
-	subi	r7,r7,1
-
-1:	bf	cr7*4+2,2f
-err1;	lhz	r0,0(r4)
-	addi	r4,r4,2
-err1;	sth	r0,0(r3)
-	addi	r3,r3,2
-	subi	r7,r7,2
-
-2:	bf	cr7*4+1,3f
-err1;	lwz	r0,0(r4)
-	addi	r4,r4,4
-err1;	stw	r0,0(r3)
-	addi	r3,r3,4
-	subi	r7,r7,4
-
-3:	sub	r5,r5,r6
-	cmpldi	r5,128
-
-	mflr	r0
-	stdu	r1,-STACKFRAMESIZE(r1)
-	std	r14,STK_REG(R14)(r1)
-	std	r15,STK_REG(R15)(r1)
-	std	r16,STK_REG(R16)(r1)
-	std	r17,STK_REG(R17)(r1)
-	std	r18,STK_REG(R18)(r1)
-	std	r19,STK_REG(R19)(r1)
-	std	r20,STK_REG(R20)(r1)
-	std	r21,STK_REG(R21)(r1)
-	std	r22,STK_REG(R22)(r1)
-	std	r0,STACKFRAMESIZE+16(r1)
-
-	blt	5f
-	srdi	r6,r5,7
-	mtctr	r6
-
-	/* Now do cacheline (128B) sized loads and stores. */
-	.align	5
-4:
-err2;	ld	r0,0(r4)
-err2;	ld	r6,8(r4)
-err2;	ld	r8,16(r4)
-err2;	ld	r9,24(r4)
-err2;	ld	r10,32(r4)
-err2;	ld	r11,40(r4)
-err2;	ld	r12,48(r4)
-err2;	ld	r14,56(r4)
-err2;	ld	r15,64(r4)
-err2;	ld	r16,72(r4)
-err2;	ld	r17,80(r4)
-err2;	ld	r18,88(r4)
-err2;	ld	r19,96(r4)
-err2;	ld	r20,104(r4)
-err2;	ld	r21,112(r4)
-err2;	ld	r22,120(r4)
-	addi	r4,r4,128
-err2;	std	r0,0(r3)
-err2;	std	r6,8(r3)
-err2;	std	r8,16(r3)
-err2;	std	r9,24(r3)
-err2;	std	r10,32(r3)
-err2;	std	r11,40(r3)
-err2;	std	r12,48(r3)
-err2;	std	r14,56(r3)
-err2;	std	r15,64(r3)
-err2;	std	r16,72(r3)
-err2;	std	r17,80(r3)
-err2;	std	r18,88(r3)
-err2;	std	r19,96(r3)
-err2;	std	r20,104(r3)
-err2;	std	r21,112(r3)
-err2;	std	r22,120(r3)
-	addi	r3,r3,128
-	subi	r7,r7,128
-	bdnz	4b
-
-	clrldi	r5,r5,(64-7)
-
-	/* Up to 127B to go */
-5:	srdi	r6,r5,4
-	mtocrf	0x01,r6
-
-6:	bf	cr7*4+1,7f
-err2;	ld	r0,0(r4)
-err2;	ld	r6,8(r4)
-err2;	ld	r8,16(r4)
-err2;	ld	r9,24(r4)
-err2;	ld	r10,32(r4)
-err2;	ld	r11,40(r4)
-err2;	ld	r12,48(r4)
-err2;	ld	r14,56(r4)
-	addi	r4,r4,64
-err2;	std	r0,0(r3)
-err2;	std	r6,8(r3)
-err2;	std	r8,16(r3)
-err2;	std	r9,24(r3)
-err2;	std	r10,32(r3)
-err2;	std	r11,40(r3)
-err2;	std	r12,48(r3)
-err2;	std	r14,56(r3)
-	addi	r3,r3,64
-	subi	r7,r7,64
-
-7:	ld	r14,STK_REG(R14)(r1)
-	ld	r15,STK_REG(R15)(r1)
-	ld	r16,STK_REG(R16)(r1)
-	ld	r17,STK_REG(R17)(r1)
-	ld	r18,STK_REG(R18)(r1)
-	ld	r19,STK_REG(R19)(r1)
-	ld	r20,STK_REG(R20)(r1)
-	ld	r21,STK_REG(R21)(r1)
-	ld	r22,STK_REG(R22)(r1)
-	addi	r1,r1,STACKFRAMESIZE
-
-	/* Up to 63B to go */
-	bf	cr7*4+2,8f
-err1;	ld	r0,0(r4)
-err1;	ld	r6,8(r4)
-err1;	ld	r8,16(r4)
-err1;	ld	r9,24(r4)
-	addi	r4,r4,32
-err1;	std	r0,0(r3)
-err1;	std	r6,8(r3)
-err1;	std	r8,16(r3)
-err1;	std	r9,24(r3)
-	addi	r3,r3,32
-	subi	r7,r7,32
-
-	/* Up to 31B to go */
-8:	bf	cr7*4+3,9f
-err1;	ld	r0,0(r4)
-err1;	ld	r6,8(r4)
-	addi	r4,r4,16
-err1;	std	r0,0(r3)
-err1;	std	r6,8(r3)
-	addi	r3,r3,16
-	subi	r7,r7,16
-
-9:	clrldi	r5,r5,(64-4)
-
-	/* Up to 15B to go */
-.Lshort_copy:
-	mtocrf	0x01,r5
-	bf	cr7*4+0,12f
-err1;	lwz	r0,0(r4)	/* Less chance of a reject with word ops */
-err1;	lwz	r6,4(r4)
-	addi	r4,r4,8
-err1;	stw	r0,0(r3)
-err1;	stw	r6,4(r3)
-	addi	r3,r3,8
-	subi	r7,r7,8
-
-12:	bf	cr7*4+1,13f
-err1;	lwz	r0,0(r4)
-	addi	r4,r4,4
-err1;	stw	r0,0(r3)
-	addi	r3,r3,4
-	subi	r7,r7,4
-
-13:	bf	cr7*4+2,14f
-err1;	lhz	r0,0(r4)
-	addi	r4,r4,2
-err1;	sth	r0,0(r3)
-	addi	r3,r3,2
-	subi	r7,r7,2
-
-14:	bf	cr7*4+3,15f
-err1;	lbz	r0,0(r4)
-err1;	stb	r0,0(r3)
-
-15:	li	r3,0
-	blr
-
-EXPORT_SYMBOL_GPL(memcpy_mcsafe);
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 7101ac64bb20..e876b3a087f9 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -75,7 +75,7 @@ config X86
 	select ARCH_HAS_PTE_DEVMAP		if X86_64
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_UACCESS_FLUSHCACHE	if X86_64
-	select ARCH_HAS_UACCESS_MCSAFE		if X86_64 && X86_MCE
+	select ARCH_HAS_COPY_MC			if X86_64
 	select ARCH_HAS_SET_MEMORY
 	select ARCH_HAS_SET_DIRECT_MAP
 	select ARCH_HAS_STRICT_KERNEL_RWX
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index ee1d3c5834c6..27b5e2bc6a01 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -62,7 +62,7 @@ config EARLY_PRINTK_USB_XDBC
 	  You should normally say N here, unless you want to debug early
 	  crashes or need a very simple printk logging facility.
 
-config MCSAFE_TEST
+config COPY_MC_TEST
 	def_bool n
 
 config EFI_PGT_DUMP
diff --git a/arch/x86/include/asm/copy_mc_test.h b/arch/x86/include/asm/copy_mc_test.h
new file mode 100644
index 000000000000..e4991ba96726
--- /dev/null
+++ b/arch/x86/include/asm/copy_mc_test.h
@@ -0,0 +1,75 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _COPY_MC_TEST_H_
+#define _COPY_MC_TEST_H_
+
+#ifndef __ASSEMBLY__
+#ifdef CONFIG_COPY_MC_TEST
+extern unsigned long copy_mc_test_src;
+extern unsigned long copy_mc_test_dst;
+
+static inline void copy_mc_inject_src(void *addr)
+{
+	if (addr)
+		copy_mc_test_src = (unsigned long) addr;
+	else
+		copy_mc_test_src = ~0UL;
+}
+
+static inline void copy_mc_inject_dst(void *addr)
+{
+	if (addr)
+		copy_mc_test_dst = (unsigned long) addr;
+	else
+		copy_mc_test_dst = ~0UL;
+}
+#else /* CONFIG_COPY_MC_TEST */
+static inline void copy_mc_inject_src(void *addr)
+{
+}
+
+static inline void copy_mc_inject_dst(void *addr)
+{
+}
+#endif /* CONFIG_COPY_MC_TEST */
+
+#else /* __ASSEMBLY__ */
+#include <asm/export.h>
+
+#ifdef CONFIG_COPY_MC_TEST
+.macro COPY_MC_TEST_CTL
+	.pushsection .data
+	.align 8
+	.globl copy_mc_test_src
+	copy_mc_test_src:
+		.quad 0
+	EXPORT_SYMBOL_GPL(copy_mc_test_src)
+	.globl copy_mc_test_dst
+	copy_mc_test_dst:
+		.quad 0
+	EXPORT_SYMBOL_GPL(copy_mc_test_dst)
+	.popsection
+.endm
+
+.macro COPY_MC_TEST_SRC reg count target
+	leaq \count(\reg), %r9
+	cmp copy_mc_test_src, %r9
+	ja \target
+.endm
+
+.macro COPY_MC_TEST_DST reg count target
+	leaq \count(\reg), %r9
+	cmp copy_mc_test_dst, %r9
+	ja \target
+.endm
+#else
+.macro COPY_MC_TEST_CTL
+.endm
+
+.macro COPY_MC_TEST_SRC reg count target
+.endm
+
+.macro COPY_MC_TEST_DST reg count target
+.endm
+#endif /* CONFIG_COPY_MC_TEST */
+#endif /* __ASSEMBLY__ */
+#endif /* _COPY_MC_TEST_H_ */
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 109af5c7f515..ba2062d6df92 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -174,6 +174,15 @@ extern void mce_unregister_decode_chain(struct notifier_block *nb);
 
 extern int mce_p5_enabled;
 
+#ifdef CONFIG_ARCH_HAS_COPY_MC
+extern void enable_copy_mc_fragile(void);
+unsigned long __must_check copy_mc_fragile(void *dst, const void *src, unsigned cnt);
+#else
+static inline void enable_copy_mc_fragile(void)
+{
+}
+#endif
+
 #ifdef CONFIG_X86_MCE
 int mcheck_init(void);
 void mcheck_cpu_init(struct cpuinfo_x86 *c);
diff --git a/arch/x86/include/asm/mcsafe_test.h b/arch/x86/include/asm/mcsafe_test.h
deleted file mode 100644
index eb59804b6201..000000000000
--- a/arch/x86/include/asm/mcsafe_test.h
+++ /dev/null
@@ -1,75 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _MCSAFE_TEST_H_
-#define _MCSAFE_TEST_H_
-
-#ifndef __ASSEMBLY__
-#ifdef CONFIG_MCSAFE_TEST
-extern unsigned long mcsafe_test_src;
-extern unsigned long mcsafe_test_dst;
-
-static inline void mcsafe_inject_src(void *addr)
-{
-	if (addr)
-		mcsafe_test_src = (unsigned long) addr;
-	else
-		mcsafe_test_src = ~0UL;
-}
-
-static inline void mcsafe_inject_dst(void *addr)
-{
-	if (addr)
-		mcsafe_test_dst = (unsigned long) addr;
-	else
-		mcsafe_test_dst = ~0UL;
-}
-#else /* CONFIG_MCSAFE_TEST */
-static inline void mcsafe_inject_src(void *addr)
-{
-}
-
-static inline void mcsafe_inject_dst(void *addr)
-{
-}
-#endif /* CONFIG_MCSAFE_TEST */
-
-#else /* __ASSEMBLY__ */
-#include <asm/export.h>
-
-#ifdef CONFIG_MCSAFE_TEST
-.macro MCSAFE_TEST_CTL
-	.pushsection .data
-	.align 8
-	.globl mcsafe_test_src
-	mcsafe_test_src:
-		.quad 0
-	EXPORT_SYMBOL_GPL(mcsafe_test_src)
-	.globl mcsafe_test_dst
-	mcsafe_test_dst:
-		.quad 0
-	EXPORT_SYMBOL_GPL(mcsafe_test_dst)
-	.popsection
-.endm
-
-.macro MCSAFE_TEST_SRC reg count target
-	leaq \count(\reg), %r9
-	cmp mcsafe_test_src, %r9
-	ja \target
-.endm
-
-.macro MCSAFE_TEST_DST reg count target
-	leaq \count(\reg), %r9
-	cmp mcsafe_test_dst, %r9
-	ja \target
-.endm
-#else
-.macro MCSAFE_TEST_CTL
-.endm
-
-.macro MCSAFE_TEST_SRC reg count target
-.endm
-
-.macro MCSAFE_TEST_DST reg count target
-.endm
-#endif /* CONFIG_MCSAFE_TEST */
-#endif /* __ASSEMBLY__ */
-#endif /* _MCSAFE_TEST_H_ */
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index 75314c3dbe47..6e450827f677 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -82,38 +82,6 @@ int strcmp(const char *cs, const char *ct);
 
 #endif
 
-#define __HAVE_ARCH_MEMCPY_MCSAFE 1
-__must_check unsigned long __memcpy_mcsafe(void *dst, const void *src,
-		size_t cnt);
-DECLARE_STATIC_KEY_FALSE(mcsafe_key);
-
-/**
- * memcpy_mcsafe - copy memory with indication if a machine check happened
- *
- * @dst:	destination address
- * @src:	source address
- * @cnt:	number of bytes to copy
- *
- * Low level memory copy function that catches machine checks
- * We only call into the "safe" function on systems that can
- * actually do machine check recovery. Everyone else can just
- * use memcpy().
- *
- * Return 0 for success, or number of bytes not copied if there was an
- * exception.
- */
-static __always_inline __must_check unsigned long
-memcpy_mcsafe(void *dst, const void *src, size_t cnt)
-{
-#ifdef CONFIG_X86_MCE
-	if (static_branch_unlikely(&mcsafe_key))
-		return __memcpy_mcsafe(dst, src, cnt);
-	else
-#endif
-		memcpy(dst, src, cnt);
-	return 0;
-}
-
 #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
 #define __HAVE_ARCH_MEMCPY_FLUSHCACHE 1
 void __memcpy_flushcache(void *dst, const void *src, size_t cnt);
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index ecefaffd15d4..eff7fb847149 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -455,6 +455,15 @@ extern __must_check long strnlen_user(const char __user *str, long n);
 unsigned long __must_check clear_user(void __user *mem, unsigned long len);
 unsigned long __must_check __clear_user(void __user *mem, unsigned long len);
 
+#ifdef CONFIG_ARCH_HAS_COPY_MC
+unsigned long __must_check
+copy_mc_to_kernel(void *to, const void *from, unsigned len);
+#define copy_mc_to_kernel copy_mc_to_kernel
+
+unsigned long __must_check
+copy_mc_to_user(void *to, const void *from, unsigned len);
+#endif
+
 /*
  * movsl can be slow when source and dest are not both 8-byte aligned
  */
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index bc10e3dc64fe..e7265a552f4f 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -46,22 +46,6 @@ copy_user_generic(void *to, const void *from, unsigned len)
 	return ret;
 }
 
-static __always_inline __must_check unsigned long
-copy_to_user_mcsafe(void *to, const void *from, unsigned len)
-{
-	unsigned long ret;
-
-	__uaccess_begin();
-	/*
-	 * Note, __memcpy_mcsafe() is explicitly used since it can
-	 * handle exceptions / faults.  memcpy_mcsafe() may fall back to
-	 * memcpy() which lacks this handling.
-	 */
-	ret = __memcpy_mcsafe(to, from, len);
-	__uaccess_end();
-	return ret;
-}
-
 static __always_inline __must_check unsigned long
 raw_copy_from_user(void *dst, const void __user *src, unsigned long size)
 {
@@ -102,8 +86,4 @@ __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size)
 	kasan_check_write(dst, size);
 	return __copy_user_flushcache(dst, src, size);
 }
-
-unsigned long
-mcsafe_handle_tail(char *to, char *from, unsigned len);
-
 #endif /* _ASM_X86_UACCESS_64_H */
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 11b6697be010..b5b70f4b351d 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -40,7 +40,6 @@
 #include <linux/debugfs.h>
 #include <linux/irq_work.h>
 #include <linux/export.h>
-#include <linux/jump_label.h>
 #include <linux/set_memory.h>
 #include <linux/sync_core.h>
 #include <linux/task_work.h>
@@ -2124,7 +2123,7 @@ void mce_disable_bank(int bank)
 	and older.
  * mce=nobootlog Don't log MCEs from before booting.
  * mce=bios_cmci_threshold Don't program the CMCI threshold
- * mce=recovery force enable memcpy_mcsafe()
+ * mce=recovery force enable copy_mc_fragile()
  */
 static int __init mcheck_enable(char *str)
 {
@@ -2732,13 +2731,10 @@ static void __init mcheck_debugfs_init(void)
 static void __init mcheck_debugfs_init(void) { }
 #endif
 
-DEFINE_STATIC_KEY_FALSE(mcsafe_key);
-EXPORT_SYMBOL_GPL(mcsafe_key);
-
 static int __init mcheck_late_init(void)
 {
 	if (mca_cfg.recovery)
-		static_branch_inc(&mcsafe_key);
+		enable_copy_mc_fragile();
 
 	mcheck_debugfs_init();
 
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 1b10717c9321..6d0df6a58873 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -8,6 +8,7 @@
 
 #include <asm/hpet.h>
 #include <asm/setup.h>
+#include <asm/mce.h>
 
 #if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_SMP) && defined(CONFIG_PCI)
 
@@ -624,10 +625,6 @@ static void amd_disable_seq_and_redirect_scrub(struct pci_dev *dev)
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3,
 			amd_disable_seq_and_redirect_scrub);
 
-#if defined(CONFIG_X86_64) && defined(CONFIG_X86_MCE)
-#include <linux/jump_label.h>
-#include <asm/string_64.h>
-
 /* Ivy Bridge, Haswell, Broadwell */
 static void quirk_intel_brickland_xeon_ras_cap(struct pci_dev *pdev)
 {
@@ -636,7 +633,7 @@ static void quirk_intel_brickland_xeon_ras_cap(struct pci_dev *pdev)
 	pci_read_config_dword(pdev, 0x84, &capid0);
 
 	if (capid0 & 0x10)
-		static_branch_inc(&mcsafe_key);
+		enable_copy_mc_fragile();
 }
 
 /* Skylake */
@@ -653,7 +650,7 @@ static void quirk_intel_purley_xeon_ras_cap(struct pci_dev *pdev)
 	 * enabled, so memory machine check recovery is also enabled.
 	 */
 	if ((capid0 & 0xc0) == 0xc0 || (capid5 & 0x1e0))
-		static_branch_inc(&mcsafe_key);
+		enable_copy_mc_fragile();
 
 }
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x0ec3, quirk_intel_brickland_xeon_ras_cap);
@@ -661,7 +658,6 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2fc0, quirk_intel_brickland_xeon_
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, quirk_intel_brickland_xeon_ras_cap);
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2083, quirk_intel_purley_xeon_ras_cap);
 #endif
-#endif
 
 bool x86_apple_machine;
 EXPORT_SYMBOL(x86_apple_machine);
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index d46fff11f06f..f7d23c9c22b2 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -44,6 +44,7 @@ obj-$(CONFIG_SMP) += msr-smp.o cache-smp.o
 lib-y := delay.o misc.o cmdline.o cpu.o
 lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o
 lib-y += memcpy_$(BITS).o
+lib-$(CONFIG_ARCH_HAS_COPY_MC) += copy_mc.o copy_mc_64.o
 lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o insn-eval.o
 lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o
 lib-$(CONFIG_FUNCTION_ERROR_INJECTION)	+= error-inject.o
diff --git a/arch/x86/lib/copy_mc.c b/arch/x86/lib/copy_mc.c
new file mode 100644
index 000000000000..2633635530b7
--- /dev/null
+++ b/arch/x86/lib/copy_mc.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2016-2020 Intel Corporation. All rights reserved. */
+
+#include <linux/jump_label.h>
+#include <linux/uaccess.h>
+#include <linux/export.h>
+#include <linux/string.h>
+#include <linux/types.h>
+
+#include <asm/mce.h>
+
+#ifdef CONFIG_X86_MCE
+/*
+ * See COPY_MC_TEST for self-test of the copy_mc_fragile()
+ * implementation.
+ */
+static DEFINE_STATIC_KEY_FALSE(copy_mc_fragile_key);
+
+void enable_copy_mc_fragile(void)
+{
+	static_branch_inc(&copy_mc_fragile_key);
+}
+#define copy_mc_fragile_enabled (static_branch_unlikely(&copy_mc_fragile_key))
+
+/*
+ * Similar to copy_user_handle_tail, probe for the write fault point, or
+ * source exception point.
+ */
+__visible notrace unsigned long
+copy_mc_fragile_handle_tail(char *to, char *from, unsigned len)
+{
+	for (; len; --len, to++, from++)
+		if (copy_mc_fragile(to, from, 1))
+			break;
+	return len;
+}
+#else
+/*
+ * No point in doing careful copying, or consulting a static key when
+ * there is no #MC handler in the CONFIG_X86_MCE=n case.
+ */
+void enable_copy_mc_fragile(void)
+{
+}
+#define copy_mc_fragile_enabled (0)
+#endif
+
+/**
+ * copy_mc_to_kernel - memory copy that handles source exceptions
+ *
+ * @dst:	destination address
+ * @src:	source address
+ * @len:	number of bytes to copy
+ *
+ * Call into the 'fragile' version on systems that have trouble
+ * actually do machine check recovery. Everyone else can just
+ * use memcpy().
+ *
+ * Return 0 for success, or number of bytes not copied if there was an
+ * exception.
+ */
+unsigned long __must_check copy_mc_to_kernel(void *dst, const void *src, unsigned len)
+{
+	if (copy_mc_fragile_enabled)
+		return copy_mc_fragile(dst, src, len);
+	memcpy(dst, src, len);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(copy_mc_to_kernel);
+
+unsigned long __must_check copy_mc_to_user(void *dst, const void *src, unsigned len)
+{
+	unsigned long ret;
+
+	if (!copy_mc_fragile_enabled)
+		return copy_user_generic(dst, src, len);
+
+	__uaccess_begin();
+	ret = copy_mc_fragile(dst, src, len);
+	__uaccess_end();
+	return ret;
+}
diff --git a/arch/x86/lib/copy_mc_64.S b/arch/x86/lib/copy_mc_64.S
new file mode 100644
index 000000000000..c3b613c4544a
--- /dev/null
+++ b/arch/x86/lib/copy_mc_64.S
@@ -0,0 +1,127 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright(c) 2016-2020 Intel Corporation. All rights reserved. */
+
+#include <linux/linkage.h>
+#include <asm/copy_mc_test.h>
+#include <asm/export.h>
+#include <asm/asm.h>
+
+#ifndef CONFIG_UML
+
+#ifdef CONFIG_X86_MCE
+COPY_MC_TEST_CTL
+
+/*
+ * copy_mc_fragile - copy memory with indication if an exception / fault happened
+ *
+ * The 'fragile' version is opted into by platform quirks and takes
+ * pains to avoid unrecoverable corner cases like 'fast-string'
+ * instruction sequences, and consuming poison across a cacheline
+ * boundary. The non-fragile version is equivalent to memcpy()
+ * regardless of CPU machine-check-recovery capability.
+ */
+SYM_FUNC_START(copy_mc_fragile)
+	cmpl $8, %edx
+	/* Less than 8 bytes? Go to byte copy loop */
+	jb .L_no_whole_words
+
+	/* Check for bad alignment of source */
+	testl $7, %esi
+	/* Already aligned */
+	jz .L_8byte_aligned
+
+	/* Copy one byte at a time until source is 8-byte aligned */
+	movl %esi, %ecx
+	andl $7, %ecx
+	subl $8, %ecx
+	negl %ecx
+	subl %ecx, %edx
+.L_read_leading_bytes:
+	movb (%rsi), %al
+	COPY_MC_TEST_SRC %rsi 1 .E_leading_bytes
+	COPY_MC_TEST_DST %rdi 1 .E_leading_bytes
+.L_write_leading_bytes:
+	movb %al, (%rdi)
+	incq %rsi
+	incq %rdi
+	decl %ecx
+	jnz .L_read_leading_bytes
+
+.L_8byte_aligned:
+	movl %edx, %ecx
+	andl $7, %edx
+	shrl $3, %ecx
+	jz .L_no_whole_words
+
+.L_read_words:
+	movq (%rsi), %r8
+	COPY_MC_TEST_SRC %rsi 8 .E_read_words
+	COPY_MC_TEST_DST %rdi 8 .E_write_words
+.L_write_words:
+	movq %r8, (%rdi)
+	addq $8, %rsi
+	addq $8, %rdi
+	decl %ecx
+	jnz .L_read_words
+
+	/* Any trailing bytes? */
+.L_no_whole_words:
+	andl %edx, %edx
+	jz .L_done_memcpy_trap
+
+	/* Copy trailing bytes */
+	movl %edx, %ecx
+.L_read_trailing_bytes:
+	movb (%rsi), %al
+	COPY_MC_TEST_SRC %rsi 1 .E_trailing_bytes
+	COPY_MC_TEST_DST %rdi 1 .E_trailing_bytes
+.L_write_trailing_bytes:
+	movb %al, (%rdi)
+	incq %rsi
+	incq %rdi
+	decl %ecx
+	jnz .L_read_trailing_bytes
+
+	/* Copy successful. Return zero */
+.L_done_memcpy_trap:
+	xorl %eax, %eax
+.L_done:
+	ret
+SYM_FUNC_END(copy_mc_fragile)
+EXPORT_SYMBOL_GPL(copy_mc_fragile)
+
+	.section .fixup, "ax"
+	/*
+	 * Return number of bytes not copied for any failure. Note that
+	 * there is no "tail" handling since the source buffer is 8-byte
+	 * aligned and poison is cacheline aligned.
+	 */
+.E_read_words:
+	shll	$3, %ecx
+.E_leading_bytes:
+	addl	%edx, %ecx
+.E_trailing_bytes:
+	mov	%ecx, %eax
+	jmp	.L_done
+
+	/*
+	 * For write fault handling, given the destination is unaligned,
+	 * we handle faults on multi-byte writes with a byte-by-byte
+	 * copy up to the write-protected page.
+	 */
+.E_write_words:
+	shll	$3, %ecx
+	addl	%edx, %ecx
+	movl	%ecx, %edx
+	jmp copy_mc_fragile_handle_tail
+
+	.previous
+
+	_ASM_EXTABLE_FAULT(.L_read_leading_bytes, .E_leading_bytes)
+	_ASM_EXTABLE_FAULT(.L_read_words, .E_read_words)
+	_ASM_EXTABLE_FAULT(.L_read_trailing_bytes, .E_trailing_bytes)
+	_ASM_EXTABLE(.L_write_leading_bytes, .E_leading_bytes)
+	_ASM_EXTABLE(.L_write_words, .E_write_words)
+	_ASM_EXTABLE(.L_write_trailing_bytes, .E_trailing_bytes)
+#endif /* CONFIG_X86_MCE */
+#endif /* !CONFIG_UML */
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index bbcc05bcefad..037faac46b0c 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -4,7 +4,6 @@
 #include <linux/linkage.h>
 #include <asm/errno.h>
 #include <asm/cpufeatures.h>
-#include <asm/mcsafe_test.h>
 #include <asm/alternative-asm.h>
 #include <asm/export.h>
 
@@ -187,117 +186,3 @@ SYM_FUNC_START_LOCAL(memcpy_orig)
 SYM_FUNC_END(memcpy_orig)
 
 .popsection
-
-#ifndef CONFIG_UML
-
-MCSAFE_TEST_CTL
-
-/*
- * __memcpy_mcsafe - memory copy with machine check exception handling
- * Note that we only catch machine checks when reading the source addresses.
- * Writes to target are posted and don't generate machine checks.
- */
-SYM_FUNC_START(__memcpy_mcsafe)
-	cmpl $8, %edx
-	/* Less than 8 bytes? Go to byte copy loop */
-	jb .L_no_whole_words
-
-	/* Check for bad alignment of source */
-	testl $7, %esi
-	/* Already aligned */
-	jz .L_8byte_aligned
-
-	/* Copy one byte at a time until source is 8-byte aligned */
-	movl %esi, %ecx
-	andl $7, %ecx
-	subl $8, %ecx
-	negl %ecx
-	subl %ecx, %edx
-.L_read_leading_bytes:
-	movb (%rsi), %al
-	MCSAFE_TEST_SRC %rsi 1 .E_leading_bytes
-	MCSAFE_TEST_DST %rdi 1 .E_leading_bytes
-.L_write_leading_bytes:
-	movb %al, (%rdi)
-	incq %rsi
-	incq %rdi
-	decl %ecx
-	jnz .L_read_leading_bytes
-
-.L_8byte_aligned:
-	movl %edx, %ecx
-	andl $7, %edx
-	shrl $3, %ecx
-	jz .L_no_whole_words
-
-.L_read_words:
-	movq (%rsi), %r8
-	MCSAFE_TEST_SRC %rsi 8 .E_read_words
-	MCSAFE_TEST_DST %rdi 8 .E_write_words
-.L_write_words:
-	movq %r8, (%rdi)
-	addq $8, %rsi
-	addq $8, %rdi
-	decl %ecx
-	jnz .L_read_words
-
-	/* Any trailing bytes? */
-.L_no_whole_words:
-	andl %edx, %edx
-	jz .L_done_memcpy_trap
-
-	/* Copy trailing bytes */
-	movl %edx, %ecx
-.L_read_trailing_bytes:
-	movb (%rsi), %al
-	MCSAFE_TEST_SRC %rsi 1 .E_trailing_bytes
-	MCSAFE_TEST_DST %rdi 1 .E_trailing_bytes
-.L_write_trailing_bytes:
-	movb %al, (%rdi)
-	incq %rsi
-	incq %rdi
-	decl %ecx
-	jnz .L_read_trailing_bytes
-
-	/* Copy successful. Return zero */
-.L_done_memcpy_trap:
-	xorl %eax, %eax
-.L_done:
-	ret
-SYM_FUNC_END(__memcpy_mcsafe)
-EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
-
-	.section .fixup, "ax"
-	/*
-	 * Return number of bytes not copied for any failure. Note that
-	 * there is no "tail" handling since the source buffer is 8-byte
-	 * aligned and poison is cacheline aligned.
-	 */
-.E_read_words:
-	shll	$3, %ecx
-.E_leading_bytes:
-	addl	%edx, %ecx
-.E_trailing_bytes:
-	mov	%ecx, %eax
-	jmp	.L_done
-
-	/*
-	 * For write fault handling, given the destination is unaligned,
-	 * we handle faults on multi-byte writes with a byte-by-byte
-	 * copy up to the write-protected page.
-	 */
-.E_write_words:
-	shll	$3, %ecx
-	addl	%edx, %ecx
-	movl	%ecx, %edx
-	jmp mcsafe_handle_tail
-
-	.previous
-
-	_ASM_EXTABLE_FAULT(.L_read_leading_bytes, .E_leading_bytes)
-	_ASM_EXTABLE_FAULT(.L_read_words, .E_read_words)
-	_ASM_EXTABLE_FAULT(.L_read_trailing_bytes, .E_trailing_bytes)
-	_ASM_EXTABLE(.L_write_leading_bytes, .E_leading_bytes)
-	_ASM_EXTABLE(.L_write_words, .E_write_words)
-	_ASM_EXTABLE(.L_write_trailing_bytes, .E_trailing_bytes)
-#endif
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index b0dfac3d3df7..5f1d4a9ebd5a 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -56,27 +56,6 @@ unsigned long clear_user(void __user *to, unsigned long n)
 }
 EXPORT_SYMBOL(clear_user);
 
-/*
- * Similar to copy_user_handle_tail, probe for the write fault point,
- * but reuse __memcpy_mcsafe in case a new read error is encountered.
- * clac() is handled in _copy_to_iter_mcsafe().
- */
-__visible notrace unsigned long
-mcsafe_handle_tail(char *to, char *from, unsigned len)
-{
-	for (; len; --len, to++, from++) {
-		/*
-		 * Call the assembly routine back directly since
-		 * memcpy_mcsafe() may silently fallback to memcpy.
-		 */
-		unsigned long rem = __memcpy_mcsafe(to, from, 1);
-
-		if (rem)
-			break;
-	}
-	return len;
-}
-
 #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
 /**
  * clean_cache_range - write back a cache range with CLWB
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index 86dbe0c8b45c..9fc18fadacc6 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -49,7 +49,7 @@ do {								\
 #define pmem_assign(dest, src)	((dest) = (src))
 #endif
 
-#if defined(__HAVE_ARCH_MEMCPY_MCSAFE) && defined(DM_WRITECACHE_HAS_PMEM)
+#if IS_ENABLED(CONFIG_ARCH_HAS_COPY_MC) && defined(DM_WRITECACHE_HAS_PMEM)
 #define DM_WRITECACHE_HANDLE_HARDWARE_ERRORS
 #endif
 
@@ -984,7 +984,8 @@ static void writecache_resume(struct dm_target *ti)
 	}
 	wc->freelist_size = 0;
 
-	r = memcpy_mcsafe(&sb_seq_count, &sb(wc)->seq_count, sizeof(uint64_t));
+	r = copy_mc_to_kernel(&sb_seq_count, &sb(wc)->seq_count,
+			      sizeof(uint64_t));
 	if (r) {
 		writecache_error(wc, r, "hardware memory error when reading superblock: %d", r);
 		sb_seq_count = cpu_to_le64(0);
@@ -1000,7 +1001,8 @@ static void writecache_resume(struct dm_target *ti)
 			e->seq_count = -1;
 			continue;
 		}
-		r = memcpy_mcsafe(&wme, memory_entry(wc, e), sizeof(struct wc_memory_entry));
+		r = copy_mc_to_kernel(&wme, memory_entry(wc, e),
+				      sizeof(struct wc_memory_entry));
 		if (r) {
 			writecache_error(wc, r, "hardware memory error when reading metadata entry %lu: %d",
 					 (unsigned long)b, r);
@@ -1198,7 +1200,7 @@ static void bio_copy_block(struct dm_writecache *wc, struct bio *bio, void *data
 
 		if (rw == READ) {
 			int r;
-			r = memcpy_mcsafe(buf, data, size);
+			r = copy_mc_to_kernel(buf, data, size);
 			flush_dcache_page(bio_page(bio));
 			if (unlikely(r)) {
 				writecache_error(wc, r, "hardware memory error when reading data: %d", r);
@@ -2341,7 +2343,7 @@ invalid_optional:
 		}
 	}
 
-	r = memcpy_mcsafe(&s, sb(wc), sizeof(struct wc_memory_superblock));
+	r = copy_mc_to_kernel(&s, sb(wc), sizeof(struct wc_memory_superblock));
 	if (r) {
 		ti->error = "Hardware memory error when reading superblock";
 		goto bad;
@@ -2352,7 +2354,8 @@ invalid_optional:
 			ti->error = "Unable to initialize device";
 			goto bad;
 		}
-		r = memcpy_mcsafe(&s, sb(wc), sizeof(struct wc_memory_superblock));
+		r = copy_mc_to_kernel(&s, sb(wc),
+				      sizeof(struct wc_memory_superblock));
 		if (r) {
 			ti->error = "Hardware memory error when reading superblock";
 			goto bad;
diff --git a/drivers/nvdimm/claim.c b/drivers/nvdimm/claim.c
index 45964acba944..22d865ba6353 100644
--- a/drivers/nvdimm/claim.c
+++ b/drivers/nvdimm/claim.c
@@ -268,7 +268,7 @@ static int nsio_rw_bytes(struct nd_namespace_common *ndns,
 	if (rw == READ) {
 		if (unlikely(is_bad_pmem(&nsio->bb, sector, sz_align)))
 			return -EIO;
-		if (memcpy_mcsafe(buf, nsio->addr + offset, size) != 0)
+		if (copy_mc_to_kernel(buf, nsio->addr + offset, size) != 0)
 			return -EIO;
 		return 0;
 	}
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index fab29b514372..5c6939e004e2 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -125,7 +125,7 @@ static blk_status_t read_pmem(struct page *page, unsigned int off,
 	while (len) {
 		mem = kmap_atomic(page);
 		chunk = min_t(unsigned int, len, PAGE_SIZE - off);
-		rem = memcpy_mcsafe(mem + off, pmem_addr, chunk);
+		rem = copy_mc_to_kernel(mem + off, pmem_addr, chunk);
 		kunmap_atomic(mem);
 		if (rem)
 			return BLK_STS_IOERR;
@@ -304,7 +304,7 @@ static long pmem_dax_direct_access(struct dax_device *dax_dev,
 
 /*
  * Use the 'no check' versions of copy_from_iter_flushcache() and
- * copy_to_iter_mcsafe() to bypass HARDENED_USERCOPY overhead. Bounds
+ * copy_mc_to_iter() to bypass HARDENED_USERCOPY overhead. Bounds
  * checking, both file offset and device offset, is handled by
  * dax_iomap_actor()
  */
@@ -317,7 +317,7 @@ static size_t pmem_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
 static size_t pmem_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff,
 		void *addr, size_t bytes, struct iov_iter *i)
 {
-	return _copy_to_iter_mcsafe(addr, bytes, i);
+	return _copy_mc_to_iter(addr, bytes, i);
 }
 
 static const struct dax_operations pmem_dax_ops = {
diff --git a/include/linux/string.h b/include/linux/string.h
index 9b7a0632e87a..b1f3894a0a3e 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -161,20 +161,13 @@ extern int bcmp(const void *,const void *,__kernel_size_t);
 #ifndef __HAVE_ARCH_MEMCHR
 extern void * memchr(const void *,int,__kernel_size_t);
 #endif
-#ifndef __HAVE_ARCH_MEMCPY_MCSAFE
-static inline __must_check unsigned long memcpy_mcsafe(void *dst,
-		const void *src, size_t cnt)
-{
-	memcpy(dst, src, cnt);
-	return 0;
-}
-#endif
 #ifndef __HAVE_ARCH_MEMCPY_FLUSHCACHE
 static inline void memcpy_flushcache(void *dst, const void *src, size_t cnt)
 {
 	memcpy(dst, src, cnt);
 }
 #endif
+
 void *memchr_inv(const void *s, int c, size_t n);
 char *strreplace(char *s, char old, char new);
 
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 94b285411659..1ae36bc8db35 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -179,6 +179,19 @@ copy_in_user(void __user *to, const void __user *from, unsigned long n)
 }
 #endif
 
+#ifndef copy_mc_to_kernel
+/*
+ * Without arch opt-in this generic copy_mc_to_kernel() will not handle
+ * #MC (or arch equivalent) during source read.
+ */
+static inline unsigned long __must_check
+copy_mc_to_kernel(void *dst, const void *src, size_t cnt)
+{
+	memcpy(dst, src, cnt);
+	return 0;
+}
+#endif
+
 static __always_inline void pagefault_disabled_inc(void)
 {
 	current->pagefault_disabled++;
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 3835a8a8e9ea..f14410c678bd 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -185,10 +185,10 @@ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i);
 #define _copy_from_iter_flushcache _copy_from_iter_nocache
 #endif
 
-#ifdef CONFIG_ARCH_HAS_UACCESS_MCSAFE
-size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i);
+#ifdef CONFIG_ARCH_HAS_COPY_MC
+size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i);
 #else
-#define _copy_to_iter_mcsafe _copy_to_iter
+#define _copy_mc_to_iter _copy_to_iter
 #endif
 
 static __always_inline __must_check
@@ -201,12 +201,12 @@ size_t copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i)
 }
 
 static __always_inline __must_check
-size_t copy_to_iter_mcsafe(void *addr, size_t bytes, struct iov_iter *i)
+size_t copy_mc_to_iter(void *addr, size_t bytes, struct iov_iter *i)
 {
 	if (unlikely(!check_copy_size(addr, bytes, true)))
 		return 0;
 	else
-		return _copy_to_iter_mcsafe(addr, bytes, i);
+		return _copy_mc_to_iter(addr, bytes, i);
 }
 
 size_t iov_iter_zero(size_t bytes, struct iov_iter *);
diff --git a/lib/Kconfig b/lib/Kconfig
index b4b98a03ff98..b46a9fd122c8 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -635,7 +635,12 @@ config UACCESS_MEMCPY
 config ARCH_HAS_UACCESS_FLUSHCACHE
 	bool
 
-config ARCH_HAS_UACCESS_MCSAFE
+# arch has a concept of a recoverable synchronous exception due to a
+# memory-read error like x86 machine-check or ARM data-abort, and
+# implements copy_mc_to_{user,kernel} to abort and report
+# 'bytes-transferred' if that exception fires when accessing the source
+# buffer.
+config ARCH_HAS_COPY_MC
 	bool
 
 # Temporary. Goes away when all archs are cleaned up
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 5e40786c8f12..d13304a034f5 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -637,30 +637,30 @@ size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
 }
 EXPORT_SYMBOL(_copy_to_iter);
 
-#ifdef CONFIG_ARCH_HAS_UACCESS_MCSAFE
-static int copyout_mcsafe(void __user *to, const void *from, size_t n)
+#ifdef CONFIG_ARCH_HAS_COPY_MC
+static int copyout_mc(void __user *to, const void *from, size_t n)
 {
 	if (access_ok(to, n)) {
 		instrument_copy_to_user(to, from, n);
-		n = copy_to_user_mcsafe((__force void *) to, from, n);
+		n = copy_mc_to_user((__force void *) to, from, n);
 	}
 	return n;
 }
 
-static unsigned long memcpy_mcsafe_to_page(struct page *page, size_t offset,
+static unsigned long copy_mc_to_page(struct page *page, size_t offset,
 		const char *from, size_t len)
 {
 	unsigned long ret;
 	char *to;
 
 	to = kmap_atomic(page);
-	ret = memcpy_mcsafe(to + offset, from, len);
+	ret = copy_mc_to_kernel(to + offset, from, len);
 	kunmap_atomic(to);
 
 	return ret;
 }
 
-static size_t copy_pipe_to_iter_mcsafe(const void *addr, size_t bytes,
+static size_t copy_mc_pipe_to_iter(const void *addr, size_t bytes,
 				struct iov_iter *i)
 {
 	struct pipe_inode_info *pipe = i->pipe;
@@ -678,7 +678,7 @@ static size_t copy_pipe_to_iter_mcsafe(const void *addr, size_t bytes,
 		size_t chunk = min_t(size_t, n, PAGE_SIZE - off);
 		unsigned long rem;
 
-		rem = memcpy_mcsafe_to_page(pipe->bufs[i_head & p_mask].page,
+		rem = copy_mc_to_page(pipe->bufs[i_head & p_mask].page,
 					    off, addr, chunk);
 		i->head = i_head;
 		i->iov_offset = off + chunk - rem;
@@ -695,18 +695,17 @@ static size_t copy_pipe_to_iter_mcsafe(const void *addr, size_t bytes,
 }
 
 /**
- * _copy_to_iter_mcsafe - copy to user with source-read error exception handling
+ * _copy_mc_to_iter - copy to iter with source memory error exception handling
  * @addr: source kernel address
  * @bytes: total transfer length
  * @iter: destination iterator
  *
- * The pmem driver arranges for filesystem-dax to use this facility via
- * dax_copy_to_iter() for protecting read/write to persistent memory.
- * Unless / until an architecture can guarantee identical performance
- * between _copy_to_iter_mcsafe() and _copy_to_iter() it would be a
- * performance regression to switch more users to the mcsafe version.
+ * The pmem driver deploys this for the dax operation
+ * (dax_copy_to_iter()) for dax reads (bypass page-cache and the
+ * block-layer). Upon #MC read(2) aborts and returns EIO or the bytes
+ * successfully copied.
  *
- * Otherwise, the main differences between this and typical _copy_to_iter().
+ * The main differences between this and typical _copy_to_iter().
  *
  * * Typical tail/residue handling after a fault retries the copy
  *   byte-by-byte until the fault happens again. Re-triggering machine
@@ -717,23 +716,22 @@ static size_t copy_pipe_to_iter_mcsafe(const void *addr, size_t bytes,
  * * ITER_KVEC, ITER_PIPE, and ITER_BVEC can return short copies.
  *   Compare to copy_to_iter() where only ITER_IOVEC attempts might return
  *   a short copy.
- *
- * See MCSAFE_TEST for self-test.
  */
-size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i)
+size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
 {
 	const char *from = addr;
 	unsigned long rem, curr_addr, s_addr = (unsigned long) addr;
 
 	if (unlikely(iov_iter_is_pipe(i)))
-		return copy_pipe_to_iter_mcsafe(addr, bytes, i);
+		return copy_mc_pipe_to_iter(addr, bytes, i);
 	if (iter_is_iovec(i))
 		might_fault();
 	iterate_and_advance(i, bytes, v,
-		copyout_mcsafe(v.iov_base, (from += v.iov_len) - v.iov_len, v.iov_len),
+		copyout_mc(v.iov_base, (from += v.iov_len) - v.iov_len,
+			   v.iov_len),
 		({
-		rem = memcpy_mcsafe_to_page(v.bv_page, v.bv_offset,
-                               (from += v.bv_len) - v.bv_len, v.bv_len);
+		rem = copy_mc_to_page(v.bv_page, v.bv_offset,
+				      (from += v.bv_len) - v.bv_len, v.bv_len);
 		if (rem) {
 			curr_addr = (unsigned long) from;
 			bytes = curr_addr - s_addr - rem;
@@ -741,8 +739,8 @@ size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i)
 		}
 		}),
 		({
-		rem = memcpy_mcsafe(v.iov_base, (from += v.iov_len) - v.iov_len,
-				v.iov_len);
+		rem = copy_mc_to_kernel(v.iov_base, (from += v.iov_len)
+					- v.iov_len, v.iov_len);
 		if (rem) {
 			curr_addr = (unsigned long) from;
 			bytes = curr_addr - s_addr - rem;
@@ -753,8 +751,8 @@ size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i)
 
 	return bytes;
 }
-EXPORT_SYMBOL_GPL(_copy_to_iter_mcsafe);
-#endif /* CONFIG_ARCH_HAS_UACCESS_MCSAFE */
+EXPORT_SYMBOL_GPL(_copy_mc_to_iter);
+#endif /* CONFIG_ARCH_HAS_COPY_MC */
 
 size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
 {
diff --git a/tools/arch/x86/include/asm/mcsafe_test.h b/tools/arch/x86/include/asm/mcsafe_test.h
deleted file mode 100644
index 2ccd588fbad4..000000000000
--- a/tools/arch/x86/include/asm/mcsafe_test.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _MCSAFE_TEST_H_
-#define _MCSAFE_TEST_H_
-
-.macro MCSAFE_TEST_CTL
-.endm
-
-.macro MCSAFE_TEST_SRC reg count target
-.endm
-
-.macro MCSAFE_TEST_DST reg count target
-.endm
-#endif /* _MCSAFE_TEST_H_ */
diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S
index 45f8e1b02241..0b5b8ae56bd9 100644
--- a/tools/arch/x86/lib/memcpy_64.S
+++ b/tools/arch/x86/lib/memcpy_64.S
@@ -4,7 +4,6 @@
 #include <linux/linkage.h>
 #include <asm/errno.h>
 #include <asm/cpufeatures.h>
-#include <asm/mcsafe_test.h>
 #include <asm/alternative-asm.h>
 #include <asm/export.h>
 
@@ -187,117 +186,3 @@ SYM_FUNC_START(memcpy_orig)
 SYM_FUNC_END(memcpy_orig)
 
 .popsection
-
-#ifndef CONFIG_UML
-
-MCSAFE_TEST_CTL
-
-/*
- * __memcpy_mcsafe - memory copy with machine check exception handling
- * Note that we only catch machine checks when reading the source addresses.
- * Writes to target are posted and don't generate machine checks.
- */
-SYM_FUNC_START(__memcpy_mcsafe)
-	cmpl $8, %edx
-	/* Less than 8 bytes? Go to byte copy loop */
-	jb .L_no_whole_words
-
-	/* Check for bad alignment of source */
-	testl $7, %esi
-	/* Already aligned */
-	jz .L_8byte_aligned
-
-	/* Copy one byte at a time until source is 8-byte aligned */
-	movl %esi, %ecx
-	andl $7, %ecx
-	subl $8, %ecx
-	negl %ecx
-	subl %ecx, %edx
-.L_read_leading_bytes:
-	movb (%rsi), %al
-	MCSAFE_TEST_SRC %rsi 1 .E_leading_bytes
-	MCSAFE_TEST_DST %rdi 1 .E_leading_bytes
-.L_write_leading_bytes:
-	movb %al, (%rdi)
-	incq %rsi
-	incq %rdi
-	decl %ecx
-	jnz .L_read_leading_bytes
-
-.L_8byte_aligned:
-	movl %edx, %ecx
-	andl $7, %edx
-	shrl $3, %ecx
-	jz .L_no_whole_words
-
-.L_read_words:
-	movq (%rsi), %r8
-	MCSAFE_TEST_SRC %rsi 8 .E_read_words
-	MCSAFE_TEST_DST %rdi 8 .E_write_words
-.L_write_words:
-	movq %r8, (%rdi)
-	addq $8, %rsi
-	addq $8, %rdi
-	decl %ecx
-	jnz .L_read_words
-
-	/* Any trailing bytes? */
-.L_no_whole_words:
-	andl %edx, %edx
-	jz .L_done_memcpy_trap
-
-	/* Copy trailing bytes */
-	movl %edx, %ecx
-.L_read_trailing_bytes:
-	movb (%rsi), %al
-	MCSAFE_TEST_SRC %rsi 1 .E_trailing_bytes
-	MCSAFE_TEST_DST %rdi 1 .E_trailing_bytes
-.L_write_trailing_bytes:
-	movb %al, (%rdi)
-	incq %rsi
-	incq %rdi
-	decl %ecx
-	jnz .L_read_trailing_bytes
-
-	/* Copy successful. Return zero */
-.L_done_memcpy_trap:
-	xorl %eax, %eax
-.L_done:
-	ret
-SYM_FUNC_END(__memcpy_mcsafe)
-EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
-
-	.section .fixup, "ax"
-	/*
-	 * Return number of bytes not copied for any failure. Note that
-	 * there is no "tail" handling since the source buffer is 8-byte
-	 * aligned and poison is cacheline aligned.
-	 */
-.E_read_words:
-	shll	$3, %ecx
-.E_leading_bytes:
-	addl	%edx, %ecx
-.E_trailing_bytes:
-	mov	%ecx, %eax
-	jmp	.L_done
-
-	/*
-	 * For write fault handling, given the destination is unaligned,
-	 * we handle faults on multi-byte writes with a byte-by-byte
-	 * copy up to the write-protected page.
-	 */
-.E_write_words:
-	shll	$3, %ecx
-	addl	%edx, %ecx
-	movl	%ecx, %edx
-	jmp mcsafe_handle_tail
-
-	.previous
-
-	_ASM_EXTABLE_FAULT(.L_read_leading_bytes, .E_leading_bytes)
-	_ASM_EXTABLE_FAULT(.L_read_words, .E_read_words)
-	_ASM_EXTABLE_FAULT(.L_read_trailing_bytes, .E_trailing_bytes)
-	_ASM_EXTABLE(.L_write_leading_bytes, .E_leading_bytes)
-	_ASM_EXTABLE(.L_write_words, .E_write_words)
-	_ASM_EXTABLE(.L_write_trailing_bytes, .E_trailing_bytes)
-#endif
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index e034a8f24f46..893f021fec63 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -548,8 +548,8 @@ static const char *uaccess_safe_builtin[] = {
 	"__ubsan_handle_shift_out_of_bounds",
 	/* misc */
 	"csum_partial_copy_generic",
-	"__memcpy_mcsafe",
-	"mcsafe_handle_tail",
+	"copy_mc_fragile",
+	"copy_mc_fragile_handle_tail",
 	"ftrace_likely_update", /* CONFIG_TRACE_BRANCH_PROFILING */
 	NULL
 };
diff --git a/tools/perf/bench/Build b/tools/perf/bench/Build
index dd68a40a790c..878db6a59a41 100644
--- a/tools/perf/bench/Build
+++ b/tools/perf/bench/Build
@@ -13,7 +13,6 @@ perf-y += synthesize.o
 perf-y += kallsyms-parse.o
 perf-y += find-bit-bench.o
 
-perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-lib.o
 perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o
 perf-$(CONFIG_X86_64) += mem-memset-x86-64-asm.o
 
diff --git a/tools/perf/bench/mem-memcpy-x86-64-lib.c b/tools/perf/bench/mem-memcpy-x86-64-lib.c
deleted file mode 100644
index 4130734dde84..000000000000
--- a/tools/perf/bench/mem-memcpy-x86-64-lib.c
+++ /dev/null
@@ -1,24 +0,0 @@
-/*
- * From code in arch/x86/lib/usercopy_64.c, copied to keep tools/ copy
- * of the kernel's arch/x86/lib/memcpy_64.s used in 'perf bench mem memcpy'
- * happy.
- */
-#include <linux/types.h>
-
-unsigned long __memcpy_mcsafe(void *dst, const void *src, size_t cnt);
-unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len);
-
-unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len)
-{
-	for (; len; --len, to++, from++) {
-		/*
-		 * Call the assembly routine back directly since
-		 * memcpy_mcsafe() may silently fallback to memcpy.
-		 */
-		unsigned long rem = __memcpy_mcsafe(to, from, 1);
-
-		if (rem)
-			break;
-	}
-	return len;
-}
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index a1a5dc645b40..2ac0fff6dad8 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -23,7 +23,8 @@
 #include "nfit_test.h"
 #include "../watermark.h"
 
-#include <asm/mcsafe_test.h>
+#include <asm/copy_mc_test.h>
+#include <asm/mce.h>
 
 /*
  * Generate an NFIT table to describe the following topology:
@@ -3283,7 +3284,7 @@ static struct platform_driver nfit_test_driver = {
 	.id_table = nfit_test_id,
 };
 
-static char mcsafe_buf[PAGE_SIZE] __attribute__((__aligned__(PAGE_SIZE)));
+static char copy_mc_buf[PAGE_SIZE] __attribute__((__aligned__(PAGE_SIZE)));
 
 enum INJECT {
 	INJECT_NONE,
@@ -3291,7 +3292,7 @@ enum INJECT {
 	INJECT_DST,
 };
 
-static void mcsafe_test_init(char *dst, char *src, size_t size)
+static void copy_mc_test_init(char *dst, char *src, size_t size)
 {
 	size_t i;
 
@@ -3300,7 +3301,7 @@ static void mcsafe_test_init(char *dst, char *src, size_t size)
 		src[i] = (char) i;
 }
 
-static bool mcsafe_test_validate(unsigned char *dst, unsigned char *src,
+static bool copy_mc_test_validate(unsigned char *dst, unsigned char *src,
 		size_t size, unsigned long rem)
 {
 	size_t i;
@@ -3321,12 +3322,12 @@ static bool mcsafe_test_validate(unsigned char *dst, unsigned char *src,
 	return true;
 }
 
-void mcsafe_test(void)
+void copy_mc_test(void)
 {
 	char *inject_desc[] = { "none", "source", "destination" };
 	enum INJECT inj;
 
-	if (IS_ENABLED(CONFIG_MCSAFE_TEST)) {
+	if (IS_ENABLED(CONFIG_COPY_MC_TEST)) {
 		pr_info("%s: run...\n", __func__);
 	} else {
 		pr_info("%s: disabled, skip.\n", __func__);
@@ -3344,31 +3345,31 @@ void mcsafe_test(void)
 
 			switch (inj) {
 			case INJECT_NONE:
-				mcsafe_inject_src(NULL);
-				mcsafe_inject_dst(NULL);
-				dst = &mcsafe_buf[2048];
-				src = &mcsafe_buf[1024 - i];
+				copy_mc_inject_src(NULL);
+				copy_mc_inject_dst(NULL);
+				dst = &copy_mc_buf[2048];
+				src = &copy_mc_buf[1024 - i];
 				expect = 0;
 				break;
 			case INJECT_SRC:
-				mcsafe_inject_src(&mcsafe_buf[1024]);
-				mcsafe_inject_dst(NULL);
-				dst = &mcsafe_buf[2048];
-				src = &mcsafe_buf[1024 - i];
+				copy_mc_inject_src(&copy_mc_buf[1024]);
+				copy_mc_inject_dst(NULL);
+				dst = &copy_mc_buf[2048];
+				src = &copy_mc_buf[1024 - i];
 				expect = 512 - i;
 				break;
 			case INJECT_DST:
-				mcsafe_inject_src(NULL);
-				mcsafe_inject_dst(&mcsafe_buf[2048]);
-				dst = &mcsafe_buf[2048 - i];
-				src = &mcsafe_buf[1024];
+				copy_mc_inject_src(NULL);
+				copy_mc_inject_dst(&copy_mc_buf[2048]);
+				dst = &copy_mc_buf[2048 - i];
+				src = &copy_mc_buf[1024];
 				expect = 512 - i;
 				break;
 			}
 
-			mcsafe_test_init(dst, src, 512);
-			rem = __memcpy_mcsafe(dst, src, 512);
-			valid = mcsafe_test_validate(dst, src, 512, expect);
+			copy_mc_test_init(dst, src, 512);
+			rem = copy_mc_fragile(dst, src, 512);
+			valid = copy_mc_test_validate(dst, src, 512, expect);
 			if (rem == expect && valid)
 				continue;
 			pr_info("%s: copy(%#lx, %#lx, %d) off: %d rem: %ld %s expect: %ld\n",
@@ -3380,8 +3381,8 @@ void mcsafe_test(void)
 		}
 	}
 
-	mcsafe_inject_src(NULL);
-	mcsafe_inject_dst(NULL);
+	copy_mc_inject_src(NULL);
+	copy_mc_inject_dst(NULL);
 }
 
 static __init int nfit_test_init(void)
@@ -3392,7 +3393,7 @@ static __init int nfit_test_init(void)
 	libnvdimm_test();
 	acpi_nfit_test();
 	device_dax_test();
-	mcsafe_test();
+	copy_mc_test();
 	dax_pmem_test();
 	dax_pmem_core_test();
 #ifdef CONFIG_DEV_DAX_PMEM_COMPAT
diff --git a/tools/testing/selftests/powerpc/copyloops/.gitignore b/tools/testing/selftests/powerpc/copyloops/.gitignore
index ddaf140b8255..994b11af765c 100644
--- a/tools/testing/selftests/powerpc/copyloops/.gitignore
+++ b/tools/testing/selftests/powerpc/copyloops/.gitignore
@@ -12,4 +12,4 @@ memcpy_p7_t1
 copyuser_64_exc_t0
 copyuser_64_exc_t1
 copyuser_64_exc_t2
-memcpy_mcsafe_64
+copy_mc_64
diff --git a/tools/testing/selftests/powerpc/copyloops/Makefile b/tools/testing/selftests/powerpc/copyloops/Makefile
index 0917983a1c78..3095b1f1c02b 100644
--- a/tools/testing/selftests/powerpc/copyloops/Makefile
+++ b/tools/testing/selftests/powerpc/copyloops/Makefile
@@ -12,7 +12,7 @@ ASFLAGS = $(CFLAGS) -Wa,-mpower4
 TEST_GEN_PROGS := copyuser_64_t0 copyuser_64_t1 copyuser_64_t2 \
 		copyuser_p7_t0 copyuser_p7_t1 \
 		memcpy_64_t0 memcpy_64_t1 memcpy_64_t2 \
-		memcpy_p7_t0 memcpy_p7_t1 memcpy_mcsafe_64 \
+		memcpy_p7_t0 memcpy_p7_t1 copy_mc_64 \
 		copyuser_64_exc_t0 copyuser_64_exc_t1 copyuser_64_exc_t2
 
 EXTRA_SOURCES := validate.c ../harness.c stubs.S
@@ -45,9 +45,9 @@ $(OUTPUT)/memcpy_p7_t%:	memcpy_power7.S $(EXTRA_SOURCES)
 		-D SELFTEST_CASE=$(subst memcpy_p7_t,,$(notdir $@)) \
 		-o $@ $^
 
-$(OUTPUT)/memcpy_mcsafe_64: memcpy_mcsafe_64.S $(EXTRA_SOURCES)
+$(OUTPUT)/copy_mc_64: copy_mc_64.S $(EXTRA_SOURCES)
 	$(CC) $(CPPFLAGS) $(CFLAGS) \
-		-D COPY_LOOP=test_memcpy_mcsafe \
+		-D COPY_LOOP=test_copy_mc_generic \
 		-o $@ $^
 
 $(OUTPUT)/copyuser_64_exc_t%: copyuser_64.S exc_validate.c ../harness.c \
diff --git a/tools/testing/selftests/powerpc/copyloops/copy_mc_64.S b/tools/testing/selftests/powerpc/copyloops/copy_mc_64.S
new file mode 120000
index 000000000000..dcbe06d500fb
--- /dev/null
+++ b/tools/testing/selftests/powerpc/copyloops/copy_mc_64.S
@@ -0,0 +1 @@
+../../../../../arch/powerpc/lib/copy_mc_64.S
\ No newline at end of file
diff --git a/tools/testing/selftests/powerpc/copyloops/memcpy_mcsafe_64.S b/tools/testing/selftests/powerpc/copyloops/memcpy_mcsafe_64.S
deleted file mode 120000
index f0feef3062f6..000000000000
--- a/tools/testing/selftests/powerpc/copyloops/memcpy_mcsafe_64.S
+++ /dev/null
@@ -1 +0,0 @@
-../../../../../arch/powerpc/lib/memcpy_mcsafe_64.S
\ No newline at end of file
-- 
cgit v1.2.3


From 90428a8eb4947f9c7c905a178f3520dc7e2ee6d2 Mon Sep 17 00:00:00 2001
From: Maulik Shah <mkshah@codeaurora.org>
Date: Mon, 28 Sep 2020 10:02:01 +0530
Subject: genirq/PM: Introduce IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND flag

An interrupt that is disabled/masked but set for wakeup may still need to
be able to wake up the system from sleep states like "suspend to RAM".

To that effect, introduce the IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND flag.
If the irqchip have this flag set, the irq PM code will enable/unmask
the irqs that are marked for wakeup, but that are in a disabled state.

On resume, such irqs will be restored back to their disabled state.

Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Maulik Shah <mkshah@codeaurora.org>
[maz: commit message fix-up]
Signed-off-by: Marc Zyngier <maz@kernel.org>
Tested-by: Stephen Boyd <swboyd@chromium.org>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Link: https://lore.kernel.org/r/1601267524-20199-4-git-send-email-mkshah@codeaurora.org
---
 include/linux/irq.h  | 49 ++++++++++++++++++++++++++++++-------------------
 kernel/irq/debugfs.c |  3 +++
 kernel/irq/pm.c      | 34 ++++++++++++++++++++++++++++++----
 3 files changed, 63 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 1b7f4dfee35b..a8b84b88e673 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -215,6 +215,8 @@ struct irq_data {
  *				  from actual interrupt context.
  * IRQD_AFFINITY_ON_ACTIVATE	- Affinity is set on activation. Don't call
  *				  irq_chip::irq_set_affinity() when deactivated.
+ * IRQD_IRQ_ENABLED_ON_SUSPEND	- Interrupt is enabled on suspend by irq pm if
+ *				  irqchip have flag IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND set.
  */
 enum {
 	IRQD_TRIGGER_MASK		= 0xf,
@@ -240,6 +242,7 @@ enum {
 	IRQD_MSI_NOMASK_QUIRK		= (1 << 27),
 	IRQD_HANDLE_ENFORCE_IRQCTX	= (1 << 28),
 	IRQD_AFFINITY_ON_ACTIVATE	= (1 << 29),
+	IRQD_IRQ_ENABLED_ON_SUSPEND	= (1 << 30),
 };
 
 #define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors)
@@ -319,6 +322,11 @@ static inline bool irqd_is_handle_enforce_irqctx(struct irq_data *d)
 	return __irqd_to_state(d) & IRQD_HANDLE_ENFORCE_IRQCTX;
 }
 
+static inline bool irqd_is_enabled_on_suspend(struct irq_data *d)
+{
+	return __irqd_to_state(d) & IRQD_IRQ_ENABLED_ON_SUSPEND;
+}
+
 static inline bool irqd_is_wakeup_set(struct irq_data *d)
 {
 	return __irqd_to_state(d) & IRQD_WAKEUP_STATE;
@@ -545,27 +553,30 @@ struct irq_chip {
 /*
  * irq_chip specific flags
  *
- * IRQCHIP_SET_TYPE_MASKED:	Mask before calling chip.irq_set_type()
- * IRQCHIP_EOI_IF_HANDLED:	Only issue irq_eoi() when irq was handled
- * IRQCHIP_MASK_ON_SUSPEND:	Mask non wake irqs in the suspend path
- * IRQCHIP_ONOFFLINE_ENABLED:	Only call irq_on/off_line callbacks
- *				when irq enabled
- * IRQCHIP_SKIP_SET_WAKE:	Skip chip.irq_set_wake(), for this irq chip
- * IRQCHIP_ONESHOT_SAFE:	One shot does not require mask/unmask
- * IRQCHIP_EOI_THREADED:	Chip requires eoi() on unmask in threaded mode
- * IRQCHIP_SUPPORTS_LEVEL_MSI	Chip can provide two doorbells for Level MSIs
- * IRQCHIP_SUPPORTS_NMI:	Chip can deliver NMIs, only for root irqchips
+ * IRQCHIP_SET_TYPE_MASKED:           Mask before calling chip.irq_set_type()
+ * IRQCHIP_EOI_IF_HANDLED:            Only issue irq_eoi() when irq was handled
+ * IRQCHIP_MASK_ON_SUSPEND:           Mask non wake irqs in the suspend path
+ * IRQCHIP_ONOFFLINE_ENABLED:         Only call irq_on/off_line callbacks
+ *                                    when irq enabled
+ * IRQCHIP_SKIP_SET_WAKE:             Skip chip.irq_set_wake(), for this irq chip
+ * IRQCHIP_ONESHOT_SAFE:              One shot does not require mask/unmask
+ * IRQCHIP_EOI_THREADED:              Chip requires eoi() on unmask in threaded mode
+ * IRQCHIP_SUPPORTS_LEVEL_MSI:        Chip can provide two doorbells for Level MSIs
+ * IRQCHIP_SUPPORTS_NMI:              Chip can deliver NMIs, only for root irqchips
+ * IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND:  Invokes __enable_irq()/__disable_irq() for wake irqs
+ *                                    in the suspend path if they are in disabled state
  */
 enum {
-	IRQCHIP_SET_TYPE_MASKED		= (1 <<  0),
-	IRQCHIP_EOI_IF_HANDLED		= (1 <<  1),
-	IRQCHIP_MASK_ON_SUSPEND		= (1 <<  2),
-	IRQCHIP_ONOFFLINE_ENABLED	= (1 <<  3),
-	IRQCHIP_SKIP_SET_WAKE		= (1 <<  4),
-	IRQCHIP_ONESHOT_SAFE		= (1 <<  5),
-	IRQCHIP_EOI_THREADED		= (1 <<  6),
-	IRQCHIP_SUPPORTS_LEVEL_MSI	= (1 <<  7),
-	IRQCHIP_SUPPORTS_NMI		= (1 <<  8),
+	IRQCHIP_SET_TYPE_MASKED			= (1 <<  0),
+	IRQCHIP_EOI_IF_HANDLED			= (1 <<  1),
+	IRQCHIP_MASK_ON_SUSPEND			= (1 <<  2),
+	IRQCHIP_ONOFFLINE_ENABLED		= (1 <<  3),
+	IRQCHIP_SKIP_SET_WAKE			= (1 <<  4),
+	IRQCHIP_ONESHOT_SAFE			= (1 <<  5),
+	IRQCHIP_EOI_THREADED			= (1 <<  6),
+	IRQCHIP_SUPPORTS_LEVEL_MSI		= (1 <<  7),
+	IRQCHIP_SUPPORTS_NMI			= (1 <<  8),
+	IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND	= (1 <<  9),
 };
 
 #include <linux/irqdesc.h>
diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c
index b95ff5d5f4bd..b6e10945e8be 100644
--- a/kernel/irq/debugfs.c
+++ b/kernel/irq/debugfs.c
@@ -57,6 +57,7 @@ static const struct irq_bit_descr irqchip_flags[] = {
 	BIT_MASK_DESCR(IRQCHIP_EOI_THREADED),
 	BIT_MASK_DESCR(IRQCHIP_SUPPORTS_LEVEL_MSI),
 	BIT_MASK_DESCR(IRQCHIP_SUPPORTS_NMI),
+	BIT_MASK_DESCR(IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND),
 };
 
 static void
@@ -125,6 +126,8 @@ static const struct irq_bit_descr irqdata_states[] = {
 	BIT_MASK_DESCR(IRQD_DEFAULT_TRIGGER_SET),
 
 	BIT_MASK_DESCR(IRQD_HANDLE_ENFORCE_IRQCTX),
+
+	BIT_MASK_DESCR(IRQD_IRQ_ENABLED_ON_SUSPEND),
 };
 
 static const struct irq_bit_descr irqdesc_states[] = {
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index c6c7e187ae74..ce0adb22ee96 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -69,12 +69,26 @@ void irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action)
 
 static bool suspend_device_irq(struct irq_desc *desc)
 {
+	unsigned long chipflags = irq_desc_get_chip(desc)->flags;
+	struct irq_data *irqd = &desc->irq_data;
+
 	if (!desc->action || irq_desc_is_chained(desc) ||
 	    desc->no_suspend_depth)
 		return false;
 
-	if (irqd_is_wakeup_set(&desc->irq_data)) {
-		irqd_set(&desc->irq_data, IRQD_WAKEUP_ARMED);
+	if (irqd_is_wakeup_set(irqd)) {
+		irqd_set(irqd, IRQD_WAKEUP_ARMED);
+
+		if ((chipflags & IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND) &&
+		     irqd_irq_disabled(irqd)) {
+			/*
+			 * Interrupt marked for wakeup is in disabled state.
+			 * Enable interrupt here to unmask/enable in irqchip
+			 * to be able to resume with such interrupts.
+			 */
+			__enable_irq(desc);
+			irqd_set(irqd, IRQD_IRQ_ENABLED_ON_SUSPEND);
+		}
 		/*
 		 * We return true here to force the caller to issue
 		 * synchronize_irq(). We need to make sure that the
@@ -93,7 +107,7 @@ static bool suspend_device_irq(struct irq_desc *desc)
 	 * chip level. The chip implementation indicates that with
 	 * IRQCHIP_MASK_ON_SUSPEND.
 	 */
-	if (irq_desc_get_chip(desc)->flags & IRQCHIP_MASK_ON_SUSPEND)
+	if (chipflags & IRQCHIP_MASK_ON_SUSPEND)
 		mask_irq(desc);
 	return true;
 }
@@ -137,7 +151,19 @@ EXPORT_SYMBOL_GPL(suspend_device_irqs);
 
 static void resume_irq(struct irq_desc *desc)
 {
-	irqd_clear(&desc->irq_data, IRQD_WAKEUP_ARMED);
+	struct irq_data *irqd = &desc->irq_data;
+
+	irqd_clear(irqd, IRQD_WAKEUP_ARMED);
+
+	if (irqd_is_enabled_on_suspend(irqd)) {
+		/*
+		 * Interrupt marked for wakeup was enabled during suspend
+		 * entry. Disable such interrupts to restore them back to
+		 * original state.
+		 */
+		__disable_irq(desc);
+		irqd_clear(irqd, IRQD_IRQ_ENABLED_ON_SUSPEND);
+	}
 
 	if (desc->istate & IRQS_SUSPENDED)
 		goto resume;
-- 
cgit v1.2.3


From c6db31ffe202c3120147e9f3455a4dbc90546d39 Mon Sep 17 00:00:00 2001
From: Igor Russkikh <irusskikh@marvell.com>
Date: Mon, 5 Oct 2020 18:39:37 +0300
Subject: ethtool: allow netdev driver to define phy tunables

Define get/set phy tunable callbacks in ethtool ops.
This will allow MAC drivers with integrated PHY still to implement
these tunables.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ethtool.h |  4 ++++
 net/ethtool/ioctl.c     | 37 ++++++++++++++++++++++++-------------
 2 files changed, 28 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 060b20f0b20f..6408b446051f 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -505,6 +505,10 @@ struct ethtool_ops {
 				      struct ethtool_fecparam *);
 	void	(*get_ethtool_phy_stats)(struct net_device *,
 					 struct ethtool_stats *, u64 *);
+	int	(*get_phy_tunable)(struct net_device *,
+				   const struct ethtool_tunable *, void *);
+	int	(*set_phy_tunable)(struct net_device *,
+				   const struct ethtool_tunable *, const void *);
 };
 
 int ethtool_check_ops(const struct ethtool_ops *ops);
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 328d15cd4006..ec2cd7aab5ad 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -2459,14 +2459,15 @@ static int ethtool_phy_tunable_valid(const struct ethtool_tunable *tuna)
 
 static int get_phy_tunable(struct net_device *dev, void __user *useraddr)
 {
-	int ret;
-	struct ethtool_tunable tuna;
 	struct phy_device *phydev = dev->phydev;
+	struct ethtool_tunable tuna;
+	bool phy_drv_tunable;
 	void *data;
+	int ret;
 
-	if (!(phydev && phydev->drv && phydev->drv->get_tunable))
+	phy_drv_tunable = phydev && phydev->drv && phydev->drv->get_tunable;
+	if (!phy_drv_tunable && !dev->ethtool_ops->get_phy_tunable)
 		return -EOPNOTSUPP;
-
 	if (copy_from_user(&tuna, useraddr, sizeof(tuna)))
 		return -EFAULT;
 	ret = ethtool_phy_tunable_valid(&tuna);
@@ -2475,9 +2476,13 @@ static int get_phy_tunable(struct net_device *dev, void __user *useraddr)
 	data = kmalloc(tuna.len, GFP_USER);
 	if (!data)
 		return -ENOMEM;
-	mutex_lock(&phydev->lock);
-	ret = phydev->drv->get_tunable(phydev, &tuna, data);
-	mutex_unlock(&phydev->lock);
+	if (phy_drv_tunable) {
+		mutex_lock(&phydev->lock);
+		ret = phydev->drv->get_tunable(phydev, &tuna, data);
+		mutex_unlock(&phydev->lock);
+	} else {
+		ret = dev->ethtool_ops->get_phy_tunable(dev, &tuna, data);
+	}
 	if (ret)
 		goto out;
 	useraddr += sizeof(tuna);
@@ -2493,12 +2498,14 @@ out:
 
 static int set_phy_tunable(struct net_device *dev, void __user *useraddr)
 {
-	int ret;
-	struct ethtool_tunable tuna;
 	struct phy_device *phydev = dev->phydev;
+	struct ethtool_tunable tuna;
+	bool phy_drv_tunable;
 	void *data;
+	int ret;
 
-	if (!(phydev && phydev->drv && phydev->drv->set_tunable))
+	phy_drv_tunable = phydev && phydev->drv && phydev->drv->get_tunable;
+	if (!phy_drv_tunable && !dev->ethtool_ops->set_phy_tunable)
 		return -EOPNOTSUPP;
 	if (copy_from_user(&tuna, useraddr, sizeof(tuna)))
 		return -EFAULT;
@@ -2509,9 +2516,13 @@ static int set_phy_tunable(struct net_device *dev, void __user *useraddr)
 	data = memdup_user(useraddr, tuna.len);
 	if (IS_ERR(data))
 		return PTR_ERR(data);
-	mutex_lock(&phydev->lock);
-	ret = phydev->drv->set_tunable(phydev, &tuna, data);
-	mutex_unlock(&phydev->lock);
+	if (phy_drv_tunable) {
+		mutex_lock(&phydev->lock);
+		ret = phydev->drv->set_tunable(phydev, &tuna, data);
+		mutex_unlock(&phydev->lock);
+	} else {
+		ret = dev->ethtool_ops->set_phy_tunable(dev, &tuna, data);
+	}
 
 	kfree(data);
 	return ret;
-- 
cgit v1.2.3


From 451b05f413d3fd89ee84ae99a5029f619ed3cb78 Mon Sep 17 00:00:00 2001
From: Fabian Frederick <fabf@skynet.be>
Date: Mon, 5 Oct 2020 22:34:18 +0200
Subject: net: netdevice.h: sw_netstats_rx_add helper

some drivers/network protocols update rx bytes/packets under
u64_stats_update_begin/end sequence.
Add a specific helper like dev_lstats_add()

Signed-off-by: Fabian Frederick <fabf@skynet.be>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d126e36580c9..a0df43b13839 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2543,6 +2543,16 @@ struct pcpu_lstats {
 
 void dev_lstats_read(struct net_device *dev, u64 *packets, u64 *bytes);
 
+static inline void dev_sw_netstats_rx_add(struct net_device *dev, unsigned int len)
+{
+	struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
+
+	u64_stats_update_begin(&tstats->syncp);
+	tstats->rx_bytes += len;
+	tstats->rx_packets++;
+	u64_stats_update_end(&tstats->syncp);
+}
+
 static inline void dev_lstats_add(struct net_device *dev, unsigned int len)
 {
 	struct pcpu_lstats *lstats = this_cpu_ptr(dev->lstats);
-- 
cgit v1.2.3


From 2b0d3d3e4fcfb19d10f9a82910b8f0f05c56ee3e Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Thu, 1 Oct 2020 23:48:41 +0800
Subject: percpu_ref: reduce memory footprint of percpu_ref in fast path

'struct percpu_ref' is often embedded into one user structure, and the
instance is usually referenced in fast path, however actually only
'percpu_count_ptr' is needed in fast path.

So move other fields into one new structure of 'percpu_ref_data', and
allocate it dynamically via kzalloc(), then memory footprint of
'percpu_ref' in fast path is reduced a lot and becomes suitable to put
into hot cacheline of user structure.

Signed-off-by: Ming Lei <ming.lei@redhat.com>
Tested-by: Veronika Kabatova <vkabatov@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Acked-by: Tejun Heo <tj@kernel.org>
Cc: Sagi Grimberg <sagi@grimberg.me>
Cc: Tejun Heo <tj@kernel.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/infiniband/sw/rdmavt/mr.c |   2 +-
 include/linux/percpu-refcount.h   |  52 +++++++--------
 lib/percpu-refcount.c             | 131 ++++++++++++++++++++++++++++----------
 3 files changed, 123 insertions(+), 62 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/infiniband/sw/rdmavt/mr.c b/drivers/infiniband/sw/rdmavt/mr.c
index 2f7c25fea44a..8490fdb9c91e 100644
--- a/drivers/infiniband/sw/rdmavt/mr.c
+++ b/drivers/infiniband/sw/rdmavt/mr.c
@@ -499,7 +499,7 @@ static int rvt_check_refs(struct rvt_mregion *mr, const char *t)
 		rvt_pr_err(rdi,
 			   "%s timeout mr %p pd %p lkey %x refcount %ld\n",
 			   t, mr, mr->pd, mr->lkey,
-			   atomic_long_read(&mr->refcount.count));
+			   atomic_long_read(&mr->refcount.data->count));
 		rvt_get_mr(mr);
 		return -EBUSY;
 	}
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 87d8a38bdea1..16c35a728b4c 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -92,18 +92,30 @@ enum {
 	PERCPU_REF_ALLOW_REINIT	= 1 << 2,
 };
 
-struct percpu_ref {
+struct percpu_ref_data {
 	atomic_long_t		count;
-	/*
-	 * The low bit of the pointer indicates whether the ref is in percpu
-	 * mode; if set, then get/put will manipulate the atomic_t.
-	 */
-	unsigned long		percpu_count_ptr;
 	percpu_ref_func_t	*release;
 	percpu_ref_func_t	*confirm_switch;
 	bool			force_atomic:1;
 	bool			allow_reinit:1;
 	struct rcu_head		rcu;
+	struct percpu_ref	*ref;
+};
+
+struct percpu_ref {
+	/*
+	 * The low bit of the pointer indicates whether the ref is in percpu
+	 * mode; if set, then get/put will manipulate the atomic_t.
+	 */
+	unsigned long		percpu_count_ptr;
+
+	/*
+	 * 'percpu_ref' is often embedded into user structure, and only
+	 * 'percpu_count_ptr' is required in fast path, move other fields
+	 * into 'percpu_ref_data', so we can reduce memory footprint in
+	 * fast path.
+	 */
+	struct percpu_ref_data  *data;
 };
 
 int __must_check percpu_ref_init(struct percpu_ref *ref,
@@ -118,6 +130,7 @@ void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
 				 percpu_ref_func_t *confirm_kill);
 void percpu_ref_resurrect(struct percpu_ref *ref);
 void percpu_ref_reinit(struct percpu_ref *ref);
+bool percpu_ref_is_zero(struct percpu_ref *ref);
 
 /**
  * percpu_ref_kill - drop the initial ref
@@ -191,7 +204,7 @@ static inline void percpu_ref_get_many(struct percpu_ref *ref, unsigned long nr)
 	if (__ref_is_percpu(ref, &percpu_count))
 		this_cpu_add(*percpu_count, nr);
 	else
-		atomic_long_add(nr, &ref->count);
+		atomic_long_add(nr, &ref->data->count);
 
 	rcu_read_unlock();
 }
@@ -231,7 +244,7 @@ static inline bool percpu_ref_tryget_many(struct percpu_ref *ref,
 		this_cpu_add(*percpu_count, nr);
 		ret = true;
 	} else {
-		ret = atomic_long_add_unless(&ref->count, nr, 0);
+		ret = atomic_long_add_unless(&ref->data->count, nr, 0);
 	}
 
 	rcu_read_unlock();
@@ -279,7 +292,7 @@ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref)
 		this_cpu_inc(*percpu_count);
 		ret = true;
 	} else if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD)) {
-		ret = atomic_long_inc_not_zero(&ref->count);
+		ret = atomic_long_inc_not_zero(&ref->data->count);
 	}
 
 	rcu_read_unlock();
@@ -305,8 +318,8 @@ static inline void percpu_ref_put_many(struct percpu_ref *ref, unsigned long nr)
 
 	if (__ref_is_percpu(ref, &percpu_count))
 		this_cpu_sub(*percpu_count, nr);
-	else if (unlikely(atomic_long_sub_and_test(nr, &ref->count)))
-		ref->release(ref);
+	else if (unlikely(atomic_long_sub_and_test(nr, &ref->data->count)))
+		ref->data->release(ref);
 
 	rcu_read_unlock();
 }
@@ -339,21 +352,4 @@ static inline bool percpu_ref_is_dying(struct percpu_ref *ref)
 	return ref->percpu_count_ptr & __PERCPU_REF_DEAD;
 }
 
-/**
- * percpu_ref_is_zero - test whether a percpu refcount reached zero
- * @ref: percpu_ref to test
- *
- * Returns %true if @ref reached zero.
- *
- * This function is safe to call as long as @ref is between init and exit.
- */
-static inline bool percpu_ref_is_zero(struct percpu_ref *ref)
-{
-	unsigned long __percpu *percpu_count;
-
-	if (__ref_is_percpu(ref, &percpu_count))
-		return false;
-	return !atomic_long_read(&ref->count);
-}
-
 #endif
diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c
index 0ba686b8fe57..b6350d13538a 100644
--- a/lib/percpu-refcount.c
+++ b/lib/percpu-refcount.c
@@ -4,6 +4,7 @@
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/wait.h>
+#include <linux/slab.h>
 #include <linux/percpu-refcount.h>
 
 /*
@@ -64,18 +65,25 @@ int percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release,
 	size_t align = max_t(size_t, 1 << __PERCPU_REF_FLAG_BITS,
 			     __alignof__(unsigned long));
 	unsigned long start_count = 0;
+	struct percpu_ref_data *data;
 
 	ref->percpu_count_ptr = (unsigned long)
 		__alloc_percpu_gfp(sizeof(unsigned long), align, gfp);
 	if (!ref->percpu_count_ptr)
 		return -ENOMEM;
 
-	ref->force_atomic = flags & PERCPU_REF_INIT_ATOMIC;
-	ref->allow_reinit = flags & PERCPU_REF_ALLOW_REINIT;
+	data = kzalloc(sizeof(*ref->data), gfp);
+	if (!data) {
+		free_percpu((void __percpu *)ref->percpu_count_ptr);
+		return -ENOMEM;
+	}
+
+	data->force_atomic = flags & PERCPU_REF_INIT_ATOMIC;
+	data->allow_reinit = flags & PERCPU_REF_ALLOW_REINIT;
 
 	if (flags & (PERCPU_REF_INIT_ATOMIC | PERCPU_REF_INIT_DEAD)) {
 		ref->percpu_count_ptr |= __PERCPU_REF_ATOMIC;
-		ref->allow_reinit = true;
+		data->allow_reinit = true;
 	} else {
 		start_count += PERCPU_COUNT_BIAS;
 	}
@@ -85,14 +93,28 @@ int percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release,
 	else
 		start_count++;
 
-	atomic_long_set(&ref->count, start_count);
+	atomic_long_set(&data->count, start_count);
 
-	ref->release = release;
-	ref->confirm_switch = NULL;
+	data->release = release;
+	data->confirm_switch = NULL;
+	data->ref = ref;
+	ref->data = data;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(percpu_ref_init);
 
+static void __percpu_ref_exit(struct percpu_ref *ref)
+{
+	unsigned long __percpu *percpu_count = percpu_count_ptr(ref);
+
+	if (percpu_count) {
+		/* non-NULL confirm_switch indicates switching in progress */
+		WARN_ON_ONCE(ref->data->confirm_switch);
+		free_percpu(percpu_count);
+		ref->percpu_count_ptr = __PERCPU_REF_ATOMIC_DEAD;
+	}
+}
+
 /**
  * percpu_ref_exit - undo percpu_ref_init()
  * @ref: percpu_ref to exit
@@ -105,27 +127,36 @@ EXPORT_SYMBOL_GPL(percpu_ref_init);
  */
 void percpu_ref_exit(struct percpu_ref *ref)
 {
-	unsigned long __percpu *percpu_count = percpu_count_ptr(ref);
+	struct percpu_ref_data *data = ref->data;
+	unsigned long flags;
 
-	if (percpu_count) {
-		/* non-NULL confirm_switch indicates switching in progress */
-		WARN_ON_ONCE(ref->confirm_switch);
-		free_percpu(percpu_count);
-		ref->percpu_count_ptr = __PERCPU_REF_ATOMIC_DEAD;
-	}
+	__percpu_ref_exit(ref);
+
+	if (!data)
+		return;
+
+	spin_lock_irqsave(&percpu_ref_switch_lock, flags);
+	ref->percpu_count_ptr |= atomic_long_read(&ref->data->count) <<
+		__PERCPU_REF_FLAG_BITS;
+	ref->data = NULL;
+	spin_unlock_irqrestore(&percpu_ref_switch_lock, flags);
+
+	kfree(data);
 }
 EXPORT_SYMBOL_GPL(percpu_ref_exit);
 
 static void percpu_ref_call_confirm_rcu(struct rcu_head *rcu)
 {
-	struct percpu_ref *ref = container_of(rcu, struct percpu_ref, rcu);
+	struct percpu_ref_data *data = container_of(rcu,
+			struct percpu_ref_data, rcu);
+	struct percpu_ref *ref = data->ref;
 
-	ref->confirm_switch(ref);
-	ref->confirm_switch = NULL;
+	data->confirm_switch(ref);
+	data->confirm_switch = NULL;
 	wake_up_all(&percpu_ref_switch_waitq);
 
-	if (!ref->allow_reinit)
-		percpu_ref_exit(ref);
+	if (!data->allow_reinit)
+		__percpu_ref_exit(ref);
 
 	/* drop ref from percpu_ref_switch_to_atomic() */
 	percpu_ref_put(ref);
@@ -133,7 +164,9 @@ static void percpu_ref_call_confirm_rcu(struct rcu_head *rcu)
 
 static void percpu_ref_switch_to_atomic_rcu(struct rcu_head *rcu)
 {
-	struct percpu_ref *ref = container_of(rcu, struct percpu_ref, rcu);
+	struct percpu_ref_data *data = container_of(rcu,
+			struct percpu_ref_data, rcu);
+	struct percpu_ref *ref = data->ref;
 	unsigned long __percpu *percpu_count = percpu_count_ptr(ref);
 	unsigned long count = 0;
 	int cpu;
@@ -142,7 +175,7 @@ static void percpu_ref_switch_to_atomic_rcu(struct rcu_head *rcu)
 		count += *per_cpu_ptr(percpu_count, cpu);
 
 	pr_debug("global %lu percpu %lu\n",
-		 atomic_long_read(&ref->count), count);
+		 atomic_long_read(&data->count), count);
 
 	/*
 	 * It's crucial that we sum the percpu counters _before_ adding the sum
@@ -156,11 +189,11 @@ static void percpu_ref_switch_to_atomic_rcu(struct rcu_head *rcu)
 	 * reaching 0 before we add the percpu counts. But doing it at the same
 	 * time is equivalent and saves us atomic operations:
 	 */
-	atomic_long_add((long)count - PERCPU_COUNT_BIAS, &ref->count);
+	atomic_long_add((long)count - PERCPU_COUNT_BIAS, &data->count);
 
-	WARN_ONCE(atomic_long_read(&ref->count) <= 0,
+	WARN_ONCE(atomic_long_read(&data->count) <= 0,
 		  "percpu ref (%ps) <= 0 (%ld) after switching to atomic",
-		  ref->release, atomic_long_read(&ref->count));
+		  data->release, atomic_long_read(&data->count));
 
 	/* @ref is viewed as dead on all CPUs, send out switch confirmation */
 	percpu_ref_call_confirm_rcu(rcu);
@@ -186,10 +219,11 @@ static void __percpu_ref_switch_to_atomic(struct percpu_ref *ref,
 	 * Non-NULL ->confirm_switch is used to indicate that switching is
 	 * in progress.  Use noop one if unspecified.
 	 */
-	ref->confirm_switch = confirm_switch ?: percpu_ref_noop_confirm_switch;
+	ref->data->confirm_switch = confirm_switch ?:
+		percpu_ref_noop_confirm_switch;
 
 	percpu_ref_get(ref);	/* put after confirmation */
-	call_rcu(&ref->rcu, percpu_ref_switch_to_atomic_rcu);
+	call_rcu(&ref->data->rcu, percpu_ref_switch_to_atomic_rcu);
 }
 
 static void __percpu_ref_switch_to_percpu(struct percpu_ref *ref)
@@ -202,10 +236,10 @@ static void __percpu_ref_switch_to_percpu(struct percpu_ref *ref)
 	if (!(ref->percpu_count_ptr & __PERCPU_REF_ATOMIC))
 		return;
 
-	if (WARN_ON_ONCE(!ref->allow_reinit))
+	if (WARN_ON_ONCE(!ref->data->allow_reinit))
 		return;
 
-	atomic_long_add(PERCPU_COUNT_BIAS, &ref->count);
+	atomic_long_add(PERCPU_COUNT_BIAS, &ref->data->count);
 
 	/*
 	 * Restore per-cpu operation.  smp_store_release() is paired
@@ -223,6 +257,8 @@ static void __percpu_ref_switch_to_percpu(struct percpu_ref *ref)
 static void __percpu_ref_switch_mode(struct percpu_ref *ref,
 				     percpu_ref_func_t *confirm_switch)
 {
+	struct percpu_ref_data *data = ref->data;
+
 	lockdep_assert_held(&percpu_ref_switch_lock);
 
 	/*
@@ -230,10 +266,10 @@ static void __percpu_ref_switch_mode(struct percpu_ref *ref,
 	 * its completion.  If the caller ensures that ATOMIC switching
 	 * isn't in progress, this function can be called from any context.
 	 */
-	wait_event_lock_irq(percpu_ref_switch_waitq, !ref->confirm_switch,
+	wait_event_lock_irq(percpu_ref_switch_waitq, !data->confirm_switch,
 			    percpu_ref_switch_lock);
 
-	if (ref->force_atomic || (ref->percpu_count_ptr & __PERCPU_REF_DEAD))
+	if (data->force_atomic || (ref->percpu_count_ptr & __PERCPU_REF_DEAD))
 		__percpu_ref_switch_to_atomic(ref, confirm_switch);
 	else
 		__percpu_ref_switch_to_percpu(ref);
@@ -266,7 +302,7 @@ void percpu_ref_switch_to_atomic(struct percpu_ref *ref,
 
 	spin_lock_irqsave(&percpu_ref_switch_lock, flags);
 
-	ref->force_atomic = true;
+	ref->data->force_atomic = true;
 	__percpu_ref_switch_mode(ref, confirm_switch);
 
 	spin_unlock_irqrestore(&percpu_ref_switch_lock, flags);
@@ -284,7 +320,7 @@ EXPORT_SYMBOL_GPL(percpu_ref_switch_to_atomic);
 void percpu_ref_switch_to_atomic_sync(struct percpu_ref *ref)
 {
 	percpu_ref_switch_to_atomic(ref, NULL);
-	wait_event(percpu_ref_switch_waitq, !ref->confirm_switch);
+	wait_event(percpu_ref_switch_waitq, !ref->data->confirm_switch);
 }
 EXPORT_SYMBOL_GPL(percpu_ref_switch_to_atomic_sync);
 
@@ -312,7 +348,7 @@ void percpu_ref_switch_to_percpu(struct percpu_ref *ref)
 
 	spin_lock_irqsave(&percpu_ref_switch_lock, flags);
 
-	ref->force_atomic = false;
+	ref->data->force_atomic = false;
 	__percpu_ref_switch_mode(ref, NULL);
 
 	spin_unlock_irqrestore(&percpu_ref_switch_lock, flags);
@@ -344,7 +380,8 @@ void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
 	spin_lock_irqsave(&percpu_ref_switch_lock, flags);
 
 	WARN_ONCE(ref->percpu_count_ptr & __PERCPU_REF_DEAD,
-		  "%s called more than once on %ps!", __func__, ref->release);
+		  "%s called more than once on %ps!", __func__,
+		  ref->data->release);
 
 	ref->percpu_count_ptr |= __PERCPU_REF_DEAD;
 	__percpu_ref_switch_mode(ref, confirm_kill);
@@ -354,6 +391,34 @@ void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
 }
 EXPORT_SYMBOL_GPL(percpu_ref_kill_and_confirm);
 
+/**
+ * percpu_ref_is_zero - test whether a percpu refcount reached zero
+ * @ref: percpu_ref to test
+ *
+ * Returns %true if @ref reached zero.
+ *
+ * This function is safe to call as long as @ref is between init and exit.
+ */
+bool percpu_ref_is_zero(struct percpu_ref *ref)
+{
+	unsigned long __percpu *percpu_count;
+	unsigned long count, flags;
+
+	if (__ref_is_percpu(ref, &percpu_count))
+		return false;
+
+	/* protect us from being destroyed */
+	spin_lock_irqsave(&percpu_ref_switch_lock, flags);
+	if (ref->data)
+		count = atomic_long_read(&ref->data->count);
+	else
+		count = ref->percpu_count_ptr >> __PERCPU_REF_FLAG_BITS;
+	spin_unlock_irqrestore(&percpu_ref_switch_lock, flags);
+
+	return count == 0;
+}
+EXPORT_SYMBOL_GPL(percpu_ref_is_zero);
+
 /**
  * percpu_ref_reinit - re-initialize a percpu refcount
  * @ref: perpcu_ref to re-initialize
-- 
cgit v1.2.3


From 0549e87c30ae0d43d7e10424f2222bcd8bbe986d Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Thu, 1 Oct 2020 23:48:42 +0800
Subject: block: move 'q_usage_counter' into front of 'request_queue'

The field of 'q_usage_counter' is always fetched in fast path of every
block driver, and move it into front of 'request_queue', so it can be
fetched into 1st cacheline of 'request_queue' instance.

Signed-off-by: Ming Lei <ming.lei@redhat.com>
Tested-by: Veronika Kabatova <vkabatov@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Sagi Grimberg <sagi@grimberg.me>
Cc: Tejun Heo <tj@kernel.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blkdev.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index cf80e61b4c5e..5fc940423e5a 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -397,6 +397,8 @@ struct request_queue {
 	struct request		*last_merge;
 	struct elevator_queue	*elevator;
 
+	struct percpu_ref	q_usage_counter;
+
 	struct blk_queue_stats	*stats;
 	struct rq_qos		*rq_qos;
 
@@ -569,7 +571,6 @@ struct request_queue {
 	 * percpu_ref_kill() and percpu_ref_reinit().
 	 */
 	struct mutex		mq_freeze_lock;
-	struct percpu_ref	q_usage_counter;
 
 	struct blk_mq_tag_set	*tag_set;
 	struct list_head	tag_set_list;
-- 
cgit v1.2.3


From 92cf2fd156b273879198bb1d7e58851f822c481f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 6 Oct 2020 09:07:17 +0200
Subject: block: remove the unused blk_integrity_merge_rq export

Also move the definition from the public blkdev.h to the private
block/blk.h header.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-integrity.c  | 1 -
 block/blk.h            | 8 ++++++++
 include/linux/blkdev.h | 8 --------
 3 files changed, 8 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index 2b36a8f9b813..a262e069eb3f 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -183,7 +183,6 @@ bool blk_integrity_merge_rq(struct request_queue *q, struct request *req,
 
 	return true;
 }
-EXPORT_SYMBOL(blk_integrity_merge_rq);
 
 bool blk_integrity_merge_bio(struct request_queue *q, struct request *req,
 			     struct bio *bio)
diff --git a/block/blk.h b/block/blk.h
index c08762e10b04..ba4e8ac538cd 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -120,6 +120,9 @@ static inline bool bio_integrity_endio(struct bio *bio)
 	return true;
 }
 
+bool blk_integrity_merge_rq(struct request_queue *, struct request *,
+		struct request *);
+
 static inline bool integrity_req_gap_back_merge(struct request *req,
 		struct bio *next)
 {
@@ -143,6 +146,11 @@ static inline bool integrity_req_gap_front_merge(struct request *req,
 void blk_integrity_add(struct gendisk *);
 void blk_integrity_del(struct gendisk *);
 #else /* CONFIG_BLK_DEV_INTEGRITY */
+static inline bool blk_integrity_merge_rq(struct request_queue *rq,
+		struct request *r1, struct request *r2)
+{
+	return true;
+}
 static inline bool integrity_req_gap_back_merge(struct request *req,
 		struct bio *next)
 {
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 5fc940423e5a..6a6d9ea7420a 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1664,8 +1664,6 @@ extern int blk_integrity_compare(struct gendisk *, struct gendisk *);
 extern int blk_rq_map_integrity_sg(struct request_queue *, struct bio *,
 				   struct scatterlist *);
 extern int blk_rq_count_integrity_sg(struct request_queue *, struct bio *);
-extern bool blk_integrity_merge_rq(struct request_queue *, struct request *,
-				   struct request *);
 extern bool blk_integrity_merge_bio(struct request_queue *, struct request *,
 				    struct bio *);
 
@@ -1795,12 +1793,6 @@ static inline unsigned short queue_max_integrity_segments(const struct request_q
 {
 	return 0;
 }
-static inline bool blk_integrity_merge_rq(struct request_queue *rq,
-					  struct request *r1,
-					  struct request *r2)
-{
-	return true;
-}
 static inline bool blk_integrity_merge_bio(struct request_queue *rq,
 					   struct request *r,
 					   struct bio *b)
-- 
cgit v1.2.3


From d59da41998bc794441d7c039a059ed6eb0c2dc4d Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 6 Oct 2020 09:07:18 +0200
Subject: block: remove the unused blk_integrity_merge_bio export

Also move the definition from the public blkdev.h to the private
block/blk.h header.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-integrity.c  | 1 -
 block/blk.h            | 7 +++++++
 include/linux/blkdev.h | 8 --------
 3 files changed, 7 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index a262e069eb3f..410da060d1f5 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -211,7 +211,6 @@ bool blk_integrity_merge_bio(struct request_queue *q, struct request *req,
 
 	return true;
 }
-EXPORT_SYMBOL(blk_integrity_merge_bio);
 
 struct integrity_sysfs_entry {
 	struct attribute attr;
diff --git a/block/blk.h b/block/blk.h
index ba4e8ac538cd..8fcb146d3003 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -122,6 +122,8 @@ static inline bool bio_integrity_endio(struct bio *bio)
 
 bool blk_integrity_merge_rq(struct request_queue *, struct request *,
 		struct request *);
+bool blk_integrity_merge_bio(struct request_queue *, struct request *,
+		struct bio *);
 
 static inline bool integrity_req_gap_back_merge(struct request *req,
 		struct bio *next)
@@ -151,6 +153,11 @@ static inline bool blk_integrity_merge_rq(struct request_queue *rq,
 {
 	return true;
 }
+static inline bool blk_integrity_merge_bio(struct request_queue *rq,
+		struct request *r, struct bio *b)
+{
+	return true;
+}
 static inline bool integrity_req_gap_back_merge(struct request *req,
 		struct bio *next)
 {
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 6a6d9ea7420a..cda786fa4341 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1664,8 +1664,6 @@ extern int blk_integrity_compare(struct gendisk *, struct gendisk *);
 extern int blk_rq_map_integrity_sg(struct request_queue *, struct bio *,
 				   struct scatterlist *);
 extern int blk_rq_count_integrity_sg(struct request_queue *, struct bio *);
-extern bool blk_integrity_merge_bio(struct request_queue *, struct request *,
-				    struct bio *);
 
 static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
 {
@@ -1793,12 +1791,6 @@ static inline unsigned short queue_max_integrity_segments(const struct request_q
 {
 	return 0;
 }
-static inline bool blk_integrity_merge_bio(struct request_queue *rq,
-					   struct request *r,
-					   struct bio *b)
-{
-	return true;
-}
 
 static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
 						   unsigned int sectors)
-- 
cgit v1.2.3


From f55a52bb2cdbc5a92ca209d0ada90a490a188f58 Mon Sep 17 00:00:00 2001
From: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Date: Sat, 3 Oct 2020 00:41:46 +0900
Subject: can: dev: fix type of get_can_dlc() and get_canfd_dlc() macros

The macros get_can_dlc() and get_canfd_dlc() are not visible in
userland. As such, type u8 should be preferred over type __u8.

Reference: https://lkml.org/lkml/2020/10/1/708
Signed-off-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://lore.kernel.org/r/20201002154219.4887-3-mailhol.vincent@wanadoo.fr
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 include/linux/can/dev.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h
index ed0482b2f4b2..f8975d0b90bb 100644
--- a/include/linux/can/dev.h
+++ b/include/linux/can/dev.h
@@ -84,13 +84,13 @@ struct can_priv {
 
 /*
  * get_can_dlc(value) - helper macro to cast a given data length code (dlc)
- * to __u8 and ensure the dlc value to be max. 8 bytes.
+ * to u8 and ensure the dlc value to be max. 8 bytes.
  *
  * To be used in the CAN netdriver receive path to ensure conformance with
  * ISO 11898-1 Chapter 8.4.2.3 (DLC field)
  */
-#define get_can_dlc(i)		(min_t(__u8, (i), CAN_MAX_DLC))
-#define get_canfd_dlc(i)	(min_t(__u8, (i), CANFD_MAX_DLC))
+#define get_can_dlc(i)		(min_t(u8, (i), CAN_MAX_DLC))
+#define get_canfd_dlc(i)	(min_t(u8, (i), CANFD_MAX_DLC))
 
 /* Check for outgoing skbs that have not been created by the CAN subsystem */
 static inline bool can_skb_headroom_valid(struct net_device *dev,
-- 
cgit v1.2.3


From 6fcd669514794da08ce6bfa272b6ec9b33cb543d Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 20 Aug 2020 09:56:58 +0200
Subject: block: optimize blk_queue_zoned_model for !CONFIG_BLK_DEV_ZONED

Always return BLK_ZONED_NONE if zoned device support is not enabled.
This allows various compiler optimizations including the dead code
elimination that we so like for avoiding ifdefs.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
---
 include/linux/blkdev.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 8e77f12de522..1b81b2766858 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -692,7 +692,9 @@ static inline bool queue_is_mq(struct request_queue *q)
 static inline enum blk_zoned_model
 blk_queue_zoned_model(struct request_queue *q)
 {
-	return q->limits.zoned;
+	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED))
+		return q->limits.zoned;
+	return BLK_ZONED_NONE;
 }
 
 static inline bool blk_queue_is_zoned(struct request_queue *q)
-- 
cgit v1.2.3


From 200da27ab32d89ca43bd8ef010f84b205e5c780a Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <natechancellor@gmail.com>
Date: Tue, 6 Oct 2020 13:11:15 -0700
Subject: LSM: Fix type of id parameter in kernel_post_load_data prototype

Clang warns:

security/security.c:1716:59: warning: implicit conversion from
enumeration type 'enum kernel_load_data_id' to different enumeration
type 'enum kernel_read_file_id' [-Wenum-conversion]
        ret = call_int_hook(kernel_post_load_data, 0, buf, size, id,
              ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~
security/security.c:715:22: note: expanded from macro 'call_int_hook'
                        RC = P->hook.FUNC(__VA_ARGS__);         \
                             ~            ^~~~~~~~~~~
1 warning generated.

There is a mismatch between the id parameter type in
security_kernel_post_load_data and the function pointer prototype that
is created by the LSM_HOOK macro in the security_list_options union. Fix
the type in the LSM_HOOK macro as 'enum kernel_load_data_id' is what is
expected.

Fixes: b64fcae74b6d ("LSM: Introduce kernel_post_load_data() hook")
Acked-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Link: https://lore.kernel.org/r/20201006201115.716550-1-natechancellor@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/lsm_hook_defs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index d67cb3502310..32a940117e7a 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -186,7 +186,7 @@ LSM_HOOK(int, 0, kernel_create_files_as, struct cred *new, struct inode *inode)
 LSM_HOOK(int, 0, kernel_module_request, char *kmod_name)
 LSM_HOOK(int, 0, kernel_load_data, enum kernel_load_data_id id, bool contents)
 LSM_HOOK(int, 0, kernel_post_load_data, char *buf, loff_t size,
-	 enum kernel_read_file_id id, char *description)
+	 enum kernel_load_data_id id, char *description)
 LSM_HOOK(int, 0, kernel_read_file, struct file *file,
 	 enum kernel_read_file_id id, bool contents)
 LSM_HOOK(int, 0, kernel_post_read_file, struct file *file, char *buf,
-- 
cgit v1.2.3


From 849facea92fa68d9292f9b06d7c4ee9e7a06b8dc Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 7 Oct 2020 11:04:08 +0200
Subject: dma-direct: simplify the DMA_ATTR_NO_KERNEL_MAPPING handling

Use and entirely separate code path for the DMA_ATTR_NO_KERNEL_MAPPING
path.  This avoids any confusion about the ret type, and avoids lots of
attr checks and helpers that can be significantly simplified now.

It also ensures that common handling is applied to architetures still
using the arch alloc/free hooks.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/dma-map-ops.h |  13 ------
 kernel/dma/direct.c         | 100 +++++++++++++++++---------------------------
 2 files changed, 39 insertions(+), 74 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 33c6e24707a9..8029f7e04145 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -219,19 +219,6 @@ static inline bool dev_is_dma_coherent(struct device *dev)
 }
 #endif /* CONFIG_ARCH_HAS_DMA_COHERENCE_H */
 
-/*
- * Check if an allocation needs to be marked uncached to be coherent.
- */
-static __always_inline bool dma_alloc_need_uncached(struct device *dev,
-		unsigned long attrs)
-{
-	if (dev_is_dma_coherent(dev))
-		return false;
-	if (attrs & DMA_ATTR_NO_KERNEL_MAPPING)
-		return false;
-	return true;
-}
-
 void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t gfp, unsigned long attrs);
 void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index eddcb70251c9..b92d08e65999 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -75,39 +75,6 @@ static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
 		min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
 }
 
-/*
- * Decrypting memory is allowed to block, so if this device requires
- * unencrypted memory it must come from atomic pools.
- */
-static inline bool dma_should_alloc_from_pool(struct device *dev, gfp_t gfp,
-					      unsigned long attrs)
-{
-	if (!IS_ENABLED(CONFIG_DMA_COHERENT_POOL))
-		return false;
-	if (gfpflags_allow_blocking(gfp))
-		return false;
-	if (force_dma_unencrypted(dev))
-		return true;
-	if (!IS_ENABLED(CONFIG_DMA_DIRECT_REMAP))
-		return false;
-	if (dma_alloc_need_uncached(dev, attrs))
-		return true;
-	return false;
-}
-
-static inline bool dma_should_free_from_pool(struct device *dev,
-					     unsigned long attrs)
-{
-	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL))
-		return true;
-	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
-	    !force_dma_unencrypted(dev))
-		return false;
-	if (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP))
-		return true;
-	return false;
-}
-
 static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 		gfp_t gfp)
 {
@@ -170,35 +137,45 @@ void *dma_direct_alloc(struct device *dev, size_t size,
 	void *ret;
 	int err;
 
-	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
-	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
-	    dma_alloc_need_uncached(dev, attrs))
-		return arch_dma_alloc(dev, size, dma_handle, gfp, attrs);
-
 	size = PAGE_ALIGN(size);
 	if (attrs & DMA_ATTR_NO_WARN)
 		gfp |= __GFP_NOWARN;
 
-	if (dma_should_alloc_from_pool(dev, gfp, attrs))
-		return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp);
-
-	/* we always manually zero the memory once we are done */
-	page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO);
-	if (!page)
-		return NULL;
-
 	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
 	    !force_dma_unencrypted(dev)) {
+		page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO);
+		if (!page)
+			return NULL;
 		/* remove any dirty cache lines on the kernel alias */
 		if (!PageHighMem(page))
 			arch_dma_prep_coherent(page, size);
+		*dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
 		/* return the page pointer as the opaque cookie */
-		ret = page;
-		goto done;
+		return page;
 	}
 
+	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
+	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
+	    !dev_is_dma_coherent(dev))
+		return arch_dma_alloc(dev, size, dma_handle, gfp, attrs);
+
+	/*
+	 * Remapping or decrypting memory may block. If either is required and
+	 * we can't block, allocate the memory from the atomic pools.
+	 */
+	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
+	    !gfpflags_allow_blocking(gfp) &&
+	    (force_dma_unencrypted(dev) ||
+	     (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && !dev_is_dma_coherent(dev))))
+		return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp);
+
+	/* we always manually zero the memory once we are done */
+	page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO);
+	if (!page)
+		return NULL;
+
 	if ((IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
-	     dma_alloc_need_uncached(dev, attrs)) ||
+	     !dev_is_dma_coherent(dev)) ||
 	    (IS_ENABLED(CONFIG_DMA_REMAP) && PageHighMem(page))) {
 		/* remove any dirty cache lines on the kernel alias */
 		arch_dma_prep_coherent(page, size);
@@ -241,7 +218,7 @@ void *dma_direct_alloc(struct device *dev, size_t size,
 	memset(ret, 0, size);
 
 	if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
-	    dma_alloc_need_uncached(dev, attrs)) {
+	    !dev_is_dma_coherent(dev)) {
 		arch_dma_prep_coherent(page, size);
 		ret = arch_dma_set_uncached(ret, size);
 		if (IS_ERR(ret))
@@ -269,25 +246,25 @@ void dma_direct_free(struct device *dev, size_t size,
 {
 	unsigned int page_order = get_order(size);
 
+	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
+	    !force_dma_unencrypted(dev)) {
+		/* cpu_addr is a struct page cookie, not a kernel address */
+		dma_free_contiguous(dev, cpu_addr, size);
+		return;
+	}
+
 	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
 	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
-	    dma_alloc_need_uncached(dev, attrs)) {
+	    !dev_is_dma_coherent(dev)) {
 		arch_dma_free(dev, size, cpu_addr, dma_addr, attrs);
 		return;
 	}
 
 	/* If cpu_addr is not from an atomic pool, dma_free_from_pool() fails */
-	if (dma_should_free_from_pool(dev, attrs) &&
+	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
 	    dma_free_from_pool(dev, cpu_addr, PAGE_ALIGN(size)))
 		return;
 
-	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
-	    !force_dma_unencrypted(dev)) {
-		/* cpu_addr is a struct page cookie, not a kernel address */
-		dma_free_contiguous(dev, cpu_addr, size);
-		return;
-	}
-
 	if (force_dma_unencrypted(dev))
 		set_memory_encrypted((unsigned long)cpu_addr, 1 << page_order);
 
@@ -305,7 +282,8 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
 	struct page *page;
 	void *ret;
 
-	if (dma_should_alloc_from_pool(dev, gfp, 0))
+	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
+	    force_dma_unencrypted(dev) && !gfpflags_allow_blocking(gfp))
 		return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp);
 
 	page = __dma_direct_alloc_pages(dev, size, gfp);
@@ -344,7 +322,7 @@ void dma_direct_free_pages(struct device *dev, size_t size,
 	void *vaddr = page_address(page);
 
 	/* If cpu_addr is not from an atomic pool, dma_free_from_pool() fails */
-	if (dma_should_free_from_pool(dev, 0) &&
+	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
 	    dma_free_from_pool(dev, vaddr, size))
 		return;
 
-- 
cgit v1.2.3


From c0ab7ffce275d3f83bd253c70889c28821d4a41d Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Tue, 6 Oct 2020 14:09:09 -0700
Subject: x86/mce: Recover from poison found while copying from user space

Existing kernel code can only recover from a machine check on code that
is tagged in the exception table with a fault handling recovery path.

Add two new fields in the task structure to pass information from
machine check handler to the "task_work" that is queued to run before
the task returns to user mode:

+ mce_vaddr: will be initialized to the user virtual address of the fault
  in the case where the fault occurred in the kernel copying data from
  a user address.  This is so that kill_me_maybe() can provide that
  information to the user SIGBUS handler.

+ mce_kflags: copy of the struct mce.kflags needed by kill_me_maybe()
  to determine if mce_vaddr is applicable to this error.

Add code to recover from a machine check while copying data from user
space to the kernel. Action for this case is the same as if the user
touched the poison directly; unmap the page and send a SIGBUS to the task.

Use a new helper function to share common code between the "fault
in user mode" case and the "fault while copying from user" case.

New code paths will be activated by the next patch which sets
MCE_IN_KERNEL_COPYIN.

Suggested-by: Borislav Petkov <bp@alien8.de>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20201006210910.21062-6-tony.luck@intel.com
---
 arch/x86/kernel/cpu/mce/core.c | 27 ++++++++++++++++++++-------
 include/linux/sched.h          |  2 ++
 2 files changed, 22 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 2d6caf09e8e6..5c423c4bab68 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1260,6 +1260,21 @@ static void kill_me_maybe(struct callback_head *cb)
 	kill_me_now(cb);
 }
 
+static void queue_task_work(struct mce *m, int kill_it)
+{
+	current->mce_addr = m->addr;
+	current->mce_kflags = m->kflags;
+	current->mce_ripv = !!(m->mcgstatus & MCG_STATUS_RIPV);
+	current->mce_whole_page = whole_page(m);
+
+	if (kill_it)
+		current->mce_kill_me.func = kill_me_now;
+	else
+		current->mce_kill_me.func = kill_me_maybe;
+
+	task_work_add(current, &current->mce_kill_me, true);
+}
+
 /*
  * The actual machine check handler. This only handles real
  * exceptions when something got corrupted coming in through int 18.
@@ -1401,13 +1416,8 @@ noinstr void do_machine_check(struct pt_regs *regs)
 		/* If this triggers there is no way to recover. Die hard. */
 		BUG_ON(!on_thread_stack() || !user_mode(regs));
 
-		current->mce_addr = m.addr;
-		current->mce_ripv = !!(m.mcgstatus & MCG_STATUS_RIPV);
-		current->mce_whole_page = whole_page(&m);
-		current->mce_kill_me.func = kill_me_maybe;
-		if (kill_it)
-			current->mce_kill_me.func = kill_me_now;
-		task_work_add(current, &current->mce_kill_me, true);
+		queue_task_work(&m, kill_it);
+
 	} else {
 		/*
 		 * Handle an MCE which has happened in kernel space but from
@@ -1422,6 +1432,9 @@ noinstr void do_machine_check(struct pt_regs *regs)
 			if (!fixup_exception(regs, X86_TRAP_MC, 0, 0))
 				mce_panic("Failed kernel mode recovery", &m, msg);
 		}
+
+		if (m.kflags & MCE_IN_KERNEL_COPYIN)
+			queue_task_work(&m, kill_it);
 	}
 out:
 	mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 93ecd930efd3..2cbba3e2b150 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1308,6 +1308,8 @@ struct task_struct {
 #endif
 
 #ifdef CONFIG_X86_MCE
+	void __user			*mce_vaddr;
+	__u64				mce_kflags;
 	u64				mce_addr;
 	__u64				mce_ripv : 1,
 					mce_whole_page : 1,
-- 
cgit v1.2.3


From c33fe275b530f1ce1ab99923d50eb399f53ed545 Mon Sep 17 00:00:00 2001
From: Goldwyn Rodrigues <rgoldwyn@suse.com>
Date: Thu, 24 Sep 2020 11:39:08 -0500
Subject: fs: remove no longer used dio_end_io()

Since we removed the last user of dio_end_io() when btrfs got converted
to iomap infrastructure ("btrfs: switch to iomap for direct IO"), remove
the helper function dio_end_io().

Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/direct-io.c     | 19 -------------------
 include/linux/fs.h |  2 --
 2 files changed, 21 deletions(-)

(limited to 'include/linux')

diff --git a/fs/direct-io.c b/fs/direct-io.c
index 183299892465..abf535b036ab 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -386,25 +386,6 @@ static void dio_bio_end_io(struct bio *bio)
 	spin_unlock_irqrestore(&dio->bio_lock, flags);
 }
 
-/**
- * dio_end_io - handle the end io action for the given bio
- * @bio: The direct io bio thats being completed
- *
- * This is meant to be called by any filesystem that uses their own dio_submit_t
- * so that the DIO specific endio actions are dealt with after the filesystem
- * has done it's completion work.
- */
-void dio_end_io(struct bio *bio)
-{
-	struct dio *dio = bio->bi_private;
-
-	if (dio->is_async)
-		dio_bio_end_aio(bio);
-	else
-		dio_bio_end_io(bio);
-}
-EXPORT_SYMBOL_GPL(dio_end_io);
-
 static inline void
 dio_bio_alloc(struct dio *dio, struct dio_submit *sdio,
 	      struct block_device *bdev,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7519ae003a08..8e2842a9c0b3 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3079,8 +3079,6 @@ enum {
 	DIO_SKIP_HOLES	= 0x02,
 };
 
-void dio_end_io(struct bio *bio);
-
 ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 			     struct block_device *bdev, struct iov_iter *iter,
 			     get_block_t get_block,
-- 
cgit v1.2.3


From dcb5cdf60a1fbbdb3b4dd2abc562206481f09ef1 Mon Sep 17 00:00:00 2001
From: Kajol Jain <kjain@linux.ibm.com>
Date: Sat, 3 Oct 2020 13:19:42 +0530
Subject: powerpc/perf/hv-gpci: Add cpu hotplug support

Patch here adds cpu hotplug functions to hv_gpci pmu.
A new cpuhp_state "CPUHP_AP_PERF_POWERPC_HV_GPCI_ONLINE" enum
is added.

The online callback function updates the cpumask only if its
empty. As the primary intention of adding hotplug support
is to designate a CPU to make HCALL to collect the
counter data.

The offline function test and clear corresponding cpu in a cpumask
and update cpumask to any other active cpu.

Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201003074943.338618-4-kjain@linux.ibm.com
---
 arch/powerpc/perf/hv-gpci.c | 46 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/cpuhotplug.h  |  1 +
 2 files changed, 47 insertions(+)

(limited to 'include/linux')

diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c
index 1667315b82e9..1bca0c1a6cfe 100644
--- a/arch/powerpc/perf/hv-gpci.c
+++ b/arch/powerpc/perf/hv-gpci.c
@@ -48,6 +48,8 @@ EVENT_DEFINE_RANGE_FORMAT(length, config1, 24, 31);
 /* u32, byte offset */
 EVENT_DEFINE_RANGE_FORMAT(offset, config1, 32, 63);
 
+static cpumask_t hv_gpci_cpumask;
+
 static struct attribute *format_attrs[] = {
 	&format_attr_request.attr,
 	&format_attr_starting_index.attr,
@@ -266,6 +268,45 @@ static struct pmu h_gpci_pmu = {
 	.capabilities = PERF_PMU_CAP_NO_EXCLUDE,
 };
 
+static int ppc_hv_gpci_cpu_online(unsigned int cpu)
+{
+	if (cpumask_empty(&hv_gpci_cpumask))
+		cpumask_set_cpu(cpu, &hv_gpci_cpumask);
+
+	return 0;
+}
+
+static int ppc_hv_gpci_cpu_offline(unsigned int cpu)
+{
+	int target;
+
+	/* Check if exiting cpu is used for collecting gpci events */
+	if (!cpumask_test_and_clear_cpu(cpu, &hv_gpci_cpumask))
+		return 0;
+
+	/* Find a new cpu to collect gpci events */
+	target = cpumask_last(cpu_active_mask);
+
+	if (target < 0 || target >= nr_cpu_ids) {
+		pr_err("hv_gpci: CPU hotplug init failed\n");
+		return -1;
+	}
+
+	/* Migrate gpci events to the new target */
+	cpumask_set_cpu(target, &hv_gpci_cpumask);
+	perf_pmu_migrate_context(&h_gpci_pmu, cpu, target);
+
+	return 0;
+}
+
+static int hv_gpci_cpu_hotplug_init(void)
+{
+	return cpuhp_setup_state(CPUHP_AP_PERF_POWERPC_HV_GPCI_ONLINE,
+			  "perf/powerpc/hv_gcpi:online",
+			  ppc_hv_gpci_cpu_online,
+			  ppc_hv_gpci_cpu_offline);
+}
+
 static int hv_gpci_init(void)
 {
 	int r;
@@ -286,6 +327,11 @@ static int hv_gpci_init(void)
 		return -ENODEV;
 	}
 
+	/* init cpuhotplug */
+	r = hv_gpci_cpu_hotplug_init();
+	if (r)
+		return r;
+
 	/* sampling not supported */
 	h_gpci_pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
 
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 3215023d4852..5d08ed922510 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -183,6 +183,7 @@ enum cpuhp_state {
 	CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE,
 	CPUHP_AP_PERF_POWERPC_TRACE_IMC_ONLINE,
 	CPUHP_AP_PERF_POWERPC_HV_24x7_ONLINE,
+	CPUHP_AP_PERF_POWERPC_HV_GPCI_ONLINE,
 	CPUHP_AP_WATCHDOG_ONLINE,
 	CPUHP_AP_WORKQUEUE_ONLINE,
 	CPUHP_AP_RCUTREE_ONLINE,
-- 
cgit v1.2.3


From dd841a749d1ded8e2e5facc4242ee0b6779fc0cb Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Sun, 14 Jun 2020 06:07:10 -0400
Subject: radix tree test suite: Fix compilation

Introducing local_lock broke compilation; fix it all up.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 include/linux/radix-tree.h                  | 1 +
 lib/radix-tree.c                            | 1 -
 tools/testing/radix-tree/linux/kernel.h     | 1 +
 tools/testing/radix-tree/linux/local_lock.h | 8 ++++++++
 tools/testing/radix-tree/test.h             | 4 ----
 5 files changed, 10 insertions(+), 5 deletions(-)
 create mode 100644 tools/testing/radix-tree/linux/local_lock.h

(limited to 'include/linux')

diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index c2a9f7c90727..5c85059a92ba 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -11,6 +11,7 @@
 #include <linux/bitops.h>
 #include <linux/kernel.h>
 #include <linux/list.h>
+#include <linux/percpu.h>
 #include <linux/preempt.h>
 #include <linux/rcupdate.h>
 #include <linux/spinlock.h>
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 8e4a3a4397f2..0f10485d46b6 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -20,7 +20,6 @@
 #include <linux/kernel.h>
 #include <linux/kmemleak.h>
 #include <linux/percpu.h>
-#include <linux/local_lock.h>
 #include <linux/preempt.h>		/* in_interrupt() */
 #include <linux/radix-tree.h>
 #include <linux/rcupdate.h>
diff --git a/tools/testing/radix-tree/linux/kernel.h b/tools/testing/radix-tree/linux/kernel.h
index 4568248222ae..39867fd80c8f 100644
--- a/tools/testing/radix-tree/linux/kernel.h
+++ b/tools/testing/radix-tree/linux/kernel.h
@@ -22,4 +22,5 @@
 #define __releases(x)
 #define __must_hold(x)
 
+#define EXPORT_PER_CPU_SYMBOL_GPL(x)
 #endif /* _KERNEL_H */
diff --git a/tools/testing/radix-tree/linux/local_lock.h b/tools/testing/radix-tree/linux/local_lock.h
new file mode 100644
index 000000000000..b3cf8b233ca4
--- /dev/null
+++ b/tools/testing/radix-tree/linux/local_lock.h
@@ -0,0 +1,8 @@
+#ifndef _LINUX_LOCAL_LOCK
+#define _LINUX_LOCAL_LOCK
+typedef struct { } local_lock_t;
+
+static inline void local_lock(local_lock_t *lock) { }
+static inline void local_unlock(local_lock_t *lock) { }
+#define INIT_LOCAL_LOCK(x) { }
+#endif
diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h
index 34dab4d18744..7ef7067e942c 100644
--- a/tools/testing/radix-tree/test.h
+++ b/tools/testing/radix-tree/test.h
@@ -56,8 +56,4 @@ int root_tag_get(struct radix_tree_root *root, unsigned int tag);
 unsigned long node_maxindex(struct radix_tree_node *);
 unsigned long shift_maxindex(unsigned int shift);
 int radix_tree_cpu_dead(unsigned int cpu);
-struct radix_tree_preload {
-	unsigned nr;
-	struct radix_tree_node *nodes;
-};
 extern struct radix_tree_preload radix_tree_preloads;
-- 
cgit v1.2.3


From fe6f0cdc49263ae61cd3d33399662808c2398e86 Mon Sep 17 00:00:00 2001
From: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Date: Wed, 7 Oct 2020 21:35:08 +0900
Subject: block: soft limit zone-append sectors as well

Martin rightfully noted that for normal filesystem IO we have soft limits
in place, to prevent them from getting too big and not lead to
unpredictable latencies. For zone append we only have the hardware limit
in place.

Cap the max sectors we submit via zone-append to the maximal number of
sectors if the second limit is lower.

Reported-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Link: https://lore.kernel.org/linux-btrfs/yq1k0w8g3rw.fsf@ca-mkp.ca.oracle.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blkdev.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index cda786fa4341..6bd667c34777 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1407,7 +1407,10 @@ static inline unsigned int queue_max_segment_size(const struct request_queue *q)
 
 static inline unsigned int queue_max_zone_append_sectors(const struct request_queue *q)
 {
-	return q->limits.max_zone_append_sectors;
+
+	const struct queue_limits *l = &q->limits;
+
+	return min(l->max_zone_append_sectors, l->max_sectors);
 }
 
 static inline unsigned queue_logical_block_size(const struct request_queue *q)
-- 
cgit v1.2.3


From 24a1877286822293684ef3f7bada4ea48a6e129e Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 24 Sep 2020 17:48:51 +0200
Subject: locking/seqlock: Tweak DEFINE_SEQLOCK() kernel doc

ctags creates a warning:
|ctags: Warning: include/linux/seqlock.h:738: null expansion of name pattern "\2"

The DEFINE_SEQLOCK() macro is passed to ctags and being told to expect
an argument.

Add a dummy argument to keep ctags quiet.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Will Deacon <will@kernel.org>
Link: https://lkml.kernel.org/r/20200924154851.skmswuyj322yuz4g@linutronix.de
---
 include/linux/seqlock.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 76e44e6c0100..ac5b07f558b0 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -821,7 +821,7 @@ typedef struct {
 	} while (0)
 
 /**
- * DEFINE_SEQLOCK() - Define a statically allocated seqlock_t
+ * DEFINE_SEQLOCK(sl) - Define a statically allocated seqlock_t
  * @sl: Name of the seqlock_t instance
  */
 #define DEFINE_SEQLOCK(sl) \
-- 
cgit v1.2.3


From cf1f08cac375630af6b6307907a3fc20fcf847c7 Mon Sep 17 00:00:00 2001
From: Anna Schumaker <Anna.Schumaker@Netapp.com>
Date: Fri, 17 Apr 2020 11:00:24 -0400
Subject: SUNRPC: Implement a xdr_page_pos() function

I'll need this for READ_PLUS to help figure out the offset where page
data is stored at, but it might also be useful for other things.

Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/linux/sunrpc/xdr.h |  1 +
 net/sunrpc/xdr.c           | 13 +++++++++++++
 2 files changed, 14 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 5a6a81b7cd9f..25a68dd87ecf 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -240,6 +240,7 @@ extern int xdr_restrict_buflen(struct xdr_stream *xdr, int newbuflen);
 extern void xdr_write_pages(struct xdr_stream *xdr, struct page **pages,
 		unsigned int base, unsigned int len);
 extern unsigned int xdr_stream_pos(const struct xdr_stream *xdr);
+extern unsigned int xdr_page_pos(const struct xdr_stream *xdr);
 extern void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf,
 			    __be32 *p, struct rpc_rqst *rqst);
 extern void xdr_init_decode_pages(struct xdr_stream *xdr, struct xdr_buf *buf,
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index fa7517c1d125..909920fab93b 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -505,6 +505,19 @@ unsigned int xdr_stream_pos(const struct xdr_stream *xdr)
 }
 EXPORT_SYMBOL_GPL(xdr_stream_pos);
 
+/**
+ * xdr_page_pos - Return the current offset from the start of the xdr pages
+ * @xdr: pointer to struct xdr_stream
+ */
+unsigned int xdr_page_pos(const struct xdr_stream *xdr)
+{
+	unsigned int pos = xdr_stream_pos(xdr);
+
+	WARN_ON(pos < xdr->buf->head[0].iov_len);
+	return pos - xdr->buf->head[0].iov_len;
+}
+EXPORT_SYMBOL_GPL(xdr_page_pos);
+
 /**
  * xdr_init_encode - Initialize a struct xdr_stream for sending data.
  * @xdr: pointer to xdr_stream struct
-- 
cgit v1.2.3


From c567552612ece787b178e3b147b5854ad422a836 Mon Sep 17 00:00:00 2001
From: Anna Schumaker <Anna.Schumaker@Netapp.com>
Date: Wed, 28 May 2014 13:41:22 -0400
Subject: NFS: Add READ_PLUS data segment support

This patch adds client support for decoding a single NFS4_CONTENT_DATA
segment returned by the server. This is the simplest implementation
possible, since it does not account for any hole segments in the reply.

Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/nfs42xdr.c         | 141 ++++++++++++++++++++++++++++++++++++++++++++++
 fs/nfs/nfs4client.c       |   2 +
 fs/nfs/nfs4proc.c         |  43 +++++++++++++-
 fs/nfs/nfs4xdr.c          |   1 +
 include/linux/nfs4.h      |   2 +-
 include/linux/nfs_fs_sb.h |   1 +
 include/linux/nfs_xdr.h   |   2 +-
 7 files changed, 187 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index cc50085e151c..930b4ca212c1 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -45,6 +45,15 @@
 #define encode_deallocate_maxsz		(op_encode_hdr_maxsz + \
 					 encode_fallocate_maxsz)
 #define decode_deallocate_maxsz		(op_decode_hdr_maxsz)
+#define encode_read_plus_maxsz		(op_encode_hdr_maxsz + \
+					 encode_stateid_maxsz + 3)
+#define NFS42_READ_PLUS_SEGMENT_SIZE	(1 /* data_content4 */ + \
+					 2 /* data_info4.di_offset */ + \
+					 2 /* data_info4.di_length */)
+#define decode_read_plus_maxsz		(op_decode_hdr_maxsz + \
+					 1 /* rpr_eof */ + \
+					 1 /* rpr_contents count */ + \
+					 NFS42_READ_PLUS_SEGMENT_SIZE)
 #define encode_seek_maxsz		(op_encode_hdr_maxsz + \
 					 encode_stateid_maxsz + \
 					 2 /* offset */ + \
@@ -128,6 +137,14 @@
 					 decode_putfh_maxsz + \
 					 decode_deallocate_maxsz + \
 					 decode_getattr_maxsz)
+#define NFS4_enc_read_plus_sz		(compound_encode_hdr_maxsz + \
+					 encode_sequence_maxsz + \
+					 encode_putfh_maxsz + \
+					 encode_read_plus_maxsz)
+#define NFS4_dec_read_plus_sz		(compound_decode_hdr_maxsz + \
+					 decode_sequence_maxsz + \
+					 decode_putfh_maxsz + \
+					 decode_read_plus_maxsz)
 #define NFS4_enc_seek_sz		(compound_encode_hdr_maxsz + \
 					 encode_sequence_maxsz + \
 					 encode_putfh_maxsz + \
@@ -324,6 +341,16 @@ static void encode_deallocate(struct xdr_stream *xdr,
 	encode_fallocate(xdr, args);
 }
 
+static void encode_read_plus(struct xdr_stream *xdr,
+			     const struct nfs_pgio_args *args,
+			     struct compound_hdr *hdr)
+{
+	encode_op_hdr(xdr, OP_READ_PLUS, decode_read_plus_maxsz, hdr);
+	encode_nfs4_stateid(xdr, &args->stateid);
+	encode_uint64(xdr, args->offset);
+	encode_uint32(xdr, args->count);
+}
+
 static void encode_seek(struct xdr_stream *xdr,
 			const struct nfs42_seek_args *args,
 			struct compound_hdr *hdr)
@@ -722,6 +749,28 @@ static void nfs4_xdr_enc_deallocate(struct rpc_rqst *req,
 	encode_nops(&hdr);
 }
 
+/*
+ * Encode READ_PLUS request
+ */
+static void nfs4_xdr_enc_read_plus(struct rpc_rqst *req,
+				   struct xdr_stream *xdr,
+				   const void *data)
+{
+	const struct nfs_pgio_args *args = data;
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->seq_args, &hdr);
+	encode_putfh(xdr, args->fh, &hdr);
+	encode_read_plus(xdr, args, &hdr);
+
+	rpc_prepare_reply_pages(req, args->pages, args->pgbase,
+				args->count, hdr.replen);
+	encode_nops(&hdr);
+}
+
 /*
  * Encode SEEK request
  */
@@ -970,6 +1019,71 @@ static int decode_deallocate(struct xdr_stream *xdr, struct nfs42_falloc_res *re
 	return decode_op_hdr(xdr, OP_DEALLOCATE);
 }
 
+static int decode_read_plus_data(struct xdr_stream *xdr, struct nfs_pgio_res *res,
+				 uint32_t *eof)
+{
+	uint32_t count, recvd;
+	uint64_t offset;
+	__be32 *p;
+
+	p = xdr_inline_decode(xdr, 8 + 4);
+	if (unlikely(!p))
+		return -EIO;
+
+	p = xdr_decode_hyper(p, &offset);
+	count = be32_to_cpup(p);
+	recvd = xdr_read_pages(xdr, count);
+	res->count += recvd;
+
+	if (count > recvd) {
+		dprintk("NFS: server cheating in read reply: "
+				"count %u > recvd %u\n", count, recvd);
+		*eof = 0;
+		return 1;
+	}
+
+	return 0;
+}
+
+static int decode_read_plus(struct xdr_stream *xdr, struct nfs_pgio_res *res)
+{
+	uint32_t eof, segments, type;
+	int status;
+	__be32 *p;
+
+	status = decode_op_hdr(xdr, OP_READ_PLUS);
+	if (status)
+		return status;
+
+	p = xdr_inline_decode(xdr, 4 + 4);
+	if (unlikely(!p))
+		return -EIO;
+
+	eof = be32_to_cpup(p++);
+	segments = be32_to_cpup(p++);
+	if (segments == 0)
+		goto out;
+
+	p = xdr_inline_decode(xdr, 4);
+	if (unlikely(!p))
+		return -EIO;
+
+	type = be32_to_cpup(p++);
+	if (type == NFS4_CONTENT_DATA)
+		status = decode_read_plus_data(xdr, res, &eof);
+	else
+		return -EINVAL;
+
+	if (status)
+		return status;
+	if (segments > 1)
+		eof = 0;
+
+out:
+	res->eof = eof;
+	return 0;
+}
+
 static int decode_seek(struct xdr_stream *xdr, struct nfs42_seek_res *res)
 {
 	int status;
@@ -1146,6 +1260,33 @@ out:
 	return status;
 }
 
+/*
+ * Decode READ_PLUS request
+ */
+static int nfs4_xdr_dec_read_plus(struct rpc_rqst *rqstp,
+				  struct xdr_stream *xdr,
+				  void *data)
+{
+	struct nfs_pgio_res *res = data;
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->seq_res, rqstp);
+	if (status)
+		goto out;
+	status = decode_putfh(xdr);
+	if (status)
+		goto out;
+	status = decode_read_plus(xdr, res);
+	if (!status)
+		status = res->count;
+out:
+	return status;
+}
+
 /*
  * Decode SEEK request
  */
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index daacc78a3d48..be7915c861ce 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -1045,6 +1045,8 @@ static int nfs4_server_common_setup(struct nfs_server *server,
 	server->caps |= server->nfs_client->cl_mvops->init_caps;
 	if (server->flags & NFS_MOUNT_NORDIRPLUS)
 			server->caps &= ~NFS_CAP_READDIRPLUS;
+	if (server->nfs_client->cl_proto == XPRT_TRANSPORT_RDMA)
+		server->caps &= ~NFS_CAP_READ_PLUS;
 	/*
 	 * Don't use NFS uid/gid mapping if we're using AUTH_SYS or lower
 	 * authentication.
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index f7ef2ca699a5..d09fd3236820 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -70,6 +70,10 @@
 
 #include "nfs4trace.h"
 
+#ifdef CONFIG_NFS_V4_2
+#include "nfs42.h"
+#endif /* CONFIG_NFS_V4_2 */
+
 #define NFSDBG_FACILITY		NFSDBG_PROC
 
 #define NFS4_BITMASK_SZ		3
@@ -5272,28 +5276,60 @@ static bool nfs4_read_stateid_changed(struct rpc_task *task,
 	return true;
 }
 
-static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
+static bool nfs4_read_plus_not_supported(struct rpc_task *task,
+					 struct nfs_pgio_header *hdr)
 {
+	struct nfs_server *server = NFS_SERVER(hdr->inode);
+	struct rpc_message *msg = &task->tk_msg;
 
+	if (msg->rpc_proc == &nfs4_procedures[NFSPROC4_CLNT_READ_PLUS] &&
+	    server->caps & NFS_CAP_READ_PLUS && task->tk_status == -ENOTSUPP) {
+		server->caps &= ~NFS_CAP_READ_PLUS;
+		msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ];
+		rpc_restart_call_prepare(task);
+		return true;
+	}
+	return false;
+}
+
+static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
+{
 	dprintk("--> %s\n", __func__);
 
 	if (!nfs4_sequence_done(task, &hdr->res.seq_res))
 		return -EAGAIN;
 	if (nfs4_read_stateid_changed(task, &hdr->args))
 		return -EAGAIN;
+	if (nfs4_read_plus_not_supported(task, hdr))
+		return -EAGAIN;
 	if (task->tk_status > 0)
 		nfs_invalidate_atime(hdr->inode);
 	return hdr->pgio_done_cb ? hdr->pgio_done_cb(task, hdr) :
 				    nfs4_read_done_cb(task, hdr);
 }
 
+#ifdef CONFIG_NFS_V4_2
+static void nfs42_read_plus_support(struct nfs_server *server, struct rpc_message *msg)
+{
+	if (server->caps & NFS_CAP_READ_PLUS)
+		msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ_PLUS];
+	else
+		msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ];
+}
+#else
+static void nfs42_read_plus_support(struct nfs_server *server, struct rpc_message *msg)
+{
+	msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ];
+}
+#endif /* CONFIG_NFS_V4_2 */
+
 static void nfs4_proc_read_setup(struct nfs_pgio_header *hdr,
 				 struct rpc_message *msg)
 {
 	hdr->timestamp   = jiffies;
 	if (!hdr->pgio_done_cb)
 		hdr->pgio_done_cb = nfs4_read_done_cb;
-	msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ];
+	nfs42_read_plus_support(NFS_SERVER(hdr->inode), msg);
 	nfs4_init_sequence(&hdr->args.seq_args, &hdr->res.seq_res, 0, 0);
 }
 
@@ -10215,7 +10251,8 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = {
 		| NFS_CAP_SEEK
 		| NFS_CAP_LAYOUTSTATS
 		| NFS_CAP_CLONE
-		| NFS_CAP_LAYOUTERROR,
+		| NFS_CAP_LAYOUTERROR
+		| NFS_CAP_READ_PLUS,
 	.init_client = nfs41_init_client,
 	.shutdown_client = nfs41_shutdown_client,
 	.match_stateid = nfs41_match_stateid,
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 3336ea3407a0..c6dbfcae7517 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -7615,6 +7615,7 @@ const struct rpc_procinfo nfs4_procedures[] = {
 	PROC42(SETXATTR,	enc_setxattr,		dec_setxattr),
 	PROC42(LISTXATTRS,	enc_listxattrs,		dec_listxattrs),
 	PROC42(REMOVEXATTR,	enc_removexattr,	dec_removexattr),
+	PROC42(READ_PLUS,	enc_read_plus,		dec_read_plus),
 };
 
 static unsigned int nfs_version4_counts[ARRAY_SIZE(nfs4_procedures)];
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index b8360be141da..9dc7eeac924f 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -551,13 +551,13 @@ enum {
 
 	NFSPROC4_CLNT_LOOKUPP,
 	NFSPROC4_CLNT_LAYOUTERROR,
-
 	NFSPROC4_CLNT_COPY_NOTIFY,
 
 	NFSPROC4_CLNT_GETXATTR,
 	NFSPROC4_CLNT_SETXATTR,
 	NFSPROC4_CLNT_LISTXATTRS,
 	NFSPROC4_CLNT_REMOVEXATTR,
+	NFSPROC4_CLNT_READ_PLUS,
 };
 
 /* nfs41 types */
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 7eae72a8762e..38e60ec742df 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -287,5 +287,6 @@ struct nfs_server {
 #define NFS_CAP_LAYOUTERROR	(1U << 26)
 #define NFS_CAP_COPY_NOTIFY	(1U << 27)
 #define NFS_CAP_XATTR		(1U << 28)
+#define NFS_CAP_READ_PLUS	(1U << 29)
 
 #endif
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 0599efd57eb9..d63cb862d58e 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -657,7 +657,7 @@ struct nfs_pgio_args {
 struct nfs_pgio_res {
 	struct nfs4_sequence_res	seq_res;
 	struct nfs_fattr *	fattr;
-	__u32			count;
+	__u64			count;
 	__u32			op_status;
 	union {
 		struct {
-- 
cgit v1.2.3


From 84ce182ab85b8ad5002fb1125ba572df99dd0d1c Mon Sep 17 00:00:00 2001
From: Anna Schumaker <Anna.Schumaker@Netapp.com>
Date: Wed, 28 May 2014 13:38:53 -0400
Subject: SUNRPC: Add the ability to expand holes in data pages

This patch adds the ability to "read a hole" into a set of XDR data
pages by taking the following steps:

1) Shift all data after the current xdr->p to the right, possibly into
   the tail,
2) Zero the specified range, and
3) Update xdr->p to point beyond the hole.

Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/linux/sunrpc/xdr.h |  1 +
 net/sunrpc/xdr.c           | 69 ++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 70 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 25a68dd87ecf..f9636d2a6d54 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -250,6 +250,7 @@ extern __be32 *xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes);
 extern unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len);
 extern void xdr_enter_page(struct xdr_stream *xdr, unsigned int len);
 extern int xdr_process_buf(struct xdr_buf *buf, unsigned int offset, unsigned int len, int (*actor)(struct scatterlist *, void *), void *data);
+extern uint64_t xdr_expand_hole(struct xdr_stream *, uint64_t, uint64_t);
 
 /**
  * xdr_stream_remaining - Return the number of bytes remaining in the stream
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 10a88a67206a..1052ccdb4e99 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -390,6 +390,38 @@ _copy_from_pages(char *p, struct page **pages, size_t pgbase, size_t len)
 }
 EXPORT_SYMBOL_GPL(_copy_from_pages);
 
+/**
+ * _zero_pages
+ * @pages: array of pages
+ * @pgbase: beginning page vector address
+ * @len: length
+ */
+static void
+_zero_pages(struct page **pages, size_t pgbase, size_t len)
+{
+	struct page **page;
+	char *vpage;
+	size_t zero;
+
+	page = pages + (pgbase >> PAGE_SHIFT);
+	pgbase &= ~PAGE_MASK;
+
+	do {
+		zero = PAGE_SIZE - pgbase;
+		if (zero > len)
+			zero = len;
+
+		vpage = kmap_atomic(*page);
+		memset(vpage + pgbase, 0, zero);
+		kunmap_atomic(vpage);
+
+		flush_dcache_page(*page);
+		pgbase = 0;
+		page++;
+
+	} while ((len -= zero) != 0);
+}
+
 /**
  * xdr_shrink_bufhead
  * @buf: xdr_buf
@@ -1096,6 +1128,43 @@ unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len)
 }
 EXPORT_SYMBOL_GPL(xdr_read_pages);
 
+uint64_t xdr_expand_hole(struct xdr_stream *xdr, uint64_t offset, uint64_t length)
+{
+	struct xdr_buf *buf = xdr->buf;
+	unsigned int bytes;
+	unsigned int from;
+	unsigned int truncated = 0;
+
+	if ((offset + length) < offset ||
+	    (offset + length) > buf->page_len)
+		length = buf->page_len - offset;
+
+	xdr_realign_pages(xdr);
+	from = xdr_page_pos(xdr);
+	bytes = xdr->nwords << 2;
+
+	if (offset + length + bytes > buf->page_len) {
+		unsigned int shift = (offset + length + bytes) - buf->page_len;
+		unsigned int res = _shift_data_right_tail(buf, from + bytes - shift, shift);
+		truncated = shift - res;
+		xdr->nwords -= XDR_QUADLEN(truncated);
+		bytes -= shift;
+	}
+
+	/* Now move the page data over and zero pages */
+	if (bytes > 0)
+		_shift_data_right_pages(buf->pages,
+					buf->page_base + offset + length,
+					buf->page_base + from,
+					bytes);
+	_zero_pages(buf->pages, buf->page_base + offset, length);
+
+	buf->len += length - (from - offset) - truncated;
+	xdr_set_page(xdr, offset + length, PAGE_SIZE);
+	return length;
+}
+EXPORT_SYMBOL_GPL(xdr_expand_hole);
+
 /**
  * xdr_enter_page - decode data from the XDR page
  * @xdr: pointer to xdr_stream struct
-- 
cgit v1.2.3


From e6ac0accb27c6892b7ebc7799e7ce56b3390a678 Mon Sep 17 00:00:00 2001
From: Anna Schumaker <Anna.Schumaker@Netapp.com>
Date: Tue, 21 Apr 2020 11:27:00 -0400
Subject: SUNRPC: Add an xdr_align_data() function

For now, this function simply aligns the data at the beginning of the
pages. This can eventually be expanded to shift data to the correct
offsets when we're ready.

Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/linux/sunrpc/xdr.h |   1 +
 net/sunrpc/xdr.c           | 121 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 122 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index f9636d2a6d54..fe7ff7f5b584 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -250,6 +250,7 @@ extern __be32 *xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes);
 extern unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len);
 extern void xdr_enter_page(struct xdr_stream *xdr, unsigned int len);
 extern int xdr_process_buf(struct xdr_buf *buf, unsigned int offset, unsigned int len, int (*actor)(struct scatterlist *, void *), void *data);
+extern uint64_t xdr_align_data(struct xdr_stream *, uint64_t, uint32_t);
 extern uint64_t xdr_expand_hole(struct xdr_stream *, uint64_t, uint64_t);
 
 /**
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 1052ccdb4e99..3feff529a764 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -19,6 +19,9 @@
 #include <linux/bvec.h>
 #include <trace/events/sunrpc.h>
 
+static void _copy_to_pages(struct page **, size_t, const char *, size_t);
+
+
 /*
  * XDR functions for basic NFS types
  */
@@ -201,6 +204,88 @@ EXPORT_SYMBOL_GPL(xdr_inline_pages);
  * Helper routines for doing 'memmove' like operations on a struct xdr_buf
  */
 
+/**
+ * _shift_data_left_pages
+ * @pages: vector of pages containing both the source and dest memory area.
+ * @pgto_base: page vector address of destination
+ * @pgfrom_base: page vector address of source
+ * @len: number of bytes to copy
+ *
+ * Note: the addresses pgto_base and pgfrom_base are both calculated in
+ *       the same way:
+ *            if a memory area starts at byte 'base' in page 'pages[i]',
+ *            then its address is given as (i << PAGE_CACHE_SHIFT) + base
+ * Alse note: pgto_base must be < pgfrom_base, but the memory areas
+ * 	they point to may overlap.
+ */
+static void
+_shift_data_left_pages(struct page **pages, size_t pgto_base,
+			size_t pgfrom_base, size_t len)
+{
+	struct page **pgfrom, **pgto;
+	char *vfrom, *vto;
+	size_t copy;
+
+	BUG_ON(pgfrom_base <= pgto_base);
+
+	pgto = pages + (pgto_base >> PAGE_SHIFT);
+	pgfrom = pages + (pgfrom_base >> PAGE_SHIFT);
+
+	pgto_base &= ~PAGE_MASK;
+	pgfrom_base &= ~PAGE_MASK;
+
+	do {
+		if (pgto_base >= PAGE_SIZE) {
+			pgto_base = 0;
+			pgto++;
+		}
+		if (pgfrom_base >= PAGE_SIZE){
+			pgfrom_base = 0;
+			pgfrom++;
+		}
+
+		copy = len;
+		if (copy > (PAGE_SIZE - pgto_base))
+			copy = PAGE_SIZE - pgto_base;
+		if (copy > (PAGE_SIZE - pgfrom_base))
+			copy = PAGE_SIZE - pgfrom_base;
+
+		vto = kmap_atomic(*pgto);
+		if (*pgto != *pgfrom) {
+			vfrom = kmap_atomic(*pgfrom);
+			memcpy(vto + pgto_base, vfrom + pgfrom_base, copy);
+			kunmap_atomic(vfrom);
+		} else
+			memmove(vto + pgto_base, vto + pgfrom_base, copy);
+		flush_dcache_page(*pgto);
+		kunmap_atomic(vto);
+
+		pgto_base += copy;
+		pgfrom_base += copy;
+
+	} while ((len -= copy) != 0);
+}
+
+static void
+_shift_data_left_tail(struct xdr_buf *buf, unsigned int pgto, size_t len)
+{
+	struct kvec *tail = buf->tail;
+
+	if (len > tail->iov_len)
+		len = tail->iov_len;
+
+	_copy_to_pages(buf->pages,
+		       buf->page_base + pgto,
+		       (char *)tail->iov_base,
+		       len);
+	tail->iov_len -= len;
+
+	if (tail->iov_len > 0)
+		memmove((char *)tail->iov_base,
+				tail->iov_base + len,
+				tail->iov_len);
+}
+
 /**
  * _shift_data_right_pages
  * @pages: vector of pages containing both the source and dest memory area.
@@ -1128,6 +1213,42 @@ unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len)
 }
 EXPORT_SYMBOL_GPL(xdr_read_pages);
 
+uint64_t xdr_align_data(struct xdr_stream *xdr, uint64_t offset, uint32_t length)
+{
+	struct xdr_buf *buf = xdr->buf;
+	unsigned int from, bytes;
+	unsigned int shift = 0;
+
+	if ((offset + length) < offset ||
+	    (offset + length) > buf->page_len)
+		length = buf->page_len - offset;
+
+	xdr_realign_pages(xdr);
+	from = xdr_page_pos(xdr);
+	bytes = xdr->nwords << 2;
+	if (length < bytes)
+		bytes = length;
+
+	/* Move page data to the left */
+	if (from > offset) {
+		shift = min_t(unsigned int, bytes, buf->page_len - from);
+		_shift_data_left_pages(buf->pages,
+				       buf->page_base + offset,
+				       buf->page_base + from,
+				       shift);
+		bytes -= shift;
+
+		/* Move tail data into the pages, if necessary */
+		if (bytes > 0)
+			_shift_data_left_tail(buf, offset + shift, bytes);
+	}
+
+	xdr->nwords -= XDR_QUADLEN(length);
+	xdr_set_page(xdr, from + length, PAGE_SIZE);
+	return length;
+}
+EXPORT_SYMBOL_GPL(xdr_align_data);
+
 uint64_t xdr_expand_hole(struct xdr_stream *xdr, uint64_t offset, uint64_t length)
 {
 	struct xdr_buf *buf = xdr->buf;
-- 
cgit v1.2.3


From 1c47fa6b31c2683f03bc2f9174902bb7dcd35d83 Mon Sep 17 00:00:00 2001
From: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Date: Sat, 3 Oct 2020 00:41:49 +0900
Subject: can: dev: add a helper function to calculate the duration of one bit

Rename macro CAN_CALC_SYNC_SEG to CAN_SYNC_SEG and make it available
through include/linux/can/dev.h

Add an helper function can_bit_time() which returns the duration (in
time quanta) of one CAN bit.

Rationale for this patch: the sync segment and the bit time are two
concepts which are defined in the CAN ISO standard. Device drivers for
CAN might need those.

Please refer to ISO 11898-1:2015, section 11.3.1.1 "Bit time" for
additional information.

Signed-off-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://lore.kernel.org/r/20201002154219.4887-6-mailhol.vincent@wanadoo.fr
[mkl: Let can_bit_time() return an unsinged int, make argument const]
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/dev.c   | 13 ++++++-------
 include/linux/can/dev.h | 15 +++++++++++++++
 2 files changed, 21 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index 3c40bba71d5b..b70ded3760f2 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -60,7 +60,6 @@ EXPORT_SYMBOL_GPL(can_len2dlc);
 
 #ifdef CONFIG_CAN_CALC_BITTIMING
 #define CAN_CALC_MAX_ERROR 50 /* in one-tenth of a percent */
-#define CAN_CALC_SYNC_SEG 1
 
 /* Bit-timing calculation derived from:
  *
@@ -86,8 +85,8 @@ can_update_sample_point(const struct can_bittiming_const *btc,
 	int i;
 
 	for (i = 0; i <= 1; i++) {
-		tseg2 = tseg + CAN_CALC_SYNC_SEG -
-			(sample_point_nominal * (tseg + CAN_CALC_SYNC_SEG)) /
+		tseg2 = tseg + CAN_SYNC_SEG -
+			(sample_point_nominal * (tseg + CAN_SYNC_SEG)) /
 			1000 - i;
 		tseg2 = clamp(tseg2, btc->tseg2_min, btc->tseg2_max);
 		tseg1 = tseg - tseg2;
@@ -96,8 +95,8 @@ can_update_sample_point(const struct can_bittiming_const *btc,
 			tseg2 = tseg - tseg1;
 		}
 
-		sample_point = 1000 * (tseg + CAN_CALC_SYNC_SEG - tseg2) /
-			(tseg + CAN_CALC_SYNC_SEG);
+		sample_point = 1000 * (tseg + CAN_SYNC_SEG - tseg2) /
+			(tseg + CAN_SYNC_SEG);
 		sample_point_error = abs(sample_point_nominal - sample_point);
 
 		if (sample_point <= sample_point_nominal &&
@@ -145,7 +144,7 @@ static int can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt,
 	/* tseg even = round down, odd = round up */
 	for (tseg = (btc->tseg1_max + btc->tseg2_max) * 2 + 1;
 	     tseg >= (btc->tseg1_min + btc->tseg2_min) * 2; tseg--) {
-		tsegall = CAN_CALC_SYNC_SEG + tseg / 2;
+		tsegall = CAN_SYNC_SEG + tseg / 2;
 
 		/* Compute all possible tseg choices (tseg=tseg1+tseg2) */
 		brp = priv->clock.freq / (tsegall * bt->bitrate) + tseg % 2;
@@ -223,7 +222,7 @@ static int can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt,
 
 	/* real bitrate */
 	bt->bitrate = priv->clock.freq /
-		(bt->brp * (CAN_CALC_SYNC_SEG + tseg1 + tseg2));
+		(bt->brp * (CAN_SYNC_SEG + tseg1 + tseg2));
 
 	return 0;
 }
diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h
index f8975d0b90bb..41ff31795320 100644
--- a/include/linux/can/dev.h
+++ b/include/linux/can/dev.h
@@ -82,6 +82,21 @@ struct can_priv {
 #endif
 };
 
+#define CAN_SYNC_SEG 1
+
+/*
+ * can_bit_time() - Duration of one bit
+ *
+ * Please refer to ISO 11898-1:2015, section 11.3.1.1 "Bit time" for
+ * additional information.
+ *
+ * Return: the number of time quanta in one bit.
+ */
+static inline unsigned int can_bit_time(const struct can_bittiming *bt)
+{
+	return CAN_SYNC_SEG + bt->prop_seg + bt->phase_seg1 + bt->phase_seg2;
+}
+
 /*
  * get_can_dlc(value) - helper macro to cast a given data length code (dlc)
  * to u8 and ensure the dlc value to be max. 8 bytes.
-- 
cgit v1.2.3


From 638eae9bc7eb1012d1e0f5a8fd4db46447f822e9 Mon Sep 17 00:00:00 2001
From: Vadim Pasternak <vadimp@nvidia.com>
Date: Wed, 23 Sep 2020 20:20:51 +0300
Subject: platform_data/mlxreg: Update module license

Update license to SPDX-License.

Signed-off-by: Vadim Pasternak <vadimp@nvidia.com>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20200923172053.26296-4-vadimp@nvidia.com
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 include/linux/platform_data/mlxreg.h | 32 ++------------------------------
 1 file changed, 2 insertions(+), 30 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h
index 1af9c01563f9..0a727d405a7a 100644
--- a/include/linux/platform_data/mlxreg.h
+++ b/include/linux/platform_data/mlxreg.h
@@ -1,34 +1,6 @@
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
 /*
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Vadim Pasternak <vadimp@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (C) 2017-2020 Mellanox Technologies Ltd.
  */
 
 #ifndef __LINUX_PLATFORM_DATA_MLXREG_H
-- 
cgit v1.2.3


From d2f3ab5b6b05f67817f3bd3f2fda5f0126e95a62 Mon Sep 17 00:00:00 2001
From: Vadim Pasternak <vadimp@nvidia.com>
Date: Wed, 23 Sep 2020 20:20:52 +0300
Subject: platform_data/mlxreg: Extend core platform structure

Add 'capability' field to structure 'mlxreg_core_platform_data'.
The purpose of this filed to indicate  the actual number of the
components within the particular group. Such components could be,
for example the number of the FAN drawers. Some systems are equipped
with FAN drawers with one tachometer inside, others with FAN drawers
with several tachometers inside.

Signed-off-by: Vadim Pasternak <vadimp@nvidia.com>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20200923172053.26296-5-vadimp@nvidia.com
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 include/linux/platform_data/mlxreg.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h
index 0a727d405a7a..101333fe2b8d 100644
--- a/include/linux/platform_data/mlxreg.h
+++ b/include/linux/platform_data/mlxreg.h
@@ -109,6 +109,7 @@ struct mlxreg_core_item {
  * @features: supported features of device;
  * @version: implementation version;
  * @identity: device identity name;
+ * @capability: device capability register;
  */
 struct mlxreg_core_platform_data {
 	struct mlxreg_core_data *data;
@@ -117,6 +118,7 @@ struct mlxreg_core_platform_data {
 	u32 features;
 	u32 version;
 	char identity[MLXREG_CORE_LABEL_MAX_SIZE];
+	u32 capability;
 };
 
 /**
-- 
cgit v1.2.3


From 9c37de297f6590937f95a28bec1b7ac68a38618f Mon Sep 17 00:00:00 2001
From: Mike Snitzer <snitzer@redhat.com>
Date: Wed, 7 Oct 2020 15:15:08 -0400
Subject: dm: remove special-casing of bio-based immutable singleton target on
 NVMe

Since commit 5a6c35f9af416 ("block: remove direct_make_request") there
is no benefit to DM special-casing NVMe. Remove all code used to
establish DM_TYPE_NVME_BIO_BASED.

Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/dm-table.c         | 32 ++-----------------------
 drivers/md/dm.c               | 55 ++++---------------------------------------
 include/linux/device-mapper.h |  1 -
 3 files changed, 7 insertions(+), 81 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 3ad22adf322d..ce543b761be7 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -804,8 +804,7 @@ EXPORT_SYMBOL(dm_consume_args);
 static bool __table_type_bio_based(enum dm_queue_mode table_type)
 {
 	return (table_type == DM_TYPE_BIO_BASED ||
-		table_type == DM_TYPE_DAX_BIO_BASED ||
-		table_type == DM_TYPE_NVME_BIO_BASED);
+		table_type == DM_TYPE_DAX_BIO_BASED);
 }
 
 static bool __table_type_request_based(enum dm_queue_mode table_type)
@@ -861,8 +860,6 @@ bool dm_table_supports_dax(struct dm_table *t,
 	return true;
 }
 
-static bool dm_table_does_not_support_partial_completion(struct dm_table *t);
-
 static int device_is_rq_stackable(struct dm_target *ti, struct dm_dev *dev,
 				  sector_t start, sector_t len, void *data)
 {
@@ -892,7 +889,6 @@ static int dm_table_determine_type(struct dm_table *t)
 			goto verify_bio_based;
 		}
 		BUG_ON(t->type == DM_TYPE_DAX_BIO_BASED);
-		BUG_ON(t->type == DM_TYPE_NVME_BIO_BASED);
 		goto verify_rq_based;
 	}
 
@@ -931,15 +927,6 @@ verify_bio_based:
 		if (dm_table_supports_dax(t, device_supports_dax, &page_size) ||
 		    (list_empty(devices) && live_md_type == DM_TYPE_DAX_BIO_BASED)) {
 			t->type = DM_TYPE_DAX_BIO_BASED;
-		} else {
-			/* Check if upgrading to NVMe bio-based is valid or required */
-			tgt = dm_table_get_immutable_target(t);
-			if (tgt && !tgt->max_io_len && dm_table_does_not_support_partial_completion(t)) {
-				t->type = DM_TYPE_NVME_BIO_BASED;
-				goto verify_rq_based; /* must be stacked directly on NVMe (blk-mq) */
-			} else if (list_empty(devices) && live_md_type == DM_TYPE_NVME_BIO_BASED) {
-				t->type = DM_TYPE_NVME_BIO_BASED;
-			}
 		}
 		return 0;
 	}
@@ -956,8 +943,7 @@ verify_rq_based:
 	 * (e.g. request completion process for partial completion.)
 	 */
 	if (t->num_targets > 1) {
-		DMERR("%s DM doesn't support multiple targets",
-		      t->type == DM_TYPE_NVME_BIO_BASED ? "nvme bio-based" : "request-based");
+		DMERR("request-based DM doesn't support multiple targets");
 		return -EINVAL;
 	}
 
@@ -1651,20 +1637,6 @@ static bool dm_table_all_devices_attribute(struct dm_table *t,
 	return true;
 }
 
-static int device_no_partial_completion(struct dm_target *ti, struct dm_dev *dev,
-					sector_t start, sector_t len, void *data)
-{
-	char b[BDEVNAME_SIZE];
-
-	/* For now, NVMe devices are the only devices of this class */
-	return (strncmp(bdevname(dev->bdev, b), "nvme", 4) == 0);
-}
-
-static bool dm_table_does_not_support_partial_completion(struct dm_table *t)
-{
-	return dm_table_all_devices_attribute(t, device_no_partial_completion);
-}
-
 static int device_not_write_same_capable(struct dm_target *ti, struct dm_dev *dev,
 					 sector_t start, sector_t len, void *data)
 {
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 32ac19645255..af1bab3a810e 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -975,7 +975,7 @@ static void clone_endio(struct bio *bio)
 	dm_endio_fn endio = tio->ti->type->end_io;
 	struct bio *orig_bio = io->orig_bio;
 
-	if (unlikely(error == BLK_STS_TARGET) && md->type != DM_TYPE_NVME_BIO_BASED) {
+	if (unlikely(error == BLK_STS_TARGET)) {
 		if (bio_op(bio) == REQ_OP_DISCARD &&
 		    !bio->bi_disk->queue->limits.max_discard_sectors)
 			disable_discard(md);
@@ -1626,45 +1626,6 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md,
 	return ret;
 }
 
-/*
- * Optimized variant of __split_and_process_bio that leverages the
- * fact that targets that use it do _not_ have a need to split bios.
- */
-static blk_qc_t __process_bio(struct mapped_device *md, struct dm_table *map,
-			      struct bio *bio)
-{
-	struct clone_info ci;
-	blk_qc_t ret = BLK_QC_T_NONE;
-	int error = 0;
-
-	init_clone_info(&ci, md, map, bio);
-
-	if (bio->bi_opf & REQ_PREFLUSH) {
-		error = __send_empty_flush(&ci);
-		/* dec_pending submits any data associated with flush */
-	} else {
-		struct dm_target_io *tio;
-		struct dm_target *ti = md->immutable_target;
-
-		if (WARN_ON_ONCE(!ti)) {
-			error = -EIO;
-			goto out;
-		}
-
-		ci.bio = bio;
-		ci.sector_count = bio_sectors(bio);
-		if (__process_abnormal_io(&ci, ti, &error))
-			goto out;
-
-		tio = alloc_tio(&ci, ti, 0, GFP_NOIO);
-		ret = __clone_and_map_simple_bio(&ci, tio, NULL);
-	}
-out:
-	/* drop the extra reference count */
-	dec_pending(ci.io, errno_to_blk_status(error));
-	return ret;
-}
-
 static blk_qc_t dm_submit_bio(struct bio *bio)
 {
 	struct mapped_device *md = bio->bi_disk->private_data;
@@ -1710,10 +1671,7 @@ static blk_qc_t dm_submit_bio(struct bio *bio)
 	if (is_abnormal_io(bio))
 		blk_queue_split(&bio);
 
-	if (dm_get_md_type(md) == DM_TYPE_NVME_BIO_BASED)
-		ret = __process_bio(md, map, bio);
-	else
-		ret = __split_and_process_bio(md, map, bio);
+	ret = __split_and_process_bio(md, map, bio);
 out:
 	dm_put_live_table(md, srcu_idx);
 	return ret;
@@ -2038,11 +1996,10 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
 	if (request_based)
 		dm_stop_queue(q);
 
-	if (request_based || md->type == DM_TYPE_NVME_BIO_BASED) {
+	if (request_based) {
 		/*
-		 * Leverage the fact that request-based DM targets and
-		 * NVMe bio based targets are immutable singletons
-		 * - used to optimize both __process_bio and dm_mq_queue_rq
+		 * Leverage the fact that request-based DM targets are
+		 * immutable singletons - used to optimize dm_mq_queue_rq.
 		 */
 		md->immutable_target = dm_table_get_immutable_target(t);
 	}
@@ -2164,7 +2121,6 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t)
 		break;
 	case DM_TYPE_BIO_BASED:
 	case DM_TYPE_DAX_BIO_BASED:
-	case DM_TYPE_NVME_BIO_BASED:
 		break;
 	case DM_TYPE_NONE:
 		WARN_ON_ONCE(true);
@@ -2922,7 +2878,6 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, enum dm_qu
 	switch (type) {
 	case DM_TYPE_BIO_BASED:
 	case DM_TYPE_DAX_BIO_BASED:
-	case DM_TYPE_NVME_BIO_BASED:
 		pool_size = max(dm_get_reserved_bio_based_ios(), min_pool_size);
 		front_pad = roundup(per_io_data_size, __alignof__(struct dm_target_io)) + offsetof(struct dm_target_io, clone);
 		io_front_pad = roundup(front_pad,  __alignof__(struct dm_io)) + offsetof(struct dm_io, tio);
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index d6f8d4ba8d48..61a66fb8ebb3 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -29,7 +29,6 @@ enum dm_queue_mode {
 	DM_TYPE_BIO_BASED	 = 1,
 	DM_TYPE_REQUEST_BASED	 = 2,
 	DM_TYPE_DAX_BIO_BASED	 = 3,
-	DM_TYPE_NVME_BIO_BASED	 = 4,
 };
 
 typedef enum { STATUSTYPE_INFO, STATUSTYPE_TABLE } status_type_t;
-- 
cgit v1.2.3


From 8dc4bd073663fa8aba2fae08b1c23ab41a2e97a2 Mon Sep 17 00:00:00 2001
From: Badhri Jagan Sridharan <badhri@google.com>
Date: Wed, 7 Oct 2020 23:15:47 -0700
Subject: usb: typec: tcpm: Add support for Sink Fast Role SWAP(FRS)

PD 3.0 spec defines a new mechanism for power role swap called
Fast role swap. This change enables TCPM to support FRS when
acting as sink.

Once the explicit contract is negotiated, sink port is
expected to query the source port for sink caps to
determine whether the source is FRS capable.
Bits 23 & 24 of fixed pdo of the sink caps from the source, when
set, indicates the current needed by the source when fast role
swap is in progress(Implicit contract phasae). 0 indicates that
the source does not support Fast Role Swap.

Upon receiving the FRS signal from the source,
TCPC(TCPM_FRS_EVENT) informs TCPM to start the Fast role swap sequence.

1. TCPM sends FRS PD message: FR_SWAP_SEND
2. If response is not received within the expiry of
   SenderResponseTimer, Error recovery is triggered.:
   FR_SWAP_SEND_TIMEOUT
3. Upon receipt of the accept message, TCPM waits for
   PSSourceOffTimer for PS_READY message from the partner:
   FR_SWAP_SNK_SRC_NEW_SINK_READY.

TCPC is expected to autonomously turn on vbus once the FRS
signal is received and vbus voltage falls below vsafe5v within
tSrcFrSwap. This is different from traditional power role swap
where the vbus sourcing is turned on by TCPM.

4. By this time, TCPC most likely would have started to
   source vbus, TCPM waits for tSrcFrSwap to see  if the
   lower level TCPC driver signals TCPM_SOURCING_VBUS event:
   FR_SWAP_SNK_SRC_SOURCE_VBUS_APPLIED.
5. When TCPC signals sourcing vbus, TCPM sends PS_READY msg and
   changes the CC pin from Rd to Rp. This is the end of fast
   role swap sequence and TCPM initiates the sequnce to negotiate
   explicit contract by transitioning into SRC_STARTUP after
   SwapSrcStart.

The code is written based on the sequence described in "Figure 8-107:
Dual-role Port in Sink to Source Fast Role Swap State Diagram" of
USB Power Delivery Specification Revision 3.0, Version 1.2.

Signed-off-by: Badhri Jagan Sridharan <badhri@google.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20201008061556.1402293-7-badhri@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/tcpm.c | 229 +++++++++++++++++++++++++++++++++++++++++-
 include/linux/usb/pd.h        |  19 ++--
 include/linux/usb/tcpm.h      |   8 +-
 3 files changed, 244 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 92806547f485..55535c4f66bf 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -106,6 +106,13 @@
 	S(VCONN_SWAP_TURN_ON_VCONN),		\
 	S(VCONN_SWAP_TURN_OFF_VCONN),		\
 						\
+	S(FR_SWAP_SEND),			\
+	S(FR_SWAP_SEND_TIMEOUT),		\
+	S(FR_SWAP_SNK_SRC_TRANSITION_TO_OFF),			\
+	S(FR_SWAP_SNK_SRC_NEW_SINK_READY),		\
+	S(FR_SWAP_SNK_SRC_SOURCE_VBUS_APPLIED),	\
+	S(FR_SWAP_CANCEL),			\
+						\
 	S(SNK_TRY),				\
 	S(SNK_TRY_WAIT),			\
 	S(SNK_TRY_WAIT_DEBOUNCE),               \
@@ -127,6 +134,9 @@
 	S(GET_PPS_STATUS_SEND),			\
 	S(GET_PPS_STATUS_SEND_TIMEOUT),		\
 						\
+	S(GET_SINK_CAP),			\
+	S(GET_SINK_CAP_TIMEOUT),		\
+						\
 	S(ERROR_RECOVERY),			\
 	S(PORT_RESET),				\
 	S(PORT_RESET_WAIT_OFF)
@@ -170,11 +180,25 @@ enum adev_actions {
 	ADEV_ATTENTION,
 };
 
+/*
+ * Initial current capability of the new source when vSafe5V is applied during PD3.0 Fast Role Swap.
+ * Based on "Table 6-14 Fixed Supply PDO - Sink" of "USB Power Delivery Specification Revision 3.0,
+ * Version 1.2"
+ */
+enum frs_typec_current {
+	FRS_NOT_SUPPORTED,
+	FRS_DEFAULT_POWER,
+	FRS_5V_1P5A,
+	FRS_5V_3A,
+};
+
 /* Events from low level driver */
 
 #define TCPM_CC_EVENT		BIT(0)
 #define TCPM_VBUS_EVENT		BIT(1)
 #define TCPM_RESET_EVENT	BIT(2)
+#define TCPM_FRS_EVENT		BIT(3)
+#define TCPM_SOURCING_VBUS	BIT(4)
 
 #define LOG_BUFFER_ENTRIES	1024
 #define LOG_BUFFER_ENTRY_SIZE	128
@@ -184,6 +208,8 @@ enum adev_actions {
 #define SVID_DISCOVERY_MAX	16
 #define ALTMODE_DISCOVERY_MAX	(SVID_DISCOVERY_MAX * MODE_DISCOVERY_MAX)
 
+#define GET_SINK_CAP_RETRY_MS	100
+
 struct pd_mode_data {
 	int svid_index;		/* current SVID index		*/
 	int nsvids;
@@ -261,6 +287,8 @@ struct tcpm_port {
 	struct kthread_work state_machine;
 	struct hrtimer vdm_state_machine_timer;
 	struct kthread_work vdm_state_machine;
+	struct hrtimer enable_frs_timer;
+	struct kthread_work enable_frs;
 	bool state_machine_running;
 
 	struct completion tx_complete;
@@ -335,6 +363,12 @@ struct tcpm_port {
 	/* port belongs to a self powered device */
 	bool self_powered;
 
+	/* FRS */
+	enum frs_typec_current frs_current;
+
+	/* Sink caps have been queried */
+	bool sink_cap_done;
+
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *dentry;
 	struct mutex logbuffer_lock;	/* log buffer access lock */
@@ -940,6 +974,16 @@ static void mod_vdm_delayed_work(struct tcpm_port *port, unsigned int delay_ms)
 	}
 }
 
+static void mod_enable_frs_delayed_work(struct tcpm_port *port, unsigned int delay_ms)
+{
+	if (delay_ms) {
+		hrtimer_start(&port->enable_frs_timer, ms_to_ktime(delay_ms), HRTIMER_MODE_REL);
+	} else {
+		hrtimer_cancel(&port->enable_frs_timer);
+		kthread_queue_work(port->wq, &port->enable_frs);
+	}
+}
+
 static void tcpm_set_state(struct tcpm_port *port, enum tcpm_state state,
 			   unsigned int delay_ms)
 {
@@ -1669,6 +1713,9 @@ static void tcpm_pd_data_request(struct tcpm_port *port,
 	unsigned int cnt = pd_header_cnt_le(msg->header);
 	unsigned int rev = pd_header_rev_le(msg->header);
 	unsigned int i;
+	enum frs_typec_current frs_current;
+	bool frs_enable;
+	int ret;
 
 	switch (type) {
 	case PD_DATA_SOURCE_CAP:
@@ -1738,7 +1785,21 @@ static void tcpm_pd_data_request(struct tcpm_port *port,
 		/* We don't do anything with this at the moment... */
 		for (i = 0; i < cnt; i++)
 			port->sink_caps[i] = le32_to_cpu(msg->payload[i]);
+
+		frs_current = (port->sink_caps[0] & PDO_FIXED_FRS_CURR_MASK) >>
+			PDO_FIXED_FRS_CURR_SHIFT;
+		frs_enable = frs_current && (frs_current <= port->frs_current);
+		tcpm_log(port,
+			 "Port partner FRS capable partner_frs_current:%u port_frs_current:%u enable:%c",
+			 frs_current, port->frs_current, frs_enable ? 'y' : 'n');
+		if (frs_enable) {
+			ret  = port->tcpc->enable_frs(port->tcpc, true);
+			tcpm_log(port, "Enable FRS %s, ret:%d\n", ret ? "fail" : "success", ret);
+		}
+
 		port->nr_sink_caps = cnt;
+		port->sink_cap_done = true;
+		tcpm_set_state(port, SNK_READY, 0);
 		break;
 	case PD_DATA_VENDOR_DEF:
 		tcpm_handle_vdm_request(port, msg->payload, cnt);
@@ -1833,6 +1894,9 @@ static void tcpm_pd_ctrl_request(struct tcpm_port *port,
 		case VCONN_SWAP_WAIT_FOR_VCONN:
 			tcpm_set_state(port, VCONN_SWAP_TURN_OFF_VCONN, 0);
 			break;
+		case FR_SWAP_SNK_SRC_TRANSITION_TO_OFF:
+			tcpm_set_state(port, FR_SWAP_SNK_SRC_NEW_SINK_READY, 0);
+			break;
 		default:
 			break;
 		}
@@ -1872,6 +1936,13 @@ static void tcpm_pd_ctrl_request(struct tcpm_port *port,
 					     -EAGAIN : -EOPNOTSUPP);
 			tcpm_set_state(port, VCONN_SWAP_CANCEL, 0);
 			break;
+		case FR_SWAP_SEND:
+			tcpm_set_state(port, FR_SWAP_CANCEL, 0);
+			break;
+		case GET_SINK_CAP:
+			port->sink_cap_done = true;
+			tcpm_set_state(port, ready_state(port), 0);
+			break;
 		default:
 			break;
 		}
@@ -1906,6 +1977,9 @@ static void tcpm_pd_ctrl_request(struct tcpm_port *port,
 		case VCONN_SWAP_SEND:
 			tcpm_set_state(port, VCONN_SWAP_START, 0);
 			break;
+		case FR_SWAP_SEND:
+			tcpm_set_state(port, FR_SWAP_SNK_SRC_TRANSITION_TO_OFF, 0);
+			break;
 		default:
 			break;
 		}
@@ -2806,6 +2880,10 @@ static void tcpm_reset_port(struct tcpm_port *port)
 	port->try_src_count = 0;
 	port->try_snk_count = 0;
 	port->usb_type = POWER_SUPPLY_USB_TYPE_C;
+	port->nr_sink_caps = 0;
+	port->sink_cap_done = false;
+	if (port->tcpc->enable_frs)
+		port->tcpc->enable_frs(port->tcpc, false);
 
 	power_supply_changed(port->psy);
 }
@@ -3356,10 +3434,9 @@ static void run_state_machine(struct tcpm_port *port)
 		tcpm_swap_complete(port, 0);
 		tcpm_typec_connect(port);
 		tcpm_check_send_discover(port);
+		mod_enable_frs_delayed_work(port, 0);
 		tcpm_pps_complete(port, port->pps_status);
-
 		power_supply_changed(port->psy);
-
 		break;
 
 	/* Accessory states */
@@ -3383,9 +3460,13 @@ static void run_state_machine(struct tcpm_port *port)
 		tcpm_set_state(port, HARD_RESET_START, 0);
 		break;
 	case HARD_RESET_START:
+		port->sink_cap_done = false;
+		if (port->tcpc->enable_frs)
+			port->tcpc->enable_frs(port->tcpc, false);
 		port->hard_reset_count++;
 		port->tcpc->set_pd_rx(port->tcpc, false);
 		tcpm_unregister_altmodes(port);
+		port->nr_sink_caps = 0;
 		port->send_discover = true;
 		if (port->pwr_role == TYPEC_SOURCE)
 			tcpm_set_state(port, SRC_HARD_RESET_VBUS_OFF,
@@ -3517,6 +3598,35 @@ static void run_state_machine(struct tcpm_port *port)
 		tcpm_set_state(port, ready_state(port), 0);
 		break;
 
+	case FR_SWAP_SEND:
+		if (tcpm_pd_send_control(port, PD_CTRL_FR_SWAP)) {
+			tcpm_set_state(port, ERROR_RECOVERY, 0);
+			break;
+		}
+		tcpm_set_state_cond(port, FR_SWAP_SEND_TIMEOUT, PD_T_SENDER_RESPONSE);
+		break;
+	case FR_SWAP_SEND_TIMEOUT:
+		tcpm_set_state(port, ERROR_RECOVERY, 0);
+		break;
+	case FR_SWAP_SNK_SRC_TRANSITION_TO_OFF:
+		tcpm_set_state(port, ERROR_RECOVERY, PD_T_PS_SOURCE_OFF);
+		break;
+	case FR_SWAP_SNK_SRC_NEW_SINK_READY:
+		if (port->vbus_source)
+			tcpm_set_state(port, FR_SWAP_SNK_SRC_SOURCE_VBUS_APPLIED, 0);
+		else
+			tcpm_set_state(port, ERROR_RECOVERY, PD_T_RECEIVER_RESPONSE);
+		break;
+	case FR_SWAP_SNK_SRC_SOURCE_VBUS_APPLIED:
+		tcpm_set_pwr_role(port, TYPEC_SOURCE);
+		if (tcpm_pd_send_control(port, PD_CTRL_PS_RDY)) {
+			tcpm_set_state(port, ERROR_RECOVERY, 0);
+			break;
+		}
+		tcpm_set_cc(port, tcpm_rp_cc(port));
+		tcpm_set_state(port, SRC_STARTUP, PD_T_SWAP_SRC_START);
+		break;
+
 	/* PR_Swap states */
 	case PR_SWAP_ACCEPT:
 		tcpm_pd_send_control(port, PD_CTRL_ACCEPT);
@@ -3640,6 +3750,12 @@ static void run_state_machine(struct tcpm_port *port)
 		else
 			tcpm_set_state(port, SNK_READY, 0);
 		break;
+	case FR_SWAP_CANCEL:
+		if (port->pwr_role == TYPEC_SOURCE)
+			tcpm_set_state(port, SRC_READY, 0);
+		else
+			tcpm_set_state(port, SNK_READY, 0);
+		break;
 
 	case BIST_RX:
 		switch (BDO_MODE_MASK(port->bist_request)) {
@@ -3674,6 +3790,14 @@ static void run_state_machine(struct tcpm_port *port)
 	case GET_PPS_STATUS_SEND_TIMEOUT:
 		tcpm_set_state(port, ready_state(port), 0);
 		break;
+	case GET_SINK_CAP:
+		tcpm_pd_send_control(port, PD_CTRL_GET_SINK_CAP);
+		tcpm_set_state(port, GET_SINK_CAP_TIMEOUT, PD_T_SENDER_RESPONSE);
+		break;
+	case GET_SINK_CAP_TIMEOUT:
+		port->sink_cap_done = true;
+		tcpm_set_state(port, ready_state(port), 0);
+		break;
 	case ERROR_RECOVERY:
 		tcpm_swap_complete(port, -EPROTO);
 		tcpm_pps_complete(port, -EPROTO);
@@ -3889,6 +4013,13 @@ static void _tcpm_cc_change(struct tcpm_port *port, enum typec_cc_status cc1,
 		 * Ignore it.
 		 */
 		break;
+	case FR_SWAP_SEND:
+	case FR_SWAP_SEND_TIMEOUT:
+	case FR_SWAP_SNK_SRC_TRANSITION_TO_OFF:
+	case FR_SWAP_SNK_SRC_NEW_SINK_READY:
+	case FR_SWAP_SNK_SRC_SOURCE_VBUS_APPLIED:
+		/* Do nothing, CC change expected */
+		break;
 
 	case PORT_RESET:
 	case PORT_RESET_WAIT_OFF:
@@ -3959,6 +4090,9 @@ static void _tcpm_pd_vbus_on(struct tcpm_port *port)
 	case SRC_TRY_DEBOUNCE:
 		/* Do nothing, waiting for sink detection */
 		break;
+	case FR_SWAP_SNK_SRC_NEW_SINK_READY:
+		tcpm_set_state(port, FR_SWAP_SNK_SRC_SOURCE_VBUS_APPLIED, 0);
+		break;
 
 	case PORT_RESET:
 	case PORT_RESET_WAIT_OFF:
@@ -4038,6 +4172,14 @@ static void _tcpm_pd_vbus_off(struct tcpm_port *port)
 		 */
 		break;
 
+	case FR_SWAP_SEND:
+	case FR_SWAP_SEND_TIMEOUT:
+	case FR_SWAP_SNK_SRC_TRANSITION_TO_OFF:
+	case FR_SWAP_SNK_SRC_NEW_SINK_READY:
+	case FR_SWAP_SNK_SRC_SOURCE_VBUS_APPLIED:
+		/* Do nothing, vbus drop expected */
+		break;
+
 	default:
 		if (port->pwr_role == TYPEC_SINK &&
 		    port->attached)
@@ -4092,6 +4234,25 @@ static void tcpm_pd_event_handler(struct kthread_work *work)
 			if (port->tcpc->get_cc(port->tcpc, &cc1, &cc2) == 0)
 				_tcpm_cc_change(port, cc1, cc2);
 		}
+		if (events & TCPM_FRS_EVENT) {
+			if (port->state == SNK_READY)
+				tcpm_set_state(port, FR_SWAP_SEND, 0);
+			else
+				tcpm_log(port, "Discarding FRS_SIGNAL! Not in sink ready");
+		}
+		if (events & TCPM_SOURCING_VBUS) {
+			tcpm_log(port, "sourcing vbus");
+			/*
+			 * In fast role swap case TCPC autonomously sources vbus. Set vbus_source
+			 * true as TCPM wouldn't have called tcpm_set_vbus.
+			 *
+			 * When vbus is sourced on the command on TCPM i.e. TCPM called
+			 * tcpm_set_vbus to source vbus, vbus_source would already be true.
+			 */
+			port->vbus_source = true;
+			_tcpm_pd_vbus_on(port);
+		}
+
 		spin_lock(&port->pd_event_lock);
 	}
 	spin_unlock(&port->pd_event_lock);
@@ -4125,6 +4286,50 @@ void tcpm_pd_hard_reset(struct tcpm_port *port)
 }
 EXPORT_SYMBOL_GPL(tcpm_pd_hard_reset);
 
+void tcpm_sink_frs(struct tcpm_port *port)
+{
+	spin_lock(&port->pd_event_lock);
+	port->pd_events = TCPM_FRS_EVENT;
+	spin_unlock(&port->pd_event_lock);
+	kthread_queue_work(port->wq, &port->event_work);
+}
+EXPORT_SYMBOL_GPL(tcpm_sink_frs);
+
+void tcpm_sourcing_vbus(struct tcpm_port *port)
+{
+	spin_lock(&port->pd_event_lock);
+	port->pd_events = TCPM_SOURCING_VBUS;
+	spin_unlock(&port->pd_event_lock);
+	kthread_queue_work(port->wq, &port->event_work);
+}
+EXPORT_SYMBOL_GPL(tcpm_sourcing_vbus);
+
+static void tcpm_enable_frs_work(struct kthread_work *work)
+{
+	struct tcpm_port *port = container_of(work, struct tcpm_port, enable_frs);
+
+	mutex_lock(&port->lock);
+	/* Not FRS capable */
+	if (!port->connected || port->port_type != TYPEC_PORT_DRP ||
+	    port->pwr_opmode != TYPEC_PWR_MODE_PD ||
+	    !port->tcpc->enable_frs ||
+	    /* Sink caps queried */
+	    port->sink_cap_done || port->negotiated_rev < PD_REV30)
+		goto unlock;
+
+	/* Send when the state machine is idle */
+	if (port->state != SNK_READY || port->vdm_state != VDM_STATE_DONE || port->send_discover)
+		goto resched;
+
+	tcpm_set_state(port, GET_SINK_CAP, 0);
+	port->sink_cap_done = true;
+
+resched:
+	mod_enable_frs_delayed_work(port, GET_SINK_CAP_RETRY_MS);
+unlock:
+	mutex_unlock(&port->lock);
+}
+
 static int tcpm_dr_set(struct typec_port *p, enum typec_data_role data)
 {
 	struct tcpm_port *port = typec_get_drvdata(p);
@@ -4532,7 +4737,7 @@ static int tcpm_fw_get_caps(struct tcpm_port *port,
 {
 	const char *cap_str;
 	int ret;
-	u32 mw;
+	u32 mw, frs_current;
 
 	if (!fwnode)
 		return -EINVAL;
@@ -4601,6 +4806,13 @@ sink:
 
 	port->self_powered = fwnode_property_read_bool(fwnode, "self-powered");
 
+	/* FRS can only be supported byb DRP ports */
+	if (port->port_type == TYPEC_PORT_DRP) {
+		ret = fwnode_property_read_u32(fwnode, "frs-typec-current", &frs_current);
+		if (ret >= 0 && frs_current <= FRS_5V_3A)
+			port->frs_current = frs_current;
+	}
+
 	return 0;
 }
 
@@ -4845,6 +5057,14 @@ static enum hrtimer_restart vdm_state_machine_timer_handler(struct hrtimer *time
 	return HRTIMER_NORESTART;
 }
 
+static enum hrtimer_restart enable_frs_timer_handler(struct hrtimer *timer)
+{
+	struct tcpm_port *port = container_of(timer, struct tcpm_port, enable_frs_timer);
+
+	kthread_queue_work(port->wq, &port->enable_frs);
+	return HRTIMER_NORESTART;
+}
+
 struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc)
 {
 	struct tcpm_port *port;
@@ -4874,10 +5094,13 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc)
 	kthread_init_work(&port->state_machine, tcpm_state_machine_work);
 	kthread_init_work(&port->vdm_state_machine, vdm_state_machine_work);
 	kthread_init_work(&port->event_work, tcpm_pd_event_handler);
+	kthread_init_work(&port->enable_frs, tcpm_enable_frs_work);
 	hrtimer_init(&port->state_machine_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	port->state_machine_timer.function = state_machine_timer_handler;
 	hrtimer_init(&port->vdm_state_machine_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	port->vdm_state_machine_timer.function = vdm_state_machine_timer_handler;
+	hrtimer_init(&port->enable_frs_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	port->enable_frs_timer.function = enable_frs_timer_handler;
 
 	spin_lock_init(&port->pd_event_lock);
 
diff --git a/include/linux/usb/pd.h b/include/linux/usb/pd.h
index f842e4589bd2..3a805e2ecbc9 100644
--- a/include/linux/usb/pd.h
+++ b/include/linux/usb/pd.h
@@ -219,14 +219,16 @@ enum pd_pdo_type {
 #define PDO_CURR_MASK		0x3ff
 #define PDO_PWR_MASK		0x3ff
 
-#define PDO_FIXED_DUAL_ROLE	BIT(29)	/* Power role swap supported */
-#define PDO_FIXED_SUSPEND	BIT(28) /* USB Suspend supported (Source) */
-#define PDO_FIXED_HIGHER_CAP	BIT(28) /* Requires more than vSafe5V (Sink) */
-#define PDO_FIXED_EXTPOWER	BIT(27) /* Externally powered */
-#define PDO_FIXED_USB_COMM	BIT(26) /* USB communications capable */
-#define PDO_FIXED_DATA_SWAP	BIT(25) /* Data role swap supported */
-#define PDO_FIXED_VOLT_SHIFT	10	/* 50mV units */
-#define PDO_FIXED_CURR_SHIFT	0	/* 10mA units */
+#define PDO_FIXED_DUAL_ROLE		BIT(29)	/* Power role swap supported */
+#define PDO_FIXED_SUSPEND		BIT(28) /* USB Suspend supported (Source) */
+#define PDO_FIXED_HIGHER_CAP		BIT(28) /* Requires more than vSafe5V (Sink) */
+#define PDO_FIXED_EXTPOWER		BIT(27) /* Externally powered */
+#define PDO_FIXED_USB_COMM		BIT(26) /* USB communications capable */
+#define PDO_FIXED_DATA_SWAP		BIT(25) /* Data role swap supported */
+#define PDO_FIXED_FRS_CURR_MASK		(BIT(24) | BIT(23)) /* FR_Swap Current (Sink) */
+#define PDO_FIXED_FRS_CURR_SHIFT	23
+#define PDO_FIXED_VOLT_SHIFT		10	/* 50mV units */
+#define PDO_FIXED_CURR_SHIFT		0	/* 10mA units */
 
 #define PDO_FIXED_VOLT(mv)	((((mv) / 50) & PDO_VOLT_MASK) << PDO_FIXED_VOLT_SHIFT)
 #define PDO_FIXED_CURR(ma)	((((ma) / 10) & PDO_CURR_MASK) << PDO_FIXED_CURR_SHIFT)
@@ -454,6 +456,7 @@ static inline unsigned int rdo_max_power(u32 rdo)
 #define PD_T_DB_DETECT		10000	/* 10 - 15 seconds */
 #define PD_T_SEND_SOURCE_CAP	150	/* 100 - 200 ms */
 #define PD_T_SENDER_RESPONSE	60	/* 24 - 30 ms, relaxed */
+#define PD_T_RECEIVER_RESPONSE	15	/* 15ms max */
 #define PD_T_SOURCE_ACTIVITY	45
 #define PD_T_SINK_ACTIVITY	135
 #define PD_T_SINK_WAIT_CAP	240
diff --git a/include/linux/usb/tcpm.h b/include/linux/usb/tcpm.h
index 89f58760cf48..09762d26fa0c 100644
--- a/include/linux/usb/tcpm.h
+++ b/include/linux/usb/tcpm.h
@@ -78,8 +78,11 @@ enum tcpm_transmit_type {
  *		automatically if a connection is established.
  * @try_role:	Optional; called to set a preferred role
  * @pd_transmit:Called to transmit PD message
- * @mux:	Pointer to multiplexer data
  * @set_bist_data: Turn on/off bist data mode for compliance testing
+ * @enable_frs:
+ *		Optional; Called to enable/disable PD 3.0 fast role swap.
+ *		Enabling frs is accessory dependent as not all PD3.0
+ *		accessories support fast role swap.
  */
 struct tcpc_dev {
 	struct fwnode_handle *fwnode;
@@ -105,6 +108,7 @@ struct tcpc_dev {
 	int (*pd_transmit)(struct tcpc_dev *dev, enum tcpm_transmit_type type,
 			   const struct pd_message *msg);
 	int (*set_bist_data)(struct tcpc_dev *dev, bool on);
+	int (*enable_frs)(struct tcpc_dev *dev, bool enable);
 };
 
 struct tcpm_port;
@@ -114,6 +118,8 @@ void tcpm_unregister_port(struct tcpm_port *port);
 
 void tcpm_vbus_change(struct tcpm_port *port);
 void tcpm_cc_change(struct tcpm_port *port);
+void tcpm_sink_frs(struct tcpm_port *port);
+void tcpm_sourcing_vbus(struct tcpm_port *port);
 void tcpm_pd_receive(struct tcpm_port *port,
 		     const struct pd_message *msg);
 void tcpm_pd_transmit_complete(struct tcpm_port *port,
-- 
cgit v1.2.3


From 8446466c9dd645da4c1848f35ffd0fc1df3524ee Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 6 Aug 2020 10:07:24 -0400
Subject: XArray: Fix xas_for_each_conflict documentation

At one point, xas_for_each_conflict() was going to work this way,
and I forgot to update the documentation when I changed my mind.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 include/linux/xarray.h | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index b4d70e7568b2..6b336098fca7 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -1714,13 +1714,12 @@ enum {
  * @xas: XArray operation state.
  * @entry: Entry retrieved from the array.
  *
- * The loop body will be executed for each entry in the XArray that lies
- * within the range specified by @xas.  If the loop completes successfully,
- * any entries that lie in this range will be replaced by @entry.  The caller
- * may break out of the loop; if they do so, the contents of the XArray will
- * be unchanged.  The operation may fail due to an out of memory condition.
- * The caller may also call xa_set_err() to exit the loop while setting an
- * error to record the reason.
+ * The loop body will be executed for each entry in the XArray that
+ * lies within the range specified by @xas.  If the loop terminates
+ * normally, @entry will be %NULL.  The user may break out of the loop,
+ * which will leave @entry set to the conflicting entry.  The caller
+ * may also call xa_set_err() to exit the loop while setting an error
+ * to record the reason.
  */
 #define xas_for_each_conflict(xas, entry) \
 	while ((entry = xas_find_conflict(xas)))
-- 
cgit v1.2.3


From a20b7053b5c47cd7de23288238ea4d23502f300a Mon Sep 17 00:00:00 2001
From: Ionela Voinescu <ionela.voinescu@arm.com>
Date: Thu, 24 Sep 2020 13:30:15 +0100
Subject: cpufreq,arm,arm64: restructure definitions of arch_set_freq_scale()

Compared to other arch_* functions, arch_set_freq_scale() has an atypical
weak definition that can be replaced by a strong architecture specific
implementation.

The more typical support for architectural functions involves defining
an empty stub in a header file if the symbol is not already defined in
architecture code. Some examples involve:
 - #define arch_scale_freq_capacity	topology_get_freq_scale
 - #define arch_scale_freq_invariant	topology_scale_freq_invariant
 - #define arch_scale_cpu_capacity	topology_get_cpu_scale
 - #define arch_update_cpu_topology	topology_update_cpu_topology
 - #define arch_scale_thermal_pressure	topology_get_thermal_pressure
 - #define arch_set_thermal_pressure	topology_set_thermal_pressure

Bring arch_set_freq_scale() in line with these functions by renaming it to
topology_set_freq_scale() in the arch topology driver, and by defining the
arch_set_freq_scale symbol to point to the new function for arm and arm64.

While there are other users of the arch_topology driver, this patch defines
arch_set_freq_scale for arm and arm64 only, due to their existing
definitions of arch_scale_freq_capacity. This is the getter function of the
frequency invariance scale factor and without a getter function, the
setter function - arch_set_freq_scale() has not purpose.

Signed-off-by: Ionela Voinescu <ionela.voinescu@arm.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Sudeep Holla <sudeep.holla@arm.com> (BL_SWITCHER and topology parts)
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 arch/arm/include/asm/topology.h   |  1 +
 arch/arm64/include/asm/topology.h |  1 +
 drivers/base/arch_topology.c      |  4 ++--
 drivers/cpufreq/cpufreq.c         |  7 -------
 include/linux/arch_topology.h     |  2 ++
 include/linux/cpufreq.h           | 11 ++++++++---
 6 files changed, 14 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
index 9219e67befbe..e5e3d5ce4d55 100644
--- a/arch/arm/include/asm/topology.h
+++ b/arch/arm/include/asm/topology.h
@@ -8,6 +8,7 @@
 #include <linux/arch_topology.h>
 
 /* Replace task scheduler's default frequency-invariant accounting */
+#define arch_set_freq_scale topology_set_freq_scale
 #define arch_scale_freq_capacity topology_get_freq_scale
 #define arch_scale_freq_invariant topology_scale_freq_invariant
 
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
index 7cb519473fbd..11a465243f66 100644
--- a/arch/arm64/include/asm/topology.h
+++ b/arch/arm64/include/asm/topology.h
@@ -26,6 +26,7 @@ void topology_scale_freq_tick(void);
 #endif /* CONFIG_ARM64_AMU_EXTN */
 
 /* Replace task scheduler's default frequency-invariant accounting */
+#define arch_set_freq_scale topology_set_freq_scale
 #define arch_scale_freq_capacity topology_get_freq_scale
 #define arch_scale_freq_invariant topology_scale_freq_invariant
 
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index 89cae168b076..c1a9e2fb634e 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -33,8 +33,8 @@ __weak bool arch_freq_counters_available(const struct cpumask *cpus)
 }
 DEFINE_PER_CPU(unsigned long, freq_scale) = SCHED_CAPACITY_SCALE;
 
-void arch_set_freq_scale(const struct cpumask *cpus, unsigned long cur_freq,
-			 unsigned long max_freq)
+void topology_set_freq_scale(const struct cpumask *cpus, unsigned long cur_freq,
+			     unsigned long max_freq)
 {
 	unsigned long scale;
 	int i;
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index db00693a586a..1877f5e2e5b0 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -160,13 +160,6 @@ u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy)
 }
 EXPORT_SYMBOL_GPL(get_cpu_idle_time);
 
-__weak void arch_set_freq_scale(const struct cpumask *cpus,
-				unsigned long cur_freq,
-				unsigned long max_freq)
-{
-}
-EXPORT_SYMBOL_GPL(arch_set_freq_scale);
-
 /*
  * This is a generic cpufreq init() routine which can be used by cpufreq
  * drivers of SMP systems. It will do following:
diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h
index 083df331a3c9..0f6cd6b73a61 100644
--- a/include/linux/arch_topology.h
+++ b/include/linux/arch_topology.h
@@ -30,6 +30,8 @@ static inline unsigned long topology_get_freq_scale(int cpu)
 	return per_cpu(freq_scale, cpu);
 }
 
+void topology_set_freq_scale(const struct cpumask *cpus, unsigned long cur_freq,
+			     unsigned long max_freq);
 bool topology_scale_freq_invariant(void);
 
 bool arch_freq_counters_available(const struct cpumask *cpus);
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 9f779fbdbe7b..fa37b1c66443 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -1011,9 +1011,14 @@ static inline void sched_cpufreq_governor_change(struct cpufreq_policy *policy,
 extern void arch_freq_prepare_all(void);
 extern unsigned int arch_freq_get_on_cpu(int cpu);
 
-extern void arch_set_freq_scale(const struct cpumask *cpus,
-				unsigned long cur_freq,
-				unsigned long max_freq);
+#ifndef arch_set_freq_scale
+static __always_inline
+void arch_set_freq_scale(const struct cpumask *cpus,
+			 unsigned long cur_freq,
+			 unsigned long max_freq)
+{
+}
+#endif
 
 /* the following are really really optional */
 extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs;
-- 
cgit v1.2.3


From 2ef0342530b0f487a65b5f6c94c85dce5f9b53b5 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 8 Oct 2020 08:53:03 +0200
Subject: PNP: remove the now unused pnp_find_card() function

All user of the pnp_find_card() compat wrapper are gone, so remove
the function as well.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/admin-guide/pnp.rst |  4 ----
 drivers/pnp/isapnp/compat.c       | 23 -----------------------
 include/linux/isapnp.h            |  6 ------
 3 files changed, 33 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/admin-guide/pnp.rst b/Documentation/admin-guide/pnp.rst
index bab2d10631f0..3eda08191d13 100644
--- a/Documentation/admin-guide/pnp.rst
+++ b/Documentation/admin-guide/pnp.rst
@@ -281,10 +281,6 @@ ISAPNP drivers.  They should serve as a temporary solution only.
 
 They are as follows::
 
-	struct pnp_card *pnp_find_card(unsigned short vendor,
-				       unsigned short device,
-				       struct pnp_card *from)
-
 	struct pnp_dev *pnp_find_dev(struct pnp_card *card,
 				     unsigned short vendor,
 				     unsigned short function,
diff --git a/drivers/pnp/isapnp/compat.c b/drivers/pnp/isapnp/compat.c
index 6c845b628316..035e95092489 100644
--- a/drivers/pnp/isapnp/compat.c
+++ b/drivers/pnp/isapnp/compat.c
@@ -21,28 +21,6 @@ static void pnp_convert_id(char *buf, unsigned short vendor,
 		(device >> 12) & 0x0f, (device >> 8) & 0x0f);
 }
 
-struct pnp_card *pnp_find_card(unsigned short vendor, unsigned short device,
-			       struct pnp_card *from)
-{
-	char id[8];
-	char any[8];
-	struct list_head *list;
-
-	pnp_convert_id(id, vendor, device);
-	pnp_convert_id(any, ISAPNP_ANY_ID, ISAPNP_ANY_ID);
-
-	list = from ? from->global_list.next : pnp_cards.next;
-
-	while (list != &pnp_cards) {
-		struct pnp_card *card = global_to_pnp_card(list);
-
-		if (compare_pnp_id(card->id, id) || (memcmp(id, any, 7) == 0))
-			return card;
-		list = list->next;
-	}
-	return NULL;
-}
-
 struct pnp_dev *pnp_find_dev(struct pnp_card *card, unsigned short vendor,
 			     unsigned short function, struct pnp_dev *from)
 {
@@ -86,5 +64,4 @@ struct pnp_dev *pnp_find_dev(struct pnp_card *card, unsigned short vendor,
 	return NULL;
 }
 
-EXPORT_SYMBOL(pnp_find_card);
 EXPORT_SYMBOL(pnp_find_dev);
diff --git a/include/linux/isapnp.h b/include/linux/isapnp.h
index 11edb2109a68..dba18c95844b 100644
--- a/include/linux/isapnp.h
+++ b/include/linux/isapnp.h
@@ -75,9 +75,6 @@ static inline int isapnp_proc_done(void) { return 0; }
 #endif
 
 /* compat */
-struct pnp_card *pnp_find_card(unsigned short vendor,
-			       unsigned short device,
-			       struct pnp_card *from);
 struct pnp_dev *pnp_find_dev(struct pnp_card *card,
 			     unsigned short vendor,
 			     unsigned short function,
@@ -92,9 +89,6 @@ static inline int isapnp_cfg_end(void) { return -ENODEV; }
 static inline unsigned char isapnp_read_byte(unsigned char idx) { return 0xff; }
 static inline void isapnp_write_byte(unsigned char idx, unsigned char val) { ; }
 
-static inline struct pnp_card *pnp_find_card(unsigned short vendor,
-					     unsigned short device,
-					     struct pnp_card *from) { return NULL; }
 static inline struct pnp_dev *pnp_find_dev(struct pnp_card *card,
 					   unsigned short vendor,
 					   unsigned short function,
-- 
cgit v1.2.3


From 02dae28f0b542969e44cbc1e14ffc9944cd2975c Mon Sep 17 00:00:00 2001
From: Wei Yang <richard.weiyang@linux.alibaba.com>
Date: Mon, 31 Aug 2020 11:11:01 +0800
Subject: ftrace: Simplify the dyn_ftrace->flags macro

All the three macro are defined to be used for ftrace_rec_count(). This
can be achieved by (flags & FTRACE_REF_MAX) directly.

Since no other places would use those macros, remove them for clarity.

Also it fixes a typo in the comment.

Link: https://lkml.kernel.org/r/20200831031104.23322-4-richard.weiyang@linux.alibaba.com

Signed-off-by: Wei Yang <richard.weiyang@linux.alibaba.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/ftrace.h | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index e5c2d5cc6e6a..b1f56e3410dc 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -432,7 +432,7 @@ bool is_ftrace_trampoline(unsigned long addr);
  *  DIRECT   - there is a direct function to call
  *
  * When a new ftrace_ops is registered and wants a function to save
- * pt_regs, the rec->flag REGS is set. When the function has been
+ * pt_regs, the rec->flags REGS is set. When the function has been
  * set up to save regs, the REG_EN flag is set. Once a function
  * starts saving regs it will do so until all ftrace_ops are removed
  * from tracing that function.
@@ -450,12 +450,9 @@ enum {
 };
 
 #define FTRACE_REF_MAX_SHIFT	23
-#define FTRACE_FL_BITS		9
-#define FTRACE_FL_MASKED_BITS	((1UL << FTRACE_FL_BITS) - 1)
-#define FTRACE_FL_MASK		(FTRACE_FL_MASKED_BITS << FTRACE_REF_MAX_SHIFT)
 #define FTRACE_REF_MAX		((1UL << FTRACE_REF_MAX_SHIFT) - 1)
 
-#define ftrace_rec_count(rec)	((rec)->flags & ~FTRACE_FL_MASK)
+#define ftrace_rec_count(rec)	((rec)->flags & FTRACE_REF_MAX)
 
 struct dyn_ftrace {
 	unsigned long		ip; /* address of mcount call-site */
-- 
cgit v1.2.3


From 40dc4a42b97ef5a52ef34a73093a7992faaab15e Mon Sep 17 00:00:00 2001
From: Wei Yang <richard.weiyang@linux.alibaba.com>
Date: Mon, 31 Aug 2020 11:11:04 +0800
Subject: ftrace: ftrace_global_list is renamed to ftrace_ops_list

Fix the comment to comply with the code.

Link: https://lkml.kernel.org/r/20200831031104.23322-7-richard.weiyang@linux.alibaba.com

Signed-off-by: Wei Yang <richard.weiyang@linux.alibaba.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/ftrace.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index b1f56e3410dc..1bd3a0356ae4 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -217,11 +217,11 @@ extern struct ftrace_ops __rcu *ftrace_ops_list;
 extern struct ftrace_ops ftrace_list_end;
 
 /*
- * Traverse the ftrace_global_list, invoking all entries.  The reason that we
+ * Traverse the ftrace_ops_list, invoking all entries.  The reason that we
  * can use rcu_dereference_raw_check() is that elements removed from this list
  * are simply leaked, so there is no need to interact with a grace-period
  * mechanism.  The rcu_dereference_raw_check() calls are needed to handle
- * concurrent insertions into the ftrace_global_list.
+ * concurrent insertions into the ftrace_ops_list.
  *
  * Silly Alpha and silly pointer-speculation compiler optimizations!
  */
-- 
cgit v1.2.3


From 2bb8945bcc1a768f2bc402a16c9610bba8d5187d Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 30 Sep 2020 11:49:37 +0200
Subject: lockdep: Fix usage_traceoverflow

Basically print_lock_class_header()'s for loop is out of sync with the
the size of of ->usage_traces[].

Also clean things up a bit while at it, to avoid such mishaps in the future.

Fixes: 23870f122768 ("locking/lockdep: Fix "USED" <- "IN-NMI" inversions")
Reported-by: Qian Cai <cai@redhat.com>
Debugged-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Qian Cai <cai@redhat.com>
Link: https://lkml.kernel.org/r/20200930094937.GE2651@hirez.programming.kicks-ass.net
---
 include/linux/lockdep_types.h      |  8 ++++++--
 kernel/locking/lockdep.c           | 32 +++++++++++++++-----------------
 kernel/locking/lockdep_internals.h |  7 +++++--
 3 files changed, 26 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h
index bb35b449f533..9a1fd49df17f 100644
--- a/include/linux/lockdep_types.h
+++ b/include/linux/lockdep_types.h
@@ -35,8 +35,12 @@ enum lockdep_wait_type {
 /*
  * We'd rather not expose kernel/lockdep_states.h this wide, but we do need
  * the total number of states... :-(
+ *
+ * XXX_LOCK_USAGE_STATES is the number of lines in lockdep_states.h, for each
+ * of those we generates 4 states, Additionally we report on USED and USED_READ.
  */
-#define XXX_LOCK_USAGE_STATES		(1+2*4)
+#define XXX_LOCK_USAGE_STATES		2
+#define LOCK_TRACE_STATES		(XXX_LOCK_USAGE_STATES*4 + 2)
 
 /*
  * NR_LOCKDEP_CACHING_CLASSES ... Number of classes
@@ -106,7 +110,7 @@ struct lock_class {
 	 * IRQ/softirq usage tracking bits:
 	 */
 	unsigned long			usage_mask;
-	const struct lock_trace		*usage_traces[XXX_LOCK_USAGE_STATES];
+	const struct lock_trace		*usage_traces[LOCK_TRACE_STATES];
 
 	/*
 	 * Generation counter, when doing certain classes of graph walking,
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 2facbbd146ec..a430fbb01eb1 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -585,6 +585,8 @@ static const char *usage_str[] =
 #include "lockdep_states.h"
 #undef LOCKDEP_STATE
 	[LOCK_USED] = "INITIAL USE",
+	[LOCK_USED_READ] = "INITIAL READ USE",
+	/* abused as string storage for verify_lock_unused() */
 	[LOCK_USAGE_STATES] = "IN-NMI",
 };
 #endif
@@ -1939,7 +1941,7 @@ static void print_lock_class_header(struct lock_class *class, int depth)
 #endif
 	printk(KERN_CONT " {\n");
 
-	for (bit = 0; bit < LOCK_USAGE_STATES; bit++) {
+	for (bit = 0; bit < LOCK_TRACE_STATES; bit++) {
 		if (class->usage_mask & (1 << bit)) {
 			int len = depth;
 
@@ -3969,7 +3971,7 @@ static int separate_irq_context(struct task_struct *curr,
 static int mark_lock(struct task_struct *curr, struct held_lock *this,
 			     enum lock_usage_bit new_bit)
 {
-	unsigned int old_mask, new_mask, ret = 1;
+	unsigned int new_mask, ret = 1;
 
 	if (new_bit >= LOCK_USAGE_STATES) {
 		DEBUG_LOCKS_WARN_ON(1);
@@ -3996,30 +3998,26 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
 	if (unlikely(hlock_class(this)->usage_mask & new_mask))
 		goto unlock;
 
-	old_mask = hlock_class(this)->usage_mask;
 	hlock_class(this)->usage_mask |= new_mask;
 
-	/*
-	 * Save one usage_traces[] entry and map both LOCK_USED and
-	 * LOCK_USED_READ onto the same entry.
-	 */
-	if (new_bit == LOCK_USED || new_bit == LOCK_USED_READ) {
-		if (old_mask & (LOCKF_USED | LOCKF_USED_READ))
-			goto unlock;
-		new_bit = LOCK_USED;
+	if (new_bit < LOCK_TRACE_STATES) {
+		if (!(hlock_class(this)->usage_traces[new_bit] = save_trace()))
+			return 0;
 	}
 
-	if (!(hlock_class(this)->usage_traces[new_bit] = save_trace()))
-		return 0;
-
 	switch (new_bit) {
+	case 0 ... LOCK_USED-1:
+		ret = mark_lock_irq(curr, this, new_bit);
+		if (!ret)
+			return 0;
+		break;
+
 	case LOCK_USED:
 		debug_atomic_dec(nr_unused_locks);
 		break;
+
 	default:
-		ret = mark_lock_irq(curr, this, new_bit);
-		if (!ret)
-			return 0;
+		break;
 	}
 
 unlock:
diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h
index b0be1560ed17..de49f9e1c11b 100644
--- a/kernel/locking/lockdep_internals.h
+++ b/kernel/locking/lockdep_internals.h
@@ -20,9 +20,12 @@ enum lock_usage_bit {
 #undef LOCKDEP_STATE
 	LOCK_USED,
 	LOCK_USED_READ,
-	LOCK_USAGE_STATES
+	LOCK_USAGE_STATES,
 };
 
+/* states after LOCK_USED_READ are not traced and printed */
+static_assert(LOCK_TRACE_STATES == LOCK_USAGE_STATES);
+
 #define LOCK_USAGE_READ_MASK 1
 #define LOCK_USAGE_DIR_MASK  2
 #define LOCK_USAGE_STATE_MASK (~(LOCK_USAGE_READ_MASK | LOCK_USAGE_DIR_MASK))
@@ -121,7 +124,7 @@ static const unsigned long LOCKF_USED_IN_IRQ_READ =
 extern struct list_head all_lock_classes;
 extern struct lock_chain lock_chains[];
 
-#define LOCK_USAGE_CHARS (1+LOCK_USAGE_STATES/2)
+#define LOCK_USAGE_CHARS (2*XXX_LOCK_USAGE_STATES + 1)
 
 extern void get_usage_chars(struct lock_class *class,
 			    char usage[LOCK_USAGE_CHARS]);
-- 
cgit v1.2.3


From 4d004099a668c41522242aa146a38cc4eb59cb1e Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 2 Oct 2020 11:04:21 +0200
Subject: lockdep: Fix lockdep recursion

Steve reported that lockdep_assert*irq*(), when nested inside lockdep
itself, will trigger a false-positive.

One example is the stack-trace code, as called from inside lockdep,
triggering tracing, which in turn calls RCU, which then uses
lockdep_assert_irqs_disabled().

Fixes: a21ee6055c30 ("lockdep: Change hardirq{s_enabled,_context} to per-cpu variables")
Reported-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/lockdep.h  | 13 ++++---
 kernel/locking/lockdep.c | 99 +++++++++++++++++++++++++++++-------------------
 2 files changed, 67 insertions(+), 45 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 6a584b3e5c74..b1227be47496 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -534,6 +534,7 @@ do {									\
 
 DECLARE_PER_CPU(int, hardirqs_enabled);
 DECLARE_PER_CPU(int, hardirq_context);
+DECLARE_PER_CPU(unsigned int, lockdep_recursion);
 
 /*
  * The below lockdep_assert_*() macros use raw_cpu_read() to access the above
@@ -543,25 +544,27 @@ DECLARE_PER_CPU(int, hardirq_context);
  * read the value from our previous CPU.
  */
 
+#define __lockdep_enabled	(debug_locks && !raw_cpu_read(lockdep_recursion))
+
 #define lockdep_assert_irqs_enabled()					\
 do {									\
-	WARN_ON_ONCE(debug_locks && !raw_cpu_read(hardirqs_enabled));	\
+	WARN_ON_ONCE(__lockdep_enabled && !raw_cpu_read(hardirqs_enabled)); \
 } while (0)
 
 #define lockdep_assert_irqs_disabled()					\
 do {									\
-	WARN_ON_ONCE(debug_locks && raw_cpu_read(hardirqs_enabled));	\
+	WARN_ON_ONCE(__lockdep_enabled && raw_cpu_read(hardirqs_enabled)); \
 } while (0)
 
 #define lockdep_assert_in_irq()						\
 do {									\
-	WARN_ON_ONCE(debug_locks && !raw_cpu_read(hardirq_context));	\
+	WARN_ON_ONCE(__lockdep_enabled && !raw_cpu_read(hardirq_context)); \
 } while (0)
 
 #define lockdep_assert_preemption_enabled()				\
 do {									\
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT)	&&		\
-		     debug_locks			&&		\
+		     __lockdep_enabled			&&		\
 		     (preempt_count() != 0		||		\
 		      !raw_cpu_read(hardirqs_enabled)));		\
 } while (0)
@@ -569,7 +572,7 @@ do {									\
 #define lockdep_assert_preemption_disabled()				\
 do {									\
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT)	&&		\
-		     debug_locks			&&		\
+		     __lockdep_enabled			&&		\
 		     (preempt_count() == 0		&&		\
 		      raw_cpu_read(hardirqs_enabled)));			\
 } while (0)
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index a430fbb01eb1..85d15f0362dc 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -76,6 +76,23 @@ module_param(lock_stat, int, 0644);
 #define lock_stat 0
 #endif
 
+DEFINE_PER_CPU(unsigned int, lockdep_recursion);
+EXPORT_PER_CPU_SYMBOL_GPL(lockdep_recursion);
+
+static inline bool lockdep_enabled(void)
+{
+	if (!debug_locks)
+		return false;
+
+	if (raw_cpu_read(lockdep_recursion))
+		return false;
+
+	if (current->lockdep_recursion)
+		return false;
+
+	return true;
+}
+
 /*
  * lockdep_lock: protects the lockdep graph, the hashes and the
  *               class/list/hash allocators.
@@ -93,7 +110,7 @@ static inline void lockdep_lock(void)
 
 	arch_spin_lock(&__lock);
 	__owner = current;
-	current->lockdep_recursion++;
+	__this_cpu_inc(lockdep_recursion);
 }
 
 static inline void lockdep_unlock(void)
@@ -101,7 +118,7 @@ static inline void lockdep_unlock(void)
 	if (debug_locks && DEBUG_LOCKS_WARN_ON(__owner != current))
 		return;
 
-	current->lockdep_recursion--;
+	__this_cpu_dec(lockdep_recursion);
 	__owner = NULL;
 	arch_spin_unlock(&__lock);
 }
@@ -393,10 +410,15 @@ void lockdep_init_task(struct task_struct *task)
 	task->lockdep_recursion = 0;
 }
 
+static __always_inline void lockdep_recursion_inc(void)
+{
+	__this_cpu_inc(lockdep_recursion);
+}
+
 static __always_inline void lockdep_recursion_finish(void)
 {
-	if (WARN_ON_ONCE((--current->lockdep_recursion) & LOCKDEP_RECURSION_MASK))
-		current->lockdep_recursion = 0;
+	if (WARN_ON_ONCE(__this_cpu_dec_return(lockdep_recursion)))
+		__this_cpu_write(lockdep_recursion, 0);
 }
 
 void lockdep_set_selftest_task(struct task_struct *task)
@@ -3659,7 +3681,7 @@ void lockdep_hardirqs_on_prepare(unsigned long ip)
 	if (unlikely(in_nmi()))
 		return;
 
-	if (unlikely(current->lockdep_recursion & LOCKDEP_RECURSION_MASK))
+	if (unlikely(__this_cpu_read(lockdep_recursion)))
 		return;
 
 	if (unlikely(lockdep_hardirqs_enabled())) {
@@ -3695,7 +3717,7 @@ void lockdep_hardirqs_on_prepare(unsigned long ip)
 
 	current->hardirq_chain_key = current->curr_chain_key;
 
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	__trace_hardirqs_on_caller();
 	lockdep_recursion_finish();
 }
@@ -3728,7 +3750,7 @@ void noinstr lockdep_hardirqs_on(unsigned long ip)
 		goto skip_checks;
 	}
 
-	if (unlikely(current->lockdep_recursion & LOCKDEP_RECURSION_MASK))
+	if (unlikely(__this_cpu_read(lockdep_recursion)))
 		return;
 
 	if (lockdep_hardirqs_enabled()) {
@@ -3781,7 +3803,7 @@ void noinstr lockdep_hardirqs_off(unsigned long ip)
 	if (in_nmi()) {
 		if (!IS_ENABLED(CONFIG_TRACE_IRQFLAGS_NMI))
 			return;
-	} else if (current->lockdep_recursion & LOCKDEP_RECURSION_MASK)
+	} else if (__this_cpu_read(lockdep_recursion))
 		return;
 
 	/*
@@ -3814,7 +3836,7 @@ void lockdep_softirqs_on(unsigned long ip)
 {
 	struct irqtrace_events *trace = &current->irqtrace;
 
-	if (unlikely(!debug_locks || current->lockdep_recursion))
+	if (unlikely(!lockdep_enabled()))
 		return;
 
 	/*
@@ -3829,7 +3851,7 @@ void lockdep_softirqs_on(unsigned long ip)
 		return;
 	}
 
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	/*
 	 * We'll do an OFF -> ON transition:
 	 */
@@ -3852,7 +3874,7 @@ void lockdep_softirqs_on(unsigned long ip)
  */
 void lockdep_softirqs_off(unsigned long ip)
 {
-	if (unlikely(!debug_locks || current->lockdep_recursion))
+	if (unlikely(!lockdep_enabled()))
 		return;
 
 	/*
@@ -4233,11 +4255,11 @@ void lockdep_init_map_waits(struct lockdep_map *lock, const char *name,
 	if (subclass) {
 		unsigned long flags;
 
-		if (DEBUG_LOCKS_WARN_ON(current->lockdep_recursion))
+		if (DEBUG_LOCKS_WARN_ON(!lockdep_enabled()))
 			return;
 
 		raw_local_irq_save(flags);
-		current->lockdep_recursion++;
+		lockdep_recursion_inc();
 		register_lock_class(lock, subclass, 1);
 		lockdep_recursion_finish();
 		raw_local_irq_restore(flags);
@@ -4920,11 +4942,11 @@ void lock_set_class(struct lockdep_map *lock, const char *name,
 {
 	unsigned long flags;
 
-	if (unlikely(current->lockdep_recursion))
+	if (unlikely(!lockdep_enabled()))
 		return;
 
 	raw_local_irq_save(flags);
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	check_flags(flags);
 	if (__lock_set_class(lock, name, key, subclass, ip))
 		check_chain_key(current);
@@ -4937,11 +4959,11 @@ void lock_downgrade(struct lockdep_map *lock, unsigned long ip)
 {
 	unsigned long flags;
 
-	if (unlikely(current->lockdep_recursion))
+	if (unlikely(!lockdep_enabled()))
 		return;
 
 	raw_local_irq_save(flags);
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	check_flags(flags);
 	if (__lock_downgrade(lock, ip))
 		check_chain_key(current);
@@ -4979,7 +5001,7 @@ static void verify_lock_unused(struct lockdep_map *lock, struct held_lock *hlock
 
 static bool lockdep_nmi(void)
 {
-	if (current->lockdep_recursion & LOCKDEP_RECURSION_MASK)
+	if (raw_cpu_read(lockdep_recursion))
 		return false;
 
 	if (!in_nmi())
@@ -5000,7 +5022,10 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 
 	trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip);
 
-	if (unlikely(current->lockdep_recursion)) {
+	if (!debug_locks)
+		return;
+
+	if (unlikely(!lockdep_enabled())) {
 		/* XXX allow trylock from NMI ?!? */
 		if (lockdep_nmi() && !trylock) {
 			struct held_lock hlock;
@@ -5023,7 +5048,7 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	raw_local_irq_save(flags);
 	check_flags(flags);
 
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	__lock_acquire(lock, subclass, trylock, read, check,
 		       irqs_disabled_flags(flags), nest_lock, ip, 0, 0);
 	lockdep_recursion_finish();
@@ -5037,13 +5062,13 @@ void lock_release(struct lockdep_map *lock, unsigned long ip)
 
 	trace_lock_release(lock, ip);
 
-	if (unlikely(current->lockdep_recursion))
+	if (unlikely(!lockdep_enabled()))
 		return;
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
 
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	if (__lock_release(lock, ip))
 		check_chain_key(current);
 	lockdep_recursion_finish();
@@ -5056,13 +5081,13 @@ noinstr int lock_is_held_type(const struct lockdep_map *lock, int read)
 	unsigned long flags;
 	int ret = 0;
 
-	if (unlikely(current->lockdep_recursion))
+	if (unlikely(!lockdep_enabled()))
 		return 1; /* avoid false negative lockdep_assert_held() */
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
 
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	ret = __lock_is_held(lock, read);
 	lockdep_recursion_finish();
 	raw_local_irq_restore(flags);
@@ -5077,13 +5102,13 @@ struct pin_cookie lock_pin_lock(struct lockdep_map *lock)
 	struct pin_cookie cookie = NIL_COOKIE;
 	unsigned long flags;
 
-	if (unlikely(current->lockdep_recursion))
+	if (unlikely(!lockdep_enabled()))
 		return cookie;
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
 
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	cookie = __lock_pin_lock(lock);
 	lockdep_recursion_finish();
 	raw_local_irq_restore(flags);
@@ -5096,13 +5121,13 @@ void lock_repin_lock(struct lockdep_map *lock, struct pin_cookie cookie)
 {
 	unsigned long flags;
 
-	if (unlikely(current->lockdep_recursion))
+	if (unlikely(!lockdep_enabled()))
 		return;
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
 
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	__lock_repin_lock(lock, cookie);
 	lockdep_recursion_finish();
 	raw_local_irq_restore(flags);
@@ -5113,13 +5138,13 @@ void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie cookie)
 {
 	unsigned long flags;
 
-	if (unlikely(current->lockdep_recursion))
+	if (unlikely(!lockdep_enabled()))
 		return;
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
 
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	__lock_unpin_lock(lock, cookie);
 	lockdep_recursion_finish();
 	raw_local_irq_restore(flags);
@@ -5249,15 +5274,12 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip)
 
 	trace_lock_acquired(lock, ip);
 
-	if (unlikely(!lock_stat || !debug_locks))
-		return;
-
-	if (unlikely(current->lockdep_recursion))
+	if (unlikely(!lock_stat || !lockdep_enabled()))
 		return;
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	__lock_contended(lock, ip);
 	lockdep_recursion_finish();
 	raw_local_irq_restore(flags);
@@ -5270,15 +5292,12 @@ void lock_acquired(struct lockdep_map *lock, unsigned long ip)
 
 	trace_lock_contended(lock, ip);
 
-	if (unlikely(!lock_stat || !debug_locks))
-		return;
-
-	if (unlikely(current->lockdep_recursion))
+	if (unlikely(!lock_stat || !lockdep_enabled()))
 		return;
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	__lock_acquired(lock, ip);
 	lockdep_recursion_finish();
 	raw_local_irq_restore(flags);
-- 
cgit v1.2.3


From baffd723e44dc3d7f84f0b8f1fe1ece00ddd2710 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 5 Oct 2020 09:56:57 +0200
Subject: lockdep: Revert "lockdep: Use raw_cpu_*() for per-cpu variables"

The thinking in commit:

  fddf9055a60d ("lockdep: Use raw_cpu_*() for per-cpu variables")

is flawed. While it is true that when we're migratable both CPUs will
have a 0 value, it doesn't hold that when we do get migrated in the
middle of a raw_cpu_op(), the old CPU will still have 0 by the time we
get around to reading it on the new CPU.

Luckily, the reason for that commit (s390 using preempt_disable()
instead of preempt_disable_notrace() in their percpu code), has since
been fixed by commit:

  1196f12a2c96 ("s390: don't trace preemption in percpu macros")

An audit of arch/*/include/asm/percpu*.h shows there are no other
architectures affected by this particular issue.

Fixes: fddf9055a60d ("lockdep: Use raw_cpu_*() for per-cpu variables")
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20201005095958.GJ2651@hirez.programming.kicks-ass.net
---
 include/linux/lockdep.h | 26 +++++++++-----------------
 1 file changed, 9 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index b1227be47496..1130f271de66 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -512,19 +512,19 @@ static inline void print_irqtrace_events(struct task_struct *curr)
 #define lock_map_release(l)			lock_release(l, _THIS_IP_)
 
 #ifdef CONFIG_PROVE_LOCKING
-# define might_lock(lock) 						\
+# define might_lock(lock)						\
 do {									\
 	typecheck(struct lockdep_map *, &(lock)->dep_map);		\
 	lock_acquire(&(lock)->dep_map, 0, 0, 0, 1, NULL, _THIS_IP_);	\
 	lock_release(&(lock)->dep_map, _THIS_IP_);			\
 } while (0)
-# define might_lock_read(lock) 						\
+# define might_lock_read(lock)						\
 do {									\
 	typecheck(struct lockdep_map *, &(lock)->dep_map);		\
 	lock_acquire(&(lock)->dep_map, 0, 0, 1, 1, NULL, _THIS_IP_);	\
 	lock_release(&(lock)->dep_map, _THIS_IP_);			\
 } while (0)
-# define might_lock_nested(lock, subclass) 				\
+# define might_lock_nested(lock, subclass)				\
 do {									\
 	typecheck(struct lockdep_map *, &(lock)->dep_map);		\
 	lock_acquire(&(lock)->dep_map, subclass, 0, 1, 1, NULL,		\
@@ -536,29 +536,21 @@ DECLARE_PER_CPU(int, hardirqs_enabled);
 DECLARE_PER_CPU(int, hardirq_context);
 DECLARE_PER_CPU(unsigned int, lockdep_recursion);
 
-/*
- * The below lockdep_assert_*() macros use raw_cpu_read() to access the above
- * per-cpu variables. This is required because this_cpu_read() will potentially
- * call into preempt/irq-disable and that obviously isn't right. This is also
- * correct because when IRQs are enabled, it doesn't matter if we accidentally
- * read the value from our previous CPU.
- */
-
-#define __lockdep_enabled	(debug_locks && !raw_cpu_read(lockdep_recursion))
+#define __lockdep_enabled	(debug_locks && !this_cpu_read(lockdep_recursion))
 
 #define lockdep_assert_irqs_enabled()					\
 do {									\
-	WARN_ON_ONCE(__lockdep_enabled && !raw_cpu_read(hardirqs_enabled)); \
+	WARN_ON_ONCE(__lockdep_enabled && !this_cpu_read(hardirqs_enabled)); \
 } while (0)
 
 #define lockdep_assert_irqs_disabled()					\
 do {									\
-	WARN_ON_ONCE(__lockdep_enabled && raw_cpu_read(hardirqs_enabled)); \
+	WARN_ON_ONCE(__lockdep_enabled && this_cpu_read(hardirqs_enabled)); \
 } while (0)
 
 #define lockdep_assert_in_irq()						\
 do {									\
-	WARN_ON_ONCE(__lockdep_enabled && !raw_cpu_read(hardirq_context)); \
+	WARN_ON_ONCE(__lockdep_enabled && !this_cpu_read(hardirq_context)); \
 } while (0)
 
 #define lockdep_assert_preemption_enabled()				\
@@ -566,7 +558,7 @@ do {									\
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT)	&&		\
 		     __lockdep_enabled			&&		\
 		     (preempt_count() != 0		||		\
-		      !raw_cpu_read(hardirqs_enabled)));		\
+		      !this_cpu_read(hardirqs_enabled)));		\
 } while (0)
 
 #define lockdep_assert_preemption_disabled()				\
@@ -574,7 +566,7 @@ do {									\
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT)	&&		\
 		     __lockdep_enabled			&&		\
 		     (preempt_count() == 0		&&		\
-		      raw_cpu_read(hardirqs_enabled)));			\
+		      this_cpu_read(hardirqs_enabled)));		\
 } while (0)
 
 #else
-- 
cgit v1.2.3


From 38b9f903f22b9baa5c4b9bfb07c8bbc49f5efbba Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Wed, 7 Oct 2020 09:00:49 +0300
Subject: net/mlx5: Handle sync reset request event

Once the driver gets sync_reset_request from firmware it prepares for the
coming reset and sends acknowledge.
After getting this event the driver expects device reset, either it will
trigger PCI reset on sync_reset_now event or such PCI reset will be
triggered by another PF of the same device. So it moves to reset
requested mode and if it gets PCI reset triggered by the other PF it
detect the reset and reloads.

Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c | 178 +++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h |   5 +
 drivers/net/ethernet/mellanox/mlx5/core/health.c   |  35 ++--
 drivers/net/ethernet/mellanox/mlx5/core/main.c     |  13 ++
 .../net/ethernet/mellanox/mlx5/core/mlx5_core.h    |   2 +
 include/linux/mlx5/driver.h                        |   2 +
 6 files changed, 220 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
index 7feae827b4bc..cd1b4e1b56ba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
@@ -3,6 +3,20 @@
 
 #include "fw_reset.h"
 
+enum {
+	MLX5_FW_RESET_FLAGS_RESET_REQUESTED,
+};
+
+struct mlx5_fw_reset {
+	struct mlx5_core_dev *dev;
+	struct mlx5_nb nb;
+	struct workqueue_struct *wq;
+	struct work_struct reset_request_work;
+	struct work_struct reset_reload_work;
+	unsigned long reset_flags;
+	struct timer_list timer;
+};
+
 static int mlx5_reg_mfrl_set(struct mlx5_core_dev *dev, u8 reset_level,
 			     u8 reset_type_sel, u8 sync_resp, bool sync_start)
 {
@@ -49,3 +63,167 @@ int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev)
 {
 	return mlx5_reg_mfrl_set(dev, MLX5_MFRL_REG_RESET_LEVEL0, 0, 0, false);
 }
+
+static void mlx5_sync_reset_reload_work(struct work_struct *work)
+{
+	struct mlx5_fw_reset *fw_reset = container_of(work, struct mlx5_fw_reset,
+						      reset_reload_work);
+	struct mlx5_core_dev *dev = fw_reset->dev;
+
+	mlx5_enter_error_state(dev, true);
+	mlx5_unload_one(dev, false);
+	if (mlx5_health_wait_pci_up(dev)) {
+		mlx5_core_err(dev, "reset reload flow aborted, PCI reads still not working\n");
+		return;
+	}
+	mlx5_load_one(dev, false);
+}
+
+static void mlx5_stop_sync_reset_poll(struct mlx5_core_dev *dev)
+{
+	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
+
+	del_timer(&fw_reset->timer);
+}
+
+static void mlx5_sync_reset_clear_reset_requested(struct mlx5_core_dev *dev, bool poll_health)
+{
+	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
+
+	mlx5_stop_sync_reset_poll(dev);
+	clear_bit(MLX5_FW_RESET_FLAGS_RESET_REQUESTED, &fw_reset->reset_flags);
+	if (poll_health)
+		mlx5_start_health_poll(dev);
+}
+
+#define MLX5_RESET_POLL_INTERVAL	(HZ / 10)
+static void poll_sync_reset(struct timer_list *t)
+{
+	struct mlx5_fw_reset *fw_reset = from_timer(fw_reset, t, timer);
+	struct mlx5_core_dev *dev = fw_reset->dev;
+	u32 fatal_error;
+
+	if (!test_bit(MLX5_FW_RESET_FLAGS_RESET_REQUESTED, &fw_reset->reset_flags))
+		return;
+
+	fatal_error = mlx5_health_check_fatal_sensors(dev);
+
+	if (fatal_error) {
+		mlx5_core_warn(dev, "Got Device Reset\n");
+		mlx5_sync_reset_clear_reset_requested(dev, false);
+		queue_work(fw_reset->wq, &fw_reset->reset_reload_work);
+		return;
+	}
+
+	mod_timer(&fw_reset->timer, round_jiffies(jiffies + MLX5_RESET_POLL_INTERVAL));
+}
+
+static void mlx5_start_sync_reset_poll(struct mlx5_core_dev *dev)
+{
+	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
+
+	timer_setup(&fw_reset->timer, poll_sync_reset, 0);
+	fw_reset->timer.expires = round_jiffies(jiffies + MLX5_RESET_POLL_INTERVAL);
+	add_timer(&fw_reset->timer);
+}
+
+static int mlx5_fw_reset_set_reset_sync_ack(struct mlx5_core_dev *dev)
+{
+	return mlx5_reg_mfrl_set(dev, MLX5_MFRL_REG_RESET_LEVEL3, 0, 1, false);
+}
+
+static void mlx5_sync_reset_set_reset_requested(struct mlx5_core_dev *dev)
+{
+	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
+
+	mlx5_stop_health_poll(dev, true);
+	set_bit(MLX5_FW_RESET_FLAGS_RESET_REQUESTED, &fw_reset->reset_flags);
+	mlx5_start_sync_reset_poll(dev);
+}
+
+static void mlx5_sync_reset_request_event(struct work_struct *work)
+{
+	struct mlx5_fw_reset *fw_reset = container_of(work, struct mlx5_fw_reset,
+						      reset_request_work);
+	struct mlx5_core_dev *dev = fw_reset->dev;
+	int err;
+
+	mlx5_sync_reset_set_reset_requested(dev);
+	err = mlx5_fw_reset_set_reset_sync_ack(dev);
+	if (err)
+		mlx5_core_warn(dev, "PCI Sync FW Update Reset Ack Failed. Error code: %d\n", err);
+	else
+		mlx5_core_warn(dev, "PCI Sync FW Update Reset Ack. Device reset is expected.\n");
+}
+
+static void mlx5_sync_reset_events_handle(struct mlx5_fw_reset *fw_reset, struct mlx5_eqe *eqe)
+{
+	struct mlx5_eqe_sync_fw_update *sync_fw_update_eqe;
+	u8 sync_event_rst_type;
+
+	sync_fw_update_eqe = &eqe->data.sync_fw_update;
+	sync_event_rst_type = sync_fw_update_eqe->sync_rst_state & SYNC_RST_STATE_MASK;
+	switch (sync_event_rst_type) {
+	case MLX5_SYNC_RST_STATE_RESET_REQUEST:
+		queue_work(fw_reset->wq, &fw_reset->reset_request_work);
+		break;
+	}
+}
+
+static int fw_reset_event_notifier(struct notifier_block *nb, unsigned long action, void *data)
+{
+	struct mlx5_fw_reset *fw_reset = mlx5_nb_cof(nb, struct mlx5_fw_reset, nb);
+	struct mlx5_eqe *eqe = data;
+
+	switch (eqe->sub_type) {
+	case MLX5_GENERAL_SUBTYPE_PCI_SYNC_FOR_FW_UPDATE_EVENT:
+		mlx5_sync_reset_events_handle(fw_reset, eqe);
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	return NOTIFY_OK;
+}
+
+void mlx5_fw_reset_events_start(struct mlx5_core_dev *dev)
+{
+	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
+
+	MLX5_NB_INIT(&fw_reset->nb, fw_reset_event_notifier, GENERAL_EVENT);
+	mlx5_eq_notifier_register(dev, &fw_reset->nb);
+}
+
+void mlx5_fw_reset_events_stop(struct mlx5_core_dev *dev)
+{
+	mlx5_eq_notifier_unregister(dev, &dev->priv.fw_reset->nb);
+}
+
+int mlx5_fw_reset_init(struct mlx5_core_dev *dev)
+{
+	struct mlx5_fw_reset *fw_reset = kzalloc(sizeof(*fw_reset), GFP_KERNEL);
+
+	if (!fw_reset)
+		return -ENOMEM;
+	fw_reset->wq = create_singlethread_workqueue("mlx5_fw_reset_events");
+	if (!fw_reset->wq) {
+		kfree(fw_reset);
+		return -ENOMEM;
+	}
+
+	fw_reset->dev = dev;
+	dev->priv.fw_reset = fw_reset;
+
+	INIT_WORK(&fw_reset->reset_request_work, mlx5_sync_reset_request_event);
+	INIT_WORK(&fw_reset->reset_reload_work, mlx5_sync_reset_reload_work);
+
+	return 0;
+}
+
+void mlx5_fw_reset_cleanup(struct mlx5_core_dev *dev)
+{
+	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
+
+	destroy_workqueue(fw_reset->wq);
+	kfree(dev->priv.fw_reset);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h
index 10b5f108cc8b..a231f7848a8f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h
@@ -10,4 +10,9 @@ int mlx5_fw_reset_query(struct mlx5_core_dev *dev, u8 *reset_level, u8 *reset_ty
 int mlx5_fw_reset_set_reset_sync(struct mlx5_core_dev *dev, u8 reset_type_sel);
 int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev);
 
+void mlx5_fw_reset_events_start(struct mlx5_core_dev *dev);
+void mlx5_fw_reset_events_stop(struct mlx5_core_dev *dev);
+int mlx5_fw_reset_init(struct mlx5_core_dev *dev);
+void mlx5_fw_reset_cleanup(struct mlx5_core_dev *dev);
+
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index b31f769d2df9..54523bed16cd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -110,7 +110,7 @@ static bool sensor_fw_synd_rfr(struct mlx5_core_dev *dev)
 	return rfr && synd;
 }
 
-static u32 check_fatal_sensors(struct mlx5_core_dev *dev)
+u32 mlx5_health_check_fatal_sensors(struct mlx5_core_dev *dev)
 {
 	if (sensor_pci_not_working(dev))
 		return MLX5_SENSOR_PCI_COMM_ERR;
@@ -173,7 +173,7 @@ static bool reset_fw_if_needed(struct mlx5_core_dev *dev)
 	 * Check again to avoid a redundant 2nd reset. If the fatal erros was
 	 * PCI related a reset won't help.
 	 */
-	fatal_error = check_fatal_sensors(dev);
+	fatal_error = mlx5_health_check_fatal_sensors(dev);
 	if (fatal_error == MLX5_SENSOR_PCI_COMM_ERR ||
 	    fatal_error == MLX5_SENSOR_NIC_DISABLED ||
 	    fatal_error == MLX5_SENSOR_NIC_SW_RESET) {
@@ -195,7 +195,7 @@ void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force)
 	bool err_detected = false;
 
 	/* Mark the device as fatal in order to abort FW commands */
-	if ((check_fatal_sensors(dev) || force) &&
+	if ((mlx5_health_check_fatal_sensors(dev) || force) &&
 	    dev->state == MLX5_DEVICE_STATE_UP) {
 		dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
 		err_detected = true;
@@ -208,7 +208,7 @@ void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force)
 		goto unlock;
 	}
 
-	if (check_fatal_sensors(dev) || force) { /* protected state setting */
+	if (mlx5_health_check_fatal_sensors(dev) || force) { /* protected state setting */
 		dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
 		mlx5_cmd_flush(dev);
 	}
@@ -231,7 +231,7 @@ void mlx5_error_sw_reset(struct mlx5_core_dev *dev)
 
 	mlx5_core_err(dev, "start\n");
 
-	if (check_fatal_sensors(dev) == MLX5_SENSOR_FW_SYND_RFR) {
+	if (mlx5_health_check_fatal_sensors(dev) == MLX5_SENSOR_FW_SYND_RFR) {
 		/* Get cr-dump and reset FW semaphore */
 		lock = lock_sem_sw_reset(dev, true);
 
@@ -308,26 +308,31 @@ static void mlx5_handle_bad_state(struct mlx5_core_dev *dev)
 
 /* How much time to wait until health resetting the driver (in msecs) */
 #define MLX5_RECOVERY_WAIT_MSECS 60000
-static int mlx5_health_try_recover(struct mlx5_core_dev *dev)
+int mlx5_health_wait_pci_up(struct mlx5_core_dev *dev)
 {
 	unsigned long end;
 
-	mlx5_core_warn(dev, "handling bad device here\n");
-	mlx5_handle_bad_state(dev);
 	end = jiffies + msecs_to_jiffies(MLX5_RECOVERY_WAIT_MSECS);
 	while (sensor_pci_not_working(dev)) {
-		if (time_after(jiffies, end)) {
-			mlx5_core_err(dev,
-				      "health recovery flow aborted, PCI reads still not working\n");
-			return -EIO;
-		}
+		if (time_after(jiffies, end))
+			return -ETIMEDOUT;
 		msleep(100);
 	}
+	return 0;
+}
 
+static int mlx5_health_try_recover(struct mlx5_core_dev *dev)
+{
+	mlx5_core_warn(dev, "handling bad device here\n");
+	mlx5_handle_bad_state(dev);
+	if (mlx5_health_wait_pci_up(dev)) {
+		mlx5_core_err(dev, "health recovery flow aborted, PCI reads still not working\n");
+		return -EIO;
+	}
 	mlx5_core_err(dev, "starting health recovery flow\n");
 	mlx5_recover_device(dev);
 	if (!test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state) ||
-	    check_fatal_sensors(dev)) {
+	    mlx5_health_check_fatal_sensors(dev)) {
 		mlx5_core_err(dev, "health recovery failed\n");
 		return -EIO;
 	}
@@ -696,7 +701,7 @@ static void poll_health(struct timer_list *t)
 	if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
 		goto out;
 
-	fatal_error = check_fatal_sensors(dev);
+	fatal_error = mlx5_health_check_fatal_sensors(dev);
 
 	if (fatal_error && !health->fatal_error) {
 		mlx5_core_err(dev, "Fatal error %u detected\n", fatal_error);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 5dd23790e7ee..8ff207aa1479 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -57,6 +57,7 @@
 #include "lib/mpfs.h"
 #include "eswitch.h"
 #include "devlink.h"
+#include "fw_reset.h"
 #include "lib/mlx5.h"
 #include "fpga/core.h"
 #include "fpga/ipsec.h"
@@ -835,6 +836,12 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 		goto err_eq_cleanup;
 	}
 
+	err = mlx5_fw_reset_init(dev);
+	if (err) {
+		mlx5_core_err(dev, "failed to initialize fw reset events\n");
+		goto err_events_cleanup;
+	}
+
 	mlx5_cq_debugfs_init(dev);
 
 	mlx5_init_reserved_gids(dev);
@@ -896,6 +903,8 @@ err_tables_cleanup:
 	mlx5_geneve_destroy(dev->geneve);
 	mlx5_vxlan_destroy(dev->vxlan);
 	mlx5_cq_debugfs_cleanup(dev);
+	mlx5_fw_reset_cleanup(dev);
+err_events_cleanup:
 	mlx5_events_cleanup(dev);
 err_eq_cleanup:
 	mlx5_eq_table_cleanup(dev);
@@ -923,6 +932,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 	mlx5_cleanup_clock(dev);
 	mlx5_cleanup_reserved_gids(dev);
 	mlx5_cq_debugfs_cleanup(dev);
+	mlx5_fw_reset_cleanup(dev);
 	mlx5_events_cleanup(dev);
 	mlx5_eq_table_cleanup(dev);
 	mlx5_irq_table_cleanup(dev);
@@ -1081,6 +1091,7 @@ static int mlx5_load(struct mlx5_core_dev *dev)
 		goto err_fw_tracer;
 	}
 
+	mlx5_fw_reset_events_start(dev);
 	mlx5_hv_vhca_init(dev->hv_vhca);
 
 	err = mlx5_rsc_dump_init(dev);
@@ -1142,6 +1153,7 @@ err_fpga_start:
 	mlx5_rsc_dump_cleanup(dev);
 err_rsc_dump:
 	mlx5_hv_vhca_cleanup(dev->hv_vhca);
+	mlx5_fw_reset_events_stop(dev);
 	mlx5_fw_tracer_cleanup(dev->tracer);
 err_fw_tracer:
 	mlx5_eq_table_destroy(dev);
@@ -1164,6 +1176,7 @@ static void mlx5_unload(struct mlx5_core_dev *dev)
 	mlx5_fpga_device_stop(dev);
 	mlx5_rsc_dump_cleanup(dev);
 	mlx5_hv_vhca_cleanup(dev->hv_vhca);
+	mlx5_fw_reset_events_stop(dev);
 	mlx5_fw_tracer_cleanup(dev->tracer);
 	mlx5_eq_table_destroy(dev);
 	mlx5_irq_table_destroy(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index e994f84f50b6..8cec85ab419d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -128,6 +128,8 @@ int mlx5_cmd_force_teardown_hca(struct mlx5_core_dev *dev);
 int mlx5_cmd_fast_teardown_hca(struct mlx5_core_dev *dev);
 void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force);
 void mlx5_error_sw_reset(struct mlx5_core_dev *dev);
+u32 mlx5_health_check_fatal_sensors(struct mlx5_core_dev *dev);
+int mlx5_health_wait_pci_up(struct mlx5_core_dev *dev);
 void mlx5_disable_device(struct mlx5_core_dev *dev);
 void mlx5_recover_device(struct mlx5_core_dev *dev);
 int mlx5_sriov_init(struct mlx5_core_dev *dev);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 239e5348ee09..add85094f9a5 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -501,6 +501,7 @@ struct mlx5_mpfs;
 struct mlx5_eswitch;
 struct mlx5_lag;
 struct mlx5_devcom;
+struct mlx5_fw_reset;
 struct mlx5_eq_table;
 struct mlx5_irq_table;
 
@@ -578,6 +579,7 @@ struct mlx5_priv {
 	struct mlx5_core_sriov	sriov;
 	struct mlx5_lag		*lag;
 	struct mlx5_devcom	*devcom;
+	struct mlx5_fw_reset	*fw_reset;
 	struct mlx5_core_roce	roce;
 	struct mlx5_fc_stats		fc_stats;
 	struct mlx5_rl_table            rl_table;
-- 
cgit v1.2.3


From 2d69356752ff862dbb0c7e6725874740799d7708 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Wed, 7 Oct 2020 09:00:55 +0300
Subject: net/mlx5: Add support for fw live patch event

Firmware live patch event notifies the driver that the firmware was just
updated using live patch. In such case the driver should not reload or
re-initiate entities, part to updating the firmware version and
re-initiate the firmware tracer which can be updated by live patch with
new strings database to help debugging an issue.

Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/mellanox/mlx5/core/diag/fw_tracer.c   | 52 ++++++++++++++++++++++
 .../ethernet/mellanox/mlx5/core/diag/fw_tracer.h   |  1 +
 drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c | 24 ++++++++++
 include/linux/mlx5/device.h                        |  1 +
 4 files changed, 78 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
index ede4640b8428..2eb022ad7fd0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
@@ -1066,6 +1066,58 @@ void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer)
 	kvfree(tracer);
 }
 
+static int mlx5_fw_tracer_recreate_strings_db(struct mlx5_fw_tracer *tracer)
+{
+	struct mlx5_core_dev *dev;
+	int err;
+
+	cancel_work_sync(&tracer->read_fw_strings_work);
+	mlx5_fw_tracer_clean_ready_list(tracer);
+	mlx5_fw_tracer_clean_print_hash(tracer);
+	mlx5_fw_tracer_clean_saved_traces_array(tracer);
+	mlx5_fw_tracer_free_strings_db(tracer);
+
+	dev = tracer->dev;
+	err = mlx5_query_mtrc_caps(tracer);
+	if (err) {
+		mlx5_core_dbg(dev, "FWTracer: Failed to query capabilities %d\n", err);
+		return err;
+	}
+
+	err = mlx5_fw_tracer_allocate_strings_db(tracer);
+	if (err) {
+		mlx5_core_warn(dev, "FWTracer: Allocate strings DB failed %d\n", err);
+		return err;
+	}
+	mlx5_fw_tracer_init_saved_traces_array(tracer);
+
+	return 0;
+}
+
+int mlx5_fw_tracer_reload(struct mlx5_fw_tracer *tracer)
+{
+	struct mlx5_core_dev *dev;
+	int err;
+
+	if (IS_ERR_OR_NULL(tracer))
+		return -EINVAL;
+
+	dev = tracer->dev;
+	mlx5_fw_tracer_cleanup(tracer);
+	err = mlx5_fw_tracer_recreate_strings_db(tracer);
+	if (err) {
+		mlx5_core_warn(dev, "Failed to recreate FW tracer strings DB\n");
+		return err;
+	}
+	err = mlx5_fw_tracer_init(tracer);
+	if (err) {
+		mlx5_core_warn(dev, "Failed to re-initialize FW tracer\n");
+		return err;
+	}
+
+	return 0;
+}
+
 static int fw_tracer_event(struct notifier_block *nb, unsigned long action, void *data)
 {
 	struct mlx5_fw_tracer *tracer = mlx5_nb_cof(nb, struct mlx5_fw_tracer, nb);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
index 40601fba80ba..97252a85d65e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
@@ -191,5 +191,6 @@ void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer);
 int mlx5_fw_tracer_trigger_core_dump_general(struct mlx5_core_dev *dev);
 int mlx5_fw_tracer_get_saved_traces_objects(struct mlx5_fw_tracer *tracer,
 					    struct devlink_fmsg *fmsg);
+int mlx5_fw_tracer_reload(struct mlx5_fw_tracer *tracer);
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
index b2aaff8d4fcd..f9042e147c7f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2020, Mellanox Technologies inc.  All rights reserved. */
 
 #include "fw_reset.h"
+#include "diag/fw_tracer.h"
 
 enum {
 	MLX5_FW_RESET_FLAGS_RESET_REQUESTED,
@@ -13,6 +14,7 @@ struct mlx5_fw_reset {
 	struct mlx5_core_dev *dev;
 	struct mlx5_nb nb;
 	struct workqueue_struct *wq;
+	struct work_struct fw_live_patch_work;
 	struct work_struct reset_request_work;
 	struct work_struct reset_reload_work;
 	struct work_struct reset_now_work;
@@ -192,6 +194,24 @@ static void mlx5_sync_reset_set_reset_requested(struct mlx5_core_dev *dev)
 	mlx5_start_sync_reset_poll(dev);
 }
 
+static void mlx5_fw_live_patch_event(struct work_struct *work)
+{
+	struct mlx5_fw_reset *fw_reset = container_of(work, struct mlx5_fw_reset,
+						      fw_live_patch_work);
+	struct mlx5_core_dev *dev = fw_reset->dev;
+	struct mlx5_fw_tracer *tracer;
+
+	mlx5_core_info(dev, "Live patch updated firmware version: %d.%d.%d\n", fw_rev_maj(dev),
+		       fw_rev_min(dev), fw_rev_sub(dev));
+
+	tracer = dev->tracer;
+	if (IS_ERR_OR_NULL(tracer))
+		return;
+
+	if (mlx5_fw_tracer_reload(tracer))
+		mlx5_core_err(dev, "Failed to reload FW tracer\n");
+}
+
 static void mlx5_sync_reset_request_event(struct work_struct *work)
 {
 	struct mlx5_fw_reset *fw_reset = container_of(work, struct mlx5_fw_reset,
@@ -364,6 +384,9 @@ static int fw_reset_event_notifier(struct notifier_block *nb, unsigned long acti
 	struct mlx5_eqe *eqe = data;
 
 	switch (eqe->sub_type) {
+	case MLX5_GENERAL_SUBTYPE_FW_LIVE_PATCH_EVENT:
+			queue_work(fw_reset->wq, &fw_reset->fw_live_patch_work);
+		break;
 	case MLX5_GENERAL_SUBTYPE_PCI_SYNC_FOR_FW_UPDATE_EVENT:
 		mlx5_sync_reset_events_handle(fw_reset, eqe);
 		break;
@@ -421,6 +444,7 @@ int mlx5_fw_reset_init(struct mlx5_core_dev *dev)
 	fw_reset->dev = dev;
 	dev->priv.fw_reset = fw_reset;
 
+	INIT_WORK(&fw_reset->fw_live_patch_work, mlx5_fw_live_patch_event);
 	INIT_WORK(&fw_reset->reset_request_work, mlx5_sync_reset_request_event);
 	INIT_WORK(&fw_reset->reset_reload_work, mlx5_sync_reset_reload_work);
 	INIT_WORK(&fw_reset->reset_now_work, mlx5_sync_reset_now_event);
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 81ca5989009b..cf824366a7d1 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -366,6 +366,7 @@ enum {
 enum {
 	MLX5_GENERAL_SUBTYPE_DELAY_DROP_TIMEOUT = 0x1,
 	MLX5_GENERAL_SUBTYPE_PCI_POWER_CHANGE_EVENT = 0x5,
+	MLX5_GENERAL_SUBTYPE_FW_LIVE_PATCH_EVENT = 0x7,
 	MLX5_GENERAL_SUBTYPE_PCI_SYNC_FOR_FW_UPDATE_EVENT = 0x8,
 };
 
-- 
cgit v1.2.3


From 44f3625bc61653ea3bde9960298faf2f5518fda5 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 8 Oct 2020 12:45:17 +0200
Subject: netlink: export policy in extended ACK

Add a new attribute NLMSGERR_ATTR_POLICY to the extended ACK
to advertise the policy, e.g. if an attribute was out of range,
you'll know the range that's permissible.

Add new NL_SET_ERR_MSG_ATTR_POL() and NL_SET_ERR_MSG_ATTR_POL()
macros to set this, since realistically it's only useful to do
this when the bad attribute (offset) is also returned.

Use it in lib/nlattr.c which practically does all the policy
validation.

v2:
 - add and use netlink_policy_dump_attr_size_estimate()
v3:
 - remove redundant break
v4:
 - really remove redundant break ... sorry

Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netlink.h      | 30 ++++++++++++++--------
 include/net/netlink.h        |  4 +++
 include/uapi/linux/netlink.h |  2 ++
 lib/nlattr.c                 | 35 +++++++++++++------------
 net/netlink/af_netlink.c     |  5 ++++
 net/netlink/policy.c         | 61 ++++++++++++++++++++++++++++++++++++++++++++
 6 files changed, 110 insertions(+), 27 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index e3e49f0e5c13..666cd0390699 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -68,12 +68,14 @@ netlink_kernel_create(struct net *net, int unit, struct netlink_kernel_cfg *cfg)
  * @_msg: message string to report - don't access directly, use
  *	%NL_SET_ERR_MSG
  * @bad_attr: attribute with error
+ * @policy: policy for a bad attribute
  * @cookie: cookie data to return to userspace (for success)
  * @cookie_len: actual cookie data length
  */
 struct netlink_ext_ack {
 	const char *_msg;
 	const struct nlattr *bad_attr;
+	const struct nla_policy *policy;
 	u8 cookie[NETLINK_MAX_COOKIE_LEN];
 	u8 cookie_len;
 };
@@ -95,21 +97,29 @@ struct netlink_ext_ack {
 #define NL_SET_ERR_MSG_MOD(extack, msg)			\
 	NL_SET_ERR_MSG((extack), KBUILD_MODNAME ": " msg)
 
-#define NL_SET_BAD_ATTR(extack, attr) do {		\
-	if ((extack))					\
+#define NL_SET_BAD_ATTR_POLICY(extack, attr, pol) do {	\
+	if ((extack)) {					\
 		(extack)->bad_attr = (attr);		\
+		(extack)->policy = (pol);		\
+	}						\
 } while (0)
 
-#define NL_SET_ERR_MSG_ATTR(extack, attr, msg) do {	\
-	static const char __msg[] = msg;		\
-	struct netlink_ext_ack *__extack = (extack);	\
-							\
-	if (__extack) {					\
-		__extack->_msg = __msg;			\
-		__extack->bad_attr = (attr);		\
-	}						\
+#define NL_SET_BAD_ATTR(extack, attr) NL_SET_BAD_ATTR_POLICY(extack, attr, NULL)
+
+#define NL_SET_ERR_MSG_ATTR_POL(extack, attr, pol, msg) do {	\
+	static const char __msg[] = msg;			\
+	struct netlink_ext_ack *__extack = (extack);		\
+								\
+	if (__extack) {						\
+		__extack->_msg = __msg;				\
+		__extack->bad_attr = (attr);			\
+		__extack->policy = (pol);			\
+	}							\
 } while (0)
 
+#define NL_SET_ERR_MSG_ATTR(extack, attr, msg)		\
+	NL_SET_ERR_MSG_ATTR_POL(extack, attr, NULL, msg)
+
 static inline void nl_set_extack_cookie_u64(struct netlink_ext_ack *extack,
 					    u64 cookie)
 {
diff --git a/include/net/netlink.h b/include/net/netlink.h
index 2b9e41075f19..7356f41d23ba 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -1957,6 +1957,10 @@ int netlink_policy_dump_get_policy_idx(struct netlink_policy_dump_state *state,
 bool netlink_policy_dump_loop(struct netlink_policy_dump_state *state);
 int netlink_policy_dump_write(struct sk_buff *skb,
 			      struct netlink_policy_dump_state *state);
+int netlink_policy_dump_attr_size_estimate(const struct nla_policy *pt);
+int netlink_policy_dump_write_attr(struct sk_buff *skb,
+				   const struct nla_policy *pt,
+				   int nestattr);
 void netlink_policy_dump_free(struct netlink_policy_dump_state *state);
 
 #endif
diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h
index d02e472ba54c..c3816ff7bfc3 100644
--- a/include/uapi/linux/netlink.h
+++ b/include/uapi/linux/netlink.h
@@ -129,6 +129,7 @@ struct nlmsgerr {
  * @NLMSGERR_ATTR_COOKIE: arbitrary subsystem specific cookie to
  *	be used - in the success case - to identify a created
  *	object or operation or similar (binary)
+ * @NLMSGERR_ATTR_POLICY: policy for a rejected attribute
  * @__NLMSGERR_ATTR_MAX: number of attributes
  * @NLMSGERR_ATTR_MAX: highest attribute number
  */
@@ -137,6 +138,7 @@ enum nlmsgerr_attrs {
 	NLMSGERR_ATTR_MSG,
 	NLMSGERR_ATTR_OFFS,
 	NLMSGERR_ATTR_COOKIE,
+	NLMSGERR_ATTR_POLICY,
 
 	__NLMSGERR_ATTR_MAX,
 	NLMSGERR_ATTR_MAX = __NLMSGERR_ATTR_MAX - 1
diff --git a/lib/nlattr.c b/lib/nlattr.c
index 9c99f5daa4d2..74019c8ebf6b 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -96,8 +96,8 @@ static int nla_validate_array(const struct nlattr *head, int len, int maxtype,
 			continue;
 
 		if (nla_len(entry) < NLA_HDRLEN) {
-			NL_SET_ERR_MSG_ATTR(extack, entry,
-					    "Array element too short");
+			NL_SET_ERR_MSG_ATTR_POL(extack, entry, policy,
+						"Array element too short");
 			return -ERANGE;
 		}
 
@@ -195,8 +195,8 @@ static int nla_validate_range_unsigned(const struct nla_policy *pt,
 		pr_warn_ratelimited("netlink: '%s': attribute type %d has an invalid length.\n",
 				    current->comm, pt->type);
 		if (validate & NL_VALIDATE_STRICT_ATTRS) {
-			NL_SET_ERR_MSG_ATTR(extack, nla,
-					    "invalid attribute length");
+			NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt,
+						"invalid attribute length");
 			return -EINVAL;
 		}
 
@@ -208,11 +208,11 @@ static int nla_validate_range_unsigned(const struct nla_policy *pt,
 		bool binary = pt->type == NLA_BINARY;
 
 		if (binary)
-			NL_SET_ERR_MSG_ATTR(extack, nla,
-					    "binary attribute size out of range");
+			NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt,
+						"binary attribute size out of range");
 		else
-			NL_SET_ERR_MSG_ATTR(extack, nla,
-					    "integer out of range");
+			NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt,
+						"integer out of range");
 
 		return -ERANGE;
 	}
@@ -291,8 +291,8 @@ static int nla_validate_int_range_signed(const struct nla_policy *pt,
 	nla_get_range_signed(pt, &range);
 
 	if (value < range.min || value > range.max) {
-		NL_SET_ERR_MSG_ATTR(extack, nla,
-				    "integer out of range");
+		NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt,
+					"integer out of range");
 		return -ERANGE;
 	}
 
@@ -377,8 +377,8 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
 		pr_warn_ratelimited("netlink: '%s': attribute type %d has an invalid length.\n",
 				    current->comm, type);
 		if (validate & NL_VALIDATE_STRICT_ATTRS) {
-			NL_SET_ERR_MSG_ATTR(extack, nla,
-					    "invalid attribute length");
+			NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt,
+						"invalid attribute length");
 			return -EINVAL;
 		}
 	}
@@ -386,14 +386,14 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
 	if (validate & NL_VALIDATE_NESTED) {
 		if ((pt->type == NLA_NESTED || pt->type == NLA_NESTED_ARRAY) &&
 		    !(nla->nla_type & NLA_F_NESTED)) {
-			NL_SET_ERR_MSG_ATTR(extack, nla,
-					    "NLA_F_NESTED is missing");
+			NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt,
+						"NLA_F_NESTED is missing");
 			return -EINVAL;
 		}
 		if (pt->type != NLA_NESTED && pt->type != NLA_NESTED_ARRAY &&
 		    pt->type != NLA_UNSPEC && (nla->nla_type & NLA_F_NESTED)) {
-			NL_SET_ERR_MSG_ATTR(extack, nla,
-					    "NLA_F_NESTED not expected");
+			NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt,
+						"NLA_F_NESTED not expected");
 			return -EINVAL;
 		}
 	}
@@ -550,7 +550,8 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
 
 	return 0;
 out_err:
-	NL_SET_ERR_MSG_ATTR(extack, nla, "Attribute failed policy validation");
+	NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt,
+				"Attribute failed policy validation");
 	return err;
 }
 
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index df675a8e1918..daca50d6bb12 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2420,6 +2420,8 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err,
 		tlvlen += nla_total_size(sizeof(u32));
 	if (nlk_has_extack && extack && extack->cookie_len)
 		tlvlen += nla_total_size(extack->cookie_len);
+	if (err && nlk_has_extack && extack && extack->policy)
+		tlvlen += netlink_policy_dump_attr_size_estimate(extack->policy);
 
 	if (tlvlen)
 		flags |= NLM_F_ACK_TLVS;
@@ -2452,6 +2454,9 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err,
 		if (extack->cookie_len)
 			WARN_ON(nla_put(skb, NLMSGERR_ATTR_COOKIE,
 					extack->cookie_len, extack->cookie));
+		if (extack->policy)
+			netlink_policy_dump_write_attr(skb, extack->policy,
+						       NLMSGERR_ATTR_POLICY);
 	}
 
 	nlmsg_end(skb, rep);
diff --git a/net/netlink/policy.c b/net/netlink/policy.c
index 4383436759e2..8d7c900e27f4 100644
--- a/net/netlink/policy.c
+++ b/net/netlink/policy.c
@@ -196,12 +196,54 @@ bool netlink_policy_dump_loop(struct netlink_policy_dump_state *state)
 	return !netlink_policy_dump_finished(state);
 }
 
+int netlink_policy_dump_attr_size_estimate(const struct nla_policy *pt)
+{
+	/* nested + type */
+	int common = 2 * nla_attr_size(sizeof(u32));
+
+	switch (pt->type) {
+	case NLA_UNSPEC:
+	case NLA_REJECT:
+		/* these actually don't need any space */
+		return 0;
+	case NLA_NESTED:
+	case NLA_NESTED_ARRAY:
+		/* common, policy idx, policy maxattr */
+		return common + 2 * nla_attr_size(sizeof(u32));
+	case NLA_U8:
+	case NLA_U16:
+	case NLA_U32:
+	case NLA_U64:
+	case NLA_MSECS:
+	case NLA_S8:
+	case NLA_S16:
+	case NLA_S32:
+	case NLA_S64:
+		/* maximum is common, u64 min/max with padding */
+		return common +
+		       2 * (nla_attr_size(0) + nla_attr_size(sizeof(u64)));
+	case NLA_BITFIELD32:
+		return common + nla_attr_size(sizeof(u32));
+	case NLA_STRING:
+	case NLA_NUL_STRING:
+	case NLA_BINARY:
+		/* maximum is common, u32 min-length/max-length */
+		return common + 2 * nla_attr_size(sizeof(u32));
+	case NLA_FLAG:
+		return common;
+	}
+
+	/* this should then cause a warning later */
+	return 0;
+}
+
 static int
 __netlink_policy_dump_write_attr(struct netlink_policy_dump_state *state,
 				 struct sk_buff *skb,
 				 const struct nla_policy *pt,
 				 int nestattr)
 {
+	int estimate = netlink_policy_dump_attr_size_estimate(pt);
 	enum netlink_attribute_type type;
 	struct nlattr *attr;
 
@@ -334,12 +376,31 @@ __netlink_policy_dump_write_attr(struct netlink_policy_dump_state *state,
 		goto nla_put_failure;
 
 	nla_nest_end(skb, attr);
+	WARN_ON(attr->nla_len > estimate);
+
 	return 0;
 nla_put_failure:
 	nla_nest_cancel(skb, attr);
 	return -ENOBUFS;
 }
 
+/**
+ * netlink_policy_dump_write_attr - write a given attribute policy
+ * @skb: the message skb to write to
+ * @pt: the attribute's policy
+ * @nestattr: the nested attribute ID to use
+ *
+ * Returns: 0 on success, an error code otherwise; -%ENODATA is
+ *	    special, indicating that there's no policy data and
+ *	    the attribute is generally rejected.
+ */
+int netlink_policy_dump_write_attr(struct sk_buff *skb,
+				   const struct nla_policy *pt,
+				   int nestattr)
+{
+	return __netlink_policy_dump_write_attr(NULL, skb, pt, nestattr);
+}
+
 /**
  * netlink_policy_dump_write - write current policy dump attributes
  * @skb: the message skb to write to
-- 
cgit v1.2.3


From 55567976629e58fde28fb70612ca73228271eef2 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 6 Oct 2020 10:10:20 +0100
Subject: genirq/irqdomain: Allow partial trimming of irq_data hierarchy

It appears that some HW is ugly enough that not all the interrupts
connected to a particular interrupt controller end up with the same
hierarchy depth (some of them are terminated early). This leaves
the irqchip hacker with only two choices, both equally bad:

- create discrete domain chains, one for each "hierarchy depth",
  which is very hard to maintain

- create fake hierarchy levels for the shallow paths, leading
  to all kind of problems (what are the safe hwirq values for these
  fake levels?)

Implement the ability to cut short a single interrupt hierarchy
from a level marked as being disconnected by using the new
irq_domain_disconnect_hierarchy() helper.

The irqdomain allocation code will then perform the trimming

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 include/linux/irqdomain.h |  3 ++
 kernel/irq/irqdomain.c    | 99 +++++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 98 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index b37350c4fe37..a52b095bd404 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -509,6 +509,9 @@ extern void irq_domain_free_irqs_parent(struct irq_domain *domain,
 					unsigned int irq_base,
 					unsigned int nr_irqs);
 
+extern int irq_domain_disconnect_hierarchy(struct irq_domain *domain,
+					   unsigned int virq);
+
 static inline bool irq_domain_is_hierarchy(struct irq_domain *domain)
 {
 	return domain->flags & IRQ_DOMAIN_FLAG_HIERARCHY;
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 76cd7ebd1178..cf8b374b892d 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -1136,6 +1136,17 @@ static struct irq_data *irq_domain_insert_irq_data(struct irq_domain *domain,
 	return irq_data;
 }
 
+static void __irq_domain_free_hierarchy(struct irq_data *irq_data)
+{
+	struct irq_data *tmp;
+
+	while (irq_data) {
+		tmp = irq_data;
+		irq_data = irq_data->parent_data;
+		kfree(tmp);
+	}
+}
+
 static void irq_domain_free_irq_data(unsigned int virq, unsigned int nr_irqs)
 {
 	struct irq_data *irq_data, *tmp;
@@ -1147,12 +1158,83 @@ static void irq_domain_free_irq_data(unsigned int virq, unsigned int nr_irqs)
 		irq_data->parent_data = NULL;
 		irq_data->domain = NULL;
 
-		while (tmp) {
-			irq_data = tmp;
-			tmp = tmp->parent_data;
-			kfree(irq_data);
+		__irq_domain_free_hierarchy(tmp);
+	}
+}
+
+/**
+ * irq_domain_disconnect_hierarchy - Mark the first unused level of a hierarchy
+ * @domain:	IRQ domain from which the hierarchy is to be disconnected
+ * @virq:	IRQ number where the hierarchy is to be trimmed
+ *
+ * Marks the @virq level belonging to @domain as disconnected.
+ * Returns -EINVAL if @virq doesn't have a valid irq_data pointing
+ * to @domain.
+ *
+ * Its only use is to be able to trim levels of hierarchy that do not
+ * have any real meaning for this interrupt, and that the driver marks
+ * as such from its .alloc() callback.
+ */
+int irq_domain_disconnect_hierarchy(struct irq_domain *domain,
+				    unsigned int virq)
+{
+	struct irq_data *irqd;
+
+	irqd = irq_domain_get_irq_data(domain, virq);
+	if (!irqd)
+		return -EINVAL;
+
+	irqd->chip = ERR_PTR(-ENOTCONN);
+	return 0;
+}
+
+static int irq_domain_trim_hierarchy(unsigned int virq)
+{
+	struct irq_data *tail, *irqd, *irq_data;
+
+	irq_data = irq_get_irq_data(virq);
+	tail = NULL;
+
+	/* The first entry must have a valid irqchip */
+	if (!irq_data->chip || IS_ERR(irq_data->chip))
+		return -EINVAL;
+
+	/*
+	 * Validate that the irq_data chain is sane in the presence of
+	 * a hierarchy trimming marker.
+	 */
+	for (irqd = irq_data->parent_data; irqd; irq_data = irqd, irqd = irqd->parent_data) {
+		/* Can't have a valid irqchip after a trim marker */
+		if (irqd->chip && tail)
+			return -EINVAL;
+
+		/* Can't have an empty irqchip before a trim marker */
+		if (!irqd->chip && !tail)
+			return -EINVAL;
+
+		if (IS_ERR(irqd->chip)) {
+			/* Only -ENOTCONN is a valid trim marker */
+			if (PTR_ERR(irqd->chip) != -ENOTCONN)
+				return -EINVAL;
+
+			tail = irq_data;
 		}
 	}
+
+	/* No trim marker, nothing to do */
+	if (!tail)
+		return 0;
+
+	pr_info("IRQ%d: trimming hierarchy from %s\n",
+		virq, tail->parent_data->domain->name);
+
+	/* Sever the inner part of the hierarchy...  */
+	irqd = tail;
+	tail = tail->parent_data;
+	irqd->parent_data = NULL;
+	__irq_domain_free_hierarchy(tail);
+
+	return 0;
 }
 
 static int irq_domain_alloc_irq_data(struct irq_domain *domain,
@@ -1362,6 +1444,15 @@ int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base,
 		mutex_unlock(&irq_domain_mutex);
 		goto out_free_irq_data;
 	}
+
+	for (i = 0; i < nr_irqs; i++) {
+		ret = irq_domain_trim_hierarchy(virq + i);
+		if (ret) {
+			mutex_unlock(&irq_domain_mutex);
+			goto out_free_irq_data;
+		}
+	}
+	
 	for (i = 0; i < nr_irqs; i++)
 		irq_domain_insert_irq(virq + i);
 	mutex_unlock(&irq_domain_mutex);
-- 
cgit v1.2.3


From ead1c9f376dbb2805796098ed6d2a70921c77ee5 Mon Sep 17 00:00:00 2001
From: Alexandru Ardelean <alexandru.ardelean@analog.com>
Date: Wed, 30 Sep 2020 16:50:48 +0300
Subject: iio: adc: at91_adc: remove platform data and move defs in driver file

The AT91 ADC driver no longer uses the 'at91_add_device_adc' platform data
type. This is no longer used (at least in mainline boards).

This change removes the platform-data initialization from the driver, since
it is mostly dead code now.

Some definitions [from the platform data at91_adc.h include] have been
moved in the driver, since they are needed in the driver.

Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Reviewed-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Link: https://lore.kernel.org/r/20200930135048.11530-5-alexandru.ardelean@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/at91_adc.c             | 60 +++++++++++++---------------------
 include/linux/platform_data/at91_adc.h | 49 ---------------------------
 2 files changed, 22 insertions(+), 87 deletions(-)
 delete mode 100644 include/linux/platform_data/at91_adc.h

(limited to 'include/linux')

diff --git a/drivers/iio/adc/at91_adc.c b/drivers/iio/adc/at91_adc.c
index 473bffe84fbd..601708168082 100644
--- a/drivers/iio/adc/at91_adc.c
+++ b/drivers/iio/adc/at91_adc.c
@@ -22,8 +22,6 @@
 #include <linux/slab.h>
 #include <linux/wait.h>
 
-#include <linux/platform_data/at91_adc.h>
-
 #include <linux/iio/iio.h>
 #include <linux/iio/buffer.h>
 #include <linux/iio/trigger.h>
@@ -153,6 +151,25 @@
 #define TOUCH_SHTIM                    0xa
 #define TOUCH_SCTIM_US		10		/* 10us for the Touchscreen Switches Closure Time */
 
+enum atmel_adc_ts_type {
+	ATMEL_ADC_TOUCHSCREEN_NONE = 0,
+	ATMEL_ADC_TOUCHSCREEN_4WIRE = 4,
+	ATMEL_ADC_TOUCHSCREEN_5WIRE = 5,
+};
+
+/**
+ * struct at91_adc_trigger - description of triggers
+ * @name:		name of the trigger advertised to the user
+ * @value:		value to set in the ADC's trigger setup register
+ *			to enable the trigger
+ * @is_external:	Does the trigger rely on an external pin?
+ */
+struct at91_adc_trigger {
+	const char	*name;
+	u8		value;
+	bool		is_external;
+};
+
 /**
  * struct at91_adc_reg_desc - Various informations relative to registers
  * @channel_base:	Base offset for the channel data registers
@@ -873,9 +890,6 @@ static int at91_adc_probe_dt(struct iio_dev *idev,
 	int i = 0, ret;
 	u32 prop;
 
-	if (!node)
-		return -EINVAL;
-
 	st->caps = of_device_get_match_data(&pdev->dev);
 
 	st->use_external = of_property_read_bool(node, "atmel,adc-use-external-triggers");
@@ -957,30 +971,6 @@ error_ret:
 	return ret;
 }
 
-static int at91_adc_probe_pdata(struct at91_adc_state *st,
-				struct platform_device *pdev)
-{
-	struct at91_adc_data *pdata = pdev->dev.platform_data;
-
-	if (!pdata)
-		return -EINVAL;
-
-	st->caps = (struct at91_adc_caps *)
-			platform_get_device_id(pdev)->driver_data;
-
-	st->use_external = pdata->use_external_triggers;
-	st->vref_mv = pdata->vref;
-	st->channels_mask = pdata->channels_used;
-	st->num_channels = st->caps->num_channels;
-	st->startup_time = pdata->startup_time;
-	st->trigger_number = pdata->trigger_number;
-	st->trigger_list = pdata->trigger_list;
-	st->registers = &st->caps->registers;
-	st->touchscreen_type = pdata->touchscreen_type;
-
-	return 0;
-}
-
 static const struct iio_info at91_adc_info = {
 	.read_raw = &at91_adc_read_raw,
 };
@@ -1157,15 +1147,9 @@ static int at91_adc_probe(struct platform_device *pdev)
 
 	st = iio_priv(idev);
 
-	if (pdev->dev.of_node)
-		ret = at91_adc_probe_dt(idev, pdev);
-	else
-		ret = at91_adc_probe_pdata(st, pdev);
-
-	if (ret) {
-		dev_err(&pdev->dev, "No platform data available.\n");
-		return -EINVAL;
-	}
+	ret = at91_adc_probe_dt(idev, pdev);
+	if (ret)
+		return ret;
 
 	platform_set_drvdata(pdev, idev);
 
diff --git a/include/linux/platform_data/at91_adc.h b/include/linux/platform_data/at91_adc.h
deleted file mode 100644
index f20eaeb827ce..000000000000
--- a/include/linux/platform_data/at91_adc.h
+++ /dev/null
@@ -1,49 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Copyright (C) 2011 Free Electrons
- */
-
-#ifndef _AT91_ADC_H_
-#define _AT91_ADC_H_
-
-enum atmel_adc_ts_type {
-	ATMEL_ADC_TOUCHSCREEN_NONE = 0,
-	ATMEL_ADC_TOUCHSCREEN_4WIRE = 4,
-	ATMEL_ADC_TOUCHSCREEN_5WIRE = 5,
-};
-
-/**
- * struct at91_adc_trigger - description of triggers
- * @name:		name of the trigger advertised to the user
- * @value:		value to set in the ADC's trigger setup register
-			to enable the trigger
- * @is_external:	Does the trigger rely on an external pin?
- */
-struct at91_adc_trigger {
-	const char	*name;
-	u8		value;
-	bool		is_external;
-};
-
-/**
- * struct at91_adc_data - platform data for ADC driver
- * @channels_used:		channels in use on the board as a bitmask
- * @startup_time:		startup time of the ADC in microseconds
- * @trigger_list:		Triggers available in the ADC
- * @trigger_number:		Number of triggers available in the ADC
- * @use_external_triggers:	does the board has external triggers availables
- * @vref:			Reference voltage for the ADC in millivolts
- * @touchscreen_type:		If a touchscreen is connected, its type (4 or 5 wires)
- */
-struct at91_adc_data {
-	unsigned long			channels_used;
-	u8				startup_time;
-	struct at91_adc_trigger		*trigger_list;
-	u8				trigger_number;
-	bool				use_external_triggers;
-	u16				vref;
-	enum atmel_adc_ts_type		touchscreen_type;
-};
-
-extern void __init at91_add_device_adc(struct at91_adc_data *data);
-#endif
-- 
cgit v1.2.3


From 5483b8d5015bb366c372870cfe4448742082e41f Mon Sep 17 00:00:00 2001
From: Alexandru Ardelean <alexandru.ardelean@analog.com>
Date: Fri, 2 Oct 2020 11:27:23 +0300
Subject: iio: adc: ad7887: invert/rework external ref logic

This change inverts/reworks the logic to use an external reference via a
provided regulator.

Now the driver tries to obtain a regulator. If one is found, then it is
used. The rest of the driver logic already checks if there is a non-NULL
reference to a regulator, so it should be fine.

Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Link: https://lore.kernel.org/r/20201002082723.184810-1-alexandru.ardelean@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad7887.c             | 12 ++++++++----
 include/linux/platform_data/ad7887.h |  4 ----
 2 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iio/adc/ad7887.c b/drivers/iio/adc/ad7887.c
index 037bcb47693c..99a480ad3985 100644
--- a/drivers/iio/adc/ad7887.c
+++ b/drivers/iio/adc/ad7887.c
@@ -246,11 +246,15 @@ static int ad7887_probe(struct spi_device *spi)
 
 	st = iio_priv(indio_dev);
 
-	if (!pdata || !pdata->use_onchip_ref) {
-		st->reg = devm_regulator_get(&spi->dev, "vref");
-		if (IS_ERR(st->reg))
+	st->reg = devm_regulator_get_optional(&spi->dev, "vref");
+	if (IS_ERR(st->reg)) {
+		if (PTR_ERR(st->reg) != -ENODEV)
 			return PTR_ERR(st->reg);
 
+		st->reg = NULL;
+	}
+
+	if (st->reg) {
 		ret = regulator_enable(st->reg);
 		if (ret)
 			return ret;
@@ -269,7 +273,7 @@ static int ad7887_probe(struct spi_device *spi)
 	/* Setup default message */
 
 	mode = AD7887_PM_MODE4;
-	if (!pdata || !pdata->use_onchip_ref)
+	if (!st->reg)
 		mode |= AD7887_REF_DIS;
 	if (pdata && pdata->en_dual)
 		mode |= AD7887_DUAL;
diff --git a/include/linux/platform_data/ad7887.h b/include/linux/platform_data/ad7887.h
index 732af46b2d16..9b4dca6ae70b 100644
--- a/include/linux/platform_data/ad7887.h
+++ b/include/linux/platform_data/ad7887.h
@@ -13,13 +13,9 @@
  *	second input channel, and Vref is internally connected to Vdd. If set to
  *	false the device is used in single channel mode and AIN1/Vref is used as
  *	VREF input.
- * @use_onchip_ref: Whether to use the onchip reference. If set to true the
- *	internal 2.5V reference is used. If set to false a external reference is
- *	used.
  */
 struct ad7887_platform_data {
 	bool en_dual;
-	bool use_onchip_ref;
 };
 
 #endif /* IIO_ADC_AD7887_H_ */
-- 
cgit v1.2.3


From 28963f2f6b46d75bda8fed15bd5ce9923427a40d Mon Sep 17 00:00:00 2001
From: Alexandru Ardelean <alexandru.ardelean@analog.com>
Date: Thu, 1 Oct 2020 17:10:48 +0300
Subject: iio: adc: ad7298: rework external ref setup & remove platform data

This change removes the old platform data for ad7298. It is only used to
provide whether to use an external regulator as a reference.

So, the logic is inverted a bit. The driver now tries to obtain a
regulator. If one is provided, then the external ref is used. The rest of
the logic should work as before.

Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Link: https://lore.kernel.org/r/20201001141048.69050-1-alexandru.ardelean@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad7298.c             | 17 +++++++++--------
 include/linux/platform_data/ad7298.h | 19 -------------------
 2 files changed, 9 insertions(+), 27 deletions(-)
 delete mode 100644 include/linux/platform_data/ad7298.h

(limited to 'include/linux')

diff --git a/drivers/iio/adc/ad7298.c b/drivers/iio/adc/ad7298.c
index 48d43cb0f932..fa1047f74a1f 100644
--- a/drivers/iio/adc/ad7298.c
+++ b/drivers/iio/adc/ad7298.c
@@ -23,8 +23,6 @@
 #include <linux/iio/trigger_consumer.h>
 #include <linux/iio/triggered_buffer.h>
 
-#include <linux/platform_data/ad7298.h>
-
 #define AD7298_WRITE	BIT(15) /* write to the control register */
 #define AD7298_REPEAT	BIT(14) /* repeated conversion enable */
 #define AD7298_CH(x)	BIT(13 - (x)) /* channel select */
@@ -283,7 +281,6 @@ static const struct iio_info ad7298_info = {
 
 static int ad7298_probe(struct spi_device *spi)
 {
-	struct ad7298_platform_data *pdata = spi->dev.platform_data;
 	struct ad7298_state *st;
 	struct iio_dev *indio_dev;
 	int ret;
@@ -294,14 +291,18 @@ static int ad7298_probe(struct spi_device *spi)
 
 	st = iio_priv(indio_dev);
 
-	if (pdata && pdata->ext_ref)
+	st->reg = devm_regulator_get_optional(&spi->dev, "vref");
+	if (!IS_ERR(st->reg)) {
 		st->ext_ref = AD7298_EXTREF;
+	} else {
+		ret = PTR_ERR(st->reg);
+		if (ret != -ENODEV)
+			return ret;
 
-	if (st->ext_ref) {
-		st->reg = devm_regulator_get(&spi->dev, "vref");
-		if (IS_ERR(st->reg))
-			return PTR_ERR(st->reg);
+		st->reg = NULL;
+	}
 
+	if (st->reg) {
 		ret = regulator_enable(st->reg);
 		if (ret)
 			return ret;
diff --git a/include/linux/platform_data/ad7298.h b/include/linux/platform_data/ad7298.h
deleted file mode 100644
index 3e0ffe2d5d3d..000000000000
--- a/include/linux/platform_data/ad7298.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * AD7298 SPI ADC driver
- *
- * Copyright 2011 Analog Devices Inc.
- */
-
-#ifndef __LINUX_PLATFORM_DATA_AD7298_H__
-#define __LINUX_PLATFORM_DATA_AD7298_H__
-
-/**
- * struct ad7298_platform_data - Platform data for the ad7298 ADC driver
- * @ext_ref: Whether to use an external reference voltage.
- **/
-struct ad7298_platform_data {
-	bool ext_ref;
-};
-
-#endif /* IIO_ADC_AD7298_H_ */
-- 
cgit v1.2.3


From 223f4d9517f8d97721647297b1cde41241a45233 Mon Sep 17 00:00:00 2001
From: Alexandru Ardelean <alexandru.ardelean@analog.com>
Date: Thu, 1 Oct 2020 17:10:04 +0300
Subject: iio: dac: ad7303: remove platform data header

The information in the ad7303 platform_data header is unused, so it's dead
code.
This change removes it and it's inclusion from the driver.

Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Link: https://lore.kernel.org/r/20201001141004.53846-1-alexandru.ardelean@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/dac/ad7303.c             |  2 --
 include/linux/platform_data/ad7303.h | 20 --------------------
 2 files changed, 22 deletions(-)
 delete mode 100644 include/linux/platform_data/ad7303.h

(limited to 'include/linux')

diff --git a/drivers/iio/dac/ad7303.c b/drivers/iio/dac/ad7303.c
index 2e46def9d8ee..dbb4645ab6b1 100644
--- a/drivers/iio/dac/ad7303.c
+++ b/drivers/iio/dac/ad7303.c
@@ -17,8 +17,6 @@
 #include <linux/iio/iio.h>
 #include <linux/iio/sysfs.h>
 
-#include <linux/platform_data/ad7303.h>
-
 #define AD7303_CFG_EXTERNAL_VREF BIT(15)
 #define AD7303_CFG_POWER_DOWN(ch) BIT(11 + (ch))
 #define AD7303_CFG_ADDR_OFFSET	10
diff --git a/include/linux/platform_data/ad7303.h b/include/linux/platform_data/ad7303.h
deleted file mode 100644
index c2bd0a13bea1..000000000000
--- a/include/linux/platform_data/ad7303.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Analog Devices AD7303 DAC driver
- *
- * Copyright 2013 Analog Devices Inc.
- */
-
-#ifndef __IIO_ADC_AD7303_H__
-#define __IIO_ADC_AD7303_H__
-
-/**
- * struct ad7303_platform_data - AD7303 platform data
- * @use_external_ref: If set to true use an external voltage reference connected
- * to the REF pin, otherwise use the internal reference derived from Vdd.
- */
-struct ad7303_platform_data {
-	bool use_external_ref;
-};
-
-#endif
-- 
cgit v1.2.3


From 9aa1206e8f48222f35a0c809f33b2f4aaa1e2661 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Sun, 11 Oct 2020 01:40:02 +0200
Subject: bpf: Add redirect_peer helper

Add an efficient ingress to ingress netns switch that can be used out of tc BPF
programs in order to redirect traffic from host ns ingress into a container
veth device ingress without having to go via CPU backlog queue [0]. For local
containers this can also be utilized and path via CPU backlog queue only needs
to be taken once, not twice. On a high level this borrows from ipvlan which does
similar switch in __netif_receive_skb_core() and then iterates via another_round.
This helps to reduce latency for mentioned use cases.

Pod to remote pod with redirect(), TCP_RR [1]:

  # percpu_netperf 10.217.1.33
          RT_LATENCY:         122.450         (per CPU:         122.666         122.401         122.333         122.401 )
        MEAN_LATENCY:         121.210         (per CPU:         121.100         121.260         121.320         121.160 )
      STDDEV_LATENCY:         120.040         (per CPU:         119.420         119.910         125.460         115.370 )
         MIN_LATENCY:          46.500         (per CPU:          47.000          47.000          47.000          45.000 )
         P50_LATENCY:         118.500         (per CPU:         118.000         119.000         118.000         119.000 )
         P90_LATENCY:         127.500         (per CPU:         127.000         128.000         127.000         128.000 )
         P99_LATENCY:         130.750         (per CPU:         131.000         131.000         129.000         132.000 )

    TRANSACTION_RATE:       32666.400         (per CPU:        8152.200        8169.842        8174.439        8169.897 )

Pod to remote pod with redirect_peer(), TCP_RR:

  # percpu_netperf 10.217.1.33
          RT_LATENCY:          44.449         (per CPU:          43.767          43.127          45.279          45.622 )
        MEAN_LATENCY:          45.065         (per CPU:          44.030          45.530          45.190          45.510 )
      STDDEV_LATENCY:          84.823         (per CPU:          66.770          97.290          84.380          90.850 )
         MIN_LATENCY:          33.500         (per CPU:          33.000          33.000          34.000          34.000 )
         P50_LATENCY:          43.250         (per CPU:          43.000          43.000          43.000          44.000 )
         P90_LATENCY:          46.750         (per CPU:          46.000          47.000          47.000          47.000 )
         P99_LATENCY:          52.750         (per CPU:          51.000          54.000          53.000          53.000 )

    TRANSACTION_RATE:       90039.500         (per CPU:       22848.186       23187.089       22085.077       21919.130 )

  [0] https://linuxplumbersconf.org/event/7/contributions/674/attachments/568/1002/plumbers_2020_cilium_load_balancer.pdf
  [1] https://github.com/borkmann/netperf_scripts/blob/master/percpu_netperf

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20201010234006.7075-3-daniel@iogearbox.net
---
 drivers/net/veth.c             |  9 +++++++
 include/linux/netdevice.h      |  4 ++++
 include/uapi/linux/bpf.h       | 17 +++++++++++++
 net/core/dev.c                 | 15 +++++++++---
 net/core/filter.c              | 54 ++++++++++++++++++++++++++++++++++++------
 tools/include/uapi/linux/bpf.h | 17 +++++++++++++
 6 files changed, 106 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 091e5b4ba042..8c737668008a 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -420,6 +420,14 @@ static int veth_select_rxq(struct net_device *dev)
 	return smp_processor_id() % dev->real_num_rx_queues;
 }
 
+static struct net_device *veth_peer_dev(struct net_device *dev)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+
+	/* Callers must be under RCU read side. */
+	return rcu_dereference(priv->peer);
+}
+
 static int veth_xdp_xmit(struct net_device *dev, int n,
 			 struct xdp_frame **frames,
 			 u32 flags, bool ndo_xmit)
@@ -1224,6 +1232,7 @@ static const struct net_device_ops veth_netdev_ops = {
 	.ndo_set_rx_headroom	= veth_set_rx_headroom,
 	.ndo_bpf		= veth_xdp,
 	.ndo_xdp_xmit		= veth_ndo_xdp_xmit,
+	.ndo_get_peer_dev	= veth_peer_dev,
 };
 
 #define VETH_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HW_CSUM | \
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 28cfa53daf72..0533f86018dd 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1277,6 +1277,9 @@ struct netdev_net_notifier {
  * int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm *p,
  *			 int cmd);
  *	Add, change, delete or get information on an IPv4 tunnel.
+ * struct net_device *(*ndo_get_peer_dev)(struct net_device *dev);
+ *	If a device is paired with a peer device, return the peer instance.
+ *	The caller must be under RCU read context.
  */
 struct net_device_ops {
 	int			(*ndo_init)(struct net_device *dev);
@@ -1484,6 +1487,7 @@ struct net_device_ops {
 	struct devlink_port *	(*ndo_get_devlink_port)(struct net_device *dev);
 	int			(*ndo_tunnel_ctl)(struct net_device *dev,
 						  struct ip_tunnel_parm *p, int cmd);
+	struct net_device *	(*ndo_get_peer_dev)(struct net_device *dev);
 };
 
 /**
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 4272cc53d478..b97bc5abb3b8 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3719,6 +3719,22 @@ union bpf_attr {
  *		never return NULL.
  *	Return
  *		A pointer pointing to the kernel percpu variable on this cpu.
+ *
+ * long bpf_redirect_peer(u32 ifindex, u64 flags)
+ * 	Description
+ * 		Redirect the packet to another net device of index *ifindex*.
+ * 		This helper is somewhat similar to **bpf_redirect**\ (), except
+ * 		that the redirection happens to the *ifindex*' peer device and
+ * 		the netns switch takes place from ingress to ingress without
+ * 		going through the CPU's backlog queue.
+ *
+ * 		The *flags* argument is reserved and must be 0. The helper is
+ * 		currently only supported for tc BPF program types at the ingress
+ * 		hook and for veth device types. The peer device must reside in a
+ * 		different network namespace.
+ * 	Return
+ * 		The helper returns **TC_ACT_REDIRECT** on success or
+ * 		**TC_ACT_SHOT** on error.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3876,6 +3892,7 @@ union bpf_attr {
 	FN(redirect_neigh),		\
 	FN(bpf_per_cpu_ptr),            \
 	FN(bpf_this_cpu_ptr),		\
+	FN(redirect_peer),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/net/core/dev.c b/net/core/dev.c
index 9d55bf5d1a65..7dd015823593 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4930,7 +4930,7 @@ EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook);
 
 static inline struct sk_buff *
 sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
-		   struct net_device *orig_dev)
+		   struct net_device *orig_dev, bool *another)
 {
 #ifdef CONFIG_NET_CLS_ACT
 	struct mini_Qdisc *miniq = rcu_dereference_bh(skb->dev->miniq_ingress);
@@ -4974,7 +4974,11 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
 		 * redirecting to another netdev
 		 */
 		__skb_push(skb, skb->mac_len);
-		skb_do_redirect(skb);
+		if (skb_do_redirect(skb) == -EAGAIN) {
+			__skb_pull(skb, skb->mac_len);
+			*another = true;
+			break;
+		}
 		return NULL;
 	case TC_ACT_CONSUMED:
 		return NULL;
@@ -5163,7 +5167,12 @@ another_round:
 skip_taps:
 #ifdef CONFIG_NET_INGRESS
 	if (static_branch_unlikely(&ingress_needed_key)) {
-		skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev);
+		bool another = false;
+
+		skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev,
+					 &another);
+		if (another)
+			goto another_round;
 		if (!skb)
 			goto out;
 
diff --git a/net/core/filter.c b/net/core/filter.c
index 5da44b11e1ec..fab951c6be57 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2380,8 +2380,9 @@ out:
 
 /* Internal, non-exposed redirect flags. */
 enum {
-	BPF_F_NEIGH = (1ULL << 1),
-#define BPF_F_REDIRECT_INTERNAL	(BPF_F_NEIGH)
+	BPF_F_NEIGH	= (1ULL << 1),
+	BPF_F_PEER	= (1ULL << 2),
+#define BPF_F_REDIRECT_INTERNAL	(BPF_F_NEIGH | BPF_F_PEER)
 };
 
 BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags)
@@ -2430,19 +2431,35 @@ EXPORT_PER_CPU_SYMBOL_GPL(bpf_redirect_info);
 int skb_do_redirect(struct sk_buff *skb)
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+	struct net *net = dev_net(skb->dev);
 	struct net_device *dev;
 	u32 flags = ri->flags;
 
-	dev = dev_get_by_index_rcu(dev_net(skb->dev), ri->tgt_index);
+	dev = dev_get_by_index_rcu(net, ri->tgt_index);
 	ri->tgt_index = 0;
-	if (unlikely(!dev)) {
-		kfree_skb(skb);
-		return -EINVAL;
+	ri->flags = 0;
+	if (unlikely(!dev))
+		goto out_drop;
+	if (flags & BPF_F_PEER) {
+		const struct net_device_ops *ops = dev->netdev_ops;
+
+		if (unlikely(!ops->ndo_get_peer_dev ||
+			     !skb_at_tc_ingress(skb)))
+			goto out_drop;
+		dev = ops->ndo_get_peer_dev(dev);
+		if (unlikely(!dev ||
+			     !is_skb_forwardable(dev, skb) ||
+			     net_eq(net, dev_net(dev))))
+			goto out_drop;
+		skb->dev = dev;
+		return -EAGAIN;
 	}
-
 	return flags & BPF_F_NEIGH ?
 	       __bpf_redirect_neigh(skb, dev) :
 	       __bpf_redirect(skb, dev, flags);
+out_drop:
+	kfree_skb(skb);
+	return -EINVAL;
 }
 
 BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags)
@@ -2466,6 +2483,27 @@ static const struct bpf_func_proto bpf_redirect_proto = {
 	.arg2_type      = ARG_ANYTHING,
 };
 
+BPF_CALL_2(bpf_redirect_peer, u32, ifindex, u64, flags)
+{
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+
+	if (unlikely(flags))
+		return TC_ACT_SHOT;
+
+	ri->flags = BPF_F_PEER;
+	ri->tgt_index = ifindex;
+
+	return TC_ACT_REDIRECT;
+}
+
+static const struct bpf_func_proto bpf_redirect_peer_proto = {
+	.func           = bpf_redirect_peer,
+	.gpl_only       = false,
+	.ret_type       = RET_INTEGER,
+	.arg1_type      = ARG_ANYTHING,
+	.arg2_type      = ARG_ANYTHING,
+};
+
 BPF_CALL_2(bpf_redirect_neigh, u32, ifindex, u64, flags)
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
@@ -7053,6 +7091,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_redirect_proto;
 	case BPF_FUNC_redirect_neigh:
 		return &bpf_redirect_neigh_proto;
+	case BPF_FUNC_redirect_peer:
+		return &bpf_redirect_peer_proto;
 	case BPF_FUNC_get_route_realm:
 		return &bpf_get_route_realm_proto;
 	case BPF_FUNC_get_hash_recalc:
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 4272cc53d478..b97bc5abb3b8 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3719,6 +3719,22 @@ union bpf_attr {
  *		never return NULL.
  *	Return
  *		A pointer pointing to the kernel percpu variable on this cpu.
+ *
+ * long bpf_redirect_peer(u32 ifindex, u64 flags)
+ * 	Description
+ * 		Redirect the packet to another net device of index *ifindex*.
+ * 		This helper is somewhat similar to **bpf_redirect**\ (), except
+ * 		that the redirection happens to the *ifindex*' peer device and
+ * 		the netns switch takes place from ingress to ingress without
+ * 		going through the CPU's backlog queue.
+ *
+ * 		The *flags* argument is reserved and must be 0. The helper is
+ * 		currently only supported for tc BPF program types at the ingress
+ * 		hook and for veth device types. The peer device must reside in a
+ * 		different network namespace.
+ * 	Return
+ * 		The helper returns **TC_ACT_REDIRECT** on success or
+ * 		**TC_ACT_SHOT** on error.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3876,6 +3892,7 @@ union bpf_attr {
 	FN(redirect_neigh),		\
 	FN(bpf_per_cpu_ptr),            \
 	FN(bpf_this_cpu_ptr),		\
+	FN(redirect_peer),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
-- 
cgit v1.2.3


From 4a8f87e60f6db40e640f1db555d063b2c4dea5f1 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Sun, 11 Oct 2020 01:40:03 +0200
Subject: bpf: Allow for map-in-map with dynamic inner array map entries

Recent work in f4d05259213f ("bpf: Add map_meta_equal map ops") and 134fede4eecf
("bpf: Relax max_entries check for most of the inner map types") added support
for dynamic inner max elements for most map-in-map types. Exceptions were maps
like array or prog array where the map_gen_lookup() callback uses the maps'
max_entries field as a constant when emitting instructions.

We recently implemented Maglev consistent hashing into Cilium's load balancer
which uses map-in-map with an outer map being hash and inner being array holding
the Maglev backend table for each service. This has been designed this way in
order to reduce overall memory consumption given the outer hash map allows to
avoid preallocating a large, flat memory area for all services. Also, the
number of service mappings is not always known a-priori.

The use case for dynamic inner array map entries is to further reduce memory
overhead, for example, some services might just have a small number of back
ends while others could have a large number. Right now the Maglev backend table
for small and large number of backends would need to have the same inner array
map entries which adds a lot of unneeded overhead.

Dynamic inner array map entries can be realized by avoiding the inlined code
generation for their lookup. The lookup will still be efficient since it will
be calling into array_map_lookup_elem() directly and thus avoiding retpoline.
The patch adds a BPF_F_INNER_MAP flag to map creation which therefore skips
inline code generation and relaxes array_map_meta_equal() check to ignore both
maps' max_entries. This also still allows to have faster lookups for map-in-map
when BPF_F_INNER_MAP is not specified and hence dynamic max_entries not needed.

Example code generation where inner map is dynamic sized array:

  # bpftool p d x i 125
  int handle__sys_enter(void * ctx):
  ; int handle__sys_enter(void *ctx)
     0: (b4) w1 = 0
  ; int key = 0;
     1: (63) *(u32 *)(r10 -4) = r1
     2: (bf) r2 = r10
  ;
     3: (07) r2 += -4
  ; inner_map = bpf_map_lookup_elem(&outer_arr_dyn, &key);
     4: (18) r1 = map[id:468]
     6: (07) r1 += 272
     7: (61) r0 = *(u32 *)(r2 +0)
     8: (35) if r0 >= 0x3 goto pc+5
     9: (67) r0 <<= 3
    10: (0f) r0 += r1
    11: (79) r0 = *(u64 *)(r0 +0)
    12: (15) if r0 == 0x0 goto pc+1
    13: (05) goto pc+1
    14: (b7) r0 = 0
    15: (b4) w6 = -1
  ; if (!inner_map)
    16: (15) if r0 == 0x0 goto pc+6
    17: (bf) r2 = r10
  ;
    18: (07) r2 += -4
  ; val = bpf_map_lookup_elem(inner_map, &key);
    19: (bf) r1 = r0                               | No inlining but instead
    20: (85) call array_map_lookup_elem#149280     | call to array_map_lookup_elem()
  ; return val ? *val : -1;                        | for inner array lookup.
    21: (15) if r0 == 0x0 goto pc+1
  ; return val ? *val : -1;
    22: (61) r6 = *(u32 *)(r0 +0)
  ; }
    23: (bc) w0 = w6
    24: (95) exit

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20201010234006.7075-4-daniel@iogearbox.net
---
 include/linux/bpf.h            |  2 +-
 include/uapi/linux/bpf.h       |  3 +++
 kernel/bpf/arraymap.c          | 17 +++++++++++------
 kernel/bpf/hashtab.c           |  6 +++---
 kernel/bpf/verifier.c          |  6 ++++--
 net/xdp/xskmap.c               |  2 +-
 tools/include/uapi/linux/bpf.h |  3 +++
 7 files changed, 26 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index dc63eeed4fd9..2b16bf48aab6 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -82,7 +82,7 @@ struct bpf_map_ops {
 	void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file,
 				int fd);
 	void (*map_fd_put_ptr)(void *ptr);
-	u32 (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf);
+	int (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf);
 	u32 (*map_fd_sys_lookup_elem)(void *ptr);
 	void (*map_seq_show_elem)(struct bpf_map *map, void *key,
 				  struct seq_file *m);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index b97bc5abb3b8..bf5a99d803e4 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -435,6 +435,9 @@ enum {
 
 /* Share perf_event among processes */
 	BPF_F_PRESERVE_ELEMS	= (1U << 11),
+
+/* Create a map that is suitable to be an inner map with dynamic max entries */
+	BPF_F_INNER_MAP		= (1U << 12),
 };
 
 /* Flags for BPF_PROG_QUERY. */
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index bd777dd6f967..c6c81eceb68f 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -16,7 +16,7 @@
 
 #define ARRAY_CREATE_FLAG_MASK \
 	(BPF_F_NUMA_NODE | BPF_F_MMAPABLE | BPF_F_ACCESS_MASK | \
-	 BPF_F_PRESERVE_ELEMS)
+	 BPF_F_PRESERVE_ELEMS | BPF_F_INNER_MAP)
 
 static void bpf_array_free_percpu(struct bpf_array *array)
 {
@@ -62,7 +62,7 @@ int array_map_alloc_check(union bpf_attr *attr)
 		return -EINVAL;
 
 	if (attr->map_type != BPF_MAP_TYPE_ARRAY &&
-	    attr->map_flags & BPF_F_MMAPABLE)
+	    attr->map_flags & (BPF_F_MMAPABLE | BPF_F_INNER_MAP))
 		return -EINVAL;
 
 	if (attr->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY &&
@@ -214,7 +214,7 @@ static int array_map_direct_value_meta(const struct bpf_map *map, u64 imm,
 }
 
 /* emit BPF instructions equivalent to C code of array_map_lookup_elem() */
-static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
+static int array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	struct bpf_insn *insn = insn_buf;
@@ -223,6 +223,9 @@ static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
 	const int map_ptr = BPF_REG_1;
 	const int index = BPF_REG_2;
 
+	if (map->map_flags & BPF_F_INNER_MAP)
+		return -EOPNOTSUPP;
+
 	*insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value));
 	*insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
 	if (!map->bypass_spec_v1) {
@@ -496,8 +499,10 @@ static int array_map_mmap(struct bpf_map *map, struct vm_area_struct *vma)
 static bool array_map_meta_equal(const struct bpf_map *meta0,
 				 const struct bpf_map *meta1)
 {
-	return meta0->max_entries == meta1->max_entries &&
-		bpf_map_meta_equal(meta0, meta1);
+	if (!bpf_map_meta_equal(meta0, meta1))
+		return false;
+	return meta0->map_flags & BPF_F_INNER_MAP ? true :
+	       meta0->max_entries == meta1->max_entries;
 }
 
 struct bpf_iter_seq_array_map_info {
@@ -1251,7 +1256,7 @@ static void *array_of_map_lookup_elem(struct bpf_map *map, void *key)
 	return READ_ONCE(*inner_map);
 }
 
-static u32 array_of_map_gen_lookup(struct bpf_map *map,
+static int array_of_map_gen_lookup(struct bpf_map *map,
 				   struct bpf_insn *insn_buf)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 3395cf140d22..1815e97d4c9c 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -612,7 +612,7 @@ static void *htab_map_lookup_elem(struct bpf_map *map, void *key)
  * bpf_prog
  *   __htab_map_lookup_elem
  */
-static u32 htab_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
+static int htab_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
 {
 	struct bpf_insn *insn = insn_buf;
 	const int ret = BPF_REG_0;
@@ -651,7 +651,7 @@ static void *htab_lru_map_lookup_elem_sys(struct bpf_map *map, void *key)
 	return __htab_lru_map_lookup_elem(map, key, false);
 }
 
-static u32 htab_lru_map_gen_lookup(struct bpf_map *map,
+static int htab_lru_map_gen_lookup(struct bpf_map *map,
 				   struct bpf_insn *insn_buf)
 {
 	struct bpf_insn *insn = insn_buf;
@@ -2070,7 +2070,7 @@ static void *htab_of_map_lookup_elem(struct bpf_map *map, void *key)
 	return READ_ONCE(*inner_map);
 }
 
-static u32 htab_of_map_gen_lookup(struct bpf_map *map,
+static int htab_of_map_gen_lookup(struct bpf_map *map,
 				  struct bpf_insn *insn_buf)
 {
 	struct bpf_insn *insn = insn_buf;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index f3e36eade3d4..fa5badc9279a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -11049,7 +11049,9 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 			if (insn->imm == BPF_FUNC_map_lookup_elem &&
 			    ops->map_gen_lookup) {
 				cnt = ops->map_gen_lookup(map_ptr, insn_buf);
-				if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) {
+				if (cnt == -EOPNOTSUPP)
+					goto patch_map_ops_generic;
+				if (cnt <= 0 || cnt >= ARRAY_SIZE(insn_buf)) {
 					verbose(env, "bpf verifier is misconfigured\n");
 					return -EINVAL;
 				}
@@ -11079,7 +11081,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 				     (int (*)(struct bpf_map *map, void *value))NULL));
 			BUILD_BUG_ON(!__same_type(ops->map_peek_elem,
 				     (int (*)(struct bpf_map *map, void *value))NULL));
-
+patch_map_ops_generic:
 			switch (insn->imm) {
 			case BPF_FUNC_map_lookup_elem:
 				insn->imm = BPF_CAST_CALL(ops->map_lookup_elem) -
diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c
index 0c5df593bc56..49da2b8ace8b 100644
--- a/net/xdp/xskmap.c
+++ b/net/xdp/xskmap.c
@@ -132,7 +132,7 @@ static int xsk_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
 	return 0;
 }
 
-static u32 xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
+static int xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
 {
 	const int ret = BPF_REG_0, mp = BPF_REG_1, index = BPF_REG_2;
 	struct bpf_insn *insn = insn_buf;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index b97bc5abb3b8..bf5a99d803e4 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -435,6 +435,9 @@ enum {
 
 /* Share perf_event among processes */
 	BPF_F_PRESERVE_ELEMS	= (1U << 11),
+
+/* Create a map that is suitable to be an inner map with dynamic max entries */
+	BPF_F_INNER_MAP		= (1U << 12),
 };
 
 /* Flags for BPF_PROG_QUERY. */
-- 
cgit v1.2.3


From ef5659280eb13e8ac31c296f58cfdfa1684ac06b Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Sat, 10 Oct 2020 22:09:38 -0700
Subject: bpf, sockmap: Allow skipping sk_skb parser program

Currently, we often run with a nop parser namely one that just does
this, 'return skb->len'. This happens when either our verdict program
can handle streaming data or it is only looking at socket data such
as IP addresses and other metadata associated with the flow. The second
case is common for a L3/L4 proxy for instance.

So lets allow loading programs without the parser then we can skip
the stream parser logic and avoid having to add a BPF program that
is effectively a nop.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/160239297866.8495.13345662302749219672.stgit@john-Precision-5820-Tower
---
 include/linux/skmsg.h |  2 ++
 net/core/skmsg.c      | 78 +++++++++++++++++++++++++++++++++++++++++++++++++++
 net/core/sock_map.c   | 22 ++++++++++-----
 3 files changed, 95 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 3119928fc103..fec0c5ac1c4f 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -308,6 +308,8 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node);
 int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock);
 void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock);
 void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock);
+void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock);
+void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock);
 
 int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock,
 			 struct sk_msg *msg);
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 881a5b290946..654182ecf87b 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -627,6 +627,8 @@ void sk_psock_drop(struct sock *sk, struct sk_psock *psock)
 	rcu_assign_sk_user_data(sk, NULL);
 	if (psock->progs.skb_parser)
 		sk_psock_stop_strp(sk, psock);
+	else if (psock->progs.skb_verdict)
+		sk_psock_stop_verdict(sk, psock);
 	write_unlock_bh(&sk->sk_callback_lock);
 	sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED);
 
@@ -871,6 +873,57 @@ static void sk_psock_strp_data_ready(struct sock *sk)
 	rcu_read_unlock();
 }
 
+static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb,
+				 unsigned int offset, size_t orig_len)
+{
+	struct sock *sk = (struct sock *)desc->arg.data;
+	struct sk_psock *psock;
+	struct bpf_prog *prog;
+	int ret = __SK_DROP;
+	int len = skb->len;
+
+	/* clone here so sk_eat_skb() in tcp_read_sock does not drop our data */
+	skb = skb_clone(skb, GFP_ATOMIC);
+	if (!skb) {
+		desc->error = -ENOMEM;
+		return 0;
+	}
+
+	rcu_read_lock();
+	psock = sk_psock(sk);
+	if (unlikely(!psock)) {
+		len = 0;
+		kfree_skb(skb);
+		goto out;
+	}
+	skb_set_owner_r(skb, sk);
+	prog = READ_ONCE(psock->progs.skb_verdict);
+	if (likely(prog)) {
+		tcp_skb_bpf_redirect_clear(skb);
+		ret = sk_psock_bpf_run(psock, prog, skb);
+		ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb));
+	}
+	sk_psock_verdict_apply(psock, skb, ret);
+out:
+	rcu_read_unlock();
+	return len;
+}
+
+static void sk_psock_verdict_data_ready(struct sock *sk)
+{
+	struct socket *sock = sk->sk_socket;
+	read_descriptor_t desc;
+
+	if (unlikely(!sock || !sock->ops || !sock->ops->read_sock))
+		return;
+
+	desc.arg.data = sk;
+	desc.error = 0;
+	desc.count = 1;
+
+	sock->ops->read_sock(sk, &desc, sk_psock_verdict_recv);
+}
+
 static void sk_psock_write_space(struct sock *sk)
 {
 	struct sk_psock *psock;
@@ -900,6 +953,19 @@ int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock)
 	return strp_init(&psock->parser.strp, sk, &cb);
 }
 
+void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock)
+{
+	struct sk_psock_parser *parser = &psock->parser;
+
+	if (parser->enabled)
+		return;
+
+	parser->saved_data_ready = sk->sk_data_ready;
+	sk->sk_data_ready = sk_psock_verdict_data_ready;
+	sk->sk_write_space = sk_psock_write_space;
+	parser->enabled = true;
+}
+
 void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock)
 {
 	struct sk_psock_parser *parser = &psock->parser;
@@ -925,3 +991,15 @@ void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock)
 	strp_stop(&parser->strp);
 	parser->enabled = false;
 }
+
+void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock)
+{
+	struct sk_psock_parser *parser = &psock->parser;
+
+	if (!parser->enabled)
+		return;
+
+	sk->sk_data_ready = parser->saved_data_ready;
+	parser->saved_data_ready = NULL;
+	parser->enabled = false;
+}
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index a2ed5b6223b9..df09c39a4dd2 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -148,8 +148,8 @@ static void sock_map_add_link(struct sk_psock *psock,
 static void sock_map_del_link(struct sock *sk,
 			      struct sk_psock *psock, void *link_raw)
 {
+	bool strp_stop = false, verdict_stop = false;
 	struct sk_psock_link *link, *tmp;
-	bool strp_stop = false;
 
 	spin_lock_bh(&psock->link_lock);
 	list_for_each_entry_safe(link, tmp, &psock->link, list) {
@@ -159,14 +159,19 @@ static void sock_map_del_link(struct sock *sk,
 							     map);
 			if (psock->parser.enabled && stab->progs.skb_parser)
 				strp_stop = true;
+			if (psock->parser.enabled && stab->progs.skb_verdict)
+				verdict_stop = true;
 			list_del(&link->list);
 			sk_psock_free_link(link);
 		}
 	}
 	spin_unlock_bh(&psock->link_lock);
-	if (strp_stop) {
+	if (strp_stop || verdict_stop) {
 		write_lock_bh(&sk->sk_callback_lock);
-		sk_psock_stop_strp(sk, psock);
+		if (strp_stop)
+			sk_psock_stop_strp(sk, psock);
+		else
+			sk_psock_stop_verdict(sk, psock);
 		write_unlock_bh(&sk->sk_callback_lock);
 	}
 }
@@ -288,16 +293,19 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs,
 	write_lock_bh(&sk->sk_callback_lock);
 	if (skb_parser && skb_verdict && !psock->parser.enabled) {
 		ret = sk_psock_init_strp(sk, psock);
-		if (ret) {
-			write_unlock_bh(&sk->sk_callback_lock);
-			goto out_drop;
-		}
+		if (ret)
+			goto out_unlock_drop;
 		psock_set_prog(&psock->progs.skb_verdict, skb_verdict);
 		psock_set_prog(&psock->progs.skb_parser, skb_parser);
 		sk_psock_start_strp(sk, psock);
+	} else if (!skb_parser && skb_verdict && !psock->parser.enabled) {
+		psock_set_prog(&psock->progs.skb_verdict, skb_verdict);
+		sk_psock_start_verdict(sk,psock);
 	}
 	write_unlock_bh(&sk->sk_callback_lock);
 	return 0;
+out_unlock_drop:
+	write_unlock_bh(&sk->sk_callback_lock);
 out_drop:
 	sk_psock_put(sk, psock);
 out_progs:
-- 
cgit v1.2.3


From f726f3d37163f714034aa5fd1f92a1a73df4297f Mon Sep 17 00:00:00 2001
From: Oliver Hartkopp <socketcan@hartkopp.net>
Date: Mon, 12 Oct 2020 09:43:54 +0200
Subject: can: remove obsolete version strings

As pointed out by Jakub Kicinski here:
http://lore.kernel.org/r/20201009175751.5c54097f@kicinski-fedora-pc1c0hjn.dhcp.thefacebook.com
this patch removes the obsolete version information of the different
CAN protocols and the AF_CAN core module.

Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Link: https://lore.kernel.org/r/20201012074354.25839-2-socketcan@hartkopp.net
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 include/linux/can/core.h |  7 -------
 include/net/netns/can.h  |  1 -
 net/can/af_can.c         |  2 +-
 net/can/bcm.c            |  4 +---
 net/can/gw.c             |  4 +---
 net/can/isotp.c          |  4 +---
 net/can/proc.c           | 12 ------------
 net/can/raw.c            |  4 +---
 8 files changed, 5 insertions(+), 33 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/can/core.h b/include/linux/can/core.h
index 7da9f1f82e8e..5fb8d0e3f9c1 100644
--- a/include/linux/can/core.h
+++ b/include/linux/can/core.h
@@ -18,13 +18,6 @@
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
 
-#define CAN_VERSION "20170425"
-
-/* increment this number each time you change some user-space interface */
-#define CAN_ABI_VERSION "9"
-
-#define CAN_VERSION_STRING "rev " CAN_VERSION " abi " CAN_ABI_VERSION
-
 #define DNAME(dev) ((dev) ? (dev)->name : "any")
 
 /**
diff --git a/include/net/netns/can.h b/include/net/netns/can.h
index b6ab7d1530d7..52fbd8291a96 100644
--- a/include/net/netns/can.h
+++ b/include/net/netns/can.h
@@ -15,7 +15,6 @@ struct can_rcv_lists_stats;
 struct netns_can {
 #if IS_ENABLED(CONFIG_PROC_FS)
 	struct proc_dir_entry *proc_dir;
-	struct proc_dir_entry *pde_version;
 	struct proc_dir_entry *pde_stats;
 	struct proc_dir_entry *pde_reset_stats;
 	struct proc_dir_entry *pde_rcvlist_all;
diff --git a/net/can/af_can.c b/net/can/af_can.c
index b7d0f6500893..6373ab9c5507 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -875,7 +875,7 @@ static __init int can_init(void)
 		     offsetof(struct can_frame, data) !=
 		     offsetof(struct canfd_frame, data));
 
-	pr_info("can: controller area network core (" CAN_VERSION_STRING ")\n");
+	pr_info("can: controller area network core\n");
 
 	rcv_cache = kmem_cache_create("can_receiver", sizeof(struct receiver),
 				      0, 0, NULL);
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 4253915800e6..0e5c37be4a2b 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -81,8 +81,6 @@
 		     (CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG) : \
 		     (CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG))
 
-#define CAN_BCM_VERSION "20170425"
-
 MODULE_DESCRIPTION("PF_CAN broadcast manager protocol");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Oliver Hartkopp <oliver.hartkopp@volkswagen.de>");
@@ -1696,7 +1694,7 @@ static int __init bcm_module_init(void)
 {
 	int err;
 
-	pr_info("can: broadcast manager protocol (rev " CAN_BCM_VERSION " t)\n");
+	pr_info("can: broadcast manager protocol\n");
 
 	err = can_proto_register(&bcm_can_proto);
 	if (err < 0) {
diff --git a/net/can/gw.c b/net/can/gw.c
index 49b4e3d91ad6..6b790b6ff8d2 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -59,7 +59,6 @@
 #include <net/net_namespace.h>
 #include <net/sock.h>
 
-#define CAN_GW_VERSION "20190810"
 #define CAN_GW_NAME "can-gw"
 
 MODULE_DESCRIPTION("PF_CAN netlink gateway");
@@ -1194,8 +1193,7 @@ static __init int cgw_module_init(void)
 	/* sanitize given module parameter */
 	max_hops = clamp_t(unsigned int, max_hops, CGW_MIN_HOPS, CGW_MAX_HOPS);
 
-	pr_info("can: netlink gateway (rev " CAN_GW_VERSION ") max_hops=%d\n",
-		max_hops);
+	pr_info("can: netlink gateway - max_hops=%d\n",	max_hops);
 
 	ret = register_pernet_subsys(&cangw_pernet_ops);
 	if (ret)
diff --git a/net/can/isotp.c b/net/can/isotp.c
index ca63061bb932..4c2062875893 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -72,8 +72,6 @@
 #include <net/sock.h>
 #include <net/net_namespace.h>
 
-#define CAN_ISOTP_VERSION "20200928"
-
 MODULE_DESCRIPTION("PF_CAN isotp 15765-2:2016 protocol");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Oliver Hartkopp <socketcan@hartkopp.net>");
@@ -1408,7 +1406,7 @@ static __init int isotp_module_init(void)
 {
 	int err;
 
-	pr_info("can: isotp protocol (rev " CAN_ISOTP_VERSION ")\n");
+	pr_info("can: isotp protocol\n");
 
 	err = can_proto_register(&isotp_can_proto);
 	if (err < 0)
diff --git a/net/can/proc.c b/net/can/proc.c
index a4eb06c9eb70..550928b8b8a2 100644
--- a/net/can/proc.c
+++ b/net/can/proc.c
@@ -54,7 +54,6 @@
  * proc filenames for the PF_CAN core
  */
 
-#define CAN_PROC_VERSION     "version"
 #define CAN_PROC_STATS       "stats"
 #define CAN_PROC_RESET_STATS "reset_stats"
 #define CAN_PROC_RCVLIST_ALL "rcvlist_all"
@@ -293,12 +292,6 @@ static int can_reset_stats_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int can_version_proc_show(struct seq_file *m, void *v)
-{
-	seq_printf(m, "%s\n", CAN_VERSION_STRING);
-	return 0;
-}
-
 static inline void can_rcvlist_proc_show_one(struct seq_file *m, int idx,
 					     struct net_device *dev,
 					     struct can_dev_rcv_lists *dev_rcv_lists)
@@ -441,8 +434,6 @@ void can_init_proc(struct net *net)
 	}
 
 	/* own procfs entries from the AF_CAN core */
-	net->can.pde_version = proc_create_net_single(CAN_PROC_VERSION, 0644,
-			net->can.proc_dir, can_version_proc_show, NULL);
 	net->can.pde_stats = proc_create_net_single(CAN_PROC_STATS, 0644,
 			net->can.proc_dir, can_stats_proc_show, NULL);
 	net->can.pde_reset_stats = proc_create_net_single(CAN_PROC_RESET_STATS,
@@ -471,9 +462,6 @@ void can_init_proc(struct net *net)
  */
 void can_remove_proc(struct net *net)
 {
-	if (net->can.pde_version)
-		remove_proc_entry(CAN_PROC_VERSION, net->can.proc_dir);
-
 	if (net->can.pde_stats)
 		remove_proc_entry(CAN_PROC_STATS, net->can.proc_dir);
 
diff --git a/net/can/raw.c b/net/can/raw.c
index ea70850f9152..6ec8aa1d0da4 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -55,8 +55,6 @@
 #include <net/sock.h>
 #include <net/net_namespace.h>
 
-#define CAN_RAW_VERSION CAN_VERSION
-
 MODULE_DESCRIPTION("PF_CAN raw protocol");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Urs Thuermann <urs.thuermann@volkswagen.de>");
@@ -885,7 +883,7 @@ static __init int raw_module_init(void)
 {
 	int err;
 
-	pr_info("can: raw protocol (rev " CAN_RAW_VERSION ")\n");
+	pr_info("can: raw protocol\n");
 
 	err = can_proto_register(&raw_can_proto);
 	if (err < 0)
-- 
cgit v1.2.3


From 585834a5eeb38a9b290786b6d3ee55f22098c602 Mon Sep 17 00:00:00 2001
From: zhuguangqing <zhuguangqing@xiaomi.com>
Date: Thu, 17 Sep 2020 15:35:53 +0800
Subject: thermal/idle_inject: Fix comment of idle_duration_us and name of
 latency_ns

The comment of idle_duration_us and the name of latency_ns can be misleading,
so fix them.

Signed-off-by: zhuguangqing <zhuguangqing@xiaomi.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Link: https://lore.kernel.org/r/20200917073553.898-1-zhuguangqing83@gmail.com
---
 drivers/thermal/cpuidle_cooling.c | 2 +-
 include/linux/idle_inject.h       | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/thermal/cpuidle_cooling.c b/drivers/thermal/cpuidle_cooling.c
index 78e3e8238116..7ecab4b16b29 100644
--- a/drivers/thermal/cpuidle_cooling.c
+++ b/drivers/thermal/cpuidle_cooling.c
@@ -30,7 +30,7 @@ static DEFINE_IDA(cpuidle_ida);
 
 /**
  * cpuidle_cooling_runtime - Running time computation
- * @idle_duration_us: the idle cooling device
+ * @idle_duration_us: CPU idle time to inject in microseconds
  * @state: a percentile based number
  *
  * The running duration is computed from the idle injection duration
diff --git a/include/linux/idle_inject.h b/include/linux/idle_inject.h
index 91a8612b8bf9..fb88e23a99d3 100644
--- a/include/linux/idle_inject.h
+++ b/include/linux/idle_inject.h
@@ -28,6 +28,6 @@ void idle_inject_get_duration(struct idle_inject_device *ii_dev,
 				 unsigned int *idle_duration_us);
 
 void idle_inject_set_latency(struct idle_inject_device *ii_dev,
-			     unsigned int latency_ns);
+			     unsigned int latency_us);
 
 #endif /* __IDLE_INJECT_H__ */
-- 
cgit v1.2.3


From 88052319620a35f827509d645e4c8063ded751c8 Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Tue, 15 Sep 2020 15:36:49 -0700
Subject: thermal: core: Add new event for sending keep alive notifications

This event is sent by the platform firmware to confirm that
user space thermal solution is alive. The response to this event
from the user space thermal solution is platform specific.

Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Link: https://lore.kernel.org/r/20200915223650.406046-3-srinivas.pandruvada@linux.intel.com
---
 include/linux/thermal.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 42ef807e5d84..42b69d4072a4 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -55,6 +55,7 @@ enum thermal_notify_event {
 	THERMAL_DEVICE_UP, /* Thermal device is up after a down event */
 	THERMAL_DEVICE_POWER_CAPABILITY_CHANGED, /* power capability changed */
 	THERMAL_TABLE_CHANGED, /* Thermal table(s) changed */
+	THERMAL_EVENT_KEEP_ALIVE, /* Request for user space handler to respond */
 };
 
 struct thermal_zone_device_ops {
-- 
cgit v1.2.3


From ecd1d2a3e4f893584578a304d7bd1591e895a8e4 Mon Sep 17 00:00:00 2001
From: zhuguangqing <zhuguangqing@xiaomi.com>
Date: Mon, 14 Sep 2020 15:11:01 +0800
Subject: thermal: cooling: Remove unused variable *tz

1. devfreq_cooling.c: The variable *tz is not used in
devfreq_cooling_get_requested_power(), devfreq_cooling_state2power()
and devfreq_cooling_power2state().

2. cpufreq_cooling.c: After 84fe2cab48590, the variable *tz is not used
anymore in cpufreq_get_requested_power(), cpufreq_state2power() and
cpufreq_power2state().

Remove the variable *tz.

Signed-off-by: zhuguangqing <zhuguangqing@xiaomi.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Link: https://lore.kernel.org/r/20200914071101.13575-1-zhuguangqing83@gmail.com
---
 drivers/thermal/cpufreq_cooling.c     |  8 +-------
 drivers/thermal/devfreq_cooling.c     |  3 ---
 drivers/thermal/gov_power_allocator.c |  6 +++---
 drivers/thermal/thermal_core.c        | 12 +++++-------
 drivers/thermal/thermal_core.h        |  4 ++--
 include/linux/thermal.h               |  9 +++------
 6 files changed, 14 insertions(+), 28 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/thermal/cpufreq_cooling.c b/drivers/thermal/cpufreq_cooling.c
index 6cf23a54e853..cc2959f22f01 100644
--- a/drivers/thermal/cpufreq_cooling.c
+++ b/drivers/thermal/cpufreq_cooling.c
@@ -182,7 +182,6 @@ static u32 get_dynamic_power(struct cpufreq_cooling_device *cpufreq_cdev,
 /**
  * cpufreq_get_requested_power() - get the current power
  * @cdev:	&thermal_cooling_device pointer
- * @tz:		a valid thermal zone device pointer
  * @power:	pointer in which to store the resulting power
  *
  * Calculate the current power consumption of the cpus in milliwatts
@@ -203,7 +202,6 @@ static u32 get_dynamic_power(struct cpufreq_cooling_device *cpufreq_cdev,
  * Return: 0 on success, -E* if getting the static power failed.
  */
 static int cpufreq_get_requested_power(struct thermal_cooling_device *cdev,
-				       struct thermal_zone_device *tz,
 				       u32 *power)
 {
 	unsigned long freq;
@@ -253,7 +251,6 @@ static int cpufreq_get_requested_power(struct thermal_cooling_device *cdev,
 /**
  * cpufreq_state2power() - convert a cpu cdev state to power consumed
  * @cdev:	&thermal_cooling_device pointer
- * @tz:		a valid thermal zone device pointer
  * @state:	cooling device state to be converted
  * @power:	pointer in which to store the resulting power
  *
@@ -266,7 +263,6 @@ static int cpufreq_get_requested_power(struct thermal_cooling_device *cdev,
  * when calculating the static power.
  */
 static int cpufreq_state2power(struct thermal_cooling_device *cdev,
-			       struct thermal_zone_device *tz,
 			       unsigned long state, u32 *power)
 {
 	unsigned int freq, num_cpus, idx;
@@ -288,7 +284,6 @@ static int cpufreq_state2power(struct thermal_cooling_device *cdev,
 /**
  * cpufreq_power2state() - convert power to a cooling device state
  * @cdev:	&thermal_cooling_device pointer
- * @tz:		a valid thermal zone device pointer
  * @power:	power in milliwatts to be converted
  * @state:	pointer in which to store the resulting state
  *
@@ -306,8 +301,7 @@ static int cpufreq_state2power(struct thermal_cooling_device *cdev,
  * device.
  */
 static int cpufreq_power2state(struct thermal_cooling_device *cdev,
-			       struct thermal_zone_device *tz, u32 power,
-			       unsigned long *state)
+			       u32 power, unsigned long *state)
 {
 	unsigned int target_freq;
 	u32 last_load, normalised_power;
diff --git a/drivers/thermal/devfreq_cooling.c b/drivers/thermal/devfreq_cooling.c
index a12d29096229..dfab49a67252 100644
--- a/drivers/thermal/devfreq_cooling.c
+++ b/drivers/thermal/devfreq_cooling.c
@@ -229,7 +229,6 @@ static inline unsigned long get_total_power(struct devfreq_cooling_device *dfc,
 
 
 static int devfreq_cooling_get_requested_power(struct thermal_cooling_device *cdev,
-					       struct thermal_zone_device *tz,
 					       u32 *power)
 {
 	struct devfreq_cooling_device *dfc = cdev->devdata;
@@ -289,7 +288,6 @@ fail:
 }
 
 static int devfreq_cooling_state2power(struct thermal_cooling_device *cdev,
-				       struct thermal_zone_device *tz,
 				       unsigned long state,
 				       u32 *power)
 {
@@ -308,7 +306,6 @@ static int devfreq_cooling_state2power(struct thermal_cooling_device *cdev,
 }
 
 static int devfreq_cooling_power2state(struct thermal_cooling_device *cdev,
-				       struct thermal_zone_device *tz,
 				       u32 power, unsigned long *state)
 {
 	struct devfreq_cooling_device *dfc = cdev->devdata;
diff --git a/drivers/thermal/gov_power_allocator.c b/drivers/thermal/gov_power_allocator.c
index 5cb518d8f156..ab0be26f0816 100644
--- a/drivers/thermal/gov_power_allocator.c
+++ b/drivers/thermal/gov_power_allocator.c
@@ -96,7 +96,7 @@ static u32 estimate_sustainable_power(struct thermal_zone_device *tz)
 		if (instance->trip != params->trip_max_desired_temperature)
 			continue;
 
-		if (power_actor_get_min_power(cdev, tz, &min_power))
+		if (power_actor_get_min_power(cdev, &min_power))
 			continue;
 
 		sustainable_power += min_power;
@@ -388,7 +388,7 @@ static int allocate_power(struct thermal_zone_device *tz,
 		if (!cdev_is_power_actor(cdev))
 			continue;
 
-		if (cdev->ops->get_requested_power(cdev, tz, &req_power[i]))
+		if (cdev->ops->get_requested_power(cdev, &req_power[i]))
 			continue;
 
 		if (!total_weight)
@@ -398,7 +398,7 @@ static int allocate_power(struct thermal_zone_device *tz,
 
 		weighted_req_power[i] = frac_to_int(weight * req_power[i]);
 
-		if (power_actor_get_max_power(cdev, tz, &max_power[i]))
+		if (power_actor_get_max_power(cdev, &max_power[i]))
 			continue;
 
 		total_req_power += req_power[i];
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 49ae4a61cbe6..c6d74bc1c90b 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -603,7 +603,6 @@ static void thermal_zone_device_check(struct work_struct *work)
 /**
  * power_actor_get_max_power() - get the maximum power that a cdev can consume
  * @cdev:	pointer to &thermal_cooling_device
- * @tz:		a valid thermal zone device pointer
  * @max_power:	pointer in which to store the maximum power
  *
  * Calculate the maximum power consumption in milliwats that the
@@ -613,18 +612,17 @@ static void thermal_zone_device_check(struct work_struct *work)
  * power_actor API or -E* on other error.
  */
 int power_actor_get_max_power(struct thermal_cooling_device *cdev,
-			      struct thermal_zone_device *tz, u32 *max_power)
+			      u32 *max_power)
 {
 	if (!cdev_is_power_actor(cdev))
 		return -EINVAL;
 
-	return cdev->ops->state2power(cdev, tz, 0, max_power);
+	return cdev->ops->state2power(cdev, 0, max_power);
 }
 
 /**
  * power_actor_get_min_power() - get the mainimum power that a cdev can consume
  * @cdev:	pointer to &thermal_cooling_device
- * @tz:		a valid thermal zone device pointer
  * @min_power:	pointer in which to store the minimum power
  *
  * Calculate the minimum power consumption in milliwatts that the
@@ -634,7 +632,7 @@ int power_actor_get_max_power(struct thermal_cooling_device *cdev,
  * power_actor API or -E* on other error.
  */
 int power_actor_get_min_power(struct thermal_cooling_device *cdev,
-			      struct thermal_zone_device *tz, u32 *min_power)
+			      u32 *min_power)
 {
 	unsigned long max_state;
 	int ret;
@@ -646,7 +644,7 @@ int power_actor_get_min_power(struct thermal_cooling_device *cdev,
 	if (ret)
 		return ret;
 
-	return cdev->ops->state2power(cdev, tz, max_state, min_power);
+	return cdev->ops->state2power(cdev, max_state, min_power);
 }
 
 /**
@@ -670,7 +668,7 @@ int power_actor_set_power(struct thermal_cooling_device *cdev,
 	if (!cdev_is_power_actor(cdev))
 		return -EINVAL;
 
-	ret = cdev->ops->power2state(cdev, instance->tz, power, &state);
+	ret = cdev->ops->power2state(cdev, power, &state);
 	if (ret)
 		return ret;
 
diff --git a/drivers/thermal/thermal_core.h b/drivers/thermal/thermal_core.h
index e00fc5585ea8..764c2de31771 100644
--- a/drivers/thermal/thermal_core.h
+++ b/drivers/thermal/thermal_core.h
@@ -66,9 +66,9 @@ static inline bool cdev_is_power_actor(struct thermal_cooling_device *cdev)
 }
 
 int power_actor_get_max_power(struct thermal_cooling_device *cdev,
-			      struct thermal_zone_device *tz, u32 *max_power);
+			      u32 *max_power);
 int power_actor_get_min_power(struct thermal_cooling_device *cdev,
-			      struct thermal_zone_device *tz, u32 *min_power);
+			      u32 *min_power);
 int power_actor_set_power(struct thermal_cooling_device *cdev,
 			  struct thermal_instance *ti, u32 power);
 /**
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 42b69d4072a4..d07ea27e72a9 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -85,12 +85,9 @@ struct thermal_cooling_device_ops {
 	int (*get_max_state) (struct thermal_cooling_device *, unsigned long *);
 	int (*get_cur_state) (struct thermal_cooling_device *, unsigned long *);
 	int (*set_cur_state) (struct thermal_cooling_device *, unsigned long);
-	int (*get_requested_power)(struct thermal_cooling_device *,
-				   struct thermal_zone_device *, u32 *);
-	int (*state2power)(struct thermal_cooling_device *,
-			   struct thermal_zone_device *, unsigned long, u32 *);
-	int (*power2state)(struct thermal_cooling_device *,
-			   struct thermal_zone_device *, u32, unsigned long *);
+	int (*get_requested_power)(struct thermal_cooling_device *, u32 *);
+	int (*state2power)(struct thermal_cooling_device *, unsigned long, u32 *);
+	int (*power2state)(struct thermal_cooling_device *, u32, unsigned long *);
 };
 
 struct thermal_cooling_device {
-- 
cgit v1.2.3


From 3986f9a42e993075af01c17dc8968cfb96a4fe53 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Mon, 17 Aug 2020 13:45:04 +0200
Subject: libceph: multiple workspaces for CRUSH computations

Replace a global map->crush_workspace (protected by a global mutex)
with a list of workspaces, up to the number of CPUs + 1.

This is based on a patch from Robin Geuze <robing@nl.team.blue>.
Robin and his team have observed a 10-20% increase in IOPS on all
queue depths and lower CPU usage as well on a high-end all-NVMe
100GbE cluster.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/osdmap.h |  14 +++-
 include/linux/crush/crush.h |   3 +
 net/ceph/osdmap.c           | 166 ++++++++++++++++++++++++++++++++++++++++----
 3 files changed, 166 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index 3f4498fef6ad..cad9acfbc320 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -137,6 +137,17 @@ int ceph_oid_aprintf(struct ceph_object_id *oid, gfp_t gfp,
 		     const char *fmt, ...);
 void ceph_oid_destroy(struct ceph_object_id *oid);
 
+struct workspace_manager {
+	struct list_head idle_ws;
+	spinlock_t ws_lock;
+	/* Number of free workspaces */
+	int free_ws;
+	/* Total number of allocated workspaces */
+	atomic_t total_ws;
+	/* Waiters for a free workspace */
+	wait_queue_head_t ws_wait;
+};
+
 struct ceph_pg_mapping {
 	struct rb_node node;
 	struct ceph_pg pgid;
@@ -184,8 +195,7 @@ struct ceph_osdmap {
 	 * the list of osds that store+replicate them. */
 	struct crush_map *crush;
 
-	struct mutex crush_workspace_mutex;
-	void *crush_workspace;
+	struct workspace_manager crush_wsm;
 };
 
 static inline bool ceph_osd_exists(struct ceph_osdmap *map, int osd)
diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h
index 2f811baf78d2..30dba392b730 100644
--- a/include/linux/crush/crush.h
+++ b/include/linux/crush/crush.h
@@ -346,6 +346,9 @@ struct crush_work_bucket {
 
 struct crush_work {
 	struct crush_work_bucket **work; /* Per-bucket working store */
+#ifdef __KERNEL__
+	struct list_head item;
+#endif
 };
 
 #ifdef __KERNEL__
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 96c25f5e064a..fa08c15be0c0 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -964,6 +964,143 @@ bad:
 	return -EINVAL;
 }
 
+/*
+ * CRUSH workspaces
+ *
+ * workspace_manager framework borrowed from fs/btrfs/compression.c.
+ * Two simplifications: there is only one type of workspace and there
+ * is always at least one workspace.
+ */
+static struct crush_work *alloc_workspace(const struct crush_map *c)
+{
+	struct crush_work *work;
+	size_t work_size;
+
+	WARN_ON(!c->working_size);
+	work_size = crush_work_size(c, CEPH_PG_MAX_SIZE);
+	dout("%s work_size %zu bytes\n", __func__, work_size);
+
+	work = ceph_kvmalloc(work_size, GFP_NOIO);
+	if (!work)
+		return NULL;
+
+	INIT_LIST_HEAD(&work->item);
+	crush_init_workspace(c, work);
+	return work;
+}
+
+static void free_workspace(struct crush_work *work)
+{
+	WARN_ON(!list_empty(&work->item));
+	kvfree(work);
+}
+
+static void init_workspace_manager(struct workspace_manager *wsm)
+{
+	INIT_LIST_HEAD(&wsm->idle_ws);
+	spin_lock_init(&wsm->ws_lock);
+	atomic_set(&wsm->total_ws, 0);
+	wsm->free_ws = 0;
+	init_waitqueue_head(&wsm->ws_wait);
+}
+
+static void add_initial_workspace(struct workspace_manager *wsm,
+				  struct crush_work *work)
+{
+	WARN_ON(!list_empty(&wsm->idle_ws));
+
+	list_add(&work->item, &wsm->idle_ws);
+	atomic_set(&wsm->total_ws, 1);
+	wsm->free_ws = 1;
+}
+
+static void cleanup_workspace_manager(struct workspace_manager *wsm)
+{
+	struct crush_work *work;
+
+	while (!list_empty(&wsm->idle_ws)) {
+		work = list_first_entry(&wsm->idle_ws, struct crush_work,
+					item);
+		list_del_init(&work->item);
+		free_workspace(work);
+	}
+	atomic_set(&wsm->total_ws, 0);
+	wsm->free_ws = 0;
+}
+
+/*
+ * Finds an available workspace or allocates a new one.  If it's not
+ * possible to allocate a new one, waits until there is one.
+ */
+static struct crush_work *get_workspace(struct workspace_manager *wsm,
+					const struct crush_map *c)
+{
+	struct crush_work *work;
+	int cpus = num_online_cpus();
+
+again:
+	spin_lock(&wsm->ws_lock);
+	if (!list_empty(&wsm->idle_ws)) {
+		work = list_first_entry(&wsm->idle_ws, struct crush_work,
+					item);
+		list_del_init(&work->item);
+		wsm->free_ws--;
+		spin_unlock(&wsm->ws_lock);
+		return work;
+
+	}
+	if (atomic_read(&wsm->total_ws) > cpus) {
+		DEFINE_WAIT(wait);
+
+		spin_unlock(&wsm->ws_lock);
+		prepare_to_wait(&wsm->ws_wait, &wait, TASK_UNINTERRUPTIBLE);
+		if (atomic_read(&wsm->total_ws) > cpus && !wsm->free_ws)
+			schedule();
+		finish_wait(&wsm->ws_wait, &wait);
+		goto again;
+	}
+	atomic_inc(&wsm->total_ws);
+	spin_unlock(&wsm->ws_lock);
+
+	work = alloc_workspace(c);
+	if (!work) {
+		atomic_dec(&wsm->total_ws);
+		wake_up(&wsm->ws_wait);
+
+		/*
+		 * Do not return the error but go back to waiting.  We
+		 * have the inital workspace and the CRUSH computation
+		 * time is bounded so we will get it eventually.
+		 */
+		WARN_ON(atomic_read(&wsm->total_ws) < 1);
+		goto again;
+	}
+	return work;
+}
+
+/*
+ * Puts a workspace back on the list or frees it if we have enough
+ * idle ones sitting around.
+ */
+static void put_workspace(struct workspace_manager *wsm,
+			  struct crush_work *work)
+{
+	spin_lock(&wsm->ws_lock);
+	if (wsm->free_ws <= num_online_cpus()) {
+		list_add(&work->item, &wsm->idle_ws);
+		wsm->free_ws++;
+		spin_unlock(&wsm->ws_lock);
+		goto wake;
+	}
+	spin_unlock(&wsm->ws_lock);
+
+	free_workspace(work);
+	atomic_dec(&wsm->total_ws);
+wake:
+	if (wq_has_sleeper(&wsm->ws_wait))
+		wake_up(&wsm->ws_wait);
+}
+
 /*
  * osd map
  */
@@ -981,7 +1118,8 @@ struct ceph_osdmap *ceph_osdmap_alloc(void)
 	map->primary_temp = RB_ROOT;
 	map->pg_upmap = RB_ROOT;
 	map->pg_upmap_items = RB_ROOT;
-	mutex_init(&map->crush_workspace_mutex);
+
+	init_workspace_manager(&map->crush_wsm);
 
 	return map;
 }
@@ -989,8 +1127,11 @@ struct ceph_osdmap *ceph_osdmap_alloc(void)
 void ceph_osdmap_destroy(struct ceph_osdmap *map)
 {
 	dout("osdmap_destroy %p\n", map);
+
 	if (map->crush)
 		crush_destroy(map->crush);
+	cleanup_workspace_manager(&map->crush_wsm);
+
 	while (!RB_EMPTY_ROOT(&map->pg_temp)) {
 		struct ceph_pg_mapping *pg =
 			rb_entry(rb_first(&map->pg_temp),
@@ -1029,7 +1170,6 @@ void ceph_osdmap_destroy(struct ceph_osdmap *map)
 	kvfree(map->osd_weight);
 	kvfree(map->osd_addr);
 	kvfree(map->osd_primary_affinity);
-	kvfree(map->crush_workspace);
 	kfree(map);
 }
 
@@ -1104,26 +1244,22 @@ static int osdmap_set_max_osd(struct ceph_osdmap *map, u32 max)
 
 static int osdmap_set_crush(struct ceph_osdmap *map, struct crush_map *crush)
 {
-	void *workspace;
-	size_t work_size;
+	struct crush_work *work;
 
 	if (IS_ERR(crush))
 		return PTR_ERR(crush);
 
-	work_size = crush_work_size(crush, CEPH_PG_MAX_SIZE);
-	dout("%s work_size %zu bytes\n", __func__, work_size);
-	workspace = ceph_kvmalloc(work_size, GFP_NOIO);
-	if (!workspace) {
+	work = alloc_workspace(crush);
+	if (!work) {
 		crush_destroy(crush);
 		return -ENOMEM;
 	}
-	crush_init_workspace(crush, workspace);
 
 	if (map->crush)
 		crush_destroy(map->crush);
-	kvfree(map->crush_workspace);
+	cleanup_workspace_manager(&map->crush_wsm);
 	map->crush = crush;
-	map->crush_workspace = workspace;
+	add_initial_workspace(&map->crush_wsm, work);
 	return 0;
 }
 
@@ -2322,6 +2458,7 @@ static int do_crush(struct ceph_osdmap *map, int ruleno, int x,
 		    s64 choose_args_index)
 {
 	struct crush_choose_arg_map *arg_map;
+	struct crush_work *work;
 	int r;
 
 	BUG_ON(result_max > CEPH_PG_MAX_SIZE);
@@ -2332,12 +2469,11 @@ static int do_crush(struct ceph_osdmap *map, int ruleno, int x,
 		arg_map = lookup_choose_arg_map(&map->crush->choose_args,
 						CEPH_DEFAULT_CHOOSE_ARGS);
 
-	mutex_lock(&map->crush_workspace_mutex);
+	work = get_workspace(&map->crush_wsm, map->crush);
 	r = crush_do_rule(map->crush, ruleno, x, result, result_max,
-			  weight, weight_max, map->crush_workspace,
+			  weight, weight_max, work,
 			  arg_map ? arg_map->args : NULL);
-	mutex_unlock(&map->crush_workspace_mutex);
-
+	put_workspace(&map->crush_wsm, work);
 	return r;
 }
 
-- 
cgit v1.2.3


From 0b98acd6188309333c3a8a6e16feadadd31e4523 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Mon, 14 Sep 2020 13:39:19 +0200
Subject: libceph, rbd, ceph: "blacklist" -> "blocklist"

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 Documentation/filesystems/ceph.rst |  6 +++---
 drivers/block/rbd.c                |  8 ++++----
 fs/ceph/addr.c                     | 24 ++++++++++++------------
 fs/ceph/file.c                     |  4 ++--
 fs/ceph/mds_client.c               | 16 ++++++++--------
 fs/ceph/super.c                    |  4 ++--
 fs/ceph/super.h                    |  4 ++--
 include/linux/ceph/mon_client.h    |  2 +-
 include/linux/ceph/rados.h         |  2 +-
 net/ceph/mon_client.c              |  8 ++++----
 10 files changed, 39 insertions(+), 39 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/ceph.rst b/Documentation/filesystems/ceph.rst
index 0aa70750df0f..7d2ef4e27273 100644
--- a/Documentation/filesystems/ceph.rst
+++ b/Documentation/filesystems/ceph.rst
@@ -163,14 +163,14 @@ Mount Options
         to the default VFS implementation if this option is used.
 
   recover_session=<no|clean>
-	Set auto reconnect mode in the case where the client is blacklisted. The
+	Set auto reconnect mode in the case where the client is blocklisted. The
 	available modes are "no" and "clean". The default is "no".
 
 	* no: never attempt to reconnect when client detects that it has been
-	  blacklisted. Operations will generally fail after being blacklisted.
+	  blocklisted. Operations will generally fail after being blocklisted.
 
 	* clean: client reconnects to the ceph cluster automatically when it
-	  detects that it has been blacklisted. During reconnect, client drops
+	  detects that it has been blocklisted. During reconnect, client drops
 	  dirty data/metadata, invalidates page caches and writable file handles.
 	  After reconnect, file locks become stale because the MDS loses track
 	  of them. If an inode contains any stale file locks, read/write on the
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index e77eaab5cf23..bdd33bcf11b1 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -4010,10 +4010,10 @@ static int rbd_try_lock(struct rbd_device *rbd_dev)
 		rbd_warn(rbd_dev, "breaking header lock owned by %s%llu",
 			 ENTITY_NAME(lockers[0].id.name));
 
-		ret = ceph_monc_blacklist_add(&client->monc,
+		ret = ceph_monc_blocklist_add(&client->monc,
 					      &lockers[0].info.addr);
 		if (ret) {
-			rbd_warn(rbd_dev, "blacklist of %s%llu failed: %d",
+			rbd_warn(rbd_dev, "blocklist of %s%llu failed: %d",
 				 ENTITY_NAME(lockers[0].id.name), ret);
 			goto out;
 		}
@@ -4077,7 +4077,7 @@ static int rbd_try_acquire_lock(struct rbd_device *rbd_dev)
 	ret = rbd_try_lock(rbd_dev);
 	if (ret < 0) {
 		rbd_warn(rbd_dev, "failed to lock header: %d", ret);
-		if (ret == -EBLACKLISTED)
+		if (ret == -EBLOCKLISTED)
 			goto out;
 
 		ret = 1; /* request lock anyway */
@@ -4613,7 +4613,7 @@ static void rbd_reregister_watch(struct work_struct *work)
 	ret = __rbd_register_watch(rbd_dev);
 	if (ret) {
 		rbd_warn(rbd_dev, "failed to reregister watch: %d", ret);
-		if (ret != -EBLACKLISTED && ret != -ENOENT) {
+		if (ret != -EBLOCKLISTED && ret != -ENOENT) {
 			queue_delayed_work(rbd_dev->task_wq,
 					   &rbd_dev->watch_dwork,
 					   RBD_RETRY_DELAY);
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index b03dbaa9d345..7b1f3dad576f 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -271,8 +271,8 @@ static int ceph_do_readpage(struct file *filp, struct page *page)
 	if (err < 0) {
 		SetPageError(page);
 		ceph_fscache_readpage_cancel(inode, page);
-		if (err == -EBLACKLISTED)
-			fsc->blacklisted = true;
+		if (err == -EBLOCKLISTED)
+			fsc->blocklisted = true;
 		goto out;
 	}
 	if (err < PAGE_SIZE)
@@ -312,8 +312,8 @@ static void finish_read(struct ceph_osd_request *req)
 	int i;
 
 	dout("finish_read %p req %p rc %d bytes %d\n", inode, req, rc, bytes);
-	if (rc == -EBLACKLISTED)
-		ceph_inode_to_client(inode)->blacklisted = true;
+	if (rc == -EBLOCKLISTED)
+		ceph_inode_to_client(inode)->blocklisted = true;
 
 	/* unlock all pages, zeroing any data we didn't read */
 	osd_data = osd_req_op_extent_osd_data(req, 0);
@@ -737,8 +737,8 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 			end_page_writeback(page);
 			return err;
 		}
-		if (err == -EBLACKLISTED)
-			fsc->blacklisted = true;
+		if (err == -EBLOCKLISTED)
+			fsc->blocklisted = true;
 		dout("writepage setting page/mapping error %d %p\n",
 		     err, page);
 		mapping_set_error(&inode->i_data, err);
@@ -801,8 +801,8 @@ static void writepages_finish(struct ceph_osd_request *req)
 	if (rc < 0) {
 		mapping_set_error(mapping, rc);
 		ceph_set_error_write(ci);
-		if (rc == -EBLACKLISTED)
-			fsc->blacklisted = true;
+		if (rc == -EBLOCKLISTED)
+			fsc->blocklisted = true;
 	} else {
 		ceph_clear_error_write(ci);
 	}
@@ -2038,16 +2038,16 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci,
 	if (err >= 0 || err == -ENOENT)
 		have |= POOL_READ;
 	else if (err != -EPERM) {
-		if (err == -EBLACKLISTED)
-			fsc->blacklisted = true;
+		if (err == -EBLOCKLISTED)
+			fsc->blocklisted = true;
 		goto out_unlock;
 	}
 
 	if (err2 == 0 || err2 == -EEXIST)
 		have |= POOL_WRITE;
 	else if (err2 != -EPERM) {
-		if (err2 == -EBLACKLISTED)
-			fsc->blacklisted = true;
+		if (err2 == -EBLOCKLISTED)
+			fsc->blocklisted = true;
 		err = err2;
 		goto out_unlock;
 	}
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 762a280b7037..209535d5b8d3 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -933,8 +933,8 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
 		ceph_release_page_vector(pages, num_pages);
 
 		if (ret < 0) {
-			if (ret == -EBLACKLISTED)
-				fsc->blacklisted = true;
+			if (ret == -EBLOCKLISTED)
+				fsc->blocklisted = true;
 			break;
 		}
 
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 76d8d9495d1d..bb2d938a17ac 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -3303,7 +3303,7 @@ bad:
 }
 
 static int __decode_session_metadata(void **p, void *end,
-				     bool *blacklisted)
+				     bool *blocklisted)
 {
 	/* map<string,string> */
 	u32 n;
@@ -3318,7 +3318,7 @@ static int __decode_session_metadata(void **p, void *end,
 		ceph_decode_32_safe(p, end, len, bad);
 		ceph_decode_need(p, end, len, bad);
 		if (err_str && strnstr(*p, "blacklisted", len))
-			*blacklisted = true;
+			*blocklisted = true;
 		*p += len;
 	}
 	return 0;
@@ -3341,7 +3341,7 @@ static void handle_session(struct ceph_mds_session *session,
 	u32 op;
 	u64 seq, features = 0;
 	int wake = 0;
-	bool blacklisted = false;
+	bool blocklisted = false;
 
 	/* decode */
 	ceph_decode_need(&p, end, sizeof(*h), bad);
@@ -3354,7 +3354,7 @@ static void handle_session(struct ceph_mds_session *session,
 	if (msg_version >= 3) {
 		u32 len;
 		/* version >= 2, metadata */
-		if (__decode_session_metadata(&p, end, &blacklisted) < 0)
+		if (__decode_session_metadata(&p, end, &blocklisted) < 0)
 			goto bad;
 		/* version >= 3, feature bits */
 		ceph_decode_32_safe(&p, end, len, bad);
@@ -3445,8 +3445,8 @@ static void handle_session(struct ceph_mds_session *session,
 		session->s_state = CEPH_MDS_SESSION_REJECTED;
 		cleanup_session_requests(mdsc, session);
 		remove_session_caps(session);
-		if (blacklisted)
-			mdsc->fsc->blacklisted = true;
+		if (blocklisted)
+			mdsc->fsc->blocklisted = true;
 		wake = 2; /* for good measure */
 		break;
 
@@ -4367,14 +4367,14 @@ static void maybe_recover_session(struct ceph_mds_client *mdsc)
 	if (READ_ONCE(fsc->mount_state) != CEPH_MOUNT_MOUNTED)
 		return;
 
-	if (!READ_ONCE(fsc->blacklisted))
+	if (!READ_ONCE(fsc->blocklisted))
 		return;
 
 	if (fsc->last_auto_reconnect &&
 	    time_before(jiffies, fsc->last_auto_reconnect + HZ * 60 * 30))
 		return;
 
-	pr_info("auto reconnect after blacklisted\n");
+	pr_info("auto reconnect after blocklisted\n");
 	fsc->last_auto_reconnect = jiffies;
 	ceph_force_reconnect(fsc->sb);
 }
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index b3fc9bb61afc..2516304379d3 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -1241,13 +1241,13 @@ int ceph_force_reconnect(struct super_block *sb)
 	 * see remove_session_caps_cb() */
 	flush_workqueue(fsc->inode_wq);
 
-	/* In case that we were blacklisted. This also reset
+	/* In case that we were blocklisted. This also reset
 	 * all mon/osd connections */
 	ceph_reset_client_addr(fsc->client);
 
 	ceph_osdc_clear_abort_err(&fsc->client->osdc);
 
-	fsc->blacklisted = false;
+	fsc->blocklisted = false;
 	fsc->mount_state = CEPH_MOUNT_MOUNTED;
 
 	if (sb->s_root) {
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 483a52d281cd..582694899130 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -32,7 +32,7 @@
 #define CEPH_BLOCK_SHIFT   22  /* 4 MB */
 #define CEPH_BLOCK         (1 << CEPH_BLOCK_SHIFT)
 
-#define CEPH_MOUNT_OPT_CLEANRECOVER    (1<<1) /* auto reonnect (clean mode) after blacklisted */
+#define CEPH_MOUNT_OPT_CLEANRECOVER    (1<<1) /* auto reonnect (clean mode) after blocklisted */
 #define CEPH_MOUNT_OPT_DIRSTAT         (1<<4) /* `cat dirname` for stats */
 #define CEPH_MOUNT_OPT_RBYTES          (1<<5) /* dir st_bytes = rbytes */
 #define CEPH_MOUNT_OPT_NOASYNCREADDIR  (1<<7) /* no dcache readdir */
@@ -109,7 +109,7 @@ struct ceph_fs_client {
 	unsigned long mount_state;
 
 	unsigned long last_auto_reconnect;
-	bool blacklisted;
+	bool blocklisted;
 
 	bool have_copy_from2;
 
diff --git a/include/linux/ceph/mon_client.h b/include/linux/ceph/mon_client.h
index ce4ffeb384d7..b658961156a0 100644
--- a/include/linux/ceph/mon_client.h
+++ b/include/linux/ceph/mon_client.h
@@ -142,7 +142,7 @@ int ceph_monc_get_version(struct ceph_mon_client *monc, const char *what,
 int ceph_monc_get_version_async(struct ceph_mon_client *monc, const char *what,
 				ceph_monc_callback_t cb, u64 private_data);
 
-int ceph_monc_blacklist_add(struct ceph_mon_client *monc,
+int ceph_monc_blocklist_add(struct ceph_mon_client *monc,
 			    struct ceph_entity_addr *client_addr);
 
 extern int ceph_monc_open_session(struct ceph_mon_client *monc);
diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h
index 3a518fd0eaad..43a7a1573b51 100644
--- a/include/linux/ceph/rados.h
+++ b/include/linux/ceph/rados.h
@@ -424,7 +424,7 @@ enum {
 };
 
 #define EOLDSNAPC    ERESTART  /* ORDERSNAP flag set; writer has old snapc*/
-#define EBLACKLISTED ESHUTDOWN /* blacklisted */
+#define EBLOCKLISTED ESHUTDOWN /* blocklisted */
 
 /* xattr comparison */
 enum {
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index d633a0aeaa55..efcdde471278 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -896,7 +896,7 @@ bad:
 	ceph_msg_dump(msg);
 }
 
-int ceph_monc_blacklist_add(struct ceph_mon_client *monc,
+int ceph_monc_blocklist_add(struct ceph_mon_client *monc,
 			    struct ceph_entity_addr *client_addr)
 {
 	struct ceph_mon_generic_request *req;
@@ -936,9 +936,9 @@ int ceph_monc_blacklist_add(struct ceph_mon_client *monc,
 	ret = wait_generic_request(req);
 	if (!ret)
 		/*
-		 * Make sure we have the osdmap that includes the blacklist
+		 * Make sure we have the osdmap that includes the blocklist
 		 * entry.  This is needed to ensure that the OSDs pick up the
-		 * new blacklist before processing any future requests from
+		 * new blocklist before processing any future requests from
 		 * this client.
 		 */
 		ret = ceph_wait_for_latest_osdmap(monc->client, 0);
@@ -947,7 +947,7 @@ out:
 	put_generic_request(req);
 	return ret;
 }
-EXPORT_SYMBOL(ceph_monc_blacklist_add);
+EXPORT_SYMBOL(ceph_monc_blocklist_add);
 
 /*
  * Resend pending generic requests.
-- 
cgit v1.2.3


From b07720d0bd1e7c2251642010efb6075dbee23bb8 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Fri, 2 Oct 2020 14:38:08 +0200
Subject: libceph: fix ENTITY_NAME format suggestion

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/messenger.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index 76371aaae2d1..60b324efd1c4 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -54,7 +54,7 @@ struct ceph_connection_operations {
 	int (*check_message_signature) (struct ceph_msg *msg);
 };
 
-/* use format string %s%d */
+/* use format string %s%lld */
 #define ENTITY_NAME(n) ceph_entity_type_name((n).type), le64_to_cpu((n).num)
 
 struct ceph_messenger {
-- 
cgit v1.2.3


From 476c5818c37a7828d558f34ae01f0c32f8bfadde Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Sat, 29 Aug 2020 22:03:13 +0900
Subject: llist: Add nonatomic __llist_add() and __llist_dell_all()

We'll use these in the new, lockless kretprobes code.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/159870619318.1229682.13027387548510028721.stgit@devnote2
---
 drivers/gpu/drm/i915/i915_request.c |  6 ------
 include/linux/llist.h               | 23 +++++++++++++++++++++++
 2 files changed, 23 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 0b2fe55e6194..0e851b925c8c 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -357,12 +357,6 @@ void i915_request_retire_upto(struct i915_request *rq)
 	} while (i915_request_retire(tmp) && tmp != rq);
 }
 
-static void __llist_add(struct llist_node *node, struct llist_head *head)
-{
-	node->next = head->first;
-	head->first = node;
-}
-
 static struct i915_request * const *
 __engine_active(struct intel_engine_cs *engine)
 {
diff --git a/include/linux/llist.h b/include/linux/llist.h
index 2e9c7215882b..24f207b0190b 100644
--- a/include/linux/llist.h
+++ b/include/linux/llist.h
@@ -197,6 +197,16 @@ static inline struct llist_node *llist_next(struct llist_node *node)
 extern bool llist_add_batch(struct llist_node *new_first,
 			    struct llist_node *new_last,
 			    struct llist_head *head);
+
+static inline bool __llist_add_batch(struct llist_node *new_first,
+				     struct llist_node *new_last,
+				     struct llist_head *head)
+{
+	new_last->next = head->first;
+	head->first = new_first;
+	return new_last->next == NULL;
+}
+
 /**
  * llist_add - add a new entry
  * @new:	new entry to be added
@@ -209,6 +219,11 @@ static inline bool llist_add(struct llist_node *new, struct llist_head *head)
 	return llist_add_batch(new, new, head);
 }
 
+static inline bool __llist_add(struct llist_node *new, struct llist_head *head)
+{
+	return __llist_add_batch(new, new, head);
+}
+
 /**
  * llist_del_all - delete all entries from lock-less list
  * @head:	the head of lock-less list to delete all entries
@@ -222,6 +237,14 @@ static inline struct llist_node *llist_del_all(struct llist_head *head)
 	return xchg(&head->first, NULL);
 }
 
+static inline struct llist_node *__llist_del_all(struct llist_head *head)
+{
+	struct llist_node *first = head->first;
+
+	head->first = NULL;
+	return first;
+}
+
 extern struct llist_node *llist_del_first(struct llist_head *head);
 
 struct llist_node *llist_reverse_order(struct llist_node *head);
-- 
cgit v1.2.3


From d741bf41d7c7db4898bacfcb020353cddc032fd8 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Sat, 29 Aug 2020 22:03:24 +0900
Subject: kprobes: Remove kretprobe hash

The kretprobe hash is mostly superfluous, replace it with a per-task
variable.

This gets rid of the task hash and it's related locking.

Note that this may change the kprobes module-exported API for kretprobe
handlers. If any out-of-tree kretprobe user uses ri->rp, use
get_kretprobe(ri) instead.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/159870620431.1229682.16325792502413731312.stgit@devnote2
---
 include/linux/kprobes.h     |  19 +++-
 include/linux/sched.h       |   4 +
 kernel/fork.c               |   4 +
 kernel/kprobes.c            | 236 +++++++++++++-------------------------------
 kernel/trace/trace_kprobe.c |   3 +-
 5 files changed, 97 insertions(+), 169 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 5c8c271fa1e9..00cf4421efd5 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -27,6 +27,7 @@
 #include <linux/rcupdate.h>
 #include <linux/mutex.h>
 #include <linux/ftrace.h>
+#include <linux/refcount.h>
 #include <asm/kprobes.h>
 
 #ifdef CONFIG_KPROBES
@@ -144,6 +145,11 @@ static inline int kprobe_ftrace(struct kprobe *p)
  * ignored, due to maxactive being too low.
  *
  */
+struct kretprobe_holder {
+	struct kretprobe	*rp;
+	refcount_t		ref;
+};
+
 struct kretprobe {
 	struct kprobe kp;
 	kretprobe_handler_t handler;
@@ -152,17 +158,18 @@ struct kretprobe {
 	int nmissed;
 	size_t data_size;
 	struct hlist_head free_instances;
+	struct kretprobe_holder *rph;
 	raw_spinlock_t lock;
 };
 
 struct kretprobe_instance {
 	union {
+		struct llist_node llist;
 		struct hlist_node hlist;
 		struct rcu_head rcu;
 	};
-	struct kretprobe *rp;
+	struct kretprobe_holder *rph;
 	kprobe_opcode_t *ret_addr;
-	struct task_struct *task;
 	void *fp;
 	char data[];
 };
@@ -221,6 +228,14 @@ unsigned long kretprobe_trampoline_handler(struct pt_regs *regs,
 	return ret;
 }
 
+static nokprobe_inline struct kretprobe *get_kretprobe(struct kretprobe_instance *ri)
+{
+	RCU_LOCKDEP_WARN(!rcu_read_lock_any_held(),
+		"Kretprobe is accessed from instance under preemptive context");
+
+	return READ_ONCE(ri->rph->rp);
+}
+
 #else /* CONFIG_KRETPROBES */
 static inline void arch_prepare_kretprobe(struct kretprobe *rp,
 					struct pt_regs *regs)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index afe01e232935..5911805cafde 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1315,6 +1315,10 @@ struct task_struct {
 	struct callback_head		mce_kill_me;
 #endif
 
+#ifdef CONFIG_KRETPROBES
+	struct llist_head               kretprobe_instances;
+#endif
+
 	/*
 	 * New fields for task_struct should be added above here, so that
 	 * they are included in the randomized portion of task_struct.
diff --git a/kernel/fork.c b/kernel/fork.c
index 49677d668de4..53a1f508a097 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2161,6 +2161,10 @@ static __latent_entropy struct task_struct *copy_process(
 	INIT_LIST_HEAD(&p->thread_group);
 	p->task_works = NULL;
 
+#ifdef CONFIG_KRETPROBES
+	p->kretprobe_instances.first = NULL;
+#endif
+
 	/*
 	 * Ensure that the cgroup subsystem policies allow the new process to be
 	 * forked. It should be noted the the new process's css_set can be changed
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 3b61ae8ff5da..850ee36a4051 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -53,7 +53,6 @@ static int kprobes_initialized;
  * - RCU hlist traversal under disabling preempt (breakpoint handlers)
  */
 static struct hlist_head kprobe_table[KPROBE_TABLE_SIZE];
-static struct hlist_head kretprobe_inst_table[KPROBE_TABLE_SIZE];
 
 /* NOTE: change this value only with kprobe_mutex held */
 static bool kprobes_all_disarmed;
@@ -61,9 +60,6 @@ static bool kprobes_all_disarmed;
 /* This protects kprobe_table and optimizing_list */
 static DEFINE_MUTEX(kprobe_mutex);
 static DEFINE_PER_CPU(struct kprobe *, kprobe_instance) = NULL;
-static struct {
-	raw_spinlock_t lock ____cacheline_aligned_in_smp;
-} kretprobe_table_locks[KPROBE_TABLE_SIZE];
 
 kprobe_opcode_t * __weak kprobe_lookup_name(const char *name,
 					unsigned int __unused)
@@ -71,11 +67,6 @@ kprobe_opcode_t * __weak kprobe_lookup_name(const char *name,
 	return ((kprobe_opcode_t *)(kallsyms_lookup_name(name)));
 }
 
-static raw_spinlock_t *kretprobe_table_lock_ptr(unsigned long hash)
-{
-	return &(kretprobe_table_locks[hash].lock);
-}
-
 /* Blacklist -- list of struct kprobe_blacklist_entry */
 static LIST_HEAD(kprobe_blacklist);
 
@@ -1223,65 +1214,30 @@ void kprobes_inc_nmissed_count(struct kprobe *p)
 }
 NOKPROBE_SYMBOL(kprobes_inc_nmissed_count);
 
+static void free_rp_inst_rcu(struct rcu_head *head)
+{
+	struct kretprobe_instance *ri = container_of(head, struct kretprobe_instance, rcu);
+
+	if (refcount_dec_and_test(&ri->rph->ref))
+		kfree(ri->rph);
+	kfree(ri);
+}
+NOKPROBE_SYMBOL(free_rp_inst_rcu);
+
 static void recycle_rp_inst(struct kretprobe_instance *ri)
 {
-	struct kretprobe *rp = ri->rp;
+	struct kretprobe *rp = get_kretprobe(ri);
 
-	/* remove rp inst off the rprobe_inst_table */
-	hlist_del(&ri->hlist);
 	INIT_HLIST_NODE(&ri->hlist);
 	if (likely(rp)) {
 		raw_spin_lock(&rp->lock);
 		hlist_add_head(&ri->hlist, &rp->free_instances);
 		raw_spin_unlock(&rp->lock);
 	} else
-		kfree_rcu(ri, rcu);
+		call_rcu(&ri->rcu, free_rp_inst_rcu);
 }
 NOKPROBE_SYMBOL(recycle_rp_inst);
 
-static void kretprobe_hash_lock(struct task_struct *tsk,
-			 struct hlist_head **head, unsigned long *flags)
-__acquires(hlist_lock)
-{
-	unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS);
-	raw_spinlock_t *hlist_lock;
-
-	*head = &kretprobe_inst_table[hash];
-	hlist_lock = kretprobe_table_lock_ptr(hash);
-	raw_spin_lock_irqsave(hlist_lock, *flags);
-}
-NOKPROBE_SYMBOL(kretprobe_hash_lock);
-
-static void kretprobe_table_lock(unsigned long hash,
-				 unsigned long *flags)
-__acquires(hlist_lock)
-{
-	raw_spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash);
-	raw_spin_lock_irqsave(hlist_lock, *flags);
-}
-NOKPROBE_SYMBOL(kretprobe_table_lock);
-
-static void kretprobe_hash_unlock(struct task_struct *tsk,
-			   unsigned long *flags)
-__releases(hlist_lock)
-{
-	unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS);
-	raw_spinlock_t *hlist_lock;
-
-	hlist_lock = kretprobe_table_lock_ptr(hash);
-	raw_spin_unlock_irqrestore(hlist_lock, *flags);
-}
-NOKPROBE_SYMBOL(kretprobe_hash_unlock);
-
-static void kretprobe_table_unlock(unsigned long hash,
-				   unsigned long *flags)
-__releases(hlist_lock)
-{
-	raw_spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash);
-	raw_spin_unlock_irqrestore(hlist_lock, *flags);
-}
-NOKPROBE_SYMBOL(kretprobe_table_unlock);
-
 static struct kprobe kprobe_busy = {
 	.addr = (void *) get_kprobe,
 };
@@ -1311,24 +1267,21 @@ void kprobe_busy_end(void)
 void kprobe_flush_task(struct task_struct *tk)
 {
 	struct kretprobe_instance *ri;
-	struct hlist_head *head;
-	struct hlist_node *tmp;
-	unsigned long hash, flags = 0;
+	struct llist_node *node;
 
+	/* Early boot, not yet initialized. */
 	if (unlikely(!kprobes_initialized))
-		/* Early boot.  kretprobe_table_locks not yet initialized. */
 		return;
 
 	kprobe_busy_begin();
 
-	hash = hash_ptr(tk, KPROBE_HASH_BITS);
-	head = &kretprobe_inst_table[hash];
-	kretprobe_table_lock(hash, &flags);
-	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
-		if (ri->task == tk)
-			recycle_rp_inst(ri);
+	node = __llist_del_all(&tk->kretprobe_instances);
+	while (node) {
+		ri = container_of(node, struct kretprobe_instance, llist);
+		node = node->next;
+
+		recycle_rp_inst(ri);
 	}
-	kretprobe_table_unlock(hash, &flags);
 
 	kprobe_busy_end();
 }
@@ -1338,36 +1291,19 @@ static inline void free_rp_inst(struct kretprobe *rp)
 {
 	struct kretprobe_instance *ri;
 	struct hlist_node *next;
+	int count = 0;
 
 	hlist_for_each_entry_safe(ri, next, &rp->free_instances, hlist) {
 		hlist_del(&ri->hlist);
 		kfree(ri);
+		count++;
 	}
-}
-
-static void cleanup_rp_inst(struct kretprobe *rp)
-{
-	unsigned long flags, hash;
-	struct kretprobe_instance *ri;
-	struct hlist_node *next;
-	struct hlist_head *head;
 
-	/* To avoid recursive kretprobe by NMI, set kprobe busy here */
-	kprobe_busy_begin();
-	for (hash = 0; hash < KPROBE_TABLE_SIZE; hash++) {
-		kretprobe_table_lock(hash, &flags);
-		head = &kretprobe_inst_table[hash];
-		hlist_for_each_entry_safe(ri, next, head, hlist) {
-			if (ri->rp == rp)
-				ri->rp = NULL;
-		}
-		kretprobe_table_unlock(hash, &flags);
+	if (refcount_sub_and_test(count, &rp->rph->ref)) {
+		kfree(rp->rph);
+		rp->rph = NULL;
 	}
-	kprobe_busy_end();
-
-	free_rp_inst(rp);
 }
-NOKPROBE_SYMBOL(cleanup_rp_inst);
 
 /* Add the new probe to ap->list */
 static int add_new_kprobe(struct kprobe *ap, struct kprobe *p)
@@ -1928,88 +1864,56 @@ unsigned long __kretprobe_trampoline_handler(struct pt_regs *regs,
 					     void *trampoline_address,
 					     void *frame_pointer)
 {
-	struct kretprobe_instance *ri = NULL, *last = NULL;
-	struct hlist_head *head;
-	struct hlist_node *tmp;
-	unsigned long flags;
 	kprobe_opcode_t *correct_ret_addr = NULL;
-	bool skipped = false;
+	struct kretprobe_instance *ri = NULL;
+	struct llist_node *first, *node;
+	struct kretprobe *rp;
 
-	kretprobe_hash_lock(current, &head, &flags);
+	/* Find all nodes for this frame. */
+	first = node = current->kretprobe_instances.first;
+	while (node) {
+		ri = container_of(node, struct kretprobe_instance, llist);
 
-	/*
-	 * It is possible to have multiple instances associated with a given
-	 * task either because multiple functions in the call path have
-	 * return probes installed on them, and/or more than one
-	 * return probe was registered for a target function.
-	 *
-	 * We can handle this because:
-	 *     - instances are always pushed into the head of the list
-	 *     - when multiple return probes are registered for the same
-	 *	 function, the (chronologically) first instance's ret_addr
-	 *	 will be the real return address, and all the rest will
-	 *	 point to kretprobe_trampoline.
-	 */
-	hlist_for_each_entry(ri, head, hlist) {
-		if (ri->task != current)
-			/* another task is sharing our hash bucket */
-			continue;
-		/*
-		 * Return probes must be pushed on this hash list correct
-		 * order (same as return order) so that it can be popped
-		 * correctly. However, if we find it is pushed it incorrect
-		 * order, this means we find a function which should not be
-		 * probed, because the wrong order entry is pushed on the
-		 * path of processing other kretprobe itself.
-		 */
-		if (ri->fp != frame_pointer) {
-			if (!skipped)
-				pr_warn("kretprobe is stacked incorrectly. Trying to fixup.\n");
-			skipped = true;
-			continue;
-		}
+		BUG_ON(ri->fp != frame_pointer);
 
-		correct_ret_addr = ri->ret_addr;
-		if (skipped)
-			pr_warn("%ps must be blacklisted because of incorrect kretprobe order\n",
-				ri->rp->kp.addr);
-
-		if (correct_ret_addr != trampoline_address)
+		if (ri->ret_addr != trampoline_address) {
+			correct_ret_addr = ri->ret_addr;
 			/*
 			 * This is the real return address. Any other
 			 * instances associated with this task are for
 			 * other calls deeper on the call stack
 			 */
-			break;
+			goto found;
+		}
+
+		node = node->next;
 	}
+	pr_err("Oops! Kretprobe fails to find correct return address.\n");
+	BUG_ON(1);
 
-	BUG_ON(!correct_ret_addr || (correct_ret_addr == trampoline_address));
-	last = ri;
+found:
+	/* Unlink all nodes for this frame. */
+	current->kretprobe_instances.first = node->next;
+	node->next = NULL;
 
-	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
-		if (ri->task != current)
-			/* another task is sharing our hash bucket */
-			continue;
-		if (ri->fp != frame_pointer)
-			continue;
+	/* Run them..  */
+	while (first) {
+		ri = container_of(first, struct kretprobe_instance, llist);
+		first = first->next;
 
-		if (ri->rp && ri->rp->handler) {
+		rp = get_kretprobe(ri);
+		if (rp && rp->handler) {
 			struct kprobe *prev = kprobe_running();
 
-			__this_cpu_write(current_kprobe, &ri->rp->kp);
+			__this_cpu_write(current_kprobe, &rp->kp);
 			ri->ret_addr = correct_ret_addr;
-			ri->rp->handler(ri, regs);
+			rp->handler(ri, regs);
 			__this_cpu_write(current_kprobe, prev);
 		}
 
 		recycle_rp_inst(ri);
-
-		if (ri == last)
-			break;
 	}
 
-	kretprobe_hash_unlock(current, &flags);
-
 	return (unsigned long)correct_ret_addr;
 }
 NOKPROBE_SYMBOL(__kretprobe_trampoline_handler)
@@ -2021,11 +1925,10 @@ NOKPROBE_SYMBOL(__kretprobe_trampoline_handler)
 static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs)
 {
 	struct kretprobe *rp = container_of(p, struct kretprobe, kp);
-	unsigned long hash, flags = 0;
+	unsigned long flags = 0;
 	struct kretprobe_instance *ri;
 
 	/* TODO: consider to only swap the RA after the last pre_handler fired */
-	hash = hash_ptr(current, KPROBE_HASH_BITS);
 	raw_spin_lock_irqsave(&rp->lock, flags);
 	if (!hlist_empty(&rp->free_instances)) {
 		ri = hlist_entry(rp->free_instances.first,
@@ -2033,9 +1936,6 @@ static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs)
 		hlist_del(&ri->hlist);
 		raw_spin_unlock_irqrestore(&rp->lock, flags);
 
-		ri->rp = rp;
-		ri->task = current;
-
 		if (rp->entry_handler && rp->entry_handler(ri, regs)) {
 			raw_spin_lock_irqsave(&rp->lock, flags);
 			hlist_add_head(&ri->hlist, &rp->free_instances);
@@ -2045,11 +1945,8 @@ static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs)
 
 		arch_prepare_kretprobe(ri, regs);
 
-		/* XXX(hch): why is there no hlist_move_head? */
-		INIT_HLIST_NODE(&ri->hlist);
-		kretprobe_table_lock(hash, &flags);
-		hlist_add_head(&ri->hlist, &kretprobe_inst_table[hash]);
-		kretprobe_table_unlock(hash, &flags);
+		__llist_add(&ri->llist, &current->kretprobe_instances);
+
 	} else {
 		rp->nmissed++;
 		raw_spin_unlock_irqrestore(&rp->lock, flags);
@@ -2112,16 +2009,24 @@ int register_kretprobe(struct kretprobe *rp)
 	}
 	raw_spin_lock_init(&rp->lock);
 	INIT_HLIST_HEAD(&rp->free_instances);
+	rp->rph = kzalloc(sizeof(struct kretprobe_holder), GFP_KERNEL);
+	if (!rp->rph)
+		return -ENOMEM;
+
+	rp->rph->rp = rp;
 	for (i = 0; i < rp->maxactive; i++) {
-		inst = kmalloc(sizeof(struct kretprobe_instance) +
+		inst = kzalloc(sizeof(struct kretprobe_instance) +
 			       rp->data_size, GFP_KERNEL);
 		if (inst == NULL) {
+			refcount_set(&rp->rph->ref, i);
 			free_rp_inst(rp);
 			return -ENOMEM;
 		}
+		inst->rph = rp->rph;
 		INIT_HLIST_NODE(&inst->hlist);
 		hlist_add_head(&inst->hlist, &rp->free_instances);
 	}
+	refcount_set(&rp->rph->ref, i);
 
 	rp->nmissed = 0;
 	/* Establish function entry probe point */
@@ -2163,16 +2068,18 @@ void unregister_kretprobes(struct kretprobe **rps, int num)
 	if (num <= 0)
 		return;
 	mutex_lock(&kprobe_mutex);
-	for (i = 0; i < num; i++)
+	for (i = 0; i < num; i++) {
 		if (__unregister_kprobe_top(&rps[i]->kp) < 0)
 			rps[i]->kp.addr = NULL;
+		rps[i]->rph->rp = NULL;
+	}
 	mutex_unlock(&kprobe_mutex);
 
 	synchronize_rcu();
 	for (i = 0; i < num; i++) {
 		if (rps[i]->kp.addr) {
 			__unregister_kprobe_bottom(&rps[i]->kp);
-			cleanup_rp_inst(rps[i]);
+			free_rp_inst(rps[i]);
 		}
 	}
 }
@@ -2535,11 +2442,8 @@ static int __init init_kprobes(void)
 
 	/* FIXME allocate the probe table, currently defined statically */
 	/* initialize all list heads */
-	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
+	for (i = 0; i < KPROBE_TABLE_SIZE; i++)
 		INIT_HLIST_HEAD(&kprobe_table[i]);
-		INIT_HLIST_HEAD(&kretprobe_inst_table[i]);
-		raw_spin_lock_init(&(kretprobe_table_locks[i].lock));
-	}
 
 	err = populate_kprobe_blacklist(__start_kprobe_blacklist,
 					__stop_kprobe_blacklist);
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index aefb6065b508..07baf6f6cecc 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1714,7 +1714,8 @@ NOKPROBE_SYMBOL(kprobe_dispatcher);
 static int
 kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs)
 {
-	struct trace_kprobe *tk = container_of(ri->rp, struct trace_kprobe, rp);
+	struct kretprobe *rp = get_kretprobe(ri);
+	struct trace_kprobe *tk = container_of(rp, struct trace_kprobe, rp);
 
 	raw_cpu_inc(*tk->nhit);
 
-- 
cgit v1.2.3


From 29f006fdefe6f88abde973a0b0f20d2704e93fd4 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Sat, 29 Aug 2020 22:03:35 +0900
Subject: asm-generic/atomic: Add try_cmpxchg() fallbacks

Only x86 provides try_cmpxchg() outside of the atomic_t interfaces,
provide generic fallbacks to create this interface from the widely
available cmpxchg() function.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/159870621515.1229682.15506193091065001742.stgit@devnote2
---
 arch/x86/include/asm/atomic.h             |   2 +-
 arch/x86/include/asm/atomic64_64.h        |   2 +-
 arch/x86/include/asm/cmpxchg.h            |   2 +-
 include/asm-generic/atomic-instrumented.h | 216 ++++++++++++++++++------------
 include/linux/atomic-arch-fallback.h      |  90 +++++++++++--
 include/linux/atomic-fallback.h           |  90 +++++++++++--
 scripts/atomic/gen-atomic-fallback.sh     |  63 ++++++++-
 scripts/atomic/gen-atomic-instrumented.sh |  29 +++-
 8 files changed, 372 insertions(+), 122 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index b6cac6e9bb70..f732741ad7c7 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -199,7 +199,7 @@ static __always_inline int arch_atomic_cmpxchg(atomic_t *v, int old, int new)
 
 static __always_inline bool arch_atomic_try_cmpxchg(atomic_t *v, int *old, int new)
 {
-	return try_cmpxchg(&v->counter, old, new);
+	return arch_try_cmpxchg(&v->counter, old, new);
 }
 #define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg
 
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 809bd010a751..7886d0578fc9 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -187,7 +187,7 @@ static inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
 
 static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new)
 {
-	return try_cmpxchg(&v->counter, old, new);
+	return arch_try_cmpxchg(&v->counter, old, new);
 }
 #define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg
 
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index a8bfac131256..4d4ec5cbdc51 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -221,7 +221,7 @@ extern void __add_wrong_size(void)
 #define __try_cmpxchg(ptr, pold, new, size)				\
 	__raw_try_cmpxchg((ptr), (pold), (new), (size), LOCK_PREFIX)
 
-#define try_cmpxchg(ptr, pold, new) 					\
+#define arch_try_cmpxchg(ptr, pold, new) 				\
 	__try_cmpxchg((ptr), (pold), (new), sizeof(*(ptr)))
 
 /*
diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h
index 379986e40159..2cab3fdaae3b 100644
--- a/include/asm-generic/atomic-instrumented.h
+++ b/include/asm-generic/atomic-instrumented.h
@@ -1642,148 +1642,192 @@ atomic64_dec_if_positive(atomic64_t *v)
 #endif
 
 #if !defined(arch_xchg_relaxed) || defined(arch_xchg)
-#define xchg(ptr, ...)						\
-({									\
-	typeof(ptr) __ai_ptr = (ptr);					\
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr));		\
-	arch_xchg(__ai_ptr, __VA_ARGS__);				\
+#define xchg(ptr, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	arch_xchg(__ai_ptr, __VA_ARGS__); \
 })
 #endif
 
 #if defined(arch_xchg_acquire)
-#define xchg_acquire(ptr, ...)						\
-({									\
-	typeof(ptr) __ai_ptr = (ptr);					\
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr));		\
-	arch_xchg_acquire(__ai_ptr, __VA_ARGS__);				\
+#define xchg_acquire(ptr, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	arch_xchg_acquire(__ai_ptr, __VA_ARGS__); \
 })
 #endif
 
 #if defined(arch_xchg_release)
-#define xchg_release(ptr, ...)						\
-({									\
-	typeof(ptr) __ai_ptr = (ptr);					\
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr));		\
-	arch_xchg_release(__ai_ptr, __VA_ARGS__);				\
+#define xchg_release(ptr, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	arch_xchg_release(__ai_ptr, __VA_ARGS__); \
 })
 #endif
 
 #if defined(arch_xchg_relaxed)
-#define xchg_relaxed(ptr, ...)						\
-({									\
-	typeof(ptr) __ai_ptr = (ptr);					\
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr));		\
-	arch_xchg_relaxed(__ai_ptr, __VA_ARGS__);				\
+#define xchg_relaxed(ptr, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	arch_xchg_relaxed(__ai_ptr, __VA_ARGS__); \
 })
 #endif
 
 #if !defined(arch_cmpxchg_relaxed) || defined(arch_cmpxchg)
-#define cmpxchg(ptr, ...)						\
-({									\
-	typeof(ptr) __ai_ptr = (ptr);					\
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr));		\
-	arch_cmpxchg(__ai_ptr, __VA_ARGS__);				\
+#define cmpxchg(ptr, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	arch_cmpxchg(__ai_ptr, __VA_ARGS__); \
 })
 #endif
 
 #if defined(arch_cmpxchg_acquire)
-#define cmpxchg_acquire(ptr, ...)						\
-({									\
-	typeof(ptr) __ai_ptr = (ptr);					\
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr));		\
-	arch_cmpxchg_acquire(__ai_ptr, __VA_ARGS__);				\
+#define cmpxchg_acquire(ptr, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	arch_cmpxchg_acquire(__ai_ptr, __VA_ARGS__); \
 })
 #endif
 
 #if defined(arch_cmpxchg_release)
-#define cmpxchg_release(ptr, ...)						\
-({									\
-	typeof(ptr) __ai_ptr = (ptr);					\
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr));		\
-	arch_cmpxchg_release(__ai_ptr, __VA_ARGS__);				\
+#define cmpxchg_release(ptr, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	arch_cmpxchg_release(__ai_ptr, __VA_ARGS__); \
 })
 #endif
 
 #if defined(arch_cmpxchg_relaxed)
-#define cmpxchg_relaxed(ptr, ...)						\
-({									\
-	typeof(ptr) __ai_ptr = (ptr);					\
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr));		\
-	arch_cmpxchg_relaxed(__ai_ptr, __VA_ARGS__);				\
+#define cmpxchg_relaxed(ptr, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	arch_cmpxchg_relaxed(__ai_ptr, __VA_ARGS__); \
 })
 #endif
 
 #if !defined(arch_cmpxchg64_relaxed) || defined(arch_cmpxchg64)
-#define cmpxchg64(ptr, ...)						\
-({									\
-	typeof(ptr) __ai_ptr = (ptr);					\
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr));		\
-	arch_cmpxchg64(__ai_ptr, __VA_ARGS__);				\
+#define cmpxchg64(ptr, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	arch_cmpxchg64(__ai_ptr, __VA_ARGS__); \
 })
 #endif
 
 #if defined(arch_cmpxchg64_acquire)
-#define cmpxchg64_acquire(ptr, ...)						\
-({									\
-	typeof(ptr) __ai_ptr = (ptr);					\
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr));		\
-	arch_cmpxchg64_acquire(__ai_ptr, __VA_ARGS__);				\
+#define cmpxchg64_acquire(ptr, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	arch_cmpxchg64_acquire(__ai_ptr, __VA_ARGS__); \
 })
 #endif
 
 #if defined(arch_cmpxchg64_release)
-#define cmpxchg64_release(ptr, ...)						\
-({									\
-	typeof(ptr) __ai_ptr = (ptr);					\
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr));		\
-	arch_cmpxchg64_release(__ai_ptr, __VA_ARGS__);				\
+#define cmpxchg64_release(ptr, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	arch_cmpxchg64_release(__ai_ptr, __VA_ARGS__); \
 })
 #endif
 
 #if defined(arch_cmpxchg64_relaxed)
-#define cmpxchg64_relaxed(ptr, ...)						\
-({									\
-	typeof(ptr) __ai_ptr = (ptr);					\
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr));		\
-	arch_cmpxchg64_relaxed(__ai_ptr, __VA_ARGS__);				\
+#define cmpxchg64_relaxed(ptr, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	arch_cmpxchg64_relaxed(__ai_ptr, __VA_ARGS__); \
 })
 #endif
 
-#define cmpxchg_local(ptr, ...)						\
-({									\
-	typeof(ptr) __ai_ptr = (ptr);					\
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr));		\
-	arch_cmpxchg_local(__ai_ptr, __VA_ARGS__);				\
+#if !defined(arch_try_cmpxchg_relaxed) || defined(arch_try_cmpxchg)
+#define try_cmpxchg(ptr, oldp, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	typeof(oldp) __ai_oldp = (oldp); \
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \
+	arch_try_cmpxchg(__ai_ptr, __ai_oldp, __VA_ARGS__); \
+})
+#endif
+
+#if defined(arch_try_cmpxchg_acquire)
+#define try_cmpxchg_acquire(ptr, oldp, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	typeof(oldp) __ai_oldp = (oldp); \
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \
+	arch_try_cmpxchg_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \
+})
+#endif
+
+#if defined(arch_try_cmpxchg_release)
+#define try_cmpxchg_release(ptr, oldp, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	typeof(oldp) __ai_oldp = (oldp); \
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \
+	arch_try_cmpxchg_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \
+})
+#endif
+
+#if defined(arch_try_cmpxchg_relaxed)
+#define try_cmpxchg_relaxed(ptr, oldp, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	typeof(oldp) __ai_oldp = (oldp); \
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \
+	arch_try_cmpxchg_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \
+})
+#endif
+
+#define cmpxchg_local(ptr, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	arch_cmpxchg_local(__ai_ptr, __VA_ARGS__); \
 })
 
-#define cmpxchg64_local(ptr, ...)						\
-({									\
-	typeof(ptr) __ai_ptr = (ptr);					\
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr));		\
-	arch_cmpxchg64_local(__ai_ptr, __VA_ARGS__);				\
+#define cmpxchg64_local(ptr, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	arch_cmpxchg64_local(__ai_ptr, __VA_ARGS__); \
 })
 
-#define sync_cmpxchg(ptr, ...)						\
-({									\
-	typeof(ptr) __ai_ptr = (ptr);					\
-	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr));		\
-	arch_sync_cmpxchg(__ai_ptr, __VA_ARGS__);				\
+#define sync_cmpxchg(ptr, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	arch_sync_cmpxchg(__ai_ptr, __VA_ARGS__); \
 })
 
-#define cmpxchg_double(ptr, ...)						\
-({									\
-	typeof(ptr) __ai_ptr = (ptr);					\
-	instrument_atomic_write(__ai_ptr, 2 * sizeof(*__ai_ptr));		\
-	arch_cmpxchg_double(__ai_ptr, __VA_ARGS__);				\
+#define cmpxchg_double(ptr, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	instrument_atomic_write(__ai_ptr, 2 * sizeof(*__ai_ptr)); \
+	arch_cmpxchg_double(__ai_ptr, __VA_ARGS__); \
 })
 
 
-#define cmpxchg_double_local(ptr, ...)						\
-({									\
-	typeof(ptr) __ai_ptr = (ptr);					\
-	instrument_atomic_write(__ai_ptr, 2 * sizeof(*__ai_ptr));		\
-	arch_cmpxchg_double_local(__ai_ptr, __VA_ARGS__);				\
+#define cmpxchg_double_local(ptr, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	instrument_atomic_write(__ai_ptr, 2 * sizeof(*__ai_ptr)); \
+	arch_cmpxchg_double_local(__ai_ptr, __VA_ARGS__); \
 })
 
 #endif /* _ASM_GENERIC_ATOMIC_INSTRUMENTED_H */
-// 89bf97f3a7509b740845e51ddf31055b48a81f40
+// ff0fe7f81ee97f01f13bb78b0e3ce800bc56d9dd
diff --git a/include/linux/atomic-arch-fallback.h b/include/linux/atomic-arch-fallback.h
index bcb6aa27cfa6..a3dba31df01e 100644
--- a/include/linux/atomic-arch-fallback.h
+++ b/include/linux/atomic-arch-fallback.h
@@ -9,9 +9,9 @@
 #include <linux/compiler.h>
 
 #ifndef arch_xchg_relaxed
-#define arch_xchg_relaxed		arch_xchg
-#define arch_xchg_acquire		arch_xchg
-#define arch_xchg_release		arch_xchg
+#define arch_xchg_acquire arch_xchg
+#define arch_xchg_release arch_xchg
+#define arch_xchg_relaxed arch_xchg
 #else /* arch_xchg_relaxed */
 
 #ifndef arch_xchg_acquire
@@ -32,9 +32,9 @@
 #endif /* arch_xchg_relaxed */
 
 #ifndef arch_cmpxchg_relaxed
-#define arch_cmpxchg_relaxed		arch_cmpxchg
-#define arch_cmpxchg_acquire		arch_cmpxchg
-#define arch_cmpxchg_release		arch_cmpxchg
+#define arch_cmpxchg_acquire arch_cmpxchg
+#define arch_cmpxchg_release arch_cmpxchg
+#define arch_cmpxchg_relaxed arch_cmpxchg
 #else /* arch_cmpxchg_relaxed */
 
 #ifndef arch_cmpxchg_acquire
@@ -55,9 +55,9 @@
 #endif /* arch_cmpxchg_relaxed */
 
 #ifndef arch_cmpxchg64_relaxed
-#define arch_cmpxchg64_relaxed		arch_cmpxchg64
-#define arch_cmpxchg64_acquire		arch_cmpxchg64
-#define arch_cmpxchg64_release		arch_cmpxchg64
+#define arch_cmpxchg64_acquire arch_cmpxchg64
+#define arch_cmpxchg64_release arch_cmpxchg64
+#define arch_cmpxchg64_relaxed arch_cmpxchg64
 #else /* arch_cmpxchg64_relaxed */
 
 #ifndef arch_cmpxchg64_acquire
@@ -77,6 +77,76 @@
 
 #endif /* arch_cmpxchg64_relaxed */
 
+#ifndef arch_try_cmpxchg_relaxed
+#ifdef arch_try_cmpxchg
+#define arch_try_cmpxchg_acquire arch_try_cmpxchg
+#define arch_try_cmpxchg_release arch_try_cmpxchg
+#define arch_try_cmpxchg_relaxed arch_try_cmpxchg
+#endif /* arch_try_cmpxchg */
+
+#ifndef arch_try_cmpxchg
+#define arch_try_cmpxchg(_ptr, _oldp, _new) \
+({ \
+	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
+	___r = arch_cmpxchg((_ptr), ___o, (_new)); \
+	if (unlikely(___r != ___o)) \
+		*___op = ___r; \
+	likely(___r == ___o); \
+})
+#endif /* arch_try_cmpxchg */
+
+#ifndef arch_try_cmpxchg_acquire
+#define arch_try_cmpxchg_acquire(_ptr, _oldp, _new) \
+({ \
+	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
+	___r = arch_cmpxchg_acquire((_ptr), ___o, (_new)); \
+	if (unlikely(___r != ___o)) \
+		*___op = ___r; \
+	likely(___r == ___o); \
+})
+#endif /* arch_try_cmpxchg_acquire */
+
+#ifndef arch_try_cmpxchg_release
+#define arch_try_cmpxchg_release(_ptr, _oldp, _new) \
+({ \
+	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
+	___r = arch_cmpxchg_release((_ptr), ___o, (_new)); \
+	if (unlikely(___r != ___o)) \
+		*___op = ___r; \
+	likely(___r == ___o); \
+})
+#endif /* arch_try_cmpxchg_release */
+
+#ifndef arch_try_cmpxchg_relaxed
+#define arch_try_cmpxchg_relaxed(_ptr, _oldp, _new) \
+({ \
+	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
+	___r = arch_cmpxchg_relaxed((_ptr), ___o, (_new)); \
+	if (unlikely(___r != ___o)) \
+		*___op = ___r; \
+	likely(___r == ___o); \
+})
+#endif /* arch_try_cmpxchg_relaxed */
+
+#else /* arch_try_cmpxchg_relaxed */
+
+#ifndef arch_try_cmpxchg_acquire
+#define arch_try_cmpxchg_acquire(...) \
+	__atomic_op_acquire(arch_try_cmpxchg, __VA_ARGS__)
+#endif
+
+#ifndef arch_try_cmpxchg_release
+#define arch_try_cmpxchg_release(...) \
+	__atomic_op_release(arch_try_cmpxchg, __VA_ARGS__)
+#endif
+
+#ifndef arch_try_cmpxchg
+#define arch_try_cmpxchg(...) \
+	__atomic_op_fence(arch_try_cmpxchg, __VA_ARGS__)
+#endif
+
+#endif /* arch_try_cmpxchg_relaxed */
+
 #ifndef arch_atomic_read_acquire
 static __always_inline int
 arch_atomic_read_acquire(const atomic_t *v)
@@ -2288,4 +2358,4 @@ arch_atomic64_dec_if_positive(atomic64_t *v)
 #endif
 
 #endif /* _LINUX_ATOMIC_FALLBACK_H */
-// 90cd26cfd69d2250303d654955a0cc12620fb91b
+// cca554917d7ea73d5e3e7397dd70c484cad9b2c4
diff --git a/include/linux/atomic-fallback.h b/include/linux/atomic-fallback.h
index fd525c71d676..2a3f55d98be9 100644
--- a/include/linux/atomic-fallback.h
+++ b/include/linux/atomic-fallback.h
@@ -9,9 +9,9 @@
 #include <linux/compiler.h>
 
 #ifndef xchg_relaxed
-#define xchg_relaxed		xchg
-#define xchg_acquire		xchg
-#define xchg_release		xchg
+#define xchg_acquire xchg
+#define xchg_release xchg
+#define xchg_relaxed xchg
 #else /* xchg_relaxed */
 
 #ifndef xchg_acquire
@@ -32,9 +32,9 @@
 #endif /* xchg_relaxed */
 
 #ifndef cmpxchg_relaxed
-#define cmpxchg_relaxed		cmpxchg
-#define cmpxchg_acquire		cmpxchg
-#define cmpxchg_release		cmpxchg
+#define cmpxchg_acquire cmpxchg
+#define cmpxchg_release cmpxchg
+#define cmpxchg_relaxed cmpxchg
 #else /* cmpxchg_relaxed */
 
 #ifndef cmpxchg_acquire
@@ -55,9 +55,9 @@
 #endif /* cmpxchg_relaxed */
 
 #ifndef cmpxchg64_relaxed
-#define cmpxchg64_relaxed		cmpxchg64
-#define cmpxchg64_acquire		cmpxchg64
-#define cmpxchg64_release		cmpxchg64
+#define cmpxchg64_acquire cmpxchg64
+#define cmpxchg64_release cmpxchg64
+#define cmpxchg64_relaxed cmpxchg64
 #else /* cmpxchg64_relaxed */
 
 #ifndef cmpxchg64_acquire
@@ -77,6 +77,76 @@
 
 #endif /* cmpxchg64_relaxed */
 
+#ifndef try_cmpxchg_relaxed
+#ifdef try_cmpxchg
+#define try_cmpxchg_acquire try_cmpxchg
+#define try_cmpxchg_release try_cmpxchg
+#define try_cmpxchg_relaxed try_cmpxchg
+#endif /* try_cmpxchg */
+
+#ifndef try_cmpxchg
+#define try_cmpxchg(_ptr, _oldp, _new) \
+({ \
+	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
+	___r = cmpxchg((_ptr), ___o, (_new)); \
+	if (unlikely(___r != ___o)) \
+		*___op = ___r; \
+	likely(___r == ___o); \
+})
+#endif /* try_cmpxchg */
+
+#ifndef try_cmpxchg_acquire
+#define try_cmpxchg_acquire(_ptr, _oldp, _new) \
+({ \
+	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
+	___r = cmpxchg_acquire((_ptr), ___o, (_new)); \
+	if (unlikely(___r != ___o)) \
+		*___op = ___r; \
+	likely(___r == ___o); \
+})
+#endif /* try_cmpxchg_acquire */
+
+#ifndef try_cmpxchg_release
+#define try_cmpxchg_release(_ptr, _oldp, _new) \
+({ \
+	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
+	___r = cmpxchg_release((_ptr), ___o, (_new)); \
+	if (unlikely(___r != ___o)) \
+		*___op = ___r; \
+	likely(___r == ___o); \
+})
+#endif /* try_cmpxchg_release */
+
+#ifndef try_cmpxchg_relaxed
+#define try_cmpxchg_relaxed(_ptr, _oldp, _new) \
+({ \
+	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
+	___r = cmpxchg_relaxed((_ptr), ___o, (_new)); \
+	if (unlikely(___r != ___o)) \
+		*___op = ___r; \
+	likely(___r == ___o); \
+})
+#endif /* try_cmpxchg_relaxed */
+
+#else /* try_cmpxchg_relaxed */
+
+#ifndef try_cmpxchg_acquire
+#define try_cmpxchg_acquire(...) \
+	__atomic_op_acquire(try_cmpxchg, __VA_ARGS__)
+#endif
+
+#ifndef try_cmpxchg_release
+#define try_cmpxchg_release(...) \
+	__atomic_op_release(try_cmpxchg, __VA_ARGS__)
+#endif
+
+#ifndef try_cmpxchg
+#define try_cmpxchg(...) \
+	__atomic_op_fence(try_cmpxchg, __VA_ARGS__)
+#endif
+
+#endif /* try_cmpxchg_relaxed */
+
 #define arch_atomic_read atomic_read
 #define arch_atomic_read_acquire atomic_read_acquire
 
@@ -2522,4 +2592,4 @@ atomic64_dec_if_positive(atomic64_t *v)
 #endif
 
 #endif /* _LINUX_ATOMIC_FALLBACK_H */
-// 9d95b56f98d82a2a26c7b79ccdd0c47572d50a6f
+// d78e6c293c661c15188f0ec05bce45188c8d5892
diff --git a/scripts/atomic/gen-atomic-fallback.sh b/scripts/atomic/gen-atomic-fallback.sh
index 693dfa1de430..317a6cec76e1 100755
--- a/scripts/atomic/gen-atomic-fallback.sh
+++ b/scripts/atomic/gen-atomic-fallback.sh
@@ -144,15 +144,11 @@ gen_proto_order_variants()
 	printf "#endif /* ${basename}_relaxed */\n\n"
 }
 
-gen_xchg_fallbacks()
+gen_order_fallbacks()
 {
 	local xchg="$1"; shift
+
 cat <<EOF
-#ifndef ${xchg}_relaxed
-#define ${xchg}_relaxed		${xchg}
-#define ${xchg}_acquire		${xchg}
-#define ${xchg}_release		${xchg}
-#else /* ${xchg}_relaxed */
 
 #ifndef ${xchg}_acquire
 #define ${xchg}_acquire(...) \\
@@ -169,11 +165,62 @@ cat <<EOF
 	__atomic_op_fence(${xchg}, __VA_ARGS__)
 #endif
 
-#endif /* ${xchg}_relaxed */
+EOF
+}
+
+gen_xchg_fallbacks()
+{
+	local xchg="$1"; shift
+	printf "#ifndef ${xchg}_relaxed\n"
+
+	gen_basic_fallbacks ${xchg}
+
+	printf "#else /* ${xchg}_relaxed */\n"
+
+	gen_order_fallbacks ${xchg}
+
+	printf "#endif /* ${xchg}_relaxed */\n\n"
+}
+
+gen_try_cmpxchg_fallback()
+{
+	local order="$1"; shift;
+
+cat <<EOF
+#ifndef ${ARCH}try_cmpxchg${order}
+#define ${ARCH}try_cmpxchg${order}(_ptr, _oldp, _new) \\
+({ \\
+	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \\
+	___r = ${ARCH}cmpxchg${order}((_ptr), ___o, (_new)); \\
+	if (unlikely(___r != ___o)) \\
+		*___op = ___r; \\
+	likely(___r == ___o); \\
+})
+#endif /* ${ARCH}try_cmpxchg${order} */
 
 EOF
 }
 
+gen_try_cmpxchg_fallbacks()
+{
+	printf "#ifndef ${ARCH}try_cmpxchg_relaxed\n"
+	printf "#ifdef ${ARCH}try_cmpxchg\n"
+
+	gen_basic_fallbacks "${ARCH}try_cmpxchg"
+
+	printf "#endif /* ${ARCH}try_cmpxchg */\n\n"
+
+	for order in "" "_acquire" "_release" "_relaxed"; do
+		gen_try_cmpxchg_fallback "${order}"
+	done
+
+	printf "#else /* ${ARCH}try_cmpxchg_relaxed */\n"
+
+	gen_order_fallbacks "${ARCH}try_cmpxchg"
+
+	printf "#endif /* ${ARCH}try_cmpxchg_relaxed */\n\n"
+}
+
 cat << EOF
 // SPDX-License-Identifier: GPL-2.0
 
@@ -191,6 +238,8 @@ for xchg in "${ARCH}xchg" "${ARCH}cmpxchg" "${ARCH}cmpxchg64"; do
 	gen_xchg_fallbacks "${xchg}"
 done
 
+gen_try_cmpxchg_fallbacks
+
 grep '^[a-z]' "$1" | while read name meta args; do
 	gen_proto "${meta}" "${name}" "${ARCH}" "atomic" "int" ${args}
 done
diff --git a/scripts/atomic/gen-atomic-instrumented.sh b/scripts/atomic/gen-atomic-instrumented.sh
index 6afadf73da17..85dc25685c0d 100755
--- a/scripts/atomic/gen-atomic-instrumented.sh
+++ b/scripts/atomic/gen-atomic-instrumented.sh
@@ -103,14 +103,31 @@ gen_xchg()
 	local xchg="$1"; shift
 	local mult="$1"; shift
 
+	if [ "${xchg%${xchg#try_cmpxchg}}" = "try_cmpxchg" ] ; then
+
+cat <<EOF
+#define ${xchg}(ptr, oldp, ...) \\
+({ \\
+	typeof(ptr) __ai_ptr = (ptr); \\
+	typeof(oldp) __ai_oldp = (oldp); \\
+	instrument_atomic_write(__ai_ptr, ${mult}sizeof(*__ai_ptr)); \\
+	instrument_atomic_write(__ai_oldp, ${mult}sizeof(*__ai_oldp)); \\
+	arch_${xchg}(__ai_ptr, __ai_oldp, __VA_ARGS__); \\
+})
+EOF
+
+	else
+
 cat <<EOF
-#define ${xchg}(ptr, ...)						\\
-({									\\
-	typeof(ptr) __ai_ptr = (ptr);					\\
-	instrument_atomic_write(__ai_ptr, ${mult}sizeof(*__ai_ptr));		\\
-	arch_${xchg}(__ai_ptr, __VA_ARGS__);				\\
+#define ${xchg}(ptr, ...) \\
+({ \\
+	typeof(ptr) __ai_ptr = (ptr); \\
+	instrument_atomic_write(__ai_ptr, ${mult}sizeof(*__ai_ptr)); \\
+	arch_${xchg}(__ai_ptr, __VA_ARGS__); \\
 })
 EOF
+
+	fi
 }
 
 gen_optional_xchg()
@@ -160,7 +177,7 @@ grep '^[a-z]' "$1" | while read name meta args; do
 	gen_proto "${meta}" "${name}" "atomic64" "s64" ${args}
 done
 
-for xchg in "xchg" "cmpxchg" "cmpxchg64"; do
+for xchg in "xchg" "cmpxchg" "cmpxchg64" "try_cmpxchg"; do
 	for order in "" "_acquire" "_release" "_relaxed"; do
 		gen_optional_xchg "${xchg}" "${order}"
 	done
-- 
cgit v1.2.3


From e563604a5f5a891283b6a8db4001cee833a7c6b8 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Sat, 29 Aug 2020 22:03:46 +0900
Subject: freelist: Implement lockless freelist

A simple CAS-based lock-free free list. Not the fastest thing in the world
under heavy contention, but simple and correct (assuming nodes are never
freed until after the free list is destroyed), and fairly speedy under low
contention.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/159870622579.1229682.16729440870040944993.stgit@devnote2
---
 include/linux/freelist.h | 129 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 129 insertions(+)
 create mode 100644 include/linux/freelist.h

(limited to 'include/linux')

diff --git a/include/linux/freelist.h b/include/linux/freelist.h
new file mode 100644
index 000000000000..fc1842b96469
--- /dev/null
+++ b/include/linux/freelist.h
@@ -0,0 +1,129 @@
+/* SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause */
+#ifndef FREELIST_H
+#define FREELIST_H
+
+#include <linux/atomic.h>
+
+/*
+ * Copyright: cameron@moodycamel.com
+ *
+ * A simple CAS-based lock-free free list. Not the fastest thing in the world
+ * under heavy contention, but simple and correct (assuming nodes are never
+ * freed until after the free list is destroyed), and fairly speedy under low
+ * contention.
+ *
+ * Adapted from: https://moodycamel.com/blog/2014/solving-the-aba-problem-for-lock-free-free-lists
+ */
+
+struct freelist_node {
+	atomic_t		refs;
+	struct freelist_node	*next;
+};
+
+struct freelist_head {
+	struct freelist_node	*head;
+};
+
+#define REFS_ON_FREELIST 0x80000000
+#define REFS_MASK	 0x7FFFFFFF
+
+static inline void __freelist_add(struct freelist_node *node, struct freelist_head *list)
+{
+	/*
+	 * Since the refcount is zero, and nobody can increase it once it's
+	 * zero (except us, and we run only one copy of this method per node at
+	 * a time, i.e. the single thread case), then we know we can safely
+	 * change the next pointer of the node; however, once the refcount is
+	 * back above zero, then other threads could increase it (happens under
+	 * heavy contention, when the refcount goes to zero in between a load
+	 * and a refcount increment of a node in try_get, then back up to
+	 * something non-zero, then the refcount increment is done by the other
+	 * thread) -- so if the CAS to add the node to the actual list fails,
+	 * decrese the refcount and leave the add operation to the next thread
+	 * who puts the refcount back to zero (which could be us, hence the
+	 * loop).
+	 */
+	struct freelist_node *head = READ_ONCE(list->head);
+
+	for (;;) {
+		WRITE_ONCE(node->next, head);
+		atomic_set_release(&node->refs, 1);
+
+		if (!try_cmpxchg_release(&list->head, &head, node)) {
+			/*
+			 * Hmm, the add failed, but we can only try again when
+			 * the refcount goes back to zero.
+			 */
+			if (atomic_fetch_add_release(REFS_ON_FREELIST - 1, &node->refs) == 1)
+				continue;
+		}
+		return;
+	}
+}
+
+static inline void freelist_add(struct freelist_node *node, struct freelist_head *list)
+{
+	/*
+	 * We know that the should-be-on-freelist bit is 0 at this point, so
+	 * it's safe to set it using a fetch_add.
+	 */
+	if (!atomic_fetch_add_release(REFS_ON_FREELIST, &node->refs)) {
+		/*
+		 * Oh look! We were the last ones referencing this node, and we
+		 * know we want to add it to the free list, so let's do it!
+		 */
+		__freelist_add(node, list);
+	}
+}
+
+static inline struct freelist_node *freelist_try_get(struct freelist_head *list)
+{
+	struct freelist_node *prev, *next, *head = smp_load_acquire(&list->head);
+	unsigned int refs;
+
+	while (head) {
+		prev = head;
+		refs = atomic_read(&head->refs);
+		if ((refs & REFS_MASK) == 0 ||
+		    !atomic_try_cmpxchg_acquire(&head->refs, &refs, refs+1)) {
+			head = smp_load_acquire(&list->head);
+			continue;
+		}
+
+		/*
+		 * Good, reference count has been incremented (it wasn't at
+		 * zero), which means we can read the next and not worry about
+		 * it changing between now and the time we do the CAS.
+		 */
+		next = READ_ONCE(head->next);
+		if (try_cmpxchg_acquire(&list->head, &head, next)) {
+			/*
+			 * Yay, got the node. This means it was on the list,
+			 * which means should-be-on-freelist must be false no
+			 * matter the refcount (because nobody else knows it's
+			 * been taken off yet, it can't have been put back on).
+			 */
+			WARN_ON_ONCE(atomic_read(&head->refs) & REFS_ON_FREELIST);
+
+			/*
+			 * Decrease refcount twice, once for our ref, and once
+			 * for the list's ref.
+			 */
+			atomic_fetch_add(-2, &head->refs);
+
+			return head;
+		}
+
+		/*
+		 * OK, the head must have changed on us, but we still need to decrement
+		 * the refcount we increased.
+		 */
+		refs = atomic_fetch_add(-1, &prev->refs);
+		if (refs == REFS_ON_FREELIST + 1)
+			__freelist_add(prev, list);
+	}
+
+	return NULL;
+}
+
+#endif /* FREELIST_H */
-- 
cgit v1.2.3


From 6e426e0fcd20ce144bb93e00b70df51e9f2e08c3 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Sat, 29 Aug 2020 22:03:56 +0900
Subject: kprobes: Replace rp->free_instance with freelist

Gets rid of rp->lock, and as a result kretprobes are now fully
lockless.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/159870623583.1229682.17472357584134058687.stgit@devnote2
---
 include/linux/kprobes.h |  8 +++----
 kernel/kprobes.c        | 56 +++++++++++++++++++++----------------------------
 2 files changed, 28 insertions(+), 36 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 00cf4421efd5..b7824e3f1ef5 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -28,6 +28,7 @@
 #include <linux/mutex.h>
 #include <linux/ftrace.h>
 #include <linux/refcount.h>
+#include <linux/freelist.h>
 #include <asm/kprobes.h>
 
 #ifdef CONFIG_KPROBES
@@ -157,17 +158,16 @@ struct kretprobe {
 	int maxactive;
 	int nmissed;
 	size_t data_size;
-	struct hlist_head free_instances;
+	struct freelist_head freelist;
 	struct kretprobe_holder *rph;
-	raw_spinlock_t lock;
 };
 
 struct kretprobe_instance {
 	union {
-		struct llist_node llist;
-		struct hlist_node hlist;
+		struct freelist_node freelist;
 		struct rcu_head rcu;
 	};
+	struct llist_node llist;
 	struct kretprobe_holder *rph;
 	kprobe_opcode_t *ret_addr;
 	void *fp;
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 850ee36a4051..30b8fe7d571d 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1228,11 +1228,8 @@ static void recycle_rp_inst(struct kretprobe_instance *ri)
 {
 	struct kretprobe *rp = get_kretprobe(ri);
 
-	INIT_HLIST_NODE(&ri->hlist);
 	if (likely(rp)) {
-		raw_spin_lock(&rp->lock);
-		hlist_add_head(&ri->hlist, &rp->free_instances);
-		raw_spin_unlock(&rp->lock);
+		freelist_add(&ri->freelist, &rp->freelist);
 	} else
 		call_rcu(&ri->rcu, free_rp_inst_rcu);
 }
@@ -1290,11 +1287,14 @@ NOKPROBE_SYMBOL(kprobe_flush_task);
 static inline void free_rp_inst(struct kretprobe *rp)
 {
 	struct kretprobe_instance *ri;
-	struct hlist_node *next;
+	struct freelist_node *node;
 	int count = 0;
 
-	hlist_for_each_entry_safe(ri, next, &rp->free_instances, hlist) {
-		hlist_del(&ri->hlist);
+	node = rp->freelist.head;
+	while (node) {
+		ri = container_of(node, struct kretprobe_instance, freelist);
+		node = node->next;
+
 		kfree(ri);
 		count++;
 	}
@@ -1925,32 +1925,26 @@ NOKPROBE_SYMBOL(__kretprobe_trampoline_handler)
 static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs)
 {
 	struct kretprobe *rp = container_of(p, struct kretprobe, kp);
-	unsigned long flags = 0;
 	struct kretprobe_instance *ri;
+	struct freelist_node *fn;
 
-	/* TODO: consider to only swap the RA after the last pre_handler fired */
-	raw_spin_lock_irqsave(&rp->lock, flags);
-	if (!hlist_empty(&rp->free_instances)) {
-		ri = hlist_entry(rp->free_instances.first,
-				struct kretprobe_instance, hlist);
-		hlist_del(&ri->hlist);
-		raw_spin_unlock_irqrestore(&rp->lock, flags);
-
-		if (rp->entry_handler && rp->entry_handler(ri, regs)) {
-			raw_spin_lock_irqsave(&rp->lock, flags);
-			hlist_add_head(&ri->hlist, &rp->free_instances);
-			raw_spin_unlock_irqrestore(&rp->lock, flags);
-			return 0;
-		}
-
-		arch_prepare_kretprobe(ri, regs);
+	fn = freelist_try_get(&rp->freelist);
+	if (!fn) {
+		rp->nmissed++;
+		return 0;
+	}
 
-		__llist_add(&ri->llist, &current->kretprobe_instances);
+	ri = container_of(fn, struct kretprobe_instance, freelist);
 
-	} else {
-		rp->nmissed++;
-		raw_spin_unlock_irqrestore(&rp->lock, flags);
+	if (rp->entry_handler && rp->entry_handler(ri, regs)) {
+		freelist_add(&ri->freelist, &rp->freelist);
+		return 0;
 	}
+
+	arch_prepare_kretprobe(ri, regs);
+
+	__llist_add(&ri->llist, &current->kretprobe_instances);
+
 	return 0;
 }
 NOKPROBE_SYMBOL(pre_handler_kretprobe);
@@ -2007,8 +2001,7 @@ int register_kretprobe(struct kretprobe *rp)
 		rp->maxactive = num_possible_cpus();
 #endif
 	}
-	raw_spin_lock_init(&rp->lock);
-	INIT_HLIST_HEAD(&rp->free_instances);
+	rp->freelist.head = NULL;
 	rp->rph = kzalloc(sizeof(struct kretprobe_holder), GFP_KERNEL);
 	if (!rp->rph)
 		return -ENOMEM;
@@ -2023,8 +2016,7 @@ int register_kretprobe(struct kretprobe *rp)
 			return -ENOMEM;
 		}
 		inst->rph = rp->rph;
-		INIT_HLIST_NODE(&inst->hlist);
-		hlist_add_head(&inst->hlist, &rp->free_instances);
+		freelist_add(&inst->freelist, &rp->freelist);
 	}
 	refcount_set(&rp->rph->ref, i);
 
-- 
cgit v1.2.3


From 9b80e4c4ddaca3501177ed41e49d0928ba2122a8 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Wed, 12 Aug 2020 14:47:03 -0700
Subject: overflow: Add __must_check attribute to check_*() helpers

Since the destination variable of the check_*_overflow() helpers will
contain a wrapped value on failure, it would be best to make sure callers
really did check the return result of the helper. Adjust the macros to use
a bool-wrapping static inline that is marked with __must_check. This means
the macros can continue to have their type-agnostic behavior while gaining
the function attribute (that cannot be applied directly to macros).

Suggested-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Link: https://lore.kernel.org/lkml/202008151007.EF679DF@keescook/
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 include/linux/overflow.h | 39 ++++++++++++++++++++++++---------------
 1 file changed, 24 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/overflow.h b/include/linux/overflow.h
index 93fcef105061..f1c4e7b56bd9 100644
--- a/include/linux/overflow.h
+++ b/include/linux/overflow.h
@@ -43,6 +43,16 @@
 #define is_non_negative(a) ((a) > 0 || (a) == 0)
 #define is_negative(a) (!(is_non_negative(a)))
 
+/*
+ * Allows for effectively applying __must_check to a macro so we can have
+ * both the type-agnostic benefits of the macros while also being able to
+ * enforce that the return value is, in fact, checked.
+ */
+static inline bool __must_check __must_check_overflow(bool overflow)
+{
+	return unlikely(overflow);
+}
+
 #ifdef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW
 /*
  * For simplicity and code hygiene, the fallback code below insists on
@@ -52,32 +62,32 @@
  * alias for __builtin_add_overflow, but add type checks similar to
  * below.
  */
-#define check_add_overflow(a, b, d) ({		\
+#define check_add_overflow(a, b, d) __must_check_overflow(({	\
 	typeof(a) __a = (a);			\
 	typeof(b) __b = (b);			\
 	typeof(d) __d = (d);			\
 	(void) (&__a == &__b);			\
 	(void) (&__a == __d);			\
 	__builtin_add_overflow(__a, __b, __d);	\
-})
+}))
 
-#define check_sub_overflow(a, b, d) ({		\
+#define check_sub_overflow(a, b, d) __must_check_overflow(({	\
 	typeof(a) __a = (a);			\
 	typeof(b) __b = (b);			\
 	typeof(d) __d = (d);			\
 	(void) (&__a == &__b);			\
 	(void) (&__a == __d);			\
 	__builtin_sub_overflow(__a, __b, __d);	\
-})
+}))
 
-#define check_mul_overflow(a, b, d) ({		\
+#define check_mul_overflow(a, b, d) __must_check_overflow(({	\
 	typeof(a) __a = (a);			\
 	typeof(b) __b = (b);			\
 	typeof(d) __d = (d);			\
 	(void) (&__a == &__b);			\
 	(void) (&__a == __d);			\
 	__builtin_mul_overflow(__a, __b, __d);	\
-})
+}))
 
 #else
 
@@ -190,21 +200,20 @@
 })
 
 
-#define check_add_overflow(a, b, d)					\
+#define check_add_overflow(a, b, d)	__must_check_overflow(		\
 	__builtin_choose_expr(is_signed_type(typeof(a)),		\
 			__signed_add_overflow(a, b, d),			\
-			__unsigned_add_overflow(a, b, d))
+			__unsigned_add_overflow(a, b, d)))
 
-#define check_sub_overflow(a, b, d)					\
+#define check_sub_overflow(a, b, d)	__must_check_overflow(		\
 	__builtin_choose_expr(is_signed_type(typeof(a)),		\
 			__signed_sub_overflow(a, b, d),			\
-			__unsigned_sub_overflow(a, b, d))
+			__unsigned_sub_overflow(a, b, d)))
 
-#define check_mul_overflow(a, b, d)					\
+#define check_mul_overflow(a, b, d)	__must_check_overflow(		\
 	__builtin_choose_expr(is_signed_type(typeof(a)),		\
 			__signed_mul_overflow(a, b, d),			\
-			__unsigned_mul_overflow(a, b, d))
-
+			__unsigned_mul_overflow(a, b, d)))
 
 #endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */
 
@@ -227,7 +236,7 @@
  * '*d' will hold the results of the attempted shift, but is not
  * considered "safe for use" if false is returned.
  */
-#define check_shl_overflow(a, s, d) ({					\
+#define check_shl_overflow(a, s, d) __must_check_overflow(({		\
 	typeof(a) _a = a;						\
 	typeof(s) _s = s;						\
 	typeof(d) _d = d;						\
@@ -237,7 +246,7 @@
 	*_d = (_a_full << _to_shift);					\
 	(_to_shift != _s || is_negative(*_d) || is_negative(_a) ||	\
 	(*_d >> _to_shift) != _a);					\
-})
+}))
 
 /**
  * array_size() - Calculate size of 2-dimensional array.
-- 
cgit v1.2.3


From ee92e4f1f95eb7b8820299f10fc5fba16d85cece Mon Sep 17 00:00:00 2001
From: Huy Nguyen <huyn@mellanox.com>
Date: Wed, 8 Apr 2020 14:47:39 -0500
Subject: net/mlx5: Add NIC TX domain namespace

Add new namespace that represents the NIC TX domain.

Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Signed-off-by: Raed Salem <raeds@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/fs.h   |  1 +
 drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c  |  3 +++
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 19 ++++++++++++++++++-
 include/linux/mlx5/fs.h                           |  1 +
 4 files changed, 23 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
index 6a97452dc60e..dc744702aee4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
@@ -236,6 +236,7 @@ struct mlx5e_accel_fs_tcp;
 
 struct mlx5e_flow_steering {
 	struct mlx5_flow_namespace      *ns;
+	struct mlx5_flow_namespace      *egress_ns;
 #ifdef CONFIG_MLX5_EN_RXNFC
 	struct mlx5e_ethtool_steering   ethtool;
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index fee169732de7..babe3405132a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -776,6 +776,9 @@ static int mlx5_cmd_modify_header_alloc(struct mlx5_flow_root_namespace *ns,
 		table_type = FS_FT_NIC_RX;
 		break;
 	case MLX5_FLOW_NAMESPACE_EGRESS:
+#ifdef CONFIG_MLX5_IPSEC
+	case MLX5_FLOW_NAMESPACE_EGRESS_KERNEL:
+#endif
 		max_actions = MLX5_CAP_FLOWTABLE_NIC_TX(dev, max_modify_header_actions);
 		table_type = FS_FT_NIC_TX;
 		break;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 6141e9ec8190..16091838bfcf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -126,6 +126,10 @@
 #define LAG_NUM_PRIOS 1
 #define LAG_MIN_LEVEL (OFFLOADS_MIN_LEVEL + 1)
 
+#define KERNEL_TX_IPSEC_NUM_PRIOS  1
+#define KERNEL_TX_IPSEC_NUM_LEVELS 1
+#define KERNEL_TX_MIN_LEVEL        (KERNEL_TX_IPSEC_NUM_LEVELS)
+
 struct node_caps {
 	size_t	arr_sz;
 	long	*caps;
@@ -180,13 +184,24 @@ static struct init_tree_node {
 
 static struct init_tree_node egress_root_fs = {
 	.type = FS_TYPE_NAMESPACE,
+#ifdef CONFIG_MLX5_IPSEC
+	.ar_size = 2,
+#else
 	.ar_size = 1,
+#endif
 	.children = (struct init_tree_node[]) {
 		ADD_PRIO(0, MLX5_BY_PASS_NUM_PRIOS, 0,
 			 FS_CHAINING_CAPS_EGRESS,
 			 ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF,
 				ADD_MULTIPLE_PRIO(MLX5_BY_PASS_NUM_PRIOS,
 						  BY_PASS_PRIO_NUM_LEVELS))),
+#ifdef CONFIG_MLX5_IPSEC
+		ADD_PRIO(0, KERNEL_TX_MIN_LEVEL, 0,
+			 FS_CHAINING_CAPS_EGRESS,
+			 ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF,
+				ADD_MULTIPLE_PRIO(KERNEL_TX_IPSEC_NUM_PRIOS,
+						  KERNEL_TX_IPSEC_NUM_LEVELS))),
+#endif
 	}
 };
 
@@ -2165,8 +2180,10 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev,
 		break;
 	}
 
-	if (type == MLX5_FLOW_NAMESPACE_EGRESS) {
+	if (type == MLX5_FLOW_NAMESPACE_EGRESS ||
+	    type == MLX5_FLOW_NAMESPACE_EGRESS_KERNEL) {
 		root_ns = steering->egress_root_ns;
+		prio = type - MLX5_FLOW_NAMESPACE_EGRESS;
 	} else if (type == MLX5_FLOW_NAMESPACE_RDMA_RX) {
 		root_ns = steering->rdma_rx_root_ns;
 		prio = RDMA_RX_BYPASS_PRIO;
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 92d991d93757..846d94ad04bc 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -76,6 +76,7 @@ enum mlx5_flow_namespace_type {
 	MLX5_FLOW_NAMESPACE_SNIFFER_RX,
 	MLX5_FLOW_NAMESPACE_SNIFFER_TX,
 	MLX5_FLOW_NAMESPACE_EGRESS,
+	MLX5_FLOW_NAMESPACE_EGRESS_KERNEL,
 	MLX5_FLOW_NAMESPACE_RDMA_RX,
 	MLX5_FLOW_NAMESPACE_RDMA_RX_KERNEL,
 	MLX5_FLOW_NAMESPACE_RDMA_TX,
-- 
cgit v1.2.3


From 9b9d454ddbf0c41391ed68ea82bc3d8ff6a65074 Mon Sep 17 00:00:00 2001
From: Huy Nguyen <huyn@mellanox.com>
Date: Fri, 5 Jun 2020 20:17:51 -0500
Subject: net/mlx5e: IPsec: Add TX steering rule per IPsec state

Add new FTE in TX IPsec FT per IPsec state. It has the
same matching criteria as the RX steering rule.

The IPsec FT is created/destroyed when the first/last rule
is added/deleted respectively.

Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Reviewed-by: Boris Pismenny <borisp@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../ethernet/mellanox/mlx5/core/en_accel/ipsec.h   |   2 +
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c         | 178 ++++++++++++++++++++-
 include/linux/mlx5/qp.h                            |   6 +-
 3 files changed, 181 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
index 0fc8b4d4f4a3..6164c7f59efb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
@@ -76,6 +76,7 @@ struct mlx5e_ipsec_stats {
 };
 
 struct mlx5e_accel_fs_esp;
+struct mlx5e_ipsec_tx;
 
 struct mlx5e_ipsec {
 	struct mlx5e_priv *en_priv;
@@ -87,6 +88,7 @@ struct mlx5e_ipsec {
 	struct mlx5e_ipsec_stats stats;
 	struct workqueue_struct *wq;
 	struct mlx5e_accel_fs_esp *rx_fs;
+	struct mlx5e_ipsec_tx *tx_fs;
 };
 
 struct mlx5e_ipsec_esn_state {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index b974f3cd1005..0e45590662a8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -34,6 +34,12 @@ struct mlx5e_accel_fs_esp {
 	struct mlx5e_accel_fs_esp_prot fs_prot[ACCEL_FS_ESP_NUM_TYPES];
 };
 
+struct mlx5e_ipsec_tx {
+	struct mlx5_flow_table *ft;
+	struct mutex mutex; /* Protect IPsec TX steering */
+	u32 refcnt;
+};
+
 /* IPsec RX flow steering */
 static enum mlx5e_traffic_types fs_esp2tt(enum accel_fs_esp_type i)
 {
@@ -323,6 +329,77 @@ out:
 	mutex_unlock(&fs_prot->prot_mutex);
 }
 
+/* IPsec TX flow steering */
+static int tx_create(struct mlx5e_priv *priv)
+{
+	struct mlx5_flow_table_attr ft_attr = {};
+	struct mlx5e_ipsec *ipsec = priv->ipsec;
+	struct mlx5_flow_table *ft;
+	int err;
+
+	priv->fs.egress_ns =
+		mlx5_get_flow_namespace(priv->mdev,
+					MLX5_FLOW_NAMESPACE_EGRESS_KERNEL);
+	if (!priv->fs.egress_ns)
+		return -EOPNOTSUPP;
+
+	ft_attr.max_fte = NUM_IPSEC_FTE;
+	ft_attr.autogroup.max_num_groups = 1;
+	ft = mlx5_create_auto_grouped_flow_table(priv->fs.egress_ns, &ft_attr);
+	if (IS_ERR(ft)) {
+		err = PTR_ERR(ft);
+		netdev_err(priv->netdev, "fail to create ipsec tx ft err=%d\n", err);
+		return err;
+	}
+	ipsec->tx_fs->ft = ft;
+	return 0;
+}
+
+static void tx_destroy(struct mlx5e_priv *priv)
+{
+	struct mlx5e_ipsec *ipsec = priv->ipsec;
+
+	if (IS_ERR_OR_NULL(ipsec->tx_fs->ft))
+		return;
+
+	mlx5_destroy_flow_table(ipsec->tx_fs->ft);
+	ipsec->tx_fs->ft = NULL;
+}
+
+static int tx_ft_get(struct mlx5e_priv *priv)
+{
+	struct mlx5e_ipsec_tx *tx_fs = priv->ipsec->tx_fs;
+	int err = 0;
+
+	mutex_lock(&tx_fs->mutex);
+	if (tx_fs->refcnt++)
+		goto out;
+
+	err = tx_create(priv);
+	if (err) {
+		tx_fs->refcnt--;
+		goto out;
+	}
+
+out:
+	mutex_unlock(&tx_fs->mutex);
+	return err;
+}
+
+static void tx_ft_put(struct mlx5e_priv *priv)
+{
+	struct mlx5e_ipsec_tx *tx_fs = priv->ipsec->tx_fs;
+
+	mutex_lock(&tx_fs->mutex);
+	if (--tx_fs->refcnt)
+		goto out;
+
+	tx_destroy(priv);
+
+out:
+	mutex_unlock(&tx_fs->mutex);
+}
+
 static void setup_fte_common(struct mlx5_accel_esp_xfrm_attrs *attrs,
 			     u32 ipsec_obj_id,
 			     struct mlx5_flow_spec *spec,
@@ -457,6 +534,54 @@ out:
 	return err;
 }
 
+static int tx_add_rule(struct mlx5e_priv *priv,
+		       struct mlx5_accel_esp_xfrm_attrs *attrs,
+		       u32 ipsec_obj_id,
+		       struct mlx5e_ipsec_rule *ipsec_rule)
+{
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_spec *spec;
+	int err = 0;
+
+	err = tx_ft_get(priv);
+	if (err)
+		return err;
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	setup_fte_common(attrs, ipsec_obj_id, spec, &flow_act);
+
+	/* Add IPsec indicator in metadata_reg_a */
+	spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2;
+	MLX5_SET(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_a,
+		 MLX5_ETH_WQE_FT_META_IPSEC);
+	MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.metadata_reg_a,
+		 MLX5_ETH_WQE_FT_META_IPSEC);
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW |
+			  MLX5_FLOW_CONTEXT_ACTION_IPSEC_ENCRYPT;
+	rule = mlx5_add_flow_rules(priv->ipsec->tx_fs->ft, spec, &flow_act, NULL, 0);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		netdev_err(priv->netdev, "fail to add ipsec rule attrs->action=0x%x, err=%d\n",
+			   attrs->action, err);
+		goto out;
+	}
+
+	ipsec_rule->rule = rule;
+
+out:
+	kvfree(spec);
+	if (err)
+		tx_ft_put(priv);
+	return err;
+}
+
 static void rx_del_rule(struct mlx5e_priv *priv,
 			struct mlx5_accel_esp_xfrm_attrs *attrs,
 			struct mlx5e_ipsec_rule *ipsec_rule)
@@ -470,15 +595,27 @@ static void rx_del_rule(struct mlx5e_priv *priv,
 	rx_ft_put(priv, attrs->is_ipv6 ? ACCEL_FS_ESP6 : ACCEL_FS_ESP4);
 }
 
+static void tx_del_rule(struct mlx5e_priv *priv,
+			struct mlx5e_ipsec_rule *ipsec_rule)
+{
+	mlx5_del_flow_rules(ipsec_rule->rule);
+	ipsec_rule->rule = NULL;
+
+	tx_ft_put(priv);
+}
+
 int mlx5e_accel_ipsec_fs_add_rule(struct mlx5e_priv *priv,
 				  struct mlx5_accel_esp_xfrm_attrs *attrs,
 				  u32 ipsec_obj_id,
 				  struct mlx5e_ipsec_rule *ipsec_rule)
 {
-	if (!priv->ipsec->rx_fs || attrs->action != MLX5_ACCEL_ESP_ACTION_DECRYPT)
+	if (!priv->ipsec->rx_fs)
 		return -EOPNOTSUPP;
 
-	return rx_add_rule(priv, attrs, ipsec_obj_id, ipsec_rule);
+	if (attrs->action == MLX5_ACCEL_ESP_ACTION_DECRYPT)
+		return rx_add_rule(priv, attrs, ipsec_obj_id, ipsec_rule);
+	else
+		return tx_add_rule(priv, attrs, ipsec_obj_id, ipsec_rule);
 }
 
 void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_priv *priv,
@@ -488,7 +625,18 @@ void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_priv *priv,
 	if (!priv->ipsec->rx_fs)
 		return;
 
-	rx_del_rule(priv, attrs, ipsec_rule);
+	if (attrs->action == MLX5_ACCEL_ESP_ACTION_DECRYPT)
+		rx_del_rule(priv, attrs, ipsec_rule);
+	else
+		tx_del_rule(priv, ipsec_rule);
+}
+
+static void fs_cleanup_tx(struct mlx5e_priv *priv)
+{
+	mutex_destroy(&priv->ipsec->tx_fs->mutex);
+	WARN_ON(priv->ipsec->tx_fs->refcnt);
+	kfree(priv->ipsec->tx_fs);
+	priv->ipsec->tx_fs = NULL;
 }
 
 static void fs_cleanup_rx(struct mlx5e_priv *priv)
@@ -507,6 +655,17 @@ static void fs_cleanup_rx(struct mlx5e_priv *priv)
 	priv->ipsec->rx_fs = NULL;
 }
 
+static int fs_init_tx(struct mlx5e_priv *priv)
+{
+	priv->ipsec->tx_fs =
+		kzalloc(sizeof(struct mlx5e_ipsec_tx), GFP_KERNEL);
+	if (!priv->ipsec->tx_fs)
+		return -ENOMEM;
+
+	mutex_init(&priv->ipsec->tx_fs->mutex);
+	return 0;
+}
+
 static int fs_init_rx(struct mlx5e_priv *priv)
 {
 	struct mlx5e_accel_fs_esp_prot *fs_prot;
@@ -532,13 +691,24 @@ void mlx5e_accel_ipsec_fs_cleanup(struct mlx5e_priv *priv)
 	if (!priv->ipsec->rx_fs)
 		return;
 
+	fs_cleanup_tx(priv);
 	fs_cleanup_rx(priv);
 }
 
 int mlx5e_accel_ipsec_fs_init(struct mlx5e_priv *priv)
 {
+	int err;
+
 	if (!mlx5_is_ipsec_device(priv->mdev) || !priv->ipsec)
 		return -EOPNOTSUPP;
 
-	return fs_init_rx(priv);
+	err = fs_init_tx(priv);
+	if (err)
+		return err;
+
+	err = fs_init_rx(priv);
+	if (err)
+		fs_cleanup_tx(priv);
+
+	return err;
 }
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index 36492a1342cf..d75ef8aa8fac 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -245,6 +245,10 @@ enum {
 	MLX5_ETH_WQE_SWP_OUTER_L4_UDP   = 1 << 5,
 };
 
+enum {
+	MLX5_ETH_WQE_FT_META_IPSEC = BIT(0),
+};
+
 struct mlx5_wqe_eth_seg {
 	u8              swp_outer_l4_offset;
 	u8              swp_outer_l3_offset;
@@ -253,7 +257,7 @@ struct mlx5_wqe_eth_seg {
 	u8              cs_flags;
 	u8              swp_flags;
 	__be16          mss;
-	__be32          rsvd2;
+	__be32          flow_table_metadata;
 	union {
 		struct {
 			__be16 sz;
-- 
cgit v1.2.3


From 3528f8ec95a5b1ee1b98d3e85371843c6428e4be Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 15 Jul 2020 18:28:58 -0700
Subject: bcm963xx_tag.h: fix duplicated word

Change doubled word "is" to "it is".

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: bcm-kernel-feedback-list@broadcom.com
Cc: linux-mips@vger.kernel.org
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 include/linux/bcm963xx_tag.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/bcm963xx_tag.h b/include/linux/bcm963xx_tag.h
index b87945cb6946..7edb809a2586 100644
--- a/include/linux/bcm963xx_tag.h
+++ b/include/linux/bcm963xx_tag.h
@@ -84,7 +84,7 @@ struct bcm_tag {
 	char flash_layout_ver[FLASHLAYOUTVER_LEN];
 	/* 196-199: kernel+rootfs CRC32 */
 	__u32 fskernel_crc;
-	/* 200-215: Unused except on Alice Gate where is is information */
+	/* 200-215: Unused except on Alice Gate where it is information */
 	char information2[TAGINFO2_LEN];
 	/* 216-219: CRC32 of image less imagetag (kernel for Alice Gate) */
 	__u32 image_crc;
-- 
cgit v1.2.3


From f82cd2f0b5eb715b1a296e20b34da7d296b6e9a4 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 18 Aug 2020 09:05:56 -0400
Subject: XArray: Add private interface for workingset node deletion

Move the tricky bits of dealing with the XArray from the workingset
code to the XArray.  Make it clear in the documentation that this is a
private interface, and only export it for the benefit of the test suite.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 include/linux/xarray.h |  2 ++
 lib/test_xarray.c      |  7 +------
 lib/xarray.c           | 23 +++++++++++++++++++++++
 mm/workingset.c        | 13 ++-----------
 4 files changed, 28 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 6b336098fca7..29db4e16eb89 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -1286,6 +1286,8 @@ static inline bool xa_is_advanced(const void *entry)
  */
 typedef void (*xa_update_node_t)(struct xa_node *node);
 
+void xa_delete_node(struct xa_node *, xa_update_node_t);
+
 /*
  * The xa_state is opaque to its users.  It contains various different pieces
  * of state involved in the current operation on the XArray.  It should be
diff --git a/lib/test_xarray.c b/lib/test_xarray.c
index 1122c4453c87..64ae07b1bcf4 100644
--- a/lib/test_xarray.c
+++ b/lib/test_xarray.c
@@ -1600,14 +1600,9 @@ static noinline void shadow_remove(struct xarray *xa)
 	xa_lock(xa);
 	while ((node = list_first_entry_or_null(&shadow_nodes,
 					struct xa_node, private_list))) {
-		XA_STATE(xas, node->array, 0);
 		XA_BUG_ON(xa, node->array != xa);
 		list_del_init(&node->private_list);
-		xas.xa_node = xa_parent_locked(node->array, node);
-		xas.xa_offset = node->offset;
-		xas.xa_shift = node->shift + XA_CHUNK_SHIFT;
-		xas_set_update(&xas, test_update_node);
-		xas_store(&xas, NULL);
+		xa_delete_node(node, test_update_node);
 	}
 	xa_unlock(xa);
 }
diff --git a/lib/xarray.c b/lib/xarray.c
index e9e641d3c0c3..1fa5c5658e63 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -1973,6 +1973,29 @@ unsigned int xa_extract(struct xarray *xa, void **dst, unsigned long start,
 }
 EXPORT_SYMBOL(xa_extract);
 
+/**
+ * xa_delete_node() - Private interface for workingset code.
+ * @node: Node to be removed from the tree.
+ * @update: Function to call to update ancestor nodes.
+ *
+ * Context: xa_lock must be held on entry and will not be released.
+ */
+void xa_delete_node(struct xa_node *node, xa_update_node_t update)
+{
+	struct xa_state xas = {
+		.xa = node->array,
+		.xa_index = (unsigned long)node->offset <<
+				(node->shift + XA_CHUNK_SHIFT),
+		.xa_shift = node->shift + XA_CHUNK_SHIFT,
+		.xa_offset = node->offset,
+		.xa_node = xa_parent_locked(node->array, node),
+		.xa_update = update,
+	};
+
+	xas_store(&xas, NULL);
+}
+EXPORT_SYMBOL_GPL(xa_delete_node);	/* For the benefit of the test suite */
+
 /**
  * xa_destroy() - Free all internal data structures.
  * @xa: XArray.
diff --git a/mm/workingset.c b/mm/workingset.c
index 92e66113a577..e185bfb8bd4e 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -519,12 +519,11 @@ static enum lru_status shadow_lru_isolate(struct list_head *item,
 					  void *arg) __must_hold(lru_lock)
 {
 	struct xa_node *node = container_of(item, struct xa_node, private_list);
-	XA_STATE(xas, node->array, 0);
 	struct address_space *mapping;
 	int ret;
 
 	/*
-	 * Page cache insertions and deletions synchroneously maintain
+	 * Page cache insertions and deletions synchronously maintain
 	 * the shadow node LRU under the i_pages lock and the
 	 * lru_lock.  Because the page cache tree is emptied before
 	 * the inode can be destroyed, holding the lru_lock pins any
@@ -559,15 +558,7 @@ static enum lru_status shadow_lru_isolate(struct list_head *item,
 	if (WARN_ON_ONCE(node->count != node->nr_values))
 		goto out_invalid;
 	mapping->nrexceptional -= node->nr_values;
-	xas.xa_node = xa_parent_locked(&mapping->i_pages, node);
-	xas.xa_offset = node->offset;
-	xas.xa_shift = node->shift + XA_CHUNK_SHIFT;
-	xas_set_update(&xas, workingset_update_node);
-	/*
-	 * We could store a shadow entry here which was the minimum of the
-	 * shadow entries we were tracking ...
-	 */
-	xas_store(&xas, NULL);
+	xa_delete_node(node, workingset_update_node);
 	__inc_lruvec_slab_state(node, WORKINGSET_NODERECLAIM);
 
 out_invalid:
-- 
cgit v1.2.3


From ca7b639e8611b3260a30b18aaa0d6db9c80a75ef Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Sun, 2 Aug 2020 14:17:21 -0400
Subject: XArray: Fix xas_reload for multi-index entries

xas_reload() was only checking that the head entry was still at the
head index.  If the entry has been split, that's not enough as there
may be a different entry at the specified index now.

Solve this by checking the slot for the requested index instead of the
head index.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 include/linux/xarray.h | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 29db4e16eb89..4be9c57132fe 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -1524,10 +1524,21 @@ void xas_create_range(struct xa_state *);
 static inline void *xas_reload(struct xa_state *xas)
 {
 	struct xa_node *node = xas->xa_node;
-
-	if (node)
-		return xa_entry(xas->xa, node, xas->xa_offset);
-	return xa_head(xas->xa);
+	void *entry;
+	char offset;
+
+	if (!node)
+		return xa_head(xas->xa);
+	if (IS_ENABLED(CONFIG_XARRAY_MULTI)) {
+		offset = (xas->xa_index >> node->shift) & XA_CHUNK_MASK;
+		entry = xa_entry(xas->xa, node, offset);
+		if (!xa_is_sibling(entry))
+			return entry;
+		offset = xa_to_sibling(entry);
+	} else {
+		offset = xas->xa_offset;
+	}
+	return xa_entry(xas->xa, node, offset);
 }
 
 /**
-- 
cgit v1.2.3


From f78b8250a076ac63ddd021c7ea9739bcc2f6f737 Mon Sep 17 00:00:00 2001
From: Hui Su <sh_def@163.com>
Date: Mon, 28 Sep 2020 01:15:53 +0800
Subject: radix-tree: fix the comment of radix_tree_next_slot()

fix the comment of radix_tree_next_slot():
interator --> iterator.

Signed-off-by: Hui Su <sh_def@163.com>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 include/linux/radix-tree.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 5c85059a92ba..64ad900ac742 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -377,7 +377,7 @@ radix_tree_chunk_size(struct radix_tree_iter *iter)
  * radix_tree_next_slot - find next slot in chunk
  *
  * @slot:	pointer to current slot
- * @iter:	pointer to interator state
+ * @iter:	pointer to iterator state
  * @flags:	RADIX_TREE_ITER_*, should be constant
  * Returns:	pointer to next slot, or NULL if there no more left
  *
-- 
cgit v1.2.3


From 8bca49e43fb5994bd2a03f3f114cf89bc6f87a14 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 22 Apr 2020 15:51:55 +0300
Subject: drm: shmobile: Reduce include dependencies

This file doesn't need anything provided by <linux/kernel.h>.
All it needs are some types, which are provided by <drm/drm_mode.h>.

Drop unneeded <linux/kernel.h> completely.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200422125201.37618-1-andriy.shevchenko@linux.intel.com
---
 include/linux/platform_data/shmob_drm.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/platform_data/shmob_drm.h b/include/linux/platform_data/shmob_drm.h
index fe815d7d9f58..d661399b217d 100644
--- a/include/linux/platform_data/shmob_drm.h
+++ b/include/linux/platform_data/shmob_drm.h
@@ -10,8 +10,6 @@
 #ifndef __SHMOB_DRM_H__
 #define __SHMOB_DRM_H__
 
-#include <linux/kernel.h>
-
 #include <drm/drm_mode.h>
 
 enum shmob_drm_clk_source {
-- 
cgit v1.2.3


From 3b481d91356e5693d8358d4ef9c383bdb92c8da0 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Thu, 24 Sep 2020 13:53:28 -0700
Subject: block: add zone specific block statuses

A zoned device with limited resources to open or activate zones may
return an error when the host exceeds those limits. The same command may
be successful if retried later, but the host needs to wait for specific
zone states before it should expect a retry to succeed. Have the block
layer provide an appropriate status for these conditions so applications
can distinuguish this error for special handling.

Cc: linux-api@vger.kernel.org
Cc: Niklas Cassel <niklas.cassel@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 Documentation/block/queue-sysfs.rst |  8 ++++++++
 block/blk-core.c                    |  4 ++++
 include/linux/blk_types.h           | 18 ++++++++++++++++++
 3 files changed, 30 insertions(+)

(limited to 'include/linux')

diff --git a/Documentation/block/queue-sysfs.rst b/Documentation/block/queue-sysfs.rst
index f261a5c84170..2638d3446b79 100644
--- a/Documentation/block/queue-sysfs.rst
+++ b/Documentation/block/queue-sysfs.rst
@@ -124,6 +124,10 @@ For zoned block devices (zoned attribute indicating "host-managed" or
 EXPLICIT OPEN, IMPLICIT OPEN or CLOSED, is limited by this value.
 If this value is 0, there is no limit.
 
+If the host attempts to exceed this limit, the driver should report this error
+with BLK_STS_ZONE_ACTIVE_RESOURCE, which user space may see as the EOVERFLOW
+errno.
+
 max_open_zones (RO)
 -------------------
 For zoned block devices (zoned attribute indicating "host-managed" or
@@ -131,6 +135,10 @@ For zoned block devices (zoned attribute indicating "host-managed" or
 EXPLICIT OPEN or IMPLICIT OPEN, is limited by this value.
 If this value is 0, there is no limit.
 
+If the host attempts to exceed this limit, the driver should report this error
+with BLK_STS_ZONE_OPEN_RESOURCE, which user space may see as the ETOOMANYREFS
+errno.
+
 max_sectors_kb (RW)
 -------------------
 This is the maximum number of kilobytes that the block layer will allow
diff --git a/block/blk-core.c b/block/blk-core.c
index ac00d2fa4eb4..2db8bda43b6e 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -186,6 +186,10 @@ static const struct {
 	/* device mapper special case, should not leak out: */
 	[BLK_STS_DM_REQUEUE]	= { -EREMCHG, "dm internal retry" },
 
+	/* zone device specific errors */
+	[BLK_STS_ZONE_OPEN_RESOURCE]	= { -ETOOMANYREFS, "open zones exceeded" },
+	[BLK_STS_ZONE_ACTIVE_RESOURCE]	= { -EOVERFLOW, "active zones exceeded" },
+
 	/* everything else not covered above: */
 	[BLK_STS_IOERR]		= { -EIO,	"I/O" },
 };
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 7d7c13238fdb..d9b69bbde5cc 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -104,6 +104,24 @@ typedef u8 __bitwise blk_status_t;
  */
 #define BLK_STS_ZONE_RESOURCE	((__force blk_status_t)14)
 
+/*
+ * BLK_STS_ZONE_OPEN_RESOURCE is returned from the driver in the completion
+ * path if the device returns a status indicating that too many zone resources
+ * are currently open. The same command should be successful if resubmitted
+ * after the number of open zones decreases below the device's limits, which is
+ * reported in the request_queue's max_open_zones.
+ */
+#define BLK_STS_ZONE_OPEN_RESOURCE	((__force blk_status_t)15)
+
+/*
+ * BLK_STS_ZONE_ACTIVE_RESOURCE is returned from the driver in the completion
+ * path if the device returns a status indicating that too many zone resources
+ * are currently active. The same command should be successful if resubmitted
+ * after the number of active zones decreases below the device's limits, which
+ * is reported in the request_queue's max_active_zones.
+ */
+#define BLK_STS_ZONE_ACTIVE_RESOURCE	((__force blk_status_t)16)
+
 /**
  * blk_path_error - returns true if error may be path related
  * @error: status the request was completed with
-- 
cgit v1.2.3


From bf41a0910cb2dd06abd4d6a920edcee798460ad7 Mon Sep 17 00:00:00 2001
From: Rishabh Bhatnagar <rishabhb@codeaurora.org>
Date: Fri, 2 Oct 2020 11:09:02 -0700
Subject: remoteproc: Change default dump configuration to "disabled"

Currently "default" configuration option means coredumps are
enabled. To avoid confusion rename the "default" configuration
option to "enabled" and disable collection of dumps by default
as doing so makes sense for production devices.

Signed-off-by: Rishabh Bhatnagar <rishabhb@codeaurora.org>
Link: https://lore.kernel.org/r/1601662144-5964-2-git-send-email-rishabhb@codeaurora.org
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 drivers/remoteproc/remoteproc_coredump.c |  6 +++---
 drivers/remoteproc/remoteproc_debugfs.c  | 21 ++++++++++-----------
 include/linux/remoteproc.h               |  8 ++++----
 3 files changed, 17 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/remoteproc/remoteproc_coredump.c b/drivers/remoteproc/remoteproc_coredump.c
index bb15a29038e8..34530dc20cb4 100644
--- a/drivers/remoteproc/remoteproc_coredump.c
+++ b/drivers/remoteproc/remoteproc_coredump.c
@@ -257,7 +257,7 @@ void rproc_coredump(struct rproc *rproc)
 		 * directly read from device memory.
 		 */
 		data_size += elf_size_of_phdr(class);
-		if (dump_conf == RPROC_COREDUMP_DEFAULT)
+		if (dump_conf == RPROC_COREDUMP_ENABLED)
 			data_size += segment->size;
 
 		phnum++;
@@ -297,14 +297,14 @@ void rproc_coredump(struct rproc *rproc)
 		elf_phdr_set_p_flags(class, phdr, PF_R | PF_W | PF_X);
 		elf_phdr_set_p_align(class, phdr, 0);
 
-		if (dump_conf == RPROC_COREDUMP_DEFAULT)
+		if (dump_conf == RPROC_COREDUMP_ENABLED)
 			rproc_copy_segment(rproc, data + offset, segment, 0,
 					   segment->size);
 
 		offset += elf_phdr_get_p_filesz(class, phdr);
 		phdr += elf_size_of_phdr(class);
 	}
-	if (dump_conf == RPROC_COREDUMP_DEFAULT) {
+	if (dump_conf == RPROC_COREDUMP_ENABLED) {
 		dev_coredumpv(&rproc->dev, data, data_size, GFP_KERNEL);
 		return;
 	}
diff --git a/drivers/remoteproc/remoteproc_debugfs.c b/drivers/remoteproc/remoteproc_debugfs.c
index 7ca823f6aa63..7e5845376e9f 100644
--- a/drivers/remoteproc/remoteproc_debugfs.c
+++ b/drivers/remoteproc/remoteproc_debugfs.c
@@ -33,9 +33,9 @@ static struct dentry *rproc_dbg;
  * enum rproc_coredump_mechanism
  */
 static const char * const rproc_coredump_str[] = {
-	[RPROC_COREDUMP_DEFAULT]	= "default",
-	[RPROC_COREDUMP_INLINE]		= "inline",
 	[RPROC_COREDUMP_DISABLED]	= "disabled",
+	[RPROC_COREDUMP_ENABLED]	= "enabled",
+	[RPROC_COREDUMP_INLINE]		= "inline",
 };
 
 /* Expose the current coredump configuration via debugfs */
@@ -54,20 +54,19 @@ static ssize_t rproc_coredump_read(struct file *filp, char __user *userbuf,
 
 /*
  * By writing to the 'coredump' debugfs entry, we control the behavior of the
- * coredump mechanism dynamically. The default value of this entry is "default".
+ * coredump mechanism dynamically. The default value of this entry is "disabled".
  *
  * The 'coredump' debugfs entry supports these commands:
  *
- * default:	This is the default coredump mechanism. When the remoteproc
- *		crashes the entire coredump will be copied to a separate buffer
- *		and exposed to userspace.
+ * disabled:	By default coredump collection is disabled. Recovery will
+ *		proceed without collecting any dump.
+ *
+ * enabled:	When the remoteproc crashes the entire coredump will be copied
+ *		to a separate buffer and exposed to userspace.
  *
  * inline:	The coredump will not be copied to a separate buffer and the
  *		recovery process will have to wait until data is read by
  *		userspace. But this avoid usage of extra memory.
- *
- * disabled:	This will disable coredump. Recovery will proceed without
- *		collecting any dump.
  */
 static ssize_t rproc_coredump_write(struct file *filp,
 				    const char __user *user_buf, size_t count,
@@ -96,10 +95,10 @@ static ssize_t rproc_coredump_write(struct file *filp,
 
 	if (!strncmp(buf, "disabled", count)) {
 		rproc->dump_conf = RPROC_COREDUMP_DISABLED;
+	} else if (!strncmp(buf, "enabled", count)) {
+		rproc->dump_conf = RPROC_COREDUMP_ENABLED;
 	} else if (!strncmp(buf, "inline", count)) {
 		rproc->dump_conf = RPROC_COREDUMP_INLINE;
-	} else if (!strncmp(buf, "default", count)) {
-		rproc->dump_conf = RPROC_COREDUMP_DEFAULT;
 	} else {
 		dev_err(&rproc->dev, "Invalid coredump configuration\n");
 		err = -EINVAL;
diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h
index 2fa68bf5aa4f..3fa3ba6498e8 100644
--- a/include/linux/remoteproc.h
+++ b/include/linux/remoteproc.h
@@ -442,16 +442,16 @@ enum rproc_crash_type {
 
 /**
  * enum rproc_dump_mechanism - Coredump options for core
- * @RPROC_COREDUMP_DEFAULT:	Copy dump to separate buffer and carry on with
+ * @RPROC_COREDUMP_DISABLED:	Don't perform any dump
+ * @RPROC_COREDUMP_ENABLED:	Copy dump to separate buffer and carry on with
 				recovery
  * @RPROC_COREDUMP_INLINE:	Read segments directly from device memory. Stall
 				recovery until all segments are read
- * @RPROC_COREDUMP_DISABLED:	Don't perform any dump
  */
 enum rproc_dump_mechanism {
-	RPROC_COREDUMP_DEFAULT,
-	RPROC_COREDUMP_INLINE,
 	RPROC_COREDUMP_DISABLED,
+	RPROC_COREDUMP_ENABLED,
+	RPROC_COREDUMP_INLINE,
 };
 
 /**
-- 
cgit v1.2.3


From 44fa32f008ab7092842095a7a474c48303a2f186 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 12 Oct 2020 10:01:27 +0200
Subject: net: add function dev_fetch_sw_netstats for fetching pcpu_sw_netstats

In several places the same code is used to populate rtnl_link_stats64
fields with data from pcpu_sw_netstats. Therefore factor out this code
to a new function dev_fetch_sw_netstats().

v2:
- constify argument netstats
- don't ignore netstats being NULL or an ERRPTR
- switch to EXPORT_SYMBOL_GPL

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://lore.kernel.org/r/6d16a338-52f5-df69-0020-6bc771a7d498@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h |  2 ++
 net/core/dev.c            | 34 ++++++++++++++++++++++++++++++++++
 2 files changed, 36 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 948d7105e91a..964b494b0e8d 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4499,6 +4499,8 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev,
 					struct rtnl_link_stats64 *storage);
 void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64,
 			     const struct net_device_stats *netdev_stats);
+void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s,
+			   const struct pcpu_sw_netstats __percpu *netstats);
 
 extern int		netdev_max_backlog;
 extern int		netdev_tstamp_prequeue;
diff --git a/net/core/dev.c b/net/core/dev.c
index 22babf5bcc88..751e5264fd49 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -10328,6 +10328,40 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev,
 }
 EXPORT_SYMBOL(dev_get_stats);
 
+/**
+ *	dev_fetch_sw_netstats - get per-cpu network device statistics
+ *	@s: place to store stats
+ *	@netstats: per-cpu network stats to read from
+ *
+ *	Read per-cpu network statistics and populate the related fields in @s.
+ */
+void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s,
+			   const struct pcpu_sw_netstats __percpu *netstats)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		const struct pcpu_sw_netstats *stats;
+		struct pcpu_sw_netstats tmp;
+		unsigned int start;
+
+		stats = per_cpu_ptr(netstats, cpu);
+		do {
+			start = u64_stats_fetch_begin_irq(&stats->syncp);
+			tmp.rx_packets = stats->rx_packets;
+			tmp.rx_bytes   = stats->rx_bytes;
+			tmp.tx_packets = stats->tx_packets;
+			tmp.tx_bytes   = stats->tx_bytes;
+		} while (u64_stats_fetch_retry_irq(&stats->syncp, start));
+
+		s->rx_packets += tmp.rx_packets;
+		s->rx_bytes   += tmp.rx_bytes;
+		s->tx_packets += tmp.tx_packets;
+		s->tx_bytes   += tmp.tx_bytes;
+	}
+}
+EXPORT_SYMBOL_GPL(dev_fetch_sw_netstats);
+
 struct netdev_queue *dev_ingress_queue_create(struct net_device *dev)
 {
 	struct netdev_queue *queue = dev_ingress_queue(dev);
-- 
cgit v1.2.3


From 1f7a44f63e6c782c9c2aa9f18f40c23914e6b46a Mon Sep 17 00:00:00 2001
From: Nick Desaulniers <ndesaulniers@google.com>
Date: Tue, 13 Oct 2020 16:47:33 -0700
Subject: compiler-clang: add build check for clang 10.0.1

Patch series "set clang minimum version to 10.0.1", v3.

Adds a compile time #error to compiler-clang.h setting the effective
minimum supported version to clang 10.0.1.  A separate patch has already
been picked up into the Documentation/ tree also confirming the version.

Next are a series of reverts. One for 32b arm is a partial revert.

Then Marco suggested fixes to KASAN docs.

Finally, improve the warning for GCC too as per Kees.

This patch (of 7):

During Plumbers 2020, we voted to just support the latest release of Clang
for now.  Add a compile time check for this.

We plan to remove workarounds for older versions now, which will break in
subtle and not so subtle ways.

Suggested-by: Sedat Dilek <sedat.dilek@gmail.com>
Suggested-by: Nathan Chancellor <natechancellor@gmail.com>
Suggested-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Sedat Dilek <sedat.dilek@gmail.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Reviewed-by: Sedat Dilek <sedat.dilek@gmail.com>
Acked-by: Marco Elver <elver@google.com>
Acked-by: Nathan Chancellor <natechancellor@gmail.com>
Acked-by: Sedat Dilek <sedat.dilek@gmail.com>
Cc: Andrey Konovalov <andreyknvl@google.com>
Cc: Fangrui Song <maskray@google.com>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Link: https://lkml.kernel.org/r/20200902225911.209899-1-ndesaulniers@google.com
Link: https://lkml.kernel.org/r/20200902225911.209899-2-ndesaulniers@google.com
Link: https://github.com/ClangBuiltLinux/linux/issues/9
Link: https://github.com/ClangBuiltLinux/linux/issues/941
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/compiler-clang.h | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index cee0c728d39a..230604e7f057 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -3,6 +3,14 @@
 #error "Please don't include <linux/compiler-clang.h> directly, include <linux/compiler.h> instead."
 #endif
 
+#define CLANG_VERSION (__clang_major__ * 10000	\
+		     + __clang_minor__ * 100	\
+		     + __clang_patchlevel__)
+
+#if CLANG_VERSION < 100001
+# error Sorry, your version of Clang is too old - please use 10.0.1 or newer.
+#endif
+
 /* Compiler specific definitions for Clang compiler */
 
 /* same as gcc, this was present in clang-2.6 so we can assume it works
-- 
cgit v1.2.3


From c8db3b0a7ba7614f761f309d6aa7499127b18a0b Mon Sep 17 00:00:00 2001
From: Nick Desaulniers <ndesaulniers@google.com>
Date: Tue, 13 Oct 2020 16:47:55 -0700
Subject: compiler-gcc: improve version error

As Kees suggests, doing so provides developers with two useful pieces of
information:
- The kernel build was attempting to use GCC.
  (Maybe they accidentally poked the wrong configs in a CI.)
- They need 4.9 or better.
  ("Upgrade to what version?" doesn't need to be dug out of documentation,
   headers, etc.)

Suggested-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Sedat Dilek <sedat.dilek@gmail.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Reviewed-by: Nathan Chancellor <natechancellor@gmail.com>
Reviewed-by: Sedat Dilek <sedat.dilek@gmail.com>
Cc: Andrey Konovalov <andreyknvl@google.com>
Cc: Fangrui Song <maskray@google.com>
Cc: Marco Elver <elver@google.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Will Deacon <will@kernel.org>
Link: https://lkml.kernel.org/r/20200902225911.209899-8-ndesaulniers@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/compiler-gcc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index 7a3769040d7d..d1e3c6896b71 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -12,7 +12,7 @@
 
 /* https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 */
 #if GCC_VERSION < 40900
-# error Sorry, your compiler is too old - please upgrade it.
+# error Sorry, your version of GCC is too old - please use 4.9 or newer.
 #endif
 
 /* Optimization barrier */
-- 
cgit v1.2.3


From a25c13b3aa1bdbf100e8770902c30908728f8410 Mon Sep 17 00:00:00 2001
From: Nick Desaulniers <ndesaulniers@google.com>
Date: Tue, 13 Oct 2020 16:47:58 -0700
Subject: compiler.h: avoid escaped section names

The stringification operator, `#`, in the preprocessor escapes strings.
For example, `# "foo"` becomes `"\"foo\""`.  GCC and Clang differ in how
they treat section names that contain \".

The portable solution is to not use a string literal with the preprocessor
stringification operator.

In this case, since __section unconditionally uses the stringification
operator, we actually want the more verbose
__attribute__((__section__())).

Fixes: commit e04462fb82f8 ("Compiler Attributes: remove uses of __attribute__ from compiler.h")
Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Cc: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>
Cc: Nathan Chancellor <natechancellor@gmail.com>
Cc: Arvind Sankar <nivedita@alum.mit.edu>
Link: https://bugs.llvm.org/show_bug.cgi?id=42950
Link: https://lkml.kernel.org/r/20200929194318.548707-1-ndesaulniers@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/compiler.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 92ef163a7479..ac45f6d40d39 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -155,7 +155,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 	extern typeof(sym) sym;					\
 	static const unsigned long __kentry_##sym		\
 	__used							\
-	__section("___kentry" "+" #sym )			\
+	__attribute__((__section__("___kentry+" #sym)))		\
 	= (unsigned long)&sym;
 #endif
 
-- 
cgit v1.2.3


From 4d6fb34acb5d0bfc579ccd29df9cc6f653e51ab2 Mon Sep 17 00:00:00 2001
From: Nick Desaulniers <ndesaulniers@google.com>
Date: Tue, 13 Oct 2020 16:48:01 -0700
Subject: export.h: fix section name for CONFIG_TRIM_UNUSED_KSYMS for Clang

When enabling CONFIG_TRIM_UNUSED_KSYMS, the linker will warn about the
orphan sections:

(".discard.ksym") is being placed in '".discard.ksym"'

repeatedly when linking vmlinux.  This is because the stringification
operator, `#`, in the preprocessor escapes strings.  GCC and Clang differ
in how they treat section names that contain \".

The portable solution is to not use a string literal with the preprocessor
stringification operator.

Fixes: commit bbda5ec671d3 ("kbuild: simplify dependency generation for CONFIG_TRIM_UNUSED_KSYMS")
Reported-by: kbuild test robot <lkp@intel.com>
Suggested-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Cc: Nathan Chancellor <natechancellor@gmail.com>
Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: Matthias Maennich <maennich@google.com>
Cc: Jessica Yu <jeyu@kernel.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Will Deacon <will@kernel.org>
Link: https://bugs.llvm.org/show_bug.cgi?id=42950
Link: https://github.com/ClangBuiltLinux/linux/issues/1166
Link: https://lkml.kernel.org/r/20200929190701.398762-1-ndesaulniers@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/export.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/export.h b/include/linux/export.h
index fceb5e855717..8933ff6ad23a 100644
--- a/include/linux/export.h
+++ b/include/linux/export.h
@@ -130,7 +130,7 @@ struct kernel_symbol {
  * discarded in the final link stage.
  */
 #define __ksym_marker(sym)	\
-	static int __ksym_marker_##sym[0] __section(".discard.ksym") __used
+	static int __ksym_marker_##sym[0] __section(.discard.ksym) __used
 
 #define __EXPORT_SYMBOL(sym, sec, ns)					\
 	__ksym_marker(sym);						\
-- 
cgit v1.2.3


From d7cff4ded857ff7cc3e49eb39cc14df9345b9662 Mon Sep 17 00:00:00 2001
From: tangjianqiang <wyqt1985@gmail.com>
Date: Tue, 13 Oct 2020 16:48:37 -0700
Subject: include/linux/slab.h: fix a typo error in comment

fix a typo error in slab.h
"allocagtor" -> "allocator"

Signed-off-by: tangjianqiang <tangjianqiang@xiaomi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Souptick Joarder <jrdr.linux@gmail.com>
Link: https://lkml.kernel.org/r/1600230053-24303-1-git-send-email-tangjianqiang@xiaomi.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/slab.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/slab.h b/include/linux/slab.h
index 24df2393ec03..9e155cc83b8a 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -279,7 +279,7 @@ static inline void __check_heap_object(const void *ptr, unsigned long n,
 #define KMALLOC_MAX_SIZE	(1UL << KMALLOC_SHIFT_MAX)
 /* Maximum size for which we actually use a slab cache */
 #define KMALLOC_MAX_CACHE_SIZE	(1UL << KMALLOC_SHIFT_HIGH)
-/* Maximum order allocatable via the slab allocagtor */
+/* Maximum order allocatable via the slab allocator */
 #define KMALLOC_MAX_ORDER	(KMALLOC_SHIFT_MAX - PAGE_SHIFT)
 
 /*
-- 
cgit v1.2.3


From 3b0d31011d39759e3ba7214f75f77bb31983b5a4 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Tue, 13 Oct 2020 16:49:02 -0700
Subject: x86/numa: add 'nohmat' option
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Disable parsing of the HMAT for debug, to workaround broken platform
instances, or cases where it is otherwise not wanted.

[rdunlap@infradead.org: fix build when CONFIG_ACPI is not set]
  Link: https://lkml.kernel.org/r/70e5ee34-9809-a997-7b49-499e4be61307@infradead.org

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Ben Skeggs <bskeggs@redhat.com>
Cc: Brice Goglin <Brice.Goglin@inria.fr>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: David Airlie <airlied@linux.ie>
Cc: David Hildenbrand <david@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Jia He <justin.he@arm.com>
Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Paul Mackerras <paulus@ozlabs.org>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Will Deacon <will@kernel.org>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Hulk Robot <hulkci@huawei.com>
Cc: Jason Yan <yanaijie@huawei.com>
Cc: "Jérôme Glisse" <jglisse@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: kernel test robot <lkp@intel.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Link: https://lkml.kernel.org/r/159643095540.4062302.732962081968036212.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/x86/x86_64/boot-options.rst | 4 ++++
 arch/x86/mm/numa.c                        | 2 ++
 drivers/acpi/numa/hmat.c                  | 8 +++++++-
 include/acpi/acpi_numa.h                  | 8 ++++++++
 include/linux/acpi.h                      | 2 ++
 5 files changed, 23 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/Documentation/x86/x86_64/boot-options.rst b/Documentation/x86/x86_64/boot-options.rst
index 2b98efb5ba7f..324cefff92e7 100644
--- a/Documentation/x86/x86_64/boot-options.rst
+++ b/Documentation/x86/x86_64/boot-options.rst
@@ -173,6 +173,10 @@ NUMA
   numa=noacpi
     Don't parse the SRAT table for NUMA setup
 
+  numa=nohmat
+    Don't parse the HMAT table for NUMA setup, or soft-reserved memory
+    partitioning.
+
   numa=fake=<size>[MG]
     If given as a memory unit, fills all system RAM with nodes of
     size interleaved over physical nodes.
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 87c52822cc44..f3805bbaa784 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -41,6 +41,8 @@ static __init int numa_setup(char *opt)
 		return numa_emu_cmdline(opt + 5);
 	if (!strncmp(opt, "noacpi", 6))
 		disable_srat();
+	if (!strncmp(opt, "nohmat", 6))
+		disable_hmat();
 	return 0;
 }
 early_param("numa", numa_setup);
diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c
index 2c32cfb72370..a12e36a12618 100644
--- a/drivers/acpi/numa/hmat.c
+++ b/drivers/acpi/numa/hmat.c
@@ -26,6 +26,12 @@
 #include <linux/sysfs.h>
 
 static u8 hmat_revision;
+static int hmat_disable __initdata;
+
+void __init disable_hmat(void)
+{
+	hmat_disable = 1;
+}
 
 static LIST_HEAD(targets);
 static LIST_HEAD(initiators);
@@ -814,7 +820,7 @@ static __init int hmat_init(void)
 	enum acpi_hmat_type i;
 	acpi_status status;
 
-	if (srat_disabled())
+	if (srat_disabled() || hmat_disable)
 		return 0;
 
 	status = acpi_get_table(ACPI_SIG_SRAT, 0, &tbl);
diff --git a/include/acpi/acpi_numa.h b/include/acpi/acpi_numa.h
index 8784183b2204..0e9302285f14 100644
--- a/include/acpi/acpi_numa.h
+++ b/include/acpi/acpi_numa.h
@@ -27,4 +27,12 @@ static inline void disable_srat(void)
 {
 }
 #endif				/* CONFIG_ACPI_NUMA */
+
+#ifdef CONFIG_ACPI_HMAT
+extern void disable_hmat(void);
+#else				/* CONFIG_ACPI_HMAT */
+static inline void disable_hmat(void)
+{
+}
+#endif				/* CONFIG_ACPI_HMAT */
 #endif				/* __ACP_NUMA_H */
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 64ae25c59d55..cfa8c0015863 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -709,6 +709,8 @@ static inline u64 acpi_arch_get_root_pointer(void)
 #define ACPI_HANDLE_FWNODE(fwnode)	(NULL)
 #define ACPI_DEVICE_CLASS(_cls, _msk)	.cls = (0), .cls_msk = (0),
 
+#include <acpi/acpi_numa.h>
+
 struct fwnode_handle;
 
 static inline bool acpi_dev_found(const char *hid)
-- 
cgit v1.2.3


From c01044cc819160323f3ca4acd44fca487c4432e6 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Tue, 13 Oct 2020 16:49:13 -0700
Subject: ACPI: HMAT: refactor hmat_register_target_device to
 hmem_register_device
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In preparation for exposing "Soft Reserved" memory ranges without an HMAT,
move the hmem device registration to its own compilation unit and make the
implementation generic.

The generic implementation drops usage acpi_map_pxm_to_online_node() that
was translating ACPI proximity domain values and instead relies on
numa_map_to_online_node() to determine the numa node for the device.

[joao.m.martins@oracle.com: CONFIG_DEV_DAX_HMEM_DEVICES should depend on CONFIG_DAX=y]
  Link: https://lkml.kernel.org/r/8f34727f-ec2d-9395-cb18-969ec8a5d0d4@oracle.com

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Ben Skeggs <bskeggs@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brice Goglin <Brice.Goglin@inria.fr>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: David Airlie <airlied@linux.ie>
Cc: David Hildenbrand <david@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Jia He <justin.he@arm.com>
Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Paul Mackerras <paulus@ozlabs.org>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Will Deacon <will@kernel.org>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Hulk Robot <hulkci@huawei.com>
Cc: Jason Yan <yanaijie@huawei.com>
Cc: "Jérôme Glisse" <jglisse@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: kernel test robot <lkp@intel.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Link: https://lkml.kernel.org/r/159643096584.4062302.5035370788475153738.stgit@dwillia2-desk3.amr.corp.intel.com
Link: https://lore.kernel.org/r/158318761484.2216124.2049322072599482736.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/acpi/numa/hmat.c  | 68 +++++------------------------------------------
 drivers/dax/Kconfig       |  4 +++
 drivers/dax/Makefile      |  3 +--
 drivers/dax/hmem.c        | 56 --------------------------------------
 drivers/dax/hmem/Makefile |  5 ++++
 drivers/dax/hmem/device.c | 65 ++++++++++++++++++++++++++++++++++++++++++++
 drivers/dax/hmem/hmem.c   | 56 ++++++++++++++++++++++++++++++++++++++
 include/linux/dax.h       |  8 ++++++
 8 files changed, 145 insertions(+), 120 deletions(-)
 delete mode 100644 drivers/dax/hmem.c
 create mode 100644 drivers/dax/hmem/Makefile
 create mode 100644 drivers/dax/hmem/device.c
 create mode 100644 drivers/dax/hmem/hmem.c

(limited to 'include/linux')

diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c
index a12e36a12618..134bcb40b2af 100644
--- a/drivers/acpi/numa/hmat.c
+++ b/drivers/acpi/numa/hmat.c
@@ -24,6 +24,7 @@
 #include <linux/mutex.h>
 #include <linux/node.h>
 #include <linux/sysfs.h>
+#include <linux/dax.h>
 
 static u8 hmat_revision;
 static int hmat_disable __initdata;
@@ -640,66 +641,6 @@ static void hmat_register_target_perf(struct memory_target *target)
 	node_set_perf_attrs(mem_nid, &target->hmem_attrs, 0);
 }
 
-static void hmat_register_target_device(struct memory_target *target,
-		struct resource *r)
-{
-	/* define a clean / non-busy resource for the platform device */
-	struct resource res = {
-		.start = r->start,
-		.end = r->end,
-		.flags = IORESOURCE_MEM,
-	};
-	struct platform_device *pdev;
-	struct memregion_info info;
-	int rc, id;
-
-	rc = region_intersects(res.start, resource_size(&res), IORESOURCE_MEM,
-			IORES_DESC_SOFT_RESERVED);
-	if (rc != REGION_INTERSECTS)
-		return;
-
-	id = memregion_alloc(GFP_KERNEL);
-	if (id < 0) {
-		pr_err("memregion allocation failure for %pr\n", &res);
-		return;
-	}
-
-	pdev = platform_device_alloc("hmem", id);
-	if (!pdev) {
-		pr_err("hmem device allocation failure for %pr\n", &res);
-		goto out_pdev;
-	}
-
-	pdev->dev.numa_node = acpi_map_pxm_to_online_node(target->memory_pxm);
-	info = (struct memregion_info) {
-		.target_node = acpi_map_pxm_to_node(target->memory_pxm),
-	};
-	rc = platform_device_add_data(pdev, &info, sizeof(info));
-	if (rc < 0) {
-		pr_err("hmem memregion_info allocation failure for %pr\n", &res);
-		goto out_pdev;
-	}
-
-	rc = platform_device_add_resources(pdev, &res, 1);
-	if (rc < 0) {
-		pr_err("hmem resource allocation failure for %pr\n", &res);
-		goto out_resource;
-	}
-
-	rc = platform_device_add(pdev);
-	if (rc < 0) {
-		dev_err(&pdev->dev, "device add failed for %pr\n", &res);
-		goto out_resource;
-	}
-
-	return;
-
-out_resource:
-	put_device(&pdev->dev);
-out_pdev:
-	memregion_free(id);
-}
-
 static void hmat_register_target_devices(struct memory_target *target)
 {
 	struct resource *res;
@@ -711,8 +652,11 @@ static void hmat_register_target_devices(struct memory_target *target)
 	if (!IS_ENABLED(CONFIG_DEV_DAX_HMEM))
 		return;
 
-	for (res = target->memregions.child; res; res = res->sibling)
-		hmat_register_target_device(target, res);
+	for (res = target->memregions.child; res; res = res->sibling) {
+		int target_nid = acpi_map_pxm_to_node(target->memory_pxm);
+
+		hmem_register_device(target_nid, res);
+	}
 }
 
 static void hmat_register_target(struct memory_target *target)
diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig
index 3b6c06f07326..a66dff78f298 100644
--- a/drivers/dax/Kconfig
+++ b/drivers/dax/Kconfig
@@ -48,6 +48,10 @@ config DEV_DAX_HMEM
 
 	  Say M if unsure.
 
+config DEV_DAX_HMEM_DEVICES
+	depends on DEV_DAX_HMEM && DAX=y
+	def_bool y
+
 config DEV_DAX_KMEM
 	tristate "KMEM DAX: volatile-use of persistent memory"
 	default DEV_DAX
diff --git a/drivers/dax/Makefile b/drivers/dax/Makefile
index 80065b38b3c4..9d4ba672d305 100644
--- a/drivers/dax/Makefile
+++ b/drivers/dax/Makefile
@@ -2,11 +2,10 @@
 obj-$(CONFIG_DAX) += dax.o
 obj-$(CONFIG_DEV_DAX) += device_dax.o
 obj-$(CONFIG_DEV_DAX_KMEM) += kmem.o
-obj-$(CONFIG_DEV_DAX_HMEM) += dax_hmem.o
 
 dax-y := super.o
 dax-y += bus.o
 device_dax-y := device.o
-dax_hmem-y := hmem.o
 
 obj-y += pmem/
+obj-y += hmem/
diff --git a/drivers/dax/hmem.c b/drivers/dax/hmem.c
deleted file mode 100644
index fe7214daf62e..000000000000
--- a/drivers/dax/hmem.c
+++ /dev/null
@@ -1,56 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/platform_device.h>
-#include <linux/memregion.h>
-#include <linux/module.h>
-#include <linux/pfn_t.h>
-#include "bus.h"
-
-static int dax_hmem_probe(struct platform_device *pdev)
-{
-	struct device *dev = &pdev->dev;
-	struct dev_pagemap pgmap = { };
-	struct dax_region *dax_region;
-	struct memregion_info *mri;
-	struct dev_dax *dev_dax;
-	struct resource *res;
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res)
-		return -ENOMEM;
-
-	mri = dev->platform_data;
-	memcpy(&pgmap.res, res, sizeof(*res));
-
-	dax_region = alloc_dax_region(dev, pdev->id, res, mri->target_node,
-			PMD_SIZE, PFN_DEV|PFN_MAP);
-	if (!dax_region)
-		return -ENOMEM;
-
-	dev_dax = devm_create_dev_dax(dax_region, 0, &pgmap);
-	if (IS_ERR(dev_dax))
-		return PTR_ERR(dev_dax);
-
-	/* child dev_dax instances now own the lifetime of the dax_region */
-	dax_region_put(dax_region);
-	return 0;
-}
-
-static int dax_hmem_remove(struct platform_device *pdev)
-{
-	/* devm handles teardown */
-	return 0;
-}
-
-static struct platform_driver dax_hmem_driver = {
-	.probe = dax_hmem_probe,
-	.remove = dax_hmem_remove,
-	.driver = {
-		.name = "hmem",
-	},
-};
-
-module_platform_driver(dax_hmem_driver);
-
-MODULE_ALIAS("platform:hmem*");
-MODULE_LICENSE("GPL v2");
-MODULE_AUTHOR("Intel Corporation");
diff --git a/drivers/dax/hmem/Makefile b/drivers/dax/hmem/Makefile
new file mode 100644
index 000000000000..a9d353d0c9ed
--- /dev/null
+++ b/drivers/dax/hmem/Makefile
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_DEV_DAX_HMEM) += dax_hmem.o
+obj-$(CONFIG_DEV_DAX_HMEM_DEVICES) += device.o
+
+dax_hmem-y := hmem.o
diff --git a/drivers/dax/hmem/device.c b/drivers/dax/hmem/device.c
new file mode 100644
index 000000000000..b9dd6b27745c
--- /dev/null
+++ b/drivers/dax/hmem/device.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/platform_device.h>
+#include <linux/memregion.h>
+#include <linux/module.h>
+#include <linux/dax.h>
+#include <linux/mm.h>
+
+void hmem_register_device(int target_nid, struct resource *r)
+{
+	/* define a clean / non-busy resource for the platform device */
+	struct resource res = {
+		.start = r->start,
+		.end = r->end,
+		.flags = IORESOURCE_MEM,
+	};
+	struct platform_device *pdev;
+	struct memregion_info info;
+	int rc, id;
+
+	rc = region_intersects(res.start, resource_size(&res), IORESOURCE_MEM,
+			IORES_DESC_SOFT_RESERVED);
+	if (rc != REGION_INTERSECTS)
+		return;
+
+	id = memregion_alloc(GFP_KERNEL);
+	if (id < 0) {
+		pr_err("memregion allocation failure for %pr\n", &res);
+		return;
+	}
+
+	pdev = platform_device_alloc("hmem", id);
+	if (!pdev) {
+		pr_err("hmem device allocation failure for %pr\n", &res);
+		goto out_pdev;
+	}
+
+	pdev->dev.numa_node = numa_map_to_online_node(target_nid);
+	info = (struct memregion_info) {
+		.target_node = target_nid,
+	};
+	rc = platform_device_add_data(pdev, &info, sizeof(info));
+	if (rc < 0) {
+		pr_err("hmem memregion_info allocation failure for %pr\n", &res);
+		goto out_pdev;
+	}
+
+	rc = platform_device_add_resources(pdev, &res, 1);
+	if (rc < 0) {
+		pr_err("hmem resource allocation failure for %pr\n", &res);
+		goto out_resource;
+	}
+
+	rc = platform_device_add(pdev);
+	if (rc < 0) {
+		dev_err(&pdev->dev, "device add failed for %pr\n", &res);
+		goto out_resource;
+	}
+
+	return;
+
+out_resource:
+	put_device(&pdev->dev);
+out_pdev:
+	memregion_free(id);
+}
diff --git a/drivers/dax/hmem/hmem.c b/drivers/dax/hmem/hmem.c
new file mode 100644
index 000000000000..29ceb5795297
--- /dev/null
+++ b/drivers/dax/hmem/hmem.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/platform_device.h>
+#include <linux/memregion.h>
+#include <linux/module.h>
+#include <linux/pfn_t.h>
+#include "../bus.h"
+
+static int dax_hmem_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct dev_pagemap pgmap = { };
+	struct dax_region *dax_region;
+	struct memregion_info *mri;
+	struct dev_dax *dev_dax;
+	struct resource *res;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -ENOMEM;
+
+	mri = dev->platform_data;
+	memcpy(&pgmap.res, res, sizeof(*res));
+
+	dax_region = alloc_dax_region(dev, pdev->id, res, mri->target_node,
+			PMD_SIZE, PFN_DEV|PFN_MAP);
+	if (!dax_region)
+		return -ENOMEM;
+
+	dev_dax = devm_create_dev_dax(dax_region, 0, &pgmap);
+	if (IS_ERR(dev_dax))
+		return PTR_ERR(dev_dax);
+
+	/* child dev_dax instances now own the lifetime of the dax_region */
+	dax_region_put(dax_region);
+	return 0;
+}
+
+static int dax_hmem_remove(struct platform_device *pdev)
+{
+	/* devm handles teardown */
+	return 0;
+}
+
+static struct platform_driver dax_hmem_driver = {
+	.probe = dax_hmem_probe,
+	.remove = dax_hmem_remove,
+	.driver = {
+		.name = "hmem",
+	},
+};
+
+module_platform_driver(dax_hmem_driver);
+
+MODULE_ALIAS("platform:hmem*");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Intel Corporation");
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 43b39ab9de1a..4ec0bbf86205 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -238,4 +238,12 @@ static inline bool dax_mapping(struct address_space *mapping)
 	return mapping->host && IS_DAX(mapping->host);
 }
 
+#ifdef CONFIG_DEV_DAX_HMEM_DEVICES
+void hmem_register_device(int target_nid, struct resource *r);
+#else
+static inline void hmem_register_device(int target_nid, struct resource *r)
+{
+}
+#endif
+
 #endif
-- 
cgit v1.2.3


From a035b6bf863e5c42c2746de2a8ed6600140307e7 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Tue, 13 Oct 2020 16:49:23 -0700
Subject: mm/memory_hotplug: introduce default phys_to_target_node()
 implementation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In preparation to set a fallback value for dev_dax->target_node, introduce
generic fallback helpers for phys_to_target_node()

A generic implementation based on node-data or memblock was proposed, but
as noted by Mike:

    "Here again, I would prefer to add a weak default for
     phys_to_target_node() because the "generic" implementation is not really
     generic.

     The fallback to reserved ranges is x86 specfic because on x86 most of
     the reserved areas is not in memblock.memory. AFAIK, no other
     architecture does this."

The info message in the generic memory_add_physaddr_to_nid()
implementation is fixed up to properly reflect that
memory_add_physaddr_to_nid() communicates "online" node info and
phys_to_target_node() indicates "target / to-be-onlined" node info.

[akpm@linux-foundation.org: fix CONFIG_MEMORY_HOTPLUG=n build]
  Link: https://lkml.kernel.org/r/202008252130.7YrHIyMI%25lkp@intel.com

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Jia He <justin.he@arm.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Ben Skeggs <bskeggs@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brice Goglin <Brice.Goglin@inria.fr>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: David Airlie <airlied@linux.ie>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paul Mackerras <paulus@ozlabs.org>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Will Deacon <will@kernel.org>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Hulk Robot <hulkci@huawei.com>
Cc: Jason Yan <yanaijie@huawei.com>
Cc: "Jérôme Glisse" <jglisse@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: kernel test robot <lkp@intel.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Link: https://lkml.kernel.org/r/159643097768.4062302.3135192588966888630.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/mm/numa.c             |  1 -
 include/linux/memory_hotplug.h | 23 ++++++++++++++---------
 include/linux/numa.h           | 11 -----------
 mm/memory_hotplug.c            | 10 +++++++++-
 4 files changed, 23 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index f3805bbaa784..c62e274d52d0 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -917,7 +917,6 @@ int phys_to_target_node(phys_addr_t start)
 
 	return meminfo_to_nid(&numa_reserved_meminfo, start);
 }
-EXPORT_SYMBOL_GPL(phys_to_target_node);
 
 int memory_add_physaddr_to_nid(u64 start)
 {
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 375515803cd8..c0faa7a30c46 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -149,15 +149,6 @@ int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
 	      struct mhp_params *params);
 #endif /* ARCH_HAS_ADD_PAGES */
 
-#ifdef CONFIG_NUMA
-extern int memory_add_physaddr_to_nid(u64 start);
-#else
-static inline int memory_add_physaddr_to_nid(u64 start)
-{
-	return 0;
-}
-#endif
-
 #ifdef CONFIG_HAVE_ARCH_NODEDATA_EXTENSION
 /*
  * For supporting node-hotadd, we have to allocate a new pgdat.
@@ -284,6 +275,20 @@ static inline bool movable_node_is_enabled(void)
 }
 #endif /* ! CONFIG_MEMORY_HOTPLUG */
 
+#ifdef CONFIG_NUMA
+extern int memory_add_physaddr_to_nid(u64 start);
+extern int phys_to_target_node(u64 start);
+#else
+static inline int memory_add_physaddr_to_nid(u64 start)
+{
+	return 0;
+}
+static inline int phys_to_target_node(u64 start)
+{
+	return 0;
+}
+#endif
+
 #if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT)
 /*
  * pgdat resizing functions
diff --git a/include/linux/numa.h b/include/linux/numa.h
index a42df804679e..8cb33ccfb671 100644
--- a/include/linux/numa.h
+++ b/include/linux/numa.h
@@ -23,22 +23,11 @@
 #ifdef CONFIG_NUMA
 /* Generic implementation available */
 int numa_map_to_online_node(int node);
-
-/*
- * Optional architecture specific implementation, users need a "depends
- * on $ARCH"
- */
-int phys_to_target_node(phys_addr_t addr);
 #else
 static inline int numa_map_to_online_node(int node)
 {
 	return NUMA_NO_NODE;
 }
-
-static inline int phys_to_target_node(phys_addr_t addr)
-{
-	return NUMA_NO_NODE;
-}
 #endif
 
 #endif /* _LINUX_NUMA_H */
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index ce3e73e3a5c1..8e9e2d44cdad 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -353,11 +353,19 @@ int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages,
 #ifdef CONFIG_NUMA
 int __weak memory_add_physaddr_to_nid(u64 start)
 {
-	pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n",
+	pr_info_once("Unknown online node for memory at 0x%llx, assuming node 0\n",
 			start);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
+
+int __weak phys_to_target_node(u64 start)
+{
+	pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n",
+			start);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(phys_to_target_node);
 #endif
 
 /* find the smallest valid pfn in the range [start_pfn, end_pfn) */
-- 
cgit v1.2.3


From a4574f63edc6f76fb46dcd65d3eb4d5a8e23ba38 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Tue, 13 Oct 2020 16:50:29 -0700
Subject: mm/memremap_pages: convert to 'struct range'
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The 'struct resource' in 'struct dev_pagemap' is only used for holding
resource span information.  The other fields, 'name', 'flags', 'desc',
'parent', 'sibling', and 'child' are all unused wasted space.

This is in preparation for introducing a multi-range extension of
devm_memremap_pages().

The bulk of this change is unwinding all the places internal to libnvdimm
that used 'struct resource' unnecessarily, and replacing instances of
'struct dev_pagemap'.res with 'struct dev_pagemap'.range.

P2PDMA had a minor usage of the resource flags field, but only to report
failures with "%pR".  That is replaced with an open coded print of the
range.

[dan.carpenter@oracle.com: mm/hmm/test: use after free in dmirror_allocate_chunk()]
  Link: https://lkml.kernel.org/r/20200926121402.GA7467@kadam

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>	[xen]
Cc: Paul Mackerras <paulus@ozlabs.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Ben Skeggs <bskeggs@redhat.com>
Cc: David Airlie <airlied@linux.ie>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: "Jérôme Glisse" <jglisse@redhat.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brice Goglin <Brice.Goglin@inria.fr>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Hulk Robot <hulkci@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: Jason Yan <yanaijie@huawei.com>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Jia He <justin.he@arm.com>
Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: kernel test robot <lkp@intel.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Will Deacon <will@kernel.org>
Link: https://lkml.kernel.org/r/159643103173.4062302.768998885691711532.stgit@dwillia2-desk3.amr.corp.intel.com
Link: https://lkml.kernel.org/r/160106115761.30709.13539840236873663620.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/powerpc/kvm/book3s_hv_uvmem.c     | 13 +++---
 drivers/dax/bus.c                      | 10 ++---
 drivers/dax/bus.h                      |  2 +-
 drivers/dax/dax-private.h              |  5 ---
 drivers/dax/device.c                   |  3 +-
 drivers/dax/hmem/hmem.c                |  5 ++-
 drivers/dax/pmem/core.c                | 12 +++---
 drivers/gpu/drm/nouveau/nouveau_dmem.c | 14 +++----
 drivers/nvdimm/badrange.c              | 26 ++++++------
 drivers/nvdimm/claim.c                 | 13 +++---
 drivers/nvdimm/nd.h                    |  3 +-
 drivers/nvdimm/pfn_devs.c              | 12 +++---
 drivers/nvdimm/pmem.c                  | 26 ++++++------
 drivers/nvdimm/region.c                | 21 ++++++----
 drivers/pci/p2pdma.c                   | 11 +++--
 drivers/xen/unpopulated-alloc.c        | 44 ++++++++++++-------
 include/linux/memremap.h               |  5 ++-
 include/linux/range.h                  |  6 +++
 lib/test_hmm.c                         | 50 +++++++++++-----------
 mm/memremap.c                          | 77 +++++++++++++++++-----------------
 tools/testing/nvdimm/test/iomap.c      |  2 +-
 21 files changed, 195 insertions(+), 165 deletions(-)

(limited to 'include/linux')

diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c
index 7705d5557239..29ec555055c2 100644
--- a/arch/powerpc/kvm/book3s_hv_uvmem.c
+++ b/arch/powerpc/kvm/book3s_hv_uvmem.c
@@ -687,9 +687,9 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm)
 	struct kvmppc_uvmem_page_pvt *pvt;
 	unsigned long pfn_last, pfn_first;
 
-	pfn_first = kvmppc_uvmem_pgmap.res.start >> PAGE_SHIFT;
+	pfn_first = kvmppc_uvmem_pgmap.range.start >> PAGE_SHIFT;
 	pfn_last = pfn_first +
-		   (resource_size(&kvmppc_uvmem_pgmap.res) >> PAGE_SHIFT);
+		   (range_len(&kvmppc_uvmem_pgmap.range) >> PAGE_SHIFT);
 
 	spin_lock(&kvmppc_uvmem_bitmap_lock);
 	bit = find_first_zero_bit(kvmppc_uvmem_bitmap,
@@ -1007,7 +1007,7 @@ static vm_fault_t kvmppc_uvmem_migrate_to_ram(struct vm_fault *vmf)
 static void kvmppc_uvmem_page_free(struct page *page)
 {
 	unsigned long pfn = page_to_pfn(page) -
-			(kvmppc_uvmem_pgmap.res.start >> PAGE_SHIFT);
+			(kvmppc_uvmem_pgmap.range.start >> PAGE_SHIFT);
 	struct kvmppc_uvmem_page_pvt *pvt;
 
 	spin_lock(&kvmppc_uvmem_bitmap_lock);
@@ -1170,7 +1170,8 @@ int kvmppc_uvmem_init(void)
 	}
 
 	kvmppc_uvmem_pgmap.type = MEMORY_DEVICE_PRIVATE;
-	kvmppc_uvmem_pgmap.res = *res;
+	kvmppc_uvmem_pgmap.range.start = res->start;
+	kvmppc_uvmem_pgmap.range.end = res->end;
 	kvmppc_uvmem_pgmap.ops = &kvmppc_uvmem_ops;
 	/* just one global instance: */
 	kvmppc_uvmem_pgmap.owner = &kvmppc_uvmem_pgmap;
@@ -1205,7 +1206,7 @@ void kvmppc_uvmem_free(void)
 		return;
 
 	memunmap_pages(&kvmppc_uvmem_pgmap);
-	release_mem_region(kvmppc_uvmem_pgmap.res.start,
-			   resource_size(&kvmppc_uvmem_pgmap.res));
+	release_mem_region(kvmppc_uvmem_pgmap.range.start,
+			   range_len(&kvmppc_uvmem_pgmap.range));
 	kfree(kvmppc_uvmem_bitmap);
 }
diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
index 53d07f2f1285..00fa73a8dfb4 100644
--- a/drivers/dax/bus.c
+++ b/drivers/dax/bus.c
@@ -515,7 +515,7 @@ static void dax_region_unregister(void *region)
 }
 
 struct dax_region *alloc_dax_region(struct device *parent, int region_id,
-		struct resource *res, int target_node, unsigned int align,
+		struct range *range, int target_node, unsigned int align,
 		unsigned long flags)
 {
 	struct dax_region *dax_region;
@@ -530,8 +530,8 @@ struct dax_region *alloc_dax_region(struct device *parent, int region_id,
 		return NULL;
 	}
 
-	if (!IS_ALIGNED(res->start, align)
-			|| !IS_ALIGNED(resource_size(res), align))
+	if (!IS_ALIGNED(range->start, align)
+			|| !IS_ALIGNED(range_len(range), align))
 		return NULL;
 
 	dax_region = kzalloc(sizeof(*dax_region), GFP_KERNEL);
@@ -546,8 +546,8 @@ struct dax_region *alloc_dax_region(struct device *parent, int region_id,
 	dax_region->target_node = target_node;
 	ida_init(&dax_region->ida);
 	dax_region->res = (struct resource) {
-		.start = res->start,
-		.end = res->end,
+		.start = range->start,
+		.end = range->end,
 		.flags = IORESOURCE_MEM | flags,
 	};
 
diff --git a/drivers/dax/bus.h b/drivers/dax/bus.h
index da27ea70a19a..72b92f95509f 100644
--- a/drivers/dax/bus.h
+++ b/drivers/dax/bus.h
@@ -13,7 +13,7 @@ void dax_region_put(struct dax_region *dax_region);
 
 #define IORESOURCE_DAX_STATIC (1UL << 0)
 struct dax_region *alloc_dax_region(struct device *parent, int region_id,
-		struct resource *res, int target_node, unsigned int align,
+		struct range *range, int target_node, unsigned int align,
 		unsigned long flags);
 
 enum dev_dax_subsys {
diff --git a/drivers/dax/dax-private.h b/drivers/dax/dax-private.h
index b81a1494d82b..0cbb2ec81ca7 100644
--- a/drivers/dax/dax-private.h
+++ b/drivers/dax/dax-private.h
@@ -61,11 +61,6 @@ struct dev_dax {
 	struct range range;
 };
 
-static inline u64 range_len(struct range *range)
-{
-	return range->end - range->start + 1;
-}
-
 static inline struct dev_dax *to_dev_dax(struct device *dev)
 {
 	return container_of(dev, struct dev_dax, dev);
diff --git a/drivers/dax/device.c b/drivers/dax/device.c
index 9833fa83b537..a14448bca83d 100644
--- a/drivers/dax/device.c
+++ b/drivers/dax/device.c
@@ -416,8 +416,7 @@ int dev_dax_probe(struct dev_dax *dev_dax)
 		pgmap = devm_kzalloc(dev, sizeof(*pgmap), GFP_KERNEL);
 		if (!pgmap)
 			return -ENOMEM;
-		pgmap->res.start = range->start;
-		pgmap->res.end = range->end;
+		pgmap->range = *range;
 	}
 	pgmap->type = MEMORY_DEVICE_GENERIC;
 	addr = devm_memremap_pages(dev, pgmap);
diff --git a/drivers/dax/hmem/hmem.c b/drivers/dax/hmem/hmem.c
index aa260009dfc7..1a3347bb6143 100644
--- a/drivers/dax/hmem/hmem.c
+++ b/drivers/dax/hmem/hmem.c
@@ -13,13 +13,16 @@ static int dax_hmem_probe(struct platform_device *pdev)
 	struct dev_dax_data data;
 	struct dev_dax *dev_dax;
 	struct resource *res;
+	struct range range;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res)
 		return -ENOMEM;
 
 	mri = dev->platform_data;
-	dax_region = alloc_dax_region(dev, pdev->id, res, mri->target_node,
+	range.start = res->start;
+	range.end = res->end;
+	dax_region = alloc_dax_region(dev, pdev->id, &range, mri->target_node,
 			PMD_SIZE, 0);
 	if (!dax_region)
 		return -ENOMEM;
diff --git a/drivers/dax/pmem/core.c b/drivers/dax/pmem/core.c
index 4fe700884338..62b26bfceab1 100644
--- a/drivers/dax/pmem/core.c
+++ b/drivers/dax/pmem/core.c
@@ -9,7 +9,7 @@
 
 struct dev_dax *__dax_pmem_probe(struct device *dev, enum dev_dax_subsys subsys)
 {
-	struct resource res;
+	struct range range;
 	int rc, id, region_id;
 	resource_size_t offset;
 	struct nd_pfn_sb *pfn_sb;
@@ -50,10 +50,10 @@ struct dev_dax *__dax_pmem_probe(struct device *dev, enum dev_dax_subsys subsys)
 	if (rc != 2)
 		return ERR_PTR(-EINVAL);
 
-	/* adjust the dax_region resource to the start of data */
-	memcpy(&res, &pgmap.res, sizeof(res));
-	res.start += offset;
-	dax_region = alloc_dax_region(dev, region_id, &res,
+	/* adjust the dax_region range to the start of data */
+	range = pgmap.range;
+	range.start += offset,
+	dax_region = alloc_dax_region(dev, region_id, &range,
 			nd_region->target_node, le32_to_cpu(pfn_sb->align),
 			IORESOURCE_DAX_STATIC);
 	if (!dax_region)
@@ -64,7 +64,7 @@ struct dev_dax *__dax_pmem_probe(struct device *dev, enum dev_dax_subsys subsys)
 		.id = id,
 		.pgmap = &pgmap,
 		.subsys = subsys,
-		.size = resource_size(&res),
+		.size = range_len(&range),
 	};
 	dev_dax = devm_create_dev_dax(&data);
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c
index 4e8112fde3e6..25811ed7e274 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dmem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c
@@ -101,7 +101,7 @@ unsigned long nouveau_dmem_page_addr(struct page *page)
 {
 	struct nouveau_dmem_chunk *chunk = nouveau_page_to_chunk(page);
 	unsigned long off = (page_to_pfn(page) << PAGE_SHIFT) -
-				chunk->pagemap.res.start;
+				chunk->pagemap.range.start;
 
 	return chunk->bo->offset + off;
 }
@@ -249,7 +249,8 @@ nouveau_dmem_chunk_alloc(struct nouveau_drm *drm, struct page **ppage)
 
 	chunk->drm = drm;
 	chunk->pagemap.type = MEMORY_DEVICE_PRIVATE;
-	chunk->pagemap.res = *res;
+	chunk->pagemap.range.start = res->start;
+	chunk->pagemap.range.end = res->end;
 	chunk->pagemap.ops = &nouveau_dmem_pagemap_ops;
 	chunk->pagemap.owner = drm->dev;
 
@@ -273,7 +274,7 @@ nouveau_dmem_chunk_alloc(struct nouveau_drm *drm, struct page **ppage)
 	list_add(&chunk->list, &drm->dmem->chunks);
 	mutex_unlock(&drm->dmem->mutex);
 
-	pfn_first = chunk->pagemap.res.start >> PAGE_SHIFT;
+	pfn_first = chunk->pagemap.range.start >> PAGE_SHIFT;
 	page = pfn_to_page(pfn_first);
 	spin_lock(&drm->dmem->lock);
 	for (i = 0; i < DMEM_CHUNK_NPAGES - 1; ++i, ++page) {
@@ -294,8 +295,7 @@ out_bo_unpin:
 out_bo_free:
 	nouveau_bo_ref(NULL, &chunk->bo);
 out_release:
-	release_mem_region(chunk->pagemap.res.start,
-			   resource_size(&chunk->pagemap.res));
+	release_mem_region(chunk->pagemap.range.start, range_len(&chunk->pagemap.range));
 out_free:
 	kfree(chunk);
 out:
@@ -382,8 +382,8 @@ nouveau_dmem_fini(struct nouveau_drm *drm)
 		nouveau_bo_ref(NULL, &chunk->bo);
 		list_del(&chunk->list);
 		memunmap_pages(&chunk->pagemap);
-		release_mem_region(chunk->pagemap.res.start,
-				   resource_size(&chunk->pagemap.res));
+		release_mem_region(chunk->pagemap.range.start,
+				   range_len(&chunk->pagemap.range));
 		kfree(chunk);
 	}
 
diff --git a/drivers/nvdimm/badrange.c b/drivers/nvdimm/badrange.c
index b9eeefa27e3a..aaf6e215a8c6 100644
--- a/drivers/nvdimm/badrange.c
+++ b/drivers/nvdimm/badrange.c
@@ -211,7 +211,7 @@ static void __add_badblock_range(struct badblocks *bb, u64 ns_offset, u64 len)
 }
 
 static void badblocks_populate(struct badrange *badrange,
-		struct badblocks *bb, const struct resource *res)
+		struct badblocks *bb, const struct range *range)
 {
 	struct badrange_entry *bre;
 
@@ -222,34 +222,34 @@ static void badblocks_populate(struct badrange *badrange,
 		u64 bre_end = bre->start + bre->length - 1;
 
 		/* Discard intervals with no intersection */
-		if (bre_end < res->start)
+		if (bre_end < range->start)
 			continue;
-		if (bre->start >  res->end)
+		if (bre->start > range->end)
 			continue;
 		/* Deal with any overlap after start of the namespace */
-		if (bre->start >= res->start) {
+		if (bre->start >= range->start) {
 			u64 start = bre->start;
 			u64 len;
 
-			if (bre_end <= res->end)
+			if (bre_end <= range->end)
 				len = bre->length;
 			else
-				len = res->start + resource_size(res)
+				len = range->start + range_len(range)
 					- bre->start;
-			__add_badblock_range(bb, start - res->start, len);
+			__add_badblock_range(bb, start - range->start, len);
 			continue;
 		}
 		/*
 		 * Deal with overlap for badrange starting before
 		 * the namespace.
 		 */
-		if (bre->start < res->start) {
+		if (bre->start < range->start) {
 			u64 len;
 
-			if (bre_end < res->end)
-				len = bre->start + bre->length - res->start;
+			if (bre_end < range->end)
+				len = bre->start + bre->length - range->start;
 			else
-				len = resource_size(res);
+				len = range_len(range);
 			__add_badblock_range(bb, 0, len);
 		}
 	}
@@ -267,7 +267,7 @@ static void badblocks_populate(struct badrange *badrange,
  * and add badblocks entries for all matching sub-ranges
  */
 void nvdimm_badblocks_populate(struct nd_region *nd_region,
-		struct badblocks *bb, const struct resource *res)
+		struct badblocks *bb, const struct range *range)
 {
 	struct nvdimm_bus *nvdimm_bus;
 
@@ -279,7 +279,7 @@ void nvdimm_badblocks_populate(struct nd_region *nd_region,
 	nvdimm_bus = walk_to_nvdimm_bus(&nd_region->dev);
 
 	nvdimm_bus_lock(&nvdimm_bus->dev);
-	badblocks_populate(&nvdimm_bus->badrange, bb, res);
+	badblocks_populate(&nvdimm_bus->badrange, bb, range);
 	nvdimm_bus_unlock(&nvdimm_bus->dev);
 }
 EXPORT_SYMBOL_GPL(nvdimm_badblocks_populate);
diff --git a/drivers/nvdimm/claim.c b/drivers/nvdimm/claim.c
index 22d865ba6353..5a7c80053c62 100644
--- a/drivers/nvdimm/claim.c
+++ b/drivers/nvdimm/claim.c
@@ -303,13 +303,16 @@ static int nsio_rw_bytes(struct nd_namespace_common *ndns,
 int devm_nsio_enable(struct device *dev, struct nd_namespace_io *nsio,
 		resource_size_t size)
 {
-	struct resource *res = &nsio->res;
 	struct nd_namespace_common *ndns = &nsio->common;
+	struct range range = {
+		.start = nsio->res.start,
+		.end = nsio->res.end,
+	};
 
 	nsio->size = size;
-	if (!devm_request_mem_region(dev, res->start, size,
+	if (!devm_request_mem_region(dev, range.start, size,
 				dev_name(&ndns->dev))) {
-		dev_warn(dev, "could not reserve region %pR\n", res);
+		dev_warn(dev, "could not reserve region %pR\n", &nsio->res);
 		return -EBUSY;
 	}
 
@@ -317,9 +320,9 @@ int devm_nsio_enable(struct device *dev, struct nd_namespace_io *nsio,
 	if (devm_init_badblocks(dev, &nsio->bb))
 		return -ENOMEM;
 	nvdimm_badblocks_populate(to_nd_region(ndns->dev.parent), &nsio->bb,
-			&nsio->res);
+			&range);
 
-	nsio->addr = devm_memremap(dev, res->start, size, ARCH_MEMREMAP_PMEM);
+	nsio->addr = devm_memremap(dev, range.start, size, ARCH_MEMREMAP_PMEM);
 
 	return PTR_ERR_OR_ZERO(nsio->addr);
 }
diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
index 72740108ba42..696b55556d4d 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -377,8 +377,9 @@ int nvdimm_namespace_detach_btt(struct nd_btt *nd_btt);
 const char *nvdimm_namespace_disk_name(struct nd_namespace_common *ndns,
 		char *name);
 unsigned int pmem_sector_size(struct nd_namespace_common *ndns);
+struct range;
 void nvdimm_badblocks_populate(struct nd_region *nd_region,
-		struct badblocks *bb, const struct resource *res);
+		struct badblocks *bb, const struct range *range);
 int devm_namespace_enable(struct device *dev, struct nd_namespace_common *ndns,
 		resource_size_t size);
 void devm_namespace_disable(struct device *dev,
diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
index 3e11ef8d3f5b..3c4787b92a6a 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/drivers/nvdimm/pfn_devs.c
@@ -672,7 +672,7 @@ static unsigned long init_altmap_reserve(resource_size_t base)
 
 static int __nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap)
 {
-	struct resource *res = &pgmap->res;
+	struct range *range = &pgmap->range;
 	struct vmem_altmap *altmap = &pgmap->altmap;
 	struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
 	u64 offset = le64_to_cpu(pfn_sb->dataoff);
@@ -689,16 +689,16 @@ static int __nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap)
 		.end_pfn = PHYS_PFN(end),
 	};
 
-	memcpy(res, &nsio->res, sizeof(*res));
-	res->start += start_pad;
-	res->end -= end_trunc;
-
+	*range = (struct range) {
+		.start = nsio->res.start + start_pad,
+		.end = nsio->res.end - end_trunc,
+	};
 	if (nd_pfn->mode == PFN_MODE_RAM) {
 		if (offset < reserve)
 			return -EINVAL;
 		nd_pfn->npfns = le64_to_cpu(pfn_sb->npfns);
 	} else if (nd_pfn->mode == PFN_MODE_PMEM) {
-		nd_pfn->npfns = PHYS_PFN((resource_size(res) - offset));
+		nd_pfn->npfns = PHYS_PFN((range_len(range) - offset));
 		if (le64_to_cpu(nd_pfn->pfn_sb->npfns) > nd_pfn->npfns)
 			dev_info(&nd_pfn->dev,
 					"number of pfns truncated from %lld to %ld\n",
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index c86a0ceaece6..1f394f44838f 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -375,7 +375,7 @@ static int pmem_attach_disk(struct device *dev,
 	struct nd_region *nd_region = to_nd_region(dev->parent);
 	int nid = dev_to_node(dev), fua;
 	struct resource *res = &nsio->res;
-	struct resource bb_res;
+	struct range bb_range;
 	struct nd_pfn *nd_pfn = NULL;
 	struct dax_device *dax_dev;
 	struct nd_pfn_sb *pfn_sb;
@@ -434,24 +434,26 @@ static int pmem_attach_disk(struct device *dev,
 		pfn_sb = nd_pfn->pfn_sb;
 		pmem->data_offset = le64_to_cpu(pfn_sb->dataoff);
 		pmem->pfn_pad = resource_size(res) -
-			resource_size(&pmem->pgmap.res);
+			range_len(&pmem->pgmap.range);
 		pmem->pfn_flags |= PFN_MAP;
-		memcpy(&bb_res, &pmem->pgmap.res, sizeof(bb_res));
-		bb_res.start += pmem->data_offset;
+		bb_range = pmem->pgmap.range;
+		bb_range.start += pmem->data_offset;
 	} else if (pmem_should_map_pages(dev)) {
-		memcpy(&pmem->pgmap.res, &nsio->res, sizeof(pmem->pgmap.res));
+		pmem->pgmap.range.start = res->start;
+		pmem->pgmap.range.end = res->end;
 		pmem->pgmap.type = MEMORY_DEVICE_FS_DAX;
 		pmem->pgmap.ops = &fsdax_pagemap_ops;
 		addr = devm_memremap_pages(dev, &pmem->pgmap);
 		pmem->pfn_flags |= PFN_MAP;
-		memcpy(&bb_res, &pmem->pgmap.res, sizeof(bb_res));
+		bb_range = pmem->pgmap.range;
 	} else {
 		if (devm_add_action_or_reset(dev, pmem_release_queue,
 					&pmem->pgmap))
 			return -ENOMEM;
 		addr = devm_memremap(dev, pmem->phys_addr,
 				pmem->size, ARCH_MEMREMAP_PMEM);
-		memcpy(&bb_res, &nsio->res, sizeof(bb_res));
+		bb_range.start =  res->start;
+		bb_range.end = res->end;
 	}
 
 	if (IS_ERR(addr))
@@ -480,7 +482,7 @@ static int pmem_attach_disk(struct device *dev,
 			/ 512);
 	if (devm_init_badblocks(dev, &pmem->bb))
 		return -ENOMEM;
-	nvdimm_badblocks_populate(nd_region, &pmem->bb, &bb_res);
+	nvdimm_badblocks_populate(nd_region, &pmem->bb, &bb_range);
 	disk->bb = &pmem->bb;
 
 	if (is_nvdimm_sync(nd_region))
@@ -591,8 +593,8 @@ static void nd_pmem_notify(struct device *dev, enum nvdimm_event event)
 	resource_size_t offset = 0, end_trunc = 0;
 	struct nd_namespace_common *ndns;
 	struct nd_namespace_io *nsio;
-	struct resource res;
 	struct badblocks *bb;
+	struct range range;
 	struct kernfs_node *bb_state;
 
 	if (event != NVDIMM_REVALIDATE_POISON)
@@ -628,9 +630,9 @@ static void nd_pmem_notify(struct device *dev, enum nvdimm_event event)
 		nsio = to_nd_namespace_io(&ndns->dev);
 	}
 
-	res.start = nsio->res.start + offset;
-	res.end = nsio->res.end - end_trunc;
-	nvdimm_badblocks_populate(nd_region, bb, &res);
+	range.start = nsio->res.start + offset;
+	range.end = nsio->res.end - end_trunc;
+	nvdimm_badblocks_populate(nd_region, bb, &range);
 	if (bb_state)
 		sysfs_notify_dirent(bb_state);
 }
diff --git a/drivers/nvdimm/region.c b/drivers/nvdimm/region.c
index 0f6978e72e7c..bfce87ed72ab 100644
--- a/drivers/nvdimm/region.c
+++ b/drivers/nvdimm/region.c
@@ -35,7 +35,10 @@ static int nd_region_probe(struct device *dev)
 		return rc;
 
 	if (is_memory(&nd_region->dev)) {
-		struct resource ndr_res;
+		struct range range = {
+			.start = nd_region->ndr_start,
+			.end = nd_region->ndr_start + nd_region->ndr_size - 1,
+		};
 
 		if (devm_init_badblocks(dev, &nd_region->bb))
 			return -ENODEV;
@@ -44,9 +47,7 @@ static int nd_region_probe(struct device *dev)
 		if (!nd_region->bb_state)
 			dev_warn(&nd_region->dev,
 					"'badblocks' notification disabled\n");
-		ndr_res.start = nd_region->ndr_start;
-		ndr_res.end = nd_region->ndr_start + nd_region->ndr_size - 1;
-		nvdimm_badblocks_populate(nd_region, &nd_region->bb, &ndr_res);
+		nvdimm_badblocks_populate(nd_region, &nd_region->bb, &range);
 	}
 
 	rc = nd_region_register_namespaces(nd_region, &err);
@@ -121,14 +122,16 @@ static void nd_region_notify(struct device *dev, enum nvdimm_event event)
 {
 	if (event == NVDIMM_REVALIDATE_POISON) {
 		struct nd_region *nd_region = to_nd_region(dev);
-		struct resource res;
 
 		if (is_memory(&nd_region->dev)) {
-			res.start = nd_region->ndr_start;
-			res.end = nd_region->ndr_start +
-				nd_region->ndr_size - 1;
+			struct range range = {
+				.start = nd_region->ndr_start,
+				.end = nd_region->ndr_start +
+					nd_region->ndr_size - 1,
+			};
+
 			nvdimm_badblocks_populate(nd_region,
-					&nd_region->bb, &res);
+					&nd_region->bb, &range);
 			if (nd_region->bb_state)
 				sysfs_notify_dirent(nd_region->bb_state);
 		}
diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c
index f357f9a32b3a..256850513813 100644
--- a/drivers/pci/p2pdma.c
+++ b/drivers/pci/p2pdma.c
@@ -185,9 +185,8 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size,
 		return -ENOMEM;
 
 	pgmap = &p2p_pgmap->pgmap;
-	pgmap->res.start = pci_resource_start(pdev, bar) + offset;
-	pgmap->res.end = pgmap->res.start + size - 1;
-	pgmap->res.flags = pci_resource_flags(pdev, bar);
+	pgmap->range.start = pci_resource_start(pdev, bar) + offset;
+	pgmap->range.end = pgmap->range.start + size - 1;
 	pgmap->type = MEMORY_DEVICE_PCI_P2PDMA;
 
 	p2p_pgmap->provider = pdev;
@@ -202,13 +201,13 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size,
 
 	error = gen_pool_add_owner(pdev->p2pdma->pool, (unsigned long)addr,
 			pci_bus_address(pdev, bar) + offset,
-			resource_size(&pgmap->res), dev_to_node(&pdev->dev),
+			range_len(&pgmap->range), dev_to_node(&pdev->dev),
 			pgmap->ref);
 	if (error)
 		goto pages_free;
 
-	pci_info(pdev, "added peer-to-peer DMA memory %pR\n",
-		 &pgmap->res);
+	pci_info(pdev, "added peer-to-peer DMA memory %#llx-%#llx\n",
+		 pgmap->range.start, pgmap->range.end);
 
 	return 0;
 
diff --git a/drivers/xen/unpopulated-alloc.c b/drivers/xen/unpopulated-alloc.c
index 3b98dc921426..091b8669eca3 100644
--- a/drivers/xen/unpopulated-alloc.c
+++ b/drivers/xen/unpopulated-alloc.c
@@ -18,27 +18,37 @@ static unsigned int list_count;
 static int fill_list(unsigned int nr_pages)
 {
 	struct dev_pagemap *pgmap;
+	struct resource *res;
 	void *vaddr;
 	unsigned int i, alloc_pages = round_up(nr_pages, PAGES_PER_SECTION);
-	int ret;
+	int ret = -ENOMEM;
+
+	res = kzalloc(sizeof(*res), GFP_KERNEL);
+	if (!res)
+		return -ENOMEM;
 
 	pgmap = kzalloc(sizeof(*pgmap), GFP_KERNEL);
 	if (!pgmap)
-		return -ENOMEM;
+		goto err_pgmap;
 
 	pgmap->type = MEMORY_DEVICE_GENERIC;
-	pgmap->res.name = "Xen scratch";
-	pgmap->res.flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+	res->name = "Xen scratch";
+	res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
 
-	ret = allocate_resource(&iomem_resource, &pgmap->res,
+	ret = allocate_resource(&iomem_resource, res,
 				alloc_pages * PAGE_SIZE, 0, -1,
 				PAGES_PER_SECTION * PAGE_SIZE, NULL, NULL);
 	if (ret < 0) {
 		pr_err("Cannot allocate new IOMEM resource\n");
-		kfree(pgmap);
-		return ret;
+		goto err_resource;
 	}
 
+	pgmap->range = (struct range) {
+		.start = res->start,
+		.end = res->end,
+	};
+	pgmap->owner = res;
+
 #ifdef CONFIG_XEN_HAVE_PVMMU
         /*
          * memremap will build page tables for the new memory so
@@ -50,14 +60,13 @@ static int fill_list(unsigned int nr_pages)
          * conflict with any devices.
          */
 	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
-		xen_pfn_t pfn = PFN_DOWN(pgmap->res.start);
+		xen_pfn_t pfn = PFN_DOWN(res->start);
 
 		for (i = 0; i < alloc_pages; i++) {
 			if (!set_phys_to_machine(pfn + i, INVALID_P2M_ENTRY)) {
 				pr_warn("set_phys_to_machine() failed, no memory added\n");
-				release_resource(&pgmap->res);
-				kfree(pgmap);
-				return -ENOMEM;
+				ret = -ENOMEM;
+				goto err_memremap;
 			}
                 }
 	}
@@ -66,9 +75,8 @@ static int fill_list(unsigned int nr_pages)
 	vaddr = memremap_pages(pgmap, NUMA_NO_NODE);
 	if (IS_ERR(vaddr)) {
 		pr_err("Cannot remap memory range\n");
-		release_resource(&pgmap->res);
-		kfree(pgmap);
-		return PTR_ERR(vaddr);
+		ret = PTR_ERR(vaddr);
+		goto err_memremap;
 	}
 
 	for (i = 0; i < alloc_pages; i++) {
@@ -80,6 +88,14 @@ static int fill_list(unsigned int nr_pages)
 	}
 
 	return 0;
+
+err_memremap:
+	release_resource(res);
+err_resource:
+	kfree(pgmap);
+err_pgmap:
+	kfree(res);
+	return ret;
 }
 
 /**
diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index e5862746751b..d0dd261d87c0 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LINUX_MEMREMAP_H_
 #define _LINUX_MEMREMAP_H_
+#include <linux/range.h>
 #include <linux/ioport.h>
 #include <linux/percpu-refcount.h>
 
@@ -93,7 +94,7 @@ struct dev_pagemap_ops {
 /**
  * struct dev_pagemap - metadata for ZONE_DEVICE mappings
  * @altmap: pre-allocated/reserved memory for vmemmap allocations
- * @res: physical address range covered by @ref
+ * @range: physical address range covered by @ref
  * @ref: reference count that pins the devm_memremap_pages() mapping
  * @internal_ref: internal reference if @ref is not provided by the caller
  * @done: completion for @internal_ref
@@ -106,7 +107,7 @@ struct dev_pagemap_ops {
  */
 struct dev_pagemap {
 	struct vmem_altmap altmap;
-	struct resource res;
+	struct range range;
 	struct percpu_ref *ref;
 	struct percpu_ref internal_ref;
 	struct completion done;
diff --git a/include/linux/range.h b/include/linux/range.h
index d1fbeb664012..274681cc3154 100644
--- a/include/linux/range.h
+++ b/include/linux/range.h
@@ -1,12 +1,18 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LINUX_RANGE_H
 #define _LINUX_RANGE_H
+#include <linux/types.h>
 
 struct range {
 	u64   start;
 	u64   end;
 };
 
+static inline u64 range_len(const struct range *range)
+{
+	return range->end - range->start + 1;
+}
+
 int add_range(struct range *range, int az, int nr_range,
 		u64 start, u64 end);
 
diff --git a/lib/test_hmm.c b/lib/test_hmm.c
index e7dc3de355b7..e97ca8ec0bce 100644
--- a/lib/test_hmm.c
+++ b/lib/test_hmm.c
@@ -460,6 +460,21 @@ static bool dmirror_allocate_chunk(struct dmirror_device *mdevice,
 	unsigned long pfn_last;
 	void *ptr;
 
+	devmem = kzalloc(sizeof(*devmem), GFP_KERNEL);
+	if (!devmem)
+		return -ENOMEM;
+
+	res = request_free_mem_region(&iomem_resource, DEVMEM_CHUNK_SIZE,
+				      "hmm_dmirror");
+	if (IS_ERR(res))
+		goto err_devmem;
+
+	devmem->pagemap.type = MEMORY_DEVICE_PRIVATE;
+	devmem->pagemap.range.start = res->start;
+	devmem->pagemap.range.end = res->end;
+	devmem->pagemap.ops = &dmirror_devmem_ops;
+	devmem->pagemap.owner = mdevice;
+
 	mutex_lock(&mdevice->devmem_lock);
 
 	if (mdevice->devmem_count == mdevice->devmem_capacity) {
@@ -472,33 +487,18 @@ static bool dmirror_allocate_chunk(struct dmirror_device *mdevice,
 				sizeof(new_chunks[0]) * new_capacity,
 				GFP_KERNEL);
 		if (!new_chunks)
-			goto err;
+			goto err_release;
 		mdevice->devmem_capacity = new_capacity;
 		mdevice->devmem_chunks = new_chunks;
 	}
 
-	res = request_free_mem_region(&iomem_resource, DEVMEM_CHUNK_SIZE,
-					"hmm_dmirror");
-	if (IS_ERR(res))
-		goto err;
-
-	devmem = kzalloc(sizeof(*devmem), GFP_KERNEL);
-	if (!devmem)
-		goto err_release;
-
-	devmem->pagemap.type = MEMORY_DEVICE_PRIVATE;
-	devmem->pagemap.res = *res;
-	devmem->pagemap.ops = &dmirror_devmem_ops;
-	devmem->pagemap.owner = mdevice;
-
 	ptr = memremap_pages(&devmem->pagemap, numa_node_id());
 	if (IS_ERR(ptr))
-		goto err_free;
+		goto err_release;
 
 	devmem->mdevice = mdevice;
-	pfn_first = devmem->pagemap.res.start >> PAGE_SHIFT;
-	pfn_last = pfn_first +
-		(resource_size(&devmem->pagemap.res) >> PAGE_SHIFT);
+	pfn_first = devmem->pagemap.range.start >> PAGE_SHIFT;
+	pfn_last = pfn_first + (range_len(&devmem->pagemap.range) >> PAGE_SHIFT);
 	mdevice->devmem_chunks[mdevice->devmem_count++] = devmem;
 
 	mutex_unlock(&mdevice->devmem_lock);
@@ -525,12 +525,12 @@ static bool dmirror_allocate_chunk(struct dmirror_device *mdevice,
 
 	return true;
 
-err_free:
-	kfree(devmem);
 err_release:
-	release_mem_region(res->start, resource_size(res));
-err:
 	mutex_unlock(&mdevice->devmem_lock);
+	release_mem_region(devmem->pagemap.range.start, range_len(&devmem->pagemap.range));
+err_devmem:
+	kfree(devmem);
+
 	return false;
 }
 
@@ -1100,8 +1100,8 @@ static void dmirror_device_remove(struct dmirror_device *mdevice)
 				mdevice->devmem_chunks[i];
 
 			memunmap_pages(&devmem->pagemap);
-			release_mem_region(devmem->pagemap.res.start,
-					   resource_size(&devmem->pagemap.res));
+			release_mem_region(devmem->pagemap.range.start,
+					   range_len(&devmem->pagemap.range));
 			kfree(devmem);
 		}
 		kfree(mdevice->devmem_chunks);
diff --git a/mm/memremap.c b/mm/memremap.c
index 006dace60b1a..d958d348b3ca 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -70,24 +70,24 @@ static void devmap_managed_enable_put(void)
 }
 #endif /* CONFIG_DEV_PAGEMAP_OPS */
 
-static void pgmap_array_delete(struct resource *res)
+static void pgmap_array_delete(struct range *range)
 {
-	xa_store_range(&pgmap_array, PHYS_PFN(res->start), PHYS_PFN(res->end),
+	xa_store_range(&pgmap_array, PHYS_PFN(range->start), PHYS_PFN(range->end),
 			NULL, GFP_KERNEL);
 	synchronize_rcu();
 }
 
 static unsigned long pfn_first(struct dev_pagemap *pgmap)
 {
-	return PHYS_PFN(pgmap->res.start) +
+	return PHYS_PFN(pgmap->range.start) +
 		vmem_altmap_offset(pgmap_altmap(pgmap));
 }
 
 static unsigned long pfn_end(struct dev_pagemap *pgmap)
 {
-	const struct resource *res = &pgmap->res;
+	const struct range *range = &pgmap->range;
 
-	return (res->start + resource_size(res)) >> PAGE_SHIFT;
+	return (range->start + range_len(range)) >> PAGE_SHIFT;
 }
 
 static unsigned long pfn_next(unsigned long pfn)
@@ -126,7 +126,7 @@ static void dev_pagemap_cleanup(struct dev_pagemap *pgmap)
 
 void memunmap_pages(struct dev_pagemap *pgmap)
 {
-	struct resource *res = &pgmap->res;
+	struct range *range = &pgmap->range;
 	struct page *first_page;
 	unsigned long pfn;
 	int nid;
@@ -143,20 +143,20 @@ void memunmap_pages(struct dev_pagemap *pgmap)
 	nid = page_to_nid(first_page);
 
 	mem_hotplug_begin();
-	remove_pfn_range_from_zone(page_zone(first_page), PHYS_PFN(res->start),
-				   PHYS_PFN(resource_size(res)));
+	remove_pfn_range_from_zone(page_zone(first_page), PHYS_PFN(range->start),
+				   PHYS_PFN(range_len(range)));
 	if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
-		__remove_pages(PHYS_PFN(res->start),
-			       PHYS_PFN(resource_size(res)), NULL);
+		__remove_pages(PHYS_PFN(range->start),
+			       PHYS_PFN(range_len(range)), NULL);
 	} else {
-		arch_remove_memory(nid, res->start, resource_size(res),
+		arch_remove_memory(nid, range->start, range_len(range),
 				pgmap_altmap(pgmap));
-		kasan_remove_zero_shadow(__va(res->start), resource_size(res));
+		kasan_remove_zero_shadow(__va(range->start), range_len(range));
 	}
 	mem_hotplug_done();
 
-	untrack_pfn(NULL, PHYS_PFN(res->start), resource_size(res));
-	pgmap_array_delete(res);
+	untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range));
+	pgmap_array_delete(range);
 	WARN_ONCE(pgmap->altmap.alloc, "failed to free all reserved pages\n");
 	devmap_managed_enable_put();
 }
@@ -182,7 +182,7 @@ static void dev_pagemap_percpu_release(struct percpu_ref *ref)
  */
 void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 {
-	struct resource *res = &pgmap->res;
+	struct range *range = &pgmap->range;
 	struct dev_pagemap *conflict_pgmap;
 	struct mhp_params params = {
 		/*
@@ -251,7 +251,7 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 			return ERR_PTR(error);
 	}
 
-	conflict_pgmap = get_dev_pagemap(PHYS_PFN(res->start), NULL);
+	conflict_pgmap = get_dev_pagemap(PHYS_PFN(range->start), NULL);
 	if (conflict_pgmap) {
 		WARN(1, "Conflicting mapping in same section\n");
 		put_dev_pagemap(conflict_pgmap);
@@ -259,7 +259,7 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 		goto err_array;
 	}
 
-	conflict_pgmap = get_dev_pagemap(PHYS_PFN(res->end), NULL);
+	conflict_pgmap = get_dev_pagemap(PHYS_PFN(range->end), NULL);
 	if (conflict_pgmap) {
 		WARN(1, "Conflicting mapping in same section\n");
 		put_dev_pagemap(conflict_pgmap);
@@ -267,26 +267,27 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 		goto err_array;
 	}
 
-	is_ram = region_intersects(res->start, resource_size(res),
+	is_ram = region_intersects(range->start, range_len(range),
 		IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);
 
 	if (is_ram != REGION_DISJOINT) {
-		WARN_ONCE(1, "%s attempted on %s region %pr\n", __func__,
-				is_ram == REGION_MIXED ? "mixed" : "ram", res);
+		WARN_ONCE(1, "attempted on %s region %#llx-%#llx\n",
+				is_ram == REGION_MIXED ? "mixed" : "ram",
+				range->start, range->end);
 		error = -ENXIO;
 		goto err_array;
 	}
 
-	error = xa_err(xa_store_range(&pgmap_array, PHYS_PFN(res->start),
-				PHYS_PFN(res->end), pgmap, GFP_KERNEL));
+	error = xa_err(xa_store_range(&pgmap_array, PHYS_PFN(range->start),
+				PHYS_PFN(range->end), pgmap, GFP_KERNEL));
 	if (error)
 		goto err_array;
 
 	if (nid < 0)
 		nid = numa_mem_id();
 
-	error = track_pfn_remap(NULL, &params.pgprot, PHYS_PFN(res->start),
-				0, resource_size(res));
+	error = track_pfn_remap(NULL, &params.pgprot, PHYS_PFN(range->start), 0,
+			range_len(range));
 	if (error)
 		goto err_pfn_remap;
 
@@ -304,16 +305,16 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 	 * arch_add_memory().
 	 */
 	if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
-		error = add_pages(nid, PHYS_PFN(res->start),
-				PHYS_PFN(resource_size(res)), &params);
+		error = add_pages(nid, PHYS_PFN(range->start),
+				PHYS_PFN(range_len(range)), &params);
 	} else {
-		error = kasan_add_zero_shadow(__va(res->start), resource_size(res));
+		error = kasan_add_zero_shadow(__va(range->start), range_len(range));
 		if (error) {
 			mem_hotplug_done();
 			goto err_kasan;
 		}
 
-		error = arch_add_memory(nid, res->start, resource_size(res),
+		error = arch_add_memory(nid, range->start, range_len(range),
 					&params);
 	}
 
@@ -321,8 +322,8 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 		struct zone *zone;
 
 		zone = &NODE_DATA(nid)->node_zones[ZONE_DEVICE];
-		move_pfn_range_to_zone(zone, PHYS_PFN(res->start),
-				PHYS_PFN(resource_size(res)), params.altmap);
+		move_pfn_range_to_zone(zone, PHYS_PFN(range->start),
+				PHYS_PFN(range_len(range)), params.altmap);
 	}
 
 	mem_hotplug_done();
@@ -334,17 +335,17 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 	 * to allow us to do the work while not holding the hotplug lock.
 	 */
 	memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
-				PHYS_PFN(res->start),
-				PHYS_PFN(resource_size(res)), pgmap);
+				PHYS_PFN(range->start),
+				PHYS_PFN(range_len(range)), pgmap);
 	percpu_ref_get_many(pgmap->ref, pfn_end(pgmap) - pfn_first(pgmap));
-	return __va(res->start);
+	return __va(range->start);
 
  err_add_memory:
-	kasan_remove_zero_shadow(__va(res->start), resource_size(res));
+	kasan_remove_zero_shadow(__va(range->start), range_len(range));
  err_kasan:
-	untrack_pfn(NULL, PHYS_PFN(res->start), resource_size(res));
+	untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range));
  err_pfn_remap:
-	pgmap_array_delete(res);
+	pgmap_array_delete(range);
  err_array:
 	dev_pagemap_kill(pgmap);
 	dev_pagemap_cleanup(pgmap);
@@ -369,7 +370,7 @@ EXPORT_SYMBOL_GPL(memremap_pages);
  *    'live' on entry and will be killed and reaped at
  *    devm_memremap_pages_release() time, or if this routine fails.
  *
- * 4/ res is expected to be a host memory range that could feasibly be
+ * 4/ range is expected to be a host memory range that could feasibly be
  *    treated as a "System RAM" range, i.e. not a device mmio range, but
  *    this is not enforced.
  */
@@ -426,7 +427,7 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
 	 * In the cached case we're already holding a live reference.
 	 */
 	if (pgmap) {
-		if (phys >= pgmap->res.start && phys <= pgmap->res.end)
+		if (phys >= pgmap->range.start && phys <= pgmap->range.end)
 			return pgmap;
 		put_dev_pagemap(pgmap);
 	}
diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c
index 03e40b3b0106..c62d372d426f 100644
--- a/tools/testing/nvdimm/test/iomap.c
+++ b/tools/testing/nvdimm/test/iomap.c
@@ -126,7 +126,7 @@ static void dev_pagemap_percpu_release(struct percpu_ref *ref)
 void *__wrap_devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 {
 	int error;
-	resource_size_t offset = pgmap->res.start;
+	resource_size_t offset = pgmap->range.start;
 	struct nfit_test_resource *nfit_res = get_nfit_res(offset);
 
 	if (!nfit_res)
-- 
cgit v1.2.3


From b7b3c01b191596d27a6980d1a42504f5b607f802 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Tue, 13 Oct 2020 16:50:34 -0700
Subject: mm/memremap_pages: support multiple ranges per invocation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In support of device-dax growing the ability to front physically
dis-contiguous ranges of memory, update devm_memremap_pages() to track
multiple ranges with a single reference counter and devm instance.

Convert all [devm_]memremap_pages() users to specify the number of ranges
they are mapping in their 'struct dev_pagemap' instance.

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Paul Mackerras <paulus@ozlabs.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Ben Skeggs <bskeggs@redhat.com>
Cc: David Airlie <airlied@linux.ie>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: "Jérôme Glisse" <jglisse@redhat.co
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brice Goglin <Brice.Goglin@inria.fr>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Hulk Robot <hulkci@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: Jason Yan <yanaijie@huawei.com>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: "Jérôme Glisse" <jglisse@redhat.com>
Cc: Jia He <justin.he@arm.com>
Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: kernel test robot <lkp@intel.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Will Deacon <will@kernel.org>
Link: https://lkml.kernel.org/r/159643103789.4062302.18426128170217903785.stgit@dwillia2-desk3.amr.corp.intel.com
Link: https://lkml.kernel.org/r/160106116293.30709.13350662794915396198.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/powerpc/kvm/book3s_hv_uvmem.c     |   1 +
 drivers/dax/device.c                   |   1 +
 drivers/gpu/drm/nouveau/nouveau_dmem.c |   1 +
 drivers/nvdimm/pfn_devs.c              |   1 +
 drivers/nvdimm/pmem.c                  |   1 +
 drivers/pci/p2pdma.c                   |   1 +
 drivers/xen/unpopulated-alloc.c        |   1 +
 include/linux/memremap.h               |  10 +-
 lib/test_hmm.c                         |   1 +
 mm/memremap.c                          | 258 +++++++++++++++++++--------------
 10 files changed, 166 insertions(+), 110 deletions(-)

(limited to 'include/linux')

diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c
index 29ec555055c2..84e5a2dc8be5 100644
--- a/arch/powerpc/kvm/book3s_hv_uvmem.c
+++ b/arch/powerpc/kvm/book3s_hv_uvmem.c
@@ -1172,6 +1172,7 @@ int kvmppc_uvmem_init(void)
 	kvmppc_uvmem_pgmap.type = MEMORY_DEVICE_PRIVATE;
 	kvmppc_uvmem_pgmap.range.start = res->start;
 	kvmppc_uvmem_pgmap.range.end = res->end;
+	kvmppc_uvmem_pgmap.nr_range = 1;
 	kvmppc_uvmem_pgmap.ops = &kvmppc_uvmem_ops;
 	/* just one global instance: */
 	kvmppc_uvmem_pgmap.owner = &kvmppc_uvmem_pgmap;
diff --git a/drivers/dax/device.c b/drivers/dax/device.c
index a14448bca83d..5f808617672a 100644
--- a/drivers/dax/device.c
+++ b/drivers/dax/device.c
@@ -417,6 +417,7 @@ int dev_dax_probe(struct dev_dax *dev_dax)
 		if (!pgmap)
 			return -ENOMEM;
 		pgmap->range = *range;
+		pgmap->nr_range = 1;
 	}
 	pgmap->type = MEMORY_DEVICE_GENERIC;
 	addr = devm_memremap_pages(dev, pgmap);
diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c
index 25811ed7e274..a13c6215bba8 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dmem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c
@@ -251,6 +251,7 @@ nouveau_dmem_chunk_alloc(struct nouveau_drm *drm, struct page **ppage)
 	chunk->pagemap.type = MEMORY_DEVICE_PRIVATE;
 	chunk->pagemap.range.start = res->start;
 	chunk->pagemap.range.end = res->end;
+	chunk->pagemap.nr_range = 1;
 	chunk->pagemap.ops = &nouveau_dmem_pagemap_ops;
 	chunk->pagemap.owner = drm->dev;
 
diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
index 3c4787b92a6a..b499df630d4d 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/drivers/nvdimm/pfn_devs.c
@@ -693,6 +693,7 @@ static int __nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap)
 		.start = nsio->res.start + start_pad,
 		.end = nsio->res.end - end_trunc,
 	};
+	pgmap->nr_range = 1;
 	if (nd_pfn->mode == PFN_MODE_RAM) {
 		if (offset < reserve)
 			return -EINVAL;
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 1f394f44838f..875076b0ea6c 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -441,6 +441,7 @@ static int pmem_attach_disk(struct device *dev,
 	} else if (pmem_should_map_pages(dev)) {
 		pmem->pgmap.range.start = res->start;
 		pmem->pgmap.range.end = res->end;
+		pmem->pgmap.nr_range = 1;
 		pmem->pgmap.type = MEMORY_DEVICE_FS_DAX;
 		pmem->pgmap.ops = &fsdax_pagemap_ops;
 		addr = devm_memremap_pages(dev, &pmem->pgmap);
diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c
index 256850513813..9d53c16b7329 100644
--- a/drivers/pci/p2pdma.c
+++ b/drivers/pci/p2pdma.c
@@ -187,6 +187,7 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size,
 	pgmap = &p2p_pgmap->pgmap;
 	pgmap->range.start = pci_resource_start(pdev, bar) + offset;
 	pgmap->range.end = pgmap->range.start + size - 1;
+	pgmap->nr_range = 1;
 	pgmap->type = MEMORY_DEVICE_PCI_P2PDMA;
 
 	p2p_pgmap->provider = pdev;
diff --git a/drivers/xen/unpopulated-alloc.c b/drivers/xen/unpopulated-alloc.c
index 091b8669eca3..8c512ea550bb 100644
--- a/drivers/xen/unpopulated-alloc.c
+++ b/drivers/xen/unpopulated-alloc.c
@@ -47,6 +47,7 @@ static int fill_list(unsigned int nr_pages)
 		.start = res->start,
 		.end = res->end,
 	};
+	pgmap->nr_range = 1;
 	pgmap->owner = res;
 
 #ifdef CONFIG_XEN_HAVE_PVMMU
diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index d0dd261d87c0..79c49e7f5c30 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -94,7 +94,6 @@ struct dev_pagemap_ops {
 /**
  * struct dev_pagemap - metadata for ZONE_DEVICE mappings
  * @altmap: pre-allocated/reserved memory for vmemmap allocations
- * @range: physical address range covered by @ref
  * @ref: reference count that pins the devm_memremap_pages() mapping
  * @internal_ref: internal reference if @ref is not provided by the caller
  * @done: completion for @internal_ref
@@ -104,10 +103,12 @@ struct dev_pagemap_ops {
  * @owner: an opaque pointer identifying the entity that manages this
  *	instance.  Used by various helpers to make sure that no
  *	foreign ZONE_DEVICE memory is accessed.
+ * @nr_range: number of ranges to be mapped
+ * @range: range to be mapped when nr_range == 1
+ * @ranges: array of ranges to be mapped when nr_range > 1
  */
 struct dev_pagemap {
 	struct vmem_altmap altmap;
-	struct range range;
 	struct percpu_ref *ref;
 	struct percpu_ref internal_ref;
 	struct completion done;
@@ -115,6 +116,11 @@ struct dev_pagemap {
 	unsigned int flags;
 	const struct dev_pagemap_ops *ops;
 	void *owner;
+	int nr_range;
+	union {
+		struct range range;
+		struct range ranges[0];
+	};
 };
 
 static inline struct vmem_altmap *pgmap_altmap(struct dev_pagemap *pgmap)
diff --git a/lib/test_hmm.c b/lib/test_hmm.c
index e97ca8ec0bce..c710b4c5714d 100644
--- a/lib/test_hmm.c
+++ b/lib/test_hmm.c
@@ -472,6 +472,7 @@ static bool dmirror_allocate_chunk(struct dmirror_device *mdevice,
 	devmem->pagemap.type = MEMORY_DEVICE_PRIVATE;
 	devmem->pagemap.range.start = res->start;
 	devmem->pagemap.range.end = res->end;
+	devmem->pagemap.nr_range = 1;
 	devmem->pagemap.ops = &dmirror_devmem_ops;
 	devmem->pagemap.owner = mdevice;
 
diff --git a/mm/memremap.c b/mm/memremap.c
index d958d348b3ca..532ec3d36ab4 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -77,15 +77,19 @@ static void pgmap_array_delete(struct range *range)
 	synchronize_rcu();
 }
 
-static unsigned long pfn_first(struct dev_pagemap *pgmap)
+static unsigned long pfn_first(struct dev_pagemap *pgmap, int range_id)
 {
-	return PHYS_PFN(pgmap->range.start) +
-		vmem_altmap_offset(pgmap_altmap(pgmap));
+	struct range *range = &pgmap->ranges[range_id];
+	unsigned long pfn = PHYS_PFN(range->start);
+
+	if (range_id)
+		return pfn;
+	return pfn + vmem_altmap_offset(pgmap_altmap(pgmap));
 }
 
-static unsigned long pfn_end(struct dev_pagemap *pgmap)
+static unsigned long pfn_end(struct dev_pagemap *pgmap, int range_id)
 {
-	const struct range *range = &pgmap->range;
+	const struct range *range = &pgmap->ranges[range_id];
 
 	return (range->start + range_len(range)) >> PAGE_SHIFT;
 }
@@ -97,8 +101,8 @@ static unsigned long pfn_next(unsigned long pfn)
 	return pfn + 1;
 }
 
-#define for_each_device_pfn(pfn, map) \
-	for (pfn = pfn_first(map); pfn < pfn_end(map); pfn = pfn_next(pfn))
+#define for_each_device_pfn(pfn, map, i) \
+	for (pfn = pfn_first(map, i); pfn < pfn_end(map, i); pfn = pfn_next(pfn))
 
 static void dev_pagemap_kill(struct dev_pagemap *pgmap)
 {
@@ -124,20 +128,14 @@ static void dev_pagemap_cleanup(struct dev_pagemap *pgmap)
 		pgmap->ref = NULL;
 }
 
-void memunmap_pages(struct dev_pagemap *pgmap)
+static void pageunmap_range(struct dev_pagemap *pgmap, int range_id)
 {
-	struct range *range = &pgmap->range;
+	struct range *range = &pgmap->ranges[range_id];
 	struct page *first_page;
-	unsigned long pfn;
 	int nid;
 
-	dev_pagemap_kill(pgmap);
-	for_each_device_pfn(pfn, pgmap)
-		put_page(pfn_to_page(pfn));
-	dev_pagemap_cleanup(pgmap);
-
 	/* make sure to access a memmap that was actually initialized */
-	first_page = pfn_to_page(pfn_first(pgmap));
+	first_page = pfn_to_page(pfn_first(pgmap, range_id));
 
 	/* pages are dead and unused, undo the arch mapping */
 	nid = page_to_nid(first_page);
@@ -157,6 +155,22 @@ void memunmap_pages(struct dev_pagemap *pgmap)
 
 	untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range));
 	pgmap_array_delete(range);
+}
+
+void memunmap_pages(struct dev_pagemap *pgmap)
+{
+	unsigned long pfn;
+	int i;
+
+	dev_pagemap_kill(pgmap);
+	for (i = 0; i < pgmap->nr_range; i++)
+		for_each_device_pfn(pfn, pgmap, i)
+			put_page(pfn_to_page(pfn));
+	dev_pagemap_cleanup(pgmap);
+
+	for (i = 0; i < pgmap->nr_range; i++)
+		pageunmap_range(pgmap, i);
+
 	WARN_ONCE(pgmap->altmap.alloc, "failed to free all reserved pages\n");
 	devmap_managed_enable_put();
 }
@@ -175,96 +189,29 @@ static void dev_pagemap_percpu_release(struct percpu_ref *ref)
 	complete(&pgmap->done);
 }
 
-/*
- * Not device managed version of dev_memremap_pages, undone by
- * memunmap_pages().  Please use dev_memremap_pages if you have a struct
- * device available.
- */
-void *memremap_pages(struct dev_pagemap *pgmap, int nid)
+static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params,
+		int range_id, int nid)
 {
-	struct range *range = &pgmap->range;
+	struct range *range = &pgmap->ranges[range_id];
 	struct dev_pagemap *conflict_pgmap;
-	struct mhp_params params = {
-		/*
-		 * We do not want any optional features only our own memmap
-		 */
-		.altmap = pgmap_altmap(pgmap),
-		.pgprot = PAGE_KERNEL,
-	};
 	int error, is_ram;
-	bool need_devmap_managed = true;
 
-	switch (pgmap->type) {
-	case MEMORY_DEVICE_PRIVATE:
-		if (!IS_ENABLED(CONFIG_DEVICE_PRIVATE)) {
-			WARN(1, "Device private memory not supported\n");
-			return ERR_PTR(-EINVAL);
-		}
-		if (!pgmap->ops || !pgmap->ops->migrate_to_ram) {
-			WARN(1, "Missing migrate_to_ram method\n");
-			return ERR_PTR(-EINVAL);
-		}
-		if (!pgmap->owner) {
-			WARN(1, "Missing owner\n");
-			return ERR_PTR(-EINVAL);
-		}
-		break;
-	case MEMORY_DEVICE_FS_DAX:
-		if (!IS_ENABLED(CONFIG_ZONE_DEVICE) ||
-		    IS_ENABLED(CONFIG_FS_DAX_LIMITED)) {
-			WARN(1, "File system DAX not supported\n");
-			return ERR_PTR(-EINVAL);
-		}
-		break;
-	case MEMORY_DEVICE_GENERIC:
-		need_devmap_managed = false;
-		break;
-	case MEMORY_DEVICE_PCI_P2PDMA:
-		params.pgprot = pgprot_noncached(params.pgprot);
-		need_devmap_managed = false;
-		break;
-	default:
-		WARN(1, "Invalid pgmap type %d\n", pgmap->type);
-		break;
-	}
-
-	if (!pgmap->ref) {
-		if (pgmap->ops && (pgmap->ops->kill || pgmap->ops->cleanup))
-			return ERR_PTR(-EINVAL);
-
-		init_completion(&pgmap->done);
-		error = percpu_ref_init(&pgmap->internal_ref,
-				dev_pagemap_percpu_release, 0, GFP_KERNEL);
-		if (error)
-			return ERR_PTR(error);
-		pgmap->ref = &pgmap->internal_ref;
-	} else {
-		if (!pgmap->ops || !pgmap->ops->kill || !pgmap->ops->cleanup) {
-			WARN(1, "Missing reference count teardown definition\n");
-			return ERR_PTR(-EINVAL);
-		}
-	}
-
-	if (need_devmap_managed) {
-		error = devmap_managed_enable_get(pgmap);
-		if (error)
-			return ERR_PTR(error);
-	}
+	if (WARN_ONCE(pgmap_altmap(pgmap) && range_id > 0,
+				"altmap not supported for multiple ranges\n"))
+		return -EINVAL;
 
 	conflict_pgmap = get_dev_pagemap(PHYS_PFN(range->start), NULL);
 	if (conflict_pgmap) {
 		WARN(1, "Conflicting mapping in same section\n");
 		put_dev_pagemap(conflict_pgmap);
-		error = -ENOMEM;
-		goto err_array;
+		return -ENOMEM;
 	}
 
 	conflict_pgmap = get_dev_pagemap(PHYS_PFN(range->end), NULL);
 	if (conflict_pgmap) {
 		WARN(1, "Conflicting mapping in same section\n");
 		put_dev_pagemap(conflict_pgmap);
-		error = -ENOMEM;
-		goto err_array;
+		return -ENOMEM;
 	}
 
 	is_ram = region_intersects(range->start, range_len(range),
@@ -274,19 +221,18 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 		WARN_ONCE(1, "attempted on %s region %#llx-%#llx\n",
 				is_ram == REGION_MIXED ? "mixed" : "ram",
 				range->start, range->end);
-		error = -ENXIO;
-		goto err_array;
+		return -ENXIO;
 	}
 
 	error = xa_err(xa_store_range(&pgmap_array, PHYS_PFN(range->start),
 				PHYS_PFN(range->end), pgmap, GFP_KERNEL));
 	if (error)
-		goto err_array;
+		return error;
 
 	if (nid < 0)
 		nid = numa_mem_id();
 
-	error = track_pfn_remap(NULL, &params.pgprot, PHYS_PFN(range->start), 0,
+	error = track_pfn_remap(NULL, &params->pgprot, PHYS_PFN(range->start), 0,
 			range_len(range));
 	if (error)
 		goto err_pfn_remap;
@@ -306,7 +252,7 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 	 */
 	if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
 		error = add_pages(nid, PHYS_PFN(range->start),
-				PHYS_PFN(range_len(range)), &params);
+				PHYS_PFN(range_len(range)), params);
 	} else {
 		error = kasan_add_zero_shadow(__va(range->start), range_len(range));
 		if (error) {
@@ -315,7 +261,7 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 		}
 
 		error = arch_add_memory(nid, range->start, range_len(range),
-					&params);
+					params);
 	}
 
 	if (!error) {
@@ -323,7 +269,7 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 
 		zone = &NODE_DATA(nid)->node_zones[ZONE_DEVICE];
 		move_pfn_range_to_zone(zone, PHYS_PFN(range->start),
-				PHYS_PFN(range_len(range)), params.altmap);
+				PHYS_PFN(range_len(range)), params->altmap);
 	}
 
 	mem_hotplug_done();
@@ -337,20 +283,116 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 	memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
 				PHYS_PFN(range->start),
 				PHYS_PFN(range_len(range)), pgmap);
-	percpu_ref_get_many(pgmap->ref, pfn_end(pgmap) - pfn_first(pgmap));
-	return __va(range->start);
+	percpu_ref_get_many(pgmap->ref, pfn_end(pgmap, range_id)
+			- pfn_first(pgmap, range_id));
+	return 0;
 
- err_add_memory:
+err_add_memory:
 	kasan_remove_zero_shadow(__va(range->start), range_len(range));
- err_kasan:
+err_kasan:
 	untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range));
- err_pfn_remap:
+err_pfn_remap:
 	pgmap_array_delete(range);
- err_array:
-	dev_pagemap_kill(pgmap);
-	dev_pagemap_cleanup(pgmap);
-	devmap_managed_enable_put();
-	return ERR_PTR(error);
+	return error;
+}
+
+
+/*
+ * Not device managed version of dev_memremap_pages, undone by
+ * memunmap_pages().  Please use dev_memremap_pages if you have a struct
+ * device available.
+ */
+void *memremap_pages(struct dev_pagemap *pgmap, int nid)
+{
+	struct mhp_params params = {
+		.altmap = pgmap_altmap(pgmap),
+		.pgprot = PAGE_KERNEL,
+	};
+	const int nr_range = pgmap->nr_range;
+	bool need_devmap_managed = true;
+	int error, i;
+
+	if (WARN_ONCE(!nr_range, "nr_range must be specified\n"))
+		return ERR_PTR(-EINVAL);
+
+	switch (pgmap->type) {
+	case MEMORY_DEVICE_PRIVATE:
+		if (!IS_ENABLED(CONFIG_DEVICE_PRIVATE)) {
+			WARN(1, "Device private memory not supported\n");
+			return ERR_PTR(-EINVAL);
+		}
+		if (!pgmap->ops || !pgmap->ops->migrate_to_ram) {
+			WARN(1, "Missing migrate_to_ram method\n");
+			return ERR_PTR(-EINVAL);
+		}
+		if (!pgmap->owner) {
+			WARN(1, "Missing owner\n");
+			return ERR_PTR(-EINVAL);
+		}
+		break;
+	case MEMORY_DEVICE_FS_DAX:
+		if (!IS_ENABLED(CONFIG_ZONE_DEVICE) ||
+		    IS_ENABLED(CONFIG_FS_DAX_LIMITED)) {
+			WARN(1, "File system DAX not supported\n");
+			return ERR_PTR(-EINVAL);
+		}
+		break;
+	case MEMORY_DEVICE_GENERIC:
+		need_devmap_managed = false;
+		break;
+	case MEMORY_DEVICE_PCI_P2PDMA:
+		params.pgprot = pgprot_noncached(params.pgprot);
+		need_devmap_managed = false;
+		break;
+	default:
+		WARN(1, "Invalid pgmap type %d\n", pgmap->type);
+		break;
+	}
+
+	if (!pgmap->ref) {
+		if (pgmap->ops && (pgmap->ops->kill || pgmap->ops->cleanup))
+			return ERR_PTR(-EINVAL);
+
+		init_completion(&pgmap->done);
+		error = percpu_ref_init(&pgmap->internal_ref,
+				dev_pagemap_percpu_release, 0, GFP_KERNEL);
+		if (error)
+			return ERR_PTR(error);
+		pgmap->ref = &pgmap->internal_ref;
+	} else {
+		if (!pgmap->ops || !pgmap->ops->kill || !pgmap->ops->cleanup) {
+			WARN(1, "Missing reference count teardown definition\n");
+			return ERR_PTR(-EINVAL);
+		}
+	}
+
+	if (need_devmap_managed) {
+		error = devmap_managed_enable_get(pgmap);
+		if (error)
+			return ERR_PTR(error);
+	}
+
+	/*
+	 * Clear the pgmap nr_range as it will be incremented for each
+	 * successfully processed range. This communicates how many
+	 * regions to unwind in the abort case.
+	 */
+	pgmap->nr_range = 0;
+	error = 0;
+	for (i = 0; i < nr_range; i++) {
+		error = pagemap_range(pgmap, &params, i, nid);
+		if (error)
+			break;
+		pgmap->nr_range++;
+	}
+
+	if (i < nr_range) {
+		memunmap_pages(pgmap);
+		pgmap->nr_range = nr_range;
+		return ERR_PTR(error);
+	}
+
+	return __va(pgmap->ranges[0].start);
 }
 EXPORT_SYMBOL_GPL(memremap_pages);
 
-- 
cgit v1.2.3


From bac3cf4d01d43b587c873360dc8c84e3b570b344 Mon Sep 17 00:00:00 2001
From: John Hubbard <jhubbard@nvidia.com>
Date: Tue, 13 Oct 2020 16:51:14 -0700
Subject: mm, dump_page: rename head_mapcount() --> head_compound_mapcount()

Rename head_pincount() --> head_compound_pincount().  These names are more
accurate (or less misleading) than the original ones.

Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Qian Cai <cai@lca.pw>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: William Kucharski <william.kucharski@oracle.com>
Link: https://lkml.kernel.org/r/20200807183358.105097-1-jhubbard@nvidia.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h | 8 ++++----
 mm/debug.c         | 6 +++---
 2 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 13dc9b9ccf8e..9cc0894e7d61 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -791,7 +791,7 @@ static inline void *kvcalloc(size_t n, size_t size, gfp_t flags)
 extern void kvfree(const void *addr);
 extern void kvfree_sensitive(const void *addr, size_t len);
 
-static inline int head_mapcount(struct page *head)
+static inline int head_compound_mapcount(struct page *head)
 {
 	return atomic_read(compound_mapcount_ptr(head)) + 1;
 }
@@ -805,7 +805,7 @@ static inline int compound_mapcount(struct page *page)
 {
 	VM_BUG_ON_PAGE(!PageCompound(page), page);
 	page = compound_head(page);
-	return head_mapcount(page);
+	return head_compound_mapcount(page);
 }
 
 /*
@@ -918,7 +918,7 @@ static inline bool hpage_pincount_available(struct page *page)
 	return PageCompound(page) && compound_order(page) > 1;
 }
 
-static inline int head_pincount(struct page *head)
+static inline int head_compound_pincount(struct page *head)
 {
 	return atomic_read(compound_pincount_ptr(head));
 }
@@ -927,7 +927,7 @@ static inline int compound_pincount(struct page *page)
 {
 	VM_BUG_ON_PAGE(!hpage_pincount_available(page), page);
 	page = compound_head(page);
-	return head_pincount(page);
+	return head_compound_pincount(page);
 }
 
 static inline void set_compound_order(struct page *page, unsigned int order)
diff --git a/mm/debug.c b/mm/debug.c
index 2a767865145c..ccca576b2899 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -102,12 +102,12 @@ void __dump_page(struct page *page, const char *reason)
 		if (hpage_pincount_available(page)) {
 			pr_warn("head:%p order:%u compound_mapcount:%d compound_pincount:%d\n",
 					head, compound_order(head),
-					head_mapcount(head),
-					head_pincount(head));
+					head_compound_mapcount(head),
+					head_compound_pincount(head));
 		} else {
 			pr_warn("head:%p order:%u compound_mapcount:%d\n",
 					head, compound_order(head),
-					head_mapcount(head));
+					head_compound_mapcount(head));
 		}
 	}
 	if (PageKsm(page))
-- 
cgit v1.2.3


From 61ef1865570452801f6e554a668e049c2e25c1fd Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 13 Oct 2020 16:51:17 -0700
Subject: mm: factor find_get_incore_page out of mincore_page

Patch series "Return head pages from find_*_entry", v2.

This patch series started out as part of the THP patch set, but it has
some nice effects along the way and it seems worth splitting it out and
submitting separately.

Currently find_get_entry() and find_lock_entry() return the page
corresponding to the requested index, but the first thing most callers do
is find the head page, which we just threw away.  As part of auditing all
the callers, I found some misuses of the APIs and some plain
inefficiencies that I've fixed.

The diffstat is unflattering, but I added more kernel-doc and a new wrapper.

This patch (of 8);

Provide this functionality from the swap cache.  It's useful for
more than just mincore().

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: William Kucharski <william.kucharski@oracle.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Huang Ying <ying.huang@intel.com>
Link: https://lkml.kernel.org/r/20200910183318.20139-1-willy@infradead.org
Link: https://lkml.kernel.org/r/20200910183318.20139-2-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/swap.h |  7 +++++++
 mm/mincore.c         | 28 ++--------------------------
 mm/swap_state.c      | 32 ++++++++++++++++++++++++++++++++
 3 files changed, 41 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 4340a7b6e7a1..23c6e43a956d 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -427,6 +427,7 @@ extern void free_pages_and_swap_cache(struct page **, int);
 extern struct page *lookup_swap_cache(swp_entry_t entry,
 				      struct vm_area_struct *vma,
 				      unsigned long addr);
+struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index);
 extern struct page *read_swap_cache_async(swp_entry_t, gfp_t,
 			struct vm_area_struct *vma, unsigned long addr,
 			bool do_poll);
@@ -570,6 +571,12 @@ static inline struct page *lookup_swap_cache(swp_entry_t swp,
 	return NULL;
 }
 
+static inline
+struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index)
+{
+	return find_get_page(mapping, index);
+}
+
 static inline int add_to_swap(struct page *page)
 {
 	return 0;
diff --git a/mm/mincore.c b/mm/mincore.c
index 453ff112470f..02db1a834021 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -48,7 +48,7 @@ static int mincore_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr,
  * and is up to date; i.e. that no page-in operation would be required
  * at this time if an application were to map and access this page.
  */
-static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff)
+static unsigned char mincore_page(struct address_space *mapping, pgoff_t index)
 {
 	unsigned char present = 0;
 	struct page *page;
@@ -59,31 +59,7 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff)
 	 * any other file mapping (ie. marked !present and faulted in with
 	 * tmpfs's .fault). So swapped out tmpfs mappings are tested here.
 	 */
-#ifdef CONFIG_SWAP
-	if (shmem_mapping(mapping)) {
-		page = find_get_entry(mapping, pgoff);
-		/*
-		 * shmem/tmpfs may return swap: account for swapcache
-		 * page too.
-		 */
-		if (xa_is_value(page)) {
-			swp_entry_t swp = radix_to_swp_entry(page);
-			struct swap_info_struct *si;
-
-			/* Prevent swap device to being swapoff under us */
-			si = get_swap_device(swp);
-			if (si) {
-				page = find_get_page(swap_address_space(swp),
-						     swp_offset(swp));
-				put_swap_device(si);
-			} else
-				page = NULL;
-		}
-	} else
-		page = find_get_page(mapping, pgoff);
-#else
-	page = find_get_page(mapping, pgoff);
-#endif
+	page = find_get_incore_page(mapping, index);
 	if (page) {
 		present = PageUptodate(page);
 		put_page(page);
diff --git a/mm/swap_state.c b/mm/swap_state.c
index c16eebb81d8b..c79e2242dd04 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -21,6 +21,7 @@
 #include <linux/vmalloc.h>
 #include <linux/swap_slots.h>
 #include <linux/huge_mm.h>
+#include <linux/shmem_fs.h>
 #include "internal.h"
 
 /*
@@ -414,6 +415,37 @@ struct page *lookup_swap_cache(swp_entry_t entry, struct vm_area_struct *vma,
 	return page;
 }
 
+/**
+ * find_get_incore_page - Find and get a page from the page or swap caches.
+ * @mapping: The address_space to search.
+ * @index: The page cache index.
+ *
+ * This differs from find_get_page() in that it will also look for the
+ * page in the swap cache.
+ *
+ * Return: The found page or %NULL.
+ */
+struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index)
+{
+	swp_entry_t swp;
+	struct swap_info_struct *si;
+	struct page *page = find_get_entry(mapping, index);
+
+	if (!xa_is_value(page))
+		return page;
+	if (!shmem_mapping(mapping))
+		return NULL;
+
+	swp = radix_to_swp_entry(page);
+	/* Prevent swapoff from happening to us */
+	si = get_swap_device(swp);
+	if (!si)
+		return NULL;
+	page = find_get_page(swap_address_space(swp), swp_offset(swp));
+	put_swap_device(si);
+	return page;
+}
+
 struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 			struct vm_area_struct *vma, unsigned long addr,
 			bool *new_page_allocated)
-- 
cgit v1.2.3


From 9dfc8ff34b951f83632815a87e97a625a11360f0 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 13 Oct 2020 16:51:31 -0700
Subject: i915: use find_lock_page instead of find_lock_entry

i915 does not want to see value entries.  Switch it to use
find_lock_page() instead, and remove the export of find_lock_entry().
Move find_lock_entry() and find_get_entry() to mm/internal.h to discourage
any future use.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: William Kucharski <william.kucharski@oracle.com>
Link: https://lkml.kernel.org/r/20200910183318.20139-6-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 4 ++--
 include/linux/pagemap.h                   | 2 --
 mm/filemap.c                              | 1 -
 mm/internal.h                             | 3 +++
 4 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
index 38113d3c0138..75e8b71c18b9 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
@@ -258,8 +258,8 @@ shmem_writeback(struct drm_i915_gem_object *obj)
 	for (i = 0; i < obj->base.size >> PAGE_SHIFT; i++) {
 		struct page *page;
 
-		page = find_lock_entry(mapping, i);
-		if (!page || xa_is_value(page))
+		page = find_lock_page(mapping, i);
+		if (!page)
 			continue;
 
 		if (!page_mapped(page) && clear_page_dirty_for_io(page)) {
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 434c9c34aeb6..9d282fe6700d 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -385,8 +385,6 @@ static inline struct page *find_subpage(struct page *head, pgoff_t index)
 	return head + (index & (thp_nr_pages(head) - 1));
 }
 
-struct page *find_get_entry(struct address_space *mapping, pgoff_t offset);
-struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset);
 unsigned find_get_entries(struct address_space *mapping, pgoff_t start,
 			  unsigned int nr_entries, struct page **entries,
 			  pgoff_t *indices);
diff --git a/mm/filemap.c b/mm/filemap.c
index 748b7b1b4f6d..089a2f02067f 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1726,7 +1726,6 @@ repeat:
 	}
 	return page;
 }
-EXPORT_SYMBOL(find_lock_entry);
 
 /**
  * pagecache_get_page - Find and get a reference to a page.
diff --git a/mm/internal.h b/mm/internal.h
index 10c677655912..a801a4d51f26 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -65,6 +65,9 @@ static inline void ra_submit(struct file_ra_state *ra,
 			ra->start, ra->size, ra->async_size);
 }
 
+struct page *find_get_entry(struct address_space *mapping, pgoff_t index);
+struct page *find_lock_entry(struct address_space *mapping, pgoff_t index);
+
 /**
  * page_evictable - test whether a page is evictable
  * @page: the page to test
-- 
cgit v1.2.3


From 63ec1973ddf3eb70feb5728088ca190f1af449cb Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 13 Oct 2020 16:51:38 -0700
Subject: mm/shmem: return head page from find_lock_entry

Convert shmem_getpage_gfp() (the only remaining caller of
find_lock_entry()) to cope with a head page being returned instead of
the subpage for the index.

[willy@infradead.org: fix BUG()s]
  Link https://lore.kernel.org/linux-mm/20200912032042.GA6583@casper.infradead.org/

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: William Kucharski <william.kucharski@oracle.com>
Link: https://lkml.kernel.org/r/20200910183318.20139-8-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/pagemap.h |  9 +++++++++
 mm/filemap.c            | 25 +++++++++++--------------
 mm/shmem.c              | 19 ++++++++++---------
 3 files changed, 30 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 9d282fe6700d..5176009e4ffa 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -372,6 +372,15 @@ static inline struct page *grab_cache_page_nowait(struct address_space *mapping,
 			mapping_gfp_mask(mapping));
 }
 
+/* Does this page contain this index? */
+static inline bool thp_contains(struct page *head, pgoff_t index)
+{
+	/* HugeTLBfs indexes the page cache in units of hpage_size */
+	if (PageHuge(head))
+		return head->index == index;
+	return page_index(head) == (index & ~(thp_nr_pages(head) - 1UL));
+}
+
 /*
  * Given the page we found in the page cache, return the page corresponding
  * to this index in the file
diff --git a/mm/filemap.c b/mm/filemap.c
index 9457d4f8b1c1..b44346a748fa 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1692,37 +1692,34 @@ out:
 }
 
 /**
- * find_lock_entry - locate, pin and lock a page cache entry
- * @mapping: the address_space to search
- * @offset: the page cache index
+ * find_lock_entry - Locate and lock a page cache entry.
+ * @mapping: The address_space to search.
+ * @index: The page cache index.
  *
- * Looks up the page cache slot at @mapping & @offset.  If there is a
- * page cache page, it is returned locked and with an increased
- * refcount.
+ * Looks up the page at @mapping & @index.  If there is a page in the
+ * cache, the head page is returned locked and with an increased refcount.
  *
  * If the slot holds a shadow entry of a previously evicted page, or a
  * swap entry from shmem/tmpfs, it is returned.
  *
- * find_lock_entry() may sleep.
- *
- * Return: the found page or shadow entry, %NULL if nothing is found.
+ * Context: May sleep.
+ * Return: The head page or shadow entry, %NULL if nothing is found.
  */
-struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset)
+struct page *find_lock_entry(struct address_space *mapping, pgoff_t index)
 {
 	struct page *page;
 
 repeat:
-	page = find_get_entry(mapping, offset);
+	page = find_get_entry(mapping, index);
 	if (page && !xa_is_value(page)) {
 		lock_page(page);
 		/* Has the page been truncated? */
-		if (unlikely(page_mapping(page) != mapping)) {
+		if (unlikely(page->mapping != mapping)) {
 			unlock_page(page);
 			put_page(page);
 			goto repeat;
 		}
-		page = find_subpage(page, offset);
-		VM_BUG_ON_PAGE(page_to_pgoff(page) != offset, page);
+		VM_BUG_ON_PAGE(!thp_contains(page, index), page);
 	}
 	return page;
 }
diff --git a/mm/shmem.c b/mm/shmem.c
index d42c27e4769f..6d4ddef4a24f 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1830,6 +1830,8 @@ repeat:
 		return error;
 	}
 
+	if (page)
+		hindex = page->index;
 	if (page && sgp == SGP_WRITE)
 		mark_page_accessed(page);
 
@@ -1840,11 +1842,10 @@ repeat:
 		unlock_page(page);
 		put_page(page);
 		page = NULL;
+		hindex = index;
 	}
-	if (page || sgp == SGP_READ) {
-		*pagep = page;
-		return 0;
-	}
+	if (page || sgp == SGP_READ)
+		goto out;
 
 	/*
 	 * Fast cache lookup did not find it:
@@ -1969,14 +1970,13 @@ clear:
 	 * it now, lest undo on failure cancel our earlier guarantee.
 	 */
 	if (sgp != SGP_WRITE && !PageUptodate(page)) {
-		struct page *head = compound_head(page);
 		int i;
 
-		for (i = 0; i < compound_nr(head); i++) {
-			clear_highpage(head + i);
-			flush_dcache_page(head + i);
+		for (i = 0; i < compound_nr(page); i++) {
+			clear_highpage(page + i);
+			flush_dcache_page(page + i);
 		}
-		SetPageUptodate(head);
+		SetPageUptodate(page);
 	}
 
 	/* Perhaps the file has been truncated since we checked */
@@ -1992,6 +1992,7 @@ clear:
 		error = -EINVAL;
 		goto unlock;
 	}
+out:
 	*pagep = page + index - hindex;
 	return 0;
 
-- 
cgit v1.2.3


From a8cf7f272b5a28a62ecfc39d6f7d75b4f486e350 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 13 Oct 2020 16:51:41 -0700
Subject: mm: add find_lock_head

Add a new FGP_HEAD flag which avoids calling find_subpage() and add a
convenience wrapper for it.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: William Kucharski <william.kucharski@oracle.com>
Link: https://lkml.kernel.org/r/20200910183318.20139-9-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/pagemap.h | 32 ++++++++++++++++++++++++++------
 mm/filemap.c            |  9 ++++++---
 2 files changed, 32 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 5176009e4ffa..1a3554f5d992 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -279,6 +279,7 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping,
 #define FGP_NOFS		0x00000010
 #define FGP_NOWAIT		0x00000020
 #define FGP_FOR_MMAP		0x00000040
+#define FGP_HEAD		0x00000080
 
 struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
 		int fgp_flags, gfp_t cache_gfp_mask);
@@ -310,18 +311,37 @@ static inline struct page *find_get_page_flags(struct address_space *mapping,
  * @mapping: the address_space to search
  * @offset: the page index
  *
- * Looks up the page cache slot at @mapping & @offset.  If there is a
+ * Looks up the page cache entry at @mapping & @offset.  If there is a
  * page cache page, it is returned locked and with an increased
  * refcount.
  *
- * Otherwise, %NULL is returned.
- *
- * find_lock_page() may sleep.
+ * Context: May sleep.
+ * Return: A struct page or %NULL if there is no page in the cache for this
+ * index.
  */
 static inline struct page *find_lock_page(struct address_space *mapping,
-					pgoff_t offset)
+					pgoff_t index)
+{
+	return pagecache_get_page(mapping, index, FGP_LOCK, 0);
+}
+
+/**
+ * find_lock_head - Locate, pin and lock a pagecache page.
+ * @mapping: The address_space to search.
+ * @offset: The page index.
+ *
+ * Looks up the page cache entry at @mapping & @offset.  If there is a
+ * page cache page, its head page is returned locked and with an increased
+ * refcount.
+ *
+ * Context: May sleep.
+ * Return: A struct page which is !PageTail, or %NULL if there is no page
+ * in the cache for this index.
+ */
+static inline struct page *find_lock_head(struct address_space *mapping,
+					pgoff_t index)
 {
-	return pagecache_get_page(mapping, offset, FGP_LOCK, 0);
+	return pagecache_get_page(mapping, index, FGP_LOCK | FGP_HEAD, 0);
 }
 
 /**
diff --git a/mm/filemap.c b/mm/filemap.c
index b44346a748fa..63d2fed539d7 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1737,6 +1737,8 @@ repeat:
  *
  * * %FGP_ACCESSED - The page will be marked accessed.
  * * %FGP_LOCK - The page is returned locked.
+ * * %FGP_HEAD - If the page is present and a THP, return the head page
+ *   rather than the exact page specified by the index.
  * * %FGP_CREAT - If no page is present then a new page is allocated using
  *   @gfp_mask and added to the page cache and the VM's LRU list.
  *   The page is returned locked and with an increased refcount.
@@ -1765,7 +1767,6 @@ repeat:
 		page = NULL;
 	if (!page)
 		goto no_page;
-	page = find_subpage(page, index);
 
 	if (fgp_flags & FGP_LOCK) {
 		if (fgp_flags & FGP_NOWAIT) {
@@ -1778,12 +1779,12 @@ repeat:
 		}
 
 		/* Has the page been truncated? */
-		if (unlikely(compound_head(page)->mapping != mapping)) {
+		if (unlikely(page->mapping != mapping)) {
 			unlock_page(page);
 			put_page(page);
 			goto repeat;
 		}
-		VM_BUG_ON_PAGE(page->index != index, page);
+		VM_BUG_ON_PAGE(!thp_contains(page, index), page);
 	}
 
 	if (fgp_flags & FGP_ACCESSED)
@@ -1793,6 +1794,8 @@ repeat:
 		if (page_is_idle(page))
 			clear_page_idle(page);
 	}
+	if (!(fgp_flags & FGP_HEAD))
+		page = find_subpage(page, index);
 
 no_page:
 	if (!page && (fgp_flags & FGP_CREAT)) {
-- 
cgit v1.2.3


From eb1d7a65f08a52dfb828bf45b4ead7f617c64047 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Tue, 13 Oct 2020 16:51:47 -0700
Subject: mm, fadvise: improve the expensive remote LRU cache draining after
 FADV_DONTNEED

Our users reported that there're some random latency spikes when their RT
process is running.  Finally we found that latency spike is caused by
FADV_DONTNEED.  Which may call lru_add_drain_all() to drain LRU cache on
remote CPUs, and then waits the per-cpu work to complete.  The wait time
is uncertain, which may be tens millisecond.

That behavior is unreasonable, because this process is bound to a specific
CPU and the file is only accessed by itself, IOW, there should be no
pagecache pages on a per-cpu pagevec of a remote CPU.  That unreasonable
behavior is partially caused by the wrong comparation of the number of
invalidated pages and the number of the target.  For example,

        if (count < (end_index - start_index + 1))

The count above is how many pages were invalidated in the local CPU, and
(end_index - start_index + 1) is how many pages should be invalidated.
The usage of (end_index - start_index + 1) is incorrect, because they are
virtual addresses, which may not mapped to pages.  Besides that, there may
be holes between start and end.  So we'd better check whether there are
still pages on per-cpu pagevec after drain the local cpu, and then decide
whether or not to call lru_add_drain_all().

After I applied it with a hotfix to our production environment, most of
the lru_add_drain_all() can be avoided.

Suggested-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Link: https://lkml.kernel.org/r/20200923133318.14373-1-laoar.shao@gmail.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/fs.h |  4 ++++
 mm/fadvise.c       |  9 +++++----
 mm/truncate.c      | 58 +++++++++++++++++++++++++++++++++++++-----------------
 3 files changed, 49 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 2e621d28cd65..5815f7d4dbf4 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2581,6 +2581,10 @@ extern bool is_bad_inode(struct inode *);
 unsigned long invalidate_mapping_pages(struct address_space *mapping,
 					pgoff_t start, pgoff_t end);
 
+void invalidate_mapping_pagevec(struct address_space *mapping,
+				pgoff_t start, pgoff_t end,
+				unsigned long *nr_pagevec);
+
 static inline void invalidate_remote_inode(struct inode *inode)
 {
 	if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
diff --git a/mm/fadvise.c b/mm/fadvise.c
index 0e66f2aaeea3..d6baa4f451c5 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -141,7 +141,7 @@ int generic_fadvise(struct file *file, loff_t offset, loff_t len, int advice)
 		}
 
 		if (end_index >= start_index) {
-			unsigned long count;
+			unsigned long nr_pagevec = 0;
 
 			/*
 			 * It's common to FADV_DONTNEED right after
@@ -154,8 +154,9 @@ int generic_fadvise(struct file *file, loff_t offset, loff_t len, int advice)
 			 */
 			lru_add_drain();
 
-			count = invalidate_mapping_pages(mapping,
-						start_index, end_index);
+			invalidate_mapping_pagevec(mapping,
+						start_index, end_index,
+						&nr_pagevec);
 
 			/*
 			 * If fewer pages were invalidated than expected then
@@ -163,7 +164,7 @@ int generic_fadvise(struct file *file, loff_t offset, loff_t len, int advice)
 			 * a per-cpu pagevec for a remote CPU. Drain all
 			 * pagevecs and try again.
 			 */
-			if (count < (end_index - start_index + 1)) {
+			if (nr_pagevec) {
 				lru_add_drain_all();
 				invalidate_mapping_pages(mapping, start_index,
 						end_index);
diff --git a/mm/truncate.c b/mm/truncate.c
index dd9ebc1da356..6bbe0f0b3ce9 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -528,23 +528,8 @@ void truncate_inode_pages_final(struct address_space *mapping)
 }
 EXPORT_SYMBOL(truncate_inode_pages_final);
 
-/**
- * invalidate_mapping_pages - Invalidate all the unlocked pages of one inode
- * @mapping: the address_space which holds the pages to invalidate
- * @start: the offset 'from' which to invalidate
- * @end: the offset 'to' which to invalidate (inclusive)
- *
- * This function only removes the unlocked pages, if you want to
- * remove all the pages of one inode, you must call truncate_inode_pages.
- *
- * invalidate_mapping_pages() will not block on IO activity. It will not
- * invalidate pages which are dirty, locked, under writeback or mapped into
- * pagetables.
- *
- * Return: the number of the pages that were invalidated
- */
-unsigned long invalidate_mapping_pages(struct address_space *mapping,
-		pgoff_t start, pgoff_t end)
+unsigned long __invalidate_mapping_pages(struct address_space *mapping,
+		pgoff_t start, pgoff_t end, unsigned long *nr_pagevec)
 {
 	pgoff_t indices[PAGEVEC_SIZE];
 	struct pagevec pvec;
@@ -610,8 +595,13 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
 			 * Invalidation is a hint that the page is no longer
 			 * of interest and try to speed up its reclaim.
 			 */
-			if (!ret)
+			if (!ret) {
 				deactivate_file_page(page);
+				/* It is likely on the pagevec of a remote CPU */
+				if (nr_pagevec)
+					(*nr_pagevec)++;
+			}
+
 			if (PageTransHuge(page))
 				put_page(page);
 			count += ret;
@@ -623,8 +613,40 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
 	}
 	return count;
 }
+
+/**
+ * invalidate_mapping_pages - Invalidate all the unlocked pages of one inode
+ * @mapping: the address_space which holds the pages to invalidate
+ * @start: the offset 'from' which to invalidate
+ * @end: the offset 'to' which to invalidate (inclusive)
+ *
+ * This function only removes the unlocked pages, if you want to
+ * remove all the pages of one inode, you must call truncate_inode_pages.
+ *
+ * invalidate_mapping_pages() will not block on IO activity. It will not
+ * invalidate pages which are dirty, locked, under writeback or mapped into
+ * pagetables.
+ *
+ * Return: the number of the pages that were invalidated
+ */
+unsigned long invalidate_mapping_pages(struct address_space *mapping,
+		pgoff_t start, pgoff_t end)
+{
+	return __invalidate_mapping_pages(mapping, start, end, NULL);
+}
 EXPORT_SYMBOL(invalidate_mapping_pages);
 
+/**
+ * This helper is similar with the above one, except that it accounts for pages
+ * that are likely on a pagevec and count them in @nr_pagevec, which will used by
+ * the caller.
+ */
+void invalidate_mapping_pagevec(struct address_space *mapping,
+		pgoff_t start, pgoff_t end, unsigned long *nr_pagevec)
+{
+	__invalidate_mapping_pages(mapping, start, end, nr_pagevec);
+}
+
 /*
  * This is like invalidate_complete_page(), except it ignores the page's
  * refcount.  We do this because invalidate_inode_pages2() needs stronger
-- 
cgit v1.2.3


From 3264631548b1f2bf89b71793d06bfd0f748f649d Mon Sep 17 00:00:00 2001
From: Gao Xiang <hsiangkao@redhat.com>
Date: Tue, 13 Oct 2020 16:52:04 -0700
Subject: swap: rename SWP_FS to SWAP_FS_OPS to avoid ambiguity

SWP_FS is used to make swap_{read,write}page() go through the filesystem,
and it's only used for swap files over NFS for now.  Otherwise it will
directly submit IO to blockdev according to swapfile extents reported by
filesystems in advance.

As Matthew pointed out [1], SWP_FS naming is somewhat confusing, so let's
rename to SWP_FS_OPS.

[1] https://lore.kernel.org/r/20200820113448.GM17456@casper.infradead.org

Suggested-by: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Gao Xiang <hsiangkao@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Link: https://lkml.kernel.org/r/20200822113019.11319-1-hsiangkao@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/swap.h | 2 +-
 mm/page_io.c         | 6 +++---
 mm/swap_state.c      | 2 +-
 mm/swapfile.c        | 2 +-
 4 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 23c6e43a956d..7bd5b4aac049 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -170,7 +170,7 @@ enum {
 	SWP_CONTINUED	= (1 << 5),	/* swap_map has count continuation */
 	SWP_BLKDEV	= (1 << 6),	/* its a block device */
 	SWP_ACTIVATED	= (1 << 7),	/* set after swap_activate success */
-	SWP_FS		= (1 << 8),	/* swap file goes through fs */
+	SWP_FS_OPS	= (1 << 8),	/* swapfile operations go through fs */
 	SWP_AREA_DISCARD = (1 << 9),	/* single-time swap area discards */
 	SWP_PAGE_DISCARD = (1 << 10),	/* freed swap page-cluster discards */
 	SWP_STABLE_WRITES = (1 << 11),	/* no overwrite PG_writeback pages */
diff --git a/mm/page_io.c b/mm/page_io.c
index f9e9267f296f..2ffe4c4a6d97 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -312,7 +312,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc,
 	struct swap_info_struct *sis = page_swap_info(page);
 
 	VM_BUG_ON_PAGE(!PageSwapCache(page), page);
-	if (data_race(sis->flags & SWP_FS)) {
+	if (data_race(sis->flags & SWP_FS_OPS)) {
 		struct kiocb kiocb;
 		struct file *swap_file = sis->swap_file;
 		struct address_space *mapping = swap_file->f_mapping;
@@ -403,7 +403,7 @@ int swap_readpage(struct page *page, bool synchronous)
 		goto out;
 	}
 
-	if (data_race(sis->flags & SWP_FS)) {
+	if (data_race(sis->flags & SWP_FS_OPS)) {
 		struct file *swap_file = sis->swap_file;
 		struct address_space *mapping = swap_file->f_mapping;
 
@@ -467,7 +467,7 @@ int swap_set_page_dirty(struct page *page)
 {
 	struct swap_info_struct *sis = page_swap_info(page);
 
-	if (data_race(sis->flags & SWP_FS)) {
+	if (data_race(sis->flags & SWP_FS_OPS)) {
 		struct address_space *mapping = sis->swap_file->f_mapping;
 
 		VM_BUG_ON_PAGE(!PageSwapCache(page), page);
diff --git a/mm/swap_state.c b/mm/swap_state.c
index f24f2cea4238..aa40e706604c 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -665,7 +665,7 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
 		goto skip;
 
 	/* Test swap type to make sure the dereference is safe */
-	if (likely(si->flags & (SWP_BLKDEV | SWP_FS))) {
+	if (likely(si->flags & (SWP_BLKDEV | SWP_FS_OPS))) {
 		struct inode *inode = si->swap_file->f_mapping->host;
 		if (inode_read_congested(inode))
 			goto skip;
diff --git a/mm/swapfile.c b/mm/swapfile.c
index ced4635d924c..183b87bc87cc 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2437,7 +2437,7 @@ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span)
 		if (ret >= 0)
 			sis->flags |= SWP_ACTIVATED;
 		if (!ret) {
-			sis->flags |= SWP_FS;
+			sis->flags |= SWP_FS_OPS;
 			ret = add_swap_extent(sis, 0, sis->max, 0);
 			*span = sis->pages;
 		}
-- 
cgit v1.2.3


From cc2828b21c764f901128ca2e7b9f056d0e72104f Mon Sep 17 00:00:00 2001
From: Yu Zhao <yuzhao@google.com>
Date: Tue, 13 Oct 2020 16:52:08 -0700
Subject: mm: remove activate_page() from unuse_pte()

We don't initially add anon pages to active lruvec after commit
b518154e59aa ("mm/vmscan: protect the workingset on anonymous LRU").
Remove activate_page() from unuse_pte(), which seems to be missed by the
commit.  And make the function static while we are at it.

Before the commit, we called lru_cache_add_active_or_unevictable() to add
new ksm pages to active lruvec.  Therefore, activate_page() wasn't
necessary for them in the first place.

Signed-off-by: Yu Zhao <yuzhao@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Yang Shi <shy828301@gmail.com>
Cc: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Qian Cai <cai@lca.pw>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Link: http://lkml.kernel.org/r/20200818184704.3625199-1-yuzhao@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/swap.h | 1 -
 mm/swap.c            | 4 ++--
 mm/swapfile.c        | 5 -----
 3 files changed, 2 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 7bd5b4aac049..667935c0dbd4 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -340,7 +340,6 @@ extern void lru_note_cost_page(struct page *);
 extern void lru_cache_add(struct page *);
 extern void lru_add_page_tail(struct page *page, struct page *page_tail,
 			 struct lruvec *lruvec, struct list_head *head);
-extern void activate_page(struct page *);
 extern void mark_page_accessed(struct page *);
 extern void lru_add_drain(void);
 extern void lru_add_drain_cpu(int cpu);
diff --git a/mm/swap.c b/mm/swap.c
index 65ef7e3525bf..82ddefda4904 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -348,7 +348,7 @@ static bool need_activate_page_drain(int cpu)
 	return pagevec_count(&per_cpu(lru_pvecs.activate_page, cpu)) != 0;
 }
 
-void activate_page(struct page *page)
+static void activate_page(struct page *page)
 {
 	page = compound_head(page);
 	if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
@@ -368,7 +368,7 @@ static inline void activate_page_drain(int cpu)
 {
 }
 
-void activate_page(struct page *page)
+static void activate_page(struct page *page)
 {
 	pg_data_t *pgdat = page_pgdat(page);
 
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 183b87bc87cc..d5c19d0baf06 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1929,11 +1929,6 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 		lru_cache_add_inactive_or_unevictable(page, vma);
 	}
 	swap_free(entry);
-	/*
-	 * Move the page to the active list so it is not
-	 * immediately swapped out again after swapon.
-	 */
-	activate_page(page);
 out:
 	pte_unmap_unlock(pte, ptl);
 	if (page != swapcache) {
-- 
cgit v1.2.3


From f3bc52cb04bcfccd12da3f03ca8bc50484898436 Mon Sep 17 00:00:00 2001
From: Miaohe Lin <linmiaohe@huawei.com>
Date: Tue, 13 Oct 2020 16:52:18 -0700
Subject: mm/swap_slots.c: remove always zero and unused return value of
 enable_swap_slots_cache()

enable_swap_slots_cache() always return zero and its return value is just
ignored by the caller.  So make enable_swap_slots_cache() void.

Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Link: https://lkml.kernel.org/r/20200924113554.50614-1-linmiaohe@huawei.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/swap_slots.h | 2 +-
 mm/swap_slots.c            | 3 +--
 2 files changed, 2 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/swap_slots.h b/include/linux/swap_slots.h
index e36b200c2a77..347f1a304190 100644
--- a/include/linux/swap_slots.h
+++ b/include/linux/swap_slots.h
@@ -23,7 +23,7 @@ struct swap_slots_cache {
 
 void disable_swap_slots_cache_lock(void);
 void reenable_swap_slots_cache_unlock(void);
-int enable_swap_slots_cache(void);
+void enable_swap_slots_cache(void);
 int free_swap_slot(swp_entry_t entry);
 
 extern bool swap_slot_cache_enabled;
diff --git a/mm/swap_slots.c b/mm/swap_slots.c
index 3e6453573a89..0357fbe70645 100644
--- a/mm/swap_slots.c
+++ b/mm/swap_slots.c
@@ -237,7 +237,7 @@ static int free_slot_cache(unsigned int cpu)
 	return 0;
 }
 
-int enable_swap_slots_cache(void)
+void enable_swap_slots_cache(void)
 {
 	mutex_lock(&swap_slots_cache_enable_mutex);
 	if (!swap_slot_cache_initialized) {
@@ -255,7 +255,6 @@ int enable_swap_slots_cache(void)
 	__reenable_swap_slots_cache();
 out_unlock:
 	mutex_unlock(&swap_slots_cache_enable_mutex);
-	return 0;
 }
 
 /* called with swap slot cache's alloc lock held */
-- 
cgit v1.2.3


From bd0b230fe14554bfffbae54e19038716f96f5a41 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Tue, 13 Oct 2020 16:52:56 -0700
Subject: mm/memcg: unify swap and memsw page counters

The swap page counter is v2 only while memsw is v1 only.  As v1 and v2
controllers cannot be active at the same time, there is no point to keep
both swap and memsw page counters in mem_cgroup.  The previous patch has
made sure that memsw page counter is updated and accessed only when in v1
code paths.  So it is now safe to alias the v1 memsw page counter to v2
swap page counter.  This saves 14 long's in the size of mem_cgroup.  This
is a saving of 112 bytes for 64-bit archs.

While at it, also document which page counters are used in v1 and/or v2.

Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Chris Down <chris@chrisdown.name>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Roman Gushchin <guro@fb.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Yafang Shao <laoar.shao@gmail.com>
Link: https://lkml.kernel.org/r/20200914024452.19167-4-longman@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 13 ++++++++-----
 mm/memcontrol.c            |  3 ---
 2 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index d0b036123c6a..6ef4a552e09d 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -215,13 +215,16 @@ struct mem_cgroup {
 	struct mem_cgroup_id id;
 
 	/* Accounted resources */
-	struct page_counter memory;
-	struct page_counter swap;
+	struct page_counter memory;		/* Both v1 & v2 */
+
+	union {
+		struct page_counter swap;	/* v2 only */
+		struct page_counter memsw;	/* v1 only */
+	};
 
 	/* Legacy consumer-oriented counters */
-	struct page_counter memsw;
-	struct page_counter kmem;
-	struct page_counter tcpmem;
+	struct page_counter kmem;		/* v1 only */
+	struct page_counter tcpmem;		/* v1 only */
 
 	/* Range enforcement for interrupt charges */
 	struct work_struct high_work;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 962f8d649b83..a0bfc92804b7 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5295,13 +5295,11 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 		memcg->use_hierarchy = true;
 		page_counter_init(&memcg->memory, &parent->memory);
 		page_counter_init(&memcg->swap, &parent->swap);
-		page_counter_init(&memcg->memsw, &parent->memsw);
 		page_counter_init(&memcg->kmem, &parent->kmem);
 		page_counter_init(&memcg->tcpmem, &parent->tcpmem);
 	} else {
 		page_counter_init(&memcg->memory, NULL);
 		page_counter_init(&memcg->swap, NULL);
-		page_counter_init(&memcg->memsw, NULL);
 		page_counter_init(&memcg->kmem, NULL);
 		page_counter_init(&memcg->tcpmem, NULL);
 		/*
@@ -5430,7 +5428,6 @@ static void mem_cgroup_css_reset(struct cgroup_subsys_state *css)
 
 	page_counter_set_max(&memcg->memory, PAGE_COUNTER_MAX);
 	page_counter_set_max(&memcg->swap, PAGE_COUNTER_MAX);
-	page_counter_set_max(&memcg->memsw, PAGE_COUNTER_MAX);
 	page_counter_set_max(&memcg->kmem, PAGE_COUNTER_MAX);
 	page_counter_set_max(&memcg->tcpmem, PAGE_COUNTER_MAX);
 	page_counter_set_min(&memcg->memory, 0);
-- 
cgit v1.2.3


From b2b29d6d01194404dfef4eafa026959be301705b Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Tue, 13 Oct 2020 16:53:22 -0700
Subject: mm: account PMD tables like PTE tables

We account the PTE level of the page tables to the process in order to
make smarter OOM decisions and help diagnose why memory is fragmented.
For these same reasons, we should account pages allocated for PMDs.  With
larger process address spaces and ASLR, the number of PMDs in use is
higher than it used to be so the inaccuracy is starting to matter.

[rppt@linux.ibm.com: arm: __pmd_free_tlb(): call page table destructor]
  Link: https://lkml.kernel.org/r/20200825111303.GB69694@linux.ibm.com

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
Cc: Abdul Haleem <abdhalee@linux.vnet.ibm.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Satheesh Rajendran <sathnaga@linux.vnet.ibm.com>
Cc: Stafford Horne <shorne@gmail.com>
Cc: Naresh Kamboju <naresh.kamboju@linaro.org>
Cc: Anders Roxell <anders.roxell@linaro.org>
Link: http://lkml.kernel.org/r/20200627184642.GF25039@casper.infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arm/include/asm/tlb.h |  1 +
 include/linux/mm.h         | 24 ++++++++++++++++++++----
 2 files changed, 21 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index 9415222b49ad..b8cbe03ad260 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -59,6 +59,7 @@ __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr)
 #ifdef CONFIG_ARM_LPAE
 	struct page *page = virt_to_page(pmdp);
 
+	pgtable_pmd_page_dtor(page);
 	tlb_remove_table(tlb, page);
 #endif
 }
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 9cc0894e7d61..5320e7ab843f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2254,7 +2254,7 @@ static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd)
 	return ptlock_ptr(pmd_to_page(pmd));
 }
 
-static inline bool pgtable_pmd_page_ctor(struct page *page)
+static inline bool pmd_ptlock_init(struct page *page)
 {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	page->pmd_huge_pte = NULL;
@@ -2262,7 +2262,7 @@ static inline bool pgtable_pmd_page_ctor(struct page *page)
 	return ptlock_init(page);
 }
 
-static inline void pgtable_pmd_page_dtor(struct page *page)
+static inline void pmd_ptlock_free(struct page *page)
 {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	VM_BUG_ON_PAGE(page->pmd_huge_pte, page);
@@ -2279,8 +2279,8 @@ static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd)
 	return &mm->page_table_lock;
 }
 
-static inline bool pgtable_pmd_page_ctor(struct page *page) { return true; }
-static inline void pgtable_pmd_page_dtor(struct page *page) {}
+static inline bool pmd_ptlock_init(struct page *page) { return true; }
+static inline void pmd_ptlock_free(struct page *page) {}
 
 #define pmd_huge_pte(mm, pmd) ((mm)->pmd_huge_pte)
 
@@ -2293,6 +2293,22 @@ static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd)
 	return ptl;
 }
 
+static inline bool pgtable_pmd_page_ctor(struct page *page)
+{
+	if (!pmd_ptlock_init(page))
+		return false;
+	__SetPageTable(page);
+	inc_zone_page_state(page, NR_PAGETABLE);
+	return true;
+}
+
+static inline void pgtable_pmd_page_dtor(struct page *page)
+{
+	pmd_ptlock_free(page);
+	__ClearPageTable(page);
+	dec_zone_page_state(page, NR_PAGETABLE);
+}
+
 /*
  * No scalability reason to split PUD locks yet, but follow the same pattern
  * as the PMD locks to make it easier if we decide to.  The VM should not be
-- 
cgit v1.2.3


From 07e5bfe651f8595ca6a777d989016aa8d8217924 Mon Sep 17 00:00:00 2001
From: Chinwen Chang <chinwen.chang@mediatek.com>
Date: Tue, 13 Oct 2020 16:53:39 -0700
Subject: mmap locking API: add mmap_lock_is_contended()

Patch series "Try to release mmap_lock temporarily in smaps_rollup", v4.

Recently, we have observed some janky issues caused by unpleasantly long
contention on mmap_lock which is held by smaps_rollup when probing large
processes.  To address the problem, we let smaps_rollup detect if anyone
wants to acquire mmap_lock for write attempts.  If yes, just release the
lock temporarily to ease the contention.

smaps_rollup is a procfs interface which allows users to summarize the
process's memory usage without the overhead of seq_* calls.  Android uses
it to sample the memory usage of various processes to balance its memory
pool sizes.  If no one wants to take the lock for write requests,
smaps_rollup with this patch will behave like the original one.

Although there are on-going mmap_lock optimizations like range-based
locks, the lock applied to smaps_rollup would be the coarse one, which is
hard to avoid the occurrence of aforementioned issues.  So the detection
and temporary release for write attempts on mmap_lock in smaps_rollup is
still necessary.

This patch (of 3):

Add new API to query if someone wants to acquire mmap_lock for write
attempts.

Using this instead of rwsem_is_contended makes it more tolerant of future
changes to the lock type.

Signed-off-by: Chinwen Chang <chinwen.chang@mediatek.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Steven Price <steven.price@arm.com>
Acked-by: Michel Lespinasse <walken@google.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: Daniel Kiss <daniel.kiss@arm.com>
Cc: Davidlohr Bueso <dbueso@suse.de>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jimmy Assarsson <jimmyassarsson@gmail.com>
Cc: Laurent Dufour <ldufour@linux.ibm.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Matthias Brugger <matthias.bgg@gmail.com>
Cc: Song Liu <songliubraving@fb.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Link: http://lkml.kernel.org/r/1597715898-3854-1-git-send-email-chinwen.chang@mediatek.com
Link: http://lkml.kernel.org/r/1597715898-3854-2-git-send-email-chinwen.chang@mediatek.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmap_lock.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h
index 0707671851a8..18e7eae9b5ba 100644
--- a/include/linux/mmap_lock.h
+++ b/include/linux/mmap_lock.h
@@ -87,4 +87,9 @@ static inline void mmap_assert_write_locked(struct mm_struct *mm)
 	VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm);
 }
 
+static inline int mmap_lock_is_contended(struct mm_struct *mm)
+{
+	return rwsem_is_contended(&mm->mmap_lock);
+}
+
 #endif /* _LINUX_MMAP_LOCK_H */
-- 
cgit v1.2.3


From e18c45ffcfa347b13c2f300f290bacff55a4b41e Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 13 Oct 2020 16:53:50 -0700
Subject: mm: move PageDoubleMap bit

Patch series "Fix PageDoubleMap".

This is a purely theoretical problem for now as none of the filesystems
which use PG_private_2 (ie PG_fscache) are being converted at this time,
but it's confusing to leave it like this.

This patch (of 2):

PG_private_2 is defined as being PF_ANY (applicable to tail pages as well
as regular & head pages).  That means that the first tail page of a
double-map page will appear to have Private2 set.  Use the Workingset bit
instead which is defined as PF_HEAD so any attempt to access the
Workingset bit on a tail page will redirect to the head page's Workingset
bit.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Link: https://lkml.kernel.org/r/20200629151933.15671-1-willy@infradead.org
Link: https://lkml.kernel.org/r/20200629151933.15671-2-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/page-flags.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 276140c94f4a..76413b2ffef0 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -167,7 +167,7 @@ enum pageflags {
 	PG_slob_free = PG_private,
 
 	/* Compound pages. Stored in first tail page's flags */
-	PG_double_map = PG_private_2,
+	PG_double_map = PG_workingset,
 
 	/* non-lru isolated movable page */
 	PG_isolated = PG_reclaim,
-- 
cgit v1.2.3


From a08d93e5752a35a771054f6c463f789720f9a3e8 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 13 Oct 2020 16:53:54 -0700
Subject: mm: simplify PageDoubleMap with PF_SECOND policy

Introduce the new page policy of PF_SECOND which lets us use the normal
pageflags generation machinery to create the various DoubleMap
manipulation functions.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Link: https://lkml.kernel.org/r/20200629151933.15671-3-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/page-flags.h | 40 ++++++++++------------------------------
 1 file changed, 10 insertions(+), 30 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 76413b2ffef0..38ded408bd4c 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -235,6 +235,9 @@ static inline void page_init_poison(struct page *page, size_t size)
  *
  * PF_NO_COMPOUND:
  *     the page flag is not relevant for compound pages.
+ *
+ * PF_SECOND:
+ *     the page flag is stored in the first tail page.
  */
 #define PF_POISONED_CHECK(page) ({					\
 		VM_BUG_ON_PGFLAGS(PagePoisoned(page), page);		\
@@ -250,6 +253,9 @@ static inline void page_init_poison(struct page *page, size_t size)
 #define PF_NO_COMPOUND(page, enforce) ({				\
 		VM_BUG_ON_PGFLAGS(enforce && PageCompound(page), page);	\
 		PF_POISONED_CHECK(page); })
+#define PF_SECOND(page, enforce) ({					\
+		VM_BUG_ON_PGFLAGS(!PageHead(page), page);		\
+		PF_POISONED_CHECK(&page[1]); })
 
 /*
  * Macros to create function definitions for page flags
@@ -688,42 +694,15 @@ static inline int PageTransTail(struct page *page)
  *
  * See also __split_huge_pmd_locked() and page_remove_anon_compound_rmap().
  */
-static inline int PageDoubleMap(struct page *page)
-{
-	return PageHead(page) && test_bit(PG_double_map, &page[1].flags);
-}
-
-static inline void SetPageDoubleMap(struct page *page)
-{
-	VM_BUG_ON_PAGE(!PageHead(page), page);
-	set_bit(PG_double_map, &page[1].flags);
-}
-
-static inline void ClearPageDoubleMap(struct page *page)
-{
-	VM_BUG_ON_PAGE(!PageHead(page), page);
-	clear_bit(PG_double_map, &page[1].flags);
-}
-static inline int TestSetPageDoubleMap(struct page *page)
-{
-	VM_BUG_ON_PAGE(!PageHead(page), page);
-	return test_and_set_bit(PG_double_map, &page[1].flags);
-}
-
-static inline int TestClearPageDoubleMap(struct page *page)
-{
-	VM_BUG_ON_PAGE(!PageHead(page), page);
-	return test_and_clear_bit(PG_double_map, &page[1].flags);
-}
-
+PAGEFLAG(DoubleMap, double_map, PF_SECOND)
+	TESTSCFLAG(DoubleMap, double_map, PF_SECOND)
 #else
 TESTPAGEFLAG_FALSE(TransHuge)
 TESTPAGEFLAG_FALSE(TransCompound)
 TESTPAGEFLAG_FALSE(TransCompoundMap)
 TESTPAGEFLAG_FALSE(TransTail)
 PAGEFLAG_FALSE(DoubleMap)
-	TESTSETFLAG_FALSE(DoubleMap)
-	TESTCLEARFLAG_FALSE(DoubleMap)
+	TESTSCFLAG_FALSE(DoubleMap)
 #endif
 
 /*
@@ -888,6 +867,7 @@ static inline int page_has_private(struct page *page)
 #undef PF_ONLY_HEAD
 #undef PF_NO_TAIL
 #undef PF_NO_COMPOUND
+#undef PF_SECOND
 #endif /* !__GENERATING_BOUNDS_H */
 
 #endif	/* PAGE_FLAGS_H */
-- 
cgit v1.2.3


From c78f463649d60f4ed12df97a32def4d77b583853 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Tue, 13 Oct 2020 16:54:21 -0700
Subject: mm: remove src/dst mm parameter in copy_page_range()

Both of the mm pointers are not needed after commit 7a4830c380f3
("mm/fork: Pass new vma pointer into copy_page_range()").

Jason Gunthorpe also reported that the ordering of copy_page_range() is
odd.  Since working at it, reorder the parameters to be logical, by (1)
always put the dst_* fields to be before src_* fields, and (2) keep the
same type of parameters together.

[peterx@redhat.com: further reorder some parameters and line format, per Jason]
  Link: https://lkml.kernel.org/r/20201002192647.7161-1-peterx@redhat.com
[peterx@redhat.com: fix warnings]
  Link: https://lkml.kernel.org/r/20201006200138.GA6026@xz-x1

Reported-by: Kirill A. Shutemov <kirill@shutemov.name>
Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Link: https://lkml.kernel.org/r/20200930204950.6668-1-peterx@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h |   4 +-
 kernel/fork.c      |   2 +-
 mm/memory.c        | 141 +++++++++++++++++++++++++++--------------------------
 3 files changed, 76 insertions(+), 71 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 5320e7ab843f..620961e4f32b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1653,8 +1653,8 @@ struct mmu_notifier_range;
 
 void free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
 		unsigned long end, unsigned long floor, unsigned long ceiling);
-int copy_page_range(struct mm_struct *dst, struct mm_struct *src,
-		    struct vm_area_struct *vma, struct vm_area_struct *new);
+int
+copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma);
 int follow_pte_pmd(struct mm_struct *mm, unsigned long address,
 		   struct mmu_notifier_range *range,
 		   pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp);
diff --git a/kernel/fork.c b/kernel/fork.c
index 2dcb19a30650..ede26e5a6097 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -590,7 +590,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 
 		mm->map_count++;
 		if (!(tmp->vm_flags & VM_WIPEONFORK))
-			retval = copy_page_range(mm, oldmm, mpnt, tmp);
+			retval = copy_page_range(tmp, mpnt);
 
 		if (tmp->vm_ops && tmp->vm_ops->open)
 			tmp->vm_ops->open(tmp);
diff --git a/mm/memory.c b/mm/memory.c
index 5a1c4c9759dc..f482af8bc828 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -794,15 +794,14 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
  * lock.
  */
 static inline int
-copy_present_page(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-		pte_t *dst_pte, pte_t *src_pte,
-		struct vm_area_struct *vma, struct vm_area_struct *new,
-		unsigned long addr, int *rss, struct page **prealloc,
-		pte_t pte, struct page *page)
+copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
+		  pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss,
+		  struct page **prealloc, pte_t pte, struct page *page)
 {
+	struct mm_struct *src_mm = src_vma->vm_mm;
 	struct page *new_page;
 
-	if (!is_cow_mapping(vma->vm_flags))
+	if (!is_cow_mapping(src_vma->vm_flags))
 		return 1;
 
 	/*
@@ -832,16 +831,16 @@ copy_present_page(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	 * over and copy the page & arm it.
 	 */
 	*prealloc = NULL;
-	copy_user_highpage(new_page, page, addr, vma);
+	copy_user_highpage(new_page, page, addr, src_vma);
 	__SetPageUptodate(new_page);
-	page_add_new_anon_rmap(new_page, new, addr, false);
-	lru_cache_add_inactive_or_unevictable(new_page, new);
+	page_add_new_anon_rmap(new_page, dst_vma, addr, false);
+	lru_cache_add_inactive_or_unevictable(new_page, dst_vma);
 	rss[mm_counter(new_page)]++;
 
 	/* All done, just insert the new page copy in the child */
-	pte = mk_pte(new_page, new->vm_page_prot);
-	pte = maybe_mkwrite(pte_mkdirty(pte), new);
-	set_pte_at(dst_mm, addr, dst_pte, pte);
+	pte = mk_pte(new_page, dst_vma->vm_page_prot);
+	pte = maybe_mkwrite(pte_mkdirty(pte), dst_vma);
+	set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte);
 	return 0;
 }
 
@@ -850,24 +849,21 @@ copy_present_page(struct mm_struct *dst_mm, struct mm_struct *src_mm,
  * is required to copy this pte.
  */
 static inline int
-copy_present_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-		pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *vma,
-		struct vm_area_struct *new,
-		unsigned long addr, int *rss, struct page **prealloc)
+copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
+		 pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss,
+		 struct page **prealloc)
 {
-	unsigned long vm_flags = vma->vm_flags;
+	struct mm_struct *src_mm = src_vma->vm_mm;
+	unsigned long vm_flags = src_vma->vm_flags;
 	pte_t pte = *src_pte;
 	struct page *page;
 
-	page = vm_normal_page(vma, addr, pte);
+	page = vm_normal_page(src_vma, addr, pte);
 	if (page) {
 		int retval;
 
-		retval = copy_present_page(dst_mm, src_mm,
-			dst_pte, src_pte,
-			vma, new,
-			addr, rss, prealloc,
-			pte, page);
+		retval = copy_present_page(dst_vma, src_vma, dst_pte, src_pte,
+					   addr, rss, prealloc, pte, page);
 		if (retval <= 0)
 			return retval;
 
@@ -901,7 +897,7 @@ copy_present_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	if (!(vm_flags & VM_UFFD_WP))
 		pte = pte_clear_uffd_wp(pte);
 
-	set_pte_at(dst_mm, addr, dst_pte, pte);
+	set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte);
 	return 0;
 }
 
@@ -924,11 +920,13 @@ page_copy_prealloc(struct mm_struct *src_mm, struct vm_area_struct *vma,
 	return new_page;
 }
 
-static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-		   pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma,
-		   struct vm_area_struct *new,
-		   unsigned long addr, unsigned long end)
+static int
+copy_pte_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
+	       pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
+	       unsigned long end)
 {
+	struct mm_struct *dst_mm = dst_vma->vm_mm;
+	struct mm_struct *src_mm = src_vma->vm_mm;
 	pte_t *orig_src_pte, *orig_dst_pte;
 	pte_t *src_pte, *dst_pte;
 	spinlock_t *src_ptl, *dst_ptl;
@@ -971,15 +969,15 @@ again:
 		if (unlikely(!pte_present(*src_pte))) {
 			entry.val = copy_nonpresent_pte(dst_mm, src_mm,
 							dst_pte, src_pte,
-							vma, addr, rss);
+							src_vma, addr, rss);
 			if (entry.val)
 				break;
 			progress += 8;
 			continue;
 		}
 		/* copy_present_pte() will clear `*prealloc' if consumed */
-		ret = copy_present_pte(dst_mm, src_mm, dst_pte, src_pte,
-				       vma, new, addr, rss, &prealloc);
+		ret = copy_present_pte(dst_vma, src_vma, dst_pte, src_pte,
+				       addr, rss, &prealloc);
 		/*
 		 * If we need a pre-allocated page for this pte, drop the
 		 * locks, allocate, and try again.
@@ -1014,7 +1012,7 @@ again:
 		entry.val = 0;
 	} else if (ret) {
 		WARN_ON_ONCE(ret != -EAGAIN);
-		prealloc = page_copy_prealloc(src_mm, vma, addr);
+		prealloc = page_copy_prealloc(src_mm, src_vma, addr);
 		if (!prealloc)
 			return -ENOMEM;
 		/* We've captured and resolved the error. Reset, try again. */
@@ -1028,11 +1026,13 @@ out:
 	return ret;
 }
 
-static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-		pud_t *dst_pud, pud_t *src_pud, struct vm_area_struct *vma,
-		struct vm_area_struct *new,
-		unsigned long addr, unsigned long end)
+static inline int
+copy_pmd_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
+	       pud_t *dst_pud, pud_t *src_pud, unsigned long addr,
+	       unsigned long end)
 {
+	struct mm_struct *dst_mm = dst_vma->vm_mm;
+	struct mm_struct *src_mm = src_vma->vm_mm;
 	pmd_t *src_pmd, *dst_pmd;
 	unsigned long next;
 
@@ -1045,9 +1045,9 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src
 		if (is_swap_pmd(*src_pmd) || pmd_trans_huge(*src_pmd)
 			|| pmd_devmap(*src_pmd)) {
 			int err;
-			VM_BUG_ON_VMA(next-addr != HPAGE_PMD_SIZE, vma);
+			VM_BUG_ON_VMA(next-addr != HPAGE_PMD_SIZE, src_vma);
 			err = copy_huge_pmd(dst_mm, src_mm,
-					    dst_pmd, src_pmd, addr, vma);
+					    dst_pmd, src_pmd, addr, src_vma);
 			if (err == -ENOMEM)
 				return -ENOMEM;
 			if (!err)
@@ -1056,18 +1056,20 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src
 		}
 		if (pmd_none_or_clear_bad(src_pmd))
 			continue;
-		if (copy_pte_range(dst_mm, src_mm, dst_pmd, src_pmd,
-				   vma, new, addr, next))
+		if (copy_pte_range(dst_vma, src_vma, dst_pmd, src_pmd,
+				   addr, next))
 			return -ENOMEM;
 	} while (dst_pmd++, src_pmd++, addr = next, addr != end);
 	return 0;
 }
 
-static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-		p4d_t *dst_p4d, p4d_t *src_p4d, struct vm_area_struct *vma,
-		struct vm_area_struct *new,
-		unsigned long addr, unsigned long end)
+static inline int
+copy_pud_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
+	       p4d_t *dst_p4d, p4d_t *src_p4d, unsigned long addr,
+	       unsigned long end)
 {
+	struct mm_struct *dst_mm = dst_vma->vm_mm;
+	struct mm_struct *src_mm = src_vma->vm_mm;
 	pud_t *src_pud, *dst_pud;
 	unsigned long next;
 
@@ -1080,9 +1082,9 @@ static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src
 		if (pud_trans_huge(*src_pud) || pud_devmap(*src_pud)) {
 			int err;
 
-			VM_BUG_ON_VMA(next-addr != HPAGE_PUD_SIZE, vma);
+			VM_BUG_ON_VMA(next-addr != HPAGE_PUD_SIZE, src_vma);
 			err = copy_huge_pud(dst_mm, src_mm,
-					    dst_pud, src_pud, addr, vma);
+					    dst_pud, src_pud, addr, src_vma);
 			if (err == -ENOMEM)
 				return -ENOMEM;
 			if (!err)
@@ -1091,18 +1093,19 @@ static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src
 		}
 		if (pud_none_or_clear_bad(src_pud))
 			continue;
-		if (copy_pmd_range(dst_mm, src_mm, dst_pud, src_pud,
-				   vma, new, addr, next))
+		if (copy_pmd_range(dst_vma, src_vma, dst_pud, src_pud,
+				   addr, next))
 			return -ENOMEM;
 	} while (dst_pud++, src_pud++, addr = next, addr != end);
 	return 0;
 }
 
-static inline int copy_p4d_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-		pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma,
-		struct vm_area_struct *new,
-		unsigned long addr, unsigned long end)
+static inline int
+copy_p4d_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
+	       pgd_t *dst_pgd, pgd_t *src_pgd, unsigned long addr,
+	       unsigned long end)
 {
+	struct mm_struct *dst_mm = dst_vma->vm_mm;
 	p4d_t *src_p4d, *dst_p4d;
 	unsigned long next;
 
@@ -1114,20 +1117,22 @@ static inline int copy_p4d_range(struct mm_struct *dst_mm, struct mm_struct *src
 		next = p4d_addr_end(addr, end);
 		if (p4d_none_or_clear_bad(src_p4d))
 			continue;
-		if (copy_pud_range(dst_mm, src_mm, dst_p4d, src_p4d,
-				   vma, new, addr, next))
+		if (copy_pud_range(dst_vma, src_vma, dst_p4d, src_p4d,
+				   addr, next))
 			return -ENOMEM;
 	} while (dst_p4d++, src_p4d++, addr = next, addr != end);
 	return 0;
 }
 
-int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-		    struct vm_area_struct *vma, struct vm_area_struct *new)
+int
+copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
 {
 	pgd_t *src_pgd, *dst_pgd;
 	unsigned long next;
-	unsigned long addr = vma->vm_start;
-	unsigned long end = vma->vm_end;
+	unsigned long addr = src_vma->vm_start;
+	unsigned long end = src_vma->vm_end;
+	struct mm_struct *dst_mm = dst_vma->vm_mm;
+	struct mm_struct *src_mm = src_vma->vm_mm;
 	struct mmu_notifier_range range;
 	bool is_cow;
 	int ret;
@@ -1138,19 +1143,19 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	 * readonly mappings. The tradeoff is that copy_page_range is more
 	 * efficient than faulting.
 	 */
-	if (!(vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP)) &&
-			!vma->anon_vma)
+	if (!(src_vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP)) &&
+	    !src_vma->anon_vma)
 		return 0;
 
-	if (is_vm_hugetlb_page(vma))
-		return copy_hugetlb_page_range(dst_mm, src_mm, vma);
+	if (is_vm_hugetlb_page(src_vma))
+		return copy_hugetlb_page_range(dst_mm, src_mm, src_vma);
 
-	if (unlikely(vma->vm_flags & VM_PFNMAP)) {
+	if (unlikely(src_vma->vm_flags & VM_PFNMAP)) {
 		/*
 		 * We do not free on error cases below as remove_vma
 		 * gets called on error from higher level routine
 		 */
-		ret = track_pfn_copy(vma);
+		ret = track_pfn_copy(src_vma);
 		if (ret)
 			return ret;
 	}
@@ -1161,11 +1166,11 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	 * parent mm. And a permission downgrade will only happen if
 	 * is_cow_mapping() returns true.
 	 */
-	is_cow = is_cow_mapping(vma->vm_flags);
+	is_cow = is_cow_mapping(src_vma->vm_flags);
 
 	if (is_cow) {
 		mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE,
-					0, vma, src_mm, addr, end);
+					0, src_vma, src_mm, addr, end);
 		mmu_notifier_invalidate_range_start(&range);
 	}
 
@@ -1176,8 +1181,8 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(src_pgd))
 			continue;
-		if (unlikely(copy_p4d_range(dst_mm, src_mm, dst_pgd, src_pgd,
-					    vma, new, addr, next))) {
+		if (unlikely(copy_p4d_range(dst_vma, src_vma, dst_pgd, src_pgd,
+					    addr, next))) {
 			ret = -ENOMEM;
 			break;
 		}
-- 
cgit v1.2.3


From f577e143d85aa7ea3d9c62c607ad00fc46a5730c Mon Sep 17 00:00:00 2001
From: yuleixzhang <yulei.kernel@gmail.com>
Date: Tue, 13 Oct 2020 16:54:25 -0700
Subject: include/linux/huge_mm.h: remove mincore_huge_pmd declaration

As mincore_huge_pmd() was dropped, remove the declaration from the header
file.

Signed-off-by: Yulei Zhang <yuleixzhang@tencent.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Link: https://lkml.kernel.org/r/20200922083423.15074-1-yuleixzhang@tencent.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/huge_mm.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 8a8bc46a2432..0365aa97f8e7 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -38,9 +38,6 @@ extern int zap_huge_pmd(struct mmu_gather *tlb,
 extern int zap_huge_pud(struct mmu_gather *tlb,
 			struct vm_area_struct *vma,
 			pud_t *pud, unsigned long addr);
-extern int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
-			unsigned long addr, unsigned long end,
-			unsigned char *vec);
 extern bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 			 unsigned long new_addr,
 			 pmd_t *old_pmd, pmd_t *new_pmd);
-- 
cgit v1.2.3


From 393824f650fabf6ea32bb09bea7acbc3a062dac8 Mon Sep 17 00:00:00 2001
From: Patricia Alfonso <trishalfonso@google.com>
Date: Tue, 13 Oct 2020 16:54:58 -0700
Subject: kasan/kunit: add KUnit Struct to Current Task

Patch series "KASAN-KUnit Integration", v14.

This patchset contains everything needed to integrate KASAN and KUnit.

KUnit will be able to:
(1) Fail tests when an unexpected KASAN error occurs
(2) Pass tests when an expected KASAN error occurs

Convert KASAN tests to KUnit with the exception of copy_user_test because
KUnit is unable to test those.

Add documentation on how to run the KASAN tests with KUnit and what to
expect when running these tests.

This patch (of 5):

In order to integrate debugging tools like KASAN into the KUnit framework,
add KUnit struct to the current task to keep track of the current KUnit
test.

Signed-off-by: Patricia Alfonso <trishalfonso@google.com>
Signed-off-by: David Gow <davidgow@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Reviewed-by: Brendan Higgins <brendanhiggins@google.com>
Cc: Brendan Higgins <brendanhiggins@google.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Shuah Khan <shuah@kernel.org>
Link: https://lkml.kernel.org/r/20200915035828.570483-1-davidgow@google.com
Link: https://lkml.kernel.org/r/20200915035828.570483-2-davidgow@google.com
Link: https://lkml.kernel.org/r/20200910070331.3358048-1-davidgow@google.com
Link: https://lkml.kernel.org/r/20200910070331.3358048-2-davidgow@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/sched.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 829b0697d19c..9030f3abd969 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1208,6 +1208,10 @@ struct task_struct {
 #endif
 #endif
 
+#if IS_ENABLED(CONFIG_KUNIT)
+	struct kunit			*kunit_test;
+#endif
+
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	/* Index of current stored address in ret_stack: */
 	int				curr_ret_stack;
-- 
cgit v1.2.3


From 83c4e7a0363bdb8104f510370907161623e31086 Mon Sep 17 00:00:00 2001
From: Patricia Alfonso <trishalfonso@google.com>
Date: Tue, 13 Oct 2020 16:55:02 -0700
Subject: KUnit: KASAN Integration

Integrate KASAN into KUnit testing framework.

        - Fail tests when KASAN reports an error that is not expected
        - Use KUNIT_EXPECT_KASAN_FAIL to expect a KASAN error in KASAN
	  tests
        - Expected KASAN reports pass tests and are still printed when run
          without kunit_tool (kunit_tool still bypasses the report due to the
          test passing)
	- KUnit struct in current task used to keep track of the current
	  test from KASAN code

Make use of "[PATCH v3 kunit-next 1/2] kunit: generalize kunit_resource
API beyond allocated resources" and "[PATCH v3 kunit-next 2/2] kunit: add
support for named resources" from Alan Maguire [1]

        - A named resource is added to a test when a KASAN report is
          expected
        - This resource contains a struct for kasan_data containing
          booleans representing if a KASAN report is expected and if a
          KASAN report is found

[1] (https://lore.kernel.org/linux-kselftest/1583251361-12748-1-git-send-email-alan.maguire@oracle.com/T/#t)

Signed-off-by: Patricia Alfonso <trishalfonso@google.com>
Signed-off-by: David Gow <davidgow@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Reviewed-by: Andrey Konovalov <andreyknvl@google.com>
Reviewed-by: Dmitry Vyukov <dvyukov@google.com>
Acked-by: Brendan Higgins <brendanhiggins@google.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20200915035828.570483-3-davidgow@google.com
Link: https://lkml.kernel.org/r/20200910070331.3358048-3-davidgow@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/kunit/test.h  |  5 +++++
 include/linux/kasan.h |  6 ++++++
 lib/kunit/test.c      | 13 ++++++++-----
 lib/test_kasan.c      | 47 +++++++++++++++++++++++++++++++++++++++++++++--
 mm/kasan/report.c     | 32 ++++++++++++++++++++++++++++++++
 5 files changed, 96 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/kunit/test.h b/include/kunit/test.h
index 59f3144f009a..3391f38389f8 100644
--- a/include/kunit/test.h
+++ b/include/kunit/test.h
@@ -224,6 +224,11 @@ struct kunit {
 	struct list_head resources; /* Protected by lock. */
 };
 
+static inline void kunit_set_failure(struct kunit *test)
+{
+	WRITE_ONCE(test->success, false);
+}
+
 void kunit_init_test(struct kunit *test, const char *name, char *log);
 
 int kunit_run_tests(struct kunit_suite *suite);
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 087fba34b209..30d343b4a40a 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -14,6 +14,12 @@ struct task_struct;
 #include <linux/pgtable.h>
 #include <asm/kasan.h>
 
+/* kasan_data struct is used in KUnit tests for KASAN expected failures */
+struct kunit_kasan_expectation {
+	bool report_expected;
+	bool report_found;
+};
+
 extern unsigned char kasan_early_shadow_page[PAGE_SIZE];
 extern pte_t kasan_early_shadow_pte[PTRS_PER_PTE];
 extern pmd_t kasan_early_shadow_pmd[PTRS_PER_PMD];
diff --git a/lib/kunit/test.c b/lib/kunit/test.c
index c36037200310..dcc35fd30d95 100644
--- a/lib/kunit/test.c
+++ b/lib/kunit/test.c
@@ -10,16 +10,12 @@
 #include <linux/kernel.h>
 #include <linux/kref.h>
 #include <linux/sched/debug.h>
+#include <linux/sched.h>
 
 #include "debugfs.h"
 #include "string-stream.h"
 #include "try-catch-impl.h"
 
-static void kunit_set_failure(struct kunit *test)
-{
-	WRITE_ONCE(test->success, false);
-}
-
 static void kunit_print_tap_version(void)
 {
 	static bool kunit_has_printed_tap_version;
@@ -288,6 +284,10 @@ static void kunit_try_run_case(void *data)
 	struct kunit_suite *suite = ctx->suite;
 	struct kunit_case *test_case = ctx->test_case;
 
+#if (IS_ENABLED(CONFIG_KASAN) && IS_ENABLED(CONFIG_KUNIT))
+	current->kunit_test = test;
+#endif /* IS_ENABLED(CONFIG_KASAN) && IS_ENABLED(CONFIG_KUNIT) */
+
 	/*
 	 * kunit_run_case_internal may encounter a fatal error; if it does,
 	 * abort will be called, this thread will exit, and finally the parent
@@ -602,6 +602,9 @@ void kunit_cleanup(struct kunit *test)
 		spin_unlock(&test->lock);
 		kunit_remove_resource(test, res);
 	}
+#if (IS_ENABLED(CONFIG_KASAN) && IS_ENABLED(CONFIG_KUNIT))
+	current->kunit_test = NULL;
+#endif /* IS_ENABLED(CONFIG_KASAN) && IS_ENABLED(CONFIG_KUNIT)*/
 }
 EXPORT_SYMBOL_GPL(kunit_cleanup);
 
diff --git a/lib/test_kasan.c b/lib/test_kasan.c
index 53e953bb1d1d..58bffadd8367 100644
--- a/lib/test_kasan.c
+++ b/lib/test_kasan.c
@@ -23,6 +23,8 @@
 
 #include <asm/page.h>
 
+#include <kunit/test.h>
+
 #include "../mm/kasan/kasan.h"
 
 #define OOB_TAG_OFF (IS_ENABLED(CONFIG_KASAN_GENERIC) ? 0 : KASAN_SHADOW_SCALE_SIZE)
@@ -32,14 +34,55 @@
  * are not eliminated as dead code.
  */
 
-int kasan_int_result;
 void *kasan_ptr_result;
+int kasan_int_result;
+
+static struct kunit_resource resource;
+static struct kunit_kasan_expectation fail_data;
+static bool multishot;
+
+static int kasan_test_init(struct kunit *test)
+{
+	/*
+	 * Temporarily enable multi-shot mode and set panic_on_warn=0.
+	 * Otherwise, we'd only get a report for the first case.
+	 */
+	multishot = kasan_save_enable_multi_shot();
+
+	return 0;
+}
+
+static void kasan_test_exit(struct kunit *test)
+{
+	kasan_restore_multi_shot(multishot);
+}
+
+/**
+ * KUNIT_EXPECT_KASAN_FAIL() - Causes a test failure when the expression does
+ * not cause a KASAN error. This uses a KUnit resource named "kasan_data." Do
+ * Do not use this name for a KUnit resource outside here.
+ *
+ */
+#define KUNIT_EXPECT_KASAN_FAIL(test, condition) do { \
+	fail_data.report_expected = true; \
+	fail_data.report_found = false; \
+	kunit_add_named_resource(test, \
+				NULL, \
+				NULL, \
+				&resource, \
+				"kasan_data", &fail_data); \
+	condition; \
+	KUNIT_EXPECT_EQ(test, \
+			fail_data.report_expected, \
+			fail_data.report_found); \
+} while (0)
+
+
 
 /*
  * Note: test functions are marked noinline so that their names appear in
  * reports.
  */
-
 static noinline void __init kmalloc_oob_right(void)
 {
 	char *ptr;
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index 4f49fa6cd1aa..e2c14b10bc81 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -33,6 +33,8 @@
 
 #include <asm/sections.h>
 
+#include <kunit/test.h>
+
 #include "kasan.h"
 #include "../slab.h"
 
@@ -464,12 +466,37 @@ static bool report_enabled(void)
 	return !test_and_set_bit(KASAN_BIT_REPORTED, &kasan_flags);
 }
 
+#if IS_ENABLED(CONFIG_KUNIT)
+static void kasan_update_kunit_status(struct kunit *cur_test)
+{
+	struct kunit_resource *resource;
+	struct kunit_kasan_expectation *kasan_data;
+
+	resource = kunit_find_named_resource(cur_test, "kasan_data");
+
+	if (!resource) {
+		kunit_set_failure(cur_test);
+		return;
+	}
+
+	kasan_data = (struct kunit_kasan_expectation *)resource->data;
+	kasan_data->report_found = true;
+	kunit_put_resource(resource);
+}
+#endif /* IS_ENABLED(CONFIG_KUNIT) */
+
 void kasan_report_invalid_free(void *object, unsigned long ip)
 {
 	unsigned long flags;
 	u8 tag = get_tag(object);
 
 	object = reset_tag(object);
+
+#if IS_ENABLED(CONFIG_KUNIT)
+	if (current->kunit_test)
+		kasan_update_kunit_status(current->kunit_test);
+#endif /* IS_ENABLED(CONFIG_KUNIT) */
+
 	start_report(&flags);
 	pr_err("BUG: KASAN: double-free or invalid-free in %pS\n", (void *)ip);
 	print_tags(tag, object);
@@ -488,6 +515,11 @@ static void __kasan_report(unsigned long addr, size_t size, bool is_write,
 	void *untagged_addr;
 	unsigned long flags;
 
+#if IS_ENABLED(CONFIG_KUNIT)
+	if (current->kunit_test)
+		kasan_update_kunit_status(current->kunit_test);
+#endif /* IS_ENABLED(CONFIG_KUNIT) */
+
 	disable_trace_on_warning();
 
 	tagged_addr = (void *)addr;
-- 
cgit v1.2.3


From 9181a980625a45425085ccec0fc38074a16470a5 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Tue, 13 Oct 2020 16:55:35 -0700
Subject: mm: document semantics of ZONE_MOVABLE

Let's document what ZONE_MOVABLE means, how it's used, and which special
cases we have regarding unmovable pages (memory offlining vs.  migration /
allocations).

Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Mike Rapoport <rppt@linux.ibm.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Qian Cai <cai@lca.pw>
Link: http://lkml.kernel.org/r/20200816125333.7434-7-david@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmzone.h | 35 +++++++++++++++++++++++++++++++++++
 1 file changed, 35 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 0f7a4ff4b059..927bd7e98a88 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -396,6 +396,41 @@ enum zone_type {
 	 */
 	ZONE_HIGHMEM,
 #endif
+	/*
+	 * ZONE_MOVABLE is similar to ZONE_NORMAL, except that it contains
+	 * movable pages with few exceptional cases described below. Main use
+	 * cases for ZONE_MOVABLE are to make memory offlining/unplug more
+	 * likely to succeed, and to locally limit unmovable allocations - e.g.,
+	 * to increase the number of THP/huge pages. Notable special cases are:
+	 *
+	 * 1. Pinned pages: (long-term) pinning of movable pages might
+	 *    essentially turn such pages unmovable. Memory offlining might
+	 *    retry a long time.
+	 * 2. memblock allocations: kernelcore/movablecore setups might create
+	 *    situations where ZONE_MOVABLE contains unmovable allocations
+	 *    after boot. Memory offlining and allocations fail early.
+	 * 3. Memory holes: kernelcore/movablecore setups might create very rare
+	 *    situations where ZONE_MOVABLE contains memory holes after boot,
+	 *    for example, if we have sections that are only partially
+	 *    populated. Memory offlining and allocations fail early.
+	 * 4. PG_hwpoison pages: while poisoned pages can be skipped during
+	 *    memory offlining, such pages cannot be allocated.
+	 * 5. Unmovable PG_offline pages: in paravirtualized environments,
+	 *    hotplugged memory blocks might only partially be managed by the
+	 *    buddy (e.g., via XEN-balloon, Hyper-V balloon, virtio-mem). The
+	 *    parts not manged by the buddy are unmovable PG_offline pages. In
+	 *    some cases (virtio-mem), such pages can be skipped during
+	 *    memory offlining, however, cannot be moved/allocated. These
+	 *    techniques might use alloc_contig_range() to hide previously
+	 *    exposed pages from the buddy again (e.g., to implement some sort
+	 *    of memory unplug in virtio-mem).
+	 *
+	 * In general, no unmovable allocations that degrade memory offlining
+	 * should end up in ZONE_MOVABLE. Allocators (like alloc_contig_range())
+	 * have to expect that migrating pages in ZONE_MOVABLE can fail (even
+	 * if has_unmovable_pages() states that there are no unmovable pages,
+	 * there can be false negatives).
+	 */
 	ZONE_MOVABLE,
 #ifdef CONFIG_ZONE_DEVICE
 	ZONE_DEVICE,
-- 
cgit v1.2.3


From 30d8ec73e8772b32a7eae626d14004bd37d8f13c Mon Sep 17 00:00:00 2001
From: Mateusz Nosek <mateusznosek0@gmail.com>
Date: Tue, 13 Oct 2020 16:55:57 -0700
Subject: mmzone: clean code by removing unused macro parameter

Previously 'for_next_zone_zonelist_nodemask' macro parameter 'zlist' was
unused so this patch removes it.

Signed-off-by: Mateusz Nosek <mateusznosek0@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Link: https://lkml.kernel.org/r/20200917211906.30059-1-mateusznosek0@gmail.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmzone.h | 2 +-
 mm/page_alloc.c        | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 927bd7e98a88..c27fb1faffe5 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1116,7 +1116,7 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist,
 		z = next_zones_zonelist(++z, highidx, nodemask),	\
 			zone = zonelist_zone(z))
 
-#define for_next_zone_zonelist_nodemask(zone, z, zlist, highidx, nodemask) \
+#define for_next_zone_zonelist_nodemask(zone, z, highidx, nodemask) \
 	for (zone = z->zone;	\
 		zone;							\
 		z = next_zones_zonelist(++z, highidx, nodemask),	\
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a105c657be37..6263a97e39c6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3741,8 +3741,8 @@ retry:
 	 */
 	no_fallback = alloc_flags & ALLOC_NOFRAGMENT;
 	z = ac->preferred_zoneref;
-	for_next_zone_zonelist_nodemask(zone, z, ac->zonelist,
-					ac->highest_zoneidx, ac->nodemask) {
+	for_next_zone_zonelist_nodemask(zone, z, ac->highest_zoneidx,
+					ac->nodemask) {
 		struct page *page;
 		unsigned long mark;
 
-- 
cgit v1.2.3


From ab00db216c9c78cc0a68bc4e27889c1ee374598d Mon Sep 17 00:00:00 2001
From: Michal Hocko <mhocko@suse.com>
Date: Tue, 13 Oct 2020 16:56:07 -0700
Subject: include/linux/gfp.h: clarify usage of GFP_ATOMIC in !preemptible
 contexts

There is a general understanding that GFP_ATOMIC/GFP_NOWAIT are to be used
from atomic contexts.  E.g.  from within a spin lock or from the IRQ
context.  This is correct but there are some atomic contexts where the
above doesn't hold.  One of them would be an NMI context.  Page allocator
has never supported that and the general fear of this context didn't let
anybody to actually even try to use the allocator there.  Good, but let's
be more specific about that.

Another such a context, and that is where people seem to be more daring,
is raw_spin_lock.  Mostly because it simply resembles regular spin lock
which is supported by the allocator and there is not any implementation
difference with !RT kernels in the first place.  Be explicit that such a
context is not supported by the allocator.  The underlying reason is that
zone->lock would have to become raw_spin_lock as well and that has turned
out to be a problem for RT
(http://lkml.kernel.org/r/87mu305c1w.fsf@nanos.tec.linutronix.de).

Signed-off-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Uladzislau Rezki <urezki@gmail.com>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Link: https://lkml.kernel.org/r/20200929123010.5137-1-mhocko@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/gfp.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 67a0774e080b..2e8370cf60c7 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -238,7 +238,9 @@ struct vm_area_struct;
  * %__GFP_FOO flags as necessary.
  *
  * %GFP_ATOMIC users can not sleep and need the allocation to succeed. A lower
- * watermark is applied to allow access to "atomic reserves"
+ * watermark is applied to allow access to "atomic reserves".
+ * The current implementation doesn't support NMI and few other strict
+ * non-preemptive contexts (e.g. raw_spin_lock). The same applies to %GFP_NOWAIT.
  *
  * %GFP_KERNEL is typical for kernel-internal allocations. The caller requires
  * %ZONE_NORMAL or a lower zone for direct access but can direct reclaim.
-- 
cgit v1.2.3


From 74c9da4e1dc0ecf70e7fa78568821e3ed8f77938 Mon Sep 17 00:00:00 2001
From: Mateusz Nosek <mateusznosek0@gmail.com>
Date: Tue, 13 Oct 2020 16:57:01 -0700
Subject: include/linux/compaction.h: clean code by removing unused enum value

The enum value 'COMPACT_INACTIVE' is never used so can be removed.

Signed-off-by: Mateusz Nosek <mateusznosek0@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Link: https://lkml.kernel.org/r/20200917110750.12015-1-mateusznosek0@gmail.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/compaction.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 25a521d299c1..1de5a1151ee7 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -29,9 +29,6 @@ enum compact_result {
 	/* compaction didn't start as it was deferred due to past failures */
 	COMPACT_DEFERRED,
 
-	/* compaction not active last round */
-	COMPACT_INACTIVE = COMPACT_DEFERRED,
-
 	/* For more detailed tracepoint output - internal to compaction */
 	COMPACT_NO_SUITABLE_PAGE,
 	/* compaction should continue to another pageblock */
-- 
cgit v1.2.3


From f8fd52535c7326d72645c9878d7897aaf44db51c Mon Sep 17 00:00:00 2001
From: Wei Yang <richard.weiyang@linux.alibaba.com>
Date: Tue, 13 Oct 2020 16:57:11 -0700
Subject: mm: remove unused alloc_page_vma_node()

No one use this macro anymore.

Also fix code style of policy_node().

Signed-off-by: Wei Yang <richard.weiyang@linux.alibaba.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Link: https://lkml.kernel.org/r/20200921021401.84508-1-richard.weiyang@linux.alibaba.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/gfp.h | 2 --
 mm/mempolicy.c      | 3 +--
 2 files changed, 1 insertion(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 2e8370cf60c7..07e481993ef5 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -562,8 +562,6 @@ extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order,
 #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0)
 #define alloc_page_vma(gfp_mask, vma, addr)			\
 	alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false)
-#define alloc_page_vma_node(gfp_mask, vma, addr, node)		\
-	alloc_pages_vma(gfp_mask, 0, vma, addr, node, false)
 
 extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order);
 extern unsigned long get_zeroed_page(gfp_t gfp_mask);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 69ce708c3a3a..3fde772ef5ef 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1882,8 +1882,7 @@ nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy)
 }
 
 /* Return the node id preferred by the given mempolicy, or the given id */
-static int policy_node(gfp_t gfp, struct mempolicy *policy,
-								int nd)
+static int policy_node(gfp_t gfp, struct mempolicy *policy, int nd)
 {
 	if (policy->mode == MPOL_PREFERRED && !(policy->flags & MPOL_F_LOCAL))
 		nd = policy->v.preferred_node;
-- 
cgit v1.2.3


From cd991db8ddc33d2d2c7af45627fc48352915001c Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.ibm.com>
Date: Tue, 13 Oct 2020 16:57:49 -0700
Subject: memblock: make for_each_memblock_type() iterator private

for_each_memblock_type() is not used outside mm/memblock.c, move it there
from include/linux/memblock.h

Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Baoquan He <bhe@redhat.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Daniel Axtens <dja@axtens.net>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Emil Renner Berthing <kernel@esmil.dk>
Cc: Hari Bathini <hbathini@linux.ibm.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Stafford Horne <shorne@gmail.com>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Link: https://lkml.kernel.org/r/20200818151634.14343-9-rppt@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memblock.h | 5 -----
 mm/memblock.c            | 5 +++++
 2 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 9d925db0d355..550faf69fc1c 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -552,11 +552,6 @@ static inline unsigned long memblock_region_reserved_end_pfn(const struct memblo
 	     region < (memblock.memblock_type.regions + memblock.memblock_type.cnt);	\
 	     region++)
 
-#define for_each_memblock_type(i, memblock_type, rgn)			\
-	for (i = 0, rgn = &memblock_type->regions[0];			\
-	     i < memblock_type->cnt;					\
-	     i++, rgn = &memblock_type->regions[i])
-
 extern void *alloc_large_system_hash(const char *tablename,
 				     unsigned long bucketsize,
 				     unsigned long numentries,
diff --git a/mm/memblock.c b/mm/memblock.c
index 45f198750be9..59f3998ae5db 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -132,6 +132,11 @@ struct memblock_type physmem = {
 };
 #endif
 
+#define for_each_memblock_type(i, memblock_type, rgn)			\
+	for (i = 0, rgn = &memblock_type->regions[0];			\
+	     i < memblock_type->cnt;					\
+	     i++, rgn = &memblock_type->regions[i])
+
 int memblock_debug __initdata_memblock;
 static bool system_has_some_mirror __initdata_memblock = false;
 static int memblock_can_resize __initdata_memblock;
-- 
cgit v1.2.3


From 87c55870f01266fe22f345a0767162f85f1cf8f1 Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.ibm.com>
Date: Tue, 13 Oct 2020 16:57:54 -0700
Subject: memblock: make memblock_debug and related functionality private

The only user of memblock_dbg() outside memblock was s390 setup code and
it is converted to use pr_debug() instead.  This allows to stop exposing
memblock_debug and memblock_dbg() to the rest of the kernel.

[akpm@linux-foundation.org: make memblock_dbg() safer and neater]

Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Baoquan He <bhe@redhat.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Daniel Axtens <dja@axtens.net>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Emil Renner Berthing <kernel@esmil.dk>
Cc: Hari Bathini <hbathini@linux.ibm.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Stafford Horne <shorne@gmail.com>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Link: https://lkml.kernel.org/r/20200818151634.14343-10-rppt@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/s390/kernel/setup.c |  4 ++--
 include/linux/memblock.h | 12 +-----------
 mm/memblock.c            | 16 ++++++++++++++--
 3 files changed, 17 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index c2c1b4e723ea..115c92839af5 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -776,8 +776,8 @@ static void __init memblock_add_mem_detect_info(void)
 	unsigned long start, end;
 	int i;
 
-	memblock_dbg("physmem info source: %s (%hhd)\n",
-		     get_mem_info_source(), mem_detect.info_source);
+	pr_debug("physmem info source: %s (%hhd)\n",
+		 get_mem_info_source(), mem_detect.info_source);
 	/* keep memblock lists close to the kernel */
 	memblock_set_bottom_up(true);
 	for_each_mem_detect_block(i, &start, &end) {
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 550faf69fc1c..47a76e237fca 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -86,7 +86,6 @@ struct memblock {
 };
 
 extern struct memblock memblock;
-extern int memblock_debug;
 
 #ifndef CONFIG_ARCH_KEEP_MEMBLOCK
 #define __init_memblock __meminit
@@ -98,9 +97,6 @@ void memblock_discard(void);
 static inline void memblock_discard(void) {}
 #endif
 
-#define memblock_dbg(fmt, ...) \
-	if (memblock_debug) printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__)
-
 phys_addr_t memblock_find_in_range(phys_addr_t start, phys_addr_t end,
 				   phys_addr_t size, phys_addr_t align);
 void memblock_allow_resize(void);
@@ -476,13 +472,7 @@ bool memblock_is_region_memory(phys_addr_t base, phys_addr_t size);
 bool memblock_is_reserved(phys_addr_t addr);
 bool memblock_is_region_reserved(phys_addr_t base, phys_addr_t size);
 
-extern void __memblock_dump_all(void);
-
-static inline void memblock_dump_all(void)
-{
-	if (memblock_debug)
-		__memblock_dump_all();
-}
+void memblock_dump_all(void);
 
 /**
  * memblock_set_current_limit - Set the current allocation limit to allow
diff --git a/mm/memblock.c b/mm/memblock.c
index 59f3998ae5db..e9b6efd74329 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -137,7 +137,13 @@ struct memblock_type physmem = {
 	     i < memblock_type->cnt;					\
 	     i++, rgn = &memblock_type->regions[i])
 
-int memblock_debug __initdata_memblock;
+#define memblock_dbg(fmt, ...)						\
+	do {								\
+		if (memblock_debug)					\
+			pr_info(fmt, ##__VA_ARGS__);			\
+	} while (0)
+
+static int memblock_debug __initdata_memblock;
 static bool system_has_some_mirror __initdata_memblock = false;
 static int memblock_can_resize __initdata_memblock;
 static int memblock_memory_in_slab __initdata_memblock = 0;
@@ -1920,7 +1926,7 @@ static void __init_memblock memblock_dump(struct memblock_type *type)
 	}
 }
 
-void __init_memblock __memblock_dump_all(void)
+static void __init_memblock __memblock_dump_all(void)
 {
 	pr_info("MEMBLOCK configuration:\n");
 	pr_info(" memory size = %pa reserved size = %pa\n",
@@ -1934,6 +1940,12 @@ void __init_memblock __memblock_dump_all(void)
 #endif
 }
 
+void __init_memblock memblock_dump_all(void)
+{
+	if (memblock_debug)
+		__memblock_dump_all();
+}
+
 void __init memblock_allow_resize(void)
 {
 	memblock_can_resize = 1;
-- 
cgit v1.2.3


From 6e245ad4a17ab92dba63406d3f517520a86c0a80 Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.ibm.com>
Date: Tue, 13 Oct 2020 16:57:59 -0700
Subject: memblock: reduce number of parameters in for_each_mem_range()

Currently for_each_mem_range() and for_each_mem_range_rev() iterators are
the most generic way to traverse memblock regions.  As such, they have 8
parameters and they are hardly convenient to users.  Most users choose to
utilize one of their wrappers and the only user that actually needs most
of the parameters is memblock itself.

To avoid yet another naming for memblock iterators, rename the existing
for_each_mem_range[_rev]() to __for_each_mem_range[_rev]() and add a new
for_each_mem_range[_rev]() wrappers with only index, start and end
parameters.

The new wrapper nicely fits into init_unavailable_mem() and will be used
in upcoming changes to simplify memblock traversals.

Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>	[MIPS]
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Baoquan He <bhe@redhat.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Daniel Axtens <dja@axtens.net>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Emil Renner Berthing <kernel@esmil.dk>
Cc: Hari Bathini <hbathini@linux.ibm.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Stafford Horne <shorne@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Link: https://lkml.kernel.org/r/20200818151634.14343-11-rppt@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 .clang-format                          |  2 ++
 arch/arm64/kernel/machine_kexec_file.c |  6 ++---
 arch/powerpc/kexec/file_load_64.c      |  6 ++---
 include/linux/memblock.h               | 41 +++++++++++++++++++++++++---------
 mm/page_alloc.c                        |  3 +--
 5 files changed, 38 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/.clang-format b/.clang-format
index badfc1ba440a..0366a3d2e561 100644
--- a/.clang-format
+++ b/.clang-format
@@ -207,7 +207,9 @@ ForEachMacros:
   - 'for_each_memblock_type'
   - 'for_each_memcg_cache_index'
   - 'for_each_mem_pfn_range'
+  - '__for_each_mem_range'
   - 'for_each_mem_range'
+  - '__for_each_mem_range_rev'
   - 'for_each_mem_range_rev'
   - 'for_each_migratetype_order'
   - 'for_each_msi_entry'
diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c
index 361a1143e09e..5b0e67b93cdc 100644
--- a/arch/arm64/kernel/machine_kexec_file.c
+++ b/arch/arm64/kernel/machine_kexec_file.c
@@ -215,8 +215,7 @@ static int prepare_elf_headers(void **addr, unsigned long *sz)
 	phys_addr_t start, end;
 
 	nr_ranges = 1; /* for exclusion of crashkernel region */
-	for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE,
-					MEMBLOCK_NONE, &start, &end, NULL)
+	for_each_mem_range(i, &start, &end)
 		nr_ranges++;
 
 	cmem = kmalloc(struct_size(cmem, ranges, nr_ranges), GFP_KERNEL);
@@ -225,8 +224,7 @@ static int prepare_elf_headers(void **addr, unsigned long *sz)
 
 	cmem->max_nr_ranges = nr_ranges;
 	cmem->nr_ranges = 0;
-	for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE,
-					MEMBLOCK_NONE, &start, &end, NULL) {
+	for_each_mem_range(i, &start, &end) {
 		cmem->ranges[cmem->nr_ranges].start = start;
 		cmem->ranges[cmem->nr_ranges].end = end - 1;
 		cmem->nr_ranges++;
diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c
index 53bb71e3a2e1..2c9d908eab96 100644
--- a/arch/powerpc/kexec/file_load_64.c
+++ b/arch/powerpc/kexec/file_load_64.c
@@ -250,8 +250,7 @@ static int __locate_mem_hole_top_down(struct kexec_buf *kbuf,
 	phys_addr_t start, end;
 	u64 i;
 
-	for_each_mem_range_rev(i, &memblock.memory, NULL, NUMA_NO_NODE,
-			       MEMBLOCK_NONE, &start, &end, NULL) {
+	for_each_mem_range_rev(i, &start, &end) {
 		/*
 		 * memblock uses [start, end) convention while it is
 		 * [start, end] here. Fix the off-by-one to have the
@@ -350,8 +349,7 @@ static int __locate_mem_hole_bottom_up(struct kexec_buf *kbuf,
 	phys_addr_t start, end;
 	u64 i;
 
-	for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE,
-			   MEMBLOCK_NONE, &start, &end, NULL) {
+	for_each_mem_range(i, &start, &end) {
 		/*
 		 * memblock uses [start, end) convention while it is
 		 * [start, end] here. Fix the off-by-one to have the
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 47a76e237fca..27c3b84d1615 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -162,7 +162,7 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type,
 #endif /* CONFIG_HAVE_MEMBLOCK_PHYS_MAP */
 
 /**
- * for_each_mem_range - iterate through memblock areas from type_a and not
+ * __for_each_mem_range - iterate through memblock areas from type_a and not
  * included in type_b. Or just type_a if type_b is NULL.
  * @i: u64 used as loop variable
  * @type_a: ptr to memblock_type to iterate
@@ -173,7 +173,7 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type,
  * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
  * @p_nid: ptr to int for nid of the range, can be %NULL
  */
-#define for_each_mem_range(i, type_a, type_b, nid, flags,		\
+#define __for_each_mem_range(i, type_a, type_b, nid, flags,		\
 			   p_start, p_end, p_nid)			\
 	for (i = 0, __next_mem_range(&i, nid, flags, type_a, type_b,	\
 				     p_start, p_end, p_nid);		\
@@ -182,7 +182,7 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type,
 			      p_start, p_end, p_nid))
 
 /**
- * for_each_mem_range_rev - reverse iterate through memblock areas from
+ * __for_each_mem_range_rev - reverse iterate through memblock areas from
  * type_a and not included in type_b. Or just type_a if type_b is NULL.
  * @i: u64 used as loop variable
  * @type_a: ptr to memblock_type to iterate
@@ -193,15 +193,36 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type,
  * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
  * @p_nid: ptr to int for nid of the range, can be %NULL
  */
-#define for_each_mem_range_rev(i, type_a, type_b, nid, flags,		\
-			       p_start, p_end, p_nid)			\
+#define __for_each_mem_range_rev(i, type_a, type_b, nid, flags,		\
+				 p_start, p_end, p_nid)			\
 	for (i = (u64)ULLONG_MAX,					\
-		     __next_mem_range_rev(&i, nid, flags, type_a, type_b,\
+		     __next_mem_range_rev(&i, nid, flags, type_a, type_b, \
 					  p_start, p_end, p_nid);	\
 	     i != (u64)ULLONG_MAX;					\
 	     __next_mem_range_rev(&i, nid, flags, type_a, type_b,	\
 				  p_start, p_end, p_nid))
 
+/**
+ * for_each_mem_range - iterate through memory areas.
+ * @i: u64 used as loop variable
+ * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
+ * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
+ */
+#define for_each_mem_range(i, p_start, p_end) \
+	__for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE,	\
+			     MEMBLOCK_NONE, p_start, p_end, NULL)
+
+/**
+ * for_each_mem_range_rev - reverse iterate through memblock areas from
+ * type_a and not included in type_b. Or just type_a if type_b is NULL.
+ * @i: u64 used as loop variable
+ * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
+ * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
+ */
+#define for_each_mem_range_rev(i, p_start, p_end)			\
+	__for_each_mem_range_rev(i, &memblock.memory, NULL, NUMA_NO_NODE, \
+				 MEMBLOCK_NONE, p_start, p_end, NULL)
+
 /**
  * for_each_reserved_mem_region - iterate over all reserved memblock areas
  * @i: u64 used as loop variable
@@ -307,8 +328,8 @@ int __init deferred_page_init_max_threads(const struct cpumask *node_cpumask);
  * soon as memblock is initialized.
  */
 #define for_each_free_mem_range(i, nid, flags, p_start, p_end, p_nid)	\
-	for_each_mem_range(i, &memblock.memory, &memblock.reserved,	\
-			   nid, flags, p_start, p_end, p_nid)
+	__for_each_mem_range(i, &memblock.memory, &memblock.reserved,	\
+			     nid, flags, p_start, p_end, p_nid)
 
 /**
  * for_each_free_mem_range_reverse - rev-iterate through free memblock areas
@@ -324,8 +345,8 @@ int __init deferred_page_init_max_threads(const struct cpumask *node_cpumask);
  */
 #define for_each_free_mem_range_reverse(i, nid, flags, p_start, p_end,	\
 					p_nid)				\
-	for_each_mem_range_rev(i, &memblock.memory, &memblock.reserved,	\
-			       nid, flags, p_start, p_end, p_nid)
+	__for_each_mem_range_rev(i, &memblock.memory, &memblock.reserved, \
+				 nid, flags, p_start, p_end, p_nid)
 
 int memblock_set_node(phys_addr_t base, phys_addr_t size,
 		      struct memblock_type *type, int nid);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 73e33ab6d249..34ac7127d1e6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6990,8 +6990,7 @@ static void __init init_unavailable_mem(void)
 	 * Loop through unavailable ranges not covered by memblock.memory.
 	 */
 	pgcnt = 0;
-	for_each_mem_range(i, &memblock.memory, NULL,
-			NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, NULL) {
+	for_each_mem_range(i, &start, &end) {
 		if (next < start)
 			pgcnt += init_unavailable_range(PFN_DOWN(next),
 							PFN_UP(start));
-- 
cgit v1.2.3


From 5bd0960b85d7e3e4a2dc5bbf1c87d0b505115d71 Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.ibm.com>
Date: Tue, 13 Oct 2020 16:58:20 -0700
Subject: memblock: remove unused memblock_mem_size()

The only user of memblock_mem_size() was x86 setup code, it is gone now
and memblock_mem_size() funciton can be removed.

Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Baoquan He <bhe@redhat.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Daniel Axtens <dja@axtens.net>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Emil Renner Berthing <kernel@esmil.dk>
Cc: Hari Bathini <hbathini@linux.ibm.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Stafford Horne <shorne@gmail.com>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Link: https://lkml.kernel.org/r/20200818151634.14343-16-rppt@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memblock.h |  1 -
 mm/memblock.c            | 15 ---------------
 2 files changed, 16 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 27c3b84d1615..15ed119701c1 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -481,7 +481,6 @@ static inline bool memblock_bottom_up(void)
 
 phys_addr_t memblock_phys_mem_size(void);
 phys_addr_t memblock_reserved_size(void);
-phys_addr_t memblock_mem_size(unsigned long limit_pfn);
 phys_addr_t memblock_start_of_DRAM(void);
 phys_addr_t memblock_end_of_DRAM(void);
 void memblock_enforce_memory_limit(phys_addr_t memory_limit);
diff --git a/mm/memblock.c b/mm/memblock.c
index d66d805dec96..4de76cf48434 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1660,21 +1660,6 @@ phys_addr_t __init_memblock memblock_reserved_size(void)
 	return memblock.reserved.total_size;
 }
 
-phys_addr_t __init memblock_mem_size(unsigned long limit_pfn)
-{
-	unsigned long pages = 0;
-	unsigned long start_pfn, end_pfn;
-	int i;
-
-	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) {
-		start_pfn = min_t(unsigned long, start_pfn, limit_pfn);
-		end_pfn = min_t(unsigned long, end_pfn, limit_pfn);
-		pages += end_pfn - start_pfn;
-	}
-
-	return PFN_PHYS(pages);
-}
-
 /* lowest address */
 phys_addr_t __init_memblock memblock_start_of_DRAM(void)
 {
-- 
cgit v1.2.3


From 9f3d5eaa3c60f95d9fff1ce4eea7553a3dc04906 Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.ibm.com>
Date: Tue, 13 Oct 2020 16:58:25 -0700
Subject: memblock: implement for_each_reserved_mem_region() using
 __next_mem_region()

Iteration over memblock.reserved with for_each_reserved_mem_region() used
__next_reserved_mem_region() that implemented a subset of
__next_mem_region().

Use __for_each_mem_range() and, essentially, __next_mem_region() with
appropriate parameters to reduce code duplication.

While on it, rename for_each_reserved_mem_region() to
for_each_reserved_mem_range() for consistency.

Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>	[.clang-format]
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Baoquan He <bhe@redhat.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Daniel Axtens <dja@axtens.net>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Emil Renner Berthing <kernel@esmil.dk>
Cc: Hari Bathini <hbathini@linux.ibm.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Stafford Horne <shorne@gmail.com>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Link: https://lkml.kernel.org/r/20200818151634.14343-17-rppt@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 .clang-format                    |  2 +-
 arch/arm64/kernel/setup.c        |  2 +-
 drivers/irqchip/irq-gic-v3-its.c |  2 +-
 include/linux/memblock.h         | 12 +++------
 mm/memblock.c                    | 56 ++++++++++++++--------------------------
 5 files changed, 27 insertions(+), 47 deletions(-)

(limited to 'include/linux')

diff --git a/.clang-format b/.clang-format
index 0366a3d2e561..8806bb21b6c2 100644
--- a/.clang-format
+++ b/.clang-format
@@ -273,7 +273,7 @@ ForEachMacros:
   - 'for_each_registered_fb'
   - 'for_each_requested_gpio'
   - 'for_each_requested_gpio_in_range'
-  - 'for_each_reserved_mem_region'
+  - 'for_each_reserved_mem_range'
   - 'for_each_rtd_codec_dais'
   - 'for_each_rtd_codec_dais_rollback'
   - 'for_each_rtd_components'
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 53acbeca4f57..16aae43badfd 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -257,7 +257,7 @@ static int __init reserve_memblock_reserved_regions(void)
 		if (!memblock_is_region_reserved(mem->start, mem_size))
 			continue;
 
-		for_each_reserved_mem_region(j, &r_start, &r_end) {
+		for_each_reserved_mem_range(j, &r_start, &r_end) {
 			resource_size_t start, end;
 
 			start = max(PFN_PHYS(PFN_DOWN(r_start)), mem->start);
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 0418071a3724..46d885575601 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -2198,7 +2198,7 @@ static bool gic_check_reserved_range(phys_addr_t addr, unsigned long size)
 
 	addr_end = addr + size - 1;
 
-	for_each_reserved_mem_region(i, &start, &end) {
+	for_each_reserved_mem_range(i, &start, &end) {
 		if (addr >= start && addr_end <= end)
 			return true;
 	}
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 15ed119701c1..354078713cd1 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -132,9 +132,6 @@ void __next_mem_range_rev(u64 *idx, int nid, enum memblock_flags flags,
 			  struct memblock_type *type_b, phys_addr_t *out_start,
 			  phys_addr_t *out_end, int *out_nid);
 
-void __next_reserved_mem_region(u64 *idx, phys_addr_t *out_start,
-				phys_addr_t *out_end);
-
 void __memblock_free_late(phys_addr_t base, phys_addr_t size);
 
 #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
@@ -224,7 +221,7 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type,
 				 MEMBLOCK_NONE, p_start, p_end, NULL)
 
 /**
- * for_each_reserved_mem_region - iterate over all reserved memblock areas
+ * for_each_reserved_mem_range - iterate over all reserved memblock areas
  * @i: u64 used as loop variable
  * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
  * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
@@ -232,10 +229,9 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type,
  * Walks over reserved areas of memblock. Available as soon as memblock
  * is initialized.
  */
-#define for_each_reserved_mem_region(i, p_start, p_end)			\
-	for (i = 0UL, __next_reserved_mem_region(&i, p_start, p_end);	\
-	     i != (u64)ULLONG_MAX;					\
-	     __next_reserved_mem_region(&i, p_start, p_end))
+#define for_each_reserved_mem_range(i, p_start, p_end)			\
+	__for_each_mem_range(i, &memblock.reserved, NULL, NUMA_NO_NODE,	\
+			     MEMBLOCK_NONE, p_start, p_end, NULL)
 
 static inline bool memblock_is_hotpluggable(struct memblock_region *m)
 {
diff --git a/mm/memblock.c b/mm/memblock.c
index 4de76cf48434..a09cc4f057f0 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -132,6 +132,14 @@ struct memblock_type physmem = {
 };
 #endif
 
+/*
+ * keep a pointer to &memblock.memory in the text section to use it in
+ * __next_mem_range() and its helpers.
+ *  For architectures that do not keep memblock data after init, this
+ * pointer will be reset to NULL at memblock_discard()
+ */
+static __refdata struct memblock_type *memblock_memory = &memblock.memory;
+
 #define for_each_memblock_type(i, memblock_type, rgn)			\
 	for (i = 0, rgn = &memblock_type->regions[0];			\
 	     i < memblock_type->cnt;					\
@@ -402,6 +410,8 @@ void __init memblock_discard(void)
 				  memblock.memory.max);
 		__memblock_free_late(addr, size);
 	}
+
+	memblock_memory = NULL;
 }
 #endif
 
@@ -952,42 +962,16 @@ int __init_memblock memblock_clear_nomap(phys_addr_t base, phys_addr_t size)
 	return memblock_setclr_flag(base, size, 0, MEMBLOCK_NOMAP);
 }
 
-/**
- * __next_reserved_mem_region - next function for for_each_reserved_region()
- * @idx: pointer to u64 loop variable
- * @out_start: ptr to phys_addr_t for start address of the region, can be %NULL
- * @out_end: ptr to phys_addr_t for end address of the region, can be %NULL
- *
- * Iterate over all reserved memory regions.
- */
-void __init_memblock __next_reserved_mem_region(u64 *idx,
-					   phys_addr_t *out_start,
-					   phys_addr_t *out_end)
-{
-	struct memblock_type *type = &memblock.reserved;
-
-	if (*idx < type->cnt) {
-		struct memblock_region *r = &type->regions[*idx];
-		phys_addr_t base = r->base;
-		phys_addr_t size = r->size;
-
-		if (out_start)
-			*out_start = base;
-		if (out_end)
-			*out_end = base + size - 1;
-
-		*idx += 1;
-		return;
-	}
-
-	/* signal end of iteration */
-	*idx = ULLONG_MAX;
-}
-
-static bool should_skip_region(struct memblock_region *m, int nid, int flags)
+static bool should_skip_region(struct memblock_type *type,
+			       struct memblock_region *m,
+			       int nid, int flags)
 {
 	int m_nid = memblock_get_region_node(m);
 
+	/* we never skip regions when iterating memblock.reserved or physmem */
+	if (type != memblock_memory)
+		return false;
+
 	/* only memory regions are associated with nodes, check it */
 	if (nid != NUMA_NO_NODE && nid != m_nid)
 		return true;
@@ -1052,7 +1036,7 @@ void __next_mem_range(u64 *idx, int nid, enum memblock_flags flags,
 		phys_addr_t m_end = m->base + m->size;
 		int	    m_nid = memblock_get_region_node(m);
 
-		if (should_skip_region(m, nid, flags))
+		if (should_skip_region(type_a, m, nid, flags))
 			continue;
 
 		if (!type_b) {
@@ -1156,7 +1140,7 @@ void __init_memblock __next_mem_range_rev(u64 *idx, int nid,
 		phys_addr_t m_end = m->base + m->size;
 		int m_nid = memblock_get_region_node(m);
 
-		if (should_skip_region(m, nid, flags))
+		if (should_skip_region(type_a, m, nid, flags))
 			continue;
 
 		if (!type_b) {
@@ -1981,7 +1965,7 @@ static unsigned long __init free_low_memory_core_early(void)
 
 	memblock_clear_hotplug(0, -1);
 
-	for_each_reserved_mem_region(i, &start, &end)
+	for_each_reserved_mem_range(i, &start, &end)
 		reserve_bootmem_region(start, end);
 
 	/*
-- 
cgit v1.2.3


From cc6de1680538633e4ef9540b2313fa2481a7c641 Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.ibm.com>
Date: Tue, 13 Oct 2020 16:58:30 -0700
Subject: memblock: use separate iterators for memory and reserved regions

for_each_memblock() is used to iterate over memblock.memory in a few
places that use data from memblock_region rather than the memory ranges.

Introduce separate for_each_mem_region() and
for_each_reserved_mem_region() to improve encapsulation of memblock
internals from its users.

Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Baoquan He <bhe@redhat.com>
Acked-by: Ingo Molnar <mingo@kernel.org>			[x86]
Acked-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>	[MIPS]
Acked-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>	[.clang-format]
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Daniel Axtens <dja@axtens.net>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Emil Renner Berthing <kernel@esmil.dk>
Cc: Hari Bathini <hbathini@linux.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Stafford Horne <shorne@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Link: https://lkml.kernel.org/r/20200818151634.14343-18-rppt@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 .clang-format                  |  3 ++-
 arch/arm64/kernel/setup.c      |  2 +-
 arch/arm64/mm/numa.c           |  2 +-
 arch/mips/netlogic/xlp/setup.c |  2 +-
 arch/riscv/mm/init.c           |  2 +-
 arch/x86/mm/numa.c             |  2 +-
 include/linux/memblock.h       | 19 ++++++++++++++++---
 mm/memblock.c                  |  4 ++--
 mm/page_alloc.c                |  8 ++++----
 9 files changed, 29 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/.clang-format b/.clang-format
index 8806bb21b6c2..6cbd6ee51610 100644
--- a/.clang-format
+++ b/.clang-format
@@ -203,7 +203,7 @@ ForEachMacros:
   - 'for_each_matching_node'
   - 'for_each_matching_node_and_match'
   - 'for_each_member'
-  - 'for_each_memblock'
+  - 'for_each_mem_region'
   - 'for_each_memblock_type'
   - 'for_each_memcg_cache_index'
   - 'for_each_mem_pfn_range'
@@ -274,6 +274,7 @@ ForEachMacros:
   - 'for_each_requested_gpio'
   - 'for_each_requested_gpio_in_range'
   - 'for_each_reserved_mem_range'
+  - 'for_each_reserved_mem_region'
   - 'for_each_rtd_codec_dais'
   - 'for_each_rtd_codec_dais_rollback'
   - 'for_each_rtd_components'
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 16aae43badfd..133257ffd859 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -217,7 +217,7 @@ static void __init request_standard_resources(void)
 	if (!standard_resources)
 		panic("%s: Failed to allocate %zu bytes\n", __func__, res_size);
 
-	for_each_memblock(memory, region) {
+	for_each_mem_region(region) {
 		res = &standard_resources[i++];
 		if (memblock_is_nomap(region)) {
 			res->name  = "reserved";
diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
index 2040b97e92d0..a8303bc6b62a 100644
--- a/arch/arm64/mm/numa.c
+++ b/arch/arm64/mm/numa.c
@@ -354,7 +354,7 @@ static int __init numa_register_nodes(void)
 	struct memblock_region *mblk;
 
 	/* Check that valid nid is set to memblks */
-	for_each_memblock(memory, mblk) {
+	for_each_mem_region(mblk) {
 		int mblk_nid = memblock_get_region_node(mblk);
 
 		if (mblk_nid == NUMA_NO_NODE || mblk_nid >= MAX_NUMNODES) {
diff --git a/arch/mips/netlogic/xlp/setup.c b/arch/mips/netlogic/xlp/setup.c
index 1a0fc5b62ba4..6e3102bcd2f1 100644
--- a/arch/mips/netlogic/xlp/setup.c
+++ b/arch/mips/netlogic/xlp/setup.c
@@ -70,7 +70,7 @@ static void nlm_fixup_mem(void)
 	const int pref_backup = 512;
 	struct memblock_region *mem;
 
-	for_each_memblock(memory, mem) {
+	for_each_mem_region(mem) {
 		memblock_remove(mem->base + mem->size - pref_backup,
 			pref_backup);
 	}
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 1e8c3e24e0c4..1dc89303b679 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -531,7 +531,7 @@ static void __init resource_init(void)
 {
 	struct memblock_region *region;
 
-	for_each_memblock(memory, region) {
+	for_each_mem_region(region) {
 		struct resource *res;
 
 		res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES);
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index c62e274d52d0..9df94e0aaee1 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -514,7 +514,7 @@ static void __init numa_clear_kernel_node_hotplug(void)
 	 *   memory ranges, because quirks such as trim_snb_memory()
 	 *   reserve specific pages for Sandy Bridge graphics. ]
 	 */
-	for_each_memblock(reserved, mb_region) {
+	for_each_reserved_mem_region(mb_region) {
 		int nid = memblock_get_region_node(mb_region);
 
 		if (nid != MAX_NUMNODES)
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 354078713cd1..ef131255cedc 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -553,9 +553,22 @@ static inline unsigned long memblock_region_reserved_end_pfn(const struct memblo
 	return PFN_UP(reg->base + reg->size);
 }
 
-#define for_each_memblock(memblock_type, region)					\
-	for (region = memblock.memblock_type.regions;					\
-	     region < (memblock.memblock_type.regions + memblock.memblock_type.cnt);	\
+/**
+ * for_each_mem_region - itereate over memory regions
+ * @region: loop variable
+ */
+#define for_each_mem_region(region)					\
+	for (region = memblock.memory.regions;				\
+	     region < (memblock.memory.regions + memblock.memory.cnt);	\
+	     region++)
+
+/**
+ * for_each_reserved_mem_region - itereate over reserved memory regions
+ * @region: loop variable
+ */
+#define for_each_reserved_mem_region(region)				\
+	for (region = memblock.reserved.regions;			\
+	     region < (memblock.reserved.regions + memblock.reserved.cnt); \
 	     region++)
 
 extern void *alloc_large_system_hash(const char *tablename,
diff --git a/mm/memblock.c b/mm/memblock.c
index a09cc4f057f0..165f40a8a254 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1667,7 +1667,7 @@ static phys_addr_t __init_memblock __find_max_addr(phys_addr_t limit)
 	 * the memory memblock regions, if the @limit exceeds the total size
 	 * of those regions, max_addr will keep original value PHYS_ADDR_MAX
 	 */
-	for_each_memblock(memory, r) {
+	for_each_mem_region(r) {
 		if (limit <= r->size) {
 			max_addr = r->base + limit;
 			break;
@@ -1837,7 +1837,7 @@ void __init_memblock memblock_trim_memory(phys_addr_t align)
 	phys_addr_t start, end, orig_start, orig_end;
 	struct memblock_region *r;
 
-	for_each_memblock(memory, r) {
+	for_each_mem_region(r) {
 		orig_start = r->base;
 		orig_end = r->base + r->size;
 		start = round_up(orig_start, align);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 34ac7127d1e6..05fe1ddb033c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5961,7 +5961,7 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn)
 
 	if (mirrored_kernelcore && zone == ZONE_MOVABLE) {
 		if (!r || *pfn >= memblock_region_memory_end_pfn(r)) {
-			for_each_memblock(memory, r) {
+			for_each_mem_region(r) {
 				if (*pfn < memblock_region_memory_end_pfn(r))
 					break;
 			}
@@ -6546,7 +6546,7 @@ static unsigned long __init zone_absent_pages_in_node(int nid,
 		unsigned long start_pfn, end_pfn;
 		struct memblock_region *r;
 
-		for_each_memblock(memory, r) {
+		for_each_mem_region(r) {
 			start_pfn = clamp(memblock_region_memory_base_pfn(r),
 					  zone_start_pfn, zone_end_pfn);
 			end_pfn = clamp(memblock_region_memory_end_pfn(r),
@@ -7140,7 +7140,7 @@ static void __init find_zone_movable_pfns_for_nodes(void)
 	 * options.
 	 */
 	if (movable_node_is_enabled()) {
-		for_each_memblock(memory, r) {
+		for_each_mem_region(r) {
 			if (!memblock_is_hotpluggable(r))
 				continue;
 
@@ -7161,7 +7161,7 @@ static void __init find_zone_movable_pfns_for_nodes(void)
 	if (mirrored_kernelcore) {
 		bool mem_below_4gb_not_mirrored = false;
 
-		for_each_memblock(memory, r) {
+		for_each_mem_region(r) {
 			if (memblock_is_mirror(r))
 				continue;
 
-- 
cgit v1.2.3


From 67197a4f28d28d0b073ab0427b03cb2ee5382578 Mon Sep 17 00:00:00 2001
From: Suren Baghdasaryan <surenb@google.com>
Date: Tue, 13 Oct 2020 16:58:35 -0700
Subject: mm, oom_adj: don't loop through tasks in __set_oom_adj when not
 necessary

Currently __set_oom_adj loops through all processes in the system to keep
oom_score_adj and oom_score_adj_min in sync between processes sharing
their mm.  This is done for any task with more that one mm_users, which
includes processes with multiple threads (sharing mm and signals).
However for such processes the loop is unnecessary because their signal
structure is shared as well.

Android updates oom_score_adj whenever a tasks changes its role
(background/foreground/...) or binds to/unbinds from a service, making it
more/less important.  Such operation can happen frequently.  We noticed
that updates to oom_score_adj became more expensive and after further
investigation found out that the patch mentioned in "Fixes" introduced a
regression.  Using Pixel 4 with a typical Android workload, write time to
oom_score_adj increased from ~3.57us to ~362us.  Moreover this regression
linearly depends on the number of multi-threaded processes running on the
system.

Mark the mm with a new MMF_MULTIPROCESS flag bit when task is created with
(CLONE_VM && !CLONE_THREAD && !CLONE_VFORK).  Change __set_oom_adj to use
MMF_MULTIPROCESS instead of mm_users to decide whether oom_score_adj
update should be synchronized between multiple processes.  To prevent
races between clone() and __set_oom_adj(), when oom_score_adj of the
process being cloned might be modified from userspace, we use
oom_adj_mutex.  Its scope is changed to global.

The combination of (CLONE_VM && !CLONE_THREAD) is rarely used except for
the case of vfork().  To prevent performance regressions of vfork(), we
skip taking oom_adj_mutex and setting MMF_MULTIPROCESS when CLONE_VFORK is
specified.  Clearing the MMF_MULTIPROCESS flag (when the last process
sharing the mm exits) is left out of this patch to keep it simple and
because it is believed that this threading model is rare.  Should there
ever be a need for optimizing that case as well, it can be done by hooking
into the exit path, likely following the mm_update_next_owner pattern.

With the combination of (CLONE_VM && !CLONE_THREAD && !CLONE_VFORK) being
quite rare, the regression is gone after the change is applied.

[surenb@google.com: v3]
  Link: https://lkml.kernel.org/r/20200902012558.2335613-1-surenb@google.com

Fixes: 44a70adec910 ("mm, oom_adj: make sure processes sharing mm have same view of oom_score_adj")
Reported-by: Tim Murray <timmurray@google.com>
Suggested-by: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Oleg Nesterov <oleg@redhat.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Eugene Syromiatnikov <esyr@redhat.com>
Cc: Christian Kellner <christian@kellner.me>
Cc: Adrian Reber <areber@redhat.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Aleksa Sarai <cyphar@cyphar.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Alexey Gladkov <gladkov.alexey@gmail.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: Andrei Vagin <avagin@gmail.com>
Cc: Bernd Edlinger <bernd.edlinger@hotmail.de>
Cc: John Johansen <john.johansen@canonical.com>
Cc: Yafang Shao <laoar.shao@gmail.com>
Link: https://lkml.kernel.org/r/20200824153036.3201505-1-surenb@google.com
Debugged-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/proc/base.c                 |  3 +--
 include/linux/oom.h            |  1 +
 include/linux/sched/coredump.h |  1 +
 kernel/fork.c                  | 21 +++++++++++++++++++++
 mm/oom_kill.c                  |  2 ++
 5 files changed, 26 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 617db4e0faa0..aa69c35d904c 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1055,7 +1055,6 @@ static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count,
 
 static int __set_oom_adj(struct file *file, int oom_adj, bool legacy)
 {
-	static DEFINE_MUTEX(oom_adj_mutex);
 	struct mm_struct *mm = NULL;
 	struct task_struct *task;
 	int err = 0;
@@ -1095,7 +1094,7 @@ static int __set_oom_adj(struct file *file, int oom_adj, bool legacy)
 		struct task_struct *p = find_lock_task_mm(task);
 
 		if (p) {
-			if (atomic_read(&p->mm->mm_users) > 1) {
+			if (test_bit(MMF_MULTIPROCESS, &p->mm->flags)) {
 				mm = p->mm;
 				mmgrab(mm);
 			}
diff --git a/include/linux/oom.h b/include/linux/oom.h
index f022f581ac29..2db9a1432511 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -55,6 +55,7 @@ struct oom_control {
 };
 
 extern struct mutex oom_lock;
+extern struct mutex oom_adj_mutex;
 
 static inline void set_current_oom_origin(void)
 {
diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h
index ecdc6542070f..dfd82eab2902 100644
--- a/include/linux/sched/coredump.h
+++ b/include/linux/sched/coredump.h
@@ -72,6 +72,7 @@ static inline int get_dumpable(struct mm_struct *mm)
 #define MMF_DISABLE_THP		24	/* disable THP for all VMAs */
 #define MMF_OOM_VICTIM		25	/* mm is the oom victim */
 #define MMF_OOM_REAP_QUEUED	26	/* mm was queued for oom_reaper */
+#define MMF_MULTIPROCESS	27	/* mm is shared between processes */
 #define MMF_DISABLE_THP_MASK	(1 << MMF_DISABLE_THP)
 
 #define MMF_INIT_MASK		(MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\
diff --git a/kernel/fork.c b/kernel/fork.c
index ede26e5a6097..50c90d368117 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1812,6 +1812,25 @@ static __always_inline void delayed_free_task(struct task_struct *tsk)
 		free_task(tsk);
 }
 
+static void copy_oom_score_adj(u64 clone_flags, struct task_struct *tsk)
+{
+	/* Skip if kernel thread */
+	if (!tsk->mm)
+		return;
+
+	/* Skip if spawning a thread or using vfork */
+	if ((clone_flags & (CLONE_VM | CLONE_THREAD | CLONE_VFORK)) != CLONE_VM)
+		return;
+
+	/* We need to synchronize with __set_oom_adj */
+	mutex_lock(&oom_adj_mutex);
+	set_bit(MMF_MULTIPROCESS, &tsk->mm->flags);
+	/* Update the values in case they were changed after copy_signal */
+	tsk->signal->oom_score_adj = current->signal->oom_score_adj;
+	tsk->signal->oom_score_adj_min = current->signal->oom_score_adj_min;
+	mutex_unlock(&oom_adj_mutex);
+}
+
 /*
  * This creates a new process as a copy of the old one,
  * but does not actually start it yet.
@@ -2288,6 +2307,8 @@ static __latent_entropy struct task_struct *copy_process(
 	trace_task_newtask(p, clone_flags);
 	uprobe_copy_process(p, clone_flags);
 
+	copy_oom_score_adj(clone_flags, p);
+
 	return p;
 
 bad_fork_cancel_cgroup:
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index e90f25d6385d..8b84661a6410 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -64,6 +64,8 @@ int sysctl_oom_dump_tasks = 1;
  * and mark_oom_victim
  */
 DEFINE_MUTEX(oom_lock);
+/* Serializes oom_score_adj and oom_score_adj_min updates */
+DEFINE_MUTEX(oom_adj_mutex);
 
 static inline bool is_memcg_oom(struct oom_control *oc)
 {
-- 
cgit v1.2.3


From ed3e453798d4f81c99056aa09fcd79d0874a60fd Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Tue, 13 Oct 2020 14:14:43 +0200
Subject: locking/seqlocks: Fix kernel-doc warnings

Right now, seqlock.h produces kernel-doc warnings:

	./include/linux/seqlock.h:181: error: Cannot parse typedef!

Convert it to a plain comment to avoid confusing kernel-doc.

Fixes: a8772dccb2ec ("seqlock: Fold seqcount_LOCKNAME_t definition")
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/a59144cdaadf7fdf1fe5d55d0e1575abbf1c0cb3.1602590106.git.mchehab+huawei@kernel.org
---
 include/linux/seqlock.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index ac5b07f558b0..cbfc78b92b65 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -154,7 +154,7 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
 #define __SEQ_LOCK(expr)
 #endif
 
-/**
+/*
  * typedef seqcount_LOCKNAME_t - sequence counter with LOCKNAME associated
  * @seqcount:	The real sequence counter
  * @lock:	Pointer to the associated lock
-- 
cgit v1.2.3


From 02e83f46ebfaf9405881e290794c913d457541f0 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Wed, 14 Oct 2020 16:47:08 -0700
Subject: vfs: move generic_remap_checks out of mm

I would like to move all the generic helpers for the vfs remap range
functionality (aka clonerange and dedupe) into a separate file so that
they won't be scattered across the vfs and the mm subsystems.  The
eventual goal is to be able to deselect remap_range.c if none of the
filesystems need that code, but the tricky part here is picking a
stable(ish) part of the merge window to rearrange code.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/Makefile        |  3 +-
 fs/remap_range.c   | 97 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/fs.h |  2 ++
 mm/filemap.c       | 81 +--------------------------------------------
 4 files changed, 102 insertions(+), 81 deletions(-)
 create mode 100644 fs/remap_range.c

(limited to 'include/linux')

diff --git a/fs/Makefile b/fs/Makefile
index 1c7b0e3f6daa..7173350739c5 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -13,7 +13,8 @@ obj-y :=	open.o read_write.o file_table.o super.o \
 		seq_file.o xattr.o libfs.o fs-writeback.o \
 		pnode.o splice.o sync.o utimes.o d_path.o \
 		stack.o fs_struct.o statfs.o fs_pin.o nsfs.o \
-		fs_types.o fs_context.o fs_parser.o fsopen.o init.o
+		fs_types.o fs_context.o fs_parser.o fsopen.o init.o \
+		remap_range.o
 
 ifeq ($(CONFIG_BLOCK),y)
 obj-y +=	buffer.o block_dev.o direct-io.o mpage.o
diff --git a/fs/remap_range.c b/fs/remap_range.c
new file mode 100644
index 000000000000..f0a8c7065d5b
--- /dev/null
+++ b/fs/remap_range.c
@@ -0,0 +1,97 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/slab.h>
+#include <linux/stat.h>
+#include <linux/sched/xacct.h>
+#include <linux/fcntl.h>
+#include <linux/file.h>
+#include <linux/uio.h>
+#include <linux/fsnotify.h>
+#include <linux/security.h>
+#include <linux/export.h>
+#include <linux/syscalls.h>
+#include <linux/pagemap.h>
+#include <linux/splice.h>
+#include <linux/compat.h>
+#include <linux/mount.h>
+#include <linux/fs.h>
+#include "internal.h"
+
+#include <linux/uaccess.h>
+#include <asm/unistd.h>
+
+/*
+ * Performs necessary checks before doing a clone.
+ *
+ * Can adjust amount of bytes to clone via @req_count argument.
+ * Returns appropriate error code that caller should return or
+ * zero in case the clone should be allowed.
+ */
+int generic_remap_checks(struct file *file_in, loff_t pos_in,
+			 struct file *file_out, loff_t pos_out,
+			 loff_t *req_count, unsigned int remap_flags)
+{
+	struct inode *inode_in = file_in->f_mapping->host;
+	struct inode *inode_out = file_out->f_mapping->host;
+	uint64_t count = *req_count;
+	uint64_t bcount;
+	loff_t size_in, size_out;
+	loff_t bs = inode_out->i_sb->s_blocksize;
+	int ret;
+
+	/* The start of both ranges must be aligned to an fs block. */
+	if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_out, bs))
+		return -EINVAL;
+
+	/* Ensure offsets don't wrap. */
+	if (pos_in + count < pos_in || pos_out + count < pos_out)
+		return -EINVAL;
+
+	size_in = i_size_read(inode_in);
+	size_out = i_size_read(inode_out);
+
+	/* Dedupe requires both ranges to be within EOF. */
+	if ((remap_flags & REMAP_FILE_DEDUP) &&
+	    (pos_in >= size_in || pos_in + count > size_in ||
+	     pos_out >= size_out || pos_out + count > size_out))
+		return -EINVAL;
+
+	/* Ensure the infile range is within the infile. */
+	if (pos_in >= size_in)
+		return -EINVAL;
+	count = min(count, size_in - (uint64_t)pos_in);
+
+	ret = generic_write_check_limits(file_out, pos_out, &count);
+	if (ret)
+		return ret;
+
+	/*
+	 * If the user wanted us to link to the infile's EOF, round up to the
+	 * next block boundary for this check.
+	 *
+	 * Otherwise, make sure the count is also block-aligned, having
+	 * already confirmed the starting offsets' block alignment.
+	 */
+	if (pos_in + count == size_in) {
+		bcount = ALIGN(size_in, bs) - pos_in;
+	} else {
+		if (!IS_ALIGNED(count, bs))
+			count = ALIGN_DOWN(count, bs);
+		bcount = count;
+	}
+
+	/* Don't allow overlapped cloning within the same file. */
+	if (inode_in == inode_out &&
+	    pos_out + bcount > pos_in &&
+	    pos_out < pos_in + bcount)
+		return -EINVAL;
+
+	/*
+	 * We shortened the request but the caller can't deal with that, so
+	 * bounce the request back to userspace.
+	 */
+	if (*req_count != count && !(remap_flags & REMAP_FILE_CAN_SHORTEN))
+		return -EINVAL;
+
+	*req_count = count;
+	return 0;
+}
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7519ae003a08..eea754a8dd67 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3012,6 +3012,8 @@ extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *);
 extern int generic_remap_checks(struct file *file_in, loff_t pos_in,
 				struct file *file_out, loff_t pos_out,
 				loff_t *count, unsigned int remap_flags);
+extern int generic_write_check_limits(struct file *file, loff_t pos,
+		loff_t *count);
 extern int generic_file_rw_checks(struct file *file_in, struct file *file_out);
 extern int generic_copy_file_checks(struct file *file_in, loff_t pos_in,
 				    struct file *file_out, loff_t pos_out,
diff --git a/mm/filemap.c b/mm/filemap.c
index 99c49eeae71b..cf20e5aeb11b 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3098,8 +3098,7 @@ EXPORT_SYMBOL(read_cache_page_gfp);
  * LFS limits.  If pos is under the limit it becomes a short access.  If it
  * exceeds the limit we return -EFBIG.
  */
-static int generic_write_check_limits(struct file *file, loff_t pos,
-				      loff_t *count)
+int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count)
 {
 	struct inode *inode = file->f_mapping->host;
 	loff_t max_size = inode->i_sb->s_maxbytes;
@@ -3161,84 +3160,6 @@ inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
 }
 EXPORT_SYMBOL(generic_write_checks);
 
-/*
- * Performs necessary checks before doing a clone.
- *
- * Can adjust amount of bytes to clone via @req_count argument.
- * Returns appropriate error code that caller should return or
- * zero in case the clone should be allowed.
- */
-int generic_remap_checks(struct file *file_in, loff_t pos_in,
-			 struct file *file_out, loff_t pos_out,
-			 loff_t *req_count, unsigned int remap_flags)
-{
-	struct inode *inode_in = file_in->f_mapping->host;
-	struct inode *inode_out = file_out->f_mapping->host;
-	uint64_t count = *req_count;
-	uint64_t bcount;
-	loff_t size_in, size_out;
-	loff_t bs = inode_out->i_sb->s_blocksize;
-	int ret;
-
-	/* The start of both ranges must be aligned to an fs block. */
-	if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_out, bs))
-		return -EINVAL;
-
-	/* Ensure offsets don't wrap. */
-	if (pos_in + count < pos_in || pos_out + count < pos_out)
-		return -EINVAL;
-
-	size_in = i_size_read(inode_in);
-	size_out = i_size_read(inode_out);
-
-	/* Dedupe requires both ranges to be within EOF. */
-	if ((remap_flags & REMAP_FILE_DEDUP) &&
-	    (pos_in >= size_in || pos_in + count > size_in ||
-	     pos_out >= size_out || pos_out + count > size_out))
-		return -EINVAL;
-
-	/* Ensure the infile range is within the infile. */
-	if (pos_in >= size_in)
-		return -EINVAL;
-	count = min(count, size_in - (uint64_t)pos_in);
-
-	ret = generic_write_check_limits(file_out, pos_out, &count);
-	if (ret)
-		return ret;
-
-	/*
-	 * If the user wanted us to link to the infile's EOF, round up to the
-	 * next block boundary for this check.
-	 *
-	 * Otherwise, make sure the count is also block-aligned, having
-	 * already confirmed the starting offsets' block alignment.
-	 */
-	if (pos_in + count == size_in) {
-		bcount = ALIGN(size_in, bs) - pos_in;
-	} else {
-		if (!IS_ALIGNED(count, bs))
-			count = ALIGN_DOWN(count, bs);
-		bcount = count;
-	}
-
-	/* Don't allow overlapped cloning within the same file. */
-	if (inode_in == inode_out &&
-	    pos_out + bcount > pos_in &&
-	    pos_out < pos_in + bcount)
-		return -EINVAL;
-
-	/*
-	 * We shortened the request but the caller can't deal with that, so
-	 * bounce the request back to userspace.
-	 */
-	if (*req_count != count && !(remap_flags & REMAP_FILE_CAN_SHORTEN))
-		return -EINVAL;
-
-	*req_count = count;
-	return 0;
-}
-
-
 /*
  * Performs common checks before doing a file copy/clone
  * from @file_in to @file_out.
-- 
cgit v1.2.3


From c2a9a645591f11761fdbe3c7f45c0ad32af97eb4 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Mon, 28 Sep 2020 15:25:17 +0200
Subject: math64.h: kernel-docs: Convert some markups into normal comments

There are several functions at math64.h that are also
defined at div64.c. As both are included at kernel-api.rst,
Sphinx 3.x complains about symbol duplication:

	./lib/math/div64.c:73: WARNING: Duplicate C declaration, also defined in 'core-api/kernel-api'.
	Declaration is 'div_s64_rem'.
	./lib/math/div64.c:104: WARNING: Duplicate C declaration, also defined in 'core-api/kernel-api'.
	Declaration is 'div64_u64_rem'.
	./lib/math/div64.c:144: WARNING: Duplicate C declaration, also defined in 'core-api/kernel-api'.
	Declaration is 'div64_u64'.
	./lib/math/div64.c:172: WARNING: Duplicate C declaration, also defined in 'core-api/kernel-api'.
	Declaration is 'div64_s64'.

In order to avoid Sphinx warnings about duplication, change the kernel-doc
markups to just comments at math64.h.

Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 include/linux/math64.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/math64.h b/include/linux/math64.h
index 3381d9e33c4e..66deb1fdc2ef 100644
--- a/include/linux/math64.h
+++ b/include/linux/math64.h
@@ -28,7 +28,7 @@ static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder)
 	return dividend / divisor;
 }
 
-/**
+/*
  * div_s64_rem - signed 64bit divide with 32bit divisor with remainder
  * @dividend: signed 64bit dividend
  * @divisor: signed 32bit divisor
@@ -42,7 +42,7 @@ static inline s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder)
 	return dividend / divisor;
 }
 
-/**
+/*
  * div64_u64_rem - unsigned 64bit divide with 64bit divisor and remainder
  * @dividend: unsigned 64bit dividend
  * @divisor: unsigned 64bit divisor
@@ -56,7 +56,7 @@ static inline u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder)
 	return dividend / divisor;
 }
 
-/**
+/*
  * div64_u64 - unsigned 64bit divide with 64bit divisor
  * @dividend: unsigned 64bit dividend
  * @divisor: unsigned 64bit divisor
@@ -68,7 +68,7 @@ static inline u64 div64_u64(u64 dividend, u64 divisor)
 	return dividend / divisor;
 }
 
-/**
+/*
  * div64_s64 - signed 64bit divide with 64bit divisor
  * @dividend: signed 64bit dividend
  * @divisor: signed 64bit divisor
-- 
cgit v1.2.3


From 1b7743912bcf2b4a9d9c96de668542156450554f Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Thu, 10 Sep 2020 09:25:14 +0200
Subject: usb: docs: document altmode register/unregister functions

The typec_bus.rst asks for documentation of those two
functions, but they don't exist:

	./drivers/usb/typec/bus.c:1: warning: 'typec_altmode_unregister_driver' not found
	./drivers/usb/typec/bus.c:1: warning: 'typec_altmode_register_driver' not found

Also, they're not declared on bus.c but, instead, at a header
file (typec_altmode.h).

So, add documentation for both functions at the header and
change the kernel-doc markup under typec_bus.rst to point
to the right place.

While here, also place the documentation for both structs
declared on typec_altmode.h at the rst file.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 Documentation/driver-api/usb/typec_bus.rst |  8 +++++++-
 include/linux/usb/typec_altmode.h          | 16 ++++++++++++++++
 2 files changed, 23 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/Documentation/driver-api/usb/typec_bus.rst b/Documentation/driver-api/usb/typec_bus.rst
index 03dfa9c018b7..21c890ae17e5 100644
--- a/Documentation/driver-api/usb/typec_bus.rst
+++ b/Documentation/driver-api/usb/typec_bus.rst
@@ -91,10 +91,16 @@ their control.
 Driver API
 ----------
 
+Alternate mode structs
+~~~~~~~~~~~~~~~~~~~~~~
+
+.. kernel-doc:: include/linux/usb/typec_altmode.h
+   :functions: typec_altmode_driver typec_altmode_ops
+
 Alternate mode driver registering/unregistering
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-.. kernel-doc:: drivers/usb/typec/bus.c
+.. kernel-doc:: include/linux/usb/typec_altmode.h
    :functions: typec_altmode_register_driver typec_altmode_unregister_driver
 
 Alternate mode driver operations
diff --git a/include/linux/usb/typec_altmode.h b/include/linux/usb/typec_altmode.h
index a4b65eaa0f62..5e0a7b7647c3 100644
--- a/include/linux/usb/typec_altmode.h
+++ b/include/linux/usb/typec_altmode.h
@@ -152,10 +152,26 @@ struct typec_altmode_driver {
 #define to_altmode_driver(d) container_of(d, struct typec_altmode_driver, \
 					  driver)
 
+/**
+ * typec_altmode_register_driver - registers a USB Type-C alternate mode
+ * 				   device driver
+ * @drv: pointer to struct typec_altmode_driver
+ *
+ * These drivers will be bind to the partner alternate mode devices. They will
+ * handle all SVID specific communication.
+ */
 #define typec_altmode_register_driver(drv) \
 		__typec_altmode_register_driver(drv, THIS_MODULE)
 int __typec_altmode_register_driver(struct typec_altmode_driver *drv,
 				    struct module *module);
+/**
+ * typec_altmode_unregister_driver - unregisters a USB Type-C alternate mode
+ * 				     device driver
+ * @drv: pointer to struct typec_altmode_driver
+ *
+ * These drivers will be bind to the partner alternate mode devices. They will
+ * handle all SVID specific communication.
+ */
 void typec_altmode_unregister_driver(struct typec_altmode_driver *drv);
 
 #define module_typec_altmode_driver(__typec_altmode_driver) \
-- 
cgit v1.2.3


From f2c6855159228861f4552d563c13f5b194b9889f Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Thu, 10 Sep 2020 10:27:17 +0200
Subject: Input: sparse-keymap: add a description for @sw

Add a description for it, in order to avoids this warning:

	./include/linux/input/sparse-keymap.h:43: warning: Function parameter or member 'sw' not described in 'key_entry'

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 include/linux/input/sparse-keymap.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/input/sparse-keymap.h b/include/linux/input/sparse-keymap.h
index d25d1452dc6e..d0dddc14ebc8 100644
--- a/include/linux/input/sparse-keymap.h
+++ b/include/linux/input/sparse-keymap.h
@@ -20,6 +20,7 @@
  *	private definitions.
  * @code: Device-specific data identifying the button/switch
  * @keycode: KEY_* code assigned to a key/button
+ * @sw: struct with code/value used by KE_SW and KE_VSW
  * @sw.code: SW_* code assigned to a switch
  * @sw.value: Value that should be sent in an input even when KE_SW
  *	switch is toggled. KE_VSW switches ignore this field and
-- 
cgit v1.2.3


From 770c03e6dabacd5b9f57bba93c4311d32b618640 Mon Sep 17 00:00:00 2001
From: Fei Shao <fshao@chromium.org>
Date: Thu, 8 Oct 2020 17:34:14 +0800
Subject: rtc: mt6397: Remove unused member dev

Removing the struct member "dev" in mt6397 RTC driver because it's not
initialized and the only usage is for one debugging message.

Also fixed a typo in the error message.

Signed-off-by: Fei Shao <fshao@chromium.org>
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Link: https://lore.kernel.org/r/20201008093414.1911699-1-fshao@chromium.org
---
 drivers/rtc/rtc-mt6397.c       | 3 ++-
 include/linux/mfd/mt6397/rtc.h | 1 -
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/rtc/rtc-mt6397.c b/drivers/rtc/rtc-mt6397.c
index f8b1353777ba..1894aded4c85 100644
--- a/drivers/rtc/rtc-mt6397.c
+++ b/drivers/rtc/rtc-mt6397.c
@@ -31,7 +31,8 @@ static int mtk_rtc_write_trigger(struct mt6397_rtc *rtc)
 					MTK_RTC_POLL_DELAY_US,
 					MTK_RTC_POLL_TIMEOUT);
 	if (ret < 0)
-		dev_err(rtc->dev, "failed to write WRTGE: %d\n", ret);
+		dev_err(rtc->rtc_dev->dev.parent,
+			"failed to write WRTGR: %d\n", ret);
 
 	return ret;
 }
diff --git a/include/linux/mfd/mt6397/rtc.h b/include/linux/mfd/mt6397/rtc.h
index 66989a16221a..c3748b53bf7d 100644
--- a/include/linux/mfd/mt6397/rtc.h
+++ b/include/linux/mfd/mt6397/rtc.h
@@ -72,7 +72,6 @@ struct mtk_rtc_data {
 };
 
 struct mt6397_rtc {
-	struct device           *dev;
 	struct rtc_device       *rtc_dev;
 
 	/* Protect register access from multiple tasks */
-- 
cgit v1.2.3


From 1b2c54d63cde7e8cf15aa6319aba168d81c7e364 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Wed, 14 Oct 2020 16:38:47 -0700
Subject: vfs: move the remap range helpers to remap_range.c

Complete the migration by moving the file remapping helper functions out
of read_write.c and into remap_range.c.  This reduces the clutter in the
first file and (eventually) will make it so that we can compile out the
second file if it isn't needed.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/read_write.c    | 473 ----------------------------------------------------
 fs/remap_range.c   | 480 ++++++++++++++++++++++++++++++++++++++++++++++++++++-
 include/linux/fs.h |   3 -
 3 files changed, 477 insertions(+), 479 deletions(-)

(limited to 'include/linux')

diff --git a/fs/read_write.c b/fs/read_write.c
index d3428189f36b..f0877f1c0c49 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1832,476 +1832,3 @@ out1:
 out2:
 	return ret;
 }
-
-static int remap_verify_area(struct file *file, loff_t pos, loff_t len,
-			     bool write)
-{
-	struct inode *inode = file_inode(file);
-
-	if (unlikely(pos < 0 || len < 0))
-		return -EINVAL;
-
-	 if (unlikely((loff_t) (pos + len) < 0))
-		return -EINVAL;
-
-	if (unlikely(inode->i_flctx && mandatory_lock(inode))) {
-		loff_t end = len ? pos + len - 1 : OFFSET_MAX;
-		int retval;
-
-		retval = locks_mandatory_area(inode, file, pos, end,
-				write ? F_WRLCK : F_RDLCK);
-		if (retval < 0)
-			return retval;
-	}
-
-	return security_file_permission(file, write ? MAY_WRITE : MAY_READ);
-}
-/*
- * Ensure that we don't remap a partial EOF block in the middle of something
- * else.  Assume that the offsets have already been checked for block
- * alignment.
- *
- * For clone we only link a partial EOF block above or at the destination file's
- * EOF.  For deduplication we accept a partial EOF block only if it ends at the
- * destination file's EOF (can not link it into the middle of a file).
- *
- * Shorten the request if possible.
- */
-static int generic_remap_check_len(struct inode *inode_in,
-				   struct inode *inode_out,
-				   loff_t pos_out,
-				   loff_t *len,
-				   unsigned int remap_flags)
-{
-	u64 blkmask = i_blocksize(inode_in) - 1;
-	loff_t new_len = *len;
-
-	if ((*len & blkmask) == 0)
-		return 0;
-
-	if (pos_out + *len < i_size_read(inode_out))
-		new_len &= ~blkmask;
-
-	if (new_len == *len)
-		return 0;
-
-	if (remap_flags & REMAP_FILE_CAN_SHORTEN) {
-		*len = new_len;
-		return 0;
-	}
-
-	return (remap_flags & REMAP_FILE_DEDUP) ? -EBADE : -EINVAL;
-}
-
-/* Read a page's worth of file data into the page cache. */
-static struct page *vfs_dedupe_get_page(struct inode *inode, loff_t offset)
-{
-	struct page *page;
-
-	page = read_mapping_page(inode->i_mapping, offset >> PAGE_SHIFT, NULL);
-	if (IS_ERR(page))
-		return page;
-	if (!PageUptodate(page)) {
-		put_page(page);
-		return ERR_PTR(-EIO);
-	}
-	return page;
-}
-
-/*
- * Lock two pages, ensuring that we lock in offset order if the pages are from
- * the same file.
- */
-static void vfs_lock_two_pages(struct page *page1, struct page *page2)
-{
-	/* Always lock in order of increasing index. */
-	if (page1->index > page2->index)
-		swap(page1, page2);
-
-	lock_page(page1);
-	if (page1 != page2)
-		lock_page(page2);
-}
-
-/* Unlock two pages, being careful not to unlock the same page twice. */
-static void vfs_unlock_two_pages(struct page *page1, struct page *page2)
-{
-	unlock_page(page1);
-	if (page1 != page2)
-		unlock_page(page2);
-}
-
-/*
- * Compare extents of two files to see if they are the same.
- * Caller must have locked both inodes to prevent write races.
- */
-static int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
-					 struct inode *dest, loff_t destoff,
-					 loff_t len, bool *is_same)
-{
-	loff_t src_poff;
-	loff_t dest_poff;
-	void *src_addr;
-	void *dest_addr;
-	struct page *src_page;
-	struct page *dest_page;
-	loff_t cmp_len;
-	bool same;
-	int error;
-
-	error = -EINVAL;
-	same = true;
-	while (len) {
-		src_poff = srcoff & (PAGE_SIZE - 1);
-		dest_poff = destoff & (PAGE_SIZE - 1);
-		cmp_len = min(PAGE_SIZE - src_poff,
-			      PAGE_SIZE - dest_poff);
-		cmp_len = min(cmp_len, len);
-		if (cmp_len <= 0)
-			goto out_error;
-
-		src_page = vfs_dedupe_get_page(src, srcoff);
-		if (IS_ERR(src_page)) {
-			error = PTR_ERR(src_page);
-			goto out_error;
-		}
-		dest_page = vfs_dedupe_get_page(dest, destoff);
-		if (IS_ERR(dest_page)) {
-			error = PTR_ERR(dest_page);
-			put_page(src_page);
-			goto out_error;
-		}
-
-		vfs_lock_two_pages(src_page, dest_page);
-
-		/*
-		 * Now that we've locked both pages, make sure they're still
-		 * mapped to the file data we're interested in.  If not,
-		 * someone is invalidating pages on us and we lose.
-		 */
-		if (!PageUptodate(src_page) || !PageUptodate(dest_page) ||
-		    src_page->mapping != src->i_mapping ||
-		    dest_page->mapping != dest->i_mapping) {
-			same = false;
-			goto unlock;
-		}
-
-		src_addr = kmap_atomic(src_page);
-		dest_addr = kmap_atomic(dest_page);
-
-		flush_dcache_page(src_page);
-		flush_dcache_page(dest_page);
-
-		if (memcmp(src_addr + src_poff, dest_addr + dest_poff, cmp_len))
-			same = false;
-
-		kunmap_atomic(dest_addr);
-		kunmap_atomic(src_addr);
-unlock:
-		vfs_unlock_two_pages(src_page, dest_page);
-		put_page(dest_page);
-		put_page(src_page);
-
-		if (!same)
-			break;
-
-		srcoff += cmp_len;
-		destoff += cmp_len;
-		len -= cmp_len;
-	}
-
-	*is_same = same;
-	return 0;
-
-out_error:
-	return error;
-}
-
-/*
- * Check that the two inodes are eligible for cloning, the ranges make
- * sense, and then flush all dirty data.  Caller must ensure that the
- * inodes have been locked against any other modifications.
- *
- * If there's an error, then the usual negative error code is returned.
- * Otherwise returns 0 with *len set to the request length.
- */
-int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
-				  struct file *file_out, loff_t pos_out,
-				  loff_t *len, unsigned int remap_flags)
-{
-	struct inode *inode_in = file_inode(file_in);
-	struct inode *inode_out = file_inode(file_out);
-	bool same_inode = (inode_in == inode_out);
-	int ret;
-
-	/* Don't touch certain kinds of inodes */
-	if (IS_IMMUTABLE(inode_out))
-		return -EPERM;
-
-	if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out))
-		return -ETXTBSY;
-
-	/* Don't reflink dirs, pipes, sockets... */
-	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
-		return -EISDIR;
-	if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
-		return -EINVAL;
-
-	/* Zero length dedupe exits immediately; reflink goes to EOF. */
-	if (*len == 0) {
-		loff_t isize = i_size_read(inode_in);
-
-		if ((remap_flags & REMAP_FILE_DEDUP) || pos_in == isize)
-			return 0;
-		if (pos_in > isize)
-			return -EINVAL;
-		*len = isize - pos_in;
-		if (*len == 0)
-			return 0;
-	}
-
-	/* Check that we don't violate system file offset limits. */
-	ret = generic_remap_checks(file_in, pos_in, file_out, pos_out, len,
-			remap_flags);
-	if (ret)
-		return ret;
-
-	/* Wait for the completion of any pending IOs on both files */
-	inode_dio_wait(inode_in);
-	if (!same_inode)
-		inode_dio_wait(inode_out);
-
-	ret = filemap_write_and_wait_range(inode_in->i_mapping,
-			pos_in, pos_in + *len - 1);
-	if (ret)
-		return ret;
-
-	ret = filemap_write_and_wait_range(inode_out->i_mapping,
-			pos_out, pos_out + *len - 1);
-	if (ret)
-		return ret;
-
-	/*
-	 * Check that the extents are the same.
-	 */
-	if (remap_flags & REMAP_FILE_DEDUP) {
-		bool		is_same = false;
-
-		ret = vfs_dedupe_file_range_compare(inode_in, pos_in,
-				inode_out, pos_out, *len, &is_same);
-		if (ret)
-			return ret;
-		if (!is_same)
-			return -EBADE;
-	}
-
-	ret = generic_remap_check_len(inode_in, inode_out, pos_out, len,
-			remap_flags);
-	if (ret)
-		return ret;
-
-	/* If can't alter the file contents, we're done. */
-	if (!(remap_flags & REMAP_FILE_DEDUP))
-		ret = file_modified(file_out);
-
-	return ret;
-}
-EXPORT_SYMBOL(generic_remap_file_range_prep);
-
-loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
-			   struct file *file_out, loff_t pos_out,
-			   loff_t len, unsigned int remap_flags)
-{
-	loff_t ret;
-
-	WARN_ON_ONCE(remap_flags & REMAP_FILE_DEDUP);
-
-	/*
-	 * FICLONE/FICLONERANGE ioctls enforce that src and dest files are on
-	 * the same mount. Practically, they only need to be on the same file
-	 * system.
-	 */
-	if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb)
-		return -EXDEV;
-
-	ret = generic_file_rw_checks(file_in, file_out);
-	if (ret < 0)
-		return ret;
-
-	if (!file_in->f_op->remap_file_range)
-		return -EOPNOTSUPP;
-
-	ret = remap_verify_area(file_in, pos_in, len, false);
-	if (ret)
-		return ret;
-
-	ret = remap_verify_area(file_out, pos_out, len, true);
-	if (ret)
-		return ret;
-
-	ret = file_in->f_op->remap_file_range(file_in, pos_in,
-			file_out, pos_out, len, remap_flags);
-	if (ret < 0)
-		return ret;
-
-	fsnotify_access(file_in);
-	fsnotify_modify(file_out);
-	return ret;
-}
-EXPORT_SYMBOL(do_clone_file_range);
-
-loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
-			    struct file *file_out, loff_t pos_out,
-			    loff_t len, unsigned int remap_flags)
-{
-	loff_t ret;
-
-	file_start_write(file_out);
-	ret = do_clone_file_range(file_in, pos_in, file_out, pos_out, len,
-				  remap_flags);
-	file_end_write(file_out);
-
-	return ret;
-}
-EXPORT_SYMBOL(vfs_clone_file_range);
-
-/* Check whether we are allowed to dedupe the destination file */
-static bool allow_file_dedupe(struct file *file)
-{
-	if (capable(CAP_SYS_ADMIN))
-		return true;
-	if (file->f_mode & FMODE_WRITE)
-		return true;
-	if (uid_eq(current_fsuid(), file_inode(file)->i_uid))
-		return true;
-	if (!inode_permission(file_inode(file), MAY_WRITE))
-		return true;
-	return false;
-}
-
-loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
-				 struct file *dst_file, loff_t dst_pos,
-				 loff_t len, unsigned int remap_flags)
-{
-	loff_t ret;
-
-	WARN_ON_ONCE(remap_flags & ~(REMAP_FILE_DEDUP |
-				     REMAP_FILE_CAN_SHORTEN));
-
-	ret = mnt_want_write_file(dst_file);
-	if (ret)
-		return ret;
-
-	ret = remap_verify_area(dst_file, dst_pos, len, true);
-	if (ret < 0)
-		goto out_drop_write;
-
-	ret = -EPERM;
-	if (!allow_file_dedupe(dst_file))
-		goto out_drop_write;
-
-	ret = -EXDEV;
-	if (src_file->f_path.mnt != dst_file->f_path.mnt)
-		goto out_drop_write;
-
-	ret = -EISDIR;
-	if (S_ISDIR(file_inode(dst_file)->i_mode))
-		goto out_drop_write;
-
-	ret = -EINVAL;
-	if (!dst_file->f_op->remap_file_range)
-		goto out_drop_write;
-
-	if (len == 0) {
-		ret = 0;
-		goto out_drop_write;
-	}
-
-	ret = dst_file->f_op->remap_file_range(src_file, src_pos, dst_file,
-			dst_pos, len, remap_flags | REMAP_FILE_DEDUP);
-out_drop_write:
-	mnt_drop_write_file(dst_file);
-
-	return ret;
-}
-EXPORT_SYMBOL(vfs_dedupe_file_range_one);
-
-int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same)
-{
-	struct file_dedupe_range_info *info;
-	struct inode *src = file_inode(file);
-	u64 off;
-	u64 len;
-	int i;
-	int ret;
-	u16 count = same->dest_count;
-	loff_t deduped;
-
-	if (!(file->f_mode & FMODE_READ))
-		return -EINVAL;
-
-	if (same->reserved1 || same->reserved2)
-		return -EINVAL;
-
-	off = same->src_offset;
-	len = same->src_length;
-
-	if (S_ISDIR(src->i_mode))
-		return -EISDIR;
-
-	if (!S_ISREG(src->i_mode))
-		return -EINVAL;
-
-	if (!file->f_op->remap_file_range)
-		return -EOPNOTSUPP;
-
-	ret = remap_verify_area(file, off, len, false);
-	if (ret < 0)
-		return ret;
-	ret = 0;
-
-	if (off + len > i_size_read(src))
-		return -EINVAL;
-
-	/* Arbitrary 1G limit on a single dedupe request, can be raised. */
-	len = min_t(u64, len, 1 << 30);
-
-	/* pre-format output fields to sane values */
-	for (i = 0; i < count; i++) {
-		same->info[i].bytes_deduped = 0ULL;
-		same->info[i].status = FILE_DEDUPE_RANGE_SAME;
-	}
-
-	for (i = 0, info = same->info; i < count; i++, info++) {
-		struct fd dst_fd = fdget(info->dest_fd);
-		struct file *dst_file = dst_fd.file;
-
-		if (!dst_file) {
-			info->status = -EBADF;
-			goto next_loop;
-		}
-
-		if (info->reserved) {
-			info->status = -EINVAL;
-			goto next_fdput;
-		}
-
-		deduped = vfs_dedupe_file_range_one(file, off, dst_file,
-						    info->dest_offset, len,
-						    REMAP_FILE_CAN_SHORTEN);
-		if (deduped == -EBADE)
-			info->status = FILE_DEDUPE_RANGE_DIFFERS;
-		else if (deduped < 0)
-			info->status = deduped;
-		else
-			info->bytes_deduped = len;
-
-next_fdput:
-		fdput(dst_fd);
-next_loop:
-		if (fatal_signal_pending(current))
-			break;
-	}
-	return ret;
-}
-EXPORT_SYMBOL(vfs_dedupe_file_range);
diff --git a/fs/remap_range.c b/fs/remap_range.c
index f0a8c7065d5b..e6099beefa97 100644
--- a/fs/remap_range.c
+++ b/fs/remap_range.c
@@ -26,9 +26,9 @@
  * Returns appropriate error code that caller should return or
  * zero in case the clone should be allowed.
  */
-int generic_remap_checks(struct file *file_in, loff_t pos_in,
-			 struct file *file_out, loff_t pos_out,
-			 loff_t *req_count, unsigned int remap_flags)
+static int generic_remap_checks(struct file *file_in, loff_t pos_in,
+				struct file *file_out, loff_t pos_out,
+				loff_t *req_count, unsigned int remap_flags)
 {
 	struct inode *inode_in = file_in->f_mapping->host;
 	struct inode *inode_out = file_out->f_mapping->host;
@@ -95,3 +95,477 @@ int generic_remap_checks(struct file *file_in, loff_t pos_in,
 	*req_count = count;
 	return 0;
 }
+
+static int remap_verify_area(struct file *file, loff_t pos, loff_t len,
+			     bool write)
+{
+	struct inode *inode = file_inode(file);
+
+	if (unlikely(pos < 0 || len < 0))
+		return -EINVAL;
+
+	if (unlikely((loff_t) (pos + len) < 0))
+		return -EINVAL;
+
+	if (unlikely(inode->i_flctx && mandatory_lock(inode))) {
+		loff_t end = len ? pos + len - 1 : OFFSET_MAX;
+		int retval;
+
+		retval = locks_mandatory_area(inode, file, pos, end,
+				write ? F_WRLCK : F_RDLCK);
+		if (retval < 0)
+			return retval;
+	}
+
+	return security_file_permission(file, write ? MAY_WRITE : MAY_READ);
+}
+
+/*
+ * Ensure that we don't remap a partial EOF block in the middle of something
+ * else.  Assume that the offsets have already been checked for block
+ * alignment.
+ *
+ * For clone we only link a partial EOF block above or at the destination file's
+ * EOF.  For deduplication we accept a partial EOF block only if it ends at the
+ * destination file's EOF (can not link it into the middle of a file).
+ *
+ * Shorten the request if possible.
+ */
+static int generic_remap_check_len(struct inode *inode_in,
+				   struct inode *inode_out,
+				   loff_t pos_out,
+				   loff_t *len,
+				   unsigned int remap_flags)
+{
+	u64 blkmask = i_blocksize(inode_in) - 1;
+	loff_t new_len = *len;
+
+	if ((*len & blkmask) == 0)
+		return 0;
+
+	if (pos_out + *len < i_size_read(inode_out))
+		new_len &= ~blkmask;
+
+	if (new_len == *len)
+		return 0;
+
+	if (remap_flags & REMAP_FILE_CAN_SHORTEN) {
+		*len = new_len;
+		return 0;
+	}
+
+	return (remap_flags & REMAP_FILE_DEDUP) ? -EBADE : -EINVAL;
+}
+
+/* Read a page's worth of file data into the page cache. */
+static struct page *vfs_dedupe_get_page(struct inode *inode, loff_t offset)
+{
+	struct page *page;
+
+	page = read_mapping_page(inode->i_mapping, offset >> PAGE_SHIFT, NULL);
+	if (IS_ERR(page))
+		return page;
+	if (!PageUptodate(page)) {
+		put_page(page);
+		return ERR_PTR(-EIO);
+	}
+	return page;
+}
+
+/*
+ * Lock two pages, ensuring that we lock in offset order if the pages are from
+ * the same file.
+ */
+static void vfs_lock_two_pages(struct page *page1, struct page *page2)
+{
+	/* Always lock in order of increasing index. */
+	if (page1->index > page2->index)
+		swap(page1, page2);
+
+	lock_page(page1);
+	if (page1 != page2)
+		lock_page(page2);
+}
+
+/* Unlock two pages, being careful not to unlock the same page twice. */
+static void vfs_unlock_two_pages(struct page *page1, struct page *page2)
+{
+	unlock_page(page1);
+	if (page1 != page2)
+		unlock_page(page2);
+}
+
+/*
+ * Compare extents of two files to see if they are the same.
+ * Caller must have locked both inodes to prevent write races.
+ */
+static int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
+					 struct inode *dest, loff_t destoff,
+					 loff_t len, bool *is_same)
+{
+	loff_t src_poff;
+	loff_t dest_poff;
+	void *src_addr;
+	void *dest_addr;
+	struct page *src_page;
+	struct page *dest_page;
+	loff_t cmp_len;
+	bool same;
+	int error;
+
+	error = -EINVAL;
+	same = true;
+	while (len) {
+		src_poff = srcoff & (PAGE_SIZE - 1);
+		dest_poff = destoff & (PAGE_SIZE - 1);
+		cmp_len = min(PAGE_SIZE - src_poff,
+			      PAGE_SIZE - dest_poff);
+		cmp_len = min(cmp_len, len);
+		if (cmp_len <= 0)
+			goto out_error;
+
+		src_page = vfs_dedupe_get_page(src, srcoff);
+		if (IS_ERR(src_page)) {
+			error = PTR_ERR(src_page);
+			goto out_error;
+		}
+		dest_page = vfs_dedupe_get_page(dest, destoff);
+		if (IS_ERR(dest_page)) {
+			error = PTR_ERR(dest_page);
+			put_page(src_page);
+			goto out_error;
+		}
+
+		vfs_lock_two_pages(src_page, dest_page);
+
+		/*
+		 * Now that we've locked both pages, make sure they're still
+		 * mapped to the file data we're interested in.  If not,
+		 * someone is invalidating pages on us and we lose.
+		 */
+		if (!PageUptodate(src_page) || !PageUptodate(dest_page) ||
+		    src_page->mapping != src->i_mapping ||
+		    dest_page->mapping != dest->i_mapping) {
+			same = false;
+			goto unlock;
+		}
+
+		src_addr = kmap_atomic(src_page);
+		dest_addr = kmap_atomic(dest_page);
+
+		flush_dcache_page(src_page);
+		flush_dcache_page(dest_page);
+
+		if (memcmp(src_addr + src_poff, dest_addr + dest_poff, cmp_len))
+			same = false;
+
+		kunmap_atomic(dest_addr);
+		kunmap_atomic(src_addr);
+unlock:
+		vfs_unlock_two_pages(src_page, dest_page);
+		put_page(dest_page);
+		put_page(src_page);
+
+		if (!same)
+			break;
+
+		srcoff += cmp_len;
+		destoff += cmp_len;
+		len -= cmp_len;
+	}
+
+	*is_same = same;
+	return 0;
+
+out_error:
+	return error;
+}
+
+/*
+ * Check that the two inodes are eligible for cloning, the ranges make
+ * sense, and then flush all dirty data.  Caller must ensure that the
+ * inodes have been locked against any other modifications.
+ *
+ * If there's an error, then the usual negative error code is returned.
+ * Otherwise returns 0 with *len set to the request length.
+ */
+int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
+				  struct file *file_out, loff_t pos_out,
+				  loff_t *len, unsigned int remap_flags)
+{
+	struct inode *inode_in = file_inode(file_in);
+	struct inode *inode_out = file_inode(file_out);
+	bool same_inode = (inode_in == inode_out);
+	int ret;
+
+	/* Don't touch certain kinds of inodes */
+	if (IS_IMMUTABLE(inode_out))
+		return -EPERM;
+
+	if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out))
+		return -ETXTBSY;
+
+	/* Don't reflink dirs, pipes, sockets... */
+	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
+		return -EISDIR;
+	if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
+		return -EINVAL;
+
+	/* Zero length dedupe exits immediately; reflink goes to EOF. */
+	if (*len == 0) {
+		loff_t isize = i_size_read(inode_in);
+
+		if ((remap_flags & REMAP_FILE_DEDUP) || pos_in == isize)
+			return 0;
+		if (pos_in > isize)
+			return -EINVAL;
+		*len = isize - pos_in;
+		if (*len == 0)
+			return 0;
+	}
+
+	/* Check that we don't violate system file offset limits. */
+	ret = generic_remap_checks(file_in, pos_in, file_out, pos_out, len,
+			remap_flags);
+	if (ret)
+		return ret;
+
+	/* Wait for the completion of any pending IOs on both files */
+	inode_dio_wait(inode_in);
+	if (!same_inode)
+		inode_dio_wait(inode_out);
+
+	ret = filemap_write_and_wait_range(inode_in->i_mapping,
+			pos_in, pos_in + *len - 1);
+	if (ret)
+		return ret;
+
+	ret = filemap_write_and_wait_range(inode_out->i_mapping,
+			pos_out, pos_out + *len - 1);
+	if (ret)
+		return ret;
+
+	/*
+	 * Check that the extents are the same.
+	 */
+	if (remap_flags & REMAP_FILE_DEDUP) {
+		bool		is_same = false;
+
+		ret = vfs_dedupe_file_range_compare(inode_in, pos_in,
+				inode_out, pos_out, *len, &is_same);
+		if (ret)
+			return ret;
+		if (!is_same)
+			return -EBADE;
+	}
+
+	ret = generic_remap_check_len(inode_in, inode_out, pos_out, len,
+			remap_flags);
+	if (ret)
+		return ret;
+
+	/* If can't alter the file contents, we're done. */
+	if (!(remap_flags & REMAP_FILE_DEDUP))
+		ret = file_modified(file_out);
+
+	return ret;
+}
+EXPORT_SYMBOL(generic_remap_file_range_prep);
+
+loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
+			   struct file *file_out, loff_t pos_out,
+			   loff_t len, unsigned int remap_flags)
+{
+	loff_t ret;
+
+	WARN_ON_ONCE(remap_flags & REMAP_FILE_DEDUP);
+
+	/*
+	 * FICLONE/FICLONERANGE ioctls enforce that src and dest files are on
+	 * the same mount. Practically, they only need to be on the same file
+	 * system.
+	 */
+	if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb)
+		return -EXDEV;
+
+	ret = generic_file_rw_checks(file_in, file_out);
+	if (ret < 0)
+		return ret;
+
+	if (!file_in->f_op->remap_file_range)
+		return -EOPNOTSUPP;
+
+	ret = remap_verify_area(file_in, pos_in, len, false);
+	if (ret)
+		return ret;
+
+	ret = remap_verify_area(file_out, pos_out, len, true);
+	if (ret)
+		return ret;
+
+	ret = file_in->f_op->remap_file_range(file_in, pos_in,
+			file_out, pos_out, len, remap_flags);
+	if (ret < 0)
+		return ret;
+
+	fsnotify_access(file_in);
+	fsnotify_modify(file_out);
+	return ret;
+}
+EXPORT_SYMBOL(do_clone_file_range);
+
+loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
+			    struct file *file_out, loff_t pos_out,
+			    loff_t len, unsigned int remap_flags)
+{
+	loff_t ret;
+
+	file_start_write(file_out);
+	ret = do_clone_file_range(file_in, pos_in, file_out, pos_out, len,
+				  remap_flags);
+	file_end_write(file_out);
+
+	return ret;
+}
+EXPORT_SYMBOL(vfs_clone_file_range);
+
+/* Check whether we are allowed to dedupe the destination file */
+static bool allow_file_dedupe(struct file *file)
+{
+	if (capable(CAP_SYS_ADMIN))
+		return true;
+	if (file->f_mode & FMODE_WRITE)
+		return true;
+	if (uid_eq(current_fsuid(), file_inode(file)->i_uid))
+		return true;
+	if (!inode_permission(file_inode(file), MAY_WRITE))
+		return true;
+	return false;
+}
+
+loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
+				 struct file *dst_file, loff_t dst_pos,
+				 loff_t len, unsigned int remap_flags)
+{
+	loff_t ret;
+
+	WARN_ON_ONCE(remap_flags & ~(REMAP_FILE_DEDUP |
+				     REMAP_FILE_CAN_SHORTEN));
+
+	ret = mnt_want_write_file(dst_file);
+	if (ret)
+		return ret;
+
+	ret = remap_verify_area(dst_file, dst_pos, len, true);
+	if (ret < 0)
+		goto out_drop_write;
+
+	ret = -EPERM;
+	if (!allow_file_dedupe(dst_file))
+		goto out_drop_write;
+
+	ret = -EXDEV;
+	if (src_file->f_path.mnt != dst_file->f_path.mnt)
+		goto out_drop_write;
+
+	ret = -EISDIR;
+	if (S_ISDIR(file_inode(dst_file)->i_mode))
+		goto out_drop_write;
+
+	ret = -EINVAL;
+	if (!dst_file->f_op->remap_file_range)
+		goto out_drop_write;
+
+	if (len == 0) {
+		ret = 0;
+		goto out_drop_write;
+	}
+
+	ret = dst_file->f_op->remap_file_range(src_file, src_pos, dst_file,
+			dst_pos, len, remap_flags | REMAP_FILE_DEDUP);
+out_drop_write:
+	mnt_drop_write_file(dst_file);
+
+	return ret;
+}
+EXPORT_SYMBOL(vfs_dedupe_file_range_one);
+
+int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same)
+{
+	struct file_dedupe_range_info *info;
+	struct inode *src = file_inode(file);
+	u64 off;
+	u64 len;
+	int i;
+	int ret;
+	u16 count = same->dest_count;
+	loff_t deduped;
+
+	if (!(file->f_mode & FMODE_READ))
+		return -EINVAL;
+
+	if (same->reserved1 || same->reserved2)
+		return -EINVAL;
+
+	off = same->src_offset;
+	len = same->src_length;
+
+	if (S_ISDIR(src->i_mode))
+		return -EISDIR;
+
+	if (!S_ISREG(src->i_mode))
+		return -EINVAL;
+
+	if (!file->f_op->remap_file_range)
+		return -EOPNOTSUPP;
+
+	ret = remap_verify_area(file, off, len, false);
+	if (ret < 0)
+		return ret;
+	ret = 0;
+
+	if (off + len > i_size_read(src))
+		return -EINVAL;
+
+	/* Arbitrary 1G limit on a single dedupe request, can be raised. */
+	len = min_t(u64, len, 1 << 30);
+
+	/* pre-format output fields to sane values */
+	for (i = 0; i < count; i++) {
+		same->info[i].bytes_deduped = 0ULL;
+		same->info[i].status = FILE_DEDUPE_RANGE_SAME;
+	}
+
+	for (i = 0, info = same->info; i < count; i++, info++) {
+		struct fd dst_fd = fdget(info->dest_fd);
+		struct file *dst_file = dst_fd.file;
+
+		if (!dst_file) {
+			info->status = -EBADF;
+			goto next_loop;
+		}
+
+		if (info->reserved) {
+			info->status = -EINVAL;
+			goto next_fdput;
+		}
+
+		deduped = vfs_dedupe_file_range_one(file, off, dst_file,
+						    info->dest_offset, len,
+						    REMAP_FILE_CAN_SHORTEN);
+		if (deduped == -EBADE)
+			info->status = FILE_DEDUPE_RANGE_DIFFERS;
+		else if (deduped < 0)
+			info->status = deduped;
+		else
+			info->bytes_deduped = len;
+
+next_fdput:
+		fdput(dst_fd);
+next_loop:
+		if (fatal_signal_pending(current))
+			break;
+	}
+	return ret;
+}
+EXPORT_SYMBOL(vfs_dedupe_file_range);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index eea754a8dd67..073da53b59b0 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3009,9 +3009,6 @@ extern int sb_min_blocksize(struct super_block *, int);
 extern int generic_file_mmap(struct file *, struct vm_area_struct *);
 extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
 extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *);
-extern int generic_remap_checks(struct file *file_in, loff_t pos_in,
-				struct file *file_out, loff_t pos_out,
-				loff_t *count, unsigned int remap_flags);
 extern int generic_write_check_limits(struct file *file, loff_t pos,
 		loff_t *count);
 extern int generic_file_rw_checks(struct file *file_in, struct file *file_out);
-- 
cgit v1.2.3


From 407e9c63ee571f44a2dfb0828fc30daa02abb6dc Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Thu, 15 Oct 2020 09:21:17 -0700
Subject: vfs: move the generic write and copy checks out of mm

The generic write check helpers also don't have much to do with the page
cache, so move them to the vfs.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/read_write.c    | 143 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/fs.h |   3 --
 mm/filemap.c       | 143 -----------------------------------------------------
 3 files changed, 143 insertions(+), 146 deletions(-)

(limited to 'include/linux')

diff --git a/fs/read_write.c b/fs/read_write.c
index f0877f1c0c49..016444255d3e 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1701,6 +1701,59 @@ static ssize_t do_copy_file_range(struct file *file_in, loff_t pos_in,
 				       flags);
 }
 
+/*
+ * Performs necessary checks before doing a file copy
+ *
+ * Can adjust amount of bytes to copy via @req_count argument.
+ * Returns appropriate error code that caller should return or
+ * zero in case the copy should be allowed.
+ */
+static int generic_copy_file_checks(struct file *file_in, loff_t pos_in,
+				    struct file *file_out, loff_t pos_out,
+				    size_t *req_count, unsigned int flags)
+{
+	struct inode *inode_in = file_inode(file_in);
+	struct inode *inode_out = file_inode(file_out);
+	uint64_t count = *req_count;
+	loff_t size_in;
+	int ret;
+
+	ret = generic_file_rw_checks(file_in, file_out);
+	if (ret)
+		return ret;
+
+	/* Don't touch certain kinds of inodes */
+	if (IS_IMMUTABLE(inode_out))
+		return -EPERM;
+
+	if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out))
+		return -ETXTBSY;
+
+	/* Ensure offsets don't wrap. */
+	if (pos_in + count < pos_in || pos_out + count < pos_out)
+		return -EOVERFLOW;
+
+	/* Shorten the copy to EOF */
+	size_in = i_size_read(inode_in);
+	if (pos_in >= size_in)
+		count = 0;
+	else
+		count = min(count, size_in - (uint64_t)pos_in);
+
+	ret = generic_write_check_limits(file_out, pos_out, &count);
+	if (ret)
+		return ret;
+
+	/* Don't allow overlapped copying within the same file. */
+	if (inode_in == inode_out &&
+	    pos_out + count > pos_in &&
+	    pos_out < pos_in + count)
+		return -EINVAL;
+
+	*req_count = count;
+	return 0;
+}
+
 /*
  * copy_file_range() differs from regular file read and write in that it
  * specifically allows return partial success.  When it does so is up to
@@ -1832,3 +1885,93 @@ out1:
 out2:
 	return ret;
 }
+
+/*
+ * Don't operate on ranges the page cache doesn't support, and don't exceed the
+ * LFS limits.  If pos is under the limit it becomes a short access.  If it
+ * exceeds the limit we return -EFBIG.
+ */
+int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count)
+{
+	struct inode *inode = file->f_mapping->host;
+	loff_t max_size = inode->i_sb->s_maxbytes;
+	loff_t limit = rlimit(RLIMIT_FSIZE);
+
+	if (limit != RLIM_INFINITY) {
+		if (pos >= limit) {
+			send_sig(SIGXFSZ, current, 0);
+			return -EFBIG;
+		}
+		*count = min(*count, limit - pos);
+	}
+
+	if (!(file->f_flags & O_LARGEFILE))
+		max_size = MAX_NON_LFS;
+
+	if (unlikely(pos >= max_size))
+		return -EFBIG;
+
+	*count = min(*count, max_size - pos);
+
+	return 0;
+}
+
+/*
+ * Performs necessary checks before doing a write
+ *
+ * Can adjust writing position or amount of bytes to write.
+ * Returns appropriate error code that caller should return or
+ * zero in case that write should be allowed.
+ */
+ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file->f_mapping->host;
+	loff_t count;
+	int ret;
+
+	if (IS_SWAPFILE(inode))
+		return -ETXTBSY;
+
+	if (!iov_iter_count(from))
+		return 0;
+
+	/* FIXME: this is for backwards compatibility with 2.4 */
+	if (iocb->ki_flags & IOCB_APPEND)
+		iocb->ki_pos = i_size_read(inode);
+
+	if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT))
+		return -EINVAL;
+
+	count = iov_iter_count(from);
+	ret = generic_write_check_limits(file, iocb->ki_pos, &count);
+	if (ret)
+		return ret;
+
+	iov_iter_truncate(from, count);
+	return iov_iter_count(from);
+}
+EXPORT_SYMBOL(generic_write_checks);
+
+/*
+ * Performs common checks before doing a file copy/clone
+ * from @file_in to @file_out.
+ */
+int generic_file_rw_checks(struct file *file_in, struct file *file_out)
+{
+	struct inode *inode_in = file_inode(file_in);
+	struct inode *inode_out = file_inode(file_out);
+
+	/* Don't copy dirs, pipes, sockets... */
+	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
+		return -EISDIR;
+	if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
+		return -EINVAL;
+
+	if (!(file_in->f_mode & FMODE_READ) ||
+	    !(file_out->f_mode & FMODE_WRITE) ||
+	    (file_out->f_flags & O_APPEND))
+		return -EBADF;
+
+	return 0;
+}
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 073da53b59b0..8fb063ab7d50 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3012,9 +3012,6 @@ extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *);
 extern int generic_write_check_limits(struct file *file, loff_t pos,
 		loff_t *count);
 extern int generic_file_rw_checks(struct file *file_in, struct file *file_out);
-extern int generic_copy_file_checks(struct file *file_in, loff_t pos_in,
-				    struct file *file_out, loff_t pos_out,
-				    size_t *count, unsigned int flags);
 extern ssize_t generic_file_buffered_read(struct kiocb *iocb,
 		struct iov_iter *to, ssize_t already_read);
 extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *);
diff --git a/mm/filemap.c b/mm/filemap.c
index cf20e5aeb11b..9962fd682f20 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3093,149 +3093,6 @@ struct page *read_cache_page_gfp(struct address_space *mapping,
 }
 EXPORT_SYMBOL(read_cache_page_gfp);
 
-/*
- * Don't operate on ranges the page cache doesn't support, and don't exceed the
- * LFS limits.  If pos is under the limit it becomes a short access.  If it
- * exceeds the limit we return -EFBIG.
- */
-int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count)
-{
-	struct inode *inode = file->f_mapping->host;
-	loff_t max_size = inode->i_sb->s_maxbytes;
-	loff_t limit = rlimit(RLIMIT_FSIZE);
-
-	if (limit != RLIM_INFINITY) {
-		if (pos >= limit) {
-			send_sig(SIGXFSZ, current, 0);
-			return -EFBIG;
-		}
-		*count = min(*count, limit - pos);
-	}
-
-	if (!(file->f_flags & O_LARGEFILE))
-		max_size = MAX_NON_LFS;
-
-	if (unlikely(pos >= max_size))
-		return -EFBIG;
-
-	*count = min(*count, max_size - pos);
-
-	return 0;
-}
-
-/*
- * Performs necessary checks before doing a write
- *
- * Can adjust writing position or amount of bytes to write.
- * Returns appropriate error code that caller should return or
- * zero in case that write should be allowed.
- */
-inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
-{
-	struct file *file = iocb->ki_filp;
-	struct inode *inode = file->f_mapping->host;
-	loff_t count;
-	int ret;
-
-	if (IS_SWAPFILE(inode))
-		return -ETXTBSY;
-
-	if (!iov_iter_count(from))
-		return 0;
-
-	/* FIXME: this is for backwards compatibility with 2.4 */
-	if (iocb->ki_flags & IOCB_APPEND)
-		iocb->ki_pos = i_size_read(inode);
-
-	if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT))
-		return -EINVAL;
-
-	count = iov_iter_count(from);
-	ret = generic_write_check_limits(file, iocb->ki_pos, &count);
-	if (ret)
-		return ret;
-
-	iov_iter_truncate(from, count);
-	return iov_iter_count(from);
-}
-EXPORT_SYMBOL(generic_write_checks);
-
-/*
- * Performs common checks before doing a file copy/clone
- * from @file_in to @file_out.
- */
-int generic_file_rw_checks(struct file *file_in, struct file *file_out)
-{
-	struct inode *inode_in = file_inode(file_in);
-	struct inode *inode_out = file_inode(file_out);
-
-	/* Don't copy dirs, pipes, sockets... */
-	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
-		return -EISDIR;
-	if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
-		return -EINVAL;
-
-	if (!(file_in->f_mode & FMODE_READ) ||
-	    !(file_out->f_mode & FMODE_WRITE) ||
-	    (file_out->f_flags & O_APPEND))
-		return -EBADF;
-
-	return 0;
-}
-
-/*
- * Performs necessary checks before doing a file copy
- *
- * Can adjust amount of bytes to copy via @req_count argument.
- * Returns appropriate error code that caller should return or
- * zero in case the copy should be allowed.
- */
-int generic_copy_file_checks(struct file *file_in, loff_t pos_in,
-			     struct file *file_out, loff_t pos_out,
-			     size_t *req_count, unsigned int flags)
-{
-	struct inode *inode_in = file_inode(file_in);
-	struct inode *inode_out = file_inode(file_out);
-	uint64_t count = *req_count;
-	loff_t size_in;
-	int ret;
-
-	ret = generic_file_rw_checks(file_in, file_out);
-	if (ret)
-		return ret;
-
-	/* Don't touch certain kinds of inodes */
-	if (IS_IMMUTABLE(inode_out))
-		return -EPERM;
-
-	if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out))
-		return -ETXTBSY;
-
-	/* Ensure offsets don't wrap. */
-	if (pos_in + count < pos_in || pos_out + count < pos_out)
-		return -EOVERFLOW;
-
-	/* Shorten the copy to EOF */
-	size_in = i_size_read(inode_in);
-	if (pos_in >= size_in)
-		count = 0;
-	else
-		count = min(count, size_in - (uint64_t)pos_in);
-
-	ret = generic_write_check_limits(file_out, pos_out, &count);
-	if (ret)
-		return ret;
-
-	/* Don't allow overlapped copying within the same file. */
-	if (inode_in == inode_out &&
-	    pos_out + count > pos_in &&
-	    pos_out < pos_in + count)
-		return -EINVAL;
-
-	*req_count = count;
-	return 0;
-}
-
 int pagecache_write_begin(struct file *file, struct address_space *mapping,
 				loff_t pos, unsigned len, unsigned flags,
 				struct page **pagep, void **fsdata)
-- 
cgit v1.2.3


From ac80cd17a615e472e3dcff0a5446a58540e64e6d Mon Sep 17 00:00:00 2001
From: Jianxin Xiong <jianxin.xiong@intel.com>
Date: Wed, 14 Oct 2020 09:16:01 -0700
Subject: dma-buf: Clarify that dma-buf sg lists are page aligned
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The dma-buf API have been used under the assumption that the sg lists
returned from dma_buf_map_attachment() are fully page aligned. Lots of
stuff can break otherwise all over the place. Clarify this in the
documentation and add a check when DMA API debug is enabled.

Signed-off-by: Jianxin Xiong <jianxin.xiong@intel.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/1602692161-107096-1-git-send-email-jianxin.xiong@intel.com
---
 drivers/dma-buf/dma-buf.c | 21 +++++++++++++++++++++
 include/linux/dma-buf.h   |  3 ++-
 2 files changed, 23 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index a6ba4d598f0e..9db211a2b6cb 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -849,6 +849,9 @@ EXPORT_SYMBOL_GPL(dma_buf_unpin);
  * Returns sg_table containing the scatterlist to be returned; returns ERR_PTR
  * on error. May return -EINTR if it is interrupted by a signal.
  *
+ * On success, the DMA addresses and lengths in the returned scatterlist are
+ * PAGE_SIZE aligned.
+ *
  * A mapping must be unmapped by using dma_buf_unmap_attachment(). Note that
  * the underlying backing storage is pinned for as long as a mapping exists,
  * therefore users/importers should not hold onto a mapping for undue amounts of
@@ -902,6 +905,24 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach,
 		attach->dir = direction;
 	}
 
+#ifdef CONFIG_DMA_API_DEBUG
+	{
+		struct scatterlist *sg;
+		u64 addr;
+		int len;
+		int i;
+
+		for_each_sgtable_dma_sg(sg_table, sg, i) {
+			addr = sg_dma_address(sg);
+			len = sg_dma_len(sg);
+			if (!PAGE_ALIGNED(addr) || !PAGE_ALIGNED(len)) {
+				pr_debug("%s: addr %llx or len %x is not page aligned!\n",
+					 __func__, addr, len);
+			}
+		}
+	}
+#endif /* CONFIG_DMA_API_DEBUG */
+
 	return sg_table;
 }
 EXPORT_SYMBOL_GPL(dma_buf_map_attachment);
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index cf77cc15f4ba..03875eaed51a 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -146,7 +146,8 @@ struct dma_buf_ops {
 	 *
 	 * A &sg_table scatter list of or the backing storage of the DMA buffer,
 	 * already mapped into the device address space of the &device attached
-	 * with the provided &dma_buf_attachment.
+	 * with the provided &dma_buf_attachment. The addresses and lengths in
+	 * the scatter list are PAGE_SIZE aligned.
 	 *
 	 * On failure, returns a negative error value wrapped into a pointer.
 	 * May also return -EINTR when a signal was received while being
-- 
cgit v1.2.3


From 3e2ac9798e13ad1f52d735ea2ea1d252cb140ae5 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Mon, 5 Oct 2020 10:58:18 +0200
Subject: PM / devfreq: remove a duplicated kernel-doc markup

The update_devfreq() is also documented at devfreq.c, which
has a more complete note.

So, drop the duplicated markup, in order to avoid this
warning:
	.../Documentation/driver-api/device_link.rst: WARNING: Duplicate C declaration, also defined in 'driver-api/infrastructure'.
	Declaration is 'device_link_state'.

(and to cause a problem with cross-references to it)

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 include/linux/devfreq.h | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index 2f4a74efa6be..121a2430d7f7 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -228,12 +228,7 @@ int devfreq_resume_device(struct devfreq *devfreq);
 void devfreq_suspend(void);
 void devfreq_resume(void);
 
-/**
- * update_devfreq() - Reevaluate the device and configure frequency
- * @devfreq:	the devfreq device
- *
- * Note: devfreq->lock must be held
- */
+/* update_devfreq() - Reevaluate the device and configure frequency */
 int update_devfreq(struct devfreq *devfreq);
 
 /* Helper functions for devfreq user device driver with OPP. */
-- 
cgit v1.2.3


From bae314dd5d8dfdd90ee584003a0f8c06e1bf3ea2 Mon Sep 17 00:00:00 2001
From: Daniel Lezcano <daniel.lezcano@linaro.org>
Date: Thu, 15 Oct 2020 16:44:27 +0200
Subject: cpuidle: Remove pointless stub

The cpuidle.h header is declaring a function with an empty stub
for the cpuidle disabled case, but that function is only called
by cpuidle governors which depend on cpuidle anyway.

In other words, the function is only called when cpuidle is enabled,
so there is no need for the stub.

Remove the pointless stub.

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
[ rjw: Changelog edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/cpuidle.h | 5 -----
 1 file changed, 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index ed0da0e58e8b..bd605b5585cf 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -271,13 +271,8 @@ struct cpuidle_governor {
 	void (*reflect)		(struct cpuidle_device *dev, int index);
 };
 
-#ifdef CONFIG_CPU_IDLE
 extern int cpuidle_register_governor(struct cpuidle_governor *gov);
 extern s64 cpuidle_governor_latency_req(unsigned int cpu);
-#else
-static inline int cpuidle_register_governor(struct cpuidle_governor *gov)
-{return 0;}
-#endif
 
 #define __CPU_PM_CPU_IDLE_ENTER(low_level_idle_enter,			\
 				idx,					\
-- 
cgit v1.2.3


From f1e8d7560d3051b38f73a0cf6acc1b0bf5305ad9 Mon Sep 17 00:00:00 2001
From: Zhang Rui <rui.zhang@intel.com>
Date: Tue, 13 Oct 2020 15:42:41 +0800
Subject: powercap/intel_rapl: enumerate Psys RAPL domain together with package
 RAPL domain

On multi-package systems, the Psys MSR is only valid for CPUs on
specific package (master package). The current code makes the
assumption that package 0 is the master package, but this is not
true on new platforms like SPR.

Fix the problem by emuerating the Psys RAPL domain for every
package, so CPUs in slave packages will read 0 for the Psys energy
counter and only CPUs in master packages can get a valid reading
and register the Psys RAPL domain.

The sysfs I/F for the Psys RAPL domain is not changed.

Signed-off-by: Zhang Rui <rui.zhang@intel.com>
[ rjw: Subject and changelog edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/powercap/intel_rapl_common.c | 80 +++++++-----------------------------
 drivers/powercap/intel_rapl_msr.c    |  5 +--
 include/linux/intel_rapl.h           |  7 ++--
 3 files changed, 18 insertions(+), 74 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c
index 2651ea6cd6d3..0b2830efc574 100644
--- a/drivers/powercap/intel_rapl_common.c
+++ b/drivers/powercap/intel_rapl_common.c
@@ -544,7 +544,14 @@ static void rapl_init_domains(struct rapl_package *rp)
 			continue;
 
 		rd->rp = rp;
-		rd->name = rapl_domain_names[i];
+
+		if (i == RAPL_DOMAIN_PLATFORM && rp->id > 0) {
+			snprintf(rd->name, RAPL_DOMAIN_NAME_LENGTH, "psys-%d",
+				cpu_data(rp->lead_cpu).phys_proc_id);
+		} else
+			snprintf(rd->name, RAPL_DOMAIN_NAME_LENGTH, "%s",
+				rapl_domain_names[i]);
+
 		rd->id = i;
 		rd->rpl[0].prim_id = PL1_ENABLE;
 		rd->rpl[0].name = pl1_name;
@@ -1112,13 +1119,17 @@ static int rapl_package_register_powercap(struct rapl_package *rp)
 	}
 	/* now register domains as children of the socket/package */
 	for (rd = rp->domains; rd < rp->domains + rp->nr_domains; rd++) {
+		struct powercap_zone *parent = rp->power_zone;
+
 		if (rd->id == RAPL_DOMAIN_PACKAGE)
 			continue;
+		if (rd->id == RAPL_DOMAIN_PLATFORM)
+			parent = NULL;
 		/* number of power limits per domain varies */
 		nr_pl = find_nr_power_limit(rd);
 		power_zone = powercap_register_zone(&rd->power_zone,
 						    rp->priv->control_type,
-						    rd->name, rp->power_zone,
+						    rd->name, parent,
 						    &zone_ops[rd->id], nr_pl,
 						    &constraint_ops);
 
@@ -1145,67 +1156,6 @@ err_cleanup:
 	return ret;
 }
 
-int rapl_add_platform_domain(struct rapl_if_priv *priv)
-{
-	struct rapl_domain *rd;
-	struct powercap_zone *power_zone;
-	struct reg_action ra;
-	int ret;
-
-	ra.reg = priv->regs[RAPL_DOMAIN_PLATFORM][RAPL_DOMAIN_REG_STATUS];
-	ra.mask = ~0;
-	ret = priv->read_raw(0, &ra);
-	if (ret || !ra.value)
-		return -ENODEV;
-
-	ra.reg = priv->regs[RAPL_DOMAIN_PLATFORM][RAPL_DOMAIN_REG_LIMIT];
-	ra.mask = ~0;
-	ret = priv->read_raw(0, &ra);
-	if (ret || !ra.value)
-		return -ENODEV;
-
-	rd = kzalloc(sizeof(*rd), GFP_KERNEL);
-	if (!rd)
-		return -ENOMEM;
-
-	rd->name = rapl_domain_names[RAPL_DOMAIN_PLATFORM];
-	rd->id = RAPL_DOMAIN_PLATFORM;
-	rd->regs[RAPL_DOMAIN_REG_LIMIT] =
-	    priv->regs[RAPL_DOMAIN_PLATFORM][RAPL_DOMAIN_REG_LIMIT];
-	rd->regs[RAPL_DOMAIN_REG_STATUS] =
-	    priv->regs[RAPL_DOMAIN_PLATFORM][RAPL_DOMAIN_REG_STATUS];
-	rd->rpl[0].prim_id = PL1_ENABLE;
-	rd->rpl[0].name = pl1_name;
-	rd->rpl[1].prim_id = PL2_ENABLE;
-	rd->rpl[1].name = pl2_name;
-	rd->rp = rapl_find_package_domain(0, priv);
-
-	power_zone = powercap_register_zone(&rd->power_zone, priv->control_type,
-					    "psys", NULL,
-					    &zone_ops[RAPL_DOMAIN_PLATFORM],
-					    2, &constraint_ops);
-
-	if (IS_ERR(power_zone)) {
-		kfree(rd);
-		return PTR_ERR(power_zone);
-	}
-
-	priv->platform_rapl_domain = rd;
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(rapl_add_platform_domain);
-
-void rapl_remove_platform_domain(struct rapl_if_priv *priv)
-{
-	if (priv->platform_rapl_domain) {
-		powercap_unregister_zone(priv->control_type,
-				 &priv->platform_rapl_domain->power_zone);
-		kfree(priv->platform_rapl_domain);
-	}
-}
-EXPORT_SYMBOL_GPL(rapl_remove_platform_domain);
-
 static int rapl_check_domain(int cpu, int domain, struct rapl_package *rp)
 {
 	struct reg_action ra;
@@ -1215,11 +1165,9 @@ static int rapl_check_domain(int cpu, int domain, struct rapl_package *rp)
 	case RAPL_DOMAIN_PP0:
 	case RAPL_DOMAIN_PP1:
 	case RAPL_DOMAIN_DRAM:
+	case RAPL_DOMAIN_PLATFORM:
 		ra.reg = rp->priv->regs[domain][RAPL_DOMAIN_REG_STATUS];
 		break;
-	case RAPL_DOMAIN_PLATFORM:
-		/* PSYS(PLATFORM) is not a CPU domain, so avoid printng error */
-		return -EINVAL;
 	default:
 		pr_err("invalid domain id %d\n", domain);
 		return -EINVAL;
diff --git a/drivers/powercap/intel_rapl_msr.c b/drivers/powercap/intel_rapl_msr.c
index d2a2627507a9..1646808d354c 100644
--- a/drivers/powercap/intel_rapl_msr.c
+++ b/drivers/powercap/intel_rapl_msr.c
@@ -44,6 +44,7 @@ static struct rapl_if_priv rapl_msr_priv = {
 	.regs[RAPL_DOMAIN_PLATFORM] = {
 		MSR_PLATFORM_POWER_LIMIT, MSR_PLATFORM_ENERGY_STATUS, 0, 0, 0},
 	.limits[RAPL_DOMAIN_PACKAGE] = 2,
+	.limits[RAPL_DOMAIN_PLATFORM] = 2,
 };
 
 /* Handles CPU hotplug on multi-socket systems.
@@ -157,9 +158,6 @@ static int rapl_msr_probe(struct platform_device *pdev)
 		goto out;
 	rapl_msr_priv.pcap_rapl_online = ret;
 
-	/* Don't bail out if PSys is not supported */
-	rapl_add_platform_domain(&rapl_msr_priv);
-
 	return 0;
 
 out:
@@ -171,7 +169,6 @@ out:
 static int rapl_msr_remove(struct platform_device *pdev)
 {
 	cpuhp_remove_state(rapl_msr_priv.pcap_rapl_online);
-	rapl_remove_platform_domain(&rapl_msr_priv);
 	powercap_unregister_control_type(rapl_msr_priv.control_type);
 	return 0;
 }
diff --git a/include/linux/intel_rapl.h b/include/linux/intel_rapl.h
index 3582176a1eca..50b8398ffd21 100644
--- a/include/linux/intel_rapl.h
+++ b/include/linux/intel_rapl.h
@@ -79,8 +79,10 @@ struct rapl_power_limit {
 
 struct rapl_package;
 
+#define RAPL_DOMAIN_NAME_LENGTH 16
+
 struct rapl_domain {
-	const char *name;
+	char name[RAPL_DOMAIN_NAME_LENGTH];
 	enum rapl_domain_type id;
 	u64 regs[RAPL_DOMAIN_REG_MAX];
 	struct powercap_zone power_zone;
@@ -152,7 +154,4 @@ struct rapl_package *rapl_find_package_domain(int cpu, struct rapl_if_priv *priv
 struct rapl_package *rapl_add_package(int cpu, struct rapl_if_priv *priv);
 void rapl_remove_package(struct rapl_package *rp);
 
-int rapl_add_platform_domain(struct rapl_if_priv *priv);
-void rapl_remove_platform_domain(struct rapl_if_priv *priv);
-
 #endif /* __INTEL_RAPL_H__ */
-- 
cgit v1.2.3


From d4f8138354b9ec290de0c7ba527a945c5549e32b Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Tue, 13 Oct 2020 14:23:39 +0200
Subject: PM: domains: Add support for PM domain on/off notifiers for genpd

A device may have specific HW constraints that must be obeyed to, before
its corresponding PM domain (genpd) can be powered off - and vice verse at
power on. These constraints can't be managed through the regular runtime PM
based deployment for a device, because the access pattern for it, isn't
always request based. In other words, using the runtime PM callbacks to
deal with the constraints doesn't work for these cases.

For these reasons, let's instead add a PM domain power on/off notification
mechanism to genpd. To add/remove a notifier for a device, the device must
already have been attached to the genpd, which also means that it needs to
be a part of the PM domain topology.

To add/remove a notifier, let's introduce two genpd specific functions:
 - dev_pm_genpd_add|remove_notifier()

Note that, to further clarify when genpd power on/off notifiers may be
used, one can compare with the existing CPU_CLUSTER_PM_ENTER|EXIT
notifiers. In the long run, the genpd power on/off notifiers should be able
to replace them, but that requires additional genpd based platform support
for the current users.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Tested-by: Lina Iyer <ilina@codeaurora.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c | 161 ++++++++++++++++++++++++++++++++++++++++----
 include/linux/pm_domain.h   |  22 ++++++
 2 files changed, 171 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 05bb4d4401b2..c2a8821bdb26 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -413,28 +413,47 @@ static int _genpd_power_on(struct generic_pm_domain *genpd, bool timed)
 	unsigned int state_idx = genpd->state_idx;
 	ktime_t time_start;
 	s64 elapsed_ns;
-	int ret;
+	int ret, nr_calls = 0;
+
+	/* Notify consumers that we are about to power on. */
+	ret = __raw_notifier_call_chain(&genpd->power_notifiers,
+					GENPD_NOTIFY_PRE_ON, NULL, -1,
+					&nr_calls);
+	ret = notifier_to_errno(ret);
+	if (ret)
+		goto err;
 
 	if (!genpd->power_on)
-		return 0;
+		goto out;
 
-	if (!timed)
-		return genpd->power_on(genpd);
+	if (!timed) {
+		ret = genpd->power_on(genpd);
+		if (ret)
+			goto err;
+
+		goto out;
+	}
 
 	time_start = ktime_get();
 	ret = genpd->power_on(genpd);
 	if (ret)
-		return ret;
+		goto err;
 
 	elapsed_ns = ktime_to_ns(ktime_sub(ktime_get(), time_start));
 	if (elapsed_ns <= genpd->states[state_idx].power_on_latency_ns)
-		return ret;
+		goto out;
 
 	genpd->states[state_idx].power_on_latency_ns = elapsed_ns;
 	genpd->max_off_time_changed = true;
 	pr_debug("%s: Power-%s latency exceeded, new value %lld ns\n",
 		 genpd->name, "on", elapsed_ns);
 
+out:
+	raw_notifier_call_chain(&genpd->power_notifiers, GENPD_NOTIFY_ON, NULL);
+	return 0;
+err:
+	raw_notifier_call_chain(&genpd->power_notifiers, GENPD_NOTIFY_OFF,
+				NULL);
 	return ret;
 }
 
@@ -443,29 +462,51 @@ static int _genpd_power_off(struct generic_pm_domain *genpd, bool timed)
 	unsigned int state_idx = genpd->state_idx;
 	ktime_t time_start;
 	s64 elapsed_ns;
-	int ret;
+	int ret, nr_calls = 0;
+
+	/* Notify consumers that we are about to power off. */
+	ret = __raw_notifier_call_chain(&genpd->power_notifiers,
+					GENPD_NOTIFY_PRE_OFF, NULL, -1,
+					&nr_calls);
+	ret = notifier_to_errno(ret);
+	if (ret)
+		goto busy;
 
 	if (!genpd->power_off)
-		return 0;
+		goto out;
+
+	if (!timed) {
+		ret = genpd->power_off(genpd);
+		if (ret)
+			goto busy;
 
-	if (!timed)
-		return genpd->power_off(genpd);
+		goto out;
+	}
 
 	time_start = ktime_get();
 	ret = genpd->power_off(genpd);
 	if (ret)
-		return ret;
+		goto busy;
 
 	elapsed_ns = ktime_to_ns(ktime_sub(ktime_get(), time_start));
 	if (elapsed_ns <= genpd->states[state_idx].power_off_latency_ns)
-		return 0;
+		goto out;
 
 	genpd->states[state_idx].power_off_latency_ns = elapsed_ns;
 	genpd->max_off_time_changed = true;
 	pr_debug("%s: Power-%s latency exceeded, new value %lld ns\n",
 		 genpd->name, "off", elapsed_ns);
 
+out:
+	raw_notifier_call_chain(&genpd->power_notifiers, GENPD_NOTIFY_OFF,
+				NULL);
 	return 0;
+busy:
+	if (nr_calls)
+		__raw_notifier_call_chain(&genpd->power_notifiers,
+					  GENPD_NOTIFY_ON, NULL, nr_calls - 1,
+					  NULL);
+	return ret;
 }
 
 /**
@@ -1592,6 +1633,101 @@ int pm_genpd_remove_device(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(pm_genpd_remove_device);
 
+/**
+ * dev_pm_genpd_add_notifier - Add a genpd power on/off notifier for @dev
+ *
+ * @dev: Device that should be associated with the notifier
+ * @nb: The notifier block to register
+ *
+ * Users may call this function to add a genpd power on/off notifier for an
+ * attached @dev. Only one notifier per device is allowed. The notifier is
+ * sent when genpd is powering on/off the PM domain.
+ *
+ * It is assumed that the user guarantee that the genpd wouldn't be detached
+ * while this routine is getting called.
+ *
+ * Returns 0 on success and negative error values on failures.
+ */
+int dev_pm_genpd_add_notifier(struct device *dev, struct notifier_block *nb)
+{
+	struct generic_pm_domain *genpd;
+	struct generic_pm_domain_data *gpd_data;
+	int ret;
+
+	genpd = dev_to_genpd_safe(dev);
+	if (!genpd)
+		return -ENODEV;
+
+	if (WARN_ON(!dev->power.subsys_data ||
+		     !dev->power.subsys_data->domain_data))
+		return -EINVAL;
+
+	gpd_data = to_gpd_data(dev->power.subsys_data->domain_data);
+	if (gpd_data->power_nb)
+		return -EEXIST;
+
+	genpd_lock(genpd);
+	ret = raw_notifier_chain_register(&genpd->power_notifiers, nb);
+	genpd_unlock(genpd);
+
+	if (ret) {
+		dev_warn(dev, "failed to add notifier for PM domain %s\n",
+			 genpd->name);
+		return ret;
+	}
+
+	gpd_data->power_nb = nb;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dev_pm_genpd_add_notifier);
+
+/**
+ * dev_pm_genpd_remove_notifier - Remove a genpd power on/off notifier for @dev
+ *
+ * @dev: Device that is associated with the notifier
+ *
+ * Users may call this function to remove a genpd power on/off notifier for an
+ * attached @dev.
+ *
+ * It is assumed that the user guarantee that the genpd wouldn't be detached
+ * while this routine is getting called.
+ *
+ * Returns 0 on success and negative error values on failures.
+ */
+int dev_pm_genpd_remove_notifier(struct device *dev)
+{
+	struct generic_pm_domain *genpd;
+	struct generic_pm_domain_data *gpd_data;
+	int ret;
+
+	genpd = dev_to_genpd_safe(dev);
+	if (!genpd)
+		return -ENODEV;
+
+	if (WARN_ON(!dev->power.subsys_data ||
+		     !dev->power.subsys_data->domain_data))
+		return -EINVAL;
+
+	gpd_data = to_gpd_data(dev->power.subsys_data->domain_data);
+	if (!gpd_data->power_nb)
+		return -ENODEV;
+
+	genpd_lock(genpd);
+	ret = raw_notifier_chain_unregister(&genpd->power_notifiers,
+					    gpd_data->power_nb);
+	genpd_unlock(genpd);
+
+	if (ret) {
+		dev_warn(dev, "failed to remove notifier for PM domain %s\n",
+			 genpd->name);
+		return ret;
+	}
+
+	gpd_data->power_nb = NULL;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dev_pm_genpd_remove_notifier);
+
 static int genpd_add_subdomain(struct generic_pm_domain *genpd,
 			       struct generic_pm_domain *subdomain)
 {
@@ -1762,6 +1898,7 @@ int pm_genpd_init(struct generic_pm_domain *genpd,
 	INIT_LIST_HEAD(&genpd->parent_links);
 	INIT_LIST_HEAD(&genpd->child_links);
 	INIT_LIST_HEAD(&genpd->dev_list);
+	RAW_INIT_NOTIFIER_HEAD(&genpd->power_notifiers);
 	genpd_lock_init(genpd);
 	genpd->gov = gov;
 	INIT_WORK(&genpd->power_off_work, genpd_power_off_work_fn);
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 66f3c5d64d81..db039da0aba2 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -68,6 +68,13 @@ enum gpd_status {
 	GENPD_STATE_OFF,	/* PM domain is off */
 };
 
+enum genpd_notication {
+	GENPD_NOTIFY_PRE_OFF = 0,
+	GENPD_NOTIFY_OFF,
+	GENPD_NOTIFY_PRE_ON,
+	GENPD_NOTIFY_ON,
+};
+
 struct dev_power_governor {
 	bool (*power_down_ok)(struct dev_pm_domain *domain);
 	bool (*suspend_ok)(struct device *dev);
@@ -112,6 +119,7 @@ struct generic_pm_domain {
 	cpumask_var_t cpus;		/* A cpumask of the attached CPUs */
 	int (*power_off)(struct generic_pm_domain *domain);
 	int (*power_on)(struct generic_pm_domain *domain);
+	struct raw_notifier_head power_notifiers; /* Power on/off notifiers */
 	struct opp_table *opp_table;	/* OPP table of the genpd */
 	unsigned int (*opp_to_performance_state)(struct generic_pm_domain *genpd,
 						 struct dev_pm_opp *opp);
@@ -178,6 +186,7 @@ struct generic_pm_domain_data {
 	struct pm_domain_data base;
 	struct gpd_timing_data td;
 	struct notifier_block nb;
+	struct notifier_block *power_nb;
 	int cpu;
 	unsigned int performance_state;
 	void *data;
@@ -204,6 +213,8 @@ int pm_genpd_init(struct generic_pm_domain *genpd,
 		  struct dev_power_governor *gov, bool is_off);
 int pm_genpd_remove(struct generic_pm_domain *genpd);
 int dev_pm_genpd_set_performance_state(struct device *dev, unsigned int state);
+int dev_pm_genpd_add_notifier(struct device *dev, struct notifier_block *nb);
+int dev_pm_genpd_remove_notifier(struct device *dev);
 
 extern struct dev_power_governor simple_qos_governor;
 extern struct dev_power_governor pm_domain_always_on_gov;
@@ -251,6 +262,17 @@ static inline int dev_pm_genpd_set_performance_state(struct device *dev,
 	return -ENOTSUPP;
 }
 
+static inline int dev_pm_genpd_add_notifier(struct device *dev,
+					    struct notifier_block *nb)
+{
+	return -ENOTSUPP;
+}
+
+static inline int dev_pm_genpd_remove_notifier(struct device *dev)
+{
+	return -ENOTSUPP;
+}
+
 #define simple_qos_governor		(*(struct dev_power_governor *)(NULL))
 #define pm_domain_always_on_gov		(*(struct dev_power_governor *)(NULL))
 #endif
-- 
cgit v1.2.3


From c6a113b52302adcfadda63af81dc05f7a669fbc8 Mon Sep 17 00:00:00 2001
From: Lina Iyer <ilina@codeaurora.org>
Date: Thu, 15 Oct 2020 14:47:22 -0600
Subject: PM: domains: enable domain idle state accounting

To enable better debug of PM domains, keep a track of successful
and failing attempts to enter each domain idle state.

This statistics are exported in debugfs when reading the
idle_states node associated with each PM domain.

Signed-off-by: Lina Iyer <ilina@codeaurora.org>
[ rjw: Subject and changelog edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c | 10 +++++++---
 include/linux/pm_domain.h   |  2 ++
 2 files changed, 9 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index bc4243943940..859cdb207010 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -591,11 +591,14 @@ static int genpd_power_off(struct generic_pm_domain *genpd, bool one_dev_on,
 		return -EBUSY;
 
 	ret = _genpd_power_off(genpd, true);
-	if (ret)
+	if (ret) {
+		genpd->states[genpd->state_idx].rejected++;
 		return ret;
+	}
 
 	genpd->status = GENPD_STATE_OFF;
 	genpd_update_accounting(genpd);
+	genpd->states[genpd->state_idx].usage++;
 
 	list_for_each_entry(link, &genpd->child_links, child_node) {
 		genpd_sd_counter_dec(link->parent);
@@ -3061,7 +3064,7 @@ static int idle_states_show(struct seq_file *s, void *data)
 	if (ret)
 		return -ERESTARTSYS;
 
-	seq_puts(s, "State          Time Spent(ms)\n");
+	seq_puts(s, "State          Time Spent(ms) Usage          Rejected\n");
 
 	for (i = 0; i < genpd->state_count; i++) {
 		ktime_t delta = 0;
@@ -3073,7 +3076,8 @@ static int idle_states_show(struct seq_file *s, void *data)
 
 		msecs = ktime_to_ms(
 			ktime_add(genpd->states[i].idle_time, delta));
-		seq_printf(s, "S%-13i %lld\n", i, msecs);
+		seq_printf(s, "S%-13i %-14lld %-14llu %llu\n", i, msecs,
+			      genpd->states[i].usage, genpd->states[i].rejected);
 	}
 
 	genpd_unlock(genpd);
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index db039da0aba2..1ad0ec481416 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -89,6 +89,8 @@ struct genpd_power_state {
 	s64 power_off_latency_ns;
 	s64 power_on_latency_ns;
 	s64 residency_ns;
+	u64 usage;
+	u64 rejected;
 	struct fwnode_handle *fwnode;
 	ktime_t idle_time;
 	void *data;
-- 
cgit v1.2.3


From ecdf57b4f6748f3cb89eaf2ffdc9cfae4829f493 Mon Sep 17 00:00:00 2001
From: "Saheed O. Bolarinwa" <refactormyself@gmail.com>
Date: Thu, 15 Oct 2020 14:30:34 -0500
Subject: PCI/ASPM: Remove struct aspm_register_info.l1ss_cap_ptr

Save the L1 Substates Capability pointer in struct pci_dev.  Then we don't
have to keep track of it in the struct aspm_register_info and struct
pcie_link_state, which makes the code easier to read.  No functional change
intended.

[bhelgaas: split to a separate patch]
Link: https://lore.kernel.org/r/20201015193039.12585-8-helgaas@kernel.org
Signed-off-by: Saheed O. Bolarinwa <refactormyself@gmail.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pcie/aspm.c | 36 +++++++++++++++---------------------
 drivers/pci/probe.c     |  3 +++
 include/linux/pci.h     |  1 +
 3 files changed, 19 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index fd6e597b9d74..77316262f982 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -77,8 +77,6 @@ struct pcie_link_state {
 
 	/* L1 PM Substate info */
 	struct {
-		u32 up_cap_ptr;		/* L1SS cap ptr in upstream dev */
-		u32 dw_cap_ptr;		/* L1SS cap ptr in downstream dev */
 		u32 ctl1;		/* value to be programmed in ctl1 */
 		u32 ctl2;		/* value to be programmed in ctl2 */
 	} l1ss;
@@ -386,7 +384,6 @@ static void encode_l12_threshold(u32 threshold_us, u32 *scale, u32 *value)
 
 struct aspm_register_info {
 	/* L1 substates */
-	u32 l1ss_cap_ptr;
 	u32 l1ss_cap;
 	u32 l1ss_ctl1;
 	u32 l1ss_ctl2;
@@ -397,19 +394,20 @@ static void pcie_get_aspm_reg(struct pci_dev *pdev,
 {
 	/* Read L1 PM substate capabilities */
 	info->l1ss_cap = info->l1ss_ctl1 = info->l1ss_ctl2 = 0;
-	info->l1ss_cap_ptr = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_L1SS);
-	if (!info->l1ss_cap_ptr)
+
+	if (!pdev->l1ss)
 		return;
-	pci_read_config_dword(pdev, info->l1ss_cap_ptr + PCI_L1SS_CAP,
+
+	pci_read_config_dword(pdev, pdev->l1ss + PCI_L1SS_CAP,
 			      &info->l1ss_cap);
 	if (!(info->l1ss_cap & PCI_L1SS_CAP_L1_PM_SS)) {
 		info->l1ss_cap = 0;
 		return;
 	}
 
-	pci_read_config_dword(pdev, info->l1ss_cap_ptr + PCI_L1SS_CTL1,
+	pci_read_config_dword(pdev, pdev->l1ss + PCI_L1SS_CTL1,
 			      &info->l1ss_ctl1);
-	pci_read_config_dword(pdev, info->l1ss_cap_ptr + PCI_L1SS_CTL2,
+	pci_read_config_dword(pdev, pdev->l1ss + PCI_L1SS_CTL2,
 			      &info->l1ss_ctl2);
 }
 
@@ -494,8 +492,6 @@ static void aspm_calc_l1ss_info(struct pcie_link_state *link,
 	u32 val1, val2, scale1, scale2;
 	u32 t_common_mode, t_power_on, l1_2_threshold, scale, value;
 
-	link->l1ss.up_cap_ptr = upreg->l1ss_cap_ptr;
-	link->l1ss.dw_cap_ptr = dwreg->l1ss_cap_ptr;
 	link->l1ss.ctl1 = link->l1ss.ctl2 = 0;
 
 	if (!(link->aspm_support & ASPM_STATE_L1_2_MASK))
@@ -664,8 +660,6 @@ static void pcie_config_aspm_l1ss(struct pcie_link_state *link, u32 state)
 {
 	u32 val, enable_req;
 	struct pci_dev *child = link->downstream, *parent = link->pdev;
-	u32 up_cap_ptr = link->l1ss.up_cap_ptr;
-	u32 dw_cap_ptr = link->l1ss.dw_cap_ptr;
 
 	enable_req = (link->aspm_enabled ^ state) & state;
 
@@ -683,9 +677,9 @@ static void pcie_config_aspm_l1ss(struct pcie_link_state *link, u32 state)
 	 */
 
 	/* Disable all L1 substates */
-	pci_clear_and_set_dword(child, dw_cap_ptr + PCI_L1SS_CTL1,
+	pci_clear_and_set_dword(child, child->l1ss + PCI_L1SS_CTL1,
 				PCI_L1SS_CTL1_L1SS_MASK, 0);
-	pci_clear_and_set_dword(parent, up_cap_ptr + PCI_L1SS_CTL1,
+	pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
 				PCI_L1SS_CTL1_L1SS_MASK, 0);
 	/*
 	 * If needed, disable L1, and it gets enabled later
@@ -701,22 +695,22 @@ static void pcie_config_aspm_l1ss(struct pcie_link_state *link, u32 state)
 	if (enable_req & ASPM_STATE_L1_2_MASK) {
 
 		/* Program T_POWER_ON times in both ports */
-		pci_write_config_dword(parent, up_cap_ptr + PCI_L1SS_CTL2,
+		pci_write_config_dword(parent, parent->l1ss + PCI_L1SS_CTL2,
 				       link->l1ss.ctl2);
-		pci_write_config_dword(child, dw_cap_ptr + PCI_L1SS_CTL2,
+		pci_write_config_dword(child, child->l1ss + PCI_L1SS_CTL2,
 				       link->l1ss.ctl2);
 
 		/* Program Common_Mode_Restore_Time in upstream device */
-		pci_clear_and_set_dword(parent, up_cap_ptr + PCI_L1SS_CTL1,
+		pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
 					PCI_L1SS_CTL1_CM_RESTORE_TIME,
 					link->l1ss.ctl1);
 
 		/* Program LTR_L1.2_THRESHOLD time in both ports */
-		pci_clear_and_set_dword(parent,	up_cap_ptr + PCI_L1SS_CTL1,
+		pci_clear_and_set_dword(parent,	parent->l1ss + PCI_L1SS_CTL1,
 					PCI_L1SS_CTL1_LTR_L12_TH_VALUE |
 					PCI_L1SS_CTL1_LTR_L12_TH_SCALE,
 					link->l1ss.ctl1);
-		pci_clear_and_set_dword(child, dw_cap_ptr + PCI_L1SS_CTL1,
+		pci_clear_and_set_dword(child, child->l1ss + PCI_L1SS_CTL1,
 					PCI_L1SS_CTL1_LTR_L12_TH_VALUE |
 					PCI_L1SS_CTL1_LTR_L12_TH_SCALE,
 					link->l1ss.ctl1);
@@ -733,9 +727,9 @@ static void pcie_config_aspm_l1ss(struct pcie_link_state *link, u32 state)
 		val |= PCI_L1SS_CTL1_PCIPM_L1_2;
 
 	/* Enable what we need to enable */
-	pci_clear_and_set_dword(parent, up_cap_ptr + PCI_L1SS_CTL1,
+	pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
 				PCI_L1SS_CTL1_L1SS_MASK, val);
-	pci_clear_and_set_dword(child, dw_cap_ptr + PCI_L1SS_CTL1,
+	pci_clear_and_set_dword(child, child->l1ss + PCI_L1SS_CTL1,
 				PCI_L1SS_CTL1_L1SS_MASK, val);
 }
 
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 03d37128a24f..06f6bbcd8131 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -2106,6 +2106,9 @@ static void pci_configure_ltr(struct pci_dev *dev)
 	if (!pci_is_pcie(dev))
 		return;
 
+	/* Read L1 PM substate capabilities */
+	dev->l1ss = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_L1SS);
+
 	pcie_capability_read_dword(dev, PCI_EXP_DEVCAP2, &cap);
 	if (!(cap & PCI_EXP_DEVCAP2_LTR))
 		return;
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 835530605c0d..c5288cd71a2e 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -380,6 +380,7 @@ struct pci_dev {
 	struct pcie_link_state	*link_state;	/* ASPM link state */
 	unsigned int	ltr_path:1;	/* Latency Tolerance Reporting
 					   supported from root to here */
+	int		l1ss;		/* L1SS Capability pointer */
 #endif
 	unsigned int	eetlp_prefix_path:1;	/* End-to-End TLP Prefix */
 
-- 
cgit v1.2.3


From 57417cebc96b57122a2207fc84a6077d20c84b4b Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 15 Oct 2020 20:05:13 -0700
Subject: XArray: add xa_get_order

Patch series "Fix read-only THP for non-tmpfs filesystems".

As described more verbosely in the [3/3] changelog, we can inadvertently
put an order-0 page in the page cache which occupies 512 consecutive
entries.  Users are running into this if they enable the
READ_ONLY_THP_FOR_FS config option; see
https://bugzilla.kernel.org/show_bug.cgi?id=206569 and Qian Cai has also
reported it here:
https://lore.kernel.org/lkml/20200616013309.GB815@lca.pw/

This is a rather intrusive way of fixing the problem, but has the
advantage that I've actually been testing it with the THP patches, which
means that it sees far more use than it does upstream -- indeed, Song has
been entirely unable to reproduce it.  It also has the advantage that it
removes a few patches from my gargantuan backlog of THP patches.

This patch (of 3):

This function returns the order of the entry at the index.  We need this
because there isn't space in the shadow entry to encode its order.

[akpm@linux-foundation.org: export xa_get_order to modules]

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Qian Cai <cai@lca.pw>
Cc: Song Liu <songliubraving@fb.com>
Link: https://lkml.kernel.org/r/20200903183029.14930-1-willy@infradead.org
Link: https://lkml.kernel.org/r/20200903183029.14930-2-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/xarray.h |  9 +++++++++
 lib/test_xarray.c      | 21 +++++++++++++++++++++
 lib/xarray.c           | 40 ++++++++++++++++++++++++++++++++++++++++
 3 files changed, 70 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index b4d70e7568b2..5b7f4ebcf4ff 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -1505,6 +1505,15 @@ void xas_pause(struct xa_state *);
 
 void xas_create_range(struct xa_state *);
 
+#ifdef CONFIG_XARRAY_MULTI
+int xa_get_order(struct xarray *, unsigned long index);
+#else
+static inline int xa_get_order(struct xarray *xa, unsigned long index)
+{
+	return 0;
+}
+#endif
+
 /**
  * xas_reload() - Refetch an entry from the xarray.
  * @xas: XArray operation state.
diff --git a/lib/test_xarray.c b/lib/test_xarray.c
index d4f97925dbd8..bdd4d7995f79 100644
--- a/lib/test_xarray.c
+++ b/lib/test_xarray.c
@@ -1649,6 +1649,26 @@ static noinline void check_account(struct xarray *xa)
 #endif
 }
 
+static noinline void check_get_order(struct xarray *xa)
+{
+	unsigned int max_order = IS_ENABLED(CONFIG_XARRAY_MULTI) ? 20 : 1;
+	unsigned int order;
+	unsigned long i, j;
+
+	for (i = 0; i < 3; i++)
+		XA_BUG_ON(xa, xa_get_order(xa, i) != 0);
+
+	for (order = 0; order < max_order; order++) {
+		for (i = 0; i < 10; i++) {
+			xa_store_order(xa, i << order, order,
+					xa_mk_index(i << order), GFP_KERNEL);
+			for (j = i << order; j < (i + 1) << order; j++)
+				XA_BUG_ON(xa, xa_get_order(xa, j) != order);
+			xa_erase(xa, i << order);
+		}
+	}
+}
+
 static noinline void check_destroy(struct xarray *xa)
 {
 	unsigned long index;
@@ -1697,6 +1717,7 @@ static int xarray_checks(void)
 	check_reserve(&array);
 	check_reserve(&xa0);
 	check_multi_store(&array);
+	check_get_order(&array);
 	check_xa_alloc();
 	check_find(&array);
 	check_find_entry(&array);
diff --git a/lib/xarray.c b/lib/xarray.c
index e9e641d3c0c3..f24cb9a43af8 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -1592,6 +1592,46 @@ unlock:
 	return xas_result(&xas, NULL);
 }
 EXPORT_SYMBOL(xa_store_range);
+
+/**
+ * xa_get_order() - Get the order of an entry.
+ * @xa: XArray.
+ * @index: Index of the entry.
+ *
+ * Return: A number between 0 and 63 indicating the order of the entry.
+ */
+int xa_get_order(struct xarray *xa, unsigned long index)
+{
+	XA_STATE(xas, xa, index);
+	void *entry;
+	int order = 0;
+
+	rcu_read_lock();
+	entry = xas_load(&xas);
+
+	if (!entry)
+		goto unlock;
+
+	if (!xas.xa_node)
+		goto unlock;
+
+	for (;;) {
+		unsigned int slot = xas.xa_offset + (1 << order);
+
+		if (slot >= XA_CHUNK_SIZE)
+			break;
+		if (!xa_is_sibling(xas.xa_node->slots[slot]))
+			break;
+		order++;
+	}
+
+	order += xas.xa_node->shift;
+unlock:
+	rcu_read_unlock();
+
+	return order;
+}
+EXPORT_SYMBOL(xa_get_order);
 #endif /* CONFIG_XARRAY_MULTI */
 
 /**
-- 
cgit v1.2.3


From 8fc75643c5e14574c8be59b69182452ece28315a Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 15 Oct 2020 20:05:16 -0700
Subject: XArray: add xas_split

In order to use multi-index entries for huge pages in the page cache, we
need to be able to split a multi-index entry (eg if a file is truncated in
the middle of a huge page entry).  This version does not support splitting
more than one level of the tree at a time.  This is an acceptable
limitation for the page cache as we do not expect to support order-12
pages in the near future.

[akpm@linux-foundation.org: export xas_split_alloc() to modules]
[willy@infradead.org: fix xarray split]
  Link: https://lkml.kernel.org/r/20200910175450.GV6583@casper.infradead.org
[willy@infradead.org: fix xarray]
  Link: https://lkml.kernel.org/r/20201001233943.GW20115@casper.infradead.org

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Qian Cai <cai@lca.pw>
Cc: Song Liu <songliubraving@fb.com>
Link: https://lkml.kernel.org/r/20200903183029.14930-3-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/core-api/xarray.rst |  16 ++--
 include/linux/xarray.h            |  13 +++
 lib/test_xarray.c                 |  44 ++++++++++
 lib/xarray.c                      | 168 ++++++++++++++++++++++++++++++++++++--
 4 files changed, 225 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/core-api/xarray.rst b/Documentation/core-api/xarray.rst
index 640934b6f7b4..a137a0e6d068 100644
--- a/Documentation/core-api/xarray.rst
+++ b/Documentation/core-api/xarray.rst
@@ -475,13 +475,15 @@ or iterations will move the index to the first index in the range.
 Each entry will only be returned once, no matter how many indices it
 occupies.
 
-Using xas_next() or xas_prev() with a multi-index xa_state
-is not supported.  Using either of these functions on a multi-index entry
-will reveal sibling entries; these should be skipped over by the caller.
-
-Storing ``NULL`` into any index of a multi-index entry will set the entry
-at every index to ``NULL`` and dissolve the tie.  Splitting a multi-index
-entry into entries occupying smaller ranges is not yet supported.
+Using xas_next() or xas_prev() with a multi-index xa_state is not
+supported.  Using either of these functions on a multi-index entry will
+reveal sibling entries; these should be skipped over by the caller.
+
+Storing ``NULL`` into any index of a multi-index entry will set the
+entry at every index to ``NULL`` and dissolve the tie.  A multi-index
+entry can be split into entries occupying smaller ranges by calling
+xas_split_alloc() without the xa_lock held, followed by taking the lock
+and calling xas_split().
 
 Functions and structures
 ========================
diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 5b7f4ebcf4ff..5cdf441f6377 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -1507,11 +1507,24 @@ void xas_create_range(struct xa_state *);
 
 #ifdef CONFIG_XARRAY_MULTI
 int xa_get_order(struct xarray *, unsigned long index);
+void xas_split(struct xa_state *, void *entry, unsigned int order);
+void xas_split_alloc(struct xa_state *, void *entry, unsigned int order, gfp_t);
 #else
 static inline int xa_get_order(struct xarray *xa, unsigned long index)
 {
 	return 0;
 }
+
+static inline void xas_split(struct xa_state *xas, void *entry,
+		unsigned int order)
+{
+	xas_store(xas, entry);
+}
+
+static inline void xas_split_alloc(struct xa_state *xas, void *entry,
+		unsigned int order, gfp_t gfp)
+{
+}
 #endif
 
 /**
diff --git a/lib/test_xarray.c b/lib/test_xarray.c
index bdd4d7995f79..8262c3f05a5d 100644
--- a/lib/test_xarray.c
+++ b/lib/test_xarray.c
@@ -1503,6 +1503,49 @@ static noinline void check_store_range(struct xarray *xa)
 	}
 }
 
+#ifdef CONFIG_XARRAY_MULTI
+static void check_split_1(struct xarray *xa, unsigned long index,
+							unsigned int order)
+{
+	XA_STATE(xas, xa, index);
+	void *entry;
+	unsigned int i = 0;
+
+	xa_store_order(xa, index, order, xa, GFP_KERNEL);
+
+	xas_split_alloc(&xas, xa, order, GFP_KERNEL);
+	xas_lock(&xas);
+	xas_split(&xas, xa, order);
+	xas_unlock(&xas);
+
+	xa_for_each(xa, index, entry) {
+		XA_BUG_ON(xa, entry != xa);
+		i++;
+	}
+	XA_BUG_ON(xa, i != 1 << order);
+
+	xa_set_mark(xa, index, XA_MARK_0);
+	XA_BUG_ON(xa, !xa_get_mark(xa, index, XA_MARK_0));
+
+	xa_destroy(xa);
+}
+
+static noinline void check_split(struct xarray *xa)
+{
+	unsigned int order;
+
+	XA_BUG_ON(xa, !xa_empty(xa));
+
+	for (order = 1; order < 2 * XA_CHUNK_SHIFT; order++) {
+		check_split_1(xa, 0, order);
+		check_split_1(xa, 1UL << order, order);
+		check_split_1(xa, 3UL << order, order);
+	}
+}
+#else
+static void check_split(struct xarray *xa) { }
+#endif
+
 static void check_align_1(struct xarray *xa, char *name)
 {
 	int i;
@@ -1729,6 +1772,7 @@ static int xarray_checks(void)
 	check_store_range(&array);
 	check_store_iter(&array);
 	check_align(&xa0);
+	check_split(&array);
 
 	check_workingset(&array, 0);
 	check_workingset(&array, 64);
diff --git a/lib/xarray.c b/lib/xarray.c
index f24cb9a43af8..b76eea7b314c 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -266,13 +266,14 @@ static void xa_node_free(struct xa_node *node)
  */
 static void xas_destroy(struct xa_state *xas)
 {
-	struct xa_node *node = xas->xa_alloc;
+	struct xa_node *next, *node = xas->xa_alloc;
 
-	if (!node)
-		return;
-	XA_NODE_BUG_ON(node, !list_empty(&node->private_list));
-	kmem_cache_free(radix_tree_node_cachep, node);
-	xas->xa_alloc = NULL;
+	while (node) {
+		XA_NODE_BUG_ON(node, !list_empty(&node->private_list));
+		next = rcu_dereference_raw(node->parent);
+		radix_tree_node_rcu_free(&node->rcu_head);
+		xas->xa_alloc = node = next;
+	}
 }
 
 /**
@@ -304,6 +305,7 @@ bool xas_nomem(struct xa_state *xas, gfp_t gfp)
 	xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp);
 	if (!xas->xa_alloc)
 		return false;
+	xas->xa_alloc->parent = NULL;
 	XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list));
 	xas->xa_node = XAS_RESTART;
 	return true;
@@ -339,6 +341,7 @@ static bool __xas_nomem(struct xa_state *xas, gfp_t gfp)
 	}
 	if (!xas->xa_alloc)
 		return false;
+	xas->xa_alloc->parent = NULL;
 	XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list));
 	xas->xa_node = XAS_RESTART;
 	return true;
@@ -403,7 +406,7 @@ static unsigned long xas_size(const struct xa_state *xas)
 /*
  * Use this to calculate the maximum index that will need to be created
  * in order to add the entry described by @xas.  Because we cannot store a
- * multiple-index entry at index 0, the calculation is a little more complex
+ * multi-index entry at index 0, the calculation is a little more complex
  * than you might expect.
  */
 static unsigned long xas_max(struct xa_state *xas)
@@ -946,6 +949,153 @@ void xas_init_marks(const struct xa_state *xas)
 }
 EXPORT_SYMBOL_GPL(xas_init_marks);
 
+#ifdef CONFIG_XARRAY_MULTI
+static unsigned int node_get_marks(struct xa_node *node, unsigned int offset)
+{
+	unsigned int marks = 0;
+	xa_mark_t mark = XA_MARK_0;
+
+	for (;;) {
+		if (node_get_mark(node, offset, mark))
+			marks |= 1 << (__force unsigned int)mark;
+		if (mark == XA_MARK_MAX)
+			break;
+		mark_inc(mark);
+	}
+
+	return marks;
+}
+
+static void node_set_marks(struct xa_node *node, unsigned int offset,
+			struct xa_node *child, unsigned int marks)
+{
+	xa_mark_t mark = XA_MARK_0;
+
+	for (;;) {
+		if (marks & (1 << (__force unsigned int)mark)) {
+			node_set_mark(node, offset, mark);
+			if (child)
+				node_mark_all(child, mark);
+		}
+		if (mark == XA_MARK_MAX)
+			break;
+		mark_inc(mark);
+	}
+}
+
+/**
+ * xas_split_alloc() - Allocate memory for splitting an entry.
+ * @xas: XArray operation state.
+ * @entry: New entry which will be stored in the array.
+ * @order: New entry order.
+ * @gfp: Memory allocation flags.
+ *
+ * This function should be called before calling xas_split().
+ * If necessary, it will allocate new nodes (and fill them with @entry)
+ * to prepare for the upcoming split of an entry of @order size into
+ * entries of the order stored in the @xas.
+ *
+ * Context: May sleep if @gfp flags permit.
+ */
+void xas_split_alloc(struct xa_state *xas, void *entry, unsigned int order,
+		gfp_t gfp)
+{
+	unsigned int sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1;
+	unsigned int mask = xas->xa_sibs;
+
+	/* XXX: no support for splitting really large entries yet */
+	if (WARN_ON(xas->xa_shift + 2 * XA_CHUNK_SHIFT < order))
+		goto nomem;
+	if (xas->xa_shift + XA_CHUNK_SHIFT > order)
+		return;
+
+	do {
+		unsigned int i;
+		void *sibling;
+		struct xa_node *node;
+
+		node = kmem_cache_alloc(radix_tree_node_cachep, gfp);
+		if (!node)
+			goto nomem;
+		node->array = xas->xa;
+		for (i = 0; i < XA_CHUNK_SIZE; i++) {
+			if ((i & mask) == 0) {
+				RCU_INIT_POINTER(node->slots[i], entry);
+				sibling = xa_mk_sibling(0);
+			} else {
+				RCU_INIT_POINTER(node->slots[i], sibling);
+			}
+		}
+		RCU_INIT_POINTER(node->parent, xas->xa_alloc);
+		xas->xa_alloc = node;
+	} while (sibs-- > 0);
+
+	return;
+nomem:
+	xas_destroy(xas);
+	xas_set_err(xas, -ENOMEM);
+}
+EXPORT_SYMBOL_GPL(xas_split_alloc);
+
+/**
+ * xas_split() - Split a multi-index entry into smaller entries.
+ * @xas: XArray operation state.
+ * @entry: New entry to store in the array.
+ * @order: New entry order.
+ *
+ * The value in the entry is copied to all the replacement entries.
+ *
+ * Context: Any context.  The caller should hold the xa_lock.
+ */
+void xas_split(struct xa_state *xas, void *entry, unsigned int order)
+{
+	unsigned int sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1;
+	unsigned int offset, marks;
+	struct xa_node *node;
+	void *curr = xas_load(xas);
+	int values = 0;
+
+	node = xas->xa_node;
+	if (xas_top(node))
+		return;
+
+	marks = node_get_marks(node, xas->xa_offset);
+
+	offset = xas->xa_offset + sibs;
+	do {
+		if (xas->xa_shift < node->shift) {
+			struct xa_node *child = xas->xa_alloc;
+
+			xas->xa_alloc = rcu_dereference_raw(child->parent);
+			child->shift = node->shift - XA_CHUNK_SHIFT;
+			child->offset = offset;
+			child->count = XA_CHUNK_SIZE;
+			child->nr_values = xa_is_value(entry) ?
+					XA_CHUNK_SIZE : 0;
+			RCU_INIT_POINTER(child->parent, node);
+			node_set_marks(node, offset, child, marks);
+			rcu_assign_pointer(node->slots[offset],
+					xa_mk_node(child));
+			if (xa_is_value(curr))
+				values--;
+		} else {
+			unsigned int canon = offset - xas->xa_sibs;
+
+			node_set_marks(node, canon, NULL, marks);
+			rcu_assign_pointer(node->slots[canon], entry);
+			while (offset > canon)
+				rcu_assign_pointer(node->slots[offset--],
+						xa_mk_sibling(canon));
+			values += (xa_is_value(entry) - xa_is_value(curr)) *
+					(xas->xa_sibs + 1);
+		}
+	} while (offset-- > xas->xa_offset);
+
+	node->nr_values += values;
+}
+EXPORT_SYMBOL_GPL(xas_split);
+#endif
+
 /**
  * xas_pause() - Pause a walk to drop a lock.
  * @xas: XArray operation state.
@@ -1407,7 +1557,7 @@ EXPORT_SYMBOL(__xa_store);
  * @gfp: Memory allocation flags.
  *
  * After this function returns, loads from this index will return @entry.
- * Storing into an existing multislot entry updates the entry of every index.
+ * Storing into an existing multi-index entry updates the entry of every index.
  * The marks associated with @index are unaffected unless @entry is %NULL.
  *
  * Context: Any context.  Takes and releases the xa_lock.
@@ -1549,7 +1699,7 @@ static void xas_set_range(struct xa_state *xas, unsigned long first,
  *
  * After this function returns, loads from any index between @first and @last,
  * inclusive will return @entry.
- * Storing into an existing multislot entry updates the entry of every index.
+ * Storing into an existing multi-index entry updates the entry of every index.
  * The marks associated with @index are unaffected unless @entry is %NULL.
  *
  * Context: Process context.  Takes and releases the xa_lock.  May sleep
-- 
cgit v1.2.3


From 8fb156c9ee2db94f7127c930c89917634a1a9f56 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 15 Oct 2020 20:05:29 -0700
Subject: mm/page_owner: change split_page_owner to take a count

The implementation of split_page_owner() prefers a count rather than the
old order of the page.  When we support a variable size THP, we won't
have the order at this point, but we will have the number of pages.
So change the interface to what the caller and callee would prefer.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: SeongJae Park <sjpark@amazon.de>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Huang Ying <ying.huang@intel.com>
Link: https://lkml.kernel.org/r/20200908195539.25896-4-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/page_owner.h | 6 +++---
 mm/huge_memory.c           | 2 +-
 mm/page_alloc.c            | 2 +-
 mm/page_owner.c            | 4 ++--
 4 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/page_owner.h b/include/linux/page_owner.h
index 8679ccd722e8..3468794f83d2 100644
--- a/include/linux/page_owner.h
+++ b/include/linux/page_owner.h
@@ -11,7 +11,7 @@ extern struct page_ext_operations page_owner_ops;
 extern void __reset_page_owner(struct page *page, unsigned int order);
 extern void __set_page_owner(struct page *page,
 			unsigned int order, gfp_t gfp_mask);
-extern void __split_page_owner(struct page *page, unsigned int order);
+extern void __split_page_owner(struct page *page, unsigned int nr);
 extern void __copy_page_owner(struct page *oldpage, struct page *newpage);
 extern void __set_page_owner_migrate_reason(struct page *page, int reason);
 extern void __dump_page_owner(struct page *page);
@@ -31,10 +31,10 @@ static inline void set_page_owner(struct page *page,
 		__set_page_owner(page, order, gfp_mask);
 }
 
-static inline void split_page_owner(struct page *page, unsigned int order)
+static inline void split_page_owner(struct page *page, unsigned int nr)
 {
 	if (static_branch_unlikely(&page_owner_inited))
-		__split_page_owner(page, order);
+		__split_page_owner(page, nr);
 }
 static inline void copy_page_owner(struct page *oldpage, struct page *newpage)
 {
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 65c289c13b58..aa612cc5b3fe 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2454,7 +2454,7 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 
 	ClearPageCompound(head);
 
-	split_page_owner(head, HPAGE_PMD_ORDER);
+	split_page_owner(head, HPAGE_PMD_NR);
 
 	/* See comment in __split_huge_page_tail() */
 	if (PageAnon(head)) {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 05fe1ddb033c..febb2d731f9e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3209,7 +3209,7 @@ void split_page(struct page *page, unsigned int order)
 
 	for (i = 1; i < (1 << order); i++)
 		set_page_refcounted(page + i);
-	split_page_owner(page, order);
+	split_page_owner(page, 1 << order);
 }
 EXPORT_SYMBOL_GPL(split_page);
 
diff --git a/mm/page_owner.c b/mm/page_owner.c
index 360461509423..4ca3051a1035 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -204,7 +204,7 @@ void __set_page_owner_migrate_reason(struct page *page, int reason)
 	page_owner->last_migrate_reason = reason;
 }
 
-void __split_page_owner(struct page *page, unsigned int order)
+void __split_page_owner(struct page *page, unsigned int nr)
 {
 	int i;
 	struct page_ext *page_ext = lookup_page_ext(page);
@@ -213,7 +213,7 @@ void __split_page_owner(struct page *page, unsigned int order)
 	if (unlikely(!page_ext))
 		return;
 
-	for (i = 0; i < (1 << order); i++) {
+	for (i = 0; i < nr; i++) {
 		page_owner = get_page_owner(page_ext);
 		page_owner->order = 0;
 		page_ext = page_ext_next(page_ext);
-- 
cgit v1.2.3


From 01c70267053d6718820ac0902d8823d5dd2a6adb Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 15 Oct 2020 20:06:00 -0700
Subject: fs: add a filesystem flag for THPs

The page cache needs to know whether the filesystem supports THPs so that
it doesn't send THPs to filesystems which can't handle them.  Dave Chinner
points out that getting from the page mapping to the filesystem type is
too many steps (mapping->host->i_sb->s_type->fs_flags) so cache that
information in the address space flags.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Song Liu <songliubraving@fb.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Dave Chinner <dchinner@redhat.com>
Cc: Christoph Hellwig <hch@infradead.org>
Link: https://lkml.kernel.org/r/20200916032717.22917-1-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/inode.c              | 2 ++
 include/linux/fs.h      | 1 +
 include/linux/pagemap.h | 6 ++++++
 mm/shmem.c              | 2 +-
 4 files changed, 10 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/fs/inode.c b/fs/inode.c
index 72c4c347afb7..9d78c37b00b8 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -181,6 +181,8 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 	mapping->a_ops = &empty_aops;
 	mapping->host = inode;
 	mapping->flags = 0;
+	if (sb->s_type->fs_flags & FS_THP_SUPPORT)
+		__set_bit(AS_THP_SUPPORT, &mapping->flags);
 	mapping->wb_err = 0;
 	atomic_set(&mapping->i_mmap_writable, 0);
 #ifdef CONFIG_READ_ONLY_THP_FOR_FS
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ae97d87a00d2..72369be23f91 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2209,6 +2209,7 @@ struct file_system_type {
 #define FS_HAS_SUBTYPE		4
 #define FS_USERNS_MOUNT		8	/* Can be mounted by userns root */
 #define FS_DISALLOW_NOTIFY_PERM	16	/* Disable fanotify permission events */
+#define FS_THP_SUPPORT		8192	/* Remove once all fs converted */
 #define FS_RENAME_DOES_D_MOVE	32768	/* FS will handle d_move() during rename() internally. */
 	int (*init_fs_context)(struct fs_context *);
 	const struct fs_parameter_spec *parameters;
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index c3afd3242b54..820c970fd24a 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -29,6 +29,7 @@ enum mapping_flags {
 	AS_EXITING	= 4, 	/* final truncate in progress */
 	/* writeback related tags are not used */
 	AS_NO_WRITEBACK_TAGS = 5,
+	AS_THP_SUPPORT = 6,	/* THPs supported */
 };
 
 /**
@@ -120,6 +121,11 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask)
 	m->gfp_mask = mask;
 }
 
+static inline bool mapping_thp_support(struct address_space *mapping)
+{
+	return test_bit(AS_THP_SUPPORT, &mapping->flags);
+}
+
 void release_pages(struct page **pages, int nr);
 
 /*
diff --git a/mm/shmem.c b/mm/shmem.c
index 6d4ddef4a24f..537c137698f8 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3984,7 +3984,7 @@ static struct file_system_type shmem_fs_type = {
 	.parameters	= shmem_fs_parameters,
 #endif
 	.kill_sb	= kill_litter_super,
-	.fs_flags	= FS_USERNS_MOUNT,
+	.fs_flags	= FS_USERNS_MOUNT | FS_THP_SUPPORT,
 };
 
 int __init shmem_init(void)
-- 
cgit v1.2.3


From 6f4d2f9770cf154f9867f466d7b1b463a39f05a7 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 15 Oct 2020 20:06:03 -0700
Subject: fs: do not update nr_thps for mappings which support THPs

The nr_thps counter is to support THPs in the page cache when the
filesystem doesn't understand THPs.  Eventually it will be removed, but we
should still support filesystems which do not understand THPs yet.  Move
the nr_thp manipulation functions to filemap.h since they're page-cache
specific.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Song Liu <songliubraving@fb.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Dave Chinner <dchinner@redhat.com>
Cc: Christoph Hellwig <hch@infradead.org>
Link: https://lkml.kernel.org/r/20200916032717.22917-2-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/fs.h      | 27 ---------------------------
 include/linux/pagemap.h | 29 +++++++++++++++++++++++++++++
 2 files changed, 29 insertions(+), 27 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 72369be23f91..d1d166b46131 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2697,33 +2697,6 @@ static inline errseq_t file_sample_sb_err(struct file *file)
 	return errseq_sample(&file->f_path.dentry->d_sb->s_wb_err);
 }
 
-static inline int filemap_nr_thps(struct address_space *mapping)
-{
-#ifdef CONFIG_READ_ONLY_THP_FOR_FS
-	return atomic_read(&mapping->nr_thps);
-#else
-	return 0;
-#endif
-}
-
-static inline void filemap_nr_thps_inc(struct address_space *mapping)
-{
-#ifdef CONFIG_READ_ONLY_THP_FOR_FS
-	atomic_inc(&mapping->nr_thps);
-#else
-	WARN_ON_ONCE(1);
-#endif
-}
-
-static inline void filemap_nr_thps_dec(struct address_space *mapping)
-{
-#ifdef CONFIG_READ_ONLY_THP_FOR_FS
-	atomic_dec(&mapping->nr_thps);
-#else
-	WARN_ON_ONCE(1);
-#endif
-}
-
 extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end,
 			   int datasync);
 extern int vfs_fsync(struct file *file, int datasync);
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 820c970fd24a..a0024528a9ee 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -126,6 +126,35 @@ static inline bool mapping_thp_support(struct address_space *mapping)
 	return test_bit(AS_THP_SUPPORT, &mapping->flags);
 }
 
+static inline int filemap_nr_thps(struct address_space *mapping)
+{
+#ifdef CONFIG_READ_ONLY_THP_FOR_FS
+	return atomic_read(&mapping->nr_thps);
+#else
+	return 0;
+#endif
+}
+
+static inline void filemap_nr_thps_inc(struct address_space *mapping)
+{
+#ifdef CONFIG_READ_ONLY_THP_FOR_FS
+	if (!mapping_thp_support(mapping))
+		atomic_inc(&mapping->nr_thps);
+#else
+	WARN_ON_ONCE(1);
+#endif
+}
+
+static inline void filemap_nr_thps_dec(struct address_space *mapping)
+{
+#ifdef CONFIG_READ_ONLY_THP_FOR_FS
+	if (!mapping_thp_support(mapping))
+		atomic_dec(&mapping->nr_thps);
+#else
+	WARN_ON_ONCE(1);
+#endif
+}
+
 void release_pages(struct page **pages, int nr);
 
 /*
-- 
cgit v1.2.3


From 1aa83cfa5a20a6bbd39d2355a89c95152e4b37b4 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 15 Oct 2020 20:06:10 -0700
Subject: mm/readahead: add DEFINE_READAHEAD

Patch series "Readahead patches for 5.9/5.10".

These are infrastructure for both the THP patchset and for the fscache
rewrite,

For both pieces of infrastructure being build on top of this patchset, we
want the ractl to be available higher in the call-stack.

For David's work, he wants to add the 'critical page' to the ractl so that
he knows which page NEEDS to be brought in from storage, and which ones
are nice-to-have.  We might want something similar in block storage too.
It used to be simple -- the first page was the critical one, but then mmap
added fault-around and so for that usecase, the middle page is the
critical one.  Anyway, I don't have any code to show that yet, we just
know that the lowest point in the callchain where we have that information
is do_sync_mmap_readahead() and so the ractl needs to start its life
there.

For THP, we havew the code that needs it.  It's actually the apex patch to
the series; the one which finally starts to allocate THPs and present them
to consenting filesystems:
http://git.infradead.org/users/willy/pagecache.git/commitdiff/798bcf30ab2eff278caad03a9edca74d2f8ae760

This patch (of 8):

Allow for a more concise definition of a struct readahead_control.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Eric Biggers <ebiggers@google.com>
Cc: David Howells <dhowells@redhat.com>
Link: https://lkml.kernel.org/r/20200903140844.14194-1-willy@infradead.org
Link: https://lkml.kernel.org/r/20200903140844.14194-3-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/pagemap.h | 7 +++++++
 mm/readahead.c          | 6 +-----
 2 files changed, 8 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index a0024528a9ee..63c81b512e80 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -812,6 +812,13 @@ struct readahead_control {
 	unsigned int _batch_count;
 };
 
+#define DEFINE_READAHEAD(rac, f, m, i)					\
+	struct readahead_control rac = {				\
+		.file = f,						\
+		.mapping = m,						\
+		._index = i,						\
+	}
+
 /**
  * readahead_page - Get the next page to read.
  * @rac: The current readahead request.
diff --git a/mm/readahead.c b/mm/readahead.c
index 3c9a8dd7c56c..2126a2754e22 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -179,11 +179,7 @@ void page_cache_readahead_unbounded(struct address_space *mapping,
 {
 	LIST_HEAD(page_pool);
 	gfp_t gfp_mask = readahead_gfp_mask(mapping);
-	struct readahead_control rac = {
-		.mapping = mapping,
-		.file = file,
-		._index = index,
-	};
+	DEFINE_READAHEAD(rac, file, mapping, index);
 	unsigned long i;
 
 	/*
-- 
cgit v1.2.3


From 73bb49da50cd460bb3ba31250ed2e7fbf2115edf Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 15 Oct 2020 20:06:14 -0700
Subject: mm/readahead: make page_cache_ra_unbounded take a readahead_control

Define it in the callers instead of in page_cache_ra_unbounded().

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Eric Biggers <ebiggers@google.com>
Link: https://lkml.kernel.org/r/20200903140844.14194-4-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/ext4/verity.c        |  4 ++--
 fs/f2fs/verity.c        |  4 ++--
 include/linux/pagemap.h |  5 ++---
 mm/readahead.c          | 30 ++++++++++++++----------------
 4 files changed, 20 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c
index bbd5e7e0632b..5b7ba8f71153 100644
--- a/fs/ext4/verity.c
+++ b/fs/ext4/verity.c
@@ -349,6 +349,7 @@ static struct page *ext4_read_merkle_tree_page(struct inode *inode,
 					       pgoff_t index,
 					       unsigned long num_ra_pages)
 {
+	DEFINE_READAHEAD(ractl, NULL, inode->i_mapping, index);
 	struct page *page;
 
 	index += ext4_verity_metadata_pos(inode) >> PAGE_SHIFT;
@@ -358,8 +359,7 @@ static struct page *ext4_read_merkle_tree_page(struct inode *inode,
 		if (page)
 			put_page(page);
 		else if (num_ra_pages > 1)
-			page_cache_readahead_unbounded(inode->i_mapping, NULL,
-					index, num_ra_pages, 0);
+			page_cache_ra_unbounded(&ractl, num_ra_pages, 0);
 		page = read_mapping_page(inode->i_mapping, index, NULL);
 	}
 	return page;
diff --git a/fs/f2fs/verity.c b/fs/f2fs/verity.c
index 9eb0dba851e8..054ec852b5ea 100644
--- a/fs/f2fs/verity.c
+++ b/fs/f2fs/verity.c
@@ -228,6 +228,7 @@ static struct page *f2fs_read_merkle_tree_page(struct inode *inode,
 					       pgoff_t index,
 					       unsigned long num_ra_pages)
 {
+	DEFINE_READAHEAD(ractl, NULL, inode->i_mapping, index);
 	struct page *page;
 
 	index += f2fs_verity_metadata_pos(inode) >> PAGE_SHIFT;
@@ -237,8 +238,7 @@ static struct page *f2fs_read_merkle_tree_page(struct inode *inode,
 		if (page)
 			put_page(page);
 		else if (num_ra_pages > 1)
-			page_cache_readahead_unbounded(inode->i_mapping, NULL,
-					index, num_ra_pages, 0);
+			page_cache_ra_unbounded(&ractl, num_ra_pages, 0);
 		page = read_mapping_page(inode->i_mapping, index, NULL);
 	}
 	return page;
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 63c81b512e80..37f209ccef0f 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -768,9 +768,8 @@ void page_cache_sync_readahead(struct address_space *, struct file_ra_state *,
 void page_cache_async_readahead(struct address_space *, struct file_ra_state *,
 		struct file *, struct page *, pgoff_t index,
 		unsigned long req_count);
-void page_cache_readahead_unbounded(struct address_space *, struct file *,
-		pgoff_t index, unsigned long nr_to_read,
-		unsigned long lookahead_count);
+void page_cache_ra_unbounded(struct readahead_control *,
+		unsigned long nr_to_read, unsigned long lookahead_count);
 
 /*
  * Like add_to_page_cache_locked, but used to add newly allocated pages:
diff --git a/mm/readahead.c b/mm/readahead.c
index 2126a2754e22..a444943781bb 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -158,10 +158,8 @@ out:
 }
 
 /**
- * page_cache_readahead_unbounded - Start unchecked readahead.
- * @mapping: File address space.
- * @file: This instance of the open file; used for authentication.
- * @index: First page index to read.
+ * page_cache_ra_unbounded - Start unchecked readahead.
+ * @ractl: Readahead control.
  * @nr_to_read: The number of pages to read.
  * @lookahead_size: Where to start the next readahead.
  *
@@ -173,13 +171,13 @@ out:
  * Context: File is referenced by caller.  Mutexes may be held by caller.
  * May sleep, but will not reenter filesystem to reclaim memory.
  */
-void page_cache_readahead_unbounded(struct address_space *mapping,
-		struct file *file, pgoff_t index, unsigned long nr_to_read,
-		unsigned long lookahead_size)
+void page_cache_ra_unbounded(struct readahead_control *ractl,
+		unsigned long nr_to_read, unsigned long lookahead_size)
 {
+	struct address_space *mapping = ractl->mapping;
+	unsigned long index = readahead_index(ractl);
 	LIST_HEAD(page_pool);
 	gfp_t gfp_mask = readahead_gfp_mask(mapping);
-	DEFINE_READAHEAD(rac, file, mapping, index);
 	unsigned long i;
 
 	/*
@@ -200,7 +198,7 @@ void page_cache_readahead_unbounded(struct address_space *mapping,
 	for (i = 0; i < nr_to_read; i++) {
 		struct page *page = xa_load(&mapping->i_pages, index + i);
 
-		BUG_ON(index + i != rac._index + rac._nr_pages);
+		BUG_ON(index + i != ractl->_index + ractl->_nr_pages);
 
 		if (page && !xa_is_value(page)) {
 			/*
@@ -211,7 +209,7 @@ void page_cache_readahead_unbounded(struct address_space *mapping,
 			 * have a stable reference to this page, and it's
 			 * not worth getting one just for that.
 			 */
-			read_pages(&rac, &page_pool, true);
+			read_pages(ractl, &page_pool, true);
 			continue;
 		}
 
@@ -224,12 +222,12 @@ void page_cache_readahead_unbounded(struct address_space *mapping,
 		} else if (add_to_page_cache_lru(page, mapping, index + i,
 					gfp_mask) < 0) {
 			put_page(page);
-			read_pages(&rac, &page_pool, true);
+			read_pages(ractl, &page_pool, true);
 			continue;
 		}
 		if (i == nr_to_read - lookahead_size)
 			SetPageReadahead(page);
-		rac._nr_pages++;
+		ractl->_nr_pages++;
 	}
 
 	/*
@@ -237,10 +235,10 @@ void page_cache_readahead_unbounded(struct address_space *mapping,
 	 * uptodate then the caller will launch readpage again, and
 	 * will then handle the error.
 	 */
-	read_pages(&rac, &page_pool, false);
+	read_pages(ractl, &page_pool, false);
 	memalloc_nofs_restore(nofs);
 }
-EXPORT_SYMBOL_GPL(page_cache_readahead_unbounded);
+EXPORT_SYMBOL_GPL(page_cache_ra_unbounded);
 
 /*
  * __do_page_cache_readahead() actually reads a chunk of disk.  It allocates
@@ -252,6 +250,7 @@ void __do_page_cache_readahead(struct address_space *mapping,
 		struct file *file, pgoff_t index, unsigned long nr_to_read,
 		unsigned long lookahead_size)
 {
+	DEFINE_READAHEAD(ractl, file, mapping, index);
 	struct inode *inode = mapping->host;
 	loff_t isize = i_size_read(inode);
 	pgoff_t end_index;	/* The last page we want to read */
@@ -266,8 +265,7 @@ void __do_page_cache_readahead(struct address_space *mapping,
 	if (nr_to_read > end_index - index)
 		nr_to_read = end_index - index + 1;
 
-	page_cache_readahead_unbounded(mapping, file, index, nr_to_read,
-			lookahead_size);
+	page_cache_ra_unbounded(&ractl, nr_to_read, lookahead_size);
 }
 
 /*
-- 
cgit v1.2.3


From fefa7c478fdafe71c64b5ddf817ac0271aed1146 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 15 Oct 2020 20:06:28 -0700
Subject: mm/readahead: add page_cache_sync_ra and page_cache_async_ra

Reimplement page_cache_sync_readahead() and page_cache_async_readahead()
as wrappers around versions of the function which take a readahead_control
in preparation for making do_sync_mmap_readahead() pass down an RAC
struct.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Eric Biggers <ebiggers@google.com>
Link: https://lkml.kernel.org/r/20200903140844.14194-8-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/pagemap.h | 64 +++++++++++++++++++++++++++++++++++++++++--------
 mm/readahead.c          | 58 ++++++++++----------------------------------
 2 files changed, 66 insertions(+), 56 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 37f209ccef0f..c77b7c31b2e4 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -761,16 +761,6 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask);
 void delete_from_page_cache_batch(struct address_space *mapping,
 				  struct pagevec *pvec);
 
-#define VM_READAHEAD_PAGES	(SZ_128K / PAGE_SIZE)
-
-void page_cache_sync_readahead(struct address_space *, struct file_ra_state *,
-		struct file *, pgoff_t index, unsigned long req_count);
-void page_cache_async_readahead(struct address_space *, struct file_ra_state *,
-		struct file *, struct page *, pgoff_t index,
-		unsigned long req_count);
-void page_cache_ra_unbounded(struct readahead_control *,
-		unsigned long nr_to_read, unsigned long lookahead_count);
-
 /*
  * Like add_to_page_cache_locked, but used to add newly allocated pages:
  * the page is new, so we can just run __SetPageLocked() against it.
@@ -818,6 +808,60 @@ struct readahead_control {
 		._index = i,						\
 	}
 
+#define VM_READAHEAD_PAGES	(SZ_128K / PAGE_SIZE)
+
+void page_cache_ra_unbounded(struct readahead_control *,
+		unsigned long nr_to_read, unsigned long lookahead_count);
+void page_cache_sync_ra(struct readahead_control *, struct file_ra_state *,
+		unsigned long req_count);
+void page_cache_async_ra(struct readahead_control *, struct file_ra_state *,
+		struct page *, unsigned long req_count);
+
+/**
+ * page_cache_sync_readahead - generic file readahead
+ * @mapping: address_space which holds the pagecache and I/O vectors
+ * @ra: file_ra_state which holds the readahead state
+ * @file: Used by the filesystem for authentication.
+ * @index: Index of first page to be read.
+ * @req_count: Total number of pages being read by the caller.
+ *
+ * page_cache_sync_readahead() should be called when a cache miss happened:
+ * it will submit the read.  The readahead logic may decide to piggyback more
+ * pages onto the read request if access patterns suggest it will improve
+ * performance.
+ */
+static inline
+void page_cache_sync_readahead(struct address_space *mapping,
+		struct file_ra_state *ra, struct file *file, pgoff_t index,
+		unsigned long req_count)
+{
+	DEFINE_READAHEAD(ractl, file, mapping, index);
+	page_cache_sync_ra(&ractl, ra, req_count);
+}
+
+/**
+ * page_cache_async_readahead - file readahead for marked pages
+ * @mapping: address_space which holds the pagecache and I/O vectors
+ * @ra: file_ra_state which holds the readahead state
+ * @file: Used by the filesystem for authentication.
+ * @page: The page at @index which triggered the readahead call.
+ * @index: Index of first page to be read.
+ * @req_count: Total number of pages being read by the caller.
+ *
+ * page_cache_async_readahead() should be called when a page is used which
+ * is marked as PageReadahead; this is a marker to suggest that the application
+ * has used up enough of the readahead window that we should start pulling in
+ * more pages.
+ */
+static inline
+void page_cache_async_readahead(struct address_space *mapping,
+		struct file_ra_state *ra, struct file *file,
+		struct page *page, pgoff_t index, unsigned long req_count)
+{
+	DEFINE_READAHEAD(ractl, file, mapping, index);
+	page_cache_async_ra(&ractl, ra, page, req_count);
+}
+
 /**
  * readahead_page - Get the next page to read.
  * @rac: The current readahead request.
diff --git a/mm/readahead.c b/mm/readahead.c
index 3115ced5faae..620ac83f35cc 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -550,25 +550,9 @@ readit:
 	do_page_cache_ra(ractl, ra->size, ra->async_size);
 }
 
-/**
- * page_cache_sync_readahead - generic file readahead
- * @mapping: address_space which holds the pagecache and I/O vectors
- * @ra: file_ra_state which holds the readahead state
- * @filp: passed on to ->readpage() and ->readpages()
- * @index: Index of first page to be read.
- * @req_count: Total number of pages being read by the caller.
- *
- * page_cache_sync_readahead() should be called when a cache miss happened:
- * it will submit the read.  The readahead logic may decide to piggyback more
- * pages onto the read request if access patterns suggest it will improve
- * performance.
- */
-void page_cache_sync_readahead(struct address_space *mapping,
-			       struct file_ra_state *ra, struct file *filp,
-			       pgoff_t index, unsigned long req_count)
+void page_cache_sync_ra(struct readahead_control *ractl,
+		struct file_ra_state *ra, unsigned long req_count)
 {
-	DEFINE_READAHEAD(ractl, filp, mapping, index);
-
 	/* no read-ahead */
 	if (!ra->ra_pages)
 		return;
@@ -577,38 +561,20 @@ void page_cache_sync_readahead(struct address_space *mapping,
 		return;
 
 	/* be dumb */
-	if (filp && (filp->f_mode & FMODE_RANDOM)) {
-		force_page_cache_ra(&ractl, req_count);
+	if (ractl->file && (ractl->file->f_mode & FMODE_RANDOM)) {
+		force_page_cache_ra(ractl, req_count);
 		return;
 	}
 
 	/* do read-ahead */
-	ondemand_readahead(&ractl, ra, false, req_count);
+	ondemand_readahead(ractl, ra, false, req_count);
 }
-EXPORT_SYMBOL_GPL(page_cache_sync_readahead);
+EXPORT_SYMBOL_GPL(page_cache_sync_ra);
 
-/**
- * page_cache_async_readahead - file readahead for marked pages
- * @mapping: address_space which holds the pagecache and I/O vectors
- * @ra: file_ra_state which holds the readahead state
- * @filp: passed on to ->readpage() and ->readpages()
- * @page: The page at @index which triggered the readahead call.
- * @index: Index of first page to be read.
- * @req_count: Total number of pages being read by the caller.
- *
- * page_cache_async_readahead() should be called when a page is used which
- * is marked as PageReadahead; this is a marker to suggest that the application
- * has used up enough of the readahead window that we should start pulling in
- * more pages.
- */
-void
-page_cache_async_readahead(struct address_space *mapping,
-			   struct file_ra_state *ra, struct file *filp,
-			   struct page *page, pgoff_t index,
-			   unsigned long req_count)
+void page_cache_async_ra(struct readahead_control *ractl,
+		struct file_ra_state *ra, struct page *page,
+		unsigned long req_count)
 {
-	DEFINE_READAHEAD(ractl, filp, mapping, index);
-
 	/* no read-ahead */
 	if (!ra->ra_pages)
 		return;
@@ -624,16 +590,16 @@ page_cache_async_readahead(struct address_space *mapping,
 	/*
 	 * Defer asynchronous read-ahead on IO congestion.
 	 */
-	if (inode_read_congested(mapping->host))
+	if (inode_read_congested(ractl->mapping->host))
 		return;
 
 	if (blk_cgroup_congested())
 		return;
 
 	/* do read-ahead */
-	ondemand_readahead(&ractl, ra, true, req_count);
+	ondemand_readahead(ractl, ra, true, req_count);
 }
-EXPORT_SYMBOL_GPL(page_cache_async_readahead);
+EXPORT_SYMBOL_GPL(page_cache_async_ra);
 
 ssize_t ksys_readahead(int fd, loff_t offset, size_t count)
 {
-- 
cgit v1.2.3


From 7e27f22c9e40b66186e0675376f0495725ff1b0a Mon Sep 17 00:00:00 2001
From: Oscar Salvador <osalvador@suse.de>
Date: Thu, 15 Oct 2020 20:06:50 -0700
Subject: mm,hwpoison: unexport get_hwpoison_page and make it static

Since get_hwpoison_page is only used in memory-failure code now, let us
un-export it and make it private to that code.

Signed-off-by: Oscar Salvador <osalvador@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Aristeu Rozanski <aris@ruivo.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Dmitry Yakunin <zeil@yandex-team.ru>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Oscar Salvador <osalvador@suse.com>
Cc: Qian Cai <cai@lca.pw>
Cc: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/20200922135650.1634-5-osalvador@suse.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h  | 1 -
 mm/memory-failure.c | 3 +--
 2 files changed, 1 insertion(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 620961e4f32b..1977c09afe7a 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3025,7 +3025,6 @@ extern int memory_failure(unsigned long pfn, int flags);
 extern void memory_failure_queue(unsigned long pfn, int flags);
 extern void memory_failure_queue_kick(int cpu);
 extern int unpoison_memory(unsigned long pfn);
-extern int get_hwpoison_page(struct page *page);
 #define put_hwpoison_page(page)	put_page(page)
 extern int sysctl_memory_failure_early_kill;
 extern int sysctl_memory_failure_recovery;
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 6876757f4b85..95d5d8f3496c 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -924,7 +924,7 @@ static int page_action(struct page_state *ps, struct page *p,
  * Return: return 0 if failed to grab the refcount, otherwise true (some
  * non-zero value.)
  */
-int get_hwpoison_page(struct page *page)
+static int get_hwpoison_page(struct page *page)
 {
 	struct page *head = compound_head(page);
 
@@ -953,7 +953,6 @@ int get_hwpoison_page(struct page *page)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(get_hwpoison_page);
 
 /*
  * Do all that is necessary to remove user space mappings. Unmap
-- 
cgit v1.2.3


From dd6e2402fad966290f35dc687294fb6049714aac Mon Sep 17 00:00:00 2001
From: Oscar Salvador <osalvador@suse.de>
Date: Thu, 15 Oct 2020 20:06:57 -0700
Subject: mm,hwpoison: kill put_hwpoison_page

After commit 4e41a30c6d50 ("mm: hwpoison: adjust for new thp
refcounting"), put_hwpoison_page got reduced to a put_page.  Let us just
use put_page instead.

Signed-off-by: Oscar Salvador <osalvador@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Aristeu Rozanski <aris@ruivo.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Dmitry Yakunin <zeil@yandex-team.ru>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Oscar Salvador <osalvador@suse.com>
Cc: Qian Cai <cai@lca.pw>
Cc: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/20200922135650.1634-7-osalvador@suse.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h  |  1 -
 mm/memory-failure.c | 30 +++++++++++++++---------------
 2 files changed, 15 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 1977c09afe7a..ab038a3521b4 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3025,7 +3025,6 @@ extern int memory_failure(unsigned long pfn, int flags);
 extern void memory_failure_queue(unsigned long pfn, int flags);
 extern void memory_failure_queue_kick(int cpu);
 extern int unpoison_memory(unsigned long pfn);
-#define put_hwpoison_page(page)	put_page(page)
 extern int sysctl_memory_failure_early_kill;
 extern int sysctl_memory_failure_recovery;
 extern void shake_page(struct page *p, int access);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 95d5d8f3496c..4a9f8dc01160 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1143,7 +1143,7 @@ static int memory_failure_hugetlb(unsigned long pfn, int flags)
 		pr_err("Memory failure: %#lx: just unpoisoned\n", pfn);
 		num_poisoned_pages_dec();
 		unlock_page(head);
-		put_hwpoison_page(head);
+		put_page(head);
 		return 0;
 	}
 
@@ -1335,7 +1335,7 @@ int memory_failure(unsigned long pfn, int flags)
 					pfn);
 			if (TestClearPageHWPoison(p))
 				num_poisoned_pages_dec();
-			put_hwpoison_page(p);
+			put_page(p);
 			return -EBUSY;
 		}
 		unlock_page(p);
@@ -1388,14 +1388,14 @@ int memory_failure(unsigned long pfn, int flags)
 		pr_err("Memory failure: %#lx: just unpoisoned\n", pfn);
 		num_poisoned_pages_dec();
 		unlock_page(p);
-		put_hwpoison_page(p);
+		put_page(p);
 		return 0;
 	}
 	if (hwpoison_filter(p)) {
 		if (TestClearPageHWPoison(p))
 			num_poisoned_pages_dec();
 		unlock_page(p);
-		put_hwpoison_page(p);
+		put_page(p);
 		return 0;
 	}
 
@@ -1629,9 +1629,9 @@ int unpoison_memory(unsigned long pfn)
 	}
 	unlock_page(page);
 
-	put_hwpoison_page(page);
+	put_page(page);
 	if (freeit && !(pfn == my_zero_pfn(0) && page_count(p) == 1))
-		put_hwpoison_page(page);
+		put_page(page);
 
 	return 0;
 }
@@ -1692,7 +1692,7 @@ static int get_any_page(struct page *page, unsigned long pfn, int flags)
 		/*
 		 * Try to free it.
 		 */
-		put_hwpoison_page(page);
+		put_page(page);
 		shake_page(page, 1);
 
 		/*
@@ -1701,7 +1701,7 @@ static int get_any_page(struct page *page, unsigned long pfn, int flags)
 		ret = __get_any_page(page, pfn, 0);
 		if (ret == 1 && !PageLRU(page)) {
 			/* Drop page reference which is from __get_any_page() */
-			put_hwpoison_page(page);
+			put_page(page);
 			pr_info("soft_offline: %#lx: unknown non LRU page type %lx (%pGp)\n",
 				pfn, page->flags, &page->flags);
 			return -EIO;
@@ -1724,7 +1724,7 @@ static int soft_offline_huge_page(struct page *page, int flags)
 	lock_page(hpage);
 	if (PageHWPoison(hpage)) {
 		unlock_page(hpage);
-		put_hwpoison_page(hpage);
+		put_page(hpage);
 		pr_info("soft offline: %#lx hugepage already poisoned\n", pfn);
 		return -EBUSY;
 	}
@@ -1735,7 +1735,7 @@ static int soft_offline_huge_page(struct page *page, int flags)
 	 * get_any_page() and isolate_huge_page() takes a refcount each,
 	 * so need to drop one here.
 	 */
-	put_hwpoison_page(hpage);
+	put_page(hpage);
 	if (!ret) {
 		pr_info("soft offline: %#lx hugepage failed to isolate\n", pfn);
 		return -EBUSY;
@@ -1784,7 +1784,7 @@ static int __soft_offline_page(struct page *page, int flags)
 	wait_on_page_writeback(page);
 	if (PageHWPoison(page)) {
 		unlock_page(page);
-		put_hwpoison_page(page);
+		put_page(page);
 		pr_info("soft offline: %#lx page already poisoned\n", pfn);
 		return -EBUSY;
 	}
@@ -1799,7 +1799,7 @@ static int __soft_offline_page(struct page *page, int flags)
 	 * would need to fix isolation locking first.
 	 */
 	if (ret == 1) {
-		put_hwpoison_page(page);
+		put_page(page);
 		pr_info("soft_offline: %#lx: invalidated\n", pfn);
 		SetPageHWPoison(page);
 		num_poisoned_pages_inc();
@@ -1819,7 +1819,7 @@ static int __soft_offline_page(struct page *page, int flags)
 	 * Drop page reference which is came from get_any_page()
 	 * successful isolate_lru_page() already took another one.
 	 */
-	put_hwpoison_page(page);
+	put_page(page);
 	if (!ret) {
 		LIST_HEAD(pagelist);
 		/*
@@ -1863,7 +1863,7 @@ static int soft_offline_in_use_page(struct page *page, int flags)
 				pr_info("soft offline: %#lx: non anonymous thp\n", page_to_pfn(page));
 			else
 				pr_info("soft offline: %#lx: thp split failed\n", page_to_pfn(page));
-			put_hwpoison_page(page);
+			put_page(page);
 			return -EBUSY;
 		}
 		unlock_page(page);
@@ -1936,7 +1936,7 @@ int soft_offline_page(unsigned long pfn, int flags)
 	if (PageHWPoison(page)) {
 		pr_info("soft offline: %#lx page already poisoned\n", pfn);
 		if (flags & MF_COUNT_INCREASED)
-			put_hwpoison_page(page);
+			put_page(page);
 		return -EBUSY;
 	}
 
-- 
cgit v1.2.3


From 06be6ff3d2ec8be806b859fc054a1909b16d2473 Mon Sep 17 00:00:00 2001
From: Oscar Salvador <osalvador@suse.de>
Date: Thu, 15 Oct 2020 20:07:05 -0700
Subject: mm,hwpoison: rework soft offline for free pages

When trying to soft-offline a free page, we need to first take it off the
buddy allocator.  Once we know is out of reach, we can safely flag it as
poisoned.

take_page_off_buddy will be used to take a page meant to be poisoned off
the buddy allocator.  take_page_off_buddy calls break_down_buddy_pages,
which splits a higher-order page in case our page belongs to one.

Once the page is under our control, we call page_handle_poison to set it
as poisoned and grab a refcount on it.

Signed-off-by: Oscar Salvador <osalvador@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Aristeu Rozanski <aris@ruivo.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Dmitry Yakunin <zeil@yandex-team.ru>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Oscar Salvador <osalvador@suse.com>
Cc: Qian Cai <cai@lca.pw>
Cc: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/20200922135650.1634-9-osalvador@suse.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/page-flags.h |  1 +
 mm/memory-failure.c        | 18 ++++++++----
 mm/page_alloc.c            | 68 ++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 81 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 38ded408bd4c..a02b6d0221db 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -432,6 +432,7 @@ PAGEFLAG(HWPoison, hwpoison, PF_ANY)
 TESTSCFLAG(HWPoison, hwpoison, PF_ANY)
 #define __PG_HWPOISON (1UL << PG_hwpoison)
 extern bool set_hwpoison_free_buddy_page(struct page *page);
+extern bool take_page_off_buddy(struct page *page);
 #else
 PAGEFLAG_FALSE(HWPoison)
 static inline bool set_hwpoison_free_buddy_page(struct page *page)
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 2ff4ba7fa99f..af7fb23b93ae 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -65,6 +65,13 @@ int sysctl_memory_failure_recovery __read_mostly = 1;
 
 atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0);
 
+static void page_handle_poison(struct page *page)
+{
+	SetPageHWPoison(page);
+	page_ref_inc(page);
+	num_poisoned_pages_inc();
+}
+
 #if defined(CONFIG_HWPOISON_INJECT) || defined(CONFIG_HWPOISON_INJECT_MODULE)
 
 u32 hwpoison_filter_enable = 0;
@@ -1884,14 +1891,13 @@ static int soft_offline_in_use_page(struct page *page, int flags)
 
 static int soft_offline_free_page(struct page *page)
 {
-	int rc = dissolve_free_huge_page(page);
+	int rc = -EBUSY;
 
-	if (!rc) {
-		if (set_hwpoison_free_buddy_page(page))
-			num_poisoned_pages_inc();
-		else
-			rc = -EBUSY;
+	if (!dissolve_free_huge_page(page) && take_page_off_buddy(page)) {
+		page_handle_poison(page);
+		rc = 0;
 	}
+
 	return rc;
 }
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index febb2d731f9e..12dcfb3dc588 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -8777,6 +8777,74 @@ bool is_free_buddy_page(struct page *page)
 }
 
 #ifdef CONFIG_MEMORY_FAILURE
+/*
+ * Break down a higher-order page in sub-pages, and keep our target out of
+ * buddy allocator.
+ */
+static void break_down_buddy_pages(struct zone *zone, struct page *page,
+				   struct page *target, int low, int high,
+				   int migratetype)
+{
+	unsigned long size = 1 << high;
+	struct page *current_buddy, *next_page;
+
+	while (high > low) {
+		high--;
+		size >>= 1;
+
+		if (target >= &page[size]) {
+			next_page = page + size;
+			current_buddy = page;
+		} else {
+			next_page = page;
+			current_buddy = page + size;
+		}
+
+		if (set_page_guard(zone, current_buddy, high, migratetype))
+			continue;
+
+		if (current_buddy != target) {
+			add_to_free_list(current_buddy, zone, high, migratetype);
+			set_page_order(current_buddy, high);
+			page = next_page;
+		}
+	}
+}
+
+/*
+ * Take a page that will be marked as poisoned off the buddy allocator.
+ */
+bool take_page_off_buddy(struct page *page)
+{
+	struct zone *zone = page_zone(page);
+	unsigned long pfn = page_to_pfn(page);
+	unsigned long flags;
+	unsigned int order;
+	bool ret = false;
+
+	spin_lock_irqsave(&zone->lock, flags);
+	for (order = 0; order < MAX_ORDER; order++) {
+		struct page *page_head = page - (pfn & ((1 << order) - 1));
+		int buddy_order = page_order(page_head);
+
+		if (PageBuddy(page_head) && buddy_order >= order) {
+			unsigned long pfn_head = page_to_pfn(page_head);
+			int migratetype = get_pfnblock_migratetype(page_head,
+								   pfn_head);
+
+			del_page_from_free_list(page_head, zone, buddy_order);
+			break_down_buddy_pages(zone, page_head, page, 0,
+						buddy_order, migratetype);
+			ret = true;
+			break;
+		}
+		if (page_count(page_head) > 0)
+			break;
+	}
+	spin_unlock_irqrestore(&zone->lock, flags);
+	return ret;
+}
+
 /*
  * Set PG_hwpoison flag if a given page is confirmed to be a free page.  This
  * test is performed under the zone lock to prevent a race against page
-- 
cgit v1.2.3


From 79f5f8fab482dfff62948214468ac4ebbf0a016f Mon Sep 17 00:00:00 2001
From: Oscar Salvador <osalvador@suse.de>
Date: Thu, 15 Oct 2020 20:07:09 -0700
Subject: mm,hwpoison: rework soft offline for in-use pages

This patch changes the way we set and handle in-use poisoned pages.  Until
now, poisoned pages were released to the buddy allocator, trusting that
the checks that take place at allocation time would act as a safe net and
would skip that page.

This has proved to be wrong, as we got some pfn walkers out there, like
compaction, that all they care is the page to be in a buddy freelist.

Although this might not be the only user, having poisoned pages in the
buddy allocator seems a bad idea as we should only have free pages that
are ready and meant to be used as such.

Before explaining the taken approach, let us break down the kind of pages
we can soft offline.

- Anonymous THP (after the split, they end up being 4K pages)
- Hugetlb
- Order-0 pages (that can be either migrated or invalited)

* Normal pages (order-0 and anon-THP)

  - If they are clean and unmapped page cache pages, we invalidate
    then by means of invalidate_inode_page().
  - If they are mapped/dirty, we do the isolate-and-migrate dance.

Either way, do not call put_page directly from those paths.  Instead, we
keep the page and send it to page_handle_poison to perform the right
handling.

page_handle_poison sets the HWPoison flag and does the last put_page.

Down the chain, we placed a check for HWPoison page in
free_pages_prepare, that just skips any poisoned page, so those pages
do not end up in any pcplist/freelist.

After that, we set the refcount on the page to 1 and we increment
the poisoned pages counter.

If we see that the check in free_pages_prepare creates trouble, we can
always do what we do for free pages:

  - wait until the page hits buddy's freelists
  - take it off, and flag it

The downside of the above approach is that we could race with an
allocation, so by the time we  want to take the page off the buddy, the
page has been already allocated so we cannot soft offline it.
But the user could always retry it.

* Hugetlb pages

  - We isolate-and-migrate them

After the migration has been successful, we call dissolve_free_huge_page,
and we set HWPoison on the page if we succeed.
Hugetlb has a slightly different handling though.

While for non-hugetlb pages we cared about closing the race with an
allocation, doing so for hugetlb pages requires quite some additional
and intrusive code (we would need to hook in free_huge_page and some other
places).
So I decided to not make the code overly complicated and just fail
normally if the page we allocated in the meantime.

We can always build on top of this.

As a bonus, because of the way we handle now in-use pages, we no longer
need the put-as-isolation-migratetype dance, that was guarding for poisoned
pages to end up in pcplists.

Signed-off-by: Oscar Salvador <osalvador@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Aristeu Rozanski <aris@ruivo.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Dmitry Yakunin <zeil@yandex-team.ru>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Oscar Salvador <osalvador@suse.com>
Cc: Qian Cai <cai@lca.pw>
Cc: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/20200922135650.1634-10-osalvador@suse.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/page-flags.h |  5 -----
 mm/memory-failure.c        | 43 ++++++++++++++-----------------------------
 mm/migrate.c               | 11 +++--------
 mm/page_alloc.c            | 39 +++++++++++----------------------------
 4 files changed, 28 insertions(+), 70 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index a02b6d0221db..4f6ba9379112 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -431,14 +431,9 @@ PAGEFLAG_FALSE(Uncached)
 PAGEFLAG(HWPoison, hwpoison, PF_ANY)
 TESTSCFLAG(HWPoison, hwpoison, PF_ANY)
 #define __PG_HWPOISON (1UL << PG_hwpoison)
-extern bool set_hwpoison_free_buddy_page(struct page *page);
 extern bool take_page_off_buddy(struct page *page);
 #else
 PAGEFLAG_FALSE(HWPoison)
-static inline bool set_hwpoison_free_buddy_page(struct page *page)
-{
-	return 0;
-}
 #define __PG_HWPOISON 0
 #endif
 
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index af7fb23b93ae..962129c50be2 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -65,9 +65,11 @@ int sysctl_memory_failure_recovery __read_mostly = 1;
 
 atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0);
 
-static void page_handle_poison(struct page *page)
+static void page_handle_poison(struct page *page, bool release)
 {
 	SetPageHWPoison(page);
+	if (release)
+		put_page(page);
 	page_ref_inc(page);
 	num_poisoned_pages_inc();
 }
@@ -1765,19 +1767,13 @@ static int soft_offline_huge_page(struct page *page, int flags)
 			ret = -EIO;
 	} else {
 		/*
-		 * We set PG_hwpoison only when the migration source hugepage
-		 * was successfully dissolved, because otherwise hwpoisoned
-		 * hugepage remains on free hugepage list, then userspace will
-		 * find it as SIGBUS by allocation failure. That's not expected
-		 * in soft-offlining.
+		 * We set PG_hwpoison only when we were able to take the page
+		 * off the buddy.
 		 */
-		ret = dissolve_free_huge_page(page);
-		if (!ret) {
-			if (set_hwpoison_free_buddy_page(page))
-				num_poisoned_pages_inc();
-			else
-				ret = -EBUSY;
-		}
+		if (!dissolve_free_huge_page(page) && take_page_off_buddy(page))
+			page_handle_poison(page, false);
+		else
+			ret = -EBUSY;
 	}
 	return ret;
 }
@@ -1812,10 +1808,8 @@ static int __soft_offline_page(struct page *page, int flags)
 	 * would need to fix isolation locking first.
 	 */
 	if (ret == 1) {
-		put_page(page);
 		pr_info("soft_offline: %#lx: invalidated\n", pfn);
-		SetPageHWPoison(page);
-		num_poisoned_pages_inc();
+		page_handle_poison(page, true);
 		return 0;
 	}
 
@@ -1846,7 +1840,9 @@ static int __soft_offline_page(struct page *page, int flags)
 		list_add(&page->lru, &pagelist);
 		ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL,
 					MIGRATE_SYNC, MR_MEMORY_FAILURE);
-		if (ret) {
+		if (!ret) {
+			page_handle_poison(page, true);
+		} else {
 			if (!list_empty(&pagelist))
 				putback_movable_pages(&pagelist);
 
@@ -1865,27 +1861,16 @@ static int __soft_offline_page(struct page *page, int flags)
 static int soft_offline_in_use_page(struct page *page, int flags)
 {
 	int ret;
-	int mt;
 	struct page *hpage = compound_head(page);
 
 	if (!PageHuge(page) && PageTransHuge(hpage))
 		if (try_to_split_thp_page(page, "soft offline") < 0)
 			return -EBUSY;
 
-	/*
-	 * Setting MIGRATE_ISOLATE here ensures that the page will be linked
-	 * to free list immediately (not via pcplist) when released after
-	 * successful page migration. Otherwise we can't guarantee that the
-	 * page is really free after put_page() returns, so
-	 * set_hwpoison_free_buddy_page() highly likely fails.
-	 */
-	mt = get_pageblock_migratetype(page);
-	set_pageblock_migratetype(page, MIGRATE_ISOLATE);
 	if (PageHuge(page))
 		ret = soft_offline_huge_page(page, flags);
 	else
 		ret = __soft_offline_page(page, flags);
-	set_pageblock_migratetype(page, mt);
 	return ret;
 }
 
@@ -1894,7 +1879,7 @@ static int soft_offline_free_page(struct page *page)
 	int rc = -EBUSY;
 
 	if (!dissolve_free_huge_page(page) && take_page_off_buddy(page)) {
-		page_handle_poison(page);
+		page_handle_poison(page, false);
 		rc = 0;
 	}
 
diff --git a/mm/migrate.c b/mm/migrate.c
index f94d7c7eeddf..4cf1af88c1dd 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1223,16 +1223,11 @@ out:
 	 * we want to retry.
 	 */
 	if (rc == MIGRATEPAGE_SUCCESS) {
-		put_page(page);
-		if (reason == MR_MEMORY_FAILURE) {
+		if (reason != MR_MEMORY_FAILURE)
 			/*
-			 * Set PG_HWPoison on just freed page
-			 * intentionally. Although it's rather weird,
-			 * it's how HWPoison flag works at the moment.
+			 * We release the page in page_handle_poison.
 			 */
-			if (set_hwpoison_free_buddy_page(page))
-				num_poisoned_pages_inc();
-		}
+			put_page(page);
 	} else {
 		if (rc != -EAGAIN) {
 			if (likely(!__PageMovable(page))) {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 12dcfb3dc588..7fa55d9a3fe4 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1174,6 +1174,17 @@ static __always_inline bool free_pages_prepare(struct page *page,
 
 	trace_mm_page_free(page, order);
 
+	if (unlikely(PageHWPoison(page)) && !order) {
+		/*
+		 * Do not let hwpoison pages hit pcplists/buddy
+		 * Untie memcg state and reset page's owner
+		 */
+		if (memcg_kmem_enabled() && PageKmemcg(page))
+			__memcg_kmem_uncharge_page(page, order);
+		reset_page_owner(page, order);
+		return false;
+	}
+
 	/*
 	 * Check tail pages before head page information is cleared to
 	 * avoid checking PageCompound for order-0 pages.
@@ -8844,32 +8855,4 @@ bool take_page_off_buddy(struct page *page)
 	spin_unlock_irqrestore(&zone->lock, flags);
 	return ret;
 }
-
-/*
- * Set PG_hwpoison flag if a given page is confirmed to be a free page.  This
- * test is performed under the zone lock to prevent a race against page
- * allocation.
- */
-bool set_hwpoison_free_buddy_page(struct page *page)
-{
-	struct zone *zone = page_zone(page);
-	unsigned long pfn = page_to_pfn(page);
-	unsigned long flags;
-	unsigned int order;
-	bool hwpoisoned = false;
-
-	spin_lock_irqsave(&zone->lock, flags);
-	for (order = 0; order < MAX_ORDER; order++) {
-		struct page *page_head = page - (pfn & ((1 << order) - 1));
-
-		if (PageBuddy(page_head) && page_order(page_head) >= order) {
-			if (!TestSetPageHWPoison(page))
-				hwpoisoned = true;
-			break;
-		}
-	}
-	spin_unlock_irqrestore(&zone->lock, flags);
-
-	return hwpoisoned;
-}
 #endif
-- 
cgit v1.2.3


From 5d1fd5dc877bc1c670e7b1c174aa659b76c07de1 Mon Sep 17 00:00:00 2001
From: Naoya Horiguchi <naoya.horiguchi@nec.com>
Date: Thu, 15 Oct 2020 20:07:21 -0700
Subject: mm,hwpoison: introduce MF_MSG_UNSPLIT_THP

memory_failure() is supposed to call action_result() when it handles a
memory error event, but there's one missing case.  So let's add it.

I find that include/ras/ras_event.h has some other MF_MSG_* undefined, so
this patch also adds them.

Signed-off-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Signed-off-by: Oscar Salvador <osalvador@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Aristeu Rozanski <aris@ruivo.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Dmitry Yakunin <zeil@yandex-team.ru>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Oscar Salvador <osalvador@suse.com>
Cc: Qian Cai <cai@lca.pw>
Cc: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/20200922135650.1634-13-osalvador@suse.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h      | 1 +
 include/ras/ras_event.h | 3 +++
 mm/memory-failure.c     | 5 ++++-
 3 files changed, 8 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index ab038a3521b4..a9df46309e07 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3064,6 +3064,7 @@ enum mf_action_page_type {
 	MF_MSG_BUDDY,
 	MF_MSG_BUDDY_2ND,
 	MF_MSG_DAX,
+	MF_MSG_UNSPLIT_THP,
 	MF_MSG_UNKNOWN,
 };
 
diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
index 36c5c5e38c1d..0bdbc0d17d2f 100644
--- a/include/ras/ras_event.h
+++ b/include/ras/ras_event.h
@@ -361,6 +361,7 @@ TRACE_EVENT(aer_event,
 	EM ( MF_MSG_POISONED_HUGE, "huge page already hardware poisoned" )	\
 	EM ( MF_MSG_HUGE, "huge page" )					\
 	EM ( MF_MSG_FREE_HUGE, "free huge page" )			\
+	EM ( MF_MSG_NON_PMD_HUGE, "non-pmd-sized huge page" )		\
 	EM ( MF_MSG_UNMAP_FAILED, "unmapping failed page" )		\
 	EM ( MF_MSG_DIRTY_SWAPCACHE, "dirty swapcache page" )		\
 	EM ( MF_MSG_CLEAN_SWAPCACHE, "clean swapcache page" )		\
@@ -373,6 +374,8 @@ TRACE_EVENT(aer_event,
 	EM ( MF_MSG_TRUNCATED_LRU, "already truncated LRU page" )	\
 	EM ( MF_MSG_BUDDY, "free buddy page" )				\
 	EM ( MF_MSG_BUDDY_2ND, "free buddy page (2nd try)" )		\
+	EM ( MF_MSG_DAX, "dax page" )					\
+	EM ( MF_MSG_UNSPLIT_THP, "unsplit thp" )			\
 	EMe ( MF_MSG_UNKNOWN, "unknown page" )
 
 /*
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 1fb290faf28e..f9fa9982b5d4 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -582,6 +582,7 @@ static const char * const action_page_types[] = {
 	[MF_MSG_BUDDY]			= "free buddy page",
 	[MF_MSG_BUDDY_2ND]		= "free buddy page (2nd try)",
 	[MF_MSG_DAX]			= "dax page",
+	[MF_MSG_UNSPLIT_THP]		= "unsplit thp",
 	[MF_MSG_UNKNOWN]		= "unknown page",
 };
 
@@ -1370,8 +1371,10 @@ int memory_failure(unsigned long pfn, int flags)
 	}
 
 	if (PageTransHuge(hpage)) {
-		if (try_to_split_thp_page(p, "Memory Failure") < 0)
+		if (try_to_split_thp_page(p, "Memory Failure") < 0) {
+			action_result(pfn, MF_MSG_UNSPLIT_THP, MF_IGNORED);
 			return -EBUSY;
+		}
 		VM_BUG_ON_PAGE(!page_count(p), p);
 	}
 
-- 
cgit v1.2.3


From 257bea71582d895894201b604990a900df489103 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Thu, 15 Oct 2020 20:07:59 -0700
Subject: mm/page_alloc: simplify __offline_isolated_pages()

offline_pages() is the only user.  __offline_isolated_pages() never gets
called with ranges that contain memory holes and we no longer care about
the return value.  Drop the return value handling and all pfn_valid()
checks.

Update the documentation.

Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Charan Teja Reddy <charante@codeaurora.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Logan Gunthorpe <logang@deltatee.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michel Lespinasse <walken@google.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/20200819175957.28465-5-david@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memory_hotplug.h |  4 ++--
 mm/page_alloc.c                | 27 ++++-----------------------
 2 files changed, 6 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index c0faa7a30c46..76b314031f09 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -103,8 +103,8 @@ extern int online_pages(unsigned long pfn, unsigned long nr_pages,
 			int online_type, int nid);
 extern struct zone *test_pages_in_a_zone(unsigned long start_pfn,
 					 unsigned long end_pfn);
-extern unsigned long __offline_isolated_pages(unsigned long start_pfn,
-						unsigned long end_pfn);
+extern void __offline_isolated_pages(unsigned long start_pfn,
+				     unsigned long end_pfn);
 
 typedef void (*online_page_callback_t)(struct page *page, unsigned int order);
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 7fa55d9a3fe4..acc04ca1831d 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -8704,35 +8704,21 @@ void zone_pcp_reset(struct zone *zone)
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
 /*
- * All pages in the range must be in a single zone and isolated
- * before calling this.
+ * All pages in the range must be in a single zone, must not contain holes,
+ * must span full sections, and must be isolated before calling this function.
  */
-unsigned long
-__offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
+void __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
 {
+	unsigned long pfn = start_pfn;
 	struct page *page;
 	struct zone *zone;
 	unsigned int order;
-	unsigned long pfn;
 	unsigned long flags;
-	unsigned long offlined_pages = 0;
-
-	/* find the first valid pfn */
-	for (pfn = start_pfn; pfn < end_pfn; pfn++)
-		if (pfn_valid(pfn))
-			break;
-	if (pfn == end_pfn)
-		return offlined_pages;
 
 	offline_mem_sections(pfn, end_pfn);
 	zone = page_zone(pfn_to_page(pfn));
 	spin_lock_irqsave(&zone->lock, flags);
-	pfn = start_pfn;
 	while (pfn < end_pfn) {
-		if (!pfn_valid(pfn)) {
-			pfn++;
-			continue;
-		}
 		page = pfn_to_page(pfn);
 		/*
 		 * The HWPoisoned page may be not in buddy system, and
@@ -8740,7 +8726,6 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
 		 */
 		if (unlikely(!PageBuddy(page) && PageHWPoison(page))) {
 			pfn++;
-			offlined_pages++;
 			continue;
 		}
 		/*
@@ -8751,20 +8736,16 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
 			BUG_ON(page_count(page));
 			BUG_ON(PageBuddy(page));
 			pfn++;
-			offlined_pages++;
 			continue;
 		}
 
 		BUG_ON(page_count(page));
 		BUG_ON(!PageBuddy(page));
 		order = page_order(page);
-		offlined_pages += 1 << order;
 		del_page_from_free_list(page, zone, order);
 		pfn += (1 << order);
 	}
 	spin_unlock_irqrestore(&zone->lock, flags);
-
-	return offlined_pages;
 }
 #endif
 
-- 
cgit v1.2.3


From d882c0067d99d0f2add9a41628703cc99511a639 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Thu, 15 Oct 2020 20:08:19 -0700
Subject: mm: pass migratetype into memmap_init_zone() and
 move_pfn_range_to_zone()

On the memory onlining path, we want to start with MIGRATE_ISOLATE, to
un-isolate the pages after memory onlining is complete.  Let's allow
passing in the migratetype.

Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Logan Gunthorpe <logang@deltatee.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michel Lespinasse <walken@google.com>
Cc: Charan Teja Reddy <charante@codeaurora.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Link: https://lkml.kernel.org/r/20200819175957.28465-10-david@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/ia64/mm/init.c            |  4 ++--
 include/linux/memory_hotplug.h |  3 ++-
 include/linux/mm.h             |  2 +-
 mm/memory_hotplug.c            | 11 ++++++++---
 mm/memremap.c                  |  3 ++-
 mm/page_alloc.c                | 21 ++++++++++++---------
 6 files changed, 27 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index d8686bf3ae2f..ef12e097f318 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -537,7 +537,7 @@ virtual_memmap_init(u64 start, u64 end, void *arg)
 	if (map_start < map_end)
 		memmap_init_zone((unsigned long)(map_end - map_start),
 				 args->nid, args->zone, page_to_pfn(map_start),
-				 MEMINIT_EARLY, NULL);
+				 MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
 	return 0;
 }
 
@@ -547,7 +547,7 @@ memmap_init (unsigned long size, int nid, unsigned long zone,
 {
 	if (!vmem_map) {
 		memmap_init_zone(size, nid, zone, start_pfn,
-				 MEMINIT_EARLY, NULL);
+				 MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
 	} else {
 		struct page *start;
 		struct memmap_init_callback_data args;
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 76b314031f09..51a877fec8da 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -351,7 +351,8 @@ extern int add_memory_resource(int nid, struct resource *resource);
 extern int add_memory_driver_managed(int nid, u64 start, u64 size,
 				     const char *resource_name);
 extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
-		unsigned long nr_pages, struct vmem_altmap *altmap);
+				   unsigned long nr_pages,
+				   struct vmem_altmap *altmap, int migratetype);
 extern void remove_pfn_range_from_zone(struct zone *zone,
 				       unsigned long start_pfn,
 				       unsigned long nr_pages);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index a9df46309e07..61a2633fcc7f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2440,7 +2440,7 @@ extern int __meminit __early_pfn_to_nid(unsigned long pfn,
 
 extern void set_dma_reserve(unsigned long new_dma_reserve);
 extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long,
-		enum meminit_context, struct vmem_altmap *);
+		enum meminit_context, struct vmem_altmap *, int migratetype);
 extern void setup_per_zone_wmarks(void);
 extern int __meminit init_per_zone_wmark_min(void);
 extern void mem_init(void);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 113edf95b908..bb30e99b7383 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -701,9 +701,14 @@ static void __meminit resize_pgdat_range(struct pglist_data *pgdat, unsigned lon
  * Associate the pfn range with the given zone, initializing the memmaps
  * and resizing the pgdat/zone data to span the added pages. After this
  * call, all affected pages are PG_reserved.
+ *
+ * All aligned pageblocks are initialized to the specified migratetype
+ * (usually MIGRATE_MOVABLE). Besides setting the migratetype, no related
+ * zone stats (e.g., nr_isolate_pageblock) are touched.
  */
 void __ref move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
-		unsigned long nr_pages, struct vmem_altmap *altmap)
+				  unsigned long nr_pages,
+				  struct vmem_altmap *altmap, int migratetype)
 {
 	struct pglist_data *pgdat = zone->zone_pgdat;
 	int nid = pgdat->node_id;
@@ -728,7 +733,7 @@ void __ref move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
 	 * are reserved so nobody should be touching them so we should be safe
 	 */
 	memmap_init_zone(nr_pages, nid, zone_idx(zone), start_pfn,
-			 MEMINIT_HOTPLUG, altmap);
+			 MEMINIT_HOTPLUG, altmap, migratetype);
 
 	set_zone_contiguous(zone);
 }
@@ -808,7 +813,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages,
 
 	/* associate pfn range with the zone */
 	zone = zone_for_pfn_range(online_type, nid, pfn, nr_pages);
-	move_pfn_range_to_zone(zone, pfn, nr_pages, NULL);
+	move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_MOVABLE);
 
 	arg.start_pfn = pfn;
 	arg.nr_pages = nr_pages;
diff --git a/mm/memremap.c b/mm/memremap.c
index 198083453182..73a206d0f645 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -266,7 +266,8 @@ static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params,
 
 		zone = &NODE_DATA(nid)->node_zones[ZONE_DEVICE];
 		move_pfn_range_to_zone(zone, PHYS_PFN(range->start),
-				PHYS_PFN(range_len(range)), params->altmap);
+				PHYS_PFN(range_len(range)), params->altmap,
+				MIGRATE_MOVABLE);
 	}
 
 	mem_hotplug_done();
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 7a99ed299443..f7f292f1d108 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5990,10 +5990,15 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn)
  * Initially all pages are reserved - free ones are freed
  * up by memblock_free_all() once the early boot process is
  * done. Non-atomic initialization, single-pass.
+ *
+ * All aligned pageblocks are initialized to the specified migratetype
+ * (usually MIGRATE_MOVABLE). Besides setting the migratetype, no related
+ * zone stats (e.g., nr_isolate_pageblock) are touched.
  */
 void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
-		unsigned long start_pfn, enum meminit_context context,
-		struct vmem_altmap *altmap)
+		unsigned long start_pfn,
+		enum meminit_context context,
+		struct vmem_altmap *altmap, int migratetype)
 {
 	unsigned long pfn, end_pfn = start_pfn + size;
 	struct page *page;
@@ -6037,14 +6042,12 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 			__SetPageReserved(page);
 
 		/*
-		 * Mark the block movable so that blocks are reserved for
-		 * movable at startup. This will force kernel allocations
-		 * to reserve their blocks rather than leaking throughout
-		 * the address space during boot when many long-lived
-		 * kernel allocations are made.
+		 * Usually, we want to mark the pageblock MIGRATE_MOVABLE,
+		 * such that unmovable allocations won't be scattered all
+		 * over the place during system boot.
 		 */
 		if (IS_ALIGNED(pfn, pageblock_nr_pages)) {
-			set_pageblock_migratetype(page, MIGRATE_MOVABLE);
+			set_pageblock_migratetype(page, migratetype);
 			cond_resched();
 		}
 		pfn++;
@@ -6144,7 +6147,7 @@ void __meminit __weak memmap_init(unsigned long size, int nid,
 		if (end_pfn > start_pfn) {
 			size = end_pfn - start_pfn;
 			memmap_init_zone(size, nid, zone, start_pfn,
-					 MEMINIT_EARLY, NULL);
+					 MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
 		}
 	}
 }
-- 
cgit v1.2.3


From ec62d04e3fdc4ba3a7912cd7f6da1a4e787a0d75 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Thu, 15 Oct 2020 20:08:28 -0700
Subject: kernel/resource: make release_mem_region_adjustable() never fail

Patch series "selective merging of system ram resources", v4.

Some add_memory*() users add memory in small, contiguous memory blocks.
Examples include virtio-mem, hyper-v balloon, and the XEN balloon.

This can quickly result in a lot of memory resources, whereby the actual
resource boundaries are not of interest (e.g., it might be relevant for
DIMMs, exposed via /proc/iomem to user space).  We really want to merge
added resources in this scenario where possible.

Resources are effectively stored in a list-based tree.  Having a lot of
resources not only wastes memory, it also makes traversing that tree more
expensive, and makes /proc/iomem explode in size (e.g., requiring
kexec-tools to manually merge resources when creating a kdump header.  The
current kexec-tools resource count limit does not allow for more than
~100GB of memory with a memory block size of 128MB on x86-64).

Let's allow to selectively merge system ram resources by specifying a new
flag for add_memory*().  Patch #5 contains a /proc/iomem example.  Only
tested with virtio-mem.

This patch (of 8):

Let's make sure splitting a resource on memory hotunplug will never fail.
This will become more relevant once we merge selected System RAM resources
- then, we'll trigger that case more often on memory hotunplug.

In general, this function is already unlikely to fail.  When we remove
memory, we free up quite a lot of metadata (memmap, page tables, memory
block device, etc.).  The only reason it could really fail would be when
injecting allocation errors.

All other error cases inside release_mem_region_adjustable() seem to be
sanity checks if the function would be abused in different context - let's
add WARN_ON_ONCE() in these cases so we can catch them.

[natechancellor@gmail.com: fix use of ternary condition in release_mem_region_adjustable]
  Link: https://lkml.kernel.org/r/20200922060748.2452056-1-natechancellor@gmail.com
  Link: https://github.com/ClangBuiltLinux/linux/issues/1159

Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Kees Cook <keescook@chromium.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Wei Yang <richardw.yang@linux.intel.com>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Julien Grall <julien@xen.org>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Len Brown <lenb@kernel.org>
Cc: Leonardo Bras <leobras.c@gmail.com>
Cc: Libor Pechacek <lpechacek@suse.cz>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: "Oliver O'Halloran" <oohall@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pingfan Liu <kernelfans@gmail.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Roger Pau Monn <roger.pau@citrix.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Wei Liu <wei.liu@kernel.org>
Link: https://lkml.kernel.org/r/20200911103459.10306-2-david@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/ioport.h |  4 ++--
 kernel/resource.c      | 49 ++++++++++++++++++++++++++++---------------------
 mm/memory_hotplug.c    | 22 +---------------------
 3 files changed, 31 insertions(+), 44 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index 6c2b06fe8beb..52a91f5fa1a3 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -248,8 +248,8 @@ extern struct resource * __request_region(struct resource *,
 extern void __release_region(struct resource *, resource_size_t,
 				resource_size_t);
 #ifdef CONFIG_MEMORY_HOTREMOVE
-extern int release_mem_region_adjustable(struct resource *, resource_size_t,
-				resource_size_t);
+extern void release_mem_region_adjustable(struct resource *, resource_size_t,
+					  resource_size_t);
 #endif
 
 /* Wrappers for managed devices */
diff --git a/kernel/resource.c b/kernel/resource.c
index f1175ce93a1d..4c1c487abbfb 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -1258,21 +1258,28 @@ EXPORT_SYMBOL(__release_region);
  *   assumes that all children remain in the lower address entry for
  *   simplicity.  Enhance this logic when necessary.
  */
-int release_mem_region_adjustable(struct resource *parent,
-				  resource_size_t start, resource_size_t size)
+void release_mem_region_adjustable(struct resource *parent,
+				   resource_size_t start, resource_size_t size)
 {
+	struct resource *new_res = NULL;
+	bool alloc_nofail = false;
 	struct resource **p;
 	struct resource *res;
-	struct resource *new_res;
 	resource_size_t end;
-	int ret = -EINVAL;
 
 	end = start + size - 1;
-	if ((start < parent->start) || (end > parent->end))
-		return ret;
+	if (WARN_ON_ONCE((start < parent->start) || (end > parent->end)))
+		return;
 
-	/* The alloc_resource() result gets checked later */
-	new_res = alloc_resource(GFP_KERNEL);
+	/*
+	 * We free up quite a lot of memory on memory hotunplug (esp., memap),
+	 * just before releasing the region. This is highly unlikely to
+	 * fail - let's play save and make it never fail as the caller cannot
+	 * perform any error handling (e.g., trying to re-add memory will fail
+	 * similarly).
+	 */
+retry:
+	new_res = alloc_resource(GFP_KERNEL | (alloc_nofail ? __GFP_NOFAIL : 0));
 
 	p = &parent->child;
 	write_lock(&resource_lock);
@@ -1298,7 +1305,6 @@ int release_mem_region_adjustable(struct resource *parent,
 		 * so if we are dealing with them, let us just back off here.
 		 */
 		if (!(res->flags & IORESOURCE_SYSRAM)) {
-			ret = 0;
 			break;
 		}
 
@@ -1315,20 +1321,23 @@ int release_mem_region_adjustable(struct resource *parent,
 			/* free the whole entry */
 			*p = res->sibling;
 			free_resource(res);
-			ret = 0;
 		} else if (res->start == start && res->end != end) {
 			/* adjust the start */
-			ret = __adjust_resource(res, end + 1,
-						res->end - end);
+			WARN_ON_ONCE(__adjust_resource(res, end + 1,
+						       res->end - end));
 		} else if (res->start != start && res->end == end) {
 			/* adjust the end */
-			ret = __adjust_resource(res, res->start,
-						start - res->start);
+			WARN_ON_ONCE(__adjust_resource(res, res->start,
+						       start - res->start));
 		} else {
-			/* split into two entries */
+			/* split into two entries - we need a new resource */
 			if (!new_res) {
-				ret = -ENOMEM;
-				break;
+				new_res = alloc_resource(GFP_ATOMIC);
+				if (!new_res) {
+					alloc_nofail = true;
+					write_unlock(&resource_lock);
+					goto retry;
+				}
 			}
 			new_res->name = res->name;
 			new_res->start = end + 1;
@@ -1339,9 +1348,8 @@ int release_mem_region_adjustable(struct resource *parent,
 			new_res->sibling = res->sibling;
 			new_res->child = NULL;
 
-			ret = __adjust_resource(res, res->start,
-						start - res->start);
-			if (ret)
+			if (WARN_ON_ONCE(__adjust_resource(res, res->start,
+							   start - res->start)))
 				break;
 			res->sibling = new_res;
 			new_res = NULL;
@@ -1352,7 +1360,6 @@ int release_mem_region_adjustable(struct resource *parent,
 
 	write_unlock(&resource_lock);
 	free_resource(new_res);
-	return ret;
 }
 #endif	/* CONFIG_MEMORY_HOTREMOVE */
 
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 1b40eebae3e4..5d9c41ec0556 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1727,26 +1727,6 @@ void try_offline_node(int nid)
 }
 EXPORT_SYMBOL(try_offline_node);
 
-static void __release_memory_resource(resource_size_t start,
-				      resource_size_t size)
-{
-	int ret;
-
-	/*
-	 * When removing memory in the same granularity as it was added,
-	 * this function never fails. It might only fail if resources
-	 * have to be adjusted or split. We'll ignore the error, as
-	 * removing of memory cannot fail.
-	 */
-	ret = release_mem_region_adjustable(&iomem_resource, start, size);
-	if (ret) {
-		resource_size_t endres = start + size - 1;
-
-		pr_warn("Unable to release resource <%pa-%pa> (%d)\n",
-			&start, &endres, ret);
-	}
-}
-
 static int __ref try_remove_memory(int nid, u64 start, u64 size)
 {
 	int rc = 0;
@@ -1780,7 +1760,7 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size)
 		memblock_remove(start, size);
 	}
 
-	__release_memory_resource(start, size);
+	release_mem_region_adjustable(&iomem_resource, start, size);
 
 	try_offline_node(nid);
 
-- 
cgit v1.2.3


From 7cf603d17d9bddbda90c424b6f30c7bc2e6f48f2 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Thu, 15 Oct 2020 20:08:33 -0700
Subject: kernel/resource: move and rename IORESOURCE_MEM_DRIVER_MANAGED
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

IORESOURCE_MEM_DRIVER_MANAGED currently uses an unused PnP bit, which is
always set to 0 by hardware.  This is far from beautiful (and confusing),
and the bit only applies to SYSRAM.  So let's move it out of the
bus-specific (PnP) defined bits.

We'll add another SYSRAM specific bit soon.  If we ever need more bits for
other purposes, we can steal some from "desc", or reshuffle/regroup what
we have.

Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Kees Cook <keescook@chromium.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Wei Yang <richardw.yang@linux.intel.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Julien Grall <julien@xen.org>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Len Brown <lenb@kernel.org>
Cc: Leonardo Bras <leobras.c@gmail.com>
Cc: Libor Pechacek <lpechacek@suse.cz>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: "Oliver O'Halloran" <oohall@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pingfan Liu <kernelfans@gmail.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Roger Pau Monné <roger.pau@citrix.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Wei Liu <wei.liu@kernel.org>
Link: https://lkml.kernel.org/r/20200911103459.10306-3-david@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/ioport.h | 4 +++-
 kernel/kexec_file.c    | 2 +-
 mm/memory_hotplug.c    | 4 ++--
 3 files changed, 6 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index 52a91f5fa1a3..d7620d7c941a 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -58,6 +58,9 @@ struct resource {
 #define IORESOURCE_EXT_TYPE_BITS 0x01000000	/* Resource extended types */
 #define IORESOURCE_SYSRAM	0x01000000	/* System RAM (modifier) */
 
+/* IORESOURCE_SYSRAM specific bits. */
+#define IORESOURCE_SYSRAM_DRIVER_MANAGED	0x02000000 /* Always detected via a driver. */
+
 #define IORESOURCE_EXCLUSIVE	0x08000000	/* Userland may not map this resource */
 
 #define IORESOURCE_DISABLED	0x10000000
@@ -103,7 +106,6 @@ struct resource {
 #define IORESOURCE_MEM_32BIT		(3<<3)
 #define IORESOURCE_MEM_SHADOWABLE	(1<<5)	/* dup: IORESOURCE_SHADOWABLE */
 #define IORESOURCE_MEM_EXPANSIONROM	(1<<6)
-#define IORESOURCE_MEM_DRIVER_MANAGED	(1<<7)
 
 /* PnP I/O specific bits (IORESOURCE_BITS) */
 #define IORESOURCE_IO_16BIT_ADDR	(1<<0)
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index 84f7316792a7..e21f6b9234f7 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -521,7 +521,7 @@ static int locate_mem_hole_callback(struct resource *res, void *arg)
 	/* Returning 0 will take to next memory range */
 
 	/* Don't use memory that will be detected and handled by a driver. */
-	if (res->flags & IORESOURCE_MEM_DRIVER_MANAGED)
+	if (res->flags & IORESOURCE_SYSRAM_DRIVER_MANAGED)
 		return 0;
 
 	if (sz < kbuf->memsz)
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 5d9c41ec0556..9a7193970e77 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -105,7 +105,7 @@ static struct resource *register_memory_resource(u64 start, u64 size,
 	unsigned long flags =  IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
 
 	if (strcmp(resource_name, "System RAM"))
-		flags |= IORESOURCE_MEM_DRIVER_MANAGED;
+		flags |= IORESOURCE_SYSRAM_DRIVER_MANAGED;
 
 	/*
 	 * Make sure value parsed from 'mem=' only restricts memory adding
@@ -1161,7 +1161,7 @@ EXPORT_SYMBOL_GPL(add_memory);
  *
  * For this memory, no entries in /sys/firmware/memmap ("raw firmware-provided
  * memory map") are created. Also, the created memory resource is flagged
- * with IORESOURCE_MEM_DRIVER_MANAGED, so in-kernel users can special-case
+ * with IORESOURCE_SYSRAM_DRIVER_MANAGED, so in-kernel users can special-case
  * this memory as well (esp., not place kexec images onto it).
  *
  * The resource_name (visible via /proc/iomem) has to have the format
-- 
cgit v1.2.3


From 3a0aaefe4134951b4e89feb873c457428154530c Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Thu, 15 Oct 2020 20:08:39 -0700
Subject: mm/memory_hotplug: guard more declarations by CONFIG_MEMORY_HOTPLUG
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We soon want to pass flags via a new type to add_memory() and friends.
That revealed that we currently don't guard some declarations by
CONFIG_MEMORY_HOTPLUG.

While some definitions could be moved to different places, let's keep it
minimal for now and use CONFIG_MEMORY_HOTPLUG for all functions only
compiled with CONFIG_MEMORY_HOTPLUG.

Wrap sparse_decode_mem_map() into CONFIG_MEMORY_HOTPLUG, it's only called
from CONFIG_MEMORY_HOTPLUG code.

While at it, remove allow_online_pfn_range(), which is no longer around,
and mhp_notimplemented(), which is unused.

Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Wei Yang <richardw.yang@linux.intel.com>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Julien Grall <julien@xen.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Len Brown <lenb@kernel.org>
Cc: Leonardo Bras <leobras.c@gmail.com>
Cc: Libor Pechacek <lpechacek@suse.cz>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: "Oliver O'Halloran" <oohall@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pingfan Liu <kernelfans@gmail.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Roger Pau Monné <roger.pau@citrix.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Wei Liu <wei.liu@kernel.org>
Link: https://lkml.kernel.org/r/20200911103459.10306-4-david@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memory_hotplug.h | 12 +++---------
 mm/sparse.c                    |  2 ++
 2 files changed, 5 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 51a877fec8da..1504b4d5ae6c 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -247,13 +247,6 @@ static inline void zone_span_writelock(struct zone *zone) {}
 static inline void zone_span_writeunlock(struct zone *zone) {}
 static inline void zone_seqlock_init(struct zone *zone) {}
 
-static inline int mhp_notimplemented(const char *func)
-{
-	printk(KERN_WARNING "%s() called, with CONFIG_MEMORY_HOTPLUG disabled\n", func);
-	dump_stack();
-	return -ENOSYS;
-}
-
 static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
 {
 }
@@ -344,6 +337,7 @@ static inline void __remove_memory(int nid, u64 start, u64 size) {}
 extern void set_zone_contiguous(struct zone *zone);
 extern void clear_zone_contiguous(struct zone *zone);
 
+#ifdef CONFIG_MEMORY_HOTPLUG
 extern void __ref free_area_init_core_hotplug(int nid);
 extern int __add_memory(int nid, u64 start, u64 size);
 extern int add_memory(int nid, u64 start, u64 size);
@@ -364,8 +358,8 @@ extern void sparse_remove_section(struct mem_section *ms,
 		unsigned long map_offset, struct vmem_altmap *altmap);
 extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
 					  unsigned long pnum);
-extern bool allow_online_pfn_range(int nid, unsigned long pfn, unsigned long nr_pages,
-		int online_type);
 extern struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_pfn,
 		unsigned long nr_pages);
+#endif /* CONFIG_MEMORY_HOTPLUG */
+
 #endif /* __LINUX_MEMORY_HOTPLUG_H */
diff --git a/mm/sparse.c b/mm/sparse.c
index b25ad8e64839..7bd23f9d6cef 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -312,6 +312,7 @@ static unsigned long sparse_encode_mem_map(struct page *mem_map, unsigned long p
 	return coded_mem_map;
 }
 
+#ifdef CONFIG_MEMORY_HOTPLUG
 /*
  * Decode mem_map from the coded memmap
  */
@@ -321,6 +322,7 @@ struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pn
 	coded_mem_map &= SECTION_MAP_MASK;
 	return ((struct page *)coded_mem_map) + section_nr_to_pfn(pnum);
 }
+#endif /* CONFIG_MEMORY_HOTPLUG */
 
 static void __meminit sparse_init_one_section(struct mem_section *ms,
 		unsigned long pnum, struct page *mem_map,
-- 
cgit v1.2.3


From b6117199787c60539105d2de0d010146e8396fc3 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Thu, 15 Oct 2020 20:08:44 -0700
Subject: mm/memory_hotplug: prepare passing flags to add_memory() and friends
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We soon want to pass flags, e.g., to mark added System RAM resources.
mergeable.  Prepare for that.

This patch is based on a similar patch by Oscar Salvador:

https://lkml.kernel.org/r/20190625075227.15193-3-osalvador@suse.de

Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Juergen Gross <jgross@suse.com> # Xen related part
Reviewed-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Acked-by: Wei Liu <wei.liu@kernel.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Baoquan He <bhe@redhat.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Len Brown <lenb@kernel.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: Wei Liu <wei.liu@kernel.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: "Oliver O'Halloran" <oohall@gmail.com>
Cc: Pingfan Liu <kernelfans@gmail.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: Libor Pechacek <lpechacek@suse.cz>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Leonardo Bras <leobras.c@gmail.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Julien Grall <julien@xen.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Roger Pau Monné <roger.pau@citrix.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Wei Yang <richardw.yang@linux.intel.com>
Link: https://lkml.kernel.org/r/20200911103459.10306-5-david@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/powerpc/platforms/powernv/memtrace.c       |  2 +-
 arch/powerpc/platforms/pseries/hotplug-memory.c |  2 +-
 drivers/acpi/acpi_memhotplug.c                  |  3 ++-
 drivers/base/memory.c                           |  3 ++-
 drivers/dax/kmem.c                              |  2 +-
 drivers/hv/hv_balloon.c                         |  2 +-
 drivers/s390/char/sclp_cmd.c                    |  2 +-
 drivers/virtio/virtio_mem.c                     |  2 +-
 drivers/xen/balloon.c                           |  2 +-
 include/linux/memory_hotplug.h                  | 16 ++++++++++++----
 mm/memory_hotplug.c                             | 14 +++++++-------
 11 files changed, 30 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c
index 13b369d2cc45..6828108486f8 100644
--- a/arch/powerpc/platforms/powernv/memtrace.c
+++ b/arch/powerpc/platforms/powernv/memtrace.c
@@ -224,7 +224,7 @@ static int memtrace_online(void)
 			ent->mem = 0;
 		}
 
-		if (add_memory(ent->nid, ent->start, ent->size)) {
+		if (add_memory(ent->nid, ent->start, ent->size, MHP_NONE)) {
 			pr_err("Failed to add trace memory to node %d\n",
 				ent->nid);
 			ret += 1;
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 5d545b78111f..d8bbf0cc1601 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -606,7 +606,7 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb)
 	block_sz = memory_block_size_bytes();
 
 	/* Add the memory */
-	rc = __add_memory(lmb->nid, lmb->base_addr, block_sz);
+	rc = __add_memory(lmb->nid, lmb->base_addr, block_sz, MHP_NONE);
 	if (rc) {
 		invalidate_lmb_associativity_index(lmb);
 		return rc;
diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c
index ad6e90fbc813..b02fd51e5589 100644
--- a/drivers/acpi/acpi_memhotplug.c
+++ b/drivers/acpi/acpi_memhotplug.c
@@ -194,7 +194,8 @@ static int acpi_memory_enable_device(struct acpi_memory_device *mem_device)
 		if (node < 0)
 			node = memory_add_physaddr_to_nid(info->start_addr);
 
-		result = __add_memory(node, info->start_addr, info->length);
+		result = __add_memory(node, info->start_addr, info->length,
+				      MHP_NONE);
 
 		/*
 		 * If the memory block has been used by the kernel, add_memory()
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index adf828dfccf0..eef4ffb6122c 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -432,7 +432,8 @@ static ssize_t probe_store(struct device *dev, struct device_attribute *attr,
 
 	nid = memory_add_physaddr_to_nid(phys_addr);
 	ret = __add_memory(nid, phys_addr,
-			   MIN_MEMORY_BLOCK_SIZE * sections_per_block);
+			   MIN_MEMORY_BLOCK_SIZE * sections_per_block,
+			   MHP_NONE);
 
 	if (ret)
 		goto out;
diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c
index af04b6d1d263..b4368c5b6a0c 100644
--- a/drivers/dax/kmem.c
+++ b/drivers/dax/kmem.c
@@ -109,7 +109,7 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
 		 * this as RAM automatically.
 		 */
 		rc = add_memory_driver_managed(numa_node, range.start,
-				range_len(&range), kmem_name);
+				range_len(&range), kmem_name, MHP_NONE);
 
 		if (rc) {
 			dev_warn(dev, "mapping%d: %#llx-%#llx memory add failed\n",
diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c
index 32e3bc0aa665..3c0d52e24452 100644
--- a/drivers/hv/hv_balloon.c
+++ b/drivers/hv/hv_balloon.c
@@ -726,7 +726,7 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size,
 
 		nid = memory_add_physaddr_to_nid(PFN_PHYS(start_pfn));
 		ret = add_memory(nid, PFN_PHYS((start_pfn)),
-				(HA_CHUNK << PAGE_SHIFT));
+				(HA_CHUNK << PAGE_SHIFT), MHP_NONE);
 
 		if (ret) {
 			pr_err("hot_add memory failed error is %d\n", ret);
diff --git a/drivers/s390/char/sclp_cmd.c b/drivers/s390/char/sclp_cmd.c
index a864b21af602..f6e97f0830f6 100644
--- a/drivers/s390/char/sclp_cmd.c
+++ b/drivers/s390/char/sclp_cmd.c
@@ -406,7 +406,7 @@ static void __init add_memory_merged(u16 rn)
 	if (!size)
 		goto skip_add;
 	for (addr = start; addr < start + size; addr += block_size)
-		add_memory(0, addr, block_size);
+		add_memory(0, addr, block_size, MHP_NONE);
 skip_add:
 	first_rn = rn;
 	num = 1;
diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c
index 834b7c13ef3d..ed99e4335401 100644
--- a/drivers/virtio/virtio_mem.c
+++ b/drivers/virtio/virtio_mem.c
@@ -424,7 +424,7 @@ static int virtio_mem_mb_add(struct virtio_mem *vm, unsigned long mb_id)
 
 	dev_dbg(&vm->vdev->dev, "adding memory block: %lu\n", mb_id);
 	return add_memory_driver_managed(nid, addr, memory_block_size_bytes(),
-					 vm->resource_name);
+					 vm->resource_name, MHP_NONE);
 }
 
 /*
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 51427c752b37..9f40a294d398 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -331,7 +331,7 @@ static enum bp_state reserve_additional_memory(void)
 	mutex_unlock(&balloon_mutex);
 	/* add_memory_resource() requires the device_hotplug lock */
 	lock_device_hotplug();
-	rc = add_memory_resource(nid, resource);
+	rc = add_memory_resource(nid, resource, MHP_NONE);
 	unlock_device_hotplug();
 	mutex_lock(&balloon_mutex);
 
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 1504b4d5ae6c..33eb80fdba22 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -57,6 +57,12 @@ enum {
 	MMOP_ONLINE_MOVABLE,
 };
 
+/* Flags for add_memory() and friends to specify memory hotplug details. */
+typedef int __bitwise mhp_t;
+
+/* No special request */
+#define MHP_NONE		((__force mhp_t)0)
+
 /*
  * Extended parameters for memory hotplug:
  * altmap: alternative allocator for memmap array (optional)
@@ -339,11 +345,13 @@ extern void clear_zone_contiguous(struct zone *zone);
 
 #ifdef CONFIG_MEMORY_HOTPLUG
 extern void __ref free_area_init_core_hotplug(int nid);
-extern int __add_memory(int nid, u64 start, u64 size);
-extern int add_memory(int nid, u64 start, u64 size);
-extern int add_memory_resource(int nid, struct resource *resource);
+extern int __add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags);
+extern int add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags);
+extern int add_memory_resource(int nid, struct resource *resource,
+			       mhp_t mhp_flags);
 extern int add_memory_driver_managed(int nid, u64 start, u64 size,
-				     const char *resource_name);
+				     const char *resource_name,
+				     mhp_t mhp_flags);
 extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
 				   unsigned long nr_pages,
 				   struct vmem_altmap *altmap, int migratetype);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 9a7193970e77..dba71bc34daa 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1039,7 +1039,7 @@ static int online_memory_block(struct memory_block *mem, void *arg)
  *
  * we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG
  */
-int __ref add_memory_resource(int nid, struct resource *res)
+int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
 {
 	struct mhp_params params = { .pgprot = PAGE_KERNEL };
 	u64 start, size;
@@ -1119,7 +1119,7 @@ error:
 }
 
 /* requires device_hotplug_lock, see add_memory_resource() */
-int __ref __add_memory(int nid, u64 start, u64 size)
+int __ref __add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags)
 {
 	struct resource *res;
 	int ret;
@@ -1128,18 +1128,18 @@ int __ref __add_memory(int nid, u64 start, u64 size)
 	if (IS_ERR(res))
 		return PTR_ERR(res);
 
-	ret = add_memory_resource(nid, res);
+	ret = add_memory_resource(nid, res, mhp_flags);
 	if (ret < 0)
 		release_memory_resource(res);
 	return ret;
 }
 
-int add_memory(int nid, u64 start, u64 size)
+int add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags)
 {
 	int rc;
 
 	lock_device_hotplug();
-	rc = __add_memory(nid, start, size);
+	rc = __add_memory(nid, start, size, mhp_flags);
 	unlock_device_hotplug();
 
 	return rc;
@@ -1168,7 +1168,7 @@ EXPORT_SYMBOL_GPL(add_memory);
  * "System RAM ($DRIVER)".
  */
 int add_memory_driver_managed(int nid, u64 start, u64 size,
-			      const char *resource_name)
+			      const char *resource_name, mhp_t mhp_flags)
 {
 	struct resource *res;
 	int rc;
@@ -1186,7 +1186,7 @@ int add_memory_driver_managed(int nid, u64 start, u64 size,
 		goto out_unlock;
 	}
 
-	rc = add_memory_resource(nid, res);
+	rc = add_memory_resource(nid, res, mhp_flags);
 	if (rc < 0)
 		release_memory_resource(res);
 
-- 
cgit v1.2.3


From 9ca6551ee24368a4d2b09566ea4d10fe87860379 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Thu, 15 Oct 2020 20:08:49 -0700
Subject: mm/memory_hotplug: MEMHP_MERGE_RESOURCE to specify merging of System
 RAM resources
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some add_memory*() users add memory in small, contiguous memory blocks.
Examples include virtio-mem, hyper-v balloon, and the XEN balloon.

This can quickly result in a lot of memory resources, whereby the actual
resource boundaries are not of interest (e.g., it might be relevant for
DIMMs, exposed via /proc/iomem to user space).  We really want to merge
added resources in this scenario where possible.

Let's provide a flag (MEMHP_MERGE_RESOURCE) to specify that a resource
either created within add_memory*() or passed via add_memory_resource()
shall be marked mergeable and merged with applicable siblings.

To implement that, we need a kernel/resource interface to mark selected
System RAM resources mergeable (IORESOURCE_SYSRAM_MERGEABLE) and trigger
merging.

Note: We really want to merge after the whole operation succeeded, not
directly when adding a resource to the resource tree (it would break
add_memory_resource() and require splitting resources again when the
operation failed - e.g., due to -ENOMEM).

Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Kees Cook <keescook@chromium.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: Wei Liu <wei.liu@kernel.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Roger Pau Monné <roger.pau@citrix.com>
Cc: Julien Grall <julien@xen.org>
Cc: Baoquan He <bhe@redhat.com>
Cc: Wei Yang <richardw.yang@linux.intel.com>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Len Brown <lenb@kernel.org>
Cc: Leonardo Bras <leobras.c@gmail.com>
Cc: Libor Pechacek <lpechacek@suse.cz>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: "Oliver O'Halloran" <oohall@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pingfan Liu <kernelfans@gmail.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Link: https://lkml.kernel.org/r/20200911103459.10306-6-david@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/ioport.h         |  4 +++
 include/linux/memory_hotplug.h |  7 +++++
 kernel/resource.c              | 60 ++++++++++++++++++++++++++++++++++++++++++
 mm/memory_hotplug.c            |  7 +++++
 4 files changed, 78 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index d7620d7c941a..7e61389dcb01 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -60,6 +60,7 @@ struct resource {
 
 /* IORESOURCE_SYSRAM specific bits. */
 #define IORESOURCE_SYSRAM_DRIVER_MANAGED	0x02000000 /* Always detected via a driver. */
+#define IORESOURCE_SYSRAM_MERGEABLE		0x04000000 /* Resource can be merged. */
 
 #define IORESOURCE_EXCLUSIVE	0x08000000	/* Userland may not map this resource */
 
@@ -253,6 +254,9 @@ extern void __release_region(struct resource *, resource_size_t,
 extern void release_mem_region_adjustable(struct resource *, resource_size_t,
 					  resource_size_t);
 #endif
+#ifdef CONFIG_MEMORY_HOTPLUG
+extern void merge_system_ram_resource(struct resource *res);
+#endif
 
 /* Wrappers for managed devices */
 struct device;
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 33eb80fdba22..d65c6fdc5cfc 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -62,6 +62,13 @@ typedef int __bitwise mhp_t;
 
 /* No special request */
 #define MHP_NONE		((__force mhp_t)0)
+/*
+ * Allow merging of the added System RAM resource with adjacent,
+ * mergeable resources. After a successful call to add_memory_resource()
+ * with this flag set, the resource pointer must no longer be used as it
+ * might be stale, or the resource might have changed.
+ */
+#define MEMHP_MERGE_RESOURCE	((__force mhp_t)BIT(0))
 
 /*
  * Extended parameters for memory hotplug:
diff --git a/kernel/resource.c b/kernel/resource.c
index 4c1c487abbfb..92026827d95b 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -1363,6 +1363,66 @@ retry:
 }
 #endif	/* CONFIG_MEMORY_HOTREMOVE */
 
+#ifdef CONFIG_MEMORY_HOTPLUG
+static bool system_ram_resources_mergeable(struct resource *r1,
+					   struct resource *r2)
+{
+	/* We assume either r1 or r2 is IORESOURCE_SYSRAM_MERGEABLE. */
+	return r1->flags == r2->flags && r1->end + 1 == r2->start &&
+	       r1->name == r2->name && r1->desc == r2->desc &&
+	       !r1->child && !r2->child;
+}
+
+/*
+ * merge_system_ram_resource - mark the System RAM resource mergeable and try to
+ * merge it with adjacent, mergeable resources
+ * @res: resource descriptor
+ *
+ * This interface is intended for memory hotplug, whereby lots of contiguous
+ * system ram resources are added (e.g., via add_memory*()) by a driver, and
+ * the actual resource boundaries are not of interest (e.g., it might be
+ * relevant for DIMMs). Only resources that are marked mergeable, that have the
+ * same parent, and that don't have any children are considered. All mergeable
+ * resources must be immutable during the request.
+ *
+ * Note:
+ * - The caller has to make sure that no pointers to resources that are
+ *   marked mergeable are used anymore after this call - the resource might
+ *   be freed and the pointer might be stale!
+ * - release_mem_region_adjustable() will split on demand on memory hotunplug
+ */
+void merge_system_ram_resource(struct resource *res)
+{
+	const unsigned long flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+	struct resource *cur;
+
+	if (WARN_ON_ONCE((res->flags & flags) != flags))
+		return;
+
+	write_lock(&resource_lock);
+	res->flags |= IORESOURCE_SYSRAM_MERGEABLE;
+
+	/* Try to merge with next item in the list. */
+	cur = res->sibling;
+	if (cur && system_ram_resources_mergeable(res, cur)) {
+		res->end = cur->end;
+		res->sibling = cur->sibling;
+		free_resource(cur);
+	}
+
+	/* Try to merge with previous item in the list. */
+	cur = res->parent->child;
+	while (cur && cur->sibling != res)
+		cur = cur->sibling;
+	if (cur && system_ram_resources_mergeable(cur, res)) {
+		cur->end = res->end;
+		cur->sibling = res->sibling;
+		free_resource(res);
+	}
+	write_unlock(&resource_lock);
+}
+#endif	/* CONFIG_MEMORY_HOTPLUG */
+
 /*
  * Managed region resource
  */
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index dba71bc34daa..dc7d82ece6cb 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1103,6 +1103,13 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
 	/* device_online() will take the lock when calling online_pages() */
 	mem_hotplug_done();
 
+	/*
+	 * In case we're allowed to merge the resource, flag it and trigger
+	 * merging now that adding succeeded.
+	 */
+	if (mhp_flags & MEMHP_MERGE_RESOURCE)
+		merge_system_ram_resource(res);
+
 	/* online pages if requested */
 	if (memhp_default_online_type != MMOP_OFFLINE)
 		walk_memory_blocks(start, size, NULL, online_memory_block);
-- 
cgit v1.2.3


From cb8e3c8b4f45e4ed8987a581956dc9c3827a5bcf Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Thu, 15 Oct 2020 20:09:12 -0700
Subject: kernel/resource: make iomem_resource implicit in
 release_mem_region_adjustable()

"mem" in the name already indicates the root, similar to
release_mem_region() and devm_request_mem_region().  Make it implicit.
The only single caller always passes iomem_resource, other parents are not
applicable.

Suggested-by: Wei Yang <richard.weiyang@linux.alibaba.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Kees Cook <keescook@chromium.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Baoquan He <bhe@redhat.com>
Link: https://lkml.kernel.org/r/20200916073041.10355-1-david@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/ioport.h | 3 +--
 kernel/resource.c      | 5 ++---
 mm/memory_hotplug.c    | 2 +-
 3 files changed, 4 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index 7e61389dcb01..5135d4b86cd6 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -251,8 +251,7 @@ extern struct resource * __request_region(struct resource *,
 extern void __release_region(struct resource *, resource_size_t,
 				resource_size_t);
 #ifdef CONFIG_MEMORY_HOTREMOVE
-extern void release_mem_region_adjustable(struct resource *, resource_size_t,
-					  resource_size_t);
+extern void release_mem_region_adjustable(resource_size_t, resource_size_t);
 #endif
 #ifdef CONFIG_MEMORY_HOTPLUG
 extern void merge_system_ram_resource(struct resource *res);
diff --git a/kernel/resource.c b/kernel/resource.c
index 92026827d95b..3ae2f56cc79d 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -1240,7 +1240,6 @@ EXPORT_SYMBOL(__release_region);
 #ifdef CONFIG_MEMORY_HOTREMOVE
 /**
  * release_mem_region_adjustable - release a previously reserved memory region
- * @parent: parent resource descriptor
  * @start: resource start address
  * @size: resource region size
  *
@@ -1258,9 +1257,9 @@ EXPORT_SYMBOL(__release_region);
  *   assumes that all children remain in the lower address entry for
  *   simplicity.  Enhance this logic when necessary.
  */
-void release_mem_region_adjustable(struct resource *parent,
-				   resource_size_t start, resource_size_t size)
+void release_mem_region_adjustable(resource_size_t start, resource_size_t size)
 {
+	struct resource *parent = &iomem_resource;
 	struct resource *new_res = NULL;
 	bool alloc_nofail = false;
 	struct resource **p;
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index dc7d82ece6cb..1efc92f66b9d 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1767,7 +1767,7 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size)
 		memblock_remove(start, size);
 	}
 
-	release_mem_region_adjustable(&iomem_resource, start, size);
+	release_mem_region_adjustable(start, size);
 
 	try_offline_node(nid);
 
-- 
cgit v1.2.3


From 90c7eaeb14a325a760d732184ff1fbed47e5fa98 Mon Sep 17 00:00:00 2001
From: Laurent Dufour <ldufour@linux.ibm.com>
Date: Thu, 15 Oct 2020 20:09:15 -0700
Subject: mm: don't panic when links can't be created in sysfs

At boot time, or when doing memory hot-add operations, if the links in
sysfs can't be created, the system is still able to run, so just report
the error in the kernel log rather than BUG_ON and potentially make system
unusable because the callpath can be called with locks held.

Since the number of memory blocks managed could be high, the messages are
rate limited.

As a consequence, link_mem_sections() has no status to report anymore.

Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: "Rafael J . Wysocki" <rafael@kernel.org>
Cc: Scott Cheloha <cheloha@linux.ibm.com>
Cc: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/20200915094143.79181-4-ldufour@linux.ibm.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/base/node.c  | 33 +++++++++++++++++++++------------
 include/linux/node.h | 16 +++++++---------
 mm/memory_hotplug.c  |  5 ++---
 3 files changed, 30 insertions(+), 24 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/node.c b/drivers/base/node.c
index 43d21f9e88b1..6ffa470e2984 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -772,8 +772,8 @@ static int __ref get_nid_for_pfn(unsigned long pfn)
 	return pfn_to_nid(pfn);
 }
 
-static int do_register_memory_block_under_node(int nid,
-					       struct memory_block *mem_blk)
+static void do_register_memory_block_under_node(int nid,
+						struct memory_block *mem_blk)
 {
 	int ret;
 
@@ -786,12 +786,19 @@ static int do_register_memory_block_under_node(int nid,
 	ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj,
 				       &mem_blk->dev.kobj,
 				       kobject_name(&mem_blk->dev.kobj));
-	if (ret)
-		return ret;
+	if (ret && ret != -EEXIST)
+		dev_err_ratelimited(&node_devices[nid]->dev,
+				    "can't create link to %s in sysfs (%d)\n",
+				    kobject_name(&mem_blk->dev.kobj), ret);
 
-	return sysfs_create_link_nowarn(&mem_blk->dev.kobj,
+	ret = sysfs_create_link_nowarn(&mem_blk->dev.kobj,
 				&node_devices[nid]->dev.kobj,
 				kobject_name(&node_devices[nid]->dev.kobj));
+	if (ret && ret != -EEXIST)
+		dev_err_ratelimited(&mem_blk->dev,
+				    "can't create link to %s in sysfs (%d)\n",
+				    kobject_name(&node_devices[nid]->dev.kobj),
+				    ret);
 }
 
 /* register memory section under specified node if it spans that node */
@@ -827,7 +834,8 @@ static int register_mem_block_under_node_early(struct memory_block *mem_blk,
 		if (page_nid != nid)
 			continue;
 
-		return do_register_memory_block_under_node(nid, mem_blk);
+		do_register_memory_block_under_node(nid, mem_blk);
+		return 0;
 	}
 	/* mem section does not span the specified node */
 	return 0;
@@ -842,7 +850,8 @@ static int register_mem_block_under_node_hotplug(struct memory_block *mem_blk,
 {
 	int nid = *(int *)arg;
 
-	return do_register_memory_block_under_node(nid, mem_blk);
+	do_register_memory_block_under_node(nid, mem_blk);
+	return 0;
 }
 
 /*
@@ -860,8 +869,8 @@ void unregister_memory_block_under_nodes(struct memory_block *mem_blk)
 			  kobject_name(&node_devices[mem_blk->nid]->dev.kobj));
 }
 
-int link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn,
-		      enum meminit_context context)
+void link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn,
+		       enum meminit_context context)
 {
 	walk_memory_blocks_func_t func;
 
@@ -870,9 +879,9 @@ int link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn,
 	else
 		func = register_mem_block_under_node_early;
 
-	return walk_memory_blocks(PFN_PHYS(start_pfn),
-				  PFN_PHYS(end_pfn - start_pfn), (void *)&nid,
-				  func);
+	walk_memory_blocks(PFN_PHYS(start_pfn), PFN_PHYS(end_pfn - start_pfn),
+			   (void *)&nid, func);
+	return;
 }
 
 #ifdef CONFIG_HUGETLBFS
diff --git a/include/linux/node.h b/include/linux/node.h
index 014ba3ab2efd..8e5a29897936 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -99,15 +99,14 @@ extern struct node *node_devices[];
 typedef  void (*node_registration_func_t)(struct node *);
 
 #if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_NUMA)
-int link_mem_sections(int nid, unsigned long start_pfn,
-		      unsigned long end_pfn,
-		      enum meminit_context context);
+void link_mem_sections(int nid, unsigned long start_pfn,
+		       unsigned long end_pfn,
+		       enum meminit_context context);
 #else
-static inline int link_mem_sections(int nid, unsigned long start_pfn,
-				    unsigned long end_pfn,
-				    enum meminit_context context)
+static inline void link_mem_sections(int nid, unsigned long start_pfn,
+				     unsigned long end_pfn,
+				     enum meminit_context context)
 {
-	return 0;
 }
 #endif
 
@@ -130,8 +129,7 @@ static inline int register_one_node(int nid)
 		if (error)
 			return error;
 		/* link memory sections under this node */
-		error = link_mem_sections(nid, start_pfn, end_pfn,
-					  MEMINIT_EARLY);
+		link_mem_sections(nid, start_pfn, end_pfn, MEMINIT_EARLY);
 	}
 
 	return error;
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 1efc92f66b9d..d397af38f9ce 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1092,9 +1092,8 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
 	}
 
 	/* link memory sections under this node.*/
-	ret = link_mem_sections(nid, PFN_DOWN(start), PFN_UP(start + size - 1),
-				MEMINIT_HOTPLUG);
-	BUG_ON(ret);
+	link_mem_sections(nid, PFN_DOWN(start), PFN_UP(start + size - 1),
+			  MEMINIT_HOTPLUG);
 
 	/* create new memmap entry */
 	if (!strcmp(res->name, "System RAM"))
-- 
cgit v1.2.3


From ed0173733dd468883198c3136284394320b8fad6 Mon Sep 17 00:00:00 2001
From: Yu Zhao <yuzhao@google.com>
Date: Thu, 15 Oct 2020 20:09:55 -0700
Subject: mm: use self-explanatory macros rather than "2"

Signed-off-by: Yu Zhao <yuzhao@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Alex Shi <alex.shi@linux.alibaba.com>
Link: http://lkml.kernel.org/r/20200831175042.3527153-2-yuzhao@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmzone.h | 12 ++++++++----
 include/linux/vmstat.h |  2 +-
 mm/vmscan.c            |  2 +-
 3 files changed, 10 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index c27fb1faffe5..7e0ea3fe95ca 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -266,6 +266,8 @@ static inline bool is_active_lru(enum lru_list lru)
 	return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE);
 }
 
+#define ANON_AND_FILE 2
+
 enum lruvec_flags {
 	LRUVEC_CONGESTED,		/* lruvec has many dirty pages
 					 * backed by a congested BDI
@@ -283,8 +285,8 @@ struct lruvec {
 	unsigned long			file_cost;
 	/* Non-resident age, driven by LRU movement */
 	atomic_long_t			nonresident_age;
-	/* Refaults at the time of last reclaim cycle, anon=0, file=1 */
-	unsigned long			refaults[2];
+	/* Refaults at the time of last reclaim cycle */
+	unsigned long			refaults[ANON_AND_FILE];
 	/* Various lruvec state flags (enum lruvec_flags) */
 	unsigned long			flags;
 #ifdef CONFIG_MEMCG
@@ -441,6 +443,8 @@ enum zone_type {
 
 #ifndef __GENERATING_BOUNDS_H
 
+#define ASYNC_AND_SYNC 2
+
 struct zone {
 	/* Read-mostly fields */
 
@@ -560,8 +564,8 @@ struct zone {
 #if defined CONFIG_COMPACTION || defined CONFIG_CMA
 	/* pfn where compaction free scanner should start */
 	unsigned long		compact_cached_free_pfn;
-	/* pfn where async and sync compaction migration scanner should start */
-	unsigned long		compact_cached_migrate_pfn[2];
+	/* pfn where compaction migration scanner should start */
+	unsigned long		compact_cached_migrate_pfn[ASYNC_AND_SYNC];
 	unsigned long		compact_init_migrate_pfn;
 	unsigned long		compact_init_free_pfn;
 #endif
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 7557c1070fd7..322dcbfcc933 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -28,7 +28,7 @@ struct reclaim_stat {
 	unsigned nr_writeback;
 	unsigned nr_immediate;
 	unsigned nr_pageout;
-	unsigned nr_activate[2];
+	unsigned nr_activate[ANON_AND_FILE];
 	unsigned nr_ref_keep;
 	unsigned nr_unmap_fail;
 	unsigned nr_lazyfree_fail;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index fc4dee9b91f8..1b8f0e059767 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2239,7 +2239,7 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
 	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
 	unsigned long anon_cost, file_cost, total_cost;
 	int swappiness = mem_cgroup_swappiness(memcg);
-	u64 fraction[2];
+	u64 fraction[ANON_AND_FILE];
 	u64 denominator = 0;	/* gcc */
 	enum scan_balance scan_balance;
 	unsigned long ap, fp;
-- 
cgit v1.2.3


From 1f0f8c0de09066d23760c1f5fac2cd53b32f1127 Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.ibm.com>
Date: Thu, 15 Oct 2020 20:10:11 -0700
Subject: include/linux/mmzone.h: remove unused early_pfn_valid()

The early_pfn_valid() macro is defined but it is never used.  Remove it.

Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: David Hildenbrand <david@redhat.com>
Link: https://lkml.kernel.org/r/20200923162915.26935-1-rppt@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmzone.h | 5 -----
 1 file changed, 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 7e0ea3fe95ca..fb3bf696c05e 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1420,7 +1420,6 @@ static inline unsigned long next_present_section_nr(unsigned long section_nr)
 #define pfn_to_nid(pfn)		(0)
 #endif
 
-#define early_pfn_valid(pfn)	pfn_valid(pfn)
 void sparse_init(void);
 #else
 #define sparse_init()	do {} while (0)
@@ -1440,10 +1439,6 @@ struct mminit_pfnnid_cache {
 	int last_nid;
 };
 
-#ifndef early_pfn_valid
-#define early_pfn_valid(pfn)	(1)
-#endif
-
 /*
  * If it is possible to have holes within a MAX_ORDER_NR_PAGES, then we
  * need to check pfn validity within that MAX_ORDER_NR_PAGES block.
-- 
cgit v1.2.3


From b296a6d53339a79082c1d2c1761e948e8b3def69 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 15 Oct 2020 20:10:21 -0700
Subject: kernel.h: split out min()/max() et al. helpers

kernel.h is being used as a dump for all kinds of stuff for a long time.
Here is the attempt to start cleaning it up by splitting out min()/max()
et al.  helpers.

At the same time convert users in header and lib folder to use new header.
Though for time being include new header back to kernel.h to avoid
twisted indirected includes for other existing users.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Joe Perches <joe@perches.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lkml.kernel.org/r/20200910164152.GA1891694@smile.fi.intel.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/blkdev.h    |   1 +
 include/linux/bvec.h      |   6 +-
 include/linux/jiffies.h   |   3 +-
 include/linux/kernel.h    | 150 +--------------------------------------------
 include/linux/minmax.h    | 153 ++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/nodemask.h  |   2 +-
 include/linux/uaccess.h   |   1 +
 kernel/range.c            |   3 +-
 lib/find_bit.c            |   1 +
 lib/hexdump.c             |   1 +
 lib/math/rational.c       |   2 +-
 lib/math/reciprocal_div.c |   1 +
 12 files changed, 170 insertions(+), 154 deletions(-)
 create mode 100644 include/linux/minmax.h

(limited to 'include/linux')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c09375e0a0eb..639cae2c158b 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -8,6 +8,7 @@
 #include <linux/genhd.h>
 #include <linux/list.h>
 #include <linux/llist.h>
+#include <linux/minmax.h>
 #include <linux/timer.h>
 #include <linux/workqueue.h>
 #include <linux/pagemap.h>
diff --git a/include/linux/bvec.h b/include/linux/bvec.h
index dd74503f7e5e..2efec10bf792 100644
--- a/include/linux/bvec.h
+++ b/include/linux/bvec.h
@@ -7,10 +7,14 @@
 #ifndef __LINUX_BVEC_ITER_H
 #define __LINUX_BVEC_ITER_H
 
-#include <linux/kernel.h>
 #include <linux/bug.h>
 #include <linux/errno.h>
+#include <linux/limits.h>
+#include <linux/minmax.h>
 #include <linux/mm.h>
+#include <linux/types.h>
+
+struct page;
 
 /**
  * struct bio_vec - a contiguous range of physical memory addresses
diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h
index fed6ba96c527..5e13f801c902 100644
--- a/include/linux/jiffies.h
+++ b/include/linux/jiffies.h
@@ -3,8 +3,9 @@
 #define _LINUX_JIFFIES_H
 
 #include <linux/cache.h>
+#include <linux/limits.h>
 #include <linux/math64.h>
-#include <linux/kernel.h>
+#include <linux/minmax.h>
 #include <linux/types.h>
 #include <linux/time.h>
 #include <linux/timex.h>
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index e4aa29b1ad62..c629215fdad9 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -11,6 +11,7 @@
 #include <linux/compiler.h>
 #include <linux/bitops.h>
 #include <linux/log2.h>
+#include <linux/minmax.h>
 #include <linux/typecheck.h>
 #include <linux/printk.h>
 #include <linux/build_bug.h>
@@ -833,155 +834,6 @@ ftrace_vprintk(const char *fmt, va_list ap)
 static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { }
 #endif /* CONFIG_TRACING */
 
-/*
- * min()/max()/clamp() macros must accomplish three things:
- *
- * - avoid multiple evaluations of the arguments (so side-effects like
- *   "x++" happen only once) when non-constant.
- * - perform strict type-checking (to generate warnings instead of
- *   nasty runtime surprises). See the "unnecessary" pointer comparison
- *   in __typecheck().
- * - retain result as a constant expressions when called with only
- *   constant expressions (to avoid tripping VLA warnings in stack
- *   allocation usage).
- */
-#define __typecheck(x, y) \
-		(!!(sizeof((typeof(x) *)1 == (typeof(y) *)1)))
-
-/*
- * This returns a constant expression while determining if an argument is
- * a constant expression, most importantly without evaluating the argument.
- * Glory to Martin Uecker <Martin.Uecker@med.uni-goettingen.de>
- */
-#define __is_constexpr(x) \
-	(sizeof(int) == sizeof(*(8 ? ((void *)((long)(x) * 0l)) : (int *)8)))
-
-#define __no_side_effects(x, y) \
-		(__is_constexpr(x) && __is_constexpr(y))
-
-#define __safe_cmp(x, y) \
-		(__typecheck(x, y) && __no_side_effects(x, y))
-
-#define __cmp(x, y, op)	((x) op (y) ? (x) : (y))
-
-#define __cmp_once(x, y, unique_x, unique_y, op) ({	\
-		typeof(x) unique_x = (x);		\
-		typeof(y) unique_y = (y);		\
-		__cmp(unique_x, unique_y, op); })
-
-#define __careful_cmp(x, y, op) \
-	__builtin_choose_expr(__safe_cmp(x, y), \
-		__cmp(x, y, op), \
-		__cmp_once(x, y, __UNIQUE_ID(__x), __UNIQUE_ID(__y), op))
-
-/**
- * min - return minimum of two values of the same or compatible types
- * @x: first value
- * @y: second value
- */
-#define min(x, y)	__careful_cmp(x, y, <)
-
-/**
- * max - return maximum of two values of the same or compatible types
- * @x: first value
- * @y: second value
- */
-#define max(x, y)	__careful_cmp(x, y, >)
-
-/**
- * min3 - return minimum of three values
- * @x: first value
- * @y: second value
- * @z: third value
- */
-#define min3(x, y, z) min((typeof(x))min(x, y), z)
-
-/**
- * max3 - return maximum of three values
- * @x: first value
- * @y: second value
- * @z: third value
- */
-#define max3(x, y, z) max((typeof(x))max(x, y), z)
-
-/**
- * min_not_zero - return the minimum that is _not_ zero, unless both are zero
- * @x: value1
- * @y: value2
- */
-#define min_not_zero(x, y) ({			\
-	typeof(x) __x = (x);			\
-	typeof(y) __y = (y);			\
-	__x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); })
-
-/**
- * clamp - return a value clamped to a given range with strict typechecking
- * @val: current value
- * @lo: lowest allowable value
- * @hi: highest allowable value
- *
- * This macro does strict typechecking of @lo/@hi to make sure they are of the
- * same type as @val.  See the unnecessary pointer comparisons.
- */
-#define clamp(val, lo, hi) min((typeof(val))max(val, lo), hi)
-
-/*
- * ..and if you can't take the strict
- * types, you can specify one yourself.
- *
- * Or not use min/max/clamp at all, of course.
- */
-
-/**
- * min_t - return minimum of two values, using the specified type
- * @type: data type to use
- * @x: first value
- * @y: second value
- */
-#define min_t(type, x, y)	__careful_cmp((type)(x), (type)(y), <)
-
-/**
- * max_t - return maximum of two values, using the specified type
- * @type: data type to use
- * @x: first value
- * @y: second value
- */
-#define max_t(type, x, y)	__careful_cmp((type)(x), (type)(y), >)
-
-/**
- * clamp_t - return a value clamped to a given range using a given type
- * @type: the type of variable to use
- * @val: current value
- * @lo: minimum allowable value
- * @hi: maximum allowable value
- *
- * This macro does no typechecking and uses temporary variables of type
- * @type to make all the comparisons.
- */
-#define clamp_t(type, val, lo, hi) min_t(type, max_t(type, val, lo), hi)
-
-/**
- * clamp_val - return a value clamped to a given range using val's type
- * @val: current value
- * @lo: minimum allowable value
- * @hi: maximum allowable value
- *
- * This macro does no typechecking and uses temporary variables of whatever
- * type the input argument @val is.  This is useful when @val is an unsigned
- * type and @lo and @hi are literals that will otherwise be assigned a signed
- * integer type.
- */
-#define clamp_val(val, lo, hi) clamp_t(typeof(val), val, lo, hi)
-
-
-/**
- * swap - swap values of @a and @b
- * @a: first value
- * @b: second value
- */
-#define swap(a, b) \
-	do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0)
-
 /* This counts to 12. Any more, it will return 13th argument. */
 #define __COUNT_ARGS(_0, _1, _2, _3, _4, _5, _6, _7, _8, _9, _10, _11, _12, _n, X...) _n
 #define COUNT_ARGS(X...) __COUNT_ARGS(, ##X, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
diff --git a/include/linux/minmax.h b/include/linux/minmax.h
new file mode 100644
index 000000000000..c0f57b0c64d9
--- /dev/null
+++ b/include/linux/minmax.h
@@ -0,0 +1,153 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_MINMAX_H
+#define _LINUX_MINMAX_H
+
+/*
+ * min()/max()/clamp() macros must accomplish three things:
+ *
+ * - avoid multiple evaluations of the arguments (so side-effects like
+ *   "x++" happen only once) when non-constant.
+ * - perform strict type-checking (to generate warnings instead of
+ *   nasty runtime surprises). See the "unnecessary" pointer comparison
+ *   in __typecheck().
+ * - retain result as a constant expressions when called with only
+ *   constant expressions (to avoid tripping VLA warnings in stack
+ *   allocation usage).
+ */
+#define __typecheck(x, y) \
+	(!!(sizeof((typeof(x) *)1 == (typeof(y) *)1)))
+
+/*
+ * This returns a constant expression while determining if an argument is
+ * a constant expression, most importantly without evaluating the argument.
+ * Glory to Martin Uecker <Martin.Uecker@med.uni-goettingen.de>
+ */
+#define __is_constexpr(x) \
+	(sizeof(int) == sizeof(*(8 ? ((void *)((long)(x) * 0l)) : (int *)8)))
+
+#define __no_side_effects(x, y) \
+		(__is_constexpr(x) && __is_constexpr(y))
+
+#define __safe_cmp(x, y) \
+		(__typecheck(x, y) && __no_side_effects(x, y))
+
+#define __cmp(x, y, op)	((x) op (y) ? (x) : (y))
+
+#define __cmp_once(x, y, unique_x, unique_y, op) ({	\
+		typeof(x) unique_x = (x);		\
+		typeof(y) unique_y = (y);		\
+		__cmp(unique_x, unique_y, op); })
+
+#define __careful_cmp(x, y, op) \
+	__builtin_choose_expr(__safe_cmp(x, y), \
+		__cmp(x, y, op), \
+		__cmp_once(x, y, __UNIQUE_ID(__x), __UNIQUE_ID(__y), op))
+
+/**
+ * min - return minimum of two values of the same or compatible types
+ * @x: first value
+ * @y: second value
+ */
+#define min(x, y)	__careful_cmp(x, y, <)
+
+/**
+ * max - return maximum of two values of the same or compatible types
+ * @x: first value
+ * @y: second value
+ */
+#define max(x, y)	__careful_cmp(x, y, >)
+
+/**
+ * min3 - return minimum of three values
+ * @x: first value
+ * @y: second value
+ * @z: third value
+ */
+#define min3(x, y, z) min((typeof(x))min(x, y), z)
+
+/**
+ * max3 - return maximum of three values
+ * @x: first value
+ * @y: second value
+ * @z: third value
+ */
+#define max3(x, y, z) max((typeof(x))max(x, y), z)
+
+/**
+ * min_not_zero - return the minimum that is _not_ zero, unless both are zero
+ * @x: value1
+ * @y: value2
+ */
+#define min_not_zero(x, y) ({			\
+	typeof(x) __x = (x);			\
+	typeof(y) __y = (y);			\
+	__x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); })
+
+/**
+ * clamp - return a value clamped to a given range with strict typechecking
+ * @val: current value
+ * @lo: lowest allowable value
+ * @hi: highest allowable value
+ *
+ * This macro does strict typechecking of @lo/@hi to make sure they are of the
+ * same type as @val.  See the unnecessary pointer comparisons.
+ */
+#define clamp(val, lo, hi) min((typeof(val))max(val, lo), hi)
+
+/*
+ * ..and if you can't take the strict
+ * types, you can specify one yourself.
+ *
+ * Or not use min/max/clamp at all, of course.
+ */
+
+/**
+ * min_t - return minimum of two values, using the specified type
+ * @type: data type to use
+ * @x: first value
+ * @y: second value
+ */
+#define min_t(type, x, y)	__careful_cmp((type)(x), (type)(y), <)
+
+/**
+ * max_t - return maximum of two values, using the specified type
+ * @type: data type to use
+ * @x: first value
+ * @y: second value
+ */
+#define max_t(type, x, y)	__careful_cmp((type)(x), (type)(y), >)
+
+/**
+ * clamp_t - return a value clamped to a given range using a given type
+ * @type: the type of variable to use
+ * @val: current value
+ * @lo: minimum allowable value
+ * @hi: maximum allowable value
+ *
+ * This macro does no typechecking and uses temporary variables of type
+ * @type to make all the comparisons.
+ */
+#define clamp_t(type, val, lo, hi) min_t(type, max_t(type, val, lo), hi)
+
+/**
+ * clamp_val - return a value clamped to a given range using val's type
+ * @val: current value
+ * @lo: minimum allowable value
+ * @hi: maximum allowable value
+ *
+ * This macro does no typechecking and uses temporary variables of whatever
+ * type the input argument @val is.  This is useful when @val is an unsigned
+ * type and @lo and @hi are literals that will otherwise be assigned a signed
+ * integer type.
+ */
+#define clamp_val(val, lo, hi) clamp_t(typeof(val), val, lo, hi)
+
+/**
+ * swap - swap values of @a and @b
+ * @a: first value
+ * @b: second value
+ */
+#define swap(a, b) \
+	do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0)
+
+#endif	/* _LINUX_MINMAX_H */
diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
index 3334ce056335..ac398e143c9a 100644
--- a/include/linux/nodemask.h
+++ b/include/linux/nodemask.h
@@ -90,9 +90,9 @@
  * for such situations. See below and CPUMASK_ALLOC also.
  */
 
-#include <linux/kernel.h>
 #include <linux/threads.h>
 #include <linux/bitmap.h>
+#include <linux/minmax.h>
 #include <linux/numa.h>
 
 typedef struct { DECLARE_BITMAP(bits, MAX_NUMNODES); } nodemask_t;
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 1ae36bc8db35..ef084eacaa7c 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -3,6 +3,7 @@
 #define __LINUX_UACCESS_H__
 
 #include <linux/instrumented.h>
+#include <linux/minmax.h>
 #include <linux/sched.h>
 #include <linux/thread_info.h>
 
diff --git a/kernel/range.c b/kernel/range.c
index d84de6766472..56435f96da73 100644
--- a/kernel/range.c
+++ b/kernel/range.c
@@ -2,8 +2,9 @@
 /*
  * Range add and subtract
  */
-#include <linux/kernel.h>
 #include <linux/init.h>
+#include <linux/minmax.h>
+#include <linux/printk.h>
 #include <linux/sort.h>
 #include <linux/string.h>
 #include <linux/range.h>
diff --git a/lib/find_bit.c b/lib/find_bit.c
index 49f875f1baf7..4a8751010d59 100644
--- a/lib/find_bit.c
+++ b/lib/find_bit.c
@@ -16,6 +16,7 @@
 #include <linux/bitmap.h>
 #include <linux/export.h>
 #include <linux/kernel.h>
+#include <linux/minmax.h>
 
 #if !defined(find_next_bit) || !defined(find_next_zero_bit) ||			\
 	!defined(find_next_bit_le) || !defined(find_next_zero_bit_le) ||	\
diff --git a/lib/hexdump.c b/lib/hexdump.c
index 147133f8eb2f..9301578f98e8 100644
--- a/lib/hexdump.c
+++ b/lib/hexdump.c
@@ -7,6 +7,7 @@
 #include <linux/ctype.h>
 #include <linux/errno.h>
 #include <linux/kernel.h>
+#include <linux/minmax.h>
 #include <linux/export.h>
 #include <asm/unaligned.h>
 
diff --git a/lib/math/rational.c b/lib/math/rational.c
index df75c8809693..9781d521963d 100644
--- a/lib/math/rational.c
+++ b/lib/math/rational.c
@@ -11,7 +11,7 @@
 #include <linux/rational.h>
 #include <linux/compiler.h>
 #include <linux/export.h>
-#include <linux/kernel.h>
+#include <linux/minmax.h>
 
 /*
  * calculate best rational approximation for a given fraction
diff --git a/lib/math/reciprocal_div.c b/lib/math/reciprocal_div.c
index bf043258fa00..32436dd4171e 100644
--- a/lib/math/reciprocal_div.c
+++ b/lib/math/reciprocal_div.c
@@ -4,6 +4,7 @@
 #include <asm/div64.h>
 #include <linux/reciprocal_div.h>
 #include <linux/export.h>
+#include <linux/minmax.h>
 
 /*
  * For a description of the algorithm please have a look at
-- 
cgit v1.2.3


From 3b6742618ed9216dd6caad968fe8c83b32dff485 Mon Sep 17 00:00:00 2001
From: Stephen Boyd <swboyd@chromium.org>
Date: Thu, 15 Oct 2020 20:11:17 -0700
Subject: lib/idr.c: document calling context for IDA APIs mustn't use locks

The documentation for these functions indicates that callers don't need to
hold a lock while calling them, but that documentation is only in one
place under "IDA Usage".  Let's state the same information on each IDA
function so that it's clear what the calling context requires.
Furthermore, let's document ida_simple_get() with the same information so
that callers know how this API works.

Signed-off-by: Stephen Boyd <swboyd@chromium.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Tri Vo <trong@android.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Matthew Wilcox <willy@infradead.org>
Link: https://lkml.kernel.org/r/20200910055246.2297797-1-swboyd@chromium.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/idr.h | 9 ++++++---
 lib/idr.c           | 9 ++++++---
 2 files changed, 12 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/idr.h b/include/linux/idr.h
index 3ade03e5c7af..b235ed987021 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -263,7 +263,8 @@ void ida_destroy(struct ida *ida);
  *
  * Allocate an ID between 0 and %INT_MAX, inclusive.
  *
- * Context: Any context.
+ * Context: Any context. It is safe to call this function without
+ * locking in your code.
  * Return: The allocated ID, or %-ENOMEM if memory could not be allocated,
  * or %-ENOSPC if there are no free IDs.
  */
@@ -280,7 +281,8 @@ static inline int ida_alloc(struct ida *ida, gfp_t gfp)
  *
  * Allocate an ID between @min and %INT_MAX, inclusive.
  *
- * Context: Any context.
+ * Context: Any context. It is safe to call this function without
+ * locking in your code.
  * Return: The allocated ID, or %-ENOMEM if memory could not be allocated,
  * or %-ENOSPC if there are no free IDs.
  */
@@ -297,7 +299,8 @@ static inline int ida_alloc_min(struct ida *ida, unsigned int min, gfp_t gfp)
  *
  * Allocate an ID between 0 and @max, inclusive.
  *
- * Context: Any context.
+ * Context: Any context. It is safe to call this function without
+ * locking in your code.
  * Return: The allocated ID, or %-ENOMEM if memory could not be allocated,
  * or %-ENOSPC if there are no free IDs.
  */
diff --git a/lib/idr.c b/lib/idr.c
index c2cf2c52bbde..3fa8be43696f 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -372,7 +372,8 @@ EXPORT_SYMBOL(idr_replace);
  * Allocate an ID between @min and @max, inclusive.  The allocated ID will
  * not exceed %INT_MAX, even if @max is larger.
  *
- * Context: Any context.
+ * Context: Any context. It is safe to call this function without
+ * locking in your code.
  * Return: The allocated ID, or %-ENOMEM if memory could not be allocated,
  * or %-ENOSPC if there are no free IDs.
  */
@@ -479,7 +480,8 @@ EXPORT_SYMBOL(ida_alloc_range);
  * @ida: IDA handle.
  * @id: Previously allocated ID.
  *
- * Context: Any context.
+ * Context: Any context. It is safe to call this function without
+ * locking in your code.
  */
 void ida_free(struct ida *ida, unsigned int id)
 {
@@ -531,7 +533,8 @@ EXPORT_SYMBOL(ida_free);
  * or freed.  If the IDA is already empty, there is no need to call this
  * function.
  *
- * Context: Any context.
+ * Context: Any context. It is safe to call this function without
+ * locking in your code.
  */
 void ida_destroy(struct ida *ida)
 {
-- 
cgit v1.2.3


From 3264ceec8f17a99a3895de7de06b4d7e9c8f3f30 Mon Sep 17 00:00:00 2001
From: Stephen Boyd <swboyd@chromium.org>
Date: Thu, 15 Oct 2020 20:11:21 -0700
Subject: lib/idr.c: document that ida_simple_{get,remove}() are deprecated

These two functions are deprecated.  Users should call ida_alloc() or
ida_free() respectively instead.  Add documentation to this effect until
the macro can be removed.

Signed-off-by: Stephen Boyd <swboyd@chromium.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Tri Vo <trong@android.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Matthew Wilcox <willy@infradead.org>
Link: https://lkml.kernel.org/r/20200910055246.2297797-2-swboyd@chromium.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/idr.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/idr.h b/include/linux/idr.h
index b235ed987021..a0dce14090a9 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -314,6 +314,10 @@ static inline void ida_init(struct ida *ida)
 	xa_init_flags(&ida->xa, IDA_INIT_FLAGS);
 }
 
+/*
+ * ida_simple_get() and ida_simple_remove() are deprecated. Use
+ * ida_alloc() and ida_free() instead respectively.
+ */
 #define ida_simple_get(ida, start, end, gfp)	\
 			ida_alloc_range(ida, start, (end) - 1, gfp)
 #define ida_simple_remove(ida, id)	ida_free(ida, id)
-- 
cgit v1.2.3


From e130816164e244b692921de49771eeb28205152d Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 15 Oct 2020 20:11:31 -0700
Subject: include/linux/list.h: add a macro to test if entry is pointing to the
 head

Add a macro to test if entry is pointing to the head of the list which is
useful in cases like:

  list_for_each_entry(pos, &head, member) {
    if (cond)
      break;
  }
  if (list_entry_is_head(pos, &head, member))
    return -ERRNO;

that allows to avoid additional variable to be added to track if loop has
not been stopped in the middle.

While here, convert list_for_each_entry*() family of macros to use a new one.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Cezary Rojewski <cezary.rojewski@intel.com>
Link: https://lkml.kernel.org/r/20200929134342.51489-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/list.h | 29 +++++++++++++++++++----------
 1 file changed, 19 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/list.h b/include/linux/list.h
index 0d0d17a10d25..a18c87b63376 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -609,6 +609,15 @@ static inline void list_splice_tail_init(struct list_head *list,
 	     pos != (head); \
 	     pos = n, n = pos->prev)
 
+/**
+ * list_entry_is_head - test if the entry points to the head of the list
+ * @pos:	the type * to cursor
+ * @head:	the head for your list.
+ * @member:	the name of the list_head within the struct.
+ */
+#define list_entry_is_head(pos, head, member)				\
+	(&pos->member == (head))
+
 /**
  * list_for_each_entry	-	iterate over list of given type
  * @pos:	the type * to use as a loop cursor.
@@ -617,7 +626,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  */
 #define list_for_each_entry(pos, head, member)				\
 	for (pos = list_first_entry(head, typeof(*pos), member);	\
-	     &pos->member != (head);					\
+	     !list_entry_is_head(pos, head, member);			\
 	     pos = list_next_entry(pos, member))
 
 /**
@@ -628,7 +637,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  */
 #define list_for_each_entry_reverse(pos, head, member)			\
 	for (pos = list_last_entry(head, typeof(*pos), member);		\
-	     &pos->member != (head); 					\
+	     !list_entry_is_head(pos, head, member); 			\
 	     pos = list_prev_entry(pos, member))
 
 /**
@@ -653,7 +662,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  */
 #define list_for_each_entry_continue(pos, head, member) 		\
 	for (pos = list_next_entry(pos, member);			\
-	     &pos->member != (head);					\
+	     !list_entry_is_head(pos, head, member);			\
 	     pos = list_next_entry(pos, member))
 
 /**
@@ -667,7 +676,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  */
 #define list_for_each_entry_continue_reverse(pos, head, member)		\
 	for (pos = list_prev_entry(pos, member);			\
-	     &pos->member != (head);					\
+	     !list_entry_is_head(pos, head, member);			\
 	     pos = list_prev_entry(pos, member))
 
 /**
@@ -679,7 +688,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * Iterate over list of given type, continuing from current position.
  */
 #define list_for_each_entry_from(pos, head, member) 			\
-	for (; &pos->member != (head);					\
+	for (; !list_entry_is_head(pos, head, member);			\
 	     pos = list_next_entry(pos, member))
 
 /**
@@ -692,7 +701,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * Iterate backwards over list of given type, continuing from current position.
  */
 #define list_for_each_entry_from_reverse(pos, head, member)		\
-	for (; &pos->member != (head);					\
+	for (; !list_entry_is_head(pos, head, member);			\
 	     pos = list_prev_entry(pos, member))
 
 /**
@@ -705,7 +714,7 @@ static inline void list_splice_tail_init(struct list_head *list,
 #define list_for_each_entry_safe(pos, n, head, member)			\
 	for (pos = list_first_entry(head, typeof(*pos), member),	\
 		n = list_next_entry(pos, member);			\
-	     &pos->member != (head); 					\
+	     !list_entry_is_head(pos, head, member); 			\
 	     pos = n, n = list_next_entry(n, member))
 
 /**
@@ -721,7 +730,7 @@ static inline void list_splice_tail_init(struct list_head *list,
 #define list_for_each_entry_safe_continue(pos, n, head, member) 		\
 	for (pos = list_next_entry(pos, member), 				\
 		n = list_next_entry(pos, member);				\
-	     &pos->member != (head);						\
+	     !list_entry_is_head(pos, head, member);				\
 	     pos = n, n = list_next_entry(n, member))
 
 /**
@@ -736,7 +745,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  */
 #define list_for_each_entry_safe_from(pos, n, head, member) 			\
 	for (n = list_next_entry(pos, member);					\
-	     &pos->member != (head);						\
+	     !list_entry_is_head(pos, head, member);				\
 	     pos = n, n = list_next_entry(n, member))
 
 /**
@@ -752,7 +761,7 @@ static inline void list_splice_tail_init(struct list_head *list,
 #define list_for_each_entry_safe_reverse(pos, n, head, member)		\
 	for (pos = list_last_entry(head, typeof(*pos), member),		\
 		n = list_prev_entry(pos, member);			\
-	     &pos->member != (head); 					\
+	     !list_entry_is_head(pos, head, member); 			\
 	     pos = n, n = list_prev_entry(n, member))
 
 /**
-- 
cgit v1.2.3


From a9eb63705e379f10a3c9d13fc6aee8b50805e862 Mon Sep 17 00:00:00 2001
From: Wei Yang <richard.weiyang@linux.alibaba.com>
Date: Thu, 15 Oct 2020 20:11:41 -0700
Subject: bitops: simplify get_count_order_long()

These two cases could be unified into one.

Signed-off-by: Wei Yang <richard.weiyang@linux.alibaba.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lkml.kernel.org/r/20200807085837.11697-2-richard.weiyang@linux.alibaba.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/bitops.h | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index 99f2ac30b1d9..030a98f0c452 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -206,10 +206,7 @@ static inline int get_count_order_long(unsigned long l)
 {
 	if (l == 0UL)
 		return -1;
-	else if (l & (l - 1UL))
-		return (int)fls_long(l);
-	else
-		return (int)fls_long(l) - 1;
+	return (int)fls_long(--l);
 }
 
 /**
-- 
cgit v1.2.3


From 004fba1ae6ddd66ba0faa4f60c603b3ca77b3554 Mon Sep 17 00:00:00 2001
From: Wei Yang <richard.weiyang@linux.alibaba.com>
Date: Thu, 15 Oct 2020 20:11:46 -0700
Subject: bitops: use the same mechanism for get_count_order[_long]

These two functions share the same logic.

Signed-off-by: Wei Yang <richard.weiyang@linux.alibaba.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lkml.kernel.org/r/20200807085837.11697-3-richard.weiyang@linux.alibaba.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/bitops.h | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index 030a98f0c452..5b74bdf159d6 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -188,12 +188,10 @@ static inline unsigned fls_long(unsigned long l)
 
 static inline int get_count_order(unsigned int count)
 {
-	int order;
+	if (count == 0)
+		return -1;
 
-	order = fls(count) - 1;
-	if (count & (count - 1))
-		order++;
-	return order;
+	return fls(--count);
 }
 
 /**
-- 
cgit v1.2.3


From afc63a97b764bc5a715762d0d9cc9785c2ef4e75 Mon Sep 17 00:00:00 2001
From: Jann Horn <jannh@google.com>
Date: Thu, 15 Oct 2020 20:12:46 -0700
Subject: coredump: refactor page range dumping into common helper

Both fs/binfmt_elf.c and fs/binfmt_elf_fdpic.c need to dump ranges of
pages into the coredump file.  Extract that logic into a common helper.

Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: "Eric W . Biederman" <ebiederm@xmission.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Link: http://lkml.kernel.org/r/20200827114932.3572699-4-jannh@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/binfmt_elf.c          | 22 ++--------------------
 fs/binfmt_elf_fdpic.c    | 18 +++---------------
 fs/coredump.c            | 34 ++++++++++++++++++++++++++++++++++
 include/linux/coredump.h |  2 ++
 4 files changed, 41 insertions(+), 35 deletions(-)

(limited to 'include/linux')

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 96370e3e3687..cf956edf05ef 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -2444,26 +2444,8 @@ static int elf_core_dump(struct coredump_params *cprm)
 
 	for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
 			vma = next_vma(vma, gate_vma)) {
-		unsigned long addr;
-		unsigned long end;
-
-		end = vma->vm_start + vma_filesz[i++];
-
-		for (addr = vma->vm_start; addr < end; addr += PAGE_SIZE) {
-			struct page *page;
-			int stop;
-
-			page = get_dump_page(addr);
-			if (page) {
-				void *kaddr = kmap(page);
-				stop = !dump_emit(cprm, kaddr, PAGE_SIZE);
-				kunmap(page);
-				put_page(page);
-			} else
-				stop = !dump_skip(cprm, PAGE_SIZE);
-			if (stop)
-				goto end_coredump;
-		}
+		if (!dump_user_range(cprm, vma->vm_start, vma_filesz[i++]))
+			goto end_coredump;
 	}
 	dump_truncate(cprm);
 
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index a53f83830986..76e8c0defdc8 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -1534,21 +1534,9 @@ static bool elf_fdpic_dump_segments(struct coredump_params *cprm)
 		if (!maydump(vma, cprm->mm_flags))
 			continue;
 
-		for (addr = vma->vm_start; addr < vma->vm_end;
-							addr += PAGE_SIZE) {
-			bool res;
-			struct page *page = get_dump_page(addr);
-			if (page) {
-				void *kaddr = kmap(page);
-				res = dump_emit(cprm, kaddr, PAGE_SIZE);
-				kunmap(page);
-				put_page(page);
-			} else {
-				res = dump_skip(cprm, PAGE_SIZE);
-			}
-			if (!res)
-				return false;
-		}
+		if (!dump_user_range(cprm, vma->vm_start,
+				     vma->vma_end - vma->vm_start))
+			return false;
 	}
 	return true;
 }
diff --git a/fs/coredump.c b/fs/coredump.c
index 5e24c06092c9..6042d15acd51 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -876,6 +876,40 @@ int dump_skip(struct coredump_params *cprm, size_t nr)
 }
 EXPORT_SYMBOL(dump_skip);
 
+#ifdef CONFIG_ELF_CORE
+int dump_user_range(struct coredump_params *cprm, unsigned long start,
+		    unsigned long len)
+{
+	unsigned long addr;
+
+	for (addr = start; addr < start + len; addr += PAGE_SIZE) {
+		struct page *page;
+		int stop;
+
+		/*
+		 * To avoid having to allocate page tables for virtual address
+		 * ranges that have never been used yet, and also to make it
+		 * easy to generate sparse core files, use a helper that returns
+		 * NULL when encountering an empty page table entry that would
+		 * otherwise have been filled with the zero page.
+		 */
+		page = get_dump_page(addr);
+		if (page) {
+			void *kaddr = kmap(page);
+
+			stop = !dump_emit(cprm, kaddr, PAGE_SIZE);
+			kunmap(page);
+			put_page(page);
+		} else {
+			stop = !dump_skip(cprm, PAGE_SIZE);
+		}
+		if (stop)
+			return 0;
+	}
+	return 1;
+}
+#endif
+
 int dump_align(struct coredump_params *cprm, int align)
 {
 	unsigned mod = cprm->pos & (align - 1);
diff --git a/include/linux/coredump.h b/include/linux/coredump.h
index 7a899e83835d..f0b71a74d0bc 100644
--- a/include/linux/coredump.h
+++ b/include/linux/coredump.h
@@ -16,6 +16,8 @@ extern int dump_skip(struct coredump_params *cprm, size_t nr);
 extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr);
 extern int dump_align(struct coredump_params *cprm, int align);
 extern void dump_truncate(struct coredump_params *cprm);
+int dump_user_range(struct coredump_params *cprm, unsigned long start,
+		    unsigned long len);
 #ifdef CONFIG_COREDUMP
 extern void do_coredump(const kernel_siginfo_t *siginfo);
 #else
-- 
cgit v1.2.3


From 429a22e776a2b9f85a2b9c53d8e647598b553dd1 Mon Sep 17 00:00:00 2001
From: Jann Horn <jannh@google.com>
Date: Thu, 15 Oct 2020 20:12:50 -0700
Subject: coredump: rework elf/elf_fdpic vma_dump_size() into common helper

At the moment, the binfmt_elf and binfmt_elf_fdpic code have slightly
different code to figure out which VMAs should be dumped, and if so,
whether the dump should contain the entire VMA or just its first page.

Eliminate duplicate code by reworking the binfmt_elf version into a
generic core dumping helper in coredump.c.

As part of that, change the heuristic for detecting executable/library
header pages to check whether the inode is executable instead of looking
at the file mode.

This is less problematic in terms of locking because it lets us avoid
get_user() under the mmap_sem.  (And arguably it looks nicer and makes
more sense in generic code.)

Adjust a little bit based on the binfmt_elf_fdpic version: ->anon_vma is
only meaningful under CONFIG_MMU, otherwise we have to assume that the VMA
has been written to.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: "Eric W . Biederman" <ebiederm@xmission.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Link: http://lkml.kernel.org/r/20200827114932.3572699-5-jannh@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/binfmt_elf.c          | 120 -----------------------------------------------
 fs/binfmt_elf_fdpic.c    |  83 ++------------------------------
 fs/coredump.c            | 101 +++++++++++++++++++++++++++++++++++++++
 include/linux/coredump.h |   1 +
 4 files changed, 106 insertions(+), 199 deletions(-)

(limited to 'include/linux')

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index cf956edf05ef..c1756fd8d10b 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1414,126 +1414,6 @@ out:
  * Jeremy Fitzhardinge <jeremy@sw.oz.au>
  */
 
-/*
- * The purpose of always_dump_vma() is to make sure that special kernel mappings
- * that are useful for post-mortem analysis are included in every core dump.
- * In that way we ensure that the core dump is fully interpretable later
- * without matching up the same kernel and hardware config to see what PC values
- * meant. These special mappings include - vDSO, vsyscall, and other
- * architecture specific mappings
- */
-static bool always_dump_vma(struct vm_area_struct *vma)
-{
-	/* Any vsyscall mappings? */
-	if (vma == get_gate_vma(vma->vm_mm))
-		return true;
-
-	/*
-	 * Assume that all vmas with a .name op should always be dumped.
-	 * If this changes, a new vm_ops field can easily be added.
-	 */
-	if (vma->vm_ops && vma->vm_ops->name && vma->vm_ops->name(vma))
-		return true;
-
-	/*
-	 * arch_vma_name() returns non-NULL for special architecture mappings,
-	 * such as vDSO sections.
-	 */
-	if (arch_vma_name(vma))
-		return true;
-
-	return false;
-}
-
-/*
- * Decide what to dump of a segment, part, all or none.
- */
-static unsigned long vma_dump_size(struct vm_area_struct *vma,
-				   unsigned long mm_flags)
-{
-#define FILTER(type)	(mm_flags & (1UL << MMF_DUMP_##type))
-
-	/* always dump the vdso and vsyscall sections */
-	if (always_dump_vma(vma))
-		goto whole;
-
-	if (vma->vm_flags & VM_DONTDUMP)
-		return 0;
-
-	/* support for DAX */
-	if (vma_is_dax(vma)) {
-		if ((vma->vm_flags & VM_SHARED) && FILTER(DAX_SHARED))
-			goto whole;
-		if (!(vma->vm_flags & VM_SHARED) && FILTER(DAX_PRIVATE))
-			goto whole;
-		return 0;
-	}
-
-	/* Hugetlb memory check */
-	if (is_vm_hugetlb_page(vma)) {
-		if ((vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_SHARED))
-			goto whole;
-		if (!(vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_PRIVATE))
-			goto whole;
-		return 0;
-	}
-
-	/* Do not dump I/O mapped devices or special mappings */
-	if (vma->vm_flags & VM_IO)
-		return 0;
-
-	/* By default, dump shared memory if mapped from an anonymous file. */
-	if (vma->vm_flags & VM_SHARED) {
-		if (file_inode(vma->vm_file)->i_nlink == 0 ?
-		    FILTER(ANON_SHARED) : FILTER(MAPPED_SHARED))
-			goto whole;
-		return 0;
-	}
-
-	/* Dump segments that have been written to.  */
-	if (vma->anon_vma && FILTER(ANON_PRIVATE))
-		goto whole;
-	if (vma->vm_file == NULL)
-		return 0;
-
-	if (FILTER(MAPPED_PRIVATE))
-		goto whole;
-
-	/*
-	 * If this looks like the beginning of a DSO or executable mapping,
-	 * check for an ELF header.  If we find one, dump the first page to
-	 * aid in determining what was mapped here.
-	 */
-	if (FILTER(ELF_HEADERS) &&
-	    vma->vm_pgoff == 0 && (vma->vm_flags & VM_READ)) {
-		u32 __user *header = (u32 __user *) vma->vm_start;
-		u32 word;
-		/*
-		 * Doing it this way gets the constant folded by GCC.
-		 */
-		union {
-			u32 cmp;
-			char elfmag[SELFMAG];
-		} magic;
-		BUILD_BUG_ON(SELFMAG != sizeof word);
-		magic.elfmag[EI_MAG0] = ELFMAG0;
-		magic.elfmag[EI_MAG1] = ELFMAG1;
-		magic.elfmag[EI_MAG2] = ELFMAG2;
-		magic.elfmag[EI_MAG3] = ELFMAG3;
-		if (unlikely(get_user(word, header)))
-			word = 0;
-		if (word == magic.cmp)
-			return PAGE_SIZE;
-	}
-
-#undef	FILTER
-
-	return 0;
-
-whole:
-	return vma->vm_end - vma->vm_start;
-}
-
 /* An ELF note in memory */
 struct memelfnote
 {
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 76e8c0defdc8..f531c6198864 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -1215,76 +1215,6 @@ struct elf_prstatus_fdpic
 	int pr_fpvalid;		/* True if math co-processor being used.  */
 };
 
-/*
- * Decide whether a segment is worth dumping; default is yes to be
- * sure (missing info is worse than too much; etc).
- * Personally I'd include everything, and use the coredump limit...
- *
- * I think we should skip something. But I am not sure how. H.J.
- */
-static int maydump(struct vm_area_struct *vma, unsigned long mm_flags)
-{
-	int dump_ok;
-
-	/* Do not dump I/O mapped devices or special mappings */
-	if (vma->vm_flags & VM_IO) {
-		kdcore("%08lx: %08lx: no (IO)", vma->vm_start, vma->vm_flags);
-		return 0;
-	}
-
-	/* If we may not read the contents, don't allow us to dump
-	 * them either. "dump_write()" can't handle it anyway.
-	 */
-	if (!(vma->vm_flags & VM_READ)) {
-		kdcore("%08lx: %08lx: no (!read)", vma->vm_start, vma->vm_flags);
-		return 0;
-	}
-
-	/* support for DAX */
-	if (vma_is_dax(vma)) {
-		if (vma->vm_flags & VM_SHARED) {
-			dump_ok = test_bit(MMF_DUMP_DAX_SHARED, &mm_flags);
-			kdcore("%08lx: %08lx: %s (DAX shared)", vma->vm_start,
-			       vma->vm_flags, dump_ok ? "yes" : "no");
-		} else {
-			dump_ok = test_bit(MMF_DUMP_DAX_PRIVATE, &mm_flags);
-			kdcore("%08lx: %08lx: %s (DAX private)", vma->vm_start,
-			       vma->vm_flags, dump_ok ? "yes" : "no");
-		}
-		return dump_ok;
-	}
-
-	/* By default, dump shared memory if mapped from an anonymous file. */
-	if (vma->vm_flags & VM_SHARED) {
-		if (file_inode(vma->vm_file)->i_nlink == 0) {
-			dump_ok = test_bit(MMF_DUMP_ANON_SHARED, &mm_flags);
-			kdcore("%08lx: %08lx: %s (share)", vma->vm_start,
-			       vma->vm_flags, dump_ok ? "yes" : "no");
-			return dump_ok;
-		}
-
-		dump_ok = test_bit(MMF_DUMP_MAPPED_SHARED, &mm_flags);
-		kdcore("%08lx: %08lx: %s (share)", vma->vm_start,
-		       vma->vm_flags, dump_ok ? "yes" : "no");
-		return dump_ok;
-	}
-
-#ifdef CONFIG_MMU
-	/* By default, if it hasn't been written to, don't write it out */
-	if (!vma->anon_vma) {
-		dump_ok = test_bit(MMF_DUMP_MAPPED_PRIVATE, &mm_flags);
-		kdcore("%08lx: %08lx: %s (!anon)", vma->vm_start,
-		       vma->vm_flags, dump_ok ? "yes" : "no");
-		return dump_ok;
-	}
-#endif
-
-	dump_ok = test_bit(MMF_DUMP_ANON_PRIVATE, &mm_flags);
-	kdcore("%08lx: %08lx: %s", vma->vm_start, vma->vm_flags,
-	       dump_ok ? "yes" : "no");
-	return dump_ok;
-}
-
 /* An ELF note in memory */
 struct memelfnote
 {
@@ -1529,13 +1459,9 @@ static bool elf_fdpic_dump_segments(struct coredump_params *cprm)
 	struct vm_area_struct *vma;
 
 	for (vma = current->mm->mmap; vma; vma = vma->vm_next) {
-		unsigned long addr;
-
-		if (!maydump(vma, cprm->mm_flags))
-			continue;
+		unsigned long size = vma_dump_size(vma, cprm->mm_flags);
 
-		if (!dump_user_range(cprm, vma->vm_start,
-				     vma->vma_end - vma->vm_start))
+		if (!dump_user_range(cprm, vma->vm_start, size))
 			return false;
 	}
 	return true;
@@ -1547,8 +1473,7 @@ static size_t elf_core_vma_data_size(unsigned long mm_flags)
 	size_t size = 0;
 
 	for (vma = current->mm->mmap; vma; vma = vma->vm_next)
-		if (maydump(vma, mm_flags))
-			size += vma->vm_end - vma->vm_start;
+		size += vma_dump_size(vma, mm_flags);
 	return size;
 }
 
@@ -1694,7 +1619,7 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 		phdr.p_offset = offset;
 		phdr.p_vaddr = vma->vm_start;
 		phdr.p_paddr = 0;
-		phdr.p_filesz = maydump(vma, cprm->mm_flags) ? sz : 0;
+		phdr.p_filesz = vma_dump_size(vma, cprm->mm_flags);
 		phdr.p_memsz = sz;
 		offset += phdr.p_filesz;
 		phdr.p_flags = vma->vm_flags & VM_READ ? PF_R : 0;
diff --git a/fs/coredump.c b/fs/coredump.c
index 6042d15acd51..4ef4c49a65b7 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -936,3 +936,104 @@ void dump_truncate(struct coredump_params *cprm)
 	}
 }
 EXPORT_SYMBOL(dump_truncate);
+
+/*
+ * The purpose of always_dump_vma() is to make sure that special kernel mappings
+ * that are useful for post-mortem analysis are included in every core dump.
+ * In that way we ensure that the core dump is fully interpretable later
+ * without matching up the same kernel and hardware config to see what PC values
+ * meant. These special mappings include - vDSO, vsyscall, and other
+ * architecture specific mappings
+ */
+static bool always_dump_vma(struct vm_area_struct *vma)
+{
+	/* Any vsyscall mappings? */
+	if (vma == get_gate_vma(vma->vm_mm))
+		return true;
+
+	/*
+	 * Assume that all vmas with a .name op should always be dumped.
+	 * If this changes, a new vm_ops field can easily be added.
+	 */
+	if (vma->vm_ops && vma->vm_ops->name && vma->vm_ops->name(vma))
+		return true;
+
+	/*
+	 * arch_vma_name() returns non-NULL for special architecture mappings,
+	 * such as vDSO sections.
+	 */
+	if (arch_vma_name(vma))
+		return true;
+
+	return false;
+}
+
+/*
+ * Decide how much of @vma's contents should be included in a core dump.
+ */
+unsigned long vma_dump_size(struct vm_area_struct *vma, unsigned long mm_flags)
+{
+#define FILTER(type)	(mm_flags & (1UL << MMF_DUMP_##type))
+
+	/* always dump the vdso and vsyscall sections */
+	if (always_dump_vma(vma))
+		goto whole;
+
+	if (vma->vm_flags & VM_DONTDUMP)
+		return 0;
+
+	/* support for DAX */
+	if (vma_is_dax(vma)) {
+		if ((vma->vm_flags & VM_SHARED) && FILTER(DAX_SHARED))
+			goto whole;
+		if (!(vma->vm_flags & VM_SHARED) && FILTER(DAX_PRIVATE))
+			goto whole;
+		return 0;
+	}
+
+	/* Hugetlb memory check */
+	if (is_vm_hugetlb_page(vma)) {
+		if ((vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_SHARED))
+			goto whole;
+		if (!(vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_PRIVATE))
+			goto whole;
+		return 0;
+	}
+
+	/* Do not dump I/O mapped devices or special mappings */
+	if (vma->vm_flags & VM_IO)
+		return 0;
+
+	/* By default, dump shared memory if mapped from an anonymous file. */
+	if (vma->vm_flags & VM_SHARED) {
+		if (file_inode(vma->vm_file)->i_nlink == 0 ?
+		    FILTER(ANON_SHARED) : FILTER(MAPPED_SHARED))
+			goto whole;
+		return 0;
+	}
+
+	/* Dump segments that have been written to.  */
+	if ((!IS_ENABLED(CONFIG_MMU) || vma->anon_vma) && FILTER(ANON_PRIVATE))
+		goto whole;
+	if (vma->vm_file == NULL)
+		return 0;
+
+	if (FILTER(MAPPED_PRIVATE))
+		goto whole;
+
+	/*
+	 * If this is the beginning of an executable file mapping,
+	 * dump the first page to aid in determining what was mapped here.
+	 */
+	if (FILTER(ELF_HEADERS) &&
+	    vma->vm_pgoff == 0 && (vma->vm_flags & VM_READ) &&
+	    (READ_ONCE(file_inode(vma->vm_file)->i_mode) & 0111) != 0)
+		return PAGE_SIZE;
+
+#undef	FILTER
+
+	return 0;
+
+whole:
+	return vma->vm_end - vma->vm_start;
+}
diff --git a/include/linux/coredump.h b/include/linux/coredump.h
index f0b71a74d0bc..bfecb8d79a7f 100644
--- a/include/linux/coredump.h
+++ b/include/linux/coredump.h
@@ -16,6 +16,7 @@ extern int dump_skip(struct coredump_params *cprm, size_t nr);
 extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr);
 extern int dump_align(struct coredump_params *cprm, int align);
 extern void dump_truncate(struct coredump_params *cprm);
+unsigned long vma_dump_size(struct vm_area_struct *vma, unsigned long mm_flags);
 int dump_user_range(struct coredump_params *cprm, unsigned long start,
 		    unsigned long len);
 #ifdef CONFIG_COREDUMP
-- 
cgit v1.2.3


From a07279c9a8cd7dbd321640ff7210591599ee00a4 Mon Sep 17 00:00:00 2001
From: Jann Horn <jannh@google.com>
Date: Thu, 15 Oct 2020 20:12:54 -0700
Subject: binfmt_elf, binfmt_elf_fdpic: use a VMA list snapshot

In both binfmt_elf and binfmt_elf_fdpic, use a new helper
dump_vma_snapshot() to take a snapshot of the VMA list (including the gate
VMA, if we have one) while protected by the mmap_lock, and then use that
snapshot instead of walking the VMA list without locking.

An alternative approach would be to keep the mmap_lock held across the
entire core dumping operation; however, keeping the mmap_lock locked while
we may be blocked for an unbounded amount of time (e.g.  because we're
dumping to a FUSE filesystem or so) isn't really optimal; the mmap_lock
blocks things like the ->release handler of userfaultfd, and we don't
really want critical system daemons to grind to a halt just because
someone "gifted" them SCM_RIGHTS to an eternally-locked userfaultfd, or
something like that.

Since both the normal ELF code and the FDPIC ELF code need this
functionality (and if any other binfmt wants to add coredump support in
the future, they'd probably need it, too), implement this with a common
helper in fs/coredump.c.

A downside of this approach is that we now need a bigger amount of kernel
memory per userspace VMA in the normal ELF case, and that we need O(n)
kernel memory in the FDPIC ELF case at all; but 40 bytes per VMA shouldn't
be terribly bad.

There currently is a data race between stack expansion and anything that
reads ->vm_start or ->vm_end under the mmap_lock held in read mode; to
mitigate that for core dumping, take the mmap_lock in write mode when
taking a snapshot of the VMA hierarchy.  (If we only took the mmap_lock in
read mode, we could end up with a corrupted core dump if someone does
get_user_pages_remote() concurrently.  Not really a major problem, but
taking the mmap_lock either way works here, so we might as well avoid the
issue.) (This doesn't do anything about the existing data races with stack
expansion in other mm code.)

Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: "Eric W . Biederman" <ebiederm@xmission.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Link: http://lkml.kernel.org/r/20200827114932.3572699-6-jannh@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/binfmt_elf.c          | 100 +++++++++++------------------------------------
 fs/binfmt_elf_fdpic.c    |  67 +++++++++++++------------------
 fs/coredump.c            |  81 +++++++++++++++++++++++++++++++++++++-
 include/linux/coredump.h |  10 ++++-
 4 files changed, 138 insertions(+), 120 deletions(-)

(limited to 'include/linux')

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index c1756fd8d10b..e7e9d0cde51a 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -2125,32 +2125,6 @@ static void free_note_info(struct elf_note_info *info)
 
 #endif
 
-static struct vm_area_struct *first_vma(struct task_struct *tsk,
-					struct vm_area_struct *gate_vma)
-{
-	struct vm_area_struct *ret = tsk->mm->mmap;
-
-	if (ret)
-		return ret;
-	return gate_vma;
-}
-/*
- * Helper function for iterating across a vma list.  It ensures that the caller
- * will visit `gate_vma' prior to terminating the search.
- */
-static struct vm_area_struct *next_vma(struct vm_area_struct *this_vma,
-					struct vm_area_struct *gate_vma)
-{
-	struct vm_area_struct *ret;
-
-	ret = this_vma->vm_next;
-	if (ret)
-		return ret;
-	if (this_vma == gate_vma)
-		return NULL;
-	return gate_vma;
-}
-
 static void fill_extnum_info(struct elfhdr *elf, struct elf_shdr *shdr4extnum,
 			     elf_addr_t e_shoff, int segs)
 {
@@ -2177,9 +2151,8 @@ static void fill_extnum_info(struct elfhdr *elf, struct elf_shdr *shdr4extnum,
 static int elf_core_dump(struct coredump_params *cprm)
 {
 	int has_dumped = 0;
-	int segs, i;
-	size_t vma_data_size = 0;
-	struct vm_area_struct *vma, *gate_vma;
+	int vma_count, segs, i;
+	size_t vma_data_size;
 	struct elfhdr elf;
 	loff_t offset = 0, dataoff;
 	struct elf_note_info info = { };
@@ -2187,30 +2160,16 @@ static int elf_core_dump(struct coredump_params *cprm)
 	struct elf_shdr *shdr4extnum = NULL;
 	Elf_Half e_phnum;
 	elf_addr_t e_shoff;
-	elf_addr_t *vma_filesz = NULL;
+	struct core_vma_metadata *vma_meta;
+
+	if (dump_vma_snapshot(cprm, &vma_count, &vma_meta, &vma_data_size))
+		return 0;
 
-	/*
-	 * We no longer stop all VM operations.
-	 * 
-	 * This is because those proceses that could possibly change map_count
-	 * or the mmap / vma pages are now blocked in do_exit on current
-	 * finishing this core dump.
-	 *
-	 * Only ptrace can touch these memory addresses, but it doesn't change
-	 * the map_count or the pages allocated. So no possibility of crashing
-	 * exists while dumping the mm->vm_next areas to the core file.
-	 */
-  
 	/*
 	 * The number of segs are recored into ELF header as 16bit value.
 	 * Please check DEFAULT_MAX_MAP_COUNT definition when you modify here.
 	 */
-	segs = current->mm->map_count;
-	segs += elf_core_extra_phdrs();
-
-	gate_vma = get_gate_vma(current->mm);
-	if (gate_vma != NULL)
-		segs++;
+	segs = vma_count + elf_core_extra_phdrs();
 
 	/* for notes section */
 	segs++;
@@ -2248,24 +2207,6 @@ static int elf_core_dump(struct coredump_params *cprm)
 
 	dataoff = offset = roundup(offset, ELF_EXEC_PAGESIZE);
 
-	/*
-	 * Zero vma process will get ZERO_SIZE_PTR here.
-	 * Let coredump continue for register state at least.
-	 */
-	vma_filesz = kvmalloc(array_size(sizeof(*vma_filesz), (segs - 1)),
-			      GFP_KERNEL);
-	if (!vma_filesz)
-		goto end_coredump;
-
-	for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
-			vma = next_vma(vma, gate_vma)) {
-		unsigned long dump_size;
-
-		dump_size = vma_dump_size(vma, cprm->mm_flags);
-		vma_filesz[i++] = dump_size;
-		vma_data_size += dump_size;
-	}
-
 	offset += vma_data_size;
 	offset += elf_core_extra_data_size();
 	e_shoff = offset;
@@ -2286,21 +2227,23 @@ static int elf_core_dump(struct coredump_params *cprm)
 		goto end_coredump;
 
 	/* Write program headers for segments dump */
-	for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
-			vma = next_vma(vma, gate_vma)) {
+	for (i = 0; i < vma_count; i++) {
+		struct core_vma_metadata *meta = vma_meta + i;
 		struct elf_phdr phdr;
 
 		phdr.p_type = PT_LOAD;
 		phdr.p_offset = offset;
-		phdr.p_vaddr = vma->vm_start;
+		phdr.p_vaddr = meta->start;
 		phdr.p_paddr = 0;
-		phdr.p_filesz = vma_filesz[i++];
-		phdr.p_memsz = vma->vm_end - vma->vm_start;
+		phdr.p_filesz = meta->dump_size;
+		phdr.p_memsz = meta->end - meta->start;
 		offset += phdr.p_filesz;
-		phdr.p_flags = vma->vm_flags & VM_READ ? PF_R : 0;
-		if (vma->vm_flags & VM_WRITE)
+		phdr.p_flags = 0;
+		if (meta->flags & VM_READ)
+			phdr.p_flags |= PF_R;
+		if (meta->flags & VM_WRITE)
 			phdr.p_flags |= PF_W;
-		if (vma->vm_flags & VM_EXEC)
+		if (meta->flags & VM_EXEC)
 			phdr.p_flags |= PF_X;
 		phdr.p_align = ELF_EXEC_PAGESIZE;
 
@@ -2322,9 +2265,10 @@ static int elf_core_dump(struct coredump_params *cprm)
 	if (!dump_skip(cprm, dataoff - cprm->pos))
 		goto end_coredump;
 
-	for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
-			vma = next_vma(vma, gate_vma)) {
-		if (!dump_user_range(cprm, vma->vm_start, vma_filesz[i++]))
+	for (i = 0; i < vma_count; i++) {
+		struct core_vma_metadata *meta = vma_meta + i;
+
+		if (!dump_user_range(cprm, meta->start, meta->dump_size))
 			goto end_coredump;
 	}
 	dump_truncate(cprm);
@@ -2340,7 +2284,7 @@ static int elf_core_dump(struct coredump_params *cprm)
 end_coredump:
 	free_note_info(&info);
 	kfree(shdr4extnum);
-	kvfree(vma_filesz);
+	kvfree(vma_meta);
 	kfree(phdr4note);
 	return has_dumped;
 }
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index f531c6198864..be4062b8ba75 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -1454,29 +1454,21 @@ static void fill_extnum_info(struct elfhdr *elf, struct elf_shdr *shdr4extnum,
 /*
  * dump the segments for an MMU process
  */
-static bool elf_fdpic_dump_segments(struct coredump_params *cprm)
+static bool elf_fdpic_dump_segments(struct coredump_params *cprm,
+				    struct core_vma_metadata *vma_meta,
+				    int vma_count)
 {
-	struct vm_area_struct *vma;
+	int i;
 
-	for (vma = current->mm->mmap; vma; vma = vma->vm_next) {
-		unsigned long size = vma_dump_size(vma, cprm->mm_flags);
+	for (i = 0; i < vma_count; i++) {
+		struct core_vma_metadata *meta = vma_meta + i;
 
-		if (!dump_user_range(cprm, vma->vm_start, size))
+		if (!dump_user_range(cprm, meta->start, meta->dump_size))
 			return false;
 	}
 	return true;
 }
 
-static size_t elf_core_vma_data_size(unsigned long mm_flags)
-{
-	struct vm_area_struct *vma;
-	size_t size = 0;
-
-	for (vma = current->mm->mmap; vma; vma = vma->vm_next)
-		size += vma_dump_size(vma, mm_flags);
-	return size;
-}
-
 /*
  * Actual dumper
  *
@@ -1487,9 +1479,8 @@ static size_t elf_core_vma_data_size(unsigned long mm_flags)
 static int elf_fdpic_core_dump(struct coredump_params *cprm)
 {
 	int has_dumped = 0;
-	int segs;
+	int vma_count, segs;
 	int i;
-	struct vm_area_struct *vma;
 	struct elfhdr *elf = NULL;
 	loff_t offset = 0, dataoff;
 	struct memelfnote psinfo_note, auxv_note;
@@ -1503,18 +1494,8 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 	elf_addr_t e_shoff;
 	struct core_thread *ct;
 	struct elf_thread_status *tmp;
-
-	/*
-	 * We no longer stop all VM operations.
-	 *
-	 * This is because those proceses that could possibly change map_count
-	 * or the mmap / vma pages are now blocked in do_exit on current
-	 * finishing this core dump.
-	 *
-	 * Only ptrace can touch these memory addresses, but it doesn't change
-	 * the map_count or the pages allocated. So no possibility of crashing
-	 * exists while dumping the mm->vm_next areas to the core file.
-	 */
+	struct core_vma_metadata *vma_meta = NULL;
+	size_t vma_data_size;
 
 	/* alloc memory for large data structures: too large to be on stack */
 	elf = kmalloc(sizeof(*elf), GFP_KERNEL);
@@ -1524,6 +1505,9 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 	if (!psinfo)
 		goto end_coredump;
 
+	if (dump_vma_snapshot(cprm, &vma_count, &vma_meta, &vma_data_size))
+		goto end_coredump;
+
 	for (ct = current->mm->core_state->dumper.next;
 					ct; ct = ct->next) {
 		tmp = elf_dump_thread_status(cprm->siginfo->si_signo,
@@ -1543,8 +1527,7 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 	tmp->next = thread_list;
 	thread_list = tmp;
 
-	segs = current->mm->map_count;
-	segs += elf_core_extra_phdrs();
+	segs = vma_count + elf_core_extra_phdrs();
 
 	/* for notes section */
 	segs++;
@@ -1589,7 +1572,7 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 	/* Page-align dumped data */
 	dataoff = offset = roundup(offset, ELF_EXEC_PAGESIZE);
 
-	offset += elf_core_vma_data_size(cprm->mm_flags);
+	offset += vma_data_size;
 	offset += elf_core_extra_data_size();
 	e_shoff = offset;
 
@@ -1609,23 +1592,26 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 		goto end_coredump;
 
 	/* write program headers for segments dump */
-	for (vma = current->mm->mmap; vma; vma = vma->vm_next) {
+	for (i = 0; i < vma_count; i++) {
+		struct core_vma_metadata *meta = vma_meta + i;
 		struct elf_phdr phdr;
 		size_t sz;
 
-		sz = vma->vm_end - vma->vm_start;
+		sz = meta->end - meta->start;
 
 		phdr.p_type = PT_LOAD;
 		phdr.p_offset = offset;
-		phdr.p_vaddr = vma->vm_start;
+		phdr.p_vaddr = meta->start;
 		phdr.p_paddr = 0;
-		phdr.p_filesz = vma_dump_size(vma, cprm->mm_flags);
+		phdr.p_filesz = meta->dump_size;
 		phdr.p_memsz = sz;
 		offset += phdr.p_filesz;
-		phdr.p_flags = vma->vm_flags & VM_READ ? PF_R : 0;
-		if (vma->vm_flags & VM_WRITE)
+		phdr.p_flags = 0;
+		if (meta->flags & VM_READ)
+			phdr.p_flags |= PF_R;
+		if (meta->flags & VM_WRITE)
 			phdr.p_flags |= PF_W;
-		if (vma->vm_flags & VM_EXEC)
+		if (meta->flags & VM_EXEC)
 			phdr.p_flags |= PF_X;
 		phdr.p_align = ELF_EXEC_PAGESIZE;
 
@@ -1657,7 +1643,7 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 	if (!dump_skip(cprm, dataoff - cprm->pos))
 		goto end_coredump;
 
-	if (!elf_fdpic_dump_segments(cprm))
+	if (!elf_fdpic_dump_segments(cprm, vma_meta, vma_count))
 		goto end_coredump;
 
 	if (!elf_core_write_extra_data(cprm))
@@ -1681,6 +1667,7 @@ end_coredump:
 		thread_list = thread_list->next;
 		kfree(tmp);
 	}
+	kvfree(vma_meta);
 	kfree(phdr4note);
 	kfree(elf);
 	kfree(psinfo);
diff --git a/fs/coredump.c b/fs/coredump.c
index 4ef4c49a65b7..0cd9056d79cc 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -971,7 +971,8 @@ static bool always_dump_vma(struct vm_area_struct *vma)
 /*
  * Decide how much of @vma's contents should be included in a core dump.
  */
-unsigned long vma_dump_size(struct vm_area_struct *vma, unsigned long mm_flags)
+static unsigned long vma_dump_size(struct vm_area_struct *vma,
+				   unsigned long mm_flags)
 {
 #define FILTER(type)	(mm_flags & (1UL << MMF_DUMP_##type))
 
@@ -1037,3 +1038,81 @@ unsigned long vma_dump_size(struct vm_area_struct *vma, unsigned long mm_flags)
 whole:
 	return vma->vm_end - vma->vm_start;
 }
+
+static struct vm_area_struct *first_vma(struct task_struct *tsk,
+					struct vm_area_struct *gate_vma)
+{
+	struct vm_area_struct *ret = tsk->mm->mmap;
+
+	if (ret)
+		return ret;
+	return gate_vma;
+}
+
+/*
+ * Helper function for iterating across a vma list.  It ensures that the caller
+ * will visit `gate_vma' prior to terminating the search.
+ */
+static struct vm_area_struct *next_vma(struct vm_area_struct *this_vma,
+				       struct vm_area_struct *gate_vma)
+{
+	struct vm_area_struct *ret;
+
+	ret = this_vma->vm_next;
+	if (ret)
+		return ret;
+	if (this_vma == gate_vma)
+		return NULL;
+	return gate_vma;
+}
+
+/*
+ * Under the mmap_lock, take a snapshot of relevant information about the task's
+ * VMAs.
+ */
+int dump_vma_snapshot(struct coredump_params *cprm, int *vma_count,
+		      struct core_vma_metadata **vma_meta,
+		      size_t *vma_data_size_ptr)
+{
+	struct vm_area_struct *vma, *gate_vma;
+	struct mm_struct *mm = current->mm;
+	int i;
+	size_t vma_data_size = 0;
+
+	/*
+	 * Once the stack expansion code is fixed to not change VMA bounds
+	 * under mmap_lock in read mode, this can be changed to take the
+	 * mmap_lock in read mode.
+	 */
+	if (mmap_write_lock_killable(mm))
+		return -EINTR;
+
+	gate_vma = get_gate_vma(mm);
+	*vma_count = mm->map_count + (gate_vma ? 1 : 0);
+
+	*vma_meta = kvmalloc_array(*vma_count, sizeof(**vma_meta), GFP_KERNEL);
+	if (!*vma_meta) {
+		mmap_write_unlock(mm);
+		return -ENOMEM;
+	}
+
+	for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
+			vma = next_vma(vma, gate_vma), i++) {
+		struct core_vma_metadata *m = (*vma_meta) + i;
+
+		m->start = vma->vm_start;
+		m->end = vma->vm_end;
+		m->flags = vma->vm_flags;
+		m->dump_size = vma_dump_size(vma, cprm->mm_flags);
+
+		vma_data_size += m->dump_size;
+	}
+
+	mmap_write_unlock(mm);
+
+	if (WARN_ON(i != *vma_count))
+		return -EFAULT;
+
+	*vma_data_size_ptr = vma_data_size;
+	return 0;
+}
diff --git a/include/linux/coredump.h b/include/linux/coredump.h
index bfecb8d79a7f..e58e8c207782 100644
--- a/include/linux/coredump.h
+++ b/include/linux/coredump.h
@@ -7,6 +7,12 @@
 #include <linux/fs.h>
 #include <asm/siginfo.h>
 
+struct core_vma_metadata {
+	unsigned long start, end;
+	unsigned long flags;
+	unsigned long dump_size;
+};
+
 /*
  * These are the only things you should do on a core-file: use only these
  * functions to write out all the necessary info.
@@ -16,9 +22,11 @@ extern int dump_skip(struct coredump_params *cprm, size_t nr);
 extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr);
 extern int dump_align(struct coredump_params *cprm, int align);
 extern void dump_truncate(struct coredump_params *cprm);
-unsigned long vma_dump_size(struct vm_area_struct *vma, unsigned long mm_flags);
 int dump_user_range(struct coredump_params *cprm, unsigned long start,
 		    unsigned long len);
+int dump_vma_snapshot(struct coredump_params *cprm, int *vma_count,
+		      struct core_vma_metadata **vma_meta,
+		      size_t *vma_data_size_ptr);
 #ifdef CONFIG_COREDUMP
 extern void do_coredump(const kernel_siginfo_t *siginfo);
 #else
-- 
cgit v1.2.3


From 4d45e75a9955ade5c2f49bd96fc4173b2cec9a72 Mon Sep 17 00:00:00 2001
From: Jann Horn <jannh@google.com>
Date: Thu, 15 Oct 2020 20:13:00 -0700
Subject: mm: remove the now-unnecessary mmget_still_valid() hack

The preceding patches have ensured that core dumping properly takes the
mmap_lock.  Thanks to that, we can now remove mmget_still_valid() and all
its users.

Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: "Eric W . Biederman" <ebiederm@xmission.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Link: http://lkml.kernel.org/r/20200827114932.3572699-8-jannh@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/infiniband/core/uverbs_main.c |  3 ---
 drivers/vfio/pci/vfio_pci.c           | 38 +++++++++++++++++------------------
 fs/proc/task_mmu.c                    | 18 -----------------
 fs/userfaultfd.c                      | 28 +++++++++-----------------
 include/linux/sched/mm.h              | 25 -----------------------
 mm/khugepaged.c                       |  2 +-
 mm/madvise.c                          | 17 ----------------
 mm/mmap.c                             |  5 +----
 8 files changed, 29 insertions(+), 107 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 37794d88b1f3..a4ba0b87d6de 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -845,8 +845,6 @@ void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile)
 		 * will only be one mm, so no big deal.
 		 */
 		mmap_read_lock(mm);
-		if (!mmget_still_valid(mm))
-			goto skip_mm;
 		mutex_lock(&ufile->umap_lock);
 		list_for_each_entry_safe (priv, next_priv, &ufile->umaps,
 					  list) {
@@ -865,7 +863,6 @@ void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile)
 			}
 		}
 		mutex_unlock(&ufile->umap_lock);
-	skip_mm:
 		mmap_read_unlock(mm);
 		mmput(mm);
 	}
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 1ab1f5cda4ac..b0f4b92a87ed 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -1480,31 +1480,29 @@ static int vfio_pci_zap_and_vma_lock(struct vfio_pci_device *vdev, bool try)
 		} else {
 			mmap_read_lock(mm);
 		}
-		if (mmget_still_valid(mm)) {
-			if (try) {
-				if (!mutex_trylock(&vdev->vma_lock)) {
-					mmap_read_unlock(mm);
-					mmput(mm);
-					return 0;
-				}
-			} else {
-				mutex_lock(&vdev->vma_lock);
+		if (try) {
+			if (!mutex_trylock(&vdev->vma_lock)) {
+				mmap_read_unlock(mm);
+				mmput(mm);
+				return 0;
 			}
-			list_for_each_entry_safe(mmap_vma, tmp,
-						 &vdev->vma_list, vma_next) {
-				struct vm_area_struct *vma = mmap_vma->vma;
+		} else {
+			mutex_lock(&vdev->vma_lock);
+		}
+		list_for_each_entry_safe(mmap_vma, tmp,
+					 &vdev->vma_list, vma_next) {
+			struct vm_area_struct *vma = mmap_vma->vma;
 
-				if (vma->vm_mm != mm)
-					continue;
+			if (vma->vm_mm != mm)
+				continue;
 
-				list_del(&mmap_vma->vma_next);
-				kfree(mmap_vma);
+			list_del(&mmap_vma->vma_next);
+			kfree(mmap_vma);
 
-				zap_vma_ptes(vma, vma->vm_start,
-					     vma->vm_end - vma->vm_start);
-			}
-			mutex_unlock(&vdev->vma_lock);
+			zap_vma_ptes(vma, vma->vm_start,
+				     vma->vm_end - vma->vm_start);
 		}
+		mutex_unlock(&vdev->vma_lock);
 		mmap_read_unlock(mm);
 		mmput(mm);
 	}
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 846d43df3fdf..217aa2705d5d 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1244,24 +1244,6 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 					count = -EINTR;
 					goto out_mm;
 				}
-				/*
-				 * Avoid to modify vma->vm_flags
-				 * without locked ops while the
-				 * coredump reads the vm_flags.
-				 */
-				if (!mmget_still_valid(mm)) {
-					/*
-					 * Silently return "count"
-					 * like if get_task_mm()
-					 * failed. FIXME: should this
-					 * function have returned
-					 * -ESRCH if get_task_mm()
-					 * failed like if
-					 * get_proc_task() fails?
-					 */
-					mmap_write_unlock(mm);
-					goto out_mm;
-				}
 				for (vma = mm->mmap; vma; vma = vma->vm_next) {
 					vma->vm_flags &= ~VM_SOFTDIRTY;
 					vma_set_page_prot(vma);
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 0e4a3837da52..000b457ad087 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -601,8 +601,6 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
 
 		/* the various vma->vm_userfaultfd_ctx still points to it */
 		mmap_write_lock(mm);
-		/* no task can run (and in turn coredump) yet */
-		VM_WARN_ON(!mmget_still_valid(mm));
 		for (vma = mm->mmap; vma; vma = vma->vm_next)
 			if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) {
 				vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
@@ -842,7 +840,6 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
 	/* len == 0 means wake all */
 	struct userfaultfd_wake_range range = { .len = 0, };
 	unsigned long new_flags;
-	bool still_valid;
 
 	WRITE_ONCE(ctx->released, true);
 
@@ -858,7 +855,6 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
 	 * taking the mmap_lock for writing.
 	 */
 	mmap_write_lock(mm);
-	still_valid = mmget_still_valid(mm);
 	prev = NULL;
 	for (vma = mm->mmap; vma; vma = vma->vm_next) {
 		cond_resched();
@@ -869,17 +865,15 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
 			continue;
 		}
 		new_flags = vma->vm_flags & ~(VM_UFFD_MISSING | VM_UFFD_WP);
-		if (still_valid) {
-			prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end,
-					 new_flags, vma->anon_vma,
-					 vma->vm_file, vma->vm_pgoff,
-					 vma_policy(vma),
-					 NULL_VM_UFFD_CTX);
-			if (prev)
-				vma = prev;
-			else
-				prev = vma;
-		}
+		prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end,
+				 new_flags, vma->anon_vma,
+				 vma->vm_file, vma->vm_pgoff,
+				 vma_policy(vma),
+				 NULL_VM_UFFD_CTX);
+		if (prev)
+			vma = prev;
+		else
+			prev = vma;
 		vma->vm_flags = new_flags;
 		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
 	}
@@ -1309,8 +1303,6 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 		goto out;
 
 	mmap_write_lock(mm);
-	if (!mmget_still_valid(mm))
-		goto out_unlock;
 	vma = find_vma_prev(mm, start, &prev);
 	if (!vma)
 		goto out_unlock;
@@ -1511,8 +1503,6 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 		goto out;
 
 	mmap_write_lock(mm);
-	if (!mmget_still_valid(mm))
-		goto out_unlock;
 	vma = find_vma_prev(mm, start, &prev);
 	if (!vma)
 		goto out_unlock;
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 15bfb06f2884..981e34cb1409 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -49,31 +49,6 @@ static inline void mmdrop(struct mm_struct *mm)
 		__mmdrop(mm);
 }
 
-/*
- * This has to be called after a get_task_mm()/mmget_not_zero()
- * followed by taking the mmap_lock for writing before modifying the
- * vmas or anything the coredump pretends not to change from under it.
- *
- * It also has to be called when mmgrab() is used in the context of
- * the process, but then the mm_count refcount is transferred outside
- * the context of the process to run down_write() on that pinned mm.
- *
- * NOTE: find_extend_vma() called from GUP context is the only place
- * that can modify the "mm" (notably the vm_start/end) under mmap_lock
- * for reading and outside the context of the process, so it is also
- * the only case that holds the mmap_lock for reading that must call
- * this function. Generally if the mmap_lock is hold for reading
- * there's no need of this check after get_task_mm()/mmget_not_zero().
- *
- * This function can be obsoleted and the check can be removed, after
- * the coredump code will hold the mmap_lock for writing before
- * invoking the ->core_dump methods.
- */
-static inline bool mmget_still_valid(struct mm_struct *mm)
-{
-	return likely(!mm->core_state);
-}
-
 /**
  * mmget() - Pin the address space associated with a &struct mm_struct.
  * @mm: The address space to pin.
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 58b0d9c502a1..4e3dff13eb70 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -434,7 +434,7 @@ static void insert_to_mm_slots_hash(struct mm_struct *mm,
 
 static inline int khugepaged_test_exit(struct mm_struct *mm)
 {
-	return atomic_read(&mm->mm_users) == 0 || !mmget_still_valid(mm);
+	return atomic_read(&mm->mm_users) == 0;
 }
 
 static bool hugepage_vma_check(struct vm_area_struct *vma,
diff --git a/mm/madvise.c b/mm/madvise.c
index 68b761c359d0..fd1f448b4e1d 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -1085,23 +1085,6 @@ int do_madvise(unsigned long start, size_t len_in, int behavior)
 	if (write) {
 		if (mmap_write_lock_killable(current->mm))
 			return -EINTR;
-
-		/*
-		 * We may have stolen the mm from another process
-		 * that is undergoing core dumping.
-		 *
-		 * Right now that's io_ring, in the future it may
-		 * be remote process management and not "current"
-		 * at all.
-		 *
-		 * We need to fix core dumping to not do this,
-		 * but for now we have the mmget_still_valid()
-		 * model.
-		 */
-		if (!mmget_still_valid(current->mm)) {
-			mmap_write_unlock(current->mm);
-			return -EINTR;
-		}
 	} else {
 		mmap_read_lock(current->mm);
 	}
diff --git a/mm/mmap.c b/mm/mmap.c
index 9fb9f8a233c7..ebb92f5515a1 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2562,7 +2562,7 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr)
 	if (vma && (vma->vm_start <= addr))
 		return vma;
 	/* don't alter vm_end if the coredump is running */
-	if (!prev || !mmget_still_valid(mm) || expand_stack(prev, addr))
+	if (!prev || expand_stack(prev, addr))
 		return NULL;
 	if (prev->vm_flags & VM_LOCKED)
 		populate_vma_page_range(prev, addr, prev->vm_end, NULL);
@@ -2588,9 +2588,6 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr)
 		return vma;
 	if (!(vma->vm_flags & VM_GROWSDOWN))
 		return NULL;
-	/* don't alter vm_start if the coredump is running */
-	if (!mmget_still_valid(mm))
-		return NULL;
 	start = vma->vm_start;
 	if (expand_stack(vma, addr))
 		return NULL;
-- 
cgit v1.2.3


From 5cf53f3ce3b9ff5321b56f9ed9d90d59307be7d0 Mon Sep 17 00:00:00 2001
From: Elena Petrova <lenaptr@google.com>
Date: Thu, 15 Oct 2020 20:13:35 -0700
Subject: sched.h: drop in_ubsan field when UBSAN is in trap mode

in_ubsan field of task_struct is only used in lib/ubsan.c, which in its
turn is used only `ifneq ($(CONFIG_UBSAN_TRAP),y)`.

Removing unnecessary field from a task_struct will help preserve the ABI
between vanilla and CONFIG_UBSAN_TRAP'ed kernels.  In particular, this
will help enabling bounds sanitizer transparently for Android's GKI.

Signed-off-by: Elena Petrova <lenaptr@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Kees Cook <keescook@chromium.org>
Cc: Jann Horn <jannh@google.com>
Link: https://lkml.kernel.org/r/20200910134802.3160311-1-lenaptr@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/sched.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9030f3abd969..063cd120b459 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1013,7 +1013,7 @@ struct task_struct {
 	struct held_lock		held_locks[MAX_LOCK_DEPTH];
 #endif
 
-#ifdef CONFIG_UBSAN
+#if defined(CONFIG_UBSAN) && !defined(CONFIG_UBSAN_TRAP)
 	unsigned int			in_ubsan;
 #endif
 
-- 
cgit v1.2.3


From 2c739ced5886cd8c8361faa79a9522ec05174ed0 Mon Sep 17 00:00:00 2001
From: Albert van der Linde <alinde@google.com>
Date: Thu, 15 Oct 2020 20:13:46 -0700
Subject: lib, include/linux: add usercopy failure capability

Patch series "add fault injection to user memory access", v3.

The goal of this series is to improve testing of fault-tolerance in usages
of user memory access functions, by adding support for fault injection.

syzkaller/syzbot are using the existing fault injection modes and will use
this particular feature also.

The first patch adds failure injection capability for usercopy functions.
The second changes usercopy functions to use this new failure capability
(copy_from_user, ...).  The third patch adds get/put/clear_user failures
to x86.

This patch (of 3):

Add a failure injection capability to improve testing of fault-tolerance
in usages of user memory access functions.

Add CONFIG_FAULT_INJECTION_USERCOPY to enable faults in usercopy
functions.  The should_fail_usercopy function is to be called by these
functions (copy_from_user, get_user, ...) in order to fail or not.

Signed-off-by: Albert van der Linde <alinde@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Akinobu Mita <akinobu.mita@gmail.com>
Reviewed-by: Alexander Potapenko <glider@google.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrey Konovalov <andreyknvl@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Marco Elver <elver@google.com>
Cc: Christoph Hellwig <hch@lst.de>
Link: http://lkml.kernel.org/r/20200831171733.955393-1-alinde@google.com
Link: http://lkml.kernel.org/r/20200831171733.955393-2-alinde@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/admin-guide/kernel-parameters.txt   |  1 +
 Documentation/fault-injection/fault-injection.rst |  7 +++-
 include/linux/fault-inject-usercopy.h             | 22 +++++++++++++
 lib/Kconfig.debug                                 |  7 ++++
 lib/Makefile                                      |  1 +
 lib/fault-inject-usercopy.c                       | 39 +++++++++++++++++++++++
 6 files changed, 76 insertions(+), 1 deletion(-)
 create mode 100644 include/linux/fault-inject-usercopy.h
 create mode 100644 lib/fault-inject-usercopy.c

(limited to 'include/linux')

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index f7ac0e663976..6d9afb221ff7 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1343,6 +1343,7 @@
 			current integrity status.
 
 	failslab=
+	fail_usercopy=
 	fail_page_alloc=
 	fail_make_request=[KNL]
 			General fault injection mechanism.
diff --git a/Documentation/fault-injection/fault-injection.rst b/Documentation/fault-injection/fault-injection.rst
index f850ad018b70..31ecfe44e5b4 100644
--- a/Documentation/fault-injection/fault-injection.rst
+++ b/Documentation/fault-injection/fault-injection.rst
@@ -16,6 +16,10 @@ Available fault injection capabilities
 
   injects page allocation failures. (alloc_pages(), get_free_pages(), ...)
 
+- fail_usercopy
+
+  injects failures in user memory access functions. (copy_from_user(), get_user(), ...)
+
 - fail_futex
 
   injects futex deadlock and uaddr fault errors.
@@ -177,6 +181,7 @@ use the boot option::
 
 	failslab=
 	fail_page_alloc=
+	fail_usercopy=
 	fail_make_request=
 	fail_futex=
 	mmc_core.fail_request=<interval>,<probability>,<space>,<times>
@@ -222,7 +227,7 @@ How to add new fault injection capability
 
 - debugfs entries
 
-  failslab, fail_page_alloc, and fail_make_request use this way.
+  failslab, fail_page_alloc, fail_usercopy, and fail_make_request use this way.
   Helper functions:
 
 	fault_create_debugfs_attr(name, parent, attr);
diff --git a/include/linux/fault-inject-usercopy.h b/include/linux/fault-inject-usercopy.h
new file mode 100644
index 000000000000..56c3a693fdd9
--- /dev/null
+++ b/include/linux/fault-inject-usercopy.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_FAULT_INJECT_USERCOPY_H__
+#define __LINUX_FAULT_INJECT_USERCOPY_H__
+
+/*
+ * This header provides a wrapper for injecting failures to user space memory
+ * access functions.
+ */
+
+#include <linux/types.h>
+
+#ifdef CONFIG_FAULT_INJECTION_USERCOPY
+
+bool should_fail_usercopy(void);
+
+#else
+
+static inline bool should_fail_usercopy(void) { return false; }
+
+#endif /* CONFIG_FAULT_INJECTION_USERCOPY */
+
+#endif /* __LINUX_FAULT_INJECT_USERCOPY_H__ */
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 491789a793ae..ebe5ab111e65 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1768,6 +1768,13 @@ config FAIL_PAGE_ALLOC
 	help
 	  Provide fault-injection capability for alloc_pages().
 
+config FAULT_INJECTION_USERCOPY
+	bool "Fault injection capability for usercopy functions"
+	depends on FAULT_INJECTION
+	help
+	  Provides fault-injection capability to inject failures
+	  in usercopy functions (copy_from_user(), get_user(), ...).
+
 config FAIL_MAKE_REQUEST
 	bool "Fault-injection capability for disk IO"
 	depends on FAULT_INJECTION && BLOCK
diff --git a/lib/Makefile b/lib/Makefile
index 49a2a9e36224..1c7577b2e86a 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -210,6 +210,7 @@ obj-$(CONFIG_AUDIT_COMPAT_GENERIC) += compat_audit.o
 
 obj-$(CONFIG_IOMMU_HELPER) += iommu-helper.o
 obj-$(CONFIG_FAULT_INJECTION) += fault-inject.o
+obj-$(CONFIG_FAULT_INJECTION_USERCOPY) += fault-inject-usercopy.o
 obj-$(CONFIG_NOTIFIER_ERROR_INJECTION) += notifier-error-inject.o
 obj-$(CONFIG_PM_NOTIFIER_ERROR_INJECT) += pm-notifier-error-inject.o
 obj-$(CONFIG_NETDEV_NOTIFIER_ERROR_INJECT) += netdev-notifier-error-inject.o
diff --git a/lib/fault-inject-usercopy.c b/lib/fault-inject-usercopy.c
new file mode 100644
index 000000000000..77558b6c29ca
--- /dev/null
+++ b/lib/fault-inject-usercopy.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/fault-inject.h>
+#include <linux/fault-inject-usercopy.h>
+
+static struct {
+	struct fault_attr attr;
+} fail_usercopy = {
+	.attr = FAULT_ATTR_INITIALIZER,
+};
+
+static int __init setup_fail_usercopy(char *str)
+{
+	return setup_fault_attr(&fail_usercopy.attr, str);
+}
+__setup("fail_usercopy=", setup_fail_usercopy);
+
+#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
+
+static int __init fail_usercopy_debugfs(void)
+{
+	struct dentry *dir;
+
+	dir = fault_create_debugfs_attr("fail_usercopy", NULL,
+					&fail_usercopy.attr);
+	if (IS_ERR(dir))
+		return PTR_ERR(dir);
+
+	return 0;
+}
+
+late_initcall(fail_usercopy_debugfs);
+
+#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */
+
+bool should_fail_usercopy(void)
+{
+	return should_fail(&fail_usercopy.attr, 1);
+}
+EXPORT_SYMBOL_GPL(should_fail_usercopy);
-- 
cgit v1.2.3


From 4d0e9df5e43dba52d38b251e3b909df8fa1110be Mon Sep 17 00:00:00 2001
From: Albert van der Linde <alinde@google.com>
Date: Thu, 15 Oct 2020 20:13:50 -0700
Subject: lib, uaccess: add failure injection to usercopy functions

To test fault-tolerance of user memory access functions, introduce fault
injection to usercopy functions.

If a failure is expected return either -EFAULT or the total amount of
bytes that were not copied.

Signed-off-by: Albert van der Linde <alinde@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Akinobu Mita <akinobu.mita@gmail.com>
Reviewed-by: Alexander Potapenko <glider@google.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrey Konovalov <andreyknvl@google.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Marco Elver <elver@google.com>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Christoph Hellwig <hch@lst.de>
Link: http://lkml.kernel.org/r/20200831171733.955393-3-alinde@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/uaccess.h | 11 ++++++++++-
 lib/iov_iter.c          |  5 +++++
 lib/strncpy_from_user.c |  3 +++
 lib/usercopy.c          |  5 ++++-
 4 files changed, 22 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index ef084eacaa7c..1b8c9d6162bc 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -2,6 +2,7 @@
 #ifndef __LINUX_UACCESS_H__
 #define __LINUX_UACCESS_H__
 
+#include <linux/fault-inject-usercopy.h>
 #include <linux/instrumented.h>
 #include <linux/minmax.h>
 #include <linux/sched.h>
@@ -84,6 +85,8 @@ static __always_inline __must_check unsigned long
 __copy_from_user(void *to, const void __user *from, unsigned long n)
 {
 	might_fault();
+	if (should_fail_usercopy())
+		return n;
 	instrument_copy_from_user(to, from, n);
 	check_object_size(to, n, false);
 	return raw_copy_from_user(to, from, n);
@@ -105,6 +108,8 @@ __copy_from_user(void *to, const void __user *from, unsigned long n)
 static __always_inline __must_check unsigned long
 __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n)
 {
+	if (should_fail_usercopy())
+		return n;
 	instrument_copy_to_user(to, from, n);
 	check_object_size(from, n, true);
 	return raw_copy_to_user(to, from, n);
@@ -114,6 +119,8 @@ static __always_inline __must_check unsigned long
 __copy_to_user(void __user *to, const void *from, unsigned long n)
 {
 	might_fault();
+	if (should_fail_usercopy())
+		return n;
 	instrument_copy_to_user(to, from, n);
 	check_object_size(from, n, true);
 	return raw_copy_to_user(to, from, n);
@@ -125,7 +132,7 @@ _copy_from_user(void *to, const void __user *from, unsigned long n)
 {
 	unsigned long res = n;
 	might_fault();
-	if (likely(access_ok(from, n))) {
+	if (!should_fail_usercopy() && likely(access_ok(from, n))) {
 		instrument_copy_from_user(to, from, n);
 		res = raw_copy_from_user(to, from, n);
 	}
@@ -143,6 +150,8 @@ static inline __must_check unsigned long
 _copy_to_user(void __user *to, const void *from, unsigned long n)
 {
 	might_fault();
+	if (should_fail_usercopy())
+		return n;
 	if (access_ok(to, n)) {
 		instrument_copy_to_user(to, from, n);
 		n = raw_copy_to_user(to, from, n);
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 14cae2584db4..1635111c5bd2 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -2,6 +2,7 @@
 #include <crypto/hash.h>
 #include <linux/export.h>
 #include <linux/bvec.h>
+#include <linux/fault-inject-usercopy.h>
 #include <linux/uio.h>
 #include <linux/pagemap.h>
 #include <linux/slab.h>
@@ -140,6 +141,8 @@
 
 static int copyout(void __user *to, const void *from, size_t n)
 {
+	if (should_fail_usercopy())
+		return n;
 	if (access_ok(to, n)) {
 		instrument_copy_to_user(to, from, n);
 		n = raw_copy_to_user(to, from, n);
@@ -149,6 +152,8 @@ static int copyout(void __user *to, const void *from, size_t n)
 
 static int copyin(void *to, const void __user *from, size_t n)
 {
+	if (should_fail_usercopy())
+		return n;
 	if (access_ok(from, n)) {
 		instrument_copy_from_user(to, from, n);
 		n = raw_copy_from_user(to, from, n);
diff --git a/lib/strncpy_from_user.c b/lib/strncpy_from_user.c
index 34696a348864..e6d5fcc2cdf3 100644
--- a/lib/strncpy_from_user.c
+++ b/lib/strncpy_from_user.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/compiler.h>
 #include <linux/export.h>
+#include <linux/fault-inject-usercopy.h>
 #include <linux/kasan-checks.h>
 #include <linux/thread_info.h>
 #include <linux/uaccess.h>
@@ -99,6 +100,8 @@ long strncpy_from_user(char *dst, const char __user *src, long count)
 	unsigned long max_addr, src_addr;
 
 	might_fault();
+	if (should_fail_usercopy())
+		return -EFAULT;
 	if (unlikely(count <= 0))
 		return 0;
 
diff --git a/lib/usercopy.c b/lib/usercopy.c
index b26509f112f9..7413dd300516 100644
--- a/lib/usercopy.c
+++ b/lib/usercopy.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/bitops.h>
+#include <linux/fault-inject-usercopy.h>
 #include <linux/instrumented.h>
 #include <linux/uaccess.h>
 
@@ -10,7 +11,7 @@ unsigned long _copy_from_user(void *to, const void __user *from, unsigned long n
 {
 	unsigned long res = n;
 	might_fault();
-	if (likely(access_ok(from, n))) {
+	if (!should_fail_usercopy() && likely(access_ok(from, n))) {
 		instrument_copy_from_user(to, from, n);
 		res = raw_copy_from_user(to, from, n);
 	}
@@ -25,6 +26,8 @@ EXPORT_SYMBOL(_copy_from_user);
 unsigned long _copy_to_user(void __user *to, const void *from, unsigned long n)
 {
 	might_fault();
+	if (should_fail_usercopy())
+		return n;
 	if (likely(access_ok(to, n))) {
 		instrument_copy_to_user(to, from, n);
 		n = raw_copy_to_user(to, from, n);
-- 
cgit v1.2.3


From 98447d65b4a7a59f8ea37dc6e5d743247d9a7b01 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Wed, 14 Oct 2020 10:48:51 -0600
Subject: io_uring: move io identity items into separate struct

io-wq contains a pointer to the identity, which we just hold in io_kiocb
for now. This is in preparation for putting this outside io_kiocb. The
only exception is struct files_struct, which we'll need different rules
for to avoid a circular dependency.

No functional changes in this patch.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io-wq.c               | 34 +++++++++++++-------------
 fs/io-wq.h               | 12 +++-------
 fs/io_uring.c            | 62 ++++++++++++++++++++++++------------------------
 include/linux/io_uring.h | 13 +++++++++-
 4 files changed, 64 insertions(+), 57 deletions(-)

(limited to 'include/linux')

diff --git a/fs/io-wq.c b/fs/io-wq.c
index b7d8e544a804..0c852b75384d 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -430,9 +430,9 @@ static void io_wq_switch_mm(struct io_worker *worker, struct io_wq_work *work)
 		worker->mm = NULL;
 	}
 
-	if (mmget_not_zero(work->mm)) {
-		kthread_use_mm(work->mm);
-		worker->mm = work->mm;
+	if (mmget_not_zero(work->identity->mm)) {
+		kthread_use_mm(work->identity->mm);
+		worker->mm = work->identity->mm;
 		return;
 	}
 
@@ -446,9 +446,9 @@ static inline void io_wq_switch_blkcg(struct io_worker *worker,
 #ifdef CONFIG_BLK_CGROUP
 	if (!(work->flags & IO_WQ_WORK_BLKCG))
 		return;
-	if (work->blkcg_css != worker->blkcg_css) {
-		kthread_associate_blkcg(work->blkcg_css);
-		worker->blkcg_css = work->blkcg_css;
+	if (work->identity->blkcg_css != worker->blkcg_css) {
+		kthread_associate_blkcg(work->identity->blkcg_css);
+		worker->blkcg_css = work->identity->blkcg_css;
 	}
 #endif
 }
@@ -456,9 +456,9 @@ static inline void io_wq_switch_blkcg(struct io_worker *worker,
 static void io_wq_switch_creds(struct io_worker *worker,
 			       struct io_wq_work *work)
 {
-	const struct cred *old_creds = override_creds(work->creds);
+	const struct cred *old_creds = override_creds(work->identity->creds);
 
-	worker->cur_creds = work->creds;
+	worker->cur_creds = work->identity->creds;
 	if (worker->saved_creds)
 		put_cred(old_creds); /* creds set by previous switch */
 	else
@@ -468,19 +468,21 @@ static void io_wq_switch_creds(struct io_worker *worker,
 static void io_impersonate_work(struct io_worker *worker,
 				struct io_wq_work *work)
 {
-	if ((work->flags & IO_WQ_WORK_FILES) && current->files != work->files) {
+	if ((work->flags & IO_WQ_WORK_FILES) &&
+	    current->files != work->identity->files) {
 		task_lock(current);
-		current->files = work->files;
-		current->nsproxy = work->nsproxy;
+		current->files = work->identity->files;
+		current->nsproxy = work->identity->nsproxy;
 		task_unlock(current);
 	}
-	if ((work->flags & IO_WQ_WORK_FS) && current->fs != work->fs)
-		current->fs = work->fs;
-	if ((work->flags & IO_WQ_WORK_MM) && work->mm != worker->mm)
+	if ((work->flags & IO_WQ_WORK_FS) && current->fs != work->identity->fs)
+		current->fs = work->identity->fs;
+	if ((work->flags & IO_WQ_WORK_MM) && work->identity->mm != worker->mm)
 		io_wq_switch_mm(worker, work);
-	if ((work->flags & IO_WQ_WORK_CREDS) && worker->cur_creds != work->creds)
+	if ((work->flags & IO_WQ_WORK_CREDS) &&
+	    worker->cur_creds != work->identity->creds)
 		io_wq_switch_creds(worker, work);
-	current->signal->rlim[RLIMIT_FSIZE].rlim_cur = work->fsize;
+	current->signal->rlim[RLIMIT_FSIZE].rlim_cur = work->identity->fsize;
 	io_wq_switch_blkcg(worker, work);
 }
 
diff --git a/fs/io-wq.h b/fs/io-wq.h
index 31a29023605a..be21c500c925 100644
--- a/fs/io-wq.h
+++ b/fs/io-wq.h
@@ -1,6 +1,8 @@
 #ifndef INTERNAL_IO_WQ_H
 #define INTERNAL_IO_WQ_H
 
+#include <linux/io_uring.h>
+
 struct io_wq;
 
 enum {
@@ -91,15 +93,7 @@ static inline void wq_list_del(struct io_wq_work_list *list,
 
 struct io_wq_work {
 	struct io_wq_work_node list;
-	struct files_struct *files;
-	struct mm_struct *mm;
-#ifdef CONFIG_BLK_CGROUP
-	struct cgroup_subsys_state *blkcg_css;
-#endif
-	const struct cred *creds;
-	struct nsproxy *nsproxy;
-	struct fs_struct *fs;
-	unsigned long fsize;
+	struct io_identity *identity;
 	unsigned flags;
 };
 
diff --git a/fs/io_uring.c b/fs/io_uring.c
index e92ed22ef924..bd6fd51302ed 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -689,6 +689,7 @@ struct io_kiocb {
 	struct hlist_node		hash_node;
 	struct async_poll		*apoll;
 	struct io_wq_work		work;
+	struct io_identity		identity;
 };
 
 struct io_defer_entry {
@@ -1050,6 +1051,7 @@ static inline void io_req_init_async(struct io_kiocb *req)
 
 	memset(&req->work, 0, sizeof(req->work));
 	req->flags |= REQ_F_WORK_INITIALIZED;
+	req->work.identity = &req->identity;
 }
 
 static inline bool io_async_submit(struct io_ring_ctx *ctx)
@@ -1163,26 +1165,26 @@ static void io_req_clean_work(struct io_kiocb *req)
 	req->flags &= ~REQ_F_WORK_INITIALIZED;
 
 	if (req->work.flags & IO_WQ_WORK_MM) {
-		mmdrop(req->work.mm);
+		mmdrop(req->work.identity->mm);
 		req->work.flags &= ~IO_WQ_WORK_MM;
 	}
 #ifdef CONFIG_BLK_CGROUP
 	if (req->work.flags & IO_WQ_WORK_BLKCG) {
-		css_put(req->work.blkcg_css);
+		css_put(req->work.identity->blkcg_css);
 		req->work.flags &= ~IO_WQ_WORK_BLKCG;
 	}
 #endif
 	if (req->work.flags & IO_WQ_WORK_CREDS) {
-		put_cred(req->work.creds);
+		put_cred(req->work.identity->creds);
 		req->work.flags &= ~IO_WQ_WORK_CREDS;
 	}
 	if (req->work.flags & IO_WQ_WORK_FS) {
-		struct fs_struct *fs = req->work.fs;
+		struct fs_struct *fs = req->work.identity->fs;
 
-		spin_lock(&req->work.fs->lock);
+		spin_lock(&req->work.identity->fs->lock);
 		if (--fs->users)
 			fs = NULL;
-		spin_unlock(&req->work.fs->lock);
+		spin_unlock(&req->work.identity->fs->lock);
 		if (fs)
 			free_fs_struct(fs);
 		req->work.flags &= ~IO_WQ_WORK_FS;
@@ -1206,9 +1208,9 @@ static void io_prep_async_work(struct io_kiocb *req)
 	if (!(req->work.flags & IO_WQ_WORK_FILES) &&
 	    (io_op_defs[req->opcode].work_flags & IO_WQ_WORK_FILES) &&
 	    !(req->flags & REQ_F_NO_FILE_TABLE)) {
-		req->work.files = get_files_struct(current);
+		req->work.identity->files = get_files_struct(current);
 		get_nsproxy(current->nsproxy);
-		req->work.nsproxy = current->nsproxy;
+		req->work.identity->nsproxy = current->nsproxy;
 		req->flags |= REQ_F_INFLIGHT;
 
 		spin_lock_irq(&ctx->inflight_lock);
@@ -1219,35 +1221,33 @@ static void io_prep_async_work(struct io_kiocb *req)
 	if (!(req->work.flags & IO_WQ_WORK_MM) &&
 	    (def->work_flags & IO_WQ_WORK_MM)) {
 		mmgrab(current->mm);
-		req->work.mm = current->mm;
+		req->work.identity->mm = current->mm;
 		req->work.flags |= IO_WQ_WORK_MM;
 	}
 #ifdef CONFIG_BLK_CGROUP
 	if (!(req->work.flags & IO_WQ_WORK_BLKCG) &&
 	    (def->work_flags & IO_WQ_WORK_BLKCG)) {
 		rcu_read_lock();
-		req->work.blkcg_css = blkcg_css();
+		req->work.identity->blkcg_css = blkcg_css();
 		/*
 		 * This should be rare, either the cgroup is dying or the task
 		 * is moving cgroups. Just punt to root for the handful of ios.
 		 */
-		if (!css_tryget_online(req->work.blkcg_css))
-			req->work.blkcg_css = NULL;
-		else
+		if (css_tryget_online(req->work.identity->blkcg_css))
 			req->work.flags |= IO_WQ_WORK_BLKCG;
 		rcu_read_unlock();
 	}
 #endif
 	if (!(req->work.flags & IO_WQ_WORK_CREDS)) {
-		req->work.creds = get_current_cred();
+		req->work.identity->creds = get_current_cred();
 		req->work.flags |= IO_WQ_WORK_CREDS;
 	}
 	if (!(req->work.flags & IO_WQ_WORK_FS) &&
 	    (def->work_flags & IO_WQ_WORK_FS)) {
 		spin_lock(&current->fs->lock);
 		if (!current->fs->in_exec) {
-			req->work.fs = current->fs;
-			req->work.fs->users++;
+			req->work.identity->fs = current->fs;
+			req->work.identity->fs->users++;
 			req->work.flags |= IO_WQ_WORK_FS;
 		} else {
 			req->work.flags |= IO_WQ_WORK_CANCEL;
@@ -1255,9 +1255,9 @@ static void io_prep_async_work(struct io_kiocb *req)
 		spin_unlock(&current->fs->lock);
 	}
 	if (def->needs_fsize)
-		req->work.fsize = rlimit(RLIMIT_FSIZE);
+		req->work.identity->fsize = rlimit(RLIMIT_FSIZE);
 	else
-		req->work.fsize = RLIM_INFINITY;
+		req->work.identity->fsize = RLIM_INFINITY;
 }
 
 static void io_prep_async_link(struct io_kiocb *req)
@@ -1449,7 +1449,7 @@ static inline bool io_match_files(struct io_kiocb *req,
 		return true;
 	if ((req->flags & REQ_F_WORK_INITIALIZED) &&
 	    (req->work.flags & IO_WQ_WORK_FILES))
-		return req->work.files == files;
+		return req->work.identity->files == files;
 	return false;
 }
 
@@ -4089,7 +4089,7 @@ static int io_close(struct io_kiocb *req, bool force_nonblock,
 	}
 
 	/* No ->flush() or already async, safely close from here */
-	ret = filp_close(close->put_file, req->work.files);
+	ret = filp_close(close->put_file, req->work.identity->files);
 	if (ret < 0)
 		req_set_fail_links(req);
 	fput(close->put_file);
@@ -5703,8 +5703,8 @@ static void io_req_drop_files(struct io_kiocb *req)
 		wake_up(&ctx->inflight_wait);
 	spin_unlock_irqrestore(&ctx->inflight_lock, flags);
 	req->flags &= ~REQ_F_INFLIGHT;
-	put_files_struct(req->work.files);
-	put_nsproxy(req->work.nsproxy);
+	put_files_struct(req->work.identity->files);
+	put_nsproxy(req->work.identity->nsproxy);
 	req->work.flags &= ~IO_WQ_WORK_FILES;
 }
 
@@ -6063,14 +6063,14 @@ static void __io_queue_sqe(struct io_kiocb *req, struct io_comp_state *cs)
 again:
 	linked_timeout = io_prep_linked_timeout(req);
 
-	if ((req->flags & REQ_F_WORK_INITIALIZED) && req->work.creds &&
-	    req->work.creds != current_cred()) {
+	if ((req->flags & REQ_F_WORK_INITIALIZED) && req->work.identity->creds &&
+	    req->work.identity->creds != current_cred()) {
 		if (old_creds)
 			revert_creds(old_creds);
-		if (old_creds == req->work.creds)
+		if (old_creds == req->work.identity->creds)
 			old_creds = NULL; /* restored original creds */
 		else
-			old_creds = override_creds(req->work.creds);
+			old_creds = override_creds(req->work.identity->creds);
 		req->work.flags |= IO_WQ_WORK_CREDS;
 	}
 
@@ -6375,10 +6375,10 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	id = READ_ONCE(sqe->personality);
 	if (id) {
 		io_req_init_async(req);
-		req->work.creds = idr_find(&ctx->personality_idr, id);
-		if (unlikely(!req->work.creds))
+		req->work.identity->creds = idr_find(&ctx->personality_idr, id);
+		if (unlikely(!req->work.identity->creds))
 			return -EINVAL;
-		get_cred(req->work.creds);
+		get_cred(req->work.identity->creds);
 		req->work.flags |= IO_WQ_WORK_CREDS;
 	}
 
@@ -8248,7 +8248,7 @@ static bool io_wq_files_match(struct io_wq_work *work, void *data)
 	struct files_struct *files = data;
 
 	return !files || ((work->flags & IO_WQ_WORK_FILES) &&
-				work->files == files);
+				work->identity->files == files);
 }
 
 /*
@@ -8404,7 +8404,7 @@ static bool io_uring_cancel_files(struct io_ring_ctx *ctx,
 		spin_lock_irq(&ctx->inflight_lock);
 		list_for_each_entry(req, &ctx->inflight_list, inflight_entry) {
 			if (files && (req->work.flags & IO_WQ_WORK_FILES) &&
-			    req->work.files != files)
+			    req->work.identity->files != files)
 				continue;
 			/* req is being completed, ignore */
 			if (!refcount_inc_not_zero(&req->refs))
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index 96315cfaf6d1..352aa6bbd36b 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -4,7 +4,18 @@
 
 #include <linux/sched.h>
 #include <linux/xarray.h>
-#include <linux/percpu-refcount.h>
+
+struct io_identity {
+	struct files_struct		*files;
+	struct mm_struct		*mm;
+#ifdef CONFIG_BLK_CGROUP
+	struct cgroup_subsys_state	*blkcg_css;
+#endif
+	const struct cred		*creds;
+	struct nsproxy			*nsproxy;
+	struct fs_struct		*fs;
+	unsigned long			fsize;
+};
 
 struct io_uring_task {
 	/* submission side */
-- 
cgit v1.2.3


From 1e6fa5216a0e59ef02e8b6b40d553238a3b81d49 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 15 Oct 2020 08:46:24 -0600
Subject: io_uring: COW io_identity on mismatch

If the io_identity doesn't completely match the task, then create a
copy of it and use that. The existing copy remains valid until the last
user of it has gone away.

This also changes the personality lookup to be indexed by io_identity,
instead of creds directly.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c            | 222 ++++++++++++++++++++++++++++++++++++-----------
 include/linux/io_uring.h |   1 +
 2 files changed, 171 insertions(+), 52 deletions(-)

(limited to 'include/linux')

diff --git a/fs/io_uring.c b/fs/io_uring.c
index bd6fd51302ed..ab30834c275f 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1040,6 +1040,27 @@ static inline void req_set_fail_links(struct io_kiocb *req)
 		req->flags |= REQ_F_FAIL_LINK;
 }
 
+/*
+ * None of these are dereferenced, they are simply used to check if any of
+ * them have changed. If we're under current and check they are still the
+ * same, we're fine to grab references to them for actual out-of-line use.
+ */
+static void io_init_identity(struct io_identity *id)
+{
+	id->files = current->files;
+	id->mm = current->mm;
+#ifdef CONFIG_BLK_CGROUP
+	rcu_read_lock();
+	id->blkcg_css = blkcg_css();
+	rcu_read_unlock();
+#endif
+	id->creds = current_cred();
+	id->nsproxy = current->nsproxy;
+	id->fs = current->fs;
+	id->fsize = rlimit(RLIMIT_FSIZE);
+	refcount_set(&id->count, 1);
+}
+
 /*
  * Note: must call io_req_init_async() for the first time you
  * touch any members of io_wq_work.
@@ -1051,6 +1072,7 @@ static inline void io_req_init_async(struct io_kiocb *req)
 
 	memset(&req->work, 0, sizeof(req->work));
 	req->flags |= REQ_F_WORK_INITIALIZED;
+	io_init_identity(&req->identity);
 	req->work.identity = &req->identity;
 }
 
@@ -1157,6 +1179,14 @@ static void __io_commit_cqring(struct io_ring_ctx *ctx)
 	}
 }
 
+static void io_put_identity(struct io_kiocb *req)
+{
+	if (req->work.identity == &req->identity)
+		return;
+	if (refcount_dec_and_test(&req->work.identity->count))
+		kfree(req->work.identity);
+}
+
 static void io_req_clean_work(struct io_kiocb *req)
 {
 	if (!(req->flags & REQ_F_WORK_INITIALIZED))
@@ -1189,28 +1219,67 @@ static void io_req_clean_work(struct io_kiocb *req)
 			free_fs_struct(fs);
 		req->work.flags &= ~IO_WQ_WORK_FS;
 	}
+
+	io_put_identity(req);
 }
 
-static void io_prep_async_work(struct io_kiocb *req)
+/*
+ * Create a private copy of io_identity, since some fields don't match
+ * the current context.
+ */
+static bool io_identity_cow(struct io_kiocb *req)
+{
+	const struct cred *creds = NULL;
+	struct io_identity *id;
+
+	if (req->work.flags & IO_WQ_WORK_CREDS)
+		creds = req->work.identity->creds;
+
+	id = kmemdup(req->work.identity, sizeof(*id), GFP_KERNEL);
+	if (unlikely(!id)) {
+		req->work.flags |= IO_WQ_WORK_CANCEL;
+		return false;
+	}
+
+	/*
+	 * We can safely just re-init the creds we copied  Either the field
+	 * matches the current one, or we haven't grabbed it yet. The only
+	 * exception is ->creds, through registered personalities, so handle
+	 * that one separately.
+	 */
+	io_init_identity(id);
+	if (creds)
+		req->work.identity->creds = creds;
+
+	/* add one for this request */
+	refcount_inc(&id->count);
+
+	/* drop old identity, assign new one. one ref for req, one for tctx */
+	if (req->work.identity != &req->identity &&
+	    refcount_sub_and_test(2, &req->work.identity->count))
+		kfree(req->work.identity);
+
+	req->work.identity = id;
+	return true;
+}
+
+static bool io_grab_identity(struct io_kiocb *req)
 {
 	const struct io_op_def *def = &io_op_defs[req->opcode];
+	struct io_identity *id = &req->identity;
 	struct io_ring_ctx *ctx = req->ctx;
 
-	io_req_init_async(req);
+	if (def->needs_fsize && id->fsize != rlimit(RLIMIT_FSIZE))
+		return false;
 
-	if (req->flags & REQ_F_ISREG) {
-		if (def->hash_reg_file || (ctx->flags & IORING_SETUP_IOPOLL))
-			io_wq_hash_work(&req->work, file_inode(req->file));
-	} else {
-		if (def->unbound_nonreg_file)
-			req->work.flags |= IO_WQ_WORK_UNBOUND;
-	}
 	if (!(req->work.flags & IO_WQ_WORK_FILES) &&
-	    (io_op_defs[req->opcode].work_flags & IO_WQ_WORK_FILES) &&
+	    (def->work_flags & IO_WQ_WORK_FILES) &&
 	    !(req->flags & REQ_F_NO_FILE_TABLE)) {
-		req->work.identity->files = get_files_struct(current);
-		get_nsproxy(current->nsproxy);
-		req->work.identity->nsproxy = current->nsproxy;
+		if (id->files != current->files ||
+		    id->nsproxy != current->nsproxy)
+			return false;
+		atomic_inc(&id->files->count);
+		get_nsproxy(id->nsproxy);
 		req->flags |= REQ_F_INFLIGHT;
 
 		spin_lock_irq(&ctx->inflight_lock);
@@ -1218,46 +1287,79 @@ static void io_prep_async_work(struct io_kiocb *req)
 		spin_unlock_irq(&ctx->inflight_lock);
 		req->work.flags |= IO_WQ_WORK_FILES;
 	}
-	if (!(req->work.flags & IO_WQ_WORK_MM) &&
-	    (def->work_flags & IO_WQ_WORK_MM)) {
-		mmgrab(current->mm);
-		req->work.identity->mm = current->mm;
-		req->work.flags |= IO_WQ_WORK_MM;
-	}
 #ifdef CONFIG_BLK_CGROUP
 	if (!(req->work.flags & IO_WQ_WORK_BLKCG) &&
 	    (def->work_flags & IO_WQ_WORK_BLKCG)) {
 		rcu_read_lock();
-		req->work.identity->blkcg_css = blkcg_css();
+		if (id->blkcg_css != blkcg_css()) {
+			rcu_read_unlock();
+			return false;
+		}
 		/*
 		 * This should be rare, either the cgroup is dying or the task
 		 * is moving cgroups. Just punt to root for the handful of ios.
 		 */
-		if (css_tryget_online(req->work.identity->blkcg_css))
+		if (css_tryget_online(id->blkcg_css))
 			req->work.flags |= IO_WQ_WORK_BLKCG;
 		rcu_read_unlock();
 	}
 #endif
 	if (!(req->work.flags & IO_WQ_WORK_CREDS)) {
-		req->work.identity->creds = get_current_cred();
+		if (id->creds != current_cred())
+			return false;
+		get_cred(id->creds);
 		req->work.flags |= IO_WQ_WORK_CREDS;
 	}
 	if (!(req->work.flags & IO_WQ_WORK_FS) &&
 	    (def->work_flags & IO_WQ_WORK_FS)) {
-		spin_lock(&current->fs->lock);
-		if (!current->fs->in_exec) {
-			req->work.identity->fs = current->fs;
-			req->work.identity->fs->users++;
+		if (current->fs != id->fs)
+			return false;
+		spin_lock(&id->fs->lock);
+		if (!id->fs->in_exec) {
+			id->fs->users++;
 			req->work.flags |= IO_WQ_WORK_FS;
 		} else {
 			req->work.flags |= IO_WQ_WORK_CANCEL;
 		}
 		spin_unlock(&current->fs->lock);
 	}
-	if (def->needs_fsize)
-		req->work.identity->fsize = rlimit(RLIMIT_FSIZE);
-	else
-		req->work.identity->fsize = RLIM_INFINITY;
+
+	return true;
+}
+
+static void io_prep_async_work(struct io_kiocb *req)
+{
+	const struct io_op_def *def = &io_op_defs[req->opcode];
+	struct io_identity *id = &req->identity;
+	struct io_ring_ctx *ctx = req->ctx;
+
+	io_req_init_async(req);
+
+	if (req->flags & REQ_F_ISREG) {
+		if (def->hash_reg_file || (ctx->flags & IORING_SETUP_IOPOLL))
+			io_wq_hash_work(&req->work, file_inode(req->file));
+	} else {
+		if (def->unbound_nonreg_file)
+			req->work.flags |= IO_WQ_WORK_UNBOUND;
+	}
+
+	/* ->mm can never change on us */
+	if (!(req->work.flags & IO_WQ_WORK_MM) &&
+	    (def->work_flags & IO_WQ_WORK_MM)) {
+		mmgrab(id->mm);
+		req->work.flags |= IO_WQ_WORK_MM;
+	}
+
+	/* if we fail grabbing identity, we must COW, regrab, and retry */
+	if (io_grab_identity(req))
+		return;
+
+	if (!io_identity_cow(req))
+		return;
+
+	/* can't fail at this point */
+	if (!io_grab_identity(req))
+		WARN_ON(1);
 }
 
 static void io_prep_async_link(struct io_kiocb *req)
@@ -1696,12 +1798,10 @@ static void io_dismantle_req(struct io_kiocb *req)
 
 static void __io_free_req(struct io_kiocb *req)
 {
-	struct io_uring_task *tctx;
-	struct io_ring_ctx *ctx;
+	struct io_uring_task *tctx = req->task->io_uring;
+	struct io_ring_ctx *ctx = req->ctx;
 
 	io_dismantle_req(req);
-	tctx = req->task->io_uring;
-	ctx = req->ctx;
 
 	atomic_long_inc(&tctx->req_complete);
 	if (tctx->in_idle)
@@ -6374,11 +6474,16 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 
 	id = READ_ONCE(sqe->personality);
 	if (id) {
+		struct io_identity *iod;
+
 		io_req_init_async(req);
-		req->work.identity->creds = idr_find(&ctx->personality_idr, id);
-		if (unlikely(!req->work.identity->creds))
+		iod = idr_find(&ctx->personality_idr, id);
+		if (unlikely(!iod))
 			return -EINVAL;
-		get_cred(req->work.identity->creds);
+		refcount_inc(&iod->count);
+		io_put_identity(req);
+		get_cred(iod->creds);
+		req->work.identity = iod;
 		req->work.flags |= IO_WQ_WORK_CREDS;
 	}
 
@@ -8171,11 +8276,14 @@ static int io_uring_fasync(int fd, struct file *file, int on)
 static int io_remove_personalities(int id, void *p, void *data)
 {
 	struct io_ring_ctx *ctx = data;
-	const struct cred *cred;
+	struct io_identity *iod;
 
-	cred = idr_remove(&ctx->personality_idr, id);
-	if (cred)
-		put_cred(cred);
+	iod = idr_remove(&ctx->personality_idr, id);
+	if (iod) {
+		put_cred(iod->creds);
+		if (refcount_dec_and_test(&iod->count))
+			kfree(iod);
+	}
 	return 0;
 }
 
@@ -9245,23 +9353,33 @@ out:
 
 static int io_register_personality(struct io_ring_ctx *ctx)
 {
-	const struct cred *creds = get_current_cred();
-	int id;
+	struct io_identity *id;
+	int ret;
 
-	id = idr_alloc_cyclic(&ctx->personality_idr, (void *) creds, 1,
-				USHRT_MAX, GFP_KERNEL);
-	if (id < 0)
-		put_cred(creds);
-	return id;
+	id = kmalloc(sizeof(*id), GFP_KERNEL);
+	if (unlikely(!id))
+		return -ENOMEM;
+
+	io_init_identity(id);
+	id->creds = get_current_cred();
+
+	ret = idr_alloc_cyclic(&ctx->personality_idr, id, 1, USHRT_MAX, GFP_KERNEL);
+	if (ret < 0) {
+		put_cred(id->creds);
+		kfree(id);
+	}
+	return ret;
 }
 
 static int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id)
 {
-	const struct cred *old_creds;
+	struct io_identity *iod;
 
-	old_creds = idr_remove(&ctx->personality_idr, id);
-	if (old_creds) {
-		put_cred(old_creds);
+	iod = idr_remove(&ctx->personality_idr, id);
+	if (iod) {
+		put_cred(iod->creds);
+		if (refcount_dec_and_test(&iod->count))
+			kfree(iod);
 		return 0;
 	}
 
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index 352aa6bbd36b..342cc574d5c0 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -15,6 +15,7 @@ struct io_identity {
 	struct nsproxy			*nsproxy;
 	struct fs_struct		*fs;
 	unsigned long			fsize;
+	refcount_t			count;
 };
 
 struct io_uring_task {
-- 
cgit v1.2.3


From 5c3462cfd123b341c9d3c947c1a2bab373f1697f Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 15 Oct 2020 09:02:33 -0600
Subject: io_uring: store io_identity in io_uring_task

This is, by definition, a per-task structure. So store it in the
task context, instead of doing carrying it in each io_kiocb. We're being
a bit inefficient if members have changed, as that requires an alloc and
copy of a new io_identity struct. The next patch will fix that up.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c            | 21 +++++++++++----------
 include/linux/io_uring.h |  1 +
 2 files changed, 12 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/fs/io_uring.c b/fs/io_uring.c
index ab30834c275f..ae91632b8bf9 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -689,7 +689,6 @@ struct io_kiocb {
 	struct hlist_node		hash_node;
 	struct async_poll		*apoll;
 	struct io_wq_work		work;
-	struct io_identity		identity;
 };
 
 struct io_defer_entry {
@@ -1072,8 +1071,7 @@ static inline void io_req_init_async(struct io_kiocb *req)
 
 	memset(&req->work, 0, sizeof(req->work));
 	req->flags |= REQ_F_WORK_INITIALIZED;
-	io_init_identity(&req->identity);
-	req->work.identity = &req->identity;
+	req->work.identity = &current->io_uring->identity;
 }
 
 static inline bool io_async_submit(struct io_ring_ctx *ctx)
@@ -1179,9 +1177,9 @@ static void __io_commit_cqring(struct io_ring_ctx *ctx)
 	}
 }
 
-static void io_put_identity(struct io_kiocb *req)
+static void io_put_identity(struct io_uring_task *tctx, struct io_kiocb *req)
 {
-	if (req->work.identity == &req->identity)
+	if (req->work.identity == &tctx->identity)
 		return;
 	if (refcount_dec_and_test(&req->work.identity->count))
 		kfree(req->work.identity);
@@ -1220,7 +1218,7 @@ static void io_req_clean_work(struct io_kiocb *req)
 		req->work.flags &= ~IO_WQ_WORK_FS;
 	}
 
-	io_put_identity(req);
+	io_put_identity(req->task->io_uring, req);
 }
 
 /*
@@ -1229,6 +1227,7 @@ static void io_req_clean_work(struct io_kiocb *req)
  */
 static bool io_identity_cow(struct io_kiocb *req)
 {
+	struct io_uring_task *tctx = current->io_uring;
 	const struct cred *creds = NULL;
 	struct io_identity *id;
 
@@ -1255,7 +1254,7 @@ static bool io_identity_cow(struct io_kiocb *req)
 	refcount_inc(&id->count);
 
 	/* drop old identity, assign new one. one ref for req, one for tctx */
-	if (req->work.identity != &req->identity &&
+	if (req->work.identity != &tctx->identity &&
 	    refcount_sub_and_test(2, &req->work.identity->count))
 		kfree(req->work.identity);
 
@@ -1266,7 +1265,7 @@ static bool io_identity_cow(struct io_kiocb *req)
 static bool io_grab_identity(struct io_kiocb *req)
 {
 	const struct io_op_def *def = &io_op_defs[req->opcode];
-	struct io_identity *id = &req->identity;
+	struct io_identity *id = req->work.identity;
 	struct io_ring_ctx *ctx = req->ctx;
 
 	if (def->needs_fsize && id->fsize != rlimit(RLIMIT_FSIZE))
@@ -1330,10 +1329,11 @@ static bool io_grab_identity(struct io_kiocb *req)
 static void io_prep_async_work(struct io_kiocb *req)
 {
 	const struct io_op_def *def = &io_op_defs[req->opcode];
-	struct io_identity *id = &req->identity;
 	struct io_ring_ctx *ctx = req->ctx;
+	struct io_identity *id;
 
 	io_req_init_async(req);
+	id = req->work.identity;
 
 	if (req->flags & REQ_F_ISREG) {
 		if (def->hash_reg_file || (ctx->flags & IORING_SETUP_IOPOLL))
@@ -6481,7 +6481,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 		if (unlikely(!iod))
 			return -EINVAL;
 		refcount_inc(&iod->count);
-		io_put_identity(req);
+		io_put_identity(current->io_uring, req);
 		get_cred(iod->creds);
 		req->work.identity = iod;
 		req->work.flags |= IO_WQ_WORK_CREDS;
@@ -7691,6 +7691,7 @@ static int io_uring_alloc_task_context(struct task_struct *task)
 	tctx->in_idle = 0;
 	atomic_long_set(&tctx->req_issue, 0);
 	atomic_long_set(&tctx->req_complete, 0);
+	io_init_identity(&tctx->identity);
 	task->io_uring = tctx;
 	return 0;
 }
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index 342cc574d5c0..bd3346194bca 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -24,6 +24,7 @@ struct io_uring_task {
 	struct wait_queue_head	wait;
 	struct file		*last;
 	atomic_long_t		req_issue;
+	struct io_identity	identity;
 
 	/* completion side */
 	bool			in_idle ____cacheline_aligned_in_smp;
-- 
cgit v1.2.3


From 500a373d731ac506612db12631ec21295c1ff360 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 15 Oct 2020 17:38:03 -0600
Subject: io_uring: assign new io_identity for task if members have changed

This avoids doing a copy for each new async IO, if some parts of the
io_identity has changed. We avoid reference counting for the normal
fast path of nothing ever changing.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c            | 19 +++++++++++++++----
 include/linux/io_uring.h |  3 ++-
 2 files changed, 17 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/fs/io_uring.c b/fs/io_uring.c
index ae91632b8bf9..7020c6a72231 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1066,12 +1066,18 @@ static void io_init_identity(struct io_identity *id)
  */
 static inline void io_req_init_async(struct io_kiocb *req)
 {
+	struct io_uring_task *tctx = current->io_uring;
+
 	if (req->flags & REQ_F_WORK_INITIALIZED)
 		return;
 
 	memset(&req->work, 0, sizeof(req->work));
 	req->flags |= REQ_F_WORK_INITIALIZED;
-	req->work.identity = &current->io_uring->identity;
+
+	/* Grab a ref if this isn't our static identity */
+	req->work.identity = tctx->identity;
+	if (tctx->identity != &tctx->__identity)
+		refcount_inc(&req->work.identity->count);
 }
 
 static inline bool io_async_submit(struct io_ring_ctx *ctx)
@@ -1179,7 +1185,7 @@ static void __io_commit_cqring(struct io_ring_ctx *ctx)
 
 static void io_put_identity(struct io_uring_task *tctx, struct io_kiocb *req)
 {
-	if (req->work.identity == &tctx->identity)
+	if (req->work.identity == &tctx->__identity)
 		return;
 	if (refcount_dec_and_test(&req->work.identity->count))
 		kfree(req->work.identity);
@@ -1254,11 +1260,12 @@ static bool io_identity_cow(struct io_kiocb *req)
 	refcount_inc(&id->count);
 
 	/* drop old identity, assign new one. one ref for req, one for tctx */
-	if (req->work.identity != &tctx->identity &&
+	if (req->work.identity != tctx->identity &&
 	    refcount_sub_and_test(2, &req->work.identity->count))
 		kfree(req->work.identity);
 
 	req->work.identity = id;
+	tctx->identity = id;
 	return true;
 }
 
@@ -7691,7 +7698,8 @@ static int io_uring_alloc_task_context(struct task_struct *task)
 	tctx->in_idle = 0;
 	atomic_long_set(&tctx->req_issue, 0);
 	atomic_long_set(&tctx->req_complete, 0);
-	io_init_identity(&tctx->identity);
+	io_init_identity(&tctx->__identity);
+	tctx->identity = &tctx->__identity;
 	task->io_uring = tctx;
 	return 0;
 }
@@ -7701,6 +7709,9 @@ void __io_uring_free(struct task_struct *tsk)
 	struct io_uring_task *tctx = tsk->io_uring;
 
 	WARN_ON_ONCE(!xa_empty(&tctx->xa));
+	WARN_ON_ONCE(refcount_read(&tctx->identity->count) != 1);
+	if (tctx->identity != &tctx->__identity)
+		kfree(tctx->identity);
 	kfree(tctx);
 	tsk->io_uring = NULL;
 }
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index bd3346194bca..607d14f61132 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -24,7 +24,8 @@ struct io_uring_task {
 	struct wait_queue_head	wait;
 	struct file		*last;
 	atomic_long_t		req_issue;
-	struct io_identity	identity;
+	struct io_identity	__identity;
+	struct io_identity	*identity;
 
 	/* completion side */
 	bool			in_idle ____cacheline_aligned_in_smp;
-- 
cgit v1.2.3


From d8a6df10aac9f2e4d5f30aff3129d552d2984ce7 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 15 Oct 2020 16:24:45 -0600
Subject: io_uring: use percpu counters to track inflight requests

Even though we place the req_issued and req_complete in separate
cachelines, there's considerable overhead in doing the atomics
particularly on the completion side.

Get rid of having the two counters, and just use a percpu_counter for
this. That's what it was made for, after all. This considerably
reduces the overhead in __io_free_req().

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c            | 50 +++++++++++++++++++++++++++---------------------
 include/linux/io_uring.h |  7 ++-----
 2 files changed, 30 insertions(+), 27 deletions(-)

(limited to 'include/linux')

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 7020c6a72231..58c445b95085 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1810,7 +1810,7 @@ static void __io_free_req(struct io_kiocb *req)
 
 	io_dismantle_req(req);
 
-	atomic_long_inc(&tctx->req_complete);
+	percpu_counter_dec(&tctx->inflight);
 	if (tctx->in_idle)
 		wake_up(&tctx->wait);
 	put_task_struct(req->task);
@@ -2089,7 +2089,9 @@ static void io_req_free_batch_finish(struct io_ring_ctx *ctx,
 	if (rb->to_free)
 		__io_req_free_batch_flush(ctx, rb);
 	if (rb->task) {
-		atomic_long_add(rb->task_refs, &rb->task->io_uring->req_complete);
+		struct io_uring_task *tctx = rb->task->io_uring;
+
+		percpu_counter_sub(&tctx->inflight, rb->task_refs);
 		put_task_struct_many(rb->task, rb->task_refs);
 		rb->task = NULL;
 	}
@@ -2106,7 +2108,9 @@ static void io_req_free_batch(struct req_batch *rb, struct io_kiocb *req)
 
 	if (req->task != rb->task) {
 		if (rb->task) {
-			atomic_long_add(rb->task_refs, &rb->task->io_uring->req_complete);
+			struct io_uring_task *tctx = rb->task->io_uring;
+
+			percpu_counter_sub(&tctx->inflight, rb->task_refs);
 			put_task_struct_many(rb->task, rb->task_refs);
 		}
 		rb->task = req->task;
@@ -6524,7 +6528,7 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr)
 	if (!percpu_ref_tryget_many(&ctx->refs, nr))
 		return -EAGAIN;
 
-	atomic_long_add(nr, &current->io_uring->req_issue);
+	percpu_counter_add(&current->io_uring->inflight, nr);
 	refcount_add(nr, &current->usage);
 
 	io_submit_state_start(&state, ctx, nr);
@@ -6566,10 +6570,12 @@ fail_req:
 
 	if (unlikely(submitted != nr)) {
 		int ref_used = (submitted == -EAGAIN) ? 0 : submitted;
+		struct io_uring_task *tctx = current->io_uring;
+		int unused = nr - ref_used;
 
-		percpu_ref_put_many(&ctx->refs, nr - ref_used);
-		atomic_long_sub(nr - ref_used, &current->io_uring->req_issue);
-		put_task_struct_many(current, nr - ref_used);
+		percpu_ref_put_many(&ctx->refs, unused);
+		percpu_counter_sub(&tctx->inflight, unused);
+		put_task_struct_many(current, unused);
 	}
 	if (link)
 		io_queue_link_head(link, &state.comp);
@@ -7687,17 +7693,22 @@ out_fput:
 static int io_uring_alloc_task_context(struct task_struct *task)
 {
 	struct io_uring_task *tctx;
+	int ret;
 
 	tctx = kmalloc(sizeof(*tctx), GFP_KERNEL);
 	if (unlikely(!tctx))
 		return -ENOMEM;
 
+	ret = percpu_counter_init(&tctx->inflight, 0, GFP_KERNEL);
+	if (unlikely(ret)) {
+		kfree(tctx);
+		return ret;
+	}
+
 	xa_init(&tctx->xa);
 	init_waitqueue_head(&tctx->wait);
 	tctx->last = NULL;
 	tctx->in_idle = 0;
-	atomic_long_set(&tctx->req_issue, 0);
-	atomic_long_set(&tctx->req_complete, 0);
 	io_init_identity(&tctx->__identity);
 	tctx->identity = &tctx->__identity;
 	task->io_uring = tctx;
@@ -7712,6 +7723,7 @@ void __io_uring_free(struct task_struct *tsk)
 	WARN_ON_ONCE(refcount_read(&tctx->identity->count) != 1);
 	if (tctx->identity != &tctx->__identity)
 		kfree(tctx->identity);
+	percpu_counter_destroy(&tctx->inflight);
 	kfree(tctx);
 	tsk->io_uring = NULL;
 }
@@ -8696,12 +8708,6 @@ void __io_uring_files_cancel(struct files_struct *files)
 	}
 }
 
-static inline bool io_uring_task_idle(struct io_uring_task *tctx)
-{
-	return atomic_long_read(&tctx->req_issue) ==
-		atomic_long_read(&tctx->req_complete);
-}
-
 /*
  * Find any io_uring fd that this task has registered or done IO on, and cancel
  * requests.
@@ -8710,14 +8716,16 @@ void __io_uring_task_cancel(void)
 {
 	struct io_uring_task *tctx = current->io_uring;
 	DEFINE_WAIT(wait);
-	long completions;
+	s64 inflight;
 
 	/* make sure overflow events are dropped */
 	tctx->in_idle = true;
 
-	while (!io_uring_task_idle(tctx)) {
+	do {
 		/* read completions before cancelations */
-		completions = atomic_long_read(&tctx->req_complete);
+		inflight = percpu_counter_sum(&tctx->inflight);
+		if (!inflight)
+			break;
 		__io_uring_files_cancel(NULL);
 
 		prepare_to_wait(&tctx->wait, &wait, TASK_UNINTERRUPTIBLE);
@@ -8726,12 +8734,10 @@ void __io_uring_task_cancel(void)
 		 * If we've seen completions, retry. This avoids a race where
 		 * a completion comes in before we did prepare_to_wait().
 		 */
-		if (completions != atomic_long_read(&tctx->req_complete))
+		if (inflight != percpu_counter_sum(&tctx->inflight))
 			continue;
-		if (io_uring_task_idle(tctx))
-			break;
 		schedule();
-	}
+	} while (1);
 
 	finish_wait(&tctx->wait, &wait);
 	tctx->in_idle = false;
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index 607d14f61132..28939820b6b0 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -23,13 +23,10 @@ struct io_uring_task {
 	struct xarray		xa;
 	struct wait_queue_head	wait;
 	struct file		*last;
-	atomic_long_t		req_issue;
+	struct percpu_counter	inflight;
 	struct io_identity	__identity;
 	struct io_identity	*identity;
-
-	/* completion side */
-	bool			in_idle ____cacheline_aligned_in_smp;
-	atomic_long_t		req_complete;
+	bool			in_idle;
 };
 
 #if defined(CONFIG_IO_URING)
-- 
cgit v1.2.3


From 4ea33a976bfe79293965d0815e1914e4b6e58967 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 15 Oct 2020 13:46:44 -0600
Subject: io-wq: inherit audit loginuid and sessionid

Make sure the async io-wq workers inherit the loginuid and sessionid from
the original task, and restore them to unset once we're done with the
async work item.

While at it, disable the ability for kernel threads to write to their own
loginuid.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io-wq.c               | 10 ++++++++++
 fs/io_uring.c            | 24 +++++++++++++++++++++++-
 fs/proc/base.c           |  4 ++++
 include/linux/io_uring.h |  4 ++++
 4 files changed, 41 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/fs/io-wq.c b/fs/io-wq.c
index 0c852b75384d..7cb3b4cb9b11 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -18,6 +18,7 @@
 #include <linux/fs_struct.h>
 #include <linux/task_work.h>
 #include <linux/blk-cgroup.h>
+#include <linux/audit.h>
 
 #include "io-wq.h"
 
@@ -484,6 +485,10 @@ static void io_impersonate_work(struct io_worker *worker,
 		io_wq_switch_creds(worker, work);
 	current->signal->rlim[RLIMIT_FSIZE].rlim_cur = work->identity->fsize;
 	io_wq_switch_blkcg(worker, work);
+#ifdef CONFIG_AUDIT
+	current->loginuid = work->identity->loginuid;
+	current->sessionid = work->identity->sessionid;
+#endif
 }
 
 static void io_assign_current_work(struct io_worker *worker,
@@ -496,6 +501,11 @@ static void io_assign_current_work(struct io_worker *worker,
 		cond_resched();
 	}
 
+#ifdef CONFIG_AUDIT
+	current->loginuid = KUIDT_INIT(AUDIT_UID_UNSET);
+	current->sessionid = AUDIT_SID_UNSET;
+#endif
+
 	spin_lock_irq(&worker->lock);
 	worker->cur_work = work;
 	spin_unlock_irq(&worker->lock);
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 58c445b95085..b9ffe98f18bc 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -81,6 +81,7 @@
 #include <linux/pagemap.h>
 #include <linux/io_uring.h>
 #include <linux/blk-cgroup.h>
+#include <linux/audit.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/io_uring.h>
@@ -327,6 +328,11 @@ struct io_ring_ctx {
 
 	const struct cred	*creds;
 
+#ifdef CONFIG_AUDIT
+	kuid_t			loginuid;
+	unsigned int		sessionid;
+#endif
+
 	struct completion	ref_comp;
 	struct completion	sq_thread_comp;
 
@@ -1057,6 +1063,10 @@ static void io_init_identity(struct io_identity *id)
 	id->nsproxy = current->nsproxy;
 	id->fs = current->fs;
 	id->fsize = rlimit(RLIMIT_FSIZE);
+#ifdef CONFIG_AUDIT
+	id->loginuid = current->loginuid;
+	id->sessionid = current->sessionid;
+#endif
 	refcount_set(&id->count, 1);
 }
 
@@ -1316,6 +1326,11 @@ static bool io_grab_identity(struct io_kiocb *req)
 		get_cred(id->creds);
 		req->work.flags |= IO_WQ_WORK_CREDS;
 	}
+#ifdef CONFIG_AUDIT
+	if (!uid_eq(current->loginuid, id->loginuid) ||
+	    current->sessionid != id->sessionid)
+		return false;
+#endif
 	if (!(req->work.flags & IO_WQ_WORK_FS) &&
 	    (def->work_flags & IO_WQ_WORK_FS)) {
 		if (current->fs != id->fs)
@@ -6755,6 +6770,10 @@ static int io_sq_thread(void *data)
 				old_cred = override_creds(ctx->creds);
 			}
 			io_sq_thread_associate_blkcg(ctx, &cur_css);
+#ifdef CONFIG_AUDIT
+			current->loginuid = ctx->loginuid;
+			current->sessionid = ctx->sessionid;
+#endif
 
 			ret |= __io_sq_thread(ctx, start_jiffies, cap_entries);
 
@@ -9203,7 +9222,10 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p,
 	ctx->compat = in_compat_syscall();
 	ctx->user = user;
 	ctx->creds = get_current_cred();
-
+#ifdef CONFIG_AUDIT
+	ctx->loginuid = current->loginuid;
+	ctx->sessionid = current->sessionid;
+#endif
 	ctx->sqo_task = get_task_struct(current);
 
 	/*
diff --git a/fs/proc/base.c b/fs/proc/base.c
index aa69c35d904c..0f707003dda5 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1268,6 +1268,10 @@ static ssize_t proc_loginuid_write(struct file * file, const char __user * buf,
 	kuid_t kloginuid;
 	int rv;
 
+	/* Don't let kthreads write their own loginuid */
+	if (current->flags & PF_KTHREAD)
+		return -EPERM;
+
 	rcu_read_lock();
 	if (current != pid_task(proc_pid(inode), PIDTYPE_PID)) {
 		rcu_read_unlock();
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index 28939820b6b0..868364cea3b7 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -15,6 +15,10 @@ struct io_identity {
 	struct nsproxy			*nsproxy;
 	struct fs_struct		*fs;
 	unsigned long			fsize;
+#ifdef CONFIG_AUDIT
+	kuid_t				loginuid;
+	unsigned int			sessionid;
+#endif
 	refcount_t			count;
 };
 
-- 
cgit v1.2.3


From 3c532798ec96b6c2d77706f04ed1d8b566a805df Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Sat, 3 Oct 2020 10:49:22 -0600
Subject: tracehook: clear TIF_NOTIFY_RESUME in tracehook_notify_resume()

All the callers currently do this, clean it up and move the clearing
into tracehook_notify_resume() instead.

Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 arch/alpha/kernel/signal.c      | 1 -
 arch/arc/kernel/signal.c        | 2 +-
 arch/arm/kernel/signal.c        | 1 -
 arch/arm64/kernel/signal.c      | 1 -
 arch/c6x/kernel/signal.c        | 4 +---
 arch/csky/kernel/signal.c       | 1 -
 arch/h8300/kernel/signal.c      | 4 +---
 arch/hexagon/kernel/process.c   | 1 -
 arch/ia64/kernel/process.c      | 2 +-
 arch/m68k/kernel/signal.c       | 2 +-
 arch/microblaze/kernel/signal.c | 2 +-
 arch/mips/kernel/signal.c       | 1 -
 arch/nds32/kernel/signal.c      | 4 +---
 arch/nios2/kernel/signal.c      | 2 +-
 arch/openrisc/kernel/signal.c   | 1 -
 arch/parisc/kernel/signal.c     | 4 +---
 arch/powerpc/kernel/signal.c    | 1 -
 arch/riscv/kernel/signal.c      | 4 +---
 arch/s390/kernel/signal.c       | 1 -
 arch/sh/kernel/signal_32.c      | 4 +---
 arch/sparc/kernel/signal_32.c   | 4 +---
 arch/sparc/kernel/signal_64.c   | 4 +---
 arch/um/kernel/process.c        | 2 +-
 arch/xtensa/kernel/signal.c     | 2 +-
 include/linux/tracehook.h       | 4 ++--
 kernel/entry/common.c           | 1 -
 kernel/entry/kvm.c              | 4 +---
 27 files changed, 18 insertions(+), 46 deletions(-)

(limited to 'include/linux')

diff --git a/arch/alpha/kernel/signal.c b/arch/alpha/kernel/signal.c
index 15bc9d1e79f4..3739efce1ec0 100644
--- a/arch/alpha/kernel/signal.c
+++ b/arch/alpha/kernel/signal.c
@@ -531,7 +531,6 @@ do_work_pending(struct pt_regs *regs, unsigned long thread_flags,
 				do_signal(regs, r0, r19);
 				r0 = 0;
 			} else {
-				clear_thread_flag(TIF_NOTIFY_RESUME);
 				tracehook_notify_resume(regs);
 			}
 		}
diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c
index 8222f8c54690..2be55fb96d87 100644
--- a/arch/arc/kernel/signal.c
+++ b/arch/arc/kernel/signal.c
@@ -394,6 +394,6 @@ void do_notify_resume(struct pt_regs *regs)
 	 * ASM glue gaurantees that this is only called when returning to
 	 * user mode
 	 */
-	if (test_and_clear_thread_flag(TIF_NOTIFY_RESUME))
+	if (test_thread_flag(TIF_NOTIFY_RESUME))
 		tracehook_notify_resume(regs);
 }
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index c1892f733f20..585edbfccf6d 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -669,7 +669,6 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
 			} else if (thread_flags & _TIF_UPROBE) {
 				uprobe_notify_resume(regs);
 			} else {
-				clear_thread_flag(TIF_NOTIFY_RESUME);
 				tracehook_notify_resume(regs);
 				rseq_handle_notify_resume(NULL, regs);
 			}
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index bdcaaf091e1e..a8184cad8890 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -946,7 +946,6 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
 				do_signal(regs);
 
 			if (thread_flags & _TIF_NOTIFY_RESUME) {
-				clear_thread_flag(TIF_NOTIFY_RESUME);
 				tracehook_notify_resume(regs);
 				rseq_handle_notify_resume(NULL, regs);
 			}
diff --git a/arch/c6x/kernel/signal.c b/arch/c6x/kernel/signal.c
index d05c78eace1b..a3f15b9a79da 100644
--- a/arch/c6x/kernel/signal.c
+++ b/arch/c6x/kernel/signal.c
@@ -316,8 +316,6 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, u32 thread_info_flags,
 	if (thread_info_flags & (1 << TIF_SIGPENDING))
 		do_signal(regs, syscall);
 
-	if (thread_info_flags & (1 << TIF_NOTIFY_RESUME)) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
+	if (thread_info_flags & (1 << TIF_NOTIFY_RESUME))
 		tracehook_notify_resume(regs);
-	}
 }
diff --git a/arch/csky/kernel/signal.c b/arch/csky/kernel/signal.c
index 970895df75ec..8b068cf37447 100644
--- a/arch/csky/kernel/signal.c
+++ b/arch/csky/kernel/signal.c
@@ -261,7 +261,6 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
 		do_signal(regs);
 
 	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
 		tracehook_notify_resume(regs);
 		rseq_handle_notify_resume(NULL, regs);
 	}
diff --git a/arch/h8300/kernel/signal.c b/arch/h8300/kernel/signal.c
index 69e68949787f..75d9b7e626b2 100644
--- a/arch/h8300/kernel/signal.c
+++ b/arch/h8300/kernel/signal.c
@@ -282,8 +282,6 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, u32 thread_info_flags)
 	if (thread_info_flags & _TIF_SIGPENDING)
 		do_signal(regs);
 
-	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
+	if (thread_info_flags & _TIF_NOTIFY_RESUME)
 		tracehook_notify_resume(regs);
-	}
 }
diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c
index dfd322c5ce83..5a0a95d93ddb 100644
--- a/arch/hexagon/kernel/process.c
+++ b/arch/hexagon/kernel/process.c
@@ -180,7 +180,6 @@ int do_work_pending(struct pt_regs *regs, u32 thread_info_flags)
 	}
 
 	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
 		tracehook_notify_resume(regs);
 		return 1;
 	}
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index f25f2f723196..6b61a703bcf5 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -176,7 +176,7 @@ do_notify_resume_user(sigset_t *unused, struct sigscratch *scr, long in_syscall)
 		ia64_do_signal(scr, in_syscall);
 	}
 
-	if (test_and_clear_thread_flag(TIF_NOTIFY_RESUME)) {
+	if (test_thread_flag(TIF_NOTIFY_RESUME)) {
 		local_irq_enable();	/* force interrupt enable */
 		tracehook_notify_resume(&scr->pt);
 	}
diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c
index a98fca977073..29e174a80bf6 100644
--- a/arch/m68k/kernel/signal.c
+++ b/arch/m68k/kernel/signal.c
@@ -1134,6 +1134,6 @@ void do_notify_resume(struct pt_regs *regs)
 	if (test_thread_flag(TIF_SIGPENDING))
 		do_signal(regs);
 
-	if (test_and_clear_thread_flag(TIF_NOTIFY_RESUME))
+	if (test_thread_flag(TIF_NOTIFY_RESUME))
 		tracehook_notify_resume(regs);
 }
diff --git a/arch/microblaze/kernel/signal.c b/arch/microblaze/kernel/signal.c
index 4a96b59f0bee..f11a0ccccabc 100644
--- a/arch/microblaze/kernel/signal.c
+++ b/arch/microblaze/kernel/signal.c
@@ -316,6 +316,6 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, int in_syscall)
 	if (test_thread_flag(TIF_SIGPENDING))
 		do_signal(regs, in_syscall);
 
-	if (test_and_clear_thread_flag(TIF_NOTIFY_RESUME))
+	if (test_thread_flag(TIF_NOTIFY_RESUME))
 		tracehook_notify_resume(regs);
 }
diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c
index f44265025281..50d0515bea21 100644
--- a/arch/mips/kernel/signal.c
+++ b/arch/mips/kernel/signal.c
@@ -907,7 +907,6 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, void *unused,
 		do_signal(regs);
 
 	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
 		tracehook_notify_resume(regs);
 		rseq_handle_notify_resume(NULL, regs);
 	}
diff --git a/arch/nds32/kernel/signal.c b/arch/nds32/kernel/signal.c
index 36e25a410bb0..2acb94812af9 100644
--- a/arch/nds32/kernel/signal.c
+++ b/arch/nds32/kernel/signal.c
@@ -379,8 +379,6 @@ do_notify_resume(struct pt_regs *regs, unsigned int thread_flags)
 	if (thread_flags & _TIF_SIGPENDING)
 		do_signal(regs);
 
-	if (thread_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
+	if (thread_flags & _TIF_NOTIFY_RESUME)
 		tracehook_notify_resume(regs);
-	}
 }
diff --git a/arch/nios2/kernel/signal.c b/arch/nios2/kernel/signal.c
index d8a087cf2b42..cf2dca2ac7c3 100644
--- a/arch/nios2/kernel/signal.c
+++ b/arch/nios2/kernel/signal.c
@@ -317,7 +317,7 @@ asmlinkage int do_notify_resume(struct pt_regs *regs)
 			 */
 			return restart;
 		}
-	} else if (test_and_clear_thread_flag(TIF_NOTIFY_RESUME))
+	} else if (test_thread_flag(TIF_NOTIFY_RESUME))
 		tracehook_notify_resume(regs);
 
 	return 0;
diff --git a/arch/openrisc/kernel/signal.c b/arch/openrisc/kernel/signal.c
index c779364f0cd0..af66f968dd45 100644
--- a/arch/openrisc/kernel/signal.c
+++ b/arch/openrisc/kernel/signal.c
@@ -311,7 +311,6 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
 				}
 				syscall = 0;
 			} else {
-				clear_thread_flag(TIF_NOTIFY_RESUME);
 				tracehook_notify_resume(regs);
 			}
 		}
diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c
index 3c037fc96038..9f43eaeb0b0a 100644
--- a/arch/parisc/kernel/signal.c
+++ b/arch/parisc/kernel/signal.c
@@ -606,8 +606,6 @@ void do_notify_resume(struct pt_regs *regs, long in_syscall)
 	if (test_thread_flag(TIF_SIGPENDING))
 		do_signal(regs, in_syscall);
 
-	if (test_thread_flag(TIF_NOTIFY_RESUME)) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
+	if (test_thread_flag(TIF_NOTIFY_RESUME))
 		tracehook_notify_resume(regs);
-	}
 }
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index d15a98c758b8..74a94a125f0d 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -327,7 +327,6 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags)
 	}
 
 	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
 		tracehook_notify_resume(regs);
 		rseq_handle_notify_resume(NULL, regs);
 	}
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index e996e08f1061..bc6841867b51 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -313,8 +313,6 @@ asmlinkage __visible void do_notify_resume(struct pt_regs *regs,
 	if (thread_info_flags & _TIF_SIGPENDING)
 		do_signal(regs);
 
-	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
+	if (thread_info_flags & _TIF_NOTIFY_RESUME)
 		tracehook_notify_resume(regs);
-	}
 }
diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c
index b295090e2ce6..9e900a8977bd 100644
--- a/arch/s390/kernel/signal.c
+++ b/arch/s390/kernel/signal.c
@@ -535,7 +535,6 @@ void do_signal(struct pt_regs *regs)
 
 void do_notify_resume(struct pt_regs *regs)
 {
-	clear_thread_flag(TIF_NOTIFY_RESUME);
 	tracehook_notify_resume(regs);
 	rseq_handle_notify_resume(NULL, regs);
 }
diff --git a/arch/sh/kernel/signal_32.c b/arch/sh/kernel/signal_32.c
index 4fe3f00137bc..1add47fd31f6 100644
--- a/arch/sh/kernel/signal_32.c
+++ b/arch/sh/kernel/signal_32.c
@@ -502,8 +502,6 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, unsigned int save_r0,
 	if (thread_info_flags & _TIF_SIGPENDING)
 		do_signal(regs, save_r0);
 
-	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
+	if (thread_info_flags & _TIF_NOTIFY_RESUME)
 		tracehook_notify_resume(regs);
-	}
 }
diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c
index d0e0025ee3ba..741d0701003a 100644
--- a/arch/sparc/kernel/signal_32.c
+++ b/arch/sparc/kernel/signal_32.c
@@ -523,10 +523,8 @@ void do_notify_resume(struct pt_regs *regs, unsigned long orig_i0,
 {
 	if (thread_info_flags & _TIF_SIGPENDING)
 		do_signal(regs, orig_i0);
-	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
+	if (thread_info_flags & _TIF_NOTIFY_RESUME)
 		tracehook_notify_resume(regs);
-	}
 }
 
 asmlinkage int do_sys_sigstack(struct sigstack __user *ssptr,
diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c
index 255264bcb46a..f7ef7edcd5c1 100644
--- a/arch/sparc/kernel/signal_64.c
+++ b/arch/sparc/kernel/signal_64.c
@@ -551,10 +551,8 @@ void do_notify_resume(struct pt_regs *regs, unsigned long orig_i0, unsigned long
 		uprobe_notify_resume(regs);
 	if (thread_info_flags & _TIF_SIGPENDING)
 		do_signal(regs, orig_i0);
-	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
+	if (thread_info_flags & _TIF_NOTIFY_RESUME)
 		tracehook_notify_resume(regs);
-	}
 	user_enter();
 }
 
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index 26b5e243d3fc..3bed09538dd9 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -101,7 +101,7 @@ void interrupt_end(void)
 		schedule();
 	if (test_thread_flag(TIF_SIGPENDING))
 		do_signal(regs);
-	if (test_and_clear_thread_flag(TIF_NOTIFY_RESUME))
+	if (test_thread_flag(TIF_NOTIFY_RESUME))
 		tracehook_notify_resume(regs);
 }
 
diff --git a/arch/xtensa/kernel/signal.c b/arch/xtensa/kernel/signal.c
index b3b17d6c50f0..1fb1047f905c 100644
--- a/arch/xtensa/kernel/signal.c
+++ b/arch/xtensa/kernel/signal.c
@@ -501,6 +501,6 @@ void do_notify_resume(struct pt_regs *regs)
 	if (test_thread_flag(TIF_SIGPENDING))
 		do_signal(regs);
 
-	if (test_and_clear_thread_flag(TIF_NOTIFY_RESUME))
+	if (test_thread_flag(TIF_NOTIFY_RESUME))
 		tracehook_notify_resume(regs);
 }
diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h
index 36fb3bbed6b2..b480e1a07ed8 100644
--- a/include/linux/tracehook.h
+++ b/include/linux/tracehook.h
@@ -178,9 +178,9 @@ static inline void set_notify_resume(struct task_struct *task)
  */
 static inline void tracehook_notify_resume(struct pt_regs *regs)
 {
+	clear_thread_flag(TIF_NOTIFY_RESUME);
 	/*
-	 * The caller just cleared TIF_NOTIFY_RESUME. This barrier
-	 * pairs with task_work_add()->set_notify_resume() after
+	 * This barrier pairs with task_work_add()->set_notify_resume() after
 	 * hlist_add_head(task->task_works);
 	 */
 	smp_mb__after_atomic();
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 145ab11b8318..971ef788b9ae 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -161,7 +161,6 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
 			arch_do_signal(regs);
 
 		if (ti_work & _TIF_NOTIFY_RESUME) {
-			clear_thread_flag(TIF_NOTIFY_RESUME);
 			tracehook_notify_resume(regs);
 			rseq_handle_notify_resume(NULL, regs);
 		}
diff --git a/kernel/entry/kvm.c b/kernel/entry/kvm.c
index eb1a8a4c867c..b6678a5e3cf6 100644
--- a/kernel/entry/kvm.c
+++ b/kernel/entry/kvm.c
@@ -16,10 +16,8 @@ static int xfer_to_guest_mode_work(struct kvm_vcpu *vcpu, unsigned long ti_work)
 		if (ti_work & _TIF_NEED_RESCHED)
 			schedule();
 
-		if (ti_work & _TIF_NOTIFY_RESUME) {
-			clear_thread_flag(TIF_NOTIFY_RESUME);
+		if (ti_work & _TIF_NOTIFY_RESUME)
 			tracehook_notify_resume(NULL);
-		}
 
 		ret = arch_xfer_to_guest_mode_handle_work(vcpu, ti_work);
 		if (ret)
-- 
cgit v1.2.3


From 91989c707884ecc7cd537281ab1a4b8fb7219da3 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Fri, 16 Oct 2020 09:02:26 -0600
Subject: task_work: cleanup notification modes

A previous commit changed the notification mode from true/false to an
int, allowing notify-no, notify-yes, or signal-notify. This was
backwards compatible in the sense that any existing true/false user
would translate to either 0 (on notification sent) or 1, the latter
which mapped to TWA_RESUME. TWA_SIGNAL was assigned a value of 2.

Clean this up properly, and define a proper enum for the notification
mode. Now we have:

- TWA_NONE. This is 0, same as before the original change, meaning no
  notification requested.
- TWA_RESUME. This is 1, same as before the original change, meaning
  that we use TIF_NOTIFY_RESUME.
- TWA_SIGNAL. This uses TIF_SIGPENDING/JOBCTL_TASK_WORK for the
  notification.

Clean up all the callers, switching their 0/1/false/true to using the
appropriate TWA_* mode for notifications.

Fixes: e91b48162332 ("task_work: teach task_work_add() to do signal_wake_up()")
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 arch/x86/kernel/cpu/mce/core.c         |  2 +-
 arch/x86/kernel/cpu/resctrl/rdtgroup.c |  2 +-
 drivers/acpi/apei/ghes.c               |  2 +-
 drivers/android/binder.c               |  2 +-
 fs/file_table.c                        |  2 +-
 fs/io_uring.c                          | 13 +++++++------
 fs/namespace.c                         |  2 +-
 include/linux/task_work.h              | 11 ++++++++---
 kernel/events/uprobes.c                |  2 +-
 kernel/irq/manage.c                    |  2 +-
 kernel/sched/fair.c                    |  2 +-
 kernel/task_work.c                     | 30 ++++++++++++++++++++----------
 security/keys/keyctl.c                 |  2 +-
 security/yama/yama_lsm.c               |  2 +-
 14 files changed, 46 insertions(+), 30 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 1c08cb9eb9f6..4102b866e7c0 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1277,7 +1277,7 @@ static void queue_task_work(struct mce *m, int kill_it)
 	else
 		current->mce_kill_me.func = kill_me_maybe;
 
-	task_work_add(current, &current->mce_kill_me, true);
+	task_work_add(current, &current->mce_kill_me, TWA_RESUME);
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index b494187632b2..af323e2e3100 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -561,7 +561,7 @@ static int __rdtgroup_move_task(struct task_struct *tsk,
 	 * callback has been invoked.
 	 */
 	atomic_inc(&rdtgrp->waitcount);
-	ret = task_work_add(tsk, &callback->work, true);
+	ret = task_work_add(tsk, &callback->work, TWA_RESUME);
 	if (ret) {
 		/*
 		 * Task is exiting. Drop the refcount and free the callback.
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 81bf71b10d44..8360f8d6be65 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -879,7 +879,7 @@ static void ghes_proc_in_irq(struct irq_work *irq_work)
 			estatus_node->task_work.func = ghes_kick_task_work;
 			estatus_node->task_work_cpu = smp_processor_id();
 			ret = task_work_add(current, &estatus_node->task_work,
-					    true);
+					    TWA_RESUME);
 			if (ret)
 				estatus_node->task_work.func = NULL;
 		}
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 4b9476521da6..b5117576792b 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -2229,7 +2229,7 @@ static void binder_deferred_fd_close(int fd)
 	__close_fd_get_file(fd, &twcb->file);
 	if (twcb->file) {
 		filp_close(twcb->file, current->files);
-		task_work_add(current, &twcb->twork, true);
+		task_work_add(current, &twcb->twork, TWA_RESUME);
 	} else {
 		kfree(twcb);
 	}
diff --git a/fs/file_table.c b/fs/file_table.c
index 656647f9575a..709ada3151da 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -339,7 +339,7 @@ void fput_many(struct file *file, unsigned int refs)
 
 		if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) {
 			init_task_work(&file->f_u.fu_rcuhead, ____fput);
-			if (!task_work_add(task, &file->f_u.fu_rcuhead, true))
+			if (!task_work_add(task, &file->f_u.fu_rcuhead, TWA_RESUME))
 				return;
 			/*
 			 * After this task has run exit_task_work(),
diff --git a/fs/io_uring.c b/fs/io_uring.c
index e1726f457461..6b502885684a 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1976,7 +1976,8 @@ static int io_req_task_work_add(struct io_kiocb *req, bool twa_signal_ok)
 {
 	struct task_struct *tsk = req->task;
 	struct io_ring_ctx *ctx = req->ctx;
-	int ret, notify;
+	enum task_work_notify_mode notify;
+	int ret;
 
 	if (tsk->flags & PF_EXITING)
 		return -ESRCH;
@@ -1987,7 +1988,7 @@ static int io_req_task_work_add(struct io_kiocb *req, bool twa_signal_ok)
 	 * processing task_work. There's no reliable way to tell if TWA_RESUME
 	 * will do the job.
 	 */
-	notify = 0;
+	notify = TWA_NONE;
 	if (!(ctx->flags & IORING_SETUP_SQPOLL) && twa_signal_ok)
 		notify = TWA_SIGNAL;
 
@@ -2056,7 +2057,7 @@ static void io_req_task_queue(struct io_kiocb *req)
 
 		init_task_work(&req->task_work, io_req_task_cancel);
 		tsk = io_wq_get_task(req->ctx->io_wq);
-		task_work_add(tsk, &req->task_work, 0);
+		task_work_add(tsk, &req->task_work, TWA_NONE);
 		wake_up_process(tsk);
 	}
 }
@@ -2177,7 +2178,7 @@ static void io_free_req_deferred(struct io_kiocb *req)
 		struct task_struct *tsk;
 
 		tsk = io_wq_get_task(req->ctx->io_wq);
-		task_work_add(tsk, &req->task_work, 0);
+		task_work_add(tsk, &req->task_work, TWA_NONE);
 		wake_up_process(tsk);
 	}
 }
@@ -3291,7 +3292,7 @@ static int io_async_buf_func(struct wait_queue_entry *wait, unsigned mode,
 		/* queue just for cancelation */
 		init_task_work(&req->task_work, io_req_task_cancel);
 		tsk = io_wq_get_task(req->ctx->io_wq);
-		task_work_add(tsk, &req->task_work, 0);
+		task_work_add(tsk, &req->task_work, TWA_NONE);
 		wake_up_process(tsk);
 	}
 	return 1;
@@ -4857,7 +4858,7 @@ static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll,
 
 		WRITE_ONCE(poll->canceled, true);
 		tsk = io_wq_get_task(req->ctx->io_wq);
-		task_work_add(tsk, &req->task_work, 0);
+		task_work_add(tsk, &req->task_work, TWA_NONE);
 		wake_up_process(tsk);
 	}
 	return 1;
diff --git a/fs/namespace.c b/fs/namespace.c
index 294e05a13d17..1a75336668a3 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1191,7 +1191,7 @@ static void mntput_no_expire(struct mount *mnt)
 		struct task_struct *task = current;
 		if (likely(!(task->flags & PF_KTHREAD))) {
 			init_task_work(&mnt->mnt_rcu, __cleanup_mnt);
-			if (!task_work_add(task, &mnt->mnt_rcu, true))
+			if (!task_work_add(task, &mnt->mnt_rcu, TWA_RESUME))
 				return;
 		}
 		if (llist_add(&mnt->mnt_llist, &delayed_mntput_list))
diff --git a/include/linux/task_work.h b/include/linux/task_work.h
index 0fb93aafa478..0d848a1e9e62 100644
--- a/include/linux/task_work.h
+++ b/include/linux/task_work.h
@@ -13,9 +13,14 @@ init_task_work(struct callback_head *twork, task_work_func_t func)
 	twork->func = func;
 }
 
-#define TWA_RESUME	1
-#define TWA_SIGNAL	2
-int task_work_add(struct task_struct *task, struct callback_head *twork, int);
+enum task_work_notify_mode {
+	TWA_NONE,
+	TWA_RESUME,
+	TWA_SIGNAL,
+};
+
+int task_work_add(struct task_struct *task, struct callback_head *twork,
+			enum task_work_notify_mode mode);
 
 struct callback_head *task_work_cancel(struct task_struct *, task_work_func_t);
 void task_work_run(void);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 0e18aaf23a7b..00b0358739ab 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1823,7 +1823,7 @@ void uprobe_copy_process(struct task_struct *t, unsigned long flags)
 
 	t->utask->dup_xol_addr = area->vaddr;
 	init_task_work(&t->utask->dup_xol_work, dup_xol_work);
-	task_work_add(t, &t->utask->dup_xol_work, true);
+	task_work_add(t, &t->utask->dup_xol_work, TWA_RESUME);
 }
 
 /*
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 5df903fccb60..c460e0496006 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1162,7 +1162,7 @@ static int irq_thread(void *data)
 		handler_fn = irq_thread_fn;
 
 	init_task_work(&on_exit_work, irq_thread_dtor);
-	task_work_add(current, &on_exit_work, false);
+	task_work_add(current, &on_exit_work, TWA_NONE);
 
 	irq_thread_check_affinity(desc, action);
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index aa4c6227cd6d..e17012be4d14 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2928,7 +2928,7 @@ static void task_tick_numa(struct rq *rq, struct task_struct *curr)
 		curr->node_stamp += period;
 
 		if (!time_before(jiffies, curr->mm->numa_next_scan))
-			task_work_add(curr, work, true);
+			task_work_add(curr, work, TWA_RESUME);
 	}
 }
 
diff --git a/kernel/task_work.c b/kernel/task_work.c
index 613b2d634af8..8d6e1217c451 100644
--- a/kernel/task_work.c
+++ b/kernel/task_work.c
@@ -9,23 +9,28 @@ static struct callback_head work_exited; /* all we need is ->next == NULL */
  * task_work_add - ask the @task to execute @work->func()
  * @task: the task which should run the callback
  * @work: the callback to run
- * @notify: send the notification if true
+ * @notify: how to notify the targeted task
  *
- * Queue @work for task_work_run() below and notify the @task if @notify.
- * Fails if the @task is exiting/exited and thus it can't process this @work.
- * Otherwise @work->func() will be called when the @task returns from kernel
- * mode or exits.
+ * Queue @work for task_work_run() below and notify the @task if @notify
+ * is @TWA_RESUME or @TWA_SIGNAL. @TWA_SIGNAL works like signals, in that the
+ * it will interrupt the targeted task and run the task_work. @TWA_RESUME
+ * work is run only when the task exits the kernel and returns to user mode,
+ * or before entering guest mode. Fails if the @task is exiting/exited and thus
+ * it can't process this @work. Otherwise @work->func() will be called when the
+ * @task goes through one of the aforementioned transitions, or exits.
  *
- * This is like the signal handler which runs in kernel mode, but it doesn't
- * try to wake up the @task.
+ * If the targeted task is exiting, then an error is returned and the work item
+ * is not queued. It's up to the caller to arrange for an alternative mechanism
+ * in that case.
  *
- * Note: there is no ordering guarantee on works queued here.
+ * Note: there is no ordering guarantee on works queued here. The task_work
+ * list is LIFO.
  *
  * RETURNS:
  * 0 if succeeds or -ESRCH.
  */
-int
-task_work_add(struct task_struct *task, struct callback_head *work, int notify)
+int task_work_add(struct task_struct *task, struct callback_head *work,
+		  enum task_work_notify_mode notify)
 {
 	struct callback_head *head;
 	unsigned long flags;
@@ -38,6 +43,8 @@ task_work_add(struct task_struct *task, struct callback_head *work, int notify)
 	} while (cmpxchg(&task->task_works, head, work) != head);
 
 	switch (notify) {
+	case TWA_NONE:
+		break;
 	case TWA_RESUME:
 		set_notify_resume(task);
 		break;
@@ -54,6 +61,9 @@ task_work_add(struct task_struct *task, struct callback_head *work, int notify)
 			unlock_task_sighand(task, &flags);
 		}
 		break;
+	default:
+		WARN_ON_ONCE(1);
+		break;
 	}
 
 	return 0;
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
index e26bbccda7cc..61a614c21b9b 100644
--- a/security/keys/keyctl.c
+++ b/security/keys/keyctl.c
@@ -1693,7 +1693,7 @@ long keyctl_session_to_parent(void)
 
 	/* the replacement session keyring is applied just prior to userspace
 	 * restarting */
-	ret = task_work_add(parent, newwork, true);
+	ret = task_work_add(parent, newwork, TWA_RESUME);
 	if (!ret)
 		newwork = NULL;
 unlock:
diff --git a/security/yama/yama_lsm.c b/security/yama/yama_lsm.c
index 536c99646f6a..06e226166aab 100644
--- a/security/yama/yama_lsm.c
+++ b/security/yama/yama_lsm.c
@@ -99,7 +99,7 @@ static void report_access(const char *access, struct task_struct *target,
 	info->access = access;
 	info->target = target;
 	info->agent = agent;
-	if (task_work_add(current, &info->work, true) == 0)
+	if (task_work_add(current, &info->work, TWA_RESUME) == 0)
 		return; /* success */
 
 	WARN(1, "report_access called from exiting task");
-- 
cgit v1.2.3


From 15a119e09344a346384ec05c781c126a29b18235 Mon Sep 17 00:00:00 2001
From: Hui Su <sh_def@163.com>
Date: Wed, 23 Sep 2020 01:12:31 +0800
Subject: jbd2: fix the comment of struct jbd2_journal_handle

the struct name was modified long ago, but the comment still
use struct handle_s.

Signed-off-by: Hui Su <sh_def@163.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20200922171231.GA53120@rlk
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 include/linux/jbd2.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 08f904943ab2..a1ef05412acf 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -452,8 +452,8 @@ struct jbd2_inode {
 struct jbd2_revoke_table_s;
 
 /**
- * struct handle_s - The handle_s type is the concrete type associated with
- *     handle_t.
+ * struct jbd2_journal_handle - The jbd2_journal_handle type is the concrete
+ *     type associated with handle_t.
  * @h_transaction: Which compound transaction is this update a part of?
  * @h_journal: Which journal handle belongs to - used iff h_reserved set.
  * @h_rsv_handle: Handle reserved for finishing the logical operation.
-- 
cgit v1.2.3


From aa3c0c61f62d682259e3e66cdc01846290f9cd6c Mon Sep 17 00:00:00 2001
From: Mauricio Faria de Oliveira <mfo@canonical.com>
Date: Mon, 5 Oct 2020 21:48:38 -0300
Subject: jbd2: introduce/export functions
 jbd2_journal_submit|finish_inode_data_buffers()

Export functions that implement the current behavior done
for an inode in journal_submit|finish_inode_data_buffers().

No functional change.

Signed-off-by: Mauricio Faria de Oliveira <mfo@canonical.com>
Suggested-by: Jan Kara <jack@suse.cz>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Andreas Dilger <adilger@dilger.ca>
Link: https://lore.kernel.org/r/20201006004841.600488-2-mfo@canonical.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/jbd2/commit.c     | 36 ++++++++++++++++--------------------
 fs/jbd2/journal.c    |  2 ++
 include/linux/jbd2.h |  4 ++++
 3 files changed, 22 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 6d2da8ad0e6f..f79b86b4241f 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -187,19 +187,17 @@ static int journal_wait_on_commit_record(journal_t *journal,
  * use writepages() because with delayed allocation we may be doing
  * block allocation in writepages().
  */
-static int journal_submit_inode_data_buffers(struct address_space *mapping,
-		loff_t dirty_start, loff_t dirty_end)
+int jbd2_journal_submit_inode_data_buffers(struct jbd2_inode *jinode)
 {
-	int ret;
+	struct address_space *mapping = jinode->i_vfs_inode->i_mapping;
 	struct writeback_control wbc = {
 		.sync_mode =  WB_SYNC_ALL,
 		.nr_to_write = mapping->nrpages * 2,
-		.range_start = dirty_start,
-		.range_end = dirty_end,
+		.range_start = jinode->i_dirty_start,
+		.range_end = jinode->i_dirty_end,
 	};
 
-	ret = generic_writepages(mapping, &wbc);
-	return ret;
+	return generic_writepages(mapping, &wbc);
 }
 
 /*
@@ -215,16 +213,11 @@ static int journal_submit_data_buffers(journal_t *journal,
 {
 	struct jbd2_inode *jinode;
 	int err, ret = 0;
-	struct address_space *mapping;
 
 	spin_lock(&journal->j_list_lock);
 	list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) {
-		loff_t dirty_start = jinode->i_dirty_start;
-		loff_t dirty_end = jinode->i_dirty_end;
-
 		if (!(jinode->i_flags & JI_WRITE_DATA))
 			continue;
-		mapping = jinode->i_vfs_inode->i_mapping;
 		jinode->i_flags |= JI_COMMIT_RUNNING;
 		spin_unlock(&journal->j_list_lock);
 		/*
@@ -234,8 +227,7 @@ static int journal_submit_data_buffers(journal_t *journal,
 		 * only allocated blocks here.
 		 */
 		trace_jbd2_submit_inode_data(jinode->i_vfs_inode);
-		err = journal_submit_inode_data_buffers(mapping, dirty_start,
-				dirty_end);
+		err = jbd2_journal_submit_inode_data_buffers(jinode);
 		if (!ret)
 			ret = err;
 		spin_lock(&journal->j_list_lock);
@@ -248,6 +240,15 @@ static int journal_submit_data_buffers(journal_t *journal,
 	return ret;
 }
 
+int jbd2_journal_finish_inode_data_buffers(struct jbd2_inode *jinode)
+{
+	struct address_space *mapping = jinode->i_vfs_inode->i_mapping;
+
+	return filemap_fdatawait_range_keep_errors(mapping,
+						   jinode->i_dirty_start,
+						   jinode->i_dirty_end);
+}
+
 /*
  * Wait for data submitted for writeout, refile inodes to proper
  * transaction if needed.
@@ -262,16 +263,11 @@ static int journal_finish_inode_data_buffers(journal_t *journal,
 	/* For locking, see the comment in journal_submit_data_buffers() */
 	spin_lock(&journal->j_list_lock);
 	list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) {
-		loff_t dirty_start = jinode->i_dirty_start;
-		loff_t dirty_end = jinode->i_dirty_end;
-
 		if (!(jinode->i_flags & JI_WAIT_DATA))
 			continue;
 		jinode->i_flags |= JI_COMMIT_RUNNING;
 		spin_unlock(&journal->j_list_lock);
-		err = filemap_fdatawait_range_keep_errors(
-				jinode->i_vfs_inode->i_mapping, dirty_start,
-				dirty_end);
+		err = jbd2_journal_finish_inode_data_buffers(jinode);
 		if (!ret)
 			ret = err;
 		spin_lock(&journal->j_list_lock);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 17fdc482f554..c0600405e7a2 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -91,6 +91,8 @@ EXPORT_SYMBOL(jbd2_journal_try_to_free_buffers);
 EXPORT_SYMBOL(jbd2_journal_force_commit);
 EXPORT_SYMBOL(jbd2_journal_inode_ranged_write);
 EXPORT_SYMBOL(jbd2_journal_inode_ranged_wait);
+EXPORT_SYMBOL(jbd2_journal_submit_inode_data_buffers);
+EXPORT_SYMBOL(jbd2_journal_finish_inode_data_buffers);
 EXPORT_SYMBOL(jbd2_journal_init_jbd_inode);
 EXPORT_SYMBOL(jbd2_journal_release_jbd_inode);
 EXPORT_SYMBOL(jbd2_journal_begin_ordered_truncate);
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index a1ef05412acf..8b7b06066bc2 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1421,6 +1421,10 @@ extern int	   jbd2_journal_inode_ranged_write(handle_t *handle,
 extern int	   jbd2_journal_inode_ranged_wait(handle_t *handle,
 			struct jbd2_inode *inode, loff_t start_byte,
 			loff_t length);
+extern int	   jbd2_journal_submit_inode_data_buffers(
+			struct jbd2_inode *jinode);
+extern int	   jbd2_journal_finish_inode_data_buffers(
+			struct jbd2_inode *jinode);
 extern int	   jbd2_journal_begin_ordered_truncate(journal_t *journal,
 				struct jbd2_inode *inode, loff_t new_size);
 extern void	   jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode);
-- 
cgit v1.2.3


From 342af94ec6c02aa478fe2adcd41b950e154b03ba Mon Sep 17 00:00:00 2001
From: Mauricio Faria de Oliveira <mfo@canonical.com>
Date: Mon, 5 Oct 2020 21:48:39 -0300
Subject: jbd2, ext4, ocfs2: introduce/use journal callbacks
 j_submit|finish_inode_data_buffers()

Introduce journal callbacks to allow different behaviors
for an inode in journal_submit|finish_inode_data_buffers().

The existing users of the current behavior (ext4, ocfs2)
are adapted to use the previously exported functions
that implement the current behavior.

Users are callers of jbd2_journal_inode_ranged_write|wait(),
which adds the inode to the transaction's inode list with
the JI_WRITE|WAIT_DATA flags. Only ext4 and ocfs2 in-tree.

Both CONFIG_EXT4_FS and CONFIG_OCSFS2_FS select CONFIG_JBD2,
which builds fs/jbd2/commit.c and journal.c that define and
export the functions, so we can call directly in ext4/ocfs2.

Signed-off-by: Mauricio Faria de Oliveira <mfo@canonical.com>
Suggested-by: Jan Kara <jack@suse.cz>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Andreas Dilger <adilger@dilger.ca>
Link: https://lore.kernel.org/r/20201006004841.600488-3-mfo@canonical.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/super.c      |  4 ++++
 fs/jbd2/commit.c     | 30 ++++++++++++++++++------------
 fs/ocfs2/journal.c   |  4 ++++
 include/linux/jbd2.h | 25 ++++++++++++++++++++++++-
 4 files changed, 50 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 0ee673e8e261..a3e57f554f1b 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -4752,6 +4752,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
 
 	sbi->s_journal->j_commit_callback = ext4_journal_commit_callback;
+	sbi->s_journal->j_submit_inode_data_buffers =
+		jbd2_journal_submit_inode_data_buffers;
+	sbi->s_journal->j_finish_inode_data_buffers =
+		jbd2_journal_finish_inode_data_buffers;
 
 no_journal:
 	if (!test_opt(sb, NO_MBCACHE)) {
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index f79b86b4241f..6252b4c50666 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -197,6 +197,12 @@ int jbd2_journal_submit_inode_data_buffers(struct jbd2_inode *jinode)
 		.range_end = jinode->i_dirty_end,
 	};
 
+	/*
+	 * submit the inode data buffers. We use writepage
+	 * instead of writepages. Because writepages can do
+	 * block allocation with delalloc. We need to write
+	 * only allocated blocks here.
+	 */
 	return generic_writepages(mapping, &wbc);
 }
 
@@ -220,16 +226,13 @@ static int journal_submit_data_buffers(journal_t *journal,
 			continue;
 		jinode->i_flags |= JI_COMMIT_RUNNING;
 		spin_unlock(&journal->j_list_lock);
-		/*
-		 * submit the inode data buffers. We use writepage
-		 * instead of writepages. Because writepages can do
-		 * block allocation  with delalloc. We need to write
-		 * only allocated blocks here.
-		 */
+		/* submit the inode data buffers. */
 		trace_jbd2_submit_inode_data(jinode->i_vfs_inode);
-		err = jbd2_journal_submit_inode_data_buffers(jinode);
-		if (!ret)
-			ret = err;
+		if (journal->j_submit_inode_data_buffers) {
+			err = journal->j_submit_inode_data_buffers(jinode);
+			if (!ret)
+				ret = err;
+		}
 		spin_lock(&journal->j_list_lock);
 		J_ASSERT(jinode->i_transaction == commit_transaction);
 		jinode->i_flags &= ~JI_COMMIT_RUNNING;
@@ -267,9 +270,12 @@ static int journal_finish_inode_data_buffers(journal_t *journal,
 			continue;
 		jinode->i_flags |= JI_COMMIT_RUNNING;
 		spin_unlock(&journal->j_list_lock);
-		err = jbd2_journal_finish_inode_data_buffers(jinode);
-		if (!ret)
-			ret = err;
+		/* wait for the inode data buffers writeout. */
+		if (journal->j_finish_inode_data_buffers) {
+			err = journal->j_finish_inode_data_buffers(jinode);
+			if (!ret)
+				ret = err;
+		}
 		spin_lock(&journal->j_list_lock);
 		jinode->i_flags &= ~JI_COMMIT_RUNNING;
 		smp_mb();
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index b425f0b01dce..b9a9d69dde7e 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -883,6 +883,10 @@ int ocfs2_journal_init(struct ocfs2_journal *journal, int *dirty)
 		  OCFS2_JOURNAL_DIRTY_FL);
 
 	journal->j_journal = j_journal;
+	journal->j_journal->j_submit_inode_data_buffers =
+		jbd2_journal_submit_inode_data_buffers;
+	journal->j_journal->j_finish_inode_data_buffers =
+		jbd2_journal_finish_inode_data_buffers;
 	journal->j_inode = inode;
 	journal->j_bh = bh;
 
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 8b7b06066bc2..04afa6dcd60d 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -629,7 +629,9 @@ struct transaction_s
 	struct journal_head	*t_shadow_list;
 
 	/*
-	 * List of inodes whose data we've modified in data=ordered mode.
+	 * List of inodes associated with the transaction; e.g., ext4 uses
+	 * this to track inodes in data=ordered and data=journal mode that
+	 * need special handling on transaction commit; also used by ocfs2.
 	 * [j_list_lock]
 	 */
 	struct list_head	t_inode_list;
@@ -1111,6 +1113,27 @@ struct journal_s
 	void			(*j_commit_callback)(journal_t *,
 						     transaction_t *);
 
+	/**
+	 * @j_submit_inode_data_buffers:
+	 *
+	 * This function is called for all inodes associated with the
+	 * committing transaction marked with JI_WRITE_DATA flag
+	 * before we start to write out the transaction to the journal.
+	 */
+	int			(*j_submit_inode_data_buffers)
+					(struct jbd2_inode *);
+
+	/**
+	 * @j_finish_inode_data_buffers:
+	 *
+	 * This function is called for all inodes associated with the
+	 * committing transaction marked with JI_WAIT_DATA flag
+	 * after we have written the transaction to the journal
+	 * but before we write out the commit block.
+	 */
+	int			(*j_finish_inode_data_buffers)
+					(struct jbd2_inode *);
+
 	/*
 	 * Journal statistics
 	 */
-- 
cgit v1.2.3


From b87d8cefe43c7f22e8aa13919c1dfa2b4b4b4e01 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Sat, 17 Oct 2020 16:13:40 -0700
Subject: mm, memcg: rework remote charging API to support nesting

Currently the remote memcg charging API consists of two functions:
memalloc_use_memcg() and memalloc_unuse_memcg(), which set and clear the
memcg value, which overwrites the memcg of the current task.

  memalloc_use_memcg(target_memcg);
  <...>
  memalloc_unuse_memcg();

It works perfectly for allocations performed from a normal context,
however an attempt to call it from an interrupt context or just nest two
remote charging blocks will lead to an incorrect accounting.  On exit from
the inner block the active memcg will be cleared instead of being
restored.

  memalloc_use_memcg(target_memcg);

  memalloc_use_memcg(target_memcg_2);
    <...>
    memalloc_unuse_memcg();

    Error: allocation here are charged to the memcg of the current
    process instead of target_memcg.

  memalloc_unuse_memcg();

This patch extends the remote charging API by switching to a single
function: struct mem_cgroup *set_active_memcg(struct mem_cgroup *memcg),
which sets the new value and returns the old one.  So a remote charging
block will look like:

  old_memcg = set_active_memcg(target_memcg);
  <...>
  set_active_memcg(old_memcg);

This patch is heavily based on the patch by Johannes Weiner, which can be
found here: https://lkml.org/lkml/2020/5/28/806 .

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Dan Schatzberg <dschatzberg@fb.com>
Link: https://lkml.kernel.org/r/20200821212056.3769116-1-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/buffer.c                          |  6 +++---
 fs/notify/fanotify/fanotify.c        |  5 +++--
 fs/notify/inotify/inotify_fsnotify.c |  5 +++--
 include/linux/sched/mm.h             | 30 ++++++++++--------------------
 mm/memcontrol.c                      |  6 +++---
 5 files changed, 22 insertions(+), 30 deletions(-)

(limited to 'include/linux')

diff --git a/fs/buffer.c b/fs/buffer.c
index 5a28a6aa7f16..23f645657488 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -842,13 +842,13 @@ struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size,
 	struct buffer_head *bh, *head;
 	gfp_t gfp = GFP_NOFS | __GFP_ACCOUNT;
 	long offset;
-	struct mem_cgroup *memcg;
+	struct mem_cgroup *memcg, *old_memcg;
 
 	if (retry)
 		gfp |= __GFP_NOFAIL;
 
 	memcg = get_mem_cgroup_from_page(page);
-	memalloc_use_memcg(memcg);
+	old_memcg = set_active_memcg(memcg);
 
 	head = NULL;
 	offset = PAGE_SIZE;
@@ -867,7 +867,7 @@ struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size,
 		set_bh_page(bh, page, offset);
 	}
 out:
-	memalloc_unuse_memcg();
+	set_active_memcg(old_memcg);
 	mem_cgroup_put(memcg);
 	return head;
 /*
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index c942910a8649..9167884a61ec 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -531,6 +531,7 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
 	struct inode *dirid = fanotify_dfid_inode(mask, data, data_type, dir);
 	const struct path *path = fsnotify_data_path(data, data_type);
 	unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
+	struct mem_cgroup *old_memcg;
 	struct inode *child = NULL;
 	bool name_event = false;
 
@@ -580,7 +581,7 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
 		gfp |= __GFP_RETRY_MAYFAIL;
 
 	/* Whoever is interested in the event, pays for the allocation. */
-	memalloc_use_memcg(group->memcg);
+	old_memcg = set_active_memcg(group->memcg);
 
 	if (fanotify_is_perm_event(mask)) {
 		event = fanotify_alloc_perm_event(path, gfp);
@@ -608,7 +609,7 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
 		event->pid = get_pid(task_tgid(current));
 
 out:
-	memalloc_unuse_memcg();
+	set_active_memcg(old_memcg);
 	return event;
 }
 
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index a65cf8c9f600..9ddcbadc98e2 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -66,6 +66,7 @@ static int inotify_one_event(struct fsnotify_group *group, u32 mask,
 	int ret;
 	int len = 0;
 	int alloc_len = sizeof(struct inotify_event_info);
+	struct mem_cgroup *old_memcg;
 
 	if ((inode_mark->mask & FS_EXCL_UNLINK) &&
 	    path && d_unlinked(path->dentry))
@@ -87,9 +88,9 @@ static int inotify_one_event(struct fsnotify_group *group, u32 mask,
 	 * trigger OOM killer in the target monitoring memcg as it may have
 	 * security repercussion.
 	 */
-	memalloc_use_memcg(group->memcg);
+	old_memcg = set_active_memcg(group->memcg);
 	event = kmalloc(alloc_len, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL);
-	memalloc_unuse_memcg();
+	set_active_memcg(old_memcg);
 
 	if (unlikely(!event)) {
 		/*
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 981e34cb1409..1a80fb128e74 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -280,38 +280,28 @@ static inline void memalloc_nocma_restore(unsigned int flags)
 
 #ifdef CONFIG_MEMCG
 /**
- * memalloc_use_memcg - Starts the remote memcg charging scope.
+ * set_active_memcg - Starts the remote memcg charging scope.
  * @memcg: memcg to charge.
  *
  * This function marks the beginning of the remote memcg charging scope. All the
  * __GFP_ACCOUNT allocations till the end of the scope will be charged to the
  * given memcg.
  *
- * NOTE: This function is not nesting safe.
+ * NOTE: This function can nest. Users must save the return value and
+ * reset the previous value after their own charging scope is over.
  */
-static inline void memalloc_use_memcg(struct mem_cgroup *memcg)
+static inline struct mem_cgroup *
+set_active_memcg(struct mem_cgroup *memcg)
 {
-	WARN_ON_ONCE(current->active_memcg);
+	struct mem_cgroup *old = current->active_memcg;
 	current->active_memcg = memcg;
-}
-
-/**
- * memalloc_unuse_memcg - Ends the remote memcg charging scope.
- *
- * This function marks the end of the remote memcg charging scope started by
- * memalloc_use_memcg().
- */
-static inline void memalloc_unuse_memcg(void)
-{
-	current->active_memcg = NULL;
+	return old;
 }
 #else
-static inline void memalloc_use_memcg(struct mem_cgroup *memcg)
-{
-}
-
-static inline void memalloc_unuse_memcg(void)
+static inline struct mem_cgroup *
+set_active_memcg(struct mem_cgroup *memcg)
 {
+	return NULL;
 }
 #endif
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 7f74a158cfa8..4c741248198b 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5290,12 +5290,12 @@ static struct cgroup_subsys_state * __ref
 mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 {
 	struct mem_cgroup *parent = mem_cgroup_from_css(parent_css);
-	struct mem_cgroup *memcg;
+	struct mem_cgroup *memcg, *old_memcg;
 	long error = -ENOMEM;
 
-	memalloc_use_memcg(parent);
+	old_memcg = set_active_memcg(parent);
 	memcg = mem_cgroup_alloc();
-	memalloc_unuse_memcg();
+	set_active_memcg(old_memcg);
 	if (IS_ERR(memcg))
 		return ERR_CAST(memcg);
 
-- 
cgit v1.2.3


From 37d5985c003daab138a72dd4af9853b396d91c26 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Sat, 17 Oct 2020 16:13:50 -0700
Subject: mm: kmem: prepare remote memcg charging infra for interrupt contexts

Remote memcg charging API uses current->active_memcg to store the
currently active memory cgroup, which overwrites the memory cgroup of the
current process.  It works well for normal contexts, but doesn't work for
interrupt contexts: indeed, if an interrupt occurs during the execution of
a section with an active memcg set, all allocations inside the interrupt
will be charged to the active memcg set (given that we'll enable
accounting for allocations from an interrupt context).  But because the
interrupt might have no relation to the active memcg set outside, it's
obviously wrong from the accounting prospective.

To resolve this problem, let's add a global percpu int_active_memcg
variable, which will be used to store an active memory cgroup which will
be used from interrupt contexts.  set_active_memcg() will transparently
use current->active_memcg or int_active_memcg depending on the context.

To make the read part simple and transparent for the caller, let's
introduce two new functions:
  - struct mem_cgroup *active_memcg(void),
  - struct mem_cgroup *get_active_memcg(void).

They are returning the active memcg if it's set, hiding all implementation
details: where to get it depending on the current context.

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Link: http://lkml.kernel.org/r/20200827225843.1270629-4-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/sched/mm.h | 13 +++++++++++--
 mm/memcontrol.c          | 48 ++++++++++++++++++++++++++++++++++--------------
 2 files changed, 45 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 1a80fb128e74..d5ece7a9a403 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -279,6 +279,7 @@ static inline void memalloc_nocma_restore(unsigned int flags)
 #endif
 
 #ifdef CONFIG_MEMCG
+DECLARE_PER_CPU(struct mem_cgroup *, int_active_memcg);
 /**
  * set_active_memcg - Starts the remote memcg charging scope.
  * @memcg: memcg to charge.
@@ -293,8 +294,16 @@ static inline void memalloc_nocma_restore(unsigned int flags)
 static inline struct mem_cgroup *
 set_active_memcg(struct mem_cgroup *memcg)
 {
-	struct mem_cgroup *old = current->active_memcg;
-	current->active_memcg = memcg;
+	struct mem_cgroup *old;
+
+	if (in_interrupt()) {
+		old = this_cpu_read(int_active_memcg);
+		this_cpu_write(int_active_memcg, memcg);
+	} else {
+		old = current->active_memcg;
+		current->active_memcg = memcg;
+	}
+
 	return old;
 }
 #else
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 51b1698bf06c..a3318b66e41e 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -73,6 +73,9 @@ EXPORT_SYMBOL(memory_cgrp_subsys);
 
 struct mem_cgroup *root_mem_cgroup __read_mostly;
 
+/* Active memory cgroup to use from an interrupt context */
+DEFINE_PER_CPU(struct mem_cgroup *, int_active_memcg);
+
 /* Socket memory accounting disabled? */
 static bool cgroup_memory_nosocket;
 
@@ -1061,26 +1064,43 @@ struct mem_cgroup *get_mem_cgroup_from_page(struct page *page)
 }
 EXPORT_SYMBOL(get_mem_cgroup_from_page);
 
-/**
- * If current->active_memcg is non-NULL, do not fallback to current->mm->memcg.
- */
-static __always_inline struct mem_cgroup *get_mem_cgroup_from_current(void)
+static __always_inline struct mem_cgroup *active_memcg(void)
 {
-	if (memcg_kmem_bypass())
-		return NULL;
+	if (in_interrupt())
+		return this_cpu_read(int_active_memcg);
+	else
+		return current->active_memcg;
+}
 
-	if (unlikely(current->active_memcg)) {
-		struct mem_cgroup *memcg;
+static __always_inline struct mem_cgroup *get_active_memcg(void)
+{
+	struct mem_cgroup *memcg;
 
-		rcu_read_lock();
+	rcu_read_lock();
+	memcg = active_memcg();
+	if (memcg) {
 		/* current->active_memcg must hold a ref. */
-		if (WARN_ON_ONCE(!css_tryget(&current->active_memcg->css)))
+		if (WARN_ON_ONCE(!css_tryget(&memcg->css)))
 			memcg = root_mem_cgroup;
 		else
 			memcg = current->active_memcg;
-		rcu_read_unlock();
-		return memcg;
 	}
+	rcu_read_unlock();
+
+	return memcg;
+}
+
+/**
+ * If active memcg is set, do not fallback to current->mm->memcg.
+ */
+static __always_inline struct mem_cgroup *get_mem_cgroup_from_current(void)
+{
+	if (memcg_kmem_bypass())
+		return NULL;
+
+	if (unlikely(active_memcg()))
+		return get_active_memcg();
+
 	return get_mem_cgroup_from_mm(current->mm);
 }
 
@@ -2940,8 +2960,8 @@ __always_inline struct obj_cgroup *get_obj_cgroup_from_current(void)
 		return NULL;
 
 	rcu_read_lock();
-	if (unlikely(current->active_memcg))
-		memcg = rcu_dereference(current->active_memcg);
+	if (unlikely(active_memcg()))
+		memcg = active_memcg();
 	else
 		memcg = mem_cgroup_from_task(current);
 
-- 
cgit v1.2.3


From 4127c6504f25c4fcff52dc996efda2ef859dd661 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Sat, 17 Oct 2020 16:13:53 -0700
Subject: mm: kmem: enable kernel memcg accounting from interrupt contexts

If a memcg to charge can be determined (using remote charging API), there
are no reasons to exclude allocations made from an interrupt context from
the accounting.

Such allocations will pass even if the resulting memcg size will exceed
the hard limit, but it will affect the application of the memory pressure
and an inability to put the workload under the limit will eventually
trigger the OOM.

To use active_memcg() helper, memcg_kmem_bypass() is moved back to
memcontrol.c.

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Link: http://lkml.kernel.org/r/20200827225843.1270629-5-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 12 ------------
 mm/memcontrol.c            | 13 +++++++++++++
 2 files changed, 13 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 6ef4a552e09d..e391e3c56de5 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1531,18 +1531,6 @@ static inline bool memcg_kmem_enabled(void)
 	return static_branch_likely(&memcg_kmem_enabled_key);
 }
 
-static inline bool memcg_kmem_bypass(void)
-{
-	if (in_interrupt())
-		return true;
-
-	/* Allow remote memcg charging in kthread contexts. */
-	if ((!current->mm || (current->flags & PF_KTHREAD)) &&
-	     !current->active_memcg)
-		return true;
-	return false;
-}
-
 static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp,
 					 int order)
 {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index a3318b66e41e..3a24e3b619f5 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1090,6 +1090,19 @@ static __always_inline struct mem_cgroup *get_active_memcg(void)
 	return memcg;
 }
 
+static __always_inline bool memcg_kmem_bypass(void)
+{
+	/* Allow remote memcg charging from any context. */
+	if (unlikely(active_memcg()))
+		return false;
+
+	/* Memcg to charge can't be determined. */
+	if (in_interrupt() || !current->mm || (current->flags & PF_KTHREAD))
+		return true;
+
+	return false;
+}
+
 /**
  * If active memcg is set, do not fallback to current->mm->memcg.
  */
-- 
cgit v1.2.3


From 0726b01e70455f9900ab524117c7b520d197dc8c Mon Sep 17 00:00:00 2001
From: Minchan Kim <minchan@kernel.org>
Date: Sat, 17 Oct 2020 16:14:50 -0700
Subject: mm/madvise: pass mm to do_madvise

Patch series "introduce memory hinting API for external process", v9.

Now, we have MADV_PAGEOUT and MADV_COLD as madvise hinting API.  With
that, application could give hints to kernel what memory range are
preferred to be reclaimed.  However, in some platform(e.g., Android), the
information required to make the hinting decision is not known to the app.
Instead, it is known to a centralized userspace daemon(e.g.,
ActivityManagerService), and that daemon must be able to initiate reclaim
on its own without any app involvement.

To solve the concern, this patch introduces new syscall -
process_madvise(2).  Bascially, it's same with madvise(2) syscall but it
has some differences.

1. It needs pidfd of target process to provide the hint

2. It supports only MADV_{COLD|PAGEOUT|MERGEABLE|UNMEREABLE} at this
   moment.  Other hints in madvise will be opened when there are explicit
   requests from community to prevent unexpected bugs we couldn't support.

3. Only privileged processes can do something for other process's
   address space.

For more detail of the new API, please see "mm: introduce external memory
hinting API" description in this patchset.

This patch (of 3):

In upcoming patches, do_madvise will be called from external process
context so we shouldn't asssume "current" is always hinted process's
task_struct.

Furthermore, we must not access mm_struct via task->mm, but obtain it via
access_mm() once (in the following patch) and only use that pointer [1],
so pass it to do_madvise() as well.  Note the vma->vm_mm pointers are
safe, so we can use them further down the call stack.

And let's pass current->mm as arguments of do_madvise so it shouldn't
change existing behavior but prepare next patch to make review easy.

[vbabka@suse.cz: changelog tweak]
[minchan@kernel.org: use current->mm for io_uring]
  Link: http://lkml.kernel.org/r/20200423145215.72666-1-minchan@kernel.org
[akpm@linux-foundation.org: fix it for upstream changes]
[akpm@linux-foundation.org: whoops]
[rdunlap@infradead.org: add missing includes]

Signed-off-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: David Rientjes <rientjes@google.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Jann Horn <jannh@google.com>
Cc: Tim Murray <timmurray@google.com>
Cc: Daniel Colascione <dancol@google.com>
Cc: Sandeep Patil <sspatil@google.com>
Cc: Sonny Rao <sonnyrao@google.com>
Cc: Brian Geffon <bgeffon@google.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: John Dias <joaodias@google.com>
Cc: Joel Fernandes <joel@joelfernandes.org>
Cc: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Cc: SeongJae Park <sj38.park@gmail.com>
Cc: Christian Brauner <christian@brauner.io>
Cc: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: Oleksandr Natalenko <oleksandr@redhat.com>
Cc: SeongJae Park <sjpark@amazon.de>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Florian Weimer <fw@deneb.enyo.de>
Cc: <linux-man@vger.kernel.org>
Link: https://lkml.kernel.org/r/20200901000633.1920247-1-minchan@kernel.org
Link: http://lkml.kernel.org/r/20200622192900.22757-1-minchan@kernel.org
Link: http://lkml.kernel.org/r/20200302193630.68771-2-minchan@kernel.org
Link: http://lkml.kernel.org/r/20200622192900.22757-2-minchan@kernel.org
Link: https://lkml.kernel.org/r/20200901000633.1920247-2-minchan@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/io_uring.c      |  2 +-
 include/linux/mm.h |  2 +-
 mm/madvise.c       | 32 ++++++++++++++++++--------------
 3 files changed, 20 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 2e1dc354cd08..b58169240c77 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -3989,7 +3989,7 @@ static int io_madvise(struct io_kiocb *req, bool force_nonblock)
 	if (force_nonblock)
 		return -EAGAIN;
 
-	ret = do_madvise(ma->addr, ma->len, ma->advice);
+	ret = do_madvise(current->mm, ma->addr, ma->len, ma->advice);
 	if (ret < 0)
 		req_set_fail_links(req);
 	io_req_complete(req, ret);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 61a2633fcc7f..ef360fe70aaf 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2579,7 +2579,7 @@ extern int __do_munmap(struct mm_struct *, unsigned long, size_t,
 		       struct list_head *uf, bool downgrade);
 extern int do_munmap(struct mm_struct *, unsigned long, size_t,
 		     struct list_head *uf);
-extern int do_madvise(unsigned long start, size_t len_in, int behavior);
+extern int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior);
 
 #ifdef CONFIG_MMU
 extern int __mm_populate(unsigned long addr, unsigned long len,
diff --git a/mm/madvise.c b/mm/madvise.c
index fd1f448b4e1d..d550ef045288 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -258,6 +258,7 @@ static long madvise_willneed(struct vm_area_struct *vma,
 			     struct vm_area_struct **prev,
 			     unsigned long start, unsigned long end)
 {
+	struct mm_struct *mm = vma->vm_mm;
 	struct file *file = vma->vm_file;
 	loff_t offset;
 
@@ -294,10 +295,10 @@ static long madvise_willneed(struct vm_area_struct *vma,
 	get_file(file);
 	offset = (loff_t)(start - vma->vm_start)
 			+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
-	mmap_read_unlock(current->mm);
+	mmap_read_unlock(mm);
 	vfs_fadvise(file, offset, end - start, POSIX_FADV_WILLNEED);
 	fput(file);
-	mmap_read_lock(current->mm);
+	mmap_read_lock(mm);
 	return 0;
 }
 
@@ -766,6 +767,8 @@ static long madvise_dontneed_free(struct vm_area_struct *vma,
 				  unsigned long start, unsigned long end,
 				  int behavior)
 {
+	struct mm_struct *mm = vma->vm_mm;
+
 	*prev = vma;
 	if (!can_madv_lru_vma(vma))
 		return -EINVAL;
@@ -773,8 +776,8 @@ static long madvise_dontneed_free(struct vm_area_struct *vma,
 	if (!userfaultfd_remove(vma, start, end)) {
 		*prev = NULL; /* mmap_lock has been dropped, prev is stale */
 
-		mmap_read_lock(current->mm);
-		vma = find_vma(current->mm, start);
+		mmap_read_lock(mm);
+		vma = find_vma(mm, start);
 		if (!vma)
 			return -ENOMEM;
 		if (start < vma->vm_start) {
@@ -828,6 +831,7 @@ static long madvise_remove(struct vm_area_struct *vma,
 	loff_t offset;
 	int error;
 	struct file *f;
+	struct mm_struct *mm = vma->vm_mm;
 
 	*prev = NULL;	/* tell sys_madvise we drop mmap_lock */
 
@@ -855,13 +859,13 @@ static long madvise_remove(struct vm_area_struct *vma,
 	get_file(f);
 	if (userfaultfd_remove(vma, start, end)) {
 		/* mmap_lock was not released by userfaultfd_remove() */
-		mmap_read_unlock(current->mm);
+		mmap_read_unlock(mm);
 	}
 	error = vfs_fallocate(f,
 				FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
 				offset, end - start);
 	fput(f);
-	mmap_read_lock(current->mm);
+	mmap_read_lock(mm);
 	return error;
 }
 
@@ -1045,7 +1049,7 @@ madvise_behavior_valid(int behavior)
  *  -EBADF  - map exists, but area maps something that isn't a file.
  *  -EAGAIN - a kernel resource was temporarily unavailable.
  */
-int do_madvise(unsigned long start, size_t len_in, int behavior)
+int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior)
 {
 	unsigned long end, tmp;
 	struct vm_area_struct *vma, *prev;
@@ -1083,10 +1087,10 @@ int do_madvise(unsigned long start, size_t len_in, int behavior)
 
 	write = madvise_need_mmap_write(behavior);
 	if (write) {
-		if (mmap_write_lock_killable(current->mm))
+		if (mmap_write_lock_killable(mm))
 			return -EINTR;
 	} else {
-		mmap_read_lock(current->mm);
+		mmap_read_lock(mm);
 	}
 
 	/*
@@ -1094,7 +1098,7 @@ int do_madvise(unsigned long start, size_t len_in, int behavior)
 	 * ranges, just ignore them, but return -ENOMEM at the end.
 	 * - different from the way of handling in mlock etc.
 	 */
-	vma = find_vma_prev(current->mm, start, &prev);
+	vma = find_vma_prev(mm, start, &prev);
 	if (vma && start > vma->vm_start)
 		prev = vma;
 
@@ -1131,19 +1135,19 @@ int do_madvise(unsigned long start, size_t len_in, int behavior)
 		if (prev)
 			vma = prev->vm_next;
 		else	/* madvise_remove dropped mmap_lock */
-			vma = find_vma(current->mm, start);
+			vma = find_vma(mm, start);
 	}
 out:
 	blk_finish_plug(&plug);
 	if (write)
-		mmap_write_unlock(current->mm);
+		mmap_write_unlock(mm);
 	else
-		mmap_read_unlock(current->mm);
+		mmap_read_unlock(mm);
 
 	return error;
 }
 
 SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
 {
-	return do_madvise(start, len_in, behavior);
+	return do_madvise(current->mm, start, len_in, behavior);
 }
-- 
cgit v1.2.3


From 1aa92cd31c1c032ddfed27e79d646bbb429e9b52 Mon Sep 17 00:00:00 2001
From: Minchan Kim <minchan@kernel.org>
Date: Sat, 17 Oct 2020 16:14:54 -0700
Subject: pid: move pidfd_get_pid() to pid.c

process_madvise syscall needs pidfd_get_pid function to translate pidfd to
pid so this patch move the function to kernel/pid.c.

Suggested-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Reviewed-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Acked-by: David Rientjes <rientjes@google.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Jann Horn <jannh@google.com>
Cc: Brian Geffon <bgeffon@google.com>
Cc: Daniel Colascione <dancol@google.com>
Cc: Joel Fernandes <joel@joelfernandes.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Dias <joaodias@google.com>
Cc: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Oleksandr Natalenko <oleksandr@redhat.com>
Cc: Sandeep Patil <sspatil@google.com>
Cc: SeongJae Park <sj38.park@gmail.com>
Cc: SeongJae Park <sjpark@amazon.de>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Sonny Rao <sonnyrao@google.com>
Cc: Tim Murray <timmurray@google.com>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Florian Weimer <fw@deneb.enyo.de>
Cc: <linux-man@vger.kernel.org>
Link: http://lkml.kernel.org/r/20200302193630.68771-5-minchan@kernel.org
Link: http://lkml.kernel.org/r/20200622192900.22757-3-minchan@kernel.org
Link: https://lkml.kernel.org/r/20200901000633.1920247-3-minchan@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/pid.h |  1 +
 kernel/exit.c       | 19 -------------------
 kernel/pid.c        | 19 +++++++++++++++++++
 3 files changed, 20 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pid.h b/include/linux/pid.h
index 176d6cf80e7c..fa10acb8d6a4 100644
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -77,6 +77,7 @@ extern const struct file_operations pidfd_fops;
 struct file;
 
 extern struct pid *pidfd_pid(const struct file *file);
+struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags);
 
 static inline struct pid *get_pid(struct pid *pid)
 {
diff --git a/kernel/exit.c b/kernel/exit.c
index 1f51c27bae59..87a2d515de0d 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1474,25 +1474,6 @@ end:
 	return retval;
 }
 
-static struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags)
-{
-	struct fd f;
-	struct pid *pid;
-
-	f = fdget(fd);
-	if (!f.file)
-		return ERR_PTR(-EBADF);
-
-	pid = pidfd_pid(f.file);
-	if (!IS_ERR(pid)) {
-		get_pid(pid);
-		*flags = f.file->f_flags;
-	}
-
-	fdput(f);
-	return pid;
-}
-
 static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop,
 			  int options, struct rusage *ru)
 {
diff --git a/kernel/pid.c b/kernel/pid.c
index 74ddbff1a6ba..a96bc4bf4f86 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -520,6 +520,25 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
 	return idr_get_next(&ns->idr, &nr);
 }
 
+struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags)
+{
+	struct fd f;
+	struct pid *pid;
+
+	f = fdget(fd);
+	if (!f.file)
+		return ERR_PTR(-EBADF);
+
+	pid = pidfd_pid(f.file);
+	if (!IS_ERR(pid)) {
+		get_pid(pid);
+		*flags = f.file->f_flags;
+	}
+
+	fdput(f);
+	return pid;
+}
+
 /**
  * pidfd_create() - Create a new pid file descriptor.
  *
-- 
cgit v1.2.3


From ecb8ac8b1f146915aa6b96449b66dd48984caacc Mon Sep 17 00:00:00 2001
From: Minchan Kim <minchan@kernel.org>
Date: Sat, 17 Oct 2020 16:14:59 -0700
Subject: mm/madvise: introduce process_madvise() syscall: an external memory
 hinting API

There is usecase that System Management Software(SMS) want to give a
memory hint like MADV_[COLD|PAGEEOUT] to other processes and in the
case of Android, it is the ActivityManagerService.

The information required to make the reclaim decision is not known to the
app.  Instead, it is known to the centralized userspace
daemon(ActivityManagerService), and that daemon must be able to initiate
reclaim on its own without any app involvement.

To solve the issue, this patch introduces a new syscall
process_madvise(2).  It uses pidfd of an external process to give the
hint.  It also supports vector address range because Android app has
thousands of vmas due to zygote so it's totally waste of CPU and power if
we should call the syscall one by one for each vma.(With testing 2000-vma
syscall vs 1-vector syscall, it showed 15% performance improvement.  I
think it would be bigger in real practice because the testing ran very
cache friendly environment).

Another potential use case for the vector range is to amortize the cost
ofTLB shootdowns for multiple ranges when using MADV_DONTNEED; this could
benefit users like TCP receive zerocopy and malloc implementations.  In
future, we could find more usecases for other advises so let's make it
happens as API since we introduce a new syscall at this moment.  With
that, existing madvise(2) user could replace it with process_madvise(2)
with their own pid if they want to have batch address ranges support
feature.

ince it could affect other process's address range, only privileged
process(PTRACE_MODE_ATTACH_FSCREDS) or something else(e.g., being the same
UID) gives it the right to ptrace the process could use it successfully.
The flag argument is reserved for future use if we need to extend the API.

I think supporting all hints madvise has/will supported/support to
process_madvise is rather risky.  Because we are not sure all hints make
sense from external process and implementation for the hint may rely on
the caller being in the current context so it could be error-prone.  Thus,
I just limited hints as MADV_[COLD|PAGEOUT] in this patch.

If someone want to add other hints, we could hear the usecase and review
it for each hint.  It's safer for maintenance rather than introducing a
buggy syscall but hard to fix it later.

So finally, the API is as follows,

      ssize_t process_madvise(int pidfd, const struct iovec *iovec,
                unsigned long vlen, int advice, unsigned int flags);

    DESCRIPTION
      The process_madvise() system call is used to give advice or directions
      to the kernel about the address ranges from external process as well as
      local process. It provides the advice to address ranges of process
      described by iovec and vlen. The goal of such advice is to improve
      system or application performance.

      The pidfd selects the process referred to by the PID file descriptor
      specified in pidfd. (See pidofd_open(2) for further information)

      The pointer iovec points to an array of iovec structures, defined in
      <sys/uio.h> as:

        struct iovec {
            void *iov_base;         /* starting address */
            size_t iov_len;         /* number of bytes to be advised */
        };

      The iovec describes address ranges beginning at address(iov_base)
      and with size length of bytes(iov_len).

      The vlen represents the number of elements in iovec.

      The advice is indicated in the advice argument, which is one of the
      following at this moment if the target process specified by pidfd is
      external.

        MADV_COLD
        MADV_PAGEOUT

      Permission to provide a hint to external process is governed by a
      ptrace access mode PTRACE_MODE_ATTACH_FSCREDS check; see ptrace(2).

      The process_madvise supports every advice madvise(2) has if target
      process is in same thread group with calling process so user could
      use process_madvise(2) to extend existing madvise(2) to support
      vector address ranges.

    RETURN VALUE
      On success, process_madvise() returns the number of bytes advised.
      This return value may be less than the total number of requested
      bytes, if an error occurred. The caller should check return value
      to determine whether a partial advice occurred.

FAQ:

Q.1 - Why does any external entity have better knowledge?

Quote from Sandeep

"For Android, every application (including the special SystemServer)
are forked from Zygote.  The reason of course is to share as many
libraries and classes between the two as possible to benefit from the
preloading during boot.

After applications start, (almost) all of the APIs end up calling into
this SystemServer process over IPC (binder) and back to the
application.

In a fully running system, the SystemServer monitors every single
process periodically to calculate their PSS / RSS and also decides
which process is "important" to the user for interactivity.

So, because of how these processes start _and_ the fact that the
SystemServer is looping to monitor each process, it does tend to *know*
which address range of the application is not used / useful.

Besides, we can never rely on applications to clean things up
themselves.  We've had the "hey app1, the system is low on memory,
please trim your memory usage down" notifications for a long time[1].
They rely on applications honoring the broadcasts and very few do.

So, if we want to avoid the inevitable killing of the application and
restarting it, some way to be able to tell the OS about unimportant
memory in these applications will be useful.

- ssp

Q.2 - How to guarantee the race(i.e., object validation) between when
giving a hint from an external process and get the hint from the target
process?

process_madvise operates on the target process's address space as it
exists at the instant that process_madvise is called.  If the space
target process can run between the time the process_madvise process
inspects the target process address space and the time that
process_madvise is actually called, process_madvise may operate on
memory regions that the calling process does not expect.  It's the
responsibility of the process calling process_madvise to close this
race condition.  For example, the calling process can suspend the
target process with ptrace, SIGSTOP, or the freezer cgroup so that it
doesn't have an opportunity to change its own address space before
process_madvise is called.  Another option is to operate on memory
regions that the caller knows a priori will be unchanged in the target
process.  Yet another option is to accept the race for certain
process_madvise calls after reasoning that mistargeting will do no
harm.  The suggested API itself does not provide synchronization.  It
also apply other APIs like move_pages, process_vm_write.

The race isn't really a problem though.  Why is it so wrong to require
that callers do their own synchronization in some manner?  Nobody
objects to write(2) merely because it's possible for two processes to
open the same file and clobber each other's writes --- instead, we tell
people to use flock or something.  Think about mmap.  It never
guarantees newly allocated address space is still valid when the user
tries to access it because other threads could unmap the memory right
before.  That's where we need synchronization by using other API or
design from userside.  It shouldn't be part of API itself.  If someone
needs more fine-grained synchronization rather than process level,
there were two ideas suggested - cookie[2] and anon-fd[3].  Both are
applicable via using last reserved argument of the API but I don't
think it's necessary right now since we have already ways to prevent
the race so don't want to add additional complexity with more
fine-grained optimization model.

To make the API extend, it reserved an unsigned long as last argument
so we could support it in future if someone really needs it.

Q.3 - Why doesn't ptrace work?

Injecting an madvise in the target process using ptrace would not work
for us because such injected madvise would have to be executed by the
target process, which means that process would have to be runnable and
that creates the risk of the abovementioned race and hinting a wrong
VMA.  Furthermore, we want to act the hint in caller's context, not the
callee's, because the callee is usually limited in cpuset/cgroups or
even freezed state so they can't act by themselves quick enough, which
causes more thrashing/kill.  It doesn't work if the target process are
ptraced(e.g., strace, debugger, minidump) because a process can have at
most one ptracer.

[1] https://developer.android.com/topic/performance/memory"

[2] process_getinfo for getting the cookie which is updated whenever
    vma of process address layout are changed - Daniel Colascione -
    https://lore.kernel.org/lkml/20190520035254.57579-1-minchan@kernel.org/T/#m7694416fd179b2066a2c62b5b139b14e3894e224

[3] anonymous fd which is used for the object(i.e., address range)
    validation - Michal Hocko -
    https://lore.kernel.org/lkml/20200120112722.GY18451@dhcp22.suse.cz/

[minchan@kernel.org: fix process_madvise build break for arm64]
  Link: http://lkml.kernel.org/r/20200303145756.GA219683@google.com
[minchan@kernel.org: fix build error for mips of process_madvise]
  Link: http://lkml.kernel.org/r/20200508052517.GA197378@google.com
[akpm@linux-foundation.org: fix patch ordering issue]
[akpm@linux-foundation.org: fix arm64 whoops]
[minchan@kernel.org: make process_madvise() vlen arg have type size_t, per Florian]
[akpm@linux-foundation.org: fix i386 build]
[sfr@canb.auug.org.au: fix syscall numbering]
  Link: https://lkml.kernel.org/r/20200905142639.49fc3f1a@canb.auug.org.au
[sfr@canb.auug.org.au: madvise.c needs compat.h]
  Link: https://lkml.kernel.org/r/20200908204547.285646b4@canb.auug.org.au
[minchan@kernel.org: fix mips build]
  Link: https://lkml.kernel.org/r/20200909173655.GC2435453@google.com
[yuehaibing@huawei.com: remove duplicate header which is included twice]
  Link: https://lkml.kernel.org/r/20200915121550.30584-1-yuehaibing@huawei.com
[minchan@kernel.org: do not use helper functions for process_madvise]
  Link: https://lkml.kernel.org/r/20200921175539.GB387368@google.com
[akpm@linux-foundation.org: pidfd_get_pid() gained an argument]
[sfr@canb.auug.org.au: fix up for "iov_iter: transparently handle compat iovecs in import_iovec"]
  Link: https://lkml.kernel.org/r/20200928212542.468e1fef@canb.auug.org.au

Signed-off-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: David Rientjes <rientjes@google.com>
Cc: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Cc: Brian Geffon <bgeffon@google.com>
Cc: Christian Brauner <christian@brauner.io>
Cc: Daniel Colascione <dancol@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Joel Fernandes <joel@joelfernandes.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Dias <joaodias@google.com>
Cc: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Oleksandr Natalenko <oleksandr@redhat.com>
Cc: Sandeep Patil <sspatil@google.com>
Cc: SeongJae Park <sj38.park@gmail.com>
Cc: SeongJae Park <sjpark@amazon.de>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Sonny Rao <sonnyrao@google.com>
Cc: Tim Murray <timmurray@google.com>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Florian Weimer <fw@deneb.enyo.de>
Cc: <linux-man@vger.kernel.org>
Link: http://lkml.kernel.org/r/20200302193630.68771-3-minchan@kernel.org
Link: http://lkml.kernel.org/r/20200508183320.GA125527@google.com
Link: http://lkml.kernel.org/r/20200622192900.22757-4-minchan@kernel.org
Link: https://lkml.kernel.org/r/20200901000633.1920247-4-minchan@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/alpha/kernel/syscalls/syscall.tbl      |  1 +
 arch/arm/tools/syscall.tbl                  |  1 +
 arch/arm64/include/asm/unistd.h             |  2 +-
 arch/arm64/include/asm/unistd32.h           |  2 +
 arch/ia64/kernel/syscalls/syscall.tbl       |  1 +
 arch/m68k/kernel/syscalls/syscall.tbl       |  1 +
 arch/microblaze/kernel/syscalls/syscall.tbl |  1 +
 arch/mips/kernel/syscalls/syscall_n32.tbl   |  1 +
 arch/mips/kernel/syscalls/syscall_n64.tbl   |  1 +
 arch/mips/kernel/syscalls/syscall_o32.tbl   |  1 +
 arch/parisc/kernel/syscalls/syscall.tbl     |  1 +
 arch/powerpc/kernel/syscalls/syscall.tbl    |  1 +
 arch/s390/kernel/syscalls/syscall.tbl       |  1 +
 arch/sh/kernel/syscalls/syscall.tbl         |  1 +
 arch/sparc/kernel/syscalls/syscall.tbl      |  1 +
 arch/x86/entry/syscalls/syscall_32.tbl      |  1 +
 arch/x86/entry/syscalls/syscall_64.tbl      |  1 +
 arch/xtensa/kernel/syscalls/syscall.tbl     |  1 +
 include/linux/syscalls.h                    |  2 +
 include/uapi/asm-generic/unistd.h           |  4 +-
 kernel/sys_ni.c                             |  1 +
 mm/madvise.c                                | 93 ++++++++++++++++++++++++++++-
 22 files changed, 117 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index ec8bed9e7b75..ee7b01bb7346 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -479,3 +479,4 @@
 547	common	openat2				sys_openat2
 548	common	pidfd_getfd			sys_pidfd_getfd
 549	common	faccessat2			sys_faccessat2
+550	common	process_madvise			sys_process_madvise
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index 171077cbf419..d056a548358e 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -453,3 +453,4 @@
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	faccessat2			sys_faccessat2
+440	common	process_madvise			sys_process_madvise
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 3b859596840d..b3b2019f8d16 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -38,7 +38,7 @@
 #define __ARM_NR_compat_set_tls		(__ARM_NR_COMPAT_BASE + 5)
 #define __ARM_NR_COMPAT_END		(__ARM_NR_COMPAT_BASE + 0x800)
 
-#define __NR_compat_syscalls		440
+#define __NR_compat_syscalls		441
 #endif
 
 #define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 2a3ad9b9accd..107f08e03b9f 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -887,6 +887,8 @@ __SYSCALL(__NR_openat2, sys_openat2)
 __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
 #define __NR_faccessat2 439
 __SYSCALL(__NR_faccessat2, sys_faccessat2)
+#define __NR_process_madvise 440
+__SYSCALL(__NR_process_madvise, sys_process_madvise)
 
 /*
  * Please add new compat syscalls above this comment and update
diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl
index 4799c96c325f..b96ed8b8a508 100644
--- a/arch/ia64/kernel/syscalls/syscall.tbl
+++ b/arch/ia64/kernel/syscalls/syscall.tbl
@@ -360,3 +360,4 @@
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	faccessat2			sys_faccessat2
+440	common	process_madvise			sys_process_madvise
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index 81fc799d8392..625fb6d32842 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -439,3 +439,4 @@
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	faccessat2			sys_faccessat2
+440	common	process_madvise			sys_process_madvise
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index b4e263916f41..aae729c95cf9 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -445,3 +445,4 @@
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	faccessat2			sys_faccessat2
+440	common	process_madvise			sys_process_madvise
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index cf72a0206a87..32817c954435 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -378,3 +378,4 @@
 437	n32	openat2				sys_openat2
 438	n32	pidfd_getfd			sys_pidfd_getfd
 439	n32	faccessat2			sys_faccessat2
+440	n32	process_madvise			sys_process_madvise
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index 557f9954a2b9..9e4ea3c31b1c 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -354,3 +354,4 @@
 437	n64	openat2				sys_openat2
 438	n64	pidfd_getfd			sys_pidfd_getfd
 439	n64	faccessat2			sys_faccessat2
+440	n64	process_madvise			sys_process_madvise
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index a17aab5abeb2..29f5f28cf5ce 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -427,3 +427,4 @@
 437	o32	openat2				sys_openat2
 438	o32	pidfd_getfd			sys_pidfd_getfd
 439	o32	faccessat2			sys_faccessat2
+440	o32	process_madvise			sys_process_madvise
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index ae3dab371f6f..38c63e5404bc 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -437,3 +437,4 @@
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	faccessat2			sys_faccessat2
+440	common	process_madvise			sys_process_madvise
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index 9d7fb4ced290..1275daec7fec 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -529,3 +529,4 @@
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	faccessat2			sys_faccessat2
+440	common	process_madvise			sys_process_madvise
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 1c3b48165e86..28c168000483 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -442,3 +442,4 @@
 437  common	openat2			sys_openat2			sys_openat2
 438  common	pidfd_getfd		sys_pidfd_getfd			sys_pidfd_getfd
 439  common	faccessat2		sys_faccessat2			sys_faccessat2
+440  common	process_madvise		sys_process_madvise		sys_process_madvise
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index ae0a00beea5f..783738448ff5 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -442,3 +442,4 @@
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	faccessat2			sys_faccessat2
+440	common	process_madvise			sys_process_madvise
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index 37ec52b34c73..78160260991b 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -485,3 +485,4 @@
 437	common	openat2			sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	faccessat2			sys_faccessat2
+440	common	process_madvise			sys_process_madvise
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 9b6931f8d555..0d0667a9fbd7 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -444,3 +444,4 @@
 437	i386	openat2			sys_openat2
 438	i386	pidfd_getfd		sys_pidfd_getfd
 439	i386	faccessat2		sys_faccessat2
+440	i386	process_madvise		sys_process_madvise
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 347809649ba2..1f47e24fb65c 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -361,6 +361,7 @@
 437	common	openat2			sys_openat2
 438	common	pidfd_getfd		sys_pidfd_getfd
 439	common	faccessat2		sys_faccessat2
+440	common	process_madvise		sys_process_madvise
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index 6276e3c2d3fc..b070f272995d 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -410,3 +410,4 @@
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	faccessat2			sys_faccessat2
+440	common	process_madvise			sys_process_madvise
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 06db09875aa4..2eda7678fe1d 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -879,6 +879,8 @@ asmlinkage long sys_munlockall(void);
 asmlinkage long sys_mincore(unsigned long start, size_t len,
 				unsigned char __user * vec);
 asmlinkage long sys_madvise(unsigned long start, size_t len, int behavior);
+asmlinkage long sys_process_madvise(int pidfd, const struct iovec __user *vec,
+			size_t vlen, int behavior, unsigned int flags);
 asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size,
 			unsigned long prot, unsigned long pgoff,
 			unsigned long flags);
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index f2b5d72a46c2..2056318988f7 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -857,9 +857,11 @@ __SYSCALL(__NR_openat2, sys_openat2)
 __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
 #define __NR_faccessat2 439
 __SYSCALL(__NR_faccessat2, sys_faccessat2)
+#define __NR_process_madvise 440
+__SYSCALL(__NR_process_madvise, sys_process_madvise)
 
 #undef __NR_syscalls
-#define __NR_syscalls 440
+#define __NR_syscalls 441
 
 /*
  * 32 bit systems traditionally used different
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index c925d1e1777e..f27ac94d5fa7 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -280,6 +280,7 @@ COND_SYSCALL(mlockall);
 COND_SYSCALL(munlockall);
 COND_SYSCALL(mincore);
 COND_SYSCALL(madvise);
+COND_SYSCALL(process_madvise);
 COND_SYSCALL(remap_file_pages);
 COND_SYSCALL(mbind);
 COND_SYSCALL_COMPAT(mbind);
diff --git a/mm/madvise.c b/mm/madvise.c
index d550ef045288..416a56b8e757 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -17,6 +17,8 @@
 #include <linux/falloc.h>
 #include <linux/fadvise.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
+#include <linux/uio.h>
 #include <linux/ksm.h>
 #include <linux/fs.h>
 #include <linux/file.h>
@@ -27,7 +29,6 @@
 #include <linux/swapops.h>
 #include <linux/shmem_fs.h>
 #include <linux/mmu_notifier.h>
-#include <linux/sched/mm.h>
 
 #include <asm/tlb.h>
 
@@ -988,6 +989,18 @@ madvise_behavior_valid(int behavior)
 	}
 }
 
+static bool
+process_madvise_behavior_valid(int behavior)
+{
+	switch (behavior) {
+	case MADV_COLD:
+	case MADV_PAGEOUT:
+		return true;
+	default:
+		return false;
+	}
+}
+
 /*
  * The madvise(2) system call.
  *
@@ -1035,6 +1048,11 @@ madvise_behavior_valid(int behavior)
  *  MADV_DONTDUMP - the application wants to prevent pages in the given range
  *		from being included in its core dump.
  *  MADV_DODUMP - cancel MADV_DONTDUMP: no longer exclude from core dump.
+ *  MADV_COLD - the application is not expected to use this memory soon,
+ *		deactivate pages in this range so that they can be reclaimed
+ *		easily if memory pressure hanppens.
+ *  MADV_PAGEOUT - the application is not expected to use this memory soon,
+ *		page out the pages in this range immediately.
  *
  * return values:
  *  zero    - success
@@ -1151,3 +1169,76 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
 {
 	return do_madvise(current->mm, start, len_in, behavior);
 }
+
+SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec,
+		size_t, vlen, int, behavior, unsigned int, flags)
+{
+	ssize_t ret;
+	struct iovec iovstack[UIO_FASTIOV], iovec;
+	struct iovec *iov = iovstack;
+	struct iov_iter iter;
+	struct pid *pid;
+	struct task_struct *task;
+	struct mm_struct *mm;
+	size_t total_len;
+	unsigned int f_flags;
+
+	if (flags != 0) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ret = import_iovec(READ, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter);
+	if (ret < 0)
+		goto out;
+
+	pid = pidfd_get_pid(pidfd, &f_flags);
+	if (IS_ERR(pid)) {
+		ret = PTR_ERR(pid);
+		goto free_iov;
+	}
+
+	task = get_pid_task(pid, PIDTYPE_PID);
+	if (!task) {
+		ret = -ESRCH;
+		goto put_pid;
+	}
+
+	if (task->mm != current->mm &&
+			!process_madvise_behavior_valid(behavior)) {
+		ret = -EINVAL;
+		goto release_task;
+	}
+
+	mm = mm_access(task, PTRACE_MODE_ATTACH_FSCREDS);
+	if (IS_ERR_OR_NULL(mm)) {
+		ret = IS_ERR(mm) ? PTR_ERR(mm) : -ESRCH;
+		goto release_task;
+	}
+
+	total_len = iov_iter_count(&iter);
+
+	while (iov_iter_count(&iter)) {
+		iovec = iov_iter_iovec(&iter);
+		ret = do_madvise(mm, (unsigned long)iovec.iov_base,
+					iovec.iov_len, behavior);
+		if (ret < 0)
+			break;
+		iov_iter_advance(&iter, iovec.iov_len);
+	}
+
+	if (ret == 0)
+		ret = total_len - iov_iter_count(&iter);
+
+	mmput(mm);
+	return ret;
+
+release_task:
+	put_task_struct(task);
+put_pid:
+	put_pid(pid);
+free_iov:
+	kfree(iov);
+out:
+	return ret;
+}
-- 
cgit v1.2.3


From b944afc9d64ddf1b6a152c23ff86bf26e1fd430c Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 17 Oct 2020 16:15:06 -0700
Subject: mm: add a VM_MAP_PUT_PAGES flag for vmap

Add a flag so that vmap takes ownership of the passed in page array.  When
vfree is called on such an allocation it will put one reference on each
page, and free the page array itself.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Uladzislau Rezki (Sony) <urezki@gmail.com>
Link: https://lkml.kernel.org/r/20201002122204.1534411-3-hch@lst.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/vmalloc.h | 1 +
 mm/vmalloc.c            | 9 +++++++--
 2 files changed, 8 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 0221f852a7e1..b899681e3ff9 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -24,6 +24,7 @@ struct notifier_block;		/* in notifier.h */
 #define VM_UNINITIALIZED	0x00000020	/* vm_struct is not fully initialized */
 #define VM_NO_GUARD		0x00000040      /* don't add guard page */
 #define VM_KASAN		0x00000080      /* has allocated kasan shadow memory */
+#define VM_MAP_PUT_PAGES	0x00000100	/* put pages and free array in vfree */
 
 /*
  * VM_KASAN is used slighly differently depending on CONFIG_KASAN_VMALLOC.
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 74af03a2a769..63b19a571be7 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2377,8 +2377,11 @@ EXPORT_SYMBOL(vunmap);
  * @flags: vm_area->flags
  * @prot: page protection for the mapping
  *
- * Maps @count pages from @pages into contiguous kernel virtual
- * space.
+ * Maps @count pages from @pages into contiguous kernel virtual space.
+ * If @flags contains %VM_MAP_PUT_PAGES the ownership of the pages array itself
+ * (which must be kmalloc or vmalloc memory) and one reference per pages in it
+ * are transferred from the caller to vmap(), and will be freed / dropped when
+ * vfree() is called on the return value.
  *
  * Return: the address of the area or %NULL on failure
  */
@@ -2404,6 +2407,8 @@ void *vmap(struct page **pages, unsigned int count,
 		return NULL;
 	}
 
+	if (flags & VM_MAP_PUT_PAGES)
+		area->pages = pages;
 	return area->addr;
 }
 EXPORT_SYMBOL(vmap);
-- 
cgit v1.2.3


From 3e9a9e256b1e1e6e8f19faf76fa9c37578ae35ee Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 17 Oct 2020 16:15:10 -0700
Subject: mm: add a vmap_pfn function

Add a proper helper to remap PFNs into kernel virtual space so that
drivers don't have to abuse alloc_vm_area and open coded PTE manipulation
for it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Uladzislau Rezki (Sony) <urezki@gmail.com>
Link: https://lkml.kernel.org/r/20201002122204.1534411-4-hch@lst.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/vmalloc.h |  1 +
 mm/Kconfig              |  3 +++
 mm/vmalloc.c            | 45 +++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 49 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index b899681e3ff9..c77efeac2425 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -122,6 +122,7 @@ extern void vfree_atomic(const void *addr);
 
 extern void *vmap(struct page **pages, unsigned int count,
 			unsigned long flags, pgprot_t prot);
+void *vmap_pfn(unsigned long *pfns, unsigned int count, pgprot_t prot);
 extern void vunmap(const void *addr);
 
 extern int remap_vmalloc_range_partial(struct vm_area_struct *vma,
diff --git a/mm/Kconfig b/mm/Kconfig
index c7f30f8b282b..d42423f884a7 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -816,6 +816,9 @@ config DEVICE_PRIVATE
 	  memory; i.e., memory that is only accessible from the device (or
 	  group of devices). You likely also want to select HMM_MIRROR.
 
+config VMAP_PFN
+	bool
+
 config FRAME_VECTOR
 	bool
 
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 63b19a571be7..c6bf73a64db8 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2413,6 +2413,51 @@ void *vmap(struct page **pages, unsigned int count,
 }
 EXPORT_SYMBOL(vmap);
 
+#ifdef CONFIG_VMAP_PFN
+struct vmap_pfn_data {
+	unsigned long	*pfns;
+	pgprot_t	prot;
+	unsigned int	idx;
+};
+
+static int vmap_pfn_apply(pte_t *pte, unsigned long addr, void *private)
+{
+	struct vmap_pfn_data *data = private;
+
+	if (WARN_ON_ONCE(pfn_valid(data->pfns[data->idx])))
+		return -EINVAL;
+	*pte = pte_mkspecial(pfn_pte(data->pfns[data->idx++], data->prot));
+	return 0;
+}
+
+/**
+ * vmap_pfn - map an array of PFNs into virtually contiguous space
+ * @pfns: array of PFNs
+ * @count: number of pages to map
+ * @prot: page protection for the mapping
+ *
+ * Maps @count PFNs from @pfns into contiguous kernel virtual space and returns
+ * the start address of the mapping.
+ */
+void *vmap_pfn(unsigned long *pfns, unsigned int count, pgprot_t prot)
+{
+	struct vmap_pfn_data data = { .pfns = pfns, .prot = pgprot_nx(prot) };
+	struct vm_struct *area;
+
+	area = get_vm_area_caller(count * PAGE_SIZE, VM_IOREMAP,
+			__builtin_return_address(0));
+	if (!area)
+		return NULL;
+	if (apply_to_page_range(&init_mm, (unsigned long)area->addr,
+			count * PAGE_SIZE, vmap_pfn_apply, &data)) {
+		free_vm_area(area);
+		return NULL;
+	}
+	return area->addr;
+}
+EXPORT_SYMBOL_GPL(vmap_pfn);
+#endif /* CONFIG_VMAP_PFN */
+
 static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 				 pgprot_t prot, int node)
 {
-- 
cgit v1.2.3


From 301fa9f2ddf7fb248c188af292c9cc04f8283dff Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 17 Oct 2020 16:15:39 -0700
Subject: mm: remove alloc_vm_area

All users are gone now.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Uladzislau Rezki (Sony) <urezki@gmail.com>
Link: https://lkml.kernel.org/r/20201002122204.1534411-12-hch@lst.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/vmalloc.h |  5 +----
 mm/nommu.c              |  7 -------
 mm/vmalloc.c            | 48 ------------------------------------------------
 3 files changed, 1 insertion(+), 59 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index c77efeac2425..938eaf9517e2 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -169,6 +169,7 @@ extern struct vm_struct *__get_vm_area_caller(unsigned long size,
 					unsigned long flags,
 					unsigned long start, unsigned long end,
 					const void *caller);
+void free_vm_area(struct vm_struct *area);
 extern struct vm_struct *remove_vm_area(const void *addr);
 extern struct vm_struct *find_vm_area(const void *addr);
 
@@ -204,10 +205,6 @@ static inline void set_vm_flush_reset_perms(void *addr)
 }
 #endif
 
-/* Allocate/destroy a 'vmalloc' VM area. */
-extern struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes);
-extern void free_vm_area(struct vm_struct *area);
-
 /* for /dev/kmem */
 extern long vread(char *buf, char *addr, unsigned long count);
 extern long vwrite(char *buf, char *addr, unsigned long count);
diff --git a/mm/nommu.c b/mm/nommu.c
index 0df7ca321314..0faf39b32cdb 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -354,13 +354,6 @@ void vm_unmap_aliases(void)
 }
 EXPORT_SYMBOL_GPL(vm_unmap_aliases);
 
-struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes)
-{
-	BUG();
-	return NULL;
-}
-EXPORT_SYMBOL_GPL(alloc_vm_area);
-
 void free_vm_area(struct vm_struct *area)
 {
 	BUG();
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index c6bf73a64db8..5c61bf85edb1 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -3083,54 +3083,6 @@ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
 }
 EXPORT_SYMBOL(remap_vmalloc_range);
 
-static int f(pte_t *pte, unsigned long addr, void *data)
-{
-	pte_t ***p = data;
-
-	if (p) {
-		*(*p) = pte;
-		(*p)++;
-	}
-	return 0;
-}
-
-/**
- * alloc_vm_area - allocate a range of kernel address space
- * @size:	   size of the area
- * @ptes:	   returns the PTEs for the address space
- *
- * Returns:	NULL on failure, vm_struct on success
- *
- * This function reserves a range of kernel address space, and
- * allocates pagetables to map that range.  No actual mappings
- * are created.
- *
- * If @ptes is non-NULL, pointers to the PTEs (in init_mm)
- * allocated for the VM area are returned.
- */
-struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes)
-{
-	struct vm_struct *area;
-
-	area = get_vm_area_caller(size, VM_IOREMAP,
-				__builtin_return_address(0));
-	if (area == NULL)
-		return NULL;
-
-	/*
-	 * This ensures that page tables are constructed for this region
-	 * of kernel virtual address space and mapped into init_mm.
-	 */
-	if (apply_to_page_range(&init_mm, (unsigned long)area->addr,
-				size, f, ptes ? &ptes : NULL)) {
-		free_vm_area(area);
-		return NULL;
-	}
-
-	return area;
-}
-EXPORT_SYMBOL_GPL(alloc_vm_area);
-
 void free_vm_area(struct vm_struct *area)
 {
 	struct vm_struct *ret;
-- 
cgit v1.2.3


From 695cebe58dcf3d9802cdfa9c327b5c7641a5914b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 20 Oct 2020 10:41:07 +0200
Subject: dma-mapping: move more functions to dma-map-ops.h

Due to a mismerge a bunch of prototypes that should have moved to
dma-map-ops.h are still in dma-mapping.h, fix that up.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/dma-map-ops.h | 23 +++++++++++++++++++++++
 include/linux/dma-mapping.h | 24 ------------------------
 kernel/dma/remap.c          |  2 +-
 3 files changed, 24 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 8029f7e04145..a5f89fc4d6df 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -203,6 +203,29 @@ static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma,
 }
 #endif /* CONFIG_DMA_DECLARE_COHERENT */
 
+int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs);
+int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs);
+struct page *dma_common_alloc_pages(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp);
+void dma_common_free_pages(struct device *dev, size_t size, struct page *vaddr,
+		dma_addr_t dma_handle, enum dma_data_direction dir);
+
+struct page **dma_common_find_pages(void *cpu_addr);
+void *dma_common_contiguous_remap(struct page *page, size_t size, pgprot_t prot,
+		const void *caller);
+void *dma_common_pages_remap(struct page **pages, size_t size, pgprot_t prot,
+		const void *caller);
+void dma_common_free_remap(void *cpu_addr, size_t size);
+
+struct page *dma_alloc_from_pool(struct device *dev, size_t size,
+		void **cpu_addr, gfp_t flags,
+		bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t));
+bool dma_free_from_pool(struct device *dev, void *start, size_t size);
+
 #ifdef CONFIG_ARCH_HAS_DMA_COHERENCE_H
 #include <asm/dma-coherence.h>
 #elif defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 3f029afdc9dc..956151052d45 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -389,30 +389,6 @@ static inline void dma_sync_sgtable_for_device(struct device *dev,
 #define dma_get_sgtable(d, t, v, h, s) dma_get_sgtable_attrs(d, t, v, h, s, 0)
 #define dma_mmap_coherent(d, v, c, h, s) dma_mmap_attrs(d, v, c, h, s, 0)
 
-extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
-		void *cpu_addr, dma_addr_t dma_addr, size_t size,
-		unsigned long attrs);
-struct page *dma_common_alloc_pages(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp);
-void dma_common_free_pages(struct device *dev, size_t size, struct page *vaddr,
-		dma_addr_t dma_handle, enum dma_data_direction dir);
-struct page **dma_common_find_pages(void *cpu_addr);
-void *dma_common_contiguous_remap(struct page *page, size_t size,
-			pgprot_t prot, const void *caller);
-
-void *dma_common_pages_remap(struct page **pages, size_t size,
-			pgprot_t prot, const void *caller);
-void dma_common_free_remap(void *cpu_addr, size_t size);
-
-struct page *dma_alloc_from_pool(struct device *dev, size_t size,
-		void **cpu_addr, gfp_t flags,
-		bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t));
-bool dma_free_from_pool(struct device *dev, void *start, size_t size);
-
-int
-dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr,
-		dma_addr_t dma_addr, size_t size, unsigned long attrs);
-
 static inline void *dma_alloc_coherent(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp)
 {
diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c
index 78b23f089cf1..905c3fa005f1 100644
--- a/kernel/dma/remap.c
+++ b/kernel/dma/remap.c
@@ -2,7 +2,7 @@
 /*
  * Copyright (c) 2014 The Linux Foundation
  */
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 
-- 
cgit v1.2.3


From cb3a92da231bcf55c243d00fa619ee36281b0001 Mon Sep 17 00:00:00 2001
From: Yufen Yu <yuyufen@huawei.com>
Date: Tue, 20 Oct 2020 05:22:56 -0400
Subject: block: remove unused members for io_context

After removing blk-sq code, there is no user of nr_batch_requests
and last_waited in kernel.

Signed-off-by: Yufen Yu <yuyufen@huawei.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/iocontext.h | 6 ------
 1 file changed, 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h
index 1dcd9198beb7..0a9dc40b7be8 100644
--- a/include/linux/iocontext.h
+++ b/include/linux/iocontext.h
@@ -106,12 +106,6 @@ struct io_context {
 
 	unsigned short ioprio;
 
-	/*
-	 * For request batching
-	 */
-	int nr_batch_requests;     /* Number of requests left in the batch */
-	unsigned long last_waited; /* Time last woken after wait for request */
-
 	struct radix_tree_root	icq_tree;
 	struct io_cq __rcu	*icq_hint;
 	struct hlist_head	icq_list;
-- 
cgit v1.2.3


From aa9c9b3f3f08cb0fda8a8139e6fb302c9a2e21ed Mon Sep 17 00:00:00 2001
From: Bean Huo <beanhuo@micron.com>
Date: Tue, 20 Oct 2020 17:00:27 +0200
Subject: PM: runtime: Fix typo in pm_runtime_set_active() helper comment

This patch is to fix typo in the comment of helper pm_runtime_set_active().

Signed-off-by: Bean Huo <beanhuo@micron.com>
[ rjw: Subject edit ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/pm_runtime.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index 6245caa18034..18b02dcc168e 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -479,7 +479,7 @@ static inline int pm_runtime_set_active(struct device *dev)
 }
 
 /**
- * pm_runtime_set_suspended - Set runtime PM status to "active".
+ * pm_runtime_set_suspended - Set runtime PM status to "suspended".
  * @dev: Target device.
  *
  * Set the runtime PM status of @dev to %RPM_SUSPENDED and ensure that
-- 
cgit v1.2.3


From 0cfcd405e758ba1d277e58436fb32f06888c3e41 Mon Sep 17 00:00:00 2001
From: Dai Ngo <dai.ngo@oracle.com>
Date: Sun, 18 Oct 2020 23:42:49 -0400
Subject: NFSv4.2: Fix NFS4ERR_STALE error when doing inter server copy

NFS_FS=y as dependency of CONFIG_NFSD_V4_2_INTER_SSC still have
build errors and some configs with NFSD=m to get NFS4ERR_STALE
error when doing inter server copy.

Added ops table in nfs_common for knfsd to access NFS client modules.

Fixes: 3ac3711adb88 ("NFSD: Fix NFS server build errors")
Signed-off-by: Dai Ngo <dai.ngo@oracle.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfs/nfs4file.c       | 38 ++++++++++++++++----
 fs/nfs/nfs4super.c      |  5 +++
 fs/nfs/super.c          | 17 +++++++++
 fs/nfs_common/Makefile  |  1 +
 fs/nfs_common/nfs_ssc.c | 94 +++++++++++++++++++++++++++++++++++++++++++++++++
 fs/nfsd/Kconfig         |  2 +-
 fs/nfsd/nfs4proc.c      |  3 +-
 include/linux/nfs_ssc.h | 67 +++++++++++++++++++++++++++++++++++
 8 files changed, 219 insertions(+), 8 deletions(-)
 create mode 100644 fs/nfs_common/nfs_ssc.c
 create mode 100644 include/linux/nfs_ssc.h

(limited to 'include/linux')

diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index fdfc77486ace..984938024011 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -9,6 +9,7 @@
 #include <linux/falloc.h>
 #include <linux/mount.h>
 #include <linux/nfs_fs.h>
+#include <linux/nfs_ssc.h>
 #include "delegation.h"
 #include "internal.h"
 #include "iostat.h"
@@ -314,9 +315,8 @@ out:
 static int read_name_gen = 1;
 #define SSC_READ_NAME_BODY "ssc_read_%d"
 
-struct file *
-nfs42_ssc_open(struct vfsmount *ss_mnt, struct nfs_fh *src_fh,
-		nfs4_stateid *stateid)
+static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt,
+		struct nfs_fh *src_fh, nfs4_stateid *stateid)
 {
 	struct nfs_fattr fattr;
 	struct file *filep, *res;
@@ -398,14 +398,40 @@ out_filep:
 	fput(filep);
 	goto out_free_name;
 }
-EXPORT_SYMBOL_GPL(nfs42_ssc_open);
-void nfs42_ssc_close(struct file *filep)
+
+static void __nfs42_ssc_close(struct file *filep)
 {
 	struct nfs_open_context *ctx = nfs_file_open_context(filep);
 
 	ctx->state->flags = 0;
 }
-EXPORT_SYMBOL_GPL(nfs42_ssc_close);
+
+static const struct nfs4_ssc_client_ops nfs4_ssc_clnt_ops_tbl = {
+	.sco_open = __nfs42_ssc_open,
+	.sco_close = __nfs42_ssc_close,
+};
+
+/**
+ * nfs42_ssc_register_ops - Wrapper to register NFS_V4 ops in nfs_common
+ *
+ * Return values:
+ *   None
+ */
+void nfs42_ssc_register_ops(void)
+{
+	nfs42_ssc_register(&nfs4_ssc_clnt_ops_tbl);
+}
+
+/**
+ * nfs42_ssc_unregister_ops - wrapper to un-register NFS_V4 ops in nfs_common
+ *
+ * Return values:
+ *   None.
+ */
+void nfs42_ssc_unregister_ops(void)
+{
+	nfs42_ssc_unregister(&nfs4_ssc_clnt_ops_tbl);
+}
 #endif /* CONFIG_NFS_V4_2 */
 
 const struct file_operations nfs4_file_operations = {
diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c
index 0c1ab846b83d..93f5c1678ec2 100644
--- a/fs/nfs/nfs4super.c
+++ b/fs/nfs/nfs4super.c
@@ -7,6 +7,7 @@
 #include <linux/mount.h>
 #include <linux/nfs4_mount.h>
 #include <linux/nfs_fs.h>
+#include <linux/nfs_ssc.h>
 #include "delegation.h"
 #include "internal.h"
 #include "nfs4_fs.h"
@@ -279,6 +280,9 @@ static int __init init_nfs_v4(void)
 	if (err)
 		goto out2;
 
+#ifdef CONFIG_NFS_V4_2
+	nfs42_ssc_register_ops();
+#endif
 	register_nfs_version(&nfs_v4);
 	return 0;
 out2:
@@ -297,6 +301,7 @@ static void __exit exit_nfs_v4(void)
 	unregister_nfs_version(&nfs_v4);
 #ifdef CONFIG_NFS_V4_2
 	nfs4_xattr_cache_exit();
+	nfs42_ssc_unregister_ops();
 #endif
 	nfs4_unregister_sysctl();
 	nfs_idmap_quit();
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 7a70287f21a2..f7dad8227a5f 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -57,6 +57,7 @@
 #include <linux/rcupdate.h>
 
 #include <linux/uaccess.h>
+#include <linux/nfs_ssc.h>
 
 #include "nfs4_fs.h"
 #include "callback.h"
@@ -85,6 +86,10 @@ const struct super_operations nfs_sops = {
 };
 EXPORT_SYMBOL_GPL(nfs_sops);
 
+static const struct nfs_ssc_client_ops nfs_ssc_clnt_ops_tbl = {
+	.sco_sb_deactive = nfs_sb_deactive,
+};
+
 #if IS_ENABLED(CONFIG_NFS_V4)
 static int __init register_nfs4_fs(void)
 {
@@ -106,6 +111,16 @@ static void unregister_nfs4_fs(void)
 }
 #endif
 
+static void nfs_ssc_register_ops(void)
+{
+	nfs_ssc_register(&nfs_ssc_clnt_ops_tbl);
+}
+
+static void nfs_ssc_unregister_ops(void)
+{
+	nfs_ssc_unregister(&nfs_ssc_clnt_ops_tbl);
+}
+
 static struct shrinker acl_shrinker = {
 	.count_objects	= nfs_access_cache_count,
 	.scan_objects	= nfs_access_cache_scan,
@@ -133,6 +148,7 @@ int __init register_nfs_fs(void)
 	ret = register_shrinker(&acl_shrinker);
 	if (ret < 0)
 		goto error_3;
+	nfs_ssc_register_ops();
 	return 0;
 error_3:
 	nfs_unregister_sysctl();
@@ -152,6 +168,7 @@ void __exit unregister_nfs_fs(void)
 	unregister_shrinker(&acl_shrinker);
 	nfs_unregister_sysctl();
 	unregister_nfs4_fs();
+	nfs_ssc_unregister_ops();
 	unregister_filesystem(&nfs_fs_type);
 }
 
diff --git a/fs/nfs_common/Makefile b/fs/nfs_common/Makefile
index 4bebe834c009..fa82f5aaa6d9 100644
--- a/fs/nfs_common/Makefile
+++ b/fs/nfs_common/Makefile
@@ -7,3 +7,4 @@ obj-$(CONFIG_NFS_ACL_SUPPORT) += nfs_acl.o
 nfs_acl-objs := nfsacl.o
 
 obj-$(CONFIG_GRACE_PERIOD) += grace.o
+obj-$(CONFIG_GRACE_PERIOD) += nfs_ssc.o
diff --git a/fs/nfs_common/nfs_ssc.c b/fs/nfs_common/nfs_ssc.c
new file mode 100644
index 000000000000..f43bbb373913
--- /dev/null
+++ b/fs/nfs_common/nfs_ssc.c
@@ -0,0 +1,94 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * fs/nfs_common/nfs_ssc_comm.c
+ *
+ * Helper for knfsd's SSC to access ops in NFS client modules
+ *
+ * Author: Dai Ngo <dai.ngo@oracle.com>
+ *
+ * Copyright (c) 2020, Oracle and/or its affiliates.
+ */
+
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/nfs_ssc.h>
+#include "../nfs/nfs4_fs.h"
+
+MODULE_LICENSE("GPL");
+
+struct nfs_ssc_client_ops_tbl nfs_ssc_client_tbl;
+EXPORT_SYMBOL_GPL(nfs_ssc_client_tbl);
+
+#ifdef CONFIG_NFS_V4_2
+/**
+ * nfs42_ssc_register - install the NFS_V4 client ops in the nfs_ssc_client_tbl
+ * @ops: NFS_V4 ops to be installed
+ *
+ * Return values:
+ *   None
+ */
+void nfs42_ssc_register(const struct nfs4_ssc_client_ops *ops)
+{
+	nfs_ssc_client_tbl.ssc_nfs4_ops = ops;
+}
+EXPORT_SYMBOL_GPL(nfs42_ssc_register);
+
+/**
+ * nfs42_ssc_unregister - uninstall the NFS_V4 client ops from
+ *				the nfs_ssc_client_tbl
+ * @ops: ops to be uninstalled
+ *
+ * Return values:
+ *   None
+ */
+void nfs42_ssc_unregister(const struct nfs4_ssc_client_ops *ops)
+{
+	if (nfs_ssc_client_tbl.ssc_nfs4_ops != ops)
+		return;
+
+	nfs_ssc_client_tbl.ssc_nfs4_ops = NULL;
+}
+EXPORT_SYMBOL_GPL(nfs42_ssc_unregister);
+#endif /* CONFIG_NFS_V4_2 */
+
+#ifdef CONFIG_NFS_V4_2
+/**
+ * nfs_ssc_register - install the NFS_FS client ops in the nfs_ssc_client_tbl
+ * @ops: NFS_FS ops to be installed
+ *
+ * Return values:
+ *   None
+ */
+void nfs_ssc_register(const struct nfs_ssc_client_ops *ops)
+{
+	nfs_ssc_client_tbl.ssc_nfs_ops = ops;
+}
+EXPORT_SYMBOL_GPL(nfs_ssc_register);
+
+/**
+ * nfs_ssc_unregister - uninstall the NFS_FS client ops from
+ *				the nfs_ssc_client_tbl
+ * @ops: ops to be uninstalled
+ *
+ * Return values:
+ *   None
+ */
+void nfs_ssc_unregister(const struct nfs_ssc_client_ops *ops)
+{
+	if (nfs_ssc_client_tbl.ssc_nfs_ops != ops)
+		return;
+	nfs_ssc_client_tbl.ssc_nfs_ops = NULL;
+}
+EXPORT_SYMBOL_GPL(nfs_ssc_unregister);
+
+#else
+void nfs_ssc_register(const struct nfs_ssc_client_ops *ops)
+{
+}
+EXPORT_SYMBOL_GPL(nfs_ssc_register);
+
+void nfs_ssc_unregister(const struct nfs_ssc_client_ops *ops)
+{
+}
+EXPORT_SYMBOL_GPL(nfs_ssc_unregister);
+#endif /* CONFIG_NFS_V4_2 */
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 9223e13c3051..dbbc583d6273 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -136,7 +136,7 @@ config NFSD_FLEXFILELAYOUT
 
 config NFSD_V4_2_INTER_SSC
 	bool "NFSv4.2 inter server to server COPY"
-	depends on NFSD_V4 && NFS_V4_1 && NFS_V4_2 && NFS_FS=y
+	depends on NFSD_V4 && NFS_V4_1 && NFS_V4_2
 	help
 	  This option enables support for NFSv4.2 inter server to
 	  server copy where the destination server calls the NFSv4.2
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 3dd69b6315c8..ad2fa1a8e7ad 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -38,6 +38,7 @@
 #include <linux/slab.h>
 #include <linux/kthread.h>
 #include <linux/sunrpc/addr.h>
+#include <linux/nfs_ssc.h>
 
 #include "idmap.h"
 #include "cache.h"
@@ -1247,7 +1248,7 @@ out_err:
 static void
 nfsd4_interssc_disconnect(struct vfsmount *ss_mnt)
 {
-	nfs_sb_deactive(ss_mnt->mnt_sb);
+	nfs_do_sb_deactive(ss_mnt->mnt_sb);
 	mntput(ss_mnt);
 }
 
diff --git a/include/linux/nfs_ssc.h b/include/linux/nfs_ssc.h
new file mode 100644
index 000000000000..f5ba0fbff72f
--- /dev/null
+++ b/include/linux/nfs_ssc.h
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * include/linux/nfs_ssc.h
+ *
+ * Author: Dai Ngo <dai.ngo@oracle.com>
+ *
+ * Copyright (c) 2020, Oracle and/or its affiliates.
+ */
+
+#include <linux/nfs_fs.h>
+
+extern struct nfs_ssc_client_ops_tbl nfs_ssc_client_tbl;
+
+/*
+ * NFS_V4
+ */
+struct nfs4_ssc_client_ops {
+	struct file *(*sco_open)(struct vfsmount *ss_mnt,
+		struct nfs_fh *src_fh, nfs4_stateid *stateid);
+	void (*sco_close)(struct file *filep);
+};
+
+/*
+ * NFS_FS
+ */
+struct nfs_ssc_client_ops {
+	void (*sco_sb_deactive)(struct super_block *sb);
+};
+
+struct nfs_ssc_client_ops_tbl {
+	const struct nfs4_ssc_client_ops *ssc_nfs4_ops;
+	const struct nfs_ssc_client_ops *ssc_nfs_ops;
+};
+
+extern void nfs42_ssc_register_ops(void);
+extern void nfs42_ssc_unregister_ops(void);
+
+extern void nfs42_ssc_register(const struct nfs4_ssc_client_ops *ops);
+extern void nfs42_ssc_unregister(const struct nfs4_ssc_client_ops *ops);
+
+#ifdef CONFIG_NFSD_V4_2_INTER_SSC
+static inline struct file *nfs42_ssc_open(struct vfsmount *ss_mnt,
+		struct nfs_fh *src_fh, nfs4_stateid *stateid)
+{
+	if (nfs_ssc_client_tbl.ssc_nfs4_ops)
+		return (*nfs_ssc_client_tbl.ssc_nfs4_ops->sco_open)(ss_mnt, src_fh, stateid);
+	return ERR_PTR(-EIO);
+}
+
+static inline void nfs42_ssc_close(struct file *filep)
+{
+	if (nfs_ssc_client_tbl.ssc_nfs4_ops)
+		(*nfs_ssc_client_tbl.ssc_nfs4_ops->sco_close)(filep);
+}
+#endif
+
+/*
+ * NFS_FS
+ */
+extern void nfs_ssc_register(const struct nfs_ssc_client_ops *ops);
+extern void nfs_ssc_unregister(const struct nfs_ssc_client_ops *ops);
+
+static inline void nfs_do_sb_deactive(struct super_block *sb)
+{
+	if (nfs_ssc_client_tbl.ssc_nfs_ops)
+		(*nfs_ssc_client_tbl.ssc_nfs_ops->sco_sb_deactive)(sb);
+}
-- 
cgit v1.2.3


From 0afa15e1a5294754066343cad24af5ec8edae96d Mon Sep 17 00:00:00 2001
From: Pierre Morel <pmorel@linux.ibm.com>
Date: Thu, 10 Sep 2020 10:53:49 +0200
Subject: virtio: let arch advertise guest's memory access restrictions

An architecture may restrict host access to guest memory,
e.g. IBM s390 Secure Execution or AMD SEV.

Provide a new Kconfig entry the architecture can select,
CONFIG_ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS, when it provides
the arch_has_restricted_virtio_memory_access callback to advertise
to VIRTIO common code when the architecture restricts memory access
from the host.

The common code can then fail the probe for any device where
VIRTIO_F_ACCESS_PLATFORM is required, but not set.

Signed-off-by: Pierre Morel <pmorel@linux.ibm.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Halil Pasic <pasic@linux.ibm.com>
Link: https://lore.kernel.org/r/1599728030-17085-2-git-send-email-pmorel@linux.ibm.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 drivers/virtio/Kconfig        |  6 ++++++
 drivers/virtio/virtio.c       | 15 +++++++++++++++
 include/linux/virtio_config.h | 10 ++++++++++
 3 files changed, 31 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
index 5c92e4a50882..ef2d49430800 100644
--- a/drivers/virtio/Kconfig
+++ b/drivers/virtio/Kconfig
@@ -6,6 +6,12 @@ config VIRTIO
 	  bus, such as CONFIG_VIRTIO_PCI, CONFIG_VIRTIO_MMIO, CONFIG_RPMSG
 	  or CONFIG_S390_GUEST.
 
+config ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS
+	bool
+	help
+	  This option is selected if the architecture may need to enforce
+	  VIRTIO_F_ACCESS_PLATFORM
+
 menuconfig VIRTIO_MENU
 	bool "Virtio drivers"
 	default y
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index a977e32a88f2..a2b3f12e10a2 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -176,6 +176,21 @@ int virtio_finalize_features(struct virtio_device *dev)
 	if (ret)
 		return ret;
 
+	ret = arch_has_restricted_virtio_memory_access();
+	if (ret) {
+		if (!virtio_has_feature(dev, VIRTIO_F_VERSION_1)) {
+			dev_warn(&dev->dev,
+				 "device must provide VIRTIO_F_VERSION_1\n");
+			return -ENODEV;
+		}
+
+		if (!virtio_has_feature(dev, VIRTIO_F_ACCESS_PLATFORM)) {
+			dev_warn(&dev->dev,
+				 "device must provide VIRTIO_F_ACCESS_PLATFORM\n");
+			return -ENODEV;
+		}
+	}
+
 	if (!virtio_has_feature(dev, VIRTIO_F_VERSION_1))
 		return 0;
 
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 8fe857e27ef3..3f697c8c8205 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -540,4 +540,14 @@ static inline void virtio_cwrite64(struct virtio_device *vdev,
 			virtio_cread_le((vdev), structname, member, ptr); \
 		_r;							\
 	})
+
+#ifdef CONFIG_ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS
+int arch_has_restricted_virtio_memory_access(void);
+#else
+static inline int arch_has_restricted_virtio_memory_access(void)
+{
+	return 0;
+}
+#endif /* CONFIG_ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS */
+
 #endif /* _LINUX_VIRTIO_CONFIG_H */
-- 
cgit v1.2.3


From 9e9eb226b91225fc199bbafc06f3cd70bfce0100 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Wed, 14 Oct 2020 11:26:46 -0700
Subject: KVM: Cache as_id in kvm_memory_slot

Cache the address space ID just like the slot ID.  It will be used in
order to fill in the dirty ring entries.

Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Suggested-by: Sean Christopherson <sean.j.christopherson@intel.com>
Reviewed-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20201014182700.2888246-7-bgardon@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/kvm_host.h | 1 +
 virt/kvm/kvm_main.c      | 6 ++++++
 2 files changed, 7 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 05e3c2fb3ef7..c6f45687ba89 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -346,6 +346,7 @@ struct kvm_memory_slot {
 	unsigned long userspace_addr;
 	u32 flags;
 	short id;
+	u16 as_id;
 };
 
 static inline unsigned long kvm_dirty_bitmap_bytes(struct kvm_memory_slot *memslot)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 68edd25dcb11..2e8539213125 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1247,6 +1247,11 @@ static int kvm_delete_memslot(struct kvm *kvm,
 
 	memset(&new, 0, sizeof(new));
 	new.id = old->id;
+	/*
+	 * This is only for debugging purpose; it should never be referenced
+	 * for a removed memslot.
+	 */
+	new.as_id = as_id;
 
 	r = kvm_set_memslot(kvm, mem, old, &new, as_id, KVM_MR_DELETE);
 	if (r)
@@ -1313,6 +1318,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	if (!mem->memory_size)
 		return kvm_delete_memslot(kvm, mem, &old, as_id);
 
+	new.as_id = as_id;
 	new.id = id;
 	new.base_gfn = mem->guest_phys_addr >> PAGE_SHIFT;
 	new.npages = mem->memory_size >> PAGE_SHIFT;
-- 
cgit v1.2.3


From ba452c9e996d8a4c347b32805f91abb70de5de7e Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@redhat.com>
Date: Tue, 20 Oct 2020 23:25:56 +0200
Subject: bpf: Fix bpf_redirect_neigh helper api to support supplying nexthop
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Based on the discussion in [0], update the bpf_redirect_neigh() helper to
accept an optional parameter specifying the nexthop information. This makes
it possible to combine bpf_fib_lookup() and bpf_redirect_neigh() without
incurring a duplicate FIB lookup - since the FIB lookup helper will return
the nexthop information even if no neighbour is present, this can simply
be passed on to bpf_redirect_neigh() if bpf_fib_lookup() returns
BPF_FIB_LKUP_RET_NO_NEIGH. Thus fix & extend it before helper API is frozen.

  [0] https://lore.kernel.org/bpf/393e17fc-d187-3a8d-2f0d-a627c7c63fca@iogearbox.net/

Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/bpf/160322915615.32199.1187570224032024535.stgit@toke.dk
---
 include/linux/filter.h         |   9 +++
 include/uapi/linux/bpf.h       |  22 ++++--
 net/core/filter.c              | 158 ++++++++++++++++++++++++++---------------
 scripts/bpf_helpers_doc.py     |   1 +
 tools/include/uapi/linux/bpf.h |  22 ++++--
 5 files changed, 145 insertions(+), 67 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 20fc24c9779a..72d62cbc1578 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -607,12 +607,21 @@ struct bpf_skb_data_end {
 	void *data_end;
 };
 
+struct bpf_nh_params {
+	u32 nh_family;
+	union {
+		u32 ipv4_nh;
+		struct in6_addr ipv6_nh;
+	};
+};
+
 struct bpf_redirect_info {
 	u32 flags;
 	u32 tgt_index;
 	void *tgt_value;
 	struct bpf_map *map;
 	u32 kern_flags;
+	struct bpf_nh_params nh;
 };
 
 DECLARE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index bf5a99d803e4..e6ceac3f7d62 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3677,15 +3677,19 @@ union bpf_attr {
  * 	Return
  * 		The id is returned or 0 in case the id could not be retrieved.
  *
- * long bpf_redirect_neigh(u32 ifindex, u64 flags)
+ * long bpf_redirect_neigh(u32 ifindex, struct bpf_redir_neigh *params, int plen, u64 flags)
  * 	Description
  * 		Redirect the packet to another net device of index *ifindex*
  * 		and fill in L2 addresses from neighboring subsystem. This helper
  * 		is somewhat similar to **bpf_redirect**\ (), except that it
  * 		populates L2 addresses as well, meaning, internally, the helper
- * 		performs a FIB lookup based on the skb's networking header to
- * 		get the address of the next hop and then relies on the neighbor
- * 		lookup for the L2 address of the nexthop.
+ * 		relies on the neighbor lookup for the L2 address of the nexthop.
+ *
+ * 		The helper will perform a FIB lookup based on the skb's
+ * 		networking header to get the address of the next hop, unless
+ * 		this is supplied by the caller in the *params* argument. The
+ * 		*plen* argument indicates the len of *params* and should be set
+ * 		to 0 if *params* is NULL.
  *
  * 		The *flags* argument is reserved and must be 0. The helper is
  * 		currently only supported for tc BPF program types, and enabled
@@ -4906,6 +4910,16 @@ struct bpf_fib_lookup {
 	__u8	dmac[6];     /* ETH_ALEN */
 };
 
+struct bpf_redir_neigh {
+	/* network family for lookup (AF_INET, AF_INET6) */
+	__u32 nh_family;
+	/* network address of nexthop; skips fib lookup to find gateway */
+	union {
+		__be32		ipv4_nh;
+		__u32		ipv6_nh[4];  /* in6_addr; network order */
+	};
+};
+
 enum bpf_task_fd_type {
 	BPF_FD_TYPE_RAW_TRACEPOINT,	/* tp name */
 	BPF_FD_TYPE_TRACEPOINT,		/* tp name */
diff --git a/net/core/filter.c b/net/core/filter.c
index c5e2a1c5fd8d..6d0fa65a4a46 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2165,12 +2165,12 @@ static int __bpf_redirect(struct sk_buff *skb, struct net_device *dev,
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
-static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb)
+static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb,
+			    struct net_device *dev, struct bpf_nh_params *nh)
 {
-	struct dst_entry *dst = skb_dst(skb);
-	struct net_device *dev = dst->dev;
 	u32 hh_len = LL_RESERVED_SPACE(dev);
 	const struct in6_addr *nexthop;
+	struct dst_entry *dst = NULL;
 	struct neighbour *neigh;
 
 	if (dev_xmit_recursion()) {
@@ -2196,8 +2196,13 @@ static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb)
 	}
 
 	rcu_read_lock_bh();
-	nexthop = rt6_nexthop(container_of(dst, struct rt6_info, dst),
-			      &ipv6_hdr(skb)->daddr);
+	if (!nh) {
+		dst = skb_dst(skb);
+		nexthop = rt6_nexthop(container_of(dst, struct rt6_info, dst),
+				      &ipv6_hdr(skb)->daddr);
+	} else {
+		nexthop = &nh->ipv6_nh;
+	}
 	neigh = ip_neigh_gw6(dev, nexthop);
 	if (likely(!IS_ERR(neigh))) {
 		int ret;
@@ -2210,36 +2215,43 @@ static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb)
 		return ret;
 	}
 	rcu_read_unlock_bh();
-	IP6_INC_STATS(dev_net(dst->dev),
-		      ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
+	if (dst)
+		IP6_INC_STATS(dev_net(dst->dev),
+			      ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
 out_drop:
 	kfree_skb(skb);
 	return -ENETDOWN;
 }
 
-static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev)
+static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev,
+				   struct bpf_nh_params *nh)
 {
 	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
 	struct net *net = dev_net(dev);
 	int err, ret = NET_XMIT_DROP;
-	struct dst_entry *dst;
-	struct flowi6 fl6 = {
-		.flowi6_flags	= FLOWI_FLAG_ANYSRC,
-		.flowi6_mark	= skb->mark,
-		.flowlabel	= ip6_flowinfo(ip6h),
-		.flowi6_oif	= dev->ifindex,
-		.flowi6_proto	= ip6h->nexthdr,
-		.daddr		= ip6h->daddr,
-		.saddr		= ip6h->saddr,
-	};
 
-	dst = ipv6_stub->ipv6_dst_lookup_flow(net, NULL, &fl6, NULL);
-	if (IS_ERR(dst))
-		goto out_drop;
+	if (!nh) {
+		struct dst_entry *dst;
+		struct flowi6 fl6 = {
+			.flowi6_flags = FLOWI_FLAG_ANYSRC,
+			.flowi6_mark  = skb->mark,
+			.flowlabel    = ip6_flowinfo(ip6h),
+			.flowi6_oif   = dev->ifindex,
+			.flowi6_proto = ip6h->nexthdr,
+			.daddr	      = ip6h->daddr,
+			.saddr	      = ip6h->saddr,
+		};
+
+		dst = ipv6_stub->ipv6_dst_lookup_flow(net, NULL, &fl6, NULL);
+		if (IS_ERR(dst))
+			goto out_drop;
 
-	skb_dst_set(skb, dst);
+		skb_dst_set(skb, dst);
+	} else if (nh->nh_family != AF_INET6) {
+		goto out_drop;
+	}
 
-	err = bpf_out_neigh_v6(net, skb);
+	err = bpf_out_neigh_v6(net, skb, dev, nh);
 	if (unlikely(net_xmit_eval(err)))
 		dev->stats.tx_errors++;
 	else
@@ -2252,7 +2264,8 @@ out_xmit:
 	return ret;
 }
 #else
-static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev)
+static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev,
+				   struct bpf_nh_params *nh)
 {
 	kfree_skb(skb);
 	return NET_XMIT_DROP;
@@ -2260,11 +2273,9 @@ static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev)
 #endif /* CONFIG_IPV6 */
 
 #if IS_ENABLED(CONFIG_INET)
-static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb)
+static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb,
+			    struct net_device *dev, struct bpf_nh_params *nh)
 {
-	struct dst_entry *dst = skb_dst(skb);
-	struct rtable *rt = container_of(dst, struct rtable, dst);
-	struct net_device *dev = dst->dev;
 	u32 hh_len = LL_RESERVED_SPACE(dev);
 	struct neighbour *neigh;
 	bool is_v6gw = false;
@@ -2292,7 +2303,21 @@ static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb)
 	}
 
 	rcu_read_lock_bh();
-	neigh = ip_neigh_for_gw(rt, skb, &is_v6gw);
+	if (!nh) {
+		struct dst_entry *dst = skb_dst(skb);
+		struct rtable *rt = container_of(dst, struct rtable, dst);
+
+		neigh = ip_neigh_for_gw(rt, skb, &is_v6gw);
+	} else if (nh->nh_family == AF_INET6) {
+		neigh = ip_neigh_gw6(dev, &nh->ipv6_nh);
+		is_v6gw = true;
+	} else if (nh->nh_family == AF_INET) {
+		neigh = ip_neigh_gw4(dev, nh->ipv4_nh);
+	} else {
+		rcu_read_unlock_bh();
+		goto out_drop;
+	}
+
 	if (likely(!IS_ERR(neigh))) {
 		int ret;
 
@@ -2309,33 +2334,37 @@ out_drop:
 	return -ENETDOWN;
 }
 
-static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev)
+static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev,
+				   struct bpf_nh_params *nh)
 {
 	const struct iphdr *ip4h = ip_hdr(skb);
 	struct net *net = dev_net(dev);
 	int err, ret = NET_XMIT_DROP;
-	struct rtable *rt;
-	struct flowi4 fl4 = {
-		.flowi4_flags	= FLOWI_FLAG_ANYSRC,
-		.flowi4_mark	= skb->mark,
-		.flowi4_tos	= RT_TOS(ip4h->tos),
-		.flowi4_oif	= dev->ifindex,
-		.flowi4_proto	= ip4h->protocol,
-		.daddr		= ip4h->daddr,
-		.saddr		= ip4h->saddr,
-	};
 
-	rt = ip_route_output_flow(net, &fl4, NULL);
-	if (IS_ERR(rt))
-		goto out_drop;
-	if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) {
-		ip_rt_put(rt);
-		goto out_drop;
-	}
+	if (!nh) {
+		struct flowi4 fl4 = {
+			.flowi4_flags = FLOWI_FLAG_ANYSRC,
+			.flowi4_mark  = skb->mark,
+			.flowi4_tos   = RT_TOS(ip4h->tos),
+			.flowi4_oif   = dev->ifindex,
+			.flowi4_proto = ip4h->protocol,
+			.daddr	      = ip4h->daddr,
+			.saddr	      = ip4h->saddr,
+		};
+		struct rtable *rt;
+
+		rt = ip_route_output_flow(net, &fl4, NULL);
+		if (IS_ERR(rt))
+			goto out_drop;
+		if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) {
+			ip_rt_put(rt);
+			goto out_drop;
+		}
 
-	skb_dst_set(skb, &rt->dst);
+		skb_dst_set(skb, &rt->dst);
+	}
 
-	err = bpf_out_neigh_v4(net, skb);
+	err = bpf_out_neigh_v4(net, skb, dev, nh);
 	if (unlikely(net_xmit_eval(err)))
 		dev->stats.tx_errors++;
 	else
@@ -2348,14 +2377,16 @@ out_xmit:
 	return ret;
 }
 #else
-static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev)
+static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev,
+				   struct bpf_nh_params *nh)
 {
 	kfree_skb(skb);
 	return NET_XMIT_DROP;
 }
 #endif /* CONFIG_INET */
 
-static int __bpf_redirect_neigh(struct sk_buff *skb, struct net_device *dev)
+static int __bpf_redirect_neigh(struct sk_buff *skb, struct net_device *dev,
+				struct bpf_nh_params *nh)
 {
 	struct ethhdr *ethh = eth_hdr(skb);
 
@@ -2370,9 +2401,9 @@ static int __bpf_redirect_neigh(struct sk_buff *skb, struct net_device *dev)
 	skb_reset_network_header(skb);
 
 	if (skb->protocol == htons(ETH_P_IP))
-		return __bpf_redirect_neigh_v4(skb, dev);
+		return __bpf_redirect_neigh_v4(skb, dev, nh);
 	else if (skb->protocol == htons(ETH_P_IPV6))
-		return __bpf_redirect_neigh_v6(skb, dev);
+		return __bpf_redirect_neigh_v6(skb, dev, nh);
 out:
 	kfree_skb(skb);
 	return -ENOTSUPP;
@@ -2382,7 +2413,8 @@ out:
 enum {
 	BPF_F_NEIGH	= (1ULL << 1),
 	BPF_F_PEER	= (1ULL << 2),
-#define BPF_F_REDIRECT_INTERNAL	(BPF_F_NEIGH | BPF_F_PEER)
+	BPF_F_NEXTHOP	= (1ULL << 3),
+#define BPF_F_REDIRECT_INTERNAL	(BPF_F_NEIGH | BPF_F_PEER | BPF_F_NEXTHOP)
 };
 
 BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags)
@@ -2455,7 +2487,8 @@ int skb_do_redirect(struct sk_buff *skb)
 		return -EAGAIN;
 	}
 	return flags & BPF_F_NEIGH ?
-	       __bpf_redirect_neigh(skb, dev) :
+	       __bpf_redirect_neigh(skb, dev, flags & BPF_F_NEXTHOP ?
+				    &ri->nh : NULL) :
 	       __bpf_redirect(skb, dev, flags);
 out_drop:
 	kfree_skb(skb);
@@ -2504,16 +2537,21 @@ static const struct bpf_func_proto bpf_redirect_peer_proto = {
 	.arg2_type      = ARG_ANYTHING,
 };
 
-BPF_CALL_2(bpf_redirect_neigh, u32, ifindex, u64, flags)
+BPF_CALL_4(bpf_redirect_neigh, u32, ifindex, struct bpf_redir_neigh *, params,
+	   int, plen, u64, flags)
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 
-	if (unlikely(flags))
+	if (unlikely((plen && plen < sizeof(*params)) || flags))
 		return TC_ACT_SHOT;
 
-	ri->flags = BPF_F_NEIGH;
+	ri->flags = BPF_F_NEIGH | (plen ? BPF_F_NEXTHOP : 0);
 	ri->tgt_index = ifindex;
 
+	BUILD_BUG_ON(sizeof(struct bpf_redir_neigh) != sizeof(struct bpf_nh_params));
+	if (plen)
+		memcpy(&ri->nh, params, sizeof(ri->nh));
+
 	return TC_ACT_REDIRECT;
 }
 
@@ -2522,7 +2560,9 @@ static const struct bpf_func_proto bpf_redirect_neigh_proto = {
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_ANYTHING,
-	.arg2_type	= ARG_ANYTHING,
+	.arg2_type      = ARG_PTR_TO_MEM_OR_NULL,
+	.arg3_type      = ARG_CONST_SIZE_OR_ZERO,
+	.arg4_type	= ARG_ANYTHING,
 };
 
 BPF_CALL_2(bpf_msg_apply_bytes, struct sk_msg *, msg, u32, bytes)
diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py
index 7d86fdd190be..6769caae142f 100755
--- a/scripts/bpf_helpers_doc.py
+++ b/scripts/bpf_helpers_doc.py
@@ -453,6 +453,7 @@ class PrinterHelpers(Printer):
             'struct bpf_perf_event_data',
             'struct bpf_perf_event_value',
             'struct bpf_pidns_info',
+            'struct bpf_redir_neigh',
             'struct bpf_sk_lookup',
             'struct bpf_sock',
             'struct bpf_sock_addr',
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index bf5a99d803e4..e6ceac3f7d62 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3677,15 +3677,19 @@ union bpf_attr {
  * 	Return
  * 		The id is returned or 0 in case the id could not be retrieved.
  *
- * long bpf_redirect_neigh(u32 ifindex, u64 flags)
+ * long bpf_redirect_neigh(u32 ifindex, struct bpf_redir_neigh *params, int plen, u64 flags)
  * 	Description
  * 		Redirect the packet to another net device of index *ifindex*
  * 		and fill in L2 addresses from neighboring subsystem. This helper
  * 		is somewhat similar to **bpf_redirect**\ (), except that it
  * 		populates L2 addresses as well, meaning, internally, the helper
- * 		performs a FIB lookup based on the skb's networking header to
- * 		get the address of the next hop and then relies on the neighbor
- * 		lookup for the L2 address of the nexthop.
+ * 		relies on the neighbor lookup for the L2 address of the nexthop.
+ *
+ * 		The helper will perform a FIB lookup based on the skb's
+ * 		networking header to get the address of the next hop, unless
+ * 		this is supplied by the caller in the *params* argument. The
+ * 		*plen* argument indicates the len of *params* and should be set
+ * 		to 0 if *params* is NULL.
  *
  * 		The *flags* argument is reserved and must be 0. The helper is
  * 		currently only supported for tc BPF program types, and enabled
@@ -4906,6 +4910,16 @@ struct bpf_fib_lookup {
 	__u8	dmac[6];     /* ETH_ALEN */
 };
 
+struct bpf_redir_neigh {
+	/* network family for lookup (AF_INET, AF_INET6) */
+	__u32 nh_family;
+	/* network address of nexthop; skips fib lookup to find gateway */
+	union {
+		__be32		ipv4_nh;
+		__u32		ipv6_nh[4];  /* in6_addr; network order */
+	};
+};
+
 enum bpf_task_fd_type {
 	BPF_FD_TYPE_RAW_TRACEPOINT,	/* tp name */
 	BPF_FD_TYPE_TRACEPOINT,		/* tp name */
-- 
cgit v1.2.3


From ebfe3c5183733f784264450a41646a482f964e5e Mon Sep 17 00:00:00 2001
From: Di Zhu <zhudi21@huawei.com>
Date: Wed, 21 Oct 2020 10:00:53 +0800
Subject: rtnetlink: fix data overflow in rtnl_calcit()

"ip addr show" command execute error when we have a physical
network card with a large number of VFs

The return value of if_nlmsg_size() in rtnl_calcit() will exceed
range of u16 data type when any network cards has a larger number of
VFs. rtnl_vfinfo_size() will significant increase needed dump size when
the value of num_vfs is larger.

Eventually we get a wrong value of min_ifinfo_dump_size because of overflow
which decides the memory size needed by netlink dump and netlink_dump()
will return -EMSGSIZE because of not enough memory was allocated.

So fix it by promoting  min_dump_alloc data type to u32 to
avoid whole netlink message size overflow and it's also align
with the data type of struct netlink_callback{}.min_dump_alloc
which is assigned by return value of rtnl_calcit()

Signed-off-by: Di Zhu <zhudi21@huawei.com>
Link: https://lore.kernel.org/r/20201021020053.1401-1-zhudi21@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netlink.h |  2 +-
 net/core/rtnetlink.c    | 13 ++++++-------
 2 files changed, 7 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index 666cd0390699..9f118771e248 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -240,7 +240,7 @@ struct netlink_dump_control {
 	int (*done)(struct netlink_callback *);
 	void *data;
 	struct module *module;
-	u16 min_dump_alloc;
+	u32 min_dump_alloc;
 };
 
 int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 68e0682450c6..7d7223691783 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3709,13 +3709,13 @@ static int rtnl_dellinkprop(struct sk_buff *skb, struct nlmsghdr *nlh,
 	return rtnl_linkprop(RTM_DELLINKPROP, skb, nlh, extack);
 }
 
-static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh)
+static u32 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
-	struct net_device *dev;
+	size_t min_ifinfo_dump_size = 0;
 	struct nlattr *tb[IFLA_MAX+1];
 	u32 ext_filter_mask = 0;
-	u16 min_ifinfo_dump_size = 0;
+	struct net_device *dev;
 	int hdrlen;
 
 	/* Same kernel<->userspace interface hack as in rtnl_dump_ifinfo. */
@@ -3735,9 +3735,8 @@ static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh)
 	 */
 	rcu_read_lock();
 	for_each_netdev_rcu(net, dev) {
-		min_ifinfo_dump_size = max_t(u16, min_ifinfo_dump_size,
-					     if_nlmsg_size(dev,
-						           ext_filter_mask));
+		min_ifinfo_dump_size = max(min_ifinfo_dump_size,
+					   if_nlmsg_size(dev, ext_filter_mask));
 	}
 	rcu_read_unlock();
 
@@ -5494,7 +5493,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) {
 		struct sock *rtnl;
 		rtnl_dumpit_func dumpit;
-		u16 min_dump_alloc = 0;
+		u32 min_dump_alloc = 0;
 
 		link = rtnl_get_link(family, type);
 		if (!link || !link->dumpit) {
-- 
cgit v1.2.3


From 995a3ed67fc8c0e3301a770016fb66f1bbf15ec8 Mon Sep 17 00:00:00 2001
From: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Date: Thu, 15 Oct 2020 13:37:54 -0700
Subject: ext4: add fast_commit feature and handling for extended mount options

We are running out of mount option bits. Add handling for using
s_mount_opt2. Add ext4 and jbd2 fast commit feature flag and also add
ability to turn off the fast commit feature in Ext4.

Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Link: https://lore.kernel.org/r/20201015203802.3597742-3-harshadshirwadkar@gmail.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/ext4.h       |  4 ++++
 fs/ext4/super.c      | 27 ++++++++++++++++++++++-----
 include/linux/jbd2.h |  5 ++++-
 3 files changed, 30 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 1879531a119f..02d7dc378505 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1213,6 +1213,8 @@ struct ext4_inode_info {
 #define EXT4_MOUNT2_EXPLICIT_JOURNAL_CHECKSUM	0x00000008 /* User explicitly
 						specified journal checksum */
 
+#define EXT4_MOUNT2_JOURNAL_FAST_COMMIT	0x00000010 /* Journal fast commit */
+
 #define clear_opt(sb, opt)		EXT4_SB(sb)->s_mount_opt &= \
 						~EXT4_MOUNT_##opt
 #define set_opt(sb, opt)		EXT4_SB(sb)->s_mount_opt |= \
@@ -1813,6 +1815,7 @@ static inline bool ext4_verity_in_progress(struct inode *inode)
 #define EXT4_FEATURE_COMPAT_RESIZE_INODE	0x0010
 #define EXT4_FEATURE_COMPAT_DIR_INDEX		0x0020
 #define EXT4_FEATURE_COMPAT_SPARSE_SUPER2	0x0200
+#define EXT4_FEATURE_COMPAT_FAST_COMMIT		0x0400
 #define EXT4_FEATURE_COMPAT_STABLE_INODES	0x0800
 
 #define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER	0x0001
@@ -1915,6 +1918,7 @@ EXT4_FEATURE_COMPAT_FUNCS(xattr,		EXT_ATTR)
 EXT4_FEATURE_COMPAT_FUNCS(resize_inode,		RESIZE_INODE)
 EXT4_FEATURE_COMPAT_FUNCS(dir_index,		DIR_INDEX)
 EXT4_FEATURE_COMPAT_FUNCS(sparse_super2,	SPARSE_SUPER2)
+EXT4_FEATURE_COMPAT_FUNCS(fast_commit,		FAST_COMMIT)
 EXT4_FEATURE_COMPAT_FUNCS(stable_inodes,	STABLE_INODES)
 
 EXT4_FEATURE_RO_COMPAT_FUNCS(sparse_super,	SPARSE_SUPER)
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index f997fc95cc31..66423c598b70 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1709,7 +1709,7 @@ enum {
 	Opt_dioread_nolock, Opt_dioread_lock,
 	Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable,
 	Opt_max_dir_size_kb, Opt_nojournal_checksum, Opt_nombcache,
-	Opt_prefetch_block_bitmaps,
+	Opt_prefetch_block_bitmaps, Opt_no_fc,
 };
 
 static const match_table_t tokens = {
@@ -1796,6 +1796,7 @@ static const match_table_t tokens = {
 	{Opt_init_itable, "init_itable=%u"},
 	{Opt_init_itable, "init_itable"},
 	{Opt_noinit_itable, "noinit_itable"},
+	{Opt_no_fc, "no_fc"},
 	{Opt_max_dir_size_kb, "max_dir_size_kb=%u"},
 	{Opt_test_dummy_encryption, "test_dummy_encryption=%s"},
 	{Opt_test_dummy_encryption, "test_dummy_encryption"},
@@ -1922,6 +1923,7 @@ static int clear_qf_name(struct super_block *sb, int qtype)
 #define MOPT_EXT4_ONLY	(MOPT_NO_EXT2 | MOPT_NO_EXT3)
 #define MOPT_STRING	0x0400
 #define MOPT_SKIP	0x0800
+#define	MOPT_2		0x1000
 
 static const struct mount_opts {
 	int	token;
@@ -2022,6 +2024,8 @@ static const struct mount_opts {
 	{Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET},
 	{Opt_prefetch_block_bitmaps, EXT4_MOUNT_PREFETCH_BLOCK_BITMAPS,
 	 MOPT_SET},
+	{Opt_no_fc, EXT4_MOUNT2_JOURNAL_FAST_COMMIT,
+	 MOPT_CLEAR | MOPT_2 | MOPT_EXT4_ONLY},
 	{Opt_err, 0, 0}
 };
 
@@ -2398,10 +2402,17 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 			WARN_ON(1);
 			return -1;
 		}
-		if (arg != 0)
-			sbi->s_mount_opt |= m->mount_opt;
-		else
-			sbi->s_mount_opt &= ~m->mount_opt;
+		if (m->flags & MOPT_2) {
+			if (arg != 0)
+				sbi->s_mount_opt2 |= m->mount_opt;
+			else
+				sbi->s_mount_opt2 &= ~m->mount_opt;
+		} else {
+			if (arg != 0)
+				sbi->s_mount_opt |= m->mount_opt;
+			else
+				sbi->s_mount_opt &= ~m->mount_opt;
+		}
 	}
 	return 1;
 }
@@ -2618,6 +2629,9 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb,
 		SEQ_OPTS_PUTS("dax=inode");
 	}
 
+	if (test_opt2(sb, JOURNAL_FAST_COMMIT))
+		SEQ_OPTS_PUTS("fast_commit");
+
 	ext4_show_quota_options(seq, sb);
 	return 0;
 }
@@ -4121,6 +4135,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 #ifdef CONFIG_EXT4_FS_POSIX_ACL
 	set_opt(sb, POSIX_ACL);
 #endif
+	if (ext4_has_feature_fast_commit(sb))
+		set_opt2(sb, JOURNAL_FAST_COMMIT);
 	/* don't forget to enable journal_csum when metadata_csum is enabled. */
 	if (ext4_has_metadata_csum(sb))
 		set_opt(sb, JOURNAL_CHECKSUM);
@@ -4777,6 +4793,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		sbi->s_def_mount_opt &= ~EXT4_MOUNT_JOURNAL_CHECKSUM;
 		clear_opt(sb, JOURNAL_CHECKSUM);
 		clear_opt(sb, DATA_FLAGS);
+		clear_opt2(sb, JOURNAL_FAST_COMMIT);
 		sbi->s_journal = NULL;
 		needs_recovery = 0;
 		goto no_journal;
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 04afa6dcd60d..0685cc95e501 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -289,6 +289,7 @@ typedef struct journal_superblock_s
 #define JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT	0x00000004
 #define JBD2_FEATURE_INCOMPAT_CSUM_V2		0x00000008
 #define JBD2_FEATURE_INCOMPAT_CSUM_V3		0x00000010
+#define JBD2_FEATURE_INCOMPAT_FAST_COMMIT	0x00000020
 
 /* See "journal feature predicate functions" below */
 
@@ -299,7 +300,8 @@ typedef struct journal_superblock_s
 					JBD2_FEATURE_INCOMPAT_64BIT | \
 					JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | \
 					JBD2_FEATURE_INCOMPAT_CSUM_V2 | \
-					JBD2_FEATURE_INCOMPAT_CSUM_V3)
+					JBD2_FEATURE_INCOMPAT_CSUM_V3 | \
+					JBD2_FEATURE_INCOMPAT_FAST_COMMIT)
 
 #ifdef __KERNEL__
 
@@ -1263,6 +1265,7 @@ JBD2_FEATURE_INCOMPAT_FUNCS(64bit,		64BIT)
 JBD2_FEATURE_INCOMPAT_FUNCS(async_commit,	ASYNC_COMMIT)
 JBD2_FEATURE_INCOMPAT_FUNCS(csum2,		CSUM_V2)
 JBD2_FEATURE_INCOMPAT_FUNCS(csum3,		CSUM_V3)
+JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit,	FAST_COMMIT)
 
 /*
  * Journal flag definitions
-- 
cgit v1.2.3


From 6866d7b3f2bb4f011041ba54c98b1584497fe2fd Mon Sep 17 00:00:00 2001
From: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Date: Thu, 15 Oct 2020 13:37:55 -0700
Subject: ext4 / jbd2: add fast commit initialization

This patch adds fast commit area trackers in the journal_t
structure. These are initialized via the jbd2_fc_init() routine that
this patch adds. This patch also adds ext4/fast_commit.c and
ext4/fast_commit.h files for fast commit code that will be added in
subsequent patches in this series.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Link: https://lore.kernel.org/r/20201015203802.3597742-4-harshadshirwadkar@gmail.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/Makefile      |  2 +-
 fs/ext4/ext4.h        |  4 ++++
 fs/ext4/fast_commit.c | 20 +++++++++++++++++++
 fs/ext4/fast_commit.h |  9 +++++++++
 fs/ext4/super.c       |  1 +
 fs/jbd2/journal.c     | 53 ++++++++++++++++++++++++++++++++++++++++++++++-----
 include/linux/jbd2.h  | 39 +++++++++++++++++++++++++++++++++++++
 7 files changed, 122 insertions(+), 6 deletions(-)
 create mode 100644 fs/ext4/fast_commit.c
 create mode 100644 fs/ext4/fast_commit.h

(limited to 'include/linux')

diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile
index 2e42f47a7f98..49e7af6cc93f 100644
--- a/fs/ext4/Makefile
+++ b/fs/ext4/Makefile
@@ -10,7 +10,7 @@ ext4-y	:= balloc.o bitmap.o block_validity.o dir.o ext4_jbd2.o extents.o \
 		indirect.o inline.o inode.o ioctl.o mballoc.o migrate.o \
 		mmp.o move_extent.o namei.o page-io.o readpage.o resize.o \
 		super.o symlink.o sysfs.o xattr.o xattr_hurd.o xattr_trusted.o \
-		xattr_user.o
+		xattr_user.o fast_commit.o
 
 ext4-$(CONFIG_EXT4_FS_POSIX_ACL)	+= acl.o
 ext4-$(CONFIG_EXT4_FS_SECURITY)		+= xattr_security.o
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 02d7dc378505..2c412d32db0f 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -963,6 +963,7 @@ do {									       \
 #endif /* defined(__KERNEL__) || defined(__linux__) */
 
 #include "extents_status.h"
+#include "fast_commit.h"
 
 /*
  * Lock subclasses for i_data_sem in the ext4_inode_info structure.
@@ -2678,6 +2679,9 @@ extern int ext4_init_inode_table(struct super_block *sb,
 				 ext4_group_t group, int barrier);
 extern void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate);
 
+/* fast_commit.c */
+
+void ext4_fc_init(struct super_block *sb, journal_t *journal);
 /* mballoc.c */
 extern const struct seq_operations ext4_mb_seq_groups_ops;
 extern long ext4_mb_stats;
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
new file mode 100644
index 000000000000..0dad8bdb1253
--- /dev/null
+++ b/fs/ext4/fast_commit.c
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * fs/ext4/fast_commit.c
+ *
+ * Written by Harshad Shirwadkar <harshadshirwadkar@gmail.com>
+ *
+ * Ext4 fast commits routines.
+ */
+#include "ext4_jbd2.h"
+
+void ext4_fc_init(struct super_block *sb, journal_t *journal)
+{
+	if (!test_opt2(sb, JOURNAL_FAST_COMMIT))
+		return;
+	if (jbd2_fc_init(journal, EXT4_NUM_FC_BLKS)) {
+		pr_warn("Error while enabling fast commits, turning off.");
+		ext4_clear_feature_fast_commit(sb);
+	}
+}
diff --git a/fs/ext4/fast_commit.h b/fs/ext4/fast_commit.h
new file mode 100644
index 000000000000..8362bf5e6e00
--- /dev/null
+++ b/fs/ext4/fast_commit.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __FAST_COMMIT_H__
+#define __FAST_COMMIT_H__
+
+/* Number of blocks in journal area to allocate for fast commits */
+#define EXT4_NUM_FC_BLKS		256
+
+#endif /* __FAST_COMMIT_H__ */
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 66423c598b70..41da649ccaea 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -5170,6 +5170,7 @@ static void ext4_init_journal_params(struct super_block *sb, journal_t *journal)
 	journal->j_commit_interval = sbi->s_commit_interval;
 	journal->j_min_batch_time = sbi->s_min_batch_time;
 	journal->j_max_batch_time = sbi->s_max_batch_time;
+	ext4_fc_init(sb, journal);
 
 	write_lock(&journal->j_state_lock);
 	if (test_opt(sb, BARRIER))
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index c0600405e7a2..4497bfbac527 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1181,6 +1181,14 @@ static journal_t *journal_init_common(struct block_device *bdev,
 	if (!journal->j_wbuf)
 		goto err_cleanup;
 
+	if (journal->j_fc_wbufsize > 0) {
+		journal->j_fc_wbuf = kmalloc_array(journal->j_fc_wbufsize,
+					sizeof(struct buffer_head *),
+					GFP_KERNEL);
+		if (!journal->j_fc_wbuf)
+			goto err_cleanup;
+	}
+
 	bh = getblk_unmovable(journal->j_dev, start, journal->j_blocksize);
 	if (!bh) {
 		pr_err("%s: Cannot get buffer for journal superblock\n",
@@ -1194,11 +1202,23 @@ static journal_t *journal_init_common(struct block_device *bdev,
 
 err_cleanup:
 	kfree(journal->j_wbuf);
+	kfree(journal->j_fc_wbuf);
 	jbd2_journal_destroy_revoke(journal);
 	kfree(journal);
 	return NULL;
 }
 
+int jbd2_fc_init(journal_t *journal, int num_fc_blks)
+{
+	journal->j_fc_wbufsize = num_fc_blks;
+	journal->j_fc_wbuf = kmalloc_array(journal->j_fc_wbufsize,
+				sizeof(struct buffer_head *), GFP_KERNEL);
+	if (!journal->j_fc_wbuf)
+		return -ENOMEM;
+	return 0;
+}
+EXPORT_SYMBOL(jbd2_fc_init);
+
 /* jbd2_journal_init_dev and jbd2_journal_init_inode:
  *
  * Create a journal structure assigned some fixed set of disk blocks to
@@ -1316,11 +1336,20 @@ static int journal_reset(journal_t *journal)
 	}
 
 	journal->j_first = first;
-	journal->j_last = last;
 
-	journal->j_head = first;
-	journal->j_tail = first;
-	journal->j_free = last - first;
+	if (jbd2_has_feature_fast_commit(journal) &&
+	    journal->j_fc_wbufsize > 0) {
+		journal->j_fc_last = last;
+		journal->j_last = last - journal->j_fc_wbufsize;
+		journal->j_fc_first = journal->j_last + 1;
+		journal->j_fc_off = 0;
+	} else {
+		journal->j_last = last;
+	}
+
+	journal->j_head = journal->j_first;
+	journal->j_tail = journal->j_first;
+	journal->j_free = journal->j_last - journal->j_first;
 
 	journal->j_tail_sequence = journal->j_transaction_sequence;
 	journal->j_commit_sequence = journal->j_transaction_sequence - 1;
@@ -1665,9 +1694,18 @@ static int load_superblock(journal_t *journal)
 	journal->j_tail_sequence = be32_to_cpu(sb->s_sequence);
 	journal->j_tail = be32_to_cpu(sb->s_start);
 	journal->j_first = be32_to_cpu(sb->s_first);
-	journal->j_last = be32_to_cpu(sb->s_maxlen);
 	journal->j_errno = be32_to_cpu(sb->s_errno);
 
+	if (jbd2_has_feature_fast_commit(journal) &&
+	    journal->j_fc_wbufsize > 0) {
+		journal->j_fc_last = be32_to_cpu(sb->s_maxlen);
+		journal->j_last = journal->j_fc_last - journal->j_fc_wbufsize;
+		journal->j_fc_first = journal->j_last + 1;
+		journal->j_fc_off = 0;
+	} else {
+		journal->j_last = be32_to_cpu(sb->s_maxlen);
+	}
+
 	return 0;
 }
 
@@ -1728,6 +1766,9 @@ int jbd2_journal_load(journal_t *journal)
 	 */
 	journal->j_flags &= ~JBD2_ABORT;
 
+	if (journal->j_fc_wbufsize > 0)
+		jbd2_journal_set_features(journal, 0, 0,
+					  JBD2_FEATURE_INCOMPAT_FAST_COMMIT);
 	/* OK, we've finished with the dynamic journal bits:
 	 * reinitialise the dynamic contents of the superblock in memory
 	 * and reset them on disk. */
@@ -1811,6 +1852,8 @@ int jbd2_journal_destroy(journal_t *journal)
 		jbd2_journal_destroy_revoke(journal);
 	if (journal->j_chksum_driver)
 		crypto_free_shash(journal->j_chksum_driver);
+	if (journal->j_fc_wbufsize > 0)
+		kfree(journal->j_fc_wbuf);
 	kfree(journal->j_wbuf);
 	kfree(journal);
 
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 0685cc95e501..008629b4d615 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -918,6 +918,30 @@ struct journal_s
 	 */
 	unsigned long		j_last;
 
+	/**
+	 * @j_fc_first:
+	 *
+	 * The block number of the first fast commit block in the journal
+	 * [j_state_lock].
+	 */
+	unsigned long		j_fc_first;
+
+	/**
+	 * @j_fc_off:
+	 *
+	 * Number of fast commit blocks currently allocated.
+	 * [j_state_lock].
+	 */
+	unsigned long		j_fc_off;
+
+	/**
+	 * @j_fc_last:
+	 *
+	 * The block number one beyond the last fast commit block in the journal
+	 * [j_state_lock].
+	 */
+	unsigned long		j_fc_last;
+
 	/**
 	 * @j_dev: Device where we store the journal.
 	 */
@@ -1068,6 +1092,12 @@ struct journal_s
 	 */
 	struct buffer_head	**j_wbuf;
 
+	/**
+	 * @j_fc_wbuf: Array of fast commit bhs for
+	 * jbd2_journal_commit_transaction.
+	 */
+	struct buffer_head	**j_fc_wbuf;
+
 	/**
 	 * @j_wbufsize:
 	 *
@@ -1075,6 +1105,13 @@ struct journal_s
 	 */
 	int			j_wbufsize;
 
+	/**
+	 * @j_fc_wbufsize:
+	 *
+	 * Size of @j_fc_wbuf array.
+	 */
+	int			j_fc_wbufsize;
+
 	/**
 	 * @j_last_sync_writer:
 	 *
@@ -1535,6 +1572,8 @@ void __jbd2_log_wait_for_space(journal_t *journal);
 extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *);
 extern int jbd2_cleanup_journal_tail(journal_t *);
 
+/* Fast commit related APIs */
+int jbd2_fc_init(journal_t *journal, int num_fc_blks);
 /*
  * is_journal_abort
  *
-- 
cgit v1.2.3


From ff780b91efe901b8eecd8114785abae5341820ad Mon Sep 17 00:00:00 2001
From: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Date: Thu, 15 Oct 2020 13:37:56 -0700
Subject: jbd2: add fast commit machinery

This functions adds necessary APIs needed in JBD2 layer for fast
commits.

Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Link: https://lore.kernel.org/r/20201015203802.3597742-5-harshadshirwadkar@gmail.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/fast_commit.c |   8 +++
 fs/jbd2/commit.c      |  44 ++++++++++++
 fs/jbd2/journal.c     | 190 +++++++++++++++++++++++++++++++++++++++++++++++++-
 include/linux/jbd2.h  |  27 +++++++
 4 files changed, 268 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index 0dad8bdb1253..f2d11b4c6b62 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -8,11 +8,19 @@
  * Ext4 fast commits routines.
  */
 #include "ext4_jbd2.h"
+/*
+ * Fast commit cleanup routine. This is called after every fast commit and
+ * full commit. full is true if we are called after a full commit.
+ */
+static void ext4_fc_cleanup(journal_t *journal, int full)
+{
+}
 
 void ext4_fc_init(struct super_block *sb, journal_t *journal)
 {
 	if (!test_opt2(sb, JOURNAL_FAST_COMMIT))
 		return;
+	journal->j_fc_cleanup_callback = ext4_fc_cleanup;
 	if (jbd2_fc_init(journal, EXT4_NUM_FC_BLKS)) {
 		pr_warn("Error while enabling fast commits, turning off.");
 		ext4_clear_feature_fast_commit(sb);
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 6252b4c50666..fa688e163a80 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -206,6 +206,30 @@ int jbd2_journal_submit_inode_data_buffers(struct jbd2_inode *jinode)
 	return generic_writepages(mapping, &wbc);
 }
 
+/* Send all the data buffers related to an inode */
+int jbd2_submit_inode_data(struct jbd2_inode *jinode)
+{
+
+	if (!jinode || !(jinode->i_flags & JI_WRITE_DATA))
+		return 0;
+
+	trace_jbd2_submit_inode_data(jinode->i_vfs_inode);
+	return jbd2_journal_submit_inode_data_buffers(jinode);
+
+}
+EXPORT_SYMBOL(jbd2_submit_inode_data);
+
+int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode)
+{
+	if (!jinode || !(jinode->i_flags & JI_WAIT_DATA) ||
+		!jinode->i_vfs_inode || !jinode->i_vfs_inode->i_mapping)
+		return 0;
+	return filemap_fdatawait_range_keep_errors(
+		jinode->i_vfs_inode->i_mapping, jinode->i_dirty_start,
+		jinode->i_dirty_end);
+}
+EXPORT_SYMBOL(jbd2_wait_inode_data);
+
 /*
  * Submit all the data buffers of inode associated with the transaction to
  * disk.
@@ -415,6 +439,20 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	J_ASSERT(journal->j_running_transaction != NULL);
 	J_ASSERT(journal->j_committing_transaction == NULL);
 
+	write_lock(&journal->j_state_lock);
+	journal->j_flags |= JBD2_FULL_COMMIT_ONGOING;
+	while (journal->j_flags & JBD2_FAST_COMMIT_ONGOING) {
+		DEFINE_WAIT(wait);
+
+		prepare_to_wait(&journal->j_fc_wait, &wait,
+				TASK_UNINTERRUPTIBLE);
+		write_unlock(&journal->j_state_lock);
+		schedule();
+		write_lock(&journal->j_state_lock);
+		finish_wait(&journal->j_fc_wait, &wait);
+	}
+	write_unlock(&journal->j_state_lock);
+
 	commit_transaction = journal->j_running_transaction;
 
 	trace_jbd2_start_commit(journal, commit_transaction);
@@ -422,6 +460,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 			commit_transaction->t_tid);
 
 	write_lock(&journal->j_state_lock);
+	journal->j_fc_off = 0;
 	J_ASSERT(commit_transaction->t_state == T_RUNNING);
 	commit_transaction->t_state = T_LOCKED;
 
@@ -1121,12 +1160,16 @@ restart_loop:
 
 	if (journal->j_commit_callback)
 		journal->j_commit_callback(journal, commit_transaction);
+	if (journal->j_fc_cleanup_callback)
+		journal->j_fc_cleanup_callback(journal, 1);
 
 	trace_jbd2_end_commit(journal, commit_transaction);
 	jbd_debug(1, "JBD2: commit %d complete, head %d\n",
 		  journal->j_commit_sequence, journal->j_tail_sequence);
 
 	write_lock(&journal->j_state_lock);
+	journal->j_flags &= ~JBD2_FULL_COMMIT_ONGOING;
+	journal->j_flags &= ~JBD2_FAST_COMMIT_ONGOING;
 	spin_lock(&journal->j_list_lock);
 	commit_transaction->t_state = T_FINISHED;
 	/* Check if the transaction can be dropped now that we are finished */
@@ -1138,6 +1181,7 @@ restart_loop:
 	spin_unlock(&journal->j_list_lock);
 	write_unlock(&journal->j_state_lock);
 	wake_up(&journal->j_wait_done_commit);
+	wake_up(&journal->j_fc_wait);
 
 	/*
 	 * Calculate overall stats
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 4497bfbac527..0c7c42bd530f 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -159,7 +159,9 @@ static void commit_timeout(struct timer_list *t)
  *
  * 1) COMMIT:  Every so often we need to commit the current state of the
  *    filesystem to disk.  The journal thread is responsible for writing
- *    all of the metadata buffers to disk.
+ *    all of the metadata buffers to disk. If a fast commit is ongoing
+ *    journal thread waits until it's done and then continues from
+ *    there on.
  *
  * 2) CHECKPOINT: We cannot reuse a used section of the log file until all
  *    of the data in that part of the log has been rewritten elsewhere on
@@ -716,6 +718,75 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid)
 	return err;
 }
 
+/*
+ * Start a fast commit. If there's an ongoing fast or full commit wait for
+ * it to complete. Returns 0 if a new fast commit was started. Returns -EALREADY
+ * if a fast commit is not needed, either because there's an already a commit
+ * going on or this tid has already been committed. Returns -EINVAL if no jbd2
+ * commit has yet been performed.
+ */
+int jbd2_fc_begin_commit(journal_t *journal, tid_t tid)
+{
+	/*
+	 * Fast commits only allowed if at least one full commit has
+	 * been processed.
+	 */
+	if (!journal->j_stats.ts_tid)
+		return -EINVAL;
+
+	if (tid <= journal->j_commit_sequence)
+		return -EALREADY;
+
+	write_lock(&journal->j_state_lock);
+	if (journal->j_flags & JBD2_FULL_COMMIT_ONGOING ||
+	    (journal->j_flags & JBD2_FAST_COMMIT_ONGOING)) {
+		DEFINE_WAIT(wait);
+
+		prepare_to_wait(&journal->j_fc_wait, &wait,
+				TASK_UNINTERRUPTIBLE);
+		write_unlock(&journal->j_state_lock);
+		schedule();
+		finish_wait(&journal->j_fc_wait, &wait);
+		return -EALREADY;
+	}
+	journal->j_flags |= JBD2_FAST_COMMIT_ONGOING;
+	write_unlock(&journal->j_state_lock);
+
+	return 0;
+}
+EXPORT_SYMBOL(jbd2_fc_begin_commit);
+
+/*
+ * Stop a fast commit. If fallback is set, this function starts commit of
+ * TID tid before any other fast commit can start.
+ */
+static int __jbd2_fc_end_commit(journal_t *journal, tid_t tid, bool fallback)
+{
+	if (journal->j_fc_cleanup_callback)
+		journal->j_fc_cleanup_callback(journal, 0);
+	write_lock(&journal->j_state_lock);
+	journal->j_flags &= ~JBD2_FAST_COMMIT_ONGOING;
+	if (fallback)
+		journal->j_flags |= JBD2_FULL_COMMIT_ONGOING;
+	write_unlock(&journal->j_state_lock);
+	wake_up(&journal->j_fc_wait);
+	if (fallback)
+		return jbd2_complete_transaction(journal, tid);
+	return 0;
+}
+
+int jbd2_fc_end_commit(journal_t *journal)
+{
+	return __jbd2_fc_end_commit(journal, 0, 0);
+}
+EXPORT_SYMBOL(jbd2_fc_end_commit);
+
+int jbd2_fc_end_commit_fallback(journal_t *journal, tid_t tid)
+{
+	return __jbd2_fc_end_commit(journal, tid, 1);
+}
+EXPORT_SYMBOL(jbd2_fc_end_commit_fallback);
+
 /* Return 1 when transaction with given tid has already committed. */
 int jbd2_transaction_committed(journal_t *journal, tid_t tid)
 {
@@ -784,6 +855,110 @@ int jbd2_journal_next_log_block(journal_t *journal, unsigned long long *retp)
 	return jbd2_journal_bmap(journal, blocknr, retp);
 }
 
+/* Map one fast commit buffer for use by the file system */
+int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out)
+{
+	unsigned long long pblock;
+	unsigned long blocknr;
+	int ret = 0;
+	struct buffer_head *bh;
+	int fc_off;
+
+	*bh_out = NULL;
+	write_lock(&journal->j_state_lock);
+
+	if (journal->j_fc_off + journal->j_fc_first < journal->j_fc_last) {
+		fc_off = journal->j_fc_off;
+		blocknr = journal->j_fc_first + fc_off;
+		journal->j_fc_off++;
+	} else {
+		ret = -EINVAL;
+	}
+	write_unlock(&journal->j_state_lock);
+
+	if (ret)
+		return ret;
+
+	ret = jbd2_journal_bmap(journal, blocknr, &pblock);
+	if (ret)
+		return ret;
+
+	bh = __getblk(journal->j_dev, pblock, journal->j_blocksize);
+	if (!bh)
+		return -ENOMEM;
+
+	lock_buffer(bh);
+
+	clear_buffer_uptodate(bh);
+	set_buffer_dirty(bh);
+	unlock_buffer(bh);
+	journal->j_fc_wbuf[fc_off] = bh;
+
+	*bh_out = bh;
+
+	return 0;
+}
+EXPORT_SYMBOL(jbd2_fc_get_buf);
+
+/*
+ * Wait on fast commit buffers that were allocated by jbd2_fc_get_buf
+ * for completion.
+ */
+int jbd2_fc_wait_bufs(journal_t *journal, int num_blks)
+{
+	struct buffer_head *bh;
+	int i, j_fc_off;
+
+	read_lock(&journal->j_state_lock);
+	j_fc_off = journal->j_fc_off;
+	read_unlock(&journal->j_state_lock);
+
+	/*
+	 * Wait in reverse order to minimize chances of us being woken up before
+	 * all IOs have completed
+	 */
+	for (i = j_fc_off - 1; i >= j_fc_off - num_blks; i--) {
+		bh = journal->j_fc_wbuf[i];
+		wait_on_buffer(bh);
+		put_bh(bh);
+		journal->j_fc_wbuf[i] = NULL;
+		if (unlikely(!buffer_uptodate(bh)))
+			return -EIO;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(jbd2_fc_wait_bufs);
+
+/*
+ * Wait on fast commit buffers that were allocated by jbd2_fc_get_buf
+ * for completion.
+ */
+int jbd2_fc_release_bufs(journal_t *journal)
+{
+	struct buffer_head *bh;
+	int i, j_fc_off;
+
+	read_lock(&journal->j_state_lock);
+	j_fc_off = journal->j_fc_off;
+	read_unlock(&journal->j_state_lock);
+
+	/*
+	 * Wait in reverse order to minimize chances of us being woken up before
+	 * all IOs have completed
+	 */
+	for (i = j_fc_off - 1; i >= 0; i--) {
+		bh = journal->j_fc_wbuf[i];
+		if (!bh)
+			break;
+		put_bh(bh);
+		journal->j_fc_wbuf[i] = NULL;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(jbd2_fc_release_bufs);
+
 /*
  * Conversion of logical to physical block numbers for the journal
  *
@@ -1142,6 +1317,7 @@ static journal_t *journal_init_common(struct block_device *bdev,
 	init_waitqueue_head(&journal->j_wait_commit);
 	init_waitqueue_head(&journal->j_wait_updates);
 	init_waitqueue_head(&journal->j_wait_reserved);
+	init_waitqueue_head(&journal->j_fc_wait);
 	mutex_init(&journal->j_abort_mutex);
 	mutex_init(&journal->j_barrier);
 	mutex_init(&journal->j_checkpoint_mutex);
@@ -1495,6 +1671,7 @@ out:
 static void jbd2_mark_journal_empty(journal_t *journal, int write_op)
 {
 	journal_superblock_t *sb = journal->j_superblock;
+	bool had_fast_commit = false;
 
 	BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex));
 	lock_buffer(journal->j_sb_buffer);
@@ -1508,9 +1685,20 @@ static void jbd2_mark_journal_empty(journal_t *journal, int write_op)
 
 	sb->s_sequence = cpu_to_be32(journal->j_tail_sequence);
 	sb->s_start    = cpu_to_be32(0);
+	if (jbd2_has_feature_fast_commit(journal)) {
+		/*
+		 * When journal is clean, no need to commit fast commit flag and
+		 * make file system incompatible with older kernels.
+		 */
+		jbd2_clear_feature_fast_commit(journal);
+		had_fast_commit = true;
+	}
 
 	jbd2_write_superblock(journal, write_op);
 
+	if (had_fast_commit)
+		jbd2_set_feature_fast_commit(journal);
+
 	/* Log is no longer empty */
 	write_lock(&journal->j_state_lock);
 	journal->j_flags |= JBD2_FLUSHED;
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 008629b4d615..a009d9b9c620 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -861,6 +861,13 @@ struct journal_s
 	 */
 	wait_queue_head_t	j_wait_reserved;
 
+	/**
+	 * @j_fc_wait:
+	 *
+	 * Wait queue to wait for completion of async fast commits.
+	 */
+	wait_queue_head_t	j_fc_wait;
+
 	/**
 	 * @j_checkpoint_mutex:
 	 *
@@ -1232,6 +1239,15 @@ struct journal_s
 	 */
 	struct lockdep_map	j_trans_commit_map;
 #endif
+
+	/**
+	 * @j_fc_cleanup_callback:
+	 *
+	 * Clean-up after fast commit or full commit. JBD2 calls this function
+	 * after every commit operation.
+	 */
+	void (*j_fc_cleanup_callback)(struct journal_s *journal, int);
+
 };
 
 #define jbd2_might_wait_for_commit(j) \
@@ -1316,6 +1332,8 @@ JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit,	FAST_COMMIT)
 #define JBD2_ABORT_ON_SYNCDATA_ERR	0x040	/* Abort the journal on file
 						 * data write error in ordered
 						 * mode */
+#define JBD2_FAST_COMMIT_ONGOING	0x100	/* Fast commit is ongoing */
+#define JBD2_FULL_COMMIT_ONGOING	0x200	/* Full commit is ongoing */
 
 /*
  * Function declarations for the journaling transaction and buffer
@@ -1574,6 +1592,15 @@ extern int jbd2_cleanup_journal_tail(journal_t *);
 
 /* Fast commit related APIs */
 int jbd2_fc_init(journal_t *journal, int num_fc_blks);
+int jbd2_fc_begin_commit(journal_t *journal, tid_t tid);
+int jbd2_fc_end_commit(journal_t *journal);
+int jbd2_fc_end_commit_fallback(journal_t *journal, tid_t tid);
+int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out);
+int jbd2_submit_inode_data(struct jbd2_inode *jinode);
+int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode);
+int jbd2_fc_wait_bufs(journal_t *journal, int num_blks);
+int jbd2_fc_release_bufs(journal_t *journal);
+
 /*
  * is_journal_abort
  *
-- 
cgit v1.2.3


From 5b849b5f96b47d82b5a432d8b91a8ad260e1de46 Mon Sep 17 00:00:00 2001
From: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Date: Thu, 15 Oct 2020 13:37:58 -0700
Subject: jbd2: fast commit recovery path

This patch adds fast commit recovery support in JBD2.

Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Link: https://lore.kernel.org/r/20201015203802.3597742-7-harshadshirwadkar@gmail.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/fast_commit.c | 15 ++++++++++++++
 fs/jbd2/recovery.c    | 57 +++++++++++++++++++++++++++++++++++++++++++++++----
 include/linux/jbd2.h  | 20 ++++++++++++++++++
 3 files changed, 88 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index 79e947c43198..888d9d217d5b 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -1188,8 +1188,23 @@ static void ext4_fc_cleanup(journal_t *journal, int full)
 	trace_ext4_fc_stats(sb);
 }
 
+/*
+ * Main recovery path entry point.
+ */
+static int ext4_fc_replay(journal_t *journal, struct buffer_head *bh,
+				enum passtype pass, int off, tid_t expected_tid)
+{
+	return 0;
+}
+
 void ext4_fc_init(struct super_block *sb, journal_t *journal)
 {
+	/*
+	 * We set replay callback even if fast commit disabled because we may
+	 * could still have fast commit blocks that need to be replayed even if
+	 * fast commit has now been turned off.
+	 */
+	journal->j_fc_replay_callback = ext4_fc_replay;
 	if (!test_opt2(sb, JOURNAL_FAST_COMMIT))
 		return;
 	journal->j_fc_cleanup_callback = ext4_fc_cleanup;
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index fb134c7a12c8..eb2606133cd8 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -35,7 +35,6 @@ struct recovery_info
 	int		nr_revoke_hits;
 };
 
-enum passtype {PASS_SCAN, PASS_REVOKE, PASS_REPLAY};
 static int do_one_pass(journal_t *journal,
 				struct recovery_info *info, enum passtype pass);
 static int scan_revoke_records(journal_t *, struct buffer_head *,
@@ -225,10 +224,51 @@ static int count_tags(journal_t *journal, struct buffer_head *bh)
 /* Make sure we wrap around the log correctly! */
 #define wrap(journal, var)						\
 do {									\
-	if (var >= (journal)->j_last)					\
-		var -= ((journal)->j_last - (journal)->j_first);	\
+	unsigned long _wrap_last =					\
+		jbd2_has_feature_fast_commit(journal) ?			\
+			(journal)->j_fc_last : (journal)->j_last;	\
+									\
+	if (var >= _wrap_last)						\
+		var -= (_wrap_last - (journal)->j_first);		\
 } while (0)
 
+static int fc_do_one_pass(journal_t *journal,
+			  struct recovery_info *info, enum passtype pass)
+{
+	unsigned int expected_commit_id = info->end_transaction;
+	unsigned long next_fc_block;
+	struct buffer_head *bh;
+	int err = 0;
+
+	next_fc_block = journal->j_fc_first;
+	if (!journal->j_fc_replay_callback)
+		return 0;
+
+	while (next_fc_block <= journal->j_fc_last) {
+		jbd_debug(3, "Fast commit replay: next block %ld",
+			  next_fc_block);
+		err = jread(&bh, journal, next_fc_block);
+		if (err) {
+			jbd_debug(3, "Fast commit replay: read error");
+			break;
+		}
+
+		jbd_debug(3, "Processing fast commit blk with seq %d");
+		err = journal->j_fc_replay_callback(journal, bh, pass,
+					next_fc_block - journal->j_fc_first,
+					expected_commit_id);
+		next_fc_block++;
+		if (err < 0 || err == JBD2_FC_REPLAY_STOP)
+			break;
+		err = 0;
+	}
+
+	if (err)
+		jbd_debug(3, "Fast commit replay failed, err = %d\n", err);
+
+	return err;
+}
+
 /**
  * jbd2_journal_recover - recovers a on-disk journal
  * @journal: the journal to recover
@@ -472,7 +512,9 @@ static int do_one_pass(journal_t *journal,
 				break;
 
 		jbd_debug(2, "Scanning for sequence ID %u at %lu/%lu\n",
-			  next_commit_ID, next_log_block, journal->j_last);
+			  next_commit_ID, next_log_block,
+			  jbd2_has_feature_fast_commit(journal) ?
+			  journal->j_fc_last : journal->j_last);
 
 		/* Skip over each chunk of the transaction looking
 		 * either the next descriptor block or the final commit
@@ -834,6 +876,13 @@ static int do_one_pass(journal_t *journal,
 				success = -EIO;
 		}
 	}
+
+	if (jbd2_has_feature_fast_commit(journal) &&  pass != PASS_REVOKE) {
+		err = fc_do_one_pass(journal, info, pass);
+		if (err)
+			success = err;
+	}
+
 	if (block_error && success == 0)
 		success = -EIO;
 	return success;
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index a009d9b9c620..fb3d71ad6eea 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -751,6 +751,11 @@ jbd2_time_diff(unsigned long start, unsigned long end)
 
 #define JBD2_NR_BATCH	64
 
+enum passtype {PASS_SCAN, PASS_REVOKE, PASS_REPLAY};
+
+#define JBD2_FC_REPLAY_STOP	0
+#define JBD2_FC_REPLAY_CONTINUE	1
+
 /**
  * struct journal_s - The journal_s type is the concrete type associated with
  *     journal_t.
@@ -1248,6 +1253,21 @@ struct journal_s
 	 */
 	void (*j_fc_cleanup_callback)(struct journal_s *journal, int);
 
+	/*
+	 * @j_fc_replay_callback:
+	 *
+	 * File-system specific function that performs replay of a fast
+	 * commit. JBD2 calls this function for each fast commit block found in
+	 * the journal. This function should return JBD2_FC_REPLAY_CONTINUE
+	 * to indicate that the block was processed correctly and more fast
+	 * commit replay should continue. Return value of JBD2_FC_REPLAY_STOP
+	 * indicates the end of replay (no more blocks remaining). A negative
+	 * return value indicates error.
+	 */
+	int (*j_fc_replay_callback)(struct journal_s *journal,
+				    struct buffer_head *bh,
+				    enum passtype pass, int off,
+				    tid_t expected_commit_id);
 };
 
 #define jbd2_might_wait_for_commit(j) \
-- 
cgit v1.2.3


From ee6e00c868221f5f7d0b6eb4e8379a148e26bc20 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 22 Oct 2020 14:15:51 -0600
Subject: splice: change exported internal do_splice() helper to take kernel
 offset

With the set_fs change, we can no longer rely on copy_{to,from}_user()
accepting a kernel pointer, and it was bad form to do so anyway. Clean
this up and change the internal helper that io_uring uses to deal with
kernel pointers instead. This puts the offset copy in/out in __do_splice()
instead, which just calls the same helper.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/splice.c            | 63 +++++++++++++++++++++++++++++++++++++++-----------
 include/linux/splice.h |  4 ++--
 2 files changed, 52 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/fs/splice.c b/fs/splice.c
index 70cc52af780b..d9305af930d8 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -1107,9 +1107,8 @@ static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe,
 /*
  * Determine where to splice to/from.
  */
-long do_splice(struct file *in, loff_t __user *off_in,
-		struct file *out, loff_t __user *off_out,
-		size_t len, unsigned int flags)
+long do_splice(struct file *in, loff_t *off_in, struct file *out,
+	       loff_t *off_out, size_t len, unsigned int flags)
 {
 	struct pipe_inode_info *ipipe;
 	struct pipe_inode_info *opipe;
@@ -1143,8 +1142,7 @@ long do_splice(struct file *in, loff_t __user *off_in,
 		if (off_out) {
 			if (!(out->f_mode & FMODE_PWRITE))
 				return -EINVAL;
-			if (copy_from_user(&offset, off_out, sizeof(loff_t)))
-				return -EFAULT;
+			offset = *off_out;
 		} else {
 			offset = out->f_pos;
 		}
@@ -1165,8 +1163,8 @@ long do_splice(struct file *in, loff_t __user *off_in,
 
 		if (!off_out)
 			out->f_pos = offset;
-		else if (copy_to_user(off_out, &offset, sizeof(loff_t)))
-			ret = -EFAULT;
+		else
+			*off_out = offset;
 
 		return ret;
 	}
@@ -1177,8 +1175,7 @@ long do_splice(struct file *in, loff_t __user *off_in,
 		if (off_in) {
 			if (!(in->f_mode & FMODE_PREAD))
 				return -EINVAL;
-			if (copy_from_user(&offset, off_in, sizeof(loff_t)))
-				return -EFAULT;
+			offset = *off_in;
 		} else {
 			offset = in->f_pos;
 		}
@@ -1202,8 +1199,8 @@ long do_splice(struct file *in, loff_t __user *off_in,
 			wakeup_pipe_readers(opipe);
 		if (!off_in)
 			in->f_pos = offset;
-		else if (copy_to_user(off_in, &offset, sizeof(loff_t)))
-			ret = -EFAULT;
+		else
+			*off_in = offset;
 
 		return ret;
 	}
@@ -1211,6 +1208,46 @@ long do_splice(struct file *in, loff_t __user *off_in,
 	return -EINVAL;
 }
 
+static long __do_splice(struct file *in, loff_t __user *off_in,
+			struct file *out, loff_t __user *off_out,
+			size_t len, unsigned int flags)
+{
+	struct pipe_inode_info *ipipe;
+	struct pipe_inode_info *opipe;
+	loff_t offset, *__off_in = NULL, *__off_out = NULL;
+	long ret;
+
+	ipipe = get_pipe_info(in, true);
+	opipe = get_pipe_info(out, true);
+
+	if (ipipe && off_in)
+		return -ESPIPE;
+	if (opipe && off_out)
+		return -ESPIPE;
+
+	if (off_out) {
+		if (copy_from_user(&offset, off_out, sizeof(loff_t)))
+			return -EFAULT;
+		__off_out = &offset;
+	}
+	if (off_in) {
+		if (copy_from_user(&offset, off_in, sizeof(loff_t)))
+			return -EFAULT;
+		__off_in = &offset;
+	}
+
+	ret = do_splice(in, __off_in, out, __off_out, len, flags);
+	if (ret < 0)
+		return ret;
+
+	if (__off_out && copy_to_user(off_out, __off_out, sizeof(loff_t)))
+		return -EFAULT;
+	if (__off_in && copy_to_user(off_in, __off_in, sizeof(loff_t)))
+		return -EFAULT;
+
+	return ret;
+}
+
 static int iter_to_pipe(struct iov_iter *from,
 			struct pipe_inode_info *pipe,
 			unsigned flags)
@@ -1405,8 +1442,8 @@ SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in,
 	if (in.file) {
 		out = fdget(fd_out);
 		if (out.file) {
-			error = do_splice(in.file, off_in, out.file, off_out,
-					  len, flags);
+			error = __do_splice(in.file, off_in, out.file, off_out,
+						len, flags);
 			fdput(out);
 		}
 		fdput(in);
diff --git a/include/linux/splice.h b/include/linux/splice.h
index 5c47013f708e..a55179fd60fc 100644
--- a/include/linux/splice.h
+++ b/include/linux/splice.h
@@ -78,8 +78,8 @@ extern ssize_t add_to_pipe(struct pipe_inode_info *,
 			      struct pipe_buffer *);
 extern ssize_t splice_direct_to_actor(struct file *, struct splice_desc *,
 				      splice_direct_actor *);
-extern long do_splice(struct file *in, loff_t __user *off_in,
-		      struct file *out, loff_t __user *off_out,
+extern long do_splice(struct file *in, loff_t *off_in,
+		      struct file *out, loff_t *off_out,
 		      size_t len, unsigned int flags);
 
 extern long do_tee(struct file *in, struct file *out, size_t len,
-- 
cgit v1.2.3


From 879bc2d27904354b98ca295b6168718e045c4aa2 Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Mon, 19 Oct 2020 16:57:50 +0200
Subject: hil/parisc: Disable HIL driver when it gets stuck

When starting a HP machine with HIL driver but without an HIL keyboard
or HIL mouse attached, it may happen that data written to the HIL loop
gets stuck (e.g. because the transaction queue is full).  Usually one
will then have to reboot the machine because all you see is and endless
output of:
 Transaction add failed: transaction already queued?

In the higher layers hp_sdc_enqueue_transaction() is called to queued up
a HIL packet. This function returns an error code, and this patch adds
the necessary checks for this return code and disables the HIL driver if
further packets can't be sent.

Tested on a HP 730 and a HP 715/64 machine.

Signed-off-by: Helge Deller <deller@gmx.de>
Cc: <stable@vger.kernel.org>
---
 drivers/input/serio/hil_mlc.c    | 21 ++++++++++++++++++---
 drivers/input/serio/hp_sdc_mlc.c |  8 ++++----
 include/linux/hil_mlc.h          |  2 +-
 3 files changed, 23 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/input/serio/hil_mlc.c b/drivers/input/serio/hil_mlc.c
index 65f4e9d62a67..d36e89d6fc54 100644
--- a/drivers/input/serio/hil_mlc.c
+++ b/drivers/input/serio/hil_mlc.c
@@ -74,7 +74,7 @@ EXPORT_SYMBOL(hil_mlc_unregister);
 static LIST_HEAD(hil_mlcs);
 static DEFINE_RWLOCK(hil_mlcs_lock);
 static struct timer_list	hil_mlcs_kicker;
-static int			hil_mlcs_probe;
+static int			hil_mlcs_probe, hil_mlc_stop;
 
 static void hil_mlcs_process(unsigned long unused);
 static DECLARE_TASKLET_DISABLED_OLD(hil_mlcs_tasklet, hil_mlcs_process);
@@ -702,9 +702,13 @@ static int hilse_donode(hil_mlc *mlc)
 		if (!mlc->ostarted) {
 			mlc->ostarted = 1;
 			mlc->opacket = pack;
-			mlc->out(mlc);
+			rc = mlc->out(mlc);
 			nextidx = HILSEN_DOZE;
 			write_unlock_irqrestore(&mlc->lock, flags);
+			if (rc) {
+				hil_mlc_stop = 1;
+				return 1;
+			}
 			break;
 		}
 		mlc->ostarted = 0;
@@ -715,8 +719,13 @@ static int hilse_donode(hil_mlc *mlc)
 
 	case HILSE_CTS:
 		write_lock_irqsave(&mlc->lock, flags);
-		nextidx = mlc->cts(mlc) ? node->bad : node->good;
+		rc = mlc->cts(mlc);
+		nextidx = rc ? node->bad : node->good;
 		write_unlock_irqrestore(&mlc->lock, flags);
+		if (rc) {
+			hil_mlc_stop = 1;
+			return 1;
+		}
 		break;
 
 	default:
@@ -780,6 +789,12 @@ static void hil_mlcs_process(unsigned long unused)
 
 static void hil_mlcs_timer(struct timer_list *unused)
 {
+	if (hil_mlc_stop) {
+		/* could not send packet - stop immediately. */
+		pr_warn(PREFIX "HIL seems stuck - Disabling HIL MLC.\n");
+		return;
+	}
+
 	hil_mlcs_probe = 1;
 	tasklet_schedule(&hil_mlcs_tasklet);
 	/* Re-insert the periodic task. */
diff --git a/drivers/input/serio/hp_sdc_mlc.c b/drivers/input/serio/hp_sdc_mlc.c
index 232d30c825bd..3e85e9039374 100644
--- a/drivers/input/serio/hp_sdc_mlc.c
+++ b/drivers/input/serio/hp_sdc_mlc.c
@@ -210,7 +210,7 @@ static int hp_sdc_mlc_cts(hil_mlc *mlc)
 	priv->tseq[2] = 1;
 	priv->tseq[3] = 0;
 	priv->tseq[4] = 0;
-	__hp_sdc_enqueue_transaction(&priv->trans);
+	return __hp_sdc_enqueue_transaction(&priv->trans);
  busy:
 	return 1;
  done:
@@ -219,7 +219,7 @@ static int hp_sdc_mlc_cts(hil_mlc *mlc)
 	return 0;
 }
 
-static void hp_sdc_mlc_out(hil_mlc *mlc)
+static int hp_sdc_mlc_out(hil_mlc *mlc)
 {
 	struct hp_sdc_mlc_priv_s *priv;
 
@@ -234,7 +234,7 @@ static void hp_sdc_mlc_out(hil_mlc *mlc)
  do_data:
 	if (priv->emtestmode) {
 		up(&mlc->osem);
-		return;
+		return 0;
 	}
 	/* Shouldn't be sending commands when loop may be busy */
 	BUG_ON(down_trylock(&mlc->csem));
@@ -296,7 +296,7 @@ static void hp_sdc_mlc_out(hil_mlc *mlc)
 		BUG_ON(down_trylock(&mlc->csem));
 	}
  enqueue:
-	hp_sdc_enqueue_transaction(&priv->trans);
+	return hp_sdc_enqueue_transaction(&priv->trans);
 }
 
 static int __init hp_sdc_mlc_init(void)
diff --git a/include/linux/hil_mlc.h b/include/linux/hil_mlc.h
index 774f7d3b8f6a..369221fd5518 100644
--- a/include/linux/hil_mlc.h
+++ b/include/linux/hil_mlc.h
@@ -103,7 +103,7 @@ struct hilse_node {
 
 /* Methods for back-end drivers, e.g. hp_sdc_mlc */
 typedef int	(hil_mlc_cts) (hil_mlc *mlc);
-typedef void	(hil_mlc_out) (hil_mlc *mlc);
+typedef int	(hil_mlc_out) (hil_mlc *mlc);
 typedef int	(hil_mlc_in)  (hil_mlc *mlc, suseconds_t timeout);
 
 struct hil_mlc_devinfo {
-- 
cgit v1.2.3


From a6a0b05da9f37ff56faa6b8351ed6e0b55032460 Mon Sep 17 00:00:00 2001
From: Ben Gardon <bgardon@google.com>
Date: Wed, 14 Oct 2020 11:26:55 -0700
Subject: kvm: x86/mmu: Support dirty logging for the TDP MMU

Dirty logging is a key feature of the KVM MMU and must be supported by
the TDP MMU. Add support for both the write protection and PML dirty
logging modes.

Tested by running kvm-unit-tests and KVM selftests on an Intel Haswell
machine. This series introduced no new failures.

This series can be viewed in Gerrit at:
	https://linux-review.googlesource.com/c/virt/kvm/kvm/+/2538

Signed-off-by: Ben Gardon <bgardon@google.com>
Message-Id: <20201014182700.2888246-16-bgardon@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c      |  14 +++
 arch/x86/kvm/mmu/tdp_iter.h |   7 +-
 arch/x86/kvm/mmu/tdp_mmu.c  | 299 +++++++++++++++++++++++++++++++++++++++++++-
 arch/x86/kvm/mmu/tdp_mmu.h  |  10 ++
 include/linux/kvm_host.h    |   1 +
 virt/kvm/kvm_main.c         |   6 +-
 6 files changed, 328 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 41f0354c7489..0c64643819b9 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1223,6 +1223,9 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
 {
 	struct kvm_rmap_head *rmap_head;
 
+	if (kvm->arch.tdp_mmu_enabled)
+		kvm_tdp_mmu_clear_dirty_pt_masked(kvm, slot,
+				slot->base_gfn + gfn_offset, mask, true);
 	while (mask) {
 		rmap_head = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask),
 					  PG_LEVEL_4K, slot);
@@ -1249,6 +1252,9 @@ void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm,
 {
 	struct kvm_rmap_head *rmap_head;
 
+	if (kvm->arch.tdp_mmu_enabled)
+		kvm_tdp_mmu_clear_dirty_pt_masked(kvm, slot,
+				slot->base_gfn + gfn_offset, mask, false);
 	while (mask) {
 		rmap_head = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask),
 					  PG_LEVEL_4K, slot);
@@ -5473,6 +5479,8 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
 	spin_lock(&kvm->mmu_lock);
 	flush = slot_handle_level(kvm, memslot, slot_rmap_write_protect,
 				start_level, KVM_MAX_HUGEPAGE_LEVEL, false);
+	if (kvm->arch.tdp_mmu_enabled)
+		flush |= kvm_tdp_mmu_wrprot_slot(kvm, memslot, PG_LEVEL_4K);
 	spin_unlock(&kvm->mmu_lock);
 
 	/*
@@ -5561,6 +5569,8 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
 
 	spin_lock(&kvm->mmu_lock);
 	flush = slot_handle_leaf(kvm, memslot, __rmap_clear_dirty, false);
+	if (kvm->arch.tdp_mmu_enabled)
+		flush |= kvm_tdp_mmu_clear_dirty_slot(kvm, memslot);
 	spin_unlock(&kvm->mmu_lock);
 
 	/*
@@ -5582,6 +5592,8 @@ void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm,
 	spin_lock(&kvm->mmu_lock);
 	flush = slot_handle_large_level(kvm, memslot, slot_rmap_write_protect,
 					false);
+	if (kvm->arch.tdp_mmu_enabled)
+		flush |= kvm_tdp_mmu_wrprot_slot(kvm, memslot, PG_LEVEL_2M);
 	spin_unlock(&kvm->mmu_lock);
 
 	if (flush)
@@ -5596,6 +5608,8 @@ void kvm_mmu_slot_set_dirty(struct kvm *kvm,
 
 	spin_lock(&kvm->mmu_lock);
 	flush = slot_handle_all_level(kvm, memslot, __rmap_set_dirty, false);
+	if (kvm->arch.tdp_mmu_enabled)
+		flush |= kvm_tdp_mmu_slot_set_dirty(kvm, memslot);
 	spin_unlock(&kvm->mmu_lock);
 
 	if (flush)
diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h
index 884ed2c70bfe..47170d0dc98e 100644
--- a/arch/x86/kvm/mmu/tdp_iter.h
+++ b/arch/x86/kvm/mmu/tdp_iter.h
@@ -41,11 +41,14 @@ struct tdp_iter {
  * Iterates over every SPTE mapping the GFN range [start, end) in a
  * preorder traversal.
  */
-#define for_each_tdp_pte(iter, root, root_level, start, end) \
-	for (tdp_iter_start(&iter, root, root_level, PG_LEVEL_4K, start); \
+#define for_each_tdp_pte_min_level(iter, root, root_level, min_level, start, end) \
+	for (tdp_iter_start(&iter, root, root_level, min_level, start); \
 	     iter.valid && iter.gfn < end;		     \
 	     tdp_iter_next(&iter))
 
+#define for_each_tdp_pte(iter, root, root_level, start, end) \
+	for_each_tdp_pte_min_level(iter, root, root_level, PG_LEVEL_4K, start, end)
+
 u64 *spte_to_child_pt(u64 pte, int level);
 
 void tdp_iter_start(struct tdp_iter *iter, u64 *root_pt, int root_level,
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 64e640cfcff9..7181b4ab54d0 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -161,6 +161,24 @@ static void handle_changed_spte_acc_track(u64 old_spte, u64 new_spte, int level)
 		kvm_set_pfn_accessed(spte_to_pfn(old_spte));
 }
 
+static void handle_changed_spte_dirty_log(struct kvm *kvm, int as_id, gfn_t gfn,
+					  u64 old_spte, u64 new_spte, int level)
+{
+	bool pfn_changed;
+	struct kvm_memory_slot *slot;
+
+	if (level > PG_LEVEL_4K)
+		return;
+
+	pfn_changed = spte_to_pfn(old_spte) != spte_to_pfn(new_spte);
+
+	if ((!is_writable_pte(old_spte) || pfn_changed) &&
+	    is_writable_pte(new_spte)) {
+		slot = __gfn_to_memslot(__kvm_memslots(kvm, as_id), gfn);
+		mark_page_dirty_in_slot(slot, gfn);
+	}
+}
+
 /**
  * handle_changed_spte - handle bookkeeping associated with an SPTE change
  * @kvm: kvm instance
@@ -273,10 +291,13 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
 {
 	__handle_changed_spte(kvm, as_id, gfn, old_spte, new_spte, level);
 	handle_changed_spte_acc_track(old_spte, new_spte, level);
+	handle_changed_spte_dirty_log(kvm, as_id, gfn, old_spte,
+				      new_spte, level);
 }
 
 static inline void __tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter,
-				      u64 new_spte, bool record_acc_track)
+				      u64 new_spte, bool record_acc_track,
+				      bool record_dirty_log)
 {
 	u64 *root_pt = tdp_iter_root_pt(iter);
 	struct kvm_mmu_page *root = sptep_to_sp(root_pt);
@@ -289,19 +310,30 @@ static inline void __tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter,
 	if (record_acc_track)
 		handle_changed_spte_acc_track(iter->old_spte, new_spte,
 					      iter->level);
+	if (record_dirty_log)
+		handle_changed_spte_dirty_log(kvm, as_id, iter->gfn,
+					      iter->old_spte, new_spte,
+					      iter->level);
 }
 
 static inline void tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter,
 				    u64 new_spte)
 {
-	__tdp_mmu_set_spte(kvm, iter, new_spte, true);
+	__tdp_mmu_set_spte(kvm, iter, new_spte, true, true);
 }
 
 static inline void tdp_mmu_set_spte_no_acc_track(struct kvm *kvm,
 						 struct tdp_iter *iter,
 						 u64 new_spte)
 {
-	__tdp_mmu_set_spte(kvm, iter, new_spte, false);
+	__tdp_mmu_set_spte(kvm, iter, new_spte, false, true);
+}
+
+static inline void tdp_mmu_set_spte_no_dirty_log(struct kvm *kvm,
+						 struct tdp_iter *iter,
+						 u64 new_spte)
+{
+	__tdp_mmu_set_spte(kvm, iter, new_spte, true, false);
 }
 
 #define tdp_root_for_each_pte(_iter, _root, _start, _end) \
@@ -334,6 +366,14 @@ static bool tdp_mmu_iter_flush_cond_resched(struct kvm *kvm, struct tdp_iter *it
 	}
 }
 
+static void tdp_mmu_iter_cond_resched(struct kvm *kvm, struct tdp_iter *iter)
+{
+	if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
+		cond_resched_lock(&kvm->mmu_lock);
+		tdp_iter_refresh_walk(iter);
+	}
+}
+
 /*
  * Tears down the mappings for the range of gfns, [start, end), and frees the
  * non-root pages mapping GFNs strictly within that range. Returns true if
@@ -638,6 +678,7 @@ static int age_gfn_range(struct kvm *kvm, struct kvm_memory_slot *slot,
 
 			new_spte = mark_spte_for_access_track(new_spte);
 		}
+		new_spte &= ~shadow_dirty_mask;
 
 		tdp_mmu_set_spte_no_acc_track(kvm, &iter, new_spte);
 		young = 1;
@@ -727,3 +768,255 @@ int kvm_tdp_mmu_set_spte_hva(struct kvm *kvm, unsigned long address,
 					    set_tdp_spte);
 }
 
+/*
+ * Remove write access from all the SPTEs mapping GFNs [start, end). If
+ * skip_4k is set, SPTEs that map 4k pages, will not be write-protected.
+ * Returns true if an SPTE has been changed and the TLBs need to be flushed.
+ */
+static bool wrprot_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
+			     gfn_t start, gfn_t end, int min_level)
+{
+	struct tdp_iter iter;
+	u64 new_spte;
+	bool spte_set = false;
+
+	BUG_ON(min_level > KVM_MAX_HUGEPAGE_LEVEL);
+
+	for_each_tdp_pte_min_level(iter, root->spt, root->role.level,
+				   min_level, start, end) {
+		if (!is_shadow_present_pte(iter.old_spte) ||
+		    !is_last_spte(iter.old_spte, iter.level))
+			continue;
+
+		new_spte = iter.old_spte & ~PT_WRITABLE_MASK;
+
+		tdp_mmu_set_spte_no_dirty_log(kvm, &iter, new_spte);
+		spte_set = true;
+
+		tdp_mmu_iter_cond_resched(kvm, &iter);
+	}
+	return spte_set;
+}
+
+/*
+ * Remove write access from all the SPTEs mapping GFNs in the memslot. Will
+ * only affect leaf SPTEs down to min_level.
+ * Returns true if an SPTE has been changed and the TLBs need to be flushed.
+ */
+bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm, struct kvm_memory_slot *slot,
+			     int min_level)
+{
+	struct kvm_mmu_page *root;
+	int root_as_id;
+	bool spte_set = false;
+
+	for_each_tdp_mmu_root(kvm, root) {
+		root_as_id = kvm_mmu_page_as_id(root);
+		if (root_as_id != slot->as_id)
+			continue;
+
+		/*
+		 * Take a reference on the root so that it cannot be freed if
+		 * this thread releases the MMU lock and yields in this loop.
+		 */
+		kvm_mmu_get_root(kvm, root);
+
+		spte_set |= wrprot_gfn_range(kvm, root, slot->base_gfn,
+			     slot->base_gfn + slot->npages, min_level);
+
+		kvm_mmu_put_root(kvm, root);
+	}
+
+	return spte_set;
+}
+
+/*
+ * Clear the dirty status of all the SPTEs mapping GFNs in the memslot. If
+ * AD bits are enabled, this will involve clearing the dirty bit on each SPTE.
+ * If AD bits are not enabled, this will require clearing the writable bit on
+ * each SPTE. Returns true if an SPTE has been changed and the TLBs need to
+ * be flushed.
+ */
+static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
+			   gfn_t start, gfn_t end)
+{
+	struct tdp_iter iter;
+	u64 new_spte;
+	bool spte_set = false;
+
+	tdp_root_for_each_leaf_pte(iter, root, start, end) {
+		if (spte_ad_need_write_protect(iter.old_spte)) {
+			if (is_writable_pte(iter.old_spte))
+				new_spte = iter.old_spte & ~PT_WRITABLE_MASK;
+			else
+				continue;
+		} else {
+			if (iter.old_spte & shadow_dirty_mask)
+				new_spte = iter.old_spte & ~shadow_dirty_mask;
+			else
+				continue;
+		}
+
+		tdp_mmu_set_spte_no_dirty_log(kvm, &iter, new_spte);
+		spte_set = true;
+
+		tdp_mmu_iter_cond_resched(kvm, &iter);
+	}
+	return spte_set;
+}
+
+/*
+ * Clear the dirty status of all the SPTEs mapping GFNs in the memslot. If
+ * AD bits are enabled, this will involve clearing the dirty bit on each SPTE.
+ * If AD bits are not enabled, this will require clearing the writable bit on
+ * each SPTE. Returns true if an SPTE has been changed and the TLBs need to
+ * be flushed.
+ */
+bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, struct kvm_memory_slot *slot)
+{
+	struct kvm_mmu_page *root;
+	int root_as_id;
+	bool spte_set = false;
+
+	for_each_tdp_mmu_root(kvm, root) {
+		root_as_id = kvm_mmu_page_as_id(root);
+		if (root_as_id != slot->as_id)
+			continue;
+
+		/*
+		 * Take a reference on the root so that it cannot be freed if
+		 * this thread releases the MMU lock and yields in this loop.
+		 */
+		kvm_mmu_get_root(kvm, root);
+
+		spte_set |= clear_dirty_gfn_range(kvm, root, slot->base_gfn,
+				slot->base_gfn + slot->npages);
+
+		kvm_mmu_put_root(kvm, root);
+	}
+
+	return spte_set;
+}
+
+/*
+ * Clears the dirty status of all the 4k SPTEs mapping GFNs for which a bit is
+ * set in mask, starting at gfn. The given memslot is expected to contain all
+ * the GFNs represented by set bits in the mask. If AD bits are enabled,
+ * clearing the dirty status will involve clearing the dirty bit on each SPTE
+ * or, if AD bits are not enabled, clearing the writable bit on each SPTE.
+ */
+static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root,
+				  gfn_t gfn, unsigned long mask, bool wrprot)
+{
+	struct tdp_iter iter;
+	u64 new_spte;
+
+	tdp_root_for_each_leaf_pte(iter, root, gfn + __ffs(mask),
+				    gfn + BITS_PER_LONG) {
+		if (!mask)
+			break;
+
+		if (iter.level > PG_LEVEL_4K ||
+		    !(mask & (1UL << (iter.gfn - gfn))))
+			continue;
+
+		if (wrprot || spte_ad_need_write_protect(iter.old_spte)) {
+			if (is_writable_pte(iter.old_spte))
+				new_spte = iter.old_spte & ~PT_WRITABLE_MASK;
+			else
+				continue;
+		} else {
+			if (iter.old_spte & shadow_dirty_mask)
+				new_spte = iter.old_spte & ~shadow_dirty_mask;
+			else
+				continue;
+		}
+
+		tdp_mmu_set_spte_no_dirty_log(kvm, &iter, new_spte);
+
+		mask &= ~(1UL << (iter.gfn - gfn));
+	}
+}
+
+/*
+ * Clears the dirty status of all the 4k SPTEs mapping GFNs for which a bit is
+ * set in mask, starting at gfn. The given memslot is expected to contain all
+ * the GFNs represented by set bits in the mask. If AD bits are enabled,
+ * clearing the dirty status will involve clearing the dirty bit on each SPTE
+ * or, if AD bits are not enabled, clearing the writable bit on each SPTE.
+ */
+void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm,
+				       struct kvm_memory_slot *slot,
+				       gfn_t gfn, unsigned long mask,
+				       bool wrprot)
+{
+	struct kvm_mmu_page *root;
+	int root_as_id;
+
+	lockdep_assert_held(&kvm->mmu_lock);
+	for_each_tdp_mmu_root(kvm, root) {
+		root_as_id = kvm_mmu_page_as_id(root);
+		if (root_as_id != slot->as_id)
+			continue;
+
+		clear_dirty_pt_masked(kvm, root, gfn, mask, wrprot);
+	}
+}
+
+/*
+ * Set the dirty status of all the SPTEs mapping GFNs in the memslot. This is
+ * only used for PML, and so will involve setting the dirty bit on each SPTE.
+ * Returns true if an SPTE has been changed and the TLBs need to be flushed.
+ */
+static bool set_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
+				gfn_t start, gfn_t end)
+{
+	struct tdp_iter iter;
+	u64 new_spte;
+	bool spte_set = false;
+
+	tdp_root_for_each_pte(iter, root, start, end) {
+		if (!is_shadow_present_pte(iter.old_spte))
+			continue;
+
+		new_spte = iter.old_spte | shadow_dirty_mask;
+
+		tdp_mmu_set_spte(kvm, &iter, new_spte);
+		spte_set = true;
+
+		tdp_mmu_iter_cond_resched(kvm, &iter);
+	}
+
+	return spte_set;
+}
+
+/*
+ * Set the dirty status of all the SPTEs mapping GFNs in the memslot. This is
+ * only used for PML, and so will involve setting the dirty bit on each SPTE.
+ * Returns true if an SPTE has been changed and the TLBs need to be flushed.
+ */
+bool kvm_tdp_mmu_slot_set_dirty(struct kvm *kvm, struct kvm_memory_slot *slot)
+{
+	struct kvm_mmu_page *root;
+	int root_as_id;
+	bool spte_set = false;
+
+	for_each_tdp_mmu_root(kvm, root) {
+		root_as_id = kvm_mmu_page_as_id(root);
+		if (root_as_id != slot->as_id)
+			continue;
+
+		/*
+		 * Take a reference on the root so that it cannot be freed if
+		 * this thread releases the MMU lock and yields in this loop.
+		 */
+		kvm_mmu_get_root(kvm, root);
+
+		spte_set |= set_dirty_gfn_range(kvm, root, slot->base_gfn,
+				slot->base_gfn + slot->npages);
+
+		kvm_mmu_put_root(kvm, root);
+	}
+	return spte_set;
+}
+
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
index aeee3ce7b3f4..ece66f10d85f 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -28,4 +28,14 @@ int kvm_tdp_mmu_test_age_hva(struct kvm *kvm, unsigned long hva);
 
 int kvm_tdp_mmu_set_spte_hva(struct kvm *kvm, unsigned long address,
 			     pte_t *host_ptep);
+
+bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm, struct kvm_memory_slot *slot,
+			     int min_level);
+bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm,
+				  struct kvm_memory_slot *slot);
+void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm,
+				       struct kvm_memory_slot *slot,
+				       gfn_t gfn, unsigned long mask,
+				       bool wrprot);
+bool kvm_tdp_mmu_slot_set_dirty(struct kvm *kvm, struct kvm_memory_slot *slot);
 #endif /* __KVM_X86_MMU_TDP_MMU_H */
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index c6f45687ba89..7f2e2a09ebbd 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -798,6 +798,7 @@ struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn);
 bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn);
 bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn);
 unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn);
+void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot, gfn_t gfn);
 void mark_page_dirty(struct kvm *kvm, gfn_t gfn);
 
 struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 2e8539213125..2541a17ff1c4 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -143,8 +143,6 @@ static void hardware_disable_all(void);
 
 static void kvm_io_bus_destroy(struct kvm_io_bus *bus);
 
-static void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot, gfn_t gfn);
-
 __visible bool kvm_rebooting;
 EXPORT_SYMBOL_GPL(kvm_rebooting);
 
@@ -2645,8 +2643,7 @@ int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len)
 }
 EXPORT_SYMBOL_GPL(kvm_clear_guest);
 
-static void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot,
-				    gfn_t gfn)
+void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot, gfn_t gfn)
 {
 	if (memslot && memslot->dirty_bitmap) {
 		unsigned long rel_gfn = gfn - memslot->base_gfn;
@@ -2654,6 +2651,7 @@ static void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot,
 		set_bit_le(rel_gfn, memslot->dirty_bitmap);
 	}
 }
+EXPORT_SYMBOL_GPL(mark_page_dirty_in_slot);
 
 void mark_page_dirty(struct kvm *kvm, gfn_t gfn)
 {
-- 
cgit v1.2.3


From 3f1b623a1be92103386bcab818e25885d6be9419 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 23 Oct 2020 17:00:41 +0800
Subject: vdpa: introduce config op to get valid iova range

This patch introduce a config op to get valid iova range from the vDPA
device.

Signed-off-by: Jason Wang <jasowang@redhat.com>
Link: https://lore.kernel.org/r/20201023090043.14430-2-jasowang@redhat.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/linux/vdpa.h | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
index eae0bfd87d91..30bc7a7223bb 100644
--- a/include/linux/vdpa.h
+++ b/include/linux/vdpa.h
@@ -52,6 +52,16 @@ struct vdpa_device {
 	int nvqs;
 };
 
+/**
+ * vDPA IOVA range - the IOVA range support by the device
+ * @first: start of the IOVA range
+ * @last: end of the IOVA range
+ */
+struct vdpa_iova_range {
+	u64 first;
+	u64 last;
+};
+
 /**
  * vDPA_config_ops - operations for configuring a vDPA device.
  * Note: vDPA device drivers are required to implement all of the
@@ -151,6 +161,10 @@ struct vdpa_device {
  * @get_generation:		Get device config generation (optional)
  *				@vdev: vdpa device
  *				Returns u32: device generation
+ * @get_iova_range:		Get supported iova range (optional)
+ *				@vdev: vdpa device
+ *				Returns the iova range supported by
+ *				the device.
  * @set_map:			Set device memory mapping (optional)
  *				Needed for device that using device
  *				specific DMA translation (on-chip IOMMU)
@@ -216,6 +230,7 @@ struct vdpa_config_ops {
 	void (*set_config)(struct vdpa_device *vdev, unsigned int offset,
 			   const void *buf, unsigned int len);
 	u32 (*get_generation)(struct vdpa_device *vdev);
+	struct vdpa_iova_range (*get_iova_range)(struct vdpa_device *vdev);
 
 	/* DMA ops */
 	int (*set_map)(struct vdpa_device *vdev, struct vhost_iotlb *iotlb);
-- 
cgit v1.2.3


From c51f8f88d705e06bd696d7510aff22b33eb8e638 Mon Sep 17 00:00:00 2001
From: George Spelvin <lkml@sdf.org>
Date: Sun, 9 Aug 2020 06:57:44 +0000
Subject: random32: make prandom_u32() output unpredictable

Non-cryptographic PRNGs may have great statistical properties, but
are usually trivially predictable to someone who knows the algorithm,
given a small sample of their output.  An LFSR like prandom_u32() is
particularly simple, even if the sample is widely scattered bits.

It turns out the network stack uses prandom_u32() for some things like
random port numbers which it would prefer are *not* trivially predictable.
Predictability led to a practical DNS spoofing attack.  Oops.

This patch replaces the LFSR with a homebrew cryptographic PRNG based
on the SipHash round function, which is in turn seeded with 128 bits
of strong random key.  (The authors of SipHash have *not* been consulted
about this abuse of their algorithm.)  Speed is prioritized over security;
attacks are rare, while performance is always wanted.

Replacing all callers of prandom_u32() is the quick fix.
Whether to reinstate a weaker PRNG for uses which can tolerate it
is an open question.

Commit f227e3ec3b5c ("random32: update the net random state on interrupt
and activity") was an earlier attempt at a solution.  This patch replaces
it.

Reported-by: Amit Klein <aksecurity@gmail.com>
Cc: Willy Tarreau <w@1wt.eu>
Cc: Eric Dumazet <edumazet@google.com>
Cc: "Jason A. Donenfeld" <Jason@zx2c4.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: tytso@mit.edu
Cc: Florian Westphal <fw@strlen.de>
Cc: Marc Plumb <lkml.mplumb@gmail.com>
Fixes: f227e3ec3b5c ("random32: update the net random state on interrupt and activity")
Signed-off-by: George Spelvin <lkml@sdf.org>
Link: https://lore.kernel.org/netdev/20200808152628.GA27941@SDF.ORG/
[ willy: partial reversal of f227e3ec3b5c; moved SIPROUND definitions
  to prandom.h for later use; merged George's prandom_seed() proposal;
  inlined siprand_u32(); replaced the net_rand_state[] array with 4
  members to fix a build issue; cosmetic cleanups to make checkpatch
  happy; fixed RANDOM32_SELFTEST build ]
Signed-off-by: Willy Tarreau <w@1wt.eu>
---
 drivers/char/random.c   |   1 -
 include/linux/prandom.h |  36 +++-
 kernel/time/timer.c     |   7 -
 lib/random32.c          | 464 +++++++++++++++++++++++++++++-------------------
 4 files changed, 318 insertions(+), 190 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/char/random.c b/drivers/char/random.c
index d20ba1b104ca..2a41b21623ae 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -1277,7 +1277,6 @@ void add_interrupt_randomness(int irq, int irq_flags)
 
 	fast_mix(fast_pool);
 	add_interrupt_bench(cycles);
-	this_cpu_add(net_rand_state.s1, fast_pool->pool[cycles & 3]);
 
 	if (unlikely(crng_init == 0)) {
 		if ((fast_pool->count >= 64) &&
diff --git a/include/linux/prandom.h b/include/linux/prandom.h
index aa16e6468f91..cc1e71334e53 100644
--- a/include/linux/prandom.h
+++ b/include/linux/prandom.h
@@ -16,12 +16,44 @@ void prandom_bytes(void *buf, size_t nbytes);
 void prandom_seed(u32 seed);
 void prandom_reseed_late(void);
 
+#if BITS_PER_LONG == 64
+/*
+ * The core SipHash round function.  Each line can be executed in
+ * parallel given enough CPU resources.
+ */
+#define PRND_SIPROUND(v0, v1, v2, v3) ( \
+	v0 += v1, v1 = rol64(v1, 13),  v2 += v3, v3 = rol64(v3, 16), \
+	v1 ^= v0, v0 = rol64(v0, 32),  v3 ^= v2,                     \
+	v0 += v3, v3 = rol64(v3, 21),  v2 += v1, v1 = rol64(v1, 17), \
+	v3 ^= v0,                      v1 ^= v2, v2 = rol64(v2, 32)  \
+)
+
+#define PRND_K0 (0x736f6d6570736575 ^ 0x6c7967656e657261)
+#define PRND_K1 (0x646f72616e646f6d ^ 0x7465646279746573)
+
+#elif BITS_PER_LONG == 32
+/*
+ * On 32-bit machines, we use HSipHash, a reduced-width version of SipHash.
+ * This is weaker, but 32-bit machines are not used for high-traffic
+ * applications, so there is less output for an attacker to analyze.
+ */
+#define PRND_SIPROUND(v0, v1, v2, v3) ( \
+	v0 += v1, v1 = rol32(v1,  5),  v2 += v3, v3 = rol32(v3,  8), \
+	v1 ^= v0, v0 = rol32(v0, 16),  v3 ^= v2,                     \
+	v0 += v3, v3 = rol32(v3,  7),  v2 += v1, v1 = rol32(v1, 13), \
+	v3 ^= v0,                      v1 ^= v2, v2 = rol32(v2, 16)  \
+)
+#define PRND_K0 0x6c796765
+#define PRND_K1 0x74656462
+
+#else
+#error Unsupported BITS_PER_LONG
+#endif
+
 struct rnd_state {
 	__u32 s1, s2, s3, s4;
 };
 
-DECLARE_PER_CPU(struct rnd_state, net_rand_state);
-
 u32 prandom_u32_state(struct rnd_state *state);
 void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes);
 void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state);
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index dda05f4b7a1f..3e341af741b9 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1717,13 +1717,6 @@ void update_process_times(int user_tick)
 	scheduler_tick();
 	if (IS_ENABLED(CONFIG_POSIX_TIMERS))
 		run_posix_cpu_timers();
-
-	/* The current CPU might make use of net randoms without receiving IRQs
-	 * to renew them often enough. Let's update the net_rand_state from a
-	 * non-constant value that's not affine to the number of calls to make
-	 * sure it's updated when there's some activity (we don't care in idle).
-	 */
-	this_cpu_add(net_rand_state.s1, rol32(jiffies, 24) + user_tick);
 }
 
 /**
diff --git a/lib/random32.c b/lib/random32.c
index dfb9981ab798..be9f242a4207 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -41,16 +41,6 @@
 #include <asm/unaligned.h>
 #include <trace/events/random.h>
 
-#ifdef CONFIG_RANDOM32_SELFTEST
-static void __init prandom_state_selftest(void);
-#else
-static inline void prandom_state_selftest(void)
-{
-}
-#endif
-
-DEFINE_PER_CPU(struct rnd_state, net_rand_state)  __latent_entropy;
-
 /**
  *	prandom_u32_state - seeded pseudo-random number generator.
  *	@state: pointer to state structure holding seeded state.
@@ -70,26 +60,6 @@ u32 prandom_u32_state(struct rnd_state *state)
 }
 EXPORT_SYMBOL(prandom_u32_state);
 
-/**
- *	prandom_u32 - pseudo random number generator
- *
- *	A 32 bit pseudo-random number is generated using a fast
- *	algorithm suitable for simulation. This algorithm is NOT
- *	considered safe for cryptographic use.
- */
-u32 prandom_u32(void)
-{
-	struct rnd_state *state = &get_cpu_var(net_rand_state);
-	u32 res;
-
-	res = prandom_u32_state(state);
-	trace_prandom_u32(res);
-	put_cpu_var(net_rand_state);
-
-	return res;
-}
-EXPORT_SYMBOL(prandom_u32);
-
 /**
  *	prandom_bytes_state - get the requested number of pseudo-random bytes
  *
@@ -121,20 +91,6 @@ void prandom_bytes_state(struct rnd_state *state, void *buf, size_t bytes)
 }
 EXPORT_SYMBOL(prandom_bytes_state);
 
-/**
- *	prandom_bytes - get the requested number of pseudo-random bytes
- *	@buf: where to copy the pseudo-random bytes to
- *	@bytes: the requested number of bytes
- */
-void prandom_bytes(void *buf, size_t bytes)
-{
-	struct rnd_state *state = &get_cpu_var(net_rand_state);
-
-	prandom_bytes_state(state, buf, bytes);
-	put_cpu_var(net_rand_state);
-}
-EXPORT_SYMBOL(prandom_bytes);
-
 static void prandom_warmup(struct rnd_state *state)
 {
 	/* Calling RNG ten times to satisfy recurrence condition */
@@ -150,96 +106,6 @@ static void prandom_warmup(struct rnd_state *state)
 	prandom_u32_state(state);
 }
 
-static u32 __extract_hwseed(void)
-{
-	unsigned int val = 0;
-
-	(void)(arch_get_random_seed_int(&val) ||
-	       arch_get_random_int(&val));
-
-	return val;
-}
-
-static void prandom_seed_early(struct rnd_state *state, u32 seed,
-			       bool mix_with_hwseed)
-{
-#define LCG(x)	 ((x) * 69069U)	/* super-duper LCG */
-#define HWSEED() (mix_with_hwseed ? __extract_hwseed() : 0)
-	state->s1 = __seed(HWSEED() ^ LCG(seed),        2U);
-	state->s2 = __seed(HWSEED() ^ LCG(state->s1),   8U);
-	state->s3 = __seed(HWSEED() ^ LCG(state->s2),  16U);
-	state->s4 = __seed(HWSEED() ^ LCG(state->s3), 128U);
-}
-
-/**
- *	prandom_seed - add entropy to pseudo random number generator
- *	@entropy: entropy value
- *
- *	Add some additional entropy to the prandom pool.
- */
-void prandom_seed(u32 entropy)
-{
-	int i;
-	/*
-	 * No locking on the CPUs, but then somewhat random results are, well,
-	 * expected.
-	 */
-	for_each_possible_cpu(i) {
-		struct rnd_state *state = &per_cpu(net_rand_state, i);
-
-		state->s1 = __seed(state->s1 ^ entropy, 2U);
-		prandom_warmup(state);
-	}
-}
-EXPORT_SYMBOL(prandom_seed);
-
-/*
- *	Generate some initially weak seeding values to allow
- *	to start the prandom_u32() engine.
- */
-static int __init prandom_init(void)
-{
-	int i;
-
-	prandom_state_selftest();
-
-	for_each_possible_cpu(i) {
-		struct rnd_state *state = &per_cpu(net_rand_state, i);
-		u32 weak_seed = (i + jiffies) ^ random_get_entropy();
-
-		prandom_seed_early(state, weak_seed, true);
-		prandom_warmup(state);
-	}
-
-	return 0;
-}
-core_initcall(prandom_init);
-
-static void __prandom_timer(struct timer_list *unused);
-
-static DEFINE_TIMER(seed_timer, __prandom_timer);
-
-static void __prandom_timer(struct timer_list *unused)
-{
-	u32 entropy;
-	unsigned long expires;
-
-	get_random_bytes(&entropy, sizeof(entropy));
-	prandom_seed(entropy);
-
-	/* reseed every ~60 seconds, in [40 .. 80) interval with slack */
-	expires = 40 + prandom_u32_max(40);
-	seed_timer.expires = jiffies + msecs_to_jiffies(expires * MSEC_PER_SEC);
-
-	add_timer(&seed_timer);
-}
-
-static void __init __prandom_start_seed_timer(void)
-{
-	seed_timer.expires = jiffies + msecs_to_jiffies(40 * MSEC_PER_SEC);
-	add_timer(&seed_timer);
-}
-
 void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state)
 {
 	int i;
@@ -259,51 +125,6 @@ void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state)
 }
 EXPORT_SYMBOL(prandom_seed_full_state);
 
-/*
- *	Generate better values after random number generator
- *	is fully initialized.
- */
-static void __prandom_reseed(bool late)
-{
-	unsigned long flags;
-	static bool latch = false;
-	static DEFINE_SPINLOCK(lock);
-
-	/* Asking for random bytes might result in bytes getting
-	 * moved into the nonblocking pool and thus marking it
-	 * as initialized. In this case we would double back into
-	 * this function and attempt to do a late reseed.
-	 * Ignore the pointless attempt to reseed again if we're
-	 * already waiting for bytes when the nonblocking pool
-	 * got initialized.
-	 */
-
-	/* only allow initial seeding (late == false) once */
-	if (!spin_trylock_irqsave(&lock, flags))
-		return;
-
-	if (latch && !late)
-		goto out;
-
-	latch = true;
-	prandom_seed_full_state(&net_rand_state);
-out:
-	spin_unlock_irqrestore(&lock, flags);
-}
-
-void prandom_reseed_late(void)
-{
-	__prandom_reseed(true);
-}
-
-static int __init prandom_reseed(void)
-{
-	__prandom_reseed(false);
-	__prandom_start_seed_timer();
-	return 0;
-}
-late_initcall(prandom_reseed);
-
 #ifdef CONFIG_RANDOM32_SELFTEST
 static struct prandom_test1 {
 	u32 seed;
@@ -423,7 +244,28 @@ static struct prandom_test2 {
 	{  407983964U, 921U,  728767059U },
 };
 
-static void __init prandom_state_selftest(void)
+static u32 __extract_hwseed(void)
+{
+	unsigned int val = 0;
+
+	(void)(arch_get_random_seed_int(&val) ||
+	       arch_get_random_int(&val));
+
+	return val;
+}
+
+static void prandom_seed_early(struct rnd_state *state, u32 seed,
+			       bool mix_with_hwseed)
+{
+#define LCG(x)	 ((x) * 69069U)	/* super-duper LCG */
+#define HWSEED() (mix_with_hwseed ? __extract_hwseed() : 0)
+	state->s1 = __seed(HWSEED() ^ LCG(seed),        2U);
+	state->s2 = __seed(HWSEED() ^ LCG(state->s1),   8U);
+	state->s3 = __seed(HWSEED() ^ LCG(state->s2),  16U);
+	state->s4 = __seed(HWSEED() ^ LCG(state->s3), 128U);
+}
+
+static int __init prandom_state_selftest(void)
 {
 	int i, j, errors = 0, runs = 0;
 	bool error = false;
@@ -463,5 +305,267 @@ static void __init prandom_state_selftest(void)
 		pr_warn("prandom: %d/%d self tests failed\n", errors, runs);
 	else
 		pr_info("prandom: %d self tests passed\n", runs);
+	return 0;
 }
+core_initcall(prandom_state_selftest);
 #endif
+
+/*
+ * The prandom_u32() implementation is now completely separate from the
+ * prandom_state() functions, which are retained (for now) for compatibility.
+ *
+ * Because of (ab)use in the networking code for choosing random TCP/UDP port
+ * numbers, which open DoS possibilities if guessable, we want something
+ * stronger than a standard PRNG.  But the performance requirements of
+ * the network code do not allow robust crypto for this application.
+ *
+ * So this is a homebrew Junior Spaceman implementation, based on the
+ * lowest-latency trustworthy crypto primitive available, SipHash.
+ * (The authors of SipHash have not been consulted about this abuse of
+ * their work.)
+ *
+ * Standard SipHash-2-4 uses 2n+4 rounds to hash n words of input to
+ * one word of output.  This abbreviated version uses 2 rounds per word
+ * of output.
+ */
+
+struct siprand_state {
+	unsigned long v0;
+	unsigned long v1;
+	unsigned long v2;
+	unsigned long v3;
+};
+
+static DEFINE_PER_CPU(struct siprand_state, net_rand_state) __latent_entropy;
+
+/*
+ * This is the core CPRNG function.  As "pseudorandom", this is not used
+ * for truly valuable things, just intended to be a PITA to guess.
+ * For maximum speed, we do just two SipHash rounds per word.  This is
+ * the same rate as 4 rounds per 64 bits that SipHash normally uses,
+ * so hopefully it's reasonably secure.
+ *
+ * There are two changes from the official SipHash finalization:
+ * - We omit some constants XORed with v2 in the SipHash spec as irrelevant;
+ *   they are there only to make the output rounds distinct from the input
+ *   rounds, and this application has no input rounds.
+ * - Rather than returning v0^v1^v2^v3, return v1+v3.
+ *   If you look at the SipHash round, the last operation on v3 is
+ *   "v3 ^= v0", so "v0 ^ v3" just undoes that, a waste of time.
+ *   Likewise "v1 ^= v2".  (The rotate of v2 makes a difference, but
+ *   it still cancels out half of the bits in v2 for no benefit.)
+ *   Second, since the last combining operation was xor, continue the
+ *   pattern of alternating xor/add for a tiny bit of extra non-linearity.
+ */
+static inline u32 siprand_u32(struct siprand_state *s)
+{
+	unsigned long v0 = s->v0, v1 = s->v1, v2 = s->v2, v3 = s->v3;
+
+	PRND_SIPROUND(v0, v1, v2, v3);
+	PRND_SIPROUND(v0, v1, v2, v3);
+	s->v0 = v0;  s->v1 = v1;  s->v2 = v2;  s->v3 = v3;
+	return v1 + v3;
+}
+
+
+/**
+ *	prandom_u32 - pseudo random number generator
+ *
+ *	A 32 bit pseudo-random number is generated using a fast
+ *	algorithm suitable for simulation. This algorithm is NOT
+ *	considered safe for cryptographic use.
+ */
+u32 prandom_u32(void)
+{
+	struct siprand_state *state = get_cpu_ptr(&net_rand_state);
+	u32 res = siprand_u32(state);
+
+	trace_prandom_u32(res);
+	put_cpu_ptr(&net_rand_state);
+	return res;
+}
+EXPORT_SYMBOL(prandom_u32);
+
+/**
+ *	prandom_bytes - get the requested number of pseudo-random bytes
+ *	@buf: where to copy the pseudo-random bytes to
+ *	@bytes: the requested number of bytes
+ */
+void prandom_bytes(void *buf, size_t bytes)
+{
+	struct siprand_state *state = get_cpu_ptr(&net_rand_state);
+	u8 *ptr = buf;
+
+	while (bytes >= sizeof(u32)) {
+		put_unaligned(siprand_u32(state), (u32 *)ptr);
+		ptr += sizeof(u32);
+		bytes -= sizeof(u32);
+	}
+
+	if (bytes > 0) {
+		u32 rem = siprand_u32(state);
+
+		do {
+			*ptr++ = (u8)rem;
+			rem >>= BITS_PER_BYTE;
+		} while (--bytes > 0);
+	}
+	put_cpu_ptr(&net_rand_state);
+}
+EXPORT_SYMBOL(prandom_bytes);
+
+/**
+ *	prandom_seed - add entropy to pseudo random number generator
+ *	@entropy: entropy value
+ *
+ *	Add some additional seed material to the prandom pool.
+ *	The "entropy" is actually our IP address (the only caller is
+ *	the network code), not for unpredictability, but to ensure that
+ *	different machines are initialized differently.
+ */
+void prandom_seed(u32 entropy)
+{
+	int i;
+
+	add_device_randomness(&entropy, sizeof(entropy));
+
+	for_each_possible_cpu(i) {
+		struct siprand_state *state = per_cpu_ptr(&net_rand_state, i);
+		unsigned long v0 = state->v0, v1 = state->v1;
+		unsigned long v2 = state->v2, v3 = state->v3;
+
+		do {
+			v3 ^= entropy;
+			PRND_SIPROUND(v0, v1, v2, v3);
+			PRND_SIPROUND(v0, v1, v2, v3);
+			v0 ^= entropy;
+		} while (unlikely(!v0 || !v1 || !v2 || !v3));
+
+		WRITE_ONCE(state->v0, v0);
+		WRITE_ONCE(state->v1, v1);
+		WRITE_ONCE(state->v2, v2);
+		WRITE_ONCE(state->v3, v3);
+	}
+}
+EXPORT_SYMBOL(prandom_seed);
+
+/*
+ *	Generate some initially weak seeding values to allow
+ *	the prandom_u32() engine to be started.
+ */
+static int __init prandom_init_early(void)
+{
+	int i;
+	unsigned long v0, v1, v2, v3;
+
+	if (!arch_get_random_long(&v0))
+		v0 = jiffies;
+	if (!arch_get_random_long(&v1))
+		v1 = random_get_entropy();
+	v2 = v0 ^ PRND_K0;
+	v3 = v1 ^ PRND_K1;
+
+	for_each_possible_cpu(i) {
+		struct siprand_state *state;
+
+		v3 ^= i;
+		PRND_SIPROUND(v0, v1, v2, v3);
+		PRND_SIPROUND(v0, v1, v2, v3);
+		v0 ^= i;
+
+		state = per_cpu_ptr(&net_rand_state, i);
+		state->v0 = v0;  state->v1 = v1;
+		state->v2 = v2;  state->v3 = v3;
+	}
+
+	return 0;
+}
+core_initcall(prandom_init_early);
+
+
+/* Stronger reseeding when available, and periodically thereafter. */
+static void prandom_reseed(struct timer_list *unused);
+
+static DEFINE_TIMER(seed_timer, prandom_reseed);
+
+static void prandom_reseed(struct timer_list *unused)
+{
+	unsigned long expires;
+	int i;
+
+	/*
+	 * Reinitialize each CPU's PRNG with 128 bits of key.
+	 * No locking on the CPUs, but then somewhat random results are,
+	 * well, expected.
+	 */
+	for_each_possible_cpu(i) {
+		struct siprand_state *state;
+		unsigned long v0 = get_random_long(), v2 = v0 ^ PRND_K0;
+		unsigned long v1 = get_random_long(), v3 = v1 ^ PRND_K1;
+#if BITS_PER_LONG == 32
+		int j;
+
+		/*
+		 * On 32-bit machines, hash in two extra words to
+		 * approximate 128-bit key length.  Not that the hash
+		 * has that much security, but this prevents a trivial
+		 * 64-bit brute force.
+		 */
+		for (j = 0; j < 2; j++) {
+			unsigned long m = get_random_long();
+
+			v3 ^= m;
+			PRND_SIPROUND(v0, v1, v2, v3);
+			PRND_SIPROUND(v0, v1, v2, v3);
+			v0 ^= m;
+		}
+#endif
+		/*
+		 * Probably impossible in practice, but there is a
+		 * theoretical risk that a race between this reseeding
+		 * and the target CPU writing its state back could
+		 * create the all-zero SipHash fixed point.
+		 *
+		 * To ensure that never happens, ensure the state
+		 * we write contains no zero words.
+		 */
+		state = per_cpu_ptr(&net_rand_state, i);
+		WRITE_ONCE(state->v0, v0 ? v0 : -1ul);
+		WRITE_ONCE(state->v1, v1 ? v1 : -1ul);
+		WRITE_ONCE(state->v2, v2 ? v2 : -1ul);
+		WRITE_ONCE(state->v3, v3 ? v3 : -1ul);
+	}
+
+	/* reseed every ~60 seconds, in [40 .. 80) interval with slack */
+	expires = round_jiffies(jiffies + 40 * HZ + prandom_u32_max(40 * HZ));
+	mod_timer(&seed_timer, expires);
+}
+
+/*
+ * The random ready callback can be called from almost any interrupt.
+ * To avoid worrying about whether it's safe to delay that interrupt
+ * long enough to seed all CPUs, just schedule an immediate timer event.
+ */
+static void prandom_timer_start(struct random_ready_callback *unused)
+{
+	mod_timer(&seed_timer, jiffies);
+}
+
+/*
+ * Start periodic full reseeding as soon as strong
+ * random numbers are available.
+ */
+static int __init prandom_init_late(void)
+{
+	static struct random_ready_callback random_ready = {
+		.func = prandom_timer_start
+	};
+	int ret = add_random_ready_callback(&random_ready);
+
+	if (ret == -EALREADY) {
+		prandom_timer_start(&random_ready);
+		ret = 0;
+	}
+	return ret;
+}
+late_initcall(prandom_init_late);
-- 
cgit v1.2.3


From 3744741adab6d9195551ce30e65e726c7a408421 Mon Sep 17 00:00:00 2001
From: Willy Tarreau <w@1wt.eu>
Date: Mon, 10 Aug 2020 10:27:42 +0200
Subject: random32: add noise from network and scheduling activity

With the removal of the interrupt perturbations in previous random32
change (random32: make prandom_u32() output unpredictable), the PRNG
has become 100% deterministic again. While SipHash is expected to be
way more robust against brute force than the previous Tausworthe LFSR,
there's still the risk that whoever has even one temporary access to
the PRNG's internal state is able to predict all subsequent draws till
the next reseed (roughly every minute). This may happen through a side
channel attack or any data leak.

This patch restores the spirit of commit f227e3ec3b5c ("random32: update
the net random state on interrupt and activity") in that it will perturb
the internal PRNG's statee using externally collected noise, except that
it will not pick that noise from the random pool's bits nor upon
interrupt, but will rather combine a few elements along the Tx path
that are collectively hard to predict, such as dev, skb and txq
pointers, packet length and jiffies values. These ones are combined
using a single round of SipHash into a single long variable that is
mixed with the net_rand_state upon each invocation.

The operation was inlined because it produces very small and efficient
code, typically 3 xor, 2 add and 2 rol. The performance was measured
to be the same (even very slightly better) than before the switch to
SipHash; on a 6-core 12-thread Core i7-8700k equipped with a 40G NIC
(i40e), the connection rate dropped from 556k/s to 555k/s while the
SYN cookie rate grew from 5.38 Mpps to 5.45 Mpps.

Link: https://lore.kernel.org/netdev/20200808152628.GA27941@SDF.ORG/
Cc: George Spelvin <lkml@sdf.org>
Cc: Amit Klein <aksecurity@gmail.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: "Jason A. Donenfeld" <Jason@zx2c4.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: tytso@mit.edu
Cc: Florian Westphal <fw@strlen.de>
Cc: Marc Plumb <lkml.mplumb@gmail.com>
Tested-by: Sedat Dilek <sedat.dilek@gmail.com>
Signed-off-by: Willy Tarreau <w@1wt.eu>
---
 include/linux/prandom.h | 19 +++++++++++++++++++
 kernel/time/timer.c     |  2 ++
 lib/random32.c          |  5 +++++
 net/core/dev.c          |  4 ++++
 4 files changed, 30 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/prandom.h b/include/linux/prandom.h
index cc1e71334e53..bbf4b4ad61df 100644
--- a/include/linux/prandom.h
+++ b/include/linux/prandom.h
@@ -16,6 +16,12 @@ void prandom_bytes(void *buf, size_t nbytes);
 void prandom_seed(u32 seed);
 void prandom_reseed_late(void);
 
+DECLARE_PER_CPU(unsigned long, net_rand_noise);
+
+#define PRANDOM_ADD_NOISE(a, b, c, d) \
+	prandom_u32_add_noise((unsigned long)(a), (unsigned long)(b), \
+			      (unsigned long)(c), (unsigned long)(d))
+
 #if BITS_PER_LONG == 64
 /*
  * The core SipHash round function.  Each line can be executed in
@@ -50,6 +56,18 @@ void prandom_reseed_late(void);
 #error Unsupported BITS_PER_LONG
 #endif
 
+static inline void prandom_u32_add_noise(unsigned long a, unsigned long b,
+					 unsigned long c, unsigned long d)
+{
+	/*
+	 * This is not used cryptographically; it's just
+	 * a convenient 4-word hash function. (3 xor, 2 add, 2 rol)
+	 */
+	a ^= raw_cpu_read(net_rand_noise);
+	PRND_SIPROUND(a, b, c, d);
+	raw_cpu_write(net_rand_noise, d);
+}
+
 struct rnd_state {
 	__u32 s1, s2, s3, s4;
 };
@@ -99,6 +117,7 @@ static inline void prandom_seed_state(struct rnd_state *state, u64 seed)
 	state->s2 = __seed(i,   8U);
 	state->s3 = __seed(i,  16U);
 	state->s4 = __seed(i, 128U);
+	PRANDOM_ADD_NOISE(state, i, 0, 0);
 }
 
 /* Pseudo random number generator from numerical recipes. */
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 3e341af741b9..de37e33a868d 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1706,6 +1706,8 @@ void update_process_times(int user_tick)
 {
 	struct task_struct *p = current;
 
+	PRANDOM_ADD_NOISE(jiffies, user_tick, p, 0);
+
 	/* Note: this timer irq context must be accounted for as well. */
 	account_process_tick(p, user_tick);
 	run_local_timers();
diff --git a/lib/random32.c b/lib/random32.c
index be9f242a4207..7f047844e494 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -337,6 +337,8 @@ struct siprand_state {
 };
 
 static DEFINE_PER_CPU(struct siprand_state, net_rand_state) __latent_entropy;
+DEFINE_PER_CPU(unsigned long, net_rand_noise);
+EXPORT_PER_CPU_SYMBOL(net_rand_noise);
 
 /*
  * This is the core CPRNG function.  As "pseudorandom", this is not used
@@ -360,9 +362,12 @@ static DEFINE_PER_CPU(struct siprand_state, net_rand_state) __latent_entropy;
 static inline u32 siprand_u32(struct siprand_state *s)
 {
 	unsigned long v0 = s->v0, v1 = s->v1, v2 = s->v2, v3 = s->v3;
+	unsigned long n = raw_cpu_read(net_rand_noise);
 
+	v3 ^= n;
 	PRND_SIPROUND(v0, v1, v2, v3);
 	PRND_SIPROUND(v0, v1, v2, v3);
+	v0 ^= n;
 	s->v0 = v0;  s->v1 = v1;  s->v2 = v2;  s->v3 = v3;
 	return v1 + v3;
 }
diff --git a/net/core/dev.c b/net/core/dev.c
index 9499a414d67e..82dc6b48e45f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -145,6 +145,7 @@
 #include <linux/indirect_call_wrapper.h>
 #include <net/devlink.h>
 #include <linux/pm_runtime.h>
+#include <linux/prandom.h>
 
 #include "net-sysfs.h"
 
@@ -3558,6 +3559,7 @@ static int xmit_one(struct sk_buff *skb, struct net_device *dev,
 		dev_queue_xmit_nit(skb, dev);
 
 	len = skb->len;
+	PRANDOM_ADD_NOISE(skb, dev, txq, len + jiffies);
 	trace_net_dev_start_xmit(skb, dev);
 	rc = netdev_start_xmit(skb, dev, txq, more);
 	trace_net_dev_xmit(skb, rc, dev, len);
@@ -4130,6 +4132,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 			if (!skb)
 				goto out;
 
+			PRANDOM_ADD_NOISE(skb, dev, txq, jiffies);
 			HARD_TX_LOCK(dev, txq, cpu);
 
 			if (!netif_xmit_stopped(txq)) {
@@ -4195,6 +4198,7 @@ int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
 
 	skb_set_queue_mapping(skb, queue_id);
 	txq = skb_get_tx_queue(dev, skb);
+	PRANDOM_ADD_NOISE(skb, dev, txq, jiffies);
 
 	local_bh_disable();
 
-- 
cgit v1.2.3


From 23224e45004ed84c8466fd1e8e5860f541187029 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Fri, 23 Oct 2020 16:27:16 -0700
Subject: mm: remove kzfree() compatibility definition

Commit 453431a54934 ("mm, treewide: rename kzfree() to
kfree_sensitive()") renamed kzfree() to kfree_sensitive(),
but it left a compatibility definition of kzfree() to avoid
being too disruptive.

Since then a few more instances of kzfree() have slipped in.

Just get rid of them and remove the compatibility definition
once and for all.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/staging/rtl8192e/rtllib_crypt_tkip.c              | 2 +-
 drivers/staging/rtl8192e/rtllib_crypt_wep.c               | 2 +-
 drivers/staging/rtl8192u/ieee80211/ieee80211_crypt_tkip.c | 2 +-
 drivers/staging/rtl8192u/ieee80211/ieee80211_crypt_wep.c  | 2 +-
 include/linux/slab.h                                      | 2 --
 net/tipc/crypto.c                                         | 4 ++--
 6 files changed, 6 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/staging/rtl8192e/rtllib_crypt_tkip.c b/drivers/staging/rtl8192e/rtllib_crypt_tkip.c
index 8c2ff37b2d3a..238387d6221b 100644
--- a/drivers/staging/rtl8192e/rtllib_crypt_tkip.c
+++ b/drivers/staging/rtl8192e/rtllib_crypt_tkip.c
@@ -100,7 +100,7 @@ static void rtllib_tkip_deinit(void *priv)
 		crypto_free_shash(_priv->tx_tfm_michael);
 		crypto_free_shash(_priv->rx_tfm_michael);
 	}
-	kzfree(priv);
+	kfree_sensitive(priv);
 }
 
 
diff --git a/drivers/staging/rtl8192e/rtllib_crypt_wep.c b/drivers/staging/rtl8192e/rtllib_crypt_wep.c
index 7cdd17f907fa..7790271a6a40 100644
--- a/drivers/staging/rtl8192e/rtllib_crypt_wep.c
+++ b/drivers/staging/rtl8192e/rtllib_crypt_wep.c
@@ -49,7 +49,7 @@ static void *prism2_wep_init(int keyidx)
 
 static void prism2_wep_deinit(void *priv)
 {
-	kzfree(priv);
+	kfree_sensitive(priv);
 }
 
 /* Perform WEP encryption on given skb that has at least 4 bytes of headroom
diff --git a/drivers/staging/rtl8192u/ieee80211/ieee80211_crypt_tkip.c b/drivers/staging/rtl8192u/ieee80211/ieee80211_crypt_tkip.c
index 4b415cc76715..e8fa1d385f24 100644
--- a/drivers/staging/rtl8192u/ieee80211/ieee80211_crypt_tkip.c
+++ b/drivers/staging/rtl8192u/ieee80211/ieee80211_crypt_tkip.c
@@ -107,7 +107,7 @@ static void ieee80211_tkip_deinit(void *priv)
 		crypto_free_shash(_priv->tx_tfm_michael);
 		crypto_free_shash(_priv->rx_tfm_michael);
 	}
-	kzfree(priv);
+	kfree_sensitive(priv);
 }
 
 
diff --git a/drivers/staging/rtl8192u/ieee80211/ieee80211_crypt_wep.c b/drivers/staging/rtl8192u/ieee80211/ieee80211_crypt_wep.c
index 1c56e2d03aae..a41b6510481b 100644
--- a/drivers/staging/rtl8192u/ieee80211/ieee80211_crypt_wep.c
+++ b/drivers/staging/rtl8192u/ieee80211/ieee80211_crypt_wep.c
@@ -54,7 +54,7 @@ static void *prism2_wep_init(int keyidx)
 
 static void prism2_wep_deinit(void *priv)
 {
-	kzfree(priv);
+	kfree_sensitive(priv);
 }
 
 /* Perform WEP encryption on given skb that has at least 4 bytes of headroom
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 9e155cc83b8a..dd6897f62010 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -187,8 +187,6 @@ void kfree_sensitive(const void *);
 size_t __ksize(const void *);
 size_t ksize(const void *);
 
-#define kzfree(x)	kfree_sensitive(x)	/* For backward compatibility */
-
 #ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR
 void __check_heap_object(const void *ptr, unsigned long n, struct page *page,
 			bool to_user);
diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c
index 40c44101fe8e..740ab9ae41a6 100644
--- a/net/tipc/crypto.c
+++ b/net/tipc/crypto.c
@@ -418,7 +418,7 @@ static void tipc_aead_free(struct rcu_head *rp)
 		kfree(head);
 	}
 	free_percpu(aead->tfm_entry);
-	kzfree(aead->key);
+	kfree_sensitive(aead->key);
 	kfree(aead);
 }
 
@@ -2452,7 +2452,7 @@ static void tipc_crypto_work_tx(struct work_struct *work)
 		     tipc_crypto_key_init(tx, skey, PER_NODE_KEY, false);
 		if (likely(rc > 0))
 			rc = tipc_crypto_key_distr(tx, rc, NULL);
-		kzfree(skey);
+		kfree_sensitive(skey);
 	}
 
 	if (unlikely(rc))
-- 
cgit v1.2.3


From 33def8498fdde180023444b08e12b72a9efed41d Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Wed, 21 Oct 2020 19:36:07 -0700
Subject: treewide: Convert macro and uses of __section(foo) to
 __section("foo")

Use a more generic form for __section that requires quotes to avoid
complications with clang and gcc differences.

Remove the quote operator # from compiler_attributes.h __section macro.

Convert all unquoted __section(foo) uses to quoted __section("foo").
Also convert __attribute__((section("foo"))) uses to __section("foo")
even if the __attribute__ has multiple list entry forms.

Conversion done using the script at:

    https://lore.kernel.org/lkml/75393e5ddc272dc7403de74d645e6c6e0f4e70eb.camel@perches.com/2-convert_section.pl

Signed-off-by: Joe Perches <joe@perches.com>
Reviewed-by: Nick Desaulniers <ndesaulniers@gooogle.com>
Reviewed-by: Miguel Ojeda <ojeda@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arc/include/asm/linkage.h        |  8 ++++----
 arch/arc/include/asm/mach_desc.h      |  2 +-
 arch/arc/plat-hsdk/platform.c         |  2 +-
 arch/arm/include/asm/cache.h          |  2 +-
 arch/arm/include/asm/cpuidle.h        |  2 +-
 arch/arm/include/asm/idmap.h          |  2 +-
 arch/arm/include/asm/mach/arch.h      |  4 ++--
 arch/arm/include/asm/setup.h          |  2 +-
 arch/arm/include/asm/smp.h            |  2 +-
 arch/arm/include/asm/tcm.h            |  8 ++++----
 arch/arm/kernel/cpuidle.c             |  2 +-
 arch/arm/kernel/devtree.c             |  2 +-
 arch/arm64/include/asm/cache.h        |  2 +-
 arch/arm64/kernel/efi.c               |  2 +-
 arch/arm64/kernel/smp_spin_table.c    |  2 +-
 arch/arm64/mm/mmu.c                   |  2 +-
 arch/csky/include/asm/tcm.h           |  8 ++++----
 arch/ia64/include/asm/cache.h         |  2 +-
 arch/microblaze/kernel/setup.c        |  2 +-
 arch/mips/include/asm/cache.h         |  2 +-
 arch/mips/include/asm/machine.h       |  2 +-
 arch/mips/kernel/setup.c              |  2 +-
 arch/mips/mm/init.c                   |  2 +-
 arch/parisc/include/asm/cache.h       |  2 +-
 arch/parisc/include/asm/ldcw.h        |  2 +-
 arch/parisc/kernel/ftrace.c           |  2 +-
 arch/parisc/mm/init.c                 |  6 +++---
 arch/powerpc/include/asm/cache.h      |  2 +-
 arch/powerpc/include/asm/machdep.h    |  2 +-
 arch/powerpc/kernel/btext.c           |  2 +-
 arch/powerpc/kernel/prom_init.c       |  2 +-
 arch/powerpc/kvm/book3s_64_vio_hv.c   |  2 +-
 arch/riscv/include/asm/soc.h          |  4 ++--
 arch/riscv/kernel/cpu_ops.c           |  4 ++--
 arch/riscv/kernel/setup.c             |  4 ++--
 arch/s390/boot/startup.c              |  2 +-
 arch/s390/include/asm/cache.h         |  2 +-
 arch/s390/include/asm/sections.h      |  4 ++--
 arch/s390/mm/init.c                   |  2 +-
 arch/sh/boards/of-generic.c           |  2 +-
 arch/sh/include/asm/cache.h           |  2 +-
 arch/sh/include/asm/machvec.h         |  2 +-
 arch/sh/include/asm/smp.h             |  2 +-
 arch/sparc/include/asm/cache.h        |  2 +-
 arch/sparc/kernel/btext.c             |  2 +-
 arch/um/include/shared/init.h         | 22 +++++++++++-----------
 arch/um/kernel/skas/clone.c           |  2 +-
 arch/um/kernel/um_arch.c              |  2 +-
 arch/x86/boot/compressed/pgtable_64.c |  8 ++++----
 arch/x86/boot/tty.c                   |  8 ++++----
 arch/x86/boot/video.h                 |  2 +-
 arch/x86/include/asm/apic.h           |  4 ++--
 arch/x86/include/asm/cache.h          |  2 +-
 arch/x86/include/asm/intel-mid.h      |  2 +-
 arch/x86/include/asm/irqflags.h       |  2 +-
 arch/x86/include/asm/mem_encrypt.h    |  2 +-
 arch/x86/include/asm/setup.h          |  2 +-
 arch/x86/kernel/cpu/cpu.h             |  2 +-
 arch/x86/kernel/head64.c              |  2 +-
 arch/x86/mm/mem_encrypt.c             |  6 +++---
 arch/x86/mm/mem_encrypt_identity.c    |  2 +-
 arch/x86/platform/pvh/enlighten.c     |  4 ++--
 arch/x86/purgatory/purgatory.c        |  4 ++--
 arch/x86/um/stub_segv.c               |  2 +-
 arch/x86/xen/enlighten.c              |  2 +-
 arch/x86/xen/enlighten_pvh.c          |  2 +-
 arch/xtensa/kernel/setup.c            |  2 +-
 drivers/clk/clk.c                     |  2 +-
 drivers/clocksource/timer-probe.c     |  2 +-
 drivers/irqchip/irqchip.c             |  2 +-
 drivers/of/of_reserved_mem.c          |  2 +-
 drivers/thermal/thermal_core.h        |  2 +-
 fs/xfs/xfs_message.h                  |  2 +-
 include/asm-generic/bug.h             |  6 +++---
 include/asm-generic/error-injection.h |  2 +-
 include/asm-generic/kprobes.h         |  4 ++--
 include/kunit/test.h                  |  2 +-
 include/linux/acpi.h                  |  4 ++--
 include/linux/cache.h                 |  2 +-
 include/linux/compiler.h              |  8 ++++----
 include/linux/compiler_attributes.h   |  2 +-
 include/linux/cpu.h                   |  2 +-
 include/linux/dynamic_debug.h         |  2 +-
 include/linux/export.h                |  2 +-
 include/linux/firmware.h              |  2 +-
 include/linux/init.h                  | 34 +++++++++++++++++-----------------
 include/linux/init_task.h             |  4 ++--
 include/linux/interrupt.h             |  4 ++--
 include/linux/kernel.h                |  6 +++---
 include/linux/linkage.h               |  4 ++--
 include/linux/lsm_hooks.h             |  4 ++--
 include/linux/module.h                |  2 +-
 include/linux/moduleparam.h           |  4 ++--
 include/linux/mtd/xip.h               |  2 +-
 include/linux/objtool.h               |  2 +-
 include/linux/of.h                    |  2 +-
 include/linux/percpu-defs.h           |  2 +-
 include/linux/printk.h                |  4 ++--
 include/linux/rcupdate.h              |  2 +-
 include/linux/sched/debug.h           |  2 +-
 include/linux/serial_core.h           |  2 +-
 include/linux/spinlock.h              |  2 +-
 include/linux/syscalls.h              |  6 +++---
 include/linux/trace_events.h          |  2 +-
 include/linux/tracepoint.h            |  8 ++++----
 include/trace/bpf_probe.h             |  2 +-
 include/trace/trace_events.h          | 10 +++++-----
 kernel/kallsyms.c                     |  4 ++--
 kernel/sched/deadline.c               |  2 +-
 kernel/sched/fair.c                   |  2 +-
 kernel/sched/idle.c                   |  2 +-
 kernel/sched/rt.c                     |  2 +-
 kernel/sched/stop_task.c              |  2 +-
 kernel/trace/trace.h                  |  2 +-
 kernel/trace/trace_export.c           |  2 +-
 scripts/mod/modpost.c                 |  4 ++--
 tools/include/linux/objtool.h         |  2 +-
 117 files changed, 196 insertions(+), 196 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arc/include/asm/linkage.h b/arch/arc/include/asm/linkage.h
index fe19f1d412e7..c9434ff3aa4c 100644
--- a/arch/arc/include/asm/linkage.h
+++ b/arch/arc/include/asm/linkage.h
@@ -64,15 +64,15 @@
 #else	/* !__ASSEMBLY__ */
 
 #ifdef CONFIG_ARC_HAS_ICCM
-#define __arcfp_code __section(.text.arcfp)
+#define __arcfp_code __section(".text.arcfp")
 #else
-#define __arcfp_code __section(.text)
+#define __arcfp_code __section(".text")
 #endif
 
 #ifdef CONFIG_ARC_HAS_DCCM
-#define __arcfp_data __section(.data.arcfp)
+#define __arcfp_data __section(".data.arcfp")
 #else
-#define __arcfp_data __section(.data)
+#define __arcfp_data __section(".data")
 #endif
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/arc/include/asm/mach_desc.h b/arch/arc/include/asm/mach_desc.h
index 73746ed5b834..c4e197059379 100644
--- a/arch/arc/include/asm/mach_desc.h
+++ b/arch/arc/include/asm/mach_desc.h
@@ -53,7 +53,7 @@ extern const struct machine_desc __arch_info_begin[], __arch_info_end[];
  */
 #define MACHINE_START(_type, _name)			\
 static const struct machine_desc __mach_desc_##_type	\
-__used __section(.arch.info.init) = {			\
+__used __section(".arch.info.init") = {			\
 	.name		= _name,
 
 #define MACHINE_END				\
diff --git a/arch/arc/plat-hsdk/platform.c b/arch/arc/plat-hsdk/platform.c
index 0b961a2a10b8..0b63fc095b99 100644
--- a/arch/arc/plat-hsdk/platform.c
+++ b/arch/arc/plat-hsdk/platform.c
@@ -13,7 +13,7 @@
 #include <asm/io.h>
 #include <asm/mach_desc.h>
 
-int arc_hsdk_axi_dmac_coherent __section(.data) = 0;
+int arc_hsdk_axi_dmac_coherent __section(".data") = 0;
 
 #define ARC_CCM_UNUSED_ADDR	0x60000000
 
diff --git a/arch/arm/include/asm/cache.h b/arch/arm/include/asm/cache.h
index 1d65ed3a2755..e3ea34558ada 100644
--- a/arch/arm/include/asm/cache.h
+++ b/arch/arm/include/asm/cache.h
@@ -24,6 +24,6 @@
 #define ARCH_SLAB_MINALIGN 8
 #endif
 
-#define __read_mostly __attribute__((__section__(".data..read_mostly")))
+#define __read_mostly __section(".data..read_mostly")
 
 #endif
diff --git a/arch/arm/include/asm/cpuidle.h b/arch/arm/include/asm/cpuidle.h
index 6b2ff7243b4b..0d67ed682e07 100644
--- a/arch/arm/include/asm/cpuidle.h
+++ b/arch/arm/include/asm/cpuidle.h
@@ -42,7 +42,7 @@ struct of_cpuidle_method {
 
 #define CPUIDLE_METHOD_OF_DECLARE(name, _method, _ops)			\
 	static const struct of_cpuidle_method __cpuidle_method_of_table_##name \
-	__used __section(__cpuidle_method_of_table)			\
+	__used __section("__cpuidle_method_of_table")			\
 	= { .method = _method, .ops = _ops }
 
 extern int arm_cpuidle_suspend(int index);
diff --git a/arch/arm/include/asm/idmap.h b/arch/arm/include/asm/idmap.h
index aab7e8358e6a..baebb67b3512 100644
--- a/arch/arm/include/asm/idmap.h
+++ b/arch/arm/include/asm/idmap.h
@@ -6,7 +6,7 @@
 #include <linux/pgtable.h>
 
 /* Tag a function as requiring to be executed via an identity mapping. */
-#define __idmap __section(.idmap.text) noinline notrace
+#define __idmap __section(".idmap.text") noinline notrace
 
 extern pgd_t *idmap_pgd;
 
diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h
index e7df5a822cab..eec0c0bda766 100644
--- a/arch/arm/include/asm/mach/arch.h
+++ b/arch/arm/include/asm/mach/arch.h
@@ -81,7 +81,7 @@ extern const struct machine_desc __arch_info_begin[], __arch_info_end[];
 #define MACHINE_START(_type,_name)			\
 static const struct machine_desc __mach_desc_##_type	\
  __used							\
- __attribute__((__section__(".arch.info.init"))) = {	\
+ __section(".arch.info.init") = {			\
 	.nr		= MACH_TYPE_##_type,		\
 	.name		= _name,
 
@@ -91,7 +91,7 @@ static const struct machine_desc __mach_desc_##_type	\
 #define DT_MACHINE_START(_name, _namestr)		\
 static const struct machine_desc __mach_desc_##_name	\
  __used							\
- __attribute__((__section__(".arch.info.init"))) = {	\
+ __section(".arch.info.init") = {			\
 	.nr		= ~0,				\
 	.name		= _namestr,
 
diff --git a/arch/arm/include/asm/setup.h b/arch/arm/include/asm/setup.h
index 67d20712cb48..3ae68a1b3de6 100644
--- a/arch/arm/include/asm/setup.h
+++ b/arch/arm/include/asm/setup.h
@@ -14,7 +14,7 @@
 #include <uapi/asm/setup.h>
 
 
-#define __tag __used __attribute__((__section__(".taglist.init")))
+#define __tag __used __section(".taglist.init")
 #define __tagtable(tag, fn) \
 static const struct tagtable __tagtable_##fn __tag = { tag, fn }
 
diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h
index 0ca55a607d0a..5d508f5d56c4 100644
--- a/arch/arm/include/asm/smp.h
+++ b/arch/arm/include/asm/smp.h
@@ -112,7 +112,7 @@ struct of_cpu_method {
 
 #define CPU_METHOD_OF_DECLARE(name, _method, _ops)			\
 	static const struct of_cpu_method __cpu_method_of_table_##name	\
-		__used __section(__cpu_method_of_table)			\
+		__used __section("__cpu_method_of_table")		\
 		= { .method = _method, .ops = _ops }
 /*
  * set platform specific SMP operations
diff --git a/arch/arm/include/asm/tcm.h b/arch/arm/include/asm/tcm.h
index b845b10fe29a..d8bd8a4b0ede 100644
--- a/arch/arm/include/asm/tcm.h
+++ b/arch/arm/include/asm/tcm.h
@@ -16,13 +16,13 @@
 #include <linux/compiler.h>
 
 /* Tag variables with this */
-#define __tcmdata __section(.tcm.data)
+#define __tcmdata __section(".tcm.data")
 /* Tag constants with this */
-#define __tcmconst __section(.tcm.rodata)
+#define __tcmconst __section(".tcm.rodata")
 /* Tag functions inside TCM called from outside TCM with this */
-#define __tcmfunc __attribute__((long_call)) __section(.tcm.text) noinline
+#define __tcmfunc __attribute__((long_call)) __section(".tcm.text") noinline
 /* Tag function inside TCM called from inside TCM  with this */
-#define __tcmlocalfunc __section(.tcm.text)
+#define __tcmlocalfunc __section(".tcm.text")
 
 void *tcm_alloc(size_t len);
 void tcm_free(void *addr, size_t len);
diff --git a/arch/arm/kernel/cpuidle.c b/arch/arm/kernel/cpuidle.c
index 093368e0d020..e1684623e1b2 100644
--- a/arch/arm/kernel/cpuidle.c
+++ b/arch/arm/kernel/cpuidle.c
@@ -11,7 +11,7 @@
 extern struct of_cpuidle_method __cpuidle_method_of_table[];
 
 static const struct of_cpuidle_method __cpuidle_method_of_table_sentinel
-	__used __section(__cpuidle_method_of_table_end);
+	__used __section("__cpuidle_method_of_table_end");
 
 static struct cpuidle_ops cpuidle_ops[NR_CPUS] __ro_after_init;
 
diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c
index 39c978698406..7f0745a97e20 100644
--- a/arch/arm/kernel/devtree.c
+++ b/arch/arm/kernel/devtree.c
@@ -29,7 +29,7 @@
 extern struct of_cpu_method __cpu_method_of_table[];
 
 static const struct of_cpu_method __cpu_method_of_table_sentinel
-	__used __section(__cpu_method_of_table_end);
+	__used __section("__cpu_method_of_table_end");
 
 
 static int __init set_smp_ops_by_method(struct device_node *node)
diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h
index a4d1b5f771f6..0ac3e06a2118 100644
--- a/arch/arm64/include/asm/cache.h
+++ b/arch/arm64/include/asm/cache.h
@@ -79,7 +79,7 @@ static inline u32 cache_type_cwg(void)
 	return (read_cpuid_cachetype() >> CTR_CWG_SHIFT) & CTR_CWG_MASK;
 }
 
-#define __read_mostly __section(.data..read_mostly)
+#define __read_mostly __section(".data..read_mostly")
 
 static inline int cache_line_size_of_cpu(void)
 {
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index d0cf596db82c..fa02efb28e88 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -54,7 +54,7 @@ static __init pteval_t create_mapping_protection(efi_memory_desc_t *md)
 }
 
 /* we will fill this structure from the stub, so don't put it in .bss */
-struct screen_info screen_info __section(.data);
+struct screen_info screen_info __section(".data");
 
 int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md)
 {
diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c
index 5892e79fa429..056772c26098 100644
--- a/arch/arm64/kernel/smp_spin_table.c
+++ b/arch/arm64/kernel/smp_spin_table.c
@@ -19,7 +19,7 @@
 #include <asm/smp_plat.h>
 
 extern void secondary_holding_pen(void);
-volatile unsigned long __section(.mmuoff.data.read)
+volatile unsigned long __section(".mmuoff.data.read")
 secondary_holding_pen_release = INVALID_HWID;
 
 static phys_addr_t cpu_release_addr[NR_CPUS];
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index beff3ad8c7f8..1c0f3e02f731 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -43,7 +43,7 @@
 u64 idmap_t0sz = TCR_T0SZ(VA_BITS);
 u64 idmap_ptrs_per_pgd = PTRS_PER_PGD;
 
-u64 __section(.mmuoff.data.write) vabits_actual;
+u64 __section(".mmuoff.data.write") vabits_actual;
 EXPORT_SYMBOL(vabits_actual);
 
 u64 kimage_voffset __ro_after_init;
diff --git a/arch/csky/include/asm/tcm.h b/arch/csky/include/asm/tcm.h
index 2b135cefb73f..bd1e662ecdfa 100644
--- a/arch/csky/include/asm/tcm.h
+++ b/arch/csky/include/asm/tcm.h
@@ -10,13 +10,13 @@
 #include <linux/compiler.h>
 
 /* Tag variables with this */
-#define __tcmdata __section(.tcm.data)
+#define __tcmdata __section(".tcm.data")
 /* Tag constants with this */
-#define __tcmconst __section(.tcm.rodata)
+#define __tcmconst __section(".tcm.rodata")
 /* Tag functions inside TCM called from outside TCM with this */
-#define __tcmfunc __section(.tcm.text) noinline
+#define __tcmfunc __section(".tcm.text") noinline
 /* Tag function inside TCM called from inside TCM  with this */
-#define __tcmlocalfunc __section(.tcm.text)
+#define __tcmlocalfunc __section(".tcm.text")
 
 void *tcm_alloc(size_t len);
 void tcm_free(void *addr, size_t len);
diff --git a/arch/ia64/include/asm/cache.h b/arch/ia64/include/asm/cache.h
index 4eb6f742d14f..2f1c70647068 100644
--- a/arch/ia64/include/asm/cache.h
+++ b/arch/ia64/include/asm/cache.h
@@ -25,6 +25,6 @@
 # define SMP_CACHE_BYTES	(1 << 3)
 #endif
 
-#define __read_mostly __attribute__((__section__(".data..read_mostly")))
+#define __read_mostly __section(".data..read_mostly")
 
 #endif /* _ASM_IA64_CACHE_H */
diff --git a/arch/microblaze/kernel/setup.c b/arch/microblaze/kernel/setup.c
index 2310daff1f8a..333b09658ca8 100644
--- a/arch/microblaze/kernel/setup.c
+++ b/arch/microblaze/kernel/setup.c
@@ -46,7 +46,7 @@ DEFINE_PER_CPU(unsigned int, CURRENT_SAVE);	/* Saved current pointer */
  * ASM code. Default position is BSS section which is cleared
  * in machine_early_init().
  */
-char cmd_line[COMMAND_LINE_SIZE] __attribute__ ((section(".data")));
+char cmd_line[COMMAND_LINE_SIZE] __section(".data");
 
 void __init setup_arch(char **cmdline_p)
 {
diff --git a/arch/mips/include/asm/cache.h b/arch/mips/include/asm/cache.h
index 8b14c2706aa5..29187e12b861 100644
--- a/arch/mips/include/asm/cache.h
+++ b/arch/mips/include/asm/cache.h
@@ -14,6 +14,6 @@
 #define L1_CACHE_SHIFT		CONFIG_MIPS_L1_CACHE_SHIFT
 #define L1_CACHE_BYTES		(1 << L1_CACHE_SHIFT)
 
-#define __read_mostly __attribute__((__section__(".data..read_mostly")))
+#define __read_mostly __section(".data..read_mostly")
 
 #endif /* _ASM_CACHE_H */
diff --git a/arch/mips/include/asm/machine.h b/arch/mips/include/asm/machine.h
index 29ca344a8cab..fc64cce270f0 100644
--- a/arch/mips/include/asm/machine.h
+++ b/arch/mips/include/asm/machine.h
@@ -23,7 +23,7 @@ extern long __mips_machines_end;
 
 #define MIPS_MACHINE(name)						\
 	static const struct mips_machine __mips_mach_##name		\
-		__used __section(.mips.machines.init)
+		__used __section(".mips.machines.init")
 
 #define for_each_mips_machine(mach)					\
 	for ((mach) = (struct mips_machine *)&__mips_machines_start;	\
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index fccdbe2e7c2b..0d4253208bde 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -44,7 +44,7 @@
 #include <asm/prom.h>
 
 #ifdef CONFIG_MIPS_ELF_APPENDED_DTB
-const char __section(.appended_dtb) __appended_dtb[0x100000];
+const char __section(".appended_dtb") __appended_dtb[0x100000];
 #endif /* CONFIG_MIPS_ELF_APPENDED_DTB */
 
 struct cpuinfo_mips cpu_data[NR_CPUS] __read_mostly;
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index 6c7bbfe35ba3..07e84a774938 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -569,7 +569,7 @@ unsigned long pgd_current[NR_CPUS];
  * size, and waste space.  So we place it in its own section and align
  * it in the linker script.
  */
-pgd_t swapper_pg_dir[PTRS_PER_PGD] __section(.bss..swapper_pg_dir);
+pgd_t swapper_pg_dir[PTRS_PER_PGD] __section(".bss..swapper_pg_dir");
 #ifndef __PAGETABLE_PUD_FOLDED
 pud_t invalid_pud_table[PTRS_PER_PUD] __page_aligned_bss;
 #endif
diff --git a/arch/parisc/include/asm/cache.h b/arch/parisc/include/asm/cache.h
index e5de3f897633..d53e9e27dba0 100644
--- a/arch/parisc/include/asm/cache.h
+++ b/arch/parisc/include/asm/cache.h
@@ -22,7 +22,7 @@
 
 #define ARCH_DMA_MINALIGN	L1_CACHE_BYTES
 
-#define __read_mostly __section(.data..read_mostly)
+#define __read_mostly __section(".data..read_mostly")
 
 void parisc_cache_init(void);	/* initializes cache-flushing */
 void disable_sr_hashing_asm(int); /* low level support for above */
diff --git a/arch/parisc/include/asm/ldcw.h b/arch/parisc/include/asm/ldcw.h
index e080143e79a3..6d28b5514699 100644
--- a/arch/parisc/include/asm/ldcw.h
+++ b/arch/parisc/include/asm/ldcw.h
@@ -52,7 +52,7 @@
 })
 
 #ifdef CONFIG_SMP
-# define __lock_aligned __section(.data..lock_aligned)
+# define __lock_aligned __section(".data..lock_aligned")
 #endif
 
 #endif /* __PARISC_LDCW_H */
diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c
index 4bab21c71055..63e3ecb9da81 100644
--- a/arch/parisc/kernel/ftrace.c
+++ b/arch/parisc/kernel/ftrace.c
@@ -21,7 +21,7 @@
 #include <asm/ftrace.h>
 #include <asm/patch.h>
 
-#define __hot __attribute__ ((__section__ (".text.hot")))
+#define __hot __section(".text.hot")
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 /*
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index 4381b65ae1e0..3ec633b11b54 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -42,11 +42,11 @@ extern void parisc_kernel_start(void);	/* Kernel entry point in head.S */
  * guarantee that global objects will be laid out in memory in the same order
  * as the order of declaration, so put these in different sections and use
  * the linker script to order them. */
-pmd_t pmd0[PTRS_PER_PMD] __attribute__ ((__section__ (".data..vm0.pmd"), aligned(PAGE_SIZE)));
+pmd_t pmd0[PTRS_PER_PMD] __section(".data..vm0.pmd") __attribute__ ((aligned(PAGE_SIZE)));
 #endif
 
-pgd_t swapper_pg_dir[PTRS_PER_PGD] __attribute__ ((__section__ (".data..vm0.pgd"), aligned(PAGE_SIZE)));
-pte_t pg0[PT_INITIAL * PTRS_PER_PTE] __attribute__ ((__section__ (".data..vm0.pte"), aligned(PAGE_SIZE)));
+pgd_t swapper_pg_dir[PTRS_PER_PGD] __section(".data..vm0.pgd") __attribute__ ((aligned(PAGE_SIZE)));
+pte_t pg0[PT_INITIAL * PTRS_PER_PTE] __section(".data..vm0.pte") __attribute__ ((aligned(PAGE_SIZE)));
 
 static struct resource data_resource = {
 	.name	= "Kernel data",
diff --git a/arch/powerpc/include/asm/cache.h b/arch/powerpc/include/asm/cache.h
index 2124b7090db9..ae0a68a838e8 100644
--- a/arch/powerpc/include/asm/cache.h
+++ b/arch/powerpc/include/asm/cache.h
@@ -97,7 +97,7 @@ static inline u32 l1_icache_bytes(void)
 
 #endif
 
-#define __read_mostly __section(.data..read_mostly)
+#define __read_mostly __section(".data..read_mostly")
 
 #ifdef CONFIG_PPC_BOOK3S_32
 extern long _get_L2CR(void);
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 95081078aa8a..475687f24f4a 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -232,7 +232,7 @@ extern void book3e_idle(void);
 extern struct machdep_calls ppc_md;
 extern struct machdep_calls *machine_id;
 
-#define __machine_desc __attribute__ ((__section__ (".machine.desc")))
+#define __machine_desc __section(".machine.desc")
 
 #define define_machine(name)					\
 	extern struct machdep_calls mach_##name;		\
diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c
index c22a8e0dbc93..803c2a45b22a 100644
--- a/arch/powerpc/kernel/btext.c
+++ b/arch/powerpc/kernel/btext.c
@@ -26,7 +26,7 @@
 static void scrollscreen(void);
 #endif
 
-#define __force_data __section(.data)
+#define __force_data __section(".data")
 
 static int g_loc_X __force_data;
 static int g_loc_Y __force_data;
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 5090a5ab54e5..38ae5933d917 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -45,7 +45,7 @@
 #include <linux/linux_logo.h>
 
 /* All of prom_init bss lives here */
-#define __prombss __section(.bss.prominit)
+#define __prombss __section(".bss.prominit")
 
 /*
  * Eventually bump that one up
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index 470e7c518a10..083a4e037718 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -32,7 +32,7 @@
 #ifdef CONFIG_BUG
 
 #define WARN_ON_ONCE_RM(condition)	({			\
-	static bool __section(.data.unlikely) __warned;		\
+	static bool __section(".data.unlikely") __warned;	\
 	int __ret_warn_once = !!(condition);			\
 								\
 	if (unlikely(__ret_warn_once && !__warned)) {		\
diff --git a/arch/riscv/include/asm/soc.h b/arch/riscv/include/asm/soc.h
index 136a442ef876..6c8363b1f327 100644
--- a/arch/riscv/include/asm/soc.h
+++ b/arch/riscv/include/asm/soc.h
@@ -13,7 +13,7 @@
 
 #define SOC_EARLY_INIT_DECLARE(name, compat, fn)			\
 	static const struct of_device_id __soc_early_init__##name	\
-		__used __section(__soc_early_init_table)		\
+		__used __section("__soc_early_init_table")		\
 		 = { .compatible = compat, .data = fn  }
 
 void soc_early_init(void);
@@ -46,7 +46,7 @@ struct soc_builtin_dtb {
 	}								\
 									\
 	static const struct soc_builtin_dtb __soc_builtin_dtb__##name	\
-		__used __section(__soc_builtin_dtb_table) =		\
+		__used __section("__soc_builtin_dtb_table") =		\
 	{								\
 		.vendor_id = vendor,					\
 		.arch_id   = arch,					\
diff --git a/arch/riscv/kernel/cpu_ops.c b/arch/riscv/kernel/cpu_ops.c
index 0ec22354018c..1985884fe829 100644
--- a/arch/riscv/kernel/cpu_ops.c
+++ b/arch/riscv/kernel/cpu_ops.c
@@ -15,8 +15,8 @@
 
 const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init;
 
-void *__cpu_up_stack_pointer[NR_CPUS] __section(.data);
-void *__cpu_up_task_pointer[NR_CPUS] __section(.data);
+void *__cpu_up_stack_pointer[NR_CPUS] __section(".data");
+void *__cpu_up_task_pointer[NR_CPUS] __section(".data");
 
 extern const struct cpu_operations cpu_ops_sbi;
 extern const struct cpu_operations cpu_ops_spinwait;
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 4c96ac198e14..c424cc6dd833 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -32,7 +32,7 @@
 #include "head.h"
 
 #if defined(CONFIG_DUMMY_CONSOLE) || defined(CONFIG_EFI)
-struct screen_info screen_info __section(.data) = {
+struct screen_info screen_info __section(".data") = {
 	.orig_video_lines	= 30,
 	.orig_video_cols	= 80,
 	.orig_video_mode	= 0,
@@ -47,7 +47,7 @@ struct screen_info screen_info __section(.data) = {
  * This is used before the kernel initializes the BSS so it can't be in the
  * BSS.
  */
-atomic_t hart_lottery __section(.sdata);
+atomic_t hart_lottery __section(".sdata");
 unsigned long boot_cpu_hartid;
 static DEFINE_PER_CPU(struct cpu, cpu_devices);
 
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index 90842936545b..cc96b04cc0ba 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -46,7 +46,7 @@ struct diag_ops __bootdata_preserved(diag_dma_ops) = {
 	.diag0c = _diag0c_dma,
 	.diag308_reset = _diag308_reset_dma
 };
-static struct diag210 _diag210_tmp_dma __section(.dma.data);
+static struct diag210 _diag210_tmp_dma __section(".dma.data");
 struct diag210 *__bootdata_preserved(__diag210_tmp_dma) = &_diag210_tmp_dma;
 
 void error(char *x)
diff --git a/arch/s390/include/asm/cache.h b/arch/s390/include/asm/cache.h
index d5e22e837416..00128174c025 100644
--- a/arch/s390/include/asm/cache.h
+++ b/arch/s390/include/asm/cache.h
@@ -14,6 +14,6 @@
 #define L1_CACHE_SHIFT     8
 #define NET_SKB_PAD	   32
 
-#define __read_mostly __section(.data..read_mostly)
+#define __read_mostly __section(".data..read_mostly")
 
 #endif
diff --git a/arch/s390/include/asm/sections.h b/arch/s390/include/asm/sections.h
index 42de04ad9c07..a996d3990a02 100644
--- a/arch/s390/include/asm/sections.h
+++ b/arch/s390/include/asm/sections.h
@@ -26,14 +26,14 @@ static inline int arch_is_kernel_initmem_freed(unsigned long addr)
  * final .boot.data section, which should be identical in the decompressor and
  * the decompressed kernel (that is checked during the build).
  */
-#define __bootdata(var) __section(.boot.data.var) var
+#define __bootdata(var) __section(".boot.data.var") var
 
 /*
  * .boot.preserved.data is similar to .boot.data, but it is not part of the
  * .init section and thus will be preserved for later use in the decompressed
  * kernel.
  */
-#define __bootdata_preserved(var) __section(.boot.preserved.data.var) var
+#define __bootdata_preserved(var) __section(".boot.preserved.data.var") var
 
 extern unsigned long __sdma, __edma;
 extern unsigned long __stext_dma, __etext_dma;
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 284939f9661c..77767850d0d0 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -48,7 +48,7 @@
 #include <asm/uv.h>
 #include <linux/virtio_config.h>
 
-pgd_t swapper_pg_dir[PTRS_PER_PGD] __section(.bss..swapper_pg_dir);
+pgd_t swapper_pg_dir[PTRS_PER_PGD] __section(".bss..swapper_pg_dir");
 
 unsigned long empty_zero_page, zero_page_mask;
 EXPORT_SYMBOL(empty_zero_page);
diff --git a/arch/sh/boards/of-generic.c b/arch/sh/boards/of-generic.c
index d91065e81a4e..bffbe69b2236 100644
--- a/arch/sh/boards/of-generic.c
+++ b/arch/sh/boards/of-generic.c
@@ -49,7 +49,7 @@ static struct plat_smp_ops dummy_smp_ops = {
 
 extern const struct of_cpu_method __cpu_method_of_table[];
 const struct of_cpu_method __cpu_method_of_table_sentinel
-	__section(__cpu_method_of_table_end);
+	__section("__cpu_method_of_table_end");
 
 static void sh_of_smp_probe(void)
 {
diff --git a/arch/sh/include/asm/cache.h b/arch/sh/include/asm/cache.h
index a293343456af..32dfa6b82ec6 100644
--- a/arch/sh/include/asm/cache.h
+++ b/arch/sh/include/asm/cache.h
@@ -14,7 +14,7 @@
 
 #define L1_CACHE_BYTES		(1 << L1_CACHE_SHIFT)
 
-#define __read_mostly __attribute__((__section__(".data..read_mostly")))
+#define __read_mostly __section(".data..read_mostly")
 
 #ifndef __ASSEMBLY__
 struct cache_info {
diff --git a/arch/sh/include/asm/machvec.h b/arch/sh/include/asm/machvec.h
index f7d05546beca..2b4b085e8f21 100644
--- a/arch/sh/include/asm/machvec.h
+++ b/arch/sh/include/asm/machvec.h
@@ -36,6 +36,6 @@ extern struct sh_machine_vector sh_mv;
 #define get_system_type()	sh_mv.mv_name
 
 #define __initmv \
-	__used __section(.machvec.init)
+	__used __section(".machvec.init")
 
 #endif /* _ASM_SH_MACHVEC_H */
diff --git a/arch/sh/include/asm/smp.h b/arch/sh/include/asm/smp.h
index 100bf241340b..199381f77293 100644
--- a/arch/sh/include/asm/smp.h
+++ b/arch/sh/include/asm/smp.h
@@ -71,7 +71,7 @@ struct of_cpu_method {
 
 #define CPU_METHOD_OF_DECLARE(name, _method, _ops)			\
 	static const struct of_cpu_method __cpu_method_of_table_##name	\
-		__used __section(__cpu_method_of_table)			\
+		__used __section("__cpu_method_of_table")		\
 		= { .method = _method, .ops = _ops }
 
 #else
diff --git a/arch/sparc/include/asm/cache.h b/arch/sparc/include/asm/cache.h
index dcfd58118c11..e62fd0e72606 100644
--- a/arch/sparc/include/asm/cache.h
+++ b/arch/sparc/include/asm/cache.h
@@ -21,6 +21,6 @@
 
 #define SMP_CACHE_BYTES (1 << SMP_CACHE_BYTES_SHIFT)
 
-#define __read_mostly __attribute__((__section__(".data..read_mostly")))
+#define __read_mostly __section(".data..read_mostly")
 
 #endif /* !(_SPARC_CACHE_H) */
diff --git a/arch/sparc/kernel/btext.c b/arch/sparc/kernel/btext.c
index 5869773f3dc4..e2d3f0d2971f 100644
--- a/arch/sparc/kernel/btext.c
+++ b/arch/sparc/kernel/btext.c
@@ -24,7 +24,7 @@ static void draw_byte_32(unsigned char *bits, unsigned int *base, int rb);
 static void draw_byte_16(unsigned char *bits, unsigned int *base, int rb);
 static void draw_byte_8(unsigned char *bits, unsigned int *base, int rb);
 
-#define __force_data __attribute__((__section__(".data")))
+#define __force_data __section(".data")
 
 static int g_loc_X __force_data;
 static int g_loc_Y __force_data;
diff --git a/arch/um/include/shared/init.h b/arch/um/include/shared/init.h
index c66de434a983..1a659e2e8cc3 100644
--- a/arch/um/include/shared/init.h
+++ b/arch/um/include/shared/init.h
@@ -45,15 +45,15 @@ typedef void (*exitcall_t)(void);
 
 /* These are for everybody (although not all archs will actually
    discard it in modules) */
-#define __init		__section(.init.text)
-#define __initdata	__section(.init.data)
-#define __exitdata	__section(.exit.data)
-#define __exit_call	__used __section(.exitcall.exit)
+#define __init		__section(".init.text")
+#define __initdata	__section(".init.data")
+#define __exitdata	__section(".exit.data")
+#define __exit_call	__used __section(".exitcall.exit")
 
 #ifdef MODULE
-#define __exit		__section(.exit.text)
+#define __exit		__section(".exit.text")
 #else
-#define __exit		__used __section(.exit.text)
+#define __exit		__used __section(".exit.text")
 #endif
 
 #endif
@@ -102,10 +102,10 @@ extern struct uml_param __uml_setup_start, __uml_setup_end;
  * Mark functions and data as being only used at initialization
  * or exit time.
  */
-#define __uml_init_setup	__used __section(.uml.setup.init)
-#define __uml_setup_help	__used __section(.uml.help.init)
-#define __uml_postsetup_call	__used __section(.uml.postsetup.init)
-#define __uml_exit_call		__used __section(.uml.exitcall.exit)
+#define __uml_init_setup	__used __section(".uml.setup.init")
+#define __uml_setup_help	__used __section(".uml.help.init")
+#define __uml_postsetup_call	__used __section(".uml.postsetup.init")
+#define __uml_exit_call		__used __section(".uml.exitcall.exit")
 
 #ifdef __UM_HOST__
 
@@ -120,7 +120,7 @@ extern struct uml_param __uml_setup_start, __uml_setup_end;
 
 #define __exitcall(fn) static exitcall_t __exitcall_##fn __exit_call = fn
 
-#define __init_call	__used __section(.initcall.init)
+#define __init_call	__used __section(".initcall.init")
 
 #endif
 
diff --git a/arch/um/kernel/skas/clone.c b/arch/um/kernel/skas/clone.c
index bfb70c456b30..95c355181dcd 100644
--- a/arch/um/kernel/skas/clone.c
+++ b/arch/um/kernel/skas/clone.c
@@ -21,7 +21,7 @@
  * on some systems.
  */
 
-void __attribute__ ((__section__ (".__syscall_stub")))
+void __section(".__syscall_stub")
 stub_clone_handler(void)
 {
 	struct stub_data *data = (struct stub_data *) STUB_DATA;
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index 00141e70de56..76b37297b7d4 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -52,7 +52,7 @@ struct cpuinfo_um boot_cpu_data = {
 };
 
 union thread_union cpu0_irqstack
-	__attribute__((__section__(".data..init_irqstack"))) =
+	__section(".data..init_irqstack") =
 		{ .thread_info = INIT_THREAD_INFO(init_task) };
 
 /* Changed in setup_arch, which is called in early boot */
diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c
index 5def1674d6f1..2a78746f5a4c 100644
--- a/arch/x86/boot/compressed/pgtable_64.c
+++ b/arch/x86/boot/compressed/pgtable_64.c
@@ -10,9 +10,9 @@
 
 #ifdef CONFIG_X86_5LEVEL
 /* __pgtable_l5_enabled needs to be in .data to avoid being cleared along with .bss */
-unsigned int __section(.data) __pgtable_l5_enabled;
-unsigned int __section(.data) pgdir_shift = 39;
-unsigned int __section(.data) ptrs_per_p4d = 1;
+unsigned int __section(".data") __pgtable_l5_enabled;
+unsigned int __section(".data") pgdir_shift = 39;
+unsigned int __section(".data") ptrs_per_p4d = 1;
 #endif
 
 struct paging_config {
@@ -30,7 +30,7 @@ static char trampoline_save[TRAMPOLINE_32BIT_SIZE];
  * Avoid putting the pointer into .bss as it will be cleared between
  * paging_prepare() and extract_kernel().
  */
-unsigned long *trampoline_32bit __section(.data);
+unsigned long *trampoline_32bit __section(".data");
 
 extern struct boot_params *boot_params;
 int cmdline_find_option_bool(const char *option);
diff --git a/arch/x86/boot/tty.c b/arch/x86/boot/tty.c
index 1fedabdb95ad..f7eb976b0a4b 100644
--- a/arch/x86/boot/tty.c
+++ b/arch/x86/boot/tty.c
@@ -25,7 +25,7 @@ int early_serial_base;
  * error during initialization.
  */
 
-static void __attribute__((section(".inittext"))) serial_putchar(int ch)
+static void __section(".inittext") serial_putchar(int ch)
 {
 	unsigned timeout = 0xffff;
 
@@ -35,7 +35,7 @@ static void __attribute__((section(".inittext"))) serial_putchar(int ch)
 	outb(ch, early_serial_base + TXR);
 }
 
-static void __attribute__((section(".inittext"))) bios_putchar(int ch)
+static void __section(".inittext") bios_putchar(int ch)
 {
 	struct biosregs ireg;
 
@@ -47,7 +47,7 @@ static void __attribute__((section(".inittext"))) bios_putchar(int ch)
 	intcall(0x10, &ireg, NULL);
 }
 
-void __attribute__((section(".inittext"))) putchar(int ch)
+void __section(".inittext") putchar(int ch)
 {
 	if (ch == '\n')
 		putchar('\r');	/* \n -> \r\n */
@@ -58,7 +58,7 @@ void __attribute__((section(".inittext"))) putchar(int ch)
 		serial_putchar(ch);
 }
 
-void __attribute__((section(".inittext"))) puts(const char *str)
+void __section(".inittext") puts(const char *str)
 {
 	while (*str)
 		putchar(*str++);
diff --git a/arch/x86/boot/video.h b/arch/x86/boot/video.h
index cbf7fed22441..04bde0bb2003 100644
--- a/arch/x86/boot/video.h
+++ b/arch/x86/boot/video.h
@@ -78,7 +78,7 @@ struct card_info {
 	u16 xmode_n;		/* Size of unprobed mode range */
 };
 
-#define __videocard struct card_info __attribute__((used,section(".videocards")))
+#define __videocard struct card_info __section(".videocards") __attribute__((used))
 extern struct card_info video_cards[], video_cards_end[];
 
 int mode_defined(u16 mode);	/* video.c */
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 1c129abb7f09..4e3099d9ae62 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -374,12 +374,12 @@ extern struct apic *apic;
 #define apic_driver(sym)					\
 	static const struct apic *__apicdrivers_##sym __used		\
 	__aligned(sizeof(struct apic *))			\
-	__section(.apicdrivers) = { &sym }
+	__section(".apicdrivers") = { &sym }
 
 #define apic_drivers(sym1, sym2)					\
 	static struct apic *__apicdrivers_##sym1##sym2[2] __used	\
 	__aligned(sizeof(struct apic *))				\
-	__section(.apicdrivers) = { &sym1, &sym2 }
+	__section(".apicdrivers") = { &sym1, &sym2 }
 
 extern struct apic *__apicdrivers[], *__apicdrivers_end[];
 
diff --git a/arch/x86/include/asm/cache.h b/arch/x86/include/asm/cache.h
index abe08690a887..69404eae9983 100644
--- a/arch/x86/include/asm/cache.h
+++ b/arch/x86/include/asm/cache.h
@@ -8,7 +8,7 @@
 #define L1_CACHE_SHIFT	(CONFIG_X86_L1_CACHE_SHIFT)
 #define L1_CACHE_BYTES	(1 << L1_CACHE_SHIFT)
 
-#define __read_mostly __attribute__((__section__(".data..read_mostly")))
+#define __read_mostly __section(".data..read_mostly")
 
 #define INTERNODE_CACHE_SHIFT CONFIG_X86_INTERNODE_CACHE_SHIFT
 #define INTERNODE_CACHE_BYTES (1 << INTERNODE_CACHE_SHIFT)
diff --git a/arch/x86/include/asm/intel-mid.h b/arch/x86/include/asm/intel-mid.h
index de58391bdee0..cf0e25f45422 100644
--- a/arch/x86/include/asm/intel-mid.h
+++ b/arch/x86/include/asm/intel-mid.h
@@ -43,7 +43,7 @@ struct devs_id {
 
 #define sfi_device(i)								\
 	static const struct devs_id *const __intel_mid_sfi_##i##_dev __used	\
-	__attribute__((__section__(".x86_intel_mid_dev.init"))) = &i
+	__section(".x86_intel_mid_dev.init") = &i
 
 /**
 * struct mid_sd_board_info - template for SD device creation
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index 02a0cf547d7b..2dfc8d380dab 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -9,7 +9,7 @@
 #include <asm/nospec-branch.h>
 
 /* Provide __cpuidle; we can't safely include <linux/cpu.h> */
-#define __cpuidle __attribute__((__section__(".cpuidle.text")))
+#define __cpuidle __section(".cpuidle.text")
 
 /*
  * Interrupt control:
diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index c9f5df0a1c10..2f62bbdd9d12 100644
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -54,7 +54,7 @@ bool sme_active(void);
 bool sev_active(void);
 bool sev_es_active(void);
 
-#define __bss_decrypted __attribute__((__section__(".bss..decrypted")))
+#define __bss_decrypted __section(".bss..decrypted")
 
 #else	/* !CONFIG_AMD_MEM_ENCRYPT */
 
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index 7d7a064af6ff..389d851a02c4 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -119,7 +119,7 @@ void *extend_brk(size_t size, size_t align);
  * executable.)
  */
 #define RESERVE_BRK(name,sz)						\
-	static void __section(.discard.text) __used notrace		\
+	static void __section(".discard.text") __used notrace		\
 	__brk_reservation_fn_##name##__(void) {				\
 		asm volatile (						\
 			".pushsection .brk_reservation,\"aw\",@nobits;" \
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 9d033693519a..67944128876d 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -38,7 +38,7 @@ struct _tlb_table {
 
 #define cpu_dev_register(cpu_devX) \
 	static const struct cpu_dev *const __cpu_dev_##cpu_devX __used \
-	__attribute__((__section__(".x86_cpu_dev.init"))) = \
+	__section(".x86_cpu_dev.init") = \
 	&cpu_devX;
 
 extern const struct cpu_dev *const __x86_cpu_dev_start[],
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 4199f25c0063..05e117137b45 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -84,7 +84,7 @@ static struct desc_ptr startup_gdt_descr = {
 	.address = 0,
 };
 
-#define __head	__section(.head.text)
+#define __head	__section(".head.text")
 
 static void __head *fixup_pointer(void *ptr, unsigned long physaddr)
 {
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index ebb7edc8bc0a..efbb3de472df 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -37,13 +37,13 @@
  * reside in the .data section so as not to be zeroed out when the .bss
  * section is later cleared.
  */
-u64 sme_me_mask __section(.data) = 0;
-u64 sev_status __section(.data) = 0;
+u64 sme_me_mask __section(".data") = 0;
+u64 sev_status __section(".data") = 0;
 EXPORT_SYMBOL(sme_me_mask);
 DEFINE_STATIC_KEY_FALSE(sev_enable_key);
 EXPORT_SYMBOL_GPL(sev_enable_key);
 
-bool sev_enabled __section(.data);
+bool sev_enabled __section(".data");
 
 /* Buffer used for early in-place encryption by BSP, no locking needed */
 static char sme_early_buffer[PAGE_SIZE] __initdata __aligned(PAGE_SIZE);
diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c
index 68d75379e06a..733b983f3a89 100644
--- a/arch/x86/mm/mem_encrypt_identity.c
+++ b/arch/x86/mm/mem_encrypt_identity.c
@@ -81,7 +81,7 @@ struct sme_populate_pgd_data {
  * section is 2MB aligned to allow for simple pagetable setup using only
  * PMD entries (see vmlinux.lds.S).
  */
-static char sme_workarea[2 * PMD_PAGE_SIZE] __section(.init.scratch);
+static char sme_workarea[2 * PMD_PAGE_SIZE] __section(".init.scratch");
 
 static char sme_cmdline_arg[] __initdata = "mem_encrypt";
 static char sme_cmdline_on[]  __initdata = "on";
diff --git a/arch/x86/platform/pvh/enlighten.c b/arch/x86/platform/pvh/enlighten.c
index c0a502f7e3a7..9ac7457f52a3 100644
--- a/arch/x86/platform/pvh/enlighten.c
+++ b/arch/x86/platform/pvh/enlighten.c
@@ -19,8 +19,8 @@
  * pvh_bootparams and pvh_start_info need to live in the data segment since
  * they are used after startup_{32|64}, which clear .bss, are invoked.
  */
-struct boot_params pvh_bootparams __attribute__((section(".data")));
-struct hvm_start_info pvh_start_info __attribute__((section(".data")));
+struct boot_params pvh_bootparams __section(".data");
+struct hvm_start_info pvh_start_info __section(".data");
 
 unsigned int pvh_start_info_sz = sizeof(pvh_start_info);
 
diff --git a/arch/x86/purgatory/purgatory.c b/arch/x86/purgatory/purgatory.c
index 2961234d0795..7b37a412f829 100644
--- a/arch/x86/purgatory/purgatory.c
+++ b/arch/x86/purgatory/purgatory.c
@@ -14,9 +14,9 @@
 
 #include "../boot/string.h"
 
-u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE] __section(.kexec-purgatory);
+u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE] __section(".kexec-purgatory");
 
-struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX] __section(.kexec-purgatory);
+struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX] __section(".kexec-purgatory");
 
 static int verify_sha256_digest(void)
 {
diff --git a/arch/x86/um/stub_segv.c b/arch/x86/um/stub_segv.c
index 27361cbb7ca9..fdcd58af707a 100644
--- a/arch/x86/um/stub_segv.c
+++ b/arch/x86/um/stub_segv.c
@@ -8,7 +8,7 @@
 #include <sysdep/mcontext.h>
 #include <sys/ucontext.h>
 
-void __attribute__ ((__section__ (".__syscall_stub")))
+void __section(".__syscall_stub")
 stub_segv_handler(int sig, siginfo_t *info, void *p)
 {
 	ucontext_t *uc = p;
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 205b1176084f..aa9f50fccc5d 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -71,7 +71,7 @@ EXPORT_SYMBOL_GPL(xen_have_vector_callback);
  * NB: needs to live in .data because it's used by xen_prepare_pvh which runs
  * before clearing the bss.
  */
-uint32_t xen_start_flags __attribute__((section(".data"))) = 0;
+uint32_t xen_start_flags __section(".data") = 0;
 EXPORT_SYMBOL(xen_start_flags);
 
 /*
diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c
index 80a79db72fcf..0d5e34b9e6f9 100644
--- a/arch/x86/xen/enlighten_pvh.c
+++ b/arch/x86/xen/enlighten_pvh.c
@@ -21,7 +21,7 @@
  * The variable xen_pvh needs to live in the data segment since it is used
  * after startup_{32|64} is invoked, which will clear the .bss segment.
  */
-bool xen_pvh __attribute__((section(".data"))) = 0;
+bool xen_pvh __section(".data") = 0;
 
 void __init xen_pvh_init(struct boot_params *boot_params)
 {
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index be2c78f71695..ed184106e4cf 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -93,7 +93,7 @@ typedef struct tagtable {
 } tagtable_t;
 
 #define __tagtable(tag, fn) static tagtable_t __tagtable_##fn 		\
-	__attribute__((used, section(".taglist"))) = { tag, fn }
+	__section(".taglist") __attribute__((used)) = { tag, fn }
 
 /* parse current tag */
 
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 0a9261a099bd..f83dac54ed85 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -4363,7 +4363,7 @@ struct of_clk_provider {
 
 extern struct of_device_id __clk_of_table;
 static const struct of_device_id __clk_of_table_sentinel
-	__used __section(__clk_of_table_end);
+	__used __section("__clk_of_table_end");
 
 static LIST_HEAD(of_clk_providers);
 static DEFINE_MUTEX(of_clk_mutex);
diff --git a/drivers/clocksource/timer-probe.c b/drivers/clocksource/timer-probe.c
index ee9574da53c0..b7860bc0db4b 100644
--- a/drivers/clocksource/timer-probe.c
+++ b/drivers/clocksource/timer-probe.c
@@ -11,7 +11,7 @@
 extern struct of_device_id __timer_of_table[];
 
 static const struct of_device_id __timer_of_table_sentinel
-	__used __section(__timer_of_table_end);
+	__used __section("__timer_of_table_end");
 
 void __init timer_probe(void)
 {
diff --git a/drivers/irqchip/irqchip.c b/drivers/irqchip/irqchip.c
index d2341153e181..3570f0a588c4 100644
--- a/drivers/irqchip/irqchip.c
+++ b/drivers/irqchip/irqchip.c
@@ -22,7 +22,7 @@
  * special section.
  */
 static const struct of_device_id
-irqchip_of_match_end __used __section(__irqchip_of_table_end);
+irqchip_of_match_end __used __section("__irqchip_of_table_end");
 
 extern struct of_device_id __irqchip_of_table[];
 
diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
index 46b9371c8a33..bcd154485972 100644
--- a/drivers/of/of_reserved_mem.c
+++ b/drivers/of/of_reserved_mem.c
@@ -162,7 +162,7 @@ static int __init __reserved_mem_alloc_size(unsigned long node,
 }
 
 static const struct of_device_id __rmem_of_table_sentinel
-	__used __section(__reservedmem_of_table_end);
+	__used __section("__reservedmem_of_table_end");
 
 /**
  * __reserved_mem_init_node() - call region specific reserved memory init code
diff --git a/drivers/thermal/thermal_core.h b/drivers/thermal/thermal_core.h
index 764c2de31771..681209db42a8 100644
--- a/drivers/thermal/thermal_core.h
+++ b/drivers/thermal/thermal_core.h
@@ -34,7 +34,7 @@ extern struct thermal_governor *__governor_thermal_table_end[];
 
 #define THERMAL_TABLE_ENTRY(table, name)			\
 	static typeof(name) *__thermal_table_entry_##name	\
-	__used __section(__##table##_thermal_table) = &name
+	__used __section("__" #table "_thermal_table") = &name
 
 #define THERMAL_GOVERNOR_DECLARE(name)	THERMAL_TABLE_ENTRY(governor, name)
 
diff --git a/fs/xfs/xfs_message.h b/fs/xfs/xfs_message.h
index 4d9bd6bb63ca..3c392b1512ac 100644
--- a/fs/xfs/xfs_message.h
+++ b/fs/xfs/xfs_message.h
@@ -42,7 +42,7 @@ do {									\
 
 #define xfs_printk_once(func, dev, fmt, ...)			\
 ({								\
-	static bool __section(.data.once) __print_once;		\
+	static bool __section(".data.once") __print_once;	\
 	bool __ret_print_once = !__print_once; 			\
 								\
 	if (!__print_once) {					\
diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h
index 18b0f4eee8cb..76a10e0dca9f 100644
--- a/include/asm-generic/bug.h
+++ b/include/asm-generic/bug.h
@@ -141,7 +141,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
 
 #ifndef WARN_ON_ONCE
 #define WARN_ON_ONCE(condition)	({				\
-	static bool __section(.data.once) __warned;		\
+	static bool __section(".data.once") __warned;		\
 	int __ret_warn_once = !!(condition);			\
 								\
 	if (unlikely(__ret_warn_once && !__warned)) {		\
@@ -153,7 +153,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
 #endif
 
 #define WARN_ONCE(condition, format...)	({			\
-	static bool __section(.data.once) __warned;		\
+	static bool __section(".data.once") __warned;		\
 	int __ret_warn_once = !!(condition);			\
 								\
 	if (unlikely(__ret_warn_once && !__warned)) {		\
@@ -164,7 +164,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
 })
 
 #define WARN_TAINT_ONCE(condition, taint, format...)	({	\
-	static bool __section(.data.once) __warned;		\
+	static bool __section(".data.once") __warned;		\
 	int __ret_warn_once = !!(condition);			\
 								\
 	if (unlikely(__ret_warn_once && !__warned)) {		\
diff --git a/include/asm-generic/error-injection.h b/include/asm-generic/error-injection.h
index 80ca61058dd2..7ddd9dc10ce9 100644
--- a/include/asm-generic/error-injection.h
+++ b/include/asm-generic/error-injection.h
@@ -25,7 +25,7 @@ struct pt_regs;
  */
 #define ALLOW_ERROR_INJECTION(fname, _etype)				\
 static struct error_injection_entry __used				\
-	__attribute__((__section__("_error_injection_whitelist")))	\
+	__section("_error_injection_whitelist")				\
 	_eil_addr_##fname = {						\
 		.addr = (unsigned long)fname,				\
 		.etype = EI_ETYPE_##_etype,				\
diff --git a/include/asm-generic/kprobes.h b/include/asm-generic/kprobes.h
index 4a982089c95c..060eab094e5a 100644
--- a/include/asm-generic/kprobes.h
+++ b/include/asm-generic/kprobes.h
@@ -10,11 +10,11 @@
  */
 # define __NOKPROBE_SYMBOL(fname)				\
 static unsigned long __used					\
-	__attribute__((__section__("_kprobe_blacklist")))	\
+	__section("_kprobe_blacklist")				\
 	_kbl_addr_##fname = (unsigned long)fname;
 # define NOKPROBE_SYMBOL(fname)	__NOKPROBE_SYMBOL(fname)
 /* Use this to forbid a kprobes attach on very low level functions */
-# define __kprobes	__attribute__((__section__(".kprobes.text")))
+# define __kprobes	__section(".kprobes.text")
 # define nokprobe_inline	__always_inline
 #else
 # define NOKPROBE_SYMBOL(fname)
diff --git a/include/kunit/test.h b/include/kunit/test.h
index a423fffefea0..9197da792336 100644
--- a/include/kunit/test.h
+++ b/include/kunit/test.h
@@ -288,7 +288,7 @@ static inline int kunit_run_all_tests(void)
 	static struct kunit_suite *unique_array[] = { __VA_ARGS__, NULL };     \
 	kunit_test_suites_for_module(unique_array);			       \
 	static struct kunit_suite **unique_suites			       \
-	__used __section(.kunit_test_suites) = unique_array
+	__used __section(".kunit_test_suites") = unique_array
 
 /**
  * kunit_test_suites() - used to register one or more &struct kunit_suite
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 143c6ffce2db..39263c6b52e1 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -1153,7 +1153,7 @@ struct acpi_probe_entry {
 #define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable,	\
 				 valid, data, fn)			\
 	static const struct acpi_probe_entry __acpi_probe_##name	\
-		__used __section(__##table##_acpi_probe_table) = {	\
+		__used __section("__" #table "_acpi_probe_table") = {	\
 			.id = table_id,					\
 			.type = subtable,				\
 			.subtable_valid = valid,			\
@@ -1164,7 +1164,7 @@ struct acpi_probe_entry {
 #define ACPI_DECLARE_SUBTABLE_PROBE_ENTRY(table, name, table_id,	\
 					  subtable, valid, data, fn)	\
 	static const struct acpi_probe_entry __acpi_probe_##name	\
-		__used __section(__##table##_acpi_probe_table) = {	\
+		__used __section("__" #table "_acpi_probe_table") = {	\
 			.id = table_id,					\
 			.type = subtable,				\
 			.subtable_valid = valid,			\
diff --git a/include/linux/cache.h b/include/linux/cache.h
index 1aa8009f6d06..d742c57eaee5 100644
--- a/include/linux/cache.h
+++ b/include/linux/cache.h
@@ -34,7 +34,7 @@
  * but may get written to during init, so can't live in .rodata (via "const").
  */
 #ifndef __ro_after_init
-#define __ro_after_init __attribute__((__section__(".data..ro_after_init")))
+#define __ro_after_init __section(".data..ro_after_init")
 #endif
 
 #ifndef ____cacheline_aligned
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index ac45f6d40d39..e512f5505dad 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -24,7 +24,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 			long ______r;					\
 			static struct ftrace_likely_data		\
 				__aligned(4)				\
-				__section(_ftrace_annotated_branch)	\
+				__section("_ftrace_annotated_branch")	\
 				______f = {				\
 				.data.func = __func__,			\
 				.data.file = __FILE__,			\
@@ -60,7 +60,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 #define __trace_if_value(cond) ({			\
 	static struct ftrace_branch_data		\
 		__aligned(4)				\
-		__section(_ftrace_branch)		\
+		__section("_ftrace_branch")		\
 		__if_trace = {				\
 			.func = __func__,		\
 			.file = __FILE__,		\
@@ -118,7 +118,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 	".popsection\n\t"
 
 /* Annotate a C jump table to allow objtool to follow the code flow */
-#define __annotate_jump_table __section(.rodata..c_jump_table)
+#define __annotate_jump_table __section(".rodata..c_jump_table")
 
 #else
 #define annotate_reachable()
@@ -206,7 +206,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
  * visible to the compiler.
  */
 #define __ADDRESSABLE(sym) \
-	static void * __section(.discard.addressable) __used \
+	static void * __section(".discard.addressable") __used \
 		__UNIQUE_ID(__PASTE(__addressable_,sym)) = (void *)&sym;
 
 /**
diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h
index ea7b756b1c8f..b2a3f4f641a7 100644
--- a/include/linux/compiler_attributes.h
+++ b/include/linux/compiler_attributes.h
@@ -254,7 +254,7 @@
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-section-variable-attribute
  * clang: https://clang.llvm.org/docs/AttributeReference.html#section-declspec-allocate
  */
-#define __section(S)                    __attribute__((__section__(#S)))
+#define __section(section)              __attribute__((__section__(section)))
 
 /*
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-unused-function-attribute
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 8aa84c052fdf..d6428aaf67e7 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -173,7 +173,7 @@ void cpu_startup_entry(enum cpuhp_state state);
 void cpu_idle_poll_ctrl(bool enable);
 
 /* Attach to any functions which should be considered cpuidle. */
-#define __cpuidle	__attribute__((__section__(".cpuidle.text")))
+#define __cpuidle	__section(".cpuidle.text")
 
 bool cpu_in_idle(unsigned long pc);
 
diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h
index 8aa0c7c2608c..a57ee75342cf 100644
--- a/include/linux/dynamic_debug.h
+++ b/include/linux/dynamic_debug.h
@@ -84,7 +84,7 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor,
 
 #define DEFINE_DYNAMIC_DEBUG_METADATA(name, fmt)		\
 	static struct _ddebug  __aligned(8)			\
-	__section(__dyndbg) name = {				\
+	__section("__dyndbg") name = {				\
 		.modname = KBUILD_MODNAME,			\
 		.function = __func__,				\
 		.filename = __FILE__,				\
diff --git a/include/linux/export.h b/include/linux/export.h
index 8933ff6ad23a..fceb5e855717 100644
--- a/include/linux/export.h
+++ b/include/linux/export.h
@@ -130,7 +130,7 @@ struct kernel_symbol {
  * discarded in the final link stage.
  */
 #define __ksym_marker(sym)	\
-	static int __ksym_marker_##sym[0] __section(.discard.ksym) __used
+	static int __ksym_marker_##sym[0] __section(".discard.ksym") __used
 
 #define __EXPORT_SYMBOL(sym, sec, ns)					\
 	__ksym_marker(sym);						\
diff --git a/include/linux/firmware.h b/include/linux/firmware.h
index c15acadc6cf4..84e346ae766e 100644
--- a/include/linux/firmware.h
+++ b/include/linux/firmware.h
@@ -36,7 +36,7 @@ struct builtin_fw {
 
 #define DECLARE_BUILTIN_FIRMWARE_SIZE(name, blob, size)			     \
 	static const struct builtin_fw __fw_concat(__builtin_fw,__COUNTER__) \
-	__used __section(.builtin_fw) = { name, blob, size }
+	__used __section(".builtin_fw") = { name, blob, size }
 
 #if defined(CONFIG_FW_LOADER) || (defined(CONFIG_FW_LOADER_MODULE) && defined(MODULE))
 int request_firmware(const struct firmware **fw, const char *name,
diff --git a/include/linux/init.h b/include/linux/init.h
index 212fc9e2f691..7b53cb3092ee 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -47,11 +47,11 @@
 
 /* These are for everybody (although not all archs will actually
    discard it in modules) */
-#define __init		__section(.init.text) __cold  __latent_entropy __noinitretpoline
-#define __initdata	__section(.init.data)
-#define __initconst	__section(.init.rodata)
-#define __exitdata	__section(.exit.data)
-#define __exit_call	__used __section(.exitcall.exit)
+#define __init		__section(".init.text") __cold  __latent_entropy __noinitretpoline
+#define __initdata	__section(".init.data")
+#define __initconst	__section(".init.rodata")
+#define __exitdata	__section(".exit.data")
+#define __exit_call	__used __section(".exitcall.exit")
 
 /*
  * modpost check for section mismatches during the kernel build.
@@ -70,9 +70,9 @@
  *
  * The markers follow same syntax rules as __init / __initdata.
  */
-#define __ref            __section(.ref.text) noinline
-#define __refdata        __section(.ref.data)
-#define __refconst       __section(.ref.rodata)
+#define __ref            __section(".ref.text") noinline
+#define __refdata        __section(".ref.data")
+#define __refconst       __section(".ref.rodata")
 
 #ifdef MODULE
 #define __exitused
@@ -80,16 +80,16 @@
 #define __exitused  __used
 #endif
 
-#define __exit          __section(.exit.text) __exitused __cold notrace
+#define __exit          __section(".exit.text") __exitused __cold notrace
 
 /* Used for MEMORY_HOTPLUG */
-#define __meminit        __section(.meminit.text) __cold notrace \
+#define __meminit        __section(".meminit.text") __cold notrace \
 						  __latent_entropy
-#define __meminitdata    __section(.meminit.data)
-#define __meminitconst   __section(.meminit.rodata)
-#define __memexit        __section(.memexit.text) __exitused __cold notrace
-#define __memexitdata    __section(.memexit.data)
-#define __memexitconst   __section(.memexit.rodata)
+#define __meminitdata    __section(".meminit.data")
+#define __meminitconst   __section(".meminit.rodata")
+#define __memexit        __section(".memexit.text") __exitused __cold notrace
+#define __memexitdata    __section(".memexit.data")
+#define __memexitconst   __section(".memexit.rodata")
 
 /* For assembly routines */
 #define __HEAD		.section	".head.text","ax"
@@ -254,7 +254,7 @@ struct obs_kernel_param {
 	static const char __setup_str_##unique_id[] __initconst		\
 		__aligned(1) = str; 					\
 	static struct obs_kernel_param __setup_##unique_id		\
-		__used __section(.init.setup)				\
+		__used __section(".init.setup")				\
 		__attribute__((aligned((sizeof(long)))))		\
 		= { __setup_str_##unique_id, fn, early }
 
@@ -298,7 +298,7 @@ void __init parse_early_options(char *cmdline);
 #endif
 
 /* Data marked not to be saved by software suspend */
-#define __nosavedata __section(.data..nosave)
+#define __nosavedata __section(".data..nosave")
 
 #ifdef MODULE
 #define __exit_p(x) x
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 2c620d7ac432..b2412b4d4c20 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -40,12 +40,12 @@ extern struct cred init_cred;
 
 /* Attach to the init_task data structure for proper alignment */
 #ifdef CONFIG_ARCH_TASK_STRUCT_ON_STACK
-#define __init_task_data __attribute__((__section__(".data..init_task")))
+#define __init_task_data __section(".data..init_task")
 #else
 #define __init_task_data /**/
 #endif
 
 /* Attach to the thread_info data structure for proper alignment */
-#define __init_thread_info __attribute__((__section__(".data..init_thread_info")))
+#define __init_thread_info __section(".data..init_thread_info")
 
 #endif
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index f9aee3538461..ee8299eb1f52 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -792,9 +792,9 @@ extern int arch_early_irq_init(void);
  * We want to know which function is an entrypoint of a hardirq or a softirq.
  */
 #ifndef __irq_entry
-# define __irq_entry	 __attribute__((__section__(".irqentry.text")))
+# define __irq_entry	 __section(".irqentry.text")
 #endif
 
-#define __softirq_entry  __attribute__((__section__(".softirqentry.text")))
+#define __softirq_entry  __section(".softirqentry.text")
 
 #endif
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index c629215fdad9..2f05e9128201 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -729,7 +729,7 @@ do {							\
 #define do_trace_printk(fmt, args...)					\
 do {									\
 	static const char *trace_printk_fmt __used			\
-		__attribute__((section("__trace_printk_fmt"))) =	\
+		__section("__trace_printk_fmt") =			\
 		__builtin_constant_p(fmt) ? fmt : NULL;			\
 									\
 	__trace_printk_check_format(fmt, ##args);			\
@@ -773,7 +773,7 @@ int __trace_printk(unsigned long ip, const char *fmt, ...);
 
 #define trace_puts(str) ({						\
 	static const char *trace_printk_fmt __used			\
-		__attribute__((section("__trace_printk_fmt"))) =	\
+		__section("__trace_printk_fmt") =			\
 		__builtin_constant_p(str) ? str : NULL;			\
 									\
 	if (__builtin_constant_p(str))					\
@@ -795,7 +795,7 @@ extern void trace_dump_stack(int skip);
 do {									\
 	if (__builtin_constant_p(fmt)) {				\
 		static const char *trace_printk_fmt __used		\
-		  __attribute__((section("__trace_printk_fmt"))) =	\
+		  __section("__trace_printk_fmt") =			\
 			__builtin_constant_p(fmt) ? fmt : NULL;		\
 									\
 		__ftrace_vbprintk(_THIS_IP_, trace_printk_fmt, vargs);	\
diff --git a/include/linux/linkage.h b/include/linux/linkage.h
index d796ec20d114..5bcfbd972e97 100644
--- a/include/linux/linkage.h
+++ b/include/linux/linkage.h
@@ -36,8 +36,8 @@
 		  __stringify(name))
 #endif
 
-#define __page_aligned_data	__section(.data..page_aligned) __aligned(PAGE_SIZE)
-#define __page_aligned_bss	__section(.bss..page_aligned) __aligned(PAGE_SIZE)
+#define __page_aligned_data	__section(".data..page_aligned") __aligned(PAGE_SIZE)
+#define __page_aligned_bss	__section(".bss..page_aligned") __aligned(PAGE_SIZE)
 
 /*
  * For assembly routines.
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index 8814e3d5952d..c503f7ab8afb 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -1611,12 +1611,12 @@ extern struct lsm_info __start_early_lsm_info[], __end_early_lsm_info[];
 
 #define DEFINE_LSM(lsm)							\
 	static struct lsm_info __lsm_##lsm				\
-		__used __section(.lsm_info.init)			\
+		__used __section(".lsm_info.init")			\
 		__aligned(sizeof(unsigned long))
 
 #define DEFINE_EARLY_LSM(lsm)						\
 	static struct lsm_info __early_lsm_##lsm			\
-		__used __section(.early_lsm_info.init)			\
+		__used __section(".early_lsm_info.init")		\
 		__aligned(sizeof(unsigned long))
 
 #ifdef CONFIG_SECURITY_SELINUX_DISABLE
diff --git a/include/linux/module.h b/include/linux/module.h
index a29187f7c360..7ccdf87f376f 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -278,7 +278,7 @@ extern typeof(name) __mod_##type##__##name##_device_table		\
 		.version	= _version,				\
 	};								\
 	static const struct module_version_attribute			\
-	__used __attribute__ ((__section__ ("__modver")))		\
+	__used __section("__modver")					\
 	* __moduleparam_const __modver_attr = &___modver_attr
 #endif
 
diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index 47879fc7f75e..6388eb9734a5 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -22,7 +22,7 @@
 
 #define __MODULE_INFO(tag, name, info)					  \
 static const char __UNIQUE_ID(name)[]					  \
-  __used __attribute__((section(".modinfo"), unused, aligned(1)))	  \
+  __used __section(".modinfo") __attribute__((unused, aligned(1)))	  \
   = __MODULE_INFO_PREFIX __stringify(tag) "=" info
 
 #define __MODULE_PARM_TYPE(name, _type)					  \
@@ -289,7 +289,7 @@ struct kparam_array
 	static const char __param_str_##name[] = prefix #name;		\
 	static struct kernel_param __moduleparam_const __param_##name	\
 	__used								\
-    __attribute__ ((unused,__section__ ("__param"),aligned(sizeof(void *)))) \
+    __section("__param") __attribute__ ((unused, aligned(sizeof(void *)))) \
 	= { __param_str_##name, THIS_MODULE, ops,			\
 	    VERIFY_OCTAL_PERMISSIONS(perm), level, flags, { arg } }
 
diff --git a/include/linux/mtd/xip.h b/include/linux/mtd/xip.h
index a4e352b1dfe6..3cac9360588f 100644
--- a/include/linux/mtd/xip.h
+++ b/include/linux/mtd/xip.h
@@ -28,7 +28,7 @@
  * those functions so they get relocated to ram.
  */
 #ifdef CONFIG_XIP_KERNEL
-#define __xipram noinline __attribute__ ((__section__ (".xiptext")))
+#define __xipram noinline __section(".xiptext")
 #endif
 
 /*
diff --git a/include/linux/objtool.h b/include/linux/objtool.h
index ab82c793c897..577f51436cf9 100644
--- a/include/linux/objtool.h
+++ b/include/linux/objtool.h
@@ -60,7 +60,7 @@ struct unwind_hint {
  * For more information, see tools/objtool/Documentation/stack-validation.txt.
  */
 #define STACK_FRAME_NON_STANDARD(func) \
-	static void __used __section(.discard.func_stack_frame_non_standard) \
+	static void __used __section(".discard.func_stack_frame_non_standard") \
 		*__func_stack_frame_non_standard_##func = func
 
 #else /* __ASSEMBLY__ */
diff --git a/include/linux/of.h b/include/linux/of.h
index 481ec0467285..5d51891cbf1a 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -1299,7 +1299,7 @@ static inline int of_get_available_child_count(const struct device_node *np)
 #if defined(CONFIG_OF) && !defined(MODULE)
 #define _OF_DECLARE(table, name, compat, fn, fn_type)			\
 	static const struct of_device_id __of_table_##name		\
-		__used __section(__##table##_of_table)			\
+		__used __section("__" #table "_of_table")		\
 		 = { .compatible = compat,				\
 		     .data = (fn == (fn_type)NULL) ? fn : fn  }
 #else
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index 176bfbd52d97..dff7040f629a 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -51,7 +51,7 @@
 	PER_CPU_ATTRIBUTES
 
 #define __PCPU_DUMMY_ATTRS						\
-	__attribute__((section(".discard"), unused))
+	__section(".discard") __attribute__((unused))
 
 /*
  * s390 and alpha modules require percpu variables to be defined as
diff --git a/include/linux/printk.h b/include/linux/printk.h
index 78479633ccfc..fe7eb2351610 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -437,7 +437,7 @@ extern int kptr_restrict;
 #ifdef CONFIG_PRINTK
 #define printk_once(fmt, ...)					\
 ({								\
-	static bool __section(.data.once) __print_once;		\
+	static bool __section(".data.once") __print_once;	\
 	bool __ret_print_once = !__print_once;			\
 								\
 	if (!__print_once) {					\
@@ -448,7 +448,7 @@ extern int kptr_restrict;
 })
 #define printk_deferred_once(fmt, ...)				\
 ({								\
-	static bool __section(.data.once) __print_once;		\
+	static bool __section(".data.once") __print_once;	\
 	bool __ret_print_once = !__print_once;			\
 								\
 	if (!__print_once) {					\
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 7c1ceff02852..6cdd0152c253 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -299,7 +299,7 @@ static inline int rcu_read_lock_any_held(void)
  */
 #define RCU_LOCKDEP_WARN(c, s)						\
 	do {								\
-		static bool __section(.data.unlikely) __warned;		\
+		static bool __section(".data.unlikely") __warned;	\
 		if (debug_lockdep_rcu_enabled() && !__warned && (c)) {	\
 			__warned = true;				\
 			lockdep_rcu_suspicious(__FILE__, __LINE__, s);	\
diff --git a/include/linux/sched/debug.h b/include/linux/sched/debug.h
index 00c45a0e6abe..ae51f4529fc9 100644
--- a/include/linux/sched/debug.h
+++ b/include/linux/sched/debug.h
@@ -43,7 +43,7 @@ extern void proc_sched_set_task(struct task_struct *p);
 #endif
 
 /* Attach to any functions which should be ignored in wchan output. */
-#define __sched		__attribute__((__section__(".sched.text")))
+#define __sched		__section(".sched.text")
 
 /* Linker adds these: start and end of __sched functions */
 extern char __sched_text_start[], __sched_text_end[];
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 8a99279a579b..ff63c2963359 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -373,7 +373,7 @@ extern const struct earlycon_id *__earlycon_table_end[];
 		    .compatible = compat,				\
 		    .setup = fn  };					\
 	static const struct earlycon_id EARLYCON_USED_OR_UNUSED		\
-		__section(__earlycon_table)				\
+		__section("__earlycon_table")				\
 		* const __PASTE(__p, unique_id) = &unique_id
 
 #define OF_EARLYCON_DECLARE(_name, compat, fn)				\
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index f2f12d746dbd..79897841a2cc 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -76,7 +76,7 @@
 #define LOCK_SECTION_END                        \
         ".previous\n\t"
 
-#define __lockfunc __attribute__((section(".spinlock.text")))
+#define __lockfunc __section(".spinlock.text")
 
 /*
  * Pull the arch_spinlock_t and arch_rwlock_t definitions:
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 2eda7678fe1d..37bea07c12f2 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -144,7 +144,7 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 		.flags                  = TRACE_EVENT_FL_CAP_ANY,	\
 	};								\
 	static struct trace_event_call __used				\
-	  __attribute__((section("_ftrace_events")))			\
+	  __section("_ftrace_events")					\
 	 *__event_enter_##sname = &event_enter_##sname;
 
 #define SYSCALL_TRACE_EXIT_EVENT(sname)					\
@@ -160,7 +160,7 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 		.flags                  = TRACE_EVENT_FL_CAP_ANY,	\
 	};								\
 	static struct trace_event_call __used				\
-	  __attribute__((section("_ftrace_events")))			\
+	  __section("_ftrace_events")					\
 	*__event_exit_##sname = &event_exit_##sname;
 
 #define SYSCALL_METADATA(sname, nb, ...)			\
@@ -184,7 +184,7 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 		.enter_fields	= LIST_HEAD_INIT(__syscall_meta_##sname.enter_fields), \
 	};							\
 	static struct syscall_metadata __used			\
-	  __attribute__((section("__syscalls_metadata")))	\
+	  __section("__syscalls_metadata")			\
 	 *__p_syscall_meta_##sname = &__syscall_meta_##sname;
 
 static inline int is_syscall_trace_event(struct trace_event_call *tp_event)
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 5c6943354049..d321fe5ad1a1 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -709,7 +709,7 @@ do {									\
 	tracing_record_cmdline(current);				\
 	if (__builtin_constant_p(fmt)) {				\
 		static const char *trace_printk_fmt			\
-		  __attribute__((section("__trace_printk_fmt"))) =	\
+		  __section("__trace_printk_fmt") =			\
 			__builtin_constant_p(fmt) ? fmt : NULL;		\
 									\
 		__trace_bprintk(ip, trace_printk_fmt, ##args);		\
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 81fa0b2f271e..0f21617f1a66 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -119,7 +119,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 
 #define __TRACEPOINT_ENTRY(name)					 \
 	static tracepoint_ptr_t __tracepoint_ptr_##name __used		 \
-	__section(__tracepoints_ptrs) = &__tracepoint_##name
+	__section("__tracepoints_ptrs") = &__tracepoint_##name
 #endif
 
 #endif /* _LINUX_TRACEPOINT_H */
@@ -286,11 +286,11 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
  */
 #define DEFINE_TRACE_FN(_name, _reg, _unreg, proto, args)		\
 	static const char __tpstrtab_##_name[]				\
-	__section(__tracepoints_strings) = #_name;			\
+	__section("__tracepoints_strings") = #_name;			\
 	extern struct static_call_key STATIC_CALL_KEY(tp_func_##_name);	\
 	int __traceiter_##_name(void *__data, proto);			\
 	struct tracepoint __tracepoint_##_name	__used			\
-	__section(__tracepoints) = {					\
+	__section("__tracepoints") = {					\
 		.name = __tpstrtab_##_name,				\
 		.key = STATIC_KEY_INIT_FALSE,				\
 		.static_call_key = &STATIC_CALL_KEY(tp_func_##_name),	\
@@ -396,7 +396,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 		static const char *___tp_str __tracepoint_string = str; \
 		___tp_str;						\
 	})
-#define __tracepoint_string	__used __section(__tracepoint_str)
+#define __tracepoint_string	__used __section("__tracepoint_str")
 #else
 /*
  * tracepoint_string() is used to save the string address for userspace
diff --git a/include/trace/bpf_probe.h b/include/trace/bpf_probe.h
index 1ce3be63add1..cd74bffed5c6 100644
--- a/include/trace/bpf_probe.h
+++ b/include/trace/bpf_probe.h
@@ -79,7 +79,7 @@ static union {								\
 	struct bpf_raw_event_map event;					\
 	btf_trace_##call handler;					\
 } __bpf_trace_tp_map_##call __used					\
-__attribute__((section("__bpf_raw_tp_map"))) = {			\
+__section("__bpf_raw_tp_map") = {					\
 	.event = {							\
 		.tp		= &__tracepoint_##call,			\
 		.bpf_func	= __bpf_trace_##template,		\
diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h
index 1bc3e7bba9a4..7785961d82ba 100644
--- a/include/trace/trace_events.h
+++ b/include/trace/trace_events.h
@@ -45,7 +45,7 @@ TRACE_MAKE_SYSTEM_STR();
 		.eval_value = a				\
 	};						\
 	static struct trace_eval_map __used		\
-	__attribute__((section("_ftrace_eval_map")))	\
+	__section("_ftrace_eval_map")			\
 	*TRACE_SYSTEM##_##a = &__##TRACE_SYSTEM##_##a
 
 #undef TRACE_DEFINE_SIZEOF
@@ -58,7 +58,7 @@ TRACE_MAKE_SYSTEM_STR();
 		.eval_value = sizeof(a)			\
 	};						\
 	static struct trace_eval_map __used		\
-	__attribute__((section("_ftrace_eval_map")))	\
+	__section("_ftrace_eval_map")			\
 	*TRACE_SYSTEM##_##a = &__##TRACE_SYSTEM##_##a
 
 /*
@@ -607,7 +607,7 @@ static inline notrace int trace_event_get_offsets_##call(		\
  * // its only safe to use pointers when doing linker tricks to
  * // create an array.
  * static struct trace_event_call __used
- * __attribute__((section("_ftrace_events"))) *__event_<call> = &event_<call>;
+ * __section("_ftrace_events") *__event_<call> = &event_<call>;
  *
  */
 
@@ -755,7 +755,7 @@ static struct trace_event_call __used event_##call = {			\
 	.flags			= TRACE_EVENT_FL_TRACEPOINT,		\
 };									\
 static struct trace_event_call __used					\
-__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call
+__section("_ftrace_events") *__event_##call = &event_##call
 
 #undef DEFINE_EVENT_PRINT
 #define DEFINE_EVENT_PRINT(template, call, proto, args, print)		\
@@ -772,6 +772,6 @@ static struct trace_event_call __used event_##call = {			\
 	.flags			= TRACE_EVENT_FL_TRACEPOINT,		\
 };									\
 static struct trace_event_call __used					\
-__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call
+__section("_ftrace_events") *__event_##call = &event_##call
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 4fb15fa96734..fe9de067771c 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -40,10 +40,10 @@ extern const u8 kallsyms_names[] __weak;
  * has one (eg: FRV).
  */
 extern const unsigned int kallsyms_num_syms
-__attribute__((weak, section(".rodata")));
+__section(".rodata") __attribute__((weak));
 
 extern const unsigned long kallsyms_relative_base
-__attribute__((weak, section(".rodata")));
+__section(".rodata") __attribute__((weak));
 
 extern const char kallsyms_token_table[] __weak;
 extern const u16 kallsyms_token_index[] __weak;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 6d93f4518734..f232305dcefe 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2504,7 +2504,7 @@ static void prio_changed_dl(struct rq *rq, struct task_struct *p,
 }
 
 const struct sched_class dl_sched_class
-	__attribute__((section("__dl_sched_class"))) = {
+	__section("__dl_sched_class") = {
 	.enqueue_task		= enqueue_task_dl,
 	.dequeue_task		= dequeue_task_dl,
 	.yield_task		= yield_task_dl,
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e17012be4d14..290f9e38378c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -11159,7 +11159,7 @@ static unsigned int get_rr_interval_fair(struct rq *rq, struct task_struct *task
  * All the scheduling class methods:
  */
 const struct sched_class fair_sched_class
-	__attribute__((section("__fair_sched_class"))) = {
+	__section("__fair_sched_class") = {
 	.enqueue_task		= enqueue_task_fair,
 	.dequeue_task		= dequeue_task_fair,
 	.yield_task		= yield_task_fair,
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index f324dc36fc43..24d0ee26377d 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -458,7 +458,7 @@ static void update_curr_idle(struct rq *rq)
  * Simple, special scheduling class for the per-CPU idle tasks:
  */
 const struct sched_class idle_sched_class
-	__attribute__((section("__idle_sched_class"))) = {
+	__section("__idle_sched_class") = {
 	/* no enqueue/yield_task for idle tasks */
 
 	/* dequeue is not valid, we print a debug message there: */
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index f215eea6a966..49ec096a8aa1 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2430,7 +2430,7 @@ static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task)
 }
 
 const struct sched_class rt_sched_class
-	__attribute__((section("__rt_sched_class"))) = {
+	__section("__rt_sched_class") = {
 	.enqueue_task		= enqueue_task_rt,
 	.dequeue_task		= dequeue_task_rt,
 	.yield_task		= yield_task_rt,
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 394bc8126a1e..ceb5b6b12561 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -110,7 +110,7 @@ static void update_curr_stop(struct rq *rq)
  * Simple, special scheduling class for the per-CPU stop tasks:
  */
 const struct sched_class stop_sched_class
-	__attribute__((section("__stop_sched_class"))) = {
+	__section("__stop_sched_class") = {
 
 	.enqueue_task		= enqueue_task_stop,
 	.dequeue_task		= dequeue_task_stop,
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 34e0c4d5a6e7..f3f5e77123ad 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -99,7 +99,7 @@ enum trace_type {
 
 /* Use this for memory failure errors */
 #define MEM_FAIL(condition, fmt, ...) ({			\
-	static bool __section(.data.once) __warned;		\
+	static bool __section(".data.once") __warned;		\
 	int __ret_warn_once = !!(condition);			\
 								\
 	if (unlikely(__ret_warn_once && !__warned)) {		\
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 70d3d0a09053..90f81d33fa3f 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -176,7 +176,7 @@ struct trace_event_call __used event_##call = {				\
 	.flags			= TRACE_EVENT_FL_IGNORE_ENABLE,		\
 };									\
 static struct trace_event_call __used						\
-__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call;
+__section("_ftrace_events") *__event_##call = &event_##call;
 
 #undef FTRACE_ENTRY
 #define FTRACE_ENTRY(call, struct_name, etype, tstruct, print)		\
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 69341b36f271..f882ce0d9327 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -2254,7 +2254,7 @@ static void add_header(struct buffer *b, struct module *mod)
 	buf_printf(b, "MODULE_INFO(name, KBUILD_MODNAME);\n");
 	buf_printf(b, "\n");
 	buf_printf(b, "__visible struct module __this_module\n");
-	buf_printf(b, "__section(.gnu.linkonce.this_module) = {\n");
+	buf_printf(b, "__section(\".gnu.linkonce.this_module\") = {\n");
 	buf_printf(b, "\t.name = KBUILD_MODNAME,\n");
 	if (mod->has_init)
 		buf_printf(b, "\t.init = init_module,\n");
@@ -2308,7 +2308,7 @@ static int add_versions(struct buffer *b, struct module *mod)
 
 	buf_printf(b, "\n");
 	buf_printf(b, "static const struct modversion_info ____versions[]\n");
-	buf_printf(b, "__used __section(__versions) = {\n");
+	buf_printf(b, "__used __section(\"__versions\") = {\n");
 
 	for (s = mod->unres; s; s = s->next) {
 		if (!s->module)
diff --git a/tools/include/linux/objtool.h b/tools/include/linux/objtool.h
index ab82c793c897..577f51436cf9 100644
--- a/tools/include/linux/objtool.h
+++ b/tools/include/linux/objtool.h
@@ -60,7 +60,7 @@ struct unwind_hint {
  * For more information, see tools/objtool/Documentation/stack-validation.txt.
  */
 #define STACK_FRAME_NON_STANDARD(func) \
-	static void __used __section(.discard.func_stack_frame_non_standard) \
+	static void __used __section(".discard.func_stack_frame_non_standard") \
 		*__func_stack_frame_non_standard_##func = func
 
 #else /* __ASSEMBLY__ */
-- 
cgit v1.2.3


From 44cdc1d952e3f7aa9944c1bbf38fc23f49885017 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 27 Sep 2020 11:18:30 -0400
Subject: convert ->f_ep_links/->fllink to hlist

we don't care about the order of elements there

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/eventpoll.c            | 18 +++++++++---------
 include/linux/eventpoll.h |  4 ++--
 include/linux/fs.h        |  2 +-
 3 files changed, 12 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 680f4ada53d4..c40576e62728 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -160,7 +160,7 @@ struct epitem {
 	struct eventpoll *ep;
 
 	/* List header used to link this item to the "struct file" items list */
-	struct list_head fllink;
+	struct hlist_node fllink;
 
 	/* wakeup_source used when EPOLLWAKEUP is set */
 	struct wakeup_source __rcu *ws;
@@ -642,7 +642,7 @@ static int ep_remove(struct eventpoll *ep, struct epitem *epi)
 
 	/* Remove the current item from the list of epoll hooks */
 	spin_lock(&file->f_lock);
-	list_del_rcu(&epi->fllink);
+	hlist_del_rcu(&epi->fllink);
 	spin_unlock(&file->f_lock);
 
 	rb_erase_cached(&epi->rbn, &ep->rbr);
@@ -835,7 +835,8 @@ static const struct file_operations eventpoll_fops = {
 void eventpoll_release_file(struct file *file)
 {
 	struct eventpoll *ep;
-	struct epitem *epi, *next;
+	struct epitem *epi;
+	struct hlist_node *next;
 
 	/*
 	 * We don't want to get "file->f_lock" because it is not
@@ -851,7 +852,7 @@ void eventpoll_release_file(struct file *file)
 	 * Besides, ep_remove() acquires the lock, so we can't hold it here.
 	 */
 	mutex_lock(&epmutex);
-	list_for_each_entry_safe(epi, next, &file->f_ep_links, fllink) {
+	hlist_for_each_entry_safe(epi, next, &file->f_ep_links, fllink) {
 		ep = epi->ep;
 		mutex_lock_nested(&ep->mtx, 0);
 		ep_remove(ep, epi);
@@ -1257,11 +1258,11 @@ static int reverse_path_check_proc(struct file *file, int depth)
 
 	/* CTL_DEL can remove links here, but that can't increase our count */
 	rcu_read_lock();
-	list_for_each_entry_rcu(epi, &file->f_ep_links, fllink) {
+	hlist_for_each_entry_rcu(epi, &file->f_ep_links, fllink) {
 		struct file *recepient = epi->ep->file;
 		if (WARN_ON(!is_file_epoll(recepient)))
 			continue;
-		if (list_empty(&recepient->f_ep_links))
+		if (hlist_empty(&recepient->f_ep_links))
 			error = path_count_inc(depth);
 		else
 			error = reverse_path_check_proc(recepient, depth + 1);
@@ -1361,7 +1362,6 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,
 
 	/* Item initialization follow here ... */
 	INIT_LIST_HEAD(&epi->rdllink);
-	INIT_LIST_HEAD(&epi->fllink);
 	epi->ep = ep;
 	ep_set_ffd(&epi->ffd, tfile, fd);
 	epi->event = *event;
@@ -1373,7 +1373,7 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,
 		mutex_lock_nested(&tep->mtx, 1);
 	/* Add the current item to the list of active epoll hook for this file */
 	spin_lock(&tfile->f_lock);
-	list_add_tail_rcu(&epi->fllink, &tfile->f_ep_links);
+	hlist_add_head_rcu(&epi->fllink, &tfile->f_ep_links);
 	spin_unlock(&tfile->f_lock);
 
 	/*
@@ -1999,7 +1999,7 @@ int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds,
 	if (error)
 		goto error_tgt_fput;
 	if (op == EPOLL_CTL_ADD) {
-		if (!list_empty(&f.file->f_ep_links) ||
+		if (!hlist_empty(&f.file->f_ep_links) ||
 				ep->gen == loop_check_gen ||
 						is_file_epoll(tf.file)) {
 			mutex_unlock(&ep->mtx);
diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h
index 8f000fada5a4..4e215ccfa792 100644
--- a/include/linux/eventpoll.h
+++ b/include/linux/eventpoll.h
@@ -25,7 +25,7 @@ struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long t
 /* Used to initialize the epoll bits inside the "struct file" */
 static inline void eventpoll_init_file(struct file *file)
 {
-	INIT_LIST_HEAD(&file->f_ep_links);
+	INIT_HLIST_HEAD(&file->f_ep_links);
 	INIT_LIST_HEAD(&file->f_tfile_llink);
 }
 
@@ -50,7 +50,7 @@ static inline void eventpoll_release(struct file *file)
 	 * because the file in on the way to be removed and nobody ( but
 	 * eventpoll ) has still a reference to this file.
 	 */
-	if (likely(list_empty(&file->f_ep_links)))
+	if (likely(hlist_empty(&file->f_ep_links)))
 		return;
 
 	/*
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 0bd126418bb6..b484ba0e474a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -946,7 +946,7 @@ struct file {
 
 #ifdef CONFIG_EPOLL
 	/* Used by fs/eventpoll.c to link all the hooks to this file */
-	struct list_head	f_ep_links;
+	struct hlist_head	f_ep_links;
 	struct list_head	f_tfile_llink;
 #endif /* #ifdef CONFIG_EPOLL */
 	struct address_space	*f_mapping;
-- 
cgit v1.2.3


From 319c15174757aaedacc89a6e55c965416f130e64 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 1 Oct 2020 20:45:51 -0400
Subject: epoll: take epitem list out of struct file

Move the head of epitem list out of struct file; for epoll ones it's
moved into struct eventpoll (->refs there), for non-epoll - into
the new object (struct epitem_head).  In place of ->f_ep_links we
leave a pointer to the list head (->f_ep).

->f_ep is protected by ->f_lock and it's zeroed as soon as the list
of epitems becomes empty (that can happen only in ep_remove() by
now).

The list of files for reverse path check is *not* going through
struct file now - it's a single-linked list going through epitem_head
instances.  It's terminated by ERR_PTR(-1) (== EP_UNACTIVE_POINTER),
so the elements of list can be distinguished by head->next != NULL.

epitem_head instances are allocated at ep_insert() time (by
attach_epitem()) and freed either by ep_remove() (if it empties
the set of epitems *and* epitem_head does not belong to the
reverse path check list) or by clear_tfile_check_list() when
the list is emptied (if the set of epitems is empty by that
point).  Allocations are done from a separate slab - minimal kmalloc()
size is too large on some architectures.

As the result, we trim struct file _and_ get rid of the games with
temporary file references.

Locking and barriers are interesting (aren't they always); see unlist_file()
and ep_remove() for details.  The non-obvious part is that ep_remove() needs
to decide if it will be the one to free the damn thing *before* actually
storing NULL to head->epitems.first - that's what smp_load_acquire is for
in there.  unlist_file() lockless path is safe, since we hit it only if
we observe NULL in head->epitems.first and whoever had done that store is
guaranteed to have observed non-NULL in head->next.  IOW, their last access
had been the store of NULL into ->epitems.first and we can safely free
the sucker.  OTOH, we are under rcu_read_lock() and both epitem and
epitem->file have their freeing RCU-delayed.  So if we see non-NULL
->epitems.first, we can grab ->f_lock (all epitems in there share the
same struct file) and safely recheck the emptiness of ->epitems; again,
->next is still non-NULL, so ep_remove() couldn't have freed head yet.
->f_lock serializes us wrt ep_remove(); the rest is trivial.

Note that once head->epitems becomes NULL, nothing can get inserted into
it - the only remaining reference to head after that point is from the
reverse path check list.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/eventpoll.c            | 168 ++++++++++++++++++++++++++++++++++------------
 fs/file_table.c           |   1 -
 include/linux/eventpoll.h |  11 +--
 include/linux/fs.h        |   5 +-
 4 files changed, 129 insertions(+), 56 deletions(-)

(limited to 'include/linux')

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 8f68095c5ce9..d89aead356df 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -215,6 +215,7 @@ struct eventpoll {
 
 	/* used to optimize loop detection check */
 	u64 gen;
+	struct hlist_head refs;
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	/* used to track busy poll napi_id */
@@ -259,7 +260,45 @@ static struct kmem_cache *pwq_cache __read_mostly;
  * List of files with newly added links, where we may need to limit the number
  * of emanating paths. Protected by the epmutex.
  */
-static LIST_HEAD(tfile_check_list);
+struct epitems_head {
+	struct hlist_head epitems;
+	struct epitems_head *next;
+};
+static struct epitems_head *tfile_check_list = EP_UNACTIVE_PTR;
+
+static struct kmem_cache *ephead_cache __read_mostly;
+
+static inline void free_ephead(struct epitems_head *head)
+{
+	if (head)
+		kmem_cache_free(ephead_cache, head);
+}
+
+static void list_file(struct file *file)
+{
+	struct epitems_head *head;
+
+	head = container_of(file->f_ep, struct epitems_head, epitems);
+	if (!head->next) {
+		head->next = tfile_check_list;
+		tfile_check_list = head;
+	}
+}
+
+static void unlist_file(struct epitems_head *head)
+{
+	struct epitems_head *to_free = head;
+	struct hlist_node *p = rcu_dereference(hlist_first_rcu(&head->epitems));
+	if (p) {
+		struct epitem *epi= container_of(p, struct epitem, fllink);
+		spin_lock(&epi->ffd.file->f_lock);
+		if (!hlist_empty(&head->epitems))
+			to_free = NULL;
+		head->next = NULL;
+		spin_unlock(&epi->ffd.file->f_lock);
+	}
+	free_ephead(to_free);
+}
 
 #ifdef CONFIG_SYSCTL
 
@@ -632,6 +671,8 @@ static void epi_rcu_free(struct rcu_head *head)
 static int ep_remove(struct eventpoll *ep, struct epitem *epi)
 {
 	struct file *file = epi->ffd.file;
+	struct epitems_head *to_free;
+	struct hlist_head *head;
 
 	lockdep_assert_irqs_enabled();
 
@@ -642,8 +683,20 @@ static int ep_remove(struct eventpoll *ep, struct epitem *epi)
 
 	/* Remove the current item from the list of epoll hooks */
 	spin_lock(&file->f_lock);
+	to_free = NULL;
+	head = file->f_ep;
+	if (head->first == &epi->fllink && !epi->fllink.next) {
+		file->f_ep = NULL;
+		if (!is_file_epoll(file)) {
+			struct epitems_head *v;
+			v = container_of(head, struct epitems_head, epitems);
+			if (!smp_load_acquire(&v->next))
+				to_free = v;
+		}
+	}
 	hlist_del_rcu(&epi->fllink);
 	spin_unlock(&file->f_lock);
+	free_ephead(to_free);
 
 	rb_erase_cached(&epi->rbn, &ep->rbr);
 
@@ -852,7 +905,11 @@ void eventpoll_release_file(struct file *file)
 	 * Besides, ep_remove() acquires the lock, so we can't hold it here.
 	 */
 	mutex_lock(&epmutex);
-	hlist_for_each_entry_safe(epi, next, &file->f_ep_links, fllink) {
+	if (unlikely(!file->f_ep)) {
+		mutex_unlock(&epmutex);
+		return;
+	}
+	hlist_for_each_entry_safe(epi, next, file->f_ep, fllink) {
 		ep = epi->ep;
 		mutex_lock_nested(&ep->mtx, 0);
 		ep_remove(ep, epi);
@@ -1248,7 +1305,7 @@ static void path_count_init(void)
 		path_count[i] = 0;
 }
 
-static int reverse_path_check_proc(struct file *file, int depth)
+static int reverse_path_check_proc(struct hlist_head *refs, int depth)
 {
 	int error = 0;
 	struct epitem *epi;
@@ -1257,14 +1314,12 @@ static int reverse_path_check_proc(struct file *file, int depth)
 		return -1;
 
 	/* CTL_DEL can remove links here, but that can't increase our count */
-	hlist_for_each_entry_rcu(epi, &file->f_ep_links, fllink) {
-		struct file *recepient = epi->ep->file;
-		if (WARN_ON(!is_file_epoll(recepient)))
-			continue;
-		if (hlist_empty(&recepient->f_ep_links))
+	hlist_for_each_entry_rcu(epi, refs, fllink) {
+		struct hlist_head *refs = &epi->ep->refs;
+		if (hlist_empty(refs))
 			error = path_count_inc(depth);
 		else
-			error = reverse_path_check_proc(recepient, depth + 1);
+			error = reverse_path_check_proc(refs, depth + 1);
 		if (error != 0)
 			break;
 	}
@@ -1272,7 +1327,7 @@ static int reverse_path_check_proc(struct file *file, int depth)
 }
 
 /**
- * reverse_path_check - The tfile_check_list is list of file *, which have
+ * reverse_path_check - The tfile_check_list is list of epitem_head, which have
  *                      links that are proposed to be newly added. We need to
  *                      make sure that those added links don't add too many
  *                      paths such that we will spend all our time waking up
@@ -1283,19 +1338,18 @@ static int reverse_path_check_proc(struct file *file, int depth)
  */
 static int reverse_path_check(void)
 {
-	int error = 0;
-	struct file *current_file;
+	struct epitems_head *p;
 
-	/* let's call this for all tfiles */
-	list_for_each_entry(current_file, &tfile_check_list, f_tfile_llink) {
+	for (p = tfile_check_list; p != EP_UNACTIVE_PTR; p = p->next) {
+		int error;
 		path_count_init();
 		rcu_read_lock();
-		error = reverse_path_check_proc(current_file, 0);
+		error = reverse_path_check_proc(&p->epitems, 0);
 		rcu_read_unlock();
 		if (error)
-			break;
+			return error;
 	}
-	return error;
+	return 0;
 }
 
 static int ep_create_wakeup_source(struct epitem *epi)
@@ -1336,6 +1390,39 @@ static noinline void ep_destroy_wakeup_source(struct epitem *epi)
 	wakeup_source_unregister(ws);
 }
 
+static int attach_epitem(struct file *file, struct epitem *epi)
+{
+	struct epitems_head *to_free = NULL;
+	struct hlist_head *head = NULL;
+	struct eventpoll *ep = NULL;
+
+	if (is_file_epoll(file))
+		ep = file->private_data;
+
+	if (ep) {
+		head = &ep->refs;
+	} else if (!READ_ONCE(file->f_ep)) {
+allocate:
+		to_free = kmem_cache_zalloc(ephead_cache, GFP_KERNEL);
+		if (!to_free)
+			return -ENOMEM;
+		head = &to_free->epitems;
+	}
+	spin_lock(&file->f_lock);
+	if (!file->f_ep) {
+		if (unlikely(!head)) {
+			spin_unlock(&file->f_lock);
+			goto allocate;
+		}
+		file->f_ep = head;
+		to_free = NULL;
+	}
+	hlist_add_head_rcu(&epi->fllink, file->f_ep);
+	spin_unlock(&file->f_lock);
+	free_ephead(to_free);
+	return 0;
+}
+
 /*
  * Must be called with "mtx" held.
  */
@@ -1367,19 +1454,21 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,
 	epi->event = *event;
 	epi->next = EP_UNACTIVE_PTR;
 
-	atomic_long_inc(&ep->user->epoll_watches);
-
 	if (tep)
 		mutex_lock_nested(&tep->mtx, 1);
 	/* Add the current item to the list of active epoll hook for this file */
-	spin_lock(&tfile->f_lock);
-	hlist_add_head_rcu(&epi->fllink, &tfile->f_ep_links);
-	spin_unlock(&tfile->f_lock);
-	if (full_check && !tep) {
-		get_file(tfile);
-		list_add(&tfile->f_tfile_llink, &tfile_check_list);
+	if (unlikely(attach_epitem(tfile, epi) < 0)) {
+		kmem_cache_free(epi_cache, epi);
+		if (tep)
+			mutex_unlock(&tep->mtx);
+		return -ENOMEM;
 	}
 
+	if (full_check && !tep)
+		list_file(tfile);
+
+	atomic_long_inc(&ep->user->epoll_watches);
+
 	/*
 	 * Add the current item to the RB tree. All RB tree operations are
 	 * protected by "mtx", and ep_insert() is called with "mtx" held.
@@ -1813,11 +1902,7 @@ static int ep_loop_check_proc(struct eventpoll *ep, int depth)
 			 * not already there, and calling reverse_path_check()
 			 * during ep_insert().
 			 */
-			if (list_empty(&epi->ffd.file->f_tfile_llink)) {
-				if (get_file_rcu(epi->ffd.file))
-					list_add(&epi->ffd.file->f_tfile_llink,
-						 &tfile_check_list);
-			}
+			list_file(epi->ffd.file);
 		}
 	}
 	mutex_unlock(&ep->mtx);
@@ -1844,16 +1929,13 @@ static int ep_loop_check(struct eventpoll *ep, struct eventpoll *to)
 
 static void clear_tfile_check_list(void)
 {
-	struct file *file;
-
-	/* first clear the tfile_check_list */
-	while (!list_empty(&tfile_check_list)) {
-		file = list_first_entry(&tfile_check_list, struct file,
-					f_tfile_llink);
-		list_del_init(&file->f_tfile_llink);
-		fput(file);
+	rcu_read_lock();
+	while (tfile_check_list != EP_UNACTIVE_PTR) {
+		struct epitems_head *head = tfile_check_list;
+		tfile_check_list = head->next;
+		unlist_file(head);
 	}
-	INIT_LIST_HEAD(&tfile_check_list);
+	rcu_read_unlock();
 }
 
 /*
@@ -2003,9 +2085,8 @@ int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds,
 	if (error)
 		goto error_tgt_fput;
 	if (op == EPOLL_CTL_ADD) {
-		if (!hlist_empty(&f.file->f_ep_links) ||
-				ep->gen == loop_check_gen ||
-						is_file_epoll(tf.file)) {
+		if (READ_ONCE(f.file->f_ep) || ep->gen == loop_check_gen ||
+		    is_file_epoll(tf.file)) {
 			mutex_unlock(&ep->mtx);
 			error = epoll_mutex_lock(&epmutex, 0, nonblock);
 			if (error)
@@ -2216,6 +2297,9 @@ static int __init eventpoll_init(void)
 	pwq_cache = kmem_cache_create("eventpoll_pwq",
 		sizeof(struct eppoll_entry), 0, SLAB_PANIC|SLAB_ACCOUNT, NULL);
 
+	ephead_cache = kmem_cache_create("ep_head",
+		sizeof(struct epitems_head), 0, SLAB_PANIC|SLAB_ACCOUNT, NULL);
+
 	return 0;
 }
 fs_initcall(eventpoll_init);
diff --git a/fs/file_table.c b/fs/file_table.c
index 709ada3151da..45437f8e1003 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -113,7 +113,6 @@ static struct file *__alloc_file(int flags, const struct cred *cred)
 	rwlock_init(&f->f_owner.lock);
 	spin_lock_init(&f->f_lock);
 	mutex_init(&f->f_pos_lock);
-	eventpoll_init_file(f);
 	f->f_flags = flags;
 	f->f_mode = OPEN_FMODE(flags);
 	/* f->f_version: 0 */
diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h
index 4e215ccfa792..0350393465d4 100644
--- a/include/linux/eventpoll.h
+++ b/include/linux/eventpoll.h
@@ -22,14 +22,6 @@ struct file;
 struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long toff);
 #endif
 
-/* Used to initialize the epoll bits inside the "struct file" */
-static inline void eventpoll_init_file(struct file *file)
-{
-	INIT_HLIST_HEAD(&file->f_ep_links);
-	INIT_LIST_HEAD(&file->f_tfile_llink);
-}
-
-
 /* Used to release the epoll bits inside the "struct file" */
 void eventpoll_release_file(struct file *file);
 
@@ -50,7 +42,7 @@ static inline void eventpoll_release(struct file *file)
 	 * because the file in on the way to be removed and nobody ( but
 	 * eventpoll ) has still a reference to this file.
 	 */
-	if (likely(hlist_empty(&file->f_ep_links)))
+	if (likely(!file->f_ep))
 		return;
 
 	/*
@@ -72,7 +64,6 @@ static inline int ep_op_has_event(int op)
 
 #else
 
-static inline void eventpoll_init_file(struct file *file) {}
 static inline void eventpoll_release(struct file *file) {}
 
 #endif
diff --git a/include/linux/fs.h b/include/linux/fs.h
index b484ba0e474a..993c540e3b77 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -923,7 +923,7 @@ struct file {
 	const struct file_operations	*f_op;
 
 	/*
-	 * Protects f_ep_links, f_flags.
+	 * Protects f_ep, f_flags.
 	 * Must not be taken from IRQ context.
 	 */
 	spinlock_t		f_lock;
@@ -946,8 +946,7 @@ struct file {
 
 #ifdef CONFIG_EPOLL
 	/* Used by fs/eventpoll.c to link all the hooks to this file */
-	struct hlist_head	f_ep_links;
-	struct list_head	f_tfile_llink;
+	struct hlist_head	*f_ep;
 #endif /* #ifdef CONFIG_EPOLL */
 	struct address_space	*f_mapping;
 	errseq_t		f_wb_err;
-- 
cgit v1.2.3


From 96ffcdf239de6f9970178bb7d643e16fd9e68ab9 Mon Sep 17 00:00:00 2001
From: Chanwoo Choi <cw00.choi@samsung.com>
Date: Tue, 20 Oct 2020 15:12:12 +0900
Subject: PM / devfreq: Remove redundant governor_name from struct devfreq

The devfreq structure instance contains the governor_name and a governor
instance. When need to show the governor name, better to use the name
of devfreq_governor structure. So, governor_name variable in struct devfreq
is a redundant and unneeded variable. Remove the redundant governor_name
of struct devfreq and then use the name of devfreq_governor instance.

Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
---
 drivers/devfreq/devfreq.c  | 18 +++++++-----------
 drivers/devfreq/governor.h |  2 ++
 include/linux/devfreq.h    |  4 ----
 3 files changed, 9 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 02cfc6552913..6aa10de792b3 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -811,7 +811,6 @@ struct devfreq *devfreq_add_device(struct device *dev,
 	devfreq->dev.release = devfreq_dev_release;
 	INIT_LIST_HEAD(&devfreq->node);
 	devfreq->profile = profile;
-	strscpy(devfreq->governor_name, governor_name, DEVFREQ_NAME_LEN);
 	devfreq->previous_freq = profile->initial_freq;
 	devfreq->last_status.current_frequency = profile->initial_freq;
 	devfreq->data = data;
@@ -907,7 +906,7 @@ struct devfreq *devfreq_add_device(struct device *dev,
 
 	mutex_lock(&devfreq_list_lock);
 
-	governor = try_then_request_governor(devfreq->governor_name);
+	governor = try_then_request_governor(governor_name);
 	if (IS_ERR(governor)) {
 		dev_err(dev, "%s: Unable to find governor for the device\n",
 			__func__);
@@ -1249,7 +1248,7 @@ int devfreq_add_governor(struct devfreq_governor *governor)
 		int ret = 0;
 		struct device *dev = devfreq->dev.parent;
 
-		if (!strncmp(devfreq->governor_name, governor->name,
+		if (!strncmp(devfreq->governor->name, governor->name,
 			     DEVFREQ_NAME_LEN)) {
 			/* The following should never occur */
 			if (devfreq->governor) {
@@ -1311,7 +1310,7 @@ int devfreq_remove_governor(struct devfreq_governor *governor)
 		int ret;
 		struct device *dev = devfreq->dev.parent;
 
-		if (!strncmp(devfreq->governor_name, governor->name,
+		if (!strncmp(devfreq->governor->name, governor->name,
 			     DEVFREQ_NAME_LEN)) {
 			/* we should have a devfreq governor! */
 			if (!devfreq->governor) {
@@ -1406,7 +1405,6 @@ static ssize_t governor_store(struct device *dev, struct device_attribute *attr,
 	 */
 	prev_governor = df->governor;
 	df->governor = governor;
-	strncpy(df->governor_name, governor->name, DEVFREQ_NAME_LEN);
 	ret = df->governor->event_handler(df, DEVFREQ_GOV_START, NULL);
 	if (ret) {
 		dev_warn(dev, "%s: Governor %s not started(%d)\n",
@@ -1414,13 +1412,11 @@ static ssize_t governor_store(struct device *dev, struct device_attribute *attr,
 
 		/* Restore previous governor */
 		df->governor = prev_governor;
-		strncpy(df->governor_name, prev_governor->name,
-			DEVFREQ_NAME_LEN);
 		ret = df->governor->event_handler(df, DEVFREQ_GOV_START, NULL);
 		if (ret) {
 			dev_err(dev,
 				"%s: reverting to Governor %s failed (%d)\n",
-				__func__, df->governor_name, ret);
+				__func__, prev_governor->name, ret);
 			df->governor = NULL;
 			goto out;
 		}
@@ -1459,7 +1455,7 @@ static ssize_t available_governors_show(struct device *d,
 	 */
 	if (IS_SUPPORTED_FLAG(df->governor->flags, IMMUTABLE)) {
 		count = scnprintf(&buf[count], DEVFREQ_NAME_LEN,
-				  "%s ", df->governor_name);
+				  "%s ", df->governor->name);
 	/*
 	 * The devfreq device shows the registered governor except for
 	 * immutable governors such as passive governor .
@@ -1902,7 +1898,7 @@ static int devfreq_summary_show(struct seq_file *s, void *data)
 
 	list_for_each_entry_reverse(devfreq, &devfreq_list, node) {
 #if IS_ENABLED(CONFIG_DEVFREQ_GOV_PASSIVE)
-		if (!strncmp(devfreq->governor_name, DEVFREQ_GOV_PASSIVE,
+		if (!strncmp(devfreq->governor->name, DEVFREQ_GOV_PASSIVE,
 							DEVFREQ_NAME_LEN)) {
 			struct devfreq_passive_data *data = devfreq->data;
 
@@ -1928,7 +1924,7 @@ static int devfreq_summary_show(struct seq_file *s, void *data)
 			"%-30s %-30s %-15s %-10s %10d %12ld %12ld %12ld\n",
 			dev_name(&devfreq->dev),
 			p_devfreq ? dev_name(&p_devfreq->dev) : "null",
-			devfreq->governor_name,
+			devfreq->governor->name,
 			polling_ms ? timer_name[timer] : "null",
 			polling_ms,
 			cur_freq,
diff --git a/drivers/devfreq/governor.h b/drivers/devfreq/governor.h
index df413b851bb2..2a52f97b542d 100644
--- a/drivers/devfreq/governor.h
+++ b/drivers/devfreq/governor.h
@@ -13,6 +13,8 @@
 
 #include <linux/devfreq.h>
 
+#define DEVFREQ_NAME_LEN			16
+
 #define to_devfreq(DEV)	container_of((DEV), struct devfreq, dev)
 
 /* Devfreq events */
diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index 121a2430d7f7..b6d3bae1c74d 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -15,8 +15,6 @@
 #include <linux/pm_opp.h>
 #include <linux/pm_qos.h>
 
-#define DEVFREQ_NAME_LEN 16
-
 /* DEVFREQ governor name */
 #define DEVFREQ_GOV_SIMPLE_ONDEMAND	"simple_ondemand"
 #define DEVFREQ_GOV_PERFORMANCE		"performance"
@@ -139,7 +137,6 @@ struct devfreq_stats {
  *		using devfreq.
  * @profile:	device-specific devfreq profile
  * @governor:	method how to choose frequency based on the usage.
- * @governor_name:	devfreq governor name for use with this devfreq
  * @nb:		notifier block used to notify devfreq object that it should
  *		reevaluate operable frequencies. Devfreq users may use
  *		devfreq.nb to the corresponding register notifier call chain.
@@ -176,7 +173,6 @@ struct devfreq {
 	struct device dev;
 	struct devfreq_dev_profile *profile;
 	const struct devfreq_governor *governor;
-	char governor_name[DEVFREQ_NAME_LEN];
 	struct notifier_block nb;
 	struct delayed_work work;
 
-- 
cgit v1.2.3


From e275d2109cdaea8b4554b9eb8a828bdb8f8ba068 Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Mon, 26 Oct 2020 10:08:47 +0200
Subject: bus: ti-sysc: Fix reset status check for modules with quirks

Commit d46f9fbec719 ("bus: ti-sysc: Use optional clocks on for enable and
wait for softreset bit") started showing a "OCP softreset timed out"
warning on enable if the interconnect target module is not out of reset.
This caused the warning to be often triggered for i2c and hdq while the
devices are working properly.

Turns out that some interconnect target modules seem to have an unusable
reset status bits unless the module specific reset quirks are activated.

Let's just skip the reset status check for those modules as we only want
to activate the reset quirks when doing a reset, and not on enable. This
way we don't see the bogus "OCP softreset timed out" warnings during boot.

Fixes: d46f9fbec719 ("bus: ti-sysc: Use optional clocks on for enable and wait for softreset bit")
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 drivers/bus/ti-sysc.c                 | 24 +++++++++++++++---------
 include/linux/platform_data/ti-sysc.h |  1 +
 2 files changed, 16 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c
index efb088df1276..88a751c11677 100644
--- a/drivers/bus/ti-sysc.c
+++ b/drivers/bus/ti-sysc.c
@@ -970,9 +970,15 @@ static int sysc_enable_module(struct device *dev)
 			return error;
 		}
 	}
-	error = sysc_wait_softreset(ddata);
-	if (error)
-		dev_warn(ddata->dev, "OCP softreset timed out\n");
+	/*
+	 * Some modules like i2c and hdq1w have unusable reset status unless
+	 * the module reset quirk is enabled. Skip status check on enable.
+	 */
+	if (!(ddata->cfg.quirks & SYSC_MODULE_QUIRK_ENA_RESETDONE)) {
+		error = sysc_wait_softreset(ddata);
+		if (error)
+			dev_warn(ddata->dev, "OCP softreset timed out\n");
+	}
 	if (ddata->cfg.quirks & SYSC_QUIRK_OPT_CLKS_IN_RESET)
 		sysc_disable_opt_clocks(ddata);
 
@@ -1373,17 +1379,17 @@ static const struct sysc_revision_quirk sysc_revision_quirks[] = {
 	SYSC_QUIRK("hdmi", 0, 0, 0x10, -ENODEV, 0x50030200, 0xffffffff,
 		   SYSC_QUIRK_OPT_CLKS_NEEDED),
 	SYSC_QUIRK("hdq1w", 0, 0, 0x14, 0x18, 0x00000006, 0xffffffff,
-		   SYSC_MODULE_QUIRK_HDQ1W),
+		   SYSC_MODULE_QUIRK_HDQ1W | SYSC_MODULE_QUIRK_ENA_RESETDONE),
 	SYSC_QUIRK("hdq1w", 0, 0, 0x14, 0x18, 0x0000000a, 0xffffffff,
-		   SYSC_MODULE_QUIRK_HDQ1W),
+		   SYSC_MODULE_QUIRK_HDQ1W | SYSC_MODULE_QUIRK_ENA_RESETDONE),
 	SYSC_QUIRK("i2c", 0, 0, 0x20, 0x10, 0x00000036, 0x000000ff,
-		   SYSC_MODULE_QUIRK_I2C),
+		   SYSC_MODULE_QUIRK_I2C | SYSC_MODULE_QUIRK_ENA_RESETDONE),
 	SYSC_QUIRK("i2c", 0, 0, 0x20, 0x10, 0x0000003c, 0x000000ff,
-		   SYSC_MODULE_QUIRK_I2C),
+		   SYSC_MODULE_QUIRK_I2C | SYSC_MODULE_QUIRK_ENA_RESETDONE),
 	SYSC_QUIRK("i2c", 0, 0, 0x20, 0x10, 0x00000040, 0x000000ff,
-		   SYSC_MODULE_QUIRK_I2C),
+		   SYSC_MODULE_QUIRK_I2C | SYSC_MODULE_QUIRK_ENA_RESETDONE),
 	SYSC_QUIRK("i2c", 0, 0, 0x10, 0x90, 0x5040000a, 0xfffff0f0,
-		   SYSC_MODULE_QUIRK_I2C),
+		   SYSC_MODULE_QUIRK_I2C | SYSC_MODULE_QUIRK_ENA_RESETDONE),
 	SYSC_QUIRK("gpu", 0x50000000, 0x14, -ENODEV, -ENODEV, 0x00010201, 0xffffffff, 0),
 	SYSC_QUIRK("gpu", 0x50000000, 0xfe00, 0xfe10, -ENODEV, 0x40000000 , 0xffffffff,
 		   SYSC_MODULE_QUIRK_SGX),
diff --git a/include/linux/platform_data/ti-sysc.h b/include/linux/platform_data/ti-sysc.h
index c59999ce044e..240dce553a0b 100644
--- a/include/linux/platform_data/ti-sysc.h
+++ b/include/linux/platform_data/ti-sysc.h
@@ -50,6 +50,7 @@ struct sysc_regbits {
 	s8 emufree_shift;
 };
 
+#define SYSC_MODULE_QUIRK_ENA_RESETDONE	BIT(25)
 #define SYSC_MODULE_QUIRK_PRUSS		BIT(24)
 #define SYSC_MODULE_QUIRK_DSS_RESET	BIT(23)
 #define SYSC_MODULE_QUIRK_RTC_UNLOCK	BIT(22)
-- 
cgit v1.2.3


From cb47755725da7b90fecbb2aa82ac3b24a7adb89b Mon Sep 17 00:00:00 2001
From: Zeng Tao <prime.zeng@hisilicon.com>
Date: Tue, 1 Sep 2020 17:30:13 +0800
Subject: time: Prevent undefined behaviour in timespec64_to_ns()

UBSAN reports:

Undefined behaviour in ./include/linux/time64.h:127:27
signed integer overflow:
17179869187 * 1000000000 cannot be represented in type 'long long int'
Call Trace:
 timespec64_to_ns include/linux/time64.h:127 [inline]
 set_cpu_itimer+0x65c/0x880 kernel/time/itimer.c:180
 do_setitimer+0x8e/0x740 kernel/time/itimer.c:245
 __x64_sys_setitimer+0x14c/0x2c0 kernel/time/itimer.c:336
 do_syscall_64+0xa1/0x540 arch/x86/entry/common.c:295

Commit bd40a175769d ("y2038: itimer: change implementation to timespec64")
replaced the original conversion which handled time clamping correctly with
timespec64_to_ns() which has no overflow protection.

Fix it in timespec64_to_ns() as this is not necessarily limited to the
usage in itimers.

[ tglx: Added comment and adjusted the fixes tag ]

Fixes: 361a3bf00582 ("time64: Add time64.h header and define struct timespec64")
Signed-off-by: Zeng Tao <prime.zeng@hisilicon.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/1598952616-6416-1-git-send-email-prime.zeng@hisilicon.com
---
 include/linux/time64.h | 4 ++++
 kernel/time/itimer.c   | 4 ----
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/time64.h b/include/linux/time64.h
index c9dcb3e5781f..5117cb5b5656 100644
--- a/include/linux/time64.h
+++ b/include/linux/time64.h
@@ -124,6 +124,10 @@ static inline bool timespec64_valid_settod(const struct timespec64 *ts)
  */
 static inline s64 timespec64_to_ns(const struct timespec64 *ts)
 {
+	/* Prevent multiplication overflow */
+	if ((unsigned long long)ts->tv_sec >= KTIME_SEC_MAX)
+		return KTIME_MAX;
+
 	return ((s64) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec;
 }
 
diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c
index ca4e6d57d68b..00629e658ca1 100644
--- a/kernel/time/itimer.c
+++ b/kernel/time/itimer.c
@@ -172,10 +172,6 @@ static void set_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
 	u64 oval, nval, ointerval, ninterval;
 	struct cpu_itimer *it = &tsk->signal->it[clock_id];
 
-	/*
-	 * Use the to_ktime conversion because that clamps the maximum
-	 * value to KTIME_MAX and avoid multiplication overflows.
-	 */
 	nval = timespec64_to_ns(&value->it_value);
 	ninterval = timespec64_to_ns(&value->it_interval);
 
-- 
cgit v1.2.3


From bc3d7bf61a9eaecccc84dc2ecc2a9a3fa4f5ec47 Mon Sep 17 00:00:00 2001
From: Gabriel Krisman Bertazi <krisman@collabora.com>
Date: Sat, 3 Oct 2020 23:25:31 -0400
Subject: elf: Expose ELF header in compat_start_thread()

Like it is done for SET_PERSONALITY with x86, which requires the ELF header
to select correct personality parameters, x86 requires the headers on
compat_start_thread() to choose starting CS for ELF32 binaries, instead of
relying on the going-away TIF_IA32/X32 flags.

Add an indirection macro to ELF invocations of START_THREAD, that x86 can
reimplement to receive the extra parameter just for ELF files.  This
requires no changes to other architectures who don't need the header
information, they can continue to use the original start_thread for ELF and
non-ELF binaries, and it prevents affecting non-ELF code paths for x86.

Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20201004032536.1229030-6-krisman@collabora.com
---
 fs/binfmt_elf.c        | 2 +-
 fs/compat_binfmt_elf.c | 9 +++++++--
 include/linux/elf.h    | 5 +++++
 3 files changed, 13 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index b6b3d052ca86..b23f7553fe9b 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1307,7 +1307,7 @@ out_free_interp:
 #endif
 
 	finalize_exec(bprm);
-	start_thread(regs, elf_entry, bprm->p);
+	START_THREAD(elf_ex, regs, elf_entry, bprm->p);
 	retval = 0;
 out:
 	return retval;
diff --git a/fs/compat_binfmt_elf.c b/fs/compat_binfmt_elf.c
index 2d24c765cbd7..12b991368f0a 100644
--- a/fs/compat_binfmt_elf.c
+++ b/fs/compat_binfmt_elf.c
@@ -106,8 +106,13 @@
 #endif
 
 #ifdef	compat_start_thread
-#undef	start_thread
-#define	start_thread		compat_start_thread
+#define COMPAT_START_THREAD(ex, regs, new_ip, new_sp)	\
+	compat_start_thread(regs, new_ip, new_sp)
+#endif
+
+#ifdef	COMPAT_START_THREAD
+#undef	START_THREAD
+#define START_THREAD		COMPAT_START_THREAD
 #endif
 
 #ifdef	compat_arch_setup_additional_pages
diff --git a/include/linux/elf.h b/include/linux/elf.h
index 5d5b0321da0b..6dbcfe7a3fd7 100644
--- a/include/linux/elf.h
+++ b/include/linux/elf.h
@@ -22,6 +22,11 @@
 	SET_PERSONALITY(ex)
 #endif
 
+#ifndef START_THREAD
+#define START_THREAD(elf_ex, regs, elf_entry, start_stack)	\
+	start_thread(regs, elf_entry, start_stack)
+#endif
+
 #define ELF32_GNU_PROPERTY_ALIGN	4
 #define ELF64_GNU_PROPERTY_ALIGN	8
 
-- 
cgit v1.2.3


From 9a29a671902c2be05d636045a4dd365219ca716c Mon Sep 17 00:00:00 2001
From: Gabriel Krisman Bertazi <krisman@collabora.com>
Date: Sat, 3 Oct 2020 23:25:33 -0400
Subject: elf: Expose ELF header on arch_setup_additional_pages()

Like it is done for SET_PERSONALITY with ARM, which requires the ELF
header to select correct personality parameters, x86 requires the
headers when selecting which VDSO to load, instead of relying on the
going-away TIF_IA32/X32 flags.

Add an indirection macro to arch_setup_additional_pages(), that x86 can
reimplement to receive the extra parameter just for ELF files.  This
requires no changes to other architectures, who can continue to use the
original arch_setup_additional_pages for ELF and non-ELF binaries.

Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20201004032536.1229030-8-krisman@collabora.com
---
 fs/binfmt_elf.c        |  2 +-
 fs/compat_binfmt_elf.c | 11 ++++++++---
 include/linux/elf.h    |  5 +++++
 3 files changed, 14 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index b23f7553fe9b..aabc11f099cf 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1246,7 +1246,7 @@ out_free_interp:
 	set_binfmt(&elf_format);
 
 #ifdef ARCH_HAS_SETUP_ADDITIONAL_PAGES
-	retval = arch_setup_additional_pages(bprm, !!interpreter);
+	retval = ARCH_SETUP_ADDITIONAL_PAGES(bprm, elf_ex, !!interpreter);
 	if (retval < 0)
 		goto out;
 #endif /* ARCH_HAS_SETUP_ADDITIONAL_PAGES */
diff --git a/fs/compat_binfmt_elf.c b/fs/compat_binfmt_elf.c
index 12b991368f0a..2c557229696a 100644
--- a/fs/compat_binfmt_elf.c
+++ b/fs/compat_binfmt_elf.c
@@ -115,11 +115,16 @@
 #define START_THREAD		COMPAT_START_THREAD
 #endif
 
-#ifdef	compat_arch_setup_additional_pages
+#ifdef compat_arch_setup_additional_pages
+#define COMPAT_ARCH_SETUP_ADDITIONAL_PAGES(bprm, ex, interpreter) \
+	compat_arch_setup_additional_pages(bprm, interpreter)
+#endif
+
+#ifdef	COMPAT_ARCH_SETUP_ADDITIONAL_PAGES
 #undef	ARCH_HAS_SETUP_ADDITIONAL_PAGES
 #define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
-#undef	arch_setup_additional_pages
-#define	arch_setup_additional_pages compat_arch_setup_additional_pages
+#undef	ARCH_SETUP_ADDITIONAL_PAGES
+#define	ARCH_SETUP_ADDITIONAL_PAGES COMPAT_ARCH_SETUP_ADDITIONAL_PAGES
 #endif
 
 #ifdef	compat_elf_read_implies_exec
diff --git a/include/linux/elf.h b/include/linux/elf.h
index 6dbcfe7a3fd7..c9a46c4e183b 100644
--- a/include/linux/elf.h
+++ b/include/linux/elf.h
@@ -27,6 +27,11 @@
 	start_thread(regs, elf_entry, start_stack)
 #endif
 
+#if defined(ARCH_HAS_SETUP_ADDITIONAL_PAGES) && !defined(ARCH_SETUP_ADDITIONAL_PAGES)
+#define ARCH_SETUP_ADDITIONAL_PAGES(bprm, ex, interpreter) \
+	arch_setup_additional_pages(bprm, interpreter)
+#endif
+
 #define ELF32_GNU_PROPERTY_ALIGN	4
 #define ELF64_GNU_PROPERTY_ALIGN	8
 
-- 
cgit v1.2.3


From ab589bac553f79d559952aa088480a72258ac5bc Mon Sep 17 00:00:00 2001
From: Alexandru Ardelean <alexandru.ardelean@analog.com>
Date: Mon, 19 Oct 2020 13:53:13 +0300
Subject: ASoC: adau1977: remove platform data and move micbias bindings
 include

The change removes the platform_data include/definition. It only contains
some values for the MICBIAS.
These are moved into 'dt-bindings/sound/adi,adau1977.h' so that they can be
used inside device-trees. When moving then, they need to be converted to
pre-compiler defines, so that the DT compiler can understand them.

The driver then, also needs to include the new
'dt-bindings/sound/adi,adau1977.h' file.

Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Link: https://lore.kernel.org/r/20201019105313.24862-1-alexandru.ardelean@analog.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/dt-bindings/sound/adi,adau1977.h | 15 +++++++++++
 include/linux/platform_data/adau1977.h   | 44 --------------------------------
 sound/soc/codecs/adau1977.c              |  9 +++----
 3 files changed, 18 insertions(+), 50 deletions(-)
 create mode 100644 include/dt-bindings/sound/adi,adau1977.h
 delete mode 100644 include/linux/platform_data/adau1977.h

(limited to 'include/linux')

diff --git a/include/dt-bindings/sound/adi,adau1977.h b/include/dt-bindings/sound/adi,adau1977.h
new file mode 100644
index 000000000000..8eebec6570f2
--- /dev/null
+++ b/include/dt-bindings/sound/adi,adau1977.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __DT_BINDINGS_ADI_ADAU1977_H__
+#define __DT_BINDINGS_ADI_ADAU1977_H__
+
+#define ADAU1977_MICBIAS_5V0	0x0
+#define ADAU1977_MICBIAS_5V5	0x1
+#define ADAU1977_MICBIAS_6V0	0x2
+#define ADAU1977_MICBIAS_6V5	0x3
+#define ADAU1977_MICBIAS_7V0	0x4
+#define ADAU1977_MICBIAS_7V5	0x5
+#define ADAU1977_MICBIAS_8V0	0x6
+#define ADAU1977_MICBIAS_8V5	0x7
+#define ADAU1977_MICBIAS_9V0	0x8
+
+#endif /* __DT_BINDINGS_ADI_ADAU1977_H__ */
diff --git a/include/linux/platform_data/adau1977.h b/include/linux/platform_data/adau1977.h
deleted file mode 100644
index 86667235077a..000000000000
--- a/include/linux/platform_data/adau1977.h
+++ /dev/null
@@ -1,44 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * ADAU1977/ADAU1978/ADAU1979 driver
- *
- * Copyright 2014 Analog Devices Inc.
- *  Author: Lars-Peter Clausen <lars@metafoo.de>
- */
-
-#ifndef __LINUX_PLATFORM_DATA_ADAU1977_H__
-#define __LINUX_PLATFORM_DATA_ADAU1977_H__
-
-/**
- * enum adau1977_micbias - ADAU1977 MICBIAS pin voltage setting
- * @ADAU1977_MICBIAS_5V0: MICBIAS is set to 5.0 V
- * @ADAU1977_MICBIAS_5V5: MICBIAS is set to 5.5 V
- * @ADAU1977_MICBIAS_6V0: MICBIAS is set to 6.0 V
- * @ADAU1977_MICBIAS_6V5: MICBIAS is set to 6.5 V
- * @ADAU1977_MICBIAS_7V0: MICBIAS is set to 7.0 V
- * @ADAU1977_MICBIAS_7V5: MICBIAS is set to 7.5 V
- * @ADAU1977_MICBIAS_8V0: MICBIAS is set to 8.0 V
- * @ADAU1977_MICBIAS_8V5: MICBIAS is set to 8.5 V
- * @ADAU1977_MICBIAS_9V0: MICBIAS is set to 9.0 V
- */
-enum adau1977_micbias {
-	ADAU1977_MICBIAS_5V0 = 0x0,
-	ADAU1977_MICBIAS_5V5 = 0x1,
-	ADAU1977_MICBIAS_6V0 = 0x2,
-	ADAU1977_MICBIAS_6V5 = 0x3,
-	ADAU1977_MICBIAS_7V0 = 0x4,
-	ADAU1977_MICBIAS_7V5 = 0x5,
-	ADAU1977_MICBIAS_8V0 = 0x6,
-	ADAU1977_MICBIAS_8V5 = 0x7,
-	ADAU1977_MICBIAS_9V0 = 0x8,
-};
-
-/**
- * struct adau1977_platform_data - Platform configuration data for the ADAU1977
- * @micbias: Specifies the voltage for the MICBIAS pin
- */
-struct adau1977_platform_data {
-	enum adau1977_micbias micbias;
-};
-
-#endif
diff --git a/sound/soc/codecs/adau1977.c b/sound/soc/codecs/adau1977.c
index 0a36e523584c..8260f49caa24 100644
--- a/sound/soc/codecs/adau1977.c
+++ b/sound/soc/codecs/adau1977.c
@@ -12,7 +12,6 @@
 #include <linux/i2c.h>
 #include <linux/init.h>
 #include <linux/module.h>
-#include <linux/platform_data/adau1977.h>
 #include <linux/regmap.h>
 #include <linux/regulator/consumer.h>
 #include <linux/slab.h>
@@ -24,6 +23,8 @@
 #include <sound/soc.h>
 #include <sound/tlv.h>
 
+#include <dt-bindings/sound/adi,adau1977.h>
+
 #include "adau1977.h"
 
 #define ADAU1977_REG_POWER		0x00
@@ -881,13 +882,9 @@ static const struct snd_soc_component_driver adau1977_component_driver = {
 
 static int adau1977_setup_micbias(struct adau1977 *adau1977)
 {
-	struct adau1977_platform_data *pdata = adau1977->dev->platform_data;
 	unsigned int micbias;
 
-	if (pdata)
-		micbias = pdata->micbias;
-	else if (device_property_read_u32(adau1977->dev, "adi,micbias",
-					  &micbias))
+	if (device_property_read_u32(adau1977->dev, "adi,micbias", &micbias))
 		micbias = ADAU1977_MICBIAS_8V5;
 
 	if (micbias > ADAU1977_MICBIAS_9V0) {
-- 
cgit v1.2.3


From 6e1e90ec027509a7e8d4efbd77a65b32b5a8b3ec Mon Sep 17 00:00:00 2001
From: Adrian Ratiu <adrian.ratiu@collabora.com>
Date: Wed, 14 Oct 2020 23:30:24 +0300
Subject: regmap: mmio: add config option to allow relaxed MMIO accesses

On some platforms (eg armv7 due to the CONFIG_ARM_DMA_MEM_BUFFERABLE)
MMIO R/W operations always add memory barriers which can increase load,
decrease battery life or in general reduce performance unnecessarily
on devices which access a lot of configuration registers and where
ordering does not matter (eg. media accelerators like the Verisilicon /
Hantro video decoders).

Drivers used to call the relaxed MMIO variants directly but since they
are now accessing the MMIO registers via regmaps (to compensate for
different VPU HW reg layouts via regmap fields), there is a need for a
relaxed API / config to preserve existing behaviour.

Cc: Mark Brown <broonie@kernel.org>
Signed-off-by: Adrian Ratiu <adrian.ratiu@collabora.com>
Link: https://lore.kernel.org/r/20201014203024.954369-1-adrian.ratiu@collabora.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/base/regmap/regmap-mmio.c | 90 +++++++++++++++++++++++++++++++++++----
 include/linux/regmap.h            |  5 +++
 2 files changed, 87 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/regmap/regmap-mmio.c b/drivers/base/regmap/regmap-mmio.c
index af967d8f975e..f9cd51afb9d2 100644
--- a/drivers/base/regmap/regmap-mmio.c
+++ b/drivers/base/regmap/regmap-mmio.c
@@ -16,6 +16,7 @@
 struct regmap_mmio_context {
 	void __iomem *regs;
 	unsigned val_bytes;
+	bool relaxed_mmio;
 
 	bool attached_clk;
 	struct clk *clk;
@@ -75,6 +76,13 @@ static void regmap_mmio_write8(struct regmap_mmio_context *ctx,
 	writeb(val, ctx->regs + reg);
 }
 
+static void regmap_mmio_write8_relaxed(struct regmap_mmio_context *ctx,
+				unsigned int reg,
+				unsigned int val)
+{
+	writeb_relaxed(val, ctx->regs + reg);
+}
+
 static void regmap_mmio_write16le(struct regmap_mmio_context *ctx,
 				  unsigned int reg,
 				  unsigned int val)
@@ -82,6 +90,13 @@ static void regmap_mmio_write16le(struct regmap_mmio_context *ctx,
 	writew(val, ctx->regs + reg);
 }
 
+static void regmap_mmio_write16le_relaxed(struct regmap_mmio_context *ctx,
+				  unsigned int reg,
+				  unsigned int val)
+{
+	writew_relaxed(val, ctx->regs + reg);
+}
+
 static void regmap_mmio_write16be(struct regmap_mmio_context *ctx,
 				  unsigned int reg,
 				  unsigned int val)
@@ -96,6 +111,13 @@ static void regmap_mmio_write32le(struct regmap_mmio_context *ctx,
 	writel(val, ctx->regs + reg);
 }
 
+static void regmap_mmio_write32le_relaxed(struct regmap_mmio_context *ctx,
+				  unsigned int reg,
+				  unsigned int val)
+{
+	writel_relaxed(val, ctx->regs + reg);
+}
+
 static void regmap_mmio_write32be(struct regmap_mmio_context *ctx,
 				  unsigned int reg,
 				  unsigned int val)
@@ -110,6 +132,13 @@ static void regmap_mmio_write64le(struct regmap_mmio_context *ctx,
 {
 	writeq(val, ctx->regs + reg);
 }
+
+static void regmap_mmio_write64le_relaxed(struct regmap_mmio_context *ctx,
+				  unsigned int reg,
+				  unsigned int val)
+{
+	writeq_relaxed(val, ctx->regs + reg);
+}
 #endif
 
 static int regmap_mmio_write(void *context, unsigned int reg, unsigned int val)
@@ -137,12 +166,24 @@ static unsigned int regmap_mmio_read8(struct regmap_mmio_context *ctx,
 	return readb(ctx->regs + reg);
 }
 
+static unsigned int regmap_mmio_read8_relaxed(struct regmap_mmio_context *ctx,
+				      unsigned int reg)
+{
+	return readb_relaxed(ctx->regs + reg);
+}
+
 static unsigned int regmap_mmio_read16le(struct regmap_mmio_context *ctx,
 				         unsigned int reg)
 {
 	return readw(ctx->regs + reg);
 }
 
+static unsigned int regmap_mmio_read16le_relaxed(struct regmap_mmio_context *ctx,
+						 unsigned int reg)
+{
+	return readw_relaxed(ctx->regs + reg);
+}
+
 static unsigned int regmap_mmio_read16be(struct regmap_mmio_context *ctx,
 				         unsigned int reg)
 {
@@ -155,6 +196,12 @@ static unsigned int regmap_mmio_read32le(struct regmap_mmio_context *ctx,
 	return readl(ctx->regs + reg);
 }
 
+static unsigned int regmap_mmio_read32le_relaxed(struct regmap_mmio_context *ctx,
+						 unsigned int reg)
+{
+	return readl_relaxed(ctx->regs + reg);
+}
+
 static unsigned int regmap_mmio_read32be(struct regmap_mmio_context *ctx,
 				         unsigned int reg)
 {
@@ -167,6 +214,12 @@ static unsigned int regmap_mmio_read64le(struct regmap_mmio_context *ctx,
 {
 	return readq(ctx->regs + reg);
 }
+
+static unsigned int regmap_mmio_read64le_relaxed(struct regmap_mmio_context *ctx,
+						 unsigned int reg)
+{
+	return readq_relaxed(ctx->regs + reg);
+}
 #endif
 
 static int regmap_mmio_read(void *context, unsigned int reg, unsigned int *val)
@@ -237,6 +290,7 @@ static struct regmap_mmio_context *regmap_mmio_gen_context(struct device *dev,
 
 	ctx->regs = regs;
 	ctx->val_bytes = config->val_bits / 8;
+	ctx->relaxed_mmio = config->use_relaxed_mmio;
 	ctx->clk = ERR_PTR(-ENODEV);
 
 	switch (regmap_get_val_endian(dev, &regmap_mmio, config)) {
@@ -247,21 +301,41 @@ static struct regmap_mmio_context *regmap_mmio_gen_context(struct device *dev,
 #endif
 		switch (config->val_bits) {
 		case 8:
-			ctx->reg_read = regmap_mmio_read8;
-			ctx->reg_write = regmap_mmio_write8;
+			if (ctx->relaxed_mmio) {
+				ctx->reg_read = regmap_mmio_read8_relaxed;
+				ctx->reg_write = regmap_mmio_write8_relaxed;
+			} else {
+				ctx->reg_read = regmap_mmio_read8;
+				ctx->reg_write = regmap_mmio_write8;
+			}
 			break;
 		case 16:
-			ctx->reg_read = regmap_mmio_read16le;
-			ctx->reg_write = regmap_mmio_write16le;
+			if (ctx->relaxed_mmio) {
+				ctx->reg_read = regmap_mmio_read16le_relaxed;
+				ctx->reg_write = regmap_mmio_write16le_relaxed;
+			} else {
+				ctx->reg_read = regmap_mmio_read16le;
+				ctx->reg_write = regmap_mmio_write16le;
+			}
 			break;
 		case 32:
-			ctx->reg_read = regmap_mmio_read32le;
-			ctx->reg_write = regmap_mmio_write32le;
+			if (ctx->relaxed_mmio) {
+				ctx->reg_read = regmap_mmio_read32le_relaxed;
+				ctx->reg_write = regmap_mmio_write32le_relaxed;
+			} else {
+				ctx->reg_read = regmap_mmio_read32le;
+				ctx->reg_write = regmap_mmio_write32le;
+			}
 			break;
 #ifdef CONFIG_64BIT
 		case 64:
-			ctx->reg_read = regmap_mmio_read64le;
-			ctx->reg_write = regmap_mmio_write64le;
+			if (ctx->relaxed_mmio) {
+				ctx->reg_read = regmap_mmio_read64le_relaxed;
+				ctx->reg_write = regmap_mmio_write64le_relaxed;
+			} else {
+				ctx->reg_read = regmap_mmio_read64le;
+				ctx->reg_write = regmap_mmio_write64le;
+			}
 			break;
 #endif
 		default:
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index e7834d98207f..126fe700d1d8 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -315,6 +315,10 @@ typedef void (*regmap_unlock)(void *);
  *                   masks are used.
  * @zero_flag_mask: If set, read_flag_mask and write_flag_mask are used even
  *                   if they are both empty.
+ * @use_relaxed_mmio: If set, MMIO R/W operations will not use memory barriers.
+ *                    This can avoid load on devices which don't require strict
+ *                    orderings, but drivers should carefully add any explicit
+ *                    memory barriers when they may require them.
  * @use_single_read: If set, converts the bulk read operation into a series of
  *                   single read operations. This is useful for a device that
  *                   does not support  bulk read.
@@ -388,6 +392,7 @@ struct regmap_config {
 
 	bool use_single_read;
 	bool use_single_write;
+	bool use_relaxed_mmio;
 	bool can_multi_write;
 
 	enum regmap_endian reg_format_endian;
-- 
cgit v1.2.3


From fbdd0049d98d44914fc57d4b91f867f4996c787b Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@nvidia.com>
Date: Mon, 26 Oct 2020 15:43:59 +0200
Subject: RDMA/mlx5: Fix devlink deadlock on net namespace deletion

When a mlx5 core devlink instance is reloaded in different net namespace,
its associated IB device is deleted and recreated.

Example sequence is:
$ ip netns add foo
$ devlink dev reload pci/0000:00:08.0 netns foo
$ ip netns del foo

mlx5 IB device needs to attach and detach the netdevice to it through the
netdev notifier chain during load and unload sequence.  A below call graph
of the unload flow.

cleanup_net()
   down_read(&pernet_ops_rwsem); <- first sem acquired
     ops_pre_exit_list()
       pre_exit()
         devlink_pernet_pre_exit()
           devlink_reload()
             mlx5_devlink_reload_down()
               mlx5_unload_one()
               [...]
                 mlx5_ib_remove()
                   mlx5_ib_unbind_slave_port()
                     mlx5_remove_netdev_notifier()
                       unregister_netdevice_notifier()
                         down_write(&pernet_ops_rwsem);<- recurrsive lock

Hence, when net namespace is deleted, mlx5 reload results in deadlock.

When deadlock occurs, devlink mutex is also held. This not only deadlocks
the mlx5 device under reload, but all the processes which attempt to
access unrelated devlink devices are deadlocked.

Hence, fix this by mlx5 ib driver to register for per net netdev notifier
instead of global one, which operats on the net namespace without holding
the pernet_ops_rwsem.

Fixes: 4383cfcc65e7 ("net/mlx5: Add devlink reload")
Link: https://lore.kernel.org/r/20201026134359.23150-1-parav@nvidia.com
Signed-off-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/hw/mlx5/main.c                  |  6 ++++--
 drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h |  5 -----
 include/linux/mlx5/driver.h                        | 18 ++++++++++++++++++
 3 files changed, 22 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 89e04ca62ae0..246e3cbe0b2c 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -3305,7 +3305,8 @@ static int mlx5_add_netdev_notifier(struct mlx5_ib_dev *dev, u8 port_num)
 	int err;
 
 	dev->port[port_num].roce.nb.notifier_call = mlx5_netdev_event;
-	err = register_netdevice_notifier(&dev->port[port_num].roce.nb);
+	err = register_netdevice_notifier_net(mlx5_core_net(dev->mdev),
+					      &dev->port[port_num].roce.nb);
 	if (err) {
 		dev->port[port_num].roce.nb.notifier_call = NULL;
 		return err;
@@ -3317,7 +3318,8 @@ static int mlx5_add_netdev_notifier(struct mlx5_ib_dev *dev, u8 port_num)
 static void mlx5_remove_netdev_notifier(struct mlx5_ib_dev *dev, u8 port_num)
 {
 	if (dev->port[port_num].roce.nb.notifier_call) {
-		unregister_netdevice_notifier(&dev->port[port_num].roce.nb);
+		unregister_netdevice_notifier_net(mlx5_core_net(dev->mdev),
+						  &dev->port[port_num].roce.nb);
 		dev->port[port_num].roce.nb.notifier_call = NULL;
 	}
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
index d046db7bb047..3a9fa629503f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
@@ -90,9 +90,4 @@ int mlx5_create_encryption_key(struct mlx5_core_dev *mdev,
 			       u32 key_type, u32 *p_key_id);
 void mlx5_destroy_encryption_key(struct mlx5_core_dev *mdev, u32 key_id);
 
-static inline struct net *mlx5_core_net(struct mlx5_core_dev *dev)
-{
-	return devlink_net(priv_to_devlink(dev));
-}
-
 #endif
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index add85094f9a5..0f23e1ed5e71 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1213,4 +1213,22 @@ static inline bool mlx5_is_roce_enabled(struct mlx5_core_dev *dev)
 	return val.vbool;
 }
 
+/**
+ * mlx5_core_net - Provide net namespace of the mlx5_core_dev
+ * @dev: mlx5 core device
+ *
+ * mlx5_core_net() returns the net namespace of mlx5 core device.
+ * This can be called only in below described limited context.
+ * (a) When a devlink instance for mlx5_core is registered and
+ *     when devlink reload operation is disabled.
+ *     or
+ * (b) during devlink reload reload_down() and reload_up callbacks
+ *     where it is ensured that devlink instance's net namespace is
+ *     stable.
+ */
+static inline struct net *mlx5_core_net(struct mlx5_core_dev *dev)
+{
+	return devlink_net(priv_to_devlink(dev));
+}
+
 #endif /* MLX5_DRIVER_H */
-- 
cgit v1.2.3


From ab7cffb8d2367e5b088c7c14452724e719a10eba Mon Sep 17 00:00:00 2001
From: Sam Ravnborg <sam@ravnborg.org>
Date: Mon, 26 Oct 2020 20:20:40 +0100
Subject: MIPS: ingenic: remove unused platform_data header file

There are no users of this headers file in the kernel.
All users are likely migrated to device tree which is a good thing.

Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Paul Cercueil <paul@crapouillou.net>
Cc: Harvey Hunt <harveyhuntnexus@gmail.com>
Cc: linux-mips@vger.kernel.org
Reviewed-by: Paul Cercueil <paul@crapouillou.net>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 include/linux/platform_data/jz4740/jz4740_nand.h | 25 ------------------------
 1 file changed, 25 deletions(-)
 delete mode 100644 include/linux/platform_data/jz4740/jz4740_nand.h

(limited to 'include/linux')

diff --git a/include/linux/platform_data/jz4740/jz4740_nand.h b/include/linux/platform_data/jz4740/jz4740_nand.h
deleted file mode 100644
index b3f066d63059..000000000000
--- a/include/linux/platform_data/jz4740/jz4740_nand.h
+++ /dev/null
@@ -1,25 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- *  Copyright (C) 2009-2010, Lars-Peter Clausen <lars@metafoo.de>
- *  JZ4740 SoC NAND controller driver
- */
-
-#ifndef __JZ4740_NAND_H__
-#define __JZ4740_NAND_H__
-
-#include <linux/mtd/rawnand.h>
-#include <linux/mtd/partitions.h>
-
-#define JZ_NAND_NUM_BANKS 4
-
-struct jz_nand_platform_data {
-	int			num_partitions;
-	struct mtd_partition	*partitions;
-
-	unsigned char banks[JZ_NAND_NUM_BANKS];
-
-	void (*ident_callback)(struct platform_device *, struct mtd_info *,
-				struct mtd_partition **, int *num_partitions);
-};
-
-#endif
-- 
cgit v1.2.3


From 343a3e8bc635bd4c58d45a4fe67f9c3a78fbd191 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 26 Oct 2020 17:20:50 +0100
Subject: bpf: Fix -Wshadow warnings

There are thousands of warnings about one macro in a W=2 build:

  include/linux/filter.h:561:6: warning: declaration of 'ret' shadows a previous local [-Wshadow]

Prefix all the locals in that macro with __ to avoid most of
these warnings.

Fixes: 492ecee892c2 ("bpf: enable program stats")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20201026162110.3710415-1-arnd@kernel.org
---
 include/linux/filter.h | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 72d62cbc1578..1b62397bd124 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -558,21 +558,21 @@ struct sk_filter {
 DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key);
 
 #define __BPF_PROG_RUN(prog, ctx, dfunc)	({			\
-	u32 ret;							\
+	u32 __ret;							\
 	cant_migrate();							\
 	if (static_branch_unlikely(&bpf_stats_enabled_key)) {		\
-		struct bpf_prog_stats *stats;				\
-		u64 start = sched_clock();				\
-		ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func);	\
-		stats = this_cpu_ptr(prog->aux->stats);			\
-		u64_stats_update_begin(&stats->syncp);			\
-		stats->cnt++;						\
-		stats->nsecs += sched_clock() - start;			\
-		u64_stats_update_end(&stats->syncp);			\
+		struct bpf_prog_stats *__stats;				\
+		u64 __start = sched_clock();				\
+		__ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func);	\
+		__stats = this_cpu_ptr(prog->aux->stats);		\
+		u64_stats_update_begin(&__stats->syncp);		\
+		__stats->cnt++;						\
+		__stats->nsecs += sched_clock() - __start;		\
+		u64_stats_update_end(&__stats->syncp);			\
 	} else {							\
-		ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func);	\
+		__ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func);	\
 	}								\
-	ret; })
+	__ret; })
 
 #define BPF_PROG_RUN(prog, ctx)						\
 	__BPF_PROG_RUN(prog, ctx, bpf_dispatcher_nop_func)
-- 
cgit v1.2.3


From 1c534352f47fd83eb08075ac2474f707e74bf7f7 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Fri, 23 Oct 2020 17:35:19 +0200
Subject: cpufreq: Introduce CPUFREQ_NEED_UPDATE_LIMITS driver flag

Generally, a cpufreq driver may need to update some internal upper
and lower frequency boundaries on policy max and min changes,
respectively, but currently this does not work if the target
frequency does not change along with the policy limit.

Namely, if the target frequency does not change along with the
policy min or max, the "target_freq == policy->cur" check in
__cpufreq_driver_target() prevents driver callbacks from being
invoked and they do not even have a chance to update the
corresponding internal boundary.

This particularly affects the "powersave" and "performance"
governors that always set the target frequency to one of the
policy limits and it never changes when the other limit is updated.

To allow cpufreq the drivers needing to update internal frequency
boundaries on policy limits changes to avoid this issue, introduce
a new driver flag, CPUFREQ_NEED_UPDATE_LIMITS, that (when set) will
neutralize the check mentioned above.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
---
 drivers/cpufreq/cpufreq.c |  3 ++-
 include/linux/cpufreq.h   | 10 +++++++++-
 2 files changed, 11 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index f4b60663efe6..ea58337fb65f 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -2187,7 +2187,8 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy,
 	 * exactly same freq is called again and so we can save on few function
 	 * calls.
 	 */
-	if (target_freq == policy->cur)
+	if (target_freq == policy->cur &&
+	    !(cpufreq_driver->flags & CPUFREQ_NEED_UPDATE_LIMITS))
 		return 0;
 
 	/* Save last value to restore later on errors */
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index fa37b1c66443..038ed83aab41 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -298,7 +298,7 @@ __ATTR(_name, 0644, show_##_name, store_##_name)
 
 struct cpufreq_driver {
 	char		name[CPUFREQ_NAME_LEN];
-	u8		flags;
+	u16		flags;
 	void		*driver_data;
 
 	/* needed by all drivers */
@@ -422,6 +422,14 @@ struct cpufreq_driver {
  */
 #define CPUFREQ_IS_COOLING_DEV			BIT(7)
 
+/*
+ * Set by drivers that need to update internale upper and lower boundaries along
+ * with the target frequency and so the core and governors should also invoke
+ * the diver if the target frequency does not change, but the policy min or max
+ * may have changed.
+ */
+#define CPUFREQ_NEED_UPDATE_LIMITS		BIT(8)
+
 int cpufreq_register_driver(struct cpufreq_driver *driver_data);
 int cpufreq_unregister_driver(struct cpufreq_driver *driver_data);
 
-- 
cgit v1.2.3


From 6d915476e67d99b73a57bceb83cff1cf153d8bf6 Mon Sep 17 00:00:00 2001
From: Richard Guy Briggs <rgb@redhat.com>
Date: Tue, 22 Sep 2020 08:44:50 -0400
Subject: audit: trigger accompanying records when no rules present

When there are no audit rules registered, mandatory records (config,
etc.) are missing their accompanying records (syscall, proctitle, etc.).

This is due to audit context dummy set on syscall entry based on absence
of rules that signals that no other records are to be printed.  Clear the dummy
bit if any record is generated, open coding this in audit_log_start().

The proctitle context and dummy checks are pointless since the
proctitle record will not be printed if no syscall records are printed.

The fds array is reset to -1 after the first syscall to indicate it
isn't valid any more, but was never set to -1 when the context was
allocated to indicate it wasn't yet valid.

Check ctx->pwd in audit_log_name().

The audit_inode* functions can be called without going through
getname_flags() or getname_kernel() that sets audit_names and cwd, so
set the cwd in audit_alloc_name() if it has not already been done so due to
audit_names being valid and purge all other audit_getcwd() calls.

Revert the LSM dump_common_audit_data() LSM_AUDIT_DATA_* cases from the
ghak96 patch since they are no longer necessary due to cwd coverage in
audit_alloc_name().

Thanks to bauen1 <j2468h@googlemail.com> for reporting LSM situations in
which context->cwd is not valid, inadvertantly fixed by the ghak96 patch.

Please see upstream github issue
https://github.com/linux-audit/audit-kernel/issues/120
This is also related to upstream github issue
https://github.com/linux-audit/audit-kernel/issues/96

Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 include/linux/audit.h |  8 --------
 kernel/audit.c        |  3 +++
 kernel/auditsc.c      | 27 +++++++--------------------
 security/lsm_audit.c  |  5 -----
 4 files changed, 10 insertions(+), 33 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index b3d859831a31..82b7c1116a85 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -292,7 +292,6 @@ extern void __audit_syscall_entry(int major, unsigned long a0, unsigned long a1,
 extern void __audit_syscall_exit(int ret_success, long ret_value);
 extern struct filename *__audit_reusename(const __user char *uptr);
 extern void __audit_getname(struct filename *name);
-extern void __audit_getcwd(void);
 extern void __audit_inode(struct filename *name, const struct dentry *dentry,
 				unsigned int flags);
 extern void __audit_file(const struct file *);
@@ -351,11 +350,6 @@ static inline void audit_getname(struct filename *name)
 	if (unlikely(!audit_dummy_context()))
 		__audit_getname(name);
 }
-static inline void audit_getcwd(void)
-{
-	if (unlikely(audit_context()))
-		__audit_getcwd();
-}
 static inline void audit_inode(struct filename *name,
 				const struct dentry *dentry,
 				unsigned int aflags) {
@@ -584,8 +578,6 @@ static inline struct filename *audit_reusename(const __user char *name)
 }
 static inline void audit_getname(struct filename *name)
 { }
-static inline void audit_getcwd(void)
-{ }
 static inline void audit_inode(struct filename *name,
 				const struct dentry *dentry,
 				unsigned int aflags)
diff --git a/kernel/audit.c b/kernel/audit.c
index 0be42cac086b..ac0aeaa99937 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -1865,6 +1865,9 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
 	}
 
 	audit_get_stamp(ab->ctx, &t, &serial);
+	/* cancel dummy context to enable supporting records */
+	if (ctx)
+		ctx->dummy = 0;
 	audit_log_format(ab, "audit(%llu.%03lu:%u): ",
 			 (unsigned long long)t.tv_sec, t.tv_nsec/1000000, serial);
 
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 8dba8f0983b5..183d79cc2e12 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -929,6 +929,7 @@ static inline struct audit_context *audit_alloc_context(enum audit_state state)
 	context->prio = state == AUDIT_RECORD_CONTEXT ? ~0ULL : 0;
 	INIT_LIST_HEAD(&context->killed_trees);
 	INIT_LIST_HEAD(&context->names_list);
+	context->fds[0] = -1;
 	return context;
 }
 
@@ -1367,7 +1368,10 @@ static void audit_log_name(struct audit_context *context, struct audit_names *n,
 			/* name was specified as a relative path and the
 			 * directory component is the cwd
 			 */
-			audit_log_d_path(ab, " name=", &context->pwd);
+			if (context->pwd.dentry && context->pwd.mnt)
+				audit_log_d_path(ab, " name=", &context->pwd);
+			else
+				audit_log_format(ab, " name=(null)");
 			break;
 		default:
 			/* log the name's directory component */
@@ -1435,9 +1439,6 @@ static void audit_log_proctitle(void)
 	struct audit_context *context = audit_context();
 	struct audit_buffer *ab;
 
-	if (!context || context->dummy)
-		return;
-
 	ab = audit_log_start(context, GFP_KERNEL, AUDIT_PROCTITLE);
 	if (!ab)
 		return;	/* audit_panic or being filtered */
@@ -1866,6 +1867,8 @@ static struct audit_names *audit_alloc_name(struct audit_context *context,
 	list_add_tail(&aname->list, &context->names_list);
 
 	context->name_count++;
+	if (!context->pwd.dentry)
+		get_fs_pwd(current->fs, &context->pwd);
 	return aname;
 }
 
@@ -1894,20 +1897,6 @@ __audit_reusename(const __user char *uptr)
 	return NULL;
 }
 
-inline void _audit_getcwd(struct audit_context *context)
-{
-	if (!context->pwd.dentry)
-		get_fs_pwd(current->fs, &context->pwd);
-}
-
-void __audit_getcwd(void)
-{
-	struct audit_context *context = audit_context();
-
-	if (context->in_syscall)
-		_audit_getcwd(context);
-}
-
 /**
  * __audit_getname - add a name to the list
  * @name: name to add
@@ -1931,8 +1920,6 @@ void __audit_getname(struct filename *name)
 	n->name_len = AUDIT_NAME_FULL;
 	name->aname = n;
 	name->refcnt++;
-
-	_audit_getcwd(context);
 }
 
 static inline int audit_copy_fcaps(struct audit_names *name,
diff --git a/security/lsm_audit.c b/security/lsm_audit.c
index 53d0d183db8f..221370794d14 100644
--- a/security/lsm_audit.c
+++ b/security/lsm_audit.c
@@ -241,7 +241,6 @@ static void dump_common_audit_data(struct audit_buffer *ab,
 			audit_log_untrustedstring(ab, inode->i_sb->s_id);
 			audit_log_format(ab, " ino=%lu", inode->i_ino);
 		}
-		audit_getcwd();
 		break;
 	}
 	case LSM_AUDIT_DATA_FILE: {
@@ -255,7 +254,6 @@ static void dump_common_audit_data(struct audit_buffer *ab,
 			audit_log_untrustedstring(ab, inode->i_sb->s_id);
 			audit_log_format(ab, " ino=%lu", inode->i_ino);
 		}
-		audit_getcwd();
 		break;
 	}
 	case LSM_AUDIT_DATA_IOCTL_OP: {
@@ -271,7 +269,6 @@ static void dump_common_audit_data(struct audit_buffer *ab,
 		}
 
 		audit_log_format(ab, " ioctlcmd=0x%hx", a->u.op->cmd);
-		audit_getcwd();
 		break;
 	}
 	case LSM_AUDIT_DATA_DENTRY: {
@@ -286,7 +283,6 @@ static void dump_common_audit_data(struct audit_buffer *ab,
 			audit_log_untrustedstring(ab, inode->i_sb->s_id);
 			audit_log_format(ab, " ino=%lu", inode->i_ino);
 		}
-		audit_getcwd();
 		break;
 	}
 	case LSM_AUDIT_DATA_INODE: {
@@ -304,7 +300,6 @@ static void dump_common_audit_data(struct audit_buffer *ab,
 		audit_log_format(ab, " dev=");
 		audit_log_untrustedstring(ab, inode->i_sb->s_id);
 		audit_log_format(ab, " ino=%lu", inode->i_ino);
-		audit_getcwd();
 		break;
 	}
 	case LSM_AUDIT_DATA_TASK: {
-- 
cgit v1.2.3


From 95de5094f5ac50b6f355f4e7dffcb6f34bd5dada Mon Sep 17 00:00:00 2001
From: Peng Fan <peng.fan@nxp.com>
Date: Tue, 22 Sep 2020 18:24:29 +0800
Subject: firmware: imx: add dummy functions

add dummy functions to avoid build failure when header files
are included, but drivers are not built.

Signed-off-by: Peng Fan <peng.fan@nxp.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
 include/linux/firmware/imx/ipc.h      | 13 +++++++++++++
 include/linux/firmware/imx/sci.h      | 27 +++++++++++++++++++++++++++
 include/linux/firmware/imx/svc/misc.h | 19 +++++++++++++++++++
 3 files changed, 59 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/firmware/imx/ipc.h b/include/linux/firmware/imx/ipc.h
index 891057434858..0b4643571625 100644
--- a/include/linux/firmware/imx/ipc.h
+++ b/include/linux/firmware/imx/ipc.h
@@ -34,6 +34,7 @@ struct imx_sc_rpc_msg {
 	uint8_t func;
 };
 
+#ifdef CONFIG_IMX_SCU
 /*
  * This is an function to send an RPC message over an IPC channel.
  * It is called by client-side SCFW API function shims.
@@ -55,4 +56,16 @@ int imx_scu_call_rpc(struct imx_sc_ipc *ipc, void *msg, bool have_resp);
  * @return Returns an error code (0 = success, failed if < 0)
  */
 int imx_scu_get_handle(struct imx_sc_ipc **ipc);
+#else
+static inline int imx_scu_call_rpc(struct imx_sc_ipc *ipc, void *msg,
+				   bool have_resp)
+{
+	return -ENOTSUPP;
+}
+
+static inline int imx_scu_get_handle(struct imx_sc_ipc **ipc)
+{
+	return -ENOTSUPP;
+}
+#endif
 #endif /* _SC_IPC_H */
diff --git a/include/linux/firmware/imx/sci.h b/include/linux/firmware/imx/sci.h
index 22c76571a294..5cc63fe7e84d 100644
--- a/include/linux/firmware/imx/sci.h
+++ b/include/linux/firmware/imx/sci.h
@@ -16,9 +16,36 @@
 #include <linux/firmware/imx/svc/pm.h>
 #include <linux/firmware/imx/svc/rm.h>
 
+#if IS_ENABLED(CONFIG_IMX_SCU)
 int imx_scu_enable_general_irq_channel(struct device *dev);
 int imx_scu_irq_register_notifier(struct notifier_block *nb);
 int imx_scu_irq_unregister_notifier(struct notifier_block *nb);
 int imx_scu_irq_group_enable(u8 group, u32 mask, u8 enable);
 int imx_scu_soc_init(struct device *dev);
+#else
+static inline int imx_scu_soc_init(struct device *dev)
+{
+	return -ENOTSUPP;
+}
+
+static inline int imx_scu_enable_general_irq_channel(struct device *dev)
+{
+	return -ENOTSUPP;
+}
+
+static inline int imx_scu_irq_register_notifier(struct notifier_block *nb)
+{
+	return -ENOTSUPP;
+}
+
+static inline int imx_scu_irq_unregister_notifier(struct notifier_block *nb)
+{
+	return -ENOTSUPP;
+}
+
+static inline int imx_scu_irq_group_enable(u8 group, u32 mask, u8 enable)
+{
+	return -ENOTSUPP;
+}
+#endif
 #endif /* _SC_SCI_H */
diff --git a/include/linux/firmware/imx/svc/misc.h b/include/linux/firmware/imx/svc/misc.h
index 031dd4d3c766..760db08a67fc 100644
--- a/include/linux/firmware/imx/svc/misc.h
+++ b/include/linux/firmware/imx/svc/misc.h
@@ -46,6 +46,7 @@ enum imx_misc_func {
  * Control Functions
  */
 
+#ifdef CONFIG_IMX_SCU
 int imx_sc_misc_set_control(struct imx_sc_ipc *ipc, u32 resource,
 			    u8 ctrl, u32 val);
 
@@ -54,5 +55,23 @@ int imx_sc_misc_get_control(struct imx_sc_ipc *ipc, u32 resource,
 
 int imx_sc_pm_cpu_start(struct imx_sc_ipc *ipc, u32 resource,
 			bool enable, u64 phys_addr);
+#else
+static inline int imx_sc_misc_set_control(struct imx_sc_ipc *ipc,
+					  u32 resource, u8 ctrl, u32 val)
+{
+	return -ENOTSUPP;
+}
 
+static inline int imx_sc_misc_get_control(struct imx_sc_ipc *ipc,
+					  u32 resource, u8 ctrl, u32 *val)
+{
+	return -ENOTSUPP;
+}
+
+static inline int imx_sc_pm_cpu_start(struct imx_sc_ipc *ipc, u32 resource,
+				      bool enable, u64 phys_addr)
+{
+	return -ENOTSUPP;
+}
+#endif
 #endif /* _SC_MISC_API_H */
-- 
cgit v1.2.3


From 1de111b51b829bcf01d2e57971f8fd07a665fa3f Mon Sep 17 00:00:00 2001
From: Stephen Boyd <swboyd@chromium.org>
Date: Fri, 23 Oct 2020 08:47:50 -0700
Subject: KVM: arm64: ARM_SMCCC_ARCH_WORKAROUND_1 doesn't return
 SMCCC_RET_NOT_REQUIRED

According to the SMCCC spec[1](7.5.2 Discovery) the
ARM_SMCCC_ARCH_WORKAROUND_1 function id only returns 0, 1, and
SMCCC_RET_NOT_SUPPORTED.

 0 is "workaround required and safe to call this function"
 1 is "workaround not required but safe to call this function"
 SMCCC_RET_NOT_SUPPORTED is "might be vulnerable or might not be, who knows, I give up!"

SMCCC_RET_NOT_SUPPORTED might as well mean "workaround required, except
calling this function may not work because it isn't implemented in some
cases". Wonderful. We map this SMC call to

 0 is SPECTRE_MITIGATED
 1 is SPECTRE_UNAFFECTED
 SMCCC_RET_NOT_SUPPORTED is SPECTRE_VULNERABLE

For KVM hypercalls (hvc), we've implemented this function id to return
SMCCC_RET_NOT_SUPPORTED, 0, and SMCCC_RET_NOT_REQUIRED. One of those
isn't supposed to be there. Per the code we call
arm64_get_spectre_v2_state() to figure out what to return for this
feature discovery call.

 0 is SPECTRE_MITIGATED
 SMCCC_RET_NOT_REQUIRED is SPECTRE_UNAFFECTED
 SMCCC_RET_NOT_SUPPORTED is SPECTRE_VULNERABLE

Let's clean this up so that KVM tells the guest this mapping:

 0 is SPECTRE_MITIGATED
 1 is SPECTRE_UNAFFECTED
 SMCCC_RET_NOT_SUPPORTED is SPECTRE_VULNERABLE

Note: SMCCC_RET_NOT_AFFECTED is 1 but isn't part of the SMCCC spec

Fixes: c118bbb52743 ("arm64: KVM: Propagate full Spectre v2 workaround state to KVM guests")
Signed-off-by: Stephen Boyd <swboyd@chromium.org>
Acked-by: Marc Zyngier <maz@kernel.org>
Acked-by: Will Deacon <will@kernel.org>
Cc: Andre Przywara <andre.przywara@arm.com>
Cc: Steven Price <steven.price@arm.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: stable@vger.kernel.org
Link: https://developer.arm.com/documentation/den0028/latest [1]
Link: https://lore.kernel.org/r/20201023154751.1973872-1-swboyd@chromium.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/proton-pack.c | 2 --
 arch/arm64/kvm/hypercalls.c     | 2 +-
 include/linux/arm-smccc.h       | 2 ++
 3 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c
index 25f3c80b5ffe..c18eb7d41274 100644
--- a/arch/arm64/kernel/proton-pack.c
+++ b/arch/arm64/kernel/proton-pack.c
@@ -135,8 +135,6 @@ static enum mitigation_state spectre_v2_get_cpu_hw_mitigation_state(void)
 	return SPECTRE_VULNERABLE;
 }
 
-#define SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED	(1)
-
 static enum mitigation_state spectre_v2_get_cpu_fw_mitigation_state(void)
 {
 	int ret;
diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c
index 9824025ccc5c..25ea4ecb6449 100644
--- a/arch/arm64/kvm/hypercalls.c
+++ b/arch/arm64/kvm/hypercalls.c
@@ -31,7 +31,7 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu)
 				val = SMCCC_RET_SUCCESS;
 				break;
 			case SPECTRE_UNAFFECTED:
-				val = SMCCC_RET_NOT_REQUIRED;
+				val = SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED;
 				break;
 			}
 			break;
diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h
index 885c9ffc835c..f860645f6512 100644
--- a/include/linux/arm-smccc.h
+++ b/include/linux/arm-smccc.h
@@ -87,6 +87,8 @@
 			   ARM_SMCCC_SMC_32,				\
 			   0, 0x7fff)
 
+#define SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED	1
+
 /* Paravirtualised time calls (defined by ARM DEN0057A) */
 #define ARM_SMCCC_HV_PV_TIME_FEATURES				\
 	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,			\
-- 
cgit v1.2.3


From ea856ec266c1e6aecd2b107032d5b5d661f0686d Mon Sep 17 00:00:00 2001
From: Samuel Čavoj <samuel@cavoj.net>
Date: Wed, 21 Oct 2020 00:09:44 +0200
Subject: platform/x86: asus-wmi: Add support for SW_TABLET_MODE on UX360
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The UX360CA has a WMI device id 0x00060062, which reports whether the
lid is flipped in tablet mode (1) or in normal laptop mode (0).

Add a quirk (quirk_asus_use_lid_flip_devid) for devices on which this
WMI device should be used to figure out the SW_TABLET_MODE state, as
opposed to the quirk_asus_use_kbd_dock_devid.

Additionally, the device needs to be queried on resume and restore
because the firmware does not generate an event if the laptop is put to
sleep while in tablet mode, flipped to normal mode, and later awoken.

It is assumed other UX360* models have the same WMI device. As such, the
quirk is applied to devices with DMI_MATCH(DMI_PRODUCT_NAME, "UX360").
More devices with this feature need to be tested and added accordingly.

The reason for using an allowlist via the quirk mechanism is that the new
WMI device (0x00060062) is also present on some models which do not have
a 360 degree hinge (at least FX503VD and GL503VD from Hans' DSTS
collection) and therefore its presence cannot be relied on.

Signed-off-by: Samuel Čavoj <samuel@cavoj.net>
Cc: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20201020220944.1075530-1-samuel@cavoj.net
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/platform/x86/asus-nb-wmi.c         | 15 +++++++++++
 drivers/platform/x86/asus-wmi.c            | 40 ++++++++++++++++++++++++++++++
 drivers/platform/x86/asus-wmi.h            |  1 +
 include/linux/platform_data/x86/asus-wmi.h |  1 +
 4 files changed, 57 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c
index 1d9fbabd02fb..d41d7ad14be0 100644
--- a/drivers/platform/x86/asus-nb-wmi.c
+++ b/drivers/platform/x86/asus-nb-wmi.c
@@ -119,6 +119,11 @@ static struct quirk_entry quirk_asus_use_kbd_dock_devid = {
 	.use_kbd_dock_devid = true,
 };
 
+static struct quirk_entry quirk_asus_use_lid_flip_devid = {
+	.wmi_backlight_set_devstate = true,
+	.use_lid_flip_devid = true,
+};
+
 static int dmi_matched(const struct dmi_system_id *dmi)
 {
 	pr_info("Identified laptop model '%s'\n", dmi->ident);
@@ -520,6 +525,16 @@ static const struct dmi_system_id asus_quirks[] = {
 		},
 		.driver_data = &quirk_asus_use_kbd_dock_devid,
 	},
+	{
+		.callback = dmi_matched,
+		.ident = "ASUS ZenBook Flip UX360",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			/* Match UX360* */
+			DMI_MATCH(DMI_PRODUCT_NAME, "UX360"),
+		},
+		.driver_data = &quirk_asus_use_lid_flip_devid,
+	},
 	{},
 };
 
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index 39e1a6396e08..fa884c418f4e 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -63,6 +63,7 @@ MODULE_LICENSE("GPL");
 #define NOTIFY_KBD_BRTTOGGLE		0xc7
 #define NOTIFY_KBD_FBM			0x99
 #define NOTIFY_KBD_TTP			0xae
+#define NOTIFY_LID_FLIP			0xfa
 
 #define ASUS_WMI_FNLOCK_BIOS_DISABLED	BIT(0)
 
@@ -375,6 +376,20 @@ static int asus_wmi_input_init(struct asus_wmi *asus)
 		}
 	}
 
+	if (asus->driver->quirks->use_lid_flip_devid) {
+		result = asus_wmi_get_devstate_simple(asus, ASUS_WMI_DEVID_LID_FLIP);
+		if (result < 0)
+			asus->driver->quirks->use_lid_flip_devid = 0;
+		if (result >= 0) {
+			input_set_capability(asus->inputdev, EV_SW, SW_TABLET_MODE);
+			input_report_switch(asus->inputdev, SW_TABLET_MODE, result);
+		} else if (result == -ENODEV) {
+			pr_err("This device has lid_flip quirk but got ENODEV checking it. This is a bug.");
+		} else {
+			pr_err("Error checking for lid-flip: %d\n", result);
+		}
+	}
+
 	err = input_register_device(asus->inputdev);
 	if (err)
 		goto err_free_dev;
@@ -394,6 +409,18 @@ static void asus_wmi_input_exit(struct asus_wmi *asus)
 	asus->inputdev = NULL;
 }
 
+/* Tablet mode ****************************************************************/
+
+static void lid_flip_tablet_mode_get_state(struct asus_wmi *asus)
+{
+	int result = asus_wmi_get_devstate_simple(asus, ASUS_WMI_DEVID_LID_FLIP);
+
+	if (result >= 0) {
+		input_report_switch(asus->inputdev, SW_TABLET_MODE, result);
+		input_sync(asus->inputdev);
+	}
+}
+
 /* Battery ********************************************************************/
 
 /* The battery maximum charging percentage */
@@ -2128,6 +2155,11 @@ static void asus_wmi_handle_event_code(int code, struct asus_wmi *asus)
 		return;
 	}
 
+	if (asus->driver->quirks->use_lid_flip_devid && code == NOTIFY_LID_FLIP) {
+		lid_flip_tablet_mode_get_state(asus);
+		return;
+	}
+
 	if (asus->fan_boost_mode_available && code == NOTIFY_KBD_FBM) {
 		fan_boost_mode_switch_next(asus);
 		return;
@@ -2719,6 +2751,10 @@ static int asus_hotk_resume(struct device *device)
 
 	if (asus_wmi_has_fnlock_key(asus))
 		asus_wmi_fnlock_update(asus);
+
+	if (asus->driver->quirks->use_lid_flip_devid)
+		lid_flip_tablet_mode_get_state(asus);
+
 	return 0;
 }
 
@@ -2757,6 +2793,10 @@ static int asus_hotk_restore(struct device *device)
 
 	if (asus_wmi_has_fnlock_key(asus))
 		asus_wmi_fnlock_update(asus);
+
+	if (asus->driver->quirks->use_lid_flip_devid)
+		lid_flip_tablet_mode_get_state(asus);
+
 	return 0;
 }
 
diff --git a/drivers/platform/x86/asus-wmi.h b/drivers/platform/x86/asus-wmi.h
index 1a95c172f94b..b302415bf1d9 100644
--- a/drivers/platform/x86/asus-wmi.h
+++ b/drivers/platform/x86/asus-wmi.h
@@ -34,6 +34,7 @@ struct quirk_entry {
 	bool wmi_backlight_set_devstate;
 	bool wmi_force_als_set;
 	bool use_kbd_dock_devid;
+	bool use_lid_flip_devid;
 	int wapf;
 	/*
 	 * For machines with AMD graphic chips, it will send out WMI event
diff --git a/include/linux/platform_data/x86/asus-wmi.h b/include/linux/platform_data/x86/asus-wmi.h
index 897b8332a39f..2f274cf52805 100644
--- a/include/linux/platform_data/x86/asus-wmi.h
+++ b/include/linux/platform_data/x86/asus-wmi.h
@@ -62,6 +62,7 @@
 
 /* Misc */
 #define ASUS_WMI_DEVID_CAMERA		0x00060013
+#define ASUS_WMI_DEVID_LID_FLIP		0x00060062
 
 /* Storage */
 #define ASUS_WMI_DEVID_CARDREADER	0x00080013
-- 
cgit v1.2.3


From cbdc0f54560f94c2205ddbebb5464d65868af0d8 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Fri, 23 Oct 2020 18:33:18 +0200
Subject: usb: fix kernel-doc markups

There is a common comment marked, instead, with kernel-doc
notation.

Also, some identifiers have different names between their
prototypes and the kernel-doc markup.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Acked-by: Felipe Balbi <balbi@kernel.org>
Link: https://lore.kernel.org/r/0b964be3884def04fcd20ea5c12cb90d0014871c.1603469755.git.mchehab+huawei@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/core.c        | 2 +-
 drivers/usb/dwc3/core.h        | 2 +-
 drivers/usb/gadget/composite.c | 2 +-
 drivers/usb/typec/mux.c        | 2 +-
 include/linux/usb/composite.h  | 2 +-
 5 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index bdf0925da6b6..841daec70b6e 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/**
+/*
  * core.c - DesignWare USB3 DRD Controller Core file
  *
  * Copyright (C) 2010-2011 Texas Instruments Incorporated - https://www.ti.com
diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index 74323b10a64a..2f95f08ca511 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -1277,7 +1277,7 @@ struct dwc3_event_type {
 #define DWC3_DEPEVT_EPCMDCMPLT		0x07
 
 /**
- * struct dwc3_event_depvt - Device Endpoint Events
+ * struct dwc3_event_depevt - Device Endpoint Events
  * @one_bit: indicates this is an endpoint event (not used)
  * @endpoint_number: number of the endpoint
  * @endpoint_event: The event we have:
diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index 05b176c82cc5..c6d455f2bb92 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -1245,7 +1245,7 @@ int usb_string_id(struct usb_composite_dev *cdev)
 EXPORT_SYMBOL_GPL(usb_string_id);
 
 /**
- * usb_string_ids() - allocate unused string IDs in batch
+ * usb_string_ids_tab() - allocate unused string IDs in batch
  * @cdev: the device whose string descriptor IDs are being allocated
  * @str: an array of usb_string objects to assign numbers to
  * Context: single threaded during gadget setup
diff --git a/drivers/usb/typec/mux.c b/drivers/usb/typec/mux.c
index b069a5122aaa..cf720e944aaa 100644
--- a/drivers/usb/typec/mux.c
+++ b/drivers/usb/typec/mux.c
@@ -71,7 +71,7 @@ struct typec_switch *fwnode_typec_switch_get(struct fwnode_handle *fwnode)
 EXPORT_SYMBOL_GPL(fwnode_typec_switch_get);
 
 /**
- * typec_put_switch - Release USB Type-C orientation switch
+ * typec_switch_put - Release USB Type-C orientation switch
  * @sw: USB Type-C orientation switch
  *
  * Decrement reference count for @sw.
diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h
index 2040696d75b6..a2d229ab63ba 100644
--- a/include/linux/usb/composite.h
+++ b/include/linux/usb/composite.h
@@ -437,7 +437,7 @@ static inline struct usb_composite_driver *to_cdriver(
 #define OS_STRING_IDX			0xEE
 
 /**
- * struct usb_composite_device - represents one composite usb gadget
+ * struct usb_composite_dev - represents one composite usb gadget
  * @gadget: read-only, abstracts the gadget's usb peripheral controller
  * @req: used for control responses; buffer is pre-allocated
  * @os_desc_req: used for OS descriptors responses; buffer is pre-allocated
-- 
cgit v1.2.3


From da31de35cd2fb78f75788873e0b61e56d4bb1a90 Mon Sep 17 00:00:00 2001
From: Laurent Vivier <laurent@vivier.eu>
Date: Sat, 10 Oct 2020 02:47:49 +0200
Subject: tty: goldfish: use __raw_writel()/__raw_readl()

gf_early_console_putchar() uses __raw_writel() but the standard driver
uses writel()/readl(). This means we can't use both on the same machine
as the device is either big-endian, little-endian or native-endian.

As android implementation defines the endianness of the device is the one
of the architecture replace all writel()/readl() by
__raw_writel()/__raw_readl()

https://android.googlesource.com/platform/external/qemu/+/refs/heads/emu-master-dev/hw/char/goldfish_tty.c#222

Signed-off-by: Laurent Vivier <laurent@vivier.eu>
Link: https://lore.kernel.org/r/20201010004749.1201695-1-laurent@vivier.eu
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/goldfish.c   | 18 +++++++++---------
 include/linux/goldfish.h |  8 ++++----
 2 files changed, 13 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/goldfish.c b/drivers/tty/goldfish.c
index c8c5cdfc5e19..cd23a4b05c8f 100644
--- a/drivers/tty/goldfish.c
+++ b/drivers/tty/goldfish.c
@@ -61,13 +61,13 @@ static void do_rw_io(struct goldfish_tty *qtty,
 	spin_lock_irqsave(&qtty->lock, irq_flags);
 	gf_write_ptr((void *)address, base + GOLDFISH_TTY_REG_DATA_PTR,
 		     base + GOLDFISH_TTY_REG_DATA_PTR_HIGH);
-	writel(count, base + GOLDFISH_TTY_REG_DATA_LEN);
+	__raw_writel(count, base + GOLDFISH_TTY_REG_DATA_LEN);
 
 	if (is_write)
-		writel(GOLDFISH_TTY_CMD_WRITE_BUFFER,
+		__raw_writel(GOLDFISH_TTY_CMD_WRITE_BUFFER,
 		       base + GOLDFISH_TTY_REG_CMD);
 	else
-		writel(GOLDFISH_TTY_CMD_READ_BUFFER,
+		__raw_writel(GOLDFISH_TTY_CMD_READ_BUFFER,
 		       base + GOLDFISH_TTY_REG_CMD);
 
 	spin_unlock_irqrestore(&qtty->lock, irq_flags);
@@ -142,7 +142,7 @@ static irqreturn_t goldfish_tty_interrupt(int irq, void *dev_id)
 	unsigned char *buf;
 	u32 count;
 
-	count = readl(base + GOLDFISH_TTY_REG_BYTES_READY);
+	count = __raw_readl(base + GOLDFISH_TTY_REG_BYTES_READY);
 	if (count == 0)
 		return IRQ_NONE;
 
@@ -159,7 +159,7 @@ static int goldfish_tty_activate(struct tty_port *port, struct tty_struct *tty)
 {
 	struct goldfish_tty *qtty = container_of(port, struct goldfish_tty,
 									port);
-	writel(GOLDFISH_TTY_CMD_INT_ENABLE, qtty->base + GOLDFISH_TTY_REG_CMD);
+	__raw_writel(GOLDFISH_TTY_CMD_INT_ENABLE, qtty->base + GOLDFISH_TTY_REG_CMD);
 	return 0;
 }
 
@@ -167,7 +167,7 @@ static void goldfish_tty_shutdown(struct tty_port *port)
 {
 	struct goldfish_tty *qtty = container_of(port, struct goldfish_tty,
 									port);
-	writel(GOLDFISH_TTY_CMD_INT_DISABLE, qtty->base + GOLDFISH_TTY_REG_CMD);
+	__raw_writel(GOLDFISH_TTY_CMD_INT_DISABLE, qtty->base + GOLDFISH_TTY_REG_CMD);
 }
 
 static int goldfish_tty_open(struct tty_struct *tty, struct file *filp)
@@ -202,7 +202,7 @@ static int goldfish_tty_chars_in_buffer(struct tty_struct *tty)
 {
 	struct goldfish_tty *qtty = &goldfish_ttys[tty->index];
 	void __iomem *base = qtty->base;
-	return readl(base + GOLDFISH_TTY_REG_BYTES_READY);
+	return __raw_readl(base + GOLDFISH_TTY_REG_BYTES_READY);
 }
 
 static void goldfish_tty_console_write(struct console *co, const char *b,
@@ -357,7 +357,7 @@ static int goldfish_tty_probe(struct platform_device *pdev)
 	 * on Ranchu emulator (qemu2) returns 1 here and
 	 * driver will use physical addresses.
 	 */
-	qtty->version = readl(base + GOLDFISH_TTY_REG_VERSION);
+	qtty->version = __raw_readl(base + GOLDFISH_TTY_REG_VERSION);
 
 	/*
 	 * Goldfish TTY device on Ranchu emulator (qemu2)
@@ -376,7 +376,7 @@ static int goldfish_tty_probe(struct platform_device *pdev)
 		}
 	}
 
-	writel(GOLDFISH_TTY_CMD_INT_DISABLE, base + GOLDFISH_TTY_REG_CMD);
+	__raw_writel(GOLDFISH_TTY_CMD_INT_DISABLE, base + GOLDFISH_TTY_REG_CMD);
 
 	ret = request_irq(irq, goldfish_tty_interrupt, IRQF_SHARED,
 			  "goldfish_tty", qtty);
diff --git a/include/linux/goldfish.h b/include/linux/goldfish.h
index 265a099cd3b8..12be1601fd84 100644
--- a/include/linux/goldfish.h
+++ b/include/linux/goldfish.h
@@ -13,9 +13,9 @@ static inline void gf_write_ptr(const void *ptr, void __iomem *portl,
 {
 	const unsigned long addr = (unsigned long)ptr;
 
-	writel(lower_32_bits(addr), portl);
+	__raw_writel(lower_32_bits(addr), portl);
 #ifdef CONFIG_64BIT
-	writel(upper_32_bits(addr), porth);
+	__raw_writel(upper_32_bits(addr), porth);
 #endif
 }
 
@@ -23,9 +23,9 @@ static inline void gf_write_dma_addr(const dma_addr_t addr,
 				     void __iomem *portl,
 				     void __iomem *porth)
 {
-	writel(lower_32_bits(addr), portl);
+	__raw_writel(lower_32_bits(addr), portl);
 #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-	writel(upper_32_bits(addr), porth);
+	__raw_writel(upper_32_bits(addr), porth);
 #endif
 }
 
-- 
cgit v1.2.3


From caabdd0f59a9771ed095efe3ad5a08867b976ab2 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 19 Oct 2020 09:35:39 +0200
Subject: ctype.h: remove duplicate isdigit() helper

gcc warns a few thousand times about the isdigit() shadow:

include/linux/ctype.h:26:19: warning: declaration of 'isdigit' shadows a built-in function [-Wshadow]

As there is already a compiler builtin, just use that, and make
it clear we do that by defining a macro.  Unfortunately, clang
does not have the isdigit() builtin, so this has to be conditional.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 include/linux/compiler_types.h | 11 +++++++++++
 include/linux/ctype.h          | 15 +++++++++++----
 2 files changed, 22 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 6e390d58a9f8..5d41dff3f79c 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -64,6 +64,17 @@ static inline void __chk_io_ptr(const volatile void __iomem *ptr) { }
 /* Attributes */
 #include <linux/compiler_attributes.h>
 
+/* Builtins */
+
+/*
+ * __has_builtin is supported on gcc >= 10, clang >= 3 and icc >= 21.
+ * In the meantime, to support gcc < 10, we implement __has_builtin
+ * by hand.
+ */
+#ifndef __has_builtin
+#define __has_builtin(x) (0)
+#endif
+
 /* Compiler specific macros. */
 #ifdef __clang__
 #include <linux/compiler-clang.h>
diff --git a/include/linux/ctype.h b/include/linux/ctype.h
index 363b004426db..bc95aef2219c 100644
--- a/include/linux/ctype.h
+++ b/include/linux/ctype.h
@@ -2,6 +2,8 @@
 #ifndef _LINUX_CTYPE_H
 #define _LINUX_CTYPE_H
 
+#include <linux/compiler.h>
+
 /*
  * NOTE! This ctype does not handle EOF like the standard C
  * library is required to.
@@ -23,10 +25,6 @@ extern const unsigned char _ctype[];
 #define isalnum(c)	((__ismask(c)&(_U|_L|_D)) != 0)
 #define isalpha(c)	((__ismask(c)&(_U|_L)) != 0)
 #define iscntrl(c)	((__ismask(c)&(_C)) != 0)
-static inline int isdigit(int c)
-{
-	return '0' <= c && c <= '9';
-}
 #define isgraph(c)	((__ismask(c)&(_P|_U|_L|_D)) != 0)
 #define islower(c)	((__ismask(c)&(_L)) != 0)
 #define isprint(c)	((__ismask(c)&(_P|_U|_L|_D|_SP)) != 0)
@@ -39,6 +37,15 @@ static inline int isdigit(int c)
 #define isascii(c) (((unsigned char)(c))<=0x7f)
 #define toascii(c) (((unsigned char)(c))&0x7f)
 
+#if __has_builtin(__builtin_isdigit)
+#define  isdigit(c) __builtin_isdigit(c)
+#else
+static inline int isdigit(int c)
+{
+	return '0' <= c && c <= '9';
+}
+#endif
+
 static inline unsigned char __tolower(unsigned char c)
 {
 	if (isupper(c))
-- 
cgit v1.2.3


From 13150bc5416f45234c955e5bed91623d178c6117 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Tue, 27 Oct 2020 16:11:32 +0100
Subject: module: use hidden visibility for weak symbol references

Geert reports that commit be2881824ae9eb92 ("arm64/build: Assert for
unwanted sections") results in build errors on arm64 for configurations
that have CONFIG_MODULES disabled.

The commit in question added ASSERT()s to the arm64 linker script to
ensure that linker generated sections such as .got.plt etc are empty,
but as it turns out, there are corner cases where the linker does emit
content into those sections. More specifically, weak references to
function symbols (which can remain unsatisfied, and can therefore not
be emitted as relative references) will be emitted as GOT and PLT
entries when linking the kernel in PIE mode (which is the case when
CONFIG_RELOCATABLE is enabled, which is on by default).

What happens is that code such as

	struct device *(*fn)(struct device *dev);
	struct device *iommu_device;

	fn = symbol_get(mdev_get_iommu_device);
	if (fn) {
		iommu_device = fn(dev);

essentially gets converted into the following when CONFIG_MODULES is off:

	struct device *iommu_device;

	if (&mdev_get_iommu_device) {
		iommu_device = mdev_get_iommu_device(dev);

where mdev_get_iommu_device is emitted as a weak symbol reference into
the object file. The first reference is decorated with an ordinary
ABS64 data relocation (which yields 0x0 if the reference remains
unsatisfied). However, the indirect call is turned into a direct call
covered by a R_AARCH64_CALL26 relocation, which is converted into a
call via a PLT entry taking the target address from the associated
GOT entry.

Given that such GOT and PLT entries are unnecessary for fully linked
binaries such as the kernel, let's give these weak symbol references
hidden visibility, so that the linker knows that the weak reference
via R_AARCH64_CALL26 can simply remain unsatisfied.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Fangrui Song <maskray@google.com>
Acked-by: Jessica Yu <jeyu@kernel.org>
Cc: Jessica Yu <jeyu@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Link: https://lore.kernel.org/r/20201027151132.14066-1-ardb@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 include/linux/module.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/module.h b/include/linux/module.h
index 7ccdf87f376f..6264617bab4d 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -740,7 +740,7 @@ static inline bool within_module(unsigned long addr, const struct module *mod)
 }
 
 /* Get/put a kernel symbol (calls should be symmetric) */
-#define symbol_get(x) ({ extern typeof(x) x __attribute__((weak)); &(x); })
+#define symbol_get(x) ({ extern typeof(x) x __attribute__((weak,visibility("hidden"))); &(x); })
 #define symbol_put(x) do { } while (0)
 #define symbol_put_addr(x) do { } while (0)
 
-- 
cgit v1.2.3


From 39613eaad3ceff320da344427a70c655e783475e Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Wed, 28 Oct 2020 12:16:10 +0530
Subject: qcom-geni-se: remove has_opp_table

has_opp_table isn't used anymore, remove it.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>

Link: https://lore.kernel.org/r/08ec1ee1d4252a266956abb5f1e0e0026d753564.1603867487.git.viresh.kumar@linaro.org
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 include/linux/qcom-geni-se.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/qcom-geni-se.h b/include/linux/qcom-geni-se.h
index f7bbea3f09ca..ec2ad4b0fe14 100644
--- a/include/linux/qcom-geni-se.h
+++ b/include/linux/qcom-geni-se.h
@@ -48,7 +48,6 @@ struct geni_icc_path {
  * @clk_perf_tbl:	Table of clock frequency input to serial engine clock
  * @icc_paths:		Array of ICC paths for SE
  * @opp_table:		Pointer to the OPP table
- * @has_opp_table:	Specifies if the SE has an OPP table
  */
 struct geni_se {
 	void __iomem *base;
@@ -59,7 +58,6 @@ struct geni_se {
 	unsigned long *clk_perf_tbl;
 	struct geni_icc_path icc_paths[3];
 	struct opp_table *opp_table;
-	bool has_opp_table;
 };
 
 /* Common SE registers */
-- 
cgit v1.2.3


From f1f37abbe6fc2b1242f78157db76e48dbf9518ee Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Mon, 19 Oct 2020 15:40:46 +0200
Subject: gpio: Retire the explicit gpio irqchip code

Now that all gpiolib irqchip users have been over to use
the irqchip template, we can finally retire the old code
path and leave just one way in to the irqchip: set up the
template when registering the gpio_chip. For a while
we had two code paths for this which was a bit confusing.

This brings this work to a conclusion, there is now one
way of doing this.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Cc: Thierry Reding <thierry.reding@gmail.com>
Link: https://lore.kernel.org/r/20201019134046.65101-1-linus.walleij@linaro.org
---
 Documentation/driver-api/gpio/driver.rst |  63 ++++++++-----
 drivers/gpio/TODO                        |  49 ----------
 drivers/gpio/gpiolib.c                   | 153 -------------------------------
 include/linux/gpio/driver.h              |  71 --------------
 4 files changed, 42 insertions(+), 294 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/driver-api/gpio/driver.rst b/Documentation/driver-api/gpio/driver.rst
index 072a7455044e..65d708093b71 100644
--- a/Documentation/driver-api/gpio/driver.rst
+++ b/Documentation/driver-api/gpio/driver.rst
@@ -416,7 +416,8 @@ The preferred way to set up the helpers is to fill in the
 struct gpio_irq_chip inside struct gpio_chip before adding the gpio_chip.
 If you do this, the additional irq_chip will be set up by gpiolib at the
 same time as setting up the rest of the GPIO functionality. The following
-is a typical example of a cascaded interrupt handler using gpio_irq_chip:
+is a typical example of a chained cascaded interrupt handler using
+the gpio_irq_chip:
 
 .. code-block:: c
 
@@ -452,7 +453,46 @@ is a typical example of a cascaded interrupt handler using gpio_irq_chip:
 
   return devm_gpiochip_add_data(dev, &g->gc, g);
 
-The helper support using hierarchical interrupt controllers as well.
+The helper supports using threaded interrupts as well. Then you just request
+the interrupt separately and go with it:
+
+.. code-block:: c
+
+  /* Typical state container with dynamic irqchip */
+  struct my_gpio {
+      struct gpio_chip gc;
+      struct irq_chip irq;
+  };
+
+  int irq; /* from platform etc */
+  struct my_gpio *g;
+  struct gpio_irq_chip *girq;
+
+  /* Set up the irqchip dynamically */
+  g->irq.name = "my_gpio_irq";
+  g->irq.irq_ack = my_gpio_ack_irq;
+  g->irq.irq_mask = my_gpio_mask_irq;
+  g->irq.irq_unmask = my_gpio_unmask_irq;
+  g->irq.irq_set_type = my_gpio_set_irq_type;
+
+  ret = devm_request_threaded_irq(dev, irq, NULL,
+		irq_thread_fn, IRQF_ONESHOT, "my-chip", g);
+  if (ret < 0)
+	return ret;
+
+  /* Get a pointer to the gpio_irq_chip */
+  girq = &g->gc.irq;
+  girq->chip = &g->irq;
+  /* This will let us handle the parent IRQ in the driver */
+  girq->parent_handler = NULL;
+  girq->num_parents = 0;
+  girq->parents = NULL;
+  girq->default_type = IRQ_TYPE_NONE;
+  girq->handler = handle_bad_irq;
+
+  return devm_gpiochip_add_data(dev, &g->gc, g);
+
+The helper supports using hierarchical interrupt controllers as well.
 In this case the typical set-up will look like this:
 
 .. code-block:: c
@@ -493,25 +533,6 @@ the parent hardware irq from a child (i.e. this gpio chip) hardware irq.
 As always it is good to look at examples in the kernel tree for advice
 on how to find the required pieces.
 
-The old way of adding irqchips to gpiochips after registration is also still
-available but we try to move away from this:
-
-- DEPRECATED: gpiochip_irqchip_add(): adds a chained cascaded irqchip to a
-  gpiochip. It will pass the struct gpio_chip* for the chip to all IRQ
-  callbacks, so the callbacks need to embed the gpio_chip in its state
-  container and obtain a pointer to the container using container_of().
-  (See Documentation/driver-api/driver-model/design-patterns.rst)
-
-- gpiochip_irqchip_add_nested(): adds a nested cascaded irqchip to a gpiochip,
-  as discussed above regarding different types of cascaded irqchips. The
-  cascaded irq has to be handled by a threaded interrupt handler.
-  Apart from that it works exactly like the chained irqchip.
-
-- gpiochip_set_nested_irqchip(): sets up a nested cascaded irq handler for a
-  gpio_chip from a parent IRQ. As the parent IRQ has usually been
-  explicitly requested by the driver, this does very little more than
-  mark all the child IRQs as having the other IRQ as parent.
-
 If there is a need to exclude certain GPIO lines from the IRQ domain handled by
 these helpers, we can set .irq.need_valid_mask of the gpiochip before
 devm_gpiochip_add_data() or gpiochip_add_data() is called. This allocates an
diff --git a/drivers/gpio/TODO b/drivers/gpio/TODO
index e560e45e84f8..cd04e0b60159 100644
--- a/drivers/gpio/TODO
+++ b/drivers/gpio/TODO
@@ -129,58 +129,9 @@ GPIOLIB irqchip
 The GPIOLIB irqchip is a helper irqchip for "simple cases" that should
 try to cover any generic kind of irqchip cascaded from a GPIO.
 
-- Convert all the GPIOLIB_IRQCHIP users to pass an irqchip template,
-  parent and flags before calling [devm_]gpiochip_add[_data]().
-  Currently we set up the irqchip after setting up the gpiochip
-  using gpiochip_irqchip_add() and gpiochip_set_[chained|nested]_irqchip().
-  This is too complex, so convert all users over to just set up
-  the irqchip before registering the gpio_chip, typical example:
-
-  /* Typical state container with dynamic irqchip */
-  struct my_gpio {
-      struct gpio_chip gc;
-      struct irq_chip irq;
-  };
-
-  int irq; /* from platform etc */
-  struct my_gpio *g;
-  struct gpio_irq_chip *girq;
-
-  /* Set up the irqchip dynamically */
-  g->irq.name = "my_gpio_irq";
-  g->irq.irq_ack = my_gpio_ack_irq;
-  g->irq.irq_mask = my_gpio_mask_irq;
-  g->irq.irq_unmask = my_gpio_unmask_irq;
-  g->irq.irq_set_type = my_gpio_set_irq_type;
-
-  /* Get a pointer to the gpio_irq_chip */
-  girq = &g->gc.irq;
-  girq->chip = &g->irq;
-  girq->parent_handler = ftgpio_gpio_irq_handler;
-  girq->num_parents = 1;
-  girq->parents = devm_kcalloc(dev, 1, sizeof(*girq->parents),
-                               GFP_KERNEL);
-  if (!girq->parents)
-      return -ENOMEM;
-  girq->default_type = IRQ_TYPE_NONE;
-  girq->handler = handle_bad_irq;
-  girq->parents[0] = irq;
-
-  When this is done, we will delete the old APIs for instatiating
-  GPIOLIB_IRQCHIP and simplify the code.
-
 - Look over and identify any remaining easily converted drivers and
   dry-code conversions to gpiolib irqchip for maintainers to test
 
-- Drop gpiochip_set_chained_irqchip() when all the chained irqchips
-  have been converted to the above infrastructure.
-
-- Add more infrastructure to make it possible to also pass a threaded
-  irqchip in struct gpio_irq_chip.
-
-- Drop gpiochip_irqchip_add_nested() when all the chained irqchips
-  have been converted to the above infrastructure.
-
 
 Increase integration with pin control
 
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 3b23a0ca77dd..8e29a60c3697 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -924,67 +924,6 @@ bool gpiochip_irqchip_irq_valid(const struct gpio_chip *gc,
 }
 EXPORT_SYMBOL_GPL(gpiochip_irqchip_irq_valid);
 
-/**
- * gpiochip_set_cascaded_irqchip() - connects a cascaded irqchip to a gpiochip
- * @gc: the gpiochip to set the irqchip chain to
- * @parent_irq: the irq number corresponding to the parent IRQ for this
- * cascaded irqchip
- * @parent_handler: the parent interrupt handler for the accumulated IRQ
- * coming out of the gpiochip. If the interrupt is nested rather than
- * cascaded, pass NULL in this handler argument
- */
-static void gpiochip_set_cascaded_irqchip(struct gpio_chip *gc,
-					  unsigned int parent_irq,
-					  irq_flow_handler_t parent_handler)
-{
-	struct gpio_irq_chip *girq = &gc->irq;
-	struct device *dev = &gc->gpiodev->dev;
-
-	if (!girq->domain) {
-		chip_err(gc, "called %s before setting up irqchip\n",
-			 __func__);
-		return;
-	}
-
-	if (parent_handler) {
-		if (gc->can_sleep) {
-			chip_err(gc,
-				 "you cannot have chained interrupts on a chip that may sleep\n");
-			return;
-		}
-		girq->parents = devm_kcalloc(dev, 1,
-					     sizeof(*girq->parents),
-					     GFP_KERNEL);
-		if (!girq->parents) {
-			chip_err(gc, "out of memory allocating parent IRQ\n");
-			return;
-		}
-		girq->parents[0] = parent_irq;
-		girq->num_parents = 1;
-		/*
-		 * The parent irqchip is already using the chip_data for this
-		 * irqchip, so our callbacks simply use the handler_data.
-		 */
-		irq_set_chained_handler_and_data(parent_irq, parent_handler,
-						 gc);
-	}
-}
-
-/**
- * gpiochip_set_nested_irqchip() - connects a nested irqchip to a gpiochip
- * @gc: the gpiochip to set the irqchip nested handler to
- * @irqchip: the irqchip to nest to the gpiochip
- * @parent_irq: the irq number corresponding to the parent IRQ for this
- * nested irqchip
- */
-void gpiochip_set_nested_irqchip(struct gpio_chip *gc,
-				 struct irq_chip *irqchip,
-				 unsigned int parent_irq)
-{
-	gpiochip_set_cascaded_irqchip(gc, parent_irq, NULL);
-}
-EXPORT_SYMBOL_GPL(gpiochip_set_nested_irqchip);
-
 #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
 
 /**
@@ -1635,98 +1574,6 @@ static void gpiochip_irqchip_remove(struct gpio_chip *gc)
 	gpiochip_irqchip_free_valid_mask(gc);
 }
 
-/**
- * gpiochip_irqchip_add_key() - adds an irqchip to a gpiochip
- * @gc: the gpiochip to add the irqchip to
- * @irqchip: the irqchip to add to the gpiochip
- * @first_irq: if not dynamically assigned, the base (first) IRQ to
- * allocate gpiochip irqs from
- * @handler: the irq handler to use (often a predefined irq core function)
- * @type: the default type for IRQs on this irqchip, pass IRQ_TYPE_NONE
- * to have the core avoid setting up any default type in the hardware.
- * @threaded: whether this irqchip uses a nested thread handler
- * @lock_key: lockdep class for IRQ lock
- * @request_key: lockdep class for IRQ request
- *
- * This function closely associates a certain irqchip with a certain
- * gpiochip, providing an irq domain to translate the local IRQs to
- * global irqs in the gpiolib core, and making sure that the gpiochip
- * is passed as chip data to all related functions. Driver callbacks
- * need to use gpiochip_get_data() to get their local state containers back
- * from the gpiochip passed as chip data. An irqdomain will be stored
- * in the gpiochip that shall be used by the driver to handle IRQ number
- * translation. The gpiochip will need to be initialized and registered
- * before calling this function.
- *
- * This function will handle two cell:ed simple IRQs and assumes all
- * the pins on the gpiochip can generate a unique IRQ. Everything else
- * need to be open coded.
- */
-int gpiochip_irqchip_add_key(struct gpio_chip *gc,
-			     struct irq_chip *irqchip,
-			     unsigned int first_irq,
-			     irq_flow_handler_t handler,
-			     unsigned int type,
-			     bool threaded,
-			     struct lock_class_key *lock_key,
-			     struct lock_class_key *request_key)
-{
-	struct device_node *of_node;
-
-	if (!gc || !irqchip)
-		return -EINVAL;
-
-	if (!gc->parent) {
-		chip_err(gc, "missing gpiochip .dev parent pointer\n");
-		return -EINVAL;
-	}
-	gc->irq.threaded = threaded;
-	of_node = gc->parent->of_node;
-#ifdef CONFIG_OF_GPIO
-	/*
-	 * If the gpiochip has an assigned OF node this takes precedence
-	 * FIXME: get rid of this and use gc->parent->of_node
-	 * everywhere
-	 */
-	if (gc->of_node)
-		of_node = gc->of_node;
-#endif
-	/*
-	 * Specifying a default trigger is a terrible idea if DT or ACPI is
-	 * used to configure the interrupts, as you may end-up with
-	 * conflicting triggers. Tell the user, and reset to NONE.
-	 */
-	if (WARN(of_node && type != IRQ_TYPE_NONE,
-		 "%pOF: Ignoring %d default trigger\n", of_node, type))
-		type = IRQ_TYPE_NONE;
-	if (has_acpi_companion(gc->parent) && type != IRQ_TYPE_NONE) {
-		acpi_handle_warn(ACPI_HANDLE(gc->parent),
-				 "Ignoring %d default trigger\n", type);
-		type = IRQ_TYPE_NONE;
-	}
-
-	gc->irq.chip = irqchip;
-	gc->irq.handler = handler;
-	gc->irq.default_type = type;
-	gc->to_irq = gpiochip_to_irq;
-	gc->irq.lock_key = lock_key;
-	gc->irq.request_key = request_key;
-	gc->irq.domain = irq_domain_add_simple(of_node,
-					gc->ngpio, first_irq,
-					&gpiochip_domain_ops, gc);
-	if (!gc->irq.domain) {
-		gc->irq.chip = NULL;
-		return -EINVAL;
-	}
-
-	gpiochip_set_irq_hooks(gc);
-
-	acpi_gpiochip_request_interrupts(gc);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(gpiochip_irqchip_add_key);
-
 /**
  * gpiochip_irqchip_add_domain() - adds an irqdomain to a gpiochip
  * @gc: the gpiochip to add the irqchip to
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index 4a7e295c3640..286de0520574 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -621,83 +621,12 @@ int gpiochip_irq_domain_activate(struct irq_domain *domain,
 void gpiochip_irq_domain_deactivate(struct irq_domain *domain,
 				    struct irq_data *data);
 
-void gpiochip_set_nested_irqchip(struct gpio_chip *gc,
-		struct irq_chip *irqchip,
-		unsigned int parent_irq);
-
-int gpiochip_irqchip_add_key(struct gpio_chip *gc,
-			     struct irq_chip *irqchip,
-			     unsigned int first_irq,
-			     irq_flow_handler_t handler,
-			     unsigned int type,
-			     bool threaded,
-			     struct lock_class_key *lock_key,
-			     struct lock_class_key *request_key);
-
 bool gpiochip_irqchip_irq_valid(const struct gpio_chip *gc,
 				unsigned int offset);
 
 int gpiochip_irqchip_add_domain(struct gpio_chip *gc,
 				struct irq_domain *domain);
 
-#ifdef CONFIG_LOCKDEP
-
-/*
- * Lockdep requires that each irqchip instance be created with a
- * unique key so as to avoid unnecessary warnings. This upfront
- * boilerplate static inlines provides such a key for each
- * unique instance.
- */
-static inline int gpiochip_irqchip_add(struct gpio_chip *gc,
-				       struct irq_chip *irqchip,
-				       unsigned int first_irq,
-				       irq_flow_handler_t handler,
-				       unsigned int type)
-{
-	static struct lock_class_key lock_key;
-	static struct lock_class_key request_key;
-
-	return gpiochip_irqchip_add_key(gc, irqchip, first_irq,
-					handler, type, false,
-					&lock_key, &request_key);
-}
-
-static inline int gpiochip_irqchip_add_nested(struct gpio_chip *gc,
-			  struct irq_chip *irqchip,
-			  unsigned int first_irq,
-			  irq_flow_handler_t handler,
-			  unsigned int type)
-{
-
-	static struct lock_class_key lock_key;
-	static struct lock_class_key request_key;
-
-	return gpiochip_irqchip_add_key(gc, irqchip, first_irq,
-					handler, type, true,
-					&lock_key, &request_key);
-}
-#else /* ! CONFIG_LOCKDEP */
-static inline int gpiochip_irqchip_add(struct gpio_chip *gc,
-				       struct irq_chip *irqchip,
-				       unsigned int first_irq,
-				       irq_flow_handler_t handler,
-				       unsigned int type)
-{
-	return gpiochip_irqchip_add_key(gc, irqchip, first_irq,
-					handler, type, false, NULL, NULL);
-}
-
-static inline int gpiochip_irqchip_add_nested(struct gpio_chip *gc,
-			  struct irq_chip *irqchip,
-			  unsigned int first_irq,
-			  irq_flow_handler_t handler,
-			  unsigned int type)
-{
-	return gpiochip_irqchip_add_key(gc, irqchip, first_irq,
-					handler, type, true, NULL, NULL);
-}
-#endif /* CONFIG_LOCKDEP */
-
 int gpiochip_generic_request(struct gpio_chip *gc, unsigned int offset);
 void gpiochip_generic_free(struct gpio_chip *gc, unsigned int offset);
 int gpiochip_generic_config(struct gpio_chip *gc, unsigned int offset,
-- 
cgit v1.2.3


From 6a6223ec7779dfdabb9c2567bb42079bc300cf27 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Tue, 27 Oct 2020 10:51:13 +0100
Subject: blk-mq: docs: add kernel-doc description for a new struct member

As reported by kernel-doc:
	./include/linux/blk-mq.h:267: warning: Function parameter or member 'active_queues_shared_sbitmap' not described in 'blk_mq_tag_set'

There is now a new member for struct blk_mq_tag_set. Add a
description for it, based on the commit that introduced it.

Fixes: f1b49fdc1c64 ("blk-mq: Record active_queues_shared_sbitmap per tag_set for when using shared sbitmap")
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Reviewed-by: John Garry <john.garry@huawei.com>
Link: https://lore.kernel.org/r/8e513153b83eefc05e358f51f2632b592c3f6772.1603791716.git.mchehab+huawei@kernel.org
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 include/linux/blk-mq.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index b23eeca4d677..794b2a33a2c3 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -235,6 +235,8 @@ enum hctx_type {
  * @flags:	   Zero or more BLK_MQ_F_* flags.
  * @driver_data:   Pointer to data owned by the block driver that created this
  *		   tag set.
+ * @active_queues_shared_sbitmap:
+ * 		   number of active request queues per tag set.
  * @__bitmap_tags: A shared tags sbitmap, used over all hctx's
  * @__breserved_tags:
  *		   A shared reserved tags sbitmap, used over all hctx's
-- 
cgit v1.2.3


From 89b422354409c275e898d26607201797cc05a932 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Tue, 27 Oct 2020 10:51:17 +0100
Subject: mm: pagemap.h: fix two kernel-doc markups

Changeset a8cf7f272b5a ("mm: add find_lock_head") renamed the
index parameter, but forgot to update the kernel-doc markups
accordingly.

Fixes: a8cf7f272b5a ("mm: add find_lock_head")
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Link: https://lore.kernel.org/r/dce89b296a4f5f9f8f798d5e76b6736c14a916ac.1603791716.git.mchehab+huawei@kernel.org
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 include/linux/pagemap.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index c77b7c31b2e4..e1e19c1f9ec9 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -344,9 +344,9 @@ static inline struct page *find_get_page_flags(struct address_space *mapping,
 /**
  * find_lock_page - locate, pin and lock a pagecache page
  * @mapping: the address_space to search
- * @offset: the page index
+ * @index: the page index
  *
- * Looks up the page cache entry at @mapping & @offset.  If there is a
+ * Looks up the page cache entry at @mapping & @index.  If there is a
  * page cache page, it is returned locked and with an increased
  * refcount.
  *
@@ -363,9 +363,9 @@ static inline struct page *find_lock_page(struct address_space *mapping,
 /**
  * find_lock_head - Locate, pin and lock a pagecache page.
  * @mapping: The address_space to search.
- * @offset: The page index.
+ * @index: The page index.
  *
- * Looks up the page cache entry at @mapping & @offset.  If there is a
+ * Looks up the page cache entry at @mapping & @index.  If there is a
  * page cache page, its head page is returned locked and with an increased
  * refcount.
  *
-- 
cgit v1.2.3


From e86c6569c588a01f20e7554cc245f8fae831957b Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Tue, 27 Oct 2020 10:51:18 +0100
Subject: net: phy: remove kernel-doc duplication

Sphinx 3 now checks for duplicated function declarations:

	.../Documentation/networking/kapi:143: ../include/linux/phy.h:163: WARNING: Duplicate C declaration, also defined in 'networking/kapi'.
	Declaration is 'unsigned int phy_supported_speeds (struct phy_device *phy, unsigned int *speeds, unsigned int size)'.
	.../Documentation/networking/kapi:143: ../include/linux/phy.h:1034: WARNING: Duplicate C declaration, also defined in 'networking/kapi'.
	Declaration is 'int phy_read_mmd (struct phy_device *phydev, int devad, u32 regnum)'.
	.../Documentation/networking/kapi:143: ../include/linux/phy.h:1076: WARNING: Duplicate C declaration, also defined in 'networking/kapi'.
	Declaration is 'int __phy_read_mmd (struct phy_device *phydev, int devad, u32 regnum)'.
	.../Documentation/networking/kapi:143: ../include/linux/phy.h:1088: WARNING: Duplicate C declaration, also defined in 'networking/kapi'.
	Declaration is 'int phy_write_mmd (struct phy_device *phydev, int devad, u32 regnum, u16 val)'.
	.../Documentation/networking/kapi:143: ../include/linux/phy.h:1100: WARNING: Duplicate C declaration, also defined in 'networking/kapi'.
	Declaration is 'int __phy_write_mmd (struct phy_device *phydev, int devad, u32 regnum, u16 val)'.

It turns that both the C and the H files have the same
kernel-doc markup for the same functions. Let's drop the
at the header file, keeping the one closer to the code.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/75e9a357f9a716833d2094b04898754876365e68.1603791716.git.mchehab+huawei@kernel.org
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 include/linux/phy.h | 40 +++++-----------------------------------
 1 file changed, 5 insertions(+), 35 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/phy.h b/include/linux/phy.h
index eb3cb1a98b45..56563e5e0dc7 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -147,16 +147,8 @@ typedef enum {
 	PHY_INTERFACE_MODE_MAX,
 } phy_interface_t;
 
-/**
+/*
  * phy_supported_speeds - return all speeds currently supported by a PHY device
- * @phy: The PHY device to return supported speeds of.
- * @speeds: buffer to store supported speeds in.
- * @size: size of speeds buffer.
- *
- * Description: Returns the number of supported speeds, and fills
- * the speeds buffer with the supported speeds. If speeds buffer is
- * too small to contain all currently supported speeds, will return as
- * many speeds as can fit.
  */
 unsigned int phy_supported_speeds(struct phy_device *phy,
 				      unsigned int *speeds,
@@ -1022,14 +1014,9 @@ static inline int __phy_modify_changed(struct phy_device *phydev, u32 regnum,
 					regnum, mask, set);
 }
 
-/**
+/*
  * phy_read_mmd - Convenience function for reading a register
  * from an MMD on a given PHY.
- * @phydev: The phy_device struct
- * @devad: The MMD to read from
- * @regnum: The register on the MMD to read
- *
- * Same rules as for phy_read();
  */
 int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum);
 
@@ -1064,38 +1051,21 @@ int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum);
 	__ret; \
 })
 
-/**
+/*
  * __phy_read_mmd - Convenience function for reading a register
  * from an MMD on a given PHY.
- * @phydev: The phy_device struct
- * @devad: The MMD to read from
- * @regnum: The register on the MMD to read
- *
- * Same rules as for __phy_read();
  */
 int __phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum);
 
-/**
+/*
  * phy_write_mmd - Convenience function for writing a register
  * on an MMD on a given PHY.
- * @phydev: The phy_device struct
- * @devad: The MMD to write to
- * @regnum: The register on the MMD to read
- * @val: value to write to @regnum
- *
- * Same rules as for phy_write();
  */
 int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val);
 
-/**
+/*
  * __phy_write_mmd - Convenience function for writing a register
  * on an MMD on a given PHY.
- * @phydev: The phy_device struct
- * @devad: The MMD to write to
- * @regnum: The register on the MMD to read
- * @val: value to write to @regnum
- *
- * Same rules as for __phy_write();
  */
 int __phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val);
 
-- 
cgit v1.2.3


From cf38cc9f1e71151f22584c40357afaab6609384b Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Tue, 27 Oct 2020 10:51:23 +0100
Subject: locking/refcount: move kernel-doc markups to the proper place

Changeset a435b9a14356 ("locking/refcount: Provide __refcount API to obtain the old value")
added a set of functions starting with __ that have a new
parameter, adding a series of new warnings:

	$ ./scripts/kernel-doc -none include/linux/refcount.h
	include/linux/refcount.h:169: warning: Function parameter or member 'oldp' not described in '__refcount_add_not_zero'
	include/linux/refcount.h:208: warning: Function parameter or member 'oldp' not described in '__refcount_add'
	include/linux/refcount.h:239: warning: Function parameter or member 'oldp' not described in '__refcount_inc_not_zero'
	include/linux/refcount.h:261: warning: Function parameter or member 'oldp' not described in '__refcount_inc'
	include/linux/refcount.h:291: warning: Function parameter or member 'oldp' not described in '__refcount_sub_and_test'
	include/linux/refcount.h:327: warning: Function parameter or member 'oldp' not described in '__refcount_dec_and_test'
	include/linux/refcount.h:347: warning: Function parameter or member 'oldp' not described in '__refcount_dec'

The issue is that the kernel-doc markups are now misplaced,
as they should be added just before the functions.

So, move the kernel-doc markups to the proper places,
in order to drop the warnings.

It should be noticed that git show produces a crappy output,
for this patch without "--patience" flag.

Fixes: a435b9a14356 ("locking/refcount: Provide __refcount API to obtain the old value")
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Link: https://lore.kernel.org/r/7985c31d1ace591bc5e1faa05c367f1295b78afd.1603791716.git.mchehab+huawei@kernel.org
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 include/linux/refcount.h | 130 +++++++++++++++++++++++------------------------
 1 file changed, 65 insertions(+), 65 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/refcount.h b/include/linux/refcount.h
index 7fabb1af18e0..497990c69b0b 100644
--- a/include/linux/refcount.h
+++ b/include/linux/refcount.h
@@ -147,24 +147,6 @@ static inline unsigned int refcount_read(const refcount_t *r)
 	return atomic_read(&r->refs);
 }
 
-/**
- * refcount_add_not_zero - add a value to a refcount unless it is 0
- * @i: the value to add to the refcount
- * @r: the refcount
- *
- * Will saturate at REFCOUNT_SATURATED and WARN.
- *
- * Provides no memory ordering, it is assumed the caller has guaranteed the
- * object memory to be stable (RCU, etc.). It does provide a control dependency
- * and thereby orders future stores. See the comment on top.
- *
- * Use of this function is not recommended for the normal reference counting
- * use case in which references are taken and released one at a time.  In these
- * cases, refcount_inc(), or one of its variants, should instead be used to
- * increment a reference count.
- *
- * Return: false if the passed refcount is 0, true otherwise
- */
 static inline __must_check bool __refcount_add_not_zero(int i, refcount_t *r, int *oldp)
 {
 	int old = refcount_read(r);
@@ -183,17 +165,12 @@ static inline __must_check bool __refcount_add_not_zero(int i, refcount_t *r, in
 	return old;
 }
 
-static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r)
-{
-	return __refcount_add_not_zero(i, r, NULL);
-}
-
 /**
- * refcount_add - add a value to a refcount
+ * refcount_add_not_zero - add a value to a refcount unless it is 0
  * @i: the value to add to the refcount
  * @r: the refcount
  *
- * Similar to atomic_add(), but will saturate at REFCOUNT_SATURATED and WARN.
+ * Will saturate at REFCOUNT_SATURATED and WARN.
  *
  * Provides no memory ordering, it is assumed the caller has guaranteed the
  * object memory to be stable (RCU, etc.). It does provide a control dependency
@@ -203,7 +180,14 @@ static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r)
  * use case in which references are taken and released one at a time.  In these
  * cases, refcount_inc(), or one of its variants, should instead be used to
  * increment a reference count.
+ *
+ * Return: false if the passed refcount is 0, true otherwise
  */
+static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r)
+{
+	return __refcount_add_not_zero(i, r, NULL);
+}
+
 static inline void __refcount_add(int i, refcount_t *r, int *oldp)
 {
 	int old = atomic_fetch_add_relaxed(i, &r->refs);
@@ -217,11 +201,32 @@ static inline void __refcount_add(int i, refcount_t *r, int *oldp)
 		refcount_warn_saturate(r, REFCOUNT_ADD_OVF);
 }
 
+/**
+ * refcount_add - add a value to a refcount
+ * @i: the value to add to the refcount
+ * @r: the refcount
+ *
+ * Similar to atomic_add(), but will saturate at REFCOUNT_SATURATED and WARN.
+ *
+ * Provides no memory ordering, it is assumed the caller has guaranteed the
+ * object memory to be stable (RCU, etc.). It does provide a control dependency
+ * and thereby orders future stores. See the comment on top.
+ *
+ * Use of this function is not recommended for the normal reference counting
+ * use case in which references are taken and released one at a time.  In these
+ * cases, refcount_inc(), or one of its variants, should instead be used to
+ * increment a reference count.
+ */
 static inline void refcount_add(int i, refcount_t *r)
 {
 	__refcount_add(i, r, NULL);
 }
 
+static inline __must_check bool __refcount_inc_not_zero(refcount_t *r, int *oldp)
+{
+	return __refcount_add_not_zero(1, r, oldp);
+}
+
 /**
  * refcount_inc_not_zero - increment a refcount unless it is 0
  * @r: the refcount to increment
@@ -235,14 +240,14 @@ static inline void refcount_add(int i, refcount_t *r)
  *
  * Return: true if the increment was successful, false otherwise
  */
-static inline __must_check bool __refcount_inc_not_zero(refcount_t *r, int *oldp)
+static inline __must_check bool refcount_inc_not_zero(refcount_t *r)
 {
-	return __refcount_add_not_zero(1, r, oldp);
+	return __refcount_inc_not_zero(r, NULL);
 }
 
-static inline __must_check bool refcount_inc_not_zero(refcount_t *r)
+static inline void __refcount_inc(refcount_t *r, int *oldp)
 {
-	return __refcount_inc_not_zero(r, NULL);
+	__refcount_add(1, r, oldp);
 }
 
 /**
@@ -257,14 +262,27 @@ static inline __must_check bool refcount_inc_not_zero(refcount_t *r)
  * Will WARN if the refcount is 0, as this represents a possible use-after-free
  * condition.
  */
-static inline void __refcount_inc(refcount_t *r, int *oldp)
+static inline void refcount_inc(refcount_t *r)
 {
-	__refcount_add(1, r, oldp);
+	__refcount_inc(r, NULL);
 }
 
-static inline void refcount_inc(refcount_t *r)
+static inline __must_check bool __refcount_sub_and_test(int i, refcount_t *r, int *oldp)
 {
-	__refcount_inc(r, NULL);
+	int old = atomic_fetch_sub_release(i, &r->refs);
+
+	if (oldp)
+		*oldp = old;
+
+	if (old == i) {
+		smp_acquire__after_ctrl_dep();
+		return true;
+	}
+
+	if (unlikely(old < 0 || old - i < 0))
+		refcount_warn_saturate(r, REFCOUNT_SUB_UAF);
+
+	return false;
 }
 
 /**
@@ -287,27 +305,14 @@ static inline void refcount_inc(refcount_t *r)
  *
  * Return: true if the resulting refcount is 0, false otherwise
  */
-static inline __must_check bool __refcount_sub_and_test(int i, refcount_t *r, int *oldp)
+static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r)
 {
-	int old = atomic_fetch_sub_release(i, &r->refs);
-
-	if (oldp)
-		*oldp = old;
-
-	if (old == i) {
-		smp_acquire__after_ctrl_dep();
-		return true;
-	}
-
-	if (unlikely(old < 0 || old - i < 0))
-		refcount_warn_saturate(r, REFCOUNT_SUB_UAF);
-
-	return false;
+	return __refcount_sub_and_test(i, r, NULL);
 }
 
-static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r)
+static inline __must_check bool __refcount_dec_and_test(refcount_t *r, int *oldp)
 {
-	return __refcount_sub_and_test(i, r, NULL);
+	return __refcount_sub_and_test(1, r, oldp);
 }
 
 /**
@@ -323,26 +328,11 @@ static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r)
  *
  * Return: true if the resulting refcount is 0, false otherwise
  */
-static inline __must_check bool __refcount_dec_and_test(refcount_t *r, int *oldp)
-{
-	return __refcount_sub_and_test(1, r, oldp);
-}
-
 static inline __must_check bool refcount_dec_and_test(refcount_t *r)
 {
 	return __refcount_dec_and_test(r, NULL);
 }
 
-/**
- * refcount_dec - decrement a refcount
- * @r: the refcount
- *
- * Similar to atomic_dec(), it will WARN on underflow and fail to decrement
- * when saturated at REFCOUNT_SATURATED.
- *
- * Provides release memory ordering, such that prior loads and stores are done
- * before.
- */
 static inline void __refcount_dec(refcount_t *r, int *oldp)
 {
 	int old = atomic_fetch_sub_release(1, &r->refs);
@@ -354,6 +344,16 @@ static inline void __refcount_dec(refcount_t *r, int *oldp)
 		refcount_warn_saturate(r, REFCOUNT_DEC_LEAK);
 }
 
+/**
+ * refcount_dec - decrement a refcount
+ * @r: the refcount
+ *
+ * Similar to atomic_dec(), it will WARN on underflow and fail to decrement
+ * when saturated at REFCOUNT_SATURATED.
+ *
+ * Provides release memory ordering, such that prior loads and stores are done
+ * before.
+ */
 static inline void refcount_dec(refcount_t *r)
 {
 	__refcount_dec(r, NULL);
-- 
cgit v1.2.3


From e029c5f2798720b463e8df0e184a4d1036311b43 Mon Sep 17 00:00:00 2001
From: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Date: Mon, 26 Oct 2020 21:49:14 -0700
Subject: ext4: make num of fast commit blocks configurable

This patch reserves a field in the jbd2 superblock for number of fast
commit blocks. When this value is non-zero, Ext4 uses this field to
set the number of fast commit blocks.

Fixes: 6866d7b3f2bb ("ext4/jbd2: add fast commit initialization")
Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Link: https://lore.kernel.org/r/20201027044915.2553163-2-harshadshirwadkar@gmail.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/fast_commit.c | 12 +++++++++++-
 include/linux/jbd2.h  |  5 ++++-
 2 files changed, 15 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index 1d72f8f13a05..dd7931400474 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -2077,6 +2077,8 @@ static int ext4_fc_replay(journal_t *journal, struct buffer_head *bh,
 
 void ext4_fc_init(struct super_block *sb, journal_t *journal)
 {
+	int num_fc_blocks;
+
 	/*
 	 * We set replay callback even if fast commit disabled because we may
 	 * could still have fast commit blocks that need to be replayed even if
@@ -2086,7 +2088,15 @@ void ext4_fc_init(struct super_block *sb, journal_t *journal)
 	if (!test_opt2(sb, JOURNAL_FAST_COMMIT))
 		return;
 	journal->j_fc_cleanup_callback = ext4_fc_cleanup;
-	if (jbd2_fc_init(journal, EXT4_NUM_FC_BLKS)) {
+	if (!buffer_uptodate(journal->j_sb_buffer)
+		&& ext4_read_bh_lock(journal->j_sb_buffer, REQ_META | REQ_PRIO,
+					true)) {
+		ext4_msg(sb, KERN_ERR, "I/O error on journal");
+		return;
+	}
+	num_fc_blocks = be32_to_cpu(journal->j_superblock->s_num_fc_blks);
+	if (jbd2_fc_init(journal, num_fc_blocks ? num_fc_blocks :
+					EXT4_NUM_FC_BLKS)) {
 		pr_warn("Error while enabling fast commits, turning off.");
 		ext4_clear_feature_fast_commit(sb);
 	}
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index fb3d71ad6eea..7e88bbc16ffb 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -263,7 +263,10 @@ typedef struct journal_superblock_s
 /* 0x0050 */
 	__u8	s_checksum_type;	/* checksum type */
 	__u8	s_padding2[3];
-	__u32	s_padding[42];
+/* 0x0054 */
+	__be32	s_num_fc_blks;		/* Number of fast commit blocks */
+/* 0x0058 */
+	__u32	s_padding[41];
 	__be32	s_checksum;		/* crc32c(superblock) */
 
 /* 0x0100 */
-- 
cgit v1.2.3


From ea4b01d9b81f5f381fc6832bc31046878a2d1a5d Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Tue, 27 Oct 2020 10:51:27 +0100
Subject: jbd2: fix a kernel-doc markup

The kernel-doc markup that documents _fc_replay_callback is
missing an asterisk, causing this warning:

	../include/linux/jbd2.h:1271: warning: Function parameter or member 'j_fc_replay_callback' not described in 'journal_s'

When building the docs.

Fixes: 609f928af48f ("jbd2: fast commit recovery path")
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Link: https://lore.kernel.org/r/6055927ada2015b55b413cdd2670533bdc9a8da2.1603791716.git.mchehab+huawei@kernel.org
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 include/linux/jbd2.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 7e88bbc16ffb..1d5566af48ac 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1256,7 +1256,7 @@ struct journal_s
 	 */
 	void (*j_fc_cleanup_callback)(struct journal_s *journal, int);
 
-	/*
+	/**
 	 * @j_fc_replay_callback:
 	 *
 	 * File-system specific function that performs replay of a fast
-- 
cgit v1.2.3


From 80ade22c06ca115b81dd168e99479c8e09843513 Mon Sep 17 00:00:00 2001
From: Sudeep Dutt <sudeep.dutt@intel.com>
Date: Tue, 27 Oct 2020 20:14:15 -0700
Subject: misc: mic: remove the MIC drivers

This patch removes the MIC drivers from the kernel tree
since the corresponding devices have been discontinued.

Removing the dma and char-misc changes in one patch and
merging via the char-misc tree is best to avoid any
potential build breakage.

Cc: Nikhil Rao <nikhil.rao@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: Sudeep Dutt <sudeep.dutt@intel.com>
Acked-By: Vinod Koul <vkoul@kernel.org>
Reviewed-by: Sherry Sun <sherry.sun@nxp.com>
Link: https://lore.kernel.org/r/8c1443136563de34699d2c084df478181c205db4.1603854416.git.sudeep.dutt@intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/misc-devices/mic/index.rst         |   16 -
 Documentation/misc-devices/mic/mic_overview.rst  |   85 -
 Documentation/misc-devices/mic/scif_overview.rst |  108 --
 MAINTAINERS                                      |   16 -
 drivers/dma/Kconfig                              |   18 -
 drivers/dma/Makefile                             |    1 -
 drivers/dma/mic_x100_dma.c                       |  770 ---------
 drivers/dma/mic_x100_dma.h                       |  275 ---
 drivers/misc/Kconfig                             |    1 -
 drivers/misc/Makefile                            |    1 -
 drivers/misc/mic/Kconfig                         |  141 --
 drivers/misc/mic/Makefile                        |   12 -
 drivers/misc/mic/bus/Makefile                    |    9 -
 drivers/misc/mic/bus/cosm_bus.c                  |  130 --
 drivers/misc/mic/bus/cosm_bus.h                  |  125 --
 drivers/misc/mic/bus/mic_bus.c                   |  194 ---
 drivers/misc/mic/bus/scif_bus.c                  |  201 ---
 drivers/misc/mic/bus/scif_bus.h                  |  125 --
 drivers/misc/mic/bus/vop_bus.c                   |  194 ---
 drivers/misc/mic/bus/vop_bus.h                   |  129 --
 drivers/misc/mic/card/Makefile                   |   11 -
 drivers/misc/mic/card/mic_debugfs.c              |   85 -
 drivers/misc/mic/card/mic_device.c               |  417 -----
 drivers/misc/mic/card/mic_device.h               |  137 --
 drivers/misc/mic/card/mic_x100.c                 |  347 ----
 drivers/misc/mic/card/mic_x100.h                 |   37 -
 drivers/misc/mic/common/mic_dev.h                |   55 -
 drivers/misc/mic/cosm/Makefile                   |   11 -
 drivers/misc/mic/cosm/cosm_debugfs.c             |  116 --
 drivers/misc/mic/cosm/cosm_main.c                |  382 -----
 drivers/misc/mic/cosm/cosm_main.h                |   61 -
 drivers/misc/mic/cosm/cosm_scif_server.c         |  399 -----
 drivers/misc/mic/cosm/cosm_sysfs.c               |  449 -----
 drivers/misc/mic/cosm_client/Makefile            |    8 -
 drivers/misc/mic/cosm_client/cosm_scif_client.c  |  269 ---
 drivers/misc/mic/host/Makefile                   |   12 -
 drivers/misc/mic/host/mic_boot.c                 |  588 -------
 drivers/misc/mic/host/mic_debugfs.c              |  149 --
 drivers/misc/mic/host/mic_device.h               |  157 --
 drivers/misc/mic/host/mic_intr.c                 |  635 -------
 drivers/misc/mic/host/mic_intr.h                 |  137 --
 drivers/misc/mic/host/mic_main.c                 |  335 ----
 drivers/misc/mic/host/mic_smpt.c                 |  427 -----
 drivers/misc/mic/host/mic_smpt.h                 |   87 -
 drivers/misc/mic/host/mic_x100.c                 |  585 -------
 drivers/misc/mic/host/mic_x100.h                 |   77 -
 drivers/misc/mic/scif/Makefile                   |   21 -
 drivers/misc/mic/scif/scif_api.c                 | 1485 -----------------
 drivers/misc/mic/scif/scif_debugfs.c             |  116 --
 drivers/misc/mic/scif/scif_dma.c                 | 1940 ----------------------
 drivers/misc/mic/scif/scif_epd.c                 |  357 ----
 drivers/misc/mic/scif/scif_epd.h                 |  200 ---
 drivers/misc/mic/scif/scif_fd.c                  |  462 ------
 drivers/misc/mic/scif/scif_fence.c               |  783 ---------
 drivers/misc/mic/scif/scif_main.c                |  351 ----
 drivers/misc/mic/scif/scif_main.h                |  274 ---
 drivers/misc/mic/scif/scif_map.h                 |  127 --
 drivers/misc/mic/scif/scif_mmap.c                |  690 --------
 drivers/misc/mic/scif/scif_nm.c                  |  229 ---
 drivers/misc/mic/scif/scif_nodeqp.c              | 1349 ---------------
 drivers/misc/mic/scif/scif_nodeqp.h              |  221 ---
 drivers/misc/mic/scif/scif_peer_bus.c            |  175 --
 drivers/misc/mic/scif/scif_peer_bus.h            |   23 -
 drivers/misc/mic/scif/scif_ports.c               |  116 --
 drivers/misc/mic/scif/scif_rb.c                  |  240 ---
 drivers/misc/mic/scif/scif_rb.h                  |  100 --
 drivers/misc/mic/scif/scif_rma.c                 | 1760 --------------------
 drivers/misc/mic/scif/scif_rma.h                 |  477 ------
 drivers/misc/mic/scif/scif_rma_list.c            |  282 ----
 drivers/misc/mic/scif/scif_rma_list.h            |   48 -
 drivers/misc/mic/vop/Makefile                    |   10 -
 drivers/misc/mic/vop/vop_debugfs.c               |  184 --
 drivers/misc/mic/vop/vop_main.c                  |  784 ---------
 drivers/misc/mic/vop/vop_main.h                  |  158 --
 drivers/misc/mic/vop/vop_vringh.c                | 1166 -------------
 include/linux/mic_bus.h                          |  100 --
 include/linux/scif.h                             | 1339 ---------------
 include/uapi/linux/mic_common.h                  |  235 ---
 include/uapi/linux/mic_ioctl.h                   |   77 -
 samples/mic/mpssd/.gitignore                     |    2 -
 samples/mic/mpssd/Makefile                       |   28 -
 samples/mic/mpssd/micctrl                        |  162 --
 samples/mic/mpssd/mpss                           |  189 ---
 samples/mic/mpssd/mpssd.c                        | 1815 --------------------
 samples/mic/mpssd/mpssd.h                        |   89 -
 samples/mic/mpssd/sysfs.c                        |   91 -
 86 files changed, 26779 deletions(-)
 delete mode 100644 Documentation/misc-devices/mic/index.rst
 delete mode 100644 Documentation/misc-devices/mic/mic_overview.rst
 delete mode 100644 Documentation/misc-devices/mic/scif_overview.rst
 delete mode 100644 drivers/dma/mic_x100_dma.c
 delete mode 100644 drivers/dma/mic_x100_dma.h
 delete mode 100644 drivers/misc/mic/Kconfig
 delete mode 100644 drivers/misc/mic/Makefile
 delete mode 100644 drivers/misc/mic/bus/Makefile
 delete mode 100644 drivers/misc/mic/bus/cosm_bus.c
 delete mode 100644 drivers/misc/mic/bus/cosm_bus.h
 delete mode 100644 drivers/misc/mic/bus/mic_bus.c
 delete mode 100644 drivers/misc/mic/bus/scif_bus.c
 delete mode 100644 drivers/misc/mic/bus/scif_bus.h
 delete mode 100644 drivers/misc/mic/bus/vop_bus.c
 delete mode 100644 drivers/misc/mic/bus/vop_bus.h
 delete mode 100644 drivers/misc/mic/card/Makefile
 delete mode 100644 drivers/misc/mic/card/mic_debugfs.c
 delete mode 100644 drivers/misc/mic/card/mic_device.c
 delete mode 100644 drivers/misc/mic/card/mic_device.h
 delete mode 100644 drivers/misc/mic/card/mic_x100.c
 delete mode 100644 drivers/misc/mic/card/mic_x100.h
 delete mode 100644 drivers/misc/mic/common/mic_dev.h
 delete mode 100644 drivers/misc/mic/cosm/Makefile
 delete mode 100644 drivers/misc/mic/cosm/cosm_debugfs.c
 delete mode 100644 drivers/misc/mic/cosm/cosm_main.c
 delete mode 100644 drivers/misc/mic/cosm/cosm_main.h
 delete mode 100644 drivers/misc/mic/cosm/cosm_scif_server.c
 delete mode 100644 drivers/misc/mic/cosm/cosm_sysfs.c
 delete mode 100644 drivers/misc/mic/cosm_client/Makefile
 delete mode 100644 drivers/misc/mic/cosm_client/cosm_scif_client.c
 delete mode 100644 drivers/misc/mic/host/Makefile
 delete mode 100644 drivers/misc/mic/host/mic_boot.c
 delete mode 100644 drivers/misc/mic/host/mic_debugfs.c
 delete mode 100644 drivers/misc/mic/host/mic_device.h
 delete mode 100644 drivers/misc/mic/host/mic_intr.c
 delete mode 100644 drivers/misc/mic/host/mic_intr.h
 delete mode 100644 drivers/misc/mic/host/mic_main.c
 delete mode 100644 drivers/misc/mic/host/mic_smpt.c
 delete mode 100644 drivers/misc/mic/host/mic_smpt.h
 delete mode 100644 drivers/misc/mic/host/mic_x100.c
 delete mode 100644 drivers/misc/mic/host/mic_x100.h
 delete mode 100644 drivers/misc/mic/scif/Makefile
 delete mode 100644 drivers/misc/mic/scif/scif_api.c
 delete mode 100644 drivers/misc/mic/scif/scif_debugfs.c
 delete mode 100644 drivers/misc/mic/scif/scif_dma.c
 delete mode 100644 drivers/misc/mic/scif/scif_epd.c
 delete mode 100644 drivers/misc/mic/scif/scif_epd.h
 delete mode 100644 drivers/misc/mic/scif/scif_fd.c
 delete mode 100644 drivers/misc/mic/scif/scif_fence.c
 delete mode 100644 drivers/misc/mic/scif/scif_main.c
 delete mode 100644 drivers/misc/mic/scif/scif_main.h
 delete mode 100644 drivers/misc/mic/scif/scif_map.h
 delete mode 100644 drivers/misc/mic/scif/scif_mmap.c
 delete mode 100644 drivers/misc/mic/scif/scif_nm.c
 delete mode 100644 drivers/misc/mic/scif/scif_nodeqp.c
 delete mode 100644 drivers/misc/mic/scif/scif_nodeqp.h
 delete mode 100644 drivers/misc/mic/scif/scif_peer_bus.c
 delete mode 100644 drivers/misc/mic/scif/scif_peer_bus.h
 delete mode 100644 drivers/misc/mic/scif/scif_ports.c
 delete mode 100644 drivers/misc/mic/scif/scif_rb.c
 delete mode 100644 drivers/misc/mic/scif/scif_rb.h
 delete mode 100644 drivers/misc/mic/scif/scif_rma.c
 delete mode 100644 drivers/misc/mic/scif/scif_rma.h
 delete mode 100644 drivers/misc/mic/scif/scif_rma_list.c
 delete mode 100644 drivers/misc/mic/scif/scif_rma_list.h
 delete mode 100644 drivers/misc/mic/vop/Makefile
 delete mode 100644 drivers/misc/mic/vop/vop_debugfs.c
 delete mode 100644 drivers/misc/mic/vop/vop_main.c
 delete mode 100644 drivers/misc/mic/vop/vop_main.h
 delete mode 100644 drivers/misc/mic/vop/vop_vringh.c
 delete mode 100644 include/linux/mic_bus.h
 delete mode 100644 include/linux/scif.h
 delete mode 100644 include/uapi/linux/mic_common.h
 delete mode 100644 include/uapi/linux/mic_ioctl.h
 delete mode 100644 samples/mic/mpssd/.gitignore
 delete mode 100644 samples/mic/mpssd/Makefile
 delete mode 100755 samples/mic/mpssd/micctrl
 delete mode 100755 samples/mic/mpssd/mpss
 delete mode 100644 samples/mic/mpssd/mpssd.c
 delete mode 100644 samples/mic/mpssd/mpssd.h
 delete mode 100644 samples/mic/mpssd/sysfs.c

(limited to 'include/linux')

diff --git a/Documentation/misc-devices/mic/index.rst b/Documentation/misc-devices/mic/index.rst
deleted file mode 100644
index 3a8d06367ef1..000000000000
--- a/Documentation/misc-devices/mic/index.rst
+++ /dev/null
@@ -1,16 +0,0 @@
-=============================================
-Intel Many Integrated Core (MIC) architecture
-=============================================
-
-.. toctree::
-    :maxdepth: 1
-
-    mic_overview
-    scif_overview
-
-.. only::  subproject and html
-
-   Indices
-   =======
-
-   * :ref:`genindex`
diff --git a/Documentation/misc-devices/mic/mic_overview.rst b/Documentation/misc-devices/mic/mic_overview.rst
deleted file mode 100644
index 17d956bdaf7c..000000000000
--- a/Documentation/misc-devices/mic/mic_overview.rst
+++ /dev/null
@@ -1,85 +0,0 @@
-======================================================
-Intel Many Integrated Core (MIC) architecture overview
-======================================================
-
-An Intel MIC X100 device is a PCIe form factor add-in coprocessor
-card based on the Intel Many Integrated Core (MIC) architecture
-that runs a Linux OS. It is a PCIe endpoint in a platform and therefore
-implements the three required standard address spaces i.e. configuration,
-memory and I/O. The host OS loads a device driver as is typical for
-PCIe devices. The card itself runs a bootstrap after reset that
-transfers control to the card OS downloaded from the host driver. The
-host driver supports OSPM suspend and resume operations. It shuts down
-the card during suspend and reboots the card OS during resume.
-The card OS as shipped by Intel is a Linux kernel with modifications
-for the X100 devices.
-
-Since it is a PCIe card, it does not have the ability to host hardware
-devices for networking, storage and console. We provide these devices
-on X100 coprocessors thus enabling a self-bootable equivalent
-environment for applications. A key benefit of our solution is that it
-leverages the standard virtio framework for network, disk and console
-devices, though in our case the virtio framework is used across a PCIe
-bus. A Virtio Over PCIe (VOP) driver allows creating user space
-backends or devices on the host which are used to probe virtio drivers
-for these devices on the MIC card. The existing VRINGH infrastructure
-in the kernel is used to access virtio rings from the host. The card
-VOP driver allows card virtio drivers to communicate with their user
-space backends on the host via a device page. Ring 3 apps on the host
-can add, remove and configure virtio devices. A thin MIC specific
-virtio_config_ops is implemented which is borrowed heavily from
-previous similar implementations in lguest and s390.
-
-MIC PCIe card has a dma controller with 8 channels. These channels are
-shared between the host s/w and the card s/w. 0 to 3 are used by host
-and 4 to 7 by card. As the dma device doesn't show up as PCIe device,
-a virtual bus called mic bus is created and virtual dma devices are
-created on it by the host/card drivers. On host the channels are private
-and used only by the host driver to transfer data for the virtio devices.
-
-The Symmetric Communication Interface (SCIF (pronounced as skiff)) is a
-low level communications API across PCIe currently implemented for MIC.
-More details are available at scif_overview.txt.
-
-The Coprocessor State Management (COSM) driver on the host allows for
-boot, shutdown and reset of Intel MIC devices. It communicates with a COSM
-"client" driver on the MIC cards over SCIF to perform these functions.
-
-Here is a block diagram of the various components described above. The
-virtio backends are situated on the host rather than the card given better
-single threaded performance for the host compared to MIC, the ability of
-the host to initiate DMA's to/from the card using the MIC DMA engine and
-the fact that the virtio block storage backend can only be on the host::
-
-               +----------+           |             +----------+
-               | Card OS  |           |             | Host OS  |
-               +----------+           |             +----------+
-                                      |
-        +-------+ +--------+ +------+ | +---------+  +--------+ +--------+
-        | Virtio| |Virtio  | |Virtio| | |Virtio   |  |Virtio  | |Virtio  |
-        | Net   | |Console | |Block | | |Net      |  |Console | |Block   |
-        | Driver| |Driver  | |Driver| | |backend  |  |backend | |backend |
-        +---+---+ +---+----+ +--+---+ | +---------+  +----+---+ +--------+
-            |         |         |     |      |            |         |
-            |         |         |     |User  |            |         |
-            |         |         |     |------|------------|--+------|-------
-            +---------+---------+     |Kernel                |
-                      |               |                      |
-  +---------+     +---+----+ +------+ | +------+ +------+ +--+---+  +-------+
-  |MIC DMA  |     |  VOP   | | SCIF | | | SCIF | | COSM | | VOP  |  |MIC DMA|
-  +---+-----+     +---+----+ +--+---+ | +--+---+ +--+---+ +------+  +----+--+
-      |               |         |     |    |        |                    |
-  +---+-----+     +---+----+ +--+---+ | +--+---+ +--+---+ +------+  +----+--+
-  |MIC      |     |  VOP   | |SCIF  | | |SCIF  | | COSM | | VOP  |  | MIC   |
-  |HW Bus   |     |  HW Bus| |HW Bus| | |HW Bus| | Bus  | |HW Bus|  |HW Bus |
-  +---------+     +--------+ +--+---+ | +--+---+ +------+ +------+  +-------+
-      |               |         |     |       |     |                    |
-      |   +-----------+--+      |     |       |    +---------------+     |
-      |   |Intel MIC     |      |     |       |    |Intel MIC      |     |
-      |   |Card Driver   |      |     |       |    |Host Driver    |     |
-      +---+--------------+------+     |       +----+---------------+-----+
-                 |                    |                   |
-             +-------------------------------------------------------------+
-             |                                                             |
-             |                    PCIe Bus                                 |
-             +-------------------------------------------------------------+
diff --git a/Documentation/misc-devices/mic/scif_overview.rst b/Documentation/misc-devices/mic/scif_overview.rst
deleted file mode 100644
index 4c8ad9e43706..000000000000
--- a/Documentation/misc-devices/mic/scif_overview.rst
+++ /dev/null
@@ -1,108 +0,0 @@
-========================================
-Symmetric Communication Interface (SCIF)
-========================================
-
-The Symmetric Communication Interface (SCIF (pronounced as skiff)) is a low
-level communications API across PCIe currently implemented for MIC. Currently
-SCIF provides inter-node communication within a single host platform, where a
-node is a MIC Coprocessor or Xeon based host. SCIF abstracts the details of
-communicating over the PCIe bus while providing an API that is symmetric
-across all the nodes in the PCIe network. An important design objective for SCIF
-is to deliver the maximum possible performance given the communication
-abilities of the hardware. SCIF has been used to implement an offload compiler
-runtime and OFED support for MPI implementations for MIC coprocessors.
-
-SCIF API Components
-===================
-
-The SCIF API has the following parts:
-
-1. Connection establishment using a client server model
-2. Byte stream messaging intended for short messages
-3. Node enumeration to determine online nodes
-4. Poll semantics for detection of incoming connections and messages
-5. Memory registration to pin down pages
-6. Remote memory mapping for low latency CPU accesses via mmap
-7. Remote DMA (RDMA) for high bandwidth DMA transfers
-8. Fence APIs for RDMA synchronization
-
-SCIF exposes the notion of a connection which can be used by peer processes on
-nodes in a SCIF PCIe "network" to share memory "windows" and to communicate. A
-process in a SCIF node initiates a SCIF connection to a peer process on a
-different node via a SCIF "endpoint". SCIF endpoints support messaging APIs
-which are similar to connection oriented socket APIs. Connected SCIF endpoints
-can also register local memory which is followed by data transfer using either
-DMA, CPU copies or remote memory mapping via mmap. SCIF supports both user and
-kernel mode clients which are functionally equivalent.
-
-SCIF Performance for MIC
-========================
-
-DMA bandwidth comparison between the TCP (over ethernet over PCIe) stack versus
-SCIF shows the performance advantages of SCIF for HPC applications and
-runtimes::
-
-             Comparison of TCP and SCIF based BW
-
-  Throughput (GB/sec)
-    8 +                                             PCIe Bandwidth ******
-      +                                                        TCP ######
-    7 +    **************************************             SCIF %%%%%%
-      |                       %%%%%%%%%%%%%%%%%%%
-    6 +                   %%%%
-      |                 %%
-      |               %%%
-    5 +              %%
-      |            %%
-    4 +           %%
-      |          %%
-    3 +         %%
-      |        %
-    2 +      %%
-      |     %%
-      |    %
-    1 +
-      +    ######################################
-    0 +++---+++--+--+-+--+--+-++-+--+-++-+--+-++-+-
-      1       10     100      1000   10000   100000
-                   Transfer Size (KBytes)
-
-SCIF allows memory sharing via mmap(..) between processes on different PCIe
-nodes and thus provides bare-metal PCIe latency. The round trip SCIF mmap
-latency from the host to an x100 MIC for an 8 byte message is 0.44 usecs.
-
-SCIF has a user space library which is a thin IOCTL wrapper providing a user
-space API similar to the kernel API in scif.h. The SCIF user space library
-is distributed @ https://software.intel.com/en-us/mic-developer
-
-Here is some pseudo code for an example of how two applications on two PCIe
-nodes would typically use the SCIF API::
-
-  Process A (on node A)			Process B (on node B)
-
-  /* get online node information */
-  scif_get_node_ids(..)			scif_get_node_ids(..)
-  scif_open(..)				scif_open(..)
-  scif_bind(..)				scif_bind(..)
-  scif_listen(..)
-  scif_accept(..)				scif_connect(..)
-  /* SCIF connection established */
-
-  /* Send and receive short messages */
-  scif_send(..)/scif_recv(..)		scif_send(..)/scif_recv(..)
-
-  /* Register memory */
-  scif_register(..)			scif_register(..)
-
-  /* RDMA */
-  scif_readfrom(..)/scif_writeto(..)	scif_readfrom(..)/scif_writeto(..)
-
-  /* Fence DMAs */
-  scif_fence_signal(..)			scif_fence_signal(..)
-
-  mmap(..)				mmap(..)
-
-  /* Access remote registered memory */
-
-  /* Close the endpoints */
-  scif_close(..)				scif_close(..)
diff --git a/MAINTAINERS b/MAINTAINERS
index e73636b75f29..9289a9b43a51 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8976,22 +8976,6 @@ S:	Supported
 W:	https://01.org/linux-acpi
 F:	drivers/platform/x86/intel_menlow.c
 
-INTEL MIC DRIVERS (mic)
-M:	Sudeep Dutt <sudeep.dutt@intel.com>
-M:	Ashutosh Dixit <ashutosh.dixit@intel.com>
-S:	Supported
-W:	https://github.com/sudeepdutt/mic
-W:	http://software.intel.com/en-us/mic-developer
-F:	Documentation/misc-devices/mic/
-F:	drivers/dma/mic_x100_dma.c
-F:	drivers/dma/mic_x100_dma.h
-F:	drivers/misc/mic/
-F:	include/linux/mic_bus.h
-F:	include/linux/scif.h
-F:	include/uapi/linux/mic_common.h
-F:	include/uapi/linux/mic_ioctl.h
-F:	include/uapi/linux/scif_ioctl.h
-
 INTEL P-Unit IPC DRIVER
 M:	Zha Qipeng <qipeng.zha@intel.com>
 L:	platform-driver-x86@vger.kernel.org
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 518a1437862a..90284ffda58a 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -318,24 +318,6 @@ config INTEL_IOP_ADMA
 	help
 	  Enable support for the Intel(R) IOP Series RAID engines.
 
-config INTEL_MIC_X100_DMA
-	tristate "Intel MIC X100 DMA Driver"
-	depends on 64BIT && X86 && INTEL_MIC_BUS
-	select DMA_ENGINE
-	help
-	  This enables DMA support for the Intel Many Integrated Core
-	  (MIC) family of PCIe form factor coprocessor X100 devices that
-	  run a 64 bit Linux OS. This driver will be used by both MIC
-	  host and card drivers.
-
-	  If you are building host kernel with a MIC device or a card
-	  kernel for a MIC device, then say M (recommended) or Y, else
-	  say N. If unsure say N.
-
-	  More information about the Intel MIC family as well as the Linux
-	  OS and tools for MIC to use with this driver are available from
-	  <http://software.intel.com/en-us/mic-developer>.
-
 config K3_DMA
 	tristate "Hisilicon K3 DMA support"
 	depends on ARCH_HI3xxx || ARCH_HISI || COMPILE_TEST
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index e60f81331d4c..948a8da05f8b 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -44,7 +44,6 @@ obj-$(CONFIG_INTEL_IDMA64) += idma64.o
 obj-$(CONFIG_INTEL_IOATDMA) += ioat/
 obj-$(CONFIG_INTEL_IDXD) += idxd/
 obj-$(CONFIG_INTEL_IOP_ADMA) += iop-adma.o
-obj-$(CONFIG_INTEL_MIC_X100_DMA) += mic_x100_dma.o
 obj-$(CONFIG_K3_DMA) += k3dma.o
 obj-$(CONFIG_LPC18XX_DMAMUX) += lpc18xx-dmamux.o
 obj-$(CONFIG_MILBEAUT_HDMAC) += milbeaut-hdmac.o
diff --git a/drivers/dma/mic_x100_dma.c b/drivers/dma/mic_x100_dma.c
deleted file mode 100644
index fea8608a7810..000000000000
--- a/drivers/dma/mic_x100_dma.c
+++ /dev/null
@@ -1,770 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel MIC X100 DMA Driver.
- *
- * Adapted from IOAT dma driver.
- */
-#include <linux/module.h>
-#include <linux/io.h>
-#include <linux/seq_file.h>
-#include <linux/vmalloc.h>
-
-#include "mic_x100_dma.h"
-
-#define MIC_DMA_MAX_XFER_SIZE_CARD  (1 * 1024 * 1024 -\
-				       MIC_DMA_ALIGN_BYTES)
-#define MIC_DMA_MAX_XFER_SIZE_HOST  (1 * 1024 * 1024 >> 1)
-#define MIC_DMA_DESC_TYPE_SHIFT	60
-#define MIC_DMA_MEMCPY_LEN_SHIFT 46
-#define MIC_DMA_STAT_INTR_SHIFT 59
-
-/* high-water mark for pushing dma descriptors */
-static int mic_dma_pending_level = 4;
-
-/* Status descriptor is used to write a 64 bit value to a memory location */
-enum mic_dma_desc_format_type {
-	MIC_DMA_MEMCPY = 1,
-	MIC_DMA_STATUS,
-};
-
-static inline u32 mic_dma_hw_ring_inc(u32 val)
-{
-	return (val + 1) % MIC_DMA_DESC_RX_SIZE;
-}
-
-static inline u32 mic_dma_hw_ring_dec(u32 val)
-{
-	return val ? val - 1 : MIC_DMA_DESC_RX_SIZE - 1;
-}
-
-static inline void mic_dma_hw_ring_inc_head(struct mic_dma_chan *ch)
-{
-	ch->head = mic_dma_hw_ring_inc(ch->head);
-}
-
-/* Prepare a memcpy desc */
-static inline void mic_dma_memcpy_desc(struct mic_dma_desc *desc,
-	dma_addr_t src_phys, dma_addr_t dst_phys, u64 size)
-{
-	u64 qw0, qw1;
-
-	qw0 = src_phys;
-	qw0 |= (size >> MIC_DMA_ALIGN_SHIFT) << MIC_DMA_MEMCPY_LEN_SHIFT;
-	qw1 = MIC_DMA_MEMCPY;
-	qw1 <<= MIC_DMA_DESC_TYPE_SHIFT;
-	qw1 |= dst_phys;
-	desc->qw0 = qw0;
-	desc->qw1 = qw1;
-}
-
-/* Prepare a status desc. with @data to be written at @dst_phys */
-static inline void mic_dma_prep_status_desc(struct mic_dma_desc *desc, u64 data,
-	dma_addr_t dst_phys, bool generate_intr)
-{
-	u64 qw0, qw1;
-
-	qw0 = data;
-	qw1 = (u64) MIC_DMA_STATUS << MIC_DMA_DESC_TYPE_SHIFT | dst_phys;
-	if (generate_intr)
-		qw1 |= (1ULL << MIC_DMA_STAT_INTR_SHIFT);
-	desc->qw0 = qw0;
-	desc->qw1 = qw1;
-}
-
-static void mic_dma_cleanup(struct mic_dma_chan *ch)
-{
-	struct dma_async_tx_descriptor *tx;
-	u32 tail;
-	u32 last_tail;
-
-	spin_lock(&ch->cleanup_lock);
-	tail = mic_dma_read_cmp_cnt(ch);
-	/*
-	 * This is the barrier pair for smp_wmb() in fn.
-	 * mic_dma_tx_submit_unlock. It's required so that we read the
-	 * updated cookie value from tx->cookie.
-	 */
-	smp_rmb();
-	for (last_tail = ch->last_tail; tail != last_tail;) {
-		tx = &ch->tx_array[last_tail];
-		if (tx->cookie) {
-			dma_cookie_complete(tx);
-			dmaengine_desc_get_callback_invoke(tx, NULL);
-			tx->callback = NULL;
-		}
-		last_tail = mic_dma_hw_ring_inc(last_tail);
-	}
-	/* finish all completion callbacks before incrementing tail */
-	smp_mb();
-	ch->last_tail = last_tail;
-	spin_unlock(&ch->cleanup_lock);
-}
-
-static u32 mic_dma_ring_count(u32 head, u32 tail)
-{
-	u32 count;
-
-	if (head >= tail)
-		count = (tail - 0) + (MIC_DMA_DESC_RX_SIZE - head);
-	else
-		count = tail - head;
-	return count - 1;
-}
-
-/* Returns the num. of free descriptors on success, -ENOMEM on failure */
-static int mic_dma_avail_desc_ring_space(struct mic_dma_chan *ch, int required)
-{
-	struct device *dev = mic_dma_ch_to_device(ch);
-	u32 count;
-
-	count = mic_dma_ring_count(ch->head, ch->last_tail);
-	if (count < required) {
-		mic_dma_cleanup(ch);
-		count = mic_dma_ring_count(ch->head, ch->last_tail);
-	}
-
-	if (count < required) {
-		dev_dbg(dev, "Not enough desc space");
-		dev_dbg(dev, "%s %d required=%u, avail=%u\n",
-			__func__, __LINE__, required, count);
-		return -ENOMEM;
-	} else {
-		return count;
-	}
-}
-
-/* Program memcpy descriptors into the descriptor ring and update s/w head ptr*/
-static int mic_dma_prog_memcpy_desc(struct mic_dma_chan *ch, dma_addr_t src,
-				    dma_addr_t dst, size_t len)
-{
-	size_t current_transfer_len;
-	size_t max_xfer_size = to_mic_dma_dev(ch)->max_xfer_size;
-	/* 3 is added to make sure we have enough space for status desc */
-	int num_desc = len / max_xfer_size + 3;
-	int ret;
-
-	if (len % max_xfer_size)
-		num_desc++;
-
-	ret = mic_dma_avail_desc_ring_space(ch, num_desc);
-	if (ret < 0)
-		return ret;
-	do {
-		current_transfer_len = min(len, max_xfer_size);
-		mic_dma_memcpy_desc(&ch->desc_ring[ch->head],
-				    src, dst, current_transfer_len);
-		mic_dma_hw_ring_inc_head(ch);
-		len -= current_transfer_len;
-		dst = dst + current_transfer_len;
-		src = src + current_transfer_len;
-	} while (len > 0);
-	return 0;
-}
-
-/* It's a h/w quirk and h/w needs 2 status descriptors for every status desc */
-static void mic_dma_prog_intr(struct mic_dma_chan *ch)
-{
-	mic_dma_prep_status_desc(&ch->desc_ring[ch->head], 0,
-				 ch->status_dest_micpa, false);
-	mic_dma_hw_ring_inc_head(ch);
-	mic_dma_prep_status_desc(&ch->desc_ring[ch->head], 0,
-				 ch->status_dest_micpa, true);
-	mic_dma_hw_ring_inc_head(ch);
-}
-
-/* Wrapper function to program memcpy descriptors/status descriptors */
-static int mic_dma_do_dma(struct mic_dma_chan *ch, int flags, dma_addr_t src,
-			  dma_addr_t dst, size_t len)
-{
-	if (len && -ENOMEM == mic_dma_prog_memcpy_desc(ch, src, dst, len)) {
-		return -ENOMEM;
-	} else {
-		/* 3 is the maximum number of status descriptors */
-		int ret = mic_dma_avail_desc_ring_space(ch, 3);
-
-		if (ret < 0)
-			return ret;
-	}
-
-	/* Above mic_dma_prog_memcpy_desc() makes sure we have enough space */
-	if (flags & DMA_PREP_FENCE) {
-		mic_dma_prep_status_desc(&ch->desc_ring[ch->head], 0,
-					 ch->status_dest_micpa, false);
-		mic_dma_hw_ring_inc_head(ch);
-	}
-
-	if (flags & DMA_PREP_INTERRUPT)
-		mic_dma_prog_intr(ch);
-
-	return 0;
-}
-
-static inline void mic_dma_issue_pending(struct dma_chan *ch)
-{
-	struct mic_dma_chan *mic_ch = to_mic_dma_chan(ch);
-
-	spin_lock(&mic_ch->issue_lock);
-	/*
-	 * Write to head triggers h/w to act on the descriptors.
-	 * On MIC, writing the same head value twice causes
-	 * a h/w error. On second write, h/w assumes we filled
-	 * the entire ring & overwrote some of the descriptors.
-	 */
-	if (mic_ch->issued == mic_ch->submitted)
-		goto out;
-	mic_ch->issued = mic_ch->submitted;
-	/*
-	 * make descriptor updates visible before advancing head,
-	 * this is purposefully not smp_wmb() since we are also
-	 * publishing the descriptor updates to a dma device
-	 */
-	wmb();
-	mic_dma_write_reg(mic_ch, MIC_DMA_REG_DHPR, mic_ch->issued);
-out:
-	spin_unlock(&mic_ch->issue_lock);
-}
-
-static inline void mic_dma_update_pending(struct mic_dma_chan *ch)
-{
-	if (mic_dma_ring_count(ch->issued, ch->submitted)
-			> mic_dma_pending_level)
-		mic_dma_issue_pending(&ch->api_ch);
-}
-
-static dma_cookie_t mic_dma_tx_submit_unlock(struct dma_async_tx_descriptor *tx)
-{
-	struct mic_dma_chan *mic_ch = to_mic_dma_chan(tx->chan);
-	dma_cookie_t cookie;
-
-	dma_cookie_assign(tx);
-	cookie = tx->cookie;
-	/*
-	 * We need an smp write barrier here because another CPU might see
-	 * an update to submitted and update h/w head even before we
-	 * assigned a cookie to this tx.
-	 */
-	smp_wmb();
-	mic_ch->submitted = mic_ch->head;
-	spin_unlock(&mic_ch->prep_lock);
-	mic_dma_update_pending(mic_ch);
-	return cookie;
-}
-
-static inline struct dma_async_tx_descriptor *
-allocate_tx(struct mic_dma_chan *ch)
-{
-	u32 idx = mic_dma_hw_ring_dec(ch->head);
-	struct dma_async_tx_descriptor *tx = &ch->tx_array[idx];
-
-	dma_async_tx_descriptor_init(tx, &ch->api_ch);
-	tx->tx_submit = mic_dma_tx_submit_unlock;
-	return tx;
-}
-
-/* Program a status descriptor with dst as address and value to be written */
-static struct dma_async_tx_descriptor *
-mic_dma_prep_status_lock(struct dma_chan *ch, dma_addr_t dst, u64 src_val,
-			 unsigned long flags)
-{
-	struct mic_dma_chan *mic_ch = to_mic_dma_chan(ch);
-	int result;
-
-	spin_lock(&mic_ch->prep_lock);
-	result = mic_dma_avail_desc_ring_space(mic_ch, 4);
-	if (result < 0)
-		goto error;
-	mic_dma_prep_status_desc(&mic_ch->desc_ring[mic_ch->head], src_val, dst,
-				 false);
-	mic_dma_hw_ring_inc_head(mic_ch);
-	result = mic_dma_do_dma(mic_ch, flags, 0, 0, 0);
-	if (result < 0)
-		goto error;
-
-	return allocate_tx(mic_ch);
-error:
-	dev_err(mic_dma_ch_to_device(mic_ch),
-		"Error enqueueing dma status descriptor, error=%d\n", result);
-	spin_unlock(&mic_ch->prep_lock);
-	return NULL;
-}
-
-/*
- * Prepare a memcpy descriptor to be added to the ring.
- * Note that the temporary descriptor adds an extra overhead of copying the
- * descriptor to ring. So, we copy directly to the descriptor ring
- */
-static struct dma_async_tx_descriptor *
-mic_dma_prep_memcpy_lock(struct dma_chan *ch, dma_addr_t dma_dest,
-			 dma_addr_t dma_src, size_t len, unsigned long flags)
-{
-	struct mic_dma_chan *mic_ch = to_mic_dma_chan(ch);
-	struct device *dev = mic_dma_ch_to_device(mic_ch);
-	int result;
-
-	if (!len && !flags)
-		return NULL;
-
-	spin_lock(&mic_ch->prep_lock);
-	result = mic_dma_do_dma(mic_ch, flags, dma_src, dma_dest, len);
-	if (result >= 0)
-		return allocate_tx(mic_ch);
-	dev_err(dev, "Error enqueueing dma, error=%d\n", result);
-	spin_unlock(&mic_ch->prep_lock);
-	return NULL;
-}
-
-static struct dma_async_tx_descriptor *
-mic_dma_prep_interrupt_lock(struct dma_chan *ch, unsigned long flags)
-{
-	struct mic_dma_chan *mic_ch = to_mic_dma_chan(ch);
-	int ret;
-
-	spin_lock(&mic_ch->prep_lock);
-	ret = mic_dma_do_dma(mic_ch, flags, 0, 0, 0);
-	if (!ret)
-		return allocate_tx(mic_ch);
-	spin_unlock(&mic_ch->prep_lock);
-	return NULL;
-}
-
-/* Return the status of the transaction */
-static enum dma_status
-mic_dma_tx_status(struct dma_chan *ch, dma_cookie_t cookie,
-		  struct dma_tx_state *txstate)
-{
-	struct mic_dma_chan *mic_ch = to_mic_dma_chan(ch);
-
-	if (DMA_COMPLETE != dma_cookie_status(ch, cookie, txstate))
-		mic_dma_cleanup(mic_ch);
-
-	return dma_cookie_status(ch, cookie, txstate);
-}
-
-static irqreturn_t mic_dma_thread_fn(int irq, void *data)
-{
-	mic_dma_cleanup((struct mic_dma_chan *)data);
-	return IRQ_HANDLED;
-}
-
-static irqreturn_t mic_dma_intr_handler(int irq, void *data)
-{
-	struct mic_dma_chan *ch = ((struct mic_dma_chan *)data);
-
-	mic_dma_ack_interrupt(ch);
-	return IRQ_WAKE_THREAD;
-}
-
-static int mic_dma_alloc_desc_ring(struct mic_dma_chan *ch)
-{
-	u64 desc_ring_size = MIC_DMA_DESC_RX_SIZE * sizeof(*ch->desc_ring);
-	struct device *dev = &to_mbus_device(ch)->dev;
-
-	desc_ring_size = ALIGN(desc_ring_size, MIC_DMA_ALIGN_BYTES);
-	ch->desc_ring = kzalloc(desc_ring_size, GFP_KERNEL);
-
-	if (!ch->desc_ring)
-		return -ENOMEM;
-
-	ch->desc_ring_micpa = dma_map_single(dev, ch->desc_ring,
-					     desc_ring_size, DMA_BIDIRECTIONAL);
-	if (dma_mapping_error(dev, ch->desc_ring_micpa))
-		goto map_error;
-
-	ch->tx_array = vzalloc(array_size(MIC_DMA_DESC_RX_SIZE,
-					  sizeof(*ch->tx_array)));
-	if (!ch->tx_array)
-		goto tx_error;
-	return 0;
-tx_error:
-	dma_unmap_single(dev, ch->desc_ring_micpa, desc_ring_size,
-			 DMA_BIDIRECTIONAL);
-map_error:
-	kfree(ch->desc_ring);
-	return -ENOMEM;
-}
-
-static void mic_dma_free_desc_ring(struct mic_dma_chan *ch)
-{
-	u64 desc_ring_size = MIC_DMA_DESC_RX_SIZE * sizeof(*ch->desc_ring);
-
-	vfree(ch->tx_array);
-	desc_ring_size = ALIGN(desc_ring_size, MIC_DMA_ALIGN_BYTES);
-	dma_unmap_single(&to_mbus_device(ch)->dev, ch->desc_ring_micpa,
-			 desc_ring_size, DMA_BIDIRECTIONAL);
-	kfree(ch->desc_ring);
-	ch->desc_ring = NULL;
-}
-
-static void mic_dma_free_status_dest(struct mic_dma_chan *ch)
-{
-	dma_unmap_single(&to_mbus_device(ch)->dev, ch->status_dest_micpa,
-			 L1_CACHE_BYTES, DMA_BIDIRECTIONAL);
-	kfree(ch->status_dest);
-}
-
-static int mic_dma_alloc_status_dest(struct mic_dma_chan *ch)
-{
-	struct device *dev = &to_mbus_device(ch)->dev;
-
-	ch->status_dest = kzalloc(L1_CACHE_BYTES, GFP_KERNEL);
-	if (!ch->status_dest)
-		return -ENOMEM;
-	ch->status_dest_micpa = dma_map_single(dev, ch->status_dest,
-					L1_CACHE_BYTES, DMA_BIDIRECTIONAL);
-	if (dma_mapping_error(dev, ch->status_dest_micpa)) {
-		kfree(ch->status_dest);
-		ch->status_dest = NULL;
-		return -ENOMEM;
-	}
-	return 0;
-}
-
-static int mic_dma_check_chan(struct mic_dma_chan *ch)
-{
-	if (mic_dma_read_reg(ch, MIC_DMA_REG_DCHERR) ||
-	    mic_dma_read_reg(ch, MIC_DMA_REG_DSTAT) & MIC_DMA_CHAN_QUIESCE) {
-		mic_dma_disable_chan(ch);
-		mic_dma_chan_mask_intr(ch);
-		dev_err(mic_dma_ch_to_device(ch),
-			"%s %d error setting up mic dma chan %d\n",
-			__func__, __LINE__, ch->ch_num);
-		return -EBUSY;
-	}
-	return 0;
-}
-
-static int mic_dma_chan_setup(struct mic_dma_chan *ch)
-{
-	if (MIC_DMA_CHAN_MIC == ch->owner)
-		mic_dma_chan_set_owner(ch);
-	mic_dma_disable_chan(ch);
-	mic_dma_chan_mask_intr(ch);
-	mic_dma_write_reg(ch, MIC_DMA_REG_DCHERRMSK, 0);
-	mic_dma_chan_set_desc_ring(ch);
-	ch->last_tail = mic_dma_read_reg(ch, MIC_DMA_REG_DTPR);
-	ch->head = ch->last_tail;
-	ch->issued = 0;
-	mic_dma_chan_unmask_intr(ch);
-	mic_dma_enable_chan(ch);
-	return mic_dma_check_chan(ch);
-}
-
-static void mic_dma_chan_destroy(struct mic_dma_chan *ch)
-{
-	mic_dma_disable_chan(ch);
-	mic_dma_chan_mask_intr(ch);
-}
-
-static int mic_dma_setup_irq(struct mic_dma_chan *ch)
-{
-	ch->cookie =
-		to_mbus_hw_ops(ch)->request_threaded_irq(to_mbus_device(ch),
-			mic_dma_intr_handler, mic_dma_thread_fn,
-			"mic dma_channel", ch, ch->ch_num);
-	return PTR_ERR_OR_ZERO(ch->cookie);
-}
-
-static inline void mic_dma_free_irq(struct mic_dma_chan *ch)
-{
-	to_mbus_hw_ops(ch)->free_irq(to_mbus_device(ch), ch->cookie, ch);
-}
-
-static int mic_dma_chan_init(struct mic_dma_chan *ch)
-{
-	int ret = mic_dma_alloc_desc_ring(ch);
-
-	if (ret)
-		goto ring_error;
-	ret = mic_dma_alloc_status_dest(ch);
-	if (ret)
-		goto status_error;
-	ret = mic_dma_chan_setup(ch);
-	if (ret)
-		goto chan_error;
-	return ret;
-chan_error:
-	mic_dma_free_status_dest(ch);
-status_error:
-	mic_dma_free_desc_ring(ch);
-ring_error:
-	return ret;
-}
-
-static int mic_dma_drain_chan(struct mic_dma_chan *ch)
-{
-	struct dma_async_tx_descriptor *tx;
-	int err = 0;
-	dma_cookie_t cookie;
-
-	tx = mic_dma_prep_memcpy_lock(&ch->api_ch, 0, 0, 0, DMA_PREP_FENCE);
-	if (!tx) {
-		err = -ENOMEM;
-		goto error;
-	}
-
-	cookie = tx->tx_submit(tx);
-	if (dma_submit_error(cookie))
-		err = -ENOMEM;
-	else
-		err = dma_sync_wait(&ch->api_ch, cookie);
-	if (err) {
-		dev_err(mic_dma_ch_to_device(ch), "%s %d TO chan 0x%x\n",
-			__func__, __LINE__, ch->ch_num);
-		err = -EIO;
-	}
-error:
-	mic_dma_cleanup(ch);
-	return err;
-}
-
-static inline void mic_dma_chan_uninit(struct mic_dma_chan *ch)
-{
-	mic_dma_chan_destroy(ch);
-	mic_dma_cleanup(ch);
-	mic_dma_free_status_dest(ch);
-	mic_dma_free_desc_ring(ch);
-}
-
-static int mic_dma_init(struct mic_dma_device *mic_dma_dev,
-			enum mic_dma_chan_owner owner)
-{
-	int i, first_chan = mic_dma_dev->start_ch;
-	struct mic_dma_chan *ch;
-	int ret;
-
-	for (i = first_chan; i < first_chan + MIC_DMA_NUM_CHAN; i++) {
-		ch = &mic_dma_dev->mic_ch[i];
-		ch->ch_num = i;
-		ch->owner = owner;
-		spin_lock_init(&ch->cleanup_lock);
-		spin_lock_init(&ch->prep_lock);
-		spin_lock_init(&ch->issue_lock);
-		ret = mic_dma_setup_irq(ch);
-		if (ret)
-			goto error;
-	}
-	return 0;
-error:
-	for (i = i - 1; i >= first_chan; i--)
-		mic_dma_free_irq(ch);
-	return ret;
-}
-
-static void mic_dma_uninit(struct mic_dma_device *mic_dma_dev)
-{
-	int i, first_chan = mic_dma_dev->start_ch;
-	struct mic_dma_chan *ch;
-
-	for (i = first_chan; i < first_chan + MIC_DMA_NUM_CHAN; i++) {
-		ch = &mic_dma_dev->mic_ch[i];
-		mic_dma_free_irq(ch);
-	}
-}
-
-static int mic_dma_alloc_chan_resources(struct dma_chan *ch)
-{
-	int ret = mic_dma_chan_init(to_mic_dma_chan(ch));
-	if (ret)
-		return ret;
-	return MIC_DMA_DESC_RX_SIZE;
-}
-
-static void mic_dma_free_chan_resources(struct dma_chan *ch)
-{
-	struct mic_dma_chan *mic_ch = to_mic_dma_chan(ch);
-	mic_dma_drain_chan(mic_ch);
-	mic_dma_chan_uninit(mic_ch);
-}
-
-/* Set the fn. handlers and register the dma device with dma api */
-static int mic_dma_register_dma_device(struct mic_dma_device *mic_dma_dev,
-				       enum mic_dma_chan_owner owner)
-{
-	int i, first_chan = mic_dma_dev->start_ch;
-
-	dma_cap_zero(mic_dma_dev->dma_dev.cap_mask);
-	/*
-	 * This dma engine is not capable of host memory to host memory
-	 * transfers
-	 */
-	dma_cap_set(DMA_MEMCPY, mic_dma_dev->dma_dev.cap_mask);
-
-	if (MIC_DMA_CHAN_HOST == owner)
-		dma_cap_set(DMA_PRIVATE, mic_dma_dev->dma_dev.cap_mask);
-	mic_dma_dev->dma_dev.device_alloc_chan_resources =
-		mic_dma_alloc_chan_resources;
-	mic_dma_dev->dma_dev.device_free_chan_resources =
-		mic_dma_free_chan_resources;
-	mic_dma_dev->dma_dev.device_tx_status = mic_dma_tx_status;
-	mic_dma_dev->dma_dev.device_prep_dma_memcpy = mic_dma_prep_memcpy_lock;
-	mic_dma_dev->dma_dev.device_prep_dma_imm_data =
-		mic_dma_prep_status_lock;
-	mic_dma_dev->dma_dev.device_prep_dma_interrupt =
-		mic_dma_prep_interrupt_lock;
-	mic_dma_dev->dma_dev.device_issue_pending = mic_dma_issue_pending;
-	mic_dma_dev->dma_dev.copy_align = MIC_DMA_ALIGN_SHIFT;
-	INIT_LIST_HEAD(&mic_dma_dev->dma_dev.channels);
-	for (i = first_chan; i < first_chan + MIC_DMA_NUM_CHAN; i++) {
-		mic_dma_dev->mic_ch[i].api_ch.device = &mic_dma_dev->dma_dev;
-		dma_cookie_init(&mic_dma_dev->mic_ch[i].api_ch);
-		list_add_tail(&mic_dma_dev->mic_ch[i].api_ch.device_node,
-			      &mic_dma_dev->dma_dev.channels);
-	}
-	return dmaenginem_async_device_register(&mic_dma_dev->dma_dev);
-}
-
-/*
- * Initializes dma channels and registers the dma device with the
- * dma engine api.
- */
-static struct mic_dma_device *mic_dma_dev_reg(struct mbus_device *mbdev,
-					      enum mic_dma_chan_owner owner)
-{
-	struct mic_dma_device *mic_dma_dev;
-	int ret;
-	struct device *dev = &mbdev->dev;
-
-	mic_dma_dev = devm_kzalloc(dev, sizeof(*mic_dma_dev), GFP_KERNEL);
-	if (!mic_dma_dev) {
-		ret = -ENOMEM;
-		goto alloc_error;
-	}
-	mic_dma_dev->mbdev = mbdev;
-	mic_dma_dev->dma_dev.dev = dev;
-	mic_dma_dev->mmio = mbdev->mmio_va;
-	if (MIC_DMA_CHAN_HOST == owner) {
-		mic_dma_dev->start_ch = 0;
-		mic_dma_dev->max_xfer_size = MIC_DMA_MAX_XFER_SIZE_HOST;
-	} else {
-		mic_dma_dev->start_ch = 4;
-		mic_dma_dev->max_xfer_size = MIC_DMA_MAX_XFER_SIZE_CARD;
-	}
-	ret = mic_dma_init(mic_dma_dev, owner);
-	if (ret)
-		goto init_error;
-	ret = mic_dma_register_dma_device(mic_dma_dev, owner);
-	if (ret)
-		goto reg_error;
-	return mic_dma_dev;
-reg_error:
-	mic_dma_uninit(mic_dma_dev);
-init_error:
-	mic_dma_dev = NULL;
-alloc_error:
-	dev_err(dev, "Error at %s %d ret=%d\n", __func__, __LINE__, ret);
-	return mic_dma_dev;
-}
-
-static void mic_dma_dev_unreg(struct mic_dma_device *mic_dma_dev)
-{
-	mic_dma_uninit(mic_dma_dev);
-}
-
-/* DEBUGFS CODE */
-static int mic_dma_reg_show(struct seq_file *s, void *pos)
-{
-	struct mic_dma_device *mic_dma_dev = s->private;
-	int i, chan_num, first_chan = mic_dma_dev->start_ch;
-	struct mic_dma_chan *ch;
-
-	seq_printf(s, "SBOX_DCR: %#x\n",
-		   mic_dma_mmio_read(&mic_dma_dev->mic_ch[first_chan],
-				     MIC_DMA_SBOX_BASE + MIC_DMA_SBOX_DCR));
-	seq_puts(s, "DMA Channel Registers\n");
-	seq_printf(s, "%-10s| %-10s %-10s %-10s %-10s %-10s",
-		   "Channel", "DCAR", "DTPR", "DHPR", "DRAR_HI", "DRAR_LO");
-	seq_printf(s, " %-11s %-14s %-10s\n", "DCHERR", "DCHERRMSK", "DSTAT");
-	for (i = first_chan; i < first_chan + MIC_DMA_NUM_CHAN; i++) {
-		ch = &mic_dma_dev->mic_ch[i];
-		chan_num = ch->ch_num;
-		seq_printf(s, "%-10i| %-#10x %-#10x %-#10x %-#10x",
-			   chan_num,
-			   mic_dma_read_reg(ch, MIC_DMA_REG_DCAR),
-			   mic_dma_read_reg(ch, MIC_DMA_REG_DTPR),
-			   mic_dma_read_reg(ch, MIC_DMA_REG_DHPR),
-			   mic_dma_read_reg(ch, MIC_DMA_REG_DRAR_HI));
-		seq_printf(s, " %-#10x %-#10x %-#14x %-#10x\n",
-			   mic_dma_read_reg(ch, MIC_DMA_REG_DRAR_LO),
-			   mic_dma_read_reg(ch, MIC_DMA_REG_DCHERR),
-			   mic_dma_read_reg(ch, MIC_DMA_REG_DCHERRMSK),
-			   mic_dma_read_reg(ch, MIC_DMA_REG_DSTAT));
-	}
-	return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(mic_dma_reg);
-
-/* Debugfs parent dir */
-static struct dentry *mic_dma_dbg;
-
-static int mic_dma_driver_probe(struct mbus_device *mbdev)
-{
-	struct mic_dma_device *mic_dma_dev;
-	enum mic_dma_chan_owner owner;
-
-	if (MBUS_DEV_DMA_MIC == mbdev->id.device)
-		owner = MIC_DMA_CHAN_MIC;
-	else
-		owner = MIC_DMA_CHAN_HOST;
-
-	mic_dma_dev = mic_dma_dev_reg(mbdev, owner);
-	dev_set_drvdata(&mbdev->dev, mic_dma_dev);
-
-	if (mic_dma_dbg) {
-		mic_dma_dev->dbg_dir = debugfs_create_dir(dev_name(&mbdev->dev),
-							  mic_dma_dbg);
-		debugfs_create_file("mic_dma_reg", 0444, mic_dma_dev->dbg_dir,
-				    mic_dma_dev, &mic_dma_reg_fops);
-	}
-	return 0;
-}
-
-static void mic_dma_driver_remove(struct mbus_device *mbdev)
-{
-	struct mic_dma_device *mic_dma_dev;
-
-	mic_dma_dev = dev_get_drvdata(&mbdev->dev);
-	debugfs_remove_recursive(mic_dma_dev->dbg_dir);
-	mic_dma_dev_unreg(mic_dma_dev);
-}
-
-static struct mbus_device_id id_table[] = {
-	{MBUS_DEV_DMA_MIC, MBUS_DEV_ANY_ID},
-	{MBUS_DEV_DMA_HOST, MBUS_DEV_ANY_ID},
-	{0},
-};
-
-static struct mbus_driver mic_dma_driver = {
-	.driver.name =	KBUILD_MODNAME,
-	.driver.owner =	THIS_MODULE,
-	.id_table = id_table,
-	.probe = mic_dma_driver_probe,
-	.remove = mic_dma_driver_remove,
-};
-
-static int __init mic_x100_dma_init(void)
-{
-	int rc = mbus_register_driver(&mic_dma_driver);
-	if (rc)
-		return rc;
-	mic_dma_dbg = debugfs_create_dir(KBUILD_MODNAME, NULL);
-	return 0;
-}
-
-static void __exit mic_x100_dma_exit(void)
-{
-	debugfs_remove_recursive(mic_dma_dbg);
-	mbus_unregister_driver(&mic_dma_driver);
-}
-
-module_init(mic_x100_dma_init);
-module_exit(mic_x100_dma_exit);
-
-MODULE_DEVICE_TABLE(mbus, id_table);
-MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Intel(R) MIC X100 DMA Driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/mic_x100_dma.h b/drivers/dma/mic_x100_dma.h
deleted file mode 100644
index 68ef43a91714..000000000000
--- a/drivers/dma/mic_x100_dma.h
+++ /dev/null
@@ -1,275 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel MIC X100 DMA Driver.
- *
- * Adapted from IOAT dma driver.
- */
-#ifndef _MIC_X100_DMA_H_
-#define _MIC_X100_DMA_H_
-
-#include <linux/kernel.h>
-#include <linux/delay.h>
-#include <linux/sched.h>
-#include <linux/debugfs.h>
-#include <linux/slab.h>
-#include <linux/interrupt.h>
-#include <linux/mic_bus.h>
-
-#include "dmaengine.h"
-
-/*
- * MIC has a total of 8 dma channels.
- * Four channels are assigned for host SW use & the remaining for MIC SW.
- * MIC DMA transfer size & addresses need to be 64 byte aligned.
- */
-#define MIC_DMA_MAX_NUM_CHAN	8
-#define MIC_DMA_NUM_CHAN	4
-#define MIC_DMA_ALIGN_SHIFT	DMAENGINE_ALIGN_64_BYTES
-#define MIC_DMA_ALIGN_BYTES	(1 << MIC_DMA_ALIGN_SHIFT)
-#define MIC_DMA_DESC_RX_SIZE	(128 * 1024 - 4)
-
-/*
- * Register descriptions
- * All the registers are 32 bit registers.
- * DCR is a global register and all others are per-channel.
- * DCR - bits 0, 2, 4, 6, 8, 10, 12, 14 - enable bits for channels 0 to 7
- *	 bits 1, 3, 5, 7, 9, 11, 13, 15 - owner bits for channels 0 to 7
- * DCAR - bit 24 & 25 interrupt masks for mic owned & host owned channels
- * DHPR - head of the descriptor ring updated by s/w
- * DTPR - tail of the descriptor ring updated by h/w
- * DRAR_LO - lower 32 bits of descriptor ring's mic address
- * DRAR_HI - 3:0 - remaining 4 bits of descriptor ring's mic address
- *	     20:4 descriptor ring size
- *	     25:21 mic smpt entry number
- * DSTAT - 16:0 h/w completion count; 31:28 dma engine status
- * DCHERR - this register is non-zero on error
- * DCHERRMSK - interrupt mask register
- */
-#define MIC_DMA_HW_CMP_CNT_MASK		0x1ffff
-#define MIC_DMA_CHAN_QUIESCE		0x20000000
-#define MIC_DMA_SBOX_BASE		0x00010000
-#define MIC_DMA_SBOX_DCR		0x0000A280
-#define MIC_DMA_SBOX_CH_BASE		0x0001A000
-#define MIC_DMA_SBOX_CHAN_OFF		0x40
-#define MIC_DMA_SBOX_DCAR_IM0		(0x1 << 24)
-#define MIC_DMA_SBOX_DCAR_IM1		(0x1 << 25)
-#define MIC_DMA_SBOX_DRARHI_SYS_MASK	(0x1 << 26)
-#define MIC_DMA_REG_DCAR		0
-#define MIC_DMA_REG_DHPR		4
-#define MIC_DMA_REG_DTPR		8
-#define MIC_DMA_REG_DRAR_LO		20
-#define MIC_DMA_REG_DRAR_HI		24
-#define MIC_DMA_REG_DSTAT		32
-#define MIC_DMA_REG_DCHERR		44
-#define MIC_DMA_REG_DCHERRMSK		48
-
-/* HW dma desc */
-struct mic_dma_desc {
-	u64 qw0;
-	u64 qw1;
-};
-
-enum mic_dma_chan_owner {
-	MIC_DMA_CHAN_MIC = 0,
-	MIC_DMA_CHAN_HOST
-};
-
-/*
- * mic_dma_chan - channel specific information
- * @ch_num: channel number
- * @owner: owner of this channel
- * @last_tail: cached value of descriptor ring tail
- * @head: index of next descriptor in desc_ring
- * @issued: hardware notification point
- * @submitted: index that will be used to submit descriptors to h/w
- * @api_ch: dma engine api channel
- * @desc_ring: dma descriptor ring
- * @desc_ring_micpa: mic physical address of desc_ring
- * @status_dest: destination for status (fence) descriptor
- * @status_dest_micpa: mic address for status_dest,
- *		       DMA controller uses this address
- * @tx_array: array of async_tx
- * @cleanup_lock: lock held when processing completed tx
- * @prep_lock: lock held in prep_memcpy & released in tx_submit
- * @issue_lock: lock used to synchronize writes to head
- * @cookie: mic_irq cookie used with mic irq request
- */
-struct mic_dma_chan {
-	int ch_num;
-	enum mic_dma_chan_owner owner;
-	u32 last_tail;
-	u32 head;
-	u32 issued;
-	u32 submitted;
-	struct dma_chan api_ch;
-	struct mic_dma_desc *desc_ring;
-	dma_addr_t desc_ring_micpa;
-	u64 *status_dest;
-	dma_addr_t status_dest_micpa;
-	struct dma_async_tx_descriptor *tx_array;
-	spinlock_t cleanup_lock;
-	spinlock_t prep_lock;
-	spinlock_t issue_lock;
-	struct mic_irq *cookie;
-};
-
-/*
- * struct mic_dma_device - per mic device
- * @mic_ch: dma channels
- * @dma_dev: underlying dma device
- * @mbdev: mic bus dma device
- * @mmio: virtual address of the mmio space
- * @dbg_dir: debugfs directory
- * @start_ch: first channel number that can be used
- * @max_xfer_size: maximum transfer size per dma descriptor
- */
-struct mic_dma_device {
-	struct mic_dma_chan mic_ch[MIC_DMA_MAX_NUM_CHAN];
-	struct dma_device dma_dev;
-	struct mbus_device *mbdev;
-	void __iomem *mmio;
-	struct dentry *dbg_dir;
-	int start_ch;
-	size_t max_xfer_size;
-};
-
-static inline struct mic_dma_chan *to_mic_dma_chan(struct dma_chan *ch)
-{
-	return container_of(ch, struct mic_dma_chan, api_ch);
-}
-
-static inline struct mic_dma_device *to_mic_dma_dev(struct mic_dma_chan *ch)
-{
-	return
-	container_of((const typeof(((struct mic_dma_device *)0)->mic_ch)*)
-		     (ch - ch->ch_num), struct mic_dma_device, mic_ch);
-}
-
-static inline struct mbus_device *to_mbus_device(struct mic_dma_chan *ch)
-{
-	return to_mic_dma_dev(ch)->mbdev;
-}
-
-static inline struct mbus_hw_ops *to_mbus_hw_ops(struct mic_dma_chan *ch)
-{
-	return to_mbus_device(ch)->hw_ops;
-}
-
-static inline struct device *mic_dma_ch_to_device(struct mic_dma_chan *ch)
-{
-	return to_mic_dma_dev(ch)->dma_dev.dev;
-}
-
-static inline void __iomem *mic_dma_chan_to_mmio(struct mic_dma_chan *ch)
-{
-	return to_mic_dma_dev(ch)->mmio;
-}
-
-static inline u32 mic_dma_read_reg(struct mic_dma_chan *ch, u32 reg)
-{
-	return ioread32(mic_dma_chan_to_mmio(ch) + MIC_DMA_SBOX_CH_BASE +
-			ch->ch_num * MIC_DMA_SBOX_CHAN_OFF + reg);
-}
-
-static inline void mic_dma_write_reg(struct mic_dma_chan *ch, u32 reg, u32 val)
-{
-	iowrite32(val, mic_dma_chan_to_mmio(ch) + MIC_DMA_SBOX_CH_BASE +
-		  ch->ch_num * MIC_DMA_SBOX_CHAN_OFF + reg);
-}
-
-static inline u32 mic_dma_mmio_read(struct mic_dma_chan *ch, u32 offset)
-{
-	return ioread32(mic_dma_chan_to_mmio(ch) + offset);
-}
-
-static inline void mic_dma_mmio_write(struct mic_dma_chan *ch, u32 val,
-				      u32 offset)
-{
-	iowrite32(val, mic_dma_chan_to_mmio(ch) + offset);
-}
-
-static inline u32 mic_dma_read_cmp_cnt(struct mic_dma_chan *ch)
-{
-	return mic_dma_read_reg(ch, MIC_DMA_REG_DSTAT) &
-	       MIC_DMA_HW_CMP_CNT_MASK;
-}
-
-static inline void mic_dma_chan_set_owner(struct mic_dma_chan *ch)
-{
-	u32 dcr = mic_dma_mmio_read(ch, MIC_DMA_SBOX_BASE + MIC_DMA_SBOX_DCR);
-	u32 chan_num = ch->ch_num;
-
-	dcr = (dcr & ~(0x1 << (chan_num * 2))) | (ch->owner << (chan_num * 2));
-	mic_dma_mmio_write(ch, dcr, MIC_DMA_SBOX_BASE + MIC_DMA_SBOX_DCR);
-}
-
-static inline void mic_dma_enable_chan(struct mic_dma_chan *ch)
-{
-	u32 dcr = mic_dma_mmio_read(ch, MIC_DMA_SBOX_BASE + MIC_DMA_SBOX_DCR);
-
-	dcr |= 2 << (ch->ch_num << 1);
-	mic_dma_mmio_write(ch, dcr, MIC_DMA_SBOX_BASE + MIC_DMA_SBOX_DCR);
-}
-
-static inline void mic_dma_disable_chan(struct mic_dma_chan *ch)
-{
-	u32 dcr = mic_dma_mmio_read(ch, MIC_DMA_SBOX_BASE + MIC_DMA_SBOX_DCR);
-
-	dcr &= ~(2 << (ch->ch_num << 1));
-	mic_dma_mmio_write(ch, dcr, MIC_DMA_SBOX_BASE + MIC_DMA_SBOX_DCR);
-}
-
-static void mic_dma_chan_set_desc_ring(struct mic_dma_chan *ch)
-{
-	u32 drar_hi;
-	dma_addr_t desc_ring_micpa = ch->desc_ring_micpa;
-
-	drar_hi = (MIC_DMA_DESC_RX_SIZE & 0x1ffff) << 4;
-	if (MIC_DMA_CHAN_MIC == ch->owner) {
-		drar_hi |= (desc_ring_micpa >> 32) & 0xf;
-	} else {
-		drar_hi |= MIC_DMA_SBOX_DRARHI_SYS_MASK;
-		drar_hi |= ((desc_ring_micpa >> 34)
-			    & 0x1f) << 21;
-		drar_hi |= (desc_ring_micpa >> 32) & 0x3;
-	}
-	mic_dma_write_reg(ch, MIC_DMA_REG_DRAR_LO, (u32) desc_ring_micpa);
-	mic_dma_write_reg(ch, MIC_DMA_REG_DRAR_HI, drar_hi);
-}
-
-static inline void mic_dma_chan_mask_intr(struct mic_dma_chan *ch)
-{
-	u32 dcar = mic_dma_read_reg(ch, MIC_DMA_REG_DCAR);
-
-	if (MIC_DMA_CHAN_MIC == ch->owner)
-		dcar |= MIC_DMA_SBOX_DCAR_IM0;
-	else
-		dcar |= MIC_DMA_SBOX_DCAR_IM1;
-	mic_dma_write_reg(ch, MIC_DMA_REG_DCAR, dcar);
-}
-
-static inline void mic_dma_chan_unmask_intr(struct mic_dma_chan *ch)
-{
-	u32 dcar = mic_dma_read_reg(ch, MIC_DMA_REG_DCAR);
-
-	if (MIC_DMA_CHAN_MIC == ch->owner)
-		dcar &= ~MIC_DMA_SBOX_DCAR_IM0;
-	else
-		dcar &= ~MIC_DMA_SBOX_DCAR_IM1;
-	mic_dma_write_reg(ch, MIC_DMA_REG_DCAR, dcar);
-}
-
-static void mic_dma_ack_interrupt(struct mic_dma_chan *ch)
-{
-	if (MIC_DMA_CHAN_MIC == ch->owner) {
-		/* HW errata */
-		mic_dma_chan_mask_intr(ch);
-		mic_dma_chan_unmask_intr(ch);
-	}
-	to_mbus_hw_ops(ch)->ack_interrupt(to_mbus_device(ch), ch->ch_num);
-}
-#endif
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index d5ce8082b0a0..fafa8b0d8099 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -474,7 +474,6 @@ source "drivers/misc/lis3lv02d/Kconfig"
 source "drivers/misc/altera-stapl/Kconfig"
 source "drivers/misc/mei/Kconfig"
 source "drivers/misc/vmw_vmci/Kconfig"
-source "drivers/misc/mic/Kconfig"
 source "drivers/misc/genwqe/Kconfig"
 source "drivers/misc/echo/Kconfig"
 source "drivers/misc/cxl/Kconfig"
diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile
index 2521359e8ef7..d23231e73330 100644
--- a/drivers/misc/Makefile
+++ b/drivers/misc/Makefile
@@ -46,7 +46,6 @@ obj-$(CONFIG_VMWARE_VMCI)	+= vmw_vmci/
 obj-$(CONFIG_LATTICE_ECP3_CONFIG)	+= lattice-ecp3-config.o
 obj-$(CONFIG_SRAM)		+= sram.o
 obj-$(CONFIG_SRAM_EXEC)		+= sram-exec.o
-obj-y				+= mic/
 obj-$(CONFIG_GENWQE)		+= genwqe/
 obj-$(CONFIG_ECHO)		+= echo/
 obj-$(CONFIG_CXL_BASE)		+= cxl/
diff --git a/drivers/misc/mic/Kconfig b/drivers/misc/mic/Kconfig
deleted file mode 100644
index 8a7c2c5711d5..000000000000
--- a/drivers/misc/mic/Kconfig
+++ /dev/null
@@ -1,141 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-menu "Intel MIC & related support"
-
-config INTEL_MIC_BUS
-	tristate "Intel MIC Bus Driver"
-	depends on 64BIT && PCI && X86
-	select DMA_OPS
-	help
-	  This option is selected by any driver which registers a
-	  device or driver on the MIC Bus, such as CONFIG_INTEL_MIC_HOST,
-	  CONFIG_INTEL_MIC_CARD, CONFIG_INTEL_MIC_X100_DMA etc.
-
-	  If you are building a host/card kernel with an Intel MIC device
-	  then say M (recommended) or Y, else say N. If unsure say N.
-
-	  More information about the Intel MIC family as well as the Linux
-	  OS and tools for MIC to use with this driver are available from
-	  <http://software.intel.com/en-us/mic-developer>.
-
-config SCIF_BUS
-	tristate "SCIF Bus Driver"
-	depends on 64BIT && PCI && X86
-	select DMA_OPS
-	help
-	  This option is selected by any driver which registers a
-	  device or driver on the SCIF Bus, such as CONFIG_INTEL_MIC_HOST
-	  and CONFIG_INTEL_MIC_CARD.
-
-	  If you are building a host/card kernel with an Intel MIC device
-	  then say M (recommended) or Y, else say N. If unsure say N.
-
-	  More information about the Intel MIC family as well as the Linux
-	  OS and tools for MIC to use with this driver are available from
-	  <http://software.intel.com/en-us/mic-developer>.
-
-config VOP_BUS
-	tristate "VOP Bus Driver"
-	depends on HAS_DMA
-	select DMA_OPS
-	help
-	  This option is selected by any driver which registers a
-	  device or driver on the VOP Bus, such as CONFIG_INTEL_MIC_HOST
-	  and CONFIG_INTEL_MIC_CARD.
-
-	  If you are building a host/card kernel with an Intel MIC device
-	  then say M (recommended) or Y, else say N. If unsure say N.
-
-	  More information about the Intel MIC family as well as the Linux
-	  OS and tools for MIC to use with this driver are available from
-	  <http://software.intel.com/en-us/mic-developer>.
-
-config INTEL_MIC_HOST
-	tristate "Intel MIC Host Driver"
-	depends on 64BIT && PCI && X86
-	depends on INTEL_MIC_BUS && SCIF_BUS && MIC_COSM && VOP_BUS
-	select DMA_OPS
-	help
-	  This enables Host Driver support for the Intel Many Integrated
-	  Core (MIC) family of PCIe form factor coprocessor devices that
-	  run a 64 bit Linux OS. The driver manages card OS state and
-	  enables communication between host and card. Intel MIC X100
-	  devices are currently supported.
-
-	  If you are building a host kernel with an Intel MIC device then
-	  say M (recommended) or Y, else say N. If unsure say N.
-
-	  More information about the Intel MIC family as well as the Linux
-	  OS and tools for MIC to use with this driver are available from
-	  <http://software.intel.com/en-us/mic-developer>.
-
-config INTEL_MIC_CARD
-	tristate "Intel MIC Card Driver"
-	depends on 64BIT && X86
-	depends on INTEL_MIC_BUS && SCIF_BUS && MIC_COSM && VOP_BUS
-	select VIRTIO
-	help
-	  This enables card driver support for the Intel Many Integrated
-	  Core (MIC) device family. The card driver communicates shutdown/
-	  crash events to the host and allows registration/configuration of
-	  virtio devices. Intel MIC X100 devices are currently supported.
-
-	  If you are building a card kernel for an Intel MIC device then
-	  say M (recommended) or Y, else say N. If unsure say N.
-
-	  For more information see
-	  <http://software.intel.com/en-us/mic-developer>.
-
-config SCIF
-	tristate "SCIF Driver"
-	depends on 64BIT && PCI && X86 && SCIF_BUS && IOMMU_SUPPORT
-	select IOMMU_IOVA
-	help
-	  This enables SCIF Driver support for the Intel Many Integrated
-	  Core (MIC) family of PCIe form factor coprocessor devices that
-	  run a 64 bit Linux OS. The Symmetric Communication Interface
-	  (SCIF (pronounced as skiff)) is a low level communications API
-	  across PCIe currently implemented for MIC.
-
-	  If you are building a host kernel with an Intel MIC device then
-	  say M (recommended) or Y, else say N. If unsure say N.
-
-	  More information about the Intel MIC family as well as the Linux
-	  OS and tools for MIC to use with this driver are available from
-	  <http://software.intel.com/en-us/mic-developer>.
-
-config MIC_COSM
-	tristate "Intel MIC Coprocessor State Management (COSM) Drivers"
-	depends on 64BIT && PCI && X86 && SCIF
-	help
-	  This enables COSM driver support for the Intel Many
-	  Integrated Core (MIC) family of PCIe form factor coprocessor
-	  devices. COSM drivers implement functions such as boot,
-	  shutdown, reset and reboot of MIC devices.
-
-	  If you are building a host kernel with an Intel MIC device then
-	  say M (recommended) or Y, else say N. If unsure say N.
-
-	  More information about the Intel MIC family as well as the Linux
-	  OS and tools for MIC to use with this driver are available from
-	  <http://software.intel.com/en-us/mic-developer>.
-
-config VOP
-	tristate "VOP Driver"
-	depends on VOP_BUS
-	select VHOST_RING
-	select VIRTIO
-	help
-	  This enables VOP (Virtio over PCIe) Driver support for the Intel
-	  Many Integrated Core (MIC) family of PCIe form factor coprocessor
-	  devices. The VOP driver allows virtio drivers, e.g. net, console
-	  and block drivers, on the card connect to user space virtio
-	  devices on the host.
-
-	  If you are building a host kernel with an Intel MIC device then
-	  say M (recommended) or Y, else say N. If unsure say N.
-
-	  More information about the Intel MIC family as well as the Linux
-	  OS and tools for MIC to use with this driver are available from
-	  <http://software.intel.com/en-us/mic-developer>.
-
-endmenu
diff --git a/drivers/misc/mic/Makefile b/drivers/misc/mic/Makefile
deleted file mode 100644
index 1a43622b183f..000000000000
--- a/drivers/misc/mic/Makefile
+++ /dev/null
@@ -1,12 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-#
-# Makefile - Intel MIC Linux driver.
-# Copyright(c) 2013, Intel Corporation.
-#
-obj-$(CONFIG_INTEL_MIC_HOST) += host/
-obj-$(CONFIG_INTEL_MIC_CARD) += card/
-obj-y += bus/
-obj-$(CONFIG_SCIF) += scif/
-obj-$(CONFIG_MIC_COSM) += cosm/
-obj-$(CONFIG_MIC_COSM) += cosm_client/
-obj-$(CONFIG_VOP) += vop/
diff --git a/drivers/misc/mic/bus/Makefile b/drivers/misc/mic/bus/Makefile
deleted file mode 100644
index 0a6aa21b2f67..000000000000
--- a/drivers/misc/mic/bus/Makefile
+++ /dev/null
@@ -1,9 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-#
-# Makefile - Intel MIC Linux driver.
-# Copyright(c) 2014, Intel Corporation.
-#
-obj-$(CONFIG_INTEL_MIC_BUS) += mic_bus.o
-obj-$(CONFIG_SCIF_BUS) += scif_bus.o
-obj-$(CONFIG_MIC_COSM) += cosm_bus.o
-obj-$(CONFIG_VOP_BUS) += vop_bus.o
diff --git a/drivers/misc/mic/bus/cosm_bus.c b/drivers/misc/mic/bus/cosm_bus.c
deleted file mode 100644
index 5f2141c71738..000000000000
--- a/drivers/misc/mic/bus/cosm_bus.c
+++ /dev/null
@@ -1,130 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel MIC COSM Bus Driver
- */
-#include <linux/slab.h>
-#include <linux/module.h>
-#include <linux/idr.h>
-#include "cosm_bus.h"
-
-/* Unique numbering for cosm devices. */
-static DEFINE_IDA(cosm_index_ida);
-
-static int cosm_dev_probe(struct device *d)
-{
-	struct cosm_device *dev = dev_to_cosm(d);
-	struct cosm_driver *drv = drv_to_cosm(dev->dev.driver);
-
-	return drv->probe(dev);
-}
-
-static int cosm_dev_remove(struct device *d)
-{
-	struct cosm_device *dev = dev_to_cosm(d);
-	struct cosm_driver *drv = drv_to_cosm(dev->dev.driver);
-
-	drv->remove(dev);
-	return 0;
-}
-
-static struct bus_type cosm_bus = {
-	.name  = "cosm_bus",
-	.probe = cosm_dev_probe,
-	.remove = cosm_dev_remove,
-};
-
-int cosm_register_driver(struct cosm_driver *driver)
-{
-	driver->driver.bus = &cosm_bus;
-	return driver_register(&driver->driver);
-}
-EXPORT_SYMBOL_GPL(cosm_register_driver);
-
-void cosm_unregister_driver(struct cosm_driver *driver)
-{
-	driver_unregister(&driver->driver);
-}
-EXPORT_SYMBOL_GPL(cosm_unregister_driver);
-
-static inline void cosm_release_dev(struct device *d)
-{
-	struct cosm_device *cdev = dev_to_cosm(d);
-
-	kfree(cdev);
-}
-
-struct cosm_device *
-cosm_register_device(struct device *pdev, struct cosm_hw_ops *hw_ops)
-{
-	struct cosm_device *cdev;
-	int ret;
-
-	cdev = kzalloc(sizeof(*cdev), GFP_KERNEL);
-	if (!cdev)
-		return ERR_PTR(-ENOMEM);
-
-	cdev->dev.parent = pdev;
-	cdev->dev.release = cosm_release_dev;
-	cdev->hw_ops = hw_ops;
-	dev_set_drvdata(&cdev->dev, cdev);
-	cdev->dev.bus = &cosm_bus;
-
-	/* Assign a unique device index and hence name */
-	ret = ida_simple_get(&cosm_index_ida, 0, 0, GFP_KERNEL);
-	if (ret < 0)
-		goto free_cdev;
-
-	cdev->index = ret;
-	cdev->dev.id = ret;
-	dev_set_name(&cdev->dev, "cosm-dev%u", cdev->index);
-
-	ret = device_register(&cdev->dev);
-	if (ret)
-		goto ida_remove;
-	return cdev;
-ida_remove:
-	ida_simple_remove(&cosm_index_ida, cdev->index);
-free_cdev:
-	put_device(&cdev->dev);
-	return ERR_PTR(ret);
-}
-EXPORT_SYMBOL_GPL(cosm_register_device);
-
-void cosm_unregister_device(struct cosm_device *dev)
-{
-	int index = dev->index; /* save for after device release */
-
-	device_unregister(&dev->dev);
-	ida_simple_remove(&cosm_index_ida, index);
-}
-EXPORT_SYMBOL_GPL(cosm_unregister_device);
-
-struct cosm_device *cosm_find_cdev_by_id(int id)
-{
-	struct device *dev = subsys_find_device_by_id(&cosm_bus, id, NULL);
-
-	return dev ? container_of(dev, struct cosm_device, dev) : NULL;
-}
-EXPORT_SYMBOL_GPL(cosm_find_cdev_by_id);
-
-static int __init cosm_init(void)
-{
-	return bus_register(&cosm_bus);
-}
-
-static void __exit cosm_exit(void)
-{
-	bus_unregister(&cosm_bus);
-	ida_destroy(&cosm_index_ida);
-}
-
-core_initcall(cosm_init);
-module_exit(cosm_exit);
-
-MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Intel(R) MIC card OS state management bus driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/misc/mic/bus/cosm_bus.h b/drivers/misc/mic/bus/cosm_bus.h
deleted file mode 100644
index d50d7aea168d..000000000000
--- a/drivers/misc/mic/bus/cosm_bus.h
+++ /dev/null
@@ -1,125 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel MIC COSM Bus Driver
- */
-#ifndef _COSM_BUS_H_
-#define _COSM_BUS_H_
-
-#include <linux/scif.h>
-#include <linux/mic_common.h>
-#include "../common/mic_dev.h"
-
-/**
- * cosm_device - representation of a cosm device
- *
- * @attr_group: Pointer to list of sysfs attribute groups.
- * @sdev: Device for sysfs entries.
- * @state: MIC state.
- * @prev_state: MIC state previous to MIC_RESETTING
- * @shutdown_status: MIC status reported by card for shutdown/crashes.
- * @shutdown_status_int: Internal shutdown status maintained by the driver
- * @cosm_mutex: Mutex for synchronizing access to data structures.
- * @reset_trigger_work: Work for triggering reset requests.
- * @scif_work: Work for handling per device SCIF connections
- * @cmdline: Kernel command line.
- * @firmware: Firmware file name.
- * @ramdisk: Ramdisk file name.
- * @bootmode: Boot mode i.e. "linux" or "elf" for flash updates.
- * @log_buf_addr: Log buffer address for MIC.
- * @log_buf_len: Log buffer length address for MIC.
- * @state_sysfs: Sysfs dirent for notifying ring 3 about MIC state changes.
- * @hw_ops: the hardware bus ops for this device.
- * @dev: underlying device.
- * @index: unique position on the cosm bus
- * @dbg_dir: debug fs directory
- * @newepd: new endpoint from scif accept to be assigned to this cdev
- * @epd: SCIF endpoint for this cdev
- * @heartbeat_watchdog_enable: if heartbeat watchdog is enabled for this cdev
- * @sysfs_heartbeat_enable: sysfs setting for disabling heartbeat notification
- */
-struct cosm_device {
-	const struct attribute_group **attr_group;
-	struct device *sdev;
-	u8 state;
-	u8 prev_state;
-	u8 shutdown_status;
-	u8 shutdown_status_int;
-	struct mutex cosm_mutex;
-	struct work_struct reset_trigger_work;
-	struct work_struct scif_work;
-	char *cmdline;
-	char *firmware;
-	char *ramdisk;
-	char *bootmode;
-	void *log_buf_addr;
-	int *log_buf_len;
-	struct kernfs_node *state_sysfs;
-	struct cosm_hw_ops *hw_ops;
-	struct device dev;
-	int index;
-	struct dentry *dbg_dir;
-	scif_epd_t newepd;
-	scif_epd_t epd;
-	bool heartbeat_watchdog_enable;
-	bool sysfs_heartbeat_enable;
-};
-
-/**
- * cosm_driver - operations for a cosm driver
- *
- * @driver: underlying device driver (populate name and owner).
- * @probe: the function to call when a device is found.  Returns 0 or -errno.
- * @remove: the function to call when a device is removed.
- */
-struct cosm_driver {
-	struct device_driver driver;
-	int (*probe)(struct cosm_device *dev);
-	void (*remove)(struct cosm_device *dev);
-};
-
-/**
- * cosm_hw_ops - cosm bus ops
- *
- * @reset: trigger MIC reset
- * @force_reset: force MIC reset
- * @post_reset: inform MIC reset is complete
- * @ready: is MIC ready for OS download
- * @start: boot MIC
- * @stop: prepare MIC for reset
- * @family: return MIC HW family string
- * @stepping: return MIC HW stepping string
- * @aper: return MIC PCIe aperture
- */
-struct cosm_hw_ops {
-	void (*reset)(struct cosm_device *cdev);
-	void (*force_reset)(struct cosm_device *cdev);
-	void (*post_reset)(struct cosm_device *cdev, enum mic_states state);
-	bool (*ready)(struct cosm_device *cdev);
-	int (*start)(struct cosm_device *cdev, int id);
-	void (*stop)(struct cosm_device *cdev, bool force);
-	ssize_t (*family)(struct cosm_device *cdev, char *buf);
-	ssize_t (*stepping)(struct cosm_device *cdev, char *buf);
-	struct mic_mw *(*aper)(struct cosm_device *cdev);
-};
-
-struct cosm_device *
-cosm_register_device(struct device *pdev, struct cosm_hw_ops *hw_ops);
-void cosm_unregister_device(struct cosm_device *dev);
-int cosm_register_driver(struct cosm_driver *drv);
-void cosm_unregister_driver(struct cosm_driver *drv);
-struct cosm_device *cosm_find_cdev_by_id(int id);
-
-static inline struct cosm_device *dev_to_cosm(struct device *dev)
-{
-	return container_of(dev, struct cosm_device, dev);
-}
-
-static inline struct cosm_driver *drv_to_cosm(struct device_driver *drv)
-{
-	return container_of(drv, struct cosm_driver, driver);
-}
-#endif /* _COSM_BUS_H */
diff --git a/drivers/misc/mic/bus/mic_bus.c b/drivers/misc/mic/bus/mic_bus.c
deleted file mode 100644
index a08cb29692a8..000000000000
--- a/drivers/misc/mic/bus/mic_bus.c
+++ /dev/null
@@ -1,194 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel MIC Bus driver.
- *
- * This implementation is very similar to the the virtio bus driver
- * implementation @ drivers/virtio/virtio.c
- */
-#include <linux/dma-map-ops.h>
-#include <linux/slab.h>
-#include <linux/module.h>
-#include <linux/idr.h>
-#include <linux/mic_bus.h>
-
-static ssize_t device_show(struct device *d,
-			   struct device_attribute *attr, char *buf)
-{
-	struct mbus_device *dev = dev_to_mbus(d);
-	return sprintf(buf, "0x%04x\n", dev->id.device);
-}
-static DEVICE_ATTR_RO(device);
-
-static ssize_t vendor_show(struct device *d,
-			   struct device_attribute *attr, char *buf)
-{
-	struct mbus_device *dev = dev_to_mbus(d);
-	return sprintf(buf, "0x%04x\n", dev->id.vendor);
-}
-static DEVICE_ATTR_RO(vendor);
-
-static ssize_t modalias_show(struct device *d,
-			     struct device_attribute *attr, char *buf)
-{
-	struct mbus_device *dev = dev_to_mbus(d);
-	return sprintf(buf, "mbus:d%08Xv%08X\n",
-		       dev->id.device, dev->id.vendor);
-}
-static DEVICE_ATTR_RO(modalias);
-
-static struct attribute *mbus_dev_attrs[] = {
-	&dev_attr_device.attr,
-	&dev_attr_vendor.attr,
-	&dev_attr_modalias.attr,
-	NULL,
-};
-ATTRIBUTE_GROUPS(mbus_dev);
-
-static inline int mbus_id_match(const struct mbus_device *dev,
-				const struct mbus_device_id *id)
-{
-	if (id->device != dev->id.device && id->device != MBUS_DEV_ANY_ID)
-		return 0;
-
-	return id->vendor == MBUS_DEV_ANY_ID || id->vendor == dev->id.vendor;
-}
-
-/*
- * This looks through all the IDs a driver claims to support.  If any of them
- * match, we return 1 and the kernel will call mbus_dev_probe().
- */
-static int mbus_dev_match(struct device *dv, struct device_driver *dr)
-{
-	unsigned int i;
-	struct mbus_device *dev = dev_to_mbus(dv);
-	const struct mbus_device_id *ids;
-
-	ids = drv_to_mbus(dr)->id_table;
-	for (i = 0; ids[i].device; i++)
-		if (mbus_id_match(dev, &ids[i]))
-			return 1;
-	return 0;
-}
-
-static int mbus_uevent(struct device *dv, struct kobj_uevent_env *env)
-{
-	struct mbus_device *dev = dev_to_mbus(dv);
-
-	return add_uevent_var(env, "MODALIAS=mbus:d%08Xv%08X",
-			      dev->id.device, dev->id.vendor);
-}
-
-static int mbus_dev_probe(struct device *d)
-{
-	int err;
-	struct mbus_device *dev = dev_to_mbus(d);
-	struct mbus_driver *drv = drv_to_mbus(dev->dev.driver);
-
-	err = drv->probe(dev);
-	if (!err)
-		if (drv->scan)
-			drv->scan(dev);
-	return err;
-}
-
-static int mbus_dev_remove(struct device *d)
-{
-	struct mbus_device *dev = dev_to_mbus(d);
-	struct mbus_driver *drv = drv_to_mbus(dev->dev.driver);
-
-	drv->remove(dev);
-	return 0;
-}
-
-static struct bus_type mic_bus = {
-	.name  = "mic_bus",
-	.match = mbus_dev_match,
-	.dev_groups = mbus_dev_groups,
-	.uevent = mbus_uevent,
-	.probe = mbus_dev_probe,
-	.remove = mbus_dev_remove,
-};
-
-int mbus_register_driver(struct mbus_driver *driver)
-{
-	driver->driver.bus = &mic_bus;
-	return driver_register(&driver->driver);
-}
-EXPORT_SYMBOL_GPL(mbus_register_driver);
-
-void mbus_unregister_driver(struct mbus_driver *driver)
-{
-	driver_unregister(&driver->driver);
-}
-EXPORT_SYMBOL_GPL(mbus_unregister_driver);
-
-static void mbus_release_dev(struct device *d)
-{
-	struct mbus_device *mbdev = dev_to_mbus(d);
-	kfree(mbdev);
-}
-
-struct mbus_device *
-mbus_register_device(struct device *pdev, int id, const struct dma_map_ops *dma_ops,
-		     struct mbus_hw_ops *hw_ops, int index,
-		     void __iomem *mmio_va)
-{
-	int ret;
-	struct mbus_device *mbdev;
-
-	mbdev = kzalloc(sizeof(*mbdev), GFP_KERNEL);
-	if (!mbdev)
-		return ERR_PTR(-ENOMEM);
-
-	mbdev->mmio_va = mmio_va;
-	mbdev->dev.parent = pdev;
-	mbdev->id.device = id;
-	mbdev->id.vendor = MBUS_DEV_ANY_ID;
-	mbdev->dev.dma_ops = dma_ops;
-	mbdev->dev.dma_mask = &mbdev->dev.coherent_dma_mask;
-	dma_set_mask(&mbdev->dev, DMA_BIT_MASK(64));
-	mbdev->dev.release = mbus_release_dev;
-	mbdev->hw_ops = hw_ops;
-	mbdev->dev.bus = &mic_bus;
-	mbdev->index = index;
-	dev_set_name(&mbdev->dev, "mbus-dev%u", mbdev->index);
-	/*
-	 * device_register() causes the bus infrastructure to look for a
-	 * matching driver.
-	 */
-	ret = device_register(&mbdev->dev);
-	if (ret)
-		goto free_mbdev;
-	return mbdev;
-free_mbdev:
-	put_device(&mbdev->dev);
-	return ERR_PTR(ret);
-}
-EXPORT_SYMBOL_GPL(mbus_register_device);
-
-void mbus_unregister_device(struct mbus_device *mbdev)
-{
-	device_unregister(&mbdev->dev);
-}
-EXPORT_SYMBOL_GPL(mbus_unregister_device);
-
-static int __init mbus_init(void)
-{
-	return bus_register(&mic_bus);
-}
-
-static void __exit mbus_exit(void)
-{
-	bus_unregister(&mic_bus);
-}
-
-core_initcall(mbus_init);
-module_exit(mbus_exit);
-
-MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Intel(R) MIC Bus driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/misc/mic/bus/scif_bus.c b/drivers/misc/mic/bus/scif_bus.c
deleted file mode 100644
index ad7c3604f151..000000000000
--- a/drivers/misc/mic/bus/scif_bus.c
+++ /dev/null
@@ -1,201 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel Symmetric Communications Interface Bus driver.
- */
-#include <linux/slab.h>
-#include <linux/module.h>
-#include <linux/idr.h>
-#include <linux/dma-map-ops.h>
-
-#include "scif_bus.h"
-
-static ssize_t device_show(struct device *d,
-			   struct device_attribute *attr, char *buf)
-{
-	struct scif_hw_dev *dev = dev_to_scif(d);
-
-	return sprintf(buf, "0x%04x\n", dev->id.device);
-}
-static DEVICE_ATTR_RO(device);
-
-static ssize_t vendor_show(struct device *d,
-			   struct device_attribute *attr, char *buf)
-{
-	struct scif_hw_dev *dev = dev_to_scif(d);
-
-	return sprintf(buf, "0x%04x\n", dev->id.vendor);
-}
-static DEVICE_ATTR_RO(vendor);
-
-static ssize_t modalias_show(struct device *d,
-			     struct device_attribute *attr, char *buf)
-{
-	struct scif_hw_dev *dev = dev_to_scif(d);
-
-	return sprintf(buf, "scif:d%08Xv%08X\n",
-		       dev->id.device, dev->id.vendor);
-}
-static DEVICE_ATTR_RO(modalias);
-
-static struct attribute *scif_dev_attrs[] = {
-	&dev_attr_device.attr,
-	&dev_attr_vendor.attr,
-	&dev_attr_modalias.attr,
-	NULL,
-};
-ATTRIBUTE_GROUPS(scif_dev);
-
-static inline int scif_id_match(const struct scif_hw_dev *dev,
-				const struct scif_hw_dev_id *id)
-{
-	if (id->device != dev->id.device && id->device != SCIF_DEV_ANY_ID)
-		return 0;
-
-	return id->vendor == SCIF_DEV_ANY_ID || id->vendor == dev->id.vendor;
-}
-
-/*
- * This looks through all the IDs a driver claims to support.  If any of them
- * match, we return 1 and the kernel will call scif_dev_probe().
- */
-static int scif_dev_match(struct device *dv, struct device_driver *dr)
-{
-	unsigned int i;
-	struct scif_hw_dev *dev = dev_to_scif(dv);
-	const struct scif_hw_dev_id *ids;
-
-	ids = drv_to_scif(dr)->id_table;
-	for (i = 0; ids[i].device; i++)
-		if (scif_id_match(dev, &ids[i]))
-			return 1;
-	return 0;
-}
-
-static int scif_uevent(struct device *dv, struct kobj_uevent_env *env)
-{
-	struct scif_hw_dev *dev = dev_to_scif(dv);
-
-	return add_uevent_var(env, "MODALIAS=scif:d%08Xv%08X",
-			      dev->id.device, dev->id.vendor);
-}
-
-static int scif_dev_probe(struct device *d)
-{
-	struct scif_hw_dev *dev = dev_to_scif(d);
-	struct scif_driver *drv = drv_to_scif(dev->dev.driver);
-
-	return drv->probe(dev);
-}
-
-static int scif_dev_remove(struct device *d)
-{
-	struct scif_hw_dev *dev = dev_to_scif(d);
-	struct scif_driver *drv = drv_to_scif(dev->dev.driver);
-
-	drv->remove(dev);
-	return 0;
-}
-
-static struct bus_type scif_bus = {
-	.name  = "scif_bus",
-	.match = scif_dev_match,
-	.dev_groups = scif_dev_groups,
-	.uevent = scif_uevent,
-	.probe = scif_dev_probe,
-	.remove = scif_dev_remove,
-};
-
-int scif_register_driver(struct scif_driver *driver)
-{
-	driver->driver.bus = &scif_bus;
-	return driver_register(&driver->driver);
-}
-EXPORT_SYMBOL_GPL(scif_register_driver);
-
-void scif_unregister_driver(struct scif_driver *driver)
-{
-	driver_unregister(&driver->driver);
-}
-EXPORT_SYMBOL_GPL(scif_unregister_driver);
-
-static void scif_release_dev(struct device *d)
-{
-	struct scif_hw_dev *sdev = dev_to_scif(d);
-
-	kfree(sdev);
-}
-
-struct scif_hw_dev *
-scif_register_device(struct device *pdev, int id, const struct dma_map_ops *dma_ops,
-		     struct scif_hw_ops *hw_ops, u8 dnode, u8 snode,
-		     struct mic_mw *mmio, struct mic_mw *aper, void *dp,
-		     void __iomem *rdp, struct dma_chan **chan, int num_chan,
-		     bool card_rel_da)
-{
-	int ret;
-	struct scif_hw_dev *sdev;
-
-	sdev = kzalloc(sizeof(*sdev), GFP_KERNEL);
-	if (!sdev)
-		return ERR_PTR(-ENOMEM);
-
-	sdev->dev.parent = pdev;
-	sdev->id.device = id;
-	sdev->id.vendor = SCIF_DEV_ANY_ID;
-	sdev->dev.dma_ops = dma_ops;
-	sdev->dev.release = scif_release_dev;
-	sdev->hw_ops = hw_ops;
-	sdev->dnode = dnode;
-	sdev->snode = snode;
-	dev_set_drvdata(&sdev->dev, sdev);
-	sdev->dev.bus = &scif_bus;
-	sdev->mmio = mmio;
-	sdev->aper = aper;
-	sdev->dp = dp;
-	sdev->rdp = rdp;
-	sdev->dev.dma_mask = &sdev->dev.coherent_dma_mask;
-	dma_set_mask(&sdev->dev, DMA_BIT_MASK(64));
-	sdev->dma_ch = chan;
-	sdev->num_dma_ch = num_chan;
-	sdev->card_rel_da = card_rel_da;
-	dev_set_name(&sdev->dev, "scif-dev%u", sdev->dnode);
-	/*
-	 * device_register() causes the bus infrastructure to look for a
-	 * matching driver.
-	 */
-	ret = device_register(&sdev->dev);
-	if (ret)
-		goto free_sdev;
-	return sdev;
-free_sdev:
-	put_device(&sdev->dev);
-	return ERR_PTR(ret);
-}
-EXPORT_SYMBOL_GPL(scif_register_device);
-
-void scif_unregister_device(struct scif_hw_dev *sdev)
-{
-	device_unregister(&sdev->dev);
-}
-EXPORT_SYMBOL_GPL(scif_unregister_device);
-
-static int __init scif_init(void)
-{
-	return bus_register(&scif_bus);
-}
-
-static void __exit scif_exit(void)
-{
-	bus_unregister(&scif_bus);
-}
-
-core_initcall(scif_init);
-module_exit(scif_exit);
-
-MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Intel(R) SCIF Bus driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/misc/mic/bus/scif_bus.h b/drivers/misc/mic/bus/scif_bus.h
deleted file mode 100644
index 4981eb56f879..000000000000
--- a/drivers/misc/mic/bus/scif_bus.h
+++ /dev/null
@@ -1,125 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel Symmetric Communications Interface Bus driver.
- */
-#ifndef _SCIF_BUS_H_
-#define _SCIF_BUS_H_
-/*
- * Everything a scif driver needs to work with any particular scif
- * hardware abstraction layer.
- */
-#include <linux/dma-map-ops.h>
-
-#include <linux/mic_common.h>
-#include "../common/mic_dev.h"
-
-struct scif_hw_dev_id {
-	u32 device;
-	u32 vendor;
-};
-
-#define MIC_SCIF_DEV 1
-#define SCIF_DEV_ANY_ID 0xffffffff
-
-/**
- * scif_hw_dev - representation of a hardware device abstracted for scif
- * @hw_ops: the hardware ops supported by this device
- * @id: the device type identification (used to match it with a driver)
- * @mmio: MMIO memory window
- * @aper: Aperture memory window
- * @dev: underlying device
- * @dnode - The destination node which this device will communicate with.
- * @snode - The source node for this device.
- * @dp - Self device page
- * @rdp - Remote device page
- * @dma_ch - Array of DMA channels
- * @num_dma_ch - Number of DMA channels available
- * @card_rel_da - Set to true if DMA addresses programmed in the DMA engine
- *		are relative to the card point of view
- */
-struct scif_hw_dev {
-	struct scif_hw_ops *hw_ops;
-	struct scif_hw_dev_id id;
-	struct mic_mw *mmio;
-	struct mic_mw *aper;
-	struct device dev;
-	u8 dnode;
-	u8 snode;
-	void *dp;
-	void __iomem *rdp;
-	struct dma_chan **dma_ch;
-	int num_dma_ch;
-	bool card_rel_da;
-};
-
-/**
- * scif_driver - operations for a scif I/O driver
- * @driver: underlying device driver (populate name and owner).
- * @id_table: the ids serviced by this driver.
- * @probe: the function to call when a device is found.  Returns 0 or -errno.
- * @remove: the function to call when a device is removed.
- */
-struct scif_driver {
-	struct device_driver driver;
-	const struct scif_hw_dev_id *id_table;
-	int (*probe)(struct scif_hw_dev *dev);
-	void (*remove)(struct scif_hw_dev *dev);
-};
-
-/**
- * scif_hw_ops - Hardware operations for accessing a SCIF device on the SCIF bus.
- *
- * @next_db: Obtain the next available doorbell.
- * @request_irq: Request an interrupt on a particular doorbell.
- * @free_irq: Free an interrupt requested previously.
- * @ack_interrupt: acknowledge an interrupt in the ISR.
- * @send_intr: Send an interrupt to the remote node on a specified doorbell.
- * @send_p2p_intr: Send an interrupt to the peer node on a specified doorbell
- * which is specifically targeted for a peer to peer node.
- * @remap: Map a buffer with the specified physical address and length.
- * @unmap: Unmap a buffer previously mapped.
- */
-struct scif_hw_ops {
-	int (*next_db)(struct scif_hw_dev *sdev);
-	struct mic_irq * (*request_irq)(struct scif_hw_dev *sdev,
-					irqreturn_t (*func)(int irq,
-							    void *data),
-					const char *name, void *data,
-					int db);
-	void (*free_irq)(struct scif_hw_dev *sdev,
-			 struct mic_irq *cookie, void *data);
-	void (*ack_interrupt)(struct scif_hw_dev *sdev, int num);
-	void (*send_intr)(struct scif_hw_dev *sdev, int db);
-	void (*send_p2p_intr)(struct scif_hw_dev *sdev, int db,
-			      struct mic_mw *mw);
-	void __iomem * (*remap)(struct scif_hw_dev *sdev,
-				  phys_addr_t pa, size_t len);
-	void (*unmap)(struct scif_hw_dev *sdev, void __iomem *va);
-};
-
-int scif_register_driver(struct scif_driver *driver);
-void scif_unregister_driver(struct scif_driver *driver);
-struct scif_hw_dev *
-scif_register_device(struct device *pdev, int id,
-		     const struct dma_map_ops *dma_ops,
-		     struct scif_hw_ops *hw_ops, u8 dnode, u8 snode,
-		     struct mic_mw *mmio, struct mic_mw *aper,
-		     void *dp, void __iomem *rdp,
-		     struct dma_chan **chan, int num_chan,
-		     bool card_rel_da);
-void scif_unregister_device(struct scif_hw_dev *sdev);
-
-static inline struct scif_hw_dev *dev_to_scif(struct device *dev)
-{
-	return container_of(dev, struct scif_hw_dev, dev);
-}
-
-static inline struct scif_driver *drv_to_scif(struct device_driver *drv)
-{
-	return container_of(drv, struct scif_driver, driver);
-}
-#endif /* _SCIF_BUS_H */
diff --git a/drivers/misc/mic/bus/vop_bus.c b/drivers/misc/mic/bus/vop_bus.c
deleted file mode 100644
index 6935ddca1bd5..000000000000
--- a/drivers/misc/mic/bus/vop_bus.c
+++ /dev/null
@@ -1,194 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Intel Virtio Over PCIe (VOP) Bus driver.
- */
-#include <linux/slab.h>
-#include <linux/module.h>
-#include <linux/idr.h>
-#include <linux/dma-map-ops.h>
-
-#include "vop_bus.h"
-
-static ssize_t device_show(struct device *d,
-			   struct device_attribute *attr, char *buf)
-{
-	struct vop_device *dev = dev_to_vop(d);
-
-	return sprintf(buf, "0x%04x\n", dev->id.device);
-}
-static DEVICE_ATTR_RO(device);
-
-static ssize_t vendor_show(struct device *d,
-			   struct device_attribute *attr, char *buf)
-{
-	struct vop_device *dev = dev_to_vop(d);
-
-	return sprintf(buf, "0x%04x\n", dev->id.vendor);
-}
-static DEVICE_ATTR_RO(vendor);
-
-static ssize_t modalias_show(struct device *d,
-			     struct device_attribute *attr, char *buf)
-{
-	struct vop_device *dev = dev_to_vop(d);
-
-	return sprintf(buf, "vop:d%08Xv%08X\n",
-		       dev->id.device, dev->id.vendor);
-}
-static DEVICE_ATTR_RO(modalias);
-
-static struct attribute *vop_dev_attrs[] = {
-	&dev_attr_device.attr,
-	&dev_attr_vendor.attr,
-	&dev_attr_modalias.attr,
-	NULL,
-};
-ATTRIBUTE_GROUPS(vop_dev);
-
-static inline int vop_id_match(const struct vop_device *dev,
-			       const struct vop_device_id *id)
-{
-	if (id->device != dev->id.device && id->device != VOP_DEV_ANY_ID)
-		return 0;
-
-	return id->vendor == VOP_DEV_ANY_ID || id->vendor == dev->id.vendor;
-}
-
-/*
- * This looks through all the IDs a driver claims to support.  If any of them
- * match, we return 1 and the kernel will call vop_dev_probe().
- */
-static int vop_dev_match(struct device *dv, struct device_driver *dr)
-{
-	unsigned int i;
-	struct vop_device *dev = dev_to_vop(dv);
-	const struct vop_device_id *ids;
-
-	ids = drv_to_vop(dr)->id_table;
-	for (i = 0; ids[i].device; i++)
-		if (vop_id_match(dev, &ids[i]))
-			return 1;
-	return 0;
-}
-
-static int vop_uevent(struct device *dv, struct kobj_uevent_env *env)
-{
-	struct vop_device *dev = dev_to_vop(dv);
-
-	return add_uevent_var(env, "MODALIAS=vop:d%08Xv%08X",
-			      dev->id.device, dev->id.vendor);
-}
-
-static int vop_dev_probe(struct device *d)
-{
-	struct vop_device *dev = dev_to_vop(d);
-	struct vop_driver *drv = drv_to_vop(dev->dev.driver);
-
-	return drv->probe(dev);
-}
-
-static int vop_dev_remove(struct device *d)
-{
-	struct vop_device *dev = dev_to_vop(d);
-	struct vop_driver *drv = drv_to_vop(dev->dev.driver);
-
-	drv->remove(dev);
-	return 0;
-}
-
-static struct bus_type vop_bus = {
-	.name  = "vop_bus",
-	.match = vop_dev_match,
-	.dev_groups = vop_dev_groups,
-	.uevent = vop_uevent,
-	.probe = vop_dev_probe,
-	.remove = vop_dev_remove,
-};
-
-int vop_register_driver(struct vop_driver *driver)
-{
-	driver->driver.bus = &vop_bus;
-	return driver_register(&driver->driver);
-}
-EXPORT_SYMBOL_GPL(vop_register_driver);
-
-void vop_unregister_driver(struct vop_driver *driver)
-{
-	driver_unregister(&driver->driver);
-}
-EXPORT_SYMBOL_GPL(vop_unregister_driver);
-
-static void vop_release_dev(struct device *d)
-{
-	struct vop_device *dev = dev_to_vop(d);
-
-	kfree(dev);
-}
-
-struct vop_device *
-vop_register_device(struct device *pdev, int id,
-		    const struct dma_map_ops *dma_ops,
-		    struct vop_hw_ops *hw_ops, u8 dnode, struct mic_mw *aper,
-		    struct dma_chan *chan)
-{
-	int ret;
-	struct vop_device *vdev;
-
-	vdev = kzalloc(sizeof(*vdev), GFP_KERNEL);
-	if (!vdev)
-		return ERR_PTR(-ENOMEM);
-
-	vdev->dev.parent = pdev;
-	vdev->id.device = id;
-	vdev->id.vendor = VOP_DEV_ANY_ID;
-	vdev->dev.dma_ops = dma_ops;
-	vdev->dev.dma_mask = &vdev->dev.coherent_dma_mask;
-	dma_set_mask(&vdev->dev, DMA_BIT_MASK(64));
-	vdev->dev.release = vop_release_dev;
-	vdev->hw_ops = hw_ops;
-	vdev->dev.bus = &vop_bus;
-	vdev->dnode = dnode;
-	vdev->aper = aper;
-	vdev->dma_ch = chan;
-	vdev->index = dnode - 1;
-	dev_set_name(&vdev->dev, "vop-dev%u", vdev->index);
-	/*
-	 * device_register() causes the bus infrastructure to look for a
-	 * matching driver.
-	 */
-	ret = device_register(&vdev->dev);
-	if (ret)
-		goto free_vdev;
-	return vdev;
-free_vdev:
-	put_device(&vdev->dev);
-	return ERR_PTR(ret);
-}
-EXPORT_SYMBOL_GPL(vop_register_device);
-
-void vop_unregister_device(struct vop_device *dev)
-{
-	device_unregister(&dev->dev);
-}
-EXPORT_SYMBOL_GPL(vop_unregister_device);
-
-static int __init vop_init(void)
-{
-	return bus_register(&vop_bus);
-}
-
-static void __exit vop_exit(void)
-{
-	bus_unregister(&vop_bus);
-}
-
-core_initcall(vop_init);
-module_exit(vop_exit);
-
-MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Intel(R) VOP Bus driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/misc/mic/bus/vop_bus.h b/drivers/misc/mic/bus/vop_bus.h
deleted file mode 100644
index 4fa02808c1e2..000000000000
--- a/drivers/misc/mic/bus/vop_bus.h
+++ /dev/null
@@ -1,129 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Intel Virtio over PCIe Bus driver.
- */
-#ifndef _VOP_BUS_H_
-#define _VOP_BUS_H_
-/*
- * Everything a vop driver needs to work with any particular vop
- * implementation.
- */
-#include <linux/dmaengine.h>
-#include <linux/interrupt.h>
-
-#include "../common/mic_dev.h"
-
-struct vop_device_id {
-	u32 device;
-	u32 vendor;
-};
-
-#define VOP_DEV_TRNSP 1
-#define VOP_DEV_ANY_ID 0xffffffff
-/*
- * Size of the internal buffer used during DMA's as an intermediate buffer
- * for copy to/from user. Must be an integral number of pages.
- */
-#define VOP_INT_DMA_BUF_SIZE PAGE_ALIGN(64 * 1024ULL)
-
-/**
- * vop_device - representation of a device using vop
- * @hw_ops: the hardware ops supported by this device.
- * @id: the device type identification (used to match it with a driver).
- * @dev: underlying device.
- * @dnode - The destination node which this device will communicate with.
- * @aper: Aperture memory window
- * @dma_ch - DMA channel
- * @index: unique position on the vop bus
- */
-struct vop_device {
-	struct vop_hw_ops *hw_ops;
-	struct vop_device_id id;
-	struct device dev;
-	u8 dnode;
-	struct mic_mw *aper;
-	struct dma_chan *dma_ch;
-	int index;
-};
-
-/**
- * vop_driver - operations for a vop I/O driver
- * @driver: underlying device driver (populate name and owner).
- * @id_table: the ids serviced by this driver.
- * @probe: the function to call when a device is found.  Returns 0 or -errno.
- * @remove: the function to call when a device is removed.
- */
-struct vop_driver {
-	struct device_driver driver;
-	const struct vop_device_id *id_table;
-	int (*probe)(struct vop_device *dev);
-	void (*remove)(struct vop_device *dev);
-};
-
-/**
- * vop_hw_ops - Hardware operations for accessing a VOP device on the VOP bus.
- *
- * @next_db: Obtain the next available doorbell.
- * @request_irq: Request an interrupt on a particular doorbell.
- * @free_irq: Free an interrupt requested previously.
- * @ack_interrupt: acknowledge an interrupt in the ISR.
- * @get_remote_dp: Get access to the virtio device page used by the remote
- *                 node to add/remove/configure virtio devices.
- * @get_dp: Get access to the virtio device page used by the self
- *          node to add/remove/configure virtio devices.
- * @send_intr: Send an interrupt to the peer node on a specified doorbell.
- * @remap: Map a buffer with the specified DMA address and length.
- * @unmap: Unmap a buffer previously mapped.
- * @dma_filter: The DMA filter function to use for obtaining access to
- *		a DMA channel on the peer node.
- */
-struct vop_hw_ops {
-	int (*next_db)(struct vop_device *vpdev);
-	struct mic_irq *(*request_irq)(struct vop_device *vpdev,
-				       irqreturn_t (*func)(int irq, void *data),
-				       const char *name, void *data,
-				       int intr_src);
-	void (*free_irq)(struct vop_device *vpdev,
-			 struct mic_irq *cookie, void *data);
-	void (*ack_interrupt)(struct vop_device *vpdev, int num);
-	void __iomem * (*get_remote_dp)(struct vop_device *vpdev);
-	void * (*get_dp)(struct vop_device *vpdev);
-	void (*send_intr)(struct vop_device *vpdev, int db);
-	void __iomem * (*remap)(struct vop_device *vpdev,
-				  dma_addr_t pa, size_t len);
-	void (*unmap)(struct vop_device *vpdev, void __iomem *va);
-};
-
-struct vop_device *
-vop_register_device(struct device *pdev, int id,
-		    const struct dma_map_ops *dma_ops,
-		    struct vop_hw_ops *hw_ops, u8 dnode, struct mic_mw *aper,
-		    struct dma_chan *chan);
-void vop_unregister_device(struct vop_device *dev);
-int vop_register_driver(struct vop_driver *drv);
-void vop_unregister_driver(struct vop_driver *drv);
-
-/*
- * module_vop_driver() - Helper macro for drivers that don't do
- * anything special in module init/exit.  This eliminates a lot of
- * boilerplate.  Each module may only use this macro once, and
- * calling it replaces module_init() and module_exit()
- */
-#define module_vop_driver(__vop_driver) \
-	module_driver(__vop_driver, vop_register_driver, \
-			vop_unregister_driver)
-
-static inline struct vop_device *dev_to_vop(struct device *dev)
-{
-	return container_of(dev, struct vop_device, dev);
-}
-
-static inline struct vop_driver *drv_to_vop(struct device_driver *drv)
-{
-	return container_of(drv, struct vop_driver, driver);
-}
-#endif /* _VOP_BUS_H */
diff --git a/drivers/misc/mic/card/Makefile b/drivers/misc/mic/card/Makefile
deleted file mode 100644
index 921a7e7e0fbd..000000000000
--- a/drivers/misc/mic/card/Makefile
+++ /dev/null
@@ -1,11 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-#
-# Makefile - Intel MIC Linux driver.
-# Copyright(c) 2013, Intel Corporation.
-#
-ccflags-y += -DINTEL_MIC_CARD
-
-obj-$(CONFIG_INTEL_MIC_CARD) += mic_card.o
-mic_card-y += mic_x100.o
-mic_card-y += mic_device.o
-mic_card-y += mic_debugfs.o
diff --git a/drivers/misc/mic/card/mic_debugfs.c b/drivers/misc/mic/card/mic_debugfs.c
deleted file mode 100644
index 4c326e8f4d99..000000000000
--- a/drivers/misc/mic/card/mic_debugfs.c
+++ /dev/null
@@ -1,85 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Disclaimer: The codes contained in these modules may be specific to
- * the Intel Software Development Platform codenamed: Knights Ferry, and
- * the Intel product codenamed: Knights Corner, and are not backward
- * compatible with other Intel products. Additionally, Intel will NOT
- * support the codes or instruction set in future products.
- *
- * Intel MIC Card driver.
- */
-#include <linux/debugfs.h>
-#include <linux/delay.h>
-#include <linux/seq_file.h>
-#include <linux/interrupt.h>
-#include <linux/device.h>
-
-#include "../common/mic_dev.h"
-#include "mic_device.h"
-
-/* Debugfs parent dir */
-static struct dentry *mic_dbg;
-
-/*
- * mic_intr_show - Send interrupts to host.
- */
-static int mic_intr_show(struct seq_file *s, void *unused)
-{
-	struct mic_driver *mdrv = s->private;
-	struct mic_device *mdev = &mdrv->mdev;
-
-	mic_send_intr(mdev, 0);
-	msleep(1000);
-	mic_send_intr(mdev, 1);
-	msleep(1000);
-	mic_send_intr(mdev, 2);
-	msleep(1000);
-	mic_send_intr(mdev, 3);
-	msleep(1000);
-
-	return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(mic_intr);
-
-/*
- * mic_create_card_debug_dir - Initialize MIC debugfs entries.
- */
-void __init mic_create_card_debug_dir(struct mic_driver *mdrv)
-{
-	if (!mic_dbg)
-		return;
-
-	mdrv->dbg_dir = debugfs_create_dir(mdrv->name, mic_dbg);
-
-	debugfs_create_file("intr_test", 0444, mdrv->dbg_dir, mdrv,
-			    &mic_intr_fops);
-}
-
-/*
- * mic_delete_card_debug_dir - Uninitialize MIC debugfs entries.
- */
-void mic_delete_card_debug_dir(struct mic_driver *mdrv)
-{
-	debugfs_remove_recursive(mdrv->dbg_dir);
-}
-
-/*
- * mic_init_card_debugfs - Initialize global debugfs entry.
- */
-void __init mic_init_card_debugfs(void)
-{
-	mic_dbg = debugfs_create_dir(KBUILD_MODNAME, NULL);
-}
-
-/*
- * mic_exit_card_debugfs - Uninitialize global debugfs entry
- */
-void mic_exit_card_debugfs(void)
-{
-	debugfs_remove(mic_dbg);
-}
diff --git a/drivers/misc/mic/card/mic_device.c b/drivers/misc/mic/card/mic_device.c
deleted file mode 100644
index a15606259bdc..000000000000
--- a/drivers/misc/mic/card/mic_device.c
+++ /dev/null
@@ -1,417 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Disclaimer: The codes contained in these modules may be specific to
- * the Intel Software Development Platform codenamed: Knights Ferry, and
- * the Intel product codenamed: Knights Corner, and are not backward
- * compatible with other Intel products. Additionally, Intel will NOT
- * support the codes or instruction set in future products.
- *
- * Intel MIC Card driver.
- */
-#include <linux/module.h>
-#include <linux/pci.h>
-#include <linux/interrupt.h>
-#include <linux/reboot.h>
-#include <linux/dmaengine.h>
-#include <linux/kmod.h>
-
-#include <linux/mic_common.h>
-#include "../common/mic_dev.h"
-#include "mic_device.h"
-
-static struct mic_driver *g_drv;
-
-static int __init mic_dp_init(void)
-{
-	struct mic_driver *mdrv = g_drv;
-	struct mic_device *mdev = &mdrv->mdev;
-	struct mic_bootparam __iomem *bootparam;
-	u64 lo, hi, dp_dma_addr;
-	u32 magic;
-
-	lo = mic_read_spad(&mdrv->mdev, MIC_DPLO_SPAD);
-	hi = mic_read_spad(&mdrv->mdev, MIC_DPHI_SPAD);
-
-	dp_dma_addr = lo | (hi << 32);
-	mdrv->dp = mic_card_map(mdev, dp_dma_addr, MIC_DP_SIZE);
-	if (!mdrv->dp) {
-		dev_err(mdrv->dev, "Cannot remap Aperture BAR\n");
-		return -ENOMEM;
-	}
-	bootparam = mdrv->dp;
-	magic = ioread32(&bootparam->magic);
-	if (MIC_MAGIC != magic) {
-		dev_err(mdrv->dev, "bootparam magic mismatch 0x%x\n", magic);
-		return -EIO;
-	}
-	return 0;
-}
-
-/* Uninitialize the device page */
-static void mic_dp_uninit(void)
-{
-	mic_card_unmap(&g_drv->mdev, g_drv->dp);
-}
-
-/**
- * mic_request_card_irq - request an irq.
- *
- * @handler: interrupt handler passed to request_threaded_irq.
- * @thread_fn: thread fn. passed to request_threaded_irq.
- * @name: The ASCII name of the callee requesting the irq.
- * @data: private data that is returned back when calling the
- * function handler.
- * @index: The doorbell index of the requester.
- *
- * returns: The cookie that is transparent to the caller. Passed
- * back when calling mic_free_irq. An appropriate error code
- * is returned on failure. Caller needs to use IS_ERR(return_val)
- * to check for failure and PTR_ERR(return_val) to obtained the
- * error code.
- *
- */
-struct mic_irq *
-mic_request_card_irq(irq_handler_t handler,
-		     irq_handler_t thread_fn, const char *name,
-		     void *data, int index)
-{
-	int rc = 0;
-	unsigned long cookie;
-	struct mic_driver *mdrv = g_drv;
-
-	rc  = request_threaded_irq(mic_db_to_irq(mdrv, index), handler,
-				   thread_fn, 0, name, data);
-	if (rc) {
-		dev_err(mdrv->dev, "request_threaded_irq failed rc = %d\n", rc);
-		goto err;
-	}
-	mdrv->irq_info.irq_usage_count[index]++;
-	cookie = index;
-	return (struct mic_irq *)cookie;
-err:
-	return ERR_PTR(rc);
-}
-
-/**
- * mic_free_card_irq - free irq.
- *
- * @cookie: cookie obtained during a successful call to mic_request_threaded_irq
- * @data: private data specified by the calling function during the
- * mic_request_threaded_irq
- *
- * returns: none.
- */
-void mic_free_card_irq(struct mic_irq *cookie, void *data)
-{
-	int index;
-	struct mic_driver *mdrv = g_drv;
-
-	index = (unsigned long)cookie & 0xFFFFU;
-	free_irq(mic_db_to_irq(mdrv, index), data);
-	mdrv->irq_info.irq_usage_count[index]--;
-}
-
-/**
- * mic_next_card_db - Get the doorbell with minimum usage count.
- *
- * Returns the irq index.
- */
-int mic_next_card_db(void)
-{
-	int i;
-	int index = 0;
-	struct mic_driver *mdrv = g_drv;
-
-	for (i = 0; i < mdrv->intr_info.num_intr; i++) {
-		if (mdrv->irq_info.irq_usage_count[i] <
-			mdrv->irq_info.irq_usage_count[index])
-			index = i;
-	}
-
-	return index;
-}
-
-/**
- * mic_init_irq - Initialize irq information.
- *
- * Returns 0 in success. Appropriate error code on failure.
- */
-static int mic_init_irq(void)
-{
-	struct mic_driver *mdrv = g_drv;
-
-	mdrv->irq_info.irq_usage_count = kzalloc((sizeof(u32) *
-			mdrv->intr_info.num_intr),
-			GFP_KERNEL);
-	if (!mdrv->irq_info.irq_usage_count)
-		return -ENOMEM;
-	return 0;
-}
-
-/**
- * mic_uninit_irq - Uninitialize irq information.
- *
- * None.
- */
-static void mic_uninit_irq(void)
-{
-	struct mic_driver *mdrv = g_drv;
-
-	kfree(mdrv->irq_info.irq_usage_count);
-}
-
-static inline struct mic_driver *scdev_to_mdrv(struct scif_hw_dev *scdev)
-{
-	return dev_get_drvdata(scdev->dev.parent);
-}
-
-static struct mic_irq *
-___mic_request_irq(struct scif_hw_dev *scdev,
-		   irqreturn_t (*func)(int irq, void *data),
-				       const char *name, void *data,
-				       int db)
-{
-	return mic_request_card_irq(func, NULL, name, data, db);
-}
-
-static void
-___mic_free_irq(struct scif_hw_dev *scdev,
-		struct mic_irq *cookie, void *data)
-{
-	return mic_free_card_irq(cookie, data);
-}
-
-static void ___mic_ack_interrupt(struct scif_hw_dev *scdev, int num)
-{
-	struct mic_driver *mdrv = scdev_to_mdrv(scdev);
-
-	mic_ack_interrupt(&mdrv->mdev);
-}
-
-static int ___mic_next_db(struct scif_hw_dev *scdev)
-{
-	return mic_next_card_db();
-}
-
-static void ___mic_send_intr(struct scif_hw_dev *scdev, int db)
-{
-	struct mic_driver *mdrv = scdev_to_mdrv(scdev);
-
-	mic_send_intr(&mdrv->mdev, db);
-}
-
-static void ___mic_send_p2p_intr(struct scif_hw_dev *scdev, int db,
-				 struct mic_mw *mw)
-{
-	mic_send_p2p_intr(db, mw);
-}
-
-static void __iomem *
-___mic_ioremap(struct scif_hw_dev *scdev,
-	       phys_addr_t pa, size_t len)
-{
-	struct mic_driver *mdrv = scdev_to_mdrv(scdev);
-
-	return mic_card_map(&mdrv->mdev, pa, len);
-}
-
-static void ___mic_iounmap(struct scif_hw_dev *scdev, void __iomem *va)
-{
-	struct mic_driver *mdrv = scdev_to_mdrv(scdev);
-
-	mic_card_unmap(&mdrv->mdev, va);
-}
-
-static struct scif_hw_ops scif_hw_ops = {
-	.request_irq = ___mic_request_irq,
-	.free_irq = ___mic_free_irq,
-	.ack_interrupt = ___mic_ack_interrupt,
-	.next_db = ___mic_next_db,
-	.send_intr = ___mic_send_intr,
-	.send_p2p_intr = ___mic_send_p2p_intr,
-	.remap = ___mic_ioremap,
-	.unmap = ___mic_iounmap,
-};
-
-static inline struct mic_driver *vpdev_to_mdrv(struct vop_device *vpdev)
-{
-	return dev_get_drvdata(vpdev->dev.parent);
-}
-
-static struct mic_irq *
-__mic_request_irq(struct vop_device *vpdev,
-		  irqreturn_t (*func)(int irq, void *data),
-		   const char *name, void *data, int intr_src)
-{
-	return mic_request_card_irq(func, NULL, name, data, intr_src);
-}
-
-static void __mic_free_irq(struct vop_device *vpdev,
-			   struct mic_irq *cookie, void *data)
-{
-	return mic_free_card_irq(cookie, data);
-}
-
-static void __mic_ack_interrupt(struct vop_device *vpdev, int num)
-{
-	struct mic_driver *mdrv = vpdev_to_mdrv(vpdev);
-
-	mic_ack_interrupt(&mdrv->mdev);
-}
-
-static int __mic_next_db(struct vop_device *vpdev)
-{
-	return mic_next_card_db();
-}
-
-static void __iomem *__mic_get_remote_dp(struct vop_device *vpdev)
-{
-	struct mic_driver *mdrv = vpdev_to_mdrv(vpdev);
-
-	return mdrv->dp;
-}
-
-static void __mic_send_intr(struct vop_device *vpdev, int db)
-{
-	struct mic_driver *mdrv = vpdev_to_mdrv(vpdev);
-
-	mic_send_intr(&mdrv->mdev, db);
-}
-
-static void __iomem *__mic_ioremap(struct vop_device *vpdev,
-				   dma_addr_t pa, size_t len)
-{
-	struct mic_driver *mdrv = vpdev_to_mdrv(vpdev);
-
-	return mic_card_map(&mdrv->mdev, pa, len);
-}
-
-static void __mic_iounmap(struct vop_device *vpdev, void __iomem *va)
-{
-	struct mic_driver *mdrv = vpdev_to_mdrv(vpdev);
-
-	mic_card_unmap(&mdrv->mdev, va);
-}
-
-static struct vop_hw_ops vop_hw_ops = {
-	.request_irq = __mic_request_irq,
-	.free_irq = __mic_free_irq,
-	.ack_interrupt = __mic_ack_interrupt,
-	.next_db = __mic_next_db,
-	.get_remote_dp = __mic_get_remote_dp,
-	.send_intr = __mic_send_intr,
-	.remap = __mic_ioremap,
-	.unmap = __mic_iounmap,
-};
-
-static int mic_request_dma_chans(struct mic_driver *mdrv)
-{
-	dma_cap_mask_t mask;
-	struct dma_chan *chan;
-
-	dma_cap_zero(mask);
-	dma_cap_set(DMA_MEMCPY, mask);
-
-	do {
-		chan = dma_request_channel(mask, NULL, NULL);
-		if (chan) {
-			mdrv->dma_ch[mdrv->num_dma_ch++] = chan;
-			if (mdrv->num_dma_ch >= MIC_MAX_DMA_CHAN)
-				break;
-		}
-	} while (chan);
-	dev_info(mdrv->dev, "DMA channels # %d\n", mdrv->num_dma_ch);
-	return mdrv->num_dma_ch;
-}
-
-static void mic_free_dma_chans(struct mic_driver *mdrv)
-{
-	int i = 0;
-
-	for (i = 0; i < mdrv->num_dma_ch; i++) {
-		dma_release_channel(mdrv->dma_ch[i]);
-		mdrv->dma_ch[i] = NULL;
-	}
-	mdrv->num_dma_ch = 0;
-}
-
-/*
- * mic_driver_init - MIC driver initialization tasks.
- *
- * Returns 0 in success. Appropriate error code on failure.
- */
-int __init mic_driver_init(struct mic_driver *mdrv)
-{
-	int rc;
-	struct mic_bootparam __iomem *bootparam;
-	u8 node_id;
-
-	g_drv = mdrv;
-	/* Unloading the card module is not supported. */
-	if (!try_module_get(mdrv->dev->driver->owner)) {
-		rc = -ENODEV;
-		goto done;
-	}
-	rc = mic_dp_init();
-	if (rc)
-		goto put;
-	rc = mic_init_irq();
-	if (rc)
-		goto dp_uninit;
-	if (!mic_request_dma_chans(mdrv)) {
-		rc = -ENODEV;
-		goto irq_uninit;
-	}
-	mdrv->vpdev = vop_register_device(mdrv->dev, VOP_DEV_TRNSP,
-					  NULL, &vop_hw_ops, 0,
-					  NULL, mdrv->dma_ch[0]);
-	if (IS_ERR(mdrv->vpdev)) {
-		rc = PTR_ERR(mdrv->vpdev);
-		goto dma_free;
-	}
-	bootparam = mdrv->dp;
-	node_id = ioread8(&bootparam->node_id);
-	mdrv->scdev = scif_register_device(mdrv->dev, MIC_SCIF_DEV,
-					   NULL, &scif_hw_ops,
-					   0, node_id, &mdrv->mdev.mmio, NULL,
-					   NULL, mdrv->dp, mdrv->dma_ch,
-					   mdrv->num_dma_ch, true);
-	if (IS_ERR(mdrv->scdev)) {
-		rc = PTR_ERR(mdrv->scdev);
-		goto vop_remove;
-	}
-	mic_create_card_debug_dir(mdrv);
-done:
-	return rc;
-vop_remove:
-	vop_unregister_device(mdrv->vpdev);
-dma_free:
-	mic_free_dma_chans(mdrv);
-irq_uninit:
-	mic_uninit_irq();
-dp_uninit:
-	mic_dp_uninit();
-put:
-	module_put(mdrv->dev->driver->owner);
-	return rc;
-}
-
-/*
- * mic_driver_uninit - MIC driver uninitialization tasks.
- *
- * Returns None
- */
-void mic_driver_uninit(struct mic_driver *mdrv)
-{
-	mic_delete_card_debug_dir(mdrv);
-	scif_unregister_device(mdrv->scdev);
-	vop_unregister_device(mdrv->vpdev);
-	mic_free_dma_chans(mdrv);
-	mic_uninit_irq();
-	mic_dp_uninit();
-	module_put(mdrv->dev->driver->owner);
-}
diff --git a/drivers/misc/mic/card/mic_device.h b/drivers/misc/mic/card/mic_device.h
deleted file mode 100644
index d6cc69a235a3..000000000000
--- a/drivers/misc/mic/card/mic_device.h
+++ /dev/null
@@ -1,137 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Disclaimer: The codes contained in these modules may be specific to
- * the Intel Software Development Platform codenamed: Knights Ferry, and
- * the Intel product codenamed: Knights Corner, and are not backward
- * compatible with other Intel products. Additionally, Intel will NOT
- * support the codes or instruction set in future products.
- *
- * Intel MIC Card driver.
- */
-#ifndef _MIC_CARD_DEVICE_H_
-#define _MIC_CARD_DEVICE_H_
-
-#include <linux/workqueue.h>
-#include <linux/io.h>
-#include <linux/interrupt.h>
-#include <linux/mic_bus.h>
-#include "../bus/scif_bus.h"
-#include "../bus/vop_bus.h"
-
-/**
- * struct mic_intr_info - Contains h/w specific interrupt sources info
- *
- * @num_intr: The number of irqs available
- */
-struct mic_intr_info {
-	u32 num_intr;
-};
-
-/**
- * struct mic_irq_info - OS specific irq information
- *
- * @irq_usage_count: usage count array tracking the number of sources
- * assigned for each irq.
- */
-struct mic_irq_info {
-	int *irq_usage_count;
-};
-
-/**
- * struct mic_device -  MIC device information.
- *
- * @mmio: MMIO bar information.
- */
-struct mic_device {
-	struct mic_mw mmio;
-};
-
-/**
- * struct mic_driver - MIC card driver information.
- *
- * @name: Name for MIC driver.
- * @dbg_dir: debugfs directory of this MIC device.
- * @dev: The device backing this MIC.
- * @dp: The pointer to the virtio device page.
- * @mdev: MIC device information for the host.
- * @hotplug_work: Hot plug work for adding/removing virtio devices.
- * @irq_info: The OS specific irq information
- * @intr_info: H/W specific interrupt information.
- * @dma_mbdev: dma device on the MIC virtual bus.
- * @dma_ch - Array of DMA channels
- * @num_dma_ch - Number of DMA channels available
- * @scdev: SCIF device on the SCIF virtual bus.
- * @vpdev: Virtio over PCIe device on the VOP virtual bus.
- */
-struct mic_driver {
-	char name[20];
-	struct dentry *dbg_dir;
-	struct device *dev;
-	void __iomem *dp;
-	struct mic_device mdev;
-	struct work_struct hotplug_work;
-	struct mic_irq_info irq_info;
-	struct mic_intr_info intr_info;
-	struct mbus_device *dma_mbdev;
-	struct dma_chan *dma_ch[MIC_MAX_DMA_CHAN];
-	int num_dma_ch;
-	struct scif_hw_dev *scdev;
-	struct vop_device *vpdev;
-};
-
-/**
- * struct mic_irq - opaque pointer used as cookie
- */
-struct mic_irq;
-
-/**
- * mic_mmio_read - read from an MMIO register.
- * @mw: MMIO register base virtual address.
- * @offset: register offset.
- *
- * RETURNS: register value.
- */
-static inline u32 mic_mmio_read(struct mic_mw *mw, u32 offset)
-{
-	return ioread32(mw->va + offset);
-}
-
-/**
- * mic_mmio_write - write to an MMIO register.
- * @mw: MMIO register base virtual address.
- * @val: the data value to put into the register
- * @offset: register offset.
- *
- * RETURNS: none.
- */
-static inline void
-mic_mmio_write(struct mic_mw *mw, u32 val, u32 offset)
-{
-	iowrite32(val, mw->va + offset);
-}
-
-int mic_driver_init(struct mic_driver *mdrv);
-void mic_driver_uninit(struct mic_driver *mdrv);
-int mic_next_card_db(void);
-struct mic_irq *
-mic_request_card_irq(irq_handler_t handler, irq_handler_t thread_fn,
-		     const char *name, void *data, int db);
-void mic_free_card_irq(struct mic_irq *cookie, void *data);
-u32 mic_read_spad(struct mic_device *mdev, unsigned int idx);
-void mic_send_intr(struct mic_device *mdev, int doorbell);
-void mic_send_p2p_intr(int doorbell, struct mic_mw *mw);
-int mic_db_to_irq(struct mic_driver *mdrv, int db);
-u32 mic_ack_interrupt(struct mic_device *mdev);
-void mic_hw_intr_init(struct mic_driver *mdrv);
-void __iomem *
-mic_card_map(struct mic_device *mdev, dma_addr_t addr, size_t size);
-void mic_card_unmap(struct mic_device *mdev, void __iomem *addr);
-void __init mic_create_card_debug_dir(struct mic_driver *mdrv);
-void mic_delete_card_debug_dir(struct mic_driver *mdrv);
-void __init mic_init_card_debugfs(void);
-void mic_exit_card_debugfs(void);
-#endif
diff --git a/drivers/misc/mic/card/mic_x100.c b/drivers/misc/mic/card/mic_x100.c
deleted file mode 100644
index c8bff2916d3d..000000000000
--- a/drivers/misc/mic/card/mic_x100.c
+++ /dev/null
@@ -1,347 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Disclaimer: The codes contained in these modules may be specific to
- * the Intel Software Development Platform codenamed: Knights Ferry, and
- * the Intel product codenamed: Knights Corner, and are not backward
- * compatible with other Intel products. Additionally, Intel will NOT
- * support the codes or instruction set in future products.
- *
- * Intel MIC Card driver.
- */
-#include <linux/module.h>
-#include <linux/pci.h>
-#include <linux/platform_device.h>
-
-#include "../common/mic_dev.h"
-#include "mic_device.h"
-#include "mic_x100.h"
-
-static const char mic_driver_name[] = "mic";
-
-static struct mic_driver g_drv;
-
-/**
- * mic_read_spad - read from the scratchpad register
- * @mdev: pointer to mic_device instance
- * @idx: index to scratchpad register, 0 based
- *
- * This function allows reading of the 32bit scratchpad register.
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-u32 mic_read_spad(struct mic_device *mdev, unsigned int idx)
-{
-	return mic_mmio_read(&mdev->mmio,
-		MIC_X100_SBOX_BASE_ADDRESS +
-		MIC_X100_SBOX_SPAD0 + idx * 4);
-}
-
-/**
- * __mic_send_intr - Send interrupt to Host.
- * @mdev: pointer to mic_device instance
- * @doorbell: Doorbell number.
- */
-void mic_send_intr(struct mic_device *mdev, int doorbell)
-{
-	struct mic_mw *mw = &mdev->mmio;
-
-	if (doorbell > MIC_X100_MAX_DOORBELL_IDX)
-		return;
-	/* Ensure that the interrupt is ordered w.r.t previous stores. */
-	wmb();
-	mic_mmio_write(mw, MIC_X100_SBOX_SDBIC0_DBREQ_BIT,
-		       MIC_X100_SBOX_BASE_ADDRESS +
-		       (MIC_X100_SBOX_SDBIC0 + (4 * doorbell)));
-}
-
-/*
- * mic_x100_send_sbox_intr - Send an MIC_X100_SBOX interrupt to MIC.
- */
-static void mic_x100_send_sbox_intr(struct mic_mw *mw, int doorbell)
-{
-	u64 apic_icr_offset = MIC_X100_SBOX_APICICR0 + doorbell * 8;
-	u32 apicicr_low = mic_mmio_read(mw, MIC_X100_SBOX_BASE_ADDRESS +
-					apic_icr_offset);
-
-	/* for MIC we need to make sure we "hit" the send_icr bit (13) */
-	apicicr_low = (apicicr_low | (1 << 13));
-	/*
-	 * Ensure that the interrupt is ordered w.r.t. previous stores
-	 * to main memory. Fence instructions are not implemented in X100
-	 * since execution is in order but a compiler barrier is still
-	 * required.
-	 */
-	wmb();
-	mic_mmio_write(mw, apicicr_low,
-		       MIC_X100_SBOX_BASE_ADDRESS + apic_icr_offset);
-}
-
-static void mic_x100_send_rdmasr_intr(struct mic_mw *mw, int doorbell)
-{
-	int rdmasr_offset = MIC_X100_SBOX_RDMASR0 + (doorbell << 2);
-	/*
-	 * Ensure that the interrupt is ordered w.r.t. previous stores
-	 * to main memory. Fence instructions are not implemented in X100
-	 * since execution is in order but a compiler barrier is still
-	 * required.
-	 */
-	wmb();
-	mic_mmio_write(mw, 0, MIC_X100_SBOX_BASE_ADDRESS + rdmasr_offset);
-}
-
-/**
- * mic_ack_interrupt - Device specific interrupt handling.
- * @mdev: pointer to mic_device instance
- *
- * Returns: bitmask of doorbell events triggered.
- */
-u32 mic_ack_interrupt(struct mic_device *mdev)
-{
-	return 0;
-}
-
-static inline int mic_get_sbox_irq(int db)
-{
-	return MIC_X100_IRQ_BASE + db;
-}
-
-static inline int mic_get_rdmasr_irq(int index)
-{
-	return  MIC_X100_RDMASR_IRQ_BASE + index;
-}
-
-void mic_send_p2p_intr(int db, struct mic_mw *mw)
-{
-	int rdmasr_index;
-
-	if (db < MIC_X100_NUM_SBOX_IRQ) {
-		mic_x100_send_sbox_intr(mw, db);
-	} else {
-		rdmasr_index = db - MIC_X100_NUM_SBOX_IRQ;
-		mic_x100_send_rdmasr_intr(mw, rdmasr_index);
-	}
-}
-
-/**
- * mic_hw_intr_init - Initialize h/w specific interrupt
- * information.
- * @mdrv: pointer to mic_driver
- */
-void mic_hw_intr_init(struct mic_driver *mdrv)
-{
-	mdrv->intr_info.num_intr = MIC_X100_NUM_SBOX_IRQ +
-				MIC_X100_NUM_RDMASR_IRQ;
-}
-
-/**
- * mic_db_to_irq - Retrieve irq number corresponding to a doorbell.
- * @mdrv: pointer to mic_driver
- * @db: The doorbell obtained for which the irq is needed. Doorbell
- * may correspond to an sbox doorbell or an rdmasr index.
- *
- * Returns the irq corresponding to the doorbell.
- */
-int mic_db_to_irq(struct mic_driver *mdrv, int db)
-{
-	int rdmasr_index;
-
-	/*
-	 * The total number of doorbell interrupts on the card are 16. Indices
-	 * 0-8 falls in the SBOX category and 8-15 fall in the RDMASR category.
-	 */
-	if (db < MIC_X100_NUM_SBOX_IRQ) {
-		return mic_get_sbox_irq(db);
-	} else {
-		rdmasr_index = db - MIC_X100_NUM_SBOX_IRQ;
-		return mic_get_rdmasr_irq(rdmasr_index);
-	}
-}
-
-/*
- * mic_card_map - Allocate virtual address for a remote memory region.
- * @mdev: pointer to mic_device instance.
- * @addr: Remote DMA address.
- * @size: Size of the region.
- *
- * Returns: Virtual address backing the remote memory region.
- */
-void __iomem *
-mic_card_map(struct mic_device *mdev, dma_addr_t addr, size_t size)
-{
-	return ioremap(addr, size);
-}
-
-/*
- * mic_card_unmap - Unmap the virtual address for a remote memory region.
- * @mdev: pointer to mic_device instance.
- * @addr: Virtual address for remote memory region.
- *
- * Returns: None.
- */
-void mic_card_unmap(struct mic_device *mdev, void __iomem *addr)
-{
-	iounmap(addr);
-}
-
-static inline struct mic_driver *mbdev_to_mdrv(struct mbus_device *mbdev)
-{
-	return dev_get_drvdata(mbdev->dev.parent);
-}
-
-static struct mic_irq *
-_mic_request_threaded_irq(struct mbus_device *mbdev,
-			  irq_handler_t handler, irq_handler_t thread_fn,
-			  const char *name, void *data, int intr_src)
-{
-	int rc = 0;
-	unsigned int irq = intr_src;
-	unsigned long cookie = irq;
-
-	rc  = request_threaded_irq(irq, handler, thread_fn, 0, name, data);
-	if (rc) {
-		dev_err(mbdev_to_mdrv(mbdev)->dev,
-			"request_threaded_irq failed rc = %d\n", rc);
-		return ERR_PTR(rc);
-	}
-	return (struct mic_irq *)cookie;
-}
-
-static void _mic_free_irq(struct mbus_device *mbdev,
-			  struct mic_irq *cookie, void *data)
-{
-	unsigned long irq = (unsigned long)cookie;
-	free_irq(irq, data);
-}
-
-static void _mic_ack_interrupt(struct mbus_device *mbdev, int num)
-{
-	mic_ack_interrupt(&mbdev_to_mdrv(mbdev)->mdev);
-}
-
-static struct mbus_hw_ops mbus_hw_ops = {
-	.request_threaded_irq = _mic_request_threaded_irq,
-	.free_irq = _mic_free_irq,
-	.ack_interrupt = _mic_ack_interrupt,
-};
-
-static int __init mic_probe(struct platform_device *pdev)
-{
-	struct mic_driver *mdrv = &g_drv;
-	struct mic_device *mdev = &mdrv->mdev;
-	int rc = 0;
-
-	mdrv->dev = &pdev->dev;
-	snprintf(mdrv->name, sizeof(mic_driver_name), mic_driver_name);
-
-	/* FIXME: use dma_set_mask_and_coherent() and check result */
-	dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
-
-	mdev->mmio.pa = MIC_X100_MMIO_BASE;
-	mdev->mmio.len = MIC_X100_MMIO_LEN;
-	mdev->mmio.va = devm_ioremap(&pdev->dev, MIC_X100_MMIO_BASE,
-				     MIC_X100_MMIO_LEN);
-	if (!mdev->mmio.va) {
-		dev_err(&pdev->dev, "Cannot remap MMIO BAR\n");
-		rc = -EIO;
-		goto done;
-	}
-	mic_hw_intr_init(mdrv);
-	platform_set_drvdata(pdev, mdrv);
-	mdrv->dma_mbdev = mbus_register_device(mdrv->dev, MBUS_DEV_DMA_MIC,
-					       NULL, &mbus_hw_ops, 0,
-					       mdrv->mdev.mmio.va);
-	if (IS_ERR(mdrv->dma_mbdev)) {
-		rc = PTR_ERR(mdrv->dma_mbdev);
-		dev_err(&pdev->dev, "mbus_add_device failed rc %d\n", rc);
-		goto done;
-	}
-	rc = mic_driver_init(mdrv);
-	if (rc) {
-		dev_err(&pdev->dev, "mic_driver_init failed rc %d\n", rc);
-		goto remove_dma;
-	}
-done:
-	return rc;
-remove_dma:
-	mbus_unregister_device(mdrv->dma_mbdev);
-	return rc;
-}
-
-static int mic_remove(struct platform_device *pdev)
-{
-	struct mic_driver *mdrv = &g_drv;
-
-	mic_driver_uninit(mdrv);
-	mbus_unregister_device(mdrv->dma_mbdev);
-	return 0;
-}
-
-static void mic_platform_shutdown(struct platform_device *pdev)
-{
-	mic_remove(pdev);
-}
-
-static struct platform_driver __refdata mic_platform_driver = {
-	.probe = mic_probe,
-	.remove = mic_remove,
-	.shutdown = mic_platform_shutdown,
-	.driver         = {
-		.name   = mic_driver_name,
-	},
-};
-
-static struct platform_device *mic_platform_dev;
-
-static int __init mic_init(void)
-{
-	int ret;
-	struct cpuinfo_x86 *c = &cpu_data(0);
-
-	if (!(c->x86 == 11 && c->x86_model == 1)) {
-		ret = -ENODEV;
-		pr_err("%s not running on X100 ret %d\n", __func__, ret);
-		goto done;
-	}
-
-	request_module("mic_x100_dma");
-	mic_init_card_debugfs();
-
-	mic_platform_dev = platform_device_register_simple(mic_driver_name,
-							   0, NULL, 0);
-	ret = PTR_ERR_OR_ZERO(mic_platform_dev);
-	if (ret) {
-		pr_err("platform_device_register_full ret %d\n", ret);
-		goto cleanup_debugfs;
-	}
-	ret = platform_driver_register(&mic_platform_driver);
-	if (ret) {
-		pr_err("platform_driver_register ret %d\n", ret);
-		goto device_unregister;
-	}
-	return ret;
-
-device_unregister:
-	platform_device_unregister(mic_platform_dev);
-cleanup_debugfs:
-	mic_exit_card_debugfs();
-done:
-	return ret;
-}
-
-static void __exit mic_exit(void)
-{
-	platform_driver_unregister(&mic_platform_driver);
-	platform_device_unregister(mic_platform_dev);
-	mic_exit_card_debugfs();
-}
-
-module_init(mic_init);
-module_exit(mic_exit);
-
-MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Intel(R) MIC X100 Card driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/misc/mic/card/mic_x100.h b/drivers/misc/mic/card/mic_x100.h
deleted file mode 100644
index 46644dde0c07..000000000000
--- a/drivers/misc/mic/card/mic_x100.h
+++ /dev/null
@@ -1,37 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Disclaimer: The codes contained in these modules may be specific to
- * the Intel Software Development Platform codenamed: Knights Ferry, and
- * the Intel product codenamed: Knights Corner, and are not backward
- * compatible with other Intel products. Additionally, Intel will NOT
- * support the codes or instruction set in future products.
- *
- * Intel MIC Card driver.
- */
-#ifndef _MIC_X100_CARD_H_
-#define _MIC_X100_CARD_H_
-
-#define MIC_X100_MMIO_BASE 0x08007C0000ULL
-#define MIC_X100_MMIO_LEN 0x00020000ULL
-#define MIC_X100_SBOX_BASE_ADDRESS 0x00010000ULL
-
-#define MIC_X100_SBOX_SPAD0 0x0000AB20
-#define MIC_X100_SBOX_SDBIC0 0x0000CC90
-#define MIC_X100_SBOX_SDBIC0_DBREQ_BIT 0x80000000
-#define MIC_X100_SBOX_RDMASR0	0x0000B180
-#define MIC_X100_SBOX_APICICR0 0x0000A9D0
-
-#define MIC_X100_MAX_DOORBELL_IDX 8
-
-#define MIC_X100_NUM_SBOX_IRQ 8
-#define MIC_X100_NUM_RDMASR_IRQ 8
-#define MIC_X100_SBOX_IRQ_BASE 0
-#define MIC_X100_RDMASR_IRQ_BASE 17
-
-#define MIC_X100_IRQ_BASE 26
-
-#endif
diff --git a/drivers/misc/mic/common/mic_dev.h b/drivers/misc/mic/common/mic_dev.h
deleted file mode 100644
index f94f08df0260..000000000000
--- a/drivers/misc/mic/common/mic_dev.h
+++ /dev/null
@@ -1,55 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC driver.
- */
-#ifndef __MIC_DEV_H__
-#define __MIC_DEV_H__
-
-/* The maximum number of MIC devices supported in a single host system. */
-#define MIC_MAX_NUM_DEVS 128
-
-/**
- * enum mic_hw_family - The hardware family to which a device belongs.
- */
-enum mic_hw_family {
-	MIC_FAMILY_X100 = 0,
-	MIC_FAMILY_X200,
-	MIC_FAMILY_UNKNOWN,
-	MIC_FAMILY_LAST
-};
-
-/**
- * struct mic_mw - MIC memory window
- *
- * @pa: Base physical address.
- * @va: Base ioremap'd virtual address.
- * @len: Size of the memory window.
- */
-struct mic_mw {
-	phys_addr_t pa;
-	void __iomem *va;
-	resource_size_t len;
-};
-
-/*
- * Scratch pad register offsets used by the host to communicate
- * device page DMA address to the card.
- */
-#define MIC_DPLO_SPAD 14
-#define MIC_DPHI_SPAD 15
-
-/*
- * These values are supposed to be in the config_change field of the
- * device page when the host sends a config change interrupt to the card.
- */
-#define MIC_VIRTIO_PARAM_DEV_REMOVE 0x1
-#define MIC_VIRTIO_PARAM_CONFIG_CHANGED 0x2
-
-/* Maximum number of DMA channels */
-#define MIC_MAX_DMA_CHAN 4
-
-#endif
diff --git a/drivers/misc/mic/cosm/Makefile b/drivers/misc/mic/cosm/Makefile
deleted file mode 100644
index 97d74cb12030..000000000000
--- a/drivers/misc/mic/cosm/Makefile
+++ /dev/null
@@ -1,11 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-#
-# Makefile - Intel MIC Coprocessor State Management (COSM) Driver
-# Copyright(c) 2015, Intel Corporation.
-#
-obj-$(CONFIG_MIC_COSM) += mic_cosm.o
-
-mic_cosm-objs := cosm_main.o
-mic_cosm-objs += cosm_debugfs.o
-mic_cosm-objs += cosm_sysfs.o
-mic_cosm-objs += cosm_scif_server.o
diff --git a/drivers/misc/mic/cosm/cosm_debugfs.c b/drivers/misc/mic/cosm/cosm_debugfs.c
deleted file mode 100644
index cb55653cf1f9..000000000000
--- a/drivers/misc/mic/cosm/cosm_debugfs.c
+++ /dev/null
@@ -1,116 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel MIC Coprocessor State Management (COSM) Driver
- */
-
-#include <linux/debugfs.h>
-#include <linux/slab.h>
-#include <linux/io.h>
-#include "cosm_main.h"
-
-/* Debugfs parent dir */
-static struct dentry *cosm_dbg;
-
-/*
- * log_buf_show - Display MIC kernel log buffer
- *
- * log_buf addr/len is read from System.map by user space
- * and populated in sysfs entries.
- */
-static int log_buf_show(struct seq_file *s, void *unused)
-{
-	void __iomem *log_buf_va;
-	int __iomem *log_buf_len_va;
-	struct cosm_device *cdev = s->private;
-	void *kva;
-	int size;
-	u64 aper_offset;
-
-	if (!cdev || !cdev->log_buf_addr || !cdev->log_buf_len)
-		goto done;
-
-	mutex_lock(&cdev->cosm_mutex);
-	switch (cdev->state) {
-	case MIC_BOOTING:
-	case MIC_ONLINE:
-	case MIC_SHUTTING_DOWN:
-		break;
-	default:
-		goto unlock;
-	}
-
-	/*
-	 * Card kernel will never be relocated and any kernel text/data mapping
-	 * can be translated to phys address by subtracting __START_KERNEL_map.
-	 */
-	aper_offset = (u64)cdev->log_buf_len - __START_KERNEL_map;
-	log_buf_len_va = cdev->hw_ops->aper(cdev)->va + aper_offset;
-	aper_offset = (u64)cdev->log_buf_addr - __START_KERNEL_map;
-	log_buf_va = cdev->hw_ops->aper(cdev)->va + aper_offset;
-
-	size = ioread32(log_buf_len_va);
-	kva = kmalloc(size, GFP_KERNEL);
-	if (!kva)
-		goto unlock;
-
-	memcpy_fromio(kva, log_buf_va, size);
-	seq_write(s, kva, size);
-	kfree(kva);
-unlock:
-	mutex_unlock(&cdev->cosm_mutex);
-done:
-	return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(log_buf);
-
-/*
- * force_reset_show - Force MIC reset
- *
- * Invokes the force_reset COSM bus op instead of the standard reset
- * op in case a force reset of the MIC device is required
- */
-static int force_reset_show(struct seq_file *s, void *pos)
-{
-	struct cosm_device *cdev = s->private;
-
-	cosm_stop(cdev, true);
-	return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(force_reset);
-
-void cosm_create_debug_dir(struct cosm_device *cdev)
-{
-	char name[16];
-
-	if (!cosm_dbg)
-		return;
-
-	scnprintf(name, sizeof(name), "mic%d", cdev->index);
-	cdev->dbg_dir = debugfs_create_dir(name, cosm_dbg);
-
-	debugfs_create_file("log_buf", 0444, cdev->dbg_dir, cdev,
-			    &log_buf_fops);
-	debugfs_create_file("force_reset", 0444, cdev->dbg_dir, cdev,
-			    &force_reset_fops);
-}
-
-void cosm_delete_debug_dir(struct cosm_device *cdev)
-{
-	debugfs_remove_recursive(cdev->dbg_dir);
-}
-
-void cosm_init_debugfs(void)
-{
-	cosm_dbg = debugfs_create_dir(KBUILD_MODNAME, NULL);
-}
-
-void cosm_exit_debugfs(void)
-{
-	debugfs_remove(cosm_dbg);
-}
diff --git a/drivers/misc/mic/cosm/cosm_main.c b/drivers/misc/mic/cosm/cosm_main.c
deleted file mode 100644
index ebb0eac43754..000000000000
--- a/drivers/misc/mic/cosm/cosm_main.c
+++ /dev/null
@@ -1,382 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel MIC Coprocessor State Management (COSM) Driver
- */
-
-#include <linux/module.h>
-#include <linux/delay.h>
-#include <linux/idr.h>
-#include <linux/slab.h>
-#include <linux/cred.h>
-#include "cosm_main.h"
-
-static const char cosm_driver_name[] = "mic";
-
-/* COSM ID allocator */
-static struct ida g_cosm_ida;
-/* Class of MIC devices for sysfs accessibility. */
-static struct class *g_cosm_class;
-/* Number of MIC devices */
-static atomic_t g_num_dev;
-
-/**
- * cosm_hw_reset - Issue a HW reset for the MIC device
- * @cdev: pointer to cosm_device instance
- * @force: force a MIC to reset even if it is already reset and ready
- */
-static void cosm_hw_reset(struct cosm_device *cdev, bool force)
-{
-	int i;
-
-#define MIC_RESET_TO (45)
-	if (force && cdev->hw_ops->force_reset)
-		cdev->hw_ops->force_reset(cdev);
-	else
-		cdev->hw_ops->reset(cdev);
-
-	for (i = 0; i < MIC_RESET_TO; i++) {
-		if (cdev->hw_ops->ready(cdev)) {
-			cosm_set_state(cdev, MIC_READY);
-			return;
-		}
-		/*
-		 * Resets typically take 10s of seconds to complete.
-		 * Since an MMIO read is required to check if the
-		 * firmware is ready or not, a 1 second delay works nicely.
-		 */
-		msleep(1000);
-	}
-	cosm_set_state(cdev, MIC_RESET_FAILED);
-}
-
-/**
- * cosm_start - Start the MIC
- * @cdev: pointer to cosm_device instance
- *
- * This function prepares an MIC for boot and initiates boot.
- * RETURNS: An appropriate -ERRNO error value on error, or 0 for success.
- */
-int cosm_start(struct cosm_device *cdev)
-{
-	const struct cred *orig_cred;
-	struct cred *override_cred;
-	int rc;
-
-	mutex_lock(&cdev->cosm_mutex);
-	if (!cdev->bootmode) {
-		dev_err(&cdev->dev, "%s %d bootmode not set\n",
-			__func__, __LINE__);
-		rc = -EINVAL;
-		goto unlock_ret;
-	}
-retry:
-	if (cdev->state != MIC_READY) {
-		dev_err(&cdev->dev, "%s %d MIC state not READY\n",
-			__func__, __LINE__);
-		rc = -EINVAL;
-		goto unlock_ret;
-	}
-	if (!cdev->hw_ops->ready(cdev)) {
-		cosm_hw_reset(cdev, false);
-		/*
-		 * The state will either be MIC_READY if the reset succeeded
-		 * or MIC_RESET_FAILED if the firmware reset failed.
-		 */
-		goto retry;
-	}
-
-	/*
-	 * Set credentials to root to allow non-root user to download initramsfs
-	 * with 600 permissions
-	 */
-	override_cred = prepare_creds();
-	if (!override_cred) {
-		dev_err(&cdev->dev, "%s %d prepare_creds failed\n",
-			__func__, __LINE__);
-		rc = -ENOMEM;
-		goto unlock_ret;
-	}
-	override_cred->fsuid = GLOBAL_ROOT_UID;
-	orig_cred = override_creds(override_cred);
-
-	rc = cdev->hw_ops->start(cdev, cdev->index);
-
-	revert_creds(orig_cred);
-	put_cred(override_cred);
-	if (rc)
-		goto unlock_ret;
-
-	/*
-	 * If linux is being booted, card is treated 'online' only
-	 * when the scif interface in the card is up. If anything else
-	 * is booted, we set card to 'online' immediately.
-	 */
-	if (!strcmp(cdev->bootmode, "linux"))
-		cosm_set_state(cdev, MIC_BOOTING);
-	else
-		cosm_set_state(cdev, MIC_ONLINE);
-unlock_ret:
-	mutex_unlock(&cdev->cosm_mutex);
-	if (rc)
-		dev_err(&cdev->dev, "cosm_start failed rc %d\n", rc);
-	return rc;
-}
-
-/**
- * cosm_stop - Prepare the MIC for reset and trigger reset
- * @cdev: pointer to cosm_device instance
- * @force: force a MIC to reset even if it is already reset and ready.
- *
- * RETURNS: None
- */
-void cosm_stop(struct cosm_device *cdev, bool force)
-{
-	mutex_lock(&cdev->cosm_mutex);
-	if (cdev->state != MIC_READY || force) {
-		/*
-		 * Don't call hw_ops if they have been called previously.
-		 * stop(..) calls device_unregister and will crash the system if
-		 * called multiple times.
-		 */
-		u8 state = cdev->state == MIC_RESETTING ?
-					cdev->prev_state : cdev->state;
-		bool call_hw_ops = state != MIC_RESET_FAILED &&
-					state != MIC_READY;
-
-		if (cdev->state != MIC_RESETTING)
-			cosm_set_state(cdev, MIC_RESETTING);
-		cdev->heartbeat_watchdog_enable = false;
-		if (call_hw_ops)
-			cdev->hw_ops->stop(cdev, force);
-		cosm_hw_reset(cdev, force);
-		cosm_set_shutdown_status(cdev, MIC_NOP);
-		if (call_hw_ops && cdev->hw_ops->post_reset)
-			cdev->hw_ops->post_reset(cdev, cdev->state);
-	}
-	mutex_unlock(&cdev->cosm_mutex);
-	flush_work(&cdev->scif_work);
-}
-
-/**
- * cosm_reset_trigger_work - Trigger MIC reset
- * @work: The work structure
- *
- * This work is scheduled whenever the host wants to reset the MIC.
- */
-static void cosm_reset_trigger_work(struct work_struct *work)
-{
-	struct cosm_device *cdev = container_of(work, struct cosm_device,
-						reset_trigger_work);
-	cosm_stop(cdev, false);
-}
-
-/**
- * cosm_reset - Schedule MIC reset
- * @cdev: pointer to cosm_device instance
- *
- * RETURNS: An -EINVAL if the card is already READY or 0 for success.
- */
-int cosm_reset(struct cosm_device *cdev)
-{
-	int rc = 0;
-
-	mutex_lock(&cdev->cosm_mutex);
-	if (cdev->state != MIC_READY) {
-		if (cdev->state != MIC_RESETTING) {
-			cdev->prev_state = cdev->state;
-			cosm_set_state(cdev, MIC_RESETTING);
-			schedule_work(&cdev->reset_trigger_work);
-		}
-	} else {
-		dev_err(&cdev->dev, "%s %d MIC is READY\n", __func__, __LINE__);
-		rc = -EINVAL;
-	}
-	mutex_unlock(&cdev->cosm_mutex);
-	return rc;
-}
-
-/**
- * cosm_shutdown - Initiate MIC shutdown.
- * @cdev: pointer to cosm_device instance
- *
- * RETURNS: None
- */
-int cosm_shutdown(struct cosm_device *cdev)
-{
-	struct cosm_msg msg = { .id = COSM_MSG_SHUTDOWN };
-	int rc = 0;
-
-	mutex_lock(&cdev->cosm_mutex);
-	if (cdev->state != MIC_ONLINE) {
-		rc = -EINVAL;
-		dev_err(&cdev->dev, "%s %d skipping shutdown in state: %s\n",
-			__func__, __LINE__, cosm_state_string[cdev->state]);
-		goto err;
-	}
-
-	if (!cdev->epd) {
-		rc = -ENOTCONN;
-		dev_err(&cdev->dev, "%s %d scif endpoint not connected rc %d\n",
-			__func__, __LINE__, rc);
-		goto err;
-	}
-
-	rc = scif_send(cdev->epd, &msg, sizeof(msg), SCIF_SEND_BLOCK);
-	if (rc < 0) {
-		dev_err(&cdev->dev, "%s %d scif_send failed rc %d\n",
-			__func__, __LINE__, rc);
-		goto err;
-	}
-	cdev->heartbeat_watchdog_enable = false;
-	cosm_set_state(cdev, MIC_SHUTTING_DOWN);
-	rc = 0;
-err:
-	mutex_unlock(&cdev->cosm_mutex);
-	return rc;
-}
-
-static int cosm_driver_probe(struct cosm_device *cdev)
-{
-	int rc;
-
-	/* Initialize SCIF server at first probe */
-	if (atomic_add_return(1, &g_num_dev) == 1) {
-		rc = cosm_scif_init();
-		if (rc)
-			goto scif_exit;
-	}
-	mutex_init(&cdev->cosm_mutex);
-	INIT_WORK(&cdev->reset_trigger_work, cosm_reset_trigger_work);
-	INIT_WORK(&cdev->scif_work, cosm_scif_work);
-	cdev->sysfs_heartbeat_enable = true;
-	cosm_sysfs_init(cdev);
-	cdev->sdev = device_create_with_groups(g_cosm_class, cdev->dev.parent,
-			       MKDEV(0, cdev->index), cdev, cdev->attr_group,
-			       "mic%d", cdev->index);
-	if (IS_ERR(cdev->sdev)) {
-		rc = PTR_ERR(cdev->sdev);
-		dev_err(&cdev->dev, "device_create_with_groups failed rc %d\n",
-			rc);
-		goto scif_exit;
-	}
-
-	cdev->state_sysfs = sysfs_get_dirent(cdev->sdev->kobj.sd,
-		"state");
-	if (!cdev->state_sysfs) {
-		rc = -ENODEV;
-		dev_err(&cdev->dev, "sysfs_get_dirent failed rc %d\n", rc);
-		goto destroy_device;
-	}
-	cosm_create_debug_dir(cdev);
-	return 0;
-destroy_device:
-	device_destroy(g_cosm_class, MKDEV(0, cdev->index));
-scif_exit:
-	if (atomic_dec_and_test(&g_num_dev))
-		cosm_scif_exit();
-	return rc;
-}
-
-static void cosm_driver_remove(struct cosm_device *cdev)
-{
-	cosm_delete_debug_dir(cdev);
-	sysfs_put(cdev->state_sysfs);
-	device_destroy(g_cosm_class, MKDEV(0, cdev->index));
-	flush_work(&cdev->reset_trigger_work);
-	cosm_stop(cdev, false);
-	if (atomic_dec_and_test(&g_num_dev))
-		cosm_scif_exit();
-
-	/* These sysfs entries might have allocated */
-	kfree(cdev->cmdline);
-	kfree(cdev->firmware);
-	kfree(cdev->ramdisk);
-	kfree(cdev->bootmode);
-}
-
-static int cosm_suspend(struct device *dev)
-{
-	struct cosm_device *cdev = dev_to_cosm(dev);
-
-	mutex_lock(&cdev->cosm_mutex);
-	switch (cdev->state) {
-	/**
-	 * Suspend/freeze hooks in userspace have already shutdown the card.
-	 * Card should be 'ready' in most cases. It is however possible that
-	 * some userspace application initiated a boot. In those cases, we
-	 * simply reset the card.
-	 */
-	case MIC_ONLINE:
-	case MIC_BOOTING:
-	case MIC_SHUTTING_DOWN:
-		mutex_unlock(&cdev->cosm_mutex);
-		cosm_stop(cdev, false);
-		break;
-	default:
-		mutex_unlock(&cdev->cosm_mutex);
-		break;
-	}
-	return 0;
-}
-
-static const struct dev_pm_ops cosm_pm_ops = {
-	.suspend = cosm_suspend,
-	.freeze = cosm_suspend
-};
-
-static struct cosm_driver cosm_driver = {
-	.driver = {
-		.name =  KBUILD_MODNAME,
-		.owner = THIS_MODULE,
-		.pm = &cosm_pm_ops,
-	},
-	.probe = cosm_driver_probe,
-	.remove = cosm_driver_remove
-};
-
-static int __init cosm_init(void)
-{
-	int ret;
-
-	cosm_init_debugfs();
-
-	g_cosm_class = class_create(THIS_MODULE, cosm_driver_name);
-	if (IS_ERR(g_cosm_class)) {
-		ret = PTR_ERR(g_cosm_class);
-		pr_err("class_create failed ret %d\n", ret);
-		goto cleanup_debugfs;
-	}
-
-	ida_init(&g_cosm_ida);
-	ret = cosm_register_driver(&cosm_driver);
-	if (ret) {
-		pr_err("cosm_register_driver failed ret %d\n", ret);
-		goto ida_destroy;
-	}
-	return 0;
-ida_destroy:
-	ida_destroy(&g_cosm_ida);
-	class_destroy(g_cosm_class);
-cleanup_debugfs:
-	cosm_exit_debugfs();
-	return ret;
-}
-
-static void __exit cosm_exit(void)
-{
-	cosm_unregister_driver(&cosm_driver);
-	ida_destroy(&g_cosm_ida);
-	class_destroy(g_cosm_class);
-	cosm_exit_debugfs();
-}
-
-module_init(cosm_init);
-module_exit(cosm_exit);
-
-MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Intel(R) MIC Coprocessor State Management (COSM) Driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/misc/mic/cosm/cosm_main.h b/drivers/misc/mic/cosm/cosm_main.h
deleted file mode 100644
index 5188ad245814..000000000000
--- a/drivers/misc/mic/cosm/cosm_main.h
+++ /dev/null
@@ -1,61 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel MIC Coprocessor State Management (COSM) Driver
- */
-#ifndef _COSM_COSM_H_
-#define _COSM_COSM_H_
-
-#include <linux/scif.h>
-#include "../bus/cosm_bus.h"
-
-#define COSM_HEARTBEAT_SEND_SEC 30
-#define SCIF_COSM_LISTEN_PORT  201
-
-/**
- * enum COSM msg id's
- * @COSM_MSG_SHUTDOWN: host->card trigger shutdown
- * @COSM_MSG_SYNC_TIME: host->card send host time to card to sync time
- * @COSM_MSG_HEARTBEAT: card->host heartbeat
- * @COSM_MSG_SHUTDOWN_STATUS: card->host with shutdown status as payload
- */
-enum cosm_msg_id {
-	COSM_MSG_SHUTDOWN,
-	COSM_MSG_SYNC_TIME,
-	COSM_MSG_HEARTBEAT,
-	COSM_MSG_SHUTDOWN_STATUS,
-};
-
-struct cosm_msg {
-	u64 id;
-	union {
-		u64 shutdown_status;
-		struct {
-			u64 tv_sec;
-			u64 tv_nsec;
-		} timespec;
-	};
-};
-
-extern const char * const cosm_state_string[];
-extern const char * const cosm_shutdown_status_string[];
-
-void cosm_sysfs_init(struct cosm_device *cdev);
-int cosm_start(struct cosm_device *cdev);
-void cosm_stop(struct cosm_device *cdev, bool force);
-int cosm_reset(struct cosm_device *cdev);
-int cosm_shutdown(struct cosm_device *cdev);
-void cosm_set_state(struct cosm_device *cdev, u8 state);
-void cosm_set_shutdown_status(struct cosm_device *cdev, u8 status);
-void cosm_init_debugfs(void);
-void cosm_exit_debugfs(void);
-void cosm_create_debug_dir(struct cosm_device *cdev);
-void cosm_delete_debug_dir(struct cosm_device *cdev);
-int cosm_scif_init(void);
-void cosm_scif_exit(void);
-void cosm_scif_work(struct work_struct *work);
-
-#endif
diff --git a/drivers/misc/mic/cosm/cosm_scif_server.c b/drivers/misc/mic/cosm/cosm_scif_server.c
deleted file mode 100644
index 7baec9fd8756..000000000000
--- a/drivers/misc/mic/cosm/cosm_scif_server.c
+++ /dev/null
@@ -1,399 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel MIC Coprocessor State Management (COSM) Driver
- */
-#include <linux/kthread.h>
-#include <linux/sched/signal.h>
-
-#include "cosm_main.h"
-
-/*
- * The COSM driver uses SCIF to communicate between the management node and the
- * MIC cards. SCIF is used to (a) Send a shutdown command to the card (b)
- * receive a shutdown status back from the card upon completion of shutdown and
- * (c) receive periodic heartbeat messages from the card used to deduce if the
- * card has crashed.
- *
- * A COSM server consisting of a SCIF listening endpoint waits for incoming
- * connections from the card. Upon acceptance of the connection, a separate
- * work-item is scheduled to handle SCIF message processing for that card. The
- * life-time of this work-item is therefore the time from which the connection
- * from a card is accepted to the time at which the connection is closed. A new
- * work-item starts each time the card boots and is alive till the card (a)
- * shuts down (b) is reset (c) crashes (d) cosm_client driver on the card is
- * unloaded.
- *
- * From the point of view of COSM interactions with SCIF during card
- * shutdown, reset and crash are as follows:
- *
- * Card shutdown
- * -------------
- * 1. COSM client on the card invokes orderly_poweroff() in response to SHUTDOWN
- *    message from the host.
- * 2. Card driver shutdown callback invokes scif_unregister_device(..) resulting
- *    in scif_remove(..) getting called on the card
- * 3. scif_remove -> scif_stop -> scif_handle_remove_node ->
- *    scif_peer_unregister_device -> device_unregister for the host peer device
- * 4. During device_unregister remove(..) method of cosm_client is invoked which
- *    closes the COSM SCIF endpoint on the card. This results in a SCIF_DISCNCT
- *    message being sent to host SCIF. SCIF_DISCNCT message processing on the
- *    host SCIF sets the host COSM SCIF endpoint state to DISCONNECTED and wakes
- *    up the host COSM thread blocked in scif_poll(..) resulting in
- *    scif_poll(..)  returning EPOLLHUP.
- * 5. On the card, scif_peer_release_dev is next called which results in an
- *    SCIF_EXIT message being sent to the host and after receiving the
- *    SCIF_EXIT_ACK from the host the peer device teardown on the card is
- *    complete.
- * 6. As part of the SCIF_EXIT message processing on the host, host sends a
- *    SCIF_REMOVE_NODE to itself corresponding to the card being removed. This
- *    starts a similar SCIF peer device teardown sequence on the host
- *    corresponding to the card being shut down.
- *
- * Card reset
- * ----------
- * The case of interest here is when the card has not been previously shut down
- * since most of the steps below are skipped in that case:
-
- * 1. cosm_stop(..) invokes hw_ops->stop(..) method of the base PCIe driver
- *    which unregisters the SCIF HW device resulting in scif_remove(..) being
- *    called on the host.
- * 2. scif_remove(..) calls scif_disconnect_node(..) which results in a
- *    SCIF_EXIT message being sent to the card.
- * 3. The card executes scif_stop() as part of SCIF_EXIT message
- *    processing. This results in the COSM endpoint on the card being closed and
- *    the SCIF host peer device on the card getting unregistered similar to
- *    steps 3, 4 and 5 for the card shutdown case above. scif_poll(..) on the
- *    host returns EPOLLHUP as a result.
- * 4. On the host, card peer device unregister and SCIF HW remove(..) also
- *    subsequently complete.
- *
- * Card crash
- * ----------
- * If a reset is issued after the card has crashed, there is no SCIF_DISCNT
- * message from the card which would result in scif_poll(..) returning
- * EPOLLHUP. In this case when the host SCIF driver sends a SCIF_REMOVE_NODE
- * message to itself resulting in the card SCIF peer device being unregistered,
- * this results in a scif_peer_release_dev -> scif_cleanup_scifdev->
- * scif_invalidate_ep call sequence which sets the endpoint state to
- * DISCONNECTED and results in scif_poll(..) returning EPOLLHUP.
- */
-
-#define COSM_SCIF_BACKLOG 16
-#define COSM_HEARTBEAT_CHECK_DELTA_SEC 10
-#define COSM_HEARTBEAT_TIMEOUT_SEC \
-		(COSM_HEARTBEAT_SEND_SEC + COSM_HEARTBEAT_CHECK_DELTA_SEC)
-#define COSM_HEARTBEAT_TIMEOUT_MSEC (COSM_HEARTBEAT_TIMEOUT_SEC * MSEC_PER_SEC)
-
-static struct task_struct *server_thread;
-static scif_epd_t listen_epd;
-
-/* Publish MIC card's shutdown status to user space MIC daemon */
-static void cosm_update_mic_status(struct cosm_device *cdev)
-{
-	if (cdev->shutdown_status_int != MIC_NOP) {
-		cosm_set_shutdown_status(cdev, cdev->shutdown_status_int);
-		cdev->shutdown_status_int = MIC_NOP;
-	}
-}
-
-/* Store MIC card's shutdown status internally when it is received */
-static void cosm_shutdown_status_int(struct cosm_device *cdev,
-				     enum mic_status shutdown_status)
-{
-	switch (shutdown_status) {
-	case MIC_HALTED:
-	case MIC_POWER_OFF:
-	case MIC_RESTART:
-	case MIC_CRASHED:
-		break;
-	default:
-		dev_err(&cdev->dev, "%s %d Unexpected shutdown_status %d\n",
-			__func__, __LINE__, shutdown_status);
-		return;
-	};
-	cdev->shutdown_status_int = shutdown_status;
-	cdev->heartbeat_watchdog_enable = false;
-
-	if (cdev->state != MIC_SHUTTING_DOWN)
-		cosm_set_state(cdev, MIC_SHUTTING_DOWN);
-}
-
-/* Non-blocking recv. Read and process all available messages */
-static void cosm_scif_recv(struct cosm_device *cdev)
-{
-	struct cosm_msg msg;
-	int rc;
-
-	while (1) {
-		rc = scif_recv(cdev->epd, &msg, sizeof(msg), 0);
-		if (!rc) {
-			break;
-		} else if (rc < 0) {
-			dev_dbg(&cdev->dev, "%s: %d rc %d\n",
-				__func__, __LINE__, rc);
-			break;
-		}
-		dev_dbg(&cdev->dev, "%s: %d rc %d id 0x%llx\n",
-			__func__, __LINE__, rc, msg.id);
-
-		switch (msg.id) {
-		case COSM_MSG_SHUTDOWN_STATUS:
-			cosm_shutdown_status_int(cdev, msg.shutdown_status);
-			break;
-		case COSM_MSG_HEARTBEAT:
-			/* Nothing to do, heartbeat only unblocks scif_poll */
-			break;
-		default:
-			dev_err(&cdev->dev, "%s: %d unknown msg.id %lld\n",
-				__func__, __LINE__, msg.id);
-			break;
-		}
-	}
-}
-
-/* Publish crashed status for this MIC card */
-static void cosm_set_crashed(struct cosm_device *cdev)
-{
-	dev_err(&cdev->dev, "node alive timeout\n");
-	cosm_shutdown_status_int(cdev, MIC_CRASHED);
-	cosm_update_mic_status(cdev);
-}
-
-/* Send host time to the MIC card to sync system time between host and MIC */
-static void cosm_send_time(struct cosm_device *cdev)
-{
-	struct cosm_msg msg = { .id = COSM_MSG_SYNC_TIME };
-	struct timespec64 ts;
-	int rc;
-
-	ktime_get_real_ts64(&ts);
-	msg.timespec.tv_sec = ts.tv_sec;
-	msg.timespec.tv_nsec = ts.tv_nsec;
-
-	rc = scif_send(cdev->epd, &msg, sizeof(msg), SCIF_SEND_BLOCK);
-	if (rc < 0)
-		dev_err(&cdev->dev, "%s %d scif_send failed rc %d\n",
-			__func__, __LINE__, rc);
-}
-
-/*
- * Close this cosm_device's endpoint after its peer endpoint on the card has
- * been closed. In all cases except MIC card crash EPOLLHUP on the host is
- * triggered by the client's endpoint being closed.
- */
-static void cosm_scif_close(struct cosm_device *cdev)
-{
-	/*
-	 * Because SHUTDOWN_STATUS message is sent by the MIC cards in the
-	 * reboot notifier when shutdown is still not complete, we notify mpssd
-	 * to reset the card when SCIF endpoint is closed.
-	 */
-	cosm_update_mic_status(cdev);
-	scif_close(cdev->epd);
-	cdev->epd = NULL;
-	dev_dbg(&cdev->dev, "%s %d\n", __func__, __LINE__);
-}
-
-/*
- * Set card state to ONLINE when a new SCIF connection from a MIC card is
- * received. Normally the state is BOOTING when the connection comes in, but can
- * be ONLINE if cosm_client driver on the card was unloaded and then reloaded.
- */
-static int cosm_set_online(struct cosm_device *cdev)
-{
-	int rc = 0;
-
-	if (MIC_BOOTING == cdev->state || MIC_ONLINE == cdev->state) {
-		cdev->heartbeat_watchdog_enable = cdev->sysfs_heartbeat_enable;
-		cdev->epd = cdev->newepd;
-		if (cdev->state == MIC_BOOTING)
-			cosm_set_state(cdev, MIC_ONLINE);
-		cosm_send_time(cdev);
-		dev_dbg(&cdev->dev, "%s %d\n", __func__, __LINE__);
-	} else {
-		dev_warn(&cdev->dev, "%s %d not going online in state: %s\n",
-			 __func__, __LINE__, cosm_state_string[cdev->state]);
-		rc = -EINVAL;
-	}
-	/* Drop reference acquired by bus_find_device in the server thread */
-	put_device(&cdev->dev);
-	return rc;
-}
-
-/*
- * Work function for handling work for a SCIF connection from a particular MIC
- * card. It first sets the card state to ONLINE and then calls scif_poll to
- * block on activity such as incoming messages on the SCIF endpoint. When the
- * endpoint is closed, the work function exits, completing its life cycle, from
- * MIC card boot to card shutdown/reset/crash.
- */
-void cosm_scif_work(struct work_struct *work)
-{
-	struct cosm_device *cdev = container_of(work, struct cosm_device,
-						scif_work);
-	struct scif_pollepd pollepd;
-	int rc;
-
-	mutex_lock(&cdev->cosm_mutex);
-	if (cosm_set_online(cdev))
-		goto exit;
-
-	while (1) {
-		pollepd.epd = cdev->epd;
-		pollepd.events = EPOLLIN;
-
-		/* Drop the mutex before blocking in scif_poll(..) */
-		mutex_unlock(&cdev->cosm_mutex);
-		/* poll(..) with timeout on our endpoint */
-		rc = scif_poll(&pollepd, 1, COSM_HEARTBEAT_TIMEOUT_MSEC);
-		mutex_lock(&cdev->cosm_mutex);
-		if (rc < 0) {
-			dev_err(&cdev->dev, "%s %d scif_poll rc %d\n",
-				__func__, __LINE__, rc);
-			continue;
-		}
-
-		/* There is a message from the card */
-		if (pollepd.revents & EPOLLIN)
-			cosm_scif_recv(cdev);
-
-		/* The peer endpoint is closed or this endpoint disconnected */
-		if (pollepd.revents & EPOLLHUP) {
-			cosm_scif_close(cdev);
-			break;
-		}
-
-		/* Did we timeout from poll? */
-		if (!rc && cdev->heartbeat_watchdog_enable)
-			cosm_set_crashed(cdev);
-	}
-exit:
-	dev_dbg(&cdev->dev, "%s %d exiting\n", __func__, __LINE__);
-	mutex_unlock(&cdev->cosm_mutex);
-}
-
-/*
- * COSM SCIF server thread function. Accepts incoming SCIF connections from MIC
- * cards, finds the correct cosm_device to associate that connection with and
- * schedules individual work items for each MIC card.
- */
-static int cosm_scif_server(void *unused)
-{
-	struct cosm_device *cdev;
-	scif_epd_t newepd;
-	struct scif_port_id port_id;
-	int rc;
-
-	allow_signal(SIGKILL);
-
-	while (!kthread_should_stop()) {
-		rc = scif_accept(listen_epd, &port_id, &newepd,
-				 SCIF_ACCEPT_SYNC);
-		if (rc < 0) {
-			if (-ERESTARTSYS != rc)
-				pr_err("%s %d rc %d\n", __func__, __LINE__, rc);
-			continue;
-		}
-
-		/*
-		 * Associate the incoming connection with a particular
-		 * cosm_device, COSM device ID == SCIF node ID - 1
-		 */
-		cdev = cosm_find_cdev_by_id(port_id.node - 1);
-		if (!cdev)
-			continue;
-		cdev->newepd = newepd;
-		schedule_work(&cdev->scif_work);
-	}
-
-	pr_debug("%s %d Server thread stopped\n", __func__, __LINE__);
-	return 0;
-}
-
-static int cosm_scif_listen(void)
-{
-	int rc;
-
-	listen_epd = scif_open();
-	if (!listen_epd) {
-		pr_err("%s %d scif_open failed\n", __func__, __LINE__);
-		return -ENOMEM;
-	}
-
-	rc = scif_bind(listen_epd, SCIF_COSM_LISTEN_PORT);
-	if (rc < 0) {
-		pr_err("%s %d scif_bind failed rc %d\n",
-		       __func__, __LINE__, rc);
-		goto err;
-	}
-
-	rc = scif_listen(listen_epd, COSM_SCIF_BACKLOG);
-	if (rc < 0) {
-		pr_err("%s %d scif_listen rc %d\n", __func__, __LINE__, rc);
-		goto err;
-	}
-	pr_debug("%s %d listen_epd set up\n", __func__, __LINE__);
-	return 0;
-err:
-	scif_close(listen_epd);
-	listen_epd = NULL;
-	return rc;
-}
-
-static void cosm_scif_listen_exit(void)
-{
-	pr_debug("%s %d closing listen_epd\n", __func__, __LINE__);
-	if (listen_epd) {
-		scif_close(listen_epd);
-		listen_epd = NULL;
-	}
-}
-
-/*
- * Create a listening SCIF endpoint and a server kthread which accepts incoming
- * SCIF connections from MIC cards
- */
-int cosm_scif_init(void)
-{
-	int rc = cosm_scif_listen();
-
-	if (rc) {
-		pr_err("%s %d cosm_scif_listen rc %d\n",
-		       __func__, __LINE__, rc);
-		goto err;
-	}
-
-	server_thread = kthread_run(cosm_scif_server, NULL, "cosm_server");
-	if (IS_ERR(server_thread)) {
-		rc = PTR_ERR(server_thread);
-		pr_err("%s %d kthread_run rc %d\n", __func__, __LINE__, rc);
-		goto listen_exit;
-	}
-	return 0;
-listen_exit:
-	cosm_scif_listen_exit();
-err:
-	return rc;
-}
-
-/* Stop the running server thread and close the listening SCIF endpoint */
-void cosm_scif_exit(void)
-{
-	int rc;
-
-	if (!IS_ERR_OR_NULL(server_thread)) {
-		rc = send_sig(SIGKILL, server_thread, 0);
-		if (rc) {
-			pr_err("%s %d send_sig rc %d\n",
-			       __func__, __LINE__, rc);
-			return;
-		}
-		kthread_stop(server_thread);
-	}
-
-	cosm_scif_listen_exit();
-}
diff --git a/drivers/misc/mic/cosm/cosm_sysfs.c b/drivers/misc/mic/cosm/cosm_sysfs.c
deleted file mode 100644
index e6dac967c1af..000000000000
--- a/drivers/misc/mic/cosm/cosm_sysfs.c
+++ /dev/null
@@ -1,449 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel MIC Coprocessor State Management (COSM) Driver
- */
-#include <linux/slab.h>
-#include "cosm_main.h"
-
-/*
- * A state-to-string lookup table, for exposing a human readable state
- * via sysfs. Always keep in sync with enum cosm_states
- */
-const char * const cosm_state_string[] = {
-	[MIC_READY] = "ready",
-	[MIC_BOOTING] = "booting",
-	[MIC_ONLINE] = "online",
-	[MIC_SHUTTING_DOWN] = "shutting_down",
-	[MIC_RESETTING] = "resetting",
-	[MIC_RESET_FAILED] = "reset_failed",
-};
-
-/*
- * A shutdown-status-to-string lookup table, for exposing a human
- * readable state via sysfs. Always keep in sync with enum cosm_shutdown_status
- */
-const char * const cosm_shutdown_status_string[] = {
-	[MIC_NOP] = "nop",
-	[MIC_CRASHED] = "crashed",
-	[MIC_HALTED] = "halted",
-	[MIC_POWER_OFF] = "poweroff",
-	[MIC_RESTART] = "restart",
-};
-
-void cosm_set_shutdown_status(struct cosm_device *cdev, u8 shutdown_status)
-{
-	dev_dbg(&cdev->dev, "Shutdown Status %s -> %s\n",
-		cosm_shutdown_status_string[cdev->shutdown_status],
-		cosm_shutdown_status_string[shutdown_status]);
-	cdev->shutdown_status = shutdown_status;
-}
-
-void cosm_set_state(struct cosm_device *cdev, u8 state)
-{
-	dev_dbg(&cdev->dev, "State %s -> %s\n",
-		cosm_state_string[cdev->state],
-		cosm_state_string[state]);
-	cdev->state = state;
-	sysfs_notify_dirent(cdev->state_sysfs);
-}
-
-static ssize_t
-family_show(struct device *dev, struct device_attribute *attr, char *buf)
-{
-	struct cosm_device *cdev = dev_get_drvdata(dev);
-
-	if (!cdev)
-		return -EINVAL;
-
-	return cdev->hw_ops->family(cdev, buf);
-}
-static DEVICE_ATTR_RO(family);
-
-static ssize_t
-stepping_show(struct device *dev, struct device_attribute *attr, char *buf)
-{
-	struct cosm_device *cdev = dev_get_drvdata(dev);
-
-	if (!cdev)
-		return -EINVAL;
-
-	return cdev->hw_ops->stepping(cdev, buf);
-}
-static DEVICE_ATTR_RO(stepping);
-
-static ssize_t
-state_show(struct device *dev, struct device_attribute *attr, char *buf)
-{
-	struct cosm_device *cdev = dev_get_drvdata(dev);
-
-	if (!cdev || cdev->state >= MIC_LAST)
-		return -EINVAL;
-
-	return scnprintf(buf, PAGE_SIZE, "%s\n",
-		cosm_state_string[cdev->state]);
-}
-
-static ssize_t
-state_store(struct device *dev, struct device_attribute *attr,
-	    const char *buf, size_t count)
-{
-	struct cosm_device *cdev = dev_get_drvdata(dev);
-	int rc;
-
-	if (!cdev)
-		return -EINVAL;
-
-	if (sysfs_streq(buf, "boot")) {
-		rc = cosm_start(cdev);
-		goto done;
-	}
-	if (sysfs_streq(buf, "reset")) {
-		rc = cosm_reset(cdev);
-		goto done;
-	}
-
-	if (sysfs_streq(buf, "shutdown")) {
-		rc = cosm_shutdown(cdev);
-		goto done;
-	}
-	rc = -EINVAL;
-done:
-	if (rc)
-		count = rc;
-	return count;
-}
-static DEVICE_ATTR_RW(state);
-
-static ssize_t shutdown_status_show(struct device *dev,
-				    struct device_attribute *attr, char *buf)
-{
-	struct cosm_device *cdev = dev_get_drvdata(dev);
-
-	if (!cdev || cdev->shutdown_status >= MIC_STATUS_LAST)
-		return -EINVAL;
-
-	return scnprintf(buf, PAGE_SIZE, "%s\n",
-		cosm_shutdown_status_string[cdev->shutdown_status]);
-}
-static DEVICE_ATTR_RO(shutdown_status);
-
-static ssize_t
-heartbeat_enable_show(struct device *dev,
-		      struct device_attribute *attr, char *buf)
-{
-	struct cosm_device *cdev = dev_get_drvdata(dev);
-
-	if (!cdev)
-		return -EINVAL;
-
-	return scnprintf(buf, PAGE_SIZE, "%d\n", cdev->sysfs_heartbeat_enable);
-}
-
-static ssize_t
-heartbeat_enable_store(struct device *dev,
-		       struct device_attribute *attr,
-		       const char *buf, size_t count)
-{
-	struct cosm_device *cdev = dev_get_drvdata(dev);
-	int enable;
-	int ret;
-
-	if (!cdev)
-		return -EINVAL;
-
-	mutex_lock(&cdev->cosm_mutex);
-	ret = kstrtoint(buf, 10, &enable);
-	if (ret)
-		goto unlock;
-
-	cdev->sysfs_heartbeat_enable = enable;
-	/* if state is not online, cdev->heartbeat_watchdog_enable is 0 */
-	if (cdev->state == MIC_ONLINE)
-		cdev->heartbeat_watchdog_enable = enable;
-	ret = count;
-unlock:
-	mutex_unlock(&cdev->cosm_mutex);
-	return ret;
-}
-static DEVICE_ATTR_RW(heartbeat_enable);
-
-static ssize_t
-cmdline_show(struct device *dev, struct device_attribute *attr, char *buf)
-{
-	struct cosm_device *cdev = dev_get_drvdata(dev);
-	char *cmdline;
-
-	if (!cdev)
-		return -EINVAL;
-
-	cmdline = cdev->cmdline;
-
-	if (cmdline)
-		return scnprintf(buf, PAGE_SIZE, "%s\n", cmdline);
-	return 0;
-}
-
-static ssize_t
-cmdline_store(struct device *dev, struct device_attribute *attr,
-	      const char *buf, size_t count)
-{
-	struct cosm_device *cdev = dev_get_drvdata(dev);
-
-	if (!cdev)
-		return -EINVAL;
-
-	mutex_lock(&cdev->cosm_mutex);
-	kfree(cdev->cmdline);
-
-	cdev->cmdline = kmalloc(count + 1, GFP_KERNEL);
-	if (!cdev->cmdline) {
-		count = -ENOMEM;
-		goto unlock;
-	}
-
-	strncpy(cdev->cmdline, buf, count);
-
-	if (cdev->cmdline[count - 1] == '\n')
-		cdev->cmdline[count - 1] = '\0';
-	else
-		cdev->cmdline[count] = '\0';
-unlock:
-	mutex_unlock(&cdev->cosm_mutex);
-	return count;
-}
-static DEVICE_ATTR_RW(cmdline);
-
-static ssize_t
-firmware_show(struct device *dev, struct device_attribute *attr, char *buf)
-{
-	struct cosm_device *cdev = dev_get_drvdata(dev);
-	char *firmware;
-
-	if (!cdev)
-		return -EINVAL;
-
-	firmware = cdev->firmware;
-
-	if (firmware)
-		return scnprintf(buf, PAGE_SIZE, "%s\n", firmware);
-	return 0;
-}
-
-static ssize_t
-firmware_store(struct device *dev, struct device_attribute *attr,
-	       const char *buf, size_t count)
-{
-	struct cosm_device *cdev = dev_get_drvdata(dev);
-
-	if (!cdev)
-		return -EINVAL;
-
-	mutex_lock(&cdev->cosm_mutex);
-	kfree(cdev->firmware);
-
-	cdev->firmware = kmalloc(count + 1, GFP_KERNEL);
-	if (!cdev->firmware) {
-		count = -ENOMEM;
-		goto unlock;
-	}
-	strncpy(cdev->firmware, buf, count);
-
-	if (cdev->firmware[count - 1] == '\n')
-		cdev->firmware[count - 1] = '\0';
-	else
-		cdev->firmware[count] = '\0';
-unlock:
-	mutex_unlock(&cdev->cosm_mutex);
-	return count;
-}
-static DEVICE_ATTR_RW(firmware);
-
-static ssize_t
-ramdisk_show(struct device *dev, struct device_attribute *attr, char *buf)
-{
-	struct cosm_device *cdev = dev_get_drvdata(dev);
-	char *ramdisk;
-
-	if (!cdev)
-		return -EINVAL;
-
-	ramdisk = cdev->ramdisk;
-
-	if (ramdisk)
-		return scnprintf(buf, PAGE_SIZE, "%s\n", ramdisk);
-	return 0;
-}
-
-static ssize_t
-ramdisk_store(struct device *dev, struct device_attribute *attr,
-	      const char *buf, size_t count)
-{
-	struct cosm_device *cdev = dev_get_drvdata(dev);
-
-	if (!cdev)
-		return -EINVAL;
-
-	mutex_lock(&cdev->cosm_mutex);
-	kfree(cdev->ramdisk);
-
-	cdev->ramdisk = kmalloc(count + 1, GFP_KERNEL);
-	if (!cdev->ramdisk) {
-		count = -ENOMEM;
-		goto unlock;
-	}
-
-	strncpy(cdev->ramdisk, buf, count);
-
-	if (cdev->ramdisk[count - 1] == '\n')
-		cdev->ramdisk[count - 1] = '\0';
-	else
-		cdev->ramdisk[count] = '\0';
-unlock:
-	mutex_unlock(&cdev->cosm_mutex);
-	return count;
-}
-static DEVICE_ATTR_RW(ramdisk);
-
-static ssize_t
-bootmode_show(struct device *dev, struct device_attribute *attr, char *buf)
-{
-	struct cosm_device *cdev = dev_get_drvdata(dev);
-	char *bootmode;
-
-	if (!cdev)
-		return -EINVAL;
-
-	bootmode = cdev->bootmode;
-
-	if (bootmode)
-		return scnprintf(buf, PAGE_SIZE, "%s\n", bootmode);
-	return 0;
-}
-
-static ssize_t
-bootmode_store(struct device *dev, struct device_attribute *attr,
-	       const char *buf, size_t count)
-{
-	struct cosm_device *cdev = dev_get_drvdata(dev);
-
-	if (!cdev)
-		return -EINVAL;
-
-	if (!sysfs_streq(buf, "linux") && !sysfs_streq(buf, "flash"))
-		return -EINVAL;
-
-	mutex_lock(&cdev->cosm_mutex);
-	kfree(cdev->bootmode);
-
-	cdev->bootmode = kmalloc(count + 1, GFP_KERNEL);
-	if (!cdev->bootmode) {
-		count = -ENOMEM;
-		goto unlock;
-	}
-
-	strncpy(cdev->bootmode, buf, count);
-
-	if (cdev->bootmode[count - 1] == '\n')
-		cdev->bootmode[count - 1] = '\0';
-	else
-		cdev->bootmode[count] = '\0';
-unlock:
-	mutex_unlock(&cdev->cosm_mutex);
-	return count;
-}
-static DEVICE_ATTR_RW(bootmode);
-
-static ssize_t
-log_buf_addr_show(struct device *dev, struct device_attribute *attr,
-		  char *buf)
-{
-	struct cosm_device *cdev = dev_get_drvdata(dev);
-
-	if (!cdev)
-		return -EINVAL;
-
-	return scnprintf(buf, PAGE_SIZE, "%p\n", cdev->log_buf_addr);
-}
-
-static ssize_t
-log_buf_addr_store(struct device *dev, struct device_attribute *attr,
-		   const char *buf, size_t count)
-{
-	struct cosm_device *cdev = dev_get_drvdata(dev);
-	int ret;
-	unsigned long addr;
-
-	if (!cdev)
-		return -EINVAL;
-
-	ret = kstrtoul(buf, 16, &addr);
-	if (ret)
-		goto exit;
-
-	cdev->log_buf_addr = (void *)addr;
-	ret = count;
-exit:
-	return ret;
-}
-static DEVICE_ATTR_RW(log_buf_addr);
-
-static ssize_t
-log_buf_len_show(struct device *dev, struct device_attribute *attr,
-		 char *buf)
-{
-	struct cosm_device *cdev = dev_get_drvdata(dev);
-
-	if (!cdev)
-		return -EINVAL;
-
-	return scnprintf(buf, PAGE_SIZE, "%p\n", cdev->log_buf_len);
-}
-
-static ssize_t
-log_buf_len_store(struct device *dev, struct device_attribute *attr,
-		  const char *buf, size_t count)
-{
-	struct cosm_device *cdev = dev_get_drvdata(dev);
-	int ret;
-	unsigned long addr;
-
-	if (!cdev)
-		return -EINVAL;
-
-	ret = kstrtoul(buf, 16, &addr);
-	if (ret)
-		goto exit;
-
-	cdev->log_buf_len = (int *)addr;
-	ret = count;
-exit:
-	return ret;
-}
-static DEVICE_ATTR_RW(log_buf_len);
-
-static struct attribute *cosm_default_attrs[] = {
-	&dev_attr_family.attr,
-	&dev_attr_stepping.attr,
-	&dev_attr_state.attr,
-	&dev_attr_shutdown_status.attr,
-	&dev_attr_heartbeat_enable.attr,
-	&dev_attr_cmdline.attr,
-	&dev_attr_firmware.attr,
-	&dev_attr_ramdisk.attr,
-	&dev_attr_bootmode.attr,
-	&dev_attr_log_buf_addr.attr,
-	&dev_attr_log_buf_len.attr,
-
-	NULL
-};
-
-ATTRIBUTE_GROUPS(cosm_default);
-
-void cosm_sysfs_init(struct cosm_device *cdev)
-{
-	cdev->attr_group = cosm_default_groups;
-}
diff --git a/drivers/misc/mic/cosm_client/Makefile b/drivers/misc/mic/cosm_client/Makefile
deleted file mode 100644
index 5b62270bc2ab..000000000000
--- a/drivers/misc/mic/cosm_client/Makefile
+++ /dev/null
@@ -1,8 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-#
-# Makefile - Intel MIC COSM Client Driver
-# Copyright(c) 2015, Intel Corporation.
-#
-obj-$(CONFIG_MIC_COSM) += cosm_client.o
-
-cosm_client-objs += cosm_scif_client.o
diff --git a/drivers/misc/mic/cosm_client/cosm_scif_client.c b/drivers/misc/mic/cosm_client/cosm_scif_client.c
deleted file mode 100644
index a03213dd9319..000000000000
--- a/drivers/misc/mic/cosm_client/cosm_scif_client.c
+++ /dev/null
@@ -1,269 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel MIC COSM Client Driver
- */
-#include <linux/module.h>
-#include <linux/delay.h>
-#include <linux/reboot.h>
-#include <linux/kthread.h>
-#include <linux/sched/signal.h>
-
-#include "../cosm/cosm_main.h"
-
-#define COSM_SCIF_MAX_RETRIES 10
-#define COSM_HEARTBEAT_SEND_MSEC (COSM_HEARTBEAT_SEND_SEC * MSEC_PER_SEC)
-
-static struct task_struct *client_thread;
-static scif_epd_t client_epd;
-static struct scif_peer_dev *client_spdev;
-
-/*
- * Reboot notifier: receives shutdown status from the OS and communicates it
- * back to the COSM process on the host
- */
-static int cosm_reboot_event(struct notifier_block *this, unsigned long event,
-			     void *ptr)
-{
-	struct cosm_msg msg = { .id = COSM_MSG_SHUTDOWN_STATUS };
-	int rc;
-
-	event = (event == SYS_RESTART) ? SYSTEM_RESTART : event;
-	dev_info(&client_spdev->dev, "%s %d received event %ld\n",
-		 __func__, __LINE__, event);
-
-	msg.shutdown_status = event;
-	rc = scif_send(client_epd, &msg, sizeof(msg), SCIF_SEND_BLOCK);
-	if (rc < 0)
-		dev_err(&client_spdev->dev, "%s %d scif_send rc %d\n",
-			__func__, __LINE__, rc);
-
-	return NOTIFY_DONE;
-}
-
-static struct notifier_block cosm_reboot = {
-	.notifier_call  = cosm_reboot_event,
-};
-
-/* Set system time from timespec value received from the host */
-static void cosm_set_time(struct cosm_msg *msg)
-{
-	struct timespec64 ts = {
-		.tv_sec = msg->timespec.tv_sec,
-		.tv_nsec = msg->timespec.tv_nsec,
-	};
-	int rc = do_settimeofday64(&ts);
-
-	if (rc)
-		dev_err(&client_spdev->dev, "%s: %d settimeofday rc %d\n",
-			__func__, __LINE__, rc);
-}
-
-/* COSM client receive message processing */
-static void cosm_client_recv(void)
-{
-	struct cosm_msg msg;
-	int rc;
-
-	while (1) {
-		rc = scif_recv(client_epd, &msg, sizeof(msg), 0);
-		if (!rc) {
-			return;
-		} else if (rc < 0) {
-			dev_err(&client_spdev->dev, "%s: %d rc %d\n",
-				__func__, __LINE__, rc);
-			return;
-		}
-
-		dev_dbg(&client_spdev->dev, "%s: %d rc %d id 0x%llx\n",
-			__func__, __LINE__, rc, msg.id);
-
-		switch (msg.id) {
-		case COSM_MSG_SYNC_TIME:
-			cosm_set_time(&msg);
-			break;
-		case COSM_MSG_SHUTDOWN:
-			orderly_poweroff(true);
-			break;
-		default:
-			dev_err(&client_spdev->dev, "%s: %d unknown id %lld\n",
-				__func__, __LINE__, msg.id);
-			break;
-		}
-	}
-}
-
-/* Initiate connection to the COSM server on the host */
-static int cosm_scif_connect(void)
-{
-	struct scif_port_id port_id;
-	int i, rc;
-
-	client_epd = scif_open();
-	if (!client_epd) {
-		dev_err(&client_spdev->dev, "%s %d scif_open failed\n",
-			__func__, __LINE__);
-		return -ENOMEM;
-	}
-
-	port_id.node = 0;
-	port_id.port = SCIF_COSM_LISTEN_PORT;
-
-	for (i = 0; i < COSM_SCIF_MAX_RETRIES; i++) {
-		rc = scif_connect(client_epd, &port_id);
-		if (rc < 0)
-			msleep(1000);
-		else
-			break;
-	}
-
-	if (rc < 0) {
-		dev_err(&client_spdev->dev, "%s %d scif_connect rc %d\n",
-			__func__, __LINE__, rc);
-		scif_close(client_epd);
-		client_epd = NULL;
-	}
-	return rc < 0 ? rc : 0;
-}
-
-/* Close host SCIF connection */
-static void cosm_scif_connect_exit(void)
-{
-	if (client_epd) {
-		scif_close(client_epd);
-		client_epd = NULL;
-	}
-}
-
-/*
- * COSM SCIF client thread function: waits for messages from the host and sends
- * a heartbeat to the host
- */
-static int cosm_scif_client(void *unused)
-{
-	struct cosm_msg msg = { .id = COSM_MSG_HEARTBEAT };
-	struct scif_pollepd pollepd;
-	int rc;
-
-	allow_signal(SIGKILL);
-
-	while (!kthread_should_stop()) {
-		pollepd.epd = client_epd;
-		pollepd.events = EPOLLIN;
-
-		rc = scif_poll(&pollepd, 1, COSM_HEARTBEAT_SEND_MSEC);
-		if (rc < 0) {
-			if (-EINTR != rc)
-				dev_err(&client_spdev->dev,
-					"%s %d scif_poll rc %d\n",
-					__func__, __LINE__, rc);
-			continue;
-		}
-
-		if (pollepd.revents & EPOLLIN)
-			cosm_client_recv();
-
-		msg.id = COSM_MSG_HEARTBEAT;
-		rc = scif_send(client_epd, &msg, sizeof(msg), SCIF_SEND_BLOCK);
-		if (rc < 0)
-			dev_err(&client_spdev->dev, "%s %d scif_send rc %d\n",
-				__func__, __LINE__, rc);
-	}
-
-	dev_dbg(&client_spdev->dev, "%s %d Client thread stopped\n",
-		__func__, __LINE__);
-	return 0;
-}
-
-static void cosm_scif_probe(struct scif_peer_dev *spdev)
-{
-	int rc;
-
-	dev_dbg(&spdev->dev, "%s %d: dnode %d\n",
-		__func__, __LINE__, spdev->dnode);
-
-	/* We are only interested in the host with spdev->dnode == 0 */
-	if (spdev->dnode)
-		return;
-
-	client_spdev = spdev;
-	rc = cosm_scif_connect();
-	if (rc)
-		goto exit;
-
-	rc = register_reboot_notifier(&cosm_reboot);
-	if (rc) {
-		dev_err(&spdev->dev,
-			"reboot notifier registration failed rc %d\n", rc);
-		goto connect_exit;
-	}
-
-	client_thread = kthread_run(cosm_scif_client, NULL, "cosm_client");
-	if (IS_ERR(client_thread)) {
-		rc = PTR_ERR(client_thread);
-		dev_err(&spdev->dev, "%s %d kthread_run rc %d\n",
-			__func__, __LINE__, rc);
-		goto unreg_reboot;
-	}
-	return;
-unreg_reboot:
-	unregister_reboot_notifier(&cosm_reboot);
-connect_exit:
-	cosm_scif_connect_exit();
-exit:
-	client_spdev = NULL;
-}
-
-static void cosm_scif_remove(struct scif_peer_dev *spdev)
-{
-	int rc;
-
-	dev_dbg(&spdev->dev, "%s %d: dnode %d\n",
-		__func__, __LINE__, spdev->dnode);
-
-	if (spdev->dnode)
-		return;
-
-	if (!IS_ERR_OR_NULL(client_thread)) {
-		rc = send_sig(SIGKILL, client_thread, 0);
-		if (rc) {
-			pr_err("%s %d send_sig rc %d\n",
-			       __func__, __LINE__, rc);
-			return;
-		}
-		kthread_stop(client_thread);
-	}
-	unregister_reboot_notifier(&cosm_reboot);
-	cosm_scif_connect_exit();
-	client_spdev = NULL;
-}
-
-static struct scif_client scif_client_cosm = {
-	.name = KBUILD_MODNAME,
-	.probe = cosm_scif_probe,
-	.remove = cosm_scif_remove,
-};
-
-static int __init cosm_client_init(void)
-{
-	int rc = scif_client_register(&scif_client_cosm);
-
-	if (rc)
-		pr_err("scif_client_register failed rc %d\n", rc);
-	return rc;
-}
-
-static void __exit cosm_client_exit(void)
-{
-	scif_client_unregister(&scif_client_cosm);
-}
-
-module_init(cosm_client_init);
-module_exit(cosm_client_exit);
-
-MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Intel(R) MIC card OS state management client driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/misc/mic/host/Makefile b/drivers/misc/mic/host/Makefile
deleted file mode 100644
index 25f153367980..000000000000
--- a/drivers/misc/mic/host/Makefile
+++ /dev/null
@@ -1,12 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-#
-# Makefile - Intel MIC Linux driver.
-# Copyright(c) 2013, Intel Corporation.
-#
-obj-$(CONFIG_INTEL_MIC_HOST) += mic_host.o
-mic_host-objs := mic_main.o
-mic_host-objs += mic_x100.o
-mic_host-objs += mic_smpt.o
-mic_host-objs += mic_intr.o
-mic_host-objs += mic_boot.o
-mic_host-objs += mic_debugfs.o
diff --git a/drivers/misc/mic/host/mic_boot.c b/drivers/misc/mic/host/mic_boot.c
deleted file mode 100644
index 8cb85b8b3e19..000000000000
--- a/drivers/misc/mic/host/mic_boot.c
+++ /dev/null
@@ -1,588 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC Host driver.
- */
-#include <linux/delay.h>
-#include <linux/firmware.h>
-#include <linux/pci.h>
-#include <linux/kmod.h>
-#include <linux/dma-map-ops.h>
-#include <linux/mic_common.h>
-#include <linux/mic_bus.h>
-#include "../bus/scif_bus.h"
-#include "../bus/vop_bus.h"
-#include "../common/mic_dev.h"
-#include "mic_device.h"
-#include "mic_smpt.h"
-
-static inline struct mic_device *vpdev_to_mdev(struct device *dev)
-{
-	return dev_get_drvdata(dev->parent);
-}
-
-static dma_addr_t
-_mic_dma_map_page(struct device *dev, struct page *page,
-		  unsigned long offset, size_t size,
-		  enum dma_data_direction dir, unsigned long attrs)
-{
-	void *va = phys_to_virt(page_to_phys(page)) + offset;
-	struct mic_device *mdev = vpdev_to_mdev(dev);
-
-	return mic_map_single(mdev, va, size);
-}
-
-static void _mic_dma_unmap_page(struct device *dev, dma_addr_t dma_addr,
-				size_t size, enum dma_data_direction dir,
-				unsigned long attrs)
-{
-	struct mic_device *mdev = vpdev_to_mdev(dev);
-
-	mic_unmap_single(mdev, dma_addr, size);
-}
-
-static const struct dma_map_ops _mic_dma_ops = {
-	.map_page = _mic_dma_map_page,
-	.unmap_page = _mic_dma_unmap_page,
-};
-
-static struct mic_irq *
-__mic_request_irq(struct vop_device *vpdev,
-		  irqreturn_t (*func)(int irq, void *data),
-		  const char *name, void *data, int intr_src)
-{
-	struct mic_device *mdev = vpdev_to_mdev(&vpdev->dev);
-
-	return mic_request_threaded_irq(mdev, func, NULL, name, data,
-					intr_src, MIC_INTR_DB);
-}
-
-static void __mic_free_irq(struct vop_device *vpdev,
-			   struct mic_irq *cookie, void *data)
-{
-	struct mic_device *mdev = vpdev_to_mdev(&vpdev->dev);
-
-	mic_free_irq(mdev, cookie, data);
-}
-
-static void __mic_ack_interrupt(struct vop_device *vpdev, int num)
-{
-	struct mic_device *mdev = vpdev_to_mdev(&vpdev->dev);
-
-	mdev->ops->intr_workarounds(mdev);
-}
-
-static int __mic_next_db(struct vop_device *vpdev)
-{
-	struct mic_device *mdev = vpdev_to_mdev(&vpdev->dev);
-
-	return mic_next_db(mdev);
-}
-
-static void *__mic_get_dp(struct vop_device *vpdev)
-{
-	struct mic_device *mdev = vpdev_to_mdev(&vpdev->dev);
-
-	return mdev->dp;
-}
-
-static void __iomem *__mic_get_remote_dp(struct vop_device *vpdev)
-{
-	return NULL;
-}
-
-static void __mic_send_intr(struct vop_device *vpdev, int db)
-{
-	struct mic_device *mdev = vpdev_to_mdev(&vpdev->dev);
-
-	mdev->ops->send_intr(mdev, db);
-}
-
-static void __iomem *__mic_ioremap(struct vop_device *vpdev,
-				   dma_addr_t pa, size_t len)
-{
-	struct mic_device *mdev = vpdev_to_mdev(&vpdev->dev);
-
-	return mdev->aper.va + pa;
-}
-
-static void __mic_iounmap(struct vop_device *vpdev, void __iomem *va)
-{
-	/* nothing to do */
-}
-
-static struct vop_hw_ops vop_hw_ops = {
-	.request_irq = __mic_request_irq,
-	.free_irq = __mic_free_irq,
-	.ack_interrupt = __mic_ack_interrupt,
-	.next_db = __mic_next_db,
-	.get_dp = __mic_get_dp,
-	.get_remote_dp = __mic_get_remote_dp,
-	.send_intr = __mic_send_intr,
-	.remap = __mic_ioremap,
-	.unmap = __mic_iounmap,
-};
-
-static inline struct mic_device *scdev_to_mdev(struct scif_hw_dev *scdev)
-{
-	return dev_get_drvdata(scdev->dev.parent);
-}
-
-static void *__mic_dma_alloc(struct device *dev, size_t size,
-			     dma_addr_t *dma_handle, gfp_t gfp,
-			     unsigned long attrs)
-{
-	struct scif_hw_dev *scdev = dev_get_drvdata(dev);
-	struct mic_device *mdev = scdev_to_mdev(scdev);
-	dma_addr_t tmp;
-	void *va = kzalloc(size, gfp);
-
-	if (va) {
-		tmp = mic_map_single(mdev, va, size);
-		if (dma_mapping_error(dev, tmp)) {
-			kfree(va);
-			va = NULL;
-		} else {
-			*dma_handle = tmp;
-		}
-	}
-	return va;
-}
-
-static void __mic_dma_free(struct device *dev, size_t size, void *vaddr,
-			   dma_addr_t dma_handle, unsigned long attrs)
-{
-	struct scif_hw_dev *scdev = dev_get_drvdata(dev);
-	struct mic_device *mdev = scdev_to_mdev(scdev);
-
-	mic_unmap_single(mdev, dma_handle, size);
-	kfree(vaddr);
-}
-
-static dma_addr_t
-__mic_dma_map_page(struct device *dev, struct page *page, unsigned long offset,
-		   size_t size, enum dma_data_direction dir,
-		   unsigned long attrs)
-{
-	void *va = phys_to_virt(page_to_phys(page)) + offset;
-	struct scif_hw_dev *scdev = dev_get_drvdata(dev);
-	struct mic_device *mdev = scdev_to_mdev(scdev);
-
-	return mic_map_single(mdev, va, size);
-}
-
-static void
-__mic_dma_unmap_page(struct device *dev, dma_addr_t dma_addr,
-		     size_t size, enum dma_data_direction dir,
-		     unsigned long attrs)
-{
-	struct scif_hw_dev *scdev = dev_get_drvdata(dev);
-	struct mic_device *mdev = scdev_to_mdev(scdev);
-
-	mic_unmap_single(mdev, dma_addr, size);
-}
-
-static int __mic_dma_map_sg(struct device *dev, struct scatterlist *sg,
-			    int nents, enum dma_data_direction dir,
-			    unsigned long attrs)
-{
-	struct scif_hw_dev *scdev = dev_get_drvdata(dev);
-	struct mic_device *mdev = scdev_to_mdev(scdev);
-	struct scatterlist *s;
-	int i, j, ret;
-	dma_addr_t da;
-
-	ret = dma_map_sg(&mdev->pdev->dev, sg, nents, dir);
-	if (ret <= 0)
-		return 0;
-
-	for_each_sg(sg, s, nents, i) {
-		da = mic_map(mdev, sg_dma_address(s) + s->offset, s->length);
-		if (!da)
-			goto err;
-		sg_dma_address(s) = da;
-	}
-	return nents;
-err:
-	for_each_sg(sg, s, i, j) {
-		mic_unmap(mdev, sg_dma_address(s), s->length);
-		sg_dma_address(s) = mic_to_dma_addr(mdev, sg_dma_address(s));
-	}
-	dma_unmap_sg(&mdev->pdev->dev, sg, nents, dir);
-	return 0;
-}
-
-static void __mic_dma_unmap_sg(struct device *dev,
-			       struct scatterlist *sg, int nents,
-			       enum dma_data_direction dir,
-			       unsigned long attrs)
-{
-	struct scif_hw_dev *scdev = dev_get_drvdata(dev);
-	struct mic_device *mdev = scdev_to_mdev(scdev);
-	struct scatterlist *s;
-	dma_addr_t da;
-	int i;
-
-	for_each_sg(sg, s, nents, i) {
-		da = mic_to_dma_addr(mdev, sg_dma_address(s));
-		mic_unmap(mdev, sg_dma_address(s), s->length);
-		sg_dma_address(s) = da;
-	}
-	dma_unmap_sg(&mdev->pdev->dev, sg, nents, dir);
-}
-
-static const struct dma_map_ops __mic_dma_ops = {
-	.alloc = __mic_dma_alloc,
-	.free = __mic_dma_free,
-	.map_page = __mic_dma_map_page,
-	.unmap_page = __mic_dma_unmap_page,
-	.map_sg = __mic_dma_map_sg,
-	.unmap_sg = __mic_dma_unmap_sg,
-};
-
-static struct mic_irq *
-___mic_request_irq(struct scif_hw_dev *scdev,
-		   irqreturn_t (*func)(int irq, void *data),
-				       const char *name,
-				       void *data, int db)
-{
-	struct mic_device *mdev = scdev_to_mdev(scdev);
-
-	return mic_request_threaded_irq(mdev, func, NULL, name, data,
-					db, MIC_INTR_DB);
-}
-
-static void
-___mic_free_irq(struct scif_hw_dev *scdev,
-		struct mic_irq *cookie, void *data)
-{
-	struct mic_device *mdev = scdev_to_mdev(scdev);
-
-	mic_free_irq(mdev, cookie, data);
-}
-
-static void ___mic_ack_interrupt(struct scif_hw_dev *scdev, int num)
-{
-	struct mic_device *mdev = scdev_to_mdev(scdev);
-
-	mdev->ops->intr_workarounds(mdev);
-}
-
-static int ___mic_next_db(struct scif_hw_dev *scdev)
-{
-	struct mic_device *mdev = scdev_to_mdev(scdev);
-
-	return mic_next_db(mdev);
-}
-
-static void ___mic_send_intr(struct scif_hw_dev *scdev, int db)
-{
-	struct mic_device *mdev = scdev_to_mdev(scdev);
-
-	mdev->ops->send_intr(mdev, db);
-}
-
-static void __iomem *___mic_ioremap(struct scif_hw_dev *scdev,
-				    phys_addr_t pa, size_t len)
-{
-	struct mic_device *mdev = scdev_to_mdev(scdev);
-
-	return mdev->aper.va + pa;
-}
-
-static void ___mic_iounmap(struct scif_hw_dev *scdev, void __iomem *va)
-{
-	/* nothing to do */
-}
-
-static struct scif_hw_ops scif_hw_ops = {
-	.request_irq = ___mic_request_irq,
-	.free_irq = ___mic_free_irq,
-	.ack_interrupt = ___mic_ack_interrupt,
-	.next_db = ___mic_next_db,
-	.send_intr = ___mic_send_intr,
-	.remap = ___mic_ioremap,
-	.unmap = ___mic_iounmap,
-};
-
-static inline struct mic_device *mbdev_to_mdev(struct mbus_device *mbdev)
-{
-	return dev_get_drvdata(mbdev->dev.parent);
-}
-
-static dma_addr_t
-mic_dma_map_page(struct device *dev, struct page *page,
-		 unsigned long offset, size_t size, enum dma_data_direction dir,
-		 unsigned long attrs)
-{
-	void *va = phys_to_virt(page_to_phys(page)) + offset;
-	struct mic_device *mdev = dev_get_drvdata(dev->parent);
-
-	return mic_map_single(mdev, va, size);
-}
-
-static void
-mic_dma_unmap_page(struct device *dev, dma_addr_t dma_addr,
-		   size_t size, enum dma_data_direction dir,
-		   unsigned long attrs)
-{
-	struct mic_device *mdev = dev_get_drvdata(dev->parent);
-	mic_unmap_single(mdev, dma_addr, size);
-}
-
-static const struct dma_map_ops mic_dma_ops = {
-	.map_page = mic_dma_map_page,
-	.unmap_page = mic_dma_unmap_page,
-};
-
-static struct mic_irq *
-_mic_request_threaded_irq(struct mbus_device *mbdev,
-			  irq_handler_t handler, irq_handler_t thread_fn,
-			  const char *name, void *data, int intr_src)
-{
-	return mic_request_threaded_irq(mbdev_to_mdev(mbdev), handler,
-					thread_fn, name, data,
-					intr_src, MIC_INTR_DMA);
-}
-
-static void _mic_free_irq(struct mbus_device *mbdev,
-			  struct mic_irq *cookie, void *data)
-{
-	mic_free_irq(mbdev_to_mdev(mbdev), cookie, data);
-}
-
-static void _mic_ack_interrupt(struct mbus_device *mbdev, int num)
-{
-	struct mic_device *mdev = mbdev_to_mdev(mbdev);
-	mdev->ops->intr_workarounds(mdev);
-}
-
-static struct mbus_hw_ops mbus_hw_ops = {
-	.request_threaded_irq = _mic_request_threaded_irq,
-	.free_irq = _mic_free_irq,
-	.ack_interrupt = _mic_ack_interrupt,
-};
-
-/* Initialize the MIC bootparams */
-void mic_bootparam_init(struct mic_device *mdev)
-{
-	struct mic_bootparam *bootparam = mdev->dp;
-
-	bootparam->magic = cpu_to_le32(MIC_MAGIC);
-	bootparam->h2c_config_db = -1;
-	bootparam->node_id = mdev->id + 1;
-	bootparam->scif_host_dma_addr = 0x0;
-	bootparam->scif_card_dma_addr = 0x0;
-	bootparam->c2h_scif_db = -1;
-	bootparam->h2c_scif_db = -1;
-}
-
-static inline struct mic_device *cosmdev_to_mdev(struct cosm_device *cdev)
-{
-	return dev_get_drvdata(cdev->dev.parent);
-}
-
-static void _mic_reset(struct cosm_device *cdev)
-{
-	struct mic_device *mdev = cosmdev_to_mdev(cdev);
-
-	mdev->ops->reset_fw_ready(mdev);
-	mdev->ops->reset(mdev);
-}
-
-static bool _mic_ready(struct cosm_device *cdev)
-{
-	struct mic_device *mdev = cosmdev_to_mdev(cdev);
-
-	return mdev->ops->is_fw_ready(mdev);
-}
-
-/**
- * mic_request_dma_chans - Request DMA channels
- * @mdev: pointer to mic_device instance
- *
- * returns number of DMA channels acquired
- */
-static int mic_request_dma_chans(struct mic_device *mdev)
-{
-	dma_cap_mask_t mask;
-	struct dma_chan *chan;
-
-	dma_cap_zero(mask);
-	dma_cap_set(DMA_MEMCPY, mask);
-
-	do {
-		chan = dma_request_channel(mask, mdev->ops->dma_filter,
-					   &mdev->pdev->dev);
-		if (chan) {
-			mdev->dma_ch[mdev->num_dma_ch++] = chan;
-			if (mdev->num_dma_ch >= MIC_MAX_DMA_CHAN)
-				break;
-		}
-	} while (chan);
-	dev_info(&mdev->pdev->dev, "DMA channels # %d\n", mdev->num_dma_ch);
-	return mdev->num_dma_ch;
-}
-
-/**
- * mic_free_dma_chans - release DMA channels
- * @mdev: pointer to mic_device instance
- *
- * returns none
- */
-static void mic_free_dma_chans(struct mic_device *mdev)
-{
-	int i = 0;
-
-	for (i = 0; i < mdev->num_dma_ch; i++) {
-		dma_release_channel(mdev->dma_ch[i]);
-		mdev->dma_ch[i] = NULL;
-	}
-	mdev->num_dma_ch = 0;
-}
-
-/**
- * _mic_start - Start the MIC.
- * @cdev: pointer to cosm_device instance
- * @id: MIC device id/index provided by COSM used in other drivers like SCIF
- *
- * This function prepares an MIC for boot and initiates boot.
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- *
- * For all cosm_hw_ops the caller holds a mutex to ensure serialization.
- */
-static int _mic_start(struct cosm_device *cdev, int id)
-{
-	struct mic_device *mdev = cosmdev_to_mdev(cdev);
-	int rc;
-
-	mic_bootparam_init(mdev);
-	mdev->dma_mbdev = mbus_register_device(&mdev->pdev->dev,
-					       MBUS_DEV_DMA_HOST, &mic_dma_ops,
-					       &mbus_hw_ops, id, mdev->mmio.va);
-	if (IS_ERR(mdev->dma_mbdev)) {
-		rc = PTR_ERR(mdev->dma_mbdev);
-		goto unlock_ret;
-	}
-	if (!mic_request_dma_chans(mdev)) {
-		rc = -ENODEV;
-		goto dma_remove;
-	}
-	mdev->scdev = scif_register_device(&mdev->pdev->dev, MIC_SCIF_DEV,
-					   &__mic_dma_ops, &scif_hw_ops,
-					   id + 1, 0, &mdev->mmio,
-					   &mdev->aper, mdev->dp, NULL,
-					   mdev->dma_ch, mdev->num_dma_ch,
-					   true);
-	if (IS_ERR(mdev->scdev)) {
-		rc = PTR_ERR(mdev->scdev);
-		goto dma_free;
-	}
-
-	mdev->vpdev = vop_register_device(&mdev->pdev->dev,
-					  VOP_DEV_TRNSP, &_mic_dma_ops,
-					  &vop_hw_ops, id + 1, &mdev->aper,
-					  mdev->dma_ch[0]);
-	if (IS_ERR(mdev->vpdev)) {
-		rc = PTR_ERR(mdev->vpdev);
-		goto scif_remove;
-	}
-
-	rc = mdev->ops->load_mic_fw(mdev, NULL);
-	if (rc)
-		goto vop_remove;
-	mic_smpt_restore(mdev);
-	mic_intr_restore(mdev);
-	mdev->intr_ops->enable_interrupts(mdev);
-	mdev->ops->write_spad(mdev, MIC_DPLO_SPAD, mdev->dp_dma_addr);
-	mdev->ops->write_spad(mdev, MIC_DPHI_SPAD, mdev->dp_dma_addr >> 32);
-	mdev->ops->send_firmware_intr(mdev);
-	goto unlock_ret;
-vop_remove:
-	vop_unregister_device(mdev->vpdev);
-scif_remove:
-	scif_unregister_device(mdev->scdev);
-dma_free:
-	mic_free_dma_chans(mdev);
-dma_remove:
-	mbus_unregister_device(mdev->dma_mbdev);
-unlock_ret:
-	return rc;
-}
-
-/**
- * _mic_stop - Prepare the MIC for reset and trigger reset.
- * @cdev: pointer to cosm_device instance
- * @force: force a MIC to reset even if it is already offline.
- *
- * RETURNS: None.
- */
-static void _mic_stop(struct cosm_device *cdev, bool force)
-{
-	struct mic_device *mdev = cosmdev_to_mdev(cdev);
-
-	/*
-	 * Since SCIF handles card shutdown and reset (using COSM), it will
-	 * will be the first to be registered and the last to be
-	 * unregistered.
-	 */
-	vop_unregister_device(mdev->vpdev);
-	scif_unregister_device(mdev->scdev);
-	mic_free_dma_chans(mdev);
-	mbus_unregister_device(mdev->dma_mbdev);
-	mic_bootparam_init(mdev);
-}
-
-static ssize_t _mic_family(struct cosm_device *cdev, char *buf)
-{
-	struct mic_device *mdev = cosmdev_to_mdev(cdev);
-	static const char *family[MIC_FAMILY_LAST] = { "x100", "Unknown" };
-
-	return scnprintf(buf, PAGE_SIZE, "%s\n", family[mdev->family]);
-}
-
-static ssize_t _mic_stepping(struct cosm_device *cdev, char *buf)
-{
-	struct mic_device *mdev = cosmdev_to_mdev(cdev);
-	const char *string = "??";
-
-	switch (mdev->stepping) {
-	case MIC_A0_STEP:
-		string = "A0";
-		break;
-	case MIC_B0_STEP:
-		string = "B0";
-		break;
-	case MIC_B1_STEP:
-		string = "B1";
-		break;
-	case MIC_C0_STEP:
-		string = "C0";
-		break;
-	default:
-		break;
-	}
-	return scnprintf(buf, PAGE_SIZE, "%s\n", string);
-}
-
-static struct mic_mw *_mic_aper(struct cosm_device *cdev)
-{
-	struct mic_device *mdev = cosmdev_to_mdev(cdev);
-
-	return &mdev->aper;
-}
-
-struct cosm_hw_ops cosm_hw_ops = {
-	.reset = _mic_reset,
-	.force_reset = _mic_reset,
-	.post_reset = NULL,
-	.ready = _mic_ready,
-	.start = _mic_start,
-	.stop = _mic_stop,
-	.family = _mic_family,
-	.stepping = _mic_stepping,
-	.aper = _mic_aper,
-};
diff --git a/drivers/misc/mic/host/mic_debugfs.c b/drivers/misc/mic/host/mic_debugfs.c
deleted file mode 100644
index ffda740e20d5..000000000000
--- a/drivers/misc/mic/host/mic_debugfs.c
+++ /dev/null
@@ -1,149 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC Host driver.
- */
-#include <linux/debugfs.h>
-#include <linux/pci.h>
-#include <linux/seq_file.h>
-
-#include <linux/mic_common.h>
-#include "../common/mic_dev.h"
-#include "mic_device.h"
-#include "mic_smpt.h"
-
-/* Debugfs parent dir */
-static struct dentry *mic_dbg;
-
-static int mic_smpt_show(struct seq_file *s, void *pos)
-{
-	int i;
-	struct mic_device *mdev = s->private;
-	unsigned long flags;
-
-	seq_printf(s, "MIC %-2d |%-10s| %-14s %-10s\n",
-		   mdev->id, "SMPT entry", "SW DMA addr", "RefCount");
-	seq_puts(s, "====================================================\n");
-
-	if (mdev->smpt) {
-		struct mic_smpt_info *smpt_info = mdev->smpt;
-		spin_lock_irqsave(&smpt_info->smpt_lock, flags);
-		for (i = 0; i < smpt_info->info.num_reg; i++) {
-			seq_printf(s, "%9s|%-10d| %-#14llx %-10lld\n",
-				   " ",  i, smpt_info->entry[i].dma_addr,
-				   smpt_info->entry[i].ref_count);
-		}
-		spin_unlock_irqrestore(&smpt_info->smpt_lock, flags);
-	}
-	seq_puts(s, "====================================================\n");
-	return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(mic_smpt);
-
-static int mic_post_code_show(struct seq_file *s, void *pos)
-{
-	struct mic_device *mdev = s->private;
-	u32 reg = mdev->ops->get_postcode(mdev);
-
-	seq_printf(s, "%c%c", reg & 0xff, (reg >> 8) & 0xff);
-	return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(mic_post_code);
-
-static int mic_msi_irq_info_show(struct seq_file *s, void *pos)
-{
-	struct mic_device *mdev  = s->private;
-	int reg;
-	int i, j;
-	u16 entry;
-	u16 vector;
-	struct pci_dev *pdev = mdev->pdev;
-
-	if (pci_dev_msi_enabled(pdev)) {
-		for (i = 0; i < mdev->irq_info.num_vectors; i++) {
-			if (pdev->msix_enabled) {
-				entry = mdev->irq_info.msix_entries[i].entry;
-				vector = mdev->irq_info.msix_entries[i].vector;
-			} else {
-				entry = 0;
-				vector = pdev->irq;
-			}
-
-			reg = mdev->intr_ops->read_msi_to_src_map(mdev, entry);
-
-			seq_printf(s, "%s %-10d %s %-10d MXAR[%d]: %08X\n",
-				   "IRQ:", vector, "Entry:", entry, i, reg);
-
-			seq_printf(s, "%-10s", "offset:");
-			for (j = (MIC_NUM_OFFSETS - 1); j >= 0; j--)
-				seq_printf(s, "%4d ", j);
-			seq_puts(s, "\n");
-
-
-			seq_printf(s, "%-10s", "count:");
-			for (j = (MIC_NUM_OFFSETS - 1); j >= 0; j--)
-				seq_printf(s, "%4d ",
-					   (mdev->irq_info.mic_msi_map[i] &
-					   BIT(j)) ? 1 : 0);
-			seq_puts(s, "\n\n");
-		}
-	} else {
-		seq_puts(s, "MSI/MSIx interrupts not enabled\n");
-	}
-
-	return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(mic_msi_irq_info);
-
-/*
- * mic_create_debug_dir - Initialize MIC debugfs entries.
- */
-void mic_create_debug_dir(struct mic_device *mdev)
-{
-	char name[16];
-
-	if (!mic_dbg)
-		return;
-
-	scnprintf(name, sizeof(name), "mic%d", mdev->id);
-	mdev->dbg_dir = debugfs_create_dir(name, mic_dbg);
-
-	debugfs_create_file("smpt", 0444, mdev->dbg_dir, mdev,
-			    &mic_smpt_fops);
-
-	debugfs_create_file("post_code", 0444, mdev->dbg_dir, mdev,
-			    &mic_post_code_fops);
-
-	debugfs_create_file("msi_irq_info", 0444, mdev->dbg_dir, mdev,
-			    &mic_msi_irq_info_fops);
-}
-
-/*
- * mic_delete_debug_dir - Uninitialize MIC debugfs entries.
- */
-void mic_delete_debug_dir(struct mic_device *mdev)
-{
-	debugfs_remove_recursive(mdev->dbg_dir);
-}
-
-/*
- * mic_init_debugfs - Initialize global debugfs entry.
- */
-void __init mic_init_debugfs(void)
-{
-	mic_dbg = debugfs_create_dir(KBUILD_MODNAME, NULL);
-}
-
-/*
- * mic_exit_debugfs - Uninitialize global debugfs entry
- */
-void mic_exit_debugfs(void)
-{
-	debugfs_remove(mic_dbg);
-}
diff --git a/drivers/misc/mic/host/mic_device.h b/drivers/misc/mic/host/mic_device.h
deleted file mode 100644
index 41bcd308ae59..000000000000
--- a/drivers/misc/mic/host/mic_device.h
+++ /dev/null
@@ -1,157 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC Host driver.
- */
-#ifndef _MIC_DEVICE_H_
-#define _MIC_DEVICE_H_
-
-#include <linux/cdev.h>
-#include <linux/idr.h>
-#include <linux/notifier.h>
-#include <linux/irqreturn.h>
-#include <linux/dmaengine.h>
-#include <linux/miscdevice.h>
-#include <linux/mic_bus.h>
-#include "../bus/scif_bus.h"
-#include "../bus/vop_bus.h"
-#include "../bus/cosm_bus.h"
-#include "mic_intr.h"
-
-/**
- * enum mic_stepping - MIC stepping ids.
- */
-enum mic_stepping {
-	MIC_A0_STEP = 0x0,
-	MIC_B0_STEP = 0x10,
-	MIC_B1_STEP = 0x11,
-	MIC_C0_STEP = 0x20,
-};
-
-extern struct cosm_hw_ops cosm_hw_ops;
-
-/**
- * struct mic_device -  MIC device information for each card.
- *
- * @mmio: MMIO bar information.
- * @aper: Aperture bar information.
- * @family: The MIC family to which this device belongs.
- * @ops: MIC HW specific operations.
- * @id: The unique device id for this MIC device.
- * @stepping: Stepping ID.
- * @pdev: Underlying PCI device.
- * @mic_mutex: Mutex for synchronizing access to mic_device.
- * @intr_ops: HW specific interrupt operations.
- * @smpt_ops: Hardware specific SMPT operations.
- * @smpt: MIC SMPT information.
- * @intr_info: H/W specific interrupt information.
- * @irq_info: The OS specific irq information
- * @dbg_dir: debugfs directory of this MIC device.
- * @bootaddr: MIC boot address.
- * @dp: virtio device page
- * @dp_dma_addr: virtio device page DMA address.
- * @dma_mbdev: MIC BUS DMA device.
- * @dma_ch - Array of DMA channels
- * @num_dma_ch - Number of DMA channels available
- * @scdev: SCIF device on the SCIF virtual bus.
- * @vpdev: Virtio over PCIe device on the VOP virtual bus.
- * @cosm_dev: COSM device
- */
-struct mic_device {
-	struct mic_mw mmio;
-	struct mic_mw aper;
-	enum mic_hw_family family;
-	struct mic_hw_ops *ops;
-	int id;
-	enum mic_stepping stepping;
-	struct pci_dev *pdev;
-	struct mutex mic_mutex;
-	struct mic_hw_intr_ops *intr_ops;
-	struct mic_smpt_ops *smpt_ops;
-	struct mic_smpt_info *smpt;
-	struct mic_intr_info *intr_info;
-	struct mic_irq_info irq_info;
-	struct dentry *dbg_dir;
-	u32 bootaddr;
-	void *dp;
-	dma_addr_t dp_dma_addr;
-	struct mbus_device *dma_mbdev;
-	struct dma_chan *dma_ch[MIC_MAX_DMA_CHAN];
-	int num_dma_ch;
-	struct scif_hw_dev *scdev;
-	struct vop_device *vpdev;
-	struct cosm_device *cosm_dev;
-};
-
-/**
- * struct mic_hw_ops - MIC HW specific operations.
- * @aper_bar: Aperture bar resource number.
- * @mmio_bar: MMIO bar resource number.
- * @read_spad: Read from scratch pad register.
- * @write_spad: Write to scratch pad register.
- * @send_intr: Send an interrupt for a particular doorbell on the card.
- * @ack_interrupt: Hardware specific operations to ack the h/w on
- * receipt of an interrupt.
- * @intr_workarounds: Hardware specific workarounds needed after
- * handling an interrupt.
- * @reset: Reset the remote processor.
- * @reset_fw_ready: Reset firmware ready field.
- * @is_fw_ready: Check if firmware is ready for OS download.
- * @send_firmware_intr: Send an interrupt to the card firmware.
- * @load_mic_fw: Load firmware segments required to boot the card
- * into card memory. This includes the kernel, command line, ramdisk etc.
- * @get_postcode: Get post code status from firmware.
- * @dma_filter: DMA filter function to be used.
- */
-struct mic_hw_ops {
-	u8 aper_bar;
-	u8 mmio_bar;
-	u32 (*read_spad)(struct mic_device *mdev, unsigned int idx);
-	void (*write_spad)(struct mic_device *mdev, unsigned int idx, u32 val);
-	void (*send_intr)(struct mic_device *mdev, int doorbell);
-	u32 (*ack_interrupt)(struct mic_device *mdev);
-	void (*intr_workarounds)(struct mic_device *mdev);
-	void (*reset)(struct mic_device *mdev);
-	void (*reset_fw_ready)(struct mic_device *mdev);
-	bool (*is_fw_ready)(struct mic_device *mdev);
-	void (*send_firmware_intr)(struct mic_device *mdev);
-	int (*load_mic_fw)(struct mic_device *mdev, const char *buf);
-	u32 (*get_postcode)(struct mic_device *mdev);
-	bool (*dma_filter)(struct dma_chan *chan, void *param);
-};
-
-/**
- * mic_mmio_read - read from an MMIO register.
- * @mw: MMIO register base virtual address.
- * @offset: register offset.
- *
- * RETURNS: register value.
- */
-static inline u32 mic_mmio_read(struct mic_mw *mw, u32 offset)
-{
-	return ioread32(mw->va + offset);
-}
-
-/**
- * mic_mmio_write - write to an MMIO register.
- * @mw: MMIO register base virtual address.
- * @val: the data value to put into the register
- * @offset: register offset.
- *
- * RETURNS: none.
- */
-static inline void
-mic_mmio_write(struct mic_mw *mw, u32 val, u32 offset)
-{
-	iowrite32(val, mw->va + offset);
-}
-
-void mic_bootparam_init(struct mic_device *mdev);
-void mic_create_debug_dir(struct mic_device *dev);
-void mic_delete_debug_dir(struct mic_device *dev);
-void __init mic_init_debugfs(void);
-void mic_exit_debugfs(void);
-#endif
diff --git a/drivers/misc/mic/host/mic_intr.c b/drivers/misc/mic/host/mic_intr.c
deleted file mode 100644
index 85b3221b5d40..000000000000
--- a/drivers/misc/mic/host/mic_intr.c
+++ /dev/null
@@ -1,635 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC Host driver.
- */
-#include <linux/pci.h>
-#include <linux/interrupt.h>
-
-#include "../common/mic_dev.h"
-#include "mic_device.h"
-
-static irqreturn_t mic_thread_fn(int irq, void *dev)
-{
-	struct mic_device *mdev = dev;
-	struct mic_intr_info *intr_info = mdev->intr_info;
-	struct mic_irq_info *irq_info = &mdev->irq_info;
-	struct mic_intr_cb *intr_cb;
-	struct pci_dev *pdev = mdev->pdev;
-	int i;
-
-	spin_lock(&irq_info->mic_thread_lock);
-	for (i = intr_info->intr_start_idx[MIC_INTR_DB];
-			i < intr_info->intr_len[MIC_INTR_DB]; i++)
-		if (test_and_clear_bit(i, &irq_info->mask)) {
-			list_for_each_entry(intr_cb, &irq_info->cb_list[i],
-					    list)
-				if (intr_cb->thread_fn)
-					intr_cb->thread_fn(pdev->irq,
-							 intr_cb->data);
-		}
-	spin_unlock(&irq_info->mic_thread_lock);
-	return IRQ_HANDLED;
-}
-/**
- * mic_interrupt - Generic interrupt handler for
- * MSI and INTx based interrupts.
- * @irq:  interrupt to handle (unused)
- * @dev: pointer to the mic_device instance
- */
-static irqreturn_t mic_interrupt(int irq, void *dev)
-{
-	struct mic_device *mdev = dev;
-	struct mic_intr_info *intr_info = mdev->intr_info;
-	struct mic_irq_info *irq_info = &mdev->irq_info;
-	struct mic_intr_cb *intr_cb;
-	struct pci_dev *pdev = mdev->pdev;
-	u32 mask;
-	int i;
-
-	mask = mdev->ops->ack_interrupt(mdev);
-	if (!mask)
-		return IRQ_NONE;
-
-	spin_lock(&irq_info->mic_intr_lock);
-	for (i = intr_info->intr_start_idx[MIC_INTR_DB];
-			i < intr_info->intr_len[MIC_INTR_DB]; i++)
-		if (mask & BIT(i)) {
-			list_for_each_entry(intr_cb, &irq_info->cb_list[i],
-					    list)
-				if (intr_cb->handler)
-					intr_cb->handler(pdev->irq,
-							 intr_cb->data);
-			set_bit(i, &irq_info->mask);
-		}
-	spin_unlock(&irq_info->mic_intr_lock);
-	return IRQ_WAKE_THREAD;
-}
-
-/* Return the interrupt offset from the index. Index is 0 based. */
-static u16 mic_map_src_to_offset(struct mic_device *mdev,
-				 int intr_src, enum mic_intr_type type)
-{
-	if (type >= MIC_NUM_INTR_TYPES)
-		return MIC_NUM_OFFSETS;
-	if (intr_src >= mdev->intr_info->intr_len[type])
-		return MIC_NUM_OFFSETS;
-
-	return mdev->intr_info->intr_start_idx[type] + intr_src;
-}
-
-/* Return next available msix_entry. */
-static struct msix_entry *mic_get_available_vector(struct mic_device *mdev)
-{
-	int i;
-	struct mic_irq_info *info = &mdev->irq_info;
-
-	for (i = 0; i < info->num_vectors; i++)
-		if (!info->mic_msi_map[i])
-			return &info->msix_entries[i];
-	return NULL;
-}
-
-/**
- * mic_register_intr_callback - Register a callback handler for the
- * given source id.
- *
- * @mdev: pointer to the mic_device instance
- * @idx: The source id to be registered.
- * @handler: The function to be called when the source id receives
- * the interrupt.
- * @thread_fn: thread fn. corresponding to the handler
- * @data: Private data of the requester.
- * Return the callback structure that was registered or an
- * appropriate error on failure.
- */
-static struct mic_intr_cb *mic_register_intr_callback(struct mic_device *mdev,
-			u8 idx, irq_handler_t handler, irq_handler_t thread_fn,
-			void *data)
-{
-	struct mic_intr_cb *intr_cb;
-	unsigned long flags;
-	int rc;
-	intr_cb = kmalloc(sizeof(*intr_cb), GFP_KERNEL);
-
-	if (!intr_cb)
-		return ERR_PTR(-ENOMEM);
-
-	intr_cb->handler = handler;
-	intr_cb->thread_fn = thread_fn;
-	intr_cb->data = data;
-	intr_cb->cb_id = ida_simple_get(&mdev->irq_info.cb_ida,
-		0, 0, GFP_KERNEL);
-	if (intr_cb->cb_id < 0) {
-		rc = intr_cb->cb_id;
-		goto ida_fail;
-	}
-
-	spin_lock(&mdev->irq_info.mic_thread_lock);
-	spin_lock_irqsave(&mdev->irq_info.mic_intr_lock, flags);
-	list_add_tail(&intr_cb->list, &mdev->irq_info.cb_list[idx]);
-	spin_unlock_irqrestore(&mdev->irq_info.mic_intr_lock, flags);
-	spin_unlock(&mdev->irq_info.mic_thread_lock);
-
-	return intr_cb;
-ida_fail:
-	kfree(intr_cb);
-	return ERR_PTR(rc);
-}
-
-/**
- * mic_unregister_intr_callback - Unregister the callback handler
- * identified by its callback id.
- *
- * @mdev: pointer to the mic_device instance
- * @idx: The callback structure id to be unregistered.
- * Return the source id that was unregistered or MIC_NUM_OFFSETS if no
- * such callback handler was found.
- */
-static u8 mic_unregister_intr_callback(struct mic_device *mdev, u32 idx)
-{
-	struct list_head *pos, *tmp;
-	struct mic_intr_cb *intr_cb;
-	unsigned long flags;
-	int i;
-
-	spin_lock(&mdev->irq_info.mic_thread_lock);
-	spin_lock_irqsave(&mdev->irq_info.mic_intr_lock, flags);
-	for (i = 0;  i < MIC_NUM_OFFSETS; i++) {
-		list_for_each_safe(pos, tmp, &mdev->irq_info.cb_list[i]) {
-			intr_cb = list_entry(pos, struct mic_intr_cb, list);
-			if (intr_cb->cb_id == idx) {
-				list_del(pos);
-				ida_simple_remove(&mdev->irq_info.cb_ida,
-						  intr_cb->cb_id);
-				kfree(intr_cb);
-				spin_unlock_irqrestore(
-					&mdev->irq_info.mic_intr_lock, flags);
-				spin_unlock(&mdev->irq_info.mic_thread_lock);
-				return i;
-			}
-		}
-	}
-	spin_unlock_irqrestore(&mdev->irq_info.mic_intr_lock, flags);
-	spin_unlock(&mdev->irq_info.mic_thread_lock);
-	return MIC_NUM_OFFSETS;
-}
-
-/**
- * mic_setup_msix - Initializes MSIx interrupts.
- *
- * @mdev: pointer to mic_device instance
- * @pdev: PCI device structure
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-static int mic_setup_msix(struct mic_device *mdev, struct pci_dev *pdev)
-{
-	int rc, i;
-	int entry_size = sizeof(*mdev->irq_info.msix_entries);
-
-	mdev->irq_info.msix_entries = kmalloc_array(MIC_MIN_MSIX,
-						    entry_size, GFP_KERNEL);
-	if (!mdev->irq_info.msix_entries) {
-		rc = -ENOMEM;
-		goto err_nomem1;
-	}
-
-	for (i = 0; i < MIC_MIN_MSIX; i++)
-		mdev->irq_info.msix_entries[i].entry = i;
-
-	rc = pci_enable_msix_exact(pdev, mdev->irq_info.msix_entries,
-				   MIC_MIN_MSIX);
-	if (rc) {
-		dev_dbg(&pdev->dev, "Error enabling MSIx. rc = %d\n", rc);
-		goto err_enable_msix;
-	}
-
-	mdev->irq_info.num_vectors = MIC_MIN_MSIX;
-	mdev->irq_info.mic_msi_map = kzalloc((sizeof(u32) *
-		mdev->irq_info.num_vectors), GFP_KERNEL);
-
-	if (!mdev->irq_info.mic_msi_map) {
-		rc = -ENOMEM;
-		goto err_nomem2;
-	}
-
-	dev_dbg(&mdev->pdev->dev,
-		"%d MSIx irqs setup\n", mdev->irq_info.num_vectors);
-	return 0;
-err_nomem2:
-	pci_disable_msix(pdev);
-err_enable_msix:
-	kfree(mdev->irq_info.msix_entries);
-err_nomem1:
-	mdev->irq_info.num_vectors = 0;
-	return rc;
-}
-
-/**
- * mic_setup_callbacks - Initialize data structures needed
- * to handle callbacks.
- *
- * @mdev: pointer to mic_device instance
- */
-static int mic_setup_callbacks(struct mic_device *mdev)
-{
-	int i;
-
-	mdev->irq_info.cb_list = kmalloc_array(MIC_NUM_OFFSETS,
-					       sizeof(*mdev->irq_info.cb_list),
-					       GFP_KERNEL);
-	if (!mdev->irq_info.cb_list)
-		return -ENOMEM;
-
-	for (i = 0; i < MIC_NUM_OFFSETS; i++)
-		INIT_LIST_HEAD(&mdev->irq_info.cb_list[i]);
-	ida_init(&mdev->irq_info.cb_ida);
-	spin_lock_init(&mdev->irq_info.mic_intr_lock);
-	spin_lock_init(&mdev->irq_info.mic_thread_lock);
-	return 0;
-}
-
-/**
- * mic_release_callbacks - Uninitialize data structures needed
- * to handle callbacks.
- *
- * @mdev: pointer to mic_device instance
- */
-static void mic_release_callbacks(struct mic_device *mdev)
-{
-	unsigned long flags;
-	struct list_head *pos, *tmp;
-	struct mic_intr_cb *intr_cb;
-	int i;
-
-	spin_lock(&mdev->irq_info.mic_thread_lock);
-	spin_lock_irqsave(&mdev->irq_info.mic_intr_lock, flags);
-	for (i = 0; i < MIC_NUM_OFFSETS; i++) {
-		if (list_empty(&mdev->irq_info.cb_list[i]))
-			break;
-
-		list_for_each_safe(pos, tmp, &mdev->irq_info.cb_list[i]) {
-			intr_cb = list_entry(pos, struct mic_intr_cb, list);
-			list_del(pos);
-			ida_simple_remove(&mdev->irq_info.cb_ida,
-					  intr_cb->cb_id);
-			kfree(intr_cb);
-		}
-	}
-	spin_unlock_irqrestore(&mdev->irq_info.mic_intr_lock, flags);
-	spin_unlock(&mdev->irq_info.mic_thread_lock);
-	ida_destroy(&mdev->irq_info.cb_ida);
-	kfree(mdev->irq_info.cb_list);
-}
-
-/**
- * mic_setup_msi - Initializes MSI interrupts.
- *
- * @mdev: pointer to mic_device instance
- * @pdev: PCI device structure
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-static int mic_setup_msi(struct mic_device *mdev, struct pci_dev *pdev)
-{
-	int rc;
-
-	rc = pci_enable_msi(pdev);
-	if (rc) {
-		dev_dbg(&pdev->dev, "Error enabling MSI. rc = %d\n", rc);
-		return rc;
-	}
-
-	mdev->irq_info.num_vectors = 1;
-	mdev->irq_info.mic_msi_map = kzalloc((sizeof(u32) *
-		mdev->irq_info.num_vectors), GFP_KERNEL);
-
-	if (!mdev->irq_info.mic_msi_map) {
-		rc = -ENOMEM;
-		goto err_nomem1;
-	}
-
-	rc = mic_setup_callbacks(mdev);
-	if (rc) {
-		dev_err(&pdev->dev, "Error setting up callbacks\n");
-		goto err_nomem2;
-	}
-
-	rc = request_threaded_irq(pdev->irq, mic_interrupt, mic_thread_fn,
-				  0, "mic-msi", mdev);
-	if (rc) {
-		dev_err(&pdev->dev, "Error allocating MSI interrupt\n");
-		goto err_irq_req_fail;
-	}
-
-	dev_dbg(&pdev->dev, "%d MSI irqs setup\n", mdev->irq_info.num_vectors);
-	return 0;
-err_irq_req_fail:
-	mic_release_callbacks(mdev);
-err_nomem2:
-	kfree(mdev->irq_info.mic_msi_map);
-err_nomem1:
-	pci_disable_msi(pdev);
-	mdev->irq_info.num_vectors = 0;
-	return rc;
-}
-
-/**
- * mic_setup_intx - Initializes legacy interrupts.
- *
- * @mdev: pointer to mic_device instance
- * @pdev: PCI device structure
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-static int mic_setup_intx(struct mic_device *mdev, struct pci_dev *pdev)
-{
-	int rc;
-
-	/* Enable intx */
-	pci_intx(pdev, 1);
-	rc = mic_setup_callbacks(mdev);
-	if (rc) {
-		dev_err(&pdev->dev, "Error setting up callbacks\n");
-		goto err_nomem;
-	}
-
-	rc = request_threaded_irq(pdev->irq, mic_interrupt, mic_thread_fn,
-				  IRQF_SHARED, "mic-intx", mdev);
-	if (rc)
-		goto err;
-
-	dev_dbg(&pdev->dev, "intx irq setup\n");
-	return 0;
-err:
-	mic_release_callbacks(mdev);
-err_nomem:
-	return rc;
-}
-
-/**
- * mic_next_db - Retrieve the next doorbell interrupt source id.
- * The id is picked sequentially from the available pool of
- * doorlbell ids.
- *
- * @mdev: pointer to the mic_device instance.
- *
- * Returns the next doorbell interrupt source.
- */
-int mic_next_db(struct mic_device *mdev)
-{
-	int next_db;
-
-	next_db = mdev->irq_info.next_avail_src %
-		mdev->intr_info->intr_len[MIC_INTR_DB];
-	mdev->irq_info.next_avail_src++;
-	return next_db;
-}
-
-#define COOKIE_ID_SHIFT 16
-#define GET_ENTRY(cookie) ((cookie) & 0xFFFF)
-#define GET_OFFSET(cookie) ((cookie) >> COOKIE_ID_SHIFT)
-#define MK_COOKIE(x, y) ((x) | (y) << COOKIE_ID_SHIFT)
-
-/**
- * mic_request_threaded_irq - request an irq. mic_mutex needs
- * to be held before calling this function.
- *
- * @mdev: pointer to mic_device instance
- * @handler: The callback function that handles the interrupt.
- * The function needs to call ack_interrupts
- * (mdev->ops->ack_interrupt(mdev)) when handling the interrupts.
- * @thread_fn: thread fn required by request_threaded_irq.
- * @name: The ASCII name of the callee requesting the irq.
- * @data: private data that is returned back when calling the
- * function handler.
- * @intr_src: The source id of the requester. Its the doorbell id
- * for Doorbell interrupts and DMA channel id for DMA interrupts.
- * @type: The type of interrupt. Values defined in mic_intr_type
- *
- * returns: The cookie that is transparent to the caller. Passed
- * back when calling mic_free_irq. An appropriate error code
- * is returned on failure. Caller needs to use IS_ERR(return_val)
- * to check for failure and PTR_ERR(return_val) to obtained the
- * error code.
- *
- */
-struct mic_irq *
-mic_request_threaded_irq(struct mic_device *mdev,
-			 irq_handler_t handler, irq_handler_t thread_fn,
-			 const char *name, void *data, int intr_src,
-			 enum mic_intr_type type)
-{
-	u16 offset;
-	int rc = 0;
-	struct msix_entry *msix = NULL;
-	unsigned long cookie = 0;
-	u16 entry;
-	struct mic_intr_cb *intr_cb;
-	struct pci_dev *pdev = mdev->pdev;
-
-	offset = mic_map_src_to_offset(mdev, intr_src, type);
-	if (offset >= MIC_NUM_OFFSETS) {
-		dev_err(&mdev->pdev->dev,
-			"Error mapping index %d to a valid source id.\n",
-			intr_src);
-		rc = -EINVAL;
-		goto err;
-	}
-
-	if (mdev->irq_info.num_vectors > 1) {
-		msix = mic_get_available_vector(mdev);
-		if (!msix) {
-			dev_err(&mdev->pdev->dev,
-				"No MSIx vectors available for use.\n");
-			rc = -ENOSPC;
-			goto err;
-		}
-
-		rc = request_threaded_irq(msix->vector, handler, thread_fn,
-					  0, name, data);
-		if (rc) {
-			dev_dbg(&mdev->pdev->dev,
-				"request irq failed rc = %d\n", rc);
-			goto err;
-		}
-		entry = msix->entry;
-		mdev->irq_info.mic_msi_map[entry] |= BIT(offset);
-		mdev->intr_ops->program_msi_to_src_map(mdev,
-				entry, offset, true);
-		cookie = MK_COOKIE(entry, offset);
-		dev_dbg(&mdev->pdev->dev, "irq: %d assigned for src: %d\n",
-			msix->vector, intr_src);
-	} else {
-		intr_cb = mic_register_intr_callback(mdev, offset, handler,
-						     thread_fn, data);
-		if (IS_ERR(intr_cb)) {
-			dev_err(&mdev->pdev->dev,
-				"No available callback entries for use\n");
-			rc = PTR_ERR(intr_cb);
-			goto err;
-		}
-
-		entry = 0;
-		if (pci_dev_msi_enabled(pdev)) {
-			mdev->irq_info.mic_msi_map[entry] |= (1 << offset);
-			mdev->intr_ops->program_msi_to_src_map(mdev,
-				entry, offset, true);
-		}
-		cookie = MK_COOKIE(entry, intr_cb->cb_id);
-		dev_dbg(&mdev->pdev->dev, "callback %d registered for src: %d\n",
-			intr_cb->cb_id, intr_src);
-	}
-	return (struct mic_irq *)cookie;
-err:
-	return ERR_PTR(rc);
-}
-
-/**
- * mic_free_irq - free irq. mic_mutex
- *  needs to be held before calling this function.
- *
- * @mdev: pointer to mic_device instance
- * @cookie: cookie obtained during a successful call to mic_request_threaded_irq
- * @data: private data specified by the calling function during the
- * mic_request_threaded_irq
- *
- * returns: none.
- */
-void mic_free_irq(struct mic_device *mdev,
-		  struct mic_irq *cookie, void *data)
-{
-	u32 offset;
-	u32 entry;
-	u8 src_id;
-	unsigned int irq;
-	struct pci_dev *pdev = mdev->pdev;
-
-	entry = GET_ENTRY((unsigned long)cookie);
-	offset = GET_OFFSET((unsigned long)cookie);
-	if (mdev->irq_info.num_vectors > 1) {
-		if (entry >= mdev->irq_info.num_vectors) {
-			dev_warn(&mdev->pdev->dev,
-				 "entry %d should be < num_irq %d\n",
-				entry, mdev->irq_info.num_vectors);
-			return;
-		}
-		irq = mdev->irq_info.msix_entries[entry].vector;
-		free_irq(irq, data);
-		mdev->irq_info.mic_msi_map[entry] &= ~(BIT(offset));
-		mdev->intr_ops->program_msi_to_src_map(mdev,
-			entry, offset, false);
-
-		dev_dbg(&mdev->pdev->dev, "irq: %d freed\n", irq);
-	} else {
-		irq = pdev->irq;
-		src_id = mic_unregister_intr_callback(mdev, offset);
-		if (src_id >= MIC_NUM_OFFSETS) {
-			dev_warn(&mdev->pdev->dev, "Error unregistering callback\n");
-			return;
-		}
-		if (pci_dev_msi_enabled(pdev)) {
-			mdev->irq_info.mic_msi_map[entry] &= ~(BIT(src_id));
-			mdev->intr_ops->program_msi_to_src_map(mdev,
-				entry, src_id, false);
-		}
-		dev_dbg(&mdev->pdev->dev, "callback %d unregistered for src: %d\n",
-			offset, src_id);
-	}
-}
-
-/**
- * mic_setup_interrupts - Initializes interrupts.
- *
- * @mdev: pointer to mic_device instance
- * @pdev: PCI device structure
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-int mic_setup_interrupts(struct mic_device *mdev, struct pci_dev *pdev)
-{
-	int rc;
-
-	rc = mic_setup_msix(mdev, pdev);
-	if (!rc)
-		goto done;
-
-	rc = mic_setup_msi(mdev, pdev);
-	if (!rc)
-		goto done;
-
-	rc = mic_setup_intx(mdev, pdev);
-	if (rc) {
-		dev_err(&mdev->pdev->dev, "no usable interrupts\n");
-		return rc;
-	}
-done:
-	mdev->intr_ops->enable_interrupts(mdev);
-	return 0;
-}
-
-/**
- * mic_free_interrupts - Frees interrupts setup by mic_setup_interrupts
- *
- * @mdev: pointer to mic_device instance
- * @pdev: PCI device structure
- *
- * returns none.
- */
-void mic_free_interrupts(struct mic_device *mdev, struct pci_dev *pdev)
-{
-	int i;
-
-	mdev->intr_ops->disable_interrupts(mdev);
-	if (mdev->irq_info.num_vectors > 1) {
-		for (i = 0; i < mdev->irq_info.num_vectors; i++) {
-			if (mdev->irq_info.mic_msi_map[i])
-				dev_warn(&pdev->dev, "irq %d may still be in use.\n",
-					 mdev->irq_info.msix_entries[i].vector);
-		}
-		kfree(mdev->irq_info.mic_msi_map);
-		kfree(mdev->irq_info.msix_entries);
-		pci_disable_msix(pdev);
-	} else {
-		if (pci_dev_msi_enabled(pdev)) {
-			free_irq(pdev->irq, mdev);
-			kfree(mdev->irq_info.mic_msi_map);
-			pci_disable_msi(pdev);
-		} else {
-			free_irq(pdev->irq, mdev);
-		}
-		mic_release_callbacks(mdev);
-	}
-}
-
-/**
- * mic_intr_restore - Restore MIC interrupt registers.
- *
- * @mdev: pointer to mic_device instance.
- *
- * Restore the interrupt registers to values previously
- * stored in the SW data structures. mic_mutex needs to
- * be held before calling this function.
- *
- * returns None.
- */
-void mic_intr_restore(struct mic_device *mdev)
-{
-	int entry, offset;
-	struct pci_dev *pdev = mdev->pdev;
-
-	if (!pci_dev_msi_enabled(pdev))
-		return;
-
-	for (entry = 0; entry < mdev->irq_info.num_vectors; entry++) {
-		for (offset = 0; offset < MIC_NUM_OFFSETS; offset++) {
-			if (mdev->irq_info.mic_msi_map[entry] & BIT(offset))
-				mdev->intr_ops->program_msi_to_src_map(mdev,
-					entry, offset, true);
-		}
-	}
-}
diff --git a/drivers/misc/mic/host/mic_intr.h b/drivers/misc/mic/host/mic_intr.h
deleted file mode 100644
index b14ba818006f..000000000000
--- a/drivers/misc/mic/host/mic_intr.h
+++ /dev/null
@@ -1,137 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC Host driver.
- */
-#ifndef _MIC_INTR_H_
-#define _MIC_INTR_H_
-
-#include <linux/bitops.h>
-#include <linux/interrupt.h>
-/*
- * The minimum number of msix vectors required for normal operation.
- * 3 for virtio network, console and block devices.
- * 1 for card shutdown notifications.
- * 4 for host owned DMA channels.
- * 1 for SCIF
- */
-#define MIC_MIN_MSIX 9
-#define MIC_NUM_OFFSETS 32
-
-/**
- * mic_intr_source - The type of source that will generate
- * the interrupt.The number of types needs to be in sync with
- * MIC_NUM_INTR_TYPES
- *
- * MIC_INTR_DB: The source is a doorbell
- * MIC_INTR_DMA: The source is a DMA channel
- * MIC_INTR_ERR: The source is an error interrupt e.g. SBOX ERR
- * MIC_NUM_INTR_TYPES: Total number of interrupt sources.
- */
-enum mic_intr_type {
-	MIC_INTR_DB = 0,
-	MIC_INTR_DMA,
-	MIC_INTR_ERR,
-	MIC_NUM_INTR_TYPES
-};
-
-/**
- * struct mic_intr_info - Contains h/w specific interrupt sources
- * information.
- *
- * @intr_start_idx: Contains the starting indexes of the
- * interrupt types.
- * @intr_len: Contains the length of the interrupt types.
- */
-struct mic_intr_info {
-	u16 intr_start_idx[MIC_NUM_INTR_TYPES];
-	u16 intr_len[MIC_NUM_INTR_TYPES];
-};
-
-/**
- * struct mic_irq_info - OS specific irq information
- *
- * @next_avail_src: next available doorbell that can be assigned.
- * @msix_entries: msix entries allocated while setting up MSI-x
- * @mic_msi_map: The MSI/MSI-x mapping information.
- * @num_vectors: The number of MSI/MSI-x vectors that have been allocated.
- * @cb_ida: callback ID allocator to track the callbacks registered.
- * @mic_intr_lock: spinlock to protect the interrupt callback list.
- * @mic_thread_lock: spinlock to protect the thread callback list.
- *		   This lock is used to protect against thread_fn while
- *		   mic_intr_lock is used to protect against interrupt handler.
- * @cb_list: Array of callback lists one for each source.
- * @mask: Mask used by the main thread fn to call the underlying thread fns.
- */
-struct mic_irq_info {
-	int next_avail_src;
-	struct msix_entry *msix_entries;
-	u32 *mic_msi_map;
-	u16 num_vectors;
-	struct ida cb_ida;
-	spinlock_t mic_intr_lock;
-	spinlock_t mic_thread_lock;
-	struct list_head *cb_list;
-	unsigned long mask;
-};
-
-/**
- * struct mic_intr_cb - Interrupt callback structure.
- *
- * @handler: The callback function
- * @thread_fn: The thread_fn.
- * @data: Private data of the requester.
- * @cb_id: The callback id. Identifies this callback.
- * @list: list head pointing to the next callback structure.
- */
-struct mic_intr_cb {
-	irq_handler_t handler;
-	irq_handler_t thread_fn;
-	void *data;
-	int cb_id;
-	struct list_head list;
-};
-
-/**
- * struct mic_irq - opaque pointer used as cookie
- */
-struct mic_irq;
-
-/* Forward declaration */
-struct mic_device;
-
-/**
- * struct mic_hw_intr_ops: MIC HW specific interrupt operations
- * @intr_init: Initialize H/W specific interrupt information.
- * @enable_interrupts: Enable interrupts from the hardware.
- * @disable_interrupts: Disable interrupts from the hardware.
- * @program_msi_to_src_map: Update MSI mapping registers with
- * irq information.
- * @read_msi_to_src_map: Read MSI mapping registers containing
- * irq information.
- */
-struct mic_hw_intr_ops {
-	void (*intr_init)(struct mic_device *mdev);
-	void (*enable_interrupts)(struct mic_device *mdev);
-	void (*disable_interrupts)(struct mic_device *mdev);
-	void (*program_msi_to_src_map) (struct mic_device *mdev,
-			int idx, int intr_src, bool set);
-	u32 (*read_msi_to_src_map) (struct mic_device *mdev,
-			int idx);
-};
-
-int mic_next_db(struct mic_device *mdev);
-struct mic_irq *
-mic_request_threaded_irq(struct mic_device *mdev,
-			 irq_handler_t handler, irq_handler_t thread_fn,
-			 const char *name, void *data, int intr_src,
-			 enum mic_intr_type type);
-void mic_free_irq(struct mic_device *mdev,
-		struct mic_irq *cookie, void *data);
-int mic_setup_interrupts(struct mic_device *mdev, struct pci_dev *pdev);
-void mic_free_interrupts(struct mic_device *mdev, struct pci_dev *pdev);
-void mic_intr_restore(struct mic_device *mdev);
-#endif
diff --git a/drivers/misc/mic/host/mic_main.c b/drivers/misc/mic/host/mic_main.c
deleted file mode 100644
index ea4608527ea0..000000000000
--- a/drivers/misc/mic/host/mic_main.c
+++ /dev/null
@@ -1,335 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC Host driver.
- */
-#include <linux/fs.h>
-#include <linux/module.h>
-#include <linux/pci.h>
-#include <linux/poll.h>
-
-#include <linux/mic_common.h>
-#include "../common/mic_dev.h"
-#include "mic_device.h"
-#include "mic_x100.h"
-#include "mic_smpt.h"
-
-static const char mic_driver_name[] = "mic";
-
-static const struct pci_device_id mic_pci_tbl[] = {
-	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2250)},
-	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2251)},
-	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2252)},
-	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2253)},
-	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2254)},
-	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2255)},
-	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2256)},
-	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2257)},
-	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2258)},
-	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2259)},
-	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_225a)},
-	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_225b)},
-	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_225c)},
-	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_225d)},
-	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_225e)},
-
-	/* required last entry */
-	{ 0, }
-};
-
-MODULE_DEVICE_TABLE(pci, mic_pci_tbl);
-
-/* ID allocator for MIC devices */
-static struct ida g_mic_ida;
-
-/* Initialize the device page */
-static int mic_dp_init(struct mic_device *mdev)
-{
-	mdev->dp = kzalloc(MIC_DP_SIZE, GFP_KERNEL);
-	if (!mdev->dp)
-		return -ENOMEM;
-
-	mdev->dp_dma_addr = mic_map_single(mdev,
-		mdev->dp, MIC_DP_SIZE);
-	if (mic_map_error(mdev->dp_dma_addr)) {
-		kfree(mdev->dp);
-		dev_err(&mdev->pdev->dev, "%s %d err %d\n",
-			__func__, __LINE__, -ENOMEM);
-		return -ENOMEM;
-	}
-	mdev->ops->write_spad(mdev, MIC_DPLO_SPAD, mdev->dp_dma_addr);
-	mdev->ops->write_spad(mdev, MIC_DPHI_SPAD, mdev->dp_dma_addr >> 32);
-	return 0;
-}
-
-/* Uninitialize the device page */
-static void mic_dp_uninit(struct mic_device *mdev)
-{
-	mic_unmap_single(mdev, mdev->dp_dma_addr, MIC_DP_SIZE);
-	kfree(mdev->dp);
-}
-
-/**
- * mic_ops_init: Initialize HW specific operation tables.
- *
- * @mdev: pointer to mic_device instance
- *
- * returns none.
- */
-static void mic_ops_init(struct mic_device *mdev)
-{
-	switch (mdev->family) {
-	case MIC_FAMILY_X100:
-		mdev->ops = &mic_x100_ops;
-		mdev->intr_ops = &mic_x100_intr_ops;
-		mdev->smpt_ops = &mic_x100_smpt_ops;
-		break;
-	default:
-		break;
-	}
-}
-
-/**
- * mic_get_family - Determine hardware family to which this MIC belongs.
- *
- * @pdev: The pci device structure
- *
- * returns family.
- */
-static enum mic_hw_family mic_get_family(struct pci_dev *pdev)
-{
-	enum mic_hw_family family;
-
-	switch (pdev->device) {
-	case MIC_X100_PCI_DEVICE_2250:
-	case MIC_X100_PCI_DEVICE_2251:
-	case MIC_X100_PCI_DEVICE_2252:
-	case MIC_X100_PCI_DEVICE_2253:
-	case MIC_X100_PCI_DEVICE_2254:
-	case MIC_X100_PCI_DEVICE_2255:
-	case MIC_X100_PCI_DEVICE_2256:
-	case MIC_X100_PCI_DEVICE_2257:
-	case MIC_X100_PCI_DEVICE_2258:
-	case MIC_X100_PCI_DEVICE_2259:
-	case MIC_X100_PCI_DEVICE_225a:
-	case MIC_X100_PCI_DEVICE_225b:
-	case MIC_X100_PCI_DEVICE_225c:
-	case MIC_X100_PCI_DEVICE_225d:
-	case MIC_X100_PCI_DEVICE_225e:
-		family = MIC_FAMILY_X100;
-		break;
-	default:
-		family = MIC_FAMILY_UNKNOWN;
-		break;
-	}
-	return family;
-}
-
-/**
- * mic_device_init - Allocates and initializes the MIC device structure
- *
- * @mdev: pointer to mic_device instance
- * @pdev: The pci device structure
- *
- * returns none.
- */
-static void
-mic_device_init(struct mic_device *mdev, struct pci_dev *pdev)
-{
-	mdev->pdev = pdev;
-	mdev->family = mic_get_family(pdev);
-	mdev->stepping = pdev->revision;
-	mic_ops_init(mdev);
-	mutex_init(&mdev->mic_mutex);
-	mdev->irq_info.next_avail_src = 0;
-}
-
-/**
- * mic_probe - Device Initialization Routine
- *
- * @pdev: PCI device structure
- * @ent: entry in mic_pci_tbl
- *
- * returns 0 on success, < 0 on failure.
- */
-static int mic_probe(struct pci_dev *pdev,
-		     const struct pci_device_id *ent)
-{
-	int rc;
-	struct mic_device *mdev;
-
-	mdev = kzalloc(sizeof(*mdev), GFP_KERNEL);
-	if (!mdev) {
-		rc = -ENOMEM;
-		goto mdev_alloc_fail;
-	}
-	mdev->id = ida_simple_get(&g_mic_ida, 0, MIC_MAX_NUM_DEVS, GFP_KERNEL);
-	if (mdev->id < 0) {
-		rc = mdev->id;
-		dev_err(&pdev->dev, "ida_simple_get failed rc %d\n", rc);
-		goto ida_fail;
-	}
-
-	mic_device_init(mdev, pdev);
-
-	rc = pci_enable_device(pdev);
-	if (rc) {
-		dev_err(&pdev->dev, "failed to enable pci device.\n");
-		goto ida_remove;
-	}
-
-	pci_set_master(pdev);
-
-	rc = pci_request_regions(pdev, mic_driver_name);
-	if (rc) {
-		dev_err(&pdev->dev, "failed to get pci regions.\n");
-		goto disable_device;
-	}
-
-	rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
-	if (rc) {
-		dev_err(&pdev->dev, "Cannot set DMA mask\n");
-		goto release_regions;
-	}
-
-	mdev->mmio.pa = pci_resource_start(pdev, mdev->ops->mmio_bar);
-	mdev->mmio.len = pci_resource_len(pdev, mdev->ops->mmio_bar);
-	mdev->mmio.va = pci_ioremap_bar(pdev, mdev->ops->mmio_bar);
-	if (!mdev->mmio.va) {
-		dev_err(&pdev->dev, "Cannot remap MMIO BAR\n");
-		rc = -EIO;
-		goto release_regions;
-	}
-
-	mdev->aper.pa = pci_resource_start(pdev, mdev->ops->aper_bar);
-	mdev->aper.len = pci_resource_len(pdev, mdev->ops->aper_bar);
-	mdev->aper.va = ioremap_wc(mdev->aper.pa, mdev->aper.len);
-	if (!mdev->aper.va) {
-		dev_err(&pdev->dev, "Cannot remap Aperture BAR\n");
-		rc = -EIO;
-		goto unmap_mmio;
-	}
-
-	mdev->intr_ops->intr_init(mdev);
-	rc = mic_setup_interrupts(mdev, pdev);
-	if (rc) {
-		dev_err(&pdev->dev, "mic_setup_interrupts failed %d\n", rc);
-		goto unmap_aper;
-	}
-	rc = mic_smpt_init(mdev);
-	if (rc) {
-		dev_err(&pdev->dev, "smpt_init failed %d\n", rc);
-		goto free_interrupts;
-	}
-
-	pci_set_drvdata(pdev, mdev);
-
-	rc = mic_dp_init(mdev);
-	if (rc) {
-		dev_err(&pdev->dev, "mic_dp_init failed rc %d\n", rc);
-		goto smpt_uninit;
-	}
-	mic_bootparam_init(mdev);
-	mic_create_debug_dir(mdev);
-
-	mdev->cosm_dev = cosm_register_device(&mdev->pdev->dev, &cosm_hw_ops);
-	if (IS_ERR(mdev->cosm_dev)) {
-		rc = PTR_ERR(mdev->cosm_dev);
-		dev_err(&pdev->dev, "cosm_add_device failed rc %d\n", rc);
-		goto cleanup_debug_dir;
-	}
-	return 0;
-cleanup_debug_dir:
-	mic_delete_debug_dir(mdev);
-	mic_dp_uninit(mdev);
-smpt_uninit:
-	mic_smpt_uninit(mdev);
-free_interrupts:
-	mic_free_interrupts(mdev, pdev);
-unmap_aper:
-	iounmap(mdev->aper.va);
-unmap_mmio:
-	iounmap(mdev->mmio.va);
-release_regions:
-	pci_release_regions(pdev);
-disable_device:
-	pci_disable_device(pdev);
-ida_remove:
-	ida_simple_remove(&g_mic_ida, mdev->id);
-ida_fail:
-	kfree(mdev);
-mdev_alloc_fail:
-	dev_err(&pdev->dev, "Probe failed rc %d\n", rc);
-	return rc;
-}
-
-/**
- * mic_remove - Device Removal Routine
- * mic_remove is called by the PCI subsystem to alert the driver
- * that it should release a PCI device.
- *
- * @pdev: PCI device structure
- */
-static void mic_remove(struct pci_dev *pdev)
-{
-	struct mic_device *mdev;
-
-	mdev = pci_get_drvdata(pdev);
-	if (!mdev)
-		return;
-
-	cosm_unregister_device(mdev->cosm_dev);
-	mic_delete_debug_dir(mdev);
-	mic_dp_uninit(mdev);
-	mic_smpt_uninit(mdev);
-	mic_free_interrupts(mdev, pdev);
-	iounmap(mdev->aper.va);
-	iounmap(mdev->mmio.va);
-	pci_release_regions(pdev);
-	pci_disable_device(pdev);
-	ida_simple_remove(&g_mic_ida, mdev->id);
-	kfree(mdev);
-}
-
-static struct pci_driver mic_driver = {
-	.name = mic_driver_name,
-	.id_table = mic_pci_tbl,
-	.probe = mic_probe,
-	.remove = mic_remove
-};
-
-static int __init mic_init(void)
-{
-	int ret;
-
-	request_module("mic_x100_dma");
-	mic_init_debugfs();
-	ida_init(&g_mic_ida);
-	ret = pci_register_driver(&mic_driver);
-	if (ret) {
-		pr_err("pci_register_driver failed ret %d\n", ret);
-		goto cleanup_debugfs;
-	}
-	return 0;
-cleanup_debugfs:
-	ida_destroy(&g_mic_ida);
-	mic_exit_debugfs();
-	return ret;
-}
-
-static void __exit mic_exit(void)
-{
-	pci_unregister_driver(&mic_driver);
-	ida_destroy(&g_mic_ida);
-	mic_exit_debugfs();
-}
-
-module_init(mic_init);
-module_exit(mic_exit);
-
-MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Intel(R) MIC X100 Host driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/misc/mic/host/mic_smpt.c b/drivers/misc/mic/host/mic_smpt.c
deleted file mode 100644
index 50d1bebecd54..000000000000
--- a/drivers/misc/mic/host/mic_smpt.c
+++ /dev/null
@@ -1,427 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC Host driver.
- */
-#include <linux/pci.h>
-
-#include "../common/mic_dev.h"
-#include "mic_device.h"
-#include "mic_smpt.h"
-
-static inline u64 mic_system_page_mask(struct mic_device *mdev)
-{
-	return (1ULL << mdev->smpt->info.page_shift) - 1ULL;
-}
-
-static inline u8 mic_sys_addr_to_smpt(struct mic_device *mdev, dma_addr_t pa)
-{
-	return (pa - mdev->smpt->info.base) >> mdev->smpt->info.page_shift;
-}
-
-static inline u64 mic_smpt_to_pa(struct mic_device *mdev, u8 index)
-{
-	return mdev->smpt->info.base + (index * mdev->smpt->info.page_size);
-}
-
-static inline u64 mic_smpt_offset(struct mic_device *mdev, dma_addr_t pa)
-{
-	return pa & mic_system_page_mask(mdev);
-}
-
-static inline u64 mic_smpt_align_low(struct mic_device *mdev, dma_addr_t pa)
-{
-	return ALIGN(pa - mic_system_page_mask(mdev),
-		mdev->smpt->info.page_size);
-}
-
-static inline u64 mic_smpt_align_high(struct mic_device *mdev, dma_addr_t pa)
-{
-	return ALIGN(pa, mdev->smpt->info.page_size);
-}
-
-/* Total Cumulative system memory accessible by MIC across all SMPT entries */
-static inline u64 mic_max_system_memory(struct mic_device *mdev)
-{
-	return mdev->smpt->info.num_reg * mdev->smpt->info.page_size;
-}
-
-/* Maximum system memory address accessible by MIC */
-static inline u64 mic_max_system_addr(struct mic_device *mdev)
-{
-	return mdev->smpt->info.base + mic_max_system_memory(mdev) - 1ULL;
-}
-
-/* Check if the DMA address is a MIC system memory address */
-static inline bool
-mic_is_system_addr(struct mic_device *mdev, dma_addr_t pa)
-{
-	return pa >= mdev->smpt->info.base && pa <= mic_max_system_addr(mdev);
-}
-
-/* Populate an SMPT entry and update the reference counts. */
-static void mic_add_smpt_entry(int spt, s64 *ref, u64 addr,
-			       int entries, struct mic_device *mdev)
-{
-	struct mic_smpt_info *smpt_info = mdev->smpt;
-	int i;
-
-	for (i = spt; i < spt + entries; i++,
-		addr += smpt_info->info.page_size) {
-		if (!smpt_info->entry[i].ref_count &&
-		    (smpt_info->entry[i].dma_addr != addr)) {
-			mdev->smpt_ops->set(mdev, addr, i);
-			smpt_info->entry[i].dma_addr = addr;
-		}
-		smpt_info->entry[i].ref_count += ref[i - spt];
-	}
-}
-
-/*
- * Find an available MIC address in MIC SMPT address space
- * for a given DMA address and size.
- */
-static dma_addr_t mic_smpt_op(struct mic_device *mdev, u64 dma_addr,
-			      int entries, s64 *ref, size_t size)
-{
-	int spt;
-	int ae = 0;
-	int i;
-	unsigned long flags;
-	dma_addr_t mic_addr = 0;
-	dma_addr_t addr = dma_addr;
-	struct mic_smpt_info *smpt_info = mdev->smpt;
-
-	spin_lock_irqsave(&smpt_info->smpt_lock, flags);
-
-	/* find existing entries */
-	for (i = 0; i < smpt_info->info.num_reg; i++) {
-		if (smpt_info->entry[i].dma_addr == addr) {
-			ae++;
-			addr += smpt_info->info.page_size;
-		} else if (ae) /* cannot find contiguous entries */
-			goto not_found;
-
-		if (ae == entries)
-			goto found;
-	}
-
-	/* find free entry */
-	for (ae = 0, i = 0; i < smpt_info->info.num_reg; i++) {
-		ae = (smpt_info->entry[i].ref_count == 0) ? ae + 1 : 0;
-		if (ae == entries)
-			goto found;
-	}
-
-not_found:
-	spin_unlock_irqrestore(&smpt_info->smpt_lock, flags);
-	return mic_addr;
-
-found:
-	spt = i - entries + 1;
-	mic_addr = mic_smpt_to_pa(mdev, spt);
-	mic_add_smpt_entry(spt, ref, dma_addr, entries, mdev);
-	smpt_info->map_count++;
-	smpt_info->ref_count += (s64)size;
-	spin_unlock_irqrestore(&smpt_info->smpt_lock, flags);
-	return mic_addr;
-}
-
-/*
- * Returns number of smpt entries needed for dma_addr to dma_addr + size
- * also returns the reference count array for each of those entries
- * and the starting smpt address
- */
-static int mic_get_smpt_ref_count(struct mic_device *mdev, dma_addr_t dma_addr,
-				  size_t size, s64 *ref,  u64 *smpt_start)
-{
-	u64 start =  dma_addr;
-	u64 end = dma_addr + size;
-	int i = 0;
-
-	while (start < end) {
-		ref[i++] = min(mic_smpt_align_high(mdev, start + 1),
-			end) - start;
-		start = mic_smpt_align_high(mdev, start + 1);
-	}
-
-	if (smpt_start)
-		*smpt_start = mic_smpt_align_low(mdev, dma_addr);
-
-	return i;
-}
-
-/*
- * mic_to_dma_addr - Converts a MIC address to a DMA address.
- *
- * @mdev: pointer to mic_device instance.
- * @mic_addr: MIC address.
- *
- * returns a DMA address.
- */
-dma_addr_t mic_to_dma_addr(struct mic_device *mdev, dma_addr_t mic_addr)
-{
-	struct mic_smpt_info *smpt_info = mdev->smpt;
-	int spt;
-	dma_addr_t dma_addr;
-
-	if (!mic_is_system_addr(mdev, mic_addr)) {
-		dev_err(&mdev->pdev->dev,
-			"mic_addr is invalid. mic_addr = 0x%llx\n", mic_addr);
-		return -EINVAL;
-	}
-	spt = mic_sys_addr_to_smpt(mdev, mic_addr);
-	dma_addr = smpt_info->entry[spt].dma_addr +
-		mic_smpt_offset(mdev, mic_addr);
-	return dma_addr;
-}
-
-/**
- * mic_map - Maps a DMA address to a MIC physical address.
- *
- * @mdev: pointer to mic_device instance.
- * @dma_addr: DMA address.
- * @size: Size of the region to be mapped.
- *
- * This API converts the DMA address provided to a DMA address understood
- * by MIC. Caller should check for errors by calling mic_map_error(..).
- *
- * returns DMA address as required by MIC.
- */
-dma_addr_t mic_map(struct mic_device *mdev, dma_addr_t dma_addr, size_t size)
-{
-	dma_addr_t mic_addr = 0;
-	int num_entries;
-	s64 *ref;
-	u64 smpt_start;
-
-	if (!size || size > mic_max_system_memory(mdev))
-		return mic_addr;
-
-	ref = kmalloc_array(mdev->smpt->info.num_reg, sizeof(s64), GFP_ATOMIC);
-	if (!ref)
-		return mic_addr;
-
-	num_entries = mic_get_smpt_ref_count(mdev, dma_addr, size,
-					     ref, &smpt_start);
-
-	/* Set the smpt table appropriately and get 16G aligned mic address */
-	mic_addr = mic_smpt_op(mdev, smpt_start, num_entries, ref, size);
-
-	kfree(ref);
-
-	/*
-	 * If mic_addr is zero then its an error case
-	 * since mic_addr can never be zero.
-	 * else generate mic_addr by adding the 16G offset in dma_addr
-	 */
-	if (!mic_addr && MIC_FAMILY_X100 == mdev->family) {
-		dev_err(&mdev->pdev->dev,
-			"mic_map failed dma_addr 0x%llx size 0x%lx\n",
-			dma_addr, size);
-		return mic_addr;
-	} else {
-		return mic_addr + mic_smpt_offset(mdev, dma_addr);
-	}
-}
-
-/**
- * mic_unmap - Unmaps a MIC physical address.
- *
- * @mdev: pointer to mic_device instance.
- * @mic_addr: MIC physical address.
- * @size: Size of the region to be unmapped.
- *
- * This API unmaps the mappings created by mic_map(..).
- *
- * returns None.
- */
-void mic_unmap(struct mic_device *mdev, dma_addr_t mic_addr, size_t size)
-{
-	struct mic_smpt_info *smpt_info = mdev->smpt;
-	s64 *ref;
-	int num_smpt;
-	int spt;
-	int i;
-	unsigned long flags;
-
-	if (!size)
-		return;
-
-	if (!mic_is_system_addr(mdev, mic_addr)) {
-		dev_err(&mdev->pdev->dev,
-			"invalid address: 0x%llx\n", mic_addr);
-		return;
-	}
-
-	spt = mic_sys_addr_to_smpt(mdev, mic_addr);
-	ref = kmalloc_array(mdev->smpt->info.num_reg, sizeof(s64), GFP_ATOMIC);
-	if (!ref)
-		return;
-
-	/* Get number of smpt entries to be mapped, ref count array */
-	num_smpt = mic_get_smpt_ref_count(mdev, mic_addr, size, ref, NULL);
-
-	spin_lock_irqsave(&smpt_info->smpt_lock, flags);
-	smpt_info->unmap_count++;
-	smpt_info->ref_count -= (s64)size;
-
-	for (i = spt; i < spt + num_smpt; i++) {
-		smpt_info->entry[i].ref_count -= ref[i - spt];
-		if (smpt_info->entry[i].ref_count < 0)
-			dev_warn(&mdev->pdev->dev,
-				 "ref count for entry %d is negative\n", i);
-	}
-	spin_unlock_irqrestore(&smpt_info->smpt_lock, flags);
-	kfree(ref);
-}
-
-/**
- * mic_map_single - Maps a virtual address to a MIC physical address.
- *
- * @mdev: pointer to mic_device instance.
- * @va: Kernel direct mapped virtual address.
- * @size: Size of the region to be mapped.
- *
- * This API calls pci_map_single(..) for the direct mapped virtual address
- * and then converts the DMA address provided to a DMA address understood
- * by MIC. Caller should check for errors by calling mic_map_error(..).
- *
- * returns DMA address as required by MIC.
- */
-dma_addr_t mic_map_single(struct mic_device *mdev, void *va, size_t size)
-{
-	dma_addr_t mic_addr = 0;
-	struct pci_dev *pdev = mdev->pdev;
-	dma_addr_t dma_addr =
-		pci_map_single(pdev, va, size, PCI_DMA_BIDIRECTIONAL);
-
-	if (!pci_dma_mapping_error(pdev, dma_addr)) {
-		mic_addr = mic_map(mdev, dma_addr, size);
-		if (!mic_addr) {
-			dev_err(&mdev->pdev->dev,
-				"mic_map failed dma_addr 0x%llx size 0x%lx\n",
-				dma_addr, size);
-			pci_unmap_single(pdev, dma_addr,
-					 size, PCI_DMA_BIDIRECTIONAL);
-		}
-	}
-	return mic_addr;
-}
-
-/**
- * mic_unmap_single - Unmaps a MIC physical address.
- *
- * @mdev: pointer to mic_device instance.
- * @mic_addr: MIC physical address.
- * @size: Size of the region to be unmapped.
- *
- * This API unmaps the mappings created by mic_map_single(..).
- *
- * returns None.
- */
-void
-mic_unmap_single(struct mic_device *mdev, dma_addr_t mic_addr, size_t size)
-{
-	struct pci_dev *pdev = mdev->pdev;
-	dma_addr_t dma_addr = mic_to_dma_addr(mdev, mic_addr);
-	mic_unmap(mdev, mic_addr, size);
-	pci_unmap_single(pdev, dma_addr, size, PCI_DMA_BIDIRECTIONAL);
-}
-
-/**
- * mic_smpt_init - Initialize MIC System Memory Page Tables.
- *
- * @mdev: pointer to mic_device instance.
- *
- * returns 0 for success and -errno for error.
- */
-int mic_smpt_init(struct mic_device *mdev)
-{
-	int i, err = 0;
-	dma_addr_t dma_addr;
-	struct mic_smpt_info *smpt_info;
-
-	mdev->smpt = kmalloc(sizeof(*mdev->smpt), GFP_KERNEL);
-	if (!mdev->smpt)
-		return -ENOMEM;
-
-	smpt_info = mdev->smpt;
-	mdev->smpt_ops->init(mdev);
-	smpt_info->entry = kmalloc_array(smpt_info->info.num_reg,
-					 sizeof(*smpt_info->entry), GFP_KERNEL);
-	if (!smpt_info->entry) {
-		err = -ENOMEM;
-		goto free_smpt;
-	}
-	spin_lock_init(&smpt_info->smpt_lock);
-	for (i = 0; i < smpt_info->info.num_reg; i++) {
-		dma_addr = i * smpt_info->info.page_size;
-		smpt_info->entry[i].dma_addr = dma_addr;
-		smpt_info->entry[i].ref_count = 0;
-		mdev->smpt_ops->set(mdev, dma_addr, i);
-	}
-	smpt_info->ref_count = 0;
-	smpt_info->map_count = 0;
-	smpt_info->unmap_count = 0;
-	return 0;
-free_smpt:
-	kfree(smpt_info);
-	return err;
-}
-
-/**
- * mic_smpt_uninit - UnInitialize MIC System Memory Page Tables.
- *
- * @mdev: pointer to mic_device instance.
- *
- * returns None.
- */
-void mic_smpt_uninit(struct mic_device *mdev)
-{
-	struct mic_smpt_info *smpt_info = mdev->smpt;
-	int i;
-
-	dev_dbg(&mdev->pdev->dev,
-		"nodeid %d SMPT ref count %lld map %lld unmap %lld\n",
-		mdev->id, smpt_info->ref_count,
-		smpt_info->map_count, smpt_info->unmap_count);
-
-	for (i = 0; i < smpt_info->info.num_reg; i++) {
-		dev_dbg(&mdev->pdev->dev,
-			"SMPT entry[%d] dma_addr = 0x%llx ref_count = %lld\n",
-			i, smpt_info->entry[i].dma_addr,
-			smpt_info->entry[i].ref_count);
-		if (smpt_info->entry[i].ref_count)
-			dev_warn(&mdev->pdev->dev,
-				 "ref count for entry %d is not zero\n", i);
-	}
-	kfree(smpt_info->entry);
-	kfree(smpt_info);
-}
-
-/**
- * mic_smpt_restore - Restore MIC System Memory Page Tables.
- *
- * @mdev: pointer to mic_device instance.
- *
- * Restore the SMPT registers to values previously stored in the
- * SW data structures. Some MIC steppings lose register state
- * across resets and this API should be called for performing
- * a restore operation if required.
- *
- * returns None.
- */
-void mic_smpt_restore(struct mic_device *mdev)
-{
-	int i;
-	dma_addr_t dma_addr;
-
-	for (i = 0; i < mdev->smpt->info.num_reg; i++) {
-		dma_addr = mdev->smpt->entry[i].dma_addr;
-		mdev->smpt_ops->set(mdev, dma_addr, i);
-	}
-}
diff --git a/drivers/misc/mic/host/mic_smpt.h b/drivers/misc/mic/host/mic_smpt.h
deleted file mode 100644
index 3b1ec14a9d81..000000000000
--- a/drivers/misc/mic/host/mic_smpt.h
+++ /dev/null
@@ -1,87 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC Host driver.
- */
-#ifndef MIC_SMPT_H
-#define MIC_SMPT_H
-/**
- * struct mic_smpt_ops - MIC HW specific SMPT operations.
- * @init: Initialize hardware specific SMPT information in mic_smpt_hw_info.
- * @set: Set the value for a particular SMPT entry.
- */
-struct mic_smpt_ops {
-	void (*init)(struct mic_device *mdev);
-	void (*set)(struct mic_device *mdev, dma_addr_t dma_addr, u8 index);
-};
-
-/**
- * struct mic_smpt - MIC SMPT entry information.
- * @dma_addr: Base DMA address for this SMPT entry.
- * @ref_count: Number of active mappings for this SMPT entry in bytes.
- */
-struct mic_smpt {
-	dma_addr_t dma_addr;
-	s64 ref_count;
-};
-
-/**
- * struct mic_smpt_hw_info - MIC SMPT hardware specific information.
- * @num_reg: Number of SMPT registers.
- * @page_shift: System memory page shift.
- * @page_size: System memory page size.
- * @base: System address base.
- */
-struct mic_smpt_hw_info {
-	u8 num_reg;
-	u8 page_shift;
-	u64 page_size;
-	u64 base;
-};
-
-/**
- * struct mic_smpt_info - MIC SMPT information.
- * @entry: Array of SMPT entries.
- * @smpt_lock: Spin lock protecting access to SMPT data structures.
- * @info: Hardware specific SMPT information.
- * @ref_count: Number of active SMPT mappings (for debug).
- * @map_count: Number of SMPT mappings created (for debug).
- * @unmap_count: Number of SMPT mappings destroyed (for debug).
- */
-struct mic_smpt_info {
-	struct mic_smpt *entry;
-	spinlock_t smpt_lock;
-	struct mic_smpt_hw_info info;
-	s64 ref_count;
-	s64 map_count;
-	s64 unmap_count;
-};
-
-dma_addr_t mic_map_single(struct mic_device *mdev, void *va, size_t size);
-void mic_unmap_single(struct mic_device *mdev,
-	dma_addr_t mic_addr, size_t size);
-dma_addr_t mic_map(struct mic_device *mdev,
-	dma_addr_t dma_addr, size_t size);
-void mic_unmap(struct mic_device *mdev, dma_addr_t mic_addr, size_t size);
-dma_addr_t mic_to_dma_addr(struct mic_device *mdev, dma_addr_t mic_addr);
-
-/**
- * mic_map_error - Check a MIC address for errors.
- *
- * @mdev: pointer to mic_device instance.
- *
- * returns Whether there was an error during mic_map..(..) APIs.
- */
-static inline bool mic_map_error(dma_addr_t mic_addr)
-{
-	return !mic_addr;
-}
-
-int mic_smpt_init(struct mic_device *mdev);
-void mic_smpt_uninit(struct mic_device *mdev);
-void mic_smpt_restore(struct mic_device *mdev);
-
-#endif
diff --git a/drivers/misc/mic/host/mic_x100.c b/drivers/misc/mic/host/mic_x100.c
deleted file mode 100644
index f5536c1ad607..000000000000
--- a/drivers/misc/mic/host/mic_x100.c
+++ /dev/null
@@ -1,585 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC Host driver.
- */
-#include <linux/fs.h>
-#include <linux/pci.h>
-#include <linux/sched.h>
-#include <linux/firmware.h>
-#include <linux/delay.h>
-
-#include "../common/mic_dev.h"
-#include "mic_device.h"
-#include "mic_x100.h"
-#include "mic_smpt.h"
-
-static const u16 mic_x100_intr_init[] = {
-		MIC_X100_DOORBELL_IDX_START,
-		MIC_X100_DMA_IDX_START,
-		MIC_X100_ERR_IDX_START,
-		MIC_X100_NUM_DOORBELL,
-		MIC_X100_NUM_DMA,
-		MIC_X100_NUM_ERR,
-};
-
-/**
- * mic_x100_write_spad - write to the scratchpad register
- * @mdev: pointer to mic_device instance
- * @idx: index to the scratchpad register, 0 based
- * @val: the data value to put into the register
- *
- * This function allows writing of a 32bit value to the indexed scratchpad
- * register.
- *
- * RETURNS: none.
- */
-static void
-mic_x100_write_spad(struct mic_device *mdev, unsigned int idx, u32 val)
-{
-	dev_dbg(&mdev->pdev->dev, "Writing 0x%x to scratch pad index %d\n",
-		val, idx);
-	mic_mmio_write(&mdev->mmio, val,
-		       MIC_X100_SBOX_BASE_ADDRESS +
-		       MIC_X100_SBOX_SPAD0 + idx * 4);
-}
-
-/**
- * mic_x100_read_spad - read from the scratchpad register
- * @mdev: pointer to mic_device instance
- * @idx: index to scratchpad register, 0 based
- *
- * This function allows reading of the 32bit scratchpad register.
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-static u32
-mic_x100_read_spad(struct mic_device *mdev, unsigned int idx)
-{
-	u32 val = mic_mmio_read(&mdev->mmio,
-		MIC_X100_SBOX_BASE_ADDRESS +
-		MIC_X100_SBOX_SPAD0 + idx * 4);
-
-	dev_dbg(&mdev->pdev->dev,
-		"Reading 0x%x from scratch pad index %d\n", val, idx);
-	return val;
-}
-
-/**
- * mic_x100_enable_interrupts - Enable interrupts.
- * @mdev: pointer to mic_device instance
- */
-static void mic_x100_enable_interrupts(struct mic_device *mdev)
-{
-	u32 reg;
-	struct mic_mw *mw = &mdev->mmio;
-	u32 sice0 = MIC_X100_SBOX_BASE_ADDRESS + MIC_X100_SBOX_SICE0;
-	u32 siac0 = MIC_X100_SBOX_BASE_ADDRESS + MIC_X100_SBOX_SIAC0;
-
-	reg = mic_mmio_read(mw, sice0);
-	reg |= MIC_X100_SBOX_DBR_BITS(0xf) | MIC_X100_SBOX_DMA_BITS(0xff);
-	mic_mmio_write(mw, reg, sice0);
-
-	/*
-	 * Enable auto-clear when enabling interrupts. Applicable only for
-	 * MSI-x. Legacy and MSI mode cannot have auto-clear enabled.
-	 */
-	if (mdev->irq_info.num_vectors > 1) {
-		reg = mic_mmio_read(mw, siac0);
-		reg |= MIC_X100_SBOX_DBR_BITS(0xf) |
-			MIC_X100_SBOX_DMA_BITS(0xff);
-		mic_mmio_write(mw, reg, siac0);
-	}
-}
-
-/**
- * mic_x100_disable_interrupts - Disable interrupts.
- * @mdev: pointer to mic_device instance
- */
-static void mic_x100_disable_interrupts(struct mic_device *mdev)
-{
-	u32 reg;
-	struct mic_mw *mw = &mdev->mmio;
-	u32 sice0 = MIC_X100_SBOX_BASE_ADDRESS + MIC_X100_SBOX_SICE0;
-	u32 siac0 = MIC_X100_SBOX_BASE_ADDRESS + MIC_X100_SBOX_SIAC0;
-	u32 sicc0 = MIC_X100_SBOX_BASE_ADDRESS + MIC_X100_SBOX_SICC0;
-
-	reg = mic_mmio_read(mw, sice0);
-	mic_mmio_write(mw, reg, sicc0);
-
-	if (mdev->irq_info.num_vectors > 1) {
-		reg = mic_mmio_read(mw, siac0);
-		reg &= ~(MIC_X100_SBOX_DBR_BITS(0xf) |
-			MIC_X100_SBOX_DMA_BITS(0xff));
-		mic_mmio_write(mw, reg, siac0);
-	}
-}
-
-/**
- * mic_x100_send_sbox_intr - Send an MIC_X100_SBOX interrupt to MIC.
- * @mdev: pointer to mic_device instance
- * @doorbell: doorbell number
- */
-static void mic_x100_send_sbox_intr(struct mic_device *mdev,
-				    int doorbell)
-{
-	struct mic_mw *mw = &mdev->mmio;
-	u64 apic_icr_offset = MIC_X100_SBOX_APICICR0 + doorbell * 8;
-	u32 apicicr_low = mic_mmio_read(mw, MIC_X100_SBOX_BASE_ADDRESS +
-					apic_icr_offset);
-
-	/* for MIC we need to make sure we "hit" the send_icr bit (13) */
-	apicicr_low = (apicicr_low | (1 << 13));
-
-	/* Ensure that the interrupt is ordered w.r.t. previous stores. */
-	wmb();
-	mic_mmio_write(mw, apicicr_low,
-		       MIC_X100_SBOX_BASE_ADDRESS + apic_icr_offset);
-}
-
-/**
- * mic_x100_send_rdmasr_intr - Send an RDMASR interrupt to MIC.
- * @mdev: pointer to mic_device instance
- * @doorbell: doorbell number
- */
-static void mic_x100_send_rdmasr_intr(struct mic_device *mdev,
-				      int doorbell)
-{
-	int rdmasr_offset = MIC_X100_SBOX_RDMASR0 + (doorbell << 2);
-	/* Ensure that the interrupt is ordered w.r.t. previous stores. */
-	wmb();
-	mic_mmio_write(&mdev->mmio, 0,
-		       MIC_X100_SBOX_BASE_ADDRESS + rdmasr_offset);
-}
-
-/**
- * __mic_x100_send_intr - Send interrupt to MIC.
- * @mdev: pointer to mic_device instance
- * @doorbell: doorbell number.
- */
-static void mic_x100_send_intr(struct mic_device *mdev, int doorbell)
-{
-	int rdmasr_db;
-	if (doorbell < MIC_X100_NUM_SBOX_IRQ) {
-		mic_x100_send_sbox_intr(mdev, doorbell);
-	} else {
-		rdmasr_db = doorbell - MIC_X100_NUM_SBOX_IRQ;
-		mic_x100_send_rdmasr_intr(mdev, rdmasr_db);
-	}
-}
-
-/**
- * mic_x100_ack_interrupt - Read the interrupt sources register and
- * clear it. This function will be called in the MSI/INTx case.
- * @mdev: Pointer to mic_device instance.
- *
- * Returns: bitmask of interrupt sources triggered.
- */
-static u32 mic_x100_ack_interrupt(struct mic_device *mdev)
-{
-	u32 sicr0 = MIC_X100_SBOX_BASE_ADDRESS + MIC_X100_SBOX_SICR0;
-	u32 reg = mic_mmio_read(&mdev->mmio, sicr0);
-	mic_mmio_write(&mdev->mmio, reg, sicr0);
-	return reg;
-}
-
-/**
- * mic_x100_intr_workarounds - These hardware specific workarounds are
- * to be invoked everytime an interrupt is handled.
- * @mdev: Pointer to mic_device instance.
- *
- * Returns: none
- */
-static void mic_x100_intr_workarounds(struct mic_device *mdev)
-{
-	struct mic_mw *mw = &mdev->mmio;
-
-	/* Clear pending bit array. */
-	if (MIC_A0_STEP == mdev->stepping)
-		mic_mmio_write(mw, 1, MIC_X100_SBOX_BASE_ADDRESS +
-			MIC_X100_SBOX_MSIXPBACR);
-
-	if (mdev->stepping >= MIC_B0_STEP)
-		mdev->intr_ops->enable_interrupts(mdev);
-}
-
-/**
- * mic_x100_hw_intr_init - Initialize h/w specific interrupt
- * information.
- * @mdev: pointer to mic_device instance
- */
-static void mic_x100_hw_intr_init(struct mic_device *mdev)
-{
-	mdev->intr_info = (struct mic_intr_info *)mic_x100_intr_init;
-}
-
-/**
- * mic_x100_read_msi_to_src_map - read from the MSI mapping registers
- * @mdev: pointer to mic_device instance
- * @idx: index to the mapping register, 0 based
- *
- * This function allows reading of the 32bit MSI mapping register.
- *
- * RETURNS: The value in the register.
- */
-static u32
-mic_x100_read_msi_to_src_map(struct mic_device *mdev, int idx)
-{
-	return mic_mmio_read(&mdev->mmio,
-		MIC_X100_SBOX_BASE_ADDRESS +
-		MIC_X100_SBOX_MXAR0 + idx * 4);
-}
-
-/**
- * mic_x100_program_msi_to_src_map - program the MSI mapping registers
- * @mdev: pointer to mic_device instance
- * @idx: index to the mapping register, 0 based
- * @offset: The bit offset in the register that needs to be updated.
- * @set: boolean specifying if the bit in the specified offset needs
- * to be set or cleared.
- *
- * RETURNS: None.
- */
-static void
-mic_x100_program_msi_to_src_map(struct mic_device *mdev,
-				int idx, int offset, bool set)
-{
-	unsigned long reg;
-	struct mic_mw *mw = &mdev->mmio;
-	u32 mxar = MIC_X100_SBOX_BASE_ADDRESS +
-		MIC_X100_SBOX_MXAR0 + idx * 4;
-
-	reg = mic_mmio_read(mw, mxar);
-	if (set)
-		__set_bit(offset, &reg);
-	else
-		__clear_bit(offset, &reg);
-	mic_mmio_write(mw, reg, mxar);
-}
-
-/*
- * mic_x100_reset_fw_ready - Reset Firmware ready status field.
- * @mdev: pointer to mic_device instance
- */
-static void mic_x100_reset_fw_ready(struct mic_device *mdev)
-{
-	mdev->ops->write_spad(mdev, MIC_X100_DOWNLOAD_INFO, 0);
-}
-
-/*
- * mic_x100_is_fw_ready - Check if firmware is ready.
- * @mdev: pointer to mic_device instance
- */
-static bool mic_x100_is_fw_ready(struct mic_device *mdev)
-{
-	u32 scratch2 = mdev->ops->read_spad(mdev, MIC_X100_DOWNLOAD_INFO);
-	return MIC_X100_SPAD2_DOWNLOAD_STATUS(scratch2) ? true : false;
-}
-
-/**
- * mic_x100_get_apic_id - Get bootstrap APIC ID.
- * @mdev: pointer to mic_device instance
- */
-static u32 mic_x100_get_apic_id(struct mic_device *mdev)
-{
-	u32 scratch2 = 0;
-
-	scratch2 = mdev->ops->read_spad(mdev, MIC_X100_DOWNLOAD_INFO);
-	return MIC_X100_SPAD2_APIC_ID(scratch2);
-}
-
-/**
- * mic_x100_send_firmware_intr - Send an interrupt to the firmware on MIC.
- * @mdev: pointer to mic_device instance
- */
-static void mic_x100_send_firmware_intr(struct mic_device *mdev)
-{
-	u32 apicicr_low;
-	u64 apic_icr_offset = MIC_X100_SBOX_APICICR7;
-	int vector = MIC_X100_BSP_INTERRUPT_VECTOR;
-	struct mic_mw *mw = &mdev->mmio;
-
-	/*
-	 * For MIC we need to make sure we "hit"
-	 * the send_icr bit (13).
-	 */
-	apicicr_low = (vector | (1 << 13));
-
-	mic_mmio_write(mw, mic_x100_get_apic_id(mdev),
-		       MIC_X100_SBOX_BASE_ADDRESS + apic_icr_offset + 4);
-
-	/* Ensure that the interrupt is ordered w.r.t. previous stores. */
-	wmb();
-	mic_mmio_write(mw, apicicr_low,
-		       MIC_X100_SBOX_BASE_ADDRESS + apic_icr_offset);
-}
-
-/**
- * mic_x100_hw_reset - Reset the MIC device.
- * @mdev: pointer to mic_device instance
- */
-static void mic_x100_hw_reset(struct mic_device *mdev)
-{
-	u32 reset_reg;
-	u32 rgcr = MIC_X100_SBOX_BASE_ADDRESS + MIC_X100_SBOX_RGCR;
-	struct mic_mw *mw = &mdev->mmio;
-
-	/* Ensure that the reset is ordered w.r.t. previous loads and stores */
-	mb();
-	/* Trigger reset */
-	reset_reg = mic_mmio_read(mw, rgcr);
-	reset_reg |= 0x1;
-	mic_mmio_write(mw, reset_reg, rgcr);
-	/*
-	 * It seems we really want to delay at least 1 second
-	 * after touching reset to prevent a lot of problems.
-	 */
-	msleep(1000);
-}
-
-/**
- * mic_x100_load_command_line - Load command line to MIC.
- * @mdev: pointer to mic_device instance
- * @fw: the firmware image
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-static int
-mic_x100_load_command_line(struct mic_device *mdev, const struct firmware *fw)
-{
-	u32 len = 0;
-	u32 boot_mem;
-	char *buf;
-	void __iomem *cmd_line_va = mdev->aper.va + mdev->bootaddr + fw->size;
-#define CMDLINE_SIZE 2048
-
-	boot_mem = mdev->aper.len >> 20;
-	buf = kzalloc(CMDLINE_SIZE, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	len += scnprintf(buf, CMDLINE_SIZE - len,
-		" mem=%dM", boot_mem);
-	if (mdev->cosm_dev->cmdline)
-		scnprintf(buf + len, CMDLINE_SIZE - len, " %s",
-			 mdev->cosm_dev->cmdline);
-	memcpy_toio(cmd_line_va, buf, strlen(buf) + 1);
-	kfree(buf);
-	return 0;
-}
-
-/**
- * mic_x100_load_ramdisk - Load ramdisk to MIC.
- * @mdev: pointer to mic_device instance
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-static int
-mic_x100_load_ramdisk(struct mic_device *mdev)
-{
-	const struct firmware *fw;
-	int rc;
-	struct boot_params __iomem *bp = mdev->aper.va + mdev->bootaddr;
-
-	rc = request_firmware(&fw, mdev->cosm_dev->ramdisk, &mdev->pdev->dev);
-	if (rc < 0) {
-		dev_err(&mdev->pdev->dev,
-			"ramdisk request_firmware failed: %d %s\n",
-			rc, mdev->cosm_dev->ramdisk);
-		goto error;
-	}
-	/*
-	 * Typically the bootaddr for card OS is 64M
-	 * so copy over the ramdisk @ 128M.
-	 */
-	memcpy_toio(mdev->aper.va + (mdev->bootaddr << 1), fw->data, fw->size);
-	iowrite32(mdev->bootaddr << 1, &bp->hdr.ramdisk_image);
-	iowrite32(fw->size, &bp->hdr.ramdisk_size);
-	release_firmware(fw);
-error:
-	return rc;
-}
-
-/**
- * mic_x100_get_boot_addr - Get MIC boot address.
- * @mdev: pointer to mic_device instance
- *
- * This function is called during firmware load to determine
- * the address at which the OS should be downloaded in card
- * memory i.e. GDDR.
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-static int
-mic_x100_get_boot_addr(struct mic_device *mdev)
-{
-	u32 scratch2, boot_addr;
-	int rc = 0;
-
-	scratch2 = mdev->ops->read_spad(mdev, MIC_X100_DOWNLOAD_INFO);
-	boot_addr = MIC_X100_SPAD2_DOWNLOAD_ADDR(scratch2);
-	dev_dbg(&mdev->pdev->dev, "%s %d boot_addr 0x%x\n",
-		__func__, __LINE__, boot_addr);
-	if (boot_addr > (1 << 31)) {
-		dev_err(&mdev->pdev->dev,
-			"incorrect bootaddr 0x%x\n",
-			boot_addr);
-		rc = -EINVAL;
-		goto error;
-	}
-	mdev->bootaddr = boot_addr;
-error:
-	return rc;
-}
-
-/**
- * mic_x100_load_firmware - Load firmware to MIC.
- * @mdev: pointer to mic_device instance
- * @buf: buffer containing boot string including firmware/ramdisk path.
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-static int
-mic_x100_load_firmware(struct mic_device *mdev, const char *buf)
-{
-	int rc;
-	const struct firmware *fw;
-
-	rc = mic_x100_get_boot_addr(mdev);
-	if (rc)
-		return rc;
-	/* load OS */
-	rc = request_firmware(&fw, mdev->cosm_dev->firmware, &mdev->pdev->dev);
-	if (rc < 0) {
-		dev_err(&mdev->pdev->dev,
-			"ramdisk request_firmware failed: %d %s\n",
-			rc, mdev->cosm_dev->firmware);
-		return rc;
-	}
-	if (mdev->bootaddr > mdev->aper.len - fw->size) {
-		rc = -EINVAL;
-		dev_err(&mdev->pdev->dev, "%s %d rc %d bootaddr 0x%x\n",
-			__func__, __LINE__, rc, mdev->bootaddr);
-		goto error;
-	}
-	memcpy_toio(mdev->aper.va + mdev->bootaddr, fw->data, fw->size);
-	mdev->ops->write_spad(mdev, MIC_X100_FW_SIZE, fw->size);
-	if (!strcmp(mdev->cosm_dev->bootmode, "flash")) {
-		rc = -EINVAL;
-		dev_err(&mdev->pdev->dev, "%s %d rc %d\n",
-			__func__, __LINE__, rc);
-		goto error;
-	}
-	/* load command line */
-	rc = mic_x100_load_command_line(mdev, fw);
-	if (rc) {
-		dev_err(&mdev->pdev->dev, "%s %d rc %d\n",
-			__func__, __LINE__, rc);
-		goto error;
-	}
-	release_firmware(fw);
-	/* load ramdisk */
-	if (mdev->cosm_dev->ramdisk)
-		rc = mic_x100_load_ramdisk(mdev);
-
-	return rc;
-
-error:
-	release_firmware(fw);
-	return rc;
-}
-
-/**
- * mic_x100_get_postcode - Get postcode status from firmware.
- * @mdev: pointer to mic_device instance
- *
- * RETURNS: postcode.
- */
-static u32 mic_x100_get_postcode(struct mic_device *mdev)
-{
-	return mic_mmio_read(&mdev->mmio, MIC_X100_POSTCODE);
-}
-
-/**
- * mic_x100_smpt_set - Update an SMPT entry with a DMA address.
- * @mdev: pointer to mic_device instance
- * @dma_addr: DMA address to use
- * @index: entry to write to
- *
- * RETURNS: none.
- */
-static void
-mic_x100_smpt_set(struct mic_device *mdev, dma_addr_t dma_addr, u8 index)
-{
-#define SNOOP_ON	(0 << 0)
-#define SNOOP_OFF	(1 << 0)
-/*
- * Sbox Smpt Reg Bits:
- * Bits	31:2	Host address
- * Bits	1	RSVD
- * Bits	0	No snoop
- */
-#define BUILD_SMPT(NO_SNOOP, HOST_ADDR)  \
-	(u32)(((HOST_ADDR) << 2) | ((NO_SNOOP) & 0x01))
-
-	uint32_t smpt_reg_val = BUILD_SMPT(SNOOP_ON,
-			dma_addr >> mdev->smpt->info.page_shift);
-	mic_mmio_write(&mdev->mmio, smpt_reg_val,
-		       MIC_X100_SBOX_BASE_ADDRESS +
-		       MIC_X100_SBOX_SMPT00 + (4 * index));
-}
-
-/**
- * mic_x100_smpt_hw_init - Initialize SMPT X100 specific fields.
- * @mdev: pointer to mic_device instance
- *
- * RETURNS: none.
- */
-static void mic_x100_smpt_hw_init(struct mic_device *mdev)
-{
-	struct mic_smpt_hw_info *info = &mdev->smpt->info;
-
-	info->num_reg = 32;
-	info->page_shift = 34;
-	info->page_size = (1ULL << info->page_shift);
-	info->base = 0x8000000000ULL;
-}
-
-struct mic_smpt_ops mic_x100_smpt_ops = {
-	.init = mic_x100_smpt_hw_init,
-	.set = mic_x100_smpt_set,
-};
-
-static bool mic_x100_dma_filter(struct dma_chan *chan, void *param)
-{
-	if (chan->device->dev->parent == (struct device *)param)
-		return true;
-	return false;
-}
-
-struct mic_hw_ops mic_x100_ops = {
-	.aper_bar = MIC_X100_APER_BAR,
-	.mmio_bar = MIC_X100_MMIO_BAR,
-	.read_spad = mic_x100_read_spad,
-	.write_spad = mic_x100_write_spad,
-	.send_intr = mic_x100_send_intr,
-	.ack_interrupt = mic_x100_ack_interrupt,
-	.intr_workarounds = mic_x100_intr_workarounds,
-	.reset = mic_x100_hw_reset,
-	.reset_fw_ready = mic_x100_reset_fw_ready,
-	.is_fw_ready = mic_x100_is_fw_ready,
-	.send_firmware_intr = mic_x100_send_firmware_intr,
-	.load_mic_fw = mic_x100_load_firmware,
-	.get_postcode = mic_x100_get_postcode,
-	.dma_filter = mic_x100_dma_filter,
-};
-
-struct mic_hw_intr_ops mic_x100_intr_ops = {
-	.intr_init = mic_x100_hw_intr_init,
-	.enable_interrupts = mic_x100_enable_interrupts,
-	.disable_interrupts = mic_x100_disable_interrupts,
-	.program_msi_to_src_map = mic_x100_program_msi_to_src_map,
-	.read_msi_to_src_map = mic_x100_read_msi_to_src_map,
-};
diff --git a/drivers/misc/mic/host/mic_x100.h b/drivers/misc/mic/host/mic_x100.h
deleted file mode 100644
index aebcaed6fa72..000000000000
--- a/drivers/misc/mic/host/mic_x100.h
+++ /dev/null
@@ -1,77 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC Host driver.
- */
-#ifndef _MIC_X100_HW_H_
-#define _MIC_X100_HW_H_
-
-#define MIC_X100_PCI_DEVICE_2250 0x2250
-#define MIC_X100_PCI_DEVICE_2251 0x2251
-#define MIC_X100_PCI_DEVICE_2252 0x2252
-#define MIC_X100_PCI_DEVICE_2253 0x2253
-#define MIC_X100_PCI_DEVICE_2254 0x2254
-#define MIC_X100_PCI_DEVICE_2255 0x2255
-#define MIC_X100_PCI_DEVICE_2256 0x2256
-#define MIC_X100_PCI_DEVICE_2257 0x2257
-#define MIC_X100_PCI_DEVICE_2258 0x2258
-#define MIC_X100_PCI_DEVICE_2259 0x2259
-#define MIC_X100_PCI_DEVICE_225a 0x225a
-#define MIC_X100_PCI_DEVICE_225b 0x225b
-#define MIC_X100_PCI_DEVICE_225c 0x225c
-#define MIC_X100_PCI_DEVICE_225d 0x225d
-#define MIC_X100_PCI_DEVICE_225e 0x225e
-
-#define MIC_X100_APER_BAR 0
-#define MIC_X100_MMIO_BAR 4
-
-#define MIC_X100_SBOX_BASE_ADDRESS 0x00010000
-#define MIC_X100_SBOX_SPAD0 0x0000AB20
-#define MIC_X100_SBOX_SICR0_DBR(x) ((x) & 0xf)
-#define MIC_X100_SBOX_SICR0_DMA(x) (((x) >> 8) & 0xff)
-#define MIC_X100_SBOX_SICE0_DBR(x) ((x) & 0xf)
-#define MIC_X100_SBOX_DBR_BITS(x) ((x) & 0xf)
-#define MIC_X100_SBOX_SICE0_DMA(x) (((x) >> 8) & 0xff)
-#define MIC_X100_SBOX_DMA_BITS(x) (((x) & 0xff) << 8)
-
-#define MIC_X100_SBOX_APICICR0 0x0000A9D0
-#define MIC_X100_SBOX_SICR0 0x00009004
-#define MIC_X100_SBOX_SICE0 0x0000900C
-#define MIC_X100_SBOX_SICC0 0x00009010
-#define MIC_X100_SBOX_SIAC0 0x00009014
-#define MIC_X100_SBOX_MSIXPBACR 0x00009084
-#define MIC_X100_SBOX_MXAR0 0x00009044
-#define MIC_X100_SBOX_SMPT00 0x00003100
-#define MIC_X100_SBOX_RDMASR0 0x0000B180
-
-#define MIC_X100_DOORBELL_IDX_START 0
-#define MIC_X100_NUM_DOORBELL 4
-#define MIC_X100_DMA_IDX_START 8
-#define MIC_X100_NUM_DMA 8
-#define MIC_X100_ERR_IDX_START 30
-#define MIC_X100_NUM_ERR 1
-
-#define MIC_X100_NUM_SBOX_IRQ 8
-#define MIC_X100_NUM_RDMASR_IRQ 8
-#define MIC_X100_RDMASR_IRQ_BASE 17
-#define MIC_X100_SPAD2_DOWNLOAD_STATUS(x) ((x) & 0x1)
-#define MIC_X100_SPAD2_APIC_ID(x)	(((x) >> 1) & 0x1ff)
-#define MIC_X100_SPAD2_DOWNLOAD_ADDR(x) ((x) & 0xfffff000)
-#define MIC_X100_SBOX_APICICR7 0x0000AA08
-#define MIC_X100_SBOX_RGCR 0x00004010
-#define MIC_X100_SBOX_SDBIC0 0x0000CC90
-#define MIC_X100_DOWNLOAD_INFO 2
-#define MIC_X100_FW_SIZE 5
-#define MIC_X100_POSTCODE 0x242c
-
-/* Host->Card(bootstrap) Interrupt Vector */
-#define MIC_X100_BSP_INTERRUPT_VECTOR 229
-
-extern struct mic_hw_ops mic_x100_ops;
-extern struct mic_smpt_ops mic_x100_smpt_ops;
-extern struct mic_hw_intr_ops mic_x100_intr_ops;
-
-#endif
diff --git a/drivers/misc/mic/scif/Makefile b/drivers/misc/mic/scif/Makefile
deleted file mode 100644
index ff372555d118..000000000000
--- a/drivers/misc/mic/scif/Makefile
+++ /dev/null
@@ -1,21 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-#
-# Makefile - SCIF driver.
-# Copyright(c) 2014, Intel Corporation.
-#
-obj-$(CONFIG_SCIF) += scif.o
-scif-objs := scif_main.o
-scif-objs += scif_peer_bus.o
-scif-objs += scif_ports.o
-scif-objs += scif_debugfs.o
-scif-objs += scif_fd.o
-scif-objs += scif_api.o
-scif-objs += scif_epd.o
-scif-objs += scif_rb.o
-scif-objs += scif_nodeqp.o
-scif-objs += scif_nm.o
-scif-objs += scif_dma.o
-scif-objs += scif_fence.o
-scif-objs += scif_mmap.o
-scif-objs += scif_rma.o
-scif-objs += scif_rma_list.o
diff --git a/drivers/misc/mic/scif/scif_api.c b/drivers/misc/mic/scif/scif_api.c
deleted file mode 100644
index 304d6c833712..000000000000
--- a/drivers/misc/mic/scif/scif_api.c
+++ /dev/null
@@ -1,1485 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include <linux/scif.h>
-#include "scif_main.h"
-#include "scif_map.h"
-
-static const char * const scif_ep_states[] = {
-	"Unbound",
-	"Bound",
-	"Listening",
-	"Connected",
-	"Connecting",
-	"Mapping",
-	"Closing",
-	"Close Listening",
-	"Disconnected",
-	"Zombie"};
-
-enum conn_async_state {
-	ASYNC_CONN_IDLE = 1,	/* ep setup for async connect */
-	ASYNC_CONN_INPROGRESS,	/* async connect in progress */
-	ASYNC_CONN_FLUSH_WORK	/* async work flush in progress  */
-};
-
-/*
- * File operations for anonymous inode file associated with a SCIF endpoint,
- * used in kernel mode SCIF poll. Kernel mode SCIF poll calls portions of the
- * poll API in the kernel and these take in a struct file *. Since a struct
- * file is not available to kernel mode SCIF, it uses an anonymous file for
- * this purpose.
- */
-const struct file_operations scif_anon_fops = {
-	.owner = THIS_MODULE,
-};
-
-scif_epd_t scif_open(void)
-{
-	struct scif_endpt *ep;
-	int err;
-
-	might_sleep();
-	ep = kzalloc(sizeof(*ep), GFP_KERNEL);
-	if (!ep)
-		goto err_ep_alloc;
-
-	ep->qp_info.qp = kzalloc(sizeof(*ep->qp_info.qp), GFP_KERNEL);
-	if (!ep->qp_info.qp)
-		goto err_qp_alloc;
-
-	err = scif_anon_inode_getfile(ep);
-	if (err)
-		goto err_anon_inode;
-
-	spin_lock_init(&ep->lock);
-	mutex_init(&ep->sendlock);
-	mutex_init(&ep->recvlock);
-
-	scif_rma_ep_init(ep);
-	ep->state = SCIFEP_UNBOUND;
-	dev_dbg(scif_info.mdev.this_device,
-		"SCIFAPI open: ep %p success\n", ep);
-	return ep;
-
-err_anon_inode:
-	kfree(ep->qp_info.qp);
-err_qp_alloc:
-	kfree(ep);
-err_ep_alloc:
-	return NULL;
-}
-EXPORT_SYMBOL_GPL(scif_open);
-
-/*
- * scif_disconnect_ep - Disconnects the endpoint if found
- * @epd: The end point returned from scif_open()
- */
-static struct scif_endpt *scif_disconnect_ep(struct scif_endpt *ep)
-{
-	struct scifmsg msg;
-	struct scif_endpt *fep = NULL;
-	struct scif_endpt *tmpep;
-	struct list_head *pos, *tmpq;
-	int err;
-
-	/*
-	 * Wake up any threads blocked in send()/recv() before closing
-	 * out the connection. Grabbing and releasing the send/recv lock
-	 * will ensure that any blocked senders/receivers have exited for
-	 * Ring 0 endpoints. It is a Ring 0 bug to call send/recv after
-	 * close. Ring 3 endpoints are not affected since close will not
-	 * be called while there are IOCTLs executing.
-	 */
-	wake_up_interruptible(&ep->sendwq);
-	wake_up_interruptible(&ep->recvwq);
-	mutex_lock(&ep->sendlock);
-	mutex_unlock(&ep->sendlock);
-	mutex_lock(&ep->recvlock);
-	mutex_unlock(&ep->recvlock);
-
-	/* Remove from the connected list */
-	mutex_lock(&scif_info.connlock);
-	list_for_each_safe(pos, tmpq, &scif_info.connected) {
-		tmpep = list_entry(pos, struct scif_endpt, list);
-		if (tmpep == ep) {
-			list_del(pos);
-			fep = tmpep;
-			spin_lock(&ep->lock);
-			break;
-		}
-	}
-
-	if (!fep) {
-		/*
-		 * The other side has completed the disconnect before
-		 * the end point can be removed from the list. Therefore
-		 * the ep lock is not locked, traverse the disconnected
-		 * list to find the endpoint and release the conn lock.
-		 */
-		list_for_each_safe(pos, tmpq, &scif_info.disconnected) {
-			tmpep = list_entry(pos, struct scif_endpt, list);
-			if (tmpep == ep) {
-				list_del(pos);
-				break;
-			}
-		}
-		mutex_unlock(&scif_info.connlock);
-		return NULL;
-	}
-
-	init_completion(&ep->discon);
-	msg.uop = SCIF_DISCNCT;
-	msg.src = ep->port;
-	msg.dst = ep->peer;
-	msg.payload[0] = (u64)ep;
-	msg.payload[1] = ep->remote_ep;
-
-	err = scif_nodeqp_send(ep->remote_dev, &msg);
-	spin_unlock(&ep->lock);
-	mutex_unlock(&scif_info.connlock);
-
-	if (!err)
-		/* Wait for the remote node to respond with SCIF_DISCNT_ACK */
-		wait_for_completion_timeout(&ep->discon,
-					    SCIF_NODE_ALIVE_TIMEOUT);
-	return ep;
-}
-
-int scif_close(scif_epd_t epd)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)epd;
-	struct scif_endpt *tmpep;
-	struct list_head *pos, *tmpq;
-	enum scif_epd_state oldstate;
-	bool flush_conn;
-
-	dev_dbg(scif_info.mdev.this_device, "SCIFAPI close: ep %p %s\n",
-		ep, scif_ep_states[ep->state]);
-	might_sleep();
-	spin_lock(&ep->lock);
-	flush_conn = (ep->conn_async_state == ASYNC_CONN_INPROGRESS);
-	spin_unlock(&ep->lock);
-
-	if (flush_conn)
-		flush_work(&scif_info.conn_work);
-
-	spin_lock(&ep->lock);
-	oldstate = ep->state;
-
-	ep->state = SCIFEP_CLOSING;
-
-	switch (oldstate) {
-	case SCIFEP_ZOMBIE:
-		dev_err(scif_info.mdev.this_device,
-			"SCIFAPI close: zombie state unexpected\n");
-		fallthrough;
-	case SCIFEP_DISCONNECTED:
-		spin_unlock(&ep->lock);
-		scif_unregister_all_windows(epd);
-		/* Remove from the disconnected list */
-		mutex_lock(&scif_info.connlock);
-		list_for_each_safe(pos, tmpq, &scif_info.disconnected) {
-			tmpep = list_entry(pos, struct scif_endpt, list);
-			if (tmpep == ep) {
-				list_del(pos);
-				break;
-			}
-		}
-		mutex_unlock(&scif_info.connlock);
-		break;
-	case SCIFEP_UNBOUND:
-	case SCIFEP_BOUND:
-	case SCIFEP_CONNECTING:
-		spin_unlock(&ep->lock);
-		break;
-	case SCIFEP_MAPPING:
-	case SCIFEP_CONNECTED:
-	case SCIFEP_CLOSING:
-	{
-		spin_unlock(&ep->lock);
-		scif_unregister_all_windows(epd);
-		scif_disconnect_ep(ep);
-		break;
-	}
-	case SCIFEP_LISTENING:
-	case SCIFEP_CLLISTEN:
-	{
-		struct scif_conreq *conreq;
-		struct scifmsg msg;
-		struct scif_endpt *aep;
-
-		spin_unlock(&ep->lock);
-		mutex_lock(&scif_info.eplock);
-
-		/* remove from listen list */
-		list_for_each_safe(pos, tmpq, &scif_info.listen) {
-			tmpep = list_entry(pos, struct scif_endpt, list);
-			if (tmpep == ep)
-				list_del(pos);
-		}
-		/* Remove any dangling accepts */
-		while (ep->acceptcnt) {
-			aep = list_first_entry(&ep->li_accept,
-					       struct scif_endpt, liacceptlist);
-			list_del(&aep->liacceptlist);
-			scif_put_port(aep->port.port);
-			list_for_each_safe(pos, tmpq, &scif_info.uaccept) {
-				tmpep = list_entry(pos, struct scif_endpt,
-						   miacceptlist);
-				if (tmpep == aep) {
-					list_del(pos);
-					break;
-				}
-			}
-			mutex_unlock(&scif_info.eplock);
-			mutex_lock(&scif_info.connlock);
-			list_for_each_safe(pos, tmpq, &scif_info.connected) {
-				tmpep = list_entry(pos,
-						   struct scif_endpt, list);
-				if (tmpep == aep) {
-					list_del(pos);
-					break;
-				}
-			}
-			list_for_each_safe(pos, tmpq, &scif_info.disconnected) {
-				tmpep = list_entry(pos,
-						   struct scif_endpt, list);
-				if (tmpep == aep) {
-					list_del(pos);
-					break;
-				}
-			}
-			mutex_unlock(&scif_info.connlock);
-			scif_teardown_ep(aep);
-			mutex_lock(&scif_info.eplock);
-			scif_add_epd_to_zombie_list(aep, SCIF_EPLOCK_HELD);
-			ep->acceptcnt--;
-		}
-
-		spin_lock(&ep->lock);
-		mutex_unlock(&scif_info.eplock);
-
-		/* Remove and reject any pending connection requests. */
-		while (ep->conreqcnt) {
-			conreq = list_first_entry(&ep->conlist,
-						  struct scif_conreq, list);
-			list_del(&conreq->list);
-
-			msg.uop = SCIF_CNCT_REJ;
-			msg.dst.node = conreq->msg.src.node;
-			msg.dst.port = conreq->msg.src.port;
-			msg.payload[0] = conreq->msg.payload[0];
-			msg.payload[1] = conreq->msg.payload[1];
-			/*
-			 * No Error Handling on purpose for scif_nodeqp_send().
-			 * If the remote node is lost we still want free the
-			 * connection requests on the self node.
-			 */
-			scif_nodeqp_send(&scif_dev[conreq->msg.src.node],
-					 &msg);
-			ep->conreqcnt--;
-			kfree(conreq);
-		}
-
-		spin_unlock(&ep->lock);
-		/* If a kSCIF accept is waiting wake it up */
-		wake_up_interruptible(&ep->conwq);
-		break;
-	}
-	}
-	scif_put_port(ep->port.port);
-	scif_anon_inode_fput(ep);
-	scif_teardown_ep(ep);
-	scif_add_epd_to_zombie_list(ep, !SCIF_EPLOCK_HELD);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(scif_close);
-
-/**
- * scif_flush() - Wakes up any blocking accepts. The endpoint will no longer
- *			accept new connections.
- * @epd: The end point returned from scif_open()
- */
-int __scif_flush(scif_epd_t epd)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)epd;
-
-	switch (ep->state) {
-	case SCIFEP_LISTENING:
-	{
-		ep->state = SCIFEP_CLLISTEN;
-
-		/* If an accept is waiting wake it up */
-		wake_up_interruptible(&ep->conwq);
-		break;
-	}
-	default:
-		break;
-	}
-	return 0;
-}
-
-int scif_bind(scif_epd_t epd, u16 pn)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)epd;
-	int ret = 0;
-	int tmp;
-
-	dev_dbg(scif_info.mdev.this_device,
-		"SCIFAPI bind: ep %p %s requested port number %d\n",
-		ep, scif_ep_states[ep->state], pn);
-	if (pn) {
-		/*
-		 * Similar to IETF RFC 1700, SCIF ports below
-		 * SCIF_ADMIN_PORT_END can only be bound by system (or root)
-		 * processes or by processes executed by privileged users.
-		 */
-		if (pn < SCIF_ADMIN_PORT_END && !capable(CAP_SYS_ADMIN)) {
-			ret = -EACCES;
-			goto scif_bind_admin_exit;
-		}
-	}
-
-	spin_lock(&ep->lock);
-	if (ep->state == SCIFEP_BOUND) {
-		ret = -EINVAL;
-		goto scif_bind_exit;
-	} else if (ep->state != SCIFEP_UNBOUND) {
-		ret = -EISCONN;
-		goto scif_bind_exit;
-	}
-
-	if (pn) {
-		tmp = scif_rsrv_port(pn);
-		if (tmp != pn) {
-			ret = -EINVAL;
-			goto scif_bind_exit;
-		}
-	} else {
-		ret = scif_get_new_port();
-		if (ret < 0)
-			goto scif_bind_exit;
-		pn = ret;
-	}
-
-	ep->state = SCIFEP_BOUND;
-	ep->port.node = scif_info.nodeid;
-	ep->port.port = pn;
-	ep->conn_async_state = ASYNC_CONN_IDLE;
-	ret = pn;
-	dev_dbg(scif_info.mdev.this_device,
-		"SCIFAPI bind: bound to port number %d\n", pn);
-scif_bind_exit:
-	spin_unlock(&ep->lock);
-scif_bind_admin_exit:
-	return ret;
-}
-EXPORT_SYMBOL_GPL(scif_bind);
-
-int scif_listen(scif_epd_t epd, int backlog)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)epd;
-
-	dev_dbg(scif_info.mdev.this_device,
-		"SCIFAPI listen: ep %p %s\n", ep, scif_ep_states[ep->state]);
-	spin_lock(&ep->lock);
-	switch (ep->state) {
-	case SCIFEP_ZOMBIE:
-	case SCIFEP_CLOSING:
-	case SCIFEP_CLLISTEN:
-	case SCIFEP_UNBOUND:
-	case SCIFEP_DISCONNECTED:
-		spin_unlock(&ep->lock);
-		return -EINVAL;
-	case SCIFEP_LISTENING:
-	case SCIFEP_CONNECTED:
-	case SCIFEP_CONNECTING:
-	case SCIFEP_MAPPING:
-		spin_unlock(&ep->lock);
-		return -EISCONN;
-	case SCIFEP_BOUND:
-		break;
-	}
-
-	ep->state = SCIFEP_LISTENING;
-	ep->backlog = backlog;
-
-	ep->conreqcnt = 0;
-	ep->acceptcnt = 0;
-	INIT_LIST_HEAD(&ep->conlist);
-	init_waitqueue_head(&ep->conwq);
-	INIT_LIST_HEAD(&ep->li_accept);
-	spin_unlock(&ep->lock);
-
-	/*
-	 * Listen status is complete so delete the qp information not needed
-	 * on a listen before placing on the list of listening ep's
-	 */
-	scif_teardown_ep(ep);
-	ep->qp_info.qp = NULL;
-
-	mutex_lock(&scif_info.eplock);
-	list_add_tail(&ep->list, &scif_info.listen);
-	mutex_unlock(&scif_info.eplock);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(scif_listen);
-
-/*
- ************************************************************************
- * SCIF connection flow:
- *
- * 1) A SCIF listening endpoint can call scif_accept(..) to wait for SCIF
- *	connections via a SCIF_CNCT_REQ message
- * 2) A SCIF endpoint can initiate a SCIF connection by calling
- *	scif_connect(..) which calls scif_setup_qp_connect(..) which
- *	allocates the local qp for the endpoint ring buffer and then sends
- *	a SCIF_CNCT_REQ to the remote node and waits for a SCIF_CNCT_GNT or
- *	a SCIF_CNCT_REJ message
- * 3) The peer node handles a SCIF_CNCT_REQ via scif_cnctreq_resp(..) which
- *	wakes up any threads blocked in step 1 or sends a SCIF_CNCT_REJ
- *	message otherwise
- * 4) A thread blocked waiting for incoming connections allocates its local
- *	endpoint QP and ring buffer following which it sends a SCIF_CNCT_GNT
- *	and waits for a SCIF_CNCT_GNT(N)ACK. If the allocation fails then
- *	the node sends a SCIF_CNCT_REJ message
- * 5) Upon receipt of a SCIF_CNCT_GNT or a SCIF_CNCT_REJ message the
- *	connecting endpoint is woken up as part of handling
- *	scif_cnctgnt_resp(..) following which it maps the remote endpoints'
- *	QP, updates its outbound QP and sends a SCIF_CNCT_GNTACK message on
- *	success or a SCIF_CNCT_GNTNACK message on failure and completes
- *	the scif_connect(..) API
- * 6) Upon receipt of a SCIF_CNCT_GNT(N)ACK the accepting endpoint blocked
- *	in step 4 is woken up and completes the scif_accept(..) API
- * 7) The SCIF connection is now established between the two SCIF endpoints.
- */
-static int scif_conn_func(struct scif_endpt *ep)
-{
-	int err = 0;
-	struct scifmsg msg;
-	struct device *spdev;
-
-	err = scif_reserve_dma_chan(ep);
-	if (err) {
-		dev_err(&ep->remote_dev->sdev->dev,
-			"%s %d err %d\n", __func__, __LINE__, err);
-		ep->state = SCIFEP_BOUND;
-		goto connect_error_simple;
-	}
-	/* Initiate the first part of the endpoint QP setup */
-	err = scif_setup_qp_connect(ep->qp_info.qp, &ep->qp_info.qp_offset,
-				    SCIF_ENDPT_QP_SIZE, ep->remote_dev);
-	if (err) {
-		dev_err(&ep->remote_dev->sdev->dev,
-			"%s err %d qp_offset 0x%llx\n",
-			__func__, err, ep->qp_info.qp_offset);
-		ep->state = SCIFEP_BOUND;
-		goto connect_error_simple;
-	}
-
-	spdev = scif_get_peer_dev(ep->remote_dev);
-	if (IS_ERR(spdev)) {
-		err = PTR_ERR(spdev);
-		goto cleanup_qp;
-	}
-	/* Format connect message and send it */
-	msg.src = ep->port;
-	msg.dst = ep->conn_port;
-	msg.uop = SCIF_CNCT_REQ;
-	msg.payload[0] = (u64)ep;
-	msg.payload[1] = ep->qp_info.qp_offset;
-	err = _scif_nodeqp_send(ep->remote_dev, &msg);
-	if (err)
-		goto connect_error_dec;
-	scif_put_peer_dev(spdev);
-	/*
-	 * Wait for the remote node to respond with SCIF_CNCT_GNT or
-	 * SCIF_CNCT_REJ message.
-	 */
-	err = wait_event_timeout(ep->conwq, ep->state != SCIFEP_CONNECTING,
-				 SCIF_NODE_ALIVE_TIMEOUT);
-	if (!err) {
-		dev_err(&ep->remote_dev->sdev->dev,
-			"%s %d timeout\n", __func__, __LINE__);
-		ep->state = SCIFEP_BOUND;
-	}
-	spdev = scif_get_peer_dev(ep->remote_dev);
-	if (IS_ERR(spdev)) {
-		err = PTR_ERR(spdev);
-		goto cleanup_qp;
-	}
-	if (ep->state == SCIFEP_MAPPING) {
-		err = scif_setup_qp_connect_response(ep->remote_dev,
-						     ep->qp_info.qp,
-						     ep->qp_info.gnt_pld);
-		/*
-		 * If the resource to map the queue are not available then
-		 * we need to tell the other side to terminate the accept
-		 */
-		if (err) {
-			dev_err(&ep->remote_dev->sdev->dev,
-				"%s %d err %d\n", __func__, __LINE__, err);
-			msg.uop = SCIF_CNCT_GNTNACK;
-			msg.payload[0] = ep->remote_ep;
-			_scif_nodeqp_send(ep->remote_dev, &msg);
-			ep->state = SCIFEP_BOUND;
-			goto connect_error_dec;
-		}
-
-		msg.uop = SCIF_CNCT_GNTACK;
-		msg.payload[0] = ep->remote_ep;
-		err = _scif_nodeqp_send(ep->remote_dev, &msg);
-		if (err) {
-			ep->state = SCIFEP_BOUND;
-			goto connect_error_dec;
-		}
-		ep->state = SCIFEP_CONNECTED;
-		mutex_lock(&scif_info.connlock);
-		list_add_tail(&ep->list, &scif_info.connected);
-		mutex_unlock(&scif_info.connlock);
-		dev_dbg(&ep->remote_dev->sdev->dev,
-			"SCIFAPI connect: ep %p connected\n", ep);
-	} else if (ep->state == SCIFEP_BOUND) {
-		dev_dbg(&ep->remote_dev->sdev->dev,
-			"SCIFAPI connect: ep %p connection refused\n", ep);
-		err = -ECONNREFUSED;
-		goto connect_error_dec;
-	}
-	scif_put_peer_dev(spdev);
-	return err;
-connect_error_dec:
-	scif_put_peer_dev(spdev);
-cleanup_qp:
-	scif_cleanup_ep_qp(ep);
-connect_error_simple:
-	return err;
-}
-
-/*
- * scif_conn_handler:
- *
- * Workqueue handler for servicing non-blocking SCIF connect
- *
- */
-void scif_conn_handler(struct work_struct *work)
-{
-	struct scif_endpt *ep;
-
-	do {
-		ep = NULL;
-		spin_lock(&scif_info.nb_connect_lock);
-		if (!list_empty(&scif_info.nb_connect_list)) {
-			ep = list_first_entry(&scif_info.nb_connect_list,
-					      struct scif_endpt, conn_list);
-			list_del(&ep->conn_list);
-		}
-		spin_unlock(&scif_info.nb_connect_lock);
-		if (ep) {
-			ep->conn_err = scif_conn_func(ep);
-			wake_up_interruptible(&ep->conn_pend_wq);
-		}
-	} while (ep);
-}
-
-int __scif_connect(scif_epd_t epd, struct scif_port_id *dst, bool non_block)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)epd;
-	int err = 0;
-	struct scif_dev *remote_dev;
-	struct device *spdev;
-
-	dev_dbg(scif_info.mdev.this_device, "SCIFAPI connect: ep %p %s\n", ep,
-		scif_ep_states[ep->state]);
-
-	if (!scif_dev || dst->node > scif_info.maxid)
-		return -ENODEV;
-
-	might_sleep();
-
-	remote_dev = &scif_dev[dst->node];
-	spdev = scif_get_peer_dev(remote_dev);
-	if (IS_ERR(spdev)) {
-		err = PTR_ERR(spdev);
-		return err;
-	}
-
-	spin_lock(&ep->lock);
-	switch (ep->state) {
-	case SCIFEP_ZOMBIE:
-	case SCIFEP_CLOSING:
-		err = -EINVAL;
-		break;
-	case SCIFEP_DISCONNECTED:
-		if (ep->conn_async_state == ASYNC_CONN_INPROGRESS)
-			ep->conn_async_state = ASYNC_CONN_FLUSH_WORK;
-		else
-			err = -EINVAL;
-		break;
-	case SCIFEP_LISTENING:
-	case SCIFEP_CLLISTEN:
-		err = -EOPNOTSUPP;
-		break;
-	case SCIFEP_CONNECTING:
-	case SCIFEP_MAPPING:
-		if (ep->conn_async_state == ASYNC_CONN_INPROGRESS)
-			err = -EINPROGRESS;
-		else
-			err = -EISCONN;
-		break;
-	case SCIFEP_CONNECTED:
-		if (ep->conn_async_state == ASYNC_CONN_INPROGRESS)
-			ep->conn_async_state = ASYNC_CONN_FLUSH_WORK;
-		else
-			err = -EISCONN;
-		break;
-	case SCIFEP_UNBOUND:
-		err = scif_get_new_port();
-		if (err < 0)
-			break;
-		ep->port.port = err;
-		ep->port.node = scif_info.nodeid;
-		ep->conn_async_state = ASYNC_CONN_IDLE;
-		fallthrough;
-	case SCIFEP_BOUND:
-		/*
-		 * If a non-blocking connect has been already initiated
-		 * (conn_async_state is either ASYNC_CONN_INPROGRESS or
-		 * ASYNC_CONN_FLUSH_WORK), the end point could end up in
-		 * SCIF_BOUND due an error in the connection process
-		 * (e.g., connection refused) If conn_async_state is
-		 * ASYNC_CONN_INPROGRESS - transition to ASYNC_CONN_FLUSH_WORK
-		 * so that the error status can be collected. If the state is
-		 * already ASYNC_CONN_FLUSH_WORK - then set the error to
-		 * EINPROGRESS since some other thread is waiting to collect
-		 * error status.
-		 */
-		if (ep->conn_async_state == ASYNC_CONN_INPROGRESS) {
-			ep->conn_async_state = ASYNC_CONN_FLUSH_WORK;
-		} else if (ep->conn_async_state == ASYNC_CONN_FLUSH_WORK) {
-			err = -EINPROGRESS;
-		} else {
-			ep->conn_port = *dst;
-			init_waitqueue_head(&ep->sendwq);
-			init_waitqueue_head(&ep->recvwq);
-			init_waitqueue_head(&ep->conwq);
-			ep->conn_async_state = 0;
-
-			if (unlikely(non_block))
-				ep->conn_async_state = ASYNC_CONN_INPROGRESS;
-		}
-		break;
-	}
-
-	if (err || ep->conn_async_state == ASYNC_CONN_FLUSH_WORK)
-			goto connect_simple_unlock1;
-
-	ep->state = SCIFEP_CONNECTING;
-	ep->remote_dev = &scif_dev[dst->node];
-	ep->qp_info.qp->magic = SCIFEP_MAGIC;
-	if (ep->conn_async_state == ASYNC_CONN_INPROGRESS) {
-		init_waitqueue_head(&ep->conn_pend_wq);
-		spin_lock(&scif_info.nb_connect_lock);
-		list_add_tail(&ep->conn_list, &scif_info.nb_connect_list);
-		spin_unlock(&scif_info.nb_connect_lock);
-		err = -EINPROGRESS;
-		schedule_work(&scif_info.conn_work);
-	}
-connect_simple_unlock1:
-	spin_unlock(&ep->lock);
-	scif_put_peer_dev(spdev);
-	if (err) {
-		return err;
-	} else if (ep->conn_async_state == ASYNC_CONN_FLUSH_WORK) {
-		flush_work(&scif_info.conn_work);
-		err = ep->conn_err;
-		spin_lock(&ep->lock);
-		ep->conn_async_state = ASYNC_CONN_IDLE;
-		spin_unlock(&ep->lock);
-	} else {
-		err = scif_conn_func(ep);
-	}
-	return err;
-}
-
-int scif_connect(scif_epd_t epd, struct scif_port_id *dst)
-{
-	return __scif_connect(epd, dst, false);
-}
-EXPORT_SYMBOL_GPL(scif_connect);
-
-/*
- * scif_accept() - Accept a connection request from the remote node
- *
- * The function accepts a connection request from the remote node.  Successful
- * complete is indicate by a new end point being created and passed back
- * to the caller for future reference.
- *
- * Upon successful complete a zero will be returned and the peer information
- * will be filled in.
- *
- * If the end point is not in the listening state -EINVAL will be returned.
- *
- * If during the connection sequence resource allocation fails the -ENOMEM
- * will be returned.
- *
- * If the function is called with the ASYNC flag set and no connection requests
- * are pending it will return -EAGAIN.
- *
- * If the remote side is not sending any connection requests the caller may
- * terminate this function with a signal.  If so a -EINTR will be returned.
- */
-int scif_accept(scif_epd_t epd, struct scif_port_id *peer,
-		scif_epd_t *newepd, int flags)
-{
-	struct scif_endpt *lep = (struct scif_endpt *)epd;
-	struct scif_endpt *cep;
-	struct scif_conreq *conreq;
-	struct scifmsg msg;
-	int err;
-	struct device *spdev;
-
-	dev_dbg(scif_info.mdev.this_device,
-		"SCIFAPI accept: ep %p %s\n", lep, scif_ep_states[lep->state]);
-
-	if (flags & ~SCIF_ACCEPT_SYNC)
-		return -EINVAL;
-
-	if (!peer || !newepd)
-		return -EINVAL;
-
-	might_sleep();
-	spin_lock(&lep->lock);
-	if (lep->state != SCIFEP_LISTENING) {
-		spin_unlock(&lep->lock);
-		return -EINVAL;
-	}
-
-	if (!lep->conreqcnt && !(flags & SCIF_ACCEPT_SYNC)) {
-		/* No connection request present and we do not want to wait */
-		spin_unlock(&lep->lock);
-		return -EAGAIN;
-	}
-
-	lep->files = current->files;
-retry_connection:
-	spin_unlock(&lep->lock);
-	/* Wait for the remote node to send us a SCIF_CNCT_REQ */
-	err = wait_event_interruptible(lep->conwq,
-				       (lep->conreqcnt ||
-				       (lep->state != SCIFEP_LISTENING)));
-	if (err)
-		return err;
-
-	if (lep->state != SCIFEP_LISTENING)
-		return -EINTR;
-
-	spin_lock(&lep->lock);
-
-	if (!lep->conreqcnt)
-		goto retry_connection;
-
-	/* Get the first connect request off the list */
-	conreq = list_first_entry(&lep->conlist, struct scif_conreq, list);
-	list_del(&conreq->list);
-	lep->conreqcnt--;
-	spin_unlock(&lep->lock);
-
-	/* Fill in the peer information */
-	peer->node = conreq->msg.src.node;
-	peer->port = conreq->msg.src.port;
-
-	cep = kzalloc(sizeof(*cep), GFP_KERNEL);
-	if (!cep) {
-		err = -ENOMEM;
-		goto scif_accept_error_epalloc;
-	}
-	spin_lock_init(&cep->lock);
-	mutex_init(&cep->sendlock);
-	mutex_init(&cep->recvlock);
-	cep->state = SCIFEP_CONNECTING;
-	cep->remote_dev = &scif_dev[peer->node];
-	cep->remote_ep = conreq->msg.payload[0];
-
-	scif_rma_ep_init(cep);
-
-	err = scif_reserve_dma_chan(cep);
-	if (err) {
-		dev_err(scif_info.mdev.this_device,
-			"%s %d err %d\n", __func__, __LINE__, err);
-		goto scif_accept_error_qpalloc;
-	}
-
-	cep->qp_info.qp = kzalloc(sizeof(*cep->qp_info.qp), GFP_KERNEL);
-	if (!cep->qp_info.qp) {
-		err = -ENOMEM;
-		goto scif_accept_error_qpalloc;
-	}
-
-	err = scif_anon_inode_getfile(cep);
-	if (err)
-		goto scif_accept_error_anon_inode;
-
-	cep->qp_info.qp->magic = SCIFEP_MAGIC;
-	spdev = scif_get_peer_dev(cep->remote_dev);
-	if (IS_ERR(spdev)) {
-		err = PTR_ERR(spdev);
-		goto scif_accept_error_map;
-	}
-	err = scif_setup_qp_accept(cep->qp_info.qp, &cep->qp_info.qp_offset,
-				   conreq->msg.payload[1], SCIF_ENDPT_QP_SIZE,
-				   cep->remote_dev);
-	if (err) {
-		dev_dbg(&cep->remote_dev->sdev->dev,
-			"SCIFAPI accept: ep %p new %p scif_setup_qp_accept %d qp_offset 0x%llx\n",
-			lep, cep, err, cep->qp_info.qp_offset);
-		scif_put_peer_dev(spdev);
-		goto scif_accept_error_map;
-	}
-
-	cep->port.node = lep->port.node;
-	cep->port.port = lep->port.port;
-	cep->peer.node = peer->node;
-	cep->peer.port = peer->port;
-	init_waitqueue_head(&cep->sendwq);
-	init_waitqueue_head(&cep->recvwq);
-	init_waitqueue_head(&cep->conwq);
-
-	msg.uop = SCIF_CNCT_GNT;
-	msg.src = cep->port;
-	msg.payload[0] = cep->remote_ep;
-	msg.payload[1] = cep->qp_info.qp_offset;
-	msg.payload[2] = (u64)cep;
-
-	err = _scif_nodeqp_send(cep->remote_dev, &msg);
-	scif_put_peer_dev(spdev);
-	if (err)
-		goto scif_accept_error_map;
-retry:
-	/* Wait for the remote node to respond with SCIF_CNCT_GNT(N)ACK */
-	err = wait_event_timeout(cep->conwq, cep->state != SCIFEP_CONNECTING,
-				 SCIF_NODE_ACCEPT_TIMEOUT);
-	if (!err && scifdev_alive(cep))
-		goto retry;
-	err = !err ? -ENODEV : 0;
-	if (err)
-		goto scif_accept_error_map;
-	kfree(conreq);
-
-	spin_lock(&cep->lock);
-
-	if (cep->state == SCIFEP_CLOSING) {
-		/*
-		 * Remote failed to allocate resources and NAKed the grant.
-		 * There is at this point nothing referencing the new end point.
-		 */
-		spin_unlock(&cep->lock);
-		scif_teardown_ep(cep);
-		kfree(cep);
-
-		/* If call with sync flag then go back and wait. */
-		if (flags & SCIF_ACCEPT_SYNC) {
-			spin_lock(&lep->lock);
-			goto retry_connection;
-		}
-		return -EAGAIN;
-	}
-
-	scif_get_port(cep->port.port);
-	*newepd = (scif_epd_t)cep;
-	spin_unlock(&cep->lock);
-	return 0;
-scif_accept_error_map:
-	scif_anon_inode_fput(cep);
-scif_accept_error_anon_inode:
-	scif_teardown_ep(cep);
-scif_accept_error_qpalloc:
-	kfree(cep);
-scif_accept_error_epalloc:
-	msg.uop = SCIF_CNCT_REJ;
-	msg.dst.node = conreq->msg.src.node;
-	msg.dst.port = conreq->msg.src.port;
-	msg.payload[0] = conreq->msg.payload[0];
-	msg.payload[1] = conreq->msg.payload[1];
-	scif_nodeqp_send(&scif_dev[conreq->msg.src.node], &msg);
-	kfree(conreq);
-	return err;
-}
-EXPORT_SYMBOL_GPL(scif_accept);
-
-/*
- * scif_msg_param_check:
- * @epd: The end point returned from scif_open()
- * @len: Length to receive
- * @flags: blocking or non blocking
- *
- * Validate parameters for messaging APIs scif_send(..)/scif_recv(..).
- */
-static inline int scif_msg_param_check(scif_epd_t epd, int len, int flags)
-{
-	int ret = -EINVAL;
-
-	if (len < 0)
-		goto err_ret;
-	if (flags && (!(flags & SCIF_RECV_BLOCK)))
-		goto err_ret;
-	ret = 0;
-err_ret:
-	return ret;
-}
-
-static int _scif_send(scif_epd_t epd, void *msg, int len, int flags)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)epd;
-	struct scifmsg notif_msg;
-	int curr_xfer_len = 0, sent_len = 0, write_count;
-	int ret = 0;
-	struct scif_qp *qp = ep->qp_info.qp;
-
-	if (flags & SCIF_SEND_BLOCK)
-		might_sleep();
-
-	spin_lock(&ep->lock);
-	while (sent_len != len && SCIFEP_CONNECTED == ep->state) {
-		write_count = scif_rb_space(&qp->outbound_q);
-		if (write_count) {
-			/* Best effort to send as much data as possible */
-			curr_xfer_len = min(len - sent_len, write_count);
-			ret = scif_rb_write(&qp->outbound_q, msg,
-					    curr_xfer_len);
-			if (ret < 0)
-				break;
-			/* Success. Update write pointer */
-			scif_rb_commit(&qp->outbound_q);
-			/*
-			 * Send a notification to the peer about the
-			 * produced data message.
-			 */
-			notif_msg.src = ep->port;
-			notif_msg.uop = SCIF_CLIENT_SENT;
-			notif_msg.payload[0] = ep->remote_ep;
-			ret = _scif_nodeqp_send(ep->remote_dev, &notif_msg);
-			if (ret)
-				break;
-			sent_len += curr_xfer_len;
-			msg = msg + curr_xfer_len;
-			continue;
-		}
-		curr_xfer_len = min(len - sent_len, SCIF_ENDPT_QP_SIZE - 1);
-		/* Not enough RB space. return for the Non Blocking case */
-		if (!(flags & SCIF_SEND_BLOCK))
-			break;
-
-		spin_unlock(&ep->lock);
-		/* Wait for a SCIF_CLIENT_RCVD message in the Blocking case */
-		ret =
-		wait_event_interruptible(ep->sendwq,
-					 (SCIFEP_CONNECTED != ep->state) ||
-					 (scif_rb_space(&qp->outbound_q) >=
-					 curr_xfer_len));
-		spin_lock(&ep->lock);
-		if (ret)
-			break;
-	}
-	if (sent_len)
-		ret = sent_len;
-	else if (!ret && SCIFEP_CONNECTED != ep->state)
-		ret = SCIFEP_DISCONNECTED == ep->state ?
-			-ECONNRESET : -ENOTCONN;
-	spin_unlock(&ep->lock);
-	return ret;
-}
-
-static int _scif_recv(scif_epd_t epd, void *msg, int len, int flags)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)epd;
-	struct scifmsg notif_msg;
-	int curr_recv_len = 0, remaining_len = len, read_count;
-	int ret = 0;
-	struct scif_qp *qp = ep->qp_info.qp;
-
-	if (flags & SCIF_RECV_BLOCK)
-		might_sleep();
-	spin_lock(&ep->lock);
-	while (remaining_len && (SCIFEP_CONNECTED == ep->state ||
-				 SCIFEP_DISCONNECTED == ep->state)) {
-		read_count = scif_rb_count(&qp->inbound_q, remaining_len);
-		if (read_count) {
-			/*
-			 * Best effort to recv as much data as there
-			 * are bytes to read in the RB particularly
-			 * important for the Non Blocking case.
-			 */
-			curr_recv_len = min(remaining_len, read_count);
-			scif_rb_get_next(&qp->inbound_q, msg, curr_recv_len);
-			if (ep->state == SCIFEP_CONNECTED) {
-				/*
-				 * Update the read pointer only if the endpoint
-				 * is still connected else the read pointer
-				 * might no longer exist since the peer has
-				 * freed resources!
-				 */
-				scif_rb_update_read_ptr(&qp->inbound_q);
-				/*
-				 * Send a notification to the peer about the
-				 * consumed data message only if the EP is in
-				 * SCIFEP_CONNECTED state.
-				 */
-				notif_msg.src = ep->port;
-				notif_msg.uop = SCIF_CLIENT_RCVD;
-				notif_msg.payload[0] = ep->remote_ep;
-				ret = _scif_nodeqp_send(ep->remote_dev,
-							&notif_msg);
-				if (ret)
-					break;
-			}
-			remaining_len -= curr_recv_len;
-			msg = msg + curr_recv_len;
-			continue;
-		}
-		/*
-		 * Bail out now if the EP is in SCIFEP_DISCONNECTED state else
-		 * we will keep looping forever.
-		 */
-		if (ep->state == SCIFEP_DISCONNECTED)
-			break;
-		/*
-		 * Return in the Non Blocking case if there is no data
-		 * to read in this iteration.
-		 */
-		if (!(flags & SCIF_RECV_BLOCK))
-			break;
-		curr_recv_len = min(remaining_len, SCIF_ENDPT_QP_SIZE - 1);
-		spin_unlock(&ep->lock);
-		/*
-		 * Wait for a SCIF_CLIENT_SEND message in the blocking case
-		 * or until other side disconnects.
-		 */
-		ret =
-		wait_event_interruptible(ep->recvwq,
-					 SCIFEP_CONNECTED != ep->state ||
-					 scif_rb_count(&qp->inbound_q,
-						       curr_recv_len)
-					 >= curr_recv_len);
-		spin_lock(&ep->lock);
-		if (ret)
-			break;
-	}
-	if (len - remaining_len)
-		ret = len - remaining_len;
-	else if (!ret && ep->state != SCIFEP_CONNECTED)
-		ret = ep->state == SCIFEP_DISCONNECTED ?
-			-ECONNRESET : -ENOTCONN;
-	spin_unlock(&ep->lock);
-	return ret;
-}
-
-/**
- * scif_user_send() - Send data to connection queue
- * @epd: The end point returned from scif_open()
- * @msg: Address to place data
- * @len: Length to receive
- * @flags: blocking or non blocking
- *
- * This function is called from the driver IOCTL entry point
- * only and is a wrapper for _scif_send().
- */
-int scif_user_send(scif_epd_t epd, void __user *msg, int len, int flags)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)epd;
-	int err = 0;
-	int sent_len = 0;
-	char *tmp;
-	int loop_len;
-	int chunk_len = min(len, (1 << (MAX_ORDER + PAGE_SHIFT - 1)));
-
-	dev_dbg(scif_info.mdev.this_device,
-		"SCIFAPI send (U): ep %p %s\n", ep, scif_ep_states[ep->state]);
-	if (!len)
-		return 0;
-
-	err = scif_msg_param_check(epd, len, flags);
-	if (err)
-		goto send_err;
-
-	tmp = kmalloc(chunk_len, GFP_KERNEL);
-	if (!tmp) {
-		err = -ENOMEM;
-		goto send_err;
-	}
-	/*
-	 * Grabbing the lock before breaking up the transfer in
-	 * multiple chunks is required to ensure that messages do
-	 * not get fragmented and reordered.
-	 */
-	mutex_lock(&ep->sendlock);
-	while (sent_len != len) {
-		loop_len = len - sent_len;
-		loop_len = min(chunk_len, loop_len);
-		if (copy_from_user(tmp, msg, loop_len)) {
-			err = -EFAULT;
-			goto send_free_err;
-		}
-		err = _scif_send(epd, tmp, loop_len, flags);
-		if (err < 0)
-			goto send_free_err;
-		sent_len += err;
-		msg += err;
-		if (err != loop_len)
-			goto send_free_err;
-	}
-send_free_err:
-	mutex_unlock(&ep->sendlock);
-	kfree(tmp);
-send_err:
-	return err < 0 ? err : sent_len;
-}
-
-/**
- * scif_user_recv() - Receive data from connection queue
- * @epd: The end point returned from scif_open()
- * @msg: Address to place data
- * @len: Length to receive
- * @flags: blocking or non blocking
- *
- * This function is called from the driver IOCTL entry point
- * only and is a wrapper for _scif_recv().
- */
-int scif_user_recv(scif_epd_t epd, void __user *msg, int len, int flags)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)epd;
-	int err = 0;
-	int recv_len = 0;
-	char *tmp;
-	int loop_len;
-	int chunk_len = min(len, (1 << (MAX_ORDER + PAGE_SHIFT - 1)));
-
-	dev_dbg(scif_info.mdev.this_device,
-		"SCIFAPI recv (U): ep %p %s\n", ep, scif_ep_states[ep->state]);
-	if (!len)
-		return 0;
-
-	err = scif_msg_param_check(epd, len, flags);
-	if (err)
-		goto recv_err;
-
-	tmp = kmalloc(chunk_len, GFP_KERNEL);
-	if (!tmp) {
-		err = -ENOMEM;
-		goto recv_err;
-	}
-	/*
-	 * Grabbing the lock before breaking up the transfer in
-	 * multiple chunks is required to ensure that messages do
-	 * not get fragmented and reordered.
-	 */
-	mutex_lock(&ep->recvlock);
-	while (recv_len != len) {
-		loop_len = len - recv_len;
-		loop_len = min(chunk_len, loop_len);
-		err = _scif_recv(epd, tmp, loop_len, flags);
-		if (err < 0)
-			goto recv_free_err;
-		if (copy_to_user(msg, tmp, err)) {
-			err = -EFAULT;
-			goto recv_free_err;
-		}
-		recv_len += err;
-		msg += err;
-		if (err != loop_len)
-			goto recv_free_err;
-	}
-recv_free_err:
-	mutex_unlock(&ep->recvlock);
-	kfree(tmp);
-recv_err:
-	return err < 0 ? err : recv_len;
-}
-
-/**
- * scif_send() - Send data to connection queue
- * @epd: The end point returned from scif_open()
- * @msg: Address to place data
- * @len: Length to receive
- * @flags: blocking or non blocking
- *
- * This function is called from the kernel mode only and is
- * a wrapper for _scif_send().
- */
-int scif_send(scif_epd_t epd, void *msg, int len, int flags)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)epd;
-	int ret;
-
-	dev_dbg(scif_info.mdev.this_device,
-		"SCIFAPI send (K): ep %p %s\n", ep, scif_ep_states[ep->state]);
-	if (!len)
-		return 0;
-
-	ret = scif_msg_param_check(epd, len, flags);
-	if (ret)
-		return ret;
-	if (!ep->remote_dev)
-		return -ENOTCONN;
-	/*
-	 * Grab the mutex lock in the blocking case only
-	 * to ensure messages do not get fragmented/reordered.
-	 * The non blocking mode is protected using spin locks
-	 * in _scif_send().
-	 */
-	if (flags & SCIF_SEND_BLOCK)
-		mutex_lock(&ep->sendlock);
-
-	ret = _scif_send(epd, msg, len, flags);
-
-	if (flags & SCIF_SEND_BLOCK)
-		mutex_unlock(&ep->sendlock);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(scif_send);
-
-/**
- * scif_recv() - Receive data from connection queue
- * @epd: The end point returned from scif_open()
- * @msg: Address to place data
- * @len: Length to receive
- * @flags: blocking or non blocking
- *
- * This function is called from the kernel mode only and is
- * a wrapper for _scif_recv().
- */
-int scif_recv(scif_epd_t epd, void *msg, int len, int flags)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)epd;
-	int ret;
-
-	dev_dbg(scif_info.mdev.this_device,
-		"SCIFAPI recv (K): ep %p %s\n", ep, scif_ep_states[ep->state]);
-	if (!len)
-		return 0;
-
-	ret = scif_msg_param_check(epd, len, flags);
-	if (ret)
-		return ret;
-	/*
-	 * Grab the mutex lock in the blocking case only
-	 * to ensure messages do not get fragmented/reordered.
-	 * The non blocking mode is protected using spin locks
-	 * in _scif_send().
-	 */
-	if (flags & SCIF_RECV_BLOCK)
-		mutex_lock(&ep->recvlock);
-
-	ret = _scif_recv(epd, msg, len, flags);
-
-	if (flags & SCIF_RECV_BLOCK)
-		mutex_unlock(&ep->recvlock);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(scif_recv);
-
-static inline void _scif_poll_wait(struct file *f, wait_queue_head_t *wq,
-				   poll_table *p, struct scif_endpt *ep)
-{
-	/*
-	 * Because poll_wait makes a GFP_KERNEL allocation, give up the lock
-	 * and regrab it afterwards. Because the endpoint state might have
-	 * changed while the lock was given up, the state must be checked
-	 * again after re-acquiring the lock. The code in __scif_pollfd(..)
-	 * does this.
-	 */
-	spin_unlock(&ep->lock);
-	poll_wait(f, wq, p);
-	spin_lock(&ep->lock);
-}
-
-__poll_t
-__scif_pollfd(struct file *f, poll_table *wait, struct scif_endpt *ep)
-{
-	__poll_t mask = 0;
-
-	dev_dbg(scif_info.mdev.this_device,
-		"SCIFAPI pollfd: ep %p %s\n", ep, scif_ep_states[ep->state]);
-
-	spin_lock(&ep->lock);
-
-	/* Endpoint is waiting for a non-blocking connect to complete */
-	if (ep->conn_async_state == ASYNC_CONN_INPROGRESS) {
-		_scif_poll_wait(f, &ep->conn_pend_wq, wait, ep);
-		if (ep->conn_async_state == ASYNC_CONN_INPROGRESS) {
-			if (ep->state == SCIFEP_CONNECTED ||
-			    ep->state == SCIFEP_DISCONNECTED ||
-			    ep->conn_err)
-				mask |= EPOLLOUT;
-			goto exit;
-		}
-	}
-
-	/* Endpoint is listening for incoming connection requests */
-	if (ep->state == SCIFEP_LISTENING) {
-		_scif_poll_wait(f, &ep->conwq, wait, ep);
-		if (ep->state == SCIFEP_LISTENING) {
-			if (ep->conreqcnt)
-				mask |= EPOLLIN;
-			goto exit;
-		}
-	}
-
-	/* Endpoint is connected or disconnected */
-	if (ep->state == SCIFEP_CONNECTED || ep->state == SCIFEP_DISCONNECTED) {
-		if (poll_requested_events(wait) & EPOLLIN)
-			_scif_poll_wait(f, &ep->recvwq, wait, ep);
-		if (poll_requested_events(wait) & EPOLLOUT)
-			_scif_poll_wait(f, &ep->sendwq, wait, ep);
-		if (ep->state == SCIFEP_CONNECTED ||
-		    ep->state == SCIFEP_DISCONNECTED) {
-			/* Data can be read without blocking */
-			if (scif_rb_count(&ep->qp_info.qp->inbound_q, 1))
-				mask |= EPOLLIN;
-			/* Data can be written without blocking */
-			if (scif_rb_space(&ep->qp_info.qp->outbound_q))
-				mask |= EPOLLOUT;
-			/* Return EPOLLHUP if endpoint is disconnected */
-			if (ep->state == SCIFEP_DISCONNECTED)
-				mask |= EPOLLHUP;
-			goto exit;
-		}
-	}
-
-	/* Return EPOLLERR if the endpoint is in none of the above states */
-	mask |= EPOLLERR;
-exit:
-	spin_unlock(&ep->lock);
-	return mask;
-}
-
-/**
- * scif_poll() - Kernel mode SCIF poll
- * @ufds: Array of scif_pollepd structures containing the end points
- *	  and events to poll on
- * @nfds: Size of the ufds array
- * @timeout_msecs: Timeout in msecs, -ve implies infinite timeout
- *
- * The code flow in this function is based on do_poll(..) in select.c
- *
- * Returns the number of endpoints which have pending events or 0 in
- * the event of a timeout. If a signal is used for wake up, -EINTR is
- * returned.
- */
-int
-scif_poll(struct scif_pollepd *ufds, unsigned int nfds, long timeout_msecs)
-{
-	struct poll_wqueues table;
-	poll_table *pt;
-	int i, count = 0, timed_out = timeout_msecs == 0;
-	__poll_t mask;
-	u64 timeout = timeout_msecs < 0 ? MAX_SCHEDULE_TIMEOUT
-		: msecs_to_jiffies(timeout_msecs);
-
-	poll_initwait(&table);
-	pt = &table.pt;
-	while (1) {
-		for (i = 0; i < nfds; i++) {
-			pt->_key = ufds[i].events | EPOLLERR | EPOLLHUP;
-			mask = __scif_pollfd(ufds[i].epd->anon,
-					     pt, ufds[i].epd);
-			mask &= ufds[i].events | EPOLLERR | EPOLLHUP;
-			if (mask) {
-				count++;
-				pt->_qproc = NULL;
-			}
-			ufds[i].revents = mask;
-		}
-		pt->_qproc = NULL;
-		if (!count) {
-			count = table.error;
-			if (signal_pending(current))
-				count = -EINTR;
-		}
-		if (count || timed_out)
-			break;
-
-		if (!schedule_timeout_interruptible(timeout))
-			timed_out = 1;
-	}
-	poll_freewait(&table);
-	return count;
-}
-EXPORT_SYMBOL_GPL(scif_poll);
-
-int scif_get_node_ids(u16 *nodes, int len, u16 *self)
-{
-	int online = 0;
-	int offset = 0;
-	int node;
-
-	if (!scif_is_mgmt_node())
-		scif_get_node_info();
-
-	*self = scif_info.nodeid;
-	mutex_lock(&scif_info.conflock);
-	len = min_t(int, len, scif_info.total);
-	for (node = 0; node <= scif_info.maxid; node++) {
-		if (_scifdev_alive(&scif_dev[node])) {
-			online++;
-			if (offset < len)
-				nodes[offset++] = node;
-		}
-	}
-	dev_dbg(scif_info.mdev.this_device,
-		"SCIFAPI get_node_ids total %d online %d filled in %d nodes\n",
-		scif_info.total, online, offset);
-	mutex_unlock(&scif_info.conflock);
-
-	return online;
-}
-EXPORT_SYMBOL_GPL(scif_get_node_ids);
-
-static int scif_add_client_dev(struct device *dev, struct subsys_interface *si)
-{
-	struct scif_client *client =
-		container_of(si, struct scif_client, si);
-	struct scif_peer_dev *spdev =
-		container_of(dev, struct scif_peer_dev, dev);
-
-	if (client->probe)
-		client->probe(spdev);
-	return 0;
-}
-
-static void scif_remove_client_dev(struct device *dev,
-				   struct subsys_interface *si)
-{
-	struct scif_client *client =
-		container_of(si, struct scif_client, si);
-	struct scif_peer_dev *spdev =
-		container_of(dev, struct scif_peer_dev, dev);
-
-	if (client->remove)
-		client->remove(spdev);
-}
-
-void scif_client_unregister(struct scif_client *client)
-{
-	subsys_interface_unregister(&client->si);
-}
-EXPORT_SYMBOL_GPL(scif_client_unregister);
-
-int scif_client_register(struct scif_client *client)
-{
-	struct subsys_interface *si = &client->si;
-
-	si->name = client->name;
-	si->subsys = &scif_peer_bus;
-	si->add_dev = scif_add_client_dev;
-	si->remove_dev = scif_remove_client_dev;
-
-	return subsys_interface_register(&client->si);
-}
-EXPORT_SYMBOL_GPL(scif_client_register);
diff --git a/drivers/misc/mic/scif/scif_debugfs.c b/drivers/misc/mic/scif/scif_debugfs.c
deleted file mode 100644
index 8fe38e7ca6e6..000000000000
--- a/drivers/misc/mic/scif/scif_debugfs.c
+++ /dev/null
@@ -1,116 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include <linux/debugfs.h>
-#include <linux/seq_file.h>
-
-#include "../common/mic_dev.h"
-#include "scif_main.h"
-
-/* Debugfs parent dir */
-static struct dentry *scif_dbg;
-
-static int scif_dev_show(struct seq_file *s, void *unused)
-{
-	int node;
-
-	seq_printf(s, "Total Nodes %d Self Node Id %d Maxid %d\n",
-		   scif_info.total, scif_info.nodeid,
-		   scif_info.maxid);
-
-	if (!scif_dev)
-		return 0;
-
-	seq_printf(s, "%-16s\t%-16s\n", "node_id", "state");
-
-	for (node = 0; node <= scif_info.maxid; node++)
-		seq_printf(s, "%-16d\t%-16s\n", scif_dev[node].node,
-			   _scifdev_alive(&scif_dev[node]) ?
-			   "Running" : "Offline");
-	return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(scif_dev);
-
-static void scif_display_window(struct scif_window *window, struct seq_file *s)
-{
-	int j;
-	struct scatterlist *sg;
-	scif_pinned_pages_t pin = window->pinned_pages;
-
-	seq_printf(s, "window %p type %d temp %d offset 0x%llx ",
-		   window, window->type, window->temp, window->offset);
-	seq_printf(s, "nr_pages 0x%llx nr_contig_chunks 0x%x prot %d ",
-		   window->nr_pages, window->nr_contig_chunks, window->prot);
-	seq_printf(s, "ref_count %d magic 0x%llx peer_window 0x%llx ",
-		   window->ref_count, window->magic, window->peer_window);
-	seq_printf(s, "unreg_state 0x%x va_for_temp 0x%lx\n",
-		   window->unreg_state, window->va_for_temp);
-
-	for (j = 0; j < window->nr_contig_chunks; j++)
-		seq_printf(s, "page[%d] dma_addr 0x%llx num_pages 0x%llx\n", j,
-			   window->dma_addr[j], window->num_pages[j]);
-
-	if (window->type == SCIF_WINDOW_SELF && pin)
-		for (j = 0; j < window->nr_pages; j++)
-			seq_printf(s, "page[%d] = pinned_pages %p address %p\n",
-				   j, pin->pages[j],
-				   page_address(pin->pages[j]));
-
-	if (window->st)
-		for_each_sg(window->st->sgl, sg, window->st->nents, j)
-			seq_printf(s, "sg[%d] dma addr 0x%llx length 0x%x\n",
-				   j, sg_dma_address(sg), sg_dma_len(sg));
-}
-
-static void scif_display_all_windows(struct list_head *head, struct seq_file *s)
-{
-	struct list_head *item;
-	struct scif_window *window;
-
-	list_for_each(item, head) {
-		window = list_entry(item, struct scif_window, list);
-		scif_display_window(window, s);
-	}
-}
-
-static int scif_rma_show(struct seq_file *s, void *unused)
-{
-	struct scif_endpt *ep;
-	struct list_head *pos;
-
-	mutex_lock(&scif_info.connlock);
-	list_for_each(pos, &scif_info.connected) {
-		ep = list_entry(pos, struct scif_endpt, list);
-		seq_printf(s, "ep %p self windows\n", ep);
-		mutex_lock(&ep->rma_info.rma_lock);
-		scif_display_all_windows(&ep->rma_info.reg_list, s);
-		seq_printf(s, "ep %p remote windows\n", ep);
-		scif_display_all_windows(&ep->rma_info.remote_reg_list, s);
-		mutex_unlock(&ep->rma_info.rma_lock);
-	}
-	mutex_unlock(&scif_info.connlock);
-	return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(scif_rma);
-
-void __init scif_init_debugfs(void)
-{
-	scif_dbg = debugfs_create_dir(KBUILD_MODNAME, NULL);
-
-	debugfs_create_file("scif_dev", 0444, scif_dbg, NULL, &scif_dev_fops);
-	debugfs_create_file("scif_rma", 0444, scif_dbg, NULL, &scif_rma_fops);
-	debugfs_create_u8("en_msg_log", 0666, scif_dbg, &scif_info.en_msg_log);
-	debugfs_create_u8("p2p_enable", 0666, scif_dbg, &scif_info.p2p_enable);
-}
-
-void scif_exit_debugfs(void)
-{
-	debugfs_remove_recursive(scif_dbg);
-}
diff --git a/drivers/misc/mic/scif/scif_dma.c b/drivers/misc/mic/scif/scif_dma.c
deleted file mode 100644
index 401b98e5ad79..000000000000
--- a/drivers/misc/mic/scif/scif_dma.c
+++ /dev/null
@@ -1,1940 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include "scif_main.h"
-#include "scif_map.h"
-
-/*
- * struct scif_dma_comp_cb - SCIF DMA completion callback
- *
- * @dma_completion_func: DMA completion callback
- * @cb_cookie: DMA completion callback cookie
- * @temp_buf: Temporary buffer
- * @temp_buf_to_free: Temporary buffer to be freed
- * @is_cache: Is a kmem_cache allocated buffer
- * @dst_offset: Destination registration offset
- * @dst_window: Destination registration window
- * @len: Length of the temp buffer
- * @temp_phys: DMA address of the temp buffer
- * @sdev: The SCIF device
- * @header_padding: padding for cache line alignment
- */
-struct scif_dma_comp_cb {
-	void (*dma_completion_func)(void *cookie);
-	void *cb_cookie;
-	u8 *temp_buf;
-	u8 *temp_buf_to_free;
-	bool is_cache;
-	s64 dst_offset;
-	struct scif_window *dst_window;
-	size_t len;
-	dma_addr_t temp_phys;
-	struct scif_dev *sdev;
-	int header_padding;
-};
-
-/**
- * struct scif_copy_work - Work for DMA copy
- *
- * @src_offset: Starting source offset
- * @dst_offset: Starting destination offset
- * @src_window: Starting src registered window
- * @dst_window: Starting dst registered window
- * @loopback: true if this is a loopback DMA transfer
- * @len: Length of the transfer
- * @comp_cb: DMA copy completion callback
- * @remote_dev: The remote SCIF peer device
- * @fence_type: polling or interrupt based
- * @ordered: is this a tail byte ordered DMA transfer
- */
-struct scif_copy_work {
-	s64 src_offset;
-	s64 dst_offset;
-	struct scif_window *src_window;
-	struct scif_window *dst_window;
-	int loopback;
-	size_t len;
-	struct scif_dma_comp_cb   *comp_cb;
-	struct scif_dev	*remote_dev;
-	int fence_type;
-	bool ordered;
-};
-
-/**
- * scif_reserve_dma_chan:
- * @ep: Endpoint Descriptor.
- *
- * This routine reserves a DMA channel for a particular
- * endpoint. All DMA transfers for an endpoint are always
- * programmed on the same DMA channel.
- */
-int scif_reserve_dma_chan(struct scif_endpt *ep)
-{
-	int err = 0;
-	struct scif_dev *scifdev;
-	struct scif_hw_dev *sdev;
-	struct dma_chan *chan;
-
-	/* Loopback DMAs are not supported on the management node */
-	if (!scif_info.nodeid && scifdev_self(ep->remote_dev))
-		return 0;
-	if (scif_info.nodeid)
-		scifdev = &scif_dev[0];
-	else
-		scifdev = ep->remote_dev;
-	sdev = scifdev->sdev;
-	if (!sdev->num_dma_ch)
-		return -ENODEV;
-	chan = sdev->dma_ch[scifdev->dma_ch_idx];
-	scifdev->dma_ch_idx = (scifdev->dma_ch_idx + 1) % sdev->num_dma_ch;
-	mutex_lock(&ep->rma_info.rma_lock);
-	ep->rma_info.dma_chan = chan;
-	mutex_unlock(&ep->rma_info.rma_lock);
-	return err;
-}
-
-#ifdef CONFIG_MMU_NOTIFIER
-/*
- * scif_rma_destroy_tcw:
- *
- * This routine destroys temporary cached windows
- */
-static
-void __scif_rma_destroy_tcw(struct scif_mmu_notif *mmn,
-			    u64 start, u64 len)
-{
-	struct list_head *item, *tmp;
-	struct scif_window *window;
-	u64 start_va, end_va;
-	u64 end = start + len;
-
-	if (end <= start)
-		return;
-
-	list_for_each_safe(item, tmp, &mmn->tc_reg_list) {
-		window = list_entry(item, struct scif_window, list);
-		if (!len)
-			break;
-		start_va = window->va_for_temp;
-		end_va = start_va + (window->nr_pages << PAGE_SHIFT);
-		if (start < start_va && end <= start_va)
-			break;
-		if (start >= end_va)
-			continue;
-		__scif_rma_destroy_tcw_helper(window);
-	}
-}
-
-static void scif_rma_destroy_tcw(struct scif_mmu_notif *mmn, u64 start, u64 len)
-{
-	struct scif_endpt *ep = mmn->ep;
-
-	spin_lock(&ep->rma_info.tc_lock);
-	__scif_rma_destroy_tcw(mmn, start, len);
-	spin_unlock(&ep->rma_info.tc_lock);
-}
-
-static void scif_rma_destroy_tcw_ep(struct scif_endpt *ep)
-{
-	struct list_head *item, *tmp;
-	struct scif_mmu_notif *mmn;
-
-	list_for_each_safe(item, tmp, &ep->rma_info.mmn_list) {
-		mmn = list_entry(item, struct scif_mmu_notif, list);
-		scif_rma_destroy_tcw(mmn, 0, ULONG_MAX);
-	}
-}
-
-static void __scif_rma_destroy_tcw_ep(struct scif_endpt *ep)
-{
-	struct list_head *item, *tmp;
-	struct scif_mmu_notif *mmn;
-
-	spin_lock(&ep->rma_info.tc_lock);
-	list_for_each_safe(item, tmp, &ep->rma_info.mmn_list) {
-		mmn = list_entry(item, struct scif_mmu_notif, list);
-		__scif_rma_destroy_tcw(mmn, 0, ULONG_MAX);
-	}
-	spin_unlock(&ep->rma_info.tc_lock);
-}
-
-static bool scif_rma_tc_can_cache(struct scif_endpt *ep, size_t cur_bytes)
-{
-	if ((cur_bytes >> PAGE_SHIFT) > scif_info.rma_tc_limit)
-		return false;
-	if ((atomic_read(&ep->rma_info.tcw_total_pages)
-			+ (cur_bytes >> PAGE_SHIFT)) >
-			scif_info.rma_tc_limit) {
-		dev_info(scif_info.mdev.this_device,
-			 "%s %d total=%d, current=%zu reached max\n",
-			 __func__, __LINE__,
-			 atomic_read(&ep->rma_info.tcw_total_pages),
-			 (1 + (cur_bytes >> PAGE_SHIFT)));
-		scif_rma_destroy_tcw_invalid();
-		__scif_rma_destroy_tcw_ep(ep);
-	}
-	return true;
-}
-
-static void scif_mmu_notifier_release(struct mmu_notifier *mn,
-				      struct mm_struct *mm)
-{
-	struct scif_mmu_notif	*mmn;
-
-	mmn = container_of(mn, struct scif_mmu_notif, ep_mmu_notifier);
-	scif_rma_destroy_tcw(mmn, 0, ULONG_MAX);
-	schedule_work(&scif_info.misc_work);
-}
-
-static int scif_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
-					const struct mmu_notifier_range *range)
-{
-	struct scif_mmu_notif	*mmn;
-
-	mmn = container_of(mn, struct scif_mmu_notif, ep_mmu_notifier);
-	scif_rma_destroy_tcw(mmn, range->start, range->end - range->start);
-
-	return 0;
-}
-
-static void scif_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
-			const struct mmu_notifier_range *range)
-{
-	/*
-	 * Nothing to do here, everything needed was done in
-	 * invalidate_range_start.
-	 */
-}
-
-static const struct mmu_notifier_ops scif_mmu_notifier_ops = {
-	.release = scif_mmu_notifier_release,
-	.clear_flush_young = NULL,
-	.invalidate_range_start = scif_mmu_notifier_invalidate_range_start,
-	.invalidate_range_end = scif_mmu_notifier_invalidate_range_end};
-
-static void scif_ep_unregister_mmu_notifier(struct scif_endpt *ep)
-{
-	struct scif_endpt_rma_info *rma = &ep->rma_info;
-	struct scif_mmu_notif *mmn = NULL;
-	struct list_head *item, *tmp;
-
-	mutex_lock(&ep->rma_info.mmn_lock);
-	list_for_each_safe(item, tmp, &rma->mmn_list) {
-		mmn = list_entry(item, struct scif_mmu_notif, list);
-		mmu_notifier_unregister(&mmn->ep_mmu_notifier, mmn->mm);
-		list_del(item);
-		kfree(mmn);
-	}
-	mutex_unlock(&ep->rma_info.mmn_lock);
-}
-
-static void scif_init_mmu_notifier(struct scif_mmu_notif *mmn,
-				   struct mm_struct *mm, struct scif_endpt *ep)
-{
-	mmn->ep = ep;
-	mmn->mm = mm;
-	mmn->ep_mmu_notifier.ops = &scif_mmu_notifier_ops;
-	INIT_LIST_HEAD(&mmn->list);
-	INIT_LIST_HEAD(&mmn->tc_reg_list);
-}
-
-static struct scif_mmu_notif *
-scif_find_mmu_notifier(struct mm_struct *mm, struct scif_endpt_rma_info *rma)
-{
-	struct scif_mmu_notif *mmn;
-
-	list_for_each_entry(mmn, &rma->mmn_list, list)
-		if (mmn->mm == mm)
-			return mmn;
-	return NULL;
-}
-
-static struct scif_mmu_notif *
-scif_add_mmu_notifier(struct mm_struct *mm, struct scif_endpt *ep)
-{
-	struct scif_mmu_notif *mmn
-		 = kzalloc(sizeof(*mmn), GFP_KERNEL);
-
-	if (!mmn)
-		return ERR_PTR(-ENOMEM);
-
-	scif_init_mmu_notifier(mmn, current->mm, ep);
-	if (mmu_notifier_register(&mmn->ep_mmu_notifier, current->mm)) {
-		kfree(mmn);
-		return ERR_PTR(-EBUSY);
-	}
-	list_add(&mmn->list, &ep->rma_info.mmn_list);
-	return mmn;
-}
-
-/*
- * Called from the misc thread to destroy temporary cached windows and
- * unregister the MMU notifier for the SCIF endpoint.
- */
-void scif_mmu_notif_handler(struct work_struct *work)
-{
-	struct list_head *pos, *tmpq;
-	struct scif_endpt *ep;
-restart:
-	scif_rma_destroy_tcw_invalid();
-	spin_lock(&scif_info.rmalock);
-	list_for_each_safe(pos, tmpq, &scif_info.mmu_notif_cleanup) {
-		ep = list_entry(pos, struct scif_endpt, mmu_list);
-		list_del(&ep->mmu_list);
-		spin_unlock(&scif_info.rmalock);
-		scif_rma_destroy_tcw_ep(ep);
-		scif_ep_unregister_mmu_notifier(ep);
-		goto restart;
-	}
-	spin_unlock(&scif_info.rmalock);
-}
-
-static bool scif_is_set_reg_cache(int flags)
-{
-	return !!(flags & SCIF_RMA_USECACHE);
-}
-#else
-static struct scif_mmu_notif *
-scif_find_mmu_notifier(struct mm_struct *mm,
-		       struct scif_endpt_rma_info *rma)
-{
-	return NULL;
-}
-
-static struct scif_mmu_notif *
-scif_add_mmu_notifier(struct mm_struct *mm, struct scif_endpt *ep)
-{
-	return NULL;
-}
-
-void scif_mmu_notif_handler(struct work_struct *work)
-{
-}
-
-static bool scif_is_set_reg_cache(int flags)
-{
-	return false;
-}
-
-static bool scif_rma_tc_can_cache(struct scif_endpt *ep, size_t cur_bytes)
-{
-	return false;
-}
-#endif
-
-/**
- * scif_register_temp:
- * @epd: End Point Descriptor.
- * @addr: virtual address to/from which to copy
- * @len: length of range to copy
- * @prot: read/write protection
- * @out_offset: computed offset returned by reference.
- * @out_window: allocated registered window returned by reference.
- *
- * Create a temporary registered window. The peer will not know about this
- * window. This API is used for scif_vreadfrom()/scif_vwriteto() API's.
- */
-static int
-scif_register_temp(scif_epd_t epd, unsigned long addr, size_t len, int prot,
-		   off_t *out_offset, struct scif_window **out_window)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)epd;
-	int err;
-	scif_pinned_pages_t pinned_pages;
-	size_t aligned_len;
-
-	aligned_len = ALIGN(len, PAGE_SIZE);
-
-	err = __scif_pin_pages((void *)(addr & PAGE_MASK),
-			       aligned_len, &prot, 0, &pinned_pages);
-	if (err)
-		return err;
-
-	pinned_pages->prot = prot;
-
-	/* Compute the offset for this registration */
-	err = scif_get_window_offset(ep, 0, 0,
-				     aligned_len >> PAGE_SHIFT,
-				     (s64 *)out_offset);
-	if (err)
-		goto error_unpin;
-
-	/* Allocate and prepare self registration window */
-	*out_window = scif_create_window(ep, aligned_len >> PAGE_SHIFT,
-					*out_offset, true);
-	if (!*out_window) {
-		scif_free_window_offset(ep, NULL, *out_offset);
-		err = -ENOMEM;
-		goto error_unpin;
-	}
-
-	(*out_window)->pinned_pages = pinned_pages;
-	(*out_window)->nr_pages = pinned_pages->nr_pages;
-	(*out_window)->prot = pinned_pages->prot;
-
-	(*out_window)->va_for_temp = addr & PAGE_MASK;
-	err = scif_map_window(ep->remote_dev, *out_window);
-	if (err) {
-		/* Something went wrong! Rollback */
-		scif_destroy_window(ep, *out_window);
-		*out_window = NULL;
-	} else {
-		*out_offset |= (addr - (*out_window)->va_for_temp);
-	}
-	return err;
-error_unpin:
-	if (err)
-		dev_err(&ep->remote_dev->sdev->dev,
-			"%s %d err %d\n", __func__, __LINE__, err);
-	scif_unpin_pages(pinned_pages);
-	return err;
-}
-
-#define SCIF_DMA_TO (3 * HZ)
-
-/*
- * scif_sync_dma - Program a DMA without an interrupt descriptor
- *
- * @dev - The address of the pointer to the device instance used
- * for DMA registration.
- * @chan - DMA channel to be used.
- * @sync_wait: Wait for DMA to complete?
- *
- * Return 0 on success and -errno on error.
- */
-static int scif_sync_dma(struct scif_hw_dev *sdev, struct dma_chan *chan,
-			 bool sync_wait)
-{
-	int err = 0;
-	struct dma_async_tx_descriptor *tx = NULL;
-	enum dma_ctrl_flags flags = DMA_PREP_FENCE;
-	dma_cookie_t cookie;
-	struct dma_device *ddev;
-
-	if (!chan) {
-		err = -EIO;
-		dev_err(&sdev->dev, "%s %d err %d\n",
-			__func__, __LINE__, err);
-		return err;
-	}
-	ddev = chan->device;
-
-	tx = ddev->device_prep_dma_memcpy(chan, 0, 0, 0, flags);
-	if (!tx) {
-		err = -ENOMEM;
-		dev_err(&sdev->dev, "%s %d err %d\n",
-			__func__, __LINE__, err);
-		goto release;
-	}
-	cookie = tx->tx_submit(tx);
-
-	if (dma_submit_error(cookie)) {
-		err = -ENOMEM;
-		dev_err(&sdev->dev, "%s %d err %d\n",
-			__func__, __LINE__, err);
-		goto release;
-	}
-	if (!sync_wait) {
-		dma_async_issue_pending(chan);
-	} else {
-		if (dma_sync_wait(chan, cookie) == DMA_COMPLETE) {
-			err = 0;
-		} else {
-			err = -EIO;
-			dev_err(&sdev->dev, "%s %d err %d\n",
-				__func__, __LINE__, err);
-		}
-	}
-release:
-	return err;
-}
-
-static void scif_dma_callback(void *arg)
-{
-	struct completion *done = (struct completion *)arg;
-
-	complete(done);
-}
-
-#define SCIF_DMA_SYNC_WAIT true
-#define SCIF_DMA_POLL BIT(0)
-#define SCIF_DMA_INTR BIT(1)
-
-/*
- * scif_async_dma - Program a DMA with an interrupt descriptor
- *
- * @dev - The address of the pointer to the device instance used
- * for DMA registration.
- * @chan - DMA channel to be used.
- * Return 0 on success and -errno on error.
- */
-static int scif_async_dma(struct scif_hw_dev *sdev, struct dma_chan *chan)
-{
-	int err = 0;
-	struct dma_device *ddev;
-	struct dma_async_tx_descriptor *tx = NULL;
-	enum dma_ctrl_flags flags = DMA_PREP_INTERRUPT | DMA_PREP_FENCE;
-	DECLARE_COMPLETION_ONSTACK(done_wait);
-	dma_cookie_t cookie;
-	enum dma_status status;
-
-	if (!chan) {
-		err = -EIO;
-		dev_err(&sdev->dev, "%s %d err %d\n",
-			__func__, __LINE__, err);
-		return err;
-	}
-	ddev = chan->device;
-
-	tx = ddev->device_prep_dma_memcpy(chan, 0, 0, 0, flags);
-	if (!tx) {
-		err = -ENOMEM;
-		dev_err(&sdev->dev, "%s %d err %d\n",
-			__func__, __LINE__, err);
-		goto release;
-	}
-	reinit_completion(&done_wait);
-	tx->callback = scif_dma_callback;
-	tx->callback_param = &done_wait;
-	cookie = tx->tx_submit(tx);
-
-	if (dma_submit_error(cookie)) {
-		err = -ENOMEM;
-		dev_err(&sdev->dev, "%s %d err %d\n",
-			__func__, __LINE__, err);
-		goto release;
-	}
-	dma_async_issue_pending(chan);
-
-	err = wait_for_completion_timeout(&done_wait, SCIF_DMA_TO);
-	if (!err) {
-		err = -EIO;
-		dev_err(&sdev->dev, "%s %d err %d\n",
-			__func__, __LINE__, err);
-		goto release;
-	}
-	err = 0;
-	status = dma_async_is_tx_complete(chan, cookie, NULL, NULL);
-	if (status != DMA_COMPLETE) {
-		err = -EIO;
-		dev_err(&sdev->dev, "%s %d err %d\n",
-			__func__, __LINE__, err);
-		goto release;
-	}
-release:
-	return err;
-}
-
-/*
- * scif_drain_dma_poll - Drain all outstanding DMA operations for a particular
- * DMA channel via polling.
- *
- * @sdev - The SCIF device
- * @chan - DMA channel
- * Return 0 on success and -errno on error.
- */
-static int scif_drain_dma_poll(struct scif_hw_dev *sdev, struct dma_chan *chan)
-{
-	if (!chan)
-		return -EINVAL;
-	return scif_sync_dma(sdev, chan, SCIF_DMA_SYNC_WAIT);
-}
-
-/*
- * scif_drain_dma_intr - Drain all outstanding DMA operations for a particular
- * DMA channel via interrupt based blocking wait.
- *
- * @sdev - The SCIF device
- * @chan - DMA channel
- * Return 0 on success and -errno on error.
- */
-int scif_drain_dma_intr(struct scif_hw_dev *sdev, struct dma_chan *chan)
-{
-	if (!chan)
-		return -EINVAL;
-	return scif_async_dma(sdev, chan);
-}
-
-/**
- * scif_rma_destroy_windows:
- *
- * This routine destroys all windows queued for cleanup
- */
-void scif_rma_destroy_windows(void)
-{
-	struct list_head *item, *tmp;
-	struct scif_window *window;
-	struct scif_endpt *ep;
-	struct dma_chan *chan;
-
-	might_sleep();
-restart:
-	spin_lock(&scif_info.rmalock);
-	list_for_each_safe(item, tmp, &scif_info.rma) {
-		window = list_entry(item, struct scif_window,
-				    list);
-		ep = (struct scif_endpt *)window->ep;
-		chan = ep->rma_info.dma_chan;
-
-		list_del_init(&window->list);
-		spin_unlock(&scif_info.rmalock);
-		if (!chan || !scifdev_alive(ep) ||
-		    !scif_drain_dma_intr(ep->remote_dev->sdev,
-					 ep->rma_info.dma_chan))
-			/* Remove window from global list */
-			window->unreg_state = OP_COMPLETED;
-		else
-			dev_warn(&ep->remote_dev->sdev->dev,
-				 "DMA engine hung?\n");
-		if (window->unreg_state == OP_COMPLETED) {
-			if (window->type == SCIF_WINDOW_SELF)
-				scif_destroy_window(ep, window);
-			else
-				scif_destroy_remote_window(window);
-			atomic_dec(&ep->rma_info.tw_refcount);
-		}
-		goto restart;
-	}
-	spin_unlock(&scif_info.rmalock);
-}
-
-/**
- * scif_rma_destroy_tcw:
- *
- * This routine destroys temporary cached registered windows
- * which have been queued for cleanup.
- */
-void scif_rma_destroy_tcw_invalid(void)
-{
-	struct list_head *item, *tmp;
-	struct scif_window *window;
-	struct scif_endpt *ep;
-	struct dma_chan *chan;
-
-	might_sleep();
-restart:
-	spin_lock(&scif_info.rmalock);
-	list_for_each_safe(item, tmp, &scif_info.rma_tc) {
-		window = list_entry(item, struct scif_window, list);
-		ep = (struct scif_endpt *)window->ep;
-		chan = ep->rma_info.dma_chan;
-		list_del_init(&window->list);
-		spin_unlock(&scif_info.rmalock);
-		mutex_lock(&ep->rma_info.rma_lock);
-		if (!chan || !scifdev_alive(ep) ||
-		    !scif_drain_dma_intr(ep->remote_dev->sdev,
-					 ep->rma_info.dma_chan)) {
-			atomic_sub(window->nr_pages,
-				   &ep->rma_info.tcw_total_pages);
-			scif_destroy_window(ep, window);
-			atomic_dec(&ep->rma_info.tcw_refcount);
-		} else {
-			dev_warn(&ep->remote_dev->sdev->dev,
-				 "DMA engine hung?\n");
-		}
-		mutex_unlock(&ep->rma_info.rma_lock);
-		goto restart;
-	}
-	spin_unlock(&scif_info.rmalock);
-}
-
-static inline
-void *_get_local_va(off_t off, struct scif_window *window, size_t len)
-{
-	int page_nr = (off - window->offset) >> PAGE_SHIFT;
-	off_t page_off = off & ~PAGE_MASK;
-	void *va = NULL;
-
-	if (window->type == SCIF_WINDOW_SELF) {
-		struct page **pages = window->pinned_pages->pages;
-
-		va = page_address(pages[page_nr]) + page_off;
-	}
-	return va;
-}
-
-static inline
-void *ioremap_remote(off_t off, struct scif_window *window,
-		     size_t len, struct scif_dev *dev,
-		     struct scif_window_iter *iter)
-{
-	dma_addr_t phys = scif_off_to_dma_addr(window, off, NULL, iter);
-
-	/*
-	 * If the DMA address is not card relative then we need the DMA
-	 * addresses to be an offset into the bar. The aperture base was already
-	 * added so subtract it here since scif_ioremap is going to add it again
-	 */
-	if (!scifdev_self(dev) && window->type == SCIF_WINDOW_PEER &&
-	    dev->sdev->aper && !dev->sdev->card_rel_da)
-		phys = phys - dev->sdev->aper->pa;
-	return scif_ioremap(phys, len, dev);
-}
-
-static inline void
-iounmap_remote(void *virt, size_t size, struct scif_copy_work *work)
-{
-	scif_iounmap(virt, size, work->remote_dev);
-}
-
-/*
- * Takes care of ordering issue caused by
- * 1. Hardware:  Only in the case of cpu copy from mgmt node to card
- * because of WC memory.
- * 2. Software: If memcpy reorders copy instructions for optimization.
- * This could happen at both mgmt node and card.
- */
-static inline void
-scif_ordered_memcpy_toio(char *dst, const char *src, size_t count)
-{
-	if (!count)
-		return;
-
-	memcpy_toio((void __iomem __force *)dst, src, --count);
-	/* Order the last byte with the previous stores */
-	wmb();
-	*(dst + count) = *(src + count);
-}
-
-static inline void scif_unaligned_cpy_toio(char *dst, const char *src,
-					   size_t count, bool ordered)
-{
-	if (ordered)
-		scif_ordered_memcpy_toio(dst, src, count);
-	else
-		memcpy_toio((void __iomem __force *)dst, src, count);
-}
-
-static inline
-void scif_ordered_memcpy_fromio(char *dst, const char *src, size_t count)
-{
-	if (!count)
-		return;
-
-	memcpy_fromio(dst, (void __iomem __force *)src, --count);
-	/* Order the last byte with the previous loads */
-	rmb();
-	*(dst + count) = *(src + count);
-}
-
-static inline void scif_unaligned_cpy_fromio(char *dst, const char *src,
-					     size_t count, bool ordered)
-{
-	if (ordered)
-		scif_ordered_memcpy_fromio(dst, src, count);
-	else
-		memcpy_fromio(dst, (void __iomem __force *)src, count);
-}
-
-#define SCIF_RMA_ERROR_CODE (~(dma_addr_t)0x0)
-
-/*
- * scif_off_to_dma_addr:
- * Obtain the dma_addr given the window and the offset.
- * @window: Registered window.
- * @off: Window offset.
- * @nr_bytes: Return the number of contiguous bytes till next DMA addr index.
- * @index: Return the index of the dma_addr array found.
- * @start_off: start offset of index of the dma addr array found.
- * The nr_bytes provides the callee an estimate of the maximum possible
- * DMA xfer possible while the index/start_off provide faster lookups
- * for the next iteration.
- */
-dma_addr_t scif_off_to_dma_addr(struct scif_window *window, s64 off,
-				size_t *nr_bytes, struct scif_window_iter *iter)
-{
-	int i, page_nr;
-	s64 start, end;
-	off_t page_off;
-
-	if (window->nr_pages == window->nr_contig_chunks) {
-		page_nr = (off - window->offset) >> PAGE_SHIFT;
-		page_off = off & ~PAGE_MASK;
-
-		if (nr_bytes)
-			*nr_bytes = PAGE_SIZE - page_off;
-		return window->dma_addr[page_nr] | page_off;
-	}
-	if (iter) {
-		i = iter->index;
-		start = iter->offset;
-	} else {
-		i =  0;
-		start =  window->offset;
-	}
-	for (; i < window->nr_contig_chunks; i++) {
-		end = start + (window->num_pages[i] << PAGE_SHIFT);
-		if (off >= start && off < end) {
-			if (iter) {
-				iter->index = i;
-				iter->offset = start;
-			}
-			if (nr_bytes)
-				*nr_bytes = end - off;
-			return (window->dma_addr[i] + (off - start));
-		}
-		start += (window->num_pages[i] << PAGE_SHIFT);
-	}
-	dev_err(scif_info.mdev.this_device,
-		"%s %d BUG. Addr not found? window %p off 0x%llx\n",
-		__func__, __LINE__, window, off);
-	return SCIF_RMA_ERROR_CODE;
-}
-
-/*
- * Copy between rma window and temporary buffer
- */
-static void scif_rma_local_cpu_copy(s64 offset, struct scif_window *window,
-				    u8 *temp, size_t rem_len, bool to_temp)
-{
-	void *window_virt;
-	size_t loop_len;
-	int offset_in_page;
-	s64 end_offset;
-
-	offset_in_page = offset & ~PAGE_MASK;
-	loop_len = PAGE_SIZE - offset_in_page;
-
-	if (rem_len < loop_len)
-		loop_len = rem_len;
-
-	window_virt = _get_local_va(offset, window, loop_len);
-	if (!window_virt)
-		return;
-	if (to_temp)
-		memcpy(temp, window_virt, loop_len);
-	else
-		memcpy(window_virt, temp, loop_len);
-
-	offset += loop_len;
-	temp += loop_len;
-	rem_len -= loop_len;
-
-	end_offset = window->offset +
-		(window->nr_pages << PAGE_SHIFT);
-	while (rem_len) {
-		if (offset == end_offset) {
-			window = list_next_entry(window, list);
-			end_offset = window->offset +
-				(window->nr_pages << PAGE_SHIFT);
-		}
-		loop_len = min(PAGE_SIZE, rem_len);
-		window_virt = _get_local_va(offset, window, loop_len);
-		if (!window_virt)
-			return;
-		if (to_temp)
-			memcpy(temp, window_virt, loop_len);
-		else
-			memcpy(window_virt, temp, loop_len);
-		offset	+= loop_len;
-		temp	+= loop_len;
-		rem_len	-= loop_len;
-	}
-}
-
-/**
- * scif_rma_completion_cb:
- * @data: RMA cookie
- *
- * RMA interrupt completion callback.
- */
-static void scif_rma_completion_cb(void *data)
-{
-	struct scif_dma_comp_cb *comp_cb = data;
-
-	/* Free DMA Completion CB. */
-	if (comp_cb->dst_window)
-		scif_rma_local_cpu_copy(comp_cb->dst_offset,
-					comp_cb->dst_window,
-					comp_cb->temp_buf +
-					comp_cb->header_padding,
-					comp_cb->len, false);
-	scif_unmap_single(comp_cb->temp_phys, comp_cb->sdev,
-			  SCIF_KMEM_UNALIGNED_BUF_SIZE);
-	if (comp_cb->is_cache)
-		kmem_cache_free(unaligned_cache,
-				comp_cb->temp_buf_to_free);
-	else
-		kfree(comp_cb->temp_buf_to_free);
-}
-
-/* Copies between temporary buffer and offsets provided in work */
-static int
-scif_rma_list_dma_copy_unaligned(struct scif_copy_work *work,
-				 u8 *temp, struct dma_chan *chan,
-				 bool src_local)
-{
-	struct scif_dma_comp_cb *comp_cb = work->comp_cb;
-	dma_addr_t window_dma_addr, temp_dma_addr;
-	dma_addr_t temp_phys = comp_cb->temp_phys;
-	size_t loop_len, nr_contig_bytes = 0, remaining_len = work->len;
-	int offset_in_ca, ret = 0;
-	s64 end_offset, offset;
-	struct scif_window *window;
-	void *window_virt_addr;
-	size_t tail_len;
-	struct dma_async_tx_descriptor *tx;
-	struct dma_device *dev = chan->device;
-	dma_cookie_t cookie;
-
-	if (src_local) {
-		offset = work->dst_offset;
-		window = work->dst_window;
-	} else {
-		offset = work->src_offset;
-		window = work->src_window;
-	}
-
-	offset_in_ca = offset & (L1_CACHE_BYTES - 1);
-	if (offset_in_ca) {
-		loop_len = L1_CACHE_BYTES - offset_in_ca;
-		loop_len = min(loop_len, remaining_len);
-		window_virt_addr = ioremap_remote(offset, window,
-						  loop_len,
-						  work->remote_dev,
-						  NULL);
-		if (!window_virt_addr)
-			return -ENOMEM;
-		if (src_local)
-			scif_unaligned_cpy_toio(window_virt_addr, temp,
-						loop_len,
-						work->ordered &&
-						!(remaining_len - loop_len));
-		else
-			scif_unaligned_cpy_fromio(temp, window_virt_addr,
-						  loop_len, work->ordered &&
-						  !(remaining_len - loop_len));
-		iounmap_remote(window_virt_addr, loop_len, work);
-
-		offset += loop_len;
-		temp += loop_len;
-		temp_phys += loop_len;
-		remaining_len -= loop_len;
-	}
-
-	offset_in_ca = offset & ~PAGE_MASK;
-	end_offset = window->offset +
-		(window->nr_pages << PAGE_SHIFT);
-
-	tail_len = remaining_len & (L1_CACHE_BYTES - 1);
-	remaining_len -= tail_len;
-	while (remaining_len) {
-		if (offset == end_offset) {
-			window = list_next_entry(window, list);
-			end_offset = window->offset +
-				(window->nr_pages << PAGE_SHIFT);
-		}
-		if (scif_is_mgmt_node())
-			temp_dma_addr = temp_phys;
-		else
-			/* Fix if we ever enable IOMMU on the card */
-			temp_dma_addr = (dma_addr_t)virt_to_phys(temp);
-		window_dma_addr = scif_off_to_dma_addr(window, offset,
-						       &nr_contig_bytes,
-						       NULL);
-		loop_len = min(nr_contig_bytes, remaining_len);
-		if (src_local) {
-			if (work->ordered && !tail_len &&
-			    !(remaining_len - loop_len) &&
-			    loop_len != L1_CACHE_BYTES) {
-				/*
-				 * Break up the last chunk of the transfer into
-				 * two steps. if there is no tail to guarantee
-				 * DMA ordering. SCIF_DMA_POLLING inserts
-				 * a status update descriptor in step 1 which
-				 * acts as a double sided synchronization fence
-				 * for the DMA engine to ensure that the last
-				 * cache line in step 2 is updated last.
-				 */
-				/* Step 1) DMA: Body Length - L1_CACHE_BYTES. */
-				tx =
-				dev->device_prep_dma_memcpy(chan,
-							    window_dma_addr,
-							    temp_dma_addr,
-							    loop_len -
-							    L1_CACHE_BYTES,
-							    DMA_PREP_FENCE);
-				if (!tx) {
-					ret = -ENOMEM;
-					goto err;
-				}
-				cookie = tx->tx_submit(tx);
-				if (dma_submit_error(cookie)) {
-					ret = -ENOMEM;
-					goto err;
-				}
-				dma_async_issue_pending(chan);
-				offset += (loop_len - L1_CACHE_BYTES);
-				temp_dma_addr += (loop_len - L1_CACHE_BYTES);
-				window_dma_addr += (loop_len - L1_CACHE_BYTES);
-				remaining_len -= (loop_len - L1_CACHE_BYTES);
-				loop_len = remaining_len;
-
-				/* Step 2) DMA: L1_CACHE_BYTES */
-				tx =
-				dev->device_prep_dma_memcpy(chan,
-							    window_dma_addr,
-							    temp_dma_addr,
-							    loop_len, 0);
-				if (!tx) {
-					ret = -ENOMEM;
-					goto err;
-				}
-				cookie = tx->tx_submit(tx);
-				if (dma_submit_error(cookie)) {
-					ret = -ENOMEM;
-					goto err;
-				}
-				dma_async_issue_pending(chan);
-			} else {
-				tx =
-				dev->device_prep_dma_memcpy(chan,
-							    window_dma_addr,
-							    temp_dma_addr,
-							    loop_len, 0);
-				if (!tx) {
-					ret = -ENOMEM;
-					goto err;
-				}
-				cookie = tx->tx_submit(tx);
-				if (dma_submit_error(cookie)) {
-					ret = -ENOMEM;
-					goto err;
-				}
-				dma_async_issue_pending(chan);
-			}
-		} else {
-			tx = dev->device_prep_dma_memcpy(chan, temp_dma_addr,
-					window_dma_addr, loop_len, 0);
-			if (!tx) {
-				ret = -ENOMEM;
-				goto err;
-			}
-			cookie = tx->tx_submit(tx);
-			if (dma_submit_error(cookie)) {
-				ret = -ENOMEM;
-				goto err;
-			}
-			dma_async_issue_pending(chan);
-		}
-		offset += loop_len;
-		temp += loop_len;
-		temp_phys += loop_len;
-		remaining_len -= loop_len;
-		offset_in_ca = 0;
-	}
-	if (tail_len) {
-		if (offset == end_offset) {
-			window = list_next_entry(window, list);
-			end_offset = window->offset +
-				(window->nr_pages << PAGE_SHIFT);
-		}
-		window_virt_addr = ioremap_remote(offset, window, tail_len,
-						  work->remote_dev,
-						  NULL);
-		if (!window_virt_addr)
-			return -ENOMEM;
-		/*
-		 * The CPU copy for the tail bytes must be initiated only once
-		 * previous DMA transfers for this endpoint have completed
-		 * to guarantee ordering.
-		 */
-		if (work->ordered) {
-			struct scif_dev *rdev = work->remote_dev;
-
-			ret = scif_drain_dma_intr(rdev->sdev, chan);
-			if (ret)
-				return ret;
-		}
-		if (src_local)
-			scif_unaligned_cpy_toio(window_virt_addr, temp,
-						tail_len, work->ordered);
-		else
-			scif_unaligned_cpy_fromio(temp, window_virt_addr,
-						  tail_len, work->ordered);
-		iounmap_remote(window_virt_addr, tail_len, work);
-	}
-	tx = dev->device_prep_dma_memcpy(chan, 0, 0, 0, DMA_PREP_INTERRUPT);
-	if (!tx) {
-		ret = -ENOMEM;
-		return ret;
-	}
-	tx->callback = &scif_rma_completion_cb;
-	tx->callback_param = comp_cb;
-	cookie = tx->tx_submit(tx);
-
-	if (dma_submit_error(cookie)) {
-		ret = -ENOMEM;
-		return ret;
-	}
-	dma_async_issue_pending(chan);
-	return 0;
-err:
-	dev_err(scif_info.mdev.this_device,
-		"%s %d Desc Prog Failed ret %d\n",
-		__func__, __LINE__, ret);
-	return ret;
-}
-
-/*
- * _scif_rma_list_dma_copy_aligned:
- *
- * Traverse all the windows and perform DMA copy.
- */
-static int _scif_rma_list_dma_copy_aligned(struct scif_copy_work *work,
-					   struct dma_chan *chan)
-{
-	dma_addr_t src_dma_addr, dst_dma_addr;
-	size_t loop_len, remaining_len, src_contig_bytes = 0;
-	size_t dst_contig_bytes = 0;
-	struct scif_window_iter src_win_iter;
-	struct scif_window_iter dst_win_iter;
-	s64 end_src_offset, end_dst_offset;
-	struct scif_window *src_window = work->src_window;
-	struct scif_window *dst_window = work->dst_window;
-	s64 src_offset = work->src_offset, dst_offset = work->dst_offset;
-	int ret = 0;
-	struct dma_async_tx_descriptor *tx;
-	struct dma_device *dev = chan->device;
-	dma_cookie_t cookie;
-
-	remaining_len = work->len;
-
-	scif_init_window_iter(src_window, &src_win_iter);
-	scif_init_window_iter(dst_window, &dst_win_iter);
-	end_src_offset = src_window->offset +
-		(src_window->nr_pages << PAGE_SHIFT);
-	end_dst_offset = dst_window->offset +
-		(dst_window->nr_pages << PAGE_SHIFT);
-	while (remaining_len) {
-		if (src_offset == end_src_offset) {
-			src_window = list_next_entry(src_window, list);
-			end_src_offset = src_window->offset +
-				(src_window->nr_pages << PAGE_SHIFT);
-			scif_init_window_iter(src_window, &src_win_iter);
-		}
-		if (dst_offset == end_dst_offset) {
-			dst_window = list_next_entry(dst_window, list);
-			end_dst_offset = dst_window->offset +
-				(dst_window->nr_pages << PAGE_SHIFT);
-			scif_init_window_iter(dst_window, &dst_win_iter);
-		}
-
-		/* compute dma addresses for transfer */
-		src_dma_addr = scif_off_to_dma_addr(src_window, src_offset,
-						    &src_contig_bytes,
-						    &src_win_iter);
-		dst_dma_addr = scif_off_to_dma_addr(dst_window, dst_offset,
-						    &dst_contig_bytes,
-						    &dst_win_iter);
-		loop_len = min(src_contig_bytes, dst_contig_bytes);
-		loop_len = min(loop_len, remaining_len);
-		if (work->ordered && !(remaining_len - loop_len)) {
-			/*
-			 * Break up the last chunk of the transfer into two
-			 * steps to ensure that the last byte in step 2 is
-			 * updated last.
-			 */
-			/* Step 1) DMA: Body Length - 1 */
-			tx = dev->device_prep_dma_memcpy(chan, dst_dma_addr,
-							 src_dma_addr,
-							 loop_len - 1,
-							 DMA_PREP_FENCE);
-			if (!tx) {
-				ret = -ENOMEM;
-				goto err;
-			}
-			cookie = tx->tx_submit(tx);
-			if (dma_submit_error(cookie)) {
-				ret = -ENOMEM;
-				goto err;
-			}
-			src_offset += (loop_len - 1);
-			dst_offset += (loop_len - 1);
-			src_dma_addr += (loop_len - 1);
-			dst_dma_addr += (loop_len - 1);
-			remaining_len -= (loop_len - 1);
-			loop_len = remaining_len;
-
-			/* Step 2) DMA: 1 BYTES */
-			tx = dev->device_prep_dma_memcpy(chan, dst_dma_addr,
-					src_dma_addr, loop_len, 0);
-			if (!tx) {
-				ret = -ENOMEM;
-				goto err;
-			}
-			cookie = tx->tx_submit(tx);
-			if (dma_submit_error(cookie)) {
-				ret = -ENOMEM;
-				goto err;
-			}
-			dma_async_issue_pending(chan);
-		} else {
-			tx = dev->device_prep_dma_memcpy(chan, dst_dma_addr,
-					src_dma_addr, loop_len, 0);
-			if (!tx) {
-				ret = -ENOMEM;
-				goto err;
-			}
-			cookie = tx->tx_submit(tx);
-			if (dma_submit_error(cookie)) {
-				ret = -ENOMEM;
-				goto err;
-			}
-		}
-		src_offset += loop_len;
-		dst_offset += loop_len;
-		remaining_len -= loop_len;
-	}
-	return ret;
-err:
-	dev_err(scif_info.mdev.this_device,
-		"%s %d Desc Prog Failed ret %d\n",
-		__func__, __LINE__, ret);
-	return ret;
-}
-
-/*
- * scif_rma_list_dma_copy_aligned:
- *
- * Traverse all the windows and perform DMA copy.
- */
-static int scif_rma_list_dma_copy_aligned(struct scif_copy_work *work,
-					  struct dma_chan *chan)
-{
-	dma_addr_t src_dma_addr, dst_dma_addr;
-	size_t loop_len, remaining_len, tail_len, src_contig_bytes = 0;
-	size_t dst_contig_bytes = 0;
-	int src_cache_off;
-	s64 end_src_offset, end_dst_offset;
-	struct scif_window_iter src_win_iter;
-	struct scif_window_iter dst_win_iter;
-	void *src_virt, *dst_virt;
-	struct scif_window *src_window = work->src_window;
-	struct scif_window *dst_window = work->dst_window;
-	s64 src_offset = work->src_offset, dst_offset = work->dst_offset;
-	int ret = 0;
-	struct dma_async_tx_descriptor *tx;
-	struct dma_device *dev = chan->device;
-	dma_cookie_t cookie;
-
-	remaining_len = work->len;
-	scif_init_window_iter(src_window, &src_win_iter);
-	scif_init_window_iter(dst_window, &dst_win_iter);
-
-	src_cache_off = src_offset & (L1_CACHE_BYTES - 1);
-	if (src_cache_off != 0) {
-		/* Head */
-		loop_len = L1_CACHE_BYTES - src_cache_off;
-		loop_len = min(loop_len, remaining_len);
-		src_dma_addr = __scif_off_to_dma_addr(src_window, src_offset);
-		dst_dma_addr = __scif_off_to_dma_addr(dst_window, dst_offset);
-		if (src_window->type == SCIF_WINDOW_SELF)
-			src_virt = _get_local_va(src_offset, src_window,
-						 loop_len);
-		else
-			src_virt = ioremap_remote(src_offset, src_window,
-						  loop_len,
-						  work->remote_dev, NULL);
-		if (!src_virt)
-			return -ENOMEM;
-		if (dst_window->type == SCIF_WINDOW_SELF)
-			dst_virt = _get_local_va(dst_offset, dst_window,
-						 loop_len);
-		else
-			dst_virt = ioremap_remote(dst_offset, dst_window,
-						  loop_len,
-						  work->remote_dev, NULL);
-		if (!dst_virt) {
-			if (src_window->type != SCIF_WINDOW_SELF)
-				iounmap_remote(src_virt, loop_len, work);
-			return -ENOMEM;
-		}
-		if (src_window->type == SCIF_WINDOW_SELF)
-			scif_unaligned_cpy_toio(dst_virt, src_virt, loop_len,
-						remaining_len == loop_len ?
-						work->ordered : false);
-		else
-			scif_unaligned_cpy_fromio(dst_virt, src_virt, loop_len,
-						  remaining_len == loop_len ?
-						  work->ordered : false);
-		if (src_window->type != SCIF_WINDOW_SELF)
-			iounmap_remote(src_virt, loop_len, work);
-		if (dst_window->type != SCIF_WINDOW_SELF)
-			iounmap_remote(dst_virt, loop_len, work);
-		src_offset += loop_len;
-		dst_offset += loop_len;
-		remaining_len -= loop_len;
-	}
-
-	end_src_offset = src_window->offset +
-		(src_window->nr_pages << PAGE_SHIFT);
-	end_dst_offset = dst_window->offset +
-		(dst_window->nr_pages << PAGE_SHIFT);
-	tail_len = remaining_len & (L1_CACHE_BYTES - 1);
-	remaining_len -= tail_len;
-	while (remaining_len) {
-		if (src_offset == end_src_offset) {
-			src_window = list_next_entry(src_window, list);
-			end_src_offset = src_window->offset +
-				(src_window->nr_pages << PAGE_SHIFT);
-			scif_init_window_iter(src_window, &src_win_iter);
-		}
-		if (dst_offset == end_dst_offset) {
-			dst_window = list_next_entry(dst_window, list);
-			end_dst_offset = dst_window->offset +
-				(dst_window->nr_pages << PAGE_SHIFT);
-			scif_init_window_iter(dst_window, &dst_win_iter);
-		}
-
-		/* compute dma addresses for transfer */
-		src_dma_addr = scif_off_to_dma_addr(src_window, src_offset,
-						    &src_contig_bytes,
-						    &src_win_iter);
-		dst_dma_addr = scif_off_to_dma_addr(dst_window, dst_offset,
-						    &dst_contig_bytes,
-						    &dst_win_iter);
-		loop_len = min(src_contig_bytes, dst_contig_bytes);
-		loop_len = min(loop_len, remaining_len);
-		if (work->ordered && !tail_len &&
-		    !(remaining_len - loop_len)) {
-			/*
-			 * Break up the last chunk of the transfer into two
-			 * steps. if there is no tail to gurantee DMA ordering.
-			 * Passing SCIF_DMA_POLLING inserts a status update
-			 * descriptor in step 1 which acts as a double sided
-			 * synchronization fence for the DMA engine to ensure
-			 * that the last cache line in step 2 is updated last.
-			 */
-			/* Step 1) DMA: Body Length - L1_CACHE_BYTES. */
-			tx = dev->device_prep_dma_memcpy(chan, dst_dma_addr,
-							 src_dma_addr,
-							 loop_len -
-							 L1_CACHE_BYTES,
-							 DMA_PREP_FENCE);
-			if (!tx) {
-				ret = -ENOMEM;
-				goto err;
-			}
-			cookie = tx->tx_submit(tx);
-			if (dma_submit_error(cookie)) {
-				ret = -ENOMEM;
-				goto err;
-			}
-			dma_async_issue_pending(chan);
-			src_offset += (loop_len - L1_CACHE_BYTES);
-			dst_offset += (loop_len - L1_CACHE_BYTES);
-			src_dma_addr += (loop_len - L1_CACHE_BYTES);
-			dst_dma_addr += (loop_len - L1_CACHE_BYTES);
-			remaining_len -= (loop_len - L1_CACHE_BYTES);
-			loop_len = remaining_len;
-
-			/* Step 2) DMA: L1_CACHE_BYTES */
-			tx = dev->device_prep_dma_memcpy(chan, dst_dma_addr,
-							 src_dma_addr,
-							 loop_len, 0);
-			if (!tx) {
-				ret = -ENOMEM;
-				goto err;
-			}
-			cookie = tx->tx_submit(tx);
-			if (dma_submit_error(cookie)) {
-				ret = -ENOMEM;
-				goto err;
-			}
-			dma_async_issue_pending(chan);
-		} else {
-			tx = dev->device_prep_dma_memcpy(chan, dst_dma_addr,
-							 src_dma_addr,
-							 loop_len, 0);
-			if (!tx) {
-				ret = -ENOMEM;
-				goto err;
-			}
-			cookie = tx->tx_submit(tx);
-			if (dma_submit_error(cookie)) {
-				ret = -ENOMEM;
-				goto err;
-			}
-			dma_async_issue_pending(chan);
-		}
-		src_offset += loop_len;
-		dst_offset += loop_len;
-		remaining_len -= loop_len;
-	}
-	remaining_len = tail_len;
-	if (remaining_len) {
-		loop_len = remaining_len;
-		if (src_offset == end_src_offset)
-			src_window = list_next_entry(src_window, list);
-		if (dst_offset == end_dst_offset)
-			dst_window = list_next_entry(dst_window, list);
-
-		src_dma_addr = __scif_off_to_dma_addr(src_window, src_offset);
-		dst_dma_addr = __scif_off_to_dma_addr(dst_window, dst_offset);
-		/*
-		 * The CPU copy for the tail bytes must be initiated only once
-		 * previous DMA transfers for this endpoint have completed to
-		 * guarantee ordering.
-		 */
-		if (work->ordered) {
-			struct scif_dev *rdev = work->remote_dev;
-
-			ret = scif_drain_dma_poll(rdev->sdev, chan);
-			if (ret)
-				return ret;
-		}
-		if (src_window->type == SCIF_WINDOW_SELF)
-			src_virt = _get_local_va(src_offset, src_window,
-						 loop_len);
-		else
-			src_virt = ioremap_remote(src_offset, src_window,
-						  loop_len,
-						  work->remote_dev, NULL);
-		if (!src_virt)
-			return -ENOMEM;
-
-		if (dst_window->type == SCIF_WINDOW_SELF)
-			dst_virt = _get_local_va(dst_offset, dst_window,
-						 loop_len);
-		else
-			dst_virt = ioremap_remote(dst_offset, dst_window,
-						  loop_len,
-						  work->remote_dev, NULL);
-		if (!dst_virt) {
-			if (src_window->type != SCIF_WINDOW_SELF)
-				iounmap_remote(src_virt, loop_len, work);
-			return -ENOMEM;
-		}
-
-		if (src_window->type == SCIF_WINDOW_SELF)
-			scif_unaligned_cpy_toio(dst_virt, src_virt, loop_len,
-						work->ordered);
-		else
-			scif_unaligned_cpy_fromio(dst_virt, src_virt,
-						  loop_len, work->ordered);
-		if (src_window->type != SCIF_WINDOW_SELF)
-			iounmap_remote(src_virt, loop_len, work);
-
-		if (dst_window->type != SCIF_WINDOW_SELF)
-			iounmap_remote(dst_virt, loop_len, work);
-		remaining_len -= loop_len;
-	}
-	return ret;
-err:
-	dev_err(scif_info.mdev.this_device,
-		"%s %d Desc Prog Failed ret %d\n",
-		__func__, __LINE__, ret);
-	return ret;
-}
-
-/*
- * scif_rma_list_cpu_copy:
- *
- * Traverse all the windows and perform CPU copy.
- */
-static int scif_rma_list_cpu_copy(struct scif_copy_work *work)
-{
-	void *src_virt, *dst_virt;
-	size_t loop_len, remaining_len;
-	int src_page_off, dst_page_off;
-	s64 src_offset = work->src_offset, dst_offset = work->dst_offset;
-	struct scif_window *src_window = work->src_window;
-	struct scif_window *dst_window = work->dst_window;
-	s64 end_src_offset, end_dst_offset;
-	int ret = 0;
-	struct scif_window_iter src_win_iter;
-	struct scif_window_iter dst_win_iter;
-
-	remaining_len = work->len;
-
-	scif_init_window_iter(src_window, &src_win_iter);
-	scif_init_window_iter(dst_window, &dst_win_iter);
-	while (remaining_len) {
-		src_page_off = src_offset & ~PAGE_MASK;
-		dst_page_off = dst_offset & ~PAGE_MASK;
-		loop_len = min(PAGE_SIZE -
-			       max(src_page_off, dst_page_off),
-			       remaining_len);
-
-		if (src_window->type == SCIF_WINDOW_SELF)
-			src_virt = _get_local_va(src_offset, src_window,
-						 loop_len);
-		else
-			src_virt = ioremap_remote(src_offset, src_window,
-						  loop_len,
-						  work->remote_dev,
-						  &src_win_iter);
-		if (!src_virt) {
-			ret = -ENOMEM;
-			goto error;
-		}
-
-		if (dst_window->type == SCIF_WINDOW_SELF)
-			dst_virt = _get_local_va(dst_offset, dst_window,
-						 loop_len);
-		else
-			dst_virt = ioremap_remote(dst_offset, dst_window,
-						  loop_len,
-						  work->remote_dev,
-						  &dst_win_iter);
-		if (!dst_virt) {
-			if (src_window->type == SCIF_WINDOW_PEER)
-				iounmap_remote(src_virt, loop_len, work);
-			ret = -ENOMEM;
-			goto error;
-		}
-
-		if (work->loopback) {
-			memcpy(dst_virt, src_virt, loop_len);
-		} else {
-			if (src_window->type == SCIF_WINDOW_SELF)
-				memcpy_toio((void __iomem __force *)dst_virt,
-					    src_virt, loop_len);
-			else
-				memcpy_fromio(dst_virt,
-					      (void __iomem __force *)src_virt,
-					      loop_len);
-		}
-		if (src_window->type == SCIF_WINDOW_PEER)
-			iounmap_remote(src_virt, loop_len, work);
-
-		if (dst_window->type == SCIF_WINDOW_PEER)
-			iounmap_remote(dst_virt, loop_len, work);
-
-		src_offset += loop_len;
-		dst_offset += loop_len;
-		remaining_len -= loop_len;
-		if (remaining_len) {
-			end_src_offset = src_window->offset +
-				(src_window->nr_pages << PAGE_SHIFT);
-			end_dst_offset = dst_window->offset +
-				(dst_window->nr_pages << PAGE_SHIFT);
-			if (src_offset == end_src_offset) {
-				src_window = list_next_entry(src_window, list);
-				scif_init_window_iter(src_window,
-						      &src_win_iter);
-			}
-			if (dst_offset == end_dst_offset) {
-				dst_window = list_next_entry(dst_window, list);
-				scif_init_window_iter(dst_window,
-						      &dst_win_iter);
-			}
-		}
-	}
-error:
-	return ret;
-}
-
-static int scif_rma_list_dma_copy_wrapper(struct scif_endpt *epd,
-					  struct scif_copy_work *work,
-					  struct dma_chan *chan, off_t loffset)
-{
-	int src_cache_off, dst_cache_off;
-	s64 src_offset = work->src_offset, dst_offset = work->dst_offset;
-	u8 *temp = NULL;
-	bool src_local = true;
-	struct scif_dma_comp_cb *comp_cb;
-	int err;
-
-	if (is_dma_copy_aligned(chan->device, 1, 1, 1))
-		return _scif_rma_list_dma_copy_aligned(work, chan);
-
-	src_cache_off = src_offset & (L1_CACHE_BYTES - 1);
-	dst_cache_off = dst_offset & (L1_CACHE_BYTES - 1);
-
-	if (dst_cache_off == src_cache_off)
-		return scif_rma_list_dma_copy_aligned(work, chan);
-
-	if (work->loopback)
-		return scif_rma_list_cpu_copy(work);
-	src_local = work->src_window->type == SCIF_WINDOW_SELF;
-
-	/* Allocate dma_completion cb */
-	comp_cb = kzalloc(sizeof(*comp_cb), GFP_KERNEL);
-	if (!comp_cb)
-		goto error;
-
-	work->comp_cb = comp_cb;
-	comp_cb->cb_cookie = comp_cb;
-	comp_cb->dma_completion_func = &scif_rma_completion_cb;
-
-	if (work->len + (L1_CACHE_BYTES << 1) < SCIF_KMEM_UNALIGNED_BUF_SIZE) {
-		comp_cb->is_cache = false;
-		/* Allocate padding bytes to align to a cache line */
-		temp = kmalloc(work->len + (L1_CACHE_BYTES << 1),
-			       GFP_KERNEL);
-		if (!temp)
-			goto free_comp_cb;
-		comp_cb->temp_buf_to_free = temp;
-		/* kmalloc(..) does not guarantee cache line alignment */
-		if (!IS_ALIGNED((u64)temp, L1_CACHE_BYTES))
-			temp = PTR_ALIGN(temp, L1_CACHE_BYTES);
-	} else {
-		comp_cb->is_cache = true;
-		temp = kmem_cache_alloc(unaligned_cache, GFP_KERNEL);
-		if (!temp)
-			goto free_comp_cb;
-		comp_cb->temp_buf_to_free = temp;
-	}
-
-	if (src_local) {
-		temp += dst_cache_off;
-		scif_rma_local_cpu_copy(work->src_offset, work->src_window,
-					temp, work->len, true);
-	} else {
-		comp_cb->dst_window = work->dst_window;
-		comp_cb->dst_offset = work->dst_offset;
-		work->src_offset = work->src_offset - src_cache_off;
-		comp_cb->len = work->len;
-		work->len = ALIGN(work->len + src_cache_off, L1_CACHE_BYTES);
-		comp_cb->header_padding = src_cache_off;
-	}
-	comp_cb->temp_buf = temp;
-
-	err = scif_map_single(&comp_cb->temp_phys, temp,
-			      work->remote_dev, SCIF_KMEM_UNALIGNED_BUF_SIZE);
-	if (err)
-		goto free_temp_buf;
-	comp_cb->sdev = work->remote_dev;
-	if (scif_rma_list_dma_copy_unaligned(work, temp, chan, src_local) < 0)
-		goto free_temp_buf;
-	if (!src_local)
-		work->fence_type = SCIF_DMA_INTR;
-	return 0;
-free_temp_buf:
-	if (comp_cb->is_cache)
-		kmem_cache_free(unaligned_cache, comp_cb->temp_buf_to_free);
-	else
-		kfree(comp_cb->temp_buf_to_free);
-free_comp_cb:
-	kfree(comp_cb);
-error:
-	return -ENOMEM;
-}
-
-/**
- * scif_rma_copy:
- * @epd: end point descriptor.
- * @loffset: offset in local registered address space to/from which to copy
- * @addr: user virtual address to/from which to copy
- * @len: length of range to copy
- * @roffset: offset in remote registered address space to/from which to copy
- * @flags: flags
- * @dir: LOCAL->REMOTE or vice versa.
- * @last_chunk: true if this is the last chunk of a larger transfer
- *
- * Validate parameters, check if src/dst registered ranges requested for copy
- * are valid and initiate either CPU or DMA copy.
- */
-static int scif_rma_copy(scif_epd_t epd, off_t loffset, unsigned long addr,
-			 size_t len, off_t roffset, int flags,
-			 enum scif_rma_dir dir, bool last_chunk)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)epd;
-	struct scif_rma_req remote_req;
-	struct scif_rma_req req;
-	struct scif_window *local_window = NULL;
-	struct scif_window *remote_window = NULL;
-	struct scif_copy_work copy_work;
-	bool loopback;
-	int err = 0;
-	struct dma_chan *chan;
-	struct scif_mmu_notif *mmn = NULL;
-	bool cache = false;
-	struct device *spdev;
-
-	err = scif_verify_epd(ep);
-	if (err)
-		return err;
-
-	if (flags && !(flags & (SCIF_RMA_USECPU | SCIF_RMA_USECACHE |
-				SCIF_RMA_SYNC | SCIF_RMA_ORDERED)))
-		return -EINVAL;
-
-	loopback = scifdev_self(ep->remote_dev) ? true : false;
-	copy_work.fence_type = ((flags & SCIF_RMA_SYNC) && last_chunk) ?
-				SCIF_DMA_POLL : 0;
-	copy_work.ordered = !!((flags & SCIF_RMA_ORDERED) && last_chunk);
-
-	/* Use CPU for Mgmt node <-> Mgmt node copies */
-	if (loopback && scif_is_mgmt_node()) {
-		flags |= SCIF_RMA_USECPU;
-		copy_work.fence_type = 0x0;
-	}
-
-	cache = scif_is_set_reg_cache(flags);
-
-	remote_req.out_window = &remote_window;
-	remote_req.offset = roffset;
-	remote_req.nr_bytes = len;
-	/*
-	 * If transfer is from local to remote then the remote window
-	 * must be writeable and vice versa.
-	 */
-	remote_req.prot = dir == SCIF_LOCAL_TO_REMOTE ? VM_WRITE : VM_READ;
-	remote_req.type = SCIF_WINDOW_PARTIAL;
-	remote_req.head = &ep->rma_info.remote_reg_list;
-
-	spdev = scif_get_peer_dev(ep->remote_dev);
-	if (IS_ERR(spdev)) {
-		err = PTR_ERR(spdev);
-		return err;
-	}
-
-	if (addr && cache) {
-		mutex_lock(&ep->rma_info.mmn_lock);
-		mmn = scif_find_mmu_notifier(current->mm, &ep->rma_info);
-		if (!mmn)
-			mmn = scif_add_mmu_notifier(current->mm, ep);
-		mutex_unlock(&ep->rma_info.mmn_lock);
-		if (IS_ERR(mmn)) {
-			scif_put_peer_dev(spdev);
-			return PTR_ERR(mmn);
-		}
-		cache = cache && !scif_rma_tc_can_cache(ep, len);
-	}
-	mutex_lock(&ep->rma_info.rma_lock);
-	if (addr) {
-		req.out_window = &local_window;
-		req.nr_bytes = ALIGN(len + (addr & ~PAGE_MASK),
-				     PAGE_SIZE);
-		req.va_for_temp = addr & PAGE_MASK;
-		req.prot = (dir == SCIF_LOCAL_TO_REMOTE ?
-			    VM_READ : VM_WRITE | VM_READ);
-		/* Does a valid local window exist? */
-		if (mmn) {
-			spin_lock(&ep->rma_info.tc_lock);
-			req.head = &mmn->tc_reg_list;
-			err = scif_query_tcw(ep, &req);
-			spin_unlock(&ep->rma_info.tc_lock);
-		}
-		if (!mmn || err) {
-			err = scif_register_temp(epd, req.va_for_temp,
-						 req.nr_bytes, req.prot,
-						 &loffset, &local_window);
-			if (err) {
-				mutex_unlock(&ep->rma_info.rma_lock);
-				goto error;
-			}
-			if (!cache)
-				goto skip_cache;
-			atomic_inc(&ep->rma_info.tcw_refcount);
-			atomic_add_return(local_window->nr_pages,
-					  &ep->rma_info.tcw_total_pages);
-			if (mmn) {
-				spin_lock(&ep->rma_info.tc_lock);
-				scif_insert_tcw(local_window,
-						&mmn->tc_reg_list);
-				spin_unlock(&ep->rma_info.tc_lock);
-			}
-		}
-skip_cache:
-		loffset = local_window->offset +
-				(addr - local_window->va_for_temp);
-	} else {
-		req.out_window = &local_window;
-		req.offset = loffset;
-		/*
-		 * If transfer is from local to remote then the self window
-		 * must be readable and vice versa.
-		 */
-		req.prot = dir == SCIF_LOCAL_TO_REMOTE ? VM_READ : VM_WRITE;
-		req.nr_bytes = len;
-		req.type = SCIF_WINDOW_PARTIAL;
-		req.head = &ep->rma_info.reg_list;
-		/* Does a valid local window exist? */
-		err = scif_query_window(&req);
-		if (err) {
-			mutex_unlock(&ep->rma_info.rma_lock);
-			goto error;
-		}
-	}
-
-	/* Does a valid remote window exist? */
-	err = scif_query_window(&remote_req);
-	if (err) {
-		mutex_unlock(&ep->rma_info.rma_lock);
-		goto error;
-	}
-
-	/*
-	 * Prepare copy_work for submitting work to the DMA kernel thread
-	 * or CPU copy routine.
-	 */
-	copy_work.len = len;
-	copy_work.loopback = loopback;
-	copy_work.remote_dev = ep->remote_dev;
-	if (dir == SCIF_LOCAL_TO_REMOTE) {
-		copy_work.src_offset = loffset;
-		copy_work.src_window = local_window;
-		copy_work.dst_offset = roffset;
-		copy_work.dst_window = remote_window;
-	} else {
-		copy_work.src_offset = roffset;
-		copy_work.src_window = remote_window;
-		copy_work.dst_offset = loffset;
-		copy_work.dst_window = local_window;
-	}
-
-	if (flags & SCIF_RMA_USECPU) {
-		scif_rma_list_cpu_copy(&copy_work);
-	} else {
-		chan = ep->rma_info.dma_chan;
-		err = scif_rma_list_dma_copy_wrapper(epd, &copy_work,
-						     chan, loffset);
-	}
-	if (addr && !cache)
-		atomic_inc(&ep->rma_info.tw_refcount);
-
-	mutex_unlock(&ep->rma_info.rma_lock);
-
-	if (last_chunk) {
-		struct scif_dev *rdev = ep->remote_dev;
-
-		if (copy_work.fence_type == SCIF_DMA_POLL)
-			err = scif_drain_dma_poll(rdev->sdev,
-						  ep->rma_info.dma_chan);
-		else if (copy_work.fence_type == SCIF_DMA_INTR)
-			err = scif_drain_dma_intr(rdev->sdev,
-						  ep->rma_info.dma_chan);
-	}
-
-	if (addr && !cache)
-		scif_queue_for_cleanup(local_window, &scif_info.rma);
-	scif_put_peer_dev(spdev);
-	return err;
-error:
-	if (err) {
-		if (addr && local_window && !cache)
-			scif_destroy_window(ep, local_window);
-		dev_err(scif_info.mdev.this_device,
-			"%s %d err %d len 0x%lx\n",
-			__func__, __LINE__, err, len);
-	}
-	scif_put_peer_dev(spdev);
-	return err;
-}
-
-int scif_readfrom(scif_epd_t epd, off_t loffset, size_t len,
-		  off_t roffset, int flags)
-{
-	int err;
-
-	dev_dbg(scif_info.mdev.this_device,
-		"SCIFAPI readfrom: ep %p loffset 0x%lx len 0x%lx offset 0x%lx flags 0x%x\n",
-		epd, loffset, len, roffset, flags);
-	if (scif_unaligned(loffset, roffset)) {
-		while (len > SCIF_MAX_UNALIGNED_BUF_SIZE) {
-			err = scif_rma_copy(epd, loffset, 0x0,
-					    SCIF_MAX_UNALIGNED_BUF_SIZE,
-					    roffset, flags,
-					    SCIF_REMOTE_TO_LOCAL, false);
-			if (err)
-				goto readfrom_err;
-			loffset += SCIF_MAX_UNALIGNED_BUF_SIZE;
-			roffset += SCIF_MAX_UNALIGNED_BUF_SIZE;
-			len -= SCIF_MAX_UNALIGNED_BUF_SIZE;
-		}
-	}
-	err = scif_rma_copy(epd, loffset, 0x0, len,
-			    roffset, flags, SCIF_REMOTE_TO_LOCAL, true);
-readfrom_err:
-	return err;
-}
-EXPORT_SYMBOL_GPL(scif_readfrom);
-
-int scif_writeto(scif_epd_t epd, off_t loffset, size_t len,
-		 off_t roffset, int flags)
-{
-	int err;
-
-	dev_dbg(scif_info.mdev.this_device,
-		"SCIFAPI writeto: ep %p loffset 0x%lx len 0x%lx roffset 0x%lx flags 0x%x\n",
-		epd, loffset, len, roffset, flags);
-	if (scif_unaligned(loffset, roffset)) {
-		while (len > SCIF_MAX_UNALIGNED_BUF_SIZE) {
-			err = scif_rma_copy(epd, loffset, 0x0,
-					    SCIF_MAX_UNALIGNED_BUF_SIZE,
-					    roffset, flags,
-					    SCIF_LOCAL_TO_REMOTE, false);
-			if (err)
-				goto writeto_err;
-			loffset += SCIF_MAX_UNALIGNED_BUF_SIZE;
-			roffset += SCIF_MAX_UNALIGNED_BUF_SIZE;
-			len -= SCIF_MAX_UNALIGNED_BUF_SIZE;
-		}
-	}
-	err = scif_rma_copy(epd, loffset, 0x0, len,
-			    roffset, flags, SCIF_LOCAL_TO_REMOTE, true);
-writeto_err:
-	return err;
-}
-EXPORT_SYMBOL_GPL(scif_writeto);
-
-int scif_vreadfrom(scif_epd_t epd, void *addr, size_t len,
-		   off_t roffset, int flags)
-{
-	int err;
-
-	dev_dbg(scif_info.mdev.this_device,
-		"SCIFAPI vreadfrom: ep %p addr %p len 0x%lx roffset 0x%lx flags 0x%x\n",
-		epd, addr, len, roffset, flags);
-	if (scif_unaligned((off_t __force)addr, roffset)) {
-		if (len > SCIF_MAX_UNALIGNED_BUF_SIZE)
-			flags &= ~SCIF_RMA_USECACHE;
-
-		while (len > SCIF_MAX_UNALIGNED_BUF_SIZE) {
-			err = scif_rma_copy(epd, 0, (u64)addr,
-					    SCIF_MAX_UNALIGNED_BUF_SIZE,
-					    roffset, flags,
-					    SCIF_REMOTE_TO_LOCAL, false);
-			if (err)
-				goto vreadfrom_err;
-			addr += SCIF_MAX_UNALIGNED_BUF_SIZE;
-			roffset += SCIF_MAX_UNALIGNED_BUF_SIZE;
-			len -= SCIF_MAX_UNALIGNED_BUF_SIZE;
-		}
-	}
-	err = scif_rma_copy(epd, 0, (u64)addr, len,
-			    roffset, flags, SCIF_REMOTE_TO_LOCAL, true);
-vreadfrom_err:
-	return err;
-}
-EXPORT_SYMBOL_GPL(scif_vreadfrom);
-
-int scif_vwriteto(scif_epd_t epd, void *addr, size_t len,
-		  off_t roffset, int flags)
-{
-	int err;
-
-	dev_dbg(scif_info.mdev.this_device,
-		"SCIFAPI vwriteto: ep %p addr %p len 0x%lx roffset 0x%lx flags 0x%x\n",
-		epd, addr, len, roffset, flags);
-	if (scif_unaligned((off_t __force)addr, roffset)) {
-		if (len > SCIF_MAX_UNALIGNED_BUF_SIZE)
-			flags &= ~SCIF_RMA_USECACHE;
-
-		while (len > SCIF_MAX_UNALIGNED_BUF_SIZE) {
-			err = scif_rma_copy(epd, 0, (u64)addr,
-					    SCIF_MAX_UNALIGNED_BUF_SIZE,
-					    roffset, flags,
-					    SCIF_LOCAL_TO_REMOTE, false);
-			if (err)
-				goto vwriteto_err;
-			addr += SCIF_MAX_UNALIGNED_BUF_SIZE;
-			roffset += SCIF_MAX_UNALIGNED_BUF_SIZE;
-			len -= SCIF_MAX_UNALIGNED_BUF_SIZE;
-		}
-	}
-	err = scif_rma_copy(epd, 0, (u64)addr, len,
-			    roffset, flags, SCIF_LOCAL_TO_REMOTE, true);
-vwriteto_err:
-	return err;
-}
-EXPORT_SYMBOL_GPL(scif_vwriteto);
diff --git a/drivers/misc/mic/scif/scif_epd.c b/drivers/misc/mic/scif/scif_epd.c
deleted file mode 100644
index 426687f6696b..000000000000
--- a/drivers/misc/mic/scif/scif_epd.c
+++ /dev/null
@@ -1,357 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include "scif_main.h"
-#include "scif_map.h"
-
-void scif_cleanup_ep_qp(struct scif_endpt *ep)
-{
-	struct scif_qp *qp = ep->qp_info.qp;
-
-	if (qp->outbound_q.rb_base) {
-		scif_iounmap((void *)qp->outbound_q.rb_base,
-			     qp->outbound_q.size, ep->remote_dev);
-		qp->outbound_q.rb_base = NULL;
-	}
-	if (qp->remote_qp) {
-		scif_iounmap((void *)qp->remote_qp,
-			     sizeof(struct scif_qp), ep->remote_dev);
-		qp->remote_qp = NULL;
-	}
-	if (qp->local_qp) {
-		scif_unmap_single(qp->local_qp, ep->remote_dev,
-				  sizeof(struct scif_qp));
-		qp->local_qp = 0x0;
-	}
-	if (qp->local_buf) {
-		scif_unmap_single(qp->local_buf, ep->remote_dev,
-				  SCIF_ENDPT_QP_SIZE);
-		qp->local_buf = 0;
-	}
-}
-
-void scif_teardown_ep(void *endpt)
-{
-	struct scif_endpt *ep = endpt;
-	struct scif_qp *qp = ep->qp_info.qp;
-
-	if (qp) {
-		spin_lock(&ep->lock);
-		scif_cleanup_ep_qp(ep);
-		spin_unlock(&ep->lock);
-		kfree(qp->inbound_q.rb_base);
-		kfree(qp);
-	}
-}
-
-/*
- * Enqueue the endpoint to the zombie list for cleanup.
- * The endpoint should not be accessed once this API returns.
- */
-void scif_add_epd_to_zombie_list(struct scif_endpt *ep, bool eplock_held)
-{
-	if (!eplock_held)
-		mutex_lock(&scif_info.eplock);
-	spin_lock(&ep->lock);
-	ep->state = SCIFEP_ZOMBIE;
-	spin_unlock(&ep->lock);
-	list_add_tail(&ep->list, &scif_info.zombie);
-	scif_info.nr_zombies++;
-	if (!eplock_held)
-		mutex_unlock(&scif_info.eplock);
-	schedule_work(&scif_info.misc_work);
-}
-
-static struct scif_endpt *scif_find_listen_ep(u16 port)
-{
-	struct scif_endpt *ep = NULL;
-	struct list_head *pos, *tmpq;
-
-	mutex_lock(&scif_info.eplock);
-	list_for_each_safe(pos, tmpq, &scif_info.listen) {
-		ep = list_entry(pos, struct scif_endpt, list);
-		if (ep->port.port == port) {
-			mutex_unlock(&scif_info.eplock);
-			return ep;
-		}
-	}
-	mutex_unlock(&scif_info.eplock);
-	return NULL;
-}
-
-void scif_cleanup_zombie_epd(void)
-{
-	struct list_head *pos, *tmpq;
-	struct scif_endpt *ep;
-
-	mutex_lock(&scif_info.eplock);
-	list_for_each_safe(pos, tmpq, &scif_info.zombie) {
-		ep = list_entry(pos, struct scif_endpt, list);
-		if (scif_rma_ep_can_uninit(ep)) {
-			list_del(pos);
-			scif_info.nr_zombies--;
-			put_iova_domain(&ep->rma_info.iovad);
-			kfree(ep);
-		}
-	}
-	mutex_unlock(&scif_info.eplock);
-}
-
-/**
- * scif_cnctreq() - Respond to SCIF_CNCT_REQ interrupt message
- * @scifdev:    SCIF device
- * @msg:        Interrupt message
- *
- * This message is initiated by the remote node to request a connection
- * to the local node.  This function looks for an end point in the
- * listen state on the requested port id.
- *
- * If it finds a listening port it places the connect request on the
- * listening end points queue and wakes up any pending accept calls.
- *
- * If it does not find a listening end point it sends a connection
- * reject message to the remote node.
- */
-void scif_cnctreq(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	struct scif_endpt *ep = NULL;
-	struct scif_conreq *conreq;
-
-	conreq = kmalloc(sizeof(*conreq), GFP_KERNEL);
-	if (!conreq)
-		/* Lack of resources so reject the request. */
-		goto conreq_sendrej;
-
-	ep = scif_find_listen_ep(msg->dst.port);
-	if (!ep)
-		/*  Send reject due to no listening ports */
-		goto conreq_sendrej_free;
-	else
-		spin_lock(&ep->lock);
-
-	if (ep->backlog <= ep->conreqcnt) {
-		/*  Send reject due to too many pending requests */
-		spin_unlock(&ep->lock);
-		goto conreq_sendrej_free;
-	}
-
-	conreq->msg = *msg;
-	list_add_tail(&conreq->list, &ep->conlist);
-	ep->conreqcnt++;
-	wake_up_interruptible(&ep->conwq);
-	spin_unlock(&ep->lock);
-	return;
-
-conreq_sendrej_free:
-	kfree(conreq);
-conreq_sendrej:
-	msg->uop = SCIF_CNCT_REJ;
-	scif_nodeqp_send(&scif_dev[msg->src.node], msg);
-}
-
-/**
- * scif_cnctgnt() - Respond to SCIF_CNCT_GNT interrupt message
- * @scifdev:    SCIF device
- * @msg:        Interrupt message
- *
- * An accept() on the remote node has occurred and sent this message
- * to indicate success.  Place the end point in the MAPPING state and
- * save the remote nodes memory information.  Then wake up the connect
- * request so it can finish.
- */
-void scif_cnctgnt(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
-
-	spin_lock(&ep->lock);
-	if (SCIFEP_CONNECTING == ep->state) {
-		ep->peer.node = msg->src.node;
-		ep->peer.port = msg->src.port;
-		ep->qp_info.gnt_pld = msg->payload[1];
-		ep->remote_ep = msg->payload[2];
-		ep->state = SCIFEP_MAPPING;
-
-		wake_up(&ep->conwq);
-	}
-	spin_unlock(&ep->lock);
-}
-
-/**
- * scif_cnctgnt_ack() - Respond to SCIF_CNCT_GNTACK interrupt message
- * @scifdev:    SCIF device
- * @msg:        Interrupt message
- *
- * The remote connection request has finished mapping the local memory.
- * Place the connection in the connected state and wake up the pending
- * accept() call.
- */
-void scif_cnctgnt_ack(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
-
-	mutex_lock(&scif_info.connlock);
-	spin_lock(&ep->lock);
-	/* New ep is now connected with all resources set. */
-	ep->state = SCIFEP_CONNECTED;
-	list_add_tail(&ep->list, &scif_info.connected);
-	wake_up(&ep->conwq);
-	spin_unlock(&ep->lock);
-	mutex_unlock(&scif_info.connlock);
-}
-
-/**
- * scif_cnctgnt_nack() - Respond to SCIF_CNCT_GNTNACK interrupt message
- * @scifdev:    SCIF device
- * @msg:        Interrupt message
- *
- * The remote connection request failed to map the local memory it was sent.
- * Place the end point in the CLOSING state to indicate it and wake up
- * the pending accept();
- */
-void scif_cnctgnt_nack(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
-
-	spin_lock(&ep->lock);
-	ep->state = SCIFEP_CLOSING;
-	wake_up(&ep->conwq);
-	spin_unlock(&ep->lock);
-}
-
-/**
- * scif_cnctrej() - Respond to SCIF_CNCT_REJ interrupt message
- * @scifdev:    SCIF device
- * @msg:        Interrupt message
- *
- * The remote end has rejected the connection request.  Set the end
- * point back to the bound state and wake up the pending connect().
- */
-void scif_cnctrej(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
-
-	spin_lock(&ep->lock);
-	if (SCIFEP_CONNECTING == ep->state) {
-		ep->state = SCIFEP_BOUND;
-		wake_up(&ep->conwq);
-	}
-	spin_unlock(&ep->lock);
-}
-
-/**
- * scif_discnct() - Respond to SCIF_DISCNCT interrupt message
- * @scifdev:    SCIF device
- * @msg:        Interrupt message
- *
- * The remote node has indicated close() has been called on its end
- * point.  Remove the local end point from the connected list, set its
- * state to disconnected and ensure accesses to the remote node are
- * shutdown.
- *
- * When all accesses to the remote end have completed then send a
- * DISCNT_ACK to indicate it can remove its resources and complete
- * the close routine.
- */
-void scif_discnct(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	struct scif_endpt *ep = NULL;
-	struct scif_endpt *tmpep;
-	struct list_head *pos, *tmpq;
-
-	mutex_lock(&scif_info.connlock);
-	list_for_each_safe(pos, tmpq, &scif_info.connected) {
-		tmpep = list_entry(pos, struct scif_endpt, list);
-		/*
-		 * The local ep may have sent a disconnect and and been closed
-		 * due to a message response time out. It may have been
-		 * allocated again and formed a new connection so we want to
-		 * check if the remote ep matches
-		 */
-		if (((u64)tmpep == msg->payload[1]) &&
-		    ((u64)tmpep->remote_ep == msg->payload[0])) {
-			list_del(pos);
-			ep = tmpep;
-			spin_lock(&ep->lock);
-			break;
-		}
-	}
-
-	/*
-	 * If the terminated end is not found then this side started closing
-	 * before the other side sent the disconnect.  If so the ep will no
-	 * longer be on the connected list.  Regardless the other side
-	 * needs to be acked to let it know close is complete.
-	 */
-	if (!ep) {
-		mutex_unlock(&scif_info.connlock);
-		goto discnct_ack;
-	}
-
-	ep->state = SCIFEP_DISCONNECTED;
-	list_add_tail(&ep->list, &scif_info.disconnected);
-
-	wake_up_interruptible(&ep->sendwq);
-	wake_up_interruptible(&ep->recvwq);
-	spin_unlock(&ep->lock);
-	mutex_unlock(&scif_info.connlock);
-
-discnct_ack:
-	msg->uop = SCIF_DISCNT_ACK;
-	scif_nodeqp_send(&scif_dev[msg->src.node], msg);
-}
-
-/**
- * scif_discnct_ack() - Respond to SCIF_DISCNT_ACK interrupt message
- * @scifdev:    SCIF device
- * @msg:        Interrupt message
- *
- * Remote side has indicated it has not more references to local resources
- */
-void scif_discnt_ack(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
-
-	spin_lock(&ep->lock);
-	ep->state = SCIFEP_DISCONNECTED;
-	spin_unlock(&ep->lock);
-	complete(&ep->discon);
-}
-
-/**
- * scif_clientsend() - Respond to SCIF_CLIENT_SEND interrupt message
- * @scifdev:    SCIF device
- * @msg:        Interrupt message
- *
- * Remote side is confirming send or receive interrupt handling is complete.
- */
-void scif_clientsend(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
-
-	spin_lock(&ep->lock);
-	if (SCIFEP_CONNECTED == ep->state)
-		wake_up_interruptible(&ep->recvwq);
-	spin_unlock(&ep->lock);
-}
-
-/**
- * scif_clientrcvd() - Respond to SCIF_CLIENT_RCVD interrupt message
- * @scifdev:    SCIF device
- * @msg:        Interrupt message
- *
- * Remote side is confirming send or receive interrupt handling is complete.
- */
-void scif_clientrcvd(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
-
-	spin_lock(&ep->lock);
-	if (SCIFEP_CONNECTED == ep->state)
-		wake_up_interruptible(&ep->sendwq);
-	spin_unlock(&ep->lock);
-}
diff --git a/drivers/misc/mic/scif/scif_epd.h b/drivers/misc/mic/scif/scif_epd.h
deleted file mode 100644
index 0b9dfe1cc06c..000000000000
--- a/drivers/misc/mic/scif/scif_epd.h
+++ /dev/null
@@ -1,200 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#ifndef SCIF_EPD_H
-#define SCIF_EPD_H
-
-#include <linux/delay.h>
-#include <linux/scif.h>
-#include <linux/scif_ioctl.h>
-
-#define SCIF_EPLOCK_HELD true
-
-enum scif_epd_state {
-	SCIFEP_UNBOUND,
-	SCIFEP_BOUND,
-	SCIFEP_LISTENING,
-	SCIFEP_CONNECTED,
-	SCIFEP_CONNECTING,
-	SCIFEP_MAPPING,
-	SCIFEP_CLOSING,
-	SCIFEP_CLLISTEN,
-	SCIFEP_DISCONNECTED,
-	SCIFEP_ZOMBIE
-};
-
-/*
- * struct scif_conreq - Data structure added to the connection list.
- *
- * @msg: connection request message received
- * @list: link to list of connection requests
- */
-struct scif_conreq {
-	struct scifmsg msg;
-	struct list_head list;
-};
-
-/* Size of the RB for the Endpoint QP */
-#define SCIF_ENDPT_QP_SIZE 0x1000
-
-/*
- * scif_endpt_qp_info - SCIF endpoint queue pair
- *
- * @qp - Qpair for this endpoint
- * @qp_offset - DMA address of the QP
- * @gnt_pld - Payload in a SCIF_CNCT_GNT message containing the
- * physical address of the remote_qp.
- */
-struct scif_endpt_qp_info {
-	struct scif_qp *qp;
-	dma_addr_t qp_offset;
-	dma_addr_t gnt_pld;
-};
-
-/*
- * struct scif_endpt - The SCIF endpoint data structure
- *
- * @state: end point state
- * @lock: lock synchronizing access to endpoint fields like state etc
- * @port: self port information
- * @peer: peer port information
- * @backlog: maximum pending connection requests
- * @qp_info: Endpoint QP information for SCIF messaging
- * @remote_dev: scifdev used by this endpt to communicate with remote node.
- * @remote_ep: remote endpoint
- * @conreqcnt: Keep track of number of connection requests.
- * @files: Open file information used to match the id passed in with
- *         the flush routine.
- * @conlist: list of connection requests
- * @conwq: waitqueue for connection processing
- * @discon: completion used during disconnection
- * @sendwq: waitqueue used during sending messages
- * @recvwq: waitqueue used during message receipt
- * @sendlock: Synchronize ordering of messages sent
- * @recvlock: Synchronize ordering of messages received
- * @list: link to list of various endpoints like connected, listening etc
- * @li_accept: pending ACCEPTREG
- * @acceptcnt: pending ACCEPTREG cnt
- * @liacceptlist: link to listen accept
- * @miacceptlist: link to uaccept
- * @listenep: associated listen ep
- * @conn_work: Non blocking connect work
- * @conn_port: Connection port
- * @conn_err: Errors during connection
- * @conn_async_state: Async connection
- * @conn_pend_wq: Used by poll while waiting for incoming connections
- * @conn_list: List of async connection requests
- * @rma_info: Information for triggering SCIF RMA and DMA operations
- * @mmu_list: link to list of MMU notifier cleanup work
- * @anon: anonymous file for use in kernel mode scif poll
- */
-struct scif_endpt {
-	enum scif_epd_state state;
-	spinlock_t lock;
-	struct scif_port_id port;
-	struct scif_port_id peer;
-	int backlog;
-	struct scif_endpt_qp_info qp_info;
-	struct scif_dev *remote_dev;
-	u64 remote_ep;
-	int conreqcnt;
-	struct files_struct *files;
-	struct list_head conlist;
-	wait_queue_head_t conwq;
-	struct completion discon;
-	wait_queue_head_t sendwq;
-	wait_queue_head_t recvwq;
-	struct mutex sendlock;
-	struct mutex recvlock;
-	struct list_head list;
-	struct list_head li_accept;
-	int acceptcnt;
-	struct list_head liacceptlist;
-	struct list_head miacceptlist;
-	struct scif_endpt *listenep;
-	struct scif_port_id conn_port;
-	int conn_err;
-	int conn_async_state;
-	wait_queue_head_t conn_pend_wq;
-	struct list_head conn_list;
-	struct scif_endpt_rma_info rma_info;
-	struct list_head mmu_list;
-	struct file *anon;
-};
-
-static inline int scifdev_alive(struct scif_endpt *ep)
-{
-	return _scifdev_alive(ep->remote_dev);
-}
-
-/*
- * scif_verify_epd:
- * ep: SCIF endpoint
- *
- * Checks several generic error conditions and returns the
- * appropriate error.
- */
-static inline int scif_verify_epd(struct scif_endpt *ep)
-{
-	if (ep->state == SCIFEP_DISCONNECTED)
-		return -ECONNRESET;
-
-	if (ep->state != SCIFEP_CONNECTED)
-		return -ENOTCONN;
-
-	if (!scifdev_alive(ep))
-		return -ENODEV;
-
-	return 0;
-}
-
-static inline int scif_anon_inode_getfile(scif_epd_t epd)
-{
-	epd->anon = anon_inode_getfile("scif", &scif_anon_fops, NULL, 0);
-
-	return PTR_ERR_OR_ZERO(epd->anon);
-}
-
-static inline void scif_anon_inode_fput(scif_epd_t epd)
-{
-	if (epd->anon) {
-		fput(epd->anon);
-		epd->anon = NULL;
-	}
-}
-
-void scif_cleanup_zombie_epd(void);
-void scif_teardown_ep(void *endpt);
-void scif_cleanup_ep_qp(struct scif_endpt *ep);
-void scif_add_epd_to_zombie_list(struct scif_endpt *ep, bool eplock_held);
-void scif_get_node_info(void);
-void scif_send_acks(struct scif_dev *dev);
-void scif_conn_handler(struct work_struct *work);
-int scif_rsrv_port(u16 port);
-void scif_get_port(u16 port);
-int scif_get_new_port(void);
-void scif_put_port(u16 port);
-int scif_user_send(scif_epd_t epd, void __user *msg, int len, int flags);
-int scif_user_recv(scif_epd_t epd, void __user *msg, int len, int flags);
-void scif_cnctreq(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_cnctgnt(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_cnctgnt_ack(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_cnctgnt_nack(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_cnctrej(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_discnct(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_discnt_ack(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_clientsend(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_clientrcvd(struct scif_dev *scifdev, struct scifmsg *msg);
-int __scif_connect(scif_epd_t epd, struct scif_port_id *dst, bool non_block);
-int __scif_flush(scif_epd_t epd);
-int scif_mmap(struct vm_area_struct *vma, scif_epd_t epd);
-__poll_t __scif_pollfd(struct file *f, poll_table *wait,
-			   struct scif_endpt *ep);
-int __scif_pin_pages(void *addr, size_t len, int *out_prot,
-		     int map_flags, scif_pinned_pages_t *pages);
-#endif /* SCIF_EPD_H */
diff --git a/drivers/misc/mic/scif/scif_fd.c b/drivers/misc/mic/scif/scif_fd.c
deleted file mode 100644
index 3f08646cd78a..000000000000
--- a/drivers/misc/mic/scif/scif_fd.c
+++ /dev/null
@@ -1,462 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include "scif_main.h"
-
-static int scif_fdopen(struct inode *inode, struct file *f)
-{
-	struct scif_endpt *priv = scif_open();
-
-	if (!priv)
-		return -ENOMEM;
-	f->private_data = priv;
-	return 0;
-}
-
-static int scif_fdclose(struct inode *inode, struct file *f)
-{
-	struct scif_endpt *priv = f->private_data;
-
-	return scif_close(priv);
-}
-
-static int scif_fdmmap(struct file *f, struct vm_area_struct *vma)
-{
-	struct scif_endpt *priv = f->private_data;
-
-	return scif_mmap(vma, priv);
-}
-
-static __poll_t scif_fdpoll(struct file *f, poll_table *wait)
-{
-	struct scif_endpt *priv = f->private_data;
-
-	return __scif_pollfd(f, wait, priv);
-}
-
-static int scif_fdflush(struct file *f, fl_owner_t id)
-{
-	struct scif_endpt *ep = f->private_data;
-
-	spin_lock(&ep->lock);
-	/*
-	 * The listening endpoint stashes the open file information before
-	 * waiting for incoming connections. The release callback would never be
-	 * called if the application closed the endpoint, while waiting for
-	 * incoming connections from a separate thread since the file descriptor
-	 * reference count is bumped up in the accept IOCTL. Call the flush
-	 * routine if the id matches the endpoint open file information so that
-	 * the listening endpoint can be woken up and the fd released.
-	 */
-	if (ep->files == id)
-		__scif_flush(ep);
-	spin_unlock(&ep->lock);
-	return 0;
-}
-
-static __always_inline void scif_err_debug(int err, const char *str)
-{
-	/*
-	 * ENOTCONN is a common uninteresting error which is
-	 * flooding debug messages to the console unnecessarily.
-	 */
-	if (err < 0 && err != -ENOTCONN)
-		dev_dbg(scif_info.mdev.this_device, "%s err %d\n", str, err);
-}
-
-static long scif_fdioctl(struct file *f, unsigned int cmd, unsigned long arg)
-{
-	struct scif_endpt *priv = f->private_data;
-	void __user *argp = (void __user *)arg;
-	int err = 0;
-	struct scifioctl_msg request;
-	bool non_block = false;
-
-	non_block = !!(f->f_flags & O_NONBLOCK);
-
-	switch (cmd) {
-	case SCIF_BIND:
-	{
-		int pn;
-
-		if (copy_from_user(&pn, argp, sizeof(pn)))
-			return -EFAULT;
-
-		pn = scif_bind(priv, pn);
-		if (pn < 0)
-			return pn;
-
-		if (copy_to_user(argp, &pn, sizeof(pn)))
-			return -EFAULT;
-
-		return 0;
-	}
-	case SCIF_LISTEN:
-		return scif_listen(priv, arg);
-	case SCIF_CONNECT:
-	{
-		struct scifioctl_connect req;
-		struct scif_endpt *ep = (struct scif_endpt *)priv;
-
-		if (copy_from_user(&req, argp, sizeof(req)))
-			return -EFAULT;
-
-		err = __scif_connect(priv, &req.peer, non_block);
-		if (err < 0)
-			return err;
-
-		req.self.node = ep->port.node;
-		req.self.port = ep->port.port;
-
-		if (copy_to_user(argp, &req, sizeof(req)))
-			return -EFAULT;
-
-		return 0;
-	}
-	/*
-	 * Accept is done in two halves.  The request ioctl does the basic
-	 * functionality of accepting the request and returning the information
-	 * about it including the internal ID of the end point.  The register
-	 * is done with the internal ID on a new file descriptor opened by the
-	 * requesting process.
-	 */
-	case SCIF_ACCEPTREQ:
-	{
-		struct scifioctl_accept request;
-		scif_epd_t *ep = (scif_epd_t *)&request.endpt;
-
-		if (copy_from_user(&request, argp, sizeof(request)))
-			return -EFAULT;
-
-		err = scif_accept(priv, &request.peer, ep, request.flags);
-		if (err < 0)
-			return err;
-
-		if (copy_to_user(argp, &request, sizeof(request))) {
-			scif_close(*ep);
-			return -EFAULT;
-		}
-		/*
-		 * Add to the list of user mode eps where the second half
-		 * of the accept is not yet completed.
-		 */
-		mutex_lock(&scif_info.eplock);
-		list_add_tail(&((*ep)->miacceptlist), &scif_info.uaccept);
-		list_add_tail(&((*ep)->liacceptlist), &priv->li_accept);
-		(*ep)->listenep = priv;
-		priv->acceptcnt++;
-		mutex_unlock(&scif_info.eplock);
-
-		return 0;
-	}
-	case SCIF_ACCEPTREG:
-	{
-		struct scif_endpt *priv = f->private_data;
-		struct scif_endpt *newep;
-		struct scif_endpt *lisep;
-		struct scif_endpt *fep = NULL;
-		struct scif_endpt *tmpep;
-		struct list_head *pos, *tmpq;
-
-		/* Finally replace the pointer to the accepted endpoint */
-		if (copy_from_user(&newep, argp, sizeof(void *)))
-			return -EFAULT;
-
-		/* Remove form the user accept queue */
-		mutex_lock(&scif_info.eplock);
-		list_for_each_safe(pos, tmpq, &scif_info.uaccept) {
-			tmpep = list_entry(pos,
-					   struct scif_endpt, miacceptlist);
-			if (tmpep == newep) {
-				list_del(pos);
-				fep = tmpep;
-				break;
-			}
-		}
-
-		if (!fep) {
-			mutex_unlock(&scif_info.eplock);
-			return -ENOENT;
-		}
-
-		lisep = newep->listenep;
-		list_for_each_safe(pos, tmpq, &lisep->li_accept) {
-			tmpep = list_entry(pos,
-					   struct scif_endpt, liacceptlist);
-			if (tmpep == newep) {
-				list_del(pos);
-				lisep->acceptcnt--;
-				break;
-			}
-		}
-
-		mutex_unlock(&scif_info.eplock);
-
-		/* Free the resources automatically created from the open. */
-		scif_anon_inode_fput(priv);
-		scif_teardown_ep(priv);
-		scif_add_epd_to_zombie_list(priv, !SCIF_EPLOCK_HELD);
-		f->private_data = newep;
-		return 0;
-	}
-	case SCIF_SEND:
-	{
-		struct scif_endpt *priv = f->private_data;
-
-		if (copy_from_user(&request, argp,
-				   sizeof(struct scifioctl_msg))) {
-			err = -EFAULT;
-			goto send_err;
-		}
-		err = scif_user_send(priv, (void __user *)request.msg,
-				     request.len, request.flags);
-		if (err < 0)
-			goto send_err;
-		if (copy_to_user(&
-				 ((struct scifioctl_msg __user *)argp)->out_len,
-				 &err, sizeof(err))) {
-			err = -EFAULT;
-			goto send_err;
-		}
-		err = 0;
-send_err:
-		scif_err_debug(err, "scif_send");
-		return err;
-	}
-	case SCIF_RECV:
-	{
-		struct scif_endpt *priv = f->private_data;
-
-		if (copy_from_user(&request, argp,
-				   sizeof(struct scifioctl_msg))) {
-			err = -EFAULT;
-			goto recv_err;
-		}
-
-		err = scif_user_recv(priv, (void __user *)request.msg,
-				     request.len, request.flags);
-		if (err < 0)
-			goto recv_err;
-
-		if (copy_to_user(&
-				 ((struct scifioctl_msg __user *)argp)->out_len,
-			&err, sizeof(err))) {
-			err = -EFAULT;
-			goto recv_err;
-		}
-		err = 0;
-recv_err:
-		scif_err_debug(err, "scif_recv");
-		return err;
-	}
-	case SCIF_GET_NODEIDS:
-	{
-		struct scifioctl_node_ids node_ids;
-		int entries;
-		u16 *nodes;
-		void __user *unodes, *uself;
-		u16 self;
-
-		if (copy_from_user(&node_ids, argp, sizeof(node_ids))) {
-			err = -EFAULT;
-			goto getnodes_err2;
-		}
-
-		entries = min_t(int, scif_info.maxid, node_ids.len);
-		nodes = kmalloc_array(entries, sizeof(u16), GFP_KERNEL);
-		if (entries && !nodes) {
-			err = -ENOMEM;
-			goto getnodes_err2;
-		}
-		node_ids.len = scif_get_node_ids(nodes, entries, &self);
-
-		unodes = (void __user *)node_ids.nodes;
-		if (copy_to_user(unodes, nodes, sizeof(u16) * entries)) {
-			err = -EFAULT;
-			goto getnodes_err1;
-		}
-
-		uself = (void __user *)node_ids.self;
-		if (copy_to_user(uself, &self, sizeof(u16))) {
-			err = -EFAULT;
-			goto getnodes_err1;
-		}
-
-		if (copy_to_user(argp, &node_ids, sizeof(node_ids))) {
-			err = -EFAULT;
-			goto getnodes_err1;
-		}
-getnodes_err1:
-		kfree(nodes);
-getnodes_err2:
-		return err;
-	}
-	case SCIF_REG:
-	{
-		struct scif_endpt *priv = f->private_data;
-		struct scifioctl_reg reg;
-		off_t ret;
-
-		if (copy_from_user(&reg, argp, sizeof(reg))) {
-			err = -EFAULT;
-			goto reg_err;
-		}
-		if (reg.flags & SCIF_MAP_KERNEL) {
-			err = -EINVAL;
-			goto reg_err;
-		}
-		ret = scif_register(priv, (void *)reg.addr, reg.len,
-				    reg.offset, reg.prot, reg.flags);
-		if (ret < 0) {
-			err = (int)ret;
-			goto reg_err;
-		}
-
-		if (copy_to_user(&((struct scifioctl_reg __user *)argp)
-				 ->out_offset, &ret, sizeof(reg.out_offset))) {
-			err = -EFAULT;
-			goto reg_err;
-		}
-		err = 0;
-reg_err:
-		scif_err_debug(err, "scif_register");
-		return err;
-	}
-	case SCIF_UNREG:
-	{
-		struct scif_endpt *priv = f->private_data;
-		struct scifioctl_unreg unreg;
-
-		if (copy_from_user(&unreg, argp, sizeof(unreg))) {
-			err = -EFAULT;
-			goto unreg_err;
-		}
-		err = scif_unregister(priv, unreg.offset, unreg.len);
-unreg_err:
-		scif_err_debug(err, "scif_unregister");
-		return err;
-	}
-	case SCIF_READFROM:
-	{
-		struct scif_endpt *priv = f->private_data;
-		struct scifioctl_copy copy;
-
-		if (copy_from_user(&copy, argp, sizeof(copy))) {
-			err = -EFAULT;
-			goto readfrom_err;
-		}
-		err = scif_readfrom(priv, copy.loffset, copy.len, copy.roffset,
-				    copy.flags);
-readfrom_err:
-		scif_err_debug(err, "scif_readfrom");
-		return err;
-	}
-	case SCIF_WRITETO:
-	{
-		struct scif_endpt *priv = f->private_data;
-		struct scifioctl_copy copy;
-
-		if (copy_from_user(&copy, argp, sizeof(copy))) {
-			err = -EFAULT;
-			goto writeto_err;
-		}
-		err = scif_writeto(priv, copy.loffset, copy.len, copy.roffset,
-				   copy.flags);
-writeto_err:
-		scif_err_debug(err, "scif_writeto");
-		return err;
-	}
-	case SCIF_VREADFROM:
-	{
-		struct scif_endpt *priv = f->private_data;
-		struct scifioctl_copy copy;
-
-		if (copy_from_user(&copy, argp, sizeof(copy))) {
-			err = -EFAULT;
-			goto vreadfrom_err;
-		}
-		err = scif_vreadfrom(priv, (void __force *)copy.addr, copy.len,
-				     copy.roffset, copy.flags);
-vreadfrom_err:
-		scif_err_debug(err, "scif_vreadfrom");
-		return err;
-	}
-	case SCIF_VWRITETO:
-	{
-		struct scif_endpt *priv = f->private_data;
-		struct scifioctl_copy copy;
-
-		if (copy_from_user(&copy, argp, sizeof(copy))) {
-			err = -EFAULT;
-			goto vwriteto_err;
-		}
-		err = scif_vwriteto(priv, (void __force *)copy.addr, copy.len,
-				    copy.roffset, copy.flags);
-vwriteto_err:
-		scif_err_debug(err, "scif_vwriteto");
-		return err;
-	}
-	case SCIF_FENCE_MARK:
-	{
-		struct scif_endpt *priv = f->private_data;
-		struct scifioctl_fence_mark mark;
-		int tmp_mark = 0;
-
-		if (copy_from_user(&mark, argp, sizeof(mark))) {
-			err = -EFAULT;
-			goto fence_mark_err;
-		}
-		err = scif_fence_mark(priv, mark.flags, &tmp_mark);
-		if (err)
-			goto fence_mark_err;
-		if (copy_to_user((void __user *)mark.mark, &tmp_mark,
-				 sizeof(tmp_mark))) {
-			err = -EFAULT;
-			goto fence_mark_err;
-		}
-fence_mark_err:
-		scif_err_debug(err, "scif_fence_mark");
-		return err;
-	}
-	case SCIF_FENCE_WAIT:
-	{
-		struct scif_endpt *priv = f->private_data;
-
-		err = scif_fence_wait(priv, arg);
-		scif_err_debug(err, "scif_fence_wait");
-		return err;
-	}
-	case SCIF_FENCE_SIGNAL:
-	{
-		struct scif_endpt *priv = f->private_data;
-		struct scifioctl_fence_signal signal;
-
-		if (copy_from_user(&signal, argp, sizeof(signal))) {
-			err = -EFAULT;
-			goto fence_signal_err;
-		}
-
-		err = scif_fence_signal(priv, signal.loff, signal.lval,
-					signal.roff, signal.rval, signal.flags);
-fence_signal_err:
-		scif_err_debug(err, "scif_fence_signal");
-		return err;
-	}
-	}
-	return -EINVAL;
-}
-
-const struct file_operations scif_fops = {
-	.open = scif_fdopen,
-	.release = scif_fdclose,
-	.unlocked_ioctl = scif_fdioctl,
-	.mmap = scif_fdmmap,
-	.poll = scif_fdpoll,
-	.flush = scif_fdflush,
-	.owner = THIS_MODULE,
-};
diff --git a/drivers/misc/mic/scif/scif_fence.c b/drivers/misc/mic/scif/scif_fence.c
deleted file mode 100644
index 4fedf6183951..000000000000
--- a/drivers/misc/mic/scif/scif_fence.c
+++ /dev/null
@@ -1,783 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-
-#include "scif_main.h"
-
-/**
- * scif_recv_mark: Handle SCIF_MARK request
- * @scifdev:	SCIF device
- * @msg:	Interrupt message
- *
- * The peer has requested a mark.
- */
-void scif_recv_mark(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
-	int mark = 0;
-	int err;
-
-	err = _scif_fence_mark(ep, &mark);
-	if (err)
-		msg->uop = SCIF_MARK_NACK;
-	else
-		msg->uop = SCIF_MARK_ACK;
-	msg->payload[0] = ep->remote_ep;
-	msg->payload[2] = mark;
-	scif_nodeqp_send(ep->remote_dev, msg);
-}
-
-/**
- * scif_recv_mark_resp: Handle SCIF_MARK_(N)ACK messages.
- * @scifdev:	SCIF device
- * @msg:	Interrupt message
- *
- * The peer has responded to a SCIF_MARK message.
- */
-void scif_recv_mark_resp(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
-	struct scif_fence_info *fence_req =
-		(struct scif_fence_info *)msg->payload[1];
-
-	mutex_lock(&ep->rma_info.rma_lock);
-	if (msg->uop == SCIF_MARK_ACK) {
-		fence_req->state = OP_COMPLETED;
-		fence_req->dma_mark = (int)msg->payload[2];
-	} else {
-		fence_req->state = OP_FAILED;
-	}
-	mutex_unlock(&ep->rma_info.rma_lock);
-	complete(&fence_req->comp);
-}
-
-/**
- * scif_recv_wait: Handle SCIF_WAIT request
- * @scifdev:	SCIF device
- * @msg:	Interrupt message
- *
- * The peer has requested waiting on a fence.
- */
-void scif_recv_wait(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
-	struct scif_remote_fence_info *fence;
-
-	/*
-	 * Allocate structure for remote fence information and
-	 * send a NACK if the allocation failed. The peer will
-	 * return ENOMEM upon receiving a NACK.
-	 */
-	fence = kmalloc(sizeof(*fence), GFP_KERNEL);
-	if (!fence) {
-		msg->payload[0] = ep->remote_ep;
-		msg->uop = SCIF_WAIT_NACK;
-		scif_nodeqp_send(ep->remote_dev, msg);
-		return;
-	}
-
-	/* Prepare the fence request */
-	memcpy(&fence->msg, msg, sizeof(struct scifmsg));
-	INIT_LIST_HEAD(&fence->list);
-
-	/* Insert to the global remote fence request list */
-	mutex_lock(&scif_info.fencelock);
-	atomic_inc(&ep->rma_info.fence_refcount);
-	list_add_tail(&fence->list, &scif_info.fence);
-	mutex_unlock(&scif_info.fencelock);
-
-	schedule_work(&scif_info.misc_work);
-}
-
-/**
- * scif_recv_wait_resp: Handle SCIF_WAIT_(N)ACK messages.
- * @scifdev:	SCIF device
- * @msg:	Interrupt message
- *
- * The peer has responded to a SCIF_WAIT message.
- */
-void scif_recv_wait_resp(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
-	struct scif_fence_info *fence_req =
-		(struct scif_fence_info *)msg->payload[1];
-
-	mutex_lock(&ep->rma_info.rma_lock);
-	if (msg->uop == SCIF_WAIT_ACK)
-		fence_req->state = OP_COMPLETED;
-	else
-		fence_req->state = OP_FAILED;
-	mutex_unlock(&ep->rma_info.rma_lock);
-	complete(&fence_req->comp);
-}
-
-/**
- * scif_recv_sig_local: Handle SCIF_SIG_LOCAL request
- * @scifdev:	SCIF device
- * @msg:	Interrupt message
- *
- * The peer has requested a signal on a local offset.
- */
-void scif_recv_sig_local(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
-	int err;
-
-	err = scif_prog_signal(ep, msg->payload[1], msg->payload[2],
-			       SCIF_WINDOW_SELF);
-	if (err)
-		msg->uop = SCIF_SIG_NACK;
-	else
-		msg->uop = SCIF_SIG_ACK;
-	msg->payload[0] = ep->remote_ep;
-	scif_nodeqp_send(ep->remote_dev, msg);
-}
-
-/**
- * scif_recv_sig_remote: Handle SCIF_SIGNAL_REMOTE request
- * @scifdev:	SCIF device
- * @msg:	Interrupt message
- *
- * The peer has requested a signal on a remote offset.
- */
-void scif_recv_sig_remote(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
-	int err;
-
-	err = scif_prog_signal(ep, msg->payload[1], msg->payload[2],
-			       SCIF_WINDOW_PEER);
-	if (err)
-		msg->uop = SCIF_SIG_NACK;
-	else
-		msg->uop = SCIF_SIG_ACK;
-	msg->payload[0] = ep->remote_ep;
-	scif_nodeqp_send(ep->remote_dev, msg);
-}
-
-/**
- * scif_recv_sig_resp: Handle SCIF_SIG_(N)ACK messages.
- * @scifdev:	SCIF device
- * @msg:	Interrupt message
- *
- * The peer has responded to a signal request.
- */
-void scif_recv_sig_resp(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
-	struct scif_fence_info *fence_req =
-		(struct scif_fence_info *)msg->payload[3];
-
-	mutex_lock(&ep->rma_info.rma_lock);
-	if (msg->uop == SCIF_SIG_ACK)
-		fence_req->state = OP_COMPLETED;
-	else
-		fence_req->state = OP_FAILED;
-	mutex_unlock(&ep->rma_info.rma_lock);
-	complete(&fence_req->comp);
-}
-
-static inline void *scif_get_local_va(off_t off, struct scif_window *window)
-{
-	struct page **pages = window->pinned_pages->pages;
-	int page_nr = (off - window->offset) >> PAGE_SHIFT;
-	off_t page_off = off & ~PAGE_MASK;
-
-	return page_address(pages[page_nr]) + page_off;
-}
-
-static void scif_prog_signal_cb(void *arg)
-{
-	struct scif_cb_arg *cb_arg = arg;
-
-	dma_pool_free(cb_arg->ep->remote_dev->signal_pool, cb_arg->status,
-		      cb_arg->src_dma_addr);
-	kfree(cb_arg);
-}
-
-static int _scif_prog_signal(scif_epd_t epd, dma_addr_t dst, u64 val)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)epd;
-	struct dma_chan *chan = ep->rma_info.dma_chan;
-	struct dma_device *ddev = chan->device;
-	bool x100 = !is_dma_copy_aligned(chan->device, 1, 1, 1);
-	struct dma_async_tx_descriptor *tx;
-	struct scif_status *status = NULL;
-	struct scif_cb_arg *cb_arg = NULL;
-	dma_addr_t src;
-	dma_cookie_t cookie;
-	int err;
-
-	tx = ddev->device_prep_dma_memcpy(chan, 0, 0, 0, DMA_PREP_FENCE);
-	if (!tx) {
-		err = -ENOMEM;
-		dev_err(&ep->remote_dev->sdev->dev, "%s %d err %d\n",
-			__func__, __LINE__, err);
-		goto alloc_fail;
-	}
-	cookie = tx->tx_submit(tx);
-	if (dma_submit_error(cookie)) {
-		err = (int)cookie;
-		dev_err(&ep->remote_dev->sdev->dev, "%s %d err %d\n",
-			__func__, __LINE__, err);
-		goto alloc_fail;
-	}
-	dma_async_issue_pending(chan);
-	if (x100) {
-		/*
-		 * For X100 use the status descriptor to write the value to
-		 * the destination.
-		 */
-		tx = ddev->device_prep_dma_imm_data(chan, dst, val, 0);
-	} else {
-		status = dma_pool_alloc(ep->remote_dev->signal_pool, GFP_KERNEL,
-					&src);
-		if (!status) {
-			err = -ENOMEM;
-			dev_err(&ep->remote_dev->sdev->dev, "%s %d err %d\n",
-				__func__, __LINE__, err);
-			goto alloc_fail;
-		}
-		status->val = val;
-		status->src_dma_addr = src;
-		status->ep = ep;
-		src += offsetof(struct scif_status, val);
-		tx = ddev->device_prep_dma_memcpy(chan, dst, src, sizeof(val),
-						  DMA_PREP_INTERRUPT);
-	}
-	if (!tx) {
-		err = -ENOMEM;
-		dev_err(&ep->remote_dev->sdev->dev, "%s %d err %d\n",
-			__func__, __LINE__, err);
-		goto dma_fail;
-	}
-	if (!x100) {
-		cb_arg = kmalloc(sizeof(*cb_arg), GFP_KERNEL);
-		if (!cb_arg) {
-			err = -ENOMEM;
-			goto dma_fail;
-		}
-		cb_arg->src_dma_addr = src;
-		cb_arg->status = status;
-		cb_arg->ep = ep;
-		tx->callback = scif_prog_signal_cb;
-		tx->callback_param = cb_arg;
-	}
-	cookie = tx->tx_submit(tx);
-	if (dma_submit_error(cookie)) {
-		err = -EIO;
-		dev_err(&ep->remote_dev->sdev->dev, "%s %d err %d\n",
-			__func__, __LINE__, err);
-		goto dma_fail;
-	}
-	dma_async_issue_pending(chan);
-	return 0;
-dma_fail:
-	if (!x100) {
-		dma_pool_free(ep->remote_dev->signal_pool, status,
-			      src - offsetof(struct scif_status, val));
-		kfree(cb_arg);
-	}
-alloc_fail:
-	return err;
-}
-
-/**
- * scif_prog_signal:
- * @epd: Endpoint Descriptor
- * @offset: registered address to write @val to
- * @val: Value to be written at @offset
- * @type: Type of the window.
- *
- * Arrange to write a value to the registered offset after ensuring that the
- * offset provided is indeed valid.
- */
-int scif_prog_signal(scif_epd_t epd, off_t offset, u64 val,
-		     enum scif_window_type type)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)epd;
-	struct scif_window *window = NULL;
-	struct scif_rma_req req;
-	dma_addr_t dst_dma_addr;
-	int err;
-
-	mutex_lock(&ep->rma_info.rma_lock);
-	req.out_window = &window;
-	req.offset = offset;
-	req.nr_bytes = sizeof(u64);
-	req.prot = SCIF_PROT_WRITE;
-	req.type = SCIF_WINDOW_SINGLE;
-	if (type == SCIF_WINDOW_SELF)
-		req.head = &ep->rma_info.reg_list;
-	else
-		req.head = &ep->rma_info.remote_reg_list;
-	/* Does a valid window exist? */
-	err = scif_query_window(&req);
-	if (err) {
-		dev_err(scif_info.mdev.this_device,
-			"%s %d err %d\n", __func__, __LINE__, err);
-		goto unlock_ret;
-	}
-
-	if (scif_is_mgmt_node() && scifdev_self(ep->remote_dev)) {
-		u64 *dst_virt;
-
-		if (type == SCIF_WINDOW_SELF)
-			dst_virt = scif_get_local_va(offset, window);
-		else
-			dst_virt =
-			scif_get_local_va(offset, (struct scif_window *)
-					  window->peer_window);
-		*dst_virt = val;
-	} else {
-		dst_dma_addr = __scif_off_to_dma_addr(window, offset);
-		err = _scif_prog_signal(epd, dst_dma_addr, val);
-	}
-unlock_ret:
-	mutex_unlock(&ep->rma_info.rma_lock);
-	return err;
-}
-
-static int _scif_fence_wait(scif_epd_t epd, int mark)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)epd;
-	dma_cookie_t cookie = mark & ~SCIF_REMOTE_FENCE;
-	int err;
-
-	/* Wait for DMA callback in scif_fence_mark_cb(..) */
-	err = wait_event_interruptible_timeout(ep->rma_info.markwq,
-					       dma_async_is_tx_complete(
-					       ep->rma_info.dma_chan,
-					       cookie, NULL, NULL) ==
-					       DMA_COMPLETE,
-					       SCIF_NODE_ALIVE_TIMEOUT);
-	if (!err)
-		err = -ETIMEDOUT;
-	else if (err > 0)
-		err = 0;
-	return err;
-}
-
-/**
- * scif_rma_handle_remote_fences:
- *
- * This routine services remote fence requests.
- */
-void scif_rma_handle_remote_fences(void)
-{
-	struct list_head *item, *tmp;
-	struct scif_remote_fence_info *fence;
-	struct scif_endpt *ep;
-	int mark, err;
-
-	might_sleep();
-	mutex_lock(&scif_info.fencelock);
-	list_for_each_safe(item, tmp, &scif_info.fence) {
-		fence = list_entry(item, struct scif_remote_fence_info,
-				   list);
-		/* Remove fence from global list */
-		list_del(&fence->list);
-
-		/* Initiate the fence operation */
-		ep = (struct scif_endpt *)fence->msg.payload[0];
-		mark = fence->msg.payload[2];
-		err = _scif_fence_wait(ep, mark);
-		if (err)
-			fence->msg.uop = SCIF_WAIT_NACK;
-		else
-			fence->msg.uop = SCIF_WAIT_ACK;
-		fence->msg.payload[0] = ep->remote_ep;
-		scif_nodeqp_send(ep->remote_dev, &fence->msg);
-		kfree(fence);
-		if (!atomic_sub_return(1, &ep->rma_info.fence_refcount))
-			schedule_work(&scif_info.misc_work);
-	}
-	mutex_unlock(&scif_info.fencelock);
-}
-
-static int _scif_send_fence(scif_epd_t epd, int uop, int mark, int *out_mark)
-{
-	int err;
-	struct scifmsg msg;
-	struct scif_fence_info *fence_req;
-	struct scif_endpt *ep = (struct scif_endpt *)epd;
-
-	fence_req = kmalloc(sizeof(*fence_req), GFP_KERNEL);
-	if (!fence_req) {
-		err = -ENOMEM;
-		goto error;
-	}
-
-	fence_req->state = OP_IN_PROGRESS;
-	init_completion(&fence_req->comp);
-
-	msg.src = ep->port;
-	msg.uop = uop;
-	msg.payload[0] = ep->remote_ep;
-	msg.payload[1] = (u64)fence_req;
-	if (uop == SCIF_WAIT)
-		msg.payload[2] = mark;
-	spin_lock(&ep->lock);
-	if (ep->state == SCIFEP_CONNECTED)
-		err = scif_nodeqp_send(ep->remote_dev, &msg);
-	else
-		err = -ENOTCONN;
-	spin_unlock(&ep->lock);
-	if (err)
-		goto error_free;
-retry:
-	/* Wait for a SCIF_WAIT_(N)ACK message */
-	err = wait_for_completion_timeout(&fence_req->comp,
-					  SCIF_NODE_ALIVE_TIMEOUT);
-	if (!err && scifdev_alive(ep))
-		goto retry;
-	if (!err)
-		err = -ENODEV;
-	if (err > 0)
-		err = 0;
-	mutex_lock(&ep->rma_info.rma_lock);
-	if (err < 0) {
-		if (fence_req->state == OP_IN_PROGRESS)
-			fence_req->state = OP_FAILED;
-	}
-	if (fence_req->state == OP_FAILED && !err)
-		err = -ENOMEM;
-	if (uop == SCIF_MARK && fence_req->state == OP_COMPLETED)
-		*out_mark = SCIF_REMOTE_FENCE | fence_req->dma_mark;
-	mutex_unlock(&ep->rma_info.rma_lock);
-error_free:
-	kfree(fence_req);
-error:
-	return err;
-}
-
-/**
- * scif_send_fence_mark:
- * @epd: end point descriptor.
- * @out_mark: Output DMA mark reported by peer.
- *
- * Send a remote fence mark request.
- */
-static int scif_send_fence_mark(scif_epd_t epd, int *out_mark)
-{
-	return _scif_send_fence(epd, SCIF_MARK, 0, out_mark);
-}
-
-/**
- * scif_send_fence_wait:
- * @epd: end point descriptor.
- * @mark: DMA mark to wait for.
- *
- * Send a remote fence wait request.
- */
-static int scif_send_fence_wait(scif_epd_t epd, int mark)
-{
-	return _scif_send_fence(epd, SCIF_WAIT, mark, NULL);
-}
-
-static int _scif_send_fence_signal_wait(struct scif_endpt *ep,
-					struct scif_fence_info *fence_req)
-{
-	int err;
-
-retry:
-	/* Wait for a SCIF_SIG_(N)ACK message */
-	err = wait_for_completion_timeout(&fence_req->comp,
-					  SCIF_NODE_ALIVE_TIMEOUT);
-	if (!err && scifdev_alive(ep))
-		goto retry;
-	if (!err)
-		err = -ENODEV;
-	if (err > 0)
-		err = 0;
-	if (err < 0) {
-		mutex_lock(&ep->rma_info.rma_lock);
-		if (fence_req->state == OP_IN_PROGRESS)
-			fence_req->state = OP_FAILED;
-		mutex_unlock(&ep->rma_info.rma_lock);
-	}
-	if (fence_req->state == OP_FAILED && !err)
-		err = -ENXIO;
-	return err;
-}
-
-/**
- * scif_send_fence_signal:
- * @epd: endpoint descriptor
- * @loff: local offset
- * @lval: local value to write to loffset
- * @roff: remote offset
- * @rval: remote value to write to roffset
- * @flags: flags
- *
- * Sends a remote fence signal request
- */
-static int scif_send_fence_signal(scif_epd_t epd, off_t roff, u64 rval,
-				  off_t loff, u64 lval, int flags)
-{
-	int err = 0;
-	struct scifmsg msg;
-	struct scif_fence_info *fence_req;
-	struct scif_endpt *ep = (struct scif_endpt *)epd;
-
-	fence_req = kmalloc(sizeof(*fence_req), GFP_KERNEL);
-	if (!fence_req) {
-		err = -ENOMEM;
-		goto error;
-	}
-
-	fence_req->state = OP_IN_PROGRESS;
-	init_completion(&fence_req->comp);
-	msg.src = ep->port;
-	if (flags & SCIF_SIGNAL_LOCAL) {
-		msg.uop = SCIF_SIG_LOCAL;
-		msg.payload[0] = ep->remote_ep;
-		msg.payload[1] = roff;
-		msg.payload[2] = rval;
-		msg.payload[3] = (u64)fence_req;
-		spin_lock(&ep->lock);
-		if (ep->state == SCIFEP_CONNECTED)
-			err = scif_nodeqp_send(ep->remote_dev, &msg);
-		else
-			err = -ENOTCONN;
-		spin_unlock(&ep->lock);
-		if (err)
-			goto error_free;
-		err = _scif_send_fence_signal_wait(ep, fence_req);
-		if (err)
-			goto error_free;
-	}
-	fence_req->state = OP_IN_PROGRESS;
-
-	if (flags & SCIF_SIGNAL_REMOTE) {
-		msg.uop = SCIF_SIG_REMOTE;
-		msg.payload[0] = ep->remote_ep;
-		msg.payload[1] = loff;
-		msg.payload[2] = lval;
-		msg.payload[3] = (u64)fence_req;
-		spin_lock(&ep->lock);
-		if (ep->state == SCIFEP_CONNECTED)
-			err = scif_nodeqp_send(ep->remote_dev, &msg);
-		else
-			err = -ENOTCONN;
-		spin_unlock(&ep->lock);
-		if (err)
-			goto error_free;
-		err = _scif_send_fence_signal_wait(ep, fence_req);
-	}
-error_free:
-	kfree(fence_req);
-error:
-	return err;
-}
-
-static void scif_fence_mark_cb(void *arg)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)arg;
-
-	wake_up_interruptible(&ep->rma_info.markwq);
-	atomic_dec(&ep->rma_info.fence_refcount);
-}
-
-/**
- * _scif_fence_mark:
- * @epd: endpoint descriptor
- * @mark: DMA mark to set-up
- *
- * Set up a mark for this endpoint and return the value of the mark.
- */
-int _scif_fence_mark(scif_epd_t epd, int *mark)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)epd;
-	struct dma_chan *chan = ep->rma_info.dma_chan;
-	struct dma_device *ddev = chan->device;
-	struct dma_async_tx_descriptor *tx;
-	dma_cookie_t cookie;
-	int err;
-
-	tx = ddev->device_prep_dma_memcpy(chan, 0, 0, 0, DMA_PREP_FENCE);
-	if (!tx) {
-		err = -ENOMEM;
-		dev_err(&ep->remote_dev->sdev->dev, "%s %d err %d\n",
-			__func__, __LINE__, err);
-		return err;
-	}
-	cookie = tx->tx_submit(tx);
-	if (dma_submit_error(cookie)) {
-		err = (int)cookie;
-		dev_err(&ep->remote_dev->sdev->dev, "%s %d err %d\n",
-			__func__, __LINE__, err);
-		return err;
-	}
-	dma_async_issue_pending(chan);
-	tx = ddev->device_prep_dma_interrupt(chan, DMA_PREP_INTERRUPT);
-	if (!tx) {
-		err = -ENOMEM;
-		dev_err(&ep->remote_dev->sdev->dev, "%s %d err %d\n",
-			__func__, __LINE__, err);
-		return err;
-	}
-	tx->callback = scif_fence_mark_cb;
-	tx->callback_param = ep;
-	*mark = cookie = tx->tx_submit(tx);
-	if (dma_submit_error(cookie)) {
-		err = (int)cookie;
-		dev_err(&ep->remote_dev->sdev->dev, "%s %d err %d\n",
-			__func__, __LINE__, err);
-		return err;
-	}
-	atomic_inc(&ep->rma_info.fence_refcount);
-	dma_async_issue_pending(chan);
-	return 0;
-}
-
-#define SCIF_LOOPB_MAGIC_MARK 0xdead
-
-int scif_fence_mark(scif_epd_t epd, int flags, int *mark)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)epd;
-	int err = 0;
-
-	dev_dbg(scif_info.mdev.this_device,
-		"SCIFAPI fence_mark: ep %p flags 0x%x mark 0x%x\n",
-		ep, flags, *mark);
-	err = scif_verify_epd(ep);
-	if (err)
-		return err;
-
-	/* Invalid flags? */
-	if (flags & ~(SCIF_FENCE_INIT_SELF | SCIF_FENCE_INIT_PEER))
-		return -EINVAL;
-
-	/* At least one of init self or peer RMA should be set */
-	if (!(flags & (SCIF_FENCE_INIT_SELF | SCIF_FENCE_INIT_PEER)))
-		return -EINVAL;
-
-	/* Exactly one of init self or peer RMA should be set but not both */
-	if ((flags & SCIF_FENCE_INIT_SELF) && (flags & SCIF_FENCE_INIT_PEER))
-		return -EINVAL;
-
-	/*
-	 * Management node loopback does not need to use DMA.
-	 * Return a valid mark to be symmetric.
-	 */
-	if (scifdev_self(ep->remote_dev) && scif_is_mgmt_node()) {
-		*mark = SCIF_LOOPB_MAGIC_MARK;
-		return 0;
-	}
-
-	if (flags & SCIF_FENCE_INIT_SELF)
-		err = _scif_fence_mark(epd, mark);
-	else
-		err = scif_send_fence_mark(ep, mark);
-
-	if (err)
-		dev_err(scif_info.mdev.this_device,
-			"%s %d err %d\n", __func__, __LINE__, err);
-	dev_dbg(scif_info.mdev.this_device,
-		"SCIFAPI fence_mark: ep %p flags 0x%x mark 0x%x err %d\n",
-		ep, flags, *mark, err);
-	return err;
-}
-EXPORT_SYMBOL_GPL(scif_fence_mark);
-
-int scif_fence_wait(scif_epd_t epd, int mark)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)epd;
-	int err = 0;
-
-	dev_dbg(scif_info.mdev.this_device,
-		"SCIFAPI fence_wait: ep %p mark 0x%x\n",
-		ep, mark);
-	err = scif_verify_epd(ep);
-	if (err)
-		return err;
-	/*
-	 * Management node loopback does not need to use DMA.
-	 * The only valid mark provided is 0 so simply
-	 * return success if the mark is valid.
-	 */
-	if (scifdev_self(ep->remote_dev) && scif_is_mgmt_node()) {
-		if (mark == SCIF_LOOPB_MAGIC_MARK)
-			return 0;
-		else
-			return -EINVAL;
-	}
-	if (mark & SCIF_REMOTE_FENCE)
-		err = scif_send_fence_wait(epd, mark);
-	else
-		err = _scif_fence_wait(epd, mark);
-	if (err < 0)
-		dev_err(scif_info.mdev.this_device,
-			"%s %d err %d\n", __func__, __LINE__, err);
-	return err;
-}
-EXPORT_SYMBOL_GPL(scif_fence_wait);
-
-int scif_fence_signal(scif_epd_t epd, off_t loff, u64 lval,
-		      off_t roff, u64 rval, int flags)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)epd;
-	int err = 0;
-
-	dev_dbg(scif_info.mdev.this_device,
-		"SCIFAPI fence_signal: ep %p loff 0x%lx lval 0x%llx roff 0x%lx rval 0x%llx flags 0x%x\n",
-		ep, loff, lval, roff, rval, flags);
-	err = scif_verify_epd(ep);
-	if (err)
-		return err;
-
-	/* Invalid flags? */
-	if (flags & ~(SCIF_FENCE_INIT_SELF | SCIF_FENCE_INIT_PEER |
-			SCIF_SIGNAL_LOCAL | SCIF_SIGNAL_REMOTE))
-		return -EINVAL;
-
-	/* At least one of init self or peer RMA should be set */
-	if (!(flags & (SCIF_FENCE_INIT_SELF | SCIF_FENCE_INIT_PEER)))
-		return -EINVAL;
-
-	/* Exactly one of init self or peer RMA should be set but not both */
-	if ((flags & SCIF_FENCE_INIT_SELF) && (flags & SCIF_FENCE_INIT_PEER))
-		return -EINVAL;
-
-	/* At least one of SCIF_SIGNAL_LOCAL or SCIF_SIGNAL_REMOTE required */
-	if (!(flags & (SCIF_SIGNAL_LOCAL | SCIF_SIGNAL_REMOTE)))
-		return -EINVAL;
-
-	/* Only Dword offsets allowed */
-	if ((flags & SCIF_SIGNAL_LOCAL) && (loff & (sizeof(u32) - 1)))
-		return -EINVAL;
-
-	/* Only Dword aligned offsets allowed */
-	if ((flags & SCIF_SIGNAL_REMOTE) && (roff & (sizeof(u32) - 1)))
-		return -EINVAL;
-
-	if (flags & SCIF_FENCE_INIT_PEER) {
-		err = scif_send_fence_signal(epd, roff, rval, loff,
-					     lval, flags);
-	} else {
-		/* Local Signal in Local RAS */
-		if (flags & SCIF_SIGNAL_LOCAL) {
-			err = scif_prog_signal(epd, loff, lval,
-					       SCIF_WINDOW_SELF);
-			if (err)
-				goto error_ret;
-		}
-
-		/* Signal in Remote RAS */
-		if (flags & SCIF_SIGNAL_REMOTE)
-			err = scif_prog_signal(epd, roff,
-					       rval, SCIF_WINDOW_PEER);
-	}
-error_ret:
-	if (err)
-		dev_err(scif_info.mdev.this_device,
-			"%s %d err %d\n", __func__, __LINE__, err);
-	return err;
-}
-EXPORT_SYMBOL_GPL(scif_fence_signal);
diff --git a/drivers/misc/mic/scif/scif_main.c b/drivers/misc/mic/scif/scif_main.c
deleted file mode 100644
index e2278bf9f11d..000000000000
--- a/drivers/misc/mic/scif/scif_main.c
+++ /dev/null
@@ -1,351 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include <linux/module.h>
-#include <linux/idr.h>
-
-#include <linux/mic_common.h>
-#include "../common/mic_dev.h"
-#include "../bus/scif_bus.h"
-#include "scif_peer_bus.h"
-#include "scif_main.h"
-#include "scif_map.h"
-
-struct scif_info scif_info = {
-	.mdev = {
-		.minor = MISC_DYNAMIC_MINOR,
-		.name = "scif",
-		.fops = &scif_fops,
-	}
-};
-
-struct scif_dev *scif_dev;
-struct kmem_cache *unaligned_cache;
-static atomic_t g_loopb_cnt;
-
-/* Runs in the context of intr_wq */
-static void scif_intr_bh_handler(struct work_struct *work)
-{
-	struct scif_dev *scifdev =
-			container_of(work, struct scif_dev, intr_bh);
-
-	if (scifdev_self(scifdev))
-		scif_loopb_msg_handler(scifdev, scifdev->qpairs);
-	else
-		scif_nodeqp_intrhandler(scifdev, scifdev->qpairs);
-}
-
-int scif_setup_intr_wq(struct scif_dev *scifdev)
-{
-	if (!scifdev->intr_wq) {
-		snprintf(scifdev->intr_wqname, sizeof(scifdev->intr_wqname),
-			 "SCIF INTR %d", scifdev->node);
-		scifdev->intr_wq =
-			alloc_ordered_workqueue(scifdev->intr_wqname, 0);
-		if (!scifdev->intr_wq)
-			return -ENOMEM;
-		INIT_WORK(&scifdev->intr_bh, scif_intr_bh_handler);
-	}
-	return 0;
-}
-
-void scif_destroy_intr_wq(struct scif_dev *scifdev)
-{
-	if (scifdev->intr_wq) {
-		destroy_workqueue(scifdev->intr_wq);
-		scifdev->intr_wq = NULL;
-	}
-}
-
-irqreturn_t scif_intr_handler(int irq, void *data)
-{
-	struct scif_dev *scifdev = data;
-	struct scif_hw_dev *sdev = scifdev->sdev;
-
-	sdev->hw_ops->ack_interrupt(sdev, scifdev->db);
-	queue_work(scifdev->intr_wq, &scifdev->intr_bh);
-	return IRQ_HANDLED;
-}
-
-static void scif_qp_setup_handler(struct work_struct *work)
-{
-	struct scif_dev *scifdev = container_of(work, struct scif_dev,
-						qp_dwork.work);
-	struct scif_hw_dev *sdev = scifdev->sdev;
-	dma_addr_t da = 0;
-	int err;
-
-	if (scif_is_mgmt_node()) {
-		struct mic_bootparam *bp = sdev->dp;
-
-		da = bp->scif_card_dma_addr;
-		scifdev->rdb = bp->h2c_scif_db;
-	} else {
-		struct mic_bootparam __iomem *bp = sdev->rdp;
-
-		da = readq(&bp->scif_host_dma_addr);
-		scifdev->rdb = ioread8(&bp->c2h_scif_db);
-	}
-	if (da) {
-		err = scif_qp_response(da, scifdev);
-		if (err)
-			dev_err(&scifdev->sdev->dev,
-				"scif_qp_response err %d\n", err);
-	} else {
-		schedule_delayed_work(&scifdev->qp_dwork,
-				      msecs_to_jiffies(1000));
-	}
-}
-
-static int scif_setup_scifdev(void)
-{
-	/* We support a maximum of 129 SCIF nodes including the mgmt node */
-#define MAX_SCIF_NODES 129
-	int i;
-	u8 num_nodes = MAX_SCIF_NODES;
-
-	scif_dev = kcalloc(num_nodes, sizeof(*scif_dev), GFP_KERNEL);
-	if (!scif_dev)
-		return -ENOMEM;
-	for (i = 0; i < num_nodes; i++) {
-		struct scif_dev *scifdev = &scif_dev[i];
-
-		scifdev->node = i;
-		scifdev->exit = OP_IDLE;
-		init_waitqueue_head(&scifdev->disconn_wq);
-		mutex_init(&scifdev->lock);
-		INIT_WORK(&scifdev->peer_add_work, scif_add_peer_device);
-		INIT_DELAYED_WORK(&scifdev->p2p_dwork,
-				  scif_poll_qp_state);
-		INIT_DELAYED_WORK(&scifdev->qp_dwork,
-				  scif_qp_setup_handler);
-		INIT_LIST_HEAD(&scifdev->p2p);
-		RCU_INIT_POINTER(scifdev->spdev, NULL);
-	}
-	return 0;
-}
-
-static void scif_destroy_scifdev(void)
-{
-	kfree(scif_dev);
-	scif_dev = NULL;
-}
-
-static int scif_probe(struct scif_hw_dev *sdev)
-{
-	struct scif_dev *scifdev = &scif_dev[sdev->dnode];
-	int rc;
-
-	dev_set_drvdata(&sdev->dev, sdev);
-	scifdev->sdev = sdev;
-
-	if (1 == atomic_add_return(1, &g_loopb_cnt)) {
-		struct scif_dev *loopb_dev = &scif_dev[sdev->snode];
-
-		loopb_dev->sdev = sdev;
-		rc = scif_setup_loopback_qp(loopb_dev);
-		if (rc)
-			goto exit;
-	}
-
-	rc = scif_setup_intr_wq(scifdev);
-	if (rc)
-		goto destroy_loopb;
-	rc = scif_setup_qp(scifdev);
-	if (rc)
-		goto destroy_intr;
-	scifdev->db = sdev->hw_ops->next_db(sdev);
-	scifdev->cookie = sdev->hw_ops->request_irq(sdev, scif_intr_handler,
-						    "SCIF_INTR", scifdev,
-						    scifdev->db);
-	if (IS_ERR(scifdev->cookie)) {
-		rc = PTR_ERR(scifdev->cookie);
-		goto free_qp;
-	}
-	if (scif_is_mgmt_node()) {
-		struct mic_bootparam *bp = sdev->dp;
-
-		bp->c2h_scif_db = scifdev->db;
-		bp->scif_host_dma_addr = scifdev->qp_dma_addr;
-	} else {
-		struct mic_bootparam __iomem *bp = sdev->rdp;
-
-		iowrite8(scifdev->db, &bp->h2c_scif_db);
-		writeq(scifdev->qp_dma_addr, &bp->scif_card_dma_addr);
-	}
-	schedule_delayed_work(&scifdev->qp_dwork,
-			      msecs_to_jiffies(1000));
-	return rc;
-free_qp:
-	scif_free_qp(scifdev);
-destroy_intr:
-	scif_destroy_intr_wq(scifdev);
-destroy_loopb:
-	if (atomic_dec_and_test(&g_loopb_cnt))
-		scif_destroy_loopback_qp(&scif_dev[sdev->snode]);
-exit:
-	return rc;
-}
-
-void scif_stop(struct scif_dev *scifdev)
-{
-	struct scif_dev *dev;
-	int i;
-
-	for (i = scif_info.maxid; i >= 0; i--) {
-		dev = &scif_dev[i];
-		if (scifdev_self(dev))
-			continue;
-		scif_handle_remove_node(i);
-	}
-}
-
-static void scif_remove(struct scif_hw_dev *sdev)
-{
-	struct scif_dev *scifdev = &scif_dev[sdev->dnode];
-
-	if (scif_is_mgmt_node()) {
-		struct mic_bootparam *bp = sdev->dp;
-
-		bp->c2h_scif_db = -1;
-		bp->scif_host_dma_addr = 0x0;
-	} else {
-		struct mic_bootparam __iomem *bp = sdev->rdp;
-
-		iowrite8(-1, &bp->h2c_scif_db);
-		writeq(0x0, &bp->scif_card_dma_addr);
-	}
-	if (scif_is_mgmt_node()) {
-		scif_disconnect_node(scifdev->node, true);
-	} else {
-		scif_info.card_initiated_exit = true;
-		scif_stop(scifdev);
-	}
-	if (atomic_dec_and_test(&g_loopb_cnt))
-		scif_destroy_loopback_qp(&scif_dev[sdev->snode]);
-	if (scifdev->cookie) {
-		sdev->hw_ops->free_irq(sdev, scifdev->cookie, scifdev);
-		scifdev->cookie = NULL;
-	}
-	scif_destroy_intr_wq(scifdev);
-	cancel_delayed_work(&scifdev->qp_dwork);
-	scif_free_qp(scifdev);
-	scifdev->rdb = -1;
-	scifdev->sdev = NULL;
-}
-
-static struct scif_hw_dev_id id_table[] = {
-	{ MIC_SCIF_DEV, SCIF_DEV_ANY_ID },
-	{ 0 },
-};
-
-static struct scif_driver scif_driver = {
-	.driver.name =	KBUILD_MODNAME,
-	.driver.owner =	THIS_MODULE,
-	.id_table = id_table,
-	.probe = scif_probe,
-	.remove = scif_remove,
-};
-
-static int _scif_init(void)
-{
-	int rc;
-
-	mutex_init(&scif_info.eplock);
-	spin_lock_init(&scif_info.rmalock);
-	spin_lock_init(&scif_info.nb_connect_lock);
-	spin_lock_init(&scif_info.port_lock);
-	mutex_init(&scif_info.conflock);
-	mutex_init(&scif_info.connlock);
-	mutex_init(&scif_info.fencelock);
-	INIT_LIST_HEAD(&scif_info.uaccept);
-	INIT_LIST_HEAD(&scif_info.listen);
-	INIT_LIST_HEAD(&scif_info.zombie);
-	INIT_LIST_HEAD(&scif_info.connected);
-	INIT_LIST_HEAD(&scif_info.disconnected);
-	INIT_LIST_HEAD(&scif_info.rma);
-	INIT_LIST_HEAD(&scif_info.rma_tc);
-	INIT_LIST_HEAD(&scif_info.mmu_notif_cleanup);
-	INIT_LIST_HEAD(&scif_info.fence);
-	INIT_LIST_HEAD(&scif_info.nb_connect_list);
-	init_waitqueue_head(&scif_info.exitwq);
-	scif_info.rma_tc_limit = SCIF_RMA_TEMP_CACHE_LIMIT;
-	scif_info.en_msg_log = 0;
-	scif_info.p2p_enable = 1;
-	rc = scif_setup_scifdev();
-	if (rc)
-		goto error;
-	unaligned_cache = kmem_cache_create("Unaligned_DMA",
-					    SCIF_KMEM_UNALIGNED_BUF_SIZE,
-					    0, SLAB_HWCACHE_ALIGN, NULL);
-	if (!unaligned_cache) {
-		rc = -ENOMEM;
-		goto free_sdev;
-	}
-	INIT_WORK(&scif_info.misc_work, scif_misc_handler);
-	INIT_WORK(&scif_info.mmu_notif_work, scif_mmu_notif_handler);
-	INIT_WORK(&scif_info.conn_work, scif_conn_handler);
-	idr_init(&scif_ports);
-	return 0;
-free_sdev:
-	scif_destroy_scifdev();
-error:
-	return rc;
-}
-
-static void _scif_exit(void)
-{
-	idr_destroy(&scif_ports);
-	kmem_cache_destroy(unaligned_cache);
-	scif_destroy_scifdev();
-}
-
-static int __init scif_init(void)
-{
-	struct miscdevice *mdev = &scif_info.mdev;
-	int rc;
-
-	_scif_init();
-	iova_cache_get();
-	rc = scif_peer_bus_init();
-	if (rc)
-		goto exit;
-	rc = scif_register_driver(&scif_driver);
-	if (rc)
-		goto peer_bus_exit;
-	rc = misc_register(mdev);
-	if (rc)
-		goto unreg_scif;
-	scif_init_debugfs();
-	return 0;
-unreg_scif:
-	scif_unregister_driver(&scif_driver);
-peer_bus_exit:
-	scif_peer_bus_exit();
-exit:
-	_scif_exit();
-	return rc;
-}
-
-static void __exit scif_exit(void)
-{
-	scif_exit_debugfs();
-	misc_deregister(&scif_info.mdev);
-	scif_unregister_driver(&scif_driver);
-	scif_peer_bus_exit();
-	iova_cache_put();
-	_scif_exit();
-}
-
-module_init(scif_init);
-module_exit(scif_exit);
-
-MODULE_DEVICE_TABLE(scif, id_table);
-MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Intel(R) SCIF driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/misc/mic/scif/scif_main.h b/drivers/misc/mic/scif/scif_main.h
deleted file mode 100644
index bb3ab97d5b35..000000000000
--- a/drivers/misc/mic/scif/scif_main.h
+++ /dev/null
@@ -1,274 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#ifndef SCIF_MAIN_H
-#define SCIF_MAIN_H
-
-#include <linux/sched/signal.h>
-#include <linux/pci.h>
-#include <linux/miscdevice.h>
-#include <linux/dmaengine.h>
-#include <linux/iova.h>
-#include <linux/anon_inodes.h>
-#include <linux/file.h>
-#include <linux/vmalloc.h>
-#include <linux/scif.h>
-#include "../common/mic_dev.h"
-
-#define SCIF_MGMT_NODE 0
-#define SCIF_DEFAULT_WATCHDOG_TO 30
-#define SCIF_NODE_ACCEPT_TIMEOUT (3 * HZ)
-#define SCIF_NODE_ALIVE_TIMEOUT (SCIF_DEFAULT_WATCHDOG_TO * HZ)
-#define SCIF_RMA_TEMP_CACHE_LIMIT 0x20000
-
-/*
- * Generic state used for certain node QP message exchanges
- * like Unregister, Alloc etc.
- */
-enum scif_msg_state {
-	OP_IDLE = 1,
-	OP_IN_PROGRESS,
-	OP_COMPLETED,
-	OP_FAILED
-};
-
-/*
- * struct scif_info - Global SCIF information
- *
- * @nodeid: Node ID this node is to others
- * @maxid: Max known node ID
- * @total: Total number of SCIF nodes
- * @nr_zombies: number of zombie endpoints
- * @eplock: Lock to synchronize listening, zombie endpoint lists
- * @connlock: Lock to synchronize connected and disconnected lists
- * @nb_connect_lock: Synchronize non blocking connect operations
- * @port_lock: Synchronize access to SCIF ports
- * @uaccept: List of user acceptreq waiting for acceptreg
- * @listen: List of listening end points
- * @zombie: List of zombie end points with pending RMA's
- * @connected: List of end points in connected state
- * @disconnected: List of end points in disconnected state
- * @nb_connect_list: List for non blocking connections
- * @misc_work: miscellaneous SCIF tasks
- * @conflock: Lock to synchronize SCIF node configuration changes
- * @en_msg_log: Enable debug message logging
- * @p2p_enable: Enable P2P SCIF network
- * @mdev: The MISC device
- * @conn_work: Work for workqueue handling all connections
- * @exitwq: Wait queue for waiting for an EXIT node QP message response
- * @loopb_dev: Dummy SCIF device used for loopback
- * @loopb_wq: Workqueue used for handling loopback messages
- * @loopb_wqname[16]: Name of loopback workqueue
- * @loopb_work: Used for submitting work to loopb_wq
- * @loopb_recv_q: List of messages received on the loopb_wq
- * @card_initiated_exit: set when the card has initiated the exit
- * @rmalock: Synchronize access to RMA operations
- * @fencelock: Synchronize access to list of remote fences requested.
- * @rma: List of temporary registered windows to be destroyed.
- * @rma_tc: List of temporary registered & cached Windows to be destroyed
- * @fence: List of remote fence requests
- * @mmu_notif_work: Work for registration caching MMU notifier workqueue
- * @mmu_notif_cleanup: List of temporary cached windows for reg cache
- * @rma_tc_limit: RMA temporary cache limit
- */
-struct scif_info {
-	u8 nodeid;
-	u8 maxid;
-	u8 total;
-	u32 nr_zombies;
-	struct mutex eplock;
-	struct mutex connlock;
-	spinlock_t nb_connect_lock;
-	spinlock_t port_lock;
-	struct list_head uaccept;
-	struct list_head listen;
-	struct list_head zombie;
-	struct list_head connected;
-	struct list_head disconnected;
-	struct list_head nb_connect_list;
-	struct work_struct misc_work;
-	struct mutex conflock;
-	u8 en_msg_log;
-	u8 p2p_enable;
-	struct miscdevice mdev;
-	struct work_struct conn_work;
-	wait_queue_head_t exitwq;
-	struct scif_dev *loopb_dev;
-	struct workqueue_struct *loopb_wq;
-	char loopb_wqname[16];
-	struct work_struct loopb_work;
-	struct list_head loopb_recv_q;
-	bool card_initiated_exit;
-	spinlock_t rmalock;
-	struct mutex fencelock;
-	struct list_head rma;
-	struct list_head rma_tc;
-	struct list_head fence;
-	struct work_struct mmu_notif_work;
-	struct list_head mmu_notif_cleanup;
-	unsigned long rma_tc_limit;
-};
-
-/*
- * struct scif_p2p_info - SCIF mapping information used for P2P
- *
- * @ppi_peer_id - SCIF peer node id
- * @ppi_sg - Scatter list for bar information (One for mmio and one for aper)
- * @sg_nentries - Number of entries in the scatterlist
- * @ppi_da: DMA address for MMIO and APER bars
- * @ppi_len: Length of MMIO and APER bars
- * @ppi_list: Link in list of mapping information
- */
-struct scif_p2p_info {
-	u8 ppi_peer_id;
-	struct scatterlist *ppi_sg[2];
-	u64 sg_nentries[2];
-	dma_addr_t ppi_da[2];
-	u64 ppi_len[2];
-#define SCIF_PPI_MMIO 0
-#define SCIF_PPI_APER 1
-	struct list_head ppi_list;
-};
-
-/*
- * struct scif_dev - SCIF remote device specific fields
- *
- * @node: Node id
- * @p2p: List of P2P mapping information
- * @qpairs: The node queue pair for exchanging control messages
- * @intr_wq: Workqueue for handling Node QP messages
- * @intr_wqname: Name of node QP workqueue for handling interrupts
- * @intr_bh: Used for submitting work to intr_wq
- * @lock: Lock used for synchronizing access to the scif device
- * @sdev: SCIF hardware device on the SCIF hardware bus
- * @db: doorbell the peer will trigger to generate an interrupt on self
- * @rdb: Doorbell to trigger on the peer to generate an interrupt on the peer
- * @cookie: Cookie received while registering the interrupt handler
- * @peer_add_work: Work for handling device_add for peer devices
- * @p2p_dwork: Delayed work to enable polling for P2P state
- * @qp_dwork: Delayed work for enabling polling for remote QP information
- * @p2p_retry: Number of times to retry polling of P2P state
- * @base_addr: P2P aperture bar base address
- * @mic_mw mmio: The peer MMIO information used for P2P
- * @spdev: SCIF peer device on the SCIF peer bus
- * @node_remove_ack_pending: True if a node_remove_ack is pending
- * @exit_ack_pending: true if an exit_ack is pending
- * @disconn_wq: Used while waiting for a node remove response
- * @disconn_rescnt: Keeps track of number of node remove requests sent
- * @exit: Status of exit message
- * @qp_dma_addr: Queue pair DMA address passed to the peer
- * @dma_ch_idx: Round robin index for DMA channels
- * @signal_pool: DMA pool used for scheduling scif_fence_signal DMA's
-*/
-struct scif_dev {
-	u8 node;
-	struct list_head p2p;
-	struct scif_qp *qpairs;
-	struct workqueue_struct *intr_wq;
-	char intr_wqname[16];
-	struct work_struct intr_bh;
-	struct mutex lock;
-	struct scif_hw_dev *sdev;
-	int db;
-	int rdb;
-	struct mic_irq *cookie;
-	struct work_struct peer_add_work;
-	struct delayed_work p2p_dwork;
-	struct delayed_work qp_dwork;
-	int p2p_retry;
-	dma_addr_t base_addr;
-	struct mic_mw mmio;
-	struct scif_peer_dev __rcu *spdev;
-	bool node_remove_ack_pending;
-	bool exit_ack_pending;
-	wait_queue_head_t disconn_wq;
-	atomic_t disconn_rescnt;
-	enum scif_msg_state exit;
-	dma_addr_t qp_dma_addr;
-	int dma_ch_idx;
-	struct dma_pool *signal_pool;
-};
-
-extern bool scif_reg_cache_enable;
-extern bool scif_ulimit_check;
-extern struct scif_info scif_info;
-extern struct idr scif_ports;
-extern struct bus_type scif_peer_bus;
-extern struct scif_dev *scif_dev;
-extern const struct file_operations scif_fops;
-extern const struct file_operations scif_anon_fops;
-
-/* Size of the RB for the Node QP */
-#define SCIF_NODE_QP_SIZE 0x10000
-
-#include "scif_nodeqp.h"
-#include "scif_rma.h"
-#include "scif_rma_list.h"
-
-/*
- * scifdev_self:
- * @dev: The remote SCIF Device
- *
- * Returns true if the SCIF Device passed is the self aka Loopback SCIF device.
- */
-static inline int scifdev_self(struct scif_dev *dev)
-{
-	return dev->node == scif_info.nodeid;
-}
-
-static inline bool scif_is_mgmt_node(void)
-{
-	return !scif_info.nodeid;
-}
-
-/*
- * scifdev_is_p2p:
- * @dev: The remote SCIF Device
- *
- * Returns true if the SCIF Device is a MIC Peer to Peer SCIF device.
- */
-static inline bool scifdev_is_p2p(struct scif_dev *dev)
-{
-	if (scif_is_mgmt_node())
-		return false;
-	else
-		return dev != &scif_dev[SCIF_MGMT_NODE] &&
-			!scifdev_self(dev);
-}
-
-/*
- * scifdev_alive:
- * @scifdev: The remote SCIF Device
- *
- * Returns true if the remote SCIF Device is running or sleeping for
- * this endpoint.
- */
-static inline int _scifdev_alive(struct scif_dev *scifdev)
-{
-	struct scif_peer_dev *spdev;
-
-	rcu_read_lock();
-	spdev = rcu_dereference(scifdev->spdev);
-	rcu_read_unlock();
-	return !!spdev;
-}
-
-#include "scif_epd.h"
-
-void __init scif_init_debugfs(void);
-void scif_exit_debugfs(void);
-int scif_setup_intr_wq(struct scif_dev *scifdev);
-void scif_destroy_intr_wq(struct scif_dev *scifdev);
-void scif_cleanup_scifdev(struct scif_dev *dev);
-void scif_handle_remove_node(int node);
-void scif_disconnect_node(u32 node_id, bool mgmt_initiated);
-void scif_free_qp(struct scif_dev *dev);
-void scif_misc_handler(struct work_struct *work);
-void scif_stop(struct scif_dev *scifdev);
-irqreturn_t scif_intr_handler(int irq, void *data);
-#endif /* SCIF_MAIN_H */
diff --git a/drivers/misc/mic/scif/scif_map.h b/drivers/misc/mic/scif/scif_map.h
deleted file mode 100644
index 96b760819bfc..000000000000
--- a/drivers/misc/mic/scif/scif_map.h
+++ /dev/null
@@ -1,127 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#ifndef SCIF_MAP_H
-#define SCIF_MAP_H
-
-#include "../bus/scif_bus.h"
-
-static __always_inline void *
-scif_alloc_coherent(dma_addr_t *dma_handle,
-		    struct scif_dev *scifdev, size_t size,
-		    gfp_t gfp)
-{
-	void *va;
-
-	if (scifdev_self(scifdev)) {
-		va = kmalloc(size, gfp);
-		if (va)
-			*dma_handle = virt_to_phys(va);
-	} else {
-		va = dma_alloc_coherent(&scifdev->sdev->dev,
-					size, dma_handle, gfp);
-		if (va && scifdev_is_p2p(scifdev))
-			*dma_handle = *dma_handle + scifdev->base_addr;
-	}
-	return va;
-}
-
-static __always_inline void
-scif_free_coherent(void *va, dma_addr_t local,
-		   struct scif_dev *scifdev, size_t size)
-{
-	if (scifdev_self(scifdev)) {
-		kfree(va);
-	} else {
-		if (scifdev_is_p2p(scifdev) && local > scifdev->base_addr)
-			local = local - scifdev->base_addr;
-		dma_free_coherent(&scifdev->sdev->dev,
-				  size, va, local);
-	}
-}
-
-static __always_inline int
-scif_map_single(dma_addr_t *dma_handle,
-		void *local, struct scif_dev *scifdev, size_t size)
-{
-	int err = 0;
-
-	if (scifdev_self(scifdev)) {
-		*dma_handle = virt_to_phys((local));
-	} else {
-		*dma_handle = dma_map_single(&scifdev->sdev->dev,
-					     local, size, DMA_BIDIRECTIONAL);
-		if (dma_mapping_error(&scifdev->sdev->dev, *dma_handle))
-			err = -ENOMEM;
-		else if (scifdev_is_p2p(scifdev))
-			*dma_handle = *dma_handle + scifdev->base_addr;
-	}
-	if (err)
-		*dma_handle = 0;
-	return err;
-}
-
-static __always_inline void
-scif_unmap_single(dma_addr_t local, struct scif_dev *scifdev,
-		  size_t size)
-{
-	if (!scifdev_self(scifdev)) {
-		if (scifdev_is_p2p(scifdev))
-			local = local - scifdev->base_addr;
-		dma_unmap_single(&scifdev->sdev->dev, local,
-				 size, DMA_BIDIRECTIONAL);
-	}
-}
-
-static __always_inline void *
-scif_ioremap(dma_addr_t phys, size_t size, struct scif_dev *scifdev)
-{
-	void *out_virt;
-	struct scif_hw_dev *sdev = scifdev->sdev;
-
-	if (scifdev_self(scifdev))
-		out_virt = phys_to_virt(phys);
-	else
-		out_virt = (void __force *)
-			   sdev->hw_ops->remap(sdev, phys, size);
-	return out_virt;
-}
-
-static __always_inline void
-scif_iounmap(void *virt, size_t len, struct scif_dev *scifdev)
-{
-	if (!scifdev_self(scifdev)) {
-		struct scif_hw_dev *sdev = scifdev->sdev;
-
-		sdev->hw_ops->unmap(sdev, (void __force __iomem *)virt);
-	}
-}
-
-static __always_inline int
-scif_map_page(dma_addr_t *dma_handle, struct page *page,
-	      struct scif_dev *scifdev)
-{
-	int err = 0;
-
-	if (scifdev_self(scifdev)) {
-		*dma_handle = page_to_phys(page);
-	} else {
-		struct scif_hw_dev *sdev = scifdev->sdev;
-		*dma_handle = dma_map_page(&sdev->dev,
-					   page, 0x0, PAGE_SIZE,
-					   DMA_BIDIRECTIONAL);
-		if (dma_mapping_error(&sdev->dev, *dma_handle))
-			err = -ENOMEM;
-		else if (scifdev_is_p2p(scifdev))
-			*dma_handle = *dma_handle + scifdev->base_addr;
-	}
-	if (err)
-		*dma_handle = 0;
-	return err;
-}
-#endif  /* SCIF_MAP_H */
diff --git a/drivers/misc/mic/scif/scif_mmap.c b/drivers/misc/mic/scif/scif_mmap.c
deleted file mode 100644
index a151d416f39c..000000000000
--- a/drivers/misc/mic/scif/scif_mmap.c
+++ /dev/null
@@ -1,690 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include "scif_main.h"
-
-/*
- * struct scif_vma_info - Information about a remote memory mapping
- *			  created via scif_mmap(..)
- * @vma: VM area struct
- * @list: link to list of active vmas
- */
-struct scif_vma_info {
-	struct vm_area_struct *vma;
-	struct list_head list;
-};
-
-void scif_recv_munmap(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	struct scif_rma_req req;
-	struct scif_window *window = NULL;
-	struct scif_window *recv_window =
-		(struct scif_window *)msg->payload[0];
-	struct scif_endpt *ep;
-
-	ep = (struct scif_endpt *)recv_window->ep;
-	req.out_window = &window;
-	req.offset = recv_window->offset;
-	req.prot = recv_window->prot;
-	req.nr_bytes = recv_window->nr_pages << PAGE_SHIFT;
-	req.type = SCIF_WINDOW_FULL;
-	req.head = &ep->rma_info.reg_list;
-	msg->payload[0] = ep->remote_ep;
-
-	mutex_lock(&ep->rma_info.rma_lock);
-	/* Does a valid window exist? */
-	if (scif_query_window(&req)) {
-		dev_err(&scifdev->sdev->dev,
-			"%s %d -ENXIO\n", __func__, __LINE__);
-		msg->uop = SCIF_UNREGISTER_ACK;
-		goto error;
-	}
-
-	scif_put_window(window, window->nr_pages);
-
-	if (!window->ref_count) {
-		atomic_inc(&ep->rma_info.tw_refcount);
-		ep->rma_info.async_list_del = 1;
-		list_del_init(&window->list);
-		scif_free_window_offset(ep, window, window->offset);
-	}
-error:
-	mutex_unlock(&ep->rma_info.rma_lock);
-	if (window && !window->ref_count)
-		scif_queue_for_cleanup(window, &scif_info.rma);
-}
-
-/*
- * Remove valid remote memory mappings created via scif_mmap(..) from the
- * process address space since the remote node is lost
- */
-static void __scif_zap_mmaps(struct scif_endpt *ep)
-{
-	struct list_head *item;
-	struct scif_vma_info *info;
-	struct vm_area_struct *vma;
-	unsigned long size;
-
-	spin_lock(&ep->lock);
-	list_for_each(item, &ep->rma_info.vma_list) {
-		info = list_entry(item, struct scif_vma_info, list);
-		vma = info->vma;
-		size = vma->vm_end - vma->vm_start;
-		zap_vma_ptes(vma, vma->vm_start, size);
-		dev_dbg(scif_info.mdev.this_device,
-			"%s ep %p zap vma %p size 0x%lx\n",
-			__func__, ep, info->vma, size);
-	}
-	spin_unlock(&ep->lock);
-}
-
-/*
- * Traverse the list of endpoints for a particular remote node and
- * zap valid remote memory mappings since the remote node is lost
- */
-static void _scif_zap_mmaps(int node, struct list_head *head)
-{
-	struct scif_endpt *ep;
-	struct list_head *item;
-
-	mutex_lock(&scif_info.connlock);
-	list_for_each(item, head) {
-		ep = list_entry(item, struct scif_endpt, list);
-		if (ep->remote_dev->node == node)
-			__scif_zap_mmaps(ep);
-	}
-	mutex_unlock(&scif_info.connlock);
-}
-
-/*
- * Wrapper for removing remote memory mappings for a particular node. This API
- * is called by peer nodes as part of handling a lost node.
- */
-void scif_zap_mmaps(int node)
-{
-	_scif_zap_mmaps(node, &scif_info.connected);
-	_scif_zap_mmaps(node, &scif_info.disconnected);
-}
-
-/*
- * This API is only called while handling a lost node:
- * a) Remote node is dead.
- * b) Remote memory mappings have been zapped
- * So we can traverse the remote_reg_list without any locks. Since
- * the window has not yet been unregistered we can drop the ref count
- * and queue it to the cleanup thread.
- */
-static void __scif_cleanup_rma_for_zombies(struct scif_endpt *ep)
-{
-	struct list_head *pos, *tmp;
-	struct scif_window *window;
-
-	list_for_each_safe(pos, tmp, &ep->rma_info.remote_reg_list) {
-		window = list_entry(pos, struct scif_window, list);
-		if (window->ref_count)
-			scif_put_window(window, window->nr_pages);
-		else
-			dev_err(scif_info.mdev.this_device,
-				"%s %d unexpected\n",
-				__func__, __LINE__);
-		if (!window->ref_count) {
-			atomic_inc(&ep->rma_info.tw_refcount);
-			list_del_init(&window->list);
-			scif_queue_for_cleanup(window, &scif_info.rma);
-		}
-	}
-}
-
-/* Cleanup remote registration lists for zombie endpoints */
-void scif_cleanup_rma_for_zombies(int node)
-{
-	struct scif_endpt *ep;
-	struct list_head *item;
-
-	mutex_lock(&scif_info.eplock);
-	list_for_each(item, &scif_info.zombie) {
-		ep = list_entry(item, struct scif_endpt, list);
-		if (ep->remote_dev && ep->remote_dev->node == node)
-			__scif_cleanup_rma_for_zombies(ep);
-	}
-	mutex_unlock(&scif_info.eplock);
-	flush_work(&scif_info.misc_work);
-}
-
-/* Insert the VMA into the per endpoint VMA list */
-static int scif_insert_vma(struct scif_endpt *ep, struct vm_area_struct *vma)
-{
-	struct scif_vma_info *info;
-	int err = 0;
-
-	info = kzalloc(sizeof(*info), GFP_KERNEL);
-	if (!info) {
-		err = -ENOMEM;
-		goto done;
-	}
-	info->vma = vma;
-	spin_lock(&ep->lock);
-	list_add_tail(&info->list, &ep->rma_info.vma_list);
-	spin_unlock(&ep->lock);
-done:
-	return err;
-}
-
-/* Delete the VMA from the per endpoint VMA list */
-static void scif_delete_vma(struct scif_endpt *ep, struct vm_area_struct *vma)
-{
-	struct list_head *item;
-	struct scif_vma_info *info;
-
-	spin_lock(&ep->lock);
-	list_for_each(item, &ep->rma_info.vma_list) {
-		info = list_entry(item, struct scif_vma_info, list);
-		if (info->vma == vma) {
-			list_del(&info->list);
-			kfree(info);
-			break;
-		}
-	}
-	spin_unlock(&ep->lock);
-}
-
-static phys_addr_t scif_get_phys(phys_addr_t phys, struct scif_endpt *ep)
-{
-	struct scif_dev *scifdev = (struct scif_dev *)ep->remote_dev;
-	struct scif_hw_dev *sdev = scifdev->sdev;
-	phys_addr_t out_phys, apt_base = 0;
-
-	/*
-	 * If the DMA address is card relative then we need to add the
-	 * aperture base for mmap to work correctly
-	 */
-	if (!scifdev_self(scifdev) && sdev->aper && sdev->card_rel_da)
-		apt_base = sdev->aper->pa;
-	out_phys = apt_base + phys;
-	return out_phys;
-}
-
-int scif_get_pages(scif_epd_t epd, off_t offset, size_t len,
-		   struct scif_range **pages)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)epd;
-	struct scif_rma_req req;
-	struct scif_window *window = NULL;
-	int nr_pages, err, i;
-
-	dev_dbg(scif_info.mdev.this_device,
-		"SCIFAPI get_pinned_pages: ep %p offset 0x%lx len 0x%lx\n",
-		ep, offset, len);
-	err = scif_verify_epd(ep);
-	if (err)
-		return err;
-
-	if (!len || (offset < 0) ||
-	    (offset + len < offset) ||
-	    (ALIGN(offset, PAGE_SIZE) != offset) ||
-	    (ALIGN(len, PAGE_SIZE) != len))
-		return -EINVAL;
-
-	nr_pages = len >> PAGE_SHIFT;
-
-	req.out_window = &window;
-	req.offset = offset;
-	req.prot = 0;
-	req.nr_bytes = len;
-	req.type = SCIF_WINDOW_SINGLE;
-	req.head = &ep->rma_info.remote_reg_list;
-
-	mutex_lock(&ep->rma_info.rma_lock);
-	/* Does a valid window exist? */
-	err = scif_query_window(&req);
-	if (err) {
-		dev_err(&ep->remote_dev->sdev->dev,
-			"%s %d err %d\n", __func__, __LINE__, err);
-		goto error;
-	}
-
-	/* Allocate scif_range */
-	*pages = kzalloc(sizeof(**pages), GFP_KERNEL);
-	if (!*pages) {
-		err = -ENOMEM;
-		goto error;
-	}
-
-	/* Allocate phys addr array */
-	(*pages)->phys_addr = scif_zalloc(nr_pages * sizeof(dma_addr_t));
-	if (!((*pages)->phys_addr)) {
-		err = -ENOMEM;
-		goto error;
-	}
-
-	if (scif_is_mgmt_node() && !scifdev_self(ep->remote_dev)) {
-		/* Allocate virtual address array */
-		((*pages)->va = scif_zalloc(nr_pages * sizeof(void *)));
-		if (!(*pages)->va) {
-			err = -ENOMEM;
-			goto error;
-		}
-	}
-	/* Populate the values */
-	(*pages)->cookie = window;
-	(*pages)->nr_pages = nr_pages;
-	(*pages)->prot_flags = window->prot;
-
-	for (i = 0; i < nr_pages; i++) {
-		(*pages)->phys_addr[i] =
-			__scif_off_to_dma_addr(window, offset +
-					       (i * PAGE_SIZE));
-		(*pages)->phys_addr[i] = scif_get_phys((*pages)->phys_addr[i],
-							ep);
-		if (scif_is_mgmt_node() && !scifdev_self(ep->remote_dev))
-			(*pages)->va[i] =
-				ep->remote_dev->sdev->aper->va +
-				(*pages)->phys_addr[i] -
-				ep->remote_dev->sdev->aper->pa;
-	}
-
-	scif_get_window(window, nr_pages);
-error:
-	mutex_unlock(&ep->rma_info.rma_lock);
-	if (err) {
-		if (*pages) {
-			scif_free((*pages)->phys_addr,
-				  nr_pages * sizeof(dma_addr_t));
-			scif_free((*pages)->va,
-				  nr_pages * sizeof(void *));
-			kfree(*pages);
-			*pages = NULL;
-		}
-		dev_err(&ep->remote_dev->sdev->dev,
-			"%s %d err %d\n", __func__, __LINE__, err);
-	}
-	return err;
-}
-EXPORT_SYMBOL_GPL(scif_get_pages);
-
-int scif_put_pages(struct scif_range *pages)
-{
-	struct scif_endpt *ep;
-	struct scif_window *window;
-	struct scifmsg msg;
-
-	if (!pages || !pages->cookie)
-		return -EINVAL;
-
-	window = pages->cookie;
-
-	if (!window || window->magic != SCIFEP_MAGIC)
-		return -EINVAL;
-
-	ep = (struct scif_endpt *)window->ep;
-	/*
-	 * If the state is SCIFEP_CONNECTED or SCIFEP_DISCONNECTED then the
-	 * callee should be allowed to release references to the pages,
-	 * else the endpoint was not connected in the first place,
-	 * hence the ENOTCONN.
-	 */
-	if (ep->state != SCIFEP_CONNECTED && ep->state != SCIFEP_DISCONNECTED)
-		return -ENOTCONN;
-
-	mutex_lock(&ep->rma_info.rma_lock);
-
-	scif_put_window(window, pages->nr_pages);
-
-	/* Initiate window destruction if ref count is zero */
-	if (!window->ref_count) {
-		list_del(&window->list);
-		mutex_unlock(&ep->rma_info.rma_lock);
-		scif_drain_dma_intr(ep->remote_dev->sdev,
-				    ep->rma_info.dma_chan);
-		/* Inform the peer about this window being destroyed. */
-		msg.uop = SCIF_MUNMAP;
-		msg.src = ep->port;
-		msg.payload[0] = window->peer_window;
-		/* No error handling for notification messages */
-		scif_nodeqp_send(ep->remote_dev, &msg);
-		/* Destroy this window from the peer's registered AS */
-		scif_destroy_remote_window(window);
-	} else {
-		mutex_unlock(&ep->rma_info.rma_lock);
-	}
-
-	scif_free(pages->phys_addr, pages->nr_pages * sizeof(dma_addr_t));
-	scif_free(pages->va, pages->nr_pages * sizeof(void *));
-	kfree(pages);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(scif_put_pages);
-
-/*
- * scif_rma_list_mmap:
- *
- * Traverse the remote registration list starting from start_window:
- * 1) Create VtoP mappings via remap_pfn_range(..)
- * 2) Once step 1) and 2) complete successfully then traverse the range of
- *    windows again and bump the reference count.
- * RMA lock must be held.
- */
-static int scif_rma_list_mmap(struct scif_window *start_window, s64 offset,
-			      int nr_pages, struct vm_area_struct *vma)
-{
-	s64 end_offset, loop_offset = offset;
-	struct scif_window *window = start_window;
-	int loop_nr_pages, nr_pages_left = nr_pages;
-	struct scif_endpt *ep = (struct scif_endpt *)start_window->ep;
-	struct list_head *head = &ep->rma_info.remote_reg_list;
-	int i, err = 0;
-	dma_addr_t phys_addr;
-	struct scif_window_iter src_win_iter;
-	size_t contig_bytes = 0;
-
-	might_sleep();
-	list_for_each_entry_from(window, head, list) {
-		end_offset = window->offset +
-			(window->nr_pages << PAGE_SHIFT);
-		loop_nr_pages = min_t(int,
-				      (end_offset - loop_offset) >> PAGE_SHIFT,
-				      nr_pages_left);
-		scif_init_window_iter(window, &src_win_iter);
-		for (i = 0; i < loop_nr_pages; i++) {
-			phys_addr = scif_off_to_dma_addr(window, loop_offset,
-							 &contig_bytes,
-							 &src_win_iter);
-			phys_addr = scif_get_phys(phys_addr, ep);
-			err = remap_pfn_range(vma,
-					      vma->vm_start +
-					      loop_offset - offset,
-					      phys_addr >> PAGE_SHIFT,
-					      PAGE_SIZE,
-					      vma->vm_page_prot);
-			if (err)
-				goto error;
-			loop_offset += PAGE_SIZE;
-		}
-		nr_pages_left -= loop_nr_pages;
-		if (!nr_pages_left)
-			break;
-	}
-	/*
-	 * No more failures expected. Bump up the ref count for all
-	 * the windows. Another traversal from start_window required
-	 * for handling errors encountered across windows during
-	 * remap_pfn_range(..).
-	 */
-	loop_offset = offset;
-	nr_pages_left = nr_pages;
-	window = start_window;
-	head = &ep->rma_info.remote_reg_list;
-	list_for_each_entry_from(window, head, list) {
-		end_offset = window->offset +
-			(window->nr_pages << PAGE_SHIFT);
-		loop_nr_pages = min_t(int,
-				      (end_offset - loop_offset) >> PAGE_SHIFT,
-				      nr_pages_left);
-		scif_get_window(window, loop_nr_pages);
-		nr_pages_left -= loop_nr_pages;
-		loop_offset += (loop_nr_pages << PAGE_SHIFT);
-		if (!nr_pages_left)
-			break;
-	}
-error:
-	if (err)
-		dev_err(scif_info.mdev.this_device,
-			"%s %d err %d\n", __func__, __LINE__, err);
-	return err;
-}
-
-/*
- * scif_rma_list_munmap:
- *
- * Traverse the remote registration list starting from window:
- * 1) Decrement ref count.
- * 2) If the ref count drops to zero then send a SCIF_MUNMAP message to peer.
- * RMA lock must be held.
- */
-static void scif_rma_list_munmap(struct scif_window *start_window,
-				 s64 offset, int nr_pages)
-{
-	struct scifmsg msg;
-	s64 loop_offset = offset, end_offset;
-	int loop_nr_pages, nr_pages_left = nr_pages;
-	struct scif_endpt *ep = (struct scif_endpt *)start_window->ep;
-	struct list_head *head = &ep->rma_info.remote_reg_list;
-	struct scif_window *window = start_window, *_window;
-
-	msg.uop = SCIF_MUNMAP;
-	msg.src = ep->port;
-	loop_offset = offset;
-	nr_pages_left = nr_pages;
-	list_for_each_entry_safe_from(window, _window, head, list) {
-		end_offset = window->offset +
-			(window->nr_pages << PAGE_SHIFT);
-		loop_nr_pages = min_t(int,
-				      (end_offset - loop_offset) >> PAGE_SHIFT,
-				      nr_pages_left);
-		scif_put_window(window, loop_nr_pages);
-		if (!window->ref_count) {
-			struct scif_dev *rdev = ep->remote_dev;
-
-			scif_drain_dma_intr(rdev->sdev,
-					    ep->rma_info.dma_chan);
-			/* Inform the peer about this munmap */
-			msg.payload[0] = window->peer_window;
-			/* No error handling for Notification messages. */
-			scif_nodeqp_send(ep->remote_dev, &msg);
-			list_del(&window->list);
-			/* Destroy this window from the peer's registered AS */
-			scif_destroy_remote_window(window);
-		}
-		nr_pages_left -= loop_nr_pages;
-		loop_offset += (loop_nr_pages << PAGE_SHIFT);
-		if (!nr_pages_left)
-			break;
-	}
-}
-
-/*
- * The private data field of each VMA used to mmap a remote window
- * points to an instance of struct vma_pvt
- */
-struct vma_pvt {
-	struct scif_endpt *ep;	/* End point for remote window */
-	s64 offset;		/* offset within remote window */
-	bool valid_offset;	/* offset is valid only if the original
-				 * mmap request was for a single page
-				 * else the offset within the vma is
-				 * the correct offset
-				 */
-	struct kref ref;
-};
-
-static void vma_pvt_release(struct kref *ref)
-{
-	struct vma_pvt *vmapvt = container_of(ref, struct vma_pvt, ref);
-
-	kfree(vmapvt);
-}
-
-/**
- * scif_vma_open - VMA open driver callback
- * @vma: VMM memory area.
- * The open method is called by the kernel to allow the subsystem implementing
- * the VMA to initialize the area. This method is invoked any time a new
- * reference to the VMA is made (when a process forks, for example).
- * The one exception happens when the VMA is first created by mmap;
- * in this case, the driver's mmap method is called instead.
- * This function is also invoked when an existing VMA is split by the kernel
- * due to a call to munmap on a subset of the VMA resulting in two VMAs.
- * The kernel invokes this function only on one of the two VMAs.
- */
-static void scif_vma_open(struct vm_area_struct *vma)
-{
-	struct vma_pvt *vmapvt = vma->vm_private_data;
-
-	dev_dbg(scif_info.mdev.this_device,
-		"SCIFAPI vma open: vma_start 0x%lx vma_end 0x%lx\n",
-		vma->vm_start, vma->vm_end);
-	scif_insert_vma(vmapvt->ep, vma);
-	kref_get(&vmapvt->ref);
-}
-
-/**
- * scif_munmap - VMA close driver callback.
- * @vma: VMM memory area.
- * When an area is destroyed, the kernel calls its close operation.
- * Note that there's no usage count associated with VMA's; the area
- * is opened and closed exactly once by each process that uses it.
- */
-static void scif_munmap(struct vm_area_struct *vma)
-{
-	struct scif_endpt *ep;
-	struct vma_pvt *vmapvt = vma->vm_private_data;
-	int nr_pages = vma_pages(vma);
-	s64 offset;
-	struct scif_rma_req req;
-	struct scif_window *window = NULL;
-	int err;
-
-	might_sleep();
-	dev_dbg(scif_info.mdev.this_device,
-		"SCIFAPI munmap: vma_start 0x%lx vma_end 0x%lx\n",
-		vma->vm_start, vma->vm_end);
-	ep = vmapvt->ep;
-	offset = vmapvt->valid_offset ? vmapvt->offset :
-		(vma->vm_pgoff) << PAGE_SHIFT;
-	dev_dbg(scif_info.mdev.this_device,
-		"SCIFAPI munmap: ep %p nr_pages 0x%x offset 0x%llx\n",
-		ep, nr_pages, offset);
-	req.out_window = &window;
-	req.offset = offset;
-	req.nr_bytes = vma->vm_end - vma->vm_start;
-	req.prot = vma->vm_flags & (VM_READ | VM_WRITE);
-	req.type = SCIF_WINDOW_PARTIAL;
-	req.head = &ep->rma_info.remote_reg_list;
-
-	mutex_lock(&ep->rma_info.rma_lock);
-
-	err = scif_query_window(&req);
-	if (err)
-		dev_err(scif_info.mdev.this_device,
-			"%s %d err %d\n", __func__, __LINE__, err);
-	else
-		scif_rma_list_munmap(window, offset, nr_pages);
-
-	mutex_unlock(&ep->rma_info.rma_lock);
-	/*
-	 * The kernel probably zeroes these out but we still want
-	 * to clean up our own mess just in case.
-	 */
-	vma->vm_ops = NULL;
-	vma->vm_private_data = NULL;
-	kref_put(&vmapvt->ref, vma_pvt_release);
-	scif_delete_vma(ep, vma);
-}
-
-static const struct vm_operations_struct scif_vm_ops = {
-	.open = scif_vma_open,
-	.close = scif_munmap,
-};
-
-/**
- * scif_mmap - Map pages in virtual address space to a remote window.
- * @vma: VMM memory area.
- * @epd: endpoint descriptor
- *
- * Return: Upon successful completion, scif_mmap() returns zero
- * else an apt error is returned as documented in scif.h
- */
-int scif_mmap(struct vm_area_struct *vma, scif_epd_t epd)
-{
-	struct scif_rma_req req;
-	struct scif_window *window = NULL;
-	struct scif_endpt *ep = (struct scif_endpt *)epd;
-	s64 start_offset = vma->vm_pgoff << PAGE_SHIFT;
-	int nr_pages = vma_pages(vma);
-	int err;
-	struct vma_pvt *vmapvt;
-
-	dev_dbg(scif_info.mdev.this_device,
-		"SCIFAPI mmap: ep %p start_offset 0x%llx nr_pages 0x%x\n",
-		ep, start_offset, nr_pages);
-	err = scif_verify_epd(ep);
-	if (err)
-		return err;
-
-	might_sleep();
-
-	err = scif_insert_vma(ep, vma);
-	if (err)
-		return err;
-
-	vmapvt = kzalloc(sizeof(*vmapvt), GFP_KERNEL);
-	if (!vmapvt) {
-		scif_delete_vma(ep, vma);
-		return -ENOMEM;
-	}
-
-	vmapvt->ep = ep;
-	kref_init(&vmapvt->ref);
-
-	req.out_window = &window;
-	req.offset = start_offset;
-	req.nr_bytes = vma->vm_end - vma->vm_start;
-	req.prot = vma->vm_flags & (VM_READ | VM_WRITE);
-	req.type = SCIF_WINDOW_PARTIAL;
-	req.head = &ep->rma_info.remote_reg_list;
-
-	mutex_lock(&ep->rma_info.rma_lock);
-	/* Does a valid window exist? */
-	err = scif_query_window(&req);
-	if (err) {
-		dev_err(&ep->remote_dev->sdev->dev,
-			"%s %d err %d\n", __func__, __LINE__, err);
-		goto error_unlock;
-	}
-
-	/* Default prot for loopback */
-	if (!scifdev_self(ep->remote_dev))
-		vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
-
-	/*
-	 * VM_DONTCOPY - Do not copy this vma on fork
-	 * VM_DONTEXPAND - Cannot expand with mremap()
-	 * VM_RESERVED - Count as reserved_vm like IO
-	 * VM_PFNMAP - Page-ranges managed without "struct page"
-	 * VM_IO - Memory mapped I/O or similar
-	 *
-	 * We do not want to copy this VMA automatically on a fork(),
-	 * expand this VMA due to mremap() or swap out these pages since
-	 * the VMA is actually backed by physical pages in the remote
-	 * node's physical memory and not via a struct page.
-	 */
-	vma->vm_flags |= VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP;
-
-	if (!scifdev_self(ep->remote_dev))
-		vma->vm_flags |= VM_IO | VM_PFNMAP;
-
-	/* Map this range of windows */
-	err = scif_rma_list_mmap(window, start_offset, nr_pages, vma);
-	if (err) {
-		dev_err(&ep->remote_dev->sdev->dev,
-			"%s %d err %d\n", __func__, __LINE__, err);
-		goto error_unlock;
-	}
-	/* Set up the driver call back */
-	vma->vm_ops = &scif_vm_ops;
-	vma->vm_private_data = vmapvt;
-error_unlock:
-	mutex_unlock(&ep->rma_info.rma_lock);
-	if (err) {
-		kfree(vmapvt);
-		dev_err(&ep->remote_dev->sdev->dev,
-			"%s %d err %d\n", __func__, __LINE__, err);
-		scif_delete_vma(ep, vma);
-	}
-	return err;
-}
diff --git a/drivers/misc/mic/scif/scif_nm.c b/drivers/misc/mic/scif/scif_nm.c
deleted file mode 100644
index c4d9422082b7..000000000000
--- a/drivers/misc/mic/scif/scif_nm.c
+++ /dev/null
@@ -1,229 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include "scif_peer_bus.h"
-
-#include "scif_main.h"
-#include "scif_map.h"
-
-/**
- * scif_invalidate_ep() - Set state for all connected endpoints
- * to disconnected and wake up all send/recv waitqueues
- *
- * @node: Node to invalidate
- */
-static void scif_invalidate_ep(int node)
-{
-	struct scif_endpt *ep;
-	struct list_head *pos, *tmpq;
-
-	flush_work(&scif_info.conn_work);
-	mutex_lock(&scif_info.connlock);
-	list_for_each_safe(pos, tmpq, &scif_info.disconnected) {
-		ep = list_entry(pos, struct scif_endpt, list);
-		if (ep->remote_dev->node == node) {
-			scif_unmap_all_windows(ep);
-			spin_lock(&ep->lock);
-			scif_cleanup_ep_qp(ep);
-			spin_unlock(&ep->lock);
-		}
-	}
-	list_for_each_safe(pos, tmpq, &scif_info.connected) {
-		ep = list_entry(pos, struct scif_endpt, list);
-		if (ep->remote_dev->node == node) {
-			list_del(pos);
-			spin_lock(&ep->lock);
-			ep->state = SCIFEP_DISCONNECTED;
-			list_add_tail(&ep->list, &scif_info.disconnected);
-			scif_cleanup_ep_qp(ep);
-			wake_up_interruptible(&ep->sendwq);
-			wake_up_interruptible(&ep->recvwq);
-			spin_unlock(&ep->lock);
-			scif_unmap_all_windows(ep);
-		}
-	}
-	mutex_unlock(&scif_info.connlock);
-}
-
-void scif_free_qp(struct scif_dev *scifdev)
-{
-	struct scif_qp *qp = scifdev->qpairs;
-
-	if (!qp)
-		return;
-	scif_unmap_single(qp->local_buf, scifdev, qp->inbound_q.size);
-	kfree(qp->inbound_q.rb_base);
-	scif_unmap_single(qp->local_qp, scifdev, sizeof(struct scif_qp));
-	kfree(scifdev->qpairs);
-	scifdev->qpairs = NULL;
-}
-
-static void scif_cleanup_qp(struct scif_dev *dev)
-{
-	struct scif_qp *qp = &dev->qpairs[0];
-
-	if (!qp)
-		return;
-	scif_iounmap((void *)qp->remote_qp, sizeof(struct scif_qp), dev);
-	scif_iounmap((void *)qp->outbound_q.rb_base,
-		     sizeof(struct scif_qp), dev);
-	qp->remote_qp = NULL;
-	qp->local_write = 0;
-	qp->inbound_q.current_write_offset = 0;
-	qp->inbound_q.current_read_offset = 0;
-	if (scifdev_is_p2p(dev))
-		scif_free_qp(dev);
-}
-
-void scif_send_acks(struct scif_dev *dev)
-{
-	struct scifmsg msg;
-
-	if (dev->node_remove_ack_pending) {
-		msg.uop = SCIF_NODE_REMOVE_ACK;
-		msg.src.node = scif_info.nodeid;
-		msg.dst.node = SCIF_MGMT_NODE;
-		msg.payload[0] = dev->node;
-		scif_nodeqp_send(&scif_dev[SCIF_MGMT_NODE], &msg);
-		dev->node_remove_ack_pending = false;
-	}
-	if (dev->exit_ack_pending) {
-		msg.uop = SCIF_EXIT_ACK;
-		msg.src.node = scif_info.nodeid;
-		msg.dst.node = dev->node;
-		scif_nodeqp_send(dev, &msg);
-		dev->exit_ack_pending = false;
-	}
-}
-
-/**
- * scif_cleanup_scifdev - Uninitialize SCIF data structures for remote
- *                        SCIF device.
- * @dev: Remote SCIF device.
- */
-void scif_cleanup_scifdev(struct scif_dev *dev)
-{
-	struct scif_hw_dev *sdev = dev->sdev;
-
-	if (!dev->sdev)
-		return;
-	if (scifdev_is_p2p(dev)) {
-		if (dev->cookie) {
-			sdev->hw_ops->free_irq(sdev, dev->cookie, dev);
-			dev->cookie = NULL;
-		}
-		scif_destroy_intr_wq(dev);
-	}
-	flush_work(&scif_info.misc_work);
-	scif_destroy_p2p(dev);
-	scif_invalidate_ep(dev->node);
-	scif_zap_mmaps(dev->node);
-	scif_cleanup_rma_for_zombies(dev->node);
-	flush_work(&scif_info.misc_work);
-	scif_send_acks(dev);
-	if (!dev->node && scif_info.card_initiated_exit) {
-		/*
-		 * Send an SCIF_EXIT message which is the last message from MIC
-		 * to the Host and wait for a SCIF_EXIT_ACK
-		 */
-		scif_send_exit(dev);
-		scif_info.card_initiated_exit = false;
-	}
-	scif_cleanup_qp(dev);
-}
-
-/**
- * scif_remove_node
- *
- * @node: Node to remove
- */
-void scif_handle_remove_node(int node)
-{
-	struct scif_dev *scifdev = &scif_dev[node];
-
-	if (scif_peer_unregister_device(scifdev))
-		scif_send_acks(scifdev);
-}
-
-static int scif_send_rmnode_msg(int node, int remove_node)
-{
-	struct scifmsg notif_msg;
-	struct scif_dev *dev = &scif_dev[node];
-
-	notif_msg.uop = SCIF_NODE_REMOVE;
-	notif_msg.src.node = scif_info.nodeid;
-	notif_msg.dst.node = node;
-	notif_msg.payload[0] = remove_node;
-	return scif_nodeqp_send(dev, &notif_msg);
-}
-
-/**
- * scif_node_disconnect
- *
- * @node_id: source node id [in]
- * @mgmt_initiated: Disconnection initiated from the mgmt node
- *
- * Disconnect a node from the scif network.
- */
-void scif_disconnect_node(u32 node_id, bool mgmt_initiated)
-{
-	int ret;
-	int msg_cnt = 0;
-	u32 i = 0;
-	struct scif_dev *scifdev = &scif_dev[node_id];
-
-	if (!node_id)
-		return;
-
-	atomic_set(&scifdev->disconn_rescnt, 0);
-
-	/* Destroy p2p network */
-	for (i = 1; i <= scif_info.maxid; i++) {
-		if (i == node_id)
-			continue;
-		ret = scif_send_rmnode_msg(i, node_id);
-		if (!ret)
-			msg_cnt++;
-	}
-	/* Wait for the remote nodes to respond with SCIF_NODE_REMOVE_ACK */
-	ret = wait_event_timeout(scifdev->disconn_wq,
-				 (atomic_read(&scifdev->disconn_rescnt)
-				 == msg_cnt), SCIF_NODE_ALIVE_TIMEOUT);
-	/* Tell the card to clean up */
-	if (mgmt_initiated && _scifdev_alive(scifdev))
-		/*
-		 * Send an SCIF_EXIT message which is the last message from Host
-		 * to the MIC and wait for a SCIF_EXIT_ACK
-		 */
-		scif_send_exit(scifdev);
-	atomic_set(&scifdev->disconn_rescnt, 0);
-	/* Tell the mgmt node to clean up */
-	ret = scif_send_rmnode_msg(SCIF_MGMT_NODE, node_id);
-	if (!ret)
-		/* Wait for mgmt node to respond with SCIF_NODE_REMOVE_ACK */
-		wait_event_timeout(scifdev->disconn_wq,
-				   (atomic_read(&scifdev->disconn_rescnt) == 1),
-				   SCIF_NODE_ALIVE_TIMEOUT);
-}
-
-void scif_get_node_info(void)
-{
-	struct scifmsg msg;
-	DECLARE_COMPLETION_ONSTACK(node_info);
-
-	msg.uop = SCIF_GET_NODE_INFO;
-	msg.src.node = scif_info.nodeid;
-	msg.dst.node = SCIF_MGMT_NODE;
-	msg.payload[3] = (u64)&node_info;
-
-	if ((scif_nodeqp_send(&scif_dev[SCIF_MGMT_NODE], &msg)))
-		return;
-
-	/* Wait for a response with SCIF_GET_NODE_INFO */
-	wait_for_completion(&node_info);
-}
diff --git a/drivers/misc/mic/scif/scif_nodeqp.c b/drivers/misc/mic/scif/scif_nodeqp.c
deleted file mode 100644
index 384ce08fa98a..000000000000
--- a/drivers/misc/mic/scif/scif_nodeqp.c
+++ /dev/null
@@ -1,1349 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include "../bus/scif_bus.h"
-#include "scif_peer_bus.h"
-#include "scif_main.h"
-#include "scif_nodeqp.h"
-#include "scif_map.h"
-
-/*
- ************************************************************************
- * SCIF node Queue Pair (QP) setup flow:
- *
- * 1) SCIF driver gets probed with a scif_hw_dev via the scif_hw_bus
- * 2) scif_setup_qp(..) allocates the local qp and calls
- *	scif_setup_qp_connect(..) which allocates and maps the local
- *	buffer for the inbound QP
- * 3) The local node updates the device page with the DMA address of the QP
- * 4) A delayed work is scheduled (qp_dwork) which periodically reads if
- *	the peer node has updated its QP DMA address
- * 5) Once a valid non zero address is found in the QP DMA address field
- *	in the device page, the local node maps the remote node's QP,
- *	updates its outbound QP and sends a SCIF_INIT message to the peer
- * 6) The SCIF_INIT message is received by the peer node QP interrupt bottom
- *	half handler by calling scif_init(..)
- * 7) scif_init(..) registers a new SCIF peer node by calling
- *	scif_peer_register_device(..) which signifies the addition of a new
- *	SCIF node
- * 8) On the mgmt node, P2P network setup/teardown is initiated if all the
- *	remote nodes are online via scif_p2p_setup(..)
- * 9) For P2P setup, the host maps the remote nodes' aperture and memory
- *	bars and sends a SCIF_NODE_ADD message to both nodes
- * 10) As part of scif_nodeadd, both nodes set up their local inbound
- *	QPs and send a SCIF_NODE_ADD_ACK to the mgmt node
- * 11) As part of scif_node_add_ack(..) the mgmt node forwards the
- *	SCIF_NODE_ADD_ACK to the remote nodes
- * 12) As part of scif_node_add_ack(..) the remote nodes update their
- *	outbound QPs, make sure they can access memory on the remote node
- *	and then add a new SCIF peer node by calling
- *	scif_peer_register_device(..) which signifies the addition of a new
- *	SCIF node.
- * 13) The SCIF network is now established across all nodes.
- *
- ************************************************************************
- * SCIF node QP teardown flow (initiated by non mgmt node):
- *
- * 1) SCIF driver gets a remove callback with a scif_hw_dev via the scif_hw_bus
- * 2) The device page QP DMA address field is updated with 0x0
- * 3) A non mgmt node now cleans up all local data structures and sends a
- *	SCIF_EXIT message to the peer and waits for a SCIF_EXIT_ACK
- * 4) As part of scif_exit(..) handling scif_disconnect_node(..) is called
- * 5) scif_disconnect_node(..) sends a SCIF_NODE_REMOVE message to all the
- *	peers and waits for a SCIF_NODE_REMOVE_ACK
- * 6) As part of scif_node_remove(..) a remote node unregisters the peer
- *	node from the SCIF network and sends a SCIF_NODE_REMOVE_ACK
- * 7) When the mgmt node has received all the SCIF_NODE_REMOVE_ACKs
- *	it sends itself a node remove message whose handling cleans up local
- *	data structures and unregisters the peer node from the SCIF network
- * 8) The mgmt node sends a SCIF_EXIT_ACK
- * 9) Upon receipt of the SCIF_EXIT_ACK the node initiating the teardown
- *	completes the SCIF remove routine
- * 10) The SCIF network is now torn down for the node initiating the
- *	teardown sequence
- *
- ************************************************************************
- * SCIF node QP teardown flow (initiated by mgmt node):
- *
- * 1) SCIF driver gets a remove callback with a scif_hw_dev via the scif_hw_bus
- * 2) The device page QP DMA address field is updated with 0x0
- * 3) The mgmt node calls scif_disconnect_node(..)
- * 4) scif_disconnect_node(..) sends a SCIF_NODE_REMOVE message to all the peers
- *	and waits for a SCIF_NODE_REMOVE_ACK
- * 5) As part of scif_node_remove(..) a remote node unregisters the peer
- *	node from the SCIF network and sends a SCIF_NODE_REMOVE_ACK
- * 6) When the mgmt node has received all the SCIF_NODE_REMOVE_ACKs
- *	it unregisters the peer node from the SCIF network
- * 7) The mgmt node sends a SCIF_EXIT message and waits for a SCIF_EXIT_ACK.
- * 8) A non mgmt node upon receipt of a SCIF_EXIT message calls scif_stop(..)
- *	which would clean up local data structures for all SCIF nodes and
- *	then send a SCIF_EXIT_ACK back to the mgmt node
- * 9) Upon receipt of the SCIF_EXIT_ACK the the mgmt node sends itself a node
- *	remove message whose handling cleans up local data structures and
- *	destroys any P2P mappings.
- * 10) The SCIF hardware device for which a remove callback was received is now
- *	disconnected from the SCIF network.
- */
-/*
- * Initializes "local" data structures for the QP. Allocates the QP
- * ring buffer (rb) and initializes the "in bound" queue.
- */
-int scif_setup_qp_connect(struct scif_qp *qp, dma_addr_t *qp_offset,
-			  int local_size, struct scif_dev *scifdev)
-{
-	void *local_q = qp->inbound_q.rb_base;
-	int err = 0;
-	u32 tmp_rd = 0;
-
-	spin_lock_init(&qp->send_lock);
-	spin_lock_init(&qp->recv_lock);
-
-	/* Allocate rb only if not already allocated */
-	if (!local_q) {
-		local_q = kzalloc(local_size, GFP_KERNEL);
-		if (!local_q) {
-			err = -ENOMEM;
-			return err;
-		}
-	}
-
-	err = scif_map_single(&qp->local_buf, local_q, scifdev, local_size);
-	if (err)
-		goto kfree;
-	/*
-	 * To setup the inbound_q, the buffer lives locally, the read pointer
-	 * is remote and the write pointer is local.
-	 */
-	scif_rb_init(&qp->inbound_q,
-		     &tmp_rd,
-		     &qp->local_write,
-		     local_q, get_count_order(local_size));
-	/*
-	 * The read pointer is NULL initially and it is unsafe to use the ring
-	 * buffer til this changes!
-	 */
-	qp->inbound_q.read_ptr = NULL;
-	err = scif_map_single(qp_offset, qp,
-			      scifdev, sizeof(struct scif_qp));
-	if (err)
-		goto unmap;
-	qp->local_qp = *qp_offset;
-	return err;
-unmap:
-	scif_unmap_single(qp->local_buf, scifdev, local_size);
-	qp->local_buf = 0;
-kfree:
-	kfree(local_q);
-	return err;
-}
-
-/* When the other side has already done it's allocation, this is called */
-int scif_setup_qp_accept(struct scif_qp *qp, dma_addr_t *qp_offset,
-			 dma_addr_t phys, int local_size,
-			 struct scif_dev *scifdev)
-{
-	void *local_q;
-	void *remote_q;
-	struct scif_qp *remote_qp;
-	int remote_size;
-	int err = 0;
-
-	spin_lock_init(&qp->send_lock);
-	spin_lock_init(&qp->recv_lock);
-	/* Start by figuring out where we need to point */
-	remote_qp = scif_ioremap(phys, sizeof(struct scif_qp), scifdev);
-	if (!remote_qp)
-		return -EIO;
-	qp->remote_qp = remote_qp;
-	if (qp->remote_qp->magic != SCIFEP_MAGIC) {
-		err = -EIO;
-		goto iounmap;
-	}
-	qp->remote_buf = remote_qp->local_buf;
-	remote_size = qp->remote_qp->inbound_q.size;
-	remote_q = scif_ioremap(qp->remote_buf, remote_size, scifdev);
-	if (!remote_q) {
-		err = -EIO;
-		goto iounmap;
-	}
-	qp->remote_qp->local_write = 0;
-	/*
-	 * To setup the outbound_q, the buffer lives in remote memory,
-	 * the read pointer is local, the write pointer is remote
-	 */
-	scif_rb_init(&qp->outbound_q,
-		     &qp->local_read,
-		     &qp->remote_qp->local_write,
-		     remote_q,
-		     get_count_order(remote_size));
-	local_q = kzalloc(local_size, GFP_KERNEL);
-	if (!local_q) {
-		err = -ENOMEM;
-		goto iounmap_1;
-	}
-	err = scif_map_single(&qp->local_buf, local_q, scifdev, local_size);
-	if (err)
-		goto kfree;
-	qp->remote_qp->local_read = 0;
-	/*
-	 * To setup the inbound_q, the buffer lives locally, the read pointer
-	 * is remote and the write pointer is local
-	 */
-	scif_rb_init(&qp->inbound_q,
-		     &qp->remote_qp->local_read,
-		     &qp->local_write,
-		     local_q, get_count_order(local_size));
-	err = scif_map_single(qp_offset, qp, scifdev,
-			      sizeof(struct scif_qp));
-	if (err)
-		goto unmap;
-	qp->local_qp = *qp_offset;
-	return err;
-unmap:
-	scif_unmap_single(qp->local_buf, scifdev, local_size);
-	qp->local_buf = 0;
-kfree:
-	kfree(local_q);
-iounmap_1:
-	scif_iounmap(remote_q, remote_size, scifdev);
-	qp->outbound_q.rb_base = NULL;
-iounmap:
-	scif_iounmap(qp->remote_qp, sizeof(struct scif_qp), scifdev);
-	qp->remote_qp = NULL;
-	return err;
-}
-
-int scif_setup_qp_connect_response(struct scif_dev *scifdev,
-				   struct scif_qp *qp, u64 payload)
-{
-	int err = 0;
-	void *r_buf;
-	int remote_size;
-	phys_addr_t tmp_phys;
-
-	qp->remote_qp = scif_ioremap(payload, sizeof(struct scif_qp), scifdev);
-
-	if (!qp->remote_qp) {
-		err = -ENOMEM;
-		goto error;
-	}
-
-	if (qp->remote_qp->magic != SCIFEP_MAGIC) {
-		dev_err(&scifdev->sdev->dev,
-			"SCIFEP_MAGIC mismatch between self %d remote %d\n",
-			scif_dev[scif_info.nodeid].node, scifdev->node);
-		err = -ENODEV;
-		goto error;
-	}
-
-	tmp_phys = qp->remote_qp->local_buf;
-	remote_size = qp->remote_qp->inbound_q.size;
-	r_buf = scif_ioremap(tmp_phys, remote_size, scifdev);
-
-	if (!r_buf)
-		return -EIO;
-
-	qp->local_read = 0;
-	scif_rb_init(&qp->outbound_q,
-		     &qp->local_read,
-		     &qp->remote_qp->local_write,
-		     r_buf,
-		     get_count_order(remote_size));
-	/*
-	 * Because the node QP may already be processing an INIT message, set
-	 * the read pointer so the cached read offset isn't lost
-	 */
-	qp->remote_qp->local_read = qp->inbound_q.current_read_offset;
-	/*
-	 * resetup the inbound_q now that we know where the
-	 * inbound_read really is.
-	 */
-	scif_rb_init(&qp->inbound_q,
-		     &qp->remote_qp->local_read,
-		     &qp->local_write,
-		     qp->inbound_q.rb_base,
-		     get_count_order(qp->inbound_q.size));
-error:
-	return err;
-}
-
-static __always_inline void
-scif_send_msg_intr(struct scif_dev *scifdev)
-{
-	struct scif_hw_dev *sdev = scifdev->sdev;
-
-	if (scifdev_is_p2p(scifdev))
-		sdev->hw_ops->send_p2p_intr(sdev, scifdev->rdb, &scifdev->mmio);
-	else
-		sdev->hw_ops->send_intr(sdev, scifdev->rdb);
-}
-
-int scif_qp_response(phys_addr_t phys, struct scif_dev *scifdev)
-{
-	int err = 0;
-	struct scifmsg msg;
-
-	err = scif_setup_qp_connect_response(scifdev, scifdev->qpairs, phys);
-	if (!err) {
-		/*
-		 * Now that everything is setup and mapped, we're ready
-		 * to tell the peer about our queue's location
-		 */
-		msg.uop = SCIF_INIT;
-		msg.dst.node = scifdev->node;
-		err = scif_nodeqp_send(scifdev, &msg);
-	}
-	return err;
-}
-
-void scif_send_exit(struct scif_dev *scifdev)
-{
-	struct scifmsg msg;
-	int ret;
-
-	scifdev->exit = OP_IN_PROGRESS;
-	msg.uop = SCIF_EXIT;
-	msg.src.node = scif_info.nodeid;
-	msg.dst.node = scifdev->node;
-	ret = scif_nodeqp_send(scifdev, &msg);
-	if (ret)
-		goto done;
-	/* Wait for a SCIF_EXIT_ACK message */
-	wait_event_timeout(scif_info.exitwq, scifdev->exit == OP_COMPLETED,
-			   SCIF_NODE_ALIVE_TIMEOUT);
-done:
-	scifdev->exit = OP_IDLE;
-}
-
-int scif_setup_qp(struct scif_dev *scifdev)
-{
-	int err = 0;
-	int local_size;
-	struct scif_qp *qp;
-
-	local_size = SCIF_NODE_QP_SIZE;
-
-	qp = kzalloc(sizeof(*qp), GFP_KERNEL);
-	if (!qp) {
-		err = -ENOMEM;
-		return err;
-	}
-	qp->magic = SCIFEP_MAGIC;
-	scifdev->qpairs = qp;
-	err = scif_setup_qp_connect(qp, &scifdev->qp_dma_addr,
-				    local_size, scifdev);
-	if (err)
-		goto free_qp;
-	/*
-	 * We're as setup as we can be. The inbound_q is setup, w/o a usable
-	 * outbound q.  When we get a message, the read_ptr will be updated,
-	 * and we will pull the message.
-	 */
-	return err;
-free_qp:
-	kfree(scifdev->qpairs);
-	scifdev->qpairs = NULL;
-	return err;
-}
-
-static void scif_p2p_freesg(struct scatterlist *sg)
-{
-	kfree(sg);
-}
-
-static struct scatterlist *
-scif_p2p_setsg(phys_addr_t pa, int page_size, int page_cnt)
-{
-	struct scatterlist *sg;
-	struct page *page;
-	int i;
-
-	sg = kmalloc_array(page_cnt, sizeof(struct scatterlist), GFP_KERNEL);
-	if (!sg)
-		return NULL;
-	sg_init_table(sg, page_cnt);
-	for (i = 0; i < page_cnt; i++) {
-		page = pfn_to_page(pa >> PAGE_SHIFT);
-		sg_set_page(&sg[i], page, page_size, 0);
-		pa += page_size;
-	}
-	return sg;
-}
-
-/* Init p2p mappings required to access peerdev from scifdev */
-static struct scif_p2p_info *
-scif_init_p2p_info(struct scif_dev *scifdev, struct scif_dev *peerdev)
-{
-	struct scif_p2p_info *p2p;
-	int num_mmio_pages, num_aper_pages, sg_page_shift, err, num_aper_chunks;
-	struct scif_hw_dev *psdev = peerdev->sdev;
-	struct scif_hw_dev *sdev = scifdev->sdev;
-
-	num_mmio_pages = psdev->mmio->len >> PAGE_SHIFT;
-	num_aper_pages = psdev->aper->len >> PAGE_SHIFT;
-
-	p2p = kzalloc(sizeof(*p2p), GFP_KERNEL);
-	if (!p2p)
-		return NULL;
-	p2p->ppi_sg[SCIF_PPI_MMIO] = scif_p2p_setsg(psdev->mmio->pa,
-						    PAGE_SIZE, num_mmio_pages);
-	if (!p2p->ppi_sg[SCIF_PPI_MMIO])
-		goto free_p2p;
-	p2p->sg_nentries[SCIF_PPI_MMIO] = num_mmio_pages;
-	sg_page_shift = get_order(min(psdev->aper->len, (u64)(1 << 30)));
-	num_aper_chunks = num_aper_pages >> (sg_page_shift - PAGE_SHIFT);
-	p2p->ppi_sg[SCIF_PPI_APER] = scif_p2p_setsg(psdev->aper->pa,
-						    1 << sg_page_shift,
-						    num_aper_chunks);
-	p2p->sg_nentries[SCIF_PPI_APER] = num_aper_chunks;
-	err = dma_map_sg(&sdev->dev, p2p->ppi_sg[SCIF_PPI_MMIO],
-			 num_mmio_pages, PCI_DMA_BIDIRECTIONAL);
-	if (err != num_mmio_pages)
-		goto scif_p2p_free;
-	err = dma_map_sg(&sdev->dev, p2p->ppi_sg[SCIF_PPI_APER],
-			 num_aper_chunks, PCI_DMA_BIDIRECTIONAL);
-	if (err != num_aper_chunks)
-		goto dma_unmap;
-	p2p->ppi_da[SCIF_PPI_MMIO] = sg_dma_address(p2p->ppi_sg[SCIF_PPI_MMIO]);
-	p2p->ppi_da[SCIF_PPI_APER] = sg_dma_address(p2p->ppi_sg[SCIF_PPI_APER]);
-	p2p->ppi_len[SCIF_PPI_MMIO] = num_mmio_pages;
-	p2p->ppi_len[SCIF_PPI_APER] = num_aper_pages;
-	p2p->ppi_peer_id = peerdev->node;
-	return p2p;
-dma_unmap:
-	dma_unmap_sg(&sdev->dev, p2p->ppi_sg[SCIF_PPI_MMIO],
-		     p2p->sg_nentries[SCIF_PPI_MMIO], DMA_BIDIRECTIONAL);
-scif_p2p_free:
-	scif_p2p_freesg(p2p->ppi_sg[SCIF_PPI_MMIO]);
-	scif_p2p_freesg(p2p->ppi_sg[SCIF_PPI_APER]);
-free_p2p:
-	kfree(p2p);
-	return NULL;
-}
-
-/* Uninitialize and release resources from a p2p mapping */
-static void scif_deinit_p2p_info(struct scif_dev *scifdev,
-				 struct scif_p2p_info *p2p)
-{
-	struct scif_hw_dev *sdev = scifdev->sdev;
-
-	dma_unmap_sg(&sdev->dev, p2p->ppi_sg[SCIF_PPI_MMIO],
-		     p2p->sg_nentries[SCIF_PPI_MMIO], DMA_BIDIRECTIONAL);
-	dma_unmap_sg(&sdev->dev, p2p->ppi_sg[SCIF_PPI_APER],
-		     p2p->sg_nentries[SCIF_PPI_APER], DMA_BIDIRECTIONAL);
-	scif_p2p_freesg(p2p->ppi_sg[SCIF_PPI_MMIO]);
-	scif_p2p_freesg(p2p->ppi_sg[SCIF_PPI_APER]);
-	kfree(p2p);
-}
-
-/**
- * scif_node_connect: Respond to SCIF_NODE_CONNECT interrupt message
- * @scifdev: SCIF device
- * @dst: Destination node
- *
- * Connect the src and dst node by setting up the p2p connection
- * between them. Management node here acts like a proxy.
- */
-static void scif_node_connect(struct scif_dev *scifdev, int dst)
-{
-	struct scif_dev *dev_j = scifdev;
-	struct scif_dev *dev_i = NULL;
-	struct scif_p2p_info *p2p_ij = NULL;    /* bus addr for j from i */
-	struct scif_p2p_info *p2p_ji = NULL;    /* bus addr for i from j */
-	struct scif_p2p_info *p2p;
-	struct list_head *pos, *tmp;
-	struct scifmsg msg;
-	int err;
-	u64 tmppayload;
-
-	if (dst < 1 || dst > scif_info.maxid)
-		return;
-
-	dev_i = &scif_dev[dst];
-
-	if (!_scifdev_alive(dev_i))
-		return;
-	/*
-	 * If the p2p connection is already setup or in the process of setting
-	 * up then just ignore this request. The requested node will get
-	 * informed by SCIF_NODE_ADD_ACK or SCIF_NODE_ADD_NACK
-	 */
-	if (!list_empty(&dev_i->p2p)) {
-		list_for_each_safe(pos, tmp, &dev_i->p2p) {
-			p2p = list_entry(pos, struct scif_p2p_info, ppi_list);
-			if (p2p->ppi_peer_id == dev_j->node)
-				return;
-		}
-	}
-	p2p_ij = scif_init_p2p_info(dev_i, dev_j);
-	if (!p2p_ij)
-		return;
-	p2p_ji = scif_init_p2p_info(dev_j, dev_i);
-	if (!p2p_ji) {
-		scif_deinit_p2p_info(dev_i, p2p_ij);
-		return;
-	}
-	list_add_tail(&p2p_ij->ppi_list, &dev_i->p2p);
-	list_add_tail(&p2p_ji->ppi_list, &dev_j->p2p);
-
-	/*
-	 * Send a SCIF_NODE_ADD to dev_i, pass it its bus address
-	 * as seen from dev_j
-	 */
-	msg.uop = SCIF_NODE_ADD;
-	msg.src.node = dev_j->node;
-	msg.dst.node = dev_i->node;
-
-	msg.payload[0] = p2p_ji->ppi_da[SCIF_PPI_APER];
-	msg.payload[1] = p2p_ij->ppi_da[SCIF_PPI_MMIO];
-	msg.payload[2] = p2p_ij->ppi_da[SCIF_PPI_APER];
-	msg.payload[3] = p2p_ij->ppi_len[SCIF_PPI_APER] << PAGE_SHIFT;
-
-	err = scif_nodeqp_send(dev_i,  &msg);
-	if (err) {
-		dev_err(&scifdev->sdev->dev,
-			"%s %d error %d\n", __func__, __LINE__, err);
-		return;
-	}
-
-	/* Same as above but to dev_j */
-	msg.uop = SCIF_NODE_ADD;
-	msg.src.node = dev_i->node;
-	msg.dst.node = dev_j->node;
-
-	tmppayload = msg.payload[0];
-	msg.payload[0] = msg.payload[2];
-	msg.payload[2] = tmppayload;
-	msg.payload[1] = p2p_ji->ppi_da[SCIF_PPI_MMIO];
-	msg.payload[3] = p2p_ji->ppi_len[SCIF_PPI_APER] << PAGE_SHIFT;
-
-	scif_nodeqp_send(dev_j, &msg);
-}
-
-static void scif_p2p_setup(void)
-{
-	int i, j;
-
-	if (!scif_info.p2p_enable)
-		return;
-
-	for (i = 1; i <= scif_info.maxid; i++)
-		if (!_scifdev_alive(&scif_dev[i]))
-			return;
-
-	for (i = 1; i <= scif_info.maxid; i++) {
-		for (j = 1; j <= scif_info.maxid; j++) {
-			struct scif_dev *scifdev = &scif_dev[i];
-
-			if (i == j)
-				continue;
-			scif_node_connect(scifdev, j);
-		}
-	}
-}
-
-static char *message_types[] = {"BAD",
-				"INIT",
-				"EXIT",
-				"SCIF_EXIT_ACK",
-				"SCIF_NODE_ADD",
-				"SCIF_NODE_ADD_ACK",
-				"SCIF_NODE_ADD_NACK",
-				"REMOVE_NODE",
-				"REMOVE_NODE_ACK",
-				"CNCT_REQ",
-				"CNCT_GNT",
-				"CNCT_GNTACK",
-				"CNCT_GNTNACK",
-				"CNCT_REJ",
-				"DISCNCT",
-				"DISCNT_ACK",
-				"CLIENT_SENT",
-				"CLIENT_RCVD",
-				"SCIF_GET_NODE_INFO",
-				"REGISTER",
-				"REGISTER_ACK",
-				"REGISTER_NACK",
-				"UNREGISTER",
-				"UNREGISTER_ACK",
-				"UNREGISTER_NACK",
-				"ALLOC_REQ",
-				"ALLOC_GNT",
-				"ALLOC_REJ",
-				"FREE_PHYS",
-				"FREE_VIRT",
-				"MUNMAP",
-				"MARK",
-				"MARK_ACK",
-				"MARK_NACK",
-				"WAIT",
-				"WAIT_ACK",
-				"WAIT_NACK",
-				"SIGNAL_LOCAL",
-				"SIGNAL_REMOTE",
-				"SIG_ACK",
-				"SIG_NACK"};
-
-static void
-scif_display_message(struct scif_dev *scifdev, struct scifmsg *msg,
-		     const char *label)
-{
-	if (!scif_info.en_msg_log)
-		return;
-	if (msg->uop > SCIF_MAX_MSG) {
-		dev_err(&scifdev->sdev->dev,
-			"%s: unknown msg type %d\n", label, msg->uop);
-		return;
-	}
-	dev_info(&scifdev->sdev->dev,
-		 "%s: msg type %s, src %d:%d, dest %d:%d payload 0x%llx:0x%llx:0x%llx:0x%llx\n",
-		 label, message_types[msg->uop], msg->src.node, msg->src.port,
-		 msg->dst.node, msg->dst.port, msg->payload[0], msg->payload[1],
-		 msg->payload[2], msg->payload[3]);
-}
-
-int _scif_nodeqp_send(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	struct scif_qp *qp = scifdev->qpairs;
-	int err = -ENOMEM, loop_cnt = 0;
-
-	scif_display_message(scifdev, msg, "Sent");
-	if (!qp) {
-		err = -EINVAL;
-		goto error;
-	}
-	spin_lock(&qp->send_lock);
-
-	while ((err = scif_rb_write(&qp->outbound_q,
-				    msg, sizeof(struct scifmsg)))) {
-		mdelay(1);
-#define SCIF_NODEQP_SEND_TO_MSEC (3 * 1000)
-		if (loop_cnt++ > (SCIF_NODEQP_SEND_TO_MSEC)) {
-			err = -ENODEV;
-			break;
-		}
-	}
-	if (!err)
-		scif_rb_commit(&qp->outbound_q);
-	spin_unlock(&qp->send_lock);
-	if (!err) {
-		if (scifdev_self(scifdev))
-			/*
-			 * For loopback we need to emulate an interrupt by
-			 * queuing work for the queue handling real node
-			 * Qp interrupts.
-			 */
-			queue_work(scifdev->intr_wq, &scifdev->intr_bh);
-		else
-			scif_send_msg_intr(scifdev);
-	}
-error:
-	if (err)
-		dev_dbg(&scifdev->sdev->dev,
-			"%s %d error %d uop %d\n",
-			 __func__, __LINE__, err, msg->uop);
-	return err;
-}
-
-/**
- * scif_nodeqp_send - Send a message on the node queue pair
- * @scifdev: Scif Device.
- * @msg: The message to be sent.
- */
-int scif_nodeqp_send(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	int err;
-	struct device *spdev = NULL;
-
-	if (msg->uop > SCIF_EXIT_ACK) {
-		/* Don't send messages once the exit flow has begun */
-		if (OP_IDLE != scifdev->exit)
-			return -ENODEV;
-		spdev = scif_get_peer_dev(scifdev);
-		if (IS_ERR(spdev)) {
-			err = PTR_ERR(spdev);
-			return err;
-		}
-	}
-	err = _scif_nodeqp_send(scifdev, msg);
-	if (msg->uop > SCIF_EXIT_ACK)
-		scif_put_peer_dev(spdev);
-	return err;
-}
-
-/*
- * scif_misc_handler:
- *
- * Work queue handler for servicing miscellaneous SCIF tasks.
- * Examples include:
- * 1) Remote fence requests.
- * 2) Destruction of temporary registered windows
- *    created during scif_vreadfrom()/scif_vwriteto().
- * 3) Cleanup of zombie endpoints.
- */
-void scif_misc_handler(struct work_struct *work)
-{
-	scif_rma_handle_remote_fences();
-	scif_rma_destroy_windows();
-	scif_rma_destroy_tcw_invalid();
-	scif_cleanup_zombie_epd();
-}
-
-/**
- * scif_init() - Respond to SCIF_INIT interrupt message
- * @scifdev:    Remote SCIF device node
- * @msg:        Interrupt message
- */
-static __always_inline void
-scif_init(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	/*
-	 * Allow the thread waiting for device page updates for the peer QP DMA
-	 * address to complete initializing the inbound_q.
-	 */
-	flush_delayed_work(&scifdev->qp_dwork);
-
-	scif_peer_register_device(scifdev);
-
-	if (scif_is_mgmt_node()) {
-		mutex_lock(&scif_info.conflock);
-		scif_p2p_setup();
-		mutex_unlock(&scif_info.conflock);
-	}
-}
-
-/**
- * scif_exit() - Respond to SCIF_EXIT interrupt message
- * @scifdev:    Remote SCIF device node
- * @unused:     Interrupt message (unused)
- *
- * This function stops the SCIF interface for the node which sent
- * the SCIF_EXIT message and starts waiting for that node to
- * resetup the queue pair again.
- */
-static __always_inline void
-scif_exit(struct scif_dev *scifdev, struct scifmsg *unused)
-{
-	scifdev->exit_ack_pending = true;
-	if (scif_is_mgmt_node())
-		scif_disconnect_node(scifdev->node, false);
-	else
-		scif_stop(scifdev);
-	schedule_delayed_work(&scifdev->qp_dwork,
-			      msecs_to_jiffies(1000));
-}
-
-/**
- * scif_exitack() - Respond to SCIF_EXIT_ACK interrupt message
- * @scifdev:    Remote SCIF device node
- * @unused:     Interrupt message (unused)
- *
- */
-static __always_inline void
-scif_exit_ack(struct scif_dev *scifdev, struct scifmsg *unused)
-{
-	scifdev->exit = OP_COMPLETED;
-	wake_up(&scif_info.exitwq);
-}
-
-/**
- * scif_node_add() - Respond to SCIF_NODE_ADD interrupt message
- * @scifdev:    Remote SCIF device node
- * @msg:        Interrupt message
- *
- * When the mgmt node driver has finished initializing a MIC node queue pair it
- * marks the node as online. It then looks for all currently online MIC cards
- * and send a SCIF_NODE_ADD message to identify the ID of the new card for
- * peer to peer initialization
- *
- * The local node allocates its incoming queue and sends its address in the
- * SCIF_NODE_ADD_ACK message back to the mgmt node, the mgmt node "reflects"
- * this message to the new node
- */
-static __always_inline void
-scif_node_add(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	struct scif_dev *newdev;
-	dma_addr_t qp_offset;
-	int qp_connect;
-	struct scif_hw_dev *sdev;
-
-	dev_dbg(&scifdev->sdev->dev,
-		"Scifdev %d:%d received NODE_ADD msg for node %d\n",
-		scifdev->node, msg->dst.node, msg->src.node);
-	dev_dbg(&scifdev->sdev->dev,
-		"Remote address for this node's aperture %llx\n",
-		msg->payload[0]);
-	newdev = &scif_dev[msg->src.node];
-	newdev->node = msg->src.node;
-	newdev->sdev = scif_dev[SCIF_MGMT_NODE].sdev;
-	sdev = newdev->sdev;
-
-	if (scif_setup_intr_wq(newdev)) {
-		dev_err(&scifdev->sdev->dev,
-			"failed to setup interrupts for %d\n", msg->src.node);
-		goto interrupt_setup_error;
-	}
-	newdev->mmio.va = ioremap(msg->payload[1], sdev->mmio->len);
-	if (!newdev->mmio.va) {
-		dev_err(&scifdev->sdev->dev,
-			"failed to map mmio for %d\n", msg->src.node);
-		goto mmio_map_error;
-	}
-	newdev->qpairs = kzalloc(sizeof(*newdev->qpairs), GFP_KERNEL);
-	if (!newdev->qpairs)
-		goto qp_alloc_error;
-	/*
-	 * Set the base address of the remote node's memory since it gets
-	 * added to qp_offset
-	 */
-	newdev->base_addr = msg->payload[0];
-
-	qp_connect = scif_setup_qp_connect(newdev->qpairs, &qp_offset,
-					   SCIF_NODE_QP_SIZE, newdev);
-	if (qp_connect) {
-		dev_err(&scifdev->sdev->dev,
-			"failed to setup qp_connect %d\n", qp_connect);
-		goto qp_connect_error;
-	}
-
-	newdev->db = sdev->hw_ops->next_db(sdev);
-	newdev->cookie = sdev->hw_ops->request_irq(sdev, scif_intr_handler,
-						   "SCIF_INTR", newdev,
-						   newdev->db);
-	if (IS_ERR(newdev->cookie))
-		goto qp_connect_error;
-	newdev->qpairs->magic = SCIFEP_MAGIC;
-	newdev->qpairs->qp_state = SCIF_QP_OFFLINE;
-
-	msg->uop = SCIF_NODE_ADD_ACK;
-	msg->dst.node = msg->src.node;
-	msg->src.node = scif_info.nodeid;
-	msg->payload[0] = qp_offset;
-	msg->payload[2] = newdev->db;
-	scif_nodeqp_send(&scif_dev[SCIF_MGMT_NODE], msg);
-	return;
-qp_connect_error:
-	kfree(newdev->qpairs);
-	newdev->qpairs = NULL;
-qp_alloc_error:
-	iounmap(newdev->mmio.va);
-	newdev->mmio.va = NULL;
-mmio_map_error:
-interrupt_setup_error:
-	dev_err(&scifdev->sdev->dev,
-		"node add failed for node %d\n", msg->src.node);
-	msg->uop = SCIF_NODE_ADD_NACK;
-	msg->dst.node = msg->src.node;
-	msg->src.node = scif_info.nodeid;
-	scif_nodeqp_send(&scif_dev[SCIF_MGMT_NODE], msg);
-}
-
-void scif_poll_qp_state(struct work_struct *work)
-{
-#define SCIF_NODE_QP_RETRY 100
-#define SCIF_NODE_QP_TIMEOUT 100
-	struct scif_dev *peerdev = container_of(work, struct scif_dev,
-							p2p_dwork.work);
-	struct scif_qp *qp = &peerdev->qpairs[0];
-
-	if (qp->qp_state != SCIF_QP_ONLINE ||
-	    qp->remote_qp->qp_state != SCIF_QP_ONLINE) {
-		if (peerdev->p2p_retry++ == SCIF_NODE_QP_RETRY) {
-			dev_err(&peerdev->sdev->dev,
-				"Warning: QP check timeout with state %d\n",
-				qp->qp_state);
-			goto timeout;
-		}
-		schedule_delayed_work(&peerdev->p2p_dwork,
-				      msecs_to_jiffies(SCIF_NODE_QP_TIMEOUT));
-		return;
-	}
-	return;
-timeout:
-	dev_err(&peerdev->sdev->dev,
-		"%s %d remote node %d offline,  state = 0x%x\n",
-		__func__, __LINE__, peerdev->node, qp->qp_state);
-	qp->remote_qp->qp_state = SCIF_QP_OFFLINE;
-	scif_peer_unregister_device(peerdev);
-	scif_cleanup_scifdev(peerdev);
-}
-
-/**
- * scif_node_add_ack() - Respond to SCIF_NODE_ADD_ACK interrupt message
- * @scifdev:    Remote SCIF device node
- * @msg:        Interrupt message
- *
- * After a MIC node receives the SCIF_NODE_ADD_ACK message it send this
- * message to the mgmt node to confirm the sequence is finished.
- *
- */
-static __always_inline void
-scif_node_add_ack(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	struct scif_dev *peerdev;
-	struct scif_qp *qp;
-	struct scif_dev *dst_dev = &scif_dev[msg->dst.node];
-
-	dev_dbg(&scifdev->sdev->dev,
-		"Scifdev %d received SCIF_NODE_ADD_ACK msg src %d dst %d\n",
-		scifdev->node, msg->src.node, msg->dst.node);
-	dev_dbg(&scifdev->sdev->dev,
-		"payload %llx %llx %llx %llx\n", msg->payload[0],
-		msg->payload[1], msg->payload[2], msg->payload[3]);
-	if (scif_is_mgmt_node()) {
-		/*
-		 * the lock serializes with scif_qp_response_ack. The mgmt node
-		 * is forwarding the NODE_ADD_ACK message from src to dst we
-		 * need to make sure that the dst has already received a
-		 * NODE_ADD for src and setup its end of the qp to dst
-		 */
-		mutex_lock(&scif_info.conflock);
-		msg->payload[1] = scif_info.maxid;
-		scif_nodeqp_send(dst_dev, msg);
-		mutex_unlock(&scif_info.conflock);
-		return;
-	}
-	peerdev = &scif_dev[msg->src.node];
-	peerdev->sdev = scif_dev[SCIF_MGMT_NODE].sdev;
-	peerdev->node = msg->src.node;
-
-	qp = &peerdev->qpairs[0];
-
-	if ((scif_setup_qp_connect_response(peerdev, &peerdev->qpairs[0],
-					    msg->payload[0])))
-		goto local_error;
-	peerdev->rdb = msg->payload[2];
-	qp->remote_qp->qp_state = SCIF_QP_ONLINE;
-
-	scif_peer_register_device(peerdev);
-
-	schedule_delayed_work(&peerdev->p2p_dwork, 0);
-	return;
-local_error:
-	scif_cleanup_scifdev(peerdev);
-}
-
-/**
- * scif_node_add_nack: Respond to SCIF_NODE_ADD_NACK interrupt message
- * @scifdev:    Remote SCIF device node
- * @msg:        Interrupt message
- *
- * SCIF_NODE_ADD failed, so inform the waiting wq.
- */
-static __always_inline void
-scif_node_add_nack(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	if (scif_is_mgmt_node()) {
-		struct scif_dev *dst_dev = &scif_dev[msg->dst.node];
-
-		dev_dbg(&scifdev->sdev->dev,
-			"SCIF_NODE_ADD_NACK received from %d\n", scifdev->node);
-		scif_nodeqp_send(dst_dev, msg);
-	}
-}
-
-/**
- * scif_node_remove: Handle SCIF_NODE_REMOVE message
- * @scifdev:    Remote SCIF device node
- * @msg: Interrupt message
- *
- * Handle node removal.
- */
-static __always_inline void
-scif_node_remove(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	int node = msg->payload[0];
-	struct scif_dev *scdev = &scif_dev[node];
-
-	scdev->node_remove_ack_pending = true;
-	scif_handle_remove_node(node);
-}
-
-/**
- * scif_node_remove_ack: Handle SCIF_NODE_REMOVE_ACK message
- * @scifdev:    Remote SCIF device node
- * @msg: Interrupt message
- *
- * The peer has acked a SCIF_NODE_REMOVE message.
- */
-static __always_inline void
-scif_node_remove_ack(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	struct scif_dev *sdev = &scif_dev[msg->payload[0]];
-
-	atomic_inc(&sdev->disconn_rescnt);
-	wake_up(&sdev->disconn_wq);
-}
-
-/**
- * scif_get_node_info: Respond to SCIF_GET_NODE_INFO interrupt message
- * @scifdev:    Remote SCIF device node
- * @msg:        Interrupt message
- *
- * Retrieve node info i.e maxid and total from the mgmt node.
- */
-static __always_inline void
-scif_get_node_info_resp(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	if (scif_is_mgmt_node()) {
-		swap(msg->dst.node, msg->src.node);
-		mutex_lock(&scif_info.conflock);
-		msg->payload[1] = scif_info.maxid;
-		msg->payload[2] = scif_info.total;
-		mutex_unlock(&scif_info.conflock);
-		scif_nodeqp_send(scifdev, msg);
-	} else {
-		struct completion *node_info =
-			(struct completion *)msg->payload[3];
-
-		mutex_lock(&scif_info.conflock);
-		scif_info.maxid = msg->payload[1];
-		scif_info.total = msg->payload[2];
-		complete_all(node_info);
-		mutex_unlock(&scif_info.conflock);
-	}
-}
-
-static void
-scif_msg_unknown(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	/* Bogus Node Qp Message? */
-	dev_err(&scifdev->sdev->dev,
-		"Unknown message 0x%xn scifdev->node 0x%x\n",
-		msg->uop, scifdev->node);
-}
-
-static void (*scif_intr_func[SCIF_MAX_MSG + 1])
-	    (struct scif_dev *, struct scifmsg *msg) = {
-	scif_msg_unknown,	/* Error */
-	scif_init,		/* SCIF_INIT */
-	scif_exit,		/* SCIF_EXIT */
-	scif_exit_ack,		/* SCIF_EXIT_ACK */
-	scif_node_add,		/* SCIF_NODE_ADD */
-	scif_node_add_ack,	/* SCIF_NODE_ADD_ACK */
-	scif_node_add_nack,	/* SCIF_NODE_ADD_NACK */
-	scif_node_remove,	/* SCIF_NODE_REMOVE */
-	scif_node_remove_ack,	/* SCIF_NODE_REMOVE_ACK */
-	scif_cnctreq,		/* SCIF_CNCT_REQ */
-	scif_cnctgnt,		/* SCIF_CNCT_GNT */
-	scif_cnctgnt_ack,	/* SCIF_CNCT_GNTACK */
-	scif_cnctgnt_nack,	/* SCIF_CNCT_GNTNACK */
-	scif_cnctrej,		/* SCIF_CNCT_REJ */
-	scif_discnct,		/* SCIF_DISCNCT */
-	scif_discnt_ack,	/* SCIF_DISCNT_ACK */
-	scif_clientsend,	/* SCIF_CLIENT_SENT */
-	scif_clientrcvd,	/* SCIF_CLIENT_RCVD */
-	scif_get_node_info_resp,/* SCIF_GET_NODE_INFO */
-	scif_recv_reg,		/* SCIF_REGISTER */
-	scif_recv_reg_ack,	/* SCIF_REGISTER_ACK */
-	scif_recv_reg_nack,	/* SCIF_REGISTER_NACK */
-	scif_recv_unreg,	/* SCIF_UNREGISTER */
-	scif_recv_unreg_ack,	/* SCIF_UNREGISTER_ACK */
-	scif_recv_unreg_nack,	/* SCIF_UNREGISTER_NACK */
-	scif_alloc_req,		/* SCIF_ALLOC_REQ */
-	scif_alloc_gnt_rej,	/* SCIF_ALLOC_GNT */
-	scif_alloc_gnt_rej,	/* SCIF_ALLOC_REJ */
-	scif_free_virt,		/* SCIF_FREE_VIRT */
-	scif_recv_munmap,	/* SCIF_MUNMAP */
-	scif_recv_mark,		/* SCIF_MARK */
-	scif_recv_mark_resp,	/* SCIF_MARK_ACK */
-	scif_recv_mark_resp,	/* SCIF_MARK_NACK */
-	scif_recv_wait,		/* SCIF_WAIT */
-	scif_recv_wait_resp,	/* SCIF_WAIT_ACK */
-	scif_recv_wait_resp,	/* SCIF_WAIT_NACK */
-	scif_recv_sig_local,	/* SCIF_SIG_LOCAL */
-	scif_recv_sig_remote,	/* SCIF_SIG_REMOTE */
-	scif_recv_sig_resp,	/* SCIF_SIG_ACK */
-	scif_recv_sig_resp,	/* SCIF_SIG_NACK */
-};
-
-static int scif_max_msg_id = SCIF_MAX_MSG;
-/**
- * scif_nodeqp_msg_handler() - Common handler for node messages
- * @scifdev: Remote device to respond to
- * @qp: Remote memory pointer
- * @msg: The message to be handled.
- *
- * This routine calls the appropriate routine to handle a Node Qp
- * message receipt
- */
-static void
-scif_nodeqp_msg_handler(struct scif_dev *scifdev,
-			struct scif_qp *qp, struct scifmsg *msg)
-{
-	scif_display_message(scifdev, msg, "Rcvd");
-
-	if (msg->uop > (u32)scif_max_msg_id) {
-		/* Bogus Node Qp Message? */
-		dev_err(&scifdev->sdev->dev,
-			"Unknown message 0x%xn scifdev->node 0x%x\n",
-			msg->uop, scifdev->node);
-		return;
-	}
-
-	scif_intr_func[msg->uop](scifdev, msg);
-}
-
-/**
- * scif_nodeqp_intrhandler() - Interrupt handler for node messages
- * @scifdev:    Remote device to respond to
- * @qp:         Remote memory pointer
- *
- * This routine is triggered by the interrupt mechanism.  It reads
- * messages from the node queue RB and calls the Node QP Message handling
- * routine.
- */
-void scif_nodeqp_intrhandler(struct scif_dev *scifdev, struct scif_qp *qp)
-{
-	struct scifmsg msg;
-	int read_size;
-
-	do {
-		read_size = scif_rb_get_next(&qp->inbound_q, &msg, sizeof(msg));
-		if (!read_size)
-			break;
-		scif_nodeqp_msg_handler(scifdev, qp, &msg);
-		/*
-		 * The node queue pair is unmapped so skip the read pointer
-		 * update after receipt of a SCIF_EXIT_ACK
-		 */
-		if (SCIF_EXIT_ACK == msg.uop)
-			break;
-		scif_rb_update_read_ptr(&qp->inbound_q);
-	} while (1);
-}
-
-/**
- * scif_loopb_wq_handler - Loopback Workqueue Handler.
- * @unused: loop back work (unused)
- *
- * This work queue routine is invoked by the loopback work queue handler.
- * It grabs the recv lock, dequeues any available messages from the head
- * of the loopback message list, calls the node QP message handler,
- * waits for it to return, then frees up this message and dequeues more
- * elements of the list if available.
- */
-static void scif_loopb_wq_handler(struct work_struct *unused)
-{
-	struct scif_dev *scifdev = scif_info.loopb_dev;
-	struct scif_qp *qp = scifdev->qpairs;
-	struct scif_loopb_msg *msg;
-
-	do {
-		msg = NULL;
-		spin_lock(&qp->recv_lock);
-		if (!list_empty(&scif_info.loopb_recv_q)) {
-			msg = list_first_entry(&scif_info.loopb_recv_q,
-					       struct scif_loopb_msg,
-					       list);
-			list_del(&msg->list);
-		}
-		spin_unlock(&qp->recv_lock);
-
-		if (msg) {
-			scif_nodeqp_msg_handler(scifdev, qp, &msg->msg);
-			kfree(msg);
-		}
-	} while (msg);
-}
-
-/**
- * scif_loopb_msg_handler() - Workqueue handler for loopback messages.
- * @scifdev: SCIF device
- * @qp: Queue pair.
- *
- * This work queue routine is triggered when a loopback message is received.
- *
- * We need special handling for receiving Node Qp messages on a loopback SCIF
- * device via two workqueues for receiving messages.
- *
- * The reason we need the extra workqueue which is not required with *normal*
- * non-loopback SCIF devices is the potential classic deadlock described below:
- *
- * Thread A tries to send a message on a loopback SCIF device and blocks since
- * there is no space in the RB while it has the send_lock held or another
- * lock called lock X for example.
- *
- * Thread B: The Loopback Node QP message receive workqueue receives the message
- * and tries to send a message (eg an ACK) to the loopback SCIF device. It tries
- * to grab the send lock again or lock X and deadlocks with Thread A. The RB
- * cannot be drained any further due to this classic deadlock.
- *
- * In order to avoid deadlocks as mentioned above we have an extra level of
- * indirection achieved by having two workqueues.
- * 1) The first workqueue whose handler is scif_loopb_msg_handler reads
- * messages from the Node QP RB, adds them to a list and queues work for the
- * second workqueue.
- *
- * 2) The second workqueue whose handler is scif_loopb_wq_handler dequeues
- * messages from the list, handles them, frees up the memory and dequeues
- * more elements from the list if possible.
- */
-int
-scif_loopb_msg_handler(struct scif_dev *scifdev, struct scif_qp *qp)
-{
-	int read_size;
-	struct scif_loopb_msg *msg;
-
-	do {
-		msg = kmalloc(sizeof(*msg), GFP_KERNEL);
-		if (!msg)
-			return -ENOMEM;
-		read_size = scif_rb_get_next(&qp->inbound_q, &msg->msg,
-					     sizeof(struct scifmsg));
-		if (read_size != sizeof(struct scifmsg)) {
-			kfree(msg);
-			scif_rb_update_read_ptr(&qp->inbound_q);
-			break;
-		}
-		spin_lock(&qp->recv_lock);
-		list_add_tail(&msg->list, &scif_info.loopb_recv_q);
-		spin_unlock(&qp->recv_lock);
-		queue_work(scif_info.loopb_wq, &scif_info.loopb_work);
-		scif_rb_update_read_ptr(&qp->inbound_q);
-	} while (read_size == sizeof(struct scifmsg));
-	return read_size;
-}
-
-/**
- * scif_setup_loopback_qp - One time setup work for Loopback Node Qp.
- * @scifdev: SCIF device
- *
- * Sets up the required loopback workqueues, queue pairs and ring buffers
- */
-int scif_setup_loopback_qp(struct scif_dev *scifdev)
-{
-	int err = 0;
-	void *local_q;
-	struct scif_qp *qp;
-
-	err = scif_setup_intr_wq(scifdev);
-	if (err)
-		goto exit;
-	INIT_LIST_HEAD(&scif_info.loopb_recv_q);
-	snprintf(scif_info.loopb_wqname, sizeof(scif_info.loopb_wqname),
-		 "SCIF LOOPB %d", scifdev->node);
-	scif_info.loopb_wq =
-		alloc_ordered_workqueue(scif_info.loopb_wqname, 0);
-	if (!scif_info.loopb_wq) {
-		err = -ENOMEM;
-		goto destroy_intr;
-	}
-	INIT_WORK(&scif_info.loopb_work, scif_loopb_wq_handler);
-	/* Allocate Self Qpair */
-	scifdev->qpairs = kzalloc(sizeof(*scifdev->qpairs), GFP_KERNEL);
-	if (!scifdev->qpairs) {
-		err = -ENOMEM;
-		goto destroy_loopb_wq;
-	}
-
-	qp = scifdev->qpairs;
-	qp->magic = SCIFEP_MAGIC;
-	spin_lock_init(&qp->send_lock);
-	spin_lock_init(&qp->recv_lock);
-
-	local_q = kzalloc(SCIF_NODE_QP_SIZE, GFP_KERNEL);
-	if (!local_q) {
-		err = -ENOMEM;
-		goto free_qpairs;
-	}
-	/*
-	 * For loopback the inbound_q and outbound_q are essentially the same
-	 * since the Node sends a message on the loopback interface to the
-	 * outbound_q which is then received on the inbound_q.
-	 */
-	scif_rb_init(&qp->outbound_q,
-		     &qp->local_read,
-		     &qp->local_write,
-		     local_q, get_count_order(SCIF_NODE_QP_SIZE));
-
-	scif_rb_init(&qp->inbound_q,
-		     &qp->local_read,
-		     &qp->local_write,
-		     local_q, get_count_order(SCIF_NODE_QP_SIZE));
-	scif_info.nodeid = scifdev->node;
-
-	scif_peer_register_device(scifdev);
-
-	scif_info.loopb_dev = scifdev;
-	return err;
-free_qpairs:
-	kfree(scifdev->qpairs);
-destroy_loopb_wq:
-	destroy_workqueue(scif_info.loopb_wq);
-destroy_intr:
-	scif_destroy_intr_wq(scifdev);
-exit:
-	return err;
-}
-
-/**
- * scif_destroy_loopback_qp - One time uninit work for Loopback Node Qp
- * @scifdev: SCIF device
- *
- * Destroys the workqueues and frees up the Ring Buffer and Queue Pair memory.
- */
-int scif_destroy_loopback_qp(struct scif_dev *scifdev)
-{
-	scif_peer_unregister_device(scifdev);
-	destroy_workqueue(scif_info.loopb_wq);
-	scif_destroy_intr_wq(scifdev);
-	kfree(scifdev->qpairs->outbound_q.rb_base);
-	kfree(scifdev->qpairs);
-	scifdev->sdev = NULL;
-	scif_info.loopb_dev = NULL;
-	return 0;
-}
-
-void scif_destroy_p2p(struct scif_dev *scifdev)
-{
-	struct scif_dev *peer_dev;
-	struct scif_p2p_info *p2p;
-	struct list_head *pos, *tmp;
-	int bd;
-
-	mutex_lock(&scif_info.conflock);
-	/* Free P2P mappings in the given node for all its peer nodes */
-	list_for_each_safe(pos, tmp, &scifdev->p2p) {
-		p2p = list_entry(pos, struct scif_p2p_info, ppi_list);
-		dma_unmap_sg(&scifdev->sdev->dev, p2p->ppi_sg[SCIF_PPI_MMIO],
-			     p2p->sg_nentries[SCIF_PPI_MMIO],
-			     DMA_BIDIRECTIONAL);
-		dma_unmap_sg(&scifdev->sdev->dev, p2p->ppi_sg[SCIF_PPI_APER],
-			     p2p->sg_nentries[SCIF_PPI_APER],
-			     DMA_BIDIRECTIONAL);
-		scif_p2p_freesg(p2p->ppi_sg[SCIF_PPI_MMIO]);
-		scif_p2p_freesg(p2p->ppi_sg[SCIF_PPI_APER]);
-		list_del(pos);
-		kfree(p2p);
-	}
-
-	/* Free P2P mapping created in the peer nodes for the given node */
-	for (bd = SCIF_MGMT_NODE + 1; bd <= scif_info.maxid; bd++) {
-		peer_dev = &scif_dev[bd];
-		list_for_each_safe(pos, tmp, &peer_dev->p2p) {
-			p2p = list_entry(pos, struct scif_p2p_info, ppi_list);
-			if (p2p->ppi_peer_id == scifdev->node) {
-				dma_unmap_sg(&peer_dev->sdev->dev,
-					     p2p->ppi_sg[SCIF_PPI_MMIO],
-					     p2p->sg_nentries[SCIF_PPI_MMIO],
-					     DMA_BIDIRECTIONAL);
-				dma_unmap_sg(&peer_dev->sdev->dev,
-					     p2p->ppi_sg[SCIF_PPI_APER],
-					     p2p->sg_nentries[SCIF_PPI_APER],
-					     DMA_BIDIRECTIONAL);
-				scif_p2p_freesg(p2p->ppi_sg[SCIF_PPI_MMIO]);
-				scif_p2p_freesg(p2p->ppi_sg[SCIF_PPI_APER]);
-				list_del(pos);
-				kfree(p2p);
-			}
-		}
-	}
-	mutex_unlock(&scif_info.conflock);
-}
diff --git a/drivers/misc/mic/scif/scif_nodeqp.h b/drivers/misc/mic/scif/scif_nodeqp.h
deleted file mode 100644
index 95896273138e..000000000000
--- a/drivers/misc/mic/scif/scif_nodeqp.h
+++ /dev/null
@@ -1,221 +0,0 @@
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * This file is provided under a dual BSD/GPLv2 license.  When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * BSD LICENSE
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- *   notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- *   notice, this list of conditions and the following disclaimer in
- *   the documentation and/or other materials provided with the
- *   distribution.
- * * Neither the name of Intel Corporation nor the names of its
- *   contributors may be used to endorse or promote products derived
- *   from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * Intel SCIF driver.
- *
- */
-#ifndef SCIF_NODEQP
-#define SCIF_NODEQP
-
-#include "scif_rb.h"
-#include "scif_peer_bus.h"
-
-#define SCIF_INIT 1  /* First message sent to the peer node for discovery */
-#define SCIF_EXIT 2  /* Last message from the peer informing intent to exit */
-#define SCIF_EXIT_ACK 3 /* Response to SCIF_EXIT message */
-#define SCIF_NODE_ADD 4  /* Tell Online nodes a new node exits */
-#define SCIF_NODE_ADD_ACK 5  /* Confirm to mgmt node sequence is finished */
-#define SCIF_NODE_ADD_NACK 6 /* SCIF_NODE_ADD failed */
-#define SCIF_NODE_REMOVE 7 /* Request to deactivate a SCIF node */
-#define SCIF_NODE_REMOVE_ACK 8 /* Response to a SCIF_NODE_REMOVE message */
-#define SCIF_CNCT_REQ 9  /* Phys addr of Request connection to a port */
-#define SCIF_CNCT_GNT 10  /* Phys addr of new Grant connection request */
-#define SCIF_CNCT_GNTACK 11  /* Error type Reject a connection request */
-#define SCIF_CNCT_GNTNACK 12  /* Error type Reject a connection request */
-#define SCIF_CNCT_REJ 13  /* Error type Reject a connection request */
-#define SCIF_DISCNCT 14 /* Notify peer that connection is being terminated */
-#define SCIF_DISCNT_ACK 15 /* Notify peer that connection is being terminated */
-#define SCIF_CLIENT_SENT 16 /* Notify the peer that data has been written */
-#define SCIF_CLIENT_RCVD 17 /* Notify the peer that data has been read */
-#define SCIF_GET_NODE_INFO 18 /* Get current node mask from the mgmt node*/
-#define SCIF_REGISTER 19 /* Tell peer about a new registered window */
-#define SCIF_REGISTER_ACK 20 /* Notify peer about unregistration success */
-#define SCIF_REGISTER_NACK 21 /* Notify peer about registration success */
-#define SCIF_UNREGISTER 22 /* Tell peer about unregistering a window */
-#define SCIF_UNREGISTER_ACK 23 /* Notify peer about registration failure */
-#define SCIF_UNREGISTER_NACK 24 /* Notify peer about unregistration failure */
-#define SCIF_ALLOC_REQ 25 /* Request a mapped buffer */
-#define SCIF_ALLOC_GNT 26 /* Notify peer about allocation success */
-#define SCIF_ALLOC_REJ 27 /* Notify peer about allocation failure */
-#define SCIF_FREE_VIRT 28 /* Free previously allocated virtual memory */
-#define SCIF_MUNMAP 29 /* Acknowledgment for a SCIF_MMAP request */
-#define SCIF_MARK 30 /* SCIF Remote Fence Mark Request */
-#define SCIF_MARK_ACK 31 /* SCIF Remote Fence Mark Success */
-#define SCIF_MARK_NACK 32 /* SCIF Remote Fence Mark Failure */
-#define SCIF_WAIT 33 /* SCIF Remote Fence Wait Request */
-#define SCIF_WAIT_ACK 34 /* SCIF Remote Fence Wait Success */
-#define SCIF_WAIT_NACK 35 /* SCIF Remote Fence Wait Failure */
-#define SCIF_SIG_LOCAL 36 /* SCIF Remote Fence Local Signal Request */
-#define SCIF_SIG_REMOTE 37 /* SCIF Remote Fence Remote Signal Request */
-#define SCIF_SIG_ACK 38 /* SCIF Remote Fence Remote Signal Success */
-#define SCIF_SIG_NACK 39 /* SCIF Remote Fence Remote Signal Failure */
-#define SCIF_MAX_MSG SCIF_SIG_NACK
-
-/*
- * struct scifmsg - Node QP message format
- *
- * @src: Source information
- * @dst: Destination information
- * @uop: The message opcode
- * @payload: Unique payload format for each message
- */
-struct scifmsg {
-	struct scif_port_id src;
-	struct scif_port_id dst;
-	u32 uop;
-	u64 payload[4];
-} __packed;
-
-/*
- * struct scif_allocmsg - Used with SCIF_ALLOC_REQ to request
- * the remote note to allocate memory
- *
- * phys_addr: Physical address of the buffer
- * vaddr: Virtual address of the buffer
- * size: Size of the buffer
- * state: Current state
- * allocwq: wait queue for status
- */
-struct scif_allocmsg {
-	dma_addr_t phys_addr;
-	unsigned long vaddr;
-	size_t size;
-	enum scif_msg_state state;
-	wait_queue_head_t allocwq;
-};
-
-/*
- * struct scif_qp - Node Queue Pair
- *
- * Interesting structure -- a little difficult because we can only
- * write across the PCIe, so any r/w pointer we need to read is
- * local. We only need to read the read pointer on the inbound_q
- * and read the write pointer in the outbound_q
- *
- * @magic: Magic value to ensure the peer sees the QP correctly
- * @outbound_q: The outbound ring buffer for sending messages
- * @inbound_q: The inbound ring buffer for receiving messages
- * @local_write: Local write index
- * @local_read: Local read index
- * @remote_qp: The remote queue pair
- * @local_buf: DMA address of local ring buffer
- * @local_qp: DMA address of the local queue pair data structure
- * @remote_buf: DMA address of remote ring buffer
- * @qp_state: QP state i.e. online or offline used for P2P
- * @send_lock: synchronize access to outbound queue
- * @recv_lock: Synchronize access to inbound queue
- */
-struct scif_qp {
-	u64 magic;
-#define SCIFEP_MAGIC 0x5c1f000000005c1fULL
-	struct scif_rb outbound_q;
-	struct scif_rb inbound_q;
-
-	u32 local_write __aligned(64);
-	u32 local_read __aligned(64);
-	struct scif_qp *remote_qp;
-	dma_addr_t local_buf;
-	dma_addr_t local_qp;
-	dma_addr_t remote_buf;
-	u32 qp_state;
-#define SCIF_QP_OFFLINE 0xdead
-#define SCIF_QP_ONLINE 0xc0de
-	spinlock_t send_lock;
-	spinlock_t recv_lock;
-};
-
-/*
- * struct scif_loopb_msg - An element in the loopback Node QP message list.
- *
- * @msg - The SCIF node QP message
- * @list - link in the list of messages
- */
-struct scif_loopb_msg {
-	struct scifmsg msg;
-	struct list_head list;
-};
-
-int scif_nodeqp_send(struct scif_dev *scifdev, struct scifmsg *msg);
-int _scif_nodeqp_send(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_nodeqp_intrhandler(struct scif_dev *scifdev, struct scif_qp *qp);
-int scif_loopb_msg_handler(struct scif_dev *scifdev, struct scif_qp *qp);
-int scif_setup_qp(struct scif_dev *scifdev);
-int scif_qp_response(phys_addr_t phys, struct scif_dev *dev);
-int scif_setup_qp_connect(struct scif_qp *qp, dma_addr_t *qp_offset,
-			  int local_size, struct scif_dev *scifdev);
-int scif_setup_qp_accept(struct scif_qp *qp, dma_addr_t *qp_offset,
-			 dma_addr_t phys, int local_size,
-			 struct scif_dev *scifdev);
-int scif_setup_qp_connect_response(struct scif_dev *scifdev,
-				   struct scif_qp *qp, u64 payload);
-int scif_setup_loopback_qp(struct scif_dev *scifdev);
-int scif_destroy_loopback_qp(struct scif_dev *scifdev);
-void scif_poll_qp_state(struct work_struct *work);
-void scif_destroy_p2p(struct scif_dev *scifdev);
-void scif_send_exit(struct scif_dev *scifdev);
-static inline struct device *scif_get_peer_dev(struct scif_dev *scifdev)
-{
-	struct scif_peer_dev *spdev;
-	struct device *spdev_ret;
-
-	rcu_read_lock();
-	spdev = rcu_dereference(scifdev->spdev);
-	if (spdev)
-		spdev_ret = get_device(&spdev->dev);
-	else
-		spdev_ret = ERR_PTR(-ENODEV);
-	rcu_read_unlock();
-	return spdev_ret;
-}
-
-static inline void scif_put_peer_dev(struct device *dev)
-{
-	put_device(dev);
-}
-#endif  /* SCIF_NODEQP */
diff --git a/drivers/misc/mic/scif/scif_peer_bus.c b/drivers/misc/mic/scif/scif_peer_bus.c
deleted file mode 100644
index 6d608308bb60..000000000000
--- a/drivers/misc/mic/scif/scif_peer_bus.c
+++ /dev/null
@@ -1,175 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include "scif_main.h"
-#include "../bus/scif_bus.h"
-#include "scif_peer_bus.h"
-
-static inline struct scif_peer_dev *
-dev_to_scif_peer(struct device *dev)
-{
-	return container_of(dev, struct scif_peer_dev, dev);
-}
-
-struct bus_type scif_peer_bus = {
-	.name  = "scif_peer_bus",
-};
-
-static void scif_peer_release_dev(struct device *d)
-{
-	struct scif_peer_dev *sdev = dev_to_scif_peer(d);
-	struct scif_dev *scifdev = &scif_dev[sdev->dnode];
-
-	scif_cleanup_scifdev(scifdev);
-	kfree(sdev);
-}
-
-static int scif_peer_initialize_device(struct scif_dev *scifdev)
-{
-	struct scif_peer_dev *spdev;
-	int ret;
-
-	spdev = kzalloc(sizeof(*spdev), GFP_KERNEL);
-	if (!spdev) {
-		ret = -ENOMEM;
-		goto err;
-	}
-
-	spdev->dev.parent = scifdev->sdev->dev.parent;
-	spdev->dev.release = scif_peer_release_dev;
-	spdev->dnode = scifdev->node;
-	spdev->dev.bus = &scif_peer_bus;
-	dev_set_name(&spdev->dev, "scif_peer-dev%u", spdev->dnode);
-
-	device_initialize(&spdev->dev);
-	get_device(&spdev->dev);
-	rcu_assign_pointer(scifdev->spdev, spdev);
-
-	mutex_lock(&scif_info.conflock);
-	scif_info.total++;
-	scif_info.maxid = max_t(u32, spdev->dnode, scif_info.maxid);
-	mutex_unlock(&scif_info.conflock);
-	return 0;
-err:
-	dev_err(&scifdev->sdev->dev,
-		"dnode %d: initialize_device rc %d\n", scifdev->node, ret);
-	return ret;
-}
-
-static int scif_peer_add_device(struct scif_dev *scifdev)
-{
-	struct scif_peer_dev *spdev = rcu_dereference(scifdev->spdev);
-	char pool_name[16];
-	int ret;
-
-	ret = device_add(&spdev->dev);
-	put_device(&spdev->dev);
-	if (ret) {
-		dev_err(&scifdev->sdev->dev,
-			"dnode %d: peer device_add failed\n", scifdev->node);
-		goto put_spdev;
-	}
-
-	scnprintf(pool_name, sizeof(pool_name), "scif-%d", spdev->dnode);
-	scifdev->signal_pool = dmam_pool_create(pool_name, &scifdev->sdev->dev,
-						sizeof(struct scif_status), 1,
-						0);
-	if (!scifdev->signal_pool) {
-		dev_err(&scifdev->sdev->dev,
-			"dnode %d: dmam_pool_create failed\n", scifdev->node);
-		ret = -ENOMEM;
-		goto del_spdev;
-	}
-	dev_dbg(&spdev->dev, "Added peer dnode %d\n", spdev->dnode);
-	return 0;
-del_spdev:
-	device_del(&spdev->dev);
-put_spdev:
-	RCU_INIT_POINTER(scifdev->spdev, NULL);
-	synchronize_rcu();
-	put_device(&spdev->dev);
-
-	mutex_lock(&scif_info.conflock);
-	scif_info.total--;
-	mutex_unlock(&scif_info.conflock);
-	return ret;
-}
-
-void scif_add_peer_device(struct work_struct *work)
-{
-	struct scif_dev *scifdev = container_of(work, struct scif_dev,
-						peer_add_work);
-
-	scif_peer_add_device(scifdev);
-}
-
-/*
- * Peer device registration is split into a device_initialize and a device_add.
- * The reason for doing this is as follows: First, peer device registration
- * itself cannot be done in the message processing thread and must be delegated
- * to another workqueue, otherwise if SCIF client probe, called during peer
- * device registration, calls scif_connect(..), it will block the message
- * processing thread causing a deadlock. Next, device_initialize is done in the
- * "top-half" message processing thread and device_add in the "bottom-half"
- * workqueue. If this is not done, SCIF_CNCT_REQ message processing executing
- * concurrently with SCIF_INIT message processing is unable to get a reference
- * on the peer device, thereby failing the connect request.
- */
-void scif_peer_register_device(struct scif_dev *scifdev)
-{
-	int ret;
-
-	mutex_lock(&scifdev->lock);
-	ret = scif_peer_initialize_device(scifdev);
-	if (ret)
-		goto exit;
-	schedule_work(&scifdev->peer_add_work);
-exit:
-	mutex_unlock(&scifdev->lock);
-}
-
-int scif_peer_unregister_device(struct scif_dev *scifdev)
-{
-	struct scif_peer_dev *spdev;
-
-	mutex_lock(&scifdev->lock);
-	/* Flush work to ensure device register is complete */
-	flush_work(&scifdev->peer_add_work);
-
-	/*
-	 * Continue holding scifdev->lock since theoretically unregister_device
-	 * can be called simultaneously from multiple threads
-	 */
-	spdev = rcu_dereference(scifdev->spdev);
-	if (!spdev) {
-		mutex_unlock(&scifdev->lock);
-		return -ENODEV;
-	}
-
-	RCU_INIT_POINTER(scifdev->spdev, NULL);
-	synchronize_rcu();
-	mutex_unlock(&scifdev->lock);
-
-	dev_dbg(&spdev->dev, "Removing peer dnode %d\n", spdev->dnode);
-	device_unregister(&spdev->dev);
-
-	mutex_lock(&scif_info.conflock);
-	scif_info.total--;
-	mutex_unlock(&scif_info.conflock);
-	return 0;
-}
-
-int scif_peer_bus_init(void)
-{
-	return bus_register(&scif_peer_bus);
-}
-
-void scif_peer_bus_exit(void)
-{
-	bus_unregister(&scif_peer_bus);
-}
diff --git a/drivers/misc/mic/scif/scif_peer_bus.h b/drivers/misc/mic/scif/scif_peer_bus.h
deleted file mode 100644
index 2ea4c51c18c1..000000000000
--- a/drivers/misc/mic/scif/scif_peer_bus.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#ifndef _SCIF_PEER_BUS_H_
-#define _SCIF_PEER_BUS_H_
-
-#include <linux/device.h>
-#include <linux/mic_common.h>
-#include <linux/scif.h>
-
-struct scif_dev;
-
-void scif_add_peer_device(struct work_struct *work);
-void scif_peer_register_device(struct scif_dev *sdev);
-int scif_peer_unregister_device(struct scif_dev *scifdev);
-int scif_peer_bus_init(void);
-void scif_peer_bus_exit(void);
-#endif /* _SCIF_PEER_BUS_H */
diff --git a/drivers/misc/mic/scif/scif_ports.c b/drivers/misc/mic/scif/scif_ports.c
deleted file mode 100644
index 4bdb5ef9a139..000000000000
--- a/drivers/misc/mic/scif/scif_ports.c
+++ /dev/null
@@ -1,116 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include <linux/idr.h>
-
-#include "scif_main.h"
-
-#define SCIF_PORT_COUNT	0x10000	/* Ports available */
-
-struct idr scif_ports;
-
-/**
- * struct scif_port - SCIF port information
- *
- * @ref_cnt:  Reference count since there can be multiple endpoints
- *	      created via scif_accept(..) simultaneously using a port.
- */
-struct scif_port {
-	int ref_cnt;
-};
-
-/**
- * __scif_get_port - Reserve a specified port # for SCIF and add it
- * to the global list.
- * @start: lowest port # to be reserved (inclusive).
- * @end:   highest port # to be reserved (exclusive).
- *
- * @return : Allocated SCIF port #, or -ENOSPC if port unavailable.
- *		On memory allocation failure, returns -ENOMEM.
- */
-static int __scif_get_port(int start, int end)
-{
-	int id;
-	struct scif_port *port = kzalloc(sizeof(*port), GFP_ATOMIC);
-
-	if (!port)
-		return -ENOMEM;
-	spin_lock(&scif_info.port_lock);
-	id = idr_alloc(&scif_ports, port, start, end, GFP_ATOMIC);
-	if (id >= 0)
-		port->ref_cnt++;
-	spin_unlock(&scif_info.port_lock);
-	return id;
-}
-
-/**
- * scif_rsrv_port - Reserve a specified port # for SCIF.
- * @port : port # to be reserved.
- *
- * @return : Allocated SCIF port #, or -ENOSPC if port unavailable.
- *		On memory allocation failure, returns -ENOMEM.
- */
-int scif_rsrv_port(u16 port)
-{
-	return __scif_get_port(port, port + 1);
-}
-
-/**
- * scif_get_new_port - Get and reserve any port # for SCIF in the range
- *			SCIF_PORT_RSVD + 1 to SCIF_PORT_COUNT - 1.
- *
- * @return : Allocated SCIF port #, or -ENOSPC if no ports available.
- *		On memory allocation failure, returns -ENOMEM.
- */
-int scif_get_new_port(void)
-{
-	return __scif_get_port(SCIF_PORT_RSVD + 1, SCIF_PORT_COUNT);
-}
-
-/**
- * scif_get_port - Increment the reference count for a SCIF port
- * @id : SCIF port
- *
- * @return : None
- */
-void scif_get_port(u16 id)
-{
-	struct scif_port *port;
-
-	if (!id)
-		return;
-	spin_lock(&scif_info.port_lock);
-	port = idr_find(&scif_ports, id);
-	if (port)
-		port->ref_cnt++;
-	spin_unlock(&scif_info.port_lock);
-}
-
-/**
- * scif_put_port - Release a reserved SCIF port
- * @id : SCIF port to be released.
- *
- * @return : None
- */
-void scif_put_port(u16 id)
-{
-	struct scif_port *port;
-
-	if (!id)
-		return;
-	spin_lock(&scif_info.port_lock);
-	port = idr_find(&scif_ports, id);
-	if (port) {
-		port->ref_cnt--;
-		if (!port->ref_cnt) {
-			idr_remove(&scif_ports, id);
-			kfree(port);
-		}
-	}
-	spin_unlock(&scif_info.port_lock);
-}
diff --git a/drivers/misc/mic/scif/scif_rb.c b/drivers/misc/mic/scif/scif_rb.c
deleted file mode 100644
index e425882ae06d..000000000000
--- a/drivers/misc/mic/scif/scif_rb.c
+++ /dev/null
@@ -1,240 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include <linux/circ_buf.h>
-#include <linux/types.h>
-#include <linux/io.h>
-#include <linux/errno.h>
-
-#include "scif_rb.h"
-
-#define scif_rb_ring_cnt(head, tail, size) CIRC_CNT(head, tail, size)
-#define scif_rb_ring_space(head, tail, size) CIRC_SPACE(head, tail, size)
-
-/**
- * scif_rb_init - Initializes the ring buffer
- * @rb: ring buffer
- * @read_ptr: A pointer to the read offset
- * @write_ptr: A pointer to the write offset
- * @rb_base: A pointer to the base of the ring buffer
- * @size: The size of the ring buffer in powers of two
- */
-void scif_rb_init(struct scif_rb *rb, u32 *read_ptr, u32 *write_ptr,
-		  void *rb_base, u8 size)
-{
-	rb->rb_base = rb_base;
-	rb->size = (1 << size);
-	rb->read_ptr = read_ptr;
-	rb->write_ptr = write_ptr;
-	rb->current_read_offset = *read_ptr;
-	rb->current_write_offset = *write_ptr;
-}
-
-/* Copies a message to the ring buffer -- handles the wrap around case */
-static void memcpy_torb(struct scif_rb *rb, void *header,
-			void *msg, u32 size)
-{
-	u32 size1, size2;
-
-	if (header + size >= rb->rb_base + rb->size) {
-		/* Need to call two copies if it wraps around */
-		size1 = (u32)(rb->rb_base + rb->size - header);
-		size2 = size - size1;
-		memcpy_toio((void __iomem __force *)header, msg, size1);
-		memcpy_toio((void __iomem __force *)rb->rb_base,
-			    msg + size1, size2);
-	} else {
-		memcpy_toio((void __iomem __force *)header, msg, size);
-	}
-}
-
-/* Copies a message from the ring buffer -- handles the wrap around case */
-static void memcpy_fromrb(struct scif_rb *rb, void *header,
-			  void *msg, u32 size)
-{
-	u32 size1, size2;
-
-	if (header + size >= rb->rb_base + rb->size) {
-		/* Need to call two copies if it wraps around */
-		size1 = (u32)(rb->rb_base + rb->size - header);
-		size2 = size - size1;
-		memcpy_fromio(msg, (void __iomem __force *)header, size1);
-		memcpy_fromio(msg + size1,
-			      (void __iomem __force *)rb->rb_base, size2);
-	} else {
-		memcpy_fromio(msg, (void __iomem __force *)header, size);
-	}
-}
-
-/**
- * scif_rb_space - Query space available for writing to the RB
- * @rb: ring buffer
- *
- * Return: size available for writing to RB in bytes.
- */
-u32 scif_rb_space(struct scif_rb *rb)
-{
-	rb->current_read_offset = *rb->read_ptr;
-	/*
-	 * Update from the HW read pointer only once the peer has exposed the
-	 * new empty slot. This barrier is paired with the memory barrier
-	 * scif_rb_update_read_ptr()
-	 */
-	mb();
-	return scif_rb_ring_space(rb->current_write_offset,
-				  rb->current_read_offset, rb->size);
-}
-
-/**
- * scif_rb_write - Write a message to the RB
- * @rb: ring buffer
- * @msg: buffer to send the message.  Must be at least size bytes long
- * @size: the size (in bytes) to be copied to the RB
- *
- * This API does not block if there isn't enough space in the RB.
- * Returns: 0 on success or -ENOMEM on failure
- */
-int scif_rb_write(struct scif_rb *rb, void *msg, u32 size)
-{
-	void *header;
-
-	if (scif_rb_space(rb) < size)
-		return -ENOMEM;
-	header = rb->rb_base + rb->current_write_offset;
-	memcpy_torb(rb, header, msg, size);
-	/*
-	 * Wait until scif_rb_commit(). Update the local ring
-	 * buffer data, not the shared data until commit.
-	 */
-	rb->current_write_offset =
-		(rb->current_write_offset + size) & (rb->size - 1);
-	return 0;
-}
-
-/**
- * scif_rb_commit - To submit the message to let the peer fetch it
- * @rb: ring buffer
- */
-void scif_rb_commit(struct scif_rb *rb)
-{
-	/*
-	 * We must ensure ordering between the all the data committed
-	 * previously before we expose the new message to the peer by
-	 * updating the write_ptr. This write barrier is paired with
-	 * the read barrier in scif_rb_count(..)
-	 */
-	wmb();
-	WRITE_ONCE(*rb->write_ptr, rb->current_write_offset);
-#ifdef CONFIG_INTEL_MIC_CARD
-	/*
-	 * X100 Si bug: For the case where a Core is performing an EXT_WR
-	 * followed by a Doorbell Write, the Core must perform two EXT_WR to the
-	 * same address with the same data before it does the Doorbell Write.
-	 * This way, if ordering is violated for the Interrupt Message, it will
-	 * fall just behind the first Posted associated with the first EXT_WR.
-	 */
-	WRITE_ONCE(*rb->write_ptr, rb->current_write_offset);
-#endif
-}
-
-/**
- * scif_rb_get - To get next message from the ring buffer
- * @rb: ring buffer
- * @size: Number of bytes to be read
- *
- * Return: NULL if no bytes to be read from the ring buffer, otherwise the
- *	pointer to the next byte
- */
-static void *scif_rb_get(struct scif_rb *rb, u32 size)
-{
-	void *header = NULL;
-
-	if (scif_rb_count(rb, size) >= size)
-		header = rb->rb_base + rb->current_read_offset;
-	return header;
-}
-
-/*
- * scif_rb_get_next - Read from ring buffer.
- * @rb: ring buffer
- * @msg: buffer to hold the message.  Must be at least size bytes long
- * @size: Number of bytes to be read
- *
- * Return: number of bytes read if available bytes are >= size, otherwise
- * returns zero.
- */
-u32 scif_rb_get_next(struct scif_rb *rb, void *msg, u32 size)
-{
-	void *header = NULL;
-	int read_size = 0;
-
-	header = scif_rb_get(rb, size);
-	if (header) {
-		u32 next_cmd_offset =
-			(rb->current_read_offset + size) & (rb->size - 1);
-
-		read_size = size;
-		rb->current_read_offset = next_cmd_offset;
-		memcpy_fromrb(rb, header, msg, size);
-	}
-	return read_size;
-}
-
-/**
- * scif_rb_update_read_ptr
- * @rb: ring buffer
- */
-void scif_rb_update_read_ptr(struct scif_rb *rb)
-{
-	u32 new_offset;
-
-	new_offset = rb->current_read_offset;
-	/*
-	 * We must ensure ordering between the all the data committed or read
-	 * previously before we expose the empty slot to the peer by updating
-	 * the read_ptr. This barrier is paired with the memory barrier in
-	 * scif_rb_space(..)
-	 */
-	mb();
-	WRITE_ONCE(*rb->read_ptr, new_offset);
-#ifdef CONFIG_INTEL_MIC_CARD
-	/*
-	 * X100 Si Bug: For the case where a Core is performing an EXT_WR
-	 * followed by a Doorbell Write, the Core must perform two EXT_WR to the
-	 * same address with the same data before it does the Doorbell Write.
-	 * This way, if ordering is violated for the Interrupt Message, it will
-	 * fall just behind the first Posted associated with the first EXT_WR.
-	 */
-	WRITE_ONCE(*rb->read_ptr, new_offset);
-#endif
-}
-
-/**
- * scif_rb_count
- * @rb: ring buffer
- * @size: Number of bytes expected to be read
- *
- * Return: number of bytes that can be read from the RB
- */
-u32 scif_rb_count(struct scif_rb *rb, u32 size)
-{
-	if (scif_rb_ring_cnt(rb->current_write_offset,
-			     rb->current_read_offset,
-			     rb->size) < size) {
-		rb->current_write_offset = *rb->write_ptr;
-		/*
-		 * Update from the HW write pointer if empty only once the peer
-		 * has exposed the new message. This read barrier is paired
-		 * with the write barrier in scif_rb_commit(..)
-		 */
-		smp_rmb();
-	}
-	return scif_rb_ring_cnt(rb->current_write_offset,
-				rb->current_read_offset,
-				rb->size);
-}
diff --git a/drivers/misc/mic/scif/scif_rb.h b/drivers/misc/mic/scif/scif_rb.h
deleted file mode 100644
index 166dffe3093d..000000000000
--- a/drivers/misc/mic/scif/scif_rb.h
+++ /dev/null
@@ -1,100 +0,0 @@
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * This file is provided under a dual BSD/GPLv2 license.  When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * BSD LICENSE
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- *   notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- *   notice, this list of conditions and the following disclaimer in
- *   the documentation and/or other materials provided with the
- *   distribution.
- * * Neither the name of Intel Corporation nor the names of its
- *   contributors may be used to endorse or promote products derived
- *   from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * Intel SCIF driver.
- */
-#ifndef SCIF_RB_H
-#define SCIF_RB_H
-/*
- * This file describes a general purpose, byte based ring buffer. Writers to the
- * ring buffer need to synchronize using a lock. The same is true for readers,
- * although in practice, the ring buffer has a single reader. It is lockless
- * between producer and consumer so it can handle being used across the PCIe
- * bus. The ring buffer ensures that there are no reads across the PCIe bus for
- * performance reasons. Two of these are used to form a single bidirectional
- * queue-pair across PCIe.
- */
-/*
- * struct scif_rb - SCIF Ring Buffer
- *
- * @rb_base: The base of the memory used for storing RB messages
- * @read_ptr: Pointer to the read offset
- * @write_ptr: Pointer to the write offset
- * @size: Size of the memory in rb_base
- * @current_read_offset: Cached read offset for performance
- * @current_write_offset: Cached write offset for performance
- */
-struct scif_rb {
-	void *rb_base;
-	u32 *read_ptr;
-	u32 *write_ptr;
-	u32 size;
-	u32 current_read_offset;
-	u32 current_write_offset;
-};
-
-/* methods used by both */
-void scif_rb_init(struct scif_rb *rb, u32 *read_ptr, u32 *write_ptr,
-		  void *rb_base, u8 size);
-/* writer only methods */
-/* write a new command, then scif_rb_commit() */
-int scif_rb_write(struct scif_rb *rb, void *msg, u32 size);
-/* after write(), then scif_rb_commit() */
-void scif_rb_commit(struct scif_rb *rb);
-/* query space available for writing to a RB. */
-u32 scif_rb_space(struct scif_rb *rb);
-
-/* reader only methods */
-/* read a new message from the ring buffer of size bytes */
-u32 scif_rb_get_next(struct scif_rb *rb, void *msg, u32 size);
-/* update the read pointer so that the space can be reused */
-void scif_rb_update_read_ptr(struct scif_rb *rb);
-/* count the number of bytes that can be read */
-u32 scif_rb_count(struct scif_rb *rb, u32 size);
-#endif
diff --git a/drivers/misc/mic/scif/scif_rma.c b/drivers/misc/mic/scif/scif_rma.c
deleted file mode 100644
index 18fb9d8b8a4b..000000000000
--- a/drivers/misc/mic/scif/scif_rma.c
+++ /dev/null
@@ -1,1760 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include <linux/intel-iommu.h>
-#include <linux/pagemap.h>
-#include <linux/sched/mm.h>
-#include <linux/sched/signal.h>
-
-#include "scif_main.h"
-#include "scif_map.h"
-
-/* Used to skip ulimit checks for registrations with SCIF_MAP_KERNEL flag */
-#define SCIF_MAP_ULIMIT 0x40
-
-bool scif_ulimit_check = 1;
-
-/**
- * scif_rma_ep_init:
- * @ep: end point
- *
- * Initialize RMA per EP data structures.
- */
-void scif_rma_ep_init(struct scif_endpt *ep)
-{
-	struct scif_endpt_rma_info *rma = &ep->rma_info;
-
-	mutex_init(&rma->rma_lock);
-	init_iova_domain(&rma->iovad, PAGE_SIZE, SCIF_IOVA_START_PFN);
-	spin_lock_init(&rma->tc_lock);
-	mutex_init(&rma->mmn_lock);
-	INIT_LIST_HEAD(&rma->reg_list);
-	INIT_LIST_HEAD(&rma->remote_reg_list);
-	atomic_set(&rma->tw_refcount, 0);
-	atomic_set(&rma->tcw_refcount, 0);
-	atomic_set(&rma->tcw_total_pages, 0);
-	atomic_set(&rma->fence_refcount, 0);
-
-	rma->async_list_del = 0;
-	rma->dma_chan = NULL;
-	INIT_LIST_HEAD(&rma->mmn_list);
-	INIT_LIST_HEAD(&rma->vma_list);
-	init_waitqueue_head(&rma->markwq);
-}
-
-/**
- * scif_rma_ep_can_uninit:
- * @ep: end point
- *
- * Returns 1 if an endpoint can be uninitialized and 0 otherwise.
- */
-int scif_rma_ep_can_uninit(struct scif_endpt *ep)
-{
-	int ret = 0;
-
-	mutex_lock(&ep->rma_info.rma_lock);
-	/* Destroy RMA Info only if both lists are empty */
-	if (list_empty(&ep->rma_info.reg_list) &&
-	    list_empty(&ep->rma_info.remote_reg_list) &&
-	    list_empty(&ep->rma_info.mmn_list) &&
-	    !atomic_read(&ep->rma_info.tw_refcount) &&
-	    !atomic_read(&ep->rma_info.tcw_refcount) &&
-	    !atomic_read(&ep->rma_info.fence_refcount))
-		ret = 1;
-	mutex_unlock(&ep->rma_info.rma_lock);
-	return ret;
-}
-
-/**
- * scif_create_pinned_pages:
- * @nr_pages: number of pages in window
- * @prot: read/write protection
- *
- * Allocate and prepare a set of pinned pages.
- */
-static struct scif_pinned_pages *
-scif_create_pinned_pages(int nr_pages, int prot)
-{
-	struct scif_pinned_pages *pin;
-
-	might_sleep();
-	pin = scif_zalloc(sizeof(*pin));
-	if (!pin)
-		goto error;
-
-	pin->pages = scif_zalloc(nr_pages * sizeof(*pin->pages));
-	if (!pin->pages)
-		goto error_free_pinned_pages;
-
-	pin->prot = prot;
-	pin->magic = SCIFEP_MAGIC;
-	return pin;
-
-error_free_pinned_pages:
-	scif_free(pin, sizeof(*pin));
-error:
-	return NULL;
-}
-
-/**
- * scif_destroy_pinned_pages:
- * @pin: A set of pinned pages.
- *
- * Deallocate resources for pinned pages.
- */
-static int scif_destroy_pinned_pages(struct scif_pinned_pages *pin)
-{
-	int j;
-	int writeable = pin->prot & SCIF_PROT_WRITE;
-	int kernel = SCIF_MAP_KERNEL & pin->map_flags;
-
-	if (kernel) {
-		for (j = 0; j < pin->nr_pages; j++) {
-			if (pin->pages[j] && !kernel) {
-				if (writeable)
-					set_page_dirty_lock(pin->pages[j]);
-				put_page(pin->pages[j]);
-			}
-		}
-	} else
-		unpin_user_pages_dirty_lock(pin->pages, pin->nr_pages,
-					    writeable);
-	scif_free(pin->pages,
-		  pin->nr_pages * sizeof(*pin->pages));
-	scif_free(pin, sizeof(*pin));
-	return 0;
-}
-
-/*
- * scif_create_window:
- * @ep: end point
- * @nr_pages: number of pages
- * @offset: registration offset
- * @temp: true if a temporary window is being created
- *
- * Allocate and prepare a self registration window.
- */
-struct scif_window *scif_create_window(struct scif_endpt *ep, int nr_pages,
-				       s64 offset, bool temp)
-{
-	struct scif_window *window;
-
-	might_sleep();
-	window = scif_zalloc(sizeof(*window));
-	if (!window)
-		goto error;
-
-	window->dma_addr = scif_zalloc(nr_pages * sizeof(*window->dma_addr));
-	if (!window->dma_addr)
-		goto error_free_window;
-
-	window->num_pages = scif_zalloc(nr_pages * sizeof(*window->num_pages));
-	if (!window->num_pages)
-		goto error_free_window;
-
-	window->offset = offset;
-	window->ep = (u64)ep;
-	window->magic = SCIFEP_MAGIC;
-	window->reg_state = OP_IDLE;
-	init_waitqueue_head(&window->regwq);
-	window->unreg_state = OP_IDLE;
-	init_waitqueue_head(&window->unregwq);
-	INIT_LIST_HEAD(&window->list);
-	window->type = SCIF_WINDOW_SELF;
-	window->temp = temp;
-	return window;
-
-error_free_window:
-	scif_free(window->dma_addr,
-		  nr_pages * sizeof(*window->dma_addr));
-	scif_free(window, sizeof(*window));
-error:
-	return NULL;
-}
-
-/**
- * scif_destroy_incomplete_window:
- * @ep: end point
- * @window: registration window
- *
- * Deallocate resources for self window.
- */
-static void scif_destroy_incomplete_window(struct scif_endpt *ep,
-					   struct scif_window *window)
-{
-	int err;
-	int nr_pages = window->nr_pages;
-	struct scif_allocmsg *alloc = &window->alloc_handle;
-	struct scifmsg msg;
-
-retry:
-	/* Wait for a SCIF_ALLOC_GNT/REJ message */
-	err = wait_event_timeout(alloc->allocwq,
-				 alloc->state != OP_IN_PROGRESS,
-				 SCIF_NODE_ALIVE_TIMEOUT);
-	if (!err && scifdev_alive(ep))
-		goto retry;
-
-	mutex_lock(&ep->rma_info.rma_lock);
-	if (alloc->state == OP_COMPLETED) {
-		msg.uop = SCIF_FREE_VIRT;
-		msg.src = ep->port;
-		msg.payload[0] = ep->remote_ep;
-		msg.payload[1] = window->alloc_handle.vaddr;
-		msg.payload[2] = (u64)window;
-		msg.payload[3] = SCIF_REGISTER;
-		_scif_nodeqp_send(ep->remote_dev, &msg);
-	}
-	mutex_unlock(&ep->rma_info.rma_lock);
-
-	scif_free_window_offset(ep, window, window->offset);
-	scif_free(window->dma_addr, nr_pages * sizeof(*window->dma_addr));
-	scif_free(window->num_pages, nr_pages * sizeof(*window->num_pages));
-	scif_free(window, sizeof(*window));
-}
-
-/**
- * scif_unmap_window:
- * @remote_dev: SCIF remote device
- * @window: registration window
- *
- * Delete any DMA mappings created for a registered self window
- */
-void scif_unmap_window(struct scif_dev *remote_dev, struct scif_window *window)
-{
-	int j;
-
-	if (scif_is_iommu_enabled() && !scifdev_self(remote_dev)) {
-		if (window->st) {
-			dma_unmap_sg(&remote_dev->sdev->dev,
-				     window->st->sgl, window->st->nents,
-				     DMA_BIDIRECTIONAL);
-			sg_free_table(window->st);
-			kfree(window->st);
-			window->st = NULL;
-		}
-	} else {
-		for (j = 0; j < window->nr_contig_chunks; j++) {
-			if (window->dma_addr[j]) {
-				scif_unmap_single(window->dma_addr[j],
-						  remote_dev,
-						  window->num_pages[j] <<
-						  PAGE_SHIFT);
-				window->dma_addr[j] = 0x0;
-			}
-		}
-	}
-}
-
-static inline struct mm_struct *__scif_acquire_mm(void)
-{
-	if (scif_ulimit_check)
-		return get_task_mm(current);
-	return NULL;
-}
-
-static inline void __scif_release_mm(struct mm_struct *mm)
-{
-	if (mm)
-		mmput(mm);
-}
-
-static inline int
-__scif_dec_pinned_vm_lock(struct mm_struct *mm,
-			  int nr_pages)
-{
-	if (!mm || !nr_pages || !scif_ulimit_check)
-		return 0;
-
-	atomic64_sub(nr_pages, &mm->pinned_vm);
-	return 0;
-}
-
-static inline int __scif_check_inc_pinned_vm(struct mm_struct *mm,
-					     int nr_pages)
-{
-	unsigned long locked, lock_limit;
-
-	if (!mm || !nr_pages || !scif_ulimit_check)
-		return 0;
-
-	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
-	locked = atomic64_add_return(nr_pages, &mm->pinned_vm);
-
-	if ((locked > lock_limit) && !capable(CAP_IPC_LOCK)) {
-		atomic64_sub(nr_pages, &mm->pinned_vm);
-		dev_err(scif_info.mdev.this_device,
-			"locked(%lu) > lock_limit(%lu)\n",
-			locked, lock_limit);
-		return -ENOMEM;
-	}
-	return 0;
-}
-
-/**
- * scif_destroy_window:
- * @ep: end point
- * @window: registration window
- *
- * Deallocate resources for self window.
- */
-int scif_destroy_window(struct scif_endpt *ep, struct scif_window *window)
-{
-	int j;
-	struct scif_pinned_pages *pinned_pages = window->pinned_pages;
-	int nr_pages = window->nr_pages;
-
-	might_sleep();
-	if (!window->temp && window->mm) {
-		__scif_dec_pinned_vm_lock(window->mm, window->nr_pages);
-		__scif_release_mm(window->mm);
-		window->mm = NULL;
-	}
-
-	scif_free_window_offset(ep, window, window->offset);
-	scif_unmap_window(ep->remote_dev, window);
-	/*
-	 * Decrement references for this set of pinned pages from
-	 * this window.
-	 */
-	j = atomic_sub_return(1, &pinned_pages->ref_count);
-	if (j < 0)
-		dev_err(scif_info.mdev.this_device,
-			"%s %d incorrect ref count %d\n",
-			__func__, __LINE__, j);
-	/*
-	 * If the ref count for pinned_pages is zero then someone
-	 * has already called scif_unpin_pages() for it and we should
-	 * destroy the page cache.
-	 */
-	if (!j)
-		scif_destroy_pinned_pages(window->pinned_pages);
-	scif_free(window->dma_addr, nr_pages * sizeof(*window->dma_addr));
-	scif_free(window->num_pages, nr_pages * sizeof(*window->num_pages));
-	window->magic = 0;
-	scif_free(window, sizeof(*window));
-	return 0;
-}
-
-/**
- * scif_create_remote_lookup:
- * @remote_dev: SCIF remote device
- * @window: remote window
- *
- * Allocate and prepare lookup entries for the remote
- * end to copy over the physical addresses.
- * Returns 0 on success and appropriate errno on failure.
- */
-static int scif_create_remote_lookup(struct scif_dev *remote_dev,
-				     struct scif_window *window)
-{
-	int i, j, err = 0;
-	int nr_pages = window->nr_pages;
-	bool vmalloc_dma_phys, vmalloc_num_pages;
-
-	might_sleep();
-	/* Map window */
-	err = scif_map_single(&window->mapped_offset,
-			      window, remote_dev, sizeof(*window));
-	if (err)
-		goto error_window;
-
-	/* Compute the number of lookup entries. 21 == 2MB Shift */
-	window->nr_lookup = ALIGN(nr_pages * PAGE_SIZE,
-					((2) * 1024 * 1024)) >> 21;
-
-	window->dma_addr_lookup.lookup =
-		scif_alloc_coherent(&window->dma_addr_lookup.offset,
-				    remote_dev, window->nr_lookup *
-				    sizeof(*window->dma_addr_lookup.lookup),
-				    GFP_KERNEL | __GFP_ZERO);
-	if (!window->dma_addr_lookup.lookup) {
-		err = -ENOMEM;
-		goto error_window;
-	}
-
-	window->num_pages_lookup.lookup =
-		scif_alloc_coherent(&window->num_pages_lookup.offset,
-				    remote_dev, window->nr_lookup *
-				    sizeof(*window->num_pages_lookup.lookup),
-				    GFP_KERNEL | __GFP_ZERO);
-	if (!window->num_pages_lookup.lookup) {
-		err = -ENOMEM;
-		goto error_window;
-	}
-
-	vmalloc_dma_phys = is_vmalloc_addr(&window->dma_addr[0]);
-	vmalloc_num_pages = is_vmalloc_addr(&window->num_pages[0]);
-
-	/* Now map each of the pages containing physical addresses */
-	for (i = 0, j = 0; i < nr_pages; i += SCIF_NR_ADDR_IN_PAGE, j++) {
-		err = scif_map_page(&window->dma_addr_lookup.lookup[j],
-				    vmalloc_dma_phys ?
-				    vmalloc_to_page(&window->dma_addr[i]) :
-				    virt_to_page(&window->dma_addr[i]),
-				    remote_dev);
-		if (err)
-			goto error_window;
-		err = scif_map_page(&window->num_pages_lookup.lookup[j],
-				    vmalloc_num_pages ?
-				    vmalloc_to_page(&window->num_pages[i]) :
-				    virt_to_page(&window->num_pages[i]),
-				    remote_dev);
-		if (err)
-			goto error_window;
-	}
-	return 0;
-error_window:
-	return err;
-}
-
-/**
- * scif_destroy_remote_lookup:
- * @remote_dev: SCIF remote device
- * @window: remote window
- *
- * Destroy lookup entries used for the remote
- * end to copy over the physical addresses.
- */
-static void scif_destroy_remote_lookup(struct scif_dev *remote_dev,
-				       struct scif_window *window)
-{
-	int i, j;
-
-	if (window->nr_lookup) {
-		struct scif_rma_lookup *lup = &window->dma_addr_lookup;
-		struct scif_rma_lookup *npup = &window->num_pages_lookup;
-
-		for (i = 0, j = 0; i < window->nr_pages;
-			i += SCIF_NR_ADDR_IN_PAGE, j++) {
-			if (lup->lookup && lup->lookup[j])
-				scif_unmap_single(lup->lookup[j],
-						  remote_dev,
-						  PAGE_SIZE);
-			if (npup->lookup && npup->lookup[j])
-				scif_unmap_single(npup->lookup[j],
-						  remote_dev,
-						  PAGE_SIZE);
-		}
-		if (lup->lookup)
-			scif_free_coherent(lup->lookup, lup->offset,
-					   remote_dev, window->nr_lookup *
-					   sizeof(*lup->lookup));
-		if (npup->lookup)
-			scif_free_coherent(npup->lookup, npup->offset,
-					   remote_dev, window->nr_lookup *
-					   sizeof(*npup->lookup));
-		if (window->mapped_offset)
-			scif_unmap_single(window->mapped_offset,
-					  remote_dev, sizeof(*window));
-		window->nr_lookup = 0;
-	}
-}
-
-/**
- * scif_create_remote_window:
- * @scifdev:  SCIF device
- * @nr_pages: number of pages in window
- *
- * Allocate and prepare a remote registration window.
- */
-static struct scif_window *
-scif_create_remote_window(struct scif_dev *scifdev, int nr_pages)
-{
-	struct scif_window *window;
-
-	might_sleep();
-	window = scif_zalloc(sizeof(*window));
-	if (!window)
-		goto error_ret;
-
-	window->magic = SCIFEP_MAGIC;
-	window->nr_pages = nr_pages;
-
-	window->dma_addr = scif_zalloc(nr_pages * sizeof(*window->dma_addr));
-	if (!window->dma_addr)
-		goto error_window;
-
-	window->num_pages = scif_zalloc(nr_pages *
-					sizeof(*window->num_pages));
-	if (!window->num_pages)
-		goto error_window;
-
-	if (scif_create_remote_lookup(scifdev, window))
-		goto error_window;
-
-	window->type = SCIF_WINDOW_PEER;
-	window->unreg_state = OP_IDLE;
-	INIT_LIST_HEAD(&window->list);
-	return window;
-error_window:
-	scif_destroy_remote_window(window);
-error_ret:
-	return NULL;
-}
-
-/**
- * scif_destroy_remote_window:
- * @window: remote registration window
- *
- * Deallocate resources for remote window.
- */
-void
-scif_destroy_remote_window(struct scif_window *window)
-{
-	scif_free(window->dma_addr, window->nr_pages *
-		  sizeof(*window->dma_addr));
-	scif_free(window->num_pages, window->nr_pages *
-		  sizeof(*window->num_pages));
-	window->magic = 0;
-	scif_free(window, sizeof(*window));
-}
-
-/**
- * scif_iommu_map: create DMA mappings if the IOMMU is enabled
- * @remote_dev: SCIF remote device
- * @window: remote registration window
- *
- * Map the physical pages using dma_map_sg(..) and then detect the number
- * of contiguous DMA mappings allocated
- */
-static int scif_iommu_map(struct scif_dev *remote_dev,
-			  struct scif_window *window)
-{
-	struct scatterlist *sg;
-	int i, err;
-	scif_pinned_pages_t pin = window->pinned_pages;
-
-	window->st = kzalloc(sizeof(*window->st), GFP_KERNEL);
-	if (!window->st)
-		return -ENOMEM;
-
-	err = sg_alloc_table(window->st, window->nr_pages, GFP_KERNEL);
-	if (err)
-		return err;
-
-	for_each_sg(window->st->sgl, sg, window->st->nents, i)
-		sg_set_page(sg, pin->pages[i], PAGE_SIZE, 0x0);
-
-	err = dma_map_sg(&remote_dev->sdev->dev, window->st->sgl,
-			 window->st->nents, DMA_BIDIRECTIONAL);
-	if (!err)
-		return -ENOMEM;
-	/* Detect contiguous ranges of DMA mappings */
-	sg = window->st->sgl;
-	for (i = 0; sg; i++) {
-		dma_addr_t last_da;
-
-		window->dma_addr[i] = sg_dma_address(sg);
-		window->num_pages[i] = sg_dma_len(sg) >> PAGE_SHIFT;
-		last_da = sg_dma_address(sg) + sg_dma_len(sg);
-		while ((sg = sg_next(sg)) && sg_dma_address(sg) == last_da) {
-			window->num_pages[i] +=
-				(sg_dma_len(sg) >> PAGE_SHIFT);
-			last_da = window->dma_addr[i] +
-				sg_dma_len(sg);
-		}
-		window->nr_contig_chunks++;
-	}
-	return 0;
-}
-
-/**
- * scif_map_window:
- * @remote_dev: SCIF remote device
- * @window: self registration window
- *
- * Map pages of a window into the aperture/PCI.
- * Also determine addresses required for DMA.
- */
-int
-scif_map_window(struct scif_dev *remote_dev, struct scif_window *window)
-{
-	int i, j, k, err = 0, nr_contig_pages;
-	scif_pinned_pages_t pin;
-	phys_addr_t phys_prev, phys_curr;
-
-	might_sleep();
-
-	pin = window->pinned_pages;
-
-	if (intel_iommu_enabled && !scifdev_self(remote_dev))
-		return scif_iommu_map(remote_dev, window);
-
-	for (i = 0, j = 0; i < window->nr_pages; i += nr_contig_pages, j++) {
-		phys_prev = page_to_phys(pin->pages[i]);
-		nr_contig_pages = 1;
-
-		/* Detect physically contiguous chunks */
-		for (k = i + 1; k < window->nr_pages; k++) {
-			phys_curr = page_to_phys(pin->pages[k]);
-			if (phys_curr != (phys_prev + PAGE_SIZE))
-				break;
-			phys_prev = phys_curr;
-			nr_contig_pages++;
-		}
-		window->num_pages[j] = nr_contig_pages;
-		window->nr_contig_chunks++;
-		if (scif_is_mgmt_node()) {
-			/*
-			 * Management node has to deal with SMPT on X100 and
-			 * hence the DMA mapping is required
-			 */
-			err = scif_map_single(&window->dma_addr[j],
-					      phys_to_virt(page_to_phys(
-							   pin->pages[i])),
-					      remote_dev,
-					      nr_contig_pages << PAGE_SHIFT);
-			if (err)
-				return err;
-		} else {
-			window->dma_addr[j] = page_to_phys(pin->pages[i]);
-		}
-	}
-	return err;
-}
-
-/**
- * scif_send_scif_unregister:
- * @ep: end point
- * @window: self registration window
- *
- * Send a SCIF_UNREGISTER message.
- */
-static int scif_send_scif_unregister(struct scif_endpt *ep,
-				     struct scif_window *window)
-{
-	struct scifmsg msg;
-
-	msg.uop = SCIF_UNREGISTER;
-	msg.src = ep->port;
-	msg.payload[0] = window->alloc_handle.vaddr;
-	msg.payload[1] = (u64)window;
-	return scif_nodeqp_send(ep->remote_dev, &msg);
-}
-
-/**
- * scif_unregister_window:
- * @window: self registration window
- *
- * Send an unregistration request and wait for a response.
- */
-int scif_unregister_window(struct scif_window *window)
-{
-	int err = 0;
-	struct scif_endpt *ep = (struct scif_endpt *)window->ep;
-	bool send_msg = false;
-
-	might_sleep();
-	switch (window->unreg_state) {
-	case OP_IDLE:
-	{
-		window->unreg_state = OP_IN_PROGRESS;
-		send_msg = true;
-	}
-		fallthrough;
-	case OP_IN_PROGRESS:
-	{
-		scif_get_window(window, 1);
-		mutex_unlock(&ep->rma_info.rma_lock);
-		if (send_msg) {
-			err = scif_send_scif_unregister(ep, window);
-			if (err) {
-				window->unreg_state = OP_COMPLETED;
-				goto done;
-			}
-		} else {
-			/* Return ENXIO since unregistration is in progress */
-			mutex_lock(&ep->rma_info.rma_lock);
-			return -ENXIO;
-		}
-retry:
-		/* Wait for a SCIF_UNREGISTER_(N)ACK message */
-		err = wait_event_timeout(window->unregwq,
-					 window->unreg_state != OP_IN_PROGRESS,
-					 SCIF_NODE_ALIVE_TIMEOUT);
-		if (!err && scifdev_alive(ep))
-			goto retry;
-		if (!err) {
-			err = -ENODEV;
-			window->unreg_state = OP_COMPLETED;
-			dev_err(scif_info.mdev.this_device,
-				"%s %d err %d\n", __func__, __LINE__, err);
-		}
-		if (err > 0)
-			err = 0;
-done:
-		mutex_lock(&ep->rma_info.rma_lock);
-		scif_put_window(window, 1);
-		break;
-	}
-	case OP_FAILED:
-	{
-		if (!scifdev_alive(ep)) {
-			err = -ENODEV;
-			window->unreg_state = OP_COMPLETED;
-		}
-		break;
-	}
-	case OP_COMPLETED:
-		break;
-	default:
-		err = -ENODEV;
-	}
-
-	if (window->unreg_state == OP_COMPLETED && window->ref_count)
-		scif_put_window(window, window->nr_pages);
-
-	if (!window->ref_count) {
-		atomic_inc(&ep->rma_info.tw_refcount);
-		list_del_init(&window->list);
-		scif_free_window_offset(ep, window, window->offset);
-		mutex_unlock(&ep->rma_info.rma_lock);
-		if ((!!(window->pinned_pages->map_flags & SCIF_MAP_KERNEL)) &&
-		    scifdev_alive(ep)) {
-			scif_drain_dma_intr(ep->remote_dev->sdev,
-					    ep->rma_info.dma_chan);
-		} else {
-			if (!__scif_dec_pinned_vm_lock(window->mm,
-						       window->nr_pages)) {
-				__scif_release_mm(window->mm);
-				window->mm = NULL;
-			}
-		}
-		scif_queue_for_cleanup(window, &scif_info.rma);
-		mutex_lock(&ep->rma_info.rma_lock);
-	}
-	return err;
-}
-
-/**
- * scif_send_alloc_request:
- * @ep: end point
- * @window: self registration window
- *
- * Send a remote window allocation request
- */
-static int scif_send_alloc_request(struct scif_endpt *ep,
-				   struct scif_window *window)
-{
-	struct scifmsg msg;
-	struct scif_allocmsg *alloc = &window->alloc_handle;
-
-	/* Set up the Alloc Handle */
-	alloc->state = OP_IN_PROGRESS;
-	init_waitqueue_head(&alloc->allocwq);
-
-	/* Send out an allocation request */
-	msg.uop = SCIF_ALLOC_REQ;
-	msg.payload[1] = window->nr_pages;
-	msg.payload[2] = (u64)&window->alloc_handle;
-	return _scif_nodeqp_send(ep->remote_dev, &msg);
-}
-
-/**
- * scif_prep_remote_window:
- * @ep: end point
- * @window: self registration window
- *
- * Send a remote window allocation request, wait for an allocation response,
- * and prepares the remote window by copying over the page lists
- */
-static int scif_prep_remote_window(struct scif_endpt *ep,
-				   struct scif_window *window)
-{
-	struct scifmsg msg;
-	struct scif_window *remote_window;
-	struct scif_allocmsg *alloc = &window->alloc_handle;
-	dma_addr_t *dma_phys_lookup, *tmp, *num_pages_lookup, *tmp1;
-	int i = 0, j = 0;
-	int nr_contig_chunks, loop_nr_contig_chunks;
-	int remaining_nr_contig_chunks, nr_lookup;
-	int err, map_err;
-
-	map_err = scif_map_window(ep->remote_dev, window);
-	if (map_err)
-		dev_err(&ep->remote_dev->sdev->dev,
-			"%s %d map_err %d\n", __func__, __LINE__, map_err);
-	remaining_nr_contig_chunks = window->nr_contig_chunks;
-	nr_contig_chunks = window->nr_contig_chunks;
-retry:
-	/* Wait for a SCIF_ALLOC_GNT/REJ message */
-	err = wait_event_timeout(alloc->allocwq,
-				 alloc->state != OP_IN_PROGRESS,
-				 SCIF_NODE_ALIVE_TIMEOUT);
-	mutex_lock(&ep->rma_info.rma_lock);
-	/* Synchronize with the thread waking up allocwq */
-	mutex_unlock(&ep->rma_info.rma_lock);
-	if (!err && scifdev_alive(ep))
-		goto retry;
-
-	if (!err)
-		err = -ENODEV;
-
-	if (err > 0)
-		err = 0;
-	else
-		return err;
-
-	/* Bail out. The remote end rejected this request */
-	if (alloc->state == OP_FAILED)
-		return -ENOMEM;
-
-	if (map_err) {
-		dev_err(&ep->remote_dev->sdev->dev,
-			"%s %d err %d\n", __func__, __LINE__, map_err);
-		msg.uop = SCIF_FREE_VIRT;
-		msg.src = ep->port;
-		msg.payload[0] = ep->remote_ep;
-		msg.payload[1] = window->alloc_handle.vaddr;
-		msg.payload[2] = (u64)window;
-		msg.payload[3] = SCIF_REGISTER;
-		spin_lock(&ep->lock);
-		if (ep->state == SCIFEP_CONNECTED)
-			err = _scif_nodeqp_send(ep->remote_dev, &msg);
-		else
-			err = -ENOTCONN;
-		spin_unlock(&ep->lock);
-		return err;
-	}
-
-	remote_window = scif_ioremap(alloc->phys_addr, sizeof(*window),
-				     ep->remote_dev);
-
-	/* Compute the number of lookup entries. 21 == 2MB Shift */
-	nr_lookup = ALIGN(nr_contig_chunks, SCIF_NR_ADDR_IN_PAGE)
-			  >> ilog2(SCIF_NR_ADDR_IN_PAGE);
-
-	dma_phys_lookup =
-		scif_ioremap(remote_window->dma_addr_lookup.offset,
-			     nr_lookup *
-			     sizeof(*remote_window->dma_addr_lookup.lookup),
-			     ep->remote_dev);
-	num_pages_lookup =
-		scif_ioremap(remote_window->num_pages_lookup.offset,
-			     nr_lookup *
-			     sizeof(*remote_window->num_pages_lookup.lookup),
-			     ep->remote_dev);
-
-	while (remaining_nr_contig_chunks) {
-		loop_nr_contig_chunks = min_t(int, remaining_nr_contig_chunks,
-					      (int)SCIF_NR_ADDR_IN_PAGE);
-		/* #1/2 - Copy  physical addresses over to the remote side */
-
-		/* #2/2 - Copy DMA addresses (addresses that are fed into the
-		 * DMA engine) We transfer bus addresses which are then
-		 * converted into a MIC physical address on the remote
-		 * side if it is a MIC, if the remote node is a mgmt node we
-		 * transfer the MIC physical address
-		 */
-		tmp = scif_ioremap(dma_phys_lookup[j],
-				   loop_nr_contig_chunks *
-				   sizeof(*window->dma_addr),
-				   ep->remote_dev);
-		tmp1 = scif_ioremap(num_pages_lookup[j],
-				    loop_nr_contig_chunks *
-				    sizeof(*window->num_pages),
-				    ep->remote_dev);
-		if (scif_is_mgmt_node()) {
-			memcpy_toio((void __force __iomem *)tmp,
-				    &window->dma_addr[i], loop_nr_contig_chunks
-				    * sizeof(*window->dma_addr));
-			memcpy_toio((void __force __iomem *)tmp1,
-				    &window->num_pages[i], loop_nr_contig_chunks
-				    * sizeof(*window->num_pages));
-		} else {
-			if (scifdev_is_p2p(ep->remote_dev)) {
-				/*
-				 * add remote node's base address for this node
-				 * to convert it into a MIC address
-				 */
-				int m;
-				dma_addr_t dma_addr;
-
-				for (m = 0; m < loop_nr_contig_chunks; m++) {
-					dma_addr = window->dma_addr[i + m] +
-						ep->remote_dev->base_addr;
-					writeq(dma_addr,
-					       (void __force __iomem *)&tmp[m]);
-				}
-				memcpy_toio((void __force __iomem *)tmp1,
-					    &window->num_pages[i],
-					    loop_nr_contig_chunks
-					    * sizeof(*window->num_pages));
-			} else {
-				/* Mgmt node or loopback - transfer DMA
-				 * addresses as is, this is the same as a
-				 * MIC physical address (we use the dma_addr
-				 * and not the phys_addr array since the
-				 * phys_addr is only setup if there is a mmap()
-				 * request from the mgmt node)
-				 */
-				memcpy_toio((void __force __iomem *)tmp,
-					    &window->dma_addr[i],
-					    loop_nr_contig_chunks *
-					    sizeof(*window->dma_addr));
-				memcpy_toio((void __force __iomem *)tmp1,
-					    &window->num_pages[i],
-					    loop_nr_contig_chunks *
-					    sizeof(*window->num_pages));
-			}
-		}
-		remaining_nr_contig_chunks -= loop_nr_contig_chunks;
-		i += loop_nr_contig_chunks;
-		j++;
-		scif_iounmap(tmp, loop_nr_contig_chunks *
-			     sizeof(*window->dma_addr), ep->remote_dev);
-		scif_iounmap(tmp1, loop_nr_contig_chunks *
-			     sizeof(*window->num_pages), ep->remote_dev);
-	}
-
-	/* Prepare the remote window for the peer */
-	remote_window->peer_window = (u64)window;
-	remote_window->offset = window->offset;
-	remote_window->prot = window->prot;
-	remote_window->nr_contig_chunks = nr_contig_chunks;
-	remote_window->ep = ep->remote_ep;
-	scif_iounmap(num_pages_lookup,
-		     nr_lookup *
-		     sizeof(*remote_window->num_pages_lookup.lookup),
-		     ep->remote_dev);
-	scif_iounmap(dma_phys_lookup,
-		     nr_lookup *
-		     sizeof(*remote_window->dma_addr_lookup.lookup),
-		     ep->remote_dev);
-	scif_iounmap(remote_window, sizeof(*remote_window), ep->remote_dev);
-	window->peer_window = alloc->vaddr;
-	return err;
-}
-
-/**
- * scif_send_scif_register:
- * @ep: end point
- * @window: self registration window
- *
- * Send a SCIF_REGISTER message if EP is connected and wait for a
- * SCIF_REGISTER_(N)ACK message else send a SCIF_FREE_VIRT
- * message so that the peer can free its remote window allocated earlier.
- */
-static int scif_send_scif_register(struct scif_endpt *ep,
-				   struct scif_window *window)
-{
-	int err = 0;
-	struct scifmsg msg;
-
-	msg.src = ep->port;
-	msg.payload[0] = ep->remote_ep;
-	msg.payload[1] = window->alloc_handle.vaddr;
-	msg.payload[2] = (u64)window;
-	spin_lock(&ep->lock);
-	if (ep->state == SCIFEP_CONNECTED) {
-		msg.uop = SCIF_REGISTER;
-		window->reg_state = OP_IN_PROGRESS;
-		err = _scif_nodeqp_send(ep->remote_dev, &msg);
-		spin_unlock(&ep->lock);
-		if (!err) {
-retry:
-			/* Wait for a SCIF_REGISTER_(N)ACK message */
-			err = wait_event_timeout(window->regwq,
-						 window->reg_state !=
-						 OP_IN_PROGRESS,
-						 SCIF_NODE_ALIVE_TIMEOUT);
-			if (!err && scifdev_alive(ep))
-				goto retry;
-			err = !err ? -ENODEV : 0;
-			if (window->reg_state == OP_FAILED)
-				err = -ENOTCONN;
-		}
-	} else {
-		msg.uop = SCIF_FREE_VIRT;
-		msg.payload[3] = SCIF_REGISTER;
-		err = _scif_nodeqp_send(ep->remote_dev, &msg);
-		spin_unlock(&ep->lock);
-		if (!err)
-			err = -ENOTCONN;
-	}
-	return err;
-}
-
-/**
- * scif_get_window_offset:
- * @ep: end point descriptor
- * @flags: flags
- * @offset: offset hint
- * @num_pages: number of pages
- * @out_offset: computed offset returned by reference.
- *
- * Compute/Claim a new offset for this EP.
- */
-int scif_get_window_offset(struct scif_endpt *ep, int flags, s64 offset,
-			   int num_pages, s64 *out_offset)
-{
-	s64 page_index;
-	struct iova *iova_ptr;
-	int err = 0;
-
-	if (flags & SCIF_MAP_FIXED) {
-		page_index = SCIF_IOVA_PFN(offset);
-		iova_ptr = reserve_iova(&ep->rma_info.iovad, page_index,
-					page_index + num_pages - 1);
-		if (!iova_ptr)
-			err = -EADDRINUSE;
-	} else {
-		iova_ptr = alloc_iova(&ep->rma_info.iovad, num_pages,
-				      SCIF_DMA_63BIT_PFN - 1, 0);
-		if (!iova_ptr)
-			err = -ENOMEM;
-	}
-	if (!err)
-		*out_offset = (iova_ptr->pfn_lo) << PAGE_SHIFT;
-	return err;
-}
-
-/**
- * scif_free_window_offset:
- * @ep: end point descriptor
- * @window: registration window
- * @offset: Offset to be freed
- *
- * Free offset for this EP. The callee is supposed to grab
- * the RMA mutex before calling this API.
- */
-void scif_free_window_offset(struct scif_endpt *ep,
-			     struct scif_window *window, s64 offset)
-{
-	if ((window && !window->offset_freed) || !window) {
-		free_iova(&ep->rma_info.iovad, offset >> PAGE_SHIFT);
-		if (window)
-			window->offset_freed = true;
-	}
-}
-
-/**
- * scif_alloc_req: Respond to SCIF_ALLOC_REQ interrupt message
- * @scifdev:    SCIF device
- * @msg:        Interrupt message
- *
- * Remote side is requesting a memory allocation.
- */
-void scif_alloc_req(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	int err;
-	struct scif_window *window = NULL;
-	int nr_pages = msg->payload[1];
-
-	window = scif_create_remote_window(scifdev, nr_pages);
-	if (!window) {
-		err = -ENOMEM;
-		goto error;
-	}
-
-	/* The peer's allocation request is granted */
-	msg->uop = SCIF_ALLOC_GNT;
-	msg->payload[0] = (u64)window;
-	msg->payload[1] = window->mapped_offset;
-	err = scif_nodeqp_send(scifdev, msg);
-	if (err)
-		scif_destroy_remote_window(window);
-	return;
-error:
-	/* The peer's allocation request is rejected */
-	dev_err(&scifdev->sdev->dev,
-		"%s %d error %d alloc_ptr %p nr_pages 0x%x\n",
-		__func__, __LINE__, err, window, nr_pages);
-	msg->uop = SCIF_ALLOC_REJ;
-	scif_nodeqp_send(scifdev, msg);
-}
-
-/**
- * scif_alloc_gnt_rej: Respond to SCIF_ALLOC_GNT/REJ interrupt message
- * @scifdev:    SCIF device
- * @msg:        Interrupt message
- *
- * Remote side responded to a memory allocation.
- */
-void scif_alloc_gnt_rej(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	struct scif_allocmsg *handle = (struct scif_allocmsg *)msg->payload[2];
-	struct scif_window *window = container_of(handle, struct scif_window,
-						  alloc_handle);
-	struct scif_endpt *ep = (struct scif_endpt *)window->ep;
-
-	mutex_lock(&ep->rma_info.rma_lock);
-	handle->vaddr = msg->payload[0];
-	handle->phys_addr = msg->payload[1];
-	if (msg->uop == SCIF_ALLOC_GNT)
-		handle->state = OP_COMPLETED;
-	else
-		handle->state = OP_FAILED;
-	wake_up(&handle->allocwq);
-	mutex_unlock(&ep->rma_info.rma_lock);
-}
-
-/**
- * scif_free_virt: Respond to SCIF_FREE_VIRT interrupt message
- * @scifdev:    SCIF device
- * @msg:        Interrupt message
- *
- * Free up memory kmalloc'd earlier.
- */
-void scif_free_virt(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	struct scif_window *window = (struct scif_window *)msg->payload[1];
-
-	scif_destroy_remote_window(window);
-}
-
-static void
-scif_fixup_aper_base(struct scif_dev *dev, struct scif_window *window)
-{
-	int j;
-	struct scif_hw_dev *sdev = dev->sdev;
-	phys_addr_t apt_base = 0;
-
-	/*
-	 * Add the aperture base if the DMA address is not card relative
-	 * since the DMA addresses need to be an offset into the bar
-	 */
-	if (!scifdev_self(dev) && window->type == SCIF_WINDOW_PEER &&
-	    sdev->aper && !sdev->card_rel_da)
-		apt_base = sdev->aper->pa;
-	else
-		return;
-
-	for (j = 0; j < window->nr_contig_chunks; j++) {
-		if (window->num_pages[j])
-			window->dma_addr[j] += apt_base;
-		else
-			break;
-	}
-}
-
-/**
- * scif_recv_reg: Respond to SCIF_REGISTER interrupt message
- * @scifdev:    SCIF device
- * @msg:        Interrupt message
- *
- * Update remote window list with a new registered window.
- */
-void scif_recv_reg(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
-	struct scif_window *window =
-		(struct scif_window *)msg->payload[1];
-
-	mutex_lock(&ep->rma_info.rma_lock);
-	spin_lock(&ep->lock);
-	if (ep->state == SCIFEP_CONNECTED) {
-		msg->uop = SCIF_REGISTER_ACK;
-		scif_nodeqp_send(ep->remote_dev, msg);
-		scif_fixup_aper_base(ep->remote_dev, window);
-		/* No further failures expected. Insert new window */
-		scif_insert_window(window, &ep->rma_info.remote_reg_list);
-	} else {
-		msg->uop = SCIF_REGISTER_NACK;
-		scif_nodeqp_send(ep->remote_dev, msg);
-	}
-	spin_unlock(&ep->lock);
-	mutex_unlock(&ep->rma_info.rma_lock);
-	/* free up any lookup resources now that page lists are transferred */
-	scif_destroy_remote_lookup(ep->remote_dev, window);
-	/*
-	 * We could not insert the window but we need to
-	 * destroy the window.
-	 */
-	if (msg->uop == SCIF_REGISTER_NACK)
-		scif_destroy_remote_window(window);
-}
-
-/**
- * scif_recv_unreg: Respond to SCIF_UNREGISTER interrupt message
- * @scifdev:    SCIF device
- * @msg:        Interrupt message
- *
- * Remove window from remote registration list;
- */
-void scif_recv_unreg(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	struct scif_rma_req req;
-	struct scif_window *window = NULL;
-	struct scif_window *recv_window =
-		(struct scif_window *)msg->payload[0];
-	struct scif_endpt *ep;
-	int del_window = 0;
-
-	ep = (struct scif_endpt *)recv_window->ep;
-	req.out_window = &window;
-	req.offset = recv_window->offset;
-	req.prot = 0;
-	req.nr_bytes = recv_window->nr_pages << PAGE_SHIFT;
-	req.type = SCIF_WINDOW_FULL;
-	req.head = &ep->rma_info.remote_reg_list;
-	msg->payload[0] = ep->remote_ep;
-
-	mutex_lock(&ep->rma_info.rma_lock);
-	/* Does a valid window exist? */
-	if (scif_query_window(&req)) {
-		dev_err(&scifdev->sdev->dev,
-			"%s %d -ENXIO\n", __func__, __LINE__);
-		msg->uop = SCIF_UNREGISTER_ACK;
-		goto error;
-	}
-	if (window) {
-		if (window->ref_count)
-			scif_put_window(window, window->nr_pages);
-		else
-			dev_err(&scifdev->sdev->dev,
-				"%s %d ref count should be +ve\n",
-				__func__, __LINE__);
-		window->unreg_state = OP_COMPLETED;
-		if (!window->ref_count) {
-			msg->uop = SCIF_UNREGISTER_ACK;
-			atomic_inc(&ep->rma_info.tw_refcount);
-			ep->rma_info.async_list_del = 1;
-			list_del_init(&window->list);
-			del_window = 1;
-		} else {
-			/* NACK! There are valid references to this window */
-			msg->uop = SCIF_UNREGISTER_NACK;
-		}
-	} else {
-		/* The window did not make its way to the list at all. ACK */
-		msg->uop = SCIF_UNREGISTER_ACK;
-		scif_destroy_remote_window(recv_window);
-	}
-error:
-	mutex_unlock(&ep->rma_info.rma_lock);
-	if (del_window)
-		scif_drain_dma_intr(ep->remote_dev->sdev,
-				    ep->rma_info.dma_chan);
-	scif_nodeqp_send(ep->remote_dev, msg);
-	if (del_window)
-		scif_queue_for_cleanup(window, &scif_info.rma);
-}
-
-/**
- * scif_recv_reg_ack: Respond to SCIF_REGISTER_ACK interrupt message
- * @scifdev:    SCIF device
- * @msg:        Interrupt message
- *
- * Wake up the window waiting to complete registration.
- */
-void scif_recv_reg_ack(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	struct scif_window *window =
-		(struct scif_window *)msg->payload[2];
-	struct scif_endpt *ep = (struct scif_endpt *)window->ep;
-
-	mutex_lock(&ep->rma_info.rma_lock);
-	window->reg_state = OP_COMPLETED;
-	wake_up(&window->regwq);
-	mutex_unlock(&ep->rma_info.rma_lock);
-}
-
-/**
- * scif_recv_reg_nack: Respond to SCIF_REGISTER_NACK interrupt message
- * @scifdev:    SCIF device
- * @msg:        Interrupt message
- *
- * Wake up the window waiting to inform it that registration
- * cannot be completed.
- */
-void scif_recv_reg_nack(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	struct scif_window *window =
-		(struct scif_window *)msg->payload[2];
-	struct scif_endpt *ep = (struct scif_endpt *)window->ep;
-
-	mutex_lock(&ep->rma_info.rma_lock);
-	window->reg_state = OP_FAILED;
-	wake_up(&window->regwq);
-	mutex_unlock(&ep->rma_info.rma_lock);
-}
-
-/**
- * scif_recv_unreg_ack: Respond to SCIF_UNREGISTER_ACK interrupt message
- * @scifdev:    SCIF device
- * @msg:        Interrupt message
- *
- * Wake up the window waiting to complete unregistration.
- */
-void scif_recv_unreg_ack(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	struct scif_window *window =
-		(struct scif_window *)msg->payload[1];
-	struct scif_endpt *ep = (struct scif_endpt *)window->ep;
-
-	mutex_lock(&ep->rma_info.rma_lock);
-	window->unreg_state = OP_COMPLETED;
-	wake_up(&window->unregwq);
-	mutex_unlock(&ep->rma_info.rma_lock);
-}
-
-/**
- * scif_recv_unreg_nack: Respond to SCIF_UNREGISTER_NACK interrupt message
- * @scifdev:    SCIF device
- * @msg:        Interrupt message
- *
- * Wake up the window waiting to inform it that unregistration
- * cannot be completed immediately.
- */
-void scif_recv_unreg_nack(struct scif_dev *scifdev, struct scifmsg *msg)
-{
-	struct scif_window *window =
-		(struct scif_window *)msg->payload[1];
-	struct scif_endpt *ep = (struct scif_endpt *)window->ep;
-
-	mutex_lock(&ep->rma_info.rma_lock);
-	window->unreg_state = OP_FAILED;
-	wake_up(&window->unregwq);
-	mutex_unlock(&ep->rma_info.rma_lock);
-}
-
-int __scif_pin_pages(void *addr, size_t len, int *out_prot,
-		     int map_flags, scif_pinned_pages_t *pages)
-{
-	struct scif_pinned_pages *pinned_pages;
-	int nr_pages, err = 0, i;
-	bool vmalloc_addr = false;
-	bool try_upgrade = false;
-	int prot = *out_prot;
-	int ulimit = 0;
-	struct mm_struct *mm = NULL;
-
-	/* Unsupported flags */
-	if (map_flags & ~(SCIF_MAP_KERNEL | SCIF_MAP_ULIMIT))
-		return -EINVAL;
-	ulimit = !!(map_flags & SCIF_MAP_ULIMIT);
-
-	/* Unsupported protection requested */
-	if (prot & ~(SCIF_PROT_READ | SCIF_PROT_WRITE))
-		return -EINVAL;
-
-	/* addr/len must be page aligned. len should be non zero */
-	if (!len ||
-	    (ALIGN((u64)addr, PAGE_SIZE) != (u64)addr) ||
-	    (ALIGN((u64)len, PAGE_SIZE) != (u64)len))
-		return -EINVAL;
-
-	might_sleep();
-
-	nr_pages = len >> PAGE_SHIFT;
-
-	/* Allocate a set of pinned pages */
-	pinned_pages = scif_create_pinned_pages(nr_pages, prot);
-	if (!pinned_pages)
-		return -ENOMEM;
-
-	if (map_flags & SCIF_MAP_KERNEL) {
-		if (is_vmalloc_addr(addr))
-			vmalloc_addr = true;
-
-		for (i = 0; i < nr_pages; i++) {
-			if (vmalloc_addr)
-				pinned_pages->pages[i] =
-					vmalloc_to_page(addr + (i * PAGE_SIZE));
-			else
-				pinned_pages->pages[i] =
-					virt_to_page(addr + (i * PAGE_SIZE));
-		}
-		pinned_pages->nr_pages = nr_pages;
-		pinned_pages->map_flags = SCIF_MAP_KERNEL;
-	} else {
-		/*
-		 * SCIF supports registration caching. If a registration has
-		 * been requested with read only permissions, then we try
-		 * to pin the pages with RW permissions so that a subsequent
-		 * transfer with RW permission can hit the cache instead of
-		 * invalidating it. If the upgrade fails with RW then we
-		 * revert back to R permission and retry
-		 */
-		if (prot == SCIF_PROT_READ)
-			try_upgrade = true;
-		prot |= SCIF_PROT_WRITE;
-retry:
-		mm = current->mm;
-		if (ulimit) {
-			err = __scif_check_inc_pinned_vm(mm, nr_pages);
-			if (err) {
-				pinned_pages->nr_pages = 0;
-				goto error_unmap;
-			}
-		}
-
-		pinned_pages->nr_pages = pin_user_pages_fast(
-				(u64)addr,
-				nr_pages,
-				(prot & SCIF_PROT_WRITE) ? FOLL_WRITE : 0,
-				pinned_pages->pages);
-		if (nr_pages != pinned_pages->nr_pages) {
-			if (pinned_pages->nr_pages < 0)
-				pinned_pages->nr_pages = 0;
-			if (try_upgrade) {
-				if (ulimit)
-					__scif_dec_pinned_vm_lock(mm, nr_pages);
-				/* Roll back any pinned pages */
-				unpin_user_pages(pinned_pages->pages,
-						 pinned_pages->nr_pages);
-				prot &= ~SCIF_PROT_WRITE;
-				try_upgrade = false;
-				goto retry;
-			}
-		}
-		pinned_pages->map_flags = 0;
-	}
-
-	if (pinned_pages->nr_pages < nr_pages) {
-		err = -EFAULT;
-		goto dec_pinned;
-	}
-
-	*out_prot = prot;
-	atomic_set(&pinned_pages->ref_count, 1);
-	*pages = pinned_pages;
-	return err;
-dec_pinned:
-	if (ulimit)
-		__scif_dec_pinned_vm_lock(mm, nr_pages);
-	/* Something went wrong! Rollback */
-error_unmap:
-	scif_destroy_pinned_pages(pinned_pages);
-	*pages = NULL;
-	dev_dbg(scif_info.mdev.this_device,
-		"%s %d err %d len 0x%lx\n", __func__, __LINE__, err, len);
-	return err;
-}
-
-int scif_pin_pages(void *addr, size_t len, int prot,
-		   int map_flags, scif_pinned_pages_t *pages)
-{
-	return __scif_pin_pages(addr, len, &prot, map_flags, pages);
-}
-EXPORT_SYMBOL_GPL(scif_pin_pages);
-
-int scif_unpin_pages(scif_pinned_pages_t pinned_pages)
-{
-	int err = 0, ret;
-
-	if (!pinned_pages || SCIFEP_MAGIC != pinned_pages->magic)
-		return -EINVAL;
-
-	ret = atomic_sub_return(1, &pinned_pages->ref_count);
-	if (ret < 0) {
-		dev_err(scif_info.mdev.this_device,
-			"%s %d scif_unpin_pages called without pinning? rc %d\n",
-			__func__, __LINE__, ret);
-		return -EINVAL;
-	}
-	/*
-	 * Destroy the window if the ref count for this set of pinned
-	 * pages has dropped to zero. If it is positive then there is
-	 * a valid registered window which is backed by these pages and
-	 * it will be destroyed once all such windows are unregistered.
-	 */
-	if (!ret)
-		err = scif_destroy_pinned_pages(pinned_pages);
-
-	return err;
-}
-EXPORT_SYMBOL_GPL(scif_unpin_pages);
-
-static inline void
-scif_insert_local_window(struct scif_window *window, struct scif_endpt *ep)
-{
-	mutex_lock(&ep->rma_info.rma_lock);
-	scif_insert_window(window, &ep->rma_info.reg_list);
-	mutex_unlock(&ep->rma_info.rma_lock);
-}
-
-off_t scif_register_pinned_pages(scif_epd_t epd,
-				 scif_pinned_pages_t pinned_pages,
-				 off_t offset, int map_flags)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)epd;
-	s64 computed_offset;
-	struct scif_window *window;
-	int err;
-	size_t len;
-	struct device *spdev;
-
-	/* Unsupported flags */
-	if (map_flags & ~SCIF_MAP_FIXED)
-		return -EINVAL;
-
-	len = pinned_pages->nr_pages << PAGE_SHIFT;
-
-	/*
-	 * Offset is not page aligned/negative or offset+len
-	 * wraps around with SCIF_MAP_FIXED.
-	 */
-	if ((map_flags & SCIF_MAP_FIXED) &&
-	    ((ALIGN(offset, PAGE_SIZE) != offset) ||
-	    (offset < 0) ||
-	    (len > LONG_MAX - offset)))
-		return -EINVAL;
-
-	might_sleep();
-
-	err = scif_verify_epd(ep);
-	if (err)
-		return err;
-	/*
-	 * It is an error to pass pinned_pages to scif_register_pinned_pages()
-	 * after calling scif_unpin_pages().
-	 */
-	if (!atomic_add_unless(&pinned_pages->ref_count, 1, 0))
-		return -EINVAL;
-
-	/* Compute the offset for this registration */
-	err = scif_get_window_offset(ep, map_flags, offset,
-				     len, &computed_offset);
-	if (err) {
-		atomic_sub(1, &pinned_pages->ref_count);
-		return err;
-	}
-
-	/* Allocate and prepare self registration window */
-	window = scif_create_window(ep, pinned_pages->nr_pages,
-				    computed_offset, false);
-	if (!window) {
-		atomic_sub(1, &pinned_pages->ref_count);
-		scif_free_window_offset(ep, NULL, computed_offset);
-		return -ENOMEM;
-	}
-
-	window->pinned_pages = pinned_pages;
-	window->nr_pages = pinned_pages->nr_pages;
-	window->prot = pinned_pages->prot;
-
-	spdev = scif_get_peer_dev(ep->remote_dev);
-	if (IS_ERR(spdev)) {
-		err = PTR_ERR(spdev);
-		scif_destroy_window(ep, window);
-		return err;
-	}
-	err = scif_send_alloc_request(ep, window);
-	if (err) {
-		dev_err(&ep->remote_dev->sdev->dev,
-			"%s %d err %d\n", __func__, __LINE__, err);
-		goto error_unmap;
-	}
-
-	/* Prepare the remote registration window */
-	err = scif_prep_remote_window(ep, window);
-	if (err) {
-		dev_err(&ep->remote_dev->sdev->dev,
-			"%s %d err %d\n", __func__, __LINE__, err);
-		goto error_unmap;
-	}
-
-	/* Tell the peer about the new window */
-	err = scif_send_scif_register(ep, window);
-	if (err) {
-		dev_err(&ep->remote_dev->sdev->dev,
-			"%s %d err %d\n", __func__, __LINE__, err);
-		goto error_unmap;
-	}
-
-	scif_put_peer_dev(spdev);
-	/* No further failures expected. Insert new window */
-	scif_insert_local_window(window, ep);
-	return computed_offset;
-error_unmap:
-	scif_destroy_window(ep, window);
-	scif_put_peer_dev(spdev);
-	dev_err(&ep->remote_dev->sdev->dev,
-		"%s %d err %d\n", __func__, __LINE__, err);
-	return err;
-}
-EXPORT_SYMBOL_GPL(scif_register_pinned_pages);
-
-off_t scif_register(scif_epd_t epd, void *addr, size_t len, off_t offset,
-		    int prot, int map_flags)
-{
-	scif_pinned_pages_t pinned_pages;
-	off_t err;
-	struct scif_endpt *ep = (struct scif_endpt *)epd;
-	s64 computed_offset;
-	struct scif_window *window;
-	struct mm_struct *mm = NULL;
-	struct device *spdev;
-
-	dev_dbg(scif_info.mdev.this_device,
-		"SCIFAPI register: ep %p addr %p len 0x%lx offset 0x%lx prot 0x%x map_flags 0x%x\n",
-		epd, addr, len, offset, prot, map_flags);
-	/* Unsupported flags */
-	if (map_flags & ~(SCIF_MAP_FIXED | SCIF_MAP_KERNEL))
-		return -EINVAL;
-
-	/*
-	 * Offset is not page aligned/negative or offset+len
-	 * wraps around with SCIF_MAP_FIXED.
-	 */
-	if ((map_flags & SCIF_MAP_FIXED) &&
-	    ((ALIGN(offset, PAGE_SIZE) != offset) ||
-	    (offset < 0) ||
-	    (len > LONG_MAX - offset)))
-		return -EINVAL;
-
-	/* Unsupported protection requested */
-	if (prot & ~(SCIF_PROT_READ | SCIF_PROT_WRITE))
-		return -EINVAL;
-
-	/* addr/len must be page aligned. len should be non zero */
-	if (!len || (ALIGN((u64)addr, PAGE_SIZE) != (u64)addr) ||
-	    (ALIGN(len, PAGE_SIZE) != len))
-		return -EINVAL;
-
-	might_sleep();
-
-	err = scif_verify_epd(ep);
-	if (err)
-		return err;
-
-	/* Compute the offset for this registration */
-	err = scif_get_window_offset(ep, map_flags, offset,
-				     len >> PAGE_SHIFT, &computed_offset);
-	if (err)
-		return err;
-
-	spdev = scif_get_peer_dev(ep->remote_dev);
-	if (IS_ERR(spdev)) {
-		err = PTR_ERR(spdev);
-		scif_free_window_offset(ep, NULL, computed_offset);
-		return err;
-	}
-	/* Allocate and prepare self registration window */
-	window = scif_create_window(ep, len >> PAGE_SHIFT,
-				    computed_offset, false);
-	if (!window) {
-		scif_free_window_offset(ep, NULL, computed_offset);
-		scif_put_peer_dev(spdev);
-		return -ENOMEM;
-	}
-
-	window->nr_pages = len >> PAGE_SHIFT;
-
-	err = scif_send_alloc_request(ep, window);
-	if (err) {
-		scif_destroy_incomplete_window(ep, window);
-		scif_put_peer_dev(spdev);
-		return err;
-	}
-
-	if (!(map_flags & SCIF_MAP_KERNEL)) {
-		mm = __scif_acquire_mm();
-		map_flags |= SCIF_MAP_ULIMIT;
-	}
-	/* Pin down the pages */
-	err = __scif_pin_pages(addr, len, &prot,
-			       map_flags & (SCIF_MAP_KERNEL | SCIF_MAP_ULIMIT),
-			       &pinned_pages);
-	if (err) {
-		scif_destroy_incomplete_window(ep, window);
-		__scif_release_mm(mm);
-		goto error;
-	}
-
-	window->pinned_pages = pinned_pages;
-	window->prot = pinned_pages->prot;
-	window->mm = mm;
-
-	/* Prepare the remote registration window */
-	err = scif_prep_remote_window(ep, window);
-	if (err) {
-		dev_err(&ep->remote_dev->sdev->dev,
-			"%s %d err %ld\n", __func__, __LINE__, err);
-		goto error_unmap;
-	}
-
-	/* Tell the peer about the new window */
-	err = scif_send_scif_register(ep, window);
-	if (err) {
-		dev_err(&ep->remote_dev->sdev->dev,
-			"%s %d err %ld\n", __func__, __LINE__, err);
-		goto error_unmap;
-	}
-
-	scif_put_peer_dev(spdev);
-	/* No further failures expected. Insert new window */
-	scif_insert_local_window(window, ep);
-	dev_dbg(&ep->remote_dev->sdev->dev,
-		"SCIFAPI register: ep %p addr %p len 0x%lx computed_offset 0x%llx\n",
-		epd, addr, len, computed_offset);
-	return computed_offset;
-error_unmap:
-	scif_destroy_window(ep, window);
-error:
-	scif_put_peer_dev(spdev);
-	dev_err(&ep->remote_dev->sdev->dev,
-		"%s %d err %ld\n", __func__, __LINE__, err);
-	return err;
-}
-EXPORT_SYMBOL_GPL(scif_register);
-
-int
-scif_unregister(scif_epd_t epd, off_t offset, size_t len)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)epd;
-	struct scif_window *window = NULL;
-	struct scif_rma_req req;
-	int nr_pages, err;
-	struct device *spdev;
-
-	dev_dbg(scif_info.mdev.this_device,
-		"SCIFAPI unregister: ep %p offset 0x%lx len 0x%lx\n",
-		ep, offset, len);
-	/* len must be page aligned. len should be non zero */
-	if (!len ||
-	    (ALIGN((u64)len, PAGE_SIZE) != (u64)len))
-		return -EINVAL;
-
-	/* Offset is not page aligned or offset+len wraps around */
-	if ((ALIGN(offset, PAGE_SIZE) != offset) ||
-	    (offset < 0) ||
-	    (len > LONG_MAX - offset))
-		return -EINVAL;
-
-	err = scif_verify_epd(ep);
-	if (err)
-		return err;
-
-	might_sleep();
-	nr_pages = len >> PAGE_SHIFT;
-
-	req.out_window = &window;
-	req.offset = offset;
-	req.prot = 0;
-	req.nr_bytes = len;
-	req.type = SCIF_WINDOW_FULL;
-	req.head = &ep->rma_info.reg_list;
-
-	spdev = scif_get_peer_dev(ep->remote_dev);
-	if (IS_ERR(spdev)) {
-		err = PTR_ERR(spdev);
-		return err;
-	}
-	mutex_lock(&ep->rma_info.rma_lock);
-	/* Does a valid window exist? */
-	err = scif_query_window(&req);
-	if (err) {
-		dev_err(&ep->remote_dev->sdev->dev,
-			"%s %d err %d\n", __func__, __LINE__, err);
-		goto error;
-	}
-	/* Unregister all the windows in this range */
-	err = scif_rma_list_unregister(window, offset, nr_pages);
-	if (err)
-		dev_err(&ep->remote_dev->sdev->dev,
-			"%s %d err %d\n", __func__, __LINE__, err);
-error:
-	mutex_unlock(&ep->rma_info.rma_lock);
-	scif_put_peer_dev(spdev);
-	return err;
-}
-EXPORT_SYMBOL_GPL(scif_unregister);
diff --git a/drivers/misc/mic/scif/scif_rma.h b/drivers/misc/mic/scif/scif_rma.h
deleted file mode 100644
index 964dd0fc3657..000000000000
--- a/drivers/misc/mic/scif/scif_rma.h
+++ /dev/null
@@ -1,477 +0,0 @@
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * This file is provided under a dual BSD/GPLv2 license.  When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * BSD LICENSE
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- *   notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- *   notice, this list of conditions and the following disclaimer in
- *   the documentation and/or other materials provided with the
- *   distribution.
- * * Neither the name of Intel Corporation nor the names of its
- *   contributors may be used to endorse or promote products derived
- *   from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * Intel SCIF driver.
- *
- */
-#ifndef SCIF_RMA_H
-#define SCIF_RMA_H
-
-#include <linux/intel-iommu.h>
-#include <linux/mmu_notifier.h>
-
-#include "../bus/scif_bus.h"
-
-/* If this bit is set then the mark is a remote fence mark */
-#define SCIF_REMOTE_FENCE_BIT          31
-/* Magic value used to indicate a remote fence request */
-#define SCIF_REMOTE_FENCE BIT_ULL(SCIF_REMOTE_FENCE_BIT)
-
-#define SCIF_MAX_UNALIGNED_BUF_SIZE (1024 * 1024ULL)
-#define SCIF_KMEM_UNALIGNED_BUF_SIZE (SCIF_MAX_UNALIGNED_BUF_SIZE + \
-				      (L1_CACHE_BYTES << 1))
-
-#define SCIF_IOVA_START_PFN		(1)
-#define SCIF_IOVA_PFN(addr) ((addr) >> PAGE_SHIFT)
-#define SCIF_DMA_64BIT_PFN SCIF_IOVA_PFN(DMA_BIT_MASK(64))
-#define SCIF_DMA_63BIT_PFN SCIF_IOVA_PFN(DMA_BIT_MASK(63))
-
-/*
- * struct scif_endpt_rma_info - Per Endpoint Remote Memory Access Information
- *
- * @reg_list: List of registration windows for self
- * @remote_reg_list: List of registration windows for peer
- * @iovad: Offset generator
- * @rma_lock: Synchronizes access to self/remote list and also protects the
- *	      window from being destroyed while RMAs are in progress.
- * @tc_lock: Synchronizes access to temporary cached windows list
- *	     for SCIF Registration Caching.
- * @mmn_lock: Synchronizes access to the list of MMU notifiers registered
- * @tw_refcount: Keeps track of number of outstanding temporary registered
- *		 windows created by scif_vreadfrom/scif_vwriteto which have
- *		 not been destroyed.
- * @tcw_refcount: Same as tw_refcount but for temporary cached windows
- * @tcw_total_pages: Same as tcw_refcount but in terms of pages pinned
- * @mmn_list: MMU notifier so that we can destroy the windows when required
- * @fence_refcount: Keeps track of number of outstanding remote fence
- *		    requests which have been received by the peer.
- * @dma_chan: DMA channel used for all DMA transfers for this endpoint.
- * @async_list_del: Detect asynchronous list entry deletion
- * @vma_list: List of vmas with remote memory mappings
- * @markwq: Wait queue used for scif_fence_mark/scif_fence_wait
-*/
-struct scif_endpt_rma_info {
-	struct list_head reg_list;
-	struct list_head remote_reg_list;
-	struct iova_domain iovad;
-	struct mutex rma_lock;
-	spinlock_t tc_lock;
-	struct mutex mmn_lock;
-	atomic_t tw_refcount;
-	atomic_t tcw_refcount;
-	atomic_t tcw_total_pages;
-	struct list_head mmn_list;
-	atomic_t fence_refcount;
-	struct dma_chan	*dma_chan;
-	int async_list_del;
-	struct list_head vma_list;
-	wait_queue_head_t markwq;
-};
-
-/*
- * struct scif_fence_info - used for tracking fence requests
- *
- * @state: State of this transfer
- * @wq: Fences wait on this queue
- * @dma_mark: Used for storing the DMA mark
- */
-struct scif_fence_info {
-	enum scif_msg_state state;
-	struct completion comp;
-	int dma_mark;
-};
-
-/*
- * struct scif_remote_fence_info - used for tracking remote fence requests
- *
- * @msg: List of SCIF node QP fence messages
- * @list: Link to list of remote fence requests
- */
-struct scif_remote_fence_info {
-	struct scifmsg msg;
-	struct list_head list;
-};
-
-/*
- * Specifies whether an RMA operation can span across partial windows, a single
- * window or multiple contiguous windows. Mmaps can span across partial windows.
- * Unregistration can span across complete windows. scif_get_pages() can span a
- * single window. A window can also be of type self or peer.
- */
-enum scif_window_type {
-	SCIF_WINDOW_PARTIAL,
-	SCIF_WINDOW_SINGLE,
-	SCIF_WINDOW_FULL,
-	SCIF_WINDOW_SELF,
-	SCIF_WINDOW_PEER
-};
-
-/* The number of physical addresses that can be stored in a PAGE. */
-#define SCIF_NR_ADDR_IN_PAGE   (0x1000 >> 3)
-
-/*
- * struct scif_rma_lookup - RMA lookup data structure for page list transfers
- *
- * Store an array of lookup offsets. Each offset in this array maps
- * one 4K page containing 512 physical addresses i.e. 2MB. 512 such
- * offsets in a 4K page will correspond to 1GB of registered address space.
-
- * @lookup: Array of offsets
- * @offset: DMA offset of lookup array
- */
-struct scif_rma_lookup {
-	dma_addr_t *lookup;
-	dma_addr_t offset;
-};
-
-/*
- * struct scif_pinned_pages - A set of pinned pages obtained with
- * scif_pin_pages() which could be part of multiple registered
- * windows across different end points.
- *
- * @nr_pages: Number of pages which is defined as a s64 instead of an int
- * to avoid sign extension with buffers >= 2GB
- * @prot: read/write protections
- * @map_flags: Flags specified during the pin operation
- * @ref_count: Reference count bumped in terms of number of pages
- * @magic: A magic value
- * @pages: Array of pointers to struct pages populated with get_user_pages(..)
- */
-struct scif_pinned_pages {
-	s64 nr_pages;
-	int prot;
-	int map_flags;
-	atomic_t ref_count;
-	u64 magic;
-	struct page **pages;
-};
-
-/*
- * struct scif_status - Stores DMA status update information
- *
- * @src_dma_addr: Source buffer DMA address
- * @val: src location for value to be written to the destination
- * @ep: SCIF endpoint
- */
-struct scif_status {
-	dma_addr_t src_dma_addr;
-	u64 val;
-	struct scif_endpt *ep;
-};
-
-/*
- * struct scif_cb_arg - Stores the argument of the callback func
- *
- * @src_dma_addr: Source buffer DMA address
- * @status: DMA status
- * @ep: SCIF endpoint
- */
-struct scif_cb_arg {
-	dma_addr_t src_dma_addr;
-	struct scif_status *status;
-	struct scif_endpt *ep;
-};
-
-/*
- * struct scif_window - Registration Window for Self and Remote
- *
- * @nr_pages: Number of pages which is defined as a s64 instead of an int
- * to avoid sign extension with buffers >= 2GB
- * @nr_contig_chunks: Number of contiguous physical chunks
- * @prot: read/write protections
- * @ref_count: reference count in terms of number of pages
- * @magic: Cookie to detect corruption
- * @offset: registered offset
- * @va_for_temp: va address that this window represents
- * @dma_mark: Used to determine if all DMAs against the window are done
- * @ep: Pointer to EP. Useful for passing EP around with messages to
-	avoid expensive list traversals.
- * @list: link to list of windows for the endpoint
- * @type: self or peer window
- * @peer_window: Pointer to peer window. Useful for sending messages to peer
- *		 without requiring an extra list traversal
- * @unreg_state: unregistration state
- * @offset_freed: True if the offset has been freed
- * @temp: True for temporary windows created via scif_vreadfrom/scif_vwriteto
- * @mm: memory descriptor for the task_struct which initiated the RMA
- * @st: scatter gather table for DMA mappings with IOMMU enabled
- * @pinned_pages: The set of pinned_pages backing this window
- * @alloc_handle: Handle for sending ALLOC_REQ
- * @regwq: Wait Queue for an registration (N)ACK
- * @reg_state: Registration state
- * @unregwq: Wait Queue for an unregistration (N)ACK
- * @dma_addr_lookup: Lookup for physical addresses used for DMA
- * @nr_lookup: Number of entries in lookup
- * @mapped_offset: Offset used to map the window by the peer
- * @dma_addr: Array of physical addresses used for Mgmt node & MIC initiated DMA
- * @num_pages: Array specifying number of pages for each physical address
- */
-struct scif_window {
-	s64 nr_pages;
-	int nr_contig_chunks;
-	int prot;
-	int ref_count;
-	u64 magic;
-	s64 offset;
-	unsigned long va_for_temp;
-	int dma_mark;
-	u64 ep;
-	struct list_head list;
-	enum scif_window_type type;
-	u64 peer_window;
-	enum scif_msg_state unreg_state;
-	bool offset_freed;
-	bool temp;
-	struct mm_struct *mm;
-	struct sg_table *st;
-	union {
-		struct {
-			struct scif_pinned_pages *pinned_pages;
-			struct scif_allocmsg alloc_handle;
-			wait_queue_head_t regwq;
-			enum scif_msg_state reg_state;
-			wait_queue_head_t unregwq;
-		};
-		struct {
-			struct scif_rma_lookup dma_addr_lookup;
-			struct scif_rma_lookup num_pages_lookup;
-			int nr_lookup;
-			dma_addr_t mapped_offset;
-		};
-	};
-	dma_addr_t *dma_addr;
-	u64 *num_pages;
-} __packed;
-
-/*
- * scif_mmu_notif - SCIF mmu notifier information
- *
- * @mmu_notifier ep_mmu_notifier: MMU notifier operations
- * @tc_reg_list: List of temp registration windows for self
- * @mm: memory descriptor for the task_struct which initiated the RMA
- * @ep: SCIF endpoint
- * @list: link to list of MMU notifier information
- */
-struct scif_mmu_notif {
-#ifdef CONFIG_MMU_NOTIFIER
-	struct mmu_notifier ep_mmu_notifier;
-#endif
-	struct list_head tc_reg_list;
-	struct mm_struct *mm;
-	struct scif_endpt *ep;
-	struct list_head list;
-};
-
-enum scif_rma_dir {
-	SCIF_LOCAL_TO_REMOTE,
-	SCIF_REMOTE_TO_LOCAL
-};
-
-extern struct kmem_cache *unaligned_cache;
-/* Initialize RMA for this EP */
-void scif_rma_ep_init(struct scif_endpt *ep);
-/* Check if epd can be uninitialized */
-int scif_rma_ep_can_uninit(struct scif_endpt *ep);
-/* Obtain a new offset. Callee must grab RMA lock */
-int scif_get_window_offset(struct scif_endpt *ep, int flags,
-			   s64 offset, int nr_pages, s64 *out_offset);
-/* Free offset. Callee must grab RMA lock */
-void scif_free_window_offset(struct scif_endpt *ep,
-			     struct scif_window *window, s64 offset);
-/* Create self registration window */
-struct scif_window *scif_create_window(struct scif_endpt *ep, int nr_pages,
-				       s64 offset, bool temp);
-/* Destroy self registration window.*/
-int scif_destroy_window(struct scif_endpt *ep, struct scif_window *window);
-void scif_unmap_window(struct scif_dev *remote_dev, struct scif_window *window);
-/* Map pages of self window to Aperture/PCI */
-int scif_map_window(struct scif_dev *remote_dev,
-		    struct scif_window *window);
-/* Unregister a self window */
-int scif_unregister_window(struct scif_window *window);
-/* Destroy remote registration window */
-void
-scif_destroy_remote_window(struct scif_window *window);
-/* remove valid remote memory mappings from process address space */
-void scif_zap_mmaps(int node);
-/* Query if any applications have remote memory mappings */
-bool scif_rma_do_apps_have_mmaps(int node);
-/* Cleanup remote registration lists for zombie endpoints */
-void scif_cleanup_rma_for_zombies(int node);
-/* Reserve a DMA channel for a particular endpoint */
-int scif_reserve_dma_chan(struct scif_endpt *ep);
-/* Setup a DMA mark for an endpoint */
-int _scif_fence_mark(scif_epd_t epd, int *mark);
-int scif_prog_signal(scif_epd_t epd, off_t offset, u64 val,
-		     enum scif_window_type type);
-void scif_alloc_req(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_alloc_gnt_rej(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_free_virt(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_reg(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_unreg(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_reg_ack(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_reg_nack(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_unreg_ack(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_unreg_nack(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_munmap(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_mark(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_mark_resp(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_wait(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_wait_resp(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_sig_local(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_sig_remote(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_sig_resp(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_mmu_notif_handler(struct work_struct *work);
-void scif_rma_handle_remote_fences(void);
-void scif_rma_destroy_windows(void);
-void scif_rma_destroy_tcw_invalid(void);
-int scif_drain_dma_intr(struct scif_hw_dev *sdev, struct dma_chan *chan);
-
-struct scif_window_iter {
-	s64 offset;
-	int index;
-};
-
-static inline void
-scif_init_window_iter(struct scif_window *window, struct scif_window_iter *iter)
-{
-	iter->offset = window->offset;
-	iter->index = 0;
-}
-
-dma_addr_t scif_off_to_dma_addr(struct scif_window *window, s64 off,
-				size_t *nr_bytes,
-				struct scif_window_iter *iter);
-static inline
-dma_addr_t __scif_off_to_dma_addr(struct scif_window *window, s64 off)
-{
-	return scif_off_to_dma_addr(window, off, NULL, NULL);
-}
-
-static inline bool scif_unaligned(off_t src_offset, off_t dst_offset)
-{
-	src_offset = src_offset & (L1_CACHE_BYTES - 1);
-	dst_offset = dst_offset & (L1_CACHE_BYTES - 1);
-	return !(src_offset == dst_offset);
-}
-
-/*
- * scif_zalloc:
- * @size: Size of the allocation request.
- *
- * Helper API which attempts to allocate zeroed pages via
- * __get_free_pages(..) first and then falls back on
- * vzalloc(..) if that fails.
- */
-static inline void *scif_zalloc(size_t size)
-{
-	void *ret = NULL;
-	size_t align = ALIGN(size, PAGE_SIZE);
-
-	if (align && get_order(align) < MAX_ORDER)
-		ret = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
-					       get_order(align));
-	return ret ? ret : vzalloc(align);
-}
-
-/*
- * scif_free:
- * @addr: Address to be freed.
- * @size: Size of the allocation.
- * Helper API which frees memory allocated via scif_zalloc().
- */
-static inline void scif_free(void *addr, size_t size)
-{
-	size_t align = ALIGN(size, PAGE_SIZE);
-
-	if (is_vmalloc_addr(addr))
-		vfree(addr);
-	else
-		free_pages((unsigned long)addr, get_order(align));
-}
-
-static inline void scif_get_window(struct scif_window *window, int nr_pages)
-{
-	window->ref_count += nr_pages;
-}
-
-static inline void scif_put_window(struct scif_window *window, int nr_pages)
-{
-	window->ref_count -= nr_pages;
-}
-
-static inline void scif_set_window_ref(struct scif_window *window, int nr_pages)
-{
-	window->ref_count = nr_pages;
-}
-
-static inline void
-scif_queue_for_cleanup(struct scif_window *window, struct list_head *list)
-{
-	spin_lock(&scif_info.rmalock);
-	list_add_tail(&window->list, list);
-	spin_unlock(&scif_info.rmalock);
-	schedule_work(&scif_info.misc_work);
-}
-
-static inline void __scif_rma_destroy_tcw_helper(struct scif_window *window)
-{
-	list_del_init(&window->list);
-	scif_queue_for_cleanup(window, &scif_info.rma_tc);
-}
-
-static inline bool scif_is_iommu_enabled(void)
-{
-#ifdef CONFIG_INTEL_IOMMU
-	return intel_iommu_enabled;
-#else
-	return false;
-#endif
-}
-#endif /* SCIF_RMA_H */
diff --git a/drivers/misc/mic/scif/scif_rma_list.c b/drivers/misc/mic/scif/scif_rma_list.c
deleted file mode 100644
index ef923ba134c8..000000000000
--- a/drivers/misc/mic/scif/scif_rma_list.c
+++ /dev/null
@@ -1,282 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include "scif_main.h"
-#include <linux/mmu_notifier.h>
-#include <linux/highmem.h>
-
-/*
- * scif_insert_tcw:
- *
- * Insert a temp window to the temp registration list sorted by va_for_temp.
- * RMA lock must be held.
- */
-void scif_insert_tcw(struct scif_window *window, struct list_head *head)
-{
-	struct scif_window *curr = NULL;
-	struct scif_window *prev = list_entry(head, struct scif_window, list);
-	struct list_head *item;
-
-	INIT_LIST_HEAD(&window->list);
-	/* Compare with tail and if the entry is new tail add it to the end */
-	if (!list_empty(head)) {
-		curr = list_entry(head->prev, struct scif_window, list);
-		if (curr->va_for_temp < window->va_for_temp) {
-			list_add_tail(&window->list, head);
-			return;
-		}
-	}
-	list_for_each(item, head) {
-		curr = list_entry(item, struct scif_window, list);
-		if (curr->va_for_temp > window->va_for_temp)
-			break;
-		prev = curr;
-	}
-	list_add(&window->list, &prev->list);
-}
-
-/*
- * scif_insert_window:
- *
- * Insert a window to the self registration list sorted by offset.
- * RMA lock must be held.
- */
-void scif_insert_window(struct scif_window *window, struct list_head *head)
-{
-	struct scif_window *curr = NULL, *prev = NULL;
-	struct list_head *item;
-
-	INIT_LIST_HEAD(&window->list);
-	list_for_each(item, head) {
-		curr = list_entry(item, struct scif_window, list);
-		if (curr->offset > window->offset)
-			break;
-		prev = curr;
-	}
-	if (!prev)
-		list_add(&window->list, head);
-	else
-		list_add(&window->list, &prev->list);
-	scif_set_window_ref(window, window->nr_pages);
-}
-
-/*
- * scif_query_tcw:
- *
- * Query the temp cached registration list of ep for an overlapping window
- * in case of permission mismatch, destroy the previous window. if permissions
- * match and overlap is partial, destroy the window but return the new range
- * RMA lock must be held.
- */
-int scif_query_tcw(struct scif_endpt *ep, struct scif_rma_req *req)
-{
-	struct list_head *item, *temp, *head = req->head;
-	struct scif_window *window;
-	u64 start_va_window, start_va_req = req->va_for_temp;
-	u64 end_va_window, end_va_req = start_va_req + req->nr_bytes;
-
-	if (!req->nr_bytes)
-		return -EINVAL;
-	/*
-	 * Avoid traversing the entire list to find out that there
-	 * is no entry that matches
-	 */
-	if (!list_empty(head)) {
-		window = list_last_entry(head, struct scif_window, list);
-		end_va_window = window->va_for_temp +
-			(window->nr_pages << PAGE_SHIFT);
-		if (start_va_req > end_va_window)
-			return -ENXIO;
-	}
-	list_for_each_safe(item, temp, head) {
-		window = list_entry(item, struct scif_window, list);
-		start_va_window = window->va_for_temp;
-		end_va_window = window->va_for_temp +
-			(window->nr_pages << PAGE_SHIFT);
-		if (start_va_req < start_va_window &&
-		    end_va_req < start_va_window)
-			break;
-		if (start_va_req >= end_va_window)
-			continue;
-		if ((window->prot & req->prot) == req->prot) {
-			if (start_va_req >= start_va_window &&
-			    end_va_req <= end_va_window) {
-				*req->out_window = window;
-				return 0;
-			}
-			/* expand window */
-			if (start_va_req < start_va_window) {
-				req->nr_bytes +=
-					start_va_window - start_va_req;
-				req->va_for_temp = start_va_window;
-			}
-			if (end_va_req >= end_va_window)
-				req->nr_bytes += end_va_window - end_va_req;
-		}
-		/* Destroy the old window to create a new one */
-		__scif_rma_destroy_tcw_helper(window);
-		break;
-	}
-	return -ENXIO;
-}
-
-/*
- * scif_query_window:
- *
- * Query the registration list and check if a valid contiguous
- * range of windows exist.
- * RMA lock must be held.
- */
-int scif_query_window(struct scif_rma_req *req)
-{
-	struct list_head *item;
-	struct scif_window *window;
-	s64 end_offset, offset = req->offset;
-	u64 tmp_min, nr_bytes_left = req->nr_bytes;
-
-	if (!req->nr_bytes)
-		return -EINVAL;
-
-	list_for_each(item, req->head) {
-		window = list_entry(item, struct scif_window, list);
-		end_offset = window->offset +
-			(window->nr_pages << PAGE_SHIFT);
-		if (offset < window->offset)
-			/* Offset not found! */
-			return -ENXIO;
-		if (offset >= end_offset)
-			continue;
-		/* Check read/write protections. */
-		if ((window->prot & req->prot) != req->prot)
-			return -EPERM;
-		if (nr_bytes_left == req->nr_bytes)
-			/* Store the first window */
-			*req->out_window = window;
-		tmp_min = min((u64)end_offset - offset, nr_bytes_left);
-		nr_bytes_left -= tmp_min;
-		offset += tmp_min;
-		/*
-		 * Range requested encompasses
-		 * multiple windows contiguously.
-		 */
-		if (!nr_bytes_left) {
-			/* Done for partial window */
-			if (req->type == SCIF_WINDOW_PARTIAL ||
-			    req->type == SCIF_WINDOW_SINGLE)
-				return 0;
-			/* Extra logic for full windows */
-			if (offset == end_offset)
-				/* Spanning multiple whole windows */
-				return 0;
-				/* Not spanning multiple whole windows */
-			return -ENXIO;
-		}
-		if (req->type == SCIF_WINDOW_SINGLE)
-			break;
-	}
-	dev_err(scif_info.mdev.this_device,
-		"%s %d ENXIO\n", __func__, __LINE__);
-	return -ENXIO;
-}
-
-/*
- * scif_rma_list_unregister:
- *
- * Traverse the self registration list starting from window:
- * 1) Call scif_unregister_window(..)
- * RMA lock must be held.
- */
-int scif_rma_list_unregister(struct scif_window *window,
-			     s64 offset, int nr_pages)
-{
-	struct scif_endpt *ep = (struct scif_endpt *)window->ep;
-	struct list_head *head = &ep->rma_info.reg_list;
-	s64 end_offset;
-	int err = 0;
-	int loop_nr_pages;
-	struct scif_window *_window;
-
-	list_for_each_entry_safe_from(window, _window, head, list) {
-		end_offset = window->offset + (window->nr_pages << PAGE_SHIFT);
-		loop_nr_pages = min((int)((end_offset - offset) >> PAGE_SHIFT),
-				    nr_pages);
-		err = scif_unregister_window(window);
-		if (err)
-			return err;
-		nr_pages -= loop_nr_pages;
-		offset += (loop_nr_pages << PAGE_SHIFT);
-		if (!nr_pages)
-			break;
-	}
-	return 0;
-}
-
-/*
- * scif_unmap_all_window:
- *
- * Traverse all the windows in the self registration list and:
- * 1) Delete any DMA mappings created
- */
-void scif_unmap_all_windows(scif_epd_t epd)
-{
-	struct list_head *item, *tmp;
-	struct scif_window *window;
-	struct scif_endpt *ep = (struct scif_endpt *)epd;
-	struct list_head *head = &ep->rma_info.reg_list;
-
-	mutex_lock(&ep->rma_info.rma_lock);
-	list_for_each_safe(item, tmp, head) {
-		window = list_entry(item, struct scif_window, list);
-		scif_unmap_window(ep->remote_dev, window);
-	}
-	mutex_unlock(&ep->rma_info.rma_lock);
-}
-
-/*
- * scif_unregister_all_window:
- *
- * Traverse all the windows in the self registration list and:
- * 1) Call scif_unregister_window(..)
- * RMA lock must be held.
- */
-int scif_unregister_all_windows(scif_epd_t epd)
-{
-	struct list_head *item, *tmp;
-	struct scif_window *window;
-	struct scif_endpt *ep = (struct scif_endpt *)epd;
-	struct list_head *head = &ep->rma_info.reg_list;
-	int err = 0;
-
-	mutex_lock(&ep->rma_info.rma_lock);
-retry:
-	item = NULL;
-	tmp = NULL;
-	list_for_each_safe(item, tmp, head) {
-		window = list_entry(item, struct scif_window, list);
-		ep->rma_info.async_list_del = 0;
-		err = scif_unregister_window(window);
-		if (err)
-			dev_err(scif_info.mdev.this_device,
-				"%s %d err %d\n",
-				__func__, __LINE__, err);
-		/*
-		 * Need to restart list traversal if there has been
-		 * an asynchronous list entry deletion.
-		 */
-		if (READ_ONCE(ep->rma_info.async_list_del))
-			goto retry;
-	}
-	mutex_unlock(&ep->rma_info.rma_lock);
-	if (!list_empty(&ep->rma_info.mmn_list)) {
-		spin_lock(&scif_info.rmalock);
-		list_add_tail(&ep->mmu_list, &scif_info.mmu_notif_cleanup);
-		spin_unlock(&scif_info.rmalock);
-		schedule_work(&scif_info.mmu_notif_work);
-	}
-	return err;
-}
diff --git a/drivers/misc/mic/scif/scif_rma_list.h b/drivers/misc/mic/scif/scif_rma_list.h
deleted file mode 100644
index 0f8e0ed65614..000000000000
--- a/drivers/misc/mic/scif/scif_rma_list.h
+++ /dev/null
@@ -1,48 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#ifndef SCIF_RMA_LIST_H
-#define SCIF_RMA_LIST_H
-
-/*
- * struct scif_rma_req - Self Registration list RMA Request query
- *
- * @out_window - Returns the window if found
- * @offset: Starting offset
- * @nr_bytes: number of bytes
- * @prot: protection requested i.e. read or write or both
- * @type: Specify single, partial or multiple windows
- * @head: Head of list on which to search
- * @va_for_temp: VA for searching temporary cached windows
- */
-struct scif_rma_req {
-	struct scif_window **out_window;
-	union {
-		s64 offset;
-		unsigned long va_for_temp;
-	};
-	size_t nr_bytes;
-	int prot;
-	enum scif_window_type type;
-	struct list_head *head;
-};
-
-/* Insert */
-void scif_insert_window(struct scif_window *window, struct list_head *head);
-void scif_insert_tcw(struct scif_window *window,
-		     struct list_head *head);
-/* Query */
-int scif_query_window(struct scif_rma_req *request);
-int scif_query_tcw(struct scif_endpt *ep, struct scif_rma_req *request);
-/* Called from close to unregister all self windows */
-int scif_unregister_all_windows(scif_epd_t epd);
-void scif_unmap_all_windows(scif_epd_t epd);
-/* Traverse list and unregister */
-int scif_rma_list_unregister(struct scif_window *window, s64 offset,
-			     int nr_pages);
-#endif /* SCIF_RMA_LIST_H */
diff --git a/drivers/misc/mic/vop/Makefile b/drivers/misc/mic/vop/Makefile
deleted file mode 100644
index 51b9b0022786..000000000000
--- a/drivers/misc/mic/vop/Makefile
+++ /dev/null
@@ -1,10 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-#
-# Makefile - Intel MIC Linux driver.
-# Copyright(c) 2016, Intel Corporation.
-#
-obj-$(CONFIG_VOP) := vop.o
-
-vop-objs += vop_main.o
-vop-objs += vop_debugfs.o
-vop-objs += vop_vringh.o
diff --git a/drivers/misc/mic/vop/vop_debugfs.c b/drivers/misc/mic/vop/vop_debugfs.c
deleted file mode 100644
index 9d4f175f4dd1..000000000000
--- a/drivers/misc/mic/vop/vop_debugfs.c
+++ /dev/null
@@ -1,184 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Intel Virtio Over PCIe (VOP) driver.
- */
-#include <linux/debugfs.h>
-#include <linux/seq_file.h>
-
-#include "vop_main.h"
-
-static int vop_dp_show(struct seq_file *s, void *pos)
-{
-	struct mic_device_desc *d;
-	struct mic_device_ctrl *dc;
-	struct mic_vqconfig *vqconfig;
-	__u32 *features;
-	__u8 *config;
-	struct vop_info *vi = s->private;
-	struct vop_device *vpdev = vi->vpdev;
-	struct mic_bootparam *bootparam = vpdev->hw_ops->get_dp(vpdev);
-	int j, k;
-
-	seq_printf(s, "Bootparam: magic 0x%x\n",
-		   bootparam->magic);
-	seq_printf(s, "Bootparam: h2c_config_db %d\n",
-		   bootparam->h2c_config_db);
-	seq_printf(s, "Bootparam: node_id %d\n",
-		   bootparam->node_id);
-	seq_printf(s, "Bootparam: c2h_scif_db %d\n",
-		   bootparam->c2h_scif_db);
-	seq_printf(s, "Bootparam: h2c_scif_db %d\n",
-		   bootparam->h2c_scif_db);
-	seq_printf(s, "Bootparam: scif_host_dma_addr 0x%llx\n",
-		   bootparam->scif_host_dma_addr);
-	seq_printf(s, "Bootparam: scif_card_dma_addr 0x%llx\n",
-		   bootparam->scif_card_dma_addr);
-
-	for (j = sizeof(*bootparam);
-		j < MIC_DP_SIZE; j += mic_total_desc_size(d)) {
-		d = (void *)bootparam + j;
-		dc = (void *)d + mic_aligned_desc_size(d);
-
-		/* end of list */
-		if (d->type == 0)
-			break;
-
-		if (d->type == -1)
-			continue;
-
-		seq_printf(s, "Type %d ", d->type);
-		seq_printf(s, "Num VQ %d ", d->num_vq);
-		seq_printf(s, "Feature Len %d\n", d->feature_len);
-		seq_printf(s, "Config Len %d ", d->config_len);
-		seq_printf(s, "Shutdown Status %d\n", d->status);
-
-		for (k = 0; k < d->num_vq; k++) {
-			vqconfig = mic_vq_config(d) + k;
-			seq_printf(s, "vqconfig[%d]: ", k);
-			seq_printf(s, "address 0x%llx ",
-				   vqconfig->address);
-			seq_printf(s, "num %d ", vqconfig->num);
-			seq_printf(s, "used address 0x%llx\n",
-				   vqconfig->used_address);
-		}
-
-		features = (__u32 *)mic_vq_features(d);
-		seq_printf(s, "Features: Host 0x%x ", features[0]);
-		seq_printf(s, "Guest 0x%x\n", features[1]);
-
-		config = mic_vq_configspace(d);
-		for (k = 0; k < d->config_len; k++)
-			seq_printf(s, "config[%d]=%d\n", k, config[k]);
-
-		seq_puts(s, "Device control:\n");
-		seq_printf(s, "Config Change %d ", dc->config_change);
-		seq_printf(s, "Vdev reset %d\n", dc->vdev_reset);
-		seq_printf(s, "Guest Ack %d ", dc->guest_ack);
-		seq_printf(s, "Host ack %d\n", dc->host_ack);
-		seq_printf(s, "Used address updated %d ",
-			   dc->used_address_updated);
-		seq_printf(s, "Vdev 0x%llx\n", dc->vdev);
-		seq_printf(s, "c2h doorbell %d ", dc->c2h_vdev_db);
-		seq_printf(s, "h2c doorbell %d\n", dc->h2c_vdev_db);
-	}
-	schedule_work(&vi->hotplug_work);
-	return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(vop_dp);
-
-static int vop_vdev_info_show(struct seq_file *s, void *unused)
-{
-	struct vop_info *vi = s->private;
-	struct list_head *pos, *tmp;
-	struct vop_vdev *vdev;
-	int i, j;
-
-	mutex_lock(&vi->vop_mutex);
-	list_for_each_safe(pos, tmp, &vi->vdev_list) {
-		vdev = list_entry(pos, struct vop_vdev, list);
-		seq_printf(s, "VDEV type %d state %s in %ld out %ld in_dma %ld out_dma %ld\n",
-			   vdev->virtio_id,
-			   vop_vdevup(vdev) ? "UP" : "DOWN",
-			   vdev->in_bytes,
-			   vdev->out_bytes,
-			   vdev->in_bytes_dma,
-			   vdev->out_bytes_dma);
-		for (i = 0; i < MIC_MAX_VRINGS; i++) {
-			struct vring_desc *desc;
-			struct vring_avail *avail;
-			struct vring_used *used;
-			struct vop_vringh *vvr = &vdev->vvr[i];
-			struct vringh *vrh = &vvr->vrh;
-			int num = vrh->vring.num;
-
-			if (!num)
-				continue;
-			desc = vrh->vring.desc;
-			seq_printf(s, "vring i %d avail_idx %d",
-				   i, vvr->vring.info->avail_idx & (num - 1));
-			seq_printf(s, " vring i %d avail_idx %d\n",
-				   i, vvr->vring.info->avail_idx);
-			seq_printf(s, "vrh i %d weak_barriers %d",
-				   i, vrh->weak_barriers);
-			seq_printf(s, " last_avail_idx %d last_used_idx %d",
-				   vrh->last_avail_idx, vrh->last_used_idx);
-			seq_printf(s, " completed %d\n", vrh->completed);
-			for (j = 0; j < num; j++) {
-				seq_printf(s, "desc[%d] addr 0x%llx len %d",
-					   j, desc->addr, desc->len);
-				seq_printf(s, " flags 0x%x next %d\n",
-					   desc->flags, desc->next);
-				desc++;
-			}
-			avail = vrh->vring.avail;
-			seq_printf(s, "avail flags 0x%x idx %d\n",
-				   vringh16_to_cpu(vrh, avail->flags),
-				   vringh16_to_cpu(vrh,
-						   avail->idx) & (num - 1));
-			seq_printf(s, "avail flags 0x%x idx %d\n",
-				   vringh16_to_cpu(vrh, avail->flags),
-				   vringh16_to_cpu(vrh, avail->idx));
-			for (j = 0; j < num; j++)
-				seq_printf(s, "avail ring[%d] %d\n",
-					   j, avail->ring[j]);
-			used = vrh->vring.used;
-			seq_printf(s, "used flags 0x%x idx %d\n",
-				   vringh16_to_cpu(vrh, used->flags),
-				   vringh16_to_cpu(vrh, used->idx) & (num - 1));
-			seq_printf(s, "used flags 0x%x idx %d\n",
-				   vringh16_to_cpu(vrh, used->flags),
-				   vringh16_to_cpu(vrh, used->idx));
-			for (j = 0; j < num; j++)
-				seq_printf(s, "used ring[%d] id %d len %d\n",
-					   j, vringh32_to_cpu(vrh,
-							      used->ring[j].id),
-					   vringh32_to_cpu(vrh,
-							   used->ring[j].len));
-		}
-	}
-	mutex_unlock(&vi->vop_mutex);
-
-	return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(vop_vdev_info);
-
-void vop_init_debugfs(struct vop_info *vi)
-{
-	char name[16];
-
-	snprintf(name, sizeof(name), "%s%d", KBUILD_MODNAME, vi->vpdev->dnode);
-	vi->dbg = debugfs_create_dir(name, NULL);
-	debugfs_create_file("dp", 0444, vi->dbg, vi, &vop_dp_fops);
-	debugfs_create_file("vdev_info", 0444, vi->dbg, vi, &vop_vdev_info_fops);
-}
-
-void vop_exit_debugfs(struct vop_info *vi)
-{
-	debugfs_remove_recursive(vi->dbg);
-}
diff --git a/drivers/misc/mic/vop/vop_main.c b/drivers/misc/mic/vop/vop_main.c
deleted file mode 100644
index 714b94f42d38..000000000000
--- a/drivers/misc/mic/vop/vop_main.c
+++ /dev/null
@@ -1,784 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Adapted from:
- *
- * virtio for kvm on s390
- *
- * Copyright IBM Corp. 2008
- *
- *    Author(s): Christian Borntraeger <borntraeger@de.ibm.com>
- *
- * Intel Virtio Over PCIe (VOP) driver.
- */
-#include <linux/delay.h>
-#include <linux/module.h>
-#include <linux/sched.h>
-#include <linux/dma-mapping.h>
-#include <linux/io-64-nonatomic-lo-hi.h>
-
-#include "vop_main.h"
-
-#define VOP_MAX_VRINGS 4
-
-/*
- * _vop_vdev - Allocated per virtio device instance injected by the peer.
- *
- * @vdev: Virtio device
- * @desc: Virtio device page descriptor
- * @dc: Virtio device control
- * @vpdev: VOP device which is the parent for this virtio device
- * @vr: Buffer for accessing the VRING
- * @used_virt: Virtual address of used ring
- * @used: DMA address of used ring
- * @used_size: Size of the used buffer
- * @reset_done: Track whether VOP reset is complete
- * @virtio_cookie: Cookie returned upon requesting a interrupt
- * @c2h_vdev_db: The doorbell used by the guest to interrupt the host
- * @h2c_vdev_db: The doorbell used by the host to interrupt the guest
- * @dnode: The destination node
- */
-struct _vop_vdev {
-	struct virtio_device vdev;
-	struct mic_device_desc __iomem *desc;
-	struct mic_device_ctrl __iomem *dc;
-	struct vop_device *vpdev;
-	void __iomem *vr[VOP_MAX_VRINGS];
-	void *used_virt[VOP_MAX_VRINGS];
-	dma_addr_t used[VOP_MAX_VRINGS];
-	int used_size[VOP_MAX_VRINGS];
-	struct completion reset_done;
-	struct mic_irq *virtio_cookie;
-	int c2h_vdev_db;
-	int h2c_vdev_db;
-	int dnode;
-};
-
-#define to_vopvdev(vd) container_of(vd, struct _vop_vdev, vdev)
-
-#define _vop_aligned_desc_size(d) __mic_align(_vop_desc_size(d), 8)
-
-/* Helper API to obtain the parent of the virtio device */
-static inline struct device *_vop_dev(struct _vop_vdev *vdev)
-{
-	return vdev->vdev.dev.parent;
-}
-
-static inline unsigned _vop_desc_size(struct mic_device_desc __iomem *desc)
-{
-	return sizeof(*desc)
-		+ ioread8(&desc->num_vq) * sizeof(struct mic_vqconfig)
-		+ ioread8(&desc->feature_len) * 2
-		+ ioread8(&desc->config_len);
-}
-
-static inline struct mic_vqconfig __iomem *
-_vop_vq_config(struct mic_device_desc __iomem *desc)
-{
-	return (struct mic_vqconfig __iomem *)(desc + 1);
-}
-
-static inline u8 __iomem *
-_vop_vq_features(struct mic_device_desc __iomem *desc)
-{
-	return (u8 __iomem *)(_vop_vq_config(desc) + ioread8(&desc->num_vq));
-}
-
-static inline u8 __iomem *
-_vop_vq_configspace(struct mic_device_desc __iomem *desc)
-{
-	return _vop_vq_features(desc) + ioread8(&desc->feature_len) * 2;
-}
-
-static inline unsigned
-_vop_total_desc_size(struct mic_device_desc __iomem *desc)
-{
-	return _vop_aligned_desc_size(desc) + sizeof(struct mic_device_ctrl);
-}
-
-/* This gets the device's feature bits. */
-static u64 vop_get_features(struct virtio_device *vdev)
-{
-	unsigned int i, bits;
-	u64 features = 0;
-	struct mic_device_desc __iomem *desc = to_vopvdev(vdev)->desc;
-	u8 __iomem *in_features = _vop_vq_features(desc);
-	int feature_len = ioread8(&desc->feature_len);
-
-	bits = min_t(unsigned, feature_len, sizeof(vdev->features)) * 8;
-	for (i = 0; i < bits; i++)
-		if (ioread8(&in_features[i / 8]) & (BIT(i % 8)))
-			features |= BIT_ULL(i);
-
-	return features;
-}
-
-static void vop_transport_features(struct virtio_device *vdev)
-{
-	/*
-	 * Packed ring isn't enabled on virtio_vop for now,
-	 * because virtio_vop uses vring_new_virtqueue() which
-	 * creates virtio rings on preallocated memory.
-	 */
-	__virtio_clear_bit(vdev, VIRTIO_F_RING_PACKED);
-	__virtio_set_bit(vdev, VIRTIO_F_ACCESS_PLATFORM);
-}
-
-static int vop_finalize_features(struct virtio_device *vdev)
-{
-	unsigned int i, bits;
-	struct mic_device_desc __iomem *desc = to_vopvdev(vdev)->desc;
-	u8 feature_len = ioread8(&desc->feature_len);
-	/* Second half of bitmap is features we accept. */
-	u8 __iomem *out_features =
-		_vop_vq_features(desc) + feature_len;
-
-	/* Give virtio_ring a chance to accept features. */
-	vring_transport_features(vdev);
-
-	/* Give virtio_vop a chance to accept features. */
-	vop_transport_features(vdev);
-
-	memset_io(out_features, 0, feature_len);
-	bits = min_t(unsigned, feature_len,
-		     sizeof(vdev->features)) * 8;
-	for (i = 0; i < bits; i++) {
-		if (__virtio_test_bit(vdev, i))
-			iowrite8(ioread8(&out_features[i / 8]) | (1 << (i % 8)),
-				 &out_features[i / 8]);
-	}
-	return 0;
-}
-
-/*
- * Reading and writing elements in config space
- */
-static void vop_get(struct virtio_device *vdev, unsigned int offset,
-		    void *buf, unsigned len)
-{
-	struct mic_device_desc __iomem *desc = to_vopvdev(vdev)->desc;
-
-	if (offset + len > ioread8(&desc->config_len))
-		return;
-	memcpy_fromio(buf, _vop_vq_configspace(desc) + offset, len);
-}
-
-static void vop_set(struct virtio_device *vdev, unsigned int offset,
-		    const void *buf, unsigned len)
-{
-	struct mic_device_desc __iomem *desc = to_vopvdev(vdev)->desc;
-
-	if (offset + len > ioread8(&desc->config_len))
-		return;
-	memcpy_toio(_vop_vq_configspace(desc) + offset, buf, len);
-}
-
-/*
- * The operations to get and set the status word just access the status
- * field of the device descriptor. set_status also interrupts the host
- * to tell about status changes.
- */
-static u8 vop_get_status(struct virtio_device *vdev)
-{
-	return ioread8(&to_vopvdev(vdev)->desc->status);
-}
-
-static void vop_set_status(struct virtio_device *dev, u8 status)
-{
-	struct _vop_vdev *vdev = to_vopvdev(dev);
-	struct vop_device *vpdev = vdev->vpdev;
-
-	if (!status)
-		return;
-	iowrite8(status, &vdev->desc->status);
-	vpdev->hw_ops->send_intr(vpdev, vdev->c2h_vdev_db);
-}
-
-/* Inform host on a virtio device reset and wait for ack from host */
-static void vop_reset_inform_host(struct virtio_device *dev)
-{
-	struct _vop_vdev *vdev = to_vopvdev(dev);
-	struct mic_device_ctrl __iomem *dc = vdev->dc;
-	struct vop_device *vpdev = vdev->vpdev;
-	int retry;
-
-	iowrite8(0, &dc->host_ack);
-	iowrite8(1, &dc->vdev_reset);
-	vpdev->hw_ops->send_intr(vpdev, vdev->c2h_vdev_db);
-
-	/* Wait till host completes all card accesses and acks the reset */
-	for (retry = 100; retry--;) {
-		if (ioread8(&dc->host_ack))
-			break;
-		msleep(100);
-	}
-
-	dev_dbg(_vop_dev(vdev), "%s: retry: %d\n", __func__, retry);
-
-	/* Reset status to 0 in case we timed out */
-	iowrite8(0, &vdev->desc->status);
-}
-
-static void vop_reset(struct virtio_device *dev)
-{
-	struct _vop_vdev *vdev = to_vopvdev(dev);
-
-	dev_dbg(_vop_dev(vdev), "%s: virtio id %d\n",
-		__func__, dev->id.device);
-
-	vop_reset_inform_host(dev);
-	complete_all(&vdev->reset_done);
-}
-
-/*
- * The virtio_ring code calls this API when it wants to notify the Host.
- */
-static bool vop_notify(struct virtqueue *vq)
-{
-	struct _vop_vdev *vdev = vq->priv;
-	struct vop_device *vpdev = vdev->vpdev;
-
-	vpdev->hw_ops->send_intr(vpdev, vdev->c2h_vdev_db);
-	return true;
-}
-
-static void vop_del_vq(struct virtqueue *vq, int n)
-{
-	struct _vop_vdev *vdev = to_vopvdev(vq->vdev);
-	struct vop_device *vpdev = vdev->vpdev;
-
-	dma_unmap_single(&vpdev->dev, vdev->used[n],
-			 vdev->used_size[n], DMA_BIDIRECTIONAL);
-	free_pages((unsigned long)vdev->used_virt[n],
-		   get_order(vdev->used_size[n]));
-	vring_del_virtqueue(vq);
-	vpdev->hw_ops->unmap(vpdev, vdev->vr[n]);
-	vdev->vr[n] = NULL;
-}
-
-static void vop_del_vqs(struct virtio_device *dev)
-{
-	struct _vop_vdev *vdev = to_vopvdev(dev);
-	struct virtqueue *vq, *n;
-	int idx = 0;
-
-	dev_dbg(_vop_dev(vdev), "%s\n", __func__);
-
-	list_for_each_entry_safe(vq, n, &dev->vqs, list)
-		vop_del_vq(vq, idx++);
-}
-
-static struct virtqueue *vop_new_virtqueue(unsigned int index,
-				      unsigned int num,
-				      struct virtio_device *vdev,
-				      bool context,
-				      void *pages,
-				      bool (*notify)(struct virtqueue *vq),
-				      void (*callback)(struct virtqueue *vq),
-				      const char *name,
-				      void *used)
-{
-	bool weak_barriers = false;
-	struct vring vring;
-
-	vring_init(&vring, num, pages, MIC_VIRTIO_RING_ALIGN);
-	vring.used = used;
-
-	return __vring_new_virtqueue(index, vring, vdev, weak_barriers, context,
-				     notify, callback, name);
-}
-
-/*
- * This routine will assign vring's allocated in host/io memory. Code in
- * virtio_ring.c however continues to access this io memory as if it were local
- * memory without io accessors.
- */
-static struct virtqueue *vop_find_vq(struct virtio_device *dev,
-				     unsigned index,
-				     void (*callback)(struct virtqueue *vq),
-				     const char *name, bool ctx)
-{
-	struct _vop_vdev *vdev = to_vopvdev(dev);
-	struct vop_device *vpdev = vdev->vpdev;
-	struct mic_vqconfig __iomem *vqconfig;
-	struct mic_vqconfig config;
-	struct virtqueue *vq;
-	void __iomem *va;
-	struct _mic_vring_info __iomem *info;
-	void *used;
-	int vr_size, _vr_size, err, magic;
-	u8 type = ioread8(&vdev->desc->type);
-
-	if (index >= ioread8(&vdev->desc->num_vq))
-		return ERR_PTR(-ENOENT);
-
-	if (!name)
-		return ERR_PTR(-ENOENT);
-
-	/* First assign the vring's allocated in host memory */
-	vqconfig = _vop_vq_config(vdev->desc) + index;
-	memcpy_fromio(&config, vqconfig, sizeof(config));
-	_vr_size = round_up(vring_size(le16_to_cpu(config.num), MIC_VIRTIO_RING_ALIGN), 4);
-	vr_size = PAGE_ALIGN(_vr_size + sizeof(struct _mic_vring_info));
-	va = vpdev->hw_ops->remap(vpdev, le64_to_cpu(config.address), vr_size);
-	if (!va)
-		return ERR_PTR(-ENOMEM);
-	vdev->vr[index] = va;
-	memset_io(va, 0x0, _vr_size);
-
-	info = va + _vr_size;
-	magic = ioread32(&info->magic);
-
-	if (WARN(magic != MIC_MAGIC + type + index, "magic mismatch")) {
-		err = -EIO;
-		goto unmap;
-	}
-
-	vdev->used_size[index] = PAGE_ALIGN(sizeof(__u16) * 3 +
-					     sizeof(struct vring_used_elem) *
-					     le16_to_cpu(config.num));
-	used = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
-					get_order(vdev->used_size[index]));
-	vdev->used_virt[index] = used;
-	if (!used) {
-		err = -ENOMEM;
-		dev_err(_vop_dev(vdev), "%s %d err %d\n",
-			__func__, __LINE__, err);
-		goto unmap;
-	}
-
-	vq = vop_new_virtqueue(index, le16_to_cpu(config.num), dev, ctx,
-			       (void __force *)va, vop_notify, callback,
-			       name, used);
-	if (!vq) {
-		err = -ENOMEM;
-		goto free_used;
-	}
-
-	vdev->used[index] = dma_map_single(&vpdev->dev, used,
-					    vdev->used_size[index],
-					    DMA_BIDIRECTIONAL);
-	if (dma_mapping_error(&vpdev->dev, vdev->used[index])) {
-		err = -ENOMEM;
-		dev_err(_vop_dev(vdev), "%s %d err %d\n",
-			__func__, __LINE__, err);
-		goto del_vq;
-	}
-	writeq(vdev->used[index], &vqconfig->used_address);
-
-	vq->priv = vdev;
-	return vq;
-del_vq:
-	vring_del_virtqueue(vq);
-free_used:
-	free_pages((unsigned long)used,
-		   get_order(vdev->used_size[index]));
-unmap:
-	vpdev->hw_ops->unmap(vpdev, vdev->vr[index]);
-	return ERR_PTR(err);
-}
-
-static int vop_find_vqs(struct virtio_device *dev, unsigned nvqs,
-			struct virtqueue *vqs[],
-			vq_callback_t *callbacks[],
-			const char * const names[], const bool *ctx,
-			struct irq_affinity *desc)
-{
-	struct _vop_vdev *vdev = to_vopvdev(dev);
-	struct vop_device *vpdev = vdev->vpdev;
-	struct mic_device_ctrl __iomem *dc = vdev->dc;
-	int i, err, retry, queue_idx = 0;
-
-	/* We must have this many virtqueues. */
-	if (nvqs > ioread8(&vdev->desc->num_vq))
-		return -ENOENT;
-
-	for (i = 0; i < nvqs; ++i) {
-		if (!names[i]) {
-			vqs[i] = NULL;
-			continue;
-		}
-
-		dev_dbg(_vop_dev(vdev), "%s: %d: %s\n",
-			__func__, i, names[i]);
-		vqs[i] = vop_find_vq(dev, queue_idx++, callbacks[i], names[i],
-				     ctx ? ctx[i] : false);
-		if (IS_ERR(vqs[i])) {
-			err = PTR_ERR(vqs[i]);
-			goto error;
-		}
-	}
-
-	iowrite8(1, &dc->used_address_updated);
-	/*
-	 * Send an interrupt to the host to inform it that used
-	 * rings have been re-assigned.
-	 */
-	vpdev->hw_ops->send_intr(vpdev, vdev->c2h_vdev_db);
-	for (retry = 100; --retry;) {
-		if (!ioread8(&dc->used_address_updated))
-			break;
-		msleep(100);
-	}
-
-	dev_dbg(_vop_dev(vdev), "%s: retry: %d\n", __func__, retry);
-	if (!retry) {
-		err = -ENODEV;
-		goto error;
-	}
-
-	return 0;
-error:
-	vop_del_vqs(dev);
-	return err;
-}
-
-/*
- * The config ops structure as defined by virtio config
- */
-static const struct virtio_config_ops vop_vq_config_ops = {
-	.get_features = vop_get_features,
-	.finalize_features = vop_finalize_features,
-	.get = vop_get,
-	.set = vop_set,
-	.get_status = vop_get_status,
-	.set_status = vop_set_status,
-	.reset = vop_reset,
-	.find_vqs = vop_find_vqs,
-	.del_vqs = vop_del_vqs,
-};
-
-static irqreturn_t vop_virtio_intr_handler(int irq, void *data)
-{
-	struct _vop_vdev *vdev = data;
-	struct vop_device *vpdev = vdev->vpdev;
-	struct virtqueue *vq;
-
-	vpdev->hw_ops->ack_interrupt(vpdev, vdev->h2c_vdev_db);
-	list_for_each_entry(vq, &vdev->vdev.vqs, list)
-		vring_interrupt(0, vq);
-
-	return IRQ_HANDLED;
-}
-
-static void vop_virtio_release_dev(struct device *_d)
-{
-	struct virtio_device *vdev =
-			container_of(_d, struct virtio_device, dev);
-	struct _vop_vdev *vop_vdev =
-			container_of(vdev, struct _vop_vdev, vdev);
-
-	kfree(vop_vdev);
-}
-
-/*
- * adds a new device and register it with virtio
- * appropriate drivers are loaded by the device model
- */
-static int _vop_add_device(struct mic_device_desc __iomem *d,
-			   unsigned int offset, struct vop_device *vpdev,
-			   int dnode)
-{
-	struct _vop_vdev *vdev, *reg_dev = NULL;
-	int ret;
-	u8 type = ioread8(&d->type);
-
-	vdev = kzalloc(sizeof(*vdev), GFP_KERNEL);
-	if (!vdev)
-		return -ENOMEM;
-
-	vdev->vpdev = vpdev;
-	vdev->vdev.dev.parent = &vpdev->dev;
-	vdev->vdev.dev.release = vop_virtio_release_dev;
-	vdev->vdev.id.device = type;
-	vdev->vdev.config = &vop_vq_config_ops;
-	vdev->desc = d;
-	vdev->dc = (void __iomem *)d + _vop_aligned_desc_size(d);
-	vdev->dnode = dnode;
-	vdev->vdev.priv = (void *)(unsigned long)dnode;
-	init_completion(&vdev->reset_done);
-
-	vdev->h2c_vdev_db = vpdev->hw_ops->next_db(vpdev);
-	vdev->virtio_cookie = vpdev->hw_ops->request_irq(vpdev,
-			vop_virtio_intr_handler, "virtio intr",
-			vdev, vdev->h2c_vdev_db);
-	if (IS_ERR(vdev->virtio_cookie)) {
-		ret = PTR_ERR(vdev->virtio_cookie);
-		goto kfree;
-	}
-	iowrite8((u8)vdev->h2c_vdev_db, &vdev->dc->h2c_vdev_db);
-	vdev->c2h_vdev_db = ioread8(&vdev->dc->c2h_vdev_db);
-
-	ret = register_virtio_device(&vdev->vdev);
-	reg_dev = vdev;
-	if (ret) {
-		dev_err(_vop_dev(vdev),
-			"Failed to register vop device %u type %u\n",
-			offset, type);
-		goto free_irq;
-	}
-	writeq((unsigned long)vdev, &vdev->dc->vdev);
-	dev_dbg(_vop_dev(vdev), "%s: registered vop device %u type %u vdev %p\n",
-		__func__, offset, type, vdev);
-
-	return 0;
-
-free_irq:
-	vpdev->hw_ops->free_irq(vpdev, vdev->virtio_cookie, vdev);
-kfree:
-	if (reg_dev)
-		put_device(&vdev->vdev.dev);
-	else
-		kfree(vdev);
-	return ret;
-}
-
-/*
- * match for a vop device with a specific desc pointer
- */
-static int vop_match_desc(struct device *dev, void *data)
-{
-	struct virtio_device *_dev = dev_to_virtio(dev);
-	struct _vop_vdev *vdev = to_vopvdev(_dev);
-
-	return vdev->desc == (void __iomem *)data;
-}
-
-static struct _vop_vdev *vop_dc_to_vdev(struct mic_device_ctrl __iomem *dc)
-{
-	return (struct _vop_vdev *)(unsigned long)readq(&dc->vdev);
-}
-
-static void _vop_handle_config_change(struct mic_device_desc __iomem *d,
-				      unsigned int offset,
-				      struct vop_device *vpdev)
-{
-	struct mic_device_ctrl __iomem *dc
-		= (void __iomem *)d + _vop_aligned_desc_size(d);
-	struct _vop_vdev *vdev = vop_dc_to_vdev(dc);
-
-	if (ioread8(&dc->config_change) != MIC_VIRTIO_PARAM_CONFIG_CHANGED)
-		return;
-
-	dev_dbg(&vpdev->dev, "%s %d\n", __func__, __LINE__);
-	virtio_config_changed(&vdev->vdev);
-	iowrite8(1, &dc->guest_ack);
-}
-
-/*
- * removes a virtio device if a hot remove event has been
- * requested by the host.
- */
-static int _vop_remove_device(struct mic_device_desc __iomem *d,
-			      unsigned int offset, struct vop_device *vpdev)
-{
-	struct mic_device_ctrl __iomem *dc
-		= (void __iomem *)d + _vop_aligned_desc_size(d);
-	struct _vop_vdev *vdev = vop_dc_to_vdev(dc);
-	u8 status;
-	int ret = -1;
-
-	if (ioread8(&dc->config_change) == MIC_VIRTIO_PARAM_DEV_REMOVE) {
-		struct device *dev = get_device(&vdev->vdev.dev);
-
-		dev_dbg(&vpdev->dev,
-			"%s %d config_change %d type %d vdev %p\n",
-			__func__, __LINE__,
-			ioread8(&dc->config_change), ioread8(&d->type), vdev);
-		status = ioread8(&d->status);
-		reinit_completion(&vdev->reset_done);
-		unregister_virtio_device(&vdev->vdev);
-		vpdev->hw_ops->free_irq(vpdev, vdev->virtio_cookie, vdev);
-		iowrite8(-1, &dc->h2c_vdev_db);
-		if (status & VIRTIO_CONFIG_S_DRIVER_OK)
-			wait_for_completion(&vdev->reset_done);
-		put_device(dev);
-		iowrite8(1, &dc->guest_ack);
-		dev_dbg(&vpdev->dev, "%s %d guest_ack %d\n",
-			__func__, __LINE__, ioread8(&dc->guest_ack));
-		iowrite8(-1, &d->type);
-		ret = 0;
-	}
-	return ret;
-}
-
-#define REMOVE_DEVICES true
-
-static void _vop_scan_devices(void __iomem *dp, struct vop_device *vpdev,
-			      bool remove, int dnode)
-{
-	s8 type;
-	unsigned int i;
-	struct mic_device_desc __iomem *d;
-	struct mic_device_ctrl __iomem *dc;
-	struct device *dev;
-
-	for (i = sizeof(struct mic_bootparam);
-			i < MIC_DP_SIZE; i += _vop_total_desc_size(d)) {
-		d = dp + i;
-		dc = (void __iomem *)d + _vop_aligned_desc_size(d);
-		/*
-		 * This read barrier is paired with the corresponding write
-		 * barrier on the host which is inserted before adding or
-		 * removing a virtio device descriptor, by updating the type.
-		 */
-		rmb();
-		type = ioread8(&d->type);
-
-		/* end of list */
-		if (type == 0)
-			break;
-
-		if (type == -1)
-			continue;
-
-		/* device already exists */
-		dev = device_find_child(&vpdev->dev, (void __force *)d,
-					vop_match_desc);
-		if (dev) {
-			if (remove)
-				iowrite8(MIC_VIRTIO_PARAM_DEV_REMOVE,
-					 &dc->config_change);
-			put_device(dev);
-			_vop_handle_config_change(d, i, vpdev);
-			_vop_remove_device(d, i, vpdev);
-			if (remove) {
-				iowrite8(0, &dc->config_change);
-				iowrite8(0, &dc->guest_ack);
-			}
-			continue;
-		}
-
-		/* new device */
-		dev_dbg(&vpdev->dev, "%s %d Adding new virtio device %p\n",
-			__func__, __LINE__, d);
-		if (!remove)
-			_vop_add_device(d, i, vpdev, dnode);
-	}
-}
-
-static void vop_scan_devices(struct vop_info *vi,
-			     struct vop_device *vpdev, bool remove)
-{
-	void __iomem *dp = vpdev->hw_ops->get_remote_dp(vpdev);
-
-	if (!dp)
-		return;
-	mutex_lock(&vi->vop_mutex);
-	_vop_scan_devices(dp, vpdev, remove, vpdev->dnode);
-	mutex_unlock(&vi->vop_mutex);
-}
-
-/*
- * vop_hotplug_device tries to find changes in the device page.
- */
-static void vop_hotplug_devices(struct work_struct *work)
-{
-	struct vop_info *vi = container_of(work, struct vop_info,
-					     hotplug_work);
-
-	vop_scan_devices(vi, vi->vpdev, !REMOVE_DEVICES);
-}
-
-/*
- * Interrupt handler for hot plug/config changes etc.
- */
-static irqreturn_t vop_extint_handler(int irq, void *data)
-{
-	struct vop_info *vi = data;
-	struct mic_bootparam __iomem *bp;
-	struct vop_device *vpdev = vi->vpdev;
-
-	bp = vpdev->hw_ops->get_remote_dp(vpdev);
-	dev_dbg(&vpdev->dev, "%s %d hotplug work\n",
-		__func__, __LINE__);
-	vpdev->hw_ops->ack_interrupt(vpdev, ioread8(&bp->h2c_config_db));
-	schedule_work(&vi->hotplug_work);
-	return IRQ_HANDLED;
-}
-
-static int vop_driver_probe(struct vop_device *vpdev)
-{
-	struct vop_info *vi;
-	int rc;
-
-	vi = kzalloc(sizeof(*vi), GFP_KERNEL);
-	if (!vi) {
-		rc = -ENOMEM;
-		goto exit;
-	}
-	dev_set_drvdata(&vpdev->dev, vi);
-	vi->vpdev = vpdev;
-
-	mutex_init(&vi->vop_mutex);
-	INIT_WORK(&vi->hotplug_work, vop_hotplug_devices);
-	if (vpdev->dnode) {
-		rc = vop_host_init(vi);
-		if (rc < 0)
-			goto free;
-	} else {
-		struct mic_bootparam __iomem *bootparam;
-
-		vop_scan_devices(vi, vpdev, !REMOVE_DEVICES);
-
-		vi->h2c_config_db = vpdev->hw_ops->next_db(vpdev);
-		vi->cookie = vpdev->hw_ops->request_irq(vpdev,
-							vop_extint_handler,
-							"virtio_config_intr",
-							vi, vi->h2c_config_db);
-		if (IS_ERR(vi->cookie)) {
-			rc = PTR_ERR(vi->cookie);
-			goto free;
-		}
-		bootparam = vpdev->hw_ops->get_remote_dp(vpdev);
-		iowrite8(vi->h2c_config_db, &bootparam->h2c_config_db);
-	}
-	vop_init_debugfs(vi);
-	return 0;
-free:
-	kfree(vi);
-exit:
-	return rc;
-}
-
-static void vop_driver_remove(struct vop_device *vpdev)
-{
-	struct vop_info *vi = dev_get_drvdata(&vpdev->dev);
-
-	if (vpdev->dnode) {
-		vop_host_uninit(vi);
-	} else {
-		struct mic_bootparam __iomem *bootparam =
-			vpdev->hw_ops->get_remote_dp(vpdev);
-		if (bootparam)
-			iowrite8(-1, &bootparam->h2c_config_db);
-		vpdev->hw_ops->free_irq(vpdev, vi->cookie, vi);
-		flush_work(&vi->hotplug_work);
-		vop_scan_devices(vi, vpdev, REMOVE_DEVICES);
-	}
-	vop_exit_debugfs(vi);
-	kfree(vi);
-}
-
-static const struct vop_device_id id_table[] = {
-	{ VOP_DEV_TRNSP, VOP_DEV_ANY_ID },
-	{ 0 },
-};
-
-static struct vop_driver vop_driver = {
-	.driver.name =	KBUILD_MODNAME,
-	.driver.owner =	THIS_MODULE,
-	.id_table = id_table,
-	.probe = vop_driver_probe,
-	.remove = vop_driver_remove,
-};
-
-module_vop_driver(vop_driver);
-
-MODULE_DEVICE_TABLE(mbus, id_table);
-MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Intel(R) Virtio Over PCIe (VOP) driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/misc/mic/vop/vop_main.h b/drivers/misc/mic/vop/vop_main.h
deleted file mode 100644
index 2451d9218137..000000000000
--- a/drivers/misc/mic/vop/vop_main.h
+++ /dev/null
@@ -1,158 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Intel Virtio Over PCIe (VOP) driver.
- */
-#ifndef _VOP_MAIN_H_
-#define _VOP_MAIN_H_
-
-#include <linux/vringh.h>
-#include <linux/virtio_config.h>
-#include <linux/virtio.h>
-#include <linux/miscdevice.h>
-
-#include <linux/mic_common.h>
-#include "../common/mic_dev.h"
-
-#include "../bus/vop_bus.h"
-
-/*
- * Note on endianness.
- * 1. Host can be both BE or LE
- * 2. Guest/card is LE. Host uses le_to_cpu to access desc/avail
- *    rings and ioreadXX/iowriteXX to access used ring.
- * 3. Device page exposed by host to guest contains LE values. Guest
- *    accesses these using ioreadXX/iowriteXX etc. This way in general we
- *    obey the virtio spec according to which guest works with native
- *    endianness and host is aware of guest endianness and does all
- *    required endianness conversion.
- * 4. Data provided from user space to guest (in ADD_DEVICE and
- *    CONFIG_CHANGE ioctl's) is not interpreted by the driver and should be
- *    in guest endianness.
- */
-
-/*
- * vop_info - Allocated per invocation of VOP probe
- *
- * @vpdev: VOP device
- * @hotplug_work: Handle virtio device creation, deletion and configuration
- * @cookie: Cookie received upon requesting a virtio configuration interrupt
- * @h2c_config_db: The doorbell used by the peer to indicate a config change
- * @vdev_list: List of "active" virtio devices injected in the peer node
- * @vop_mutex: Synchronize access to the device page as well as serialize
- *             creation/deletion of virtio devices on the peer node
- * @dp: Peer device page information
- * @dbg: Debugfs entry
- * @dma_ch: The DMA channel used by this transport for data transfers.
- * @name: Name for this transport used in misc device creation.
- * @miscdev: The misc device registered.
- */
-struct vop_info {
-	struct vop_device *vpdev;
-	struct work_struct hotplug_work;
-	struct mic_irq *cookie;
-	int h2c_config_db;
-	struct list_head vdev_list;
-	struct mutex vop_mutex;
-	void __iomem *dp;
-	struct dentry *dbg;
-	struct dma_chan *dma_ch;
-	char name[16];
-	struct miscdevice miscdev;
-};
-
-/**
- * struct vop_vringh - Virtio ring host information.
- *
- * @vring: The VOP vring used for setting up user space mappings.
- * @vrh: The host VRINGH used for accessing the card vrings.
- * @riov: The VRINGH read kernel IOV.
- * @wiov: The VRINGH write kernel IOV.
- * @head: The VRINGH head index address passed to vringh_getdesc_kern(..).
- * @vr_mutex: Mutex for synchronizing access to the VRING.
- * @buf: Temporary kernel buffer used to copy in/out data
- * from/to the card via DMA.
- * @buf_da: dma address of buf.
- * @vdev: Back pointer to VOP virtio device for vringh_notify(..).
- */
-struct vop_vringh {
-	struct mic_vring vring;
-	struct vringh vrh;
-	struct vringh_kiov riov;
-	struct vringh_kiov wiov;
-	u16 head;
-	struct mutex vr_mutex;
-	void *buf;
-	dma_addr_t buf_da;
-	struct vop_vdev *vdev;
-};
-
-/**
- * struct vop_vdev - Host information for a card Virtio device.
- *
- * @virtio_id - Virtio device id.
- * @waitq - Waitqueue to allow ring3 apps to poll.
- * @vpdev - pointer to VOP bus device.
- * @poll_wake - Used for waking up threads blocked in poll.
- * @out_bytes - Debug stats for number of bytes copied from host to card.
- * @in_bytes - Debug stats for number of bytes copied from card to host.
- * @out_bytes_dma - Debug stats for number of bytes copied from host to card
- * using DMA.
- * @in_bytes_dma - Debug stats for number of bytes copied from card to host
- * using DMA.
- * @tx_len_unaligned - Debug stats for number of bytes copied to the card where
- * the transfer length did not have the required DMA alignment.
- * @tx_dst_unaligned - Debug stats for number of bytes copied where the
- * destination address on the card did not have the required DMA alignment.
- * @vvr - Store per VRING data structures.
- * @virtio_bh_work - Work struct used to schedule virtio bottom half handling.
- * @dd - Virtio device descriptor.
- * @dc - Virtio device control fields.
- * @list - List of Virtio devices.
- * @virtio_db - The doorbell used by the card to interrupt the host.
- * @virtio_cookie - The cookie returned while requesting interrupts.
- * @vi: Transport information.
- * @vdev_mutex: Mutex synchronizing virtio device injection,
- *              removal and data transfers.
- * @destroy: Track if a virtio device is being destroyed.
- * @deleted: The virtio device has been deleted.
- */
-struct vop_vdev {
-	int virtio_id;
-	wait_queue_head_t waitq;
-	struct vop_device *vpdev;
-	int poll_wake;
-	unsigned long out_bytes;
-	unsigned long in_bytes;
-	unsigned long out_bytes_dma;
-	unsigned long in_bytes_dma;
-	unsigned long tx_len_unaligned;
-	unsigned long tx_dst_unaligned;
-	unsigned long rx_dst_unaligned;
-	struct vop_vringh vvr[MIC_MAX_VRINGS];
-	struct work_struct virtio_bh_work;
-	struct mic_device_desc *dd;
-	struct mic_device_ctrl *dc;
-	struct list_head list;
-	int virtio_db;
-	struct mic_irq *virtio_cookie;
-	struct vop_info *vi;
-	struct mutex vdev_mutex;
-	struct completion destroy;
-	bool deleted;
-};
-
-/* Helper API to check if a virtio device is running */
-static inline bool vop_vdevup(struct vop_vdev *vdev)
-{
-	return !!vdev->dd->status;
-}
-
-void vop_init_debugfs(struct vop_info *vi);
-void vop_exit_debugfs(struct vop_info *vi);
-int vop_host_init(struct vop_info *vi);
-void vop_host_uninit(struct vop_info *vi);
-#endif
diff --git a/drivers/misc/mic/vop/vop_vringh.c b/drivers/misc/mic/vop/vop_vringh.c
deleted file mode 100644
index 7014ffe88632..000000000000
--- a/drivers/misc/mic/vop/vop_vringh.c
+++ /dev/null
@@ -1,1166 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Intel Virtio Over PCIe (VOP) driver.
- */
-#include <linux/sched.h>
-#include <linux/poll.h>
-#include <linux/dma-mapping.h>
-
-#include <linux/mic_common.h>
-#include "../common/mic_dev.h"
-
-#include <linux/mic_ioctl.h>
-#include "vop_main.h"
-
-/* Helper API to obtain the VOP PCIe device */
-static inline struct device *vop_dev(struct vop_vdev *vdev)
-{
-	return vdev->vpdev->dev.parent;
-}
-
-/* Helper API to check if a virtio device is initialized */
-static inline int vop_vdev_inited(struct vop_vdev *vdev)
-{
-	if (!vdev)
-		return -EINVAL;
-	/* Device has not been created yet */
-	if (!vdev->dd || !vdev->dd->type) {
-		dev_err(vop_dev(vdev), "%s %d err %d\n",
-			__func__, __LINE__, -EINVAL);
-		return -EINVAL;
-	}
-	/* Device has been removed/deleted */
-	if (vdev->dd->type == -1) {
-		dev_dbg(vop_dev(vdev), "%s %d err %d\n",
-			__func__, __LINE__, -ENODEV);
-		return -ENODEV;
-	}
-	return 0;
-}
-
-static void _vop_notify(struct vringh *vrh)
-{
-	struct vop_vringh *vvrh = container_of(vrh, struct vop_vringh, vrh);
-	struct vop_vdev *vdev = vvrh->vdev;
-	struct vop_device *vpdev = vdev->vpdev;
-	s8 db = vdev->dc->h2c_vdev_db;
-
-	if (db != -1)
-		vpdev->hw_ops->send_intr(vpdev, db);
-}
-
-static void vop_virtio_init_post(struct vop_vdev *vdev)
-{
-	struct mic_vqconfig *vqconfig = mic_vq_config(vdev->dd);
-	struct vop_device *vpdev = vdev->vpdev;
-	int i, used_size;
-
-	for (i = 0; i < vdev->dd->num_vq; i++) {
-		used_size = PAGE_ALIGN(sizeof(u16) * 3 +
-				sizeof(struct vring_used_elem) *
-				le16_to_cpu(vqconfig->num));
-		if (!le64_to_cpu(vqconfig[i].used_address)) {
-			dev_warn(vop_dev(vdev), "used_address zero??\n");
-			continue;
-		}
-		vdev->vvr[i].vrh.vring.used =
-			(void __force *)vpdev->hw_ops->remap(
-			vpdev,
-			le64_to_cpu(vqconfig[i].used_address),
-			used_size);
-	}
-
-	vdev->dc->used_address_updated = 0;
-
-	dev_info(vop_dev(vdev), "%s: device type %d LINKUP\n",
-		 __func__, vdev->virtio_id);
-}
-
-static inline void vop_virtio_device_reset(struct vop_vdev *vdev)
-{
-	int i;
-
-	dev_dbg(vop_dev(vdev), "%s: status %d device type %d RESET\n",
-		__func__, vdev->dd->status, vdev->virtio_id);
-
-	for (i = 0; i < vdev->dd->num_vq; i++)
-		/*
-		 * Avoid lockdep false positive. The + 1 is for the vop
-		 * mutex which is held in the reset devices code path.
-		 */
-		mutex_lock_nested(&vdev->vvr[i].vr_mutex, i + 1);
-
-	/* 0 status means "reset" */
-	vdev->dd->status = 0;
-	vdev->dc->vdev_reset = 0;
-	vdev->dc->host_ack = 1;
-
-	for (i = 0; i < vdev->dd->num_vq; i++) {
-		struct vringh *vrh = &vdev->vvr[i].vrh;
-
-		vdev->vvr[i].vring.info->avail_idx = 0;
-		vrh->completed = 0;
-		vrh->last_avail_idx = 0;
-		vrh->last_used_idx = 0;
-	}
-
-	for (i = 0; i < vdev->dd->num_vq; i++)
-		mutex_unlock(&vdev->vvr[i].vr_mutex);
-}
-
-static void vop_virtio_reset_devices(struct vop_info *vi)
-{
-	struct list_head *pos, *tmp;
-	struct vop_vdev *vdev;
-
-	list_for_each_safe(pos, tmp, &vi->vdev_list) {
-		vdev = list_entry(pos, struct vop_vdev, list);
-		vop_virtio_device_reset(vdev);
-		vdev->poll_wake = 1;
-		wake_up(&vdev->waitq);
-	}
-}
-
-static void vop_bh_handler(struct work_struct *work)
-{
-	struct vop_vdev *vdev = container_of(work, struct vop_vdev,
-			virtio_bh_work);
-
-	if (vdev->dc->used_address_updated)
-		vop_virtio_init_post(vdev);
-
-	if (vdev->dc->vdev_reset)
-		vop_virtio_device_reset(vdev);
-
-	vdev->poll_wake = 1;
-	wake_up(&vdev->waitq);
-}
-
-static irqreturn_t _vop_virtio_intr_handler(int irq, void *data)
-{
-	struct vop_vdev *vdev = data;
-	struct vop_device *vpdev = vdev->vpdev;
-
-	vpdev->hw_ops->ack_interrupt(vpdev, vdev->virtio_db);
-	schedule_work(&vdev->virtio_bh_work);
-	return IRQ_HANDLED;
-}
-
-static int vop_virtio_config_change(struct vop_vdev *vdev, void *argp)
-{
-	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wake);
-	int ret = 0, retry, i;
-	struct vop_device *vpdev = vdev->vpdev;
-	struct vop_info *vi = dev_get_drvdata(&vpdev->dev);
-	struct mic_bootparam *bootparam = vpdev->hw_ops->get_dp(vpdev);
-	s8 db = bootparam->h2c_config_db;
-
-	mutex_lock(&vi->vop_mutex);
-	for (i = 0; i < vdev->dd->num_vq; i++)
-		mutex_lock_nested(&vdev->vvr[i].vr_mutex, i + 1);
-
-	if (db == -1 || vdev->dd->type == -1) {
-		ret = -EIO;
-		goto exit;
-	}
-
-	memcpy(mic_vq_configspace(vdev->dd), argp, vdev->dd->config_len);
-	vdev->dc->config_change = MIC_VIRTIO_PARAM_CONFIG_CHANGED;
-	vpdev->hw_ops->send_intr(vpdev, db);
-
-	for (retry = 100; retry--;) {
-		ret = wait_event_timeout(wake, vdev->dc->guest_ack,
-					 msecs_to_jiffies(100));
-		if (ret)
-			break;
-	}
-
-	dev_dbg(vop_dev(vdev),
-		"%s %d retry: %d\n", __func__, __LINE__, retry);
-	vdev->dc->config_change = 0;
-	vdev->dc->guest_ack = 0;
-exit:
-	for (i = 0; i < vdev->dd->num_vq; i++)
-		mutex_unlock(&vdev->vvr[i].vr_mutex);
-	mutex_unlock(&vi->vop_mutex);
-	return ret;
-}
-
-static int vop_copy_dp_entry(struct vop_vdev *vdev,
-			     struct mic_device_desc *argp, __u8 *type,
-			     struct mic_device_desc **devpage)
-{
-	struct vop_device *vpdev = vdev->vpdev;
-	struct mic_device_desc *devp;
-	struct mic_vqconfig *vqconfig;
-	int ret = 0, i;
-	bool slot_found = false;
-
-	vqconfig = mic_vq_config(argp);
-	for (i = 0; i < argp->num_vq; i++) {
-		if (le16_to_cpu(vqconfig[i].num) > MIC_MAX_VRING_ENTRIES) {
-			ret =  -EINVAL;
-			dev_err(vop_dev(vdev), "%s %d err %d\n",
-				__func__, __LINE__, ret);
-			goto exit;
-		}
-	}
-
-	/* Find the first free device page entry */
-	for (i = sizeof(struct mic_bootparam);
-		i < MIC_DP_SIZE - mic_total_desc_size(argp);
-		i += mic_total_desc_size(devp)) {
-		devp = vpdev->hw_ops->get_dp(vpdev) + i;
-		if (devp->type == 0 || devp->type == -1) {
-			slot_found = true;
-			break;
-		}
-	}
-	if (!slot_found) {
-		ret =  -EINVAL;
-		dev_err(vop_dev(vdev), "%s %d err %d\n",
-			__func__, __LINE__, ret);
-		goto exit;
-	}
-	/*
-	 * Save off the type before doing the memcpy. Type will be set in the
-	 * end after completing all initialization for the new device.
-	 */
-	*type = argp->type;
-	argp->type = 0;
-	memcpy(devp, argp, mic_desc_size(argp));
-
-	*devpage = devp;
-exit:
-	return ret;
-}
-
-static void vop_init_device_ctrl(struct vop_vdev *vdev,
-				 struct mic_device_desc *devpage)
-{
-	struct mic_device_ctrl *dc;
-
-	dc = (void *)devpage + mic_aligned_desc_size(devpage);
-
-	dc->config_change = 0;
-	dc->guest_ack = 0;
-	dc->vdev_reset = 0;
-	dc->host_ack = 0;
-	dc->used_address_updated = 0;
-	dc->c2h_vdev_db = -1;
-	dc->h2c_vdev_db = -1;
-	vdev->dc = dc;
-}
-
-static int vop_virtio_add_device(struct vop_vdev *vdev,
-				 struct mic_device_desc *argp)
-{
-	struct vop_info *vi = vdev->vi;
-	struct vop_device *vpdev = vi->vpdev;
-	struct mic_device_desc *dd = NULL;
-	struct mic_vqconfig *vqconfig;
-	int vr_size, i, j, ret;
-	u8 type = 0;
-	s8 db = -1;
-	char irqname[16];
-	struct mic_bootparam *bootparam;
-	u16 num;
-	dma_addr_t vr_addr;
-
-	bootparam = vpdev->hw_ops->get_dp(vpdev);
-	init_waitqueue_head(&vdev->waitq);
-	INIT_LIST_HEAD(&vdev->list);
-	vdev->vpdev = vpdev;
-
-	ret = vop_copy_dp_entry(vdev, argp, &type, &dd);
-	if (ret) {
-		dev_err(vop_dev(vdev), "%s %d err %d\n",
-			__func__, __LINE__, ret);
-		return ret;
-	}
-
-	vop_init_device_ctrl(vdev, dd);
-
-	vdev->dd = dd;
-	vdev->virtio_id = type;
-	vqconfig = mic_vq_config(dd);
-	INIT_WORK(&vdev->virtio_bh_work, vop_bh_handler);
-
-	for (i = 0; i < dd->num_vq; i++) {
-		struct vop_vringh *vvr = &vdev->vvr[i];
-		struct mic_vring *vr = &vdev->vvr[i].vring;
-
-		num = le16_to_cpu(vqconfig[i].num);
-		mutex_init(&vvr->vr_mutex);
-		vr_size = PAGE_ALIGN(round_up(vring_size(num, MIC_VIRTIO_RING_ALIGN), 4) +
-			sizeof(struct _mic_vring_info));
-		vr->va = (void *)
-			__get_free_pages(GFP_KERNEL | __GFP_ZERO,
-					 get_order(vr_size));
-		if (!vr->va) {
-			ret = -ENOMEM;
-			dev_err(vop_dev(vdev), "%s %d err %d\n",
-				__func__, __LINE__, ret);
-			goto err;
-		}
-		vr->len = vr_size;
-		vr->info = vr->va + round_up(vring_size(num, MIC_VIRTIO_RING_ALIGN), 4);
-		vr->info->magic = cpu_to_le32(MIC_MAGIC + vdev->virtio_id + i);
-		vr_addr = dma_map_single(&vpdev->dev, vr->va, vr_size,
-					 DMA_BIDIRECTIONAL);
-		if (dma_mapping_error(&vpdev->dev, vr_addr)) {
-			free_pages((unsigned long)vr->va, get_order(vr_size));
-			ret = -ENOMEM;
-			dev_err(vop_dev(vdev), "%s %d err %d\n",
-				__func__, __LINE__, ret);
-			goto err;
-		}
-		vqconfig[i].address = cpu_to_le64(vr_addr);
-
-		vring_init(&vr->vr, num, vr->va, MIC_VIRTIO_RING_ALIGN);
-		ret = vringh_init_kern(&vvr->vrh,
-				       *(u32 *)mic_vq_features(vdev->dd),
-				       num, false, vr->vr.desc, vr->vr.avail,
-				       vr->vr.used);
-		if (ret) {
-			dev_err(vop_dev(vdev), "%s %d err %d\n",
-				__func__, __LINE__, ret);
-			goto err;
-		}
-		vringh_kiov_init(&vvr->riov, NULL, 0);
-		vringh_kiov_init(&vvr->wiov, NULL, 0);
-		vvr->head = USHRT_MAX;
-		vvr->vdev = vdev;
-		vvr->vrh.notify = _vop_notify;
-		dev_dbg(&vpdev->dev,
-			"%s %d index %d va %p info %p vr_size 0x%x\n",
-			__func__, __LINE__, i, vr->va, vr->info, vr_size);
-		vvr->buf = (void *)__get_free_pages(GFP_KERNEL,
-					get_order(VOP_INT_DMA_BUF_SIZE));
-		vvr->buf_da = dma_map_single(&vpdev->dev,
-					  vvr->buf, VOP_INT_DMA_BUF_SIZE,
-					  DMA_BIDIRECTIONAL);
-	}
-
-	snprintf(irqname, sizeof(irqname), "vop%dvirtio%d", vpdev->index,
-		 vdev->virtio_id);
-	vdev->virtio_db = vpdev->hw_ops->next_db(vpdev);
-	vdev->virtio_cookie = vpdev->hw_ops->request_irq(vpdev,
-			_vop_virtio_intr_handler, irqname, vdev,
-			vdev->virtio_db);
-	if (IS_ERR(vdev->virtio_cookie)) {
-		ret = PTR_ERR(vdev->virtio_cookie);
-		dev_dbg(&vpdev->dev, "request irq failed\n");
-		goto err;
-	}
-
-	vdev->dc->c2h_vdev_db = vdev->virtio_db;
-
-	/*
-	 * Order the type update with previous stores. This write barrier
-	 * is paired with the corresponding read barrier before the uncached
-	 * system memory read of the type, on the card while scanning the
-	 * device page.
-	 */
-	smp_wmb();
-	dd->type = type;
-	argp->type = type;
-
-	if (bootparam) {
-		db = bootparam->h2c_config_db;
-		if (db != -1)
-			vpdev->hw_ops->send_intr(vpdev, db);
-	}
-	dev_dbg(&vpdev->dev, "Added virtio id %d db %d\n", dd->type, db);
-	return 0;
-err:
-	vqconfig = mic_vq_config(dd);
-	for (j = 0; j < i; j++) {
-		struct vop_vringh *vvr = &vdev->vvr[j];
-
-		dma_unmap_single(&vpdev->dev, le64_to_cpu(vqconfig[j].address),
-				 vvr->vring.len, DMA_BIDIRECTIONAL);
-		free_pages((unsigned long)vvr->vring.va,
-			   get_order(vvr->vring.len));
-	}
-	return ret;
-}
-
-static void vop_dev_remove(struct vop_info *pvi, struct mic_device_ctrl *devp,
-			   struct vop_device *vpdev)
-{
-	struct mic_bootparam *bootparam = vpdev->hw_ops->get_dp(vpdev);
-	s8 db;
-	int ret, retry;
-	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wake);
-
-	devp->config_change = MIC_VIRTIO_PARAM_DEV_REMOVE;
-	db = bootparam->h2c_config_db;
-	if (db != -1)
-		vpdev->hw_ops->send_intr(vpdev, db);
-	else
-		goto done;
-	for (retry = 15; retry--;) {
-		ret = wait_event_timeout(wake, devp->guest_ack,
-					 msecs_to_jiffies(1000));
-		if (ret)
-			break;
-	}
-done:
-	devp->config_change = 0;
-	devp->guest_ack = 0;
-}
-
-static void vop_virtio_del_device(struct vop_vdev *vdev)
-{
-	struct vop_info *vi = vdev->vi;
-	struct vop_device *vpdev = vdev->vpdev;
-	int i;
-	struct mic_vqconfig *vqconfig;
-	struct mic_bootparam *bootparam = vpdev->hw_ops->get_dp(vpdev);
-
-	if (!bootparam)
-		goto skip_hot_remove;
-	vop_dev_remove(vi, vdev->dc, vpdev);
-skip_hot_remove:
-	vpdev->hw_ops->free_irq(vpdev, vdev->virtio_cookie, vdev);
-	flush_work(&vdev->virtio_bh_work);
-	vqconfig = mic_vq_config(vdev->dd);
-	for (i = 0; i < vdev->dd->num_vq; i++) {
-		struct vop_vringh *vvr = &vdev->vvr[i];
-
-		dma_unmap_single(&vpdev->dev,
-				 vvr->buf_da, VOP_INT_DMA_BUF_SIZE,
-				 DMA_BIDIRECTIONAL);
-		free_pages((unsigned long)vvr->buf,
-			   get_order(VOP_INT_DMA_BUF_SIZE));
-		vringh_kiov_cleanup(&vvr->riov);
-		vringh_kiov_cleanup(&vvr->wiov);
-		dma_unmap_single(&vpdev->dev, le64_to_cpu(vqconfig[i].address),
-				 vvr->vring.len, DMA_BIDIRECTIONAL);
-		free_pages((unsigned long)vvr->vring.va,
-			   get_order(vvr->vring.len));
-	}
-	/*
-	 * Order the type update with previous stores. This write barrier
-	 * is paired with the corresponding read barrier before the uncached
-	 * system memory read of the type, on the card while scanning the
-	 * device page.
-	 */
-	smp_wmb();
-	vdev->dd->type = -1;
-}
-
-/*
- * vop_sync_dma - Wrapper for synchronous DMAs.
- *
- * @dev - The address of the pointer to the device instance used
- * for DMA registration.
- * @dst - destination DMA address.
- * @src - source DMA address.
- * @len - size of the transfer.
- *
- * Return DMA_SUCCESS on success
- */
-static int vop_sync_dma(struct vop_vdev *vdev, dma_addr_t dst, dma_addr_t src,
-			size_t len)
-{
-	int err = 0;
-	struct dma_device *ddev;
-	struct dma_async_tx_descriptor *tx;
-	struct vop_info *vi = dev_get_drvdata(&vdev->vpdev->dev);
-	struct dma_chan *vop_ch = vi->dma_ch;
-
-	if (!vop_ch) {
-		err = -EBUSY;
-		goto error;
-	}
-	ddev = vop_ch->device;
-	tx = ddev->device_prep_dma_memcpy(vop_ch, dst, src, len,
-		DMA_PREP_FENCE);
-	if (!tx) {
-		err = -ENOMEM;
-		goto error;
-	} else {
-		dma_cookie_t cookie;
-
-		cookie = tx->tx_submit(tx);
-		if (dma_submit_error(cookie)) {
-			err = -ENOMEM;
-			goto error;
-		}
-		dma_async_issue_pending(vop_ch);
-		err = dma_sync_wait(vop_ch, cookie);
-	}
-error:
-	if (err)
-		dev_err(&vi->vpdev->dev, "%s %d err %d\n",
-			__func__, __LINE__, err);
-	return err;
-}
-
-#define VOP_USE_DMA true
-
-/*
- * Initiates the copies across the PCIe bus from card memory to a user
- * space buffer. When transfers are done using DMA, source/destination
- * addresses and transfer length must follow the alignment requirements of
- * the MIC DMA engine.
- */
-static int vop_virtio_copy_to_user(struct vop_vdev *vdev, void __user *ubuf,
-				   size_t len, u64 daddr, size_t dlen,
-				   int vr_idx)
-{
-	struct vop_device *vpdev = vdev->vpdev;
-	void __iomem *dbuf = vpdev->hw_ops->remap(vpdev, daddr, len);
-	struct vop_vringh *vvr = &vdev->vvr[vr_idx];
-	struct vop_info *vi = dev_get_drvdata(&vpdev->dev);
-	size_t dma_alignment;
-	bool x200;
-	size_t dma_offset, partlen;
-	int err;
-
-	if (!VOP_USE_DMA || !vi->dma_ch) {
-		if (copy_to_user(ubuf, (void __force *)dbuf, len)) {
-			err = -EFAULT;
-			dev_err(vop_dev(vdev), "%s %d err %d\n",
-				__func__, __LINE__, err);
-			goto err;
-		}
-		vdev->in_bytes += len;
-		err = 0;
-		goto err;
-	}
-
-	dma_alignment = 1 << vi->dma_ch->device->copy_align;
-	x200 = is_dma_copy_aligned(vi->dma_ch->device, 1, 1, 1);
-
-	dma_offset = daddr - round_down(daddr, dma_alignment);
-	daddr -= dma_offset;
-	len += dma_offset;
-	/*
-	 * X100 uses DMA addresses as seen by the card so adding
-	 * the aperture base is not required for DMA. However x200
-	 * requires DMA addresses to be an offset into the bar so
-	 * add the aperture base for x200.
-	 */
-	if (x200)
-		daddr += vpdev->aper->pa;
-	while (len) {
-		partlen = min_t(size_t, len, VOP_INT_DMA_BUF_SIZE);
-		err = vop_sync_dma(vdev, vvr->buf_da, daddr,
-				   ALIGN(partlen, dma_alignment));
-		if (err) {
-			dev_err(vop_dev(vdev), "%s %d err %d\n",
-				__func__, __LINE__, err);
-			goto err;
-		}
-		if (copy_to_user(ubuf, vvr->buf + dma_offset,
-				 partlen - dma_offset)) {
-			err = -EFAULT;
-			dev_err(vop_dev(vdev), "%s %d err %d\n",
-				__func__, __LINE__, err);
-			goto err;
-		}
-		daddr += partlen;
-		ubuf += partlen;
-		dbuf += partlen;
-		vdev->in_bytes_dma += partlen;
-		vdev->in_bytes += partlen;
-		len -= partlen;
-		dma_offset = 0;
-	}
-	err = 0;
-err:
-	vpdev->hw_ops->unmap(vpdev, dbuf);
-	dev_dbg(vop_dev(vdev),
-		"%s: ubuf %p dbuf %p len 0x%zx vr_idx 0x%x\n",
-		__func__, ubuf, dbuf, len, vr_idx);
-	return err;
-}
-
-/*
- * Initiates copies across the PCIe bus from a user space buffer to card
- * memory. When transfers are done using DMA, source/destination addresses
- * and transfer length must follow the alignment requirements of the MIC
- * DMA engine.
- */
-static int vop_virtio_copy_from_user(struct vop_vdev *vdev, void __user *ubuf,
-				     size_t len, u64 daddr, size_t dlen,
-				     int vr_idx)
-{
-	struct vop_device *vpdev = vdev->vpdev;
-	void __iomem *dbuf = vpdev->hw_ops->remap(vpdev, daddr, len);
-	struct vop_vringh *vvr = &vdev->vvr[vr_idx];
-	struct vop_info *vi = dev_get_drvdata(&vdev->vpdev->dev);
-	size_t dma_alignment;
-	bool x200;
-	size_t partlen;
-	bool dma = VOP_USE_DMA && vi->dma_ch;
-	int err = 0;
-	size_t offset = 0;
-
-	if (dma) {
-		dma_alignment = 1 << vi->dma_ch->device->copy_align;
-		x200 = is_dma_copy_aligned(vi->dma_ch->device, 1, 1, 1);
-
-		if (daddr & (dma_alignment - 1)) {
-			vdev->tx_dst_unaligned += len;
-			dma = false;
-		} else if (ALIGN(len, dma_alignment) > dlen) {
-			vdev->tx_len_unaligned += len;
-			dma = false;
-		}
-	}
-
-	if (!dma)
-		goto memcpy;
-
-	/*
-	 * X100 uses DMA addresses as seen by the card so adding
-	 * the aperture base is not required for DMA. However x200
-	 * requires DMA addresses to be an offset into the bar so
-	 * add the aperture base for x200.
-	 */
-	if (x200)
-		daddr += vpdev->aper->pa;
-	while (len) {
-		partlen = min_t(size_t, len, VOP_INT_DMA_BUF_SIZE);
-
-		if (copy_from_user(vvr->buf, ubuf, partlen)) {
-			err = -EFAULT;
-			dev_err(vop_dev(vdev), "%s %d err %d\n",
-				__func__, __LINE__, err);
-			goto err;
-		}
-		err = vop_sync_dma(vdev, daddr, vvr->buf_da,
-				   ALIGN(partlen, dma_alignment));
-		if (err) {
-			dev_err(vop_dev(vdev), "%s %d err %d\n",
-				__func__, __LINE__, err);
-			goto err;
-		}
-		daddr += partlen;
-		ubuf += partlen;
-		dbuf += partlen;
-		vdev->out_bytes_dma += partlen;
-		vdev->out_bytes += partlen;
-		len -= partlen;
-	}
-memcpy:
-	/*
-	 * We are copying to IO below and should ideally use something
-	 * like copy_from_user_toio(..) if it existed.
-	 */
-	while (len) {
-		partlen = min_t(size_t, len, VOP_INT_DMA_BUF_SIZE);
-
-		if (copy_from_user(vvr->buf, ubuf + offset, partlen)) {
-			err = -EFAULT;
-			dev_err(vop_dev(vdev), "%s %d err %d\n",
-				__func__, __LINE__, err);
-			goto err;
-		}
-		memcpy_toio(dbuf + offset, vvr->buf, partlen);
-		offset += partlen;
-		vdev->out_bytes += partlen;
-		len -= partlen;
-	}
-	err = 0;
-err:
-	vpdev->hw_ops->unmap(vpdev, dbuf);
-	dev_dbg(vop_dev(vdev),
-		"%s: ubuf %p dbuf %p len 0x%zx vr_idx 0x%x\n",
-		__func__, ubuf, dbuf, len, vr_idx);
-	return err;
-}
-
-#define MIC_VRINGH_READ true
-
-/* Determine the total number of bytes consumed in a VRINGH KIOV */
-static inline u32 vop_vringh_iov_consumed(struct vringh_kiov *iov)
-{
-	int i;
-	u32 total = iov->consumed;
-
-	for (i = 0; i < iov->i; i++)
-		total += iov->iov[i].iov_len;
-	return total;
-}
-
-/*
- * Traverse the VRINGH KIOV and issue the APIs to trigger the copies.
- * This API is heavily based on the vringh_iov_xfer(..) implementation
- * in vringh.c. The reason we cannot reuse vringh_iov_pull_kern(..)
- * and vringh_iov_push_kern(..) directly is because there is no
- * way to override the VRINGH xfer(..) routines as of v3.10.
- */
-static int vop_vringh_copy(struct vop_vdev *vdev, struct vringh_kiov *iov,
-			   void __user *ubuf, size_t len, bool read, int vr_idx,
-			   size_t *out_len)
-{
-	int ret = 0;
-	size_t partlen, tot_len = 0;
-
-	while (len && iov->i < iov->used) {
-		struct kvec *kiov = &iov->iov[iov->i];
-		unsigned long daddr = (unsigned long)kiov->iov_base;
-
-		partlen = min(kiov->iov_len, len);
-		if (read)
-			ret = vop_virtio_copy_to_user(vdev, ubuf, partlen,
-						      daddr,
-						      kiov->iov_len,
-						      vr_idx);
-		else
-			ret = vop_virtio_copy_from_user(vdev, ubuf, partlen,
-							daddr,
-							kiov->iov_len,
-							vr_idx);
-		if (ret) {
-			dev_err(vop_dev(vdev), "%s %d err %d\n",
-				__func__, __LINE__, ret);
-			break;
-		}
-		len -= partlen;
-		ubuf += partlen;
-		tot_len += partlen;
-		iov->consumed += partlen;
-		kiov->iov_len -= partlen;
-		kiov->iov_base += partlen;
-		if (!kiov->iov_len) {
-			/* Fix up old iov element then increment. */
-			kiov->iov_len = iov->consumed;
-			kiov->iov_base -= iov->consumed;
-
-			iov->consumed = 0;
-			iov->i++;
-		}
-	}
-	*out_len = tot_len;
-	return ret;
-}
-
-/*
- * Use the standard VRINGH infrastructure in the kernel to fetch new
- * descriptors, initiate the copies and update the used ring.
- */
-static int _vop_virtio_copy(struct vop_vdev *vdev, struct mic_copy_desc *copy)
-{
-	int ret = 0;
-	u32 iovcnt = copy->iovcnt;
-	struct iovec iov;
-	struct iovec __user *u_iov = copy->iov;
-	void __user *ubuf = NULL;
-	struct vop_vringh *vvr = &vdev->vvr[copy->vr_idx];
-	struct vringh_kiov *riov = &vvr->riov;
-	struct vringh_kiov *wiov = &vvr->wiov;
-	struct vringh *vrh = &vvr->vrh;
-	u16 *head = &vvr->head;
-	struct mic_vring *vr = &vvr->vring;
-	size_t len = 0, out_len;
-
-	copy->out_len = 0;
-	/* Fetch a new IOVEC if all previous elements have been processed */
-	if (riov->i == riov->used && wiov->i == wiov->used) {
-		ret = vringh_getdesc_kern(vrh, riov, wiov,
-					  head, GFP_KERNEL);
-		/* Check if there are available descriptors */
-		if (ret <= 0)
-			return ret;
-	}
-	while (iovcnt) {
-		if (!len) {
-			/* Copy over a new iovec from user space. */
-			ret = copy_from_user(&iov, u_iov, sizeof(*u_iov));
-			if (ret) {
-				ret = -EINVAL;
-				dev_err(vop_dev(vdev), "%s %d err %d\n",
-					__func__, __LINE__, ret);
-				break;
-			}
-			len = iov.iov_len;
-			ubuf = iov.iov_base;
-		}
-		/* Issue all the read descriptors first */
-		ret = vop_vringh_copy(vdev, riov, ubuf, len,
-				      MIC_VRINGH_READ, copy->vr_idx, &out_len);
-		if (ret) {
-			dev_err(vop_dev(vdev), "%s %d err %d\n",
-				__func__, __LINE__, ret);
-			break;
-		}
-		len -= out_len;
-		ubuf += out_len;
-		copy->out_len += out_len;
-		/* Issue the write descriptors next */
-		ret = vop_vringh_copy(vdev, wiov, ubuf, len,
-				      !MIC_VRINGH_READ, copy->vr_idx, &out_len);
-		if (ret) {
-			dev_err(vop_dev(vdev), "%s %d err %d\n",
-				__func__, __LINE__, ret);
-			break;
-		}
-		len -= out_len;
-		ubuf += out_len;
-		copy->out_len += out_len;
-		if (!len) {
-			/* One user space iovec is now completed */
-			iovcnt--;
-			u_iov++;
-		}
-		/* Exit loop if all elements in KIOVs have been processed. */
-		if (riov->i == riov->used && wiov->i == wiov->used)
-			break;
-	}
-	/*
-	 * Update the used ring if a descriptor was available and some data was
-	 * copied in/out and the user asked for a used ring update.
-	 */
-	if (*head != USHRT_MAX && copy->out_len && copy->update_used) {
-		u32 total = 0;
-
-		/* Determine the total data consumed */
-		total += vop_vringh_iov_consumed(riov);
-		total += vop_vringh_iov_consumed(wiov);
-		vringh_complete_kern(vrh, *head, total);
-		*head = USHRT_MAX;
-		if (vringh_need_notify_kern(vrh) > 0)
-			vringh_notify(vrh);
-		vringh_kiov_cleanup(riov);
-		vringh_kiov_cleanup(wiov);
-		/* Update avail idx for user space */
-		vr->info->avail_idx = vrh->last_avail_idx;
-	}
-	return ret;
-}
-
-static inline int vop_verify_copy_args(struct vop_vdev *vdev,
-				       struct mic_copy_desc *copy)
-{
-	if (!vdev || copy->vr_idx >= vdev->dd->num_vq)
-		return -EINVAL;
-	return 0;
-}
-
-/* Copy a specified number of virtio descriptors in a chain */
-static int vop_virtio_copy_desc(struct vop_vdev *vdev,
-				struct mic_copy_desc *copy)
-{
-	int err;
-	struct vop_vringh *vvr;
-
-	err = vop_verify_copy_args(vdev, copy);
-	if (err)
-		return err;
-
-	vvr = &vdev->vvr[copy->vr_idx];
-	mutex_lock(&vvr->vr_mutex);
-	if (!vop_vdevup(vdev)) {
-		err = -ENODEV;
-		dev_err(vop_dev(vdev), "%s %d err %d\n",
-			__func__, __LINE__, err);
-		goto err;
-	}
-	err = _vop_virtio_copy(vdev, copy);
-	if (err) {
-		dev_err(vop_dev(vdev), "%s %d err %d\n",
-			__func__, __LINE__, err);
-	}
-err:
-	mutex_unlock(&vvr->vr_mutex);
-	return err;
-}
-
-static int vop_open(struct inode *inode, struct file *f)
-{
-	struct vop_vdev *vdev;
-	struct vop_info *vi = container_of(f->private_data,
-		struct vop_info, miscdev);
-
-	vdev = kzalloc(sizeof(*vdev), GFP_KERNEL);
-	if (!vdev)
-		return -ENOMEM;
-	vdev->vi = vi;
-	mutex_init(&vdev->vdev_mutex);
-	f->private_data = vdev;
-	init_completion(&vdev->destroy);
-	complete(&vdev->destroy);
-	return 0;
-}
-
-static int vop_release(struct inode *inode, struct file *f)
-{
-	struct vop_vdev *vdev = f->private_data, *vdev_tmp;
-	struct vop_info *vi = vdev->vi;
-	struct list_head *pos, *tmp;
-	bool found = false;
-
-	mutex_lock(&vdev->vdev_mutex);
-	if (vdev->deleted)
-		goto unlock;
-	mutex_lock(&vi->vop_mutex);
-	list_for_each_safe(pos, tmp, &vi->vdev_list) {
-		vdev_tmp = list_entry(pos, struct vop_vdev, list);
-		if (vdev == vdev_tmp) {
-			vop_virtio_del_device(vdev);
-			list_del(pos);
-			found = true;
-			break;
-		}
-	}
-	mutex_unlock(&vi->vop_mutex);
-unlock:
-	mutex_unlock(&vdev->vdev_mutex);
-	if (!found)
-		wait_for_completion(&vdev->destroy);
-	f->private_data = NULL;
-	kfree(vdev);
-	return 0;
-}
-
-static long vop_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
-{
-	struct vop_vdev *vdev = f->private_data;
-	struct vop_info *vi = vdev->vi;
-	void __user *argp = (void __user *)arg;
-	int ret;
-
-	switch (cmd) {
-	case MIC_VIRTIO_ADD_DEVICE:
-	{
-		struct mic_device_desc dd, *dd_config;
-
-		if (copy_from_user(&dd, argp, sizeof(dd)))
-			return -EFAULT;
-
-		if (mic_aligned_desc_size(&dd) > MIC_MAX_DESC_BLK_SIZE ||
-		    dd.num_vq > MIC_MAX_VRINGS)
-			return -EINVAL;
-
-		dd_config = memdup_user(argp, mic_desc_size(&dd));
-		if (IS_ERR(dd_config))
-			return PTR_ERR(dd_config);
-
-		/* Ensure desc has not changed between the two reads */
-		if (memcmp(&dd, dd_config, sizeof(dd))) {
-			ret = -EINVAL;
-			goto free_ret;
-		}
-		mutex_lock(&vdev->vdev_mutex);
-		mutex_lock(&vi->vop_mutex);
-		ret = vop_virtio_add_device(vdev, dd_config);
-		if (ret)
-			goto unlock_ret;
-		list_add_tail(&vdev->list, &vi->vdev_list);
-unlock_ret:
-		mutex_unlock(&vi->vop_mutex);
-		mutex_unlock(&vdev->vdev_mutex);
-free_ret:
-		kfree(dd_config);
-		return ret;
-	}
-	case MIC_VIRTIO_COPY_DESC:
-	{
-		struct mic_copy_desc copy;
-
-		mutex_lock(&vdev->vdev_mutex);
-		ret = vop_vdev_inited(vdev);
-		if (ret)
-			goto _unlock_ret;
-
-		if (copy_from_user(&copy, argp, sizeof(copy))) {
-			ret = -EFAULT;
-			goto _unlock_ret;
-		}
-
-		ret = vop_virtio_copy_desc(vdev, &copy);
-		if (ret < 0)
-			goto _unlock_ret;
-		if (copy_to_user(
-			&((struct mic_copy_desc __user *)argp)->out_len,
-			&copy.out_len, sizeof(copy.out_len)))
-			ret = -EFAULT;
-_unlock_ret:
-		mutex_unlock(&vdev->vdev_mutex);
-		return ret;
-	}
-	case MIC_VIRTIO_CONFIG_CHANGE:
-	{
-		void *buf;
-
-		mutex_lock(&vdev->vdev_mutex);
-		ret = vop_vdev_inited(vdev);
-		if (ret)
-			goto __unlock_ret;
-		buf = memdup_user(argp, vdev->dd->config_len);
-		if (IS_ERR(buf)) {
-			ret = PTR_ERR(buf);
-			goto __unlock_ret;
-		}
-		ret = vop_virtio_config_change(vdev, buf);
-		kfree(buf);
-__unlock_ret:
-		mutex_unlock(&vdev->vdev_mutex);
-		return ret;
-	}
-	default:
-		return -ENOIOCTLCMD;
-	};
-	return 0;
-}
-
-/*
- * We return EPOLLIN | EPOLLOUT from poll when new buffers are enqueued, and
- * not when previously enqueued buffers may be available. This means that
- * in the card->host (TX) path, when userspace is unblocked by poll it
- * must drain all available descriptors or it can stall.
- */
-static __poll_t vop_poll(struct file *f, poll_table *wait)
-{
-	struct vop_vdev *vdev = f->private_data;
-	__poll_t mask = 0;
-
-	mutex_lock(&vdev->vdev_mutex);
-	if (vop_vdev_inited(vdev)) {
-		mask = EPOLLERR;
-		goto done;
-	}
-	poll_wait(f, &vdev->waitq, wait);
-	if (vop_vdev_inited(vdev)) {
-		mask = EPOLLERR;
-	} else if (vdev->poll_wake) {
-		vdev->poll_wake = 0;
-		mask = EPOLLIN | EPOLLOUT;
-	}
-done:
-	mutex_unlock(&vdev->vdev_mutex);
-	return mask;
-}
-
-static inline int
-vop_query_offset(struct vop_vdev *vdev, unsigned long offset,
-		 unsigned long *size, unsigned long *pa)
-{
-	struct vop_device *vpdev = vdev->vpdev;
-	unsigned long start = MIC_DP_SIZE;
-	int i;
-
-	/*
-	 * MMAP interface is as follows:
-	 * offset				region
-	 * 0x0					virtio device_page
-	 * 0x1000				first vring
-	 * 0x1000 + size of 1st vring		second vring
-	 * ....
-	 */
-	if (!offset) {
-		*pa = virt_to_phys(vpdev->hw_ops->get_dp(vpdev));
-		*size = MIC_DP_SIZE;
-		return 0;
-	}
-
-	for (i = 0; i < vdev->dd->num_vq; i++) {
-		struct vop_vringh *vvr = &vdev->vvr[i];
-
-		if (offset == start) {
-			*pa = virt_to_phys(vvr->vring.va);
-			*size = vvr->vring.len;
-			return 0;
-		}
-		start += vvr->vring.len;
-	}
-	return -1;
-}
-
-/*
- * Maps the device page and virtio rings to user space for readonly access.
- */
-static int vop_mmap(struct file *f, struct vm_area_struct *vma)
-{
-	struct vop_vdev *vdev = f->private_data;
-	unsigned long offset = vma->vm_pgoff << PAGE_SHIFT;
-	unsigned long pa, size = vma->vm_end - vma->vm_start, size_rem = size;
-	int i, err;
-
-	err = vop_vdev_inited(vdev);
-	if (err)
-		goto ret;
-	if (vma->vm_flags & VM_WRITE) {
-		err = -EACCES;
-		goto ret;
-	}
-	while (size_rem) {
-		i = vop_query_offset(vdev, offset, &size, &pa);
-		if (i < 0) {
-			err = -EINVAL;
-			goto ret;
-		}
-		err = remap_pfn_range(vma, vma->vm_start + offset,
-				      pa >> PAGE_SHIFT, size,
-				      vma->vm_page_prot);
-		if (err)
-			goto ret;
-		size_rem -= size;
-		offset += size;
-	}
-ret:
-	return err;
-}
-
-static const struct file_operations vop_fops = {
-	.open = vop_open,
-	.release = vop_release,
-	.unlocked_ioctl = vop_ioctl,
-	.poll = vop_poll,
-	.mmap = vop_mmap,
-	.owner = THIS_MODULE,
-};
-
-int vop_host_init(struct vop_info *vi)
-{
-	int rc;
-	struct miscdevice *mdev;
-	struct vop_device *vpdev = vi->vpdev;
-
-	INIT_LIST_HEAD(&vi->vdev_list);
-	vi->dma_ch = vpdev->dma_ch;
-	mdev = &vi->miscdev;
-	mdev->minor = MISC_DYNAMIC_MINOR;
-	snprintf(vi->name, sizeof(vi->name), "vop_virtio%d", vpdev->index);
-	mdev->name = vi->name;
-	mdev->fops = &vop_fops;
-	mdev->parent = &vpdev->dev;
-
-	rc = misc_register(mdev);
-	if (rc)
-		dev_err(&vpdev->dev, "%s failed rc %d\n", __func__, rc);
-	return rc;
-}
-
-void vop_host_uninit(struct vop_info *vi)
-{
-	struct list_head *pos, *tmp;
-	struct vop_vdev *vdev;
-
-	mutex_lock(&vi->vop_mutex);
-	vop_virtio_reset_devices(vi);
-	list_for_each_safe(pos, tmp, &vi->vdev_list) {
-		vdev = list_entry(pos, struct vop_vdev, list);
-		list_del(pos);
-		reinit_completion(&vdev->destroy);
-		mutex_unlock(&vi->vop_mutex);
-		mutex_lock(&vdev->vdev_mutex);
-		vop_virtio_del_device(vdev);
-		vdev->deleted = true;
-		mutex_unlock(&vdev->vdev_mutex);
-		complete(&vdev->destroy);
-		mutex_lock(&vi->vop_mutex);
-	}
-	mutex_unlock(&vi->vop_mutex);
-	misc_deregister(&vi->miscdev);
-}
diff --git a/include/linux/mic_bus.h b/include/linux/mic_bus.h
deleted file mode 100644
index e99c789424e0..000000000000
--- a/include/linux/mic_bus.h
+++ /dev/null
@@ -1,100 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel MIC Bus driver.
- *
- * This implementation is very similar to the virtio bus driver
- * implementation @ include/linux/virtio.h.
- */
-#ifndef _MIC_BUS_H_
-#define _MIC_BUS_H_
-/*
- * Everything a mbus driver needs to work with any particular mbus
- * implementation.
- */
-#include <linux/interrupt.h>
-#include <linux/dma-mapping.h>
-
-struct mbus_device_id {
-	__u32 device;
-	__u32 vendor;
-};
-
-#define MBUS_DEV_DMA_HOST 2
-#define MBUS_DEV_DMA_MIC 3
-#define MBUS_DEV_ANY_ID 0xffffffff
-
-/**
- * mbus_device - representation of a device using mbus
- * @mmio_va: virtual address of mmio space
- * @hw_ops: the hardware ops supported by this device.
- * @id: the device type identification (used to match it with a driver).
- * @dev: underlying device.
- * be used to communicate with.
- * @index: unique position on the mbus bus
- */
-struct mbus_device {
-	void __iomem *mmio_va;
-	struct mbus_hw_ops *hw_ops;
-	struct mbus_device_id id;
-	struct device dev;
-	int index;
-};
-
-/**
- * mbus_driver - operations for a mbus I/O driver
- * @driver: underlying device driver (populate name and owner).
- * @id_table: the ids serviced by this driver.
- * @probe: the function to call when a device is found.  Returns 0 or -errno.
- * @remove: the function to call when a device is removed.
- */
-struct mbus_driver {
-	struct device_driver driver;
-	const struct mbus_device_id *id_table;
-	int (*probe)(struct mbus_device *dev);
-	void (*scan)(struct mbus_device *dev);
-	void (*remove)(struct mbus_device *dev);
-};
-
-/**
- * struct mic_irq - opaque pointer used as cookie
- */
-struct mic_irq;
-
-/**
- * mbus_hw_ops - Hardware operations for accessing a MIC device on the MIC bus.
- */
-struct mbus_hw_ops {
-	struct mic_irq* (*request_threaded_irq)(struct mbus_device *mbdev,
-						irq_handler_t handler,
-						irq_handler_t thread_fn,
-						const char *name, void *data,
-						int intr_src);
-	void (*free_irq)(struct mbus_device *mbdev,
-			 struct mic_irq *cookie, void *data);
-	void (*ack_interrupt)(struct mbus_device *mbdev, int num);
-};
-
-struct mbus_device *
-mbus_register_device(struct device *pdev, int id, const struct dma_map_ops *dma_ops,
-		     struct mbus_hw_ops *hw_ops, int index,
-		     void __iomem *mmio_va);
-void mbus_unregister_device(struct mbus_device *mbdev);
-
-int mbus_register_driver(struct mbus_driver *drv);
-void mbus_unregister_driver(struct mbus_driver *drv);
-
-static inline struct mbus_device *dev_to_mbus(struct device *_dev)
-{
-	return container_of(_dev, struct mbus_device, dev);
-}
-
-static inline struct mbus_driver *drv_to_mbus(struct device_driver *drv)
-{
-	return container_of(drv, struct mbus_driver, driver);
-}
-
-#endif /* _MIC_BUS_H */
diff --git a/include/linux/scif.h b/include/linux/scif.h
deleted file mode 100644
index 329e695b8fe5..000000000000
--- a/include/linux/scif.h
+++ /dev/null
@@ -1,1339 +0,0 @@
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * This file is provided under a dual BSD/GPLv2 license.  When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * BSD LICENSE
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- *   notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- *   notice, this list of conditions and the following disclaimer in
- *   the documentation and/or other materials provided with the
- *   distribution.
- * * Neither the name of Intel Corporation nor the names of its
- *   contributors may be used to endorse or promote products derived
- *   from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * Intel SCIF driver.
- *
- */
-#ifndef __SCIF_H__
-#define __SCIF_H__
-
-#include <linux/types.h>
-#include <linux/poll.h>
-#include <linux/device.h>
-#include <linux/scif_ioctl.h>
-
-#define SCIF_ACCEPT_SYNC	1
-#define SCIF_SEND_BLOCK		1
-#define SCIF_RECV_BLOCK		1
-
-enum {
-	SCIF_PROT_READ = (1 << 0),
-	SCIF_PROT_WRITE = (1 << 1)
-};
-
-enum {
-	SCIF_MAP_FIXED = 0x10,
-	SCIF_MAP_KERNEL	= 0x20,
-};
-
-enum {
-	SCIF_FENCE_INIT_SELF = (1 << 0),
-	SCIF_FENCE_INIT_PEER = (1 << 1),
-	SCIF_SIGNAL_LOCAL = (1 << 4),
-	SCIF_SIGNAL_REMOTE = (1 << 5)
-};
-
-enum {
-	SCIF_RMA_USECPU = (1 << 0),
-	SCIF_RMA_USECACHE = (1 << 1),
-	SCIF_RMA_SYNC = (1 << 2),
-	SCIF_RMA_ORDERED = (1 << 3)
-};
-
-/* End of SCIF Admin Reserved Ports */
-#define SCIF_ADMIN_PORT_END	1024
-
-/* End of SCIF Reserved Ports */
-#define SCIF_PORT_RSVD		1088
-
-typedef struct scif_endpt *scif_epd_t;
-typedef struct scif_pinned_pages *scif_pinned_pages_t;
-
-/**
- * struct scif_range - SCIF registered range used in kernel mode
- * @cookie: cookie used internally by SCIF
- * @nr_pages: number of pages of PAGE_SIZE
- * @prot_flags: R/W protection
- * @phys_addr: Array of bus addresses
- * @va: Array of kernel virtual addresses backed by the pages in the phys_addr
- *	array. The va is populated only when called on the host for a remote
- *	SCIF connection on MIC. This is required to support the use case of DMA
- *	between MIC and another device which is not a SCIF node e.g., an IB or
- *	ethernet NIC.
- */
-struct scif_range {
-	void *cookie;
-	int nr_pages;
-	int prot_flags;
-	dma_addr_t *phys_addr;
-	void __iomem **va;
-};
-
-/**
- * struct scif_pollepd - SCIF endpoint to be monitored via scif_poll
- * @epd: SCIF endpoint
- * @events: requested events
- * @revents: returned events
- */
-struct scif_pollepd {
-	scif_epd_t epd;
-	__poll_t events;
-	__poll_t revents;
-};
-
-/**
- * scif_peer_dev - representation of a peer SCIF device
- *
- * Peer devices show up as PCIe devices for the mgmt node but not the cards.
- * The mgmt node discovers all the cards on the PCIe bus and informs the other
- * cards about their peers. Upon notification of a peer a node adds a peer
- * device to the peer bus to maintain symmetry in the way devices are
- * discovered across all nodes in the SCIF network.
- *
- * @dev: underlying device
- * @dnode - The destination node which this device will communicate with.
- */
-struct scif_peer_dev {
-	struct device dev;
-	u8 dnode;
-};
-
-/**
- * scif_client - representation of a SCIF client
- * @name: client name
- * @probe - client method called when a peer device is registered
- * @remove - client method called when a peer device is unregistered
- * @si - subsys_interface used internally for implementing SCIF clients
- */
-struct scif_client {
-	const char *name;
-	void (*probe)(struct scif_peer_dev *spdev);
-	void (*remove)(struct scif_peer_dev *spdev);
-	struct subsys_interface si;
-};
-
-#define SCIF_OPEN_FAILED ((scif_epd_t)-1)
-#define SCIF_REGISTER_FAILED ((off_t)-1)
-#define SCIF_MMAP_FAILED ((void *)-1)
-
-/**
- * scif_open() - Create an endpoint
- *
- * Return:
- * Upon successful completion, scif_open() returns an endpoint descriptor to
- * be used in subsequent SCIF functions calls to refer to that endpoint;
- * otherwise in user mode SCIF_OPEN_FAILED (that is ((scif_epd_t)-1)) is
- * returned and errno is set to indicate the error; in kernel mode a NULL
- * scif_epd_t is returned.
- *
- * Errors:
- * ENOMEM - Insufficient kernel memory was available
- */
-scif_epd_t scif_open(void);
-
-/**
- * scif_bind() - Bind an endpoint to a port
- * @epd:	endpoint descriptor
- * @pn:		port number
- *
- * scif_bind() binds endpoint epd to port pn, where pn is a port number on the
- * local node. If pn is zero, a port number greater than or equal to
- * SCIF_PORT_RSVD is assigned and returned. Each endpoint may be bound to
- * exactly one local port. Ports less than 1024 when requested can only be bound
- * by system (or root) processes or by processes executed by privileged users.
- *
- * Return:
- * Upon successful completion, scif_bind() returns the port number to which epd
- * is bound; otherwise in user mode -1 is returned and errno is set to
- * indicate the error; in kernel mode the negative of one of the following
- * errors is returned.
- *
- * Errors:
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * EINVAL - the endpoint or the port is already bound
- * EISCONN - The endpoint is already connected
- * ENOSPC - No port number available for assignment
- * EACCES - The port requested is protected and the user is not the superuser
- */
-int scif_bind(scif_epd_t epd, u16 pn);
-
-/**
- * scif_listen() - Listen for connections on an endpoint
- * @epd:	endpoint descriptor
- * @backlog:	maximum pending connection requests
- *
- * scif_listen() marks the endpoint epd as a listening endpoint - that is, as
- * an endpoint that will be used to accept incoming connection requests. Once
- * so marked, the endpoint is said to be in the listening state and may not be
- * used as the endpoint of a connection.
- *
- * The endpoint, epd, must have been bound to a port.
- *
- * The backlog argument defines the maximum length to which the queue of
- * pending connections for epd may grow. If a connection request arrives when
- * the queue is full, the client may receive an error with an indication that
- * the connection was refused.
- *
- * Return:
- * Upon successful completion, scif_listen() returns 0; otherwise in user mode
- * -1 is returned and errno is set to indicate the error; in kernel mode the
- * negative of one of the following errors is returned.
- *
- * Errors:
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * EINVAL - the endpoint is not bound to a port
- * EISCONN - The endpoint is already connected or listening
- */
-int scif_listen(scif_epd_t epd, int backlog);
-
-/**
- * scif_connect() - Initiate a connection on a port
- * @epd:	endpoint descriptor
- * @dst:	global id of port to which to connect
- *
- * The scif_connect() function requests the connection of endpoint epd to remote
- * port dst. If the connection is successful, a peer endpoint, bound to dst, is
- * created on node dst.node. On successful return, the connection is complete.
- *
- * If the endpoint epd has not already been bound to a port, scif_connect()
- * will bind it to an unused local port.
- *
- * A connection is terminated when an endpoint of the connection is closed,
- * either explicitly by scif_close(), or when a process that owns one of the
- * endpoints of the connection is terminated.
- *
- * In user space, scif_connect() supports an asynchronous connection mode
- * if the application has set the O_NONBLOCK flag on the endpoint via the
- * fcntl() system call. Setting this flag will result in the calling process
- * not to wait during scif_connect().
- *
- * Return:
- * Upon successful completion, scif_connect() returns the port ID to which the
- * endpoint, epd, is bound; otherwise in user mode -1 is returned and errno is
- * set to indicate the error; in kernel mode the negative of one of the
- * following errors is returned.
- *
- * Errors:
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNREFUSED - The destination was not listening for connections or refused
- * the connection request
- * EINVAL - dst.port is not a valid port ID
- * EISCONN - The endpoint is already connected
- * ENOMEM - No buffer space is available
- * ENODEV - The destination node does not exist, or the node is lost or existed,
- * but is not currently in the network since it may have crashed
- * ENOSPC - No port number available for assignment
- * EOPNOTSUPP - The endpoint is listening and cannot be connected
- */
-int scif_connect(scif_epd_t epd, struct scif_port_id *dst);
-
-/**
- * scif_accept() - Accept a connection on an endpoint
- * @epd:	endpoint descriptor
- * @peer:	global id of port to which connected
- * @newepd:	new connected endpoint descriptor
- * @flags:	flags
- *
- * The scif_accept() call extracts the first connection request from the queue
- * of pending connections for the port on which epd is listening. scif_accept()
- * creates a new endpoint, bound to the same port as epd, and allocates a new
- * SCIF endpoint descriptor, returned in newepd, for the endpoint. The new
- * endpoint is connected to the endpoint through which the connection was
- * requested. epd is unaffected by this call, and remains in the listening
- * state.
- *
- * On successful return, peer holds the global port identifier (node id and
- * local port number) of the port which requested the connection.
- *
- * A connection is terminated when an endpoint of the connection is closed,
- * either explicitly by scif_close(), or when a process that owns one of the
- * endpoints of the connection is terminated.
- *
- * The number of connections that can (subsequently) be accepted on epd is only
- * limited by system resources (memory).
- *
- * The flags argument is formed by OR'ing together zero or more of the
- * following values.
- * SCIF_ACCEPT_SYNC - block until a connection request is presented. If
- *			SCIF_ACCEPT_SYNC is not in flags, and no pending
- *			connections are present on the queue, scif_accept()
- *			fails with an EAGAIN error
- *
- * In user mode, the select() and poll() functions can be used to determine
- * when there is a connection request. In kernel mode, the scif_poll()
- * function may be used for this purpose. A readable event will be delivered
- * when a connection is requested.
- *
- * Return:
- * Upon successful completion, scif_accept() returns 0; otherwise in user mode
- * -1 is returned and errno is set to indicate the error; in kernel mode the
- *	negative of one of the following errors is returned.
- *
- * Errors:
- * EAGAIN - SCIF_ACCEPT_SYNC is not set and no connections are present to be
- * accepted or SCIF_ACCEPT_SYNC is not set and remote node failed to complete
- * its connection request
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * EINTR - Interrupted function
- * EINVAL - epd is not a listening endpoint, or flags is invalid, or peer is
- * NULL, or newepd is NULL
- * ENODEV - The requesting node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOMEM - Not enough space
- * ENOENT - Secondary part of epd registration failed
- */
-int scif_accept(scif_epd_t epd, struct scif_port_id *peer, scif_epd_t
-		*newepd, int flags);
-
-/**
- * scif_close() - Close an endpoint
- * @epd:	endpoint descriptor
- *
- * scif_close() closes an endpoint and performs necessary teardown of
- * facilities associated with that endpoint.
- *
- * If epd is a listening endpoint then it will no longer accept connection
- * requests on the port to which it is bound. Any pending connection requests
- * are rejected.
- *
- * If epd is a connected endpoint, then its peer endpoint is also closed. RMAs
- * which are in-process through epd or its peer endpoint will complete before
- * scif_close() returns. Registered windows of the local and peer endpoints are
- * released as if scif_unregister() was called against each window.
- *
- * Closing a SCIF endpoint does not affect local registered memory mapped by
- * a SCIF endpoint on a remote node. The local memory remains mapped by the peer
- * SCIF endpoint explicitly removed by calling munmap(..) by the peer.
- *
- * If the peer endpoint's receive queue is not empty at the time that epd is
- * closed, then the peer endpoint can be passed as the endpoint parameter to
- * scif_recv() until the receive queue is empty.
- *
- * epd is freed and may no longer be accessed.
- *
- * Return:
- * Upon successful completion, scif_close() returns 0; otherwise in user mode
- * -1 is returned and errno is set to indicate the error; in kernel mode the
- * negative of one of the following errors is returned.
- *
- * Errors:
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- */
-int scif_close(scif_epd_t epd);
-
-/**
- * scif_send() - Send a message
- * @epd:	endpoint descriptor
- * @msg:	message buffer address
- * @len:	message length
- * @flags:	blocking mode flags
- *
- * scif_send() sends data to the peer of endpoint epd. Up to len bytes of data
- * are copied from memory starting at address msg. On successful execution the
- * return value of scif_send() is the number of bytes that were sent, and is
- * zero if no bytes were sent because len was zero. scif_send() may be called
- * only when the endpoint is in a connected state.
- *
- * If a scif_send() call is non-blocking, then it sends only those bytes which
- * can be sent without waiting, up to a maximum of len bytes.
- *
- * If a scif_send() call is blocking, then it normally returns after sending
- * all len bytes. If a blocking call is interrupted or the connection is
- * reset, the call is considered successful if some bytes were sent or len is
- * zero, otherwise the call is considered unsuccessful.
- *
- * In user mode, the select() and poll() functions can be used to determine
- * when the send queue is not full. In kernel mode, the scif_poll() function
- * may be used for this purpose.
- *
- * It is recommended that scif_send()/scif_recv() only be used for short
- * control-type message communication between SCIF endpoints. The SCIF RMA
- * APIs are expected to provide better performance for transfer sizes of
- * 1024 bytes or longer for the current MIC hardware and software
- * implementation.
- *
- * scif_send() will block until the entire message is sent if SCIF_SEND_BLOCK
- * is passed as the flags argument.
- *
- * Return:
- * Upon successful completion, scif_send() returns the number of bytes sent;
- * otherwise in user mode -1 is returned and errno is set to indicate the
- * error; in kernel mode the negative of one of the following errors is
- * returned.
- *
- * Errors:
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNRESET - Connection reset by peer
- * EINVAL - flags is invalid, or len is negative
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOMEM - Not enough space
- * ENOTCONN - The endpoint is not connected
- */
-int scif_send(scif_epd_t epd, void *msg, int len, int flags);
-
-/**
- * scif_recv() - Receive a message
- * @epd:	endpoint descriptor
- * @msg:	message buffer address
- * @len:	message buffer length
- * @flags:	blocking mode flags
- *
- * scif_recv() receives data from the peer of endpoint epd. Up to len bytes of
- * data are copied to memory starting at address msg. On successful execution
- * the return value of scif_recv() is the number of bytes that were received,
- * and is zero if no bytes were received because len was zero. scif_recv() may
- * be called only when the endpoint is in a connected state.
- *
- * If a scif_recv() call is non-blocking, then it receives only those bytes
- * which can be received without waiting, up to a maximum of len bytes.
- *
- * If a scif_recv() call is blocking, then it normally returns after receiving
- * all len bytes. If the blocking call was interrupted due to a disconnection,
- * subsequent calls to scif_recv() will copy all bytes received upto the point
- * of disconnection.
- *
- * In user mode, the select() and poll() functions can be used to determine
- * when data is available to be received. In kernel mode, the scif_poll()
- * function may be used for this purpose.
- *
- * It is recommended that scif_send()/scif_recv() only be used for short
- * control-type message communication between SCIF endpoints. The SCIF RMA
- * APIs are expected to provide better performance for transfer sizes of
- * 1024 bytes or longer for the current MIC hardware and software
- * implementation.
- *
- * scif_recv() will block until the entire message is received if
- * SCIF_RECV_BLOCK is passed as the flags argument.
- *
- * Return:
- * Upon successful completion, scif_recv() returns the number of bytes
- * received; otherwise in user mode -1 is returned and errno is set to
- * indicate the error; in kernel mode the negative of one of the following
- * errors is returned.
- *
- * Errors:
- * EAGAIN - The destination node is returning from a low power state
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNRESET - Connection reset by peer
- * EINVAL - flags is invalid, or len is negative
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOMEM - Not enough space
- * ENOTCONN - The endpoint is not connected
- */
-int scif_recv(scif_epd_t epd, void *msg, int len, int flags);
-
-/**
- * scif_register() - Mark a memory region for remote access.
- * @epd:		endpoint descriptor
- * @addr:		starting virtual address
- * @len:		length of range
- * @offset:		offset of window
- * @prot_flags:		read/write protection flags
- * @map_flags:		mapping flags
- *
- * The scif_register() function opens a window, a range of whole pages of the
- * registered address space of the endpoint epd, starting at offset po and
- * continuing for len bytes. The value of po, further described below, is a
- * function of the parameters offset and len, and the value of map_flags. Each
- * page of the window represents the physical memory page which backs the
- * corresponding page of the range of virtual address pages starting at addr
- * and continuing for len bytes. addr and len are constrained to be multiples
- * of the page size. A successful scif_register() call returns po.
- *
- * When SCIF_MAP_FIXED is set in the map_flags argument, po will be offset
- * exactly, and offset is constrained to be a multiple of the page size. The
- * mapping established by scif_register() will not replace any existing
- * registration; an error is returned if any page within the range [offset,
- * offset + len - 1] intersects an existing window.
- *
- * When SCIF_MAP_FIXED is not set, the implementation uses offset in an
- * implementation-defined manner to arrive at po. The po value so chosen will
- * be an area of the registered address space that the implementation deems
- * suitable for a mapping of len bytes. An offset value of 0 is interpreted as
- * granting the implementation complete freedom in selecting po, subject to
- * constraints described below. A non-zero value of offset is taken to be a
- * suggestion of an offset near which the mapping should be placed. When the
- * implementation selects a value for po, it does not replace any extant
- * window. In all cases, po will be a multiple of the page size.
- *
- * The physical pages which are so represented by a window are available for
- * access in calls to mmap(), scif_readfrom(), scif_writeto(),
- * scif_vreadfrom(), and scif_vwriteto(). While a window is registered, the
- * physical pages represented by the window will not be reused by the memory
- * subsystem for any other purpose. Note that the same physical page may be
- * represented by multiple windows.
- *
- * Subsequent operations which change the memory pages to which virtual
- * addresses are mapped (such as mmap(), munmap()) have no effect on
- * existing window.
- *
- * If the process will fork(), it is recommended that the registered
- * virtual address range be marked with MADV_DONTFORK. Doing so will prevent
- * problems due to copy-on-write semantics.
- *
- * The prot_flags argument is formed by OR'ing together one or more of the
- * following values.
- * SCIF_PROT_READ - allow read operations from the window
- * SCIF_PROT_WRITE - allow write operations to the window
- *
- * Return:
- * Upon successful completion, scif_register() returns the offset at which the
- * mapping was placed (po); otherwise in user mode SCIF_REGISTER_FAILED (that
- * is (off_t *)-1) is returned and errno is set to indicate the error; in
- * kernel mode the negative of one of the following errors is returned.
- *
- * Errors:
- * EADDRINUSE - SCIF_MAP_FIXED is set in map_flags, and pages in the range
- * [offset, offset + len -1] are already registered
- * EAGAIN - The mapping could not be performed due to lack of resources
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNRESET - Connection reset by peer
- * EINVAL - map_flags is invalid, or prot_flags is invalid, or SCIF_MAP_FIXED is
- * set in flags, and offset is not a multiple of the page size, or addr is not a
- * multiple of the page size, or len is not a multiple of the page size, or is
- * 0, or offset is negative
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOMEM - Not enough space
- * ENOTCONN -The endpoint is not connected
- */
-off_t scif_register(scif_epd_t epd, void *addr, size_t len, off_t offset,
-		    int prot_flags, int map_flags);
-
-/**
- * scif_unregister() - Mark a memory region for remote access.
- * @epd:	endpoint descriptor
- * @offset:	start of range to unregister
- * @len:	length of range to unregister
- *
- * The scif_unregister() function closes those previously registered windows
- * which are entirely within the range [offset, offset + len - 1]. It is an
- * error to specify a range which intersects only a subrange of a window.
- *
- * On a successful return, pages within the window may no longer be specified
- * in calls to mmap(), scif_readfrom(), scif_writeto(), scif_vreadfrom(),
- * scif_vwriteto(), scif_get_pages, and scif_fence_signal(). The window,
- * however, continues to exist until all previous references against it are
- * removed. A window is referenced if there is a mapping to it created by
- * mmap(), or if scif_get_pages() was called against the window
- * (and the pages have not been returned via scif_put_pages()). A window is
- * also referenced while an RMA, in which some range of the window is a source
- * or destination, is in progress. Finally a window is referenced while some
- * offset in that window was specified to scif_fence_signal(), and the RMAs
- * marked by that call to scif_fence_signal() have not completed. While a
- * window is in this state, its registered address space pages are not
- * available for use in a new registered window.
- *
- * When all such references to the window have been removed, its references to
- * all the physical pages which it represents are removed. Similarly, the
- * registered address space pages of the window become available for
- * registration in a new window.
- *
- * Return:
- * Upon successful completion, scif_unregister() returns 0; otherwise in user
- * mode -1 is returned and errno is set to indicate the error; in kernel mode
- * the negative of one of the following errors is returned. In the event of an
- * error, no windows are unregistered.
- *
- * Errors:
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNRESET - Connection reset by peer
- * EINVAL - the range [offset, offset + len - 1] intersects a subrange of a
- * window, or offset is negative
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOTCONN - The endpoint is not connected
- * ENXIO - Offsets in the range [offset, offset + len - 1] are invalid for the
- * registered address space of epd
- */
-int scif_unregister(scif_epd_t epd, off_t offset, size_t len);
-
-/**
- * scif_readfrom() - Copy from a remote address space
- * @epd:	endpoint descriptor
- * @loffset:	offset in local registered address space to
- *		which to copy
- * @len:	length of range to copy
- * @roffset:	offset in remote registered address space
- *		from which to copy
- * @rma_flags:	transfer mode flags
- *
- * scif_readfrom() copies len bytes from the remote registered address space of
- * the peer of endpoint epd, starting at the offset roffset to the local
- * registered address space of epd, starting at the offset loffset.
- *
- * Each of the specified ranges [loffset, loffset + len - 1] and [roffset,
- * roffset + len - 1] must be within some registered window or windows of the
- * local and remote nodes. A range may intersect multiple registered windows,
- * but only if those windows are contiguous in the registered address space.
- *
- * If rma_flags includes SCIF_RMA_USECPU, then the data is copied using
- * programmed read/writes. Otherwise the data is copied using DMA. If rma_-
- * flags includes SCIF_RMA_SYNC, then scif_readfrom() will return after the
- * transfer is complete. Otherwise, the transfer may be performed asynchron-
- * ously. The order in which any two asynchronous RMA operations complete
- * is non-deterministic. The synchronization functions, scif_fence_mark()/
- * scif_fence_wait() and scif_fence_signal(), can be used to synchronize to
- * the completion of asynchronous RMA operations on the same endpoint.
- *
- * The DMA transfer of individual bytes is not guaranteed to complete in
- * address order. If rma_flags includes SCIF_RMA_ORDERED, then the last
- * cacheline or partial cacheline of the source range will become visible on
- * the destination node after all other transferred data in the source
- * range has become visible on the destination node.
- *
- * The optimal DMA performance will likely be realized if both
- * loffset and roffset are cacheline aligned (are a multiple of 64). Lower
- * performance will likely be realized if loffset and roffset are not
- * cacheline aligned but are separated by some multiple of 64. The lowest level
- * of performance is likely if loffset and roffset are not separated by a
- * multiple of 64.
- *
- * The rma_flags argument is formed by ORing together zero or more of the
- * following values.
- * SCIF_RMA_USECPU - perform the transfer using the CPU, otherwise use the DMA
- *	engine.
- * SCIF_RMA_SYNC - perform the transfer synchronously, returning after the
- *		transfer has completed. Passing this flag results in the
- *		current implementation busy waiting and consuming CPU cycles
- *		while the DMA transfer is in progress for best performance by
- *		avoiding the interrupt latency.
- * SCIF_RMA_ORDERED - ensure that the last cacheline or partial cacheline of
- *		the source range becomes visible on the destination node
- *		after all other transferred data in the source range has
- *		become visible on the destination
- *
- * Return:
- * Upon successful completion, scif_readfrom() returns 0; otherwise in user
- * mode -1 is returned and errno is set to indicate the error; in kernel mode
- * the negative of one of the following errors is returned.
- *
- * Errors:
- * EACCES - Attempt to write to a read-only range
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNRESET - Connection reset by peer
- * EINVAL - rma_flags is invalid
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOTCONN - The endpoint is not connected
- * ENXIO - The range [loffset, loffset + len - 1] is invalid for the registered
- * address space of epd, or, The range [roffset, roffset + len - 1] is invalid
- * for the registered address space of the peer of epd, or loffset or roffset
- * is negative
- */
-int scif_readfrom(scif_epd_t epd, off_t loffset, size_t len, off_t
-		  roffset, int rma_flags);
-
-/**
- * scif_writeto() - Copy to a remote address space
- * @epd:	endpoint descriptor
- * @loffset:	offset in local registered address space
- *		from which to copy
- * @len:	length of range to copy
- * @roffset:	offset in remote registered address space to
- *		which to copy
- * @rma_flags:	transfer mode flags
- *
- * scif_writeto() copies len bytes from the local registered address space of
- * epd, starting at the offset loffset to the remote registered address space
- * of the peer of endpoint epd, starting at the offset roffset.
- *
- * Each of the specified ranges [loffset, loffset + len - 1] and [roffset,
- * roffset + len - 1] must be within some registered window or windows of the
- * local and remote nodes. A range may intersect multiple registered windows,
- * but only if those windows are contiguous in the registered address space.
- *
- * If rma_flags includes SCIF_RMA_USECPU, then the data is copied using
- * programmed read/writes. Otherwise the data is copied using DMA. If rma_-
- * flags includes SCIF_RMA_SYNC, then scif_writeto() will return after the
- * transfer is complete. Otherwise, the transfer may be performed asynchron-
- * ously. The order in which any two asynchronous RMA operations complete
- * is non-deterministic. The synchronization functions, scif_fence_mark()/
- * scif_fence_wait() and scif_fence_signal(), can be used to synchronize to
- * the completion of asynchronous RMA operations on the same endpoint.
- *
- * The DMA transfer of individual bytes is not guaranteed to complete in
- * address order. If rma_flags includes SCIF_RMA_ORDERED, then the last
- * cacheline or partial cacheline of the source range will become visible on
- * the destination node after all other transferred data in the source
- * range has become visible on the destination node.
- *
- * The optimal DMA performance will likely be realized if both
- * loffset and roffset are cacheline aligned (are a multiple of 64). Lower
- * performance will likely be realized if loffset and roffset are not cacheline
- * aligned but are separated by some multiple of 64. The lowest level of
- * performance is likely if loffset and roffset are not separated by a multiple
- * of 64.
- *
- * The rma_flags argument is formed by ORing together zero or more of the
- * following values.
- * SCIF_RMA_USECPU - perform the transfer using the CPU, otherwise use the DMA
- *			engine.
- * SCIF_RMA_SYNC - perform the transfer synchronously, returning after the
- *		transfer has completed. Passing this flag results in the
- *		current implementation busy waiting and consuming CPU cycles
- *		while the DMA transfer is in progress for best performance by
- *		avoiding the interrupt latency.
- * SCIF_RMA_ORDERED - ensure that the last cacheline or partial cacheline of
- *		the source range becomes visible on the destination node
- *		after all other transferred data in the source range has
- *		become visible on the destination
- *
- * Return:
- * Upon successful completion, scif_readfrom() returns 0; otherwise in user
- * mode -1 is returned and errno is set to indicate the error; in kernel mode
- * the negative of one of the following errors is returned.
- *
- * Errors:
- * EACCES - Attempt to write to a read-only range
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNRESET - Connection reset by peer
- * EINVAL - rma_flags is invalid
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOTCONN - The endpoint is not connected
- * ENXIO - The range [loffset, loffset + len - 1] is invalid for the registered
- * address space of epd, or, The range [roffset , roffset + len -1] is invalid
- * for the registered address space of the peer of epd, or loffset or roffset
- * is negative
- */
-int scif_writeto(scif_epd_t epd, off_t loffset, size_t len, off_t
-		 roffset, int rma_flags);
-
-/**
- * scif_vreadfrom() - Copy from a remote address space
- * @epd:	endpoint descriptor
- * @addr:	address to which to copy
- * @len:	length of range to copy
- * @roffset:	offset in remote registered address space
- *		from which to copy
- * @rma_flags:	transfer mode flags
- *
- * scif_vreadfrom() copies len bytes from the remote registered address
- * space of the peer of endpoint epd, starting at the offset roffset, to local
- * memory, starting at addr.
- *
- * The specified range [roffset, roffset + len - 1] must be within some
- * registered window or windows of the remote nodes. The range may
- * intersect multiple registered windows, but only if those windows are
- * contiguous in the registered address space.
- *
- * If rma_flags includes SCIF_RMA_USECPU, then the data is copied using
- * programmed read/writes. Otherwise the data is copied using DMA. If rma_-
- * flags includes SCIF_RMA_SYNC, then scif_vreadfrom() will return after the
- * transfer is complete. Otherwise, the transfer may be performed asynchron-
- * ously. The order in which any two asynchronous RMA operations complete
- * is non-deterministic. The synchronization functions, scif_fence_mark()/
- * scif_fence_wait() and scif_fence_signal(), can be used to synchronize to
- * the completion of asynchronous RMA operations on the same endpoint.
- *
- * The DMA transfer of individual bytes is not guaranteed to complete in
- * address order. If rma_flags includes SCIF_RMA_ORDERED, then the last
- * cacheline or partial cacheline of the source range will become visible on
- * the destination node after all other transferred data in the source
- * range has become visible on the destination node.
- *
- * If rma_flags includes SCIF_RMA_USECACHE, then the physical pages which back
- * the specified local memory range may be remain in a pinned state even after
- * the specified transfer completes. This may reduce overhead if some or all of
- * the same virtual address range is referenced in a subsequent call of
- * scif_vreadfrom() or scif_vwriteto().
- *
- * The optimal DMA performance will likely be realized if both
- * addr and roffset are cacheline aligned (are a multiple of 64). Lower
- * performance will likely be realized if addr and roffset are not
- * cacheline aligned but are separated by some multiple of 64. The lowest level
- * of performance is likely if addr and roffset are not separated by a
- * multiple of 64.
- *
- * The rma_flags argument is formed by ORing together zero or more of the
- * following values.
- * SCIF_RMA_USECPU - perform the transfer using the CPU, otherwise use the DMA
- *	engine.
- * SCIF_RMA_USECACHE - enable registration caching
- * SCIF_RMA_SYNC - perform the transfer synchronously, returning after the
- *		transfer has completed. Passing this flag results in the
- *		current implementation busy waiting and consuming CPU cycles
- *		while the DMA transfer is in progress for best performance by
- *		avoiding the interrupt latency.
- * SCIF_RMA_ORDERED - ensure that the last cacheline or partial cacheline of
- *	the source range becomes visible on the destination node
- *	after all other transferred data in the source range has
- *	become visible on the destination
- *
- * Return:
- * Upon successful completion, scif_vreadfrom() returns 0; otherwise in user
- * mode -1 is returned and errno is set to indicate the error; in kernel mode
- * the negative of one of the following errors is returned.
- *
- * Errors:
- * EACCES - Attempt to write to a read-only range
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNRESET - Connection reset by peer
- * EINVAL - rma_flags is invalid
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOTCONN - The endpoint is not connected
- * ENXIO - Offsets in the range [roffset, roffset + len - 1] are invalid for the
- * registered address space of epd
- */
-int scif_vreadfrom(scif_epd_t epd, void *addr, size_t len, off_t roffset,
-		   int rma_flags);
-
-/**
- * scif_vwriteto() - Copy to a remote address space
- * @epd:	endpoint descriptor
- * @addr:	address from which to copy
- * @len:	length of range to copy
- * @roffset:	offset in remote registered address space to
- *		which to copy
- * @rma_flags:	transfer mode flags
- *
- * scif_vwriteto() copies len bytes from the local memory, starting at addr, to
- * the remote registered address space of the peer of endpoint epd, starting at
- * the offset roffset.
- *
- * The specified range [roffset, roffset + len - 1] must be within some
- * registered window or windows of the remote nodes. The range may intersect
- * multiple registered windows, but only if those windows are contiguous in the
- * registered address space.
- *
- * If rma_flags includes SCIF_RMA_USECPU, then the data is copied using
- * programmed read/writes. Otherwise the data is copied using DMA. If rma_-
- * flags includes SCIF_RMA_SYNC, then scif_vwriteto() will return after the
- * transfer is complete. Otherwise, the transfer may be performed asynchron-
- * ously. The order in which any two asynchronous RMA operations complete
- * is non-deterministic. The synchronization functions, scif_fence_mark()/
- * scif_fence_wait() and scif_fence_signal(), can be used to synchronize to
- * the completion of asynchronous RMA operations on the same endpoint.
- *
- * The DMA transfer of individual bytes is not guaranteed to complete in
- * address order. If rma_flags includes SCIF_RMA_ORDERED, then the last
- * cacheline or partial cacheline of the source range will become visible on
- * the destination node after all other transferred data in the source
- * range has become visible on the destination node.
- *
- * If rma_flags includes SCIF_RMA_USECACHE, then the physical pages which back
- * the specified local memory range may be remain in a pinned state even after
- * the specified transfer completes. This may reduce overhead if some or all of
- * the same virtual address range is referenced in a subsequent call of
- * scif_vreadfrom() or scif_vwriteto().
- *
- * The optimal DMA performance will likely be realized if both
- * addr and offset are cacheline aligned (are a multiple of 64). Lower
- * performance will likely be realized if addr and offset are not cacheline
- * aligned but are separated by some multiple of 64. The lowest level of
- * performance is likely if addr and offset are not separated by a multiple of
- * 64.
- *
- * The rma_flags argument is formed by ORing together zero or more of the
- * following values.
- * SCIF_RMA_USECPU - perform the transfer using the CPU, otherwise use the DMA
- *	engine.
- * SCIF_RMA_USECACHE - allow registration caching
- * SCIF_RMA_SYNC - perform the transfer synchronously, returning after the
- *		transfer has completed. Passing this flag results in the
- *		current implementation busy waiting and consuming CPU cycles
- *		while the DMA transfer is in progress for best performance by
- *		avoiding the interrupt latency.
- * SCIF_RMA_ORDERED - ensure that the last cacheline or partial cacheline of
- *		the source range becomes visible on the destination node
- *		after all other transferred data in the source range has
- *		become visible on the destination
- *
- * Return:
- * Upon successful completion, scif_vwriteto() returns 0; otherwise in user
- * mode -1 is returned and errno is set to indicate the error; in kernel mode
- * the negative of one of the following errors is returned.
- *
- * Errors:
- * EACCES - Attempt to write to a read-only range
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNRESET - Connection reset by peer
- * EINVAL - rma_flags is invalid
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOTCONN - The endpoint is not connected
- * ENXIO - Offsets in the range [roffset, roffset + len - 1] are invalid for the
- * registered address space of epd
- */
-int scif_vwriteto(scif_epd_t epd, void *addr, size_t len, off_t roffset,
-		  int rma_flags);
-
-/**
- * scif_fence_mark() - Mark previously issued RMAs
- * @epd:	endpoint descriptor
- * @flags:	control flags
- * @mark:	marked value returned as output.
- *
- * scif_fence_mark() returns after marking the current set of all uncompleted
- * RMAs initiated through the endpoint epd or the current set of all
- * uncompleted RMAs initiated through the peer of endpoint epd. The RMAs are
- * marked with a value returned at mark. The application may subsequently call
- * scif_fence_wait(), passing the value returned at mark, to await completion
- * of all RMAs so marked.
- *
- * The flags argument has exactly one of the following values.
- * SCIF_FENCE_INIT_SELF - RMA operations initiated through endpoint
- *	epd are marked
- * SCIF_FENCE_INIT_PEER - RMA operations initiated through the peer
- *	of endpoint epd are marked
- *
- * Return:
- * Upon successful completion, scif_fence_mark() returns 0; otherwise in user
- * mode -1 is returned and errno is set to indicate the error; in kernel mode
- * the negative of one of the following errors is returned.
- *
- * Errors:
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNRESET - Connection reset by peer
- * EINVAL - flags is invalid
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOTCONN - The endpoint is not connected
- * ENOMEM - Insufficient kernel memory was available
- */
-int scif_fence_mark(scif_epd_t epd, int flags, int *mark);
-
-/**
- * scif_fence_wait() - Wait for completion of marked RMAs
- * @epd:	endpoint descriptor
- * @mark:	mark request
- *
- * scif_fence_wait() returns after all RMAs marked with mark have completed.
- * The value passed in mark must have been obtained in a previous call to
- * scif_fence_mark().
- *
- * Return:
- * Upon successful completion, scif_fence_wait() returns 0; otherwise in user
- * mode -1 is returned and errno is set to indicate the error; in kernel mode
- * the negative of one of the following errors is returned.
- *
- * Errors:
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNRESET - Connection reset by peer
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOTCONN - The endpoint is not connected
- * ENOMEM - Insufficient kernel memory was available
- */
-int scif_fence_wait(scif_epd_t epd, int mark);
-
-/**
- * scif_fence_signal() - Request a memory update on completion of RMAs
- * @epd:	endpoint descriptor
- * @loff:	local offset
- * @lval:	local value to write to loffset
- * @roff:	remote offset
- * @rval:	remote value to write to roffset
- * @flags:	flags
- *
- * scif_fence_signal() returns after marking the current set of all uncompleted
- * RMAs initiated through the endpoint epd or marking the current set of all
- * uncompleted RMAs initiated through the peer of endpoint epd.
- *
- * If flags includes SCIF_SIGNAL_LOCAL, then on completion of the RMAs in the
- * marked set, lval is written to memory at the address corresponding to offset
- * loff in the local registered address space of epd. loff must be within a
- * registered window. If flags includes SCIF_SIGNAL_REMOTE, then on completion
- * of the RMAs in the marked set, rval is written to memory at the address
- * corresponding to offset roff in the remote registered address space of epd.
- * roff must be within a remote registered window of the peer of epd. Note
- * that any specified offset must be DWORD (4 byte / 32 bit) aligned.
- *
- * The flags argument is formed by OR'ing together the following.
- * Exactly one of the following values.
- * SCIF_FENCE_INIT_SELF - RMA operations initiated through endpoint
- *	epd are marked
- * SCIF_FENCE_INIT_PEER - RMA operations initiated through the peer
- *	of endpoint epd are marked
- * One or more of the following values.
- * SCIF_SIGNAL_LOCAL - On completion of the marked set of RMAs, write lval to
- *	memory at the address corresponding to offset loff in the local
- *	registered address space of epd.
- * SCIF_SIGNAL_REMOTE - On completion of the marked set of RMAs, write rval to
- *	memory at the address corresponding to offset roff in the remote
- *	registered address space of epd.
- *
- * Return:
- * Upon successful completion, scif_fence_signal() returns 0; otherwise in
- * user mode -1 is returned and errno is set to indicate the error; in kernel
- * mode the negative of one of the following errors is returned.
- *
- * Errors:
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNRESET - Connection reset by peer
- * EINVAL - flags is invalid, or loff or roff are not DWORD aligned
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOTCONN - The endpoint is not connected
- * ENXIO - loff is invalid for the registered address of epd, or roff is invalid
- * for the registered address space, of the peer of epd
- */
-int scif_fence_signal(scif_epd_t epd, off_t loff, u64 lval, off_t roff,
-		      u64 rval, int flags);
-
-/**
- * scif_get_node_ids() - Return information about online nodes
- * @nodes:	array in which to return online node IDs
- * @len:	number of entries in the nodes array
- * @self:	address to place the node ID of the local node
- *
- * scif_get_node_ids() fills in the nodes array with up to len node IDs of the
- * nodes in the SCIF network. If there is not enough space in nodes, as
- * indicated by the len parameter, only len node IDs are returned in nodes. The
- * return value of scif_get_node_ids() is the total number of nodes currently in
- * the SCIF network. By checking the return value against the len parameter,
- * the user may determine if enough space for nodes was allocated.
- *
- * The node ID of the local node is returned at self.
- *
- * Return:
- * Upon successful completion, scif_get_node_ids() returns the actual number of
- * online nodes in the SCIF network including 'self'; otherwise in user mode
- * -1 is returned and errno is set to indicate the error; in kernel mode no
- * errors are returned.
- */
-int scif_get_node_ids(u16 *nodes, int len, u16 *self);
-
-/**
- * scif_pin_pages() - Pin a set of pages
- * @addr:		Virtual address of range to pin
- * @len:		Length of range to pin
- * @prot_flags:		Page protection flags
- * @map_flags:		Page classification flags
- * @pinned_pages:	Handle to pinned pages
- *
- * scif_pin_pages() pins (locks in physical memory) the physical pages which
- * back the range of virtual address pages starting at addr and continuing for
- * len bytes. addr and len are constrained to be multiples of the page size. A
- * successful scif_pin_pages() call returns a handle to pinned_pages which may
- * be used in subsequent calls to scif_register_pinned_pages().
- *
- * The pages will remain pinned as long as there is a reference against the
- * scif_pinned_pages_t value returned by scif_pin_pages() and until
- * scif_unpin_pages() is called, passing the scif_pinned_pages_t value. A
- * reference is added to a scif_pinned_pages_t value each time a window is
- * created by calling scif_register_pinned_pages() and passing the
- * scif_pinned_pages_t value. A reference is removed from a
- * scif_pinned_pages_t value each time such a window is deleted.
- *
- * Subsequent operations which change the memory pages to which virtual
- * addresses are mapped (such as mmap(), munmap()) have no effect on the
- * scif_pinned_pages_t value or windows created against it.
- *
- * If the process will fork(), it is recommended that the registered
- * virtual address range be marked with MADV_DONTFORK. Doing so will prevent
- * problems due to copy-on-write semantics.
- *
- * The prot_flags argument is formed by OR'ing together one or more of the
- * following values.
- * SCIF_PROT_READ - allow read operations against the pages
- * SCIF_PROT_WRITE - allow write operations against the pages
- * The map_flags argument can be set as SCIF_MAP_KERNEL to interpret addr as a
- * kernel space address. By default, addr is interpreted as a user space
- * address.
- *
- * Return:
- * Upon successful completion, scif_pin_pages() returns 0; otherwise the
- * negative of one of the following errors is returned.
- *
- * Errors:
- * EINVAL - prot_flags is invalid, map_flags is invalid, or offset is negative
- * ENOMEM - Not enough space
- */
-int scif_pin_pages(void *addr, size_t len, int prot_flags, int map_flags,
-		   scif_pinned_pages_t *pinned_pages);
-
-/**
- * scif_unpin_pages() - Unpin a set of pages
- * @pinned_pages:	Handle to pinned pages to be unpinned
- *
- * scif_unpin_pages() prevents scif_register_pinned_pages() from registering new
- * windows against pinned_pages. The physical pages represented by pinned_pages
- * will remain pinned until all windows previously registered against
- * pinned_pages are deleted (the window is scif_unregister()'d and all
- * references to the window are removed (see scif_unregister()).
- *
- * pinned_pages must have been obtain from a previous call to scif_pin_pages().
- * After calling scif_unpin_pages(), it is an error to pass pinned_pages to
- * scif_register_pinned_pages().
- *
- * Return:
- * Upon successful completion, scif_unpin_pages() returns 0; otherwise the
- * negative of one of the following errors is returned.
- *
- * Errors:
- * EINVAL - pinned_pages is not valid
- */
-int scif_unpin_pages(scif_pinned_pages_t pinned_pages);
-
-/**
- * scif_register_pinned_pages() - Mark a memory region for remote access.
- * @epd:		endpoint descriptor
- * @pinned_pages:	Handle to pinned pages
- * @offset:		Registered address space offset
- * @map_flags:		Flags which control where pages are mapped
- *
- * The scif_register_pinned_pages() function opens a window, a range of whole
- * pages of the registered address space of the endpoint epd, starting at
- * offset po. The value of po, further described below, is a function of the
- * parameters offset and pinned_pages, and the value of map_flags. Each page of
- * the window represents a corresponding physical memory page of the range
- * represented by pinned_pages; the length of the window is the same as the
- * length of range represented by pinned_pages. A successful
- * scif_register_pinned_pages() call returns po as the return value.
- *
- * When SCIF_MAP_FIXED is set in the map_flags argument, po will be offset
- * exactly, and offset is constrained to be a multiple of the page size. The
- * mapping established by scif_register_pinned_pages() will not replace any
- * existing registration; an error is returned if any page of the new window
- * would intersect an existing window.
- *
- * When SCIF_MAP_FIXED is not set, the implementation uses offset in an
- * implementation-defined manner to arrive at po. The po so chosen will be an
- * area of the registered address space that the implementation deems suitable
- * for a mapping of the required size. An offset value of 0 is interpreted as
- * granting the implementation complete freedom in selecting po, subject to
- * constraints described below. A non-zero value of offset is taken to be a
- * suggestion of an offset near which the mapping should be placed. When the
- * implementation selects a value for po, it does not replace any extant
- * window. In all cases, po will be a multiple of the page size.
- *
- * The physical pages which are so represented by a window are available for
- * access in calls to scif_get_pages(), scif_readfrom(), scif_writeto(),
- * scif_vreadfrom(), and scif_vwriteto(). While a window is registered, the
- * physical pages represented by the window will not be reused by the memory
- * subsystem for any other purpose. Note that the same physical page may be
- * represented by multiple windows.
- *
- * Windows created by scif_register_pinned_pages() are unregistered by
- * scif_unregister().
- *
- * The map_flags argument can be set to SCIF_MAP_FIXED which interprets a
- * fixed offset.
- *
- * Return:
- * Upon successful completion, scif_register_pinned_pages() returns the offset
- * at which the mapping was placed (po); otherwise the negative of one of the
- * following errors is returned.
- *
- * Errors:
- * EADDRINUSE - SCIF_MAP_FIXED is set in map_flags and pages in the new window
- * would intersect an existing window
- * EAGAIN - The mapping could not be performed due to lack of resources
- * ECONNRESET - Connection reset by peer
- * EINVAL - map_flags is invalid, or SCIF_MAP_FIXED is set in map_flags, and
- * offset is not a multiple of the page size, or offset is negative
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOMEM - Not enough space
- * ENOTCONN - The endpoint is not connected
- */
-off_t scif_register_pinned_pages(scif_epd_t epd,
-				 scif_pinned_pages_t pinned_pages,
-				 off_t offset, int map_flags);
-
-/**
- * scif_get_pages() - Add references to remote registered pages
- * @epd:	endpoint descriptor
- * @offset:	remote registered offset
- * @len:	length of range of pages
- * @pages:	returned scif_range structure
- *
- * scif_get_pages() returns the addresses of the physical pages represented by
- * those pages of the registered address space of the peer of epd, starting at
- * offset and continuing for len bytes. offset and len are constrained to be
- * multiples of the page size.
- *
- * All of the pages in the specified range [offset, offset + len - 1] must be
- * within a single window of the registered address space of the peer of epd.
- *
- * The addresses are returned as a virtually contiguous array pointed to by the
- * phys_addr component of the scif_range structure whose address is returned in
- * pages. The nr_pages component of scif_range is the length of the array. The
- * prot_flags component of scif_range holds the protection flag value passed
- * when the pages were registered.
- *
- * Each physical page whose address is returned by scif_get_pages() remains
- * available and will not be released for reuse until the scif_range structure
- * is returned in a call to scif_put_pages(). The scif_range structure returned
- * by scif_get_pages() must be unmodified.
- *
- * It is an error to call scif_close() on an endpoint on which a scif_range
- * structure of that endpoint has not been returned to scif_put_pages().
- *
- * Return:
- * Upon successful completion, scif_get_pages() returns 0; otherwise the
- * negative of one of the following errors is returned.
- * Errors:
- * ECONNRESET - Connection reset by peer.
- * EINVAL - offset is not a multiple of the page size, or offset is negative, or
- * len is not a multiple of the page size
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOTCONN - The endpoint is not connected
- * ENXIO - Offsets in the range [offset, offset + len - 1] are invalid
- * for the registered address space of the peer epd
- */
-int scif_get_pages(scif_epd_t epd, off_t offset, size_t len,
-		   struct scif_range **pages);
-
-/**
- * scif_put_pages() - Remove references from remote registered pages
- * @pages:	pages to be returned
- *
- * scif_put_pages() releases a scif_range structure previously obtained by
- * calling scif_get_pages(). The physical pages represented by pages may
- * be reused when the window which represented those pages is unregistered.
- * Therefore, those pages must not be accessed after calling scif_put_pages().
- *
- * Return:
- * Upon successful completion, scif_put_pages() returns 0; otherwise the
- * negative of one of the following errors is returned.
- * Errors:
- * EINVAL - pages does not point to a valid scif_range structure, or
- * the scif_range structure pointed to by pages was already returned
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOTCONN - The endpoint is not connected
- */
-int scif_put_pages(struct scif_range *pages);
-
-/**
- * scif_poll() - Wait for some event on an endpoint
- * @epds:	Array of endpoint descriptors
- * @nepds:	Length of epds
- * @timeout:	Upper limit on time for which scif_poll() will block
- *
- * scif_poll() waits for one of a set of endpoints to become ready to perform
- * an I/O operation.
- *
- * The epds argument specifies the endpoint descriptors to be examined and the
- * events of interest for each endpoint descriptor. epds is a pointer to an
- * array with one member for each open endpoint descriptor of interest.
- *
- * The number of items in the epds array is specified in nepds. The epd field
- * of scif_pollepd is an endpoint descriptor of an open endpoint. The field
- * events is a bitmask specifying the events which the application is
- * interested in. The field revents is an output parameter, filled by the
- * kernel with the events that actually occurred. The bits returned in revents
- * can include any of those specified in events, or one of the values EPOLLERR,
- * EPOLLHUP, or EPOLLNVAL. (These three bits are meaningless in the events
- * field, and will be set in the revents field whenever the corresponding
- * condition is true.)
- *
- * If none of the events requested (and no error) has occurred for any of the
- * endpoint descriptors, then scif_poll() blocks until one of the events occurs.
- *
- * The timeout argument specifies an upper limit on the time for which
- * scif_poll() will block, in milliseconds. Specifying a negative value in
- * timeout means an infinite timeout.
- *
- * The following bits may be set in events and returned in revents.
- * EPOLLIN - Data may be received without blocking. For a connected
- * endpoint, this means that scif_recv() may be called without blocking. For a
- * listening endpoint, this means that scif_accept() may be called without
- * blocking.
- * EPOLLOUT - Data may be sent without blocking. For a connected endpoint, this
- * means that scif_send() may be called without blocking. EPOLLOUT may also be
- * used to block waiting for a non-blocking connect to complete. This bit value
- * has no meaning for a listening endpoint and is ignored if specified.
- *
- * The following bits are only returned in revents, and are ignored if set in
- * events.
- * EPOLLERR - An error occurred on the endpoint
- * EPOLLHUP - The connection to the peer endpoint was disconnected
- * EPOLLNVAL - The specified endpoint descriptor is invalid.
- *
- * Return:
- * Upon successful completion, scif_poll() returns a non-negative value. A
- * positive value indicates the total number of endpoint descriptors that have
- * been selected (that is, endpoint descriptors for which the revents member is
- * non-zero). A value of 0 indicates that the call timed out and no endpoint
- * descriptors have been selected. Otherwise in user mode -1 is returned and
- * errno is set to indicate the error; in kernel mode the negative of one of
- * the following errors is returned.
- *
- * Errors:
- * EINTR - A signal occurred before any requested event
- * EINVAL - The nepds argument is greater than {OPEN_MAX}
- * ENOMEM - There was no space to allocate file descriptor tables
- */
-int scif_poll(struct scif_pollepd *epds, unsigned int nepds, long timeout);
-
-/**
- * scif_client_register() - Register a SCIF client
- * @client:	client to be registered
- *
- * scif_client_register() registers a SCIF client. The probe() method
- * of the client is called when SCIF peer devices come online and the
- * remove() method is called when the peer devices disappear.
- *
- * Return:
- * Upon successful completion, scif_client_register() returns a non-negative
- * value. Otherwise the return value is the same as subsys_interface_register()
- * in the kernel.
- */
-int scif_client_register(struct scif_client *client);
-
-/**
- * scif_client_unregister() - Unregister a SCIF client
- * @client:	client to be unregistered
- *
- * scif_client_unregister() unregisters a SCIF client.
- *
- * Return:
- * None
- */
-void scif_client_unregister(struct scif_client *client);
-
-#endif /* __SCIF_H__ */
diff --git a/include/uapi/linux/mic_common.h b/include/uapi/linux/mic_common.h
deleted file mode 100644
index 504e523f702c..000000000000
--- a/include/uapi/linux/mic_common.h
+++ /dev/null
@@ -1,235 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Intel MIC driver.
- *
- */
-#ifndef __MIC_COMMON_H_
-#define __MIC_COMMON_H_
-
-#include <linux/virtio_ring.h>
-
-#define __mic_align(a, x) (((a) + (x) - 1) & ~((x) - 1))
-
-/**
- * struct mic_device_desc: Virtio device information shared between the
- * virtio driver and userspace backend
- *
- * @type: Device type: console/network/disk etc.  Type 0/-1 terminates.
- * @num_vq: Number of virtqueues.
- * @feature_len: Number of bytes of feature bits.  Multiply by 2: one for
-   host features and one for guest acknowledgements.
- * @config_len: Number of bytes of the config array after virtqueues.
- * @status: A status byte, written by the Guest.
- * @config: Start of the following variable length config.
- */
-struct mic_device_desc {
-	__s8 type;
-	__u8 num_vq;
-	__u8 feature_len;
-	__u8 config_len;
-	__u8 status;
-	__le64 config[0];
-} __attribute__ ((aligned(8)));
-
-/**
- * struct mic_device_ctrl: Per virtio device information in the device page
- * used internally by the host and card side drivers.
- *
- * @vdev: Used for storing MIC vdev information by the guest.
- * @config_change: Set to 1 by host when a config change is requested.
- * @vdev_reset: Set to 1 by guest to indicate virtio device has been reset.
- * @guest_ack: Set to 1 by guest to ack a command.
- * @host_ack: Set to 1 by host to ack a command.
- * @used_address_updated: Set to 1 by guest when the used address should be
- * updated.
- * @c2h_vdev_db: The doorbell number to be used by guest. Set by host.
- * @h2c_vdev_db: The doorbell number to be used by host. Set by guest.
- */
-struct mic_device_ctrl {
-	__le64 vdev;
-	__u8 config_change;
-	__u8 vdev_reset;
-	__u8 guest_ack;
-	__u8 host_ack;
-	__u8 used_address_updated;
-	__s8 c2h_vdev_db;
-	__s8 h2c_vdev_db;
-} __attribute__ ((aligned(8)));
-
-/**
- * struct mic_bootparam: Virtio device independent information in device page
- *
- * @magic: A magic value used by the card to ensure it can see the host
- * @h2c_config_db: Host to Card Virtio config doorbell set by card
- * @node_id: Unique id of the node
- * @h2c_scif_db - Host to card SCIF doorbell set by card
- * @c2h_scif_db - Card to host SCIF doorbell set by host
- * @scif_host_dma_addr - SCIF host queue pair DMA address
- * @scif_card_dma_addr - SCIF card queue pair DMA address
- */
-struct mic_bootparam {
-	__le32 magic;
-	__s8 h2c_config_db;
-	__u8 node_id;
-	__u8 h2c_scif_db;
-	__u8 c2h_scif_db;
-	__u64 scif_host_dma_addr;
-	__u64 scif_card_dma_addr;
-} __attribute__ ((aligned(8)));
-
-/**
- * struct mic_device_page: High level representation of the device page
- *
- * @bootparam: The bootparam structure is used for sharing information and
- * status updates between MIC host and card drivers.
- * @desc: Array of MIC virtio device descriptors.
- */
-struct mic_device_page {
-	struct mic_bootparam bootparam;
-	struct mic_device_desc desc[0];
-};
-/**
- * struct mic_vqconfig: This is how we expect the device configuration field
- * for a virtqueue to be laid out in config space.
- *
- * @address: Guest/MIC physical address of the virtio ring
- * (avail and desc rings)
- * @used_address: Guest/MIC physical address of the used ring
- * @num: The number of entries in the virtio_ring
- */
-struct mic_vqconfig {
-	__le64 address;
-	__le64 used_address;
-	__le16 num;
-} __attribute__ ((aligned(8)));
-
-/*
- * The alignment to use between consumer and producer parts of vring.
- * This is pagesize for historical reasons.
- */
-#define MIC_VIRTIO_RING_ALIGN		4096
-
-#define MIC_MAX_VRINGS			4
-#define MIC_VRING_ENTRIES		128
-
-/*
- * Max vring entries (power of 2) to ensure desc and avail rings
- * fit in a single page
- */
-#define MIC_MAX_VRING_ENTRIES		128
-
-/**
- * Max size of the desc block in bytes: includes:
- *	- struct mic_device_desc
- *	- struct mic_vqconfig (num_vq of these)
- *	- host and guest features
- *	- virtio device config space
- */
-#define MIC_MAX_DESC_BLK_SIZE		256
-
-/**
- * struct _mic_vring_info - Host vring info exposed to userspace backend
- * for the avail index and magic for the card.
- *
- * @avail_idx: host avail idx
- * @magic: A magic debug cookie.
- */
-struct _mic_vring_info {
-	__u16 avail_idx;
-	__le32 magic;
-};
-
-/**
- * struct mic_vring - Vring information.
- *
- * @vr: The virtio ring.
- * @info: Host vring information exposed to the userspace backend for the
- * avail index and magic for the card.
- * @va: The va for the buffer allocated for vr and info.
- * @len: The length of the buffer required for allocating vr and info.
- */
-struct mic_vring {
-	struct vring vr;
-	struct _mic_vring_info *info;
-	void *va;
-	int len;
-};
-
-#define mic_aligned_desc_size(d) __mic_align(mic_desc_size(d), 8)
-
-#ifndef INTEL_MIC_CARD
-static inline unsigned mic_desc_size(const struct mic_device_desc *desc)
-{
-	return sizeof(*desc) + desc->num_vq * sizeof(struct mic_vqconfig)
-		+ desc->feature_len * 2 + desc->config_len;
-}
-
-static inline struct mic_vqconfig *
-mic_vq_config(const struct mic_device_desc *desc)
-{
-	return (struct mic_vqconfig *)(desc + 1);
-}
-
-static inline __u8 *mic_vq_features(const struct mic_device_desc *desc)
-{
-	return (__u8 *)(mic_vq_config(desc) + desc->num_vq);
-}
-
-static inline __u8 *mic_vq_configspace(const struct mic_device_desc *desc)
-{
-	return mic_vq_features(desc) + desc->feature_len * 2;
-}
-static inline unsigned mic_total_desc_size(struct mic_device_desc *desc)
-{
-	return mic_aligned_desc_size(desc) + sizeof(struct mic_device_ctrl);
-}
-#endif
-
-/* Device page size */
-#define MIC_DP_SIZE 4096
-
-#define MIC_MAGIC 0xc0ffee00
-
-/**
- * enum mic_states - MIC states.
- */
-enum mic_states {
-	MIC_READY = 0,
-	MIC_BOOTING,
-	MIC_ONLINE,
-	MIC_SHUTTING_DOWN,
-	MIC_RESETTING,
-	MIC_RESET_FAILED,
-	MIC_LAST
-};
-
-/**
- * enum mic_status - MIC status reported by card after
- * a host or card initiated shutdown or a card crash.
- */
-enum mic_status {
-	MIC_NOP = 0,
-	MIC_CRASHED,
-	MIC_HALTED,
-	MIC_POWER_OFF,
-	MIC_RESTART,
-	MIC_STATUS_LAST
-};
-
-#endif
diff --git a/include/uapi/linux/mic_ioctl.h b/include/uapi/linux/mic_ioctl.h
deleted file mode 100644
index 687b9cd9d3e2..000000000000
--- a/include/uapi/linux/mic_ioctl.h
+++ /dev/null
@@ -1,77 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Intel MIC Host driver.
- *
- */
-#ifndef _MIC_IOCTL_H_
-#define _MIC_IOCTL_H_
-
-#include <linux/types.h>
-
-/*
- * mic_copy - MIC virtio descriptor copy.
- *
- * @iov: An array of IOVEC structures containing user space buffers.
- * @iovcnt: Number of IOVEC structures in iov.
- * @vr_idx: The vring index.
- * @update_used: A non zero value results in used index being updated.
- * @out_len: The aggregate of the total length written to or read from
- *	the virtio device.
- */
-struct mic_copy_desc {
-#ifdef __KERNEL__
-	struct iovec __user *iov;
-#else
-	struct iovec *iov;
-#endif
-	__u32 iovcnt;
-	__u8 vr_idx;
-	__u8 update_used;
-	__u32 out_len;
-};
-
-/*
- * Add a new virtio device
- * The (struct mic_device_desc *) pointer points to a device page entry
- *	for the virtio device consisting of:
- *	- struct mic_device_desc
- *	- struct mic_vqconfig (num_vq of these)
- *	- host and guest features
- *	- virtio device config space
- * The total size referenced by the pointer should equal the size returned
- * by desc_size() in mic_common.h
- */
-#define MIC_VIRTIO_ADD_DEVICE _IOWR('s', 1, struct mic_device_desc *)
-
-/*
- * Copy the number of entries in the iovec and update the used index
- * if requested by the user.
- */
-#define MIC_VIRTIO_COPY_DESC	_IOWR('s', 2, struct mic_copy_desc *)
-
-/*
- * Notify virtio device of a config change
- * The (__u8 *) pointer points to config space values for the device
- * as they should be written into the device page. The total size
- * referenced by the pointer should equal the config_len field of struct
- * mic_device_desc.
- */
-#define MIC_VIRTIO_CONFIG_CHANGE _IOWR('s', 5, __u8 *)
-
-#endif
diff --git a/samples/mic/mpssd/.gitignore b/samples/mic/mpssd/.gitignore
deleted file mode 100644
index aa03f1eb37a0..000000000000
--- a/samples/mic/mpssd/.gitignore
+++ /dev/null
@@ -1,2 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-mpssd
diff --git a/samples/mic/mpssd/Makefile b/samples/mic/mpssd/Makefile
deleted file mode 100644
index a7a6e0c70424..000000000000
--- a/samples/mic/mpssd/Makefile
+++ /dev/null
@@ -1,28 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-ifndef CROSS_COMPILE
-uname_M := $(shell uname -m 2>/dev/null || echo not)
-ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/)
-
-ifeq ($(ARCH),x86)
-
-PROGS := mpssd
-CC = $(CROSS_COMPILE)gcc
-CFLAGS := -I../../../usr/include -I../../../tools/include
-
-ifdef DEBUG
-CFLAGS += -DDEBUG=$(DEBUG)
-endif
-
-all: $(PROGS)
-mpssd: mpssd.c sysfs.c
-	$(CC) $(CFLAGS) mpssd.c sysfs.c -o mpssd -lpthread
-
-install:
-	install mpssd /usr/sbin/mpssd
-	install micctrl /usr/sbin/micctrl
-
-clean:
-	rm -fr $(PROGS)
-
-endif
-endif
diff --git a/samples/mic/mpssd/micctrl b/samples/mic/mpssd/micctrl
deleted file mode 100755
index 030a60b04046..000000000000
--- a/samples/mic/mpssd/micctrl
+++ /dev/null
@@ -1,162 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0-only
-# Intel MIC Platform Software Stack (MPSS)
-#
-# Copyright(c) 2013 Intel Corporation.
-#
-# Intel MIC User Space Tools.
-#
-# micctrl - Controls MIC boot/start/stop.
-#
-# chkconfig: 2345 95 05
-# description: start MPSS stack processing.
-#
-### BEGIN INIT INFO
-# Provides: micctrl
-### END INIT INFO
-
-# Source function library.
-. /etc/init.d/functions
-
-sysfs="/sys/class/mic"
-
-_status()
-{
-	f=$sysfs/$1
-	echo -e $1 state: "`cat $f/state`" shutdown_status: "`cat $f/shutdown_status`"
-}
-
-status()
-{
-	if [ "`echo $1 | head -c3`" == "mic" ]; then
-		_status $1
-		return $?
-	fi
-	for f in $sysfs/*
-	do
-		_status `basename $f`
-		RETVAL=$?
-		[ $RETVAL -ne 0 ] && return $RETVAL
-	done
-	return 0
-}
-
-_reset()
-{
-	f=$sysfs/$1
-	echo reset > $f/state
-}
-
-reset()
-{
-	if [ "`echo $1 | head -c3`" == "mic" ]; then
-		_reset $1
-		return $?
-	fi
-	for f in $sysfs/*
-	do
-		_reset `basename $f`
-		RETVAL=$?
-		[ $RETVAL -ne 0 ] && return $RETVAL
-	done
-	return 0
-}
-
-_boot()
-{
-	f=$sysfs/$1
-	echo "linux" > $f/bootmode
-	echo "mic/uos.img" > $f/firmware
-	echo "mic/$1.image" > $f/ramdisk
-	echo "boot" > $f/state
-}
-
-boot()
-{
-	if [ "`echo $1 | head -c3`" == "mic" ]; then
-		_boot $1
-		return $?
-	fi
-	for f in $sysfs/*
-	do
-		_boot `basename $f`
-		RETVAL=$?
-		[ $RETVAL -ne 0 ] && return $RETVAL
-	done
-	return 0
-}
-
-_shutdown()
-{
-	f=$sysfs/$1
-	echo shutdown > $f/state
-}
-
-shutdown()
-{
-	if [ "`echo $1 | head -c3`" == "mic" ]; then
-		_shutdown $1
-		return $?
-	fi
-	for f in $sysfs/*
-	do
-		_shutdown `basename $f`
-		RETVAL=$?
-		[ $RETVAL -ne 0 ] && return $RETVAL
-	done
-	return 0
-}
-
-_wait()
-{
-	f=$sysfs/$1
-	while [ "`cat $f/state`" != "offline" -a "`cat $f/state`" != "online" ]
-	do
-		sleep 1
-		echo -e "Waiting for $1 to go offline"
-	done
-}
-
-wait()
-{
-	if [ "`echo $1 | head -c3`" == "mic" ]; then
-		_wait $1
-		return $?
-	fi
-	# Wait for the cards to go offline
-	for f in $sysfs/*
-	do
-		_wait `basename $f`
-		RETVAL=$?
-		[ $RETVAL -ne 0 ] && return $RETVAL
-	done
-	return 0
-}
-
-if [ ! -d "$sysfs" ]; then
-	echo -e $"Module unloaded "
-	exit 3
-fi
-
-case $1 in
-	-s)
-		status $2
-		;;
-	-r)
-		reset $2
-		;;
-	-b)
-		boot $2
-		;;
-	-S)
-		shutdown $2
-		;;
-	-w)
-		wait $2
-		;;
-	*)
-		echo $"Usage: $0 {-s (status) |-r (reset) |-b (boot) |-S (shutdown) |-w (wait)}"
-		exit 2
-esac
-
-exit $?
diff --git a/samples/mic/mpssd/mpss b/samples/mic/mpssd/mpss
deleted file mode 100755
index 248ac7313c71..000000000000
--- a/samples/mic/mpssd/mpss
+++ /dev/null
@@ -1,189 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0-only
-# Intel MIC Platform Software Stack (MPSS)
-#
-# Copyright(c) 2013 Intel Corporation.
-#
-# Intel MIC User Space Tools.
-#
-# mpss	Start mpssd.
-#
-# chkconfig: 2345 95 05
-# description: start MPSS stack processing.
-#
-### BEGIN INIT INFO
-# Provides: mpss
-# Required-Start:
-# Required-Stop:
-# Short-Description: MPSS stack control
-# Description: MPSS stack control
-### END INIT INFO
-
-# Source function library.
-. /etc/init.d/functions
-
-exec=/usr/sbin/mpssd
-sysfs="/sys/class/mic"
-mic_modules="mic_host mic_x100_dma scif vop"
-
-start()
-{
-	[ -x $exec ] || exit 5
-
-	if [ "`ps -e | awk '{print $4}' | grep mpssd | head -1`" = "mpssd" ]; then
-		echo -e $"MPSSD already running! "
-		success
-		echo
-		return 0
-	fi
-
-	echo -e $"Starting MPSS Stack"
-	echo -e $"Loading MIC drivers:" $mic_modules
-
-	modprobe -a $mic_modules
-	RETVAL=$?
-	if [ $RETVAL -ne 0 ]; then
-		failure
-		echo
-		return $RETVAL
-	fi
-
-	# Start the daemon
-	echo -n $"Starting MPSSD "
-	$exec
-	RETVAL=$?
-	if [ $RETVAL -ne 0 ]; then
-		failure
-		echo
-		return $RETVAL
-	fi
-	success
-	echo
-
-	sleep 5
-
-	# Boot the cards
-	micctrl -b
-
-	# Wait till ping works
-	for f in $sysfs/*
-	do
-		count=100
-		ipaddr=`cat $f/cmdline`
-		ipaddr=${ipaddr#*address,}
-		ipaddr=`echo $ipaddr | cut -d, -f1 | cut -d\; -f1`
-		while [ $count -ge 0 ]
-		do
-			echo -e "Pinging "`basename $f`" "
-			ping -c 1 $ipaddr &> /dev/null
-			RETVAL=$?
-			if [ $RETVAL -eq 0 ]; then
-				success
-				break
-			fi
-			sleep 1
-			count=`expr $count - 1`
-		done
-		[ $RETVAL -ne 0 ] && failure || success
-		echo
-	done
-	return $RETVAL
-}
-
-stop()
-{
-	echo -e $"Shutting down MPSS Stack: "
-
-	# Bail out if module is unloaded
-	if [ ! -d "$sysfs" ]; then
-		echo -n $"Module unloaded "
-		success
-		echo
-		return 0
-	fi
-
-	# Shut down the cards.
-	micctrl -S
-
-	# Wait for the cards to go offline
-	for f in $sysfs/*
-	do
-		while [ "`cat $f/state`" != "ready" ]
-		do
-			sleep 1
-			echo -e "Waiting for "`basename $f`" to become ready"
-		done
-	done
-
-	# Display the status of the cards
-	micctrl -s
-
-	# Kill MPSSD now
-	echo -n $"Killing MPSSD"
-	killall -9 mpssd 2>/dev/null
-	RETVAL=$?
-	[ $RETVAL -ne 0 ] && failure || success
-	echo
-	return $RETVAL
-}
-
-restart()
-{
-	stop
-	sleep 5
-	start
-}
-
-status()
-{
-	micctrl -s
-	if [ "`ps -e | awk '{print $4}' | grep mpssd | head -n 1`" = "mpssd" ]; then
-		echo "mpssd is running"
-	else
-		echo "mpssd is stopped"
-	fi
-	return 0
-}
-
-unload()
-{
-	if [ ! -d "$sysfs" ]; then
-		echo -n $"No MIC_HOST Module: "
-		success
-		echo
-		return
-	fi
-
-	stop
-
-	sleep 5
-	echo -n $"Removing MIC drivers:" $mic_modules
-	modprobe -r $mic_modules
-	RETVAL=$?
-	[ $RETVAL -ne 0 ] && failure || success
-	echo
-	return $RETVAL
-}
-
-case $1 in
-	start)
-		start
-		;;
-	stop)
-		stop
-		;;
-	restart)
-		restart
-		;;
-	status)
-		status
-		;;
-	unload)
-		unload
-		;;
-	*)
-		echo $"Usage: $0 {start|stop|restart|status|unload}"
-		exit 2
-esac
-
-exit $?
diff --git a/samples/mic/mpssd/mpssd.c b/samples/mic/mpssd/mpssd.c
deleted file mode 100644
index c03a05d498f0..000000000000
--- a/samples/mic/mpssd/mpssd.c
+++ /dev/null
@@ -1,1815 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC User Space Tools.
- */
-
-#define _GNU_SOURCE
-
-#include <stdlib.h>
-#include <fcntl.h>
-#include <getopt.h>
-#include <assert.h>
-#include <unistd.h>
-#include <stdbool.h>
-#include <signal.h>
-#include <poll.h>
-#include <features.h>
-#include <sys/types.h>
-#include <sys/stat.h>
-#include <sys/mman.h>
-#include <sys/socket.h>
-#include <linux/virtio_ring.h>
-#include <linux/virtio_net.h>
-#include <linux/virtio_console.h>
-#include <linux/virtio_blk.h>
-#include <linux/version.h>
-#include "mpssd.h"
-#include <linux/mic_ioctl.h>
-#include <linux/mic_common.h>
-#include <tools/endian.h>
-
-static void *init_mic(void *arg);
-
-static FILE *logfp;
-static struct mic_info mic_list;
-
-#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
-
-#define min_t(type, x, y) ({				\
-		type __min1 = (x);                      \
-		type __min2 = (y);                      \
-		__min1 < __min2 ? __min1 : __min2; })
-
-/* align addr on a size boundary - adjust address up/down if needed */
-#define _ALIGN_DOWN(addr, size)  ((addr)&(~((size)-1)))
-#define _ALIGN_UP(addr, size)    _ALIGN_DOWN(addr + size - 1, size)
-
-/* align addr on a size boundary - adjust address up if needed */
-#define _ALIGN(addr, size)     _ALIGN_UP(addr, size)
-
-/* to align the pointer to the (next) page boundary */
-#define PAGE_ALIGN(addr)        _ALIGN(addr, PAGE_SIZE)
-
-#define READ_ONCE(x) (*(volatile typeof(x) *)&(x))
-
-#define GSO_ENABLED		1
-#define MAX_GSO_SIZE		(64 * 1024)
-#define ETH_H_LEN		14
-#define MAX_NET_PKT_SIZE	(_ALIGN_UP(MAX_GSO_SIZE + ETH_H_LEN, 64))
-#define MIC_DEVICE_PAGE_END	0x1000
-
-#ifndef VIRTIO_NET_HDR_F_DATA_VALID
-#define VIRTIO_NET_HDR_F_DATA_VALID	2	/* Csum is valid */
-#endif
-
-static struct {
-	struct mic_device_desc dd;
-	struct mic_vqconfig vqconfig[2];
-	__u32 host_features, guest_acknowledgements;
-	struct virtio_console_config cons_config;
-} virtcons_dev_page = {
-	.dd = {
-		.type = VIRTIO_ID_CONSOLE,
-		.num_vq = ARRAY_SIZE(virtcons_dev_page.vqconfig),
-		.feature_len = sizeof(virtcons_dev_page.host_features),
-		.config_len = sizeof(virtcons_dev_page.cons_config),
-	},
-	.vqconfig[0] = {
-		.num = htole16(MIC_VRING_ENTRIES),
-	},
-	.vqconfig[1] = {
-		.num = htole16(MIC_VRING_ENTRIES),
-	},
-};
-
-static struct {
-	struct mic_device_desc dd;
-	struct mic_vqconfig vqconfig[2];
-	__u32 host_features, guest_acknowledgements;
-	struct virtio_net_config net_config;
-} virtnet_dev_page = {
-	.dd = {
-		.type = VIRTIO_ID_NET,
-		.num_vq = ARRAY_SIZE(virtnet_dev_page.vqconfig),
-		.feature_len = sizeof(virtnet_dev_page.host_features),
-		.config_len = sizeof(virtnet_dev_page.net_config),
-	},
-	.vqconfig[0] = {
-		.num = htole16(MIC_VRING_ENTRIES),
-	},
-	.vqconfig[1] = {
-		.num = htole16(MIC_VRING_ENTRIES),
-	},
-#if GSO_ENABLED
-	.host_features = htole32(
-		1 << VIRTIO_NET_F_CSUM |
-		1 << VIRTIO_NET_F_GSO |
-		1 << VIRTIO_NET_F_GUEST_TSO4 |
-		1 << VIRTIO_NET_F_GUEST_TSO6 |
-		1 << VIRTIO_NET_F_GUEST_ECN),
-#else
-		.host_features = 0,
-#endif
-};
-
-static const char *mic_config_dir = "/etc/mpss";
-static const char *virtblk_backend = "VIRTBLK_BACKEND";
-static struct {
-	struct mic_device_desc dd;
-	struct mic_vqconfig vqconfig[1];
-	__u32 host_features, guest_acknowledgements;
-	struct virtio_blk_config blk_config;
-} virtblk_dev_page = {
-	.dd = {
-		.type = VIRTIO_ID_BLOCK,
-		.num_vq = ARRAY_SIZE(virtblk_dev_page.vqconfig),
-		.feature_len = sizeof(virtblk_dev_page.host_features),
-		.config_len = sizeof(virtblk_dev_page.blk_config),
-	},
-	.vqconfig[0] = {
-		.num = htole16(MIC_VRING_ENTRIES),
-	},
-	.host_features =
-		htole32(1<<VIRTIO_BLK_F_SEG_MAX),
-	.blk_config = {
-		.seg_max = htole32(MIC_VRING_ENTRIES - 2),
-		.capacity = htole64(0),
-	 }
-};
-
-static char *myname;
-
-static int
-tap_configure(struct mic_info *mic, char *dev)
-{
-	pid_t pid;
-	char *ifargv[7];
-	char ipaddr[IFNAMSIZ];
-	int ret = 0;
-
-	pid = fork();
-	if (pid == 0) {
-		ifargv[0] = "ip";
-		ifargv[1] = "link";
-		ifargv[2] = "set";
-		ifargv[3] = dev;
-		ifargv[4] = "up";
-		ifargv[5] = NULL;
-		mpsslog("Configuring %s\n", dev);
-		ret = execvp("ip", ifargv);
-		if (ret < 0) {
-			mpsslog("%s execvp failed errno %s\n",
-				mic->name, strerror(errno));
-			return ret;
-		}
-	}
-	if (pid < 0) {
-		mpsslog("%s fork failed errno %s\n",
-			mic->name, strerror(errno));
-		return ret;
-	}
-
-	ret = waitpid(pid, NULL, 0);
-	if (ret < 0) {
-		mpsslog("%s waitpid failed errno %s\n",
-			mic->name, strerror(errno));
-		return ret;
-	}
-
-	snprintf(ipaddr, IFNAMSIZ, "172.31.%d.254/24", mic->id + 1);
-
-	pid = fork();
-	if (pid == 0) {
-		ifargv[0] = "ip";
-		ifargv[1] = "addr";
-		ifargv[2] = "add";
-		ifargv[3] = ipaddr;
-		ifargv[4] = "dev";
-		ifargv[5] = dev;
-		ifargv[6] = NULL;
-		mpsslog("Configuring %s ipaddr %s\n", dev, ipaddr);
-		ret = execvp("ip", ifargv);
-		if (ret < 0) {
-			mpsslog("%s execvp failed errno %s\n",
-				mic->name, strerror(errno));
-			return ret;
-		}
-	}
-	if (pid < 0) {
-		mpsslog("%s fork failed errno %s\n",
-			mic->name, strerror(errno));
-		return ret;
-	}
-
-	ret = waitpid(pid, NULL, 0);
-	if (ret < 0) {
-		mpsslog("%s waitpid failed errno %s\n",
-			mic->name, strerror(errno));
-		return ret;
-	}
-	mpsslog("MIC name %s %s %d DONE!\n",
-		mic->name, __func__, __LINE__);
-	return 0;
-}
-
-static int tun_alloc(struct mic_info *mic, char *dev)
-{
-	struct ifreq ifr;
-	int fd, err;
-#if GSO_ENABLED
-	unsigned offload;
-#endif
-	fd = open("/dev/net/tun", O_RDWR);
-	if (fd < 0) {
-		mpsslog("Could not open /dev/net/tun %s\n", strerror(errno));
-		goto done;
-	}
-
-	memset(&ifr, 0, sizeof(ifr));
-
-	ifr.ifr_flags = IFF_TAP | IFF_NO_PI | IFF_VNET_HDR;
-	if (*dev)
-		strncpy(ifr.ifr_name, dev, IFNAMSIZ);
-
-	err = ioctl(fd, TUNSETIFF, (void *)&ifr);
-	if (err < 0) {
-		mpsslog("%s %s %d TUNSETIFF failed %s\n",
-			mic->name, __func__, __LINE__, strerror(errno));
-		close(fd);
-		return err;
-	}
-#if GSO_ENABLED
-	offload = TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 | TUN_F_TSO_ECN;
-
-	err = ioctl(fd, TUNSETOFFLOAD, offload);
-	if (err < 0) {
-		mpsslog("%s %s %d TUNSETOFFLOAD failed %s\n",
-			mic->name, __func__, __LINE__, strerror(errno));
-		close(fd);
-		return err;
-	}
-#endif
-	strcpy(dev, ifr.ifr_name);
-	mpsslog("Created TAP %s\n", dev);
-done:
-	return fd;
-}
-
-#define NET_FD_VIRTIO_NET 0
-#define NET_FD_TUN 1
-#define MAX_NET_FD 2
-
-static void set_dp(struct mic_info *mic, int type, void *dp)
-{
-	switch (type) {
-	case VIRTIO_ID_CONSOLE:
-		mic->mic_console.console_dp = dp;
-		return;
-	case VIRTIO_ID_NET:
-		mic->mic_net.net_dp = dp;
-		return;
-	case VIRTIO_ID_BLOCK:
-		mic->mic_virtblk.block_dp = dp;
-		return;
-	}
-	mpsslog("%s %s %d not found\n", mic->name, __func__, type);
-	assert(0);
-}
-
-static void *get_dp(struct mic_info *mic, int type)
-{
-	switch (type) {
-	case VIRTIO_ID_CONSOLE:
-		return mic->mic_console.console_dp;
-	case VIRTIO_ID_NET:
-		return mic->mic_net.net_dp;
-	case VIRTIO_ID_BLOCK:
-		return mic->mic_virtblk.block_dp;
-	}
-	mpsslog("%s %s %d not found\n", mic->name, __func__, type);
-	assert(0);
-	return NULL;
-}
-
-static struct mic_device_desc *get_device_desc(struct mic_info *mic, int type)
-{
-	struct mic_device_desc *d;
-	int i;
-	void *dp = get_dp(mic, type);
-
-	for (i = sizeof(struct mic_bootparam); i < PAGE_SIZE;
-		i += mic_total_desc_size(d)) {
-		d = dp + i;
-
-		/* End of list */
-		if (d->type == 0)
-			break;
-
-		if (d->type == -1)
-			continue;
-
-		mpsslog("%s %s d-> type %d d %p\n",
-			mic->name, __func__, d->type, d);
-
-		if (d->type == (__u8)type)
-			return d;
-	}
-	mpsslog("%s %s %d not found\n", mic->name, __func__, type);
-	return NULL;
-}
-
-/* See comments in vhost.c for explanation of next_desc() */
-static unsigned next_desc(struct vring_desc *desc)
-{
-	unsigned int next;
-
-	if (!(le16toh(desc->flags) & VRING_DESC_F_NEXT))
-		return -1U;
-	next = le16toh(desc->next);
-	return next;
-}
-
-/* Sum up all the IOVEC length */
-static ssize_t
-sum_iovec_len(struct mic_copy_desc *copy)
-{
-	ssize_t sum = 0;
-	unsigned int i;
-
-	for (i = 0; i < copy->iovcnt; i++)
-		sum += copy->iov[i].iov_len;
-	return sum;
-}
-
-static inline void verify_out_len(struct mic_info *mic,
-	struct mic_copy_desc *copy)
-{
-	if (copy->out_len != sum_iovec_len(copy)) {
-		mpsslog("%s %s %d BUG copy->out_len 0x%x len 0x%zx\n",
-			mic->name, __func__, __LINE__,
-			copy->out_len, sum_iovec_len(copy));
-		assert(copy->out_len == sum_iovec_len(copy));
-	}
-}
-
-/* Display an iovec */
-static void
-disp_iovec(struct mic_info *mic, struct mic_copy_desc *copy,
-	   const char *s, int line)
-{
-	unsigned int i;
-
-	for (i = 0; i < copy->iovcnt; i++)
-		mpsslog("%s %s %d copy->iov[%d] addr %p len 0x%zx\n",
-			mic->name, s, line, i,
-			copy->iov[i].iov_base, copy->iov[i].iov_len);
-}
-
-static inline __u16 read_avail_idx(struct mic_vring *vr)
-{
-	return READ_ONCE(vr->info->avail_idx);
-}
-
-static inline void txrx_prepare(int type, bool tx, struct mic_vring *vr,
-				struct mic_copy_desc *copy, ssize_t len)
-{
-	copy->vr_idx = tx ? 0 : 1;
-	copy->update_used = true;
-	if (type == VIRTIO_ID_NET)
-		copy->iov[1].iov_len = len - sizeof(struct virtio_net_hdr);
-	else
-		copy->iov[0].iov_len = len;
-}
-
-/* Central API which triggers the copies */
-static int
-mic_virtio_copy(struct mic_info *mic, int fd,
-		struct mic_vring *vr, struct mic_copy_desc *copy)
-{
-	int ret;
-
-	ret = ioctl(fd, MIC_VIRTIO_COPY_DESC, copy);
-	if (ret) {
-		mpsslog("%s %s %d errno %s ret %d\n",
-			mic->name, __func__, __LINE__,
-			strerror(errno), ret);
-	}
-	return ret;
-}
-
-static inline unsigned _vring_size(unsigned int num, unsigned long align)
-{
-	return _ALIGN_UP(((sizeof(struct vring_desc) * num + sizeof(__u16) * (3 + num)
-				+ align - 1) & ~(align - 1))
-		+ sizeof(__u16) * 3 + sizeof(struct vring_used_elem) * num, 4);
-}
-
-/*
- * This initialization routine requires at least one
- * vring i.e. vr0. vr1 is optional.
- */
-static void *
-init_vr(struct mic_info *mic, int fd, int type,
-	struct mic_vring *vr0, struct mic_vring *vr1, int num_vq)
-{
-	int vr_size;
-	char *va;
-
-	vr_size = PAGE_ALIGN(_vring_size(MIC_VRING_ENTRIES,
-					 MIC_VIRTIO_RING_ALIGN) +
-			     sizeof(struct _mic_vring_info));
-	va = mmap(NULL, MIC_DEVICE_PAGE_END + vr_size * num_vq,
-		PROT_READ, MAP_SHARED, fd, 0);
-	if (MAP_FAILED == va) {
-		mpsslog("%s %s %d mmap failed errno %s\n",
-			mic->name, __func__, __LINE__,
-			strerror(errno));
-		goto done;
-	}
-	set_dp(mic, type, va);
-	vr0->va = (struct mic_vring *)&va[MIC_DEVICE_PAGE_END];
-	vr0->info = vr0->va +
-		_vring_size(MIC_VRING_ENTRIES, MIC_VIRTIO_RING_ALIGN);
-	vring_init(&vr0->vr,
-		   MIC_VRING_ENTRIES, vr0->va, MIC_VIRTIO_RING_ALIGN);
-	mpsslog("%s %s vr0 %p vr0->info %p vr_size 0x%x vring 0x%x ",
-		__func__, mic->name, vr0->va, vr0->info, vr_size,
-		_vring_size(MIC_VRING_ENTRIES, MIC_VIRTIO_RING_ALIGN));
-	mpsslog("magic 0x%x expected 0x%x\n",
-		le32toh(vr0->info->magic), MIC_MAGIC + type);
-	assert(le32toh(vr0->info->magic) == MIC_MAGIC + type);
-	if (vr1) {
-		vr1->va = (struct mic_vring *)
-			&va[MIC_DEVICE_PAGE_END + vr_size];
-		vr1->info = vr1->va + _vring_size(MIC_VRING_ENTRIES,
-			MIC_VIRTIO_RING_ALIGN);
-		vring_init(&vr1->vr,
-			   MIC_VRING_ENTRIES, vr1->va, MIC_VIRTIO_RING_ALIGN);
-		mpsslog("%s %s vr1 %p vr1->info %p vr_size 0x%x vring 0x%x ",
-			__func__, mic->name, vr1->va, vr1->info, vr_size,
-			_vring_size(MIC_VRING_ENTRIES, MIC_VIRTIO_RING_ALIGN));
-		mpsslog("magic 0x%x expected 0x%x\n",
-			le32toh(vr1->info->magic), MIC_MAGIC + type + 1);
-		assert(le32toh(vr1->info->magic) == MIC_MAGIC + type + 1);
-	}
-done:
-	return va;
-}
-
-static int
-wait_for_card_driver(struct mic_info *mic, int fd, int type)
-{
-	struct pollfd pollfd;
-	int err;
-	struct mic_device_desc *desc = get_device_desc(mic, type);
-	__u8 prev_status;
-
-	if (!desc)
-		return -ENODEV;
-	prev_status = desc->status;
-	pollfd.fd = fd;
-	mpsslog("%s %s Waiting .... desc-> type %d status 0x%x\n",
-		mic->name, __func__, type, desc->status);
-
-	while (1) {
-		pollfd.events = POLLIN;
-		pollfd.revents = 0;
-		err = poll(&pollfd, 1, -1);
-		if (err < 0) {
-			mpsslog("%s %s poll failed %s\n",
-				mic->name, __func__, strerror(errno));
-			continue;
-		}
-
-		if (pollfd.revents) {
-			if (desc->status != prev_status) {
-				mpsslog("%s %s Waiting... desc-> type %d "
-					"status 0x%x\n",
-					mic->name, __func__, type,
-					desc->status);
-				prev_status = desc->status;
-			}
-			if (desc->status & VIRTIO_CONFIG_S_DRIVER_OK) {
-				mpsslog("%s %s poll.revents %d\n",
-					mic->name, __func__, pollfd.revents);
-				mpsslog("%s %s desc-> type %d status 0x%x\n",
-					mic->name, __func__, type,
-					desc->status);
-				break;
-			}
-		}
-	}
-	return 0;
-}
-
-/* Spin till we have some descriptors */
-static void
-spin_for_descriptors(struct mic_info *mic, struct mic_vring *vr)
-{
-	__u16 avail_idx = read_avail_idx(vr);
-
-	while (avail_idx == le16toh(READ_ONCE(vr->vr.avail->idx))) {
-#ifdef DEBUG
-		mpsslog("%s %s waiting for desc avail %d info_avail %d\n",
-			mic->name, __func__,
-			le16toh(vr->vr.avail->idx), vr->info->avail_idx);
-#endif
-		sched_yield();
-	}
-}
-
-static void *
-virtio_net(void *arg)
-{
-	static __u8 vnet_hdr[2][sizeof(struct virtio_net_hdr)];
-	static __u8 vnet_buf[2][MAX_NET_PKT_SIZE] __attribute__ ((aligned(64)));
-	struct iovec vnet_iov[2][2] = {
-		{ { .iov_base = vnet_hdr[0], .iov_len = sizeof(vnet_hdr[0]) },
-		  { .iov_base = vnet_buf[0], .iov_len = sizeof(vnet_buf[0]) } },
-		{ { .iov_base = vnet_hdr[1], .iov_len = sizeof(vnet_hdr[1]) },
-		  { .iov_base = vnet_buf[1], .iov_len = sizeof(vnet_buf[1]) } },
-	};
-	struct iovec *iov0 = vnet_iov[0], *iov1 = vnet_iov[1];
-	struct mic_info *mic = (struct mic_info *)arg;
-	char if_name[IFNAMSIZ];
-	struct pollfd net_poll[MAX_NET_FD];
-	struct mic_vring tx_vr, rx_vr;
-	struct mic_copy_desc copy;
-	struct mic_device_desc *desc;
-	int err;
-
-	snprintf(if_name, IFNAMSIZ, "mic%d", mic->id);
-	mic->mic_net.tap_fd = tun_alloc(mic, if_name);
-	if (mic->mic_net.tap_fd < 0)
-		goto done;
-
-	if (tap_configure(mic, if_name))
-		goto done;
-	mpsslog("MIC name %s id %d\n", mic->name, mic->id);
-
-	net_poll[NET_FD_VIRTIO_NET].fd = mic->mic_net.virtio_net_fd;
-	net_poll[NET_FD_VIRTIO_NET].events = POLLIN;
-	net_poll[NET_FD_TUN].fd = mic->mic_net.tap_fd;
-	net_poll[NET_FD_TUN].events = POLLIN;
-
-	if (MAP_FAILED == init_vr(mic, mic->mic_net.virtio_net_fd,
-				  VIRTIO_ID_NET, &tx_vr, &rx_vr,
-		virtnet_dev_page.dd.num_vq)) {
-		mpsslog("%s init_vr failed %s\n",
-			mic->name, strerror(errno));
-		goto done;
-	}
-
-	copy.iovcnt = 2;
-	desc = get_device_desc(mic, VIRTIO_ID_NET);
-
-	while (1) {
-		ssize_t len;
-
-		net_poll[NET_FD_VIRTIO_NET].revents = 0;
-		net_poll[NET_FD_TUN].revents = 0;
-
-		/* Start polling for data from tap and virtio net */
-		err = poll(net_poll, 2, -1);
-		if (err < 0) {
-			mpsslog("%s poll failed %s\n",
-				__func__, strerror(errno));
-			continue;
-		}
-		if (!(desc->status & VIRTIO_CONFIG_S_DRIVER_OK)) {
-			err = wait_for_card_driver(mic,
-						   mic->mic_net.virtio_net_fd,
-						   VIRTIO_ID_NET);
-			if (err) {
-				mpsslog("%s %s %d Exiting...\n",
-					mic->name, __func__, __LINE__);
-				break;
-			}
-		}
-		/*
-		 * Check if there is data to be read from TUN and write to
-		 * virtio net fd if there is.
-		 */
-		if (net_poll[NET_FD_TUN].revents & POLLIN) {
-			copy.iov = iov0;
-			len = readv(net_poll[NET_FD_TUN].fd,
-				copy.iov, copy.iovcnt);
-			if (len > 0) {
-				struct virtio_net_hdr *hdr
-					= (struct virtio_net_hdr *)vnet_hdr[0];
-
-				/* Disable checksums on the card since we are on
-				   a reliable PCIe link */
-				hdr->flags |= VIRTIO_NET_HDR_F_DATA_VALID;
-#ifdef DEBUG
-				mpsslog("%s %s %d hdr->flags 0x%x ", mic->name,
-					__func__, __LINE__, hdr->flags);
-				mpsslog("copy.out_len %d hdr->gso_type 0x%x\n",
-					copy.out_len, hdr->gso_type);
-#endif
-#ifdef DEBUG
-				disp_iovec(mic, &copy, __func__, __LINE__);
-				mpsslog("%s %s %d read from tap 0x%lx\n",
-					mic->name, __func__, __LINE__,
-					len);
-#endif
-				spin_for_descriptors(mic, &tx_vr);
-				txrx_prepare(VIRTIO_ID_NET, 1, &tx_vr, &copy,
-					     len);
-
-				err = mic_virtio_copy(mic,
-					mic->mic_net.virtio_net_fd, &tx_vr,
-					&copy);
-				if (err < 0) {
-					mpsslog("%s %s %d mic_virtio_copy %s\n",
-						mic->name, __func__, __LINE__,
-						strerror(errno));
-				}
-				if (!err)
-					verify_out_len(mic, &copy);
-#ifdef DEBUG
-				disp_iovec(mic, &copy, __func__, __LINE__);
-				mpsslog("%s %s %d wrote to net 0x%lx\n",
-					mic->name, __func__, __LINE__,
-					sum_iovec_len(&copy));
-#endif
-				/* Reinitialize IOV for next run */
-				iov0[1].iov_len = MAX_NET_PKT_SIZE;
-			} else if (len < 0) {
-				disp_iovec(mic, &copy, __func__, __LINE__);
-				mpsslog("%s %s %d read failed %s ", mic->name,
-					__func__, __LINE__, strerror(errno));
-				mpsslog("cnt %d sum %zd\n",
-					copy.iovcnt, sum_iovec_len(&copy));
-			}
-		}
-
-		/*
-		 * Check if there is data to be read from virtio net and
-		 * write to TUN if there is.
-		 */
-		if (net_poll[NET_FD_VIRTIO_NET].revents & POLLIN) {
-			while (rx_vr.info->avail_idx !=
-				le16toh(rx_vr.vr.avail->idx)) {
-				copy.iov = iov1;
-				txrx_prepare(VIRTIO_ID_NET, 0, &rx_vr, &copy,
-					     MAX_NET_PKT_SIZE
-					+ sizeof(struct virtio_net_hdr));
-
-				err = mic_virtio_copy(mic,
-					mic->mic_net.virtio_net_fd, &rx_vr,
-					&copy);
-				if (!err) {
-#ifdef DEBUG
-					struct virtio_net_hdr *hdr
-						= (struct virtio_net_hdr *)
-							vnet_hdr[1];
-
-					mpsslog("%s %s %d hdr->flags 0x%x, ",
-						mic->name, __func__, __LINE__,
-						hdr->flags);
-					mpsslog("out_len %d gso_type 0x%x\n",
-						copy.out_len,
-						hdr->gso_type);
-#endif
-					/* Set the correct output iov_len */
-					iov1[1].iov_len = copy.out_len -
-						sizeof(struct virtio_net_hdr);
-					verify_out_len(mic, &copy);
-#ifdef DEBUG
-					disp_iovec(mic, &copy, __func__,
-						   __LINE__);
-					mpsslog("%s %s %d ",
-						mic->name, __func__, __LINE__);
-					mpsslog("read from net 0x%lx\n",
-						sum_iovec_len(&copy));
-#endif
-					len = writev(net_poll[NET_FD_TUN].fd,
-						copy.iov, copy.iovcnt);
-					if (len != sum_iovec_len(&copy)) {
-						mpsslog("Tun write failed %s ",
-							strerror(errno));
-						mpsslog("len 0x%zx ", len);
-						mpsslog("read_len 0x%zx\n",
-							sum_iovec_len(&copy));
-					} else {
-#ifdef DEBUG
-						disp_iovec(mic, &copy, __func__,
-							   __LINE__);
-						mpsslog("%s %s %d ",
-							mic->name, __func__,
-							__LINE__);
-						mpsslog("wrote to tap 0x%lx\n",
-							len);
-#endif
-					}
-				} else {
-					mpsslog("%s %s %d mic_virtio_copy %s\n",
-						mic->name, __func__, __LINE__,
-						strerror(errno));
-					break;
-				}
-			}
-		}
-		if (net_poll[NET_FD_VIRTIO_NET].revents & POLLERR)
-			mpsslog("%s: %s: POLLERR\n", __func__, mic->name);
-	}
-done:
-	pthread_exit(NULL);
-}
-
-/* virtio_console */
-#define VIRTIO_CONSOLE_FD 0
-#define MONITOR_FD (VIRTIO_CONSOLE_FD + 1)
-#define MAX_CONSOLE_FD (MONITOR_FD + 1)  /* must be the last one + 1 */
-#define MAX_BUFFER_SIZE PAGE_SIZE
-
-static void *
-virtio_console(void *arg)
-{
-	static __u8 vcons_buf[2][PAGE_SIZE];
-	struct iovec vcons_iov[2] = {
-		{ .iov_base = vcons_buf[0], .iov_len = sizeof(vcons_buf[0]) },
-		{ .iov_base = vcons_buf[1], .iov_len = sizeof(vcons_buf[1]) },
-	};
-	struct iovec *iov0 = &vcons_iov[0], *iov1 = &vcons_iov[1];
-	struct mic_info *mic = (struct mic_info *)arg;
-	int err;
-	struct pollfd console_poll[MAX_CONSOLE_FD];
-	int pty_fd;
-	char *pts_name;
-	ssize_t len;
-	struct mic_vring tx_vr, rx_vr;
-	struct mic_copy_desc copy;
-	struct mic_device_desc *desc;
-
-	pty_fd = posix_openpt(O_RDWR);
-	if (pty_fd < 0) {
-		mpsslog("can't open a pseudoterminal master device: %s\n",
-			strerror(errno));
-		goto _return;
-	}
-	pts_name = ptsname(pty_fd);
-	if (pts_name == NULL) {
-		mpsslog("can't get pts name\n");
-		goto _close_pty;
-	}
-	printf("%s console message goes to %s\n", mic->name, pts_name);
-	mpsslog("%s console message goes to %s\n", mic->name, pts_name);
-	err = grantpt(pty_fd);
-	if (err < 0) {
-		mpsslog("can't grant access: %s %s\n",
-			pts_name, strerror(errno));
-		goto _close_pty;
-	}
-	err = unlockpt(pty_fd);
-	if (err < 0) {
-		mpsslog("can't unlock a pseudoterminal: %s %s\n",
-			pts_name, strerror(errno));
-		goto _close_pty;
-	}
-	console_poll[MONITOR_FD].fd = pty_fd;
-	console_poll[MONITOR_FD].events = POLLIN;
-
-	console_poll[VIRTIO_CONSOLE_FD].fd = mic->mic_console.virtio_console_fd;
-	console_poll[VIRTIO_CONSOLE_FD].events = POLLIN;
-
-	if (MAP_FAILED == init_vr(mic, mic->mic_console.virtio_console_fd,
-				  VIRTIO_ID_CONSOLE, &tx_vr, &rx_vr,
-		virtcons_dev_page.dd.num_vq)) {
-		mpsslog("%s init_vr failed %s\n",
-			mic->name, strerror(errno));
-		goto _close_pty;
-	}
-
-	copy.iovcnt = 1;
-	desc = get_device_desc(mic, VIRTIO_ID_CONSOLE);
-
-	for (;;) {
-		console_poll[MONITOR_FD].revents = 0;
-		console_poll[VIRTIO_CONSOLE_FD].revents = 0;
-		err = poll(console_poll, MAX_CONSOLE_FD, -1);
-		if (err < 0) {
-			mpsslog("%s %d: poll failed: %s\n", __func__, __LINE__,
-				strerror(errno));
-			continue;
-		}
-		if (!(desc->status & VIRTIO_CONFIG_S_DRIVER_OK)) {
-			err = wait_for_card_driver(mic,
-					mic->mic_console.virtio_console_fd,
-					VIRTIO_ID_CONSOLE);
-			if (err) {
-				mpsslog("%s %s %d Exiting...\n",
-					mic->name, __func__, __LINE__);
-				break;
-			}
-		}
-
-		if (console_poll[MONITOR_FD].revents & POLLIN) {
-			copy.iov = iov0;
-			len = readv(pty_fd, copy.iov, copy.iovcnt);
-			if (len > 0) {
-#ifdef DEBUG
-				disp_iovec(mic, &copy, __func__, __LINE__);
-				mpsslog("%s %s %d read from tap 0x%lx\n",
-					mic->name, __func__, __LINE__,
-					len);
-#endif
-				spin_for_descriptors(mic, &tx_vr);
-				txrx_prepare(VIRTIO_ID_CONSOLE, 1, &tx_vr,
-					     &copy, len);
-
-				err = mic_virtio_copy(mic,
-					mic->mic_console.virtio_console_fd,
-					&tx_vr, &copy);
-				if (err < 0) {
-					mpsslog("%s %s %d mic_virtio_copy %s\n",
-						mic->name, __func__, __LINE__,
-						strerror(errno));
-				}
-				if (!err)
-					verify_out_len(mic, &copy);
-#ifdef DEBUG
-				disp_iovec(mic, &copy, __func__, __LINE__);
-				mpsslog("%s %s %d wrote to net 0x%lx\n",
-					mic->name, __func__, __LINE__,
-					sum_iovec_len(&copy));
-#endif
-				/* Reinitialize IOV for next run */
-				iov0->iov_len = PAGE_SIZE;
-			} else if (len < 0) {
-				disp_iovec(mic, &copy, __func__, __LINE__);
-				mpsslog("%s %s %d read failed %s ",
-					mic->name, __func__, __LINE__,
-					strerror(errno));
-				mpsslog("cnt %d sum %zd\n",
-					copy.iovcnt, sum_iovec_len(&copy));
-			}
-		}
-
-		if (console_poll[VIRTIO_CONSOLE_FD].revents & POLLIN) {
-			while (rx_vr.info->avail_idx !=
-				le16toh(rx_vr.vr.avail->idx)) {
-				copy.iov = iov1;
-				txrx_prepare(VIRTIO_ID_CONSOLE, 0, &rx_vr,
-					     &copy, PAGE_SIZE);
-
-				err = mic_virtio_copy(mic,
-					mic->mic_console.virtio_console_fd,
-					&rx_vr, &copy);
-				if (!err) {
-					/* Set the correct output iov_len */
-					iov1->iov_len = copy.out_len;
-					verify_out_len(mic, &copy);
-#ifdef DEBUG
-					disp_iovec(mic, &copy, __func__,
-						   __LINE__);
-					mpsslog("%s %s %d ",
-						mic->name, __func__, __LINE__);
-					mpsslog("read from net 0x%lx\n",
-						sum_iovec_len(&copy));
-#endif
-					len = writev(pty_fd,
-						copy.iov, copy.iovcnt);
-					if (len != sum_iovec_len(&copy)) {
-						mpsslog("Tun write failed %s ",
-							strerror(errno));
-						mpsslog("len 0x%zx ", len);
-						mpsslog("read_len 0x%zx\n",
-							sum_iovec_len(&copy));
-					} else {
-#ifdef DEBUG
-						disp_iovec(mic, &copy, __func__,
-							   __LINE__);
-						mpsslog("%s %s %d ",
-							mic->name, __func__,
-							__LINE__);
-						mpsslog("wrote to tap 0x%lx\n",
-							len);
-#endif
-					}
-				} else {
-					mpsslog("%s %s %d mic_virtio_copy %s\n",
-						mic->name, __func__, __LINE__,
-						strerror(errno));
-					break;
-				}
-			}
-		}
-		if (console_poll[NET_FD_VIRTIO_NET].revents & POLLERR)
-			mpsslog("%s: %s: POLLERR\n", __func__, mic->name);
-	}
-_close_pty:
-	close(pty_fd);
-_return:
-	pthread_exit(NULL);
-}
-
-static void
-add_virtio_device(struct mic_info *mic, struct mic_device_desc *dd)
-{
-	char path[PATH_MAX];
-	int fd, err;
-
-	snprintf(path, PATH_MAX, "/dev/vop_virtio%d", mic->id);
-	fd = open(path, O_RDWR);
-	if (fd < 0) {
-		mpsslog("Could not open %s %s\n", path, strerror(errno));
-		return;
-	}
-
-	err = ioctl(fd, MIC_VIRTIO_ADD_DEVICE, dd);
-	if (err < 0) {
-		mpsslog("Could not add %d %s\n", dd->type, strerror(errno));
-		close(fd);
-		return;
-	}
-	switch (dd->type) {
-	case VIRTIO_ID_NET:
-		mic->mic_net.virtio_net_fd = fd;
-		mpsslog("Added VIRTIO_ID_NET for %s\n", mic->name);
-		break;
-	case VIRTIO_ID_CONSOLE:
-		mic->mic_console.virtio_console_fd = fd;
-		mpsslog("Added VIRTIO_ID_CONSOLE for %s\n", mic->name);
-		break;
-	case VIRTIO_ID_BLOCK:
-		mic->mic_virtblk.virtio_block_fd = fd;
-		mpsslog("Added VIRTIO_ID_BLOCK for %s\n", mic->name);
-		break;
-	}
-}
-
-static bool
-set_backend_file(struct mic_info *mic)
-{
-	FILE *config;
-	char buff[PATH_MAX], *line, *evv, *p;
-
-	snprintf(buff, PATH_MAX, "%s/mpssd%03d.conf", mic_config_dir, mic->id);
-	config = fopen(buff, "r");
-	if (config == NULL)
-		return false;
-	do {  /* look for "virtblk_backend=XXXX" */
-		line = fgets(buff, PATH_MAX, config);
-		if (line == NULL)
-			break;
-		if (*line == '#')
-			continue;
-		p = strchr(line, '\n');
-		if (p)
-			*p = '\0';
-	} while (strncmp(line, virtblk_backend, strlen(virtblk_backend)) != 0);
-	fclose(config);
-	if (line == NULL)
-		return false;
-	evv = strchr(line, '=');
-	if (evv == NULL)
-		return false;
-	mic->mic_virtblk.backend_file = malloc(strlen(evv) + 1);
-	if (mic->mic_virtblk.backend_file == NULL) {
-		mpsslog("%s %d can't allocate memory\n", mic->name, mic->id);
-		return false;
-	}
-	strcpy(mic->mic_virtblk.backend_file, evv + 1);
-	return true;
-}
-
-#define SECTOR_SIZE 512
-static bool
-set_backend_size(struct mic_info *mic)
-{
-	mic->mic_virtblk.backend_size = lseek(mic->mic_virtblk.backend, 0,
-		SEEK_END);
-	if (mic->mic_virtblk.backend_size < 0) {
-		mpsslog("%s: can't seek: %s\n",
-			mic->name, mic->mic_virtblk.backend_file);
-		return false;
-	}
-	virtblk_dev_page.blk_config.capacity =
-		mic->mic_virtblk.backend_size / SECTOR_SIZE;
-	if ((mic->mic_virtblk.backend_size % SECTOR_SIZE) != 0)
-		virtblk_dev_page.blk_config.capacity++;
-
-	virtblk_dev_page.blk_config.capacity =
-		htole64(virtblk_dev_page.blk_config.capacity);
-
-	return true;
-}
-
-static bool
-open_backend(struct mic_info *mic)
-{
-	if (!set_backend_file(mic))
-		goto _error_exit;
-	mic->mic_virtblk.backend = open(mic->mic_virtblk.backend_file, O_RDWR);
-	if (mic->mic_virtblk.backend < 0) {
-		mpsslog("%s: can't open: %s\n", mic->name,
-			mic->mic_virtblk.backend_file);
-		goto _error_free;
-	}
-	if (!set_backend_size(mic))
-		goto _error_close;
-	mic->mic_virtblk.backend_addr = mmap(NULL,
-		mic->mic_virtblk.backend_size,
-		PROT_READ|PROT_WRITE, MAP_SHARED,
-		mic->mic_virtblk.backend, 0L);
-	if (mic->mic_virtblk.backend_addr == MAP_FAILED) {
-		mpsslog("%s: can't map: %s %s\n",
-			mic->name, mic->mic_virtblk.backend_file,
-			strerror(errno));
-		goto _error_close;
-	}
-	return true;
-
- _error_close:
-	close(mic->mic_virtblk.backend);
- _error_free:
-	free(mic->mic_virtblk.backend_file);
- _error_exit:
-	return false;
-}
-
-static void
-close_backend(struct mic_info *mic)
-{
-	munmap(mic->mic_virtblk.backend_addr, mic->mic_virtblk.backend_size);
-	close(mic->mic_virtblk.backend);
-	free(mic->mic_virtblk.backend_file);
-}
-
-static bool
-start_virtblk(struct mic_info *mic, struct mic_vring *vring)
-{
-	if (((unsigned long)&virtblk_dev_page.blk_config % 8) != 0) {
-		mpsslog("%s: blk_config is not 8 byte aligned.\n",
-			mic->name);
-		return false;
-	}
-	add_virtio_device(mic, &virtblk_dev_page.dd);
-	if (MAP_FAILED == init_vr(mic, mic->mic_virtblk.virtio_block_fd,
-				  VIRTIO_ID_BLOCK, vring, NULL,
-				  virtblk_dev_page.dd.num_vq)) {
-		mpsslog("%s init_vr failed %s\n",
-			mic->name, strerror(errno));
-		return false;
-	}
-	return true;
-}
-
-static void
-stop_virtblk(struct mic_info *mic)
-{
-	int vr_size, ret;
-
-	vr_size = PAGE_ALIGN(_vring_size(MIC_VRING_ENTRIES,
-					 MIC_VIRTIO_RING_ALIGN) +
-			     sizeof(struct _mic_vring_info));
-	ret = munmap(mic->mic_virtblk.block_dp,
-		MIC_DEVICE_PAGE_END + vr_size * virtblk_dev_page.dd.num_vq);
-	if (ret < 0)
-		mpsslog("%s munmap errno %d\n", mic->name, errno);
-	close(mic->mic_virtblk.virtio_block_fd);
-}
-
-static __u8
-header_error_check(struct vring_desc *desc)
-{
-	if (le32toh(desc->len) != sizeof(struct virtio_blk_outhdr)) {
-		mpsslog("%s() %d: length is not sizeof(virtio_blk_outhd)\n",
-			__func__, __LINE__);
-		return -EIO;
-	}
-	if (!(le16toh(desc->flags) & VRING_DESC_F_NEXT)) {
-		mpsslog("%s() %d: alone\n",
-			__func__, __LINE__);
-		return -EIO;
-	}
-	if (le16toh(desc->flags) & VRING_DESC_F_WRITE) {
-		mpsslog("%s() %d: not read\n",
-			__func__, __LINE__);
-		return -EIO;
-	}
-	return 0;
-}
-
-static int
-read_header(int fd, struct virtio_blk_outhdr *hdr, __u32 desc_idx)
-{
-	struct iovec iovec;
-	struct mic_copy_desc copy;
-
-	iovec.iov_len = sizeof(*hdr);
-	iovec.iov_base = hdr;
-	copy.iov = &iovec;
-	copy.iovcnt = 1;
-	copy.vr_idx = 0;  /* only one vring on virtio_block */
-	copy.update_used = false;  /* do not update used index */
-	return ioctl(fd, MIC_VIRTIO_COPY_DESC, &copy);
-}
-
-static int
-transfer_blocks(int fd, struct iovec *iovec, __u32 iovcnt)
-{
-	struct mic_copy_desc copy;
-
-	copy.iov = iovec;
-	copy.iovcnt = iovcnt;
-	copy.vr_idx = 0;  /* only one vring on virtio_block */
-	copy.update_used = false;  /* do not update used index */
-	return ioctl(fd, MIC_VIRTIO_COPY_DESC, &copy);
-}
-
-static __u8
-status_error_check(struct vring_desc *desc)
-{
-	if (le32toh(desc->len) != sizeof(__u8)) {
-		mpsslog("%s() %d: length is not sizeof(status)\n",
-			__func__, __LINE__);
-		return -EIO;
-	}
-	return 0;
-}
-
-static int
-write_status(int fd, __u8 *status)
-{
-	struct iovec iovec;
-	struct mic_copy_desc copy;
-
-	iovec.iov_base = status;
-	iovec.iov_len = sizeof(*status);
-	copy.iov = &iovec;
-	copy.iovcnt = 1;
-	copy.vr_idx = 0;  /* only one vring on virtio_block */
-	copy.update_used = true; /* Update used index */
-	return ioctl(fd, MIC_VIRTIO_COPY_DESC, &copy);
-}
-
-#ifndef VIRTIO_BLK_T_GET_ID
-#define VIRTIO_BLK_T_GET_ID    8
-#endif
-
-static void *
-virtio_block(void *arg)
-{
-	struct mic_info *mic = (struct mic_info *)arg;
-	int ret;
-	struct pollfd block_poll;
-	struct mic_vring vring;
-	__u16 avail_idx;
-	__u32 desc_idx;
-	struct vring_desc *desc;
-	struct iovec *iovec, *piov;
-	__u8 status;
-	__u32 buffer_desc_idx;
-	struct virtio_blk_outhdr hdr;
-	void *fos;
-
-	for (;;) {  /* forever */
-		if (!open_backend(mic)) { /* No virtblk */
-			for (mic->mic_virtblk.signaled = 0;
-				!mic->mic_virtblk.signaled;)
-				sleep(1);
-			continue;
-		}
-
-		/* backend file is specified. */
-		if (!start_virtblk(mic, &vring))
-			goto _close_backend;
-		iovec = malloc(sizeof(*iovec) *
-			le32toh(virtblk_dev_page.blk_config.seg_max));
-		if (!iovec) {
-			mpsslog("%s: can't alloc iovec: %s\n",
-				mic->name, strerror(ENOMEM));
-			goto _stop_virtblk;
-		}
-
-		block_poll.fd = mic->mic_virtblk.virtio_block_fd;
-		block_poll.events = POLLIN;
-		for (mic->mic_virtblk.signaled = 0;
-		     !mic->mic_virtblk.signaled;) {
-			block_poll.revents = 0;
-					/* timeout in 1 sec to see signaled */
-			ret = poll(&block_poll, 1, 1000);
-			if (ret < 0) {
-				mpsslog("%s %d: poll failed: %s\n",
-					__func__, __LINE__,
-					strerror(errno));
-				continue;
-			}
-
-			if (!(block_poll.revents & POLLIN)) {
-#ifdef DEBUG
-				mpsslog("%s %d: block_poll.revents=0x%x\n",
-					__func__, __LINE__, block_poll.revents);
-#endif
-				continue;
-			}
-
-			/* POLLIN */
-			while (vring.info->avail_idx !=
-				le16toh(vring.vr.avail->idx)) {
-				/* read header element */
-				avail_idx =
-					vring.info->avail_idx &
-					(vring.vr.num - 1);
-				desc_idx = le16toh(
-					vring.vr.avail->ring[avail_idx]);
-				desc = &vring.vr.desc[desc_idx];
-#ifdef DEBUG
-				mpsslog("%s() %d: avail_idx=%d ",
-					__func__, __LINE__,
-					vring.info->avail_idx);
-				mpsslog("vring.vr.num=%d desc=%p\n",
-					vring.vr.num, desc);
-#endif
-				status = header_error_check(desc);
-				ret = read_header(
-					mic->mic_virtblk.virtio_block_fd,
-					&hdr, desc_idx);
-				if (ret < 0) {
-					mpsslog("%s() %d %s: ret=%d %s\n",
-						__func__, __LINE__,
-						mic->name, ret,
-						strerror(errno));
-					break;
-				}
-				/* buffer element */
-				piov = iovec;
-				status = 0;
-				fos = mic->mic_virtblk.backend_addr +
-					(hdr.sector * SECTOR_SIZE);
-				buffer_desc_idx = next_desc(desc);
-				desc_idx = buffer_desc_idx;
-				for (desc = &vring.vr.desc[buffer_desc_idx];
-				     desc->flags & VRING_DESC_F_NEXT;
-				     desc_idx = next_desc(desc),
-					     desc = &vring.vr.desc[desc_idx]) {
-					piov->iov_len = desc->len;
-					piov->iov_base = fos;
-					piov++;
-					fos += desc->len;
-				}
-				/* Returning NULLs for VIRTIO_BLK_T_GET_ID. */
-				if (hdr.type & ~(VIRTIO_BLK_T_OUT |
-					VIRTIO_BLK_T_GET_ID)) {
-					/*
-					  VIRTIO_BLK_T_IN - does not do
-					  anything. Probably for documenting.
-					  VIRTIO_BLK_T_SCSI_CMD - for
-					  virtio_scsi.
-					  VIRTIO_BLK_T_FLUSH - turned off in
-					  config space.
-					  VIRTIO_BLK_T_BARRIER - defined but not
-					  used in anywhere.
-					*/
-					mpsslog("%s() %d: type %x ",
-						__func__, __LINE__,
-						hdr.type);
-					mpsslog("is not supported\n");
-					status = -ENOTSUP;
-
-				} else {
-					ret = transfer_blocks(
-					mic->mic_virtblk.virtio_block_fd,
-						iovec,
-						piov - iovec);
-					if (ret < 0 &&
-					    status != 0)
-						status = ret;
-				}
-				/* write status and update used pointer */
-				if (status != 0)
-					status = status_error_check(desc);
-				ret = write_status(
-					mic->mic_virtblk.virtio_block_fd,
-					&status);
-#ifdef DEBUG
-				mpsslog("%s() %d: write status=%d on desc=%p\n",
-					__func__, __LINE__,
-					status, desc);
-#endif
-			}
-		}
-		free(iovec);
-_stop_virtblk:
-		stop_virtblk(mic);
-_close_backend:
-		close_backend(mic);
-	}  /* forever */
-
-	pthread_exit(NULL);
-}
-
-static void
-reset(struct mic_info *mic)
-{
-#define RESET_TIMEOUT 120
-	int i = RESET_TIMEOUT;
-	setsysfs(mic->name, "state", "reset");
-	while (i) {
-		char *state;
-		state = readsysfs(mic->name, "state");
-		if (!state)
-			goto retry;
-		mpsslog("%s: %s %d state %s\n",
-			mic->name, __func__, __LINE__, state);
-
-		if (!strcmp(state, "ready")) {
-			free(state);
-			break;
-		}
-		free(state);
-retry:
-		sleep(1);
-		i--;
-	}
-}
-
-static int
-get_mic_shutdown_status(struct mic_info *mic, char *shutdown_status)
-{
-	if (!strcmp(shutdown_status, "nop"))
-		return MIC_NOP;
-	if (!strcmp(shutdown_status, "crashed"))
-		return MIC_CRASHED;
-	if (!strcmp(shutdown_status, "halted"))
-		return MIC_HALTED;
-	if (!strcmp(shutdown_status, "poweroff"))
-		return MIC_POWER_OFF;
-	if (!strcmp(shutdown_status, "restart"))
-		return MIC_RESTART;
-	mpsslog("%s: BUG invalid status %s\n", mic->name, shutdown_status);
-	/* Invalid state */
-	assert(0);
-};
-
-static int get_mic_state(struct mic_info *mic)
-{
-	char *state = NULL;
-	enum mic_states mic_state;
-
-	while (!state) {
-		state = readsysfs(mic->name, "state");
-		sleep(1);
-	}
-	mpsslog("%s: %s %d state %s\n",
-		mic->name, __func__, __LINE__, state);
-
-	if (!strcmp(state, "ready")) {
-		mic_state = MIC_READY;
-	} else if (!strcmp(state, "booting")) {
-		mic_state = MIC_BOOTING;
-	} else if (!strcmp(state, "online")) {
-		mic_state = MIC_ONLINE;
-	} else if (!strcmp(state, "shutting_down")) {
-		mic_state = MIC_SHUTTING_DOWN;
-	} else if (!strcmp(state, "reset_failed")) {
-		mic_state = MIC_RESET_FAILED;
-	} else if (!strcmp(state, "resetting")) {
-		mic_state = MIC_RESETTING;
-	} else {
-		mpsslog("%s: BUG invalid state %s\n", mic->name, state);
-		assert(0);
-	}
-
-	free(state);
-	return mic_state;
-};
-
-static void mic_handle_shutdown(struct mic_info *mic)
-{
-#define SHUTDOWN_TIMEOUT 60
-	int i = SHUTDOWN_TIMEOUT;
-	char *shutdown_status;
-	while (i) {
-		shutdown_status = readsysfs(mic->name, "shutdown_status");
-		if (!shutdown_status) {
-			sleep(1);
-			continue;
-		}
-		mpsslog("%s: %s %d shutdown_status %s\n",
-			mic->name, __func__, __LINE__, shutdown_status);
-		switch (get_mic_shutdown_status(mic, shutdown_status)) {
-		case MIC_RESTART:
-			mic->restart = 1;
-		case MIC_HALTED:
-		case MIC_POWER_OFF:
-		case MIC_CRASHED:
-			free(shutdown_status);
-			goto reset;
-		default:
-			break;
-		}
-		free(shutdown_status);
-		sleep(1);
-		i--;
-	}
-reset:
-	if (!i)
-		mpsslog("%s: %s %d timing out waiting for shutdown_status %s\n",
-			mic->name, __func__, __LINE__, shutdown_status);
-	reset(mic);
-}
-
-static int open_state_fd(struct mic_info *mic)
-{
-	char pathname[PATH_MAX];
-	int fd;
-
-	snprintf(pathname, PATH_MAX - 1, "%s/%s/%s",
-		 MICSYSFSDIR, mic->name, "state");
-
-	fd = open(pathname, O_RDONLY);
-	if (fd < 0)
-		mpsslog("%s: opening file %s failed %s\n",
-			mic->name, pathname, strerror(errno));
-	return fd;
-}
-
-static int block_till_state_change(int fd, struct mic_info *mic)
-{
-	struct pollfd ufds[1];
-	char value[PAGE_SIZE];
-	int ret;
-
-	ufds[0].fd = fd;
-	ufds[0].events = POLLERR | POLLPRI;
-	ret = poll(ufds, 1, -1);
-	if (ret < 0) {
-		mpsslog("%s: %s %d poll failed %s\n",
-			mic->name, __func__, __LINE__, strerror(errno));
-		return ret;
-	}
-
-	ret = lseek(fd, 0, SEEK_SET);
-	if (ret < 0) {
-		mpsslog("%s: %s %d Failed to seek to 0: %s\n",
-			mic->name, __func__, __LINE__, strerror(errno));
-		return ret;
-	}
-
-	ret = read(fd, value, sizeof(value));
-	if (ret < 0) {
-		mpsslog("%s: %s %d Failed to read sysfs entry: %s\n",
-			mic->name, __func__, __LINE__, strerror(errno));
-		return ret;
-	}
-
-	return 0;
-}
-
-static void *
-mic_config(void *arg)
-{
-	struct mic_info *mic = (struct mic_info *)arg;
-	int fd, ret, stat = 0;
-
-	fd = open_state_fd(mic);
-	if (fd < 0) {
-		mpsslog("%s: %s %d open state fd failed %s\n",
-			mic->name, __func__, __LINE__, strerror(errno));
-		goto exit;
-	}
-
-	do {
-		ret = block_till_state_change(fd, mic);
-		if (ret < 0) {
-			mpsslog("%s: %s %d block_till_state_change error %s\n",
-				mic->name, __func__, __LINE__, strerror(errno));
-			goto close_exit;
-		}
-
-		switch (get_mic_state(mic)) {
-		case MIC_SHUTTING_DOWN:
-			mic_handle_shutdown(mic);
-			break;
-		case MIC_READY:
-		case MIC_RESET_FAILED:
-			ret = kill(mic->pid, SIGTERM);
-			mpsslog("%s: %s %d kill pid %d ret %d\n",
-				mic->name, __func__, __LINE__,
-				mic->pid, ret);
-			if (!ret) {
-				ret = waitpid(mic->pid, &stat,
-					      WIFSIGNALED(stat));
-				mpsslog("%s: %s %d waitpid ret %d pid %d\n",
-					mic->name, __func__, __LINE__,
-					ret, mic->pid);
-			}
-			if (mic->boot_on_resume) {
-				setsysfs(mic->name, "state", "boot");
-				mic->boot_on_resume = 0;
-			}
-			goto close_exit;
-		default:
-			break;
-		}
-	} while (1);
-
-close_exit:
-	close(fd);
-exit:
-	init_mic(mic);
-	pthread_exit(NULL);
-}
-
-static void
-set_cmdline(struct mic_info *mic)
-{
-	char buffer[PATH_MAX];
-	int len;
-
-	len = snprintf(buffer, PATH_MAX,
-		"clocksource=tsc highres=off nohz=off ");
-	len += snprintf(buffer + len, PATH_MAX - len,
-		"cpufreq_on;corec6_off;pc3_off;pc6_off ");
-	len += snprintf(buffer + len, PATH_MAX - len,
-		"ifcfg=static;address,172.31.%d.1;netmask,255.255.255.0",
-		mic->id + 1);
-
-	setsysfs(mic->name, "cmdline", buffer);
-	mpsslog("%s: Command line: \"%s\"\n", mic->name, buffer);
-	snprintf(buffer, PATH_MAX, "172.31.%d.1", mic->id + 1);
-	mpsslog("%s: IPADDR: \"%s\"\n", mic->name, buffer);
-}
-
-static void
-set_log_buf_info(struct mic_info *mic)
-{
-	int fd;
-	off_t len;
-	char system_map[] = "/lib/firmware/mic/System.map";
-	char *map, *temp, log_buf[17] = {'\0'};
-
-	fd = open(system_map, O_RDONLY);
-	if (fd < 0) {
-		mpsslog("%s: Opening System.map failed: %d\n",
-			mic->name, errno);
-		return;
-	}
-	len = lseek(fd, 0, SEEK_END);
-	if (len < 0) {
-		mpsslog("%s: Reading System.map size failed: %d\n",
-			mic->name, errno);
-		close(fd);
-		return;
-	}
-	map = mmap(NULL, len, PROT_READ, MAP_PRIVATE, fd, 0);
-	if (map == MAP_FAILED) {
-		mpsslog("%s: mmap of System.map failed: %d\n",
-			mic->name, errno);
-		close(fd);
-		return;
-	}
-	temp = strstr(map, "__log_buf");
-	if (!temp) {
-		mpsslog("%s: __log_buf not found: %d\n", mic->name, errno);
-		munmap(map, len);
-		close(fd);
-		return;
-	}
-	strncpy(log_buf, temp - 19, 16);
-	setsysfs(mic->name, "log_buf_addr", log_buf);
-	mpsslog("%s: log_buf_addr: %s\n", mic->name, log_buf);
-	temp = strstr(map, "log_buf_len");
-	if (!temp) {
-		mpsslog("%s: log_buf_len not found: %d\n", mic->name, errno);
-		munmap(map, len);
-		close(fd);
-		return;
-	}
-	strncpy(log_buf, temp - 19, 16);
-	setsysfs(mic->name, "log_buf_len", log_buf);
-	mpsslog("%s: log_buf_len: %s\n", mic->name, log_buf);
-	munmap(map, len);
-	close(fd);
-}
-
-static void
-change_virtblk_backend(int x, siginfo_t *siginfo, void *p)
-{
-	struct mic_info *mic;
-
-	for (mic = mic_list.next; mic != NULL; mic = mic->next)
-		mic->mic_virtblk.signaled = 1/* true */;
-}
-
-static void
-set_mic_boot_params(struct mic_info *mic)
-{
-	set_log_buf_info(mic);
-	set_cmdline(mic);
-}
-
-static void *
-init_mic(void *arg)
-{
-	struct mic_info *mic = (struct mic_info *)arg;
-	struct sigaction ignore = {
-		.sa_flags = 0,
-		.sa_handler = SIG_IGN
-	};
-	struct sigaction act = {
-		.sa_flags = SA_SIGINFO,
-		.sa_sigaction = change_virtblk_backend,
-	};
-	char buffer[PATH_MAX];
-	int err, fd;
-
-	/*
-	 * Currently, one virtio block device is supported for each MIC card
-	 * at a time. Any user (or test) can send a SIGUSR1 to the MIC daemon.
-	 * The signal informs the virtio block backend about a change in the
-	 * configuration file which specifies the virtio backend file name on
-	 * the host. Virtio block backend then re-reads the configuration file
-	 * and switches to the new block device. This signalling mechanism may
-	 * not be required once multiple virtio block devices are supported by
-	 * the MIC daemon.
-	 */
-	sigaction(SIGUSR1, &ignore, NULL);
-retry:
-	fd = open_state_fd(mic);
-	if (fd < 0) {
-		mpsslog("%s: %s %d open state fd failed %s\n",
-			mic->name, __func__, __LINE__, strerror(errno));
-		sleep(2);
-		goto retry;
-	}
-
-	if (mic->restart) {
-		snprintf(buffer, PATH_MAX, "boot");
-		setsysfs(mic->name, "state", buffer);
-		mpsslog("%s restarting mic %d\n",
-			mic->name, mic->restart);
-		mic->restart = 0;
-	}
-
-	while (1) {
-		while (block_till_state_change(fd, mic)) {
-			mpsslog("%s: %s %d block_till_state_change error %s\n",
-				mic->name, __func__, __LINE__, strerror(errno));
-			sleep(2);
-			continue;
-		}
-
-		if (get_mic_state(mic) == MIC_BOOTING)
-			break;
-	}
-
-	mic->pid = fork();
-	switch (mic->pid) {
-	case 0:
-		add_virtio_device(mic, &virtcons_dev_page.dd);
-		add_virtio_device(mic, &virtnet_dev_page.dd);
-		err = pthread_create(&mic->mic_console.console_thread, NULL,
-			virtio_console, mic);
-		if (err)
-			mpsslog("%s virtcons pthread_create failed %s\n",
-				mic->name, strerror(err));
-		err = pthread_create(&mic->mic_net.net_thread, NULL,
-			virtio_net, mic);
-		if (err)
-			mpsslog("%s virtnet pthread_create failed %s\n",
-				mic->name, strerror(err));
-		err = pthread_create(&mic->mic_virtblk.block_thread, NULL,
-			virtio_block, mic);
-		if (err)
-			mpsslog("%s virtblk pthread_create failed %s\n",
-				mic->name, strerror(err));
-		sigemptyset(&act.sa_mask);
-		err = sigaction(SIGUSR1, &act, NULL);
-		if (err)
-			mpsslog("%s sigaction SIGUSR1 failed %s\n",
-				mic->name, strerror(errno));
-		while (1)
-			sleep(60);
-	case -1:
-		mpsslog("fork failed MIC name %s id %d errno %d\n",
-			mic->name, mic->id, errno);
-		break;
-	default:
-		err = pthread_create(&mic->config_thread, NULL,
-				     mic_config, mic);
-		if (err)
-			mpsslog("%s mic_config pthread_create failed %s\n",
-				mic->name, strerror(err));
-	}
-
-	return NULL;
-}
-
-static void
-start_daemon(void)
-{
-	struct mic_info *mic;
-	int err;
-
-	for (mic = mic_list.next; mic; mic = mic->next) {
-		set_mic_boot_params(mic);
-		err = pthread_create(&mic->init_thread, NULL, init_mic, mic);
-		if (err)
-			mpsslog("%s init_mic pthread_create failed %s\n",
-				mic->name, strerror(err));
-	}
-
-	while (1)
-		sleep(60);
-}
-
-static int
-init_mic_list(void)
-{
-	struct mic_info *mic = &mic_list;
-	struct dirent *file;
-	DIR *dp;
-	int cnt = 0;
-
-	dp = opendir(MICSYSFSDIR);
-	if (!dp)
-		return 0;
-
-	while ((file = readdir(dp)) != NULL) {
-		if (!strncmp(file->d_name, "mic", 3)) {
-			mic->next = calloc(1, sizeof(struct mic_info));
-			if (mic->next) {
-				mic = mic->next;
-				mic->id = atoi(&file->d_name[3]);
-				mic->name = malloc(strlen(file->d_name) + 16);
-				if (mic->name)
-					strcpy(mic->name, file->d_name);
-				mpsslog("MIC name %s id %d\n", mic->name,
-					mic->id);
-				cnt++;
-			}
-		}
-	}
-
-	closedir(dp);
-	return cnt;
-}
-
-void
-mpsslog(char *format, ...)
-{
-	va_list args;
-	char buffer[4096];
-	char ts[52], *ts1;
-	time_t t;
-
-	if (logfp == NULL)
-		return;
-
-	va_start(args, format);
-	vsprintf(buffer, format, args);
-	va_end(args);
-
-	time(&t);
-	ts1 = ctime_r(&t, ts);
-	ts1[strlen(ts1) - 1] = '\0';
-	fprintf(logfp, "%s: %s", ts1, buffer);
-
-	fflush(logfp);
-}
-
-int
-main(int argc, char *argv[])
-{
-	int cnt;
-	pid_t pid;
-
-	myname = argv[0];
-
-	logfp = fopen(LOGFILE_NAME, "a+");
-	if (!logfp) {
-		fprintf(stderr, "cannot open logfile '%s'\n", LOGFILE_NAME);
-		exit(1);
-	}
-	pid = fork();
-	switch (pid) {
-	case 0:
-		break;
-	case -1:
-		exit(2);
-	default:
-		exit(0);
-	}
-
-	mpsslog("MIC Daemon start\n");
-
-	cnt = init_mic_list();
-	if (cnt == 0) {
-		mpsslog("MIC module not loaded\n");
-		exit(3);
-	}
-	mpsslog("MIC found %d devices\n", cnt);
-
-	start_daemon();
-
-	exit(0);
-}
diff --git a/samples/mic/mpssd/mpssd.h b/samples/mic/mpssd/mpssd.h
deleted file mode 100644
index 5f98bdafe653..000000000000
--- a/samples/mic/mpssd/mpssd.h
+++ /dev/null
@@ -1,89 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC User Space Tools.
- */
-#ifndef _MPSSD_H_
-#define _MPSSD_H_
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <fcntl.h>
-#include <unistd.h>
-#include <dirent.h>
-#include <libgen.h>
-#include <pthread.h>
-#include <stdarg.h>
-#include <time.h>
-#include <errno.h>
-#include <sys/dir.h>
-#include <sys/ioctl.h>
-#include <sys/poll.h>
-#include <sys/types.h>
-#include <sys/socket.h>
-#include <sys/stat.h>
-#include <sys/mman.h>
-#include <sys/utsname.h>
-#include <sys/wait.h>
-#include <netinet/in.h>
-#include <arpa/inet.h>
-#include <netdb.h>
-#include <signal.h>
-#include <limits.h>
-#include <syslog.h>
-#include <getopt.h>
-#include <net/if.h>
-#include <linux/if_tun.h>
-#include <linux/virtio_ids.h>
-
-#define MICSYSFSDIR "/sys/class/mic"
-#define LOGFILE_NAME "/var/log/mpssd"
-#define PAGE_SIZE 4096
-
-struct mic_console_info {
-	pthread_t       console_thread;
-	int		virtio_console_fd;
-	void		*console_dp;
-};
-
-struct mic_net_info {
-	pthread_t       net_thread;
-	int		virtio_net_fd;
-	int		tap_fd;
-	void		*net_dp;
-};
-
-struct mic_virtblk_info {
-	pthread_t       block_thread;
-	int		virtio_block_fd;
-	void		*block_dp;
-	volatile sig_atomic_t	signaled;
-	char		*backend_file;
-	int		backend;
-	void		*backend_addr;
-	long		backend_size;
-};
-
-struct mic_info {
-	int		id;
-	char		*name;
-	pthread_t       config_thread;
-	pthread_t       init_thread;
-	pid_t		pid;
-	struct mic_console_info	mic_console;
-	struct mic_net_info	mic_net;
-	struct mic_virtblk_info	mic_virtblk;
-	int		restart;
-	int		boot_on_resume;
-	struct mic_info *next;
-};
-
-__attribute__((format(printf, 1, 2)))
-void mpsslog(char *format, ...);
-char *readsysfs(char *dir, char *entry);
-int setsysfs(char *dir, char *entry, char *value);
-#endif
diff --git a/samples/mic/mpssd/sysfs.c b/samples/mic/mpssd/sysfs.c
deleted file mode 100644
index 3fb08eb7ed9d..000000000000
--- a/samples/mic/mpssd/sysfs.c
+++ /dev/null
@@ -1,91 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC User Space Tools.
- */
-
-#include "mpssd.h"
-
-#define PAGE_SIZE 4096
-
-char *
-readsysfs(char *dir, char *entry)
-{
-	char filename[PATH_MAX];
-	char value[PAGE_SIZE];
-	char *string = NULL;
-	int fd;
-	int len;
-
-	if (dir == NULL)
-		snprintf(filename, PATH_MAX, "%s/%s", MICSYSFSDIR, entry);
-	else
-		snprintf(filename, PATH_MAX,
-			 "%s/%s/%s", MICSYSFSDIR, dir, entry);
-
-	fd = open(filename, O_RDONLY);
-	if (fd < 0) {
-		mpsslog("Failed to open sysfs entry '%s': %s\n",
-			filename, strerror(errno));
-		return NULL;
-	}
-
-	len = read(fd, value, sizeof(value));
-	if (len < 0) {
-		mpsslog("Failed to read sysfs entry '%s': %s\n",
-			filename, strerror(errno));
-		goto readsys_ret;
-	}
-	if (len == 0)
-		goto readsys_ret;
-
-	value[len - 1] = '\0';
-
-	string = malloc(strlen(value) + 1);
-	if (string)
-		strcpy(string, value);
-
-readsys_ret:
-	close(fd);
-	return string;
-}
-
-int
-setsysfs(char *dir, char *entry, char *value)
-{
-	char filename[PATH_MAX];
-	char *oldvalue;
-	int fd, ret = 0;
-
-	if (dir == NULL)
-		snprintf(filename, PATH_MAX, "%s/%s", MICSYSFSDIR, entry);
-	else
-		snprintf(filename, PATH_MAX, "%s/%s/%s",
-			 MICSYSFSDIR, dir, entry);
-
-	oldvalue = readsysfs(dir, entry);
-
-	fd = open(filename, O_RDWR);
-	if (fd < 0) {
-		ret = errno;
-		mpsslog("Failed to open sysfs entry '%s': %s\n",
-			filename, strerror(errno));
-		goto done;
-	}
-
-	if (!oldvalue || strcmp(value, oldvalue)) {
-		if (write(fd, value, strlen(value)) < 0) {
-			ret = errno;
-			mpsslog("Failed to write new sysfs entry '%s': %s\n",
-				filename, strerror(errno));
-		}
-	}
-	close(fd);
-done:
-	if (oldvalue)
-		free(oldvalue);
-	return ret;
-}
-- 
cgit v1.2.3


From 7cb415003468d41aecd6877ae088c38f6c0fc174 Mon Sep 17 00:00:00 2001
From: Peilin Ye <yepeilin.cs@gmail.com>
Date: Wed, 28 Oct 2020 06:56:47 -0400
Subject: Fonts: Make font size unsigned in font_desc

`width` and `height` are defined as unsigned in our UAPI font descriptor
`struct console_font`. Make them unsigned in our kernel font descriptor
`struct font_desc`, too.

Also, change the corresponding printk() format identifiers from `%d` to
`%u`, in sti_select_fbfont().

Signed-off-by: Peilin Ye <yepeilin.cs@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20201028105647.1210161-1-yepeilin.cs@gmail.com
---
 drivers/video/console/sticore.c | 2 +-
 include/linux/font.h            | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/video/console/sticore.c b/drivers/video/console/sticore.c
index 84c3ca37040a..fade32aa6737 100644
--- a/drivers/video/console/sticore.c
+++ b/drivers/video/console/sticore.c
@@ -506,7 +506,7 @@ sti_select_fbfont(struct sti_cooked_rom *cooked_rom, const char *fbfont_name)
 	if (!fbfont)
 		return NULL;
 
-	pr_info("STI selected %dx%d framebuffer font %s for sticon\n",
+	pr_info("STI selected %ux%u framebuffer font %s for sticon\n",
 			fbfont->width, fbfont->height, fbfont->name);
 			
 	bpc = ((fbfont->width+7)/8) * fbfont->height; 
diff --git a/include/linux/font.h b/include/linux/font.h
index 4a3f8741bb7e..b7214d7881f0 100644
--- a/include/linux/font.h
+++ b/include/linux/font.h
@@ -16,7 +16,7 @@
 struct font_desc {
     int idx;
     const char *name;
-    int width, height;
+    unsigned int width, height;
     const void *data;
     int pref;
 };
-- 
cgit v1.2.3


From 8073c1ac82c12aaf1b475a3ce5328d43b3eaa4ae Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sat, 24 Oct 2020 22:35:11 +0100
Subject: genirq/msi: Allow shadow declarations of msi_msg:: $member

Architectures like x86 have their MSI messages in various bits of the data,
address_lo and address_hi field. Composing or decomposing these messages
with bitmasks and shifts is possible, but unreadable gunk.

Allow architectures to provide an architecture specific representation for
each member of msi_msg. Provide empty defaults for each and stick them into
an union.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20201024213535.443185-12-dwmw2@infradead.org
---
 include/asm-generic/msi.h |  4 ++++
 include/linux/msi.h       | 46 ++++++++++++++++++++++++++++++++++++++++++----
 2 files changed, 46 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/asm-generic/msi.h b/include/asm-generic/msi.h
index e6795f088bdd..25344de0e8f9 100644
--- a/include/asm-generic/msi.h
+++ b/include/asm-generic/msi.h
@@ -4,6 +4,8 @@
 
 #include <linux/types.h>
 
+#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN
+
 #ifndef NUM_MSI_ALLOC_SCRATCHPAD_REGS
 # define NUM_MSI_ALLOC_SCRATCHPAD_REGS	2
 #endif
@@ -30,4 +32,6 @@ typedef struct msi_alloc_info {
 
 #define GENERIC_MSI_DOMAIN_OPS		1
 
+#endif /* CONFIG_GENERIC_MSI_IRQ_DOMAIN */
+
 #endif
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 6b584cc4757c..360a0a7e7341 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -4,11 +4,50 @@
 
 #include <linux/kobject.h>
 #include <linux/list.h>
+#include <asm/msi.h>
+
+/* Dummy shadow structures if an architecture does not define them */
+#ifndef arch_msi_msg_addr_lo
+typedef struct arch_msi_msg_addr_lo {
+	u32	address_lo;
+} __attribute__ ((packed)) arch_msi_msg_addr_lo_t;
+#endif
+
+#ifndef arch_msi_msg_addr_hi
+typedef struct arch_msi_msg_addr_hi {
+	u32	address_hi;
+} __attribute__ ((packed)) arch_msi_msg_addr_hi_t;
+#endif
+
+#ifndef arch_msi_msg_data
+typedef struct arch_msi_msg_data {
+	u32	data;
+} __attribute__ ((packed)) arch_msi_msg_data_t;
+#endif
 
+/**
+ * msi_msg - Representation of a MSI message
+ * @address_lo:		Low 32 bits of msi message address
+ * @arch_addrlo:	Architecture specific shadow of @address_lo
+ * @address_hi:		High 32 bits of msi message address
+ *			(only used when device supports it)
+ * @arch_addrhi:	Architecture specific shadow of @address_hi
+ * @data:		MSI message data (usually 16 bits)
+ * @arch_data:		Architecture specific shadow of @data
+ */
 struct msi_msg {
-	u32	address_lo;	/* low 32 bits of msi message address */
-	u32	address_hi;	/* high 32 bits of msi message address */
-	u32	data;		/* 16 bits of msi message data */
+	union {
+		u32			address_lo;
+		arch_msi_msg_addr_lo_t	arch_addr_lo;
+	};
+	union {
+		u32			address_hi;
+		arch_msi_msg_addr_hi_t	arch_addr_hi;
+	};
+	union {
+		u32			data;
+		arch_msi_msg_data_t	arch_data;
+	};
 };
 
 extern int pci_msi_ignore_mask;
@@ -243,7 +282,6 @@ struct msi_controller {
 #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN
 
 #include <linux/irqhandler.h>
-#include <asm/msi.h>
 
 struct irq_domain;
 struct irq_domain_ops;
-- 
cgit v1.2.3


From cf83b2d2e2b64920bd6999b199dfa271d7e94cf8 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Tue, 27 Oct 2020 23:10:54 -0700
Subject: bpf: Permit cond_resched for some iterators

Commit e679654a704e ("bpf: Fix a rcu_sched stall issue with
bpf task/task_file iterator") tries to fix rcu stalls warning
which is caused by bpf task_file iterator when running
"bpftool prog".

      rcu: INFO: rcu_sched self-detected stall on CPU
      rcu: \x097-....: (20999 ticks this GP) idle=302/1/0x4000000000000000 softirq=1508852/1508852 fqs=4913
      \x09(t=21031 jiffies g=2534773 q=179750)
      NMI backtrace for cpu 7
      CPU: 7 PID: 184195 Comm: bpftool Kdump: loaded Tainted: G        W         5.8.0-00004-g68bfc7f8c1b4 #6
      Hardware name: Quanta Twin Lakes MP/Twin Lakes Passive MP, BIOS F09_3A17 05/03/2019
      Call Trace:
      <IRQ>
      dump_stack+0x57/0x70
      nmi_cpu_backtrace.cold+0x14/0x53
      ? lapic_can_unplug_cpu.cold+0x39/0x39
      nmi_trigger_cpumask_backtrace+0xb7/0xc7
      rcu_dump_cpu_stacks+0xa2/0xd0
      rcu_sched_clock_irq.cold+0x1ff/0x3d9
      ? tick_nohz_handler+0x100/0x100
      update_process_times+0x5b/0x90
      tick_sched_timer+0x5e/0xf0
      __hrtimer_run_queues+0x12a/0x2a0
      hrtimer_interrupt+0x10e/0x280
      __sysvec_apic_timer_interrupt+0x51/0xe0
      asm_call_on_stack+0xf/0x20
      </IRQ>
      sysvec_apic_timer_interrupt+0x6f/0x80
      ...
      task_file_seq_next+0x52/0xa0
      bpf_seq_read+0xb9/0x320
      vfs_read+0x9d/0x180
      ksys_read+0x5f/0xe0
      do_syscall_64+0x38/0x60
      entry_SYSCALL_64_after_hwframe+0x44/0xa9

The fix is to limit the number of bpf program runs to be
one million. This fixed the program in most cases. But
we also found under heavy load, which can increase the wallclock
time for bpf_seq_read(), the warning may still be possible.

For example, calling bpf_delay() in the "while" loop of
bpf_seq_read(), which will introduce artificial delay,
the warning will show up in my qemu run.

  static unsigned q;
  volatile unsigned *p = &q;
  volatile unsigned long long ll;
  static void bpf_delay(void)
  {
         int i, j;

         for (i = 0; i < 10000; i++)
                 for (j = 0; j < 10000; j++)
                         ll += *p;
  }

There are two ways to fix this issue. One is to reduce the above
one million threshold to say 100,000 and hopefully rcu warning will
not show up any more. Another is to introduce a target feature
which enables bpf_seq_read() calling cond_resched().

This patch took second approach as the first approach may cause
more -EAGAIN failures for read() syscalls. Note that not all bpf_iter
targets can permit cond_resched() in bpf_seq_read() as some, e.g.,
netlink seq iterator, rcu read lock critical section spans through
seq_ops->next() -> seq_ops->show() -> seq_ops->next().

For the kernel code with the above hack, "bpftool p" roughly takes
38 seconds to finish on my VM with 184 bpf program runs.
Using the following command, I am able to collect the number of
context switches:
   perf stat -e context-switches -- ./bpftool p >& log
Without this patch,
   69      context-switches
With this patch,
   75      context-switches
This patch added additional 6 context switches, roughly every 6 seconds
to reschedule, to avoid lengthy no-rescheduling which may cause the
above RCU warnings.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20201028061054.1411116-1-yhs@fb.com
---
 include/linux/bpf.h    |  5 +++++
 kernel/bpf/bpf_iter.c  | 14 ++++++++++++++
 kernel/bpf/task_iter.c |  2 ++
 3 files changed, 21 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 2b16bf48aab6..2fffd30e13ac 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1294,6 +1294,10 @@ typedef void (*bpf_iter_show_fdinfo_t) (const struct bpf_iter_aux_info *aux,
 typedef int (*bpf_iter_fill_link_info_t)(const struct bpf_iter_aux_info *aux,
 					 struct bpf_link_info *info);
 
+enum bpf_iter_feature {
+	BPF_ITER_RESCHED	= BIT(0),
+};
+
 #define BPF_ITER_CTX_ARG_MAX 2
 struct bpf_iter_reg {
 	const char *target;
@@ -1302,6 +1306,7 @@ struct bpf_iter_reg {
 	bpf_iter_show_fdinfo_t show_fdinfo;
 	bpf_iter_fill_link_info_t fill_link_info;
 	u32 ctx_arg_info_size;
+	u32 feature;
 	struct bpf_ctx_arg_aux ctx_arg_info[BPF_ITER_CTX_ARG_MAX];
 	const struct bpf_iter_seq_info *seq_info;
 };
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index 8f10e30ea0b0..5454161407f1 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -67,6 +67,15 @@ static void bpf_iter_done_stop(struct seq_file *seq)
 	iter_priv->done_stop = true;
 }
 
+static bool bpf_iter_support_resched(struct seq_file *seq)
+{
+	struct bpf_iter_priv_data *iter_priv;
+
+	iter_priv = container_of(seq->private, struct bpf_iter_priv_data,
+				 target_private);
+	return iter_priv->tinfo->reg_info->feature & BPF_ITER_RESCHED;
+}
+
 /* maximum visited objects before bailing out */
 #define MAX_ITER_OBJECTS	1000000
 
@@ -83,6 +92,7 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size,
 	struct seq_file *seq = file->private_data;
 	size_t n, offs, copied = 0;
 	int err = 0, num_objs = 0;
+	bool can_resched;
 	void *p;
 
 	mutex_lock(&seq->lock);
@@ -135,6 +145,7 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size,
 		goto done;
 	}
 
+	can_resched = bpf_iter_support_resched(seq);
 	while (1) {
 		loff_t pos = seq->index;
 
@@ -180,6 +191,9 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size,
 			}
 			break;
 		}
+
+		if (can_resched)
+			cond_resched();
 	}
 stop:
 	offs = seq->count;
diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index 5b6af30bfbcd..1fdb2fc196cd 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -337,6 +337,7 @@ static const struct bpf_iter_seq_info task_seq_info = {
 
 static struct bpf_iter_reg task_reg_info = {
 	.target			= "task",
+	.feature		= BPF_ITER_RESCHED,
 	.ctx_arg_info_size	= 1,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__task, task),
@@ -354,6 +355,7 @@ static const struct bpf_iter_seq_info task_file_seq_info = {
 
 static struct bpf_iter_reg task_file_reg_info = {
 	.target			= "task_file",
+	.feature		= BPF_ITER_RESCHED,
 	.ctx_arg_info_size	= 2,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__task_file, task),
-- 
cgit v1.2.3


From 5c251e9dc0e127bac6fc5b8e6696363d2e35f515 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Mon, 26 Oct 2020 14:32:27 -0600
Subject: signal: Add task_sigpending() helper

This is in preparation for maintaining signal_pending() as the decider of
whether or not a schedule() loop should be broken, or continue sleeping.
This is different than the core signal use cases, which really need to know
whether an actual signal is pending or not. task_sigpending() returns
non-zero if TIF_SIGPENDING is set.

Only core kernel use cases should care about the distinction between
the two, make sure those use the task_sigpending() helper.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Link: https://lore.kernel.org/r/20201026203230.386348-2-axboe@kernel.dk
---
 include/linux/sched/signal.h | 9 +++++++--
 kernel/events/uprobes.c      | 2 +-
 kernel/signal.c              | 8 ++++----
 3 files changed, 12 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 1bad18a1d8ba..404145dc536e 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -353,11 +353,16 @@ static inline int restart_syscall(void)
 	return -ERESTARTNOINTR;
 }
 
-static inline int signal_pending(struct task_struct *p)
+static inline int task_sigpending(struct task_struct *p)
 {
 	return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING));
 }
 
+static inline int signal_pending(struct task_struct *p)
+{
+	return task_sigpending(p);
+}
+
 static inline int __fatal_signal_pending(struct task_struct *p)
 {
 	return unlikely(sigismember(&p->pending.signal, SIGKILL));
@@ -365,7 +370,7 @@ static inline int __fatal_signal_pending(struct task_struct *p)
 
 static inline int fatal_signal_pending(struct task_struct *p)
 {
-	return signal_pending(p) && __fatal_signal_pending(p);
+	return task_sigpending(p) && __fatal_signal_pending(p);
 }
 
 static inline int signal_pending_state(long state, struct task_struct *p)
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 649fd53dc9ad..edd0c985a939 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1973,7 +1973,7 @@ bool uprobe_deny_signal(void)
 
 	WARN_ON_ONCE(utask->state != UTASK_SSTEP);
 
-	if (signal_pending(t)) {
+	if (task_sigpending(t)) {
 		spin_lock_irq(&t->sighand->siglock);
 		clear_tsk_thread_flag(t, TIF_SIGPENDING);
 		spin_unlock_irq(&t->sighand->siglock);
diff --git a/kernel/signal.c b/kernel/signal.c
index 42b67d2cea37..b179eccc86d0 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -983,7 +983,7 @@ static inline bool wants_signal(int sig, struct task_struct *p)
 	if (task_is_stopped_or_traced(p))
 		return false;
 
-	return task_curr(p) || !signal_pending(p);
+	return task_curr(p) || !task_sigpending(p);
 }
 
 static void complete_signal(int sig, struct task_struct *p, enum pid_type type)
@@ -2822,7 +2822,7 @@ static void retarget_shared_pending(struct task_struct *tsk, sigset_t *which)
 		/* Remove the signals this thread can handle. */
 		sigandsets(&retarget, &retarget, &t->blocked);
 
-		if (!signal_pending(t))
+		if (!task_sigpending(t))
 			signal_wake_up(t, 0);
 
 		if (sigisemptyset(&retarget))
@@ -2856,7 +2856,7 @@ void exit_signals(struct task_struct *tsk)
 
 	cgroup_threadgroup_change_end(tsk);
 
-	if (!signal_pending(tsk))
+	if (!task_sigpending(tsk))
 		goto out;
 
 	unblocked = tsk->blocked;
@@ -2900,7 +2900,7 @@ long do_no_restart_syscall(struct restart_block *param)
 
 static void __set_task_blocked(struct task_struct *tsk, const sigset_t *newset)
 {
-	if (signal_pending(tsk) && !thread_group_empty(tsk)) {
+	if (task_sigpending(tsk) && !thread_group_empty(tsk)) {
 		sigset_t newblocked;
 		/* A set of now blocked but previously unblocked signals. */
 		sigandnsets(&newblocked, newset, &current->blocked);
-- 
cgit v1.2.3


From 12db8b690010ccfadf9d0b49a1e1798e47dbbe1a Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Mon, 26 Oct 2020 14:32:28 -0600
Subject: entry: Add support for TIF_NOTIFY_SIGNAL

Add TIF_NOTIFY_SIGNAL handling in the generic entry code, which if set,
will return true if signal_pending() is used in a wait loop. That causes an
exit of the loop so that notify_signal tracehooks can be run. If the wait
loop is currently inside a system call, the system call is restarted once
task_work has been processed.

In preparation for only having arch_do_signal() handle syscall restarts if
_TIF_SIGPENDING isn't set, rename it to arch_do_signal_or_restart().  Pass
in a boolean that tells the architecture specific signal handler if it
should attempt to get a signal, or just process a potential syscall
restart.

For !CONFIG_GENERIC_ENTRY archs, add the TIF_NOTIFY_SIGNAL handling to
get_signal(). This is done to minimize the needed architecture changes to
support this feature.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Link: https://lore.kernel.org/r/20201026203230.386348-3-axboe@kernel.dk
---
 arch/x86/kernel/signal.c     |  4 ++--
 include/linux/entry-common.h | 11 ++++++++---
 include/linux/entry-kvm.h    |  4 ++--
 include/linux/sched/signal.h | 11 ++++++++++-
 include/linux/tracehook.h    | 27 +++++++++++++++++++++++++++
 kernel/entry/common.c        | 14 +++++++++++---
 kernel/entry/kvm.c           |  3 +++
 kernel/signal.c              | 14 ++++++++++++++
 8 files changed, 77 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index d5fa494c2304..ec3b9c6e5a4c 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -804,11 +804,11 @@ static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs)
  * want to handle. Thus you cannot kill init even with a SIGKILL even by
  * mistake.
  */
-void arch_do_signal(struct pt_regs *regs)
+void arch_do_signal_or_restart(struct pt_regs *regs, bool has_signal)
 {
 	struct ksignal ksig;
 
-	if (get_signal(&ksig)) {
+	if (has_signal && get_signal(&ksig)) {
 		/* Whee! Actually deliver the signal.  */
 		handle_signal(&ksig, regs);
 		return;
diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index efebbffcd5cc..c7bfac45f951 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -37,6 +37,10 @@
 # define _TIF_UPROBE			(0)
 #endif
 
+#ifndef _TIF_NOTIFY_SIGNAL
+# define _TIF_NOTIFY_SIGNAL		(0)
+#endif
+
 /*
  * TIF flags handled in syscall_enter_from_usermode()
  */
@@ -69,7 +73,7 @@
 
 #define EXIT_TO_USER_MODE_WORK						\
 	(_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE |		\
-	 _TIF_NEED_RESCHED | _TIF_PATCH_PENDING |			\
+	 _TIF_NEED_RESCHED | _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL |	\
 	 ARCH_EXIT_TO_USER_MODE_WORK)
 
 /**
@@ -226,12 +230,13 @@ static __always_inline void arch_exit_to_user_mode(void) { }
 #endif
 
 /**
- * arch_do_signal -  Architecture specific signal delivery function
+ * arch_do_signal_or_restart -  Architecture specific signal delivery function
  * @regs:	Pointer to currents pt_regs
+ * @has_signal:	actual signal to handle
  *
  * Invoked from exit_to_user_mode_loop().
  */
-void arch_do_signal(struct pt_regs *regs);
+void arch_do_signal_or_restart(struct pt_regs *regs, bool has_signal);
 
 /**
  * arch_syscall_exit_tracehook - Wrapper around tracehook_report_syscall_exit()
diff --git a/include/linux/entry-kvm.h b/include/linux/entry-kvm.h
index 0cef17afb41a..9b93f8584ff7 100644
--- a/include/linux/entry-kvm.h
+++ b/include/linux/entry-kvm.h
@@ -11,8 +11,8 @@
 # define ARCH_XFER_TO_GUEST_MODE_WORK	(0)
 #endif
 
-#define XFER_TO_GUEST_MODE_WORK					\
-	(_TIF_NEED_RESCHED | _TIF_SIGPENDING |			\
+#define XFER_TO_GUEST_MODE_WORK						\
+	(_TIF_NEED_RESCHED | _TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL |	\
 	 _TIF_NOTIFY_RESUME | ARCH_XFER_TO_GUEST_MODE_WORK)
 
 struct kvm_vcpu;
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 404145dc536e..bd5afa076189 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -360,6 +360,15 @@ static inline int task_sigpending(struct task_struct *p)
 
 static inline int signal_pending(struct task_struct *p)
 {
+#if defined(TIF_NOTIFY_SIGNAL)
+	/*
+	 * TIF_NOTIFY_SIGNAL isn't really a signal, but it requires the same
+	 * behavior in terms of ensuring that we break out of wait loops
+	 * so that notify signal callbacks can be processed.
+	 */
+	if (unlikely(test_tsk_thread_flag(p, TIF_NOTIFY_SIGNAL)))
+		return 1;
+#endif
 	return task_sigpending(p);
 }
 
@@ -507,7 +516,7 @@ extern int set_user_sigmask(const sigset_t __user *umask, size_t sigsetsize);
 static inline void restore_saved_sigmask_unless(bool interrupted)
 {
 	if (interrupted)
-		WARN_ON(!test_thread_flag(TIF_SIGPENDING));
+		WARN_ON(!signal_pending(current));
 	else
 		restore_saved_sigmask();
 }
diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h
index 36fb3bbed6b2..1e8caca92e1f 100644
--- a/include/linux/tracehook.h
+++ b/include/linux/tracehook.h
@@ -198,4 +198,31 @@ static inline void tracehook_notify_resume(struct pt_regs *regs)
 	blkcg_maybe_throttle_current();
 }
 
+/*
+ * called by exit_to_user_mode_loop() if ti_work & _TIF_NOTIFY_SIGNAL. This
+ * is currently used by TWA_SIGNAL based task_work, which requires breaking
+ * wait loops to ensure that task_work is noticed and run.
+ */
+static inline void tracehook_notify_signal(void)
+{
+#if defined(TIF_NOTIFY_SIGNAL)
+	clear_thread_flag(TIF_NOTIFY_SIGNAL);
+	smp_mb__after_atomic();
+	if (current->task_works)
+		task_work_run();
+#endif
+}
+
+/*
+ * Called when we have work to process from exit_to_user_mode_loop()
+ */
+static inline void set_notify_signal(struct task_struct *task)
+{
+#if defined(TIF_NOTIFY_SIGNAL)
+	if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) &&
+	    !wake_up_state(task, TASK_INTERRUPTIBLE))
+		kick_process(task);
+#endif
+}
+
 #endif	/* <linux/tracehook.h> */
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 9852e0d62d95..42eff115c426 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -109,7 +109,15 @@ static __always_inline void exit_to_user_mode(void)
 }
 
 /* Workaround to allow gradual conversion of architecture code */
-void __weak arch_do_signal(struct pt_regs *regs) { }
+void __weak arch_do_signal_or_restart(struct pt_regs *regs, bool has_signal) { }
+
+static void handle_signal_work(struct pt_regs *regs, unsigned long ti_work)
+{
+	if (ti_work & _TIF_NOTIFY_SIGNAL)
+		tracehook_notify_signal();
+
+	arch_do_signal_or_restart(regs, ti_work & _TIF_SIGPENDING);
+}
 
 static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
 					    unsigned long ti_work)
@@ -131,8 +139,8 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
 		if (ti_work & _TIF_PATCH_PENDING)
 			klp_update_patch_state(current);
 
-		if (ti_work & _TIF_SIGPENDING)
-			arch_do_signal(regs);
+		if (ti_work & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL))
+			handle_signal_work(regs, ti_work);
 
 		if (ti_work & _TIF_NOTIFY_RESUME) {
 			clear_thread_flag(TIF_NOTIFY_RESUME);
diff --git a/kernel/entry/kvm.c b/kernel/entry/kvm.c
index eb1a8a4c867c..b828a3ddebf1 100644
--- a/kernel/entry/kvm.c
+++ b/kernel/entry/kvm.c
@@ -8,6 +8,9 @@ static int xfer_to_guest_mode_work(struct kvm_vcpu *vcpu, unsigned long ti_work)
 	do {
 		int ret;
 
+		if (ti_work & _TIF_NOTIFY_SIGNAL)
+			tracehook_notify_signal();
+
 		if (ti_work & _TIF_SIGPENDING) {
 			kvm_handle_signal_exit(vcpu);
 			return -EINTR;
diff --git a/kernel/signal.c b/kernel/signal.c
index b179eccc86d0..61b377e65c46 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2529,6 +2529,20 @@ bool get_signal(struct ksignal *ksig)
 	struct signal_struct *signal = current->signal;
 	int signr;
 
+	/*
+	 * For non-generic architectures, check for TIF_NOTIFY_SIGNAL so
+	 * that the arch handlers don't all have to do it. If we get here
+	 * without TIF_SIGPENDING, just exit after running signal work.
+	 */
+#ifdef TIF_NOTIFY_SIGNAL
+	if (!IS_ENABLED(CONFIG_GENERIC_ENTRY)) {
+		if (test_thread_flag(TIF_NOTIFY_SIGNAL))
+			tracehook_notify_signal();
+		if (!task_sigpending(current))
+			return false;
+	}
+#endif
+
 	if (unlikely(uprobe_deny_signal()))
 		return false;
 
-- 
cgit v1.2.3


From 5bc78502322a5e4eef3f1b2a2813751dc6434143 Mon Sep 17 00:00:00 2001
From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Date: Tue, 20 Oct 2020 09:47:13 -0400
Subject: sched: fix exit_mm vs membarrier (v4)

exit_mm should issue memory barriers after user-space memory accesses,
before clearing current->mm, to order user-space memory accesses
performed prior to exit_mm before clearing tsk->mm, which has the
effect of skipping the membarrier private expedited IPIs.

exit_mm should also update the runqueue's membarrier_state so
membarrier global expedited IPIs are not sent when they are not
needed.

The membarrier system call can be issued concurrently with do_exit
if we have thread groups created with CLONE_VM but not CLONE_THREAD.

Here is the scenario I have in mind:

Two thread groups are created, A and B. Thread group B is created by
issuing clone from group A with flag CLONE_VM set, but not CLONE_THREAD.
Let's assume we have a single thread within each thread group (Thread A
and Thread B).

The AFAIU we can have:

Userspace variables:

int x = 0, y = 0;

CPU 0                   CPU 1
Thread A                Thread B
(in thread group A)     (in thread group B)

x = 1
barrier()
y = 1
exit()
exit_mm()
current->mm = NULL;
                        r1 = load y
                        membarrier()
                          skips CPU 0 (no IPI) because its current mm is NULL
                        r2 = load x
                        BUG_ON(r1 == 1 && r2 == 0)

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20201020134715.13909-2-mathieu.desnoyers@efficios.com
---
 include/linux/sched/mm.h  |  5 +++++
 kernel/exit.c             | 16 +++++++++++++++-
 kernel/sched/membarrier.c | 12 ++++++++++++
 3 files changed, 32 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index d5ece7a9a403..a91fb3ad9ec7 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -347,6 +347,8 @@ static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm)
 
 extern void membarrier_exec_mmap(struct mm_struct *mm);
 
+extern void membarrier_update_current_mm(struct mm_struct *next_mm);
+
 #else
 #ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS
 static inline void membarrier_arch_switch_mm(struct mm_struct *prev,
@@ -361,6 +363,9 @@ static inline void membarrier_exec_mmap(struct mm_struct *mm)
 static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm)
 {
 }
+static inline void membarrier_update_current_mm(struct mm_struct *next_mm)
+{
+}
 #endif
 
 #endif /* _LINUX_SCHED_MM_H */
diff --git a/kernel/exit.c b/kernel/exit.c
index 87a2d515de0d..a3dd6b36f99a 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -475,10 +475,24 @@ static void exit_mm(void)
 	BUG_ON(mm != current->active_mm);
 	/* more a memory barrier than a real lock */
 	task_lock(current);
+	/*
+	 * When a thread stops operating on an address space, the loop
+	 * in membarrier_private_expedited() may not observe that
+	 * tsk->mm, and the loop in membarrier_global_expedited() may
+	 * not observe a MEMBARRIER_STATE_GLOBAL_EXPEDITED
+	 * rq->membarrier_state, so those would not issue an IPI.
+	 * Membarrier requires a memory barrier after accessing
+	 * user-space memory, before clearing tsk->mm or the
+	 * rq->membarrier_state.
+	 */
+	smp_mb__after_spinlock();
+	local_irq_disable();
 	current->mm = NULL;
-	mmap_read_unlock(mm);
+	membarrier_update_current_mm(NULL);
 	enter_lazy_tlb(mm, current);
+	local_irq_enable();
 	task_unlock(current);
+	mmap_read_unlock(mm);
 	mm_update_next_owner(mm);
 	mmput(mm);
 	if (test_thread_flag(TIF_MEMDIE))
diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
index e23e74d52db5..aac329258af0 100644
--- a/kernel/sched/membarrier.c
+++ b/kernel/sched/membarrier.c
@@ -76,6 +76,18 @@ void membarrier_exec_mmap(struct mm_struct *mm)
 	this_cpu_write(runqueues.membarrier_state, 0);
 }
 
+void membarrier_update_current_mm(struct mm_struct *next_mm)
+{
+	struct rq *rq = this_rq();
+	int membarrier_state = 0;
+
+	if (next_mm)
+		membarrier_state = atomic_read(&next_mm->membarrier_state);
+	if (READ_ONCE(rq->membarrier_state) == membarrier_state)
+		return;
+	WRITE_ONCE(rq->membarrier_state, membarrier_state);
+}
+
 static int membarrier_global_expedited(void)
 {
 	int cpu;
-- 
cgit v1.2.3


From 8d97e71811aaafe4abf611dc24822fd6e73df1a1 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Thu, 1 Oct 2020 06:57:46 -0700
Subject: perf/core: Add PERF_SAMPLE_DATA_PAGE_SIZE

Current perf can report both virtual addresses and physical addresses,
but not the MMU page size. Without the MMU page size information of the
utilized page, users cannot decide whether to promote/demote large pages
to optimize memory usage.

Add a new sample type for the data MMU page size.

Current perf already has a facility to collect data virtual addresses.
A page walker is required to walk the pages tables and calculate the
MMU page size from a given virtual address.

On some platforms, e.g., X86, the page walker is invoked in an NMI
handler. So the page walker must be NMI-safe and low overhead. Besides,
the page walker should work for both user and kernel virtual address.
The existing generic page walker, e.g., walk_page_range_novma(), is a
little bit complex and doesn't guarantee the NMI-safe. The follow_page()
is only for user-virtual address.

Add a new function perf_get_page_size() to walk the page tables and
calculate the MMU page size. In the function:
- Interrupts have to be disabled to prevent any teardown of the page
  tables.
- For user space threads, the current->mm is used for the page walker.
  For kernel threads and the like, the current->mm is NULL. The init_mm
  is used for the page walker. The active_mm is not used here, because
  it can be NULL.
  Quote from Peter Zijlstra,
  "context_switch() can set prev->active_mm to NULL when it transfers it
   to @next. It does this before @current is updated. So an NMI that
   comes in between this active_mm swizzling and updating @current will
   see !active_mm."
- The MMU page size is calculated from the page table level.

The method should work for all architectures, but it has only been
verified on X86. Should there be some architectures, which support perf,
where the method doesn't work, it can be fixed later separately.
Reporting the wrong page size would not be fatal for the architecture.

Some under discussion features may impact the method in the future.
Quote from Dave Hansen,
  "There are lots of weird things folks are trying to do with the page
   tables, like Address Space Isolation.  For instance, if you get a
   perf NMI when running userspace, current->mm->pgd is *different* than
   the PGD that was in use when userspace was running. It's close enough
   today, but it might not stay that way."
If the case happens later, lots of consecutive page walk errors will
happen. The worst case is that lots of page-size '0' are returned, which
would not be fatal.
In the perf tool, a check is implemented to detect this case. Once it
happens, a kernel patch could be implemented accordingly then.

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20201001135749.2804-2-kan.liang@linux.intel.com
---
 include/linux/perf_event.h      |   1 +
 include/uapi/linux/perf_event.h |   4 +-
 kernel/events/core.c            | 103 ++++++++++++++++++++++++++++++++++++++++
 3 files changed, 107 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 0c19d279b97f..7e3785dd27d9 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1034,6 +1034,7 @@ struct perf_sample_data {
 
 	u64				phys_addr;
 	u64				cgroup;
+	u64				data_page_size;
 } ____cacheline_aligned;
 
 /* default value for data source */
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 077e7ee69e3d..cc6ea346e9f9 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -143,8 +143,9 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_PHYS_ADDR			= 1U << 19,
 	PERF_SAMPLE_AUX				= 1U << 20,
 	PERF_SAMPLE_CGROUP			= 1U << 21,
+	PERF_SAMPLE_DATA_PAGE_SIZE		= 1U << 22,
 
-	PERF_SAMPLE_MAX = 1U << 22,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 23,		/* non-ABI */
 
 	__PERF_SAMPLE_CALLCHAIN_EARLY		= 1ULL << 63, /* non-ABI; internal use */
 };
@@ -896,6 +897,7 @@ enum perf_event_type {
 	 *	{ u64			phys_addr;} && PERF_SAMPLE_PHYS_ADDR
 	 *	{ u64			size;
 	 *	  char			data[size]; } && PERF_SAMPLE_AUX
+	 *	{ u64			data_page_size;} && PERF_SAMPLE_DATA_PAGE_SIZE
 	 * };
 	 */
 	PERF_RECORD_SAMPLE			= 9,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index fb662eb4fb69..a796db2f3b57 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -51,6 +51,7 @@
 #include <linux/proc_ns.h>
 #include <linux/mount.h>
 #include <linux/min_heap.h>
+#include <linux/highmem.h>
 
 #include "internal.h"
 
@@ -1894,6 +1895,9 @@ static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
 	if (sample_type & PERF_SAMPLE_CGROUP)
 		size += sizeof(data->cgroup);
 
+	if (sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)
+		size += sizeof(data->data_page_size);
+
 	event->header_size = size;
 }
 
@@ -6938,6 +6942,9 @@ void perf_output_sample(struct perf_output_handle *handle,
 	if (sample_type & PERF_SAMPLE_CGROUP)
 		perf_output_put(handle, data->cgroup);
 
+	if (sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)
+		perf_output_put(handle, data->data_page_size);
+
 	if (sample_type & PERF_SAMPLE_AUX) {
 		perf_output_put(handle, data->aux_size);
 
@@ -6995,6 +7002,94 @@ static u64 perf_virt_to_phys(u64 virt)
 	return phys_addr;
 }
 
+#ifdef CONFIG_MMU
+
+/*
+ * Return the MMU page size of a given virtual address
+ */
+static u64 __perf_get_page_size(struct mm_struct *mm, unsigned long addr)
+{
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+
+	pgd = pgd_offset(mm, addr);
+	if (pgd_none(*pgd))
+		return 0;
+
+	p4d = p4d_offset(pgd, addr);
+	if (!p4d_present(*p4d))
+		return 0;
+
+	if (p4d_leaf(*p4d))
+		return 1ULL << P4D_SHIFT;
+
+	pud = pud_offset(p4d, addr);
+	if (!pud_present(*pud))
+		return 0;
+
+	if (pud_leaf(*pud))
+		return 1ULL << PUD_SHIFT;
+
+	pmd = pmd_offset(pud, addr);
+	if (!pmd_present(*pmd))
+		return 0;
+
+	if (pmd_leaf(*pmd))
+		return 1ULL << PMD_SHIFT;
+
+	pte = pte_offset_map(pmd, addr);
+	if (!pte_present(*pte)) {
+		pte_unmap(pte);
+		return 0;
+	}
+
+	pte_unmap(pte);
+	return PAGE_SIZE;
+}
+
+#else
+
+static u64 __perf_get_page_size(struct mm_struct *mm, unsigned long addr)
+{
+	return 0;
+}
+
+#endif
+
+static u64 perf_get_page_size(unsigned long addr)
+{
+	struct mm_struct *mm;
+	unsigned long flags;
+	u64 size;
+
+	if (!addr)
+		return 0;
+
+	/*
+	 * Software page-table walkers must disable IRQs,
+	 * which prevents any tear down of the page tables.
+	 */
+	local_irq_save(flags);
+
+	mm = current->mm;
+	if (!mm) {
+		/*
+		 * For kernel threads and the like, use init_mm so that
+		 * we can find kernel memory.
+		 */
+		mm = &init_mm;
+	}
+
+	size = __perf_get_page_size(mm, addr);
+
+	local_irq_restore(flags);
+
+	return size;
+}
+
 static struct perf_callchain_entry __empty_callchain = { .nr = 0, };
 
 struct perf_callchain_entry *
@@ -7150,6 +7245,14 @@ void perf_prepare_sample(struct perf_event_header *header,
 	}
 #endif
 
+	/*
+	 * PERF_DATA_PAGE_SIZE requires PERF_SAMPLE_ADDR. If the user doesn't
+	 * require PERF_SAMPLE_ADDR, kernel implicitly retrieve the data->addr,
+	 * but the value will not dump to the userspace.
+	 */
+	if (sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)
+		data->data_page_size = perf_get_page_size(data->addr);
+
 	if (sample_type & PERF_SAMPLE_AUX) {
 		u64 size;
 
-- 
cgit v1.2.3


From 995f088efebe1eba0282a6ffa12411b37f8990c2 Mon Sep 17 00:00:00 2001
From: Stephane Eranian <eranian@google.com>
Date: Thu, 1 Oct 2020 06:57:49 -0700
Subject: perf/core: Add support for PERF_SAMPLE_CODE_PAGE_SIZE

When studying code layout, it is useful to capture the page size of the
sampled code address.

Add a new sample type for code page size.
The new sample type requires collecting the ip. The code page size can
be calculated from the NMI-safe perf_get_page_size().

For large PEBS, it's very unlikely that the mapping is gone for the
earlier PEBS records. Enable the feature for the large PEBS. The worst
case is that page-size '0' is returned.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20201001135749.2804-5-kan.liang@linux.intel.com
---
 arch/x86/events/perf_event.h    |  2 +-
 include/linux/perf_event.h      |  1 +
 include/uapi/linux/perf_event.h |  4 +++-
 kernel/events/core.c            | 11 ++++++++++-
 4 files changed, 15 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index ee2b9b9fc2a5..10032f023fcc 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -132,7 +132,7 @@ struct amd_nb {
 	PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \
 	PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR | \
 	PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER | \
-	PERF_SAMPLE_PERIOD)
+	PERF_SAMPLE_PERIOD | PERF_SAMPLE_CODE_PAGE_SIZE)
 
 #define PEBS_GP_REGS			\
 	((1ULL << PERF_REG_X86_AX)    | \
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 7e3785dd27d9..e533b03af053 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1035,6 +1035,7 @@ struct perf_sample_data {
 	u64				phys_addr;
 	u64				cgroup;
 	u64				data_page_size;
+	u64				code_page_size;
 } ____cacheline_aligned;
 
 /* default value for data source */
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index cc6ea346e9f9..c2f20ee3124d 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -144,8 +144,9 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_AUX				= 1U << 20,
 	PERF_SAMPLE_CGROUP			= 1U << 21,
 	PERF_SAMPLE_DATA_PAGE_SIZE		= 1U << 22,
+	PERF_SAMPLE_CODE_PAGE_SIZE		= 1U << 23,
 
-	PERF_SAMPLE_MAX = 1U << 23,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 24,		/* non-ABI */
 
 	__PERF_SAMPLE_CALLCHAIN_EARLY		= 1ULL << 63, /* non-ABI; internal use */
 };
@@ -898,6 +899,7 @@ enum perf_event_type {
 	 *	{ u64			size;
 	 *	  char			data[size]; } && PERF_SAMPLE_AUX
 	 *	{ u64			data_page_size;} && PERF_SAMPLE_DATA_PAGE_SIZE
+	 *	{ u64			code_page_size;} && PERF_SAMPLE_CODE_PAGE_SIZE
 	 * };
 	 */
 	PERF_RECORD_SAMPLE			= 9,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index a796db2f3b57..7f655d19b8c4 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1898,6 +1898,9 @@ static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
 	if (sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)
 		size += sizeof(data->data_page_size);
 
+	if (sample_type & PERF_SAMPLE_CODE_PAGE_SIZE)
+		size += sizeof(data->code_page_size);
+
 	event->header_size = size;
 }
 
@@ -6945,6 +6948,9 @@ void perf_output_sample(struct perf_output_handle *handle,
 	if (sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)
 		perf_output_put(handle, data->data_page_size);
 
+	if (sample_type & PERF_SAMPLE_CODE_PAGE_SIZE)
+		perf_output_put(handle, data->code_page_size);
+
 	if (sample_type & PERF_SAMPLE_AUX) {
 		perf_output_put(handle, data->aux_size);
 
@@ -7125,7 +7131,7 @@ void perf_prepare_sample(struct perf_event_header *header,
 
 	__perf_event_header__init_id(header, data, event);
 
-	if (sample_type & PERF_SAMPLE_IP)
+	if (sample_type & (PERF_SAMPLE_IP | PERF_SAMPLE_CODE_PAGE_SIZE))
 		data->ip = perf_instruction_pointer(regs);
 
 	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
@@ -7253,6 +7259,9 @@ void perf_prepare_sample(struct perf_event_header *header,
 	if (sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)
 		data->data_page_size = perf_get_page_size(data->addr);
 
+	if (sample_type & PERF_SAMPLE_CODE_PAGE_SIZE)
+		data->code_page_size = perf_get_page_size(data->ip);
+
 	if (sample_type & PERF_SAMPLE_AUX) {
 		u64 size;
 
-- 
cgit v1.2.3


From 51b646b2d9f84d6ff6300e3c1d09f2be4329a424 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 9 Oct 2020 11:09:27 +0200
Subject: perf,mm: Handle non-page-table-aligned hugetlbfs

A limited nunmber of architectures support hugetlbfs sizes that do not
align with the page-tables (ARM64, Power, Sparc64). Add support for
this to the generic perf_get_page_size() implementation, and also
allow an architecture to override this implementation.

This latter is only needed when it uses non-page-table aligned huge
pages in its kernel map.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 include/linux/perf_event.h |  4 ++++
 kernel/events/core.c       | 39 +++++++++++++++++++++++++++++++++------
 2 files changed, 37 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index e533b03af053..0defb526cd0c 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1590,4 +1590,8 @@ extern void __weak arch_perf_update_userpage(struct perf_event *event,
 					     struct perf_event_mmap_page *userpg,
 					     u64 now);
 
+#ifdef CONFIG_MMU
+extern __weak u64 arch_perf_get_page_size(struct mm_struct *mm, unsigned long addr);
+#endif
+
 #endif /* _LINUX_PERF_EVENT_H */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 7f655d19b8c4..b458ed3dc81b 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7011,10 +7011,18 @@ static u64 perf_virt_to_phys(u64 virt)
 #ifdef CONFIG_MMU
 
 /*
- * Return the MMU page size of a given virtual address
+ * Return the MMU page size of a given virtual address.
+ *
+ * This generic implementation handles page-table aligned huge pages, as well
+ * as non-page-table aligned hugetlbfs compound pages.
+ *
+ * If an architecture supports and uses non-page-table aligned pages in their
+ * kernel mapping it will need to provide it's own implementation of this
+ * function.
  */
-static u64 __perf_get_page_size(struct mm_struct *mm, unsigned long addr)
+__weak u64 arch_perf_get_page_size(struct mm_struct *mm, unsigned long addr)
 {
+	struct page *page;
 	pgd_t *pgd;
 	p4d_t *p4d;
 	pud_t *pud;
@@ -7036,15 +7044,27 @@ static u64 __perf_get_page_size(struct mm_struct *mm, unsigned long addr)
 	if (!pud_present(*pud))
 		return 0;
 
-	if (pud_leaf(*pud))
+	if (pud_leaf(*pud)) {
+#ifdef pud_page
+		page = pud_page(*pud);
+		if (PageHuge(page))
+			return page_size(compound_head(page));
+#endif
 		return 1ULL << PUD_SHIFT;
+	}
 
 	pmd = pmd_offset(pud, addr);
 	if (!pmd_present(*pmd))
 		return 0;
 
-	if (pmd_leaf(*pmd))
+	if (pmd_leaf(*pmd)) {
+#ifdef pmd_page
+		page = pmd_page(*pmd);
+		if (PageHuge(page))
+			return page_size(compound_head(page));
+#endif
 		return 1ULL << PMD_SHIFT;
+	}
 
 	pte = pte_offset_map(pmd, addr);
 	if (!pte_present(*pte)) {
@@ -7052,13 +7072,20 @@ static u64 __perf_get_page_size(struct mm_struct *mm, unsigned long addr)
 		return 0;
 	}
 
+	page = pte_page(*pte);
+	if (PageHuge(page)) {
+		u64 size = page_size(compound_head(page));
+		pte_unmap(pte);
+		return size;
+	}
+
 	pte_unmap(pte);
 	return PAGE_SIZE;
 }
 
 #else
 
-static u64 __perf_get_page_size(struct mm_struct *mm, unsigned long addr)
+static u64 arch_perf_get_page_size(struct mm_struct *mm, unsigned long addr)
 {
 	return 0;
 }
@@ -7089,7 +7116,7 @@ static u64 perf_get_page_size(unsigned long addr)
 		mm = &init_mm;
 	}
 
-	size = __perf_get_page_size(mm, addr);
+	size = arch_perf_get_page_size(mm, addr);
 
 	local_irq_restore(flags);
 
-- 
cgit v1.2.3


From a62f68f5ca53ab61cba2f0a410d0add7a6d54a52 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Fri, 23 Oct 2020 17:35:46 +0200
Subject: cpufreq: Introduce cpufreq_driver_test_flags()

Add a helper function to test the flags of the cpufreq driver in use
againt a given flags mask.

In particular, this will be needed to test the
CPUFREQ_NEED_UPDATE_LIMITS cpufreq driver flag in the schedutil
governor.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/cpufreq.c | 12 ++++++++++++
 include/linux/cpufreq.h   |  1 +
 2 files changed, 13 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index ea58337fb65f..336b5e94cbc8 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1907,6 +1907,18 @@ void cpufreq_resume(void)
 	}
 }
 
+/**
+ * cpufreq_driver_test_flags - Test cpufreq driver's flags against given ones.
+ * @flags: Flags to test against the current cpufreq driver's flags.
+ *
+ * Assumes that the driver is there, so callers must ensure that this is the
+ * case.
+ */
+bool cpufreq_driver_test_flags(u16 flags)
+{
+	return !!(cpufreq_driver->flags & flags);
+}
+
 /**
  *	cpufreq_get_current_driver - return current driver's name
  *
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 038ed83aab41..1eaa04f1bae6 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -433,6 +433,7 @@ struct cpufreq_driver {
 int cpufreq_register_driver(struct cpufreq_driver *driver_data);
 int cpufreq_unregister_driver(struct cpufreq_driver *driver_data);
 
+bool cpufreq_driver_test_flags(u16 flags);
 const char *cpufreq_get_current_driver(void);
 void *cpufreq_get_driver_data(void);
 
-- 
cgit v1.2.3


From c6838eeef2fbc7e3e1f83759aa016ae6b70c643e Mon Sep 17 00:00:00 2001
From: "dmitry.torokhov@gmail.com" <dmitry.torokhov@gmail.com>
Date: Wed, 30 Sep 2020 15:47:13 -0700
Subject: HID: hid-input: occasionally report stylus battery even if not
 changed

There are styluses that only report their battery status when they are
touching the touchscreen; additionally we currently suppress battery
reports if capacity has not changed. To help userspace recognize how long
ago the device reported battery status, let's send the change event through
if either capacity has changed, or at least 30 seconds have passed since
last report we've let through.

Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/hid-input.c | 5 ++++-
 include/linux/hid.h     | 1 +
 2 files changed, 5 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index 9770db624bfa..b0db2a2ac15a 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -534,9 +534,12 @@ static void hidinput_update_battery(struct hid_device *dev, int value)
 	capacity = hidinput_scale_battery_capacity(dev, value);
 
 	if (dev->battery_status != HID_BATTERY_REPORTED ||
-	    capacity != dev->battery_capacity) {
+	    capacity != dev->battery_capacity ||
+	    ktime_after(ktime_get_coarse(), dev->battery_ratelimit_time)) {
 		dev->battery_capacity = capacity;
 		dev->battery_status = HID_BATTERY_REPORTED;
+		dev->battery_ratelimit_time =
+			ktime_add_ms(ktime_get_coarse(), 30 * 1000);
 		power_supply_changed(dev->battery);
 	}
 }
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 58684657960b..b079146850e6 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -585,6 +585,7 @@ struct hid_device {							/* device report descriptor */
 	__s32 battery_report_id;
 	enum hid_battery_status battery_status;
 	bool battery_avoid_query;
+	ktime_t battery_ratelimit_time;
 #endif
 
 	unsigned long status;						/* see STAT flags above */
-- 
cgit v1.2.3


From 4169e889e5889405d54cec27d6e9f7f0ce3c7096 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Wed, 2 Sep 2020 23:25:55 -0500
Subject: include: jhash/signal: Fix fall-through warnings for Clang

In preparation to enable -Wimplicit-fallthrough for Clang, explicitly
add break statements instead of letting the code fall through to the
next case.

This patch adds four break statements that, together, fix almost 40,000
warnings when building Linux 5.10-rc1 with Clang 12.0.0 and this[1] change
reverted. Notice that in order to enable -Wimplicit-fallthrough for Clang,
such change[1] is meant to be reverted at some point. So, this patch helps
to move in that direction.

Something important to mention is that there is currently a discrepancy
between GCC and Clang when dealing with switch fall-through to empty case
statements or to cases that only contain a break/continue/return
statement[2][3][4].

Now that the -Wimplicit-fallthrough option has been globally enabled[5],
any compiler should really warn on missing either a fallthrough annotation
or any of the other case-terminating statements (break/continue/return/
goto) when falling through to the next case statement. Making exceptions
to this introduces variation in case handling which may continue to lead
to bugs, misunderstandings, and a general lack of robustness. The point
of enabling options like -Wimplicit-fallthrough is to prevent human error
and aid developers in spotting bugs before their code is even built/
submitted/committed, therefore eliminating classes of bugs. So, in order
to really accomplish this, we should, and can, move in the direction of
addressing any error-prone scenarios and get rid of the unintentional
fallthrough bug-class in the kernel, entirely, even if there is some minor
redundancy. Better to have explicit case-ending statements than continue to
have exceptions where one must guess as to the right result. The compiler
will eliminate any actual redundancy.

[1] commit e2079e93f562c ("kbuild: Do not enable -Wimplicit-fallthrough for clang for now")
[2] https://github.com/ClangBuiltLinux/linux/issues/636
[3] https://gcc.gnu.org/bugzilla/show_bug.cgi?id=91432
[4] https://godbolt.org/z/xgkvIh
[5] commit a035d552a93b ("Makefile: Globally enable fall-through warning")

Co-developed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
---
 include/linux/jhash.h  | 2 ++
 include/linux/signal.h | 2 ++
 2 files changed, 4 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/jhash.h b/include/linux/jhash.h
index cfb62e9f37be..ab7f8c152b89 100644
--- a/include/linux/jhash.h
+++ b/include/linux/jhash.h
@@ -99,6 +99,7 @@ static inline u32 jhash(const void *key, u32 length, u32 initval)
 	case 2:  a += (u32)k[1]<<8;	fallthrough;
 	case 1:  a += k[0];
 		 __jhash_final(a, b, c);
+		 break;
 	case 0: /* Nothing left to add */
 		break;
 	}
@@ -136,6 +137,7 @@ static inline u32 jhash2(const u32 *k, u32 length, u32 initval)
 	case 2: b += k[1];	fallthrough;
 	case 1: a += k[0];
 		__jhash_final(a, b, c);
+		break;
 	case 0:	/* Nothing left to add */
 		break;
 	}
diff --git a/include/linux/signal.h b/include/linux/signal.h
index 7bbc0e9cf084..b256f9c65661 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -238,6 +238,7 @@ static inline void siginitset(sigset_t *set, unsigned long mask)
 		memset(&set->sig[1], 0, sizeof(long)*(_NSIG_WORDS-1));
 		break;
 	case 2: set->sig[1] = 0;
+		break;
 	case 1: ;
 	}
 }
@@ -250,6 +251,7 @@ static inline void siginitsetinv(sigset_t *set, unsigned long mask)
 		memset(&set->sig[1], -1, sizeof(long)*(_NSIG_WORDS-1));
 		break;
 	case 2: set->sig[1] = -1;
+		break;
 	case 1: ;
 	}
 }
-- 
cgit v1.2.3


From f54ec58fee837ec847cb8b50593e81bfaa46107f Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 27 Oct 2020 21:12:12 +0100
Subject: wimax: move out to staging

There are no known users of this driver as of October 2020, and it will
be removed unless someone turns out to still need it in future releases.

According to https://en.wikipedia.org/wiki/List_of_WiMAX_networks, there
have been many public wimax networks, but it appears that many of these
have migrated to LTE or discontinued their service altogether.
As most PCs and phones lack WiMAX hardware support, the remaining
networks tend to use standalone routers. These almost certainly
run Linux, but not a modern kernel or the mainline wimax driver stack.

NetworkManager appears to have dropped userspace support in 2015
https://bugzilla.gnome.org/show_bug.cgi?id=747846, the
www.linuxwimax.org
site had already shut down earlier.

WiMax is apparently still being deployed on airport campus networks
("AeroMACS"), but in a frequency band that was not supported by the old
Intel 2400m (used in Sandy Bridge laptops and earlier), which is the
only driver using the kernel's wimax stack.

Move all files into drivers/staging/wimax, including the uapi header
files and documentation, to make it easier to remove it when it gets
to that. Only minimal changes are made to the source files, in order
to make it possible to port patches across the move.

Also remove the MAINTAINERS entry that refers to a broken mailing
list and website.

Acked-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-By: Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
Acked-by: Johannes Berg <johannes@sipsolutions.net>
Suggested-by: Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 Documentation/admin-guide/index.rst                |    1 -
 Documentation/admin-guide/wimax/i2400m.rst         |  283 ----
 Documentation/admin-guide/wimax/index.rst          |   19 -
 Documentation/admin-guide/wimax/wimax.rst          |   89 --
 Documentation/networking/kapi.rst                  |   21 -
 .../translations/zh_CN/admin-guide/index.rst       |    1 -
 MAINTAINERS                                        |   22 -
 drivers/net/Kconfig                                |    2 -
 drivers/net/Makefile                               |    1 -
 drivers/net/wimax/Kconfig                          |   18 -
 drivers/net/wimax/Makefile                         |    2 -
 drivers/net/wimax/i2400m/Kconfig                   |   37 -
 drivers/net/wimax/i2400m/Makefile                  |   23 -
 drivers/net/wimax/i2400m/control.c                 | 1434 -----------------
 drivers/net/wimax/i2400m/debug-levels.h            |   32 -
 drivers/net/wimax/i2400m/debugfs.c                 |  253 ---
 drivers/net/wimax/i2400m/driver.c                  | 1002 ------------
 drivers/net/wimax/i2400m/fw.c                      | 1653 --------------------
 drivers/net/wimax/i2400m/i2400m-usb.h              |  275 ----
 drivers/net/wimax/i2400m/i2400m.h                  |  970 ------------
 drivers/net/wimax/i2400m/netdev.c                  |  603 -------
 drivers/net/wimax/i2400m/op-rfkill.c               |  196 ---
 drivers/net/wimax/i2400m/rx.c                      | 1395 -----------------
 drivers/net/wimax/i2400m/sysfs.c                   |   65 -
 drivers/net/wimax/i2400m/tx.c                      | 1011 ------------
 drivers/net/wimax/i2400m/usb-debug-levels.h        |   28 -
 drivers/net/wimax/i2400m/usb-fw.c                  |  365 -----
 drivers/net/wimax/i2400m/usb-notif.c               |  258 ---
 drivers/net/wimax/i2400m/usb-rx.c                  |  462 ------
 drivers/net/wimax/i2400m/usb-tx.c                  |  273 ----
 drivers/net/wimax/i2400m/usb.c                     |  764 ---------
 drivers/staging/Kconfig                            |    2 +
 drivers/staging/Makefile                           |    1 +
 drivers/staging/wimax/Documentation/i2400m.rst     |  283 ++++
 drivers/staging/wimax/Documentation/index.rst      |   19 +
 drivers/staging/wimax/Documentation/wimax.rst      |   89 ++
 drivers/staging/wimax/Kconfig                      |   46 +
 drivers/staging/wimax/Makefile                     |   15 +
 drivers/staging/wimax/TODO                         |   18 +
 drivers/staging/wimax/debug-levels.h               |   29 +
 drivers/staging/wimax/debugfs.c                    |   38 +
 drivers/staging/wimax/i2400m/Kconfig               |   37 +
 drivers/staging/wimax/i2400m/Makefile              |   23 +
 drivers/staging/wimax/i2400m/control.c             | 1434 +++++++++++++++++
 drivers/staging/wimax/i2400m/debug-levels.h        |   32 +
 drivers/staging/wimax/i2400m/debugfs.c             |  253 +++
 drivers/staging/wimax/i2400m/driver.c              | 1002 ++++++++++++
 drivers/staging/wimax/i2400m/fw.c                  | 1653 ++++++++++++++++++++
 drivers/staging/wimax/i2400m/i2400m-usb.h          |  275 ++++
 drivers/staging/wimax/i2400m/i2400m.h              |  970 ++++++++++++
 drivers/staging/wimax/i2400m/linux-wimax-i2400m.h  |  572 +++++++
 drivers/staging/wimax/i2400m/netdev.c              |  603 +++++++
 drivers/staging/wimax/i2400m/op-rfkill.c           |  196 +++
 drivers/staging/wimax/i2400m/rx.c                  | 1395 +++++++++++++++++
 drivers/staging/wimax/i2400m/sysfs.c               |   65 +
 drivers/staging/wimax/i2400m/tx.c                  | 1011 ++++++++++++
 drivers/staging/wimax/i2400m/usb-debug-levels.h    |   28 +
 drivers/staging/wimax/i2400m/usb-fw.c              |  365 +++++
 drivers/staging/wimax/i2400m/usb-notif.c           |  258 +++
 drivers/staging/wimax/i2400m/usb-rx.c              |  462 ++++++
 drivers/staging/wimax/i2400m/usb-tx.c              |  273 ++++
 drivers/staging/wimax/i2400m/usb.c                 |  764 +++++++++
 drivers/staging/wimax/id-table.c                   |  130 ++
 drivers/staging/wimax/linux-wimax-debug.h          |  491 ++++++
 drivers/staging/wimax/linux-wimax.h                |  239 +++
 drivers/staging/wimax/net-wimax.h                  |  503 ++++++
 drivers/staging/wimax/op-msg.c                     |  391 +++++
 drivers/staging/wimax/op-reset.c                   |  108 ++
 drivers/staging/wimax/op-rfkill.c                  |  431 +++++
 drivers/staging/wimax/op-state-get.c               |   52 +
 drivers/staging/wimax/stack.c                      |  616 ++++++++
 drivers/staging/wimax/wimax-internal.h             |   85 +
 include/linux/wimax/debug.h                        |  491 ------
 include/net/wimax.h                                |  503 ------
 include/uapi/linux/wimax.h                         |  239 ---
 include/uapi/linux/wimax/i2400m.h                  |  572 -------
 net/Kconfig                                        |    2 -
 net/Makefile                                       |    1 -
 net/wimax/Kconfig                                  |   40 -
 net/wimax/Makefile                                 |   13 -
 net/wimax/debug-levels.h                           |   29 -
 net/wimax/debugfs.c                                |   38 -
 net/wimax/id-table.c                               |  130 --
 net/wimax/op-msg.c                                 |  391 -----
 net/wimax/op-reset.c                               |  108 --
 net/wimax/op-rfkill.c                              |  431 -----
 net/wimax/op-state-get.c                           |   52 -
 net/wimax/stack.c                                  |  616 --------
 net/wimax/wimax-internal.h                         |   85 -
 89 files changed, 15257 insertions(+), 15299 deletions(-)
 delete mode 100644 Documentation/admin-guide/wimax/i2400m.rst
 delete mode 100644 Documentation/admin-guide/wimax/index.rst
 delete mode 100644 Documentation/admin-guide/wimax/wimax.rst
 delete mode 100644 drivers/net/wimax/Kconfig
 delete mode 100644 drivers/net/wimax/Makefile
 delete mode 100644 drivers/net/wimax/i2400m/Kconfig
 delete mode 100644 drivers/net/wimax/i2400m/Makefile
 delete mode 100644 drivers/net/wimax/i2400m/control.c
 delete mode 100644 drivers/net/wimax/i2400m/debug-levels.h
 delete mode 100644 drivers/net/wimax/i2400m/debugfs.c
 delete mode 100644 drivers/net/wimax/i2400m/driver.c
 delete mode 100644 drivers/net/wimax/i2400m/fw.c
 delete mode 100644 drivers/net/wimax/i2400m/i2400m-usb.h
 delete mode 100644 drivers/net/wimax/i2400m/i2400m.h
 delete mode 100644 drivers/net/wimax/i2400m/netdev.c
 delete mode 100644 drivers/net/wimax/i2400m/op-rfkill.c
 delete mode 100644 drivers/net/wimax/i2400m/rx.c
 delete mode 100644 drivers/net/wimax/i2400m/sysfs.c
 delete mode 100644 drivers/net/wimax/i2400m/tx.c
 delete mode 100644 drivers/net/wimax/i2400m/usb-debug-levels.h
 delete mode 100644 drivers/net/wimax/i2400m/usb-fw.c
 delete mode 100644 drivers/net/wimax/i2400m/usb-notif.c
 delete mode 100644 drivers/net/wimax/i2400m/usb-rx.c
 delete mode 100644 drivers/net/wimax/i2400m/usb-tx.c
 delete mode 100644 drivers/net/wimax/i2400m/usb.c
 create mode 100644 drivers/staging/wimax/Documentation/i2400m.rst
 create mode 100644 drivers/staging/wimax/Documentation/index.rst
 create mode 100644 drivers/staging/wimax/Documentation/wimax.rst
 create mode 100644 drivers/staging/wimax/Kconfig
 create mode 100644 drivers/staging/wimax/Makefile
 create mode 100644 drivers/staging/wimax/TODO
 create mode 100644 drivers/staging/wimax/debug-levels.h
 create mode 100644 drivers/staging/wimax/debugfs.c
 create mode 100644 drivers/staging/wimax/i2400m/Kconfig
 create mode 100644 drivers/staging/wimax/i2400m/Makefile
 create mode 100644 drivers/staging/wimax/i2400m/control.c
 create mode 100644 drivers/staging/wimax/i2400m/debug-levels.h
 create mode 100644 drivers/staging/wimax/i2400m/debugfs.c
 create mode 100644 drivers/staging/wimax/i2400m/driver.c
 create mode 100644 drivers/staging/wimax/i2400m/fw.c
 create mode 100644 drivers/staging/wimax/i2400m/i2400m-usb.h
 create mode 100644 drivers/staging/wimax/i2400m/i2400m.h
 create mode 100644 drivers/staging/wimax/i2400m/linux-wimax-i2400m.h
 create mode 100644 drivers/staging/wimax/i2400m/netdev.c
 create mode 100644 drivers/staging/wimax/i2400m/op-rfkill.c
 create mode 100644 drivers/staging/wimax/i2400m/rx.c
 create mode 100644 drivers/staging/wimax/i2400m/sysfs.c
 create mode 100644 drivers/staging/wimax/i2400m/tx.c
 create mode 100644 drivers/staging/wimax/i2400m/usb-debug-levels.h
 create mode 100644 drivers/staging/wimax/i2400m/usb-fw.c
 create mode 100644 drivers/staging/wimax/i2400m/usb-notif.c
 create mode 100644 drivers/staging/wimax/i2400m/usb-rx.c
 create mode 100644 drivers/staging/wimax/i2400m/usb-tx.c
 create mode 100644 drivers/staging/wimax/i2400m/usb.c
 create mode 100644 drivers/staging/wimax/id-table.c
 create mode 100644 drivers/staging/wimax/linux-wimax-debug.h
 create mode 100644 drivers/staging/wimax/linux-wimax.h
 create mode 100644 drivers/staging/wimax/net-wimax.h
 create mode 100644 drivers/staging/wimax/op-msg.c
 create mode 100644 drivers/staging/wimax/op-reset.c
 create mode 100644 drivers/staging/wimax/op-rfkill.c
 create mode 100644 drivers/staging/wimax/op-state-get.c
 create mode 100644 drivers/staging/wimax/stack.c
 create mode 100644 drivers/staging/wimax/wimax-internal.h
 delete mode 100644 include/linux/wimax/debug.h
 delete mode 100644 include/net/wimax.h
 delete mode 100644 include/uapi/linux/wimax.h
 delete mode 100644 include/uapi/linux/wimax/i2400m.h
 delete mode 100644 net/wimax/Kconfig
 delete mode 100644 net/wimax/Makefile
 delete mode 100644 net/wimax/debug-levels.h
 delete mode 100644 net/wimax/debugfs.c
 delete mode 100644 net/wimax/id-table.c
 delete mode 100644 net/wimax/op-msg.c
 delete mode 100644 net/wimax/op-reset.c
 delete mode 100644 net/wimax/op-rfkill.c
 delete mode 100644 net/wimax/op-state-get.c
 delete mode 100644 net/wimax/stack.c
 delete mode 100644 net/wimax/wimax-internal.h

(limited to 'include/linux')

diff --git a/Documentation/admin-guide/index.rst b/Documentation/admin-guide/index.rst
index ed1cf94ea50c..d53986a424c4 100644
--- a/Documentation/admin-guide/index.rst
+++ b/Documentation/admin-guide/index.rst
@@ -115,7 +115,6 @@ configure specific aspects of kernel behavior to your liking.
    unicode
    vga-softcursor
    video-output
-   wimax/index
    xfs
 
 .. only::  subproject and html
diff --git a/Documentation/admin-guide/wimax/i2400m.rst b/Documentation/admin-guide/wimax/i2400m.rst
deleted file mode 100644
index 194388c0c351..000000000000
--- a/Documentation/admin-guide/wimax/i2400m.rst
+++ /dev/null
@@ -1,283 +0,0 @@
-.. include:: <isonum.txt>
-
-====================================================
-Driver for the Intel Wireless Wimax Connection 2400m
-====================================================
-
-:Copyright: |copy| 2008 Intel Corporation < linux-wimax@intel.com >
-
-   This provides a driver for the Intel Wireless WiMAX Connection 2400m
-   and a basic Linux kernel WiMAX stack.
-
-1. Requirements
-===============
-
-     * Linux installation with Linux kernel 2.6.22 or newer (if building
-       from a separate tree)
-     * Intel i2400m Echo Peak or Baxter Peak; this includes the Intel
-       Wireless WiMAX/WiFi Link 5x50 series.
-     * build tools:
-
-          + Linux kernel development package for the target kernel; to
-            build against your currently running kernel, you need to have
-            the kernel development package corresponding to the running
-            image installed (usually if your kernel is named
-            linux-VERSION, the development package is called
-            linux-dev-VERSION or linux-headers-VERSION).
-          + GNU C Compiler, make
-
-2. Compilation and installation
-===============================
-
-2.1. Compilation of the drivers included in the kernel
-------------------------------------------------------
-
-   Configure the kernel; to enable the WiMAX drivers select Drivers >
-   Networking Drivers > WiMAX device support. Enable all of them as
-   modules (easier).
-
-   If USB or SDIO are not enabled in the kernel configuration, the options
-   to build the i2400m USB or SDIO drivers will not show. Enable said
-   subsystems and go back to the WiMAX menu to enable the drivers.
-
-   Compile and install your kernel as usual.
-
-2.2. Compilation of the drivers distributed as an standalone module
--------------------------------------------------------------------
-
-   To compile::
-
-	$ cd source/directory
-	$ make
-
-   Once built you can load and unload using the provided load.sh script;
-   load.sh will load the modules, load.sh u will unload them.
-
-   To install in the default kernel directories (and enable auto loading
-   when the device is plugged)::
-
-	$ make install
-	$ depmod -a
-
-   If your kernel development files are located in a non standard
-   directory or if you want to build for a kernel that is not the
-   currently running one, set KDIR to the right location::
-
-	$ make KDIR=/path/to/kernel/dev/tree
-
-   For more information, please contact linux-wimax@intel.com.
-
-3. Installing the firmware
---------------------------
-
-   The firmware can be obtained from http://linuxwimax.org or might have
-   been supplied with your hardware.
-
-   It has to be installed in the target system::
-
-	$ cp FIRMWAREFILE.sbcf /lib/firmware/i2400m-fw-BUSTYPE-1.3.sbcf
-
-     * NOTE: if your firmware came in an .rpm or .deb file, just install
-       it as normal, with the rpm (rpm -i FIRMWARE.rpm) or dpkg
-       (dpkg -i FIRMWARE.deb) commands. No further action is needed.
-     * BUSTYPE will be usb or sdio, depending on the hardware you have.
-       Each hardware type comes with its own firmware and will not work
-       with other types.
-
-4. Design
-=========
-
-   This package contains two major parts: a WiMAX kernel stack and a
-   driver for the Intel i2400m.
-
-   The WiMAX stack is designed to provide for common WiMAX control
-   services to current and future WiMAX devices from any vendor; please
-   see README.wimax for details.
-
-   The i2400m kernel driver is broken up in two main parts: the bus
-   generic driver and the bus-specific drivers. The bus generic driver
-   forms the drivercore and contain no knowledge of the actual method we
-   use to connect to the device. The bus specific drivers are just the
-   glue to connect the bus-generic driver and the device. Currently only
-   USB and SDIO are supported. See drivers/net/wimax/i2400m/i2400m.h for
-   more information.
-
-   The bus generic driver is logically broken up in two parts: OS-glue and
-   hardware-glue. The OS-glue interfaces with Linux. The hardware-glue
-   interfaces with the device on using an interface provided by the
-   bus-specific driver. The reason for this breakup is to be able to
-   easily reuse the hardware-glue to write drivers for other OSes; note
-   the hardware glue part is written as a native Linux driver; no
-   abstraction layers are used, so to port to another OS, the Linux kernel
-   API calls should be replaced with the target OS's.
-
-5. Usage
-========
-
-   To load the driver, follow the instructions in the install section;
-   once the driver is loaded, plug in the device (unless it is permanently
-   plugged in). The driver will enumerate the device, upload the firmware
-   and output messages in the kernel log (dmesg, /var/log/messages or
-   /var/log/kern.log) such as::
-
-	...
-	i2400m_usb 5-4:1.0: firmware interface version 8.0.0
-	i2400m_usb 5-4:1.0: WiMAX interface wmx0 (00:1d:e1:01:94:2c) ready
-
-   At this point the device is ready to work.
-
-   Current versions require the Intel WiMAX Network Service in userspace
-   to make things work. See the network service's README for instructions
-   on how to scan, connect and disconnect.
-
-5.1. Module parameters
-----------------------
-
-   Module parameters can be set at kernel or module load time or by
-   echoing values::
-
-	$ echo VALUE > /sys/module/MODULENAME/parameters/PARAMETERNAME
-
-   To make changes permanent, for example, for the i2400m module, you can
-   also create a file named /etc/modprobe.d/i2400m containing::
-
-	options i2400m idle_mode_disabled=1
-
-   To find which parameters are supported by a module, run::
-
-	$ modinfo path/to/module.ko
-
-   During kernel bootup (if the driver is linked in the kernel), specify
-   the following to the kernel command line::
-
-	i2400m.PARAMETER=VALUE
-
-5.1.1. i2400m: idle_mode_disabled
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
-   The i2400m module supports a parameter to disable idle mode. This
-   parameter, once set, will take effect only when the device is
-   reinitialized by the driver (eg: following a reset or a reconnect).
-
-5.2. Debug operations: debugfs entries
---------------------------------------
-
-   The driver will register debugfs entries that allow the user to tweak
-   debug settings. There are three main container directories where
-   entries are placed, which correspond to the three blocks a i2400m WiMAX
-   driver has:
-
-     * /sys/kernel/debug/wimax:DEVNAME/ for the generic WiMAX stack
-       controls
-     * /sys/kernel/debug/wimax:DEVNAME/i2400m for the i2400m generic
-       driver controls
-     * /sys/kernel/debug/wimax:DEVNAME/i2400m-usb (or -sdio) for the
-       bus-specific i2400m-usb or i2400m-sdio controls).
-
-   Of course, if debugfs is mounted in a directory other than
-   /sys/kernel/debug, those paths will change.
-
-5.2.1. Increasing debug output
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
-   The files named *dl_* indicate knobs for controlling the debug output
-   of different submodules::
-
-	# find /sys/kernel/debug/wimax\:wmx0 -name \*dl_\*
-	/sys/kernel/debug/wimax:wmx0/i2400m-usb/dl_tx
-	/sys/kernel/debug/wimax:wmx0/i2400m-usb/dl_rx
-	/sys/kernel/debug/wimax:wmx0/i2400m-usb/dl_notif
-	/sys/kernel/debug/wimax:wmx0/i2400m-usb/dl_fw
-	/sys/kernel/debug/wimax:wmx0/i2400m-usb/dl_usb
-	/sys/kernel/debug/wimax:wmx0/i2400m/dl_tx
-	/sys/kernel/debug/wimax:wmx0/i2400m/dl_rx
-	/sys/kernel/debug/wimax:wmx0/i2400m/dl_rfkill
-	/sys/kernel/debug/wimax:wmx0/i2400m/dl_netdev
-	/sys/kernel/debug/wimax:wmx0/i2400m/dl_fw
-	/sys/kernel/debug/wimax:wmx0/i2400m/dl_debugfs
-	/sys/kernel/debug/wimax:wmx0/i2400m/dl_driver
-	/sys/kernel/debug/wimax:wmx0/i2400m/dl_control
-	/sys/kernel/debug/wimax:wmx0/wimax_dl_stack
-	/sys/kernel/debug/wimax:wmx0/wimax_dl_op_rfkill
-	/sys/kernel/debug/wimax:wmx0/wimax_dl_op_reset
-	/sys/kernel/debug/wimax:wmx0/wimax_dl_op_msg
-	/sys/kernel/debug/wimax:wmx0/wimax_dl_id_table
-	/sys/kernel/debug/wimax:wmx0/wimax_dl_debugfs
-
-   By reading the file you can obtain the current value of said debug
-   level; by writing to it, you can set it.
-
-   To increase the debug level of, for example, the i2400m's generic TX
-   engine, just write::
-
-	$ echo 3 > /sys/kernel/debug/wimax:wmx0/i2400m/dl_tx
-
-   Increasing numbers yield increasing debug information; for details of
-   what is printed and the available levels, check the source. The code
-   uses 0 for disabled and increasing values until 8.
-
-5.2.2. RX and TX statistics
-^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
-   The i2400m/rx_stats and i2400m/tx_stats provide statistics about the
-   data reception/delivery from the device::
-
-	$ cat /sys/kernel/debug/wimax:wmx0/i2400m/rx_stats
-	45 1 3 34 3104 48 480
-
-   The numbers reported are:
-
-     * packets/RX-buffer: total, min, max
-     * RX-buffers: total RX buffers received, accumulated RX buffer size
-       in bytes, min size received, max size received
-
-   Thus, to find the average buffer size received, divide accumulated
-   RX-buffer / total RX-buffers.
-
-   To clear the statistics back to 0, write anything to the rx_stats file::
-
-	$ echo 1 > /sys/kernel/debug/wimax:wmx0/i2400m_rx_stats
-
-   Likewise for TX.
-
-   Note the packets this debug file refers to are not network packet, but
-   packets in the sense of the device-specific protocol for communication
-   to the host. See drivers/net/wimax/i2400m/tx.c.
-
-5.2.3. Tracing messages received from user space
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
-   To echo messages received from user space into the trace pipe that the
-   i2400m driver creates, set the debug file i2400m/trace_msg_from_user to
-   1::
-
-	$ echo 1 > /sys/kernel/debug/wimax:wmx0/i2400m/trace_msg_from_user
-
-5.2.4. Performing a device reset
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
-   By writing a 0, a 1 or a 2 to the file
-   /sys/kernel/debug/wimax:wmx0/reset, the driver performs a warm (without
-   disconnecting from the bus), cold (disconnecting from the bus) or bus
-   (bus specific) reset on the device.
-
-5.2.5. Asking the device to enter power saving mode
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
-   By writing any value to the /sys/kernel/debug/wimax:wmx0 file, the
-   device will attempt to enter power saving mode.
-
-6. Troubleshooting
-==================
-
-6.1. Driver complains about ``i2400m-fw-usb-1.2.sbcf: request failed``
-----------------------------------------------------------------------
-
-   If upon connecting the device, the following is output in the kernel
-   log::
-
-	i2400m_usb 5-4:1.0: fw i2400m-fw-usb-1.3.sbcf: request failed: -2
-
-   This means that the driver cannot locate the firmware file named
-   /lib/firmware/i2400m-fw-usb-1.2.sbcf. Check that the file is present in
-   the right location.
diff --git a/Documentation/admin-guide/wimax/index.rst b/Documentation/admin-guide/wimax/index.rst
deleted file mode 100644
index fdf7c1f99ff5..000000000000
--- a/Documentation/admin-guide/wimax/index.rst
+++ /dev/null
@@ -1,19 +0,0 @@
-.. SPDX-License-Identifier: GPL-2.0
-
-===============
-WiMAX subsystem
-===============
-
-.. toctree::
-   :maxdepth: 2
-
-   wimax
-
-   i2400m
-
-.. only::  subproject and html
-
-   Indices
-   =======
-
-   * :ref:`genindex`
diff --git a/Documentation/admin-guide/wimax/wimax.rst b/Documentation/admin-guide/wimax/wimax.rst
deleted file mode 100644
index 817ee8ba2732..000000000000
--- a/Documentation/admin-guide/wimax/wimax.rst
+++ /dev/null
@@ -1,89 +0,0 @@
-.. include:: <isonum.txt>
-
-========================
-Linux kernel WiMAX stack
-========================
-
-:Copyright: |copy| 2008 Intel Corporation < linux-wimax@intel.com >
-
-   This provides a basic Linux kernel WiMAX stack to provide a common
-   control API for WiMAX devices, usable from kernel and user space.
-
-1. Design
-=========
-
-   The WiMAX stack is designed to provide for common WiMAX control
-   services to current and future WiMAX devices from any vendor.
-
-   Because currently there is only one and we don't know what would be the
-   common services, the APIs it currently provides are very minimal.
-   However, it is done in such a way that it is easily extensible to
-   accommodate future requirements.
-
-   The stack works by embedding a struct wimax_dev in your device's
-   control structures. This provides a set of callbacks that the WiMAX
-   stack will call in order to implement control operations requested by
-   the user. As well, the stack provides API functions that the driver
-   calls to notify about changes of state in the device.
-
-   The stack exports the API calls needed to control the device to user
-   space using generic netlink as a marshalling mechanism. You can access
-   them using your own code or use the wrappers provided for your
-   convenience in libwimax (in the wimax-tools package).
-
-   For detailed information on the stack, please see
-   include/linux/wimax.h.
-
-2. Usage
-========
-
-   For usage in a driver (registration, API, etc) please refer to the
-   instructions in the header file include/linux/wimax.h.
-
-   When a device is registered with the WiMAX stack, a set of debugfs
-   files will appear in /sys/kernel/debug/wimax:wmxX can tweak for
-   control.
-
-2.1. Obtaining debug information: debugfs entries
--------------------------------------------------
-
-   The WiMAX stack is compiled, by default, with debug messages that can
-   be used to diagnose issues. By default, said messages are disabled.
-
-   The drivers will register debugfs entries that allow the user to tweak
-   debug settings.
-
-   Each driver, when registering with the stack, will cause a debugfs
-   directory named wimax:DEVICENAME to be created; optionally, it might
-   create more subentries below it.
-
-2.1.1. Increasing debug output
-------------------------------
-
-   The files named *dl_* indicate knobs for controlling the debug output
-   of different submodules of the WiMAX stack::
-
-	# find /sys/kernel/debug/wimax\:wmx0 -name \*dl_\*
-	/sys/kernel/debug/wimax:wmx0/wimax_dl_stack
-	/sys/kernel/debug/wimax:wmx0/wimax_dl_op_rfkill
-	/sys/kernel/debug/wimax:wmx0/wimax_dl_op_reset
-	/sys/kernel/debug/wimax:wmx0/wimax_dl_op_msg
-	/sys/kernel/debug/wimax:wmx0/wimax_dl_id_table
-	/sys/kernel/debug/wimax:wmx0/wimax_dl_debugfs
-	/sys/kernel/debug/wimax:wmx0/.... # other driver specific files
-
-   NOTE:
-       Of course, if debugfs is mounted in a directory other than
-       /sys/kernel/debug, those paths will change.
-
-   By reading the file you can obtain the current value of said debug
-   level; by writing to it, you can set it.
-
-   To increase the debug level of, for example, the id-table submodule,
-   just write:
-
-	$ echo 3 > /sys/kernel/debug/wimax:wmx0/wimax_dl_id_table
-
-   Increasing numbers yield increasing debug information; for details of
-   what is printed and the available levels, check the source. The code
-   uses 0 for disabled and increasing values until 8.
diff --git a/Documentation/networking/kapi.rst b/Documentation/networking/kapi.rst
index d198fa5eaacd..ea55f462cefa 100644
--- a/Documentation/networking/kapi.rst
+++ b/Documentation/networking/kapi.rst
@@ -83,27 +83,6 @@ SUN RPC subsystem
 .. kernel-doc:: net/sunrpc/clnt.c
    :export:
 
-WiMAX
------
-
-.. kernel-doc:: net/wimax/op-msg.c
-   :export:
-
-.. kernel-doc:: net/wimax/op-reset.c
-   :export:
-
-.. kernel-doc:: net/wimax/op-rfkill.c
-   :export:
-
-.. kernel-doc:: net/wimax/stack.c
-   :export:
-
-.. kernel-doc:: include/net/wimax.h
-   :internal:
-
-.. kernel-doc:: include/uapi/linux/wimax.h
-   :internal:
-
 Network device support
 ======================
 
diff --git a/Documentation/translations/zh_CN/admin-guide/index.rst b/Documentation/translations/zh_CN/admin-guide/index.rst
index ed5ab7e37f38..48bbd3ebad48 100644
--- a/Documentation/translations/zh_CN/admin-guide/index.rst
+++ b/Documentation/translations/zh_CN/admin-guide/index.rst
@@ -114,7 +114,6 @@ Todolist:
    unicode
    vga-softcursor
    video-output
-   wimax/index
    xfs
 
 .. only::  subproject and html
diff --git a/MAINTAINERS b/MAINTAINERS
index e73636b75f29..17f5571788c9 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9106,16 +9106,6 @@ W:	https://wireless.wiki.kernel.org/en/users/drivers/iwlwifi
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/iwlwifi/iwlwifi.git
 F:	drivers/net/wireless/intel/iwlwifi/
 
-INTEL WIRELESS WIMAX CONNECTION 2400
-M:	Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
-M:	linux-wimax@intel.com
-L:	wimax@linuxwimax.org (subscribers-only)
-S:	Supported
-W:	http://linuxwimax.org
-F:	Documentation/admin-guide/wimax/i2400m.rst
-F:	drivers/net/wimax/i2400m/
-F:	include/uapi/linux/wimax/i2400m.h
-
 INTEL WMI SLIM BOOTLOADER (SBL) FIRMWARE UPDATE DRIVER
 M:	Jithu Joseph <jithu.joseph@intel.com>
 R:	Maurice Ma <maurice.ma@intel.com>
@@ -18907,18 +18897,6 @@ S:	Supported
 W:	https://wireless.wiki.kernel.org/en/users/Drivers/wil6210
 F:	drivers/net/wireless/ath/wil6210/
 
-WIMAX STACK
-M:	Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
-M:	linux-wimax@intel.com
-L:	wimax@linuxwimax.org (subscribers-only)
-S:	Supported
-W:	http://linuxwimax.org
-F:	Documentation/admin-guide/wimax/wimax.rst
-F:	include/linux/wimax/debug.h
-F:	include/net/wimax.h
-F:	include/uapi/linux/wimax.h
-F:	net/wimax/
-
 WINBOND CIR DRIVER
 M:	David Härdeman <david@hardeman.nu>
 S:	Maintained
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index c3dbe64e628e..c0af2dc8b938 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -489,8 +489,6 @@ source "drivers/net/usb/Kconfig"
 
 source "drivers/net/wireless/Kconfig"
 
-source "drivers/net/wimax/Kconfig"
-
 source "drivers/net/wan/Kconfig"
 
 source "drivers/net/ieee802154/Kconfig"
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index 72e18d505d1a..b27e8633c305 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -66,7 +66,6 @@ obj-$(CONFIG_NET_SB1000) += sb1000.o
 obj-$(CONFIG_SUNGEM_PHY) += sungem_phy.o
 obj-$(CONFIG_WAN) += wan/
 obj-$(CONFIG_WLAN) += wireless/
-obj-$(CONFIG_WIMAX) += wimax/
 obj-$(CONFIG_IEEE802154) += ieee802154/
 
 obj-$(CONFIG_VMXNET3) += vmxnet3/
diff --git a/drivers/net/wimax/Kconfig b/drivers/net/wimax/Kconfig
deleted file mode 100644
index 2249e3d77a76..000000000000
--- a/drivers/net/wimax/Kconfig
+++ /dev/null
@@ -1,18 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-#
-# WiMAX LAN device drivers configuration
-#
-
-
-comment "Enable WiMAX (Networking options) to see the WiMAX drivers"
-	depends on WIMAX = n
-
-if WIMAX
-
-menu "WiMAX Wireless Broadband devices"
-
-source "drivers/net/wimax/i2400m/Kconfig"
-
-endmenu
-
-endif
diff --git a/drivers/net/wimax/Makefile b/drivers/net/wimax/Makefile
deleted file mode 100644
index b4575bacf994..000000000000
--- a/drivers/net/wimax/Makefile
+++ /dev/null
@@ -1,2 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-obj-$(CONFIG_WIMAX_I2400M)	+= i2400m/
diff --git a/drivers/net/wimax/i2400m/Kconfig b/drivers/net/wimax/i2400m/Kconfig
deleted file mode 100644
index 843b905a26a3..000000000000
--- a/drivers/net/wimax/i2400m/Kconfig
+++ /dev/null
@@ -1,37 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-
-config WIMAX_I2400M
-	tristate
-	depends on WIMAX
-	select FW_LOADER
-
-comment "Enable USB support to see WiMAX USB drivers"
-	depends on USB = n
-
-config WIMAX_I2400M_USB
-	tristate "Intel Wireless WiMAX Connection 2400 over USB (including 5x50)"
-	depends on WIMAX && USB
-	select WIMAX_I2400M
-	help
-	  Select if you have a device based on the Intel WiMAX
-	  Connection 2400 over USB (like any of the Intel Wireless
-	  WiMAX/WiFi Link 5x50 series).
-
-	  If unsure, it is safe to select M (module).
-
-config WIMAX_I2400M_DEBUG_LEVEL
-	int "WiMAX i2400m debug level"
-	depends on WIMAX_I2400M
-	default 8
-	help
-
-	  Select the maximum debug verbosity level to be compiled into
-	  the WiMAX i2400m driver code.
-
-	  By default, this is disabled at runtime and can be
-	  selectively enabled at runtime for different parts of the
-	  code using the sysfs debug-levels file.
-
-	  If set at zero, this will compile out all the debug code.
-
-	  It is recommended that it is left at 8.
diff --git a/drivers/net/wimax/i2400m/Makefile b/drivers/net/wimax/i2400m/Makefile
deleted file mode 100644
index b1db1eff0648..000000000000
--- a/drivers/net/wimax/i2400m/Makefile
+++ /dev/null
@@ -1,23 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-
-obj-$(CONFIG_WIMAX_I2400M) += i2400m.o
-obj-$(CONFIG_WIMAX_I2400M_USB) += i2400m-usb.o
-
-i2400m-y :=		\
-	control.o	\
-	driver.o	\
-	fw.o		\
-	op-rfkill.o	\
-	sysfs.o		\
-	netdev.o	\
-	tx.o		\
-	rx.o
-
-i2400m-$(CONFIG_DEBUG_FS) += debugfs.o
-
-i2400m-usb-y :=			\
-	usb-fw.o		\
-	usb-notif.o		\
-	usb-tx.o		\
-	usb-rx.o		\
-	usb.o
diff --git a/drivers/net/wimax/i2400m/control.c b/drivers/net/wimax/i2400m/control.c
deleted file mode 100644
index 8df98757d901..000000000000
--- a/drivers/net/wimax/i2400m/control.c
+++ /dev/null
@@ -1,1434 +0,0 @@
-/*
- * Intel Wireless WiMAX Connection 2400m
- * Miscellaneous control functions for managing the device
- *
- *
- * Copyright (C) 2007-2008 Intel Corporation. All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- *   * Redistributions of source code must retain the above copyright
- *     notice, this list of conditions and the following disclaimer.
- *   * Redistributions in binary form must reproduce the above copyright
- *     notice, this list of conditions and the following disclaimer in
- *     the documentation and/or other materials provided with the
- *     distribution.
- *   * Neither the name of Intel Corporation nor the names of its
- *     contributors may be used to endorse or promote products derived
- *     from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *  - Initial implementation
- *
- * This is a collection of functions used to control the device (plus
- * a few helpers).
- *
- * There are utilities for handling TLV buffers, hooks on the device's
- * reports to act on device changes of state [i2400m_report_hook()],
- * on acks to commands [i2400m_msg_ack_hook()], a helper for sending
- * commands to the device and blocking until a reply arrives
- * [i2400m_msg_to_dev()], a few high level commands for manipulating
- * the device state, powersving mode and configuration plus the
- * routines to setup the device once communication is stablished with
- * it [i2400m_dev_initialize()].
- *
- * ROADMAP
- *
- * i2400m_dev_initialize()       Called by i2400m_dev_start()
- *   i2400m_set_init_config()
- *   i2400m_cmd_get_state()
- * i2400m_dev_shutdown()        Called by i2400m_dev_stop()
- *   i2400m_reset()
- *
- * i2400m_{cmd,get,set}_*()
- *   i2400m_msg_to_dev()
- *   i2400m_msg_check_status()
- *
- * i2400m_report_hook()         Called on reception of an event
- *   i2400m_report_state_hook()
- *     i2400m_tlv_buffer_walk()
- *     i2400m_tlv_match()
- *     i2400m_report_tlv_system_state()
- *     i2400m_report_tlv_rf_switches_status()
- *     i2400m_report_tlv_media_status()
- *   i2400m_cmd_enter_powersave()
- *
- * i2400m_msg_ack_hook()        Called on reception of a reply to a
- *                              command, get or set
- */
-
-#include <stdarg.h>
-#include "i2400m.h"
-#include <linux/kernel.h>
-#include <linux/slab.h>
-#include <linux/wimax/i2400m.h>
-#include <linux/export.h>
-#include <linux/moduleparam.h>
-
-
-#define D_SUBMODULE control
-#include "debug-levels.h"
-
-static int i2400m_idle_mode_disabled;/* 0 (idle mode enabled) by default */
-module_param_named(idle_mode_disabled, i2400m_idle_mode_disabled, int, 0644);
-MODULE_PARM_DESC(idle_mode_disabled,
-		 "If true, the device will not enable idle mode negotiation "
-		 "with the base station (when connected) to save power.");
-
-/* 0 (power saving enabled) by default */
-static int i2400m_power_save_disabled;
-module_param_named(power_save_disabled, i2400m_power_save_disabled, int, 0644);
-MODULE_PARM_DESC(power_save_disabled,
-		 "If true, the driver will not tell the device to enter "
-		 "power saving mode when it reports it is ready for it. "
-		 "False by default (so the device is told to do power "
-		 "saving).");
-
-static int i2400m_passive_mode;	/* 0 (passive mode disabled) by default */
-module_param_named(passive_mode, i2400m_passive_mode, int, 0644);
-MODULE_PARM_DESC(passive_mode,
-		 "If true, the driver will not do any device setup "
-		 "and leave it up to user space, who must be properly "
-		 "setup.");
-
-
-/*
- * Return if a TLV is of a give type and size
- *
- * @tlv_hdr: pointer to the TLV
- * @tlv_type: type of the TLV we are looking for
- * @tlv_size: expected size of the TLV we are looking for (if -1,
- *            don't check the size). This includes the header
- * Returns: 0 if the TLV matches
- *          < 0 if it doesn't match at all
- *          > 0 total TLV + payload size, if the type matches, but not
- *              the size
- */
-static
-ssize_t i2400m_tlv_match(const struct i2400m_tlv_hdr *tlv,
-		     enum i2400m_tlv tlv_type, ssize_t tlv_size)
-{
-	if (le16_to_cpu(tlv->type) != tlv_type)	/* Not our type? skip */
-		return -1;
-	if (tlv_size != -1
-	    && le16_to_cpu(tlv->length) + sizeof(*tlv) != tlv_size) {
-		size_t size = le16_to_cpu(tlv->length) + sizeof(*tlv);
-		printk(KERN_WARNING "W: tlv type 0x%x mismatched because of "
-		       "size (got %zu vs %zd expected)\n",
-		       tlv_type, size, tlv_size);
-		return size;
-	}
-	return 0;
-}
-
-
-/*
- * Given a buffer of TLVs, iterate over them
- *
- * @i2400m: device instance
- * @tlv_buf: pointer to the beginning of the TLV buffer
- * @buf_size: buffer size in bytes
- * @tlv_pos: seek position; this is assumed to be a pointer returned
- *           by i2400m_tlv_buffer_walk() [and thus, validated]. The
- *           TLV returned will be the one following this one.
- *
- * Usage:
- *
- * tlv_itr = NULL;
- * while (tlv_itr = i2400m_tlv_buffer_walk(i2400m, buf, size, tlv_itr))  {
- *         ...
- *         // Do stuff with tlv_itr, DON'T MODIFY IT
- *         ...
- * }
- */
-static
-const struct i2400m_tlv_hdr *i2400m_tlv_buffer_walk(
-	struct i2400m *i2400m,
-	const void *tlv_buf, size_t buf_size,
-	const struct i2400m_tlv_hdr *tlv_pos)
-{
-	struct device *dev = i2400m_dev(i2400m);
-	const struct i2400m_tlv_hdr *tlv_top = tlv_buf + buf_size;
-	size_t offset, length, avail_size;
-	unsigned type;
-
-	if (tlv_pos == NULL)	/* Take the first one? */
-		tlv_pos = tlv_buf;
-	else			/* Nope, the next one */
-		tlv_pos = (void *) tlv_pos
-			+ le16_to_cpu(tlv_pos->length) + sizeof(*tlv_pos);
-	if (tlv_pos == tlv_top) {	/* buffer done */
-		tlv_pos = NULL;
-		goto error_beyond_end;
-	}
-	if (tlv_pos > tlv_top) {
-		tlv_pos = NULL;
-		WARN_ON(1);
-		goto error_beyond_end;
-	}
-	offset = (void *) tlv_pos - (void *) tlv_buf;
-	avail_size = buf_size - offset;
-	if (avail_size < sizeof(*tlv_pos)) {
-		dev_err(dev, "HW BUG? tlv_buf %p [%zu bytes], tlv @%zu: "
-			"short header\n", tlv_buf, buf_size, offset);
-		goto error_short_header;
-	}
-	type = le16_to_cpu(tlv_pos->type);
-	length = le16_to_cpu(tlv_pos->length);
-	if (avail_size < sizeof(*tlv_pos) + length) {
-		dev_err(dev, "HW BUG? tlv_buf %p [%zu bytes], "
-			"tlv type 0x%04x @%zu: "
-			"short data (%zu bytes vs %zu needed)\n",
-			tlv_buf, buf_size, type, offset, avail_size,
-			sizeof(*tlv_pos) + length);
-		goto error_short_header;
-	}
-error_short_header:
-error_beyond_end:
-	return tlv_pos;
-}
-
-
-/*
- * Find a TLV in a buffer of sequential TLVs
- *
- * @i2400m: device descriptor
- * @tlv_hdr: pointer to the first TLV in the sequence
- * @size: size of the buffer in bytes; all TLVs are assumed to fit
- *        fully in the buffer (otherwise we'll complain).
- * @tlv_type: type of the TLV we are looking for
- * @tlv_size: expected size of the TLV we are looking for (if -1,
- *            don't check the size). This includes the header
- *
- * Returns: NULL if the TLV is not found, otherwise a pointer to
- *          it. If the sizes don't match, an error is printed and NULL
- *          returned.
- */
-static
-const struct i2400m_tlv_hdr *i2400m_tlv_find(
-	struct i2400m *i2400m,
-	const struct i2400m_tlv_hdr *tlv_hdr, size_t size,
-	enum i2400m_tlv tlv_type, ssize_t tlv_size)
-{
-	ssize_t match;
-	struct device *dev = i2400m_dev(i2400m);
-	const struct i2400m_tlv_hdr *tlv = NULL;
-	while ((tlv = i2400m_tlv_buffer_walk(i2400m, tlv_hdr, size, tlv))) {
-		match = i2400m_tlv_match(tlv, tlv_type, tlv_size);
-		if (match == 0)		/* found it :) */
-			break;
-		if (match > 0)
-			dev_warn(dev, "TLV type 0x%04x found with size "
-				 "mismatch (%zu vs %zd needed)\n",
-				 tlv_type, match, tlv_size);
-	}
-	return tlv;
-}
-
-
-static const struct
-{
-	char *msg;
-	int errno;
-} ms_to_errno[I2400M_MS_MAX] = {
-	[I2400M_MS_DONE_OK] = { "", 0 },
-	[I2400M_MS_DONE_IN_PROGRESS] = { "", 0 },
-	[I2400M_MS_INVALID_OP] = { "invalid opcode", -ENOSYS },
-	[I2400M_MS_BAD_STATE] = { "invalid state", -EILSEQ },
-	[I2400M_MS_ILLEGAL_VALUE] = { "illegal value", -EINVAL },
-	[I2400M_MS_MISSING_PARAMS] = { "missing parameters", -ENOMSG },
-	[I2400M_MS_VERSION_ERROR] = { "bad version", -EIO },
-	[I2400M_MS_ACCESSIBILITY_ERROR] = { "accesibility error", -EIO },
-	[I2400M_MS_BUSY] = { "busy", -EBUSY },
-	[I2400M_MS_CORRUPTED_TLV] = { "corrupted TLV", -EILSEQ },
-	[I2400M_MS_UNINITIALIZED] = { "uninitialized", -EILSEQ },
-	[I2400M_MS_UNKNOWN_ERROR] = { "unknown error", -EIO },
-	[I2400M_MS_PRODUCTION_ERROR] = { "production error", -EIO },
-	[I2400M_MS_NO_RF] = { "no RF", -EIO },
-	[I2400M_MS_NOT_READY_FOR_POWERSAVE] =
-		{ "not ready for powersave", -EACCES },
-	[I2400M_MS_THERMAL_CRITICAL] = { "thermal critical", -EL3HLT },
-};
-
-
-/*
- * i2400m_msg_check_status - translate a message's status code
- *
- * @i2400m: device descriptor
- * @l3l4_hdr: message header
- * @strbuf: buffer to place a formatted error message (unless NULL).
- * @strbuf_size: max amount of available space; larger messages will
- * be truncated.
- *
- * Returns: errno code corresponding to the status code in @l3l4_hdr
- *          and a message in @strbuf describing the error.
- */
-int i2400m_msg_check_status(const struct i2400m_l3l4_hdr *l3l4_hdr,
-			    char *strbuf, size_t strbuf_size)
-{
-	int result;
-	enum i2400m_ms status = le16_to_cpu(l3l4_hdr->status);
-	const char *str;
-
-	if (status == 0)
-		return 0;
-	if (status >= ARRAY_SIZE(ms_to_errno)) {
-		str = "unknown status code";
-		result = -EBADR;
-	} else {
-		str = ms_to_errno[status].msg;
-		result = ms_to_errno[status].errno;
-	}
-	if (strbuf)
-		snprintf(strbuf, strbuf_size, "%s (%d)", str, status);
-	return result;
-}
-
-
-/*
- * Act on a TLV System State reported by the device
- *
- * @i2400m: device descriptor
- * @ss: validated System State TLV
- */
-static
-void i2400m_report_tlv_system_state(struct i2400m *i2400m,
-				    const struct i2400m_tlv_system_state *ss)
-{
-	struct device *dev = i2400m_dev(i2400m);
-	struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
-	enum i2400m_system_state i2400m_state = le32_to_cpu(ss->state);
-
-	d_fnstart(3, dev, "(i2400m %p ss %p [%u])\n", i2400m, ss, i2400m_state);
-
-	if (i2400m->state != i2400m_state) {
-		i2400m->state = i2400m_state;
-		wake_up_all(&i2400m->state_wq);
-	}
-	switch (i2400m_state) {
-	case I2400M_SS_UNINITIALIZED:
-	case I2400M_SS_INIT:
-	case I2400M_SS_CONFIG:
-	case I2400M_SS_PRODUCTION:
-		wimax_state_change(wimax_dev, WIMAX_ST_UNINITIALIZED);
-		break;
-
-	case I2400M_SS_RF_OFF:
-	case I2400M_SS_RF_SHUTDOWN:
-		wimax_state_change(wimax_dev, WIMAX_ST_RADIO_OFF);
-		break;
-
-	case I2400M_SS_READY:
-	case I2400M_SS_STANDBY:
-	case I2400M_SS_SLEEPACTIVE:
-		wimax_state_change(wimax_dev, WIMAX_ST_READY);
-		break;
-
-	case I2400M_SS_CONNECTING:
-	case I2400M_SS_WIMAX_CONNECTED:
-		wimax_state_change(wimax_dev, WIMAX_ST_READY);
-		break;
-
-	case I2400M_SS_SCAN:
-	case I2400M_SS_OUT_OF_ZONE:
-		wimax_state_change(wimax_dev, WIMAX_ST_SCANNING);
-		break;
-
-	case I2400M_SS_IDLE:
-		d_printf(1, dev, "entering BS-negotiated idle mode\n");
-		fallthrough;
-	case I2400M_SS_DISCONNECTING:
-	case I2400M_SS_DATA_PATH_CONNECTED:
-		wimax_state_change(wimax_dev, WIMAX_ST_CONNECTED);
-		break;
-
-	default:
-		/* Huh? just in case, shut it down */
-		dev_err(dev, "HW BUG? unknown state %u: shutting down\n",
-			i2400m_state);
-		i2400m_reset(i2400m, I2400M_RT_WARM);
-		break;
-	}
-	d_fnend(3, dev, "(i2400m %p ss %p [%u]) = void\n",
-		i2400m, ss, i2400m_state);
-}
-
-
-/*
- * Parse and act on a TLV Media Status sent by the device
- *
- * @i2400m: device descriptor
- * @ms: validated Media Status TLV
- *
- * This will set the carrier up on down based on the device's link
- * report. This is done asides of what the WiMAX stack does based on
- * the device's state as sometimes we need to do a link-renew (the BS
- * wants us to renew a DHCP lease, for example).
- *
- * In fact, doc says that every time we get a link-up, we should do a
- * DHCP negotiation...
- */
-static
-void i2400m_report_tlv_media_status(struct i2400m *i2400m,
-				    const struct i2400m_tlv_media_status *ms)
-{
-	struct device *dev = i2400m_dev(i2400m);
-	struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
-	struct net_device *net_dev = wimax_dev->net_dev;
-	enum i2400m_media_status status = le32_to_cpu(ms->media_status);
-
-	d_fnstart(3, dev, "(i2400m %p ms %p [%u])\n", i2400m, ms, status);
-
-	switch (status) {
-	case I2400M_MEDIA_STATUS_LINK_UP:
-		netif_carrier_on(net_dev);
-		break;
-	case I2400M_MEDIA_STATUS_LINK_DOWN:
-		netif_carrier_off(net_dev);
-		break;
-	/*
-	 * This is the network telling us we need to retrain the DHCP
-	 * lease -- so far, we are trusting the WiMAX Network Service
-	 * in user space to pick this up and poke the DHCP client.
-	 */
-	case I2400M_MEDIA_STATUS_LINK_RENEW:
-		netif_carrier_on(net_dev);
-		break;
-	default:
-		dev_err(dev, "HW BUG? unknown media status %u\n",
-			status);
-	}
-	d_fnend(3, dev, "(i2400m %p ms %p [%u]) = void\n",
-		i2400m, ms, status);
-}
-
-
-/*
- * Process a TLV from a 'state report'
- *
- * @i2400m: device descriptor
- * @tlv: pointer to the TLV header; it has been already validated for
- *     consistent size.
- * @tag: for error messages
- *
- * Act on the TLVs from a 'state report'.
- */
-static
-void i2400m_report_state_parse_tlv(struct i2400m *i2400m,
-				   const struct i2400m_tlv_hdr *tlv,
-				   const char *tag)
-{
-	struct device *dev = i2400m_dev(i2400m);
-	const struct i2400m_tlv_media_status *ms;
-	const struct i2400m_tlv_system_state *ss;
-	const struct i2400m_tlv_rf_switches_status *rfss;
-
-	if (0 == i2400m_tlv_match(tlv, I2400M_TLV_SYSTEM_STATE, sizeof(*ss))) {
-		ss = container_of(tlv, typeof(*ss), hdr);
-		d_printf(2, dev, "%s: system state TLV "
-			 "found (0x%04x), state 0x%08x\n",
-			 tag, I2400M_TLV_SYSTEM_STATE,
-			 le32_to_cpu(ss->state));
-		i2400m_report_tlv_system_state(i2400m, ss);
-	}
-	if (0 == i2400m_tlv_match(tlv, I2400M_TLV_RF_STATUS, sizeof(*rfss))) {
-		rfss = container_of(tlv, typeof(*rfss), hdr);
-		d_printf(2, dev, "%s: RF status TLV "
-			 "found (0x%04x), sw 0x%02x hw 0x%02x\n",
-			 tag, I2400M_TLV_RF_STATUS,
-			 le32_to_cpu(rfss->sw_rf_switch),
-			 le32_to_cpu(rfss->hw_rf_switch));
-		i2400m_report_tlv_rf_switches_status(i2400m, rfss);
-	}
-	if (0 == i2400m_tlv_match(tlv, I2400M_TLV_MEDIA_STATUS, sizeof(*ms))) {
-		ms = container_of(tlv, typeof(*ms), hdr);
-		d_printf(2, dev, "%s: Media Status TLV: %u\n",
-			 tag, le32_to_cpu(ms->media_status));
-		i2400m_report_tlv_media_status(i2400m, ms);
-	}
-}
-
-
-/*
- * Parse a 'state report' and extract information
- *
- * @i2400m: device descriptor
- * @l3l4_hdr: pointer to message; it has been already validated for
- *            consistent size.
- * @size: size of the message (header + payload). The header length
- *        declaration is assumed to be congruent with @size (as in
- *        sizeof(*l3l4_hdr) + l3l4_hdr->length == size)
- *
- * Walk over the TLVs in a report state and act on them.
- */
-static
-void i2400m_report_state_hook(struct i2400m *i2400m,
-			      const struct i2400m_l3l4_hdr *l3l4_hdr,
-			      size_t size, const char *tag)
-{
-	struct device *dev = i2400m_dev(i2400m);
-	const struct i2400m_tlv_hdr *tlv;
-	size_t tlv_size = le16_to_cpu(l3l4_hdr->length);
-
-	d_fnstart(4, dev, "(i2400m %p, l3l4_hdr %p, size %zu, %s)\n",
-		  i2400m, l3l4_hdr, size, tag);
-	tlv = NULL;
-
-	while ((tlv = i2400m_tlv_buffer_walk(i2400m, &l3l4_hdr->pl,
-					     tlv_size, tlv)))
-		i2400m_report_state_parse_tlv(i2400m, tlv, tag);
-	d_fnend(4, dev, "(i2400m %p, l3l4_hdr %p, size %zu, %s) = void\n",
-		i2400m, l3l4_hdr, size, tag);
-}
-
-
-/*
- * i2400m_report_hook - (maybe) act on a report
- *
- * @i2400m: device descriptor
- * @l3l4_hdr: pointer to message; it has been already validated for
- *            consistent size.
- * @size: size of the message (header + payload). The header length
- *        declaration is assumed to be congruent with @size (as in
- *        sizeof(*l3l4_hdr) + l3l4_hdr->length == size)
- *
- * Extract information we might need (like carrien on/off) from a
- * device report.
- */
-void i2400m_report_hook(struct i2400m *i2400m,
-			const struct i2400m_l3l4_hdr *l3l4_hdr, size_t size)
-{
-	struct device *dev = i2400m_dev(i2400m);
-	unsigned msg_type;
-
-	d_fnstart(3, dev, "(i2400m %p l3l4_hdr %p size %zu)\n",
-		  i2400m, l3l4_hdr, size);
-	/* Chew on the message, we might need some information from
-	 * here */
-	msg_type = le16_to_cpu(l3l4_hdr->type);
-	switch (msg_type) {
-	case I2400M_MT_REPORT_STATE:	/* carrier detection... */
-		i2400m_report_state_hook(i2400m,
-					 l3l4_hdr, size, "REPORT STATE");
-		break;
-	/* If the device is ready for power save, then ask it to do
-	 * it. */
-	case I2400M_MT_REPORT_POWERSAVE_READY:	/* zzzzz */
-		if (l3l4_hdr->status == cpu_to_le16(I2400M_MS_DONE_OK)) {
-			if (i2400m_power_save_disabled)
-				d_printf(1, dev, "ready for powersave, "
-					 "not requesting (disabled by module "
-					 "parameter)\n");
-			else {
-				d_printf(1, dev, "ready for powersave, "
-					 "requesting\n");
-				i2400m_cmd_enter_powersave(i2400m);
-			}
-		}
-		break;
-	}
-	d_fnend(3, dev, "(i2400m %p l3l4_hdr %p size %zu) = void\n",
-		i2400m, l3l4_hdr, size);
-}
-
-
-/*
- * i2400m_msg_ack_hook - process cmd/set/get ack for internal status
- *
- * @i2400m: device descriptor
- * @l3l4_hdr: pointer to message; it has been already validated for
- *            consistent size.
- * @size: size of the message
- *
- * Extract information we might need from acks to commands and act on
- * it. This is akin to i2400m_report_hook(). Note most of this
- * processing should be done in the function that calls the
- * command. This is here for some cases where it can't happen...
- */
-static void i2400m_msg_ack_hook(struct i2400m *i2400m,
-				 const struct i2400m_l3l4_hdr *l3l4_hdr,
-				 size_t size)
-{
-	int result;
-	struct device *dev = i2400m_dev(i2400m);
-	unsigned int ack_type;
-	char strerr[32];
-
-	/* Chew on the message, we might need some information from
-	 * here */
-	ack_type = le16_to_cpu(l3l4_hdr->type);
-	switch (ack_type) {
-	case I2400M_MT_CMD_ENTER_POWERSAVE:
-		/* This is just left here for the sake of example, as
-		 * the processing is done somewhere else. */
-		if (0) {
-			result = i2400m_msg_check_status(
-				l3l4_hdr, strerr, sizeof(strerr));
-			if (result >= 0)
-				d_printf(1, dev, "ready for power save: %zd\n",
-					 size);
-		}
-		break;
-	}
-}
-
-
-/*
- * i2400m_msg_size_check() - verify message size and header are congruent
- *
- * It is ok if the total message size is larger than the expected
- * size, as there can be padding.
- */
-int i2400m_msg_size_check(struct i2400m *i2400m,
-			  const struct i2400m_l3l4_hdr *l3l4_hdr,
-			  size_t msg_size)
-{
-	int result;
-	struct device *dev = i2400m_dev(i2400m);
-	size_t expected_size;
-	d_fnstart(4, dev, "(i2400m %p l3l4_hdr %p msg_size %zu)\n",
-		  i2400m, l3l4_hdr, msg_size);
-	if (msg_size < sizeof(*l3l4_hdr)) {
-		dev_err(dev, "bad size for message header "
-			"(expected at least %zu, got %zu)\n",
-			(size_t) sizeof(*l3l4_hdr), msg_size);
-		result = -EIO;
-		goto error_hdr_size;
-	}
-	expected_size = le16_to_cpu(l3l4_hdr->length) + sizeof(*l3l4_hdr);
-	if (msg_size < expected_size) {
-		dev_err(dev, "bad size for message code 0x%04x (expected %zu, "
-			"got %zu)\n", le16_to_cpu(l3l4_hdr->type),
-			expected_size, msg_size);
-		result = -EIO;
-	} else
-		result = 0;
-error_hdr_size:
-	d_fnend(4, dev,
-		"(i2400m %p l3l4_hdr %p msg_size %zu) = %d\n",
-		i2400m, l3l4_hdr, msg_size, result);
-	return result;
-}
-
-
-
-/*
- * Cancel a wait for a command ACK
- *
- * @i2400m: device descriptor
- * @code: [negative] errno code to cancel with (don't use
- *     -EINPROGRESS)
- *
- * If there is an ack already filled out, free it.
- */
-void i2400m_msg_to_dev_cancel_wait(struct i2400m *i2400m, int code)
-{
-	struct sk_buff *ack_skb;
-	unsigned long flags;
-
-	spin_lock_irqsave(&i2400m->rx_lock, flags);
-	ack_skb = i2400m->ack_skb;
-	if (ack_skb && !IS_ERR(ack_skb))
-		kfree_skb(ack_skb);
-	i2400m->ack_skb = ERR_PTR(code);
-	spin_unlock_irqrestore(&i2400m->rx_lock, flags);
-}
-
-
-/**
- * i2400m_msg_to_dev - Send a control message to the device and get a response
- *
- * @i2400m: device descriptor
- *
- * @buf: pointer to the buffer containing the message to be sent; it
- *           has to start with a &struct i2400M_l3l4_hdr and then
- *           followed by the payload. Once this function returns, the
- *           buffer can be reused.
- *
- * @buf_len: buffer size
- *
- * Returns:
- *
- * Pointer to skb containing the ack message. You need to check the
- * pointer with IS_ERR(), as it might be an error code. Error codes
- * could happen because:
- *
- *  - the message wasn't formatted correctly
- *  - couldn't send the message
- *  - failed waiting for a response
- *  - the ack message wasn't formatted correctly
- *
- * The returned skb has been allocated with wimax_msg_to_user_alloc(),
- * it contains the response in a netlink attribute and is ready to be
- * passed up to user space with wimax_msg_to_user_send(). To access
- * the payload and its length, use wimax_msg_{data,len}() on the skb.
- *
- * The skb has to be freed with kfree_skb() once done.
- *
- * Description:
- *
- * This function delivers a message/command to the device and waits
- * for an ack to be received. The format is described in
- * linux/wimax/i2400m.h. In summary, a command/get/set is followed by an
- * ack.
- *
- * This function will not check the ack status, that's left up to the
- * caller.  Once done with the ack skb, it has to be kfree_skb()ed.
- *
- * The i2400m handles only one message at the same time, thus we need
- * the mutex to exclude other players.
- *
- * We write the message and then wait for an answer to come back. The
- * RX path intercepts control messages and handles them in
- * i2400m_rx_ctl(). Reports (notifications) are (maybe) processed
- * locally and then forwarded (as needed) to user space on the WiMAX
- * stack message pipe. Acks are saved and passed back to us through an
- * skb in i2400m->ack_skb which is ready to be given to generic
- * netlink if need be.
- */
-struct sk_buff *i2400m_msg_to_dev(struct i2400m *i2400m,
-				  const void *buf, size_t buf_len)
-{
-	int result;
-	struct device *dev = i2400m_dev(i2400m);
-	const struct i2400m_l3l4_hdr *msg_l3l4_hdr;
-	struct sk_buff *ack_skb;
-	const struct i2400m_l3l4_hdr *ack_l3l4_hdr;
-	size_t ack_len;
-	int ack_timeout;
-	unsigned msg_type;
-	unsigned long flags;
-
-	d_fnstart(3, dev, "(i2400m %p buf %p len %zu)\n",
-		  i2400m, buf, buf_len);
-
-	rmb();		/* Make sure we see what i2400m_dev_reset_handle() */
-	if (i2400m->boot_mode)
-		return ERR_PTR(-EL3RST);
-
-	msg_l3l4_hdr = buf;
-	/* Check msg & payload consistency */
-	result = i2400m_msg_size_check(i2400m, msg_l3l4_hdr, buf_len);
-	if (result < 0)
-		goto error_bad_msg;
-	msg_type = le16_to_cpu(msg_l3l4_hdr->type);
-	d_printf(1, dev, "CMD/GET/SET 0x%04x %zu bytes\n",
-		 msg_type, buf_len);
-	d_dump(2, dev, buf, buf_len);
-
-	/* Setup the completion, ack_skb ("we are waiting") and send
-	 * the message to the device */
-	mutex_lock(&i2400m->msg_mutex);
-	spin_lock_irqsave(&i2400m->rx_lock, flags);
-	i2400m->ack_skb = ERR_PTR(-EINPROGRESS);
-	spin_unlock_irqrestore(&i2400m->rx_lock, flags);
-	init_completion(&i2400m->msg_completion);
-	result = i2400m_tx(i2400m, buf, buf_len, I2400M_PT_CTRL);
-	if (result < 0) {
-		dev_err(dev, "can't send message 0x%04x: %d\n",
-			le16_to_cpu(msg_l3l4_hdr->type), result);
-		goto error_tx;
-	}
-
-	/* Some commands take longer to execute because of crypto ops,
-	 * so we give them some more leeway on timeout */
-	switch (msg_type) {
-	case I2400M_MT_GET_TLS_OPERATION_RESULT:
-	case I2400M_MT_CMD_SEND_EAP_RESPONSE:
-		ack_timeout = 5 * HZ;
-		break;
-	default:
-		ack_timeout = HZ;
-	}
-
-	if (unlikely(i2400m->trace_msg_from_user))
-		wimax_msg(&i2400m->wimax_dev, "echo", buf, buf_len, GFP_KERNEL);
-	/* The RX path in rx.c will put any response for this message
-	 * in i2400m->ack_skb and wake us up. If we cancel the wait,
-	 * we need to change the value of i2400m->ack_skb to something
-	 * not -EINPROGRESS so RX knows there is no one waiting. */
-	result = wait_for_completion_interruptible_timeout(
-		&i2400m->msg_completion, ack_timeout);
-	if (result == 0) {
-		dev_err(dev, "timeout waiting for reply to message 0x%04x\n",
-			msg_type);
-		result = -ETIMEDOUT;
-		i2400m_msg_to_dev_cancel_wait(i2400m, result);
-		goto error_wait_for_completion;
-	} else if (result < 0) {
-		dev_err(dev, "error waiting for reply to message 0x%04x: %d\n",
-			msg_type, result);
-		i2400m_msg_to_dev_cancel_wait(i2400m, result);
-		goto error_wait_for_completion;
-	}
-
-	/* Pull out the ack data from i2400m->ack_skb -- see if it is
-	 * an error and act accordingly */
-	spin_lock_irqsave(&i2400m->rx_lock, flags);
-	ack_skb = i2400m->ack_skb;
-	if (IS_ERR(ack_skb))
-		result = PTR_ERR(ack_skb);
-	else
-		result = 0;
-	i2400m->ack_skb = NULL;
-	spin_unlock_irqrestore(&i2400m->rx_lock, flags);
-	if (result < 0)
-		goto error_ack_status;
-	ack_l3l4_hdr = wimax_msg_data_len(ack_skb, &ack_len);
-
-	/* Check the ack and deliver it if it is ok */
-	if (unlikely(i2400m->trace_msg_from_user))
-		wimax_msg(&i2400m->wimax_dev, "echo",
-			  ack_l3l4_hdr, ack_len, GFP_KERNEL);
-	result = i2400m_msg_size_check(i2400m, ack_l3l4_hdr, ack_len);
-	if (result < 0) {
-		dev_err(dev, "HW BUG? reply to message 0x%04x: %d\n",
-			msg_type, result);
-		goto error_bad_ack_len;
-	}
-	if (msg_type != le16_to_cpu(ack_l3l4_hdr->type)) {
-		dev_err(dev, "HW BUG? bad reply 0x%04x to message 0x%04x\n",
-			le16_to_cpu(ack_l3l4_hdr->type), msg_type);
-		result = -EIO;
-		goto error_bad_ack_type;
-	}
-	i2400m_msg_ack_hook(i2400m, ack_l3l4_hdr, ack_len);
-	mutex_unlock(&i2400m->msg_mutex);
-	d_fnend(3, dev, "(i2400m %p buf %p len %zu) = %p\n",
-		i2400m, buf, buf_len, ack_skb);
-	return ack_skb;
-
-error_bad_ack_type:
-error_bad_ack_len:
-	kfree_skb(ack_skb);
-error_ack_status:
-error_wait_for_completion:
-error_tx:
-	mutex_unlock(&i2400m->msg_mutex);
-error_bad_msg:
-	d_fnend(3, dev, "(i2400m %p buf %p len %zu) = %d\n",
-		i2400m, buf, buf_len, result);
-	return ERR_PTR(result);
-}
-
-
-/*
- * Definitions for the Enter Power Save command
- *
- * The Enter Power Save command requests the device to go into power
- * saving mode. The device will ack or nak the command depending on it
- * being ready for it. If it acks, we tell the USB subsystem to
- *
- * As well, the device might request to go into power saving mode by
- * sending a report (REPORT_POWERSAVE_READY), in which case, we issue
- * this command. The hookups in the RX coder allow
- */
-enum {
-	I2400M_WAKEUP_ENABLED  = 0x01,
-	I2400M_WAKEUP_DISABLED = 0x02,
-	I2400M_TLV_TYPE_WAKEUP_MODE = 144,
-};
-
-struct i2400m_cmd_enter_power_save {
-	struct i2400m_l3l4_hdr hdr;
-	struct i2400m_tlv_hdr tlv;
-	__le32 val;
-} __packed;
-
-
-/*
- * Request entering power save
- *
- * This command is (mainly) executed when the device indicates that it
- * is ready to go into powersave mode via a REPORT_POWERSAVE_READY.
- */
-int i2400m_cmd_enter_powersave(struct i2400m *i2400m)
-{
-	int result;
-	struct device *dev = i2400m_dev(i2400m);
-	struct sk_buff *ack_skb;
-	struct i2400m_cmd_enter_power_save *cmd;
-	char strerr[32];
-
-	result = -ENOMEM;
-	cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
-	if (cmd == NULL)
-		goto error_alloc;
-	cmd->hdr.type = cpu_to_le16(I2400M_MT_CMD_ENTER_POWERSAVE);
-	cmd->hdr.length = cpu_to_le16(sizeof(*cmd) - sizeof(cmd->hdr));
-	cmd->hdr.version = cpu_to_le16(I2400M_L3L4_VERSION);
-	cmd->tlv.type = cpu_to_le16(I2400M_TLV_TYPE_WAKEUP_MODE);
-	cmd->tlv.length = cpu_to_le16(sizeof(cmd->val));
-	cmd->val = cpu_to_le32(I2400M_WAKEUP_ENABLED);
-
-	ack_skb = i2400m_msg_to_dev(i2400m, cmd, sizeof(*cmd));
-	result = PTR_ERR(ack_skb);
-	if (IS_ERR(ack_skb)) {
-		dev_err(dev, "Failed to issue 'Enter power save' command: %d\n",
-			result);
-		goto error_msg_to_dev;
-	}
-	result = i2400m_msg_check_status(wimax_msg_data(ack_skb),
-					 strerr, sizeof(strerr));
-	if (result == -EACCES)
-		d_printf(1, dev, "Cannot enter power save mode\n");
-	else if (result < 0)
-		dev_err(dev, "'Enter power save' (0x%04x) command failed: "
-			"%d - %s\n", I2400M_MT_CMD_ENTER_POWERSAVE,
-			result, strerr);
-	else
-		d_printf(1, dev, "device ready to power save\n");
-	kfree_skb(ack_skb);
-error_msg_to_dev:
-	kfree(cmd);
-error_alloc:
-	return result;
-}
-EXPORT_SYMBOL_GPL(i2400m_cmd_enter_powersave);
-
-
-/*
- * Definitions for getting device information
- */
-enum {
-	I2400M_TLV_DETAILED_DEVICE_INFO = 140
-};
-
-/**
- * i2400m_get_device_info - Query the device for detailed device information
- *
- * @i2400m: device descriptor
- *
- * Returns: an skb whose skb->data points to a 'struct
- *    i2400m_tlv_detailed_device_info'. When done, kfree_skb() it. The
- *    skb is *guaranteed* to contain the whole TLV data structure.
- *
- *    On error, IS_ERR(skb) is true and ERR_PTR(skb) is the error
- *    code.
- */
-struct sk_buff *i2400m_get_device_info(struct i2400m *i2400m)
-{
-	int result;
-	struct device *dev = i2400m_dev(i2400m);
-	struct sk_buff *ack_skb;
-	struct i2400m_l3l4_hdr *cmd;
-	const struct i2400m_l3l4_hdr *ack;
-	size_t ack_len;
-	const struct i2400m_tlv_hdr *tlv;
-	const struct i2400m_tlv_detailed_device_info *ddi;
-	char strerr[32];
-
-	ack_skb = ERR_PTR(-ENOMEM);
-	cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
-	if (cmd == NULL)
-		goto error_alloc;
-	cmd->type = cpu_to_le16(I2400M_MT_GET_DEVICE_INFO);
-	cmd->length = 0;
-	cmd->version = cpu_to_le16(I2400M_L3L4_VERSION);
-
-	ack_skb = i2400m_msg_to_dev(i2400m, cmd, sizeof(*cmd));
-	if (IS_ERR(ack_skb)) {
-		dev_err(dev, "Failed to issue 'get device info' command: %ld\n",
-			PTR_ERR(ack_skb));
-		goto error_msg_to_dev;
-	}
-	ack = wimax_msg_data_len(ack_skb, &ack_len);
-	result = i2400m_msg_check_status(ack, strerr, sizeof(strerr));
-	if (result < 0) {
-		dev_err(dev, "'get device info' (0x%04x) command failed: "
-			"%d - %s\n", I2400M_MT_GET_DEVICE_INFO, result,
-			strerr);
-		goto error_cmd_failed;
-	}
-	tlv = i2400m_tlv_find(i2400m, ack->pl, ack_len - sizeof(*ack),
-			      I2400M_TLV_DETAILED_DEVICE_INFO, sizeof(*ddi));
-	if (tlv == NULL) {
-		dev_err(dev, "GET DEVICE INFO: "
-			"detailed device info TLV not found (0x%04x)\n",
-			I2400M_TLV_DETAILED_DEVICE_INFO);
-		result = -EIO;
-		goto error_no_tlv;
-	}
-	skb_pull(ack_skb, (void *) tlv - (void *) ack_skb->data);
-error_msg_to_dev:
-	kfree(cmd);
-error_alloc:
-	return ack_skb;
-
-error_no_tlv:
-error_cmd_failed:
-	kfree_skb(ack_skb);
-	kfree(cmd);
-	return ERR_PTR(result);
-}
-
-
-/* Firmware interface versions we support */
-enum {
-	I2400M_HDIv_MAJOR = 9,
-	I2400M_HDIv_MINOR = 1,
-	I2400M_HDIv_MINOR_2 = 2,
-};
-
-
-/**
- * i2400m_firmware_check - check firmware versions are compatible with
- * the driver
- *
- * @i2400m: device descriptor
- *
- * Returns: 0 if ok, < 0 errno code an error and a message in the
- *    kernel log.
- *
- * Long function, but quite simple; first chunk launches the command
- * and double checks the reply for the right TLV. Then we process the
- * TLV (where the meat is).
- *
- * Once we process the TLV that gives us the firmware's interface
- * version, we encode it and save it in i2400m->fw_version for future
- * reference.
- */
-int i2400m_firmware_check(struct i2400m *i2400m)
-{
-	int result;
-	struct device *dev = i2400m_dev(i2400m);
-	struct sk_buff *ack_skb;
-	struct i2400m_l3l4_hdr *cmd;
-	const struct i2400m_l3l4_hdr *ack;
-	size_t ack_len;
-	const struct i2400m_tlv_hdr *tlv;
-	const struct i2400m_tlv_l4_message_versions *l4mv;
-	char strerr[32];
-	unsigned major, minor, branch;
-
-	result = -ENOMEM;
-	cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
-	if (cmd == NULL)
-		goto error_alloc;
-	cmd->type = cpu_to_le16(I2400M_MT_GET_LM_VERSION);
-	cmd->length = 0;
-	cmd->version = cpu_to_le16(I2400M_L3L4_VERSION);
-
-	ack_skb = i2400m_msg_to_dev(i2400m, cmd, sizeof(*cmd));
-	if (IS_ERR(ack_skb)) {
-		result = PTR_ERR(ack_skb);
-		dev_err(dev, "Failed to issue 'get lm version' command: %-d\n",
-			result);
-		goto error_msg_to_dev;
-	}
-	ack = wimax_msg_data_len(ack_skb, &ack_len);
-	result = i2400m_msg_check_status(ack, strerr, sizeof(strerr));
-	if (result < 0) {
-		dev_err(dev, "'get lm version' (0x%04x) command failed: "
-			"%d - %s\n", I2400M_MT_GET_LM_VERSION, result,
-			strerr);
-		goto error_cmd_failed;
-	}
-	tlv = i2400m_tlv_find(i2400m, ack->pl, ack_len - sizeof(*ack),
-			      I2400M_TLV_L4_MESSAGE_VERSIONS, sizeof(*l4mv));
-	if (tlv == NULL) {
-		dev_err(dev, "get lm version: TLV not found (0x%04x)\n",
-			I2400M_TLV_L4_MESSAGE_VERSIONS);
-		result = -EIO;
-		goto error_no_tlv;
-	}
-	l4mv = container_of(tlv, typeof(*l4mv), hdr);
-	major = le16_to_cpu(l4mv->major);
-	minor = le16_to_cpu(l4mv->minor);
-	branch = le16_to_cpu(l4mv->branch);
-	result = -EINVAL;
-	if (major != I2400M_HDIv_MAJOR) {
-		dev_err(dev, "unsupported major fw version "
-			"%u.%u.%u\n", major, minor, branch);
-		goto error_bad_major;
-	}
-	result = 0;
-	if (minor > I2400M_HDIv_MINOR_2 || minor < I2400M_HDIv_MINOR)
-		dev_warn(dev, "untested minor fw version %u.%u.%u\n",
-			 major, minor, branch);
-	/* Yes, we ignore the branch -- we don't have to track it */
-	i2400m->fw_version = major << 16 | minor;
-	dev_info(dev, "firmware interface version %u.%u.%u\n",
-		 major, minor, branch);
-error_bad_major:
-error_no_tlv:
-error_cmd_failed:
-	kfree_skb(ack_skb);
-error_msg_to_dev:
-	kfree(cmd);
-error_alloc:
-	return result;
-}
-
-
-/*
- * Send an DoExitIdle command to the device to ask it to go out of
- * basestation-idle mode.
- *
- * @i2400m: device descriptor
- *
- * This starts a renegotiation with the basestation that might involve
- * another crypto handshake with user space.
- *
- * Returns: 0 if ok, < 0 errno code on error.
- */
-int i2400m_cmd_exit_idle(struct i2400m *i2400m)
-{
-	int result;
-	struct device *dev = i2400m_dev(i2400m);
-	struct sk_buff *ack_skb;
-	struct i2400m_l3l4_hdr *cmd;
-	char strerr[32];
-
-	result = -ENOMEM;
-	cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
-	if (cmd == NULL)
-		goto error_alloc;
-	cmd->type = cpu_to_le16(I2400M_MT_CMD_EXIT_IDLE);
-	cmd->length = 0;
-	cmd->version = cpu_to_le16(I2400M_L3L4_VERSION);
-
-	ack_skb = i2400m_msg_to_dev(i2400m, cmd, sizeof(*cmd));
-	result = PTR_ERR(ack_skb);
-	if (IS_ERR(ack_skb)) {
-		dev_err(dev, "Failed to issue 'exit idle' command: %d\n",
-			result);
-		goto error_msg_to_dev;
-	}
-	result = i2400m_msg_check_status(wimax_msg_data(ack_skb),
-					 strerr, sizeof(strerr));
-	kfree_skb(ack_skb);
-error_msg_to_dev:
-	kfree(cmd);
-error_alloc:
-	return result;
-
-}
-
-
-/*
- * Query the device for its state, update the WiMAX stack's idea of it
- *
- * @i2400m: device descriptor
- *
- * Returns: 0 if ok, < 0 errno code on error.
- *
- * Executes a 'Get State' command and parses the returned
- * TLVs.
- *
- * Because this is almost identical to a 'Report State', we use
- * i2400m_report_state_hook() to parse the answer. This will set the
- * carrier state, as well as the RF Kill switches state.
- */
-static int i2400m_cmd_get_state(struct i2400m *i2400m)
-{
-	int result;
-	struct device *dev = i2400m_dev(i2400m);
-	struct sk_buff *ack_skb;
-	struct i2400m_l3l4_hdr *cmd;
-	const struct i2400m_l3l4_hdr *ack;
-	size_t ack_len;
-	char strerr[32];
-
-	result = -ENOMEM;
-	cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
-	if (cmd == NULL)
-		goto error_alloc;
-	cmd->type = cpu_to_le16(I2400M_MT_GET_STATE);
-	cmd->length = 0;
-	cmd->version = cpu_to_le16(I2400M_L3L4_VERSION);
-
-	ack_skb = i2400m_msg_to_dev(i2400m, cmd, sizeof(*cmd));
-	if (IS_ERR(ack_skb)) {
-		dev_err(dev, "Failed to issue 'get state' command: %ld\n",
-			PTR_ERR(ack_skb));
-		result = PTR_ERR(ack_skb);
-		goto error_msg_to_dev;
-	}
-	ack = wimax_msg_data_len(ack_skb, &ack_len);
-	result = i2400m_msg_check_status(ack, strerr, sizeof(strerr));
-	if (result < 0) {
-		dev_err(dev, "'get state' (0x%04x) command failed: "
-			"%d - %s\n", I2400M_MT_GET_STATE, result, strerr);
-		goto error_cmd_failed;
-	}
-	i2400m_report_state_hook(i2400m, ack, ack_len - sizeof(*ack),
-				 "GET STATE");
-	result = 0;
-	kfree_skb(ack_skb);
-error_cmd_failed:
-error_msg_to_dev:
-	kfree(cmd);
-error_alloc:
-	return result;
-}
-
-/**
- * Set basic configuration settings
- *
- * @i2400m: device descriptor
- * @args: array of pointers to the TLV headers to send for
- *     configuration (each followed by its payload).
- *     TLV headers and payloads must be properly initialized, with the
- *     right endianess (LE).
- * @arg_size: number of pointers in the @args array
- */
-static int i2400m_set_init_config(struct i2400m *i2400m,
-				  const struct i2400m_tlv_hdr **arg,
-				  size_t args)
-{
-	int result;
-	struct device *dev = i2400m_dev(i2400m);
-	struct sk_buff *ack_skb;
-	struct i2400m_l3l4_hdr *cmd;
-	char strerr[32];
-	unsigned argc, argsize, tlv_size;
-	const struct i2400m_tlv_hdr *tlv_hdr;
-	void *buf, *itr;
-
-	d_fnstart(3, dev, "(i2400m %p arg %p args %zu)\n", i2400m, arg, args);
-	result = 0;
-	if (args == 0)
-		goto none;
-	/* Compute the size of all the TLVs, so we can alloc a
-	 * contiguous command block to copy them. */
-	argsize = 0;
-	for (argc = 0; argc < args; argc++) {
-		tlv_hdr = arg[argc];
-		argsize += sizeof(*tlv_hdr) + le16_to_cpu(tlv_hdr->length);
-	}
-	WARN_ON(argc >= 9);	/* As per hw spec */
-
-	/* Alloc the space for the command and TLVs*/
-	result = -ENOMEM;
-	buf = kzalloc(sizeof(*cmd) + argsize, GFP_KERNEL);
-	if (buf == NULL)
-		goto error_alloc;
-	cmd = buf;
-	cmd->type = cpu_to_le16(I2400M_MT_SET_INIT_CONFIG);
-	cmd->length = cpu_to_le16(argsize);
-	cmd->version = cpu_to_le16(I2400M_L3L4_VERSION);
-
-	/* Copy the TLVs */
-	itr = buf + sizeof(*cmd);
-	for (argc = 0; argc < args; argc++) {
-		tlv_hdr = arg[argc];
-		tlv_size = sizeof(*tlv_hdr) + le16_to_cpu(tlv_hdr->length);
-		memcpy(itr, tlv_hdr, tlv_size);
-		itr += tlv_size;
-	}
-
-	/* Send the message! */
-	ack_skb = i2400m_msg_to_dev(i2400m, buf, sizeof(*cmd) + argsize);
-	result = PTR_ERR(ack_skb);
-	if (IS_ERR(ack_skb)) {
-		dev_err(dev, "Failed to issue 'init config' command: %d\n",
-			result);
-
-		goto error_msg_to_dev;
-	}
-	result = i2400m_msg_check_status(wimax_msg_data(ack_skb),
-					 strerr, sizeof(strerr));
-	if (result < 0)
-		dev_err(dev, "'init config' (0x%04x) command failed: %d - %s\n",
-			I2400M_MT_SET_INIT_CONFIG, result, strerr);
-	kfree_skb(ack_skb);
-error_msg_to_dev:
-	kfree(buf);
-error_alloc:
-none:
-	d_fnend(3, dev, "(i2400m %p arg %p args %zu) = %d\n",
-		i2400m, arg, args, result);
-	return result;
-
-}
-
-/**
- * i2400m_set_idle_timeout - Set the device's idle mode timeout
- *
- * @i2400m: i2400m device descriptor
- *
- * @msecs: milliseconds for the timeout to enter idle mode. Between
- *     100 to 300000 (5m); 0 to disable. In increments of 100.
- *
- * After this @msecs of the link being idle (no data being sent or
- * received), the device will negotiate with the basestation entering
- * idle mode for saving power. The connection is maintained, but
- * getting out of it (done in tx.c) will require some negotiation,
- * possible crypto re-handshake and a possible DHCP re-lease.
- *
- * Only available if fw_version >= 0x00090002.
- *
- * Returns: 0 if ok, < 0 errno code on error.
- */
-int i2400m_set_idle_timeout(struct i2400m *i2400m, unsigned msecs)
-{
-	int result;
-	struct device *dev = i2400m_dev(i2400m);
-	struct sk_buff *ack_skb;
-	struct {
-		struct i2400m_l3l4_hdr hdr;
-		struct i2400m_tlv_config_idle_timeout cit;
-	} *cmd;
-	const struct i2400m_l3l4_hdr *ack;
-	size_t ack_len;
-	char strerr[32];
-
-	result = -ENOSYS;
-	if (i2400m_le_v1_3(i2400m))
-		goto error_alloc;
-	result = -ENOMEM;
-	cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
-	if (cmd == NULL)
-		goto error_alloc;
-	cmd->hdr.type = cpu_to_le16(I2400M_MT_GET_STATE);
-	cmd->hdr.length = cpu_to_le16(sizeof(*cmd) - sizeof(cmd->hdr));
-	cmd->hdr.version = cpu_to_le16(I2400M_L3L4_VERSION);
-
-	cmd->cit.hdr.type =
-		cpu_to_le16(I2400M_TLV_CONFIG_IDLE_TIMEOUT);
-	cmd->cit.hdr.length = cpu_to_le16(sizeof(cmd->cit.timeout));
-	cmd->cit.timeout = cpu_to_le32(msecs);
-
-	ack_skb = i2400m_msg_to_dev(i2400m, cmd, sizeof(*cmd));
-	if (IS_ERR(ack_skb)) {
-		dev_err(dev, "Failed to issue 'set idle timeout' command: "
-			"%ld\n", PTR_ERR(ack_skb));
-		result = PTR_ERR(ack_skb);
-		goto error_msg_to_dev;
-	}
-	ack = wimax_msg_data_len(ack_skb, &ack_len);
-	result = i2400m_msg_check_status(ack, strerr, sizeof(strerr));
-	if (result < 0) {
-		dev_err(dev, "'set idle timeout' (0x%04x) command failed: "
-			"%d - %s\n", I2400M_MT_GET_STATE, result, strerr);
-		goto error_cmd_failed;
-	}
-	result = 0;
-	kfree_skb(ack_skb);
-error_cmd_failed:
-error_msg_to_dev:
-	kfree(cmd);
-error_alloc:
-	return result;
-}
-
-
-/**
- * i2400m_dev_initialize - Initialize the device once communications are ready
- *
- * @i2400m: device descriptor
- *
- * Returns: 0 if ok, < 0 errno code on error.
- *
- * Configures the device to work the way we like it.
- *
- * At the point of this call, the device is registered with the WiMAX
- * and netdev stacks, firmware is uploaded and we can talk to the
- * device normally.
- */
-int i2400m_dev_initialize(struct i2400m *i2400m)
-{
-	int result;
-	struct device *dev = i2400m_dev(i2400m);
-	struct i2400m_tlv_config_idle_parameters idle_params;
-	struct i2400m_tlv_config_idle_timeout idle_timeout;
-	struct i2400m_tlv_config_d2h_data_format df;
-	struct i2400m_tlv_config_dl_host_reorder dlhr;
-	const struct i2400m_tlv_hdr *args[9];
-	unsigned argc = 0;
-
-	d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
-	if (i2400m_passive_mode)
-		goto out_passive;
-	/* Disable idle mode? (enabled by default) */
-	if (i2400m_idle_mode_disabled) {
-		if (i2400m_le_v1_3(i2400m)) {
-			idle_params.hdr.type =
-				cpu_to_le16(I2400M_TLV_CONFIG_IDLE_PARAMETERS);
-			idle_params.hdr.length = cpu_to_le16(
-				sizeof(idle_params) - sizeof(idle_params.hdr));
-			idle_params.idle_timeout = 0;
-			idle_params.idle_paging_interval = 0;
-			args[argc++] = &idle_params.hdr;
-		} else {
-			idle_timeout.hdr.type =
-				cpu_to_le16(I2400M_TLV_CONFIG_IDLE_TIMEOUT);
-			idle_timeout.hdr.length = cpu_to_le16(
-				sizeof(idle_timeout) - sizeof(idle_timeout.hdr));
-			idle_timeout.timeout = 0;
-			args[argc++] = &idle_timeout.hdr;
-		}
-	}
-	if (i2400m_ge_v1_4(i2400m)) {
-		/* Enable extended RX data format? */
-		df.hdr.type =
-			cpu_to_le16(I2400M_TLV_CONFIG_D2H_DATA_FORMAT);
-		df.hdr.length = cpu_to_le16(
-			sizeof(df) - sizeof(df.hdr));
-		df.format = 1;
-		args[argc++] = &df.hdr;
-
-		/* Enable RX data reordering?
-		 * (switch flipped in rx.c:i2400m_rx_setup() after fw upload) */
-		if (i2400m->rx_reorder) {
-			dlhr.hdr.type =
-				cpu_to_le16(I2400M_TLV_CONFIG_DL_HOST_REORDER);
-			dlhr.hdr.length = cpu_to_le16(
-				sizeof(dlhr) - sizeof(dlhr.hdr));
-			dlhr.reorder = 1;
-			args[argc++] = &dlhr.hdr;
-		}
-	}
-	result = i2400m_set_init_config(i2400m, args, argc);
-	if (result < 0)
-		goto error;
-out_passive:
-	/*
-	 * Update state: Here it just calls a get state; parsing the
-	 * result (System State TLV and RF Status TLV [done in the rx
-	 * path hooks]) will set the hardware and software RF-Kill
-	 * status.
-	 */
-	result = i2400m_cmd_get_state(i2400m);
-error:
-	if (result < 0)
-		dev_err(dev, "failed to initialize the device: %d\n", result);
-	d_fnend(3, dev, "(i2400m %p) = %d\n", i2400m, result);
-	return result;
-}
-
-
-/**
- * i2400m_dev_shutdown - Shutdown a running device
- *
- * @i2400m: device descriptor
- *
- * Release resources acquired during the running of the device; in
- * theory, should also tell the device to go to sleep, switch off the
- * radio, all that, but at this point, in most cases (driver
- * disconnection, reset handling) we can't even talk to the device.
- */
-void i2400m_dev_shutdown(struct i2400m *i2400m)
-{
-	struct device *dev = i2400m_dev(i2400m);
-
-	d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
-	d_fnend(3, dev, "(i2400m %p) = void\n", i2400m);
-}
diff --git a/drivers/net/wimax/i2400m/debug-levels.h b/drivers/net/wimax/i2400m/debug-levels.h
deleted file mode 100644
index 00942bb1489b..000000000000
--- a/drivers/net/wimax/i2400m/debug-levels.h
+++ /dev/null
@@ -1,32 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel Wireless WiMAX Connection 2400m
- * Debug levels control file for the i2400m module
- *
- * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- */
-#ifndef __debug_levels__h__
-#define __debug_levels__h__
-
-/* Maximum compile and run time debug level for all submodules */
-#define D_MODULENAME i2400m
-#define D_MASTER CONFIG_WIMAX_I2400M_DEBUG_LEVEL
-
-#include <linux/wimax/debug.h>
-
-/* List of all the enabled modules */
-enum d_module {
-	D_SUBMODULE_DECLARE(control),
-	D_SUBMODULE_DECLARE(driver),
-	D_SUBMODULE_DECLARE(debugfs),
-	D_SUBMODULE_DECLARE(fw),
-	D_SUBMODULE_DECLARE(netdev),
-	D_SUBMODULE_DECLARE(rfkill),
-	D_SUBMODULE_DECLARE(rx),
-	D_SUBMODULE_DECLARE(sysfs),
-	D_SUBMODULE_DECLARE(tx),
-};
-
-
-#endif /* #ifndef __debug_levels__h__ */
diff --git a/drivers/net/wimax/i2400m/debugfs.c b/drivers/net/wimax/i2400m/debugfs.c
deleted file mode 100644
index 1c640b41ea4c..000000000000
--- a/drivers/net/wimax/i2400m/debugfs.c
+++ /dev/null
@@ -1,253 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel Wireless WiMAX Connection 2400m
- * Debugfs interfaces to manipulate driver and device information
- *
- * Copyright (C) 2007 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- */
-
-#include <linux/debugfs.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/spinlock.h>
-#include <linux/device.h>
-#include <linux/export.h>
-#include "i2400m.h"
-
-
-#define D_SUBMODULE debugfs
-#include "debug-levels.h"
-
-static
-int debugfs_netdev_queue_stopped_get(void *data, u64 *val)
-{
-	struct i2400m *i2400m = data;
-	*val = netif_queue_stopped(i2400m->wimax_dev.net_dev);
-	return 0;
-}
-DEFINE_DEBUGFS_ATTRIBUTE(fops_netdev_queue_stopped,
-			debugfs_netdev_queue_stopped_get,
-			NULL, "%llu\n");
-
-/*
- * We don't allow partial reads of this file, as then the reader would
- * get weirdly confused data as it is updated.
- *
- * So or you read it all or nothing; if you try to read with an offset
- * != 0, we consider you are done reading.
- */
-static
-ssize_t i2400m_rx_stats_read(struct file *filp, char __user *buffer,
-			     size_t count, loff_t *ppos)
-{
-	struct i2400m *i2400m = filp->private_data;
-	char buf[128];
-	unsigned long flags;
-
-	if (*ppos != 0)
-		return 0;
-	if (count < sizeof(buf))
-		return -ENOSPC;
-	spin_lock_irqsave(&i2400m->rx_lock, flags);
-	snprintf(buf, sizeof(buf), "%u %u %u %u %u %u %u\n",
-		 i2400m->rx_pl_num, i2400m->rx_pl_min,
-		 i2400m->rx_pl_max, i2400m->rx_num,
-		 i2400m->rx_size_acc,
-		 i2400m->rx_size_min, i2400m->rx_size_max);
-	spin_unlock_irqrestore(&i2400m->rx_lock, flags);
-	return simple_read_from_buffer(buffer, count, ppos, buf, strlen(buf));
-}
-
-
-/* Any write clears the stats */
-static
-ssize_t i2400m_rx_stats_write(struct file *filp, const char __user *buffer,
-			      size_t count, loff_t *ppos)
-{
-	struct i2400m *i2400m = filp->private_data;
-	unsigned long flags;
-
-	spin_lock_irqsave(&i2400m->rx_lock, flags);
-	i2400m->rx_pl_num = 0;
-	i2400m->rx_pl_max = 0;
-	i2400m->rx_pl_min = UINT_MAX;
-	i2400m->rx_num = 0;
-	i2400m->rx_size_acc = 0;
-	i2400m->rx_size_min = UINT_MAX;
-	i2400m->rx_size_max = 0;
-	spin_unlock_irqrestore(&i2400m->rx_lock, flags);
-	return count;
-}
-
-static
-const struct file_operations i2400m_rx_stats_fops = {
-	.owner =	THIS_MODULE,
-	.open =		simple_open,
-	.read =		i2400m_rx_stats_read,
-	.write =	i2400m_rx_stats_write,
-	.llseek =	default_llseek,
-};
-
-
-/* See i2400m_rx_stats_read() */
-static
-ssize_t i2400m_tx_stats_read(struct file *filp, char __user *buffer,
-			     size_t count, loff_t *ppos)
-{
-	struct i2400m *i2400m = filp->private_data;
-	char buf[128];
-	unsigned long flags;
-
-	if (*ppos != 0)
-		return 0;
-	if (count < sizeof(buf))
-		return -ENOSPC;
-	spin_lock_irqsave(&i2400m->tx_lock, flags);
-	snprintf(buf, sizeof(buf), "%u %u %u %u %u %u %u\n",
-		 i2400m->tx_pl_num, i2400m->tx_pl_min,
-		 i2400m->tx_pl_max, i2400m->tx_num,
-		 i2400m->tx_size_acc,
-		 i2400m->tx_size_min, i2400m->tx_size_max);
-	spin_unlock_irqrestore(&i2400m->tx_lock, flags);
-	return simple_read_from_buffer(buffer, count, ppos, buf, strlen(buf));
-}
-
-/* Any write clears the stats */
-static
-ssize_t i2400m_tx_stats_write(struct file *filp, const char __user *buffer,
-			      size_t count, loff_t *ppos)
-{
-	struct i2400m *i2400m = filp->private_data;
-	unsigned long flags;
-
-	spin_lock_irqsave(&i2400m->tx_lock, flags);
-	i2400m->tx_pl_num = 0;
-	i2400m->tx_pl_max = 0;
-	i2400m->tx_pl_min = UINT_MAX;
-	i2400m->tx_num = 0;
-	i2400m->tx_size_acc = 0;
-	i2400m->tx_size_min = UINT_MAX;
-	i2400m->tx_size_max = 0;
-	spin_unlock_irqrestore(&i2400m->tx_lock, flags);
-	return count;
-}
-
-static
-const struct file_operations i2400m_tx_stats_fops = {
-	.owner =	THIS_MODULE,
-	.open =		simple_open,
-	.read =		i2400m_tx_stats_read,
-	.write =	i2400m_tx_stats_write,
-	.llseek =	default_llseek,
-};
-
-
-/* Write 1 to ask the device to go into suspend */
-static
-int debugfs_i2400m_suspend_set(void *data, u64 val)
-{
-	int result;
-	struct i2400m *i2400m = data;
-	result = i2400m_cmd_enter_powersave(i2400m);
-	if (result >= 0)
-		result = 0;
-	return result;
-}
-DEFINE_DEBUGFS_ATTRIBUTE(fops_i2400m_suspend,
-			NULL, debugfs_i2400m_suspend_set,
-			"%llu\n");
-
-/*
- * Reset the device
- *
- * Write 0 to ask the device to soft reset, 1 to cold reset, 2 to bus
- * reset (as defined by enum i2400m_reset_type).
- */
-static
-int debugfs_i2400m_reset_set(void *data, u64 val)
-{
-	int result;
-	struct i2400m *i2400m = data;
-	enum i2400m_reset_type rt = val;
-	switch(rt) {
-	case I2400M_RT_WARM:
-	case I2400M_RT_COLD:
-	case I2400M_RT_BUS:
-		result = i2400m_reset(i2400m, rt);
-		if (result >= 0)
-			result = 0;
-		break;
-	default:
-		result = -EINVAL;
-	}
-	return result;
-}
-DEFINE_DEBUGFS_ATTRIBUTE(fops_i2400m_reset,
-			NULL, debugfs_i2400m_reset_set,
-			"%llu\n");
-
-void i2400m_debugfs_add(struct i2400m *i2400m)
-{
-	struct dentry *dentry = i2400m->wimax_dev.debugfs_dentry;
-
-	dentry = debugfs_create_dir("i2400m", dentry);
-	i2400m->debugfs_dentry = dentry;
-
-	d_level_register_debugfs("dl_", control, dentry);
-	d_level_register_debugfs("dl_", driver, dentry);
-	d_level_register_debugfs("dl_", debugfs, dentry);
-	d_level_register_debugfs("dl_", fw, dentry);
-	d_level_register_debugfs("dl_", netdev, dentry);
-	d_level_register_debugfs("dl_", rfkill, dentry);
-	d_level_register_debugfs("dl_", rx, dentry);
-	d_level_register_debugfs("dl_", tx, dentry);
-
-	debugfs_create_size_t("tx_in", 0400, dentry, &i2400m->tx_in);
-	debugfs_create_size_t("tx_out", 0400, dentry, &i2400m->tx_out);
-	debugfs_create_u32("state", 0600, dentry, &i2400m->state);
-
-	/*
-	 * Trace received messages from user space
-	 *
-	 * In order to tap the bidirectional message stream in the
-	 * 'msg' pipe, user space can read from the 'msg' pipe;
-	 * however, due to limitations in libnl, we can't know what
-	 * the different applications are sending down to the kernel.
-	 *
-	 * So we have this hack where the driver will echo any message
-	 * received on the msg pipe from user space [through a call to
-	 * wimax_dev->op_msg_from_user() into
-	 * i2400m_op_msg_from_user()] into the 'trace' pipe that this
-	 * driver creates.
-	 *
-	 * So then, reading from both the 'trace' and 'msg' pipes in
-	 * user space will provide a full dump of the traffic.
-	 *
-	 * Write 1 to activate, 0 to clear.
-	 *
-	 * It is not really very atomic, but it is also not too
-	 * critical.
-	 */
-	debugfs_create_u8("trace_msg_from_user", 0600, dentry,
-			  &i2400m->trace_msg_from_user);
-
-	debugfs_create_file("netdev_queue_stopped", 0400, dentry, i2400m,
-			    &fops_netdev_queue_stopped);
-
-	debugfs_create_file("rx_stats", 0600, dentry, i2400m,
-			    &i2400m_rx_stats_fops);
-
-	debugfs_create_file("tx_stats", 0600, dentry, i2400m,
-			    &i2400m_tx_stats_fops);
-
-	debugfs_create_file("suspend", 0200, dentry, i2400m,
-			    &fops_i2400m_suspend);
-
-	debugfs_create_file("reset", 0200, dentry, i2400m, &fops_i2400m_reset);
-}
-
-void i2400m_debugfs_rm(struct i2400m *i2400m)
-{
-	debugfs_remove_recursive(i2400m->debugfs_dentry);
-}
diff --git a/drivers/net/wimax/i2400m/driver.c b/drivers/net/wimax/i2400m/driver.c
deleted file mode 100644
index ecb3fccca603..000000000000
--- a/drivers/net/wimax/i2400m/driver.c
+++ /dev/null
@@ -1,1002 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel Wireless WiMAX Connection 2400m
- * Generic probe/disconnect, reset and message passing
- *
- * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * See i2400m.h for driver documentation. This contains helpers for
- * the driver model glue [_setup()/_release()], handling device resets
- * [_dev_reset_handle()], and the backends for the WiMAX stack ops
- * reset [_op_reset()] and message from user [_op_msg_from_user()].
- *
- * ROADMAP:
- *
- * i2400m_op_msg_from_user()
- *   i2400m_msg_to_dev()
- *   wimax_msg_to_user_send()
- *
- * i2400m_op_reset()
- *   i240m->bus_reset()
- *
- * i2400m_dev_reset_handle()
- *   __i2400m_dev_reset_handle()
- *     __i2400m_dev_stop()
- *     __i2400m_dev_start()
- *
- * i2400m_setup()
- *   i2400m->bus_setup()
- *   i2400m_bootrom_init()
- *   register_netdev()
- *   wimax_dev_add()
- *   i2400m_dev_start()
- *     __i2400m_dev_start()
- *       i2400m_dev_bootstrap()
- *       i2400m_tx_setup()
- *       i2400m->bus_dev_start()
- *       i2400m_firmware_check()
- *       i2400m_check_mac_addr()
- *
- * i2400m_release()
- *   i2400m_dev_stop()
- *     __i2400m_dev_stop()
- *       i2400m_dev_shutdown()
- *       i2400m->bus_dev_stop()
- *       i2400m_tx_release()
- *   i2400m->bus_release()
- *   wimax_dev_rm()
- *   unregister_netdev()
- */
-#include "i2400m.h"
-#include <linux/etherdevice.h>
-#include <linux/wimax/i2400m.h>
-#include <linux/module.h>
-#include <linux/moduleparam.h>
-#include <linux/suspend.h>
-#include <linux/slab.h>
-
-#define D_SUBMODULE driver
-#include "debug-levels.h"
-
-
-static char i2400m_debug_params[128];
-module_param_string(debug, i2400m_debug_params, sizeof(i2400m_debug_params),
-		    0644);
-MODULE_PARM_DESC(debug,
-		 "String of space-separated NAME:VALUE pairs, where NAMEs "
-		 "are the different debug submodules and VALUE are the "
-		 "initial debug value to set.");
-
-static char i2400m_barkers_params[128];
-module_param_string(barkers, i2400m_barkers_params,
-		    sizeof(i2400m_barkers_params), 0644);
-MODULE_PARM_DESC(barkers,
-		 "String of comma-separated 32-bit values; each is "
-		 "recognized as the value the device sends as a reboot "
-		 "signal; values are appended to a list--setting one value "
-		 "as zero cleans the existing list and starts a new one.");
-
-/*
- * WiMAX stack operation: relay a message from user space
- *
- * @wimax_dev: device descriptor
- * @pipe_name: named pipe the message is for
- * @msg_buf: pointer to the message bytes
- * @msg_len: length of the buffer
- * @genl_info: passed by the generic netlink layer
- *
- * The WiMAX stack will call this function when a message was received
- * from user space.
- *
- * For the i2400m, this is an L3L4 message, as specified in
- * include/linux/wimax/i2400m.h, and thus prefixed with a 'struct
- * i2400m_l3l4_hdr'. Driver (and device) expect the messages to be
- * coded in Little Endian.
- *
- * This function just verifies that the header declaration and the
- * payload are consistent and then deals with it, either forwarding it
- * to the device or procesing it locally.
- *
- * In the i2400m, messages are basically commands that will carry an
- * ack, so we use i2400m_msg_to_dev() and then deliver the ack back to
- * user space. The rx.c code might intercept the response and use it
- * to update the driver's state, but then it will pass it on so it can
- * be relayed back to user space.
- *
- * Note that asynchronous events from the device are processed and
- * sent to user space in rx.c.
- */
-static
-int i2400m_op_msg_from_user(struct wimax_dev *wimax_dev,
-			    const char *pipe_name,
-			    const void *msg_buf, size_t msg_len,
-			    const struct genl_info *genl_info)
-{
-	int result;
-	struct i2400m *i2400m = wimax_dev_to_i2400m(wimax_dev);
-	struct device *dev = i2400m_dev(i2400m);
-	struct sk_buff *ack_skb;
-
-	d_fnstart(4, dev, "(wimax_dev %p [i2400m %p] msg_buf %p "
-		  "msg_len %zu genl_info %p)\n", wimax_dev, i2400m,
-		  msg_buf, msg_len, genl_info);
-	ack_skb = i2400m_msg_to_dev(i2400m, msg_buf, msg_len);
-	result = PTR_ERR(ack_skb);
-	if (IS_ERR(ack_skb))
-		goto error_msg_to_dev;
-	result = wimax_msg_send(&i2400m->wimax_dev, ack_skb);
-error_msg_to_dev:
-	d_fnend(4, dev, "(wimax_dev %p [i2400m %p] msg_buf %p msg_len %zu "
-		"genl_info %p) = %d\n", wimax_dev, i2400m, msg_buf, msg_len,
-		genl_info, result);
-	return result;
-}
-
-
-/*
- * Context to wait for a reset to finalize
- */
-struct i2400m_reset_ctx {
-	struct completion completion;
-	int result;
-};
-
-
-/*
- * WiMAX stack operation: reset a device
- *
- * @wimax_dev: device descriptor
- *
- * See the documentation for wimax_reset() and wimax_dev->op_reset for
- * the requirements of this function. The WiMAX stack guarantees
- * serialization on calls to this function.
- *
- * Do a warm reset on the device; if it fails, resort to a cold reset
- * and return -ENODEV. On successful warm reset, we need to block
- * until it is complete.
- *
- * The bus-driver implementation of reset takes care of falling back
- * to cold reset if warm fails.
- */
-static
-int i2400m_op_reset(struct wimax_dev *wimax_dev)
-{
-	int result;
-	struct i2400m *i2400m = wimax_dev_to_i2400m(wimax_dev);
-	struct device *dev = i2400m_dev(i2400m);
-	struct i2400m_reset_ctx ctx = {
-		.completion = COMPLETION_INITIALIZER_ONSTACK(ctx.completion),
-		.result = 0,
-	};
-
-	d_fnstart(4, dev, "(wimax_dev %p)\n", wimax_dev);
-	mutex_lock(&i2400m->init_mutex);
-	i2400m->reset_ctx = &ctx;
-	mutex_unlock(&i2400m->init_mutex);
-	result = i2400m_reset(i2400m, I2400M_RT_WARM);
-	if (result < 0)
-		goto out;
-	result = wait_for_completion_timeout(&ctx.completion, 4*HZ);
-	if (result == 0)
-		result = -ETIMEDOUT;
-	else if (result > 0)
-		result = ctx.result;
-	/* if result < 0, pass it on */
-	mutex_lock(&i2400m->init_mutex);
-	i2400m->reset_ctx = NULL;
-	mutex_unlock(&i2400m->init_mutex);
-out:
-	d_fnend(4, dev, "(wimax_dev %p) = %d\n", wimax_dev, result);
-	return result;
-}
-
-
-/*
- * Check the MAC address we got from boot mode is ok
- *
- * @i2400m: device descriptor
- *
- * Returns: 0 if ok, < 0 errno code on error.
- */
-static
-int i2400m_check_mac_addr(struct i2400m *i2400m)
-{
-	int result;
-	struct device *dev = i2400m_dev(i2400m);
-	struct sk_buff *skb;
-	const struct i2400m_tlv_detailed_device_info *ddi;
-	struct net_device *net_dev = i2400m->wimax_dev.net_dev;
-
-	d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
-	skb = i2400m_get_device_info(i2400m);
-	if (IS_ERR(skb)) {
-		result = PTR_ERR(skb);
-		dev_err(dev, "Cannot verify MAC address, error reading: %d\n",
-			result);
-		goto error;
-	}
-	/* Extract MAC address */
-	ddi = (void *) skb->data;
-	BUILD_BUG_ON(ETH_ALEN != sizeof(ddi->mac_address));
-	d_printf(2, dev, "GET DEVICE INFO: mac addr %pM\n",
-		 ddi->mac_address);
-	if (!memcmp(net_dev->perm_addr, ddi->mac_address,
-		   sizeof(ddi->mac_address)))
-		goto ok;
-	dev_warn(dev, "warning: device reports a different MAC address "
-		 "to that of boot mode's\n");
-	dev_warn(dev, "device reports     %pM\n", ddi->mac_address);
-	dev_warn(dev, "boot mode reported %pM\n", net_dev->perm_addr);
-	if (is_zero_ether_addr(ddi->mac_address))
-		dev_err(dev, "device reports an invalid MAC address, "
-			"not updating\n");
-	else {
-		dev_warn(dev, "updating MAC address\n");
-		net_dev->addr_len = ETH_ALEN;
-		memcpy(net_dev->perm_addr, ddi->mac_address, ETH_ALEN);
-		memcpy(net_dev->dev_addr, ddi->mac_address, ETH_ALEN);
-	}
-ok:
-	result = 0;
-	kfree_skb(skb);
-error:
-	d_fnend(3, dev, "(i2400m %p) = %d\n", i2400m, result);
-	return result;
-}
-
-
-/**
- * __i2400m_dev_start - Bring up driver communication with the device
- *
- * @i2400m: device descriptor
- * @flags: boot mode flags
- *
- * Returns: 0 if ok, < 0 errno code on error.
- *
- * Uploads firmware and brings up all the resources needed to be able
- * to communicate with the device.
- *
- * The workqueue has to be setup early, at least before RX handling
- * (it's only real user for now) so it can process reports as they
- * arrive. We also want to destroy it if we retry, to make sure it is
- * flushed...easier like this.
- *
- * TX needs to be setup before the bus-specific code (otherwise on
- * shutdown, the bus-tx code could try to access it).
- */
-static
-int __i2400m_dev_start(struct i2400m *i2400m, enum i2400m_bri flags)
-{
-	int result;
-	struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
-	struct net_device *net_dev = wimax_dev->net_dev;
-	struct device *dev = i2400m_dev(i2400m);
-	int times = i2400m->bus_bm_retries;
-
-	d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
-retry:
-	result = i2400m_dev_bootstrap(i2400m, flags);
-	if (result < 0) {
-		dev_err(dev, "cannot bootstrap device: %d\n", result);
-		goto error_bootstrap;
-	}
-	result = i2400m_tx_setup(i2400m);
-	if (result < 0)
-		goto error_tx_setup;
-	result = i2400m_rx_setup(i2400m);
-	if (result < 0)
-		goto error_rx_setup;
-	i2400m->work_queue = create_singlethread_workqueue(wimax_dev->name);
-	if (i2400m->work_queue == NULL) {
-		result = -ENOMEM;
-		dev_err(dev, "cannot create workqueue\n");
-		goto error_create_workqueue;
-	}
-	if (i2400m->bus_dev_start) {
-		result = i2400m->bus_dev_start(i2400m);
-		if (result < 0)
-			goto error_bus_dev_start;
-	}
-	i2400m->ready = 1;
-	wmb();		/* see i2400m->ready's documentation  */
-	/* process pending reports from the device */
-	queue_work(i2400m->work_queue, &i2400m->rx_report_ws);
-	result = i2400m_firmware_check(i2400m);	/* fw versions ok? */
-	if (result < 0)
-		goto error_fw_check;
-	/* At this point is ok to send commands to the device */
-	result = i2400m_check_mac_addr(i2400m);
-	if (result < 0)
-		goto error_check_mac_addr;
-	result = i2400m_dev_initialize(i2400m);
-	if (result < 0)
-		goto error_dev_initialize;
-
-	/* We don't want any additional unwanted error recovery triggered
-	 * from any other context so if anything went wrong before we come
-	 * here, let's keep i2400m->error_recovery untouched and leave it to
-	 * dev_reset_handle(). See dev_reset_handle(). */
-
-	atomic_dec(&i2400m->error_recovery);
-	/* Every thing works so far, ok, now we are ready to
-	 * take error recovery if it's required. */
-
-	/* At this point, reports will come for the device and set it
-	 * to the right state if it is different than UNINITIALIZED */
-	d_fnend(3, dev, "(net_dev %p [i2400m %p]) = %d\n",
-		net_dev, i2400m, result);
-	return result;
-
-error_dev_initialize:
-error_check_mac_addr:
-error_fw_check:
-	i2400m->ready = 0;
-	wmb();		/* see i2400m->ready's documentation  */
-	flush_workqueue(i2400m->work_queue);
-	if (i2400m->bus_dev_stop)
-		i2400m->bus_dev_stop(i2400m);
-error_bus_dev_start:
-	destroy_workqueue(i2400m->work_queue);
-error_create_workqueue:
-	i2400m_rx_release(i2400m);
-error_rx_setup:
-	i2400m_tx_release(i2400m);
-error_tx_setup:
-error_bootstrap:
-	if (result == -EL3RST && times-- > 0) {
-		flags = I2400M_BRI_SOFT|I2400M_BRI_MAC_REINIT;
-		goto retry;
-	}
-	d_fnend(3, dev, "(net_dev %p [i2400m %p]) = %d\n",
-		net_dev, i2400m, result);
-	return result;
-}
-
-
-static
-int i2400m_dev_start(struct i2400m *i2400m, enum i2400m_bri bm_flags)
-{
-	int result = 0;
-	mutex_lock(&i2400m->init_mutex);	/* Well, start the device */
-	if (i2400m->updown == 0) {
-		result = __i2400m_dev_start(i2400m, bm_flags);
-		if (result >= 0) {
-			i2400m->updown = 1;
-			i2400m->alive = 1;
-			wmb();/* see i2400m->updown and i2400m->alive's doc */
-		}
-	}
-	mutex_unlock(&i2400m->init_mutex);
-	return result;
-}
-
-
-/**
- * i2400m_dev_stop - Tear down driver communication with the device
- *
- * @i2400m: device descriptor
- *
- * Returns: 0 if ok, < 0 errno code on error.
- *
- * Releases all the resources allocated to communicate with the
- * device. Note we cannot destroy the workqueue earlier as until RX is
- * fully destroyed, it could still try to schedule jobs.
- */
-static
-void __i2400m_dev_stop(struct i2400m *i2400m)
-{
-	struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
-	struct device *dev = i2400m_dev(i2400m);
-
-	d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
-	wimax_state_change(wimax_dev, __WIMAX_ST_QUIESCING);
-	i2400m_msg_to_dev_cancel_wait(i2400m, -EL3RST);
-	complete(&i2400m->msg_completion);
-	i2400m_net_wake_stop(i2400m);
-	i2400m_dev_shutdown(i2400m);
-	/*
-	 * Make sure no report hooks are running *before* we stop the
-	 * communication infrastructure with the device.
-	 */
-	i2400m->ready = 0;	/* nobody can queue work anymore */
-	wmb();		/* see i2400m->ready's documentation  */
-	flush_workqueue(i2400m->work_queue);
-
-	if (i2400m->bus_dev_stop)
-		i2400m->bus_dev_stop(i2400m);
-	destroy_workqueue(i2400m->work_queue);
-	i2400m_rx_release(i2400m);
-	i2400m_tx_release(i2400m);
-	wimax_state_change(wimax_dev, WIMAX_ST_DOWN);
-	d_fnend(3, dev, "(i2400m %p) = 0\n", i2400m);
-}
-
-
-/*
- * Watch out -- we only need to stop if there is a need for it. The
- * device could have reset itself and failed to come up again (see
- * _i2400m_dev_reset_handle()).
- */
-static
-void i2400m_dev_stop(struct i2400m *i2400m)
-{
-	mutex_lock(&i2400m->init_mutex);
-	if (i2400m->updown) {
-		__i2400m_dev_stop(i2400m);
-		i2400m->updown = 0;
-		i2400m->alive = 0;
-		wmb();	/* see i2400m->updown and i2400m->alive's doc */
-	}
-	mutex_unlock(&i2400m->init_mutex);
-}
-
-
-/*
- * Listen to PM events to cache the firmware before suspend/hibernation
- *
- * When the device comes out of suspend, it might go into reset and
- * firmware has to be uploaded again. At resume, most of the times, we
- * can't load firmware images from disk, so we need to cache it.
- *
- * i2400m_fw_cache() will allocate a kobject and attach the firmware
- * to it; that way we don't have to worry too much about the fw loader
- * hitting a race condition.
- *
- * Note: modus operandi stolen from the Orinoco driver; thx.
- */
-static
-int i2400m_pm_notifier(struct notifier_block *notifier,
-		       unsigned long pm_event,
-		       void *unused)
-{
-	struct i2400m *i2400m =
-		container_of(notifier, struct i2400m, pm_notifier);
-	struct device *dev = i2400m_dev(i2400m);
-
-	d_fnstart(3, dev, "(i2400m %p pm_event %lx)\n", i2400m, pm_event);
-	switch (pm_event) {
-	case PM_HIBERNATION_PREPARE:
-	case PM_SUSPEND_PREPARE:
-		i2400m_fw_cache(i2400m);
-		break;
-	case PM_POST_RESTORE:
-		/* Restore from hibernation failed. We need to clean
-		 * up in exactly the same way, so fall through. */
-	case PM_POST_HIBERNATION:
-	case PM_POST_SUSPEND:
-		i2400m_fw_uncache(i2400m);
-		break;
-
-	case PM_RESTORE_PREPARE:
-	default:
-		break;
-	}
-	d_fnend(3, dev, "(i2400m %p pm_event %lx) = void\n", i2400m, pm_event);
-	return NOTIFY_DONE;
-}
-
-
-/*
- * pre-reset is called before a device is going on reset
- *
- * This has to be followed by a call to i2400m_post_reset(), otherwise
- * bad things might happen.
- */
-int i2400m_pre_reset(struct i2400m *i2400m)
-{
-	struct device *dev = i2400m_dev(i2400m);
-
-	d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
-	d_printf(1, dev, "pre-reset shut down\n");
-
-	mutex_lock(&i2400m->init_mutex);
-	if (i2400m->updown) {
-		netif_tx_disable(i2400m->wimax_dev.net_dev);
-		__i2400m_dev_stop(i2400m);
-		/* down't set updown to zero -- this way
-		 * post_reset can restore properly */
-	}
-	mutex_unlock(&i2400m->init_mutex);
-	if (i2400m->bus_release)
-		i2400m->bus_release(i2400m);
-	d_fnend(3, dev, "(i2400m %p) = 0\n", i2400m);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(i2400m_pre_reset);
-
-
-/*
- * Restore device state after a reset
- *
- * Do the work needed after a device reset to bring it up to the same
- * state as it was before the reset.
- *
- * NOTE: this requires i2400m->init_mutex taken
- */
-int i2400m_post_reset(struct i2400m *i2400m)
-{
-	int result = 0;
-	struct device *dev = i2400m_dev(i2400m);
-
-	d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
-	d_printf(1, dev, "post-reset start\n");
-	if (i2400m->bus_setup) {
-		result = i2400m->bus_setup(i2400m);
-		if (result < 0) {
-			dev_err(dev, "bus-specific setup failed: %d\n",
-				result);
-			goto error_bus_setup;
-		}
-	}
-	mutex_lock(&i2400m->init_mutex);
-	if (i2400m->updown) {
-		result = __i2400m_dev_start(
-			i2400m, I2400M_BRI_SOFT | I2400M_BRI_MAC_REINIT);
-		if (result < 0)
-			goto error_dev_start;
-	}
-	mutex_unlock(&i2400m->init_mutex);
-	d_fnend(3, dev, "(i2400m %p) = %d\n", i2400m, result);
-	return result;
-
-error_dev_start:
-	if (i2400m->bus_release)
-		i2400m->bus_release(i2400m);
-	/* even if the device was up, it could not be recovered, so we
-	 * mark it as down. */
-	i2400m->updown = 0;
-	wmb();		/* see i2400m->updown's documentation  */
-	mutex_unlock(&i2400m->init_mutex);
-error_bus_setup:
-	d_fnend(3, dev, "(i2400m %p) = %d\n", i2400m, result);
-	return result;
-}
-EXPORT_SYMBOL_GPL(i2400m_post_reset);
-
-
-/*
- * The device has rebooted; fix up the device and the driver
- *
- * Tear down the driver communication with the device, reload the
- * firmware and reinitialize the communication with the device.
- *
- * If someone calls a reset when the device's firmware is down, in
- * theory we won't see it because we are not listening. However, just
- * in case, leave the code to handle it.
- *
- * If there is a reset context, use it; this means someone is waiting
- * for us to tell him when the reset operation is complete and the
- * device is ready to rock again.
- *
- * NOTE: if we are in the process of bringing up or down the
- *       communication with the device [running i2400m_dev_start() or
- *       _stop()], don't do anything, let it fail and handle it.
- *
- * This function is ran always in a thread context
- *
- * This function gets passed, as payload to i2400m_work() a 'const
- * char *' ptr with a "reason" why the reset happened (for messages).
- */
-static
-void __i2400m_dev_reset_handle(struct work_struct *ws)
-{
-	struct i2400m *i2400m = container_of(ws, struct i2400m, reset_ws);
-	const char *reason = i2400m->reset_reason;
-	struct device *dev = i2400m_dev(i2400m);
-	struct i2400m_reset_ctx *ctx = i2400m->reset_ctx;
-	int result;
-
-	d_fnstart(3, dev, "(ws %p i2400m %p reason %s)\n", ws, i2400m, reason);
-
-	i2400m->boot_mode = 1;
-	wmb();		/* Make sure i2400m_msg_to_dev() sees boot_mode */
-
-	result = 0;
-	if (mutex_trylock(&i2400m->init_mutex) == 0) {
-		/* We are still in i2400m_dev_start() [let it fail] or
-		 * i2400m_dev_stop() [we are shutting down anyway, so
-		 * ignore it] or we are resetting somewhere else. */
-		dev_err(dev, "device rebooted somewhere else?\n");
-		i2400m_msg_to_dev_cancel_wait(i2400m, -EL3RST);
-		complete(&i2400m->msg_completion);
-		goto out;
-	}
-
-	dev_err(dev, "%s: reinitializing driver\n", reason);
-	rmb();
-	if (i2400m->updown) {
-		__i2400m_dev_stop(i2400m);
-		i2400m->updown = 0;
-		wmb();		/* see i2400m->updown's documentation  */
-	}
-
-	if (i2400m->alive) {
-		result = __i2400m_dev_start(i2400m,
-				    I2400M_BRI_SOFT | I2400M_BRI_MAC_REINIT);
-		if (result < 0) {
-			dev_err(dev, "%s: cannot start the device: %d\n",
-				reason, result);
-			result = -EUCLEAN;
-			if (atomic_read(&i2400m->bus_reset_retries)
-					>= I2400M_BUS_RESET_RETRIES) {
-				result = -ENODEV;
-				dev_err(dev, "tried too many times to "
-					"reset the device, giving up\n");
-			}
-		}
-	}
-
-	if (i2400m->reset_ctx) {
-		ctx->result = result;
-		complete(&ctx->completion);
-	}
-	mutex_unlock(&i2400m->init_mutex);
-	if (result == -EUCLEAN) {
-		/*
-		 * We come here because the reset during operational mode
-		 * wasn't successfully done and need to proceed to a bus
-		 * reset. For the dev_reset_handle() to be able to handle
-		 * the reset event later properly, we restore boot_mode back
-		 * to the state before previous reset. ie: just like we are
-		 * issuing the bus reset for the first time
-		 */
-		i2400m->boot_mode = 0;
-		wmb();
-
-		atomic_inc(&i2400m->bus_reset_retries);
-		/* ops, need to clean up [w/ init_mutex not held] */
-		result = i2400m_reset(i2400m, I2400M_RT_BUS);
-		if (result >= 0)
-			result = -ENODEV;
-	} else {
-		rmb();
-		if (i2400m->alive) {
-			/* great, we expect the device state up and
-			 * dev_start() actually brings the device state up */
-			i2400m->updown = 1;
-			wmb();
-			atomic_set(&i2400m->bus_reset_retries, 0);
-		}
-	}
-out:
-	d_fnend(3, dev, "(ws %p i2400m %p reason %s) = void\n",
-		ws, i2400m, reason);
-}
-
-
-/**
- * i2400m_dev_reset_handle - Handle a device's reset in a thread context
- *
- * Schedule a device reset handling out on a thread context, so it
- * is safe to call from atomic context. We can't use the i2400m's
- * queue as we are going to destroy it and reinitialize it as part of
- * the driver bringup/bringup process.
- *
- * See __i2400m_dev_reset_handle() for details; that takes care of
- * reinitializing the driver to handle the reset, calling into the
- * bus-specific functions ops as needed.
- */
-int i2400m_dev_reset_handle(struct i2400m *i2400m, const char *reason)
-{
-	i2400m->reset_reason = reason;
-	return schedule_work(&i2400m->reset_ws);
-}
-EXPORT_SYMBOL_GPL(i2400m_dev_reset_handle);
-
-
- /*
- * The actual work of error recovery.
- *
- * The current implementation of error recovery is to trigger a bus reset.
- */
-static
-void __i2400m_error_recovery(struct work_struct *ws)
-{
-	struct i2400m *i2400m = container_of(ws, struct i2400m, recovery_ws);
-
-	i2400m_reset(i2400m, I2400M_RT_BUS);
-}
-
-/*
- * Schedule a work struct for error recovery.
- *
- * The intention of error recovery is to bring back the device to some
- * known state whenever TX sees -110 (-ETIMEOUT) on copying the data to
- * the device. The TX failure could mean a device bus stuck, so the current
- * error recovery implementation is to trigger a bus reset to the device
- * and hopefully it can bring back the device.
- *
- * The actual work of error recovery has to be in a thread context because
- * it is kicked off in the TX thread (i2400ms->tx_workqueue) which is to be
- * destroyed by the error recovery mechanism (currently a bus reset).
- *
- * Also, there may be already a queue of TX works that all hit
- * the -ETIMEOUT error condition because the device is stuck already.
- * Since bus reset is used as the error recovery mechanism and we don't
- * want consecutive bus resets simply because the multiple TX works
- * in the queue all hit the same device erratum, the flag "error_recovery"
- * is introduced for preventing unwanted consecutive bus resets.
- *
- * Error recovery shall only be invoked again if previous one was completed.
- * The flag error_recovery is set when error recovery mechanism is scheduled,
- * and is checked when we need to schedule another error recovery. If it is
- * in place already, then we shouldn't schedule another one.
- */
-void i2400m_error_recovery(struct i2400m *i2400m)
-{
-	if (atomic_add_return(1, &i2400m->error_recovery) == 1)
-		schedule_work(&i2400m->recovery_ws);
-	else
-		atomic_dec(&i2400m->error_recovery);
-}
-EXPORT_SYMBOL_GPL(i2400m_error_recovery);
-
-/*
- * Alloc the command and ack buffers for boot mode
- *
- * Get the buffers needed to deal with boot mode messages.
- */
-static
-int i2400m_bm_buf_alloc(struct i2400m *i2400m)
-{
-	i2400m->bm_cmd_buf = kzalloc(I2400M_BM_CMD_BUF_SIZE, GFP_KERNEL);
-	if (i2400m->bm_cmd_buf == NULL)
-		goto error_bm_cmd_kzalloc;
-	i2400m->bm_ack_buf = kzalloc(I2400M_BM_ACK_BUF_SIZE, GFP_KERNEL);
-	if (i2400m->bm_ack_buf == NULL)
-		goto error_bm_ack_buf_kzalloc;
-	return 0;
-
-error_bm_ack_buf_kzalloc:
-	kfree(i2400m->bm_cmd_buf);
-error_bm_cmd_kzalloc:
-	return -ENOMEM;
-}
-
-
-/*
- * Free boot mode command and ack buffers.
- */
-static
-void i2400m_bm_buf_free(struct i2400m *i2400m)
-{
-	kfree(i2400m->bm_ack_buf);
-	kfree(i2400m->bm_cmd_buf);
-}
-
-
-/**
- * i2400m_init - Initialize a 'struct i2400m' from all zeroes
- *
- * This is a bus-generic API call.
- */
-void i2400m_init(struct i2400m *i2400m)
-{
-	wimax_dev_init(&i2400m->wimax_dev);
-
-	i2400m->boot_mode = 1;
-	i2400m->rx_reorder = 1;
-	init_waitqueue_head(&i2400m->state_wq);
-
-	spin_lock_init(&i2400m->tx_lock);
-	i2400m->tx_pl_min = UINT_MAX;
-	i2400m->tx_size_min = UINT_MAX;
-
-	spin_lock_init(&i2400m->rx_lock);
-	i2400m->rx_pl_min = UINT_MAX;
-	i2400m->rx_size_min = UINT_MAX;
-	INIT_LIST_HEAD(&i2400m->rx_reports);
-	INIT_WORK(&i2400m->rx_report_ws, i2400m_report_hook_work);
-
-	mutex_init(&i2400m->msg_mutex);
-	init_completion(&i2400m->msg_completion);
-
-	mutex_init(&i2400m->init_mutex);
-	/* wake_tx_ws is initialized in i2400m_tx_setup() */
-
-	INIT_WORK(&i2400m->reset_ws, __i2400m_dev_reset_handle);
-	INIT_WORK(&i2400m->recovery_ws, __i2400m_error_recovery);
-
-	atomic_set(&i2400m->bus_reset_retries, 0);
-
-	i2400m->alive = 0;
-
-	/* initialize error_recovery to 1 for denoting we
-	 * are not yet ready to take any error recovery */
-	atomic_set(&i2400m->error_recovery, 1);
-}
-EXPORT_SYMBOL_GPL(i2400m_init);
-
-
-int i2400m_reset(struct i2400m *i2400m, enum i2400m_reset_type rt)
-{
-	struct net_device *net_dev = i2400m->wimax_dev.net_dev;
-
-	/*
-	 * Make sure we stop TXs and down the carrier before
-	 * resetting; this is needed to avoid things like
-	 * i2400m_wake_tx() scheduling stuff in parallel.
-	 */
-	if (net_dev->reg_state == NETREG_REGISTERED) {
-		netif_tx_disable(net_dev);
-		netif_carrier_off(net_dev);
-	}
-	return i2400m->bus_reset(i2400m, rt);
-}
-EXPORT_SYMBOL_GPL(i2400m_reset);
-
-
-/**
- * i2400m_setup - bus-generic setup function for the i2400m device
- *
- * @i2400m: device descriptor (bus-specific parts have been initialized)
- *
- * Returns: 0 if ok, < 0 errno code on error.
- *
- * Sets up basic device comunication infrastructure, boots the ROM to
- * read the MAC address, registers with the WiMAX and network stacks
- * and then brings up the device.
- */
-int i2400m_setup(struct i2400m *i2400m, enum i2400m_bri bm_flags)
-{
-	int result;
-	struct device *dev = i2400m_dev(i2400m);
-	struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
-	struct net_device *net_dev = i2400m->wimax_dev.net_dev;
-
-	d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
-
-	snprintf(wimax_dev->name, sizeof(wimax_dev->name),
-		 "i2400m-%s:%s", dev->bus->name, dev_name(dev));
-
-	result = i2400m_bm_buf_alloc(i2400m);
-	if (result < 0) {
-		dev_err(dev, "cannot allocate bootmode scratch buffers\n");
-		goto error_bm_buf_alloc;
-	}
-
-	if (i2400m->bus_setup) {
-		result = i2400m->bus_setup(i2400m);
-		if (result < 0) {
-			dev_err(dev, "bus-specific setup failed: %d\n",
-				result);
-			goto error_bus_setup;
-		}
-	}
-
-	result = i2400m_bootrom_init(i2400m, bm_flags);
-	if (result < 0) {
-		dev_err(dev, "read mac addr: bootrom init "
-			"failed: %d\n", result);
-		goto error_bootrom_init;
-	}
-	result = i2400m_read_mac_addr(i2400m);
-	if (result < 0)
-		goto error_read_mac_addr;
-	eth_random_addr(i2400m->src_mac_addr);
-
-	i2400m->pm_notifier.notifier_call = i2400m_pm_notifier;
-	register_pm_notifier(&i2400m->pm_notifier);
-
-	result = register_netdev(net_dev);	/* Okey dokey, bring it up */
-	if (result < 0) {
-		dev_err(dev, "cannot register i2400m network device: %d\n",
-			result);
-		goto error_register_netdev;
-	}
-	netif_carrier_off(net_dev);
-
-	i2400m->wimax_dev.op_msg_from_user = i2400m_op_msg_from_user;
-	i2400m->wimax_dev.op_rfkill_sw_toggle = i2400m_op_rfkill_sw_toggle;
-	i2400m->wimax_dev.op_reset = i2400m_op_reset;
-
-	result = wimax_dev_add(&i2400m->wimax_dev, net_dev);
-	if (result < 0)
-		goto error_wimax_dev_add;
-
-	/* Now setup all that requires a registered net and wimax device. */
-	result = sysfs_create_group(&net_dev->dev.kobj, &i2400m_dev_attr_group);
-	if (result < 0) {
-		dev_err(dev, "cannot setup i2400m's sysfs: %d\n", result);
-		goto error_sysfs_setup;
-	}
-
-	i2400m_debugfs_add(i2400m);
-
-	result = i2400m_dev_start(i2400m, bm_flags);
-	if (result < 0)
-		goto error_dev_start;
-	d_fnend(3, dev, "(i2400m %p) = %d\n", i2400m, result);
-	return result;
-
-error_dev_start:
-	i2400m_debugfs_rm(i2400m);
-	sysfs_remove_group(&i2400m->wimax_dev.net_dev->dev.kobj,
-			   &i2400m_dev_attr_group);
-error_sysfs_setup:
-	wimax_dev_rm(&i2400m->wimax_dev);
-error_wimax_dev_add:
-	unregister_netdev(net_dev);
-error_register_netdev:
-	unregister_pm_notifier(&i2400m->pm_notifier);
-error_read_mac_addr:
-error_bootrom_init:
-	if (i2400m->bus_release)
-		i2400m->bus_release(i2400m);
-error_bus_setup:
-	i2400m_bm_buf_free(i2400m);
-error_bm_buf_alloc:
-	d_fnend(3, dev, "(i2400m %p) = %d\n", i2400m, result);
-	return result;
-}
-EXPORT_SYMBOL_GPL(i2400m_setup);
-
-
-/**
- * i2400m_release - release the bus-generic driver resources
- *
- * Sends a disconnect message and undoes any setup done by i2400m_setup()
- */
-void i2400m_release(struct i2400m *i2400m)
-{
-	struct device *dev = i2400m_dev(i2400m);
-
-	d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
-	netif_stop_queue(i2400m->wimax_dev.net_dev);
-
-	i2400m_dev_stop(i2400m);
-
-	cancel_work_sync(&i2400m->reset_ws);
-	cancel_work_sync(&i2400m->recovery_ws);
-
-	i2400m_debugfs_rm(i2400m);
-	sysfs_remove_group(&i2400m->wimax_dev.net_dev->dev.kobj,
-			   &i2400m_dev_attr_group);
-	wimax_dev_rm(&i2400m->wimax_dev);
-	unregister_netdev(i2400m->wimax_dev.net_dev);
-	unregister_pm_notifier(&i2400m->pm_notifier);
-	if (i2400m->bus_release)
-		i2400m->bus_release(i2400m);
-	i2400m_bm_buf_free(i2400m);
-	d_fnend(3, dev, "(i2400m %p) = void\n", i2400m);
-}
-EXPORT_SYMBOL_GPL(i2400m_release);
-
-
-/*
- * Debug levels control; see debug.h
- */
-struct d_level D_LEVEL[] = {
-	D_SUBMODULE_DEFINE(control),
-	D_SUBMODULE_DEFINE(driver),
-	D_SUBMODULE_DEFINE(debugfs),
-	D_SUBMODULE_DEFINE(fw),
-	D_SUBMODULE_DEFINE(netdev),
-	D_SUBMODULE_DEFINE(rfkill),
-	D_SUBMODULE_DEFINE(rx),
-	D_SUBMODULE_DEFINE(sysfs),
-	D_SUBMODULE_DEFINE(tx),
-};
-size_t D_LEVEL_SIZE = ARRAY_SIZE(D_LEVEL);
-
-
-static
-int __init i2400m_driver_init(void)
-{
-	d_parse_params(D_LEVEL, D_LEVEL_SIZE, i2400m_debug_params,
-		       "i2400m.debug");
-	return i2400m_barker_db_init(i2400m_barkers_params);
-}
-module_init(i2400m_driver_init);
-
-static
-void __exit i2400m_driver_exit(void)
-{
-	i2400m_barker_db_exit();
-}
-module_exit(i2400m_driver_exit);
-
-MODULE_AUTHOR("Intel Corporation <linux-wimax@intel.com>");
-MODULE_DESCRIPTION("Intel 2400M WiMAX networking bus-generic driver");
-MODULE_LICENSE("GPL");
diff --git a/drivers/net/wimax/i2400m/fw.c b/drivers/net/wimax/i2400m/fw.c
deleted file mode 100644
index 6c9a41bff2e0..000000000000
--- a/drivers/net/wimax/i2400m/fw.c
+++ /dev/null
@@ -1,1653 +0,0 @@
-/*
- * Intel Wireless WiMAX Connection 2400m
- * Firmware uploader
- *
- *
- * Copyright (C) 2007-2008 Intel Corporation. All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- *   * Redistributions of source code must retain the above copyright
- *     notice, this list of conditions and the following disclaimer.
- *   * Redistributions in binary form must reproduce the above copyright
- *     notice, this list of conditions and the following disclaimer in
- *     the documentation and/or other materials provided with the
- *     distribution.
- *   * Neither the name of Intel Corporation nor the names of its
- *     contributors may be used to endorse or promote products derived
- *     from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * Intel Corporation <linux-wimax@intel.com>
- * Yanir Lubetkin <yanirx.lubetkin@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *  - Initial implementation
- *
- *
- * THE PROCEDURE
- *
- * The 2400m and derived devices work in two modes: boot-mode or
- * normal mode. In boot mode we can execute only a handful of commands
- * targeted at uploading the firmware and launching it.
- *
- * The 2400m enters boot mode when it is first connected to the
- * system, when it crashes and when you ask it to reboot. There are
- * two submodes of the boot mode: signed and non-signed. Signed takes
- * firmwares signed with a certain private key, non-signed takes any
- * firmware. Normal hardware takes only signed firmware.
- *
- * On boot mode, in USB, we write to the device using the bulk out
- * endpoint and read from it in the notification endpoint.
- *
- * Upon entrance to boot mode, the device sends (preceded with a few
- * zero length packets (ZLPs) on the notification endpoint in USB) a
- * reboot barker (4 le32 words with the same value). We ack it by
- * sending the same barker to the device. The device acks with a
- * reboot ack barker (4 le32 words with value I2400M_ACK_BARKER) and
- * then is fully booted. At this point we can upload the firmware.
- *
- * Note that different iterations of the device and EEPROM
- * configurations will send different [re]boot barkers; these are
- * collected in i2400m_barker_db along with the firmware
- * characteristics they require.
- *
- * This process is accomplished by the i2400m_bootrom_init()
- * function. All the device interaction happens through the
- * i2400m_bm_cmd() [boot mode command]. Special return values will
- * indicate if the device did reset during the process.
- *
- * After this, we read the MAC address and then (if needed)
- * reinitialize the device. We need to read it ahead of time because
- * in the future, we might not upload the firmware until userspace
- * 'ifconfig up's the device.
- *
- * We can then upload the firmware file. The file is composed of a BCF
- * header (basic data, keys and signatures) and a list of write
- * commands and payloads. Optionally more BCF headers might follow the
- * main payload. We first upload the header [i2400m_dnload_init()] and
- * then pass the commands and payloads verbatim to the i2400m_bm_cmd()
- * function [i2400m_dnload_bcf()]. Then we tell the device to jump to
- * the new firmware [i2400m_dnload_finalize()].
- *
- * Once firmware is uploaded, we are good to go :)
- *
- * When we don't know in which mode we are, we first try by sending a
- * warm reset request that will take us to boot-mode. If we time out
- * waiting for a reboot barker, that means maybe we are already in
- * boot mode, so we send a reboot barker.
- *
- * COMMAND EXECUTION
- *
- * This code (and process) is single threaded; for executing commands,
- * we post a URB to the notification endpoint, post the command, wait
- * for data on the notification buffer. We don't need to worry about
- * others as we know we are the only ones in there.
- *
- * BACKEND IMPLEMENTATION
- *
- * This code is bus-generic; the bus-specific driver provides back end
- * implementations to send a boot mode command to the device and to
- * read an acknolwedgement from it (or an asynchronous notification)
- * from it.
- *
- * FIRMWARE LOADING
- *
- * Note that in some cases, we can't just load a firmware file (for
- * example, when resuming). For that, we might cache the firmware
- * file. Thus, when doing the bootstrap, if there is a cache firmware
- * file, it is used; if not, loading from disk is attempted.
- *
- * ROADMAP
- *
- * i2400m_barker_db_init              Called by i2400m_driver_init()
- *   i2400m_barker_db_add
- *
- * i2400m_barker_db_exit              Called by i2400m_driver_exit()
- *
- * i2400m_dev_bootstrap               Called by __i2400m_dev_start()
- *   request_firmware
- *   i2400m_fw_bootstrap
- *     i2400m_fw_check
- *       i2400m_fw_hdr_check
- *     i2400m_fw_dnload
- *   release_firmware
- *
- * i2400m_fw_dnload
- *   i2400m_bootrom_init
- *     i2400m_bm_cmd
- *     i2400m_reset
- *   i2400m_dnload_init
- *     i2400m_dnload_init_signed
- *     i2400m_dnload_init_nonsigned
- *       i2400m_download_chunk
- *         i2400m_bm_cmd
- *   i2400m_dnload_bcf
- *     i2400m_bm_cmd
- *   i2400m_dnload_finalize
- *     i2400m_bm_cmd
- *
- * i2400m_bm_cmd
- *   i2400m->bus_bm_cmd_send()
- *   i2400m->bus_bm_wait_for_ack
- *   __i2400m_bm_ack_verify
- *     i2400m_is_boot_barker
- *
- * i2400m_bm_cmd_prepare              Used by bus-drivers to prep
- *                                    commands before sending
- *
- * i2400m_pm_notifier                 Called on Power Management events
- *   i2400m_fw_cache
- *   i2400m_fw_uncache
- */
-#include <linux/firmware.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/usb.h>
-#include <linux/export.h>
-#include "i2400m.h"
-
-
-#define D_SUBMODULE fw
-#include "debug-levels.h"
-
-
-static const __le32 i2400m_ACK_BARKER[4] = {
-	cpu_to_le32(I2400M_ACK_BARKER),
-	cpu_to_le32(I2400M_ACK_BARKER),
-	cpu_to_le32(I2400M_ACK_BARKER),
-	cpu_to_le32(I2400M_ACK_BARKER)
-};
-
-
-/**
- * Prepare a boot-mode command for delivery
- *
- * @cmd: pointer to bootrom header to prepare
- *
- * Computes checksum if so needed. After calling this function, DO NOT
- * modify the command or header as the checksum won't work anymore.
- *
- * We do it from here because some times we cannot do it in the
- * original context the command was sent (it is a const), so when we
- * copy it to our staging buffer, we add the checksum there.
- */
-void i2400m_bm_cmd_prepare(struct i2400m_bootrom_header *cmd)
-{
-	if (i2400m_brh_get_use_checksum(cmd)) {
-		int i;
-		u32 checksum = 0;
-		const u32 *checksum_ptr = (void *) cmd->payload;
-		for (i = 0; i < cmd->data_size / 4; i++)
-			checksum += cpu_to_le32(*checksum_ptr++);
-		checksum += cmd->command + cmd->target_addr + cmd->data_size;
-		cmd->block_checksum = cpu_to_le32(checksum);
-	}
-}
-EXPORT_SYMBOL_GPL(i2400m_bm_cmd_prepare);
-
-
-/*
- * Database of known barkers.
- *
- * A barker is what the device sends indicating he is ready to be
- * bootloaded. Different versions of the device will send different
- * barkers. Depending on the barker, it might mean the device wants
- * some kind of firmware or the other.
- */
-static struct i2400m_barker_db {
-	__le32 data[4];
-} *i2400m_barker_db;
-static size_t i2400m_barker_db_used, i2400m_barker_db_size;
-
-
-static
-int i2400m_zrealloc_2x(void **ptr, size_t *_count, size_t el_size,
-		       gfp_t gfp_flags)
-{
-	size_t old_count = *_count,
-		new_count = old_count ? 2 * old_count : 2,
-		old_size = el_size * old_count,
-		new_size = el_size * new_count;
-	void *nptr = krealloc(*ptr, new_size, gfp_flags);
-	if (nptr) {
-		/* zero the other half or the whole thing if old_count
-		 * was zero */
-		if (old_size == 0)
-			memset(nptr, 0, new_size);
-		else
-			memset(nptr + old_size, 0, old_size);
-		*_count = new_count;
-		*ptr = nptr;
-		return 0;
-	} else
-		return -ENOMEM;
-}
-
-
-/*
- * Add a barker to the database
- *
- * This cannot used outside of this module and only at at module_init
- * time. This is to avoid the need to do locking.
- */
-static
-int i2400m_barker_db_add(u32 barker_id)
-{
-	int result;
-
-	struct i2400m_barker_db *barker;
-	if (i2400m_barker_db_used >= i2400m_barker_db_size) {
-		result = i2400m_zrealloc_2x(
-			(void **) &i2400m_barker_db, &i2400m_barker_db_size,
-			sizeof(i2400m_barker_db[0]), GFP_KERNEL);
-		if (result < 0)
-			return result;
-	}
-	barker = i2400m_barker_db + i2400m_barker_db_used++;
-	barker->data[0] = le32_to_cpu(barker_id);
-	barker->data[1] = le32_to_cpu(barker_id);
-	barker->data[2] = le32_to_cpu(barker_id);
-	barker->data[3] = le32_to_cpu(barker_id);
-	return 0;
-}
-
-
-void i2400m_barker_db_exit(void)
-{
-	kfree(i2400m_barker_db);
-	i2400m_barker_db = NULL;
-	i2400m_barker_db_size = 0;
-	i2400m_barker_db_used = 0;
-}
-
-
-/*
- * Helper function to add all the known stable barkers to the barker
- * database.
- */
-static
-int i2400m_barker_db_known_barkers(void)
-{
-	int result;
-
-	result = i2400m_barker_db_add(I2400M_NBOOT_BARKER);
-	if (result < 0)
-		goto error_add;
-	result = i2400m_barker_db_add(I2400M_SBOOT_BARKER);
-	if (result < 0)
-		goto error_add;
-	result = i2400m_barker_db_add(I2400M_SBOOT_BARKER_6050);
-	if (result < 0)
-		goto error_add;
-error_add:
-       return result;
-}
-
-
-/*
- * Initialize the barker database
- *
- * This can only be used from the module_init function for this
- * module; this is to avoid the need to do locking.
- *
- * @options: command line argument with extra barkers to
- *     recognize. This is a comma-separated list of 32-bit hex
- *     numbers. They are appended to the existing list. Setting 0
- *     cleans the existing list and starts a new one.
- */
-int i2400m_barker_db_init(const char *_options)
-{
-	int result;
-	char *options = NULL, *options_orig, *token;
-
-	i2400m_barker_db = NULL;
-	i2400m_barker_db_size = 0;
-	i2400m_barker_db_used = 0;
-
-	result = i2400m_barker_db_known_barkers();
-	if (result < 0)
-		goto error_add;
-	/* parse command line options from i2400m.barkers */
-	if (_options != NULL) {
-		unsigned barker;
-
-		options_orig = kstrdup(_options, GFP_KERNEL);
-		if (options_orig == NULL) {
-			result = -ENOMEM;
-			goto error_parse;
-		}
-		options = options_orig;
-
-		while ((token = strsep(&options, ",")) != NULL) {
-			if (*token == '\0')	/* eat joint commas */
-				continue;
-			if (sscanf(token, "%x", &barker) != 1
-			    || barker > 0xffffffff) {
-				printk(KERN_ERR "%s: can't recognize "
-				       "i2400m.barkers value '%s' as "
-				       "a 32-bit number\n",
-				       __func__, token);
-				result = -EINVAL;
-				goto error_parse;
-			}
-			if (barker == 0) {
-				/* clean list and start new */
-				i2400m_barker_db_exit();
-				continue;
-			}
-			result = i2400m_barker_db_add(barker);
-			if (result < 0)
-				goto error_parse_add;
-		}
-		kfree(options_orig);
-	}
-	return 0;
-
-error_parse_add:
-error_parse:
-	kfree(options_orig);
-error_add:
-	kfree(i2400m_barker_db);
-	return result;
-}
-
-
-/*
- * Recognize a boot barker
- *
- * @buf: buffer where the boot barker.
- * @buf_size: size of the buffer (has to be 16 bytes). It is passed
- *     here so the function can check it for the caller.
- *
- * Note that as a side effect, upon identifying the obtained boot
- * barker, this function will set i2400m->barker to point to the right
- * barker database entry. Subsequent calls to the function will result
- * in verifying that the same type of boot barker is returned when the
- * device [re]boots (as long as the same device instance is used).
- *
- * Return: 0 if @buf matches a known boot barker. -ENOENT if the
- *     buffer in @buf doesn't match any boot barker in the database or
- *     -EILSEQ if the buffer doesn't have the right size.
- */
-int i2400m_is_boot_barker(struct i2400m *i2400m,
-			  const void *buf, size_t buf_size)
-{
-	int result;
-	struct device *dev = i2400m_dev(i2400m);
-	struct i2400m_barker_db *barker;
-	int i;
-
-	result = -ENOENT;
-	if (buf_size != sizeof(i2400m_barker_db[i].data))
-		return result;
-
-	/* Short circuit if we have already discovered the barker
-	 * associated with the device. */
-	if (i2400m->barker &&
-	    !memcmp(buf, i2400m->barker, sizeof(i2400m->barker->data)))
-		return 0;
-
-	for (i = 0; i < i2400m_barker_db_used; i++) {
-		barker = &i2400m_barker_db[i];
-		BUILD_BUG_ON(sizeof(barker->data) != 16);
-		if (memcmp(buf, barker->data, sizeof(barker->data)))
-			continue;
-
-		if (i2400m->barker == NULL) {
-			i2400m->barker = barker;
-			d_printf(1, dev, "boot barker set to #%u/%08x\n",
-				 i, le32_to_cpu(barker->data[0]));
-			if (barker->data[0] == le32_to_cpu(I2400M_NBOOT_BARKER))
-				i2400m->sboot = 0;
-			else
-				i2400m->sboot = 1;
-		} else if (i2400m->barker != barker) {
-			dev_err(dev, "HW inconsistency: device "
-				"reports a different boot barker "
-				"than set (from %08x to %08x)\n",
-				le32_to_cpu(i2400m->barker->data[0]),
-				le32_to_cpu(barker->data[0]));
-			result = -EIO;
-		} else
-			d_printf(2, dev, "boot barker confirmed #%u/%08x\n",
-				 i, le32_to_cpu(barker->data[0]));
-		result = 0;
-		break;
-	}
-	return result;
-}
-EXPORT_SYMBOL_GPL(i2400m_is_boot_barker);
-
-
-/*
- * Verify the ack data received
- *
- * Given a reply to a boot mode command, chew it and verify everything
- * is ok.
- *
- * @opcode: opcode which generated this ack. For error messages.
- * @ack: pointer to ack data we received
- * @ack_size: size of that data buffer
- * @flags: I2400M_BM_CMD_* flags we called the command with.
- *
- * Way too long function -- maybe it should be further split
- */
-static
-ssize_t __i2400m_bm_ack_verify(struct i2400m *i2400m, int opcode,
-			       struct i2400m_bootrom_header *ack,
-			       size_t ack_size, int flags)
-{
-	ssize_t result = -ENOMEM;
-	struct device *dev = i2400m_dev(i2400m);
-
-	d_fnstart(8, dev, "(i2400m %p opcode %d ack %p size %zu)\n",
-		  i2400m, opcode, ack, ack_size);
-	if (ack_size < sizeof(*ack)) {
-		result = -EIO;
-		dev_err(dev, "boot-mode cmd %d: HW BUG? notification didn't "
-			"return enough data (%zu bytes vs %zu expected)\n",
-			opcode, ack_size, sizeof(*ack));
-		goto error_ack_short;
-	}
-	result = i2400m_is_boot_barker(i2400m, ack, ack_size);
-	if (result >= 0) {
-		result = -ERESTARTSYS;
-		d_printf(6, dev, "boot-mode cmd %d: HW boot barker\n", opcode);
-		goto error_reboot;
-	}
-	if (ack_size == sizeof(i2400m_ACK_BARKER)
-		 && memcmp(ack, i2400m_ACK_BARKER, sizeof(*ack)) == 0) {
-		result = -EISCONN;
-		d_printf(3, dev, "boot-mode cmd %d: HW reboot ack barker\n",
-			 opcode);
-		goto error_reboot_ack;
-	}
-	result = 0;
-	if (flags & I2400M_BM_CMD_RAW)
-		goto out_raw;
-	ack->data_size = le32_to_cpu(ack->data_size);
-	ack->target_addr = le32_to_cpu(ack->target_addr);
-	ack->block_checksum = le32_to_cpu(ack->block_checksum);
-	d_printf(5, dev, "boot-mode cmd %d: notification for opcode %u "
-		 "response %u csum %u rr %u da %u\n",
-		 opcode, i2400m_brh_get_opcode(ack),
-		 i2400m_brh_get_response(ack),
-		 i2400m_brh_get_use_checksum(ack),
-		 i2400m_brh_get_response_required(ack),
-		 i2400m_brh_get_direct_access(ack));
-	result = -EIO;
-	if (i2400m_brh_get_signature(ack) != 0xcbbc) {
-		dev_err(dev, "boot-mode cmd %d: HW BUG? wrong signature "
-			"0x%04x\n", opcode, i2400m_brh_get_signature(ack));
-		goto error_ack_signature;
-	}
-	if (opcode != -1 && opcode != i2400m_brh_get_opcode(ack)) {
-		dev_err(dev, "boot-mode cmd %d: HW BUG? "
-			"received response for opcode %u, expected %u\n",
-			opcode, i2400m_brh_get_opcode(ack), opcode);
-		goto error_ack_opcode;
-	}
-	if (i2400m_brh_get_response(ack) != 0) {	/* failed? */
-		dev_err(dev, "boot-mode cmd %d: error; hw response %u\n",
-			opcode, i2400m_brh_get_response(ack));
-		goto error_ack_failed;
-	}
-	if (ack_size < ack->data_size + sizeof(*ack)) {
-		dev_err(dev, "boot-mode cmd %d: SW BUG "
-			"driver provided only %zu bytes for %zu bytes "
-			"of data\n", opcode, ack_size,
-			(size_t) le32_to_cpu(ack->data_size) + sizeof(*ack));
-		goto error_ack_short_buffer;
-	}
-	result = ack_size;
-	/* Don't you love this stack of empty targets? Well, I don't
-	 * either, but it helps track exactly who comes in here and
-	 * why :) */
-error_ack_short_buffer:
-error_ack_failed:
-error_ack_opcode:
-error_ack_signature:
-out_raw:
-error_reboot_ack:
-error_reboot:
-error_ack_short:
-	d_fnend(8, dev, "(i2400m %p opcode %d ack %p size %zu) = %d\n",
-		i2400m, opcode, ack, ack_size, (int) result);
-	return result;
-}
-
-
-/**
- * i2400m_bm_cmd - Execute a boot mode command
- *
- * @cmd: buffer containing the command data (pointing at the header).
- *     This data can be ANYWHERE (for USB, we will copy it to an
- *     specific buffer). Make sure everything is in proper little
- *     endian.
- *
- *     A raw buffer can be also sent, just cast it and set flags to
- *     I2400M_BM_CMD_RAW.
- *
- *     This function will generate a checksum for you if the
- *     checksum bit in the command is set (unless I2400M_BM_CMD_RAW
- *     is set).
- *
- *     You can use the i2400m->bm_cmd_buf to stage your commands and
- *     send them.
- *
- *     If NULL, no command is sent (we just wait for an ack).
- *
- * @cmd_size: size of the command. Will be auto padded to the
- *     bus-specific drivers padding requirements.
- *
- * @ack: buffer where to place the acknowledgement. If it is a regular
- *     command response, all fields will be returned with the right,
- *     native endianess.
- *
- *     You *cannot* use i2400m->bm_ack_buf for this buffer.
- *
- * @ack_size: size of @ack, 16 aligned; you need to provide at least
- *     sizeof(*ack) bytes and then enough to contain the return data
- *     from the command
- *
- * @flags: see I2400M_BM_CMD_* above.
- *
- * @returns: bytes received by the notification; if < 0, an errno code
- *     denoting an error or:
- *
- *     -ERESTARTSYS  The device has rebooted
- *
- * Executes a boot-mode command and waits for a response, doing basic
- * validation on it; if a zero length response is received, it retries
- * waiting for a response until a non-zero one is received (timing out
- * after %I2400M_BOOT_RETRIES retries).
- */
-static
-ssize_t i2400m_bm_cmd(struct i2400m *i2400m,
-		      const struct i2400m_bootrom_header *cmd, size_t cmd_size,
-		      struct i2400m_bootrom_header *ack, size_t ack_size,
-		      int flags)
-{
-	ssize_t result = -ENOMEM, rx_bytes;
-	struct device *dev = i2400m_dev(i2400m);
-	int opcode = cmd == NULL ? -1 : i2400m_brh_get_opcode(cmd);
-
-	d_fnstart(6, dev, "(i2400m %p cmd %p size %zu ack %p size %zu)\n",
-		  i2400m, cmd, cmd_size, ack, ack_size);
-	BUG_ON(ack_size < sizeof(*ack));
-	BUG_ON(i2400m->boot_mode == 0);
-
-	if (cmd != NULL) {		/* send the command */
-		result = i2400m->bus_bm_cmd_send(i2400m, cmd, cmd_size, flags);
-		if (result < 0)
-			goto error_cmd_send;
-		if ((flags & I2400M_BM_CMD_RAW) == 0)
-			d_printf(5, dev,
-				 "boot-mode cmd %d csum %u rr %u da %u: "
-				 "addr 0x%04x size %u block csum 0x%04x\n",
-				 opcode, i2400m_brh_get_use_checksum(cmd),
-				 i2400m_brh_get_response_required(cmd),
-				 i2400m_brh_get_direct_access(cmd),
-				 cmd->target_addr, cmd->data_size,
-				 cmd->block_checksum);
-	}
-	result = i2400m->bus_bm_wait_for_ack(i2400m, ack, ack_size);
-	if (result < 0) {
-		dev_err(dev, "boot-mode cmd %d: error waiting for an ack: %d\n",
-			opcode, (int) result);	/* bah, %zd doesn't work */
-		goto error_wait_for_ack;
-	}
-	rx_bytes = result;
-	/* verify the ack and read more if necessary [result is the
-	 * final amount of bytes we get in the ack]  */
-	result = __i2400m_bm_ack_verify(i2400m, opcode, ack, ack_size, flags);
-	if (result < 0)
-		goto error_bad_ack;
-	/* Don't you love this stack of empty targets? Well, I don't
-	 * either, but it helps track exactly who comes in here and
-	 * why :) */
-	result = rx_bytes;
-error_bad_ack:
-error_wait_for_ack:
-error_cmd_send:
-	d_fnend(6, dev, "(i2400m %p cmd %p size %zu ack %p size %zu) = %d\n",
-		i2400m, cmd, cmd_size, ack, ack_size, (int) result);
-	return result;
-}
-
-
-/**
- * i2400m_download_chunk - write a single chunk of data to the device's memory
- *
- * @i2400m: device descriptor
- * @buf: the buffer to write
- * @buf_len: length of the buffer to write
- * @addr: address in the device memory space
- * @direct: bootrom write mode
- * @do_csum: should a checksum validation be performed
- */
-static int i2400m_download_chunk(struct i2400m *i2400m, const void *chunk,
-				 size_t __chunk_len, unsigned long addr,
-				 unsigned int direct, unsigned int do_csum)
-{
-	int ret;
-	size_t chunk_len = ALIGN(__chunk_len, I2400M_PL_ALIGN);
-	struct device *dev = i2400m_dev(i2400m);
-	struct {
-		struct i2400m_bootrom_header cmd;
-		u8 cmd_payload[];
-	} __packed *buf;
-	struct i2400m_bootrom_header ack;
-
-	d_fnstart(5, dev, "(i2400m %p chunk %p __chunk_len %zu addr 0x%08lx "
-		  "direct %u do_csum %u)\n", i2400m, chunk, __chunk_len,
-		  addr, direct, do_csum);
-	buf = i2400m->bm_cmd_buf;
-	memcpy(buf->cmd_payload, chunk, __chunk_len);
-	memset(buf->cmd_payload + __chunk_len, 0xad, chunk_len - __chunk_len);
-
-	buf->cmd.command = i2400m_brh_command(I2400M_BRH_WRITE,
-					      __chunk_len & 0x3 ? 0 : do_csum,
-					      __chunk_len & 0xf ? 0 : direct);
-	buf->cmd.target_addr = cpu_to_le32(addr);
-	buf->cmd.data_size = cpu_to_le32(__chunk_len);
-	ret = i2400m_bm_cmd(i2400m, &buf->cmd, sizeof(buf->cmd) + chunk_len,
-			    &ack, sizeof(ack), 0);
-	if (ret >= 0)
-		ret = 0;
-	d_fnend(5, dev, "(i2400m %p chunk %p __chunk_len %zu addr 0x%08lx "
-		"direct %u do_csum %u) = %d\n", i2400m, chunk, __chunk_len,
-		addr, direct, do_csum, ret);
-	return ret;
-}
-
-
-/*
- * Download a BCF file's sections to the device
- *
- * @i2400m: device descriptor
- * @bcf: pointer to firmware data (first header followed by the
- *     payloads). Assumed verified and consistent.
- * @bcf_len: length (in bytes) of the @bcf buffer.
- *
- * Returns: < 0 errno code on error or the offset to the jump instruction.
- *
- * Given a BCF file, downloads each section (a command and a payload)
- * to the device's address space. Actually, it just executes each
- * command i the BCF file.
- *
- * The section size has to be aligned to 4 bytes AND the padding has
- * to be taken from the firmware file, as the signature takes it into
- * account.
- */
-static
-ssize_t i2400m_dnload_bcf(struct i2400m *i2400m,
-			  const struct i2400m_bcf_hdr *bcf, size_t bcf_len)
-{
-	ssize_t ret;
-	struct device *dev = i2400m_dev(i2400m);
-	size_t offset,		/* iterator offset */
-		data_size,	/* Size of the data payload */
-		section_size,	/* Size of the whole section (cmd + payload) */
-		section = 1;
-	const struct i2400m_bootrom_header *bh;
-	struct i2400m_bootrom_header ack;
-
-	d_fnstart(3, dev, "(i2400m %p bcf %p bcf_len %zu)\n",
-		  i2400m, bcf, bcf_len);
-	/* Iterate over the command blocks in the BCF file that start
-	 * after the header */
-	offset = le32_to_cpu(bcf->header_len) * sizeof(u32);
-	while (1) {	/* start sending the file */
-		bh = (void *) bcf + offset;
-		data_size = le32_to_cpu(bh->data_size);
-		section_size = ALIGN(sizeof(*bh) + data_size, 4);
-		d_printf(7, dev,
-			 "downloading section #%zu (@%zu %zu B) to 0x%08x\n",
-			 section, offset, sizeof(*bh) + data_size,
-			 le32_to_cpu(bh->target_addr));
-		/*
-		 * We look for JUMP cmd from the bootmode header,
-		 * either I2400M_BRH_SIGNED_JUMP for secure boot
-		 * or I2400M_BRH_JUMP for unsecure boot, the last chunk
-		 * should be the bootmode header with JUMP cmd.
-		 */
-		if (i2400m_brh_get_opcode(bh) == I2400M_BRH_SIGNED_JUMP ||
-			i2400m_brh_get_opcode(bh) == I2400M_BRH_JUMP) {
-			d_printf(5, dev,  "jump found @%zu\n", offset);
-			break;
-		}
-		if (offset + section_size > bcf_len) {
-			dev_err(dev, "fw %s: bad section #%zu, "
-				"end (@%zu) beyond EOF (@%zu)\n",
-				i2400m->fw_name, section,
-				offset + section_size,  bcf_len);
-			ret = -EINVAL;
-			goto error_section_beyond_eof;
-		}
-		__i2400m_msleep(20);
-		ret = i2400m_bm_cmd(i2400m, bh, section_size,
-				    &ack, sizeof(ack), I2400M_BM_CMD_RAW);
-		if (ret < 0) {
-			dev_err(dev, "fw %s: section #%zu (@%zu %zu B) "
-				"failed %d\n", i2400m->fw_name, section,
-				offset, sizeof(*bh) + data_size, (int) ret);
-			goto error_send;
-		}
-		offset += section_size;
-		section++;
-	}
-	ret = offset;
-error_section_beyond_eof:
-error_send:
-	d_fnend(3, dev, "(i2400m %p bcf %p bcf_len %zu) = %d\n",
-		i2400m, bcf, bcf_len, (int) ret);
-	return ret;
-}
-
-
-/*
- * Indicate if the device emitted a reboot barker that indicates
- * "signed boot"
- */
-static
-unsigned i2400m_boot_is_signed(struct i2400m *i2400m)
-{
-	return likely(i2400m->sboot);
-}
-
-
-/*
- * Do the final steps of uploading firmware
- *
- * @bcf_hdr: BCF header we are actually using
- * @bcf: pointer to the firmware image (which matches the first header
- *     that is followed by the actual payloads).
- * @offset: [byte] offset into @bcf for the command we need to send.
- *
- * Depending on the boot mode (signed vs non-signed), different
- * actions need to be taken.
- */
-static
-int i2400m_dnload_finalize(struct i2400m *i2400m,
-			   const struct i2400m_bcf_hdr *bcf_hdr,
-			   const struct i2400m_bcf_hdr *bcf, size_t offset)
-{
-	int ret = 0;
-	struct device *dev = i2400m_dev(i2400m);
-	struct i2400m_bootrom_header *cmd, ack;
-	struct {
-		struct i2400m_bootrom_header cmd;
-		u8 cmd_pl[0];
-	} __packed *cmd_buf;
-	size_t signature_block_offset, signature_block_size;
-
-	d_fnstart(3, dev, "offset %zu\n", offset);
-	cmd = (void *) bcf + offset;
-	if (i2400m_boot_is_signed(i2400m) == 0) {
-		struct i2400m_bootrom_header jump_ack;
-		d_printf(1, dev, "unsecure boot, jumping to 0x%08x\n",
-			le32_to_cpu(cmd->target_addr));
-		cmd_buf = i2400m->bm_cmd_buf;
-		memcpy(&cmd_buf->cmd, cmd, sizeof(*cmd));
-		cmd = &cmd_buf->cmd;
-		/* now cmd points to the actual bootrom_header in cmd_buf */
-		i2400m_brh_set_opcode(cmd, I2400M_BRH_JUMP);
-		cmd->data_size = 0;
-		ret = i2400m_bm_cmd(i2400m, cmd, sizeof(*cmd),
-				    &jump_ack, sizeof(jump_ack), 0);
-	} else {
-		d_printf(1, dev, "secure boot, jumping to 0x%08x\n",
-			 le32_to_cpu(cmd->target_addr));
-		cmd_buf = i2400m->bm_cmd_buf;
-		memcpy(&cmd_buf->cmd, cmd, sizeof(*cmd));
-		signature_block_offset =
-			sizeof(*bcf_hdr)
-			+ le32_to_cpu(bcf_hdr->key_size) * sizeof(u32)
-			+ le32_to_cpu(bcf_hdr->exponent_size) * sizeof(u32);
-		signature_block_size =
-			le32_to_cpu(bcf_hdr->modulus_size) * sizeof(u32);
-		memcpy(cmd_buf->cmd_pl,
-		       (void *) bcf_hdr + signature_block_offset,
-		       signature_block_size);
-		ret = i2400m_bm_cmd(i2400m, &cmd_buf->cmd,
-				    sizeof(cmd_buf->cmd) + signature_block_size,
-				    &ack, sizeof(ack), I2400M_BM_CMD_RAW);
-	}
-	d_fnend(3, dev, "returning %d\n", ret);
-	return ret;
-}
-
-
-/**
- * i2400m_bootrom_init - Reboots a powered device into boot mode
- *
- * @i2400m: device descriptor
- * @flags:
- *      I2400M_BRI_SOFT: a reboot barker has been seen
- *          already, so don't wait for it.
- *
- *      I2400M_BRI_NO_REBOOT: Don't send a reboot command, but wait
- *          for a reboot barker notification. This is a one shot; if
- *          the state machine needs to send a reboot command it will.
- *
- * Returns:
- *
- *     < 0 errno code on error, 0 if ok.
- *
- * Description:
- *
- * Tries hard enough to put the device in boot-mode. There are two
- * main phases to this:
- *
- * a. (1) send a reboot command and (2) get a reboot barker
- *
- * b. (1) echo/ack the reboot sending the reboot barker back and (2)
- *        getting an ack barker in return
- *
- * We want to skip (a) in some cases [soft]. The state machine is
- * horrible, but it is basically: on each phase, send what has to be
- * sent (if any), wait for the answer and act on the answer. We might
- * have to backtrack and retry, so we keep a max tries counter for
- * that.
- *
- * It sucks because we don't know ahead of time which is going to be
- * the reboot barker (the device might send different ones depending
- * on its EEPROM config) and once the device reboots and waits for the
- * echo/ack reboot barker being sent back, it doesn't understand
- * anything else. So we can be left at the point where we don't know
- * what to send to it -- cold reset and bus reset seem to have little
- * effect. So the function iterates (in this case) through all the
- * known barkers and tries them all until an ACK is
- * received. Otherwise, it gives up.
- *
- * If we get a timeout after sending a warm reset, we do it again.
- */
-int i2400m_bootrom_init(struct i2400m *i2400m, enum i2400m_bri flags)
-{
-	int result;
-	struct device *dev = i2400m_dev(i2400m);
-	struct i2400m_bootrom_header *cmd;
-	struct i2400m_bootrom_header ack;
-	int count = i2400m->bus_bm_retries;
-	int ack_timeout_cnt = 1;
-	unsigned i;
-
-	BUILD_BUG_ON(sizeof(*cmd) != sizeof(i2400m_barker_db[0].data));
-	BUILD_BUG_ON(sizeof(ack) != sizeof(i2400m_ACK_BARKER));
-
-	d_fnstart(4, dev, "(i2400m %p flags 0x%08x)\n", i2400m, flags);
-	result = -ENOMEM;
-	cmd = i2400m->bm_cmd_buf;
-	if (flags & I2400M_BRI_SOFT)
-		goto do_reboot_ack;
-do_reboot:
-	ack_timeout_cnt = 1;
-	if (--count < 0)
-		goto error_timeout;
-	d_printf(4, dev, "device reboot: reboot command [%d # left]\n",
-		 count);
-	if ((flags & I2400M_BRI_NO_REBOOT) == 0)
-		i2400m_reset(i2400m, I2400M_RT_WARM);
-	result = i2400m_bm_cmd(i2400m, NULL, 0, &ack, sizeof(ack),
-			       I2400M_BM_CMD_RAW);
-	flags &= ~I2400M_BRI_NO_REBOOT;
-	switch (result) {
-	case -ERESTARTSYS:
-		/*
-		 * at this point, i2400m_bm_cmd(), through
-		 * __i2400m_bm_ack_process(), has updated
-		 * i2400m->barker and we are good to go.
-		 */
-		d_printf(4, dev, "device reboot: got reboot barker\n");
-		break;
-	case -EISCONN:	/* we don't know how it got here...but we follow it */
-		d_printf(4, dev, "device reboot: got ack barker - whatever\n");
-		goto do_reboot;
-	case -ETIMEDOUT:
-		/*
-		 * Device has timed out, we might be in boot mode
-		 * already and expecting an ack; if we don't know what
-		 * the barker is, we just send them all. Cold reset
-		 * and bus reset don't work. Beats me.
-		 */
-		if (i2400m->barker != NULL) {
-			dev_err(dev, "device boot: reboot barker timed out, "
-				"trying (set) %08x echo/ack\n",
-				le32_to_cpu(i2400m->barker->data[0]));
-			goto do_reboot_ack;
-		}
-		for (i = 0; i < i2400m_barker_db_used; i++) {
-			struct i2400m_barker_db *barker = &i2400m_barker_db[i];
-			memcpy(cmd, barker->data, sizeof(barker->data));
-			result = i2400m_bm_cmd(i2400m, cmd, sizeof(*cmd),
-					       &ack, sizeof(ack),
-					       I2400M_BM_CMD_RAW);
-			if (result == -EISCONN) {
-				dev_warn(dev, "device boot: got ack barker "
-					 "after sending echo/ack barker "
-					 "#%d/%08x; rebooting j.i.c.\n",
-					 i, le32_to_cpu(barker->data[0]));
-				flags &= ~I2400M_BRI_NO_REBOOT;
-				goto do_reboot;
-			}
-		}
-		dev_err(dev, "device boot: tried all the echo/acks, could "
-			"not get device to respond; giving up");
-		result = -ESHUTDOWN;
-	case -EPROTO:
-	case -ESHUTDOWN:	/* dev is gone */
-	case -EINTR:		/* user cancelled */
-		goto error_dev_gone;
-	default:
-		dev_err(dev, "device reboot: error %d while waiting "
-			"for reboot barker - rebooting\n", result);
-		d_dump(1, dev, &ack, result);
-		goto do_reboot;
-	}
-	/* At this point we ack back with 4 REBOOT barkers and expect
-	 * 4 ACK barkers. This is ugly, as we send a raw command --
-	 * hence the cast. _bm_cmd() will catch the reboot ack
-	 * notification and report it as -EISCONN. */
-do_reboot_ack:
-	d_printf(4, dev, "device reboot ack: sending ack [%d # left]\n", count);
-	memcpy(cmd, i2400m->barker->data, sizeof(i2400m->barker->data));
-	result = i2400m_bm_cmd(i2400m, cmd, sizeof(*cmd),
-			       &ack, sizeof(ack), I2400M_BM_CMD_RAW);
-	switch (result) {
-	case -ERESTARTSYS:
-		d_printf(4, dev, "reboot ack: got reboot barker - retrying\n");
-		if (--count < 0)
-			goto error_timeout;
-		goto do_reboot_ack;
-	case -EISCONN:
-		d_printf(4, dev, "reboot ack: got ack barker - good\n");
-		break;
-	case -ETIMEDOUT:	/* no response, maybe it is the other type? */
-		if (ack_timeout_cnt-- < 0) {
-			d_printf(4, dev, "reboot ack timedout: retrying\n");
-			goto do_reboot_ack;
-		} else {
-			dev_err(dev, "reboot ack timedout too long: "
-				"trying reboot\n");
-			goto do_reboot;
-		}
-		break;
-	case -EPROTO:
-	case -ESHUTDOWN:	/* dev is gone */
-		goto error_dev_gone;
-	default:
-		dev_err(dev, "device reboot ack: error %d while waiting for "
-			"reboot ack barker - rebooting\n", result);
-		goto do_reboot;
-	}
-	d_printf(2, dev, "device reboot ack: got ack barker - boot done\n");
-	result = 0;
-exit_timeout:
-error_dev_gone:
-	d_fnend(4, dev, "(i2400m %p flags 0x%08x) = %d\n",
-		i2400m, flags, result);
-	return result;
-
-error_timeout:
-	dev_err(dev, "Timed out waiting for reboot ack\n");
-	result = -ETIMEDOUT;
-	goto exit_timeout;
-}
-
-
-/*
- * Read the MAC addr
- *
- * The position this function reads is fixed in device memory and
- * always available, even without firmware.
- *
- * Note we specify we want to read only six bytes, but provide space
- * for 16, as we always get it rounded up.
- */
-int i2400m_read_mac_addr(struct i2400m *i2400m)
-{
-	int result;
-	struct device *dev = i2400m_dev(i2400m);
-	struct net_device *net_dev = i2400m->wimax_dev.net_dev;
-	struct i2400m_bootrom_header *cmd;
-	struct {
-		struct i2400m_bootrom_header ack;
-		u8 ack_pl[16];
-	} __packed ack_buf;
-
-	d_fnstart(5, dev, "(i2400m %p)\n", i2400m);
-	cmd = i2400m->bm_cmd_buf;
-	cmd->command = i2400m_brh_command(I2400M_BRH_READ, 0, 1);
-	cmd->target_addr = cpu_to_le32(0x00203fe8);
-	cmd->data_size = cpu_to_le32(6);
-	result = i2400m_bm_cmd(i2400m, cmd, sizeof(*cmd),
-			       &ack_buf.ack, sizeof(ack_buf), 0);
-	if (result < 0) {
-		dev_err(dev, "BM: read mac addr failed: %d\n", result);
-		goto error_read_mac;
-	}
-	d_printf(2, dev, "mac addr is %pM\n", ack_buf.ack_pl);
-	if (i2400m->bus_bm_mac_addr_impaired == 1) {
-		ack_buf.ack_pl[0] = 0x00;
-		ack_buf.ack_pl[1] = 0x16;
-		ack_buf.ack_pl[2] = 0xd3;
-		get_random_bytes(&ack_buf.ack_pl[3], 3);
-		dev_err(dev, "BM is MAC addr impaired, faking MAC addr to "
-			"mac addr is %pM\n", ack_buf.ack_pl);
-		result = 0;
-	}
-	net_dev->addr_len = ETH_ALEN;
-	memcpy(net_dev->dev_addr, ack_buf.ack_pl, ETH_ALEN);
-error_read_mac:
-	d_fnend(5, dev, "(i2400m %p) = %d\n", i2400m, result);
-	return result;
-}
-
-
-/*
- * Initialize a non signed boot
- *
- * This implies sending some magic values to the device's memory. Note
- * we convert the values to little endian in the same array
- * declaration.
- */
-static
-int i2400m_dnload_init_nonsigned(struct i2400m *i2400m)
-{
-	unsigned i = 0;
-	int ret = 0;
-	struct device *dev = i2400m_dev(i2400m);
-	d_fnstart(5, dev, "(i2400m %p)\n", i2400m);
-	if (i2400m->bus_bm_pokes_table) {
-		while (i2400m->bus_bm_pokes_table[i].address) {
-			ret = i2400m_download_chunk(
-				i2400m,
-				&i2400m->bus_bm_pokes_table[i].data,
-				sizeof(i2400m->bus_bm_pokes_table[i].data),
-				i2400m->bus_bm_pokes_table[i].address, 1, 1);
-			if (ret < 0)
-				break;
-			i++;
-		}
-	}
-	d_fnend(5, dev, "(i2400m %p) = %d\n", i2400m, ret);
-	return ret;
-}
-
-
-/*
- * Initialize the signed boot process
- *
- * @i2400m: device descriptor
- *
- * @bcf_hdr: pointer to the firmware header; assumes it is fully in
- *     memory (it has gone through basic validation).
- *
- * Returns: 0 if ok, < 0 errno code on error, -ERESTARTSYS if the hw
- *     rebooted.
- *
- * This writes the firmware BCF header to the device using the
- * HASH_PAYLOAD_ONLY command.
- */
-static
-int i2400m_dnload_init_signed(struct i2400m *i2400m,
-			      const struct i2400m_bcf_hdr *bcf_hdr)
-{
-	int ret;
-	struct device *dev = i2400m_dev(i2400m);
-	struct {
-		struct i2400m_bootrom_header cmd;
-		struct i2400m_bcf_hdr cmd_pl;
-	} __packed *cmd_buf;
-	struct i2400m_bootrom_header ack;
-
-	d_fnstart(5, dev, "(i2400m %p bcf_hdr %p)\n", i2400m, bcf_hdr);
-	cmd_buf = i2400m->bm_cmd_buf;
-	cmd_buf->cmd.command =
-		i2400m_brh_command(I2400M_BRH_HASH_PAYLOAD_ONLY, 0, 0);
-	cmd_buf->cmd.target_addr = 0;
-	cmd_buf->cmd.data_size = cpu_to_le32(sizeof(cmd_buf->cmd_pl));
-	memcpy(&cmd_buf->cmd_pl, bcf_hdr, sizeof(*bcf_hdr));
-	ret = i2400m_bm_cmd(i2400m, &cmd_buf->cmd, sizeof(*cmd_buf),
-			    &ack, sizeof(ack), 0);
-	if (ret >= 0)
-		ret = 0;
-	d_fnend(5, dev, "(i2400m %p bcf_hdr %p) = %d\n", i2400m, bcf_hdr, ret);
-	return ret;
-}
-
-
-/*
- * Initialize the firmware download at the device size
- *
- * Multiplex to the one that matters based on the device's mode
- * (signed or non-signed).
- */
-static
-int i2400m_dnload_init(struct i2400m *i2400m,
-		       const struct i2400m_bcf_hdr *bcf_hdr)
-{
-	int result;
-	struct device *dev = i2400m_dev(i2400m);
-
-	if (i2400m_boot_is_signed(i2400m)) {
-		d_printf(1, dev, "signed boot\n");
-		result = i2400m_dnload_init_signed(i2400m, bcf_hdr);
-		if (result == -ERESTARTSYS)
-			return result;
-		if (result < 0)
-			dev_err(dev, "firmware %s: signed boot download "
-				"initialization failed: %d\n",
-				i2400m->fw_name, result);
-	} else {
-		/* non-signed boot process without pokes */
-		d_printf(1, dev, "non-signed boot\n");
-		result = i2400m_dnload_init_nonsigned(i2400m);
-		if (result == -ERESTARTSYS)
-			return result;
-		if (result < 0)
-			dev_err(dev, "firmware %s: non-signed download "
-				"initialization failed: %d\n",
-				i2400m->fw_name, result);
-	}
-	return result;
-}
-
-
-/*
- * Run consistency tests on the firmware file and load up headers
- *
- * Check for the firmware being made for the i2400m device,
- * etc...These checks are mostly informative, as the device will make
- * them too; but the driver's response is more informative on what
- * went wrong.
- *
- * This will also look at all the headers present on the firmware
- * file, and update i2400m->fw_bcf_hdr to point to them.
- */
-static
-int i2400m_fw_hdr_check(struct i2400m *i2400m,
-			const struct i2400m_bcf_hdr *bcf_hdr,
-			size_t index, size_t offset)
-{
-	struct device *dev = i2400m_dev(i2400m);
-
-	unsigned module_type, header_len, major_version, minor_version,
-		module_id, module_vendor, date, size;
-
-	module_type = le32_to_cpu(bcf_hdr->module_type);
-	header_len = sizeof(u32) * le32_to_cpu(bcf_hdr->header_len);
-	major_version = (le32_to_cpu(bcf_hdr->header_version) & 0xffff0000)
-		>> 16;
-	minor_version = le32_to_cpu(bcf_hdr->header_version) & 0x0000ffff;
-	module_id = le32_to_cpu(bcf_hdr->module_id);
-	module_vendor = le32_to_cpu(bcf_hdr->module_vendor);
-	date = le32_to_cpu(bcf_hdr->date);
-	size = sizeof(u32) * le32_to_cpu(bcf_hdr->size);
-
-	d_printf(1, dev, "firmware %s #%zd@%08zx: BCF header "
-		 "type:vendor:id 0x%x:%x:%x v%u.%u (%u/%u B) built %08x\n",
-		 i2400m->fw_name, index, offset,
-		 module_type, module_vendor, module_id,
-		 major_version, minor_version, header_len, size, date);
-
-	/* Hard errors */
-	if (major_version != 1) {
-		dev_err(dev, "firmware %s #%zd@%08zx: major header version "
-			"v%u.%u not supported\n",
-			i2400m->fw_name, index, offset,
-			major_version, minor_version);
-		return -EBADF;
-	}
-
-	if (module_type != 6) {		/* built for the right hardware? */
-		dev_err(dev, "firmware %s #%zd@%08zx: unexpected module "
-			"type 0x%x; aborting\n",
-			i2400m->fw_name, index, offset,
-			module_type);
-		return -EBADF;
-	}
-
-	if (module_vendor != 0x8086) {
-		dev_err(dev, "firmware %s #%zd@%08zx: unexpected module "
-			"vendor 0x%x; aborting\n",
-			i2400m->fw_name, index, offset, module_vendor);
-		return -EBADF;
-	}
-
-	if (date < 0x20080300)
-		dev_warn(dev, "firmware %s #%zd@%08zx: build date %08x "
-			 "too old; unsupported\n",
-			 i2400m->fw_name, index, offset, date);
-	return 0;
-}
-
-
-/*
- * Run consistency tests on the firmware file and load up headers
- *
- * Check for the firmware being made for the i2400m device,
- * etc...These checks are mostly informative, as the device will make
- * them too; but the driver's response is more informative on what
- * went wrong.
- *
- * This will also look at all the headers present on the firmware
- * file, and update i2400m->fw_hdrs to point to them.
- */
-static
-int i2400m_fw_check(struct i2400m *i2400m, const void *bcf, size_t bcf_size)
-{
-	int result;
-	struct device *dev = i2400m_dev(i2400m);
-	size_t headers = 0;
-	const struct i2400m_bcf_hdr *bcf_hdr;
-	const void *itr, *next, *top;
-	size_t slots = 0, used_slots = 0;
-
-	for (itr = bcf, top = itr + bcf_size;
-	     itr < top;
-	     headers++, itr = next) {
-		size_t leftover, offset, header_len, size;
-
-		leftover = top - itr;
-		offset = itr - bcf;
-		if (leftover <= sizeof(*bcf_hdr)) {
-			dev_err(dev, "firmware %s: %zu B left at @%zx, "
-				"not enough for BCF header\n",
-				i2400m->fw_name, leftover, offset);
-			break;
-		}
-		bcf_hdr = itr;
-		/* Only the first header is supposed to be followed by
-		 * payload */
-		header_len = sizeof(u32) * le32_to_cpu(bcf_hdr->header_len);
-		size = sizeof(u32) * le32_to_cpu(bcf_hdr->size);
-		if (headers == 0)
-			next = itr + size;
-		else
-			next = itr + header_len;
-
-		result = i2400m_fw_hdr_check(i2400m, bcf_hdr, headers, offset);
-		if (result < 0)
-			continue;
-		if (used_slots + 1 >= slots) {
-			/* +1 -> we need to account for the one we'll
-			 * occupy and at least an extra one for
-			 * always being NULL */
-			result = i2400m_zrealloc_2x(
-				(void **) &i2400m->fw_hdrs, &slots,
-				sizeof(i2400m->fw_hdrs[0]),
-				GFP_KERNEL);
-			if (result < 0)
-				goto error_zrealloc;
-		}
-		i2400m->fw_hdrs[used_slots] = bcf_hdr;
-		used_slots++;
-	}
-	if (headers == 0) {
-		dev_err(dev, "firmware %s: no usable headers found\n",
-			i2400m->fw_name);
-		result = -EBADF;
-	} else
-		result = 0;
-error_zrealloc:
-	return result;
-}
-
-
-/*
- * Match a barker to a BCF header module ID
- *
- * The device sends a barker which tells the firmware loader which
- * header in the BCF file has to be used. This does the matching.
- */
-static
-unsigned i2400m_bcf_hdr_match(struct i2400m *i2400m,
-			      const struct i2400m_bcf_hdr *bcf_hdr)
-{
-	u32 barker = le32_to_cpu(i2400m->barker->data[0])
-		& 0x7fffffff;
-	u32 module_id = le32_to_cpu(bcf_hdr->module_id)
-		& 0x7fffffff;	/* high bit used for something else */
-
-	/* special case for 5x50 */
-	if (barker == I2400M_SBOOT_BARKER && module_id == 0)
-		return 1;
-	if (module_id == barker)
-		return 1;
-	return 0;
-}
-
-static
-const struct i2400m_bcf_hdr *i2400m_bcf_hdr_find(struct i2400m *i2400m)
-{
-	struct device *dev = i2400m_dev(i2400m);
-	const struct i2400m_bcf_hdr **bcf_itr, *bcf_hdr;
-	unsigned i = 0;
-	u32 barker = le32_to_cpu(i2400m->barker->data[0]);
-
-	d_printf(2, dev, "finding BCF header for barker %08x\n", barker);
-	if (barker == I2400M_NBOOT_BARKER) {
-		bcf_hdr = i2400m->fw_hdrs[0];
-		d_printf(1, dev, "using BCF header #%u/%08x for non-signed "
-			 "barker\n", 0, le32_to_cpu(bcf_hdr->module_id));
-		return bcf_hdr;
-	}
-	for (bcf_itr = i2400m->fw_hdrs; *bcf_itr != NULL; bcf_itr++, i++) {
-		bcf_hdr = *bcf_itr;
-		if (i2400m_bcf_hdr_match(i2400m, bcf_hdr)) {
-			d_printf(1, dev, "hit on BCF hdr #%u/%08x\n",
-				 i, le32_to_cpu(bcf_hdr->module_id));
-			return bcf_hdr;
-		} else
-			d_printf(1, dev, "miss on BCF hdr #%u/%08x\n",
-				 i, le32_to_cpu(bcf_hdr->module_id));
-	}
-	dev_err(dev, "cannot find a matching BCF header for barker %08x\n",
-		barker);
-	return NULL;
-}
-
-
-/*
- * Download the firmware to the device
- *
- * @i2400m: device descriptor
- * @bcf: pointer to loaded (and minimally verified for consistency)
- *    firmware
- * @bcf_size: size of the @bcf buffer (header plus payloads)
- *
- * The process for doing this is described in this file's header.
- *
- * Note we only reinitialize boot-mode if the flags say so. Some hw
- * iterations need it, some don't. In any case, if we loop, we always
- * need to reinitialize the boot room, hence the flags modification.
- */
-static
-int i2400m_fw_dnload(struct i2400m *i2400m, const struct i2400m_bcf_hdr *bcf,
-		     size_t fw_size, enum i2400m_bri flags)
-{
-	int ret = 0;
-	struct device *dev = i2400m_dev(i2400m);
-	int count = i2400m->bus_bm_retries;
-	const struct i2400m_bcf_hdr *bcf_hdr;
-	size_t bcf_size;
-
-	d_fnstart(5, dev, "(i2400m %p bcf %p fw size %zu)\n",
-		  i2400m, bcf, fw_size);
-	i2400m->boot_mode = 1;
-	wmb();		/* Make sure other readers see it */
-hw_reboot:
-	if (count-- == 0) {
-		ret = -ERESTARTSYS;
-		dev_err(dev, "device rebooted too many times, aborting\n");
-		goto error_too_many_reboots;
-	}
-	if (flags & I2400M_BRI_MAC_REINIT) {
-		ret = i2400m_bootrom_init(i2400m, flags);
-		if (ret < 0) {
-			dev_err(dev, "bootrom init failed: %d\n", ret);
-			goto error_bootrom_init;
-		}
-	}
-	flags |= I2400M_BRI_MAC_REINIT;
-
-	/*
-	 * Initialize the download, push the bytes to the device and
-	 * then jump to the new firmware. Note @ret is passed with the
-	 * offset of the jump instruction to _dnload_finalize()
-	 *
-	 * Note we need to use the BCF header in the firmware image
-	 * that matches the barker that the device sent when it
-	 * rebooted, so it has to be passed along.
-	 */
-	ret = -EBADF;
-	bcf_hdr = i2400m_bcf_hdr_find(i2400m);
-	if (bcf_hdr == NULL)
-		goto error_bcf_hdr_find;
-
-	ret = i2400m_dnload_init(i2400m, bcf_hdr);
-	if (ret == -ERESTARTSYS)
-		goto error_dev_rebooted;
-	if (ret < 0)
-		goto error_dnload_init;
-
-	/*
-	 * bcf_size refers to one header size plus the fw sections size
-	 * indicated by the header,ie. if there are other extended headers
-	 * at the tail, they are not counted
-	 */
-	bcf_size = sizeof(u32) * le32_to_cpu(bcf_hdr->size);
-	ret = i2400m_dnload_bcf(i2400m, bcf, bcf_size);
-	if (ret == -ERESTARTSYS)
-		goto error_dev_rebooted;
-	if (ret < 0) {
-		dev_err(dev, "fw %s: download failed: %d\n",
-			i2400m->fw_name, ret);
-		goto error_dnload_bcf;
-	}
-
-	ret = i2400m_dnload_finalize(i2400m, bcf_hdr, bcf, ret);
-	if (ret == -ERESTARTSYS)
-		goto error_dev_rebooted;
-	if (ret < 0) {
-		dev_err(dev, "fw %s: "
-			"download finalization failed: %d\n",
-			i2400m->fw_name, ret);
-		goto error_dnload_finalize;
-	}
-
-	d_printf(2, dev, "fw %s successfully uploaded\n",
-		 i2400m->fw_name);
-	i2400m->boot_mode = 0;
-	wmb();		/* Make sure i2400m_msg_to_dev() sees boot_mode */
-error_dnload_finalize:
-error_dnload_bcf:
-error_dnload_init:
-error_bcf_hdr_find:
-error_bootrom_init:
-error_too_many_reboots:
-	d_fnend(5, dev, "(i2400m %p bcf %p size %zu) = %d\n",
-		i2400m, bcf, fw_size, ret);
-	return ret;
-
-error_dev_rebooted:
-	dev_err(dev, "device rebooted, %d tries left\n", count);
-	/* we got the notification already, no need to wait for it again */
-	flags |= I2400M_BRI_SOFT;
-	goto hw_reboot;
-}
-
-static
-int i2400m_fw_bootstrap(struct i2400m *i2400m, const struct firmware *fw,
-			enum i2400m_bri flags)
-{
-	int ret;
-	struct device *dev = i2400m_dev(i2400m);
-	const struct i2400m_bcf_hdr *bcf;	/* Firmware data */
-
-	d_fnstart(5, dev, "(i2400m %p)\n", i2400m);
-	bcf = (void *) fw->data;
-	ret = i2400m_fw_check(i2400m, bcf, fw->size);
-	if (ret >= 0)
-		ret = i2400m_fw_dnload(i2400m, bcf, fw->size, flags);
-	if (ret < 0)
-		dev_err(dev, "%s: cannot use: %d, skipping\n",
-			i2400m->fw_name, ret);
-	kfree(i2400m->fw_hdrs);
-	i2400m->fw_hdrs = NULL;
-	d_fnend(5, dev, "(i2400m %p) = %d\n", i2400m, ret);
-	return ret;
-}
-
-
-/* Refcounted container for firmware data */
-struct i2400m_fw {
-	struct kref kref;
-	const struct firmware *fw;
-};
-
-
-static
-void i2400m_fw_destroy(struct kref *kref)
-{
-	struct i2400m_fw *i2400m_fw =
-		container_of(kref, struct i2400m_fw, kref);
-	release_firmware(i2400m_fw->fw);
-	kfree(i2400m_fw);
-}
-
-
-static
-struct i2400m_fw *i2400m_fw_get(struct i2400m_fw *i2400m_fw)
-{
-	if (i2400m_fw != NULL && i2400m_fw != (void *) ~0)
-		kref_get(&i2400m_fw->kref);
-	return i2400m_fw;
-}
-
-
-static
-void i2400m_fw_put(struct i2400m_fw *i2400m_fw)
-{
-	kref_put(&i2400m_fw->kref, i2400m_fw_destroy);
-}
-
-
-/**
- * i2400m_dev_bootstrap - Bring the device to a known state and upload firmware
- *
- * @i2400m: device descriptor
- *
- * Returns: >= 0 if ok, < 0 errno code on error.
- *
- * This sets up the firmware upload environment, loads the firmware
- * file from disk, verifies and then calls the firmware upload process
- * per se.
- *
- * Can be called either from probe, or after a warm reset.  Can not be
- * called from within an interrupt.  All the flow in this code is
- * single-threade; all I/Os are synchronous.
- */
-int i2400m_dev_bootstrap(struct i2400m *i2400m, enum i2400m_bri flags)
-{
-	int ret, itr;
-	struct device *dev = i2400m_dev(i2400m);
-	struct i2400m_fw *i2400m_fw;
-	const struct firmware *fw;
-	const char *fw_name;
-
-	d_fnstart(5, dev, "(i2400m %p)\n", i2400m);
-
-	ret = -ENODEV;
-	spin_lock(&i2400m->rx_lock);
-	i2400m_fw = i2400m_fw_get(i2400m->fw_cached);
-	spin_unlock(&i2400m->rx_lock);
-	if (i2400m_fw == (void *) ~0) {
-		dev_err(dev, "can't load firmware now!");
-		goto out;
-	} else if (i2400m_fw != NULL) {
-		dev_info(dev, "firmware %s: loading from cache\n",
-			 i2400m->fw_name);
-		ret = i2400m_fw_bootstrap(i2400m, i2400m_fw->fw, flags);
-		i2400m_fw_put(i2400m_fw);
-		goto out;
-	}
-
-	/* Load firmware files to memory. */
-	for (itr = 0, ret = -ENOENT; ; itr++) {
-		fw_name = i2400m->bus_fw_names[itr];
-		if (fw_name == NULL) {
-			dev_err(dev, "Could not find a usable firmware image\n");
-			break;
-		}
-		d_printf(1, dev, "trying firmware %s (%d)\n", fw_name, itr);
-		ret = request_firmware(&fw, fw_name, dev);
-		if (ret < 0) {
-			dev_err(dev, "fw %s: cannot load file: %d\n",
-				fw_name, ret);
-			continue;
-		}
-		i2400m->fw_name = fw_name;
-		ret = i2400m_fw_bootstrap(i2400m, fw, flags);
-		release_firmware(fw);
-		if (ret >= 0)	/* firmware loaded successfully */
-			break;
-		i2400m->fw_name = NULL;
-	}
-out:
-	d_fnend(5, dev, "(i2400m %p) = %d\n", i2400m, ret);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(i2400m_dev_bootstrap);
-
-
-void i2400m_fw_cache(struct i2400m *i2400m)
-{
-	int result;
-	struct i2400m_fw *i2400m_fw;
-	struct device *dev = i2400m_dev(i2400m);
-
-	/* if there is anything there, free it -- now, this'd be weird */
-	spin_lock(&i2400m->rx_lock);
-	i2400m_fw = i2400m->fw_cached;
-	spin_unlock(&i2400m->rx_lock);
-	if (i2400m_fw != NULL && i2400m_fw != (void *) ~0) {
-		i2400m_fw_put(i2400m_fw);
-		WARN(1, "%s:%u: still cached fw still present?\n",
-		     __func__, __LINE__);
-	}
-
-	if (i2400m->fw_name == NULL) {
-		dev_err(dev, "firmware n/a: can't cache\n");
-		i2400m_fw = (void *) ~0;
-		goto out;
-	}
-
-	i2400m_fw = kzalloc(sizeof(*i2400m_fw), GFP_ATOMIC);
-	if (i2400m_fw == NULL)
-		goto out;
-	kref_init(&i2400m_fw->kref);
-	result = request_firmware(&i2400m_fw->fw, i2400m->fw_name, dev);
-	if (result < 0) {
-		dev_err(dev, "firmware %s: failed to cache: %d\n",
-			i2400m->fw_name, result);
-		kfree(i2400m_fw);
-		i2400m_fw = (void *) ~0;
-	} else
-		dev_info(dev, "firmware %s: cached\n", i2400m->fw_name);
-out:
-	spin_lock(&i2400m->rx_lock);
-	i2400m->fw_cached = i2400m_fw;
-	spin_unlock(&i2400m->rx_lock);
-}
-
-
-void i2400m_fw_uncache(struct i2400m *i2400m)
-{
-	struct i2400m_fw *i2400m_fw;
-
-	spin_lock(&i2400m->rx_lock);
-	i2400m_fw = i2400m->fw_cached;
-	i2400m->fw_cached = NULL;
-	spin_unlock(&i2400m->rx_lock);
-
-	if (i2400m_fw != NULL && i2400m_fw != (void *) ~0)
-		i2400m_fw_put(i2400m_fw);
-}
-
diff --git a/drivers/net/wimax/i2400m/i2400m-usb.h b/drivers/net/wimax/i2400m/i2400m-usb.h
deleted file mode 100644
index eff4f464a23e..000000000000
--- a/drivers/net/wimax/i2400m/i2400m-usb.h
+++ /dev/null
@@ -1,275 +0,0 @@
-/*
- * Intel Wireless WiMAX Connection 2400m
- * USB-specific i2400m driver definitions
- *
- *
- * Copyright (C) 2007-2008 Intel Corporation. All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- *   * Redistributions of source code must retain the above copyright
- *     notice, this list of conditions and the following disclaimer.
- *   * Redistributions in binary form must reproduce the above copyright
- *     notice, this list of conditions and the following disclaimer in
- *     the documentation and/or other materials provided with the
- *     distribution.
- *   * Neither the name of Intel Corporation nor the names of its
- *     contributors may be used to endorse or promote products derived
- *     from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- * Yanir Lubetkin <yanirx.lubetkin@intel.com>
- *  - Initial implementation
- *
- *
- * This driver implements the bus-specific part of the i2400m for
- * USB. Check i2400m.h for a generic driver description.
- *
- * ARCHITECTURE
- *
- * This driver listens to notifications sent from the notification
- * endpoint (in usb-notif.c); when data is ready to read, the code in
- * there schedules a read from the device (usb-rx.c) and then passes
- * the data to the generic RX code (rx.c).
- *
- * When the generic driver needs to send data (network or control), it
- * queues up in the TX FIFO (tx.c) and that will notify the driver
- * through the i2400m->bus_tx_kick() callback
- * (usb-tx.c:i2400mu_bus_tx_kick) which will send the items in the
- * FIFO queue.
- *
- * This driver, as well, implements the USB-specific ops for the generic
- * driver to be able to setup/teardown communication with the device
- * [i2400m_bus_dev_start() and i2400m_bus_dev_stop()], reseting the
- * device [i2400m_bus_reset()] and performing firmware upload
- * [i2400m_bus_bm_cmd() and i2400_bus_bm_wait_for_ack()].
- */
-
-#ifndef __I2400M_USB_H__
-#define __I2400M_USB_H__
-
-#include "i2400m.h"
-#include <linux/kthread.h>
-
-
-/*
- * Error Density Count: cheapo error density (over time) counter
- *
- * Originally by Reinette Chatre <reinette.chatre@intel.com>
- *
- * Embed an 'struct edc' somewhere. Each time there is a soft or
- * retryable error, call edc_inc() and check if the error top
- * watermark has been reached.
- */
-enum {
-	EDC_MAX_ERRORS = 10,
-	EDC_ERROR_TIMEFRAME = HZ,
-};
-
-/* error density counter */
-struct edc {
-	unsigned long timestart;
-	u16 errorcount;
-};
-
-struct i2400m_endpoint_cfg {
-	unsigned char bulk_out;
-	unsigned char notification;
-	unsigned char reset_cold;
-	unsigned char bulk_in;
-};
-
-static inline void edc_init(struct edc *edc)
-{
-	edc->timestart = jiffies;
-}
-
-/**
- * edc_inc - report a soft error and check if we are over the watermark
- *
- * @edc: pointer to error density counter.
- * @max_err: maximum number of errors we can accept over the timeframe
- * @timeframe: length of the timeframe (in jiffies).
- *
- * Returns: !0 1 if maximum acceptable errors per timeframe has been
- *     exceeded. 0 otherwise.
- *
- * This is way to determine if the number of acceptable errors per time
- * period has been exceeded. It is not accurate as there are cases in which
- * this scheme will not work, for example if there are periodic occurrences
- * of errors that straddle updates to the start time. This scheme is
- * sufficient for our usage.
- *
- * To use, embed a 'struct edc' somewhere, initialize it with
- * edc_init() and when an error hits:
- *
- * if (do_something_fails_with_a_soft_error) {
- *        if (edc_inc(&my->edc, MAX_ERRORS, MAX_TIMEFRAME))
- * 	           Ops, hard error, do something about it
- *        else
- *                 Retry or ignore, depending on whatever
- * }
- */
-static inline int edc_inc(struct edc *edc, u16 max_err, u16 timeframe)
-{
-	unsigned long now;
-
-	now = jiffies;
-	if (time_after(now, edc->timestart + timeframe)) {
-		edc->errorcount = 1;
-		edc->timestart = now;
-	} else if (++edc->errorcount > max_err) {
-		edc->errorcount = 0;
-		edc->timestart = now;
-		return 1;
-	}
-	return 0;
-}
-
-/* Host-Device interface for USB */
-enum {
-	I2400M_USB_BOOT_RETRIES = 3,
-	I2400MU_MAX_NOTIFICATION_LEN = 256,
-	I2400MU_BLK_SIZE = 16,
-	I2400MU_PL_SIZE_MAX = 0x3EFF,
-
-	/* Device IDs */
-	USB_DEVICE_ID_I6050 = 0x0186,
-	USB_DEVICE_ID_I6050_2 = 0x0188,
-	USB_DEVICE_ID_I6150 = 0x07d6,
-	USB_DEVICE_ID_I6150_2 = 0x07d7,
-	USB_DEVICE_ID_I6150_3 = 0x07d9,
-	USB_DEVICE_ID_I6250 = 0x0187,
-};
-
-
-/**
- * struct i2400mu - descriptor for a USB connected i2400m
- *
- * @i2400m: bus-generic i2400m implementation; has to be first (see
- *     it's documentation in i2400m.h).
- *
- * @usb_dev: pointer to our USB device
- *
- * @usb_iface: pointer to our USB interface
- *
- * @urb_edc: error density counter; used to keep a density-on-time tab
- *     on how many soft (retryable or ignorable) errors we get. If we
- *     go over the threshold, we consider the bus transport is failing
- *     too much and reset.
- *
- * @notif_urb: URB for receiving notifications from the device.
- *
- * @tx_kthread: thread we use for data TX. We use a thread because in
- *     order to do deep power saving and put the device to sleep, we
- *     need to call usb_autopm_*() [blocking functions].
- *
- * @tx_wq: waitqueue for the TX kthread to sleep when there is no data
- *     to be sent; when more data is available, it is woken up by
- *     i2400mu_bus_tx_kick().
- *
- * @rx_kthread: thread we use for data RX. We use a thread because in
- *     order to do deep power saving and put the device to sleep, we
- *     need to call usb_autopm_*() [blocking functions].
- *
- * @rx_wq: waitqueue for the RX kthread to sleep when there is no data
- *     to receive. When data is available, it is woken up by
- *     usb-notif.c:i2400mu_notification_grok().
- *
- * @rx_pending_count: number of rx-data-ready notifications that were
- *     still not handled by the RX kthread.
- *
- * @rx_size: current RX buffer size that is being used.
- *
- * @rx_size_acc: accumulator of the sizes of the previous read
- *     transactions.
- *
- * @rx_size_cnt: number of read transactions accumulated in
- *     @rx_size_acc.
- *
- * @do_autopm: disable(0)/enable(>0) calling the
- *     usb_autopm_get/put_interface() barriers when executing
- *     commands. See doc in i2400mu_suspend() for more information.
- *
- * @rx_size_auto_shrink: if true, the rx_size is shrunk
- *     automatically based on the average size of the received
- *     transactions. This allows the receive code to allocate smaller
- *     chunks of memory and thus reduce pressure on the memory
- *     allocator by not wasting so much space. By default it is
- *     enabled.
- *
- * @debugfs_dentry: hookup for debugfs files.
- *     These have to be in a separate directory, a child of
- *     (wimax_dev->debugfs_dentry) so they can be removed when the
- *     module unloads, as we don't keep each dentry.
- */
-struct i2400mu {
-	struct i2400m i2400m;		/* FIRST! See doc */
-
-	struct usb_device *usb_dev;
-	struct usb_interface *usb_iface;
-	struct edc urb_edc;		/* Error density counter */
-	struct i2400m_endpoint_cfg endpoint_cfg;
-
-	struct urb *notif_urb;
-	struct task_struct *tx_kthread;
-	wait_queue_head_t tx_wq;
-
-	struct task_struct *rx_kthread;
-	wait_queue_head_t rx_wq;
-	atomic_t rx_pending_count;
-	size_t rx_size, rx_size_acc, rx_size_cnt;
-	atomic_t do_autopm;
-	u8 rx_size_auto_shrink;
-
-	struct dentry *debugfs_dentry;
-	unsigned i6050:1;	/* 1 if this is a 6050 based SKU */
-};
-
-
-static inline
-void i2400mu_init(struct i2400mu *i2400mu)
-{
-	i2400m_init(&i2400mu->i2400m);
-	edc_init(&i2400mu->urb_edc);
-	init_waitqueue_head(&i2400mu->tx_wq);
-	atomic_set(&i2400mu->rx_pending_count, 0);
-	init_waitqueue_head(&i2400mu->rx_wq);
-	i2400mu->rx_size = PAGE_SIZE - sizeof(struct skb_shared_info);
-	atomic_set(&i2400mu->do_autopm, 1);
-	i2400mu->rx_size_auto_shrink = 1;
-}
-
-int i2400mu_notification_setup(struct i2400mu *);
-void i2400mu_notification_release(struct i2400mu *);
-
-int i2400mu_rx_setup(struct i2400mu *);
-void i2400mu_rx_release(struct i2400mu *);
-void i2400mu_rx_kick(struct i2400mu *);
-
-int i2400mu_tx_setup(struct i2400mu *);
-void i2400mu_tx_release(struct i2400mu *);
-void i2400mu_bus_tx_kick(struct i2400m *);
-
-ssize_t i2400mu_bus_bm_cmd_send(struct i2400m *,
-				const struct i2400m_bootrom_header *, size_t,
-				int);
-ssize_t i2400mu_bus_bm_wait_for_ack(struct i2400m *,
-				    struct i2400m_bootrom_header *, size_t);
-#endif /* #ifndef __I2400M_USB_H__ */
diff --git a/drivers/net/wimax/i2400m/i2400m.h b/drivers/net/wimax/i2400m/i2400m.h
deleted file mode 100644
index a3733a6d14f5..000000000000
--- a/drivers/net/wimax/i2400m/i2400m.h
+++ /dev/null
@@ -1,970 +0,0 @@
-/*
- * Intel Wireless WiMAX Connection 2400m
- * Declarations for bus-generic internal APIs
- *
- *
- * Copyright (C) 2007-2008 Intel Corporation. All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- *   * Redistributions of source code must retain the above copyright
- *     notice, this list of conditions and the following disclaimer.
- *   * Redistributions in binary form must reproduce the above copyright
- *     notice, this list of conditions and the following disclaimer in
- *     the documentation and/or other materials provided with the
- *     distribution.
- *   * Neither the name of Intel Corporation nor the names of its
- *     contributors may be used to endorse or promote products derived
- *     from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- * Yanir Lubetkin <yanirx.lubetkin@intel.com>
- *  - Initial implementation
- *
- *
- * GENERAL DRIVER ARCHITECTURE
- *
- * The i2400m driver is split in the following two major parts:
- *
- *  - bus specific driver
- *  - bus generic driver (this part)
- *
- * The bus specific driver sets up stuff specific to the bus the
- * device is connected to (USB, PCI, tam-tam...non-authoritative
- * nor binding list) which is basically the device-model management
- * (probe/disconnect, etc), moving data from device to kernel and
- * back, doing the power saving details and reseting the device.
- *
- * For details on each bus-specific driver, see it's include file,
- * i2400m-BUSNAME.h
- *
- * The bus-generic functionality break up is:
- *
- *  - Firmware upload: fw.c - takes care of uploading firmware to the
- *        device. bus-specific driver just needs to provides a way to
- *        execute boot-mode commands and to reset the device.
- *
- *  - RX handling: rx.c - receives data from the bus-specific code and
- *        feeds it to the network or WiMAX stack or uses it to modify
- *        the driver state. bus-specific driver only has to receive
- *        frames and pass them to this module.
- *
- *  - TX handling: tx.c - manages the TX FIFO queue and provides means
- *        for the bus-specific TX code to pull data from the FIFO
- *        queue. bus-specific code just pulls frames from this module
- *        to sends them to the device.
- *
- *  - netdev glue: netdev.c - interface with Linux networking
- *        stack. Pass around data frames, and configure when the
- *        device is up and running or shutdown (through ifconfig up /
- *        down). Bus-generic only.
- *
- *  - control ops: control.c - implements various commands for
- *        controlling the device. bus-generic only.
- *
- *  - device model glue: driver.c - implements helpers for the
- *        device-model glue done by the bus-specific layer
- *        (setup/release the driver resources), turning the device on
- *        and off, handling the device reboots/resets and a few simple
- *        WiMAX stack ops.
- *
- * Code is also broken up in linux-glue / device-glue.
- *
- * Linux glue contains functions that deal mostly with gluing with the
- * rest of the Linux kernel.
- *
- * Device-glue are functions that deal mostly with the way the device
- * does things and talk the device's language.
- *
- * device-glue code is licensed BSD so other open source OSes can take
- * it to implement their drivers.
- *
- *
- * APIs AND HEADER FILES
- *
- * This bus generic code exports three APIs:
- *
- *  - HDI (host-device interface) definitions common to all busses
- *    (include/linux/wimax/i2400m.h); these can be also used by user
- *    space code.
- *  - internal API for the bus-generic code
- *  - external API for the bus-specific drivers
- *
- *
- * LIFE CYCLE:
- *
- * When the bus-specific driver probes, it allocates a network device
- * with enough space for it's data structue, that must contain a
- * &struct i2400m at the top.
- *
- * On probe, it needs to fill the i2400m members marked as [fill], as
- * well as i2400m->wimax_dev.net_dev and call i2400m_setup(). The
- * i2400m driver will only register with the WiMAX and network stacks;
- * the only access done to the device is to read the MAC address so we
- * can register a network device.
- *
- * The high-level call flow is:
- *
- * bus_probe()
- *   i2400m_setup()
- *     i2400m->bus_setup()
- *     boot rom initialization / read mac addr
- *     network / WiMAX stacks registration
- *     i2400m_dev_start()
- *       i2400m->bus_dev_start()
- *       i2400m_dev_initialize()
- *
- * The reverse applies for a disconnect() call:
- *
- * bus_disconnect()
- *   i2400m_release()
- *     i2400m_dev_stop()
- *       i2400m_dev_shutdown()
- *       i2400m->bus_dev_stop()
- *     network / WiMAX stack unregistration
- *     i2400m->bus_release()
- *
- * At this point, control and data communications are possible.
- *
- * While the device is up, it might reset. The bus-specific driver has
- * to catch that situation and call i2400m_dev_reset_handle() to deal
- * with it (reset the internal driver structures and go back to square
- * one).
- */
-
-#ifndef __I2400M_H__
-#define __I2400M_H__
-
-#include <linux/usb.h>
-#include <linux/netdevice.h>
-#include <linux/completion.h>
-#include <linux/rwsem.h>
-#include <linux/atomic.h>
-#include <net/wimax.h>
-#include <linux/wimax/i2400m.h>
-#include <asm/byteorder.h>
-
-enum {
-/* netdev interface */
-	/*
-	 * Out of NWG spec (R1_v1.2.2), 3.3.3 ASN Bearer Plane MTU Size
-	 *
-	 * The MTU is 1400 or less
-	 */
-	I2400M_MAX_MTU = 1400,
-};
-
-/* Misc constants */
-enum {
-	/* Size of the Boot Mode Command buffer */
-	I2400M_BM_CMD_BUF_SIZE = 16 * 1024,
-	I2400M_BM_ACK_BUF_SIZE = 256,
-};
-
-enum {
-	/* Maximum number of bus reset can be retried */
-	I2400M_BUS_RESET_RETRIES = 3,
-};
-
-/**
- * struct i2400m_poke_table - Hardware poke table for the Intel 2400m
- *
- * This structure will be used to create a device specific poke table
- * to put the device in a consistent state at boot time.
- *
- * @address: The device address to poke
- *
- * @data: The data value to poke to the device address
- *
- */
-struct i2400m_poke_table{
-	__le32 address;
-	__le32 data;
-};
-
-#define I2400M_FW_POKE(a, d) {		\
-	.address = cpu_to_le32(a),	\
-	.data = cpu_to_le32(d)		\
-}
-
-
-/**
- * i2400m_reset_type - methods to reset a device
- *
- * @I2400M_RT_WARM: Reset without device disconnection, device handles
- *     are kept valid but state is back to power on, with firmware
- *     re-uploaded.
- * @I2400M_RT_COLD: Tell the device to disconnect itself from the bus
- *     and reconnect. Renders all device handles invalid.
- * @I2400M_RT_BUS: Tells the bus to reset the device; last measure
- *     used when both types above don't work.
- */
-enum i2400m_reset_type {
-	I2400M_RT_WARM,	/* first measure */
-	I2400M_RT_COLD,	/* second measure */
-	I2400M_RT_BUS,	/* call in artillery */
-};
-
-struct i2400m_reset_ctx;
-struct i2400m_roq;
-struct i2400m_barker_db;
-
-/**
- * struct i2400m - descriptor for an Intel 2400m
- *
- * Members marked with [fill] must be filled out/initialized before
- * calling i2400m_setup().
- *
- * Note the @bus_setup/@bus_release, @bus_dev_start/@bus_dev_release
- * call pairs are very much doing almost the same, and depending on
- * the underlying bus, some stuff has to be put in one or the
- * other. The idea of setup/release is that they setup the minimal
- * amount needed for loading firmware, where us dev_start/stop setup
- * the rest needed to do full data/control traffic.
- *
- * @bus_tx_block_size: [fill] USB imposes a 16 block size, but other
- *     busses will differ.  So we have a tx_blk_size variable that the
- *     bus layer sets to tell the engine how much of that we need.
- *
- * @bus_tx_room_min: [fill] Minimum room required while allocating
- *     TX queue's buffer space for message header. USB requires
- *     16 bytes. Refer to bus specific driver code for details.
- *
- * @bus_pl_size_max: [fill] Maximum payload size.
- *
- * @bus_setup: [optional fill] Function called by the bus-generic code
- *     [i2400m_setup()] to setup the basic bus-specific communications
- *     to the the device needed to load firmware. See LIFE CYCLE above.
- *
- *     NOTE: Doesn't need to upload the firmware, as that is taken
- *     care of by the bus-generic code.
- *
- * @bus_release: [optional fill] Function called by the bus-generic
- *     code [i2400m_release()] to shutdown the basic bus-specific
- *     communications to the the device needed to load firmware. See
- *     LIFE CYCLE above.
- *
- *     This function does not need to reset the device, just tear down
- *     all the host resources created to  handle communication with
- *     the device.
- *
- * @bus_dev_start: [optional fill] Function called by the bus-generic
- *     code [i2400m_dev_start()] to do things needed to start the
- *     device. See LIFE CYCLE above.
- *
- *     NOTE: Doesn't need to upload the firmware, as that is taken
- *     care of by the bus-generic code.
- *
- * @bus_dev_stop: [optional fill] Function called by the bus-generic
- *     code [i2400m_dev_stop()] to do things needed for stopping the
- *     device. See LIFE CYCLE above.
- *
- *     This function does not need to reset the device, just tear down
- *     all the host resources created to handle communication with
- *     the device.
- *
- * @bus_tx_kick: [fill] Function called by the bus-generic code to let
- *     the bus-specific code know that there is data available in the
- *     TX FIFO for transmission to the device.
- *
- *     This function cannot sleep.
- *
- * @bus_reset: [fill] Function called by the bus-generic code to reset
- *     the device in in various ways. Doesn't need to wait for the
- *     reset to finish.
- *
- *     If warm or cold reset fail, this function is expected to do a
- *     bus-specific reset (eg: USB reset) to get the device to a
- *     working state (even if it implies device disconecction).
- *
- *     Note the warm reset is used by the firmware uploader to
- *     reinitialize the device.
- *
- *     IMPORTANT: this is called very early in the device setup
- *     process, so it cannot rely on common infrastructure being laid
- *     out.
- *
- *     IMPORTANT: don't call reset on RT_BUS with i2400m->init_mutex
- *     held, as the .pre/.post reset handlers will deadlock.
- *
- * @bus_bm_retries: [fill] How many times shall a firmware upload /
- *     device initialization be retried? Different models of the same
- *     device might need different values, hence it is set by the
- *     bus-specific driver. Note this value is used in two places,
- *     i2400m_fw_dnload() and __i2400m_dev_start(); they won't become
- *     multiplicative (__i2400m_dev_start() calling N times
- *     i2400m_fw_dnload() and this trying N times to download the
- *     firmware), as if __i2400m_dev_start() only retries if the
- *     firmware crashed while initializing the device (not in a
- *     general case).
- *
- * @bus_bm_cmd_send: [fill] Function called to send a boot-mode
- *     command. Flags are defined in 'enum i2400m_bm_cmd_flags'. This
- *     is synchronous and has to return 0 if ok or < 0 errno code in
- *     any error condition.
- *
- * @bus_bm_wait_for_ack: [fill] Function called to wait for a
- *     boot-mode notification (that can be a response to a previously
- *     issued command or an asynchronous one). Will read until all the
- *     indicated size is read or timeout. Reading more or less data
- *     than asked for is an error condition. Return 0 if ok, < 0 errno
- *     code on error.
- *
- *     The caller to this function will check if the response is a
- *     barker that indicates the device going into reset mode.
- *
- * @bus_fw_names: [fill] a NULL-terminated array with the names of the
- *     firmware images to try loading. This is made a list so we can
- *     support backward compatibility of firmware releases (eg: if we
- *     can't find the default v1.4, we try v1.3). In general, the name
- *     should be i2400m-fw-X-VERSION.sbcf, where X is the bus name.
- *     The list is tried in order and the first one that loads is
- *     used. The fw loader will set i2400m->fw_name to point to the
- *     active firmware image.
- *
- * @bus_bm_mac_addr_impaired: [fill] Set to true if the device's MAC
- *     address provided in boot mode is kind of broken and needs to
- *     be re-read later on.
- *
- * @bus_bm_pokes_table: [fill/optional] A table of device addresses
- *     and values that will be poked at device init time to move the
- *     device to the correct state for the type of boot/firmware being
- *     used.  This table MUST be terminated with (0x000000,
- *     0x00000000) or bad things will happen.
- *
- *
- * @wimax_dev: WiMAX generic device for linkage into the kernel WiMAX
- *     stack. Due to the way a net_device is allocated, we need to
- *     force this to be the first field so that we can get from
- *     netdev_priv() the right pointer.
- *
- * @updown: the device is up and ready for transmitting control and
- *     data packets. This implies @ready (communication infrastructure
- *     with the device is ready) and the device's firmware has been
- *     loaded and the device initialized.
- *
- *     Write to it only inside a i2400m->init_mutex protected area
- *     followed with a wmb(); rmb() before accesing (unless locked
- *     inside i2400m->init_mutex). Read access can be loose like that
- *     [just using rmb()] because the paths that use this also do
- *     other error checks later on.
- *
- * @ready: Communication infrastructure with the device is ready, data
- *     frames can start to be passed around (this is lighter than
- *     using the WiMAX state for certain hot paths).
- *
- *     Write to it only inside a i2400m->init_mutex protected area
- *     followed with a wmb(); rmb() before accesing (unless locked
- *     inside i2400m->init_mutex). Read access can be loose like that
- *     [just using rmb()] because the paths that use this also do
- *     other error checks later on.
- *
- * @rx_reorder: 1 if RX reordering is enabled; this can only be
- *     set at probe time.
- *
- * @state: device's state (as reported by it)
- *
- * @state_wq: waitqueue that is woken up whenever the state changes
- *
- * @tx_lock: spinlock to protect TX members
- *
- * @tx_buf: FIFO buffer for TX; we queue data here
- *
- * @tx_in: FIFO index for incoming data. Note this doesn't wrap around
- *     and it is always greater than @tx_out.
- *
- * @tx_out: FIFO index for outgoing data
- *
- * @tx_msg: current TX message that is active in the FIFO for
- *     appending payloads.
- *
- * @tx_sequence: current sequence number for TX messages from the
- *     device to the host.
- *
- * @tx_msg_size: size of the current message being transmitted by the
- *     bus-specific code.
- *
- * @tx_pl_num: total number of payloads sent
- *
- * @tx_pl_max: maximum number of payloads sent in a TX message
- *
- * @tx_pl_min: minimum number of payloads sent in a TX message
- *
- * @tx_num: number of TX messages sent
- *
- * @tx_size_acc: number of bytes in all TX messages sent
- *     (this is different to net_dev's statistics as it also counts
- *     control messages).
- *
- * @tx_size_min: smallest TX message sent.
- *
- * @tx_size_max: biggest TX message sent.
- *
- * @rx_lock: spinlock to protect RX members and rx_roq_refcount.
- *
- * @rx_pl_num: total number of payloads received
- *
- * @rx_pl_max: maximum number of payloads received in a RX message
- *
- * @rx_pl_min: minimum number of payloads received in a RX message
- *
- * @rx_num: number of RX messages received
- *
- * @rx_size_acc: number of bytes in all RX messages received
- *     (this is different to net_dev's statistics as it also counts
- *     control messages).
- *
- * @rx_size_min: smallest RX message received.
- *
- * @rx_size_max: buggest RX message received.
- *
- * @rx_roq: RX ReOrder queues. (fw >= v1.4) When packets are received
- *     out of order, the device will ask the driver to hold certain
- *     packets until the ones that are received out of order can be
- *     delivered. Then the driver can release them to the host. See
- *     drivers/net/i2400m/rx.c for details.
- *
- * @rx_roq_refcount: refcount rx_roq. This refcounts any access to
- *     rx_roq thus preventing rx_roq being destroyed when rx_roq
- *     is being accessed. rx_roq_refcount is protected by rx_lock.
- *
- * @rx_reports: reports received from the device that couldn't be
- *     processed because the driver wasn't still ready; when ready,
- *     they are pulled from here and chewed.
- *
- * @rx_reports_ws: Work struct used to kick a scan of the RX reports
- *     list and to process each.
- *
- * @src_mac_addr: MAC address used to make ethernet packets be coming
- *     from. This is generated at i2400m_setup() time and used during
- *     the life cycle of the instance. See i2400m_fake_eth_header().
- *
- * @init_mutex: Mutex used for serializing the device bringup
- *     sequence; this way if the device reboots in the middle, we
- *     don't try to do a bringup again while we are tearing down the
- *     one that failed.
- *
- *     Can't reuse @msg_mutex because from within the bringup sequence
- *     we need to send messages to the device and thus use @msg_mutex.
- *
- * @msg_mutex: mutex used to send control commands to the device (we
- *     only allow one at a time, per host-device interface design).
- *
- * @msg_completion: used to wait for an ack to a control command sent
- *     to the device.
- *
- * @ack_skb: used to store the actual ack to a control command if the
- *     reception of the command was successful. Otherwise, a ERR_PTR()
- *     errno code that indicates what failed with the ack reception.
- *
- *     Only valid after @msg_completion is woken up. Only updateable
- *     if @msg_completion is armed. Only touched by
- *     i2400m_msg_to_dev().
- *
- *     Protected by @rx_lock. In theory the command execution flow is
- *     sequential, but in case the device sends an out-of-phase or
- *     very delayed response, we need to avoid it trampling current
- *     execution.
- *
- * @bm_cmd_buf: boot mode command buffer for composing firmware upload
- *     commands.
- *
- *     USB can't r/w to stack, vmalloc, etc...as well, we end up
- *     having to alloc/free a lot to compose commands, so we use these
- *     for stagging and not having to realloc all the time.
- *
- *     This assumes the code always runs serialized. Only one thread
- *     can call i2400m_bm_cmd() at the same time.
- *
- * @bm_ack_buf: boot mode acknoledge buffer for staging reception of
- *     responses to commands.
- *
- *     See @bm_cmd_buf.
- *
- * @work_queue: work queue for processing device reports. This
- *     workqueue cannot be used for processing TX or RX to the device,
- *     as from it we'll process device reports, which might require
- *     further communication with the device.
- *
- * @debugfs_dentry: hookup for debugfs files.
- *     These have to be in a separate directory, a child of
- *     (wimax_dev->debugfs_dentry) so they can be removed when the
- *     module unloads, as we don't keep each dentry.
- *
- * @fw_name: name of the firmware image that is currently being used.
- *
- * @fw_version: version of the firmware interface, Major.minor,
- *     encoded in the high word and low word (major << 16 | minor).
- *
- * @fw_hdrs: NULL terminated array of pointers to the firmware
- *     headers. This is only available during firmware load time.
- *
- * @fw_cached: Used to cache firmware when the system goes to
- *     suspend/standby/hibernation (as on resume we can't read it). If
- *     NULL, no firmware was cached, read it. If ~0, you can't read
- *     any firmware files (the system still didn't come out of suspend
- *     and failed to cache one), so abort; otherwise, a valid cached
- *     firmware to be used. Access to this variable is protected by
- *     the spinlock i2400m->rx_lock.
- *
- * @barker: barker type that the device uses; this is initialized by
- *     i2400m_is_boot_barker() the first time it is called. Then it
- *     won't change during the life cycle of the device and every time
- *     a boot barker is received, it is just verified for it being the
- *     same.
- *
- * @pm_notifier: used to register for PM events
- *
- * @bus_reset_retries: counter for the number of bus resets attempted for
- *	this boot. It's not for tracking the number of bus resets during
- *	the whole driver life cycle (from insmod to rmmod) but for the
- *	number of dev_start() executed until dev_start() returns a success
- *	(ie: a good boot means a dev_stop() followed by a successful
- *	dev_start()). dev_reset_handler() increments this counter whenever
- *	it is triggering a bus reset. It checks this counter to decide if a
- *	subsequent bus reset should be retried. dev_reset_handler() retries
- *	the bus reset until dev_start() succeeds or the counter reaches
- *	I2400M_BUS_RESET_RETRIES. The counter is cleared to 0 in
- *	dev_reset_handle() when dev_start() returns a success,
- *	ie: a successul boot is completed.
- *
- * @alive: flag to denote if the device *should* be alive. This flag is
- *	everything like @updown (see doc for @updown) except reflecting
- *	the device state *we expect* rather than the actual state as denoted
- *	by @updown. It is set 1 whenever @updown is set 1 in dev_start().
- *	Then the device is expected to be alive all the time
- *	(i2400m->alive remains 1) until the driver is removed. Therefore
- *	all the device reboot events detected can be still handled properly
- *	by either dev_reset_handle() or .pre_reset/.post_reset as long as
- *	the driver presents. It is set 0 along with @updown in dev_stop().
- *
- * @error_recovery: flag to denote if we are ready to take an error recovery.
- *	0 for ready to take an error recovery; 1 for not ready. It is
- *	initialized to 1 while probe() since we don't tend to take any error
- *	recovery during probe(). It is decremented by 1 whenever dev_start()
- *	succeeds to indicate we are ready to take error recovery from now on.
- *	It is checked every time we wanna schedule an error recovery. If an
- *	error recovery is already in place (error_recovery was set 1), we
- *	should not schedule another one until the last one is done.
- */
-struct i2400m {
-	struct wimax_dev wimax_dev;	/* FIRST! See doc */
-
-	unsigned updown:1;		/* Network device is up or down */
-	unsigned boot_mode:1;		/* is the device in boot mode? */
-	unsigned sboot:1;		/* signed or unsigned fw boot */
-	unsigned ready:1;		/* Device comm infrastructure ready */
-	unsigned rx_reorder:1;		/* RX reorder is enabled */
-	u8 trace_msg_from_user;		/* echo rx msgs to 'trace' pipe */
-					/* typed u8 so /sys/kernel/debug/u8 can tweak */
-	enum i2400m_system_state state;
-	wait_queue_head_t state_wq;	/* Woken up when on state updates */
-
-	size_t bus_tx_block_size;
-	size_t bus_tx_room_min;
-	size_t bus_pl_size_max;
-	unsigned bus_bm_retries;
-
-	int (*bus_setup)(struct i2400m *);
-	int (*bus_dev_start)(struct i2400m *);
-	void (*bus_dev_stop)(struct i2400m *);
-	void (*bus_release)(struct i2400m *);
-	void (*bus_tx_kick)(struct i2400m *);
-	int (*bus_reset)(struct i2400m *, enum i2400m_reset_type);
-	ssize_t (*bus_bm_cmd_send)(struct i2400m *,
-				   const struct i2400m_bootrom_header *,
-				   size_t, int flags);
-	ssize_t (*bus_bm_wait_for_ack)(struct i2400m *,
-				       struct i2400m_bootrom_header *, size_t);
-	const char **bus_fw_names;
-	unsigned bus_bm_mac_addr_impaired:1;
-	const struct i2400m_poke_table *bus_bm_pokes_table;
-
-	spinlock_t tx_lock;		/* protect TX state */
-	void *tx_buf;
-	size_t tx_in, tx_out;
-	struct i2400m_msg_hdr *tx_msg;
-	size_t tx_sequence, tx_msg_size;
-	/* TX stats */
-	unsigned tx_pl_num, tx_pl_max, tx_pl_min,
-		tx_num, tx_size_acc, tx_size_min, tx_size_max;
-
-	/* RX stuff */
-	/* protect RX state and rx_roq_refcount */
-	spinlock_t rx_lock;
-	unsigned rx_pl_num, rx_pl_max, rx_pl_min,
-		rx_num, rx_size_acc, rx_size_min, rx_size_max;
-	struct i2400m_roq *rx_roq;	/* access is refcounted */
-	struct kref rx_roq_refcount;	/* refcount access to rx_roq */
-	u8 src_mac_addr[ETH_HLEN];
-	struct list_head rx_reports;	/* under rx_lock! */
-	struct work_struct rx_report_ws;
-
-	struct mutex msg_mutex;		/* serialize command execution */
-	struct completion msg_completion;
-	struct sk_buff *ack_skb;	/* protected by rx_lock */
-
-	void *bm_ack_buf;		/* for receiving acks over USB */
-	void *bm_cmd_buf;		/* for issuing commands over USB */
-
-	struct workqueue_struct *work_queue;
-
-	struct mutex init_mutex;	/* protect bringup seq */
-	struct i2400m_reset_ctx *reset_ctx;	/* protected by init_mutex */
-
-	struct work_struct wake_tx_ws;
-	struct sk_buff *wake_tx_skb;
-
-	struct work_struct reset_ws;
-	const char *reset_reason;
-
-	struct work_struct recovery_ws;
-
-	struct dentry *debugfs_dentry;
-	const char *fw_name;		/* name of the current firmware image */
-	unsigned long fw_version;	/* version of the firmware interface */
-	const struct i2400m_bcf_hdr **fw_hdrs;
-	struct i2400m_fw *fw_cached;	/* protected by rx_lock */
-	struct i2400m_barker_db *barker;
-
-	struct notifier_block pm_notifier;
-
-	/* counting bus reset retries in this boot */
-	atomic_t bus_reset_retries;
-
-	/* if the device is expected to be alive */
-	unsigned alive;
-
-	/* 0 if we are ready for error recovery; 1 if not ready  */
-	atomic_t error_recovery;
-
-};
-
-
-/*
- * Bus-generic internal APIs
- * -------------------------
- */
-
-static inline
-struct i2400m *wimax_dev_to_i2400m(struct wimax_dev *wimax_dev)
-{
-	return container_of(wimax_dev, struct i2400m, wimax_dev);
-}
-
-static inline
-struct i2400m *net_dev_to_i2400m(struct net_device *net_dev)
-{
-	return wimax_dev_to_i2400m(netdev_priv(net_dev));
-}
-
-/*
- * Boot mode support
- */
-
-/**
- * i2400m_bm_cmd_flags - flags to i2400m_bm_cmd()
- *
- * @I2400M_BM_CMD_RAW: send the command block as-is, without doing any
- *     extra processing for adding CRC.
- */
-enum i2400m_bm_cmd_flags {
-	I2400M_BM_CMD_RAW	= 1 << 2,
-};
-
-/**
- * i2400m_bri - Boot-ROM indicators
- *
- * Flags for i2400m_bootrom_init() and i2400m_dev_bootstrap() [which
- * are passed from things like i2400m_setup()]. Can be combined with
- * |.
- *
- * @I2400M_BRI_SOFT: The device rebooted already and a reboot
- *     barker received, proceed directly to ack the boot sequence.
- * @I2400M_BRI_NO_REBOOT: Do not reboot the device and proceed
- *     directly to wait for a reboot barker from the device.
- * @I2400M_BRI_MAC_REINIT: We need to reinitialize the boot
- *     rom after reading the MAC address. This is quite a dirty hack,
- *     if you ask me -- the device requires the bootrom to be
- *     initialized after reading the MAC address.
- */
-enum i2400m_bri {
-	I2400M_BRI_SOFT       = 1 << 1,
-	I2400M_BRI_NO_REBOOT  = 1 << 2,
-	I2400M_BRI_MAC_REINIT = 1 << 3,
-};
-
-void i2400m_bm_cmd_prepare(struct i2400m_bootrom_header *);
-int i2400m_dev_bootstrap(struct i2400m *, enum i2400m_bri);
-int i2400m_read_mac_addr(struct i2400m *);
-int i2400m_bootrom_init(struct i2400m *, enum i2400m_bri);
-int i2400m_is_boot_barker(struct i2400m *, const void *, size_t);
-static inline
-int i2400m_is_d2h_barker(const void *buf)
-{
-	const __le32 *barker = buf;
-	return le32_to_cpu(*barker) == I2400M_D2H_MSG_BARKER;
-}
-void i2400m_unknown_barker(struct i2400m *, const void *, size_t);
-
-/* Make/grok boot-rom header commands */
-
-static inline
-__le32 i2400m_brh_command(enum i2400m_brh_opcode opcode, unsigned use_checksum,
-			  unsigned direct_access)
-{
-	return cpu_to_le32(
-		I2400M_BRH_SIGNATURE
-		| (direct_access ? I2400M_BRH_DIRECT_ACCESS : 0)
-		| I2400M_BRH_RESPONSE_REQUIRED /* response always required */
-		| (use_checksum ? I2400M_BRH_USE_CHECKSUM : 0)
-		| (opcode & I2400M_BRH_OPCODE_MASK));
-}
-
-static inline
-void i2400m_brh_set_opcode(struct i2400m_bootrom_header *hdr,
-			   enum i2400m_brh_opcode opcode)
-{
-	hdr->command = cpu_to_le32(
-		(le32_to_cpu(hdr->command) & ~I2400M_BRH_OPCODE_MASK)
-		| (opcode & I2400M_BRH_OPCODE_MASK));
-}
-
-static inline
-unsigned i2400m_brh_get_opcode(const struct i2400m_bootrom_header *hdr)
-{
-	return le32_to_cpu(hdr->command) & I2400M_BRH_OPCODE_MASK;
-}
-
-static inline
-unsigned i2400m_brh_get_response(const struct i2400m_bootrom_header *hdr)
-{
-	return (le32_to_cpu(hdr->command) & I2400M_BRH_RESPONSE_MASK)
-		>> I2400M_BRH_RESPONSE_SHIFT;
-}
-
-static inline
-unsigned i2400m_brh_get_use_checksum(const struct i2400m_bootrom_header *hdr)
-{
-	return le32_to_cpu(hdr->command) & I2400M_BRH_USE_CHECKSUM;
-}
-
-static inline
-unsigned i2400m_brh_get_response_required(
-	const struct i2400m_bootrom_header *hdr)
-{
-	return le32_to_cpu(hdr->command) & I2400M_BRH_RESPONSE_REQUIRED;
-}
-
-static inline
-unsigned i2400m_brh_get_direct_access(const struct i2400m_bootrom_header *hdr)
-{
-	return le32_to_cpu(hdr->command) & I2400M_BRH_DIRECT_ACCESS;
-}
-
-static inline
-unsigned i2400m_brh_get_signature(const struct i2400m_bootrom_header *hdr)
-{
-	return (le32_to_cpu(hdr->command) & I2400M_BRH_SIGNATURE_MASK)
-		>> I2400M_BRH_SIGNATURE_SHIFT;
-}
-
-
-/*
- * Driver / device setup and internal functions
- */
-void i2400m_init(struct i2400m *);
-int i2400m_reset(struct i2400m *, enum i2400m_reset_type);
-void i2400m_netdev_setup(struct net_device *net_dev);
-int i2400m_sysfs_setup(struct device_driver *);
-void i2400m_sysfs_release(struct device_driver *);
-int i2400m_tx_setup(struct i2400m *);
-void i2400m_wake_tx_work(struct work_struct *);
-void i2400m_tx_release(struct i2400m *);
-
-int i2400m_rx_setup(struct i2400m *);
-void i2400m_rx_release(struct i2400m *);
-
-void i2400m_fw_cache(struct i2400m *);
-void i2400m_fw_uncache(struct i2400m *);
-
-void i2400m_net_rx(struct i2400m *, struct sk_buff *, unsigned, const void *,
-		   int);
-void i2400m_net_erx(struct i2400m *, struct sk_buff *, enum i2400m_cs);
-void i2400m_net_wake_stop(struct i2400m *);
-enum i2400m_pt;
-int i2400m_tx(struct i2400m *, const void *, size_t, enum i2400m_pt);
-
-#ifdef CONFIG_DEBUG_FS
-void i2400m_debugfs_add(struct i2400m *);
-void i2400m_debugfs_rm(struct i2400m *);
-#else
-static inline void i2400m_debugfs_add(struct i2400m *i2400m) {}
-static inline void i2400m_debugfs_rm(struct i2400m *i2400m) {}
-#endif
-
-/* Initialize/shutdown the device */
-int i2400m_dev_initialize(struct i2400m *);
-void i2400m_dev_shutdown(struct i2400m *);
-
-extern struct attribute_group i2400m_dev_attr_group;
-
-
-/* HDI message's payload description handling */
-
-static inline
-size_t i2400m_pld_size(const struct i2400m_pld *pld)
-{
-	return I2400M_PLD_SIZE_MASK & le32_to_cpu(pld->val);
-}
-
-static inline
-enum i2400m_pt i2400m_pld_type(const struct i2400m_pld *pld)
-{
-	return (I2400M_PLD_TYPE_MASK & le32_to_cpu(pld->val))
-		>> I2400M_PLD_TYPE_SHIFT;
-}
-
-static inline
-void i2400m_pld_set(struct i2400m_pld *pld, size_t size,
-		    enum i2400m_pt type)
-{
-	pld->val = cpu_to_le32(
-		((type << I2400M_PLD_TYPE_SHIFT) & I2400M_PLD_TYPE_MASK)
-		|  (size & I2400M_PLD_SIZE_MASK));
-}
-
-
-/*
- * API for the bus-specific drivers
- * --------------------------------
- */
-
-static inline
-struct i2400m *i2400m_get(struct i2400m *i2400m)
-{
-	dev_hold(i2400m->wimax_dev.net_dev);
-	return i2400m;
-}
-
-static inline
-void i2400m_put(struct i2400m *i2400m)
-{
-	dev_put(i2400m->wimax_dev.net_dev);
-}
-
-int i2400m_dev_reset_handle(struct i2400m *, const char *);
-int i2400m_pre_reset(struct i2400m *);
-int i2400m_post_reset(struct i2400m *);
-void i2400m_error_recovery(struct i2400m *);
-
-/*
- * _setup()/_release() are called by the probe/disconnect functions of
- * the bus-specific drivers.
- */
-int i2400m_setup(struct i2400m *, enum i2400m_bri bm_flags);
-void i2400m_release(struct i2400m *);
-
-int i2400m_rx(struct i2400m *, struct sk_buff *);
-struct i2400m_msg_hdr *i2400m_tx_msg_get(struct i2400m *, size_t *);
-void i2400m_tx_msg_sent(struct i2400m *);
-
-
-/*
- * Utility functions
- */
-
-static inline
-struct device *i2400m_dev(struct i2400m *i2400m)
-{
-	return i2400m->wimax_dev.net_dev->dev.parent;
-}
-
-int i2400m_msg_check_status(const struct i2400m_l3l4_hdr *, char *, size_t);
-int i2400m_msg_size_check(struct i2400m *, const struct i2400m_l3l4_hdr *,
-			  size_t);
-struct sk_buff *i2400m_msg_to_dev(struct i2400m *, const void *, size_t);
-void i2400m_msg_to_dev_cancel_wait(struct i2400m *, int);
-void i2400m_report_hook(struct i2400m *, const struct i2400m_l3l4_hdr *,
-			size_t);
-void i2400m_report_hook_work(struct work_struct *);
-int i2400m_cmd_enter_powersave(struct i2400m *);
-int i2400m_cmd_exit_idle(struct i2400m *);
-struct sk_buff *i2400m_get_device_info(struct i2400m *);
-int i2400m_firmware_check(struct i2400m *);
-int i2400m_set_idle_timeout(struct i2400m *, unsigned);
-
-static inline
-struct usb_endpoint_descriptor *usb_get_epd(struct usb_interface *iface, int ep)
-{
-	return &iface->cur_altsetting->endpoint[ep].desc;
-}
-
-int i2400m_op_rfkill_sw_toggle(struct wimax_dev *, enum wimax_rf_state);
-void i2400m_report_tlv_rf_switches_status(struct i2400m *,
-					  const struct i2400m_tlv_rf_switches_status *);
-
-/*
- * Helpers for firmware backwards compatibility
- *
- * As we aim to support at least the firmware version that was
- * released with the previous kernel/driver release, some code will be
- * conditionally executed depending on the firmware version. On each
- * release, the code to support fw releases past the last two ones
- * will be purged.
- *
- * By making it depend on this macros, it is easier to keep it a tab
- * on what has to go and what not.
- */
-static inline
-unsigned i2400m_le_v1_3(struct i2400m *i2400m)
-{
-	/* running fw is lower or v1.3 */
-	return i2400m->fw_version <= 0x00090001;
-}
-
-static inline
-unsigned i2400m_ge_v1_4(struct i2400m *i2400m)
-{
-	/* running fw is higher or v1.4 */
-	return i2400m->fw_version >= 0x00090002;
-}
-
-
-/*
- * Do a millisecond-sleep for allowing wireshark to dump all the data
- * packets. Used only for debugging.
- */
-static inline
-void __i2400m_msleep(unsigned ms)
-{
-#if 1
-#else
-	msleep(ms);
-#endif
-}
-
-
-/* module initialization helpers */
-int i2400m_barker_db_init(const char *);
-void i2400m_barker_db_exit(void);
-
-
-
-#endif /* #ifndef __I2400M_H__ */
diff --git a/drivers/net/wimax/i2400m/netdev.c b/drivers/net/wimax/i2400m/netdev.c
deleted file mode 100644
index a7fcbceb6e6b..000000000000
--- a/drivers/net/wimax/i2400m/netdev.c
+++ /dev/null
@@ -1,603 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel Wireless WiMAX Connection 2400m
- * Glue with the networking stack
- *
- * Copyright (C) 2007 Intel Corporation <linux-wimax@intel.com>
- * Yanir Lubetkin <yanirx.lubetkin@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * This implements an ethernet device for the i2400m.
- *
- * We fake being an ethernet device to simplify the support from user
- * space and from the other side. The world is (sadly) configured to
- * take in only Ethernet devices...
- *
- * Because of this, when using firmwares <= v1.3, there is an
- * copy-each-rxed-packet overhead on the RX path. Each IP packet has
- * to be reallocated to add an ethernet header (as there is no space
- * in what we get from the device). This is a known drawback and
- * firmwares >= 1.4 add header space that can be used to insert the
- * ethernet header without having to reallocate and copy.
- *
- * TX error handling is tricky; because we have to FIFO/queue the
- * buffers for transmission (as the hardware likes it aggregated), we
- * just give the skb to the TX subsystem and by the time it is
- * transmitted, we have long forgotten about it. So we just don't care
- * too much about it.
- *
- * Note that when the device is in idle mode with the basestation, we
- * need to negotiate coming back up online. That involves negotiation
- * and possible user space interaction. Thus, we defer to a workqueue
- * to do all that. By default, we only queue a single packet and drop
- * the rest, as potentially the time to go back from idle to normal is
- * long.
- *
- * ROADMAP
- *
- * i2400m_open         Called on ifconfig up
- * i2400m_stop         Called on ifconfig down
- *
- * i2400m_hard_start_xmit Called by the network stack to send a packet
- *   i2400m_net_wake_tx	  Wake up device from basestation-IDLE & TX
- *     i2400m_wake_tx_work
- *       i2400m_cmd_exit_idle
- *       i2400m_tx
- *   i2400m_net_tx        TX a data frame
- *     i2400m_tx
- *
- * i2400m_change_mtu      Called on ifconfig mtu XXX
- *
- * i2400m_tx_timeout      Called when the device times out
- *
- * i2400m_net_rx          Called by the RX code when a data frame is
- *                        available (firmware <= 1.3)
- * i2400m_net_erx         Called by the RX code when a data frame is
- *                        available (firmware >= 1.4).
- * i2400m_netdev_setup    Called to setup all the netdev stuff from
- *                        alloc_netdev.
- */
-#include <linux/if_arp.h>
-#include <linux/slab.h>
-#include <linux/netdevice.h>
-#include <linux/ethtool.h>
-#include <linux/export.h>
-#include "i2400m.h"
-
-
-#define D_SUBMODULE netdev
-#include "debug-levels.h"
-
-enum {
-/* netdev interface */
-	/* 20 secs? yep, this is the maximum timeout that the device
-	 * might take to get out of IDLE / negotiate it with the base
-	 * station. We add 1sec for good measure. */
-	I2400M_TX_TIMEOUT = 21 * HZ,
-	/*
-	 * Experimentation has determined that, 20 to be a good value
-	 * for minimizing the jitter in the throughput.
-	 */
-	I2400M_TX_QLEN = 20,
-};
-
-
-static
-int i2400m_open(struct net_device *net_dev)
-{
-	int result;
-	struct i2400m *i2400m = net_dev_to_i2400m(net_dev);
-	struct device *dev = i2400m_dev(i2400m);
-
-	d_fnstart(3, dev, "(net_dev %p [i2400m %p])\n", net_dev, i2400m);
-	/* Make sure we wait until init is complete... */
-	mutex_lock(&i2400m->init_mutex);
-	if (i2400m->updown)
-		result = 0;
-	else
-		result = -EBUSY;
-	mutex_unlock(&i2400m->init_mutex);
-	d_fnend(3, dev, "(net_dev %p [i2400m %p]) = %d\n",
-		net_dev, i2400m, result);
-	return result;
-}
-
-
-static
-int i2400m_stop(struct net_device *net_dev)
-{
-	struct i2400m *i2400m = net_dev_to_i2400m(net_dev);
-	struct device *dev = i2400m_dev(i2400m);
-
-	d_fnstart(3, dev, "(net_dev %p [i2400m %p])\n", net_dev, i2400m);
-	i2400m_net_wake_stop(i2400m);
-	d_fnend(3, dev, "(net_dev %p [i2400m %p]) = 0\n", net_dev, i2400m);
-	return 0;
-}
-
-
-/*
- * Wake up the device and transmit a held SKB, then restart the net queue
- *
- * When the device goes into basestation-idle mode, we need to tell it
- * to exit that mode; it will negotiate with the base station, user
- * space may have to intervene to rehandshake crypto and then tell us
- * when it is ready to transmit the packet we have "queued". Still we
- * need to give it sometime after it reports being ok.
- *
- * On error, there is not much we can do. If the error was on TX, we
- * still wake the queue up to see if the next packet will be luckier.
- *
- * If _cmd_exit_idle() fails...well, it could be many things; most
- * commonly it is that something else took the device out of IDLE mode
- * (for example, the base station). In that case we get an -EILSEQ and
- * we are just going to ignore that one. If the device is back to
- * connected, then fine -- if it is someother state, the packet will
- * be dropped anyway.
- */
-void i2400m_wake_tx_work(struct work_struct *ws)
-{
-	int result;
-	struct i2400m *i2400m = container_of(ws, struct i2400m, wake_tx_ws);
-	struct net_device *net_dev = i2400m->wimax_dev.net_dev;
-	struct device *dev = i2400m_dev(i2400m);
-	struct sk_buff *skb;
-	unsigned long flags;
-
-	spin_lock_irqsave(&i2400m->tx_lock, flags);
-	skb = i2400m->wake_tx_skb;
-	i2400m->wake_tx_skb = NULL;
-	spin_unlock_irqrestore(&i2400m->tx_lock, flags);
-
-	d_fnstart(3, dev, "(ws %p i2400m %p skb %p)\n", ws, i2400m, skb);
-	result = -EINVAL;
-	if (skb == NULL) {
-		dev_err(dev, "WAKE&TX: skb disappeared!\n");
-		goto out_put;
-	}
-	/* If we have, somehow, lost the connection after this was
-	 * queued, don't do anything; this might be the device got
-	 * reset or just disconnected. */
-	if (unlikely(!netif_carrier_ok(net_dev)))
-		goto out_kfree;
-	result = i2400m_cmd_exit_idle(i2400m);
-	if (result == -EILSEQ)
-		result = 0;
-	if (result < 0) {
-		dev_err(dev, "WAKE&TX: device didn't get out of idle: "
-			"%d - resetting\n", result);
-		i2400m_reset(i2400m, I2400M_RT_BUS);
-		goto error;
-	}
-	result = wait_event_timeout(i2400m->state_wq,
-				    i2400m->state != I2400M_SS_IDLE,
-				    net_dev->watchdog_timeo - HZ/2);
-	if (result == 0)
-		result = -ETIMEDOUT;
-	if (result < 0) {
-		dev_err(dev, "WAKE&TX: error waiting for device to exit IDLE: "
-			"%d - resetting\n", result);
-		i2400m_reset(i2400m, I2400M_RT_BUS);
-		goto error;
-	}
-	msleep(20);	/* device still needs some time or it drops it */
-	result = i2400m_tx(i2400m, skb->data, skb->len, I2400M_PT_DATA);
-error:
-	netif_wake_queue(net_dev);
-out_kfree:
-	kfree_skb(skb);	/* refcount transferred by _hard_start_xmit() */
-out_put:
-	i2400m_put(i2400m);
-	d_fnend(3, dev, "(ws %p i2400m %p skb %p) = void [%d]\n",
-		ws, i2400m, skb, result);
-}
-
-
-/*
- * Prepare the data payload TX header
- *
- * The i2400m expects a 4 byte header in front of a data packet.
- *
- * Because we pretend to be an ethernet device, this packet comes with
- * an ethernet header. Pull it and push our header.
- */
-static
-void i2400m_tx_prep_header(struct sk_buff *skb)
-{
-	struct i2400m_pl_data_hdr *pl_hdr;
-	skb_pull(skb, ETH_HLEN);
-	pl_hdr = skb_push(skb, sizeof(*pl_hdr));
-	pl_hdr->reserved = 0;
-}
-
-
-
-/*
- * Cleanup resources acquired during i2400m_net_wake_tx()
- *
- * This is called by __i2400m_dev_stop and means we have to make sure
- * the workqueue is flushed from any pending work.
- */
-void i2400m_net_wake_stop(struct i2400m *i2400m)
-{
-	struct device *dev = i2400m_dev(i2400m);
-	struct sk_buff *wake_tx_skb;
-	unsigned long flags;
-
-	d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
-	/*
-	 * See i2400m_hard_start_xmit(), references are taken there and
-	 * here we release them if the packet was still pending.
-	 */
-	cancel_work_sync(&i2400m->wake_tx_ws);
-
-	spin_lock_irqsave(&i2400m->tx_lock, flags);
-	wake_tx_skb = i2400m->wake_tx_skb;
-	i2400m->wake_tx_skb = NULL;
-	spin_unlock_irqrestore(&i2400m->tx_lock, flags);
-
-	if (wake_tx_skb) {
-		i2400m_put(i2400m);
-		kfree_skb(wake_tx_skb);
-	}
-
-	d_fnend(3, dev, "(i2400m %p) = void\n", i2400m);
-}
-
-
-/*
- * TX an skb to an idle device
- *
- * When the device is in basestation-idle mode, we need to wake it up
- * and then TX. So we queue a work_struct for doing so.
- *
- * We need to get an extra ref for the skb (so it is not dropped), as
- * well as be careful not to queue more than one request (won't help
- * at all). If more than one request comes or there are errors, we
- * just drop the packets (see i2400m_hard_start_xmit()).
- */
-static
-int i2400m_net_wake_tx(struct i2400m *i2400m, struct net_device *net_dev,
-		       struct sk_buff *skb)
-{
-	int result;
-	struct device *dev = i2400m_dev(i2400m);
-	unsigned long flags;
-
-	d_fnstart(3, dev, "(skb %p net_dev %p)\n", skb, net_dev);
-	if (net_ratelimit()) {
-		d_printf(3, dev, "WAKE&NETTX: "
-			 "skb %p sending %d bytes to radio\n",
-			 skb, skb->len);
-		d_dump(4, dev, skb->data, skb->len);
-	}
-	/* We hold a ref count for i2400m and skb, so when
-	 * stopping() the device, we need to cancel that work
-	 * and if pending, release those resources. */
-	result = 0;
-	spin_lock_irqsave(&i2400m->tx_lock, flags);
-	if (!i2400m->wake_tx_skb) {
-		netif_stop_queue(net_dev);
-		i2400m_get(i2400m);
-		i2400m->wake_tx_skb = skb_get(skb);	/* transfer ref count */
-		i2400m_tx_prep_header(skb);
-		result = schedule_work(&i2400m->wake_tx_ws);
-		WARN_ON(result == 0);
-	}
-	spin_unlock_irqrestore(&i2400m->tx_lock, flags);
-	if (result == 0) {
-		/* Yes, this happens even if we stopped the
-		 * queue -- blame the queue disciplines that
-		 * queue without looking -- I guess there is a reason
-		 * for that. */
-		if (net_ratelimit())
-			d_printf(1, dev, "NETTX: device exiting idle, "
-				 "dropping skb %p, queue running %d\n",
-				 skb, netif_queue_stopped(net_dev));
-		result = -EBUSY;
-	}
-	d_fnend(3, dev, "(skb %p net_dev %p) = %d\n", skb, net_dev, result);
-	return result;
-}
-
-
-/*
- * Transmit a packet to the base station on behalf of the network stack.
- *
- * Returns: 0 if ok, < 0 errno code on error.
- *
- * We need to pull the ethernet header and add the hardware header,
- * which is currently set to all zeroes and reserved.
- */
-static
-int i2400m_net_tx(struct i2400m *i2400m, struct net_device *net_dev,
-		  struct sk_buff *skb)
-{
-	int result;
-	struct device *dev = i2400m_dev(i2400m);
-
-	d_fnstart(3, dev, "(i2400m %p net_dev %p skb %p)\n",
-		  i2400m, net_dev, skb);
-	/* FIXME: check eth hdr, only IPv4 is routed by the device as of now */
-	netif_trans_update(net_dev);
-	i2400m_tx_prep_header(skb);
-	d_printf(3, dev, "NETTX: skb %p sending %d bytes to radio\n",
-		 skb, skb->len);
-	d_dump(4, dev, skb->data, skb->len);
-	result = i2400m_tx(i2400m, skb->data, skb->len, I2400M_PT_DATA);
-	d_fnend(3, dev, "(i2400m %p net_dev %p skb %p) = %d\n",
-		i2400m, net_dev, skb, result);
-	return result;
-}
-
-
-/*
- * Transmit a packet to the base station on behalf of the network stack
- *
- *
- * Returns: NETDEV_TX_OK (always, even in case of error)
- *
- * In case of error, we just drop it. Reasons:
- *
- *  - we add a hw header to each skb, and if the network stack
- *    retries, we have no way to know if that skb has it or not.
- *
- *  - network protocols have their own drop-recovery mechanisms
- *
- *  - there is not much else we can do
- *
- * If the device is idle, we need to wake it up; that is an operation
- * that will sleep. See i2400m_net_wake_tx() for details.
- */
-static
-netdev_tx_t i2400m_hard_start_xmit(struct sk_buff *skb,
-					 struct net_device *net_dev)
-{
-	struct i2400m *i2400m = net_dev_to_i2400m(net_dev);
-	struct device *dev = i2400m_dev(i2400m);
-	int result = -1;
-
-	d_fnstart(3, dev, "(skb %p net_dev %p)\n", skb, net_dev);
-
-	if (skb_cow_head(skb, 0))
-		goto drop;
-
-	if (i2400m->state == I2400M_SS_IDLE)
-		result = i2400m_net_wake_tx(i2400m, net_dev, skb);
-	else
-		result = i2400m_net_tx(i2400m, net_dev, skb);
-	if (result <  0) {
-drop:
-		net_dev->stats.tx_dropped++;
-	} else {
-		net_dev->stats.tx_packets++;
-		net_dev->stats.tx_bytes += skb->len;
-	}
-	dev_kfree_skb(skb);
-	d_fnend(3, dev, "(skb %p net_dev %p) = %d\n", skb, net_dev, result);
-	return NETDEV_TX_OK;
-}
-
-
-static
-void i2400m_tx_timeout(struct net_device *net_dev, unsigned int txqueue)
-{
-	/*
-	 * We might want to kick the device
-	 *
-	 * There is not much we can do though, as the device requires
-	 * that we send the data aggregated. By the time we receive
-	 * this, there might be data pending to be sent or not...
-	 */
-	net_dev->stats.tx_errors++;
-}
-
-
-/*
- * Create a fake ethernet header
- *
- * For emulating an ethernet device, every received IP header has to
- * be prefixed with an ethernet header. Fake it with the given
- * protocol.
- */
-static
-void i2400m_rx_fake_eth_header(struct net_device *net_dev,
-			       void *_eth_hdr, __be16 protocol)
-{
-	struct i2400m *i2400m = net_dev_to_i2400m(net_dev);
-	struct ethhdr *eth_hdr = _eth_hdr;
-
-	memcpy(eth_hdr->h_dest, net_dev->dev_addr, sizeof(eth_hdr->h_dest));
-	memcpy(eth_hdr->h_source, i2400m->src_mac_addr,
-	       sizeof(eth_hdr->h_source));
-	eth_hdr->h_proto = protocol;
-}
-
-
-/*
- * i2400m_net_rx - pass a network packet to the stack
- *
- * @i2400m: device instance
- * @skb_rx: the skb where the buffer pointed to by @buf is
- * @i: 1 if payload is the only one
- * @buf: pointer to the buffer containing the data
- * @len: buffer's length
- *
- * This is only used now for the v1.3 firmware. It will be deprecated
- * in >= 2.6.31.
- *
- * Note that due to firmware limitations, we don't have space to add
- * an ethernet header, so we need to copy each packet. Firmware
- * versions >= v1.4 fix this [see i2400m_net_erx()].
- *
- * We just clone the skb and set it up so that it's skb->data pointer
- * points to "buf" and it's length.
- *
- * Note that if the payload is the last (or the only one) in a
- * multi-payload message, we don't clone the SKB but just reuse it.
- *
- * This function is normally run from a thread context. However, we
- * still use netif_rx() instead of netif_receive_skb() as was
- * recommended in the mailing list. Reason is in some stress tests
- * when sending/receiving a lot of data we seem to hit a softlock in
- * the kernel's TCP implementation [aroudn tcp_delay_timer()]. Using
- * netif_rx() took care of the issue.
- *
- * This is, of course, still open to do more research on why running
- * with netif_receive_skb() hits this softlock. FIXME.
- *
- * FIXME: currently we don't do any efforts at distinguishing if what
- * we got was an IPv4 or IPv6 header, to setup the protocol field
- * correctly.
- */
-void i2400m_net_rx(struct i2400m *i2400m, struct sk_buff *skb_rx,
-		   unsigned i, const void *buf, int buf_len)
-{
-	struct net_device *net_dev = i2400m->wimax_dev.net_dev;
-	struct device *dev = i2400m_dev(i2400m);
-	struct sk_buff *skb;
-
-	d_fnstart(2, dev, "(i2400m %p buf %p buf_len %d)\n",
-		  i2400m, buf, buf_len);
-	if (i) {
-		skb = skb_get(skb_rx);
-		d_printf(2, dev, "RX: reusing first payload skb %p\n", skb);
-		skb_pull(skb, buf - (void *) skb->data);
-		skb_trim(skb, (void *) skb_end_pointer(skb) - buf);
-	} else {
-		/* Yes, this is bad -- a lot of overhead -- see
-		 * comments at the top of the file */
-		skb = __netdev_alloc_skb(net_dev, buf_len, GFP_KERNEL);
-		if (skb == NULL) {
-			dev_err(dev, "NETRX: no memory to realloc skb\n");
-			net_dev->stats.rx_dropped++;
-			goto error_skb_realloc;
-		}
-		skb_put_data(skb, buf, buf_len);
-	}
-	i2400m_rx_fake_eth_header(i2400m->wimax_dev.net_dev,
-				  skb->data - ETH_HLEN,
-				  cpu_to_be16(ETH_P_IP));
-	skb_set_mac_header(skb, -ETH_HLEN);
-	skb->dev = i2400m->wimax_dev.net_dev;
-	skb->protocol = htons(ETH_P_IP);
-	net_dev->stats.rx_packets++;
-	net_dev->stats.rx_bytes += buf_len;
-	d_printf(3, dev, "NETRX: receiving %d bytes to network stack\n",
-		buf_len);
-	d_dump(4, dev, buf, buf_len);
-	netif_rx_ni(skb);	/* see notes in function header */
-error_skb_realloc:
-	d_fnend(2, dev, "(i2400m %p buf %p buf_len %d) = void\n",
-		i2400m, buf, buf_len);
-}
-
-
-/*
- * i2400m_net_erx - pass a network packet to the stack (extended version)
- *
- * @i2400m: device descriptor
- * @skb: the skb where the packet is - the skb should be set to point
- *     at the IP packet; this function will add ethernet headers if
- *     needed.
- * @cs: packet type
- *
- * This is only used now for firmware >= v1.4. Note it is quite
- * similar to i2400m_net_rx() (used only for v1.3 firmware).
- *
- * This function is normally run from a thread context. However, we
- * still use netif_rx() instead of netif_receive_skb() as was
- * recommended in the mailing list. Reason is in some stress tests
- * when sending/receiving a lot of data we seem to hit a softlock in
- * the kernel's TCP implementation [aroudn tcp_delay_timer()]. Using
- * netif_rx() took care of the issue.
- *
- * This is, of course, still open to do more research on why running
- * with netif_receive_skb() hits this softlock. FIXME.
- */
-void i2400m_net_erx(struct i2400m *i2400m, struct sk_buff *skb,
-		    enum i2400m_cs cs)
-{
-	struct net_device *net_dev = i2400m->wimax_dev.net_dev;
-	struct device *dev = i2400m_dev(i2400m);
-
-	d_fnstart(2, dev, "(i2400m %p skb %p [%u] cs %d)\n",
-		  i2400m, skb, skb->len, cs);
-	switch(cs) {
-	case I2400M_CS_IPV4_0:
-	case I2400M_CS_IPV4:
-		i2400m_rx_fake_eth_header(i2400m->wimax_dev.net_dev,
-					  skb->data - ETH_HLEN,
-					  cpu_to_be16(ETH_P_IP));
-		skb_set_mac_header(skb, -ETH_HLEN);
-		skb->dev = i2400m->wimax_dev.net_dev;
-		skb->protocol = htons(ETH_P_IP);
-		net_dev->stats.rx_packets++;
-		net_dev->stats.rx_bytes += skb->len;
-		break;
-	default:
-		dev_err(dev, "ERX: BUG? CS type %u unsupported\n", cs);
-		goto error;
-
-	}
-	d_printf(3, dev, "ERX: receiving %d bytes to the network stack\n",
-		 skb->len);
-	d_dump(4, dev, skb->data, skb->len);
-	netif_rx_ni(skb);	/* see notes in function header */
-error:
-	d_fnend(2, dev, "(i2400m %p skb %p [%u] cs %d) = void\n",
-		i2400m, skb, skb->len, cs);
-}
-
-static const struct net_device_ops i2400m_netdev_ops = {
-	.ndo_open = i2400m_open,
-	.ndo_stop = i2400m_stop,
-	.ndo_start_xmit = i2400m_hard_start_xmit,
-	.ndo_tx_timeout = i2400m_tx_timeout,
-};
-
-static void i2400m_get_drvinfo(struct net_device *net_dev,
-			       struct ethtool_drvinfo *info)
-{
-	struct i2400m *i2400m = net_dev_to_i2400m(net_dev);
-
-	strlcpy(info->driver, KBUILD_MODNAME, sizeof(info->driver));
-	strlcpy(info->fw_version, i2400m->fw_name ? : "",
-		sizeof(info->fw_version));
-	if (net_dev->dev.parent)
-		strlcpy(info->bus_info, dev_name(net_dev->dev.parent),
-			sizeof(info->bus_info));
-}
-
-static const struct ethtool_ops i2400m_ethtool_ops = {
-	.get_drvinfo = i2400m_get_drvinfo,
-	.get_link = ethtool_op_get_link,
-};
-
-/**
- * i2400m_netdev_setup - Setup setup @net_dev's i2400m private data
- *
- * Called by alloc_netdev()
- */
-void i2400m_netdev_setup(struct net_device *net_dev)
-{
-	d_fnstart(3, NULL, "(net_dev %p)\n", net_dev);
-	ether_setup(net_dev);
-	net_dev->mtu = I2400M_MAX_MTU;
-	net_dev->min_mtu = 0;
-	net_dev->max_mtu = I2400M_MAX_MTU;
-	net_dev->tx_queue_len = I2400M_TX_QLEN;
-	net_dev->features =
-		  NETIF_F_VLAN_CHALLENGED
-		| NETIF_F_HIGHDMA;
-	net_dev->flags =
-		IFF_NOARP		/* i2400m is apure IP device */
-		& (~IFF_BROADCAST	/* i2400m is P2P */
-		   & ~IFF_MULTICAST);
-	net_dev->watchdog_timeo = I2400M_TX_TIMEOUT;
-	net_dev->netdev_ops = &i2400m_netdev_ops;
-	net_dev->ethtool_ops = &i2400m_ethtool_ops;
-	d_fnend(3, NULL, "(net_dev %p) = void\n", net_dev);
-}
-EXPORT_SYMBOL_GPL(i2400m_netdev_setup);
-
diff --git a/drivers/net/wimax/i2400m/op-rfkill.c b/drivers/net/wimax/i2400m/op-rfkill.c
deleted file mode 100644
index 5c79f052cad2..000000000000
--- a/drivers/net/wimax/i2400m/op-rfkill.c
+++ /dev/null
@@ -1,196 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel Wireless WiMAX Connection 2400m
- * Implement backend for the WiMAX stack rfkill support
- *
- * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * The WiMAX kernel stack integrates into RF-Kill and keeps the
- * switches's status. We just need to:
- *
- * - report changes in the HW RF Kill switch [with
- *   wimax_rfkill_{sw,hw}_report(), which happens when we detect those
- *   indications coming through hardware reports]. We also do it on
- *   initialization to let the stack know the initial HW state.
- *
- * - implement indications from the stack to change the SW RF Kill
- *   switch (coming from sysfs, the wimax stack or user space).
- */
-#include "i2400m.h"
-#include <linux/wimax/i2400m.h>
-#include <linux/slab.h>
-
-
-
-#define D_SUBMODULE rfkill
-#include "debug-levels.h"
-
-/*
- * Return true if the i2400m radio is in the requested wimax_rf_state state
- *
- */
-static
-int i2400m_radio_is(struct i2400m *i2400m, enum wimax_rf_state state)
-{
-	if (state == WIMAX_RF_OFF)
-		return i2400m->state == I2400M_SS_RF_OFF
-			|| i2400m->state == I2400M_SS_RF_SHUTDOWN;
-	else if (state == WIMAX_RF_ON)
-		/* state == WIMAX_RF_ON */
-		return i2400m->state != I2400M_SS_RF_OFF
-			&& i2400m->state != I2400M_SS_RF_SHUTDOWN;
-	else {
-		BUG();
-		return -EINVAL;	/* shut gcc warnings on certain arches */
-	}
-}
-
-
-/*
- * WiMAX stack operation: implement SW RFKill toggling
- *
- * @wimax_dev: device descriptor
- * @skb: skb where the message has been received; skb->data is
- *       expected to point to the message payload.
- * @genl_info: passed by the generic netlink layer
- *
- * Generic Netlink will call this function when a message is sent from
- * userspace to change the software RF-Kill switch status.
- *
- * This function will set the device's software RF-Kill switch state to
- * match what is requested.
- *
- * NOTE: the i2400m has a strict state machine; we can only set the
- *       RF-Kill switch when it is on, the HW RF-Kill is on and the
- *       device is initialized. So we ignore errors steaming from not
- *       being in the right state (-EILSEQ).
- */
-int i2400m_op_rfkill_sw_toggle(struct wimax_dev *wimax_dev,
-			       enum wimax_rf_state state)
-{
-	int result;
-	struct i2400m *i2400m = wimax_dev_to_i2400m(wimax_dev);
-	struct device *dev = i2400m_dev(i2400m);
-	struct sk_buff *ack_skb;
-	struct {
-		struct i2400m_l3l4_hdr hdr;
-		struct i2400m_tlv_rf_operation sw_rf;
-	} __packed *cmd;
-	char strerr[32];
-
-	d_fnstart(4, dev, "(wimax_dev %p state %d)\n", wimax_dev, state);
-
-	result = -ENOMEM;
-	cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
-	if (cmd == NULL)
-		goto error_alloc;
-	cmd->hdr.type = cpu_to_le16(I2400M_MT_CMD_RF_CONTROL);
-	cmd->hdr.length = sizeof(cmd->sw_rf);
-	cmd->hdr.version = cpu_to_le16(I2400M_L3L4_VERSION);
-	cmd->sw_rf.hdr.type = cpu_to_le16(I2400M_TLV_RF_OPERATION);
-	cmd->sw_rf.hdr.length = cpu_to_le16(sizeof(cmd->sw_rf.status));
-	switch (state) {
-	case WIMAX_RF_OFF:	/* RFKILL ON, radio OFF */
-		cmd->sw_rf.status = cpu_to_le32(2);
-		break;
-	case WIMAX_RF_ON:	/* RFKILL OFF, radio ON */
-		cmd->sw_rf.status = cpu_to_le32(1);
-		break;
-	default:
-		BUG();
-	}
-
-	ack_skb = i2400m_msg_to_dev(i2400m, cmd, sizeof(*cmd));
-	result = PTR_ERR(ack_skb);
-	if (IS_ERR(ack_skb)) {
-		dev_err(dev, "Failed to issue 'RF Control' command: %d\n",
-			result);
-		goto error_msg_to_dev;
-	}
-	result = i2400m_msg_check_status(wimax_msg_data(ack_skb),
-					 strerr, sizeof(strerr));
-	if (result < 0) {
-		dev_err(dev, "'RF Control' (0x%04x) command failed: %d - %s\n",
-			I2400M_MT_CMD_RF_CONTROL, result, strerr);
-		goto error_cmd;
-	}
-
-	/* Now we wait for the state to change to RADIO_OFF or RADIO_ON */
-	result = wait_event_timeout(
-		i2400m->state_wq, i2400m_radio_is(i2400m, state),
-		5 * HZ);
-	if (result == 0)
-		result = -ETIMEDOUT;
-	if (result < 0)
-		dev_err(dev, "Error waiting for device to toggle RF state: "
-			"%d\n", result);
-	result = 0;
-error_cmd:
-	kfree_skb(ack_skb);
-error_msg_to_dev:
-error_alloc:
-	d_fnend(4, dev, "(wimax_dev %p state %d) = %d\n",
-		wimax_dev, state, result);
-	kfree(cmd);
-	return result;
-}
-
-
-/*
- * Inform the WiMAX stack of changes in the RF Kill switches reported
- * by the device
- *
- * @i2400m: device descriptor
- * @rfss: TLV for RF Switches status; already validated
- *
- * NOTE: the reports on RF switch status cannot be trusted
- *       or used until the device is in a state of RADIO_OFF
- *       or greater.
- */
-void i2400m_report_tlv_rf_switches_status(
-	struct i2400m *i2400m,
-	const struct i2400m_tlv_rf_switches_status *rfss)
-{
-	struct device *dev = i2400m_dev(i2400m);
-	enum i2400m_rf_switch_status hw, sw;
-	enum wimax_st wimax_state;
-
-	sw = le32_to_cpu(rfss->sw_rf_switch);
-	hw = le32_to_cpu(rfss->hw_rf_switch);
-
-	d_fnstart(3, dev, "(i2400m %p rfss %p [hw %u sw %u])\n",
-		  i2400m, rfss, hw, sw);
-	/* We only process rw switch evens when the device has been
-	 * fully initialized */
-	wimax_state = wimax_state_get(&i2400m->wimax_dev);
-	if (wimax_state < WIMAX_ST_RADIO_OFF) {
-		d_printf(3, dev, "ignoring RF switches report, state %u\n",
-			 wimax_state);
-		goto out;
-	}
-	switch (sw) {
-	case I2400M_RF_SWITCH_ON:	/* RF Kill disabled (radio on) */
-		wimax_report_rfkill_sw(&i2400m->wimax_dev, WIMAX_RF_ON);
-		break;
-	case I2400M_RF_SWITCH_OFF:	/* RF Kill enabled (radio off) */
-		wimax_report_rfkill_sw(&i2400m->wimax_dev, WIMAX_RF_OFF);
-		break;
-	default:
-		dev_err(dev, "HW BUG? Unknown RF SW state 0x%x\n", sw);
-	}
-
-	switch (hw) {
-	case I2400M_RF_SWITCH_ON:	/* RF Kill disabled (radio on) */
-		wimax_report_rfkill_hw(&i2400m->wimax_dev, WIMAX_RF_ON);
-		break;
-	case I2400M_RF_SWITCH_OFF:	/* RF Kill enabled (radio off) */
-		wimax_report_rfkill_hw(&i2400m->wimax_dev, WIMAX_RF_OFF);
-		break;
-	default:
-		dev_err(dev, "HW BUG? Unknown RF HW state 0x%x\n", hw);
-	}
-out:
-	d_fnend(3, dev, "(i2400m %p rfss %p [hw %u sw %u]) = void\n",
-		i2400m, rfss, hw, sw);
-}
diff --git a/drivers/net/wimax/i2400m/rx.c b/drivers/net/wimax/i2400m/rx.c
deleted file mode 100644
index c9fb619a9e01..000000000000
--- a/drivers/net/wimax/i2400m/rx.c
+++ /dev/null
@@ -1,1395 +0,0 @@
-/*
- * Intel Wireless WiMAX Connection 2400m
- * Handle incoming traffic and deliver it to the control or data planes
- *
- *
- * Copyright (C) 2007-2008 Intel Corporation. All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- *   * Redistributions of source code must retain the above copyright
- *     notice, this list of conditions and the following disclaimer.
- *   * Redistributions in binary form must reproduce the above copyright
- *     notice, this list of conditions and the following disclaimer in
- *     the documentation and/or other materials provided with the
- *     distribution.
- *   * Neither the name of Intel Corporation nor the names of its
- *     contributors may be used to endorse or promote products derived
- *     from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * Intel Corporation <linux-wimax@intel.com>
- * Yanir Lubetkin <yanirx.lubetkin@intel.com>
- *  - Initial implementation
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *  - Use skb_clone(), break up processing in chunks
- *  - Split transport/device specific
- *  - Make buffer size dynamic to exert less memory pressure
- *  - RX reorder support
- *
- * This handles the RX path.
- *
- * We receive an RX message from the bus-specific driver, which
- * contains one or more payloads that have potentially different
- * destinataries (data or control paths).
- *
- * So we just take that payload from the transport specific code in
- * the form of an skb, break it up in chunks (a cloned skb each in the
- * case of network packets) and pass it to netdev or to the
- * command/ack handler (and from there to the WiMAX stack).
- *
- * PROTOCOL FORMAT
- *
- * The format of the buffer is:
- *
- * HEADER                      (struct i2400m_msg_hdr)
- * PAYLOAD DESCRIPTOR 0        (struct i2400m_pld)
- * PAYLOAD DESCRIPTOR 1
- * ...
- * PAYLOAD DESCRIPTOR N
- * PAYLOAD 0                   (raw bytes)
- * PAYLOAD 1
- * ...
- * PAYLOAD N
- *
- * See tx.c for a deeper description on alignment requirements and
- * other fun facts of it.
- *
- * DATA PACKETS
- *
- * In firmwares <= v1.3, data packets have no header for RX, but they
- * do for TX (currently unused).
- *
- * In firmware >= 1.4, RX packets have an extended header (16
- * bytes). This header conveys information for management of host
- * reordering of packets (the device offloads storage of the packets
- * for reordering to the host). Read below for more information.
- *
- * The header is used as dummy space to emulate an ethernet header and
- * thus be able to act as an ethernet device without having to reallocate.
- *
- * DATA RX REORDERING
- *
- * Starting in firmware v1.4, the device can deliver packets for
- * delivery with special reordering information; this allows it to
- * more effectively do packet management when some frames were lost in
- * the radio traffic.
- *
- * Thus, for RX packets that come out of order, the device gives the
- * driver enough information to queue them properly and then at some
- * point, the signal to deliver the whole (or part) of the queued
- * packets to the networking stack. There are 16 such queues.
- *
- * This only happens when a packet comes in with the "need reorder"
- * flag set in the RX header. When such bit is set, the following
- * operations might be indicated:
- *
- *  - reset queue: send all queued packets to the OS
- *
- *  - queue: queue a packet
- *
- *  - update ws: update the queue's window start and deliver queued
- *    packets that meet the criteria
- *
- *  - queue & update ws: queue a packet, update the window start and
- *    deliver queued packets that meet the criteria
- *
- * (delivery criteria: the packet's [normalized] sequence number is
- * lower than the new [normalized] window start).
- *
- * See the i2400m_roq_*() functions for details.
- *
- * ROADMAP
- *
- * i2400m_rx
- *   i2400m_rx_msg_hdr_check
- *   i2400m_rx_pl_descr_check
- *   i2400m_rx_payload
- *     i2400m_net_rx
- *     i2400m_rx_edata
- *       i2400m_net_erx
- *       i2400m_roq_reset
- *         i2400m_net_erx
- *       i2400m_roq_queue
- *         __i2400m_roq_queue
- *       i2400m_roq_update_ws
- *         __i2400m_roq_update_ws
- *           i2400m_net_erx
- *       i2400m_roq_queue_update_ws
- *         __i2400m_roq_queue
- *         __i2400m_roq_update_ws
- *           i2400m_net_erx
- *     i2400m_rx_ctl
- *       i2400m_msg_size_check
- *       i2400m_report_hook_work    [in a workqueue]
- *         i2400m_report_hook
- *       wimax_msg_to_user
- *       i2400m_rx_ctl_ack
- *         wimax_msg_to_user_alloc
- *     i2400m_rx_trace
- *       i2400m_msg_size_check
- *       wimax_msg
- */
-#include <linux/slab.h>
-#include <linux/kernel.h>
-#include <linux/if_arp.h>
-#include <linux/netdevice.h>
-#include <linux/workqueue.h>
-#include <linux/export.h>
-#include <linux/moduleparam.h>
-#include "i2400m.h"
-
-
-#define D_SUBMODULE rx
-#include "debug-levels.h"
-
-static int i2400m_rx_reorder_disabled;	/* 0 (rx reorder enabled) by default */
-module_param_named(rx_reorder_disabled, i2400m_rx_reorder_disabled, int, 0644);
-MODULE_PARM_DESC(rx_reorder_disabled,
-		 "If true, RX reordering will be disabled.");
-
-struct i2400m_report_hook_args {
-	struct sk_buff *skb_rx;
-	const struct i2400m_l3l4_hdr *l3l4_hdr;
-	size_t size;
-	struct list_head list_node;
-};
-
-
-/*
- * Execute i2400m_report_hook in a workqueue
- *
- * Goes over the list of queued reports in i2400m->rx_reports and
- * processes them.
- *
- * NOTE: refcounts on i2400m are not needed because we flush the
- *     workqueue this runs on (i2400m->work_queue) before destroying
- *     i2400m.
- */
-void i2400m_report_hook_work(struct work_struct *ws)
-{
-	struct i2400m *i2400m = container_of(ws, struct i2400m, rx_report_ws);
-	struct device *dev = i2400m_dev(i2400m);
-	struct i2400m_report_hook_args *args, *args_next;
-	LIST_HEAD(list);
-	unsigned long flags;
-
-	while (1) {
-		spin_lock_irqsave(&i2400m->rx_lock, flags);
-		list_splice_init(&i2400m->rx_reports, &list);
-		spin_unlock_irqrestore(&i2400m->rx_lock, flags);
-		if (list_empty(&list))
-			break;
-		else
-			d_printf(1, dev, "processing queued reports\n");
-		list_for_each_entry_safe(args, args_next, &list, list_node) {
-			d_printf(2, dev, "processing queued report %p\n", args);
-			i2400m_report_hook(i2400m, args->l3l4_hdr, args->size);
-			kfree_skb(args->skb_rx);
-			list_del(&args->list_node);
-			kfree(args);
-		}
-	}
-}
-
-
-/*
- * Flush the list of queued reports
- */
-static
-void i2400m_report_hook_flush(struct i2400m *i2400m)
-{
-	struct device *dev = i2400m_dev(i2400m);
-	struct i2400m_report_hook_args *args, *args_next;
-	LIST_HEAD(list);
-	unsigned long flags;
-
-	d_printf(1, dev, "flushing queued reports\n");
-	spin_lock_irqsave(&i2400m->rx_lock, flags);
-	list_splice_init(&i2400m->rx_reports, &list);
-	spin_unlock_irqrestore(&i2400m->rx_lock, flags);
-	list_for_each_entry_safe(args, args_next, &list, list_node) {
-		d_printf(2, dev, "flushing queued report %p\n", args);
-		kfree_skb(args->skb_rx);
-		list_del(&args->list_node);
-		kfree(args);
-	}
-}
-
-
-/*
- * Queue a report for later processing
- *
- * @i2400m: device descriptor
- * @skb_rx: skb that contains the payload (for reference counting)
- * @l3l4_hdr: pointer to the control
- * @size: size of the message
- */
-static
-void i2400m_report_hook_queue(struct i2400m *i2400m, struct sk_buff *skb_rx,
-			      const void *l3l4_hdr, size_t size)
-{
-	struct device *dev = i2400m_dev(i2400m);
-	unsigned long flags;
-	struct i2400m_report_hook_args *args;
-
-	args = kzalloc(sizeof(*args), GFP_NOIO);
-	if (args) {
-		args->skb_rx = skb_get(skb_rx);
-		args->l3l4_hdr = l3l4_hdr;
-		args->size = size;
-		spin_lock_irqsave(&i2400m->rx_lock, flags);
-		list_add_tail(&args->list_node, &i2400m->rx_reports);
-		spin_unlock_irqrestore(&i2400m->rx_lock, flags);
-		d_printf(2, dev, "queued report %p\n", args);
-		rmb();		/* see i2400m->ready's documentation  */
-		if (likely(i2400m->ready))	/* only send if up */
-			queue_work(i2400m->work_queue, &i2400m->rx_report_ws);
-	} else  {
-		if (printk_ratelimit())
-			dev_err(dev, "%s:%u: Can't allocate %zu B\n",
-				__func__, __LINE__, sizeof(*args));
-	}
-}
-
-
-/*
- * Process an ack to a command
- *
- * @i2400m: device descriptor
- * @payload: pointer to message
- * @size: size of the message
- *
- * Pass the acknodledgment (in an skb) to the thread that is waiting
- * for it in i2400m->msg_completion.
- *
- * We need to coordinate properly with the thread waiting for the
- * ack. Check if it is waiting or if it is gone. We loose the spinlock
- * to avoid allocating on atomic contexts (yeah, could use GFP_ATOMIC,
- * but this is not so speed critical).
- */
-static
-void i2400m_rx_ctl_ack(struct i2400m *i2400m,
-		       const void *payload, size_t size)
-{
-	struct device *dev = i2400m_dev(i2400m);
-	struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
-	unsigned long flags;
-	struct sk_buff *ack_skb;
-
-	/* Anyone waiting for an answer? */
-	spin_lock_irqsave(&i2400m->rx_lock, flags);
-	if (i2400m->ack_skb != ERR_PTR(-EINPROGRESS)) {
-		dev_err(dev, "Huh? reply to command with no waiters\n");
-		goto error_no_waiter;
-	}
-	spin_unlock_irqrestore(&i2400m->rx_lock, flags);
-
-	ack_skb = wimax_msg_alloc(wimax_dev, NULL, payload, size, GFP_KERNEL);
-
-	/* Check waiter didn't time out waiting for the answer... */
-	spin_lock_irqsave(&i2400m->rx_lock, flags);
-	if (i2400m->ack_skb != ERR_PTR(-EINPROGRESS)) {
-		d_printf(1, dev, "Huh? waiter for command reply cancelled\n");
-		goto error_waiter_cancelled;
-	}
-	if (IS_ERR(ack_skb))
-		dev_err(dev, "CMD/GET/SET ack: cannot allocate SKB\n");
-	i2400m->ack_skb = ack_skb;
-	spin_unlock_irqrestore(&i2400m->rx_lock, flags);
-	complete(&i2400m->msg_completion);
-	return;
-
-error_waiter_cancelled:
-	if (!IS_ERR(ack_skb))
-		kfree_skb(ack_skb);
-error_no_waiter:
-	spin_unlock_irqrestore(&i2400m->rx_lock, flags);
-}
-
-
-/*
- * Receive and process a control payload
- *
- * @i2400m: device descriptor
- * @skb_rx: skb that contains the payload (for reference counting)
- * @payload: pointer to message
- * @size: size of the message
- *
- * There are two types of control RX messages: reports (asynchronous,
- * like your every day interrupts) and 'acks' (reponses to a command,
- * get or set request).
- *
- * If it is a report, we run hooks on it (to extract information for
- * things we need to do in the driver) and then pass it over to the
- * WiMAX stack to send it to user space.
- *
- * NOTE: report processing is done in a workqueue specific to the
- *     generic driver, to avoid deadlocks in the system.
- *
- * If it is not a report, it is an ack to a previously executed
- * command, set or get, so wake up whoever is waiting for it from
- * i2400m_msg_to_dev(). i2400m_rx_ctl_ack() takes care of that.
- *
- * Note that the sizes we pass to other functions from here are the
- * sizes of the _l3l4_hdr + payload, not full buffer sizes, as we have
- * verified in _msg_size_check() that they are congruent.
- *
- * For reports: We can't clone the original skb where the data is
- * because we need to send this up via netlink; netlink has to add
- * headers and we can't overwrite what's preceding the payload...as
- * it is another message. So we just dup them.
- */
-static
-void i2400m_rx_ctl(struct i2400m *i2400m, struct sk_buff *skb_rx,
-		   const void *payload, size_t size)
-{
-	int result;
-	struct device *dev = i2400m_dev(i2400m);
-	const struct i2400m_l3l4_hdr *l3l4_hdr = payload;
-	unsigned msg_type;
-
-	result = i2400m_msg_size_check(i2400m, l3l4_hdr, size);
-	if (result < 0) {
-		dev_err(dev, "HW BUG? device sent a bad message: %d\n",
-			result);
-		goto error_check;
-	}
-	msg_type = le16_to_cpu(l3l4_hdr->type);
-	d_printf(1, dev, "%s 0x%04x: %zu bytes\n",
-		 msg_type & I2400M_MT_REPORT_MASK ? "REPORT" : "CMD/SET/GET",
-		 msg_type, size);
-	d_dump(2, dev, l3l4_hdr, size);
-	if (msg_type & I2400M_MT_REPORT_MASK) {
-		/*
-		 * Process each report
-		 *
-		 * - has to be ran serialized as well
-		 *
-		 * - the handling might force the execution of
-		 *   commands. That might cause reentrancy issues with
-		 *   bus-specific subdrivers and workqueues, so the we
-		 *   run it in a separate workqueue.
-		 *
-		 * - when the driver is not yet ready to handle them,
-		 *   they are queued and at some point the queue is
-		 *   restarted [NOTE: we can't queue SKBs directly, as
-		 *   this might be a piece of a SKB, not the whole
-		 *   thing, and this is cheaper than cloning the
-		 *   SKB].
-		 *
-		 * Note we don't do refcounting for the device
-		 * structure; this is because before destroying
-		 * 'i2400m', we make sure to flush the
-		 * i2400m->work_queue, so there are no issues.
-		 */
-		i2400m_report_hook_queue(i2400m, skb_rx, l3l4_hdr, size);
-		if (unlikely(i2400m->trace_msg_from_user))
-			wimax_msg(&i2400m->wimax_dev, "echo",
-				  l3l4_hdr, size, GFP_KERNEL);
-		result = wimax_msg(&i2400m->wimax_dev, NULL, l3l4_hdr, size,
-				   GFP_KERNEL);
-		if (result < 0)
-			dev_err(dev, "error sending report to userspace: %d\n",
-				result);
-	} else		/* an ack to a CMD, GET or SET */
-		i2400m_rx_ctl_ack(i2400m, payload, size);
-error_check:
-	return;
-}
-
-
-/*
- * Receive and send up a trace
- *
- * @i2400m: device descriptor
- * @skb_rx: skb that contains the trace (for reference counting)
- * @payload: pointer to trace message inside the skb
- * @size: size of the message
- *
- * THe i2400m might produce trace information (diagnostics) and we
- * send them through a different kernel-to-user pipe (to avoid
- * clogging it).
- *
- * As in i2400m_rx_ctl(), we can't clone the original skb where the
- * data is because we need to send this up via netlink; netlink has to
- * add headers and we can't overwrite what's preceding the
- * payload...as it is another message. So we just dup them.
- */
-static
-void i2400m_rx_trace(struct i2400m *i2400m,
-		     const void *payload, size_t size)
-{
-	int result;
-	struct device *dev = i2400m_dev(i2400m);
-	struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
-	const struct i2400m_l3l4_hdr *l3l4_hdr = payload;
-	unsigned msg_type;
-
-	result = i2400m_msg_size_check(i2400m, l3l4_hdr, size);
-	if (result < 0) {
-		dev_err(dev, "HW BUG? device sent a bad trace message: %d\n",
-			result);
-		goto error_check;
-	}
-	msg_type = le16_to_cpu(l3l4_hdr->type);
-	d_printf(1, dev, "Trace %s 0x%04x: %zu bytes\n",
-		 msg_type & I2400M_MT_REPORT_MASK ? "REPORT" : "CMD/SET/GET",
-		 msg_type, size);
-	d_dump(2, dev, l3l4_hdr, size);
-	result = wimax_msg(wimax_dev, "trace", l3l4_hdr, size, GFP_KERNEL);
-	if (result < 0)
-		dev_err(dev, "error sending trace to userspace: %d\n",
-			result);
-error_check:
-	return;
-}
-
-
-/*
- * Reorder queue data stored on skb->cb while the skb is queued in the
- * reorder queues.
- */
-struct i2400m_roq_data {
-	unsigned sn;		/* Serial number for the skb */
-	enum i2400m_cs cs;	/* packet type for the skb */
-};
-
-
-/*
- * ReOrder Queue
- *
- * @ws: Window Start; sequence number where the current window start
- *     is for this queue
- * @queue: the skb queue itself
- * @log: circular ring buffer used to log information about the
- *     reorder process in this queue that can be displayed in case of
- *     error to help diagnose it.
- *
- * This is the head for a list of skbs. In the skb->cb member of the
- * skb when queued here contains a 'struct i2400m_roq_data' were we
- * store the sequence number (sn) and the cs (packet type) coming from
- * the RX payload header from the device.
- */
-struct i2400m_roq
-{
-	unsigned ws;
-	struct sk_buff_head queue;
-	struct i2400m_roq_log *log;
-};
-
-
-static
-void __i2400m_roq_init(struct i2400m_roq *roq)
-{
-	roq->ws = 0;
-	skb_queue_head_init(&roq->queue);
-}
-
-
-static
-unsigned __i2400m_roq_index(struct i2400m *i2400m, struct i2400m_roq *roq)
-{
-	return ((unsigned long) roq - (unsigned long) i2400m->rx_roq)
-		/ sizeof(*roq);
-}
-
-
-/*
- * Normalize a sequence number based on the queue's window start
- *
- * nsn = (sn - ws) % 2048
- *
- * Note that if @sn < @roq->ws, we still need a positive number; %'s
- * sign is implementation specific, so we normalize it by adding 2048
- * to bring it to be positive.
- */
-static
-unsigned __i2400m_roq_nsn(struct i2400m_roq *roq, unsigned sn)
-{
-	int r;
-	r =  ((int) sn - (int) roq->ws) % 2048;
-	if (r < 0)
-		r += 2048;
-	return r;
-}
-
-
-/*
- * Circular buffer to keep the last N reorder operations
- *
- * In case something fails, dumb then to try to come up with what
- * happened.
- */
-enum {
-	I2400M_ROQ_LOG_LENGTH = 32,
-};
-
-struct i2400m_roq_log {
-	struct i2400m_roq_log_entry {
-		enum i2400m_ro_type type;
-		unsigned ws, count, sn, nsn, new_ws;
-	} entry[I2400M_ROQ_LOG_LENGTH];
-	unsigned in, out;
-};
-
-
-/* Print a log entry */
-static
-void i2400m_roq_log_entry_print(struct i2400m *i2400m, unsigned index,
-				unsigned e_index,
-				struct i2400m_roq_log_entry *e)
-{
-	struct device *dev = i2400m_dev(i2400m);
-
-	switch(e->type) {
-	case I2400M_RO_TYPE_RESET:
-		dev_err(dev, "q#%d reset           ws %u cnt %u sn %u/%u"
-			" - new nws %u\n",
-			index, e->ws, e->count, e->sn, e->nsn, e->new_ws);
-		break;
-	case I2400M_RO_TYPE_PACKET:
-		dev_err(dev, "q#%d queue           ws %u cnt %u sn %u/%u\n",
-			index, e->ws, e->count, e->sn, e->nsn);
-		break;
-	case I2400M_RO_TYPE_WS:
-		dev_err(dev, "q#%d update_ws       ws %u cnt %u sn %u/%u"
-			" - new nws %u\n",
-			index, e->ws, e->count, e->sn, e->nsn, e->new_ws);
-		break;
-	case I2400M_RO_TYPE_PACKET_WS:
-		dev_err(dev, "q#%d queue_update_ws ws %u cnt %u sn %u/%u"
-			" - new nws %u\n",
-			index, e->ws, e->count, e->sn, e->nsn, e->new_ws);
-		break;
-	default:
-		dev_err(dev, "q#%d BUG? entry %u - unknown type %u\n",
-			index, e_index, e->type);
-		break;
-	}
-}
-
-
-static
-void i2400m_roq_log_add(struct i2400m *i2400m,
-			struct i2400m_roq *roq, enum i2400m_ro_type type,
-			unsigned ws, unsigned count, unsigned sn,
-			unsigned nsn, unsigned new_ws)
-{
-	struct i2400m_roq_log_entry *e;
-	unsigned cnt_idx;
-	int index = __i2400m_roq_index(i2400m, roq);
-
-	/* if we run out of space, we eat from the end */
-	if (roq->log->in - roq->log->out == I2400M_ROQ_LOG_LENGTH)
-		roq->log->out++;
-	cnt_idx = roq->log->in++ % I2400M_ROQ_LOG_LENGTH;
-	e = &roq->log->entry[cnt_idx];
-
-	e->type = type;
-	e->ws = ws;
-	e->count = count;
-	e->sn = sn;
-	e->nsn = nsn;
-	e->new_ws = new_ws;
-
-	if (d_test(1))
-		i2400m_roq_log_entry_print(i2400m, index, cnt_idx, e);
-}
-
-
-/* Dump all the entries in the FIFO and reinitialize it */
-static
-void i2400m_roq_log_dump(struct i2400m *i2400m, struct i2400m_roq *roq)
-{
-	unsigned cnt, cnt_idx;
-	struct i2400m_roq_log_entry *e;
-	int index = __i2400m_roq_index(i2400m, roq);
-
-	BUG_ON(roq->log->out > roq->log->in);
-	for (cnt = roq->log->out; cnt < roq->log->in; cnt++) {
-		cnt_idx = cnt % I2400M_ROQ_LOG_LENGTH;
-		e = &roq->log->entry[cnt_idx];
-		i2400m_roq_log_entry_print(i2400m, index, cnt_idx, e);
-		memset(e, 0, sizeof(*e));
-	}
-	roq->log->in = roq->log->out = 0;
-}
-
-
-/*
- * Backbone for the queuing of an skb (by normalized sequence number)
- *
- * @i2400m: device descriptor
- * @roq: reorder queue where to add
- * @skb: the skb to add
- * @sn: the sequence number of the skb
- * @nsn: the normalized sequence number of the skb (pre-computed by the
- *     caller from the @sn and @roq->ws).
- *
- * We try first a couple of quick cases:
- *
- *   - the queue is empty
- *   - the skb would be appended to the queue
- *
- * These will be the most common operations.
- *
- * If these fail, then we have to do a sorted insertion in the queue,
- * which is the slowest path.
- *
- * We don't have to acquire a reference count as we are going to own it.
- */
-static
-void __i2400m_roq_queue(struct i2400m *i2400m, struct i2400m_roq *roq,
-			struct sk_buff *skb, unsigned sn, unsigned nsn)
-{
-	struct device *dev = i2400m_dev(i2400m);
-	struct sk_buff *skb_itr;
-	struct i2400m_roq_data *roq_data_itr, *roq_data;
-	unsigned nsn_itr;
-
-	d_fnstart(4, dev, "(i2400m %p roq %p skb %p sn %u nsn %u)\n",
-		  i2400m, roq, skb, sn, nsn);
-
-	roq_data = (struct i2400m_roq_data *) &skb->cb;
-	BUILD_BUG_ON(sizeof(*roq_data) > sizeof(skb->cb));
-	roq_data->sn = sn;
-	d_printf(3, dev, "ERX: roq %p [ws %u] nsn %d sn %u\n",
-		 roq, roq->ws, nsn, roq_data->sn);
-
-	/* Queues will be empty on not-so-bad environments, so try
-	 * that first */
-	if (skb_queue_empty(&roq->queue)) {
-		d_printf(2, dev, "ERX: roq %p - first one\n", roq);
-		__skb_queue_head(&roq->queue, skb);
-		goto out;
-	}
-	/* Now try append, as most of the operations will be that */
-	skb_itr = skb_peek_tail(&roq->queue);
-	roq_data_itr = (struct i2400m_roq_data *) &skb_itr->cb;
-	nsn_itr = __i2400m_roq_nsn(roq, roq_data_itr->sn);
-	/* NSN bounds assumed correct (checked when it was queued) */
-	if (nsn >= nsn_itr) {
-		d_printf(2, dev, "ERX: roq %p - appended after %p (nsn %d sn %u)\n",
-			 roq, skb_itr, nsn_itr, roq_data_itr->sn);
-		__skb_queue_tail(&roq->queue, skb);
-		goto out;
-	}
-	/* None of the fast paths option worked. Iterate to find the
-	 * right spot where to insert the packet; we know the queue is
-	 * not empty, so we are not the first ones; we also know we
-	 * are not going to be the last ones. The list is sorted, so
-	 * we have to insert before the the first guy with an nsn_itr
-	 * greater that our nsn. */
-	skb_queue_walk(&roq->queue, skb_itr) {
-		roq_data_itr = (struct i2400m_roq_data *) &skb_itr->cb;
-		nsn_itr = __i2400m_roq_nsn(roq, roq_data_itr->sn);
-		/* NSN bounds assumed correct (checked when it was queued) */
-		if (nsn_itr > nsn) {
-			d_printf(2, dev, "ERX: roq %p - queued before %p "
-				 "(nsn %d sn %u)\n", roq, skb_itr, nsn_itr,
-				 roq_data_itr->sn);
-			__skb_queue_before(&roq->queue, skb_itr, skb);
-			goto out;
-		}
-	}
-	/* If we get here, that is VERY bad -- print info to help
-	 * diagnose and crash it */
-	dev_err(dev, "SW BUG? failed to insert packet\n");
-	dev_err(dev, "ERX: roq %p [ws %u] skb %p nsn %d sn %u\n",
-		roq, roq->ws, skb, nsn, roq_data->sn);
-	skb_queue_walk(&roq->queue, skb_itr) {
-		roq_data_itr = (struct i2400m_roq_data *) &skb_itr->cb;
-		nsn_itr = __i2400m_roq_nsn(roq, roq_data_itr->sn);
-		/* NSN bounds assumed correct (checked when it was queued) */
-		dev_err(dev, "ERX: roq %p skb_itr %p nsn %d sn %u\n",
-			roq, skb_itr, nsn_itr, roq_data_itr->sn);
-	}
-	BUG();
-out:
-	d_fnend(4, dev, "(i2400m %p roq %p skb %p sn %u nsn %d) = void\n",
-		i2400m, roq, skb, sn, nsn);
-}
-
-
-/*
- * Backbone for the update window start operation
- *
- * @i2400m: device descriptor
- * @roq: Reorder queue
- * @sn: New sequence number
- *
- * Updates the window start of a queue; when doing so, it must deliver
- * to the networking stack all the queued skb's whose normalized
- * sequence number is lower than the new normalized window start.
- */
-static
-unsigned __i2400m_roq_update_ws(struct i2400m *i2400m, struct i2400m_roq *roq,
-				unsigned sn)
-{
-	struct device *dev = i2400m_dev(i2400m);
-	struct sk_buff *skb_itr, *tmp_itr;
-	struct i2400m_roq_data *roq_data_itr;
-	unsigned new_nws, nsn_itr;
-
-	new_nws = __i2400m_roq_nsn(roq, sn);
-	/*
-	 * For type 2(update_window_start) rx messages, there is no
-	 * need to check if the normalized sequence number is greater 1023.
-	 * Simply insert and deliver all packets to the host up to the
-	 * window start.
-	 */
-	skb_queue_walk_safe(&roq->queue, skb_itr, tmp_itr) {
-		roq_data_itr = (struct i2400m_roq_data *) &skb_itr->cb;
-		nsn_itr = __i2400m_roq_nsn(roq, roq_data_itr->sn);
-		/* NSN bounds assumed correct (checked when it was queued) */
-		if (nsn_itr < new_nws) {
-			d_printf(2, dev, "ERX: roq %p - release skb %p "
-				 "(nsn %u/%u new nws %u)\n",
-				 roq, skb_itr, nsn_itr, roq_data_itr->sn,
-				 new_nws);
-			__skb_unlink(skb_itr, &roq->queue);
-			i2400m_net_erx(i2400m, skb_itr, roq_data_itr->cs);
-		}
-		else
-			break;	/* rest of packets all nsn_itr > nws */
-	}
-	roq->ws = sn;
-	return new_nws;
-}
-
-
-/*
- * Reset a queue
- *
- * @i2400m: device descriptor
- * @cin: Queue Index
- *
- * Deliver all the packets and reset the window-start to zero. Name is
- * kind of misleading.
- */
-static
-void i2400m_roq_reset(struct i2400m *i2400m, struct i2400m_roq *roq)
-{
-	struct device *dev = i2400m_dev(i2400m);
-	struct sk_buff *skb_itr, *tmp_itr;
-	struct i2400m_roq_data *roq_data_itr;
-
-	d_fnstart(2, dev, "(i2400m %p roq %p)\n", i2400m, roq);
-	i2400m_roq_log_add(i2400m, roq, I2400M_RO_TYPE_RESET,
-			     roq->ws, skb_queue_len(&roq->queue),
-			     ~0, ~0, 0);
-	skb_queue_walk_safe(&roq->queue, skb_itr, tmp_itr) {
-		roq_data_itr = (struct i2400m_roq_data *) &skb_itr->cb;
-		d_printf(2, dev, "ERX: roq %p - release skb %p (sn %u)\n",
-			 roq, skb_itr, roq_data_itr->sn);
-		__skb_unlink(skb_itr, &roq->queue);
-		i2400m_net_erx(i2400m, skb_itr, roq_data_itr->cs);
-	}
-	roq->ws = 0;
-	d_fnend(2, dev, "(i2400m %p roq %p) = void\n", i2400m, roq);
-}
-
-
-/*
- * Queue a packet
- *
- * @i2400m: device descriptor
- * @cin: Queue Index
- * @skb: containing the packet data
- * @fbn: First block number of the packet in @skb
- * @lbn: Last block number of the packet in @skb
- *
- * The hardware is asking the driver to queue a packet for later
- * delivery to the networking stack.
- */
-static
-void i2400m_roq_queue(struct i2400m *i2400m, struct i2400m_roq *roq,
-		      struct sk_buff * skb, unsigned lbn)
-{
-	struct device *dev = i2400m_dev(i2400m);
-	unsigned nsn, len;
-
-	d_fnstart(2, dev, "(i2400m %p roq %p skb %p lbn %u) = void\n",
-		  i2400m, roq, skb, lbn);
-	len = skb_queue_len(&roq->queue);
-	nsn = __i2400m_roq_nsn(roq, lbn);
-	if (unlikely(nsn >= 1024)) {
-		dev_err(dev, "SW BUG? queue nsn %d (lbn %u ws %u)\n",
-			nsn, lbn, roq->ws);
-		i2400m_roq_log_dump(i2400m, roq);
-		i2400m_reset(i2400m, I2400M_RT_WARM);
-	} else {
-		__i2400m_roq_queue(i2400m, roq, skb, lbn, nsn);
-		i2400m_roq_log_add(i2400m, roq, I2400M_RO_TYPE_PACKET,
-				     roq->ws, len, lbn, nsn, ~0);
-	}
-	d_fnend(2, dev, "(i2400m %p roq %p skb %p lbn %u) = void\n",
-		i2400m, roq, skb, lbn);
-}
-
-
-/*
- * Update the window start in a reorder queue and deliver all skbs
- * with a lower window start
- *
- * @i2400m: device descriptor
- * @roq: Reorder queue
- * @sn: New sequence number
- */
-static
-void i2400m_roq_update_ws(struct i2400m *i2400m, struct i2400m_roq *roq,
-			  unsigned sn)
-{
-	struct device *dev = i2400m_dev(i2400m);
-	unsigned old_ws, nsn, len;
-
-	d_fnstart(2, dev, "(i2400m %p roq %p sn %u)\n", i2400m, roq, sn);
-	old_ws = roq->ws;
-	len = skb_queue_len(&roq->queue);
-	nsn = __i2400m_roq_update_ws(i2400m, roq, sn);
-	i2400m_roq_log_add(i2400m, roq, I2400M_RO_TYPE_WS,
-			     old_ws, len, sn, nsn, roq->ws);
-	d_fnstart(2, dev, "(i2400m %p roq %p sn %u) = void\n", i2400m, roq, sn);
-}
-
-
-/*
- * Queue a packet and update the window start
- *
- * @i2400m: device descriptor
- * @cin: Queue Index
- * @skb: containing the packet data
- * @fbn: First block number of the packet in @skb
- * @sn: Last block number of the packet in @skb
- *
- * Note that unlike i2400m_roq_update_ws(), which sets the new window
- * start to @sn, in here we'll set it to @sn + 1.
- */
-static
-void i2400m_roq_queue_update_ws(struct i2400m *i2400m, struct i2400m_roq *roq,
-				struct sk_buff * skb, unsigned sn)
-{
-	struct device *dev = i2400m_dev(i2400m);
-	unsigned nsn, old_ws, len;
-
-	d_fnstart(2, dev, "(i2400m %p roq %p skb %p sn %u)\n",
-		  i2400m, roq, skb, sn);
-	len = skb_queue_len(&roq->queue);
-	nsn = __i2400m_roq_nsn(roq, sn);
-	/*
-	 * For type 3(queue_update_window_start) rx messages, there is no
-	 * need to check if the normalized sequence number is greater 1023.
-	 * Simply insert and deliver all packets to the host up to the
-	 * window start.
-	 */
-	old_ws = roq->ws;
-	/* If the queue is empty, don't bother as we'd queue
-	 * it and immediately unqueue it -- just deliver it.
-	 */
-	if (len == 0) {
-		struct i2400m_roq_data *roq_data;
-		roq_data = (struct i2400m_roq_data *) &skb->cb;
-		i2400m_net_erx(i2400m, skb, roq_data->cs);
-	} else
-		__i2400m_roq_queue(i2400m, roq, skb, sn, nsn);
-
-	__i2400m_roq_update_ws(i2400m, roq, sn + 1);
-	i2400m_roq_log_add(i2400m, roq, I2400M_RO_TYPE_PACKET_WS,
-			   old_ws, len, sn, nsn, roq->ws);
-
-	d_fnend(2, dev, "(i2400m %p roq %p skb %p sn %u) = void\n",
-		i2400m, roq, skb, sn);
-}
-
-
-/*
- * This routine destroys the memory allocated for rx_roq, when no
- * other thread is accessing it. Access to rx_roq is refcounted by
- * rx_roq_refcount, hence memory allocated must be destroyed when
- * rx_roq_refcount becomes zero. This routine gets executed when
- * rx_roq_refcount becomes zero.
- */
-static void i2400m_rx_roq_destroy(struct kref *ref)
-{
-	unsigned itr;
-	struct i2400m *i2400m
-			= container_of(ref, struct i2400m, rx_roq_refcount);
-	for (itr = 0; itr < I2400M_RO_CIN + 1; itr++)
-		__skb_queue_purge(&i2400m->rx_roq[itr].queue);
-	kfree(i2400m->rx_roq[0].log);
-	kfree(i2400m->rx_roq);
-	i2400m->rx_roq = NULL;
-}
-
-/*
- * Receive and send up an extended data packet
- *
- * @i2400m: device descriptor
- * @skb_rx: skb that contains the extended data packet
- * @single_last: 1 if the payload is the only one or the last one of
- *     the skb.
- * @payload: pointer to the packet's data inside the skb
- * @size: size of the payload
- *
- * Starting in v1.4 of the i2400m's firmware, the device can send data
- * packets to the host in an extended format that; this incudes a 16
- * byte header (struct i2400m_pl_edata_hdr). Using this header's space
- * we can fake ethernet headers for ethernet device emulation without
- * having to copy packets around.
- *
- * This function handles said path.
- *
- *
- * Receive and send up an extended data packet that requires no reordering
- *
- * @i2400m: device descriptor
- * @skb_rx: skb that contains the extended data packet
- * @single_last: 1 if the payload is the only one or the last one of
- *     the skb.
- * @payload: pointer to the packet's data (past the actual extended
- *     data payload header).
- * @size: size of the payload
- *
- * Pass over to the networking stack a data packet that might have
- * reordering requirements.
- *
- * This needs to the decide if the skb in which the packet is
- * contained can be reused or if it needs to be cloned. Then it has to
- * be trimmed in the edges so that the beginning is the space for eth
- * header and then pass it to i2400m_net_erx() for the stack
- *
- * Assumes the caller has verified the sanity of the payload (size,
- * etc) already.
- */
-static
-void i2400m_rx_edata(struct i2400m *i2400m, struct sk_buff *skb_rx,
-		     unsigned single_last, const void *payload, size_t size)
-{
-	struct device *dev = i2400m_dev(i2400m);
-	const struct i2400m_pl_edata_hdr *hdr = payload;
-	struct net_device *net_dev = i2400m->wimax_dev.net_dev;
-	struct sk_buff *skb;
-	enum i2400m_cs cs;
-	u32 reorder;
-	unsigned ro_needed, ro_type, ro_cin, ro_sn;
-	struct i2400m_roq *roq;
-	struct i2400m_roq_data *roq_data;
-	unsigned long flags;
-
-	BUILD_BUG_ON(ETH_HLEN > sizeof(*hdr));
-
-	d_fnstart(2, dev, "(i2400m %p skb_rx %p single %u payload %p "
-		  "size %zu)\n", i2400m, skb_rx, single_last, payload, size);
-	if (size < sizeof(*hdr)) {
-		dev_err(dev, "ERX: HW BUG? message with short header (%zu "
-			"vs %zu bytes expected)\n", size, sizeof(*hdr));
-		goto error;
-	}
-
-	if (single_last) {
-		skb = skb_get(skb_rx);
-		d_printf(3, dev, "ERX: skb %p reusing\n", skb);
-	} else {
-		skb = skb_clone(skb_rx, GFP_KERNEL);
-		if (skb == NULL) {
-			dev_err(dev, "ERX: no memory to clone skb\n");
-			net_dev->stats.rx_dropped++;
-			goto error_skb_clone;
-		}
-		d_printf(3, dev, "ERX: skb %p cloned from %p\n", skb, skb_rx);
-	}
-	/* now we have to pull and trim so that the skb points to the
-	 * beginning of the IP packet; the netdev part will add the
-	 * ethernet header as needed - we know there is enough space
-	 * because we checked in i2400m_rx_edata(). */
-	skb_pull(skb, payload + sizeof(*hdr) - (void *) skb->data);
-	skb_trim(skb, (void *) skb_end_pointer(skb) - payload - sizeof(*hdr));
-
-	reorder = le32_to_cpu(hdr->reorder);
-	ro_needed = reorder & I2400M_RO_NEEDED;
-	cs = hdr->cs;
-	if (ro_needed) {
-		ro_type = (reorder >> I2400M_RO_TYPE_SHIFT) & I2400M_RO_TYPE;
-		ro_cin = (reorder >> I2400M_RO_CIN_SHIFT) & I2400M_RO_CIN;
-		ro_sn = (reorder >> I2400M_RO_SN_SHIFT) & I2400M_RO_SN;
-
-		spin_lock_irqsave(&i2400m->rx_lock, flags);
-		if (i2400m->rx_roq == NULL) {
-			kfree_skb(skb);	/* rx_roq is already destroyed */
-			spin_unlock_irqrestore(&i2400m->rx_lock, flags);
-			goto error;
-		}
-		roq = &i2400m->rx_roq[ro_cin];
-		kref_get(&i2400m->rx_roq_refcount);
-		spin_unlock_irqrestore(&i2400m->rx_lock, flags);
-
-		roq_data = (struct i2400m_roq_data *) &skb->cb;
-		roq_data->sn = ro_sn;
-		roq_data->cs = cs;
-		d_printf(2, dev, "ERX: reorder needed: "
-			 "type %u cin %u [ws %u] sn %u/%u len %zuB\n",
-			 ro_type, ro_cin, roq->ws, ro_sn,
-			 __i2400m_roq_nsn(roq, ro_sn), size);
-		d_dump(2, dev, payload, size);
-		switch(ro_type) {
-		case I2400M_RO_TYPE_RESET:
-			i2400m_roq_reset(i2400m, roq);
-			kfree_skb(skb);	/* no data here */
-			break;
-		case I2400M_RO_TYPE_PACKET:
-			i2400m_roq_queue(i2400m, roq, skb, ro_sn);
-			break;
-		case I2400M_RO_TYPE_WS:
-			i2400m_roq_update_ws(i2400m, roq, ro_sn);
-			kfree_skb(skb);	/* no data here */
-			break;
-		case I2400M_RO_TYPE_PACKET_WS:
-			i2400m_roq_queue_update_ws(i2400m, roq, skb, ro_sn);
-			break;
-		default:
-			dev_err(dev, "HW BUG? unknown reorder type %u\n", ro_type);
-		}
-
-		spin_lock_irqsave(&i2400m->rx_lock, flags);
-		kref_put(&i2400m->rx_roq_refcount, i2400m_rx_roq_destroy);
-		spin_unlock_irqrestore(&i2400m->rx_lock, flags);
-	}
-	else
-		i2400m_net_erx(i2400m, skb, cs);
-error_skb_clone:
-error:
-	d_fnend(2, dev, "(i2400m %p skb_rx %p single %u payload %p "
-		"size %zu) = void\n", i2400m, skb_rx, single_last, payload, size);
-}
-
-
-/*
- * Act on a received payload
- *
- * @i2400m: device instance
- * @skb_rx: skb where the transaction was received
- * @single_last: 1 this is the only payload or the last one (so the
- *     skb can be reused instead of cloned).
- * @pld: payload descriptor
- * @payload: payload data
- *
- * Upon reception of a payload, look at its guts in the payload
- * descriptor and decide what to do with it. If it is a single payload
- * skb or if the last skb is a data packet, the skb will be referenced
- * and modified (so it doesn't have to be cloned).
- */
-static
-void i2400m_rx_payload(struct i2400m *i2400m, struct sk_buff *skb_rx,
-		       unsigned single_last, const struct i2400m_pld *pld,
-		       const void *payload)
-{
-	struct device *dev = i2400m_dev(i2400m);
-	size_t pl_size = i2400m_pld_size(pld);
-	enum i2400m_pt pl_type = i2400m_pld_type(pld);
-
-	d_printf(7, dev, "RX: received payload type %u, %zu bytes\n",
-		 pl_type, pl_size);
-	d_dump(8, dev, payload, pl_size);
-
-	switch (pl_type) {
-	case I2400M_PT_DATA:
-		d_printf(3, dev, "RX: data payload %zu bytes\n", pl_size);
-		i2400m_net_rx(i2400m, skb_rx, single_last, payload, pl_size);
-		break;
-	case I2400M_PT_CTRL:
-		i2400m_rx_ctl(i2400m, skb_rx, payload, pl_size);
-		break;
-	case I2400M_PT_TRACE:
-		i2400m_rx_trace(i2400m, payload, pl_size);
-		break;
-	case I2400M_PT_EDATA:
-		d_printf(3, dev, "ERX: data payload %zu bytes\n", pl_size);
-		i2400m_rx_edata(i2400m, skb_rx, single_last, payload, pl_size);
-		break;
-	default:	/* Anything else shouldn't come to the host */
-		if (printk_ratelimit())
-			dev_err(dev, "RX: HW BUG? unexpected payload type %u\n",
-				pl_type);
-	}
-}
-
-
-/*
- * Check a received transaction's message header
- *
- * @i2400m: device descriptor
- * @msg_hdr: message header
- * @buf_size: size of the received buffer
- *
- * Check that the declarations done by a RX buffer message header are
- * sane and consistent with the amount of data that was received.
- */
-static
-int i2400m_rx_msg_hdr_check(struct i2400m *i2400m,
-			    const struct i2400m_msg_hdr *msg_hdr,
-			    size_t buf_size)
-{
-	int result = -EIO;
-	struct device *dev = i2400m_dev(i2400m);
-	if (buf_size < sizeof(*msg_hdr)) {
-		dev_err(dev, "RX: HW BUG? message with short header (%zu "
-			"vs %zu bytes expected)\n", buf_size, sizeof(*msg_hdr));
-		goto error;
-	}
-	if (msg_hdr->barker != cpu_to_le32(I2400M_D2H_MSG_BARKER)) {
-		dev_err(dev, "RX: HW BUG? message received with unknown "
-			"barker 0x%08x (buf_size %zu bytes)\n",
-			le32_to_cpu(msg_hdr->barker), buf_size);
-		goto error;
-	}
-	if (msg_hdr->num_pls == 0) {
-		dev_err(dev, "RX: HW BUG? zero payload packets in message\n");
-		goto error;
-	}
-	if (le16_to_cpu(msg_hdr->num_pls) > I2400M_MAX_PLS_IN_MSG) {
-		dev_err(dev, "RX: HW BUG? message contains more payload "
-			"than maximum; ignoring.\n");
-		goto error;
-	}
-	result = 0;
-error:
-	return result;
-}
-
-
-/*
- * Check a payload descriptor against the received data
- *
- * @i2400m: device descriptor
- * @pld: payload descriptor
- * @pl_itr: offset (in bytes) in the received buffer the payload is
- *          located
- * @buf_size: size of the received buffer
- *
- * Given a payload descriptor (part of a RX buffer), check it is sane
- * and that the data it declares fits in the buffer.
- */
-static
-int i2400m_rx_pl_descr_check(struct i2400m *i2400m,
-			      const struct i2400m_pld *pld,
-			      size_t pl_itr, size_t buf_size)
-{
-	int result = -EIO;
-	struct device *dev = i2400m_dev(i2400m);
-	size_t pl_size = i2400m_pld_size(pld);
-	enum i2400m_pt pl_type = i2400m_pld_type(pld);
-
-	if (pl_size > i2400m->bus_pl_size_max) {
-		dev_err(dev, "RX: HW BUG? payload @%zu: size %zu is "
-			"bigger than maximum %zu; ignoring message\n",
-			pl_itr, pl_size, i2400m->bus_pl_size_max);
-		goto error;
-	}
-	if (pl_itr + pl_size > buf_size) {	/* enough? */
-		dev_err(dev, "RX: HW BUG? payload @%zu: size %zu "
-			"goes beyond the received buffer "
-			"size (%zu bytes); ignoring message\n",
-			pl_itr, pl_size, buf_size);
-		goto error;
-	}
-	if (pl_type >= I2400M_PT_ILLEGAL) {
-		dev_err(dev, "RX: HW BUG? illegal payload type %u; "
-			"ignoring message\n", pl_type);
-		goto error;
-	}
-	result = 0;
-error:
-	return result;
-}
-
-
-/**
- * i2400m_rx - Receive a buffer of data from the device
- *
- * @i2400m: device descriptor
- * @skb: skbuff where the data has been received
- *
- * Parse in a buffer of data that contains an RX message sent from the
- * device. See the file header for the format. Run all checks on the
- * buffer header, then run over each payload's descriptors, verify
- * their consistency and act on each payload's contents.  If
- * everything is successful, update the device's statistics.
- *
- * Note: You need to set the skb to contain only the length of the
- * received buffer; for that, use skb_trim(skb, RECEIVED_SIZE).
- *
- * Returns:
- *
- * 0 if ok, < 0 errno on error
- *
- * If ok, this function owns now the skb and the caller DOESN'T have
- * to run kfree_skb() on it. However, on error, the caller still owns
- * the skb and it is responsible for releasing it.
- */
-int i2400m_rx(struct i2400m *i2400m, struct sk_buff *skb)
-{
-	int i, result;
-	struct device *dev = i2400m_dev(i2400m);
-	const struct i2400m_msg_hdr *msg_hdr;
-	size_t pl_itr, pl_size;
-	unsigned long flags;
-	unsigned num_pls, single_last, skb_len;
-
-	skb_len = skb->len;
-	d_fnstart(4, dev, "(i2400m %p skb %p [size %u])\n",
-		  i2400m, skb, skb_len);
-	msg_hdr = (void *) skb->data;
-	result = i2400m_rx_msg_hdr_check(i2400m, msg_hdr, skb_len);
-	if (result < 0)
-		goto error_msg_hdr_check;
-	result = -EIO;
-	num_pls = le16_to_cpu(msg_hdr->num_pls);
-	/* Check payload descriptor(s) */
-	pl_itr = struct_size(msg_hdr, pld, num_pls);
-	pl_itr = ALIGN(pl_itr, I2400M_PL_ALIGN);
-	if (pl_itr > skb_len) {	/* got all the payload descriptors? */
-		dev_err(dev, "RX: HW BUG? message too short (%u bytes) for "
-			"%u payload descriptors (%zu each, total %zu)\n",
-			skb_len, num_pls, sizeof(msg_hdr->pld[0]), pl_itr);
-		goto error_pl_descr_short;
-	}
-	/* Walk each payload payload--check we really got it */
-	for (i = 0; i < num_pls; i++) {
-		/* work around old gcc warnings */
-		pl_size = i2400m_pld_size(&msg_hdr->pld[i]);
-		result = i2400m_rx_pl_descr_check(i2400m, &msg_hdr->pld[i],
-						  pl_itr, skb_len);
-		if (result < 0)
-			goto error_pl_descr_check;
-		single_last = num_pls == 1 || i == num_pls - 1;
-		i2400m_rx_payload(i2400m, skb, single_last, &msg_hdr->pld[i],
-				  skb->data + pl_itr);
-		pl_itr += ALIGN(pl_size, I2400M_PL_ALIGN);
-		cond_resched();		/* Don't monopolize */
-	}
-	kfree_skb(skb);
-	/* Update device statistics */
-	spin_lock_irqsave(&i2400m->rx_lock, flags);
-	i2400m->rx_pl_num += i;
-	if (i > i2400m->rx_pl_max)
-		i2400m->rx_pl_max = i;
-	if (i < i2400m->rx_pl_min)
-		i2400m->rx_pl_min = i;
-	i2400m->rx_num++;
-	i2400m->rx_size_acc += skb_len;
-	if (skb_len < i2400m->rx_size_min)
-		i2400m->rx_size_min = skb_len;
-	if (skb_len > i2400m->rx_size_max)
-		i2400m->rx_size_max = skb_len;
-	spin_unlock_irqrestore(&i2400m->rx_lock, flags);
-error_pl_descr_check:
-error_pl_descr_short:
-error_msg_hdr_check:
-	d_fnend(4, dev, "(i2400m %p skb %p [size %u]) = %d\n",
-		i2400m, skb, skb_len, result);
-	return result;
-}
-EXPORT_SYMBOL_GPL(i2400m_rx);
-
-
-void i2400m_unknown_barker(struct i2400m *i2400m,
-			   const void *buf, size_t size)
-{
-	struct device *dev = i2400m_dev(i2400m);
-	char prefix[64];
-	const __le32 *barker = buf;
-	dev_err(dev, "RX: HW BUG? unknown barker %08x, "
-		"dropping %zu bytes\n", le32_to_cpu(*barker), size);
-	snprintf(prefix, sizeof(prefix), "%s %s: ",
-		 dev_driver_string(dev), dev_name(dev));
-	if (size > 64) {
-		print_hex_dump(KERN_ERR, prefix, DUMP_PREFIX_OFFSET,
-			       8, 4, buf, 64, 0);
-		printk(KERN_ERR "%s... (only first 64 bytes "
-		       "dumped)\n", prefix);
-	} else
-		print_hex_dump(KERN_ERR, prefix, DUMP_PREFIX_OFFSET,
-			       8, 4, buf, size, 0);
-}
-EXPORT_SYMBOL(i2400m_unknown_barker);
-
-
-/*
- * Initialize the RX queue and infrastructure
- *
- * This sets up all the RX reordering infrastructures, which will not
- * be used if reordering is not enabled or if the firmware does not
- * support it. The device is told to do reordering in
- * i2400m_dev_initialize(), where it also looks at the value of the
- * i2400m->rx_reorder switch before taking a decission.
- *
- * Note we allocate the roq queues in one chunk and the actual logging
- * support for it (logging) in another one and then we setup the
- * pointers from the first to the last.
- */
-int i2400m_rx_setup(struct i2400m *i2400m)
-{
-	int result = 0;
-
-	i2400m->rx_reorder = i2400m_rx_reorder_disabled? 0 : 1;
-	if (i2400m->rx_reorder) {
-		unsigned itr;
-		struct i2400m_roq_log *rd;
-
-		result = -ENOMEM;
-
-		i2400m->rx_roq = kcalloc(I2400M_RO_CIN + 1,
-					 sizeof(i2400m->rx_roq[0]), GFP_KERNEL);
-		if (i2400m->rx_roq == NULL)
-			goto error_roq_alloc;
-
-		rd = kcalloc(I2400M_RO_CIN + 1, sizeof(*i2400m->rx_roq[0].log),
-			     GFP_KERNEL);
-		if (rd == NULL) {
-			result = -ENOMEM;
-			goto error_roq_log_alloc;
-		}
-
-		for(itr = 0; itr < I2400M_RO_CIN + 1; itr++) {
-			__i2400m_roq_init(&i2400m->rx_roq[itr]);
-			i2400m->rx_roq[itr].log = &rd[itr];
-		}
-		kref_init(&i2400m->rx_roq_refcount);
-	}
-	return 0;
-
-error_roq_log_alloc:
-	kfree(i2400m->rx_roq);
-error_roq_alloc:
-	return result;
-}
-
-
-/* Tear down the RX queue and infrastructure */
-void i2400m_rx_release(struct i2400m *i2400m)
-{
-	unsigned long flags;
-
-	if (i2400m->rx_reorder) {
-		spin_lock_irqsave(&i2400m->rx_lock, flags);
-		kref_put(&i2400m->rx_roq_refcount, i2400m_rx_roq_destroy);
-		spin_unlock_irqrestore(&i2400m->rx_lock, flags);
-	}
-	/* at this point, nothing can be received... */
-	i2400m_report_hook_flush(i2400m);
-}
diff --git a/drivers/net/wimax/i2400m/sysfs.c b/drivers/net/wimax/i2400m/sysfs.c
deleted file mode 100644
index 895ee265909b..000000000000
--- a/drivers/net/wimax/i2400m/sysfs.c
+++ /dev/null
@@ -1,65 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel Wireless WiMAX Connection 2400m
- * Sysfs interfaces to show driver and device information
- *
- * Copyright (C) 2007 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- */
-
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/spinlock.h>
-#include <linux/device.h>
-#include "i2400m.h"
-
-
-#define D_SUBMODULE sysfs
-#include "debug-levels.h"
-
-
-/*
- * Set the idle timeout (msecs)
- *
- * FIXME: eventually this should be a common WiMAX stack method, but
- * would like to wait to see how other devices manage it.
- */
-static
-ssize_t i2400m_idle_timeout_store(struct device *dev,
-				  struct device_attribute *attr,
-				  const char *buf, size_t size)
-{
-	ssize_t result;
-	struct i2400m *i2400m = net_dev_to_i2400m(to_net_dev(dev));
-	unsigned val;
-
-	result = -EINVAL;
-	if (sscanf(buf, "%u\n", &val) != 1)
-		goto error_no_unsigned;
-	if (val != 0 && (val < 100 || val > 300000 || val % 100 != 0)) {
-		dev_err(dev, "idle_timeout: %u: invalid msecs specification; "
-			"valid values are 0, 100-300000 in 100 increments\n",
-			val);
-		goto error_bad_value;
-	}
-	result = i2400m_set_idle_timeout(i2400m, val);
-	if (result >= 0)
-		result = size;
-error_no_unsigned:
-error_bad_value:
-	return result;
-}
-
-static
-DEVICE_ATTR_WO(i2400m_idle_timeout);
-
-static
-struct attribute *i2400m_dev_attrs[] = {
-	&dev_attr_i2400m_idle_timeout.attr,
-	NULL,
-};
-
-struct attribute_group i2400m_dev_attr_group = {
-	.name = NULL,		/* we want them in the same directory */
-	.attrs = i2400m_dev_attrs,
-};
diff --git a/drivers/net/wimax/i2400m/tx.c b/drivers/net/wimax/i2400m/tx.c
deleted file mode 100644
index 1255302e251e..000000000000
--- a/drivers/net/wimax/i2400m/tx.c
+++ /dev/null
@@ -1,1011 +0,0 @@
-/*
- * Intel Wireless WiMAX Connection 2400m
- * Generic (non-bus specific) TX handling
- *
- *
- * Copyright (C) 2007-2008 Intel Corporation. All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- *   * Redistributions of source code must retain the above copyright
- *     notice, this list of conditions and the following disclaimer.
- *   * Redistributions in binary form must reproduce the above copyright
- *     notice, this list of conditions and the following disclaimer in
- *     the documentation and/or other materials provided with the
- *     distribution.
- *   * Neither the name of Intel Corporation nor the names of its
- *     contributors may be used to endorse or promote products derived
- *     from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * Intel Corporation <linux-wimax@intel.com>
- * Yanir Lubetkin <yanirx.lubetkin@intel.com>
- *  - Initial implementation
- *
- * Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *  - Rewritten to use a single FIFO to lower the memory allocation
- *    pressure and optimize cache hits when copying to the queue, as
- *    well as splitting out bus-specific code.
- *
- *
- * Implements data transmission to the device; this is done through a
- * software FIFO, as data/control frames can be coalesced (while the
- * device is reading the previous tx transaction, others accumulate).
- *
- * A FIFO is used because at the end it is resource-cheaper that trying
- * to implement scatter/gather over USB. As well, most traffic is going
- * to be download (vs upload).
- *
- * The format for sending/receiving data to/from the i2400m is
- * described in detail in rx.c:PROTOCOL FORMAT. In here we implement
- * the transmission of that. This is split between a bus-independent
- * part that just prepares everything and a bus-specific part that
- * does the actual transmission over the bus to the device (in the
- * bus-specific driver).
- *
- *
- * The general format of a device-host transaction is MSG-HDR, PLD1,
- * PLD2...PLDN, PL1, PL2,...PLN, PADDING.
- *
- * Because we need the send payload descriptors and then payloads and
- * because it is kind of expensive to do scatterlists in USB (one URB
- * per node), it becomes cheaper to append all the data to a FIFO
- * (copying to a FIFO potentially in cache is cheaper).
- *
- * Then the bus-specific code takes the parts of that FIFO that are
- * written and passes them to the device.
- *
- * So the concepts to keep in mind there are:
- *
- * We use a FIFO to queue the data in a linear buffer. We first append
- * a MSG-HDR, space for I2400M_TX_PLD_MAX payload descriptors and then
- * go appending payloads until we run out of space or of payload
- * descriptors. Then we append padding to make the whole transaction a
- * multiple of i2400m->bus_tx_block_size (as defined by the bus layer).
- *
- * - A TX message: a combination of a message header, payload
- *   descriptors and payloads.
- *
- *     Open: it is marked as active (i2400m->tx_msg is valid) and we
- *       can keep adding payloads to it.
- *
- *     Closed: we are not appending more payloads to this TX message
- *       (exahusted space in the queue, too many payloads or
- *       whichever).  We have appended padding so the whole message
- *       length is aligned to i2400m->bus_tx_block_size (as set by the
- *       bus/transport layer).
- *
- * - Most of the time we keep a TX message open to which we append
- *   payloads.
- *
- * - If we are going to append and there is no more space (we are at
- *   the end of the FIFO), we close the message, mark the rest of the
- *   FIFO space unusable (skip_tail), create a new message at the
- *   beginning of the FIFO (if there is space) and append the message
- *   there.
- *
- *   This is because we need to give linear TX messages to the bus
- *   engine. So we don't write a message to the remaining FIFO space
- *   until the tail and continue at the head of it.
- *
- * - We overload one of the fields in the message header to use it as
- *   'size' of the TX message, so we can iterate over them. It also
- *   contains a flag that indicates if we have to skip it or not.
- *   When we send the buffer, we update that to its real on-the-wire
- *   value.
- *
- * - The MSG-HDR PLD1...PLD2 stuff has to be a size multiple of 16.
- *
- *   It follows that if MSG-HDR says we have N messages, the whole
- *   header + descriptors is 16 + 4*N; for those to be a multiple of
- *   16, it follows that N can be 4, 8, 12, ... (32, 48, 64, 80...
- *   bytes).
- *
- *   So if we have only 1 payload, we have to submit a header that in
- *   all truth has space for 4.
- *
- *   The implication is that we reserve space for 12 (64 bytes); but
- *   if we fill up only (eg) 2, our header becomes 32 bytes only. So
- *   the TX engine has to shift those 32 bytes of msg header and 2
- *   payloads and padding so that right after it the payloads start
- *   and the TX engine has to know about that.
- *
- *   It is cheaper to move the header up than the whole payloads down.
- *
- *   We do this in i2400m_tx_close(). See 'i2400m_msg_hdr->offset'.
- *
- * - Each payload has to be size-padded to 16 bytes; before appending
- *   it, we just do it.
- *
- * - The whole message has to be padded to i2400m->bus_tx_block_size;
- *   we do this at close time. Thus, when reserving space for the
- *   payload, we always make sure there is also free space for this
- *   padding that sooner or later will happen.
- *
- * When we append a message, we tell the bus specific code to kick in
- * TXs. It will TX (in parallel) until the buffer is exhausted--hence
- * the lockin we do. The TX code will only send a TX message at the
- * time (which remember, might contain more than one payload). Of
- * course, when the bus-specific driver attempts to TX a message that
- * is still open, it gets closed first.
- *
- * Gee, this is messy; well a picture. In the example below we have a
- * partially full FIFO, with a closed message ready to be delivered
- * (with a moved message header to make sure it is size-aligned to
- * 16), TAIL room that was unusable (and thus is marked with a message
- * header that says 'skip this') and at the head of the buffer, an
- * incomplete message with a couple of payloads.
- *
- * N   ___________________________________________________
- *    |                                                   |
- *    |     TAIL room                                     |
- *    |                                                   |
- *    |  msg_hdr to skip (size |= 0x80000)                |
- *    |---------------------------------------------------|-------
- *    |                                                   |  /|\
- *    |                                                   |   |
- *    |  TX message padding                               |   |
- *    |                                                   |   |
- *    |                                                   |   |
- *    |- - - - - - - - - - - - - - - - - - - - - - - - - -|   |
- *    |                                                   |   |
- *    |  payload 1                                        |   |
- *    |                                                   | N * tx_block_size
- *    |                                                   |   |
- *    |- - - - - - - - - - - - - - - - - - - - - - - - - -|   |
- *    |                                                   |   |
- *    |  payload 1                                        |   |
- *    |                                                   |   |
- *    |                                                   |   |
- *    |- - - - - - - - - - - - - - - - - - - - - - - - - -|- -|- - - -
- *    |  padding 3                  /|\                   |   |   /|\
- *    |  padding 2                   |                    |   |    |
- *    |  pld 1                32 bytes (2 * 16)           |   |    |
- *    |  pld 0                       |                    |   |    |
- *    |  moved msg_hdr              \|/                   |  \|/   |
- *    |- - - - - - - - - - - - - - - - - - - - - - - - - -|- - -   |
- *    |                                                   |    _PLD_SIZE
- *    |  unused                                           |        |
- *    |                                                   |        |
- *    |- - - - - - - - - - - - - - - - - - - - - - - - - -|        |
- *    |  msg_hdr (size X)       [this message is closed]  |       \|/
- *    |===================================================|========== <=== OUT
- *    |                                                   |
- *    |                                                   |
- *    |                                                   |
- *    |          Free rooom                               |
- *    |                                                   |
- *    |                                                   |
- *    |                                                   |
- *    |                                                   |
- *    |                                                   |
- *    |                                                   |
- *    |                                                   |
- *    |                                                   |
- *    |                                                   |
- *    |===================================================|========== <=== IN
- *    |                                                   |
- *    |                                                   |
- *    |                                                   |
- *    |                                                   |
- *    |  payload 1                                        |
- *    |                                                   |
- *    |                                                   |
- *    |- - - - - - - - - - - - - - - - - - - - - - - - - -|
- *    |                                                   |
- *    |  payload 0                                        |
- *    |                                                   |
- *    |                                                   |
- *    |- - - - - - - - - - - - - - - - - - - - - - - - - -|
- *    |  pld 11                     /|\                   |
- *    |  ...                         |                    |
- *    |  pld 1                64 bytes (2 * 16)           |
- *    |  pld 0                       |                    |
- *    |  msg_hdr (size X)           \|/ [message is open] |
- * 0   ---------------------------------------------------
- *
- *
- * ROADMAP
- *
- * i2400m_tx_setup()           Called by i2400m_setup
- * i2400m_tx_release()         Called by i2400m_release()
- *
- *  i2400m_tx()                 Called to send data or control frames
- *    i2400m_tx_fifo_push()     Allocates append-space in the FIFO
- *    i2400m_tx_new()           Opens a new message in the FIFO
- *    i2400m_tx_fits()          Checks if a new payload fits in the message
- *    i2400m_tx_close()         Closes an open message in the FIFO
- *    i2400m_tx_skip_tail()     Marks unusable FIFO tail space
- *    i2400m->bus_tx_kick()
- *
- * Now i2400m->bus_tx_kick() is the the bus-specific driver backend
- * implementation; that would do:
- *
- * i2400m->bus_tx_kick()
- *   i2400m_tx_msg_get()	Gets first message ready to go
- *   ...sends it...
- *   i2400m_tx_msg_sent()       Ack the message is sent; repeat from
- *                              _tx_msg_get() until it returns NULL
- *                               (FIFO empty).
- */
-#include <linux/netdevice.h>
-#include <linux/slab.h>
-#include <linux/export.h>
-#include "i2400m.h"
-
-
-#define D_SUBMODULE tx
-#include "debug-levels.h"
-
-enum {
-	/**
-	 * TX Buffer size
-	 *
-	 * Doc says maximum transaction is 16KiB. If we had 16KiB en
-	 * route and 16KiB being queued, it boils down to needing
-	 * 32KiB.
-	 * 32KiB is insufficient for 1400 MTU, hence increasing
-	 * tx buffer size to 64KiB.
-	 */
-	I2400M_TX_BUF_SIZE = 65536,
-	/**
-	 * Message header and payload descriptors have to be 16
-	 * aligned (16 + 4 * N = 16 * M). If we take that average sent
-	 * packets are MTU size (~1400-~1500) it follows that we could
-	 * fit at most 10-11 payloads in one transaction. To meet the
-	 * alignment requirement, that means we need to leave space
-	 * for 12 (64 bytes). To simplify, we leave space for that. If
-	 * at the end there are less, we pad up to the nearest
-	 * multiple of 16.
-	 */
-	/*
-	 * According to Intel Wimax i3200, i5x50 and i6x50 specification
-	 * documents, the maximum number of payloads per message can be
-	 * up to 60. Increasing the number of payloads to 60 per message
-	 * helps to accommodate smaller payloads in a single transaction.
-	 */
-	I2400M_TX_PLD_MAX = 60,
-	I2400M_TX_PLD_SIZE = sizeof(struct i2400m_msg_hdr)
-	+ I2400M_TX_PLD_MAX * sizeof(struct i2400m_pld),
-	I2400M_TX_SKIP = 0x80000000,
-	/*
-	 * According to Intel Wimax i3200, i5x50 and i6x50 specification
-	 * documents, the maximum size of each message can be up to 16KiB.
-	 */
-	I2400M_TX_MSG_SIZE = 16384,
-};
-
-#define TAIL_FULL ((void *)~(unsigned long)NULL)
-
-/*
- * Calculate how much tail room is available
- *
- * Note the trick here. This path is ONLY caleed for Case A (see
- * i2400m_tx_fifo_push() below), where we have:
- *
- *       Case A
- * N  ___________
- *   | tail room |
- *   |           |
- *   |<-  IN   ->|
- *   |           |
- *   |   data    |
- *   |           |
- *   |<-  OUT  ->|
- *   |           |
- *   | head room |
- * 0  -----------
- *
- * When calculating the tail_room, tx_in might get to be zero if
- * i2400m->tx_in is right at the end of the buffer (really full
- * buffer) if there is no head room. In this case, tail_room would be
- * I2400M_TX_BUF_SIZE, although it is actually zero. Hence the final
- * mod (%) operation. However, when doing this kind of optimization,
- * i2400m->tx_in being zero would fail, so we treat is an a special
- * case.
- */
-static inline
-size_t __i2400m_tx_tail_room(struct i2400m *i2400m)
-{
-	size_t tail_room;
-	size_t tx_in;
-
-	if (unlikely(i2400m->tx_in == 0))
-		return I2400M_TX_BUF_SIZE;
-	tx_in = i2400m->tx_in % I2400M_TX_BUF_SIZE;
-	tail_room = I2400M_TX_BUF_SIZE - tx_in;
-	tail_room %= I2400M_TX_BUF_SIZE;
-	return tail_room;
-}
-
-
-/*
- * Allocate @size bytes in the TX fifo, return a pointer to it
- *
- * @i2400m: device descriptor
- * @size: size of the buffer we need to allocate
- * @padding: ensure that there is at least this many bytes of free
- *     contiguous space in the fifo. This is needed because later on
- *     we might need to add padding.
- * @try_head: specify either to allocate head room or tail room space
- *     in the TX FIFO. This boolean is required to avoids a system hang
- *     due to an infinite loop caused by i2400m_tx_fifo_push().
- *     The caller must always try to allocate tail room space first by
- *     calling this routine with try_head = 0. In case if there
- *     is not enough tail room space but there is enough head room space,
- *     (i2400m_tx_fifo_push() returns TAIL_FULL) try to allocate head
- *     room space, by calling this routine again with try_head = 1.
- *
- * Returns:
- *
- *     Pointer to the allocated space. NULL if there is no
- *     space. TAIL_FULL if there is no space at the tail but there is at
- *     the head (Case B below).
- *
- * These are the two basic cases we need to keep an eye for -- it is
- * much better explained in linux/kernel/kfifo.c, but this code
- * basically does the same. No rocket science here.
- *
- *       Case A               Case B
- * N  ___________          ___________
- *   | tail room |        |   data    |
- *   |           |        |           |
- *   |<-  IN   ->|        |<-  OUT  ->|
- *   |           |        |           |
- *   |   data    |        |   room    |
- *   |           |        |           |
- *   |<-  OUT  ->|        |<-  IN   ->|
- *   |           |        |           |
- *   | head room |        |   data    |
- * 0  -----------          -----------
- *
- * We allocate only *contiguous* space.
- *
- * We can allocate only from 'room'. In Case B, it is simple; in case
- * A, we only try from the tail room; if it is not enough, we just
- * fail and return TAIL_FULL and let the caller figure out if we wants to
- * skip the tail room and try to allocate from the head.
- *
- * There is a corner case, wherein i2400m_tx_new() can get into
- * an infinite loop calling i2400m_tx_fifo_push().
- * In certain situations, tx_in would have reached on the top of TX FIFO
- * and i2400m_tx_tail_room() returns 0, as described below:
- *
- * N  ___________ tail room is zero
- *   |<-  IN   ->|
- *   |           |
- *   |           |
- *   |           |
- *   |   data    |
- *   |<-  OUT  ->|
- *   |           |
- *   |           |
- *   | head room |
- * 0  -----------
- * During such a time, where tail room is zero in the TX FIFO and if there
- * is a request to add a payload to TX FIFO, which calls:
- * i2400m_tx()
- *         ->calls i2400m_tx_close()
- *         ->calls i2400m_tx_skip_tail()
- *         goto try_new;
- *         ->calls i2400m_tx_new()
- *                    |----> [try_head:]
- *     infinite loop  |     ->calls i2400m_tx_fifo_push()
- *                    |                if (tail_room < needed)
- *                    |                   if (head_room => needed)
- *                    |                       return TAIL_FULL;
- *                    |<----  goto try_head;
- *
- * i2400m_tx() calls i2400m_tx_close() to close the message, since there
- * is no tail room to accommodate the payload and calls
- * i2400m_tx_skip_tail() to skip the tail space. Now i2400m_tx() calls
- * i2400m_tx_new() to allocate space for new message header calling
- * i2400m_tx_fifo_push() that returns TAIL_FULL, since there is no tail space
- * to accommodate the message header, but there is enough head space.
- * The i2400m_tx_new() keeps re-retrying by calling i2400m_tx_fifo_push()
- * ending up in a loop causing system freeze.
- *
- * This corner case is avoided by using a try_head boolean,
- * as an argument to i2400m_tx_fifo_push().
- *
- * Note:
- *
- *     Assumes i2400m->tx_lock is taken, and we use that as a barrier
- *
- *     The indexes keep increasing and we reset them to zero when we
- *     pop data off the queue
- */
-static
-void *i2400m_tx_fifo_push(struct i2400m *i2400m, size_t size,
-			  size_t padding, bool try_head)
-{
-	struct device *dev = i2400m_dev(i2400m);
-	size_t room, tail_room, needed_size;
-	void *ptr;
-
-	needed_size = size + padding;
-	room = I2400M_TX_BUF_SIZE - (i2400m->tx_in - i2400m->tx_out);
-	if (room < needed_size)	{ /* this takes care of Case B */
-		d_printf(2, dev, "fifo push %zu/%zu: no space\n",
-			 size, padding);
-		return NULL;
-	}
-	/* Is there space at the tail? */
-	tail_room = __i2400m_tx_tail_room(i2400m);
-	if (!try_head && tail_room < needed_size) {
-		/*
-		 * If the tail room space is not enough to push the message
-		 * in the TX FIFO, then there are two possibilities:
-		 * 1. There is enough head room space to accommodate
-		 * this message in the TX FIFO.
-		 * 2. There is not enough space in the head room and
-		 * in tail room of the TX FIFO to accommodate the message.
-		 * In the case (1), return TAIL_FULL so that the caller
-		 * can figure out, if the caller wants to push the message
-		 * into the head room space.
-		 * In the case (2), return NULL, indicating that the TX FIFO
-		 * cannot accommodate the message.
-		 */
-		if (room - tail_room >= needed_size) {
-			d_printf(2, dev, "fifo push %zu/%zu: tail full\n",
-				 size, padding);
-			return TAIL_FULL;	/* There might be head space */
-		} else {
-			d_printf(2, dev, "fifo push %zu/%zu: no head space\n",
-				 size, padding);
-			return NULL;	/* There is no space */
-		}
-	}
-	ptr = i2400m->tx_buf + i2400m->tx_in % I2400M_TX_BUF_SIZE;
-	d_printf(2, dev, "fifo push %zu/%zu: at @%zu\n", size, padding,
-		 i2400m->tx_in % I2400M_TX_BUF_SIZE);
-	i2400m->tx_in += size;
-	return ptr;
-}
-
-
-/*
- * Mark the tail of the FIFO buffer as 'to-skip'
- *
- * We should never hit the BUG_ON() because all the sizes we push to
- * the FIFO are padded to be a multiple of 16 -- the size of *msg
- * (I2400M_PL_PAD for the payloads, I2400M_TX_PLD_SIZE for the
- * header).
- *
- * Tail room can get to be zero if a message was opened when there was
- * space only for a header. _tx_close() will mark it as to-skip (as it
- * will have no payloads) and there will be no more space to flush, so
- * nothing has to be done here. This is probably cheaper than ensuring
- * in _tx_new() that there is some space for payloads...as we could
- * always possibly hit the same problem if the payload wouldn't fit.
- *
- * Note:
- *
- *     Assumes i2400m->tx_lock is taken, and we use that as a barrier
- *
- *     This path is only taken for Case A FIFO situations [see
- *     i2400m_tx_fifo_push()]
- */
-static
-void i2400m_tx_skip_tail(struct i2400m *i2400m)
-{
-	struct device *dev = i2400m_dev(i2400m);
-	size_t tx_in = i2400m->tx_in % I2400M_TX_BUF_SIZE;
-	size_t tail_room = __i2400m_tx_tail_room(i2400m);
-	struct i2400m_msg_hdr *msg = i2400m->tx_buf + tx_in;
-	if (unlikely(tail_room == 0))
-		return;
-	BUG_ON(tail_room < sizeof(*msg));
-	msg->size = tail_room | I2400M_TX_SKIP;
-	d_printf(2, dev, "skip tail: skipping %zu bytes @%zu\n",
-		 tail_room, tx_in);
-	i2400m->tx_in += tail_room;
-}
-
-
-/*
- * Check if a skb will fit in the TX queue's current active TX
- * message (if there are still descriptors left unused).
- *
- * Returns:
- *     0 if the message won't fit, 1 if it will.
- *
- * Note:
- *
- *     Assumes a TX message is active (i2400m->tx_msg).
- *
- *     Assumes i2400m->tx_lock is taken, and we use that as a barrier
- */
-static
-unsigned i2400m_tx_fits(struct i2400m *i2400m)
-{
-	struct i2400m_msg_hdr *msg_hdr = i2400m->tx_msg;
-	return le16_to_cpu(msg_hdr->num_pls) < I2400M_TX_PLD_MAX;
-
-}
-
-
-/*
- * Start a new TX message header in the queue.
- *
- * Reserve memory from the base FIFO engine and then just initialize
- * the message header.
- *
- * We allocate the biggest TX message header we might need (one that'd
- * fit I2400M_TX_PLD_MAX payloads) -- when it is closed it will be
- * 'ironed it out' and the unneeded parts removed.
- *
- * NOTE:
- *
- *     Assumes that the previous message is CLOSED (eg: either
- *     there was none or 'i2400m_tx_close()' was called on it).
- *
- *     Assumes i2400m->tx_lock is taken, and we use that as a barrier
- */
-static
-void i2400m_tx_new(struct i2400m *i2400m)
-{
-	struct device *dev = i2400m_dev(i2400m);
-	struct i2400m_msg_hdr *tx_msg;
-	bool try_head = false;
-	BUG_ON(i2400m->tx_msg != NULL);
-	/*
-	 * In certain situations, TX queue might have enough space to
-	 * accommodate the new message header I2400M_TX_PLD_SIZE, but
-	 * might not have enough space to accommodate the payloads.
-	 * Adding bus_tx_room_min padding while allocating a new TX message
-	 * increases the possibilities of including at least one payload of the
-	 * size <= bus_tx_room_min.
-	 */
-try_head:
-	tx_msg = i2400m_tx_fifo_push(i2400m, I2400M_TX_PLD_SIZE,
-				     i2400m->bus_tx_room_min, try_head);
-	if (tx_msg == NULL)
-		goto out;
-	else if (tx_msg == TAIL_FULL) {
-		i2400m_tx_skip_tail(i2400m);
-		d_printf(2, dev, "new TX message: tail full, trying head\n");
-		try_head = true;
-		goto try_head;
-	}
-	memset(tx_msg, 0, I2400M_TX_PLD_SIZE);
-	tx_msg->size = I2400M_TX_PLD_SIZE;
-out:
-	i2400m->tx_msg = tx_msg;
-	d_printf(2, dev, "new TX message: %p @%zu\n",
-		 tx_msg, (void *) tx_msg - i2400m->tx_buf);
-}
-
-
-/*
- * Finalize the current TX message header
- *
- * Sets the message header to be at the proper location depending on
- * how many descriptors we have (check documentation at the file's
- * header for more info on that).
- *
- * Appends padding bytes to make sure the whole TX message (counting
- * from the 'relocated' message header) is aligned to
- * tx_block_size. We assume the _append() code has left enough space
- * in the FIFO for that. If there are no payloads, just pass, as it
- * won't be transferred.
- *
- * The amount of padding bytes depends on how many payloads are in the
- * TX message, as the "msg header and payload descriptors" will be
- * shifted up in the buffer.
- */
-static
-void i2400m_tx_close(struct i2400m *i2400m)
-{
-	struct device *dev = i2400m_dev(i2400m);
-	struct i2400m_msg_hdr *tx_msg = i2400m->tx_msg;
-	struct i2400m_msg_hdr *tx_msg_moved;
-	size_t aligned_size, padding, hdr_size;
-	void *pad_buf;
-	unsigned num_pls;
-
-	if (tx_msg->size & I2400M_TX_SKIP)	/* a skipper? nothing to do */
-		goto out;
-	num_pls = le16_to_cpu(tx_msg->num_pls);
-	/* We can get this situation when a new message was started
-	 * and there was no space to add payloads before hitting the
-	 tail (and taking padding into consideration). */
-	if (num_pls == 0) {
-		tx_msg->size |= I2400M_TX_SKIP;
-		goto out;
-	}
-	/* Relocate the message header
-	 *
-	 * Find the current header size, align it to 16 and if we need
-	 * to move it so the tail is next to the payloads, move it and
-	 * set the offset.
-	 *
-	 * If it moved, this header is good only for transmission; the
-	 * original one (it is kept if we moved) is still used to
-	 * figure out where the next TX message starts (and where the
-	 * offset to the moved header is).
-	 */
-	hdr_size = struct_size(tx_msg, pld, le16_to_cpu(tx_msg->num_pls));
-	hdr_size = ALIGN(hdr_size, I2400M_PL_ALIGN);
-	tx_msg->offset = I2400M_TX_PLD_SIZE - hdr_size;
-	tx_msg_moved = (void *) tx_msg + tx_msg->offset;
-	memmove(tx_msg_moved, tx_msg, hdr_size);
-	tx_msg_moved->size -= tx_msg->offset;
-	/*
-	 * Now figure out how much we have to add to the (moved!)
-	 * message so the size is a multiple of i2400m->bus_tx_block_size.
-	 */
-	aligned_size = ALIGN(tx_msg_moved->size, i2400m->bus_tx_block_size);
-	padding = aligned_size - tx_msg_moved->size;
-	if (padding > 0) {
-		pad_buf = i2400m_tx_fifo_push(i2400m, padding, 0, 0);
-		if (WARN_ON(pad_buf == NULL || pad_buf == TAIL_FULL)) {
-			/* This should not happen -- append should verify
-			 * there is always space left at least to append
-			 * tx_block_size */
-			dev_err(dev,
-				"SW BUG! Possible data leakage from memory the "
-				"device should not read for padding - "
-				"size %lu aligned_size %zu tx_buf %p in "
-				"%zu out %zu\n",
-				(unsigned long) tx_msg_moved->size,
-				aligned_size, i2400m->tx_buf, i2400m->tx_in,
-				i2400m->tx_out);
-		} else
-			memset(pad_buf, 0xad, padding);
-	}
-	tx_msg_moved->padding = cpu_to_le16(padding);
-	tx_msg_moved->size += padding;
-	if (tx_msg != tx_msg_moved)
-		tx_msg->size += padding;
-out:
-	i2400m->tx_msg = NULL;
-}
-
-
-/**
- * i2400m_tx - send the data in a buffer to the device
- *
- * @buf: pointer to the buffer to transmit
- *
- * @buf_len: buffer size
- *
- * @pl_type: type of the payload we are sending.
- *
- * Returns:
- *     0 if ok, < 0 errno code on error (-ENOSPC, if there is no more
- *     room for the message in the queue).
- *
- * Appends the buffer to the TX FIFO and notifies the bus-specific
- * part of the driver that there is new data ready to transmit.
- * Once this function returns, the buffer has been copied, so it can
- * be reused.
- *
- * The steps followed to append are explained in detail in the file
- * header.
- *
- * Whenever we write to a message, we increase msg->size, so it
- * reflects exactly how big the message is. This is needed so that if
- * we concatenate two messages before they can be sent, the code that
- * sends the messages can find the boundaries (and it will replace the
- * size with the real barker before sending).
- *
- * Note:
- *
- *     Cold and warm reset payloads need to be sent as a single
- *     payload, so we handle that.
- */
-int i2400m_tx(struct i2400m *i2400m, const void *buf, size_t buf_len,
-	      enum i2400m_pt pl_type)
-{
-	int result = -ENOSPC;
-	struct device *dev = i2400m_dev(i2400m);
-	unsigned long flags;
-	size_t padded_len;
-	void *ptr;
-	bool try_head = false;
-	unsigned is_singleton = pl_type == I2400M_PT_RESET_WARM
-		|| pl_type == I2400M_PT_RESET_COLD;
-
-	d_fnstart(3, dev, "(i2400m %p skb %p [%zu bytes] pt %u)\n",
-		  i2400m, buf, buf_len, pl_type);
-	padded_len = ALIGN(buf_len, I2400M_PL_ALIGN);
-	d_printf(5, dev, "padded_len %zd buf_len %zd\n", padded_len, buf_len);
-	/* If there is no current TX message, create one; if the
-	 * current one is out of payload slots or we have a singleton,
-	 * close it and start a new one */
-	spin_lock_irqsave(&i2400m->tx_lock, flags);
-	/* If tx_buf is NULL, device is shutdown */
-	if (i2400m->tx_buf == NULL) {
-		result = -ESHUTDOWN;
-		goto error_tx_new;
-	}
-try_new:
-	if (unlikely(i2400m->tx_msg == NULL))
-		i2400m_tx_new(i2400m);
-	else if (unlikely(!i2400m_tx_fits(i2400m)
-			  || (is_singleton && i2400m->tx_msg->num_pls != 0))) {
-		d_printf(2, dev, "closing TX message (fits %u singleton "
-			 "%u num_pls %u)\n", i2400m_tx_fits(i2400m),
-			 is_singleton, i2400m->tx_msg->num_pls);
-		i2400m_tx_close(i2400m);
-		i2400m_tx_new(i2400m);
-	}
-	if (i2400m->tx_msg == NULL)
-		goto error_tx_new;
-	/*
-	 * Check if this skb will fit in the TX queue's current active
-	 * TX message. The total message size must not exceed the maximum
-	 * size of each message I2400M_TX_MSG_SIZE. If it exceeds,
-	 * close the current message and push this skb into the new message.
-	 */
-	if (i2400m->tx_msg->size + padded_len > I2400M_TX_MSG_SIZE) {
-		d_printf(2, dev, "TX: message too big, going new\n");
-		i2400m_tx_close(i2400m);
-		i2400m_tx_new(i2400m);
-	}
-	if (i2400m->tx_msg == NULL)
-		goto error_tx_new;
-	/* So we have a current message header; now append space for
-	 * the message -- if there is not enough, try the head */
-	ptr = i2400m_tx_fifo_push(i2400m, padded_len,
-				  i2400m->bus_tx_block_size, try_head);
-	if (ptr == TAIL_FULL) {	/* Tail is full, try head */
-		d_printf(2, dev, "pl append: tail full\n");
-		i2400m_tx_close(i2400m);
-		i2400m_tx_skip_tail(i2400m);
-		try_head = true;
-		goto try_new;
-	} else if (ptr == NULL) {	/* All full */
-		result = -ENOSPC;
-		d_printf(2, dev, "pl append: all full\n");
-	} else {			/* Got space, copy it, set padding */
-		struct i2400m_msg_hdr *tx_msg = i2400m->tx_msg;
-		unsigned num_pls = le16_to_cpu(tx_msg->num_pls);
-		memcpy(ptr, buf, buf_len);
-		memset(ptr + buf_len, 0xad, padded_len - buf_len);
-		i2400m_pld_set(&tx_msg->pld[num_pls], buf_len, pl_type);
-		d_printf(3, dev, "pld 0x%08x (type 0x%1x len 0x%04zx\n",
-			 le32_to_cpu(tx_msg->pld[num_pls].val),
-			 pl_type, buf_len);
-		tx_msg->num_pls = le16_to_cpu(num_pls+1);
-		tx_msg->size += padded_len;
-		d_printf(2, dev, "TX: appended %zu b (up to %u b) pl #%u\n",
-			padded_len, tx_msg->size, num_pls+1);
-		d_printf(2, dev,
-			 "TX: appended hdr @%zu %zu b pl #%u @%zu %zu/%zu b\n",
-			 (void *)tx_msg - i2400m->tx_buf, (size_t)tx_msg->size,
-			 num_pls+1, ptr - i2400m->tx_buf, buf_len, padded_len);
-		result = 0;
-		if (is_singleton)
-			i2400m_tx_close(i2400m);
-	}
-error_tx_new:
-	spin_unlock_irqrestore(&i2400m->tx_lock, flags);
-	/* kick in most cases, except when the TX subsys is down, as
-	 * it might free space */
-	if (likely(result != -ESHUTDOWN))
-		i2400m->bus_tx_kick(i2400m);
-	d_fnend(3, dev, "(i2400m %p skb %p [%zu bytes] pt %u) = %d\n",
-		i2400m, buf, buf_len, pl_type, result);
-	return result;
-}
-EXPORT_SYMBOL_GPL(i2400m_tx);
-
-
-/**
- * i2400m_tx_msg_get - Get the first TX message in the FIFO to start sending it
- *
- * @i2400m: device descriptors
- * @bus_size: where to place the size of the TX message
- *
- * Called by the bus-specific driver to get the first TX message at
- * the FIF that is ready for transmission.
- *
- * It sets the state in @i2400m to indicate the bus-specific driver is
- * transferring that message (i2400m->tx_msg_size).
- *
- * Once the transfer is completed, call i2400m_tx_msg_sent().
- *
- * Notes:
- *
- *     The size of the TX message to be transmitted might be smaller than
- *     that of the TX message in the FIFO (in case the header was
- *     shorter). Hence, we copy it in @bus_size, for the bus layer to
- *     use. We keep the message's size in i2400m->tx_msg_size so that
- *     when the bus later is done transferring we know how much to
- *     advance the fifo.
- *
- *     We collect statistics here as all the data is available and we
- *     assume it is going to work [see i2400m_tx_msg_sent()].
- */
-struct i2400m_msg_hdr *i2400m_tx_msg_get(struct i2400m *i2400m,
-					 size_t *bus_size)
-{
-	struct device *dev = i2400m_dev(i2400m);
-	struct i2400m_msg_hdr *tx_msg, *tx_msg_moved;
-	unsigned long flags, pls;
-
-	d_fnstart(3, dev, "(i2400m %p bus_size %p)\n", i2400m, bus_size);
-	spin_lock_irqsave(&i2400m->tx_lock, flags);
-	tx_msg_moved = NULL;
-	if (i2400m->tx_buf == NULL)
-		goto out_unlock;
-skip:
-	tx_msg_moved = NULL;
-	if (i2400m->tx_in == i2400m->tx_out) {	/* Empty FIFO? */
-		i2400m->tx_in = 0;
-		i2400m->tx_out = 0;
-		d_printf(2, dev, "TX: FIFO empty: resetting\n");
-		goto out_unlock;
-	}
-	tx_msg = i2400m->tx_buf + i2400m->tx_out % I2400M_TX_BUF_SIZE;
-	if (tx_msg->size & I2400M_TX_SKIP) {	/* skip? */
-		d_printf(2, dev, "TX: skip: msg @%zu (%zu b)\n",
-			 i2400m->tx_out % I2400M_TX_BUF_SIZE,
-			 (size_t) tx_msg->size & ~I2400M_TX_SKIP);
-		i2400m->tx_out += tx_msg->size & ~I2400M_TX_SKIP;
-		goto skip;
-	}
-
-	if (tx_msg->num_pls == 0) {		/* No payloads? */
-		if (tx_msg == i2400m->tx_msg) {	/* open, we are done */
-			d_printf(2, dev,
-				 "TX: FIFO empty: open msg w/o payloads @%zu\n",
-				 (void *) tx_msg - i2400m->tx_buf);
-			tx_msg = NULL;
-			goto out_unlock;
-		} else {			/* closed, skip it */
-			d_printf(2, dev,
-				 "TX: skip msg w/o payloads @%zu (%zu b)\n",
-				 (void *) tx_msg - i2400m->tx_buf,
-				 (size_t) tx_msg->size);
-			i2400m->tx_out += tx_msg->size & ~I2400M_TX_SKIP;
-			goto skip;
-		}
-	}
-	if (tx_msg == i2400m->tx_msg)		/* open msg? */
-		i2400m_tx_close(i2400m);
-
-	/* Now we have a valid TX message (with payloads) to TX */
-	tx_msg_moved = (void *) tx_msg + tx_msg->offset;
-	i2400m->tx_msg_size = tx_msg->size;
-	*bus_size = tx_msg_moved->size;
-	d_printf(2, dev, "TX: pid %d msg hdr at @%zu offset +@%zu "
-		 "size %zu bus_size %zu\n",
-		 current->pid, (void *) tx_msg - i2400m->tx_buf,
-		 (size_t) tx_msg->offset, (size_t) tx_msg->size,
-		 (size_t) tx_msg_moved->size);
-	tx_msg_moved->barker = le32_to_cpu(I2400M_H2D_PREVIEW_BARKER);
-	tx_msg_moved->sequence = le32_to_cpu(i2400m->tx_sequence++);
-
-	pls = le32_to_cpu(tx_msg_moved->num_pls);
-	i2400m->tx_pl_num += pls;		/* Update stats */
-	if (pls > i2400m->tx_pl_max)
-		i2400m->tx_pl_max = pls;
-	if (pls < i2400m->tx_pl_min)
-		i2400m->tx_pl_min = pls;
-	i2400m->tx_num++;
-	i2400m->tx_size_acc += *bus_size;
-	if (*bus_size < i2400m->tx_size_min)
-		i2400m->tx_size_min = *bus_size;
-	if (*bus_size > i2400m->tx_size_max)
-		i2400m->tx_size_max = *bus_size;
-out_unlock:
-	spin_unlock_irqrestore(&i2400m->tx_lock, flags);
-	d_fnstart(3, dev, "(i2400m %p bus_size %p [%zu]) = %p\n",
-		  i2400m, bus_size, *bus_size, tx_msg_moved);
-	return tx_msg_moved;
-}
-EXPORT_SYMBOL_GPL(i2400m_tx_msg_get);
-
-
-/**
- * i2400m_tx_msg_sent - indicate the transmission of a TX message
- *
- * @i2400m: device descriptor
- *
- * Called by the bus-specific driver when a message has been sent;
- * this pops it from the FIFO; and as there is space, start the queue
- * in case it was stopped.
- *
- * Should be called even if the message send failed and we are
- * dropping this TX message.
- */
-void i2400m_tx_msg_sent(struct i2400m *i2400m)
-{
-	unsigned n;
-	unsigned long flags;
-	struct device *dev = i2400m_dev(i2400m);
-
-	d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
-	spin_lock_irqsave(&i2400m->tx_lock, flags);
-	if (i2400m->tx_buf == NULL)
-		goto out_unlock;
-	i2400m->tx_out += i2400m->tx_msg_size;
-	d_printf(2, dev, "TX: sent %zu b\n", (size_t) i2400m->tx_msg_size);
-	i2400m->tx_msg_size = 0;
-	BUG_ON(i2400m->tx_out > i2400m->tx_in);
-	/* level them FIFO markers off */
-	n = i2400m->tx_out / I2400M_TX_BUF_SIZE;
-	i2400m->tx_out %= I2400M_TX_BUF_SIZE;
-	i2400m->tx_in -= n * I2400M_TX_BUF_SIZE;
-out_unlock:
-	spin_unlock_irqrestore(&i2400m->tx_lock, flags);
-	d_fnend(3, dev, "(i2400m %p) = void\n", i2400m);
-}
-EXPORT_SYMBOL_GPL(i2400m_tx_msg_sent);
-
-
-/**
- * i2400m_tx_setup - Initialize the TX queue and infrastructure
- *
- * Make sure we reset the TX sequence to zero, as when this function
- * is called, the firmware has been just restarted. Same rational
- * for tx_in, tx_out, tx_msg_size and tx_msg. We reset them since
- * the memory for TX queue is reallocated.
- */
-int i2400m_tx_setup(struct i2400m *i2400m)
-{
-	int result = 0;
-	void *tx_buf;
-	unsigned long flags;
-
-	/* Do this here only once -- can't do on
-	 * i2400m_hard_start_xmit() as we'll cause race conditions if
-	 * the WS was scheduled on another CPU */
-	INIT_WORK(&i2400m->wake_tx_ws, i2400m_wake_tx_work);
-
-	tx_buf = kmalloc(I2400M_TX_BUF_SIZE, GFP_ATOMIC);
-	if (tx_buf == NULL) {
-		result = -ENOMEM;
-		goto error_kmalloc;
-	}
-
-	/*
-	 * Fail the build if we can't fit at least two maximum size messages
-	 * on the TX FIFO [one being delivered while one is constructed].
-	 */
-	BUILD_BUG_ON(2 * I2400M_TX_MSG_SIZE > I2400M_TX_BUF_SIZE);
-	spin_lock_irqsave(&i2400m->tx_lock, flags);
-	i2400m->tx_sequence = 0;
-	i2400m->tx_in = 0;
-	i2400m->tx_out = 0;
-	i2400m->tx_msg_size = 0;
-	i2400m->tx_msg = NULL;
-	i2400m->tx_buf = tx_buf;
-	spin_unlock_irqrestore(&i2400m->tx_lock, flags);
-	/* Huh? the bus layer has to define this... */
-	BUG_ON(i2400m->bus_tx_block_size == 0);
-error_kmalloc:
-	return result;
-
-}
-
-
-/**
- * i2400m_tx_release - Tear down the TX queue and infrastructure
- */
-void i2400m_tx_release(struct i2400m *i2400m)
-{
-	unsigned long flags;
-	spin_lock_irqsave(&i2400m->tx_lock, flags);
-	kfree(i2400m->tx_buf);
-	i2400m->tx_buf = NULL;
-	spin_unlock_irqrestore(&i2400m->tx_lock, flags);
-}
diff --git a/drivers/net/wimax/i2400m/usb-debug-levels.h b/drivers/net/wimax/i2400m/usb-debug-levels.h
deleted file mode 100644
index b6f7335de765..000000000000
--- a/drivers/net/wimax/i2400m/usb-debug-levels.h
+++ /dev/null
@@ -1,28 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel Wireless WiMAX Connection 2400m
- * Debug levels control file for the i2400m-usb module
- *
- * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- */
-#ifndef __debug_levels__h__
-#define __debug_levels__h__
-
-/* Maximum compile and run time debug level for all submodules */
-#define D_MODULENAME i2400m_usb
-#define D_MASTER CONFIG_WIMAX_I2400M_DEBUG_LEVEL
-
-#include <linux/wimax/debug.h>
-
-/* List of all the enabled modules */
-enum d_module {
-	D_SUBMODULE_DECLARE(usb),
-	D_SUBMODULE_DECLARE(fw),
-	D_SUBMODULE_DECLARE(notif),
-	D_SUBMODULE_DECLARE(rx),
-	D_SUBMODULE_DECLARE(tx),
-};
-
-
-#endif /* #ifndef __debug_levels__h__ */
diff --git a/drivers/net/wimax/i2400m/usb-fw.c b/drivers/net/wimax/i2400m/usb-fw.c
deleted file mode 100644
index 27ab233650d5..000000000000
--- a/drivers/net/wimax/i2400m/usb-fw.c
+++ /dev/null
@@ -1,365 +0,0 @@
-/*
- * Intel Wireless WiMAX Connection 2400m
- * Firmware uploader's USB specifics
- *
- *
- * Copyright (C) 2007-2008 Intel Corporation. All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- *   * Redistributions of source code must retain the above copyright
- *     notice, this list of conditions and the following disclaimer.
- *   * Redistributions in binary form must reproduce the above copyright
- *     notice, this list of conditions and the following disclaimer in
- *     the documentation and/or other materials provided with the
- *     distribution.
- *   * Neither the name of Intel Corporation nor the names of its
- *     contributors may be used to endorse or promote products derived
- *     from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * Intel Corporation <linux-wimax@intel.com>
- * Yanir Lubetkin <yanirx.lubetkin@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *  - Initial implementation
- *
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *  - bus generic/specific split
- *
- * THE PROCEDURE
- *
- * See fw.c for the generic description of this procedure.
- *
- * This file implements only the USB specifics. It boils down to how
- * to send a command and waiting for an acknowledgement from the
- * device.
- *
- * This code (and process) is single threaded. It assumes it is the
- * only thread poking around (guaranteed by fw.c).
- *
- * COMMAND EXECUTION
- *
- * A write URB is posted with the buffer to the bulk output endpoint.
- *
- * ACK RECEPTION
- *
- * We just post a URB to the notification endpoint and wait for
- * data. We repeat until we get all the data we expect (as indicated
- * by the call from the bus generic code).
- *
- * The data is not read from the bulk in endpoint for boot mode.
- *
- * ROADMAP
- *
- * i2400mu_bus_bm_cmd_send
- *   i2400m_bm_cmd_prepare...
- *   i2400mu_tx_bulk_out
- *
- * i2400mu_bus_bm_wait_for_ack
- *   i2400m_notif_submit
- */
-#include <linux/usb.h>
-#include <linux/gfp.h>
-#include "i2400m-usb.h"
-
-
-#define D_SUBMODULE fw
-#include "usb-debug-levels.h"
-
-
-/*
- * Synchronous write to the device
- *
- * Takes care of updating EDC counts and thus, handle device errors.
- */
-static
-ssize_t i2400mu_tx_bulk_out(struct i2400mu *i2400mu, void *buf, size_t buf_size)
-{
-	int result;
-	struct device *dev = &i2400mu->usb_iface->dev;
-	int len;
-	struct usb_endpoint_descriptor *epd;
-	int pipe, do_autopm = 1;
-
-	result = usb_autopm_get_interface(i2400mu->usb_iface);
-	if (result < 0) {
-		dev_err(dev, "BM-CMD: can't get autopm: %d\n", result);
-		do_autopm = 0;
-	}
-	epd = usb_get_epd(i2400mu->usb_iface, i2400mu->endpoint_cfg.bulk_out);
-	pipe = usb_sndbulkpipe(i2400mu->usb_dev, epd->bEndpointAddress);
-retry:
-	result = usb_bulk_msg(i2400mu->usb_dev, pipe, buf, buf_size, &len, 200);
-	switch (result) {
-	case 0:
-		if (len != buf_size) {
-			dev_err(dev, "BM-CMD: short write (%u B vs %zu "
-				"expected)\n", len, buf_size);
-			result = -EIO;
-			break;
-		}
-		result = len;
-		break;
-	case -EPIPE:
-		/*
-		 * Stall -- maybe the device is choking with our
-		 * requests. Clear it and give it some time. If they
-		 * happen to often, it might be another symptom, so we
-		 * reset.
-		 *
-		 * No error handling for usb_clear_halt(0; if it
-		 * works, the retry works; if it fails, this switch
-		 * does the error handling for us.
-		 */
-		if (edc_inc(&i2400mu->urb_edc,
-			    10 * EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME)) {
-			dev_err(dev, "BM-CMD: too many stalls in "
-				"URB; resetting device\n");
-			usb_queue_reset_device(i2400mu->usb_iface);
-		} else {
-			usb_clear_halt(i2400mu->usb_dev, pipe);
-			msleep(10);	/* give the device some time */
-			goto retry;
-		}
-		fallthrough;
-	case -EINVAL:			/* while removing driver */
-	case -ENODEV:			/* dev disconnect ... */
-	case -ENOENT:			/* just ignore it */
-	case -ESHUTDOWN:		/* and exit */
-	case -ECONNRESET:
-		result = -ESHUTDOWN;
-		break;
-	case -ETIMEDOUT:			/* bah... */
-		break;
-	default:				/* any other? */
-		if (edc_inc(&i2400mu->urb_edc,
-			    EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME)) {
-				dev_err(dev, "BM-CMD: maximum errors in "
-					"URB exceeded; resetting device\n");
-				usb_queue_reset_device(i2400mu->usb_iface);
-				result = -ENODEV;
-				break;
-		}
-		dev_err(dev, "BM-CMD: URB error %d, retrying\n",
-			result);
-		goto retry;
-	}
-	if (do_autopm)
-		usb_autopm_put_interface(i2400mu->usb_iface);
-	return result;
-}
-
-
-/*
- * Send a boot-mode command over the bulk-out pipe
- *
- * Command can be a raw command, which requires no preparation (and
- * which might not even be following the command format). Checks that
- * the right amount of data was transferred.
- *
- * To satisfy USB requirements (no onstack, vmalloc or in data segment
- * buffers), we copy the command to i2400m->bm_cmd_buf and send it from
- * there.
- *
- * @flags: pass thru from i2400m_bm_cmd()
- * @return: cmd_size if ok, < 0 errno code on error.
- */
-ssize_t i2400mu_bus_bm_cmd_send(struct i2400m *i2400m,
-				const struct i2400m_bootrom_header *_cmd,
-				size_t cmd_size, int flags)
-{
-	ssize_t result;
-	struct device *dev = i2400m_dev(i2400m);
-	struct i2400mu *i2400mu = container_of(i2400m, struct i2400mu, i2400m);
-	int opcode = _cmd == NULL ? -1 : i2400m_brh_get_opcode(_cmd);
-	struct i2400m_bootrom_header *cmd;
-	size_t cmd_size_a = ALIGN(cmd_size, 16);	/* USB restriction */
-
-	d_fnstart(8, dev, "(i2400m %p cmd %p size %zu)\n",
-		  i2400m, _cmd, cmd_size);
-	result = -E2BIG;
-	if (cmd_size > I2400M_BM_CMD_BUF_SIZE)
-		goto error_too_big;
-	if (_cmd != i2400m->bm_cmd_buf)
-		memmove(i2400m->bm_cmd_buf, _cmd, cmd_size);
-	cmd = i2400m->bm_cmd_buf;
-	if (cmd_size_a > cmd_size)			/* Zero pad space */
-		memset(i2400m->bm_cmd_buf + cmd_size, 0, cmd_size_a - cmd_size);
-	if ((flags & I2400M_BM_CMD_RAW) == 0) {
-		if (WARN_ON(i2400m_brh_get_response_required(cmd) == 0))
-			dev_warn(dev, "SW BUG: response_required == 0\n");
-		i2400m_bm_cmd_prepare(cmd);
-	}
-	result = i2400mu_tx_bulk_out(i2400mu, i2400m->bm_cmd_buf, cmd_size);
-	if (result < 0) {
-		dev_err(dev, "boot-mode cmd %d: cannot send: %zd\n",
-			opcode, result);
-		goto error_cmd_send;
-	}
-	if (result != cmd_size) {		/* all was transferred? */
-		dev_err(dev, "boot-mode cmd %d: incomplete transfer "
-			"(%zd vs %zu submitted)\n",  opcode, result, cmd_size);
-		result = -EIO;
-		goto error_cmd_size;
-	}
-error_cmd_size:
-error_cmd_send:
-error_too_big:
-	d_fnend(8, dev, "(i2400m %p cmd %p size %zu) = %zd\n",
-		i2400m, _cmd, cmd_size, result);
-	return result;
-}
-
-
-static
-void __i2400mu_bm_notif_cb(struct urb *urb)
-{
-	complete(urb->context);
-}
-
-
-/*
- * submit a read to the notification endpoint
- *
- * @i2400m: device descriptor
- * @urb: urb to use
- * @completion: completion variable to complete when done
- *
- * Data is always read to i2400m->bm_ack_buf
- */
-static
-int i2400mu_notif_submit(struct i2400mu *i2400mu, struct urb *urb,
-			 struct completion *completion)
-{
-	struct i2400m *i2400m = &i2400mu->i2400m;
-	struct usb_endpoint_descriptor *epd;
-	int pipe;
-
-	epd = usb_get_epd(i2400mu->usb_iface,
-			  i2400mu->endpoint_cfg.notification);
-	pipe = usb_rcvintpipe(i2400mu->usb_dev, epd->bEndpointAddress);
-	usb_fill_int_urb(urb, i2400mu->usb_dev, pipe,
-			 i2400m->bm_ack_buf, I2400M_BM_ACK_BUF_SIZE,
-			 __i2400mu_bm_notif_cb, completion,
-			 epd->bInterval);
-	return usb_submit_urb(urb, GFP_KERNEL);
-}
-
-
-/*
- * Read an ack from  the notification endpoint
- *
- * @i2400m:
- * @_ack: pointer to where to store the read data
- * @ack_size: how many bytes we should read
- *
- * Returns: < 0 errno code on error; otherwise, amount of received bytes.
- *
- * Submits a notification read, appends the read data to the given ack
- * buffer and then repeats (until @ack_size bytes have been
- * received).
- */
-ssize_t i2400mu_bus_bm_wait_for_ack(struct i2400m *i2400m,
-				    struct i2400m_bootrom_header *_ack,
-				    size_t ack_size)
-{
-	ssize_t result = -ENOMEM;
-	struct device *dev = i2400m_dev(i2400m);
-	struct i2400mu *i2400mu = container_of(i2400m, struct i2400mu, i2400m);
-	struct urb notif_urb;
-	void *ack = _ack;
-	size_t offset, len;
-	long val;
-	int do_autopm = 1;
-	DECLARE_COMPLETION_ONSTACK(notif_completion);
-
-	d_fnstart(8, dev, "(i2400m %p ack %p size %zu)\n",
-		  i2400m, ack, ack_size);
-	BUG_ON(_ack == i2400m->bm_ack_buf);
-	result = usb_autopm_get_interface(i2400mu->usb_iface);
-	if (result < 0) {
-		dev_err(dev, "BM-ACK: can't get autopm: %d\n", (int) result);
-		do_autopm = 0;
-	}
-	usb_init_urb(&notif_urb);	/* ready notifications */
-	usb_get_urb(&notif_urb);
-	offset = 0;
-	while (offset < ack_size) {
-		init_completion(&notif_completion);
-		result = i2400mu_notif_submit(i2400mu, &notif_urb,
-					      &notif_completion);
-		if (result < 0)
-			goto error_notif_urb_submit;
-		val = wait_for_completion_interruptible_timeout(
-			&notif_completion, HZ);
-		if (val == 0) {
-			result = -ETIMEDOUT;
-			usb_kill_urb(&notif_urb);	/* Timedout */
-			goto error_notif_wait;
-		}
-		if (val == -ERESTARTSYS) {
-			result = -EINTR;		/* Interrupted */
-			usb_kill_urb(&notif_urb);
-			goto error_notif_wait;
-		}
-		result = notif_urb.status;		/* How was the ack? */
-		switch (result) {
-		case 0:
-			break;
-		case -EINVAL:			/* while removing driver */
-		case -ENODEV:			/* dev disconnect ... */
-		case -ENOENT:			/* just ignore it */
-		case -ESHUTDOWN:		/* and exit */
-		case -ECONNRESET:
-			result = -ESHUTDOWN;
-			goto error_dev_gone;
-		default:				/* any other? */
-			usb_kill_urb(&notif_urb);	/* Timedout */
-			if (edc_inc(&i2400mu->urb_edc,
-				    EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME))
-				goto error_exceeded;
-			dev_err(dev, "BM-ACK: URB error %d, "
-				"retrying\n", notif_urb.status);
-			continue;	/* retry */
-		}
-		if (notif_urb.actual_length == 0) {
-			d_printf(6, dev, "ZLP received, retrying\n");
-			continue;
-		}
-		/* Got data, append it to the buffer */
-		len = min(ack_size - offset, (size_t) notif_urb.actual_length);
-		memcpy(ack + offset, i2400m->bm_ack_buf, len);
-		offset += len;
-	}
-	result = offset;
-error_notif_urb_submit:
-error_notif_wait:
-error_dev_gone:
-out:
-	if (do_autopm)
-		usb_autopm_put_interface(i2400mu->usb_iface);
-	d_fnend(8, dev, "(i2400m %p ack %p size %zu) = %ld\n",
-		i2400m, ack, ack_size, (long) result);
-	usb_put_urb(&notif_urb);
-	return result;
-
-error_exceeded:
-	dev_err(dev, "bm: maximum errors in notification URB exceeded; "
-		"resetting device\n");
-	usb_queue_reset_device(i2400mu->usb_iface);
-	goto out;
-}
diff --git a/drivers/net/wimax/i2400m/usb-notif.c b/drivers/net/wimax/i2400m/usb-notif.c
deleted file mode 100644
index 5d429f816125..000000000000
--- a/drivers/net/wimax/i2400m/usb-notif.c
+++ /dev/null
@@ -1,258 +0,0 @@
-/*
- * Intel Wireless WiMAX Connection 2400m over USB
- * Notification handling
- *
- *
- * Copyright (C) 2007-2008 Intel Corporation. All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- *   * Redistributions of source code must retain the above copyright
- *     notice, this list of conditions and the following disclaimer.
- *   * Redistributions in binary form must reproduce the above copyright
- *     notice, this list of conditions and the following disclaimer in
- *     the documentation and/or other materials provided with the
- *     distribution.
- *   * Neither the name of Intel Corporation nor the names of its
- *     contributors may be used to endorse or promote products derived
- *     from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * Intel Corporation <linux-wimax@intel.com>
- * Yanir Lubetkin <yanirx.lubetkin@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *  - Initial implementation
- *
- *
- * The notification endpoint is active when the device is not in boot
- * mode; in here we just read and get notifications; based on those,
- * we act to either reinitialize the device after a reboot or to
- * submit a RX request.
- *
- * ROADMAP
- *
- * i2400mu_usb_notification_setup()
- *
- * i2400mu_usb_notification_release()
- *
- * i2400mu_usb_notification_cb()	Called when a URB is ready
- *   i2400mu_notif_grok()
- *     i2400m_is_boot_barker()
- *     i2400m_dev_reset_handle()
- *     i2400mu_rx_kick()
- */
-#include <linux/usb.h>
-#include <linux/slab.h>
-#include "i2400m-usb.h"
-
-
-#define D_SUBMODULE notif
-#include "usb-debug-levels.h"
-
-
-static const
-__le32 i2400m_ZERO_BARKER[4] = { 0, 0, 0, 0 };
-
-
-/*
- * Process a received notification
- *
- * In normal operation mode, we can only receive two types of payloads
- * on the notification endpoint:
- *
- *   - a reboot barker, we do a bootstrap (the device has reseted).
- *
- *   - a block of zeroes: there is pending data in the IN endpoint
- */
-static
-int i2400mu_notification_grok(struct i2400mu *i2400mu, const void *buf,
-				 size_t buf_len)
-{
-	int ret;
-	struct device *dev = &i2400mu->usb_iface->dev;
-	struct i2400m *i2400m = &i2400mu->i2400m;
-
-	d_fnstart(4, dev, "(i2400m %p buf %p buf_len %zu)\n",
-		  i2400mu, buf, buf_len);
-	ret = -EIO;
-	if (buf_len < sizeof(i2400m_ZERO_BARKER))
-		/* Not a bug, just ignore */
-		goto error_bad_size;
-	ret = 0;
-	if (!memcmp(i2400m_ZERO_BARKER, buf, sizeof(i2400m_ZERO_BARKER))) {
-		i2400mu_rx_kick(i2400mu);
-		goto out;
-	}
-	ret = i2400m_is_boot_barker(i2400m, buf, buf_len);
-	if (unlikely(ret >= 0))
-		ret = i2400m_dev_reset_handle(i2400m, "device rebooted");
-	else	/* Unknown or unexpected data in the notif message */
-		i2400m_unknown_barker(i2400m, buf, buf_len);
-error_bad_size:
-out:
-	d_fnend(4, dev, "(i2400m %p buf %p buf_len %zu) = %d\n",
-		i2400mu, buf, buf_len, ret);
-	return ret;
-}
-
-
-/*
- * URB callback for the notification endpoint
- *
- * @urb: the urb received from the notification endpoint
- *
- * This function will just process the USB side of the transaction,
- * checking everything is fine, pass the processing to
- * i2400m_notification_grok() and resubmit the URB.
- */
-static
-void i2400mu_notification_cb(struct urb *urb)
-{
-	int ret;
-	struct i2400mu *i2400mu = urb->context;
-	struct device *dev = &i2400mu->usb_iface->dev;
-
-	d_fnstart(4, dev, "(urb %p status %d actual_length %d)\n",
-		  urb, urb->status, urb->actual_length);
-	ret = urb->status;
-	switch (ret) {
-	case 0:
-		ret = i2400mu_notification_grok(i2400mu, urb->transfer_buffer,
-						urb->actual_length);
-		if (ret == -EIO && edc_inc(&i2400mu->urb_edc, EDC_MAX_ERRORS,
-					   EDC_ERROR_TIMEFRAME))
-			goto error_exceeded;
-		if (ret == -ENOMEM)	/* uff...power cycle? shutdown? */
-			goto error_exceeded;
-		break;
-	case -EINVAL:			/* while removing driver */
-	case -ENODEV:			/* dev disconnect ... */
-	case -ENOENT:			/* ditto */
-	case -ESHUTDOWN:		/* URB killed */
-	case -ECONNRESET:		/* disconnection */
-		goto out;		/* Notify around */
-	default:			/* Some error? */
-		if (edc_inc(&i2400mu->urb_edc,
-			    EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME))
-			goto error_exceeded;
-		dev_err(dev, "notification: URB error %d, retrying\n",
-			urb->status);
-	}
-	usb_mark_last_busy(i2400mu->usb_dev);
-	ret = usb_submit_urb(i2400mu->notif_urb, GFP_ATOMIC);
-	switch (ret) {
-	case 0:
-	case -EINVAL:			/* while removing driver */
-	case -ENODEV:			/* dev disconnect ... */
-	case -ENOENT:			/* ditto */
-	case -ESHUTDOWN:		/* URB killed */
-	case -ECONNRESET:		/* disconnection */
-		break;			/* just ignore */
-	default:			/* Some error? */
-		dev_err(dev, "notification: cannot submit URB: %d\n", ret);
-		goto error_submit;
-	}
-	d_fnend(4, dev, "(urb %p status %d actual_length %d) = void\n",
-		urb, urb->status, urb->actual_length);
-	return;
-
-error_exceeded:
-	dev_err(dev, "maximum errors in notification URB exceeded; "
-		"resetting device\n");
-error_submit:
-	usb_queue_reset_device(i2400mu->usb_iface);
-out:
-	d_fnend(4, dev, "(urb %p status %d actual_length %d) = void\n",
-		urb, urb->status, urb->actual_length);
-}
-
-
-/*
- * setup the notification endpoint
- *
- * @i2400m: device descriptor
- *
- * This procedure prepares the notification urb and handler for receiving
- * unsolicited barkers from the device.
- */
-int i2400mu_notification_setup(struct i2400mu *i2400mu)
-{
-	struct device *dev = &i2400mu->usb_iface->dev;
-	int usb_pipe, ret = 0;
-	struct usb_endpoint_descriptor *epd;
-	char *buf;
-
-	d_fnstart(4, dev, "(i2400m %p)\n", i2400mu);
-	buf = kmalloc(I2400MU_MAX_NOTIFICATION_LEN, GFP_KERNEL | GFP_DMA);
-	if (buf == NULL) {
-		ret = -ENOMEM;
-		goto error_buf_alloc;
-	}
-
-	i2400mu->notif_urb = usb_alloc_urb(0, GFP_KERNEL);
-	if (!i2400mu->notif_urb) {
-		ret = -ENOMEM;
-		goto error_alloc_urb;
-	}
-	epd = usb_get_epd(i2400mu->usb_iface,
-			  i2400mu->endpoint_cfg.notification);
-	usb_pipe = usb_rcvintpipe(i2400mu->usb_dev, epd->bEndpointAddress);
-	usb_fill_int_urb(i2400mu->notif_urb, i2400mu->usb_dev, usb_pipe,
-			 buf, I2400MU_MAX_NOTIFICATION_LEN,
-			 i2400mu_notification_cb, i2400mu, epd->bInterval);
-	ret = usb_submit_urb(i2400mu->notif_urb, GFP_KERNEL);
-	if (ret != 0) {
-		dev_err(dev, "notification: cannot submit URB: %d\n", ret);
-		goto error_submit;
-	}
-	d_fnend(4, dev, "(i2400m %p) = %d\n", i2400mu, ret);
-	return ret;
-
-error_submit:
-	usb_free_urb(i2400mu->notif_urb);
-error_alloc_urb:
-	kfree(buf);
-error_buf_alloc:
-	d_fnend(4, dev, "(i2400m %p) = %d\n", i2400mu, ret);
-	return ret;
-}
-
-
-/*
- * Tear down of the notification mechanism
- *
- * @i2400m: device descriptor
- *
- * Kill the interrupt endpoint urb, free any allocated resources.
- *
- * We need to check if we have done it before as for example,
- * _suspend() call this; if after a suspend() we get a _disconnect()
- * (as the case is when hibernating), nothing bad happens.
- */
-void i2400mu_notification_release(struct i2400mu *i2400mu)
-{
-	struct device *dev = &i2400mu->usb_iface->dev;
-
-	d_fnstart(4, dev, "(i2400mu %p)\n", i2400mu);
-	if (i2400mu->notif_urb != NULL) {
-		usb_kill_urb(i2400mu->notif_urb);
-		kfree(i2400mu->notif_urb->transfer_buffer);
-		usb_free_urb(i2400mu->notif_urb);
-		i2400mu->notif_urb = NULL;
-	}
-	d_fnend(4, dev, "(i2400mu %p)\n", i2400mu);
-}
diff --git a/drivers/net/wimax/i2400m/usb-rx.c b/drivers/net/wimax/i2400m/usb-rx.c
deleted file mode 100644
index 5b64bda7d9e7..000000000000
--- a/drivers/net/wimax/i2400m/usb-rx.c
+++ /dev/null
@@ -1,462 +0,0 @@
-/*
- * Intel Wireless WiMAX Connection 2400m
- * USB RX handling
- *
- *
- * Copyright (C) 2007-2008 Intel Corporation. All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- *   * Redistributions of source code must retain the above copyright
- *     notice, this list of conditions and the following disclaimer.
- *   * Redistributions in binary form must reproduce the above copyright
- *     notice, this list of conditions and the following disclaimer in
- *     the documentation and/or other materials provided with the
- *     distribution.
- *   * Neither the name of Intel Corporation nor the names of its
- *     contributors may be used to endorse or promote products derived
- *     from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * Intel Corporation <linux-wimax@intel.com>
- * Yanir Lubetkin <yanirx.lubetkin@intel.com>
- *  - Initial implementation
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *  - Use skb_clone(), break up processing in chunks
- *  - Split transport/device specific
- *  - Make buffer size dynamic to exert less memory pressure
- *
- *
- * This handles the RX path on USB.
- *
- * When a notification is received that says 'there is RX data ready',
- * we call i2400mu_rx_kick(); that wakes up the RX kthread, which
- * reads a buffer from USB and passes it to i2400m_rx() in the generic
- * handling code. The RX buffer has an specific format that is
- * described in rx.c.
- *
- * We use a kernel thread in a loop because:
- *
- *  - we want to be able to call the USB power management get/put
- *    functions (blocking) before each transaction.
- *
- *  - We might get a lot of notifications and we don't want to submit
- *    a zillion reads; by serializing, we are throttling.
- *
- *  - RX data processing can get heavy enough so that it is not
- *    appropriate for doing it in the USB callback; thus we run it in a
- *    process context.
- *
- * We provide a read buffer of an arbitrary size (short of a page); if
- * the callback reports -EOVERFLOW, it means it was too small, so we
- * just double the size and retry (being careful to append, as
- * sometimes the device provided some data). Every now and then we
- * check if the average packet size is smaller than the current packet
- * size and if so, we halve it. At the end, the size of the
- * preallocated buffer should be following the average received
- * transaction size, adapting dynamically to it.
- *
- * ROADMAP
- *
- * i2400mu_rx_kick()		   Called from notif.c when we get a
- *   			           'data ready' notification
- * i2400mu_rxd()                   Kernel RX daemon
- *   i2400mu_rx()                  Receive USB data
- *   i2400m_rx()                   Send data to generic i2400m RX handling
- *
- * i2400mu_rx_setup()              called from i2400mu_bus_dev_start()
- *
- * i2400mu_rx_release()            called from i2400mu_bus_dev_stop()
- */
-#include <linux/workqueue.h>
-#include <linux/slab.h>
-#include <linux/usb.h>
-#include "i2400m-usb.h"
-
-
-#define D_SUBMODULE rx
-#include "usb-debug-levels.h"
-
-/*
- * Dynamic RX size
- *
- * We can't let the rx_size be a multiple of 512 bytes (the RX
- * endpoint's max packet size). On some USB host controllers (we
- * haven't been able to fully characterize which), if the device is
- * about to send (for example) X bytes and we only post a buffer to
- * receive n*512, it will fail to mark that as babble (so that
- * i2400mu_rx() [case -EOVERFLOW] can resize the buffer and get the
- * rest).
- *
- * So on growing or shrinking, if it is a multiple of the
- * maxpacketsize, we remove some (instead of incresing some, so in a
- * buddy allocator we try to waste less space).
- *
- * Note we also need a hook for this on i2400mu_rx() -- when we do the
- * first read, we are sure we won't hit this spot because
- * i240mm->rx_size has been set properly. However, if we have to
- * double because of -EOVERFLOW, when we launch the read to get the
- * rest of the data, we *have* to make sure that also is not a
- * multiple of the max_pkt_size.
- */
-
-static
-size_t i2400mu_rx_size_grow(struct i2400mu *i2400mu)
-{
-	struct device *dev = &i2400mu->usb_iface->dev;
-	size_t rx_size;
-	const size_t max_pkt_size = 512;
-
-	rx_size = 2 * i2400mu->rx_size;
-	if (rx_size % max_pkt_size == 0) {
-		rx_size -= 8;
-		d_printf(1, dev,
-			 "RX: expected size grew to %zu [adjusted -8] "
-			 "from %zu\n",
-			 rx_size, i2400mu->rx_size);
-	} else
-		d_printf(1, dev,
-			 "RX: expected size grew to %zu from %zu\n",
-			 rx_size, i2400mu->rx_size);
-	return rx_size;
-}
-
-
-static
-void i2400mu_rx_size_maybe_shrink(struct i2400mu *i2400mu)
-{
-	const size_t max_pkt_size = 512;
-	struct device *dev = &i2400mu->usb_iface->dev;
-
-	if (unlikely(i2400mu->rx_size_cnt >= 100
-		     && i2400mu->rx_size_auto_shrink)) {
-		size_t avg_rx_size =
-			i2400mu->rx_size_acc / i2400mu->rx_size_cnt;
-		size_t new_rx_size = i2400mu->rx_size / 2;
-		if (avg_rx_size < new_rx_size) {
-			if (new_rx_size % max_pkt_size == 0) {
-				new_rx_size -= 8;
-				d_printf(1, dev,
-					 "RX: expected size shrank to %zu "
-					 "[adjusted -8] from %zu\n",
-					 new_rx_size, i2400mu->rx_size);
-			} else
-				d_printf(1, dev,
-					 "RX: expected size shrank to %zu "
-					 "from %zu\n",
-					 new_rx_size, i2400mu->rx_size);
-			i2400mu->rx_size = new_rx_size;
-			i2400mu->rx_size_cnt = 0;
-			i2400mu->rx_size_acc = i2400mu->rx_size;
-		}
-	}
-}
-
-/*
- * Receive a message with payloads from the USB bus into an skb
- *
- * @i2400mu: USB device descriptor
- * @rx_skb: skb where to place the received message
- *
- * Deals with all the USB-specifics of receiving, dynamically
- * increasing the buffer size if so needed. Returns the payload in the
- * skb, ready to process. On a zero-length packet, we retry.
- *
- * On soft USB errors, we retry (until they become too frequent and
- * then are promoted to hard); on hard USB errors, we reset the
- * device. On other errors (skb realloacation, we just drop it and
- * hope for the next invocation to solve it).
- *
- * Returns: pointer to the skb if ok, ERR_PTR on error.
- *   NOTE: this function might realloc the skb (if it is too small),
- *   so always update with the one returned.
- *   ERR_PTR() is < 0 on error.
- *   Will return NULL if it cannot reallocate -- this can be
- *   considered a transient retryable error.
- */
-static
-struct sk_buff *i2400mu_rx(struct i2400mu *i2400mu, struct sk_buff *rx_skb)
-{
-	int result = 0;
-	struct device *dev = &i2400mu->usb_iface->dev;
-	int usb_pipe, read_size, rx_size, do_autopm;
-	struct usb_endpoint_descriptor *epd;
-	const size_t max_pkt_size = 512;
-
-	d_fnstart(4, dev, "(i2400mu %p)\n", i2400mu);
-	do_autopm = atomic_read(&i2400mu->do_autopm);
-	result = do_autopm ?
-		usb_autopm_get_interface(i2400mu->usb_iface) : 0;
-	if (result < 0) {
-		dev_err(dev, "RX: can't get autopm: %d\n", result);
-		do_autopm = 0;
-	}
-	epd = usb_get_epd(i2400mu->usb_iface, i2400mu->endpoint_cfg.bulk_in);
-	usb_pipe = usb_rcvbulkpipe(i2400mu->usb_dev, epd->bEndpointAddress);
-retry:
-	rx_size = skb_end_pointer(rx_skb) - rx_skb->data - rx_skb->len;
-	if (unlikely(rx_size % max_pkt_size == 0)) {
-		rx_size -= 8;
-		d_printf(1, dev, "RX: rx_size adapted to %d [-8]\n", rx_size);
-	}
-	result = usb_bulk_msg(
-		i2400mu->usb_dev, usb_pipe, rx_skb->data + rx_skb->len,
-		rx_size, &read_size, 200);
-	usb_mark_last_busy(i2400mu->usb_dev);
-	switch (result) {
-	case 0:
-		if (read_size == 0)
-			goto retry;	/* ZLP, just resubmit */
-		skb_put(rx_skb, read_size);
-		break;
-	case -EPIPE:
-		/*
-		 * Stall -- maybe the device is choking with our
-		 * requests. Clear it and give it some time. If they
-		 * happen to often, it might be another symptom, so we
-		 * reset.
-		 *
-		 * No error handling for usb_clear_halt(0; if it
-		 * works, the retry works; if it fails, this switch
-		 * does the error handling for us.
-		 */
-		if (edc_inc(&i2400mu->urb_edc,
-			    10 * EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME)) {
-			dev_err(dev, "BM-CMD: too many stalls in "
-				"URB; resetting device\n");
-			goto do_reset;
-		}
-		usb_clear_halt(i2400mu->usb_dev, usb_pipe);
-		msleep(10);	/* give the device some time */
-		goto retry;
-	case -EINVAL:			/* while removing driver */
-	case -ENODEV:			/* dev disconnect ... */
-	case -ENOENT:			/* just ignore it */
-	case -ESHUTDOWN:
-	case -ECONNRESET:
-		break;
-	case -EOVERFLOW: {		/* too small, reallocate */
-		struct sk_buff *new_skb;
-		rx_size = i2400mu_rx_size_grow(i2400mu);
-		if (rx_size <= (1 << 16))	/* cap it */
-			i2400mu->rx_size = rx_size;
-		else if (printk_ratelimit()) {
-			dev_err(dev, "BUG? rx_size up to %d\n", rx_size);
-			result = -EINVAL;
-			goto out;
-		}
-		skb_put(rx_skb, read_size);
-		new_skb = skb_copy_expand(rx_skb, 0, rx_size - rx_skb->len,
-					  GFP_KERNEL);
-		if (new_skb == NULL) {
-			kfree_skb(rx_skb);
-			rx_skb = NULL;
-			goto out;	/* drop it...*/
-		}
-		kfree_skb(rx_skb);
-		rx_skb = new_skb;
-		i2400mu->rx_size_cnt = 0;
-		i2400mu->rx_size_acc = i2400mu->rx_size;
-		d_printf(1, dev, "RX: size changed to %d, received %d, "
-			 "copied %d, capacity %ld\n",
-			 rx_size, read_size, rx_skb->len,
-			 (long) skb_end_offset(new_skb));
-		goto retry;
-	}
-		/* In most cases, it happens due to the hardware scheduling a
-		 * read when there was no data - unfortunately, we have no way
-		 * to tell this timeout from a USB timeout. So we just ignore
-		 * it. */
-	case -ETIMEDOUT:
-		dev_err(dev, "RX: timeout: %d\n", result);
-		result = 0;
-		break;
-	default:			/* Any error */
-		if (edc_inc(&i2400mu->urb_edc,
-			    EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME))
-			goto error_reset;
-		dev_err(dev, "RX: error receiving URB: %d, retrying\n", result);
-		goto retry;
-	}
-out:
-	if (do_autopm)
-		usb_autopm_put_interface(i2400mu->usb_iface);
-	d_fnend(4, dev, "(i2400mu %p) = %p\n", i2400mu, rx_skb);
-	return rx_skb;
-
-error_reset:
-	dev_err(dev, "RX: maximum errors in URB exceeded; "
-		"resetting device\n");
-do_reset:
-	usb_queue_reset_device(i2400mu->usb_iface);
-	rx_skb = ERR_PTR(result);
-	goto out;
-}
-
-
-/*
- * Kernel thread for USB reception of data
- *
- * This thread waits for a kick; once kicked, it will allocate an skb
- * and receive a single message to it from USB (using
- * i2400mu_rx()). Once received, it is passed to the generic i2400m RX
- * code for processing.
- *
- * When done processing, it runs some dirty statistics to verify if
- * the last 100 messages received were smaller than half of the
- * current RX buffer size. In that case, the RX buffer size is
- * halved. This will helps lowering the pressure on the memory
- * allocator.
- *
- * Hard errors force the thread to exit.
- */
-static
-int i2400mu_rxd(void *_i2400mu)
-{
-	int result = 0;
-	struct i2400mu *i2400mu = _i2400mu;
-	struct i2400m *i2400m = &i2400mu->i2400m;
-	struct device *dev = &i2400mu->usb_iface->dev;
-	struct net_device *net_dev = i2400m->wimax_dev.net_dev;
-	size_t pending;
-	int rx_size;
-	struct sk_buff *rx_skb;
-	unsigned long flags;
-
-	d_fnstart(4, dev, "(i2400mu %p)\n", i2400mu);
-	spin_lock_irqsave(&i2400m->rx_lock, flags);
-	BUG_ON(i2400mu->rx_kthread != NULL);
-	i2400mu->rx_kthread = current;
-	spin_unlock_irqrestore(&i2400m->rx_lock, flags);
-	while (1) {
-		d_printf(2, dev, "RX: waiting for messages\n");
-		pending = 0;
-		wait_event_interruptible(
-			i2400mu->rx_wq,
-			(kthread_should_stop()	/* check this first! */
-			 || (pending = atomic_read(&i2400mu->rx_pending_count)))
-			);
-		if (kthread_should_stop())
-			break;
-		if (pending == 0)
-			continue;
-		rx_size = i2400mu->rx_size;
-		d_printf(2, dev, "RX: reading up to %d bytes\n", rx_size);
-		rx_skb = __netdev_alloc_skb(net_dev, rx_size, GFP_KERNEL);
-		if (rx_skb == NULL) {
-			dev_err(dev, "RX: can't allocate skb [%d bytes]\n",
-				rx_size);
-			msleep(50);	/* give it some time? */
-			continue;
-		}
-
-		/* Receive the message with the payloads */
-		rx_skb = i2400mu_rx(i2400mu, rx_skb);
-		result = PTR_ERR(rx_skb);
-		if (IS_ERR(rx_skb))
-			goto out;
-		atomic_dec(&i2400mu->rx_pending_count);
-		if (rx_skb == NULL || rx_skb->len == 0) {
-			/* some "ignorable" condition */
-			kfree_skb(rx_skb);
-			continue;
-		}
-
-		/* Deliver the message to the generic i2400m code */
-		i2400mu->rx_size_cnt++;
-		i2400mu->rx_size_acc += rx_skb->len;
-		result = i2400m_rx(i2400m, rx_skb);
-		if (result == -EIO
-		    && edc_inc(&i2400mu->urb_edc,
-			       EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME)) {
-			goto error_reset;
-		}
-
-		/* Maybe adjust RX buffer size */
-		i2400mu_rx_size_maybe_shrink(i2400mu);
-	}
-	result = 0;
-out:
-	spin_lock_irqsave(&i2400m->rx_lock, flags);
-	i2400mu->rx_kthread = NULL;
-	spin_unlock_irqrestore(&i2400m->rx_lock, flags);
-	d_fnend(4, dev, "(i2400mu %p) = %d\n", i2400mu, result);
-	return result;
-
-error_reset:
-	dev_err(dev, "RX: maximum errors in received buffer exceeded; "
-		"resetting device\n");
-	usb_queue_reset_device(i2400mu->usb_iface);
-	goto out;
-}
-
-
-/*
- * Start reading from the device
- *
- * @i2400m: device instance
- *
- * Notify the RX thread that there is data pending.
- */
-void i2400mu_rx_kick(struct i2400mu *i2400mu)
-{
-	struct i2400m *i2400m = &i2400mu->i2400m;
-	struct device *dev = &i2400mu->usb_iface->dev;
-
-	d_fnstart(3, dev, "(i2400mu %p)\n", i2400m);
-	atomic_inc(&i2400mu->rx_pending_count);
-	wake_up_all(&i2400mu->rx_wq);
-	d_fnend(3, dev, "(i2400m %p) = void\n", i2400m);
-}
-
-
-int i2400mu_rx_setup(struct i2400mu *i2400mu)
-{
-	int result = 0;
-	struct i2400m *i2400m = &i2400mu->i2400m;
-	struct device *dev = &i2400mu->usb_iface->dev;
-	struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
-	struct task_struct *kthread;
-
-	kthread = kthread_run(i2400mu_rxd, i2400mu, "%s-rx",
-			      wimax_dev->name);
-	/* the kthread function sets i2400mu->rx_thread */
-	if (IS_ERR(kthread)) {
-		result = PTR_ERR(kthread);
-		dev_err(dev, "RX: cannot start thread: %d\n", result);
-	}
-	return result;
-}
-
-
-void i2400mu_rx_release(struct i2400mu *i2400mu)
-{
-	unsigned long flags;
-	struct i2400m *i2400m = &i2400mu->i2400m;
-	struct device *dev = i2400m_dev(i2400m);
-	struct task_struct *kthread;
-
-	spin_lock_irqsave(&i2400m->rx_lock, flags);
-	kthread = i2400mu->rx_kthread;
-	i2400mu->rx_kthread = NULL;
-	spin_unlock_irqrestore(&i2400m->rx_lock, flags);
-	if (kthread)
-		kthread_stop(kthread);
-	else
-		d_printf(1, dev, "RX: kthread had already exited\n");
-}
-
diff --git a/drivers/net/wimax/i2400m/usb-tx.c b/drivers/net/wimax/i2400m/usb-tx.c
deleted file mode 100644
index 3ba9d70cca1b..000000000000
--- a/drivers/net/wimax/i2400m/usb-tx.c
+++ /dev/null
@@ -1,273 +0,0 @@
-/*
- * Intel Wireless WiMAX Connection 2400m
- * USB specific TX handling
- *
- *
- * Copyright (C) 2007-2008 Intel Corporation. All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- *   * Redistributions of source code must retain the above copyright
- *     notice, this list of conditions and the following disclaimer.
- *   * Redistributions in binary form must reproduce the above copyright
- *     notice, this list of conditions and the following disclaimer in
- *     the documentation and/or other materials provided with the
- *     distribution.
- *   * Neither the name of Intel Corporation nor the names of its
- *     contributors may be used to endorse or promote products derived
- *     from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * Intel Corporation <linux-wimax@intel.com>
- * Yanir Lubetkin <yanirx.lubetkin@intel.com>
- *  - Initial implementation
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *  - Split transport/device specific
- *
- *
- * Takes the TX messages in the i2400m's driver TX FIFO and sends them
- * to the device until there are no more.
- *
- * If we fail sending the message, we just drop it. There isn't much
- * we can do at this point. We could also retry, but the USB stack has
- * already retried and still failed, so there is not much of a
- * point. As well, most of the traffic is network, which has recovery
- * methods for dropped packets.
- *
- * For sending we just obtain a FIFO buffer to send, send it to the
- * USB bulk out, tell the TX FIFO code we have sent it; query for
- * another one, etc... until done.
- *
- * We use a thread so we can call usb_autopm_enable() and
- * usb_autopm_disable() for each transaction; this way when the device
- * goes idle, it will suspend. It also has less overhead than a
- * dedicated workqueue, as it is being used for a single task.
- *
- * ROADMAP
- *
- * i2400mu_tx_setup()
- * i2400mu_tx_release()
- *
- * i2400mu_bus_tx_kick()	- Called by the tx.c code when there
- *                                is new data in the FIFO.
- * i2400mu_txd()
- *   i2400m_tx_msg_get()
- *   i2400m_tx_msg_sent()
- */
-#include "i2400m-usb.h"
-
-
-#define D_SUBMODULE tx
-#include "usb-debug-levels.h"
-
-
-/*
- * Get the next TX message in the TX FIFO and send it to the device
- *
- * Note that any iteration consumes a message to be sent, no matter if
- * it succeeds or fails (we have no real way to retry or complain).
- *
- * Return: 0 if ok, < 0 errno code on hard error.
- */
-static
-int i2400mu_tx(struct i2400mu *i2400mu, struct i2400m_msg_hdr *tx_msg,
-	       size_t tx_msg_size)
-{
-	int result = 0;
-	struct i2400m *i2400m = &i2400mu->i2400m;
-	struct device *dev = &i2400mu->usb_iface->dev;
-	int usb_pipe, sent_size, do_autopm;
-	struct usb_endpoint_descriptor *epd;
-
-	d_fnstart(4, dev, "(i2400mu %p)\n", i2400mu);
-	do_autopm = atomic_read(&i2400mu->do_autopm);
-	result = do_autopm ?
-		usb_autopm_get_interface(i2400mu->usb_iface) : 0;
-	if (result < 0) {
-		dev_err(dev, "TX: can't get autopm: %d\n", result);
-		do_autopm = 0;
-	}
-	epd = usb_get_epd(i2400mu->usb_iface, i2400mu->endpoint_cfg.bulk_out);
-	usb_pipe = usb_sndbulkpipe(i2400mu->usb_dev, epd->bEndpointAddress);
-retry:
-	result = usb_bulk_msg(i2400mu->usb_dev, usb_pipe,
-			      tx_msg, tx_msg_size, &sent_size, 200);
-	usb_mark_last_busy(i2400mu->usb_dev);
-	switch (result) {
-	case 0:
-		if (sent_size != tx_msg_size) {	/* Too short? drop it */
-			dev_err(dev, "TX: short write (%d B vs %zu "
-				"expected)\n", sent_size, tx_msg_size);
-			result = -EIO;
-		}
-		break;
-	case -EPIPE:
-		/*
-		 * Stall -- maybe the device is choking with our
-		 * requests. Clear it and give it some time. If they
-		 * happen to often, it might be another symptom, so we
-		 * reset.
-		 *
-		 * No error handling for usb_clear_halt(0; if it
-		 * works, the retry works; if it fails, this switch
-		 * does the error handling for us.
-		 */
-		if (edc_inc(&i2400mu->urb_edc,
-			    10 * EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME)) {
-			dev_err(dev, "BM-CMD: too many stalls in "
-				"URB; resetting device\n");
-			usb_queue_reset_device(i2400mu->usb_iface);
-		} else {
-			usb_clear_halt(i2400mu->usb_dev, usb_pipe);
-			msleep(10);	/* give the device some time */
-			goto retry;
-		}
-		fallthrough;
-	case -EINVAL:			/* while removing driver */
-	case -ENODEV:			/* dev disconnect ... */
-	case -ENOENT:			/* just ignore it */
-	case -ESHUTDOWN:		/* and exit */
-	case -ECONNRESET:
-		result = -ESHUTDOWN;
-		break;
-	default:			/* Some error? */
-		if (edc_inc(&i2400mu->urb_edc,
-			    EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME)) {
-			dev_err(dev, "TX: maximum errors in URB "
-				"exceeded; resetting device\n");
-			usb_queue_reset_device(i2400mu->usb_iface);
-		} else {
-			dev_err(dev, "TX: cannot send URB; retrying. "
-				"tx_msg @%zu %zu B [%d sent]: %d\n",
-				(void *) tx_msg - i2400m->tx_buf,
-				tx_msg_size, sent_size, result);
-			goto retry;
-		}
-	}
-	if (do_autopm)
-		usb_autopm_put_interface(i2400mu->usb_iface);
-	d_fnend(4, dev, "(i2400mu %p) = result\n", i2400mu);
-	return result;
-}
-
-
-/*
- * Get the next TX message in the TX FIFO and send it to the device
- *
- * Note we exit the loop if i2400mu_tx() fails; that function only
- * fails on hard error (failing to tx a buffer not being one of them,
- * see its doc).
- *
- * Return: 0
- */
-static
-int i2400mu_txd(void *_i2400mu)
-{
-	struct i2400mu *i2400mu = _i2400mu;
-	struct i2400m *i2400m = &i2400mu->i2400m;
-	struct device *dev = &i2400mu->usb_iface->dev;
-	struct i2400m_msg_hdr *tx_msg;
-	size_t tx_msg_size;
-	unsigned long flags;
-
-	d_fnstart(4, dev, "(i2400mu %p)\n", i2400mu);
-
-	spin_lock_irqsave(&i2400m->tx_lock, flags);
-	BUG_ON(i2400mu->tx_kthread != NULL);
-	i2400mu->tx_kthread = current;
-	spin_unlock_irqrestore(&i2400m->tx_lock, flags);
-
-	while (1) {
-		d_printf(2, dev, "TX: waiting for messages\n");
-		tx_msg = NULL;
-		wait_event_interruptible(
-			i2400mu->tx_wq,
-			(kthread_should_stop()	/* check this first! */
-			 || (tx_msg = i2400m_tx_msg_get(i2400m, &tx_msg_size)))
-			);
-		if (kthread_should_stop())
-			break;
-		WARN_ON(tx_msg == NULL);	/* should not happen...*/
-		d_printf(2, dev, "TX: submitting %zu bytes\n", tx_msg_size);
-		d_dump(5, dev, tx_msg, tx_msg_size);
-		/* Yeah, we ignore errors ... not much we can do */
-		i2400mu_tx(i2400mu, tx_msg, tx_msg_size);
-		i2400m_tx_msg_sent(i2400m);	/* ack it, advance the FIFO */
-	}
-
-	spin_lock_irqsave(&i2400m->tx_lock, flags);
-	i2400mu->tx_kthread = NULL;
-	spin_unlock_irqrestore(&i2400m->tx_lock, flags);
-
-	d_fnend(4, dev, "(i2400mu %p)\n", i2400mu);
-	return 0;
-}
-
-
-/*
- * i2400m TX engine notifies us that there is data in the FIFO ready
- * for TX
- *
- * If there is a URB in flight, don't do anything; when it finishes,
- * it will see there is data in the FIFO and send it. Else, just
- * submit a write.
- */
-void i2400mu_bus_tx_kick(struct i2400m *i2400m)
-{
-	struct i2400mu *i2400mu = container_of(i2400m, struct i2400mu, i2400m);
-	struct device *dev = &i2400mu->usb_iface->dev;
-
-	d_fnstart(3, dev, "(i2400m %p) = void\n", i2400m);
-	wake_up_all(&i2400mu->tx_wq);
-	d_fnend(3, dev, "(i2400m %p) = void\n", i2400m);
-}
-
-
-int i2400mu_tx_setup(struct i2400mu *i2400mu)
-{
-	int result = 0;
-	struct i2400m *i2400m = &i2400mu->i2400m;
-	struct device *dev = &i2400mu->usb_iface->dev;
-	struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
-	struct task_struct *kthread;
-
-	kthread = kthread_run(i2400mu_txd, i2400mu, "%s-tx",
-			      wimax_dev->name);
-	/* the kthread function sets i2400mu->tx_thread */
-	if (IS_ERR(kthread)) {
-		result = PTR_ERR(kthread);
-		dev_err(dev, "TX: cannot start thread: %d\n", result);
-	}
-	return result;
-}
-
-void i2400mu_tx_release(struct i2400mu *i2400mu)
-{
-	unsigned long flags;
-	struct i2400m *i2400m = &i2400mu->i2400m;
-	struct device *dev = i2400m_dev(i2400m);
-	struct task_struct *kthread;
-
-	spin_lock_irqsave(&i2400m->tx_lock, flags);
-	kthread = i2400mu->tx_kthread;
-	i2400mu->tx_kthread = NULL;
-	spin_unlock_irqrestore(&i2400m->tx_lock, flags);
-	if (kthread)
-		kthread_stop(kthread);
-	else
-		d_printf(1, dev, "TX: kthread had already exited\n");
-}
diff --git a/drivers/net/wimax/i2400m/usb.c b/drivers/net/wimax/i2400m/usb.c
deleted file mode 100644
index b684e97ac976..000000000000
--- a/drivers/net/wimax/i2400m/usb.c
+++ /dev/null
@@ -1,764 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel Wireless WiMAX Connection 2400m
- * Linux driver model glue for USB device, reset & fw upload
- *
- * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- * Yanir Lubetkin <yanirx.lubetkin@intel.com>
- *
- * See i2400m-usb.h for a general description of this driver.
- *
- * This file implements driver model glue, and hook ups for the
- * generic driver to implement the bus-specific functions (device
- * communication setup/tear down, firmware upload and resetting).
- *
- * ROADMAP
- *
- * i2400mu_probe()
- *   alloc_netdev()...
- *     i2400mu_netdev_setup()
- *       i2400mu_init()
- *       i2400m_netdev_setup()
- *   i2400m_setup()...
- *
- * i2400mu_disconnect
- *   i2400m_release()
- *   free_netdev()
- *
- * i2400mu_suspend()
- *   i2400m_cmd_enter_powersave()
- *   i2400mu_notification_release()
- *
- * i2400mu_resume()
- *   i2400mu_notification_setup()
- *
- * i2400mu_bus_dev_start()        Called by i2400m_dev_start() [who is
- *   i2400mu_tx_setup()           called by i2400m_setup()]
- *   i2400mu_rx_setup()
- *   i2400mu_notification_setup()
- *
- * i2400mu_bus_dev_stop()         Called by i2400m_dev_stop() [who is
- *   i2400mu_notification_release()  called by i2400m_release()]
- *   i2400mu_rx_release()
- *   i2400mu_tx_release()
- *
- * i2400mu_bus_reset()            Called by i2400m_reset
- *   __i2400mu_reset()
- *     __i2400mu_send_barker()
- *   usb_reset_device()
- */
-#include "i2400m-usb.h"
-#include <linux/wimax/i2400m.h>
-#include <linux/debugfs.h>
-#include <linux/slab.h>
-#include <linux/module.h>
-
-
-#define D_SUBMODULE usb
-#include "usb-debug-levels.h"
-
-static char i2400mu_debug_params[128];
-module_param_string(debug, i2400mu_debug_params, sizeof(i2400mu_debug_params),
-		    0644);
-MODULE_PARM_DESC(debug,
-		 "String of space-separated NAME:VALUE pairs, where NAMEs "
-		 "are the different debug submodules and VALUE are the "
-		 "initial debug value to set.");
-
-/* Our firmware file name */
-static const char *i2400mu_bus_fw_names_5x50[] = {
-#define I2400MU_FW_FILE_NAME_v1_5 "i2400m-fw-usb-1.5.sbcf"
-	I2400MU_FW_FILE_NAME_v1_5,
-#define I2400MU_FW_FILE_NAME_v1_4 "i2400m-fw-usb-1.4.sbcf"
-	I2400MU_FW_FILE_NAME_v1_4,
-	NULL,
-};
-
-
-static const char *i2400mu_bus_fw_names_6050[] = {
-#define I6050U_FW_FILE_NAME_v1_5 "i6050-fw-usb-1.5.sbcf"
-	I6050U_FW_FILE_NAME_v1_5,
-	NULL,
-};
-
-
-static
-int i2400mu_bus_dev_start(struct i2400m *i2400m)
-{
-	int result;
-	struct i2400mu *i2400mu = container_of(i2400m, struct i2400mu, i2400m);
-	struct device *dev = &i2400mu->usb_iface->dev;
-
-	d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
-	result = i2400mu_tx_setup(i2400mu);
-	if (result < 0)
-		goto error_usb_tx_setup;
-	result = i2400mu_rx_setup(i2400mu);
-	if (result < 0)
-		goto error_usb_rx_setup;
-	result = i2400mu_notification_setup(i2400mu);
-	if (result < 0)
-		goto error_notif_setup;
-	d_fnend(3, dev, "(i2400m %p) = %d\n", i2400m, result);
-	return result;
-
-error_notif_setup:
-	i2400mu_rx_release(i2400mu);
-error_usb_rx_setup:
-	i2400mu_tx_release(i2400mu);
-error_usb_tx_setup:
-	d_fnend(3, dev, "(i2400m %p) = void\n", i2400m);
-	return result;
-}
-
-
-static
-void i2400mu_bus_dev_stop(struct i2400m *i2400m)
-{
-	struct i2400mu *i2400mu = container_of(i2400m, struct i2400mu, i2400m);
-	struct device *dev = &i2400mu->usb_iface->dev;
-
-	d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
-	i2400mu_notification_release(i2400mu);
-	i2400mu_rx_release(i2400mu);
-	i2400mu_tx_release(i2400mu);
-	d_fnend(3, dev, "(i2400m %p) = void\n", i2400m);
-}
-
-
-/*
- * Sends a barker buffer to the device
- *
- * This helper will allocate a kmalloced buffer and use it to transmit
- * (then free it). Reason for this is that other arches cannot use
- * stack/vmalloc/text areas for DMA transfers.
- *
- * Error recovery here is simpler: anything is considered a hard error
- * and will move the reset code to use a last-resort bus-based reset.
- */
-static
-int __i2400mu_send_barker(struct i2400mu *i2400mu,
-			  const __le32 *barker,
-			  size_t barker_size,
-			  unsigned endpoint)
-{
-	struct usb_endpoint_descriptor *epd = NULL;
-	int pipe, actual_len, ret;
-	struct device *dev = &i2400mu->usb_iface->dev;
-	void *buffer;
-	int do_autopm = 1;
-
-	ret = usb_autopm_get_interface(i2400mu->usb_iface);
-	if (ret < 0) {
-		dev_err(dev, "RESET: can't get autopm: %d\n", ret);
-		do_autopm = 0;
-	}
-	ret = -ENOMEM;
-	buffer = kmalloc(barker_size, GFP_KERNEL);
-	if (buffer == NULL)
-		goto error_kzalloc;
-	epd = usb_get_epd(i2400mu->usb_iface, endpoint);
-	pipe = usb_sndbulkpipe(i2400mu->usb_dev, epd->bEndpointAddress);
-	memcpy(buffer, barker, barker_size);
-retry:
-	ret = usb_bulk_msg(i2400mu->usb_dev, pipe, buffer, barker_size,
-			   &actual_len, 200);
-	switch (ret) {
-	case 0:
-		if (actual_len != barker_size) {	/* Too short? drop it */
-			dev_err(dev, "E: %s: short write (%d B vs %zu "
-				"expected)\n",
-				__func__, actual_len, barker_size);
-			ret = -EIO;
-		}
-		break;
-	case -EPIPE:
-		/*
-		 * Stall -- maybe the device is choking with our
-		 * requests. Clear it and give it some time. If they
-		 * happen to often, it might be another symptom, so we
-		 * reset.
-		 *
-		 * No error handling for usb_clear_halt(0; if it
-		 * works, the retry works; if it fails, this switch
-		 * does the error handling for us.
-		 */
-		if (edc_inc(&i2400mu->urb_edc,
-			    10 * EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME)) {
-			dev_err(dev, "E: %s: too many stalls in "
-				"URB; resetting device\n", __func__);
-			usb_queue_reset_device(i2400mu->usb_iface);
-			/* fallthrough */
-		} else {
-			usb_clear_halt(i2400mu->usb_dev, pipe);
-			msleep(10);	/* give the device some time */
-			goto retry;
-		}
-		fallthrough;
-	case -EINVAL:			/* while removing driver */
-	case -ENODEV:			/* dev disconnect ... */
-	case -ENOENT:			/* just ignore it */
-	case -ESHUTDOWN:		/* and exit */
-	case -ECONNRESET:
-		ret = -ESHUTDOWN;
-		break;
-	default:			/* Some error? */
-		if (edc_inc(&i2400mu->urb_edc,
-			    EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME)) {
-			dev_err(dev, "E: %s: maximum errors in URB "
-				"exceeded; resetting device\n",
-				__func__);
-			usb_queue_reset_device(i2400mu->usb_iface);
-		} else {
-			dev_warn(dev, "W: %s: cannot send URB: %d\n",
-				 __func__, ret);
-			goto retry;
-		}
-	}
-	kfree(buffer);
-error_kzalloc:
-	if (do_autopm)
-		usb_autopm_put_interface(i2400mu->usb_iface);
-	return ret;
-}
-
-
-/*
- * Reset a device at different levels (warm, cold or bus)
- *
- * @i2400m: device descriptor
- * @reset_type: soft, warm or bus reset (I2400M_RT_WARM/SOFT/BUS)
- *
- * Warm and cold resets get a USB reset if they fail.
- *
- * Warm reset:
- *
- * The device will be fully reset internally, but won't be
- * disconnected from the USB bus (so no reenumeration will
- * happen). Firmware upload will be necessary.
- *
- * The device will send a reboot barker in the notification endpoint
- * that will trigger the driver to reinitialize the state
- * automatically from notif.c:i2400m_notification_grok() into
- * i2400m_dev_bootstrap_delayed().
- *
- * Cold and bus (USB) reset:
- *
- * The device will be fully reset internally, disconnected from the
- * USB bus an a reenumeration will happen. Firmware upload will be
- * necessary. Thus, we don't do any locking or struct
- * reinitialization, as we are going to be fully disconnected and
- * reenumerated.
- *
- * Note we need to return -ENODEV if a warm reset was requested and we
- * had to resort to a bus reset. See i2400m_op_reset(), wimax_reset()
- * and wimax_dev->op_reset.
- *
- * WARNING: no driver state saved/fixed
- */
-static
-int i2400mu_bus_reset(struct i2400m *i2400m, enum i2400m_reset_type rt)
-{
-	int result;
-	struct i2400mu *i2400mu =
-		container_of(i2400m, struct i2400mu, i2400m);
-	struct device *dev = i2400m_dev(i2400m);
-	static const __le32 i2400m_WARM_BOOT_BARKER[4] = {
-		cpu_to_le32(I2400M_WARM_RESET_BARKER),
-		cpu_to_le32(I2400M_WARM_RESET_BARKER),
-		cpu_to_le32(I2400M_WARM_RESET_BARKER),
-		cpu_to_le32(I2400M_WARM_RESET_BARKER),
-	};
-	static const __le32 i2400m_COLD_BOOT_BARKER[4] = {
-		cpu_to_le32(I2400M_COLD_RESET_BARKER),
-		cpu_to_le32(I2400M_COLD_RESET_BARKER),
-		cpu_to_le32(I2400M_COLD_RESET_BARKER),
-		cpu_to_le32(I2400M_COLD_RESET_BARKER),
-	};
-
-	d_fnstart(3, dev, "(i2400m %p rt %u)\n", i2400m, rt);
-	if (rt == I2400M_RT_WARM)
-		result = __i2400mu_send_barker(
-			i2400mu, i2400m_WARM_BOOT_BARKER,
-			sizeof(i2400m_WARM_BOOT_BARKER),
-			i2400mu->endpoint_cfg.bulk_out);
-	else if (rt == I2400M_RT_COLD)
-		result = __i2400mu_send_barker(
-			i2400mu, i2400m_COLD_BOOT_BARKER,
-			sizeof(i2400m_COLD_BOOT_BARKER),
-			i2400mu->endpoint_cfg.reset_cold);
-	else if (rt == I2400M_RT_BUS) {
-		result = usb_reset_device(i2400mu->usb_dev);
-		switch (result) {
-		case 0:
-		case -EINVAL:	/* device is gone */
-		case -ENODEV:
-		case -ENOENT:
-		case -ESHUTDOWN:
-			result = 0;
-			break;	/* We assume the device is disconnected */
-		default:
-			dev_err(dev, "USB reset failed (%d), giving up!\n",
-				result);
-		}
-	} else {
-		result = -EINVAL;	/* shut gcc up in certain arches */
-		BUG();
-	}
-	if (result < 0
-	    && result != -EINVAL	/* device is gone */
-	    && rt != I2400M_RT_BUS) {
-		/*
-		 * Things failed -- resort to lower level reset, that
-		 * we queue in another context; the reason for this is
-		 * that the pre and post reset functionality requires
-		 * the i2400m->init_mutex; RT_WARM and RT_COLD can
-		 * come from areas where i2400m->init_mutex is taken.
-		 */
-		dev_err(dev, "%s reset failed (%d); trying USB reset\n",
-			rt == I2400M_RT_WARM ? "warm" : "cold", result);
-		usb_queue_reset_device(i2400mu->usb_iface);
-		result = -ENODEV;
-	}
-	d_fnend(3, dev, "(i2400m %p rt %u) = %d\n", i2400m, rt, result);
-	return result;
-}
-
-static void i2400mu_get_drvinfo(struct net_device *net_dev,
-                                struct ethtool_drvinfo *info)
-{
-	struct i2400m *i2400m = net_dev_to_i2400m(net_dev);
-	struct i2400mu *i2400mu = container_of(i2400m, struct i2400mu, i2400m);
-	struct usb_device *udev = i2400mu->usb_dev;
-
-	strlcpy(info->driver, KBUILD_MODNAME, sizeof(info->driver));
-	strlcpy(info->fw_version, i2400m->fw_name ? : "",
-		sizeof(info->fw_version));
-	usb_make_path(udev, info->bus_info, sizeof(info->bus_info));
-}
-
-static const struct ethtool_ops i2400mu_ethtool_ops = {
-	.get_drvinfo = i2400mu_get_drvinfo,
-	.get_link = ethtool_op_get_link,
-};
-
-static
-void i2400mu_netdev_setup(struct net_device *net_dev)
-{
-	struct i2400m *i2400m = net_dev_to_i2400m(net_dev);
-	struct i2400mu *i2400mu = container_of(i2400m, struct i2400mu, i2400m);
-	i2400mu_init(i2400mu);
-	i2400m_netdev_setup(net_dev);
-	net_dev->ethtool_ops = &i2400mu_ethtool_ops;
-}
-
-
-/*
- * Debug levels control; see debug.h
- */
-struct d_level D_LEVEL[] = {
-	D_SUBMODULE_DEFINE(usb),
-	D_SUBMODULE_DEFINE(fw),
-	D_SUBMODULE_DEFINE(notif),
-	D_SUBMODULE_DEFINE(rx),
-	D_SUBMODULE_DEFINE(tx),
-};
-size_t D_LEVEL_SIZE = ARRAY_SIZE(D_LEVEL);
-
-static
-void i2400mu_debugfs_add(struct i2400mu *i2400mu)
-{
-	struct dentry *dentry = i2400mu->i2400m.wimax_dev.debugfs_dentry;
-
-	dentry = debugfs_create_dir("i2400m-usb", dentry);
-	i2400mu->debugfs_dentry = dentry;
-
-	d_level_register_debugfs("dl_", usb, dentry);
-	d_level_register_debugfs("dl_", fw, dentry);
-	d_level_register_debugfs("dl_", notif, dentry);
-	d_level_register_debugfs("dl_", rx, dentry);
-	d_level_register_debugfs("dl_", tx, dentry);
-
-	/* Don't touch these if you don't know what you are doing */
-	debugfs_create_u8("rx_size_auto_shrink", 0600, dentry,
-			  &i2400mu->rx_size_auto_shrink);
-
-	debugfs_create_size_t("rx_size", 0600, dentry, &i2400mu->rx_size);
-}
-
-
-static struct device_type i2400mu_type = {
-	.name	= "wimax",
-};
-
-/*
- * Probe a i2400m interface and register it
- *
- * @iface:   USB interface to link to
- * @id:      USB class/subclass/protocol id
- * @returns: 0 if ok, < 0 errno code on error.
- *
- * Alloc a net device, initialize the bus-specific details and then
- * calls the bus-generic initialization routine. That will register
- * the wimax and netdev devices, upload the firmware [using
- * _bus_bm_*()], call _bus_dev_start() to finalize the setup of the
- * communication with the device and then will start to talk to it to
- * finnish setting it up.
- */
-static
-int i2400mu_probe(struct usb_interface *iface,
-		  const struct usb_device_id *id)
-{
-	int result;
-	struct net_device *net_dev;
-	struct device *dev = &iface->dev;
-	struct i2400m *i2400m;
-	struct i2400mu *i2400mu;
-	struct usb_device *usb_dev = interface_to_usbdev(iface);
-
-	if (iface->cur_altsetting->desc.bNumEndpoints < 4)
-		return -ENODEV;
-
-	if (usb_dev->speed != USB_SPEED_HIGH)
-		dev_err(dev, "device not connected as high speed\n");
-
-	/* Allocate instance [calls i2400m_netdev_setup() on it]. */
-	result = -ENOMEM;
-	net_dev = alloc_netdev(sizeof(*i2400mu), "wmx%d", NET_NAME_UNKNOWN,
-			       i2400mu_netdev_setup);
-	if (net_dev == NULL) {
-		dev_err(dev, "no memory for network device instance\n");
-		goto error_alloc_netdev;
-	}
-	SET_NETDEV_DEV(net_dev, dev);
-	SET_NETDEV_DEVTYPE(net_dev, &i2400mu_type);
-	i2400m = net_dev_to_i2400m(net_dev);
-	i2400mu = container_of(i2400m, struct i2400mu, i2400m);
-	i2400m->wimax_dev.net_dev = net_dev;
-	i2400mu->usb_dev = usb_get_dev(usb_dev);
-	i2400mu->usb_iface = iface;
-	usb_set_intfdata(iface, i2400mu);
-
-	i2400m->bus_tx_block_size = I2400MU_BLK_SIZE;
-	/*
-	 * Room required in the Tx queue for USB message to accommodate
-	 * a smallest payload while allocating header space is 16 bytes.
-	 * Adding this room  for the new tx message increases the
-	 * possibilities of including any payload with size <= 16 bytes.
-	 */
-	i2400m->bus_tx_room_min = I2400MU_BLK_SIZE;
-	i2400m->bus_pl_size_max = I2400MU_PL_SIZE_MAX;
-	i2400m->bus_setup = NULL;
-	i2400m->bus_dev_start = i2400mu_bus_dev_start;
-	i2400m->bus_dev_stop = i2400mu_bus_dev_stop;
-	i2400m->bus_release = NULL;
-	i2400m->bus_tx_kick = i2400mu_bus_tx_kick;
-	i2400m->bus_reset = i2400mu_bus_reset;
-	i2400m->bus_bm_retries = I2400M_USB_BOOT_RETRIES;
-	i2400m->bus_bm_cmd_send = i2400mu_bus_bm_cmd_send;
-	i2400m->bus_bm_wait_for_ack = i2400mu_bus_bm_wait_for_ack;
-	i2400m->bus_bm_mac_addr_impaired = 0;
-
-	switch (id->idProduct) {
-	case USB_DEVICE_ID_I6050:
-	case USB_DEVICE_ID_I6050_2:
-	case USB_DEVICE_ID_I6150:
-	case USB_DEVICE_ID_I6150_2:
-	case USB_DEVICE_ID_I6150_3:
-	case USB_DEVICE_ID_I6250:
-		i2400mu->i6050 = 1;
-		break;
-	default:
-		break;
-	}
-
-	if (i2400mu->i6050) {
-		i2400m->bus_fw_names = i2400mu_bus_fw_names_6050;
-		i2400mu->endpoint_cfg.bulk_out = 0;
-		i2400mu->endpoint_cfg.notification = 3;
-		i2400mu->endpoint_cfg.reset_cold = 2;
-		i2400mu->endpoint_cfg.bulk_in = 1;
-	} else {
-		i2400m->bus_fw_names = i2400mu_bus_fw_names_5x50;
-		i2400mu->endpoint_cfg.bulk_out = 0;
-		i2400mu->endpoint_cfg.notification = 1;
-		i2400mu->endpoint_cfg.reset_cold = 2;
-		i2400mu->endpoint_cfg.bulk_in = 3;
-	}
-#ifdef CONFIG_PM
-	iface->needs_remote_wakeup = 1;		/* autosuspend (15s delay) */
-	device_init_wakeup(dev, 1);
-	pm_runtime_set_autosuspend_delay(&usb_dev->dev, 15000);
-	usb_enable_autosuspend(usb_dev);
-#endif
-
-	result = i2400m_setup(i2400m, I2400M_BRI_MAC_REINIT);
-	if (result < 0) {
-		dev_err(dev, "cannot setup device: %d\n", result);
-		goto error_setup;
-	}
-	i2400mu_debugfs_add(i2400mu);
-	return 0;
-
-error_setup:
-	usb_set_intfdata(iface, NULL);
-	usb_put_dev(i2400mu->usb_dev);
-	free_netdev(net_dev);
-error_alloc_netdev:
-	return result;
-}
-
-
-/*
- * Disconnect a i2400m from the system.
- *
- * i2400m_stop() has been called before, so al the rx and tx contexts
- * have been taken down already. Make sure the queue is stopped,
- * unregister netdev and i2400m, free and kill.
- */
-static
-void i2400mu_disconnect(struct usb_interface *iface)
-{
-	struct i2400mu *i2400mu = usb_get_intfdata(iface);
-	struct i2400m *i2400m = &i2400mu->i2400m;
-	struct net_device *net_dev = i2400m->wimax_dev.net_dev;
-	struct device *dev = &iface->dev;
-
-	d_fnstart(3, dev, "(iface %p i2400m %p)\n", iface, i2400m);
-
-	debugfs_remove_recursive(i2400mu->debugfs_dentry);
-	i2400m_release(i2400m);
-	usb_set_intfdata(iface, NULL);
-	usb_put_dev(i2400mu->usb_dev);
-	free_netdev(net_dev);
-	d_fnend(3, dev, "(iface %p i2400m %p) = void\n", iface, i2400m);
-}
-
-
-/*
- * Get the device ready for USB port or system standby and hibernation
- *
- * USB port and system standby are handled the same.
- *
- * When the system hibernates, the USB device is powered down and then
- * up, so we don't really have to do much here, as it will be seen as
- * a reconnect. Still for simplicity we consider this case the same as
- * suspend, so that the device has a chance to do notify the base
- * station (if connected).
- *
- * So at the end, the three cases require common handling.
- *
- * If at the time of this call the device's firmware is not loaded,
- * nothing has to be done. Note we can be "loose" about not reading
- * i2400m->updown under i2400m->init_mutex. If it happens to change
- * inmediately, other parts of the call flow will fail and effectively
- * catch it.
- *
- * If the firmware is loaded, we need to:
- *
- *  - tell the device to go into host interface power save mode, wait
- *    for it to ack
- *
- *    This is quite more interesting than it is; we need to execute a
- *    command, but this time, we don't want the code in usb-{tx,rx}.c
- *    to call the usb_autopm_get/put_interface() barriers as it'd
- *    deadlock, so we need to decrement i2400mu->do_autopm, that acts
- *    as a poor man's semaphore. Ugly, but it works.
- *
- *    As well, the device might refuse going to sleep for whichever
- *    reason. In this case we just fail. For system suspend/hibernate,
- *    we *can't* fail. We check PMSG_IS_AUTO to see if the
- *    suspend call comes from the USB stack or from the system and act
- *    in consequence.
- *
- *  - stop the notification endpoint polling
- */
-static
-int i2400mu_suspend(struct usb_interface *iface, pm_message_t pm_msg)
-{
-	int result = 0;
-	struct device *dev = &iface->dev;
-	struct i2400mu *i2400mu = usb_get_intfdata(iface);
-	unsigned is_autosuspend = 0;
-	struct i2400m *i2400m = &i2400mu->i2400m;
-
-#ifdef CONFIG_PM
-	if (PMSG_IS_AUTO(pm_msg))
-		is_autosuspend = 1;
-#endif
-
-	d_fnstart(3, dev, "(iface %p pm_msg %u)\n", iface, pm_msg.event);
-	rmb();		/* see i2400m->updown's documentation  */
-	if (i2400m->updown == 0)
-		goto no_firmware;
-	if (i2400m->state == I2400M_SS_DATA_PATH_CONNECTED && is_autosuspend) {
-		/* ugh -- the device is connected and this suspend
-		 * request is an autosuspend one (not a system standby
-		 * / hibernate).
-		 *
-		 * The only way the device can go to standby is if the
-		 * link with the base station is in IDLE mode; that
-		 * were the case, we'd be in status
-		 * I2400M_SS_CONNECTED_IDLE. But we are not.
-		 *
-		 * If we *tell* him to go power save now, it'll reset
-		 * as a precautionary measure, so if this is an
-		 * autosuspend thing, say no and it'll come back
-		 * later, when the link is IDLE
-		 */
-		result = -EBADF;
-		d_printf(1, dev, "fw up, link up, not-idle, autosuspend: "
-			 "not entering powersave\n");
-		goto error_not_now;
-	}
-	d_printf(1, dev, "fw up: entering powersave\n");
-	atomic_dec(&i2400mu->do_autopm);
-	result = i2400m_cmd_enter_powersave(i2400m);
-	atomic_inc(&i2400mu->do_autopm);
-	if (result < 0 && !is_autosuspend) {
-		/* System suspend, can't fail */
-		dev_err(dev, "failed to suspend, will reset on resume\n");
-		result = 0;
-	}
-	if (result < 0)
-		goto error_enter_powersave;
-	i2400mu_notification_release(i2400mu);
-	d_printf(1, dev, "powersave requested\n");
-error_enter_powersave:
-error_not_now:
-no_firmware:
-	d_fnend(3, dev, "(iface %p pm_msg %u) = %d\n",
-		iface, pm_msg.event, result);
-	return result;
-}
-
-
-static
-int i2400mu_resume(struct usb_interface *iface)
-{
-	int ret = 0;
-	struct device *dev = &iface->dev;
-	struct i2400mu *i2400mu = usb_get_intfdata(iface);
-	struct i2400m *i2400m = &i2400mu->i2400m;
-
-	d_fnstart(3, dev, "(iface %p)\n", iface);
-	rmb();		/* see i2400m->updown's documentation  */
-	if (i2400m->updown == 0) {
-		d_printf(1, dev, "fw was down, no resume needed\n");
-		goto out;
-	}
-	d_printf(1, dev, "fw was up, resuming\n");
-	i2400mu_notification_setup(i2400mu);
-	/* USB has flow control, so we don't need to give it time to
-	 * come back; otherwise, we'd use something like a get-state
-	 * command... */
-out:
-	d_fnend(3, dev, "(iface %p) = %d\n", iface, ret);
-	return ret;
-}
-
-
-static
-int i2400mu_reset_resume(struct usb_interface *iface)
-{
-	int result;
-	struct device *dev = &iface->dev;
-	struct i2400mu *i2400mu = usb_get_intfdata(iface);
-	struct i2400m *i2400m = &i2400mu->i2400m;
-
-	d_fnstart(3, dev, "(iface %p)\n", iface);
-	result = i2400m_dev_reset_handle(i2400m, "device reset on resume");
-	d_fnend(3, dev, "(iface %p) = %d\n", iface, result);
-	return result < 0 ? result : 0;
-}
-
-
-/*
- * Another driver or user space is triggering a reset on the device
- * which contains the interface passed as an argument. Cease IO and
- * save any device state you need to restore.
- *
- * If you need to allocate memory here, use GFP_NOIO or GFP_ATOMIC, if
- * you are in atomic context.
- */
-static
-int i2400mu_pre_reset(struct usb_interface *iface)
-{
-	struct i2400mu *i2400mu = usb_get_intfdata(iface);
-	return i2400m_pre_reset(&i2400mu->i2400m);
-}
-
-
-/*
- * The reset has completed.  Restore any saved device state and begin
- * using the device again.
- *
- * If you need to allocate memory here, use GFP_NOIO or GFP_ATOMIC, if
- * you are in atomic context.
- */
-static
-int i2400mu_post_reset(struct usb_interface *iface)
-{
-	struct i2400mu *i2400mu = usb_get_intfdata(iface);
-	return i2400m_post_reset(&i2400mu->i2400m);
-}
-
-
-static
-struct usb_device_id i2400mu_id_table[] = {
-	{ USB_DEVICE(0x8086, USB_DEVICE_ID_I6050) },
-	{ USB_DEVICE(0x8086, USB_DEVICE_ID_I6050_2) },
-	{ USB_DEVICE(0x8087, USB_DEVICE_ID_I6150) },
-	{ USB_DEVICE(0x8087, USB_DEVICE_ID_I6150_2) },
-	{ USB_DEVICE(0x8087, USB_DEVICE_ID_I6150_3) },
-	{ USB_DEVICE(0x8086, USB_DEVICE_ID_I6250) },
-	{ USB_DEVICE(0x8086, 0x0181) },
-	{ USB_DEVICE(0x8086, 0x1403) },
-	{ USB_DEVICE(0x8086, 0x1405) },
-	{ USB_DEVICE(0x8086, 0x0180) },
-	{ USB_DEVICE(0x8086, 0x0182) },
-	{ USB_DEVICE(0x8086, 0x1406) },
-	{ USB_DEVICE(0x8086, 0x1403) },
-	{ },
-};
-MODULE_DEVICE_TABLE(usb, i2400mu_id_table);
-
-
-static
-struct usb_driver i2400mu_driver = {
-	.name = KBUILD_MODNAME,
-	.suspend = i2400mu_suspend,
-	.resume = i2400mu_resume,
-	.reset_resume = i2400mu_reset_resume,
-	.probe = i2400mu_probe,
-	.disconnect = i2400mu_disconnect,
-	.pre_reset = i2400mu_pre_reset,
-	.post_reset = i2400mu_post_reset,
-	.id_table = i2400mu_id_table,
-	.supports_autosuspend = 1,
-};
-
-static
-int __init i2400mu_driver_init(void)
-{
-	d_parse_params(D_LEVEL, D_LEVEL_SIZE, i2400mu_debug_params,
-		       "i2400m_usb.debug");
-	return usb_register(&i2400mu_driver);
-}
-module_init(i2400mu_driver_init);
-
-
-static
-void __exit i2400mu_driver_exit(void)
-{
-	usb_deregister(&i2400mu_driver);
-}
-module_exit(i2400mu_driver_exit);
-
-MODULE_AUTHOR("Intel Corporation <linux-wimax@intel.com>");
-MODULE_DESCRIPTION("Driver for USB based Intel Wireless WiMAX Connection 2400M "
-		   "(5x50 & 6050)");
-MODULE_LICENSE("GPL");
-MODULE_FIRMWARE(I2400MU_FW_FILE_NAME_v1_5);
-MODULE_FIRMWARE(I6050U_FW_FILE_NAME_v1_5);
diff --git a/drivers/staging/Kconfig b/drivers/staging/Kconfig
index 2d0310448eba..443ca3f3cdf0 100644
--- a/drivers/staging/Kconfig
+++ b/drivers/staging/Kconfig
@@ -114,6 +114,8 @@ source "drivers/staging/kpc2000/Kconfig"
 
 source "drivers/staging/qlge/Kconfig"
 
+source "drivers/staging/wimax/Kconfig"
+
 source "drivers/staging/wfx/Kconfig"
 
 source "drivers/staging/hikey9xx/Kconfig"
diff --git a/drivers/staging/Makefile b/drivers/staging/Makefile
index 757a892ab5b9..dc45128ef525 100644
--- a/drivers/staging/Makefile
+++ b/drivers/staging/Makefile
@@ -47,5 +47,6 @@ obj-$(CONFIG_XIL_AXIS_FIFO)	+= axis-fifo/
 obj-$(CONFIG_FIELDBUS_DEV)     += fieldbus/
 obj-$(CONFIG_KPC2000)		+= kpc2000/
 obj-$(CONFIG_QLGE)		+= qlge/
+obj-$(CONFIG_WIMAX)		+= wimax/
 obj-$(CONFIG_WFX)		+= wfx/
 obj-y				+= hikey9xx/
diff --git a/drivers/staging/wimax/Documentation/i2400m.rst b/drivers/staging/wimax/Documentation/i2400m.rst
new file mode 100644
index 000000000000..194388c0c351
--- /dev/null
+++ b/drivers/staging/wimax/Documentation/i2400m.rst
@@ -0,0 +1,283 @@
+.. include:: <isonum.txt>
+
+====================================================
+Driver for the Intel Wireless Wimax Connection 2400m
+====================================================
+
+:Copyright: |copy| 2008 Intel Corporation < linux-wimax@intel.com >
+
+   This provides a driver for the Intel Wireless WiMAX Connection 2400m
+   and a basic Linux kernel WiMAX stack.
+
+1. Requirements
+===============
+
+     * Linux installation with Linux kernel 2.6.22 or newer (if building
+       from a separate tree)
+     * Intel i2400m Echo Peak or Baxter Peak; this includes the Intel
+       Wireless WiMAX/WiFi Link 5x50 series.
+     * build tools:
+
+          + Linux kernel development package for the target kernel; to
+            build against your currently running kernel, you need to have
+            the kernel development package corresponding to the running
+            image installed (usually if your kernel is named
+            linux-VERSION, the development package is called
+            linux-dev-VERSION or linux-headers-VERSION).
+          + GNU C Compiler, make
+
+2. Compilation and installation
+===============================
+
+2.1. Compilation of the drivers included in the kernel
+------------------------------------------------------
+
+   Configure the kernel; to enable the WiMAX drivers select Drivers >
+   Networking Drivers > WiMAX device support. Enable all of them as
+   modules (easier).
+
+   If USB or SDIO are not enabled in the kernel configuration, the options
+   to build the i2400m USB or SDIO drivers will not show. Enable said
+   subsystems and go back to the WiMAX menu to enable the drivers.
+
+   Compile and install your kernel as usual.
+
+2.2. Compilation of the drivers distributed as an standalone module
+-------------------------------------------------------------------
+
+   To compile::
+
+	$ cd source/directory
+	$ make
+
+   Once built you can load and unload using the provided load.sh script;
+   load.sh will load the modules, load.sh u will unload them.
+
+   To install in the default kernel directories (and enable auto loading
+   when the device is plugged)::
+
+	$ make install
+	$ depmod -a
+
+   If your kernel development files are located in a non standard
+   directory or if you want to build for a kernel that is not the
+   currently running one, set KDIR to the right location::
+
+	$ make KDIR=/path/to/kernel/dev/tree
+
+   For more information, please contact linux-wimax@intel.com.
+
+3. Installing the firmware
+--------------------------
+
+   The firmware can be obtained from http://linuxwimax.org or might have
+   been supplied with your hardware.
+
+   It has to be installed in the target system::
+
+	$ cp FIRMWAREFILE.sbcf /lib/firmware/i2400m-fw-BUSTYPE-1.3.sbcf
+
+     * NOTE: if your firmware came in an .rpm or .deb file, just install
+       it as normal, with the rpm (rpm -i FIRMWARE.rpm) or dpkg
+       (dpkg -i FIRMWARE.deb) commands. No further action is needed.
+     * BUSTYPE will be usb or sdio, depending on the hardware you have.
+       Each hardware type comes with its own firmware and will not work
+       with other types.
+
+4. Design
+=========
+
+   This package contains two major parts: a WiMAX kernel stack and a
+   driver for the Intel i2400m.
+
+   The WiMAX stack is designed to provide for common WiMAX control
+   services to current and future WiMAX devices from any vendor; please
+   see README.wimax for details.
+
+   The i2400m kernel driver is broken up in two main parts: the bus
+   generic driver and the bus-specific drivers. The bus generic driver
+   forms the drivercore and contain no knowledge of the actual method we
+   use to connect to the device. The bus specific drivers are just the
+   glue to connect the bus-generic driver and the device. Currently only
+   USB and SDIO are supported. See drivers/net/wimax/i2400m/i2400m.h for
+   more information.
+
+   The bus generic driver is logically broken up in two parts: OS-glue and
+   hardware-glue. The OS-glue interfaces with Linux. The hardware-glue
+   interfaces with the device on using an interface provided by the
+   bus-specific driver. The reason for this breakup is to be able to
+   easily reuse the hardware-glue to write drivers for other OSes; note
+   the hardware glue part is written as a native Linux driver; no
+   abstraction layers are used, so to port to another OS, the Linux kernel
+   API calls should be replaced with the target OS's.
+
+5. Usage
+========
+
+   To load the driver, follow the instructions in the install section;
+   once the driver is loaded, plug in the device (unless it is permanently
+   plugged in). The driver will enumerate the device, upload the firmware
+   and output messages in the kernel log (dmesg, /var/log/messages or
+   /var/log/kern.log) such as::
+
+	...
+	i2400m_usb 5-4:1.0: firmware interface version 8.0.0
+	i2400m_usb 5-4:1.0: WiMAX interface wmx0 (00:1d:e1:01:94:2c) ready
+
+   At this point the device is ready to work.
+
+   Current versions require the Intel WiMAX Network Service in userspace
+   to make things work. See the network service's README for instructions
+   on how to scan, connect and disconnect.
+
+5.1. Module parameters
+----------------------
+
+   Module parameters can be set at kernel or module load time or by
+   echoing values::
+
+	$ echo VALUE > /sys/module/MODULENAME/parameters/PARAMETERNAME
+
+   To make changes permanent, for example, for the i2400m module, you can
+   also create a file named /etc/modprobe.d/i2400m containing::
+
+	options i2400m idle_mode_disabled=1
+
+   To find which parameters are supported by a module, run::
+
+	$ modinfo path/to/module.ko
+
+   During kernel bootup (if the driver is linked in the kernel), specify
+   the following to the kernel command line::
+
+	i2400m.PARAMETER=VALUE
+
+5.1.1. i2400m: idle_mode_disabled
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+   The i2400m module supports a parameter to disable idle mode. This
+   parameter, once set, will take effect only when the device is
+   reinitialized by the driver (eg: following a reset or a reconnect).
+
+5.2. Debug operations: debugfs entries
+--------------------------------------
+
+   The driver will register debugfs entries that allow the user to tweak
+   debug settings. There are three main container directories where
+   entries are placed, which correspond to the three blocks a i2400m WiMAX
+   driver has:
+
+     * /sys/kernel/debug/wimax:DEVNAME/ for the generic WiMAX stack
+       controls
+     * /sys/kernel/debug/wimax:DEVNAME/i2400m for the i2400m generic
+       driver controls
+     * /sys/kernel/debug/wimax:DEVNAME/i2400m-usb (or -sdio) for the
+       bus-specific i2400m-usb or i2400m-sdio controls).
+
+   Of course, if debugfs is mounted in a directory other than
+   /sys/kernel/debug, those paths will change.
+
+5.2.1. Increasing debug output
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+   The files named *dl_* indicate knobs for controlling the debug output
+   of different submodules::
+
+	# find /sys/kernel/debug/wimax\:wmx0 -name \*dl_\*
+	/sys/kernel/debug/wimax:wmx0/i2400m-usb/dl_tx
+	/sys/kernel/debug/wimax:wmx0/i2400m-usb/dl_rx
+	/sys/kernel/debug/wimax:wmx0/i2400m-usb/dl_notif
+	/sys/kernel/debug/wimax:wmx0/i2400m-usb/dl_fw
+	/sys/kernel/debug/wimax:wmx0/i2400m-usb/dl_usb
+	/sys/kernel/debug/wimax:wmx0/i2400m/dl_tx
+	/sys/kernel/debug/wimax:wmx0/i2400m/dl_rx
+	/sys/kernel/debug/wimax:wmx0/i2400m/dl_rfkill
+	/sys/kernel/debug/wimax:wmx0/i2400m/dl_netdev
+	/sys/kernel/debug/wimax:wmx0/i2400m/dl_fw
+	/sys/kernel/debug/wimax:wmx0/i2400m/dl_debugfs
+	/sys/kernel/debug/wimax:wmx0/i2400m/dl_driver
+	/sys/kernel/debug/wimax:wmx0/i2400m/dl_control
+	/sys/kernel/debug/wimax:wmx0/wimax_dl_stack
+	/sys/kernel/debug/wimax:wmx0/wimax_dl_op_rfkill
+	/sys/kernel/debug/wimax:wmx0/wimax_dl_op_reset
+	/sys/kernel/debug/wimax:wmx0/wimax_dl_op_msg
+	/sys/kernel/debug/wimax:wmx0/wimax_dl_id_table
+	/sys/kernel/debug/wimax:wmx0/wimax_dl_debugfs
+
+   By reading the file you can obtain the current value of said debug
+   level; by writing to it, you can set it.
+
+   To increase the debug level of, for example, the i2400m's generic TX
+   engine, just write::
+
+	$ echo 3 > /sys/kernel/debug/wimax:wmx0/i2400m/dl_tx
+
+   Increasing numbers yield increasing debug information; for details of
+   what is printed and the available levels, check the source. The code
+   uses 0 for disabled and increasing values until 8.
+
+5.2.2. RX and TX statistics
+^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+   The i2400m/rx_stats and i2400m/tx_stats provide statistics about the
+   data reception/delivery from the device::
+
+	$ cat /sys/kernel/debug/wimax:wmx0/i2400m/rx_stats
+	45 1 3 34 3104 48 480
+
+   The numbers reported are:
+
+     * packets/RX-buffer: total, min, max
+     * RX-buffers: total RX buffers received, accumulated RX buffer size
+       in bytes, min size received, max size received
+
+   Thus, to find the average buffer size received, divide accumulated
+   RX-buffer / total RX-buffers.
+
+   To clear the statistics back to 0, write anything to the rx_stats file::
+
+	$ echo 1 > /sys/kernel/debug/wimax:wmx0/i2400m_rx_stats
+
+   Likewise for TX.
+
+   Note the packets this debug file refers to are not network packet, but
+   packets in the sense of the device-specific protocol for communication
+   to the host. See drivers/net/wimax/i2400m/tx.c.
+
+5.2.3. Tracing messages received from user space
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+   To echo messages received from user space into the trace pipe that the
+   i2400m driver creates, set the debug file i2400m/trace_msg_from_user to
+   1::
+
+	$ echo 1 > /sys/kernel/debug/wimax:wmx0/i2400m/trace_msg_from_user
+
+5.2.4. Performing a device reset
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+   By writing a 0, a 1 or a 2 to the file
+   /sys/kernel/debug/wimax:wmx0/reset, the driver performs a warm (without
+   disconnecting from the bus), cold (disconnecting from the bus) or bus
+   (bus specific) reset on the device.
+
+5.2.5. Asking the device to enter power saving mode
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+   By writing any value to the /sys/kernel/debug/wimax:wmx0 file, the
+   device will attempt to enter power saving mode.
+
+6. Troubleshooting
+==================
+
+6.1. Driver complains about ``i2400m-fw-usb-1.2.sbcf: request failed``
+----------------------------------------------------------------------
+
+   If upon connecting the device, the following is output in the kernel
+   log::
+
+	i2400m_usb 5-4:1.0: fw i2400m-fw-usb-1.3.sbcf: request failed: -2
+
+   This means that the driver cannot locate the firmware file named
+   /lib/firmware/i2400m-fw-usb-1.2.sbcf. Check that the file is present in
+   the right location.
diff --git a/drivers/staging/wimax/Documentation/index.rst b/drivers/staging/wimax/Documentation/index.rst
new file mode 100644
index 000000000000..fdf7c1f99ff5
--- /dev/null
+++ b/drivers/staging/wimax/Documentation/index.rst
@@ -0,0 +1,19 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===============
+WiMAX subsystem
+===============
+
+.. toctree::
+   :maxdepth: 2
+
+   wimax
+
+   i2400m
+
+.. only::  subproject and html
+
+   Indices
+   =======
+
+   * :ref:`genindex`
diff --git a/drivers/staging/wimax/Documentation/wimax.rst b/drivers/staging/wimax/Documentation/wimax.rst
new file mode 100644
index 000000000000..817ee8ba2732
--- /dev/null
+++ b/drivers/staging/wimax/Documentation/wimax.rst
@@ -0,0 +1,89 @@
+.. include:: <isonum.txt>
+
+========================
+Linux kernel WiMAX stack
+========================
+
+:Copyright: |copy| 2008 Intel Corporation < linux-wimax@intel.com >
+
+   This provides a basic Linux kernel WiMAX stack to provide a common
+   control API for WiMAX devices, usable from kernel and user space.
+
+1. Design
+=========
+
+   The WiMAX stack is designed to provide for common WiMAX control
+   services to current and future WiMAX devices from any vendor.
+
+   Because currently there is only one and we don't know what would be the
+   common services, the APIs it currently provides are very minimal.
+   However, it is done in such a way that it is easily extensible to
+   accommodate future requirements.
+
+   The stack works by embedding a struct wimax_dev in your device's
+   control structures. This provides a set of callbacks that the WiMAX
+   stack will call in order to implement control operations requested by
+   the user. As well, the stack provides API functions that the driver
+   calls to notify about changes of state in the device.
+
+   The stack exports the API calls needed to control the device to user
+   space using generic netlink as a marshalling mechanism. You can access
+   them using your own code or use the wrappers provided for your
+   convenience in libwimax (in the wimax-tools package).
+
+   For detailed information on the stack, please see
+   include/linux/wimax.h.
+
+2. Usage
+========
+
+   For usage in a driver (registration, API, etc) please refer to the
+   instructions in the header file include/linux/wimax.h.
+
+   When a device is registered with the WiMAX stack, a set of debugfs
+   files will appear in /sys/kernel/debug/wimax:wmxX can tweak for
+   control.
+
+2.1. Obtaining debug information: debugfs entries
+-------------------------------------------------
+
+   The WiMAX stack is compiled, by default, with debug messages that can
+   be used to diagnose issues. By default, said messages are disabled.
+
+   The drivers will register debugfs entries that allow the user to tweak
+   debug settings.
+
+   Each driver, when registering with the stack, will cause a debugfs
+   directory named wimax:DEVICENAME to be created; optionally, it might
+   create more subentries below it.
+
+2.1.1. Increasing debug output
+------------------------------
+
+   The files named *dl_* indicate knobs for controlling the debug output
+   of different submodules of the WiMAX stack::
+
+	# find /sys/kernel/debug/wimax\:wmx0 -name \*dl_\*
+	/sys/kernel/debug/wimax:wmx0/wimax_dl_stack
+	/sys/kernel/debug/wimax:wmx0/wimax_dl_op_rfkill
+	/sys/kernel/debug/wimax:wmx0/wimax_dl_op_reset
+	/sys/kernel/debug/wimax:wmx0/wimax_dl_op_msg
+	/sys/kernel/debug/wimax:wmx0/wimax_dl_id_table
+	/sys/kernel/debug/wimax:wmx0/wimax_dl_debugfs
+	/sys/kernel/debug/wimax:wmx0/.... # other driver specific files
+
+   NOTE:
+       Of course, if debugfs is mounted in a directory other than
+       /sys/kernel/debug, those paths will change.
+
+   By reading the file you can obtain the current value of said debug
+   level; by writing to it, you can set it.
+
+   To increase the debug level of, for example, the id-table submodule,
+   just write:
+
+	$ echo 3 > /sys/kernel/debug/wimax:wmx0/wimax_dl_id_table
+
+   Increasing numbers yield increasing debug information; for details of
+   what is printed and the available levels, check the source. The code
+   uses 0 for disabled and increasing values until 8.
diff --git a/drivers/staging/wimax/Kconfig b/drivers/staging/wimax/Kconfig
new file mode 100644
index 000000000000..ded8b70b25ee
--- /dev/null
+++ b/drivers/staging/wimax/Kconfig
@@ -0,0 +1,46 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# WiMAX LAN device configuration
+#
+
+menuconfig WIMAX
+	tristate "WiMAX Wireless Broadband support"
+	depends on RFKILL || !RFKILL
+	help
+
+	  Select to configure support for devices that provide
+	  wireless broadband connectivity using the WiMAX protocol
+	  (IEEE 802.16).
+
+	  Please note that most of these devices require signing up
+	  for a service plan with a provider.
+
+	  The different WiMAX drivers can be enabled in the menu entry
+
+	  Device Drivers > Network device support > WiMAX Wireless
+	  Broadband devices
+
+	  If unsure, it is safe to select M (module).
+
+if WIMAX
+
+config WIMAX_DEBUG_LEVEL
+	int "WiMAX debug level"
+	depends on WIMAX
+	default 8
+	help
+
+	  Select the maximum debug verbosity level to be compiled into
+	  the WiMAX stack code.
+
+	  By default, debug messages are disabled at runtime and can
+	  be selectively enabled for different parts of the code using
+	  the sysfs debug-levels file.
+
+	  If set at zero, this will compile out all the debug code.
+
+	  It is recommended that it is left at 8.
+
+source "drivers/staging/wimax/i2400m/Kconfig"
+
+endif
diff --git a/drivers/staging/wimax/Makefile b/drivers/staging/wimax/Makefile
new file mode 100644
index 000000000000..0e3f988656aa
--- /dev/null
+++ b/drivers/staging/wimax/Makefile
@@ -0,0 +1,15 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-$(CONFIG_WIMAX)		+= wimax.o
+
+wimax-y :=		\
+	id-table.o	\
+	op-msg.o	\
+	op-reset.o	\
+	op-rfkill.o	\
+	op-state-get.o	\
+	stack.o
+
+wimax-$(CONFIG_DEBUG_FS) += debugfs.o
+
+obj-$(CONFIG_WIMAX_I2400M)	+= i2400m/
diff --git a/drivers/staging/wimax/TODO b/drivers/staging/wimax/TODO
new file mode 100644
index 000000000000..26e4cb9e9599
--- /dev/null
+++ b/drivers/staging/wimax/TODO
@@ -0,0 +1,18 @@
+There are no known users of this driver as of October 2020, and it will
+be removed unless someone turns out to still need it in future releases.
+
+According to https://en.wikipedia.org/wiki/List_of_WiMAX_networks, there
+have been many public wimax networks, but it appears that many of these
+have migrated to LTE or discontinued their service altogether.  As most
+PCs and phones lack WiMAX hardware support, the remaining networks tend
+to use standalone routers. These almost certainly run Linux, but not a
+modern kernel or the mainline wimax driver stack.
+
+NetworkManager appears to have dropped userspace support in 2015
+https://bugzilla.gnome.org/show_bug.cgi?id=747846, the www.linuxwimax.org
+site had already shut down earlier.
+
+WiMax is apparently still being deployed on airport campus networks
+("AeroMACS"), but in a frequency band that was not supported by the old
+Intel 2400m (used in Sandy Bridge laptops and earlier), which is the
+only driver using the kernel's wimax stack.
diff --git a/drivers/staging/wimax/debug-levels.h b/drivers/staging/wimax/debug-levels.h
new file mode 100644
index 000000000000..b854802d1d00
--- /dev/null
+++ b/drivers/staging/wimax/debug-levels.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Linux WiMAX Stack
+ * Debug levels control file for the wimax module
+ *
+ * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ */
+#ifndef __debug_levels__h__
+#define __debug_levels__h__
+
+/* Maximum compile and run time debug level for all submodules */
+#define D_MODULENAME wimax
+#define D_MASTER CONFIG_WIMAX_DEBUG_LEVEL
+
+#include "linux-wimax-debug.h"
+
+/* List of all the enabled modules */
+enum d_module {
+	D_SUBMODULE_DECLARE(debugfs),
+	D_SUBMODULE_DECLARE(id_table),
+	D_SUBMODULE_DECLARE(op_msg),
+	D_SUBMODULE_DECLARE(op_reset),
+	D_SUBMODULE_DECLARE(op_rfkill),
+	D_SUBMODULE_DECLARE(op_state_get),
+	D_SUBMODULE_DECLARE(stack),
+};
+
+#endif /* #ifndef __debug_levels__h__ */
diff --git a/drivers/staging/wimax/debugfs.c b/drivers/staging/wimax/debugfs.c
new file mode 100644
index 000000000000..e11bff61ffcf
--- /dev/null
+++ b/drivers/staging/wimax/debugfs.c
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Linux WiMAX
+ * Debugfs support
+ *
+ * Copyright (C) 2005-2006 Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ */
+#include <linux/debugfs.h>
+#include "linux-wimax.h"
+#include "wimax-internal.h"
+
+#define D_SUBMODULE debugfs
+#include "debug-levels.h"
+
+void wimax_debugfs_add(struct wimax_dev *wimax_dev)
+{
+	struct net_device *net_dev = wimax_dev->net_dev;
+	struct dentry *dentry;
+	char buf[128];
+
+	snprintf(buf, sizeof(buf), "wimax:%s", net_dev->name);
+	dentry = debugfs_create_dir(buf, NULL);
+	wimax_dev->debugfs_dentry = dentry;
+
+	d_level_register_debugfs("wimax_dl_", debugfs, dentry);
+	d_level_register_debugfs("wimax_dl_", id_table, dentry);
+	d_level_register_debugfs("wimax_dl_", op_msg, dentry);
+	d_level_register_debugfs("wimax_dl_", op_reset, dentry);
+	d_level_register_debugfs("wimax_dl_", op_rfkill, dentry);
+	d_level_register_debugfs("wimax_dl_", op_state_get, dentry);
+	d_level_register_debugfs("wimax_dl_", stack, dentry);
+}
+
+void wimax_debugfs_rm(struct wimax_dev *wimax_dev)
+{
+	debugfs_remove_recursive(wimax_dev->debugfs_dentry);
+}
diff --git a/drivers/staging/wimax/i2400m/Kconfig b/drivers/staging/wimax/i2400m/Kconfig
new file mode 100644
index 000000000000..843b905a26a3
--- /dev/null
+++ b/drivers/staging/wimax/i2400m/Kconfig
@@ -0,0 +1,37 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+config WIMAX_I2400M
+	tristate
+	depends on WIMAX
+	select FW_LOADER
+
+comment "Enable USB support to see WiMAX USB drivers"
+	depends on USB = n
+
+config WIMAX_I2400M_USB
+	tristate "Intel Wireless WiMAX Connection 2400 over USB (including 5x50)"
+	depends on WIMAX && USB
+	select WIMAX_I2400M
+	help
+	  Select if you have a device based on the Intel WiMAX
+	  Connection 2400 over USB (like any of the Intel Wireless
+	  WiMAX/WiFi Link 5x50 series).
+
+	  If unsure, it is safe to select M (module).
+
+config WIMAX_I2400M_DEBUG_LEVEL
+	int "WiMAX i2400m debug level"
+	depends on WIMAX_I2400M
+	default 8
+	help
+
+	  Select the maximum debug verbosity level to be compiled into
+	  the WiMAX i2400m driver code.
+
+	  By default, this is disabled at runtime and can be
+	  selectively enabled at runtime for different parts of the
+	  code using the sysfs debug-levels file.
+
+	  If set at zero, this will compile out all the debug code.
+
+	  It is recommended that it is left at 8.
diff --git a/drivers/staging/wimax/i2400m/Makefile b/drivers/staging/wimax/i2400m/Makefile
new file mode 100644
index 000000000000..b1db1eff0648
--- /dev/null
+++ b/drivers/staging/wimax/i2400m/Makefile
@@ -0,0 +1,23 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-$(CONFIG_WIMAX_I2400M) += i2400m.o
+obj-$(CONFIG_WIMAX_I2400M_USB) += i2400m-usb.o
+
+i2400m-y :=		\
+	control.o	\
+	driver.o	\
+	fw.o		\
+	op-rfkill.o	\
+	sysfs.o		\
+	netdev.o	\
+	tx.o		\
+	rx.o
+
+i2400m-$(CONFIG_DEBUG_FS) += debugfs.o
+
+i2400m-usb-y :=			\
+	usb-fw.o		\
+	usb-notif.o		\
+	usb-tx.o		\
+	usb-rx.o		\
+	usb.o
diff --git a/drivers/staging/wimax/i2400m/control.c b/drivers/staging/wimax/i2400m/control.c
new file mode 100644
index 000000000000..fe885aa56cf3
--- /dev/null
+++ b/drivers/staging/wimax/i2400m/control.c
@@ -0,0 +1,1434 @@
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * Miscellaneous control functions for managing the device
+ *
+ *
+ * Copyright (C) 2007-2008 Intel Corporation. All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *
+ * Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *  - Initial implementation
+ *
+ * This is a collection of functions used to control the device (plus
+ * a few helpers).
+ *
+ * There are utilities for handling TLV buffers, hooks on the device's
+ * reports to act on device changes of state [i2400m_report_hook()],
+ * on acks to commands [i2400m_msg_ack_hook()], a helper for sending
+ * commands to the device and blocking until a reply arrives
+ * [i2400m_msg_to_dev()], a few high level commands for manipulating
+ * the device state, powersving mode and configuration plus the
+ * routines to setup the device once communication is stablished with
+ * it [i2400m_dev_initialize()].
+ *
+ * ROADMAP
+ *
+ * i2400m_dev_initialize()       Called by i2400m_dev_start()
+ *   i2400m_set_init_config()
+ *   i2400m_cmd_get_state()
+ * i2400m_dev_shutdown()        Called by i2400m_dev_stop()
+ *   i2400m_reset()
+ *
+ * i2400m_{cmd,get,set}_*()
+ *   i2400m_msg_to_dev()
+ *   i2400m_msg_check_status()
+ *
+ * i2400m_report_hook()         Called on reception of an event
+ *   i2400m_report_state_hook()
+ *     i2400m_tlv_buffer_walk()
+ *     i2400m_tlv_match()
+ *     i2400m_report_tlv_system_state()
+ *     i2400m_report_tlv_rf_switches_status()
+ *     i2400m_report_tlv_media_status()
+ *   i2400m_cmd_enter_powersave()
+ *
+ * i2400m_msg_ack_hook()        Called on reception of a reply to a
+ *                              command, get or set
+ */
+
+#include <stdarg.h>
+#include "i2400m.h"
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include "linux-wimax-i2400m.h"
+#include <linux/export.h>
+#include <linux/moduleparam.h>
+
+
+#define D_SUBMODULE control
+#include "debug-levels.h"
+
+static int i2400m_idle_mode_disabled;/* 0 (idle mode enabled) by default */
+module_param_named(idle_mode_disabled, i2400m_idle_mode_disabled, int, 0644);
+MODULE_PARM_DESC(idle_mode_disabled,
+		 "If true, the device will not enable idle mode negotiation "
+		 "with the base station (when connected) to save power.");
+
+/* 0 (power saving enabled) by default */
+static int i2400m_power_save_disabled;
+module_param_named(power_save_disabled, i2400m_power_save_disabled, int, 0644);
+MODULE_PARM_DESC(power_save_disabled,
+		 "If true, the driver will not tell the device to enter "
+		 "power saving mode when it reports it is ready for it. "
+		 "False by default (so the device is told to do power "
+		 "saving).");
+
+static int i2400m_passive_mode;	/* 0 (passive mode disabled) by default */
+module_param_named(passive_mode, i2400m_passive_mode, int, 0644);
+MODULE_PARM_DESC(passive_mode,
+		 "If true, the driver will not do any device setup "
+		 "and leave it up to user space, who must be properly "
+		 "setup.");
+
+
+/*
+ * Return if a TLV is of a give type and size
+ *
+ * @tlv_hdr: pointer to the TLV
+ * @tlv_type: type of the TLV we are looking for
+ * @tlv_size: expected size of the TLV we are looking for (if -1,
+ *            don't check the size). This includes the header
+ * Returns: 0 if the TLV matches
+ *          < 0 if it doesn't match at all
+ *          > 0 total TLV + payload size, if the type matches, but not
+ *              the size
+ */
+static
+ssize_t i2400m_tlv_match(const struct i2400m_tlv_hdr *tlv,
+		     enum i2400m_tlv tlv_type, ssize_t tlv_size)
+{
+	if (le16_to_cpu(tlv->type) != tlv_type)	/* Not our type? skip */
+		return -1;
+	if (tlv_size != -1
+	    && le16_to_cpu(tlv->length) + sizeof(*tlv) != tlv_size) {
+		size_t size = le16_to_cpu(tlv->length) + sizeof(*tlv);
+		printk(KERN_WARNING "W: tlv type 0x%x mismatched because of "
+		       "size (got %zu vs %zd expected)\n",
+		       tlv_type, size, tlv_size);
+		return size;
+	}
+	return 0;
+}
+
+
+/*
+ * Given a buffer of TLVs, iterate over them
+ *
+ * @i2400m: device instance
+ * @tlv_buf: pointer to the beginning of the TLV buffer
+ * @buf_size: buffer size in bytes
+ * @tlv_pos: seek position; this is assumed to be a pointer returned
+ *           by i2400m_tlv_buffer_walk() [and thus, validated]. The
+ *           TLV returned will be the one following this one.
+ *
+ * Usage:
+ *
+ * tlv_itr = NULL;
+ * while (tlv_itr = i2400m_tlv_buffer_walk(i2400m, buf, size, tlv_itr))  {
+ *         ...
+ *         // Do stuff with tlv_itr, DON'T MODIFY IT
+ *         ...
+ * }
+ */
+static
+const struct i2400m_tlv_hdr *i2400m_tlv_buffer_walk(
+	struct i2400m *i2400m,
+	const void *tlv_buf, size_t buf_size,
+	const struct i2400m_tlv_hdr *tlv_pos)
+{
+	struct device *dev = i2400m_dev(i2400m);
+	const struct i2400m_tlv_hdr *tlv_top = tlv_buf + buf_size;
+	size_t offset, length, avail_size;
+	unsigned type;
+
+	if (tlv_pos == NULL)	/* Take the first one? */
+		tlv_pos = tlv_buf;
+	else			/* Nope, the next one */
+		tlv_pos = (void *) tlv_pos
+			+ le16_to_cpu(tlv_pos->length) + sizeof(*tlv_pos);
+	if (tlv_pos == tlv_top) {	/* buffer done */
+		tlv_pos = NULL;
+		goto error_beyond_end;
+	}
+	if (tlv_pos > tlv_top) {
+		tlv_pos = NULL;
+		WARN_ON(1);
+		goto error_beyond_end;
+	}
+	offset = (void *) tlv_pos - (void *) tlv_buf;
+	avail_size = buf_size - offset;
+	if (avail_size < sizeof(*tlv_pos)) {
+		dev_err(dev, "HW BUG? tlv_buf %p [%zu bytes], tlv @%zu: "
+			"short header\n", tlv_buf, buf_size, offset);
+		goto error_short_header;
+	}
+	type = le16_to_cpu(tlv_pos->type);
+	length = le16_to_cpu(tlv_pos->length);
+	if (avail_size < sizeof(*tlv_pos) + length) {
+		dev_err(dev, "HW BUG? tlv_buf %p [%zu bytes], "
+			"tlv type 0x%04x @%zu: "
+			"short data (%zu bytes vs %zu needed)\n",
+			tlv_buf, buf_size, type, offset, avail_size,
+			sizeof(*tlv_pos) + length);
+		goto error_short_header;
+	}
+error_short_header:
+error_beyond_end:
+	return tlv_pos;
+}
+
+
+/*
+ * Find a TLV in a buffer of sequential TLVs
+ *
+ * @i2400m: device descriptor
+ * @tlv_hdr: pointer to the first TLV in the sequence
+ * @size: size of the buffer in bytes; all TLVs are assumed to fit
+ *        fully in the buffer (otherwise we'll complain).
+ * @tlv_type: type of the TLV we are looking for
+ * @tlv_size: expected size of the TLV we are looking for (if -1,
+ *            don't check the size). This includes the header
+ *
+ * Returns: NULL if the TLV is not found, otherwise a pointer to
+ *          it. If the sizes don't match, an error is printed and NULL
+ *          returned.
+ */
+static
+const struct i2400m_tlv_hdr *i2400m_tlv_find(
+	struct i2400m *i2400m,
+	const struct i2400m_tlv_hdr *tlv_hdr, size_t size,
+	enum i2400m_tlv tlv_type, ssize_t tlv_size)
+{
+	ssize_t match;
+	struct device *dev = i2400m_dev(i2400m);
+	const struct i2400m_tlv_hdr *tlv = NULL;
+	while ((tlv = i2400m_tlv_buffer_walk(i2400m, tlv_hdr, size, tlv))) {
+		match = i2400m_tlv_match(tlv, tlv_type, tlv_size);
+		if (match == 0)		/* found it :) */
+			break;
+		if (match > 0)
+			dev_warn(dev, "TLV type 0x%04x found with size "
+				 "mismatch (%zu vs %zd needed)\n",
+				 tlv_type, match, tlv_size);
+	}
+	return tlv;
+}
+
+
+static const struct
+{
+	char *msg;
+	int errno;
+} ms_to_errno[I2400M_MS_MAX] = {
+	[I2400M_MS_DONE_OK] = { "", 0 },
+	[I2400M_MS_DONE_IN_PROGRESS] = { "", 0 },
+	[I2400M_MS_INVALID_OP] = { "invalid opcode", -ENOSYS },
+	[I2400M_MS_BAD_STATE] = { "invalid state", -EILSEQ },
+	[I2400M_MS_ILLEGAL_VALUE] = { "illegal value", -EINVAL },
+	[I2400M_MS_MISSING_PARAMS] = { "missing parameters", -ENOMSG },
+	[I2400M_MS_VERSION_ERROR] = { "bad version", -EIO },
+	[I2400M_MS_ACCESSIBILITY_ERROR] = { "accesibility error", -EIO },
+	[I2400M_MS_BUSY] = { "busy", -EBUSY },
+	[I2400M_MS_CORRUPTED_TLV] = { "corrupted TLV", -EILSEQ },
+	[I2400M_MS_UNINITIALIZED] = { "uninitialized", -EILSEQ },
+	[I2400M_MS_UNKNOWN_ERROR] = { "unknown error", -EIO },
+	[I2400M_MS_PRODUCTION_ERROR] = { "production error", -EIO },
+	[I2400M_MS_NO_RF] = { "no RF", -EIO },
+	[I2400M_MS_NOT_READY_FOR_POWERSAVE] =
+		{ "not ready for powersave", -EACCES },
+	[I2400M_MS_THERMAL_CRITICAL] = { "thermal critical", -EL3HLT },
+};
+
+
+/*
+ * i2400m_msg_check_status - translate a message's status code
+ *
+ * @i2400m: device descriptor
+ * @l3l4_hdr: message header
+ * @strbuf: buffer to place a formatted error message (unless NULL).
+ * @strbuf_size: max amount of available space; larger messages will
+ * be truncated.
+ *
+ * Returns: errno code corresponding to the status code in @l3l4_hdr
+ *          and a message in @strbuf describing the error.
+ */
+int i2400m_msg_check_status(const struct i2400m_l3l4_hdr *l3l4_hdr,
+			    char *strbuf, size_t strbuf_size)
+{
+	int result;
+	enum i2400m_ms status = le16_to_cpu(l3l4_hdr->status);
+	const char *str;
+
+	if (status == 0)
+		return 0;
+	if (status >= ARRAY_SIZE(ms_to_errno)) {
+		str = "unknown status code";
+		result = -EBADR;
+	} else {
+		str = ms_to_errno[status].msg;
+		result = ms_to_errno[status].errno;
+	}
+	if (strbuf)
+		snprintf(strbuf, strbuf_size, "%s (%d)", str, status);
+	return result;
+}
+
+
+/*
+ * Act on a TLV System State reported by the device
+ *
+ * @i2400m: device descriptor
+ * @ss: validated System State TLV
+ */
+static
+void i2400m_report_tlv_system_state(struct i2400m *i2400m,
+				    const struct i2400m_tlv_system_state *ss)
+{
+	struct device *dev = i2400m_dev(i2400m);
+	struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
+	enum i2400m_system_state i2400m_state = le32_to_cpu(ss->state);
+
+	d_fnstart(3, dev, "(i2400m %p ss %p [%u])\n", i2400m, ss, i2400m_state);
+
+	if (i2400m->state != i2400m_state) {
+		i2400m->state = i2400m_state;
+		wake_up_all(&i2400m->state_wq);
+	}
+	switch (i2400m_state) {
+	case I2400M_SS_UNINITIALIZED:
+	case I2400M_SS_INIT:
+	case I2400M_SS_CONFIG:
+	case I2400M_SS_PRODUCTION:
+		wimax_state_change(wimax_dev, WIMAX_ST_UNINITIALIZED);
+		break;
+
+	case I2400M_SS_RF_OFF:
+	case I2400M_SS_RF_SHUTDOWN:
+		wimax_state_change(wimax_dev, WIMAX_ST_RADIO_OFF);
+		break;
+
+	case I2400M_SS_READY:
+	case I2400M_SS_STANDBY:
+	case I2400M_SS_SLEEPACTIVE:
+		wimax_state_change(wimax_dev, WIMAX_ST_READY);
+		break;
+
+	case I2400M_SS_CONNECTING:
+	case I2400M_SS_WIMAX_CONNECTED:
+		wimax_state_change(wimax_dev, WIMAX_ST_READY);
+		break;
+
+	case I2400M_SS_SCAN:
+	case I2400M_SS_OUT_OF_ZONE:
+		wimax_state_change(wimax_dev, WIMAX_ST_SCANNING);
+		break;
+
+	case I2400M_SS_IDLE:
+		d_printf(1, dev, "entering BS-negotiated idle mode\n");
+		fallthrough;
+	case I2400M_SS_DISCONNECTING:
+	case I2400M_SS_DATA_PATH_CONNECTED:
+		wimax_state_change(wimax_dev, WIMAX_ST_CONNECTED);
+		break;
+
+	default:
+		/* Huh? just in case, shut it down */
+		dev_err(dev, "HW BUG? unknown state %u: shutting down\n",
+			i2400m_state);
+		i2400m_reset(i2400m, I2400M_RT_WARM);
+		break;
+	}
+	d_fnend(3, dev, "(i2400m %p ss %p [%u]) = void\n",
+		i2400m, ss, i2400m_state);
+}
+
+
+/*
+ * Parse and act on a TLV Media Status sent by the device
+ *
+ * @i2400m: device descriptor
+ * @ms: validated Media Status TLV
+ *
+ * This will set the carrier up on down based on the device's link
+ * report. This is done asides of what the WiMAX stack does based on
+ * the device's state as sometimes we need to do a link-renew (the BS
+ * wants us to renew a DHCP lease, for example).
+ *
+ * In fact, doc says that every time we get a link-up, we should do a
+ * DHCP negotiation...
+ */
+static
+void i2400m_report_tlv_media_status(struct i2400m *i2400m,
+				    const struct i2400m_tlv_media_status *ms)
+{
+	struct device *dev = i2400m_dev(i2400m);
+	struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
+	struct net_device *net_dev = wimax_dev->net_dev;
+	enum i2400m_media_status status = le32_to_cpu(ms->media_status);
+
+	d_fnstart(3, dev, "(i2400m %p ms %p [%u])\n", i2400m, ms, status);
+
+	switch (status) {
+	case I2400M_MEDIA_STATUS_LINK_UP:
+		netif_carrier_on(net_dev);
+		break;
+	case I2400M_MEDIA_STATUS_LINK_DOWN:
+		netif_carrier_off(net_dev);
+		break;
+	/*
+	 * This is the network telling us we need to retrain the DHCP
+	 * lease -- so far, we are trusting the WiMAX Network Service
+	 * in user space to pick this up and poke the DHCP client.
+	 */
+	case I2400M_MEDIA_STATUS_LINK_RENEW:
+		netif_carrier_on(net_dev);
+		break;
+	default:
+		dev_err(dev, "HW BUG? unknown media status %u\n",
+			status);
+	}
+	d_fnend(3, dev, "(i2400m %p ms %p [%u]) = void\n",
+		i2400m, ms, status);
+}
+
+
+/*
+ * Process a TLV from a 'state report'
+ *
+ * @i2400m: device descriptor
+ * @tlv: pointer to the TLV header; it has been already validated for
+ *     consistent size.
+ * @tag: for error messages
+ *
+ * Act on the TLVs from a 'state report'.
+ */
+static
+void i2400m_report_state_parse_tlv(struct i2400m *i2400m,
+				   const struct i2400m_tlv_hdr *tlv,
+				   const char *tag)
+{
+	struct device *dev = i2400m_dev(i2400m);
+	const struct i2400m_tlv_media_status *ms;
+	const struct i2400m_tlv_system_state *ss;
+	const struct i2400m_tlv_rf_switches_status *rfss;
+
+	if (0 == i2400m_tlv_match(tlv, I2400M_TLV_SYSTEM_STATE, sizeof(*ss))) {
+		ss = container_of(tlv, typeof(*ss), hdr);
+		d_printf(2, dev, "%s: system state TLV "
+			 "found (0x%04x), state 0x%08x\n",
+			 tag, I2400M_TLV_SYSTEM_STATE,
+			 le32_to_cpu(ss->state));
+		i2400m_report_tlv_system_state(i2400m, ss);
+	}
+	if (0 == i2400m_tlv_match(tlv, I2400M_TLV_RF_STATUS, sizeof(*rfss))) {
+		rfss = container_of(tlv, typeof(*rfss), hdr);
+		d_printf(2, dev, "%s: RF status TLV "
+			 "found (0x%04x), sw 0x%02x hw 0x%02x\n",
+			 tag, I2400M_TLV_RF_STATUS,
+			 le32_to_cpu(rfss->sw_rf_switch),
+			 le32_to_cpu(rfss->hw_rf_switch));
+		i2400m_report_tlv_rf_switches_status(i2400m, rfss);
+	}
+	if (0 == i2400m_tlv_match(tlv, I2400M_TLV_MEDIA_STATUS, sizeof(*ms))) {
+		ms = container_of(tlv, typeof(*ms), hdr);
+		d_printf(2, dev, "%s: Media Status TLV: %u\n",
+			 tag, le32_to_cpu(ms->media_status));
+		i2400m_report_tlv_media_status(i2400m, ms);
+	}
+}
+
+
+/*
+ * Parse a 'state report' and extract information
+ *
+ * @i2400m: device descriptor
+ * @l3l4_hdr: pointer to message; it has been already validated for
+ *            consistent size.
+ * @size: size of the message (header + payload). The header length
+ *        declaration is assumed to be congruent with @size (as in
+ *        sizeof(*l3l4_hdr) + l3l4_hdr->length == size)
+ *
+ * Walk over the TLVs in a report state and act on them.
+ */
+static
+void i2400m_report_state_hook(struct i2400m *i2400m,
+			      const struct i2400m_l3l4_hdr *l3l4_hdr,
+			      size_t size, const char *tag)
+{
+	struct device *dev = i2400m_dev(i2400m);
+	const struct i2400m_tlv_hdr *tlv;
+	size_t tlv_size = le16_to_cpu(l3l4_hdr->length);
+
+	d_fnstart(4, dev, "(i2400m %p, l3l4_hdr %p, size %zu, %s)\n",
+		  i2400m, l3l4_hdr, size, tag);
+	tlv = NULL;
+
+	while ((tlv = i2400m_tlv_buffer_walk(i2400m, &l3l4_hdr->pl,
+					     tlv_size, tlv)))
+		i2400m_report_state_parse_tlv(i2400m, tlv, tag);
+	d_fnend(4, dev, "(i2400m %p, l3l4_hdr %p, size %zu, %s) = void\n",
+		i2400m, l3l4_hdr, size, tag);
+}
+
+
+/*
+ * i2400m_report_hook - (maybe) act on a report
+ *
+ * @i2400m: device descriptor
+ * @l3l4_hdr: pointer to message; it has been already validated for
+ *            consistent size.
+ * @size: size of the message (header + payload). The header length
+ *        declaration is assumed to be congruent with @size (as in
+ *        sizeof(*l3l4_hdr) + l3l4_hdr->length == size)
+ *
+ * Extract information we might need (like carrien on/off) from a
+ * device report.
+ */
+void i2400m_report_hook(struct i2400m *i2400m,
+			const struct i2400m_l3l4_hdr *l3l4_hdr, size_t size)
+{
+	struct device *dev = i2400m_dev(i2400m);
+	unsigned msg_type;
+
+	d_fnstart(3, dev, "(i2400m %p l3l4_hdr %p size %zu)\n",
+		  i2400m, l3l4_hdr, size);
+	/* Chew on the message, we might need some information from
+	 * here */
+	msg_type = le16_to_cpu(l3l4_hdr->type);
+	switch (msg_type) {
+	case I2400M_MT_REPORT_STATE:	/* carrier detection... */
+		i2400m_report_state_hook(i2400m,
+					 l3l4_hdr, size, "REPORT STATE");
+		break;
+	/* If the device is ready for power save, then ask it to do
+	 * it. */
+	case I2400M_MT_REPORT_POWERSAVE_READY:	/* zzzzz */
+		if (l3l4_hdr->status == cpu_to_le16(I2400M_MS_DONE_OK)) {
+			if (i2400m_power_save_disabled)
+				d_printf(1, dev, "ready for powersave, "
+					 "not requesting (disabled by module "
+					 "parameter)\n");
+			else {
+				d_printf(1, dev, "ready for powersave, "
+					 "requesting\n");
+				i2400m_cmd_enter_powersave(i2400m);
+			}
+		}
+		break;
+	}
+	d_fnend(3, dev, "(i2400m %p l3l4_hdr %p size %zu) = void\n",
+		i2400m, l3l4_hdr, size);
+}
+
+
+/*
+ * i2400m_msg_ack_hook - process cmd/set/get ack for internal status
+ *
+ * @i2400m: device descriptor
+ * @l3l4_hdr: pointer to message; it has been already validated for
+ *            consistent size.
+ * @size: size of the message
+ *
+ * Extract information we might need from acks to commands and act on
+ * it. This is akin to i2400m_report_hook(). Note most of this
+ * processing should be done in the function that calls the
+ * command. This is here for some cases where it can't happen...
+ */
+static void i2400m_msg_ack_hook(struct i2400m *i2400m,
+				 const struct i2400m_l3l4_hdr *l3l4_hdr,
+				 size_t size)
+{
+	int result;
+	struct device *dev = i2400m_dev(i2400m);
+	unsigned int ack_type;
+	char strerr[32];
+
+	/* Chew on the message, we might need some information from
+	 * here */
+	ack_type = le16_to_cpu(l3l4_hdr->type);
+	switch (ack_type) {
+	case I2400M_MT_CMD_ENTER_POWERSAVE:
+		/* This is just left here for the sake of example, as
+		 * the processing is done somewhere else. */
+		if (0) {
+			result = i2400m_msg_check_status(
+				l3l4_hdr, strerr, sizeof(strerr));
+			if (result >= 0)
+				d_printf(1, dev, "ready for power save: %zd\n",
+					 size);
+		}
+		break;
+	}
+}
+
+
+/*
+ * i2400m_msg_size_check() - verify message size and header are congruent
+ *
+ * It is ok if the total message size is larger than the expected
+ * size, as there can be padding.
+ */
+int i2400m_msg_size_check(struct i2400m *i2400m,
+			  const struct i2400m_l3l4_hdr *l3l4_hdr,
+			  size_t msg_size)
+{
+	int result;
+	struct device *dev = i2400m_dev(i2400m);
+	size_t expected_size;
+	d_fnstart(4, dev, "(i2400m %p l3l4_hdr %p msg_size %zu)\n",
+		  i2400m, l3l4_hdr, msg_size);
+	if (msg_size < sizeof(*l3l4_hdr)) {
+		dev_err(dev, "bad size for message header "
+			"(expected at least %zu, got %zu)\n",
+			(size_t) sizeof(*l3l4_hdr), msg_size);
+		result = -EIO;
+		goto error_hdr_size;
+	}
+	expected_size = le16_to_cpu(l3l4_hdr->length) + sizeof(*l3l4_hdr);
+	if (msg_size < expected_size) {
+		dev_err(dev, "bad size for message code 0x%04x (expected %zu, "
+			"got %zu)\n", le16_to_cpu(l3l4_hdr->type),
+			expected_size, msg_size);
+		result = -EIO;
+	} else
+		result = 0;
+error_hdr_size:
+	d_fnend(4, dev,
+		"(i2400m %p l3l4_hdr %p msg_size %zu) = %d\n",
+		i2400m, l3l4_hdr, msg_size, result);
+	return result;
+}
+
+
+
+/*
+ * Cancel a wait for a command ACK
+ *
+ * @i2400m: device descriptor
+ * @code: [negative] errno code to cancel with (don't use
+ *     -EINPROGRESS)
+ *
+ * If there is an ack already filled out, free it.
+ */
+void i2400m_msg_to_dev_cancel_wait(struct i2400m *i2400m, int code)
+{
+	struct sk_buff *ack_skb;
+	unsigned long flags;
+
+	spin_lock_irqsave(&i2400m->rx_lock, flags);
+	ack_skb = i2400m->ack_skb;
+	if (ack_skb && !IS_ERR(ack_skb))
+		kfree_skb(ack_skb);
+	i2400m->ack_skb = ERR_PTR(code);
+	spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+}
+
+
+/**
+ * i2400m_msg_to_dev - Send a control message to the device and get a response
+ *
+ * @i2400m: device descriptor
+ *
+ * @buf: pointer to the buffer containing the message to be sent; it
+ *           has to start with a &struct i2400M_l3l4_hdr and then
+ *           followed by the payload. Once this function returns, the
+ *           buffer can be reused.
+ *
+ * @buf_len: buffer size
+ *
+ * Returns:
+ *
+ * Pointer to skb containing the ack message. You need to check the
+ * pointer with IS_ERR(), as it might be an error code. Error codes
+ * could happen because:
+ *
+ *  - the message wasn't formatted correctly
+ *  - couldn't send the message
+ *  - failed waiting for a response
+ *  - the ack message wasn't formatted correctly
+ *
+ * The returned skb has been allocated with wimax_msg_to_user_alloc(),
+ * it contains the response in a netlink attribute and is ready to be
+ * passed up to user space with wimax_msg_to_user_send(). To access
+ * the payload and its length, use wimax_msg_{data,len}() on the skb.
+ *
+ * The skb has to be freed with kfree_skb() once done.
+ *
+ * Description:
+ *
+ * This function delivers a message/command to the device and waits
+ * for an ack to be received. The format is described in
+ * linux/wimax/i2400m.h. In summary, a command/get/set is followed by an
+ * ack.
+ *
+ * This function will not check the ack status, that's left up to the
+ * caller.  Once done with the ack skb, it has to be kfree_skb()ed.
+ *
+ * The i2400m handles only one message at the same time, thus we need
+ * the mutex to exclude other players.
+ *
+ * We write the message and then wait for an answer to come back. The
+ * RX path intercepts control messages and handles them in
+ * i2400m_rx_ctl(). Reports (notifications) are (maybe) processed
+ * locally and then forwarded (as needed) to user space on the WiMAX
+ * stack message pipe. Acks are saved and passed back to us through an
+ * skb in i2400m->ack_skb which is ready to be given to generic
+ * netlink if need be.
+ */
+struct sk_buff *i2400m_msg_to_dev(struct i2400m *i2400m,
+				  const void *buf, size_t buf_len)
+{
+	int result;
+	struct device *dev = i2400m_dev(i2400m);
+	const struct i2400m_l3l4_hdr *msg_l3l4_hdr;
+	struct sk_buff *ack_skb;
+	const struct i2400m_l3l4_hdr *ack_l3l4_hdr;
+	size_t ack_len;
+	int ack_timeout;
+	unsigned msg_type;
+	unsigned long flags;
+
+	d_fnstart(3, dev, "(i2400m %p buf %p len %zu)\n",
+		  i2400m, buf, buf_len);
+
+	rmb();		/* Make sure we see what i2400m_dev_reset_handle() */
+	if (i2400m->boot_mode)
+		return ERR_PTR(-EL3RST);
+
+	msg_l3l4_hdr = buf;
+	/* Check msg & payload consistency */
+	result = i2400m_msg_size_check(i2400m, msg_l3l4_hdr, buf_len);
+	if (result < 0)
+		goto error_bad_msg;
+	msg_type = le16_to_cpu(msg_l3l4_hdr->type);
+	d_printf(1, dev, "CMD/GET/SET 0x%04x %zu bytes\n",
+		 msg_type, buf_len);
+	d_dump(2, dev, buf, buf_len);
+
+	/* Setup the completion, ack_skb ("we are waiting") and send
+	 * the message to the device */
+	mutex_lock(&i2400m->msg_mutex);
+	spin_lock_irqsave(&i2400m->rx_lock, flags);
+	i2400m->ack_skb = ERR_PTR(-EINPROGRESS);
+	spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+	init_completion(&i2400m->msg_completion);
+	result = i2400m_tx(i2400m, buf, buf_len, I2400M_PT_CTRL);
+	if (result < 0) {
+		dev_err(dev, "can't send message 0x%04x: %d\n",
+			le16_to_cpu(msg_l3l4_hdr->type), result);
+		goto error_tx;
+	}
+
+	/* Some commands take longer to execute because of crypto ops,
+	 * so we give them some more leeway on timeout */
+	switch (msg_type) {
+	case I2400M_MT_GET_TLS_OPERATION_RESULT:
+	case I2400M_MT_CMD_SEND_EAP_RESPONSE:
+		ack_timeout = 5 * HZ;
+		break;
+	default:
+		ack_timeout = HZ;
+	}
+
+	if (unlikely(i2400m->trace_msg_from_user))
+		wimax_msg(&i2400m->wimax_dev, "echo", buf, buf_len, GFP_KERNEL);
+	/* The RX path in rx.c will put any response for this message
+	 * in i2400m->ack_skb and wake us up. If we cancel the wait,
+	 * we need to change the value of i2400m->ack_skb to something
+	 * not -EINPROGRESS so RX knows there is no one waiting. */
+	result = wait_for_completion_interruptible_timeout(
+		&i2400m->msg_completion, ack_timeout);
+	if (result == 0) {
+		dev_err(dev, "timeout waiting for reply to message 0x%04x\n",
+			msg_type);
+		result = -ETIMEDOUT;
+		i2400m_msg_to_dev_cancel_wait(i2400m, result);
+		goto error_wait_for_completion;
+	} else if (result < 0) {
+		dev_err(dev, "error waiting for reply to message 0x%04x: %d\n",
+			msg_type, result);
+		i2400m_msg_to_dev_cancel_wait(i2400m, result);
+		goto error_wait_for_completion;
+	}
+
+	/* Pull out the ack data from i2400m->ack_skb -- see if it is
+	 * an error and act accordingly */
+	spin_lock_irqsave(&i2400m->rx_lock, flags);
+	ack_skb = i2400m->ack_skb;
+	if (IS_ERR(ack_skb))
+		result = PTR_ERR(ack_skb);
+	else
+		result = 0;
+	i2400m->ack_skb = NULL;
+	spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+	if (result < 0)
+		goto error_ack_status;
+	ack_l3l4_hdr = wimax_msg_data_len(ack_skb, &ack_len);
+
+	/* Check the ack and deliver it if it is ok */
+	if (unlikely(i2400m->trace_msg_from_user))
+		wimax_msg(&i2400m->wimax_dev, "echo",
+			  ack_l3l4_hdr, ack_len, GFP_KERNEL);
+	result = i2400m_msg_size_check(i2400m, ack_l3l4_hdr, ack_len);
+	if (result < 0) {
+		dev_err(dev, "HW BUG? reply to message 0x%04x: %d\n",
+			msg_type, result);
+		goto error_bad_ack_len;
+	}
+	if (msg_type != le16_to_cpu(ack_l3l4_hdr->type)) {
+		dev_err(dev, "HW BUG? bad reply 0x%04x to message 0x%04x\n",
+			le16_to_cpu(ack_l3l4_hdr->type), msg_type);
+		result = -EIO;
+		goto error_bad_ack_type;
+	}
+	i2400m_msg_ack_hook(i2400m, ack_l3l4_hdr, ack_len);
+	mutex_unlock(&i2400m->msg_mutex);
+	d_fnend(3, dev, "(i2400m %p buf %p len %zu) = %p\n",
+		i2400m, buf, buf_len, ack_skb);
+	return ack_skb;
+
+error_bad_ack_type:
+error_bad_ack_len:
+	kfree_skb(ack_skb);
+error_ack_status:
+error_wait_for_completion:
+error_tx:
+	mutex_unlock(&i2400m->msg_mutex);
+error_bad_msg:
+	d_fnend(3, dev, "(i2400m %p buf %p len %zu) = %d\n",
+		i2400m, buf, buf_len, result);
+	return ERR_PTR(result);
+}
+
+
+/*
+ * Definitions for the Enter Power Save command
+ *
+ * The Enter Power Save command requests the device to go into power
+ * saving mode. The device will ack or nak the command depending on it
+ * being ready for it. If it acks, we tell the USB subsystem to
+ *
+ * As well, the device might request to go into power saving mode by
+ * sending a report (REPORT_POWERSAVE_READY), in which case, we issue
+ * this command. The hookups in the RX coder allow
+ */
+enum {
+	I2400M_WAKEUP_ENABLED  = 0x01,
+	I2400M_WAKEUP_DISABLED = 0x02,
+	I2400M_TLV_TYPE_WAKEUP_MODE = 144,
+};
+
+struct i2400m_cmd_enter_power_save {
+	struct i2400m_l3l4_hdr hdr;
+	struct i2400m_tlv_hdr tlv;
+	__le32 val;
+} __packed;
+
+
+/*
+ * Request entering power save
+ *
+ * This command is (mainly) executed when the device indicates that it
+ * is ready to go into powersave mode via a REPORT_POWERSAVE_READY.
+ */
+int i2400m_cmd_enter_powersave(struct i2400m *i2400m)
+{
+	int result;
+	struct device *dev = i2400m_dev(i2400m);
+	struct sk_buff *ack_skb;
+	struct i2400m_cmd_enter_power_save *cmd;
+	char strerr[32];
+
+	result = -ENOMEM;
+	cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
+	if (cmd == NULL)
+		goto error_alloc;
+	cmd->hdr.type = cpu_to_le16(I2400M_MT_CMD_ENTER_POWERSAVE);
+	cmd->hdr.length = cpu_to_le16(sizeof(*cmd) - sizeof(cmd->hdr));
+	cmd->hdr.version = cpu_to_le16(I2400M_L3L4_VERSION);
+	cmd->tlv.type = cpu_to_le16(I2400M_TLV_TYPE_WAKEUP_MODE);
+	cmd->tlv.length = cpu_to_le16(sizeof(cmd->val));
+	cmd->val = cpu_to_le32(I2400M_WAKEUP_ENABLED);
+
+	ack_skb = i2400m_msg_to_dev(i2400m, cmd, sizeof(*cmd));
+	result = PTR_ERR(ack_skb);
+	if (IS_ERR(ack_skb)) {
+		dev_err(dev, "Failed to issue 'Enter power save' command: %d\n",
+			result);
+		goto error_msg_to_dev;
+	}
+	result = i2400m_msg_check_status(wimax_msg_data(ack_skb),
+					 strerr, sizeof(strerr));
+	if (result == -EACCES)
+		d_printf(1, dev, "Cannot enter power save mode\n");
+	else if (result < 0)
+		dev_err(dev, "'Enter power save' (0x%04x) command failed: "
+			"%d - %s\n", I2400M_MT_CMD_ENTER_POWERSAVE,
+			result, strerr);
+	else
+		d_printf(1, dev, "device ready to power save\n");
+	kfree_skb(ack_skb);
+error_msg_to_dev:
+	kfree(cmd);
+error_alloc:
+	return result;
+}
+EXPORT_SYMBOL_GPL(i2400m_cmd_enter_powersave);
+
+
+/*
+ * Definitions for getting device information
+ */
+enum {
+	I2400M_TLV_DETAILED_DEVICE_INFO = 140
+};
+
+/**
+ * i2400m_get_device_info - Query the device for detailed device information
+ *
+ * @i2400m: device descriptor
+ *
+ * Returns: an skb whose skb->data points to a 'struct
+ *    i2400m_tlv_detailed_device_info'. When done, kfree_skb() it. The
+ *    skb is *guaranteed* to contain the whole TLV data structure.
+ *
+ *    On error, IS_ERR(skb) is true and ERR_PTR(skb) is the error
+ *    code.
+ */
+struct sk_buff *i2400m_get_device_info(struct i2400m *i2400m)
+{
+	int result;
+	struct device *dev = i2400m_dev(i2400m);
+	struct sk_buff *ack_skb;
+	struct i2400m_l3l4_hdr *cmd;
+	const struct i2400m_l3l4_hdr *ack;
+	size_t ack_len;
+	const struct i2400m_tlv_hdr *tlv;
+	const struct i2400m_tlv_detailed_device_info *ddi;
+	char strerr[32];
+
+	ack_skb = ERR_PTR(-ENOMEM);
+	cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
+	if (cmd == NULL)
+		goto error_alloc;
+	cmd->type = cpu_to_le16(I2400M_MT_GET_DEVICE_INFO);
+	cmd->length = 0;
+	cmd->version = cpu_to_le16(I2400M_L3L4_VERSION);
+
+	ack_skb = i2400m_msg_to_dev(i2400m, cmd, sizeof(*cmd));
+	if (IS_ERR(ack_skb)) {
+		dev_err(dev, "Failed to issue 'get device info' command: %ld\n",
+			PTR_ERR(ack_skb));
+		goto error_msg_to_dev;
+	}
+	ack = wimax_msg_data_len(ack_skb, &ack_len);
+	result = i2400m_msg_check_status(ack, strerr, sizeof(strerr));
+	if (result < 0) {
+		dev_err(dev, "'get device info' (0x%04x) command failed: "
+			"%d - %s\n", I2400M_MT_GET_DEVICE_INFO, result,
+			strerr);
+		goto error_cmd_failed;
+	}
+	tlv = i2400m_tlv_find(i2400m, ack->pl, ack_len - sizeof(*ack),
+			      I2400M_TLV_DETAILED_DEVICE_INFO, sizeof(*ddi));
+	if (tlv == NULL) {
+		dev_err(dev, "GET DEVICE INFO: "
+			"detailed device info TLV not found (0x%04x)\n",
+			I2400M_TLV_DETAILED_DEVICE_INFO);
+		result = -EIO;
+		goto error_no_tlv;
+	}
+	skb_pull(ack_skb, (void *) tlv - (void *) ack_skb->data);
+error_msg_to_dev:
+	kfree(cmd);
+error_alloc:
+	return ack_skb;
+
+error_no_tlv:
+error_cmd_failed:
+	kfree_skb(ack_skb);
+	kfree(cmd);
+	return ERR_PTR(result);
+}
+
+
+/* Firmware interface versions we support */
+enum {
+	I2400M_HDIv_MAJOR = 9,
+	I2400M_HDIv_MINOR = 1,
+	I2400M_HDIv_MINOR_2 = 2,
+};
+
+
+/**
+ * i2400m_firmware_check - check firmware versions are compatible with
+ * the driver
+ *
+ * @i2400m: device descriptor
+ *
+ * Returns: 0 if ok, < 0 errno code an error and a message in the
+ *    kernel log.
+ *
+ * Long function, but quite simple; first chunk launches the command
+ * and double checks the reply for the right TLV. Then we process the
+ * TLV (where the meat is).
+ *
+ * Once we process the TLV that gives us the firmware's interface
+ * version, we encode it and save it in i2400m->fw_version for future
+ * reference.
+ */
+int i2400m_firmware_check(struct i2400m *i2400m)
+{
+	int result;
+	struct device *dev = i2400m_dev(i2400m);
+	struct sk_buff *ack_skb;
+	struct i2400m_l3l4_hdr *cmd;
+	const struct i2400m_l3l4_hdr *ack;
+	size_t ack_len;
+	const struct i2400m_tlv_hdr *tlv;
+	const struct i2400m_tlv_l4_message_versions *l4mv;
+	char strerr[32];
+	unsigned major, minor, branch;
+
+	result = -ENOMEM;
+	cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
+	if (cmd == NULL)
+		goto error_alloc;
+	cmd->type = cpu_to_le16(I2400M_MT_GET_LM_VERSION);
+	cmd->length = 0;
+	cmd->version = cpu_to_le16(I2400M_L3L4_VERSION);
+
+	ack_skb = i2400m_msg_to_dev(i2400m, cmd, sizeof(*cmd));
+	if (IS_ERR(ack_skb)) {
+		result = PTR_ERR(ack_skb);
+		dev_err(dev, "Failed to issue 'get lm version' command: %-d\n",
+			result);
+		goto error_msg_to_dev;
+	}
+	ack = wimax_msg_data_len(ack_skb, &ack_len);
+	result = i2400m_msg_check_status(ack, strerr, sizeof(strerr));
+	if (result < 0) {
+		dev_err(dev, "'get lm version' (0x%04x) command failed: "
+			"%d - %s\n", I2400M_MT_GET_LM_VERSION, result,
+			strerr);
+		goto error_cmd_failed;
+	}
+	tlv = i2400m_tlv_find(i2400m, ack->pl, ack_len - sizeof(*ack),
+			      I2400M_TLV_L4_MESSAGE_VERSIONS, sizeof(*l4mv));
+	if (tlv == NULL) {
+		dev_err(dev, "get lm version: TLV not found (0x%04x)\n",
+			I2400M_TLV_L4_MESSAGE_VERSIONS);
+		result = -EIO;
+		goto error_no_tlv;
+	}
+	l4mv = container_of(tlv, typeof(*l4mv), hdr);
+	major = le16_to_cpu(l4mv->major);
+	minor = le16_to_cpu(l4mv->minor);
+	branch = le16_to_cpu(l4mv->branch);
+	result = -EINVAL;
+	if (major != I2400M_HDIv_MAJOR) {
+		dev_err(dev, "unsupported major fw version "
+			"%u.%u.%u\n", major, minor, branch);
+		goto error_bad_major;
+	}
+	result = 0;
+	if (minor > I2400M_HDIv_MINOR_2 || minor < I2400M_HDIv_MINOR)
+		dev_warn(dev, "untested minor fw version %u.%u.%u\n",
+			 major, minor, branch);
+	/* Yes, we ignore the branch -- we don't have to track it */
+	i2400m->fw_version = major << 16 | minor;
+	dev_info(dev, "firmware interface version %u.%u.%u\n",
+		 major, minor, branch);
+error_bad_major:
+error_no_tlv:
+error_cmd_failed:
+	kfree_skb(ack_skb);
+error_msg_to_dev:
+	kfree(cmd);
+error_alloc:
+	return result;
+}
+
+
+/*
+ * Send an DoExitIdle command to the device to ask it to go out of
+ * basestation-idle mode.
+ *
+ * @i2400m: device descriptor
+ *
+ * This starts a renegotiation with the basestation that might involve
+ * another crypto handshake with user space.
+ *
+ * Returns: 0 if ok, < 0 errno code on error.
+ */
+int i2400m_cmd_exit_idle(struct i2400m *i2400m)
+{
+	int result;
+	struct device *dev = i2400m_dev(i2400m);
+	struct sk_buff *ack_skb;
+	struct i2400m_l3l4_hdr *cmd;
+	char strerr[32];
+
+	result = -ENOMEM;
+	cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
+	if (cmd == NULL)
+		goto error_alloc;
+	cmd->type = cpu_to_le16(I2400M_MT_CMD_EXIT_IDLE);
+	cmd->length = 0;
+	cmd->version = cpu_to_le16(I2400M_L3L4_VERSION);
+
+	ack_skb = i2400m_msg_to_dev(i2400m, cmd, sizeof(*cmd));
+	result = PTR_ERR(ack_skb);
+	if (IS_ERR(ack_skb)) {
+		dev_err(dev, "Failed to issue 'exit idle' command: %d\n",
+			result);
+		goto error_msg_to_dev;
+	}
+	result = i2400m_msg_check_status(wimax_msg_data(ack_skb),
+					 strerr, sizeof(strerr));
+	kfree_skb(ack_skb);
+error_msg_to_dev:
+	kfree(cmd);
+error_alloc:
+	return result;
+
+}
+
+
+/*
+ * Query the device for its state, update the WiMAX stack's idea of it
+ *
+ * @i2400m: device descriptor
+ *
+ * Returns: 0 if ok, < 0 errno code on error.
+ *
+ * Executes a 'Get State' command and parses the returned
+ * TLVs.
+ *
+ * Because this is almost identical to a 'Report State', we use
+ * i2400m_report_state_hook() to parse the answer. This will set the
+ * carrier state, as well as the RF Kill switches state.
+ */
+static int i2400m_cmd_get_state(struct i2400m *i2400m)
+{
+	int result;
+	struct device *dev = i2400m_dev(i2400m);
+	struct sk_buff *ack_skb;
+	struct i2400m_l3l4_hdr *cmd;
+	const struct i2400m_l3l4_hdr *ack;
+	size_t ack_len;
+	char strerr[32];
+
+	result = -ENOMEM;
+	cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
+	if (cmd == NULL)
+		goto error_alloc;
+	cmd->type = cpu_to_le16(I2400M_MT_GET_STATE);
+	cmd->length = 0;
+	cmd->version = cpu_to_le16(I2400M_L3L4_VERSION);
+
+	ack_skb = i2400m_msg_to_dev(i2400m, cmd, sizeof(*cmd));
+	if (IS_ERR(ack_skb)) {
+		dev_err(dev, "Failed to issue 'get state' command: %ld\n",
+			PTR_ERR(ack_skb));
+		result = PTR_ERR(ack_skb);
+		goto error_msg_to_dev;
+	}
+	ack = wimax_msg_data_len(ack_skb, &ack_len);
+	result = i2400m_msg_check_status(ack, strerr, sizeof(strerr));
+	if (result < 0) {
+		dev_err(dev, "'get state' (0x%04x) command failed: "
+			"%d - %s\n", I2400M_MT_GET_STATE, result, strerr);
+		goto error_cmd_failed;
+	}
+	i2400m_report_state_hook(i2400m, ack, ack_len - sizeof(*ack),
+				 "GET STATE");
+	result = 0;
+	kfree_skb(ack_skb);
+error_cmd_failed:
+error_msg_to_dev:
+	kfree(cmd);
+error_alloc:
+	return result;
+}
+
+/**
+ * Set basic configuration settings
+ *
+ * @i2400m: device descriptor
+ * @args: array of pointers to the TLV headers to send for
+ *     configuration (each followed by its payload).
+ *     TLV headers and payloads must be properly initialized, with the
+ *     right endianess (LE).
+ * @arg_size: number of pointers in the @args array
+ */
+static int i2400m_set_init_config(struct i2400m *i2400m,
+				  const struct i2400m_tlv_hdr **arg,
+				  size_t args)
+{
+	int result;
+	struct device *dev = i2400m_dev(i2400m);
+	struct sk_buff *ack_skb;
+	struct i2400m_l3l4_hdr *cmd;
+	char strerr[32];
+	unsigned argc, argsize, tlv_size;
+	const struct i2400m_tlv_hdr *tlv_hdr;
+	void *buf, *itr;
+
+	d_fnstart(3, dev, "(i2400m %p arg %p args %zu)\n", i2400m, arg, args);
+	result = 0;
+	if (args == 0)
+		goto none;
+	/* Compute the size of all the TLVs, so we can alloc a
+	 * contiguous command block to copy them. */
+	argsize = 0;
+	for (argc = 0; argc < args; argc++) {
+		tlv_hdr = arg[argc];
+		argsize += sizeof(*tlv_hdr) + le16_to_cpu(tlv_hdr->length);
+	}
+	WARN_ON(argc >= 9);	/* As per hw spec */
+
+	/* Alloc the space for the command and TLVs*/
+	result = -ENOMEM;
+	buf = kzalloc(sizeof(*cmd) + argsize, GFP_KERNEL);
+	if (buf == NULL)
+		goto error_alloc;
+	cmd = buf;
+	cmd->type = cpu_to_le16(I2400M_MT_SET_INIT_CONFIG);
+	cmd->length = cpu_to_le16(argsize);
+	cmd->version = cpu_to_le16(I2400M_L3L4_VERSION);
+
+	/* Copy the TLVs */
+	itr = buf + sizeof(*cmd);
+	for (argc = 0; argc < args; argc++) {
+		tlv_hdr = arg[argc];
+		tlv_size = sizeof(*tlv_hdr) + le16_to_cpu(tlv_hdr->length);
+		memcpy(itr, tlv_hdr, tlv_size);
+		itr += tlv_size;
+	}
+
+	/* Send the message! */
+	ack_skb = i2400m_msg_to_dev(i2400m, buf, sizeof(*cmd) + argsize);
+	result = PTR_ERR(ack_skb);
+	if (IS_ERR(ack_skb)) {
+		dev_err(dev, "Failed to issue 'init config' command: %d\n",
+			result);
+
+		goto error_msg_to_dev;
+	}
+	result = i2400m_msg_check_status(wimax_msg_data(ack_skb),
+					 strerr, sizeof(strerr));
+	if (result < 0)
+		dev_err(dev, "'init config' (0x%04x) command failed: %d - %s\n",
+			I2400M_MT_SET_INIT_CONFIG, result, strerr);
+	kfree_skb(ack_skb);
+error_msg_to_dev:
+	kfree(buf);
+error_alloc:
+none:
+	d_fnend(3, dev, "(i2400m %p arg %p args %zu) = %d\n",
+		i2400m, arg, args, result);
+	return result;
+
+}
+
+/**
+ * i2400m_set_idle_timeout - Set the device's idle mode timeout
+ *
+ * @i2400m: i2400m device descriptor
+ *
+ * @msecs: milliseconds for the timeout to enter idle mode. Between
+ *     100 to 300000 (5m); 0 to disable. In increments of 100.
+ *
+ * After this @msecs of the link being idle (no data being sent or
+ * received), the device will negotiate with the basestation entering
+ * idle mode for saving power. The connection is maintained, but
+ * getting out of it (done in tx.c) will require some negotiation,
+ * possible crypto re-handshake and a possible DHCP re-lease.
+ *
+ * Only available if fw_version >= 0x00090002.
+ *
+ * Returns: 0 if ok, < 0 errno code on error.
+ */
+int i2400m_set_idle_timeout(struct i2400m *i2400m, unsigned msecs)
+{
+	int result;
+	struct device *dev = i2400m_dev(i2400m);
+	struct sk_buff *ack_skb;
+	struct {
+		struct i2400m_l3l4_hdr hdr;
+		struct i2400m_tlv_config_idle_timeout cit;
+	} *cmd;
+	const struct i2400m_l3l4_hdr *ack;
+	size_t ack_len;
+	char strerr[32];
+
+	result = -ENOSYS;
+	if (i2400m_le_v1_3(i2400m))
+		goto error_alloc;
+	result = -ENOMEM;
+	cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
+	if (cmd == NULL)
+		goto error_alloc;
+	cmd->hdr.type = cpu_to_le16(I2400M_MT_GET_STATE);
+	cmd->hdr.length = cpu_to_le16(sizeof(*cmd) - sizeof(cmd->hdr));
+	cmd->hdr.version = cpu_to_le16(I2400M_L3L4_VERSION);
+
+	cmd->cit.hdr.type =
+		cpu_to_le16(I2400M_TLV_CONFIG_IDLE_TIMEOUT);
+	cmd->cit.hdr.length = cpu_to_le16(sizeof(cmd->cit.timeout));
+	cmd->cit.timeout = cpu_to_le32(msecs);
+
+	ack_skb = i2400m_msg_to_dev(i2400m, cmd, sizeof(*cmd));
+	if (IS_ERR(ack_skb)) {
+		dev_err(dev, "Failed to issue 'set idle timeout' command: "
+			"%ld\n", PTR_ERR(ack_skb));
+		result = PTR_ERR(ack_skb);
+		goto error_msg_to_dev;
+	}
+	ack = wimax_msg_data_len(ack_skb, &ack_len);
+	result = i2400m_msg_check_status(ack, strerr, sizeof(strerr));
+	if (result < 0) {
+		dev_err(dev, "'set idle timeout' (0x%04x) command failed: "
+			"%d - %s\n", I2400M_MT_GET_STATE, result, strerr);
+		goto error_cmd_failed;
+	}
+	result = 0;
+	kfree_skb(ack_skb);
+error_cmd_failed:
+error_msg_to_dev:
+	kfree(cmd);
+error_alloc:
+	return result;
+}
+
+
+/**
+ * i2400m_dev_initialize - Initialize the device once communications are ready
+ *
+ * @i2400m: device descriptor
+ *
+ * Returns: 0 if ok, < 0 errno code on error.
+ *
+ * Configures the device to work the way we like it.
+ *
+ * At the point of this call, the device is registered with the WiMAX
+ * and netdev stacks, firmware is uploaded and we can talk to the
+ * device normally.
+ */
+int i2400m_dev_initialize(struct i2400m *i2400m)
+{
+	int result;
+	struct device *dev = i2400m_dev(i2400m);
+	struct i2400m_tlv_config_idle_parameters idle_params;
+	struct i2400m_tlv_config_idle_timeout idle_timeout;
+	struct i2400m_tlv_config_d2h_data_format df;
+	struct i2400m_tlv_config_dl_host_reorder dlhr;
+	const struct i2400m_tlv_hdr *args[9];
+	unsigned argc = 0;
+
+	d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
+	if (i2400m_passive_mode)
+		goto out_passive;
+	/* Disable idle mode? (enabled by default) */
+	if (i2400m_idle_mode_disabled) {
+		if (i2400m_le_v1_3(i2400m)) {
+			idle_params.hdr.type =
+				cpu_to_le16(I2400M_TLV_CONFIG_IDLE_PARAMETERS);
+			idle_params.hdr.length = cpu_to_le16(
+				sizeof(idle_params) - sizeof(idle_params.hdr));
+			idle_params.idle_timeout = 0;
+			idle_params.idle_paging_interval = 0;
+			args[argc++] = &idle_params.hdr;
+		} else {
+			idle_timeout.hdr.type =
+				cpu_to_le16(I2400M_TLV_CONFIG_IDLE_TIMEOUT);
+			idle_timeout.hdr.length = cpu_to_le16(
+				sizeof(idle_timeout) - sizeof(idle_timeout.hdr));
+			idle_timeout.timeout = 0;
+			args[argc++] = &idle_timeout.hdr;
+		}
+	}
+	if (i2400m_ge_v1_4(i2400m)) {
+		/* Enable extended RX data format? */
+		df.hdr.type =
+			cpu_to_le16(I2400M_TLV_CONFIG_D2H_DATA_FORMAT);
+		df.hdr.length = cpu_to_le16(
+			sizeof(df) - sizeof(df.hdr));
+		df.format = 1;
+		args[argc++] = &df.hdr;
+
+		/* Enable RX data reordering?
+		 * (switch flipped in rx.c:i2400m_rx_setup() after fw upload) */
+		if (i2400m->rx_reorder) {
+			dlhr.hdr.type =
+				cpu_to_le16(I2400M_TLV_CONFIG_DL_HOST_REORDER);
+			dlhr.hdr.length = cpu_to_le16(
+				sizeof(dlhr) - sizeof(dlhr.hdr));
+			dlhr.reorder = 1;
+			args[argc++] = &dlhr.hdr;
+		}
+	}
+	result = i2400m_set_init_config(i2400m, args, argc);
+	if (result < 0)
+		goto error;
+out_passive:
+	/*
+	 * Update state: Here it just calls a get state; parsing the
+	 * result (System State TLV and RF Status TLV [done in the rx
+	 * path hooks]) will set the hardware and software RF-Kill
+	 * status.
+	 */
+	result = i2400m_cmd_get_state(i2400m);
+error:
+	if (result < 0)
+		dev_err(dev, "failed to initialize the device: %d\n", result);
+	d_fnend(3, dev, "(i2400m %p) = %d\n", i2400m, result);
+	return result;
+}
+
+
+/**
+ * i2400m_dev_shutdown - Shutdown a running device
+ *
+ * @i2400m: device descriptor
+ *
+ * Release resources acquired during the running of the device; in
+ * theory, should also tell the device to go to sleep, switch off the
+ * radio, all that, but at this point, in most cases (driver
+ * disconnection, reset handling) we can't even talk to the device.
+ */
+void i2400m_dev_shutdown(struct i2400m *i2400m)
+{
+	struct device *dev = i2400m_dev(i2400m);
+
+	d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
+	d_fnend(3, dev, "(i2400m %p) = void\n", i2400m);
+}
diff --git a/drivers/staging/wimax/i2400m/debug-levels.h b/drivers/staging/wimax/i2400m/debug-levels.h
new file mode 100644
index 000000000000..a317e9fbb734
--- /dev/null
+++ b/drivers/staging/wimax/i2400m/debug-levels.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * Debug levels control file for the i2400m module
+ *
+ * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ */
+#ifndef __debug_levels__h__
+#define __debug_levels__h__
+
+/* Maximum compile and run time debug level for all submodules */
+#define D_MODULENAME i2400m
+#define D_MASTER CONFIG_WIMAX_I2400M_DEBUG_LEVEL
+
+#include "../linux-wimax-debug.h"
+
+/* List of all the enabled modules */
+enum d_module {
+	D_SUBMODULE_DECLARE(control),
+	D_SUBMODULE_DECLARE(driver),
+	D_SUBMODULE_DECLARE(debugfs),
+	D_SUBMODULE_DECLARE(fw),
+	D_SUBMODULE_DECLARE(netdev),
+	D_SUBMODULE_DECLARE(rfkill),
+	D_SUBMODULE_DECLARE(rx),
+	D_SUBMODULE_DECLARE(sysfs),
+	D_SUBMODULE_DECLARE(tx),
+};
+
+
+#endif /* #ifndef __debug_levels__h__ */
diff --git a/drivers/staging/wimax/i2400m/debugfs.c b/drivers/staging/wimax/i2400m/debugfs.c
new file mode 100644
index 000000000000..1c640b41ea4c
--- /dev/null
+++ b/drivers/staging/wimax/i2400m/debugfs.c
@@ -0,0 +1,253 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * Debugfs interfaces to manipulate driver and device information
+ *
+ * Copyright (C) 2007 Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ */
+
+#include <linux/debugfs.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/spinlock.h>
+#include <linux/device.h>
+#include <linux/export.h>
+#include "i2400m.h"
+
+
+#define D_SUBMODULE debugfs
+#include "debug-levels.h"
+
+static
+int debugfs_netdev_queue_stopped_get(void *data, u64 *val)
+{
+	struct i2400m *i2400m = data;
+	*val = netif_queue_stopped(i2400m->wimax_dev.net_dev);
+	return 0;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(fops_netdev_queue_stopped,
+			debugfs_netdev_queue_stopped_get,
+			NULL, "%llu\n");
+
+/*
+ * We don't allow partial reads of this file, as then the reader would
+ * get weirdly confused data as it is updated.
+ *
+ * So or you read it all or nothing; if you try to read with an offset
+ * != 0, we consider you are done reading.
+ */
+static
+ssize_t i2400m_rx_stats_read(struct file *filp, char __user *buffer,
+			     size_t count, loff_t *ppos)
+{
+	struct i2400m *i2400m = filp->private_data;
+	char buf[128];
+	unsigned long flags;
+
+	if (*ppos != 0)
+		return 0;
+	if (count < sizeof(buf))
+		return -ENOSPC;
+	spin_lock_irqsave(&i2400m->rx_lock, flags);
+	snprintf(buf, sizeof(buf), "%u %u %u %u %u %u %u\n",
+		 i2400m->rx_pl_num, i2400m->rx_pl_min,
+		 i2400m->rx_pl_max, i2400m->rx_num,
+		 i2400m->rx_size_acc,
+		 i2400m->rx_size_min, i2400m->rx_size_max);
+	spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+	return simple_read_from_buffer(buffer, count, ppos, buf, strlen(buf));
+}
+
+
+/* Any write clears the stats */
+static
+ssize_t i2400m_rx_stats_write(struct file *filp, const char __user *buffer,
+			      size_t count, loff_t *ppos)
+{
+	struct i2400m *i2400m = filp->private_data;
+	unsigned long flags;
+
+	spin_lock_irqsave(&i2400m->rx_lock, flags);
+	i2400m->rx_pl_num = 0;
+	i2400m->rx_pl_max = 0;
+	i2400m->rx_pl_min = UINT_MAX;
+	i2400m->rx_num = 0;
+	i2400m->rx_size_acc = 0;
+	i2400m->rx_size_min = UINT_MAX;
+	i2400m->rx_size_max = 0;
+	spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+	return count;
+}
+
+static
+const struct file_operations i2400m_rx_stats_fops = {
+	.owner =	THIS_MODULE,
+	.open =		simple_open,
+	.read =		i2400m_rx_stats_read,
+	.write =	i2400m_rx_stats_write,
+	.llseek =	default_llseek,
+};
+
+
+/* See i2400m_rx_stats_read() */
+static
+ssize_t i2400m_tx_stats_read(struct file *filp, char __user *buffer,
+			     size_t count, loff_t *ppos)
+{
+	struct i2400m *i2400m = filp->private_data;
+	char buf[128];
+	unsigned long flags;
+
+	if (*ppos != 0)
+		return 0;
+	if (count < sizeof(buf))
+		return -ENOSPC;
+	spin_lock_irqsave(&i2400m->tx_lock, flags);
+	snprintf(buf, sizeof(buf), "%u %u %u %u %u %u %u\n",
+		 i2400m->tx_pl_num, i2400m->tx_pl_min,
+		 i2400m->tx_pl_max, i2400m->tx_num,
+		 i2400m->tx_size_acc,
+		 i2400m->tx_size_min, i2400m->tx_size_max);
+	spin_unlock_irqrestore(&i2400m->tx_lock, flags);
+	return simple_read_from_buffer(buffer, count, ppos, buf, strlen(buf));
+}
+
+/* Any write clears the stats */
+static
+ssize_t i2400m_tx_stats_write(struct file *filp, const char __user *buffer,
+			      size_t count, loff_t *ppos)
+{
+	struct i2400m *i2400m = filp->private_data;
+	unsigned long flags;
+
+	spin_lock_irqsave(&i2400m->tx_lock, flags);
+	i2400m->tx_pl_num = 0;
+	i2400m->tx_pl_max = 0;
+	i2400m->tx_pl_min = UINT_MAX;
+	i2400m->tx_num = 0;
+	i2400m->tx_size_acc = 0;
+	i2400m->tx_size_min = UINT_MAX;
+	i2400m->tx_size_max = 0;
+	spin_unlock_irqrestore(&i2400m->tx_lock, flags);
+	return count;
+}
+
+static
+const struct file_operations i2400m_tx_stats_fops = {
+	.owner =	THIS_MODULE,
+	.open =		simple_open,
+	.read =		i2400m_tx_stats_read,
+	.write =	i2400m_tx_stats_write,
+	.llseek =	default_llseek,
+};
+
+
+/* Write 1 to ask the device to go into suspend */
+static
+int debugfs_i2400m_suspend_set(void *data, u64 val)
+{
+	int result;
+	struct i2400m *i2400m = data;
+	result = i2400m_cmd_enter_powersave(i2400m);
+	if (result >= 0)
+		result = 0;
+	return result;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(fops_i2400m_suspend,
+			NULL, debugfs_i2400m_suspend_set,
+			"%llu\n");
+
+/*
+ * Reset the device
+ *
+ * Write 0 to ask the device to soft reset, 1 to cold reset, 2 to bus
+ * reset (as defined by enum i2400m_reset_type).
+ */
+static
+int debugfs_i2400m_reset_set(void *data, u64 val)
+{
+	int result;
+	struct i2400m *i2400m = data;
+	enum i2400m_reset_type rt = val;
+	switch(rt) {
+	case I2400M_RT_WARM:
+	case I2400M_RT_COLD:
+	case I2400M_RT_BUS:
+		result = i2400m_reset(i2400m, rt);
+		if (result >= 0)
+			result = 0;
+		break;
+	default:
+		result = -EINVAL;
+	}
+	return result;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(fops_i2400m_reset,
+			NULL, debugfs_i2400m_reset_set,
+			"%llu\n");
+
+void i2400m_debugfs_add(struct i2400m *i2400m)
+{
+	struct dentry *dentry = i2400m->wimax_dev.debugfs_dentry;
+
+	dentry = debugfs_create_dir("i2400m", dentry);
+	i2400m->debugfs_dentry = dentry;
+
+	d_level_register_debugfs("dl_", control, dentry);
+	d_level_register_debugfs("dl_", driver, dentry);
+	d_level_register_debugfs("dl_", debugfs, dentry);
+	d_level_register_debugfs("dl_", fw, dentry);
+	d_level_register_debugfs("dl_", netdev, dentry);
+	d_level_register_debugfs("dl_", rfkill, dentry);
+	d_level_register_debugfs("dl_", rx, dentry);
+	d_level_register_debugfs("dl_", tx, dentry);
+
+	debugfs_create_size_t("tx_in", 0400, dentry, &i2400m->tx_in);
+	debugfs_create_size_t("tx_out", 0400, dentry, &i2400m->tx_out);
+	debugfs_create_u32("state", 0600, dentry, &i2400m->state);
+
+	/*
+	 * Trace received messages from user space
+	 *
+	 * In order to tap the bidirectional message stream in the
+	 * 'msg' pipe, user space can read from the 'msg' pipe;
+	 * however, due to limitations in libnl, we can't know what
+	 * the different applications are sending down to the kernel.
+	 *
+	 * So we have this hack where the driver will echo any message
+	 * received on the msg pipe from user space [through a call to
+	 * wimax_dev->op_msg_from_user() into
+	 * i2400m_op_msg_from_user()] into the 'trace' pipe that this
+	 * driver creates.
+	 *
+	 * So then, reading from both the 'trace' and 'msg' pipes in
+	 * user space will provide a full dump of the traffic.
+	 *
+	 * Write 1 to activate, 0 to clear.
+	 *
+	 * It is not really very atomic, but it is also not too
+	 * critical.
+	 */
+	debugfs_create_u8("trace_msg_from_user", 0600, dentry,
+			  &i2400m->trace_msg_from_user);
+
+	debugfs_create_file("netdev_queue_stopped", 0400, dentry, i2400m,
+			    &fops_netdev_queue_stopped);
+
+	debugfs_create_file("rx_stats", 0600, dentry, i2400m,
+			    &i2400m_rx_stats_fops);
+
+	debugfs_create_file("tx_stats", 0600, dentry, i2400m,
+			    &i2400m_tx_stats_fops);
+
+	debugfs_create_file("suspend", 0200, dentry, i2400m,
+			    &fops_i2400m_suspend);
+
+	debugfs_create_file("reset", 0200, dentry, i2400m, &fops_i2400m_reset);
+}
+
+void i2400m_debugfs_rm(struct i2400m *i2400m)
+{
+	debugfs_remove_recursive(i2400m->debugfs_dentry);
+}
diff --git a/drivers/staging/wimax/i2400m/driver.c b/drivers/staging/wimax/i2400m/driver.c
new file mode 100644
index 000000000000..dc8939ff78c0
--- /dev/null
+++ b/drivers/staging/wimax/i2400m/driver.c
@@ -0,0 +1,1002 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * Generic probe/disconnect, reset and message passing
+ *
+ * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *
+ * See i2400m.h for driver documentation. This contains helpers for
+ * the driver model glue [_setup()/_release()], handling device resets
+ * [_dev_reset_handle()], and the backends for the WiMAX stack ops
+ * reset [_op_reset()] and message from user [_op_msg_from_user()].
+ *
+ * ROADMAP:
+ *
+ * i2400m_op_msg_from_user()
+ *   i2400m_msg_to_dev()
+ *   wimax_msg_to_user_send()
+ *
+ * i2400m_op_reset()
+ *   i240m->bus_reset()
+ *
+ * i2400m_dev_reset_handle()
+ *   __i2400m_dev_reset_handle()
+ *     __i2400m_dev_stop()
+ *     __i2400m_dev_start()
+ *
+ * i2400m_setup()
+ *   i2400m->bus_setup()
+ *   i2400m_bootrom_init()
+ *   register_netdev()
+ *   wimax_dev_add()
+ *   i2400m_dev_start()
+ *     __i2400m_dev_start()
+ *       i2400m_dev_bootstrap()
+ *       i2400m_tx_setup()
+ *       i2400m->bus_dev_start()
+ *       i2400m_firmware_check()
+ *       i2400m_check_mac_addr()
+ *
+ * i2400m_release()
+ *   i2400m_dev_stop()
+ *     __i2400m_dev_stop()
+ *       i2400m_dev_shutdown()
+ *       i2400m->bus_dev_stop()
+ *       i2400m_tx_release()
+ *   i2400m->bus_release()
+ *   wimax_dev_rm()
+ *   unregister_netdev()
+ */
+#include "i2400m.h"
+#include <linux/etherdevice.h>
+#include "linux-wimax-i2400m.h"
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/suspend.h>
+#include <linux/slab.h>
+
+#define D_SUBMODULE driver
+#include "debug-levels.h"
+
+
+static char i2400m_debug_params[128];
+module_param_string(debug, i2400m_debug_params, sizeof(i2400m_debug_params),
+		    0644);
+MODULE_PARM_DESC(debug,
+		 "String of space-separated NAME:VALUE pairs, where NAMEs "
+		 "are the different debug submodules and VALUE are the "
+		 "initial debug value to set.");
+
+static char i2400m_barkers_params[128];
+module_param_string(barkers, i2400m_barkers_params,
+		    sizeof(i2400m_barkers_params), 0644);
+MODULE_PARM_DESC(barkers,
+		 "String of comma-separated 32-bit values; each is "
+		 "recognized as the value the device sends as a reboot "
+		 "signal; values are appended to a list--setting one value "
+		 "as zero cleans the existing list and starts a new one.");
+
+/*
+ * WiMAX stack operation: relay a message from user space
+ *
+ * @wimax_dev: device descriptor
+ * @pipe_name: named pipe the message is for
+ * @msg_buf: pointer to the message bytes
+ * @msg_len: length of the buffer
+ * @genl_info: passed by the generic netlink layer
+ *
+ * The WiMAX stack will call this function when a message was received
+ * from user space.
+ *
+ * For the i2400m, this is an L3L4 message, as specified in
+ * include/linux/wimax/i2400m.h, and thus prefixed with a 'struct
+ * i2400m_l3l4_hdr'. Driver (and device) expect the messages to be
+ * coded in Little Endian.
+ *
+ * This function just verifies that the header declaration and the
+ * payload are consistent and then deals with it, either forwarding it
+ * to the device or procesing it locally.
+ *
+ * In the i2400m, messages are basically commands that will carry an
+ * ack, so we use i2400m_msg_to_dev() and then deliver the ack back to
+ * user space. The rx.c code might intercept the response and use it
+ * to update the driver's state, but then it will pass it on so it can
+ * be relayed back to user space.
+ *
+ * Note that asynchronous events from the device are processed and
+ * sent to user space in rx.c.
+ */
+static
+int i2400m_op_msg_from_user(struct wimax_dev *wimax_dev,
+			    const char *pipe_name,
+			    const void *msg_buf, size_t msg_len,
+			    const struct genl_info *genl_info)
+{
+	int result;
+	struct i2400m *i2400m = wimax_dev_to_i2400m(wimax_dev);
+	struct device *dev = i2400m_dev(i2400m);
+	struct sk_buff *ack_skb;
+
+	d_fnstart(4, dev, "(wimax_dev %p [i2400m %p] msg_buf %p "
+		  "msg_len %zu genl_info %p)\n", wimax_dev, i2400m,
+		  msg_buf, msg_len, genl_info);
+	ack_skb = i2400m_msg_to_dev(i2400m, msg_buf, msg_len);
+	result = PTR_ERR(ack_skb);
+	if (IS_ERR(ack_skb))
+		goto error_msg_to_dev;
+	result = wimax_msg_send(&i2400m->wimax_dev, ack_skb);
+error_msg_to_dev:
+	d_fnend(4, dev, "(wimax_dev %p [i2400m %p] msg_buf %p msg_len %zu "
+		"genl_info %p) = %d\n", wimax_dev, i2400m, msg_buf, msg_len,
+		genl_info, result);
+	return result;
+}
+
+
+/*
+ * Context to wait for a reset to finalize
+ */
+struct i2400m_reset_ctx {
+	struct completion completion;
+	int result;
+};
+
+
+/*
+ * WiMAX stack operation: reset a device
+ *
+ * @wimax_dev: device descriptor
+ *
+ * See the documentation for wimax_reset() and wimax_dev->op_reset for
+ * the requirements of this function. The WiMAX stack guarantees
+ * serialization on calls to this function.
+ *
+ * Do a warm reset on the device; if it fails, resort to a cold reset
+ * and return -ENODEV. On successful warm reset, we need to block
+ * until it is complete.
+ *
+ * The bus-driver implementation of reset takes care of falling back
+ * to cold reset if warm fails.
+ */
+static
+int i2400m_op_reset(struct wimax_dev *wimax_dev)
+{
+	int result;
+	struct i2400m *i2400m = wimax_dev_to_i2400m(wimax_dev);
+	struct device *dev = i2400m_dev(i2400m);
+	struct i2400m_reset_ctx ctx = {
+		.completion = COMPLETION_INITIALIZER_ONSTACK(ctx.completion),
+		.result = 0,
+	};
+
+	d_fnstart(4, dev, "(wimax_dev %p)\n", wimax_dev);
+	mutex_lock(&i2400m->init_mutex);
+	i2400m->reset_ctx = &ctx;
+	mutex_unlock(&i2400m->init_mutex);
+	result = i2400m_reset(i2400m, I2400M_RT_WARM);
+	if (result < 0)
+		goto out;
+	result = wait_for_completion_timeout(&ctx.completion, 4*HZ);
+	if (result == 0)
+		result = -ETIMEDOUT;
+	else if (result > 0)
+		result = ctx.result;
+	/* if result < 0, pass it on */
+	mutex_lock(&i2400m->init_mutex);
+	i2400m->reset_ctx = NULL;
+	mutex_unlock(&i2400m->init_mutex);
+out:
+	d_fnend(4, dev, "(wimax_dev %p) = %d\n", wimax_dev, result);
+	return result;
+}
+
+
+/*
+ * Check the MAC address we got from boot mode is ok
+ *
+ * @i2400m: device descriptor
+ *
+ * Returns: 0 if ok, < 0 errno code on error.
+ */
+static
+int i2400m_check_mac_addr(struct i2400m *i2400m)
+{
+	int result;
+	struct device *dev = i2400m_dev(i2400m);
+	struct sk_buff *skb;
+	const struct i2400m_tlv_detailed_device_info *ddi;
+	struct net_device *net_dev = i2400m->wimax_dev.net_dev;
+
+	d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
+	skb = i2400m_get_device_info(i2400m);
+	if (IS_ERR(skb)) {
+		result = PTR_ERR(skb);
+		dev_err(dev, "Cannot verify MAC address, error reading: %d\n",
+			result);
+		goto error;
+	}
+	/* Extract MAC address */
+	ddi = (void *) skb->data;
+	BUILD_BUG_ON(ETH_ALEN != sizeof(ddi->mac_address));
+	d_printf(2, dev, "GET DEVICE INFO: mac addr %pM\n",
+		 ddi->mac_address);
+	if (!memcmp(net_dev->perm_addr, ddi->mac_address,
+		   sizeof(ddi->mac_address)))
+		goto ok;
+	dev_warn(dev, "warning: device reports a different MAC address "
+		 "to that of boot mode's\n");
+	dev_warn(dev, "device reports     %pM\n", ddi->mac_address);
+	dev_warn(dev, "boot mode reported %pM\n", net_dev->perm_addr);
+	if (is_zero_ether_addr(ddi->mac_address))
+		dev_err(dev, "device reports an invalid MAC address, "
+			"not updating\n");
+	else {
+		dev_warn(dev, "updating MAC address\n");
+		net_dev->addr_len = ETH_ALEN;
+		memcpy(net_dev->perm_addr, ddi->mac_address, ETH_ALEN);
+		memcpy(net_dev->dev_addr, ddi->mac_address, ETH_ALEN);
+	}
+ok:
+	result = 0;
+	kfree_skb(skb);
+error:
+	d_fnend(3, dev, "(i2400m %p) = %d\n", i2400m, result);
+	return result;
+}
+
+
+/**
+ * __i2400m_dev_start - Bring up driver communication with the device
+ *
+ * @i2400m: device descriptor
+ * @flags: boot mode flags
+ *
+ * Returns: 0 if ok, < 0 errno code on error.
+ *
+ * Uploads firmware and brings up all the resources needed to be able
+ * to communicate with the device.
+ *
+ * The workqueue has to be setup early, at least before RX handling
+ * (it's only real user for now) so it can process reports as they
+ * arrive. We also want to destroy it if we retry, to make sure it is
+ * flushed...easier like this.
+ *
+ * TX needs to be setup before the bus-specific code (otherwise on
+ * shutdown, the bus-tx code could try to access it).
+ */
+static
+int __i2400m_dev_start(struct i2400m *i2400m, enum i2400m_bri flags)
+{
+	int result;
+	struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
+	struct net_device *net_dev = wimax_dev->net_dev;
+	struct device *dev = i2400m_dev(i2400m);
+	int times = i2400m->bus_bm_retries;
+
+	d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
+retry:
+	result = i2400m_dev_bootstrap(i2400m, flags);
+	if (result < 0) {
+		dev_err(dev, "cannot bootstrap device: %d\n", result);
+		goto error_bootstrap;
+	}
+	result = i2400m_tx_setup(i2400m);
+	if (result < 0)
+		goto error_tx_setup;
+	result = i2400m_rx_setup(i2400m);
+	if (result < 0)
+		goto error_rx_setup;
+	i2400m->work_queue = create_singlethread_workqueue(wimax_dev->name);
+	if (i2400m->work_queue == NULL) {
+		result = -ENOMEM;
+		dev_err(dev, "cannot create workqueue\n");
+		goto error_create_workqueue;
+	}
+	if (i2400m->bus_dev_start) {
+		result = i2400m->bus_dev_start(i2400m);
+		if (result < 0)
+			goto error_bus_dev_start;
+	}
+	i2400m->ready = 1;
+	wmb();		/* see i2400m->ready's documentation  */
+	/* process pending reports from the device */
+	queue_work(i2400m->work_queue, &i2400m->rx_report_ws);
+	result = i2400m_firmware_check(i2400m);	/* fw versions ok? */
+	if (result < 0)
+		goto error_fw_check;
+	/* At this point is ok to send commands to the device */
+	result = i2400m_check_mac_addr(i2400m);
+	if (result < 0)
+		goto error_check_mac_addr;
+	result = i2400m_dev_initialize(i2400m);
+	if (result < 0)
+		goto error_dev_initialize;
+
+	/* We don't want any additional unwanted error recovery triggered
+	 * from any other context so if anything went wrong before we come
+	 * here, let's keep i2400m->error_recovery untouched and leave it to
+	 * dev_reset_handle(). See dev_reset_handle(). */
+
+	atomic_dec(&i2400m->error_recovery);
+	/* Every thing works so far, ok, now we are ready to
+	 * take error recovery if it's required. */
+
+	/* At this point, reports will come for the device and set it
+	 * to the right state if it is different than UNINITIALIZED */
+	d_fnend(3, dev, "(net_dev %p [i2400m %p]) = %d\n",
+		net_dev, i2400m, result);
+	return result;
+
+error_dev_initialize:
+error_check_mac_addr:
+error_fw_check:
+	i2400m->ready = 0;
+	wmb();		/* see i2400m->ready's documentation  */
+	flush_workqueue(i2400m->work_queue);
+	if (i2400m->bus_dev_stop)
+		i2400m->bus_dev_stop(i2400m);
+error_bus_dev_start:
+	destroy_workqueue(i2400m->work_queue);
+error_create_workqueue:
+	i2400m_rx_release(i2400m);
+error_rx_setup:
+	i2400m_tx_release(i2400m);
+error_tx_setup:
+error_bootstrap:
+	if (result == -EL3RST && times-- > 0) {
+		flags = I2400M_BRI_SOFT|I2400M_BRI_MAC_REINIT;
+		goto retry;
+	}
+	d_fnend(3, dev, "(net_dev %p [i2400m %p]) = %d\n",
+		net_dev, i2400m, result);
+	return result;
+}
+
+
+static
+int i2400m_dev_start(struct i2400m *i2400m, enum i2400m_bri bm_flags)
+{
+	int result = 0;
+	mutex_lock(&i2400m->init_mutex);	/* Well, start the device */
+	if (i2400m->updown == 0) {
+		result = __i2400m_dev_start(i2400m, bm_flags);
+		if (result >= 0) {
+			i2400m->updown = 1;
+			i2400m->alive = 1;
+			wmb();/* see i2400m->updown and i2400m->alive's doc */
+		}
+	}
+	mutex_unlock(&i2400m->init_mutex);
+	return result;
+}
+
+
+/**
+ * i2400m_dev_stop - Tear down driver communication with the device
+ *
+ * @i2400m: device descriptor
+ *
+ * Returns: 0 if ok, < 0 errno code on error.
+ *
+ * Releases all the resources allocated to communicate with the
+ * device. Note we cannot destroy the workqueue earlier as until RX is
+ * fully destroyed, it could still try to schedule jobs.
+ */
+static
+void __i2400m_dev_stop(struct i2400m *i2400m)
+{
+	struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
+	struct device *dev = i2400m_dev(i2400m);
+
+	d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
+	wimax_state_change(wimax_dev, __WIMAX_ST_QUIESCING);
+	i2400m_msg_to_dev_cancel_wait(i2400m, -EL3RST);
+	complete(&i2400m->msg_completion);
+	i2400m_net_wake_stop(i2400m);
+	i2400m_dev_shutdown(i2400m);
+	/*
+	 * Make sure no report hooks are running *before* we stop the
+	 * communication infrastructure with the device.
+	 */
+	i2400m->ready = 0;	/* nobody can queue work anymore */
+	wmb();		/* see i2400m->ready's documentation  */
+	flush_workqueue(i2400m->work_queue);
+
+	if (i2400m->bus_dev_stop)
+		i2400m->bus_dev_stop(i2400m);
+	destroy_workqueue(i2400m->work_queue);
+	i2400m_rx_release(i2400m);
+	i2400m_tx_release(i2400m);
+	wimax_state_change(wimax_dev, WIMAX_ST_DOWN);
+	d_fnend(3, dev, "(i2400m %p) = 0\n", i2400m);
+}
+
+
+/*
+ * Watch out -- we only need to stop if there is a need for it. The
+ * device could have reset itself and failed to come up again (see
+ * _i2400m_dev_reset_handle()).
+ */
+static
+void i2400m_dev_stop(struct i2400m *i2400m)
+{
+	mutex_lock(&i2400m->init_mutex);
+	if (i2400m->updown) {
+		__i2400m_dev_stop(i2400m);
+		i2400m->updown = 0;
+		i2400m->alive = 0;
+		wmb();	/* see i2400m->updown and i2400m->alive's doc */
+	}
+	mutex_unlock(&i2400m->init_mutex);
+}
+
+
+/*
+ * Listen to PM events to cache the firmware before suspend/hibernation
+ *
+ * When the device comes out of suspend, it might go into reset and
+ * firmware has to be uploaded again. At resume, most of the times, we
+ * can't load firmware images from disk, so we need to cache it.
+ *
+ * i2400m_fw_cache() will allocate a kobject and attach the firmware
+ * to it; that way we don't have to worry too much about the fw loader
+ * hitting a race condition.
+ *
+ * Note: modus operandi stolen from the Orinoco driver; thx.
+ */
+static
+int i2400m_pm_notifier(struct notifier_block *notifier,
+		       unsigned long pm_event,
+		       void *unused)
+{
+	struct i2400m *i2400m =
+		container_of(notifier, struct i2400m, pm_notifier);
+	struct device *dev = i2400m_dev(i2400m);
+
+	d_fnstart(3, dev, "(i2400m %p pm_event %lx)\n", i2400m, pm_event);
+	switch (pm_event) {
+	case PM_HIBERNATION_PREPARE:
+	case PM_SUSPEND_PREPARE:
+		i2400m_fw_cache(i2400m);
+		break;
+	case PM_POST_RESTORE:
+		/* Restore from hibernation failed. We need to clean
+		 * up in exactly the same way, so fall through. */
+	case PM_POST_HIBERNATION:
+	case PM_POST_SUSPEND:
+		i2400m_fw_uncache(i2400m);
+		break;
+
+	case PM_RESTORE_PREPARE:
+	default:
+		break;
+	}
+	d_fnend(3, dev, "(i2400m %p pm_event %lx) = void\n", i2400m, pm_event);
+	return NOTIFY_DONE;
+}
+
+
+/*
+ * pre-reset is called before a device is going on reset
+ *
+ * This has to be followed by a call to i2400m_post_reset(), otherwise
+ * bad things might happen.
+ */
+int i2400m_pre_reset(struct i2400m *i2400m)
+{
+	struct device *dev = i2400m_dev(i2400m);
+
+	d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
+	d_printf(1, dev, "pre-reset shut down\n");
+
+	mutex_lock(&i2400m->init_mutex);
+	if (i2400m->updown) {
+		netif_tx_disable(i2400m->wimax_dev.net_dev);
+		__i2400m_dev_stop(i2400m);
+		/* down't set updown to zero -- this way
+		 * post_reset can restore properly */
+	}
+	mutex_unlock(&i2400m->init_mutex);
+	if (i2400m->bus_release)
+		i2400m->bus_release(i2400m);
+	d_fnend(3, dev, "(i2400m %p) = 0\n", i2400m);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(i2400m_pre_reset);
+
+
+/*
+ * Restore device state after a reset
+ *
+ * Do the work needed after a device reset to bring it up to the same
+ * state as it was before the reset.
+ *
+ * NOTE: this requires i2400m->init_mutex taken
+ */
+int i2400m_post_reset(struct i2400m *i2400m)
+{
+	int result = 0;
+	struct device *dev = i2400m_dev(i2400m);
+
+	d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
+	d_printf(1, dev, "post-reset start\n");
+	if (i2400m->bus_setup) {
+		result = i2400m->bus_setup(i2400m);
+		if (result < 0) {
+			dev_err(dev, "bus-specific setup failed: %d\n",
+				result);
+			goto error_bus_setup;
+		}
+	}
+	mutex_lock(&i2400m->init_mutex);
+	if (i2400m->updown) {
+		result = __i2400m_dev_start(
+			i2400m, I2400M_BRI_SOFT | I2400M_BRI_MAC_REINIT);
+		if (result < 0)
+			goto error_dev_start;
+	}
+	mutex_unlock(&i2400m->init_mutex);
+	d_fnend(3, dev, "(i2400m %p) = %d\n", i2400m, result);
+	return result;
+
+error_dev_start:
+	if (i2400m->bus_release)
+		i2400m->bus_release(i2400m);
+	/* even if the device was up, it could not be recovered, so we
+	 * mark it as down. */
+	i2400m->updown = 0;
+	wmb();		/* see i2400m->updown's documentation  */
+	mutex_unlock(&i2400m->init_mutex);
+error_bus_setup:
+	d_fnend(3, dev, "(i2400m %p) = %d\n", i2400m, result);
+	return result;
+}
+EXPORT_SYMBOL_GPL(i2400m_post_reset);
+
+
+/*
+ * The device has rebooted; fix up the device and the driver
+ *
+ * Tear down the driver communication with the device, reload the
+ * firmware and reinitialize the communication with the device.
+ *
+ * If someone calls a reset when the device's firmware is down, in
+ * theory we won't see it because we are not listening. However, just
+ * in case, leave the code to handle it.
+ *
+ * If there is a reset context, use it; this means someone is waiting
+ * for us to tell him when the reset operation is complete and the
+ * device is ready to rock again.
+ *
+ * NOTE: if we are in the process of bringing up or down the
+ *       communication with the device [running i2400m_dev_start() or
+ *       _stop()], don't do anything, let it fail and handle it.
+ *
+ * This function is ran always in a thread context
+ *
+ * This function gets passed, as payload to i2400m_work() a 'const
+ * char *' ptr with a "reason" why the reset happened (for messages).
+ */
+static
+void __i2400m_dev_reset_handle(struct work_struct *ws)
+{
+	struct i2400m *i2400m = container_of(ws, struct i2400m, reset_ws);
+	const char *reason = i2400m->reset_reason;
+	struct device *dev = i2400m_dev(i2400m);
+	struct i2400m_reset_ctx *ctx = i2400m->reset_ctx;
+	int result;
+
+	d_fnstart(3, dev, "(ws %p i2400m %p reason %s)\n", ws, i2400m, reason);
+
+	i2400m->boot_mode = 1;
+	wmb();		/* Make sure i2400m_msg_to_dev() sees boot_mode */
+
+	result = 0;
+	if (mutex_trylock(&i2400m->init_mutex) == 0) {
+		/* We are still in i2400m_dev_start() [let it fail] or
+		 * i2400m_dev_stop() [we are shutting down anyway, so
+		 * ignore it] or we are resetting somewhere else. */
+		dev_err(dev, "device rebooted somewhere else?\n");
+		i2400m_msg_to_dev_cancel_wait(i2400m, -EL3RST);
+		complete(&i2400m->msg_completion);
+		goto out;
+	}
+
+	dev_err(dev, "%s: reinitializing driver\n", reason);
+	rmb();
+	if (i2400m->updown) {
+		__i2400m_dev_stop(i2400m);
+		i2400m->updown = 0;
+		wmb();		/* see i2400m->updown's documentation  */
+	}
+
+	if (i2400m->alive) {
+		result = __i2400m_dev_start(i2400m,
+				    I2400M_BRI_SOFT | I2400M_BRI_MAC_REINIT);
+		if (result < 0) {
+			dev_err(dev, "%s: cannot start the device: %d\n",
+				reason, result);
+			result = -EUCLEAN;
+			if (atomic_read(&i2400m->bus_reset_retries)
+					>= I2400M_BUS_RESET_RETRIES) {
+				result = -ENODEV;
+				dev_err(dev, "tried too many times to "
+					"reset the device, giving up\n");
+			}
+		}
+	}
+
+	if (i2400m->reset_ctx) {
+		ctx->result = result;
+		complete(&ctx->completion);
+	}
+	mutex_unlock(&i2400m->init_mutex);
+	if (result == -EUCLEAN) {
+		/*
+		 * We come here because the reset during operational mode
+		 * wasn't successfully done and need to proceed to a bus
+		 * reset. For the dev_reset_handle() to be able to handle
+		 * the reset event later properly, we restore boot_mode back
+		 * to the state before previous reset. ie: just like we are
+		 * issuing the bus reset for the first time
+		 */
+		i2400m->boot_mode = 0;
+		wmb();
+
+		atomic_inc(&i2400m->bus_reset_retries);
+		/* ops, need to clean up [w/ init_mutex not held] */
+		result = i2400m_reset(i2400m, I2400M_RT_BUS);
+		if (result >= 0)
+			result = -ENODEV;
+	} else {
+		rmb();
+		if (i2400m->alive) {
+			/* great, we expect the device state up and
+			 * dev_start() actually brings the device state up */
+			i2400m->updown = 1;
+			wmb();
+			atomic_set(&i2400m->bus_reset_retries, 0);
+		}
+	}
+out:
+	d_fnend(3, dev, "(ws %p i2400m %p reason %s) = void\n",
+		ws, i2400m, reason);
+}
+
+
+/**
+ * i2400m_dev_reset_handle - Handle a device's reset in a thread context
+ *
+ * Schedule a device reset handling out on a thread context, so it
+ * is safe to call from atomic context. We can't use the i2400m's
+ * queue as we are going to destroy it and reinitialize it as part of
+ * the driver bringup/bringup process.
+ *
+ * See __i2400m_dev_reset_handle() for details; that takes care of
+ * reinitializing the driver to handle the reset, calling into the
+ * bus-specific functions ops as needed.
+ */
+int i2400m_dev_reset_handle(struct i2400m *i2400m, const char *reason)
+{
+	i2400m->reset_reason = reason;
+	return schedule_work(&i2400m->reset_ws);
+}
+EXPORT_SYMBOL_GPL(i2400m_dev_reset_handle);
+
+
+ /*
+ * The actual work of error recovery.
+ *
+ * The current implementation of error recovery is to trigger a bus reset.
+ */
+static
+void __i2400m_error_recovery(struct work_struct *ws)
+{
+	struct i2400m *i2400m = container_of(ws, struct i2400m, recovery_ws);
+
+	i2400m_reset(i2400m, I2400M_RT_BUS);
+}
+
+/*
+ * Schedule a work struct for error recovery.
+ *
+ * The intention of error recovery is to bring back the device to some
+ * known state whenever TX sees -110 (-ETIMEOUT) on copying the data to
+ * the device. The TX failure could mean a device bus stuck, so the current
+ * error recovery implementation is to trigger a bus reset to the device
+ * and hopefully it can bring back the device.
+ *
+ * The actual work of error recovery has to be in a thread context because
+ * it is kicked off in the TX thread (i2400ms->tx_workqueue) which is to be
+ * destroyed by the error recovery mechanism (currently a bus reset).
+ *
+ * Also, there may be already a queue of TX works that all hit
+ * the -ETIMEOUT error condition because the device is stuck already.
+ * Since bus reset is used as the error recovery mechanism and we don't
+ * want consecutive bus resets simply because the multiple TX works
+ * in the queue all hit the same device erratum, the flag "error_recovery"
+ * is introduced for preventing unwanted consecutive bus resets.
+ *
+ * Error recovery shall only be invoked again if previous one was completed.
+ * The flag error_recovery is set when error recovery mechanism is scheduled,
+ * and is checked when we need to schedule another error recovery. If it is
+ * in place already, then we shouldn't schedule another one.
+ */
+void i2400m_error_recovery(struct i2400m *i2400m)
+{
+	if (atomic_add_return(1, &i2400m->error_recovery) == 1)
+		schedule_work(&i2400m->recovery_ws);
+	else
+		atomic_dec(&i2400m->error_recovery);
+}
+EXPORT_SYMBOL_GPL(i2400m_error_recovery);
+
+/*
+ * Alloc the command and ack buffers for boot mode
+ *
+ * Get the buffers needed to deal with boot mode messages.
+ */
+static
+int i2400m_bm_buf_alloc(struct i2400m *i2400m)
+{
+	i2400m->bm_cmd_buf = kzalloc(I2400M_BM_CMD_BUF_SIZE, GFP_KERNEL);
+	if (i2400m->bm_cmd_buf == NULL)
+		goto error_bm_cmd_kzalloc;
+	i2400m->bm_ack_buf = kzalloc(I2400M_BM_ACK_BUF_SIZE, GFP_KERNEL);
+	if (i2400m->bm_ack_buf == NULL)
+		goto error_bm_ack_buf_kzalloc;
+	return 0;
+
+error_bm_ack_buf_kzalloc:
+	kfree(i2400m->bm_cmd_buf);
+error_bm_cmd_kzalloc:
+	return -ENOMEM;
+}
+
+
+/*
+ * Free boot mode command and ack buffers.
+ */
+static
+void i2400m_bm_buf_free(struct i2400m *i2400m)
+{
+	kfree(i2400m->bm_ack_buf);
+	kfree(i2400m->bm_cmd_buf);
+}
+
+
+/**
+ * i2400m_init - Initialize a 'struct i2400m' from all zeroes
+ *
+ * This is a bus-generic API call.
+ */
+void i2400m_init(struct i2400m *i2400m)
+{
+	wimax_dev_init(&i2400m->wimax_dev);
+
+	i2400m->boot_mode = 1;
+	i2400m->rx_reorder = 1;
+	init_waitqueue_head(&i2400m->state_wq);
+
+	spin_lock_init(&i2400m->tx_lock);
+	i2400m->tx_pl_min = UINT_MAX;
+	i2400m->tx_size_min = UINT_MAX;
+
+	spin_lock_init(&i2400m->rx_lock);
+	i2400m->rx_pl_min = UINT_MAX;
+	i2400m->rx_size_min = UINT_MAX;
+	INIT_LIST_HEAD(&i2400m->rx_reports);
+	INIT_WORK(&i2400m->rx_report_ws, i2400m_report_hook_work);
+
+	mutex_init(&i2400m->msg_mutex);
+	init_completion(&i2400m->msg_completion);
+
+	mutex_init(&i2400m->init_mutex);
+	/* wake_tx_ws is initialized in i2400m_tx_setup() */
+
+	INIT_WORK(&i2400m->reset_ws, __i2400m_dev_reset_handle);
+	INIT_WORK(&i2400m->recovery_ws, __i2400m_error_recovery);
+
+	atomic_set(&i2400m->bus_reset_retries, 0);
+
+	i2400m->alive = 0;
+
+	/* initialize error_recovery to 1 for denoting we
+	 * are not yet ready to take any error recovery */
+	atomic_set(&i2400m->error_recovery, 1);
+}
+EXPORT_SYMBOL_GPL(i2400m_init);
+
+
+int i2400m_reset(struct i2400m *i2400m, enum i2400m_reset_type rt)
+{
+	struct net_device *net_dev = i2400m->wimax_dev.net_dev;
+
+	/*
+	 * Make sure we stop TXs and down the carrier before
+	 * resetting; this is needed to avoid things like
+	 * i2400m_wake_tx() scheduling stuff in parallel.
+	 */
+	if (net_dev->reg_state == NETREG_REGISTERED) {
+		netif_tx_disable(net_dev);
+		netif_carrier_off(net_dev);
+	}
+	return i2400m->bus_reset(i2400m, rt);
+}
+EXPORT_SYMBOL_GPL(i2400m_reset);
+
+
+/**
+ * i2400m_setup - bus-generic setup function for the i2400m device
+ *
+ * @i2400m: device descriptor (bus-specific parts have been initialized)
+ *
+ * Returns: 0 if ok, < 0 errno code on error.
+ *
+ * Sets up basic device comunication infrastructure, boots the ROM to
+ * read the MAC address, registers with the WiMAX and network stacks
+ * and then brings up the device.
+ */
+int i2400m_setup(struct i2400m *i2400m, enum i2400m_bri bm_flags)
+{
+	int result;
+	struct device *dev = i2400m_dev(i2400m);
+	struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
+	struct net_device *net_dev = i2400m->wimax_dev.net_dev;
+
+	d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
+
+	snprintf(wimax_dev->name, sizeof(wimax_dev->name),
+		 "i2400m-%s:%s", dev->bus->name, dev_name(dev));
+
+	result = i2400m_bm_buf_alloc(i2400m);
+	if (result < 0) {
+		dev_err(dev, "cannot allocate bootmode scratch buffers\n");
+		goto error_bm_buf_alloc;
+	}
+
+	if (i2400m->bus_setup) {
+		result = i2400m->bus_setup(i2400m);
+		if (result < 0) {
+			dev_err(dev, "bus-specific setup failed: %d\n",
+				result);
+			goto error_bus_setup;
+		}
+	}
+
+	result = i2400m_bootrom_init(i2400m, bm_flags);
+	if (result < 0) {
+		dev_err(dev, "read mac addr: bootrom init "
+			"failed: %d\n", result);
+		goto error_bootrom_init;
+	}
+	result = i2400m_read_mac_addr(i2400m);
+	if (result < 0)
+		goto error_read_mac_addr;
+	eth_random_addr(i2400m->src_mac_addr);
+
+	i2400m->pm_notifier.notifier_call = i2400m_pm_notifier;
+	register_pm_notifier(&i2400m->pm_notifier);
+
+	result = register_netdev(net_dev);	/* Okey dokey, bring it up */
+	if (result < 0) {
+		dev_err(dev, "cannot register i2400m network device: %d\n",
+			result);
+		goto error_register_netdev;
+	}
+	netif_carrier_off(net_dev);
+
+	i2400m->wimax_dev.op_msg_from_user = i2400m_op_msg_from_user;
+	i2400m->wimax_dev.op_rfkill_sw_toggle = i2400m_op_rfkill_sw_toggle;
+	i2400m->wimax_dev.op_reset = i2400m_op_reset;
+
+	result = wimax_dev_add(&i2400m->wimax_dev, net_dev);
+	if (result < 0)
+		goto error_wimax_dev_add;
+
+	/* Now setup all that requires a registered net and wimax device. */
+	result = sysfs_create_group(&net_dev->dev.kobj, &i2400m_dev_attr_group);
+	if (result < 0) {
+		dev_err(dev, "cannot setup i2400m's sysfs: %d\n", result);
+		goto error_sysfs_setup;
+	}
+
+	i2400m_debugfs_add(i2400m);
+
+	result = i2400m_dev_start(i2400m, bm_flags);
+	if (result < 0)
+		goto error_dev_start;
+	d_fnend(3, dev, "(i2400m %p) = %d\n", i2400m, result);
+	return result;
+
+error_dev_start:
+	i2400m_debugfs_rm(i2400m);
+	sysfs_remove_group(&i2400m->wimax_dev.net_dev->dev.kobj,
+			   &i2400m_dev_attr_group);
+error_sysfs_setup:
+	wimax_dev_rm(&i2400m->wimax_dev);
+error_wimax_dev_add:
+	unregister_netdev(net_dev);
+error_register_netdev:
+	unregister_pm_notifier(&i2400m->pm_notifier);
+error_read_mac_addr:
+error_bootrom_init:
+	if (i2400m->bus_release)
+		i2400m->bus_release(i2400m);
+error_bus_setup:
+	i2400m_bm_buf_free(i2400m);
+error_bm_buf_alloc:
+	d_fnend(3, dev, "(i2400m %p) = %d\n", i2400m, result);
+	return result;
+}
+EXPORT_SYMBOL_GPL(i2400m_setup);
+
+
+/**
+ * i2400m_release - release the bus-generic driver resources
+ *
+ * Sends a disconnect message and undoes any setup done by i2400m_setup()
+ */
+void i2400m_release(struct i2400m *i2400m)
+{
+	struct device *dev = i2400m_dev(i2400m);
+
+	d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
+	netif_stop_queue(i2400m->wimax_dev.net_dev);
+
+	i2400m_dev_stop(i2400m);
+
+	cancel_work_sync(&i2400m->reset_ws);
+	cancel_work_sync(&i2400m->recovery_ws);
+
+	i2400m_debugfs_rm(i2400m);
+	sysfs_remove_group(&i2400m->wimax_dev.net_dev->dev.kobj,
+			   &i2400m_dev_attr_group);
+	wimax_dev_rm(&i2400m->wimax_dev);
+	unregister_netdev(i2400m->wimax_dev.net_dev);
+	unregister_pm_notifier(&i2400m->pm_notifier);
+	if (i2400m->bus_release)
+		i2400m->bus_release(i2400m);
+	i2400m_bm_buf_free(i2400m);
+	d_fnend(3, dev, "(i2400m %p) = void\n", i2400m);
+}
+EXPORT_SYMBOL_GPL(i2400m_release);
+
+
+/*
+ * Debug levels control; see debug.h
+ */
+struct d_level D_LEVEL[] = {
+	D_SUBMODULE_DEFINE(control),
+	D_SUBMODULE_DEFINE(driver),
+	D_SUBMODULE_DEFINE(debugfs),
+	D_SUBMODULE_DEFINE(fw),
+	D_SUBMODULE_DEFINE(netdev),
+	D_SUBMODULE_DEFINE(rfkill),
+	D_SUBMODULE_DEFINE(rx),
+	D_SUBMODULE_DEFINE(sysfs),
+	D_SUBMODULE_DEFINE(tx),
+};
+size_t D_LEVEL_SIZE = ARRAY_SIZE(D_LEVEL);
+
+
+static
+int __init i2400m_driver_init(void)
+{
+	d_parse_params(D_LEVEL, D_LEVEL_SIZE, i2400m_debug_params,
+		       "i2400m.debug");
+	return i2400m_barker_db_init(i2400m_barkers_params);
+}
+module_init(i2400m_driver_init);
+
+static
+void __exit i2400m_driver_exit(void)
+{
+	i2400m_barker_db_exit();
+}
+module_exit(i2400m_driver_exit);
+
+MODULE_AUTHOR("Intel Corporation <linux-wimax@intel.com>");
+MODULE_DESCRIPTION("Intel 2400M WiMAX networking bus-generic driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/staging/wimax/i2400m/fw.c b/drivers/staging/wimax/i2400m/fw.c
new file mode 100644
index 000000000000..6c9a41bff2e0
--- /dev/null
+++ b/drivers/staging/wimax/i2400m/fw.c
@@ -0,0 +1,1653 @@
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * Firmware uploader
+ *
+ *
+ * Copyright (C) 2007-2008 Intel Corporation. All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *
+ * Intel Corporation <linux-wimax@intel.com>
+ * Yanir Lubetkin <yanirx.lubetkin@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *  - Initial implementation
+ *
+ *
+ * THE PROCEDURE
+ *
+ * The 2400m and derived devices work in two modes: boot-mode or
+ * normal mode. In boot mode we can execute only a handful of commands
+ * targeted at uploading the firmware and launching it.
+ *
+ * The 2400m enters boot mode when it is first connected to the
+ * system, when it crashes and when you ask it to reboot. There are
+ * two submodes of the boot mode: signed and non-signed. Signed takes
+ * firmwares signed with a certain private key, non-signed takes any
+ * firmware. Normal hardware takes only signed firmware.
+ *
+ * On boot mode, in USB, we write to the device using the bulk out
+ * endpoint and read from it in the notification endpoint.
+ *
+ * Upon entrance to boot mode, the device sends (preceded with a few
+ * zero length packets (ZLPs) on the notification endpoint in USB) a
+ * reboot barker (4 le32 words with the same value). We ack it by
+ * sending the same barker to the device. The device acks with a
+ * reboot ack barker (4 le32 words with value I2400M_ACK_BARKER) and
+ * then is fully booted. At this point we can upload the firmware.
+ *
+ * Note that different iterations of the device and EEPROM
+ * configurations will send different [re]boot barkers; these are
+ * collected in i2400m_barker_db along with the firmware
+ * characteristics they require.
+ *
+ * This process is accomplished by the i2400m_bootrom_init()
+ * function. All the device interaction happens through the
+ * i2400m_bm_cmd() [boot mode command]. Special return values will
+ * indicate if the device did reset during the process.
+ *
+ * After this, we read the MAC address and then (if needed)
+ * reinitialize the device. We need to read it ahead of time because
+ * in the future, we might not upload the firmware until userspace
+ * 'ifconfig up's the device.
+ *
+ * We can then upload the firmware file. The file is composed of a BCF
+ * header (basic data, keys and signatures) and a list of write
+ * commands and payloads. Optionally more BCF headers might follow the
+ * main payload. We first upload the header [i2400m_dnload_init()] and
+ * then pass the commands and payloads verbatim to the i2400m_bm_cmd()
+ * function [i2400m_dnload_bcf()]. Then we tell the device to jump to
+ * the new firmware [i2400m_dnload_finalize()].
+ *
+ * Once firmware is uploaded, we are good to go :)
+ *
+ * When we don't know in which mode we are, we first try by sending a
+ * warm reset request that will take us to boot-mode. If we time out
+ * waiting for a reboot barker, that means maybe we are already in
+ * boot mode, so we send a reboot barker.
+ *
+ * COMMAND EXECUTION
+ *
+ * This code (and process) is single threaded; for executing commands,
+ * we post a URB to the notification endpoint, post the command, wait
+ * for data on the notification buffer. We don't need to worry about
+ * others as we know we are the only ones in there.
+ *
+ * BACKEND IMPLEMENTATION
+ *
+ * This code is bus-generic; the bus-specific driver provides back end
+ * implementations to send a boot mode command to the device and to
+ * read an acknolwedgement from it (or an asynchronous notification)
+ * from it.
+ *
+ * FIRMWARE LOADING
+ *
+ * Note that in some cases, we can't just load a firmware file (for
+ * example, when resuming). For that, we might cache the firmware
+ * file. Thus, when doing the bootstrap, if there is a cache firmware
+ * file, it is used; if not, loading from disk is attempted.
+ *
+ * ROADMAP
+ *
+ * i2400m_barker_db_init              Called by i2400m_driver_init()
+ *   i2400m_barker_db_add
+ *
+ * i2400m_barker_db_exit              Called by i2400m_driver_exit()
+ *
+ * i2400m_dev_bootstrap               Called by __i2400m_dev_start()
+ *   request_firmware
+ *   i2400m_fw_bootstrap
+ *     i2400m_fw_check
+ *       i2400m_fw_hdr_check
+ *     i2400m_fw_dnload
+ *   release_firmware
+ *
+ * i2400m_fw_dnload
+ *   i2400m_bootrom_init
+ *     i2400m_bm_cmd
+ *     i2400m_reset
+ *   i2400m_dnload_init
+ *     i2400m_dnload_init_signed
+ *     i2400m_dnload_init_nonsigned
+ *       i2400m_download_chunk
+ *         i2400m_bm_cmd
+ *   i2400m_dnload_bcf
+ *     i2400m_bm_cmd
+ *   i2400m_dnload_finalize
+ *     i2400m_bm_cmd
+ *
+ * i2400m_bm_cmd
+ *   i2400m->bus_bm_cmd_send()
+ *   i2400m->bus_bm_wait_for_ack
+ *   __i2400m_bm_ack_verify
+ *     i2400m_is_boot_barker
+ *
+ * i2400m_bm_cmd_prepare              Used by bus-drivers to prep
+ *                                    commands before sending
+ *
+ * i2400m_pm_notifier                 Called on Power Management events
+ *   i2400m_fw_cache
+ *   i2400m_fw_uncache
+ */
+#include <linux/firmware.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/usb.h>
+#include <linux/export.h>
+#include "i2400m.h"
+
+
+#define D_SUBMODULE fw
+#include "debug-levels.h"
+
+
+static const __le32 i2400m_ACK_BARKER[4] = {
+	cpu_to_le32(I2400M_ACK_BARKER),
+	cpu_to_le32(I2400M_ACK_BARKER),
+	cpu_to_le32(I2400M_ACK_BARKER),
+	cpu_to_le32(I2400M_ACK_BARKER)
+};
+
+
+/**
+ * Prepare a boot-mode command for delivery
+ *
+ * @cmd: pointer to bootrom header to prepare
+ *
+ * Computes checksum if so needed. After calling this function, DO NOT
+ * modify the command or header as the checksum won't work anymore.
+ *
+ * We do it from here because some times we cannot do it in the
+ * original context the command was sent (it is a const), so when we
+ * copy it to our staging buffer, we add the checksum there.
+ */
+void i2400m_bm_cmd_prepare(struct i2400m_bootrom_header *cmd)
+{
+	if (i2400m_brh_get_use_checksum(cmd)) {
+		int i;
+		u32 checksum = 0;
+		const u32 *checksum_ptr = (void *) cmd->payload;
+		for (i = 0; i < cmd->data_size / 4; i++)
+			checksum += cpu_to_le32(*checksum_ptr++);
+		checksum += cmd->command + cmd->target_addr + cmd->data_size;
+		cmd->block_checksum = cpu_to_le32(checksum);
+	}
+}
+EXPORT_SYMBOL_GPL(i2400m_bm_cmd_prepare);
+
+
+/*
+ * Database of known barkers.
+ *
+ * A barker is what the device sends indicating he is ready to be
+ * bootloaded. Different versions of the device will send different
+ * barkers. Depending on the barker, it might mean the device wants
+ * some kind of firmware or the other.
+ */
+static struct i2400m_barker_db {
+	__le32 data[4];
+} *i2400m_barker_db;
+static size_t i2400m_barker_db_used, i2400m_barker_db_size;
+
+
+static
+int i2400m_zrealloc_2x(void **ptr, size_t *_count, size_t el_size,
+		       gfp_t gfp_flags)
+{
+	size_t old_count = *_count,
+		new_count = old_count ? 2 * old_count : 2,
+		old_size = el_size * old_count,
+		new_size = el_size * new_count;
+	void *nptr = krealloc(*ptr, new_size, gfp_flags);
+	if (nptr) {
+		/* zero the other half or the whole thing if old_count
+		 * was zero */
+		if (old_size == 0)
+			memset(nptr, 0, new_size);
+		else
+			memset(nptr + old_size, 0, old_size);
+		*_count = new_count;
+		*ptr = nptr;
+		return 0;
+	} else
+		return -ENOMEM;
+}
+
+
+/*
+ * Add a barker to the database
+ *
+ * This cannot used outside of this module and only at at module_init
+ * time. This is to avoid the need to do locking.
+ */
+static
+int i2400m_barker_db_add(u32 barker_id)
+{
+	int result;
+
+	struct i2400m_barker_db *barker;
+	if (i2400m_barker_db_used >= i2400m_barker_db_size) {
+		result = i2400m_zrealloc_2x(
+			(void **) &i2400m_barker_db, &i2400m_barker_db_size,
+			sizeof(i2400m_barker_db[0]), GFP_KERNEL);
+		if (result < 0)
+			return result;
+	}
+	barker = i2400m_barker_db + i2400m_barker_db_used++;
+	barker->data[0] = le32_to_cpu(barker_id);
+	barker->data[1] = le32_to_cpu(barker_id);
+	barker->data[2] = le32_to_cpu(barker_id);
+	barker->data[3] = le32_to_cpu(barker_id);
+	return 0;
+}
+
+
+void i2400m_barker_db_exit(void)
+{
+	kfree(i2400m_barker_db);
+	i2400m_barker_db = NULL;
+	i2400m_barker_db_size = 0;
+	i2400m_barker_db_used = 0;
+}
+
+
+/*
+ * Helper function to add all the known stable barkers to the barker
+ * database.
+ */
+static
+int i2400m_barker_db_known_barkers(void)
+{
+	int result;
+
+	result = i2400m_barker_db_add(I2400M_NBOOT_BARKER);
+	if (result < 0)
+		goto error_add;
+	result = i2400m_barker_db_add(I2400M_SBOOT_BARKER);
+	if (result < 0)
+		goto error_add;
+	result = i2400m_barker_db_add(I2400M_SBOOT_BARKER_6050);
+	if (result < 0)
+		goto error_add;
+error_add:
+       return result;
+}
+
+
+/*
+ * Initialize the barker database
+ *
+ * This can only be used from the module_init function for this
+ * module; this is to avoid the need to do locking.
+ *
+ * @options: command line argument with extra barkers to
+ *     recognize. This is a comma-separated list of 32-bit hex
+ *     numbers. They are appended to the existing list. Setting 0
+ *     cleans the existing list and starts a new one.
+ */
+int i2400m_barker_db_init(const char *_options)
+{
+	int result;
+	char *options = NULL, *options_orig, *token;
+
+	i2400m_barker_db = NULL;
+	i2400m_barker_db_size = 0;
+	i2400m_barker_db_used = 0;
+
+	result = i2400m_barker_db_known_barkers();
+	if (result < 0)
+		goto error_add;
+	/* parse command line options from i2400m.barkers */
+	if (_options != NULL) {
+		unsigned barker;
+
+		options_orig = kstrdup(_options, GFP_KERNEL);
+		if (options_orig == NULL) {
+			result = -ENOMEM;
+			goto error_parse;
+		}
+		options = options_orig;
+
+		while ((token = strsep(&options, ",")) != NULL) {
+			if (*token == '\0')	/* eat joint commas */
+				continue;
+			if (sscanf(token, "%x", &barker) != 1
+			    || barker > 0xffffffff) {
+				printk(KERN_ERR "%s: can't recognize "
+				       "i2400m.barkers value '%s' as "
+				       "a 32-bit number\n",
+				       __func__, token);
+				result = -EINVAL;
+				goto error_parse;
+			}
+			if (barker == 0) {
+				/* clean list and start new */
+				i2400m_barker_db_exit();
+				continue;
+			}
+			result = i2400m_barker_db_add(barker);
+			if (result < 0)
+				goto error_parse_add;
+		}
+		kfree(options_orig);
+	}
+	return 0;
+
+error_parse_add:
+error_parse:
+	kfree(options_orig);
+error_add:
+	kfree(i2400m_barker_db);
+	return result;
+}
+
+
+/*
+ * Recognize a boot barker
+ *
+ * @buf: buffer where the boot barker.
+ * @buf_size: size of the buffer (has to be 16 bytes). It is passed
+ *     here so the function can check it for the caller.
+ *
+ * Note that as a side effect, upon identifying the obtained boot
+ * barker, this function will set i2400m->barker to point to the right
+ * barker database entry. Subsequent calls to the function will result
+ * in verifying that the same type of boot barker is returned when the
+ * device [re]boots (as long as the same device instance is used).
+ *
+ * Return: 0 if @buf matches a known boot barker. -ENOENT if the
+ *     buffer in @buf doesn't match any boot barker in the database or
+ *     -EILSEQ if the buffer doesn't have the right size.
+ */
+int i2400m_is_boot_barker(struct i2400m *i2400m,
+			  const void *buf, size_t buf_size)
+{
+	int result;
+	struct device *dev = i2400m_dev(i2400m);
+	struct i2400m_barker_db *barker;
+	int i;
+
+	result = -ENOENT;
+	if (buf_size != sizeof(i2400m_barker_db[i].data))
+		return result;
+
+	/* Short circuit if we have already discovered the barker
+	 * associated with the device. */
+	if (i2400m->barker &&
+	    !memcmp(buf, i2400m->barker, sizeof(i2400m->barker->data)))
+		return 0;
+
+	for (i = 0; i < i2400m_barker_db_used; i++) {
+		barker = &i2400m_barker_db[i];
+		BUILD_BUG_ON(sizeof(barker->data) != 16);
+		if (memcmp(buf, barker->data, sizeof(barker->data)))
+			continue;
+
+		if (i2400m->barker == NULL) {
+			i2400m->barker = barker;
+			d_printf(1, dev, "boot barker set to #%u/%08x\n",
+				 i, le32_to_cpu(barker->data[0]));
+			if (barker->data[0] == le32_to_cpu(I2400M_NBOOT_BARKER))
+				i2400m->sboot = 0;
+			else
+				i2400m->sboot = 1;
+		} else if (i2400m->barker != barker) {
+			dev_err(dev, "HW inconsistency: device "
+				"reports a different boot barker "
+				"than set (from %08x to %08x)\n",
+				le32_to_cpu(i2400m->barker->data[0]),
+				le32_to_cpu(barker->data[0]));
+			result = -EIO;
+		} else
+			d_printf(2, dev, "boot barker confirmed #%u/%08x\n",
+				 i, le32_to_cpu(barker->data[0]));
+		result = 0;
+		break;
+	}
+	return result;
+}
+EXPORT_SYMBOL_GPL(i2400m_is_boot_barker);
+
+
+/*
+ * Verify the ack data received
+ *
+ * Given a reply to a boot mode command, chew it and verify everything
+ * is ok.
+ *
+ * @opcode: opcode which generated this ack. For error messages.
+ * @ack: pointer to ack data we received
+ * @ack_size: size of that data buffer
+ * @flags: I2400M_BM_CMD_* flags we called the command with.
+ *
+ * Way too long function -- maybe it should be further split
+ */
+static
+ssize_t __i2400m_bm_ack_verify(struct i2400m *i2400m, int opcode,
+			       struct i2400m_bootrom_header *ack,
+			       size_t ack_size, int flags)
+{
+	ssize_t result = -ENOMEM;
+	struct device *dev = i2400m_dev(i2400m);
+
+	d_fnstart(8, dev, "(i2400m %p opcode %d ack %p size %zu)\n",
+		  i2400m, opcode, ack, ack_size);
+	if (ack_size < sizeof(*ack)) {
+		result = -EIO;
+		dev_err(dev, "boot-mode cmd %d: HW BUG? notification didn't "
+			"return enough data (%zu bytes vs %zu expected)\n",
+			opcode, ack_size, sizeof(*ack));
+		goto error_ack_short;
+	}
+	result = i2400m_is_boot_barker(i2400m, ack, ack_size);
+	if (result >= 0) {
+		result = -ERESTARTSYS;
+		d_printf(6, dev, "boot-mode cmd %d: HW boot barker\n", opcode);
+		goto error_reboot;
+	}
+	if (ack_size == sizeof(i2400m_ACK_BARKER)
+		 && memcmp(ack, i2400m_ACK_BARKER, sizeof(*ack)) == 0) {
+		result = -EISCONN;
+		d_printf(3, dev, "boot-mode cmd %d: HW reboot ack barker\n",
+			 opcode);
+		goto error_reboot_ack;
+	}
+	result = 0;
+	if (flags & I2400M_BM_CMD_RAW)
+		goto out_raw;
+	ack->data_size = le32_to_cpu(ack->data_size);
+	ack->target_addr = le32_to_cpu(ack->target_addr);
+	ack->block_checksum = le32_to_cpu(ack->block_checksum);
+	d_printf(5, dev, "boot-mode cmd %d: notification for opcode %u "
+		 "response %u csum %u rr %u da %u\n",
+		 opcode, i2400m_brh_get_opcode(ack),
+		 i2400m_brh_get_response(ack),
+		 i2400m_brh_get_use_checksum(ack),
+		 i2400m_brh_get_response_required(ack),
+		 i2400m_brh_get_direct_access(ack));
+	result = -EIO;
+	if (i2400m_brh_get_signature(ack) != 0xcbbc) {
+		dev_err(dev, "boot-mode cmd %d: HW BUG? wrong signature "
+			"0x%04x\n", opcode, i2400m_brh_get_signature(ack));
+		goto error_ack_signature;
+	}
+	if (opcode != -1 && opcode != i2400m_brh_get_opcode(ack)) {
+		dev_err(dev, "boot-mode cmd %d: HW BUG? "
+			"received response for opcode %u, expected %u\n",
+			opcode, i2400m_brh_get_opcode(ack), opcode);
+		goto error_ack_opcode;
+	}
+	if (i2400m_brh_get_response(ack) != 0) {	/* failed? */
+		dev_err(dev, "boot-mode cmd %d: error; hw response %u\n",
+			opcode, i2400m_brh_get_response(ack));
+		goto error_ack_failed;
+	}
+	if (ack_size < ack->data_size + sizeof(*ack)) {
+		dev_err(dev, "boot-mode cmd %d: SW BUG "
+			"driver provided only %zu bytes for %zu bytes "
+			"of data\n", opcode, ack_size,
+			(size_t) le32_to_cpu(ack->data_size) + sizeof(*ack));
+		goto error_ack_short_buffer;
+	}
+	result = ack_size;
+	/* Don't you love this stack of empty targets? Well, I don't
+	 * either, but it helps track exactly who comes in here and
+	 * why :) */
+error_ack_short_buffer:
+error_ack_failed:
+error_ack_opcode:
+error_ack_signature:
+out_raw:
+error_reboot_ack:
+error_reboot:
+error_ack_short:
+	d_fnend(8, dev, "(i2400m %p opcode %d ack %p size %zu) = %d\n",
+		i2400m, opcode, ack, ack_size, (int) result);
+	return result;
+}
+
+
+/**
+ * i2400m_bm_cmd - Execute a boot mode command
+ *
+ * @cmd: buffer containing the command data (pointing at the header).
+ *     This data can be ANYWHERE (for USB, we will copy it to an
+ *     specific buffer). Make sure everything is in proper little
+ *     endian.
+ *
+ *     A raw buffer can be also sent, just cast it and set flags to
+ *     I2400M_BM_CMD_RAW.
+ *
+ *     This function will generate a checksum for you if the
+ *     checksum bit in the command is set (unless I2400M_BM_CMD_RAW
+ *     is set).
+ *
+ *     You can use the i2400m->bm_cmd_buf to stage your commands and
+ *     send them.
+ *
+ *     If NULL, no command is sent (we just wait for an ack).
+ *
+ * @cmd_size: size of the command. Will be auto padded to the
+ *     bus-specific drivers padding requirements.
+ *
+ * @ack: buffer where to place the acknowledgement. If it is a regular
+ *     command response, all fields will be returned with the right,
+ *     native endianess.
+ *
+ *     You *cannot* use i2400m->bm_ack_buf for this buffer.
+ *
+ * @ack_size: size of @ack, 16 aligned; you need to provide at least
+ *     sizeof(*ack) bytes and then enough to contain the return data
+ *     from the command
+ *
+ * @flags: see I2400M_BM_CMD_* above.
+ *
+ * @returns: bytes received by the notification; if < 0, an errno code
+ *     denoting an error or:
+ *
+ *     -ERESTARTSYS  The device has rebooted
+ *
+ * Executes a boot-mode command and waits for a response, doing basic
+ * validation on it; if a zero length response is received, it retries
+ * waiting for a response until a non-zero one is received (timing out
+ * after %I2400M_BOOT_RETRIES retries).
+ */
+static
+ssize_t i2400m_bm_cmd(struct i2400m *i2400m,
+		      const struct i2400m_bootrom_header *cmd, size_t cmd_size,
+		      struct i2400m_bootrom_header *ack, size_t ack_size,
+		      int flags)
+{
+	ssize_t result = -ENOMEM, rx_bytes;
+	struct device *dev = i2400m_dev(i2400m);
+	int opcode = cmd == NULL ? -1 : i2400m_brh_get_opcode(cmd);
+
+	d_fnstart(6, dev, "(i2400m %p cmd %p size %zu ack %p size %zu)\n",
+		  i2400m, cmd, cmd_size, ack, ack_size);
+	BUG_ON(ack_size < sizeof(*ack));
+	BUG_ON(i2400m->boot_mode == 0);
+
+	if (cmd != NULL) {		/* send the command */
+		result = i2400m->bus_bm_cmd_send(i2400m, cmd, cmd_size, flags);
+		if (result < 0)
+			goto error_cmd_send;
+		if ((flags & I2400M_BM_CMD_RAW) == 0)
+			d_printf(5, dev,
+				 "boot-mode cmd %d csum %u rr %u da %u: "
+				 "addr 0x%04x size %u block csum 0x%04x\n",
+				 opcode, i2400m_brh_get_use_checksum(cmd),
+				 i2400m_brh_get_response_required(cmd),
+				 i2400m_brh_get_direct_access(cmd),
+				 cmd->target_addr, cmd->data_size,
+				 cmd->block_checksum);
+	}
+	result = i2400m->bus_bm_wait_for_ack(i2400m, ack, ack_size);
+	if (result < 0) {
+		dev_err(dev, "boot-mode cmd %d: error waiting for an ack: %d\n",
+			opcode, (int) result);	/* bah, %zd doesn't work */
+		goto error_wait_for_ack;
+	}
+	rx_bytes = result;
+	/* verify the ack and read more if necessary [result is the
+	 * final amount of bytes we get in the ack]  */
+	result = __i2400m_bm_ack_verify(i2400m, opcode, ack, ack_size, flags);
+	if (result < 0)
+		goto error_bad_ack;
+	/* Don't you love this stack of empty targets? Well, I don't
+	 * either, but it helps track exactly who comes in here and
+	 * why :) */
+	result = rx_bytes;
+error_bad_ack:
+error_wait_for_ack:
+error_cmd_send:
+	d_fnend(6, dev, "(i2400m %p cmd %p size %zu ack %p size %zu) = %d\n",
+		i2400m, cmd, cmd_size, ack, ack_size, (int) result);
+	return result;
+}
+
+
+/**
+ * i2400m_download_chunk - write a single chunk of data to the device's memory
+ *
+ * @i2400m: device descriptor
+ * @buf: the buffer to write
+ * @buf_len: length of the buffer to write
+ * @addr: address in the device memory space
+ * @direct: bootrom write mode
+ * @do_csum: should a checksum validation be performed
+ */
+static int i2400m_download_chunk(struct i2400m *i2400m, const void *chunk,
+				 size_t __chunk_len, unsigned long addr,
+				 unsigned int direct, unsigned int do_csum)
+{
+	int ret;
+	size_t chunk_len = ALIGN(__chunk_len, I2400M_PL_ALIGN);
+	struct device *dev = i2400m_dev(i2400m);
+	struct {
+		struct i2400m_bootrom_header cmd;
+		u8 cmd_payload[];
+	} __packed *buf;
+	struct i2400m_bootrom_header ack;
+
+	d_fnstart(5, dev, "(i2400m %p chunk %p __chunk_len %zu addr 0x%08lx "
+		  "direct %u do_csum %u)\n", i2400m, chunk, __chunk_len,
+		  addr, direct, do_csum);
+	buf = i2400m->bm_cmd_buf;
+	memcpy(buf->cmd_payload, chunk, __chunk_len);
+	memset(buf->cmd_payload + __chunk_len, 0xad, chunk_len - __chunk_len);
+
+	buf->cmd.command = i2400m_brh_command(I2400M_BRH_WRITE,
+					      __chunk_len & 0x3 ? 0 : do_csum,
+					      __chunk_len & 0xf ? 0 : direct);
+	buf->cmd.target_addr = cpu_to_le32(addr);
+	buf->cmd.data_size = cpu_to_le32(__chunk_len);
+	ret = i2400m_bm_cmd(i2400m, &buf->cmd, sizeof(buf->cmd) + chunk_len,
+			    &ack, sizeof(ack), 0);
+	if (ret >= 0)
+		ret = 0;
+	d_fnend(5, dev, "(i2400m %p chunk %p __chunk_len %zu addr 0x%08lx "
+		"direct %u do_csum %u) = %d\n", i2400m, chunk, __chunk_len,
+		addr, direct, do_csum, ret);
+	return ret;
+}
+
+
+/*
+ * Download a BCF file's sections to the device
+ *
+ * @i2400m: device descriptor
+ * @bcf: pointer to firmware data (first header followed by the
+ *     payloads). Assumed verified and consistent.
+ * @bcf_len: length (in bytes) of the @bcf buffer.
+ *
+ * Returns: < 0 errno code on error or the offset to the jump instruction.
+ *
+ * Given a BCF file, downloads each section (a command and a payload)
+ * to the device's address space. Actually, it just executes each
+ * command i the BCF file.
+ *
+ * The section size has to be aligned to 4 bytes AND the padding has
+ * to be taken from the firmware file, as the signature takes it into
+ * account.
+ */
+static
+ssize_t i2400m_dnload_bcf(struct i2400m *i2400m,
+			  const struct i2400m_bcf_hdr *bcf, size_t bcf_len)
+{
+	ssize_t ret;
+	struct device *dev = i2400m_dev(i2400m);
+	size_t offset,		/* iterator offset */
+		data_size,	/* Size of the data payload */
+		section_size,	/* Size of the whole section (cmd + payload) */
+		section = 1;
+	const struct i2400m_bootrom_header *bh;
+	struct i2400m_bootrom_header ack;
+
+	d_fnstart(3, dev, "(i2400m %p bcf %p bcf_len %zu)\n",
+		  i2400m, bcf, bcf_len);
+	/* Iterate over the command blocks in the BCF file that start
+	 * after the header */
+	offset = le32_to_cpu(bcf->header_len) * sizeof(u32);
+	while (1) {	/* start sending the file */
+		bh = (void *) bcf + offset;
+		data_size = le32_to_cpu(bh->data_size);
+		section_size = ALIGN(sizeof(*bh) + data_size, 4);
+		d_printf(7, dev,
+			 "downloading section #%zu (@%zu %zu B) to 0x%08x\n",
+			 section, offset, sizeof(*bh) + data_size,
+			 le32_to_cpu(bh->target_addr));
+		/*
+		 * We look for JUMP cmd from the bootmode header,
+		 * either I2400M_BRH_SIGNED_JUMP for secure boot
+		 * or I2400M_BRH_JUMP for unsecure boot, the last chunk
+		 * should be the bootmode header with JUMP cmd.
+		 */
+		if (i2400m_brh_get_opcode(bh) == I2400M_BRH_SIGNED_JUMP ||
+			i2400m_brh_get_opcode(bh) == I2400M_BRH_JUMP) {
+			d_printf(5, dev,  "jump found @%zu\n", offset);
+			break;
+		}
+		if (offset + section_size > bcf_len) {
+			dev_err(dev, "fw %s: bad section #%zu, "
+				"end (@%zu) beyond EOF (@%zu)\n",
+				i2400m->fw_name, section,
+				offset + section_size,  bcf_len);
+			ret = -EINVAL;
+			goto error_section_beyond_eof;
+		}
+		__i2400m_msleep(20);
+		ret = i2400m_bm_cmd(i2400m, bh, section_size,
+				    &ack, sizeof(ack), I2400M_BM_CMD_RAW);
+		if (ret < 0) {
+			dev_err(dev, "fw %s: section #%zu (@%zu %zu B) "
+				"failed %d\n", i2400m->fw_name, section,
+				offset, sizeof(*bh) + data_size, (int) ret);
+			goto error_send;
+		}
+		offset += section_size;
+		section++;
+	}
+	ret = offset;
+error_section_beyond_eof:
+error_send:
+	d_fnend(3, dev, "(i2400m %p bcf %p bcf_len %zu) = %d\n",
+		i2400m, bcf, bcf_len, (int) ret);
+	return ret;
+}
+
+
+/*
+ * Indicate if the device emitted a reboot barker that indicates
+ * "signed boot"
+ */
+static
+unsigned i2400m_boot_is_signed(struct i2400m *i2400m)
+{
+	return likely(i2400m->sboot);
+}
+
+
+/*
+ * Do the final steps of uploading firmware
+ *
+ * @bcf_hdr: BCF header we are actually using
+ * @bcf: pointer to the firmware image (which matches the first header
+ *     that is followed by the actual payloads).
+ * @offset: [byte] offset into @bcf for the command we need to send.
+ *
+ * Depending on the boot mode (signed vs non-signed), different
+ * actions need to be taken.
+ */
+static
+int i2400m_dnload_finalize(struct i2400m *i2400m,
+			   const struct i2400m_bcf_hdr *bcf_hdr,
+			   const struct i2400m_bcf_hdr *bcf, size_t offset)
+{
+	int ret = 0;
+	struct device *dev = i2400m_dev(i2400m);
+	struct i2400m_bootrom_header *cmd, ack;
+	struct {
+		struct i2400m_bootrom_header cmd;
+		u8 cmd_pl[0];
+	} __packed *cmd_buf;
+	size_t signature_block_offset, signature_block_size;
+
+	d_fnstart(3, dev, "offset %zu\n", offset);
+	cmd = (void *) bcf + offset;
+	if (i2400m_boot_is_signed(i2400m) == 0) {
+		struct i2400m_bootrom_header jump_ack;
+		d_printf(1, dev, "unsecure boot, jumping to 0x%08x\n",
+			le32_to_cpu(cmd->target_addr));
+		cmd_buf = i2400m->bm_cmd_buf;
+		memcpy(&cmd_buf->cmd, cmd, sizeof(*cmd));
+		cmd = &cmd_buf->cmd;
+		/* now cmd points to the actual bootrom_header in cmd_buf */
+		i2400m_brh_set_opcode(cmd, I2400M_BRH_JUMP);
+		cmd->data_size = 0;
+		ret = i2400m_bm_cmd(i2400m, cmd, sizeof(*cmd),
+				    &jump_ack, sizeof(jump_ack), 0);
+	} else {
+		d_printf(1, dev, "secure boot, jumping to 0x%08x\n",
+			 le32_to_cpu(cmd->target_addr));
+		cmd_buf = i2400m->bm_cmd_buf;
+		memcpy(&cmd_buf->cmd, cmd, sizeof(*cmd));
+		signature_block_offset =
+			sizeof(*bcf_hdr)
+			+ le32_to_cpu(bcf_hdr->key_size) * sizeof(u32)
+			+ le32_to_cpu(bcf_hdr->exponent_size) * sizeof(u32);
+		signature_block_size =
+			le32_to_cpu(bcf_hdr->modulus_size) * sizeof(u32);
+		memcpy(cmd_buf->cmd_pl,
+		       (void *) bcf_hdr + signature_block_offset,
+		       signature_block_size);
+		ret = i2400m_bm_cmd(i2400m, &cmd_buf->cmd,
+				    sizeof(cmd_buf->cmd) + signature_block_size,
+				    &ack, sizeof(ack), I2400M_BM_CMD_RAW);
+	}
+	d_fnend(3, dev, "returning %d\n", ret);
+	return ret;
+}
+
+
+/**
+ * i2400m_bootrom_init - Reboots a powered device into boot mode
+ *
+ * @i2400m: device descriptor
+ * @flags:
+ *      I2400M_BRI_SOFT: a reboot barker has been seen
+ *          already, so don't wait for it.
+ *
+ *      I2400M_BRI_NO_REBOOT: Don't send a reboot command, but wait
+ *          for a reboot barker notification. This is a one shot; if
+ *          the state machine needs to send a reboot command it will.
+ *
+ * Returns:
+ *
+ *     < 0 errno code on error, 0 if ok.
+ *
+ * Description:
+ *
+ * Tries hard enough to put the device in boot-mode. There are two
+ * main phases to this:
+ *
+ * a. (1) send a reboot command and (2) get a reboot barker
+ *
+ * b. (1) echo/ack the reboot sending the reboot barker back and (2)
+ *        getting an ack barker in return
+ *
+ * We want to skip (a) in some cases [soft]. The state machine is
+ * horrible, but it is basically: on each phase, send what has to be
+ * sent (if any), wait for the answer and act on the answer. We might
+ * have to backtrack and retry, so we keep a max tries counter for
+ * that.
+ *
+ * It sucks because we don't know ahead of time which is going to be
+ * the reboot barker (the device might send different ones depending
+ * on its EEPROM config) and once the device reboots and waits for the
+ * echo/ack reboot barker being sent back, it doesn't understand
+ * anything else. So we can be left at the point where we don't know
+ * what to send to it -- cold reset and bus reset seem to have little
+ * effect. So the function iterates (in this case) through all the
+ * known barkers and tries them all until an ACK is
+ * received. Otherwise, it gives up.
+ *
+ * If we get a timeout after sending a warm reset, we do it again.
+ */
+int i2400m_bootrom_init(struct i2400m *i2400m, enum i2400m_bri flags)
+{
+	int result;
+	struct device *dev = i2400m_dev(i2400m);
+	struct i2400m_bootrom_header *cmd;
+	struct i2400m_bootrom_header ack;
+	int count = i2400m->bus_bm_retries;
+	int ack_timeout_cnt = 1;
+	unsigned i;
+
+	BUILD_BUG_ON(sizeof(*cmd) != sizeof(i2400m_barker_db[0].data));
+	BUILD_BUG_ON(sizeof(ack) != sizeof(i2400m_ACK_BARKER));
+
+	d_fnstart(4, dev, "(i2400m %p flags 0x%08x)\n", i2400m, flags);
+	result = -ENOMEM;
+	cmd = i2400m->bm_cmd_buf;
+	if (flags & I2400M_BRI_SOFT)
+		goto do_reboot_ack;
+do_reboot:
+	ack_timeout_cnt = 1;
+	if (--count < 0)
+		goto error_timeout;
+	d_printf(4, dev, "device reboot: reboot command [%d # left]\n",
+		 count);
+	if ((flags & I2400M_BRI_NO_REBOOT) == 0)
+		i2400m_reset(i2400m, I2400M_RT_WARM);
+	result = i2400m_bm_cmd(i2400m, NULL, 0, &ack, sizeof(ack),
+			       I2400M_BM_CMD_RAW);
+	flags &= ~I2400M_BRI_NO_REBOOT;
+	switch (result) {
+	case -ERESTARTSYS:
+		/*
+		 * at this point, i2400m_bm_cmd(), through
+		 * __i2400m_bm_ack_process(), has updated
+		 * i2400m->barker and we are good to go.
+		 */
+		d_printf(4, dev, "device reboot: got reboot barker\n");
+		break;
+	case -EISCONN:	/* we don't know how it got here...but we follow it */
+		d_printf(4, dev, "device reboot: got ack barker - whatever\n");
+		goto do_reboot;
+	case -ETIMEDOUT:
+		/*
+		 * Device has timed out, we might be in boot mode
+		 * already and expecting an ack; if we don't know what
+		 * the barker is, we just send them all. Cold reset
+		 * and bus reset don't work. Beats me.
+		 */
+		if (i2400m->barker != NULL) {
+			dev_err(dev, "device boot: reboot barker timed out, "
+				"trying (set) %08x echo/ack\n",
+				le32_to_cpu(i2400m->barker->data[0]));
+			goto do_reboot_ack;
+		}
+		for (i = 0; i < i2400m_barker_db_used; i++) {
+			struct i2400m_barker_db *barker = &i2400m_barker_db[i];
+			memcpy(cmd, barker->data, sizeof(barker->data));
+			result = i2400m_bm_cmd(i2400m, cmd, sizeof(*cmd),
+					       &ack, sizeof(ack),
+					       I2400M_BM_CMD_RAW);
+			if (result == -EISCONN) {
+				dev_warn(dev, "device boot: got ack barker "
+					 "after sending echo/ack barker "
+					 "#%d/%08x; rebooting j.i.c.\n",
+					 i, le32_to_cpu(barker->data[0]));
+				flags &= ~I2400M_BRI_NO_REBOOT;
+				goto do_reboot;
+			}
+		}
+		dev_err(dev, "device boot: tried all the echo/acks, could "
+			"not get device to respond; giving up");
+		result = -ESHUTDOWN;
+	case -EPROTO:
+	case -ESHUTDOWN:	/* dev is gone */
+	case -EINTR:		/* user cancelled */
+		goto error_dev_gone;
+	default:
+		dev_err(dev, "device reboot: error %d while waiting "
+			"for reboot barker - rebooting\n", result);
+		d_dump(1, dev, &ack, result);
+		goto do_reboot;
+	}
+	/* At this point we ack back with 4 REBOOT barkers and expect
+	 * 4 ACK barkers. This is ugly, as we send a raw command --
+	 * hence the cast. _bm_cmd() will catch the reboot ack
+	 * notification and report it as -EISCONN. */
+do_reboot_ack:
+	d_printf(4, dev, "device reboot ack: sending ack [%d # left]\n", count);
+	memcpy(cmd, i2400m->barker->data, sizeof(i2400m->barker->data));
+	result = i2400m_bm_cmd(i2400m, cmd, sizeof(*cmd),
+			       &ack, sizeof(ack), I2400M_BM_CMD_RAW);
+	switch (result) {
+	case -ERESTARTSYS:
+		d_printf(4, dev, "reboot ack: got reboot barker - retrying\n");
+		if (--count < 0)
+			goto error_timeout;
+		goto do_reboot_ack;
+	case -EISCONN:
+		d_printf(4, dev, "reboot ack: got ack barker - good\n");
+		break;
+	case -ETIMEDOUT:	/* no response, maybe it is the other type? */
+		if (ack_timeout_cnt-- < 0) {
+			d_printf(4, dev, "reboot ack timedout: retrying\n");
+			goto do_reboot_ack;
+		} else {
+			dev_err(dev, "reboot ack timedout too long: "
+				"trying reboot\n");
+			goto do_reboot;
+		}
+		break;
+	case -EPROTO:
+	case -ESHUTDOWN:	/* dev is gone */
+		goto error_dev_gone;
+	default:
+		dev_err(dev, "device reboot ack: error %d while waiting for "
+			"reboot ack barker - rebooting\n", result);
+		goto do_reboot;
+	}
+	d_printf(2, dev, "device reboot ack: got ack barker - boot done\n");
+	result = 0;
+exit_timeout:
+error_dev_gone:
+	d_fnend(4, dev, "(i2400m %p flags 0x%08x) = %d\n",
+		i2400m, flags, result);
+	return result;
+
+error_timeout:
+	dev_err(dev, "Timed out waiting for reboot ack\n");
+	result = -ETIMEDOUT;
+	goto exit_timeout;
+}
+
+
+/*
+ * Read the MAC addr
+ *
+ * The position this function reads is fixed in device memory and
+ * always available, even without firmware.
+ *
+ * Note we specify we want to read only six bytes, but provide space
+ * for 16, as we always get it rounded up.
+ */
+int i2400m_read_mac_addr(struct i2400m *i2400m)
+{
+	int result;
+	struct device *dev = i2400m_dev(i2400m);
+	struct net_device *net_dev = i2400m->wimax_dev.net_dev;
+	struct i2400m_bootrom_header *cmd;
+	struct {
+		struct i2400m_bootrom_header ack;
+		u8 ack_pl[16];
+	} __packed ack_buf;
+
+	d_fnstart(5, dev, "(i2400m %p)\n", i2400m);
+	cmd = i2400m->bm_cmd_buf;
+	cmd->command = i2400m_brh_command(I2400M_BRH_READ, 0, 1);
+	cmd->target_addr = cpu_to_le32(0x00203fe8);
+	cmd->data_size = cpu_to_le32(6);
+	result = i2400m_bm_cmd(i2400m, cmd, sizeof(*cmd),
+			       &ack_buf.ack, sizeof(ack_buf), 0);
+	if (result < 0) {
+		dev_err(dev, "BM: read mac addr failed: %d\n", result);
+		goto error_read_mac;
+	}
+	d_printf(2, dev, "mac addr is %pM\n", ack_buf.ack_pl);
+	if (i2400m->bus_bm_mac_addr_impaired == 1) {
+		ack_buf.ack_pl[0] = 0x00;
+		ack_buf.ack_pl[1] = 0x16;
+		ack_buf.ack_pl[2] = 0xd3;
+		get_random_bytes(&ack_buf.ack_pl[3], 3);
+		dev_err(dev, "BM is MAC addr impaired, faking MAC addr to "
+			"mac addr is %pM\n", ack_buf.ack_pl);
+		result = 0;
+	}
+	net_dev->addr_len = ETH_ALEN;
+	memcpy(net_dev->dev_addr, ack_buf.ack_pl, ETH_ALEN);
+error_read_mac:
+	d_fnend(5, dev, "(i2400m %p) = %d\n", i2400m, result);
+	return result;
+}
+
+
+/*
+ * Initialize a non signed boot
+ *
+ * This implies sending some magic values to the device's memory. Note
+ * we convert the values to little endian in the same array
+ * declaration.
+ */
+static
+int i2400m_dnload_init_nonsigned(struct i2400m *i2400m)
+{
+	unsigned i = 0;
+	int ret = 0;
+	struct device *dev = i2400m_dev(i2400m);
+	d_fnstart(5, dev, "(i2400m %p)\n", i2400m);
+	if (i2400m->bus_bm_pokes_table) {
+		while (i2400m->bus_bm_pokes_table[i].address) {
+			ret = i2400m_download_chunk(
+				i2400m,
+				&i2400m->bus_bm_pokes_table[i].data,
+				sizeof(i2400m->bus_bm_pokes_table[i].data),
+				i2400m->bus_bm_pokes_table[i].address, 1, 1);
+			if (ret < 0)
+				break;
+			i++;
+		}
+	}
+	d_fnend(5, dev, "(i2400m %p) = %d\n", i2400m, ret);
+	return ret;
+}
+
+
+/*
+ * Initialize the signed boot process
+ *
+ * @i2400m: device descriptor
+ *
+ * @bcf_hdr: pointer to the firmware header; assumes it is fully in
+ *     memory (it has gone through basic validation).
+ *
+ * Returns: 0 if ok, < 0 errno code on error, -ERESTARTSYS if the hw
+ *     rebooted.
+ *
+ * This writes the firmware BCF header to the device using the
+ * HASH_PAYLOAD_ONLY command.
+ */
+static
+int i2400m_dnload_init_signed(struct i2400m *i2400m,
+			      const struct i2400m_bcf_hdr *bcf_hdr)
+{
+	int ret;
+	struct device *dev = i2400m_dev(i2400m);
+	struct {
+		struct i2400m_bootrom_header cmd;
+		struct i2400m_bcf_hdr cmd_pl;
+	} __packed *cmd_buf;
+	struct i2400m_bootrom_header ack;
+
+	d_fnstart(5, dev, "(i2400m %p bcf_hdr %p)\n", i2400m, bcf_hdr);
+	cmd_buf = i2400m->bm_cmd_buf;
+	cmd_buf->cmd.command =
+		i2400m_brh_command(I2400M_BRH_HASH_PAYLOAD_ONLY, 0, 0);
+	cmd_buf->cmd.target_addr = 0;
+	cmd_buf->cmd.data_size = cpu_to_le32(sizeof(cmd_buf->cmd_pl));
+	memcpy(&cmd_buf->cmd_pl, bcf_hdr, sizeof(*bcf_hdr));
+	ret = i2400m_bm_cmd(i2400m, &cmd_buf->cmd, sizeof(*cmd_buf),
+			    &ack, sizeof(ack), 0);
+	if (ret >= 0)
+		ret = 0;
+	d_fnend(5, dev, "(i2400m %p bcf_hdr %p) = %d\n", i2400m, bcf_hdr, ret);
+	return ret;
+}
+
+
+/*
+ * Initialize the firmware download at the device size
+ *
+ * Multiplex to the one that matters based on the device's mode
+ * (signed or non-signed).
+ */
+static
+int i2400m_dnload_init(struct i2400m *i2400m,
+		       const struct i2400m_bcf_hdr *bcf_hdr)
+{
+	int result;
+	struct device *dev = i2400m_dev(i2400m);
+
+	if (i2400m_boot_is_signed(i2400m)) {
+		d_printf(1, dev, "signed boot\n");
+		result = i2400m_dnload_init_signed(i2400m, bcf_hdr);
+		if (result == -ERESTARTSYS)
+			return result;
+		if (result < 0)
+			dev_err(dev, "firmware %s: signed boot download "
+				"initialization failed: %d\n",
+				i2400m->fw_name, result);
+	} else {
+		/* non-signed boot process without pokes */
+		d_printf(1, dev, "non-signed boot\n");
+		result = i2400m_dnload_init_nonsigned(i2400m);
+		if (result == -ERESTARTSYS)
+			return result;
+		if (result < 0)
+			dev_err(dev, "firmware %s: non-signed download "
+				"initialization failed: %d\n",
+				i2400m->fw_name, result);
+	}
+	return result;
+}
+
+
+/*
+ * Run consistency tests on the firmware file and load up headers
+ *
+ * Check for the firmware being made for the i2400m device,
+ * etc...These checks are mostly informative, as the device will make
+ * them too; but the driver's response is more informative on what
+ * went wrong.
+ *
+ * This will also look at all the headers present on the firmware
+ * file, and update i2400m->fw_bcf_hdr to point to them.
+ */
+static
+int i2400m_fw_hdr_check(struct i2400m *i2400m,
+			const struct i2400m_bcf_hdr *bcf_hdr,
+			size_t index, size_t offset)
+{
+	struct device *dev = i2400m_dev(i2400m);
+
+	unsigned module_type, header_len, major_version, minor_version,
+		module_id, module_vendor, date, size;
+
+	module_type = le32_to_cpu(bcf_hdr->module_type);
+	header_len = sizeof(u32) * le32_to_cpu(bcf_hdr->header_len);
+	major_version = (le32_to_cpu(bcf_hdr->header_version) & 0xffff0000)
+		>> 16;
+	minor_version = le32_to_cpu(bcf_hdr->header_version) & 0x0000ffff;
+	module_id = le32_to_cpu(bcf_hdr->module_id);
+	module_vendor = le32_to_cpu(bcf_hdr->module_vendor);
+	date = le32_to_cpu(bcf_hdr->date);
+	size = sizeof(u32) * le32_to_cpu(bcf_hdr->size);
+
+	d_printf(1, dev, "firmware %s #%zd@%08zx: BCF header "
+		 "type:vendor:id 0x%x:%x:%x v%u.%u (%u/%u B) built %08x\n",
+		 i2400m->fw_name, index, offset,
+		 module_type, module_vendor, module_id,
+		 major_version, minor_version, header_len, size, date);
+
+	/* Hard errors */
+	if (major_version != 1) {
+		dev_err(dev, "firmware %s #%zd@%08zx: major header version "
+			"v%u.%u not supported\n",
+			i2400m->fw_name, index, offset,
+			major_version, minor_version);
+		return -EBADF;
+	}
+
+	if (module_type != 6) {		/* built for the right hardware? */
+		dev_err(dev, "firmware %s #%zd@%08zx: unexpected module "
+			"type 0x%x; aborting\n",
+			i2400m->fw_name, index, offset,
+			module_type);
+		return -EBADF;
+	}
+
+	if (module_vendor != 0x8086) {
+		dev_err(dev, "firmware %s #%zd@%08zx: unexpected module "
+			"vendor 0x%x; aborting\n",
+			i2400m->fw_name, index, offset, module_vendor);
+		return -EBADF;
+	}
+
+	if (date < 0x20080300)
+		dev_warn(dev, "firmware %s #%zd@%08zx: build date %08x "
+			 "too old; unsupported\n",
+			 i2400m->fw_name, index, offset, date);
+	return 0;
+}
+
+
+/*
+ * Run consistency tests on the firmware file and load up headers
+ *
+ * Check for the firmware being made for the i2400m device,
+ * etc...These checks are mostly informative, as the device will make
+ * them too; but the driver's response is more informative on what
+ * went wrong.
+ *
+ * This will also look at all the headers present on the firmware
+ * file, and update i2400m->fw_hdrs to point to them.
+ */
+static
+int i2400m_fw_check(struct i2400m *i2400m, const void *bcf, size_t bcf_size)
+{
+	int result;
+	struct device *dev = i2400m_dev(i2400m);
+	size_t headers = 0;
+	const struct i2400m_bcf_hdr *bcf_hdr;
+	const void *itr, *next, *top;
+	size_t slots = 0, used_slots = 0;
+
+	for (itr = bcf, top = itr + bcf_size;
+	     itr < top;
+	     headers++, itr = next) {
+		size_t leftover, offset, header_len, size;
+
+		leftover = top - itr;
+		offset = itr - bcf;
+		if (leftover <= sizeof(*bcf_hdr)) {
+			dev_err(dev, "firmware %s: %zu B left at @%zx, "
+				"not enough for BCF header\n",
+				i2400m->fw_name, leftover, offset);
+			break;
+		}
+		bcf_hdr = itr;
+		/* Only the first header is supposed to be followed by
+		 * payload */
+		header_len = sizeof(u32) * le32_to_cpu(bcf_hdr->header_len);
+		size = sizeof(u32) * le32_to_cpu(bcf_hdr->size);
+		if (headers == 0)
+			next = itr + size;
+		else
+			next = itr + header_len;
+
+		result = i2400m_fw_hdr_check(i2400m, bcf_hdr, headers, offset);
+		if (result < 0)
+			continue;
+		if (used_slots + 1 >= slots) {
+			/* +1 -> we need to account for the one we'll
+			 * occupy and at least an extra one for
+			 * always being NULL */
+			result = i2400m_zrealloc_2x(
+				(void **) &i2400m->fw_hdrs, &slots,
+				sizeof(i2400m->fw_hdrs[0]),
+				GFP_KERNEL);
+			if (result < 0)
+				goto error_zrealloc;
+		}
+		i2400m->fw_hdrs[used_slots] = bcf_hdr;
+		used_slots++;
+	}
+	if (headers == 0) {
+		dev_err(dev, "firmware %s: no usable headers found\n",
+			i2400m->fw_name);
+		result = -EBADF;
+	} else
+		result = 0;
+error_zrealloc:
+	return result;
+}
+
+
+/*
+ * Match a barker to a BCF header module ID
+ *
+ * The device sends a barker which tells the firmware loader which
+ * header in the BCF file has to be used. This does the matching.
+ */
+static
+unsigned i2400m_bcf_hdr_match(struct i2400m *i2400m,
+			      const struct i2400m_bcf_hdr *bcf_hdr)
+{
+	u32 barker = le32_to_cpu(i2400m->barker->data[0])
+		& 0x7fffffff;
+	u32 module_id = le32_to_cpu(bcf_hdr->module_id)
+		& 0x7fffffff;	/* high bit used for something else */
+
+	/* special case for 5x50 */
+	if (barker == I2400M_SBOOT_BARKER && module_id == 0)
+		return 1;
+	if (module_id == barker)
+		return 1;
+	return 0;
+}
+
+static
+const struct i2400m_bcf_hdr *i2400m_bcf_hdr_find(struct i2400m *i2400m)
+{
+	struct device *dev = i2400m_dev(i2400m);
+	const struct i2400m_bcf_hdr **bcf_itr, *bcf_hdr;
+	unsigned i = 0;
+	u32 barker = le32_to_cpu(i2400m->barker->data[0]);
+
+	d_printf(2, dev, "finding BCF header for barker %08x\n", barker);
+	if (barker == I2400M_NBOOT_BARKER) {
+		bcf_hdr = i2400m->fw_hdrs[0];
+		d_printf(1, dev, "using BCF header #%u/%08x for non-signed "
+			 "barker\n", 0, le32_to_cpu(bcf_hdr->module_id));
+		return bcf_hdr;
+	}
+	for (bcf_itr = i2400m->fw_hdrs; *bcf_itr != NULL; bcf_itr++, i++) {
+		bcf_hdr = *bcf_itr;
+		if (i2400m_bcf_hdr_match(i2400m, bcf_hdr)) {
+			d_printf(1, dev, "hit on BCF hdr #%u/%08x\n",
+				 i, le32_to_cpu(bcf_hdr->module_id));
+			return bcf_hdr;
+		} else
+			d_printf(1, dev, "miss on BCF hdr #%u/%08x\n",
+				 i, le32_to_cpu(bcf_hdr->module_id));
+	}
+	dev_err(dev, "cannot find a matching BCF header for barker %08x\n",
+		barker);
+	return NULL;
+}
+
+
+/*
+ * Download the firmware to the device
+ *
+ * @i2400m: device descriptor
+ * @bcf: pointer to loaded (and minimally verified for consistency)
+ *    firmware
+ * @bcf_size: size of the @bcf buffer (header plus payloads)
+ *
+ * The process for doing this is described in this file's header.
+ *
+ * Note we only reinitialize boot-mode if the flags say so. Some hw
+ * iterations need it, some don't. In any case, if we loop, we always
+ * need to reinitialize the boot room, hence the flags modification.
+ */
+static
+int i2400m_fw_dnload(struct i2400m *i2400m, const struct i2400m_bcf_hdr *bcf,
+		     size_t fw_size, enum i2400m_bri flags)
+{
+	int ret = 0;
+	struct device *dev = i2400m_dev(i2400m);
+	int count = i2400m->bus_bm_retries;
+	const struct i2400m_bcf_hdr *bcf_hdr;
+	size_t bcf_size;
+
+	d_fnstart(5, dev, "(i2400m %p bcf %p fw size %zu)\n",
+		  i2400m, bcf, fw_size);
+	i2400m->boot_mode = 1;
+	wmb();		/* Make sure other readers see it */
+hw_reboot:
+	if (count-- == 0) {
+		ret = -ERESTARTSYS;
+		dev_err(dev, "device rebooted too many times, aborting\n");
+		goto error_too_many_reboots;
+	}
+	if (flags & I2400M_BRI_MAC_REINIT) {
+		ret = i2400m_bootrom_init(i2400m, flags);
+		if (ret < 0) {
+			dev_err(dev, "bootrom init failed: %d\n", ret);
+			goto error_bootrom_init;
+		}
+	}
+	flags |= I2400M_BRI_MAC_REINIT;
+
+	/*
+	 * Initialize the download, push the bytes to the device and
+	 * then jump to the new firmware. Note @ret is passed with the
+	 * offset of the jump instruction to _dnload_finalize()
+	 *
+	 * Note we need to use the BCF header in the firmware image
+	 * that matches the barker that the device sent when it
+	 * rebooted, so it has to be passed along.
+	 */
+	ret = -EBADF;
+	bcf_hdr = i2400m_bcf_hdr_find(i2400m);
+	if (bcf_hdr == NULL)
+		goto error_bcf_hdr_find;
+
+	ret = i2400m_dnload_init(i2400m, bcf_hdr);
+	if (ret == -ERESTARTSYS)
+		goto error_dev_rebooted;
+	if (ret < 0)
+		goto error_dnload_init;
+
+	/*
+	 * bcf_size refers to one header size plus the fw sections size
+	 * indicated by the header,ie. if there are other extended headers
+	 * at the tail, they are not counted
+	 */
+	bcf_size = sizeof(u32) * le32_to_cpu(bcf_hdr->size);
+	ret = i2400m_dnload_bcf(i2400m, bcf, bcf_size);
+	if (ret == -ERESTARTSYS)
+		goto error_dev_rebooted;
+	if (ret < 0) {
+		dev_err(dev, "fw %s: download failed: %d\n",
+			i2400m->fw_name, ret);
+		goto error_dnload_bcf;
+	}
+
+	ret = i2400m_dnload_finalize(i2400m, bcf_hdr, bcf, ret);
+	if (ret == -ERESTARTSYS)
+		goto error_dev_rebooted;
+	if (ret < 0) {
+		dev_err(dev, "fw %s: "
+			"download finalization failed: %d\n",
+			i2400m->fw_name, ret);
+		goto error_dnload_finalize;
+	}
+
+	d_printf(2, dev, "fw %s successfully uploaded\n",
+		 i2400m->fw_name);
+	i2400m->boot_mode = 0;
+	wmb();		/* Make sure i2400m_msg_to_dev() sees boot_mode */
+error_dnload_finalize:
+error_dnload_bcf:
+error_dnload_init:
+error_bcf_hdr_find:
+error_bootrom_init:
+error_too_many_reboots:
+	d_fnend(5, dev, "(i2400m %p bcf %p size %zu) = %d\n",
+		i2400m, bcf, fw_size, ret);
+	return ret;
+
+error_dev_rebooted:
+	dev_err(dev, "device rebooted, %d tries left\n", count);
+	/* we got the notification already, no need to wait for it again */
+	flags |= I2400M_BRI_SOFT;
+	goto hw_reboot;
+}
+
+static
+int i2400m_fw_bootstrap(struct i2400m *i2400m, const struct firmware *fw,
+			enum i2400m_bri flags)
+{
+	int ret;
+	struct device *dev = i2400m_dev(i2400m);
+	const struct i2400m_bcf_hdr *bcf;	/* Firmware data */
+
+	d_fnstart(5, dev, "(i2400m %p)\n", i2400m);
+	bcf = (void *) fw->data;
+	ret = i2400m_fw_check(i2400m, bcf, fw->size);
+	if (ret >= 0)
+		ret = i2400m_fw_dnload(i2400m, bcf, fw->size, flags);
+	if (ret < 0)
+		dev_err(dev, "%s: cannot use: %d, skipping\n",
+			i2400m->fw_name, ret);
+	kfree(i2400m->fw_hdrs);
+	i2400m->fw_hdrs = NULL;
+	d_fnend(5, dev, "(i2400m %p) = %d\n", i2400m, ret);
+	return ret;
+}
+
+
+/* Refcounted container for firmware data */
+struct i2400m_fw {
+	struct kref kref;
+	const struct firmware *fw;
+};
+
+
+static
+void i2400m_fw_destroy(struct kref *kref)
+{
+	struct i2400m_fw *i2400m_fw =
+		container_of(kref, struct i2400m_fw, kref);
+	release_firmware(i2400m_fw->fw);
+	kfree(i2400m_fw);
+}
+
+
+static
+struct i2400m_fw *i2400m_fw_get(struct i2400m_fw *i2400m_fw)
+{
+	if (i2400m_fw != NULL && i2400m_fw != (void *) ~0)
+		kref_get(&i2400m_fw->kref);
+	return i2400m_fw;
+}
+
+
+static
+void i2400m_fw_put(struct i2400m_fw *i2400m_fw)
+{
+	kref_put(&i2400m_fw->kref, i2400m_fw_destroy);
+}
+
+
+/**
+ * i2400m_dev_bootstrap - Bring the device to a known state and upload firmware
+ *
+ * @i2400m: device descriptor
+ *
+ * Returns: >= 0 if ok, < 0 errno code on error.
+ *
+ * This sets up the firmware upload environment, loads the firmware
+ * file from disk, verifies and then calls the firmware upload process
+ * per se.
+ *
+ * Can be called either from probe, or after a warm reset.  Can not be
+ * called from within an interrupt.  All the flow in this code is
+ * single-threade; all I/Os are synchronous.
+ */
+int i2400m_dev_bootstrap(struct i2400m *i2400m, enum i2400m_bri flags)
+{
+	int ret, itr;
+	struct device *dev = i2400m_dev(i2400m);
+	struct i2400m_fw *i2400m_fw;
+	const struct firmware *fw;
+	const char *fw_name;
+
+	d_fnstart(5, dev, "(i2400m %p)\n", i2400m);
+
+	ret = -ENODEV;
+	spin_lock(&i2400m->rx_lock);
+	i2400m_fw = i2400m_fw_get(i2400m->fw_cached);
+	spin_unlock(&i2400m->rx_lock);
+	if (i2400m_fw == (void *) ~0) {
+		dev_err(dev, "can't load firmware now!");
+		goto out;
+	} else if (i2400m_fw != NULL) {
+		dev_info(dev, "firmware %s: loading from cache\n",
+			 i2400m->fw_name);
+		ret = i2400m_fw_bootstrap(i2400m, i2400m_fw->fw, flags);
+		i2400m_fw_put(i2400m_fw);
+		goto out;
+	}
+
+	/* Load firmware files to memory. */
+	for (itr = 0, ret = -ENOENT; ; itr++) {
+		fw_name = i2400m->bus_fw_names[itr];
+		if (fw_name == NULL) {
+			dev_err(dev, "Could not find a usable firmware image\n");
+			break;
+		}
+		d_printf(1, dev, "trying firmware %s (%d)\n", fw_name, itr);
+		ret = request_firmware(&fw, fw_name, dev);
+		if (ret < 0) {
+			dev_err(dev, "fw %s: cannot load file: %d\n",
+				fw_name, ret);
+			continue;
+		}
+		i2400m->fw_name = fw_name;
+		ret = i2400m_fw_bootstrap(i2400m, fw, flags);
+		release_firmware(fw);
+		if (ret >= 0)	/* firmware loaded successfully */
+			break;
+		i2400m->fw_name = NULL;
+	}
+out:
+	d_fnend(5, dev, "(i2400m %p) = %d\n", i2400m, ret);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(i2400m_dev_bootstrap);
+
+
+void i2400m_fw_cache(struct i2400m *i2400m)
+{
+	int result;
+	struct i2400m_fw *i2400m_fw;
+	struct device *dev = i2400m_dev(i2400m);
+
+	/* if there is anything there, free it -- now, this'd be weird */
+	spin_lock(&i2400m->rx_lock);
+	i2400m_fw = i2400m->fw_cached;
+	spin_unlock(&i2400m->rx_lock);
+	if (i2400m_fw != NULL && i2400m_fw != (void *) ~0) {
+		i2400m_fw_put(i2400m_fw);
+		WARN(1, "%s:%u: still cached fw still present?\n",
+		     __func__, __LINE__);
+	}
+
+	if (i2400m->fw_name == NULL) {
+		dev_err(dev, "firmware n/a: can't cache\n");
+		i2400m_fw = (void *) ~0;
+		goto out;
+	}
+
+	i2400m_fw = kzalloc(sizeof(*i2400m_fw), GFP_ATOMIC);
+	if (i2400m_fw == NULL)
+		goto out;
+	kref_init(&i2400m_fw->kref);
+	result = request_firmware(&i2400m_fw->fw, i2400m->fw_name, dev);
+	if (result < 0) {
+		dev_err(dev, "firmware %s: failed to cache: %d\n",
+			i2400m->fw_name, result);
+		kfree(i2400m_fw);
+		i2400m_fw = (void *) ~0;
+	} else
+		dev_info(dev, "firmware %s: cached\n", i2400m->fw_name);
+out:
+	spin_lock(&i2400m->rx_lock);
+	i2400m->fw_cached = i2400m_fw;
+	spin_unlock(&i2400m->rx_lock);
+}
+
+
+void i2400m_fw_uncache(struct i2400m *i2400m)
+{
+	struct i2400m_fw *i2400m_fw;
+
+	spin_lock(&i2400m->rx_lock);
+	i2400m_fw = i2400m->fw_cached;
+	i2400m->fw_cached = NULL;
+	spin_unlock(&i2400m->rx_lock);
+
+	if (i2400m_fw != NULL && i2400m_fw != (void *) ~0)
+		i2400m_fw_put(i2400m_fw);
+}
+
diff --git a/drivers/staging/wimax/i2400m/i2400m-usb.h b/drivers/staging/wimax/i2400m/i2400m-usb.h
new file mode 100644
index 000000000000..eff4f464a23e
--- /dev/null
+++ b/drivers/staging/wimax/i2400m/i2400m-usb.h
@@ -0,0 +1,275 @@
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * USB-specific i2400m driver definitions
+ *
+ *
+ * Copyright (C) 2007-2008 Intel Corporation. All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *
+ * Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ * Yanir Lubetkin <yanirx.lubetkin@intel.com>
+ *  - Initial implementation
+ *
+ *
+ * This driver implements the bus-specific part of the i2400m for
+ * USB. Check i2400m.h for a generic driver description.
+ *
+ * ARCHITECTURE
+ *
+ * This driver listens to notifications sent from the notification
+ * endpoint (in usb-notif.c); when data is ready to read, the code in
+ * there schedules a read from the device (usb-rx.c) and then passes
+ * the data to the generic RX code (rx.c).
+ *
+ * When the generic driver needs to send data (network or control), it
+ * queues up in the TX FIFO (tx.c) and that will notify the driver
+ * through the i2400m->bus_tx_kick() callback
+ * (usb-tx.c:i2400mu_bus_tx_kick) which will send the items in the
+ * FIFO queue.
+ *
+ * This driver, as well, implements the USB-specific ops for the generic
+ * driver to be able to setup/teardown communication with the device
+ * [i2400m_bus_dev_start() and i2400m_bus_dev_stop()], reseting the
+ * device [i2400m_bus_reset()] and performing firmware upload
+ * [i2400m_bus_bm_cmd() and i2400_bus_bm_wait_for_ack()].
+ */
+
+#ifndef __I2400M_USB_H__
+#define __I2400M_USB_H__
+
+#include "i2400m.h"
+#include <linux/kthread.h>
+
+
+/*
+ * Error Density Count: cheapo error density (over time) counter
+ *
+ * Originally by Reinette Chatre <reinette.chatre@intel.com>
+ *
+ * Embed an 'struct edc' somewhere. Each time there is a soft or
+ * retryable error, call edc_inc() and check if the error top
+ * watermark has been reached.
+ */
+enum {
+	EDC_MAX_ERRORS = 10,
+	EDC_ERROR_TIMEFRAME = HZ,
+};
+
+/* error density counter */
+struct edc {
+	unsigned long timestart;
+	u16 errorcount;
+};
+
+struct i2400m_endpoint_cfg {
+	unsigned char bulk_out;
+	unsigned char notification;
+	unsigned char reset_cold;
+	unsigned char bulk_in;
+};
+
+static inline void edc_init(struct edc *edc)
+{
+	edc->timestart = jiffies;
+}
+
+/**
+ * edc_inc - report a soft error and check if we are over the watermark
+ *
+ * @edc: pointer to error density counter.
+ * @max_err: maximum number of errors we can accept over the timeframe
+ * @timeframe: length of the timeframe (in jiffies).
+ *
+ * Returns: !0 1 if maximum acceptable errors per timeframe has been
+ *     exceeded. 0 otherwise.
+ *
+ * This is way to determine if the number of acceptable errors per time
+ * period has been exceeded. It is not accurate as there are cases in which
+ * this scheme will not work, for example if there are periodic occurrences
+ * of errors that straddle updates to the start time. This scheme is
+ * sufficient for our usage.
+ *
+ * To use, embed a 'struct edc' somewhere, initialize it with
+ * edc_init() and when an error hits:
+ *
+ * if (do_something_fails_with_a_soft_error) {
+ *        if (edc_inc(&my->edc, MAX_ERRORS, MAX_TIMEFRAME))
+ * 	           Ops, hard error, do something about it
+ *        else
+ *                 Retry or ignore, depending on whatever
+ * }
+ */
+static inline int edc_inc(struct edc *edc, u16 max_err, u16 timeframe)
+{
+	unsigned long now;
+
+	now = jiffies;
+	if (time_after(now, edc->timestart + timeframe)) {
+		edc->errorcount = 1;
+		edc->timestart = now;
+	} else if (++edc->errorcount > max_err) {
+		edc->errorcount = 0;
+		edc->timestart = now;
+		return 1;
+	}
+	return 0;
+}
+
+/* Host-Device interface for USB */
+enum {
+	I2400M_USB_BOOT_RETRIES = 3,
+	I2400MU_MAX_NOTIFICATION_LEN = 256,
+	I2400MU_BLK_SIZE = 16,
+	I2400MU_PL_SIZE_MAX = 0x3EFF,
+
+	/* Device IDs */
+	USB_DEVICE_ID_I6050 = 0x0186,
+	USB_DEVICE_ID_I6050_2 = 0x0188,
+	USB_DEVICE_ID_I6150 = 0x07d6,
+	USB_DEVICE_ID_I6150_2 = 0x07d7,
+	USB_DEVICE_ID_I6150_3 = 0x07d9,
+	USB_DEVICE_ID_I6250 = 0x0187,
+};
+
+
+/**
+ * struct i2400mu - descriptor for a USB connected i2400m
+ *
+ * @i2400m: bus-generic i2400m implementation; has to be first (see
+ *     it's documentation in i2400m.h).
+ *
+ * @usb_dev: pointer to our USB device
+ *
+ * @usb_iface: pointer to our USB interface
+ *
+ * @urb_edc: error density counter; used to keep a density-on-time tab
+ *     on how many soft (retryable or ignorable) errors we get. If we
+ *     go over the threshold, we consider the bus transport is failing
+ *     too much and reset.
+ *
+ * @notif_urb: URB for receiving notifications from the device.
+ *
+ * @tx_kthread: thread we use for data TX. We use a thread because in
+ *     order to do deep power saving and put the device to sleep, we
+ *     need to call usb_autopm_*() [blocking functions].
+ *
+ * @tx_wq: waitqueue for the TX kthread to sleep when there is no data
+ *     to be sent; when more data is available, it is woken up by
+ *     i2400mu_bus_tx_kick().
+ *
+ * @rx_kthread: thread we use for data RX. We use a thread because in
+ *     order to do deep power saving and put the device to sleep, we
+ *     need to call usb_autopm_*() [blocking functions].
+ *
+ * @rx_wq: waitqueue for the RX kthread to sleep when there is no data
+ *     to receive. When data is available, it is woken up by
+ *     usb-notif.c:i2400mu_notification_grok().
+ *
+ * @rx_pending_count: number of rx-data-ready notifications that were
+ *     still not handled by the RX kthread.
+ *
+ * @rx_size: current RX buffer size that is being used.
+ *
+ * @rx_size_acc: accumulator of the sizes of the previous read
+ *     transactions.
+ *
+ * @rx_size_cnt: number of read transactions accumulated in
+ *     @rx_size_acc.
+ *
+ * @do_autopm: disable(0)/enable(>0) calling the
+ *     usb_autopm_get/put_interface() barriers when executing
+ *     commands. See doc in i2400mu_suspend() for more information.
+ *
+ * @rx_size_auto_shrink: if true, the rx_size is shrunk
+ *     automatically based on the average size of the received
+ *     transactions. This allows the receive code to allocate smaller
+ *     chunks of memory and thus reduce pressure on the memory
+ *     allocator by not wasting so much space. By default it is
+ *     enabled.
+ *
+ * @debugfs_dentry: hookup for debugfs files.
+ *     These have to be in a separate directory, a child of
+ *     (wimax_dev->debugfs_dentry) so they can be removed when the
+ *     module unloads, as we don't keep each dentry.
+ */
+struct i2400mu {
+	struct i2400m i2400m;		/* FIRST! See doc */
+
+	struct usb_device *usb_dev;
+	struct usb_interface *usb_iface;
+	struct edc urb_edc;		/* Error density counter */
+	struct i2400m_endpoint_cfg endpoint_cfg;
+
+	struct urb *notif_urb;
+	struct task_struct *tx_kthread;
+	wait_queue_head_t tx_wq;
+
+	struct task_struct *rx_kthread;
+	wait_queue_head_t rx_wq;
+	atomic_t rx_pending_count;
+	size_t rx_size, rx_size_acc, rx_size_cnt;
+	atomic_t do_autopm;
+	u8 rx_size_auto_shrink;
+
+	struct dentry *debugfs_dentry;
+	unsigned i6050:1;	/* 1 if this is a 6050 based SKU */
+};
+
+
+static inline
+void i2400mu_init(struct i2400mu *i2400mu)
+{
+	i2400m_init(&i2400mu->i2400m);
+	edc_init(&i2400mu->urb_edc);
+	init_waitqueue_head(&i2400mu->tx_wq);
+	atomic_set(&i2400mu->rx_pending_count, 0);
+	init_waitqueue_head(&i2400mu->rx_wq);
+	i2400mu->rx_size = PAGE_SIZE - sizeof(struct skb_shared_info);
+	atomic_set(&i2400mu->do_autopm, 1);
+	i2400mu->rx_size_auto_shrink = 1;
+}
+
+int i2400mu_notification_setup(struct i2400mu *);
+void i2400mu_notification_release(struct i2400mu *);
+
+int i2400mu_rx_setup(struct i2400mu *);
+void i2400mu_rx_release(struct i2400mu *);
+void i2400mu_rx_kick(struct i2400mu *);
+
+int i2400mu_tx_setup(struct i2400mu *);
+void i2400mu_tx_release(struct i2400mu *);
+void i2400mu_bus_tx_kick(struct i2400m *);
+
+ssize_t i2400mu_bus_bm_cmd_send(struct i2400m *,
+				const struct i2400m_bootrom_header *, size_t,
+				int);
+ssize_t i2400mu_bus_bm_wait_for_ack(struct i2400m *,
+				    struct i2400m_bootrom_header *, size_t);
+#endif /* #ifndef __I2400M_USB_H__ */
diff --git a/drivers/staging/wimax/i2400m/i2400m.h b/drivers/staging/wimax/i2400m/i2400m.h
new file mode 100644
index 000000000000..de22cc6f2c5c
--- /dev/null
+++ b/drivers/staging/wimax/i2400m/i2400m.h
@@ -0,0 +1,970 @@
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * Declarations for bus-generic internal APIs
+ *
+ *
+ * Copyright (C) 2007-2008 Intel Corporation. All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *
+ * Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ * Yanir Lubetkin <yanirx.lubetkin@intel.com>
+ *  - Initial implementation
+ *
+ *
+ * GENERAL DRIVER ARCHITECTURE
+ *
+ * The i2400m driver is split in the following two major parts:
+ *
+ *  - bus specific driver
+ *  - bus generic driver (this part)
+ *
+ * The bus specific driver sets up stuff specific to the bus the
+ * device is connected to (USB, PCI, tam-tam...non-authoritative
+ * nor binding list) which is basically the device-model management
+ * (probe/disconnect, etc), moving data from device to kernel and
+ * back, doing the power saving details and reseting the device.
+ *
+ * For details on each bus-specific driver, see it's include file,
+ * i2400m-BUSNAME.h
+ *
+ * The bus-generic functionality break up is:
+ *
+ *  - Firmware upload: fw.c - takes care of uploading firmware to the
+ *        device. bus-specific driver just needs to provides a way to
+ *        execute boot-mode commands and to reset the device.
+ *
+ *  - RX handling: rx.c - receives data from the bus-specific code and
+ *        feeds it to the network or WiMAX stack or uses it to modify
+ *        the driver state. bus-specific driver only has to receive
+ *        frames and pass them to this module.
+ *
+ *  - TX handling: tx.c - manages the TX FIFO queue and provides means
+ *        for the bus-specific TX code to pull data from the FIFO
+ *        queue. bus-specific code just pulls frames from this module
+ *        to sends them to the device.
+ *
+ *  - netdev glue: netdev.c - interface with Linux networking
+ *        stack. Pass around data frames, and configure when the
+ *        device is up and running or shutdown (through ifconfig up /
+ *        down). Bus-generic only.
+ *
+ *  - control ops: control.c - implements various commands for
+ *        controlling the device. bus-generic only.
+ *
+ *  - device model glue: driver.c - implements helpers for the
+ *        device-model glue done by the bus-specific layer
+ *        (setup/release the driver resources), turning the device on
+ *        and off, handling the device reboots/resets and a few simple
+ *        WiMAX stack ops.
+ *
+ * Code is also broken up in linux-glue / device-glue.
+ *
+ * Linux glue contains functions that deal mostly with gluing with the
+ * rest of the Linux kernel.
+ *
+ * Device-glue are functions that deal mostly with the way the device
+ * does things and talk the device's language.
+ *
+ * device-glue code is licensed BSD so other open source OSes can take
+ * it to implement their drivers.
+ *
+ *
+ * APIs AND HEADER FILES
+ *
+ * This bus generic code exports three APIs:
+ *
+ *  - HDI (host-device interface) definitions common to all busses
+ *    (include/linux/wimax/i2400m.h); these can be also used by user
+ *    space code.
+ *  - internal API for the bus-generic code
+ *  - external API for the bus-specific drivers
+ *
+ *
+ * LIFE CYCLE:
+ *
+ * When the bus-specific driver probes, it allocates a network device
+ * with enough space for it's data structue, that must contain a
+ * &struct i2400m at the top.
+ *
+ * On probe, it needs to fill the i2400m members marked as [fill], as
+ * well as i2400m->wimax_dev.net_dev and call i2400m_setup(). The
+ * i2400m driver will only register with the WiMAX and network stacks;
+ * the only access done to the device is to read the MAC address so we
+ * can register a network device.
+ *
+ * The high-level call flow is:
+ *
+ * bus_probe()
+ *   i2400m_setup()
+ *     i2400m->bus_setup()
+ *     boot rom initialization / read mac addr
+ *     network / WiMAX stacks registration
+ *     i2400m_dev_start()
+ *       i2400m->bus_dev_start()
+ *       i2400m_dev_initialize()
+ *
+ * The reverse applies for a disconnect() call:
+ *
+ * bus_disconnect()
+ *   i2400m_release()
+ *     i2400m_dev_stop()
+ *       i2400m_dev_shutdown()
+ *       i2400m->bus_dev_stop()
+ *     network / WiMAX stack unregistration
+ *     i2400m->bus_release()
+ *
+ * At this point, control and data communications are possible.
+ *
+ * While the device is up, it might reset. The bus-specific driver has
+ * to catch that situation and call i2400m_dev_reset_handle() to deal
+ * with it (reset the internal driver structures and go back to square
+ * one).
+ */
+
+#ifndef __I2400M_H__
+#define __I2400M_H__
+
+#include <linux/usb.h>
+#include <linux/netdevice.h>
+#include <linux/completion.h>
+#include <linux/rwsem.h>
+#include <linux/atomic.h>
+#include "../net-wimax.h"
+#include "linux-wimax-i2400m.h"
+#include <asm/byteorder.h>
+
+enum {
+/* netdev interface */
+	/*
+	 * Out of NWG spec (R1_v1.2.2), 3.3.3 ASN Bearer Plane MTU Size
+	 *
+	 * The MTU is 1400 or less
+	 */
+	I2400M_MAX_MTU = 1400,
+};
+
+/* Misc constants */
+enum {
+	/* Size of the Boot Mode Command buffer */
+	I2400M_BM_CMD_BUF_SIZE = 16 * 1024,
+	I2400M_BM_ACK_BUF_SIZE = 256,
+};
+
+enum {
+	/* Maximum number of bus reset can be retried */
+	I2400M_BUS_RESET_RETRIES = 3,
+};
+
+/**
+ * struct i2400m_poke_table - Hardware poke table for the Intel 2400m
+ *
+ * This structure will be used to create a device specific poke table
+ * to put the device in a consistent state at boot time.
+ *
+ * @address: The device address to poke
+ *
+ * @data: The data value to poke to the device address
+ *
+ */
+struct i2400m_poke_table{
+	__le32 address;
+	__le32 data;
+};
+
+#define I2400M_FW_POKE(a, d) {		\
+	.address = cpu_to_le32(a),	\
+	.data = cpu_to_le32(d)		\
+}
+
+
+/**
+ * i2400m_reset_type - methods to reset a device
+ *
+ * @I2400M_RT_WARM: Reset without device disconnection, device handles
+ *     are kept valid but state is back to power on, with firmware
+ *     re-uploaded.
+ * @I2400M_RT_COLD: Tell the device to disconnect itself from the bus
+ *     and reconnect. Renders all device handles invalid.
+ * @I2400M_RT_BUS: Tells the bus to reset the device; last measure
+ *     used when both types above don't work.
+ */
+enum i2400m_reset_type {
+	I2400M_RT_WARM,	/* first measure */
+	I2400M_RT_COLD,	/* second measure */
+	I2400M_RT_BUS,	/* call in artillery */
+};
+
+struct i2400m_reset_ctx;
+struct i2400m_roq;
+struct i2400m_barker_db;
+
+/**
+ * struct i2400m - descriptor for an Intel 2400m
+ *
+ * Members marked with [fill] must be filled out/initialized before
+ * calling i2400m_setup().
+ *
+ * Note the @bus_setup/@bus_release, @bus_dev_start/@bus_dev_release
+ * call pairs are very much doing almost the same, and depending on
+ * the underlying bus, some stuff has to be put in one or the
+ * other. The idea of setup/release is that they setup the minimal
+ * amount needed for loading firmware, where us dev_start/stop setup
+ * the rest needed to do full data/control traffic.
+ *
+ * @bus_tx_block_size: [fill] USB imposes a 16 block size, but other
+ *     busses will differ.  So we have a tx_blk_size variable that the
+ *     bus layer sets to tell the engine how much of that we need.
+ *
+ * @bus_tx_room_min: [fill] Minimum room required while allocating
+ *     TX queue's buffer space for message header. USB requires
+ *     16 bytes. Refer to bus specific driver code for details.
+ *
+ * @bus_pl_size_max: [fill] Maximum payload size.
+ *
+ * @bus_setup: [optional fill] Function called by the bus-generic code
+ *     [i2400m_setup()] to setup the basic bus-specific communications
+ *     to the the device needed to load firmware. See LIFE CYCLE above.
+ *
+ *     NOTE: Doesn't need to upload the firmware, as that is taken
+ *     care of by the bus-generic code.
+ *
+ * @bus_release: [optional fill] Function called by the bus-generic
+ *     code [i2400m_release()] to shutdown the basic bus-specific
+ *     communications to the the device needed to load firmware. See
+ *     LIFE CYCLE above.
+ *
+ *     This function does not need to reset the device, just tear down
+ *     all the host resources created to  handle communication with
+ *     the device.
+ *
+ * @bus_dev_start: [optional fill] Function called by the bus-generic
+ *     code [i2400m_dev_start()] to do things needed to start the
+ *     device. See LIFE CYCLE above.
+ *
+ *     NOTE: Doesn't need to upload the firmware, as that is taken
+ *     care of by the bus-generic code.
+ *
+ * @bus_dev_stop: [optional fill] Function called by the bus-generic
+ *     code [i2400m_dev_stop()] to do things needed for stopping the
+ *     device. See LIFE CYCLE above.
+ *
+ *     This function does not need to reset the device, just tear down
+ *     all the host resources created to handle communication with
+ *     the device.
+ *
+ * @bus_tx_kick: [fill] Function called by the bus-generic code to let
+ *     the bus-specific code know that there is data available in the
+ *     TX FIFO for transmission to the device.
+ *
+ *     This function cannot sleep.
+ *
+ * @bus_reset: [fill] Function called by the bus-generic code to reset
+ *     the device in in various ways. Doesn't need to wait for the
+ *     reset to finish.
+ *
+ *     If warm or cold reset fail, this function is expected to do a
+ *     bus-specific reset (eg: USB reset) to get the device to a
+ *     working state (even if it implies device disconecction).
+ *
+ *     Note the warm reset is used by the firmware uploader to
+ *     reinitialize the device.
+ *
+ *     IMPORTANT: this is called very early in the device setup
+ *     process, so it cannot rely on common infrastructure being laid
+ *     out.
+ *
+ *     IMPORTANT: don't call reset on RT_BUS with i2400m->init_mutex
+ *     held, as the .pre/.post reset handlers will deadlock.
+ *
+ * @bus_bm_retries: [fill] How many times shall a firmware upload /
+ *     device initialization be retried? Different models of the same
+ *     device might need different values, hence it is set by the
+ *     bus-specific driver. Note this value is used in two places,
+ *     i2400m_fw_dnload() and __i2400m_dev_start(); they won't become
+ *     multiplicative (__i2400m_dev_start() calling N times
+ *     i2400m_fw_dnload() and this trying N times to download the
+ *     firmware), as if __i2400m_dev_start() only retries if the
+ *     firmware crashed while initializing the device (not in a
+ *     general case).
+ *
+ * @bus_bm_cmd_send: [fill] Function called to send a boot-mode
+ *     command. Flags are defined in 'enum i2400m_bm_cmd_flags'. This
+ *     is synchronous and has to return 0 if ok or < 0 errno code in
+ *     any error condition.
+ *
+ * @bus_bm_wait_for_ack: [fill] Function called to wait for a
+ *     boot-mode notification (that can be a response to a previously
+ *     issued command or an asynchronous one). Will read until all the
+ *     indicated size is read or timeout. Reading more or less data
+ *     than asked for is an error condition. Return 0 if ok, < 0 errno
+ *     code on error.
+ *
+ *     The caller to this function will check if the response is a
+ *     barker that indicates the device going into reset mode.
+ *
+ * @bus_fw_names: [fill] a NULL-terminated array with the names of the
+ *     firmware images to try loading. This is made a list so we can
+ *     support backward compatibility of firmware releases (eg: if we
+ *     can't find the default v1.4, we try v1.3). In general, the name
+ *     should be i2400m-fw-X-VERSION.sbcf, where X is the bus name.
+ *     The list is tried in order and the first one that loads is
+ *     used. The fw loader will set i2400m->fw_name to point to the
+ *     active firmware image.
+ *
+ * @bus_bm_mac_addr_impaired: [fill] Set to true if the device's MAC
+ *     address provided in boot mode is kind of broken and needs to
+ *     be re-read later on.
+ *
+ * @bus_bm_pokes_table: [fill/optional] A table of device addresses
+ *     and values that will be poked at device init time to move the
+ *     device to the correct state for the type of boot/firmware being
+ *     used.  This table MUST be terminated with (0x000000,
+ *     0x00000000) or bad things will happen.
+ *
+ *
+ * @wimax_dev: WiMAX generic device for linkage into the kernel WiMAX
+ *     stack. Due to the way a net_device is allocated, we need to
+ *     force this to be the first field so that we can get from
+ *     netdev_priv() the right pointer.
+ *
+ * @updown: the device is up and ready for transmitting control and
+ *     data packets. This implies @ready (communication infrastructure
+ *     with the device is ready) and the device's firmware has been
+ *     loaded and the device initialized.
+ *
+ *     Write to it only inside a i2400m->init_mutex protected area
+ *     followed with a wmb(); rmb() before accesing (unless locked
+ *     inside i2400m->init_mutex). Read access can be loose like that
+ *     [just using rmb()] because the paths that use this also do
+ *     other error checks later on.
+ *
+ * @ready: Communication infrastructure with the device is ready, data
+ *     frames can start to be passed around (this is lighter than
+ *     using the WiMAX state for certain hot paths).
+ *
+ *     Write to it only inside a i2400m->init_mutex protected area
+ *     followed with a wmb(); rmb() before accesing (unless locked
+ *     inside i2400m->init_mutex). Read access can be loose like that
+ *     [just using rmb()] because the paths that use this also do
+ *     other error checks later on.
+ *
+ * @rx_reorder: 1 if RX reordering is enabled; this can only be
+ *     set at probe time.
+ *
+ * @state: device's state (as reported by it)
+ *
+ * @state_wq: waitqueue that is woken up whenever the state changes
+ *
+ * @tx_lock: spinlock to protect TX members
+ *
+ * @tx_buf: FIFO buffer for TX; we queue data here
+ *
+ * @tx_in: FIFO index for incoming data. Note this doesn't wrap around
+ *     and it is always greater than @tx_out.
+ *
+ * @tx_out: FIFO index for outgoing data
+ *
+ * @tx_msg: current TX message that is active in the FIFO for
+ *     appending payloads.
+ *
+ * @tx_sequence: current sequence number for TX messages from the
+ *     device to the host.
+ *
+ * @tx_msg_size: size of the current message being transmitted by the
+ *     bus-specific code.
+ *
+ * @tx_pl_num: total number of payloads sent
+ *
+ * @tx_pl_max: maximum number of payloads sent in a TX message
+ *
+ * @tx_pl_min: minimum number of payloads sent in a TX message
+ *
+ * @tx_num: number of TX messages sent
+ *
+ * @tx_size_acc: number of bytes in all TX messages sent
+ *     (this is different to net_dev's statistics as it also counts
+ *     control messages).
+ *
+ * @tx_size_min: smallest TX message sent.
+ *
+ * @tx_size_max: biggest TX message sent.
+ *
+ * @rx_lock: spinlock to protect RX members and rx_roq_refcount.
+ *
+ * @rx_pl_num: total number of payloads received
+ *
+ * @rx_pl_max: maximum number of payloads received in a RX message
+ *
+ * @rx_pl_min: minimum number of payloads received in a RX message
+ *
+ * @rx_num: number of RX messages received
+ *
+ * @rx_size_acc: number of bytes in all RX messages received
+ *     (this is different to net_dev's statistics as it also counts
+ *     control messages).
+ *
+ * @rx_size_min: smallest RX message received.
+ *
+ * @rx_size_max: buggest RX message received.
+ *
+ * @rx_roq: RX ReOrder queues. (fw >= v1.4) When packets are received
+ *     out of order, the device will ask the driver to hold certain
+ *     packets until the ones that are received out of order can be
+ *     delivered. Then the driver can release them to the host. See
+ *     drivers/net/i2400m/rx.c for details.
+ *
+ * @rx_roq_refcount: refcount rx_roq. This refcounts any access to
+ *     rx_roq thus preventing rx_roq being destroyed when rx_roq
+ *     is being accessed. rx_roq_refcount is protected by rx_lock.
+ *
+ * @rx_reports: reports received from the device that couldn't be
+ *     processed because the driver wasn't still ready; when ready,
+ *     they are pulled from here and chewed.
+ *
+ * @rx_reports_ws: Work struct used to kick a scan of the RX reports
+ *     list and to process each.
+ *
+ * @src_mac_addr: MAC address used to make ethernet packets be coming
+ *     from. This is generated at i2400m_setup() time and used during
+ *     the life cycle of the instance. See i2400m_fake_eth_header().
+ *
+ * @init_mutex: Mutex used for serializing the device bringup
+ *     sequence; this way if the device reboots in the middle, we
+ *     don't try to do a bringup again while we are tearing down the
+ *     one that failed.
+ *
+ *     Can't reuse @msg_mutex because from within the bringup sequence
+ *     we need to send messages to the device and thus use @msg_mutex.
+ *
+ * @msg_mutex: mutex used to send control commands to the device (we
+ *     only allow one at a time, per host-device interface design).
+ *
+ * @msg_completion: used to wait for an ack to a control command sent
+ *     to the device.
+ *
+ * @ack_skb: used to store the actual ack to a control command if the
+ *     reception of the command was successful. Otherwise, a ERR_PTR()
+ *     errno code that indicates what failed with the ack reception.
+ *
+ *     Only valid after @msg_completion is woken up. Only updateable
+ *     if @msg_completion is armed. Only touched by
+ *     i2400m_msg_to_dev().
+ *
+ *     Protected by @rx_lock. In theory the command execution flow is
+ *     sequential, but in case the device sends an out-of-phase or
+ *     very delayed response, we need to avoid it trampling current
+ *     execution.
+ *
+ * @bm_cmd_buf: boot mode command buffer for composing firmware upload
+ *     commands.
+ *
+ *     USB can't r/w to stack, vmalloc, etc...as well, we end up
+ *     having to alloc/free a lot to compose commands, so we use these
+ *     for stagging and not having to realloc all the time.
+ *
+ *     This assumes the code always runs serialized. Only one thread
+ *     can call i2400m_bm_cmd() at the same time.
+ *
+ * @bm_ack_buf: boot mode acknoledge buffer for staging reception of
+ *     responses to commands.
+ *
+ *     See @bm_cmd_buf.
+ *
+ * @work_queue: work queue for processing device reports. This
+ *     workqueue cannot be used for processing TX or RX to the device,
+ *     as from it we'll process device reports, which might require
+ *     further communication with the device.
+ *
+ * @debugfs_dentry: hookup for debugfs files.
+ *     These have to be in a separate directory, a child of
+ *     (wimax_dev->debugfs_dentry) so they can be removed when the
+ *     module unloads, as we don't keep each dentry.
+ *
+ * @fw_name: name of the firmware image that is currently being used.
+ *
+ * @fw_version: version of the firmware interface, Major.minor,
+ *     encoded in the high word and low word (major << 16 | minor).
+ *
+ * @fw_hdrs: NULL terminated array of pointers to the firmware
+ *     headers. This is only available during firmware load time.
+ *
+ * @fw_cached: Used to cache firmware when the system goes to
+ *     suspend/standby/hibernation (as on resume we can't read it). If
+ *     NULL, no firmware was cached, read it. If ~0, you can't read
+ *     any firmware files (the system still didn't come out of suspend
+ *     and failed to cache one), so abort; otherwise, a valid cached
+ *     firmware to be used. Access to this variable is protected by
+ *     the spinlock i2400m->rx_lock.
+ *
+ * @barker: barker type that the device uses; this is initialized by
+ *     i2400m_is_boot_barker() the first time it is called. Then it
+ *     won't change during the life cycle of the device and every time
+ *     a boot barker is received, it is just verified for it being the
+ *     same.
+ *
+ * @pm_notifier: used to register for PM events
+ *
+ * @bus_reset_retries: counter for the number of bus resets attempted for
+ *	this boot. It's not for tracking the number of bus resets during
+ *	the whole driver life cycle (from insmod to rmmod) but for the
+ *	number of dev_start() executed until dev_start() returns a success
+ *	(ie: a good boot means a dev_stop() followed by a successful
+ *	dev_start()). dev_reset_handler() increments this counter whenever
+ *	it is triggering a bus reset. It checks this counter to decide if a
+ *	subsequent bus reset should be retried. dev_reset_handler() retries
+ *	the bus reset until dev_start() succeeds or the counter reaches
+ *	I2400M_BUS_RESET_RETRIES. The counter is cleared to 0 in
+ *	dev_reset_handle() when dev_start() returns a success,
+ *	ie: a successul boot is completed.
+ *
+ * @alive: flag to denote if the device *should* be alive. This flag is
+ *	everything like @updown (see doc for @updown) except reflecting
+ *	the device state *we expect* rather than the actual state as denoted
+ *	by @updown. It is set 1 whenever @updown is set 1 in dev_start().
+ *	Then the device is expected to be alive all the time
+ *	(i2400m->alive remains 1) until the driver is removed. Therefore
+ *	all the device reboot events detected can be still handled properly
+ *	by either dev_reset_handle() or .pre_reset/.post_reset as long as
+ *	the driver presents. It is set 0 along with @updown in dev_stop().
+ *
+ * @error_recovery: flag to denote if we are ready to take an error recovery.
+ *	0 for ready to take an error recovery; 1 for not ready. It is
+ *	initialized to 1 while probe() since we don't tend to take any error
+ *	recovery during probe(). It is decremented by 1 whenever dev_start()
+ *	succeeds to indicate we are ready to take error recovery from now on.
+ *	It is checked every time we wanna schedule an error recovery. If an
+ *	error recovery is already in place (error_recovery was set 1), we
+ *	should not schedule another one until the last one is done.
+ */
+struct i2400m {
+	struct wimax_dev wimax_dev;	/* FIRST! See doc */
+
+	unsigned updown:1;		/* Network device is up or down */
+	unsigned boot_mode:1;		/* is the device in boot mode? */
+	unsigned sboot:1;		/* signed or unsigned fw boot */
+	unsigned ready:1;		/* Device comm infrastructure ready */
+	unsigned rx_reorder:1;		/* RX reorder is enabled */
+	u8 trace_msg_from_user;		/* echo rx msgs to 'trace' pipe */
+					/* typed u8 so /sys/kernel/debug/u8 can tweak */
+	enum i2400m_system_state state;
+	wait_queue_head_t state_wq;	/* Woken up when on state updates */
+
+	size_t bus_tx_block_size;
+	size_t bus_tx_room_min;
+	size_t bus_pl_size_max;
+	unsigned bus_bm_retries;
+
+	int (*bus_setup)(struct i2400m *);
+	int (*bus_dev_start)(struct i2400m *);
+	void (*bus_dev_stop)(struct i2400m *);
+	void (*bus_release)(struct i2400m *);
+	void (*bus_tx_kick)(struct i2400m *);
+	int (*bus_reset)(struct i2400m *, enum i2400m_reset_type);
+	ssize_t (*bus_bm_cmd_send)(struct i2400m *,
+				   const struct i2400m_bootrom_header *,
+				   size_t, int flags);
+	ssize_t (*bus_bm_wait_for_ack)(struct i2400m *,
+				       struct i2400m_bootrom_header *, size_t);
+	const char **bus_fw_names;
+	unsigned bus_bm_mac_addr_impaired:1;
+	const struct i2400m_poke_table *bus_bm_pokes_table;
+
+	spinlock_t tx_lock;		/* protect TX state */
+	void *tx_buf;
+	size_t tx_in, tx_out;
+	struct i2400m_msg_hdr *tx_msg;
+	size_t tx_sequence, tx_msg_size;
+	/* TX stats */
+	unsigned tx_pl_num, tx_pl_max, tx_pl_min,
+		tx_num, tx_size_acc, tx_size_min, tx_size_max;
+
+	/* RX stuff */
+	/* protect RX state and rx_roq_refcount */
+	spinlock_t rx_lock;
+	unsigned rx_pl_num, rx_pl_max, rx_pl_min,
+		rx_num, rx_size_acc, rx_size_min, rx_size_max;
+	struct i2400m_roq *rx_roq;	/* access is refcounted */
+	struct kref rx_roq_refcount;	/* refcount access to rx_roq */
+	u8 src_mac_addr[ETH_HLEN];
+	struct list_head rx_reports;	/* under rx_lock! */
+	struct work_struct rx_report_ws;
+
+	struct mutex msg_mutex;		/* serialize command execution */
+	struct completion msg_completion;
+	struct sk_buff *ack_skb;	/* protected by rx_lock */
+
+	void *bm_ack_buf;		/* for receiving acks over USB */
+	void *bm_cmd_buf;		/* for issuing commands over USB */
+
+	struct workqueue_struct *work_queue;
+
+	struct mutex init_mutex;	/* protect bringup seq */
+	struct i2400m_reset_ctx *reset_ctx;	/* protected by init_mutex */
+
+	struct work_struct wake_tx_ws;
+	struct sk_buff *wake_tx_skb;
+
+	struct work_struct reset_ws;
+	const char *reset_reason;
+
+	struct work_struct recovery_ws;
+
+	struct dentry *debugfs_dentry;
+	const char *fw_name;		/* name of the current firmware image */
+	unsigned long fw_version;	/* version of the firmware interface */
+	const struct i2400m_bcf_hdr **fw_hdrs;
+	struct i2400m_fw *fw_cached;	/* protected by rx_lock */
+	struct i2400m_barker_db *barker;
+
+	struct notifier_block pm_notifier;
+
+	/* counting bus reset retries in this boot */
+	atomic_t bus_reset_retries;
+
+	/* if the device is expected to be alive */
+	unsigned alive;
+
+	/* 0 if we are ready for error recovery; 1 if not ready  */
+	atomic_t error_recovery;
+
+};
+
+
+/*
+ * Bus-generic internal APIs
+ * -------------------------
+ */
+
+static inline
+struct i2400m *wimax_dev_to_i2400m(struct wimax_dev *wimax_dev)
+{
+	return container_of(wimax_dev, struct i2400m, wimax_dev);
+}
+
+static inline
+struct i2400m *net_dev_to_i2400m(struct net_device *net_dev)
+{
+	return wimax_dev_to_i2400m(netdev_priv(net_dev));
+}
+
+/*
+ * Boot mode support
+ */
+
+/**
+ * i2400m_bm_cmd_flags - flags to i2400m_bm_cmd()
+ *
+ * @I2400M_BM_CMD_RAW: send the command block as-is, without doing any
+ *     extra processing for adding CRC.
+ */
+enum i2400m_bm_cmd_flags {
+	I2400M_BM_CMD_RAW	= 1 << 2,
+};
+
+/**
+ * i2400m_bri - Boot-ROM indicators
+ *
+ * Flags for i2400m_bootrom_init() and i2400m_dev_bootstrap() [which
+ * are passed from things like i2400m_setup()]. Can be combined with
+ * |.
+ *
+ * @I2400M_BRI_SOFT: The device rebooted already and a reboot
+ *     barker received, proceed directly to ack the boot sequence.
+ * @I2400M_BRI_NO_REBOOT: Do not reboot the device and proceed
+ *     directly to wait for a reboot barker from the device.
+ * @I2400M_BRI_MAC_REINIT: We need to reinitialize the boot
+ *     rom after reading the MAC address. This is quite a dirty hack,
+ *     if you ask me -- the device requires the bootrom to be
+ *     initialized after reading the MAC address.
+ */
+enum i2400m_bri {
+	I2400M_BRI_SOFT       = 1 << 1,
+	I2400M_BRI_NO_REBOOT  = 1 << 2,
+	I2400M_BRI_MAC_REINIT = 1 << 3,
+};
+
+void i2400m_bm_cmd_prepare(struct i2400m_bootrom_header *);
+int i2400m_dev_bootstrap(struct i2400m *, enum i2400m_bri);
+int i2400m_read_mac_addr(struct i2400m *);
+int i2400m_bootrom_init(struct i2400m *, enum i2400m_bri);
+int i2400m_is_boot_barker(struct i2400m *, const void *, size_t);
+static inline
+int i2400m_is_d2h_barker(const void *buf)
+{
+	const __le32 *barker = buf;
+	return le32_to_cpu(*barker) == I2400M_D2H_MSG_BARKER;
+}
+void i2400m_unknown_barker(struct i2400m *, const void *, size_t);
+
+/* Make/grok boot-rom header commands */
+
+static inline
+__le32 i2400m_brh_command(enum i2400m_brh_opcode opcode, unsigned use_checksum,
+			  unsigned direct_access)
+{
+	return cpu_to_le32(
+		I2400M_BRH_SIGNATURE
+		| (direct_access ? I2400M_BRH_DIRECT_ACCESS : 0)
+		| I2400M_BRH_RESPONSE_REQUIRED /* response always required */
+		| (use_checksum ? I2400M_BRH_USE_CHECKSUM : 0)
+		| (opcode & I2400M_BRH_OPCODE_MASK));
+}
+
+static inline
+void i2400m_brh_set_opcode(struct i2400m_bootrom_header *hdr,
+			   enum i2400m_brh_opcode opcode)
+{
+	hdr->command = cpu_to_le32(
+		(le32_to_cpu(hdr->command) & ~I2400M_BRH_OPCODE_MASK)
+		| (opcode & I2400M_BRH_OPCODE_MASK));
+}
+
+static inline
+unsigned i2400m_brh_get_opcode(const struct i2400m_bootrom_header *hdr)
+{
+	return le32_to_cpu(hdr->command) & I2400M_BRH_OPCODE_MASK;
+}
+
+static inline
+unsigned i2400m_brh_get_response(const struct i2400m_bootrom_header *hdr)
+{
+	return (le32_to_cpu(hdr->command) & I2400M_BRH_RESPONSE_MASK)
+		>> I2400M_BRH_RESPONSE_SHIFT;
+}
+
+static inline
+unsigned i2400m_brh_get_use_checksum(const struct i2400m_bootrom_header *hdr)
+{
+	return le32_to_cpu(hdr->command) & I2400M_BRH_USE_CHECKSUM;
+}
+
+static inline
+unsigned i2400m_brh_get_response_required(
+	const struct i2400m_bootrom_header *hdr)
+{
+	return le32_to_cpu(hdr->command) & I2400M_BRH_RESPONSE_REQUIRED;
+}
+
+static inline
+unsigned i2400m_brh_get_direct_access(const struct i2400m_bootrom_header *hdr)
+{
+	return le32_to_cpu(hdr->command) & I2400M_BRH_DIRECT_ACCESS;
+}
+
+static inline
+unsigned i2400m_brh_get_signature(const struct i2400m_bootrom_header *hdr)
+{
+	return (le32_to_cpu(hdr->command) & I2400M_BRH_SIGNATURE_MASK)
+		>> I2400M_BRH_SIGNATURE_SHIFT;
+}
+
+
+/*
+ * Driver / device setup and internal functions
+ */
+void i2400m_init(struct i2400m *);
+int i2400m_reset(struct i2400m *, enum i2400m_reset_type);
+void i2400m_netdev_setup(struct net_device *net_dev);
+int i2400m_sysfs_setup(struct device_driver *);
+void i2400m_sysfs_release(struct device_driver *);
+int i2400m_tx_setup(struct i2400m *);
+void i2400m_wake_tx_work(struct work_struct *);
+void i2400m_tx_release(struct i2400m *);
+
+int i2400m_rx_setup(struct i2400m *);
+void i2400m_rx_release(struct i2400m *);
+
+void i2400m_fw_cache(struct i2400m *);
+void i2400m_fw_uncache(struct i2400m *);
+
+void i2400m_net_rx(struct i2400m *, struct sk_buff *, unsigned, const void *,
+		   int);
+void i2400m_net_erx(struct i2400m *, struct sk_buff *, enum i2400m_cs);
+void i2400m_net_wake_stop(struct i2400m *);
+enum i2400m_pt;
+int i2400m_tx(struct i2400m *, const void *, size_t, enum i2400m_pt);
+
+#ifdef CONFIG_DEBUG_FS
+void i2400m_debugfs_add(struct i2400m *);
+void i2400m_debugfs_rm(struct i2400m *);
+#else
+static inline void i2400m_debugfs_add(struct i2400m *i2400m) {}
+static inline void i2400m_debugfs_rm(struct i2400m *i2400m) {}
+#endif
+
+/* Initialize/shutdown the device */
+int i2400m_dev_initialize(struct i2400m *);
+void i2400m_dev_shutdown(struct i2400m *);
+
+extern struct attribute_group i2400m_dev_attr_group;
+
+
+/* HDI message's payload description handling */
+
+static inline
+size_t i2400m_pld_size(const struct i2400m_pld *pld)
+{
+	return I2400M_PLD_SIZE_MASK & le32_to_cpu(pld->val);
+}
+
+static inline
+enum i2400m_pt i2400m_pld_type(const struct i2400m_pld *pld)
+{
+	return (I2400M_PLD_TYPE_MASK & le32_to_cpu(pld->val))
+		>> I2400M_PLD_TYPE_SHIFT;
+}
+
+static inline
+void i2400m_pld_set(struct i2400m_pld *pld, size_t size,
+		    enum i2400m_pt type)
+{
+	pld->val = cpu_to_le32(
+		((type << I2400M_PLD_TYPE_SHIFT) & I2400M_PLD_TYPE_MASK)
+		|  (size & I2400M_PLD_SIZE_MASK));
+}
+
+
+/*
+ * API for the bus-specific drivers
+ * --------------------------------
+ */
+
+static inline
+struct i2400m *i2400m_get(struct i2400m *i2400m)
+{
+	dev_hold(i2400m->wimax_dev.net_dev);
+	return i2400m;
+}
+
+static inline
+void i2400m_put(struct i2400m *i2400m)
+{
+	dev_put(i2400m->wimax_dev.net_dev);
+}
+
+int i2400m_dev_reset_handle(struct i2400m *, const char *);
+int i2400m_pre_reset(struct i2400m *);
+int i2400m_post_reset(struct i2400m *);
+void i2400m_error_recovery(struct i2400m *);
+
+/*
+ * _setup()/_release() are called by the probe/disconnect functions of
+ * the bus-specific drivers.
+ */
+int i2400m_setup(struct i2400m *, enum i2400m_bri bm_flags);
+void i2400m_release(struct i2400m *);
+
+int i2400m_rx(struct i2400m *, struct sk_buff *);
+struct i2400m_msg_hdr *i2400m_tx_msg_get(struct i2400m *, size_t *);
+void i2400m_tx_msg_sent(struct i2400m *);
+
+
+/*
+ * Utility functions
+ */
+
+static inline
+struct device *i2400m_dev(struct i2400m *i2400m)
+{
+	return i2400m->wimax_dev.net_dev->dev.parent;
+}
+
+int i2400m_msg_check_status(const struct i2400m_l3l4_hdr *, char *, size_t);
+int i2400m_msg_size_check(struct i2400m *, const struct i2400m_l3l4_hdr *,
+			  size_t);
+struct sk_buff *i2400m_msg_to_dev(struct i2400m *, const void *, size_t);
+void i2400m_msg_to_dev_cancel_wait(struct i2400m *, int);
+void i2400m_report_hook(struct i2400m *, const struct i2400m_l3l4_hdr *,
+			size_t);
+void i2400m_report_hook_work(struct work_struct *);
+int i2400m_cmd_enter_powersave(struct i2400m *);
+int i2400m_cmd_exit_idle(struct i2400m *);
+struct sk_buff *i2400m_get_device_info(struct i2400m *);
+int i2400m_firmware_check(struct i2400m *);
+int i2400m_set_idle_timeout(struct i2400m *, unsigned);
+
+static inline
+struct usb_endpoint_descriptor *usb_get_epd(struct usb_interface *iface, int ep)
+{
+	return &iface->cur_altsetting->endpoint[ep].desc;
+}
+
+int i2400m_op_rfkill_sw_toggle(struct wimax_dev *, enum wimax_rf_state);
+void i2400m_report_tlv_rf_switches_status(struct i2400m *,
+					  const struct i2400m_tlv_rf_switches_status *);
+
+/*
+ * Helpers for firmware backwards compatibility
+ *
+ * As we aim to support at least the firmware version that was
+ * released with the previous kernel/driver release, some code will be
+ * conditionally executed depending on the firmware version. On each
+ * release, the code to support fw releases past the last two ones
+ * will be purged.
+ *
+ * By making it depend on this macros, it is easier to keep it a tab
+ * on what has to go and what not.
+ */
+static inline
+unsigned i2400m_le_v1_3(struct i2400m *i2400m)
+{
+	/* running fw is lower or v1.3 */
+	return i2400m->fw_version <= 0x00090001;
+}
+
+static inline
+unsigned i2400m_ge_v1_4(struct i2400m *i2400m)
+{
+	/* running fw is higher or v1.4 */
+	return i2400m->fw_version >= 0x00090002;
+}
+
+
+/*
+ * Do a millisecond-sleep for allowing wireshark to dump all the data
+ * packets. Used only for debugging.
+ */
+static inline
+void __i2400m_msleep(unsigned ms)
+{
+#if 1
+#else
+	msleep(ms);
+#endif
+}
+
+
+/* module initialization helpers */
+int i2400m_barker_db_init(const char *);
+void i2400m_barker_db_exit(void);
+
+
+
+#endif /* #ifndef __I2400M_H__ */
diff --git a/drivers/staging/wimax/i2400m/linux-wimax-i2400m.h b/drivers/staging/wimax/i2400m/linux-wimax-i2400m.h
new file mode 100644
index 000000000000..fd198bc24a3c
--- /dev/null
+++ b/drivers/staging/wimax/i2400m/linux-wimax-i2400m.h
@@ -0,0 +1,572 @@
+/*
+ * Intel Wireless WiMax Connection 2400m
+ * Host-Device protocol interface definitions
+ *
+ *
+ * Copyright (C) 2007-2008 Intel Corporation. All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *
+ * Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *  - Initial implementation
+ *
+ *
+ * This header defines the data structures and constants used to
+ * communicate with the device.
+ *
+ * BOOTMODE/BOOTROM/FIRMWARE UPLOAD PROTOCOL
+ *
+ * The firmware upload protocol is quite simple and only requires a
+ * handful of commands. See drivers/net/wimax/i2400m/fw.c for more
+ * details.
+ *
+ * The BCF data structure is for the firmware file header.
+ *
+ *
+ * THE DATA / CONTROL PROTOCOL
+ *
+ * This is the normal protocol spoken with the device once the
+ * firmware is uploaded. It transports data payloads and control
+ * messages back and forth.
+ *
+ * It consists 'messages' that pack one or more payloads each. The
+ * format is described in detail in drivers/net/wimax/i2400m/rx.c and
+ * tx.c.
+ *
+ *
+ * THE L3L4 PROTOCOL
+ *
+ * The term L3L4 refers to Layer 3 (the device), Layer 4 (the
+ * driver/host software).
+ *
+ * This is the control protocol used by the host to control the i2400m
+ * device (scan, connect, disconnect...). This is sent to / received
+ * as control frames. These frames consist of a header and zero or
+ * more TLVs with information. We call each control frame a "message".
+ *
+ * Each message is composed of:
+ *
+ * HEADER
+ * [TLV0 + PAYLOAD0]
+ * [TLV1 + PAYLOAD1]
+ * [...]
+ * [TLVN + PAYLOADN]
+ *
+ * The HEADER is defined by 'struct i2400m_l3l4_hdr'. The payloads are
+ * defined by a TLV structure (Type Length Value) which is a 'header'
+ * (struct i2400m_tlv_hdr) and then the payload.
+ *
+ * All integers are represented as Little Endian.
+ *
+ * - REQUESTS AND EVENTS
+ *
+ * The requests can be clasified as follows:
+ *
+ *   COMMAND:  implies a request from the host to the device requesting
+ *             an action being performed. The device will reply with a
+ *             message (with the same type as the command), status and
+ *             no (TLV) payload. Execution of a command might cause
+ *             events (of different type) to be sent later on as
+ *             device's state changes.
+ *
+ *   GET/SET:  similar to COMMAND, but will not cause other
+ *             EVENTs. The reply, in the case of GET, will contain
+ *             TLVs with the requested information.
+ *
+ *   EVENT:    asynchronous messages sent from the device, maybe as a
+ *             consequence of previous COMMANDs but disassociated from
+ *             them.
+ *
+ * Only one request might be pending at the same time (ie: don't
+ * parallelize nor post another GET request before the previous
+ * COMMAND has been acknowledged with it's corresponding reply by the
+ * device).
+ *
+ * The different requests and their formats are described below:
+ *
+ *  I2400M_MT_*   Message types
+ *  I2400M_MS_*   Message status (for replies, events)
+ *  i2400m_tlv_*  TLVs
+ *
+ * data types are named 'struct i2400m_msg_OPNAME', OPNAME matching the
+ * operation.
+ */
+
+#ifndef __LINUX__WIMAX__I2400M_H__
+#define __LINUX__WIMAX__I2400M_H__
+
+#include <linux/types.h>
+#include <linux/if_ether.h>
+
+/*
+ * Host Device Interface (HDI) common to all busses
+ */
+
+/* Boot-mode (firmware upload mode) commands */
+
+/* Header for the firmware file */
+struct i2400m_bcf_hdr {
+	__le32 module_type;
+	__le32 header_len;
+	__le32 header_version;
+	__le32 module_id;
+	__le32 module_vendor;
+	__le32 date;		/* BCD YYYMMDD */
+	__le32 size;            /* in dwords */
+	__le32 key_size;	/* in dwords */
+	__le32 modulus_size;	/* in dwords */
+	__le32 exponent_size;	/* in dwords */
+	__u8 reserved[88];
+} __attribute__ ((packed));
+
+/* Boot mode opcodes */
+enum i2400m_brh_opcode {
+	I2400M_BRH_READ = 1,
+	I2400M_BRH_WRITE = 2,
+	I2400M_BRH_JUMP = 3,
+	I2400M_BRH_SIGNED_JUMP = 8,
+	I2400M_BRH_HASH_PAYLOAD_ONLY = 9,
+};
+
+/* Boot mode command masks and stuff */
+enum i2400m_brh {
+	I2400M_BRH_SIGNATURE = 0xcbbc0000,
+	I2400M_BRH_SIGNATURE_MASK = 0xffff0000,
+	I2400M_BRH_SIGNATURE_SHIFT = 16,
+	I2400M_BRH_OPCODE_MASK = 0x0000000f,
+	I2400M_BRH_RESPONSE_MASK = 0x000000f0,
+	I2400M_BRH_RESPONSE_SHIFT = 4,
+	I2400M_BRH_DIRECT_ACCESS = 0x00000400,
+	I2400M_BRH_RESPONSE_REQUIRED = 0x00000200,
+	I2400M_BRH_USE_CHECKSUM = 0x00000100,
+};
+
+
+/**
+ * i2400m_bootrom_header - Header for a boot-mode command
+ *
+ * @cmd: the above command descriptor
+ * @target_addr: where on the device memory should the action be performed.
+ * @data_size: for read/write, amount of data to be read/written
+ * @block_checksum: checksum value (if applicable)
+ * @payload: the beginning of data attached to this header
+ */
+struct i2400m_bootrom_header {
+	__le32 command;		/* Compose with enum i2400_brh */
+	__le32 target_addr;
+	__le32 data_size;
+	__le32 block_checksum;
+	char payload[0];
+} __attribute__ ((packed));
+
+
+/*
+ * Data / control protocol
+ */
+
+/* Packet types for the host-device interface */
+enum i2400m_pt {
+	I2400M_PT_DATA = 0,
+	I2400M_PT_CTRL,
+	I2400M_PT_TRACE,	/* For device debug */
+	I2400M_PT_RESET_WARM,	/* device reset */
+	I2400M_PT_RESET_COLD,	/* USB[transport] reset, like reconnect */
+	I2400M_PT_EDATA,	/* Extended RX data */
+	I2400M_PT_ILLEGAL
+};
+
+
+/*
+ * Payload for a data packet
+ *
+ * This is prefixed to each and every outgoing DATA type.
+ */
+struct i2400m_pl_data_hdr {
+	__le32 reserved;
+} __attribute__((packed));
+
+
+/*
+ * Payload for an extended data packet
+ *
+ * New in fw v1.4
+ *
+ * @reorder: if this payload has to be reorder or not (and how)
+ * @cs: the type of data in the packet, as defined per (802.16e
+ *     T11.13.19.1). Currently only 2 (IPv4 packet) supported.
+ *
+ * This is prefixed to each and every INCOMING DATA packet.
+ */
+struct i2400m_pl_edata_hdr {
+	__le32 reorder;		/* bits defined in i2400m_ro */
+	__u8 cs;
+	__u8 reserved[11];
+} __attribute__((packed));
+
+enum i2400m_cs {
+	I2400M_CS_IPV4_0 = 0,
+	I2400M_CS_IPV4 = 2,
+};
+
+enum i2400m_ro {
+	I2400M_RO_NEEDED     = 0x01,
+	I2400M_RO_TYPE       = 0x03,
+	I2400M_RO_TYPE_SHIFT = 1,
+	I2400M_RO_CIN        = 0x0f,
+	I2400M_RO_CIN_SHIFT  = 4,
+	I2400M_RO_FBN        = 0x07ff,
+	I2400M_RO_FBN_SHIFT  = 8,
+	I2400M_RO_SN         = 0x07ff,
+	I2400M_RO_SN_SHIFT   = 21,
+};
+
+enum i2400m_ro_type {
+	I2400M_RO_TYPE_RESET = 0,
+	I2400M_RO_TYPE_PACKET,
+	I2400M_RO_TYPE_WS,
+	I2400M_RO_TYPE_PACKET_WS,
+};
+
+
+/* Misc constants */
+enum {
+	I2400M_PL_ALIGN = 16,	/* Payload data size alignment */
+	I2400M_PL_SIZE_MAX = 0x3EFF,
+	I2400M_MAX_PLS_IN_MSG = 60,
+	/* protocol barkers: sync sequences; for notifications they
+	 * are sent in groups of four. */
+	I2400M_H2D_PREVIEW_BARKER = 0xcafe900d,
+	I2400M_COLD_RESET_BARKER = 0xc01dc01d,
+	I2400M_WARM_RESET_BARKER = 0x50f750f7,
+	I2400M_NBOOT_BARKER = 0xdeadbeef,
+	I2400M_SBOOT_BARKER = 0x0ff1c1a1,
+	I2400M_SBOOT_BARKER_6050 = 0x80000001,
+	I2400M_ACK_BARKER = 0xfeedbabe,
+	I2400M_D2H_MSG_BARKER = 0xbeefbabe,
+};
+
+
+/*
+ * Hardware payload descriptor
+ *
+ * Bitfields encoded in a struct to enforce typing semantics.
+ *
+ * Look in rx.c and tx.c for a full description of the format.
+ */
+struct i2400m_pld {
+	__le32 val;
+} __attribute__ ((packed));
+
+#define I2400M_PLD_SIZE_MASK 0x00003fff
+#define I2400M_PLD_TYPE_SHIFT 16
+#define I2400M_PLD_TYPE_MASK 0x000f0000
+
+/*
+ * Header for a TX message or RX message
+ *
+ * @barker: preamble
+ * @size: used for management of the FIFO queue buffer; before
+ *     sending, this is converted to be a real preamble. This
+ *     indicates the real size of the TX message that starts at this
+ *     point. If the highest bit is set, then this message is to be
+ *     skipped.
+ * @sequence: sequence number of this message
+ * @offset: offset where the message itself starts -- see the comments
+ *     in the file header about message header and payload descriptor
+ *     alignment.
+ * @num_pls: number of payloads in this message
+ * @padding: amount of padding bytes at the end of the message to make
+ *           it be of block-size aligned
+ *
+ * Look in rx.c and tx.c for a full description of the format.
+ */
+struct i2400m_msg_hdr {
+	union {
+		__le32 barker;
+		__u32 size;	/* same size type as barker!! */
+	};
+	union {
+		__le32 sequence;
+		__u32 offset;	/* same size type as barker!! */
+	};
+	__le16 num_pls;
+	__le16 rsv1;
+	__le16 padding;
+	__le16 rsv2;
+	struct i2400m_pld pld[0];
+} __attribute__ ((packed));
+
+
+
+/*
+ * L3/L4 control protocol
+ */
+
+enum {
+	/* Interface version */
+	I2400M_L3L4_VERSION             = 0x0100,
+};
+
+/* Message types */
+enum i2400m_mt {
+	I2400M_MT_RESERVED              = 0x0000,
+	I2400M_MT_INVALID               = 0xffff,
+	I2400M_MT_REPORT_MASK		= 0x8000,
+
+	I2400M_MT_GET_SCAN_RESULT  	= 0x4202,
+	I2400M_MT_SET_SCAN_PARAM   	= 0x4402,
+	I2400M_MT_CMD_RF_CONTROL   	= 0x4602,
+	I2400M_MT_CMD_SCAN         	= 0x4603,
+	I2400M_MT_CMD_CONNECT      	= 0x4604,
+	I2400M_MT_CMD_DISCONNECT   	= 0x4605,
+	I2400M_MT_CMD_EXIT_IDLE   	= 0x4606,
+	I2400M_MT_GET_LM_VERSION   	= 0x5201,
+	I2400M_MT_GET_DEVICE_INFO  	= 0x5202,
+	I2400M_MT_GET_LINK_STATUS  	= 0x5203,
+	I2400M_MT_GET_STATISTICS   	= 0x5204,
+	I2400M_MT_GET_STATE        	= 0x5205,
+	I2400M_MT_GET_MEDIA_STATUS	= 0x5206,
+	I2400M_MT_SET_INIT_CONFIG	= 0x5404,
+	I2400M_MT_CMD_INIT	        = 0x5601,
+	I2400M_MT_CMD_TERMINATE		= 0x5602,
+	I2400M_MT_CMD_MODE_OF_OP	= 0x5603,
+	I2400M_MT_CMD_RESET_DEVICE	= 0x5604,
+	I2400M_MT_CMD_MONITOR_CONTROL   = 0x5605,
+	I2400M_MT_CMD_ENTER_POWERSAVE   = 0x5606,
+	I2400M_MT_GET_TLS_OPERATION_RESULT = 0x6201,
+	I2400M_MT_SET_EAP_SUCCESS       = 0x6402,
+	I2400M_MT_SET_EAP_FAIL          = 0x6403,
+	I2400M_MT_SET_EAP_KEY          	= 0x6404,
+	I2400M_MT_CMD_SEND_EAP_RESPONSE = 0x6602,
+	I2400M_MT_REPORT_SCAN_RESULT    = 0xc002,
+	I2400M_MT_REPORT_STATE		= 0xd002,
+	I2400M_MT_REPORT_POWERSAVE_READY = 0xd005,
+	I2400M_MT_REPORT_EAP_REQUEST    = 0xe002,
+	I2400M_MT_REPORT_EAP_RESTART    = 0xe003,
+	I2400M_MT_REPORT_ALT_ACCEPT    	= 0xe004,
+	I2400M_MT_REPORT_KEY_REQUEST 	= 0xe005,
+};
+
+
+/*
+ * Message Ack Status codes
+ *
+ * When a message is replied-to, this status is reported.
+ */
+enum i2400m_ms {
+	I2400M_MS_DONE_OK                  = 0,
+	I2400M_MS_DONE_IN_PROGRESS         = 1,
+	I2400M_MS_INVALID_OP               = 2,
+	I2400M_MS_BAD_STATE                = 3,
+	I2400M_MS_ILLEGAL_VALUE            = 4,
+	I2400M_MS_MISSING_PARAMS           = 5,
+	I2400M_MS_VERSION_ERROR            = 6,
+	I2400M_MS_ACCESSIBILITY_ERROR      = 7,
+	I2400M_MS_BUSY                     = 8,
+	I2400M_MS_CORRUPTED_TLV            = 9,
+	I2400M_MS_UNINITIALIZED            = 10,
+	I2400M_MS_UNKNOWN_ERROR            = 11,
+	I2400M_MS_PRODUCTION_ERROR         = 12,
+	I2400M_MS_NO_RF                    = 13,
+	I2400M_MS_NOT_READY_FOR_POWERSAVE  = 14,
+	I2400M_MS_THERMAL_CRITICAL         = 15,
+	I2400M_MS_MAX
+};
+
+
+/**
+ * i2400m_tlv - enumeration of the different types of TLVs
+ *
+ * TLVs stand for type-length-value and are the header for a payload
+ * composed of almost anything. Each payload has a type assigned
+ * and a length.
+ */
+enum i2400m_tlv {
+	I2400M_TLV_L4_MESSAGE_VERSIONS = 129,
+	I2400M_TLV_SYSTEM_STATE = 141,
+	I2400M_TLV_MEDIA_STATUS = 161,
+	I2400M_TLV_RF_OPERATION = 162,
+	I2400M_TLV_RF_STATUS = 163,
+	I2400M_TLV_DEVICE_RESET_TYPE = 132,
+	I2400M_TLV_CONFIG_IDLE_PARAMETERS = 601,
+	I2400M_TLV_CONFIG_IDLE_TIMEOUT = 611,
+	I2400M_TLV_CONFIG_D2H_DATA_FORMAT = 614,
+	I2400M_TLV_CONFIG_DL_HOST_REORDER = 615,
+};
+
+
+struct i2400m_tlv_hdr {
+	__le16 type;
+	__le16 length;		/* payload's */
+	__u8   pl[0];
+} __attribute__((packed));
+
+
+struct i2400m_l3l4_hdr {
+	__le16 type;
+	__le16 length;		/* payload's */
+	__le16 version;
+	__le16 resv1;
+	__le16 status;
+	__le16 resv2;
+	struct i2400m_tlv_hdr pl[0];
+} __attribute__((packed));
+
+
+/**
+ * i2400m_system_state - different states of the device
+ */
+enum i2400m_system_state {
+	I2400M_SS_UNINITIALIZED = 1,
+	I2400M_SS_INIT,
+	I2400M_SS_READY,
+	I2400M_SS_SCAN,
+	I2400M_SS_STANDBY,
+	I2400M_SS_CONNECTING,
+	I2400M_SS_WIMAX_CONNECTED,
+	I2400M_SS_DATA_PATH_CONNECTED,
+	I2400M_SS_IDLE,
+	I2400M_SS_DISCONNECTING,
+	I2400M_SS_OUT_OF_ZONE,
+	I2400M_SS_SLEEPACTIVE,
+	I2400M_SS_PRODUCTION,
+	I2400M_SS_CONFIG,
+	I2400M_SS_RF_OFF,
+	I2400M_SS_RF_SHUTDOWN,
+	I2400M_SS_DEVICE_DISCONNECT,
+	I2400M_SS_MAX,
+};
+
+
+/**
+ * i2400m_tlv_system_state - report on the state of the system
+ *
+ * @state: see enum i2400m_system_state
+ */
+struct i2400m_tlv_system_state {
+	struct i2400m_tlv_hdr hdr;
+	__le32 state;
+} __attribute__((packed));
+
+
+struct i2400m_tlv_l4_message_versions {
+	struct i2400m_tlv_hdr hdr;
+	__le16 major;
+	__le16 minor;
+	__le16 branch;
+	__le16 reserved;
+} __attribute__((packed));
+
+
+struct i2400m_tlv_detailed_device_info {
+	struct i2400m_tlv_hdr hdr;
+	__u8 reserved1[400];
+	__u8 mac_address[ETH_ALEN];
+	__u8 reserved2[2];
+} __attribute__((packed));
+
+
+enum i2400m_rf_switch_status {
+	I2400M_RF_SWITCH_ON = 1,
+	I2400M_RF_SWITCH_OFF = 2,
+};
+
+struct i2400m_tlv_rf_switches_status {
+	struct i2400m_tlv_hdr hdr;
+	__u8 sw_rf_switch;	/* 1 ON, 2 OFF */
+	__u8 hw_rf_switch;	/* 1 ON, 2 OFF */
+	__u8 reserved[2];
+} __attribute__((packed));
+
+
+enum {
+	i2400m_rf_operation_on = 1,
+	i2400m_rf_operation_off = 2
+};
+
+struct i2400m_tlv_rf_operation {
+	struct i2400m_tlv_hdr hdr;
+	__le32 status;	/* 1 ON, 2 OFF */
+} __attribute__((packed));
+
+
+enum i2400m_tlv_reset_type {
+	I2400M_RESET_TYPE_COLD = 1,
+	I2400M_RESET_TYPE_WARM
+};
+
+struct i2400m_tlv_device_reset_type {
+	struct i2400m_tlv_hdr hdr;
+	__le32 reset_type;
+} __attribute__((packed));
+
+
+struct i2400m_tlv_config_idle_parameters {
+	struct i2400m_tlv_hdr hdr;
+	__le32 idle_timeout;	/* 100 to 300000 ms [5min], 100 increments
+				 * 0 disabled */
+	__le32 idle_paging_interval;	/* frames */
+} __attribute__((packed));
+
+
+enum i2400m_media_status {
+	I2400M_MEDIA_STATUS_LINK_UP = 1,
+	I2400M_MEDIA_STATUS_LINK_DOWN,
+	I2400M_MEDIA_STATUS_LINK_RENEW,
+};
+
+struct i2400m_tlv_media_status {
+	struct i2400m_tlv_hdr hdr;
+	__le32 media_status;
+} __attribute__((packed));
+
+
+/* New in v1.4 */
+struct i2400m_tlv_config_idle_timeout {
+	struct i2400m_tlv_hdr hdr;
+	__le32 timeout;	/* 100 to 300000 ms [5min], 100 increments
+			 * 0 disabled */
+} __attribute__((packed));
+
+/* New in v1.4 -- for backward compat, will be removed */
+struct i2400m_tlv_config_d2h_data_format {
+	struct i2400m_tlv_hdr hdr;
+	__u8 format; 		/* 0 old format, 1 enhanced */
+	__u8 reserved[3];
+} __attribute__((packed));
+
+/* New in v1.4 */
+struct i2400m_tlv_config_dl_host_reorder {
+	struct i2400m_tlv_hdr hdr;
+	__u8 reorder; 		/* 0 disabled, 1 enabled */
+	__u8 reserved[3];
+} __attribute__((packed));
+
+
+#endif /* #ifndef __LINUX__WIMAX__I2400M_H__ */
diff --git a/drivers/staging/wimax/i2400m/netdev.c b/drivers/staging/wimax/i2400m/netdev.c
new file mode 100644
index 000000000000..a7fcbceb6e6b
--- /dev/null
+++ b/drivers/staging/wimax/i2400m/netdev.c
@@ -0,0 +1,603 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * Glue with the networking stack
+ *
+ * Copyright (C) 2007 Intel Corporation <linux-wimax@intel.com>
+ * Yanir Lubetkin <yanirx.lubetkin@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *
+ * This implements an ethernet device for the i2400m.
+ *
+ * We fake being an ethernet device to simplify the support from user
+ * space and from the other side. The world is (sadly) configured to
+ * take in only Ethernet devices...
+ *
+ * Because of this, when using firmwares <= v1.3, there is an
+ * copy-each-rxed-packet overhead on the RX path. Each IP packet has
+ * to be reallocated to add an ethernet header (as there is no space
+ * in what we get from the device). This is a known drawback and
+ * firmwares >= 1.4 add header space that can be used to insert the
+ * ethernet header without having to reallocate and copy.
+ *
+ * TX error handling is tricky; because we have to FIFO/queue the
+ * buffers for transmission (as the hardware likes it aggregated), we
+ * just give the skb to the TX subsystem and by the time it is
+ * transmitted, we have long forgotten about it. So we just don't care
+ * too much about it.
+ *
+ * Note that when the device is in idle mode with the basestation, we
+ * need to negotiate coming back up online. That involves negotiation
+ * and possible user space interaction. Thus, we defer to a workqueue
+ * to do all that. By default, we only queue a single packet and drop
+ * the rest, as potentially the time to go back from idle to normal is
+ * long.
+ *
+ * ROADMAP
+ *
+ * i2400m_open         Called on ifconfig up
+ * i2400m_stop         Called on ifconfig down
+ *
+ * i2400m_hard_start_xmit Called by the network stack to send a packet
+ *   i2400m_net_wake_tx	  Wake up device from basestation-IDLE & TX
+ *     i2400m_wake_tx_work
+ *       i2400m_cmd_exit_idle
+ *       i2400m_tx
+ *   i2400m_net_tx        TX a data frame
+ *     i2400m_tx
+ *
+ * i2400m_change_mtu      Called on ifconfig mtu XXX
+ *
+ * i2400m_tx_timeout      Called when the device times out
+ *
+ * i2400m_net_rx          Called by the RX code when a data frame is
+ *                        available (firmware <= 1.3)
+ * i2400m_net_erx         Called by the RX code when a data frame is
+ *                        available (firmware >= 1.4).
+ * i2400m_netdev_setup    Called to setup all the netdev stuff from
+ *                        alloc_netdev.
+ */
+#include <linux/if_arp.h>
+#include <linux/slab.h>
+#include <linux/netdevice.h>
+#include <linux/ethtool.h>
+#include <linux/export.h>
+#include "i2400m.h"
+
+
+#define D_SUBMODULE netdev
+#include "debug-levels.h"
+
+enum {
+/* netdev interface */
+	/* 20 secs? yep, this is the maximum timeout that the device
+	 * might take to get out of IDLE / negotiate it with the base
+	 * station. We add 1sec for good measure. */
+	I2400M_TX_TIMEOUT = 21 * HZ,
+	/*
+	 * Experimentation has determined that, 20 to be a good value
+	 * for minimizing the jitter in the throughput.
+	 */
+	I2400M_TX_QLEN = 20,
+};
+
+
+static
+int i2400m_open(struct net_device *net_dev)
+{
+	int result;
+	struct i2400m *i2400m = net_dev_to_i2400m(net_dev);
+	struct device *dev = i2400m_dev(i2400m);
+
+	d_fnstart(3, dev, "(net_dev %p [i2400m %p])\n", net_dev, i2400m);
+	/* Make sure we wait until init is complete... */
+	mutex_lock(&i2400m->init_mutex);
+	if (i2400m->updown)
+		result = 0;
+	else
+		result = -EBUSY;
+	mutex_unlock(&i2400m->init_mutex);
+	d_fnend(3, dev, "(net_dev %p [i2400m %p]) = %d\n",
+		net_dev, i2400m, result);
+	return result;
+}
+
+
+static
+int i2400m_stop(struct net_device *net_dev)
+{
+	struct i2400m *i2400m = net_dev_to_i2400m(net_dev);
+	struct device *dev = i2400m_dev(i2400m);
+
+	d_fnstart(3, dev, "(net_dev %p [i2400m %p])\n", net_dev, i2400m);
+	i2400m_net_wake_stop(i2400m);
+	d_fnend(3, dev, "(net_dev %p [i2400m %p]) = 0\n", net_dev, i2400m);
+	return 0;
+}
+
+
+/*
+ * Wake up the device and transmit a held SKB, then restart the net queue
+ *
+ * When the device goes into basestation-idle mode, we need to tell it
+ * to exit that mode; it will negotiate with the base station, user
+ * space may have to intervene to rehandshake crypto and then tell us
+ * when it is ready to transmit the packet we have "queued". Still we
+ * need to give it sometime after it reports being ok.
+ *
+ * On error, there is not much we can do. If the error was on TX, we
+ * still wake the queue up to see if the next packet will be luckier.
+ *
+ * If _cmd_exit_idle() fails...well, it could be many things; most
+ * commonly it is that something else took the device out of IDLE mode
+ * (for example, the base station). In that case we get an -EILSEQ and
+ * we are just going to ignore that one. If the device is back to
+ * connected, then fine -- if it is someother state, the packet will
+ * be dropped anyway.
+ */
+void i2400m_wake_tx_work(struct work_struct *ws)
+{
+	int result;
+	struct i2400m *i2400m = container_of(ws, struct i2400m, wake_tx_ws);
+	struct net_device *net_dev = i2400m->wimax_dev.net_dev;
+	struct device *dev = i2400m_dev(i2400m);
+	struct sk_buff *skb;
+	unsigned long flags;
+
+	spin_lock_irqsave(&i2400m->tx_lock, flags);
+	skb = i2400m->wake_tx_skb;
+	i2400m->wake_tx_skb = NULL;
+	spin_unlock_irqrestore(&i2400m->tx_lock, flags);
+
+	d_fnstart(3, dev, "(ws %p i2400m %p skb %p)\n", ws, i2400m, skb);
+	result = -EINVAL;
+	if (skb == NULL) {
+		dev_err(dev, "WAKE&TX: skb disappeared!\n");
+		goto out_put;
+	}
+	/* If we have, somehow, lost the connection after this was
+	 * queued, don't do anything; this might be the device got
+	 * reset or just disconnected. */
+	if (unlikely(!netif_carrier_ok(net_dev)))
+		goto out_kfree;
+	result = i2400m_cmd_exit_idle(i2400m);
+	if (result == -EILSEQ)
+		result = 0;
+	if (result < 0) {
+		dev_err(dev, "WAKE&TX: device didn't get out of idle: "
+			"%d - resetting\n", result);
+		i2400m_reset(i2400m, I2400M_RT_BUS);
+		goto error;
+	}
+	result = wait_event_timeout(i2400m->state_wq,
+				    i2400m->state != I2400M_SS_IDLE,
+				    net_dev->watchdog_timeo - HZ/2);
+	if (result == 0)
+		result = -ETIMEDOUT;
+	if (result < 0) {
+		dev_err(dev, "WAKE&TX: error waiting for device to exit IDLE: "
+			"%d - resetting\n", result);
+		i2400m_reset(i2400m, I2400M_RT_BUS);
+		goto error;
+	}
+	msleep(20);	/* device still needs some time or it drops it */
+	result = i2400m_tx(i2400m, skb->data, skb->len, I2400M_PT_DATA);
+error:
+	netif_wake_queue(net_dev);
+out_kfree:
+	kfree_skb(skb);	/* refcount transferred by _hard_start_xmit() */
+out_put:
+	i2400m_put(i2400m);
+	d_fnend(3, dev, "(ws %p i2400m %p skb %p) = void [%d]\n",
+		ws, i2400m, skb, result);
+}
+
+
+/*
+ * Prepare the data payload TX header
+ *
+ * The i2400m expects a 4 byte header in front of a data packet.
+ *
+ * Because we pretend to be an ethernet device, this packet comes with
+ * an ethernet header. Pull it and push our header.
+ */
+static
+void i2400m_tx_prep_header(struct sk_buff *skb)
+{
+	struct i2400m_pl_data_hdr *pl_hdr;
+	skb_pull(skb, ETH_HLEN);
+	pl_hdr = skb_push(skb, sizeof(*pl_hdr));
+	pl_hdr->reserved = 0;
+}
+
+
+
+/*
+ * Cleanup resources acquired during i2400m_net_wake_tx()
+ *
+ * This is called by __i2400m_dev_stop and means we have to make sure
+ * the workqueue is flushed from any pending work.
+ */
+void i2400m_net_wake_stop(struct i2400m *i2400m)
+{
+	struct device *dev = i2400m_dev(i2400m);
+	struct sk_buff *wake_tx_skb;
+	unsigned long flags;
+
+	d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
+	/*
+	 * See i2400m_hard_start_xmit(), references are taken there and
+	 * here we release them if the packet was still pending.
+	 */
+	cancel_work_sync(&i2400m->wake_tx_ws);
+
+	spin_lock_irqsave(&i2400m->tx_lock, flags);
+	wake_tx_skb = i2400m->wake_tx_skb;
+	i2400m->wake_tx_skb = NULL;
+	spin_unlock_irqrestore(&i2400m->tx_lock, flags);
+
+	if (wake_tx_skb) {
+		i2400m_put(i2400m);
+		kfree_skb(wake_tx_skb);
+	}
+
+	d_fnend(3, dev, "(i2400m %p) = void\n", i2400m);
+}
+
+
+/*
+ * TX an skb to an idle device
+ *
+ * When the device is in basestation-idle mode, we need to wake it up
+ * and then TX. So we queue a work_struct for doing so.
+ *
+ * We need to get an extra ref for the skb (so it is not dropped), as
+ * well as be careful not to queue more than one request (won't help
+ * at all). If more than one request comes or there are errors, we
+ * just drop the packets (see i2400m_hard_start_xmit()).
+ */
+static
+int i2400m_net_wake_tx(struct i2400m *i2400m, struct net_device *net_dev,
+		       struct sk_buff *skb)
+{
+	int result;
+	struct device *dev = i2400m_dev(i2400m);
+	unsigned long flags;
+
+	d_fnstart(3, dev, "(skb %p net_dev %p)\n", skb, net_dev);
+	if (net_ratelimit()) {
+		d_printf(3, dev, "WAKE&NETTX: "
+			 "skb %p sending %d bytes to radio\n",
+			 skb, skb->len);
+		d_dump(4, dev, skb->data, skb->len);
+	}
+	/* We hold a ref count for i2400m and skb, so when
+	 * stopping() the device, we need to cancel that work
+	 * and if pending, release those resources. */
+	result = 0;
+	spin_lock_irqsave(&i2400m->tx_lock, flags);
+	if (!i2400m->wake_tx_skb) {
+		netif_stop_queue(net_dev);
+		i2400m_get(i2400m);
+		i2400m->wake_tx_skb = skb_get(skb);	/* transfer ref count */
+		i2400m_tx_prep_header(skb);
+		result = schedule_work(&i2400m->wake_tx_ws);
+		WARN_ON(result == 0);
+	}
+	spin_unlock_irqrestore(&i2400m->tx_lock, flags);
+	if (result == 0) {
+		/* Yes, this happens even if we stopped the
+		 * queue -- blame the queue disciplines that
+		 * queue without looking -- I guess there is a reason
+		 * for that. */
+		if (net_ratelimit())
+			d_printf(1, dev, "NETTX: device exiting idle, "
+				 "dropping skb %p, queue running %d\n",
+				 skb, netif_queue_stopped(net_dev));
+		result = -EBUSY;
+	}
+	d_fnend(3, dev, "(skb %p net_dev %p) = %d\n", skb, net_dev, result);
+	return result;
+}
+
+
+/*
+ * Transmit a packet to the base station on behalf of the network stack.
+ *
+ * Returns: 0 if ok, < 0 errno code on error.
+ *
+ * We need to pull the ethernet header and add the hardware header,
+ * which is currently set to all zeroes and reserved.
+ */
+static
+int i2400m_net_tx(struct i2400m *i2400m, struct net_device *net_dev,
+		  struct sk_buff *skb)
+{
+	int result;
+	struct device *dev = i2400m_dev(i2400m);
+
+	d_fnstart(3, dev, "(i2400m %p net_dev %p skb %p)\n",
+		  i2400m, net_dev, skb);
+	/* FIXME: check eth hdr, only IPv4 is routed by the device as of now */
+	netif_trans_update(net_dev);
+	i2400m_tx_prep_header(skb);
+	d_printf(3, dev, "NETTX: skb %p sending %d bytes to radio\n",
+		 skb, skb->len);
+	d_dump(4, dev, skb->data, skb->len);
+	result = i2400m_tx(i2400m, skb->data, skb->len, I2400M_PT_DATA);
+	d_fnend(3, dev, "(i2400m %p net_dev %p skb %p) = %d\n",
+		i2400m, net_dev, skb, result);
+	return result;
+}
+
+
+/*
+ * Transmit a packet to the base station on behalf of the network stack
+ *
+ *
+ * Returns: NETDEV_TX_OK (always, even in case of error)
+ *
+ * In case of error, we just drop it. Reasons:
+ *
+ *  - we add a hw header to each skb, and if the network stack
+ *    retries, we have no way to know if that skb has it or not.
+ *
+ *  - network protocols have their own drop-recovery mechanisms
+ *
+ *  - there is not much else we can do
+ *
+ * If the device is idle, we need to wake it up; that is an operation
+ * that will sleep. See i2400m_net_wake_tx() for details.
+ */
+static
+netdev_tx_t i2400m_hard_start_xmit(struct sk_buff *skb,
+					 struct net_device *net_dev)
+{
+	struct i2400m *i2400m = net_dev_to_i2400m(net_dev);
+	struct device *dev = i2400m_dev(i2400m);
+	int result = -1;
+
+	d_fnstart(3, dev, "(skb %p net_dev %p)\n", skb, net_dev);
+
+	if (skb_cow_head(skb, 0))
+		goto drop;
+
+	if (i2400m->state == I2400M_SS_IDLE)
+		result = i2400m_net_wake_tx(i2400m, net_dev, skb);
+	else
+		result = i2400m_net_tx(i2400m, net_dev, skb);
+	if (result <  0) {
+drop:
+		net_dev->stats.tx_dropped++;
+	} else {
+		net_dev->stats.tx_packets++;
+		net_dev->stats.tx_bytes += skb->len;
+	}
+	dev_kfree_skb(skb);
+	d_fnend(3, dev, "(skb %p net_dev %p) = %d\n", skb, net_dev, result);
+	return NETDEV_TX_OK;
+}
+
+
+static
+void i2400m_tx_timeout(struct net_device *net_dev, unsigned int txqueue)
+{
+	/*
+	 * We might want to kick the device
+	 *
+	 * There is not much we can do though, as the device requires
+	 * that we send the data aggregated. By the time we receive
+	 * this, there might be data pending to be sent or not...
+	 */
+	net_dev->stats.tx_errors++;
+}
+
+
+/*
+ * Create a fake ethernet header
+ *
+ * For emulating an ethernet device, every received IP header has to
+ * be prefixed with an ethernet header. Fake it with the given
+ * protocol.
+ */
+static
+void i2400m_rx_fake_eth_header(struct net_device *net_dev,
+			       void *_eth_hdr, __be16 protocol)
+{
+	struct i2400m *i2400m = net_dev_to_i2400m(net_dev);
+	struct ethhdr *eth_hdr = _eth_hdr;
+
+	memcpy(eth_hdr->h_dest, net_dev->dev_addr, sizeof(eth_hdr->h_dest));
+	memcpy(eth_hdr->h_source, i2400m->src_mac_addr,
+	       sizeof(eth_hdr->h_source));
+	eth_hdr->h_proto = protocol;
+}
+
+
+/*
+ * i2400m_net_rx - pass a network packet to the stack
+ *
+ * @i2400m: device instance
+ * @skb_rx: the skb where the buffer pointed to by @buf is
+ * @i: 1 if payload is the only one
+ * @buf: pointer to the buffer containing the data
+ * @len: buffer's length
+ *
+ * This is only used now for the v1.3 firmware. It will be deprecated
+ * in >= 2.6.31.
+ *
+ * Note that due to firmware limitations, we don't have space to add
+ * an ethernet header, so we need to copy each packet. Firmware
+ * versions >= v1.4 fix this [see i2400m_net_erx()].
+ *
+ * We just clone the skb and set it up so that it's skb->data pointer
+ * points to "buf" and it's length.
+ *
+ * Note that if the payload is the last (or the only one) in a
+ * multi-payload message, we don't clone the SKB but just reuse it.
+ *
+ * This function is normally run from a thread context. However, we
+ * still use netif_rx() instead of netif_receive_skb() as was
+ * recommended in the mailing list. Reason is in some stress tests
+ * when sending/receiving a lot of data we seem to hit a softlock in
+ * the kernel's TCP implementation [aroudn tcp_delay_timer()]. Using
+ * netif_rx() took care of the issue.
+ *
+ * This is, of course, still open to do more research on why running
+ * with netif_receive_skb() hits this softlock. FIXME.
+ *
+ * FIXME: currently we don't do any efforts at distinguishing if what
+ * we got was an IPv4 or IPv6 header, to setup the protocol field
+ * correctly.
+ */
+void i2400m_net_rx(struct i2400m *i2400m, struct sk_buff *skb_rx,
+		   unsigned i, const void *buf, int buf_len)
+{
+	struct net_device *net_dev = i2400m->wimax_dev.net_dev;
+	struct device *dev = i2400m_dev(i2400m);
+	struct sk_buff *skb;
+
+	d_fnstart(2, dev, "(i2400m %p buf %p buf_len %d)\n",
+		  i2400m, buf, buf_len);
+	if (i) {
+		skb = skb_get(skb_rx);
+		d_printf(2, dev, "RX: reusing first payload skb %p\n", skb);
+		skb_pull(skb, buf - (void *) skb->data);
+		skb_trim(skb, (void *) skb_end_pointer(skb) - buf);
+	} else {
+		/* Yes, this is bad -- a lot of overhead -- see
+		 * comments at the top of the file */
+		skb = __netdev_alloc_skb(net_dev, buf_len, GFP_KERNEL);
+		if (skb == NULL) {
+			dev_err(dev, "NETRX: no memory to realloc skb\n");
+			net_dev->stats.rx_dropped++;
+			goto error_skb_realloc;
+		}
+		skb_put_data(skb, buf, buf_len);
+	}
+	i2400m_rx_fake_eth_header(i2400m->wimax_dev.net_dev,
+				  skb->data - ETH_HLEN,
+				  cpu_to_be16(ETH_P_IP));
+	skb_set_mac_header(skb, -ETH_HLEN);
+	skb->dev = i2400m->wimax_dev.net_dev;
+	skb->protocol = htons(ETH_P_IP);
+	net_dev->stats.rx_packets++;
+	net_dev->stats.rx_bytes += buf_len;
+	d_printf(3, dev, "NETRX: receiving %d bytes to network stack\n",
+		buf_len);
+	d_dump(4, dev, buf, buf_len);
+	netif_rx_ni(skb);	/* see notes in function header */
+error_skb_realloc:
+	d_fnend(2, dev, "(i2400m %p buf %p buf_len %d) = void\n",
+		i2400m, buf, buf_len);
+}
+
+
+/*
+ * i2400m_net_erx - pass a network packet to the stack (extended version)
+ *
+ * @i2400m: device descriptor
+ * @skb: the skb where the packet is - the skb should be set to point
+ *     at the IP packet; this function will add ethernet headers if
+ *     needed.
+ * @cs: packet type
+ *
+ * This is only used now for firmware >= v1.4. Note it is quite
+ * similar to i2400m_net_rx() (used only for v1.3 firmware).
+ *
+ * This function is normally run from a thread context. However, we
+ * still use netif_rx() instead of netif_receive_skb() as was
+ * recommended in the mailing list. Reason is in some stress tests
+ * when sending/receiving a lot of data we seem to hit a softlock in
+ * the kernel's TCP implementation [aroudn tcp_delay_timer()]. Using
+ * netif_rx() took care of the issue.
+ *
+ * This is, of course, still open to do more research on why running
+ * with netif_receive_skb() hits this softlock. FIXME.
+ */
+void i2400m_net_erx(struct i2400m *i2400m, struct sk_buff *skb,
+		    enum i2400m_cs cs)
+{
+	struct net_device *net_dev = i2400m->wimax_dev.net_dev;
+	struct device *dev = i2400m_dev(i2400m);
+
+	d_fnstart(2, dev, "(i2400m %p skb %p [%u] cs %d)\n",
+		  i2400m, skb, skb->len, cs);
+	switch(cs) {
+	case I2400M_CS_IPV4_0:
+	case I2400M_CS_IPV4:
+		i2400m_rx_fake_eth_header(i2400m->wimax_dev.net_dev,
+					  skb->data - ETH_HLEN,
+					  cpu_to_be16(ETH_P_IP));
+		skb_set_mac_header(skb, -ETH_HLEN);
+		skb->dev = i2400m->wimax_dev.net_dev;
+		skb->protocol = htons(ETH_P_IP);
+		net_dev->stats.rx_packets++;
+		net_dev->stats.rx_bytes += skb->len;
+		break;
+	default:
+		dev_err(dev, "ERX: BUG? CS type %u unsupported\n", cs);
+		goto error;
+
+	}
+	d_printf(3, dev, "ERX: receiving %d bytes to the network stack\n",
+		 skb->len);
+	d_dump(4, dev, skb->data, skb->len);
+	netif_rx_ni(skb);	/* see notes in function header */
+error:
+	d_fnend(2, dev, "(i2400m %p skb %p [%u] cs %d) = void\n",
+		i2400m, skb, skb->len, cs);
+}
+
+static const struct net_device_ops i2400m_netdev_ops = {
+	.ndo_open = i2400m_open,
+	.ndo_stop = i2400m_stop,
+	.ndo_start_xmit = i2400m_hard_start_xmit,
+	.ndo_tx_timeout = i2400m_tx_timeout,
+};
+
+static void i2400m_get_drvinfo(struct net_device *net_dev,
+			       struct ethtool_drvinfo *info)
+{
+	struct i2400m *i2400m = net_dev_to_i2400m(net_dev);
+
+	strlcpy(info->driver, KBUILD_MODNAME, sizeof(info->driver));
+	strlcpy(info->fw_version, i2400m->fw_name ? : "",
+		sizeof(info->fw_version));
+	if (net_dev->dev.parent)
+		strlcpy(info->bus_info, dev_name(net_dev->dev.parent),
+			sizeof(info->bus_info));
+}
+
+static const struct ethtool_ops i2400m_ethtool_ops = {
+	.get_drvinfo = i2400m_get_drvinfo,
+	.get_link = ethtool_op_get_link,
+};
+
+/**
+ * i2400m_netdev_setup - Setup setup @net_dev's i2400m private data
+ *
+ * Called by alloc_netdev()
+ */
+void i2400m_netdev_setup(struct net_device *net_dev)
+{
+	d_fnstart(3, NULL, "(net_dev %p)\n", net_dev);
+	ether_setup(net_dev);
+	net_dev->mtu = I2400M_MAX_MTU;
+	net_dev->min_mtu = 0;
+	net_dev->max_mtu = I2400M_MAX_MTU;
+	net_dev->tx_queue_len = I2400M_TX_QLEN;
+	net_dev->features =
+		  NETIF_F_VLAN_CHALLENGED
+		| NETIF_F_HIGHDMA;
+	net_dev->flags =
+		IFF_NOARP		/* i2400m is apure IP device */
+		& (~IFF_BROADCAST	/* i2400m is P2P */
+		   & ~IFF_MULTICAST);
+	net_dev->watchdog_timeo = I2400M_TX_TIMEOUT;
+	net_dev->netdev_ops = &i2400m_netdev_ops;
+	net_dev->ethtool_ops = &i2400m_ethtool_ops;
+	d_fnend(3, NULL, "(net_dev %p) = void\n", net_dev);
+}
+EXPORT_SYMBOL_GPL(i2400m_netdev_setup);
+
diff --git a/drivers/staging/wimax/i2400m/op-rfkill.c b/drivers/staging/wimax/i2400m/op-rfkill.c
new file mode 100644
index 000000000000..fbddf2e18c14
--- /dev/null
+++ b/drivers/staging/wimax/i2400m/op-rfkill.c
@@ -0,0 +1,196 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * Implement backend for the WiMAX stack rfkill support
+ *
+ * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *
+ * The WiMAX kernel stack integrates into RF-Kill and keeps the
+ * switches's status. We just need to:
+ *
+ * - report changes in the HW RF Kill switch [with
+ *   wimax_rfkill_{sw,hw}_report(), which happens when we detect those
+ *   indications coming through hardware reports]. We also do it on
+ *   initialization to let the stack know the initial HW state.
+ *
+ * - implement indications from the stack to change the SW RF Kill
+ *   switch (coming from sysfs, the wimax stack or user space).
+ */
+#include "i2400m.h"
+#include "linux-wimax-i2400m.h"
+#include <linux/slab.h>
+
+
+
+#define D_SUBMODULE rfkill
+#include "debug-levels.h"
+
+/*
+ * Return true if the i2400m radio is in the requested wimax_rf_state state
+ *
+ */
+static
+int i2400m_radio_is(struct i2400m *i2400m, enum wimax_rf_state state)
+{
+	if (state == WIMAX_RF_OFF)
+		return i2400m->state == I2400M_SS_RF_OFF
+			|| i2400m->state == I2400M_SS_RF_SHUTDOWN;
+	else if (state == WIMAX_RF_ON)
+		/* state == WIMAX_RF_ON */
+		return i2400m->state != I2400M_SS_RF_OFF
+			&& i2400m->state != I2400M_SS_RF_SHUTDOWN;
+	else {
+		BUG();
+		return -EINVAL;	/* shut gcc warnings on certain arches */
+	}
+}
+
+
+/*
+ * WiMAX stack operation: implement SW RFKill toggling
+ *
+ * @wimax_dev: device descriptor
+ * @skb: skb where the message has been received; skb->data is
+ *       expected to point to the message payload.
+ * @genl_info: passed by the generic netlink layer
+ *
+ * Generic Netlink will call this function when a message is sent from
+ * userspace to change the software RF-Kill switch status.
+ *
+ * This function will set the device's software RF-Kill switch state to
+ * match what is requested.
+ *
+ * NOTE: the i2400m has a strict state machine; we can only set the
+ *       RF-Kill switch when it is on, the HW RF-Kill is on and the
+ *       device is initialized. So we ignore errors steaming from not
+ *       being in the right state (-EILSEQ).
+ */
+int i2400m_op_rfkill_sw_toggle(struct wimax_dev *wimax_dev,
+			       enum wimax_rf_state state)
+{
+	int result;
+	struct i2400m *i2400m = wimax_dev_to_i2400m(wimax_dev);
+	struct device *dev = i2400m_dev(i2400m);
+	struct sk_buff *ack_skb;
+	struct {
+		struct i2400m_l3l4_hdr hdr;
+		struct i2400m_tlv_rf_operation sw_rf;
+	} __packed *cmd;
+	char strerr[32];
+
+	d_fnstart(4, dev, "(wimax_dev %p state %d)\n", wimax_dev, state);
+
+	result = -ENOMEM;
+	cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
+	if (cmd == NULL)
+		goto error_alloc;
+	cmd->hdr.type = cpu_to_le16(I2400M_MT_CMD_RF_CONTROL);
+	cmd->hdr.length = sizeof(cmd->sw_rf);
+	cmd->hdr.version = cpu_to_le16(I2400M_L3L4_VERSION);
+	cmd->sw_rf.hdr.type = cpu_to_le16(I2400M_TLV_RF_OPERATION);
+	cmd->sw_rf.hdr.length = cpu_to_le16(sizeof(cmd->sw_rf.status));
+	switch (state) {
+	case WIMAX_RF_OFF:	/* RFKILL ON, radio OFF */
+		cmd->sw_rf.status = cpu_to_le32(2);
+		break;
+	case WIMAX_RF_ON:	/* RFKILL OFF, radio ON */
+		cmd->sw_rf.status = cpu_to_le32(1);
+		break;
+	default:
+		BUG();
+	}
+
+	ack_skb = i2400m_msg_to_dev(i2400m, cmd, sizeof(*cmd));
+	result = PTR_ERR(ack_skb);
+	if (IS_ERR(ack_skb)) {
+		dev_err(dev, "Failed to issue 'RF Control' command: %d\n",
+			result);
+		goto error_msg_to_dev;
+	}
+	result = i2400m_msg_check_status(wimax_msg_data(ack_skb),
+					 strerr, sizeof(strerr));
+	if (result < 0) {
+		dev_err(dev, "'RF Control' (0x%04x) command failed: %d - %s\n",
+			I2400M_MT_CMD_RF_CONTROL, result, strerr);
+		goto error_cmd;
+	}
+
+	/* Now we wait for the state to change to RADIO_OFF or RADIO_ON */
+	result = wait_event_timeout(
+		i2400m->state_wq, i2400m_radio_is(i2400m, state),
+		5 * HZ);
+	if (result == 0)
+		result = -ETIMEDOUT;
+	if (result < 0)
+		dev_err(dev, "Error waiting for device to toggle RF state: "
+			"%d\n", result);
+	result = 0;
+error_cmd:
+	kfree_skb(ack_skb);
+error_msg_to_dev:
+error_alloc:
+	d_fnend(4, dev, "(wimax_dev %p state %d) = %d\n",
+		wimax_dev, state, result);
+	kfree(cmd);
+	return result;
+}
+
+
+/*
+ * Inform the WiMAX stack of changes in the RF Kill switches reported
+ * by the device
+ *
+ * @i2400m: device descriptor
+ * @rfss: TLV for RF Switches status; already validated
+ *
+ * NOTE: the reports on RF switch status cannot be trusted
+ *       or used until the device is in a state of RADIO_OFF
+ *       or greater.
+ */
+void i2400m_report_tlv_rf_switches_status(
+	struct i2400m *i2400m,
+	const struct i2400m_tlv_rf_switches_status *rfss)
+{
+	struct device *dev = i2400m_dev(i2400m);
+	enum i2400m_rf_switch_status hw, sw;
+	enum wimax_st wimax_state;
+
+	sw = le32_to_cpu(rfss->sw_rf_switch);
+	hw = le32_to_cpu(rfss->hw_rf_switch);
+
+	d_fnstart(3, dev, "(i2400m %p rfss %p [hw %u sw %u])\n",
+		  i2400m, rfss, hw, sw);
+	/* We only process rw switch evens when the device has been
+	 * fully initialized */
+	wimax_state = wimax_state_get(&i2400m->wimax_dev);
+	if (wimax_state < WIMAX_ST_RADIO_OFF) {
+		d_printf(3, dev, "ignoring RF switches report, state %u\n",
+			 wimax_state);
+		goto out;
+	}
+	switch (sw) {
+	case I2400M_RF_SWITCH_ON:	/* RF Kill disabled (radio on) */
+		wimax_report_rfkill_sw(&i2400m->wimax_dev, WIMAX_RF_ON);
+		break;
+	case I2400M_RF_SWITCH_OFF:	/* RF Kill enabled (radio off) */
+		wimax_report_rfkill_sw(&i2400m->wimax_dev, WIMAX_RF_OFF);
+		break;
+	default:
+		dev_err(dev, "HW BUG? Unknown RF SW state 0x%x\n", sw);
+	}
+
+	switch (hw) {
+	case I2400M_RF_SWITCH_ON:	/* RF Kill disabled (radio on) */
+		wimax_report_rfkill_hw(&i2400m->wimax_dev, WIMAX_RF_ON);
+		break;
+	case I2400M_RF_SWITCH_OFF:	/* RF Kill enabled (radio off) */
+		wimax_report_rfkill_hw(&i2400m->wimax_dev, WIMAX_RF_OFF);
+		break;
+	default:
+		dev_err(dev, "HW BUG? Unknown RF HW state 0x%x\n", hw);
+	}
+out:
+	d_fnend(3, dev, "(i2400m %p rfss %p [hw %u sw %u]) = void\n",
+		i2400m, rfss, hw, sw);
+}
diff --git a/drivers/staging/wimax/i2400m/rx.c b/drivers/staging/wimax/i2400m/rx.c
new file mode 100644
index 000000000000..c9fb619a9e01
--- /dev/null
+++ b/drivers/staging/wimax/i2400m/rx.c
@@ -0,0 +1,1395 @@
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * Handle incoming traffic and deliver it to the control or data planes
+ *
+ *
+ * Copyright (C) 2007-2008 Intel Corporation. All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *
+ * Intel Corporation <linux-wimax@intel.com>
+ * Yanir Lubetkin <yanirx.lubetkin@intel.com>
+ *  - Initial implementation
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *  - Use skb_clone(), break up processing in chunks
+ *  - Split transport/device specific
+ *  - Make buffer size dynamic to exert less memory pressure
+ *  - RX reorder support
+ *
+ * This handles the RX path.
+ *
+ * We receive an RX message from the bus-specific driver, which
+ * contains one or more payloads that have potentially different
+ * destinataries (data or control paths).
+ *
+ * So we just take that payload from the transport specific code in
+ * the form of an skb, break it up in chunks (a cloned skb each in the
+ * case of network packets) and pass it to netdev or to the
+ * command/ack handler (and from there to the WiMAX stack).
+ *
+ * PROTOCOL FORMAT
+ *
+ * The format of the buffer is:
+ *
+ * HEADER                      (struct i2400m_msg_hdr)
+ * PAYLOAD DESCRIPTOR 0        (struct i2400m_pld)
+ * PAYLOAD DESCRIPTOR 1
+ * ...
+ * PAYLOAD DESCRIPTOR N
+ * PAYLOAD 0                   (raw bytes)
+ * PAYLOAD 1
+ * ...
+ * PAYLOAD N
+ *
+ * See tx.c for a deeper description on alignment requirements and
+ * other fun facts of it.
+ *
+ * DATA PACKETS
+ *
+ * In firmwares <= v1.3, data packets have no header for RX, but they
+ * do for TX (currently unused).
+ *
+ * In firmware >= 1.4, RX packets have an extended header (16
+ * bytes). This header conveys information for management of host
+ * reordering of packets (the device offloads storage of the packets
+ * for reordering to the host). Read below for more information.
+ *
+ * The header is used as dummy space to emulate an ethernet header and
+ * thus be able to act as an ethernet device without having to reallocate.
+ *
+ * DATA RX REORDERING
+ *
+ * Starting in firmware v1.4, the device can deliver packets for
+ * delivery with special reordering information; this allows it to
+ * more effectively do packet management when some frames were lost in
+ * the radio traffic.
+ *
+ * Thus, for RX packets that come out of order, the device gives the
+ * driver enough information to queue them properly and then at some
+ * point, the signal to deliver the whole (or part) of the queued
+ * packets to the networking stack. There are 16 such queues.
+ *
+ * This only happens when a packet comes in with the "need reorder"
+ * flag set in the RX header. When such bit is set, the following
+ * operations might be indicated:
+ *
+ *  - reset queue: send all queued packets to the OS
+ *
+ *  - queue: queue a packet
+ *
+ *  - update ws: update the queue's window start and deliver queued
+ *    packets that meet the criteria
+ *
+ *  - queue & update ws: queue a packet, update the window start and
+ *    deliver queued packets that meet the criteria
+ *
+ * (delivery criteria: the packet's [normalized] sequence number is
+ * lower than the new [normalized] window start).
+ *
+ * See the i2400m_roq_*() functions for details.
+ *
+ * ROADMAP
+ *
+ * i2400m_rx
+ *   i2400m_rx_msg_hdr_check
+ *   i2400m_rx_pl_descr_check
+ *   i2400m_rx_payload
+ *     i2400m_net_rx
+ *     i2400m_rx_edata
+ *       i2400m_net_erx
+ *       i2400m_roq_reset
+ *         i2400m_net_erx
+ *       i2400m_roq_queue
+ *         __i2400m_roq_queue
+ *       i2400m_roq_update_ws
+ *         __i2400m_roq_update_ws
+ *           i2400m_net_erx
+ *       i2400m_roq_queue_update_ws
+ *         __i2400m_roq_queue
+ *         __i2400m_roq_update_ws
+ *           i2400m_net_erx
+ *     i2400m_rx_ctl
+ *       i2400m_msg_size_check
+ *       i2400m_report_hook_work    [in a workqueue]
+ *         i2400m_report_hook
+ *       wimax_msg_to_user
+ *       i2400m_rx_ctl_ack
+ *         wimax_msg_to_user_alloc
+ *     i2400m_rx_trace
+ *       i2400m_msg_size_check
+ *       wimax_msg
+ */
+#include <linux/slab.h>
+#include <linux/kernel.h>
+#include <linux/if_arp.h>
+#include <linux/netdevice.h>
+#include <linux/workqueue.h>
+#include <linux/export.h>
+#include <linux/moduleparam.h>
+#include "i2400m.h"
+
+
+#define D_SUBMODULE rx
+#include "debug-levels.h"
+
+static int i2400m_rx_reorder_disabled;	/* 0 (rx reorder enabled) by default */
+module_param_named(rx_reorder_disabled, i2400m_rx_reorder_disabled, int, 0644);
+MODULE_PARM_DESC(rx_reorder_disabled,
+		 "If true, RX reordering will be disabled.");
+
+struct i2400m_report_hook_args {
+	struct sk_buff *skb_rx;
+	const struct i2400m_l3l4_hdr *l3l4_hdr;
+	size_t size;
+	struct list_head list_node;
+};
+
+
+/*
+ * Execute i2400m_report_hook in a workqueue
+ *
+ * Goes over the list of queued reports in i2400m->rx_reports and
+ * processes them.
+ *
+ * NOTE: refcounts on i2400m are not needed because we flush the
+ *     workqueue this runs on (i2400m->work_queue) before destroying
+ *     i2400m.
+ */
+void i2400m_report_hook_work(struct work_struct *ws)
+{
+	struct i2400m *i2400m = container_of(ws, struct i2400m, rx_report_ws);
+	struct device *dev = i2400m_dev(i2400m);
+	struct i2400m_report_hook_args *args, *args_next;
+	LIST_HEAD(list);
+	unsigned long flags;
+
+	while (1) {
+		spin_lock_irqsave(&i2400m->rx_lock, flags);
+		list_splice_init(&i2400m->rx_reports, &list);
+		spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+		if (list_empty(&list))
+			break;
+		else
+			d_printf(1, dev, "processing queued reports\n");
+		list_for_each_entry_safe(args, args_next, &list, list_node) {
+			d_printf(2, dev, "processing queued report %p\n", args);
+			i2400m_report_hook(i2400m, args->l3l4_hdr, args->size);
+			kfree_skb(args->skb_rx);
+			list_del(&args->list_node);
+			kfree(args);
+		}
+	}
+}
+
+
+/*
+ * Flush the list of queued reports
+ */
+static
+void i2400m_report_hook_flush(struct i2400m *i2400m)
+{
+	struct device *dev = i2400m_dev(i2400m);
+	struct i2400m_report_hook_args *args, *args_next;
+	LIST_HEAD(list);
+	unsigned long flags;
+
+	d_printf(1, dev, "flushing queued reports\n");
+	spin_lock_irqsave(&i2400m->rx_lock, flags);
+	list_splice_init(&i2400m->rx_reports, &list);
+	spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+	list_for_each_entry_safe(args, args_next, &list, list_node) {
+		d_printf(2, dev, "flushing queued report %p\n", args);
+		kfree_skb(args->skb_rx);
+		list_del(&args->list_node);
+		kfree(args);
+	}
+}
+
+
+/*
+ * Queue a report for later processing
+ *
+ * @i2400m: device descriptor
+ * @skb_rx: skb that contains the payload (for reference counting)
+ * @l3l4_hdr: pointer to the control
+ * @size: size of the message
+ */
+static
+void i2400m_report_hook_queue(struct i2400m *i2400m, struct sk_buff *skb_rx,
+			      const void *l3l4_hdr, size_t size)
+{
+	struct device *dev = i2400m_dev(i2400m);
+	unsigned long flags;
+	struct i2400m_report_hook_args *args;
+
+	args = kzalloc(sizeof(*args), GFP_NOIO);
+	if (args) {
+		args->skb_rx = skb_get(skb_rx);
+		args->l3l4_hdr = l3l4_hdr;
+		args->size = size;
+		spin_lock_irqsave(&i2400m->rx_lock, flags);
+		list_add_tail(&args->list_node, &i2400m->rx_reports);
+		spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+		d_printf(2, dev, "queued report %p\n", args);
+		rmb();		/* see i2400m->ready's documentation  */
+		if (likely(i2400m->ready))	/* only send if up */
+			queue_work(i2400m->work_queue, &i2400m->rx_report_ws);
+	} else  {
+		if (printk_ratelimit())
+			dev_err(dev, "%s:%u: Can't allocate %zu B\n",
+				__func__, __LINE__, sizeof(*args));
+	}
+}
+
+
+/*
+ * Process an ack to a command
+ *
+ * @i2400m: device descriptor
+ * @payload: pointer to message
+ * @size: size of the message
+ *
+ * Pass the acknodledgment (in an skb) to the thread that is waiting
+ * for it in i2400m->msg_completion.
+ *
+ * We need to coordinate properly with the thread waiting for the
+ * ack. Check if it is waiting or if it is gone. We loose the spinlock
+ * to avoid allocating on atomic contexts (yeah, could use GFP_ATOMIC,
+ * but this is not so speed critical).
+ */
+static
+void i2400m_rx_ctl_ack(struct i2400m *i2400m,
+		       const void *payload, size_t size)
+{
+	struct device *dev = i2400m_dev(i2400m);
+	struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
+	unsigned long flags;
+	struct sk_buff *ack_skb;
+
+	/* Anyone waiting for an answer? */
+	spin_lock_irqsave(&i2400m->rx_lock, flags);
+	if (i2400m->ack_skb != ERR_PTR(-EINPROGRESS)) {
+		dev_err(dev, "Huh? reply to command with no waiters\n");
+		goto error_no_waiter;
+	}
+	spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+
+	ack_skb = wimax_msg_alloc(wimax_dev, NULL, payload, size, GFP_KERNEL);
+
+	/* Check waiter didn't time out waiting for the answer... */
+	spin_lock_irqsave(&i2400m->rx_lock, flags);
+	if (i2400m->ack_skb != ERR_PTR(-EINPROGRESS)) {
+		d_printf(1, dev, "Huh? waiter for command reply cancelled\n");
+		goto error_waiter_cancelled;
+	}
+	if (IS_ERR(ack_skb))
+		dev_err(dev, "CMD/GET/SET ack: cannot allocate SKB\n");
+	i2400m->ack_skb = ack_skb;
+	spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+	complete(&i2400m->msg_completion);
+	return;
+
+error_waiter_cancelled:
+	if (!IS_ERR(ack_skb))
+		kfree_skb(ack_skb);
+error_no_waiter:
+	spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+}
+
+
+/*
+ * Receive and process a control payload
+ *
+ * @i2400m: device descriptor
+ * @skb_rx: skb that contains the payload (for reference counting)
+ * @payload: pointer to message
+ * @size: size of the message
+ *
+ * There are two types of control RX messages: reports (asynchronous,
+ * like your every day interrupts) and 'acks' (reponses to a command,
+ * get or set request).
+ *
+ * If it is a report, we run hooks on it (to extract information for
+ * things we need to do in the driver) and then pass it over to the
+ * WiMAX stack to send it to user space.
+ *
+ * NOTE: report processing is done in a workqueue specific to the
+ *     generic driver, to avoid deadlocks in the system.
+ *
+ * If it is not a report, it is an ack to a previously executed
+ * command, set or get, so wake up whoever is waiting for it from
+ * i2400m_msg_to_dev(). i2400m_rx_ctl_ack() takes care of that.
+ *
+ * Note that the sizes we pass to other functions from here are the
+ * sizes of the _l3l4_hdr + payload, not full buffer sizes, as we have
+ * verified in _msg_size_check() that they are congruent.
+ *
+ * For reports: We can't clone the original skb where the data is
+ * because we need to send this up via netlink; netlink has to add
+ * headers and we can't overwrite what's preceding the payload...as
+ * it is another message. So we just dup them.
+ */
+static
+void i2400m_rx_ctl(struct i2400m *i2400m, struct sk_buff *skb_rx,
+		   const void *payload, size_t size)
+{
+	int result;
+	struct device *dev = i2400m_dev(i2400m);
+	const struct i2400m_l3l4_hdr *l3l4_hdr = payload;
+	unsigned msg_type;
+
+	result = i2400m_msg_size_check(i2400m, l3l4_hdr, size);
+	if (result < 0) {
+		dev_err(dev, "HW BUG? device sent a bad message: %d\n",
+			result);
+		goto error_check;
+	}
+	msg_type = le16_to_cpu(l3l4_hdr->type);
+	d_printf(1, dev, "%s 0x%04x: %zu bytes\n",
+		 msg_type & I2400M_MT_REPORT_MASK ? "REPORT" : "CMD/SET/GET",
+		 msg_type, size);
+	d_dump(2, dev, l3l4_hdr, size);
+	if (msg_type & I2400M_MT_REPORT_MASK) {
+		/*
+		 * Process each report
+		 *
+		 * - has to be ran serialized as well
+		 *
+		 * - the handling might force the execution of
+		 *   commands. That might cause reentrancy issues with
+		 *   bus-specific subdrivers and workqueues, so the we
+		 *   run it in a separate workqueue.
+		 *
+		 * - when the driver is not yet ready to handle them,
+		 *   they are queued and at some point the queue is
+		 *   restarted [NOTE: we can't queue SKBs directly, as
+		 *   this might be a piece of a SKB, not the whole
+		 *   thing, and this is cheaper than cloning the
+		 *   SKB].
+		 *
+		 * Note we don't do refcounting for the device
+		 * structure; this is because before destroying
+		 * 'i2400m', we make sure to flush the
+		 * i2400m->work_queue, so there are no issues.
+		 */
+		i2400m_report_hook_queue(i2400m, skb_rx, l3l4_hdr, size);
+		if (unlikely(i2400m->trace_msg_from_user))
+			wimax_msg(&i2400m->wimax_dev, "echo",
+				  l3l4_hdr, size, GFP_KERNEL);
+		result = wimax_msg(&i2400m->wimax_dev, NULL, l3l4_hdr, size,
+				   GFP_KERNEL);
+		if (result < 0)
+			dev_err(dev, "error sending report to userspace: %d\n",
+				result);
+	} else		/* an ack to a CMD, GET or SET */
+		i2400m_rx_ctl_ack(i2400m, payload, size);
+error_check:
+	return;
+}
+
+
+/*
+ * Receive and send up a trace
+ *
+ * @i2400m: device descriptor
+ * @skb_rx: skb that contains the trace (for reference counting)
+ * @payload: pointer to trace message inside the skb
+ * @size: size of the message
+ *
+ * THe i2400m might produce trace information (diagnostics) and we
+ * send them through a different kernel-to-user pipe (to avoid
+ * clogging it).
+ *
+ * As in i2400m_rx_ctl(), we can't clone the original skb where the
+ * data is because we need to send this up via netlink; netlink has to
+ * add headers and we can't overwrite what's preceding the
+ * payload...as it is another message. So we just dup them.
+ */
+static
+void i2400m_rx_trace(struct i2400m *i2400m,
+		     const void *payload, size_t size)
+{
+	int result;
+	struct device *dev = i2400m_dev(i2400m);
+	struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
+	const struct i2400m_l3l4_hdr *l3l4_hdr = payload;
+	unsigned msg_type;
+
+	result = i2400m_msg_size_check(i2400m, l3l4_hdr, size);
+	if (result < 0) {
+		dev_err(dev, "HW BUG? device sent a bad trace message: %d\n",
+			result);
+		goto error_check;
+	}
+	msg_type = le16_to_cpu(l3l4_hdr->type);
+	d_printf(1, dev, "Trace %s 0x%04x: %zu bytes\n",
+		 msg_type & I2400M_MT_REPORT_MASK ? "REPORT" : "CMD/SET/GET",
+		 msg_type, size);
+	d_dump(2, dev, l3l4_hdr, size);
+	result = wimax_msg(wimax_dev, "trace", l3l4_hdr, size, GFP_KERNEL);
+	if (result < 0)
+		dev_err(dev, "error sending trace to userspace: %d\n",
+			result);
+error_check:
+	return;
+}
+
+
+/*
+ * Reorder queue data stored on skb->cb while the skb is queued in the
+ * reorder queues.
+ */
+struct i2400m_roq_data {
+	unsigned sn;		/* Serial number for the skb */
+	enum i2400m_cs cs;	/* packet type for the skb */
+};
+
+
+/*
+ * ReOrder Queue
+ *
+ * @ws: Window Start; sequence number where the current window start
+ *     is for this queue
+ * @queue: the skb queue itself
+ * @log: circular ring buffer used to log information about the
+ *     reorder process in this queue that can be displayed in case of
+ *     error to help diagnose it.
+ *
+ * This is the head for a list of skbs. In the skb->cb member of the
+ * skb when queued here contains a 'struct i2400m_roq_data' were we
+ * store the sequence number (sn) and the cs (packet type) coming from
+ * the RX payload header from the device.
+ */
+struct i2400m_roq
+{
+	unsigned ws;
+	struct sk_buff_head queue;
+	struct i2400m_roq_log *log;
+};
+
+
+static
+void __i2400m_roq_init(struct i2400m_roq *roq)
+{
+	roq->ws = 0;
+	skb_queue_head_init(&roq->queue);
+}
+
+
+static
+unsigned __i2400m_roq_index(struct i2400m *i2400m, struct i2400m_roq *roq)
+{
+	return ((unsigned long) roq - (unsigned long) i2400m->rx_roq)
+		/ sizeof(*roq);
+}
+
+
+/*
+ * Normalize a sequence number based on the queue's window start
+ *
+ * nsn = (sn - ws) % 2048
+ *
+ * Note that if @sn < @roq->ws, we still need a positive number; %'s
+ * sign is implementation specific, so we normalize it by adding 2048
+ * to bring it to be positive.
+ */
+static
+unsigned __i2400m_roq_nsn(struct i2400m_roq *roq, unsigned sn)
+{
+	int r;
+	r =  ((int) sn - (int) roq->ws) % 2048;
+	if (r < 0)
+		r += 2048;
+	return r;
+}
+
+
+/*
+ * Circular buffer to keep the last N reorder operations
+ *
+ * In case something fails, dumb then to try to come up with what
+ * happened.
+ */
+enum {
+	I2400M_ROQ_LOG_LENGTH = 32,
+};
+
+struct i2400m_roq_log {
+	struct i2400m_roq_log_entry {
+		enum i2400m_ro_type type;
+		unsigned ws, count, sn, nsn, new_ws;
+	} entry[I2400M_ROQ_LOG_LENGTH];
+	unsigned in, out;
+};
+
+
+/* Print a log entry */
+static
+void i2400m_roq_log_entry_print(struct i2400m *i2400m, unsigned index,
+				unsigned e_index,
+				struct i2400m_roq_log_entry *e)
+{
+	struct device *dev = i2400m_dev(i2400m);
+
+	switch(e->type) {
+	case I2400M_RO_TYPE_RESET:
+		dev_err(dev, "q#%d reset           ws %u cnt %u sn %u/%u"
+			" - new nws %u\n",
+			index, e->ws, e->count, e->sn, e->nsn, e->new_ws);
+		break;
+	case I2400M_RO_TYPE_PACKET:
+		dev_err(dev, "q#%d queue           ws %u cnt %u sn %u/%u\n",
+			index, e->ws, e->count, e->sn, e->nsn);
+		break;
+	case I2400M_RO_TYPE_WS:
+		dev_err(dev, "q#%d update_ws       ws %u cnt %u sn %u/%u"
+			" - new nws %u\n",
+			index, e->ws, e->count, e->sn, e->nsn, e->new_ws);
+		break;
+	case I2400M_RO_TYPE_PACKET_WS:
+		dev_err(dev, "q#%d queue_update_ws ws %u cnt %u sn %u/%u"
+			" - new nws %u\n",
+			index, e->ws, e->count, e->sn, e->nsn, e->new_ws);
+		break;
+	default:
+		dev_err(dev, "q#%d BUG? entry %u - unknown type %u\n",
+			index, e_index, e->type);
+		break;
+	}
+}
+
+
+static
+void i2400m_roq_log_add(struct i2400m *i2400m,
+			struct i2400m_roq *roq, enum i2400m_ro_type type,
+			unsigned ws, unsigned count, unsigned sn,
+			unsigned nsn, unsigned new_ws)
+{
+	struct i2400m_roq_log_entry *e;
+	unsigned cnt_idx;
+	int index = __i2400m_roq_index(i2400m, roq);
+
+	/* if we run out of space, we eat from the end */
+	if (roq->log->in - roq->log->out == I2400M_ROQ_LOG_LENGTH)
+		roq->log->out++;
+	cnt_idx = roq->log->in++ % I2400M_ROQ_LOG_LENGTH;
+	e = &roq->log->entry[cnt_idx];
+
+	e->type = type;
+	e->ws = ws;
+	e->count = count;
+	e->sn = sn;
+	e->nsn = nsn;
+	e->new_ws = new_ws;
+
+	if (d_test(1))
+		i2400m_roq_log_entry_print(i2400m, index, cnt_idx, e);
+}
+
+
+/* Dump all the entries in the FIFO and reinitialize it */
+static
+void i2400m_roq_log_dump(struct i2400m *i2400m, struct i2400m_roq *roq)
+{
+	unsigned cnt, cnt_idx;
+	struct i2400m_roq_log_entry *e;
+	int index = __i2400m_roq_index(i2400m, roq);
+
+	BUG_ON(roq->log->out > roq->log->in);
+	for (cnt = roq->log->out; cnt < roq->log->in; cnt++) {
+		cnt_idx = cnt % I2400M_ROQ_LOG_LENGTH;
+		e = &roq->log->entry[cnt_idx];
+		i2400m_roq_log_entry_print(i2400m, index, cnt_idx, e);
+		memset(e, 0, sizeof(*e));
+	}
+	roq->log->in = roq->log->out = 0;
+}
+
+
+/*
+ * Backbone for the queuing of an skb (by normalized sequence number)
+ *
+ * @i2400m: device descriptor
+ * @roq: reorder queue where to add
+ * @skb: the skb to add
+ * @sn: the sequence number of the skb
+ * @nsn: the normalized sequence number of the skb (pre-computed by the
+ *     caller from the @sn and @roq->ws).
+ *
+ * We try first a couple of quick cases:
+ *
+ *   - the queue is empty
+ *   - the skb would be appended to the queue
+ *
+ * These will be the most common operations.
+ *
+ * If these fail, then we have to do a sorted insertion in the queue,
+ * which is the slowest path.
+ *
+ * We don't have to acquire a reference count as we are going to own it.
+ */
+static
+void __i2400m_roq_queue(struct i2400m *i2400m, struct i2400m_roq *roq,
+			struct sk_buff *skb, unsigned sn, unsigned nsn)
+{
+	struct device *dev = i2400m_dev(i2400m);
+	struct sk_buff *skb_itr;
+	struct i2400m_roq_data *roq_data_itr, *roq_data;
+	unsigned nsn_itr;
+
+	d_fnstart(4, dev, "(i2400m %p roq %p skb %p sn %u nsn %u)\n",
+		  i2400m, roq, skb, sn, nsn);
+
+	roq_data = (struct i2400m_roq_data *) &skb->cb;
+	BUILD_BUG_ON(sizeof(*roq_data) > sizeof(skb->cb));
+	roq_data->sn = sn;
+	d_printf(3, dev, "ERX: roq %p [ws %u] nsn %d sn %u\n",
+		 roq, roq->ws, nsn, roq_data->sn);
+
+	/* Queues will be empty on not-so-bad environments, so try
+	 * that first */
+	if (skb_queue_empty(&roq->queue)) {
+		d_printf(2, dev, "ERX: roq %p - first one\n", roq);
+		__skb_queue_head(&roq->queue, skb);
+		goto out;
+	}
+	/* Now try append, as most of the operations will be that */
+	skb_itr = skb_peek_tail(&roq->queue);
+	roq_data_itr = (struct i2400m_roq_data *) &skb_itr->cb;
+	nsn_itr = __i2400m_roq_nsn(roq, roq_data_itr->sn);
+	/* NSN bounds assumed correct (checked when it was queued) */
+	if (nsn >= nsn_itr) {
+		d_printf(2, dev, "ERX: roq %p - appended after %p (nsn %d sn %u)\n",
+			 roq, skb_itr, nsn_itr, roq_data_itr->sn);
+		__skb_queue_tail(&roq->queue, skb);
+		goto out;
+	}
+	/* None of the fast paths option worked. Iterate to find the
+	 * right spot where to insert the packet; we know the queue is
+	 * not empty, so we are not the first ones; we also know we
+	 * are not going to be the last ones. The list is sorted, so
+	 * we have to insert before the the first guy with an nsn_itr
+	 * greater that our nsn. */
+	skb_queue_walk(&roq->queue, skb_itr) {
+		roq_data_itr = (struct i2400m_roq_data *) &skb_itr->cb;
+		nsn_itr = __i2400m_roq_nsn(roq, roq_data_itr->sn);
+		/* NSN bounds assumed correct (checked when it was queued) */
+		if (nsn_itr > nsn) {
+			d_printf(2, dev, "ERX: roq %p - queued before %p "
+				 "(nsn %d sn %u)\n", roq, skb_itr, nsn_itr,
+				 roq_data_itr->sn);
+			__skb_queue_before(&roq->queue, skb_itr, skb);
+			goto out;
+		}
+	}
+	/* If we get here, that is VERY bad -- print info to help
+	 * diagnose and crash it */
+	dev_err(dev, "SW BUG? failed to insert packet\n");
+	dev_err(dev, "ERX: roq %p [ws %u] skb %p nsn %d sn %u\n",
+		roq, roq->ws, skb, nsn, roq_data->sn);
+	skb_queue_walk(&roq->queue, skb_itr) {
+		roq_data_itr = (struct i2400m_roq_data *) &skb_itr->cb;
+		nsn_itr = __i2400m_roq_nsn(roq, roq_data_itr->sn);
+		/* NSN bounds assumed correct (checked when it was queued) */
+		dev_err(dev, "ERX: roq %p skb_itr %p nsn %d sn %u\n",
+			roq, skb_itr, nsn_itr, roq_data_itr->sn);
+	}
+	BUG();
+out:
+	d_fnend(4, dev, "(i2400m %p roq %p skb %p sn %u nsn %d) = void\n",
+		i2400m, roq, skb, sn, nsn);
+}
+
+
+/*
+ * Backbone for the update window start operation
+ *
+ * @i2400m: device descriptor
+ * @roq: Reorder queue
+ * @sn: New sequence number
+ *
+ * Updates the window start of a queue; when doing so, it must deliver
+ * to the networking stack all the queued skb's whose normalized
+ * sequence number is lower than the new normalized window start.
+ */
+static
+unsigned __i2400m_roq_update_ws(struct i2400m *i2400m, struct i2400m_roq *roq,
+				unsigned sn)
+{
+	struct device *dev = i2400m_dev(i2400m);
+	struct sk_buff *skb_itr, *tmp_itr;
+	struct i2400m_roq_data *roq_data_itr;
+	unsigned new_nws, nsn_itr;
+
+	new_nws = __i2400m_roq_nsn(roq, sn);
+	/*
+	 * For type 2(update_window_start) rx messages, there is no
+	 * need to check if the normalized sequence number is greater 1023.
+	 * Simply insert and deliver all packets to the host up to the
+	 * window start.
+	 */
+	skb_queue_walk_safe(&roq->queue, skb_itr, tmp_itr) {
+		roq_data_itr = (struct i2400m_roq_data *) &skb_itr->cb;
+		nsn_itr = __i2400m_roq_nsn(roq, roq_data_itr->sn);
+		/* NSN bounds assumed correct (checked when it was queued) */
+		if (nsn_itr < new_nws) {
+			d_printf(2, dev, "ERX: roq %p - release skb %p "
+				 "(nsn %u/%u new nws %u)\n",
+				 roq, skb_itr, nsn_itr, roq_data_itr->sn,
+				 new_nws);
+			__skb_unlink(skb_itr, &roq->queue);
+			i2400m_net_erx(i2400m, skb_itr, roq_data_itr->cs);
+		}
+		else
+			break;	/* rest of packets all nsn_itr > nws */
+	}
+	roq->ws = sn;
+	return new_nws;
+}
+
+
+/*
+ * Reset a queue
+ *
+ * @i2400m: device descriptor
+ * @cin: Queue Index
+ *
+ * Deliver all the packets and reset the window-start to zero. Name is
+ * kind of misleading.
+ */
+static
+void i2400m_roq_reset(struct i2400m *i2400m, struct i2400m_roq *roq)
+{
+	struct device *dev = i2400m_dev(i2400m);
+	struct sk_buff *skb_itr, *tmp_itr;
+	struct i2400m_roq_data *roq_data_itr;
+
+	d_fnstart(2, dev, "(i2400m %p roq %p)\n", i2400m, roq);
+	i2400m_roq_log_add(i2400m, roq, I2400M_RO_TYPE_RESET,
+			     roq->ws, skb_queue_len(&roq->queue),
+			     ~0, ~0, 0);
+	skb_queue_walk_safe(&roq->queue, skb_itr, tmp_itr) {
+		roq_data_itr = (struct i2400m_roq_data *) &skb_itr->cb;
+		d_printf(2, dev, "ERX: roq %p - release skb %p (sn %u)\n",
+			 roq, skb_itr, roq_data_itr->sn);
+		__skb_unlink(skb_itr, &roq->queue);
+		i2400m_net_erx(i2400m, skb_itr, roq_data_itr->cs);
+	}
+	roq->ws = 0;
+	d_fnend(2, dev, "(i2400m %p roq %p) = void\n", i2400m, roq);
+}
+
+
+/*
+ * Queue a packet
+ *
+ * @i2400m: device descriptor
+ * @cin: Queue Index
+ * @skb: containing the packet data
+ * @fbn: First block number of the packet in @skb
+ * @lbn: Last block number of the packet in @skb
+ *
+ * The hardware is asking the driver to queue a packet for later
+ * delivery to the networking stack.
+ */
+static
+void i2400m_roq_queue(struct i2400m *i2400m, struct i2400m_roq *roq,
+		      struct sk_buff * skb, unsigned lbn)
+{
+	struct device *dev = i2400m_dev(i2400m);
+	unsigned nsn, len;
+
+	d_fnstart(2, dev, "(i2400m %p roq %p skb %p lbn %u) = void\n",
+		  i2400m, roq, skb, lbn);
+	len = skb_queue_len(&roq->queue);
+	nsn = __i2400m_roq_nsn(roq, lbn);
+	if (unlikely(nsn >= 1024)) {
+		dev_err(dev, "SW BUG? queue nsn %d (lbn %u ws %u)\n",
+			nsn, lbn, roq->ws);
+		i2400m_roq_log_dump(i2400m, roq);
+		i2400m_reset(i2400m, I2400M_RT_WARM);
+	} else {
+		__i2400m_roq_queue(i2400m, roq, skb, lbn, nsn);
+		i2400m_roq_log_add(i2400m, roq, I2400M_RO_TYPE_PACKET,
+				     roq->ws, len, lbn, nsn, ~0);
+	}
+	d_fnend(2, dev, "(i2400m %p roq %p skb %p lbn %u) = void\n",
+		i2400m, roq, skb, lbn);
+}
+
+
+/*
+ * Update the window start in a reorder queue and deliver all skbs
+ * with a lower window start
+ *
+ * @i2400m: device descriptor
+ * @roq: Reorder queue
+ * @sn: New sequence number
+ */
+static
+void i2400m_roq_update_ws(struct i2400m *i2400m, struct i2400m_roq *roq,
+			  unsigned sn)
+{
+	struct device *dev = i2400m_dev(i2400m);
+	unsigned old_ws, nsn, len;
+
+	d_fnstart(2, dev, "(i2400m %p roq %p sn %u)\n", i2400m, roq, sn);
+	old_ws = roq->ws;
+	len = skb_queue_len(&roq->queue);
+	nsn = __i2400m_roq_update_ws(i2400m, roq, sn);
+	i2400m_roq_log_add(i2400m, roq, I2400M_RO_TYPE_WS,
+			     old_ws, len, sn, nsn, roq->ws);
+	d_fnstart(2, dev, "(i2400m %p roq %p sn %u) = void\n", i2400m, roq, sn);
+}
+
+
+/*
+ * Queue a packet and update the window start
+ *
+ * @i2400m: device descriptor
+ * @cin: Queue Index
+ * @skb: containing the packet data
+ * @fbn: First block number of the packet in @skb
+ * @sn: Last block number of the packet in @skb
+ *
+ * Note that unlike i2400m_roq_update_ws(), which sets the new window
+ * start to @sn, in here we'll set it to @sn + 1.
+ */
+static
+void i2400m_roq_queue_update_ws(struct i2400m *i2400m, struct i2400m_roq *roq,
+				struct sk_buff * skb, unsigned sn)
+{
+	struct device *dev = i2400m_dev(i2400m);
+	unsigned nsn, old_ws, len;
+
+	d_fnstart(2, dev, "(i2400m %p roq %p skb %p sn %u)\n",
+		  i2400m, roq, skb, sn);
+	len = skb_queue_len(&roq->queue);
+	nsn = __i2400m_roq_nsn(roq, sn);
+	/*
+	 * For type 3(queue_update_window_start) rx messages, there is no
+	 * need to check if the normalized sequence number is greater 1023.
+	 * Simply insert and deliver all packets to the host up to the
+	 * window start.
+	 */
+	old_ws = roq->ws;
+	/* If the queue is empty, don't bother as we'd queue
+	 * it and immediately unqueue it -- just deliver it.
+	 */
+	if (len == 0) {
+		struct i2400m_roq_data *roq_data;
+		roq_data = (struct i2400m_roq_data *) &skb->cb;
+		i2400m_net_erx(i2400m, skb, roq_data->cs);
+	} else
+		__i2400m_roq_queue(i2400m, roq, skb, sn, nsn);
+
+	__i2400m_roq_update_ws(i2400m, roq, sn + 1);
+	i2400m_roq_log_add(i2400m, roq, I2400M_RO_TYPE_PACKET_WS,
+			   old_ws, len, sn, nsn, roq->ws);
+
+	d_fnend(2, dev, "(i2400m %p roq %p skb %p sn %u) = void\n",
+		i2400m, roq, skb, sn);
+}
+
+
+/*
+ * This routine destroys the memory allocated for rx_roq, when no
+ * other thread is accessing it. Access to rx_roq is refcounted by
+ * rx_roq_refcount, hence memory allocated must be destroyed when
+ * rx_roq_refcount becomes zero. This routine gets executed when
+ * rx_roq_refcount becomes zero.
+ */
+static void i2400m_rx_roq_destroy(struct kref *ref)
+{
+	unsigned itr;
+	struct i2400m *i2400m
+			= container_of(ref, struct i2400m, rx_roq_refcount);
+	for (itr = 0; itr < I2400M_RO_CIN + 1; itr++)
+		__skb_queue_purge(&i2400m->rx_roq[itr].queue);
+	kfree(i2400m->rx_roq[0].log);
+	kfree(i2400m->rx_roq);
+	i2400m->rx_roq = NULL;
+}
+
+/*
+ * Receive and send up an extended data packet
+ *
+ * @i2400m: device descriptor
+ * @skb_rx: skb that contains the extended data packet
+ * @single_last: 1 if the payload is the only one or the last one of
+ *     the skb.
+ * @payload: pointer to the packet's data inside the skb
+ * @size: size of the payload
+ *
+ * Starting in v1.4 of the i2400m's firmware, the device can send data
+ * packets to the host in an extended format that; this incudes a 16
+ * byte header (struct i2400m_pl_edata_hdr). Using this header's space
+ * we can fake ethernet headers for ethernet device emulation without
+ * having to copy packets around.
+ *
+ * This function handles said path.
+ *
+ *
+ * Receive and send up an extended data packet that requires no reordering
+ *
+ * @i2400m: device descriptor
+ * @skb_rx: skb that contains the extended data packet
+ * @single_last: 1 if the payload is the only one or the last one of
+ *     the skb.
+ * @payload: pointer to the packet's data (past the actual extended
+ *     data payload header).
+ * @size: size of the payload
+ *
+ * Pass over to the networking stack a data packet that might have
+ * reordering requirements.
+ *
+ * This needs to the decide if the skb in which the packet is
+ * contained can be reused or if it needs to be cloned. Then it has to
+ * be trimmed in the edges so that the beginning is the space for eth
+ * header and then pass it to i2400m_net_erx() for the stack
+ *
+ * Assumes the caller has verified the sanity of the payload (size,
+ * etc) already.
+ */
+static
+void i2400m_rx_edata(struct i2400m *i2400m, struct sk_buff *skb_rx,
+		     unsigned single_last, const void *payload, size_t size)
+{
+	struct device *dev = i2400m_dev(i2400m);
+	const struct i2400m_pl_edata_hdr *hdr = payload;
+	struct net_device *net_dev = i2400m->wimax_dev.net_dev;
+	struct sk_buff *skb;
+	enum i2400m_cs cs;
+	u32 reorder;
+	unsigned ro_needed, ro_type, ro_cin, ro_sn;
+	struct i2400m_roq *roq;
+	struct i2400m_roq_data *roq_data;
+	unsigned long flags;
+
+	BUILD_BUG_ON(ETH_HLEN > sizeof(*hdr));
+
+	d_fnstart(2, dev, "(i2400m %p skb_rx %p single %u payload %p "
+		  "size %zu)\n", i2400m, skb_rx, single_last, payload, size);
+	if (size < sizeof(*hdr)) {
+		dev_err(dev, "ERX: HW BUG? message with short header (%zu "
+			"vs %zu bytes expected)\n", size, sizeof(*hdr));
+		goto error;
+	}
+
+	if (single_last) {
+		skb = skb_get(skb_rx);
+		d_printf(3, dev, "ERX: skb %p reusing\n", skb);
+	} else {
+		skb = skb_clone(skb_rx, GFP_KERNEL);
+		if (skb == NULL) {
+			dev_err(dev, "ERX: no memory to clone skb\n");
+			net_dev->stats.rx_dropped++;
+			goto error_skb_clone;
+		}
+		d_printf(3, dev, "ERX: skb %p cloned from %p\n", skb, skb_rx);
+	}
+	/* now we have to pull and trim so that the skb points to the
+	 * beginning of the IP packet; the netdev part will add the
+	 * ethernet header as needed - we know there is enough space
+	 * because we checked in i2400m_rx_edata(). */
+	skb_pull(skb, payload + sizeof(*hdr) - (void *) skb->data);
+	skb_trim(skb, (void *) skb_end_pointer(skb) - payload - sizeof(*hdr));
+
+	reorder = le32_to_cpu(hdr->reorder);
+	ro_needed = reorder & I2400M_RO_NEEDED;
+	cs = hdr->cs;
+	if (ro_needed) {
+		ro_type = (reorder >> I2400M_RO_TYPE_SHIFT) & I2400M_RO_TYPE;
+		ro_cin = (reorder >> I2400M_RO_CIN_SHIFT) & I2400M_RO_CIN;
+		ro_sn = (reorder >> I2400M_RO_SN_SHIFT) & I2400M_RO_SN;
+
+		spin_lock_irqsave(&i2400m->rx_lock, flags);
+		if (i2400m->rx_roq == NULL) {
+			kfree_skb(skb);	/* rx_roq is already destroyed */
+			spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+			goto error;
+		}
+		roq = &i2400m->rx_roq[ro_cin];
+		kref_get(&i2400m->rx_roq_refcount);
+		spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+
+		roq_data = (struct i2400m_roq_data *) &skb->cb;
+		roq_data->sn = ro_sn;
+		roq_data->cs = cs;
+		d_printf(2, dev, "ERX: reorder needed: "
+			 "type %u cin %u [ws %u] sn %u/%u len %zuB\n",
+			 ro_type, ro_cin, roq->ws, ro_sn,
+			 __i2400m_roq_nsn(roq, ro_sn), size);
+		d_dump(2, dev, payload, size);
+		switch(ro_type) {
+		case I2400M_RO_TYPE_RESET:
+			i2400m_roq_reset(i2400m, roq);
+			kfree_skb(skb);	/* no data here */
+			break;
+		case I2400M_RO_TYPE_PACKET:
+			i2400m_roq_queue(i2400m, roq, skb, ro_sn);
+			break;
+		case I2400M_RO_TYPE_WS:
+			i2400m_roq_update_ws(i2400m, roq, ro_sn);
+			kfree_skb(skb);	/* no data here */
+			break;
+		case I2400M_RO_TYPE_PACKET_WS:
+			i2400m_roq_queue_update_ws(i2400m, roq, skb, ro_sn);
+			break;
+		default:
+			dev_err(dev, "HW BUG? unknown reorder type %u\n", ro_type);
+		}
+
+		spin_lock_irqsave(&i2400m->rx_lock, flags);
+		kref_put(&i2400m->rx_roq_refcount, i2400m_rx_roq_destroy);
+		spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+	}
+	else
+		i2400m_net_erx(i2400m, skb, cs);
+error_skb_clone:
+error:
+	d_fnend(2, dev, "(i2400m %p skb_rx %p single %u payload %p "
+		"size %zu) = void\n", i2400m, skb_rx, single_last, payload, size);
+}
+
+
+/*
+ * Act on a received payload
+ *
+ * @i2400m: device instance
+ * @skb_rx: skb where the transaction was received
+ * @single_last: 1 this is the only payload or the last one (so the
+ *     skb can be reused instead of cloned).
+ * @pld: payload descriptor
+ * @payload: payload data
+ *
+ * Upon reception of a payload, look at its guts in the payload
+ * descriptor and decide what to do with it. If it is a single payload
+ * skb or if the last skb is a data packet, the skb will be referenced
+ * and modified (so it doesn't have to be cloned).
+ */
+static
+void i2400m_rx_payload(struct i2400m *i2400m, struct sk_buff *skb_rx,
+		       unsigned single_last, const struct i2400m_pld *pld,
+		       const void *payload)
+{
+	struct device *dev = i2400m_dev(i2400m);
+	size_t pl_size = i2400m_pld_size(pld);
+	enum i2400m_pt pl_type = i2400m_pld_type(pld);
+
+	d_printf(7, dev, "RX: received payload type %u, %zu bytes\n",
+		 pl_type, pl_size);
+	d_dump(8, dev, payload, pl_size);
+
+	switch (pl_type) {
+	case I2400M_PT_DATA:
+		d_printf(3, dev, "RX: data payload %zu bytes\n", pl_size);
+		i2400m_net_rx(i2400m, skb_rx, single_last, payload, pl_size);
+		break;
+	case I2400M_PT_CTRL:
+		i2400m_rx_ctl(i2400m, skb_rx, payload, pl_size);
+		break;
+	case I2400M_PT_TRACE:
+		i2400m_rx_trace(i2400m, payload, pl_size);
+		break;
+	case I2400M_PT_EDATA:
+		d_printf(3, dev, "ERX: data payload %zu bytes\n", pl_size);
+		i2400m_rx_edata(i2400m, skb_rx, single_last, payload, pl_size);
+		break;
+	default:	/* Anything else shouldn't come to the host */
+		if (printk_ratelimit())
+			dev_err(dev, "RX: HW BUG? unexpected payload type %u\n",
+				pl_type);
+	}
+}
+
+
+/*
+ * Check a received transaction's message header
+ *
+ * @i2400m: device descriptor
+ * @msg_hdr: message header
+ * @buf_size: size of the received buffer
+ *
+ * Check that the declarations done by a RX buffer message header are
+ * sane and consistent with the amount of data that was received.
+ */
+static
+int i2400m_rx_msg_hdr_check(struct i2400m *i2400m,
+			    const struct i2400m_msg_hdr *msg_hdr,
+			    size_t buf_size)
+{
+	int result = -EIO;
+	struct device *dev = i2400m_dev(i2400m);
+	if (buf_size < sizeof(*msg_hdr)) {
+		dev_err(dev, "RX: HW BUG? message with short header (%zu "
+			"vs %zu bytes expected)\n", buf_size, sizeof(*msg_hdr));
+		goto error;
+	}
+	if (msg_hdr->barker != cpu_to_le32(I2400M_D2H_MSG_BARKER)) {
+		dev_err(dev, "RX: HW BUG? message received with unknown "
+			"barker 0x%08x (buf_size %zu bytes)\n",
+			le32_to_cpu(msg_hdr->barker), buf_size);
+		goto error;
+	}
+	if (msg_hdr->num_pls == 0) {
+		dev_err(dev, "RX: HW BUG? zero payload packets in message\n");
+		goto error;
+	}
+	if (le16_to_cpu(msg_hdr->num_pls) > I2400M_MAX_PLS_IN_MSG) {
+		dev_err(dev, "RX: HW BUG? message contains more payload "
+			"than maximum; ignoring.\n");
+		goto error;
+	}
+	result = 0;
+error:
+	return result;
+}
+
+
+/*
+ * Check a payload descriptor against the received data
+ *
+ * @i2400m: device descriptor
+ * @pld: payload descriptor
+ * @pl_itr: offset (in bytes) in the received buffer the payload is
+ *          located
+ * @buf_size: size of the received buffer
+ *
+ * Given a payload descriptor (part of a RX buffer), check it is sane
+ * and that the data it declares fits in the buffer.
+ */
+static
+int i2400m_rx_pl_descr_check(struct i2400m *i2400m,
+			      const struct i2400m_pld *pld,
+			      size_t pl_itr, size_t buf_size)
+{
+	int result = -EIO;
+	struct device *dev = i2400m_dev(i2400m);
+	size_t pl_size = i2400m_pld_size(pld);
+	enum i2400m_pt pl_type = i2400m_pld_type(pld);
+
+	if (pl_size > i2400m->bus_pl_size_max) {
+		dev_err(dev, "RX: HW BUG? payload @%zu: size %zu is "
+			"bigger than maximum %zu; ignoring message\n",
+			pl_itr, pl_size, i2400m->bus_pl_size_max);
+		goto error;
+	}
+	if (pl_itr + pl_size > buf_size) {	/* enough? */
+		dev_err(dev, "RX: HW BUG? payload @%zu: size %zu "
+			"goes beyond the received buffer "
+			"size (%zu bytes); ignoring message\n",
+			pl_itr, pl_size, buf_size);
+		goto error;
+	}
+	if (pl_type >= I2400M_PT_ILLEGAL) {
+		dev_err(dev, "RX: HW BUG? illegal payload type %u; "
+			"ignoring message\n", pl_type);
+		goto error;
+	}
+	result = 0;
+error:
+	return result;
+}
+
+
+/**
+ * i2400m_rx - Receive a buffer of data from the device
+ *
+ * @i2400m: device descriptor
+ * @skb: skbuff where the data has been received
+ *
+ * Parse in a buffer of data that contains an RX message sent from the
+ * device. See the file header for the format. Run all checks on the
+ * buffer header, then run over each payload's descriptors, verify
+ * their consistency and act on each payload's contents.  If
+ * everything is successful, update the device's statistics.
+ *
+ * Note: You need to set the skb to contain only the length of the
+ * received buffer; for that, use skb_trim(skb, RECEIVED_SIZE).
+ *
+ * Returns:
+ *
+ * 0 if ok, < 0 errno on error
+ *
+ * If ok, this function owns now the skb and the caller DOESN'T have
+ * to run kfree_skb() on it. However, on error, the caller still owns
+ * the skb and it is responsible for releasing it.
+ */
+int i2400m_rx(struct i2400m *i2400m, struct sk_buff *skb)
+{
+	int i, result;
+	struct device *dev = i2400m_dev(i2400m);
+	const struct i2400m_msg_hdr *msg_hdr;
+	size_t pl_itr, pl_size;
+	unsigned long flags;
+	unsigned num_pls, single_last, skb_len;
+
+	skb_len = skb->len;
+	d_fnstart(4, dev, "(i2400m %p skb %p [size %u])\n",
+		  i2400m, skb, skb_len);
+	msg_hdr = (void *) skb->data;
+	result = i2400m_rx_msg_hdr_check(i2400m, msg_hdr, skb_len);
+	if (result < 0)
+		goto error_msg_hdr_check;
+	result = -EIO;
+	num_pls = le16_to_cpu(msg_hdr->num_pls);
+	/* Check payload descriptor(s) */
+	pl_itr = struct_size(msg_hdr, pld, num_pls);
+	pl_itr = ALIGN(pl_itr, I2400M_PL_ALIGN);
+	if (pl_itr > skb_len) {	/* got all the payload descriptors? */
+		dev_err(dev, "RX: HW BUG? message too short (%u bytes) for "
+			"%u payload descriptors (%zu each, total %zu)\n",
+			skb_len, num_pls, sizeof(msg_hdr->pld[0]), pl_itr);
+		goto error_pl_descr_short;
+	}
+	/* Walk each payload payload--check we really got it */
+	for (i = 0; i < num_pls; i++) {
+		/* work around old gcc warnings */
+		pl_size = i2400m_pld_size(&msg_hdr->pld[i]);
+		result = i2400m_rx_pl_descr_check(i2400m, &msg_hdr->pld[i],
+						  pl_itr, skb_len);
+		if (result < 0)
+			goto error_pl_descr_check;
+		single_last = num_pls == 1 || i == num_pls - 1;
+		i2400m_rx_payload(i2400m, skb, single_last, &msg_hdr->pld[i],
+				  skb->data + pl_itr);
+		pl_itr += ALIGN(pl_size, I2400M_PL_ALIGN);
+		cond_resched();		/* Don't monopolize */
+	}
+	kfree_skb(skb);
+	/* Update device statistics */
+	spin_lock_irqsave(&i2400m->rx_lock, flags);
+	i2400m->rx_pl_num += i;
+	if (i > i2400m->rx_pl_max)
+		i2400m->rx_pl_max = i;
+	if (i < i2400m->rx_pl_min)
+		i2400m->rx_pl_min = i;
+	i2400m->rx_num++;
+	i2400m->rx_size_acc += skb_len;
+	if (skb_len < i2400m->rx_size_min)
+		i2400m->rx_size_min = skb_len;
+	if (skb_len > i2400m->rx_size_max)
+		i2400m->rx_size_max = skb_len;
+	spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+error_pl_descr_check:
+error_pl_descr_short:
+error_msg_hdr_check:
+	d_fnend(4, dev, "(i2400m %p skb %p [size %u]) = %d\n",
+		i2400m, skb, skb_len, result);
+	return result;
+}
+EXPORT_SYMBOL_GPL(i2400m_rx);
+
+
+void i2400m_unknown_barker(struct i2400m *i2400m,
+			   const void *buf, size_t size)
+{
+	struct device *dev = i2400m_dev(i2400m);
+	char prefix[64];
+	const __le32 *barker = buf;
+	dev_err(dev, "RX: HW BUG? unknown barker %08x, "
+		"dropping %zu bytes\n", le32_to_cpu(*barker), size);
+	snprintf(prefix, sizeof(prefix), "%s %s: ",
+		 dev_driver_string(dev), dev_name(dev));
+	if (size > 64) {
+		print_hex_dump(KERN_ERR, prefix, DUMP_PREFIX_OFFSET,
+			       8, 4, buf, 64, 0);
+		printk(KERN_ERR "%s... (only first 64 bytes "
+		       "dumped)\n", prefix);
+	} else
+		print_hex_dump(KERN_ERR, prefix, DUMP_PREFIX_OFFSET,
+			       8, 4, buf, size, 0);
+}
+EXPORT_SYMBOL(i2400m_unknown_barker);
+
+
+/*
+ * Initialize the RX queue and infrastructure
+ *
+ * This sets up all the RX reordering infrastructures, which will not
+ * be used if reordering is not enabled or if the firmware does not
+ * support it. The device is told to do reordering in
+ * i2400m_dev_initialize(), where it also looks at the value of the
+ * i2400m->rx_reorder switch before taking a decission.
+ *
+ * Note we allocate the roq queues in one chunk and the actual logging
+ * support for it (logging) in another one and then we setup the
+ * pointers from the first to the last.
+ */
+int i2400m_rx_setup(struct i2400m *i2400m)
+{
+	int result = 0;
+
+	i2400m->rx_reorder = i2400m_rx_reorder_disabled? 0 : 1;
+	if (i2400m->rx_reorder) {
+		unsigned itr;
+		struct i2400m_roq_log *rd;
+
+		result = -ENOMEM;
+
+		i2400m->rx_roq = kcalloc(I2400M_RO_CIN + 1,
+					 sizeof(i2400m->rx_roq[0]), GFP_KERNEL);
+		if (i2400m->rx_roq == NULL)
+			goto error_roq_alloc;
+
+		rd = kcalloc(I2400M_RO_CIN + 1, sizeof(*i2400m->rx_roq[0].log),
+			     GFP_KERNEL);
+		if (rd == NULL) {
+			result = -ENOMEM;
+			goto error_roq_log_alloc;
+		}
+
+		for(itr = 0; itr < I2400M_RO_CIN + 1; itr++) {
+			__i2400m_roq_init(&i2400m->rx_roq[itr]);
+			i2400m->rx_roq[itr].log = &rd[itr];
+		}
+		kref_init(&i2400m->rx_roq_refcount);
+	}
+	return 0;
+
+error_roq_log_alloc:
+	kfree(i2400m->rx_roq);
+error_roq_alloc:
+	return result;
+}
+
+
+/* Tear down the RX queue and infrastructure */
+void i2400m_rx_release(struct i2400m *i2400m)
+{
+	unsigned long flags;
+
+	if (i2400m->rx_reorder) {
+		spin_lock_irqsave(&i2400m->rx_lock, flags);
+		kref_put(&i2400m->rx_roq_refcount, i2400m_rx_roq_destroy);
+		spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+	}
+	/* at this point, nothing can be received... */
+	i2400m_report_hook_flush(i2400m);
+}
diff --git a/drivers/staging/wimax/i2400m/sysfs.c b/drivers/staging/wimax/i2400m/sysfs.c
new file mode 100644
index 000000000000..895ee265909b
--- /dev/null
+++ b/drivers/staging/wimax/i2400m/sysfs.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * Sysfs interfaces to show driver and device information
+ *
+ * Copyright (C) 2007 Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ */
+
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/spinlock.h>
+#include <linux/device.h>
+#include "i2400m.h"
+
+
+#define D_SUBMODULE sysfs
+#include "debug-levels.h"
+
+
+/*
+ * Set the idle timeout (msecs)
+ *
+ * FIXME: eventually this should be a common WiMAX stack method, but
+ * would like to wait to see how other devices manage it.
+ */
+static
+ssize_t i2400m_idle_timeout_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	ssize_t result;
+	struct i2400m *i2400m = net_dev_to_i2400m(to_net_dev(dev));
+	unsigned val;
+
+	result = -EINVAL;
+	if (sscanf(buf, "%u\n", &val) != 1)
+		goto error_no_unsigned;
+	if (val != 0 && (val < 100 || val > 300000 || val % 100 != 0)) {
+		dev_err(dev, "idle_timeout: %u: invalid msecs specification; "
+			"valid values are 0, 100-300000 in 100 increments\n",
+			val);
+		goto error_bad_value;
+	}
+	result = i2400m_set_idle_timeout(i2400m, val);
+	if (result >= 0)
+		result = size;
+error_no_unsigned:
+error_bad_value:
+	return result;
+}
+
+static
+DEVICE_ATTR_WO(i2400m_idle_timeout);
+
+static
+struct attribute *i2400m_dev_attrs[] = {
+	&dev_attr_i2400m_idle_timeout.attr,
+	NULL,
+};
+
+struct attribute_group i2400m_dev_attr_group = {
+	.name = NULL,		/* we want them in the same directory */
+	.attrs = i2400m_dev_attrs,
+};
diff --git a/drivers/staging/wimax/i2400m/tx.c b/drivers/staging/wimax/i2400m/tx.c
new file mode 100644
index 000000000000..1255302e251e
--- /dev/null
+++ b/drivers/staging/wimax/i2400m/tx.c
@@ -0,0 +1,1011 @@
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * Generic (non-bus specific) TX handling
+ *
+ *
+ * Copyright (C) 2007-2008 Intel Corporation. All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *
+ * Intel Corporation <linux-wimax@intel.com>
+ * Yanir Lubetkin <yanirx.lubetkin@intel.com>
+ *  - Initial implementation
+ *
+ * Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *  - Rewritten to use a single FIFO to lower the memory allocation
+ *    pressure and optimize cache hits when copying to the queue, as
+ *    well as splitting out bus-specific code.
+ *
+ *
+ * Implements data transmission to the device; this is done through a
+ * software FIFO, as data/control frames can be coalesced (while the
+ * device is reading the previous tx transaction, others accumulate).
+ *
+ * A FIFO is used because at the end it is resource-cheaper that trying
+ * to implement scatter/gather over USB. As well, most traffic is going
+ * to be download (vs upload).
+ *
+ * The format for sending/receiving data to/from the i2400m is
+ * described in detail in rx.c:PROTOCOL FORMAT. In here we implement
+ * the transmission of that. This is split between a bus-independent
+ * part that just prepares everything and a bus-specific part that
+ * does the actual transmission over the bus to the device (in the
+ * bus-specific driver).
+ *
+ *
+ * The general format of a device-host transaction is MSG-HDR, PLD1,
+ * PLD2...PLDN, PL1, PL2,...PLN, PADDING.
+ *
+ * Because we need the send payload descriptors and then payloads and
+ * because it is kind of expensive to do scatterlists in USB (one URB
+ * per node), it becomes cheaper to append all the data to a FIFO
+ * (copying to a FIFO potentially in cache is cheaper).
+ *
+ * Then the bus-specific code takes the parts of that FIFO that are
+ * written and passes them to the device.
+ *
+ * So the concepts to keep in mind there are:
+ *
+ * We use a FIFO to queue the data in a linear buffer. We first append
+ * a MSG-HDR, space for I2400M_TX_PLD_MAX payload descriptors and then
+ * go appending payloads until we run out of space or of payload
+ * descriptors. Then we append padding to make the whole transaction a
+ * multiple of i2400m->bus_tx_block_size (as defined by the bus layer).
+ *
+ * - A TX message: a combination of a message header, payload
+ *   descriptors and payloads.
+ *
+ *     Open: it is marked as active (i2400m->tx_msg is valid) and we
+ *       can keep adding payloads to it.
+ *
+ *     Closed: we are not appending more payloads to this TX message
+ *       (exahusted space in the queue, too many payloads or
+ *       whichever).  We have appended padding so the whole message
+ *       length is aligned to i2400m->bus_tx_block_size (as set by the
+ *       bus/transport layer).
+ *
+ * - Most of the time we keep a TX message open to which we append
+ *   payloads.
+ *
+ * - If we are going to append and there is no more space (we are at
+ *   the end of the FIFO), we close the message, mark the rest of the
+ *   FIFO space unusable (skip_tail), create a new message at the
+ *   beginning of the FIFO (if there is space) and append the message
+ *   there.
+ *
+ *   This is because we need to give linear TX messages to the bus
+ *   engine. So we don't write a message to the remaining FIFO space
+ *   until the tail and continue at the head of it.
+ *
+ * - We overload one of the fields in the message header to use it as
+ *   'size' of the TX message, so we can iterate over them. It also
+ *   contains a flag that indicates if we have to skip it or not.
+ *   When we send the buffer, we update that to its real on-the-wire
+ *   value.
+ *
+ * - The MSG-HDR PLD1...PLD2 stuff has to be a size multiple of 16.
+ *
+ *   It follows that if MSG-HDR says we have N messages, the whole
+ *   header + descriptors is 16 + 4*N; for those to be a multiple of
+ *   16, it follows that N can be 4, 8, 12, ... (32, 48, 64, 80...
+ *   bytes).
+ *
+ *   So if we have only 1 payload, we have to submit a header that in
+ *   all truth has space for 4.
+ *
+ *   The implication is that we reserve space for 12 (64 bytes); but
+ *   if we fill up only (eg) 2, our header becomes 32 bytes only. So
+ *   the TX engine has to shift those 32 bytes of msg header and 2
+ *   payloads and padding so that right after it the payloads start
+ *   and the TX engine has to know about that.
+ *
+ *   It is cheaper to move the header up than the whole payloads down.
+ *
+ *   We do this in i2400m_tx_close(). See 'i2400m_msg_hdr->offset'.
+ *
+ * - Each payload has to be size-padded to 16 bytes; before appending
+ *   it, we just do it.
+ *
+ * - The whole message has to be padded to i2400m->bus_tx_block_size;
+ *   we do this at close time. Thus, when reserving space for the
+ *   payload, we always make sure there is also free space for this
+ *   padding that sooner or later will happen.
+ *
+ * When we append a message, we tell the bus specific code to kick in
+ * TXs. It will TX (in parallel) until the buffer is exhausted--hence
+ * the lockin we do. The TX code will only send a TX message at the
+ * time (which remember, might contain more than one payload). Of
+ * course, when the bus-specific driver attempts to TX a message that
+ * is still open, it gets closed first.
+ *
+ * Gee, this is messy; well a picture. In the example below we have a
+ * partially full FIFO, with a closed message ready to be delivered
+ * (with a moved message header to make sure it is size-aligned to
+ * 16), TAIL room that was unusable (and thus is marked with a message
+ * header that says 'skip this') and at the head of the buffer, an
+ * incomplete message with a couple of payloads.
+ *
+ * N   ___________________________________________________
+ *    |                                                   |
+ *    |     TAIL room                                     |
+ *    |                                                   |
+ *    |  msg_hdr to skip (size |= 0x80000)                |
+ *    |---------------------------------------------------|-------
+ *    |                                                   |  /|\
+ *    |                                                   |   |
+ *    |  TX message padding                               |   |
+ *    |                                                   |   |
+ *    |                                                   |   |
+ *    |- - - - - - - - - - - - - - - - - - - - - - - - - -|   |
+ *    |                                                   |   |
+ *    |  payload 1                                        |   |
+ *    |                                                   | N * tx_block_size
+ *    |                                                   |   |
+ *    |- - - - - - - - - - - - - - - - - - - - - - - - - -|   |
+ *    |                                                   |   |
+ *    |  payload 1                                        |   |
+ *    |                                                   |   |
+ *    |                                                   |   |
+ *    |- - - - - - - - - - - - - - - - - - - - - - - - - -|- -|- - - -
+ *    |  padding 3                  /|\                   |   |   /|\
+ *    |  padding 2                   |                    |   |    |
+ *    |  pld 1                32 bytes (2 * 16)           |   |    |
+ *    |  pld 0                       |                    |   |    |
+ *    |  moved msg_hdr              \|/                   |  \|/   |
+ *    |- - - - - - - - - - - - - - - - - - - - - - - - - -|- - -   |
+ *    |                                                   |    _PLD_SIZE
+ *    |  unused                                           |        |
+ *    |                                                   |        |
+ *    |- - - - - - - - - - - - - - - - - - - - - - - - - -|        |
+ *    |  msg_hdr (size X)       [this message is closed]  |       \|/
+ *    |===================================================|========== <=== OUT
+ *    |                                                   |
+ *    |                                                   |
+ *    |                                                   |
+ *    |          Free rooom                               |
+ *    |                                                   |
+ *    |                                                   |
+ *    |                                                   |
+ *    |                                                   |
+ *    |                                                   |
+ *    |                                                   |
+ *    |                                                   |
+ *    |                                                   |
+ *    |                                                   |
+ *    |===================================================|========== <=== IN
+ *    |                                                   |
+ *    |                                                   |
+ *    |                                                   |
+ *    |                                                   |
+ *    |  payload 1                                        |
+ *    |                                                   |
+ *    |                                                   |
+ *    |- - - - - - - - - - - - - - - - - - - - - - - - - -|
+ *    |                                                   |
+ *    |  payload 0                                        |
+ *    |                                                   |
+ *    |                                                   |
+ *    |- - - - - - - - - - - - - - - - - - - - - - - - - -|
+ *    |  pld 11                     /|\                   |
+ *    |  ...                         |                    |
+ *    |  pld 1                64 bytes (2 * 16)           |
+ *    |  pld 0                       |                    |
+ *    |  msg_hdr (size X)           \|/ [message is open] |
+ * 0   ---------------------------------------------------
+ *
+ *
+ * ROADMAP
+ *
+ * i2400m_tx_setup()           Called by i2400m_setup
+ * i2400m_tx_release()         Called by i2400m_release()
+ *
+ *  i2400m_tx()                 Called to send data or control frames
+ *    i2400m_tx_fifo_push()     Allocates append-space in the FIFO
+ *    i2400m_tx_new()           Opens a new message in the FIFO
+ *    i2400m_tx_fits()          Checks if a new payload fits in the message
+ *    i2400m_tx_close()         Closes an open message in the FIFO
+ *    i2400m_tx_skip_tail()     Marks unusable FIFO tail space
+ *    i2400m->bus_tx_kick()
+ *
+ * Now i2400m->bus_tx_kick() is the the bus-specific driver backend
+ * implementation; that would do:
+ *
+ * i2400m->bus_tx_kick()
+ *   i2400m_tx_msg_get()	Gets first message ready to go
+ *   ...sends it...
+ *   i2400m_tx_msg_sent()       Ack the message is sent; repeat from
+ *                              _tx_msg_get() until it returns NULL
+ *                               (FIFO empty).
+ */
+#include <linux/netdevice.h>
+#include <linux/slab.h>
+#include <linux/export.h>
+#include "i2400m.h"
+
+
+#define D_SUBMODULE tx
+#include "debug-levels.h"
+
+enum {
+	/**
+	 * TX Buffer size
+	 *
+	 * Doc says maximum transaction is 16KiB. If we had 16KiB en
+	 * route and 16KiB being queued, it boils down to needing
+	 * 32KiB.
+	 * 32KiB is insufficient for 1400 MTU, hence increasing
+	 * tx buffer size to 64KiB.
+	 */
+	I2400M_TX_BUF_SIZE = 65536,
+	/**
+	 * Message header and payload descriptors have to be 16
+	 * aligned (16 + 4 * N = 16 * M). If we take that average sent
+	 * packets are MTU size (~1400-~1500) it follows that we could
+	 * fit at most 10-11 payloads in one transaction. To meet the
+	 * alignment requirement, that means we need to leave space
+	 * for 12 (64 bytes). To simplify, we leave space for that. If
+	 * at the end there are less, we pad up to the nearest
+	 * multiple of 16.
+	 */
+	/*
+	 * According to Intel Wimax i3200, i5x50 and i6x50 specification
+	 * documents, the maximum number of payloads per message can be
+	 * up to 60. Increasing the number of payloads to 60 per message
+	 * helps to accommodate smaller payloads in a single transaction.
+	 */
+	I2400M_TX_PLD_MAX = 60,
+	I2400M_TX_PLD_SIZE = sizeof(struct i2400m_msg_hdr)
+	+ I2400M_TX_PLD_MAX * sizeof(struct i2400m_pld),
+	I2400M_TX_SKIP = 0x80000000,
+	/*
+	 * According to Intel Wimax i3200, i5x50 and i6x50 specification
+	 * documents, the maximum size of each message can be up to 16KiB.
+	 */
+	I2400M_TX_MSG_SIZE = 16384,
+};
+
+#define TAIL_FULL ((void *)~(unsigned long)NULL)
+
+/*
+ * Calculate how much tail room is available
+ *
+ * Note the trick here. This path is ONLY caleed for Case A (see
+ * i2400m_tx_fifo_push() below), where we have:
+ *
+ *       Case A
+ * N  ___________
+ *   | tail room |
+ *   |           |
+ *   |<-  IN   ->|
+ *   |           |
+ *   |   data    |
+ *   |           |
+ *   |<-  OUT  ->|
+ *   |           |
+ *   | head room |
+ * 0  -----------
+ *
+ * When calculating the tail_room, tx_in might get to be zero if
+ * i2400m->tx_in is right at the end of the buffer (really full
+ * buffer) if there is no head room. In this case, tail_room would be
+ * I2400M_TX_BUF_SIZE, although it is actually zero. Hence the final
+ * mod (%) operation. However, when doing this kind of optimization,
+ * i2400m->tx_in being zero would fail, so we treat is an a special
+ * case.
+ */
+static inline
+size_t __i2400m_tx_tail_room(struct i2400m *i2400m)
+{
+	size_t tail_room;
+	size_t tx_in;
+
+	if (unlikely(i2400m->tx_in == 0))
+		return I2400M_TX_BUF_SIZE;
+	tx_in = i2400m->tx_in % I2400M_TX_BUF_SIZE;
+	tail_room = I2400M_TX_BUF_SIZE - tx_in;
+	tail_room %= I2400M_TX_BUF_SIZE;
+	return tail_room;
+}
+
+
+/*
+ * Allocate @size bytes in the TX fifo, return a pointer to it
+ *
+ * @i2400m: device descriptor
+ * @size: size of the buffer we need to allocate
+ * @padding: ensure that there is at least this many bytes of free
+ *     contiguous space in the fifo. This is needed because later on
+ *     we might need to add padding.
+ * @try_head: specify either to allocate head room or tail room space
+ *     in the TX FIFO. This boolean is required to avoids a system hang
+ *     due to an infinite loop caused by i2400m_tx_fifo_push().
+ *     The caller must always try to allocate tail room space first by
+ *     calling this routine with try_head = 0. In case if there
+ *     is not enough tail room space but there is enough head room space,
+ *     (i2400m_tx_fifo_push() returns TAIL_FULL) try to allocate head
+ *     room space, by calling this routine again with try_head = 1.
+ *
+ * Returns:
+ *
+ *     Pointer to the allocated space. NULL if there is no
+ *     space. TAIL_FULL if there is no space at the tail but there is at
+ *     the head (Case B below).
+ *
+ * These are the two basic cases we need to keep an eye for -- it is
+ * much better explained in linux/kernel/kfifo.c, but this code
+ * basically does the same. No rocket science here.
+ *
+ *       Case A               Case B
+ * N  ___________          ___________
+ *   | tail room |        |   data    |
+ *   |           |        |           |
+ *   |<-  IN   ->|        |<-  OUT  ->|
+ *   |           |        |           |
+ *   |   data    |        |   room    |
+ *   |           |        |           |
+ *   |<-  OUT  ->|        |<-  IN   ->|
+ *   |           |        |           |
+ *   | head room |        |   data    |
+ * 0  -----------          -----------
+ *
+ * We allocate only *contiguous* space.
+ *
+ * We can allocate only from 'room'. In Case B, it is simple; in case
+ * A, we only try from the tail room; if it is not enough, we just
+ * fail and return TAIL_FULL and let the caller figure out if we wants to
+ * skip the tail room and try to allocate from the head.
+ *
+ * There is a corner case, wherein i2400m_tx_new() can get into
+ * an infinite loop calling i2400m_tx_fifo_push().
+ * In certain situations, tx_in would have reached on the top of TX FIFO
+ * and i2400m_tx_tail_room() returns 0, as described below:
+ *
+ * N  ___________ tail room is zero
+ *   |<-  IN   ->|
+ *   |           |
+ *   |           |
+ *   |           |
+ *   |   data    |
+ *   |<-  OUT  ->|
+ *   |           |
+ *   |           |
+ *   | head room |
+ * 0  -----------
+ * During such a time, where tail room is zero in the TX FIFO and if there
+ * is a request to add a payload to TX FIFO, which calls:
+ * i2400m_tx()
+ *         ->calls i2400m_tx_close()
+ *         ->calls i2400m_tx_skip_tail()
+ *         goto try_new;
+ *         ->calls i2400m_tx_new()
+ *                    |----> [try_head:]
+ *     infinite loop  |     ->calls i2400m_tx_fifo_push()
+ *                    |                if (tail_room < needed)
+ *                    |                   if (head_room => needed)
+ *                    |                       return TAIL_FULL;
+ *                    |<----  goto try_head;
+ *
+ * i2400m_tx() calls i2400m_tx_close() to close the message, since there
+ * is no tail room to accommodate the payload and calls
+ * i2400m_tx_skip_tail() to skip the tail space. Now i2400m_tx() calls
+ * i2400m_tx_new() to allocate space for new message header calling
+ * i2400m_tx_fifo_push() that returns TAIL_FULL, since there is no tail space
+ * to accommodate the message header, but there is enough head space.
+ * The i2400m_tx_new() keeps re-retrying by calling i2400m_tx_fifo_push()
+ * ending up in a loop causing system freeze.
+ *
+ * This corner case is avoided by using a try_head boolean,
+ * as an argument to i2400m_tx_fifo_push().
+ *
+ * Note:
+ *
+ *     Assumes i2400m->tx_lock is taken, and we use that as a barrier
+ *
+ *     The indexes keep increasing and we reset them to zero when we
+ *     pop data off the queue
+ */
+static
+void *i2400m_tx_fifo_push(struct i2400m *i2400m, size_t size,
+			  size_t padding, bool try_head)
+{
+	struct device *dev = i2400m_dev(i2400m);
+	size_t room, tail_room, needed_size;
+	void *ptr;
+
+	needed_size = size + padding;
+	room = I2400M_TX_BUF_SIZE - (i2400m->tx_in - i2400m->tx_out);
+	if (room < needed_size)	{ /* this takes care of Case B */
+		d_printf(2, dev, "fifo push %zu/%zu: no space\n",
+			 size, padding);
+		return NULL;
+	}
+	/* Is there space at the tail? */
+	tail_room = __i2400m_tx_tail_room(i2400m);
+	if (!try_head && tail_room < needed_size) {
+		/*
+		 * If the tail room space is not enough to push the message
+		 * in the TX FIFO, then there are two possibilities:
+		 * 1. There is enough head room space to accommodate
+		 * this message in the TX FIFO.
+		 * 2. There is not enough space in the head room and
+		 * in tail room of the TX FIFO to accommodate the message.
+		 * In the case (1), return TAIL_FULL so that the caller
+		 * can figure out, if the caller wants to push the message
+		 * into the head room space.
+		 * In the case (2), return NULL, indicating that the TX FIFO
+		 * cannot accommodate the message.
+		 */
+		if (room - tail_room >= needed_size) {
+			d_printf(2, dev, "fifo push %zu/%zu: tail full\n",
+				 size, padding);
+			return TAIL_FULL;	/* There might be head space */
+		} else {
+			d_printf(2, dev, "fifo push %zu/%zu: no head space\n",
+				 size, padding);
+			return NULL;	/* There is no space */
+		}
+	}
+	ptr = i2400m->tx_buf + i2400m->tx_in % I2400M_TX_BUF_SIZE;
+	d_printf(2, dev, "fifo push %zu/%zu: at @%zu\n", size, padding,
+		 i2400m->tx_in % I2400M_TX_BUF_SIZE);
+	i2400m->tx_in += size;
+	return ptr;
+}
+
+
+/*
+ * Mark the tail of the FIFO buffer as 'to-skip'
+ *
+ * We should never hit the BUG_ON() because all the sizes we push to
+ * the FIFO are padded to be a multiple of 16 -- the size of *msg
+ * (I2400M_PL_PAD for the payloads, I2400M_TX_PLD_SIZE for the
+ * header).
+ *
+ * Tail room can get to be zero if a message was opened when there was
+ * space only for a header. _tx_close() will mark it as to-skip (as it
+ * will have no payloads) and there will be no more space to flush, so
+ * nothing has to be done here. This is probably cheaper than ensuring
+ * in _tx_new() that there is some space for payloads...as we could
+ * always possibly hit the same problem if the payload wouldn't fit.
+ *
+ * Note:
+ *
+ *     Assumes i2400m->tx_lock is taken, and we use that as a barrier
+ *
+ *     This path is only taken for Case A FIFO situations [see
+ *     i2400m_tx_fifo_push()]
+ */
+static
+void i2400m_tx_skip_tail(struct i2400m *i2400m)
+{
+	struct device *dev = i2400m_dev(i2400m);
+	size_t tx_in = i2400m->tx_in % I2400M_TX_BUF_SIZE;
+	size_t tail_room = __i2400m_tx_tail_room(i2400m);
+	struct i2400m_msg_hdr *msg = i2400m->tx_buf + tx_in;
+	if (unlikely(tail_room == 0))
+		return;
+	BUG_ON(tail_room < sizeof(*msg));
+	msg->size = tail_room | I2400M_TX_SKIP;
+	d_printf(2, dev, "skip tail: skipping %zu bytes @%zu\n",
+		 tail_room, tx_in);
+	i2400m->tx_in += tail_room;
+}
+
+
+/*
+ * Check if a skb will fit in the TX queue's current active TX
+ * message (if there are still descriptors left unused).
+ *
+ * Returns:
+ *     0 if the message won't fit, 1 if it will.
+ *
+ * Note:
+ *
+ *     Assumes a TX message is active (i2400m->tx_msg).
+ *
+ *     Assumes i2400m->tx_lock is taken, and we use that as a barrier
+ */
+static
+unsigned i2400m_tx_fits(struct i2400m *i2400m)
+{
+	struct i2400m_msg_hdr *msg_hdr = i2400m->tx_msg;
+	return le16_to_cpu(msg_hdr->num_pls) < I2400M_TX_PLD_MAX;
+
+}
+
+
+/*
+ * Start a new TX message header in the queue.
+ *
+ * Reserve memory from the base FIFO engine and then just initialize
+ * the message header.
+ *
+ * We allocate the biggest TX message header we might need (one that'd
+ * fit I2400M_TX_PLD_MAX payloads) -- when it is closed it will be
+ * 'ironed it out' and the unneeded parts removed.
+ *
+ * NOTE:
+ *
+ *     Assumes that the previous message is CLOSED (eg: either
+ *     there was none or 'i2400m_tx_close()' was called on it).
+ *
+ *     Assumes i2400m->tx_lock is taken, and we use that as a barrier
+ */
+static
+void i2400m_tx_new(struct i2400m *i2400m)
+{
+	struct device *dev = i2400m_dev(i2400m);
+	struct i2400m_msg_hdr *tx_msg;
+	bool try_head = false;
+	BUG_ON(i2400m->tx_msg != NULL);
+	/*
+	 * In certain situations, TX queue might have enough space to
+	 * accommodate the new message header I2400M_TX_PLD_SIZE, but
+	 * might not have enough space to accommodate the payloads.
+	 * Adding bus_tx_room_min padding while allocating a new TX message
+	 * increases the possibilities of including at least one payload of the
+	 * size <= bus_tx_room_min.
+	 */
+try_head:
+	tx_msg = i2400m_tx_fifo_push(i2400m, I2400M_TX_PLD_SIZE,
+				     i2400m->bus_tx_room_min, try_head);
+	if (tx_msg == NULL)
+		goto out;
+	else if (tx_msg == TAIL_FULL) {
+		i2400m_tx_skip_tail(i2400m);
+		d_printf(2, dev, "new TX message: tail full, trying head\n");
+		try_head = true;
+		goto try_head;
+	}
+	memset(tx_msg, 0, I2400M_TX_PLD_SIZE);
+	tx_msg->size = I2400M_TX_PLD_SIZE;
+out:
+	i2400m->tx_msg = tx_msg;
+	d_printf(2, dev, "new TX message: %p @%zu\n",
+		 tx_msg, (void *) tx_msg - i2400m->tx_buf);
+}
+
+
+/*
+ * Finalize the current TX message header
+ *
+ * Sets the message header to be at the proper location depending on
+ * how many descriptors we have (check documentation at the file's
+ * header for more info on that).
+ *
+ * Appends padding bytes to make sure the whole TX message (counting
+ * from the 'relocated' message header) is aligned to
+ * tx_block_size. We assume the _append() code has left enough space
+ * in the FIFO for that. If there are no payloads, just pass, as it
+ * won't be transferred.
+ *
+ * The amount of padding bytes depends on how many payloads are in the
+ * TX message, as the "msg header and payload descriptors" will be
+ * shifted up in the buffer.
+ */
+static
+void i2400m_tx_close(struct i2400m *i2400m)
+{
+	struct device *dev = i2400m_dev(i2400m);
+	struct i2400m_msg_hdr *tx_msg = i2400m->tx_msg;
+	struct i2400m_msg_hdr *tx_msg_moved;
+	size_t aligned_size, padding, hdr_size;
+	void *pad_buf;
+	unsigned num_pls;
+
+	if (tx_msg->size & I2400M_TX_SKIP)	/* a skipper? nothing to do */
+		goto out;
+	num_pls = le16_to_cpu(tx_msg->num_pls);
+	/* We can get this situation when a new message was started
+	 * and there was no space to add payloads before hitting the
+	 tail (and taking padding into consideration). */
+	if (num_pls == 0) {
+		tx_msg->size |= I2400M_TX_SKIP;
+		goto out;
+	}
+	/* Relocate the message header
+	 *
+	 * Find the current header size, align it to 16 and if we need
+	 * to move it so the tail is next to the payloads, move it and
+	 * set the offset.
+	 *
+	 * If it moved, this header is good only for transmission; the
+	 * original one (it is kept if we moved) is still used to
+	 * figure out where the next TX message starts (and where the
+	 * offset to the moved header is).
+	 */
+	hdr_size = struct_size(tx_msg, pld, le16_to_cpu(tx_msg->num_pls));
+	hdr_size = ALIGN(hdr_size, I2400M_PL_ALIGN);
+	tx_msg->offset = I2400M_TX_PLD_SIZE - hdr_size;
+	tx_msg_moved = (void *) tx_msg + tx_msg->offset;
+	memmove(tx_msg_moved, tx_msg, hdr_size);
+	tx_msg_moved->size -= tx_msg->offset;
+	/*
+	 * Now figure out how much we have to add to the (moved!)
+	 * message so the size is a multiple of i2400m->bus_tx_block_size.
+	 */
+	aligned_size = ALIGN(tx_msg_moved->size, i2400m->bus_tx_block_size);
+	padding = aligned_size - tx_msg_moved->size;
+	if (padding > 0) {
+		pad_buf = i2400m_tx_fifo_push(i2400m, padding, 0, 0);
+		if (WARN_ON(pad_buf == NULL || pad_buf == TAIL_FULL)) {
+			/* This should not happen -- append should verify
+			 * there is always space left at least to append
+			 * tx_block_size */
+			dev_err(dev,
+				"SW BUG! Possible data leakage from memory the "
+				"device should not read for padding - "
+				"size %lu aligned_size %zu tx_buf %p in "
+				"%zu out %zu\n",
+				(unsigned long) tx_msg_moved->size,
+				aligned_size, i2400m->tx_buf, i2400m->tx_in,
+				i2400m->tx_out);
+		} else
+			memset(pad_buf, 0xad, padding);
+	}
+	tx_msg_moved->padding = cpu_to_le16(padding);
+	tx_msg_moved->size += padding;
+	if (tx_msg != tx_msg_moved)
+		tx_msg->size += padding;
+out:
+	i2400m->tx_msg = NULL;
+}
+
+
+/**
+ * i2400m_tx - send the data in a buffer to the device
+ *
+ * @buf: pointer to the buffer to transmit
+ *
+ * @buf_len: buffer size
+ *
+ * @pl_type: type of the payload we are sending.
+ *
+ * Returns:
+ *     0 if ok, < 0 errno code on error (-ENOSPC, if there is no more
+ *     room for the message in the queue).
+ *
+ * Appends the buffer to the TX FIFO and notifies the bus-specific
+ * part of the driver that there is new data ready to transmit.
+ * Once this function returns, the buffer has been copied, so it can
+ * be reused.
+ *
+ * The steps followed to append are explained in detail in the file
+ * header.
+ *
+ * Whenever we write to a message, we increase msg->size, so it
+ * reflects exactly how big the message is. This is needed so that if
+ * we concatenate two messages before they can be sent, the code that
+ * sends the messages can find the boundaries (and it will replace the
+ * size with the real barker before sending).
+ *
+ * Note:
+ *
+ *     Cold and warm reset payloads need to be sent as a single
+ *     payload, so we handle that.
+ */
+int i2400m_tx(struct i2400m *i2400m, const void *buf, size_t buf_len,
+	      enum i2400m_pt pl_type)
+{
+	int result = -ENOSPC;
+	struct device *dev = i2400m_dev(i2400m);
+	unsigned long flags;
+	size_t padded_len;
+	void *ptr;
+	bool try_head = false;
+	unsigned is_singleton = pl_type == I2400M_PT_RESET_WARM
+		|| pl_type == I2400M_PT_RESET_COLD;
+
+	d_fnstart(3, dev, "(i2400m %p skb %p [%zu bytes] pt %u)\n",
+		  i2400m, buf, buf_len, pl_type);
+	padded_len = ALIGN(buf_len, I2400M_PL_ALIGN);
+	d_printf(5, dev, "padded_len %zd buf_len %zd\n", padded_len, buf_len);
+	/* If there is no current TX message, create one; if the
+	 * current one is out of payload slots or we have a singleton,
+	 * close it and start a new one */
+	spin_lock_irqsave(&i2400m->tx_lock, flags);
+	/* If tx_buf is NULL, device is shutdown */
+	if (i2400m->tx_buf == NULL) {
+		result = -ESHUTDOWN;
+		goto error_tx_new;
+	}
+try_new:
+	if (unlikely(i2400m->tx_msg == NULL))
+		i2400m_tx_new(i2400m);
+	else if (unlikely(!i2400m_tx_fits(i2400m)
+			  || (is_singleton && i2400m->tx_msg->num_pls != 0))) {
+		d_printf(2, dev, "closing TX message (fits %u singleton "
+			 "%u num_pls %u)\n", i2400m_tx_fits(i2400m),
+			 is_singleton, i2400m->tx_msg->num_pls);
+		i2400m_tx_close(i2400m);
+		i2400m_tx_new(i2400m);
+	}
+	if (i2400m->tx_msg == NULL)
+		goto error_tx_new;
+	/*
+	 * Check if this skb will fit in the TX queue's current active
+	 * TX message. The total message size must not exceed the maximum
+	 * size of each message I2400M_TX_MSG_SIZE. If it exceeds,
+	 * close the current message and push this skb into the new message.
+	 */
+	if (i2400m->tx_msg->size + padded_len > I2400M_TX_MSG_SIZE) {
+		d_printf(2, dev, "TX: message too big, going new\n");
+		i2400m_tx_close(i2400m);
+		i2400m_tx_new(i2400m);
+	}
+	if (i2400m->tx_msg == NULL)
+		goto error_tx_new;
+	/* So we have a current message header; now append space for
+	 * the message -- if there is not enough, try the head */
+	ptr = i2400m_tx_fifo_push(i2400m, padded_len,
+				  i2400m->bus_tx_block_size, try_head);
+	if (ptr == TAIL_FULL) {	/* Tail is full, try head */
+		d_printf(2, dev, "pl append: tail full\n");
+		i2400m_tx_close(i2400m);
+		i2400m_tx_skip_tail(i2400m);
+		try_head = true;
+		goto try_new;
+	} else if (ptr == NULL) {	/* All full */
+		result = -ENOSPC;
+		d_printf(2, dev, "pl append: all full\n");
+	} else {			/* Got space, copy it, set padding */
+		struct i2400m_msg_hdr *tx_msg = i2400m->tx_msg;
+		unsigned num_pls = le16_to_cpu(tx_msg->num_pls);
+		memcpy(ptr, buf, buf_len);
+		memset(ptr + buf_len, 0xad, padded_len - buf_len);
+		i2400m_pld_set(&tx_msg->pld[num_pls], buf_len, pl_type);
+		d_printf(3, dev, "pld 0x%08x (type 0x%1x len 0x%04zx\n",
+			 le32_to_cpu(tx_msg->pld[num_pls].val),
+			 pl_type, buf_len);
+		tx_msg->num_pls = le16_to_cpu(num_pls+1);
+		tx_msg->size += padded_len;
+		d_printf(2, dev, "TX: appended %zu b (up to %u b) pl #%u\n",
+			padded_len, tx_msg->size, num_pls+1);
+		d_printf(2, dev,
+			 "TX: appended hdr @%zu %zu b pl #%u @%zu %zu/%zu b\n",
+			 (void *)tx_msg - i2400m->tx_buf, (size_t)tx_msg->size,
+			 num_pls+1, ptr - i2400m->tx_buf, buf_len, padded_len);
+		result = 0;
+		if (is_singleton)
+			i2400m_tx_close(i2400m);
+	}
+error_tx_new:
+	spin_unlock_irqrestore(&i2400m->tx_lock, flags);
+	/* kick in most cases, except when the TX subsys is down, as
+	 * it might free space */
+	if (likely(result != -ESHUTDOWN))
+		i2400m->bus_tx_kick(i2400m);
+	d_fnend(3, dev, "(i2400m %p skb %p [%zu bytes] pt %u) = %d\n",
+		i2400m, buf, buf_len, pl_type, result);
+	return result;
+}
+EXPORT_SYMBOL_GPL(i2400m_tx);
+
+
+/**
+ * i2400m_tx_msg_get - Get the first TX message in the FIFO to start sending it
+ *
+ * @i2400m: device descriptors
+ * @bus_size: where to place the size of the TX message
+ *
+ * Called by the bus-specific driver to get the first TX message at
+ * the FIF that is ready for transmission.
+ *
+ * It sets the state in @i2400m to indicate the bus-specific driver is
+ * transferring that message (i2400m->tx_msg_size).
+ *
+ * Once the transfer is completed, call i2400m_tx_msg_sent().
+ *
+ * Notes:
+ *
+ *     The size of the TX message to be transmitted might be smaller than
+ *     that of the TX message in the FIFO (in case the header was
+ *     shorter). Hence, we copy it in @bus_size, for the bus layer to
+ *     use. We keep the message's size in i2400m->tx_msg_size so that
+ *     when the bus later is done transferring we know how much to
+ *     advance the fifo.
+ *
+ *     We collect statistics here as all the data is available and we
+ *     assume it is going to work [see i2400m_tx_msg_sent()].
+ */
+struct i2400m_msg_hdr *i2400m_tx_msg_get(struct i2400m *i2400m,
+					 size_t *bus_size)
+{
+	struct device *dev = i2400m_dev(i2400m);
+	struct i2400m_msg_hdr *tx_msg, *tx_msg_moved;
+	unsigned long flags, pls;
+
+	d_fnstart(3, dev, "(i2400m %p bus_size %p)\n", i2400m, bus_size);
+	spin_lock_irqsave(&i2400m->tx_lock, flags);
+	tx_msg_moved = NULL;
+	if (i2400m->tx_buf == NULL)
+		goto out_unlock;
+skip:
+	tx_msg_moved = NULL;
+	if (i2400m->tx_in == i2400m->tx_out) {	/* Empty FIFO? */
+		i2400m->tx_in = 0;
+		i2400m->tx_out = 0;
+		d_printf(2, dev, "TX: FIFO empty: resetting\n");
+		goto out_unlock;
+	}
+	tx_msg = i2400m->tx_buf + i2400m->tx_out % I2400M_TX_BUF_SIZE;
+	if (tx_msg->size & I2400M_TX_SKIP) {	/* skip? */
+		d_printf(2, dev, "TX: skip: msg @%zu (%zu b)\n",
+			 i2400m->tx_out % I2400M_TX_BUF_SIZE,
+			 (size_t) tx_msg->size & ~I2400M_TX_SKIP);
+		i2400m->tx_out += tx_msg->size & ~I2400M_TX_SKIP;
+		goto skip;
+	}
+
+	if (tx_msg->num_pls == 0) {		/* No payloads? */
+		if (tx_msg == i2400m->tx_msg) {	/* open, we are done */
+			d_printf(2, dev,
+				 "TX: FIFO empty: open msg w/o payloads @%zu\n",
+				 (void *) tx_msg - i2400m->tx_buf);
+			tx_msg = NULL;
+			goto out_unlock;
+		} else {			/* closed, skip it */
+			d_printf(2, dev,
+				 "TX: skip msg w/o payloads @%zu (%zu b)\n",
+				 (void *) tx_msg - i2400m->tx_buf,
+				 (size_t) tx_msg->size);
+			i2400m->tx_out += tx_msg->size & ~I2400M_TX_SKIP;
+			goto skip;
+		}
+	}
+	if (tx_msg == i2400m->tx_msg)		/* open msg? */
+		i2400m_tx_close(i2400m);
+
+	/* Now we have a valid TX message (with payloads) to TX */
+	tx_msg_moved = (void *) tx_msg + tx_msg->offset;
+	i2400m->tx_msg_size = tx_msg->size;
+	*bus_size = tx_msg_moved->size;
+	d_printf(2, dev, "TX: pid %d msg hdr at @%zu offset +@%zu "
+		 "size %zu bus_size %zu\n",
+		 current->pid, (void *) tx_msg - i2400m->tx_buf,
+		 (size_t) tx_msg->offset, (size_t) tx_msg->size,
+		 (size_t) tx_msg_moved->size);
+	tx_msg_moved->barker = le32_to_cpu(I2400M_H2D_PREVIEW_BARKER);
+	tx_msg_moved->sequence = le32_to_cpu(i2400m->tx_sequence++);
+
+	pls = le32_to_cpu(tx_msg_moved->num_pls);
+	i2400m->tx_pl_num += pls;		/* Update stats */
+	if (pls > i2400m->tx_pl_max)
+		i2400m->tx_pl_max = pls;
+	if (pls < i2400m->tx_pl_min)
+		i2400m->tx_pl_min = pls;
+	i2400m->tx_num++;
+	i2400m->tx_size_acc += *bus_size;
+	if (*bus_size < i2400m->tx_size_min)
+		i2400m->tx_size_min = *bus_size;
+	if (*bus_size > i2400m->tx_size_max)
+		i2400m->tx_size_max = *bus_size;
+out_unlock:
+	spin_unlock_irqrestore(&i2400m->tx_lock, flags);
+	d_fnstart(3, dev, "(i2400m %p bus_size %p [%zu]) = %p\n",
+		  i2400m, bus_size, *bus_size, tx_msg_moved);
+	return tx_msg_moved;
+}
+EXPORT_SYMBOL_GPL(i2400m_tx_msg_get);
+
+
+/**
+ * i2400m_tx_msg_sent - indicate the transmission of a TX message
+ *
+ * @i2400m: device descriptor
+ *
+ * Called by the bus-specific driver when a message has been sent;
+ * this pops it from the FIFO; and as there is space, start the queue
+ * in case it was stopped.
+ *
+ * Should be called even if the message send failed and we are
+ * dropping this TX message.
+ */
+void i2400m_tx_msg_sent(struct i2400m *i2400m)
+{
+	unsigned n;
+	unsigned long flags;
+	struct device *dev = i2400m_dev(i2400m);
+
+	d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
+	spin_lock_irqsave(&i2400m->tx_lock, flags);
+	if (i2400m->tx_buf == NULL)
+		goto out_unlock;
+	i2400m->tx_out += i2400m->tx_msg_size;
+	d_printf(2, dev, "TX: sent %zu b\n", (size_t) i2400m->tx_msg_size);
+	i2400m->tx_msg_size = 0;
+	BUG_ON(i2400m->tx_out > i2400m->tx_in);
+	/* level them FIFO markers off */
+	n = i2400m->tx_out / I2400M_TX_BUF_SIZE;
+	i2400m->tx_out %= I2400M_TX_BUF_SIZE;
+	i2400m->tx_in -= n * I2400M_TX_BUF_SIZE;
+out_unlock:
+	spin_unlock_irqrestore(&i2400m->tx_lock, flags);
+	d_fnend(3, dev, "(i2400m %p) = void\n", i2400m);
+}
+EXPORT_SYMBOL_GPL(i2400m_tx_msg_sent);
+
+
+/**
+ * i2400m_tx_setup - Initialize the TX queue and infrastructure
+ *
+ * Make sure we reset the TX sequence to zero, as when this function
+ * is called, the firmware has been just restarted. Same rational
+ * for tx_in, tx_out, tx_msg_size and tx_msg. We reset them since
+ * the memory for TX queue is reallocated.
+ */
+int i2400m_tx_setup(struct i2400m *i2400m)
+{
+	int result = 0;
+	void *tx_buf;
+	unsigned long flags;
+
+	/* Do this here only once -- can't do on
+	 * i2400m_hard_start_xmit() as we'll cause race conditions if
+	 * the WS was scheduled on another CPU */
+	INIT_WORK(&i2400m->wake_tx_ws, i2400m_wake_tx_work);
+
+	tx_buf = kmalloc(I2400M_TX_BUF_SIZE, GFP_ATOMIC);
+	if (tx_buf == NULL) {
+		result = -ENOMEM;
+		goto error_kmalloc;
+	}
+
+	/*
+	 * Fail the build if we can't fit at least two maximum size messages
+	 * on the TX FIFO [one being delivered while one is constructed].
+	 */
+	BUILD_BUG_ON(2 * I2400M_TX_MSG_SIZE > I2400M_TX_BUF_SIZE);
+	spin_lock_irqsave(&i2400m->tx_lock, flags);
+	i2400m->tx_sequence = 0;
+	i2400m->tx_in = 0;
+	i2400m->tx_out = 0;
+	i2400m->tx_msg_size = 0;
+	i2400m->tx_msg = NULL;
+	i2400m->tx_buf = tx_buf;
+	spin_unlock_irqrestore(&i2400m->tx_lock, flags);
+	/* Huh? the bus layer has to define this... */
+	BUG_ON(i2400m->bus_tx_block_size == 0);
+error_kmalloc:
+	return result;
+
+}
+
+
+/**
+ * i2400m_tx_release - Tear down the TX queue and infrastructure
+ */
+void i2400m_tx_release(struct i2400m *i2400m)
+{
+	unsigned long flags;
+	spin_lock_irqsave(&i2400m->tx_lock, flags);
+	kfree(i2400m->tx_buf);
+	i2400m->tx_buf = NULL;
+	spin_unlock_irqrestore(&i2400m->tx_lock, flags);
+}
diff --git a/drivers/staging/wimax/i2400m/usb-debug-levels.h b/drivers/staging/wimax/i2400m/usb-debug-levels.h
new file mode 100644
index 000000000000..8fd0111560f6
--- /dev/null
+++ b/drivers/staging/wimax/i2400m/usb-debug-levels.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * Debug levels control file for the i2400m-usb module
+ *
+ * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ */
+#ifndef __debug_levels__h__
+#define __debug_levels__h__
+
+/* Maximum compile and run time debug level for all submodules */
+#define D_MODULENAME i2400m_usb
+#define D_MASTER CONFIG_WIMAX_I2400M_DEBUG_LEVEL
+
+#include "../linux-wimax-debug.h"
+
+/* List of all the enabled modules */
+enum d_module {
+	D_SUBMODULE_DECLARE(usb),
+	D_SUBMODULE_DECLARE(fw),
+	D_SUBMODULE_DECLARE(notif),
+	D_SUBMODULE_DECLARE(rx),
+	D_SUBMODULE_DECLARE(tx),
+};
+
+
+#endif /* #ifndef __debug_levels__h__ */
diff --git a/drivers/staging/wimax/i2400m/usb-fw.c b/drivers/staging/wimax/i2400m/usb-fw.c
new file mode 100644
index 000000000000..27ab233650d5
--- /dev/null
+++ b/drivers/staging/wimax/i2400m/usb-fw.c
@@ -0,0 +1,365 @@
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * Firmware uploader's USB specifics
+ *
+ *
+ * Copyright (C) 2007-2008 Intel Corporation. All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *
+ * Intel Corporation <linux-wimax@intel.com>
+ * Yanir Lubetkin <yanirx.lubetkin@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *  - Initial implementation
+ *
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *  - bus generic/specific split
+ *
+ * THE PROCEDURE
+ *
+ * See fw.c for the generic description of this procedure.
+ *
+ * This file implements only the USB specifics. It boils down to how
+ * to send a command and waiting for an acknowledgement from the
+ * device.
+ *
+ * This code (and process) is single threaded. It assumes it is the
+ * only thread poking around (guaranteed by fw.c).
+ *
+ * COMMAND EXECUTION
+ *
+ * A write URB is posted with the buffer to the bulk output endpoint.
+ *
+ * ACK RECEPTION
+ *
+ * We just post a URB to the notification endpoint and wait for
+ * data. We repeat until we get all the data we expect (as indicated
+ * by the call from the bus generic code).
+ *
+ * The data is not read from the bulk in endpoint for boot mode.
+ *
+ * ROADMAP
+ *
+ * i2400mu_bus_bm_cmd_send
+ *   i2400m_bm_cmd_prepare...
+ *   i2400mu_tx_bulk_out
+ *
+ * i2400mu_bus_bm_wait_for_ack
+ *   i2400m_notif_submit
+ */
+#include <linux/usb.h>
+#include <linux/gfp.h>
+#include "i2400m-usb.h"
+
+
+#define D_SUBMODULE fw
+#include "usb-debug-levels.h"
+
+
+/*
+ * Synchronous write to the device
+ *
+ * Takes care of updating EDC counts and thus, handle device errors.
+ */
+static
+ssize_t i2400mu_tx_bulk_out(struct i2400mu *i2400mu, void *buf, size_t buf_size)
+{
+	int result;
+	struct device *dev = &i2400mu->usb_iface->dev;
+	int len;
+	struct usb_endpoint_descriptor *epd;
+	int pipe, do_autopm = 1;
+
+	result = usb_autopm_get_interface(i2400mu->usb_iface);
+	if (result < 0) {
+		dev_err(dev, "BM-CMD: can't get autopm: %d\n", result);
+		do_autopm = 0;
+	}
+	epd = usb_get_epd(i2400mu->usb_iface, i2400mu->endpoint_cfg.bulk_out);
+	pipe = usb_sndbulkpipe(i2400mu->usb_dev, epd->bEndpointAddress);
+retry:
+	result = usb_bulk_msg(i2400mu->usb_dev, pipe, buf, buf_size, &len, 200);
+	switch (result) {
+	case 0:
+		if (len != buf_size) {
+			dev_err(dev, "BM-CMD: short write (%u B vs %zu "
+				"expected)\n", len, buf_size);
+			result = -EIO;
+			break;
+		}
+		result = len;
+		break;
+	case -EPIPE:
+		/*
+		 * Stall -- maybe the device is choking with our
+		 * requests. Clear it and give it some time. If they
+		 * happen to often, it might be another symptom, so we
+		 * reset.
+		 *
+		 * No error handling for usb_clear_halt(0; if it
+		 * works, the retry works; if it fails, this switch
+		 * does the error handling for us.
+		 */
+		if (edc_inc(&i2400mu->urb_edc,
+			    10 * EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME)) {
+			dev_err(dev, "BM-CMD: too many stalls in "
+				"URB; resetting device\n");
+			usb_queue_reset_device(i2400mu->usb_iface);
+		} else {
+			usb_clear_halt(i2400mu->usb_dev, pipe);
+			msleep(10);	/* give the device some time */
+			goto retry;
+		}
+		fallthrough;
+	case -EINVAL:			/* while removing driver */
+	case -ENODEV:			/* dev disconnect ... */
+	case -ENOENT:			/* just ignore it */
+	case -ESHUTDOWN:		/* and exit */
+	case -ECONNRESET:
+		result = -ESHUTDOWN;
+		break;
+	case -ETIMEDOUT:			/* bah... */
+		break;
+	default:				/* any other? */
+		if (edc_inc(&i2400mu->urb_edc,
+			    EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME)) {
+				dev_err(dev, "BM-CMD: maximum errors in "
+					"URB exceeded; resetting device\n");
+				usb_queue_reset_device(i2400mu->usb_iface);
+				result = -ENODEV;
+				break;
+		}
+		dev_err(dev, "BM-CMD: URB error %d, retrying\n",
+			result);
+		goto retry;
+	}
+	if (do_autopm)
+		usb_autopm_put_interface(i2400mu->usb_iface);
+	return result;
+}
+
+
+/*
+ * Send a boot-mode command over the bulk-out pipe
+ *
+ * Command can be a raw command, which requires no preparation (and
+ * which might not even be following the command format). Checks that
+ * the right amount of data was transferred.
+ *
+ * To satisfy USB requirements (no onstack, vmalloc or in data segment
+ * buffers), we copy the command to i2400m->bm_cmd_buf and send it from
+ * there.
+ *
+ * @flags: pass thru from i2400m_bm_cmd()
+ * @return: cmd_size if ok, < 0 errno code on error.
+ */
+ssize_t i2400mu_bus_bm_cmd_send(struct i2400m *i2400m,
+				const struct i2400m_bootrom_header *_cmd,
+				size_t cmd_size, int flags)
+{
+	ssize_t result;
+	struct device *dev = i2400m_dev(i2400m);
+	struct i2400mu *i2400mu = container_of(i2400m, struct i2400mu, i2400m);
+	int opcode = _cmd == NULL ? -1 : i2400m_brh_get_opcode(_cmd);
+	struct i2400m_bootrom_header *cmd;
+	size_t cmd_size_a = ALIGN(cmd_size, 16);	/* USB restriction */
+
+	d_fnstart(8, dev, "(i2400m %p cmd %p size %zu)\n",
+		  i2400m, _cmd, cmd_size);
+	result = -E2BIG;
+	if (cmd_size > I2400M_BM_CMD_BUF_SIZE)
+		goto error_too_big;
+	if (_cmd != i2400m->bm_cmd_buf)
+		memmove(i2400m->bm_cmd_buf, _cmd, cmd_size);
+	cmd = i2400m->bm_cmd_buf;
+	if (cmd_size_a > cmd_size)			/* Zero pad space */
+		memset(i2400m->bm_cmd_buf + cmd_size, 0, cmd_size_a - cmd_size);
+	if ((flags & I2400M_BM_CMD_RAW) == 0) {
+		if (WARN_ON(i2400m_brh_get_response_required(cmd) == 0))
+			dev_warn(dev, "SW BUG: response_required == 0\n");
+		i2400m_bm_cmd_prepare(cmd);
+	}
+	result = i2400mu_tx_bulk_out(i2400mu, i2400m->bm_cmd_buf, cmd_size);
+	if (result < 0) {
+		dev_err(dev, "boot-mode cmd %d: cannot send: %zd\n",
+			opcode, result);
+		goto error_cmd_send;
+	}
+	if (result != cmd_size) {		/* all was transferred? */
+		dev_err(dev, "boot-mode cmd %d: incomplete transfer "
+			"(%zd vs %zu submitted)\n",  opcode, result, cmd_size);
+		result = -EIO;
+		goto error_cmd_size;
+	}
+error_cmd_size:
+error_cmd_send:
+error_too_big:
+	d_fnend(8, dev, "(i2400m %p cmd %p size %zu) = %zd\n",
+		i2400m, _cmd, cmd_size, result);
+	return result;
+}
+
+
+static
+void __i2400mu_bm_notif_cb(struct urb *urb)
+{
+	complete(urb->context);
+}
+
+
+/*
+ * submit a read to the notification endpoint
+ *
+ * @i2400m: device descriptor
+ * @urb: urb to use
+ * @completion: completion variable to complete when done
+ *
+ * Data is always read to i2400m->bm_ack_buf
+ */
+static
+int i2400mu_notif_submit(struct i2400mu *i2400mu, struct urb *urb,
+			 struct completion *completion)
+{
+	struct i2400m *i2400m = &i2400mu->i2400m;
+	struct usb_endpoint_descriptor *epd;
+	int pipe;
+
+	epd = usb_get_epd(i2400mu->usb_iface,
+			  i2400mu->endpoint_cfg.notification);
+	pipe = usb_rcvintpipe(i2400mu->usb_dev, epd->bEndpointAddress);
+	usb_fill_int_urb(urb, i2400mu->usb_dev, pipe,
+			 i2400m->bm_ack_buf, I2400M_BM_ACK_BUF_SIZE,
+			 __i2400mu_bm_notif_cb, completion,
+			 epd->bInterval);
+	return usb_submit_urb(urb, GFP_KERNEL);
+}
+
+
+/*
+ * Read an ack from  the notification endpoint
+ *
+ * @i2400m:
+ * @_ack: pointer to where to store the read data
+ * @ack_size: how many bytes we should read
+ *
+ * Returns: < 0 errno code on error; otherwise, amount of received bytes.
+ *
+ * Submits a notification read, appends the read data to the given ack
+ * buffer and then repeats (until @ack_size bytes have been
+ * received).
+ */
+ssize_t i2400mu_bus_bm_wait_for_ack(struct i2400m *i2400m,
+				    struct i2400m_bootrom_header *_ack,
+				    size_t ack_size)
+{
+	ssize_t result = -ENOMEM;
+	struct device *dev = i2400m_dev(i2400m);
+	struct i2400mu *i2400mu = container_of(i2400m, struct i2400mu, i2400m);
+	struct urb notif_urb;
+	void *ack = _ack;
+	size_t offset, len;
+	long val;
+	int do_autopm = 1;
+	DECLARE_COMPLETION_ONSTACK(notif_completion);
+
+	d_fnstart(8, dev, "(i2400m %p ack %p size %zu)\n",
+		  i2400m, ack, ack_size);
+	BUG_ON(_ack == i2400m->bm_ack_buf);
+	result = usb_autopm_get_interface(i2400mu->usb_iface);
+	if (result < 0) {
+		dev_err(dev, "BM-ACK: can't get autopm: %d\n", (int) result);
+		do_autopm = 0;
+	}
+	usb_init_urb(&notif_urb);	/* ready notifications */
+	usb_get_urb(&notif_urb);
+	offset = 0;
+	while (offset < ack_size) {
+		init_completion(&notif_completion);
+		result = i2400mu_notif_submit(i2400mu, &notif_urb,
+					      &notif_completion);
+		if (result < 0)
+			goto error_notif_urb_submit;
+		val = wait_for_completion_interruptible_timeout(
+			&notif_completion, HZ);
+		if (val == 0) {
+			result = -ETIMEDOUT;
+			usb_kill_urb(&notif_urb);	/* Timedout */
+			goto error_notif_wait;
+		}
+		if (val == -ERESTARTSYS) {
+			result = -EINTR;		/* Interrupted */
+			usb_kill_urb(&notif_urb);
+			goto error_notif_wait;
+		}
+		result = notif_urb.status;		/* How was the ack? */
+		switch (result) {
+		case 0:
+			break;
+		case -EINVAL:			/* while removing driver */
+		case -ENODEV:			/* dev disconnect ... */
+		case -ENOENT:			/* just ignore it */
+		case -ESHUTDOWN:		/* and exit */
+		case -ECONNRESET:
+			result = -ESHUTDOWN;
+			goto error_dev_gone;
+		default:				/* any other? */
+			usb_kill_urb(&notif_urb);	/* Timedout */
+			if (edc_inc(&i2400mu->urb_edc,
+				    EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME))
+				goto error_exceeded;
+			dev_err(dev, "BM-ACK: URB error %d, "
+				"retrying\n", notif_urb.status);
+			continue;	/* retry */
+		}
+		if (notif_urb.actual_length == 0) {
+			d_printf(6, dev, "ZLP received, retrying\n");
+			continue;
+		}
+		/* Got data, append it to the buffer */
+		len = min(ack_size - offset, (size_t) notif_urb.actual_length);
+		memcpy(ack + offset, i2400m->bm_ack_buf, len);
+		offset += len;
+	}
+	result = offset;
+error_notif_urb_submit:
+error_notif_wait:
+error_dev_gone:
+out:
+	if (do_autopm)
+		usb_autopm_put_interface(i2400mu->usb_iface);
+	d_fnend(8, dev, "(i2400m %p ack %p size %zu) = %ld\n",
+		i2400m, ack, ack_size, (long) result);
+	usb_put_urb(&notif_urb);
+	return result;
+
+error_exceeded:
+	dev_err(dev, "bm: maximum errors in notification URB exceeded; "
+		"resetting device\n");
+	usb_queue_reset_device(i2400mu->usb_iface);
+	goto out;
+}
diff --git a/drivers/staging/wimax/i2400m/usb-notif.c b/drivers/staging/wimax/i2400m/usb-notif.c
new file mode 100644
index 000000000000..5d429f816125
--- /dev/null
+++ b/drivers/staging/wimax/i2400m/usb-notif.c
@@ -0,0 +1,258 @@
+/*
+ * Intel Wireless WiMAX Connection 2400m over USB
+ * Notification handling
+ *
+ *
+ * Copyright (C) 2007-2008 Intel Corporation. All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *
+ * Intel Corporation <linux-wimax@intel.com>
+ * Yanir Lubetkin <yanirx.lubetkin@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *  - Initial implementation
+ *
+ *
+ * The notification endpoint is active when the device is not in boot
+ * mode; in here we just read and get notifications; based on those,
+ * we act to either reinitialize the device after a reboot or to
+ * submit a RX request.
+ *
+ * ROADMAP
+ *
+ * i2400mu_usb_notification_setup()
+ *
+ * i2400mu_usb_notification_release()
+ *
+ * i2400mu_usb_notification_cb()	Called when a URB is ready
+ *   i2400mu_notif_grok()
+ *     i2400m_is_boot_barker()
+ *     i2400m_dev_reset_handle()
+ *     i2400mu_rx_kick()
+ */
+#include <linux/usb.h>
+#include <linux/slab.h>
+#include "i2400m-usb.h"
+
+
+#define D_SUBMODULE notif
+#include "usb-debug-levels.h"
+
+
+static const
+__le32 i2400m_ZERO_BARKER[4] = { 0, 0, 0, 0 };
+
+
+/*
+ * Process a received notification
+ *
+ * In normal operation mode, we can only receive two types of payloads
+ * on the notification endpoint:
+ *
+ *   - a reboot barker, we do a bootstrap (the device has reseted).
+ *
+ *   - a block of zeroes: there is pending data in the IN endpoint
+ */
+static
+int i2400mu_notification_grok(struct i2400mu *i2400mu, const void *buf,
+				 size_t buf_len)
+{
+	int ret;
+	struct device *dev = &i2400mu->usb_iface->dev;
+	struct i2400m *i2400m = &i2400mu->i2400m;
+
+	d_fnstart(4, dev, "(i2400m %p buf %p buf_len %zu)\n",
+		  i2400mu, buf, buf_len);
+	ret = -EIO;
+	if (buf_len < sizeof(i2400m_ZERO_BARKER))
+		/* Not a bug, just ignore */
+		goto error_bad_size;
+	ret = 0;
+	if (!memcmp(i2400m_ZERO_BARKER, buf, sizeof(i2400m_ZERO_BARKER))) {
+		i2400mu_rx_kick(i2400mu);
+		goto out;
+	}
+	ret = i2400m_is_boot_barker(i2400m, buf, buf_len);
+	if (unlikely(ret >= 0))
+		ret = i2400m_dev_reset_handle(i2400m, "device rebooted");
+	else	/* Unknown or unexpected data in the notif message */
+		i2400m_unknown_barker(i2400m, buf, buf_len);
+error_bad_size:
+out:
+	d_fnend(4, dev, "(i2400m %p buf %p buf_len %zu) = %d\n",
+		i2400mu, buf, buf_len, ret);
+	return ret;
+}
+
+
+/*
+ * URB callback for the notification endpoint
+ *
+ * @urb: the urb received from the notification endpoint
+ *
+ * This function will just process the USB side of the transaction,
+ * checking everything is fine, pass the processing to
+ * i2400m_notification_grok() and resubmit the URB.
+ */
+static
+void i2400mu_notification_cb(struct urb *urb)
+{
+	int ret;
+	struct i2400mu *i2400mu = urb->context;
+	struct device *dev = &i2400mu->usb_iface->dev;
+
+	d_fnstart(4, dev, "(urb %p status %d actual_length %d)\n",
+		  urb, urb->status, urb->actual_length);
+	ret = urb->status;
+	switch (ret) {
+	case 0:
+		ret = i2400mu_notification_grok(i2400mu, urb->transfer_buffer,
+						urb->actual_length);
+		if (ret == -EIO && edc_inc(&i2400mu->urb_edc, EDC_MAX_ERRORS,
+					   EDC_ERROR_TIMEFRAME))
+			goto error_exceeded;
+		if (ret == -ENOMEM)	/* uff...power cycle? shutdown? */
+			goto error_exceeded;
+		break;
+	case -EINVAL:			/* while removing driver */
+	case -ENODEV:			/* dev disconnect ... */
+	case -ENOENT:			/* ditto */
+	case -ESHUTDOWN:		/* URB killed */
+	case -ECONNRESET:		/* disconnection */
+		goto out;		/* Notify around */
+	default:			/* Some error? */
+		if (edc_inc(&i2400mu->urb_edc,
+			    EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME))
+			goto error_exceeded;
+		dev_err(dev, "notification: URB error %d, retrying\n",
+			urb->status);
+	}
+	usb_mark_last_busy(i2400mu->usb_dev);
+	ret = usb_submit_urb(i2400mu->notif_urb, GFP_ATOMIC);
+	switch (ret) {
+	case 0:
+	case -EINVAL:			/* while removing driver */
+	case -ENODEV:			/* dev disconnect ... */
+	case -ENOENT:			/* ditto */
+	case -ESHUTDOWN:		/* URB killed */
+	case -ECONNRESET:		/* disconnection */
+		break;			/* just ignore */
+	default:			/* Some error? */
+		dev_err(dev, "notification: cannot submit URB: %d\n", ret);
+		goto error_submit;
+	}
+	d_fnend(4, dev, "(urb %p status %d actual_length %d) = void\n",
+		urb, urb->status, urb->actual_length);
+	return;
+
+error_exceeded:
+	dev_err(dev, "maximum errors in notification URB exceeded; "
+		"resetting device\n");
+error_submit:
+	usb_queue_reset_device(i2400mu->usb_iface);
+out:
+	d_fnend(4, dev, "(urb %p status %d actual_length %d) = void\n",
+		urb, urb->status, urb->actual_length);
+}
+
+
+/*
+ * setup the notification endpoint
+ *
+ * @i2400m: device descriptor
+ *
+ * This procedure prepares the notification urb and handler for receiving
+ * unsolicited barkers from the device.
+ */
+int i2400mu_notification_setup(struct i2400mu *i2400mu)
+{
+	struct device *dev = &i2400mu->usb_iface->dev;
+	int usb_pipe, ret = 0;
+	struct usb_endpoint_descriptor *epd;
+	char *buf;
+
+	d_fnstart(4, dev, "(i2400m %p)\n", i2400mu);
+	buf = kmalloc(I2400MU_MAX_NOTIFICATION_LEN, GFP_KERNEL | GFP_DMA);
+	if (buf == NULL) {
+		ret = -ENOMEM;
+		goto error_buf_alloc;
+	}
+
+	i2400mu->notif_urb = usb_alloc_urb(0, GFP_KERNEL);
+	if (!i2400mu->notif_urb) {
+		ret = -ENOMEM;
+		goto error_alloc_urb;
+	}
+	epd = usb_get_epd(i2400mu->usb_iface,
+			  i2400mu->endpoint_cfg.notification);
+	usb_pipe = usb_rcvintpipe(i2400mu->usb_dev, epd->bEndpointAddress);
+	usb_fill_int_urb(i2400mu->notif_urb, i2400mu->usb_dev, usb_pipe,
+			 buf, I2400MU_MAX_NOTIFICATION_LEN,
+			 i2400mu_notification_cb, i2400mu, epd->bInterval);
+	ret = usb_submit_urb(i2400mu->notif_urb, GFP_KERNEL);
+	if (ret != 0) {
+		dev_err(dev, "notification: cannot submit URB: %d\n", ret);
+		goto error_submit;
+	}
+	d_fnend(4, dev, "(i2400m %p) = %d\n", i2400mu, ret);
+	return ret;
+
+error_submit:
+	usb_free_urb(i2400mu->notif_urb);
+error_alloc_urb:
+	kfree(buf);
+error_buf_alloc:
+	d_fnend(4, dev, "(i2400m %p) = %d\n", i2400mu, ret);
+	return ret;
+}
+
+
+/*
+ * Tear down of the notification mechanism
+ *
+ * @i2400m: device descriptor
+ *
+ * Kill the interrupt endpoint urb, free any allocated resources.
+ *
+ * We need to check if we have done it before as for example,
+ * _suspend() call this; if after a suspend() we get a _disconnect()
+ * (as the case is when hibernating), nothing bad happens.
+ */
+void i2400mu_notification_release(struct i2400mu *i2400mu)
+{
+	struct device *dev = &i2400mu->usb_iface->dev;
+
+	d_fnstart(4, dev, "(i2400mu %p)\n", i2400mu);
+	if (i2400mu->notif_urb != NULL) {
+		usb_kill_urb(i2400mu->notif_urb);
+		kfree(i2400mu->notif_urb->transfer_buffer);
+		usb_free_urb(i2400mu->notif_urb);
+		i2400mu->notif_urb = NULL;
+	}
+	d_fnend(4, dev, "(i2400mu %p)\n", i2400mu);
+}
diff --git a/drivers/staging/wimax/i2400m/usb-rx.c b/drivers/staging/wimax/i2400m/usb-rx.c
new file mode 100644
index 000000000000..5b64bda7d9e7
--- /dev/null
+++ b/drivers/staging/wimax/i2400m/usb-rx.c
@@ -0,0 +1,462 @@
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * USB RX handling
+ *
+ *
+ * Copyright (C) 2007-2008 Intel Corporation. All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *
+ * Intel Corporation <linux-wimax@intel.com>
+ * Yanir Lubetkin <yanirx.lubetkin@intel.com>
+ *  - Initial implementation
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *  - Use skb_clone(), break up processing in chunks
+ *  - Split transport/device specific
+ *  - Make buffer size dynamic to exert less memory pressure
+ *
+ *
+ * This handles the RX path on USB.
+ *
+ * When a notification is received that says 'there is RX data ready',
+ * we call i2400mu_rx_kick(); that wakes up the RX kthread, which
+ * reads a buffer from USB and passes it to i2400m_rx() in the generic
+ * handling code. The RX buffer has an specific format that is
+ * described in rx.c.
+ *
+ * We use a kernel thread in a loop because:
+ *
+ *  - we want to be able to call the USB power management get/put
+ *    functions (blocking) before each transaction.
+ *
+ *  - We might get a lot of notifications and we don't want to submit
+ *    a zillion reads; by serializing, we are throttling.
+ *
+ *  - RX data processing can get heavy enough so that it is not
+ *    appropriate for doing it in the USB callback; thus we run it in a
+ *    process context.
+ *
+ * We provide a read buffer of an arbitrary size (short of a page); if
+ * the callback reports -EOVERFLOW, it means it was too small, so we
+ * just double the size and retry (being careful to append, as
+ * sometimes the device provided some data). Every now and then we
+ * check if the average packet size is smaller than the current packet
+ * size and if so, we halve it. At the end, the size of the
+ * preallocated buffer should be following the average received
+ * transaction size, adapting dynamically to it.
+ *
+ * ROADMAP
+ *
+ * i2400mu_rx_kick()		   Called from notif.c when we get a
+ *   			           'data ready' notification
+ * i2400mu_rxd()                   Kernel RX daemon
+ *   i2400mu_rx()                  Receive USB data
+ *   i2400m_rx()                   Send data to generic i2400m RX handling
+ *
+ * i2400mu_rx_setup()              called from i2400mu_bus_dev_start()
+ *
+ * i2400mu_rx_release()            called from i2400mu_bus_dev_stop()
+ */
+#include <linux/workqueue.h>
+#include <linux/slab.h>
+#include <linux/usb.h>
+#include "i2400m-usb.h"
+
+
+#define D_SUBMODULE rx
+#include "usb-debug-levels.h"
+
+/*
+ * Dynamic RX size
+ *
+ * We can't let the rx_size be a multiple of 512 bytes (the RX
+ * endpoint's max packet size). On some USB host controllers (we
+ * haven't been able to fully characterize which), if the device is
+ * about to send (for example) X bytes and we only post a buffer to
+ * receive n*512, it will fail to mark that as babble (so that
+ * i2400mu_rx() [case -EOVERFLOW] can resize the buffer and get the
+ * rest).
+ *
+ * So on growing or shrinking, if it is a multiple of the
+ * maxpacketsize, we remove some (instead of incresing some, so in a
+ * buddy allocator we try to waste less space).
+ *
+ * Note we also need a hook for this on i2400mu_rx() -- when we do the
+ * first read, we are sure we won't hit this spot because
+ * i240mm->rx_size has been set properly. However, if we have to
+ * double because of -EOVERFLOW, when we launch the read to get the
+ * rest of the data, we *have* to make sure that also is not a
+ * multiple of the max_pkt_size.
+ */
+
+static
+size_t i2400mu_rx_size_grow(struct i2400mu *i2400mu)
+{
+	struct device *dev = &i2400mu->usb_iface->dev;
+	size_t rx_size;
+	const size_t max_pkt_size = 512;
+
+	rx_size = 2 * i2400mu->rx_size;
+	if (rx_size % max_pkt_size == 0) {
+		rx_size -= 8;
+		d_printf(1, dev,
+			 "RX: expected size grew to %zu [adjusted -8] "
+			 "from %zu\n",
+			 rx_size, i2400mu->rx_size);
+	} else
+		d_printf(1, dev,
+			 "RX: expected size grew to %zu from %zu\n",
+			 rx_size, i2400mu->rx_size);
+	return rx_size;
+}
+
+
+static
+void i2400mu_rx_size_maybe_shrink(struct i2400mu *i2400mu)
+{
+	const size_t max_pkt_size = 512;
+	struct device *dev = &i2400mu->usb_iface->dev;
+
+	if (unlikely(i2400mu->rx_size_cnt >= 100
+		     && i2400mu->rx_size_auto_shrink)) {
+		size_t avg_rx_size =
+			i2400mu->rx_size_acc / i2400mu->rx_size_cnt;
+		size_t new_rx_size = i2400mu->rx_size / 2;
+		if (avg_rx_size < new_rx_size) {
+			if (new_rx_size % max_pkt_size == 0) {
+				new_rx_size -= 8;
+				d_printf(1, dev,
+					 "RX: expected size shrank to %zu "
+					 "[adjusted -8] from %zu\n",
+					 new_rx_size, i2400mu->rx_size);
+			} else
+				d_printf(1, dev,
+					 "RX: expected size shrank to %zu "
+					 "from %zu\n",
+					 new_rx_size, i2400mu->rx_size);
+			i2400mu->rx_size = new_rx_size;
+			i2400mu->rx_size_cnt = 0;
+			i2400mu->rx_size_acc = i2400mu->rx_size;
+		}
+	}
+}
+
+/*
+ * Receive a message with payloads from the USB bus into an skb
+ *
+ * @i2400mu: USB device descriptor
+ * @rx_skb: skb where to place the received message
+ *
+ * Deals with all the USB-specifics of receiving, dynamically
+ * increasing the buffer size if so needed. Returns the payload in the
+ * skb, ready to process. On a zero-length packet, we retry.
+ *
+ * On soft USB errors, we retry (until they become too frequent and
+ * then are promoted to hard); on hard USB errors, we reset the
+ * device. On other errors (skb realloacation, we just drop it and
+ * hope for the next invocation to solve it).
+ *
+ * Returns: pointer to the skb if ok, ERR_PTR on error.
+ *   NOTE: this function might realloc the skb (if it is too small),
+ *   so always update with the one returned.
+ *   ERR_PTR() is < 0 on error.
+ *   Will return NULL if it cannot reallocate -- this can be
+ *   considered a transient retryable error.
+ */
+static
+struct sk_buff *i2400mu_rx(struct i2400mu *i2400mu, struct sk_buff *rx_skb)
+{
+	int result = 0;
+	struct device *dev = &i2400mu->usb_iface->dev;
+	int usb_pipe, read_size, rx_size, do_autopm;
+	struct usb_endpoint_descriptor *epd;
+	const size_t max_pkt_size = 512;
+
+	d_fnstart(4, dev, "(i2400mu %p)\n", i2400mu);
+	do_autopm = atomic_read(&i2400mu->do_autopm);
+	result = do_autopm ?
+		usb_autopm_get_interface(i2400mu->usb_iface) : 0;
+	if (result < 0) {
+		dev_err(dev, "RX: can't get autopm: %d\n", result);
+		do_autopm = 0;
+	}
+	epd = usb_get_epd(i2400mu->usb_iface, i2400mu->endpoint_cfg.bulk_in);
+	usb_pipe = usb_rcvbulkpipe(i2400mu->usb_dev, epd->bEndpointAddress);
+retry:
+	rx_size = skb_end_pointer(rx_skb) - rx_skb->data - rx_skb->len;
+	if (unlikely(rx_size % max_pkt_size == 0)) {
+		rx_size -= 8;
+		d_printf(1, dev, "RX: rx_size adapted to %d [-8]\n", rx_size);
+	}
+	result = usb_bulk_msg(
+		i2400mu->usb_dev, usb_pipe, rx_skb->data + rx_skb->len,
+		rx_size, &read_size, 200);
+	usb_mark_last_busy(i2400mu->usb_dev);
+	switch (result) {
+	case 0:
+		if (read_size == 0)
+			goto retry;	/* ZLP, just resubmit */
+		skb_put(rx_skb, read_size);
+		break;
+	case -EPIPE:
+		/*
+		 * Stall -- maybe the device is choking with our
+		 * requests. Clear it and give it some time. If they
+		 * happen to often, it might be another symptom, so we
+		 * reset.
+		 *
+		 * No error handling for usb_clear_halt(0; if it
+		 * works, the retry works; if it fails, this switch
+		 * does the error handling for us.
+		 */
+		if (edc_inc(&i2400mu->urb_edc,
+			    10 * EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME)) {
+			dev_err(dev, "BM-CMD: too many stalls in "
+				"URB; resetting device\n");
+			goto do_reset;
+		}
+		usb_clear_halt(i2400mu->usb_dev, usb_pipe);
+		msleep(10);	/* give the device some time */
+		goto retry;
+	case -EINVAL:			/* while removing driver */
+	case -ENODEV:			/* dev disconnect ... */
+	case -ENOENT:			/* just ignore it */
+	case -ESHUTDOWN:
+	case -ECONNRESET:
+		break;
+	case -EOVERFLOW: {		/* too small, reallocate */
+		struct sk_buff *new_skb;
+		rx_size = i2400mu_rx_size_grow(i2400mu);
+		if (rx_size <= (1 << 16))	/* cap it */
+			i2400mu->rx_size = rx_size;
+		else if (printk_ratelimit()) {
+			dev_err(dev, "BUG? rx_size up to %d\n", rx_size);
+			result = -EINVAL;
+			goto out;
+		}
+		skb_put(rx_skb, read_size);
+		new_skb = skb_copy_expand(rx_skb, 0, rx_size - rx_skb->len,
+					  GFP_KERNEL);
+		if (new_skb == NULL) {
+			kfree_skb(rx_skb);
+			rx_skb = NULL;
+			goto out;	/* drop it...*/
+		}
+		kfree_skb(rx_skb);
+		rx_skb = new_skb;
+		i2400mu->rx_size_cnt = 0;
+		i2400mu->rx_size_acc = i2400mu->rx_size;
+		d_printf(1, dev, "RX: size changed to %d, received %d, "
+			 "copied %d, capacity %ld\n",
+			 rx_size, read_size, rx_skb->len,
+			 (long) skb_end_offset(new_skb));
+		goto retry;
+	}
+		/* In most cases, it happens due to the hardware scheduling a
+		 * read when there was no data - unfortunately, we have no way
+		 * to tell this timeout from a USB timeout. So we just ignore
+		 * it. */
+	case -ETIMEDOUT:
+		dev_err(dev, "RX: timeout: %d\n", result);
+		result = 0;
+		break;
+	default:			/* Any error */
+		if (edc_inc(&i2400mu->urb_edc,
+			    EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME))
+			goto error_reset;
+		dev_err(dev, "RX: error receiving URB: %d, retrying\n", result);
+		goto retry;
+	}
+out:
+	if (do_autopm)
+		usb_autopm_put_interface(i2400mu->usb_iface);
+	d_fnend(4, dev, "(i2400mu %p) = %p\n", i2400mu, rx_skb);
+	return rx_skb;
+
+error_reset:
+	dev_err(dev, "RX: maximum errors in URB exceeded; "
+		"resetting device\n");
+do_reset:
+	usb_queue_reset_device(i2400mu->usb_iface);
+	rx_skb = ERR_PTR(result);
+	goto out;
+}
+
+
+/*
+ * Kernel thread for USB reception of data
+ *
+ * This thread waits for a kick; once kicked, it will allocate an skb
+ * and receive a single message to it from USB (using
+ * i2400mu_rx()). Once received, it is passed to the generic i2400m RX
+ * code for processing.
+ *
+ * When done processing, it runs some dirty statistics to verify if
+ * the last 100 messages received were smaller than half of the
+ * current RX buffer size. In that case, the RX buffer size is
+ * halved. This will helps lowering the pressure on the memory
+ * allocator.
+ *
+ * Hard errors force the thread to exit.
+ */
+static
+int i2400mu_rxd(void *_i2400mu)
+{
+	int result = 0;
+	struct i2400mu *i2400mu = _i2400mu;
+	struct i2400m *i2400m = &i2400mu->i2400m;
+	struct device *dev = &i2400mu->usb_iface->dev;
+	struct net_device *net_dev = i2400m->wimax_dev.net_dev;
+	size_t pending;
+	int rx_size;
+	struct sk_buff *rx_skb;
+	unsigned long flags;
+
+	d_fnstart(4, dev, "(i2400mu %p)\n", i2400mu);
+	spin_lock_irqsave(&i2400m->rx_lock, flags);
+	BUG_ON(i2400mu->rx_kthread != NULL);
+	i2400mu->rx_kthread = current;
+	spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+	while (1) {
+		d_printf(2, dev, "RX: waiting for messages\n");
+		pending = 0;
+		wait_event_interruptible(
+			i2400mu->rx_wq,
+			(kthread_should_stop()	/* check this first! */
+			 || (pending = atomic_read(&i2400mu->rx_pending_count)))
+			);
+		if (kthread_should_stop())
+			break;
+		if (pending == 0)
+			continue;
+		rx_size = i2400mu->rx_size;
+		d_printf(2, dev, "RX: reading up to %d bytes\n", rx_size);
+		rx_skb = __netdev_alloc_skb(net_dev, rx_size, GFP_KERNEL);
+		if (rx_skb == NULL) {
+			dev_err(dev, "RX: can't allocate skb [%d bytes]\n",
+				rx_size);
+			msleep(50);	/* give it some time? */
+			continue;
+		}
+
+		/* Receive the message with the payloads */
+		rx_skb = i2400mu_rx(i2400mu, rx_skb);
+		result = PTR_ERR(rx_skb);
+		if (IS_ERR(rx_skb))
+			goto out;
+		atomic_dec(&i2400mu->rx_pending_count);
+		if (rx_skb == NULL || rx_skb->len == 0) {
+			/* some "ignorable" condition */
+			kfree_skb(rx_skb);
+			continue;
+		}
+
+		/* Deliver the message to the generic i2400m code */
+		i2400mu->rx_size_cnt++;
+		i2400mu->rx_size_acc += rx_skb->len;
+		result = i2400m_rx(i2400m, rx_skb);
+		if (result == -EIO
+		    && edc_inc(&i2400mu->urb_edc,
+			       EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME)) {
+			goto error_reset;
+		}
+
+		/* Maybe adjust RX buffer size */
+		i2400mu_rx_size_maybe_shrink(i2400mu);
+	}
+	result = 0;
+out:
+	spin_lock_irqsave(&i2400m->rx_lock, flags);
+	i2400mu->rx_kthread = NULL;
+	spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+	d_fnend(4, dev, "(i2400mu %p) = %d\n", i2400mu, result);
+	return result;
+
+error_reset:
+	dev_err(dev, "RX: maximum errors in received buffer exceeded; "
+		"resetting device\n");
+	usb_queue_reset_device(i2400mu->usb_iface);
+	goto out;
+}
+
+
+/*
+ * Start reading from the device
+ *
+ * @i2400m: device instance
+ *
+ * Notify the RX thread that there is data pending.
+ */
+void i2400mu_rx_kick(struct i2400mu *i2400mu)
+{
+	struct i2400m *i2400m = &i2400mu->i2400m;
+	struct device *dev = &i2400mu->usb_iface->dev;
+
+	d_fnstart(3, dev, "(i2400mu %p)\n", i2400m);
+	atomic_inc(&i2400mu->rx_pending_count);
+	wake_up_all(&i2400mu->rx_wq);
+	d_fnend(3, dev, "(i2400m %p) = void\n", i2400m);
+}
+
+
+int i2400mu_rx_setup(struct i2400mu *i2400mu)
+{
+	int result = 0;
+	struct i2400m *i2400m = &i2400mu->i2400m;
+	struct device *dev = &i2400mu->usb_iface->dev;
+	struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
+	struct task_struct *kthread;
+
+	kthread = kthread_run(i2400mu_rxd, i2400mu, "%s-rx",
+			      wimax_dev->name);
+	/* the kthread function sets i2400mu->rx_thread */
+	if (IS_ERR(kthread)) {
+		result = PTR_ERR(kthread);
+		dev_err(dev, "RX: cannot start thread: %d\n", result);
+	}
+	return result;
+}
+
+
+void i2400mu_rx_release(struct i2400mu *i2400mu)
+{
+	unsigned long flags;
+	struct i2400m *i2400m = &i2400mu->i2400m;
+	struct device *dev = i2400m_dev(i2400m);
+	struct task_struct *kthread;
+
+	spin_lock_irqsave(&i2400m->rx_lock, flags);
+	kthread = i2400mu->rx_kthread;
+	i2400mu->rx_kthread = NULL;
+	spin_unlock_irqrestore(&i2400m->rx_lock, flags);
+	if (kthread)
+		kthread_stop(kthread);
+	else
+		d_printf(1, dev, "RX: kthread had already exited\n");
+}
+
diff --git a/drivers/staging/wimax/i2400m/usb-tx.c b/drivers/staging/wimax/i2400m/usb-tx.c
new file mode 100644
index 000000000000..3ba9d70cca1b
--- /dev/null
+++ b/drivers/staging/wimax/i2400m/usb-tx.c
@@ -0,0 +1,273 @@
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * USB specific TX handling
+ *
+ *
+ * Copyright (C) 2007-2008 Intel Corporation. All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *
+ * Intel Corporation <linux-wimax@intel.com>
+ * Yanir Lubetkin <yanirx.lubetkin@intel.com>
+ *  - Initial implementation
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *  - Split transport/device specific
+ *
+ *
+ * Takes the TX messages in the i2400m's driver TX FIFO and sends them
+ * to the device until there are no more.
+ *
+ * If we fail sending the message, we just drop it. There isn't much
+ * we can do at this point. We could also retry, but the USB stack has
+ * already retried and still failed, so there is not much of a
+ * point. As well, most of the traffic is network, which has recovery
+ * methods for dropped packets.
+ *
+ * For sending we just obtain a FIFO buffer to send, send it to the
+ * USB bulk out, tell the TX FIFO code we have sent it; query for
+ * another one, etc... until done.
+ *
+ * We use a thread so we can call usb_autopm_enable() and
+ * usb_autopm_disable() for each transaction; this way when the device
+ * goes idle, it will suspend. It also has less overhead than a
+ * dedicated workqueue, as it is being used for a single task.
+ *
+ * ROADMAP
+ *
+ * i2400mu_tx_setup()
+ * i2400mu_tx_release()
+ *
+ * i2400mu_bus_tx_kick()	- Called by the tx.c code when there
+ *                                is new data in the FIFO.
+ * i2400mu_txd()
+ *   i2400m_tx_msg_get()
+ *   i2400m_tx_msg_sent()
+ */
+#include "i2400m-usb.h"
+
+
+#define D_SUBMODULE tx
+#include "usb-debug-levels.h"
+
+
+/*
+ * Get the next TX message in the TX FIFO and send it to the device
+ *
+ * Note that any iteration consumes a message to be sent, no matter if
+ * it succeeds or fails (we have no real way to retry or complain).
+ *
+ * Return: 0 if ok, < 0 errno code on hard error.
+ */
+static
+int i2400mu_tx(struct i2400mu *i2400mu, struct i2400m_msg_hdr *tx_msg,
+	       size_t tx_msg_size)
+{
+	int result = 0;
+	struct i2400m *i2400m = &i2400mu->i2400m;
+	struct device *dev = &i2400mu->usb_iface->dev;
+	int usb_pipe, sent_size, do_autopm;
+	struct usb_endpoint_descriptor *epd;
+
+	d_fnstart(4, dev, "(i2400mu %p)\n", i2400mu);
+	do_autopm = atomic_read(&i2400mu->do_autopm);
+	result = do_autopm ?
+		usb_autopm_get_interface(i2400mu->usb_iface) : 0;
+	if (result < 0) {
+		dev_err(dev, "TX: can't get autopm: %d\n", result);
+		do_autopm = 0;
+	}
+	epd = usb_get_epd(i2400mu->usb_iface, i2400mu->endpoint_cfg.bulk_out);
+	usb_pipe = usb_sndbulkpipe(i2400mu->usb_dev, epd->bEndpointAddress);
+retry:
+	result = usb_bulk_msg(i2400mu->usb_dev, usb_pipe,
+			      tx_msg, tx_msg_size, &sent_size, 200);
+	usb_mark_last_busy(i2400mu->usb_dev);
+	switch (result) {
+	case 0:
+		if (sent_size != tx_msg_size) {	/* Too short? drop it */
+			dev_err(dev, "TX: short write (%d B vs %zu "
+				"expected)\n", sent_size, tx_msg_size);
+			result = -EIO;
+		}
+		break;
+	case -EPIPE:
+		/*
+		 * Stall -- maybe the device is choking with our
+		 * requests. Clear it and give it some time. If they
+		 * happen to often, it might be another symptom, so we
+		 * reset.
+		 *
+		 * No error handling for usb_clear_halt(0; if it
+		 * works, the retry works; if it fails, this switch
+		 * does the error handling for us.
+		 */
+		if (edc_inc(&i2400mu->urb_edc,
+			    10 * EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME)) {
+			dev_err(dev, "BM-CMD: too many stalls in "
+				"URB; resetting device\n");
+			usb_queue_reset_device(i2400mu->usb_iface);
+		} else {
+			usb_clear_halt(i2400mu->usb_dev, usb_pipe);
+			msleep(10);	/* give the device some time */
+			goto retry;
+		}
+		fallthrough;
+	case -EINVAL:			/* while removing driver */
+	case -ENODEV:			/* dev disconnect ... */
+	case -ENOENT:			/* just ignore it */
+	case -ESHUTDOWN:		/* and exit */
+	case -ECONNRESET:
+		result = -ESHUTDOWN;
+		break;
+	default:			/* Some error? */
+		if (edc_inc(&i2400mu->urb_edc,
+			    EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME)) {
+			dev_err(dev, "TX: maximum errors in URB "
+				"exceeded; resetting device\n");
+			usb_queue_reset_device(i2400mu->usb_iface);
+		} else {
+			dev_err(dev, "TX: cannot send URB; retrying. "
+				"tx_msg @%zu %zu B [%d sent]: %d\n",
+				(void *) tx_msg - i2400m->tx_buf,
+				tx_msg_size, sent_size, result);
+			goto retry;
+		}
+	}
+	if (do_autopm)
+		usb_autopm_put_interface(i2400mu->usb_iface);
+	d_fnend(4, dev, "(i2400mu %p) = result\n", i2400mu);
+	return result;
+}
+
+
+/*
+ * Get the next TX message in the TX FIFO and send it to the device
+ *
+ * Note we exit the loop if i2400mu_tx() fails; that function only
+ * fails on hard error (failing to tx a buffer not being one of them,
+ * see its doc).
+ *
+ * Return: 0
+ */
+static
+int i2400mu_txd(void *_i2400mu)
+{
+	struct i2400mu *i2400mu = _i2400mu;
+	struct i2400m *i2400m = &i2400mu->i2400m;
+	struct device *dev = &i2400mu->usb_iface->dev;
+	struct i2400m_msg_hdr *tx_msg;
+	size_t tx_msg_size;
+	unsigned long flags;
+
+	d_fnstart(4, dev, "(i2400mu %p)\n", i2400mu);
+
+	spin_lock_irqsave(&i2400m->tx_lock, flags);
+	BUG_ON(i2400mu->tx_kthread != NULL);
+	i2400mu->tx_kthread = current;
+	spin_unlock_irqrestore(&i2400m->tx_lock, flags);
+
+	while (1) {
+		d_printf(2, dev, "TX: waiting for messages\n");
+		tx_msg = NULL;
+		wait_event_interruptible(
+			i2400mu->tx_wq,
+			(kthread_should_stop()	/* check this first! */
+			 || (tx_msg = i2400m_tx_msg_get(i2400m, &tx_msg_size)))
+			);
+		if (kthread_should_stop())
+			break;
+		WARN_ON(tx_msg == NULL);	/* should not happen...*/
+		d_printf(2, dev, "TX: submitting %zu bytes\n", tx_msg_size);
+		d_dump(5, dev, tx_msg, tx_msg_size);
+		/* Yeah, we ignore errors ... not much we can do */
+		i2400mu_tx(i2400mu, tx_msg, tx_msg_size);
+		i2400m_tx_msg_sent(i2400m);	/* ack it, advance the FIFO */
+	}
+
+	spin_lock_irqsave(&i2400m->tx_lock, flags);
+	i2400mu->tx_kthread = NULL;
+	spin_unlock_irqrestore(&i2400m->tx_lock, flags);
+
+	d_fnend(4, dev, "(i2400mu %p)\n", i2400mu);
+	return 0;
+}
+
+
+/*
+ * i2400m TX engine notifies us that there is data in the FIFO ready
+ * for TX
+ *
+ * If there is a URB in flight, don't do anything; when it finishes,
+ * it will see there is data in the FIFO and send it. Else, just
+ * submit a write.
+ */
+void i2400mu_bus_tx_kick(struct i2400m *i2400m)
+{
+	struct i2400mu *i2400mu = container_of(i2400m, struct i2400mu, i2400m);
+	struct device *dev = &i2400mu->usb_iface->dev;
+
+	d_fnstart(3, dev, "(i2400m %p) = void\n", i2400m);
+	wake_up_all(&i2400mu->tx_wq);
+	d_fnend(3, dev, "(i2400m %p) = void\n", i2400m);
+}
+
+
+int i2400mu_tx_setup(struct i2400mu *i2400mu)
+{
+	int result = 0;
+	struct i2400m *i2400m = &i2400mu->i2400m;
+	struct device *dev = &i2400mu->usb_iface->dev;
+	struct wimax_dev *wimax_dev = &i2400m->wimax_dev;
+	struct task_struct *kthread;
+
+	kthread = kthread_run(i2400mu_txd, i2400mu, "%s-tx",
+			      wimax_dev->name);
+	/* the kthread function sets i2400mu->tx_thread */
+	if (IS_ERR(kthread)) {
+		result = PTR_ERR(kthread);
+		dev_err(dev, "TX: cannot start thread: %d\n", result);
+	}
+	return result;
+}
+
+void i2400mu_tx_release(struct i2400mu *i2400mu)
+{
+	unsigned long flags;
+	struct i2400m *i2400m = &i2400mu->i2400m;
+	struct device *dev = i2400m_dev(i2400m);
+	struct task_struct *kthread;
+
+	spin_lock_irqsave(&i2400m->tx_lock, flags);
+	kthread = i2400mu->tx_kthread;
+	i2400mu->tx_kthread = NULL;
+	spin_unlock_irqrestore(&i2400m->tx_lock, flags);
+	if (kthread)
+		kthread_stop(kthread);
+	else
+		d_printf(1, dev, "TX: kthread had already exited\n");
+}
diff --git a/drivers/staging/wimax/i2400m/usb.c b/drivers/staging/wimax/i2400m/usb.c
new file mode 100644
index 000000000000..3b84dd7b5567
--- /dev/null
+++ b/drivers/staging/wimax/i2400m/usb.c
@@ -0,0 +1,764 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Intel Wireless WiMAX Connection 2400m
+ * Linux driver model glue for USB device, reset & fw upload
+ *
+ * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ * Yanir Lubetkin <yanirx.lubetkin@intel.com>
+ *
+ * See i2400m-usb.h for a general description of this driver.
+ *
+ * This file implements driver model glue, and hook ups for the
+ * generic driver to implement the bus-specific functions (device
+ * communication setup/tear down, firmware upload and resetting).
+ *
+ * ROADMAP
+ *
+ * i2400mu_probe()
+ *   alloc_netdev()...
+ *     i2400mu_netdev_setup()
+ *       i2400mu_init()
+ *       i2400m_netdev_setup()
+ *   i2400m_setup()...
+ *
+ * i2400mu_disconnect
+ *   i2400m_release()
+ *   free_netdev()
+ *
+ * i2400mu_suspend()
+ *   i2400m_cmd_enter_powersave()
+ *   i2400mu_notification_release()
+ *
+ * i2400mu_resume()
+ *   i2400mu_notification_setup()
+ *
+ * i2400mu_bus_dev_start()        Called by i2400m_dev_start() [who is
+ *   i2400mu_tx_setup()           called by i2400m_setup()]
+ *   i2400mu_rx_setup()
+ *   i2400mu_notification_setup()
+ *
+ * i2400mu_bus_dev_stop()         Called by i2400m_dev_stop() [who is
+ *   i2400mu_notification_release()  called by i2400m_release()]
+ *   i2400mu_rx_release()
+ *   i2400mu_tx_release()
+ *
+ * i2400mu_bus_reset()            Called by i2400m_reset
+ *   __i2400mu_reset()
+ *     __i2400mu_send_barker()
+ *   usb_reset_device()
+ */
+#include "i2400m-usb.h"
+#include "linux-wimax-i2400m.h"
+#include <linux/debugfs.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+
+
+#define D_SUBMODULE usb
+#include "usb-debug-levels.h"
+
+static char i2400mu_debug_params[128];
+module_param_string(debug, i2400mu_debug_params, sizeof(i2400mu_debug_params),
+		    0644);
+MODULE_PARM_DESC(debug,
+		 "String of space-separated NAME:VALUE pairs, where NAMEs "
+		 "are the different debug submodules and VALUE are the "
+		 "initial debug value to set.");
+
+/* Our firmware file name */
+static const char *i2400mu_bus_fw_names_5x50[] = {
+#define I2400MU_FW_FILE_NAME_v1_5 "i2400m-fw-usb-1.5.sbcf"
+	I2400MU_FW_FILE_NAME_v1_5,
+#define I2400MU_FW_FILE_NAME_v1_4 "i2400m-fw-usb-1.4.sbcf"
+	I2400MU_FW_FILE_NAME_v1_4,
+	NULL,
+};
+
+
+static const char *i2400mu_bus_fw_names_6050[] = {
+#define I6050U_FW_FILE_NAME_v1_5 "i6050-fw-usb-1.5.sbcf"
+	I6050U_FW_FILE_NAME_v1_5,
+	NULL,
+};
+
+
+static
+int i2400mu_bus_dev_start(struct i2400m *i2400m)
+{
+	int result;
+	struct i2400mu *i2400mu = container_of(i2400m, struct i2400mu, i2400m);
+	struct device *dev = &i2400mu->usb_iface->dev;
+
+	d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
+	result = i2400mu_tx_setup(i2400mu);
+	if (result < 0)
+		goto error_usb_tx_setup;
+	result = i2400mu_rx_setup(i2400mu);
+	if (result < 0)
+		goto error_usb_rx_setup;
+	result = i2400mu_notification_setup(i2400mu);
+	if (result < 0)
+		goto error_notif_setup;
+	d_fnend(3, dev, "(i2400m %p) = %d\n", i2400m, result);
+	return result;
+
+error_notif_setup:
+	i2400mu_rx_release(i2400mu);
+error_usb_rx_setup:
+	i2400mu_tx_release(i2400mu);
+error_usb_tx_setup:
+	d_fnend(3, dev, "(i2400m %p) = void\n", i2400m);
+	return result;
+}
+
+
+static
+void i2400mu_bus_dev_stop(struct i2400m *i2400m)
+{
+	struct i2400mu *i2400mu = container_of(i2400m, struct i2400mu, i2400m);
+	struct device *dev = &i2400mu->usb_iface->dev;
+
+	d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
+	i2400mu_notification_release(i2400mu);
+	i2400mu_rx_release(i2400mu);
+	i2400mu_tx_release(i2400mu);
+	d_fnend(3, dev, "(i2400m %p) = void\n", i2400m);
+}
+
+
+/*
+ * Sends a barker buffer to the device
+ *
+ * This helper will allocate a kmalloced buffer and use it to transmit
+ * (then free it). Reason for this is that other arches cannot use
+ * stack/vmalloc/text areas for DMA transfers.
+ *
+ * Error recovery here is simpler: anything is considered a hard error
+ * and will move the reset code to use a last-resort bus-based reset.
+ */
+static
+int __i2400mu_send_barker(struct i2400mu *i2400mu,
+			  const __le32 *barker,
+			  size_t barker_size,
+			  unsigned endpoint)
+{
+	struct usb_endpoint_descriptor *epd = NULL;
+	int pipe, actual_len, ret;
+	struct device *dev = &i2400mu->usb_iface->dev;
+	void *buffer;
+	int do_autopm = 1;
+
+	ret = usb_autopm_get_interface(i2400mu->usb_iface);
+	if (ret < 0) {
+		dev_err(dev, "RESET: can't get autopm: %d\n", ret);
+		do_autopm = 0;
+	}
+	ret = -ENOMEM;
+	buffer = kmalloc(barker_size, GFP_KERNEL);
+	if (buffer == NULL)
+		goto error_kzalloc;
+	epd = usb_get_epd(i2400mu->usb_iface, endpoint);
+	pipe = usb_sndbulkpipe(i2400mu->usb_dev, epd->bEndpointAddress);
+	memcpy(buffer, barker, barker_size);
+retry:
+	ret = usb_bulk_msg(i2400mu->usb_dev, pipe, buffer, barker_size,
+			   &actual_len, 200);
+	switch (ret) {
+	case 0:
+		if (actual_len != barker_size) {	/* Too short? drop it */
+			dev_err(dev, "E: %s: short write (%d B vs %zu "
+				"expected)\n",
+				__func__, actual_len, barker_size);
+			ret = -EIO;
+		}
+		break;
+	case -EPIPE:
+		/*
+		 * Stall -- maybe the device is choking with our
+		 * requests. Clear it and give it some time. If they
+		 * happen to often, it might be another symptom, so we
+		 * reset.
+		 *
+		 * No error handling for usb_clear_halt(0; if it
+		 * works, the retry works; if it fails, this switch
+		 * does the error handling for us.
+		 */
+		if (edc_inc(&i2400mu->urb_edc,
+			    10 * EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME)) {
+			dev_err(dev, "E: %s: too many stalls in "
+				"URB; resetting device\n", __func__);
+			usb_queue_reset_device(i2400mu->usb_iface);
+			/* fallthrough */
+		} else {
+			usb_clear_halt(i2400mu->usb_dev, pipe);
+			msleep(10);	/* give the device some time */
+			goto retry;
+		}
+		fallthrough;
+	case -EINVAL:			/* while removing driver */
+	case -ENODEV:			/* dev disconnect ... */
+	case -ENOENT:			/* just ignore it */
+	case -ESHUTDOWN:		/* and exit */
+	case -ECONNRESET:
+		ret = -ESHUTDOWN;
+		break;
+	default:			/* Some error? */
+		if (edc_inc(&i2400mu->urb_edc,
+			    EDC_MAX_ERRORS, EDC_ERROR_TIMEFRAME)) {
+			dev_err(dev, "E: %s: maximum errors in URB "
+				"exceeded; resetting device\n",
+				__func__);
+			usb_queue_reset_device(i2400mu->usb_iface);
+		} else {
+			dev_warn(dev, "W: %s: cannot send URB: %d\n",
+				 __func__, ret);
+			goto retry;
+		}
+	}
+	kfree(buffer);
+error_kzalloc:
+	if (do_autopm)
+		usb_autopm_put_interface(i2400mu->usb_iface);
+	return ret;
+}
+
+
+/*
+ * Reset a device at different levels (warm, cold or bus)
+ *
+ * @i2400m: device descriptor
+ * @reset_type: soft, warm or bus reset (I2400M_RT_WARM/SOFT/BUS)
+ *
+ * Warm and cold resets get a USB reset if they fail.
+ *
+ * Warm reset:
+ *
+ * The device will be fully reset internally, but won't be
+ * disconnected from the USB bus (so no reenumeration will
+ * happen). Firmware upload will be necessary.
+ *
+ * The device will send a reboot barker in the notification endpoint
+ * that will trigger the driver to reinitialize the state
+ * automatically from notif.c:i2400m_notification_grok() into
+ * i2400m_dev_bootstrap_delayed().
+ *
+ * Cold and bus (USB) reset:
+ *
+ * The device will be fully reset internally, disconnected from the
+ * USB bus an a reenumeration will happen. Firmware upload will be
+ * necessary. Thus, we don't do any locking or struct
+ * reinitialization, as we are going to be fully disconnected and
+ * reenumerated.
+ *
+ * Note we need to return -ENODEV if a warm reset was requested and we
+ * had to resort to a bus reset. See i2400m_op_reset(), wimax_reset()
+ * and wimax_dev->op_reset.
+ *
+ * WARNING: no driver state saved/fixed
+ */
+static
+int i2400mu_bus_reset(struct i2400m *i2400m, enum i2400m_reset_type rt)
+{
+	int result;
+	struct i2400mu *i2400mu =
+		container_of(i2400m, struct i2400mu, i2400m);
+	struct device *dev = i2400m_dev(i2400m);
+	static const __le32 i2400m_WARM_BOOT_BARKER[4] = {
+		cpu_to_le32(I2400M_WARM_RESET_BARKER),
+		cpu_to_le32(I2400M_WARM_RESET_BARKER),
+		cpu_to_le32(I2400M_WARM_RESET_BARKER),
+		cpu_to_le32(I2400M_WARM_RESET_BARKER),
+	};
+	static const __le32 i2400m_COLD_BOOT_BARKER[4] = {
+		cpu_to_le32(I2400M_COLD_RESET_BARKER),
+		cpu_to_le32(I2400M_COLD_RESET_BARKER),
+		cpu_to_le32(I2400M_COLD_RESET_BARKER),
+		cpu_to_le32(I2400M_COLD_RESET_BARKER),
+	};
+
+	d_fnstart(3, dev, "(i2400m %p rt %u)\n", i2400m, rt);
+	if (rt == I2400M_RT_WARM)
+		result = __i2400mu_send_barker(
+			i2400mu, i2400m_WARM_BOOT_BARKER,
+			sizeof(i2400m_WARM_BOOT_BARKER),
+			i2400mu->endpoint_cfg.bulk_out);
+	else if (rt == I2400M_RT_COLD)
+		result = __i2400mu_send_barker(
+			i2400mu, i2400m_COLD_BOOT_BARKER,
+			sizeof(i2400m_COLD_BOOT_BARKER),
+			i2400mu->endpoint_cfg.reset_cold);
+	else if (rt == I2400M_RT_BUS) {
+		result = usb_reset_device(i2400mu->usb_dev);
+		switch (result) {
+		case 0:
+		case -EINVAL:	/* device is gone */
+		case -ENODEV:
+		case -ENOENT:
+		case -ESHUTDOWN:
+			result = 0;
+			break;	/* We assume the device is disconnected */
+		default:
+			dev_err(dev, "USB reset failed (%d), giving up!\n",
+				result);
+		}
+	} else {
+		result = -EINVAL;	/* shut gcc up in certain arches */
+		BUG();
+	}
+	if (result < 0
+	    && result != -EINVAL	/* device is gone */
+	    && rt != I2400M_RT_BUS) {
+		/*
+		 * Things failed -- resort to lower level reset, that
+		 * we queue in another context; the reason for this is
+		 * that the pre and post reset functionality requires
+		 * the i2400m->init_mutex; RT_WARM and RT_COLD can
+		 * come from areas where i2400m->init_mutex is taken.
+		 */
+		dev_err(dev, "%s reset failed (%d); trying USB reset\n",
+			rt == I2400M_RT_WARM ? "warm" : "cold", result);
+		usb_queue_reset_device(i2400mu->usb_iface);
+		result = -ENODEV;
+	}
+	d_fnend(3, dev, "(i2400m %p rt %u) = %d\n", i2400m, rt, result);
+	return result;
+}
+
+static void i2400mu_get_drvinfo(struct net_device *net_dev,
+                                struct ethtool_drvinfo *info)
+{
+	struct i2400m *i2400m = net_dev_to_i2400m(net_dev);
+	struct i2400mu *i2400mu = container_of(i2400m, struct i2400mu, i2400m);
+	struct usb_device *udev = i2400mu->usb_dev;
+
+	strlcpy(info->driver, KBUILD_MODNAME, sizeof(info->driver));
+	strlcpy(info->fw_version, i2400m->fw_name ? : "",
+		sizeof(info->fw_version));
+	usb_make_path(udev, info->bus_info, sizeof(info->bus_info));
+}
+
+static const struct ethtool_ops i2400mu_ethtool_ops = {
+	.get_drvinfo = i2400mu_get_drvinfo,
+	.get_link = ethtool_op_get_link,
+};
+
+static
+void i2400mu_netdev_setup(struct net_device *net_dev)
+{
+	struct i2400m *i2400m = net_dev_to_i2400m(net_dev);
+	struct i2400mu *i2400mu = container_of(i2400m, struct i2400mu, i2400m);
+	i2400mu_init(i2400mu);
+	i2400m_netdev_setup(net_dev);
+	net_dev->ethtool_ops = &i2400mu_ethtool_ops;
+}
+
+
+/*
+ * Debug levels control; see debug.h
+ */
+struct d_level D_LEVEL[] = {
+	D_SUBMODULE_DEFINE(usb),
+	D_SUBMODULE_DEFINE(fw),
+	D_SUBMODULE_DEFINE(notif),
+	D_SUBMODULE_DEFINE(rx),
+	D_SUBMODULE_DEFINE(tx),
+};
+size_t D_LEVEL_SIZE = ARRAY_SIZE(D_LEVEL);
+
+static
+void i2400mu_debugfs_add(struct i2400mu *i2400mu)
+{
+	struct dentry *dentry = i2400mu->i2400m.wimax_dev.debugfs_dentry;
+
+	dentry = debugfs_create_dir("i2400m-usb", dentry);
+	i2400mu->debugfs_dentry = dentry;
+
+	d_level_register_debugfs("dl_", usb, dentry);
+	d_level_register_debugfs("dl_", fw, dentry);
+	d_level_register_debugfs("dl_", notif, dentry);
+	d_level_register_debugfs("dl_", rx, dentry);
+	d_level_register_debugfs("dl_", tx, dentry);
+
+	/* Don't touch these if you don't know what you are doing */
+	debugfs_create_u8("rx_size_auto_shrink", 0600, dentry,
+			  &i2400mu->rx_size_auto_shrink);
+
+	debugfs_create_size_t("rx_size", 0600, dentry, &i2400mu->rx_size);
+}
+
+
+static struct device_type i2400mu_type = {
+	.name	= "wimax",
+};
+
+/*
+ * Probe a i2400m interface and register it
+ *
+ * @iface:   USB interface to link to
+ * @id:      USB class/subclass/protocol id
+ * @returns: 0 if ok, < 0 errno code on error.
+ *
+ * Alloc a net device, initialize the bus-specific details and then
+ * calls the bus-generic initialization routine. That will register
+ * the wimax and netdev devices, upload the firmware [using
+ * _bus_bm_*()], call _bus_dev_start() to finalize the setup of the
+ * communication with the device and then will start to talk to it to
+ * finnish setting it up.
+ */
+static
+int i2400mu_probe(struct usb_interface *iface,
+		  const struct usb_device_id *id)
+{
+	int result;
+	struct net_device *net_dev;
+	struct device *dev = &iface->dev;
+	struct i2400m *i2400m;
+	struct i2400mu *i2400mu;
+	struct usb_device *usb_dev = interface_to_usbdev(iface);
+
+	if (iface->cur_altsetting->desc.bNumEndpoints < 4)
+		return -ENODEV;
+
+	if (usb_dev->speed != USB_SPEED_HIGH)
+		dev_err(dev, "device not connected as high speed\n");
+
+	/* Allocate instance [calls i2400m_netdev_setup() on it]. */
+	result = -ENOMEM;
+	net_dev = alloc_netdev(sizeof(*i2400mu), "wmx%d", NET_NAME_UNKNOWN,
+			       i2400mu_netdev_setup);
+	if (net_dev == NULL) {
+		dev_err(dev, "no memory for network device instance\n");
+		goto error_alloc_netdev;
+	}
+	SET_NETDEV_DEV(net_dev, dev);
+	SET_NETDEV_DEVTYPE(net_dev, &i2400mu_type);
+	i2400m = net_dev_to_i2400m(net_dev);
+	i2400mu = container_of(i2400m, struct i2400mu, i2400m);
+	i2400m->wimax_dev.net_dev = net_dev;
+	i2400mu->usb_dev = usb_get_dev(usb_dev);
+	i2400mu->usb_iface = iface;
+	usb_set_intfdata(iface, i2400mu);
+
+	i2400m->bus_tx_block_size = I2400MU_BLK_SIZE;
+	/*
+	 * Room required in the Tx queue for USB message to accommodate
+	 * a smallest payload while allocating header space is 16 bytes.
+	 * Adding this room  for the new tx message increases the
+	 * possibilities of including any payload with size <= 16 bytes.
+	 */
+	i2400m->bus_tx_room_min = I2400MU_BLK_SIZE;
+	i2400m->bus_pl_size_max = I2400MU_PL_SIZE_MAX;
+	i2400m->bus_setup = NULL;
+	i2400m->bus_dev_start = i2400mu_bus_dev_start;
+	i2400m->bus_dev_stop = i2400mu_bus_dev_stop;
+	i2400m->bus_release = NULL;
+	i2400m->bus_tx_kick = i2400mu_bus_tx_kick;
+	i2400m->bus_reset = i2400mu_bus_reset;
+	i2400m->bus_bm_retries = I2400M_USB_BOOT_RETRIES;
+	i2400m->bus_bm_cmd_send = i2400mu_bus_bm_cmd_send;
+	i2400m->bus_bm_wait_for_ack = i2400mu_bus_bm_wait_for_ack;
+	i2400m->bus_bm_mac_addr_impaired = 0;
+
+	switch (id->idProduct) {
+	case USB_DEVICE_ID_I6050:
+	case USB_DEVICE_ID_I6050_2:
+	case USB_DEVICE_ID_I6150:
+	case USB_DEVICE_ID_I6150_2:
+	case USB_DEVICE_ID_I6150_3:
+	case USB_DEVICE_ID_I6250:
+		i2400mu->i6050 = 1;
+		break;
+	default:
+		break;
+	}
+
+	if (i2400mu->i6050) {
+		i2400m->bus_fw_names = i2400mu_bus_fw_names_6050;
+		i2400mu->endpoint_cfg.bulk_out = 0;
+		i2400mu->endpoint_cfg.notification = 3;
+		i2400mu->endpoint_cfg.reset_cold = 2;
+		i2400mu->endpoint_cfg.bulk_in = 1;
+	} else {
+		i2400m->bus_fw_names = i2400mu_bus_fw_names_5x50;
+		i2400mu->endpoint_cfg.bulk_out = 0;
+		i2400mu->endpoint_cfg.notification = 1;
+		i2400mu->endpoint_cfg.reset_cold = 2;
+		i2400mu->endpoint_cfg.bulk_in = 3;
+	}
+#ifdef CONFIG_PM
+	iface->needs_remote_wakeup = 1;		/* autosuspend (15s delay) */
+	device_init_wakeup(dev, 1);
+	pm_runtime_set_autosuspend_delay(&usb_dev->dev, 15000);
+	usb_enable_autosuspend(usb_dev);
+#endif
+
+	result = i2400m_setup(i2400m, I2400M_BRI_MAC_REINIT);
+	if (result < 0) {
+		dev_err(dev, "cannot setup device: %d\n", result);
+		goto error_setup;
+	}
+	i2400mu_debugfs_add(i2400mu);
+	return 0;
+
+error_setup:
+	usb_set_intfdata(iface, NULL);
+	usb_put_dev(i2400mu->usb_dev);
+	free_netdev(net_dev);
+error_alloc_netdev:
+	return result;
+}
+
+
+/*
+ * Disconnect a i2400m from the system.
+ *
+ * i2400m_stop() has been called before, so al the rx and tx contexts
+ * have been taken down already. Make sure the queue is stopped,
+ * unregister netdev and i2400m, free and kill.
+ */
+static
+void i2400mu_disconnect(struct usb_interface *iface)
+{
+	struct i2400mu *i2400mu = usb_get_intfdata(iface);
+	struct i2400m *i2400m = &i2400mu->i2400m;
+	struct net_device *net_dev = i2400m->wimax_dev.net_dev;
+	struct device *dev = &iface->dev;
+
+	d_fnstart(3, dev, "(iface %p i2400m %p)\n", iface, i2400m);
+
+	debugfs_remove_recursive(i2400mu->debugfs_dentry);
+	i2400m_release(i2400m);
+	usb_set_intfdata(iface, NULL);
+	usb_put_dev(i2400mu->usb_dev);
+	free_netdev(net_dev);
+	d_fnend(3, dev, "(iface %p i2400m %p) = void\n", iface, i2400m);
+}
+
+
+/*
+ * Get the device ready for USB port or system standby and hibernation
+ *
+ * USB port and system standby are handled the same.
+ *
+ * When the system hibernates, the USB device is powered down and then
+ * up, so we don't really have to do much here, as it will be seen as
+ * a reconnect. Still for simplicity we consider this case the same as
+ * suspend, so that the device has a chance to do notify the base
+ * station (if connected).
+ *
+ * So at the end, the three cases require common handling.
+ *
+ * If at the time of this call the device's firmware is not loaded,
+ * nothing has to be done. Note we can be "loose" about not reading
+ * i2400m->updown under i2400m->init_mutex. If it happens to change
+ * inmediately, other parts of the call flow will fail and effectively
+ * catch it.
+ *
+ * If the firmware is loaded, we need to:
+ *
+ *  - tell the device to go into host interface power save mode, wait
+ *    for it to ack
+ *
+ *    This is quite more interesting than it is; we need to execute a
+ *    command, but this time, we don't want the code in usb-{tx,rx}.c
+ *    to call the usb_autopm_get/put_interface() barriers as it'd
+ *    deadlock, so we need to decrement i2400mu->do_autopm, that acts
+ *    as a poor man's semaphore. Ugly, but it works.
+ *
+ *    As well, the device might refuse going to sleep for whichever
+ *    reason. In this case we just fail. For system suspend/hibernate,
+ *    we *can't* fail. We check PMSG_IS_AUTO to see if the
+ *    suspend call comes from the USB stack or from the system and act
+ *    in consequence.
+ *
+ *  - stop the notification endpoint polling
+ */
+static
+int i2400mu_suspend(struct usb_interface *iface, pm_message_t pm_msg)
+{
+	int result = 0;
+	struct device *dev = &iface->dev;
+	struct i2400mu *i2400mu = usb_get_intfdata(iface);
+	unsigned is_autosuspend = 0;
+	struct i2400m *i2400m = &i2400mu->i2400m;
+
+#ifdef CONFIG_PM
+	if (PMSG_IS_AUTO(pm_msg))
+		is_autosuspend = 1;
+#endif
+
+	d_fnstart(3, dev, "(iface %p pm_msg %u)\n", iface, pm_msg.event);
+	rmb();		/* see i2400m->updown's documentation  */
+	if (i2400m->updown == 0)
+		goto no_firmware;
+	if (i2400m->state == I2400M_SS_DATA_PATH_CONNECTED && is_autosuspend) {
+		/* ugh -- the device is connected and this suspend
+		 * request is an autosuspend one (not a system standby
+		 * / hibernate).
+		 *
+		 * The only way the device can go to standby is if the
+		 * link with the base station is in IDLE mode; that
+		 * were the case, we'd be in status
+		 * I2400M_SS_CONNECTED_IDLE. But we are not.
+		 *
+		 * If we *tell* him to go power save now, it'll reset
+		 * as a precautionary measure, so if this is an
+		 * autosuspend thing, say no and it'll come back
+		 * later, when the link is IDLE
+		 */
+		result = -EBADF;
+		d_printf(1, dev, "fw up, link up, not-idle, autosuspend: "
+			 "not entering powersave\n");
+		goto error_not_now;
+	}
+	d_printf(1, dev, "fw up: entering powersave\n");
+	atomic_dec(&i2400mu->do_autopm);
+	result = i2400m_cmd_enter_powersave(i2400m);
+	atomic_inc(&i2400mu->do_autopm);
+	if (result < 0 && !is_autosuspend) {
+		/* System suspend, can't fail */
+		dev_err(dev, "failed to suspend, will reset on resume\n");
+		result = 0;
+	}
+	if (result < 0)
+		goto error_enter_powersave;
+	i2400mu_notification_release(i2400mu);
+	d_printf(1, dev, "powersave requested\n");
+error_enter_powersave:
+error_not_now:
+no_firmware:
+	d_fnend(3, dev, "(iface %p pm_msg %u) = %d\n",
+		iface, pm_msg.event, result);
+	return result;
+}
+
+
+static
+int i2400mu_resume(struct usb_interface *iface)
+{
+	int ret = 0;
+	struct device *dev = &iface->dev;
+	struct i2400mu *i2400mu = usb_get_intfdata(iface);
+	struct i2400m *i2400m = &i2400mu->i2400m;
+
+	d_fnstart(3, dev, "(iface %p)\n", iface);
+	rmb();		/* see i2400m->updown's documentation  */
+	if (i2400m->updown == 0) {
+		d_printf(1, dev, "fw was down, no resume needed\n");
+		goto out;
+	}
+	d_printf(1, dev, "fw was up, resuming\n");
+	i2400mu_notification_setup(i2400mu);
+	/* USB has flow control, so we don't need to give it time to
+	 * come back; otherwise, we'd use something like a get-state
+	 * command... */
+out:
+	d_fnend(3, dev, "(iface %p) = %d\n", iface, ret);
+	return ret;
+}
+
+
+static
+int i2400mu_reset_resume(struct usb_interface *iface)
+{
+	int result;
+	struct device *dev = &iface->dev;
+	struct i2400mu *i2400mu = usb_get_intfdata(iface);
+	struct i2400m *i2400m = &i2400mu->i2400m;
+
+	d_fnstart(3, dev, "(iface %p)\n", iface);
+	result = i2400m_dev_reset_handle(i2400m, "device reset on resume");
+	d_fnend(3, dev, "(iface %p) = %d\n", iface, result);
+	return result < 0 ? result : 0;
+}
+
+
+/*
+ * Another driver or user space is triggering a reset on the device
+ * which contains the interface passed as an argument. Cease IO and
+ * save any device state you need to restore.
+ *
+ * If you need to allocate memory here, use GFP_NOIO or GFP_ATOMIC, if
+ * you are in atomic context.
+ */
+static
+int i2400mu_pre_reset(struct usb_interface *iface)
+{
+	struct i2400mu *i2400mu = usb_get_intfdata(iface);
+	return i2400m_pre_reset(&i2400mu->i2400m);
+}
+
+
+/*
+ * The reset has completed.  Restore any saved device state and begin
+ * using the device again.
+ *
+ * If you need to allocate memory here, use GFP_NOIO or GFP_ATOMIC, if
+ * you are in atomic context.
+ */
+static
+int i2400mu_post_reset(struct usb_interface *iface)
+{
+	struct i2400mu *i2400mu = usb_get_intfdata(iface);
+	return i2400m_post_reset(&i2400mu->i2400m);
+}
+
+
+static
+struct usb_device_id i2400mu_id_table[] = {
+	{ USB_DEVICE(0x8086, USB_DEVICE_ID_I6050) },
+	{ USB_DEVICE(0x8086, USB_DEVICE_ID_I6050_2) },
+	{ USB_DEVICE(0x8087, USB_DEVICE_ID_I6150) },
+	{ USB_DEVICE(0x8087, USB_DEVICE_ID_I6150_2) },
+	{ USB_DEVICE(0x8087, USB_DEVICE_ID_I6150_3) },
+	{ USB_DEVICE(0x8086, USB_DEVICE_ID_I6250) },
+	{ USB_DEVICE(0x8086, 0x0181) },
+	{ USB_DEVICE(0x8086, 0x1403) },
+	{ USB_DEVICE(0x8086, 0x1405) },
+	{ USB_DEVICE(0x8086, 0x0180) },
+	{ USB_DEVICE(0x8086, 0x0182) },
+	{ USB_DEVICE(0x8086, 0x1406) },
+	{ USB_DEVICE(0x8086, 0x1403) },
+	{ },
+};
+MODULE_DEVICE_TABLE(usb, i2400mu_id_table);
+
+
+static
+struct usb_driver i2400mu_driver = {
+	.name = KBUILD_MODNAME,
+	.suspend = i2400mu_suspend,
+	.resume = i2400mu_resume,
+	.reset_resume = i2400mu_reset_resume,
+	.probe = i2400mu_probe,
+	.disconnect = i2400mu_disconnect,
+	.pre_reset = i2400mu_pre_reset,
+	.post_reset = i2400mu_post_reset,
+	.id_table = i2400mu_id_table,
+	.supports_autosuspend = 1,
+};
+
+static
+int __init i2400mu_driver_init(void)
+{
+	d_parse_params(D_LEVEL, D_LEVEL_SIZE, i2400mu_debug_params,
+		       "i2400m_usb.debug");
+	return usb_register(&i2400mu_driver);
+}
+module_init(i2400mu_driver_init);
+
+
+static
+void __exit i2400mu_driver_exit(void)
+{
+	usb_deregister(&i2400mu_driver);
+}
+module_exit(i2400mu_driver_exit);
+
+MODULE_AUTHOR("Intel Corporation <linux-wimax@intel.com>");
+MODULE_DESCRIPTION("Driver for USB based Intel Wireless WiMAX Connection 2400M "
+		   "(5x50 & 6050)");
+MODULE_LICENSE("GPL");
+MODULE_FIRMWARE(I2400MU_FW_FILE_NAME_v1_5);
+MODULE_FIRMWARE(I6050U_FW_FILE_NAME_v1_5);
diff --git a/drivers/staging/wimax/id-table.c b/drivers/staging/wimax/id-table.c
new file mode 100644
index 000000000000..0e6f4aa87bc9
--- /dev/null
+++ b/drivers/staging/wimax/id-table.c
@@ -0,0 +1,130 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Linux WiMAX
+ * Mappping of generic netlink family IDs to net devices
+ *
+ * Copyright (C) 2005-2006 Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *
+ * We assign a single generic netlink family ID to each device (to
+ * simplify lookup).
+ *
+ * We need a way to map family ID to a wimax_dev pointer.
+ *
+ * The idea is to use a very simple lookup. Using a netlink attribute
+ * with (for example) the interface name implies a heavier search over
+ * all the network devices; seemed kind of a waste given that we know
+ * we are looking for a WiMAX device and that most systems will have
+ * just a single WiMAX adapter.
+ *
+ * We put all the WiMAX devices in the system in a linked list and
+ * match the generic link family ID against the list.
+ *
+ * By using a linked list, the case of a single adapter in the system
+ * becomes (almost) no overhead, while still working for many more. If
+ * it ever goes beyond two, I'll be surprised.
+ */
+#include <linux/device.h>
+#include <net/genetlink.h>
+#include <linux/netdevice.h>
+#include <linux/list.h>
+#include "linux-wimax.h"
+#include "wimax-internal.h"
+
+
+#define D_SUBMODULE id_table
+#include "debug-levels.h"
+
+
+static DEFINE_SPINLOCK(wimax_id_table_lock);
+static struct list_head wimax_id_table = LIST_HEAD_INIT(wimax_id_table);
+
+
+/*
+ * wimax_id_table_add - add a gennetlink familiy ID / wimax_dev mapping
+ *
+ * @wimax_dev: WiMAX device descriptor to associate to the Generic
+ *     Netlink family ID.
+ *
+ * Look for an empty spot in the ID table; if none found, double the
+ * table's size and get the first spot.
+ */
+void wimax_id_table_add(struct wimax_dev *wimax_dev)
+{
+	d_fnstart(3, NULL, "(wimax_dev %p)\n", wimax_dev);
+	spin_lock(&wimax_id_table_lock);
+	list_add(&wimax_dev->id_table_node, &wimax_id_table);
+	spin_unlock(&wimax_id_table_lock);
+	d_fnend(3, NULL, "(wimax_dev %p)\n", wimax_dev);
+}
+
+
+/*
+ * wimax_get_netdev_by_info - lookup a wimax_dev from the gennetlink info
+ *
+ * The generic netlink family ID has been filled out in the
+ * nlmsghdr->nlmsg_type field, so we pull it from there, look it up in
+ * the mapping table and reference the wimax_dev.
+ *
+ * When done, the reference should be dropped with
+ * 'dev_put(wimax_dev->net_dev)'.
+ */
+struct wimax_dev *wimax_dev_get_by_genl_info(
+	struct genl_info *info, int ifindex)
+{
+	struct wimax_dev *wimax_dev = NULL;
+
+	d_fnstart(3, NULL, "(info %p ifindex %d)\n", info, ifindex);
+	spin_lock(&wimax_id_table_lock);
+	list_for_each_entry(wimax_dev, &wimax_id_table, id_table_node) {
+		if (wimax_dev->net_dev->ifindex == ifindex) {
+			dev_hold(wimax_dev->net_dev);
+			goto found;
+		}
+	}
+	wimax_dev = NULL;
+	d_printf(1, NULL, "wimax: no devices found with ifindex %d\n",
+		 ifindex);
+found:
+	spin_unlock(&wimax_id_table_lock);
+	d_fnend(3, NULL, "(info %p ifindex %d) = %p\n",
+		info, ifindex, wimax_dev);
+	return wimax_dev;
+}
+
+
+/*
+ * wimax_id_table_rm - Remove a gennetlink familiy ID / wimax_dev mapping
+ *
+ * @id: family ID to remove from the table
+ */
+void wimax_id_table_rm(struct wimax_dev *wimax_dev)
+{
+	spin_lock(&wimax_id_table_lock);
+	list_del_init(&wimax_dev->id_table_node);
+	spin_unlock(&wimax_id_table_lock);
+}
+
+
+/*
+ * Release the gennetlink family id / mapping table
+ *
+ * On debug, verify that the table is empty upon removal. We want the
+ * code always compiled, to ensure it doesn't bit rot. It will be
+ * compiled out if CONFIG_BUG is disabled.
+ */
+void wimax_id_table_release(void)
+{
+	struct wimax_dev *wimax_dev;
+
+#ifndef CONFIG_BUG
+	return;
+#endif
+	spin_lock(&wimax_id_table_lock);
+	list_for_each_entry(wimax_dev, &wimax_id_table, id_table_node) {
+		pr_err("BUG: %s wimax_dev %p ifindex %d not cleared\n",
+		       __func__, wimax_dev, wimax_dev->net_dev->ifindex);
+		WARN_ON(1);
+	}
+	spin_unlock(&wimax_id_table_lock);
+}
diff --git a/drivers/staging/wimax/linux-wimax-debug.h b/drivers/staging/wimax/linux-wimax-debug.h
new file mode 100644
index 000000000000..5b5ec405143b
--- /dev/null
+++ b/drivers/staging/wimax/linux-wimax-debug.h
@@ -0,0 +1,491 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Linux WiMAX
+ * Collection of tools to manage debug operations.
+ *
+ * Copyright (C) 2005-2007 Intel Corporation
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *
+ * Don't #include this file directly, read on!
+ *
+ * EXECUTING DEBUGGING ACTIONS OR NOT
+ *
+ * The main thing this framework provides is decission power to take a
+ * debug action (like printing a message) if the current debug level
+ * allows it.
+ *
+ * The decission power is at two levels: at compile-time (what does
+ * not make it is compiled out) and at run-time. The run-time
+ * selection is done per-submodule (as they are declared by the user
+ * of the framework).
+ *
+ * A call to d_test(L) (L being the target debug level) returns true
+ * if the action should be taken because the current debug levels
+ * allow it (both compile and run time).
+ *
+ * It follows that a call to d_test() that can be determined to be
+ * always false at compile time will get the code depending on it
+ * compiled out by optimization.
+ *
+ * DEBUG LEVELS
+ *
+ * It is up to the caller to define how much a debugging level is.
+ *
+ * Convention sets 0 as "no debug" (so an action marked as debug level 0
+ * will always be taken). The increasing debug levels are used for
+ * increased verbosity.
+ *
+ * USAGE
+ *
+ * Group the code in modules and submodules inside each module [which
+ * in most cases maps to Linux modules and .c files that compose
+ * those].
+ *
+ * For each module, there is:
+ *
+ *  - a MODULENAME (single word, legal C identifier)
+ *
+ *  - a debug-levels.h header file that declares the list of
+ *    submodules and that is included by all .c files that use
+ *    the debugging tools. The file name can be anything.
+ *
+ *  - some (optional) .c code to manipulate the runtime debug levels
+ *    through debugfs.
+ *
+ * The debug-levels.h file would look like:
+ *
+ *     #ifndef __debug_levels__h__
+ *     #define __debug_levels__h__
+ *
+ *     #define D_MODULENAME modulename
+ *     #define D_MASTER 10
+ *
+ *     #include "linux-wimax-debug.h"
+ *
+ *     enum d_module {
+ *             D_SUBMODULE_DECLARE(submodule_1),
+ *             D_SUBMODULE_DECLARE(submodule_2),
+ *             ...
+ *             D_SUBMODULE_DECLARE(submodule_N)
+ *     };
+ *
+ *     #endif
+ *
+ * D_MASTER is the maximum compile-time debug level; any debug actions
+ * above this will be out. D_MODULENAME is the module name (legal C
+ * identifier), which has to be unique for each module (to avoid
+ * namespace collisions during linkage). Note those #defines need to
+ * be done before #including debug.h
+ *
+ * We declare N different submodules whose debug level can be
+ * independently controlled during runtime.
+ *
+ * In a .c file of the module (and only in one of them), define the
+ * following code:
+ *
+ *     struct d_level D_LEVEL[] = {
+ *             D_SUBMODULE_DEFINE(submodule_1),
+ *             D_SUBMODULE_DEFINE(submodule_2),
+ *             ...
+ *             D_SUBMODULE_DEFINE(submodule_N),
+ *     };
+ *     size_t D_LEVEL_SIZE = ARRAY_SIZE(D_LEVEL);
+ *
+ * Externs for d_level_MODULENAME and d_level_size_MODULENAME are used
+ * and declared in this file using the D_LEVEL and D_LEVEL_SIZE macros
+ * #defined also in this file.
+ *
+ * To manipulate from user space the levels, create a debugfs dentry
+ * and then register each submodule with:
+ *
+ *     d_level_register_debugfs("PREFIX_", submodule_X, parent);
+ *
+ * Where PREFIX_ is a name of your chosing. This will create debugfs
+ * file with a single numeric value that can be use to tweak it. To
+ * remove the entires, just use debugfs_remove_recursive() on 'parent'.
+ *
+ * NOTE: remember that even if this will show attached to some
+ *     particular instance of a device, the settings are *global*.
+ *
+ * On each submodule (for example, .c files), the debug infrastructure
+ * should be included like this:
+ *
+ *     #define D_SUBMODULE submodule_x     // matches one in debug-levels.h
+ *     #include "debug-levels.h"
+ *
+ * after #including all your include files.
+ *
+ * Now you can use the d_*() macros below [d_test(), d_fnstart(),
+ * d_fnend(), d_printf(), d_dump()].
+ *
+ * If their debug level is greater than D_MASTER, they will be
+ * compiled out.
+ *
+ * If their debug level is lower or equal than D_MASTER but greater
+ * than the current debug level of their submodule, they'll be
+ * ignored.
+ *
+ * Otherwise, the action will be performed.
+ */
+#ifndef __debug__h__
+#define __debug__h__
+
+#include <linux/types.h>
+#include <linux/slab.h>
+
+struct device;
+
+/* Backend stuff */
+
+/*
+ * Debug backend: generate a message header from a 'struct device'
+ *
+ * @head: buffer where to place the header
+ * @head_size: length of @head
+ * @dev: pointer to device used to generate a header from. If NULL,
+ *     an empty ("") header is generated.
+ */
+static inline
+void __d_head(char *head, size_t head_size,
+	      struct device *dev)
+{
+	if (dev == NULL)
+		head[0] = 0;
+	else if ((unsigned long)dev < 4096) {
+		printk(KERN_ERR "E: Corrupt dev %p\n", dev);
+		WARN_ON(1);
+	} else
+		snprintf(head, head_size, "%s %s: ",
+			 dev_driver_string(dev), dev_name(dev));
+}
+
+
+/*
+ * Debug backend: log some message if debugging is enabled
+ *
+ * @l: intended debug level
+ * @tag: tag to prefix the message with
+ * @dev: 'struct device' associated to this message
+ * @f: printf-like format and arguments
+ *
+ * Note this is optimized out if it doesn't pass the compile-time
+ * check; however, it is *always* compiled. This is useful to make
+ * sure the printf-like formats and variables are always checked and
+ * they don't get bit rot if you have all the debugging disabled.
+ */
+#define _d_printf(l, tag, dev, f, a...)					\
+do {									\
+	char head[64];							\
+	if (!d_test(l))							\
+		break;							\
+	__d_head(head, sizeof(head), dev);				\
+	printk(KERN_ERR "%s%s%s: " f, head, __func__, tag, ##a);	\
+} while (0)
+
+
+/*
+ * CPP syntactic sugar to generate A_B like symbol names when one of
+ * the arguments is a preprocessor #define.
+ */
+#define __D_PASTE__(varname, modulename) varname##_##modulename
+#define __D_PASTE(varname, modulename) (__D_PASTE__(varname, modulename))
+#define _D_SUBMODULE_INDEX(_name) (D_SUBMODULE_DECLARE(_name))
+
+
+/*
+ * Store a submodule's runtime debug level and name
+ */
+struct d_level {
+	u8 level;
+	const char *name;
+};
+
+
+/*
+ * List of available submodules and their debug levels
+ *
+ * We call them d_level_MODULENAME and d_level_size_MODULENAME; the
+ * macros D_LEVEL and D_LEVEL_SIZE contain the name already for
+ * convenience.
+ *
+ * This array and the size are defined on some .c file that is part of
+ * the current module.
+ */
+#define D_LEVEL __D_PASTE(d_level, D_MODULENAME)
+#define D_LEVEL_SIZE __D_PASTE(d_level_size, D_MODULENAME)
+
+extern struct d_level D_LEVEL[];
+extern size_t D_LEVEL_SIZE;
+
+
+/*
+ * Frontend stuff
+ *
+ *
+ * Stuff you need to declare prior to using the actual "debug" actions
+ * (defined below).
+ */
+
+#ifndef D_MODULENAME
+#error D_MODULENAME is not defined in your debug-levels.h file
+/**
+ * D_MODULE - Name of the current module
+ *
+ * #define in your module's debug-levels.h, making sure it is
+ * unique. This has to be a legal C identifier.
+ */
+#define D_MODULENAME undefined_modulename
+#endif
+
+
+#ifndef D_MASTER
+#warning D_MASTER not defined, but debug.h included! [see docs]
+/**
+ * D_MASTER - Compile time maximum debug level
+ *
+ * #define in your debug-levels.h file to the maximum debug level the
+ * runtime code will be allowed to have. This allows you to provide a
+ * main knob.
+ *
+ * Anything above that level will be optimized out of the compile.
+ *
+ * Defaults to zero (no debug code compiled in).
+ *
+ * Maximum one definition per module (at the debug-levels.h file).
+ */
+#define D_MASTER 0
+#endif
+
+#ifndef D_SUBMODULE
+#error D_SUBMODULE not defined, but debug.h included! [see docs]
+/**
+ * D_SUBMODULE - Name of the current submodule
+ *
+ * #define in your submodule .c file before #including debug-levels.h
+ * to the name of the current submodule as previously declared and
+ * defined with D_SUBMODULE_DECLARE() (in your module's
+ * debug-levels.h) and D_SUBMODULE_DEFINE().
+ *
+ * This is used to provide runtime-control over the debug levels.
+ *
+ * Maximum one per .c file! Can be shared among different .c files
+ * (meaning they belong to the same submodule categorization).
+ */
+#define D_SUBMODULE undefined_module
+#endif
+
+
+/**
+ * D_SUBMODULE_DECLARE - Declare a submodule for runtime debug level control
+ *
+ * @_name: name of the submodule, restricted to the chars that make up a
+ *     valid C identifier ([a-zA-Z0-9_]).
+ *
+ * Declare in the module's debug-levels.h header file as:
+ *
+ * enum d_module {
+ *         D_SUBMODULE_DECLARE(submodule_1),
+ *         D_SUBMODULE_DECLARE(submodule_2),
+ *         D_SUBMODULE_DECLARE(submodule_3),
+ * };
+ *
+ * Some corresponding .c file needs to have a matching
+ * D_SUBMODULE_DEFINE().
+ */
+#define D_SUBMODULE_DECLARE(_name) __D_SUBMODULE_##_name
+
+
+/**
+ * D_SUBMODULE_DEFINE - Define a submodule for runtime debug level control
+ *
+ * @_name: name of the submodule, restricted to the chars that make up a
+ *     valid C identifier ([a-zA-Z0-9_]).
+ *
+ * Use once per module (in some .c file) as:
+ *
+ * static
+ * struct d_level d_level_SUBMODULENAME[] = {
+ *         D_SUBMODULE_DEFINE(submodule_1),
+ *         D_SUBMODULE_DEFINE(submodule_2),
+ *         D_SUBMODULE_DEFINE(submodule_3),
+ * };
+ * size_t d_level_size_SUBDMODULENAME = ARRAY_SIZE(d_level_SUBDMODULENAME);
+ *
+ * Matching D_SUBMODULE_DECLARE()s have to be present in a
+ * debug-levels.h header file.
+ */
+#define D_SUBMODULE_DEFINE(_name)		\
+[__D_SUBMODULE_##_name] = {			\
+	.level = 0,				\
+	.name = #_name				\
+}
+
+
+
+/* The actual "debug" operations */
+
+
+/**
+ * d_test - Returns true if debugging should be enabled
+ *
+ * @l: intended debug level (unsigned)
+ *
+ * If the master debug switch is enabled and the current settings are
+ * higher or equal to the requested level, then debugging
+ * output/actions should be enabled.
+ *
+ * NOTE:
+ *
+ * This needs to be coded so that it can be evaluated in compile
+ * time; this is why the ugly BUG_ON() is placed in there, so the
+ * D_MASTER evaluation compiles all out if it is compile-time false.
+ */
+#define d_test(l)							\
+({									\
+	unsigned __l = l;	/* type enforcer */			\
+	(D_MASTER) >= __l						\
+	&& ({								\
+		BUG_ON(_D_SUBMODULE_INDEX(D_SUBMODULE) >= D_LEVEL_SIZE);\
+		D_LEVEL[_D_SUBMODULE_INDEX(D_SUBMODULE)].level >= __l;	\
+	});								\
+})
+
+
+/**
+ * d_fnstart - log message at function start if debugging enabled
+ *
+ * @l: intended debug level
+ * @_dev: 'struct device' pointer, NULL if none (for context)
+ * @f: printf-like format and arguments
+ */
+#define d_fnstart(l, _dev, f, a...) _d_printf(l, " FNSTART", _dev, f, ## a)
+
+
+/**
+ * d_fnend - log message at function end if debugging enabled
+ *
+ * @l: intended debug level
+ * @_dev: 'struct device' pointer, NULL if none (for context)
+ * @f: printf-like format and arguments
+ */
+#define d_fnend(l, _dev, f, a...) _d_printf(l, " FNEND", _dev, f, ## a)
+
+
+/**
+ * d_printf - log message if debugging enabled
+ *
+ * @l: intended debug level
+ * @_dev: 'struct device' pointer, NULL if none (for context)
+ * @f: printf-like format and arguments
+ */
+#define d_printf(l, _dev, f, a...) _d_printf(l, "", _dev, f, ## a)
+
+
+/**
+ * d_dump - log buffer hex dump if debugging enabled
+ *
+ * @l: intended debug level
+ * @_dev: 'struct device' pointer, NULL if none (for context)
+ * @f: printf-like format and arguments
+ */
+#define d_dump(l, dev, ptr, size)			\
+do {							\
+	char head[64];					\
+	if (!d_test(l))					\
+		break;					\
+	__d_head(head, sizeof(head), dev);		\
+	print_hex_dump(KERN_ERR, head, 0, 16, 1,	\
+		       ((void *) ptr), (size), 0);	\
+} while (0)
+
+
+/**
+ * Export a submodule's debug level over debugfs as PREFIXSUBMODULE
+ *
+ * @prefix: string to prefix the name with
+ * @submodule: name of submodule (not a string, just the name)
+ * @dentry: debugfs parent dentry
+ *
+ * For removing, just use debugfs_remove_recursive() on the parent.
+ */
+#define d_level_register_debugfs(prefix, name, parent)			\
+({									\
+	debugfs_create_u8(						\
+		prefix #name, 0600, parent,				\
+		&(D_LEVEL[__D_SUBMODULE_ ## name].level));		\
+})
+
+
+static inline
+void d_submodule_set(struct d_level *d_level, size_t d_level_size,
+		     const char *submodule, u8 level, const char *tag)
+{
+	struct d_level *itr, *top;
+	int index = -1;
+
+	for (itr = d_level, top = itr + d_level_size; itr < top; itr++) {
+		index++;
+		if (itr->name == NULL) {
+			printk(KERN_ERR "%s: itr->name NULL?? (%p, #%d)\n",
+			       tag, itr, index);
+			continue;
+		}
+		if (!strcmp(itr->name, submodule)) {
+			itr->level = level;
+			return;
+		}
+	}
+	printk(KERN_ERR "%s: unknown submodule %s\n", tag, submodule);
+}
+
+
+/**
+ * d_parse_params - Parse a string with debug parameters from the
+ * command line
+ *
+ * @d_level: level structure (D_LEVEL)
+ * @d_level_size: number of items in the level structure
+ *     (D_LEVEL_SIZE).
+ * @_params: string with the parameters; this is a space (not tab!)
+ *     separated list of NAME:VALUE, where value is the debug level
+ *     and NAME is the name of the submodule.
+ * @tag: string for error messages (example: MODULE.ARGNAME).
+ */
+static inline
+void d_parse_params(struct d_level *d_level, size_t d_level_size,
+		    const char *_params, const char *tag)
+{
+	char submodule[130], *params, *params_orig, *token, *colon;
+	unsigned level, tokens;
+
+	if (_params == NULL)
+		return;
+	params_orig = kstrdup(_params, GFP_KERNEL);
+	params = params_orig;
+	while (1) {
+		token = strsep(&params, " ");
+		if (token == NULL)
+			break;
+		if (*token == '\0')	/* eat joint spaces */
+			continue;
+		/* kernel's sscanf %s eats until whitespace, so we
+		 * replace : by \n so it doesn't get eaten later by
+		 * strsep */
+		colon = strchr(token, ':');
+		if (colon != NULL)
+			*colon = '\n';
+		tokens = sscanf(token, "%s\n%u", submodule, &level);
+		if (colon != NULL)
+			*colon = ':';	/* set back, for error messages */
+		if (tokens == 2)
+			d_submodule_set(d_level, d_level_size,
+					submodule, level, tag);
+		else
+			printk(KERN_ERR "%s: can't parse '%s' as a "
+			       "SUBMODULE:LEVEL (%d tokens)\n",
+			       tag, token, tokens);
+	}
+	kfree(params_orig);
+}
+
+#endif /* #ifndef __debug__h__ */
diff --git a/drivers/staging/wimax/linux-wimax.h b/drivers/staging/wimax/linux-wimax.h
new file mode 100644
index 000000000000..9f6b77af2f6d
--- /dev/null
+++ b/drivers/staging/wimax/linux-wimax.h
@@ -0,0 +1,239 @@
+/*
+ * Linux WiMax
+ * API for user space
+ *
+ *
+ * Copyright (C) 2007-2008 Intel Corporation. All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *
+ * Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *  - Initial implementation
+ *
+ *
+ * This file declares the user/kernel protocol that is spoken over
+ * Generic Netlink, as well as any type declaration that is to be used
+ * by kernel and user space.
+ *
+ * It is intended for user space to clone it verbatim to use it as a
+ * primary reference for definitions.
+ *
+ * Stuff intended for kernel usage as well as full protocol and stack
+ * documentation is rooted in include/net/wimax.h.
+ */
+
+#ifndef __LINUX__WIMAX_H__
+#define __LINUX__WIMAX_H__
+
+#include <linux/types.h>
+
+enum {
+	/**
+	 * Version of the interface (unsigned decimal, MMm, max 25.5)
+	 * M - Major: change if removing or modifying an existing call.
+	 * m - minor: change when adding a new call
+	 */
+	WIMAX_GNL_VERSION = 01,
+	/* Generic NetLink attributes */
+	WIMAX_GNL_ATTR_INVALID = 0x00,
+	WIMAX_GNL_ATTR_MAX = 10,
+};
+
+
+/*
+ * Generic NetLink operations
+ *
+ * Most of these map to an API call; _OP_ stands for operation, _RP_
+ * for reply and _RE_ for report (aka: signal).
+ */
+enum {
+	WIMAX_GNL_OP_MSG_FROM_USER,	/* User to kernel message */
+	WIMAX_GNL_OP_MSG_TO_USER,	/* Kernel to user message */
+	WIMAX_GNL_OP_RFKILL,	/* Run wimax_rfkill() */
+	WIMAX_GNL_OP_RESET,	/* Run wimax_rfkill() */
+	WIMAX_GNL_RE_STATE_CHANGE,	/* Report: status change */
+	WIMAX_GNL_OP_STATE_GET,		/* Request for current state */
+};
+
+
+/* Message from user / to user */
+enum {
+	WIMAX_GNL_MSG_IFIDX = 1,
+	WIMAX_GNL_MSG_PIPE_NAME,
+	WIMAX_GNL_MSG_DATA,
+};
+
+
+/*
+ * wimax_rfkill()
+ *
+ * The state of the radio (ON/OFF) is mapped to the rfkill subsystem's
+ * switch state (DISABLED/ENABLED).
+ */
+enum wimax_rf_state {
+	WIMAX_RF_OFF = 0,	/* Radio is off, rfkill on/enabled */
+	WIMAX_RF_ON = 1,	/* Radio is on, rfkill off/disabled */
+	WIMAX_RF_QUERY = 2,
+};
+
+/* Attributes */
+enum {
+	WIMAX_GNL_RFKILL_IFIDX = 1,
+	WIMAX_GNL_RFKILL_STATE,
+};
+
+
+/* Attributes for wimax_reset() */
+enum {
+	WIMAX_GNL_RESET_IFIDX = 1,
+};
+
+/* Attributes for wimax_state_get() */
+enum {
+	WIMAX_GNL_STGET_IFIDX = 1,
+};
+
+/*
+ * Attributes for the Report State Change
+ *
+ * For now we just have the old and new states; new attributes might
+ * be added later on.
+ */
+enum {
+	WIMAX_GNL_STCH_IFIDX = 1,
+	WIMAX_GNL_STCH_STATE_OLD,
+	WIMAX_GNL_STCH_STATE_NEW,
+};
+
+
+/**
+ * enum wimax_st - The different states of a WiMAX device
+ * @__WIMAX_ST_NULL: The device structure has been allocated and zeroed,
+ *     but still wimax_dev_add() hasn't been called. There is no state.
+ *
+ * @WIMAX_ST_DOWN: The device has been registered with the WiMAX and
+ *     networking stacks, but it is not initialized (normally that is
+ *     done with 'ifconfig DEV up' [or equivalent], which can upload
+ *     firmware and enable communications with the device).
+ *     In this state, the device is powered down and using as less
+ *     power as possible.
+ *     This state is the default after a call to wimax_dev_add(). It
+ *     is ok to have drivers move directly to %WIMAX_ST_UNINITIALIZED
+ *     or %WIMAX_ST_RADIO_OFF in _probe() after the call to
+ *     wimax_dev_add().
+ *     It is recommended that the driver leaves this state when
+ *     calling 'ifconfig DEV up' and enters it back on 'ifconfig DEV
+ *     down'.
+ *
+ * @__WIMAX_ST_QUIESCING: The device is being torn down, so no API
+ *     operations are allowed to proceed except the ones needed to
+ *     complete the device clean up process.
+ *
+ * @WIMAX_ST_UNINITIALIZED: [optional] Communication with the device
+ *     is setup, but the device still requires some configuration
+ *     before being operational.
+ *     Some WiMAX API calls might work.
+ *
+ * @WIMAX_ST_RADIO_OFF: The device is fully up; radio is off (wether
+ *     by hardware or software switches).
+ *     It is recommended to always leave the device in this state
+ *     after initialization.
+ *
+ * @WIMAX_ST_READY: The device is fully up and radio is on.
+ *
+ * @WIMAX_ST_SCANNING: [optional] The device has been instructed to
+ *     scan. In this state, the device cannot be actively connected to
+ *     a network.
+ *
+ * @WIMAX_ST_CONNECTING: The device is connecting to a network. This
+ *     state exists because in some devices, the connect process can
+ *     include a number of negotiations between user space, kernel
+ *     space and the device. User space needs to know what the device
+ *     is doing. If the connect sequence in a device is atomic and
+ *     fast, the device can transition directly to CONNECTED
+ *
+ * @WIMAX_ST_CONNECTED: The device is connected to a network.
+ *
+ * @__WIMAX_ST_INVALID: This is an invalid state used to mark the
+ *     maximum numeric value of states.
+ *
+ * Description:
+ *
+ * Transitions from one state to another one are atomic and can only
+ * be caused in kernel space with wimax_state_change(). To read the
+ * state, use wimax_state_get().
+ *
+ * States starting with __ are internal and shall not be used or
+ * referred to by drivers or userspace. They look ugly, but that's the
+ * point -- if any use is made non-internal to the stack, it is easier
+ * to catch on review.
+ *
+ * All API operations [with well defined exceptions] will take the
+ * device mutex before starting and then check the state. If the state
+ * is %__WIMAX_ST_NULL, %WIMAX_ST_DOWN, %WIMAX_ST_UNINITIALIZED or
+ * %__WIMAX_ST_QUIESCING, it will drop the lock and quit with
+ * -%EINVAL, -%ENOMEDIUM, -%ENOTCONN or -%ESHUTDOWN.
+ *
+ * The order of the definitions is important, so we can do numerical
+ * comparisons (eg: < %WIMAX_ST_RADIO_OFF means the device is not ready
+ * to operate).
+ */
+/*
+ * The allowed state transitions are described in the table below
+ * (states in rows can go to states in columns where there is an X):
+ *
+ *                                  UNINI   RADIO READY SCAN CONNEC CONNEC
+ *             NULL DOWN QUIESCING TIALIZED  OFF        NING  TING   TED
+ * NULL         -    x
+ * DOWN              -      x        x       x
+ * QUIESCING         x      -
+ * UNINITIALIZED            x        -       x
+ * RADIO_OFF                x                -     x
+ * READY                    x                x     -     x     x      x
+ * SCANNING                 x                x     x     -     x      x
+ * CONNECTING               x                x     x     x     -      x
+ * CONNECTED                x                x     x                  -
+ *
+ * This table not available in kernel-doc because the formatting messes it up.
+ */
+ enum wimax_st {
+	__WIMAX_ST_NULL = 0,
+	WIMAX_ST_DOWN,
+	__WIMAX_ST_QUIESCING,
+	WIMAX_ST_UNINITIALIZED,
+	WIMAX_ST_RADIO_OFF,
+	WIMAX_ST_READY,
+	WIMAX_ST_SCANNING,
+	WIMAX_ST_CONNECTING,
+	WIMAX_ST_CONNECTED,
+	__WIMAX_ST_INVALID			/* Always keep last */
+};
+
+
+#endif /* #ifndef __LINUX__WIMAX_H__ */
diff --git a/drivers/staging/wimax/net-wimax.h b/drivers/staging/wimax/net-wimax.h
new file mode 100644
index 000000000000..f578e345e2bd
--- /dev/null
+++ b/drivers/staging/wimax/net-wimax.h
@@ -0,0 +1,503 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Linux WiMAX
+ * Kernel space API for accessing WiMAX devices
+ *
+ * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *
+ * The WiMAX stack provides an API for controlling and managing the
+ * system's WiMAX devices. This API affects the control plane; the
+ * data plane is accessed via the network stack (netdev).
+ *
+ * Parts of the WiMAX stack API and notifications are exported to
+ * user space via Generic Netlink. In user space, libwimax (part of
+ * the wimax-tools package) provides a shim layer for accessing those
+ * calls.
+ *
+ * The API is standarized for all WiMAX devices and different drivers
+ * implement the backend support for it. However, device-specific
+ * messaging pipes are provided that can be used to issue commands and
+ * receive notifications in free form.
+ *
+ * Currently the messaging pipes are the only means of control as it
+ * is not known (due to the lack of more devices in the market) what
+ * will be a good abstraction layer. Expect this to change as more
+ * devices show in the market. This API is designed to be growable in
+ * order to address this problem.
+ *
+ * USAGE
+ *
+ * Embed a `struct wimax_dev` at the beginning of the device's
+ * private structure, initialize and register it. For details, see
+ * `struct wimax_dev`s documentation.
+ *
+ * Once this is done, wimax-tools's libwimaxll can be used to
+ * communicate with the driver from user space. You user space
+ * application does not have to forcibily use libwimaxll and can talk
+ * the generic netlink protocol directly if desired.
+ *
+ * Remember this is a very low level API that will to provide all of
+ * WiMAX features. Other daemons and services running in user space
+ * are the expected clients of it. They offer a higher level API that
+ * applications should use (an example of this is the Intel's WiMAX
+ * Network Service for the i2400m).
+ *
+ * DESIGN
+ *
+ * Although not set on final stone, this very basic interface is
+ * mostly completed. Remember this is meant to grow as new common
+ * operations are decided upon. New operations will be added to the
+ * interface, intent being on keeping backwards compatibility as much
+ * as possible.
+ *
+ * This layer implements a set of calls to control a WiMAX device,
+ * exposing a frontend to the rest of the kernel and user space (via
+ * generic netlink) and a backend implementation in the driver through
+ * function pointers.
+ *
+ * WiMAX devices have a state, and a kernel-only API allows the
+ * drivers to manipulate that state. State transitions are atomic, and
+ * only some of them are allowed (see `enum wimax_st`).
+ *
+ * Most API calls will set the state automatically; in most cases
+ * drivers have to only report state changes due to external
+ * conditions.
+ *
+ * All API operations are 'atomic', serialized through a mutex in the
+ * `struct wimax_dev`.
+ *
+ * EXPORTING TO USER SPACE THROUGH GENERIC NETLINK
+ *
+ * The API is exported to user space using generic netlink (other
+ * methods can be added as needed).
+ *
+ * There is a Generic Netlink Family named "WiMAX", where interfaces
+ * supporting the WiMAX interface receive commands and broadcast their
+ * signals over a multicast group named "msg".
+ *
+ * Mapping to the source/destination interface is done by an interface
+ * index attribute.
+ *
+ * For user-to-kernel traffic (commands) we use a function call
+ * marshalling mechanism, where a message X with attributes A, B, C
+ * sent from user space to kernel space means executing the WiMAX API
+ * call wimax_X(A, B, C), sending the results back as a message.
+ *
+ * Kernel-to-user (notifications or signals) communication is sent
+ * over multicast groups. This allows to have multiple applications
+ * monitoring them.
+ *
+ * Each command/signal gets assigned it's own attribute policy. This
+ * way the validator will verify that all the attributes in there are
+ * only the ones that should be for each command/signal. Thing of an
+ * attribute mapping to a type+argumentname for each command/signal.
+ *
+ * If we had a single policy for *all* commands/signals, after running
+ * the validator we'd have to check "does this attribute belong in
+ * here"?  for each one. It can be done manually, but it's just easier
+ * to have the validator do that job with multiple policies. As well,
+ * it makes it easier to later expand each command/signal signature
+ * without affecting others and keeping the namespace more or less
+ * sane. Not that it is too complicated, but it makes it even easier.
+ *
+ * No state information is maintained in the kernel for each user
+ * space connection (the connection is stateless).
+ *
+ * TESTING FOR THE INTERFACE AND VERSIONING
+ *
+ * If network interface X is a WiMAX device, there will be a Generic
+ * Netlink family named "WiMAX X" and the device will present a
+ * "wimax" directory in it's network sysfs directory
+ * (/sys/class/net/DEVICE/wimax) [used by HAL].
+ *
+ * The inexistence of any of these means the device does not support
+ * this WiMAX API.
+ *
+ * By querying the generic netlink controller, versioning information
+ * and the multicast groups available can be found. Applications using
+ * the interface can either rely on that or use the generic netlink
+ * controller to figure out which generic netlink commands/signals are
+ * supported.
+ *
+ * NOTE: this versioning is a last resort to avoid hard
+ *    incompatibilities. It is the intention of the design of this
+ *    stack not to introduce backward incompatible changes.
+ *
+ * The version code has to fit in one byte (restrictions imposed by
+ * generic netlink); we use `version / 10` for the major version and
+ * `version % 10` for the minor. This gives 9 minors for each major
+ * and 25 majors.
+ *
+ * The version change protocol is as follow:
+ *
+ * - Major versions: needs to be increased if an existing message/API
+ *   call is changed or removed. Doesn't need to be changed if a new
+ *   message is added.
+ *
+ * - Minor version: needs to be increased if new messages/API calls are
+ *   being added or some other consideration that doesn't impact the
+ *   user-kernel interface too much (like some kind of bug fix) and
+ *   that is kind of left up in the air to common sense.
+ *
+ * User space code should not try to work if the major version it was
+ * compiled for differs from what the kernel offers. As well, if the
+ * minor version of the kernel interface is lower than the one user
+ * space is expecting (the one it was compiled for), the kernel
+ * might be missing API calls; user space shall be ready to handle
+ * said condition. Use the generic netlink controller operations to
+ * find which ones are supported and which not.
+ *
+ * libwimaxll:wimaxll_open() takes care of checking versions.
+ *
+ * THE OPERATIONS:
+ *
+ * Each operation is defined in its on file (drivers/net/wimax/op-*.c)
+ * for clarity. The parts needed for an operation are:
+ *
+ *  - a function pointer in `struct wimax_dev`: optional, as the
+ *    operation might be implemented by the stack and not by the
+ *    driver.
+ *
+ *    All function pointers are named wimax_dev->op_*(), and drivers
+ *    must implement them except where noted otherwise.
+ *
+ *  - When exported to user space, a `struct nla_policy` to define the
+ *    attributes of the generic netlink command and a `struct genl_ops`
+ *    to define the operation.
+ *
+ * All the declarations for the operation codes (WIMAX_GNL_OP_<NAME>)
+ * and generic netlink attributes (WIMAX_GNL_<NAME>_*) are declared in
+ * include/linux/wimax.h; this file is intended to be cloned by user
+ * space to gain access to those declarations.
+ *
+ * A few caveats to remember:
+ *
+ *  - Need to define attribute numbers starting in 1; otherwise it
+ *    fails.
+ *
+ *  - the `struct genl_family` requires a maximum attribute id; when
+ *    defining the `struct nla_policy` for each message, it has to have
+ *    an array size of WIMAX_GNL_ATTR_MAX+1.
+ *
+ * The op_*() function pointers will not be called if the wimax_dev is
+ * in a state <= %WIMAX_ST_UNINITIALIZED. The exception is:
+ *
+ * - op_reset: can be called at any time after wimax_dev_add() has
+ *   been called.
+ *
+ * THE PIPE INTERFACE:
+ *
+ * This interface is kept intentionally simple. The driver can send
+ * and receive free-form messages to/from user space through a
+ * pipe. See drivers/net/wimax/op-msg.c for details.
+ *
+ * The kernel-to-user messages are sent with
+ * wimax_msg(). user-to-kernel messages are delivered via
+ * wimax_dev->op_msg_from_user().
+ *
+ * RFKILL:
+ *
+ * RFKILL support is built into the wimax_dev layer; the driver just
+ * needs to call wimax_report_rfkill_{hw,sw}() to inform of changes in
+ * the hardware or software RF kill switches. When the stack wants to
+ * turn the radio off, it will call wimax_dev->op_rfkill_sw_toggle(),
+ * which the driver implements.
+ *
+ * User space can set the software RF Kill switch by calling
+ * wimax_rfkill().
+ *
+ * The code for now only supports devices that don't require polling;
+ * If the device needs to be polled, create a self-rearming delayed
+ * work struct for polling or look into adding polled support to the
+ * WiMAX stack.
+ *
+ * When initializing the hardware (_probe), after calling
+ * wimax_dev_add(), query the device for it's RF Kill switches status
+ * and feed it back to the WiMAX stack using
+ * wimax_report_rfkill_{hw,sw}(). If any switch is missing, always
+ * report it as ON.
+ *
+ * NOTE: the wimax stack uses an inverted terminology to that of the
+ * RFKILL subsystem:
+ *
+ *  - ON: radio is ON, RFKILL is DISABLED or OFF.
+ *  - OFF: radio is OFF, RFKILL is ENABLED or ON.
+ *
+ * MISCELLANEOUS OPS:
+ *
+ * wimax_reset() can be used to reset the device to power on state; by
+ * default it issues a warm reset that maintains the same device
+ * node. If that is not possible, it falls back to a cold reset
+ * (device reconnect). The driver implements the backend to this
+ * through wimax_dev->op_reset().
+ */
+
+#ifndef __NET__WIMAX_H__
+#define __NET__WIMAX_H__
+
+#include "linux-wimax.h"
+#include <net/genetlink.h>
+#include <linux/netdevice.h>
+
+struct net_device;
+struct genl_info;
+struct wimax_dev;
+
+/**
+ * struct wimax_dev - Generic WiMAX device
+ *
+ * @net_dev: [fill] Pointer to the &struct net_device this WiMAX
+ *     device implements.
+ *
+ * @op_msg_from_user: [fill] Driver-specific operation to
+ *     handle a raw message from user space to the driver. The
+ *     driver can send messages to user space using with
+ *     wimax_msg_to_user().
+ *
+ * @op_rfkill_sw_toggle: [fill] Driver-specific operation to act on
+ *     userspace (or any other agent) requesting the WiMAX device to
+ *     change the RF Kill software switch (WIMAX_RF_ON or
+ *     WIMAX_RF_OFF).
+ *     If such hardware support is not present, it is assumed the
+ *     radio cannot be switched off and it is always on (and the stack
+ *     will error out when trying to switch it off). In such case,
+ *     this function pointer can be left as NULL.
+ *
+ * @op_reset: [fill] Driver specific operation to reset the
+ *     device.
+ *     This operation should always attempt first a warm reset that
+ *     does not disconnect the device from the bus and return 0.
+ *     If that fails, it should resort to some sort of cold or bus
+ *     reset (even if it implies a bus disconnection and device
+ *     disappearance). In that case, -ENODEV should be returned to
+ *     indicate the device is gone.
+ *     This operation has to be synchronous, and return only when the
+ *     reset is complete. In case of having had to resort to bus/cold
+ *     reset implying a device disconnection, the call is allowed to
+ *     return immediately.
+ *     NOTE: wimax_dev->mutex is NOT locked when this op is being
+ *     called; however, wimax_dev->mutex_reset IS locked to ensure
+ *     serialization of calls to wimax_reset().
+ *     See wimax_reset()'s documentation.
+ *
+ * @name: [fill] A way to identify this device. We need to register a
+ *     name with many subsystems (rfkill, workqueue creation, etc).
+ *     We can't use the network device name as that
+ *     might change and in some instances we don't know it yet (until
+ *     we don't call register_netdev()). So we generate an unique one
+ *     using the driver name and device bus id, place it here and use
+ *     it across the board. Recommended naming:
+ *     DRIVERNAME-BUSNAME:BUSID (dev->bus->name, dev->bus_id).
+ *
+ * @id_table_node: [private] link to the list of wimax devices kept by
+ *     id-table.c. Protected by it's own spinlock.
+ *
+ * @mutex: [private] Serializes all concurrent access and execution of
+ *     operations.
+ *
+ * @mutex_reset: [private] Serializes reset operations. Needs to be a
+ *     different mutex because as part of the reset operation, the
+ *     driver has to call back into the stack to do things such as
+ *     state change, that require wimax_dev->mutex.
+ *
+ * @state: [private] Current state of the WiMAX device.
+ *
+ * @rfkill: [private] integration into the RF-Kill infrastructure.
+ *
+ * @rf_sw: [private] State of the software radio switch (OFF/ON)
+ *
+ * @rf_hw: [private] State of the hardware radio switch (OFF/ON)
+ *
+ * @debugfs_dentry: [private] Used to hook up a debugfs entry. This
+ *     shows up in the debugfs root as wimax\:DEVICENAME.
+ *
+ * Description:
+ * This structure defines a common interface to access all WiMAX
+ * devices from different vendors and provides a common API as well as
+ * a free-form device-specific messaging channel.
+ *
+ * Usage:
+ *  1. Embed a &struct wimax_dev at *the beginning* the network
+ *     device structure so that netdev_priv() points to it.
+ *
+ *  2. memset() it to zero
+ *
+ *  3. Initialize with wimax_dev_init(). This will leave the WiMAX
+ *     device in the %__WIMAX_ST_NULL state.
+ *
+ *  4. Fill all the fields marked with [fill]; once called
+ *     wimax_dev_add(), those fields CANNOT be modified.
+ *
+ *  5. Call wimax_dev_add() *after* registering the network
+ *     device. This will leave the WiMAX device in the %WIMAX_ST_DOWN
+ *     state.
+ *     Protect the driver's net_device->open() against succeeding if
+ *     the wimax device state is lower than %WIMAX_ST_DOWN.
+ *
+ *  6. Select when the device is going to be turned on/initialized;
+ *     for example, it could be initialized on 'ifconfig up' (when the
+ *     netdev op 'open()' is called on the driver).
+ *
+ * When the device is initialized (at `ifconfig up` time, or right
+ * after calling wimax_dev_add() from _probe(), make sure the
+ * following steps are taken
+ *
+ *  a. Move the device to %WIMAX_ST_UNINITIALIZED. This is needed so
+ *     some API calls that shouldn't work until the device is ready
+ *     can be blocked.
+ *
+ *  b. Initialize the device. Make sure to turn the SW radio switch
+ *     off and move the device to state %WIMAX_ST_RADIO_OFF when
+ *     done. When just initialized, a device should be left in RADIO
+ *     OFF state until user space devices to turn it on.
+ *
+ *  c. Query the device for the state of the hardware rfkill switch
+ *     and call wimax_rfkill_report_hw() and wimax_rfkill_report_sw()
+ *     as needed. See below.
+ *
+ * wimax_dev_rm() undoes before unregistering the network device. Once
+ * wimax_dev_add() is called, the driver can get called on the
+ * wimax_dev->op_* function pointers
+ *
+ * CONCURRENCY:
+ *
+ * The stack provides a mutex for each device that will disallow API
+ * calls happening concurrently; thus, op calls into the driver
+ * through the wimax_dev->op*() function pointers will always be
+ * serialized and *never* concurrent.
+ *
+ * For locking, take wimax_dev->mutex is taken; (most) operations in
+ * the API have to check for wimax_dev_is_ready() to return 0 before
+ * continuing (this is done internally).
+ *
+ * REFERENCE COUNTING:
+ *
+ * The WiMAX device is reference counted by the associated network
+ * device. The only operation that can be used to reference the device
+ * is wimax_dev_get_by_genl_info(), and the reference it acquires has
+ * to be released with dev_put(wimax_dev->net_dev).
+ *
+ * RFKILL:
+ *
+ * At startup, both HW and SW radio switchess are assumed to be off.
+ *
+ * At initialization time [after calling wimax_dev_add()], have the
+ * driver query the device for the status of the software and hardware
+ * RF kill switches and call wimax_report_rfkill_hw() and
+ * wimax_rfkill_report_sw() to indicate their state. If any is
+ * missing, just call it to indicate it is ON (radio always on).
+ *
+ * Whenever the driver detects a change in the state of the RF kill
+ * switches, it should call wimax_report_rfkill_hw() or
+ * wimax_report_rfkill_sw() to report it to the stack.
+ */
+struct wimax_dev {
+	struct net_device *net_dev;
+	struct list_head id_table_node;
+	struct mutex mutex;		/* Protects all members and API calls */
+	struct mutex mutex_reset;
+	enum wimax_st state;
+
+	int (*op_msg_from_user)(struct wimax_dev *wimax_dev,
+				const char *,
+				const void *, size_t,
+				const struct genl_info *info);
+	int (*op_rfkill_sw_toggle)(struct wimax_dev *wimax_dev,
+				   enum wimax_rf_state);
+	int (*op_reset)(struct wimax_dev *wimax_dev);
+
+	struct rfkill *rfkill;
+	unsigned int rf_hw;
+	unsigned int rf_sw;
+	char name[32];
+
+	struct dentry *debugfs_dentry;
+};
+
+
+
+/*
+ * WiMAX stack public API for device drivers
+ * -----------------------------------------
+ *
+ * These functions are not exported to user space.
+ */
+void wimax_dev_init(struct wimax_dev *);
+int wimax_dev_add(struct wimax_dev *, struct net_device *);
+void wimax_dev_rm(struct wimax_dev *);
+
+static inline
+struct wimax_dev *net_dev_to_wimax(struct net_device *net_dev)
+{
+	return netdev_priv(net_dev);
+}
+
+static inline
+struct device *wimax_dev_to_dev(struct wimax_dev *wimax_dev)
+{
+	return wimax_dev->net_dev->dev.parent;
+}
+
+void wimax_state_change(struct wimax_dev *, enum wimax_st);
+enum wimax_st wimax_state_get(struct wimax_dev *);
+
+/*
+ * Radio Switch state reporting.
+ *
+ * enum wimax_rf_state is declared in linux/wimax.h so the exports
+ * to user space can use it.
+ */
+void wimax_report_rfkill_hw(struct wimax_dev *, enum wimax_rf_state);
+void wimax_report_rfkill_sw(struct wimax_dev *, enum wimax_rf_state);
+
+
+/*
+ * Free-form messaging to/from user space
+ *
+ * Sending a message:
+ *
+ *   wimax_msg(wimax_dev, pipe_name, buf, buf_size, GFP_KERNEL);
+ *
+ * Broken up:
+ *
+ *   skb = wimax_msg_alloc(wimax_dev, pipe_name, buf_size, GFP_KERNEL);
+ *   ...fill up skb...
+ *   wimax_msg_send(wimax_dev, pipe_name, skb);
+ *
+ * Be sure not to modify skb->data in the middle (ie: don't use
+ * skb_push()/skb_pull()/skb_reserve() on the skb).
+ *
+ * "pipe_name" is any string, that can be interpreted as the name of
+ * the pipe or recipient; the interpretation of it is driver
+ * specific, so the recipient can multiplex it as wished. It can be
+ * NULL, it won't be used - an example is using a "diagnostics" tag to
+ * send diagnostics information that a device-specific diagnostics
+ * tool would be interested in.
+ */
+struct sk_buff *wimax_msg_alloc(struct wimax_dev *, const char *, const void *,
+				size_t, gfp_t);
+int wimax_msg_send(struct wimax_dev *, struct sk_buff *);
+int wimax_msg(struct wimax_dev *, const char *, const void *, size_t, gfp_t);
+
+const void *wimax_msg_data_len(struct sk_buff *, size_t *);
+const void *wimax_msg_data(struct sk_buff *);
+ssize_t wimax_msg_len(struct sk_buff *);
+
+
+/*
+ * WiMAX stack user space API
+ * --------------------------
+ *
+ * This API is what gets exported to user space for general
+ * operations. As well, they can be called from within the kernel,
+ * (with a properly referenced `struct wimax_dev`).
+ *
+ * Properly referenced means: the 'struct net_device' that embeds the
+ * device's control structure and (as such) the 'struct wimax_dev' is
+ * referenced by the caller.
+ */
+int wimax_rfkill(struct wimax_dev *, enum wimax_rf_state);
+int wimax_reset(struct wimax_dev *);
+
+#endif /* #ifndef __NET__WIMAX_H__ */
diff --git a/drivers/staging/wimax/op-msg.c b/drivers/staging/wimax/op-msg.c
new file mode 100644
index 000000000000..e20ac7d84e82
--- /dev/null
+++ b/drivers/staging/wimax/op-msg.c
@@ -0,0 +1,391 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Linux WiMAX
+ * Generic messaging interface between userspace and driver/device
+ *
+ * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *
+ * This implements a direct communication channel between user space and
+ * the driver/device, by which free form messages can be sent back and
+ * forth.
+ *
+ * This is intended for device-specific features, vendor quirks, etc.
+ *
+ * See include/net/wimax.h
+ *
+ * GENERIC NETLINK ENCODING AND CAPACITY
+ *
+ * A destination "pipe name" is added to each message; it is up to the
+ * drivers to assign or use those names (if using them at all).
+ *
+ * Messages are encoded as a binary netlink attribute using nla_put()
+ * using type NLA_UNSPEC (as some versions of libnl still in
+ * deployment don't yet understand NLA_BINARY).
+ *
+ * The maximum capacity of this transport is PAGESIZE per message (so
+ * the actual payload will be bit smaller depending on the
+ * netlink/generic netlink attributes and headers).
+ *
+ * RECEPTION OF MESSAGES
+ *
+ * When a message is received from user space, it is passed verbatim
+ * to the driver calling wimax_dev->op_msg_from_user(). The return
+ * value from this function is passed back to user space as an ack
+ * over the generic netlink protocol.
+ *
+ * The stack doesn't do any processing or interpretation of these
+ * messages.
+ *
+ * SENDING MESSAGES
+ *
+ * Messages can be sent with wimax_msg().
+ *
+ * If the message delivery needs to happen on a different context to
+ * that of its creation, wimax_msg_alloc() can be used to get a
+ * pointer to the message that can be delivered later on with
+ * wimax_msg_send().
+ *
+ * ROADMAP
+ *
+ * wimax_gnl_doit_msg_from_user()    Process a message from user space
+ *   wimax_dev_get_by_genl_info()
+ *   wimax_dev->op_msg_from_user()   Delivery of message to the driver
+ *
+ * wimax_msg()                       Send a message to user space
+ *   wimax_msg_alloc()
+ *   wimax_msg_send()
+ */
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <net/genetlink.h>
+#include <linux/netdevice.h>
+#include "linux-wimax.h"
+#include <linux/security.h>
+#include <linux/export.h>
+#include "wimax-internal.h"
+
+
+#define D_SUBMODULE op_msg
+#include "debug-levels.h"
+
+
+/**
+ * wimax_msg_alloc - Create a new skb for sending a message to userspace
+ *
+ * @wimax_dev: WiMAX device descriptor
+ * @pipe_name: "named pipe" the message will be sent to
+ * @msg: pointer to the message data to send
+ * @size: size of the message to send (in bytes), including the header.
+ * @gfp_flags: flags for memory allocation.
+ *
+ * Returns: %0 if ok, negative errno code on error
+ *
+ * Description:
+ *
+ * Allocates an skb that will contain the message to send to user
+ * space over the messaging pipe and initializes it, copying the
+ * payload.
+ *
+ * Once this call is done, you can deliver it with
+ * wimax_msg_send().
+ *
+ * IMPORTANT:
+ *
+ * Don't use skb_push()/skb_pull()/skb_reserve() on the skb, as
+ * wimax_msg_send() depends on skb->data being placed at the
+ * beginning of the user message.
+ *
+ * Unlike other WiMAX stack calls, this call can be used way early,
+ * even before wimax_dev_add() is called, as long as the
+ * wimax_dev->net_dev pointer is set to point to a proper
+ * net_dev. This is so that drivers can use it early in case they need
+ * to send stuff around or communicate with user space.
+ */
+struct sk_buff *wimax_msg_alloc(struct wimax_dev *wimax_dev,
+				const char *pipe_name,
+				const void *msg, size_t size,
+				gfp_t gfp_flags)
+{
+	int result;
+	struct device *dev = wimax_dev_to_dev(wimax_dev);
+	size_t msg_size;
+	void *genl_msg;
+	struct sk_buff *skb;
+
+	msg_size = nla_total_size(size)
+		+ nla_total_size(sizeof(u32))
+		+ (pipe_name ? nla_total_size(strlen(pipe_name)) : 0);
+	result = -ENOMEM;
+	skb = genlmsg_new(msg_size, gfp_flags);
+	if (skb == NULL)
+		goto error_new;
+	genl_msg = genlmsg_put(skb, 0, 0, &wimax_gnl_family,
+			       0, WIMAX_GNL_OP_MSG_TO_USER);
+	if (genl_msg == NULL) {
+		dev_err(dev, "no memory to create generic netlink message\n");
+		goto error_genlmsg_put;
+	}
+	result = nla_put_u32(skb, WIMAX_GNL_MSG_IFIDX,
+			     wimax_dev->net_dev->ifindex);
+	if (result < 0) {
+		dev_err(dev, "no memory to add ifindex attribute\n");
+		goto error_nla_put;
+	}
+	if (pipe_name) {
+		result = nla_put_string(skb, WIMAX_GNL_MSG_PIPE_NAME,
+					pipe_name);
+		if (result < 0) {
+			dev_err(dev, "no memory to add pipe_name attribute\n");
+			goto error_nla_put;
+		}
+	}
+	result = nla_put(skb, WIMAX_GNL_MSG_DATA, size, msg);
+	if (result < 0) {
+		dev_err(dev, "no memory to add payload (msg %p size %zu) in "
+			"attribute: %d\n", msg, size, result);
+		goto error_nla_put;
+	}
+	genlmsg_end(skb, genl_msg);
+	return skb;
+
+error_nla_put:
+error_genlmsg_put:
+error_new:
+	nlmsg_free(skb);
+	return ERR_PTR(result);
+}
+EXPORT_SYMBOL_GPL(wimax_msg_alloc);
+
+
+/**
+ * wimax_msg_data_len - Return a pointer and size of a message's payload
+ *
+ * @msg: Pointer to a message created with wimax_msg_alloc()
+ * @size: Pointer to where to store the message's size
+ *
+ * Returns the pointer to the message data.
+ */
+const void *wimax_msg_data_len(struct sk_buff *msg, size_t *size)
+{
+	struct nlmsghdr *nlh = (void *) msg->head;
+	struct nlattr *nla;
+
+	nla = nlmsg_find_attr(nlh, sizeof(struct genlmsghdr),
+			      WIMAX_GNL_MSG_DATA);
+	if (nla == NULL) {
+		pr_err("Cannot find attribute WIMAX_GNL_MSG_DATA\n");
+		return NULL;
+	}
+	*size = nla_len(nla);
+	return nla_data(nla);
+}
+EXPORT_SYMBOL_GPL(wimax_msg_data_len);
+
+
+/**
+ * wimax_msg_data - Return a pointer to a message's payload
+ *
+ * @msg: Pointer to a message created with wimax_msg_alloc()
+ */
+const void *wimax_msg_data(struct sk_buff *msg)
+{
+	struct nlmsghdr *nlh = (void *) msg->head;
+	struct nlattr *nla;
+
+	nla = nlmsg_find_attr(nlh, sizeof(struct genlmsghdr),
+			      WIMAX_GNL_MSG_DATA);
+	if (nla == NULL) {
+		pr_err("Cannot find attribute WIMAX_GNL_MSG_DATA\n");
+		return NULL;
+	}
+	return nla_data(nla);
+}
+EXPORT_SYMBOL_GPL(wimax_msg_data);
+
+
+/**
+ * wimax_msg_len - Return a message's payload length
+ *
+ * @msg: Pointer to a message created with wimax_msg_alloc()
+ */
+ssize_t wimax_msg_len(struct sk_buff *msg)
+{
+	struct nlmsghdr *nlh = (void *) msg->head;
+	struct nlattr *nla;
+
+	nla = nlmsg_find_attr(nlh, sizeof(struct genlmsghdr),
+			      WIMAX_GNL_MSG_DATA);
+	if (nla == NULL) {
+		pr_err("Cannot find attribute WIMAX_GNL_MSG_DATA\n");
+		return -EINVAL;
+	}
+	return nla_len(nla);
+}
+EXPORT_SYMBOL_GPL(wimax_msg_len);
+
+
+/**
+ * wimax_msg_send - Send a pre-allocated message to user space
+ *
+ * @wimax_dev: WiMAX device descriptor
+ *
+ * @skb: &struct sk_buff returned by wimax_msg_alloc(). Note the
+ *     ownership of @skb is transferred to this function.
+ *
+ * Returns: 0 if ok, < 0 errno code on error
+ *
+ * Description:
+ *
+ * Sends a free-form message that was preallocated with
+ * wimax_msg_alloc() and filled up.
+ *
+ * Assumes that once you pass an skb to this function for sending, it
+ * owns it and will release it when done (on success).
+ *
+ * IMPORTANT:
+ *
+ * Don't use skb_push()/skb_pull()/skb_reserve() on the skb, as
+ * wimax_msg_send() depends on skb->data being placed at the
+ * beginning of the user message.
+ *
+ * Unlike other WiMAX stack calls, this call can be used way early,
+ * even before wimax_dev_add() is called, as long as the
+ * wimax_dev->net_dev pointer is set to point to a proper
+ * net_dev. This is so that drivers can use it early in case they need
+ * to send stuff around or communicate with user space.
+ */
+int wimax_msg_send(struct wimax_dev *wimax_dev, struct sk_buff *skb)
+{
+	struct device *dev = wimax_dev_to_dev(wimax_dev);
+	void *msg = skb->data;
+	size_t size = skb->len;
+	might_sleep();
+
+	d_printf(1, dev, "CTX: wimax msg, %zu bytes\n", size);
+	d_dump(2, dev, msg, size);
+	genlmsg_multicast(&wimax_gnl_family, skb, 0, 0, GFP_KERNEL);
+	d_printf(1, dev, "CTX: genl multicast done\n");
+	return 0;
+}
+EXPORT_SYMBOL_GPL(wimax_msg_send);
+
+
+/**
+ * wimax_msg - Send a message to user space
+ *
+ * @wimax_dev: WiMAX device descriptor (properly referenced)
+ * @pipe_name: "named pipe" the message will be sent to
+ * @buf: pointer to the message to send.
+ * @size: size of the buffer pointed to by @buf (in bytes).
+ * @gfp_flags: flags for memory allocation.
+ *
+ * Returns: %0 if ok, negative errno code on error.
+ *
+ * Description:
+ *
+ * Sends a free-form message to user space on the device @wimax_dev.
+ *
+ * NOTES:
+ *
+ * Once the @skb is given to this function, who will own it and will
+ * release it when done (unless it returns error).
+ */
+int wimax_msg(struct wimax_dev *wimax_dev, const char *pipe_name,
+	      const void *buf, size_t size, gfp_t gfp_flags)
+{
+	int result = -ENOMEM;
+	struct sk_buff *skb;
+
+	skb = wimax_msg_alloc(wimax_dev, pipe_name, buf, size, gfp_flags);
+	if (IS_ERR(skb))
+		result = PTR_ERR(skb);
+	else
+		result = wimax_msg_send(wimax_dev, skb);
+	return result;
+}
+EXPORT_SYMBOL_GPL(wimax_msg);
+
+/*
+ * Relays a message from user space to the driver
+ *
+ * The skb is passed to the driver-specific function with the netlink
+ * and generic netlink headers already stripped.
+ *
+ * This call will block while handling/relaying the message.
+ */
+int wimax_gnl_doit_msg_from_user(struct sk_buff *skb, struct genl_info *info)
+{
+	int result, ifindex;
+	struct wimax_dev *wimax_dev;
+	struct device *dev;
+	struct nlmsghdr *nlh = info->nlhdr;
+	char *pipe_name;
+	void *msg_buf;
+	size_t msg_len;
+
+	might_sleep();
+	d_fnstart(3, NULL, "(skb %p info %p)\n", skb, info);
+	result = -ENODEV;
+	if (info->attrs[WIMAX_GNL_MSG_IFIDX] == NULL) {
+		pr_err("WIMAX_GNL_MSG_FROM_USER: can't find IFIDX attribute\n");
+		goto error_no_wimax_dev;
+	}
+	ifindex = nla_get_u32(info->attrs[WIMAX_GNL_MSG_IFIDX]);
+	wimax_dev = wimax_dev_get_by_genl_info(info, ifindex);
+	if (wimax_dev == NULL)
+		goto error_no_wimax_dev;
+	dev = wimax_dev_to_dev(wimax_dev);
+
+	/* Unpack arguments */
+	result = -EINVAL;
+	if (info->attrs[WIMAX_GNL_MSG_DATA] == NULL) {
+		dev_err(dev, "WIMAX_GNL_MSG_FROM_USER: can't find MSG_DATA "
+			"attribute\n");
+		goto error_no_data;
+	}
+	msg_buf = nla_data(info->attrs[WIMAX_GNL_MSG_DATA]);
+	msg_len = nla_len(info->attrs[WIMAX_GNL_MSG_DATA]);
+
+	if (info->attrs[WIMAX_GNL_MSG_PIPE_NAME] == NULL)
+		pipe_name = NULL;
+	else {
+		struct nlattr *attr = info->attrs[WIMAX_GNL_MSG_PIPE_NAME];
+		size_t attr_len = nla_len(attr);
+		/* libnl-1.1 does not yet support NLA_NUL_STRING */
+		result = -ENOMEM;
+		pipe_name = kstrndup(nla_data(attr), attr_len + 1, GFP_KERNEL);
+		if (pipe_name == NULL)
+			goto error_alloc;
+		pipe_name[attr_len] = 0;
+	}
+	mutex_lock(&wimax_dev->mutex);
+	result = wimax_dev_is_ready(wimax_dev);
+	if (result == -ENOMEDIUM)
+		result = 0;
+	if (result < 0)
+		goto error_not_ready;
+	result = -ENOSYS;
+	if (wimax_dev->op_msg_from_user == NULL)
+		goto error_noop;
+
+	d_printf(1, dev,
+		 "CRX: nlmsghdr len %u type %u flags 0x%04x seq 0x%x pid %u\n",
+		 nlh->nlmsg_len, nlh->nlmsg_type, nlh->nlmsg_flags,
+		 nlh->nlmsg_seq, nlh->nlmsg_pid);
+	d_printf(1, dev, "CRX: wimax message %zu bytes\n", msg_len);
+	d_dump(2, dev, msg_buf, msg_len);
+
+	result = wimax_dev->op_msg_from_user(wimax_dev, pipe_name,
+					     msg_buf, msg_len, info);
+error_noop:
+error_not_ready:
+	mutex_unlock(&wimax_dev->mutex);
+error_alloc:
+	kfree(pipe_name);
+error_no_data:
+	dev_put(wimax_dev->net_dev);
+error_no_wimax_dev:
+	d_fnend(3, NULL, "(skb %p info %p) = %d\n", skb, info, result);
+	return result;
+}
diff --git a/drivers/staging/wimax/op-reset.c b/drivers/staging/wimax/op-reset.c
new file mode 100644
index 000000000000..b3f000cbe112
--- /dev/null
+++ b/drivers/staging/wimax/op-reset.c
@@ -0,0 +1,108 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Linux WiMAX
+ * Implement and export a method for resetting a WiMAX device
+ *
+ * Copyright (C) 2008 Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *
+ * This implements a simple synchronous call to reset a WiMAX device.
+ *
+ * Resets aim at being warm, keeping the device handles active;
+ * however, when that fails, it falls back to a cold reset (that will
+ * disconnect and reconnect the device).
+ */
+
+#include "net-wimax.h"
+#include <net/genetlink.h>
+#include "linux-wimax.h"
+#include <linux/security.h>
+#include <linux/export.h>
+#include "wimax-internal.h"
+
+#define D_SUBMODULE op_reset
+#include "debug-levels.h"
+
+
+/**
+ * wimax_reset - Reset a WiMAX device
+ *
+ * @wimax_dev: WiMAX device descriptor
+ *
+ * Returns:
+ *
+ * %0 if ok and a warm reset was done (the device still exists in
+ * the system).
+ *
+ * -%ENODEV if a cold/bus reset had to be done (device has
+ * disconnected and reconnected, so current handle is not valid
+ * any more).
+ *
+ * -%EINVAL if the device is not even registered.
+ *
+ * Any other negative error code shall be considered as
+ * non-recoverable.
+ *
+ * Description:
+ *
+ * Called when wanting to reset the device for any reason. Device is
+ * taken back to power on status.
+ *
+ * This call blocks; on successful return, the device has completed the
+ * reset process and is ready to operate.
+ */
+int wimax_reset(struct wimax_dev *wimax_dev)
+{
+	int result = -EINVAL;
+	struct device *dev = wimax_dev_to_dev(wimax_dev);
+	enum wimax_st state;
+
+	might_sleep();
+	d_fnstart(3, dev, "(wimax_dev %p)\n", wimax_dev);
+	mutex_lock(&wimax_dev->mutex);
+	dev_hold(wimax_dev->net_dev);
+	state = wimax_dev->state;
+	mutex_unlock(&wimax_dev->mutex);
+
+	if (state >= WIMAX_ST_DOWN) {
+		mutex_lock(&wimax_dev->mutex_reset);
+		result = wimax_dev->op_reset(wimax_dev);
+		mutex_unlock(&wimax_dev->mutex_reset);
+	}
+	dev_put(wimax_dev->net_dev);
+
+	d_fnend(3, dev, "(wimax_dev %p) = %d\n", wimax_dev, result);
+	return result;
+}
+EXPORT_SYMBOL(wimax_reset);
+
+
+/*
+ * Exporting to user space over generic netlink
+ *
+ * Parse the reset command from user space, return error code.
+ *
+ * No attributes.
+ */
+int wimax_gnl_doit_reset(struct sk_buff *skb, struct genl_info *info)
+{
+	int result, ifindex;
+	struct wimax_dev *wimax_dev;
+
+	d_fnstart(3, NULL, "(skb %p info %p)\n", skb, info);
+	result = -ENODEV;
+	if (info->attrs[WIMAX_GNL_RESET_IFIDX] == NULL) {
+		pr_err("WIMAX_GNL_OP_RFKILL: can't find IFIDX attribute\n");
+		goto error_no_wimax_dev;
+	}
+	ifindex = nla_get_u32(info->attrs[WIMAX_GNL_RESET_IFIDX]);
+	wimax_dev = wimax_dev_get_by_genl_info(info, ifindex);
+	if (wimax_dev == NULL)
+		goto error_no_wimax_dev;
+	/* Execute the operation and send the result back to user space */
+	result = wimax_reset(wimax_dev);
+	dev_put(wimax_dev->net_dev);
+error_no_wimax_dev:
+	d_fnend(3, NULL, "(skb %p info %p) = %d\n", skb, info, result);
+	return result;
+}
diff --git a/drivers/staging/wimax/op-rfkill.c b/drivers/staging/wimax/op-rfkill.c
new file mode 100644
index 000000000000..78b294481a59
--- /dev/null
+++ b/drivers/staging/wimax/op-rfkill.c
@@ -0,0 +1,431 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Linux WiMAX
+ * RF-kill framework integration
+ *
+ * Copyright (C) 2008 Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *
+ * This integrates into the Linux Kernel rfkill susbystem so that the
+ * drivers just have to do the bare minimal work, which is providing a
+ * method to set the software RF-Kill switch and to report changes in
+ * the software and hardware switch status.
+ *
+ * A non-polled generic rfkill device is embedded into the WiMAX
+ * subsystem's representation of a device.
+ *
+ * FIXME: Need polled support? Let drivers provide a poll routine
+ *	  and hand it to rfkill ops then?
+ *
+ * All device drivers have to do is after wimax_dev_init(), call
+ * wimax_report_rfkill_hw() and wimax_report_rfkill_sw() to update
+ * initial state and then every time it changes. See wimax.h:struct
+ * wimax_dev for more information.
+ *
+ * ROADMAP
+ *
+ * wimax_gnl_doit_rfkill()      User space calling wimax_rfkill()
+ *   wimax_rfkill()             Kernel calling wimax_rfkill()
+ *     __wimax_rf_toggle_radio()
+ *
+ * wimax_rfkill_set_radio_block()  RF-Kill subsystem calling
+ *   __wimax_rf_toggle_radio()
+ *
+ * __wimax_rf_toggle_radio()
+ *   wimax_dev->op_rfkill_sw_toggle() Driver backend
+ *   __wimax_state_change()
+ *
+ * wimax_report_rfkill_sw()     Driver reports state change
+ *   __wimax_state_change()
+ *
+ * wimax_report_rfkill_hw()     Driver reports state change
+ *   __wimax_state_change()
+ *
+ * wimax_rfkill_add()           Initialize/shutdown rfkill support
+ * wimax_rfkill_rm()            [called by wimax_dev_add/rm()]
+ */
+
+#include "net-wimax.h"
+#include <net/genetlink.h>
+#include "linux-wimax.h"
+#include <linux/security.h>
+#include <linux/rfkill.h>
+#include <linux/export.h>
+#include "wimax-internal.h"
+
+#define D_SUBMODULE op_rfkill
+#include "debug-levels.h"
+
+/**
+ * wimax_report_rfkill_hw - Reports changes in the hardware RF switch
+ *
+ * @wimax_dev: WiMAX device descriptor
+ *
+ * @state: New state of the RF Kill switch. %WIMAX_RF_ON radio on,
+ *     %WIMAX_RF_OFF radio off.
+ *
+ * When the device detects a change in the state of thehardware RF
+ * switch, it must call this function to let the WiMAX kernel stack
+ * know that the state has changed so it can be properly propagated.
+ *
+ * The WiMAX stack caches the state (the driver doesn't need to). As
+ * well, as the change is propagated it will come back as a request to
+ * change the software state to mirror the hardware state.
+ *
+ * If the device doesn't have a hardware kill switch, just report
+ * it on initialization as always on (%WIMAX_RF_ON, radio on).
+ */
+void wimax_report_rfkill_hw(struct wimax_dev *wimax_dev,
+			    enum wimax_rf_state state)
+{
+	int result;
+	struct device *dev = wimax_dev_to_dev(wimax_dev);
+	enum wimax_st wimax_state;
+
+	d_fnstart(3, dev, "(wimax_dev %p state %u)\n", wimax_dev, state);
+	BUG_ON(state == WIMAX_RF_QUERY);
+	BUG_ON(state != WIMAX_RF_ON && state != WIMAX_RF_OFF);
+
+	mutex_lock(&wimax_dev->mutex);
+	result = wimax_dev_is_ready(wimax_dev);
+	if (result < 0)
+		goto error_not_ready;
+
+	if (state != wimax_dev->rf_hw) {
+		wimax_dev->rf_hw = state;
+		if (wimax_dev->rf_hw == WIMAX_RF_ON &&
+		    wimax_dev->rf_sw == WIMAX_RF_ON)
+			wimax_state = WIMAX_ST_READY;
+		else
+			wimax_state = WIMAX_ST_RADIO_OFF;
+
+		result = rfkill_set_hw_state(wimax_dev->rfkill,
+					     state == WIMAX_RF_OFF);
+
+		__wimax_state_change(wimax_dev, wimax_state);
+	}
+error_not_ready:
+	mutex_unlock(&wimax_dev->mutex);
+	d_fnend(3, dev, "(wimax_dev %p state %u) = void [%d]\n",
+		wimax_dev, state, result);
+}
+EXPORT_SYMBOL_GPL(wimax_report_rfkill_hw);
+
+
+/**
+ * wimax_report_rfkill_sw - Reports changes in the software RF switch
+ *
+ * @wimax_dev: WiMAX device descriptor
+ *
+ * @state: New state of the RF kill switch. %WIMAX_RF_ON radio on,
+ *     %WIMAX_RF_OFF radio off.
+ *
+ * Reports changes in the software RF switch state to the WiMAX stack.
+ *
+ * The main use is during initialization, so the driver can query the
+ * device for its current software radio kill switch state and feed it
+ * to the system.
+ *
+ * On the side, the device does not change the software state by
+ * itself. In practice, this can happen, as the device might decide to
+ * switch (in software) the radio off for different reasons.
+ */
+void wimax_report_rfkill_sw(struct wimax_dev *wimax_dev,
+			    enum wimax_rf_state state)
+{
+	int result;
+	struct device *dev = wimax_dev_to_dev(wimax_dev);
+	enum wimax_st wimax_state;
+
+	d_fnstart(3, dev, "(wimax_dev %p state %u)\n", wimax_dev, state);
+	BUG_ON(state == WIMAX_RF_QUERY);
+	BUG_ON(state != WIMAX_RF_ON && state != WIMAX_RF_OFF);
+
+	mutex_lock(&wimax_dev->mutex);
+	result = wimax_dev_is_ready(wimax_dev);
+	if (result < 0)
+		goto error_not_ready;
+
+	if (state != wimax_dev->rf_sw) {
+		wimax_dev->rf_sw = state;
+		if (wimax_dev->rf_hw == WIMAX_RF_ON &&
+		    wimax_dev->rf_sw == WIMAX_RF_ON)
+			wimax_state = WIMAX_ST_READY;
+		else
+			wimax_state = WIMAX_ST_RADIO_OFF;
+		__wimax_state_change(wimax_dev, wimax_state);
+		rfkill_set_sw_state(wimax_dev->rfkill, state == WIMAX_RF_OFF);
+	}
+error_not_ready:
+	mutex_unlock(&wimax_dev->mutex);
+	d_fnend(3, dev, "(wimax_dev %p state %u) = void [%d]\n",
+		wimax_dev, state, result);
+}
+EXPORT_SYMBOL_GPL(wimax_report_rfkill_sw);
+
+
+/*
+ * Callback for the RF Kill toggle operation
+ *
+ * This function is called by:
+ *
+ * - The rfkill subsystem when the RF-Kill key is pressed in the
+ *   hardware and the driver notifies through
+ *   wimax_report_rfkill_hw(). The rfkill subsystem ends up calling back
+ *   here so the software RF Kill switch state is changed to reflect
+ *   the hardware switch state.
+ *
+ * - When the user sets the state through sysfs' rfkill/state file
+ *
+ * - When the user calls wimax_rfkill().
+ *
+ * This call blocks!
+ *
+ * WARNING! When we call rfkill_unregister(), this will be called with
+ * state 0!
+ *
+ * WARNING: wimax_dev must be locked
+ */
+static
+int __wimax_rf_toggle_radio(struct wimax_dev *wimax_dev,
+			    enum wimax_rf_state state)
+{
+	int result = 0;
+	struct device *dev = wimax_dev_to_dev(wimax_dev);
+	enum wimax_st wimax_state;
+
+	might_sleep();
+	d_fnstart(3, dev, "(wimax_dev %p state %u)\n", wimax_dev, state);
+	if (wimax_dev->rf_sw == state)
+		goto out_no_change;
+	if (wimax_dev->op_rfkill_sw_toggle != NULL)
+		result = wimax_dev->op_rfkill_sw_toggle(wimax_dev, state);
+	else if (state == WIMAX_RF_OFF)	/* No op? can't turn off */
+		result = -ENXIO;
+	else				/* No op? can turn on */
+		result = 0;		/* should never happen tho */
+	if (result >= 0) {
+		result = 0;
+		wimax_dev->rf_sw = state;
+		wimax_state = state == WIMAX_RF_ON ?
+			WIMAX_ST_READY : WIMAX_ST_RADIO_OFF;
+		__wimax_state_change(wimax_dev, wimax_state);
+	}
+out_no_change:
+	d_fnend(3, dev, "(wimax_dev %p state %u) = %d\n",
+		wimax_dev, state, result);
+	return result;
+}
+
+
+/*
+ * Translate from rfkill state to wimax state
+ *
+ * NOTE: Special state handling rules here
+ *
+ *     Just pretend the call didn't happen if we are in a state where
+ *     we know for sure it cannot be handled (WIMAX_ST_DOWN or
+ *     __WIMAX_ST_QUIESCING). rfkill() needs it to register and
+ *     unregister, as it will run this path.
+ *
+ * NOTE: This call will block until the operation is completed.
+ */
+static int wimax_rfkill_set_radio_block(void *data, bool blocked)
+{
+	int result;
+	struct wimax_dev *wimax_dev = data;
+	struct device *dev = wimax_dev_to_dev(wimax_dev);
+	enum wimax_rf_state rf_state;
+
+	d_fnstart(3, dev, "(wimax_dev %p blocked %u)\n", wimax_dev, blocked);
+	rf_state = WIMAX_RF_ON;
+	if (blocked)
+		rf_state = WIMAX_RF_OFF;
+	mutex_lock(&wimax_dev->mutex);
+	if (wimax_dev->state <= __WIMAX_ST_QUIESCING)
+		result = 0;
+	else
+		result = __wimax_rf_toggle_radio(wimax_dev, rf_state);
+	mutex_unlock(&wimax_dev->mutex);
+	d_fnend(3, dev, "(wimax_dev %p blocked %u) = %d\n",
+		wimax_dev, blocked, result);
+	return result;
+}
+
+static const struct rfkill_ops wimax_rfkill_ops = {
+	.set_block = wimax_rfkill_set_radio_block,
+};
+
+/**
+ * wimax_rfkill - Set the software RF switch state for a WiMAX device
+ *
+ * @wimax_dev: WiMAX device descriptor
+ *
+ * @state: New RF state.
+ *
+ * Returns:
+ *
+ * >= 0 toggle state if ok, < 0 errno code on error. The toggle state
+ * is returned as a bitmap, bit 0 being the hardware RF state, bit 1
+ * the software RF state.
+ *
+ * 0 means disabled (%WIMAX_RF_ON, radio on), 1 means enabled radio
+ * off (%WIMAX_RF_OFF).
+ *
+ * Description:
+ *
+ * Called by the user when he wants to request the WiMAX radio to be
+ * switched on (%WIMAX_RF_ON) or off (%WIMAX_RF_OFF). With
+ * %WIMAX_RF_QUERY, just the current state is returned.
+ *
+ * NOTE:
+ *
+ * This call will block until the operation is complete.
+ */
+int wimax_rfkill(struct wimax_dev *wimax_dev, enum wimax_rf_state state)
+{
+	int result;
+	struct device *dev = wimax_dev_to_dev(wimax_dev);
+
+	d_fnstart(3, dev, "(wimax_dev %p state %u)\n", wimax_dev, state);
+	mutex_lock(&wimax_dev->mutex);
+	result = wimax_dev_is_ready(wimax_dev);
+	if (result < 0) {
+		/* While initializing, < 1.4.3 wimax-tools versions use
+		 * this call to check if the device is a valid WiMAX
+		 * device; so we allow it to proceed always,
+		 * considering the radios are all off. */
+		if (result == -ENOMEDIUM && state == WIMAX_RF_QUERY)
+			result = WIMAX_RF_OFF << 1 | WIMAX_RF_OFF;
+		goto error_not_ready;
+	}
+	switch (state) {
+	case WIMAX_RF_ON:
+	case WIMAX_RF_OFF:
+		result = __wimax_rf_toggle_radio(wimax_dev, state);
+		if (result < 0)
+			goto error;
+		rfkill_set_sw_state(wimax_dev->rfkill, state == WIMAX_RF_OFF);
+		break;
+	case WIMAX_RF_QUERY:
+		break;
+	default:
+		result = -EINVAL;
+		goto error;
+	}
+	result = wimax_dev->rf_sw << 1 | wimax_dev->rf_hw;
+error:
+error_not_ready:
+	mutex_unlock(&wimax_dev->mutex);
+	d_fnend(3, dev, "(wimax_dev %p state %u) = %d\n",
+		wimax_dev, state, result);
+	return result;
+}
+EXPORT_SYMBOL(wimax_rfkill);
+
+
+/*
+ * Register a new WiMAX device's RF Kill support
+ *
+ * WARNING: wimax_dev->mutex must be unlocked
+ */
+int wimax_rfkill_add(struct wimax_dev *wimax_dev)
+{
+	int result;
+	struct rfkill *rfkill;
+	struct device *dev = wimax_dev_to_dev(wimax_dev);
+
+	d_fnstart(3, dev, "(wimax_dev %p)\n", wimax_dev);
+	/* Initialize RF Kill */
+	result = -ENOMEM;
+	rfkill = rfkill_alloc(wimax_dev->name, dev, RFKILL_TYPE_WIMAX,
+			      &wimax_rfkill_ops, wimax_dev);
+	if (rfkill == NULL)
+		goto error_rfkill_allocate;
+
+	d_printf(1, dev, "rfkill %p\n", rfkill);
+
+	wimax_dev->rfkill = rfkill;
+
+	rfkill_init_sw_state(rfkill, 1);
+	result = rfkill_register(wimax_dev->rfkill);
+	if (result < 0)
+		goto error_rfkill_register;
+
+	/* If there is no SW toggle op, SW RFKill is always on */
+	if (wimax_dev->op_rfkill_sw_toggle == NULL)
+		wimax_dev->rf_sw = WIMAX_RF_ON;
+
+	d_fnend(3, dev, "(wimax_dev %p) = 0\n", wimax_dev);
+	return 0;
+
+error_rfkill_register:
+	rfkill_destroy(wimax_dev->rfkill);
+error_rfkill_allocate:
+	d_fnend(3, dev, "(wimax_dev %p) = %d\n", wimax_dev, result);
+	return result;
+}
+
+
+/*
+ * Deregister a WiMAX device's RF Kill support
+ *
+ * Ick, we can't call rfkill_free() after rfkill_unregister()...oh
+ * well.
+ *
+ * WARNING: wimax_dev->mutex must be unlocked
+ */
+void wimax_rfkill_rm(struct wimax_dev *wimax_dev)
+{
+	struct device *dev = wimax_dev_to_dev(wimax_dev);
+	d_fnstart(3, dev, "(wimax_dev %p)\n", wimax_dev);
+	rfkill_unregister(wimax_dev->rfkill);
+	rfkill_destroy(wimax_dev->rfkill);
+	d_fnend(3, dev, "(wimax_dev %p)\n", wimax_dev);
+}
+
+
+/*
+ * Exporting to user space over generic netlink
+ *
+ * Parse the rfkill command from user space, return a combination
+ * value that describe the states of the different toggles.
+ *
+ * Only one attribute: the new state requested (on, off or no change,
+ * just query).
+ */
+
+int wimax_gnl_doit_rfkill(struct sk_buff *skb, struct genl_info *info)
+{
+	int result, ifindex;
+	struct wimax_dev *wimax_dev;
+	struct device *dev;
+	enum wimax_rf_state new_state;
+
+	d_fnstart(3, NULL, "(skb %p info %p)\n", skb, info);
+	result = -ENODEV;
+	if (info->attrs[WIMAX_GNL_RFKILL_IFIDX] == NULL) {
+		pr_err("WIMAX_GNL_OP_RFKILL: can't find IFIDX attribute\n");
+		goto error_no_wimax_dev;
+	}
+	ifindex = nla_get_u32(info->attrs[WIMAX_GNL_RFKILL_IFIDX]);
+	wimax_dev = wimax_dev_get_by_genl_info(info, ifindex);
+	if (wimax_dev == NULL)
+		goto error_no_wimax_dev;
+	dev = wimax_dev_to_dev(wimax_dev);
+	result = -EINVAL;
+	if (info->attrs[WIMAX_GNL_RFKILL_STATE] == NULL) {
+		dev_err(dev, "WIMAX_GNL_RFKILL: can't find RFKILL_STATE "
+			"attribute\n");
+		goto error_no_pid;
+	}
+	new_state = nla_get_u32(info->attrs[WIMAX_GNL_RFKILL_STATE]);
+
+	/* Execute the operation and send the result back to user space */
+	result = wimax_rfkill(wimax_dev, new_state);
+error_no_pid:
+	dev_put(wimax_dev->net_dev);
+error_no_wimax_dev:
+	d_fnend(3, NULL, "(skb %p info %p) = %d\n", skb, info, result);
+	return result;
+}
diff --git a/drivers/staging/wimax/op-state-get.c b/drivers/staging/wimax/op-state-get.c
new file mode 100644
index 000000000000..c5bfbed505f5
--- /dev/null
+++ b/drivers/staging/wimax/op-state-get.c
@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Linux WiMAX
+ * Implement and export a method for getting a WiMAX device current state
+ *
+ * Copyright (C) 2009 Paulius Zaleckas <paulius.zaleckas@teltonika.lt>
+ *
+ * Based on previous WiMAX core work by:
+ *  Copyright (C) 2008 Intel Corporation <linux-wimax@intel.com>
+ *  Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ */
+
+#include "net-wimax.h"
+#include <net/genetlink.h>
+#include "linux-wimax.h"
+#include <linux/security.h>
+#include "wimax-internal.h"
+
+#define D_SUBMODULE op_state_get
+#include "debug-levels.h"
+
+
+/*
+ * Exporting to user space over generic netlink
+ *
+ * Parse the state get command from user space, return a combination
+ * value that describe the current state.
+ *
+ * No attributes.
+ */
+int wimax_gnl_doit_state_get(struct sk_buff *skb, struct genl_info *info)
+{
+	int result, ifindex;
+	struct wimax_dev *wimax_dev;
+
+	d_fnstart(3, NULL, "(skb %p info %p)\n", skb, info);
+	result = -ENODEV;
+	if (info->attrs[WIMAX_GNL_STGET_IFIDX] == NULL) {
+		pr_err("WIMAX_GNL_OP_STATE_GET: can't find IFIDX attribute\n");
+		goto error_no_wimax_dev;
+	}
+	ifindex = nla_get_u32(info->attrs[WIMAX_GNL_STGET_IFIDX]);
+	wimax_dev = wimax_dev_get_by_genl_info(info, ifindex);
+	if (wimax_dev == NULL)
+		goto error_no_wimax_dev;
+	/* Execute the operation and send the result back to user space */
+	result = wimax_state_get(wimax_dev);
+	dev_put(wimax_dev->net_dev);
+error_no_wimax_dev:
+	d_fnend(3, NULL, "(skb %p info %p) = %d\n", skb, info, result);
+	return result;
+}
diff --git a/drivers/staging/wimax/stack.c b/drivers/staging/wimax/stack.c
new file mode 100644
index 000000000000..ace24a6dfd2d
--- /dev/null
+++ b/drivers/staging/wimax/stack.c
@@ -0,0 +1,616 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Linux WiMAX
+ * Initialization, addition and removal of wimax devices
+ *
+ * Copyright (C) 2005-2006 Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *
+ * This implements:
+ *
+ *   - basic life cycle of 'struct wimax_dev' [wimax_dev_*()]; on
+ *     addition/registration initialize all subfields and allocate
+ *     generic netlink resources for user space communication. On
+ *     removal/unregistration, undo all that.
+ *
+ *   - device state machine [wimax_state_change()] and support to send
+ *     reports to user space when the state changes
+ *     [wimax_gnl_re_state_change*()].
+ *
+ * See include/net/wimax.h for rationales and design.
+ *
+ * ROADMAP
+ *
+ * [__]wimax_state_change()     Called by drivers to update device's state
+ *   wimax_gnl_re_state_change_alloc()
+ *   wimax_gnl_re_state_change_send()
+ *
+ * wimax_dev_init()	        Init a device
+ * wimax_dev_add()              Register
+ *   wimax_rfkill_add()
+ *   wimax_gnl_add()            Register all the generic netlink resources.
+ *   wimax_id_table_add()
+ * wimax_dev_rm()               Unregister
+ *   wimax_id_table_rm()
+ *   wimax_gnl_rm()
+ *   wimax_rfkill_rm()
+ */
+#include <linux/device.h>
+#include <linux/gfp.h>
+#include <net/genetlink.h>
+#include <linux/netdevice.h>
+#include "linux-wimax.h"
+#include <linux/module.h>
+#include "wimax-internal.h"
+
+
+#define D_SUBMODULE stack
+#include "debug-levels.h"
+
+static char wimax_debug_params[128];
+module_param_string(debug, wimax_debug_params, sizeof(wimax_debug_params),
+		    0644);
+MODULE_PARM_DESC(debug,
+		 "String of space-separated NAME:VALUE pairs, where NAMEs "
+		 "are the different debug submodules and VALUE are the "
+		 "initial debug value to set.");
+
+/*
+ * Authoritative source for the RE_STATE_CHANGE attribute policy
+ *
+ * We don't really use it here, but /me likes to keep the definition
+ * close to where the data is generated.
+ */
+/*
+static const struct nla_policy wimax_gnl_re_status_change[WIMAX_GNL_ATTR_MAX + 1] = {
+	[WIMAX_GNL_STCH_STATE_OLD] = { .type = NLA_U8 },
+	[WIMAX_GNL_STCH_STATE_NEW] = { .type = NLA_U8 },
+};
+*/
+
+
+/*
+ * Allocate a Report State Change message
+ *
+ * @header: save it, you need it for _send()
+ *
+ * Creates and fills a basic state change message; different code
+ * paths can then add more attributes to the message as needed.
+ *
+ * Use wimax_gnl_re_state_change_send() to send the returned skb.
+ *
+ * Returns: skb with the genl message if ok, IS_ERR() ptr on error
+ *     with an errno code.
+ */
+static
+struct sk_buff *wimax_gnl_re_state_change_alloc(
+	struct wimax_dev *wimax_dev,
+	enum wimax_st new_state, enum wimax_st old_state,
+	void **header)
+{
+	int result;
+	struct device *dev = wimax_dev_to_dev(wimax_dev);
+	void *data;
+	struct sk_buff *report_skb;
+
+	d_fnstart(3, dev, "(wimax_dev %p new_state %u old_state %u)\n",
+		  wimax_dev, new_state, old_state);
+	result = -ENOMEM;
+	report_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (report_skb == NULL) {
+		dev_err(dev, "RE_STCH: can't create message\n");
+		goto error_new;
+	}
+	/* FIXME: sending a group ID as the seq is wrong */
+	data = genlmsg_put(report_skb, 0, wimax_gnl_family.mcgrp_offset,
+			   &wimax_gnl_family, 0, WIMAX_GNL_RE_STATE_CHANGE);
+	if (data == NULL) {
+		dev_err(dev, "RE_STCH: can't put data into message\n");
+		goto error_put;
+	}
+	*header = data;
+
+	result = nla_put_u8(report_skb, WIMAX_GNL_STCH_STATE_OLD, old_state);
+	if (result < 0) {
+		dev_err(dev, "RE_STCH: Error adding OLD attr: %d\n", result);
+		goto error_put;
+	}
+	result = nla_put_u8(report_skb, WIMAX_GNL_STCH_STATE_NEW, new_state);
+	if (result < 0) {
+		dev_err(dev, "RE_STCH: Error adding NEW attr: %d\n", result);
+		goto error_put;
+	}
+	result = nla_put_u32(report_skb, WIMAX_GNL_STCH_IFIDX,
+			     wimax_dev->net_dev->ifindex);
+	if (result < 0) {
+		dev_err(dev, "RE_STCH: Error adding IFINDEX attribute\n");
+		goto error_put;
+	}
+	d_fnend(3, dev, "(wimax_dev %p new_state %u old_state %u) = %p\n",
+		wimax_dev, new_state, old_state, report_skb);
+	return report_skb;
+
+error_put:
+	nlmsg_free(report_skb);
+error_new:
+	d_fnend(3, dev, "(wimax_dev %p new_state %u old_state %u) = %d\n",
+		wimax_dev, new_state, old_state, result);
+	return ERR_PTR(result);
+}
+
+
+/*
+ * Send a Report State Change message (as created with _alloc).
+ *
+ * @report_skb: as returned by wimax_gnl_re_state_change_alloc()
+ * @header: as returned by wimax_gnl_re_state_change_alloc()
+ *
+ * Returns: 0 if ok, < 0 errno code on error.
+ *
+ * If the message is  NULL, pretend it didn't happen.
+ */
+static
+int wimax_gnl_re_state_change_send(
+	struct wimax_dev *wimax_dev, struct sk_buff *report_skb,
+	void *header)
+{
+	int result = 0;
+	struct device *dev = wimax_dev_to_dev(wimax_dev);
+	d_fnstart(3, dev, "(wimax_dev %p report_skb %p)\n",
+		  wimax_dev, report_skb);
+	if (report_skb == NULL) {
+		result = -ENOMEM;
+		goto out;
+	}
+	genlmsg_end(report_skb, header);
+	genlmsg_multicast(&wimax_gnl_family, report_skb, 0, 0, GFP_KERNEL);
+out:
+	d_fnend(3, dev, "(wimax_dev %p report_skb %p) = %d\n",
+		wimax_dev, report_skb, result);
+	return result;
+}
+
+
+static
+void __check_new_state(enum wimax_st old_state, enum wimax_st new_state,
+		       unsigned int allowed_states_bm)
+{
+	if (WARN_ON(((1 << new_state) & allowed_states_bm) == 0)) {
+		pr_err("SW BUG! Forbidden state change %u -> %u\n",
+		       old_state, new_state);
+	}
+}
+
+
+/*
+ * Set the current state of a WiMAX device [unlocking version of
+ * wimax_state_change().
+ */
+void __wimax_state_change(struct wimax_dev *wimax_dev, enum wimax_st new_state)
+{
+	struct device *dev = wimax_dev_to_dev(wimax_dev);
+	enum wimax_st old_state = wimax_dev->state;
+	struct sk_buff *stch_skb;
+	void *header;
+
+	d_fnstart(3, dev, "(wimax_dev %p new_state %u [old %u])\n",
+		  wimax_dev, new_state, old_state);
+
+	if (WARN_ON(new_state >= __WIMAX_ST_INVALID)) {
+		dev_err(dev, "SW BUG: requesting invalid state %u\n",
+			new_state);
+		goto out;
+	}
+	if (old_state == new_state)
+		goto out;
+	header = NULL;	/* gcc complains? can't grok why */
+	stch_skb = wimax_gnl_re_state_change_alloc(
+		wimax_dev, new_state, old_state, &header);
+
+	/* Verify the state transition and do exit-from-state actions */
+	switch (old_state) {
+	case __WIMAX_ST_NULL:
+		__check_new_state(old_state, new_state,
+				  1 << WIMAX_ST_DOWN);
+		break;
+	case WIMAX_ST_DOWN:
+		__check_new_state(old_state, new_state,
+				  1 << __WIMAX_ST_QUIESCING
+				  | 1 << WIMAX_ST_UNINITIALIZED
+				  | 1 << WIMAX_ST_RADIO_OFF);
+		break;
+	case __WIMAX_ST_QUIESCING:
+		__check_new_state(old_state, new_state, 1 << WIMAX_ST_DOWN);
+		break;
+	case WIMAX_ST_UNINITIALIZED:
+		__check_new_state(old_state, new_state,
+				  1 << __WIMAX_ST_QUIESCING
+				  | 1 << WIMAX_ST_RADIO_OFF);
+		break;
+	case WIMAX_ST_RADIO_OFF:
+		__check_new_state(old_state, new_state,
+				  1 << __WIMAX_ST_QUIESCING
+				  | 1 << WIMAX_ST_READY);
+		break;
+	case WIMAX_ST_READY:
+		__check_new_state(old_state, new_state,
+				  1 << __WIMAX_ST_QUIESCING
+				  | 1 << WIMAX_ST_RADIO_OFF
+				  | 1 << WIMAX_ST_SCANNING
+				  | 1 << WIMAX_ST_CONNECTING
+				  | 1 << WIMAX_ST_CONNECTED);
+		break;
+	case WIMAX_ST_SCANNING:
+		__check_new_state(old_state, new_state,
+				  1 << __WIMAX_ST_QUIESCING
+				  | 1 << WIMAX_ST_RADIO_OFF
+				  | 1 << WIMAX_ST_READY
+				  | 1 << WIMAX_ST_CONNECTING
+				  | 1 << WIMAX_ST_CONNECTED);
+		break;
+	case WIMAX_ST_CONNECTING:
+		__check_new_state(old_state, new_state,
+				  1 << __WIMAX_ST_QUIESCING
+				  | 1 << WIMAX_ST_RADIO_OFF
+				  | 1 << WIMAX_ST_READY
+				  | 1 << WIMAX_ST_SCANNING
+				  | 1 << WIMAX_ST_CONNECTED);
+		break;
+	case WIMAX_ST_CONNECTED:
+		__check_new_state(old_state, new_state,
+				  1 << __WIMAX_ST_QUIESCING
+				  | 1 << WIMAX_ST_RADIO_OFF
+				  | 1 << WIMAX_ST_READY);
+		netif_tx_disable(wimax_dev->net_dev);
+		netif_carrier_off(wimax_dev->net_dev);
+		break;
+	case __WIMAX_ST_INVALID:
+	default:
+		dev_err(dev, "SW BUG: wimax_dev %p is in unknown state %u\n",
+			wimax_dev, wimax_dev->state);
+		WARN_ON(1);
+		goto out;
+	}
+
+	/* Execute the actions of entry to the new state */
+	switch (new_state) {
+	case __WIMAX_ST_NULL:
+		dev_err(dev, "SW BUG: wimax_dev %p entering NULL state "
+			"from %u\n", wimax_dev, wimax_dev->state);
+		WARN_ON(1);		/* Nobody can enter this state */
+		break;
+	case WIMAX_ST_DOWN:
+		break;
+	case __WIMAX_ST_QUIESCING:
+		break;
+	case WIMAX_ST_UNINITIALIZED:
+		break;
+	case WIMAX_ST_RADIO_OFF:
+		break;
+	case WIMAX_ST_READY:
+		break;
+	case WIMAX_ST_SCANNING:
+		break;
+	case WIMAX_ST_CONNECTING:
+		break;
+	case WIMAX_ST_CONNECTED:
+		netif_carrier_on(wimax_dev->net_dev);
+		netif_wake_queue(wimax_dev->net_dev);
+		break;
+	case __WIMAX_ST_INVALID:
+	default:
+		BUG();
+	}
+	__wimax_state_set(wimax_dev, new_state);
+	if (!IS_ERR(stch_skb))
+		wimax_gnl_re_state_change_send(wimax_dev, stch_skb, header);
+out:
+	d_fnend(3, dev, "(wimax_dev %p new_state %u [old %u]) = void\n",
+		wimax_dev, new_state, old_state);
+}
+
+
+/**
+ * wimax_state_change - Set the current state of a WiMAX device
+ *
+ * @wimax_dev: WiMAX device descriptor (properly referenced)
+ * @new_state: New state to switch to
+ *
+ * This implements the state changes for the wimax devices. It will
+ *
+ * - verify that the state transition is legal (for now it'll just
+ *   print a warning if not) according to the table in
+ *   linux/wimax.h's documentation for 'enum wimax_st'.
+ *
+ * - perform the actions needed for leaving the current state and
+ *   whichever are needed for entering the new state.
+ *
+ * - issue a report to user space indicating the new state (and an
+ *   optional payload with information about the new state).
+ *
+ * NOTE: @wimax_dev must be locked
+ */
+void wimax_state_change(struct wimax_dev *wimax_dev, enum wimax_st new_state)
+{
+	/*
+	 * A driver cannot take the wimax_dev out of the
+	 * __WIMAX_ST_NULL state unless by calling wimax_dev_add(). If
+	 * the wimax_dev's state is still NULL, we ignore any request
+	 * to change its state because it means it hasn't been yet
+	 * registered.
+	 *
+	 * There is no need to complain about it, as routines that
+	 * call this might be shared from different code paths that
+	 * are called before or after wimax_dev_add() has done its
+	 * job.
+	 */
+	mutex_lock(&wimax_dev->mutex);
+	if (wimax_dev->state > __WIMAX_ST_NULL)
+		__wimax_state_change(wimax_dev, new_state);
+	mutex_unlock(&wimax_dev->mutex);
+}
+EXPORT_SYMBOL_GPL(wimax_state_change);
+
+
+/**
+ * wimax_state_get() - Return the current state of a WiMAX device
+ *
+ * @wimax_dev: WiMAX device descriptor
+ *
+ * Returns: Current state of the device according to its driver.
+ */
+enum wimax_st wimax_state_get(struct wimax_dev *wimax_dev)
+{
+	enum wimax_st state;
+	mutex_lock(&wimax_dev->mutex);
+	state = wimax_dev->state;
+	mutex_unlock(&wimax_dev->mutex);
+	return state;
+}
+EXPORT_SYMBOL_GPL(wimax_state_get);
+
+
+/**
+ * wimax_dev_init - initialize a newly allocated instance
+ *
+ * @wimax_dev: WiMAX device descriptor to initialize.
+ *
+ * Initializes fields of a freshly allocated @wimax_dev instance. This
+ * function assumes that after allocation, the memory occupied by
+ * @wimax_dev was zeroed.
+ */
+void wimax_dev_init(struct wimax_dev *wimax_dev)
+{
+	INIT_LIST_HEAD(&wimax_dev->id_table_node);
+	__wimax_state_set(wimax_dev, __WIMAX_ST_NULL);
+	mutex_init(&wimax_dev->mutex);
+	mutex_init(&wimax_dev->mutex_reset);
+}
+EXPORT_SYMBOL_GPL(wimax_dev_init);
+
+/*
+ * There are multiple enums reusing the same values, adding
+ * others is only possible if they use a compatible policy.
+ */
+static const struct nla_policy wimax_gnl_policy[WIMAX_GNL_ATTR_MAX + 1] = {
+	/*
+	 * WIMAX_GNL_RESET_IFIDX, WIMAX_GNL_RFKILL_IFIDX,
+	 * WIMAX_GNL_STGET_IFIDX, WIMAX_GNL_MSG_IFIDX
+	 */
+	[1] = { .type = NLA_U32, },
+	/*
+	 * WIMAX_GNL_RFKILL_STATE, WIMAX_GNL_MSG_PIPE_NAME
+	 */
+	[2] = { .type = NLA_U32, }, /* enum wimax_rf_state */
+	/*
+	 * WIMAX_GNL_MSG_DATA
+	 */
+	[3] = { .type = NLA_UNSPEC, }, /* libnl doesn't grok BINARY yet */
+};
+
+static const struct genl_small_ops wimax_gnl_ops[] = {
+	{
+		.cmd = WIMAX_GNL_OP_MSG_FROM_USER,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags = GENL_ADMIN_PERM,
+		.doit = wimax_gnl_doit_msg_from_user,
+	},
+	{
+		.cmd = WIMAX_GNL_OP_RESET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags = GENL_ADMIN_PERM,
+		.doit = wimax_gnl_doit_reset,
+	},
+	{
+		.cmd = WIMAX_GNL_OP_RFKILL,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags = GENL_ADMIN_PERM,
+		.doit = wimax_gnl_doit_rfkill,
+	},
+	{
+		.cmd = WIMAX_GNL_OP_STATE_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags = GENL_ADMIN_PERM,
+		.doit = wimax_gnl_doit_state_get,
+	},
+};
+
+
+static
+size_t wimax_addr_scnprint(char *addr_str, size_t addr_str_size,
+			   unsigned char *addr, size_t addr_len)
+{
+	unsigned int cnt, total;
+
+	for (total = cnt = 0; cnt < addr_len; cnt++)
+		total += scnprintf(addr_str + total, addr_str_size - total,
+				   "%02x%c", addr[cnt],
+				   cnt == addr_len - 1 ? '\0' : ':');
+	return total;
+}
+
+
+/**
+ * wimax_dev_add - Register a new WiMAX device
+ *
+ * @wimax_dev: WiMAX device descriptor (as embedded in your @net_dev's
+ *     priv data). You must have called wimax_dev_init() on it before.
+ *
+ * @net_dev: net device the @wimax_dev is associated with. The
+ *     function expects SET_NETDEV_DEV() and register_netdev() were
+ *     already called on it.
+ *
+ * Registers the new WiMAX device, sets up the user-kernel control
+ * interface (generic netlink) and common WiMAX infrastructure.
+ *
+ * Note that the parts that will allow interaction with user space are
+ * setup at the very end, when the rest is in place, as once that
+ * happens, the driver might get user space control requests via
+ * netlink or from debugfs that might translate into calls into
+ * wimax_dev->op_*().
+ */
+int wimax_dev_add(struct wimax_dev *wimax_dev, struct net_device *net_dev)
+{
+	int result;
+	struct device *dev = net_dev->dev.parent;
+	char addr_str[32];
+
+	d_fnstart(3, dev, "(wimax_dev %p net_dev %p)\n", wimax_dev, net_dev);
+
+	/* Do the RFKILL setup before locking, as RFKILL will call
+	 * into our functions.
+	 */
+	wimax_dev->net_dev = net_dev;
+	result = wimax_rfkill_add(wimax_dev);
+	if (result < 0)
+		goto error_rfkill_add;
+
+	/* Set up user-space interaction */
+	mutex_lock(&wimax_dev->mutex);
+	wimax_id_table_add(wimax_dev);
+	wimax_debugfs_add(wimax_dev);
+
+	__wimax_state_set(wimax_dev, WIMAX_ST_DOWN);
+	mutex_unlock(&wimax_dev->mutex);
+
+	wimax_addr_scnprint(addr_str, sizeof(addr_str),
+			    net_dev->dev_addr, net_dev->addr_len);
+	dev_err(dev, "WiMAX interface %s (%s) ready\n",
+		net_dev->name, addr_str);
+	d_fnend(3, dev, "(wimax_dev %p net_dev %p) = 0\n", wimax_dev, net_dev);
+	return 0;
+
+error_rfkill_add:
+	d_fnend(3, dev, "(wimax_dev %p net_dev %p) = %d\n",
+		wimax_dev, net_dev, result);
+	return result;
+}
+EXPORT_SYMBOL_GPL(wimax_dev_add);
+
+
+/**
+ * wimax_dev_rm - Unregister an existing WiMAX device
+ *
+ * @wimax_dev: WiMAX device descriptor
+ *
+ * Unregisters a WiMAX device previously registered for use with
+ * wimax_add_rm().
+ *
+ * IMPORTANT! Must call before calling unregister_netdev().
+ *
+ * After this function returns, you will not get any more user space
+ * control requests (via netlink or debugfs) and thus to wimax_dev->ops.
+ *
+ * Reentrancy control is ensured by setting the state to
+ * %__WIMAX_ST_QUIESCING. rfkill operations coming through
+ * wimax_*rfkill*() will be stopped by the quiescing state; ops coming
+ * from the rfkill subsystem will be stopped by the support being
+ * removed by wimax_rfkill_rm().
+ */
+void wimax_dev_rm(struct wimax_dev *wimax_dev)
+{
+	d_fnstart(3, NULL, "(wimax_dev %p)\n", wimax_dev);
+
+	mutex_lock(&wimax_dev->mutex);
+	__wimax_state_change(wimax_dev, __WIMAX_ST_QUIESCING);
+	wimax_debugfs_rm(wimax_dev);
+	wimax_id_table_rm(wimax_dev);
+	__wimax_state_change(wimax_dev, WIMAX_ST_DOWN);
+	mutex_unlock(&wimax_dev->mutex);
+	wimax_rfkill_rm(wimax_dev);
+	d_fnend(3, NULL, "(wimax_dev %p) = void\n", wimax_dev);
+}
+EXPORT_SYMBOL_GPL(wimax_dev_rm);
+
+
+/* Debug framework control of debug levels */
+struct d_level D_LEVEL[] = {
+	D_SUBMODULE_DEFINE(debugfs),
+	D_SUBMODULE_DEFINE(id_table),
+	D_SUBMODULE_DEFINE(op_msg),
+	D_SUBMODULE_DEFINE(op_reset),
+	D_SUBMODULE_DEFINE(op_rfkill),
+	D_SUBMODULE_DEFINE(op_state_get),
+	D_SUBMODULE_DEFINE(stack),
+};
+size_t D_LEVEL_SIZE = ARRAY_SIZE(D_LEVEL);
+
+
+static const struct genl_multicast_group wimax_gnl_mcgrps[] = {
+	{ .name = "msg", },
+};
+
+struct genl_family wimax_gnl_family __ro_after_init = {
+	.name = "WiMAX",
+	.version = WIMAX_GNL_VERSION,
+	.hdrsize = 0,
+	.maxattr = WIMAX_GNL_ATTR_MAX,
+	.policy = wimax_gnl_policy,
+	.module = THIS_MODULE,
+	.small_ops = wimax_gnl_ops,
+	.n_small_ops = ARRAY_SIZE(wimax_gnl_ops),
+	.mcgrps = wimax_gnl_mcgrps,
+	.n_mcgrps = ARRAY_SIZE(wimax_gnl_mcgrps),
+};
+
+
+
+/* Shutdown the wimax stack */
+static
+int __init wimax_subsys_init(void)
+{
+	int result;
+
+	d_fnstart(4, NULL, "()\n");
+	d_parse_params(D_LEVEL, D_LEVEL_SIZE, wimax_debug_params,
+		       "wimax.debug");
+
+	result = genl_register_family(&wimax_gnl_family);
+	if (unlikely(result < 0)) {
+		pr_err("cannot register generic netlink family: %d\n", result);
+		goto error_register_family;
+	}
+
+	d_fnend(4, NULL, "() = 0\n");
+	return 0;
+
+error_register_family:
+	d_fnend(4, NULL, "() = %d\n", result);
+	return result;
+
+}
+module_init(wimax_subsys_init);
+
+
+/* Shutdown the wimax stack */
+static
+void __exit wimax_subsys_exit(void)
+{
+	wimax_id_table_release();
+	genl_unregister_family(&wimax_gnl_family);
+}
+module_exit(wimax_subsys_exit);
+
+MODULE_AUTHOR("Intel Corporation <linux-wimax@intel.com>");
+MODULE_DESCRIPTION("Linux WiMAX stack");
+MODULE_LICENSE("GPL");
diff --git a/drivers/staging/wimax/wimax-internal.h b/drivers/staging/wimax/wimax-internal.h
new file mode 100644
index 000000000000..a6b6990642a1
--- /dev/null
+++ b/drivers/staging/wimax/wimax-internal.h
@@ -0,0 +1,85 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Linux WiMAX
+ * Internal API for kernel space WiMAX stack
+ *
+ * Copyright (C) 2007 Intel Corporation <linux-wimax@intel.com>
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *
+ * This header file is for declarations and definitions internal to
+ * the WiMAX stack. For public APIs and documentation, see
+ * include/net/wimax.h and include/linux/wimax.h.
+ */
+
+#ifndef __WIMAX_INTERNAL_H__
+#define __WIMAX_INTERNAL_H__
+#ifdef __KERNEL__
+
+#ifdef pr_fmt
+#undef pr_fmt
+#endif
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/device.h>
+#include "net-wimax.h"
+
+
+/*
+ * Decide if a (locked) device is ready for use
+ *
+ * Before using the device structure, it must be locked
+ * (wimax_dev->mutex). As well, most operations need to call this
+ * function to check if the state is the right one.
+ *
+ * An error value will be returned if the state is not the right
+ * one. In that case, the caller should not attempt to use the device
+ * and just unlock it.
+ */
+static inline __must_check
+int wimax_dev_is_ready(struct wimax_dev *wimax_dev)
+{
+	if (wimax_dev->state == __WIMAX_ST_NULL)
+		return -EINVAL;	/* Device is not even registered! */
+	if (wimax_dev->state == WIMAX_ST_DOWN)
+		return -ENOMEDIUM;
+	if (wimax_dev->state == __WIMAX_ST_QUIESCING)
+		return -ESHUTDOWN;
+	return 0;
+}
+
+
+static inline
+void __wimax_state_set(struct wimax_dev *wimax_dev, enum wimax_st state)
+{
+	wimax_dev->state = state;
+}
+void __wimax_state_change(struct wimax_dev *, enum wimax_st);
+
+#ifdef CONFIG_DEBUG_FS
+void wimax_debugfs_add(struct wimax_dev *);
+void wimax_debugfs_rm(struct wimax_dev *);
+#else
+static inline void wimax_debugfs_add(struct wimax_dev *wimax_dev) {}
+static inline void wimax_debugfs_rm(struct wimax_dev *wimax_dev) {}
+#endif
+
+void wimax_id_table_add(struct wimax_dev *);
+struct wimax_dev *wimax_dev_get_by_genl_info(struct genl_info *, int);
+void wimax_id_table_rm(struct wimax_dev *);
+void wimax_id_table_release(void);
+
+int wimax_rfkill_add(struct wimax_dev *);
+void wimax_rfkill_rm(struct wimax_dev *);
+
+/* generic netlink */
+extern struct genl_family wimax_gnl_family;
+
+/* ops */
+int wimax_gnl_doit_msg_from_user(struct sk_buff *skb, struct genl_info *info);
+int wimax_gnl_doit_reset(struct sk_buff *skb, struct genl_info *info);
+int wimax_gnl_doit_rfkill(struct sk_buff *skb, struct genl_info *info);
+int wimax_gnl_doit_state_get(struct sk_buff *skb, struct genl_info *info);
+
+#endif /* #ifdef __KERNEL__ */
+#endif /* #ifndef __WIMAX_INTERNAL_H__ */
diff --git a/include/linux/wimax/debug.h b/include/linux/wimax/debug.h
deleted file mode 100644
index cdae052bcdcd..000000000000
--- a/include/linux/wimax/debug.h
+++ /dev/null
@@ -1,491 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Linux WiMAX
- * Collection of tools to manage debug operations.
- *
- * Copyright (C) 2005-2007 Intel Corporation
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * Don't #include this file directly, read on!
- *
- * EXECUTING DEBUGGING ACTIONS OR NOT
- *
- * The main thing this framework provides is decission power to take a
- * debug action (like printing a message) if the current debug level
- * allows it.
- *
- * The decission power is at two levels: at compile-time (what does
- * not make it is compiled out) and at run-time. The run-time
- * selection is done per-submodule (as they are declared by the user
- * of the framework).
- *
- * A call to d_test(L) (L being the target debug level) returns true
- * if the action should be taken because the current debug levels
- * allow it (both compile and run time).
- *
- * It follows that a call to d_test() that can be determined to be
- * always false at compile time will get the code depending on it
- * compiled out by optimization.
- *
- * DEBUG LEVELS
- *
- * It is up to the caller to define how much a debugging level is.
- *
- * Convention sets 0 as "no debug" (so an action marked as debug level 0
- * will always be taken). The increasing debug levels are used for
- * increased verbosity.
- *
- * USAGE
- *
- * Group the code in modules and submodules inside each module [which
- * in most cases maps to Linux modules and .c files that compose
- * those].
- *
- * For each module, there is:
- *
- *  - a MODULENAME (single word, legal C identifier)
- *
- *  - a debug-levels.h header file that declares the list of
- *    submodules and that is included by all .c files that use
- *    the debugging tools. The file name can be anything.
- *
- *  - some (optional) .c code to manipulate the runtime debug levels
- *    through debugfs.
- *
- * The debug-levels.h file would look like:
- *
- *     #ifndef __debug_levels__h__
- *     #define __debug_levels__h__
- *
- *     #define D_MODULENAME modulename
- *     #define D_MASTER 10
- *
- *     #include <linux/wimax/debug.h>
- *
- *     enum d_module {
- *             D_SUBMODULE_DECLARE(submodule_1),
- *             D_SUBMODULE_DECLARE(submodule_2),
- *             ...
- *             D_SUBMODULE_DECLARE(submodule_N)
- *     };
- *
- *     #endif
- *
- * D_MASTER is the maximum compile-time debug level; any debug actions
- * above this will be out. D_MODULENAME is the module name (legal C
- * identifier), which has to be unique for each module (to avoid
- * namespace collisions during linkage). Note those #defines need to
- * be done before #including debug.h
- *
- * We declare N different submodules whose debug level can be
- * independently controlled during runtime.
- *
- * In a .c file of the module (and only in one of them), define the
- * following code:
- *
- *     struct d_level D_LEVEL[] = {
- *             D_SUBMODULE_DEFINE(submodule_1),
- *             D_SUBMODULE_DEFINE(submodule_2),
- *             ...
- *             D_SUBMODULE_DEFINE(submodule_N),
- *     };
- *     size_t D_LEVEL_SIZE = ARRAY_SIZE(D_LEVEL);
- *
- * Externs for d_level_MODULENAME and d_level_size_MODULENAME are used
- * and declared in this file using the D_LEVEL and D_LEVEL_SIZE macros
- * #defined also in this file.
- *
- * To manipulate from user space the levels, create a debugfs dentry
- * and then register each submodule with:
- *
- *     d_level_register_debugfs("PREFIX_", submodule_X, parent);
- *
- * Where PREFIX_ is a name of your chosing. This will create debugfs
- * file with a single numeric value that can be use to tweak it. To
- * remove the entires, just use debugfs_remove_recursive() on 'parent'.
- *
- * NOTE: remember that even if this will show attached to some
- *     particular instance of a device, the settings are *global*.
- *
- * On each submodule (for example, .c files), the debug infrastructure
- * should be included like this:
- *
- *     #define D_SUBMODULE submodule_x     // matches one in debug-levels.h
- *     #include "debug-levels.h"
- *
- * after #including all your include files.
- *
- * Now you can use the d_*() macros below [d_test(), d_fnstart(),
- * d_fnend(), d_printf(), d_dump()].
- *
- * If their debug level is greater than D_MASTER, they will be
- * compiled out.
- *
- * If their debug level is lower or equal than D_MASTER but greater
- * than the current debug level of their submodule, they'll be
- * ignored.
- *
- * Otherwise, the action will be performed.
- */
-#ifndef __debug__h__
-#define __debug__h__
-
-#include <linux/types.h>
-#include <linux/slab.h>
-
-struct device;
-
-/* Backend stuff */
-
-/*
- * Debug backend: generate a message header from a 'struct device'
- *
- * @head: buffer where to place the header
- * @head_size: length of @head
- * @dev: pointer to device used to generate a header from. If NULL,
- *     an empty ("") header is generated.
- */
-static inline
-void __d_head(char *head, size_t head_size,
-	      struct device *dev)
-{
-	if (dev == NULL)
-		head[0] = 0;
-	else if ((unsigned long)dev < 4096) {
-		printk(KERN_ERR "E: Corrupt dev %p\n", dev);
-		WARN_ON(1);
-	} else
-		snprintf(head, head_size, "%s %s: ",
-			 dev_driver_string(dev), dev_name(dev));
-}
-
-
-/*
- * Debug backend: log some message if debugging is enabled
- *
- * @l: intended debug level
- * @tag: tag to prefix the message with
- * @dev: 'struct device' associated to this message
- * @f: printf-like format and arguments
- *
- * Note this is optimized out if it doesn't pass the compile-time
- * check; however, it is *always* compiled. This is useful to make
- * sure the printf-like formats and variables are always checked and
- * they don't get bit rot if you have all the debugging disabled.
- */
-#define _d_printf(l, tag, dev, f, a...)					\
-do {									\
-	char head[64];							\
-	if (!d_test(l))							\
-		break;							\
-	__d_head(head, sizeof(head), dev);				\
-	printk(KERN_ERR "%s%s%s: " f, head, __func__, tag, ##a);	\
-} while (0)
-
-
-/*
- * CPP syntactic sugar to generate A_B like symbol names when one of
- * the arguments is a preprocessor #define.
- */
-#define __D_PASTE__(varname, modulename) varname##_##modulename
-#define __D_PASTE(varname, modulename) (__D_PASTE__(varname, modulename))
-#define _D_SUBMODULE_INDEX(_name) (D_SUBMODULE_DECLARE(_name))
-
-
-/*
- * Store a submodule's runtime debug level and name
- */
-struct d_level {
-	u8 level;
-	const char *name;
-};
-
-
-/*
- * List of available submodules and their debug levels
- *
- * We call them d_level_MODULENAME and d_level_size_MODULENAME; the
- * macros D_LEVEL and D_LEVEL_SIZE contain the name already for
- * convenience.
- *
- * This array and the size are defined on some .c file that is part of
- * the current module.
- */
-#define D_LEVEL __D_PASTE(d_level, D_MODULENAME)
-#define D_LEVEL_SIZE __D_PASTE(d_level_size, D_MODULENAME)
-
-extern struct d_level D_LEVEL[];
-extern size_t D_LEVEL_SIZE;
-
-
-/*
- * Frontend stuff
- *
- *
- * Stuff you need to declare prior to using the actual "debug" actions
- * (defined below).
- */
-
-#ifndef D_MODULENAME
-#error D_MODULENAME is not defined in your debug-levels.h file
-/**
- * D_MODULE - Name of the current module
- *
- * #define in your module's debug-levels.h, making sure it is
- * unique. This has to be a legal C identifier.
- */
-#define D_MODULENAME undefined_modulename
-#endif
-
-
-#ifndef D_MASTER
-#warning D_MASTER not defined, but debug.h included! [see docs]
-/**
- * D_MASTER - Compile time maximum debug level
- *
- * #define in your debug-levels.h file to the maximum debug level the
- * runtime code will be allowed to have. This allows you to provide a
- * main knob.
- *
- * Anything above that level will be optimized out of the compile.
- *
- * Defaults to zero (no debug code compiled in).
- *
- * Maximum one definition per module (at the debug-levels.h file).
- */
-#define D_MASTER 0
-#endif
-
-#ifndef D_SUBMODULE
-#error D_SUBMODULE not defined, but debug.h included! [see docs]
-/**
- * D_SUBMODULE - Name of the current submodule
- *
- * #define in your submodule .c file before #including debug-levels.h
- * to the name of the current submodule as previously declared and
- * defined with D_SUBMODULE_DECLARE() (in your module's
- * debug-levels.h) and D_SUBMODULE_DEFINE().
- *
- * This is used to provide runtime-control over the debug levels.
- *
- * Maximum one per .c file! Can be shared among different .c files
- * (meaning they belong to the same submodule categorization).
- */
-#define D_SUBMODULE undefined_module
-#endif
-
-
-/**
- * D_SUBMODULE_DECLARE - Declare a submodule for runtime debug level control
- *
- * @_name: name of the submodule, restricted to the chars that make up a
- *     valid C identifier ([a-zA-Z0-9_]).
- *
- * Declare in the module's debug-levels.h header file as:
- *
- * enum d_module {
- *         D_SUBMODULE_DECLARE(submodule_1),
- *         D_SUBMODULE_DECLARE(submodule_2),
- *         D_SUBMODULE_DECLARE(submodule_3),
- * };
- *
- * Some corresponding .c file needs to have a matching
- * D_SUBMODULE_DEFINE().
- */
-#define D_SUBMODULE_DECLARE(_name) __D_SUBMODULE_##_name
-
-
-/**
- * D_SUBMODULE_DEFINE - Define a submodule for runtime debug level control
- *
- * @_name: name of the submodule, restricted to the chars that make up a
- *     valid C identifier ([a-zA-Z0-9_]).
- *
- * Use once per module (in some .c file) as:
- *
- * static
- * struct d_level d_level_SUBMODULENAME[] = {
- *         D_SUBMODULE_DEFINE(submodule_1),
- *         D_SUBMODULE_DEFINE(submodule_2),
- *         D_SUBMODULE_DEFINE(submodule_3),
- * };
- * size_t d_level_size_SUBDMODULENAME = ARRAY_SIZE(d_level_SUBDMODULENAME);
- *
- * Matching D_SUBMODULE_DECLARE()s have to be present in a
- * debug-levels.h header file.
- */
-#define D_SUBMODULE_DEFINE(_name)		\
-[__D_SUBMODULE_##_name] = {			\
-	.level = 0,				\
-	.name = #_name				\
-}
-
-
-
-/* The actual "debug" operations */
-
-
-/**
- * d_test - Returns true if debugging should be enabled
- *
- * @l: intended debug level (unsigned)
- *
- * If the master debug switch is enabled and the current settings are
- * higher or equal to the requested level, then debugging
- * output/actions should be enabled.
- *
- * NOTE:
- *
- * This needs to be coded so that it can be evaluated in compile
- * time; this is why the ugly BUG_ON() is placed in there, so the
- * D_MASTER evaluation compiles all out if it is compile-time false.
- */
-#define d_test(l)							\
-({									\
-	unsigned __l = l;	/* type enforcer */			\
-	(D_MASTER) >= __l						\
-	&& ({								\
-		BUG_ON(_D_SUBMODULE_INDEX(D_SUBMODULE) >= D_LEVEL_SIZE);\
-		D_LEVEL[_D_SUBMODULE_INDEX(D_SUBMODULE)].level >= __l;	\
-	});								\
-})
-
-
-/**
- * d_fnstart - log message at function start if debugging enabled
- *
- * @l: intended debug level
- * @_dev: 'struct device' pointer, NULL if none (for context)
- * @f: printf-like format and arguments
- */
-#define d_fnstart(l, _dev, f, a...) _d_printf(l, " FNSTART", _dev, f, ## a)
-
-
-/**
- * d_fnend - log message at function end if debugging enabled
- *
- * @l: intended debug level
- * @_dev: 'struct device' pointer, NULL if none (for context)
- * @f: printf-like format and arguments
- */
-#define d_fnend(l, _dev, f, a...) _d_printf(l, " FNEND", _dev, f, ## a)
-
-
-/**
- * d_printf - log message if debugging enabled
- *
- * @l: intended debug level
- * @_dev: 'struct device' pointer, NULL if none (for context)
- * @f: printf-like format and arguments
- */
-#define d_printf(l, _dev, f, a...) _d_printf(l, "", _dev, f, ## a)
-
-
-/**
- * d_dump - log buffer hex dump if debugging enabled
- *
- * @l: intended debug level
- * @_dev: 'struct device' pointer, NULL if none (for context)
- * @f: printf-like format and arguments
- */
-#define d_dump(l, dev, ptr, size)			\
-do {							\
-	char head[64];					\
-	if (!d_test(l))					\
-		break;					\
-	__d_head(head, sizeof(head), dev);		\
-	print_hex_dump(KERN_ERR, head, 0, 16, 1,	\
-		       ((void *) ptr), (size), 0);	\
-} while (0)
-
-
-/**
- * Export a submodule's debug level over debugfs as PREFIXSUBMODULE
- *
- * @prefix: string to prefix the name with
- * @submodule: name of submodule (not a string, just the name)
- * @dentry: debugfs parent dentry
- *
- * For removing, just use debugfs_remove_recursive() on the parent.
- */
-#define d_level_register_debugfs(prefix, name, parent)			\
-({									\
-	debugfs_create_u8(						\
-		prefix #name, 0600, parent,				\
-		&(D_LEVEL[__D_SUBMODULE_ ## name].level));		\
-})
-
-
-static inline
-void d_submodule_set(struct d_level *d_level, size_t d_level_size,
-		     const char *submodule, u8 level, const char *tag)
-{
-	struct d_level *itr, *top;
-	int index = -1;
-
-	for (itr = d_level, top = itr + d_level_size; itr < top; itr++) {
-		index++;
-		if (itr->name == NULL) {
-			printk(KERN_ERR "%s: itr->name NULL?? (%p, #%d)\n",
-			       tag, itr, index);
-			continue;
-		}
-		if (!strcmp(itr->name, submodule)) {
-			itr->level = level;
-			return;
-		}
-	}
-	printk(KERN_ERR "%s: unknown submodule %s\n", tag, submodule);
-}
-
-
-/**
- * d_parse_params - Parse a string with debug parameters from the
- * command line
- *
- * @d_level: level structure (D_LEVEL)
- * @d_level_size: number of items in the level structure
- *     (D_LEVEL_SIZE).
- * @_params: string with the parameters; this is a space (not tab!)
- *     separated list of NAME:VALUE, where value is the debug level
- *     and NAME is the name of the submodule.
- * @tag: string for error messages (example: MODULE.ARGNAME).
- */
-static inline
-void d_parse_params(struct d_level *d_level, size_t d_level_size,
-		    const char *_params, const char *tag)
-{
-	char submodule[130], *params, *params_orig, *token, *colon;
-	unsigned level, tokens;
-
-	if (_params == NULL)
-		return;
-	params_orig = kstrdup(_params, GFP_KERNEL);
-	params = params_orig;
-	while (1) {
-		token = strsep(&params, " ");
-		if (token == NULL)
-			break;
-		if (*token == '\0')	/* eat joint spaces */
-			continue;
-		/* kernel's sscanf %s eats until whitespace, so we
-		 * replace : by \n so it doesn't get eaten later by
-		 * strsep */
-		colon = strchr(token, ':');
-		if (colon != NULL)
-			*colon = '\n';
-		tokens = sscanf(token, "%s\n%u", submodule, &level);
-		if (colon != NULL)
-			*colon = ':';	/* set back, for error messages */
-		if (tokens == 2)
-			d_submodule_set(d_level, d_level_size,
-					submodule, level, tag);
-		else
-			printk(KERN_ERR "%s: can't parse '%s' as a "
-			       "SUBMODULE:LEVEL (%d tokens)\n",
-			       tag, token, tokens);
-	}
-	kfree(params_orig);
-}
-
-#endif /* #ifndef __debug__h__ */
diff --git a/include/net/wimax.h b/include/net/wimax.h
deleted file mode 100644
index f6e31d2f47aa..000000000000
--- a/include/net/wimax.h
+++ /dev/null
@@ -1,503 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Linux WiMAX
- * Kernel space API for accessing WiMAX devices
- *
- * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * The WiMAX stack provides an API for controlling and managing the
- * system's WiMAX devices. This API affects the control plane; the
- * data plane is accessed via the network stack (netdev).
- *
- * Parts of the WiMAX stack API and notifications are exported to
- * user space via Generic Netlink. In user space, libwimax (part of
- * the wimax-tools package) provides a shim layer for accessing those
- * calls.
- *
- * The API is standarized for all WiMAX devices and different drivers
- * implement the backend support for it. However, device-specific
- * messaging pipes are provided that can be used to issue commands and
- * receive notifications in free form.
- *
- * Currently the messaging pipes are the only means of control as it
- * is not known (due to the lack of more devices in the market) what
- * will be a good abstraction layer. Expect this to change as more
- * devices show in the market. This API is designed to be growable in
- * order to address this problem.
- *
- * USAGE
- *
- * Embed a `struct wimax_dev` at the beginning of the device's
- * private structure, initialize and register it. For details, see
- * `struct wimax_dev`s documentation.
- *
- * Once this is done, wimax-tools's libwimaxll can be used to
- * communicate with the driver from user space. You user space
- * application does not have to forcibily use libwimaxll and can talk
- * the generic netlink protocol directly if desired.
- *
- * Remember this is a very low level API that will to provide all of
- * WiMAX features. Other daemons and services running in user space
- * are the expected clients of it. They offer a higher level API that
- * applications should use (an example of this is the Intel's WiMAX
- * Network Service for the i2400m).
- *
- * DESIGN
- *
- * Although not set on final stone, this very basic interface is
- * mostly completed. Remember this is meant to grow as new common
- * operations are decided upon. New operations will be added to the
- * interface, intent being on keeping backwards compatibility as much
- * as possible.
- *
- * This layer implements a set of calls to control a WiMAX device,
- * exposing a frontend to the rest of the kernel and user space (via
- * generic netlink) and a backend implementation in the driver through
- * function pointers.
- *
- * WiMAX devices have a state, and a kernel-only API allows the
- * drivers to manipulate that state. State transitions are atomic, and
- * only some of them are allowed (see `enum wimax_st`).
- *
- * Most API calls will set the state automatically; in most cases
- * drivers have to only report state changes due to external
- * conditions.
- *
- * All API operations are 'atomic', serialized through a mutex in the
- * `struct wimax_dev`.
- *
- * EXPORTING TO USER SPACE THROUGH GENERIC NETLINK
- *
- * The API is exported to user space using generic netlink (other
- * methods can be added as needed).
- *
- * There is a Generic Netlink Family named "WiMAX", where interfaces
- * supporting the WiMAX interface receive commands and broadcast their
- * signals over a multicast group named "msg".
- *
- * Mapping to the source/destination interface is done by an interface
- * index attribute.
- *
- * For user-to-kernel traffic (commands) we use a function call
- * marshalling mechanism, where a message X with attributes A, B, C
- * sent from user space to kernel space means executing the WiMAX API
- * call wimax_X(A, B, C), sending the results back as a message.
- *
- * Kernel-to-user (notifications or signals) communication is sent
- * over multicast groups. This allows to have multiple applications
- * monitoring them.
- *
- * Each command/signal gets assigned it's own attribute policy. This
- * way the validator will verify that all the attributes in there are
- * only the ones that should be for each command/signal. Thing of an
- * attribute mapping to a type+argumentname for each command/signal.
- *
- * If we had a single policy for *all* commands/signals, after running
- * the validator we'd have to check "does this attribute belong in
- * here"?  for each one. It can be done manually, but it's just easier
- * to have the validator do that job with multiple policies. As well,
- * it makes it easier to later expand each command/signal signature
- * without affecting others and keeping the namespace more or less
- * sane. Not that it is too complicated, but it makes it even easier.
- *
- * No state information is maintained in the kernel for each user
- * space connection (the connection is stateless).
- *
- * TESTING FOR THE INTERFACE AND VERSIONING
- *
- * If network interface X is a WiMAX device, there will be a Generic
- * Netlink family named "WiMAX X" and the device will present a
- * "wimax" directory in it's network sysfs directory
- * (/sys/class/net/DEVICE/wimax) [used by HAL].
- *
- * The inexistence of any of these means the device does not support
- * this WiMAX API.
- *
- * By querying the generic netlink controller, versioning information
- * and the multicast groups available can be found. Applications using
- * the interface can either rely on that or use the generic netlink
- * controller to figure out which generic netlink commands/signals are
- * supported.
- *
- * NOTE: this versioning is a last resort to avoid hard
- *    incompatibilities. It is the intention of the design of this
- *    stack not to introduce backward incompatible changes.
- *
- * The version code has to fit in one byte (restrictions imposed by
- * generic netlink); we use `version / 10` for the major version and
- * `version % 10` for the minor. This gives 9 minors for each major
- * and 25 majors.
- *
- * The version change protocol is as follow:
- *
- * - Major versions: needs to be increased if an existing message/API
- *   call is changed or removed. Doesn't need to be changed if a new
- *   message is added.
- *
- * - Minor version: needs to be increased if new messages/API calls are
- *   being added or some other consideration that doesn't impact the
- *   user-kernel interface too much (like some kind of bug fix) and
- *   that is kind of left up in the air to common sense.
- *
- * User space code should not try to work if the major version it was
- * compiled for differs from what the kernel offers. As well, if the
- * minor version of the kernel interface is lower than the one user
- * space is expecting (the one it was compiled for), the kernel
- * might be missing API calls; user space shall be ready to handle
- * said condition. Use the generic netlink controller operations to
- * find which ones are supported and which not.
- *
- * libwimaxll:wimaxll_open() takes care of checking versions.
- *
- * THE OPERATIONS:
- *
- * Each operation is defined in its on file (drivers/net/wimax/op-*.c)
- * for clarity. The parts needed for an operation are:
- *
- *  - a function pointer in `struct wimax_dev`: optional, as the
- *    operation might be implemented by the stack and not by the
- *    driver.
- *
- *    All function pointers are named wimax_dev->op_*(), and drivers
- *    must implement them except where noted otherwise.
- *
- *  - When exported to user space, a `struct nla_policy` to define the
- *    attributes of the generic netlink command and a `struct genl_ops`
- *    to define the operation.
- *
- * All the declarations for the operation codes (WIMAX_GNL_OP_<NAME>)
- * and generic netlink attributes (WIMAX_GNL_<NAME>_*) are declared in
- * include/linux/wimax.h; this file is intended to be cloned by user
- * space to gain access to those declarations.
- *
- * A few caveats to remember:
- *
- *  - Need to define attribute numbers starting in 1; otherwise it
- *    fails.
- *
- *  - the `struct genl_family` requires a maximum attribute id; when
- *    defining the `struct nla_policy` for each message, it has to have
- *    an array size of WIMAX_GNL_ATTR_MAX+1.
- *
- * The op_*() function pointers will not be called if the wimax_dev is
- * in a state <= %WIMAX_ST_UNINITIALIZED. The exception is:
- *
- * - op_reset: can be called at any time after wimax_dev_add() has
- *   been called.
- *
- * THE PIPE INTERFACE:
- *
- * This interface is kept intentionally simple. The driver can send
- * and receive free-form messages to/from user space through a
- * pipe. See drivers/net/wimax/op-msg.c for details.
- *
- * The kernel-to-user messages are sent with
- * wimax_msg(). user-to-kernel messages are delivered via
- * wimax_dev->op_msg_from_user().
- *
- * RFKILL:
- *
- * RFKILL support is built into the wimax_dev layer; the driver just
- * needs to call wimax_report_rfkill_{hw,sw}() to inform of changes in
- * the hardware or software RF kill switches. When the stack wants to
- * turn the radio off, it will call wimax_dev->op_rfkill_sw_toggle(),
- * which the driver implements.
- *
- * User space can set the software RF Kill switch by calling
- * wimax_rfkill().
- *
- * The code for now only supports devices that don't require polling;
- * If the device needs to be polled, create a self-rearming delayed
- * work struct for polling or look into adding polled support to the
- * WiMAX stack.
- *
- * When initializing the hardware (_probe), after calling
- * wimax_dev_add(), query the device for it's RF Kill switches status
- * and feed it back to the WiMAX stack using
- * wimax_report_rfkill_{hw,sw}(). If any switch is missing, always
- * report it as ON.
- *
- * NOTE: the wimax stack uses an inverted terminology to that of the
- * RFKILL subsystem:
- *
- *  - ON: radio is ON, RFKILL is DISABLED or OFF.
- *  - OFF: radio is OFF, RFKILL is ENABLED or ON.
- *
- * MISCELLANEOUS OPS:
- *
- * wimax_reset() can be used to reset the device to power on state; by
- * default it issues a warm reset that maintains the same device
- * node. If that is not possible, it falls back to a cold reset
- * (device reconnect). The driver implements the backend to this
- * through wimax_dev->op_reset().
- */
-
-#ifndef __NET__WIMAX_H__
-#define __NET__WIMAX_H__
-
-#include <linux/wimax.h>
-#include <net/genetlink.h>
-#include <linux/netdevice.h>
-
-struct net_device;
-struct genl_info;
-struct wimax_dev;
-
-/**
- * struct wimax_dev - Generic WiMAX device
- *
- * @net_dev: [fill] Pointer to the &struct net_device this WiMAX
- *     device implements.
- *
- * @op_msg_from_user: [fill] Driver-specific operation to
- *     handle a raw message from user space to the driver. The
- *     driver can send messages to user space using with
- *     wimax_msg_to_user().
- *
- * @op_rfkill_sw_toggle: [fill] Driver-specific operation to act on
- *     userspace (or any other agent) requesting the WiMAX device to
- *     change the RF Kill software switch (WIMAX_RF_ON or
- *     WIMAX_RF_OFF).
- *     If such hardware support is not present, it is assumed the
- *     radio cannot be switched off and it is always on (and the stack
- *     will error out when trying to switch it off). In such case,
- *     this function pointer can be left as NULL.
- *
- * @op_reset: [fill] Driver specific operation to reset the
- *     device.
- *     This operation should always attempt first a warm reset that
- *     does not disconnect the device from the bus and return 0.
- *     If that fails, it should resort to some sort of cold or bus
- *     reset (even if it implies a bus disconnection and device
- *     disappearance). In that case, -ENODEV should be returned to
- *     indicate the device is gone.
- *     This operation has to be synchronous, and return only when the
- *     reset is complete. In case of having had to resort to bus/cold
- *     reset implying a device disconnection, the call is allowed to
- *     return immediately.
- *     NOTE: wimax_dev->mutex is NOT locked when this op is being
- *     called; however, wimax_dev->mutex_reset IS locked to ensure
- *     serialization of calls to wimax_reset().
- *     See wimax_reset()'s documentation.
- *
- * @name: [fill] A way to identify this device. We need to register a
- *     name with many subsystems (rfkill, workqueue creation, etc).
- *     We can't use the network device name as that
- *     might change and in some instances we don't know it yet (until
- *     we don't call register_netdev()). So we generate an unique one
- *     using the driver name and device bus id, place it here and use
- *     it across the board. Recommended naming:
- *     DRIVERNAME-BUSNAME:BUSID (dev->bus->name, dev->bus_id).
- *
- * @id_table_node: [private] link to the list of wimax devices kept by
- *     id-table.c. Protected by it's own spinlock.
- *
- * @mutex: [private] Serializes all concurrent access and execution of
- *     operations.
- *
- * @mutex_reset: [private] Serializes reset operations. Needs to be a
- *     different mutex because as part of the reset operation, the
- *     driver has to call back into the stack to do things such as
- *     state change, that require wimax_dev->mutex.
- *
- * @state: [private] Current state of the WiMAX device.
- *
- * @rfkill: [private] integration into the RF-Kill infrastructure.
- *
- * @rf_sw: [private] State of the software radio switch (OFF/ON)
- *
- * @rf_hw: [private] State of the hardware radio switch (OFF/ON)
- *
- * @debugfs_dentry: [private] Used to hook up a debugfs entry. This
- *     shows up in the debugfs root as wimax\:DEVICENAME.
- *
- * Description:
- * This structure defines a common interface to access all WiMAX
- * devices from different vendors and provides a common API as well as
- * a free-form device-specific messaging channel.
- *
- * Usage:
- *  1. Embed a &struct wimax_dev at *the beginning* the network
- *     device structure so that netdev_priv() points to it.
- *
- *  2. memset() it to zero
- *
- *  3. Initialize with wimax_dev_init(). This will leave the WiMAX
- *     device in the %__WIMAX_ST_NULL state.
- *
- *  4. Fill all the fields marked with [fill]; once called
- *     wimax_dev_add(), those fields CANNOT be modified.
- *
- *  5. Call wimax_dev_add() *after* registering the network
- *     device. This will leave the WiMAX device in the %WIMAX_ST_DOWN
- *     state.
- *     Protect the driver's net_device->open() against succeeding if
- *     the wimax device state is lower than %WIMAX_ST_DOWN.
- *
- *  6. Select when the device is going to be turned on/initialized;
- *     for example, it could be initialized on 'ifconfig up' (when the
- *     netdev op 'open()' is called on the driver).
- *
- * When the device is initialized (at `ifconfig up` time, or right
- * after calling wimax_dev_add() from _probe(), make sure the
- * following steps are taken
- *
- *  a. Move the device to %WIMAX_ST_UNINITIALIZED. This is needed so
- *     some API calls that shouldn't work until the device is ready
- *     can be blocked.
- *
- *  b. Initialize the device. Make sure to turn the SW radio switch
- *     off and move the device to state %WIMAX_ST_RADIO_OFF when
- *     done. When just initialized, a device should be left in RADIO
- *     OFF state until user space devices to turn it on.
- *
- *  c. Query the device for the state of the hardware rfkill switch
- *     and call wimax_rfkill_report_hw() and wimax_rfkill_report_sw()
- *     as needed. See below.
- *
- * wimax_dev_rm() undoes before unregistering the network device. Once
- * wimax_dev_add() is called, the driver can get called on the
- * wimax_dev->op_* function pointers
- *
- * CONCURRENCY:
- *
- * The stack provides a mutex for each device that will disallow API
- * calls happening concurrently; thus, op calls into the driver
- * through the wimax_dev->op*() function pointers will always be
- * serialized and *never* concurrent.
- *
- * For locking, take wimax_dev->mutex is taken; (most) operations in
- * the API have to check for wimax_dev_is_ready() to return 0 before
- * continuing (this is done internally).
- *
- * REFERENCE COUNTING:
- *
- * The WiMAX device is reference counted by the associated network
- * device. The only operation that can be used to reference the device
- * is wimax_dev_get_by_genl_info(), and the reference it acquires has
- * to be released with dev_put(wimax_dev->net_dev).
- *
- * RFKILL:
- *
- * At startup, both HW and SW radio switchess are assumed to be off.
- *
- * At initialization time [after calling wimax_dev_add()], have the
- * driver query the device for the status of the software and hardware
- * RF kill switches and call wimax_report_rfkill_hw() and
- * wimax_rfkill_report_sw() to indicate their state. If any is
- * missing, just call it to indicate it is ON (radio always on).
- *
- * Whenever the driver detects a change in the state of the RF kill
- * switches, it should call wimax_report_rfkill_hw() or
- * wimax_report_rfkill_sw() to report it to the stack.
- */
-struct wimax_dev {
-	struct net_device *net_dev;
-	struct list_head id_table_node;
-	struct mutex mutex;		/* Protects all members and API calls */
-	struct mutex mutex_reset;
-	enum wimax_st state;
-
-	int (*op_msg_from_user)(struct wimax_dev *wimax_dev,
-				const char *,
-				const void *, size_t,
-				const struct genl_info *info);
-	int (*op_rfkill_sw_toggle)(struct wimax_dev *wimax_dev,
-				   enum wimax_rf_state);
-	int (*op_reset)(struct wimax_dev *wimax_dev);
-
-	struct rfkill *rfkill;
-	unsigned int rf_hw;
-	unsigned int rf_sw;
-	char name[32];
-
-	struct dentry *debugfs_dentry;
-};
-
-
-
-/*
- * WiMAX stack public API for device drivers
- * -----------------------------------------
- *
- * These functions are not exported to user space.
- */
-void wimax_dev_init(struct wimax_dev *);
-int wimax_dev_add(struct wimax_dev *, struct net_device *);
-void wimax_dev_rm(struct wimax_dev *);
-
-static inline
-struct wimax_dev *net_dev_to_wimax(struct net_device *net_dev)
-{
-	return netdev_priv(net_dev);
-}
-
-static inline
-struct device *wimax_dev_to_dev(struct wimax_dev *wimax_dev)
-{
-	return wimax_dev->net_dev->dev.parent;
-}
-
-void wimax_state_change(struct wimax_dev *, enum wimax_st);
-enum wimax_st wimax_state_get(struct wimax_dev *);
-
-/*
- * Radio Switch state reporting.
- *
- * enum wimax_rf_state is declared in linux/wimax.h so the exports
- * to user space can use it.
- */
-void wimax_report_rfkill_hw(struct wimax_dev *, enum wimax_rf_state);
-void wimax_report_rfkill_sw(struct wimax_dev *, enum wimax_rf_state);
-
-
-/*
- * Free-form messaging to/from user space
- *
- * Sending a message:
- *
- *   wimax_msg(wimax_dev, pipe_name, buf, buf_size, GFP_KERNEL);
- *
- * Broken up:
- *
- *   skb = wimax_msg_alloc(wimax_dev, pipe_name, buf_size, GFP_KERNEL);
- *   ...fill up skb...
- *   wimax_msg_send(wimax_dev, pipe_name, skb);
- *
- * Be sure not to modify skb->data in the middle (ie: don't use
- * skb_push()/skb_pull()/skb_reserve() on the skb).
- *
- * "pipe_name" is any string, that can be interpreted as the name of
- * the pipe or recipient; the interpretation of it is driver
- * specific, so the recipient can multiplex it as wished. It can be
- * NULL, it won't be used - an example is using a "diagnostics" tag to
- * send diagnostics information that a device-specific diagnostics
- * tool would be interested in.
- */
-struct sk_buff *wimax_msg_alloc(struct wimax_dev *, const char *, const void *,
-				size_t, gfp_t);
-int wimax_msg_send(struct wimax_dev *, struct sk_buff *);
-int wimax_msg(struct wimax_dev *, const char *, const void *, size_t, gfp_t);
-
-const void *wimax_msg_data_len(struct sk_buff *, size_t *);
-const void *wimax_msg_data(struct sk_buff *);
-ssize_t wimax_msg_len(struct sk_buff *);
-
-
-/*
- * WiMAX stack user space API
- * --------------------------
- *
- * This API is what gets exported to user space for general
- * operations. As well, they can be called from within the kernel,
- * (with a properly referenced `struct wimax_dev`).
- *
- * Properly referenced means: the 'struct net_device' that embeds the
- * device's control structure and (as such) the 'struct wimax_dev' is
- * referenced by the caller.
- */
-int wimax_rfkill(struct wimax_dev *, enum wimax_rf_state);
-int wimax_reset(struct wimax_dev *);
-
-#endif /* #ifndef __NET__WIMAX_H__ */
diff --git a/include/uapi/linux/wimax.h b/include/uapi/linux/wimax.h
deleted file mode 100644
index 9f6b77af2f6d..000000000000
--- a/include/uapi/linux/wimax.h
+++ /dev/null
@@ -1,239 +0,0 @@
-/*
- * Linux WiMax
- * API for user space
- *
- *
- * Copyright (C) 2007-2008 Intel Corporation. All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- *   * Redistributions of source code must retain the above copyright
- *     notice, this list of conditions and the following disclaimer.
- *   * Redistributions in binary form must reproduce the above copyright
- *     notice, this list of conditions and the following disclaimer in
- *     the documentation and/or other materials provided with the
- *     distribution.
- *   * Neither the name of Intel Corporation nor the names of its
- *     contributors may be used to endorse or promote products derived
- *     from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *  - Initial implementation
- *
- *
- * This file declares the user/kernel protocol that is spoken over
- * Generic Netlink, as well as any type declaration that is to be used
- * by kernel and user space.
- *
- * It is intended for user space to clone it verbatim to use it as a
- * primary reference for definitions.
- *
- * Stuff intended for kernel usage as well as full protocol and stack
- * documentation is rooted in include/net/wimax.h.
- */
-
-#ifndef __LINUX__WIMAX_H__
-#define __LINUX__WIMAX_H__
-
-#include <linux/types.h>
-
-enum {
-	/**
-	 * Version of the interface (unsigned decimal, MMm, max 25.5)
-	 * M - Major: change if removing or modifying an existing call.
-	 * m - minor: change when adding a new call
-	 */
-	WIMAX_GNL_VERSION = 01,
-	/* Generic NetLink attributes */
-	WIMAX_GNL_ATTR_INVALID = 0x00,
-	WIMAX_GNL_ATTR_MAX = 10,
-};
-
-
-/*
- * Generic NetLink operations
- *
- * Most of these map to an API call; _OP_ stands for operation, _RP_
- * for reply and _RE_ for report (aka: signal).
- */
-enum {
-	WIMAX_GNL_OP_MSG_FROM_USER,	/* User to kernel message */
-	WIMAX_GNL_OP_MSG_TO_USER,	/* Kernel to user message */
-	WIMAX_GNL_OP_RFKILL,	/* Run wimax_rfkill() */
-	WIMAX_GNL_OP_RESET,	/* Run wimax_rfkill() */
-	WIMAX_GNL_RE_STATE_CHANGE,	/* Report: status change */
-	WIMAX_GNL_OP_STATE_GET,		/* Request for current state */
-};
-
-
-/* Message from user / to user */
-enum {
-	WIMAX_GNL_MSG_IFIDX = 1,
-	WIMAX_GNL_MSG_PIPE_NAME,
-	WIMAX_GNL_MSG_DATA,
-};
-
-
-/*
- * wimax_rfkill()
- *
- * The state of the radio (ON/OFF) is mapped to the rfkill subsystem's
- * switch state (DISABLED/ENABLED).
- */
-enum wimax_rf_state {
-	WIMAX_RF_OFF = 0,	/* Radio is off, rfkill on/enabled */
-	WIMAX_RF_ON = 1,	/* Radio is on, rfkill off/disabled */
-	WIMAX_RF_QUERY = 2,
-};
-
-/* Attributes */
-enum {
-	WIMAX_GNL_RFKILL_IFIDX = 1,
-	WIMAX_GNL_RFKILL_STATE,
-};
-
-
-/* Attributes for wimax_reset() */
-enum {
-	WIMAX_GNL_RESET_IFIDX = 1,
-};
-
-/* Attributes for wimax_state_get() */
-enum {
-	WIMAX_GNL_STGET_IFIDX = 1,
-};
-
-/*
- * Attributes for the Report State Change
- *
- * For now we just have the old and new states; new attributes might
- * be added later on.
- */
-enum {
-	WIMAX_GNL_STCH_IFIDX = 1,
-	WIMAX_GNL_STCH_STATE_OLD,
-	WIMAX_GNL_STCH_STATE_NEW,
-};
-
-
-/**
- * enum wimax_st - The different states of a WiMAX device
- * @__WIMAX_ST_NULL: The device structure has been allocated and zeroed,
- *     but still wimax_dev_add() hasn't been called. There is no state.
- *
- * @WIMAX_ST_DOWN: The device has been registered with the WiMAX and
- *     networking stacks, but it is not initialized (normally that is
- *     done with 'ifconfig DEV up' [or equivalent], which can upload
- *     firmware and enable communications with the device).
- *     In this state, the device is powered down and using as less
- *     power as possible.
- *     This state is the default after a call to wimax_dev_add(). It
- *     is ok to have drivers move directly to %WIMAX_ST_UNINITIALIZED
- *     or %WIMAX_ST_RADIO_OFF in _probe() after the call to
- *     wimax_dev_add().
- *     It is recommended that the driver leaves this state when
- *     calling 'ifconfig DEV up' and enters it back on 'ifconfig DEV
- *     down'.
- *
- * @__WIMAX_ST_QUIESCING: The device is being torn down, so no API
- *     operations are allowed to proceed except the ones needed to
- *     complete the device clean up process.
- *
- * @WIMAX_ST_UNINITIALIZED: [optional] Communication with the device
- *     is setup, but the device still requires some configuration
- *     before being operational.
- *     Some WiMAX API calls might work.
- *
- * @WIMAX_ST_RADIO_OFF: The device is fully up; radio is off (wether
- *     by hardware or software switches).
- *     It is recommended to always leave the device in this state
- *     after initialization.
- *
- * @WIMAX_ST_READY: The device is fully up and radio is on.
- *
- * @WIMAX_ST_SCANNING: [optional] The device has been instructed to
- *     scan. In this state, the device cannot be actively connected to
- *     a network.
- *
- * @WIMAX_ST_CONNECTING: The device is connecting to a network. This
- *     state exists because in some devices, the connect process can
- *     include a number of negotiations between user space, kernel
- *     space and the device. User space needs to know what the device
- *     is doing. If the connect sequence in a device is atomic and
- *     fast, the device can transition directly to CONNECTED
- *
- * @WIMAX_ST_CONNECTED: The device is connected to a network.
- *
- * @__WIMAX_ST_INVALID: This is an invalid state used to mark the
- *     maximum numeric value of states.
- *
- * Description:
- *
- * Transitions from one state to another one are atomic and can only
- * be caused in kernel space with wimax_state_change(). To read the
- * state, use wimax_state_get().
- *
- * States starting with __ are internal and shall not be used or
- * referred to by drivers or userspace. They look ugly, but that's the
- * point -- if any use is made non-internal to the stack, it is easier
- * to catch on review.
- *
- * All API operations [with well defined exceptions] will take the
- * device mutex before starting and then check the state. If the state
- * is %__WIMAX_ST_NULL, %WIMAX_ST_DOWN, %WIMAX_ST_UNINITIALIZED or
- * %__WIMAX_ST_QUIESCING, it will drop the lock and quit with
- * -%EINVAL, -%ENOMEDIUM, -%ENOTCONN or -%ESHUTDOWN.
- *
- * The order of the definitions is important, so we can do numerical
- * comparisons (eg: < %WIMAX_ST_RADIO_OFF means the device is not ready
- * to operate).
- */
-/*
- * The allowed state transitions are described in the table below
- * (states in rows can go to states in columns where there is an X):
- *
- *                                  UNINI   RADIO READY SCAN CONNEC CONNEC
- *             NULL DOWN QUIESCING TIALIZED  OFF        NING  TING   TED
- * NULL         -    x
- * DOWN              -      x        x       x
- * QUIESCING         x      -
- * UNINITIALIZED            x        -       x
- * RADIO_OFF                x                -     x
- * READY                    x                x     -     x     x      x
- * SCANNING                 x                x     x     -     x      x
- * CONNECTING               x                x     x     x     -      x
- * CONNECTED                x                x     x                  -
- *
- * This table not available in kernel-doc because the formatting messes it up.
- */
- enum wimax_st {
-	__WIMAX_ST_NULL = 0,
-	WIMAX_ST_DOWN,
-	__WIMAX_ST_QUIESCING,
-	WIMAX_ST_UNINITIALIZED,
-	WIMAX_ST_RADIO_OFF,
-	WIMAX_ST_READY,
-	WIMAX_ST_SCANNING,
-	WIMAX_ST_CONNECTING,
-	WIMAX_ST_CONNECTED,
-	__WIMAX_ST_INVALID			/* Always keep last */
-};
-
-
-#endif /* #ifndef __LINUX__WIMAX_H__ */
diff --git a/include/uapi/linux/wimax/i2400m.h b/include/uapi/linux/wimax/i2400m.h
deleted file mode 100644
index fd198bc24a3c..000000000000
--- a/include/uapi/linux/wimax/i2400m.h
+++ /dev/null
@@ -1,572 +0,0 @@
-/*
- * Intel Wireless WiMax Connection 2400m
- * Host-Device protocol interface definitions
- *
- *
- * Copyright (C) 2007-2008 Intel Corporation. All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- *   * Redistributions of source code must retain the above copyright
- *     notice, this list of conditions and the following disclaimer.
- *   * Redistributions in binary form must reproduce the above copyright
- *     notice, this list of conditions and the following disclaimer in
- *     the documentation and/or other materials provided with the
- *     distribution.
- *   * Neither the name of Intel Corporation nor the names of its
- *     contributors may be used to endorse or promote products derived
- *     from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- *
- * Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *  - Initial implementation
- *
- *
- * This header defines the data structures and constants used to
- * communicate with the device.
- *
- * BOOTMODE/BOOTROM/FIRMWARE UPLOAD PROTOCOL
- *
- * The firmware upload protocol is quite simple and only requires a
- * handful of commands. See drivers/net/wimax/i2400m/fw.c for more
- * details.
- *
- * The BCF data structure is for the firmware file header.
- *
- *
- * THE DATA / CONTROL PROTOCOL
- *
- * This is the normal protocol spoken with the device once the
- * firmware is uploaded. It transports data payloads and control
- * messages back and forth.
- *
- * It consists 'messages' that pack one or more payloads each. The
- * format is described in detail in drivers/net/wimax/i2400m/rx.c and
- * tx.c.
- *
- *
- * THE L3L4 PROTOCOL
- *
- * The term L3L4 refers to Layer 3 (the device), Layer 4 (the
- * driver/host software).
- *
- * This is the control protocol used by the host to control the i2400m
- * device (scan, connect, disconnect...). This is sent to / received
- * as control frames. These frames consist of a header and zero or
- * more TLVs with information. We call each control frame a "message".
- *
- * Each message is composed of:
- *
- * HEADER
- * [TLV0 + PAYLOAD0]
- * [TLV1 + PAYLOAD1]
- * [...]
- * [TLVN + PAYLOADN]
- *
- * The HEADER is defined by 'struct i2400m_l3l4_hdr'. The payloads are
- * defined by a TLV structure (Type Length Value) which is a 'header'
- * (struct i2400m_tlv_hdr) and then the payload.
- *
- * All integers are represented as Little Endian.
- *
- * - REQUESTS AND EVENTS
- *
- * The requests can be clasified as follows:
- *
- *   COMMAND:  implies a request from the host to the device requesting
- *             an action being performed. The device will reply with a
- *             message (with the same type as the command), status and
- *             no (TLV) payload. Execution of a command might cause
- *             events (of different type) to be sent later on as
- *             device's state changes.
- *
- *   GET/SET:  similar to COMMAND, but will not cause other
- *             EVENTs. The reply, in the case of GET, will contain
- *             TLVs with the requested information.
- *
- *   EVENT:    asynchronous messages sent from the device, maybe as a
- *             consequence of previous COMMANDs but disassociated from
- *             them.
- *
- * Only one request might be pending at the same time (ie: don't
- * parallelize nor post another GET request before the previous
- * COMMAND has been acknowledged with it's corresponding reply by the
- * device).
- *
- * The different requests and their formats are described below:
- *
- *  I2400M_MT_*   Message types
- *  I2400M_MS_*   Message status (for replies, events)
- *  i2400m_tlv_*  TLVs
- *
- * data types are named 'struct i2400m_msg_OPNAME', OPNAME matching the
- * operation.
- */
-
-#ifndef __LINUX__WIMAX__I2400M_H__
-#define __LINUX__WIMAX__I2400M_H__
-
-#include <linux/types.h>
-#include <linux/if_ether.h>
-
-/*
- * Host Device Interface (HDI) common to all busses
- */
-
-/* Boot-mode (firmware upload mode) commands */
-
-/* Header for the firmware file */
-struct i2400m_bcf_hdr {
-	__le32 module_type;
-	__le32 header_len;
-	__le32 header_version;
-	__le32 module_id;
-	__le32 module_vendor;
-	__le32 date;		/* BCD YYYMMDD */
-	__le32 size;            /* in dwords */
-	__le32 key_size;	/* in dwords */
-	__le32 modulus_size;	/* in dwords */
-	__le32 exponent_size;	/* in dwords */
-	__u8 reserved[88];
-} __attribute__ ((packed));
-
-/* Boot mode opcodes */
-enum i2400m_brh_opcode {
-	I2400M_BRH_READ = 1,
-	I2400M_BRH_WRITE = 2,
-	I2400M_BRH_JUMP = 3,
-	I2400M_BRH_SIGNED_JUMP = 8,
-	I2400M_BRH_HASH_PAYLOAD_ONLY = 9,
-};
-
-/* Boot mode command masks and stuff */
-enum i2400m_brh {
-	I2400M_BRH_SIGNATURE = 0xcbbc0000,
-	I2400M_BRH_SIGNATURE_MASK = 0xffff0000,
-	I2400M_BRH_SIGNATURE_SHIFT = 16,
-	I2400M_BRH_OPCODE_MASK = 0x0000000f,
-	I2400M_BRH_RESPONSE_MASK = 0x000000f0,
-	I2400M_BRH_RESPONSE_SHIFT = 4,
-	I2400M_BRH_DIRECT_ACCESS = 0x00000400,
-	I2400M_BRH_RESPONSE_REQUIRED = 0x00000200,
-	I2400M_BRH_USE_CHECKSUM = 0x00000100,
-};
-
-
-/**
- * i2400m_bootrom_header - Header for a boot-mode command
- *
- * @cmd: the above command descriptor
- * @target_addr: where on the device memory should the action be performed.
- * @data_size: for read/write, amount of data to be read/written
- * @block_checksum: checksum value (if applicable)
- * @payload: the beginning of data attached to this header
- */
-struct i2400m_bootrom_header {
-	__le32 command;		/* Compose with enum i2400_brh */
-	__le32 target_addr;
-	__le32 data_size;
-	__le32 block_checksum;
-	char payload[0];
-} __attribute__ ((packed));
-
-
-/*
- * Data / control protocol
- */
-
-/* Packet types for the host-device interface */
-enum i2400m_pt {
-	I2400M_PT_DATA = 0,
-	I2400M_PT_CTRL,
-	I2400M_PT_TRACE,	/* For device debug */
-	I2400M_PT_RESET_WARM,	/* device reset */
-	I2400M_PT_RESET_COLD,	/* USB[transport] reset, like reconnect */
-	I2400M_PT_EDATA,	/* Extended RX data */
-	I2400M_PT_ILLEGAL
-};
-
-
-/*
- * Payload for a data packet
- *
- * This is prefixed to each and every outgoing DATA type.
- */
-struct i2400m_pl_data_hdr {
-	__le32 reserved;
-} __attribute__((packed));
-
-
-/*
- * Payload for an extended data packet
- *
- * New in fw v1.4
- *
- * @reorder: if this payload has to be reorder or not (and how)
- * @cs: the type of data in the packet, as defined per (802.16e
- *     T11.13.19.1). Currently only 2 (IPv4 packet) supported.
- *
- * This is prefixed to each and every INCOMING DATA packet.
- */
-struct i2400m_pl_edata_hdr {
-	__le32 reorder;		/* bits defined in i2400m_ro */
-	__u8 cs;
-	__u8 reserved[11];
-} __attribute__((packed));
-
-enum i2400m_cs {
-	I2400M_CS_IPV4_0 = 0,
-	I2400M_CS_IPV4 = 2,
-};
-
-enum i2400m_ro {
-	I2400M_RO_NEEDED     = 0x01,
-	I2400M_RO_TYPE       = 0x03,
-	I2400M_RO_TYPE_SHIFT = 1,
-	I2400M_RO_CIN        = 0x0f,
-	I2400M_RO_CIN_SHIFT  = 4,
-	I2400M_RO_FBN        = 0x07ff,
-	I2400M_RO_FBN_SHIFT  = 8,
-	I2400M_RO_SN         = 0x07ff,
-	I2400M_RO_SN_SHIFT   = 21,
-};
-
-enum i2400m_ro_type {
-	I2400M_RO_TYPE_RESET = 0,
-	I2400M_RO_TYPE_PACKET,
-	I2400M_RO_TYPE_WS,
-	I2400M_RO_TYPE_PACKET_WS,
-};
-
-
-/* Misc constants */
-enum {
-	I2400M_PL_ALIGN = 16,	/* Payload data size alignment */
-	I2400M_PL_SIZE_MAX = 0x3EFF,
-	I2400M_MAX_PLS_IN_MSG = 60,
-	/* protocol barkers: sync sequences; for notifications they
-	 * are sent in groups of four. */
-	I2400M_H2D_PREVIEW_BARKER = 0xcafe900d,
-	I2400M_COLD_RESET_BARKER = 0xc01dc01d,
-	I2400M_WARM_RESET_BARKER = 0x50f750f7,
-	I2400M_NBOOT_BARKER = 0xdeadbeef,
-	I2400M_SBOOT_BARKER = 0x0ff1c1a1,
-	I2400M_SBOOT_BARKER_6050 = 0x80000001,
-	I2400M_ACK_BARKER = 0xfeedbabe,
-	I2400M_D2H_MSG_BARKER = 0xbeefbabe,
-};
-
-
-/*
- * Hardware payload descriptor
- *
- * Bitfields encoded in a struct to enforce typing semantics.
- *
- * Look in rx.c and tx.c for a full description of the format.
- */
-struct i2400m_pld {
-	__le32 val;
-} __attribute__ ((packed));
-
-#define I2400M_PLD_SIZE_MASK 0x00003fff
-#define I2400M_PLD_TYPE_SHIFT 16
-#define I2400M_PLD_TYPE_MASK 0x000f0000
-
-/*
- * Header for a TX message or RX message
- *
- * @barker: preamble
- * @size: used for management of the FIFO queue buffer; before
- *     sending, this is converted to be a real preamble. This
- *     indicates the real size of the TX message that starts at this
- *     point. If the highest bit is set, then this message is to be
- *     skipped.
- * @sequence: sequence number of this message
- * @offset: offset where the message itself starts -- see the comments
- *     in the file header about message header and payload descriptor
- *     alignment.
- * @num_pls: number of payloads in this message
- * @padding: amount of padding bytes at the end of the message to make
- *           it be of block-size aligned
- *
- * Look in rx.c and tx.c for a full description of the format.
- */
-struct i2400m_msg_hdr {
-	union {
-		__le32 barker;
-		__u32 size;	/* same size type as barker!! */
-	};
-	union {
-		__le32 sequence;
-		__u32 offset;	/* same size type as barker!! */
-	};
-	__le16 num_pls;
-	__le16 rsv1;
-	__le16 padding;
-	__le16 rsv2;
-	struct i2400m_pld pld[0];
-} __attribute__ ((packed));
-
-
-
-/*
- * L3/L4 control protocol
- */
-
-enum {
-	/* Interface version */
-	I2400M_L3L4_VERSION             = 0x0100,
-};
-
-/* Message types */
-enum i2400m_mt {
-	I2400M_MT_RESERVED              = 0x0000,
-	I2400M_MT_INVALID               = 0xffff,
-	I2400M_MT_REPORT_MASK		= 0x8000,
-
-	I2400M_MT_GET_SCAN_RESULT  	= 0x4202,
-	I2400M_MT_SET_SCAN_PARAM   	= 0x4402,
-	I2400M_MT_CMD_RF_CONTROL   	= 0x4602,
-	I2400M_MT_CMD_SCAN         	= 0x4603,
-	I2400M_MT_CMD_CONNECT      	= 0x4604,
-	I2400M_MT_CMD_DISCONNECT   	= 0x4605,
-	I2400M_MT_CMD_EXIT_IDLE   	= 0x4606,
-	I2400M_MT_GET_LM_VERSION   	= 0x5201,
-	I2400M_MT_GET_DEVICE_INFO  	= 0x5202,
-	I2400M_MT_GET_LINK_STATUS  	= 0x5203,
-	I2400M_MT_GET_STATISTICS   	= 0x5204,
-	I2400M_MT_GET_STATE        	= 0x5205,
-	I2400M_MT_GET_MEDIA_STATUS	= 0x5206,
-	I2400M_MT_SET_INIT_CONFIG	= 0x5404,
-	I2400M_MT_CMD_INIT	        = 0x5601,
-	I2400M_MT_CMD_TERMINATE		= 0x5602,
-	I2400M_MT_CMD_MODE_OF_OP	= 0x5603,
-	I2400M_MT_CMD_RESET_DEVICE	= 0x5604,
-	I2400M_MT_CMD_MONITOR_CONTROL   = 0x5605,
-	I2400M_MT_CMD_ENTER_POWERSAVE   = 0x5606,
-	I2400M_MT_GET_TLS_OPERATION_RESULT = 0x6201,
-	I2400M_MT_SET_EAP_SUCCESS       = 0x6402,
-	I2400M_MT_SET_EAP_FAIL          = 0x6403,
-	I2400M_MT_SET_EAP_KEY          	= 0x6404,
-	I2400M_MT_CMD_SEND_EAP_RESPONSE = 0x6602,
-	I2400M_MT_REPORT_SCAN_RESULT    = 0xc002,
-	I2400M_MT_REPORT_STATE		= 0xd002,
-	I2400M_MT_REPORT_POWERSAVE_READY = 0xd005,
-	I2400M_MT_REPORT_EAP_REQUEST    = 0xe002,
-	I2400M_MT_REPORT_EAP_RESTART    = 0xe003,
-	I2400M_MT_REPORT_ALT_ACCEPT    	= 0xe004,
-	I2400M_MT_REPORT_KEY_REQUEST 	= 0xe005,
-};
-
-
-/*
- * Message Ack Status codes
- *
- * When a message is replied-to, this status is reported.
- */
-enum i2400m_ms {
-	I2400M_MS_DONE_OK                  = 0,
-	I2400M_MS_DONE_IN_PROGRESS         = 1,
-	I2400M_MS_INVALID_OP               = 2,
-	I2400M_MS_BAD_STATE                = 3,
-	I2400M_MS_ILLEGAL_VALUE            = 4,
-	I2400M_MS_MISSING_PARAMS           = 5,
-	I2400M_MS_VERSION_ERROR            = 6,
-	I2400M_MS_ACCESSIBILITY_ERROR      = 7,
-	I2400M_MS_BUSY                     = 8,
-	I2400M_MS_CORRUPTED_TLV            = 9,
-	I2400M_MS_UNINITIALIZED            = 10,
-	I2400M_MS_UNKNOWN_ERROR            = 11,
-	I2400M_MS_PRODUCTION_ERROR         = 12,
-	I2400M_MS_NO_RF                    = 13,
-	I2400M_MS_NOT_READY_FOR_POWERSAVE  = 14,
-	I2400M_MS_THERMAL_CRITICAL         = 15,
-	I2400M_MS_MAX
-};
-
-
-/**
- * i2400m_tlv - enumeration of the different types of TLVs
- *
- * TLVs stand for type-length-value and are the header for a payload
- * composed of almost anything. Each payload has a type assigned
- * and a length.
- */
-enum i2400m_tlv {
-	I2400M_TLV_L4_MESSAGE_VERSIONS = 129,
-	I2400M_TLV_SYSTEM_STATE = 141,
-	I2400M_TLV_MEDIA_STATUS = 161,
-	I2400M_TLV_RF_OPERATION = 162,
-	I2400M_TLV_RF_STATUS = 163,
-	I2400M_TLV_DEVICE_RESET_TYPE = 132,
-	I2400M_TLV_CONFIG_IDLE_PARAMETERS = 601,
-	I2400M_TLV_CONFIG_IDLE_TIMEOUT = 611,
-	I2400M_TLV_CONFIG_D2H_DATA_FORMAT = 614,
-	I2400M_TLV_CONFIG_DL_HOST_REORDER = 615,
-};
-
-
-struct i2400m_tlv_hdr {
-	__le16 type;
-	__le16 length;		/* payload's */
-	__u8   pl[0];
-} __attribute__((packed));
-
-
-struct i2400m_l3l4_hdr {
-	__le16 type;
-	__le16 length;		/* payload's */
-	__le16 version;
-	__le16 resv1;
-	__le16 status;
-	__le16 resv2;
-	struct i2400m_tlv_hdr pl[0];
-} __attribute__((packed));
-
-
-/**
- * i2400m_system_state - different states of the device
- */
-enum i2400m_system_state {
-	I2400M_SS_UNINITIALIZED = 1,
-	I2400M_SS_INIT,
-	I2400M_SS_READY,
-	I2400M_SS_SCAN,
-	I2400M_SS_STANDBY,
-	I2400M_SS_CONNECTING,
-	I2400M_SS_WIMAX_CONNECTED,
-	I2400M_SS_DATA_PATH_CONNECTED,
-	I2400M_SS_IDLE,
-	I2400M_SS_DISCONNECTING,
-	I2400M_SS_OUT_OF_ZONE,
-	I2400M_SS_SLEEPACTIVE,
-	I2400M_SS_PRODUCTION,
-	I2400M_SS_CONFIG,
-	I2400M_SS_RF_OFF,
-	I2400M_SS_RF_SHUTDOWN,
-	I2400M_SS_DEVICE_DISCONNECT,
-	I2400M_SS_MAX,
-};
-
-
-/**
- * i2400m_tlv_system_state - report on the state of the system
- *
- * @state: see enum i2400m_system_state
- */
-struct i2400m_tlv_system_state {
-	struct i2400m_tlv_hdr hdr;
-	__le32 state;
-} __attribute__((packed));
-
-
-struct i2400m_tlv_l4_message_versions {
-	struct i2400m_tlv_hdr hdr;
-	__le16 major;
-	__le16 minor;
-	__le16 branch;
-	__le16 reserved;
-} __attribute__((packed));
-
-
-struct i2400m_tlv_detailed_device_info {
-	struct i2400m_tlv_hdr hdr;
-	__u8 reserved1[400];
-	__u8 mac_address[ETH_ALEN];
-	__u8 reserved2[2];
-} __attribute__((packed));
-
-
-enum i2400m_rf_switch_status {
-	I2400M_RF_SWITCH_ON = 1,
-	I2400M_RF_SWITCH_OFF = 2,
-};
-
-struct i2400m_tlv_rf_switches_status {
-	struct i2400m_tlv_hdr hdr;
-	__u8 sw_rf_switch;	/* 1 ON, 2 OFF */
-	__u8 hw_rf_switch;	/* 1 ON, 2 OFF */
-	__u8 reserved[2];
-} __attribute__((packed));
-
-
-enum {
-	i2400m_rf_operation_on = 1,
-	i2400m_rf_operation_off = 2
-};
-
-struct i2400m_tlv_rf_operation {
-	struct i2400m_tlv_hdr hdr;
-	__le32 status;	/* 1 ON, 2 OFF */
-} __attribute__((packed));
-
-
-enum i2400m_tlv_reset_type {
-	I2400M_RESET_TYPE_COLD = 1,
-	I2400M_RESET_TYPE_WARM
-};
-
-struct i2400m_tlv_device_reset_type {
-	struct i2400m_tlv_hdr hdr;
-	__le32 reset_type;
-} __attribute__((packed));
-
-
-struct i2400m_tlv_config_idle_parameters {
-	struct i2400m_tlv_hdr hdr;
-	__le32 idle_timeout;	/* 100 to 300000 ms [5min], 100 increments
-				 * 0 disabled */
-	__le32 idle_paging_interval;	/* frames */
-} __attribute__((packed));
-
-
-enum i2400m_media_status {
-	I2400M_MEDIA_STATUS_LINK_UP = 1,
-	I2400M_MEDIA_STATUS_LINK_DOWN,
-	I2400M_MEDIA_STATUS_LINK_RENEW,
-};
-
-struct i2400m_tlv_media_status {
-	struct i2400m_tlv_hdr hdr;
-	__le32 media_status;
-} __attribute__((packed));
-
-
-/* New in v1.4 */
-struct i2400m_tlv_config_idle_timeout {
-	struct i2400m_tlv_hdr hdr;
-	__le32 timeout;	/* 100 to 300000 ms [5min], 100 increments
-			 * 0 disabled */
-} __attribute__((packed));
-
-/* New in v1.4 -- for backward compat, will be removed */
-struct i2400m_tlv_config_d2h_data_format {
-	struct i2400m_tlv_hdr hdr;
-	__u8 format; 		/* 0 old format, 1 enhanced */
-	__u8 reserved[3];
-} __attribute__((packed));
-
-/* New in v1.4 */
-struct i2400m_tlv_config_dl_host_reorder {
-	struct i2400m_tlv_hdr hdr;
-	__u8 reorder; 		/* 0 disabled, 1 enabled */
-	__u8 reserved[3];
-} __attribute__((packed));
-
-
-#endif /* #ifndef __LINUX__WIMAX__I2400M_H__ */
diff --git a/net/Kconfig b/net/Kconfig
index d6567162c1cf..f4c32d982af6 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -386,8 +386,6 @@ source "net/mac80211/Kconfig"
 
 endif # WIRELESS
 
-source "net/wimax/Kconfig"
-
 source "net/rfkill/Kconfig"
 source "net/9p/Kconfig"
 source "net/caif/Kconfig"
diff --git a/net/Makefile b/net/Makefile
index 5744bf1997fd..d96b0aa8f39f 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -66,7 +66,6 @@ obj-$(CONFIG_MAC802154)		+= mac802154/
 ifeq ($(CONFIG_NET),y)
 obj-$(CONFIG_SYSCTL)		+= sysctl_net.o
 endif
-obj-$(CONFIG_WIMAX)		+= wimax/
 obj-$(CONFIG_DNS_RESOLVER)	+= dns_resolver/
 obj-$(CONFIG_CEPH_LIB)		+= ceph/
 obj-$(CONFIG_BATMAN_ADV)	+= batman-adv/
diff --git a/net/wimax/Kconfig b/net/wimax/Kconfig
deleted file mode 100644
index d13762bc4abc..000000000000
--- a/net/wimax/Kconfig
+++ /dev/null
@@ -1,40 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-#
-# WiMAX LAN device configuration
-#
-
-menuconfig WIMAX
-	tristate "WiMAX Wireless Broadband support"
-	depends on RFKILL || !RFKILL
-	help
-
-	  Select to configure support for devices that provide
-	  wireless broadband connectivity using the WiMAX protocol
-	  (IEEE 802.16).
-
-	  Please note that most of these devices require signing up
-	  for a service plan with a provider.
-
-	  The different WiMAX drivers can be enabled in the menu entry
-
-	  Device Drivers > Network device support > WiMAX Wireless
-	  Broadband devices
-
-	  If unsure, it is safe to select M (module).
-
-config WIMAX_DEBUG_LEVEL
-	int "WiMAX debug level"
-	depends on WIMAX
-	default 8
-	help
-
-	  Select the maximum debug verbosity level to be compiled into
-	  the WiMAX stack code.
-
-	  By default, debug messages are disabled at runtime and can
-	  be selectively enabled for different parts of the code using
-	  the sysfs debug-levels file.
-
-	  If set at zero, this will compile out all the debug code.
-
-	  It is recommended that it is left at 8.
diff --git a/net/wimax/Makefile b/net/wimax/Makefile
deleted file mode 100644
index c2a71ae487ac..000000000000
--- a/net/wimax/Makefile
+++ /dev/null
@@ -1,13 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-
-obj-$(CONFIG_WIMAX)		+= wimax.o
-
-wimax-y :=		\
-	id-table.o	\
-	op-msg.o	\
-	op-reset.o	\
-	op-rfkill.o	\
-	op-state-get.o	\
-	stack.o
-
-wimax-$(CONFIG_DEBUG_FS) += debugfs.o
diff --git a/net/wimax/debug-levels.h b/net/wimax/debug-levels.h
deleted file mode 100644
index ebc287cde336..000000000000
--- a/net/wimax/debug-levels.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Linux WiMAX Stack
- * Debug levels control file for the wimax module
- *
- * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- */
-#ifndef __debug_levels__h__
-#define __debug_levels__h__
-
-/* Maximum compile and run time debug level for all submodules */
-#define D_MODULENAME wimax
-#define D_MASTER CONFIG_WIMAX_DEBUG_LEVEL
-
-#include <linux/wimax/debug.h>
-
-/* List of all the enabled modules */
-enum d_module {
-	D_SUBMODULE_DECLARE(debugfs),
-	D_SUBMODULE_DECLARE(id_table),
-	D_SUBMODULE_DECLARE(op_msg),
-	D_SUBMODULE_DECLARE(op_reset),
-	D_SUBMODULE_DECLARE(op_rfkill),
-	D_SUBMODULE_DECLARE(op_state_get),
-	D_SUBMODULE_DECLARE(stack),
-};
-
-#endif /* #ifndef __debug_levels__h__ */
diff --git a/net/wimax/debugfs.c b/net/wimax/debugfs.c
deleted file mode 100644
index 3c54bb6b925a..000000000000
--- a/net/wimax/debugfs.c
+++ /dev/null
@@ -1,38 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Linux WiMAX
- * Debugfs support
- *
- * Copyright (C) 2005-2006 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- */
-#include <linux/debugfs.h>
-#include <linux/wimax.h>
-#include "wimax-internal.h"
-
-#define D_SUBMODULE debugfs
-#include "debug-levels.h"
-
-void wimax_debugfs_add(struct wimax_dev *wimax_dev)
-{
-	struct net_device *net_dev = wimax_dev->net_dev;
-	struct dentry *dentry;
-	char buf[128];
-
-	snprintf(buf, sizeof(buf), "wimax:%s", net_dev->name);
-	dentry = debugfs_create_dir(buf, NULL);
-	wimax_dev->debugfs_dentry = dentry;
-
-	d_level_register_debugfs("wimax_dl_", debugfs, dentry);
-	d_level_register_debugfs("wimax_dl_", id_table, dentry);
-	d_level_register_debugfs("wimax_dl_", op_msg, dentry);
-	d_level_register_debugfs("wimax_dl_", op_reset, dentry);
-	d_level_register_debugfs("wimax_dl_", op_rfkill, dentry);
-	d_level_register_debugfs("wimax_dl_", op_state_get, dentry);
-	d_level_register_debugfs("wimax_dl_", stack, dentry);
-}
-
-void wimax_debugfs_rm(struct wimax_dev *wimax_dev)
-{
-	debugfs_remove_recursive(wimax_dev->debugfs_dentry);
-}
diff --git a/net/wimax/id-table.c b/net/wimax/id-table.c
deleted file mode 100644
index 02eee37b7e31..000000000000
--- a/net/wimax/id-table.c
+++ /dev/null
@@ -1,130 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Linux WiMAX
- * Mappping of generic netlink family IDs to net devices
- *
- * Copyright (C) 2005-2006 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * We assign a single generic netlink family ID to each device (to
- * simplify lookup).
- *
- * We need a way to map family ID to a wimax_dev pointer.
- *
- * The idea is to use a very simple lookup. Using a netlink attribute
- * with (for example) the interface name implies a heavier search over
- * all the network devices; seemed kind of a waste given that we know
- * we are looking for a WiMAX device and that most systems will have
- * just a single WiMAX adapter.
- *
- * We put all the WiMAX devices in the system in a linked list and
- * match the generic link family ID against the list.
- *
- * By using a linked list, the case of a single adapter in the system
- * becomes (almost) no overhead, while still working for many more. If
- * it ever goes beyond two, I'll be surprised.
- */
-#include <linux/device.h>
-#include <net/genetlink.h>
-#include <linux/netdevice.h>
-#include <linux/list.h>
-#include <linux/wimax.h>
-#include "wimax-internal.h"
-
-
-#define D_SUBMODULE id_table
-#include "debug-levels.h"
-
-
-static DEFINE_SPINLOCK(wimax_id_table_lock);
-static struct list_head wimax_id_table = LIST_HEAD_INIT(wimax_id_table);
-
-
-/*
- * wimax_id_table_add - add a gennetlink familiy ID / wimax_dev mapping
- *
- * @wimax_dev: WiMAX device descriptor to associate to the Generic
- *     Netlink family ID.
- *
- * Look for an empty spot in the ID table; if none found, double the
- * table's size and get the first spot.
- */
-void wimax_id_table_add(struct wimax_dev *wimax_dev)
-{
-	d_fnstart(3, NULL, "(wimax_dev %p)\n", wimax_dev);
-	spin_lock(&wimax_id_table_lock);
-	list_add(&wimax_dev->id_table_node, &wimax_id_table);
-	spin_unlock(&wimax_id_table_lock);
-	d_fnend(3, NULL, "(wimax_dev %p)\n", wimax_dev);
-}
-
-
-/*
- * wimax_get_netdev_by_info - lookup a wimax_dev from the gennetlink info
- *
- * The generic netlink family ID has been filled out in the
- * nlmsghdr->nlmsg_type field, so we pull it from there, look it up in
- * the mapping table and reference the wimax_dev.
- *
- * When done, the reference should be dropped with
- * 'dev_put(wimax_dev->net_dev)'.
- */
-struct wimax_dev *wimax_dev_get_by_genl_info(
-	struct genl_info *info, int ifindex)
-{
-	struct wimax_dev *wimax_dev = NULL;
-
-	d_fnstart(3, NULL, "(info %p ifindex %d)\n", info, ifindex);
-	spin_lock(&wimax_id_table_lock);
-	list_for_each_entry(wimax_dev, &wimax_id_table, id_table_node) {
-		if (wimax_dev->net_dev->ifindex == ifindex) {
-			dev_hold(wimax_dev->net_dev);
-			goto found;
-		}
-	}
-	wimax_dev = NULL;
-	d_printf(1, NULL, "wimax: no devices found with ifindex %d\n",
-		 ifindex);
-found:
-	spin_unlock(&wimax_id_table_lock);
-	d_fnend(3, NULL, "(info %p ifindex %d) = %p\n",
-		info, ifindex, wimax_dev);
-	return wimax_dev;
-}
-
-
-/*
- * wimax_id_table_rm - Remove a gennetlink familiy ID / wimax_dev mapping
- *
- * @id: family ID to remove from the table
- */
-void wimax_id_table_rm(struct wimax_dev *wimax_dev)
-{
-	spin_lock(&wimax_id_table_lock);
-	list_del_init(&wimax_dev->id_table_node);
-	spin_unlock(&wimax_id_table_lock);
-}
-
-
-/*
- * Release the gennetlink family id / mapping table
- *
- * On debug, verify that the table is empty upon removal. We want the
- * code always compiled, to ensure it doesn't bit rot. It will be
- * compiled out if CONFIG_BUG is disabled.
- */
-void wimax_id_table_release(void)
-{
-	struct wimax_dev *wimax_dev;
-
-#ifndef CONFIG_BUG
-	return;
-#endif
-	spin_lock(&wimax_id_table_lock);
-	list_for_each_entry(wimax_dev, &wimax_id_table, id_table_node) {
-		pr_err("BUG: %s wimax_dev %p ifindex %d not cleared\n",
-		       __func__, wimax_dev, wimax_dev->net_dev->ifindex);
-		WARN_ON(1);
-	}
-	spin_unlock(&wimax_id_table_lock);
-}
diff --git a/net/wimax/op-msg.c b/net/wimax/op-msg.c
deleted file mode 100644
index 6460b5785758..000000000000
--- a/net/wimax/op-msg.c
+++ /dev/null
@@ -1,391 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Linux WiMAX
- * Generic messaging interface between userspace and driver/device
- *
- * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * This implements a direct communication channel between user space and
- * the driver/device, by which free form messages can be sent back and
- * forth.
- *
- * This is intended for device-specific features, vendor quirks, etc.
- *
- * See include/net/wimax.h
- *
- * GENERIC NETLINK ENCODING AND CAPACITY
- *
- * A destination "pipe name" is added to each message; it is up to the
- * drivers to assign or use those names (if using them at all).
- *
- * Messages are encoded as a binary netlink attribute using nla_put()
- * using type NLA_UNSPEC (as some versions of libnl still in
- * deployment don't yet understand NLA_BINARY).
- *
- * The maximum capacity of this transport is PAGESIZE per message (so
- * the actual payload will be bit smaller depending on the
- * netlink/generic netlink attributes and headers).
- *
- * RECEPTION OF MESSAGES
- *
- * When a message is received from user space, it is passed verbatim
- * to the driver calling wimax_dev->op_msg_from_user(). The return
- * value from this function is passed back to user space as an ack
- * over the generic netlink protocol.
- *
- * The stack doesn't do any processing or interpretation of these
- * messages.
- *
- * SENDING MESSAGES
- *
- * Messages can be sent with wimax_msg().
- *
- * If the message delivery needs to happen on a different context to
- * that of its creation, wimax_msg_alloc() can be used to get a
- * pointer to the message that can be delivered later on with
- * wimax_msg_send().
- *
- * ROADMAP
- *
- * wimax_gnl_doit_msg_from_user()    Process a message from user space
- *   wimax_dev_get_by_genl_info()
- *   wimax_dev->op_msg_from_user()   Delivery of message to the driver
- *
- * wimax_msg()                       Send a message to user space
- *   wimax_msg_alloc()
- *   wimax_msg_send()
- */
-#include <linux/device.h>
-#include <linux/slab.h>
-#include <net/genetlink.h>
-#include <linux/netdevice.h>
-#include <linux/wimax.h>
-#include <linux/security.h>
-#include <linux/export.h>
-#include "wimax-internal.h"
-
-
-#define D_SUBMODULE op_msg
-#include "debug-levels.h"
-
-
-/**
- * wimax_msg_alloc - Create a new skb for sending a message to userspace
- *
- * @wimax_dev: WiMAX device descriptor
- * @pipe_name: "named pipe" the message will be sent to
- * @msg: pointer to the message data to send
- * @size: size of the message to send (in bytes), including the header.
- * @gfp_flags: flags for memory allocation.
- *
- * Returns: %0 if ok, negative errno code on error
- *
- * Description:
- *
- * Allocates an skb that will contain the message to send to user
- * space over the messaging pipe and initializes it, copying the
- * payload.
- *
- * Once this call is done, you can deliver it with
- * wimax_msg_send().
- *
- * IMPORTANT:
- *
- * Don't use skb_push()/skb_pull()/skb_reserve() on the skb, as
- * wimax_msg_send() depends on skb->data being placed at the
- * beginning of the user message.
- *
- * Unlike other WiMAX stack calls, this call can be used way early,
- * even before wimax_dev_add() is called, as long as the
- * wimax_dev->net_dev pointer is set to point to a proper
- * net_dev. This is so that drivers can use it early in case they need
- * to send stuff around or communicate with user space.
- */
-struct sk_buff *wimax_msg_alloc(struct wimax_dev *wimax_dev,
-				const char *pipe_name,
-				const void *msg, size_t size,
-				gfp_t gfp_flags)
-{
-	int result;
-	struct device *dev = wimax_dev_to_dev(wimax_dev);
-	size_t msg_size;
-	void *genl_msg;
-	struct sk_buff *skb;
-
-	msg_size = nla_total_size(size)
-		+ nla_total_size(sizeof(u32))
-		+ (pipe_name ? nla_total_size(strlen(pipe_name)) : 0);
-	result = -ENOMEM;
-	skb = genlmsg_new(msg_size, gfp_flags);
-	if (skb == NULL)
-		goto error_new;
-	genl_msg = genlmsg_put(skb, 0, 0, &wimax_gnl_family,
-			       0, WIMAX_GNL_OP_MSG_TO_USER);
-	if (genl_msg == NULL) {
-		dev_err(dev, "no memory to create generic netlink message\n");
-		goto error_genlmsg_put;
-	}
-	result = nla_put_u32(skb, WIMAX_GNL_MSG_IFIDX,
-			     wimax_dev->net_dev->ifindex);
-	if (result < 0) {
-		dev_err(dev, "no memory to add ifindex attribute\n");
-		goto error_nla_put;
-	}
-	if (pipe_name) {
-		result = nla_put_string(skb, WIMAX_GNL_MSG_PIPE_NAME,
-					pipe_name);
-		if (result < 0) {
-			dev_err(dev, "no memory to add pipe_name attribute\n");
-			goto error_nla_put;
-		}
-	}
-	result = nla_put(skb, WIMAX_GNL_MSG_DATA, size, msg);
-	if (result < 0) {
-		dev_err(dev, "no memory to add payload (msg %p size %zu) in "
-			"attribute: %d\n", msg, size, result);
-		goto error_nla_put;
-	}
-	genlmsg_end(skb, genl_msg);
-	return skb;
-
-error_nla_put:
-error_genlmsg_put:
-error_new:
-	nlmsg_free(skb);
-	return ERR_PTR(result);
-}
-EXPORT_SYMBOL_GPL(wimax_msg_alloc);
-
-
-/**
- * wimax_msg_data_len - Return a pointer and size of a message's payload
- *
- * @msg: Pointer to a message created with wimax_msg_alloc()
- * @size: Pointer to where to store the message's size
- *
- * Returns the pointer to the message data.
- */
-const void *wimax_msg_data_len(struct sk_buff *msg, size_t *size)
-{
-	struct nlmsghdr *nlh = (void *) msg->head;
-	struct nlattr *nla;
-
-	nla = nlmsg_find_attr(nlh, sizeof(struct genlmsghdr),
-			      WIMAX_GNL_MSG_DATA);
-	if (nla == NULL) {
-		pr_err("Cannot find attribute WIMAX_GNL_MSG_DATA\n");
-		return NULL;
-	}
-	*size = nla_len(nla);
-	return nla_data(nla);
-}
-EXPORT_SYMBOL_GPL(wimax_msg_data_len);
-
-
-/**
- * wimax_msg_data - Return a pointer to a message's payload
- *
- * @msg: Pointer to a message created with wimax_msg_alloc()
- */
-const void *wimax_msg_data(struct sk_buff *msg)
-{
-	struct nlmsghdr *nlh = (void *) msg->head;
-	struct nlattr *nla;
-
-	nla = nlmsg_find_attr(nlh, sizeof(struct genlmsghdr),
-			      WIMAX_GNL_MSG_DATA);
-	if (nla == NULL) {
-		pr_err("Cannot find attribute WIMAX_GNL_MSG_DATA\n");
-		return NULL;
-	}
-	return nla_data(nla);
-}
-EXPORT_SYMBOL_GPL(wimax_msg_data);
-
-
-/**
- * wimax_msg_len - Return a message's payload length
- *
- * @msg: Pointer to a message created with wimax_msg_alloc()
- */
-ssize_t wimax_msg_len(struct sk_buff *msg)
-{
-	struct nlmsghdr *nlh = (void *) msg->head;
-	struct nlattr *nla;
-
-	nla = nlmsg_find_attr(nlh, sizeof(struct genlmsghdr),
-			      WIMAX_GNL_MSG_DATA);
-	if (nla == NULL) {
-		pr_err("Cannot find attribute WIMAX_GNL_MSG_DATA\n");
-		return -EINVAL;
-	}
-	return nla_len(nla);
-}
-EXPORT_SYMBOL_GPL(wimax_msg_len);
-
-
-/**
- * wimax_msg_send - Send a pre-allocated message to user space
- *
- * @wimax_dev: WiMAX device descriptor
- *
- * @skb: &struct sk_buff returned by wimax_msg_alloc(). Note the
- *     ownership of @skb is transferred to this function.
- *
- * Returns: 0 if ok, < 0 errno code on error
- *
- * Description:
- *
- * Sends a free-form message that was preallocated with
- * wimax_msg_alloc() and filled up.
- *
- * Assumes that once you pass an skb to this function for sending, it
- * owns it and will release it when done (on success).
- *
- * IMPORTANT:
- *
- * Don't use skb_push()/skb_pull()/skb_reserve() on the skb, as
- * wimax_msg_send() depends on skb->data being placed at the
- * beginning of the user message.
- *
- * Unlike other WiMAX stack calls, this call can be used way early,
- * even before wimax_dev_add() is called, as long as the
- * wimax_dev->net_dev pointer is set to point to a proper
- * net_dev. This is so that drivers can use it early in case they need
- * to send stuff around or communicate with user space.
- */
-int wimax_msg_send(struct wimax_dev *wimax_dev, struct sk_buff *skb)
-{
-	struct device *dev = wimax_dev_to_dev(wimax_dev);
-	void *msg = skb->data;
-	size_t size = skb->len;
-	might_sleep();
-
-	d_printf(1, dev, "CTX: wimax msg, %zu bytes\n", size);
-	d_dump(2, dev, msg, size);
-	genlmsg_multicast(&wimax_gnl_family, skb, 0, 0, GFP_KERNEL);
-	d_printf(1, dev, "CTX: genl multicast done\n");
-	return 0;
-}
-EXPORT_SYMBOL_GPL(wimax_msg_send);
-
-
-/**
- * wimax_msg - Send a message to user space
- *
- * @wimax_dev: WiMAX device descriptor (properly referenced)
- * @pipe_name: "named pipe" the message will be sent to
- * @buf: pointer to the message to send.
- * @size: size of the buffer pointed to by @buf (in bytes).
- * @gfp_flags: flags for memory allocation.
- *
- * Returns: %0 if ok, negative errno code on error.
- *
- * Description:
- *
- * Sends a free-form message to user space on the device @wimax_dev.
- *
- * NOTES:
- *
- * Once the @skb is given to this function, who will own it and will
- * release it when done (unless it returns error).
- */
-int wimax_msg(struct wimax_dev *wimax_dev, const char *pipe_name,
-	      const void *buf, size_t size, gfp_t gfp_flags)
-{
-	int result = -ENOMEM;
-	struct sk_buff *skb;
-
-	skb = wimax_msg_alloc(wimax_dev, pipe_name, buf, size, gfp_flags);
-	if (IS_ERR(skb))
-		result = PTR_ERR(skb);
-	else
-		result = wimax_msg_send(wimax_dev, skb);
-	return result;
-}
-EXPORT_SYMBOL_GPL(wimax_msg);
-
-/*
- * Relays a message from user space to the driver
- *
- * The skb is passed to the driver-specific function with the netlink
- * and generic netlink headers already stripped.
- *
- * This call will block while handling/relaying the message.
- */
-int wimax_gnl_doit_msg_from_user(struct sk_buff *skb, struct genl_info *info)
-{
-	int result, ifindex;
-	struct wimax_dev *wimax_dev;
-	struct device *dev;
-	struct nlmsghdr *nlh = info->nlhdr;
-	char *pipe_name;
-	void *msg_buf;
-	size_t msg_len;
-
-	might_sleep();
-	d_fnstart(3, NULL, "(skb %p info %p)\n", skb, info);
-	result = -ENODEV;
-	if (info->attrs[WIMAX_GNL_MSG_IFIDX] == NULL) {
-		pr_err("WIMAX_GNL_MSG_FROM_USER: can't find IFIDX attribute\n");
-		goto error_no_wimax_dev;
-	}
-	ifindex = nla_get_u32(info->attrs[WIMAX_GNL_MSG_IFIDX]);
-	wimax_dev = wimax_dev_get_by_genl_info(info, ifindex);
-	if (wimax_dev == NULL)
-		goto error_no_wimax_dev;
-	dev = wimax_dev_to_dev(wimax_dev);
-
-	/* Unpack arguments */
-	result = -EINVAL;
-	if (info->attrs[WIMAX_GNL_MSG_DATA] == NULL) {
-		dev_err(dev, "WIMAX_GNL_MSG_FROM_USER: can't find MSG_DATA "
-			"attribute\n");
-		goto error_no_data;
-	}
-	msg_buf = nla_data(info->attrs[WIMAX_GNL_MSG_DATA]);
-	msg_len = nla_len(info->attrs[WIMAX_GNL_MSG_DATA]);
-
-	if (info->attrs[WIMAX_GNL_MSG_PIPE_NAME] == NULL)
-		pipe_name = NULL;
-	else {
-		struct nlattr *attr = info->attrs[WIMAX_GNL_MSG_PIPE_NAME];
-		size_t attr_len = nla_len(attr);
-		/* libnl-1.1 does not yet support NLA_NUL_STRING */
-		result = -ENOMEM;
-		pipe_name = kstrndup(nla_data(attr), attr_len + 1, GFP_KERNEL);
-		if (pipe_name == NULL)
-			goto error_alloc;
-		pipe_name[attr_len] = 0;
-	}
-	mutex_lock(&wimax_dev->mutex);
-	result = wimax_dev_is_ready(wimax_dev);
-	if (result == -ENOMEDIUM)
-		result = 0;
-	if (result < 0)
-		goto error_not_ready;
-	result = -ENOSYS;
-	if (wimax_dev->op_msg_from_user == NULL)
-		goto error_noop;
-
-	d_printf(1, dev,
-		 "CRX: nlmsghdr len %u type %u flags 0x%04x seq 0x%x pid %u\n",
-		 nlh->nlmsg_len, nlh->nlmsg_type, nlh->nlmsg_flags,
-		 nlh->nlmsg_seq, nlh->nlmsg_pid);
-	d_printf(1, dev, "CRX: wimax message %zu bytes\n", msg_len);
-	d_dump(2, dev, msg_buf, msg_len);
-
-	result = wimax_dev->op_msg_from_user(wimax_dev, pipe_name,
-					     msg_buf, msg_len, info);
-error_noop:
-error_not_ready:
-	mutex_unlock(&wimax_dev->mutex);
-error_alloc:
-	kfree(pipe_name);
-error_no_data:
-	dev_put(wimax_dev->net_dev);
-error_no_wimax_dev:
-	d_fnend(3, NULL, "(skb %p info %p) = %d\n", skb, info, result);
-	return result;
-}
diff --git a/net/wimax/op-reset.c b/net/wimax/op-reset.c
deleted file mode 100644
index 9899b2e56721..000000000000
--- a/net/wimax/op-reset.c
+++ /dev/null
@@ -1,108 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Linux WiMAX
- * Implement and export a method for resetting a WiMAX device
- *
- * Copyright (C) 2008 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * This implements a simple synchronous call to reset a WiMAX device.
- *
- * Resets aim at being warm, keeping the device handles active;
- * however, when that fails, it falls back to a cold reset (that will
- * disconnect and reconnect the device).
- */
-
-#include <net/wimax.h>
-#include <net/genetlink.h>
-#include <linux/wimax.h>
-#include <linux/security.h>
-#include <linux/export.h>
-#include "wimax-internal.h"
-
-#define D_SUBMODULE op_reset
-#include "debug-levels.h"
-
-
-/**
- * wimax_reset - Reset a WiMAX device
- *
- * @wimax_dev: WiMAX device descriptor
- *
- * Returns:
- *
- * %0 if ok and a warm reset was done (the device still exists in
- * the system).
- *
- * -%ENODEV if a cold/bus reset had to be done (device has
- * disconnected and reconnected, so current handle is not valid
- * any more).
- *
- * -%EINVAL if the device is not even registered.
- *
- * Any other negative error code shall be considered as
- * non-recoverable.
- *
- * Description:
- *
- * Called when wanting to reset the device for any reason. Device is
- * taken back to power on status.
- *
- * This call blocks; on successful return, the device has completed the
- * reset process and is ready to operate.
- */
-int wimax_reset(struct wimax_dev *wimax_dev)
-{
-	int result = -EINVAL;
-	struct device *dev = wimax_dev_to_dev(wimax_dev);
-	enum wimax_st state;
-
-	might_sleep();
-	d_fnstart(3, dev, "(wimax_dev %p)\n", wimax_dev);
-	mutex_lock(&wimax_dev->mutex);
-	dev_hold(wimax_dev->net_dev);
-	state = wimax_dev->state;
-	mutex_unlock(&wimax_dev->mutex);
-
-	if (state >= WIMAX_ST_DOWN) {
-		mutex_lock(&wimax_dev->mutex_reset);
-		result = wimax_dev->op_reset(wimax_dev);
-		mutex_unlock(&wimax_dev->mutex_reset);
-	}
-	dev_put(wimax_dev->net_dev);
-
-	d_fnend(3, dev, "(wimax_dev %p) = %d\n", wimax_dev, result);
-	return result;
-}
-EXPORT_SYMBOL(wimax_reset);
-
-
-/*
- * Exporting to user space over generic netlink
- *
- * Parse the reset command from user space, return error code.
- *
- * No attributes.
- */
-int wimax_gnl_doit_reset(struct sk_buff *skb, struct genl_info *info)
-{
-	int result, ifindex;
-	struct wimax_dev *wimax_dev;
-
-	d_fnstart(3, NULL, "(skb %p info %p)\n", skb, info);
-	result = -ENODEV;
-	if (info->attrs[WIMAX_GNL_RESET_IFIDX] == NULL) {
-		pr_err("WIMAX_GNL_OP_RFKILL: can't find IFIDX attribute\n");
-		goto error_no_wimax_dev;
-	}
-	ifindex = nla_get_u32(info->attrs[WIMAX_GNL_RESET_IFIDX]);
-	wimax_dev = wimax_dev_get_by_genl_info(info, ifindex);
-	if (wimax_dev == NULL)
-		goto error_no_wimax_dev;
-	/* Execute the operation and send the result back to user space */
-	result = wimax_reset(wimax_dev);
-	dev_put(wimax_dev->net_dev);
-error_no_wimax_dev:
-	d_fnend(3, NULL, "(skb %p info %p) = %d\n", skb, info, result);
-	return result;
-}
diff --git a/net/wimax/op-rfkill.c b/net/wimax/op-rfkill.c
deleted file mode 100644
index 248d10b60b05..000000000000
--- a/net/wimax/op-rfkill.c
+++ /dev/null
@@ -1,431 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Linux WiMAX
- * RF-kill framework integration
- *
- * Copyright (C) 2008 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * This integrates into the Linux Kernel rfkill susbystem so that the
- * drivers just have to do the bare minimal work, which is providing a
- * method to set the software RF-Kill switch and to report changes in
- * the software and hardware switch status.
- *
- * A non-polled generic rfkill device is embedded into the WiMAX
- * subsystem's representation of a device.
- *
- * FIXME: Need polled support? Let drivers provide a poll routine
- *	  and hand it to rfkill ops then?
- *
- * All device drivers have to do is after wimax_dev_init(), call
- * wimax_report_rfkill_hw() and wimax_report_rfkill_sw() to update
- * initial state and then every time it changes. See wimax.h:struct
- * wimax_dev for more information.
- *
- * ROADMAP
- *
- * wimax_gnl_doit_rfkill()      User space calling wimax_rfkill()
- *   wimax_rfkill()             Kernel calling wimax_rfkill()
- *     __wimax_rf_toggle_radio()
- *
- * wimax_rfkill_set_radio_block()  RF-Kill subsystem calling
- *   __wimax_rf_toggle_radio()
- *
- * __wimax_rf_toggle_radio()
- *   wimax_dev->op_rfkill_sw_toggle() Driver backend
- *   __wimax_state_change()
- *
- * wimax_report_rfkill_sw()     Driver reports state change
- *   __wimax_state_change()
- *
- * wimax_report_rfkill_hw()     Driver reports state change
- *   __wimax_state_change()
- *
- * wimax_rfkill_add()           Initialize/shutdown rfkill support
- * wimax_rfkill_rm()            [called by wimax_dev_add/rm()]
- */
-
-#include <net/wimax.h>
-#include <net/genetlink.h>
-#include <linux/wimax.h>
-#include <linux/security.h>
-#include <linux/rfkill.h>
-#include <linux/export.h>
-#include "wimax-internal.h"
-
-#define D_SUBMODULE op_rfkill
-#include "debug-levels.h"
-
-/**
- * wimax_report_rfkill_hw - Reports changes in the hardware RF switch
- *
- * @wimax_dev: WiMAX device descriptor
- *
- * @state: New state of the RF Kill switch. %WIMAX_RF_ON radio on,
- *     %WIMAX_RF_OFF radio off.
- *
- * When the device detects a change in the state of thehardware RF
- * switch, it must call this function to let the WiMAX kernel stack
- * know that the state has changed so it can be properly propagated.
- *
- * The WiMAX stack caches the state (the driver doesn't need to). As
- * well, as the change is propagated it will come back as a request to
- * change the software state to mirror the hardware state.
- *
- * If the device doesn't have a hardware kill switch, just report
- * it on initialization as always on (%WIMAX_RF_ON, radio on).
- */
-void wimax_report_rfkill_hw(struct wimax_dev *wimax_dev,
-			    enum wimax_rf_state state)
-{
-	int result;
-	struct device *dev = wimax_dev_to_dev(wimax_dev);
-	enum wimax_st wimax_state;
-
-	d_fnstart(3, dev, "(wimax_dev %p state %u)\n", wimax_dev, state);
-	BUG_ON(state == WIMAX_RF_QUERY);
-	BUG_ON(state != WIMAX_RF_ON && state != WIMAX_RF_OFF);
-
-	mutex_lock(&wimax_dev->mutex);
-	result = wimax_dev_is_ready(wimax_dev);
-	if (result < 0)
-		goto error_not_ready;
-
-	if (state != wimax_dev->rf_hw) {
-		wimax_dev->rf_hw = state;
-		if (wimax_dev->rf_hw == WIMAX_RF_ON &&
-		    wimax_dev->rf_sw == WIMAX_RF_ON)
-			wimax_state = WIMAX_ST_READY;
-		else
-			wimax_state = WIMAX_ST_RADIO_OFF;
-
-		result = rfkill_set_hw_state(wimax_dev->rfkill,
-					     state == WIMAX_RF_OFF);
-
-		__wimax_state_change(wimax_dev, wimax_state);
-	}
-error_not_ready:
-	mutex_unlock(&wimax_dev->mutex);
-	d_fnend(3, dev, "(wimax_dev %p state %u) = void [%d]\n",
-		wimax_dev, state, result);
-}
-EXPORT_SYMBOL_GPL(wimax_report_rfkill_hw);
-
-
-/**
- * wimax_report_rfkill_sw - Reports changes in the software RF switch
- *
- * @wimax_dev: WiMAX device descriptor
- *
- * @state: New state of the RF kill switch. %WIMAX_RF_ON radio on,
- *     %WIMAX_RF_OFF radio off.
- *
- * Reports changes in the software RF switch state to the WiMAX stack.
- *
- * The main use is during initialization, so the driver can query the
- * device for its current software radio kill switch state and feed it
- * to the system.
- *
- * On the side, the device does not change the software state by
- * itself. In practice, this can happen, as the device might decide to
- * switch (in software) the radio off for different reasons.
- */
-void wimax_report_rfkill_sw(struct wimax_dev *wimax_dev,
-			    enum wimax_rf_state state)
-{
-	int result;
-	struct device *dev = wimax_dev_to_dev(wimax_dev);
-	enum wimax_st wimax_state;
-
-	d_fnstart(3, dev, "(wimax_dev %p state %u)\n", wimax_dev, state);
-	BUG_ON(state == WIMAX_RF_QUERY);
-	BUG_ON(state != WIMAX_RF_ON && state != WIMAX_RF_OFF);
-
-	mutex_lock(&wimax_dev->mutex);
-	result = wimax_dev_is_ready(wimax_dev);
-	if (result < 0)
-		goto error_not_ready;
-
-	if (state != wimax_dev->rf_sw) {
-		wimax_dev->rf_sw = state;
-		if (wimax_dev->rf_hw == WIMAX_RF_ON &&
-		    wimax_dev->rf_sw == WIMAX_RF_ON)
-			wimax_state = WIMAX_ST_READY;
-		else
-			wimax_state = WIMAX_ST_RADIO_OFF;
-		__wimax_state_change(wimax_dev, wimax_state);
-		rfkill_set_sw_state(wimax_dev->rfkill, state == WIMAX_RF_OFF);
-	}
-error_not_ready:
-	mutex_unlock(&wimax_dev->mutex);
-	d_fnend(3, dev, "(wimax_dev %p state %u) = void [%d]\n",
-		wimax_dev, state, result);
-}
-EXPORT_SYMBOL_GPL(wimax_report_rfkill_sw);
-
-
-/*
- * Callback for the RF Kill toggle operation
- *
- * This function is called by:
- *
- * - The rfkill subsystem when the RF-Kill key is pressed in the
- *   hardware and the driver notifies through
- *   wimax_report_rfkill_hw(). The rfkill subsystem ends up calling back
- *   here so the software RF Kill switch state is changed to reflect
- *   the hardware switch state.
- *
- * - When the user sets the state through sysfs' rfkill/state file
- *
- * - When the user calls wimax_rfkill().
- *
- * This call blocks!
- *
- * WARNING! When we call rfkill_unregister(), this will be called with
- * state 0!
- *
- * WARNING: wimax_dev must be locked
- */
-static
-int __wimax_rf_toggle_radio(struct wimax_dev *wimax_dev,
-			    enum wimax_rf_state state)
-{
-	int result = 0;
-	struct device *dev = wimax_dev_to_dev(wimax_dev);
-	enum wimax_st wimax_state;
-
-	might_sleep();
-	d_fnstart(3, dev, "(wimax_dev %p state %u)\n", wimax_dev, state);
-	if (wimax_dev->rf_sw == state)
-		goto out_no_change;
-	if (wimax_dev->op_rfkill_sw_toggle != NULL)
-		result = wimax_dev->op_rfkill_sw_toggle(wimax_dev, state);
-	else if (state == WIMAX_RF_OFF)	/* No op? can't turn off */
-		result = -ENXIO;
-	else				/* No op? can turn on */
-		result = 0;		/* should never happen tho */
-	if (result >= 0) {
-		result = 0;
-		wimax_dev->rf_sw = state;
-		wimax_state = state == WIMAX_RF_ON ?
-			WIMAX_ST_READY : WIMAX_ST_RADIO_OFF;
-		__wimax_state_change(wimax_dev, wimax_state);
-	}
-out_no_change:
-	d_fnend(3, dev, "(wimax_dev %p state %u) = %d\n",
-		wimax_dev, state, result);
-	return result;
-}
-
-
-/*
- * Translate from rfkill state to wimax state
- *
- * NOTE: Special state handling rules here
- *
- *     Just pretend the call didn't happen if we are in a state where
- *     we know for sure it cannot be handled (WIMAX_ST_DOWN or
- *     __WIMAX_ST_QUIESCING). rfkill() needs it to register and
- *     unregister, as it will run this path.
- *
- * NOTE: This call will block until the operation is completed.
- */
-static int wimax_rfkill_set_radio_block(void *data, bool blocked)
-{
-	int result;
-	struct wimax_dev *wimax_dev = data;
-	struct device *dev = wimax_dev_to_dev(wimax_dev);
-	enum wimax_rf_state rf_state;
-
-	d_fnstart(3, dev, "(wimax_dev %p blocked %u)\n", wimax_dev, blocked);
-	rf_state = WIMAX_RF_ON;
-	if (blocked)
-		rf_state = WIMAX_RF_OFF;
-	mutex_lock(&wimax_dev->mutex);
-	if (wimax_dev->state <= __WIMAX_ST_QUIESCING)
-		result = 0;
-	else
-		result = __wimax_rf_toggle_radio(wimax_dev, rf_state);
-	mutex_unlock(&wimax_dev->mutex);
-	d_fnend(3, dev, "(wimax_dev %p blocked %u) = %d\n",
-		wimax_dev, blocked, result);
-	return result;
-}
-
-static const struct rfkill_ops wimax_rfkill_ops = {
-	.set_block = wimax_rfkill_set_radio_block,
-};
-
-/**
- * wimax_rfkill - Set the software RF switch state for a WiMAX device
- *
- * @wimax_dev: WiMAX device descriptor
- *
- * @state: New RF state.
- *
- * Returns:
- *
- * >= 0 toggle state if ok, < 0 errno code on error. The toggle state
- * is returned as a bitmap, bit 0 being the hardware RF state, bit 1
- * the software RF state.
- *
- * 0 means disabled (%WIMAX_RF_ON, radio on), 1 means enabled radio
- * off (%WIMAX_RF_OFF).
- *
- * Description:
- *
- * Called by the user when he wants to request the WiMAX radio to be
- * switched on (%WIMAX_RF_ON) or off (%WIMAX_RF_OFF). With
- * %WIMAX_RF_QUERY, just the current state is returned.
- *
- * NOTE:
- *
- * This call will block until the operation is complete.
- */
-int wimax_rfkill(struct wimax_dev *wimax_dev, enum wimax_rf_state state)
-{
-	int result;
-	struct device *dev = wimax_dev_to_dev(wimax_dev);
-
-	d_fnstart(3, dev, "(wimax_dev %p state %u)\n", wimax_dev, state);
-	mutex_lock(&wimax_dev->mutex);
-	result = wimax_dev_is_ready(wimax_dev);
-	if (result < 0) {
-		/* While initializing, < 1.4.3 wimax-tools versions use
-		 * this call to check if the device is a valid WiMAX
-		 * device; so we allow it to proceed always,
-		 * considering the radios are all off. */
-		if (result == -ENOMEDIUM && state == WIMAX_RF_QUERY)
-			result = WIMAX_RF_OFF << 1 | WIMAX_RF_OFF;
-		goto error_not_ready;
-	}
-	switch (state) {
-	case WIMAX_RF_ON:
-	case WIMAX_RF_OFF:
-		result = __wimax_rf_toggle_radio(wimax_dev, state);
-		if (result < 0)
-			goto error;
-		rfkill_set_sw_state(wimax_dev->rfkill, state == WIMAX_RF_OFF);
-		break;
-	case WIMAX_RF_QUERY:
-		break;
-	default:
-		result = -EINVAL;
-		goto error;
-	}
-	result = wimax_dev->rf_sw << 1 | wimax_dev->rf_hw;
-error:
-error_not_ready:
-	mutex_unlock(&wimax_dev->mutex);
-	d_fnend(3, dev, "(wimax_dev %p state %u) = %d\n",
-		wimax_dev, state, result);
-	return result;
-}
-EXPORT_SYMBOL(wimax_rfkill);
-
-
-/*
- * Register a new WiMAX device's RF Kill support
- *
- * WARNING: wimax_dev->mutex must be unlocked
- */
-int wimax_rfkill_add(struct wimax_dev *wimax_dev)
-{
-	int result;
-	struct rfkill *rfkill;
-	struct device *dev = wimax_dev_to_dev(wimax_dev);
-
-	d_fnstart(3, dev, "(wimax_dev %p)\n", wimax_dev);
-	/* Initialize RF Kill */
-	result = -ENOMEM;
-	rfkill = rfkill_alloc(wimax_dev->name, dev, RFKILL_TYPE_WIMAX,
-			      &wimax_rfkill_ops, wimax_dev);
-	if (rfkill == NULL)
-		goto error_rfkill_allocate;
-
-	d_printf(1, dev, "rfkill %p\n", rfkill);
-
-	wimax_dev->rfkill = rfkill;
-
-	rfkill_init_sw_state(rfkill, 1);
-	result = rfkill_register(wimax_dev->rfkill);
-	if (result < 0)
-		goto error_rfkill_register;
-
-	/* If there is no SW toggle op, SW RFKill is always on */
-	if (wimax_dev->op_rfkill_sw_toggle == NULL)
-		wimax_dev->rf_sw = WIMAX_RF_ON;
-
-	d_fnend(3, dev, "(wimax_dev %p) = 0\n", wimax_dev);
-	return 0;
-
-error_rfkill_register:
-	rfkill_destroy(wimax_dev->rfkill);
-error_rfkill_allocate:
-	d_fnend(3, dev, "(wimax_dev %p) = %d\n", wimax_dev, result);
-	return result;
-}
-
-
-/*
- * Deregister a WiMAX device's RF Kill support
- *
- * Ick, we can't call rfkill_free() after rfkill_unregister()...oh
- * well.
- *
- * WARNING: wimax_dev->mutex must be unlocked
- */
-void wimax_rfkill_rm(struct wimax_dev *wimax_dev)
-{
-	struct device *dev = wimax_dev_to_dev(wimax_dev);
-	d_fnstart(3, dev, "(wimax_dev %p)\n", wimax_dev);
-	rfkill_unregister(wimax_dev->rfkill);
-	rfkill_destroy(wimax_dev->rfkill);
-	d_fnend(3, dev, "(wimax_dev %p)\n", wimax_dev);
-}
-
-
-/*
- * Exporting to user space over generic netlink
- *
- * Parse the rfkill command from user space, return a combination
- * value that describe the states of the different toggles.
- *
- * Only one attribute: the new state requested (on, off or no change,
- * just query).
- */
-
-int wimax_gnl_doit_rfkill(struct sk_buff *skb, struct genl_info *info)
-{
-	int result, ifindex;
-	struct wimax_dev *wimax_dev;
-	struct device *dev;
-	enum wimax_rf_state new_state;
-
-	d_fnstart(3, NULL, "(skb %p info %p)\n", skb, info);
-	result = -ENODEV;
-	if (info->attrs[WIMAX_GNL_RFKILL_IFIDX] == NULL) {
-		pr_err("WIMAX_GNL_OP_RFKILL: can't find IFIDX attribute\n");
-		goto error_no_wimax_dev;
-	}
-	ifindex = nla_get_u32(info->attrs[WIMAX_GNL_RFKILL_IFIDX]);
-	wimax_dev = wimax_dev_get_by_genl_info(info, ifindex);
-	if (wimax_dev == NULL)
-		goto error_no_wimax_dev;
-	dev = wimax_dev_to_dev(wimax_dev);
-	result = -EINVAL;
-	if (info->attrs[WIMAX_GNL_RFKILL_STATE] == NULL) {
-		dev_err(dev, "WIMAX_GNL_RFKILL: can't find RFKILL_STATE "
-			"attribute\n");
-		goto error_no_pid;
-	}
-	new_state = nla_get_u32(info->attrs[WIMAX_GNL_RFKILL_STATE]);
-
-	/* Execute the operation and send the result back to user space */
-	result = wimax_rfkill(wimax_dev, new_state);
-error_no_pid:
-	dev_put(wimax_dev->net_dev);
-error_no_wimax_dev:
-	d_fnend(3, NULL, "(skb %p info %p) = %d\n", skb, info, result);
-	return result;
-}
diff --git a/net/wimax/op-state-get.c b/net/wimax/op-state-get.c
deleted file mode 100644
index 5bc712de1563..000000000000
--- a/net/wimax/op-state-get.c
+++ /dev/null
@@ -1,52 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Linux WiMAX
- * Implement and export a method for getting a WiMAX device current state
- *
- * Copyright (C) 2009 Paulius Zaleckas <paulius.zaleckas@teltonika.lt>
- *
- * Based on previous WiMAX core work by:
- *  Copyright (C) 2008 Intel Corporation <linux-wimax@intel.com>
- *  Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- */
-
-#include <net/wimax.h>
-#include <net/genetlink.h>
-#include <linux/wimax.h>
-#include <linux/security.h>
-#include "wimax-internal.h"
-
-#define D_SUBMODULE op_state_get
-#include "debug-levels.h"
-
-
-/*
- * Exporting to user space over generic netlink
- *
- * Parse the state get command from user space, return a combination
- * value that describe the current state.
- *
- * No attributes.
- */
-int wimax_gnl_doit_state_get(struct sk_buff *skb, struct genl_info *info)
-{
-	int result, ifindex;
-	struct wimax_dev *wimax_dev;
-
-	d_fnstart(3, NULL, "(skb %p info %p)\n", skb, info);
-	result = -ENODEV;
-	if (info->attrs[WIMAX_GNL_STGET_IFIDX] == NULL) {
-		pr_err("WIMAX_GNL_OP_STATE_GET: can't find IFIDX attribute\n");
-		goto error_no_wimax_dev;
-	}
-	ifindex = nla_get_u32(info->attrs[WIMAX_GNL_STGET_IFIDX]);
-	wimax_dev = wimax_dev_get_by_genl_info(info, ifindex);
-	if (wimax_dev == NULL)
-		goto error_no_wimax_dev;
-	/* Execute the operation and send the result back to user space */
-	result = wimax_state_get(wimax_dev);
-	dev_put(wimax_dev->net_dev);
-error_no_wimax_dev:
-	d_fnend(3, NULL, "(skb %p info %p) = %d\n", skb, info, result);
-	return result;
-}
diff --git a/net/wimax/stack.c b/net/wimax/stack.c
deleted file mode 100644
index 3a62af3f80bf..000000000000
--- a/net/wimax/stack.c
+++ /dev/null
@@ -1,616 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Linux WiMAX
- * Initialization, addition and removal of wimax devices
- *
- * Copyright (C) 2005-2006 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * This implements:
- *
- *   - basic life cycle of 'struct wimax_dev' [wimax_dev_*()]; on
- *     addition/registration initialize all subfields and allocate
- *     generic netlink resources for user space communication. On
- *     removal/unregistration, undo all that.
- *
- *   - device state machine [wimax_state_change()] and support to send
- *     reports to user space when the state changes
- *     [wimax_gnl_re_state_change*()].
- *
- * See include/net/wimax.h for rationales and design.
- *
- * ROADMAP
- *
- * [__]wimax_state_change()     Called by drivers to update device's state
- *   wimax_gnl_re_state_change_alloc()
- *   wimax_gnl_re_state_change_send()
- *
- * wimax_dev_init()	        Init a device
- * wimax_dev_add()              Register
- *   wimax_rfkill_add()
- *   wimax_gnl_add()            Register all the generic netlink resources.
- *   wimax_id_table_add()
- * wimax_dev_rm()               Unregister
- *   wimax_id_table_rm()
- *   wimax_gnl_rm()
- *   wimax_rfkill_rm()
- */
-#include <linux/device.h>
-#include <linux/gfp.h>
-#include <net/genetlink.h>
-#include <linux/netdevice.h>
-#include <linux/wimax.h>
-#include <linux/module.h>
-#include "wimax-internal.h"
-
-
-#define D_SUBMODULE stack
-#include "debug-levels.h"
-
-static char wimax_debug_params[128];
-module_param_string(debug, wimax_debug_params, sizeof(wimax_debug_params),
-		    0644);
-MODULE_PARM_DESC(debug,
-		 "String of space-separated NAME:VALUE pairs, where NAMEs "
-		 "are the different debug submodules and VALUE are the "
-		 "initial debug value to set.");
-
-/*
- * Authoritative source for the RE_STATE_CHANGE attribute policy
- *
- * We don't really use it here, but /me likes to keep the definition
- * close to where the data is generated.
- */
-/*
-static const struct nla_policy wimax_gnl_re_status_change[WIMAX_GNL_ATTR_MAX + 1] = {
-	[WIMAX_GNL_STCH_STATE_OLD] = { .type = NLA_U8 },
-	[WIMAX_GNL_STCH_STATE_NEW] = { .type = NLA_U8 },
-};
-*/
-
-
-/*
- * Allocate a Report State Change message
- *
- * @header: save it, you need it for _send()
- *
- * Creates and fills a basic state change message; different code
- * paths can then add more attributes to the message as needed.
- *
- * Use wimax_gnl_re_state_change_send() to send the returned skb.
- *
- * Returns: skb with the genl message if ok, IS_ERR() ptr on error
- *     with an errno code.
- */
-static
-struct sk_buff *wimax_gnl_re_state_change_alloc(
-	struct wimax_dev *wimax_dev,
-	enum wimax_st new_state, enum wimax_st old_state,
-	void **header)
-{
-	int result;
-	struct device *dev = wimax_dev_to_dev(wimax_dev);
-	void *data;
-	struct sk_buff *report_skb;
-
-	d_fnstart(3, dev, "(wimax_dev %p new_state %u old_state %u)\n",
-		  wimax_dev, new_state, old_state);
-	result = -ENOMEM;
-	report_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (report_skb == NULL) {
-		dev_err(dev, "RE_STCH: can't create message\n");
-		goto error_new;
-	}
-	/* FIXME: sending a group ID as the seq is wrong */
-	data = genlmsg_put(report_skb, 0, wimax_gnl_family.mcgrp_offset,
-			   &wimax_gnl_family, 0, WIMAX_GNL_RE_STATE_CHANGE);
-	if (data == NULL) {
-		dev_err(dev, "RE_STCH: can't put data into message\n");
-		goto error_put;
-	}
-	*header = data;
-
-	result = nla_put_u8(report_skb, WIMAX_GNL_STCH_STATE_OLD, old_state);
-	if (result < 0) {
-		dev_err(dev, "RE_STCH: Error adding OLD attr: %d\n", result);
-		goto error_put;
-	}
-	result = nla_put_u8(report_skb, WIMAX_GNL_STCH_STATE_NEW, new_state);
-	if (result < 0) {
-		dev_err(dev, "RE_STCH: Error adding NEW attr: %d\n", result);
-		goto error_put;
-	}
-	result = nla_put_u32(report_skb, WIMAX_GNL_STCH_IFIDX,
-			     wimax_dev->net_dev->ifindex);
-	if (result < 0) {
-		dev_err(dev, "RE_STCH: Error adding IFINDEX attribute\n");
-		goto error_put;
-	}
-	d_fnend(3, dev, "(wimax_dev %p new_state %u old_state %u) = %p\n",
-		wimax_dev, new_state, old_state, report_skb);
-	return report_skb;
-
-error_put:
-	nlmsg_free(report_skb);
-error_new:
-	d_fnend(3, dev, "(wimax_dev %p new_state %u old_state %u) = %d\n",
-		wimax_dev, new_state, old_state, result);
-	return ERR_PTR(result);
-}
-
-
-/*
- * Send a Report State Change message (as created with _alloc).
- *
- * @report_skb: as returned by wimax_gnl_re_state_change_alloc()
- * @header: as returned by wimax_gnl_re_state_change_alloc()
- *
- * Returns: 0 if ok, < 0 errno code on error.
- *
- * If the message is  NULL, pretend it didn't happen.
- */
-static
-int wimax_gnl_re_state_change_send(
-	struct wimax_dev *wimax_dev, struct sk_buff *report_skb,
-	void *header)
-{
-	int result = 0;
-	struct device *dev = wimax_dev_to_dev(wimax_dev);
-	d_fnstart(3, dev, "(wimax_dev %p report_skb %p)\n",
-		  wimax_dev, report_skb);
-	if (report_skb == NULL) {
-		result = -ENOMEM;
-		goto out;
-	}
-	genlmsg_end(report_skb, header);
-	genlmsg_multicast(&wimax_gnl_family, report_skb, 0, 0, GFP_KERNEL);
-out:
-	d_fnend(3, dev, "(wimax_dev %p report_skb %p) = %d\n",
-		wimax_dev, report_skb, result);
-	return result;
-}
-
-
-static
-void __check_new_state(enum wimax_st old_state, enum wimax_st new_state,
-		       unsigned int allowed_states_bm)
-{
-	if (WARN_ON(((1 << new_state) & allowed_states_bm) == 0)) {
-		pr_err("SW BUG! Forbidden state change %u -> %u\n",
-		       old_state, new_state);
-	}
-}
-
-
-/*
- * Set the current state of a WiMAX device [unlocking version of
- * wimax_state_change().
- */
-void __wimax_state_change(struct wimax_dev *wimax_dev, enum wimax_st new_state)
-{
-	struct device *dev = wimax_dev_to_dev(wimax_dev);
-	enum wimax_st old_state = wimax_dev->state;
-	struct sk_buff *stch_skb;
-	void *header;
-
-	d_fnstart(3, dev, "(wimax_dev %p new_state %u [old %u])\n",
-		  wimax_dev, new_state, old_state);
-
-	if (WARN_ON(new_state >= __WIMAX_ST_INVALID)) {
-		dev_err(dev, "SW BUG: requesting invalid state %u\n",
-			new_state);
-		goto out;
-	}
-	if (old_state == new_state)
-		goto out;
-	header = NULL;	/* gcc complains? can't grok why */
-	stch_skb = wimax_gnl_re_state_change_alloc(
-		wimax_dev, new_state, old_state, &header);
-
-	/* Verify the state transition and do exit-from-state actions */
-	switch (old_state) {
-	case __WIMAX_ST_NULL:
-		__check_new_state(old_state, new_state,
-				  1 << WIMAX_ST_DOWN);
-		break;
-	case WIMAX_ST_DOWN:
-		__check_new_state(old_state, new_state,
-				  1 << __WIMAX_ST_QUIESCING
-				  | 1 << WIMAX_ST_UNINITIALIZED
-				  | 1 << WIMAX_ST_RADIO_OFF);
-		break;
-	case __WIMAX_ST_QUIESCING:
-		__check_new_state(old_state, new_state, 1 << WIMAX_ST_DOWN);
-		break;
-	case WIMAX_ST_UNINITIALIZED:
-		__check_new_state(old_state, new_state,
-				  1 << __WIMAX_ST_QUIESCING
-				  | 1 << WIMAX_ST_RADIO_OFF);
-		break;
-	case WIMAX_ST_RADIO_OFF:
-		__check_new_state(old_state, new_state,
-				  1 << __WIMAX_ST_QUIESCING
-				  | 1 << WIMAX_ST_READY);
-		break;
-	case WIMAX_ST_READY:
-		__check_new_state(old_state, new_state,
-				  1 << __WIMAX_ST_QUIESCING
-				  | 1 << WIMAX_ST_RADIO_OFF
-				  | 1 << WIMAX_ST_SCANNING
-				  | 1 << WIMAX_ST_CONNECTING
-				  | 1 << WIMAX_ST_CONNECTED);
-		break;
-	case WIMAX_ST_SCANNING:
-		__check_new_state(old_state, new_state,
-				  1 << __WIMAX_ST_QUIESCING
-				  | 1 << WIMAX_ST_RADIO_OFF
-				  | 1 << WIMAX_ST_READY
-				  | 1 << WIMAX_ST_CONNECTING
-				  | 1 << WIMAX_ST_CONNECTED);
-		break;
-	case WIMAX_ST_CONNECTING:
-		__check_new_state(old_state, new_state,
-				  1 << __WIMAX_ST_QUIESCING
-				  | 1 << WIMAX_ST_RADIO_OFF
-				  | 1 << WIMAX_ST_READY
-				  | 1 << WIMAX_ST_SCANNING
-				  | 1 << WIMAX_ST_CONNECTED);
-		break;
-	case WIMAX_ST_CONNECTED:
-		__check_new_state(old_state, new_state,
-				  1 << __WIMAX_ST_QUIESCING
-				  | 1 << WIMAX_ST_RADIO_OFF
-				  | 1 << WIMAX_ST_READY);
-		netif_tx_disable(wimax_dev->net_dev);
-		netif_carrier_off(wimax_dev->net_dev);
-		break;
-	case __WIMAX_ST_INVALID:
-	default:
-		dev_err(dev, "SW BUG: wimax_dev %p is in unknown state %u\n",
-			wimax_dev, wimax_dev->state);
-		WARN_ON(1);
-		goto out;
-	}
-
-	/* Execute the actions of entry to the new state */
-	switch (new_state) {
-	case __WIMAX_ST_NULL:
-		dev_err(dev, "SW BUG: wimax_dev %p entering NULL state "
-			"from %u\n", wimax_dev, wimax_dev->state);
-		WARN_ON(1);		/* Nobody can enter this state */
-		break;
-	case WIMAX_ST_DOWN:
-		break;
-	case __WIMAX_ST_QUIESCING:
-		break;
-	case WIMAX_ST_UNINITIALIZED:
-		break;
-	case WIMAX_ST_RADIO_OFF:
-		break;
-	case WIMAX_ST_READY:
-		break;
-	case WIMAX_ST_SCANNING:
-		break;
-	case WIMAX_ST_CONNECTING:
-		break;
-	case WIMAX_ST_CONNECTED:
-		netif_carrier_on(wimax_dev->net_dev);
-		netif_wake_queue(wimax_dev->net_dev);
-		break;
-	case __WIMAX_ST_INVALID:
-	default:
-		BUG();
-	}
-	__wimax_state_set(wimax_dev, new_state);
-	if (!IS_ERR(stch_skb))
-		wimax_gnl_re_state_change_send(wimax_dev, stch_skb, header);
-out:
-	d_fnend(3, dev, "(wimax_dev %p new_state %u [old %u]) = void\n",
-		wimax_dev, new_state, old_state);
-}
-
-
-/**
- * wimax_state_change - Set the current state of a WiMAX device
- *
- * @wimax_dev: WiMAX device descriptor (properly referenced)
- * @new_state: New state to switch to
- *
- * This implements the state changes for the wimax devices. It will
- *
- * - verify that the state transition is legal (for now it'll just
- *   print a warning if not) according to the table in
- *   linux/wimax.h's documentation for 'enum wimax_st'.
- *
- * - perform the actions needed for leaving the current state and
- *   whichever are needed for entering the new state.
- *
- * - issue a report to user space indicating the new state (and an
- *   optional payload with information about the new state).
- *
- * NOTE: @wimax_dev must be locked
- */
-void wimax_state_change(struct wimax_dev *wimax_dev, enum wimax_st new_state)
-{
-	/*
-	 * A driver cannot take the wimax_dev out of the
-	 * __WIMAX_ST_NULL state unless by calling wimax_dev_add(). If
-	 * the wimax_dev's state is still NULL, we ignore any request
-	 * to change its state because it means it hasn't been yet
-	 * registered.
-	 *
-	 * There is no need to complain about it, as routines that
-	 * call this might be shared from different code paths that
-	 * are called before or after wimax_dev_add() has done its
-	 * job.
-	 */
-	mutex_lock(&wimax_dev->mutex);
-	if (wimax_dev->state > __WIMAX_ST_NULL)
-		__wimax_state_change(wimax_dev, new_state);
-	mutex_unlock(&wimax_dev->mutex);
-}
-EXPORT_SYMBOL_GPL(wimax_state_change);
-
-
-/**
- * wimax_state_get() - Return the current state of a WiMAX device
- *
- * @wimax_dev: WiMAX device descriptor
- *
- * Returns: Current state of the device according to its driver.
- */
-enum wimax_st wimax_state_get(struct wimax_dev *wimax_dev)
-{
-	enum wimax_st state;
-	mutex_lock(&wimax_dev->mutex);
-	state = wimax_dev->state;
-	mutex_unlock(&wimax_dev->mutex);
-	return state;
-}
-EXPORT_SYMBOL_GPL(wimax_state_get);
-
-
-/**
- * wimax_dev_init - initialize a newly allocated instance
- *
- * @wimax_dev: WiMAX device descriptor to initialize.
- *
- * Initializes fields of a freshly allocated @wimax_dev instance. This
- * function assumes that after allocation, the memory occupied by
- * @wimax_dev was zeroed.
- */
-void wimax_dev_init(struct wimax_dev *wimax_dev)
-{
-	INIT_LIST_HEAD(&wimax_dev->id_table_node);
-	__wimax_state_set(wimax_dev, __WIMAX_ST_NULL);
-	mutex_init(&wimax_dev->mutex);
-	mutex_init(&wimax_dev->mutex_reset);
-}
-EXPORT_SYMBOL_GPL(wimax_dev_init);
-
-/*
- * There are multiple enums reusing the same values, adding
- * others is only possible if they use a compatible policy.
- */
-static const struct nla_policy wimax_gnl_policy[WIMAX_GNL_ATTR_MAX + 1] = {
-	/*
-	 * WIMAX_GNL_RESET_IFIDX, WIMAX_GNL_RFKILL_IFIDX,
-	 * WIMAX_GNL_STGET_IFIDX, WIMAX_GNL_MSG_IFIDX
-	 */
-	[1] = { .type = NLA_U32, },
-	/*
-	 * WIMAX_GNL_RFKILL_STATE, WIMAX_GNL_MSG_PIPE_NAME
-	 */
-	[2] = { .type = NLA_U32, }, /* enum wimax_rf_state */
-	/*
-	 * WIMAX_GNL_MSG_DATA
-	 */
-	[3] = { .type = NLA_UNSPEC, }, /* libnl doesn't grok BINARY yet */
-};
-
-static const struct genl_small_ops wimax_gnl_ops[] = {
-	{
-		.cmd = WIMAX_GNL_OP_MSG_FROM_USER,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.flags = GENL_ADMIN_PERM,
-		.doit = wimax_gnl_doit_msg_from_user,
-	},
-	{
-		.cmd = WIMAX_GNL_OP_RESET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.flags = GENL_ADMIN_PERM,
-		.doit = wimax_gnl_doit_reset,
-	},
-	{
-		.cmd = WIMAX_GNL_OP_RFKILL,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.flags = GENL_ADMIN_PERM,
-		.doit = wimax_gnl_doit_rfkill,
-	},
-	{
-		.cmd = WIMAX_GNL_OP_STATE_GET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.flags = GENL_ADMIN_PERM,
-		.doit = wimax_gnl_doit_state_get,
-	},
-};
-
-
-static
-size_t wimax_addr_scnprint(char *addr_str, size_t addr_str_size,
-			   unsigned char *addr, size_t addr_len)
-{
-	unsigned int cnt, total;
-
-	for (total = cnt = 0; cnt < addr_len; cnt++)
-		total += scnprintf(addr_str + total, addr_str_size - total,
-				   "%02x%c", addr[cnt],
-				   cnt == addr_len - 1 ? '\0' : ':');
-	return total;
-}
-
-
-/**
- * wimax_dev_add - Register a new WiMAX device
- *
- * @wimax_dev: WiMAX device descriptor (as embedded in your @net_dev's
- *     priv data). You must have called wimax_dev_init() on it before.
- *
- * @net_dev: net device the @wimax_dev is associated with. The
- *     function expects SET_NETDEV_DEV() and register_netdev() were
- *     already called on it.
- *
- * Registers the new WiMAX device, sets up the user-kernel control
- * interface (generic netlink) and common WiMAX infrastructure.
- *
- * Note that the parts that will allow interaction with user space are
- * setup at the very end, when the rest is in place, as once that
- * happens, the driver might get user space control requests via
- * netlink or from debugfs that might translate into calls into
- * wimax_dev->op_*().
- */
-int wimax_dev_add(struct wimax_dev *wimax_dev, struct net_device *net_dev)
-{
-	int result;
-	struct device *dev = net_dev->dev.parent;
-	char addr_str[32];
-
-	d_fnstart(3, dev, "(wimax_dev %p net_dev %p)\n", wimax_dev, net_dev);
-
-	/* Do the RFKILL setup before locking, as RFKILL will call
-	 * into our functions.
-	 */
-	wimax_dev->net_dev = net_dev;
-	result = wimax_rfkill_add(wimax_dev);
-	if (result < 0)
-		goto error_rfkill_add;
-
-	/* Set up user-space interaction */
-	mutex_lock(&wimax_dev->mutex);
-	wimax_id_table_add(wimax_dev);
-	wimax_debugfs_add(wimax_dev);
-
-	__wimax_state_set(wimax_dev, WIMAX_ST_DOWN);
-	mutex_unlock(&wimax_dev->mutex);
-
-	wimax_addr_scnprint(addr_str, sizeof(addr_str),
-			    net_dev->dev_addr, net_dev->addr_len);
-	dev_err(dev, "WiMAX interface %s (%s) ready\n",
-		net_dev->name, addr_str);
-	d_fnend(3, dev, "(wimax_dev %p net_dev %p) = 0\n", wimax_dev, net_dev);
-	return 0;
-
-error_rfkill_add:
-	d_fnend(3, dev, "(wimax_dev %p net_dev %p) = %d\n",
-		wimax_dev, net_dev, result);
-	return result;
-}
-EXPORT_SYMBOL_GPL(wimax_dev_add);
-
-
-/**
- * wimax_dev_rm - Unregister an existing WiMAX device
- *
- * @wimax_dev: WiMAX device descriptor
- *
- * Unregisters a WiMAX device previously registered for use with
- * wimax_add_rm().
- *
- * IMPORTANT! Must call before calling unregister_netdev().
- *
- * After this function returns, you will not get any more user space
- * control requests (via netlink or debugfs) and thus to wimax_dev->ops.
- *
- * Reentrancy control is ensured by setting the state to
- * %__WIMAX_ST_QUIESCING. rfkill operations coming through
- * wimax_*rfkill*() will be stopped by the quiescing state; ops coming
- * from the rfkill subsystem will be stopped by the support being
- * removed by wimax_rfkill_rm().
- */
-void wimax_dev_rm(struct wimax_dev *wimax_dev)
-{
-	d_fnstart(3, NULL, "(wimax_dev %p)\n", wimax_dev);
-
-	mutex_lock(&wimax_dev->mutex);
-	__wimax_state_change(wimax_dev, __WIMAX_ST_QUIESCING);
-	wimax_debugfs_rm(wimax_dev);
-	wimax_id_table_rm(wimax_dev);
-	__wimax_state_change(wimax_dev, WIMAX_ST_DOWN);
-	mutex_unlock(&wimax_dev->mutex);
-	wimax_rfkill_rm(wimax_dev);
-	d_fnend(3, NULL, "(wimax_dev %p) = void\n", wimax_dev);
-}
-EXPORT_SYMBOL_GPL(wimax_dev_rm);
-
-
-/* Debug framework control of debug levels */
-struct d_level D_LEVEL[] = {
-	D_SUBMODULE_DEFINE(debugfs),
-	D_SUBMODULE_DEFINE(id_table),
-	D_SUBMODULE_DEFINE(op_msg),
-	D_SUBMODULE_DEFINE(op_reset),
-	D_SUBMODULE_DEFINE(op_rfkill),
-	D_SUBMODULE_DEFINE(op_state_get),
-	D_SUBMODULE_DEFINE(stack),
-};
-size_t D_LEVEL_SIZE = ARRAY_SIZE(D_LEVEL);
-
-
-static const struct genl_multicast_group wimax_gnl_mcgrps[] = {
-	{ .name = "msg", },
-};
-
-struct genl_family wimax_gnl_family __ro_after_init = {
-	.name = "WiMAX",
-	.version = WIMAX_GNL_VERSION,
-	.hdrsize = 0,
-	.maxattr = WIMAX_GNL_ATTR_MAX,
-	.policy = wimax_gnl_policy,
-	.module = THIS_MODULE,
-	.small_ops = wimax_gnl_ops,
-	.n_small_ops = ARRAY_SIZE(wimax_gnl_ops),
-	.mcgrps = wimax_gnl_mcgrps,
-	.n_mcgrps = ARRAY_SIZE(wimax_gnl_mcgrps),
-};
-
-
-
-/* Shutdown the wimax stack */
-static
-int __init wimax_subsys_init(void)
-{
-	int result;
-
-	d_fnstart(4, NULL, "()\n");
-	d_parse_params(D_LEVEL, D_LEVEL_SIZE, wimax_debug_params,
-		       "wimax.debug");
-
-	result = genl_register_family(&wimax_gnl_family);
-	if (unlikely(result < 0)) {
-		pr_err("cannot register generic netlink family: %d\n", result);
-		goto error_register_family;
-	}
-
-	d_fnend(4, NULL, "() = 0\n");
-	return 0;
-
-error_register_family:
-	d_fnend(4, NULL, "() = %d\n", result);
-	return result;
-
-}
-module_init(wimax_subsys_init);
-
-
-/* Shutdown the wimax stack */
-static
-void __exit wimax_subsys_exit(void)
-{
-	wimax_id_table_release();
-	genl_unregister_family(&wimax_gnl_family);
-}
-module_exit(wimax_subsys_exit);
-
-MODULE_AUTHOR("Intel Corporation <linux-wimax@intel.com>");
-MODULE_DESCRIPTION("Linux WiMAX stack");
-MODULE_LICENSE("GPL");
diff --git a/net/wimax/wimax-internal.h b/net/wimax/wimax-internal.h
deleted file mode 100644
index 40751207296c..000000000000
--- a/net/wimax/wimax-internal.h
+++ /dev/null
@@ -1,85 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Linux WiMAX
- * Internal API for kernel space WiMAX stack
- *
- * Copyright (C) 2007 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * This header file is for declarations and definitions internal to
- * the WiMAX stack. For public APIs and documentation, see
- * include/net/wimax.h and include/linux/wimax.h.
- */
-
-#ifndef __WIMAX_INTERNAL_H__
-#define __WIMAX_INTERNAL_H__
-#ifdef __KERNEL__
-
-#ifdef pr_fmt
-#undef pr_fmt
-#endif
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/device.h>
-#include <net/wimax.h>
-
-
-/*
- * Decide if a (locked) device is ready for use
- *
- * Before using the device structure, it must be locked
- * (wimax_dev->mutex). As well, most operations need to call this
- * function to check if the state is the right one.
- *
- * An error value will be returned if the state is not the right
- * one. In that case, the caller should not attempt to use the device
- * and just unlock it.
- */
-static inline __must_check
-int wimax_dev_is_ready(struct wimax_dev *wimax_dev)
-{
-	if (wimax_dev->state == __WIMAX_ST_NULL)
-		return -EINVAL;	/* Device is not even registered! */
-	if (wimax_dev->state == WIMAX_ST_DOWN)
-		return -ENOMEDIUM;
-	if (wimax_dev->state == __WIMAX_ST_QUIESCING)
-		return -ESHUTDOWN;
-	return 0;
-}
-
-
-static inline
-void __wimax_state_set(struct wimax_dev *wimax_dev, enum wimax_st state)
-{
-	wimax_dev->state = state;
-}
-void __wimax_state_change(struct wimax_dev *, enum wimax_st);
-
-#ifdef CONFIG_DEBUG_FS
-void wimax_debugfs_add(struct wimax_dev *);
-void wimax_debugfs_rm(struct wimax_dev *);
-#else
-static inline void wimax_debugfs_add(struct wimax_dev *wimax_dev) {}
-static inline void wimax_debugfs_rm(struct wimax_dev *wimax_dev) {}
-#endif
-
-void wimax_id_table_add(struct wimax_dev *);
-struct wimax_dev *wimax_dev_get_by_genl_info(struct genl_info *, int);
-void wimax_id_table_rm(struct wimax_dev *);
-void wimax_id_table_release(void);
-
-int wimax_rfkill_add(struct wimax_dev *);
-void wimax_rfkill_rm(struct wimax_dev *);
-
-/* generic netlink */
-extern struct genl_family wimax_gnl_family;
-
-/* ops */
-int wimax_gnl_doit_msg_from_user(struct sk_buff *skb, struct genl_info *info);
-int wimax_gnl_doit_reset(struct sk_buff *skb, struct genl_info *info);
-int wimax_gnl_doit_rfkill(struct sk_buff *skb, struct genl_info *info);
-int wimax_gnl_doit_state_get(struct sk_buff *skb, struct genl_info *info);
-
-#endif /* #ifdef __KERNEL__ */
-#endif /* #ifndef __WIMAX_INTERNAL_H__ */
-- 
cgit v1.2.3


From a4147d855f50a676ebe61833a681f7c71945f343 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Mon, 31 Aug 2020 10:18:04 -0500
Subject: dmaengine: ti-cppi5: Replace zero-length array with flexible-array
 member
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is a regular need in the kernel to provide a way to declare having a
dynamically sized set of trailing elements in a structure. Kernel code should
always use “flexible array members”[1] for these cases. The older style of
one-element or zero-length arrays should no longer be used[2].

[1] https://en.wikipedia.org/wiki/Flexible_array_member
[2] https://www.kernel.org/doc/html/v5.9-rc1/process/deprecated.html#zero-length-and-one-element-arrays

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
---
 include/linux/dma/ti-cppi5.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/dma/ti-cppi5.h b/include/linux/dma/ti-cppi5.h
index 5896441ee604..efa2f0309f00 100644
--- a/include/linux/dma/ti-cppi5.h
+++ b/include/linux/dma/ti-cppi5.h
@@ -47,7 +47,7 @@ struct cppi5_host_desc_t {
 	u32 buf_info1;
 	u32 org_buf_len;
 	u64 org_buf_ptr;
-	u32 epib[0];
+	u32 epib[];
 } __packed;
 
 #define CPPI5_DESC_MIN_ALIGN			(16U)
@@ -139,7 +139,7 @@ struct cppi5_desc_epib_t {
  */
 struct cppi5_monolithic_desc_t {
 	struct cppi5_desc_hdr_t hdr;
-	u32 epib[0];
+	u32 epib[];
 };
 
 #define CPPI5_INFO2_MDESC_DATA_OFFSET_SHIFT	(18U)
-- 
cgit v1.2.3


From 277ffd6c1ec0aa60856a03e18455fcca7d2a1186 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Mon, 31 Aug 2020 10:19:18 -0500
Subject: mailbox: zynqmp-ipi-message: Replace zero-length array with
 flexible-array member
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is a regular need in the kernel to provide a way to declare having a
dynamically sized set of trailing elements in a structure. Kernel code should
always use “flexible array members”[1] for these cases. The older style of
one-element or zero-length arrays should no longer be used[2].

[1] https://en.wikipedia.org/wiki/Flexible_array_member
[2] https://www.kernel.org/doc/html/v5.9-rc1/process/deprecated.html#zero-length-and-one-element-arrays

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
---
 include/linux/mailbox/zynqmp-ipi-message.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/mailbox/zynqmp-ipi-message.h b/include/linux/mailbox/zynqmp-ipi-message.h
index 9542b41eacfd..35ce84c8ca02 100644
--- a/include/linux/mailbox/zynqmp-ipi-message.h
+++ b/include/linux/mailbox/zynqmp-ipi-message.h
@@ -14,7 +14,7 @@
  */
 struct zynqmp_ipi_message {
 	size_t len;
-	u8 data[0];
+	u8 data[];
 };
 
 #endif /* _LINUX_ZYNQMP_IPI_MESSAGE_H_ */
-- 
cgit v1.2.3


From 883541051567a62add043a9f4ca5a31f2970bffd Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Mon, 31 Aug 2020 10:21:14 -0500
Subject: platform/chrome: cros_ec_commands: Replace zero-length array with
 flexible-array member
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is a regular need in the kernel to provide a way to declare having a
dynamically sized set of trailing elements in a structure. Kernel code should
always use “flexible array members”[1] for these cases. The older style of
one-element or zero-length arrays should no longer be used[2].

[1] https://en.wikipedia.org/wiki/Flexible_array_member
[2] https://www.kernel.org/doc/html/v5.9-rc1/process/deprecated.html#zero-length-and-one-element-arrays

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
---
 include/linux/platform_data/cros_ec_commands.h | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h
index 1fcfe9e63cb9..a3a9a878415f 100644
--- a/include/linux/platform_data/cros_ec_commands.h
+++ b/include/linux/platform_data/cros_ec_commands.h
@@ -1419,7 +1419,7 @@ struct ec_response_flash_info_2 {
 	uint16_t num_banks_total;
 	/* Number of banks described in banks array. */
 	uint16_t num_banks_desc;
-	struct ec_flash_bank banks[0];
+	struct ec_flash_bank banks[];
 } __ec_align4;
 
 /*
@@ -2420,12 +2420,12 @@ struct ec_response_motion_sense_fifo_info {
 	/* Total amount of vector lost */
 	uint16_t total_lost;
 	/* Lost events since the last fifo_info, per sensors */
-	uint16_t lost[0];
+	uint16_t lost[];
 } __ec_todo_packed;
 
 struct ec_response_motion_sense_fifo_data {
 	uint32_t number_data;
-	struct ec_response_motion_sensor_data data[0];
+	struct ec_response_motion_sensor_data data[];
 } __ec_todo_packed;
 
 /* List supported activity recognition */
@@ -3093,7 +3093,7 @@ struct ec_response_tmp006_get_calibration_v1 {
 	uint8_t algorithm;
 	uint8_t num_params;
 	uint8_t reserved[2];
-	float val[0];
+	float val[];
 } __ec_align4;
 
 struct ec_params_tmp006_set_calibration_v1 {
@@ -3101,7 +3101,7 @@ struct ec_params_tmp006_set_calibration_v1 {
 	uint8_t algorithm;
 	uint8_t num_params;
 	uint8_t reserved;
-	float val[0];
+	float val[];
 } __ec_align4;
 
 
@@ -5076,7 +5076,7 @@ struct ec_response_pd_log {
 	uint8_t type;       /* event type : see PD_EVENT_xx below */
 	uint8_t size_port;  /* [7:5] port number [4:0] payload size in bytes */
 	uint16_t data;      /* type-defined data payload */
-	uint8_t payload[0]; /* optional additional data payload: 0..16 bytes */
+	uint8_t payload[];  /* optional additional data payload: 0..16 bytes */
 } __ec_align4;
 
 /* The timestamp is the microsecond counter shifted to get about a ms. */
@@ -5789,7 +5789,7 @@ struct ec_response_fp_encryption_status {
 
 struct ec_response_tp_frame_info {
 	uint32_t n_frames;
-	uint32_t frame_sizes[0];
+	uint32_t frame_sizes[];
 } __ec_align4;
 
 /* Create a snapshot of current frame readings */
-- 
cgit v1.2.3


From 120088832042e6dc9866160ff267f8c347bf53e6 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Mon, 31 Aug 2020 10:21:55 -0500
Subject: platform/chrome: cros_ec_proto: Replace zero-length array with
 flexible-array member
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is a regular need in the kernel to provide a way to declare having a
dynamically sized set of trailing elements in a structure. Kernel code should
always use “flexible array members”[1] for these cases. The older style of
one-element or zero-length arrays should no longer be used[2].

[1] https://en.wikipedia.org/wiki/Flexible_array_member
[2] https://www.kernel.org/doc/html/v5.9-rc1/process/deprecated.html#zero-length-and-one-element-arrays

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
---
 include/linux/platform_data/cros_ec_proto.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h
index 4a415ae851ef..02599687770c 100644
--- a/include/linux/platform_data/cros_ec_proto.h
+++ b/include/linux/platform_data/cros_ec_proto.h
@@ -69,7 +69,7 @@ struct cros_ec_command {
 	uint32_t outsize;
 	uint32_t insize;
 	uint32_t result;
-	uint8_t data[0];
+	uint8_t data[];
 };
 
 /**
-- 
cgit v1.2.3


From 5e01fdff04b7f7c3b8d456c11c8a9f978b4ddf65 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Mon, 31 Aug 2020 08:25:42 -0500
Subject: fs: Replace zero-length array with flexible-array member
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is a regular need in the kernel to provide a way to declare having a
dynamically sized set of trailing elements in a structure. Kernel code should
always use “flexible array members”[1] for these cases. The older style of
one-element or zero-length arrays should no longer be used[2].

[1] https://en.wikipedia.org/wiki/Flexible_array_member
[2] https://www.kernel.org/doc/html/v5.9-rc1/process/deprecated.html#zero-length-and-one-element-arrays

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
---
 fs/binfmt_elf.c         | 2 +-
 fs/hfs/btree.h          | 2 +-
 fs/hfsplus/hfsplus_fs.h | 2 +-
 fs/isofs/rock.h         | 8 ++++----
 fs/select.c             | 4 ++--
 include/linux/fs.h      | 2 +-
 6 files changed, 10 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index b6b3d052ca86..fa50e8936f5f 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1690,7 +1690,7 @@ struct elf_thread_core_info {
 	struct elf_thread_core_info *next;
 	struct task_struct *task;
 	struct elf_prstatus prstatus;
-	struct memelfnote notes[0];
+	struct memelfnote notes[];
 };
 
 struct elf_note_info {
diff --git a/fs/hfs/btree.h b/fs/hfs/btree.h
index dcc2aab1b2c4..4ba45caf5939 100644
--- a/fs/hfs/btree.h
+++ b/fs/hfs/btree.h
@@ -60,7 +60,7 @@ struct hfs_bnode {
 	wait_queue_head_t lock_wq;
 	atomic_t refcnt;
 	unsigned int page_offset;
-	struct page *page[0];
+	struct page *page[];
 };
 
 #define HFS_BNODE_ERROR		0
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index 3b03fff68543..a92de5199ec3 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -117,7 +117,7 @@ struct hfs_bnode {
 	wait_queue_head_t lock_wq;
 	atomic_t refcnt;
 	unsigned int page_offset;
-	struct page *page[0];
+	struct page *page[];
 };
 
 #define HFS_BNODE_LOCK		0
diff --git a/fs/isofs/rock.h b/fs/isofs/rock.h
index 1558cf22ef8a..ee9660e9671c 100644
--- a/fs/isofs/rock.h
+++ b/fs/isofs/rock.h
@@ -22,7 +22,7 @@ struct SU_ER_s {
 	__u8 len_des;
 	__u8 len_src;
 	__u8 ext_ver;
-	__u8 data[0];
+	__u8 data[];
 } __attribute__ ((packed));
 
 struct RR_RR_s {
@@ -44,7 +44,7 @@ struct RR_PN_s {
 struct SL_component {
 	__u8 flags;
 	__u8 len;
-	__u8 text[0];
+	__u8 text[];
 } __attribute__ ((packed));
 
 struct RR_SL_s {
@@ -54,7 +54,7 @@ struct RR_SL_s {
 
 struct RR_NM_s {
 	__u8 flags;
-	char name[0];
+	char name[];
 } __attribute__ ((packed));
 
 struct RR_CL_s {
@@ -71,7 +71,7 @@ struct stamp {
 
 struct RR_TF_s {
 	__u8 flags;
-	struct stamp times[0];	/* Variable number of these beasts */
+	struct stamp times[];	/* Variable number of these beasts */
 } __attribute__ ((packed));
 
 /* Linux-specific extension for transparent decompression */
diff --git a/fs/select.c b/fs/select.c
index 7aef49552d4c..ebfebdfe5c69 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -97,7 +97,7 @@ u64 select_estimate_accuracy(struct timespec64 *tv)
 struct poll_table_page {
 	struct poll_table_page * next;
 	struct poll_table_entry * entry;
-	struct poll_table_entry entries[0];
+	struct poll_table_entry entries[];
 };
 
 #define POLL_TABLE_FULL(table) \
@@ -836,7 +836,7 @@ SYSCALL_DEFINE1(old_select, struct sel_arg_struct __user *, arg)
 struct poll_list {
 	struct poll_list *next;
 	int len;
-	struct pollfd entries[0];
+	struct pollfd entries[];
 };
 
 #define POLLFD_PER_PAGE  ((PAGE_SIZE-sizeof(struct poll_list)) / sizeof(struct pollfd))
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 0bd126418bb6..21cc971fd960 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3285,7 +3285,7 @@ static inline ino_t parent_ino(struct dentry *dentry)
  */
 struct simple_transaction_argresp {
 	ssize_t size;
-	char data[0];
+	char data[];
 };
 
 #define SIMPLE_TRANSACTION_LIMIT (PAGE_SIZE - sizeof(struct simple_transaction_argresp))
-- 
cgit v1.2.3


From 080b6f40763565f65ebb9540219c71ce885cf568 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Wed, 28 Oct 2020 18:15:05 +0100
Subject: bpf: Don't rely on GCC __attribute__((optimize)) to disable GCSE

Commit 3193c0836 ("bpf: Disable GCC -fgcse optimization for
___bpf_prog_run()") introduced a __no_fgcse macro that expands to a
function scope __attribute__((optimize("-fno-gcse"))), to disable a
GCC specific optimization that was causing trouble on x86 builds, and
was not expected to have any positive effect in the first place.

However, as the GCC manual documents, __attribute__((optimize))
is not for production use, and results in all other optimization
options to be forgotten for the function in question. This can
cause all kinds of trouble, but in one particular reported case,
it causes -fno-asynchronous-unwind-tables to be disregarded,
resulting in .eh_frame info to be emitted for the function.

This reverts commit 3193c0836, and instead, it disables the -fgcse
optimization for the entire source file, but only when building for
X86 using GCC with CONFIG_BPF_JIT_ALWAYS_ON disabled. Note that the
original commit states that CONFIG_RETPOLINE=n triggers the issue,
whereas CONFIG_RETPOLINE=y performs better without the optimization,
so it is kept disabled in both cases.

Fixes: 3193c0836f20 ("bpf: Disable GCC -fgcse optimization for ___bpf_prog_run()")
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Link: https://lore.kernel.org/lkml/CAMuHMdUg0WJHEcq6to0-eODpXPOywLot6UD2=GFHpzoj_hCoBQ@mail.gmail.com/
Link: https://lore.kernel.org/bpf/20201028171506.15682-2-ardb@kernel.org
---
 include/linux/compiler-gcc.h   | 2 --
 include/linux/compiler_types.h | 4 ----
 kernel/bpf/Makefile            | 6 +++++-
 kernel/bpf/core.c              | 2 +-
 4 files changed, 6 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index d1e3c6896b71..5deb37024574 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -175,5 +175,3 @@
 #else
 #define __diag_GCC_8(s)
 #endif
-
-#define __no_fgcse __attribute__((optimize("-fno-gcse")))
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 6e390d58a9f8..ac3fa37a84f9 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -247,10 +247,6 @@ struct ftrace_likely_data {
 #define asm_inline asm
 #endif
 
-#ifndef __no_fgcse
-# define __no_fgcse
-#endif
-
 /* Are two types/vars the same type (ignoring qualifiers)? */
 #define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b))
 
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index bdc8cd1b6767..c1b9f71ee6aa 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -1,6 +1,10 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-y := core.o
-CFLAGS_core.o += $(call cc-disable-warning, override-init)
+ifneq ($(CONFIG_BPF_JIT_ALWAYS_ON),y)
+# ___bpf_prog_run() needs GCSE disabled on x86; see 3193c0836f203 for details
+cflags-nogcse-$(CONFIG_X86)$(CONFIG_CC_IS_GCC) := -fno-gcse
+endif
+CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy)
 
 obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o prog_iter.o
 obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 9268d77898b7..55454d2278b1 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1369,7 +1369,7 @@ u64 __weak bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr)
  *
  * Decode and execute eBPF instructions.
  */
-static u64 __no_fgcse ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
+static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
 {
 #define BPF_INSN_2_LBL(x, y)    [BPF_##x | BPF_##y] = &&x##_##y
 #define BPF_INSN_3_LBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = &&x##_##y##_##z
-- 
cgit v1.2.3


From 0d519cbf38eed4f895aed197d4b135fa7f60f7c2 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Fri, 23 Oct 2020 15:10:37 +0200
Subject: debugfs: remove return value of debugfs_create_devm_seqfile()

No one checks the return value of debugfs_create_devm_seqfile(), as it's
not needed, so make the return value void, so that no one tries to do so
in the future.

Link: https://lore.kernel.org/r/20201023131037.2500765-1-gregkh@linuxfoundation.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/filesystems/debugfs.rst |  2 +-
 fs/debugfs/file.c                     | 15 +++++++--------
 include/linux/debugfs.h               | 18 ++++++++----------
 3 files changed, 16 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/debugfs.rst b/Documentation/filesystems/debugfs.rst
index 728ab57a611a..0f2292e367e6 100644
--- a/Documentation/filesystems/debugfs.rst
+++ b/Documentation/filesystems/debugfs.rst
@@ -199,7 +199,7 @@ of its elements. Note: Once array is created its size can not be changed.
 
 There is a helper function to create device related seq_file::
 
-   struct dentry *debugfs_create_devm_seqfile(struct device *dev,
+   void debugfs_create_devm_seqfile(struct device *dev,
 				const char *name,
 				struct dentry *parent,
 				int (*read_fn)(struct seq_file *s,
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index a768a09430c3..686e0ad28788 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -1127,24 +1127,23 @@ static const struct file_operations debugfs_devm_entry_ops = {
  *	file will be created in the root of the debugfs filesystem.
  * @read_fn: function pointer called to print the seq_file content.
  */
-struct dentry *debugfs_create_devm_seqfile(struct device *dev, const char *name,
-					   struct dentry *parent,
-					   int (*read_fn)(struct seq_file *s,
-							  void *data))
+void debugfs_create_devm_seqfile(struct device *dev, const char *name,
+				 struct dentry *parent,
+				 int (*read_fn)(struct seq_file *s, void *data))
 {
 	struct debugfs_devm_entry *entry;
 
 	if (IS_ERR(parent))
-		return ERR_PTR(-ENOENT);
+		return;
 
 	entry = devm_kzalloc(dev, sizeof(*entry), GFP_KERNEL);
 	if (!entry)
-		return ERR_PTR(-ENOMEM);
+		return;
 
 	entry->read = read_fn;
 	entry->dev = dev;
 
-	return debugfs_create_file(name, S_IRUGO, parent, entry,
-				   &debugfs_devm_entry_ops);
+	debugfs_create_file(name, S_IRUGO, parent, entry,
+			    &debugfs_devm_entry_ops);
 }
 EXPORT_SYMBOL_GPL(debugfs_create_devm_seqfile);
diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h
index 851dd1f9a8a5..d6c4cc9ecc77 100644
--- a/include/linux/debugfs.h
+++ b/include/linux/debugfs.h
@@ -144,10 +144,9 @@ void debugfs_create_u32_array(const char *name, umode_t mode,
 			      struct dentry *parent,
 			      struct debugfs_u32_array *array);
 
-struct dentry *debugfs_create_devm_seqfile(struct device *dev, const char *name,
-					   struct dentry *parent,
-					   int (*read_fn)(struct seq_file *s,
-							  void *data));
+void debugfs_create_devm_seqfile(struct device *dev, const char *name,
+				 struct dentry *parent,
+				 int (*read_fn)(struct seq_file *s, void *data));
 
 bool debugfs_initialized(void);
 
@@ -327,13 +326,12 @@ static inline void debugfs_create_u32_array(const char *name, umode_t mode,
 {
 }
 
-static inline struct dentry *debugfs_create_devm_seqfile(struct device *dev,
-							 const char *name,
-							 struct dentry *parent,
-					   int (*read_fn)(struct seq_file *s,
-							  void *data))
+static inline void debugfs_create_devm_seqfile(struct device *dev,
+					       const char *name,
+					       struct dentry *parent,
+					       int (*read_fn)(struct seq_file *s,
+							      void *data))
 {
-	return ERR_PTR(-ENODEV);
 }
 
 static inline ssize_t debugfs_read_file_bool(struct file *file,
-- 
cgit v1.2.3


From 46d6c5ae953cc0be38efd0e469284df7c4328cf8 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Thu, 29 Oct 2020 03:56:06 +0100
Subject: netfilter: use actual socket sk rather than skb sk when routing
 harder

If netfilter changes the packet mark when mangling, the packet is
rerouted using the route_me_harder set of functions. Prior to this
commit, there's one big difference between route_me_harder and the
ordinary initial routing functions, described in the comment above
__ip_queue_xmit():

   /* Note: skb->sk can be different from sk, in case of tunnels */
   int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,

That function goes on to correctly make use of sk->sk_bound_dev_if,
rather than skb->sk->sk_bound_dev_if. And indeed the comment is true: a
tunnel will receive a packet in ndo_start_xmit with an initial skb->sk.
It will make some transformations to that packet, and then it will send
the encapsulated packet out of a *new* socket. That new socket will
basically always have a different sk_bound_dev_if (otherwise there'd be
a routing loop). So for the purposes of routing the encapsulated packet,
the routing information as it pertains to the socket should come from
that socket's sk, rather than the packet's original skb->sk. For that
reason __ip_queue_xmit() and related functions all do the right thing.

One might argue that all tunnels should just call skb_orphan(skb) before
transmitting the encapsulated packet into the new socket. But tunnels do
*not* do this -- and this is wisely avoided in skb_scrub_packet() too --
because features like TSQ rely on skb->destructor() being called when
that buffer space is truely available again. Calling skb_orphan(skb) too
early would result in buffers filling up unnecessarily and accounting
info being all wrong. Instead, additional routing must take into account
the new sk, just as __ip_queue_xmit() notes.

So, this commit addresses the problem by fishing the correct sk out of
state->sk -- it's already set properly in the call to nf_hook() in
__ip_local_out(), which receives the sk as part of its normal
functionality. So we make sure to plumb state->sk through the various
route_me_harder functions, and then make correct use of it following the
example of __ip_queue_xmit().

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Reviewed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter_ipv4.h       |  2 +-
 include/linux/netfilter_ipv6.h       | 10 +++++-----
 net/ipv4/netfilter.c                 |  8 +++++---
 net/ipv4/netfilter/iptable_mangle.c  |  2 +-
 net/ipv4/netfilter/nf_reject_ipv4.c  |  2 +-
 net/ipv6/netfilter.c                 |  6 +++---
 net/ipv6/netfilter/ip6table_mangle.c |  2 +-
 net/netfilter/ipvs/ip_vs_core.c      |  4 ++--
 net/netfilter/nf_nat_proto.c         |  4 ++--
 net/netfilter/nf_synproxy_core.c     |  2 +-
 net/netfilter/nft_chain_route.c      |  4 ++--
 net/netfilter/utils.c                |  4 ++--
 12 files changed, 26 insertions(+), 24 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netfilter_ipv4.h b/include/linux/netfilter_ipv4.h
index 082e2c41b7ff..5b70ca868bb1 100644
--- a/include/linux/netfilter_ipv4.h
+++ b/include/linux/netfilter_ipv4.h
@@ -16,7 +16,7 @@ struct ip_rt_info {
 	u_int32_t mark;
 };
 
-int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned addr_type);
+int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned addr_type);
 
 struct nf_queue_entry;
 
diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h
index 9b67394471e1..48314ade1506 100644
--- a/include/linux/netfilter_ipv6.h
+++ b/include/linux/netfilter_ipv6.h
@@ -42,7 +42,7 @@ struct nf_ipv6_ops {
 #if IS_MODULE(CONFIG_IPV6)
 	int (*chk_addr)(struct net *net, const struct in6_addr *addr,
 			const struct net_device *dev, int strict);
-	int (*route_me_harder)(struct net *net, struct sk_buff *skb);
+	int (*route_me_harder)(struct net *net, struct sock *sk, struct sk_buff *skb);
 	int (*dev_get_saddr)(struct net *net, const struct net_device *dev,
 		       const struct in6_addr *daddr, unsigned int srcprefs,
 		       struct in6_addr *saddr);
@@ -143,9 +143,9 @@ static inline int nf_br_ip6_fragment(struct net *net, struct sock *sk,
 #endif
 }
 
-int ip6_route_me_harder(struct net *net, struct sk_buff *skb);
+int ip6_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb);
 
-static inline int nf_ip6_route_me_harder(struct net *net, struct sk_buff *skb)
+static inline int nf_ip6_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 #if IS_MODULE(CONFIG_IPV6)
 	const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops();
@@ -153,9 +153,9 @@ static inline int nf_ip6_route_me_harder(struct net *net, struct sk_buff *skb)
 	if (!v6_ops)
 		return -EHOSTUNREACH;
 
-	return v6_ops->route_me_harder(net, skb);
+	return v6_ops->route_me_harder(net, sk, skb);
 #elif IS_BUILTIN(CONFIG_IPV6)
-	return ip6_route_me_harder(net, skb);
+	return ip6_route_me_harder(net, sk, skb);
 #else
 	return -EHOSTUNREACH;
 #endif
diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index a058213b77a7..7c841037c533 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -17,17 +17,19 @@
 #include <net/netfilter/nf_queue.h>
 
 /* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */
-int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned int addr_type)
+int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int addr_type)
 {
 	const struct iphdr *iph = ip_hdr(skb);
 	struct rtable *rt;
 	struct flowi4 fl4 = {};
 	__be32 saddr = iph->saddr;
-	const struct sock *sk = skb_to_full_sk(skb);
-	__u8 flags = sk ? inet_sk_flowi_flags(sk) : 0;
+	__u8 flags;
 	struct net_device *dev = skb_dst(skb)->dev;
 	unsigned int hh_len;
 
+	sk = sk_to_full_sk(sk);
+	flags = sk ? inet_sk_flowi_flags(sk) : 0;
+
 	if (addr_type == RTN_UNSPEC)
 		addr_type = inet_addr_type_dev_table(net, dev, saddr);
 	if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST)
diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c
index f703a717ab1d..833079589273 100644
--- a/net/ipv4/netfilter/iptable_mangle.c
+++ b/net/ipv4/netfilter/iptable_mangle.c
@@ -62,7 +62,7 @@ ipt_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state)
 		    iph->daddr != daddr ||
 		    skb->mark != mark ||
 		    iph->tos != tos) {
-			err = ip_route_me_harder(state->net, skb, RTN_UNSPEC);
+			err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC);
 			if (err < 0)
 				ret = NF_DROP_ERR(err);
 		}
diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
index 9dcfa4e461b6..93b07739807b 100644
--- a/net/ipv4/netfilter/nf_reject_ipv4.c
+++ b/net/ipv4/netfilter/nf_reject_ipv4.c
@@ -145,7 +145,7 @@ void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook)
 				   ip4_dst_hoplimit(skb_dst(nskb)));
 	nf_reject_ip_tcphdr_put(nskb, oldskb, oth);
 
-	if (ip_route_me_harder(net, nskb, RTN_UNSPEC))
+	if (ip_route_me_harder(net, nskb->sk, nskb, RTN_UNSPEC))
 		goto free_nskb;
 
 	niph = ip_hdr(nskb);
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 6d0e942d082d..ab9a279dd6d4 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -20,10 +20,10 @@
 #include <net/netfilter/ipv6/nf_defrag_ipv6.h>
 #include "../bridge/br_private.h"
 
-int ip6_route_me_harder(struct net *net, struct sk_buff *skb)
+int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff *skb)
 {
 	const struct ipv6hdr *iph = ipv6_hdr(skb);
-	struct sock *sk = sk_to_full_sk(skb->sk);
+	struct sock *sk = sk_to_full_sk(sk_partial);
 	unsigned int hh_len;
 	struct dst_entry *dst;
 	int strict = (ipv6_addr_type(&iph->daddr) &
@@ -84,7 +84,7 @@ static int nf_ip6_reroute(struct sk_buff *skb,
 		if (!ipv6_addr_equal(&iph->daddr, &rt_info->daddr) ||
 		    !ipv6_addr_equal(&iph->saddr, &rt_info->saddr) ||
 		    skb->mark != rt_info->mark)
-			return ip6_route_me_harder(entry->state.net, skb);
+			return ip6_route_me_harder(entry->state.net, entry->state.sk, skb);
 	}
 	return 0;
 }
diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c
index 1a2748611e00..cee74803d7a1 100644
--- a/net/ipv6/netfilter/ip6table_mangle.c
+++ b/net/ipv6/netfilter/ip6table_mangle.c
@@ -57,7 +57,7 @@ ip6t_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state)
 	     skb->mark != mark ||
 	     ipv6_hdr(skb)->hop_limit != hop_limit ||
 	     flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) {
-		err = ip6_route_me_harder(state->net, skb);
+		err = ip6_route_me_harder(state->net, state->sk, skb);
 		if (err < 0)
 			ret = NF_DROP_ERR(err);
 	}
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index cc3c275934f4..c0b8215ab3d4 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -742,12 +742,12 @@ static int ip_vs_route_me_harder(struct netns_ipvs *ipvs, int af,
 		struct dst_entry *dst = skb_dst(skb);
 
 		if (dst->dev && !(dst->dev->flags & IFF_LOOPBACK) &&
-		    ip6_route_me_harder(ipvs->net, skb) != 0)
+		    ip6_route_me_harder(ipvs->net, skb->sk, skb) != 0)
 			return 1;
 	} else
 #endif
 		if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
-		    ip_route_me_harder(ipvs->net, skb, RTN_LOCAL) != 0)
+		    ip_route_me_harder(ipvs->net, skb->sk, skb, RTN_LOCAL) != 0)
 			return 1;
 
 	return 0;
diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c
index 59151dc07fdc..e87b6bd6b3cd 100644
--- a/net/netfilter/nf_nat_proto.c
+++ b/net/netfilter/nf_nat_proto.c
@@ -715,7 +715,7 @@ nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb,
 
 		if (ct->tuplehash[dir].tuple.dst.u3.ip !=
 		    ct->tuplehash[!dir].tuple.src.u3.ip) {
-			err = ip_route_me_harder(state->net, skb, RTN_UNSPEC);
+			err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC);
 			if (err < 0)
 				ret = NF_DROP_ERR(err);
 		}
@@ -953,7 +953,7 @@ nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb,
 
 		if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3,
 				      &ct->tuplehash[!dir].tuple.src.u3)) {
-			err = nf_ip6_route_me_harder(state->net, skb);
+			err = nf_ip6_route_me_harder(state->net, state->sk, skb);
 			if (err < 0)
 				ret = NF_DROP_ERR(err);
 		}
diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c
index 9cca35d22927..d7d34a62d3bf 100644
--- a/net/netfilter/nf_synproxy_core.c
+++ b/net/netfilter/nf_synproxy_core.c
@@ -446,7 +446,7 @@ synproxy_send_tcp(struct net *net,
 
 	skb_dst_set_noref(nskb, skb_dst(skb));
 	nskb->protocol = htons(ETH_P_IP);
-	if (ip_route_me_harder(net, nskb, RTN_UNSPEC))
+	if (ip_route_me_harder(net, nskb->sk, nskb, RTN_UNSPEC))
 		goto free_nskb;
 
 	if (nfct) {
diff --git a/net/netfilter/nft_chain_route.c b/net/netfilter/nft_chain_route.c
index 8826bbe71136..edd02cda57fc 100644
--- a/net/netfilter/nft_chain_route.c
+++ b/net/netfilter/nft_chain_route.c
@@ -42,7 +42,7 @@ static unsigned int nf_route_table_hook4(void *priv,
 		    iph->daddr != daddr ||
 		    skb->mark != mark ||
 		    iph->tos != tos) {
-			err = ip_route_me_harder(state->net, skb, RTN_UNSPEC);
+			err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC);
 			if (err < 0)
 				ret = NF_DROP_ERR(err);
 		}
@@ -92,7 +92,7 @@ static unsigned int nf_route_table_hook6(void *priv,
 	     skb->mark != mark ||
 	     ipv6_hdr(skb)->hop_limit != hop_limit ||
 	     flowlabel != *((u32 *)ipv6_hdr(skb)))) {
-		err = nf_ip6_route_me_harder(state->net, skb);
+		err = nf_ip6_route_me_harder(state->net, state->sk, skb);
 		if (err < 0)
 			ret = NF_DROP_ERR(err);
 	}
diff --git a/net/netfilter/utils.c b/net/netfilter/utils.c
index cedf47ab3c6f..2182d361e273 100644
--- a/net/netfilter/utils.c
+++ b/net/netfilter/utils.c
@@ -191,8 +191,8 @@ static int nf_ip_reroute(struct sk_buff *skb, const struct nf_queue_entry *entry
 		      skb->mark == rt_info->mark &&
 		      iph->daddr == rt_info->daddr &&
 		      iph->saddr == rt_info->saddr))
-			return ip_route_me_harder(entry->state.net, skb,
-						  RTN_UNSPEC);
+			return ip_route_me_harder(entry->state.net, entry->state.sk,
+						  skb, RTN_UNSPEC);
 	}
 #endif
 	return 0;
-- 
cgit v1.2.3


From c0391b6ab810381df632677a1dcbbbbd63d05b6d Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Thu, 29 Oct 2020 13:50:03 +0100
Subject: netfilter: nf_tables: missing validation from the abort path

If userspace does not include the trailing end of batch message, then
nfnetlink aborts the transaction. This allows to check that ruleset
updates trigger no errors.

After this patch, invoking this command from the prerouting chain:

 # nft -c add rule x y fib saddr . oif type local

fails since oif is not supported there.

This patch fixes the lack of rule validation from the abort/check path
to catch configuration errors such as the one above.

Fixes: a654de8fdc18 ("netfilter: nf_tables: fix chain dependency validation")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/nfnetlink.h |  9 ++++++++-
 net/netfilter/nf_tables_api.c       | 15 ++++++++++-----
 net/netfilter/nfnetlink.c           | 22 ++++++++++++++++++----
 3 files changed, 36 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h
index 89016d08f6a2..f6267e2883f2 100644
--- a/include/linux/netfilter/nfnetlink.h
+++ b/include/linux/netfilter/nfnetlink.h
@@ -24,6 +24,12 @@ struct nfnl_callback {
 	const u_int16_t attr_count;		/* number of nlattr's */
 };
 
+enum nfnl_abort_action {
+	NFNL_ABORT_NONE		= 0,
+	NFNL_ABORT_AUTOLOAD,
+	NFNL_ABORT_VALIDATE,
+};
+
 struct nfnetlink_subsystem {
 	const char *name;
 	__u8 subsys_id;			/* nfnetlink subsystem ID */
@@ -31,7 +37,8 @@ struct nfnetlink_subsystem {
 	const struct nfnl_callback *cb;	/* callback for individual types */
 	struct module *owner;
 	int (*commit)(struct net *net, struct sk_buff *skb);
-	int (*abort)(struct net *net, struct sk_buff *skb, bool autoload);
+	int (*abort)(struct net *net, struct sk_buff *skb,
+		     enum nfnl_abort_action action);
 	void (*cleanup)(struct net *net);
 	bool (*valid_genid)(struct net *net, u32 genid);
 };
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 9b70e136fb5d..0f58e98542be 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -8053,12 +8053,16 @@ static void nf_tables_abort_release(struct nft_trans *trans)
 	kfree(trans);
 }
 
-static int __nf_tables_abort(struct net *net, bool autoload)
+static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
 {
 	struct nft_trans *trans, *next;
 	struct nft_trans_elem *te;
 	struct nft_hook *hook;
 
+	if (action == NFNL_ABORT_VALIDATE &&
+	    nf_tables_validate(net) < 0)
+		return -EAGAIN;
+
 	list_for_each_entry_safe_reverse(trans, next, &net->nft.commit_list,
 					 list) {
 		switch (trans->msg_type) {
@@ -8190,7 +8194,7 @@ static int __nf_tables_abort(struct net *net, bool autoload)
 		nf_tables_abort_release(trans);
 	}
 
-	if (autoload)
+	if (action == NFNL_ABORT_AUTOLOAD)
 		nf_tables_module_autoload(net);
 	else
 		nf_tables_module_autoload_cleanup(net);
@@ -8203,9 +8207,10 @@ static void nf_tables_cleanup(struct net *net)
 	nft_validate_state_update(net, NFT_VALIDATE_SKIP);
 }
 
-static int nf_tables_abort(struct net *net, struct sk_buff *skb, bool autoload)
+static int nf_tables_abort(struct net *net, struct sk_buff *skb,
+			   enum nfnl_abort_action action)
 {
-	int ret = __nf_tables_abort(net, autoload);
+	int ret = __nf_tables_abort(net, action);
 
 	mutex_unlock(&net->nft.commit_mutex);
 
@@ -8836,7 +8841,7 @@ static void __net_exit nf_tables_exit_net(struct net *net)
 {
 	mutex_lock(&net->nft.commit_mutex);
 	if (!list_empty(&net->nft.commit_list))
-		__nf_tables_abort(net, false);
+		__nf_tables_abort(net, NFNL_ABORT_NONE);
 	__nft_release_tables(net);
 	mutex_unlock(&net->nft.commit_mutex);
 	WARN_ON_ONCE(!list_empty(&net->nft.tables));
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 2daa1f6ae344..d3df66a39b5e 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -333,7 +333,7 @@ static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh,
 		return netlink_ack(skb, nlh, -EINVAL, NULL);
 replay:
 	status = 0;
-
+replay_abort:
 	skb = netlink_skb_clone(oskb, GFP_KERNEL);
 	if (!skb)
 		return netlink_ack(oskb, nlh, -ENOMEM, NULL);
@@ -499,7 +499,7 @@ ack:
 	}
 done:
 	if (status & NFNL_BATCH_REPLAY) {
-		ss->abort(net, oskb, true);
+		ss->abort(net, oskb, NFNL_ABORT_AUTOLOAD);
 		nfnl_err_reset(&err_list);
 		kfree_skb(skb);
 		module_put(ss->owner);
@@ -510,11 +510,25 @@ done:
 			status |= NFNL_BATCH_REPLAY;
 			goto done;
 		} else if (err) {
-			ss->abort(net, oskb, false);
+			ss->abort(net, oskb, NFNL_ABORT_NONE);
 			netlink_ack(oskb, nlmsg_hdr(oskb), err, NULL);
 		}
 	} else {
-		ss->abort(net, oskb, false);
+		enum nfnl_abort_action abort_action;
+
+		if (status & NFNL_BATCH_FAILURE)
+			abort_action = NFNL_ABORT_NONE;
+		else
+			abort_action = NFNL_ABORT_VALIDATE;
+
+		err = ss->abort(net, oskb, abort_action);
+		if (err == -EAGAIN) {
+			nfnl_err_reset(&err_list);
+			kfree_skb(skb);
+			module_put(ss->owner);
+			status |= NFNL_BATCH_FAILURE;
+			goto replay_abort;
+		}
 	}
 	if (ss->cleanup)
 		ss->cleanup(net);
-- 
cgit v1.2.3


From 77f6c0b87479c4578ac0798fc249637092ac45a3 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 24 Sep 2020 12:30:50 +0200
Subject: timekeeping: remove arch_gettimeoffset

With Arm EBSA110 gone, nothing uses it any more, so the corresponding
code and the Kconfig option can be removed.

Acked-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 .../time/modern-timekeeping/arch-support.txt       | 33 ----------------------
 drivers/Makefile                                   |  2 --
 drivers/clocksource/Kconfig                        |  2 +-
 include/linux/time.h                               | 13 ---------
 kernel/time/Kconfig                                |  9 ------
 kernel/time/clocksource.c                          |  8 ------
 kernel/time/timekeeping.c                          | 25 +---------------
 kernel/trace/Kconfig                               |  2 --
 8 files changed, 2 insertions(+), 92 deletions(-)
 delete mode 100644 Documentation/features/time/modern-timekeeping/arch-support.txt

(limited to 'include/linux')

diff --git a/Documentation/features/time/modern-timekeeping/arch-support.txt b/Documentation/features/time/modern-timekeeping/arch-support.txt
deleted file mode 100644
index a84c3b9d9a94..000000000000
--- a/Documentation/features/time/modern-timekeeping/arch-support.txt
+++ /dev/null
@@ -1,33 +0,0 @@
-#
-# Feature name:          modern-timekeeping
-#         Kconfig:       !ARCH_USES_GETTIMEOFFSET
-#         description:   arch does not use arch_gettimeoffset() anymore
-#
-    -----------------------
-    |         arch |status|
-    -----------------------
-    |       alpha: |  ok  |
-    |         arc: |  ok  |
-    |         arm: | TODO |
-    |       arm64: |  ok  |
-    |         c6x: |  ok  |
-    |        csky: |  ok  |
-    |       h8300: |  ok  |
-    |     hexagon: |  ok  |
-    |        ia64: |  ok  |
-    |        m68k: |  ok  |
-    |  microblaze: |  ok  |
-    |        mips: |  ok  |
-    |       nds32: |  ok  |
-    |       nios2: |  ok  |
-    |    openrisc: |  ok  |
-    |      parisc: |  ok  |
-    |     powerpc: |  ok  |
-    |       riscv: |  ok  |
-    |        s390: |  ok  |
-    |          sh: |  ok  |
-    |       sparc: |  ok  |
-    |          um: |  ok  |
-    |         x86: |  ok  |
-    |      xtensa: |  ok  |
-    -----------------------
diff --git a/drivers/Makefile b/drivers/Makefile
index c0cd1b9075e3..4ff1e4459512 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -135,9 +135,7 @@ obj-$(CONFIG_INFINIBAND)	+= infiniband/
 obj-y				+= firmware/
 obj-$(CONFIG_CRYPTO)		+= crypto/
 obj-$(CONFIG_SUPERH)		+= sh/
-ifndef CONFIG_ARCH_USES_GETTIMEOFFSET
 obj-y				+= clocksource/
-endif
 obj-$(CONFIG_DCA)		+= dca/
 obj-$(CONFIG_HID)		+= hid/
 obj-$(CONFIG_PPC_PS3)		+= ps3/
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 68b087bff59c..764936bfcb2c 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -563,7 +563,7 @@ config CLKSRC_QCOM
 
 config CLKSRC_VERSATILE
 	bool "ARM Versatile (Express) reference platforms clock source" if COMPILE_TEST
-	depends on GENERIC_SCHED_CLOCK && !ARCH_USES_GETTIMEOFFSET
+	depends on GENERIC_SCHED_CLOCK
 	select TIMER_OF
 	default y if (ARCH_VEXPRESS || ARCH_VERSATILE) && ARM
 	help
diff --git a/include/linux/time.h b/include/linux/time.h
index b142cb5f5a53..16cf4522d6f3 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -21,19 +21,6 @@ extern time64_t mktime64(const unsigned int year, const unsigned int mon,
 			const unsigned int day, const unsigned int hour,
 			const unsigned int min, const unsigned int sec);
 
-/* Some architectures do not supply their own clocksource.
- * This is mainly the case in architectures that get their
- * inter-tick times by reading the counter on their interval
- * timer. Since these timers wrap every tick, they're not really
- * useful as clocksources. Wrapping them to act like one is possible
- * but not very efficient. So we provide a callout these arches
- * can implement for use with the jiffies clocksource to provide
- * finer then tick granular time.
- */
-#ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
-extern u32 (*arch_gettimeoffset)(void);
-#endif
-
 #ifdef CONFIG_POSIX_TIMERS
 extern void clear_itimer(void);
 #else
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index a09b1d61df6a..51d298ccbe05 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -26,10 +26,6 @@ config CLOCKSOURCE_VALIDATE_LAST_CYCLE
 config GENERIC_TIME_VSYSCALL
 	bool
 
-# Old style timekeeping
-config ARCH_USES_GETTIMEOFFSET
-	bool
-
 # The generic clock events infrastructure
 config GENERIC_CLOCKEVENTS
 	bool
@@ -72,7 +68,6 @@ config TICK_ONESHOT
 
 config NO_HZ_COMMON
 	bool
-	depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS
 	select TICK_ONESHOT
 
 choice
@@ -87,7 +82,6 @@ config HZ_PERIODIC
 
 config NO_HZ_IDLE
 	bool "Idle dynticks system (tickless idle)"
-	depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS
 	select NO_HZ_COMMON
 	help
 	  This option enables a tickless idle system: timer interrupts
@@ -99,7 +93,6 @@ config NO_HZ_IDLE
 config NO_HZ_FULL
 	bool "Full dynticks system (tickless)"
 	# NO_HZ_COMMON dependency
-	depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS
 	# We need at least one periodic CPU for timekeeping
 	depends on SMP
 	depends on HAVE_CONTEXT_TRACKING
@@ -158,7 +151,6 @@ config CONTEXT_TRACKING_FORCE
 
 config NO_HZ
 	bool "Old Idle dynticks config"
-	depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS
 	help
 	  This is the old config entry that enables dynticks idle.
 	  We keep it around for a little while to enforce backward
@@ -166,7 +158,6 @@ config NO_HZ
 
 config HIGH_RES_TIMERS
 	bool "High Resolution Timer Support"
-	depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS
 	select TICK_ONESHOT
 	help
 	  This option enables high resolution timer support. If your
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 02441ead3c3b..cce484a2cc7c 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -705,8 +705,6 @@ static inline void clocksource_update_max_deferment(struct clocksource *cs)
 						&cs->max_cycles);
 }
 
-#ifndef CONFIG_ARCH_USES_GETTIMEOFFSET
-
 static struct clocksource *clocksource_find_best(bool oneshot, bool skipcur)
 {
 	struct clocksource *cs;
@@ -798,12 +796,6 @@ static void clocksource_select_fallback(void)
 	__clocksource_select(true);
 }
 
-#else /* !CONFIG_ARCH_USES_GETTIMEOFFSET */
-static inline void clocksource_select(void) { }
-static inline void clocksource_select_fallback(void) { }
-
-#endif
-
 /*
  * clocksource_done_booting - Called near the end of core bootup
  *
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 6858a31364b6..52fff7e9edcd 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -369,13 +369,6 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock)
 
 /* Timekeeper helper functions. */
 
-#ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
-static u32 default_arch_gettimeoffset(void) { return 0; }
-u32 (*arch_gettimeoffset)(void) = default_arch_gettimeoffset;
-#else
-static inline u32 arch_gettimeoffset(void) { return 0; }
-#endif
-
 static inline u64 timekeeping_delta_to_ns(const struct tk_read_base *tkr, u64 delta)
 {
 	u64 nsec;
@@ -383,8 +376,7 @@ static inline u64 timekeeping_delta_to_ns(const struct tk_read_base *tkr, u64 de
 	nsec = delta * tkr->mult + tkr->xtime_nsec;
 	nsec >>= tkr->shift;
 
-	/* If arch requires, add in get_arch_timeoffset() */
-	return nsec + arch_gettimeoffset();
+	return nsec;
 }
 
 static inline u64 timekeeping_get_ns(const struct tk_read_base *tkr)
@@ -778,16 +770,8 @@ static void timekeeping_forward_now(struct timekeeper *tk)
 	tk->tkr_raw.cycle_last  = cycle_now;
 
 	tk->tkr_mono.xtime_nsec += delta * tk->tkr_mono.mult;
-
-	/* If arch requires, add in get_arch_timeoffset() */
-	tk->tkr_mono.xtime_nsec += (u64)arch_gettimeoffset() << tk->tkr_mono.shift;
-
-
 	tk->tkr_raw.xtime_nsec += delta * tk->tkr_raw.mult;
 
-	/* If arch requires, add in get_arch_timeoffset() */
-	tk->tkr_raw.xtime_nsec += (u64)arch_gettimeoffset() << tk->tkr_raw.shift;
-
 	tk_normalize_xtime(tk);
 }
 
@@ -2133,19 +2117,12 @@ static void timekeeping_advance(enum timekeeping_adv_mode mode)
 	if (unlikely(timekeeping_suspended))
 		goto out;
 
-#ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
-	offset = real_tk->cycle_interval;
-
-	if (mode != TK_ADV_TICK)
-		goto out;
-#else
 	offset = clocksource_delta(tk_clock_read(&tk->tkr_mono),
 				   tk->tkr_mono.cycle_last, tk->tkr_mono.mask);
 
 	/* Check if there's really nothing to do */
 	if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK)
 		goto out;
-#endif
 
 	/* Do some additional sanity checking */
 	timekeeping_check_update(tk, offset);
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index a4020c0b4508..b74099f990bf 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -253,7 +253,6 @@ config IRQSOFF_TRACER
 	bool "Interrupts-off Latency Tracer"
 	default n
 	depends on TRACE_IRQFLAGS_SUPPORT
-	depends on !ARCH_USES_GETTIMEOFFSET
 	select TRACE_IRQFLAGS
 	select GENERIC_TRACER
 	select TRACER_MAX_TRACE
@@ -277,7 +276,6 @@ config IRQSOFF_TRACER
 config PREEMPT_TRACER
 	bool "Preemption-off Latency Tracer"
 	default n
-	depends on !ARCH_USES_GETTIMEOFFSET
 	depends on PREEMPTION
 	select GENERIC_TRACER
 	select TRACER_MAX_TRACE
-- 
cgit v1.2.3


From b3550164a19d62e515af6cacb5a31f0b2b3f9501 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 24 Sep 2020 15:21:43 +0200
Subject: timekeeping: add CONFIG_LEGACY_TIMER_TICK

All platforms that currently do not use generic clockevents roughly call
the same set of functions in their timer interrupts: xtime_update(),
update_process_times() and profile_tick(), sometimes in a different
sequence.

Add a helper function that performs all three of them, to make the
callers more uniform and simplify the interface.

Reviewed-by: Geert Uytterhoeven <geert@linux-m68k.org>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 include/linux/timekeeping.h |  1 +
 kernel/time/Kconfig         |  7 +++++++
 kernel/time/Makefile        |  1 +
 kernel/time/tick-legacy.c   | 19 +++++++++++++++++++
 4 files changed, 28 insertions(+)
 create mode 100644 kernel/time/tick-legacy.c

(limited to 'include/linux')

diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 7f7e4a3f4394..3670cb1670ff 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -12,6 +12,7 @@ extern int timekeeping_suspended;
 /* Architecture timer tick functions: */
 extern void update_process_times(int user);
 extern void xtime_update(unsigned long ticks);
+extern void legacy_timer_tick(unsigned long ticks);
 
 /*
  * Get and set timeofday
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index 51d298ccbe05..c6867f29d279 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -57,6 +57,13 @@ config POSIX_CPU_TIMERS_TASK_WORK
 	bool
 	default y if POSIX_TIMERS && HAVE_POSIX_CPU_TIMERS_TASK_WORK
 
+config LEGACY_TIMER_TICK
+	bool
+	help
+	  The legacy timer tick helper is used by platforms that
+	  lack support for the generic clockevent framework.
+	  New platforms should use generic clockevents instead.
+
 if GENERIC_CLOCKEVENTS
 menu "Timers subsystem"
 
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index c8f00168afe8..1fb1c1ef6a19 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -16,6 +16,7 @@ ifeq ($(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST),y)
 endif
 obj-$(CONFIG_GENERIC_SCHED_CLOCK)		+= sched_clock.o
 obj-$(CONFIG_TICK_ONESHOT)			+= tick-oneshot.o tick-sched.o
+obj-$(CONFIG_LEGACY_TIMER_TICK)			+= tick-legacy.o
 obj-$(CONFIG_HAVE_GENERIC_VDSO)			+= vsyscall.o
 obj-$(CONFIG_DEBUG_FS)				+= timekeeping_debug.o
 obj-$(CONFIG_TEST_UDELAY)			+= test_udelay.o
diff --git a/kernel/time/tick-legacy.c b/kernel/time/tick-legacy.c
new file mode 100644
index 000000000000..73c5a0af4743
--- /dev/null
+++ b/kernel/time/tick-legacy.c
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Timer tick function for architectures that lack generic clockevents,
+ * consolidated here from m68k/ia64/parisc/arm.
+ */
+
+#include <linux/irq.h>
+#include <linux/profile.h>
+#include <linux/timekeeper_internal.h>
+
+#include "tick-internal.h"
+
+void legacy_timer_tick(unsigned long ticks)
+{
+	if (ticks)
+		xtime_update(ticks);
+	update_process_times(user_mode(get_irq_regs()));
+	profile_tick(CPU_PROFILING);
+}
-- 
cgit v1.2.3


From 56cc7b8acfb7c763f71c0492fa8da01dca7c1760 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 24 Sep 2020 17:39:11 +0200
Subject: timekeeping: remove xtime_update

There are no more users of xtime_update aside from legacy_timer_tick(),
so fold it into that function and remove the declaration.

update_process_times() is now only called inside of the kernel/time/
code, so the declaration can be moved there.

Reviewed-by: Geert Uytterhoeven <geert@linux-m68k.org>
Tested-by: Geert Uytterhoeven <geert@linux-m68k.org>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 include/linux/timekeeping.h |  2 --
 kernel/time/tick-legacy.c   | 22 ++++++++++++++++++++--
 kernel/time/timekeeping.c   | 16 ----------------
 kernel/time/timekeeping.h   |  1 +
 4 files changed, 21 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 3670cb1670ff..d47009611109 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -10,8 +10,6 @@ void timekeeping_init(void);
 extern int timekeeping_suspended;
 
 /* Architecture timer tick functions: */
-extern void update_process_times(int user);
-extern void xtime_update(unsigned long ticks);
 extern void legacy_timer_tick(unsigned long ticks);
 
 /*
diff --git a/kernel/time/tick-legacy.c b/kernel/time/tick-legacy.c
index 73c5a0af4743..af225b32f5b3 100644
--- a/kernel/time/tick-legacy.c
+++ b/kernel/time/tick-legacy.c
@@ -10,10 +10,28 @@
 
 #include "tick-internal.h"
 
+/**
+ * legacy_timer_tick() - advances the timekeeping infrastructure
+ * @ticks:	number of ticks, that have elapsed since the last call.
+ *
+ * This is used by platforms that have not been converted to
+ * generic clockevents.
+ *
+ * If 'ticks' is zero, the CPU is not handling timekeeping, so
+ * only perform process accounting and profiling.
+ *
+ * Must be called with interrupts disabled.
+ */
 void legacy_timer_tick(unsigned long ticks)
 {
-	if (ticks)
-		xtime_update(ticks);
+	if (ticks) {
+		raw_spin_lock(&jiffies_lock);
+		write_seqcount_begin(&jiffies_seq);
+		do_timer(ticks);
+		write_seqcount_end(&jiffies_seq);
+		raw_spin_unlock(&jiffies_lock);
+		update_wall_time();
+	}
 	update_process_times(user_mode(get_irq_regs()));
 	profile_tick(CPU_PROFILING);
 }
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 52fff7e9edcd..daa0ff017819 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -2438,19 +2438,3 @@ void hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts)
 }
 EXPORT_SYMBOL(hardpps);
 #endif /* CONFIG_NTP_PPS */
-
-/**
- * xtime_update() - advances the timekeeping infrastructure
- * @ticks:	number of ticks, that have elapsed since the last call.
- *
- * Must be called with interrupts disabled.
- */
-void xtime_update(unsigned long ticks)
-{
-	raw_spin_lock(&jiffies_lock);
-	write_seqcount_begin(&jiffies_seq);
-	do_timer(ticks);
-	write_seqcount_end(&jiffies_seq);
-	raw_spin_unlock(&jiffies_lock);
-	update_wall_time();
-}
diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h
index 099737f6f10c..d94b69c5b869 100644
--- a/kernel/time/timekeeping.h
+++ b/kernel/time/timekeeping.h
@@ -22,6 +22,7 @@ static inline int sched_clock_suspend(void) { return 0; }
 static inline void sched_clock_resume(void) { }
 #endif
 
+extern void update_process_times(int user);
 extern void do_timer(unsigned long ticks);
 extern void update_wall_time(void);
 
-- 
cgit v1.2.3


From 290562075d4d9e85b7ff4104f9a634ffc3cccb69 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Tue, 27 Oct 2020 15:28:40 -0500
Subject: net/mlx5: Replace zero-length array with flexible-array member
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is a regular need in the kernel to provide a way to declare having a
dynamically sized set of trailing elements in a structure. Kernel code should
always use “flexible array members”[1] for these cases. The older style of
one-element or zero-length arrays should no longer be used[2].

[1] https://en.wikipedia.org/wiki/Flexible_array_member
[2] https://www.kernel.org/doc/html/v5.9/process/deprecated.html#zero-length-and-one-element-arrays

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
---
 include/linux/mlx5/mlx5_ifc.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 651591a2965d..a092346c7b2d 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -5823,7 +5823,7 @@ struct mlx5_ifc_alloc_modify_header_context_in_bits {
 	u8         reserved_at_68[0x10];
 	u8         num_of_actions[0x8];
 
-	union mlx5_ifc_set_add_copy_action_in_auto_bits actions[0];
+	union mlx5_ifc_set_add_copy_action_in_auto_bits actions[];
 };
 
 struct mlx5_ifc_dealloc_modify_header_context_out_bits {
@@ -9761,7 +9761,7 @@ struct mlx5_ifc_mcda_reg_bits {
 
 	u8         reserved_at_60[0x20];
 
-	u8         data[0][0x20];
+	u8         data[][0x20];
 };
 
 enum {
-- 
cgit v1.2.3


From e38d86b354f96e3ed6f5e6c7dbb442d7107fc0bd Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 29 Oct 2020 15:05:08 +0800
Subject: sctp: add the error cause for new encapsulation port restart

This patch is to add the function to make the abort chunk with
the error cause for new encapsulation port restart, defined
on Section 4.4 in draft-tuexen-tsvwg-sctp-udp-encaps-cons-03.

v1->v2:
  - no change.
v2->v3:
  - no need to call htons() when setting nep.cur_port/new_port.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/sctp.h     | 20 ++++++++++++++++++++
 include/net/sctp/sm.h    |  3 +++
 net/sctp/sm_make_chunk.c | 20 ++++++++++++++++++++
 3 files changed, 43 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/sctp.h b/include/linux/sctp.h
index 76731230bbc5..bb1926589693 100644
--- a/include/linux/sctp.h
+++ b/include/linux/sctp.h
@@ -482,11 +482,13 @@ enum sctp_error {
 	 *  11  Restart of an association with new addresses
 	 *  12  User Initiated Abort
 	 *  13  Protocol Violation
+	 *  14  Restart of an Association with New Encapsulation Port
 	 */
 
 	SCTP_ERROR_RESTART         = cpu_to_be16(0x0b),
 	SCTP_ERROR_USER_ABORT      = cpu_to_be16(0x0c),
 	SCTP_ERROR_PROTO_VIOLATION = cpu_to_be16(0x0d),
+	SCTP_ERROR_NEW_ENCAP_PORT  = cpu_to_be16(0x0e),
 
 	/* ADDIP Section 3.3  New Error Causes
 	 *
@@ -793,4 +795,22 @@ enum {
 	SCTP_FLOWLABEL_VAL_MASK = 0xfffff
 };
 
+/* UDP Encapsulation
+ * draft-tuexen-tsvwg-sctp-udp-encaps-cons-03.html#section-4-4
+ *
+ *   The error cause indicating an "Restart of an Association with
+ *   New Encapsulation Port"
+ *
+ * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |        Cause Code = 14        |       Cause Length = 8        |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |   Current Encapsulation Port  |     New Encapsulation Port    |
+ * +-------------------------------+-------------------------------+
+ */
+struct sctp_new_encap_port_hdr {
+	__be16 cur_port;
+	__be16 new_port;
+};
+
 #endif /* __LINUX_SCTP_H__ */
diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h
index a499341472ad..fd223c94589a 100644
--- a/include/net/sctp/sm.h
+++ b/include/net/sctp/sm.h
@@ -221,6 +221,9 @@ struct sctp_chunk *sctp_make_violation_paramlen(
 struct sctp_chunk *sctp_make_violation_max_retrans(
 					const struct sctp_association *asoc,
 					const struct sctp_chunk *chunk);
+struct sctp_chunk *sctp_make_new_encap_port(
+					const struct sctp_association *asoc,
+					const struct sctp_chunk *chunk);
 struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc,
 				       const struct sctp_transport *transport);
 struct sctp_chunk *sctp_make_heartbeat_ack(const struct sctp_association *asoc,
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 21d0ff1c6ab9..f77484df097b 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -1142,6 +1142,26 @@ nodata:
 	return retval;
 }
 
+struct sctp_chunk *sctp_make_new_encap_port(const struct sctp_association *asoc,
+					    const struct sctp_chunk *chunk)
+{
+	struct sctp_new_encap_port_hdr nep;
+	struct sctp_chunk *retval;
+
+	retval = sctp_make_abort(asoc, chunk,
+				 sizeof(struct sctp_errhdr) + sizeof(nep));
+	if (!retval)
+		goto nodata;
+
+	sctp_init_cause(retval, SCTP_ERROR_NEW_ENCAP_PORT, sizeof(nep));
+	nep.cur_port = SCTP_INPUT_CB(chunk->skb)->encap_port;
+	nep.new_port = chunk->transport->encap_port;
+	sctp_addto_chunk(retval, sizeof(nep), &nep);
+
+nodata:
+	return retval;
+}
+
 /* Make a HEARTBEAT chunk.  */
 struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc,
 				       const struct sctp_transport *transport)
-- 
cgit v1.2.3


From 1887023a5e96f98249574e0785b7aa2e5742ca68 Mon Sep 17 00:00:00 2001
From: Robert Hancock <robert.hancock@calian.com>
Date: Wed, 28 Oct 2020 11:15:40 -0600
Subject: net: phy: marvell: add special handling of Finisar modules with
 88E1111

The Finisar FCLF8520P2BTL 1000BaseT SFP module uses a Marvel 88E1111 PHY
with a modified PHY ID. Add support for this ID using the 88E1111
methods.

By default these modules do not have 1000BaseX auto-negotiation enabled,
which is not generally desirable with Linux networking drivers. Add
handling to enable 1000BaseX auto-negotiation when these modules are
used in 1000BaseX mode. Also, some special handling is required to ensure
that 1000BaseT auto-negotiation is enabled properly when desired.

Based on existing handling in the AMD xgbe driver and the information in
the Finisar FAQ:
https://www.finisar.com/sites/default/files/resources/an-2036_1000base-t_sfp_faqreve1.pdf

Signed-off-by: Robert Hancock <robert.hancock@calian.com>
Reviewed-by: Russell King <rmk+kernel@armlinux.org.uk>
Link: https://lore.kernel.org/r/20201028171540.1700032-1-robert.hancock@calian.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/marvell.c   | 100 +++++++++++++++++++++++++++++++++++++++++++-
 include/linux/marvell_phy.h |   3 ++
 2 files changed, 102 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 77540f5d2622..2563526bf4a6 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -80,8 +80,11 @@
 #define MII_M1111_HWCFG_MODE_FIBER_RGMII	0x3
 #define MII_M1111_HWCFG_MODE_SGMII_NO_CLK	0x4
 #define MII_M1111_HWCFG_MODE_RTBI		0x7
+#define MII_M1111_HWCFG_MODE_COPPER_1000X_AN	0x8
 #define MII_M1111_HWCFG_MODE_COPPER_RTBI	0x9
 #define MII_M1111_HWCFG_MODE_COPPER_RGMII	0xb
+#define MII_M1111_HWCFG_MODE_COPPER_1000X_NOAN	0xc
+#define MII_M1111_HWCFG_SERIAL_AN_BYPASS	BIT(12)
 #define MII_M1111_HWCFG_FIBER_COPPER_RES	BIT(13)
 #define MII_M1111_HWCFG_FIBER_COPPER_AUTO	BIT(15)
 
@@ -629,6 +632,51 @@ static int marvell_config_aneg_fiber(struct phy_device *phydev)
 	return genphy_check_and_restart_aneg(phydev, changed);
 }
 
+static int m88e1111_config_aneg(struct phy_device *phydev)
+{
+	int extsr = phy_read(phydev, MII_M1111_PHY_EXT_SR);
+	int err;
+
+	if (extsr < 0)
+		return extsr;
+
+	/* If not using SGMII or copper 1000BaseX modes, use normal process.
+	 * Steps below are only required for these modes.
+	 */
+	if (phydev->interface != PHY_INTERFACE_MODE_SGMII &&
+	    (extsr & MII_M1111_HWCFG_MODE_MASK) !=
+	    MII_M1111_HWCFG_MODE_COPPER_1000X_AN)
+		return marvell_config_aneg(phydev);
+
+	err = marvell_set_page(phydev, MII_MARVELL_COPPER_PAGE);
+	if (err < 0)
+		goto error;
+
+	/* Configure the copper link first */
+	err = marvell_config_aneg(phydev);
+	if (err < 0)
+		goto error;
+
+	/* Do not touch the fiber page if we're in copper->sgmii mode */
+	if (phydev->interface == PHY_INTERFACE_MODE_SGMII)
+		return 0;
+
+	/* Then the fiber link */
+	err = marvell_set_page(phydev, MII_MARVELL_FIBER_PAGE);
+	if (err < 0)
+		goto error;
+
+	err = marvell_config_aneg_fiber(phydev);
+	if (err < 0)
+		goto error;
+
+	return marvell_set_page(phydev, MII_MARVELL_COPPER_PAGE);
+
+error:
+	marvell_set_page(phydev, MII_MARVELL_COPPER_PAGE);
+	return err;
+}
+
 static int m88e1510_config_aneg(struct phy_device *phydev)
 {
 	int err;
@@ -814,6 +862,28 @@ static int m88e1111_config_init_rtbi(struct phy_device *phydev)
 		MII_M1111_HWCFG_FIBER_COPPER_AUTO);
 }
 
+static int m88e1111_config_init_1000basex(struct phy_device *phydev)
+{
+	int extsr = phy_read(phydev, MII_M1111_PHY_EXT_SR);
+	int err, mode;
+
+	if (extsr < 0)
+		return extsr;
+
+	/* If using copper mode, ensure 1000BaseX auto-negotiation is enabled */
+	mode = extsr & MII_M1111_HWCFG_MODE_MASK;
+	if (mode == MII_M1111_HWCFG_MODE_COPPER_1000X_NOAN) {
+		err = phy_modify(phydev, MII_M1111_PHY_EXT_SR,
+				 MII_M1111_HWCFG_MODE_MASK |
+				 MII_M1111_HWCFG_SERIAL_AN_BYPASS,
+				 MII_M1111_HWCFG_MODE_COPPER_1000X_AN |
+				 MII_M1111_HWCFG_SERIAL_AN_BYPASS);
+		if (err < 0)
+			return err;
+	}
+	return 0;
+}
+
 static int m88e1111_config_init(struct phy_device *phydev)
 {
 	int err;
@@ -836,6 +906,12 @@ static int m88e1111_config_init(struct phy_device *phydev)
 			return err;
 	}
 
+	if (phydev->interface == PHY_INTERFACE_MODE_1000BASEX) {
+		err = m88e1111_config_init_1000basex(phydev);
+		if (err < 0)
+			return err;
+	}
+
 	err = marvell_of_reg_init(phydev);
 	if (err < 0)
 		return err;
@@ -2658,7 +2734,28 @@ static struct phy_driver marvell_drivers[] = {
 		/* PHY_GBIT_FEATURES */
 		.probe = marvell_probe,
 		.config_init = m88e1111_config_init,
-		.config_aneg = marvell_config_aneg,
+		.config_aneg = m88e1111_config_aneg,
+		.read_status = marvell_read_status,
+		.ack_interrupt = marvell_ack_interrupt,
+		.config_intr = marvell_config_intr,
+		.resume = genphy_resume,
+		.suspend = genphy_suspend,
+		.read_page = marvell_read_page,
+		.write_page = marvell_write_page,
+		.get_sset_count = marvell_get_sset_count,
+		.get_strings = marvell_get_strings,
+		.get_stats = marvell_get_stats,
+		.get_tunable = m88e1111_get_tunable,
+		.set_tunable = m88e1111_set_tunable,
+	},
+	{
+		.phy_id = MARVELL_PHY_ID_88E1111_FINISAR,
+		.phy_id_mask = MARVELL_PHY_ID_MASK,
+		.name = "Marvell 88E1111 (Finisar)",
+		/* PHY_GBIT_FEATURES */
+		.probe = marvell_probe,
+		.config_init = m88e1111_config_init,
+		.config_aneg = m88e1111_config_aneg,
 		.read_status = marvell_read_status,
 		.ack_interrupt = marvell_ack_interrupt,
 		.config_intr = marvell_config_intr,
@@ -2989,6 +3086,7 @@ static struct mdio_device_id __maybe_unused marvell_tbl[] = {
 	{ MARVELL_PHY_ID_88E1101, MARVELL_PHY_ID_MASK },
 	{ MARVELL_PHY_ID_88E1112, MARVELL_PHY_ID_MASK },
 	{ MARVELL_PHY_ID_88E1111, MARVELL_PHY_ID_MASK },
+	{ MARVELL_PHY_ID_88E1111_FINISAR, MARVELL_PHY_ID_MASK },
 	{ MARVELL_PHY_ID_88E1118, MARVELL_PHY_ID_MASK },
 	{ MARVELL_PHY_ID_88E1121R, MARVELL_PHY_ID_MASK },
 	{ MARVELL_PHY_ID_88E1145, MARVELL_PHY_ID_MASK },
diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h
index ff7b7607c8cf..52b1610eae68 100644
--- a/include/linux/marvell_phy.h
+++ b/include/linux/marvell_phy.h
@@ -25,6 +25,9 @@
 #define MARVELL_PHY_ID_88X3310		0x002b09a0
 #define MARVELL_PHY_ID_88E2110		0x002b09b0
 
+/* Marvel 88E1111 in Finisar SFP module with modified PHY ID */
+#define MARVELL_PHY_ID_88E1111_FINISAR	0x01ff0cc0
+
 /* The MV88e6390 Ethernet switch contains embedded PHYs. These PHYs do
  * not have a model ID. So the switch driver traps reads to the ID2
  * register and returns the switch family ID
-- 
cgit v1.2.3


From 955062b03fa62b802a1ee34fbb04e39f7a70ae73 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@nvidia.com>
Date: Thu, 29 Oct 2020 01:38:31 +0200
Subject: net: bridge: mcast: add support for raw L2 multicast groups

Extend the bridge multicast control and data path to configure routes
for L2 (non-IP) multicast groups.

The uapi struct br_mdb_entry union u is extended with another variant,
mac_addr, which does not change the structure size, and which is valid
when the proto field is zero.

To be compatible with the forwarding code that is already in place,
which acts as an IGMP/MLD snooping bridge with querier capabilities, we
need to declare that for L2 MDB entries (for which there exists no such
thing as IGMP/MLD snooping/querying), that there is always a querier.
Otherwise, these entries would be flooded to all bridge ports and not
just to those that are members of the L2 multicast group.

Needless to say, only permanent L2 multicast groups can be installed on
a bridge port.

Signed-off-by: Nikolay Aleksandrov <nikolay@nvidia.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://lore.kernel.org/r/20201028233831.610076-1-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/if_bridge.h      |  1 +
 include/uapi/linux/if_bridge.h |  1 +
 net/bridge/br_device.c         |  2 +-
 net/bridge/br_input.c          |  2 +-
 net/bridge/br_mdb.c            | 24 ++++++++++++++++++++++--
 net/bridge/br_multicast.c      | 13 +++++++++----
 net/bridge/br_private.h        | 10 ++++++++--
 7 files changed, 43 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index 556caed00258..b979005ea39c 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -25,6 +25,7 @@ struct br_ip {
 #if IS_ENABLED(CONFIG_IPV6)
 		struct in6_addr ip6;
 #endif
+		unsigned char	mac_addr[ETH_ALEN];
 	} dst;
 	__be16		proto;
 	__u16           vid;
diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h
index d975e1223884..13d59c51ef5b 100644
--- a/include/uapi/linux/if_bridge.h
+++ b/include/uapi/linux/if_bridge.h
@@ -651,6 +651,7 @@ struct br_mdb_entry {
 		union {
 			__be32	ip4;
 			struct in6_addr ip6;
+			unsigned char mac_addr[ETH_ALEN];
 		} u;
 		__be16		proto;
 	} addr;
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 9b5d62744acc..2400a66fe76e 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -93,7 +93,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 
 		mdst = br_mdb_get(br, skb, vid);
 		if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) &&
-		    br_multicast_querier_exists(br, eth_hdr(skb)))
+		    br_multicast_querier_exists(br, eth_hdr(skb), mdst))
 			br_multicast_flood(mdst, skb, false, true);
 		else
 			br_flood(br, skb, BR_PKT_MULTICAST, false, true);
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index bece03bf83c4..21808985f268 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -134,7 +134,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
 	case BR_PKT_MULTICAST:
 		mdst = br_mdb_get(br, skb, vid);
 		if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) &&
-		    br_multicast_querier_exists(br, eth_hdr(skb))) {
+		    br_multicast_querier_exists(br, eth_hdr(skb), mdst)) {
 			if ((mdst && mdst->host_joined) ||
 			    br_multicast_is_router(br)) {
 				local_rcv = true;
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index e15bab19a012..3c8863418d0b 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -87,6 +87,8 @@ static void __mdb_entry_to_br_ip(struct br_mdb_entry *entry, struct br_ip *ip,
 			ip->src.ip6 = nla_get_in6_addr(mdb_attrs[MDBE_ATTR_SOURCE]);
 		break;
 #endif
+	default:
+		ether_addr_copy(ip->dst.mac_addr, entry->addr.u.mac_addr);
 	}
 
 }
@@ -174,9 +176,11 @@ static int __mdb_fill_info(struct sk_buff *skb,
 	if (mp->addr.proto == htons(ETH_P_IP))
 		e.addr.u.ip4 = mp->addr.dst.ip4;
 #if IS_ENABLED(CONFIG_IPV6)
-	if (mp->addr.proto == htons(ETH_P_IPV6))
+	else if (mp->addr.proto == htons(ETH_P_IPV6))
 		e.addr.u.ip6 = mp->addr.dst.ip6;
 #endif
+	else
+		ether_addr_copy(e.addr.u.mac_addr, mp->addr.dst.mac_addr);
 	e.addr.proto = mp->addr.proto;
 	nest_ent = nla_nest_start_noflag(skb,
 					 MDBA_MDB_ENTRY_INFO);
@@ -210,6 +214,8 @@ static int __mdb_fill_info(struct sk_buff *skb,
 		}
 		break;
 #endif
+	default:
+		ether_addr_copy(e.addr.u.mac_addr, mp->addr.dst.mac_addr);
 	}
 	if (p) {
 		if (nla_put_u8(skb, MDBA_MDB_EATTR_RTPROT, p->rt_protocol))
@@ -562,9 +568,12 @@ void br_mdb_notify(struct net_device *dev,
 		if (mp->addr.proto == htons(ETH_P_IP))
 			ip_eth_mc_map(mp->addr.dst.ip4, mdb.addr);
 #if IS_ENABLED(CONFIG_IPV6)
-		else
+		else if (mp->addr.proto == htons(ETH_P_IPV6))
 			ipv6_eth_mc_map(&mp->addr.dst.ip6, mdb.addr);
 #endif
+		else
+			ether_addr_copy(mdb.addr, mp->addr.dst.mac_addr);
+
 		mdb.obj.orig_dev = pg->key.port->dev;
 		switch (type) {
 		case RTM_NEWMDB:
@@ -693,6 +702,12 @@ static bool is_valid_mdb_entry(struct br_mdb_entry *entry,
 			return false;
 		}
 #endif
+	} else if (entry->addr.proto == 0) {
+		/* L2 mdb */
+		if (!is_multicast_ether_addr(entry->addr.u.mac_addr)) {
+			NL_SET_ERR_MSG_MOD(extack, "L2 entry group is not multicast");
+			return false;
+		}
 	} else {
 		NL_SET_ERR_MSG_MOD(extack, "Unknown entry protocol");
 		return false;
@@ -849,6 +864,11 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
 		}
 	}
 
+	if (br_group_is_l2(&group) && entry->state != MDB_PERMANENT) {
+		NL_SET_ERR_MSG_MOD(extack, "Only permanent L2 entries allowed");
+		return -EINVAL;
+	}
+
 	mp = br_mdb_ip_get(br, &group);
 	if (!mp) {
 		mp = br_multicast_new_group(br, &group);
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index eae898c3cff7..484820c223a3 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -179,7 +179,8 @@ struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br,
 		break;
 #endif
 	default:
-		return NULL;
+		ip.proto = 0;
+		ether_addr_copy(ip.dst.mac_addr, eth_hdr(skb)->h_dest);
 	}
 
 	return br_mdb_ip_get_rcu(br, &ip);
@@ -1203,6 +1204,10 @@ void br_multicast_host_join(struct net_bridge_mdb_entry *mp, bool notify)
 		if (notify)
 			br_mdb_notify(mp->br->dev, mp, NULL, RTM_NEWMDB);
 	}
+
+	if (br_group_is_l2(&mp->addr))
+		return;
+
 	mod_timer(&mp->timer, jiffies + mp->br->multicast_membership_interval);
 }
 
@@ -1254,8 +1259,8 @@ __br_multicast_add_group(struct net_bridge *br,
 			break;
 	}
 
-	p = br_multicast_new_port_group(port, group, *pp, 0, src, filter_mode,
-					RTPROT_KERNEL);
+	p = br_multicast_new_port_group(port, group, *pp, 0, src,
+					filter_mode, RTPROT_KERNEL);
 	if (unlikely(!p)) {
 		p = ERR_PTR(-ENOMEM);
 		goto out;
@@ -3690,7 +3695,7 @@ bool br_multicast_has_querier_anywhere(struct net_device *dev, int proto)
 	memset(&eth, 0, sizeof(eth));
 	eth.h_proto = htons(proto);
 
-	ret = br_multicast_querier_exists(br, &eth);
+	ret = br_multicast_querier_exists(br, &eth, NULL);
 
 unlock:
 	rcu_read_unlock();
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 905d406a2fc7..4c691c371884 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -854,6 +854,11 @@ void br_multicast_star_g_handle_mode(struct net_bridge_port_group *pg,
 void br_multicast_sg_add_exclude_ports(struct net_bridge_mdb_entry *star_mp,
 				       struct net_bridge_port_group *sg);
 
+static inline bool br_group_is_l2(const struct br_ip *group)
+{
+	return group->proto == 0;
+}
+
 #define mlock_dereference(X, br) \
 	rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock))
 
@@ -885,7 +890,8 @@ __br_multicast_querier_exists(struct net_bridge *br,
 }
 
 static inline bool br_multicast_querier_exists(struct net_bridge *br,
-					       struct ethhdr *eth)
+					       struct ethhdr *eth,
+					       const struct net_bridge_mdb_entry *mdb)
 {
 	switch (eth->h_proto) {
 	case (htons(ETH_P_IP)):
@@ -897,7 +903,7 @@ static inline bool br_multicast_querier_exists(struct net_bridge *br,
 			&br->ip6_other_query, true);
 #endif
 	default:
-		return false;
+		return !!mdb && br_group_is_l2(&mdb->addr);
 	}
 }
 
-- 
cgit v1.2.3


From ccf0a4b7fc688561428290265e4effde41446668 Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@netfilter.org>
Date: Thu, 29 Oct 2020 16:39:48 +0100
Subject: netfilter: ipset: Add bucketsize parameter to all hash types

The parameter defines the upper limit in any hash bucket at adding new entries
from userspace - if the limit would be exceeded, ipset doubles the hash size
and rehashes. It means the set may consume more memory but gives faster
evaluation at matching in the set.

Signed-off-by: Jozsef Kadlecsik <kadlec@netfilter.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/ipset/ip_set.h       |  5 ++++
 include/uapi/linux/netfilter/ipset/ip_set.h  |  4 ++-
 net/netfilter/ipset/ip_set_core.c            |  2 ++
 net/netfilter/ipset/ip_set_hash_gen.h        | 38 +++++++++++++++++-----------
 net/netfilter/ipset/ip_set_hash_ip.c         |  6 +++--
 net/netfilter/ipset/ip_set_hash_ipmac.c      |  5 ++--
 net/netfilter/ipset/ip_set_hash_ipmark.c     |  6 +++--
 net/netfilter/ipset/ip_set_hash_ipport.c     |  6 +++--
 net/netfilter/ipset/ip_set_hash_ipportip.c   |  6 +++--
 net/netfilter/ipset/ip_set_hash_ipportnet.c  |  6 +++--
 net/netfilter/ipset/ip_set_hash_mac.c        |  5 ++--
 net/netfilter/ipset/ip_set_hash_net.c        |  6 +++--
 net/netfilter/ipset/ip_set_hash_netiface.c   |  6 +++--
 net/netfilter/ipset/ip_set_hash_netnet.c     |  6 +++--
 net/netfilter/ipset/ip_set_hash_netport.c    |  6 +++--
 net/netfilter/ipset/ip_set_hash_netportnet.c |  6 +++--
 16 files changed, 79 insertions(+), 40 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index ab192720e2d6..46d9a0c26c67 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -198,6 +198,9 @@ struct ip_set_region {
 	u32 elements;		/* Number of elements vs timeout */
 };
 
+/* The max revision number supported by any set type + 1 */
+#define IPSET_REVISION_MAX	9
+
 /* The core set type structure */
 struct ip_set_type {
 	struct list_head list;
@@ -215,6 +218,8 @@ struct ip_set_type {
 	u8 family;
 	/* Type revisions */
 	u8 revision_min, revision_max;
+	/* Revision-specific supported (create) flags */
+	u8 create_flags[IPSET_REVISION_MAX+1];
 	/* Set features to control swapping */
 	u16 features;
 
diff --git a/include/uapi/linux/netfilter/ipset/ip_set.h b/include/uapi/linux/netfilter/ipset/ip_set.h
index 11a72a938eb1..398f7b909b7d 100644
--- a/include/uapi/linux/netfilter/ipset/ip_set.h
+++ b/include/uapi/linux/netfilter/ipset/ip_set.h
@@ -96,7 +96,7 @@ enum {
 	IPSET_ATTR_HASHSIZE,
 	IPSET_ATTR_MAXELEM,
 	IPSET_ATTR_NETMASK,
-	IPSET_ATTR_PROBES,
+	IPSET_ATTR_BUCKETSIZE,	/* was unused IPSET_ATTR_PROBES */
 	IPSET_ATTR_RESIZE,
 	IPSET_ATTR_SIZE,
 	/* Kernel-only */
@@ -214,6 +214,8 @@ enum ipset_cadt_flags {
 enum ipset_create_flags {
 	IPSET_CREATE_FLAG_BIT_FORCEADD = 0,
 	IPSET_CREATE_FLAG_FORCEADD = (1 << IPSET_CREATE_FLAG_BIT_FORCEADD),
+	IPSET_CREATE_FLAG_BIT_BUCKETSIZE = 1,
+	IPSET_CREATE_FLAG_BUCKETSIZE = (1 << IPSET_CREATE_FLAG_BIT_BUCKETSIZE),
 	IPSET_CREATE_FLAG_BIT_MAX = 7,
 };
 
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index e3c00dacec5c..e76bfca2d3ef 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -1109,6 +1109,8 @@ static int ip_set_create(struct net *net, struct sock *ctnl,
 		ret = -IPSET_ERR_PROTOCOL;
 		goto put_out;
 	}
+	/* Set create flags depending on the type revision */
+	set->flags |= set->type->create_flags[revision];
 
 	ret = set->type->create(net, set, tb, flags);
 	if (ret != 0)
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index 521e970be402..4e3544442b26 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -37,18 +37,18 @@
  */
 
 /* Number of elements to store in an initial array block */
-#define AHASH_INIT_SIZE			4
+#define AHASH_INIT_SIZE			2
 /* Max number of elements to store in an array block */
-#define AHASH_MAX_SIZE			(3 * AHASH_INIT_SIZE)
+#define AHASH_MAX_SIZE			(6 * AHASH_INIT_SIZE)
 /* Max muber of elements in the array block when tuned */
 #define AHASH_MAX_TUNED			64
 
+#define AHASH_MAX(h)			((h)->bucketsize)
+
 /* Max number of elements can be tuned */
 #ifdef IP_SET_HASH_WITH_MULTI
-#define AHASH_MAX(h)			((h)->ahash_max)
-
 static u8
-tune_ahash_max(u8 curr, u32 multi)
+tune_bucketsize(u8 curr, u32 multi)
 {
 	u32 n;
 
@@ -61,12 +61,10 @@ tune_ahash_max(u8 curr, u32 multi)
 	 */
 	return n > curr && n <= AHASH_MAX_TUNED ? n : curr;
 }
-
-#define TUNE_AHASH_MAX(h, multi)	\
-	((h)->ahash_max = tune_ahash_max((h)->ahash_max, multi))
+#define TUNE_BUCKETSIZE(h, multi)	\
+	((h)->bucketsize = tune_bucketsize((h)->bucketsize, multi))
 #else
-#define AHASH_MAX(h)			AHASH_MAX_SIZE
-#define TUNE_AHASH_MAX(h, multi)
+#define TUNE_BUCKETSIZE(h, multi)
 #endif
 
 /* A hash bucket */
@@ -321,9 +319,7 @@ struct htype {
 #ifdef IP_SET_HASH_WITH_MARKMASK
 	u32 markmask;		/* markmask value for mark mask to store */
 #endif
-#ifdef IP_SET_HASH_WITH_MULTI
-	u8 ahash_max;		/* max elements in an array block */
-#endif
+	u8 bucketsize;		/* max elements in an array block */
 #ifdef IP_SET_HASH_WITH_NETMASK
 	u8 netmask;		/* netmask value for subnets to store */
 #endif
@@ -950,7 +946,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 		goto set_full;
 	/* Create a new slot */
 	if (n->pos >= n->size) {
-		TUNE_AHASH_MAX(h, multi);
+		TUNE_BUCKETSIZE(h, multi);
 		if (n->size >= AHASH_MAX(h)) {
 			/* Trigger rehashing */
 			mtype_data_next(&h->next, d);
@@ -1305,6 +1301,9 @@ mtype_head(struct ip_set *set, struct sk_buff *skb)
 	if (nla_put_u32(skb, IPSET_ATTR_MARKMASK, h->markmask))
 		goto nla_put_failure;
 #endif
+	if (set->flags & IPSET_CREATE_FLAG_BUCKETSIZE &&
+	    nla_put_u8(skb, IPSET_ATTR_BUCKETSIZE, h->bucketsize))
+		goto nla_put_failure;
 	if (nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref)) ||
 	    nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)) ||
 	    nla_put_net32(skb, IPSET_ATTR_ELEMENTS, htonl(elements)))
@@ -1548,7 +1547,16 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set,
 	h->markmask = markmask;
 #endif
 	get_random_bytes(&h->initval, sizeof(h->initval));
-
+	h->bucketsize = AHASH_MAX_SIZE;
+	if (tb[IPSET_ATTR_BUCKETSIZE]) {
+		h->bucketsize = nla_get_u8(tb[IPSET_ATTR_BUCKETSIZE]);
+		if (h->bucketsize < AHASH_INIT_SIZE)
+			h->bucketsize = AHASH_INIT_SIZE;
+		else if (h->bucketsize > AHASH_MAX_SIZE)
+			h->bucketsize = AHASH_MAX_SIZE;
+		else if (h->bucketsize % 2)
+			h->bucketsize += 1;
+	}
 	t->htable_bits = hbits;
 	t->maxelem = h->maxelem / ahash_numof_locks(hbits);
 	RCU_INIT_POINTER(h->table, t);
diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c
index 5d6d68eaf6a9..0495d515c498 100644
--- a/net/netfilter/ipset/ip_set_hash_ip.c
+++ b/net/netfilter/ipset/ip_set_hash_ip.c
@@ -23,7 +23,8 @@
 /*				1	   Counters support */
 /*				2	   Comments support */
 /*				3	   Forceadd support */
-#define IPSET_TYPE_REV_MAX	4	/* skbinfo support  */
+/*				4	   skbinfo support */
+#define IPSET_TYPE_REV_MAX	5	/* bucketsize support  */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>");
@@ -277,11 +278,12 @@ static struct ip_set_type hash_ip_type __read_mostly = {
 	.family		= NFPROTO_UNSPEC,
 	.revision_min	= IPSET_TYPE_REV_MIN,
 	.revision_max	= IPSET_TYPE_REV_MAX,
+	.create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
 	.create		= hash_ip_create,
 	.create_policy	= {
 		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
 		[IPSET_ATTR_MAXELEM]	= { .type = NLA_U32 },
-		[IPSET_ATTR_PROBES]	= { .type = NLA_U8 },
+		[IPSET_ATTR_BUCKETSIZE]	= { .type = NLA_U8 },
 		[IPSET_ATTR_RESIZE]	= { .type = NLA_U8  },
 		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
 		[IPSET_ATTR_NETMASK]	= { .type = NLA_U8  },
diff --git a/net/netfilter/ipset/ip_set_hash_ipmac.c b/net/netfilter/ipset/ip_set_hash_ipmac.c
index eceb7bc4a93a..2655501f9fe3 100644
--- a/net/netfilter/ipset/ip_set_hash_ipmac.c
+++ b/net/netfilter/ipset/ip_set_hash_ipmac.c
@@ -23,7 +23,7 @@
 #include <linux/netfilter/ipset/ip_set_hash.h>
 
 #define IPSET_TYPE_REV_MIN	0
-#define IPSET_TYPE_REV_MAX	0
+#define IPSET_TYPE_REV_MAX	1	/* bucketsize support  */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Tomasz Chilinski <tomasz.chilinski@chilan.com>");
@@ -268,11 +268,12 @@ static struct ip_set_type hash_ipmac_type __read_mostly = {
 	.family		= NFPROTO_UNSPEC,
 	.revision_min	= IPSET_TYPE_REV_MIN,
 	.revision_max	= IPSET_TYPE_REV_MAX,
+	.create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
 	.create		= hash_ipmac_create,
 	.create_policy	= {
 		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
 		[IPSET_ATTR_MAXELEM]	= { .type = NLA_U32 },
-		[IPSET_ATTR_PROBES]	= { .type = NLA_U8 },
+		[IPSET_ATTR_BUCKETSIZE]	= { .type = NLA_U8 },
 		[IPSET_ATTR_RESIZE]	= { .type = NLA_U8  },
 		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
 		[IPSET_ATTR_CADT_FLAGS]	= { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_ipmark.c b/net/netfilter/ipset/ip_set_hash_ipmark.c
index aba1df617d6e..5bbed85d0e47 100644
--- a/net/netfilter/ipset/ip_set_hash_ipmark.c
+++ b/net/netfilter/ipset/ip_set_hash_ipmark.c
@@ -21,7 +21,8 @@
 
 #define IPSET_TYPE_REV_MIN	0
 /*				1	   Forceadd support */
-#define IPSET_TYPE_REV_MAX	2	/* skbinfo support  */
+/*				2	   skbinfo support */
+#define IPSET_TYPE_REV_MAX	3	/* bucketsize support  */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Vytas Dauksa <vytas.dauksa@smoothwall.net>");
@@ -274,12 +275,13 @@ static struct ip_set_type hash_ipmark_type __read_mostly = {
 	.family		= NFPROTO_UNSPEC,
 	.revision_min	= IPSET_TYPE_REV_MIN,
 	.revision_max	= IPSET_TYPE_REV_MAX,
+	.create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
 	.create		= hash_ipmark_create,
 	.create_policy	= {
 		[IPSET_ATTR_MARKMASK]	= { .type = NLA_U32 },
 		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
 		[IPSET_ATTR_MAXELEM]	= { .type = NLA_U32 },
-		[IPSET_ATTR_PROBES]	= { .type = NLA_U8 },
+		[IPSET_ATTR_BUCKETSIZE]	= { .type = NLA_U8 },
 		[IPSET_ATTR_RESIZE]	= { .type = NLA_U8  },
 		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
 		[IPSET_ATTR_CADT_FLAGS]	= { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c
index 1ff228717e29..c1ac2e89e2d3 100644
--- a/net/netfilter/ipset/ip_set_hash_ipport.c
+++ b/net/netfilter/ipset/ip_set_hash_ipport.c
@@ -25,7 +25,8 @@
 /*				2    Counters support added */
 /*				3    Comments support added */
 /*				4    Forceadd support added */
-#define IPSET_TYPE_REV_MAX	5 /* skbinfo support added */
+/*				5    skbinfo support added */
+#define IPSET_TYPE_REV_MAX	6 /* bucketsize support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>");
@@ -341,11 +342,12 @@ static struct ip_set_type hash_ipport_type __read_mostly = {
 	.family		= NFPROTO_UNSPEC,
 	.revision_min	= IPSET_TYPE_REV_MIN,
 	.revision_max	= IPSET_TYPE_REV_MAX,
+	.create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
 	.create		= hash_ipport_create,
 	.create_policy	= {
 		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
 		[IPSET_ATTR_MAXELEM]	= { .type = NLA_U32 },
-		[IPSET_ATTR_PROBES]	= { .type = NLA_U8 },
+		[IPSET_ATTR_BUCKETSIZE]	= { .type = NLA_U8 },
 		[IPSET_ATTR_RESIZE]	= { .type = NLA_U8  },
 		[IPSET_ATTR_PROTO]	= { .type = NLA_U8 },
 		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c
index fa88afd812fa..d3f4a672986e 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportip.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportip.c
@@ -25,7 +25,8 @@
 /*				2    Counters support added */
 /*				3    Comments support added */
 /*				4    Forceadd support added */
-#define IPSET_TYPE_REV_MAX	5 /* skbinfo support added */
+/*				5    skbinfo support added */
+#define IPSET_TYPE_REV_MAX	6 /* bucketsize support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>");
@@ -356,11 +357,12 @@ static struct ip_set_type hash_ipportip_type __read_mostly = {
 	.family		= NFPROTO_UNSPEC,
 	.revision_min	= IPSET_TYPE_REV_MIN,
 	.revision_max	= IPSET_TYPE_REV_MAX,
+	.create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
 	.create		= hash_ipportip_create,
 	.create_policy	= {
 		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
 		[IPSET_ATTR_MAXELEM]	= { .type = NLA_U32 },
-		[IPSET_ATTR_PROBES]	= { .type = NLA_U8 },
+		[IPSET_ATTR_BUCKETSIZE]	= { .type = NLA_U8 },
 		[IPSET_ATTR_RESIZE]	= { .type = NLA_U8  },
 		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
 		[IPSET_ATTR_CADT_FLAGS]	= { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c
index eef6ecfcb409..8f7fe360736a 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c
@@ -27,7 +27,8 @@
 /*				4    Counters support added */
 /*				5    Comments support added */
 /*				6    Forceadd support added */
-#define IPSET_TYPE_REV_MAX	7 /* skbinfo support added */
+/*				7    skbinfo support added */
+#define IPSET_TYPE_REV_MAX	8 /* bucketsize support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>");
@@ -513,11 +514,12 @@ static struct ip_set_type hash_ipportnet_type __read_mostly = {
 	.family		= NFPROTO_UNSPEC,
 	.revision_min	= IPSET_TYPE_REV_MIN,
 	.revision_max	= IPSET_TYPE_REV_MAX,
+	.create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
 	.create		= hash_ipportnet_create,
 	.create_policy	= {
 		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
 		[IPSET_ATTR_MAXELEM]	= { .type = NLA_U32 },
-		[IPSET_ATTR_PROBES]	= { .type = NLA_U8 },
+		[IPSET_ATTR_BUCKETSIZE]	= { .type = NLA_U8 },
 		[IPSET_ATTR_RESIZE]	= { .type = NLA_U8  },
 		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
 		[IPSET_ATTR_CADT_FLAGS]	= { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_mac.c b/net/netfilter/ipset/ip_set_hash_mac.c
index 0b61593165ef..00dd7e20df3c 100644
--- a/net/netfilter/ipset/ip_set_hash_mac.c
+++ b/net/netfilter/ipset/ip_set_hash_mac.c
@@ -16,7 +16,7 @@
 #include <linux/netfilter/ipset/ip_set_hash.h>
 
 #define IPSET_TYPE_REV_MIN	0
-#define IPSET_TYPE_REV_MAX	0
+#define IPSET_TYPE_REV_MAX	1	/* bucketsize support */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>");
@@ -125,11 +125,12 @@ static struct ip_set_type hash_mac_type __read_mostly = {
 	.family		= NFPROTO_UNSPEC,
 	.revision_min	= IPSET_TYPE_REV_MIN,
 	.revision_max	= IPSET_TYPE_REV_MAX,
+	.create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
 	.create		= hash_mac_create,
 	.create_policy	= {
 		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
 		[IPSET_ATTR_MAXELEM]	= { .type = NLA_U32 },
-		[IPSET_ATTR_PROBES]	= { .type = NLA_U8 },
+		[IPSET_ATTR_BUCKETSIZE]	= { .type = NLA_U8 },
 		[IPSET_ATTR_RESIZE]	= { .type = NLA_U8  },
 		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
 		[IPSET_ATTR_CADT_FLAGS]	= { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c
index 136cf0781d3a..d366e816b6ed 100644
--- a/net/netfilter/ipset/ip_set_hash_net.c
+++ b/net/netfilter/ipset/ip_set_hash_net.c
@@ -24,7 +24,8 @@
 /*				3    Counters support added */
 /*				4    Comments support added */
 /*				5    Forceadd support added */
-#define IPSET_TYPE_REV_MAX	6 /* skbinfo mapping support added */
+/*				6    skbinfo support added */
+#define IPSET_TYPE_REV_MAX	7 /* bucketsize support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>");
@@ -354,11 +355,12 @@ static struct ip_set_type hash_net_type __read_mostly = {
 	.family		= NFPROTO_UNSPEC,
 	.revision_min	= IPSET_TYPE_REV_MIN,
 	.revision_max	= IPSET_TYPE_REV_MAX,
+	.create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
 	.create		= hash_net_create,
 	.create_policy	= {
 		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
 		[IPSET_ATTR_MAXELEM]	= { .type = NLA_U32 },
-		[IPSET_ATTR_PROBES]	= { .type = NLA_U8 },
+		[IPSET_ATTR_BUCKETSIZE]	= { .type = NLA_U8 },
 		[IPSET_ATTR_RESIZE]	= { .type = NLA_U8  },
 		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
 		[IPSET_ATTR_CADT_FLAGS]	= { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c
index be5e95a0d876..38b1d77584d4 100644
--- a/net/netfilter/ipset/ip_set_hash_netiface.c
+++ b/net/netfilter/ipset/ip_set_hash_netiface.c
@@ -26,7 +26,8 @@
 /*				4    Comments support added */
 /*				5    Forceadd support added */
 /*				6    skbinfo support added */
-#define IPSET_TYPE_REV_MAX	7 /* interface wildcard support added */
+/*				7    interface wildcard support added */
+#define IPSET_TYPE_REV_MAX	8 /* bucketsize support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>");
@@ -470,11 +471,12 @@ static struct ip_set_type hash_netiface_type __read_mostly = {
 	.family		= NFPROTO_UNSPEC,
 	.revision_min	= IPSET_TYPE_REV_MIN,
 	.revision_max	= IPSET_TYPE_REV_MAX,
+	.create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
 	.create		= hash_netiface_create,
 	.create_policy	= {
 		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
 		[IPSET_ATTR_MAXELEM]	= { .type = NLA_U32 },
-		[IPSET_ATTR_PROBES]	= { .type = NLA_U8 },
+		[IPSET_ATTR_BUCKETSIZE]	= { .type = NLA_U8 },
 		[IPSET_ATTR_RESIZE]	= { .type = NLA_U8  },
 		[IPSET_ATTR_PROTO]	= { .type = NLA_U8 },
 		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c
index da4ef910b12d..0cc7970f36e9 100644
--- a/net/netfilter/ipset/ip_set_hash_netnet.c
+++ b/net/netfilter/ipset/ip_set_hash_netnet.c
@@ -22,7 +22,8 @@
 
 #define IPSET_TYPE_REV_MIN	0
 /*				1	   Forceadd support added */
-#define IPSET_TYPE_REV_MAX	2	/* skbinfo support added */
+/*				2	   skbinfo support added */
+#define IPSET_TYPE_REV_MAX	3	/* bucketsize support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Oliver Smith <oliver@8.c.9.b.0.7.4.0.1.0.0.2.ip6.arpa>");
@@ -459,11 +460,12 @@ static struct ip_set_type hash_netnet_type __read_mostly = {
 	.family		= NFPROTO_UNSPEC,
 	.revision_min	= IPSET_TYPE_REV_MIN,
 	.revision_max	= IPSET_TYPE_REV_MAX,
+	.create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
 	.create		= hash_netnet_create,
 	.create_policy	= {
 		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
 		[IPSET_ATTR_MAXELEM]	= { .type = NLA_U32 },
-		[IPSET_ATTR_PROBES]	= { .type = NLA_U8 },
+		[IPSET_ATTR_BUCKETSIZE]	= { .type = NLA_U8 },
 		[IPSET_ATTR_RESIZE]	= { .type = NLA_U8  },
 		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
 		[IPSET_ATTR_CADT_FLAGS]	= { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c
index 34448df80fb9..b356d7d85e34 100644
--- a/net/netfilter/ipset/ip_set_hash_netport.c
+++ b/net/netfilter/ipset/ip_set_hash_netport.c
@@ -26,7 +26,8 @@
 /*				4    Counters support added */
 /*				5    Comments support added */
 /*				6    Forceadd support added */
-#define IPSET_TYPE_REV_MAX	7 /* skbinfo support added */
+/*				7    skbinfo support added */
+#define IPSET_TYPE_REV_MAX	8 /* bucketsize support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>");
@@ -460,11 +461,12 @@ static struct ip_set_type hash_netport_type __read_mostly = {
 	.family		= NFPROTO_UNSPEC,
 	.revision_min	= IPSET_TYPE_REV_MIN,
 	.revision_max	= IPSET_TYPE_REV_MAX,
+	.create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
 	.create		= hash_netport_create,
 	.create_policy	= {
 		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
 		[IPSET_ATTR_MAXELEM]	= { .type = NLA_U32 },
-		[IPSET_ATTR_PROBES]	= { .type = NLA_U8 },
+		[IPSET_ATTR_BUCKETSIZE]	= { .type = NLA_U8 },
 		[IPSET_ATTR_RESIZE]	= { .type = NLA_U8  },
 		[IPSET_ATTR_PROTO]	= { .type = NLA_U8 },
 		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c
index 934c1712cba8..eeb39688f26f 100644
--- a/net/netfilter/ipset/ip_set_hash_netportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_netportnet.c
@@ -23,7 +23,8 @@
 #define IPSET_TYPE_REV_MIN	0
 /*				0    Comments support added */
 /*				1    Forceadd support added */
-#define IPSET_TYPE_REV_MAX	2 /* skbinfo support added */
+/*				2    skbinfo support added */
+#define IPSET_TYPE_REV_MAX	3 /* bucketsize support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Oliver Smith <oliver@8.c.9.b.0.7.4.0.1.0.0.2.ip6.arpa>");
@@ -558,11 +559,12 @@ static struct ip_set_type hash_netportnet_type __read_mostly = {
 	.family		= NFPROTO_UNSPEC,
 	.revision_min	= IPSET_TYPE_REV_MIN,
 	.revision_max	= IPSET_TYPE_REV_MAX,
+	.create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
 	.create		= hash_netportnet_create,
 	.create_policy	= {
 		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
 		[IPSET_ATTR_MAXELEM]	= { .type = NLA_U32 },
-		[IPSET_ATTR_PROBES]	= { .type = NLA_U8 },
+		[IPSET_ATTR_BUCKETSIZE]	= { .type = NLA_U8 },
 		[IPSET_ATTR_RESIZE]	= { .type = NLA_U8  },
 		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
 		[IPSET_ATTR_CADT_FLAGS]	= { .type = NLA_U32 },
-- 
cgit v1.2.3


From 3ebc0ef06e4a78522e9d1488dcf61b7d8fcfb792 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Fri, 11 Sep 2020 16:33:42 +0200
Subject: serial: s3c: Update path of Samsung S3C machine file

Correct the path to Samsung S3C24xx machine file, mentioned in
documentation.

Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Link: https://lore.kernel.org/r/20200911143343.498-2-krzk@kernel.org
---
 include/linux/serial_s3c.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/serial_s3c.h b/include/linux/serial_s3c.h
index 463ed28d2b27..ca2c5393dc6b 100644
--- a/include/linux/serial_s3c.h
+++ b/include/linux/serial_s3c.h
@@ -254,7 +254,7 @@
  * serial port
  *
  * the pointer is setup by the machine specific initialisation from the
- * arch/arm/mach-s3c2410/ directory.
+ * arch/arm/mach-s3c/ directory.
 */
 
 struct s3c2410_uartcfg {
-- 
cgit v1.2.3


From 3a096c2bda7d2f0c0866d466447c41bc4b8ecdec Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Fri, 23 Oct 2020 18:33:32 +0200
Subject: iio: fix a kernel-doc markup

A function has a different name between their prototype
and its kernel-doc markup.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Link: https://lore.kernel.org/r/46622c3bdcffb76e79719f0fe5011c2952960b32.1603469755.git.mchehab+huawei@kernel.org
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 include/linux/iio/trigger.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/iio/trigger.h b/include/linux/iio/trigger.h
index cad8325903f9..f930c4ccf378 100644
--- a/include/linux/iio/trigger.h
+++ b/include/linux/iio/trigger.h
@@ -97,7 +97,7 @@ static inline struct iio_trigger *iio_trigger_get(struct iio_trigger *trig)
 }
 
 /**
- * iio_device_set_drvdata() - Set trigger driver data
+ * iio_trigger_set_drvdata() - Set trigger driver data
  * @trig: IIO trigger structure
  * @data: Driver specific data
  *
-- 
cgit v1.2.3


From d3fd65484c78102bac92f176c53537a7691a38b2 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 29 Oct 2020 18:29:59 +0100
Subject: net: core: add dev_sw_netstats_tx_add

Add dev_sw_netstats_tx_add(), complementing already existing
dev_sw_netstats_rx_add(). Other than dev_sw_netstats_rx_add allow to
pass the number of packets as function argument.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 964b494b0e8d..568fab708ac6 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2557,6 +2557,18 @@ static inline void dev_sw_netstats_rx_add(struct net_device *dev, unsigned int l
 	u64_stats_update_end(&tstats->syncp);
 }
 
+static inline void dev_sw_netstats_tx_add(struct net_device *dev,
+					  unsigned int packets,
+					  unsigned int len)
+{
+	struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
+
+	u64_stats_update_begin(&tstats->syncp);
+	tstats->tx_bytes += len;
+	tstats->tx_packets += packets;
+	u64_stats_update_end(&tstats->syncp);
+}
+
 static inline void dev_lstats_add(struct net_device *dev, unsigned int len)
 {
 	struct pcpu_lstats *lstats = this_cpu_ptr(dev->lstats);
-- 
cgit v1.2.3


From 81b01894d792db8d4746c9c1b39c6e2a94fa0a04 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 29 Oct 2020 18:31:21 +0100
Subject: net: core: add devm_netdev_alloc_pcpu_stats

We have netdev_alloc_pcpu_stats(), and we have devm_alloc_percpu().
Add a managed version of netdev_alloc_pcpu_stats, e.g. for allocating
the per-cpu stats in the probe() callback of a driver. It needs to be
a macro for dealing properly with the type argument.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 568fab708ac6..a53ed2d1ed1d 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2596,6 +2596,20 @@ static inline void dev_lstats_add(struct net_device *dev, unsigned int len)
 #define netdev_alloc_pcpu_stats(type)					\
 	__netdev_alloc_pcpu_stats(type, GFP_KERNEL)
 
+#define devm_netdev_alloc_pcpu_stats(dev, type)				\
+({									\
+	typeof(type) __percpu *pcpu_stats = devm_alloc_percpu(dev, type);\
+	if (pcpu_stats) {						\
+		int __cpu;						\
+		for_each_possible_cpu(__cpu) {				\
+			typeof(type) *stat;				\
+			stat = per_cpu_ptr(pcpu_stats, __cpu);		\
+			u64_stats_init(&stat->syncp);			\
+		}							\
+	}								\
+	pcpu_stats;							\
+})
+
 enum netdev_lag_tx_type {
 	NETDEV_LAG_TX_TYPE_UNKNOWN,
 	NETDEV_LAG_TX_TYPE_RANDOM,
-- 
cgit v1.2.3


From 1c552e08b29895d31bbf82bdb549811cfde31db4 Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@ti.com>
Date: Sun, 25 Oct 2020 12:10:02 -0700
Subject: firmware: ti_sci: rm: Add support for tx_tdtype parameter for tx
 channel

The system controller's resource manager have support for configuring the
TDTYPE of TCHAN_CFG register on j721e.
With this parameter the teardown completion can be controlled:
TDTYPE == 0: Return without waiting for peer to complete the teardown
TDTYPE == 1: Wait for peer to complete the teardown

Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Reviewed-by: Tero Kristo <t-kristo@ti.com>
Tested-by: Keerthy <j-keerthy@ti.com>
Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
---
 drivers/firmware/ti_sci.c              | 1 +
 drivers/firmware/ti_sci.h              | 7 +++++++
 include/linux/soc/ti/ti_sci_protocol.h | 2 ++
 3 files changed, 10 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/firmware/ti_sci.c b/drivers/firmware/ti_sci.c
index 896f53ec7857..65a8c2e82093 100644
--- a/drivers/firmware/ti_sci.c
+++ b/drivers/firmware/ti_sci.c
@@ -2362,6 +2362,7 @@ static int ti_sci_cmd_rm_udmap_tx_ch_cfg(const struct ti_sci_handle *handle,
 	req->fdepth = params->fdepth;
 	req->tx_sched_priority = params->tx_sched_priority;
 	req->tx_burst_size = params->tx_burst_size;
+	req->tx_tdtype = params->tx_tdtype;
 
 	ret = ti_sci_do_xfer(info, xfer);
 	if (ret) {
diff --git a/drivers/firmware/ti_sci.h b/drivers/firmware/ti_sci.h
index 57cd04062994..dca19ca5fc49 100644
--- a/drivers/firmware/ti_sci.h
+++ b/drivers/firmware/ti_sci.h
@@ -910,6 +910,7 @@ struct rm_ti_sci_msg_udmap_rx_flow_opt_cfg {
  *   12 - Valid bit for @ref ti_sci_msg_rm_udmap_tx_ch_cfg::tx_credit_count
  *   13 - Valid bit for @ref ti_sci_msg_rm_udmap_tx_ch_cfg::fdepth
  *   14 - Valid bit for @ref ti_sci_msg_rm_udmap_tx_ch_cfg::tx_burst_size
+ *   15 - Valid bit for @ref ti_sci_msg_rm_udmap_tx_ch_cfg::tx_tdtype
  *
  * @nav_id: SoC device ID of Navigator Subsystem where tx channel is located
  *
@@ -973,6 +974,11 @@ struct rm_ti_sci_msg_udmap_rx_flow_opt_cfg {
  *
  * @tx_burst_size: UDMAP transmit channel burst size configuration to be
  * programmed into the tx_burst_size field of the TCHAN_TCFG register.
+ *
+ * @tx_tdtype: UDMAP transmit channel teardown type configuration to be
+ * programmed into the tdtype field of the TCHAN_TCFG register:
+ * 0 - Return immediately
+ * 1 - Wait for completion message from remote peer
  */
 struct ti_sci_msg_rm_udmap_tx_ch_cfg_req {
 	struct ti_sci_msg_hdr hdr;
@@ -994,6 +1000,7 @@ struct ti_sci_msg_rm_udmap_tx_ch_cfg_req {
 	u16 fdepth;
 	u8 tx_sched_priority;
 	u8 tx_burst_size;
+	u8 tx_tdtype;
 } __packed;
 
 /**
diff --git a/include/linux/soc/ti/ti_sci_protocol.h b/include/linux/soc/ti/ti_sci_protocol.h
index cf27b080e148..d254d99fd45b 100644
--- a/include/linux/soc/ti/ti_sci_protocol.h
+++ b/include/linux/soc/ti/ti_sci_protocol.h
@@ -345,6 +345,7 @@ struct ti_sci_msg_rm_udmap_tx_ch_cfg {
 #define TI_SCI_MSG_VALUE_RM_UDMAP_CH_TX_SUPR_TDPKT_VALID        BIT(11)
 #define TI_SCI_MSG_VALUE_RM_UDMAP_CH_TX_CREDIT_COUNT_VALID      BIT(12)
 #define TI_SCI_MSG_VALUE_RM_UDMAP_CH_TX_FDEPTH_VALID            BIT(13)
+#define TI_SCI_MSG_VALUE_RM_UDMAP_CH_TX_TDTYPE_VALID            BIT(15)
 	u16 nav_id;
 	u16 index;
 	u8 tx_pause_on_err;
@@ -362,6 +363,7 @@ struct ti_sci_msg_rm_udmap_tx_ch_cfg {
 	u16 fdepth;
 	u8 tx_sched_priority;
 	u8 tx_burst_size;
+	u8 tx_tdtype;
 };
 
 /**
-- 
cgit v1.2.3


From 967a020bd3deddf9a0af73aeb4d4b46d90030937 Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@ti.com>
Date: Sun, 25 Oct 2020 12:10:03 -0700
Subject: firmware: ti_sci: Use struct ti_sci_resource_desc in get_range ops

Use the ti_sci_resource_desc directly and update it's start and num members
directly instead of requiring individual parameters for them.

This will allow easy extension of the RM parameters without changing API.

Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
---
 drivers/firmware/ti_sci.c              | 32 +++++++++++++++-----------------
 include/linux/soc/ti/ti_sci_protocol.h | 32 ++++++++++++++++----------------
 2 files changed, 31 insertions(+), 33 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/ti_sci.c b/drivers/firmware/ti_sci.c
index 65a8c2e82093..7a777e91ce3e 100644
--- a/drivers/firmware/ti_sci.c
+++ b/drivers/firmware/ti_sci.c
@@ -1703,14 +1703,14 @@ fail:
  * @subtype:		Resource assignment subtype that is being requested
  *			from the given device.
  * @s_host:		Host processor ID to which the resources are allocated
- * @range_start:	Start index of the resource range
- * @range_num:		Number of resources in the range
+ * @desc:		Pointer to ti_sci_resource_desc to be updated with the
+ *			resource range start index and number of resources
  *
  * Return: 0 if all went fine, else return appropriate error.
  */
 static int ti_sci_get_resource_range(const struct ti_sci_handle *handle,
 				     u32 dev_id, u8 subtype, u8 s_host,
-				     u16 *range_start, u16 *range_num)
+				     struct ti_sci_resource_desc *desc)
 {
 	struct ti_sci_msg_resp_get_resource_range *resp;
 	struct ti_sci_msg_req_get_resource_range *req;
@@ -1721,7 +1721,7 @@ static int ti_sci_get_resource_range(const struct ti_sci_handle *handle,
 
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
-	if (!handle)
+	if (!handle || !desc)
 		return -EINVAL;
 
 	info = handle_to_ti_sci_info(handle);
@@ -1754,8 +1754,8 @@ static int ti_sci_get_resource_range(const struct ti_sci_handle *handle,
 	} else if (!resp->range_start && !resp->range_num) {
 		ret = -ENODEV;
 	} else {
-		*range_start = resp->range_start;
-		*range_num = resp->range_num;
+		desc->start = resp->range_start;
+		desc->num = resp->range_num;
 	};
 
 fail:
@@ -1771,18 +1771,18 @@ fail:
  * @dev_id:		TISCI device ID.
  * @subtype:		Resource assignment subtype that is being requested
  *			from the given device.
- * @range_start:	Start index of the resource range
- * @range_num:		Number of resources in the range
+ * @desc:		Pointer to ti_sci_resource_desc to be updated with the
+ *			resource range start index and number of resources
  *
  * Return: 0 if all went fine, else return appropriate error.
  */
 static int ti_sci_cmd_get_resource_range(const struct ti_sci_handle *handle,
 					 u32 dev_id, u8 subtype,
-					 u16 *range_start, u16 *range_num)
+					 struct ti_sci_resource_desc *desc)
 {
 	return ti_sci_get_resource_range(handle, dev_id, subtype,
 					 TI_SCI_IRQ_SECONDARY_HOST_INVALID,
-					 range_start, range_num);
+					 desc);
 }
 
 /**
@@ -1793,18 +1793,17 @@ static int ti_sci_cmd_get_resource_range(const struct ti_sci_handle *handle,
  * @subtype:		Resource assignment subtype that is being requested
  *			from the given device.
  * @s_host:		Host processor ID to which the resources are allocated
- * @range_start:	Start index of the resource range
- * @range_num:		Number of resources in the range
+ * @desc:		Pointer to ti_sci_resource_desc to be updated with the
+ *			resource range start index and number of resources
  *
  * Return: 0 if all went fine, else return appropriate error.
  */
 static
 int ti_sci_cmd_get_resource_range_from_shost(const struct ti_sci_handle *handle,
 					     u32 dev_id, u8 subtype, u8 s_host,
-					     u16 *range_start, u16 *range_num)
+					     struct ti_sci_resource_desc *desc)
 {
-	return ti_sci_get_resource_range(handle, dev_id, subtype, s_host,
-					 range_start, range_num);
+	return ti_sci_get_resource_range(handle, dev_id, subtype, s_host, desc);
 }
 
 /**
@@ -3243,8 +3242,7 @@ devm_ti_sci_get_resource_sets(const struct ti_sci_handle *handle,
 	for (i = 0; i < res->sets; i++) {
 		ret = handle->ops.rm_core_ops.get_range(handle, dev_id,
 							sub_types[i],
-							&res->desc[i].start,
-							&res->desc[i].num);
+							&res->desc[i]);
 		if (ret) {
 			dev_dbg(dev, "dev = %d subtype %d not allocated for this host\n",
 				dev_id, sub_types[i]);
diff --git a/include/linux/soc/ti/ti_sci_protocol.h b/include/linux/soc/ti/ti_sci_protocol.h
index d254d99fd45b..6cd537db4d33 100644
--- a/include/linux/soc/ti/ti_sci_protocol.h
+++ b/include/linux/soc/ti/ti_sci_protocol.h
@@ -195,6 +195,18 @@ struct ti_sci_clk_ops {
 			u64 *current_freq);
 };
 
+/**
+ * struct ti_sci_resource_desc - Description of TI SCI resource instance range.
+ * @start:	Start index of the resource.
+ * @num:	Number of resources.
+ * @res_map:	Bitmap to manage the allocation of these resources.
+ */
+struct ti_sci_resource_desc {
+	u16 start;
+	u16 num;
+	unsigned long *res_map;
+};
+
 /**
  * struct ti_sci_rm_core_ops - Resource management core operations
  * @get_range:		Get a range of resources belonging to ti sci host.
@@ -209,15 +221,15 @@ struct ti_sci_clk_ops {
  * - dev_id:	TISCI device ID.
  * - subtype:	Resource assignment subtype that is being requested
  *		from the given device.
- * - range_start:	Start index of the resource range
- * - range_end:		Number of resources in the range
+ * - desc:	Pointer to ti_sci_resource_desc to be updated with the resource
+ *		range start index and number of resources
  */
 struct ti_sci_rm_core_ops {
 	int (*get_range)(const struct ti_sci_handle *handle, u32 dev_id,
-			 u8 subtype, u16 *range_start, u16 *range_num);
+			 u8 subtype, struct ti_sci_resource_desc *desc);
 	int (*get_range_from_shost)(const struct ti_sci_handle *handle,
 				    u32 dev_id, u8 subtype, u8 s_host,
-				    u16 *range_start, u16 *range_num);
+				    struct ti_sci_resource_desc *desc);
 };
 
 #define TI_SCI_RESASG_SUBTYPE_IR_OUTPUT		0
@@ -522,18 +534,6 @@ struct ti_sci_handle {
 
 #define TI_SCI_RESOURCE_NULL	0xffff
 
-/**
- * struct ti_sci_resource_desc - Description of TI SCI resource instance range.
- * @start:	Start index of the resource.
- * @num:	Number of resources.
- * @res_map:	Bitmap to manage the allocation of these resources.
- */
-struct ti_sci_resource_desc {
-	u16 start;
-	u16 num;
-	unsigned long *res_map;
-};
-
 /**
  * struct ti_sci_resource - Structure representing a resource assigned
  *			    to a device.
-- 
cgit v1.2.3


From 519c5c0c558b529f835c9bb30f9a1eb2034d585c Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@ti.com>
Date: Sun, 25 Oct 2020 12:10:03 -0700
Subject: firmware: ti_sci: rm: Add support for second resource range

Sysfw added support for a second range in the resource range API to be able
to describe complex allocations mainly for DMA channels.

Update the ti_sci part to consider the second range as well.

Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
---
 drivers/firmware/ti_sci.c              | 48 ++++++++++++++++++++++------------
 drivers/firmware/ti_sci.h              |  8 ++++--
 include/linux/soc/ti/ti_sci_protocol.h |  8 ++++--
 3 files changed, 43 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/ti_sci.c b/drivers/firmware/ti_sci.c
index 7a777e91ce3e..2793bb923881 100644
--- a/drivers/firmware/ti_sci.c
+++ b/drivers/firmware/ti_sci.c
@@ -1751,11 +1751,14 @@ static int ti_sci_get_resource_range(const struct ti_sci_handle *handle,
 
 	if (!ti_sci_is_response_ack(resp)) {
 		ret = -ENODEV;
-	} else if (!resp->range_start && !resp->range_num) {
+	} else if (!resp->range_num && !resp->range_num_sec) {
+		/* Neither of the two resource range is valid */
 		ret = -ENODEV;
 	} else {
 		desc->start = resp->range_start;
 		desc->num = resp->range_num;
+		desc->start_sec = resp->range_start_sec;
+		desc->num_sec = resp->range_num_sec;
 	};
 
 fail:
@@ -3157,12 +3160,18 @@ u16 ti_sci_get_free_resource(struct ti_sci_resource *res)
 
 	raw_spin_lock_irqsave(&res->lock, flags);
 	for (set = 0; set < res->sets; set++) {
-		free_bit = find_first_zero_bit(res->desc[set].res_map,
-					       res->desc[set].num);
-		if (free_bit != res->desc[set].num) {
-			set_bit(free_bit, res->desc[set].res_map);
+		struct ti_sci_resource_desc *desc = &res->desc[set];
+		int res_count = desc->num + desc->num_sec;
+
+		free_bit = find_first_zero_bit(desc->res_map, res_count);
+		if (free_bit != res_count) {
+			set_bit(free_bit, desc->res_map);
 			raw_spin_unlock_irqrestore(&res->lock, flags);
-			return res->desc[set].start + free_bit;
+
+			if (desc->num && free_bit < desc->num)
+				return desc->start + free_bit;
+			else
+				return desc->start_sec + free_bit;
 		}
 	}
 	raw_spin_unlock_irqrestore(&res->lock, flags);
@@ -3183,10 +3192,14 @@ void ti_sci_release_resource(struct ti_sci_resource *res, u16 id)
 
 	raw_spin_lock_irqsave(&res->lock, flags);
 	for (set = 0; set < res->sets; set++) {
-		if (res->desc[set].start <= id &&
-		    (res->desc[set].num + res->desc[set].start) > id)
-			clear_bit(id - res->desc[set].start,
-				  res->desc[set].res_map);
+		struct ti_sci_resource_desc *desc = &res->desc[set];
+
+		if (desc->num && desc->start <= id &&
+		    (desc->start + desc->num) > id)
+			clear_bit(id - desc->start, desc->res_map);
+		else if (desc->num_sec && desc->start_sec <= id &&
+			 (desc->start_sec + desc->num_sec) > id)
+			clear_bit(id - desc->start_sec, desc->res_map);
 	}
 	raw_spin_unlock_irqrestore(&res->lock, flags);
 }
@@ -3203,7 +3216,7 @@ u32 ti_sci_get_num_resources(struct ti_sci_resource *res)
 	u32 set, count = 0;
 
 	for (set = 0; set < res->sets; set++)
-		count += res->desc[set].num;
+		count += res->desc[set].num + res->desc[set].num_sec;
 
 	return count;
 }
@@ -3227,7 +3240,7 @@ devm_ti_sci_get_resource_sets(const struct ti_sci_handle *handle,
 {
 	struct ti_sci_resource *res;
 	bool valid_set = false;
-	int i, ret;
+	int i, ret, res_count;
 
 	res = devm_kzalloc(dev, sizeof(*res), GFP_KERNEL);
 	if (!res)
@@ -3246,18 +3259,19 @@ devm_ti_sci_get_resource_sets(const struct ti_sci_handle *handle,
 		if (ret) {
 			dev_dbg(dev, "dev = %d subtype %d not allocated for this host\n",
 				dev_id, sub_types[i]);
-			res->desc[i].start = 0;
-			res->desc[i].num = 0;
+			memset(&res->desc[i], 0, sizeof(res->desc[i]));
 			continue;
 		}
 
-		dev_dbg(dev, "dev = %d, subtype = %d, start = %d, num = %d\n",
+		dev_dbg(dev, "dev/sub_type: %d/%d, start/num: %d/%d | %d/%d\n",
 			dev_id, sub_types[i], res->desc[i].start,
-			res->desc[i].num);
+			res->desc[i].num, res->desc[i].start_sec,
+			res->desc[i].num_sec);
 
 		valid_set = true;
+		res_count = res->desc[i].num + res->desc[i].num_sec;
 		res->desc[i].res_map =
-			devm_kzalloc(dev, BITS_TO_LONGS(res->desc[i].num) *
+			devm_kzalloc(dev, BITS_TO_LONGS(res_count) *
 				     sizeof(*res->desc[i].res_map), GFP_KERNEL);
 		if (!res->desc[i].res_map)
 			return ERR_PTR(-ENOMEM);
diff --git a/drivers/firmware/ti_sci.h b/drivers/firmware/ti_sci.h
index dca19ca5fc49..4d980eb592c4 100644
--- a/drivers/firmware/ti_sci.h
+++ b/drivers/firmware/ti_sci.h
@@ -574,8 +574,10 @@ struct ti_sci_msg_req_get_resource_range {
 /**
  * struct ti_sci_msg_resp_get_resource_range - Response to resource get range.
  * @hdr:		Generic Header
- * @range_start:	Start index of the resource range.
- * @range_num:		Number of resources in the range.
+ * @range_start:	Start index of the first resource range.
+ * @range_num:		Number of resources in the first range.
+ * @range_start_sec:	Start index of the second resource range.
+ * @range_num_sec:	Number of resources in the second range.
  *
  * Response to request TI_SCI_MSG_GET_RESOURCE_RANGE.
  */
@@ -583,6 +585,8 @@ struct ti_sci_msg_resp_get_resource_range {
 	struct ti_sci_msg_hdr hdr;
 	u16 range_start;
 	u16 range_num;
+	u16 range_start_sec;
+	u16 range_num_sec;
 } __packed;
 
 /**
diff --git a/include/linux/soc/ti/ti_sci_protocol.h b/include/linux/soc/ti/ti_sci_protocol.h
index 6cd537db4d33..9699b260de59 100644
--- a/include/linux/soc/ti/ti_sci_protocol.h
+++ b/include/linux/soc/ti/ti_sci_protocol.h
@@ -197,13 +197,17 @@ struct ti_sci_clk_ops {
 
 /**
  * struct ti_sci_resource_desc - Description of TI SCI resource instance range.
- * @start:	Start index of the resource.
- * @num:	Number of resources.
+ * @start:	Start index of the first resource range.
+ * @num:	Number of resources in the first range.
+ * @start_sec:	Start index of the second resource range.
+ * @num_sec:	Number of resources in the second range.
  * @res_map:	Bitmap to manage the allocation of these resources.
  */
 struct ti_sci_resource_desc {
 	u16 start;
 	u16 num;
+	u16 start_sec;
+	u16 num_sec;
 	unsigned long *res_map;
 };
 
-- 
cgit v1.2.3


From ce1feed58534d8489afb4900bee75dff15d950e0 Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@ti.com>
Date: Sun, 25 Oct 2020 12:10:05 -0700
Subject: firmware: ti_sci: rm: Add support for extended_ch_type for tx channel

Sysfw added 'extended_ch_type' to the tx_ch_cfg_req message which should be
used when BCDMA block copy channels are configured:
extended_ch_type = 0 : the channel is split tx channel (tchan)
extended_ch_type = 1 : the channel is block copy channel (bchan)

Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
---
 drivers/firmware/ti_sci.c              | 1 +
 drivers/firmware/ti_sci.h              | 6 ++++++
 include/linux/soc/ti/ti_sci_protocol.h | 5 +++++
 3 files changed, 12 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/firmware/ti_sci.c b/drivers/firmware/ti_sci.c
index 2793bb923881..0dd3fbb4f964 100644
--- a/drivers/firmware/ti_sci.c
+++ b/drivers/firmware/ti_sci.c
@@ -2365,6 +2365,7 @@ static int ti_sci_cmd_rm_udmap_tx_ch_cfg(const struct ti_sci_handle *handle,
 	req->tx_sched_priority = params->tx_sched_priority;
 	req->tx_burst_size = params->tx_burst_size;
 	req->tx_tdtype = params->tx_tdtype;
+	req->extended_ch_type = params->extended_ch_type;
 
 	ret = ti_sci_do_xfer(info, xfer);
 	if (ret) {
diff --git a/drivers/firmware/ti_sci.h b/drivers/firmware/ti_sci.h
index 4d980eb592c4..ca15d8f1f8de 100644
--- a/drivers/firmware/ti_sci.h
+++ b/drivers/firmware/ti_sci.h
@@ -915,6 +915,7 @@ struct rm_ti_sci_msg_udmap_rx_flow_opt_cfg {
  *   13 - Valid bit for @ref ti_sci_msg_rm_udmap_tx_ch_cfg::fdepth
  *   14 - Valid bit for @ref ti_sci_msg_rm_udmap_tx_ch_cfg::tx_burst_size
  *   15 - Valid bit for @ref ti_sci_msg_rm_udmap_tx_ch_cfg::tx_tdtype
+ *   16 - Valid bit for @ref ti_sci_msg_rm_udmap_tx_ch_cfg::extended_ch_type
  *
  * @nav_id: SoC device ID of Navigator Subsystem where tx channel is located
  *
@@ -983,6 +984,10 @@ struct rm_ti_sci_msg_udmap_rx_flow_opt_cfg {
  * programmed into the tdtype field of the TCHAN_TCFG register:
  * 0 - Return immediately
  * 1 - Wait for completion message from remote peer
+ *
+ * @extended_ch_type: Valid for BCDMA.
+ * 0 - the channel is split tx channel (tchan)
+ * 1 - the channel is block copy channel (bchan)
  */
 struct ti_sci_msg_rm_udmap_tx_ch_cfg_req {
 	struct ti_sci_msg_hdr hdr;
@@ -1005,6 +1010,7 @@ struct ti_sci_msg_rm_udmap_tx_ch_cfg_req {
 	u8 tx_sched_priority;
 	u8 tx_burst_size;
 	u8 tx_tdtype;
+	u8 extended_ch_type;
 } __packed;
 
 /**
diff --git a/include/linux/soc/ti/ti_sci_protocol.h b/include/linux/soc/ti/ti_sci_protocol.h
index 9699b260de59..6978afc00823 100644
--- a/include/linux/soc/ti/ti_sci_protocol.h
+++ b/include/linux/soc/ti/ti_sci_protocol.h
@@ -336,6 +336,9 @@ struct ti_sci_rm_psil_ops {
 #define TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_128_BYTES	2
 #define TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_256_BYTES	3
 
+#define TI_SCI_RM_BCDMA_EXTENDED_CH_TYPE_TCHAN		0
+#define TI_SCI_RM_BCDMA_EXTENDED_CH_TYPE_BCHAN		1
+
 /* UDMAP TX/RX channel valid_params common declarations */
 #define TI_SCI_MSG_VALUE_RM_UDMAP_CH_PAUSE_ON_ERR_VALID		BIT(0)
 #define TI_SCI_MSG_VALUE_RM_UDMAP_CH_ATYPE_VALID                BIT(1)
@@ -362,6 +365,7 @@ struct ti_sci_msg_rm_udmap_tx_ch_cfg {
 #define TI_SCI_MSG_VALUE_RM_UDMAP_CH_TX_CREDIT_COUNT_VALID      BIT(12)
 #define TI_SCI_MSG_VALUE_RM_UDMAP_CH_TX_FDEPTH_VALID            BIT(13)
 #define TI_SCI_MSG_VALUE_RM_UDMAP_CH_TX_TDTYPE_VALID            BIT(15)
+#define TI_SCI_MSG_VALUE_RM_UDMAP_CH_EXTENDED_CH_TYPE_VALID	BIT(16)
 	u16 nav_id;
 	u16 index;
 	u8 tx_pause_on_err;
@@ -380,6 +384,7 @@ struct ti_sci_msg_rm_udmap_tx_ch_cfg {
 	u8 tx_sched_priority;
 	u8 tx_burst_size;
 	u8 tx_tdtype;
+	u8 extended_ch_type;
 };
 
 /**
-- 
cgit v1.2.3


From 4d8ddf673a420aa25668eceeb4fbf33e2521fdf2 Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@ti.com>
Date: Sun, 25 Oct 2020 12:10:05 -0700
Subject: firmware: ti_sci: rm: Remove ring_get_config support

The ring_get_cfg (0x1111 message) is not used and it is not supported by
sysfw for a long time.

Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
---
 drivers/firmware/ti_sci.c              | 80 ----------------------------------
 drivers/firmware/ti_sci.h              | 44 -------------------
 include/linux/soc/ti/ti_sci_protocol.h |  6 ---
 3 files changed, 130 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/ti_sci.c b/drivers/firmware/ti_sci.c
index 0dd3fbb4f964..0b801e67e672 100644
--- a/drivers/firmware/ti_sci.c
+++ b/drivers/firmware/ti_sci.c
@@ -2119,85 +2119,6 @@ fail:
 	return ret;
 }
 
-/**
- * ti_sci_cmd_ring_get_config() - get RA ring configuration
- * @handle:	Pointer to TI SCI handle.
- * @nav_id:	Device ID of Navigator Subsystem from which the ring is
- *		allocated
- * @index:	Ring index
- * @addr_lo:	Returns ring's base address lo 32 bits
- * @addr_hi:	Returns ring's base address hi 32 bits
- * @count:	Returns number of ring elements
- * @mode:	Returns mode of the ring
- * @size:	Returns ring element size
- * @order_id:	Returns ring's bus order ID
- *
- * Return: 0 if all went well, else returns appropriate error value.
- *
- * See @ti_sci_msg_rm_ring_get_cfg_req for more info.
- */
-static int ti_sci_cmd_ring_get_config(const struct ti_sci_handle *handle,
-				      u32 nav_id, u32 index, u8 *mode,
-				      u32 *addr_lo, u32 *addr_hi,
-				      u32 *count, u8 *size, u8 *order_id)
-{
-	struct ti_sci_msg_rm_ring_get_cfg_resp *resp;
-	struct ti_sci_msg_rm_ring_get_cfg_req *req;
-	struct ti_sci_xfer *xfer;
-	struct ti_sci_info *info;
-	struct device *dev;
-	int ret = 0;
-
-	if (IS_ERR_OR_NULL(handle))
-		return -EINVAL;
-
-	info = handle_to_ti_sci_info(handle);
-	dev = info->dev;
-
-	xfer = ti_sci_get_one_xfer(info, TI_SCI_MSG_RM_RING_GET_CFG,
-				   TI_SCI_FLAG_REQ_ACK_ON_PROCESSED,
-				   sizeof(*req), sizeof(*resp));
-	if (IS_ERR(xfer)) {
-		ret = PTR_ERR(xfer);
-		dev_err(dev,
-			"RM_RA:Message get config failed(%d)\n", ret);
-		return ret;
-	}
-	req = (struct ti_sci_msg_rm_ring_get_cfg_req *)xfer->xfer_buf;
-	req->nav_id = nav_id;
-	req->index = index;
-
-	ret = ti_sci_do_xfer(info, xfer);
-	if (ret) {
-		dev_err(dev, "RM_RA:Mbox get config send fail %d\n", ret);
-		goto fail;
-	}
-
-	resp = (struct ti_sci_msg_rm_ring_get_cfg_resp *)xfer->xfer_buf;
-
-	if (!ti_sci_is_response_ack(resp)) {
-		ret = -ENODEV;
-	} else {
-		if (mode)
-			*mode = resp->mode;
-		if (addr_lo)
-			*addr_lo = resp->addr_lo;
-		if (addr_hi)
-			*addr_hi = resp->addr_hi;
-		if (count)
-			*count = resp->count;
-		if (size)
-			*size = resp->size;
-		if (order_id)
-			*order_id = resp->order_id;
-	};
-
-fail:
-	ti_sci_put_one_xfer(&info->minfo, xfer);
-	dev_dbg(dev, "RM_RA:get config ring %u ret:%d\n", index, ret);
-	return ret;
-}
-
 /**
  * ti_sci_cmd_rm_psil_pair() - Pair PSI-L source to destination thread
  * @handle:	Pointer to TI SCI handle.
@@ -2926,7 +2847,6 @@ static void ti_sci_setup_ops(struct ti_sci_info *info)
 	iops->free_event_map = ti_sci_cmd_free_event_map;
 
 	rops->config = ti_sci_cmd_ring_config;
-	rops->get_config = ti_sci_cmd_ring_get_config;
 
 	psilops->pair = ti_sci_cmd_rm_psil_pair;
 	psilops->unpair = ti_sci_cmd_rm_psil_unpair;
diff --git a/drivers/firmware/ti_sci.h b/drivers/firmware/ti_sci.h
index ca15d8f1f8de..1cdf918be861 100644
--- a/drivers/firmware/ti_sci.h
+++ b/drivers/firmware/ti_sci.h
@@ -49,7 +49,6 @@
 #define TI_SCI_MSG_RM_RING_RECONFIG		0x1102
 #define TI_SCI_MSG_RM_RING_RESET		0x1103
 #define TI_SCI_MSG_RM_RING_CFG			0x1110
-#define TI_SCI_MSG_RM_RING_GET_CFG		0x1111
 
 /* PSI-L requests */
 #define TI_SCI_MSG_RM_PSIL_PAIR			0x1280
@@ -687,49 +686,6 @@ struct ti_sci_msg_rm_ring_cfg_req {
 	u8 order_id;
 } __packed;
 
-/**
- * struct ti_sci_msg_rm_ring_get_cfg_req - Get RA ring's configuration
- *
- * Gets the configuration of the non-real-time register fields of a ring.  The
- * host, or a supervisor of the host, who owns the ring must be the requesting
- * host.  The values of the non-real-time registers are returned in
- * @ti_sci_msg_rm_ring_get_cfg_resp.
- *
- * @hdr: Generic Header
- * @nav_id: Device ID of Navigator Subsystem from which the ring is allocated
- * @index: ring index.
- */
-struct ti_sci_msg_rm_ring_get_cfg_req {
-	struct ti_sci_msg_hdr hdr;
-	u16 nav_id;
-	u16 index;
-} __packed;
-
-/**
- * struct ti_sci_msg_rm_ring_get_cfg_resp -  Ring get configuration response
- *
- * Response received by host processor after RM has handled
- * @ti_sci_msg_rm_ring_get_cfg_req. The response contains the ring's
- * non-real-time register values.
- *
- * @hdr: Generic Header
- * @addr_lo: Ring 32 LSBs of base address
- * @addr_hi: Ring 16 MSBs of base address.
- * @count: Ring number of elements.
- * @mode: Ring mode.
- * @size: encoded Ring element size
- * @order_id: ing order ID.
- */
-struct ti_sci_msg_rm_ring_get_cfg_resp {
-	struct ti_sci_msg_hdr hdr;
-	u32 addr_lo;
-	u32 addr_hi;
-	u32 count;
-	u8 mode;
-	u8 size;
-	u8 order_id;
-} __packed;
-
 /**
  * struct ti_sci_msg_psil_pair - Pairs a PSI-L source thread to a destination
  *				 thread
diff --git a/include/linux/soc/ti/ti_sci_protocol.h b/include/linux/soc/ti/ti_sci_protocol.h
index 6978afc00823..6710d7ac7a72 100644
--- a/include/linux/soc/ti/ti_sci_protocol.h
+++ b/include/linux/soc/ti/ti_sci_protocol.h
@@ -286,8 +286,6 @@ struct ti_sci_rm_irq_ops {
 /**
  * struct ti_sci_rm_ringacc_ops - Ring Accelerator Management operations
  * @config: configure the SoC Navigator Subsystem Ring Accelerator ring
- * @get_config: get the SoC Navigator Subsystem Ring Accelerator ring
- *		configuration
  */
 struct ti_sci_rm_ringacc_ops {
 	int (*config)(const struct ti_sci_handle *handle,
@@ -295,10 +293,6 @@ struct ti_sci_rm_ringacc_ops {
 		      u32 addr_lo, u32 addr_hi, u32 count, u8 mode,
 		      u8 size, u8 order_id
 	);
-	int (*get_config)(const struct ti_sci_handle *handle,
-			  u32 nav_id, u32 index, u8 *mode,
-			  u32 *addr_lo, u32 *addr_hi, u32 *count,
-			  u8 *size, u8 *order_id);
 };
 
 /**
-- 
cgit v1.2.3


From 3c2017536f3a122bf246cc87f9327e9ec138db92 Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@ti.com>
Date: Sun, 25 Oct 2020 12:10:06 -0700
Subject: firmware: ti_sci: rm: Add new ops for ring configuration

The sysfw ring configuration message has been extended to include virtid
and asel value for the ring.
Add the ASEL_VALID to TI_SCI_MSG_VALUE_RM_ALL_NO_ORDER as it is required
for DMA rings.

Instead of extending the current .config() ops - which would need same
patch change in the ringacc driver - add ti_sci_msg_rm_ring_cfg struct and
a new ops using it to configure the ring.

This will allow easy update path in case new members are added for the ring
configuration.

Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
---
 drivers/firmware/ti_sci.c              | 63 ++++++++++++++++++++++++++++++++++
 drivers/firmware/ti_sci.h              |  7 ++++
 include/linux/soc/ti/ti_sci_protocol.h | 31 ++++++++++++++++-
 3 files changed, 100 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/ti_sci.c b/drivers/firmware/ti_sci.c
index 0b801e67e672..a4d2b318795c 100644
--- a/drivers/firmware/ti_sci.c
+++ b/drivers/firmware/ti_sci.c
@@ -2119,6 +2119,68 @@ fail:
 	return ret;
 }
 
+/**
+ * ti_sci_cmd_rm_ring_cfg() - Configure a NAVSS ring
+ * @handle:	Pointer to TI SCI handle.
+ * @params:	Pointer to ti_sci_msg_rm_ring_cfg ring config structure
+ *
+ * Return: 0 if all went well, else returns appropriate error value.
+ *
+ * See @ti_sci_msg_rm_ring_cfg and @ti_sci_msg_rm_ring_cfg_req for
+ * more info.
+ */
+static int ti_sci_cmd_rm_ring_cfg(const struct ti_sci_handle *handle,
+				  const struct ti_sci_msg_rm_ring_cfg *params)
+{
+	struct ti_sci_msg_rm_ring_cfg_req *req;
+	struct ti_sci_msg_hdr *resp;
+	struct ti_sci_xfer *xfer;
+	struct ti_sci_info *info;
+	struct device *dev;
+	int ret = 0;
+
+	if (IS_ERR_OR_NULL(handle))
+		return -EINVAL;
+
+	info = handle_to_ti_sci_info(handle);
+	dev = info->dev;
+
+	xfer = ti_sci_get_one_xfer(info, TI_SCI_MSG_RM_RING_CFG,
+				   TI_SCI_FLAG_REQ_ACK_ON_PROCESSED,
+				   sizeof(*req), sizeof(*resp));
+	if (IS_ERR(xfer)) {
+		ret = PTR_ERR(xfer);
+		dev_err(dev, "RM_RA:Message config failed(%d)\n", ret);
+		return ret;
+	}
+	req = (struct ti_sci_msg_rm_ring_cfg_req *)xfer->xfer_buf;
+	req->valid_params = params->valid_params;
+	req->nav_id = params->nav_id;
+	req->index = params->index;
+	req->addr_lo = params->addr_lo;
+	req->addr_hi = params->addr_hi;
+	req->count = params->count;
+	req->mode = params->mode;
+	req->size = params->size;
+	req->order_id = params->order_id;
+	req->virtid = params->virtid;
+	req->asel = params->asel;
+
+	ret = ti_sci_do_xfer(info, xfer);
+	if (ret) {
+		dev_err(dev, "RM_RA:Mbox config send fail %d\n", ret);
+		goto fail;
+	}
+
+	resp = (struct ti_sci_msg_hdr *)xfer->xfer_buf;
+	ret = ti_sci_is_response_ack(resp) ? 0 : -EINVAL;
+
+fail:
+	ti_sci_put_one_xfer(&info->minfo, xfer);
+	dev_dbg(dev, "RM_RA:config ring %u ret:%d\n", params->index, ret);
+	return ret;
+}
+
 /**
  * ti_sci_cmd_rm_psil_pair() - Pair PSI-L source to destination thread
  * @handle:	Pointer to TI SCI handle.
@@ -2847,6 +2909,7 @@ static void ti_sci_setup_ops(struct ti_sci_info *info)
 	iops->free_event_map = ti_sci_cmd_free_event_map;
 
 	rops->config = ti_sci_cmd_ring_config;
+	rops->set_cfg = ti_sci_cmd_rm_ring_cfg;
 
 	psilops->pair = ti_sci_cmd_rm_psil_pair;
 	psilops->unpair = ti_sci_cmd_rm_psil_unpair;
diff --git a/drivers/firmware/ti_sci.h b/drivers/firmware/ti_sci.h
index 1cdf918be861..ef3a8214d002 100644
--- a/drivers/firmware/ti_sci.h
+++ b/drivers/firmware/ti_sci.h
@@ -659,6 +659,8 @@ struct ti_sci_msg_req_manage_irq {
  *	3 - Valid bit for @tisci_msg_rm_ring_cfg_req mode
  *	4 - Valid bit for @tisci_msg_rm_ring_cfg_req size
  *	5 - Valid bit for @tisci_msg_rm_ring_cfg_req order_id
+ *	6 - Valid bit for @tisci_msg_rm_ring_cfg_req virtid
+ *	7 - Valid bit for @tisci_msg_rm_ring_cfg_req ASEL
  * @nav_id: Device ID of Navigator Subsystem from which the ring is allocated
  * @index: ring index to be configured.
  * @addr_lo: 32 LSBs of ring base address to be programmed into the ring's
@@ -672,6 +674,9 @@ struct ti_sci_msg_req_manage_irq {
  *	the formula (log2(size_bytes) - 2), where size_bytes cannot be
  *	greater than 256.
  * @order_id: Specifies the ring's bus order ID.
+ * @virtid: Ring virt ID value
+ * @asel: Ring ASEL (address select) value to be set into the ASEL field of the
+ *	ring's RING_BA_HI register.
  */
 struct ti_sci_msg_rm_ring_cfg_req {
 	struct ti_sci_msg_hdr hdr;
@@ -684,6 +689,8 @@ struct ti_sci_msg_rm_ring_cfg_req {
 	u8 mode;
 	u8 size;
 	u8 order_id;
+	u16 virtid;
+	u8 asel;
 } __packed;
 
 /**
diff --git a/include/linux/soc/ti/ti_sci_protocol.h b/include/linux/soc/ti/ti_sci_protocol.h
index 6710d7ac7a72..d1711050cd9d 100644
--- a/include/linux/soc/ti/ti_sci_protocol.h
+++ b/include/linux/soc/ti/ti_sci_protocol.h
@@ -275,17 +275,44 @@ struct ti_sci_rm_irq_ops {
 #define TI_SCI_MSG_VALUE_RM_RING_SIZE_VALID	BIT(4)
 /* RA config.order_id parameter is valid for RM ring configure TISCI message */
 #define TI_SCI_MSG_VALUE_RM_RING_ORDER_ID_VALID	BIT(5)
+/* RA config.virtid parameter is valid for RM ring configure TISCI message */
+#define TI_SCI_MSG_VALUE_RM_RING_VIRTID_VALID	BIT(6)
+/* RA config.asel parameter is valid for RM ring configure TISCI message */
+#define TI_SCI_MSG_VALUE_RM_RING_ASEL_VALID	BIT(7)
 
 #define TI_SCI_MSG_VALUE_RM_ALL_NO_ORDER \
 	(TI_SCI_MSG_VALUE_RM_RING_ADDR_LO_VALID | \
 	TI_SCI_MSG_VALUE_RM_RING_ADDR_HI_VALID | \
 	TI_SCI_MSG_VALUE_RM_RING_COUNT_VALID | \
 	TI_SCI_MSG_VALUE_RM_RING_MODE_VALID | \
-	TI_SCI_MSG_VALUE_RM_RING_SIZE_VALID)
+	TI_SCI_MSG_VALUE_RM_RING_SIZE_VALID | \
+	TI_SCI_MSG_VALUE_RM_RING_ASEL_VALID)
+
+/**
+ * struct ti_sci_msg_rm_ring_cfg - Ring configuration
+ *
+ * Parameters for Navigator Subsystem ring configuration
+ * See @ti_sci_msg_rm_ring_cfg_req
+ */
+struct ti_sci_msg_rm_ring_cfg {
+	u32 valid_params;
+	u16 nav_id;
+	u16 index;
+	u32 addr_lo;
+	u32 addr_hi;
+	u32 count;
+	u8 mode;
+	u8 size;
+	u8 order_id;
+	u16 virtid;
+	u8 asel;
+};
 
 /**
  * struct ti_sci_rm_ringacc_ops - Ring Accelerator Management operations
  * @config: configure the SoC Navigator Subsystem Ring Accelerator ring
+ *	    Deprecated
+ * @set_cfg: configure the SoC Navigator Subsystem Ring Accelerator ring
  */
 struct ti_sci_rm_ringacc_ops {
 	int (*config)(const struct ti_sci_handle *handle,
@@ -293,6 +320,8 @@ struct ti_sci_rm_ringacc_ops {
 		      u32 addr_lo, u32 addr_hi, u32 count, u8 mode,
 		      u8 size, u8 order_id
 	);
+	int (*set_cfg)(const struct ti_sci_handle *handle,
+		       const struct ti_sci_msg_rm_ring_cfg *params);
 };
 
 /**
-- 
cgit v1.2.3


From fed7552f1e69296461fca62ebaa0bb5a06fec0df Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@ti.com>
Date: Sun, 25 Oct 2020 12:10:07 -0700
Subject: firmware: ti_sci: rm: Remove unused config() from
 ti_sci_rm_ringacc_ops

The ringacc driver has been converted to use the new set_cfg function to
configure the ring, the old config ops can be removed.

Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
---
 drivers/firmware/ti_sci.c              | 72 ----------------------------------
 include/linux/soc/ti/ti_sci_protocol.h |  7 ----
 2 files changed, 79 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/ti_sci.c b/drivers/firmware/ti_sci.c
index a4d2b318795c..235c7e7869aa 100644
--- a/drivers/firmware/ti_sci.c
+++ b/drivers/firmware/ti_sci.c
@@ -2048,77 +2048,6 @@ static int ti_sci_cmd_free_event_map(const struct ti_sci_handle *handle,
 			       ia_id, vint, global_event, vint_status_bit, 0);
 }
 
-/**
- * ti_sci_cmd_ring_config() - configure RA ring
- * @handle:		Pointer to TI SCI handle.
- * @valid_params:	Bitfield defining validity of ring configuration
- *			parameters
- * @nav_id:		Device ID of Navigator Subsystem from which the ring is
- *			allocated
- * @index:		Ring index
- * @addr_lo:		The ring base address lo 32 bits
- * @addr_hi:		The ring base address hi 32 bits
- * @count:		Number of ring elements
- * @mode:		The mode of the ring
- * @size:		The ring element size.
- * @order_id:		Specifies the ring's bus order ID
- *
- * Return: 0 if all went well, else returns appropriate error value.
- *
- * See @ti_sci_msg_rm_ring_cfg_req for more info.
- */
-static int ti_sci_cmd_ring_config(const struct ti_sci_handle *handle,
-				  u32 valid_params, u16 nav_id, u16 index,
-				  u32 addr_lo, u32 addr_hi, u32 count,
-				  u8 mode, u8 size, u8 order_id)
-{
-	struct ti_sci_msg_rm_ring_cfg_req *req;
-	struct ti_sci_msg_hdr *resp;
-	struct ti_sci_xfer *xfer;
-	struct ti_sci_info *info;
-	struct device *dev;
-	int ret = 0;
-
-	if (IS_ERR_OR_NULL(handle))
-		return -EINVAL;
-
-	info = handle_to_ti_sci_info(handle);
-	dev = info->dev;
-
-	xfer = ti_sci_get_one_xfer(info, TI_SCI_MSG_RM_RING_CFG,
-				   TI_SCI_FLAG_REQ_ACK_ON_PROCESSED,
-				   sizeof(*req), sizeof(*resp));
-	if (IS_ERR(xfer)) {
-		ret = PTR_ERR(xfer);
-		dev_err(dev, "RM_RA:Message config failed(%d)\n", ret);
-		return ret;
-	}
-	req = (struct ti_sci_msg_rm_ring_cfg_req *)xfer->xfer_buf;
-	req->valid_params = valid_params;
-	req->nav_id = nav_id;
-	req->index = index;
-	req->addr_lo = addr_lo;
-	req->addr_hi = addr_hi;
-	req->count = count;
-	req->mode = mode;
-	req->size = size;
-	req->order_id = order_id;
-
-	ret = ti_sci_do_xfer(info, xfer);
-	if (ret) {
-		dev_err(dev, "RM_RA:Mbox config send fail %d\n", ret);
-		goto fail;
-	}
-
-	resp = (struct ti_sci_msg_hdr *)xfer->xfer_buf;
-	ret = ti_sci_is_response_ack(resp) ? 0 : -ENODEV;
-
-fail:
-	ti_sci_put_one_xfer(&info->minfo, xfer);
-	dev_dbg(dev, "RM_RA:config ring %u ret:%d\n", index, ret);
-	return ret;
-}
-
 /**
  * ti_sci_cmd_rm_ring_cfg() - Configure a NAVSS ring
  * @handle:	Pointer to TI SCI handle.
@@ -2908,7 +2837,6 @@ static void ti_sci_setup_ops(struct ti_sci_info *info)
 	iops->free_irq = ti_sci_cmd_free_irq;
 	iops->free_event_map = ti_sci_cmd_free_event_map;
 
-	rops->config = ti_sci_cmd_ring_config;
 	rops->set_cfg = ti_sci_cmd_rm_ring_cfg;
 
 	psilops->pair = ti_sci_cmd_rm_psil_pair;
diff --git a/include/linux/soc/ti/ti_sci_protocol.h b/include/linux/soc/ti/ti_sci_protocol.h
index d1711050cd9d..0aad7009b50e 100644
--- a/include/linux/soc/ti/ti_sci_protocol.h
+++ b/include/linux/soc/ti/ti_sci_protocol.h
@@ -310,16 +310,9 @@ struct ti_sci_msg_rm_ring_cfg {
 
 /**
  * struct ti_sci_rm_ringacc_ops - Ring Accelerator Management operations
- * @config: configure the SoC Navigator Subsystem Ring Accelerator ring
- *	    Deprecated
  * @set_cfg: configure the SoC Navigator Subsystem Ring Accelerator ring
  */
 struct ti_sci_rm_ringacc_ops {
-	int (*config)(const struct ti_sci_handle *handle,
-		      u32 valid_params, u16 nav_id, u16 index,
-		      u32 addr_lo, u32 addr_hi, u32 count, u8 mode,
-		      u8 size, u8 order_id
-	);
 	int (*set_cfg)(const struct ti_sci_handle *handle,
 		       const struct ti_sci_msg_rm_ring_cfg *params);
 };
-- 
cgit v1.2.3


From 8c42379e40e2db4199ceeb6a6ef9fff73ff132cf Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@ti.com>
Date: Sun, 25 Oct 2020 12:10:22 -0700
Subject: soc: ti: k3-ringacc: Use correct device for allocation in RING mode

In RING mode the ringacc does not access the ring memory. In this access
mode the ringacc coherency does not have meaning.

If the ring is configured in RING mode, then the ringacc itself will not
access to the ring memory. Only the requester (user) of the ring is going
to read/write to the memory.
Extend the ring configuration parameters with a device pointer to be used
for DMA API when the ring is configured in RING mode.

Extending the ring configuration struct will allow per ring selection of
device to be used for allocation, thus allowing per ring coherency.

To avoid regression, fall back to use the ringacc dev in case the alloc_dev
is not provided.

Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
---
 drivers/soc/ti/k3-ringacc.c       | 18 +++++++++++++-----
 include/linux/soc/ti/k3-ringacc.h |  5 +++++
 2 files changed, 18 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/soc/ti/k3-ringacc.c b/drivers/soc/ti/k3-ringacc.c
index 9ddd77113c5a..7fdb688452f7 100644
--- a/drivers/soc/ti/k3-ringacc.c
+++ b/drivers/soc/ti/k3-ringacc.c
@@ -141,6 +141,7 @@ struct k3_ring_state {
  * @parent: Pointer on struct @k3_ringacc
  * @use_count: Use count for shared rings
  * @proxy_id: RA Ring Proxy Id (only if @K3_RINGACC_RING_USE_PROXY)
+ * @dma_dev: device to be used for DMA API (allocation, mapping)
  */
 struct k3_ring {
 	struct k3_ring_rt_regs __iomem *rt;
@@ -160,6 +161,7 @@ struct k3_ring {
 	struct k3_ringacc	*parent;
 	u32		use_count;
 	int		proxy_id;
+	struct device	*dma_dev;
 };
 
 struct k3_ringacc_ops {
@@ -508,11 +510,12 @@ int k3_ringacc_ring_free(struct k3_ring *ring)
 
 	k3_ringacc_ring_free_sci(ring);
 
-	dma_free_coherent(ringacc->dev,
+	dma_free_coherent(ring->dma_dev,
 			  ring->size * (4 << ring->elm_size),
 			  ring->ring_mem_virt, ring->ring_mem_dma);
 	ring->flags = 0;
 	ring->ops = NULL;
+	ring->dma_dev = NULL;
 	if (ring->proxy_id != K3_RINGACC_PROXY_NOT_USED) {
 		clear_bit(ring->proxy_id, ringacc->proxy_inuse);
 		ring->proxy = NULL;
@@ -633,8 +636,12 @@ int k3_ringacc_ring_cfg(struct k3_ring *ring, struct k3_ring_cfg *cfg)
 	switch (ring->mode) {
 	case K3_RINGACC_RING_MODE_RING:
 		ring->ops = &k3_ring_mode_ring_ops;
+		ring->dma_dev = cfg->dma_dev;
+		if (!ring->dma_dev)
+			ring->dma_dev = ringacc->dev;
 		break;
 	case K3_RINGACC_RING_MODE_MESSAGE:
+		ring->dma_dev = ringacc->dev;
 		if (ring->proxy)
 			ring->ops = &k3_ring_mode_proxy_ops;
 		else
@@ -646,9 +653,9 @@ int k3_ringacc_ring_cfg(struct k3_ring *ring, struct k3_ring_cfg *cfg)
 		goto err_free_proxy;
 	}
 
-	ring->ring_mem_virt = dma_alloc_coherent(ringacc->dev,
-					ring->size * (4 << ring->elm_size),
-					&ring->ring_mem_dma, GFP_KERNEL);
+	ring->ring_mem_virt = dma_alloc_coherent(ring->dma_dev,
+						 ring->size * (4 << ring->elm_size),
+						 &ring->ring_mem_dma, GFP_KERNEL);
 	if (!ring->ring_mem_virt) {
 		dev_err(ringacc->dev, "Failed to alloc ring mem\n");
 		ret = -ENOMEM;
@@ -669,12 +676,13 @@ int k3_ringacc_ring_cfg(struct k3_ring *ring, struct k3_ring_cfg *cfg)
 	return 0;
 
 err_free_mem:
-	dma_free_coherent(ringacc->dev,
+	dma_free_coherent(ring->dma_dev,
 			  ring->size * (4 << ring->elm_size),
 			  ring->ring_mem_virt,
 			  ring->ring_mem_dma);
 err_free_ops:
 	ring->ops = NULL;
+	ring->dma_dev = NULL;
 err_free_proxy:
 	ring->proxy = NULL;
 	return ret;
diff --git a/include/linux/soc/ti/k3-ringacc.h b/include/linux/soc/ti/k3-ringacc.h
index 5a472eca5ee4..658dc71d2901 100644
--- a/include/linux/soc/ti/k3-ringacc.h
+++ b/include/linux/soc/ti/k3-ringacc.h
@@ -67,6 +67,9 @@ struct k3_ring;
  *	 few times. It's usable when the same ring is used as Free Host PD ring
  *	 for different flows, for example.
  *	 Note: Locking should be done by consumer if required
+ * @dma_dev: Master device which is using and accessing to the ring
+ *	memory when the mode is K3_RINGACC_RING_MODE_RING. Memory allocations
+ *	should be done using this device.
  */
 struct k3_ring_cfg {
 	u32 size;
@@ -74,6 +77,8 @@ struct k3_ring_cfg {
 	enum k3_ring_mode mode;
 #define K3_RINGACC_RING_SHARED BIT(1)
 	u32 flags;
+
+	struct device *dma_dev;
 };
 
 #define K3_RINGACC_RING_ID_ANY (-1)
-- 
cgit v1.2.3


From f51778db088b2407ec177f2f4da0f6290602aa3f Mon Sep 17 00:00:00 2001
From: Stephen Rothwell <sfr@canb.auug.org.au>
Date: Mon, 2 Nov 2020 12:43:27 +1100
Subject: swiotlb: using SIZE_MAX needs limits.h included

After merging the drm-misc tree, linux-next build (arm
multi_v7_defconfig) failed like this:

In file included from drivers/gpu/drm/nouveau/nouveau_ttm.c:26:
include/linux/swiotlb.h: In function 'swiotlb_max_mapping_size':
include/linux/swiotlb.h:99:9: error: 'SIZE_MAX' undeclared (first use in this function)
   99 |  return SIZE_MAX;
      |         ^~~~~~~~
include/linux/swiotlb.h:7:1: note: 'SIZE_MAX' is defined in header '<stdint.h>'; did you forget to '#include <stdint.h>'?
    6 | #include <linux/init.h>
  +++ |+#include <stdint.h>
    7 | #include <linux/types.h>
include/linux/swiotlb.h:99:9: note: each undeclared identifier is reported only once for each function it appears in
   99 |  return SIZE_MAX;
      |         ^~~~~~~~

Caused by commit

  abe420bfae52 ("swiotlb: Introduce swiotlb_max_mapping_size()")

but only exposed by commit "drm/nouveu: fix swiotlb include"

Fix it by including linux/limits.h as appropriate.

Fixes: abe420bfae52 ("swiotlb: Introduce swiotlb_max_mapping_size()")
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Link: https://lore.kernel.org/r/20201102124327.2f82b2a7@canb.auug.org.au
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/linux/swiotlb.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 046bb94bd4d6..fa5122c6711e 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -5,6 +5,7 @@
 #include <linux/dma-direction.h>
 #include <linux/init.h>
 #include <linux/types.h>
+#include <linux/limits.h>
 
 struct device;
 struct page;
-- 
cgit v1.2.3


From 7a60c2dd0f575ab14a457e99582af0ca1e072a74 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Wed, 28 Oct 2020 16:15:26 -0300
Subject: drm: Remove SCATTERLIST_MAX_SEGMENT

Since commit 9a40401cfa13 ("lib/scatterlist: Do not limit max_segment to
PAGE_ALIGNED values") the max_segment input to sg_alloc_table_from_pages()
does not have to be any special value. The new algorithm will always
create something less than what the user provides. Thus eliminate this
confusing constant.

- vmwgfx should use the HW capability, not mix in the OS page size for
  calling dma_set_max_seg_size()

- i915 uses i915_sg_segment_size() both for sg_alloc_table_from_pages
  and for some open coded sgl construction. This doesn't change the value
  since rounddown(size, UINT_MAX) == SCATTERLIST_MAX_SEGMENT

- drm_prime_pages_to_sg uses it as a default if max_segment is zero,
  UINT_MAX is fine to use directly.

Cc: Gerd Hoffmann <kraxel@redhat.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Thomas Hellstrom <thellstrom@vmware.com>
Cc: Qian Cai <cai@lca.pw>
Cc: "Ursulin, Tvrtko" <tvrtko.ursulin@intel.com>
Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/0-v1-44733fccd781+13d-rm_scatterlist_max_jgg@nvidia.com
---
 drivers/gpu/drm/drm_prime.c             | 4 ++--
 drivers/gpu/drm/i915/i915_scatterlist.h | 2 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.c     | 3 +--
 include/linux/scatterlist.h             | 6 ------
 tools/testing/scatterlist/main.c        | 2 +-
 5 files changed, 5 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 187b55ede62e..a7b61c2d9190 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -820,8 +820,8 @@ struct sg_table *drm_prime_pages_to_sg(struct drm_device *dev,
 
 	if (dev)
 		max_segment = dma_max_mapping_size(dev->dev);
-	if (max_segment == 0 || max_segment > SCATTERLIST_MAX_SEGMENT)
-		max_segment = SCATTERLIST_MAX_SEGMENT;
+	if (max_segment == 0)
+		max_segment = UINT_MAX;
 	sge = __sg_alloc_table_from_pages(sg, pages, nr_pages, 0,
 					  nr_pages << PAGE_SHIFT,
 					  max_segment,
diff --git a/drivers/gpu/drm/i915/i915_scatterlist.h b/drivers/gpu/drm/i915/i915_scatterlist.h
index b7b59328cb76..883dd8d09d6b 100644
--- a/drivers/gpu/drm/i915/i915_scatterlist.h
+++ b/drivers/gpu/drm/i915/i915_scatterlist.h
@@ -112,7 +112,7 @@ static inline unsigned int i915_sg_segment_size(void)
 	unsigned int size = swiotlb_max_segment();
 
 	if (size == 0)
-		return SCATTERLIST_MAX_SEGMENT;
+		size = UINT_MAX;
 
 	size = rounddown(size, PAGE_SIZE);
 	/* swiotlb_max_segment_size can return 1 byte when it means one page. */
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index b3a60959b5d5..0c42d2c05f43 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -794,8 +794,7 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 	if (unlikely(ret != 0))
 		goto out_err0;
 
-	dma_set_max_seg_size(dev->dev, min_t(unsigned int, U32_MAX & PAGE_MASK,
-					     SCATTERLIST_MAX_SEGMENT));
+	dma_set_max_seg_size(dev->dev, U32_MAX);
 
 	if (dev_priv->capabilities & SVGA_CAP_GMR2) {
 		DRM_INFO("Max GMR ids is %u\n",
diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h
index 36c47e7e66a2..6f70572b2938 100644
--- a/include/linux/scatterlist.h
+++ b/include/linux/scatterlist.h
@@ -18,12 +18,6 @@ struct scatterlist {
 #endif
 };
 
-/*
- * Since the above length field is an unsigned int, below we define the maximum
- * length in bytes that can be stored in one scatterlist entry.
- */
-#define SCATTERLIST_MAX_SEGMENT (UINT_MAX & PAGE_MASK)
-
 /*
  * These macros should be used after a dma_map_sg call has been done
  * to get bus addresses of each of the SG entries and their lengths.
diff --git a/tools/testing/scatterlist/main.c b/tools/testing/scatterlist/main.c
index b2c7e9f7b8d3..d264bf853034 100644
--- a/tools/testing/scatterlist/main.c
+++ b/tools/testing/scatterlist/main.c
@@ -50,7 +50,7 @@ static void fail(struct test *test, struct sg_table *st, const char *cond)
 
 int main(void)
 {
-	const unsigned int sgmax = SCATTERLIST_MAX_SEGMENT;
+	const unsigned int sgmax = UINT_MAX;
 	struct test *test, tests[] = {
 		{ -EINVAL, 1, pfn(0), PAGE_SIZE, PAGE_SIZE + 1, 1 },
 		{ -EINVAL, 1, pfn(0), PAGE_SIZE, 0, 1 },
-- 
cgit v1.2.3


From fc0021aa340af65a0a37d77be39e22aa886a6132 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 23 Oct 2020 08:33:09 +0200
Subject: swiotlb: remove the tbl_dma_addr argument to swiotlb_tbl_map_single

The tbl_dma_addr argument is used to check the DMA boundary for the
allocations, and thus needs to be a dma_addr_t.  swiotlb-xen instead
passed a physical address, which could lead to incorrect results for
strange offsets.  Fix this by removing the parameter entirely and hard
code the DMA address for io_tlb_start instead.

Fixes: 91ffe4ad534a ("swiotlb-xen: introduce phys_to_dma/dma_to_phys translations")
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 drivers/iommu/intel/iommu.c |  5 ++---
 drivers/xen/swiotlb-xen.c   |  3 +--
 include/linux/swiotlb.h     | 10 +++-------
 kernel/dma/swiotlb.c        | 16 ++++++----------
 4 files changed, 12 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 8651f6d4dfa0..6b560e6f1930 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -3815,9 +3815,8 @@ bounce_map_single(struct device *dev, phys_addr_t paddr, size_t size,
 	 * page aligned, we don't need to use a bounce page.
 	 */
 	if (!IS_ALIGNED(paddr | size, VTD_PAGE_SIZE)) {
-		tlb_addr = swiotlb_tbl_map_single(dev,
-				phys_to_dma_unencrypted(dev, io_tlb_start),
-				paddr, size, aligned_size, dir, attrs);
+		tlb_addr = swiotlb_tbl_map_single(dev, paddr, size,
+				aligned_size, dir, attrs);
 		if (tlb_addr == DMA_MAPPING_ERROR) {
 			goto swiotlb_error;
 		} else {
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 71ce1b7a23d1..2b385c1b4a99 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -395,8 +395,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 	 */
 	trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force);
 
-	map = swiotlb_tbl_map_single(dev, virt_to_phys(xen_io_tlb_start),
-				     phys, size, size, dir, attrs);
+	map = swiotlb_tbl_map_single(dev, phys, size, size, dir, attrs);
 	if (map == (phys_addr_t)DMA_MAPPING_ERROR)
 		return DMA_MAPPING_ERROR;
 
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 513913ff7486..3bb72266a75a 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -45,13 +45,9 @@ enum dma_sync_target {
 	SYNC_FOR_DEVICE = 1,
 };
 
-extern phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
-					  dma_addr_t tbl_dma_addr,
-					  phys_addr_t phys,
-					  size_t mapping_size,
-					  size_t alloc_size,
-					  enum dma_data_direction dir,
-					  unsigned long attrs);
+phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys,
+		size_t mapping_size, size_t alloc_size,
+		enum dma_data_direction dir, unsigned long attrs);
 
 extern void swiotlb_tbl_unmap_single(struct device *hwdev,
 				     phys_addr_t tlb_addr,
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 54078f0d4c87..781b9dca197c 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -445,14 +445,11 @@ static void swiotlb_bounce(phys_addr_t orig_addr, phys_addr_t tlb_addr,
 	}
 }
 
-phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
-				   dma_addr_t tbl_dma_addr,
-				   phys_addr_t orig_addr,
-				   size_t mapping_size,
-				   size_t alloc_size,
-				   enum dma_data_direction dir,
-				   unsigned long attrs)
+phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t orig_addr,
+		size_t mapping_size, size_t alloc_size,
+		enum dma_data_direction dir, unsigned long attrs)
 {
+	dma_addr_t tbl_dma_addr = phys_to_dma_unencrypted(hwdev, io_tlb_start);
 	unsigned long flags;
 	phys_addr_t tlb_addr;
 	unsigned int nslots, stride, index, wrap;
@@ -671,9 +668,8 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size,
 	trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size,
 			      swiotlb_force);
 
-	swiotlb_addr = swiotlb_tbl_map_single(dev,
-			phys_to_dma_unencrypted(dev, io_tlb_start),
-			paddr, size, size, dir, attrs);
+	swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, size, dir,
+			attrs);
 	if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR)
 		return DMA_MAPPING_ERROR;
 
-- 
cgit v1.2.3


From e0e398e204634db8fb71bd89cf2f6e3e5bd09b51 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Wed, 21 Oct 2020 21:12:15 +0200
Subject: PM: runtime: Drop runtime PM references to supplier on link removal

While removing a device link, drop the supplier device's runtime PM
usage counter as many times as needed to drop all of the runtime PM
references to it from the consumer in addition to dropping the
consumer's link count.

Fixes: baa8809f6097 ("PM / runtime: Optimize the use of device links")
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: 5.1+ <stable@vger.kernel.org> # 5.1+
Tested-by: Xiang Chen <chenxiang66@hisilicon.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/core.c          |  6 ++----
 drivers/base/power/runtime.c | 21 ++++++++++++++++++++-
 include/linux/pm_runtime.h   |  4 ++--
 3 files changed, 24 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/core.c b/drivers/base/core.c
index 78114ddac755..d661ada1518f 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -773,8 +773,7 @@ static void __device_link_del(struct kref *kref)
 	dev_dbg(link->consumer, "Dropping the link to %s\n",
 		dev_name(link->supplier));
 
-	if (link->flags & DL_FLAG_PM_RUNTIME)
-		pm_runtime_drop_link(link->consumer);
+	pm_runtime_drop_link(link);
 
 	list_del_rcu(&link->s_node);
 	list_del_rcu(&link->c_node);
@@ -788,8 +787,7 @@ static void __device_link_del(struct kref *kref)
 	dev_info(link->consumer, "Dropping the link to %s\n",
 		 dev_name(link->supplier));
 
-	if (link->flags & DL_FLAG_PM_RUNTIME)
-		pm_runtime_drop_link(link->consumer);
+	pm_runtime_drop_link(link);
 
 	list_del(&link->s_node);
 	list_del(&link->c_node);
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 6f605f7820bb..6919f7fc226b 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -1729,7 +1729,7 @@ void pm_runtime_new_link(struct device *dev)
 	spin_unlock_irq(&dev->power.lock);
 }
 
-void pm_runtime_drop_link(struct device *dev)
+static void pm_runtime_drop_link_count(struct device *dev)
 {
 	spin_lock_irq(&dev->power.lock);
 	WARN_ON(dev->power.links_count == 0);
@@ -1737,6 +1737,25 @@ void pm_runtime_drop_link(struct device *dev)
 	spin_unlock_irq(&dev->power.lock);
 }
 
+/**
+ * pm_runtime_drop_link - Prepare for device link removal.
+ * @link: Device link going away.
+ *
+ * Drop the link count of the consumer end of @link and decrement the supplier
+ * device's runtime PM usage counter as many times as needed to drop all of the
+ * PM runtime reference to it from the consumer.
+ */
+void pm_runtime_drop_link(struct device_link *link)
+{
+	if (!(link->flags & DL_FLAG_PM_RUNTIME))
+		return;
+
+	pm_runtime_drop_link_count(link->consumer);
+
+	while (refcount_dec_not_one(&link->rpm_active))
+		pm_runtime_put(link->supplier);
+}
+
 static bool pm_runtime_need_not_resume(struct device *dev)
 {
 	return atomic_read(&dev->power.usage_count) <= 1 &&
diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index 18b02dcc168e..eadc1fdebce6 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -58,7 +58,7 @@ extern void pm_runtime_clean_up_links(struct device *dev);
 extern void pm_runtime_get_suppliers(struct device *dev);
 extern void pm_runtime_put_suppliers(struct device *dev);
 extern void pm_runtime_new_link(struct device *dev);
-extern void pm_runtime_drop_link(struct device *dev);
+extern void pm_runtime_drop_link(struct device_link *link);
 
 /**
  * pm_runtime_get_if_in_use - Conditionally bump up runtime PM usage counter.
@@ -280,7 +280,7 @@ static inline void pm_runtime_clean_up_links(struct device *dev) {}
 static inline void pm_runtime_get_suppliers(struct device *dev) {}
 static inline void pm_runtime_put_suppliers(struct device *dev) {}
 static inline void pm_runtime_new_link(struct device *dev) {}
-static inline void pm_runtime_drop_link(struct device *dev) {}
+static inline void pm_runtime_drop_link(struct device_link *link) {}
 
 #endif /* !CONFIG_PM */
 
-- 
cgit v1.2.3


From d6e36668598154820177bfd78c1621d8e6c580a2 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Wed, 21 Oct 2020 21:13:10 +0200
Subject: PM: runtime: Drop pm_runtime_clean_up_links()

After commit d12544fb2aa9 ("PM: runtime: Remove link state checks in
rpm_get/put_supplier()") nothing prevents the consumer device's
runtime PM from acquiring additional references to the supplier
device after pm_runtime_clean_up_links() has run (or even while it
is running), so calling this function from __device_release_driver()
may be pointless (or even harmful).

Moreover, it ignores stateless device links, so the runtime PM
handling of managed and stateless device links is inconsistent
because of it, so better get rid of it entirely.

Fixes: d12544fb2aa9 ("PM: runtime: Remove link state checks in rpm_get/put_supplier()")
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: 5.1+ <stable@vger.kernel.org> # 5.1+
Tested-by: Xiang Chen <chenxiang66@hisilicon.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/dd.c            |  1 -
 drivers/base/power/runtime.c | 36 ------------------------------------
 include/linux/pm_runtime.h   |  2 --
 3 files changed, 39 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index b42229b74fd6..122b0372fdc9 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -1133,7 +1133,6 @@ static void __device_release_driver(struct device *dev, struct device *parent)
 		}
 
 		pm_runtime_get_sync(dev);
-		pm_runtime_clean_up_links(dev);
 
 		driver_sysfs_remove(dev);
 
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 6919f7fc226b..bfda153b1a41 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -1642,42 +1642,6 @@ void pm_runtime_remove(struct device *dev)
 	pm_runtime_reinit(dev);
 }
 
-/**
- * pm_runtime_clean_up_links - Prepare links to consumers for driver removal.
- * @dev: Device whose driver is going to be removed.
- *
- * Check links from this device to any consumers and if any of them have active
- * runtime PM references to the device, drop the usage counter of the device
- * (as many times as needed).
- *
- * Links with the DL_FLAG_MANAGED flag unset are ignored.
- *
- * Since the device is guaranteed to be runtime-active at the point this is
- * called, nothing else needs to be done here.
- *
- * Moreover, this is called after device_links_busy() has returned 'false', so
- * the status of each link is guaranteed to be DL_STATE_SUPPLIER_UNBIND and
- * therefore rpm_active can't be manipulated concurrently.
- */
-void pm_runtime_clean_up_links(struct device *dev)
-{
-	struct device_link *link;
-	int idx;
-
-	idx = device_links_read_lock();
-
-	list_for_each_entry_rcu(link, &dev->links.consumers, s_node,
-				device_links_read_lock_held()) {
-		if (!(link->flags & DL_FLAG_MANAGED))
-			continue;
-
-		while (refcount_dec_not_one(&link->rpm_active))
-			pm_runtime_put_noidle(dev);
-	}
-
-	device_links_read_unlock(idx);
-}
-
 /**
  * pm_runtime_get_suppliers - Resume and reference-count supplier devices.
  * @dev: Consumer device.
diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index eadc1fdebce6..4b708f4e8eed 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -54,7 +54,6 @@ extern u64 pm_runtime_autosuspend_expiration(struct device *dev);
 extern void pm_runtime_update_max_time_suspended(struct device *dev,
 						 s64 delta_ns);
 extern void pm_runtime_set_memalloc_noio(struct device *dev, bool enable);
-extern void pm_runtime_clean_up_links(struct device *dev);
 extern void pm_runtime_get_suppliers(struct device *dev);
 extern void pm_runtime_put_suppliers(struct device *dev);
 extern void pm_runtime_new_link(struct device *dev);
@@ -276,7 +275,6 @@ static inline u64 pm_runtime_autosuspend_expiration(
 				struct device *dev) { return 0; }
 static inline void pm_runtime_set_memalloc_noio(struct device *dev,
 						bool enable){}
-static inline void pm_runtime_clean_up_links(struct device *dev) {}
 static inline void pm_runtime_get_suppliers(struct device *dev) {}
 static inline void pm_runtime_put_suppliers(struct device *dev) {}
 static inline void pm_runtime_new_link(struct device *dev) {}
-- 
cgit v1.2.3


From 56a7ff75cd08987812209971e319f78156ea2bb1 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Thu, 22 Oct 2020 13:57:45 +0200
Subject: cpufreq: Drop restore_freq from struct cpufreq_policy

The restore_freq field in struct cpufreq_policy is only used by
__target_index() in one place and a local variable in that function
may as well be used instead of it, so drop it and modify
__target_index() accordingly.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
---
 drivers/cpufreq/cpufreq.c | 10 +++++-----
 include/linux/cpufreq.h   |  5 -----
 2 files changed, 5 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 336b5e94cbc8..f2d96175f62d 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -2123,7 +2123,7 @@ static int __target_intermediate(struct cpufreq_policy *policy,
 static int __target_index(struct cpufreq_policy *policy, int index)
 {
 	struct cpufreq_freqs freqs = {.old = policy->cur, .flags = 0};
-	unsigned int intermediate_freq = 0;
+	unsigned int restore_freq, intermediate_freq = 0;
 	unsigned int newfreq = policy->freq_table[index].frequency;
 	int retval = -EINVAL;
 	bool notify;
@@ -2131,6 +2131,9 @@ static int __target_index(struct cpufreq_policy *policy, int index)
 	if (newfreq == policy->cur)
 		return 0;
 
+	/* Save last value to restore later on errors */
+	restore_freq = policy->cur;
+
 	notify = !(cpufreq_driver->flags & CPUFREQ_ASYNC_NOTIFICATION);
 	if (notify) {
 		/* Handle switching to intermediate frequency */
@@ -2168,7 +2171,7 @@ static int __target_index(struct cpufreq_policy *policy, int index)
 		 */
 		if (unlikely(retval && intermediate_freq)) {
 			freqs.old = intermediate_freq;
-			freqs.new = policy->restore_freq;
+			freqs.new = restore_freq;
 			cpufreq_freq_transition_begin(policy, &freqs);
 			cpufreq_freq_transition_end(policy, &freqs, 0);
 		}
@@ -2203,9 +2206,6 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy,
 	    !(cpufreq_driver->flags & CPUFREQ_NEED_UPDATE_LIMITS))
 		return 0;
 
-	/* Save last value to restore later on errors */
-	policy->restore_freq = policy->cur;
-
 	if (cpufreq_driver->target)
 		return cpufreq_driver->target(policy, target_freq, relation);
 
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 1eaa04f1bae6..9779a6cd8baa 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -65,7 +65,6 @@ struct cpufreq_policy {
 	unsigned int		max;    /* in kHz */
 	unsigned int		cur;    /* in kHz, only needed if cpufreq
 					 * governors are used */
-	unsigned int		restore_freq; /* = policy->cur before transition */
 	unsigned int		suspend_freq; /* freq to set during suspend */
 
 	unsigned int		policy; /* see above */
@@ -308,10 +307,6 @@ struct cpufreq_driver {
 	/* define one out of two */
 	int		(*setpolicy)(struct cpufreq_policy *policy);
 
-	/*
-	 * On failure, should always restore frequency to policy->restore_freq
-	 * (i.e. old freq).
-	 */
 	int		(*target)(struct cpufreq_policy *policy,
 				  unsigned int target_freq,
 				  unsigned int relation);	/* Deprecated */
-- 
cgit v1.2.3


From b000d5cb954fe25ac1ea929ae6da321033ace927 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Tue, 13 Oct 2020 10:18:04 +0200
Subject: ima: defer arch_ima_get_secureboot() call to IMA init time

Chester reports that it is necessary to introduce a new way to pass
the EFI secure boot status between the EFI stub and the core kernel
on ARM systems. The usual way of obtaining this information is by
checking the SecureBoot and SetupMode EFI variables, but this can
only be done after the EFI variable workqueue is created, which
occurs in a subsys_initcall(), whereas arch_ima_get_secureboot()
is called much earlier by the IMA framework.

However, the IMA framework itself is started as a late_initcall,
and the only reason the call to arch_ima_get_secureboot() occurs
so early is because it happens in the context of a __setup()
callback that parses the ima_appraise= command line parameter.

So let's refactor this code a little bit, by using a core_param()
callback to capture the command line argument, and deferring any
reasoning based on its contents to the IMA init routine.

Cc: Chester Lin <clin@suse.com>
Cc: Dmitry Kasatkin <dmitry.kasatkin@gmail.com>
Cc: James Morris <jmorris@namei.org>
Cc: "Serge E. Hallyn" <serge@hallyn.com>
Link: https://lore.kernel.org/linux-arm-kernel/20200904072905.25332-2-clin@suse.com/
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Reported-by: kernel test robot <lkp@intel.com> [missing core_param()]
[zohar@linux.ibm.com: included linux/module.h]
Tested-by: Chester Lin <clin@suse.com>
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
---
 include/linux/ima.h                   |  6 ++++++
 security/integrity/ima/ima_appraise.c | 17 +++++++++++------
 security/integrity/ima/ima_main.c     |  1 +
 3 files changed, 18 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ima.h b/include/linux/ima.h
index 8fa7bcfb2da2..ac3d82f962f2 100644
--- a/include/linux/ima.h
+++ b/include/linux/ima.h
@@ -31,6 +31,12 @@ extern void ima_post_path_mknod(struct dentry *dentry);
 extern int ima_file_hash(struct file *file, char *buf, size_t buf_size);
 extern void ima_kexec_cmdline(int kernel_fd, const void *buf, int size);
 
+#ifdef CONFIG_IMA_APPRAISE_BOOTPARAM
+extern void ima_appraise_parse_cmdline(void);
+#else
+static inline void ima_appraise_parse_cmdline(void) {}
+#endif
+
 #ifdef CONFIG_IMA_KEXEC
 extern void ima_add_kexec_buffer(struct kimage *image);
 #endif
diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c
index 3dd8c2e4314e..8361941ee0a1 100644
--- a/security/integrity/ima/ima_appraise.c
+++ b/security/integrity/ima/ima_appraise.c
@@ -5,6 +5,7 @@
  * Author:
  * Mimi Zohar <zohar@us.ibm.com>
  */
+#include <linux/module.h>
 #include <linux/init.h>
 #include <linux/file.h>
 #include <linux/fs.h>
@@ -16,12 +17,19 @@
 
 #include "ima.h"
 
-static int __init default_appraise_setup(char *str)
-{
 #ifdef CONFIG_IMA_APPRAISE_BOOTPARAM
+static char *ima_appraise_cmdline_default __initdata;
+core_param(ima_appraise, ima_appraise_cmdline_default, charp, 0);
+
+void __init ima_appraise_parse_cmdline(void)
+{
+	const char *str = ima_appraise_cmdline_default;
 	bool sb_state = arch_ima_get_secureboot();
 	int appraisal_state = ima_appraise;
 
+	if (!str)
+		return;
+
 	if (strncmp(str, "off", 3) == 0)
 		appraisal_state = 0;
 	else if (strncmp(str, "log", 3) == 0)
@@ -42,11 +50,8 @@ static int __init default_appraise_setup(char *str)
 	} else {
 		ima_appraise = appraisal_state;
 	}
-#endif
-	return 1;
 }
-
-__setup("ima_appraise=", default_appraise_setup);
+#endif
 
 /*
  * is_ima_appraise_enabled - return appraise status
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index 2d1af8899cab..a962b23e0429 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -904,6 +904,7 @@ static int __init init_ima(void)
 {
 	int error;
 
+	ima_appraise_parse_cmdline();
 	ima_init_template_list();
 	hash_setup(CONFIG_IMA_DEFAULT_HASH);
 	error = ima_init();
-- 
cgit v1.2.3


From 24269999027e6b161c0078ad9c1557f9a1575128 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Fri, 23 Oct 2020 18:32:57 +0200
Subject: EDAC: Fix some kernel-doc markups

Kernel-doc markup should use this format:
        identifier - description

Correct that and also fix some enums' names in the kernel-doc markup.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/1d291393ba58c7b80908a3fedf02d2f53921ffe9.1603469755.git.mchehab+huawei@kernel.org
---
 drivers/edac/edac_device.h | 11 +++++------
 include/linux/edac.h       |  4 ++--
 2 files changed, 7 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/edac/edac_device.h b/drivers/edac/edac_device.h
index c4c0e0bdce14..fc2d2c218064 100644
--- a/drivers/edac/edac_device.h
+++ b/drivers/edac/edac_device.h
@@ -258,7 +258,7 @@ extern struct edac_device_ctl_info *edac_device_alloc_ctl_info(
 extern void edac_device_free_ctl_info(struct edac_device_ctl_info *ctl_info);
 
 /**
- * edac_device_add_device: Insert the 'edac_dev' structure into the
+ * edac_device_add_device - Insert the 'edac_dev' structure into the
  *	 edac_device global list and create sysfs entries associated with
  *	 edac_device structure.
  *
@@ -271,9 +271,8 @@ extern void edac_device_free_ctl_info(struct edac_device_ctl_info *ctl_info);
 extern int edac_device_add_device(struct edac_device_ctl_info *edac_dev);
 
 /**
- * edac_device_del_device:
- *	Remove sysfs entries for specified edac_device structure and
- *	then remove edac_device structure from global list
+ * edac_device_del_device - Remove sysfs entries for specified edac_device
+ *	structure and then remove edac_device structure from global list
  *
  * @dev:
  *	Pointer to struct &device representing the edac device
@@ -286,7 +285,7 @@ extern int edac_device_add_device(struct edac_device_ctl_info *edac_dev);
 extern struct edac_device_ctl_info *edac_device_del_device(struct device *dev);
 
 /**
- * Log correctable errors.
+ * edac_device_handle_ce_count - Log correctable errors.
  *
  * @edac_dev: pointer to struct &edac_device_ctl_info
  * @inst_nr: number of the instance where the CE error happened
@@ -299,7 +298,7 @@ void edac_device_handle_ce_count(struct edac_device_ctl_info *edac_dev,
 				 const char *msg);
 
 /**
- * Log uncorrectable errors.
+ * edac_device_handle_ue_count - Log uncorrectable errors.
  *
  * @edac_dev: pointer to struct &edac_device_ctl_info
  * @inst_nr: number of the instance where the CE error happened
diff --git a/include/linux/edac.h b/include/linux/edac.h
index 15e8f3d8a895..52d7487f6bd4 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -229,7 +229,7 @@ enum mem_type {
 #define MEM_FLAG_NVDIMM         BIT(MEM_NVDIMM)
 
 /**
- * enum edac-type - Error Detection and Correction capabilities and mode
+ * enum edac_type - Error Detection and Correction capabilities and mode
  * @EDAC_UNKNOWN:	Unknown if ECC is available
  * @EDAC_NONE:		Doesn't support ECC
  * @EDAC_RESERVED:	Reserved ECC type
@@ -309,7 +309,7 @@ enum scrub_type {
 #define OP_OFFLINE		0x300
 
 /**
- * enum edac_mc_layer - memory controller hierarchy layer
+ * enum edac_mc_layer_type - memory controller hierarchy layer
  *
  * @EDAC_MC_LAYER_BRANCH:	memory layer is named "branch"
  * @EDAC_MC_LAYER_CHANNEL:	memory layer is named "channel"
-- 
cgit v1.2.3


From f8f6ae5d077a9bdaf5cbf2ac960a5d1a04b47482 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Sun, 1 Nov 2020 17:08:00 -0800
Subject: mm: always have io_remap_pfn_range() set pgprot_decrypted()

The purpose of io_remap_pfn_range() is to map IO memory, such as a
memory mapped IO exposed through a PCI BAR.  IO devices do not
understand encryption, so this memory must always be decrypted.
Automatically call pgprot_decrypted() as part of the generic
implementation.

This fixes a bug where enabling AMD SME causes subsystems, such as RDMA,
using io_remap_pfn_range() to expose BAR pages to user space to fail.
The CPU will encrypt access to those BAR pages instead of passing
unencrypted IO directly to the device.

Places not mapping IO should use remap_pfn_range().

Fixes: aca20d546214 ("x86/mm: Add support to make use of Secure Memory Encryption")
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brijesh Singh <brijesh.singh@amd.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: "Dave Young" <dyoung@redhat.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Larry Woodman <lwoodman@redhat.com>
Cc: Matt Fleming <matt@codeblueprint.co.uk>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Toshimitsu Kani <toshi.kani@hpe.com>
Cc: <stable@vger.kernel.org>
Link: https://lkml.kernel.org/r/0-v1-025d64bdf6c4+e-amd_sme_fix_jgg@nvidia.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h      | 9 +++++++++
 include/linux/pgtable.h | 4 ----
 2 files changed, 9 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index ef360fe70aaf..db6ae4d3fb4e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2759,6 +2759,15 @@ static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma,
 	return VM_FAULT_NOPAGE;
 }
 
+#ifndef io_remap_pfn_range
+static inline int io_remap_pfn_range(struct vm_area_struct *vma,
+				     unsigned long addr, unsigned long pfn,
+				     unsigned long size, pgprot_t prot)
+{
+	return remap_pfn_range(vma, addr, pfn, size, pgprot_decrypted(prot));
+}
+#endif
+
 static inline vm_fault_t vmf_error(int err)
 {
 	if (err == -ENOMEM)
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 38c33eabea89..71125a4676c4 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1427,10 +1427,6 @@ typedef unsigned int pgtbl_mod_mask;
 
 #endif /* !__ASSEMBLY__ */
 
-#ifndef io_remap_pfn_range
-#define io_remap_pfn_range remap_pfn_range
-#endif
-
 #ifndef has_transparent_hugepage
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define has_transparent_hugepage() 1
-- 
cgit v1.2.3


From 9f14cb030d987ae5e201e88cd345c6d772bcce51 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 16 Sep 2020 11:45:22 -0700
Subject: sched: Un-hide lockdep_tasklist_lock_is_held() for !LOCKDEP

Currently, variables used only within lockdep expressions are flagged as
unused, requiring that these variables' declarations be decorated with
either #ifdef or __maybe_unused.  This results in ugly code.  This commit
therefore causes the lockdep_tasklist_lock_is_held() function to be
visible even when lockdep is not enabled, thus removing the need for
these decorations.  This approach further relies on dead-code elimination
to remove any references to functions or variables that are not available
in non-lockdep kernels.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/sched/task.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 85fb2f34c59b..c0f71f2e7160 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -47,9 +47,7 @@ extern spinlock_t mmlist_lock;
 extern union thread_union init_thread_union;
 extern struct task_struct init_task;
 
-#ifdef CONFIG_PROVE_RCU
 extern int lockdep_tasklist_lock_is_held(void);
-#endif /* #ifdef CONFIG_PROVE_RCU */
 
 extern asmlinkage void schedule_tail(struct task_struct *prev);
 extern void init_idle(struct task_struct *idle, int cpu);
-- 
cgit v1.2.3


From 891cd1f99dd94746f0caf5eea0121079178ee9bf Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 16 Sep 2020 11:45:23 -0700
Subject: rcu: Un-hide lockdep maps for !LOCKDEP

Currently, variables used only within lockdep expressions are flagged as
unused, requiring that these variables' declarations be decorated with
either #ifdef or __maybe_unused.  This results in ugly code.  This commit
therefore causes the RCU lock maps to be visible even when lockdep is not
enabled, thus removing the need for these decorations.  This approach
further relies on dead-code elimination to remove any references to
functions or variables that are not available in non-lockdep kernels.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/rcupdate.h       | 9 +++++----
 include/linux/rcupdate_trace.h | 4 ++--
 2 files changed, 7 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 6cdd0152c253..f9533bbcbb36 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -241,6 +241,11 @@ bool rcu_lockdep_current_cpu_online(void);
 static inline bool rcu_lockdep_current_cpu_online(void) { return true; }
 #endif /* #else #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */
 
+extern struct lockdep_map rcu_lock_map;
+extern struct lockdep_map rcu_bh_lock_map;
+extern struct lockdep_map rcu_sched_lock_map;
+extern struct lockdep_map rcu_callback_map;
+
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 
 static inline void rcu_lock_acquire(struct lockdep_map *map)
@@ -253,10 +258,6 @@ static inline void rcu_lock_release(struct lockdep_map *map)
 	lock_release(map, _THIS_IP_);
 }
 
-extern struct lockdep_map rcu_lock_map;
-extern struct lockdep_map rcu_bh_lock_map;
-extern struct lockdep_map rcu_sched_lock_map;
-extern struct lockdep_map rcu_callback_map;
 int debug_lockdep_rcu_enabled(void);
 int rcu_read_lock_held(void);
 int rcu_read_lock_bh_held(void);
diff --git a/include/linux/rcupdate_trace.h b/include/linux/rcupdate_trace.h
index 3e7919fc5f34..86c8f6c98412 100644
--- a/include/linux/rcupdate_trace.h
+++ b/include/linux/rcupdate_trace.h
@@ -11,10 +11,10 @@
 #include <linux/sched.h>
 #include <linux/rcupdate.h>
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-
 extern struct lockdep_map rcu_trace_lock_map;
 
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+
 static inline int rcu_read_lock_trace_held(void)
 {
 	return lock_is_held(&rcu_trace_lock_map);
-- 
cgit v1.2.3


From cd539cff9470fe1dacf0bf5ab3f54f37b854d6fc Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 16 Sep 2020 11:45:27 -0700
Subject: lockdep: Provide dummy forward declaration of *_is_held() helpers

When CONFIG_LOCKDEP is not set, lock_is_held() and lockdep_is_held()
are not declared or defined.  This forces all callers to use #ifdefs
around these checks.

Recent RCU changes added a lot of lockdep_is_held() calls inside
rcu_dereference_protected().  This macro hides its argument on !LOCKDEP
builds, which can lead to false-positive unused-variable warnings.

This commit therefore provides forward declarations of lock_is_held()
and lockdep_is_held() but without defining them.  This way callers
(including those internal to RCU) can keep them visible to the compiler
on !LOCKDEP builds and instead depend on dead code elimination to remove
the references, which in turn prevents the linker from complaining about
the lack of the corresponding function definitions.

[ paulmck: Apply Peter Zijlstra feedback on "extern". ]
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
--
CC: peterz@infradead.org
CC: mingo@redhat.com
CC: will@kernel.org
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/lockdep.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index f5594879175a..ccc3ce66c7e0 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -375,6 +375,12 @@ static inline void lockdep_unregister_key(struct lock_class_key *key)
 
 #define lockdep_depth(tsk)	(0)
 
+/*
+ * Dummy forward declarations, allow users to write less ifdef-y code
+ * and depend on dead code elimination.
+ */
+extern int lock_is_held(const void *);
+extern int lockdep_is_held(const void *);
 #define lockdep_is_held_type(l, r)		(1)
 
 #define lockdep_assert_held(l)			do { (void)(l); } while (0)
-- 
cgit v1.2.3


From 65e9eb1ccfe56b41a0d8bfec651ea014968413cb Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 16 Sep 2020 11:45:28 -0700
Subject: rcu: Prevent RCU_LOCKDEP_WARN() from swallowing the condition

We run into a unused variable warning in bridge code when variable is
only used inside the condition of rcu_dereference_protected().

 #define mlock_dereference(X, br) \
	rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock))

Since on builds with CONFIG_PROVE_RCU=n rcu_dereference_protected()
compiles to nothing the compiler doesn't see the variable use.

This commit therefore prevents this warning by adding the condition as
dead code.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
--
CC: paulmck@kernel.org
CC: josh@joshtriplett.org
CC: rostedt@goodmis.org
CC: mathieu.desnoyers@efficios.com
CC: joel@joelfernandes.org
CC: jiangshanlai@gmail.com
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/rcupdate.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index f9533bbcbb36..de0826411311 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -328,7 +328,7 @@ static inline void rcu_preempt_sleep_check(void) { }
 
 #else /* #ifdef CONFIG_PROVE_RCU */
 
-#define RCU_LOCKDEP_WARN(c, s) do { } while (0)
+#define RCU_LOCKDEP_WARN(c, s) do { } while (0 && (c))
 #define rcu_sleep_check() do { } while (0)
 
 #endif /* #else #ifdef CONFIG_PROVE_RCU */
-- 
cgit v1.2.3


From 6370cc3bbd8a0f9bf975b013781243ab147876c6 Mon Sep 17 00:00:00 2001
From: Aleksandr Nogikh <nogikh@google.com>
Date: Thu, 29 Oct 2020 17:36:19 +0000
Subject: net: add kcov handle to skb extensions

Remote KCOV coverage collection enables coverage-guided fuzzing of the
code that is not reachable during normal system call execution. It is
especially helpful for fuzzing networking subsystems, where it is
common to perform packet handling in separate work queues even for the
packets that originated directly from the user space.

Enable coverage-guided frame injection by adding kcov remote handle to
skb extensions. Default initialization in __alloc_skb and
__build_skb_around ensures that no socket buffer that was generated
during a system call will be missed.

Code that is of interest and that performs packet processing should be
annotated with kcov_remote_start()/kcov_remote_stop().

An alternative approach is to determine kcov_handle solely on the
basis of the device/interface that received the specific socket
buffer. However, in this case it would be impossible to distinguish
between packets that originated during normal background network
processes or were intentionally injected from the user space.

Signed-off-by: Aleksandr Nogikh <nogikh@google.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/skbuff.h | 33 +++++++++++++++++++++++++++++++++
 lib/Kconfig.debug      |  1 +
 net/core/skbuff.c      | 11 +++++++++++
 3 files changed, 45 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index a828cf99c521..2d01b2bbb746 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -4150,6 +4150,9 @@ enum skb_ext_id {
 #endif
 #if IS_ENABLED(CONFIG_MPTCP)
 	SKB_EXT_MPTCP,
+#endif
+#if IS_ENABLED(CONFIG_KCOV)
+	SKB_EXT_KCOV_HANDLE,
 #endif
 	SKB_EXT_NUM, /* must be last */
 };
@@ -4605,5 +4608,35 @@ static inline void skb_reset_redirect(struct sk_buff *skb)
 #endif
 }
 
+#ifdef CONFIG_KCOV
+static inline void skb_set_kcov_handle(struct sk_buff *skb,
+				       const u64 kcov_handle)
+{
+	/* Do not allocate skb extensions only to set kcov_handle to zero
+	 * (as it is zero by default). However, if the extensions are
+	 * already allocated, update kcov_handle anyway since
+	 * skb_set_kcov_handle can be called to zero a previously set
+	 * value.
+	 */
+	if (skb_has_extensions(skb) || kcov_handle) {
+		u64 *kcov_handle_ptr = skb_ext_add(skb, SKB_EXT_KCOV_HANDLE);
+
+		if (kcov_handle_ptr)
+			*kcov_handle_ptr = kcov_handle;
+	}
+}
+
+static inline u64 skb_get_kcov_handle(struct sk_buff *skb)
+{
+	u64 *kcov_handle = skb_ext_find(skb, SKB_EXT_KCOV_HANDLE);
+
+	return kcov_handle ? *kcov_handle : 0;
+}
+#else
+static inline void skb_set_kcov_handle(struct sk_buff *skb,
+				       const u64 kcov_handle) { }
+static inline u64 skb_get_kcov_handle(struct sk_buff *skb) { return 0; }
+#endif /* CONFIG_KCOV */
+
 #endif	/* __KERNEL__ */
 #endif	/* _LINUX_SKBUFF_H */
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index d7a7bc3b6098..d171a032db78 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1870,6 +1870,7 @@ config KCOV
 	depends on CC_HAS_SANCOV_TRACE_PC || GCC_PLUGINS
 	select DEBUG_FS
 	select GCC_PLUGIN_SANCOV if !CC_HAS_SANCOV_TRACE_PC
+	select SKB_EXTENSIONS
 	help
 	  KCOV exposes kernel code coverage information in a form suitable
 	  for coverage-guided fuzzing (randomized testing).
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 1ba8f0163744..c5e6c0b83a92 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -249,6 +249,9 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
 
 		fclones->skb2.fclone = SKB_FCLONE_CLONE;
 	}
+
+	skb_set_kcov_handle(skb, kcov_common_handle());
+
 out:
 	return skb;
 nodata:
@@ -282,6 +285,8 @@ static struct sk_buff *__build_skb_around(struct sk_buff *skb,
 	memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
 	atomic_set(&shinfo->dataref, 1);
 
+	skb_set_kcov_handle(skb, kcov_common_handle());
+
 	return skb;
 }
 
@@ -4203,6 +4208,9 @@ static const u8 skb_ext_type_len[] = {
 #if IS_ENABLED(CONFIG_MPTCP)
 	[SKB_EXT_MPTCP] = SKB_EXT_CHUNKSIZEOF(struct mptcp_ext),
 #endif
+#if IS_ENABLED(CONFIG_KCOV)
+	[SKB_EXT_KCOV_HANDLE] = SKB_EXT_CHUNKSIZEOF(u64),
+#endif
 };
 
 static __always_inline unsigned int skb_ext_total_length(void)
@@ -4219,6 +4227,9 @@ static __always_inline unsigned int skb_ext_total_length(void)
 #endif
 #if IS_ENABLED(CONFIG_MPTCP)
 		skb_ext_type_len[SKB_EXT_MPTCP] +
+#endif
+#if IS_ENABLED(CONFIG_KCOV)
+		skb_ext_type_len[SKB_EXT_KCOV_HANDLE] +
 #endif
 		0;
 }
-- 
cgit v1.2.3


From 31909e3330c8d65e9a928d40833ebd5feb4f64e6 Mon Sep 17 00:00:00 2001
From: Michael Weiß <michael.weiss@aisec.fraunhofer.de>
Date: Tue, 27 Oct 2020 21:42:56 +0100
Subject: timens: additional helper functions for boottime offset handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Provide functions for time_namespace to subtract the boottime offset
from a timespec64 as well as to apply the boottime offset to u64 types in
nanoseconds.

Signed-off-by: Michael Weiß <michael.weiss@aisec.fraunhofer.de>
Reviewed-by: Andrei Vagin <avagin@gmail.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Link: https://lore.kernel.org/r/20201027204258.7869-2-michael.weiss@aisec.fraunhofer.de
---
 include/linux/time_namespace.h | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/time_namespace.h b/include/linux/time_namespace.h
index 5b6031385db0..68770ac9ba89 100644
--- a/include/linux/time_namespace.h
+++ b/include/linux/time_namespace.h
@@ -77,6 +77,20 @@ static inline void timens_add_boottime(struct timespec64 *ts)
 	*ts = timespec64_add(*ts, ns_offsets->boottime);
 }
 
+static inline u64 timens_add_boottime_ns(u64 nsec)
+{
+	struct timens_offsets *ns_offsets = &current->nsproxy->time_ns->offsets;
+
+	return nsec + timespec64_to_ns(&ns_offsets->boottime);
+}
+
+static inline void timens_sub_boottime(struct timespec64 *ts)
+{
+	struct timens_offsets *ns_offsets = &current->nsproxy->time_ns->offsets;
+
+	*ts = timespec64_sub(*ts, ns_offsets->boottime);
+}
+
 ktime_t do_timens_ktime_to_host(clockid_t clockid, ktime_t tim,
 				struct timens_offsets *offsets);
 
@@ -130,6 +144,14 @@ static inline int timens_on_fork(struct nsproxy *nsproxy,
 
 static inline void timens_add_monotonic(struct timespec64 *ts) { }
 static inline void timens_add_boottime(struct timespec64 *ts) { }
+
+static inline u64 timens_add_boottime_ns(u64 nsec)
+{
+	return nsec;
+}
+
+static inline void timens_sub_boottime(struct timespec64 *ts) { }
+
 static inline ktime_t timens_ktime_to_host(clockid_t clockid, ktime_t tim)
 {
 	return tim;
-- 
cgit v1.2.3


From 5190db9fdd20fa5ba6084c98a3bc71c2fdf6a871 Mon Sep 17 00:00:00 2001
From: Roman Anufriev <dotdot@yandex-team.ru>
Date: Sun, 18 Oct 2020 05:56:54 +0300
Subject: fs/quota: update quota state flags scheme with project quota flags

Current quota state flags scheme doesn't include project quota and thus
shows all flags after DQUOT_USAGE_ENABLED wrong. Fix this and also add
DQUOT_NOLIST_DIRTY to the scheme.

Link: https://lore.kernel.org/r/1602989814-28922-1-git-send-email-dotdot@yandex-team.ru
Signed-off-by: Roman Anufriev <dotdot@yandex-team.ru>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 include/linux/quota.h | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/quota.h b/include/linux/quota.h
index 27aab84fcbaa..18ebd39c9487 100644
--- a/include/linux/quota.h
+++ b/include/linux/quota.h
@@ -448,17 +448,18 @@ struct quota_format_type {
 };
 
 /**
- * Quota state flags - they actually come in two flavors - for users and groups.
+ * Quota state flags - they come in three flavors - for users, groups and projects.
  *
  * Actual typed flags layout:
- *				USRQUOTA	GRPQUOTA
- *  DQUOT_USAGE_ENABLED		0x0001		0x0002
- *  DQUOT_LIMITS_ENABLED	0x0004		0x0008
- *  DQUOT_SUSPENDED		0x0010		0x0020
+ *				USRQUOTA	GRPQUOTA	PRJQUOTA
+ *  DQUOT_USAGE_ENABLED		0x0001		0x0002		0x0004
+ *  DQUOT_LIMITS_ENABLED	0x0008		0x0010		0x0020
+ *  DQUOT_SUSPENDED		0x0040		0x0080		0x0100
  *
  * Following bits are used for non-typed flags:
- *  DQUOT_QUOTA_SYS_FILE	0x0040
- *  DQUOT_NEGATIVE_USAGE	0x0080
+ *  DQUOT_QUOTA_SYS_FILE	0x0200
+ *  DQUOT_NEGATIVE_USAGE	0x0400
+ *  DQUOT_NOLIST_DIRTY		0x0800
  */
 enum {
 	_DQUOT_USAGE_ENABLED = 0,		/* Track disk usage for users */
-- 
cgit v1.2.3


From 286228d382ba6320f04fa2e7c6fc8d4d92e428f4 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Wed, 18 Dec 2019 09:39:02 +0100
Subject: can: can_create_echo_skb(): fix echo skb generation: always use
 skb_clone()

All user space generated SKBs are owned by a socket (unless injected into the
key via AF_PACKET). If a socket is closed, all associated skbs will be cleaned
up.

This leads to a problem when a CAN driver calls can_put_echo_skb() on a
unshared SKB. If the socket is closed prior to the TX complete handler,
can_get_echo_skb() and the subsequent delivering of the echo SKB to all
registered callbacks, a SKB with a refcount of 0 is delivered.

To avoid the problem, in can_get_echo_skb() the original SKB is now always
cloned, regardless of shared SKB or not. If the process exists it can now
safely discard its SKBs, without disturbing the delivery of the echo SKB.

The problem shows up in the j1939 stack, when it clones the incoming skb, which
detects the already 0 refcount.

We can easily reproduce this with following example:

testj1939 -B -r can0: &
cansend can0 1823ff40#0123

WARNING: CPU: 0 PID: 293 at lib/refcount.c:25 refcount_warn_saturate+0x108/0x174
refcount_t: addition on 0; use-after-free.
Modules linked in: coda_vpu imx_vdoa videobuf2_vmalloc dw_hdmi_ahb_audio vcan
CPU: 0 PID: 293 Comm: cansend Not tainted 5.5.0-rc6-00376-g9e20dcb7040d #1
Hardware name: Freescale i.MX6 Quad/DualLite (Device Tree)
Backtrace:
[<c010f570>] (dump_backtrace) from [<c010f90c>] (show_stack+0x20/0x24)
[<c010f8ec>] (show_stack) from [<c0c3e1a4>] (dump_stack+0x8c/0xa0)
[<c0c3e118>] (dump_stack) from [<c0127fec>] (__warn+0xe0/0x108)
[<c0127f0c>] (__warn) from [<c01283c8>] (warn_slowpath_fmt+0xa8/0xcc)
[<c0128324>] (warn_slowpath_fmt) from [<c0539c0c>] (refcount_warn_saturate+0x108/0x174)
[<c0539b04>] (refcount_warn_saturate) from [<c0ad2cac>] (j1939_can_recv+0x20c/0x210)
[<c0ad2aa0>] (j1939_can_recv) from [<c0ac9dc8>] (can_rcv_filter+0xb4/0x268)
[<c0ac9d14>] (can_rcv_filter) from [<c0aca2cc>] (can_receive+0xb0/0xe4)
[<c0aca21c>] (can_receive) from [<c0aca348>] (can_rcv+0x48/0x98)
[<c0aca300>] (can_rcv) from [<c09b1fdc>] (__netif_receive_skb_one_core+0x64/0x88)
[<c09b1f78>] (__netif_receive_skb_one_core) from [<c09b2070>] (__netif_receive_skb+0x38/0x94)
[<c09b2038>] (__netif_receive_skb) from [<c09b2130>] (netif_receive_skb_internal+0x64/0xf8)
[<c09b20cc>] (netif_receive_skb_internal) from [<c09b21f8>] (netif_receive_skb+0x34/0x19c)
[<c09b21c4>] (netif_receive_skb) from [<c0791278>] (can_rx_offload_napi_poll+0x58/0xb4)

Fixes: 0ae89beb283a ("can: add destructor for self generated skbs")
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: http://lore.kernel.org/r/20200124132656.22156-1-o.rempel@pengutronix.de
Acked-by: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 include/linux/can/skb.h | 20 ++++++++------------
 1 file changed, 8 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h
index 900b9f4e0605..fc61cf4eff1c 100644
--- a/include/linux/can/skb.h
+++ b/include/linux/can/skb.h
@@ -61,21 +61,17 @@ static inline void can_skb_set_owner(struct sk_buff *skb, struct sock *sk)
  */
 static inline struct sk_buff *can_create_echo_skb(struct sk_buff *skb)
 {
-	if (skb_shared(skb)) {
-		struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
+	struct sk_buff *nskb;
 
-		if (likely(nskb)) {
-			can_skb_set_owner(nskb, skb->sk);
-			consume_skb(skb);
-			return nskb;
-		} else {
-			kfree_skb(skb);
-			return NULL;
-		}
+	nskb = skb_clone(skb, GFP_ATOMIC);
+	if (unlikely(!nskb)) {
+		kfree_skb(skb);
+		return NULL;
 	}
 
-	/* we can assume to have an unshared skb with proper owner */
-	return skb;
+	can_skb_set_owner(nskb, skb->sk);
+	consume_skb(skb);
+	return nskb;
 }
 
 #endif /* !_CAN_SKB_H */
-- 
cgit v1.2.3


From 2e4ef10f58502323ea470bc30ba84d5ddd4e77f0 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <alobakin@pm.me>
Date: Sun, 1 Nov 2020 13:17:07 +0000
Subject: net: add GSO UDP L4 and GSO fraglists to the list of software-backed
 types

Commit e20cf8d3f1f7 ("udp: implement GRO for plain UDP sockets.") and
commit 9fd1ff5d2ac7 ("udp: Support UDP fraglist GRO/GSO.") made UDP L4
and fraglisted GRO/GSO fully supported by the software fallback mode.
We can safely add them to NETIF_F_GSO_SOFTWARE to allow logical/virtual
netdevs to forward these types of skbs up to the real drivers.

Signed-off-by: Alexander Lobakin <alobakin@pm.me>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdev_features.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index 0b17c4322b09..934de56644e7 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -207,8 +207,8 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start)
 				 NETIF_F_FSO)
 
 /* List of features with software fallbacks. */
-#define NETIF_F_GSO_SOFTWARE	(NETIF_F_ALL_TSO | \
-				 NETIF_F_GSO_SCTP)
+#define NETIF_F_GSO_SOFTWARE	(NETIF_F_ALL_TSO | NETIF_F_GSO_SCTP |	     \
+				 NETIF_F_GSO_UDP_L4 | NETIF_F_GSO_FRAGLIST)
 
 /*
  * If one device supports one of these features, then enable them
-- 
cgit v1.2.3


From 179dfb954790410f65605f1c479c029c2cd73c55 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 26 Oct 2020 11:44:21 +0100
Subject: USB: serial: remove write wait queue

The digi_acceleport driver is the only driver still using the port
write wake queue so move it to that driver's port data.

Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Johan Hovold <johan@kernel.org>
---
 drivers/usb/serial/digi_acceleport.c | 12 ++++++------
 include/linux/usb/serial.h           |  2 --
 2 files changed, 6 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/usb/serial/digi_acceleport.c b/drivers/usb/serial/digi_acceleport.c
index 968e08cdcb09..0ecd5316d85f 100644
--- a/drivers/usb/serial/digi_acceleport.c
+++ b/drivers/usb/serial/digi_acceleport.c
@@ -197,6 +197,7 @@ struct digi_port {
 	int dp_throttle_restart;
 	wait_queue_head_t dp_flush_wait;
 	wait_queue_head_t dp_close_wait;	/* wait queue for close */
+	wait_queue_head_t write_wait;
 	struct usb_serial_port *dp_port;
 };
 
@@ -381,7 +382,7 @@ static int digi_write_oob_command(struct usb_serial_port *port,
 	while (count > 0) {
 		while (oob_priv->dp_write_urb_in_use) {
 			cond_wait_interruptible_timeout_irqrestore(
-				&oob_port->write_wait, DIGI_RETRY_TIMEOUT,
+				&oob_priv->write_wait, DIGI_RETRY_TIMEOUT,
 				&oob_priv->dp_port_lock, flags);
 			if (interruptible && signal_pending(current))
 				return -EINTR;
@@ -444,7 +445,7 @@ static int digi_write_inb_command(struct usb_serial_port *port,
 		while (priv->dp_write_urb_in_use &&
 		       time_before(jiffies, timeout)) {
 			cond_wait_interruptible_timeout_irqrestore(
-				&port->write_wait, DIGI_RETRY_TIMEOUT,
+				&priv->write_wait, DIGI_RETRY_TIMEOUT,
 				&priv->dp_port_lock, flags);
 			if (signal_pending(current))
 				return -EINTR;
@@ -523,7 +524,7 @@ static int digi_set_modem_signals(struct usb_serial_port *port,
 	while (oob_priv->dp_write_urb_in_use) {
 		spin_unlock(&port_priv->dp_port_lock);
 		cond_wait_interruptible_timeout_irqrestore(
-			&oob_port->write_wait, DIGI_RETRY_TIMEOUT,
+			&oob_priv->write_wait, DIGI_RETRY_TIMEOUT,
 			&oob_priv->dp_port_lock, flags);
 		if (interruptible && signal_pending(current))
 			return -EINTR;
@@ -983,7 +984,7 @@ static void digi_write_bulk_callback(struct urb *urb)
 		dev_dbg(&port->dev, "digi_write_bulk_callback: oob callback\n");
 		spin_lock_irqsave(&priv->dp_port_lock, flags);
 		priv->dp_write_urb_in_use = 0;
-		wake_up_interruptible(&port->write_wait);
+		wake_up_interruptible(&priv->write_wait);
 		spin_unlock_irqrestore(&priv->dp_port_lock, flags);
 		return;
 	}
@@ -1216,10 +1217,9 @@ static int digi_port_init(struct usb_serial_port *port, unsigned port_num)
 	init_waitqueue_head(&priv->dp_transmit_idle_wait);
 	init_waitqueue_head(&priv->dp_flush_wait);
 	init_waitqueue_head(&priv->dp_close_wait);
+	init_waitqueue_head(&priv->write_wait);
 	priv->dp_port = port;
 
-	init_waitqueue_head(&port->write_wait);
-
 	usb_set_serial_port_data(port, priv);
 
 	return 0;
diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h
index 8e67eff9039f..1c09b922f8b0 100644
--- a/include/linux/usb/serial.h
+++ b/include/linux/usb/serial.h
@@ -62,7 +62,6 @@
  * @bulk_out_endpointAddress: endpoint address for the bulk out pipe for this
  *	port.
  * @flags: usb serial port flags
- * @write_wait: a wait_queue_head_t used by the port.
  * @work: work queue entry for the line discipline waking up.
  * @dev: pointer to the serial device
  *
@@ -108,7 +107,6 @@ struct usb_serial_port {
 	int			tx_bytes;
 
 	unsigned long		flags;
-	wait_queue_head_t	write_wait;
 	struct work_struct	work;
 	unsigned long		sysrq; /* sysrq timeout */
 	struct device		dev;
-- 
cgit v1.2.3


From 2374a045263b47f763571ec87ad7c65ea505188a Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jslaby@suse.cz>
Date: Thu, 29 Oct 2020 12:32:18 +0100
Subject: vt: keyboard, remove unneeded func_* declarations

Now that we removed the ugly handling of func_buf, remove unneeded
declarations of func_* variables. The definitions are in the generated
defkeymap.c_shipped, so we cannot really remove them (but we would love
to).

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Link: https://lore.kernel.org/r/20201029113222.32640-13-jslaby@suse.cz
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/kbd_kern.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kbd_kern.h b/include/linux/kbd_kern.h
index bb2246c8ec13..82f29aa35062 100644
--- a/include/linux/kbd_kern.h
+++ b/include/linux/kbd_kern.h
@@ -9,9 +9,6 @@
 extern struct tasklet_struct keyboard_tasklet;
 
 extern char *func_table[MAX_NR_FUNC];
-extern char func_buf[];
-extern char *funcbufptr;
-extern int funcbufsize, funcbufleft;
 
 /*
  * kbd->xxx contains the VC-local things (flag settings etc..)
-- 
cgit v1.2.3


From 763e4cdc0f6d5cea45c896fef67f7be4bdefcca7 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Thu, 29 Oct 2020 14:30:48 -0700
Subject: iomap: support partial page discard on writeback block mapping
 failure

iomap writeback mapping failure only calls into ->discard_page() if
the current page has not been added to the ioend. Accordingly, the
XFS callback assumes a full page discard and invalidation. This is
problematic for sub-page block size filesystems where some portion
of a page might have been mapped successfully before a failure to
map a delalloc block occurs. ->discard_page() is not called in that
error scenario and the bio is explicitly failed by iomap via the
error return from ->prepare_ioend(). As a result, the filesystem
leaks delalloc blocks and corrupts the filesystem block counters.

Since XFS is the only user of ->discard_page(), tweak the semantics
to invoke the callback unconditionally on mapping errors and provide
the file offset that failed to map. Update xfs_discard_page() to
discard the corresponding portion of the file and pass the range
along to iomap_invalidatepage(). The latter already properly handles
both full and sub-page scenarios by not changing any iomap or page
state on sub-page invalidations.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/iomap/buffered-io.c | 15 ++++++++-------
 fs/xfs/xfs_aops.c      | 14 ++++++++------
 include/linux/iomap.h  |  2 +-
 3 files changed, 17 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 8180061b9e16..e4ea1f9f94d0 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1382,14 +1382,15 @@ iomap_writepage_map(struct iomap_writepage_ctx *wpc,
 	 * appropriately.
 	 */
 	if (unlikely(error)) {
+		/*
+		 * Let the filesystem know what portion of the current page
+		 * failed to map. If the page wasn't been added to ioend, it
+		 * won't be affected by I/O completion and we must unlock it
+		 * now.
+		 */
+		if (wpc->ops->discard_page)
+			wpc->ops->discard_page(page, file_offset);
 		if (!count) {
-			/*
-			 * If the current page hasn't been added to ioend, it
-			 * won't be affected by I/O completions and we must
-			 * discard and unlock it right here.
-			 */
-			if (wpc->ops->discard_page)
-				wpc->ops->discard_page(page);
 			ClearPageUptodate(page);
 			unlock_page(page);
 			goto done;
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 55d126d4e096..5bf37afae5e9 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -527,13 +527,15 @@ xfs_prepare_ioend(
  */
 static void
 xfs_discard_page(
-	struct page		*page)
+	struct page		*page,
+	loff_t			fileoff)
 {
 	struct inode		*inode = page->mapping->host;
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
-	loff_t			offset = page_offset(page);
-	xfs_fileoff_t		start_fsb = XFS_B_TO_FSBT(mp, offset);
+	unsigned int		pageoff = offset_in_page(fileoff);
+	xfs_fileoff_t		start_fsb = XFS_B_TO_FSBT(mp, fileoff);
+	xfs_fileoff_t		pageoff_fsb = XFS_B_TO_FSBT(mp, pageoff);
 	int			error;
 
 	if (XFS_FORCED_SHUTDOWN(mp))
@@ -541,14 +543,14 @@ xfs_discard_page(
 
 	xfs_alert_ratelimited(mp,
 		"page discard on page "PTR_FMT", inode 0x%llx, offset %llu.",
-			page, ip->i_ino, offset);
+			page, ip->i_ino, fileoff);
 
 	error = xfs_bmap_punch_delalloc_range(ip, start_fsb,
-			i_blocks_per_page(inode, page));
+			i_blocks_per_page(inode, page) - pageoff_fsb);
 	if (error && !XFS_FORCED_SHUTDOWN(mp))
 		xfs_alert(mp, "page discard unable to remove delalloc mapping.");
 out_invalidate:
-	iomap_invalidatepage(page, 0, PAGE_SIZE);
+	iomap_invalidatepage(page, pageoff, PAGE_SIZE - pageoff);
 }
 
 static const struct iomap_writeback_ops xfs_writeback_ops = {
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 172b3397a1a3..5bd3cac4df9c 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -221,7 +221,7 @@ struct iomap_writeback_ops {
 	 * Optional, allows the file system to discard state on a page where
 	 * we failed to submit any I/O.
 	 */
-	void (*discard_page)(struct page *page);
+	void (*discard_page)(struct page *page, loff_t fileoff);
 };
 
 struct iomap_writepage_ctx {
-- 
cgit v1.2.3


From fdaf083cdfb556a45c422c8998268baf1ab26829 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Fri, 30 Oct 2020 09:37:30 -0600
Subject: io_uring: properly handle SQPOLL request cancelations

Track if a given task io_uring context contains SQPOLL instances, so we
can iterate those for cancelation (and request counts). This ensures that
we properly wait on SQPOLL contexts, and find everything that needs
canceling.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c            | 77 ++++++++++++++++++++++++++++++++++++++++--------
 include/linux/io_uring.h |  3 +-
 2 files changed, 67 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/fs/io_uring.c b/fs/io_uring.c
index a7429c977eb3..b398394a919e 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1668,7 +1668,8 @@ static void __io_cqring_fill_event(struct io_kiocb *req, long res, long cflags)
 		WRITE_ONCE(cqe->user_data, req->user_data);
 		WRITE_ONCE(cqe->res, res);
 		WRITE_ONCE(cqe->flags, cflags);
-	} else if (ctx->cq_overflow_flushed || req->task->io_uring->in_idle) {
+	} else if (ctx->cq_overflow_flushed ||
+		   atomic_read(&req->task->io_uring->in_idle)) {
 		/*
 		 * If we're in ring overflow flush mode, or in task cancel mode,
 		 * then we cannot store the request for later flushing, we need
@@ -1838,7 +1839,7 @@ static void __io_free_req(struct io_kiocb *req)
 	io_dismantle_req(req);
 
 	percpu_counter_dec(&tctx->inflight);
-	if (tctx->in_idle)
+	if (atomic_read(&tctx->in_idle))
 		wake_up(&tctx->wait);
 	put_task_struct(req->task);
 
@@ -7695,7 +7696,8 @@ static int io_uring_alloc_task_context(struct task_struct *task)
 	xa_init(&tctx->xa);
 	init_waitqueue_head(&tctx->wait);
 	tctx->last = NULL;
-	tctx->in_idle = 0;
+	atomic_set(&tctx->in_idle, 0);
+	tctx->sqpoll = false;
 	io_init_identity(&tctx->__identity);
 	tctx->identity = &tctx->__identity;
 	task->io_uring = tctx;
@@ -8598,8 +8600,11 @@ static void io_uring_cancel_task_requests(struct io_ring_ctx *ctx,
 {
 	struct task_struct *task = current;
 
-	if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data)
+	if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) {
 		task = ctx->sq_data->thread;
+		atomic_inc(&task->io_uring->in_idle);
+		io_sq_thread_park(ctx->sq_data);
+	}
 
 	io_cqring_overflow_flush(ctx, true, task, files);
 
@@ -8607,12 +8612,23 @@ static void io_uring_cancel_task_requests(struct io_ring_ctx *ctx,
 		io_run_task_work();
 		cond_resched();
 	}
+
+	if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) {
+		atomic_dec(&task->io_uring->in_idle);
+		/*
+		 * If the files that are going away are the ones in the thread
+		 * identity, clear them out.
+		 */
+		if (task->io_uring->identity->files == files)
+			task->io_uring->identity->files = NULL;
+		io_sq_thread_unpark(ctx->sq_data);
+	}
 }
 
 /*
  * Note that this task has used io_uring. We use it for cancelation purposes.
  */
-static int io_uring_add_task_file(struct file *file)
+static int io_uring_add_task_file(struct io_ring_ctx *ctx, struct file *file)
 {
 	struct io_uring_task *tctx = current->io_uring;
 
@@ -8634,6 +8650,14 @@ static int io_uring_add_task_file(struct file *file)
 		tctx->last = file;
 	}
 
+	/*
+	 * This is race safe in that the task itself is doing this, hence it
+	 * cannot be going through the exit/cancel paths at the same time.
+	 * This cannot be modified while exit/cancel is running.
+	 */
+	if (!tctx->sqpoll && (ctx->flags & IORING_SETUP_SQPOLL))
+		tctx->sqpoll = true;
+
 	return 0;
 }
 
@@ -8675,7 +8699,7 @@ void __io_uring_files_cancel(struct files_struct *files)
 	unsigned long index;
 
 	/* make sure overflow events are dropped */
-	tctx->in_idle = true;
+	atomic_inc(&tctx->in_idle);
 
 	xa_for_each(&tctx->xa, index, file) {
 		struct io_ring_ctx *ctx = file->private_data;
@@ -8684,6 +8708,35 @@ void __io_uring_files_cancel(struct files_struct *files)
 		if (files)
 			io_uring_del_task_file(file);
 	}
+
+	atomic_dec(&tctx->in_idle);
+}
+
+static s64 tctx_inflight(struct io_uring_task *tctx)
+{
+	unsigned long index;
+	struct file *file;
+	s64 inflight;
+
+	inflight = percpu_counter_sum(&tctx->inflight);
+	if (!tctx->sqpoll)
+		return inflight;
+
+	/*
+	 * If we have SQPOLL rings, then we need to iterate and find them, and
+	 * add the pending count for those.
+	 */
+	xa_for_each(&tctx->xa, index, file) {
+		struct io_ring_ctx *ctx = file->private_data;
+
+		if (ctx->flags & IORING_SETUP_SQPOLL) {
+			struct io_uring_task *__tctx = ctx->sqo_task->io_uring;
+
+			inflight += percpu_counter_sum(&__tctx->inflight);
+		}
+	}
+
+	return inflight;
 }
 
 /*
@@ -8697,11 +8750,11 @@ void __io_uring_task_cancel(void)
 	s64 inflight;
 
 	/* make sure overflow events are dropped */
-	tctx->in_idle = true;
+	atomic_inc(&tctx->in_idle);
 
 	do {
 		/* read completions before cancelations */
-		inflight = percpu_counter_sum(&tctx->inflight);
+		inflight = tctx_inflight(tctx);
 		if (!inflight)
 			break;
 		__io_uring_files_cancel(NULL);
@@ -8712,13 +8765,13 @@ void __io_uring_task_cancel(void)
 		 * If we've seen completions, retry. This avoids a race where
 		 * a completion comes in before we did prepare_to_wait().
 		 */
-		if (inflight != percpu_counter_sum(&tctx->inflight))
+		if (inflight != tctx_inflight(tctx))
 			continue;
 		schedule();
 	} while (1);
 
 	finish_wait(&tctx->wait, &wait);
-	tctx->in_idle = false;
+	atomic_dec(&tctx->in_idle);
 }
 
 static int io_uring_flush(struct file *file, void *data)
@@ -8863,7 +8916,7 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 			io_sqpoll_wait_sq(ctx);
 		submitted = to_submit;
 	} else if (to_submit) {
-		ret = io_uring_add_task_file(f.file);
+		ret = io_uring_add_task_file(ctx, f.file);
 		if (unlikely(ret))
 			goto out;
 		mutex_lock(&ctx->uring_lock);
@@ -9092,7 +9145,7 @@ err_fd:
 #if defined(CONFIG_UNIX)
 	ctx->ring_sock->file = file;
 #endif
-	if (unlikely(io_uring_add_task_file(file))) {
+	if (unlikely(io_uring_add_task_file(ctx, file))) {
 		file = ERR_PTR(-ENOMEM);
 		goto err_fd;
 	}
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index 868364cea3b7..35b2d845704d 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -30,7 +30,8 @@ struct io_uring_task {
 	struct percpu_counter	inflight;
 	struct io_identity	__identity;
 	struct io_identity	*identity;
-	bool			in_idle;
+	atomic_t		in_idle;
+	bool			sqpoll;
 };
 
 #if defined(CONFIG_IO_URING)
-- 
cgit v1.2.3


From b6be002bcd1dd1dedb926abf3c90c794eacb77dc Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 2 Nov 2020 12:53:16 -0800
Subject: x86/entry: Move nmi entry/exit into common code

Lockdep state handling on NMI enter and exit is nothing specific to X86. It's
not any different on other architectures. Also the extra state type is not
necessary, irqentry_state_t can carry the necessary information as well.

Move it to common code and extend irqentry_state_t to carry lockdep state.

[ Ira: Make exit_rcu and lockdep a union as they are mutually exclusive
  between the IRQ and NMI exceptions, and add kernel documentation for
  struct irqentry_state_t ]

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20201102205320.1458656-7-ira.weiny@intel.com
---
 arch/x86/entry/common.c         | 34 ----------------------------------
 arch/x86/include/asm/idtentry.h |  3 ---
 arch/x86/kernel/cpu/mce/core.c  |  6 +++---
 arch/x86/kernel/nmi.c           |  6 +++---
 arch/x86/kernel/traps.c         | 13 +++++++------
 include/linux/entry-common.h    | 39 ++++++++++++++++++++++++++++++++++++++-
 kernel/entry/common.c           | 36 ++++++++++++++++++++++++++++++++++++
 7 files changed, 87 insertions(+), 50 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 870efeec8bda..18d8f17f755c 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -209,40 +209,6 @@ SYSCALL_DEFINE0(ni_syscall)
 	return -ENOSYS;
 }
 
-noinstr bool idtentry_enter_nmi(struct pt_regs *regs)
-{
-	bool irq_state = lockdep_hardirqs_enabled();
-
-	__nmi_enter();
-	lockdep_hardirqs_off(CALLER_ADDR0);
-	lockdep_hardirq_enter();
-	rcu_nmi_enter();
-
-	instrumentation_begin();
-	trace_hardirqs_off_finish();
-	ftrace_nmi_enter();
-	instrumentation_end();
-
-	return irq_state;
-}
-
-noinstr void idtentry_exit_nmi(struct pt_regs *regs, bool restore)
-{
-	instrumentation_begin();
-	ftrace_nmi_exit();
-	if (restore) {
-		trace_hardirqs_on_prepare();
-		lockdep_hardirqs_on_prepare(CALLER_ADDR0);
-	}
-	instrumentation_end();
-
-	rcu_nmi_exit();
-	lockdep_hardirq_exit();
-	if (restore)
-		lockdep_hardirqs_on(CALLER_ADDR0);
-	__nmi_exit();
-}
-
 #ifdef CONFIG_XEN_PV
 #ifndef CONFIG_PREEMPTION
 /*
diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index b2442eb0ac2f..247a60a47331 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -11,9 +11,6 @@
 
 #include <asm/irq_stack.h>
 
-bool idtentry_enter_nmi(struct pt_regs *regs);
-void idtentry_exit_nmi(struct pt_regs *regs, bool irq_state);
-
 /**
  * DECLARE_IDTENTRY - Declare functions for simple IDT entry points
  *		      No error code pushed by hardware
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 4102b866e7c0..f5c860b1a50b 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1983,7 +1983,7 @@ void (*machine_check_vector)(struct pt_regs *) = unexpected_machine_check;
 
 static __always_inline void exc_machine_check_kernel(struct pt_regs *regs)
 {
-	bool irq_state;
+	irqentry_state_t irq_state;
 
 	WARN_ON_ONCE(user_mode(regs));
 
@@ -1995,7 +1995,7 @@ static __always_inline void exc_machine_check_kernel(struct pt_regs *regs)
 	    mce_check_crashing_cpu())
 		return;
 
-	irq_state = idtentry_enter_nmi(regs);
+	irq_state = irqentry_nmi_enter(regs);
 	/*
 	 * The call targets are marked noinstr, but objtool can't figure
 	 * that out because it's an indirect call. Annotate it.
@@ -2006,7 +2006,7 @@ static __always_inline void exc_machine_check_kernel(struct pt_regs *regs)
 	if (regs->flags & X86_EFLAGS_IF)
 		trace_hardirqs_on_prepare();
 	instrumentation_end();
-	idtentry_exit_nmi(regs, irq_state);
+	irqentry_nmi_exit(regs, irq_state);
 }
 
 static __always_inline void exc_machine_check_user(struct pt_regs *regs)
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 4bc77aaf1303..bf250a339655 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -475,7 +475,7 @@ static DEFINE_PER_CPU(unsigned long, nmi_dr7);
 
 DEFINE_IDTENTRY_RAW(exc_nmi)
 {
-	bool irq_state;
+	irqentry_state_t irq_state;
 
 	/*
 	 * Re-enable NMIs right here when running as an SEV-ES guest. This might
@@ -502,14 +502,14 @@ nmi_restart:
 
 	this_cpu_write(nmi_dr7, local_db_save());
 
-	irq_state = idtentry_enter_nmi(regs);
+	irq_state = irqentry_nmi_enter(regs);
 
 	inc_irq_stat(__nmi_count);
 
 	if (!ignore_nmis)
 		default_do_nmi(regs);
 
-	idtentry_exit_nmi(regs, irq_state);
+	irqentry_nmi_exit(regs, irq_state);
 
 	local_db_restore(this_cpu_read(nmi_dr7));
 
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index e19df6cde35d..e1b78829d909 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -405,7 +405,7 @@ DEFINE_IDTENTRY_DF(exc_double_fault)
 	}
 #endif
 
-	idtentry_enter_nmi(regs);
+	irqentry_nmi_enter(regs);
 	instrumentation_begin();
 	notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV);
 
@@ -651,12 +651,13 @@ DEFINE_IDTENTRY_RAW(exc_int3)
 		instrumentation_end();
 		irqentry_exit_to_user_mode(regs);
 	} else {
-		bool irq_state = idtentry_enter_nmi(regs);
+		irqentry_state_t irq_state = irqentry_nmi_enter(regs);
+
 		instrumentation_begin();
 		if (!do_int3(regs))
 			die("int3", regs, 0);
 		instrumentation_end();
-		idtentry_exit_nmi(regs, irq_state);
+		irqentry_nmi_exit(regs, irq_state);
 	}
 }
 
@@ -851,7 +852,7 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs,
 	 * includes the entry stack is excluded for everything.
 	 */
 	unsigned long dr7 = local_db_save();
-	bool irq_state = idtentry_enter_nmi(regs);
+	irqentry_state_t irq_state = irqentry_nmi_enter(regs);
 	instrumentation_begin();
 
 	/*
@@ -908,7 +909,7 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs,
 		regs->flags &= ~X86_EFLAGS_TF;
 out:
 	instrumentation_end();
-	idtentry_exit_nmi(regs, irq_state);
+	irqentry_nmi_exit(regs, irq_state);
 
 	local_db_restore(dr7);
 }
@@ -926,7 +927,7 @@ static __always_inline void exc_debug_user(struct pt_regs *regs,
 
 	/*
 	 * NB: We can't easily clear DR7 here because
-	 * idtentry_exit_to_usermode() can invoke ptrace, schedule, access
+	 * irqentry_exit_to_usermode() can invoke ptrace, schedule, access
 	 * user memory, etc.  This means that a recursive #DB is possible.  If
 	 * this happens, that #DB will hit exc_debug_kernel() and clear DR7.
 	 * Since we're not on the IST stack right now, everything will be
diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index b9711e813ec2..1a128baf3628 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -346,8 +346,26 @@ void irqentry_enter_from_user_mode(struct pt_regs *regs);
 void irqentry_exit_to_user_mode(struct pt_regs *regs);
 
 #ifndef irqentry_state
+/**
+ * struct irqentry_state - Opaque object for exception state storage
+ * @exit_rcu: Used exclusively in the irqentry_*() calls; signals whether the
+ *            exit path has to invoke rcu_irq_exit().
+ * @lockdep: Used exclusively in the irqentry_nmi_*() calls; ensures that
+ *           lockdep state is restored correctly on exit from nmi.
+ *
+ * This opaque object is filled in by the irqentry_*_enter() functions and
+ * must be passed back into the corresponding irqentry_*_exit() functions
+ * when the exception is complete.
+ *
+ * Callers of irqentry_*_[enter|exit]() must consider this structure opaque
+ * and all members private.  Descriptions of the members are provided to aid in
+ * the maintenance of the irqentry_*() functions.
+ */
 typedef struct irqentry_state {
-	bool	exit_rcu;
+	union {
+		bool	exit_rcu;
+		bool	lockdep;
+	};
 } irqentry_state_t;
 #endif
 
@@ -407,4 +425,23 @@ void irqentry_exit_cond_resched(void);
  */
 void noinstr irqentry_exit(struct pt_regs *regs, irqentry_state_t state);
 
+/**
+ * irqentry_nmi_enter - Handle NMI entry
+ * @regs:	Pointer to currents pt_regs
+ *
+ * Similar to irqentry_enter() but taking care of the NMI constraints.
+ */
+irqentry_state_t noinstr irqentry_nmi_enter(struct pt_regs *regs);
+
+/**
+ * irqentry_nmi_exit - Handle return from NMI handling
+ * @regs:	Pointer to pt_regs (NMI entry regs)
+ * @irq_state:	Return value from matching call to irqentry_nmi_enter()
+ *
+ * Last action before returning to the low level assmenbly code.
+ *
+ * Counterpart to irqentry_nmi_enter().
+ */
+void noinstr irqentry_nmi_exit(struct pt_regs *regs, irqentry_state_t irq_state);
+
 #endif
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 3a1dfecc533e..bc75c114c1b3 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -405,3 +405,39 @@ noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state)
 			rcu_irq_exit();
 	}
 }
+
+irqentry_state_t noinstr irqentry_nmi_enter(struct pt_regs *regs)
+{
+	irqentry_state_t irq_state;
+
+	irq_state.lockdep = lockdep_hardirqs_enabled();
+
+	__nmi_enter();
+	lockdep_hardirqs_off(CALLER_ADDR0);
+	lockdep_hardirq_enter();
+	rcu_nmi_enter();
+
+	instrumentation_begin();
+	trace_hardirqs_off_finish();
+	ftrace_nmi_enter();
+	instrumentation_end();
+
+	return irq_state;
+}
+
+void noinstr irqentry_nmi_exit(struct pt_regs *regs, irqentry_state_t irq_state)
+{
+	instrumentation_begin();
+	ftrace_nmi_exit();
+	if (irq_state.lockdep) {
+		trace_hardirqs_on_prepare();
+		lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+	}
+	instrumentation_end();
+
+	rcu_nmi_exit();
+	lockdep_hardirq_exit();
+	if (irq_state.lockdep)
+		lockdep_hardirqs_on(CALLER_ADDR0);
+	__nmi_exit();
+}
-- 
cgit v1.2.3


From e1ac4b2406d94eddce8ac2c5ab4235f6075a9602 Mon Sep 17 00:00:00 2001
From: Chester Lin <clin@suse.com>
Date: Fri, 30 Oct 2020 14:08:38 +0800
Subject: efi: generalize efi_get_secureboot

Generalize the efi_get_secureboot() function so not only efistub but also
other subsystems can use it.

Note that the MokSbState handling is not factored out: the variable is
boot time only, and so it cannot be parameterized as easily. Also, the
IMA code will switch to this version in a future patch, and it does not
incorporate the MokSbState exception in the first place.

Note that the new efi_get_secureboot_mode() helper treats any failures
to read SetupMode as setup mode being disabled.

Co-developed-by: Chester Lin <clin@suse.com>
Signed-off-by: Chester Lin <clin@suse.com>
Acked-by: Mimi Zohar <zohar@linux.ibm.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 arch/x86/boot/compressed/Makefile         |  2 +-
 drivers/firmware/efi/libstub/efistub.h    |  2 ++
 drivers/firmware/efi/libstub/secureboot.c | 41 +++++++++++--------------------
 include/linux/efi.h                       | 23 ++++++++++++++++-
 4 files changed, 40 insertions(+), 28 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index ee249088cbfe..8d358a6fe6ec 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -35,7 +35,7 @@ cflags-$(CONFIG_X86_32) := -march=i386
 cflags-$(CONFIG_X86_64) := -mcmodel=small -mno-red-zone
 KBUILD_CFLAGS += $(cflags-y)
 KBUILD_CFLAGS += -mno-mmx -mno-sse
-KBUILD_CFLAGS += -ffreestanding
+KBUILD_CFLAGS += -ffreestanding -fshort-wchar
 KBUILD_CFLAGS += -fno-stack-protector
 KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member)
 KBUILD_CFLAGS += $(call cc-disable-warning, gnu)
diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h
index 2d7abcd99de9..b8ec29d6a74a 100644
--- a/drivers/firmware/efi/libstub/efistub.h
+++ b/drivers/firmware/efi/libstub/efistub.h
@@ -848,4 +848,6 @@ asmlinkage void __noreturn efi_enter_kernel(unsigned long entrypoint,
 
 void efi_handle_post_ebs_state(void);
 
+enum efi_secureboot_mode efi_get_secureboot(void);
+
 #endif
diff --git a/drivers/firmware/efi/libstub/secureboot.c b/drivers/firmware/efi/libstub/secureboot.c
index 5efc524b14be..af18d86c1604 100644
--- a/drivers/firmware/efi/libstub/secureboot.c
+++ b/drivers/firmware/efi/libstub/secureboot.c
@@ -12,15 +12,16 @@
 
 #include "efistub.h"
 
-/* BIOS variables */
-static const efi_guid_t efi_variable_guid = EFI_GLOBAL_VARIABLE_GUID;
-static const efi_char16_t efi_SecureBoot_name[] = L"SecureBoot";
-static const efi_char16_t efi_SetupMode_name[] = L"SetupMode";
-
 /* SHIM variables */
 static const efi_guid_t shim_guid = EFI_SHIM_LOCK_GUID;
 static const efi_char16_t shim_MokSBState_name[] = L"MokSBState";
 
+static efi_status_t get_var(efi_char16_t *name, efi_guid_t *vendor, u32 *attr,
+			    unsigned long *data_size, void *data)
+{
+	return get_efi_var(name, vendor, attr, data_size, data);
+}
+
 /*
  * Determine whether we're in secure boot mode.
  *
@@ -30,26 +31,18 @@ static const efi_char16_t shim_MokSBState_name[] = L"MokSBState";
 enum efi_secureboot_mode efi_get_secureboot(void)
 {
 	u32 attr;
-	u8 secboot, setupmode, moksbstate;
 	unsigned long size;
+	enum efi_secureboot_mode mode;
 	efi_status_t status;
+	u8 moksbstate;
 
-	size = sizeof(secboot);
-	status = get_efi_var(efi_SecureBoot_name, &efi_variable_guid,
-			     NULL, &size, &secboot);
-	if (status == EFI_NOT_FOUND)
-		return efi_secureboot_mode_disabled;
-	if (status != EFI_SUCCESS)
-		goto out_efi_err;
-
-	size = sizeof(setupmode);
-	status = get_efi_var(efi_SetupMode_name, &efi_variable_guid,
-			     NULL, &size, &setupmode);
-	if (status != EFI_SUCCESS)
-		goto out_efi_err;
-
-	if (secboot == 0 || setupmode == 1)
-		return efi_secureboot_mode_disabled;
+	mode = efi_get_secureboot_mode(get_var);
+	if (mode == efi_secureboot_mode_unknown) {
+		efi_err("Could not determine UEFI Secure Boot status.\n");
+		return efi_secureboot_mode_unknown;
+	}
+	if (mode != efi_secureboot_mode_enabled)
+		return mode;
 
 	/*
 	 * See if a user has put the shim into insecure mode. If so, and if the
@@ -69,8 +62,4 @@ enum efi_secureboot_mode efi_get_secureboot(void)
 secure_boot_enabled:
 	efi_info("UEFI Secure Boot is enabled.\n");
 	return efi_secureboot_mode_enabled;
-
-out_efi_err:
-	efi_err("Could not determine UEFI Secure Boot status.\n");
-	return efi_secureboot_mode_unknown;
 }
diff --git a/include/linux/efi.h b/include/linux/efi.h
index d7c0e73af2b9..1cd5d91d8ca1 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -1089,7 +1089,28 @@ enum efi_secureboot_mode {
 	efi_secureboot_mode_disabled,
 	efi_secureboot_mode_enabled,
 };
-enum efi_secureboot_mode efi_get_secureboot(void);
+
+static inline
+enum efi_secureboot_mode efi_get_secureboot_mode(efi_get_variable_t *get_var)
+{
+	u8 secboot, setupmode = 0;
+	efi_status_t status;
+	unsigned long size;
+
+	size = sizeof(secboot);
+	status = get_var(L"SecureBoot", &EFI_GLOBAL_VARIABLE_GUID, NULL, &size,
+			 &secboot);
+	if (status == EFI_NOT_FOUND)
+		return efi_secureboot_mode_disabled;
+	if (status != EFI_SUCCESS)
+		return efi_secureboot_mode_unknown;
+
+	size = sizeof(setupmode);
+	get_var(L"SetupMode", &EFI_GLOBAL_VARIABLE_GUID, NULL, &size, &setupmode);
+	if (secboot == 0 || setupmode == 1)
+		return efi_secureboot_mode_disabled;
+	return efi_secureboot_mode_enabled;
+}
 
 #ifdef CONFIG_RESET_ATTACK_MITIGATION
 void efi_enable_reset_attack_mitigation(void);
-- 
cgit v1.2.3


From 9d1c94a69d70f1b02bdf06b231cd16ad47ef06cd Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Fri, 23 Oct 2020 18:33:25 +0200
Subject: clk: fix a kernel-doc markup

clk_get_duty_cycle -> clk_get_scaled_duty_cycle

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Link: https://lore.kernel.org/r/b2336f3f3cdfe6e1a2d3a7a056ab7ccc7a81b945.1603469755.git.mchehab+huawei@kernel.org
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 include/linux/clk.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/clk.h b/include/linux/clk.h
index 7fd6a1febcf4..5f8d5f4931c0 100644
--- a/include/linux/clk.h
+++ b/include/linux/clk.h
@@ -150,7 +150,7 @@ int clk_get_phase(struct clk *clk);
 int clk_set_duty_cycle(struct clk *clk, unsigned int num, unsigned int den);
 
 /**
- * clk_get_duty_cycle - return the duty cycle ratio of a clock signal
+ * clk_get_scaled_duty_cycle - return the duty cycle ratio of a clock signal
  * @clk: clock signal source
  * @scale: scaling factor to be applied to represent the ratio as an integer
  *
-- 
cgit v1.2.3


From 2b5b95b1ff3d70a95013a45e3b5b90f1daf42348 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Mon, 14 Sep 2020 15:09:33 +0200
Subject: mm: introduce vma_set_file function v4
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add the new vma_set_file() function to allow changing
vma->vm_file with the necessary refcount dance.

v2: add more users of this.
v3: add missing EXPORT_SYMBOL, rebase on mmap cleanup,
    add comments why we drop the reference on two occasions.
v4: make it clear that changing an anonymous vma is illegal.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> (v2)
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/394773/
---
 drivers/dma-buf/dma-buf.c                  |  3 +--
 drivers/gpu/drm/etnaviv/etnaviv_gem.c      |  4 +---
 drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c |  3 +--
 drivers/gpu/drm/i915/gem/i915_gem_mman.c   |  5 +++--
 drivers/gpu/drm/msm/msm_gem.c              |  4 +---
 drivers/gpu/drm/omapdrm/omap_gem.c         |  3 +--
 drivers/gpu/drm/vgem/vgem_drv.c            |  3 +--
 drivers/staging/android/ashmem.c           |  6 +++---
 include/linux/mm.h                         |  2 ++
 mm/mmap.c                                  | 12 ++++++++++++
 10 files changed, 26 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index 3d22dff1dab9..696b4ce4cfd9 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -1183,8 +1183,7 @@ int dma_buf_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma,
 		return -EINVAL;
 
 	/* readjust the vma */
-	fput(vma->vm_file);
-	vma->vm_file = get_file(dmabuf->file);
+	vma_set_file(vma, dmabuf->file);
 	vma->vm_pgoff = pgoff;
 
 	return dmabuf->ops->mmap(dmabuf, vma);
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
index 67d9a2b9ea6a..4132acfa11be 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
@@ -145,10 +145,8 @@ static int etnaviv_gem_mmap_obj(struct etnaviv_gem_object *etnaviv_obj,
 		 * address_space (so unmap_mapping_range does what we want,
 		 * in particular in the case of mmap'd dmabufs)
 		 */
-		fput(vma->vm_file);
-		get_file(etnaviv_obj->base.filp);
 		vma->vm_pgoff = 0;
-		vma->vm_file  = etnaviv_obj->base.filp;
+		vma_set_file(vma, etnaviv_obj->base.filp);
 
 		vma->vm_page_prot = vm_page_prot;
 	}
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
index 0dd477e56573..04e9c04545ad 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
@@ -114,8 +114,7 @@ static int i915_gem_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struct *
 	if (ret)
 		return ret;
 
-	fput(vma->vm_file);
-	vma->vm_file = get_file(obj->base.filp);
+	vma_set_file(vma, obj->base.filp);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index 3d69e51f3e4d..ec28a6cde49b 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -893,8 +893,9 @@ int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma)
 	 * requires avoiding extraneous references to their filp, hence why
 	 * we prefer to use an anonymous file for their mmaps.
 	 */
-	fput(vma->vm_file);
-	vma->vm_file = anon;
+	vma_set_file(vma, anon);
+	/* Drop the initial creation reference, the vma is now holding one. */
+	fput(anon);
 
 	switch (mmo->mmap_type) {
 	case I915_MMAP_TYPE_WC:
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 2e1bce7c0b19..311721ceee50 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -212,10 +212,8 @@ int msm_gem_mmap_obj(struct drm_gem_object *obj,
 		 * address_space (so unmap_mapping_range does what we want,
 		 * in particular in the case of mmap'd dmabufs)
 		 */
-		fput(vma->vm_file);
-		get_file(obj->filp);
 		vma->vm_pgoff = 0;
-		vma->vm_file  = obj->filp;
+		vma_set_file(vma, obj->filp);
 
 		vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
 	}
diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index d8e09792793a..f063f5a04fb0 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem.c
@@ -564,9 +564,8 @@ int omap_gem_mmap_obj(struct drm_gem_object *obj,
 		 * address_space (so unmap_mapping_range does what we want,
 		 * in particular in the case of mmap'd dmabufs)
 		 */
-		fput(vma->vm_file);
 		vma->vm_pgoff = 0;
-		vma->vm_file  = get_file(obj->filp);
+		vma_set_file(vma, obj->filp);
 
 		vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
 	}
diff --git a/drivers/gpu/drm/vgem/vgem_drv.c b/drivers/gpu/drm/vgem/vgem_drv.c
index fa54a6d1403d..ea0eecae5153 100644
--- a/drivers/gpu/drm/vgem/vgem_drv.c
+++ b/drivers/gpu/drm/vgem/vgem_drv.c
@@ -397,8 +397,7 @@ static int vgem_prime_mmap(struct drm_gem_object *obj,
 	if (ret)
 		return ret;
 
-	fput(vma->vm_file);
-	vma->vm_file = get_file(obj->filp);
+	vma_set_file(vma, obj->filp);
 	vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP;
 	vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags));
 
diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c
index 10b4be1f3e78..4789d36ddfd3 100644
--- a/drivers/staging/android/ashmem.c
+++ b/drivers/staging/android/ashmem.c
@@ -450,9 +450,9 @@ static int ashmem_mmap(struct file *file, struct vm_area_struct *vma)
 		vma_set_anonymous(vma);
 	}
 
-	if (vma->vm_file)
-		fput(vma->vm_file);
-	vma->vm_file = asma->file;
+	vma_set_file(vma, asma->file);
+	/* XXX: merge this with the get_file() above if possible */
+	fput(asma->file);
 
 out:
 	mutex_unlock(&ashmem_mutex);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index ef360fe70aaf..2b7ac36c42dd 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2719,6 +2719,8 @@ static inline void vma_set_page_prot(struct vm_area_struct *vma)
 }
 #endif
 
+void vma_set_file(struct vm_area_struct *vma, struct file *file);
+
 #ifdef CONFIG_NUMA_BALANCING
 unsigned long change_prot_numa(struct vm_area_struct *vma,
 			unsigned long start, unsigned long end);
diff --git a/mm/mmap.c b/mm/mmap.c
index 30a4e8412a58..b0093cc69240 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -136,6 +136,18 @@ void vma_set_page_prot(struct vm_area_struct *vma)
 	WRITE_ONCE(vma->vm_page_prot, vm_page_prot);
 }
 
+/*
+ * Change backing file, only valid to use during initial VMA setup.
+ */
+void vma_set_file(struct vm_area_struct *vma, struct file *file)
+{
+	/* Changing an anonymous vma with this is illegal */
+	get_file(file);
+	swap(vma->vm_file, file);
+	fput(file);
+}
+EXPORT_SYMBOL(vma_set_file);
+
 /*
  * Requires inode->i_mapping->i_mmap_rwsem
  */
-- 
cgit v1.2.3


From a4da45dda6475816f4c8b9e0d512261991ba31e5 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Wed, 28 Oct 2020 15:51:17 +0100
Subject: pinctrl: Remove hole in pinctrl_gpio_range

On 64-bit platforms, pointer size and alignment are 64-bit, hence two
4-byte holes are present before the pins and gc members of the
pinctrl_gpio_range structure.  Get rid of these holes by moving the
pins pointer.

This reduces kernel size of an arm64 Rockchip kernel by ca. 512 bytes.

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20201028145117.1731876-1-geert+renesas@glider.be
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 include/linux/pinctrl/pinctrl.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pinctrl/pinctrl.h b/include/linux/pinctrl/pinctrl.h
index 2aef59df93d7..70b45d28e7a9 100644
--- a/include/linux/pinctrl/pinctrl.h
+++ b/include/linux/pinctrl/pinctrl.h
@@ -51,8 +51,8 @@ struct pinctrl_pin_desc {
  * @id: an ID number for the chip in this range
  * @base: base offset of the GPIO range
  * @pin_base: base pin number of the GPIO range if pins == NULL
- * @pins: enumeration of pins in GPIO range or NULL
  * @npins: number of pins in the GPIO range, including the base number
+ * @pins: enumeration of pins in GPIO range or NULL
  * @gc: an optional pointer to a gpio_chip
  */
 struct pinctrl_gpio_range {
@@ -61,8 +61,8 @@ struct pinctrl_gpio_range {
 	unsigned int id;
 	unsigned int base;
 	unsigned int pin_base;
-	unsigned const *pins;
 	unsigned int npins;
+	unsigned const *pins;
 	struct gpio_chip *gc;
 };
 
-- 
cgit v1.2.3


From e40b0b56ffdc16edce207904a7782da6a1a47162 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Thu, 5 Nov 2020 17:05:35 +0100
Subject: Revert "mm: introduce vma_set_file function v4"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The kernel test robot is not happy with that.

This reverts commit 2b5b95b1ff3d70a95013a45e3b5b90f1daf42348.

Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Daniel Vetter <daniel@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/394773/
---
 drivers/dma-buf/dma-buf.c                  |  3 ++-
 drivers/gpu/drm/etnaviv/etnaviv_gem.c      |  4 +++-
 drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c |  3 ++-
 drivers/gpu/drm/i915/gem/i915_gem_mman.c   |  5 ++---
 drivers/gpu/drm/msm/msm_gem.c              |  4 +++-
 drivers/gpu/drm/omapdrm/omap_gem.c         |  3 ++-
 drivers/gpu/drm/vgem/vgem_drv.c            |  3 ++-
 drivers/staging/android/ashmem.c           |  6 +++---
 include/linux/mm.h                         |  2 --
 mm/mmap.c                                  | 12 ------------
 10 files changed, 19 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index e63684d4cd90..282bd8b84170 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -1183,7 +1183,8 @@ int dma_buf_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma,
 		return -EINVAL;
 
 	/* readjust the vma */
-	vma_set_file(vma, dmabuf->file);
+	fput(vma->vm_file);
+	vma->vm_file = get_file(dmabuf->file);
 	vma->vm_pgoff = pgoff;
 
 	return dmabuf->ops->mmap(dmabuf, vma);
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
index 4132acfa11be..67d9a2b9ea6a 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
@@ -145,8 +145,10 @@ static int etnaviv_gem_mmap_obj(struct etnaviv_gem_object *etnaviv_obj,
 		 * address_space (so unmap_mapping_range does what we want,
 		 * in particular in the case of mmap'd dmabufs)
 		 */
+		fput(vma->vm_file);
+		get_file(etnaviv_obj->base.filp);
 		vma->vm_pgoff = 0;
-		vma_set_file(vma, etnaviv_obj->base.filp);
+		vma->vm_file  = etnaviv_obj->base.filp;
 
 		vma->vm_page_prot = vm_page_prot;
 	}
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
index 04e9c04545ad..0dd477e56573 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
@@ -114,7 +114,8 @@ static int i915_gem_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struct *
 	if (ret)
 		return ret;
 
-	vma_set_file(vma, obj->base.filp);
+	fput(vma->vm_file);
+	vma->vm_file = get_file(obj->base.filp);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index ec28a6cde49b..3d69e51f3e4d 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -893,9 +893,8 @@ int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma)
 	 * requires avoiding extraneous references to their filp, hence why
 	 * we prefer to use an anonymous file for their mmaps.
 	 */
-	vma_set_file(vma, anon);
-	/* Drop the initial creation reference, the vma is now holding one. */
-	fput(anon);
+	fput(vma->vm_file);
+	vma->vm_file = anon;
 
 	switch (mmo->mmap_type) {
 	case I915_MMAP_TYPE_WC:
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 311721ceee50..2e1bce7c0b19 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -212,8 +212,10 @@ int msm_gem_mmap_obj(struct drm_gem_object *obj,
 		 * address_space (so unmap_mapping_range does what we want,
 		 * in particular in the case of mmap'd dmabufs)
 		 */
+		fput(vma->vm_file);
+		get_file(obj->filp);
 		vma->vm_pgoff = 0;
-		vma_set_file(vma, obj->filp);
+		vma->vm_file  = obj->filp;
 
 		vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
 	}
diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index f063f5a04fb0..d8e09792793a 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem.c
@@ -564,8 +564,9 @@ int omap_gem_mmap_obj(struct drm_gem_object *obj,
 		 * address_space (so unmap_mapping_range does what we want,
 		 * in particular in the case of mmap'd dmabufs)
 		 */
+		fput(vma->vm_file);
 		vma->vm_pgoff = 0;
-		vma_set_file(vma, obj->filp);
+		vma->vm_file  = get_file(obj->filp);
 
 		vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
 	}
diff --git a/drivers/gpu/drm/vgem/vgem_drv.c b/drivers/gpu/drm/vgem/vgem_drv.c
index ea0eecae5153..fa54a6d1403d 100644
--- a/drivers/gpu/drm/vgem/vgem_drv.c
+++ b/drivers/gpu/drm/vgem/vgem_drv.c
@@ -397,7 +397,8 @@ static int vgem_prime_mmap(struct drm_gem_object *obj,
 	if (ret)
 		return ret;
 
-	vma_set_file(vma, obj->filp);
+	fput(vma->vm_file);
+	vma->vm_file = get_file(obj->filp);
 	vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP;
 	vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags));
 
diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c
index 4789d36ddfd3..10b4be1f3e78 100644
--- a/drivers/staging/android/ashmem.c
+++ b/drivers/staging/android/ashmem.c
@@ -450,9 +450,9 @@ static int ashmem_mmap(struct file *file, struct vm_area_struct *vma)
 		vma_set_anonymous(vma);
 	}
 
-	vma_set_file(vma, asma->file);
-	/* XXX: merge this with the get_file() above if possible */
-	fput(asma->file);
+	if (vma->vm_file)
+		fput(vma->vm_file);
+	vma->vm_file = asma->file;
 
 out:
 	mutex_unlock(&ashmem_mutex);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 2b7ac36c42dd..ef360fe70aaf 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2719,8 +2719,6 @@ static inline void vma_set_page_prot(struct vm_area_struct *vma)
 }
 #endif
 
-void vma_set_file(struct vm_area_struct *vma, struct file *file);
-
 #ifdef CONFIG_NUMA_BALANCING
 unsigned long change_prot_numa(struct vm_area_struct *vma,
 			unsigned long start, unsigned long end);
diff --git a/mm/mmap.c b/mm/mmap.c
index b0093cc69240..30a4e8412a58 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -136,18 +136,6 @@ void vma_set_page_prot(struct vm_area_struct *vma)
 	WRITE_ONCE(vma->vm_page_prot, vm_page_prot);
 }
 
-/*
- * Change backing file, only valid to use during initial VMA setup.
- */
-void vma_set_file(struct vm_area_struct *vma, struct file *file)
-{
-	/* Changing an anonymous vma with this is illegal */
-	get_file(file);
-	swap(vma->vm_file, file);
-	fput(file);
-}
-EXPORT_SYMBOL(vma_set_file);
-
 /*
  * Requires inode->i_mapping->i_mmap_rwsem
  */
-- 
cgit v1.2.3


From 3b20369313a486246582c8ef6ff5d1d0b9c34613 Mon Sep 17 00:00:00 2001
From: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
Date: Thu, 5 Nov 2020 15:48:51 +0800
Subject: EDAC: Add three new memory types

There are {Low-Power DDR3/4, WIO2} types of memory.
Add new entries to 'enum mem_type' and new strings to
'edac_mem_types[]' for the new types.

Signed-off-by: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
---
 drivers/edac/edac_mc.c | 3 +++
 include/linux/edac.h   | 9 +++++++++
 2 files changed, 12 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index 01ff71f7b645..eef8724faae0 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -158,10 +158,13 @@ const char * const edac_mem_types[] = {
 	[MEM_DDR3]	= "Unbuffered-DDR3",
 	[MEM_RDDR3]	= "Registered-DDR3",
 	[MEM_LRDDR3]	= "Load-Reduced-DDR3-RAM",
+	[MEM_LPDDR3]	= "Low-Power-DDR3-RAM",
 	[MEM_DDR4]	= "Unbuffered-DDR4",
 	[MEM_RDDR4]	= "Registered-DDR4",
+	[MEM_LPDDR4]	= "Low-Power-DDR4-RAM",
 	[MEM_LRDDR4]	= "Load-Reduced-DDR4-RAM",
 	[MEM_NVDIMM]	= "Non-volatile-RAM",
+	[MEM_WIO2]	= "Wide-IO-2",
 };
 EXPORT_SYMBOL_GPL(edac_mem_types);
 
diff --git a/include/linux/edac.h b/include/linux/edac.h
index 15e8f3d8a895..8f63245f7f7c 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -175,11 +175,14 @@ static inline char *mc_event_error_type(const unsigned int err_type)
  * @MEM_RDDR3:		Registered DDR3 RAM
  *			This is a variant of the DDR3 memories.
  * @MEM_LRDDR3:		Load-Reduced DDR3 memory.
+ * @MEM_LPDDR3:		Low-Power DDR3 memory.
  * @MEM_DDR4:		Unbuffered DDR4 RAM
  * @MEM_RDDR4:		Registered DDR4 RAM
  *			This is a variant of the DDR4 memories.
  * @MEM_LRDDR4:		Load-Reduced DDR4 memory.
+ * @MEM_LPDDR4:		Low-Power DDR4 memory.
  * @MEM_NVDIMM:		Non-volatile RAM
+ * @MEM_WIO2:		Wide I/O 2.
  */
 enum mem_type {
 	MEM_EMPTY = 0,
@@ -200,10 +203,13 @@ enum mem_type {
 	MEM_DDR3,
 	MEM_RDDR3,
 	MEM_LRDDR3,
+	MEM_LPDDR3,
 	MEM_DDR4,
 	MEM_RDDR4,
 	MEM_LRDDR4,
+	MEM_LPDDR4,
 	MEM_NVDIMM,
+	MEM_WIO2,
 };
 
 #define MEM_FLAG_EMPTY		BIT(MEM_EMPTY)
@@ -223,10 +229,13 @@ enum mem_type {
 #define MEM_FLAG_XDR            BIT(MEM_XDR)
 #define MEM_FLAG_DDR3           BIT(MEM_DDR3)
 #define MEM_FLAG_RDDR3          BIT(MEM_RDDR3)
+#define MEM_FLAG_LPDDR3         BIT(MEM_LPDDR3)
 #define MEM_FLAG_DDR4           BIT(MEM_DDR4)
 #define MEM_FLAG_RDDR4          BIT(MEM_RDDR4)
 #define MEM_FLAG_LRDDR4         BIT(MEM_LRDDR4)
+#define MEM_FLAG_LPDDR4         BIT(MEM_LPDDR4)
 #define MEM_FLAG_NVDIMM         BIT(MEM_NVDIMM)
+#define MEM_FLAG_WIO2		BIT(MEM_WIO2)
 
 /**
  * enum edac-type - Error Detection and Correction capabilities and mode
-- 
cgit v1.2.3


From e4b27ebc780fa7fa951d81d241912755532568ff Mon Sep 17 00:00:00 2001
From: Kurt Kanzenbach <kurt@linutronix.de>
Date: Tue, 3 Nov 2020 08:10:56 +0100
Subject: net: dsa: Add DSA driver for Hirschmann Hellcreek switches

Add a basic DSA driver for Hirschmann Hellcreek switches. Those switches are
implementing features needed for Time Sensitive Networking (TSN) such as support
for the Time Precision Protocol and various shapers like the Time Aware Shaper.

This driver includes basic support for networking:

 * VLAN handling
 * FDB handling
 * Port statistics
 * STP
 * Phylink

Signed-off-by: Kurt Kanzenbach <kurt@linutronix.de>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/Kconfig                            |    2 +
 drivers/net/dsa/Makefile                           |    1 +
 drivers/net/dsa/hirschmann/Kconfig                 |    8 +
 drivers/net/dsa/hirschmann/Makefile                |    2 +
 drivers/net/dsa/hirschmann/hellcreek.c             | 1253 ++++++++++++++++++++
 drivers/net/dsa/hirschmann/hellcreek.h             |  249 ++++
 include/linux/platform_data/hirschmann-hellcreek.h |   23 +
 7 files changed, 1538 insertions(+)
 create mode 100644 drivers/net/dsa/hirschmann/Kconfig
 create mode 100644 drivers/net/dsa/hirschmann/Makefile
 create mode 100644 drivers/net/dsa/hirschmann/hellcreek.c
 create mode 100644 drivers/net/dsa/hirschmann/hellcreek.h
 create mode 100644 include/linux/platform_data/hirschmann-hellcreek.h

(limited to 'include/linux')

diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig
index 2451f61a38e4..f6a0488589fc 100644
--- a/drivers/net/dsa/Kconfig
+++ b/drivers/net/dsa/Kconfig
@@ -24,6 +24,8 @@ config NET_DSA_LOOP
 	  This enables support for a fake mock-up switch chip which
 	  exercises the DSA APIs.
 
+source "drivers/net/dsa/hirschmann/Kconfig"
+
 config NET_DSA_LANTIQ_GSWIP
 	tristate "Lantiq / Intel GSWIP"
 	depends on HAS_IOMEM && NET_DSA
diff --git a/drivers/net/dsa/Makefile b/drivers/net/dsa/Makefile
index 4a943ccc2ca4..a84adb140a04 100644
--- a/drivers/net/dsa/Makefile
+++ b/drivers/net/dsa/Makefile
@@ -18,6 +18,7 @@ obj-$(CONFIG_NET_DSA_VITESSE_VSC73XX) += vitesse-vsc73xx-core.o
 obj-$(CONFIG_NET_DSA_VITESSE_VSC73XX_PLATFORM) += vitesse-vsc73xx-platform.o
 obj-$(CONFIG_NET_DSA_VITESSE_VSC73XX_SPI) += vitesse-vsc73xx-spi.o
 obj-y				+= b53/
+obj-y				+= hirschmann/
 obj-y				+= microchip/
 obj-y				+= mv88e6xxx/
 obj-y				+= ocelot/
diff --git a/drivers/net/dsa/hirschmann/Kconfig b/drivers/net/dsa/hirschmann/Kconfig
new file mode 100644
index 000000000000..7d189cb936e3
--- /dev/null
+++ b/drivers/net/dsa/hirschmann/Kconfig
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0
+config NET_DSA_HIRSCHMANN_HELLCREEK
+	tristate "Hirschmann Hellcreek TSN Switch support"
+	depends on HAS_IOMEM
+	depends on NET_DSA
+	select NET_DSA_TAG_HELLCREEK
+	help
+	  This driver adds support for Hirschmann Hellcreek TSN switches.
diff --git a/drivers/net/dsa/hirschmann/Makefile b/drivers/net/dsa/hirschmann/Makefile
new file mode 100644
index 000000000000..0e12e149e40f
--- /dev/null
+++ b/drivers/net/dsa/hirschmann/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_NET_DSA_HIRSCHMANN_HELLCREEK)	+= hellcreek.o
diff --git a/drivers/net/dsa/hirschmann/hellcreek.c b/drivers/net/dsa/hirschmann/hellcreek.c
new file mode 100644
index 000000000000..a4965a23db20
--- /dev/null
+++ b/drivers/net/dsa/hirschmann/hellcreek.c
@@ -0,0 +1,1253 @@
+// SPDX-License-Identifier: (GPL-2.0 or MIT)
+/*
+ * DSA driver for:
+ * Hirschmann Hellcreek TSN switch.
+ *
+ * Copyright (C) 2019,2020 Linutronix GmbH
+ * Author Kurt Kanzenbach <kurt@linutronix.de>
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_mdio.h>
+#include <linux/platform_device.h>
+#include <linux/bitops.h>
+#include <linux/if_bridge.h>
+#include <linux/if_vlan.h>
+#include <linux/etherdevice.h>
+#include <linux/random.h>
+#include <linux/iopoll.h>
+#include <linux/mutex.h>
+#include <linux/delay.h>
+#include <net/dsa.h>
+
+#include "hellcreek.h"
+
+static const struct hellcreek_counter hellcreek_counter[] = {
+	{ 0x00, "RxFiltered", },
+	{ 0x01, "RxOctets1k", },
+	{ 0x02, "RxVTAG", },
+	{ 0x03, "RxL2BAD", },
+	{ 0x04, "RxOverloadDrop", },
+	{ 0x05, "RxUC", },
+	{ 0x06, "RxMC", },
+	{ 0x07, "RxBC", },
+	{ 0x08, "RxRS<64", },
+	{ 0x09, "RxRS64", },
+	{ 0x0a, "RxRS65_127", },
+	{ 0x0b, "RxRS128_255", },
+	{ 0x0c, "RxRS256_511", },
+	{ 0x0d, "RxRS512_1023", },
+	{ 0x0e, "RxRS1024_1518", },
+	{ 0x0f, "RxRS>1518", },
+	{ 0x10, "TxTailDropQueue0", },
+	{ 0x11, "TxTailDropQueue1", },
+	{ 0x12, "TxTailDropQueue2", },
+	{ 0x13, "TxTailDropQueue3", },
+	{ 0x14, "TxTailDropQueue4", },
+	{ 0x15, "TxTailDropQueue5", },
+	{ 0x16, "TxTailDropQueue6", },
+	{ 0x17, "TxTailDropQueue7", },
+	{ 0x18, "RxTrafficClass0", },
+	{ 0x19, "RxTrafficClass1", },
+	{ 0x1a, "RxTrafficClass2", },
+	{ 0x1b, "RxTrafficClass3", },
+	{ 0x1c, "RxTrafficClass4", },
+	{ 0x1d, "RxTrafficClass5", },
+	{ 0x1e, "RxTrafficClass6", },
+	{ 0x1f, "RxTrafficClass7", },
+	{ 0x21, "TxOctets1k", },
+	{ 0x22, "TxVTAG", },
+	{ 0x23, "TxL2BAD", },
+	{ 0x25, "TxUC", },
+	{ 0x26, "TxMC", },
+	{ 0x27, "TxBC", },
+	{ 0x28, "TxTS<64", },
+	{ 0x29, "TxTS64", },
+	{ 0x2a, "TxTS65_127", },
+	{ 0x2b, "TxTS128_255", },
+	{ 0x2c, "TxTS256_511", },
+	{ 0x2d, "TxTS512_1023", },
+	{ 0x2e, "TxTS1024_1518", },
+	{ 0x2f, "TxTS>1518", },
+	{ 0x30, "TxTrafficClassOverrun0", },
+	{ 0x31, "TxTrafficClassOverrun1", },
+	{ 0x32, "TxTrafficClassOverrun2", },
+	{ 0x33, "TxTrafficClassOverrun3", },
+	{ 0x34, "TxTrafficClassOverrun4", },
+	{ 0x35, "TxTrafficClassOverrun5", },
+	{ 0x36, "TxTrafficClassOverrun6", },
+	{ 0x37, "TxTrafficClassOverrun7", },
+	{ 0x38, "TxTrafficClass0", },
+	{ 0x39, "TxTrafficClass1", },
+	{ 0x3a, "TxTrafficClass2", },
+	{ 0x3b, "TxTrafficClass3", },
+	{ 0x3c, "TxTrafficClass4", },
+	{ 0x3d, "TxTrafficClass5", },
+	{ 0x3e, "TxTrafficClass6", },
+	{ 0x3f, "TxTrafficClass7", },
+};
+
+static u16 hellcreek_read(struct hellcreek *hellcreek, unsigned int offset)
+{
+	return readw(hellcreek->base + offset);
+}
+
+static u16 hellcreek_read_ctrl(struct hellcreek *hellcreek)
+{
+	return readw(hellcreek->base + HR_CTRL_C);
+}
+
+static u16 hellcreek_read_stat(struct hellcreek *hellcreek)
+{
+	return readw(hellcreek->base + HR_SWSTAT);
+}
+
+static void hellcreek_write(struct hellcreek *hellcreek, u16 data,
+			    unsigned int offset)
+{
+	writew(data, hellcreek->base + offset);
+}
+
+static void hellcreek_select_port(struct hellcreek *hellcreek, int port)
+{
+	u16 val = port << HR_PSEL_PTWSEL_SHIFT;
+
+	hellcreek_write(hellcreek, val, HR_PSEL);
+}
+
+static void hellcreek_select_prio(struct hellcreek *hellcreek, int prio)
+{
+	u16 val = prio << HR_PSEL_PRTCWSEL_SHIFT;
+
+	hellcreek_write(hellcreek, val, HR_PSEL);
+}
+
+static void hellcreek_select_counter(struct hellcreek *hellcreek, int counter)
+{
+	u16 val = counter << HR_CSEL_SHIFT;
+
+	hellcreek_write(hellcreek, val, HR_CSEL);
+
+	/* Data sheet states to wait at least 20 internal clock cycles */
+	ndelay(200);
+}
+
+static void hellcreek_select_vlan(struct hellcreek *hellcreek, int vid,
+				  bool pvid)
+{
+	u16 val = 0;
+
+	/* Set pvid bit first */
+	if (pvid)
+		val |= HR_VIDCFG_PVID;
+	hellcreek_write(hellcreek, val, HR_VIDCFG);
+
+	/* Set vlan */
+	val |= vid << HR_VIDCFG_VID_SHIFT;
+	hellcreek_write(hellcreek, val, HR_VIDCFG);
+}
+
+static int hellcreek_wait_until_ready(struct hellcreek *hellcreek)
+{
+	u16 val;
+
+	/* Wait up to 1ms, although 3 us should be enough */
+	return readx_poll_timeout(hellcreek_read_ctrl, hellcreek,
+				  val, val & HR_CTRL_C_READY,
+				  3, 1000);
+}
+
+static int hellcreek_wait_until_transitioned(struct hellcreek *hellcreek)
+{
+	u16 val;
+
+	return readx_poll_timeout_atomic(hellcreek_read_ctrl, hellcreek,
+					 val, !(val & HR_CTRL_C_TRANSITION),
+					 1, 1000);
+}
+
+static int hellcreek_wait_fdb_ready(struct hellcreek *hellcreek)
+{
+	u16 val;
+
+	return readx_poll_timeout_atomic(hellcreek_read_stat, hellcreek,
+					 val, !(val & HR_SWSTAT_BUSY),
+					 1, 1000);
+}
+
+static int hellcreek_detect(struct hellcreek *hellcreek)
+{
+	u16 id, rel_low, rel_high, date_low, date_high, tgd_ver;
+	u8 tgd_maj, tgd_min;
+	u32 rel, date;
+
+	id	  = hellcreek_read(hellcreek, HR_MODID_C);
+	rel_low	  = hellcreek_read(hellcreek, HR_REL_L_C);
+	rel_high  = hellcreek_read(hellcreek, HR_REL_H_C);
+	date_low  = hellcreek_read(hellcreek, HR_BLD_L_C);
+	date_high = hellcreek_read(hellcreek, HR_BLD_H_C);
+	tgd_ver   = hellcreek_read(hellcreek, TR_TGDVER);
+
+	if (id != hellcreek->pdata->module_id)
+		return -ENODEV;
+
+	rel	= rel_low | (rel_high << 16);
+	date	= date_low | (date_high << 16);
+	tgd_maj = (tgd_ver & TR_TGDVER_REV_MAJ_MASK) >> TR_TGDVER_REV_MAJ_SHIFT;
+	tgd_min = (tgd_ver & TR_TGDVER_REV_MIN_MASK) >> TR_TGDVER_REV_MIN_SHIFT;
+
+	dev_info(hellcreek->dev, "Module ID=%02x Release=%04x Date=%04x TGD Version=%02x.%02x\n",
+		 id, rel, date, tgd_maj, tgd_min);
+
+	return 0;
+}
+
+static void hellcreek_feature_detect(struct hellcreek *hellcreek)
+{
+	u16 features;
+
+	features = hellcreek_read(hellcreek, HR_FEABITS0);
+
+	/* Currently we only detect the size of the FDB table */
+	hellcreek->fdb_entries = ((features & HR_FEABITS0_FDBBINS_MASK) >>
+			       HR_FEABITS0_FDBBINS_SHIFT) * 32;
+
+	dev_info(hellcreek->dev, "Feature detect: FDB entries=%zu\n",
+		 hellcreek->fdb_entries);
+}
+
+static enum dsa_tag_protocol hellcreek_get_tag_protocol(struct dsa_switch *ds,
+							int port,
+							enum dsa_tag_protocol mp)
+{
+	return DSA_TAG_PROTO_HELLCREEK;
+}
+
+static int hellcreek_port_enable(struct dsa_switch *ds, int port,
+				 struct phy_device *phy)
+{
+	struct hellcreek *hellcreek = ds->priv;
+	struct hellcreek_port *hellcreek_port;
+	u16 val;
+
+	hellcreek_port = &hellcreek->ports[port];
+
+	dev_dbg(hellcreek->dev, "Enable port %d\n", port);
+
+	mutex_lock(&hellcreek->reg_lock);
+
+	hellcreek_select_port(hellcreek, port);
+	val = hellcreek_port->ptcfg;
+	val |= HR_PTCFG_ADMIN_EN;
+	hellcreek_write(hellcreek, val, HR_PTCFG);
+	hellcreek_port->ptcfg = val;
+
+	mutex_unlock(&hellcreek->reg_lock);
+
+	return 0;
+}
+
+static void hellcreek_port_disable(struct dsa_switch *ds, int port)
+{
+	struct hellcreek *hellcreek = ds->priv;
+	struct hellcreek_port *hellcreek_port;
+	u16 val;
+
+	hellcreek_port = &hellcreek->ports[port];
+
+	dev_dbg(hellcreek->dev, "Disable port %d\n", port);
+
+	mutex_lock(&hellcreek->reg_lock);
+
+	hellcreek_select_port(hellcreek, port);
+	val = hellcreek_port->ptcfg;
+	val &= ~HR_PTCFG_ADMIN_EN;
+	hellcreek_write(hellcreek, val, HR_PTCFG);
+	hellcreek_port->ptcfg = val;
+
+	mutex_unlock(&hellcreek->reg_lock);
+}
+
+static void hellcreek_get_strings(struct dsa_switch *ds, int port,
+				  u32 stringset, uint8_t *data)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(hellcreek_counter); ++i) {
+		const struct hellcreek_counter *counter = &hellcreek_counter[i];
+
+		strlcpy(data + i * ETH_GSTRING_LEN,
+			counter->name, ETH_GSTRING_LEN);
+	}
+}
+
+static int hellcreek_get_sset_count(struct dsa_switch *ds, int port, int sset)
+{
+	if (sset != ETH_SS_STATS)
+		return 0;
+
+	return ARRAY_SIZE(hellcreek_counter);
+}
+
+static void hellcreek_get_ethtool_stats(struct dsa_switch *ds, int port,
+					uint64_t *data)
+{
+	struct hellcreek *hellcreek = ds->priv;
+	struct hellcreek_port *hellcreek_port;
+	int i;
+
+	hellcreek_port = &hellcreek->ports[port];
+
+	for (i = 0; i < ARRAY_SIZE(hellcreek_counter); ++i) {
+		const struct hellcreek_counter *counter = &hellcreek_counter[i];
+		u8 offset = counter->offset + port * 64;
+		u16 high, low;
+		u64 value = 0;
+
+		mutex_lock(&hellcreek->reg_lock);
+
+		hellcreek_select_counter(hellcreek, offset);
+
+		/* The registers are locked internally by selecting the
+		 * counter. So low and high can be read without reading high
+		 * again.
+		 */
+		high  = hellcreek_read(hellcreek, HR_CRDH);
+		low   = hellcreek_read(hellcreek, HR_CRDL);
+		value = (high << 16) | low;
+
+		hellcreek_port->counter_values[i] += value;
+		data[i] = hellcreek_port->counter_values[i];
+
+		mutex_unlock(&hellcreek->reg_lock);
+	}
+}
+
+static u16 hellcreek_private_vid(int port)
+{
+	return VLAN_N_VID - port + 1;
+}
+
+static int hellcreek_vlan_prepare(struct dsa_switch *ds, int port,
+				  const struct switchdev_obj_port_vlan *vlan)
+{
+	struct hellcreek *hellcreek = ds->priv;
+	int i;
+
+	dev_dbg(hellcreek->dev, "VLAN prepare for port %d\n", port);
+
+	/* Restriction: Make sure that nobody uses the "private" VLANs. These
+	 * VLANs are internally used by the driver to ensure port
+	 * separation. Thus, they cannot be used by someone else.
+	 */
+	for (i = 0; i < hellcreek->pdata->num_ports; ++i) {
+		const u16 restricted_vid = hellcreek_private_vid(i);
+		u16 vid;
+
+		if (!dsa_is_user_port(ds, i))
+			continue;
+
+		for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid)
+			if (vid == restricted_vid)
+				return -EBUSY;
+	}
+
+	return 0;
+}
+
+static void hellcreek_select_vlan_params(struct hellcreek *hellcreek, int port,
+					 int *shift, int *mask)
+{
+	switch (port) {
+	case 0:
+		*shift = HR_VIDMBRCFG_P0MBR_SHIFT;
+		*mask  = HR_VIDMBRCFG_P0MBR_MASK;
+		break;
+	case 1:
+		*shift = HR_VIDMBRCFG_P1MBR_SHIFT;
+		*mask  = HR_VIDMBRCFG_P1MBR_MASK;
+		break;
+	case 2:
+		*shift = HR_VIDMBRCFG_P2MBR_SHIFT;
+		*mask  = HR_VIDMBRCFG_P2MBR_MASK;
+		break;
+	case 3:
+		*shift = HR_VIDMBRCFG_P3MBR_SHIFT;
+		*mask  = HR_VIDMBRCFG_P3MBR_MASK;
+		break;
+	default:
+		*shift = *mask = 0;
+		dev_err(hellcreek->dev, "Unknown port %d selected!\n", port);
+	}
+}
+
+static void hellcreek_apply_vlan(struct hellcreek *hellcreek, int port, u16 vid,
+				 bool pvid, bool untagged)
+{
+	int shift, mask;
+	u16 val;
+
+	dev_dbg(hellcreek->dev, "Apply VLAN: port=%d vid=%u pvid=%d untagged=%d",
+		port, vid, pvid, untagged);
+
+	mutex_lock(&hellcreek->reg_lock);
+
+	hellcreek_select_port(hellcreek, port);
+	hellcreek_select_vlan(hellcreek, vid, pvid);
+
+	/* Setup port vlan membership */
+	hellcreek_select_vlan_params(hellcreek, port, &shift, &mask);
+	val = hellcreek->vidmbrcfg[vid];
+	val &= ~mask;
+	if (untagged)
+		val |= HELLCREEK_VLAN_UNTAGGED_MEMBER << shift;
+	else
+		val |= HELLCREEK_VLAN_TAGGED_MEMBER << shift;
+
+	hellcreek_write(hellcreek, val, HR_VIDMBRCFG);
+	hellcreek->vidmbrcfg[vid] = val;
+
+	mutex_unlock(&hellcreek->reg_lock);
+}
+
+static void hellcreek_unapply_vlan(struct hellcreek *hellcreek, int port,
+				   u16 vid)
+{
+	int shift, mask;
+	u16 val;
+
+	dev_dbg(hellcreek->dev, "Unapply VLAN: port=%d vid=%u\n", port, vid);
+
+	mutex_lock(&hellcreek->reg_lock);
+
+	hellcreek_select_vlan(hellcreek, vid, 0);
+
+	/* Setup port vlan membership */
+	hellcreek_select_vlan_params(hellcreek, port, &shift, &mask);
+	val = hellcreek->vidmbrcfg[vid];
+	val &= ~mask;
+	val |= HELLCREEK_VLAN_NO_MEMBER << shift;
+
+	hellcreek_write(hellcreek, val, HR_VIDMBRCFG);
+	hellcreek->vidmbrcfg[vid] = val;
+
+	mutex_unlock(&hellcreek->reg_lock);
+}
+
+static void hellcreek_vlan_add(struct dsa_switch *ds, int port,
+			       const struct switchdev_obj_port_vlan *vlan)
+{
+	bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
+	bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
+	struct hellcreek *hellcreek = ds->priv;
+	u16 vid;
+
+	dev_dbg(hellcreek->dev, "Add VLANs (%d -- %d) on port %d, %s, %s\n",
+		vlan->vid_begin, vlan->vid_end, port,
+		untagged ? "untagged" : "tagged",
+		pvid ? "PVID" : "no PVID");
+
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid)
+		hellcreek_apply_vlan(hellcreek, port, vid, pvid, untagged);
+}
+
+static int hellcreek_vlan_del(struct dsa_switch *ds, int port,
+			      const struct switchdev_obj_port_vlan *vlan)
+{
+	struct hellcreek *hellcreek = ds->priv;
+	u16 vid;
+
+	dev_dbg(hellcreek->dev, "Remove VLANs (%d -- %d) on port %d\n",
+		vlan->vid_begin, vlan->vid_end, port);
+
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid)
+		hellcreek_unapply_vlan(hellcreek, port, vid);
+
+	return 0;
+}
+
+static void hellcreek_port_stp_state_set(struct dsa_switch *ds, int port,
+					 u8 state)
+{
+	struct hellcreek *hellcreek = ds->priv;
+	struct hellcreek_port *hellcreek_port;
+	const char *new_state;
+	u16 val;
+
+	mutex_lock(&hellcreek->reg_lock);
+
+	hellcreek_port = &hellcreek->ports[port];
+	val = hellcreek_port->ptcfg;
+
+	switch (state) {
+	case BR_STATE_DISABLED:
+		new_state = "DISABLED";
+		val |= HR_PTCFG_BLOCKED;
+		val &= ~HR_PTCFG_LEARNING_EN;
+		break;
+	case BR_STATE_BLOCKING:
+		new_state = "BLOCKING";
+		val |= HR_PTCFG_BLOCKED;
+		val &= ~HR_PTCFG_LEARNING_EN;
+		break;
+	case BR_STATE_LISTENING:
+		new_state = "LISTENING";
+		val |= HR_PTCFG_BLOCKED;
+		val &= ~HR_PTCFG_LEARNING_EN;
+		break;
+	case BR_STATE_LEARNING:
+		new_state = "LEARNING";
+		val |= HR_PTCFG_BLOCKED;
+		val |= HR_PTCFG_LEARNING_EN;
+		break;
+	case BR_STATE_FORWARDING:
+		new_state = "FORWARDING";
+		val &= ~HR_PTCFG_BLOCKED;
+		val |= HR_PTCFG_LEARNING_EN;
+		break;
+	default:
+		new_state = "UNKNOWN";
+	}
+
+	hellcreek_select_port(hellcreek, port);
+	hellcreek_write(hellcreek, val, HR_PTCFG);
+	hellcreek_port->ptcfg = val;
+
+	mutex_unlock(&hellcreek->reg_lock);
+
+	dev_dbg(hellcreek->dev, "Configured STP state for port %d: %s\n",
+		port, new_state);
+}
+
+static void hellcreek_setup_ingressflt(struct hellcreek *hellcreek, int port,
+				       bool enable)
+{
+	struct hellcreek_port *hellcreek_port = &hellcreek->ports[port];
+	u16 ptcfg;
+
+	mutex_lock(&hellcreek->reg_lock);
+
+	ptcfg = hellcreek_port->ptcfg;
+
+	if (enable)
+		ptcfg |= HR_PTCFG_INGRESSFLT;
+	else
+		ptcfg &= ~HR_PTCFG_INGRESSFLT;
+
+	hellcreek_select_port(hellcreek, port);
+	hellcreek_write(hellcreek, ptcfg, HR_PTCFG);
+	hellcreek_port->ptcfg = ptcfg;
+
+	mutex_unlock(&hellcreek->reg_lock);
+}
+
+static void hellcreek_setup_vlan_awareness(struct hellcreek *hellcreek,
+					   bool enable)
+{
+	u16 swcfg;
+
+	mutex_lock(&hellcreek->reg_lock);
+
+	swcfg = hellcreek->swcfg;
+
+	if (enable)
+		swcfg |= HR_SWCFG_VLAN_UNAWARE;
+	else
+		swcfg &= ~HR_SWCFG_VLAN_UNAWARE;
+
+	hellcreek_write(hellcreek, swcfg, HR_SWCFG);
+
+	mutex_unlock(&hellcreek->reg_lock);
+}
+
+/* Default setup for DSA: VLAN <X>: CPU and Port <X> egress untagged. */
+static void hellcreek_setup_vlan_membership(struct dsa_switch *ds, int port,
+					    bool enabled)
+{
+	const u16 vid = hellcreek_private_vid(port);
+	int upstream = dsa_upstream_port(ds, port);
+	struct hellcreek *hellcreek = ds->priv;
+
+	/* Apply vid to port as egress untagged and port vlan id */
+	if (enabled)
+		hellcreek_apply_vlan(hellcreek, port, vid, true, true);
+	else
+		hellcreek_unapply_vlan(hellcreek, port, vid);
+
+	/* Apply vid to cpu port as well */
+	if (enabled)
+		hellcreek_apply_vlan(hellcreek, upstream, vid, false, true);
+	else
+		hellcreek_unapply_vlan(hellcreek, upstream, vid);
+}
+
+static int hellcreek_port_bridge_join(struct dsa_switch *ds, int port,
+				      struct net_device *br)
+{
+	struct hellcreek *hellcreek = ds->priv;
+
+	dev_dbg(hellcreek->dev, "Port %d joins a bridge\n", port);
+
+	/* When joining a vlan_filtering bridge, keep the switch VLAN aware */
+	if (!ds->vlan_filtering)
+		hellcreek_setup_vlan_awareness(hellcreek, false);
+
+	/* Drop private vlans */
+	hellcreek_setup_vlan_membership(ds, port, false);
+
+	return 0;
+}
+
+static void hellcreek_port_bridge_leave(struct dsa_switch *ds, int port,
+					struct net_device *br)
+{
+	struct hellcreek *hellcreek = ds->priv;
+
+	dev_dbg(hellcreek->dev, "Port %d leaves a bridge\n", port);
+
+	/* Enable VLAN awareness */
+	hellcreek_setup_vlan_awareness(hellcreek, true);
+
+	/* Enable private vlans */
+	hellcreek_setup_vlan_membership(ds, port, true);
+}
+
+static int __hellcreek_fdb_add(struct hellcreek *hellcreek,
+			       const struct hellcreek_fdb_entry *entry)
+{
+	u16 meta = 0;
+
+	dev_dbg(hellcreek->dev, "Add static FDB entry: MAC=%pM, MASK=0x%02x, "
+		"OBT=%d, REPRIO_EN=%d, PRIO=%d\n", entry->mac, entry->portmask,
+		entry->is_obt, entry->reprio_en, entry->reprio_tc);
+
+	/* Add mac address */
+	hellcreek_write(hellcreek, entry->mac[1] | (entry->mac[0] << 8), HR_FDBWDH);
+	hellcreek_write(hellcreek, entry->mac[3] | (entry->mac[2] << 8), HR_FDBWDM);
+	hellcreek_write(hellcreek, entry->mac[5] | (entry->mac[4] << 8), HR_FDBWDL);
+
+	/* Meta data */
+	meta |= entry->portmask << HR_FDBWRM0_PORTMASK_SHIFT;
+	if (entry->is_obt)
+		meta |= HR_FDBWRM0_OBT;
+	if (entry->reprio_en) {
+		meta |= HR_FDBWRM0_REPRIO_EN;
+		meta |= entry->reprio_tc << HR_FDBWRM0_REPRIO_TC_SHIFT;
+	}
+	hellcreek_write(hellcreek, meta, HR_FDBWRM0);
+
+	/* Commit */
+	hellcreek_write(hellcreek, 0x00, HR_FDBWRCMD);
+
+	/* Wait until done */
+	return hellcreek_wait_fdb_ready(hellcreek);
+}
+
+static int __hellcreek_fdb_del(struct hellcreek *hellcreek,
+			       const struct hellcreek_fdb_entry *entry)
+{
+	dev_dbg(hellcreek->dev, "Delete FDB entry: MAC=%pM!\n", entry->mac);
+
+	/* Delete by matching idx */
+	hellcreek_write(hellcreek, entry->idx | HR_FDBWRCMD_FDBDEL, HR_FDBWRCMD);
+
+	/* Wait until done */
+	return hellcreek_wait_fdb_ready(hellcreek);
+}
+
+/* Retrieve the index of a FDB entry by mac address. Currently we search through
+ * the complete table in hardware. If that's too slow, we might have to cache
+ * the complete FDB table in software.
+ */
+static int hellcreek_fdb_get(struct hellcreek *hellcreek,
+			     const unsigned char *dest,
+			     struct hellcreek_fdb_entry *entry)
+{
+	size_t i;
+
+	/* Set read pointer to zero: The read of HR_FDBMAX (read-only register)
+	 * should reset the internal pointer. But, that doesn't work. The vendor
+	 * suggested a subsequent write as workaround. Same for HR_FDBRDH below.
+	 */
+	hellcreek_read(hellcreek, HR_FDBMAX);
+	hellcreek_write(hellcreek, 0x00, HR_FDBMAX);
+
+	/* We have to read the complete table, because the switch/driver might
+	 * enter new entries anywhere.
+	 */
+	for (i = 0; i < hellcreek->fdb_entries; ++i) {
+		unsigned char addr[ETH_ALEN];
+		u16 meta, mac;
+
+		meta	= hellcreek_read(hellcreek, HR_FDBMDRD);
+		mac	= hellcreek_read(hellcreek, HR_FDBRDL);
+		addr[5] = mac & 0xff;
+		addr[4] = (mac & 0xff00) >> 8;
+		mac	= hellcreek_read(hellcreek, HR_FDBRDM);
+		addr[3] = mac & 0xff;
+		addr[2] = (mac & 0xff00) >> 8;
+		mac	= hellcreek_read(hellcreek, HR_FDBRDH);
+		addr[1] = mac & 0xff;
+		addr[0] = (mac & 0xff00) >> 8;
+
+		/* Force next entry */
+		hellcreek_write(hellcreek, 0x00, HR_FDBRDH);
+
+		if (memcmp(addr, dest, ETH_ALEN))
+			continue;
+
+		/* Match found */
+		entry->idx	    = i;
+		entry->portmask	    = (meta & HR_FDBMDRD_PORTMASK_MASK) >>
+			HR_FDBMDRD_PORTMASK_SHIFT;
+		entry->age	    = (meta & HR_FDBMDRD_AGE_MASK) >>
+			HR_FDBMDRD_AGE_SHIFT;
+		entry->is_obt	    = !!(meta & HR_FDBMDRD_OBT);
+		entry->pass_blocked = !!(meta & HR_FDBMDRD_PASS_BLOCKED);
+		entry->is_static    = !!(meta & HR_FDBMDRD_STATIC);
+		entry->reprio_tc    = (meta & HR_FDBMDRD_REPRIO_TC_MASK) >>
+			HR_FDBMDRD_REPRIO_TC_SHIFT;
+		entry->reprio_en    = !!(meta & HR_FDBMDRD_REPRIO_EN);
+		memcpy(entry->mac, addr, sizeof(addr));
+
+		return 0;
+	}
+
+	return -ENOENT;
+}
+
+static int hellcreek_fdb_add(struct dsa_switch *ds, int port,
+			     const unsigned char *addr, u16 vid)
+{
+	struct hellcreek_fdb_entry entry = { 0 };
+	struct hellcreek *hellcreek = ds->priv;
+	int ret;
+
+	dev_dbg(hellcreek->dev, "Add FDB entry for MAC=%pM\n", addr);
+
+	mutex_lock(&hellcreek->reg_lock);
+
+	ret = hellcreek_fdb_get(hellcreek, addr, &entry);
+	if (ret) {
+		/* Not found */
+		memcpy(entry.mac, addr, sizeof(entry.mac));
+		entry.portmask = BIT(port);
+
+		ret = __hellcreek_fdb_add(hellcreek, &entry);
+		if (ret) {
+			dev_err(hellcreek->dev, "Failed to add FDB entry!\n");
+			goto out;
+		}
+	} else {
+		/* Found */
+		ret = __hellcreek_fdb_del(hellcreek, &entry);
+		if (ret) {
+			dev_err(hellcreek->dev, "Failed to delete FDB entry!\n");
+			goto out;
+		}
+
+		entry.portmask |= BIT(port);
+
+		ret = __hellcreek_fdb_add(hellcreek, &entry);
+		if (ret) {
+			dev_err(hellcreek->dev, "Failed to add FDB entry!\n");
+			goto out;
+		}
+	}
+
+out:
+	mutex_unlock(&hellcreek->reg_lock);
+
+	return ret;
+}
+
+static int hellcreek_fdb_del(struct dsa_switch *ds, int port,
+			     const unsigned char *addr, u16 vid)
+{
+	struct hellcreek_fdb_entry entry = { 0 };
+	struct hellcreek *hellcreek = ds->priv;
+	int ret;
+
+	dev_dbg(hellcreek->dev, "Delete FDB entry for MAC=%pM\n", addr);
+
+	mutex_lock(&hellcreek->reg_lock);
+
+	ret = hellcreek_fdb_get(hellcreek, addr, &entry);
+	if (ret) {
+		/* Not found */
+		dev_err(hellcreek->dev, "FDB entry for deletion not found!\n");
+	} else {
+		/* Found */
+		ret = __hellcreek_fdb_del(hellcreek, &entry);
+		if (ret) {
+			dev_err(hellcreek->dev, "Failed to delete FDB entry!\n");
+			goto out;
+		}
+
+		entry.portmask &= ~BIT(port);
+
+		if (entry.portmask != 0x00) {
+			ret = __hellcreek_fdb_add(hellcreek, &entry);
+			if (ret) {
+				dev_err(hellcreek->dev, "Failed to add FDB entry!\n");
+				goto out;
+			}
+		}
+	}
+
+out:
+	mutex_unlock(&hellcreek->reg_lock);
+
+	return ret;
+}
+
+static int hellcreek_fdb_dump(struct dsa_switch *ds, int port,
+			      dsa_fdb_dump_cb_t *cb, void *data)
+{
+	struct hellcreek *hellcreek = ds->priv;
+	u16 entries;
+	size_t i;
+
+	mutex_lock(&hellcreek->reg_lock);
+
+	/* Set read pointer to zero: The read of HR_FDBMAX (read-only register)
+	 * should reset the internal pointer. But, that doesn't work. The vendor
+	 * suggested a subsequent write as workaround. Same for HR_FDBRDH below.
+	 */
+	entries = hellcreek_read(hellcreek, HR_FDBMAX);
+	hellcreek_write(hellcreek, 0x00, HR_FDBMAX);
+
+	dev_dbg(hellcreek->dev, "FDB dump for port %d, entries=%d!\n", port, entries);
+
+	/* Read table */
+	for (i = 0; i < hellcreek->fdb_entries; ++i) {
+		unsigned char null_addr[ETH_ALEN] = { 0 };
+		struct hellcreek_fdb_entry entry = { 0 };
+		u16 meta, mac;
+
+		meta	= hellcreek_read(hellcreek, HR_FDBMDRD);
+		mac	= hellcreek_read(hellcreek, HR_FDBRDL);
+		entry.mac[5] = mac & 0xff;
+		entry.mac[4] = (mac & 0xff00) >> 8;
+		mac	= hellcreek_read(hellcreek, HR_FDBRDM);
+		entry.mac[3] = mac & 0xff;
+		entry.mac[2] = (mac & 0xff00) >> 8;
+		mac	= hellcreek_read(hellcreek, HR_FDBRDH);
+		entry.mac[1] = mac & 0xff;
+		entry.mac[0] = (mac & 0xff00) >> 8;
+
+		/* Force next entry */
+		hellcreek_write(hellcreek, 0x00, HR_FDBRDH);
+
+		/* Check valid */
+		if (!memcmp(entry.mac, null_addr, ETH_ALEN))
+			continue;
+
+		entry.portmask	= (meta & HR_FDBMDRD_PORTMASK_MASK) >>
+			HR_FDBMDRD_PORTMASK_SHIFT;
+		entry.is_static	= !!(meta & HR_FDBMDRD_STATIC);
+
+		/* Check port mask */
+		if (!(entry.portmask & BIT(port)))
+			continue;
+
+		cb(entry.mac, 0, entry.is_static, data);
+	}
+
+	mutex_unlock(&hellcreek->reg_lock);
+
+	return 0;
+}
+
+static int hellcreek_vlan_filtering(struct dsa_switch *ds, int port,
+				    bool vlan_filtering,
+				    struct switchdev_trans *trans)
+{
+	struct hellcreek *hellcreek = ds->priv;
+
+	if (switchdev_trans_ph_prepare(trans))
+		return 0;
+
+	dev_dbg(hellcreek->dev, "%s VLAN filtering on port %d\n",
+		vlan_filtering ? "Enable" : "Disable", port);
+
+	/* Configure port to drop packages with not known vids */
+	hellcreek_setup_ingressflt(hellcreek, port, vlan_filtering);
+
+	/* Enable VLAN awareness on the switch. This save due to
+	 * ds->vlan_filtering_is_global.
+	 */
+	hellcreek_setup_vlan_awareness(hellcreek, vlan_filtering);
+
+	return 0;
+}
+
+static int hellcreek_enable_ip_core(struct hellcreek *hellcreek)
+{
+	int ret;
+	u16 val;
+
+	mutex_lock(&hellcreek->reg_lock);
+
+	val = hellcreek_read(hellcreek, HR_CTRL_C);
+	val |= HR_CTRL_C_ENABLE;
+	hellcreek_write(hellcreek, val, HR_CTRL_C);
+	ret = hellcreek_wait_until_transitioned(hellcreek);
+
+	mutex_unlock(&hellcreek->reg_lock);
+
+	return ret;
+}
+
+static void hellcreek_setup_cpu_and_tunnel_port(struct hellcreek *hellcreek)
+{
+	struct hellcreek_port *tunnel_port = &hellcreek->ports[TUNNEL_PORT];
+	struct hellcreek_port *cpu_port = &hellcreek->ports[CPU_PORT];
+	u16 ptcfg = 0;
+
+	ptcfg |= HR_PTCFG_LEARNING_EN | HR_PTCFG_ADMIN_EN;
+
+	mutex_lock(&hellcreek->reg_lock);
+
+	hellcreek_select_port(hellcreek, CPU_PORT);
+	hellcreek_write(hellcreek, ptcfg, HR_PTCFG);
+
+	hellcreek_select_port(hellcreek, TUNNEL_PORT);
+	hellcreek_write(hellcreek, ptcfg, HR_PTCFG);
+
+	cpu_port->ptcfg	   = ptcfg;
+	tunnel_port->ptcfg = ptcfg;
+
+	mutex_unlock(&hellcreek->reg_lock);
+}
+
+static void hellcreek_setup_tc_identity_mapping(struct hellcreek *hellcreek)
+{
+	int i;
+
+	/* The switch has multiple egress queues per port. The queue is selected
+	 * via the PCP field in the VLAN header. The switch internally deals
+	 * with traffic classes instead of PCP values and this mapping is
+	 * configurable.
+	 *
+	 * The default mapping is (PCP - TC):
+	 *  7 - 7
+	 *  6 - 6
+	 *  5 - 5
+	 *  4 - 4
+	 *  3 - 3
+	 *  2 - 1
+	 *  1 - 0
+	 *  0 - 2
+	 *
+	 * The default should be an identity mapping.
+	 */
+
+	for (i = 0; i < 8; ++i) {
+		mutex_lock(&hellcreek->reg_lock);
+
+		hellcreek_select_prio(hellcreek, i);
+		hellcreek_write(hellcreek,
+				i << HR_PRTCCFG_PCP_TC_MAP_SHIFT,
+				HR_PRTCCFG);
+
+		mutex_unlock(&hellcreek->reg_lock);
+	}
+}
+
+static int hellcreek_setup(struct dsa_switch *ds)
+{
+	struct hellcreek *hellcreek = ds->priv;
+	u16 swcfg = 0;
+	int ret, i;
+
+	dev_dbg(hellcreek->dev, "Set up the switch\n");
+
+	/* Let's go */
+	ret = hellcreek_enable_ip_core(hellcreek);
+	if (ret) {
+		dev_err(hellcreek->dev, "Failed to enable IP core!\n");
+		return ret;
+	}
+
+	/* Enable CPU/Tunnel ports */
+	hellcreek_setup_cpu_and_tunnel_port(hellcreek);
+
+	/* Switch config: Keep defaults, enable FDB aging and learning and tag
+	 * each frame from/to cpu port for DSA tagging.  Also enable the length
+	 * aware shaping mode. This eliminates the need for Qbv guard bands.
+	 */
+	swcfg |= HR_SWCFG_FDBAGE_EN |
+		HR_SWCFG_FDBLRN_EN  |
+		HR_SWCFG_ALWAYS_OBT |
+		(HR_SWCFG_LAS_ON << HR_SWCFG_LAS_MODE_SHIFT);
+	hellcreek->swcfg = swcfg;
+	hellcreek_write(hellcreek, swcfg, HR_SWCFG);
+
+	/* Initial vlan membership to reflect port separation */
+	for (i = 0; i < ds->num_ports; ++i) {
+		if (!dsa_is_user_port(ds, i))
+			continue;
+
+		hellcreek_setup_vlan_membership(ds, i, true);
+	}
+
+	/* Configure PCP <-> TC mapping */
+	hellcreek_setup_tc_identity_mapping(hellcreek);
+
+	/* Allow VLAN configurations while not filtering which is the default
+	 * for new DSA drivers.
+	 */
+	ds->configure_vlan_while_not_filtering = true;
+
+	/* The VLAN awareness is a global switch setting. Therefore, mixed vlan
+	 * filtering setups are not supported.
+	 */
+	ds->vlan_filtering_is_global = true;
+
+	return 0;
+}
+
+static void hellcreek_phylink_validate(struct dsa_switch *ds, int port,
+				       unsigned long *supported,
+				       struct phylink_link_state *state)
+{
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
+	struct hellcreek *hellcreek = ds->priv;
+
+	dev_dbg(hellcreek->dev, "Phylink validate for port %d\n", port);
+
+	/* The MAC settings are a hardware configuration option and cannot be
+	 * changed at run time or by strapping. Therefore the attached PHYs
+	 * should be programmed to only advertise settings which are supported
+	 * by the hardware.
+	 */
+	if (hellcreek->pdata->is_100_mbits)
+		phylink_set(mask, 100baseT_Full);
+	else
+		phylink_set(mask, 1000baseT_Full);
+
+	bitmap_and(supported, supported, mask,
+		   __ETHTOOL_LINK_MODE_MASK_NBITS);
+	bitmap_and(state->advertising, state->advertising, mask,
+		   __ETHTOOL_LINK_MODE_MASK_NBITS);
+}
+
+static int
+hellcreek_port_prechangeupper(struct dsa_switch *ds, int port,
+			      struct netdev_notifier_changeupper_info *info)
+{
+	struct hellcreek *hellcreek = ds->priv;
+	bool used = true;
+	int ret = -EBUSY;
+	u16 vid;
+	int i;
+
+	dev_dbg(hellcreek->dev, "Pre change upper for port %d\n", port);
+
+	/*
+	 * Deny VLAN devices on top of lan ports with the same VLAN ids, because
+	 * it breaks the port separation due to the private VLANs. Example:
+	 *
+	 * lan0.100 *and* lan1.100 cannot be used in parallel. However, lan0.99
+	 * and lan1.100 works.
+	 */
+
+	if (!is_vlan_dev(info->upper_dev))
+		return 0;
+
+	vid = vlan_dev_vlan_id(info->upper_dev);
+
+	/* For all ports, check bitmaps */
+	mutex_lock(&hellcreek->vlan_lock);
+	for (i = 0; i < hellcreek->pdata->num_ports; ++i) {
+		if (!dsa_is_user_port(ds, i))
+			continue;
+
+		if (port == i)
+			continue;
+
+		used = used && test_bit(vid, hellcreek->ports[i].vlan_dev_bitmap);
+	}
+
+	if (used)
+		goto out;
+
+	/* Update bitmap */
+	set_bit(vid, hellcreek->ports[port].vlan_dev_bitmap);
+
+	ret = 0;
+
+out:
+	mutex_unlock(&hellcreek->vlan_lock);
+
+	return ret;
+}
+
+static const struct dsa_switch_ops hellcreek_ds_ops = {
+	.get_ethtool_stats   = hellcreek_get_ethtool_stats,
+	.get_sset_count	     = hellcreek_get_sset_count,
+	.get_strings	     = hellcreek_get_strings,
+	.get_tag_protocol    = hellcreek_get_tag_protocol,
+	.phylink_validate    = hellcreek_phylink_validate,
+	.port_bridge_join    = hellcreek_port_bridge_join,
+	.port_bridge_leave   = hellcreek_port_bridge_leave,
+	.port_disable	     = hellcreek_port_disable,
+	.port_enable	     = hellcreek_port_enable,
+	.port_fdb_add	     = hellcreek_fdb_add,
+	.port_fdb_del	     = hellcreek_fdb_del,
+	.port_fdb_dump	     = hellcreek_fdb_dump,
+	.port_prechangeupper = hellcreek_port_prechangeupper,
+	.port_stp_state_set  = hellcreek_port_stp_state_set,
+	.port_vlan_add	     = hellcreek_vlan_add,
+	.port_vlan_del	     = hellcreek_vlan_del,
+	.port_vlan_filtering = hellcreek_vlan_filtering,
+	.port_vlan_prepare   = hellcreek_vlan_prepare,
+	.setup		     = hellcreek_setup,
+};
+
+static int hellcreek_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct hellcreek *hellcreek;
+	struct resource *res;
+	int ret, i;
+
+	hellcreek = devm_kzalloc(dev, sizeof(*hellcreek), GFP_KERNEL);
+	if (!hellcreek)
+		return -ENOMEM;
+
+	hellcreek->vidmbrcfg = devm_kcalloc(dev, VLAN_N_VID,
+					    sizeof(*hellcreek->vidmbrcfg),
+					    GFP_KERNEL);
+	if (!hellcreek->vidmbrcfg)
+		return -ENOMEM;
+
+	hellcreek->pdata = of_device_get_match_data(dev);
+
+	hellcreek->ports = devm_kcalloc(dev, hellcreek->pdata->num_ports,
+					sizeof(*hellcreek->ports),
+					GFP_KERNEL);
+	if (!hellcreek->ports)
+		return -ENOMEM;
+
+	for (i = 0; i < hellcreek->pdata->num_ports; ++i) {
+		struct hellcreek_port *port = &hellcreek->ports[i];
+
+		port->counter_values =
+			devm_kcalloc(dev,
+				     ARRAY_SIZE(hellcreek_counter),
+				     sizeof(*port->counter_values),
+				     GFP_KERNEL);
+		if (!port->counter_values)
+			return -ENOMEM;
+
+		port->vlan_dev_bitmap =
+			devm_kcalloc(dev,
+				     BITS_TO_LONGS(VLAN_N_VID),
+				     sizeof(unsigned long),
+				     GFP_KERNEL);
+		if (!port->vlan_dev_bitmap)
+			return -ENOMEM;
+
+		port->hellcreek	= hellcreek;
+		port->port	= i;
+	}
+
+	mutex_init(&hellcreek->reg_lock);
+	mutex_init(&hellcreek->vlan_lock);
+
+	hellcreek->dev = dev;
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "tsn");
+	if (!res) {
+		dev_err(dev, "No memory region provided!\n");
+		return -ENODEV;
+	}
+
+	hellcreek->base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(hellcreek->base)) {
+		dev_err(dev, "No memory available!\n");
+		return PTR_ERR(hellcreek->base);
+	}
+
+	ret = hellcreek_detect(hellcreek);
+	if (ret) {
+		dev_err(dev, "No (known) chip found!\n");
+		return ret;
+	}
+
+	ret = hellcreek_wait_until_ready(hellcreek);
+	if (ret) {
+		dev_err(dev, "Switch didn't become ready!\n");
+		return ret;
+	}
+
+	hellcreek_feature_detect(hellcreek);
+
+	hellcreek->ds = devm_kzalloc(dev, sizeof(*hellcreek->ds), GFP_KERNEL);
+	if (!hellcreek->ds)
+		return -ENOMEM;
+
+	hellcreek->ds->dev	     = dev;
+	hellcreek->ds->priv	     = hellcreek;
+	hellcreek->ds->ops	     = &hellcreek_ds_ops;
+	hellcreek->ds->num_ports     = hellcreek->pdata->num_ports;
+	hellcreek->ds->num_tx_queues = HELLCREEK_NUM_EGRESS_QUEUES;
+
+	ret = dsa_register_switch(hellcreek->ds);
+	if (ret) {
+		dev_err(dev, "Unable to register switch\n");
+		return ret;
+	}
+
+	platform_set_drvdata(pdev, hellcreek);
+
+	return 0;
+}
+
+static int hellcreek_remove(struct platform_device *pdev)
+{
+	struct hellcreek *hellcreek = platform_get_drvdata(pdev);
+
+	dsa_unregister_switch(hellcreek->ds);
+	platform_set_drvdata(pdev, NULL);
+
+	return 0;
+}
+
+static const struct hellcreek_platform_data de1soc_r1_pdata = {
+	.num_ports	 = 4,
+	.is_100_mbits	 = 1,
+	.qbv_support	 = 1,
+	.qbv_on_cpu_port = 1,
+	.qbu_support	 = 0,
+	.module_id	 = 0x4c30,
+};
+
+static const struct of_device_id hellcreek_of_match[] = {
+	{
+		.compatible = "hirschmann,hellcreek-de1soc-r1",
+		.data	    = &de1soc_r1_pdata,
+	},
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, hellcreek_of_match);
+
+static struct platform_driver hellcreek_driver = {
+	.probe	= hellcreek_probe,
+	.remove = hellcreek_remove,
+	.driver = {
+		.name = "hellcreek",
+		.of_match_table = hellcreek_of_match,
+	},
+};
+module_platform_driver(hellcreek_driver);
+
+MODULE_AUTHOR("Kurt Kanzenbach <kurt@linutronix.de>");
+MODULE_DESCRIPTION("Hirschmann Hellcreek driver");
+MODULE_LICENSE("Dual MIT/GPL");
diff --git a/drivers/net/dsa/hirschmann/hellcreek.h b/drivers/net/dsa/hirschmann/hellcreek.h
new file mode 100644
index 000000000000..762bf9734630
--- /dev/null
+++ b/drivers/net/dsa/hirschmann/hellcreek.h
@@ -0,0 +1,249 @@
+/* SPDX-License-Identifier: (GPL-2.0 or MIT) */
+/*
+ * DSA driver for:
+ * Hirschmann Hellcreek TSN switch.
+ *
+ * Copyright (C) 2019,2020 Linutronix GmbH
+ * Author Kurt Kanzenbach <kurt@linutronix.de>
+ */
+
+#ifndef _HELLCREEK_H_
+#define _HELLCREEK_H_
+
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/mutex.h>
+#include <linux/platform_data/hirschmann-hellcreek.h>
+#include <linux/ptp_clock_kernel.h>
+#include <linux/timecounter.h>
+#include <net/dsa.h>
+
+/* Ports:
+ *  - 0: CPU
+ *  - 1: Tunnel
+ *  - 2: TSN front port 1
+ *  - 3: TSN front port 2
+ *  - ...
+ */
+#define CPU_PORT			0
+#define TUNNEL_PORT			1
+
+#define HELLCREEK_VLAN_NO_MEMBER	0x0
+#define HELLCREEK_VLAN_UNTAGGED_MEMBER	0x1
+#define HELLCREEK_VLAN_TAGGED_MEMBER	0x3
+#define HELLCREEK_NUM_EGRESS_QUEUES	8
+
+/* Register definitions */
+#define HR_MODID_C			(0 * 2)
+#define HR_REL_L_C			(1 * 2)
+#define HR_REL_H_C			(2 * 2)
+#define HR_BLD_L_C			(3 * 2)
+#define HR_BLD_H_C			(4 * 2)
+#define HR_CTRL_C			(5 * 2)
+#define HR_CTRL_C_READY			BIT(14)
+#define HR_CTRL_C_TRANSITION		BIT(13)
+#define HR_CTRL_C_ENABLE		BIT(0)
+
+#define HR_PSEL				(0xa6 * 2)
+#define HR_PSEL_PTWSEL_SHIFT		4
+#define HR_PSEL_PTWSEL_MASK		GENMASK(5, 4)
+#define HR_PSEL_PRTCWSEL_SHIFT		0
+#define HR_PSEL_PRTCWSEL_MASK		GENMASK(2, 0)
+
+#define HR_PTCFG			(0xa7 * 2)
+#define HR_PTCFG_MLIMIT_EN		BIT(13)
+#define HR_PTCFG_UMC_FLT		BIT(10)
+#define HR_PTCFG_UUC_FLT		BIT(9)
+#define HR_PTCFG_UNTRUST		BIT(8)
+#define HR_PTCFG_TAG_REQUIRED		BIT(7)
+#define HR_PTCFG_PPRIO_SHIFT		4
+#define HR_PTCFG_PPRIO_MASK		GENMASK(6, 4)
+#define HR_PTCFG_INGRESSFLT		BIT(3)
+#define HR_PTCFG_BLOCKED		BIT(2)
+#define HR_PTCFG_LEARNING_EN		BIT(1)
+#define HR_PTCFG_ADMIN_EN		BIT(0)
+
+#define HR_PRTCCFG			(0xa8 * 2)
+#define HR_PRTCCFG_PCP_TC_MAP_SHIFT	0
+#define HR_PRTCCFG_PCP_TC_MAP_MASK	GENMASK(2, 0)
+
+#define HR_CSEL				(0x8d * 2)
+#define HR_CSEL_SHIFT			0
+#define HR_CSEL_MASK			GENMASK(7, 0)
+#define HR_CRDL				(0x8e * 2)
+#define HR_CRDH				(0x8f * 2)
+
+#define HR_SWTRC_CFG			(0x90 * 2)
+#define HR_SWTRC0			(0x91 * 2)
+#define HR_SWTRC1			(0x92 * 2)
+#define HR_PFREE			(0x93 * 2)
+#define HR_MFREE			(0x94 * 2)
+
+#define HR_FDBAGE			(0x97 * 2)
+#define HR_FDBMAX			(0x98 * 2)
+#define HR_FDBRDL			(0x99 * 2)
+#define HR_FDBRDM			(0x9a * 2)
+#define HR_FDBRDH			(0x9b * 2)
+
+#define HR_FDBMDRD			(0x9c * 2)
+#define HR_FDBMDRD_PORTMASK_SHIFT	0
+#define HR_FDBMDRD_PORTMASK_MASK	GENMASK(3, 0)
+#define HR_FDBMDRD_AGE_SHIFT		4
+#define HR_FDBMDRD_AGE_MASK		GENMASK(7, 4)
+#define HR_FDBMDRD_OBT			BIT(8)
+#define HR_FDBMDRD_PASS_BLOCKED		BIT(9)
+#define HR_FDBMDRD_STATIC		BIT(11)
+#define HR_FDBMDRD_REPRIO_TC_SHIFT	12
+#define HR_FDBMDRD_REPRIO_TC_MASK	GENMASK(14, 12)
+#define HR_FDBMDRD_REPRIO_EN		BIT(15)
+
+#define HR_FDBWDL			(0x9d * 2)
+#define HR_FDBWDM			(0x9e * 2)
+#define HR_FDBWDH			(0x9f * 2)
+#define HR_FDBWRM0			(0xa0 * 2)
+#define HR_FDBWRM0_PORTMASK_SHIFT	0
+#define HR_FDBWRM0_PORTMASK_MASK	GENMASK(3, 0)
+#define HR_FDBWRM0_OBT			BIT(8)
+#define HR_FDBWRM0_PASS_BLOCKED		BIT(9)
+#define HR_FDBWRM0_REPRIO_TC_SHIFT	12
+#define HR_FDBWRM0_REPRIO_TC_MASK	GENMASK(14, 12)
+#define HR_FDBWRM0_REPRIO_EN		BIT(15)
+#define HR_FDBWRM1			(0xa1 * 2)
+
+#define HR_FDBWRCMD			(0xa2 * 2)
+#define HR_FDBWRCMD_FDBDEL		BIT(9)
+
+#define HR_SWCFG			(0xa3 * 2)
+#define HR_SWCFG_GM_STATEMD		BIT(15)
+#define HR_SWCFG_LAS_MODE_SHIFT		12
+#define HR_SWCFG_LAS_MODE_MASK		GENMASK(13, 12)
+#define HR_SWCFG_LAS_OFF		(0x00)
+#define HR_SWCFG_LAS_ON			(0x01)
+#define HR_SWCFG_LAS_STATIC		(0x10)
+#define HR_SWCFG_CT_EN			BIT(11)
+#define HR_SWCFG_VLAN_UNAWARE		BIT(10)
+#define HR_SWCFG_ALWAYS_OBT		BIT(9)
+#define HR_SWCFG_FDBAGE_EN		BIT(5)
+#define HR_SWCFG_FDBLRN_EN		BIT(4)
+
+#define HR_SWSTAT			(0xa4 * 2)
+#define HR_SWSTAT_FAIL			BIT(4)
+#define HR_SWSTAT_BUSY			BIT(0)
+
+#define HR_SWCMD			(0xa5 * 2)
+#define HW_SWCMD_FLUSH			BIT(0)
+
+#define HR_VIDCFG			(0xaa * 2)
+#define HR_VIDCFG_VID_SHIFT		0
+#define HR_VIDCFG_VID_MASK		GENMASK(11, 0)
+#define HR_VIDCFG_PVID			BIT(12)
+
+#define HR_VIDMBRCFG			(0xab * 2)
+#define HR_VIDMBRCFG_P0MBR_SHIFT	0
+#define HR_VIDMBRCFG_P0MBR_MASK		GENMASK(1, 0)
+#define HR_VIDMBRCFG_P1MBR_SHIFT	2
+#define HR_VIDMBRCFG_P1MBR_MASK		GENMASK(3, 2)
+#define HR_VIDMBRCFG_P2MBR_SHIFT	4
+#define HR_VIDMBRCFG_P2MBR_MASK		GENMASK(5, 4)
+#define HR_VIDMBRCFG_P3MBR_SHIFT	6
+#define HR_VIDMBRCFG_P3MBR_MASK		GENMASK(7, 6)
+
+#define HR_FEABITS0			(0xac * 2)
+#define HR_FEABITS0_FDBBINS_SHIFT	4
+#define HR_FEABITS0_FDBBINS_MASK	GENMASK(7, 4)
+#define HR_FEABITS0_PCNT_SHIFT		8
+#define HR_FEABITS0_PCNT_MASK		GENMASK(11, 8)
+#define HR_FEABITS0_MCNT_SHIFT		12
+#define HR_FEABITS0_MCNT_MASK		GENMASK(15, 12)
+
+#define TR_QTRACK			(0xb1 * 2)
+#define TR_TGDVER			(0xb3 * 2)
+#define TR_TGDVER_REV_MIN_MASK		GENMASK(7, 0)
+#define TR_TGDVER_REV_MIN_SHIFT		0
+#define TR_TGDVER_REV_MAJ_MASK		GENMASK(15, 8)
+#define TR_TGDVER_REV_MAJ_SHIFT		8
+#define TR_TGDSEL			(0xb4 * 2)
+#define TR_TGDSEL_TDGSEL_MASK		GENMASK(1, 0)
+#define TR_TGDSEL_TDGSEL_SHIFT		0
+#define TR_TGDCTRL			(0xb5 * 2)
+#define TR_TGDCTRL_GATE_EN		BIT(0)
+#define TR_TGDCTRL_CYC_SNAP		BIT(4)
+#define TR_TGDCTRL_SNAP_EST		BIT(5)
+#define TR_TGDCTRL_ADMINGATESTATES_MASK	GENMASK(15, 8)
+#define TR_TGDCTRL_ADMINGATESTATES_SHIFT	8
+#define TR_TGDSTAT0			(0xb6 * 2)
+#define TR_TGDSTAT1			(0xb7 * 2)
+#define TR_ESTWRL			(0xb8 * 2)
+#define TR_ESTWRH			(0xb9 * 2)
+#define TR_ESTCMD			(0xba * 2)
+#define TR_ESTCMD_ESTSEC_MASK		GENMASK(2, 0)
+#define TR_ESTCMD_ESTSEC_SHIFT		0
+#define TR_ESTCMD_ESTARM		BIT(4)
+#define TR_ESTCMD_ESTSWCFG		BIT(5)
+#define TR_EETWRL			(0xbb * 2)
+#define TR_EETWRH			(0xbc * 2)
+#define TR_EETCMD			(0xbd * 2)
+#define TR_EETCMD_EETSEC_MASK		GEMASK(2, 0)
+#define TR_EETCMD_EETSEC_SHIFT		0
+#define TR_EETCMD_EETARM		BIT(4)
+#define TR_CTWRL			(0xbe * 2)
+#define TR_CTWRH			(0xbf * 2)
+#define TR_LCNSL			(0xc1 * 2)
+#define TR_LCNSH			(0xc2 * 2)
+#define TR_LCS				(0xc3 * 2)
+#define TR_GCLDAT			(0xc4 * 2)
+#define TR_GCLDAT_GCLWRGATES_MASK	GENMASK(7, 0)
+#define TR_GCLDAT_GCLWRGATES_SHIFT	0
+#define TR_GCLDAT_GCLWRLAST		BIT(8)
+#define TR_GCLDAT_GCLOVRI		BIT(9)
+#define TR_GCLTIL			(0xc5 * 2)
+#define TR_GCLTIH			(0xc6 * 2)
+#define TR_GCLCMD			(0xc7 * 2)
+#define TR_GCLCMD_GCLWRADR_MASK		GENMASK(7, 0)
+#define TR_GCLCMD_GCLWRADR_SHIFT	0
+#define TR_GCLCMD_INIT_GATE_STATES_MASK	GENMASK(15, 8)
+#define TR_GCLCMD_INIT_GATE_STATES_SHIFT	8
+
+struct hellcreek_counter {
+	u8 offset;
+	const char *name;
+};
+
+struct hellcreek;
+
+struct hellcreek_port {
+	struct hellcreek *hellcreek;
+	unsigned long *vlan_dev_bitmap;
+	int port;
+	u16 ptcfg;		/* ptcfg shadow */
+	u64 *counter_values;
+};
+
+struct hellcreek_fdb_entry {
+	size_t idx;
+	unsigned char mac[ETH_ALEN];
+	u8 portmask;
+	u8 age;
+	u8 is_obt;
+	u8 pass_blocked;
+	u8 is_static;
+	u8 reprio_tc;
+	u8 reprio_en;
+};
+
+struct hellcreek {
+	const struct hellcreek_platform_data *pdata;
+	struct device *dev;
+	struct dsa_switch *ds;
+	struct hellcreek_port *ports;
+	struct mutex reg_lock;	/* Switch IP register lock */
+	struct mutex vlan_lock;	/* VLAN bitmaps lock */
+	void __iomem *base;
+	u16 swcfg;		/* swcfg shadow */
+	u8 *vidmbrcfg;		/* vidmbrcfg shadow */
+	size_t fdb_entries;
+};
+
+#endif /* _HELLCREEK_H_ */
diff --git a/include/linux/platform_data/hirschmann-hellcreek.h b/include/linux/platform_data/hirschmann-hellcreek.h
new file mode 100644
index 000000000000..388846766bb2
--- /dev/null
+++ b/include/linux/platform_data/hirschmann-hellcreek.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: (GPL-2.0 or MIT) */
+/*
+ * Hirschmann Hellcreek TSN switch platform data.
+ *
+ * Copyright (C) 2020 Linutronix GmbH
+ * Author Kurt Kanzenbach <kurt@linutronix.de>
+ */
+
+#ifndef _HIRSCHMANN_HELLCREEK_H_
+#define _HIRSCHMANN_HELLCREEK_H_
+
+#include <linux/types.h>
+
+struct hellcreek_platform_data {
+	int num_ports;		/* Amount of switch ports */
+	int is_100_mbits;	/* Is it configured to 100 or 1000 mbit/s */
+	int qbv_support;	/* Qbv support on front TSN ports */
+	int qbv_on_cpu_port;	/* Qbv support on the CPU port */
+	int qbu_support;	/* Qbu support on front TSN ports */
+	u16 module_id;		/* Module identificaton */
+};
+
+#endif /* _HIRSCHMANN_HELLCREEK_H_ */
-- 
cgit v1.2.3


From 293e9a3d950dfebc76d9fa6931e6f91ef856b9ab Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Sun, 1 Nov 2020 14:50:56 +0200
Subject: net: phy: export phy_error and phy_trigger_machine

These functions are currently used by phy_interrupt() to either signal
an error condition or to trigger the link state machine. In an attempt
to actually support shared PHY IRQs, export these two functions so that
the actual PHY drivers can use them.

Cc: Alexandru Ardelean <alexandru.ardelean@analog.com>
Cc: Andre Edich <andre.edich@microchip.com>
Cc: Antoine Tenart <atenart@kernel.org>
Cc: Baruch Siach <baruch@tkos.co.il>
Cc: Christophe Leroy <christophe.leroy@c-s.fr>
Cc: Dan Murphy <dmurphy@ti.com>
Cc: Divya Koppera <Divya.Koppera@microchip.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: Hauke Mehrtens <hauke@hauke-m.de>
Cc: Heiner Kallweit <hkallweit1@gmail.com>
Cc: Jerome Brunet <jbrunet@baylibre.com>
Cc: Kavya Sree Kotagiri <kavyasree.kotagiri@microchip.com>
Cc: Linus Walleij <linus.walleij@linaro.org>
Cc: Marco Felsch <m.felsch@pengutronix.de>
Cc: Marek Vasut <marex@denx.de>
Cc: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Cc: Mathias Kresin <dev@kresin.me>
Cc: Maxim Kochetkov <fido_max@inbox.ru>
Cc: Michael Walle <michael@walle.cc>
Cc: Neil Armstrong <narmstrong@baylibre.com>
Cc: Nisar Sayed <Nisar.Sayed@microchip.com>
Cc: Oleksij Rempel <o.rempel@pengutronix.de>
Cc: Philippe Schenker <philippe.schenker@toradex.com>
Cc: Willy Liu <willy.liu@realtek.com>
Cc: Yuiko Oshino <yuiko.oshino@microchip.com>
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy.c | 6 ++++--
 include/linux/phy.h   | 2 ++
 2 files changed, 6 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 35525a671400..477bdf2f94df 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -493,10 +493,11 @@ EXPORT_SYMBOL(phy_queue_state_machine);
  *
  * @phydev: the phy_device struct
  */
-static void phy_trigger_machine(struct phy_device *phydev)
+void phy_trigger_machine(struct phy_device *phydev)
 {
 	phy_queue_state_machine(phydev, 0);
 }
+EXPORT_SYMBOL(phy_trigger_machine);
 
 static void phy_abort_cable_test(struct phy_device *phydev)
 {
@@ -924,7 +925,7 @@ void phy_stop_machine(struct phy_device *phydev)
  * Must not be called from interrupt context, or while the
  * phydev->lock is held.
  */
-static void phy_error(struct phy_device *phydev)
+void phy_error(struct phy_device *phydev)
 {
 	WARN_ON(1);
 
@@ -934,6 +935,7 @@ static void phy_error(struct phy_device *phydev)
 
 	phy_trigger_machine(phydev);
 }
+EXPORT_SYMBOL(phy_error);
 
 /**
  * phy_disable_interrupts - Disable the PHY interrupts from the PHY side
diff --git a/include/linux/phy.h b/include/linux/phy.h
index eb3cb1a98b45..566b39f6cd64 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1570,8 +1570,10 @@ void phy_drivers_unregister(struct phy_driver *drv, int n);
 int phy_driver_register(struct phy_driver *new_driver, struct module *owner);
 int phy_drivers_register(struct phy_driver *new_driver, int n,
 			 struct module *owner);
+void phy_error(struct phy_device *phydev);
 void phy_state_machine(struct work_struct *work);
 void phy_queue_state_machine(struct phy_device *phydev, unsigned long jiffies);
+void phy_trigger_machine(struct phy_device *phydev);
 void phy_mac_interrupt(struct phy_device *phydev);
 void phy_start_machine(struct phy_device *phydev);
 void phy_stop_machine(struct phy_device *phydev);
-- 
cgit v1.2.3


From 87de1f058aacc8ce4be94e36a38f77b860914a76 Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Sun, 1 Nov 2020 14:51:12 +0200
Subject: net: phy: add genphy_handle_interrupt_no_ack()

It seems there are cases where the interrupts are handled by another
entity (ie an IRQ controller embedded inside the PHY) and do not need
any other interraction from phylib. For this kind of PHYs, like the
RTL8366RB, add the genphy_handle_interrupt_no_ack() function which just
triggers the link state machine.

Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy_device.c | 13 +++++++++++++
 include/linux/phy.h          |  1 +
 2 files changed, 14 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index f54f483d7fd6..e13a46c25437 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -2463,6 +2463,19 @@ int genphy_soft_reset(struct phy_device *phydev)
 }
 EXPORT_SYMBOL(genphy_soft_reset);
 
+irqreturn_t genphy_handle_interrupt_no_ack(struct phy_device *phydev)
+{
+	/* It seems there are cases where the interrupts are handled by another
+	 * entity (ie an IRQ controller embedded inside the PHY) and do not
+	 * need any other interraction from phylib. In this case, just trigger
+	 * the state machine directly.
+	 */
+	phy_trigger_machine(phydev);
+
+	return 0;
+}
+EXPORT_SYMBOL(genphy_handle_interrupt_no_ack);
+
 /**
  * genphy_read_abilities - read PHY abilities from Clause 22 registers
  * @phydev: target phy_device struct
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 566b39f6cd64..4f158d6352ae 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1510,6 +1510,7 @@ int genphy_suspend(struct phy_device *phydev);
 int genphy_resume(struct phy_device *phydev);
 int genphy_loopback(struct phy_device *phydev, bool enable);
 int genphy_soft_reset(struct phy_device *phydev);
+irqreturn_t genphy_handle_interrupt_no_ack(struct phy_device *phydev);
 
 static inline int genphy_config_aneg(struct phy_device *phydev)
 {
-- 
cgit v1.2.3


From d8c4a22363853e196497b06a8ee9be9773873a14 Mon Sep 17 00:00:00 2001
From: Loic Poulain <loic.poulain@linaro.org>
Date: Tue, 3 Nov 2020 18:23:53 +0100
Subject: bus: mhi: Add mhi_queue_is_full function

This function can be used by client driver to determine whether it's
possible to queue new elements in a channel ring.

Signed-off-by: Loic Poulain <loic.poulain@linaro.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/1604424234-24446-1-git-send-email-loic.poulain@linaro.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/bus/mhi/core/main.c | 11 +++++++++++
 include/linux/mhi.h         |  7 +++++++
 2 files changed, 18 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/bus/mhi/core/main.c b/drivers/bus/mhi/core/main.c
index 2cff5ddff225..ba9e721d61b7 100644
--- a/drivers/bus/mhi/core/main.c
+++ b/drivers/bus/mhi/core/main.c
@@ -1165,6 +1165,17 @@ int mhi_queue_buf(struct mhi_device *mhi_dev, enum dma_data_direction dir,
 }
 EXPORT_SYMBOL_GPL(mhi_queue_buf);
 
+bool mhi_queue_is_full(struct mhi_device *mhi_dev, enum dma_data_direction dir)
+{
+	struct mhi_controller *mhi_cntrl = mhi_dev->mhi_cntrl;
+	struct mhi_chan *mhi_chan = (dir == DMA_TO_DEVICE) ?
+					mhi_dev->ul_chan : mhi_dev->dl_chan;
+	struct mhi_ring *tre_ring = &mhi_chan->tre_ring;
+
+	return mhi_is_ring_full(mhi_cntrl, tre_ring);
+}
+EXPORT_SYMBOL_GPL(mhi_queue_is_full);
+
 int mhi_send_cmd(struct mhi_controller *mhi_cntrl,
 		 struct mhi_chan *mhi_chan,
 		 enum mhi_cmd_type cmd)
diff --git a/include/linux/mhi.h b/include/linux/mhi.h
index d4841e5a5f45..b9bb7dff32e2 100644
--- a/include/linux/mhi.h
+++ b/include/linux/mhi.h
@@ -737,4 +737,11 @@ int mhi_queue_buf(struct mhi_device *mhi_dev, enum dma_data_direction dir,
 int mhi_queue_skb(struct mhi_device *mhi_dev, enum dma_data_direction dir,
 		  struct sk_buff *skb, size_t len, enum mhi_flags mflags);
 
+/**
+ * mhi_queue_is_full - Determine whether queueing new elements is possible
+ * @mhi_dev: Device associated with the channels
+ * @dir: DMA direction for the channel
+ */
+bool mhi_queue_is_full(struct mhi_device *mhi_dev, enum dma_data_direction dir);
+
 #endif /* _MHI_H_ */
-- 
cgit v1.2.3


From c1aedf015ebdd0232757a66e2daccf1246bd609c Mon Sep 17 00:00:00 2001
From: Hayes Wang <hayeswang@realtek.com>
Date: Wed, 4 Nov 2020 10:19:22 +0800
Subject: net/usb/r8153_ecm: support ECM mode for RTL8153

Support ECM mode based on cdc_ether with relative mii functions,
when CONFIG_USB_RTL8152 is not set, or the device is not supported
by r8152 driver.

Both r8152 and r8153_ecm would check the return value of
rtl8152_get_version() in porbe(). If rtl8152_get_version()
return none zero value, the r8152 is used for the device
with vendor mode. Otherwise, the r8153_ecm is used for the
device with ECM mode.

Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Link: https://lore.kernel.org/r/1394712342-15778-392-Taiwan-albertk@realtek.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/Makefile    |   2 +-
 drivers/net/usb/r8152.c     |  30 ++------
 drivers/net/usb/r8153_ecm.c | 162 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/usb/r8152.h   |  37 ++++++++++
 4 files changed, 204 insertions(+), 27 deletions(-)
 create mode 100644 drivers/net/usb/r8153_ecm.c
 create mode 100644 include/linux/usb/r8152.h

(limited to 'include/linux')

diff --git a/drivers/net/usb/Makefile b/drivers/net/usb/Makefile
index 99fd12be2111..99381e6bea78 100644
--- a/drivers/net/usb/Makefile
+++ b/drivers/net/usb/Makefile
@@ -13,7 +13,7 @@ obj-$(CONFIG_USB_LAN78XX)	+= lan78xx.o
 obj-$(CONFIG_USB_NET_AX8817X)	+= asix.o
 asix-y := asix_devices.o asix_common.o ax88172a.o
 obj-$(CONFIG_USB_NET_AX88179_178A)      += ax88179_178a.o
-obj-$(CONFIG_USB_NET_CDCETHER)	+= cdc_ether.o
+obj-$(CONFIG_USB_NET_CDCETHER)	+= cdc_ether.o r8153_ecm.o
 obj-$(CONFIG_USB_NET_CDC_EEM)	+= cdc_eem.o
 obj-$(CONFIG_USB_NET_DM9601)	+= dm9601.o
 obj-$(CONFIG_USB_NET_SR9700)	+= sr9700.o
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index b9b3d19a2e98..c448d6089821 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -26,6 +26,7 @@
 #include <linux/acpi.h>
 #include <linux/firmware.h>
 #include <crypto/hash.h>
+#include <linux/usb/r8152.h>
 
 /* Information for net-next */
 #define NETNEXT_VERSION		"11"
@@ -653,18 +654,6 @@ enum rtl_register_content {
 
 #define INTR_LINK		0x0004
 
-#define RTL8152_REQT_READ	0xc0
-#define RTL8152_REQT_WRITE	0x40
-#define RTL8152_REQ_GET_REGS	0x05
-#define RTL8152_REQ_SET_REGS	0x05
-
-#define BYTE_EN_DWORD		0xff
-#define BYTE_EN_WORD		0x33
-#define BYTE_EN_BYTE		0x11
-#define BYTE_EN_SIX_BYTES	0x3f
-#define BYTE_EN_START_MASK	0x0f
-#define BYTE_EN_END_MASK	0xf0
-
 #define RTL8153_MAX_PACKET	9216 /* 9K */
 #define RTL8153_MAX_MTU		(RTL8153_MAX_PACKET - VLAN_ETH_HLEN - \
 				 ETH_FCS_LEN)
@@ -689,21 +678,9 @@ enum rtl8152_flags {
 	LENOVO_MACPASSTHRU,
 };
 
-/* Define these values to match your device */
-#define VENDOR_ID_REALTEK		0x0bda
-#define VENDOR_ID_MICROSOFT		0x045e
-#define VENDOR_ID_SAMSUNG		0x04e8
-#define VENDOR_ID_LENOVO		0x17ef
-#define VENDOR_ID_LINKSYS		0x13b1
-#define VENDOR_ID_NVIDIA		0x0955
-#define VENDOR_ID_TPLINK		0x2357
-
 #define DEVICE_ID_THINKPAD_THUNDERBOLT3_DOCK_GEN2	0x3082
 #define DEVICE_ID_THINKPAD_USB_C_DOCK_GEN2		0xa387
 
-#define MCU_TYPE_PLA			0x0100
-#define MCU_TYPE_USB			0x0000
-
 struct tally_counter {
 	__le64	tx_packets;
 	__le64	rx_packets;
@@ -6621,7 +6598,7 @@ static int rtl_fw_init(struct r8152 *tp)
 	return 0;
 }
 
-static u8 rtl_get_version(struct usb_interface *intf)
+u8 rtl8152_get_version(struct usb_interface *intf)
 {
 	struct usb_device *udev = interface_to_usbdev(intf);
 	u32 ocp_data = 0;
@@ -6679,12 +6656,13 @@ static u8 rtl_get_version(struct usb_interface *intf)
 
 	return version;
 }
+EXPORT_SYMBOL_GPL(rtl8152_get_version);
 
 static int rtl8152_probe(struct usb_interface *intf,
 			 const struct usb_device_id *id)
 {
 	struct usb_device *udev = interface_to_usbdev(intf);
-	u8 version = rtl_get_version(intf);
+	u8 version = rtl8152_get_version(intf);
 	struct r8152 *tp;
 	struct net_device *netdev;
 	int ret;
diff --git a/drivers/net/usb/r8153_ecm.c b/drivers/net/usb/r8153_ecm.c
new file mode 100644
index 000000000000..2c3fabd38b16
--- /dev/null
+++ b/drivers/net/usb/r8153_ecm.c
@@ -0,0 +1,162 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/mii.h>
+#include <linux/usb.h>
+#include <linux/usb/cdc.h>
+#include <linux/usb/usbnet.h>
+#include <linux/usb/r8152.h>
+
+#define OCP_BASE		0xe86c
+
+static int pla_read_word(struct usbnet *dev, u16 index)
+{
+	u16 byen = BYTE_EN_WORD;
+	u8 shift = index & 2;
+	__le32 tmp;
+	int ret;
+
+	if (shift)
+		byen <<= shift;
+
+	index &= ~3;
+
+	ret = usbnet_read_cmd(dev, RTL8152_REQ_GET_REGS, RTL8152_REQT_READ, index,
+			      MCU_TYPE_PLA | byen, &tmp, sizeof(tmp));
+	if (ret < 0)
+		goto out;
+
+	ret = __le32_to_cpu(tmp);
+	ret >>= (shift * 8);
+	ret &= 0xffff;
+
+out:
+	return ret;
+}
+
+static int pla_write_word(struct usbnet *dev, u16 index, u32 data)
+{
+	u32 mask = 0xffff;
+	u16 byen = BYTE_EN_WORD;
+	u8 shift = index & 2;
+	__le32 tmp;
+	int ret;
+
+	data &= mask;
+
+	if (shift) {
+		byen <<= shift;
+		mask <<= (shift * 8);
+		data <<= (shift * 8);
+	}
+
+	index &= ~3;
+
+	ret = usbnet_read_cmd(dev, RTL8152_REQ_GET_REGS, RTL8152_REQT_READ, index,
+			      MCU_TYPE_PLA | byen, &tmp, sizeof(tmp));
+
+	if (ret < 0)
+		goto out;
+
+	data |= __le32_to_cpu(tmp) & ~mask;
+	tmp = __cpu_to_le32(data);
+
+	ret = usbnet_write_cmd(dev, RTL8152_REQ_SET_REGS, RTL8152_REQT_WRITE, index,
+			       MCU_TYPE_PLA | byen, &tmp, sizeof(tmp));
+
+out:
+	return ret;
+}
+
+static int r8153_ecm_mdio_read(struct net_device *netdev, int phy_id, int reg)
+{
+	struct usbnet *dev = netdev_priv(netdev);
+	int ret;
+
+	ret = pla_write_word(dev, OCP_BASE, 0xa000);
+	if (ret < 0)
+		goto out;
+
+	ret = pla_read_word(dev, 0xb400 + reg * 2);
+
+out:
+	return ret;
+}
+
+static void r8153_ecm_mdio_write(struct net_device *netdev, int phy_id, int reg, int val)
+{
+	struct usbnet *dev = netdev_priv(netdev);
+	int ret;
+
+	ret = pla_write_word(dev, OCP_BASE, 0xa000);
+	if (ret < 0)
+		return;
+
+	ret = pla_write_word(dev, 0xb400 + reg * 2, val);
+}
+
+static int r8153_bind(struct usbnet *dev, struct usb_interface *intf)
+{
+	int status;
+
+	status = usbnet_cdc_bind(dev, intf);
+	if (status < 0)
+		return status;
+
+	dev->mii.dev = dev->net;
+	dev->mii.mdio_read = r8153_ecm_mdio_read;
+	dev->mii.mdio_write = r8153_ecm_mdio_write;
+	dev->mii.reg_num_mask = 0x1f;
+	dev->mii.supports_gmii = 1;
+
+	return status;
+}
+
+static const struct driver_info r8153_info = {
+	.description =	"RTL8153 ECM Device",
+	.flags =	FLAG_ETHER,
+	.bind =		r8153_bind,
+	.unbind =	usbnet_cdc_unbind,
+	.status =	usbnet_cdc_status,
+	.manage_power =	usbnet_manage_power,
+};
+
+static const struct usb_device_id products[] = {
+{
+	USB_DEVICE_AND_INTERFACE_INFO(VENDOR_ID_REALTEK, 0x8153, USB_CLASS_COMM,
+				      USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+	.driver_info = (unsigned long)&r8153_info,
+},
+
+	{ },		/* END */
+};
+MODULE_DEVICE_TABLE(usb, products);
+
+static int rtl8153_ecm_probe(struct usb_interface *intf,
+			     const struct usb_device_id *id)
+{
+#if IS_REACHABLE(CONFIG_USB_RTL8152)
+	if (rtl8152_get_version(intf))
+		return -ENODEV;
+#endif
+
+	return usbnet_probe(intf, id);
+}
+
+static struct usb_driver r8153_ecm_driver = {
+	.name =		"r8153_ecm",
+	.id_table =	products,
+	.probe =	rtl8153_ecm_probe,
+	.disconnect =	usbnet_disconnect,
+	.suspend =	usbnet_suspend,
+	.resume =	usbnet_resume,
+	.reset_resume =	usbnet_resume,
+	.supports_autosuspend = 1,
+	.disable_hub_initiated_lpm = 1,
+};
+
+module_usb_driver(r8153_ecm_driver);
+
+MODULE_AUTHOR("Hayes Wang");
+MODULE_DESCRIPTION("Realtek USB ECM device");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/usb/r8152.h b/include/linux/usb/r8152.h
new file mode 100644
index 000000000000..20d88b1defc3
--- /dev/null
+++ b/include/linux/usb/r8152.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *  Copyright (c) 2020 Realtek Semiconductor Corp. All rights reserved.
+ */
+
+#ifndef	__LINUX_R8152_H
+#define __LINUX_R8152_H
+
+#define RTL8152_REQT_READ		0xc0
+#define RTL8152_REQT_WRITE		0x40
+#define RTL8152_REQ_GET_REGS		0x05
+#define RTL8152_REQ_SET_REGS		0x05
+
+#define BYTE_EN_DWORD			0xff
+#define BYTE_EN_WORD			0x33
+#define BYTE_EN_BYTE			0x11
+#define BYTE_EN_SIX_BYTES		0x3f
+#define BYTE_EN_START_MASK		0x0f
+#define BYTE_EN_END_MASK		0xf0
+
+#define MCU_TYPE_PLA			0x0100
+#define MCU_TYPE_USB			0x0000
+
+/* Define these values to match your device */
+#define VENDOR_ID_REALTEK		0x0bda
+#define VENDOR_ID_MICROSOFT		0x045e
+#define VENDOR_ID_SAMSUNG		0x04e8
+#define VENDOR_ID_LENOVO		0x17ef
+#define VENDOR_ID_LINKSYS		0x13b1
+#define VENDOR_ID_NVIDIA		0x0955
+#define VENDOR_ID_TPLINK		0x2357
+
+#if IS_REACHABLE(CONFIG_USB_RTL8152)
+extern u8 rtl8152_get_version(struct usb_interface *intf);
+#endif
+
+#endif /* __LINUX_R8152_H */
-- 
cgit v1.2.3


From 8280c07e0762ba753876c427584a792e86f3f7e7 Mon Sep 17 00:00:00 2001
From: Kurt Lee <kurt.lee@cypress.com>
Date: Mon, 12 Oct 2020 03:43:46 -0500
Subject: ieee80211: Add definition for WFA DPP

Add Wi-Fi Alliance definition for DPP (Device Provisioning Protocol).

Signed-off-by: Kurt Lee <kurt.lee@cypress.com>
Signed-off-by: Wright Feng <wright.feng@cypress.com>
Link: https://lore.kernel.org/r/20201012084347.121557-2-wright.feng@cypress.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 770408b2fdaf..5e8cc9c3d45a 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -3417,6 +3417,8 @@ struct ieee80211_multiple_bssid_configuration {
 #define WLAN_AKM_SUITE_FT_PSK_SHA384		SUITE(0x000FAC, 19)
 #define WLAN_AKM_SUITE_PSK_SHA384		SUITE(0x000FAC, 20)
 
+#define WLAN_AKM_SUITE_WFA_DPP			SUITE(WLAN_OUI_WFA, 2)
+
 #define WLAN_MAX_KEY_LEN		32
 
 #define WLAN_PMK_NAME_LEN		16
@@ -3427,6 +3429,7 @@ struct ieee80211_multiple_bssid_configuration {
 
 #define WLAN_OUI_WFA			0x506f9a
 #define WLAN_OUI_TYPE_WFA_P2P		9
+#define WLAN_OUI_TYPE_WFA_DPP		0x1A
 #define WLAN_OUI_MICROSOFT		0x0050f2
 #define WLAN_OUI_TYPE_MICROSOFT_WPA	1
 #define WLAN_OUI_TYPE_MICROSOFT_WMM	2
-- 
cgit v1.2.3


From aec51036a166a0aecc26cba101bfbbdc53d64139 Mon Sep 17 00:00:00 2001
From: Lee Jones <lee.jones@linaro.org>
Date: Wed, 4 Nov 2020 19:35:17 +0000
Subject: tty: tty_io: Move 'tty_sysctl_init's prototype to shared space
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fixes the following W=1 kernel build warning(s):

 drivers/tty/tty_ldisc.c:883:6: warning: no previous prototype for ‘tty_sysctl_init’ [-Wmissing-prototypes]
 883 | void tty_sysctl_init(void)
 | ^~~~~~~~~~~~~~~

Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jiri Slaby <jirislaby@kernel.org>
Cc: Nick Holloway <alfie@dcs.warwick.ac.uk>
Cc: -- <julian@uhunix.uhcc.hawaii.edu>
Cc: Marko Kohtala <Marko.Kohtala@hut.fi>
Cc: Bill Hawes <whawes@star.net>
Cc: "C. Scott Ananian" <cananian@alumni.princeton.edu>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: Andrew Morton <andrewm@uow.edu.eu>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
Link: https://lore.kernel.org/r/20201104193549.4026187-5-lee.jones@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/tty_io.c | 2 --
 include/linux/tty.h  | 1 +
 2 files changed, 1 insertion(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 7a4c02548fb3..88b00c47b606 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -514,8 +514,6 @@ static const struct file_operations hung_up_tty_fops = {
 static DEFINE_SPINLOCK(redirect_lock);
 static struct file *redirect;
 
-extern void tty_sysctl_init(void);
-
 /**
  *	tty_wakeup	-	request more data
  *	@tty: terminal
diff --git a/include/linux/tty.h b/include/linux/tty.h
index a99e9b8e4e31..10212c6e4345 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -716,6 +716,7 @@ extern int __must_check tty_ldisc_init(struct tty_struct *tty);
 extern void tty_ldisc_deinit(struct tty_struct *tty);
 extern int tty_ldisc_receive_buf(struct tty_ldisc *ld, const unsigned char *p,
 				 char *f, int count);
+extern void tty_sysctl_init(void);
 
 /* n_tty.c */
 extern void n_tty_inherit_ops(struct tty_ldisc_ops *ops);
-- 
cgit v1.2.3


From 0264c8c9e1b53e9dbb41fae5e54756e84644bc60 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Thu, 5 Nov 2020 21:32:36 -0500
Subject: ftrace: Move the recursion testing into global headers

Currently, if a callback is registered to a ftrace function and its
ftrace_ops does not have the RECURSION flag set, it is encapsulated in a
helper function that does the recursion for it.

Really, all the callbacks should have their own recursion protection for
performance reasons. But they should not all implement their own. Move the
recursion helpers to global headers, so that all callbacks can use them.

Link: https://lkml.kernel.org/r/20201028115612.460535535@goodmis.org
Link: https://lkml.kernel.org/r/20201106023546.166456258@goodmis.org

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/ftrace.h          |   1 +
 include/linux/trace_recursion.h | 187 ++++++++++++++++++++++++++++++++++++++++
 kernel/trace/trace.h            | 177 -------------------------------------
 3 files changed, 188 insertions(+), 177 deletions(-)
 create mode 100644 include/linux/trace_recursion.h

(limited to 'include/linux')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 1bd3a0356ae4..0e4164a7f56d 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -7,6 +7,7 @@
 #ifndef _LINUX_FTRACE_H
 #define _LINUX_FTRACE_H
 
+#include <linux/trace_recursion.h>
 #include <linux/trace_clock.h>
 #include <linux/kallsyms.h>
 #include <linux/linkage.h>
diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h
new file mode 100644
index 000000000000..dbb7b6d4c94c
--- /dev/null
+++ b/include/linux/trace_recursion.h
@@ -0,0 +1,187 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_TRACE_RECURSION_H
+#define _LINUX_TRACE_RECURSION_H
+
+#include <linux/interrupt.h>
+#include <linux/sched.h>
+
+#ifdef CONFIG_TRACING
+
+/* Only current can touch trace_recursion */
+
+/*
+ * For function tracing recursion:
+ *  The order of these bits are important.
+ *
+ *  When function tracing occurs, the following steps are made:
+ *   If arch does not support a ftrace feature:
+ *    call internal function (uses INTERNAL bits) which calls...
+ *   If callback is registered to the "global" list, the list
+ *    function is called and recursion checks the GLOBAL bits.
+ *    then this function calls...
+ *   The function callback, which can use the FTRACE bits to
+ *    check for recursion.
+ *
+ * Now if the arch does not support a feature, and it calls
+ * the global list function which calls the ftrace callback
+ * all three of these steps will do a recursion protection.
+ * There's no reason to do one if the previous caller already
+ * did. The recursion that we are protecting against will
+ * go through the same steps again.
+ *
+ * To prevent the multiple recursion checks, if a recursion
+ * bit is set that is higher than the MAX bit of the current
+ * check, then we know that the check was made by the previous
+ * caller, and we can skip the current check.
+ */
+enum {
+	/* Function recursion bits */
+	TRACE_FTRACE_BIT,
+	TRACE_FTRACE_NMI_BIT,
+	TRACE_FTRACE_IRQ_BIT,
+	TRACE_FTRACE_SIRQ_BIT,
+
+	/* INTERNAL_BITs must be greater than FTRACE_BITs */
+	TRACE_INTERNAL_BIT,
+	TRACE_INTERNAL_NMI_BIT,
+	TRACE_INTERNAL_IRQ_BIT,
+	TRACE_INTERNAL_SIRQ_BIT,
+
+	TRACE_BRANCH_BIT,
+/*
+ * Abuse of the trace_recursion.
+ * As we need a way to maintain state if we are tracing the function
+ * graph in irq because we want to trace a particular function that
+ * was called in irq context but we have irq tracing off. Since this
+ * can only be modified by current, we can reuse trace_recursion.
+ */
+	TRACE_IRQ_BIT,
+
+	/* Set if the function is in the set_graph_function file */
+	TRACE_GRAPH_BIT,
+
+	/*
+	 * In the very unlikely case that an interrupt came in
+	 * at a start of graph tracing, and we want to trace
+	 * the function in that interrupt, the depth can be greater
+	 * than zero, because of the preempted start of a previous
+	 * trace. In an even more unlikely case, depth could be 2
+	 * if a softirq interrupted the start of graph tracing,
+	 * followed by an interrupt preempting a start of graph
+	 * tracing in the softirq, and depth can even be 3
+	 * if an NMI came in at the start of an interrupt function
+	 * that preempted a softirq start of a function that
+	 * preempted normal context!!!! Luckily, it can't be
+	 * greater than 3, so the next two bits are a mask
+	 * of what the depth is when we set TRACE_GRAPH_BIT
+	 */
+
+	TRACE_GRAPH_DEPTH_START_BIT,
+	TRACE_GRAPH_DEPTH_END_BIT,
+
+	/*
+	 * To implement set_graph_notrace, if this bit is set, we ignore
+	 * function graph tracing of called functions, until the return
+	 * function is called to clear it.
+	 */
+	TRACE_GRAPH_NOTRACE_BIT,
+
+	/*
+	 * When transitioning between context, the preempt_count() may
+	 * not be correct. Allow for a single recursion to cover this case.
+	 */
+	TRACE_TRANSITION_BIT,
+};
+
+#define trace_recursion_set(bit)	do { (current)->trace_recursion |= (1<<(bit)); } while (0)
+#define trace_recursion_clear(bit)	do { (current)->trace_recursion &= ~(1<<(bit)); } while (0)
+#define trace_recursion_test(bit)	((current)->trace_recursion & (1<<(bit)))
+
+#define trace_recursion_depth() \
+	(((current)->trace_recursion >> TRACE_GRAPH_DEPTH_START_BIT) & 3)
+#define trace_recursion_set_depth(depth) \
+	do {								\
+		current->trace_recursion &=				\
+			~(3 << TRACE_GRAPH_DEPTH_START_BIT);		\
+		current->trace_recursion |=				\
+			((depth) & 3) << TRACE_GRAPH_DEPTH_START_BIT;	\
+	} while (0)
+
+#define TRACE_CONTEXT_BITS	4
+
+#define TRACE_FTRACE_START	TRACE_FTRACE_BIT
+#define TRACE_FTRACE_MAX	((1 << (TRACE_FTRACE_START + TRACE_CONTEXT_BITS)) - 1)
+
+#define TRACE_LIST_START	TRACE_INTERNAL_BIT
+#define TRACE_LIST_MAX		((1 << (TRACE_LIST_START + TRACE_CONTEXT_BITS)) - 1)
+
+#define TRACE_CONTEXT_MASK	TRACE_LIST_MAX
+
+static __always_inline int trace_get_context_bit(void)
+{
+	int bit;
+
+	if (in_interrupt()) {
+		if (in_nmi())
+			bit = 0;
+
+		else if (in_irq())
+			bit = 1;
+		else
+			bit = 2;
+	} else
+		bit = 3;
+
+	return bit;
+}
+
+static __always_inline int trace_test_and_set_recursion(int start, int max)
+{
+	unsigned int val = current->trace_recursion;
+	int bit;
+
+	/* A previous recursion check was made */
+	if ((val & TRACE_CONTEXT_MASK) > max)
+		return 0;
+
+	bit = trace_get_context_bit() + start;
+	if (unlikely(val & (1 << bit))) {
+		/*
+		 * It could be that preempt_count has not been updated during
+		 * a switch between contexts. Allow for a single recursion.
+		 */
+		bit = TRACE_TRANSITION_BIT;
+		if (trace_recursion_test(bit))
+			return -1;
+		trace_recursion_set(bit);
+		barrier();
+		return bit + 1;
+	}
+
+	/* Normal check passed, clear the transition to allow it again */
+	trace_recursion_clear(TRACE_TRANSITION_BIT);
+
+	val |= 1 << bit;
+	current->trace_recursion = val;
+	barrier();
+
+	return bit + 1;
+}
+
+static __always_inline void trace_clear_recursion(int bit)
+{
+	unsigned int val = current->trace_recursion;
+
+	if (!bit)
+		return;
+
+	bit--;
+	bit = 1 << bit;
+	val &= ~bit;
+
+	barrier();
+	current->trace_recursion = val;
+}
+
+#endif /* CONFIG_TRACING */
+#endif /* _LINUX_TRACE_RECURSION_H */
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 1dadef445cd1..9462251cab92 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -558,183 +558,6 @@ struct tracer {
 	bool			noboot;
 };
 
-
-/* Only current can touch trace_recursion */
-
-/*
- * For function tracing recursion:
- *  The order of these bits are important.
- *
- *  When function tracing occurs, the following steps are made:
- *   If arch does not support a ftrace feature:
- *    call internal function (uses INTERNAL bits) which calls...
- *   If callback is registered to the "global" list, the list
- *    function is called and recursion checks the GLOBAL bits.
- *    then this function calls...
- *   The function callback, which can use the FTRACE bits to
- *    check for recursion.
- *
- * Now if the arch does not support a feature, and it calls
- * the global list function which calls the ftrace callback
- * all three of these steps will do a recursion protection.
- * There's no reason to do one if the previous caller already
- * did. The recursion that we are protecting against will
- * go through the same steps again.
- *
- * To prevent the multiple recursion checks, if a recursion
- * bit is set that is higher than the MAX bit of the current
- * check, then we know that the check was made by the previous
- * caller, and we can skip the current check.
- */
-enum {
-	/* Function recursion bits */
-	TRACE_FTRACE_BIT,
-	TRACE_FTRACE_NMI_BIT,
-	TRACE_FTRACE_IRQ_BIT,
-	TRACE_FTRACE_SIRQ_BIT,
-
-	/* INTERNAL_BITs must be greater than FTRACE_BITs */
-	TRACE_INTERNAL_BIT,
-	TRACE_INTERNAL_NMI_BIT,
-	TRACE_INTERNAL_IRQ_BIT,
-	TRACE_INTERNAL_SIRQ_BIT,
-
-	TRACE_BRANCH_BIT,
-/*
- * Abuse of the trace_recursion.
- * As we need a way to maintain state if we are tracing the function
- * graph in irq because we want to trace a particular function that
- * was called in irq context but we have irq tracing off. Since this
- * can only be modified by current, we can reuse trace_recursion.
- */
-	TRACE_IRQ_BIT,
-
-	/* Set if the function is in the set_graph_function file */
-	TRACE_GRAPH_BIT,
-
-	/*
-	 * In the very unlikely case that an interrupt came in
-	 * at a start of graph tracing, and we want to trace
-	 * the function in that interrupt, the depth can be greater
-	 * than zero, because of the preempted start of a previous
-	 * trace. In an even more unlikely case, depth could be 2
-	 * if a softirq interrupted the start of graph tracing,
-	 * followed by an interrupt preempting a start of graph
-	 * tracing in the softirq, and depth can even be 3
-	 * if an NMI came in at the start of an interrupt function
-	 * that preempted a softirq start of a function that
-	 * preempted normal context!!!! Luckily, it can't be
-	 * greater than 3, so the next two bits are a mask
-	 * of what the depth is when we set TRACE_GRAPH_BIT
-	 */
-
-	TRACE_GRAPH_DEPTH_START_BIT,
-	TRACE_GRAPH_DEPTH_END_BIT,
-
-	/*
-	 * To implement set_graph_notrace, if this bit is set, we ignore
-	 * function graph tracing of called functions, until the return
-	 * function is called to clear it.
-	 */
-	TRACE_GRAPH_NOTRACE_BIT,
-
-	/*
-	 * When transitioning between context, the preempt_count() may
-	 * not be correct. Allow for a single recursion to cover this case.
-	 */
-	TRACE_TRANSITION_BIT,
-};
-
-#define trace_recursion_set(bit)	do { (current)->trace_recursion |= (1<<(bit)); } while (0)
-#define trace_recursion_clear(bit)	do { (current)->trace_recursion &= ~(1<<(bit)); } while (0)
-#define trace_recursion_test(bit)	((current)->trace_recursion & (1<<(bit)))
-
-#define trace_recursion_depth() \
-	(((current)->trace_recursion >> TRACE_GRAPH_DEPTH_START_BIT) & 3)
-#define trace_recursion_set_depth(depth) \
-	do {								\
-		current->trace_recursion &=				\
-			~(3 << TRACE_GRAPH_DEPTH_START_BIT);		\
-		current->trace_recursion |=				\
-			((depth) & 3) << TRACE_GRAPH_DEPTH_START_BIT;	\
-	} while (0)
-
-#define TRACE_CONTEXT_BITS	4
-
-#define TRACE_FTRACE_START	TRACE_FTRACE_BIT
-#define TRACE_FTRACE_MAX	((1 << (TRACE_FTRACE_START + TRACE_CONTEXT_BITS)) - 1)
-
-#define TRACE_LIST_START	TRACE_INTERNAL_BIT
-#define TRACE_LIST_MAX		((1 << (TRACE_LIST_START + TRACE_CONTEXT_BITS)) - 1)
-
-#define TRACE_CONTEXT_MASK	TRACE_LIST_MAX
-
-static __always_inline int trace_get_context_bit(void)
-{
-	int bit;
-
-	if (in_interrupt()) {
-		if (in_nmi())
-			bit = 0;
-
-		else if (in_irq())
-			bit = 1;
-		else
-			bit = 2;
-	} else
-		bit = 3;
-
-	return bit;
-}
-
-static __always_inline int trace_test_and_set_recursion(int start, int max)
-{
-	unsigned int val = current->trace_recursion;
-	int bit;
-
-	/* A previous recursion check was made */
-	if ((val & TRACE_CONTEXT_MASK) > max)
-		return 0;
-
-	bit = trace_get_context_bit() + start;
-	if (unlikely(val & (1 << bit))) {
-		/*
-		 * It could be that preempt_count has not been updated during
-		 * a switch between contexts. Allow for a single recursion.
-		 */
-		bit = TRACE_TRANSITION_BIT;
-		if (trace_recursion_test(bit))
-			return -1;
-		trace_recursion_set(bit);
-		barrier();
-		return bit + 1;
-	}
-
-	/* Normal check passed, clear the transition to allow it again */
-	trace_recursion_clear(TRACE_TRANSITION_BIT);
-
-	val |= 1 << bit;
-	current->trace_recursion = val;
-	barrier();
-
-	return bit + 1;
-}
-
-static __always_inline void trace_clear_recursion(int bit)
-{
-	unsigned int val = current->trace_recursion;
-
-	if (!bit)
-		return;
-
-	bit--;
-	bit = 1 << bit;
-	val &= ~bit;
-
-	barrier();
-	current->trace_recursion = val;
-}
-
 static inline struct ring_buffer_iter *
 trace_buffer_iter(struct trace_iterator *iter, int cpu)
 {
-- 
cgit v1.2.3


From 6e4eb9cb22fc8a893cb708ed42644de5ee7c3827 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Thu, 5 Nov 2020 21:32:37 -0500
Subject: ftrace: Add ftrace_test_recursion_trylock() helper function

To make it easier for ftrace callbacks to have recursion protection, provide
a ftrace_test_recursion_trylock() and ftrace_test_recursion_unlock() helper
that tests for recursion.

Link: https://lkml.kernel.org/r/20201028115612.634927593@goodmis.org
Link: https://lkml.kernel.org/r/20201106023546.378584067@goodmis.org

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/trace_recursion.h | 25 +++++++++++++++++++++++++
 kernel/trace/trace_functions.c  | 12 +++++-------
 2 files changed, 30 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h
index dbb7b6d4c94c..f2a949dbfec7 100644
--- a/include/linux/trace_recursion.h
+++ b/include/linux/trace_recursion.h
@@ -183,5 +183,30 @@ static __always_inline void trace_clear_recursion(int bit)
 	current->trace_recursion = val;
 }
 
+/**
+ * ftrace_test_recursion_trylock - tests for recursion in same context
+ *
+ * Use this for ftrace callbacks. This will detect if the function
+ * tracing recursed in the same context (normal vs interrupt),
+ *
+ * Returns: -1 if a recursion happened.
+ *           >= 0 if no recursion
+ */
+static __always_inline int ftrace_test_recursion_trylock(void)
+{
+	return trace_test_and_set_recursion(TRACE_FTRACE_START, TRACE_FTRACE_MAX);
+}
+
+/**
+ * ftrace_test_recursion_unlock - called when function callback is complete
+ * @bit: The return of a successful ftrace_test_recursion_trylock()
+ *
+ * This is used at the end of a ftrace callback.
+ */
+static __always_inline void ftrace_test_recursion_unlock(int bit)
+{
+	trace_clear_recursion(bit);
+}
+
 #endif /* CONFIG_TRACING */
 #endif /* _LINUX_TRACE_RECURSION_H */
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 2c2126e1871d..943756c01190 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -141,22 +141,20 @@ function_trace_call(unsigned long ip, unsigned long parent_ip,
 	if (unlikely(!tr->function_enabled))
 		return;
 
+	bit = ftrace_test_recursion_trylock();
+	if (bit < 0)
+		return;
+
 	pc = preempt_count();
 	preempt_disable_notrace();
 
-	bit = trace_test_and_set_recursion(TRACE_FTRACE_START, TRACE_FTRACE_MAX);
-	if (bit < 0)
-		goto out;
-
 	cpu = smp_processor_id();
 	data = per_cpu_ptr(tr->array_buffer.data, cpu);
 	if (!atomic_read(&data->disabled)) {
 		local_save_flags(flags);
 		trace_function(tr, ip, parent_ip, flags, pc);
 	}
-	trace_clear_recursion(bit);
-
- out:
+	ftrace_test_recursion_unlock(bit);
 	preempt_enable_notrace();
 }
 
-- 
cgit v1.2.3


From da5afbeb1724609996ca7bb4fbce2cd104c95914 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Thu, 5 Nov 2020 21:32:38 -0500
Subject: ftrace: Optimize testing what context current is in

The preempt_count() is not a simple location in memory, it could be part of
per_cpu code or more. Each access to preempt_count(), or one of its accessor
functions (like in_interrupt()) takes several cycles. By reading
preempt_count() once, and then doing tests to find the context against the
value return is slightly faster than using in_nmi() and in_interrupt().

Link: https://lkml.kernel.org/r/20201028115612.780796355@goodmis.org
Link: https://lkml.kernel.org/r/20201106023546.558881845@goodmis.org

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/trace_recursion.h | 33 ++++++++++++++++++++-------------
 1 file changed, 20 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h
index f2a949dbfec7..ac3d73484cb2 100644
--- a/include/linux/trace_recursion.h
+++ b/include/linux/trace_recursion.h
@@ -117,22 +117,29 @@ enum {
 
 #define TRACE_CONTEXT_MASK	TRACE_LIST_MAX
 
+/*
+ * Used for setting context
+ *  NMI     = 0
+ *  IRQ     = 1
+ *  SOFTIRQ = 2
+ *  NORMAL  = 3
+ */
+enum {
+	TRACE_CTX_NMI,
+	TRACE_CTX_IRQ,
+	TRACE_CTX_SOFTIRQ,
+	TRACE_CTX_NORMAL,
+};
+
 static __always_inline int trace_get_context_bit(void)
 {
-	int bit;
-
-	if (in_interrupt()) {
-		if (in_nmi())
-			bit = 0;
-
-		else if (in_irq())
-			bit = 1;
-		else
-			bit = 2;
-	} else
-		bit = 3;
+	unsigned long pc = preempt_count();
 
-	return bit;
+	if (!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET)))
+		return TRACE_CTX_NORMAL;
+	else
+		return pc & NMI_MASK ? TRACE_CTX_NMI :
+			pc & HARDIRQ_MASK ? TRACE_CTX_IRQ : TRACE_CTX_SOFTIRQ;
 }
 
 static __always_inline int trace_test_and_set_recursion(int start, int max)
-- 
cgit v1.2.3


From a25d036d939a30623ff73ecad9c8b9116b02e823 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Thu, 5 Nov 2020 21:32:45 -0500
Subject: ftrace: Reverse what the RECURSION flag means in the ftrace_ops

Now that all callbacks are recursion safe, reverse the meaning of the
RECURSION flag and rename it from RECURSION_SAFE to simply RECURSION.
Now only callbacks that request to have recursion protecting it will
have the added trampoline to do so.

Also remove the outdated comment about "PER_CPU" when determining to
use the ftrace_ops_assist_func.

Link: https://lkml.kernel.org/r/20201028115613.742454631@goodmis.org
Link: https://lkml.kernel.org/r/20201106023547.904270143@goodmis.org

Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Josh  Poimboeuf <jpoimboe@redhat.com>
Cc: Jiri Kosina <jikos@kernel.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Miroslav Benes <mbenes@suse.cz>
Cc: Kamalesh Babulal <kamalesh@linux.vnet.ibm.com>
Cc: Petr Mladek <pmladek@suse.com>
Cc: linux-doc@vger.kernel.org
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 Documentation/trace/ftrace-uses.rst | 82 +++++++++++++++++++++++++++----------
 include/linux/ftrace.h              | 12 +++---
 kernel/trace/fgraph.c               |  3 +-
 kernel/trace/ftrace.c               | 20 ++++-----
 kernel/trace/trace_events.c         |  1 -
 kernel/trace/trace_functions.c      |  2 +-
 kernel/trace/trace_selftest.c       |  7 +---
 kernel/trace/trace_stack.c          |  1 -
 8 files changed, 79 insertions(+), 49 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/trace/ftrace-uses.rst b/Documentation/trace/ftrace-uses.rst
index a4955f7e3d19..86cd14b8e126 100644
--- a/Documentation/trace/ftrace-uses.rst
+++ b/Documentation/trace/ftrace-uses.rst
@@ -30,8 +30,8 @@ The ftrace context
   This requires extra care to what can be done inside a callback. A callback
   can be called outside the protective scope of RCU.
 
-The ftrace infrastructure has some protections against recursions and RCU
-but one must still be very careful how they use the callbacks.
+There are helper functions to help against recursion, and making sure
+RCU is watching. These are explained below.
 
 
 The ftrace_ops structure
@@ -108,6 +108,50 @@ The prototype of the callback function is as follows (as of v4.14):
 	at the start of the function where ftrace was tracing. Otherwise it
 	either contains garbage, or NULL.
 
+Protect your callback
+=====================
+
+As functions can be called from anywhere, and it is possible that a function
+called by a callback may also be traced, and call that same callback,
+recursion protection must be used. There are two helper functions that
+can help in this regard. If you start your code with:
+
+	int bit;
+
+	bit = ftrace_test_recursion_trylock();
+	if (bit < 0)
+		return;
+
+and end it with:
+
+	ftrace_test_recursion_unlock(bit);
+
+The code in between will be safe to use, even if it ends up calling a
+function that the callback is tracing. Note, on success,
+ftrace_test_recursion_trylock() will disable preemption, and the
+ftrace_test_recursion_unlock() will enable it again (if it was previously
+enabled).
+
+Alternatively, if the FTRACE_OPS_FL_RECURSION flag is set on the ftrace_ops
+(as explained below), then a helper trampoline will be used to test
+for recursion for the callback and no recursion test needs to be done.
+But this is at the expense of a slightly more overhead from an extra
+function call.
+
+If your callback accesses any data or critical section that requires RCU
+protection, it is best to make sure that RCU is "watching", otherwise
+that data or critical section will not be protected as expected. In this
+case add:
+
+	if (!rcu_is_watching())
+		return;
+
+Alternatively, if the FTRACE_OPS_FL_RCU flag is set on the ftrace_ops
+(as explained below), then a helper trampoline will be used to test
+for rcu_is_watching for the callback and no other test needs to be done.
+But this is at the expense of a slightly more overhead from an extra
+function call.
+
 
 The ftrace FLAGS
 ================
@@ -128,26 +172,20 @@ FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED
 	will not fail with this flag set. But the callback must check if
 	regs is NULL or not to determine if the architecture supports it.
 
-FTRACE_OPS_FL_RECURSION_SAFE
-	By default, a wrapper is added around the callback to
-	make sure that recursion of the function does not occur. That is,
-	if a function that is called as a result of the callback's execution
-	is also traced, ftrace will prevent the callback from being called
-	again. But this wrapper adds some overhead, and if the callback is
-	safe from recursion, it can set this flag to disable the ftrace
-	protection.
-
-	Note, if this flag is set, and recursion does occur, it could cause
-	the system to crash, and possibly reboot via a triple fault.
-
-	It is OK if another callback traces a function that is called by a
-	callback that is marked recursion safe. Recursion safe callbacks
-	must never trace any function that are called by the callback
-	itself or any nested functions that those functions call.
-
-	If this flag is set, it is possible that the callback will also
-	be called with preemption enabled (when CONFIG_PREEMPTION is set),
-	but this is not guaranteed.
+FTRACE_OPS_FL_RECURSION
+	By default, it is expected that the callback can handle recursion.
+	But if the callback is not that worried about overehead, then
+	setting this bit will add the recursion protection around the
+	callback by calling a helper function that will do the recursion
+	protection and only call the callback if it did not recurse.
+
+	Note, if this flag is not set, and recursion does occur, it could
+	cause the system to crash, and possibly reboot via a triple fault.
+
+	Not, if this flag is set, then the callback will always be called
+	with preemption disabled. If it is not set, then it is possible
+	(but not guaranteed) that the callback will be called in
+	preemptable context.
 
 FTRACE_OPS_FL_IPMODIFY
 	Requires FTRACE_OPS_FL_SAVE_REGS set. If the callback is to "hijack"
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 0e4164a7f56d..806196345c3f 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -98,7 +98,7 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops);
 /*
  * FTRACE_OPS_FL_* bits denote the state of ftrace_ops struct and are
  * set in the flags member.
- * CONTROL, SAVE_REGS, SAVE_REGS_IF_SUPPORTED, RECURSION_SAFE, STUB and
+ * CONTROL, SAVE_REGS, SAVE_REGS_IF_SUPPORTED, RECURSION, STUB and
  * IPMODIFY are a kind of attribute flags which can be set only before
  * registering the ftrace_ops, and can not be modified while registered.
  * Changing those attribute flags after registering ftrace_ops will
@@ -121,10 +121,10 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops);
  *            passing regs to the handler.
  *            Note, if this flag is set, the SAVE_REGS flag will automatically
  *            get set upon registering the ftrace_ops, if the arch supports it.
- * RECURSION_SAFE - The ftrace_ops can set this to tell the ftrace infrastructure
- *            that the call back has its own recursion protection. If it does
- *            not set this, then the ftrace infrastructure will add recursion
- *            protection for the caller.
+ * RECURSION - The ftrace_ops can set this to tell the ftrace infrastructure
+ *            that the call back needs recursion protection. If it does
+ *            not set this, then the ftrace infrastructure will assume
+ *            that the callback can handle recursion on its own.
  * STUB   - The ftrace_ops is just a place holder.
  * INITIALIZED - The ftrace_ops has already been initialized (first use time
  *            register_ftrace_function() is called, it will initialized the ops)
@@ -156,7 +156,7 @@ enum {
 	FTRACE_OPS_FL_DYNAMIC			= BIT(1),
 	FTRACE_OPS_FL_SAVE_REGS			= BIT(2),
 	FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED	= BIT(3),
-	FTRACE_OPS_FL_RECURSION_SAFE		= BIT(4),
+	FTRACE_OPS_FL_RECURSION			= BIT(4),
 	FTRACE_OPS_FL_STUB			= BIT(5),
 	FTRACE_OPS_FL_INITIALIZED		= BIT(6),
 	FTRACE_OPS_FL_DELETED			= BIT(7),
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 5658f13037b3..73edb9e4f354 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -334,8 +334,7 @@ unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx,
 
 static struct ftrace_ops graph_ops = {
 	.func			= ftrace_stub,
-	.flags			= FTRACE_OPS_FL_RECURSION_SAFE |
-				   FTRACE_OPS_FL_INITIALIZED |
+	.flags			= FTRACE_OPS_FL_INITIALIZED |
 				   FTRACE_OPS_FL_PID |
 				   FTRACE_OPS_FL_STUB,
 #ifdef FTRACE_GRAPH_TRAMP_ADDR
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 8185f7240095..39f2bba89b76 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -80,7 +80,7 @@ enum {
 
 struct ftrace_ops ftrace_list_end __read_mostly = {
 	.func		= ftrace_stub,
-	.flags		= FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_STUB,
+	.flags		= FTRACE_OPS_FL_STUB,
 	INIT_OPS_HASH(ftrace_list_end)
 };
 
@@ -866,7 +866,7 @@ static void unregister_ftrace_profiler(void)
 #else
 static struct ftrace_ops ftrace_profile_ops __read_mostly = {
 	.func		= function_profile_call,
-	.flags		= FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_INITIALIZED,
+	.flags		= FTRACE_OPS_FL_INITIALIZED,
 	INIT_OPS_HASH(ftrace_profile_ops)
 };
 
@@ -1040,8 +1040,7 @@ struct ftrace_ops global_ops = {
 	.local_hash.notrace_hash	= EMPTY_HASH,
 	.local_hash.filter_hash		= EMPTY_HASH,
 	INIT_OPS_HASH(global_ops)
-	.flags				= FTRACE_OPS_FL_RECURSION_SAFE |
-					  FTRACE_OPS_FL_INITIALIZED |
+	.flags				= FTRACE_OPS_FL_INITIALIZED |
 					  FTRACE_OPS_FL_PID,
 };
 
@@ -2382,7 +2381,7 @@ static void call_direct_funcs(unsigned long ip, unsigned long pip,
 
 struct ftrace_ops direct_ops = {
 	.func		= call_direct_funcs,
-	.flags		= FTRACE_OPS_FL_IPMODIFY | FTRACE_OPS_FL_RECURSION_SAFE
+	.flags		= FTRACE_OPS_FL_IPMODIFY
 			  | FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_REGS
 			  | FTRACE_OPS_FL_PERMANENT,
 	/*
@@ -6864,8 +6863,7 @@ void ftrace_init_trace_array(struct trace_array *tr)
 
 struct ftrace_ops global_ops = {
 	.func			= ftrace_stub,
-	.flags			= FTRACE_OPS_FL_RECURSION_SAFE |
-				  FTRACE_OPS_FL_INITIALIZED |
+	.flags			= FTRACE_OPS_FL_INITIALIZED |
 				  FTRACE_OPS_FL_PID,
 };
 
@@ -7023,11 +7021,11 @@ NOKPROBE_SYMBOL(ftrace_ops_assist_func);
 ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops)
 {
 	/*
-	 * If the function does not handle recursion, needs to be RCU safe,
-	 * or does per cpu logic, then we need to call the assist handler.
+	 * If the function does not handle recursion or needs to be RCU safe,
+	 * then we need to call the assist handler.
 	 */
-	if (!(ops->flags & FTRACE_OPS_FL_RECURSION_SAFE) ||
-	    ops->flags & FTRACE_OPS_FL_RCU)
+	if (ops->flags & (FTRACE_OPS_FL_RECURSION |
+			  FTRACE_OPS_FL_RCU))
 		return ftrace_ops_assist_func;
 
 	return ops->func;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 47a71f96e5bc..244abbcd1db5 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -3712,7 +3712,6 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip,
 static struct ftrace_ops trace_ops __initdata  =
 {
 	.func = function_test_events_call,
-	.flags = FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
 static __init void event_trace_self_test_with_function(void)
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 943756c01190..89c414ce1388 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -48,7 +48,7 @@ int ftrace_allocate_ftrace_ops(struct trace_array *tr)
 
 	/* Currently only the non stack version is supported */
 	ops->func = function_trace_call;
-	ops->flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_PID;
+	ops->flags = FTRACE_OPS_FL_PID;
 
 	tr->ops = ops;
 	ops->private = tr;
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 4738ad48a667..8ee3c0bb5d8a 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -150,17 +150,14 @@ static void trace_selftest_test_dyn_func(unsigned long ip,
 
 static struct ftrace_ops test_probe1 = {
 	.func			= trace_selftest_test_probe1_func,
-	.flags			= FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
 static struct ftrace_ops test_probe2 = {
 	.func			= trace_selftest_test_probe2_func,
-	.flags			= FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
 static struct ftrace_ops test_probe3 = {
 	.func			= trace_selftest_test_probe3_func,
-	.flags			= FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
 static void print_counts(void)
@@ -448,11 +445,11 @@ static void trace_selftest_test_recursion_safe_func(unsigned long ip,
 
 static struct ftrace_ops test_rec_probe = {
 	.func			= trace_selftest_test_recursion_func,
+	.flags			= FTRACE_OPS_FL_RECURSION,
 };
 
 static struct ftrace_ops test_recsafe_probe = {
 	.func			= trace_selftest_test_recursion_safe_func,
-	.flags			= FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
 static int
@@ -561,7 +558,7 @@ static void trace_selftest_test_regs_func(unsigned long ip,
 
 static struct ftrace_ops test_regs_probe = {
 	.func		= trace_selftest_test_regs_func,
-	.flags		= FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_SAVE_REGS,
+	.flags		= FTRACE_OPS_FL_SAVE_REGS,
 };
 
 static int
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index c408423e5d65..969db526a563 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -318,7 +318,6 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip,
 static struct ftrace_ops trace_ops __read_mostly =
 {
 	.func = stack_trace_call,
-	.flags = FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
 static ssize_t
-- 
cgit v1.2.3


From 773c16705058e9be7b0f4ce124e89cd231c120a2 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Thu, 5 Nov 2020 21:32:46 -0500
Subject: ftrace: Add recording of functions that caused recursion

This adds CONFIG_FTRACE_RECORD_RECURSION that will record to a file
"recursed_functions" all the functions that caused recursion while a
callback to the function tracer was running.

Link: https://lkml.kernel.org/r/20201106023548.102375687@goodmis.org

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Guo Ren <guoren@kernel.org>
Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com>
Cc: Helge Deller <deller@gmx.de>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Borislav Petkov <bp@alien8.de>
Cc: x86@kernel.org
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Anton Vorontsov <anton@enomsg.org>
Cc: Colin Cross <ccross@android.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Jiri Kosina <jikos@kernel.org>
Cc: Miroslav Benes <mbenes@suse.cz>
Cc: Petr Mladek <pmladek@suse.com>
Cc: Joe Lawrence <joe.lawrence@redhat.com>
Cc: Kamalesh Babulal <kamalesh@linux.vnet.ibm.com>
Cc: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: linux-doc@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-csky@vger.kernel.org
Cc: linux-parisc@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: linux-s390@vger.kernel.org
Cc: live-patching@vger.kernel.org
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 Documentation/trace/ftrace-uses.rst   |   6 +-
 arch/csky/kernel/probes/ftrace.c      |   2 +-
 arch/parisc/kernel/ftrace.c           |   2 +-
 arch/powerpc/kernel/kprobes-ftrace.c  |   2 +-
 arch/s390/kernel/ftrace.c             |   2 +-
 arch/x86/kernel/kprobes/ftrace.c      |   2 +-
 fs/pstore/ftrace.c                    |   2 +-
 include/linux/trace_recursion.h       |  29 ++++-
 kernel/livepatch/patch.c              |   2 +-
 kernel/trace/Kconfig                  |  25 ++++
 kernel/trace/Makefile                 |   1 +
 kernel/trace/ftrace.c                 |   4 +-
 kernel/trace/trace_event_perf.c       |   2 +-
 kernel/trace/trace_functions.c        |   2 +-
 kernel/trace/trace_output.c           |   6 +-
 kernel/trace/trace_output.h           |   1 +
 kernel/trace/trace_recursion_record.c | 236 ++++++++++++++++++++++++++++++++++
 17 files changed, 306 insertions(+), 20 deletions(-)
 create mode 100644 kernel/trace/trace_recursion_record.c

(limited to 'include/linux')

diff --git a/Documentation/trace/ftrace-uses.rst b/Documentation/trace/ftrace-uses.rst
index 86cd14b8e126..5981d5691745 100644
--- a/Documentation/trace/ftrace-uses.rst
+++ b/Documentation/trace/ftrace-uses.rst
@@ -118,7 +118,7 @@ can help in this regard. If you start your code with:
 
 	int bit;
 
-	bit = ftrace_test_recursion_trylock();
+	bit = ftrace_test_recursion_trylock(ip, parent_ip);
 	if (bit < 0)
 		return;
 
@@ -130,7 +130,9 @@ The code in between will be safe to use, even if it ends up calling a
 function that the callback is tracing. Note, on success,
 ftrace_test_recursion_trylock() will disable preemption, and the
 ftrace_test_recursion_unlock() will enable it again (if it was previously
-enabled).
+enabled). The instruction pointer (ip) and its parent (parent_ip) is passed to
+ftrace_test_recursion_trylock() to record where the recursion happened
+(if CONFIG_FTRACE_RECORD_RECURSION is set).
 
 Alternatively, if the FTRACE_OPS_FL_RECURSION flag is set on the ftrace_ops
 (as explained below), then a helper trampoline will be used to test
diff --git a/arch/csky/kernel/probes/ftrace.c b/arch/csky/kernel/probes/ftrace.c
index 5eb2604fdf71..f30b179924ef 100644
--- a/arch/csky/kernel/probes/ftrace.c
+++ b/arch/csky/kernel/probes/ftrace.c
@@ -18,7 +18,7 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 	struct kprobe *p;
 	struct kprobe_ctlblk *kcb;
 
-	bit = ftrace_test_recursion_trylock();
+	bit = ftrace_test_recursion_trylock(ip, parent_ip);
 	if (bit < 0)
 		return;
 
diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c
index 13d85042810a..1c5d3732bda2 100644
--- a/arch/parisc/kernel/ftrace.c
+++ b/arch/parisc/kernel/ftrace.c
@@ -210,7 +210,7 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 	struct kprobe *p;
 	int bit;
 
-	bit = ftrace_test_recursion_trylock();
+	bit = ftrace_test_recursion_trylock(ip, parent_ip);
 	if (bit < 0)
 		return;
 
diff --git a/arch/powerpc/kernel/kprobes-ftrace.c b/arch/powerpc/kernel/kprobes-ftrace.c
index 5df8d50c65ae..fdfee39938ea 100644
--- a/arch/powerpc/kernel/kprobes-ftrace.c
+++ b/arch/powerpc/kernel/kprobes-ftrace.c
@@ -20,7 +20,7 @@ void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip,
 	struct kprobe_ctlblk *kcb;
 	int bit;
 
-	bit = ftrace_test_recursion_trylock();
+	bit = ftrace_test_recursion_trylock(nip, parent_nip);
 	if (bit < 0)
 		return;
 
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 8f31c726537a..657c1ab45408 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -204,7 +204,7 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 	struct kprobe *p;
 	int bit;
 
-	bit = ftrace_test_recursion_trylock();
+	bit = ftrace_test_recursion_trylock(ip, parent_ip);
 	if (bit < 0)
 		return;
 
diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c
index a40a6cdfcca3..954d930a7127 100644
--- a/arch/x86/kernel/kprobes/ftrace.c
+++ b/arch/x86/kernel/kprobes/ftrace.c
@@ -20,7 +20,7 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 	struct kprobe_ctlblk *kcb;
 	int bit;
 
-	bit = ftrace_test_recursion_trylock();
+	bit = ftrace_test_recursion_trylock(ip, parent_ip);
 	if (bit < 0)
 		return;
 
diff --git a/fs/pstore/ftrace.c b/fs/pstore/ftrace.c
index 816210fc5d3a..adb0935eb062 100644
--- a/fs/pstore/ftrace.c
+++ b/fs/pstore/ftrace.c
@@ -41,7 +41,7 @@ static void notrace pstore_ftrace_call(unsigned long ip,
 	if (unlikely(oops_in_progress))
 		return;
 
-	bit = ftrace_test_recursion_trylock();
+	bit = ftrace_test_recursion_trylock(ip, parent_ip);
 	if (bit < 0)
 		return;
 
diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h
index ac3d73484cb2..228cc56ed66e 100644
--- a/include/linux/trace_recursion.h
+++ b/include/linux/trace_recursion.h
@@ -91,6 +91,9 @@ enum {
 	 * not be correct. Allow for a single recursion to cover this case.
 	 */
 	TRACE_TRANSITION_BIT,
+
+	/* Used to prevent recursion recording from recursing. */
+	TRACE_RECORD_RECURSION_BIT,
 };
 
 #define trace_recursion_set(bit)	do { (current)->trace_recursion |= (1<<(bit)); } while (0)
@@ -142,7 +145,22 @@ static __always_inline int trace_get_context_bit(void)
 			pc & HARDIRQ_MASK ? TRACE_CTX_IRQ : TRACE_CTX_SOFTIRQ;
 }
 
-static __always_inline int trace_test_and_set_recursion(int start, int max)
+#ifdef CONFIG_FTRACE_RECORD_RECURSION
+extern void ftrace_record_recursion(unsigned long ip, unsigned long parent_ip);
+# define do_ftrace_record_recursion(ip, pip)				\
+	do {								\
+		if (!trace_recursion_test(TRACE_RECORD_RECURSION_BIT)) { \
+			trace_recursion_set(TRACE_RECORD_RECURSION_BIT); \
+			ftrace_record_recursion(ip, pip);		\
+			trace_recursion_clear(TRACE_RECORD_RECURSION_BIT); \
+		}							\
+	} while (0)
+#else
+# define do_ftrace_record_recursion(ip, pip)	do { } while (0)
+#endif
+
+static __always_inline int trace_test_and_set_recursion(unsigned long ip, unsigned long pip,
+							int start, int max)
 {
 	unsigned int val = current->trace_recursion;
 	int bit;
@@ -158,8 +176,10 @@ static __always_inline int trace_test_and_set_recursion(int start, int max)
 		 * a switch between contexts. Allow for a single recursion.
 		 */
 		bit = TRACE_TRANSITION_BIT;
-		if (trace_recursion_test(bit))
+		if (trace_recursion_test(bit)) {
+			do_ftrace_record_recursion(ip, pip);
 			return -1;
+		}
 		trace_recursion_set(bit);
 		barrier();
 		return bit + 1;
@@ -199,9 +219,10 @@ static __always_inline void trace_clear_recursion(int bit)
  * Returns: -1 if a recursion happened.
  *           >= 0 if no recursion
  */
-static __always_inline int ftrace_test_recursion_trylock(void)
+static __always_inline int ftrace_test_recursion_trylock(unsigned long ip,
+							 unsigned long parent_ip)
 {
-	return trace_test_and_set_recursion(TRACE_FTRACE_START, TRACE_FTRACE_MAX);
+	return trace_test_and_set_recursion(ip, parent_ip, TRACE_FTRACE_START, TRACE_FTRACE_MAX);
 }
 
 /**
diff --git a/kernel/livepatch/patch.c b/kernel/livepatch/patch.c
index 15480bf3ce88..875c5dbbdd33 100644
--- a/kernel/livepatch/patch.c
+++ b/kernel/livepatch/patch.c
@@ -49,7 +49,7 @@ static void notrace klp_ftrace_handler(unsigned long ip,
 
 	ops = container_of(fops, struct klp_ops, fops);
 
-	bit = ftrace_test_recursion_trylock();
+	bit = ftrace_test_recursion_trylock(ip, parent_ip);
 	if (WARN_ON_ONCE(bit < 0))
 		return;
 	/*
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index a4020c0b4508..9b11c096d139 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -727,6 +727,31 @@ config TRACE_EVAL_MAP_FILE
 
 	If unsure, say N.
 
+config FTRACE_RECORD_RECURSION
+	bool "Record functions that recurse in function tracing"
+	depends on FUNCTION_TRACER
+	help
+	  All callbacks that attach to the function tracing have some sort
+	  of protection against recursion. Even though the protection exists,
+	  it adds overhead. This option will create a file in the tracefs
+	  file system called "recursed_functions" that will list the functions
+	  that triggered a recursion.
+
+	  This will add more overhead to cases that have recursion.
+
+	  If unsure, say N
+
+config FTRACE_RECORD_RECURSION_SIZE
+	int "Max number of recursed functions to record"
+	default	128
+	depends on FTRACE_RECORD_RECURSION
+	help
+	  This defines the limit of number of functions that can be
+	  listed in the "recursed_functions" file, that lists all
+	  the functions that caused a recursion to happen.
+	  This file can be reset, but the limit can not change in
+	  size at runtime.
+
 config GCOV_PROFILE_FTRACE
 	bool "Enable GCOV profiling on ftrace subsystem"
 	depends on GCOV_KERNEL
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index e153be351548..7e44cea89fdc 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -92,6 +92,7 @@ obj-$(CONFIG_DYNAMIC_EVENTS) += trace_dynevent.o
 obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o
 obj-$(CONFIG_UPROBE_EVENTS) += trace_uprobe.o
 obj-$(CONFIG_BOOTTIME_TRACING) += trace_boot.o
+obj-$(CONFIG_FTRACE_RECORD_RECURSION) += trace_recursion_record.o
 
 obj-$(CONFIG_TRACEPOINT_BENCHMARK) += trace_benchmark.o
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 39f2bba89b76..03aad2b5cd5e 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -6918,7 +6918,7 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
 	struct ftrace_ops *op;
 	int bit;
 
-	bit = trace_test_and_set_recursion(TRACE_LIST_START, TRACE_LIST_MAX);
+	bit = trace_test_and_set_recursion(ip, parent_ip, TRACE_LIST_START, TRACE_LIST_MAX);
 	if (bit < 0)
 		return;
 
@@ -6993,7 +6993,7 @@ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip,
 {
 	int bit;
 
-	bit = trace_test_and_set_recursion(TRACE_LIST_START, TRACE_LIST_MAX);
+	bit = trace_test_and_set_recursion(ip, parent_ip, TRACE_LIST_START, TRACE_LIST_MAX);
 	if (bit < 0)
 		return;
 
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index a2b9fddb8148..1b202e28dfaa 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -447,7 +447,7 @@ perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip,
 	if ((unsigned long)ops->private != smp_processor_id())
 		return;
 
-	bit = ftrace_test_recursion_trylock();
+	bit = ftrace_test_recursion_trylock(ip, parent_ip);
 	if (bit < 0)
 		return;
 
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 89c414ce1388..646eda6c44a5 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -141,7 +141,7 @@ function_trace_call(unsigned long ip, unsigned long parent_ip,
 	if (unlikely(!tr->function_enabled))
 		return;
 
-	bit = ftrace_test_recursion_trylock();
+	bit = ftrace_test_recursion_trylock(ip, parent_ip);
 	if (bit < 0)
 		return;
 
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 000e9dc224c6..92b1575ae0ca 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -353,8 +353,8 @@ static inline const char *kretprobed(const char *name)
 }
 #endif /* CONFIG_KRETPROBES */
 
-static void
-seq_print_sym(struct trace_seq *s, unsigned long address, bool offset)
+void
+trace_seq_print_sym(struct trace_seq *s, unsigned long address, bool offset)
 {
 #ifdef CONFIG_KALLSYMS
 	char str[KSYM_SYMBOL_LEN];
@@ -420,7 +420,7 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags)
 		goto out;
 	}
 
-	seq_print_sym(s, ip, sym_flags & TRACE_ITER_SYM_OFFSET);
+	trace_seq_print_sym(s, ip, sym_flags & TRACE_ITER_SYM_OFFSET);
 
 	if (sym_flags & TRACE_ITER_SYM_ADDR)
 		trace_seq_printf(s, " <" IP_FMT ">", ip);
diff --git a/kernel/trace/trace_output.h b/kernel/trace/trace_output.h
index 2f742b74e7e6..4c954636caf0 100644
--- a/kernel/trace/trace_output.h
+++ b/kernel/trace/trace_output.h
@@ -16,6 +16,7 @@ extern int
 seq_print_ip_sym(struct trace_seq *s, unsigned long ip,
 		unsigned long sym_flags);
 
+extern void trace_seq_print_sym(struct trace_seq *s, unsigned long address, bool offset);
 extern int trace_print_context(struct trace_iterator *iter);
 extern int trace_print_lat_context(struct trace_iterator *iter);
 
diff --git a/kernel/trace/trace_recursion_record.c b/kernel/trace/trace_recursion_record.c
new file mode 100644
index 000000000000..b2edac1fe156
--- /dev/null
+++ b/kernel/trace/trace_recursion_record.c
@@ -0,0 +1,236 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/seq_file.h>
+#include <linux/kallsyms.h>
+#include <linux/module.h>
+#include <linux/ftrace.h>
+#include <linux/fs.h>
+
+#include "trace_output.h"
+
+struct recursed_functions {
+	unsigned long		ip;
+	unsigned long		parent_ip;
+};
+
+static struct recursed_functions recursed_functions[CONFIG_FTRACE_RECORD_RECURSION_SIZE];
+static atomic_t nr_records;
+
+/*
+ * Cache the last found function. Yes, updates to this is racey, but
+ * so is memory cache ;-)
+ */
+static unsigned long cached_function;
+
+void ftrace_record_recursion(unsigned long ip, unsigned long parent_ip)
+{
+	int index = 0;
+	int i;
+	unsigned long old;
+
+ again:
+	/* First check the last one recorded */
+	if (ip == cached_function)
+		return;
+
+	i = atomic_read(&nr_records);
+	/* nr_records is -1 when clearing records */
+	smp_mb__after_atomic();
+	if (i < 0)
+		return;
+
+	/*
+	 * If there's two writers and this writer comes in second,
+	 * the cmpxchg() below to update the ip will fail. Then this
+	 * writer will try again. It is possible that index will now
+	 * be greater than nr_records. This is because the writer
+	 * that succeeded has not updated the nr_records yet.
+	 * This writer could keep trying again until the other writer
+	 * updates nr_records. But if the other writer takes an
+	 * interrupt, and that interrupt locks up that CPU, we do
+	 * not want this CPU to lock up due to the recursion protection,
+	 * and have a bug report showing this CPU as the cause of
+	 * locking up the computer. To not lose this record, this
+	 * writer will simply use the next position to update the
+	 * recursed_functions, and it will update the nr_records
+	 * accordingly.
+	 */
+	if (index < i)
+		index = i;
+	if (index >= CONFIG_FTRACE_RECORD_RECURSION_SIZE)
+		return;
+
+	for (i = index - 1; i >= 0; i--) {
+		if (recursed_functions[i].ip == ip) {
+			cached_function = ip;
+			return;
+		}
+	}
+
+	cached_function = ip;
+
+	/*
+	 * We only want to add a function if it hasn't been added before.
+	 * Add to the current location before incrementing the count.
+	 * If it fails to add, then increment the index (save in i)
+	 * and try again.
+	 */
+	old = cmpxchg(&recursed_functions[index].ip, 0, ip);
+	if (old != 0) {
+		/* Did something else already added this for us? */
+		if (old == ip)
+			return;
+		/* Try the next location (use i for the next index) */
+		index++;
+		goto again;
+	}
+
+	recursed_functions[index].parent_ip = parent_ip;
+
+	/*
+	 * It's still possible that we could race with the clearing
+	 *    CPU0                                    CPU1
+	 *    ----                                    ----
+	 *                                       ip = func
+	 *  nr_records = -1;
+	 *  recursed_functions[0] = 0;
+	 *                                       i = -1
+	 *                                       if (i < 0)
+	 *  nr_records = 0;
+	 *  (new recursion detected)
+	 *      recursed_functions[0] = func
+	 *                                            cmpxchg(recursed_functions[0],
+	 *                                                    func, 0)
+	 *
+	 * But the worse that could happen is that we get a zero in
+	 * the recursed_functions array, and it's likely that "func" will
+	 * be recorded again.
+	 */
+	i = atomic_read(&nr_records);
+	smp_mb__after_atomic();
+	if (i < 0)
+		cmpxchg(&recursed_functions[index].ip, ip, 0);
+	else if (i <= index)
+		atomic_cmpxchg(&nr_records, i, index + 1);
+}
+EXPORT_SYMBOL_GPL(ftrace_record_recursion);
+
+static DEFINE_MUTEX(recursed_function_lock);
+static struct trace_seq *tseq;
+
+static void *recursed_function_seq_start(struct seq_file *m, loff_t *pos)
+{
+	void *ret = NULL;
+	int index;
+
+	mutex_lock(&recursed_function_lock);
+	index = atomic_read(&nr_records);
+	if (*pos < index) {
+		ret = &recursed_functions[*pos];
+	}
+
+	tseq = kzalloc(sizeof(*tseq), GFP_KERNEL);
+	if (!tseq)
+		return ERR_PTR(-ENOMEM);
+
+	trace_seq_init(tseq);
+
+	return ret;
+}
+
+static void *recursed_function_seq_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	int index;
+	int p;
+
+	index = atomic_read(&nr_records);
+	p = ++(*pos);
+
+	return p < index ? &recursed_functions[p] : NULL;
+}
+
+static void recursed_function_seq_stop(struct seq_file *m, void *v)
+{
+	kfree(tseq);
+	mutex_unlock(&recursed_function_lock);
+}
+
+static int recursed_function_seq_show(struct seq_file *m, void *v)
+{
+	struct recursed_functions *record = v;
+	int ret = 0;
+
+	if (record) {
+		trace_seq_print_sym(tseq, record->parent_ip, true);
+		trace_seq_puts(tseq, ":\t");
+		trace_seq_print_sym(tseq, record->ip, true);
+		trace_seq_putc(tseq, '\n');
+		ret = trace_print_seq(m, tseq);
+	}
+
+	return ret;
+}
+
+static const struct seq_operations recursed_function_seq_ops = {
+	.start  = recursed_function_seq_start,
+	.next   = recursed_function_seq_next,
+	.stop   = recursed_function_seq_stop,
+	.show   = recursed_function_seq_show
+};
+
+static int recursed_function_open(struct inode *inode, struct file *file)
+{
+	int ret = 0;
+
+	mutex_lock(&recursed_function_lock);
+	/* If this file was opened for write, then erase contents */
+	if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
+		/* disable updating records */
+		atomic_set(&nr_records, -1);
+		smp_mb__after_atomic();
+		memset(recursed_functions, 0, sizeof(recursed_functions));
+		smp_wmb();
+		/* enable them again */
+		atomic_set(&nr_records, 0);
+	}
+	if (file->f_mode & FMODE_READ)
+		ret = seq_open(file, &recursed_function_seq_ops);
+	mutex_unlock(&recursed_function_lock);
+
+	return ret;
+}
+
+static ssize_t recursed_function_write(struct file *file,
+				       const char __user *buffer,
+				       size_t count, loff_t *ppos)
+{
+	return count;
+}
+
+static int recursed_function_release(struct inode *inode, struct file *file)
+{
+	if (file->f_mode & FMODE_READ)
+		seq_release(inode, file);
+	return 0;
+}
+
+static const struct file_operations recursed_functions_fops = {
+	.open           = recursed_function_open,
+	.write		= recursed_function_write,
+	.read           = seq_read,
+	.llseek         = seq_lseek,
+	.release        = recursed_function_release,
+};
+
+__init static int create_recursed_functions(void)
+{
+	struct dentry *dentry;
+
+	dentry = trace_create_file("recursed_functions", 0644, NULL, NULL,
+				   &recursed_functions_fops);
+	if (!dentry)
+		pr_warn("WARNING: Failed to create recursed_functions\n");
+	return 0;
+}
+
+fs_initcall(create_recursed_functions);
-- 
cgit v1.2.3


From 88b8138b240b43d5215bf7cb422692cd8db51f6f Mon Sep 17 00:00:00 2001
From: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Date: Fri, 6 Nov 2020 14:03:31 +0100
Subject: tty: serial: remove pnx8xxx uart driver

Commit 625326ea9c84 ("MIPS: Remove PNX833x alias NXP_STB22x") removed
support for PNX833x, so it's time to remove serial driver, too.

Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Link: https://lore.kernel.org/r/20201106130332.103476-1-tsbogend@alpha.franken.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/Kconfig        |  16 -
 drivers/tty/serial/Makefile       |   1 -
 drivers/tty/serial/pnx8xxx_uart.c | 858 --------------------------------------
 include/linux/serial_pnx8xxx.h    |  67 ---
 include/uapi/linux/serial_core.h  |   2 -
 5 files changed, 944 deletions(-)
 delete mode 100644 drivers/tty/serial/pnx8xxx_uart.c
 delete mode 100644 include/linux/serial_pnx8xxx.h

(limited to 'include/linux')

diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig
index 1044fc387691..b146c93146ee 100644
--- a/drivers/tty/serial/Kconfig
+++ b/drivers/tty/serial/Kconfig
@@ -703,22 +703,6 @@ config SERIAL_SH_SCI_DMA
 	depends on SERIAL_SH_SCI && DMA_ENGINE
 	default ARCH_RENESAS
 
-config SERIAL_PNX8XXX
-	bool "Enable PNX8XXX SoCs' UART Support"
-	depends on SOC_PNX833X
-	select SERIAL_CORE
-	help
-	  If you have a MIPS-based Philips SoC such as PNX8330 and you want
-	  to use serial ports, say Y.  Otherwise, say N.
-
-config SERIAL_PNX8XXX_CONSOLE
-	bool "Enable PNX8XX0 serial console"
-	depends on SERIAL_PNX8XXX
-	select SERIAL_CORE_CONSOLE
-	help
-	  If you have a MIPS-based Philips SoC such as PNX8330 and you want
-	  to use serial console, say Y. Otherwise, say N.
-
 config SERIAL_HS_LPC32XX
 	tristate "LPC32XX high speed serial port support"
 	depends on ARCH_LPC32XX || COMPILE_TEST
diff --git a/drivers/tty/serial/Makefile b/drivers/tty/serial/Makefile
index caf167f0c10a..af44b231123c 100644
--- a/drivers/tty/serial/Makefile
+++ b/drivers/tty/serial/Makefile
@@ -27,7 +27,6 @@ obj-$(CONFIG_SERIAL_AMBA_PL010) += amba-pl010.o
 obj-$(CONFIG_SERIAL_AMBA_PL011) += amba-pl011.o
 obj-$(CONFIG_SERIAL_CLPS711X) += clps711x.o
 obj-$(CONFIG_SERIAL_PXA_NON8250) += pxa.o
-obj-$(CONFIG_SERIAL_PNX8XXX) += pnx8xxx_uart.o
 obj-$(CONFIG_SERIAL_SA1100) += sa1100.o
 obj-$(CONFIG_SERIAL_BCM63XX) += bcm63xx_uart.o
 obj-$(CONFIG_SERIAL_SAMSUNG) += samsung_tty.o
diff --git a/drivers/tty/serial/pnx8xxx_uart.c b/drivers/tty/serial/pnx8xxx_uart.c
deleted file mode 100644
index 972d94e8d32b..000000000000
--- a/drivers/tty/serial/pnx8xxx_uart.c
+++ /dev/null
@@ -1,858 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * UART driver for PNX8XXX SoCs
- *
- * Author: Per Hallsmark per.hallsmark@mvista.com
- * Ported to 2.6 kernel by EmbeddedAlley
- * Reworked by Vitaly Wool <vitalywool@gmail.com>
- *
- * Based on drivers/char/serial.c, by Linus Torvalds, Theodore Ts'o.
- * Copyright (C) 2000 Deep Blue Solutions Ltd.
- */
-
-#include <linux/module.h>
-#include <linux/ioport.h>
-#include <linux/init.h>
-#include <linux/console.h>
-#include <linux/sysrq.h>
-#include <linux/device.h>
-#include <linux/platform_device.h>
-#include <linux/tty.h>
-#include <linux/tty_flip.h>
-#include <linux/serial_core.h>
-#include <linux/serial.h>
-#include <linux/serial_pnx8xxx.h>
-
-#include <asm/io.h>
-#include <asm/irq.h>
-
-/* We'll be using StrongARM sa1100 serial port major/minor */
-#define SERIAL_PNX8XXX_MAJOR	204
-#define MINOR_START		5
-
-#define NR_PORTS		2
-
-#define PNX8XXX_ISR_PASS_LIMIT	256
-
-/*
- * Convert from ignore_status_mask or read_status_mask to FIFO
- * and interrupt status bits
- */
-#define SM_TO_FIFO(x)	((x) >> 10)
-#define SM_TO_ISTAT(x)	((x) & 0x000001ff)
-#define FIFO_TO_SM(x)	((x) << 10)
-#define ISTAT_TO_SM(x)	((x) & 0x000001ff)
-
-/*
- * This is the size of our serial port register set.
- */
-#define UART_PORT_SIZE	0x1000
-
-/*
- * This determines how often we check the modem status signals
- * for any change.  They generally aren't connected to an IRQ
- * so we have to poll them.  We also check immediately before
- * filling the TX fifo incase CTS has been dropped.
- */
-#define MCTRL_TIMEOUT	(250*HZ/1000)
-
-extern struct pnx8xxx_port pnx8xxx_ports[];
-
-static inline int serial_in(struct pnx8xxx_port *sport, int offset)
-{
-	return (__raw_readl(sport->port.membase + offset));
-}
-
-static inline void serial_out(struct pnx8xxx_port *sport, int offset, int value)
-{
-	__raw_writel(value, sport->port.membase + offset);
-}
-
-/*
- * Handle any change of modem status signal since we were last called.
- */
-static void pnx8xxx_mctrl_check(struct pnx8xxx_port *sport)
-{
-	unsigned int status, changed;
-
-	status = sport->port.ops->get_mctrl(&sport->port);
-	changed = status ^ sport->old_status;
-
-	if (changed == 0)
-		return;
-
-	sport->old_status = status;
-
-	if (changed & TIOCM_RI)
-		sport->port.icount.rng++;
-	if (changed & TIOCM_DSR)
-		sport->port.icount.dsr++;
-	if (changed & TIOCM_CAR)
-		uart_handle_dcd_change(&sport->port, status & TIOCM_CAR);
-	if (changed & TIOCM_CTS)
-		uart_handle_cts_change(&sport->port, status & TIOCM_CTS);
-
-	wake_up_interruptible(&sport->port.state->port.delta_msr_wait);
-}
-
-/*
- * This is our per-port timeout handler, for checking the
- * modem status signals.
- */
-static void pnx8xxx_timeout(struct timer_list *t)
-{
-	struct pnx8xxx_port *sport = from_timer(sport, t, timer);
-	unsigned long flags;
-
-	if (sport->port.state) {
-		spin_lock_irqsave(&sport->port.lock, flags);
-		pnx8xxx_mctrl_check(sport);
-		spin_unlock_irqrestore(&sport->port.lock, flags);
-
-		mod_timer(&sport->timer, jiffies + MCTRL_TIMEOUT);
-	}
-}
-
-/*
- * interrupts disabled on entry
- */
-static void pnx8xxx_stop_tx(struct uart_port *port)
-{
-	struct pnx8xxx_port *sport =
-		container_of(port, struct pnx8xxx_port, port);
-	u32 ien;
-
-	/* Disable TX intr */
-	ien = serial_in(sport, PNX8XXX_IEN);
-	serial_out(sport, PNX8XXX_IEN, ien & ~PNX8XXX_UART_INT_ALLTX);
-
-	/* Clear all pending TX intr */
-	serial_out(sport, PNX8XXX_ICLR, PNX8XXX_UART_INT_ALLTX);
-}
-
-/*
- * interrupts may not be disabled on entry
- */
-static void pnx8xxx_start_tx(struct uart_port *port)
-{
-	struct pnx8xxx_port *sport =
-		container_of(port, struct pnx8xxx_port, port);
-	u32 ien;
-
-	/* Clear all pending TX intr */
-	serial_out(sport, PNX8XXX_ICLR, PNX8XXX_UART_INT_ALLTX);
-
-	/* Enable TX intr */
-	ien = serial_in(sport, PNX8XXX_IEN);
-	serial_out(sport, PNX8XXX_IEN, ien | PNX8XXX_UART_INT_ALLTX);
-}
-
-/*
- * Interrupts enabled
- */
-static void pnx8xxx_stop_rx(struct uart_port *port)
-{
-	struct pnx8xxx_port *sport =
-		container_of(port, struct pnx8xxx_port, port);
-	u32 ien;
-
-	/* Disable RX intr */
-	ien = serial_in(sport, PNX8XXX_IEN);
-	serial_out(sport, PNX8XXX_IEN, ien & ~PNX8XXX_UART_INT_ALLRX);
-
-	/* Clear all pending RX intr */
-	serial_out(sport, PNX8XXX_ICLR, PNX8XXX_UART_INT_ALLRX);
-}
-
-/*
- * Set the modem control timer to fire immediately.
- */
-static void pnx8xxx_enable_ms(struct uart_port *port)
-{
-	struct pnx8xxx_port *sport =
-		container_of(port, struct pnx8xxx_port, port);
-
-	mod_timer(&sport->timer, jiffies);
-}
-
-static void pnx8xxx_rx_chars(struct pnx8xxx_port *sport)
-{
-	unsigned int status, ch, flg;
-
-	status = FIFO_TO_SM(serial_in(sport, PNX8XXX_FIFO)) |
-		 ISTAT_TO_SM(serial_in(sport, PNX8XXX_ISTAT));
-	while (status & FIFO_TO_SM(PNX8XXX_UART_FIFO_RXFIFO)) {
-		ch = serial_in(sport, PNX8XXX_FIFO) & 0xff;
-
-		sport->port.icount.rx++;
-
-		flg = TTY_NORMAL;
-
-		/*
-		 * note that the error handling code is
-		 * out of the main execution path
-		 */
-		if (status & (FIFO_TO_SM(PNX8XXX_UART_FIFO_RXFE |
-					PNX8XXX_UART_FIFO_RXPAR |
-					PNX8XXX_UART_FIFO_RXBRK) |
-			      ISTAT_TO_SM(PNX8XXX_UART_INT_RXOVRN))) {
-			if (status & FIFO_TO_SM(PNX8XXX_UART_FIFO_RXBRK)) {
-				status &= ~(FIFO_TO_SM(PNX8XXX_UART_FIFO_RXFE) |
-					FIFO_TO_SM(PNX8XXX_UART_FIFO_RXPAR));
-				sport->port.icount.brk++;
-				if (uart_handle_break(&sport->port))
-					goto ignore_char;
-			} else if (status & FIFO_TO_SM(PNX8XXX_UART_FIFO_RXPAR))
-				sport->port.icount.parity++;
-			else if (status & FIFO_TO_SM(PNX8XXX_UART_FIFO_RXFE))
-				sport->port.icount.frame++;
-			if (status & ISTAT_TO_SM(PNX8XXX_UART_INT_RXOVRN))
-				sport->port.icount.overrun++;
-
-			status &= sport->port.read_status_mask;
-
-			if (status & FIFO_TO_SM(PNX8XXX_UART_FIFO_RXPAR))
-				flg = TTY_PARITY;
-			else if (status & FIFO_TO_SM(PNX8XXX_UART_FIFO_RXFE))
-				flg = TTY_FRAME;
-
-			sport->port.sysrq = 0;
-		}
-
-		if (uart_handle_sysrq_char(&sport->port, ch))
-			goto ignore_char;
-
-		uart_insert_char(&sport->port, status,
-				ISTAT_TO_SM(PNX8XXX_UART_INT_RXOVRN), ch, flg);
-
-	ignore_char:
-		serial_out(sport, PNX8XXX_LCR, serial_in(sport, PNX8XXX_LCR) |
-				PNX8XXX_UART_LCR_RX_NEXT);
-		status = FIFO_TO_SM(serial_in(sport, PNX8XXX_FIFO)) |
-			 ISTAT_TO_SM(serial_in(sport, PNX8XXX_ISTAT));
-	}
-
-	spin_unlock(&sport->port.lock);
-	tty_flip_buffer_push(&sport->port.state->port);
-	spin_lock(&sport->port.lock);
-}
-
-static void pnx8xxx_tx_chars(struct pnx8xxx_port *sport)
-{
-	struct circ_buf *xmit = &sport->port.state->xmit;
-
-	if (sport->port.x_char) {
-		serial_out(sport, PNX8XXX_FIFO, sport->port.x_char);
-		sport->port.icount.tx++;
-		sport->port.x_char = 0;
-		return;
-	}
-
-	/*
-	 * Check the modem control lines before
-	 * transmitting anything.
-	 */
-	pnx8xxx_mctrl_check(sport);
-
-	if (uart_circ_empty(xmit) || uart_tx_stopped(&sport->port)) {
-		pnx8xxx_stop_tx(&sport->port);
-		return;
-	}
-
-	/*
-	 * TX while bytes available
-	 */
-	while (((serial_in(sport, PNX8XXX_FIFO) &
-					PNX8XXX_UART_FIFO_TXFIFO) >> 16) < 16) {
-		serial_out(sport, PNX8XXX_FIFO, xmit->buf[xmit->tail]);
-		xmit->tail = (xmit->tail + 1) & (UART_XMIT_SIZE - 1);
-		sport->port.icount.tx++;
-		if (uart_circ_empty(xmit))
-			break;
-	}
-
-	if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS)
-		uart_write_wakeup(&sport->port);
-
-	if (uart_circ_empty(xmit))
-		pnx8xxx_stop_tx(&sport->port);
-}
-
-static irqreturn_t pnx8xxx_int(int irq, void *dev_id)
-{
-	struct pnx8xxx_port *sport = dev_id;
-	unsigned int status;
-
-	spin_lock(&sport->port.lock);
-	/* Get the interrupts */
-	status  = serial_in(sport, PNX8XXX_ISTAT) & serial_in(sport, PNX8XXX_IEN);
-
-	/* Byte or break signal received */
-	if (status & (PNX8XXX_UART_INT_RX | PNX8XXX_UART_INT_BREAK))
-		pnx8xxx_rx_chars(sport);
-
-	/* TX holding register empty - transmit a byte */
-	if (status & PNX8XXX_UART_INT_TX)
-		pnx8xxx_tx_chars(sport);
-
-	/* Clear the ISTAT register */
-	serial_out(sport, PNX8XXX_ICLR, status);
-
-	spin_unlock(&sport->port.lock);
-	return IRQ_HANDLED;
-}
-
-/*
- * Return TIOCSER_TEMT when transmitter is not busy.
- */
-static unsigned int pnx8xxx_tx_empty(struct uart_port *port)
-{
-	struct pnx8xxx_port *sport =
-		container_of(port, struct pnx8xxx_port, port);
-
-	return serial_in(sport, PNX8XXX_FIFO) & PNX8XXX_UART_FIFO_TXFIFO_STA ? 0 : TIOCSER_TEMT;
-}
-
-static unsigned int pnx8xxx_get_mctrl(struct uart_port *port)
-{
-	struct pnx8xxx_port *sport =
-		container_of(port, struct pnx8xxx_port, port);
-	unsigned int mctrl = TIOCM_DSR;
-	unsigned int msr;
-
-	/* REVISIT */
-
-	msr = serial_in(sport, PNX8XXX_MCR);
-
-	mctrl |= msr & PNX8XXX_UART_MCR_CTS ? TIOCM_CTS : 0;
-	mctrl |= msr & PNX8XXX_UART_MCR_DCD ? TIOCM_CAR : 0;
-
-	return mctrl;
-}
-
-static void pnx8xxx_set_mctrl(struct uart_port *port, unsigned int mctrl)
-{
-#if	0	/* FIXME */
-	struct pnx8xxx_port *sport = (struct pnx8xxx_port *)port;
-	unsigned int msr;
-#endif
-}
-
-/*
- * Interrupts always disabled.
- */
-static void pnx8xxx_break_ctl(struct uart_port *port, int break_state)
-{
-	struct pnx8xxx_port *sport =
-		container_of(port, struct pnx8xxx_port, port);
-	unsigned long flags;
-	unsigned int lcr;
-
-	spin_lock_irqsave(&sport->port.lock, flags);
-	lcr = serial_in(sport, PNX8XXX_LCR);
-	if (break_state == -1)
-		lcr |= PNX8XXX_UART_LCR_TXBREAK;
-	else
-		lcr &= ~PNX8XXX_UART_LCR_TXBREAK;
-	serial_out(sport, PNX8XXX_LCR, lcr);
-	spin_unlock_irqrestore(&sport->port.lock, flags);
-}
-
-static int pnx8xxx_startup(struct uart_port *port)
-{
-	struct pnx8xxx_port *sport =
-		container_of(port, struct pnx8xxx_port, port);
-	int retval;
-
-	/*
-	 * Allocate the IRQ
-	 */
-	retval = request_irq(sport->port.irq, pnx8xxx_int, 0,
-			     "pnx8xxx-uart", sport);
-	if (retval)
-		return retval;
-
-	/*
-	 * Finally, clear and enable interrupts
-	 */
-
-	serial_out(sport, PNX8XXX_ICLR, PNX8XXX_UART_INT_ALLRX |
-			     PNX8XXX_UART_INT_ALLTX);
-
-	serial_out(sport, PNX8XXX_IEN, serial_in(sport, PNX8XXX_IEN) |
-			    PNX8XXX_UART_INT_ALLRX |
-			    PNX8XXX_UART_INT_ALLTX);
-
-	/*
-	 * Enable modem status interrupts
-	 */
-	spin_lock_irq(&sport->port.lock);
-	pnx8xxx_enable_ms(&sport->port);
-	spin_unlock_irq(&sport->port.lock);
-
-	return 0;
-}
-
-static void pnx8xxx_shutdown(struct uart_port *port)
-{
-	struct pnx8xxx_port *sport =
-		container_of(port, struct pnx8xxx_port, port);
-	int lcr;
-
-	/*
-	 * Stop our timer.
-	 */
-	del_timer_sync(&sport->timer);
-
-	/*
-	 * Disable all interrupts
-	 */
-	serial_out(sport, PNX8XXX_IEN, 0);
-
-	/*
-	 * Reset the Tx and Rx FIFOS, disable the break condition
-	 */
-	lcr = serial_in(sport, PNX8XXX_LCR);
-	lcr &= ~PNX8XXX_UART_LCR_TXBREAK;
-	lcr |= PNX8XXX_UART_LCR_TX_RST | PNX8XXX_UART_LCR_RX_RST;
-	serial_out(sport, PNX8XXX_LCR, lcr);
-
-	/*
-	 * Clear all interrupts
-	 */
-	serial_out(sport, PNX8XXX_ICLR, PNX8XXX_UART_INT_ALLRX |
-			     PNX8XXX_UART_INT_ALLTX);
-
-	/*
-	 * Free the interrupt
-	 */
-	free_irq(sport->port.irq, sport);
-}
-
-static void
-pnx8xxx_set_termios(struct uart_port *port, struct ktermios *termios,
-		   struct ktermios *old)
-{
-	struct pnx8xxx_port *sport =
-		container_of(port, struct pnx8xxx_port, port);
-	unsigned long flags;
-	unsigned int lcr_fcr, old_ien, baud, quot;
-	unsigned int old_csize = old ? old->c_cflag & CSIZE : CS8;
-
-	/*
-	 * We only support CS7 and CS8.
-	 */
-	while ((termios->c_cflag & CSIZE) != CS7 &&
-	       (termios->c_cflag & CSIZE) != CS8) {
-		termios->c_cflag &= ~CSIZE;
-		termios->c_cflag |= old_csize;
-		old_csize = CS8;
-	}
-
-	if ((termios->c_cflag & CSIZE) == CS8)
-		lcr_fcr = PNX8XXX_UART_LCR_8BIT;
-	else
-		lcr_fcr = 0;
-
-	if (termios->c_cflag & CSTOPB)
-		lcr_fcr |= PNX8XXX_UART_LCR_2STOPB;
-	if (termios->c_cflag & PARENB) {
-		lcr_fcr |= PNX8XXX_UART_LCR_PAREN;
-		if (!(termios->c_cflag & PARODD))
-			lcr_fcr |= PNX8XXX_UART_LCR_PAREVN;
-	}
-
-	/*
-	 * Ask the core to calculate the divisor for us.
-	 */
-	baud = uart_get_baud_rate(port, termios, old, 0, port->uartclk/16);
-	quot = uart_get_divisor(port, baud);
-
-	spin_lock_irqsave(&sport->port.lock, flags);
-
-	sport->port.read_status_mask = ISTAT_TO_SM(PNX8XXX_UART_INT_RXOVRN) |
-				ISTAT_TO_SM(PNX8XXX_UART_INT_EMPTY) |
-				ISTAT_TO_SM(PNX8XXX_UART_INT_RX);
-	if (termios->c_iflag & INPCK)
-		sport->port.read_status_mask |=
-			FIFO_TO_SM(PNX8XXX_UART_FIFO_RXFE) |
-			FIFO_TO_SM(PNX8XXX_UART_FIFO_RXPAR);
-	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
-		sport->port.read_status_mask |=
-			ISTAT_TO_SM(PNX8XXX_UART_INT_BREAK);
-
-	/*
-	 * Characters to ignore
-	 */
-	sport->port.ignore_status_mask = 0;
-	if (termios->c_iflag & IGNPAR)
-		sport->port.ignore_status_mask |=
-			FIFO_TO_SM(PNX8XXX_UART_FIFO_RXFE) |
-			FIFO_TO_SM(PNX8XXX_UART_FIFO_RXPAR);
-	if (termios->c_iflag & IGNBRK) {
-		sport->port.ignore_status_mask |=
-			ISTAT_TO_SM(PNX8XXX_UART_INT_BREAK);
-		/*
-		 * If we're ignoring parity and break indicators,
-		 * ignore overruns too (for real raw support).
-		 */
-		if (termios->c_iflag & IGNPAR)
-			sport->port.ignore_status_mask |=
-				ISTAT_TO_SM(PNX8XXX_UART_INT_RXOVRN);
-	}
-
-	/*
-	 * ignore all characters if CREAD is not set
-	 */
-	if ((termios->c_cflag & CREAD) == 0)
-		sport->port.ignore_status_mask |=
-			ISTAT_TO_SM(PNX8XXX_UART_INT_RX);
-
-	del_timer_sync(&sport->timer);
-
-	/*
-	 * Update the per-port timeout.
-	 */
-	uart_update_timeout(port, termios->c_cflag, baud);
-
-	/*
-	 * disable interrupts and drain transmitter
-	 */
-	old_ien = serial_in(sport, PNX8XXX_IEN);
-	serial_out(sport, PNX8XXX_IEN, old_ien & ~(PNX8XXX_UART_INT_ALLTX |
-					PNX8XXX_UART_INT_ALLRX));
-
-	while (serial_in(sport, PNX8XXX_FIFO) & PNX8XXX_UART_FIFO_TXFIFO_STA)
-		barrier();
-
-	/* then, disable everything */
-	serial_out(sport, PNX8XXX_IEN, 0);
-
-	/* Reset the Rx and Tx FIFOs too */
-	lcr_fcr |= PNX8XXX_UART_LCR_TX_RST;
-	lcr_fcr |= PNX8XXX_UART_LCR_RX_RST;
-
-	/* set the parity, stop bits and data size */
-	serial_out(sport, PNX8XXX_LCR, lcr_fcr);
-
-	/* set the baud rate */
-	quot -= 1;
-	serial_out(sport, PNX8XXX_BAUD, quot);
-
-	serial_out(sport, PNX8XXX_ICLR, -1);
-
-	serial_out(sport, PNX8XXX_IEN, old_ien);
-
-	if (UART_ENABLE_MS(&sport->port, termios->c_cflag))
-		pnx8xxx_enable_ms(&sport->port);
-
-	spin_unlock_irqrestore(&sport->port.lock, flags);
-}
-
-static const char *pnx8xxx_type(struct uart_port *port)
-{
-	struct pnx8xxx_port *sport =
-		container_of(port, struct pnx8xxx_port, port);
-
-	return sport->port.type == PORT_PNX8XXX ? "PNX8XXX" : NULL;
-}
-
-/*
- * Release the memory region(s) being used by 'port'.
- */
-static void pnx8xxx_release_port(struct uart_port *port)
-{
-	struct pnx8xxx_port *sport =
-		container_of(port, struct pnx8xxx_port, port);
-
-	release_mem_region(sport->port.mapbase, UART_PORT_SIZE);
-}
-
-/*
- * Request the memory region(s) being used by 'port'.
- */
-static int pnx8xxx_request_port(struct uart_port *port)
-{
-	struct pnx8xxx_port *sport =
-		container_of(port, struct pnx8xxx_port, port);
-	return request_mem_region(sport->port.mapbase, UART_PORT_SIZE,
-			"pnx8xxx-uart") != NULL ? 0 : -EBUSY;
-}
-
-/*
- * Configure/autoconfigure the port.
- */
-static void pnx8xxx_config_port(struct uart_port *port, int flags)
-{
-	struct pnx8xxx_port *sport =
-		container_of(port, struct pnx8xxx_port, port);
-
-	if (flags & UART_CONFIG_TYPE &&
-	    pnx8xxx_request_port(&sport->port) == 0)
-		sport->port.type = PORT_PNX8XXX;
-}
-
-/*
- * Verify the new serial_struct (for TIOCSSERIAL).
- * The only change we allow are to the flags and type, and
- * even then only between PORT_PNX8XXX and PORT_UNKNOWN
- */
-static int
-pnx8xxx_verify_port(struct uart_port *port, struct serial_struct *ser)
-{
-	struct pnx8xxx_port *sport =
-		container_of(port, struct pnx8xxx_port,	port);
-	int ret = 0;
-
-	if (ser->type != PORT_UNKNOWN && ser->type != PORT_PNX8XXX)
-		ret = -EINVAL;
-	if (sport->port.irq != ser->irq)
-		ret = -EINVAL;
-	if (ser->io_type != SERIAL_IO_MEM)
-		ret = -EINVAL;
-	if (sport->port.uartclk / 16 != ser->baud_base)
-		ret = -EINVAL;
-	if ((void *)sport->port.mapbase != ser->iomem_base)
-		ret = -EINVAL;
-	if (sport->port.iobase != ser->port)
-		ret = -EINVAL;
-	if (ser->hub6 != 0)
-		ret = -EINVAL;
-	return ret;
-}
-
-static const struct uart_ops pnx8xxx_pops = {
-	.tx_empty	= pnx8xxx_tx_empty,
-	.set_mctrl	= pnx8xxx_set_mctrl,
-	.get_mctrl	= pnx8xxx_get_mctrl,
-	.stop_tx	= pnx8xxx_stop_tx,
-	.start_tx	= pnx8xxx_start_tx,
-	.stop_rx	= pnx8xxx_stop_rx,
-	.enable_ms	= pnx8xxx_enable_ms,
-	.break_ctl	= pnx8xxx_break_ctl,
-	.startup	= pnx8xxx_startup,
-	.shutdown	= pnx8xxx_shutdown,
-	.set_termios	= pnx8xxx_set_termios,
-	.type		= pnx8xxx_type,
-	.release_port	= pnx8xxx_release_port,
-	.request_port	= pnx8xxx_request_port,
-	.config_port	= pnx8xxx_config_port,
-	.verify_port	= pnx8xxx_verify_port,
-};
-
-
-/*
- * Setup the PNX8XXX serial ports.
- *
- * Note also that we support "console=ttySx" where "x" is either 0 or 1.
- */
-static void __init pnx8xxx_init_ports(void)
-{
-	static int first = 1;
-	int i;
-
-	if (!first)
-		return;
-	first = 0;
-
-	for (i = 0; i < NR_PORTS; i++) {
-		timer_setup(&pnx8xxx_ports[i].timer, pnx8xxx_timeout, 0);
-		pnx8xxx_ports[i].port.ops = &pnx8xxx_pops;
-	}
-}
-
-#ifdef CONFIG_SERIAL_PNX8XXX_CONSOLE
-
-static void pnx8xxx_console_putchar(struct uart_port *port, int ch)
-{
-	struct pnx8xxx_port *sport =
-		container_of(port, struct pnx8xxx_port, port);
-	int status;
-
-	do {
-		/* Wait for UART_TX register to empty */
-		status = serial_in(sport, PNX8XXX_FIFO);
-	} while (status & PNX8XXX_UART_FIFO_TXFIFO);
-	serial_out(sport, PNX8XXX_FIFO, ch);
-}
-
-/*
- * Interrupts are disabled on entering
- */static void
-pnx8xxx_console_write(struct console *co, const char *s, unsigned int count)
-{
-	struct pnx8xxx_port *sport = &pnx8xxx_ports[co->index];
-	unsigned int old_ien, status;
-
-	/*
-	 *	First, save IEN and then disable interrupts
-	 */
-	old_ien = serial_in(sport, PNX8XXX_IEN);
-	serial_out(sport, PNX8XXX_IEN, old_ien & ~(PNX8XXX_UART_INT_ALLTX |
-					PNX8XXX_UART_INT_ALLRX));
-
-	uart_console_write(&sport->port, s, count, pnx8xxx_console_putchar);
-
-	/*
-	 *	Finally, wait for transmitter to become empty
-	 *	and restore IEN
-	 */
-	do {
-		/* Wait for UART_TX register to empty */
-		status = serial_in(sport, PNX8XXX_FIFO);
-	} while (status & PNX8XXX_UART_FIFO_TXFIFO);
-
-	/* Clear TX and EMPTY interrupt */
-	serial_out(sport, PNX8XXX_ICLR, PNX8XXX_UART_INT_TX |
-			     PNX8XXX_UART_INT_EMPTY);
-
-	serial_out(sport, PNX8XXX_IEN, old_ien);
-}
-
-static int __init
-pnx8xxx_console_setup(struct console *co, char *options)
-{
-	struct pnx8xxx_port *sport;
-	int baud = 38400;
-	int bits = 8;
-	int parity = 'n';
-	int flow = 'n';
-
-	/*
-	 * Check whether an invalid uart number has been specified, and
-	 * if so, search for the first available port that does have
-	 * console support.
-	 */
-	if (co->index == -1 || co->index >= NR_PORTS)
-		co->index = 0;
-	sport = &pnx8xxx_ports[co->index];
-
-	if (options)
-		uart_parse_options(options, &baud, &parity, &bits, &flow);
-
-	return uart_set_options(&sport->port, co, baud, parity, bits, flow);
-}
-
-static struct uart_driver pnx8xxx_reg;
-static struct console pnx8xxx_console = {
-	.name		= "ttyS",
-	.write		= pnx8xxx_console_write,
-	.device		= uart_console_device,
-	.setup		= pnx8xxx_console_setup,
-	.flags		= CON_PRINTBUFFER,
-	.index		= -1,
-	.data		= &pnx8xxx_reg,
-};
-
-static int __init pnx8xxx_rs_console_init(void)
-{
-	pnx8xxx_init_ports();
-	register_console(&pnx8xxx_console);
-	return 0;
-}
-console_initcall(pnx8xxx_rs_console_init);
-
-#define PNX8XXX_CONSOLE	&pnx8xxx_console
-#else
-#define PNX8XXX_CONSOLE	NULL
-#endif
-
-static struct uart_driver pnx8xxx_reg = {
-	.owner			= THIS_MODULE,
-	.driver_name		= "ttyS",
-	.dev_name		= "ttyS",
-	.major			= SERIAL_PNX8XXX_MAJOR,
-	.minor			= MINOR_START,
-	.nr			= NR_PORTS,
-	.cons			= PNX8XXX_CONSOLE,
-};
-
-static int pnx8xxx_serial_suspend(struct platform_device *pdev, pm_message_t state)
-{
-	struct pnx8xxx_port *sport = platform_get_drvdata(pdev);
-
-	return uart_suspend_port(&pnx8xxx_reg, &sport->port);
-}
-
-static int pnx8xxx_serial_resume(struct platform_device *pdev)
-{
-	struct pnx8xxx_port *sport = platform_get_drvdata(pdev);
-
-	return uart_resume_port(&pnx8xxx_reg, &sport->port);
-}
-
-static int pnx8xxx_serial_probe(struct platform_device *pdev)
-{
-	struct resource *res = pdev->resource;
-	int i;
-
-	for (i = 0; i < pdev->num_resources; i++, res++) {
-		if (!(res->flags & IORESOURCE_MEM))
-			continue;
-
-		for (i = 0; i < NR_PORTS; i++) {
-			if (pnx8xxx_ports[i].port.mapbase != res->start)
-				continue;
-
-			pnx8xxx_ports[i].port.has_sysrq = IS_ENABLED(CONFIG_SERIAL_PNX8XXX_CONSOLE);
-			pnx8xxx_ports[i].port.dev = &pdev->dev;
-			uart_add_one_port(&pnx8xxx_reg, &pnx8xxx_ports[i].port);
-			platform_set_drvdata(pdev, &pnx8xxx_ports[i]);
-			break;
-		}
-	}
-
-	return 0;
-}
-
-static int pnx8xxx_serial_remove(struct platform_device *pdev)
-{
-	struct pnx8xxx_port *sport = platform_get_drvdata(pdev);
-
-	if (sport)
-		uart_remove_one_port(&pnx8xxx_reg, &sport->port);
-
-	return 0;
-}
-
-static struct platform_driver pnx8xxx_serial_driver = {
-	.driver		= {
-		.name	= "pnx8xxx-uart",
-	},
-	.probe		= pnx8xxx_serial_probe,
-	.remove		= pnx8xxx_serial_remove,
-	.suspend	= pnx8xxx_serial_suspend,
-	.resume		= pnx8xxx_serial_resume,
-};
-
-static int __init pnx8xxx_serial_init(void)
-{
-	int ret;
-
-	printk(KERN_INFO "Serial: PNX8XXX driver\n");
-
-	pnx8xxx_init_ports();
-
-	ret = uart_register_driver(&pnx8xxx_reg);
-	if (ret == 0) {
-		ret = platform_driver_register(&pnx8xxx_serial_driver);
-		if (ret)
-			uart_unregister_driver(&pnx8xxx_reg);
-	}
-	return ret;
-}
-
-static void __exit pnx8xxx_serial_exit(void)
-{
-	platform_driver_unregister(&pnx8xxx_serial_driver);
-	uart_unregister_driver(&pnx8xxx_reg);
-}
-
-module_init(pnx8xxx_serial_init);
-module_exit(pnx8xxx_serial_exit);
-
-MODULE_AUTHOR("Embedded Alley Solutions, Inc.");
-MODULE_DESCRIPTION("PNX8XXX SoCs serial port driver");
-MODULE_LICENSE("GPL");
-MODULE_ALIAS_CHARDEV_MAJOR(SERIAL_PNX8XXX_MAJOR);
-MODULE_ALIAS("platform:pnx8xxx-uart");
diff --git a/include/linux/serial_pnx8xxx.h b/include/linux/serial_pnx8xxx.h
deleted file mode 100644
index 619d748dcd44..000000000000
--- a/include/linux/serial_pnx8xxx.h
+++ /dev/null
@@ -1,67 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Embedded Alley Solutions, source@embeddedalley.com.
- */
-
-#ifndef _LINUX_SERIAL_PNX8XXX_H
-#define _LINUX_SERIAL_PNX8XXX_H
-
-#include <linux/serial_core.h>
-
-#define PNX8XXX_NR_PORTS	2
-
-struct pnx8xxx_port {
-	struct uart_port	port;
-	struct timer_list	timer;
-	unsigned int		old_status;
-};
-
-/* register offsets */
-#define PNX8XXX_LCR		0
-#define PNX8XXX_MCR		0x004
-#define PNX8XXX_BAUD		0x008
-#define PNX8XXX_CFG		0x00c
-#define PNX8XXX_FIFO		0x028
-#define PNX8XXX_ISTAT		0xfe0
-#define PNX8XXX_IEN		0xfe4
-#define PNX8XXX_ICLR		0xfe8
-#define PNX8XXX_ISET		0xfec
-#define PNX8XXX_PD		0xff4
-#define PNX8XXX_MID		0xffc
-
-#define PNX8XXX_UART_LCR_TXBREAK	(1<<30)
-#define PNX8XXX_UART_LCR_PAREVN		0x10000000
-#define PNX8XXX_UART_LCR_PAREN		0x08000000
-#define PNX8XXX_UART_LCR_2STOPB		0x04000000
-#define PNX8XXX_UART_LCR_8BIT		0x01000000
-#define PNX8XXX_UART_LCR_TX_RST		0x00040000
-#define PNX8XXX_UART_LCR_RX_RST		0x00020000
-#define PNX8XXX_UART_LCR_RX_NEXT	0x00010000
-
-#define PNX8XXX_UART_MCR_SCR		0xFF000000
-#define PNX8XXX_UART_MCR_DCD		0x00800000
-#define PNX8XXX_UART_MCR_CTS		0x00100000
-#define PNX8XXX_UART_MCR_LOOP		0x00000010
-#define PNX8XXX_UART_MCR_RTS		0x00000002
-#define PNX8XXX_UART_MCR_DTR		0x00000001
-
-#define PNX8XXX_UART_INT_TX		0x00000080
-#define PNX8XXX_UART_INT_EMPTY		0x00000040
-#define PNX8XXX_UART_INT_RCVTO		0x00000020
-#define PNX8XXX_UART_INT_RX		0x00000010
-#define PNX8XXX_UART_INT_RXOVRN		0x00000008
-#define PNX8XXX_UART_INT_FRERR		0x00000004
-#define PNX8XXX_UART_INT_BREAK		0x00000002
-#define PNX8XXX_UART_INT_PARITY		0x00000001
-#define PNX8XXX_UART_INT_ALLRX		0x0000003F
-#define PNX8XXX_UART_INT_ALLTX		0x000000C0
-
-#define PNX8XXX_UART_FIFO_TXFIFO	0x001F0000
-#define PNX8XXX_UART_FIFO_TXFIFO_STA	(0x1f<<16)
-#define PNX8XXX_UART_FIFO_RXBRK		0x00008000
-#define PNX8XXX_UART_FIFO_RXFE		0x00004000
-#define PNX8XXX_UART_FIFO_RXPAR		0x00002000
-#define PNX8XXX_UART_FIFO_RXFIFO	0x00001F00
-#define PNX8XXX_UART_FIFO_RBRTHR	0x000000FF
-
-#endif
diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h
index 851b982f8c4b..62c22045fe65 100644
--- a/include/uapi/linux/serial_core.h
+++ b/include/uapi/linux/serial_core.h
@@ -134,8 +134,6 @@
 /*Digi jsm */
 #define PORT_JSM        69
 
-#define PORT_PNX8XXX	70
-
 /* SUN4V Hypervisor Console */
 #define PORT_SUNHV	72
 
-- 
cgit v1.2.3


From 4cf1bc1f10452065a29d576fc5693fc4fab5b919 Mon Sep 17 00:00:00 2001
From: KP Singh <kpsingh@google.com>
Date: Fri, 6 Nov 2020 10:37:40 +0000
Subject: bpf: Implement task local storage

Similar to bpf_local_storage for sockets and inodes add local storage
for task_struct.

The life-cycle of storage is managed with the life-cycle of the
task_struct.  i.e. the storage is destroyed along with the owning task
with a callback to the bpf_task_storage_free from the task_free LSM
hook.

The BPF LSM allocates an __rcu pointer to the bpf_local_storage in
the security blob which are now stackable and can co-exist with other
LSMs.

The userspace map operations can be done by using a pid fd as a key
passed to the lookup, update and delete operations.

Signed-off-by: KP Singh <kpsingh@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20201106103747.2780972-3-kpsingh@chromium.org
---
 include/linux/bpf_lsm.h        |  23 +++
 include/linux/bpf_types.h      |   1 +
 include/uapi/linux/bpf.h       |  39 +++++
 kernel/bpf/Makefile            |   1 +
 kernel/bpf/bpf_lsm.c           |   4 +
 kernel/bpf/bpf_task_storage.c  | 315 +++++++++++++++++++++++++++++++++++++++++
 kernel/bpf/syscall.c           |   3 +-
 kernel/bpf/verifier.c          |  10 ++
 security/bpf/hooks.c           |   2 +
 tools/include/uapi/linux/bpf.h |  39 +++++
 10 files changed, 436 insertions(+), 1 deletion(-)
 create mode 100644 kernel/bpf/bpf_task_storage.c

(limited to 'include/linux')

diff --git a/include/linux/bpf_lsm.h b/include/linux/bpf_lsm.h
index aaacb6aafc87..73226181b744 100644
--- a/include/linux/bpf_lsm.h
+++ b/include/linux/bpf_lsm.h
@@ -7,6 +7,7 @@
 #ifndef _LINUX_BPF_LSM_H
 #define _LINUX_BPF_LSM_H
 
+#include <linux/sched.h>
 #include <linux/bpf.h>
 #include <linux/lsm_hooks.h>
 
@@ -35,9 +36,21 @@ static inline struct bpf_storage_blob *bpf_inode(
 	return inode->i_security + bpf_lsm_blob_sizes.lbs_inode;
 }
 
+static inline struct bpf_storage_blob *bpf_task(
+	const struct task_struct *task)
+{
+	if (unlikely(!task->security))
+		return NULL;
+
+	return task->security + bpf_lsm_blob_sizes.lbs_task;
+}
+
 extern const struct bpf_func_proto bpf_inode_storage_get_proto;
 extern const struct bpf_func_proto bpf_inode_storage_delete_proto;
+extern const struct bpf_func_proto bpf_task_storage_get_proto;
+extern const struct bpf_func_proto bpf_task_storage_delete_proto;
 void bpf_inode_storage_free(struct inode *inode);
+void bpf_task_storage_free(struct task_struct *task);
 
 #else /* !CONFIG_BPF_LSM */
 
@@ -53,10 +66,20 @@ static inline struct bpf_storage_blob *bpf_inode(
 	return NULL;
 }
 
+static inline struct bpf_storage_blob *bpf_task(
+	const struct task_struct *task)
+{
+	return NULL;
+}
+
 static inline void bpf_inode_storage_free(struct inode *inode)
 {
 }
 
+static inline void bpf_task_storage_free(struct task_struct *task)
+{
+}
+
 #endif /* CONFIG_BPF_LSM */
 
 #endif /* _LINUX_BPF_LSM_H */
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 2e6f568377f1..99f7fd657d87 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -109,6 +109,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKHASH, sock_hash_ops)
 #endif
 #ifdef CONFIG_BPF_LSM
 BPF_MAP_TYPE(BPF_MAP_TYPE_INODE_STORAGE, inode_storage_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_TASK_STORAGE, task_storage_map_ops)
 #endif
 BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops)
 #if defined(CONFIG_XDP_SOCKETS)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index e6ceac3f7d62..f4037b2161a6 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -157,6 +157,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_STRUCT_OPS,
 	BPF_MAP_TYPE_RINGBUF,
 	BPF_MAP_TYPE_INODE_STORAGE,
+	BPF_MAP_TYPE_TASK_STORAGE,
 };
 
 /* Note that tracing related programs such as
@@ -3742,6 +3743,42 @@ union bpf_attr {
  * 	Return
  * 		The helper returns **TC_ACT_REDIRECT** on success or
  * 		**TC_ACT_SHOT** on error.
+ *
+ * void *bpf_task_storage_get(struct bpf_map *map, struct task_struct *task, void *value, u64 flags)
+ *	Description
+ *		Get a bpf_local_storage from the *task*.
+ *
+ *		Logically, it could be thought of as getting the value from
+ *		a *map* with *task* as the **key**.  From this
+ *		perspective,  the usage is not much different from
+ *		**bpf_map_lookup_elem**\ (*map*, **&**\ *task*) except this
+ *		helper enforces the key must be an task_struct and the map must also
+ *		be a **BPF_MAP_TYPE_TASK_STORAGE**.
+ *
+ *		Underneath, the value is stored locally at *task* instead of
+ *		the *map*.  The *map* is used as the bpf-local-storage
+ *		"type". The bpf-local-storage "type" (i.e. the *map*) is
+ *		searched against all bpf_local_storage residing at *task*.
+ *
+ *		An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be
+ *		used such that a new bpf_local_storage will be
+ *		created if one does not exist.  *value* can be used
+ *		together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify
+ *		the initial value of a bpf_local_storage.  If *value* is
+ *		**NULL**, the new bpf_local_storage will be zero initialized.
+ *	Return
+ *		A bpf_local_storage pointer is returned on success.
+ *
+ *		**NULL** if not found or there was an error in adding
+ *		a new bpf_local_storage.
+ *
+ * long bpf_task_storage_delete(struct bpf_map *map, struct task_struct *task)
+ *	Description
+ *		Delete a bpf_local_storage from a *task*.
+ *	Return
+ *		0 on success.
+ *
+ *		**-ENOENT** if the bpf_local_storage cannot be found.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3900,6 +3937,8 @@ union bpf_attr {
 	FN(bpf_per_cpu_ptr),            \
 	FN(bpf_this_cpu_ptr),		\
 	FN(redirect_peer),		\
+	FN(task_storage_get),		\
+	FN(task_storage_delete),	\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index bdc8cd1b6767..f0b93ced5a7f 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -6,6 +6,7 @@ obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_i
 obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
 obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o
 obj-${CONFIG_BPF_LSM}	  += bpf_inode_storage.o
+obj-${CONFIG_BPF_LSM}	  += bpf_task_storage.o
 obj-$(CONFIG_BPF_SYSCALL) += disasm.o
 obj-$(CONFIG_BPF_JIT) += trampoline.o
 obj-$(CONFIG_BPF_SYSCALL) += btf.o
diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
index cd8a617f2109..e92c51bebb47 100644
--- a/kernel/bpf/bpf_lsm.c
+++ b/kernel/bpf/bpf_lsm.c
@@ -63,6 +63,10 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_spin_lock_proto;
 	case BPF_FUNC_spin_unlock:
 		return &bpf_spin_unlock_proto;
+	case BPF_FUNC_task_storage_get:
+		return &bpf_task_storage_get_proto;
+	case BPF_FUNC_task_storage_delete:
+		return &bpf_task_storage_delete_proto;
 	default:
 		return tracing_prog_func_proto(func_id, prog);
 	}
diff --git a/kernel/bpf/bpf_task_storage.c b/kernel/bpf/bpf_task_storage.c
new file mode 100644
index 000000000000..39a45fba4fb0
--- /dev/null
+++ b/kernel/bpf/bpf_task_storage.c
@@ -0,0 +1,315 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2020 Facebook
+ * Copyright 2020 Google LLC.
+ */
+
+#include <linux/pid.h>
+#include <linux/sched.h>
+#include <linux/rculist.h>
+#include <linux/list.h>
+#include <linux/hash.h>
+#include <linux/types.h>
+#include <linux/spinlock.h>
+#include <linux/bpf.h>
+#include <linux/bpf_local_storage.h>
+#include <linux/filter.h>
+#include <uapi/linux/btf.h>
+#include <linux/bpf_lsm.h>
+#include <linux/btf_ids.h>
+#include <linux/fdtable.h>
+
+DEFINE_BPF_STORAGE_CACHE(task_cache);
+
+static struct bpf_local_storage __rcu **task_storage_ptr(void *owner)
+{
+	struct task_struct *task = owner;
+	struct bpf_storage_blob *bsb;
+
+	bsb = bpf_task(task);
+	if (!bsb)
+		return NULL;
+	return &bsb->storage;
+}
+
+static struct bpf_local_storage_data *
+task_storage_lookup(struct task_struct *task, struct bpf_map *map,
+		    bool cacheit_lockit)
+{
+	struct bpf_local_storage *task_storage;
+	struct bpf_local_storage_map *smap;
+	struct bpf_storage_blob *bsb;
+
+	bsb = bpf_task(task);
+	if (!bsb)
+		return NULL;
+
+	task_storage = rcu_dereference(bsb->storage);
+	if (!task_storage)
+		return NULL;
+
+	smap = (struct bpf_local_storage_map *)map;
+	return bpf_local_storage_lookup(task_storage, smap, cacheit_lockit);
+}
+
+void bpf_task_storage_free(struct task_struct *task)
+{
+	struct bpf_local_storage_elem *selem;
+	struct bpf_local_storage *local_storage;
+	bool free_task_storage = false;
+	struct bpf_storage_blob *bsb;
+	struct hlist_node *n;
+
+	bsb = bpf_task(task);
+	if (!bsb)
+		return;
+
+	rcu_read_lock();
+
+	local_storage = rcu_dereference(bsb->storage);
+	if (!local_storage) {
+		rcu_read_unlock();
+		return;
+	}
+
+	/* Neither the bpf_prog nor the bpf-map's syscall
+	 * could be modifying the local_storage->list now.
+	 * Thus, no elem can be added-to or deleted-from the
+	 * local_storage->list by the bpf_prog or by the bpf-map's syscall.
+	 *
+	 * It is racing with bpf_local_storage_map_free() alone
+	 * when unlinking elem from the local_storage->list and
+	 * the map's bucket->list.
+	 */
+	raw_spin_lock_bh(&local_storage->lock);
+	hlist_for_each_entry_safe(selem, n, &local_storage->list, snode) {
+		/* Always unlink from map before unlinking from
+		 * local_storage.
+		 */
+		bpf_selem_unlink_map(selem);
+		free_task_storage = bpf_selem_unlink_storage_nolock(
+			local_storage, selem, false);
+	}
+	raw_spin_unlock_bh(&local_storage->lock);
+	rcu_read_unlock();
+
+	/* free_task_storage should always be true as long as
+	 * local_storage->list was non-empty.
+	 */
+	if (free_task_storage)
+		kfree_rcu(local_storage, rcu);
+}
+
+static void *bpf_pid_task_storage_lookup_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_local_storage_data *sdata;
+	struct task_struct *task;
+	unsigned int f_flags;
+	struct pid *pid;
+	int fd, err;
+
+	fd = *(int *)key;
+	pid = pidfd_get_pid(fd, &f_flags);
+	if (IS_ERR(pid))
+		return ERR_CAST(pid);
+
+	/* We should be in an RCU read side critical section, it should be safe
+	 * to call pid_task.
+	 */
+	WARN_ON_ONCE(!rcu_read_lock_held());
+	task = pid_task(pid, PIDTYPE_PID);
+	if (!task) {
+		err = -ENOENT;
+		goto out;
+	}
+
+	sdata = task_storage_lookup(task, map, true);
+	put_pid(pid);
+	return sdata ? sdata->data : NULL;
+out:
+	put_pid(pid);
+	return ERR_PTR(err);
+}
+
+static int bpf_pid_task_storage_update_elem(struct bpf_map *map, void *key,
+					    void *value, u64 map_flags)
+{
+	struct bpf_local_storage_data *sdata;
+	struct task_struct *task;
+	unsigned int f_flags;
+	struct pid *pid;
+	int fd, err;
+
+	fd = *(int *)key;
+	pid = pidfd_get_pid(fd, &f_flags);
+	if (IS_ERR(pid))
+		return PTR_ERR(pid);
+
+	/* We should be in an RCU read side critical section, it should be safe
+	 * to call pid_task.
+	 */
+	WARN_ON_ONCE(!rcu_read_lock_held());
+	task = pid_task(pid, PIDTYPE_PID);
+	if (!task) {
+		err = -ENOENT;
+		goto out;
+	}
+
+	sdata = bpf_local_storage_update(
+		task, (struct bpf_local_storage_map *)map, value, map_flags);
+
+	err = PTR_ERR_OR_ZERO(sdata);
+out:
+	put_pid(pid);
+	return err;
+}
+
+static int task_storage_delete(struct task_struct *task, struct bpf_map *map)
+{
+	struct bpf_local_storage_data *sdata;
+
+	sdata = task_storage_lookup(task, map, false);
+	if (!sdata)
+		return -ENOENT;
+
+	bpf_selem_unlink(SELEM(sdata));
+
+	return 0;
+}
+
+static int bpf_pid_task_storage_delete_elem(struct bpf_map *map, void *key)
+{
+	struct task_struct *task;
+	unsigned int f_flags;
+	struct pid *pid;
+	int fd, err;
+
+	fd = *(int *)key;
+	pid = pidfd_get_pid(fd, &f_flags);
+	if (IS_ERR(pid))
+		return PTR_ERR(pid);
+
+	/* We should be in an RCU read side critical section, it should be safe
+	 * to call pid_task.
+	 */
+	WARN_ON_ONCE(!rcu_read_lock_held());
+	task = pid_task(pid, PIDTYPE_PID);
+	if (!task) {
+		err = -ENOENT;
+		goto out;
+	}
+
+	err = task_storage_delete(task, map);
+out:
+	put_pid(pid);
+	return err;
+}
+
+BPF_CALL_4(bpf_task_storage_get, struct bpf_map *, map, struct task_struct *,
+	   task, void *, value, u64, flags)
+{
+	struct bpf_local_storage_data *sdata;
+
+	if (flags & ~(BPF_LOCAL_STORAGE_GET_F_CREATE))
+		return (unsigned long)NULL;
+
+	/* explicitly check that the task_storage_ptr is not
+	 * NULL as task_storage_lookup returns NULL in this case and
+	 * bpf_local_storage_update expects the owner to have a
+	 * valid storage pointer.
+	 */
+	if (!task_storage_ptr(task))
+		return (unsigned long)NULL;
+
+	sdata = task_storage_lookup(task, map, true);
+	if (sdata)
+		return (unsigned long)sdata->data;
+
+	/* This helper must only be called from places where the lifetime of the task
+	 * is guaranteed. Either by being refcounted or by being protected
+	 * by an RCU read-side critical section.
+	 */
+	if (flags & BPF_LOCAL_STORAGE_GET_F_CREATE) {
+		sdata = bpf_local_storage_update(
+			task, (struct bpf_local_storage_map *)map, value,
+			BPF_NOEXIST);
+		return IS_ERR(sdata) ? (unsigned long)NULL :
+					     (unsigned long)sdata->data;
+	}
+
+	return (unsigned long)NULL;
+}
+
+BPF_CALL_2(bpf_task_storage_delete, struct bpf_map *, map, struct task_struct *,
+	   task)
+{
+	/* This helper must only be called from places where the lifetime of the task
+	 * is guaranteed. Either by being refcounted or by being protected
+	 * by an RCU read-side critical section.
+	 */
+	return task_storage_delete(task, map);
+}
+
+static int notsupp_get_next_key(struct bpf_map *map, void *key, void *next_key)
+{
+	return -ENOTSUPP;
+}
+
+static struct bpf_map *task_storage_map_alloc(union bpf_attr *attr)
+{
+	struct bpf_local_storage_map *smap;
+
+	smap = bpf_local_storage_map_alloc(attr);
+	if (IS_ERR(smap))
+		return ERR_CAST(smap);
+
+	smap->cache_idx = bpf_local_storage_cache_idx_get(&task_cache);
+	return &smap->map;
+}
+
+static void task_storage_map_free(struct bpf_map *map)
+{
+	struct bpf_local_storage_map *smap;
+
+	smap = (struct bpf_local_storage_map *)map;
+	bpf_local_storage_cache_idx_free(&task_cache, smap->cache_idx);
+	bpf_local_storage_map_free(smap);
+}
+
+static int task_storage_map_btf_id;
+const struct bpf_map_ops task_storage_map_ops = {
+	.map_meta_equal = bpf_map_meta_equal,
+	.map_alloc_check = bpf_local_storage_map_alloc_check,
+	.map_alloc = task_storage_map_alloc,
+	.map_free = task_storage_map_free,
+	.map_get_next_key = notsupp_get_next_key,
+	.map_lookup_elem = bpf_pid_task_storage_lookup_elem,
+	.map_update_elem = bpf_pid_task_storage_update_elem,
+	.map_delete_elem = bpf_pid_task_storage_delete_elem,
+	.map_check_btf = bpf_local_storage_map_check_btf,
+	.map_btf_name = "bpf_local_storage_map",
+	.map_btf_id = &task_storage_map_btf_id,
+	.map_owner_storage_ptr = task_storage_ptr,
+};
+
+BTF_ID_LIST_SINGLE(bpf_task_storage_btf_ids, struct, task_struct)
+
+const struct bpf_func_proto bpf_task_storage_get_proto = {
+	.func = bpf_task_storage_get,
+	.gpl_only = false,
+	.ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL,
+	.arg1_type = ARG_CONST_MAP_PTR,
+	.arg2_type = ARG_PTR_TO_BTF_ID,
+	.arg2_btf_id = &bpf_task_storage_btf_ids[0],
+	.arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL,
+	.arg4_type = ARG_ANYTHING,
+};
+
+const struct bpf_func_proto bpf_task_storage_delete_proto = {
+	.func = bpf_task_storage_delete,
+	.gpl_only = false,
+	.ret_type = RET_INTEGER,
+	.arg1_type = ARG_CONST_MAP_PTR,
+	.arg2_type = ARG_PTR_TO_BTF_ID,
+	.arg2_btf_id = &bpf_task_storage_btf_ids[0],
+};
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 8f50c9c19f1b..f3fe9f53f93c 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -773,7 +773,8 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
 		    map->map_type != BPF_MAP_TYPE_ARRAY &&
 		    map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE &&
 		    map->map_type != BPF_MAP_TYPE_SK_STORAGE &&
-		    map->map_type != BPF_MAP_TYPE_INODE_STORAGE)
+		    map->map_type != BPF_MAP_TYPE_INODE_STORAGE &&
+		    map->map_type != BPF_MAP_TYPE_TASK_STORAGE)
 			return -ENOTSUPP;
 		if (map->spin_lock_off + sizeof(struct bpf_spin_lock) >
 		    map->value_size) {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index f863aa84d0a2..00960f6a83ec 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4469,6 +4469,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		    func_id != BPF_FUNC_inode_storage_delete)
 			goto error;
 		break;
+	case BPF_MAP_TYPE_TASK_STORAGE:
+		if (func_id != BPF_FUNC_task_storage_get &&
+		    func_id != BPF_FUNC_task_storage_delete)
+			goto error;
+		break;
 	default:
 		break;
 	}
@@ -4547,6 +4552,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		if (map->map_type != BPF_MAP_TYPE_INODE_STORAGE)
 			goto error;
 		break;
+	case BPF_FUNC_task_storage_get:
+	case BPF_FUNC_task_storage_delete:
+		if (map->map_type != BPF_MAP_TYPE_TASK_STORAGE)
+			goto error;
+		break;
 	default:
 		break;
 	}
diff --git a/security/bpf/hooks.c b/security/bpf/hooks.c
index 788667d582ae..e5971fa74fd7 100644
--- a/security/bpf/hooks.c
+++ b/security/bpf/hooks.c
@@ -12,6 +12,7 @@ static struct security_hook_list bpf_lsm_hooks[] __lsm_ro_after_init = {
 	#include <linux/lsm_hook_defs.h>
 	#undef LSM_HOOK
 	LSM_HOOK_INIT(inode_free_security, bpf_inode_storage_free),
+	LSM_HOOK_INIT(task_free, bpf_task_storage_free),
 };
 
 static int __init bpf_lsm_init(void)
@@ -23,6 +24,7 @@ static int __init bpf_lsm_init(void)
 
 struct lsm_blob_sizes bpf_lsm_blob_sizes __lsm_ro_after_init = {
 	.lbs_inode = sizeof(struct bpf_storage_blob),
+	.lbs_task = sizeof(struct bpf_storage_blob),
 };
 
 DEFINE_LSM(bpf) = {
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index e6ceac3f7d62..f4037b2161a6 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -157,6 +157,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_STRUCT_OPS,
 	BPF_MAP_TYPE_RINGBUF,
 	BPF_MAP_TYPE_INODE_STORAGE,
+	BPF_MAP_TYPE_TASK_STORAGE,
 };
 
 /* Note that tracing related programs such as
@@ -3742,6 +3743,42 @@ union bpf_attr {
  * 	Return
  * 		The helper returns **TC_ACT_REDIRECT** on success or
  * 		**TC_ACT_SHOT** on error.
+ *
+ * void *bpf_task_storage_get(struct bpf_map *map, struct task_struct *task, void *value, u64 flags)
+ *	Description
+ *		Get a bpf_local_storage from the *task*.
+ *
+ *		Logically, it could be thought of as getting the value from
+ *		a *map* with *task* as the **key**.  From this
+ *		perspective,  the usage is not much different from
+ *		**bpf_map_lookup_elem**\ (*map*, **&**\ *task*) except this
+ *		helper enforces the key must be an task_struct and the map must also
+ *		be a **BPF_MAP_TYPE_TASK_STORAGE**.
+ *
+ *		Underneath, the value is stored locally at *task* instead of
+ *		the *map*.  The *map* is used as the bpf-local-storage
+ *		"type". The bpf-local-storage "type" (i.e. the *map*) is
+ *		searched against all bpf_local_storage residing at *task*.
+ *
+ *		An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be
+ *		used such that a new bpf_local_storage will be
+ *		created if one does not exist.  *value* can be used
+ *		together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify
+ *		the initial value of a bpf_local_storage.  If *value* is
+ *		**NULL**, the new bpf_local_storage will be zero initialized.
+ *	Return
+ *		A bpf_local_storage pointer is returned on success.
+ *
+ *		**NULL** if not found or there was an error in adding
+ *		a new bpf_local_storage.
+ *
+ * long bpf_task_storage_delete(struct bpf_map *map, struct task_struct *task)
+ *	Description
+ *		Delete a bpf_local_storage from a *task*.
+ *	Return
+ *		0 on success.
+ *
+ *		**-ENOENT** if the bpf_local_storage cannot be found.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3900,6 +3937,8 @@ union bpf_attr {
 	FN(bpf_per_cpu_ptr),            \
 	FN(bpf_this_cpu_ptr),		\
 	FN(redirect_peer),		\
+	FN(task_storage_get),		\
+	FN(task_storage_delete),	\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
-- 
cgit v1.2.3


From 3ca1032ab7ab010eccb107aa515598788f7d93bb Mon Sep 17 00:00:00 2001
From: KP Singh <kpsingh@google.com>
Date: Fri, 6 Nov 2020 10:37:43 +0000
Subject: bpf: Implement get_current_task_btf and RET_PTR_TO_BTF_ID

The currently available bpf_get_current_task returns an unsigned integer
which can be used along with BPF_CORE_READ to read data from
the task_struct but still cannot be used as an input argument to a
helper that accepts an ARG_PTR_TO_BTF_ID of type task_struct.

In order to implement this helper a new return type, RET_PTR_TO_BTF_ID,
is added. This is similar to RET_PTR_TO_BTF_ID_OR_NULL but does not
require checking the nullness of returned pointer.

Signed-off-by: KP Singh <kpsingh@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20201106103747.2780972-6-kpsingh@chromium.org
---
 include/linux/bpf.h            |  1 +
 include/uapi/linux/bpf.h       |  9 +++++++++
 kernel/bpf/verifier.c          |  7 +++++--
 kernel/trace/bpf_trace.c       | 16 ++++++++++++++++
 tools/include/uapi/linux/bpf.h |  9 +++++++++
 5 files changed, 40 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 2fffd30e13ac..73d5381a5d5c 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -310,6 +310,7 @@ enum bpf_return_type {
 	RET_PTR_TO_BTF_ID_OR_NULL,	/* returns a pointer to a btf_id or NULL */
 	RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL, /* returns a pointer to a valid memory or a btf_id or NULL */
 	RET_PTR_TO_MEM_OR_BTF_ID,	/* returns a pointer to a valid memory or a btf_id */
+	RET_PTR_TO_BTF_ID,		/* returns a pointer to a btf_id */
 };
 
 /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index f4037b2161a6..9879d6793e90 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3779,6 +3779,14 @@ union bpf_attr {
  *		0 on success.
  *
  *		**-ENOENT** if the bpf_local_storage cannot be found.
+ *
+ * struct task_struct *bpf_get_current_task_btf(void)
+ *	Description
+ *		Return a BTF pointer to the "current" task.
+ *		This pointer can also be used in helpers that accept an
+ *		*ARG_PTR_TO_BTF_ID* of type *task_struct*.
+ *	Return
+ *		Pointer to the current task.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3939,6 +3947,7 @@ union bpf_attr {
 	FN(redirect_peer),		\
 	FN(task_storage_get),		\
 	FN(task_storage_delete),	\
+	FN(get_current_task_btf),	\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 00960f6a83ec..10da26e55130 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5186,11 +5186,14 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 				PTR_TO_BTF_ID : PTR_TO_BTF_ID_OR_NULL;
 			regs[BPF_REG_0].btf_id = meta.ret_btf_id;
 		}
-	} else if (fn->ret_type == RET_PTR_TO_BTF_ID_OR_NULL) {
+	} else if (fn->ret_type == RET_PTR_TO_BTF_ID_OR_NULL ||
+		   fn->ret_type == RET_PTR_TO_BTF_ID) {
 		int ret_btf_id;
 
 		mark_reg_known_zero(env, regs, BPF_REG_0);
-		regs[BPF_REG_0].type = PTR_TO_BTF_ID_OR_NULL;
+		regs[BPF_REG_0].type = fn->ret_type == RET_PTR_TO_BTF_ID ?
+						     PTR_TO_BTF_ID :
+						     PTR_TO_BTF_ID_OR_NULL;
 		ret_btf_id = *fn->ret_btf_id;
 		if (ret_btf_id == 0) {
 			verbose(env, "invalid return type %d of func %s#%d\n",
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 4517c8b66518..e4515b0f62a8 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1022,6 +1022,20 @@ const struct bpf_func_proto bpf_get_current_task_proto = {
 	.ret_type	= RET_INTEGER,
 };
 
+BPF_CALL_0(bpf_get_current_task_btf)
+{
+	return (unsigned long) current;
+}
+
+BTF_ID_LIST_SINGLE(bpf_get_current_btf_ids, struct, task_struct)
+
+static const struct bpf_func_proto bpf_get_current_task_btf_proto = {
+	.func		= bpf_get_current_task_btf,
+	.gpl_only	= true,
+	.ret_type	= RET_PTR_TO_BTF_ID,
+	.ret_btf_id	= &bpf_get_current_btf_ids[0],
+};
+
 BPF_CALL_2(bpf_current_task_under_cgroup, struct bpf_map *, map, u32, idx)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
@@ -1265,6 +1279,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_current_pid_tgid_proto;
 	case BPF_FUNC_get_current_task:
 		return &bpf_get_current_task_proto;
+	case BPF_FUNC_get_current_task_btf:
+		return &bpf_get_current_task_btf_proto;
 	case BPF_FUNC_get_current_uid_gid:
 		return &bpf_get_current_uid_gid_proto;
 	case BPF_FUNC_get_current_comm:
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index f4037b2161a6..9879d6793e90 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3779,6 +3779,14 @@ union bpf_attr {
  *		0 on success.
  *
  *		**-ENOENT** if the bpf_local_storage cannot be found.
+ *
+ * struct task_struct *bpf_get_current_task_btf(void)
+ *	Description
+ *		Return a BTF pointer to the "current" task.
+ *		This pointer can also be used in helpers that accept an
+ *		*ARG_PTR_TO_BTF_ID* of type *task_struct*.
+ *	Return
+ *		Pointer to the current task.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3939,6 +3947,7 @@ union bpf_attr {
 	FN(redirect_peer),		\
 	FN(task_storage_get),		\
 	FN(task_storage_delete),	\
+	FN(get_current_task_btf),	\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
-- 
cgit v1.2.3


From d4d50710a8b46082224376ef119a4dbb75b25c56 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 4 Nov 2020 09:27:33 +0100
Subject: seq_file: add seq_read_iter

iov_iter based variant for reading a seq_file.  seq_read is
reimplemented on top of the iter variant.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/seq_file.c            | 45 ++++++++++++++++++++++++++++++++-------------
 include/linux/seq_file.h |  1 +
 2 files changed, 33 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/fs/seq_file.c b/fs/seq_file.c
index 31219c1db17d..3b20e21604e7 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -18,6 +18,7 @@
 #include <linux/mm.h>
 #include <linux/printk.h>
 #include <linux/string_helpers.h>
+#include <linux/uio.h>
 
 #include <linux/uaccess.h>
 #include <asm/page.h>
@@ -146,7 +147,28 @@ Eoverflow:
  */
 ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos)
 {
-	struct seq_file *m = file->private_data;
+	struct iovec iov = { .iov_base = buf, .iov_len = size};
+	struct kiocb kiocb;
+	struct iov_iter iter;
+	ssize_t ret;
+
+	init_sync_kiocb(&kiocb, file);
+	iov_iter_init(&iter, READ, &iov, 1, size);
+
+	kiocb.ki_pos = *ppos;
+	ret = seq_read_iter(&kiocb, &iter);
+	*ppos = kiocb.ki_pos;
+	return ret;
+}
+EXPORT_SYMBOL(seq_read);
+
+/*
+ * Ready-made ->f_op->read_iter()
+ */
+ssize_t seq_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct seq_file *m = iocb->ki_filp->private_data;
+	size_t size = iov_iter_count(iter);
 	size_t copied = 0;
 	size_t n;
 	void *p;
@@ -158,14 +180,14 @@ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos)
 	 * if request is to read from zero offset, reset iterator to first
 	 * record as it might have been already advanced by previous requests
 	 */
-	if (*ppos == 0) {
+	if (iocb->ki_pos == 0) {
 		m->index = 0;
 		m->count = 0;
 	}
 
-	/* Don't assume *ppos is where we left it */
-	if (unlikely(*ppos != m->read_pos)) {
-		while ((err = traverse(m, *ppos)) == -EAGAIN)
+	/* Don't assume ki_pos is where we left it */
+	if (unlikely(iocb->ki_pos != m->read_pos)) {
+		while ((err = traverse(m, iocb->ki_pos)) == -EAGAIN)
 			;
 		if (err) {
 			/* With prejudice... */
@@ -174,7 +196,7 @@ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos)
 			m->count = 0;
 			goto Done;
 		} else {
-			m->read_pos = *ppos;
+			m->read_pos = iocb->ki_pos;
 		}
 	}
 
@@ -187,13 +209,11 @@ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos)
 	/* if not empty - flush it first */
 	if (m->count) {
 		n = min(m->count, size);
-		err = copy_to_user(buf, m->buf + m->from, n);
-		if (err)
+		if (copy_to_iter(m->buf + m->from, n, iter) != n)
 			goto Efault;
 		m->count -= n;
 		m->from += n;
 		size -= n;
-		buf += n;
 		copied += n;
 		if (!size)
 			goto Done;
@@ -254,8 +274,7 @@ Fill:
 	}
 	m->op->stop(m, p);
 	n = min(m->count, size);
-	err = copy_to_user(buf, m->buf, n);
-	if (err)
+	if (copy_to_iter(m->buf, n, iter) != n)
 		goto Efault;
 	copied += n;
 	m->count -= n;
@@ -264,7 +283,7 @@ Done:
 	if (!copied)
 		copied = err;
 	else {
-		*ppos += copied;
+		iocb->ki_pos += copied;
 		m->read_pos += copied;
 	}
 	mutex_unlock(&m->lock);
@@ -276,7 +295,7 @@ Efault:
 	err = -EFAULT;
 	goto Done;
 }
-EXPORT_SYMBOL(seq_read);
+EXPORT_SYMBOL(seq_read_iter);
 
 /**
  *	seq_lseek -	->llseek() method for sequential files.
diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h
index 813614d4b71f..b83b3ae3c877 100644
--- a/include/linux/seq_file.h
+++ b/include/linux/seq_file.h
@@ -107,6 +107,7 @@ void seq_pad(struct seq_file *m, char c);
 char *mangle_path(char *s, const char *p, const char *esc);
 int seq_open(struct file *, const struct seq_operations *);
 ssize_t seq_read(struct file *, char __user *, size_t, loff_t *);
+ssize_t seq_read_iter(struct kiocb *iocb, struct iov_iter *iter);
 loff_t seq_lseek(struct file *, loff_t, int);
 int seq_release(struct inode *, struct file *);
 int seq_write(struct seq_file *seq, const void *data, size_t len);
-- 
cgit v1.2.3


From b819fd9da38508e0504624b87d9983fcc4237f3c Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 3 Nov 2020 10:27:14 +0100
Subject: highmem: Remove unused functions

Nothing uses totalhigh_pages_dec() and totalhigh_pages_set().

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: https://lore.kernel.org/r/20201103095856.732891880@linutronix.de
---
 include/linux/highmem.h | 10 ----------
 1 file changed, 10 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 14e6202ce47f..f5c31338f0a3 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -104,21 +104,11 @@ static inline void totalhigh_pages_inc(void)
 	atomic_long_inc(&_totalhigh_pages);
 }
 
-static inline void totalhigh_pages_dec(void)
-{
-	atomic_long_dec(&_totalhigh_pages);
-}
-
 static inline void totalhigh_pages_add(long count)
 {
 	atomic_long_add(count, &_totalhigh_pages);
 }
 
-static inline void totalhigh_pages_set(long val)
-{
-	atomic_long_set(&_totalhigh_pages, val);
-}
-
 void kmap_flush_unused(void);
 
 struct page *kmap_to_page(void *addr);
-- 
cgit v1.2.3


From 298fa1ad5571f59cb3ca5497a9455f36867f065e Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 3 Nov 2020 10:27:18 +0100
Subject: highmem: Provide generic variant of kmap_atomic*

The kmap_atomic* interfaces in all architectures are pretty much the same
except for post map operations (flush) and pre- and post unmap operations.

Provide a generic variant for that.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Linus Torvalds <torvalds@linuxfoundation.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: https://lore.kernel.org/r/20201103095857.175939340@linutronix.de
---
 include/linux/highmem.h |  82 +++++++++++++++++++++------
 mm/Kconfig              |   3 +
 mm/highmem.c            | 144 +++++++++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 211 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index f5c31338f0a3..f5ecee9c2576 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -31,9 +31,16 @@ static inline void invalidate_kernel_vmap_range(void *vaddr, int size)
 
 #include <asm/kmap_types.h>
 
+/*
+ * Outside of CONFIG_HIGHMEM to support X86 32bit iomap_atomic() cruft.
+ */
+#ifdef CONFIG_KMAP_LOCAL
+void *__kmap_local_pfn_prot(unsigned long pfn, pgprot_t prot);
+void *__kmap_local_page_prot(struct page *page, pgprot_t prot);
+void kunmap_local_indexed(void *vaddr);
+#endif
+
 #ifdef CONFIG_HIGHMEM
-extern void *kmap_atomic_high_prot(struct page *page, pgprot_t prot);
-extern void kunmap_atomic_high(void *kvaddr);
 #include <asm/highmem.h>
 
 #ifndef ARCH_HAS_KMAP_FLUSH_TLB
@@ -81,6 +88,11 @@ static inline void kunmap(struct page *page)
  * be used in IRQ contexts, so in some (very limited) cases we need
  * it.
  */
+
+#ifndef CONFIG_KMAP_LOCAL
+void *kmap_atomic_high_prot(struct page *page, pgprot_t prot);
+void kunmap_atomic_high(void *kvaddr);
+
 static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot)
 {
 	preempt_disable();
@@ -89,7 +101,38 @@ static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot)
 		return page_address(page);
 	return kmap_atomic_high_prot(page, prot);
 }
-#define kmap_atomic(page)	kmap_atomic_prot(page, kmap_prot)
+
+static inline void __kunmap_atomic(void *vaddr)
+{
+	kunmap_atomic_high(vaddr);
+}
+#else /* !CONFIG_KMAP_LOCAL */
+
+static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot)
+{
+	preempt_disable();
+	pagefault_disable();
+	return __kmap_local_page_prot(page, prot);
+}
+
+static inline void *kmap_atomic_pfn(unsigned long pfn)
+{
+	preempt_disable();
+	pagefault_disable();
+	return __kmap_local_pfn_prot(pfn, kmap_prot);
+}
+
+static inline void __kunmap_atomic(void *addr)
+{
+	kunmap_local_indexed(addr);
+}
+
+#endif /* CONFIG_KMAP_LOCAL */
+
+static inline void *kmap_atomic(struct page *page)
+{
+	return kmap_atomic_prot(page, kmap_prot);
+}
 
 /* declarations for linux/mm/highmem.c */
 unsigned int nr_free_highpages(void);
@@ -147,25 +190,33 @@ static inline void *kmap_atomic(struct page *page)
 	pagefault_disable();
 	return page_address(page);
 }
-#define kmap_atomic_prot(page, prot)	kmap_atomic(page)
 
-static inline void kunmap_atomic_high(void *addr)
+static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot)
+{
+	return kmap_atomic(page);
+}
+
+static inline void *kmap_atomic_pfn(unsigned long pfn)
+{
+	return kmap_atomic(pfn_to_page(pfn));
+}
+
+static inline void __kunmap_atomic(void *addr)
 {
 	/*
 	 * Mostly nothing to do in the CONFIG_HIGHMEM=n case as kunmap_atomic()
-	 * handles re-enabling faults + preemption
+	 * handles re-enabling faults and preemption
 	 */
 #ifdef ARCH_HAS_FLUSH_ON_KUNMAP
 	kunmap_flush_on_unmap(addr);
 #endif
 }
 
-#define kmap_atomic_pfn(pfn)	kmap_atomic(pfn_to_page(pfn))
-
 #define kmap_flush_unused()	do {} while(0)
 
 #endif /* CONFIG_HIGHMEM */
 
+#if !defined(CONFIG_KMAP_LOCAL)
 #if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32)
 
 DECLARE_PER_CPU(int, __kmap_atomic_idx);
@@ -196,22 +247,21 @@ static inline void kmap_atomic_idx_pop(void)
 	__this_cpu_dec(__kmap_atomic_idx);
 #endif
 }
-
+#endif
 #endif
 
 /*
  * Prevent people trying to call kunmap_atomic() as if it were kunmap()
  * kunmap_atomic() should get the return value of kmap_atomic, not the page.
  */
-#define kunmap_atomic(addr)                                     \
-do {                                                            \
-	BUILD_BUG_ON(__same_type((addr), struct page *));       \
-	kunmap_atomic_high(addr);                                  \
-	pagefault_enable();                                     \
-	preempt_enable();                                       \
+#define kunmap_atomic(__addr)					\
+do {								\
+	BUILD_BUG_ON(__same_type((__addr), struct page *));	\
+	__kunmap_atomic(__addr);				\
+	pagefault_enable();					\
+	preempt_enable();					\
 } while (0)
 
-
 /* when CONFIG_HIGHMEM is not set these will be plain clear/copy_page */
 #ifndef clear_user_highpage
 static inline void clear_user_highpage(struct page *page, unsigned long vaddr)
diff --git a/mm/Kconfig b/mm/Kconfig
index d42423f884a7..a1ccf98b7333 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -872,4 +872,7 @@ config ARCH_HAS_HUGEPD
 config MAPPING_DIRTY_HELPERS
         bool
 
+config KMAP_LOCAL
+	bool
+
 endmenu
diff --git a/mm/highmem.c b/mm/highmem.c
index 6abfd762eee7..bb4ce13ee7e7 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -31,9 +31,11 @@
 #include <asm/tlbflush.h>
 #include <linux/vmalloc.h>
 
+#ifndef CONFIG_KMAP_LOCAL
 #if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32)
 DEFINE_PER_CPU(int, __kmap_atomic_idx);
 #endif
+#endif
 
 /*
  * Virtual_count is not a pure "count".
@@ -365,9 +367,147 @@ void kunmap_high(struct page *page)
 	if (need_wakeup)
 		wake_up(pkmap_map_wait);
 }
-
 EXPORT_SYMBOL(kunmap_high);
-#endif	/* CONFIG_HIGHMEM */
+#endif /* CONFIG_HIGHMEM */
+
+#ifdef CONFIG_KMAP_LOCAL
+
+#include <asm/kmap_size.h>
+
+static DEFINE_PER_CPU(int, __kmap_local_idx);
+
+static inline int kmap_local_idx_push(void)
+{
+	int idx = __this_cpu_inc_return(__kmap_local_idx) - 1;
+
+	WARN_ON_ONCE(in_irq() && !irqs_disabled());
+	BUG_ON(idx >= KM_MAX_IDX);
+	return idx;
+}
+
+static inline int kmap_local_idx(void)
+{
+	return __this_cpu_read(__kmap_local_idx) - 1;
+}
+
+static inline void kmap_local_idx_pop(void)
+{
+	int idx = __this_cpu_dec_return(__kmap_local_idx);
+
+	BUG_ON(idx < 0);
+}
+
+#ifndef arch_kmap_local_post_map
+# define arch_kmap_local_post_map(vaddr, pteval)	do { } while (0)
+#endif
+#ifndef arch_kmap_local_pre_unmap
+# define arch_kmap_local_pre_unmap(vaddr)		do { } while (0)
+#endif
+
+#ifndef arch_kmap_local_post_unmap
+# define arch_kmap_local_post_unmap(vaddr)		do { } while (0)
+#endif
+
+#ifndef arch_kmap_local_map_idx
+#define arch_kmap_local_map_idx(idx, pfn)	kmap_local_calc_idx(idx)
+#endif
+
+#ifndef arch_kmap_local_unmap_idx
+#define arch_kmap_local_unmap_idx(idx, vaddr)	kmap_local_calc_idx(idx)
+#endif
+
+#ifndef arch_kmap_local_high_get
+static inline void *arch_kmap_local_high_get(struct page *page)
+{
+	return NULL;
+}
+#endif
+
+/* Unmap a local mapping which was obtained by kmap_high_get() */
+static inline void kmap_high_unmap_local(unsigned long vaddr)
+{
+#ifdef ARCH_NEEDS_KMAP_HIGH_GET
+	if (vaddr >= PKMAP_ADDR(0) && vaddr < PKMAP_ADDR(LAST_PKMAP))
+		kunmap_high(pte_page(pkmap_page_table[PKMAP_NR(vaddr)]));
+#endif
+}
+
+static inline int kmap_local_calc_idx(int idx)
+{
+	return idx + KM_MAX_IDX * smp_processor_id();
+}
+
+static pte_t *__kmap_pte;
+
+static pte_t *kmap_get_pte(void)
+{
+	if (!__kmap_pte)
+		__kmap_pte = virt_to_kpte(__fix_to_virt(FIX_KMAP_BEGIN));
+	return __kmap_pte;
+}
+
+void *__kmap_local_pfn_prot(unsigned long pfn, pgprot_t prot)
+{
+	pte_t pteval, *kmap_pte = kmap_get_pte();
+	unsigned long vaddr;
+	int idx;
+
+	preempt_disable();
+	idx = arch_kmap_local_map_idx(kmap_local_idx_push(), pfn);
+	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
+	BUG_ON(!pte_none(*(kmap_pte - idx)));
+	pteval = pfn_pte(pfn, prot);
+	set_pte_at(&init_mm, vaddr, kmap_pte - idx, pteval);
+	arch_kmap_local_post_map(vaddr, pteval);
+	preempt_enable();
+
+	return (void *)vaddr;
+}
+EXPORT_SYMBOL_GPL(__kmap_local_pfn_prot);
+
+void *__kmap_local_page_prot(struct page *page, pgprot_t prot)
+{
+	void *kmap;
+
+	if (!PageHighMem(page))
+		return page_address(page);
+
+	/* Try kmap_high_get() if architecture has it enabled */
+	kmap = arch_kmap_local_high_get(page);
+	if (kmap)
+		return kmap;
+
+	return __kmap_local_pfn_prot(page_to_pfn(page), prot);
+}
+EXPORT_SYMBOL(__kmap_local_page_prot);
+
+void kunmap_local_indexed(void *vaddr)
+{
+	unsigned long addr = (unsigned long) vaddr & PAGE_MASK;
+	pte_t *kmap_pte = kmap_get_pte();
+	int idx;
+
+	if (addr < __fix_to_virt(FIX_KMAP_END) ||
+	    addr > __fix_to_virt(FIX_KMAP_BEGIN)) {
+		WARN_ON_ONCE(addr < PAGE_OFFSET);
+
+		/* Handle mappings which were obtained by kmap_high_get() */
+		kmap_high_unmap_local(addr);
+		return;
+	}
+
+	preempt_disable();
+	idx = arch_kmap_local_unmap_idx(kmap_local_idx(), addr);
+	WARN_ON_ONCE(addr != __fix_to_virt(FIX_KMAP_BEGIN + idx));
+
+	arch_kmap_local_pre_unmap(addr);
+	pte_clear(&init_mm, addr, kmap_pte - idx);
+	arch_kmap_local_post_unmap(addr);
+	kmap_local_idx_pop();
+	preempt_enable();
+}
+EXPORT_SYMBOL(kunmap_local_indexed);
+#endif
 
 #if defined(HASHED_PAGE_VIRTUAL)
 
-- 
cgit v1.2.3


From 157e118b55113d1e6c7f8ddfcec0a1dbf3a69511 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 3 Nov 2020 10:27:20 +0100
Subject: x86/mm/highmem: Use generic kmap atomic implementation

Convert X86 to the generic kmap atomic implementation and make the
iomap_atomic() naming convention consistent while at it.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20201103095857.375127260@linutronix.de
---
 arch/x86/Kconfig                      |  3 +-
 arch/x86/include/asm/fixmap.h         |  5 ++-
 arch/x86/include/asm/highmem.h        | 13 +++++---
 arch/x86/include/asm/iomap.h          | 18 ++++++-----
 arch/x86/include/asm/kmap_types.h     | 13 --------
 arch/x86/include/asm/paravirt_types.h |  1 -
 arch/x86/mm/highmem_32.c              | 59 -----------------------------------
 arch/x86/mm/init_32.c                 | 15 ---------
 arch/x86/mm/iomap_32.c                | 59 +++--------------------------------
 include/linux/highmem.h               |  2 +-
 include/linux/io-mapping.h            |  2 +-
 mm/highmem.c                          |  2 +-
 12 files changed, 31 insertions(+), 161 deletions(-)
 delete mode 100644 arch/x86/include/asm/kmap_types.h

(limited to 'include/linux')

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index f6946b81f74a..33c273cb3023 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -14,10 +14,11 @@ config X86_32
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select CLKSRC_I8253
 	select CLONE_BACKWARDS
+	select GENERIC_VDSO_32
 	select HAVE_DEBUG_STACKOVERFLOW
+	select KMAP_LOCAL
 	select MODULES_USE_ELF_REL
 	select OLD_SIGACTION
-	select GENERIC_VDSO_32
 
 config X86_64
 	def_bool y
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 77217bd292bd..8eba66a33e39 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -31,7 +31,7 @@
 #include <asm/pgtable_types.h>
 #ifdef CONFIG_X86_32
 #include <linux/threads.h>
-#include <asm/kmap_types.h>
+#include <asm/kmap_size.h>
 #else
 #include <uapi/asm/vsyscall.h>
 #endif
@@ -94,7 +94,7 @@ enum fixed_addresses {
 #endif
 #ifdef CONFIG_X86_32
 	FIX_KMAP_BEGIN,	/* reserved pte's for temporary kernel mappings */
-	FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
+	FIX_KMAP_END = FIX_KMAP_BEGIN + (KM_MAX_IDX * NR_CPUS) - 1,
 #ifdef CONFIG_PCI_MMCONFIG
 	FIX_PCIE_MCFG,
 #endif
@@ -151,7 +151,6 @@ extern void reserve_top_address(unsigned long reserve);
 
 extern int fixmaps_set;
 
-extern pte_t *kmap_pte;
 extern pte_t *pkmap_page_table;
 
 void __native_set_fixmap(enum fixed_addresses idx, pte_t pte);
diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h
index 0f420b24e0fc..032e020853aa 100644
--- a/arch/x86/include/asm/highmem.h
+++ b/arch/x86/include/asm/highmem.h
@@ -23,7 +23,6 @@
 
 #include <linux/interrupt.h>
 #include <linux/threads.h>
-#include <asm/kmap_types.h>
 #include <asm/tlbflush.h>
 #include <asm/paravirt.h>
 #include <asm/fixmap.h>
@@ -58,11 +57,17 @@ extern unsigned long highstart_pfn, highend_pfn;
 #define PKMAP_NR(virt)  ((virt-PKMAP_BASE) >> PAGE_SHIFT)
 #define PKMAP_ADDR(nr)  (PKMAP_BASE + ((nr) << PAGE_SHIFT))
 
-void *kmap_atomic_pfn(unsigned long pfn);
-void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot);
-
 #define flush_cache_kmaps()	do { } while (0)
 
+#define	arch_kmap_local_post_map(vaddr, pteval)		\
+	arch_flush_lazy_mmu_mode()
+
+#define	arch_kmap_local_post_unmap(vaddr)		\
+	do {						\
+		flush_tlb_one_kernel((vaddr));		\
+		arch_flush_lazy_mmu_mode();		\
+	} while (0)
+
 extern void add_highpages_with_active_regions(int nid, unsigned long start_pfn,
 					unsigned long end_pfn);
 
diff --git a/arch/x86/include/asm/iomap.h b/arch/x86/include/asm/iomap.h
index bacf68c4d70e..0be7a30fd6bc 100644
--- a/arch/x86/include/asm/iomap.h
+++ b/arch/x86/include/asm/iomap.h
@@ -9,19 +9,21 @@
 #include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/uaccess.h>
+#include <linux/highmem.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 
-void __iomem *
-iomap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot);
+void __iomem *iomap_atomic_pfn_prot(unsigned long pfn, pgprot_t prot);
 
-void
-iounmap_atomic(void __iomem *kvaddr);
+static inline void iounmap_atomic(void __iomem *vaddr)
+{
+	kunmap_local_indexed((void __force *)vaddr);
+	pagefault_enable();
+	preempt_enable();
+}
 
-int
-iomap_create_wc(resource_size_t base, unsigned long size, pgprot_t *prot);
+int iomap_create_wc(resource_size_t base, unsigned long size, pgprot_t *prot);
 
-void
-iomap_free(resource_size_t base, unsigned long size);
+void iomap_free(resource_size_t base, unsigned long size);
 
 #endif /* _ASM_X86_IOMAP_H */
diff --git a/arch/x86/include/asm/kmap_types.h b/arch/x86/include/asm/kmap_types.h
deleted file mode 100644
index 04ab8266e347..000000000000
--- a/arch/x86/include/asm/kmap_types.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_KMAP_TYPES_H
-#define _ASM_X86_KMAP_TYPES_H
-
-#if defined(CONFIG_X86_32) && defined(CONFIG_DEBUG_HIGHMEM)
-#define  __WITH_KM_FENCE
-#endif
-
-#include <asm-generic/kmap_types.h>
-
-#undef __WITH_KM_FENCE
-
-#endif /* _ASM_X86_KMAP_TYPES_H */
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 0fad9f61c76a..b6b02b7c19cc 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -41,7 +41,6 @@
 #ifndef __ASSEMBLY__
 
 #include <asm/desc_defs.h>
-#include <asm/kmap_types.h>
 #include <asm/pgtable_types.h>
 #include <asm/nospec-branch.h>
 
diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c
index 075fe51317b0..2c54b76d8f84 100644
--- a/arch/x86/mm/highmem_32.c
+++ b/arch/x86/mm/highmem_32.c
@@ -4,65 +4,6 @@
 #include <linux/swap.h> /* for totalram_pages */
 #include <linux/memblock.h>
 
-void *kmap_atomic_high_prot(struct page *page, pgprot_t prot)
-{
-	unsigned long vaddr;
-	int idx, type;
-
-	type = kmap_atomic_idx_push();
-	idx = type + KM_TYPE_NR*smp_processor_id();
-	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
-	BUG_ON(!pte_none(*(kmap_pte-idx)));
-	set_pte(kmap_pte-idx, mk_pte(page, prot));
-	arch_flush_lazy_mmu_mode();
-
-	return (void *)vaddr;
-}
-EXPORT_SYMBOL(kmap_atomic_high_prot);
-
-/*
- * This is the same as kmap_atomic() but can map memory that doesn't
- * have a struct page associated with it.
- */
-void *kmap_atomic_pfn(unsigned long pfn)
-{
-	return kmap_atomic_prot_pfn(pfn, kmap_prot);
-}
-EXPORT_SYMBOL_GPL(kmap_atomic_pfn);
-
-void kunmap_atomic_high(void *kvaddr)
-{
-	unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
-
-	if (vaddr >= __fix_to_virt(FIX_KMAP_END) &&
-	    vaddr <= __fix_to_virt(FIX_KMAP_BEGIN)) {
-		int idx, type;
-
-		type = kmap_atomic_idx();
-		idx = type + KM_TYPE_NR * smp_processor_id();
-
-#ifdef CONFIG_DEBUG_HIGHMEM
-		WARN_ON_ONCE(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx));
-#endif
-		/*
-		 * Force other mappings to Oops if they'll try to access this
-		 * pte without first remap it.  Keeping stale mappings around
-		 * is a bad idea also, in case the page changes cacheability
-		 * attributes or becomes a protected page in a hypervisor.
-		 */
-		kpte_clear_flush(kmap_pte-idx, vaddr);
-		kmap_atomic_idx_pop();
-		arch_flush_lazy_mmu_mode();
-	}
-#ifdef CONFIG_DEBUG_HIGHMEM
-	else {
-		BUG_ON(vaddr < PAGE_OFFSET);
-		BUG_ON(vaddr >= (unsigned long)high_memory);
-	}
-#endif
-}
-EXPORT_SYMBOL(kunmap_atomic_high);
-
 void __init set_highmem_pages_init(void)
 {
 	struct zone *zone;
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 7c055259de3a..da31c2635ee4 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -394,19 +394,6 @@ repeat:
 	return last_map_addr;
 }
 
-pte_t *kmap_pte;
-
-static void __init kmap_init(void)
-{
-	unsigned long kmap_vstart;
-
-	/*
-	 * Cache the first kmap pte:
-	 */
-	kmap_vstart = __fix_to_virt(FIX_KMAP_BEGIN);
-	kmap_pte = virt_to_kpte(kmap_vstart);
-}
-
 #ifdef CONFIG_HIGHMEM
 static void __init permanent_kmaps_init(pgd_t *pgd_base)
 {
@@ -712,8 +699,6 @@ void __init paging_init(void)
 
 	__flush_tlb_all();
 
-	kmap_init();
-
 	/*
 	 * NOTE: at this point the bootmem allocator is fully available.
 	 */
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
index f60398aeb644..e0a40d7cc66c 100644
--- a/arch/x86/mm/iomap_32.c
+++ b/arch/x86/mm/iomap_32.c
@@ -44,28 +44,7 @@ void iomap_free(resource_size_t base, unsigned long size)
 }
 EXPORT_SYMBOL_GPL(iomap_free);
 
-void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot)
-{
-	unsigned long vaddr;
-	int idx, type;
-
-	preempt_disable();
-	pagefault_disable();
-
-	type = kmap_atomic_idx_push();
-	idx = type + KM_TYPE_NR * smp_processor_id();
-	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
-	set_pte(kmap_pte - idx, pfn_pte(pfn, prot));
-	arch_flush_lazy_mmu_mode();
-
-	return (void *)vaddr;
-}
-
-/*
- * Map 'pfn' using protections 'prot'
- */
-void __iomem *
-iomap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot)
+void __iomem *iomap_atomic_pfn_prot(unsigned long pfn, pgprot_t prot)
 {
 	/*
 	 * For non-PAT systems, translate non-WB request to UC- just in
@@ -81,36 +60,8 @@ iomap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot)
 	/* Filter out unsupported __PAGE_KERNEL* bits: */
 	pgprot_val(prot) &= __default_kernel_pte_mask;
 
-	return (void __force __iomem *) kmap_atomic_prot_pfn(pfn, prot);
-}
-EXPORT_SYMBOL_GPL(iomap_atomic_prot_pfn);
-
-void
-iounmap_atomic(void __iomem *kvaddr)
-{
-	unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
-
-	if (vaddr >= __fix_to_virt(FIX_KMAP_END) &&
-	    vaddr <= __fix_to_virt(FIX_KMAP_BEGIN)) {
-		int idx, type;
-
-		type = kmap_atomic_idx();
-		idx = type + KM_TYPE_NR * smp_processor_id();
-
-#ifdef CONFIG_DEBUG_HIGHMEM
-		WARN_ON_ONCE(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx));
-#endif
-		/*
-		 * Force other mappings to Oops if they'll try to access this
-		 * pte without first remap it.  Keeping stale mappings around
-		 * is a bad idea also, in case the page changes cacheability
-		 * attributes or becomes a protected page in a hypervisor.
-		 */
-		kpte_clear_flush(kmap_pte-idx, vaddr);
-		kmap_atomic_idx_pop();
-	}
-
-	pagefault_enable();
-	preempt_enable();
+	preempt_disable();
+	pagefault_disable();
+	return (void __force __iomem *)__kmap_local_pfn_prot(pfn, prot);
 }
-EXPORT_SYMBOL_GPL(iounmap_atomic);
+EXPORT_SYMBOL_GPL(iomap_atomic_pfn_prot);
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index f5ecee9c2576..1222a31be842 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -217,7 +217,7 @@ static inline void __kunmap_atomic(void *addr)
 #endif /* CONFIG_HIGHMEM */
 
 #if !defined(CONFIG_KMAP_LOCAL)
-#if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32)
+#if defined(CONFIG_HIGHMEM)
 
 DECLARE_PER_CPU(int, __kmap_atomic_idx);
 
diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h
index c75e4d3d8833..3b0940be72e9 100644
--- a/include/linux/io-mapping.h
+++ b/include/linux/io-mapping.h
@@ -69,7 +69,7 @@ io_mapping_map_atomic_wc(struct io_mapping *mapping,
 
 	BUG_ON(offset >= mapping->size);
 	phys_addr = mapping->base + offset;
-	return iomap_atomic_prot_pfn(PHYS_PFN(phys_addr), mapping->prot);
+	return iomap_atomic_pfn_prot(PHYS_PFN(phys_addr), mapping->prot);
 }
 
 static inline void
diff --git a/mm/highmem.c b/mm/highmem.c
index 67d2d5983cb0..77677c6844f7 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -32,7 +32,7 @@
 #include <linux/vmalloc.h>
 
 #ifndef CONFIG_KMAP_LOCAL
-#if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32)
+#ifdef CONFIG_HIGHMEM
 DEFINE_PER_CPU(int, __kmap_atomic_idx);
 #endif
 #endif
-- 
cgit v1.2.3


From d7029e4549691ecaf1ead536d3322a00bda85659 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 3 Nov 2020 10:27:30 +0100
Subject: highmem: Get rid of kmap_types.h

The header is not longer used and on alpha, ia64, openrisc, parisc and um
it was completely unused anyway as these architectures have no highmem
support.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20201103095858.422094352@linutronix.de
---
 arch/alpha/include/asm/kmap_types.h  | 15 ---------------
 arch/ia64/include/asm/kmap_types.h   | 13 -------------
 arch/openrisc/mm/init.c              |  1 -
 arch/openrisc/mm/ioremap.c           |  1 -
 arch/parisc/include/asm/kmap_types.h | 13 -------------
 arch/um/include/asm/fixmap.h         |  1 -
 arch/um/include/asm/kmap_types.h     | 13 -------------
 include/asm-generic/Kbuild           |  1 -
 include/asm-generic/kmap_types.h     | 11 -----------
 include/linux/highmem.h              |  2 --
 10 files changed, 71 deletions(-)
 delete mode 100644 arch/alpha/include/asm/kmap_types.h
 delete mode 100644 arch/ia64/include/asm/kmap_types.h
 delete mode 100644 arch/parisc/include/asm/kmap_types.h
 delete mode 100644 arch/um/include/asm/kmap_types.h
 delete mode 100644 include/asm-generic/kmap_types.h

(limited to 'include/linux')

diff --git a/arch/alpha/include/asm/kmap_types.h b/arch/alpha/include/asm/kmap_types.h
deleted file mode 100644
index 651714b45729..000000000000
--- a/arch/alpha/include/asm/kmap_types.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_KMAP_TYPES_H
-#define _ASM_KMAP_TYPES_H
-
-/* Dummy header just to define km_type. */
-
-#ifdef CONFIG_DEBUG_HIGHMEM
-#define  __WITH_KM_FENCE
-#endif
-
-#include <asm-generic/kmap_types.h>
-
-#undef __WITH_KM_FENCE
-
-#endif
diff --git a/arch/ia64/include/asm/kmap_types.h b/arch/ia64/include/asm/kmap_types.h
deleted file mode 100644
index 5c268cf7c2bd..000000000000
--- a/arch/ia64/include/asm/kmap_types.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_IA64_KMAP_TYPES_H
-#define _ASM_IA64_KMAP_TYPES_H
-
-#ifdef CONFIG_DEBUG_HIGHMEM
-#define  __WITH_KM_FENCE
-#endif
-
-#include <asm-generic/kmap_types.h>
-
-#undef __WITH_KM_FENCE
-
-#endif /* _ASM_IA64_KMAP_TYPES_H */
diff --git a/arch/openrisc/mm/init.c b/arch/openrisc/mm/init.c
index 8348feaaf46e..bf9b2310fc93 100644
--- a/arch/openrisc/mm/init.c
+++ b/arch/openrisc/mm/init.c
@@ -33,7 +33,6 @@
 #include <asm/io.h>
 #include <asm/tlb.h>
 #include <asm/mmu_context.h>
-#include <asm/kmap_types.h>
 #include <asm/fixmap.h>
 #include <asm/tlbflush.h>
 #include <asm/sections.h>
diff --git a/arch/openrisc/mm/ioremap.c b/arch/openrisc/mm/ioremap.c
index a978590d802d..5aed97a18bac 100644
--- a/arch/openrisc/mm/ioremap.c
+++ b/arch/openrisc/mm/ioremap.c
@@ -15,7 +15,6 @@
 #include <linux/io.h>
 #include <linux/pgtable.h>
 #include <asm/pgalloc.h>
-#include <asm/kmap_types.h>
 #include <asm/fixmap.h>
 #include <asm/bug.h>
 #include <linux/sched.h>
diff --git a/arch/parisc/include/asm/kmap_types.h b/arch/parisc/include/asm/kmap_types.h
deleted file mode 100644
index 3e70b5cd1123..000000000000
--- a/arch/parisc/include/asm/kmap_types.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_KMAP_TYPES_H
-#define _ASM_KMAP_TYPES_H
-
-#ifdef CONFIG_DEBUG_HIGHMEM
-#define  __WITH_KM_FENCE
-#endif
-
-#include <asm-generic/kmap_types.h>
-
-#undef __WITH_KM_FENCE
-
-#endif
diff --git a/arch/um/include/asm/fixmap.h b/arch/um/include/asm/fixmap.h
index 2c697a145ac1..2efac5827188 100644
--- a/arch/um/include/asm/fixmap.h
+++ b/arch/um/include/asm/fixmap.h
@@ -3,7 +3,6 @@
 #define __UM_FIXMAP_H
 
 #include <asm/processor.h>
-#include <asm/kmap_types.h>
 #include <asm/archparam.h>
 #include <asm/page.h>
 #include <linux/threads.h>
diff --git a/arch/um/include/asm/kmap_types.h b/arch/um/include/asm/kmap_types.h
deleted file mode 100644
index b0bd12de1d23..000000000000
--- a/arch/um/include/asm/kmap_types.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* 
- * Copyright (C) 2002 Jeff Dike (jdike@karaya.com)
- */
-
-#ifndef __UM_KMAP_TYPES_H
-#define __UM_KMAP_TYPES_H
-
-/* No more #include "asm/arch/kmap_types.h" ! */
-
-#define KM_TYPE_NR 14
-
-#endif
diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild
index ed62d384fb79..4365b9aa3e3f 100644
--- a/include/asm-generic/Kbuild
+++ b/include/asm-generic/Kbuild
@@ -30,7 +30,6 @@ mandatory-y += irq.h
 mandatory-y += irq_regs.h
 mandatory-y += irq_work.h
 mandatory-y += kdebug.h
-mandatory-y += kmap_types.h
 mandatory-y += kmap_size.h
 mandatory-y += kprobes.h
 mandatory-y += linkage.h
diff --git a/include/asm-generic/kmap_types.h b/include/asm-generic/kmap_types.h
deleted file mode 100644
index 9f95b7b63d19..000000000000
--- a/include/asm-generic/kmap_types.h
+++ /dev/null
@@ -1,11 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_GENERIC_KMAP_TYPES_H
-#define _ASM_GENERIC_KMAP_TYPES_H
-
-#ifdef __WITH_KM_FENCE
-# define KM_TYPE_NR 41
-#else
-# define KM_TYPE_NR 20
-#endif
-
-#endif
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 1222a31be842..de78869454b1 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -29,8 +29,6 @@ static inline void invalidate_kernel_vmap_range(void *vaddr, int size)
 }
 #endif
 
-#include <asm/kmap_types.h>
-
 /*
  * Outside of CONFIG_HIGHMEM to support X86 32bit iomap_atomic() cruft.
  */
-- 
cgit v1.2.3


From 3c1016b53c311906878c703af1e2b29855a9a962 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 3 Nov 2020 10:27:31 +0100
Subject: mm/highmem: Remove the old kmap_atomic cruft

All users gone.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Linus Torvalds <torvalds@linuxfoundation.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20201103095858.516281567@linutronix.de
---
 include/linux/highmem.h | 63 ++++---------------------------------------------
 mm/highmem.c            |  7 +-----
 2 files changed, 5 insertions(+), 65 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index de78869454b1..3180a8f7307f 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -86,31 +86,16 @@ static inline void kunmap(struct page *page)
  * be used in IRQ contexts, so in some (very limited) cases we need
  * it.
  */
-
-#ifndef CONFIG_KMAP_LOCAL
-void *kmap_atomic_high_prot(struct page *page, pgprot_t prot);
-void kunmap_atomic_high(void *kvaddr);
-
 static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot)
 {
 	preempt_disable();
 	pagefault_disable();
-	if (!PageHighMem(page))
-		return page_address(page);
-	return kmap_atomic_high_prot(page, prot);
-}
-
-static inline void __kunmap_atomic(void *vaddr)
-{
-	kunmap_atomic_high(vaddr);
+	return __kmap_local_page_prot(page, prot);
 }
-#else /* !CONFIG_KMAP_LOCAL */
 
-static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot)
+static inline void *kmap_atomic(struct page *page)
 {
-	preempt_disable();
-	pagefault_disable();
-	return __kmap_local_page_prot(page, prot);
+	return kmap_atomic_prot(page, kmap_prot);
 }
 
 static inline void *kmap_atomic_pfn(unsigned long pfn)
@@ -125,13 +110,6 @@ static inline void __kunmap_atomic(void *addr)
 	kunmap_local_indexed(addr);
 }
 
-#endif /* CONFIG_KMAP_LOCAL */
-
-static inline void *kmap_atomic(struct page *page)
-{
-	return kmap_atomic_prot(page, kmap_prot);
-}
-
 /* declarations for linux/mm/highmem.c */
 unsigned int nr_free_highpages(void);
 extern atomic_long_t _totalhigh_pages;
@@ -212,41 +190,8 @@ static inline void __kunmap_atomic(void *addr)
 
 #define kmap_flush_unused()	do {} while(0)
 
-#endif /* CONFIG_HIGHMEM */
-
-#if !defined(CONFIG_KMAP_LOCAL)
-#if defined(CONFIG_HIGHMEM)
-
-DECLARE_PER_CPU(int, __kmap_atomic_idx);
-
-static inline int kmap_atomic_idx_push(void)
-{
-	int idx = __this_cpu_inc_return(__kmap_atomic_idx) - 1;
-
-#ifdef CONFIG_DEBUG_HIGHMEM
-	WARN_ON_ONCE(in_irq() && !irqs_disabled());
-	BUG_ON(idx >= KM_TYPE_NR);
-#endif
-	return idx;
-}
-
-static inline int kmap_atomic_idx(void)
-{
-	return __this_cpu_read(__kmap_atomic_idx) - 1;
-}
 
-static inline void kmap_atomic_idx_pop(void)
-{
-#ifdef CONFIG_DEBUG_HIGHMEM
-	int idx = __this_cpu_dec_return(__kmap_atomic_idx);
-
-	BUG_ON(idx < 0);
-#else
-	__this_cpu_dec(__kmap_atomic_idx);
-#endif
-}
-#endif
-#endif
+#endif /* CONFIG_HIGHMEM */
 
 /*
  * Prevent people trying to call kunmap_atomic() as if it were kunmap()
diff --git a/mm/highmem.c b/mm/highmem.c
index 77677c6844f7..499dfafd36b7 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -31,12 +31,6 @@
 #include <asm/tlbflush.h>
 #include <linux/vmalloc.h>
 
-#ifndef CONFIG_KMAP_LOCAL
-#ifdef CONFIG_HIGHMEM
-DEFINE_PER_CPU(int, __kmap_atomic_idx);
-#endif
-#endif
-
 /*
  * Virtual_count is not a pure "count".
  *  0 means that it is not mapped, and has not been mapped
@@ -410,6 +404,7 @@ static inline void kmap_local_idx_pop(void)
 #ifndef arch_kmap_local_post_map
 # define arch_kmap_local_post_map(vaddr, pteval)	do { } while (0)
 #endif
+
 #ifndef arch_kmap_local_pre_unmap
 # define arch_kmap_local_pre_unmap(vaddr)		do { } while (0)
 #endif
-- 
cgit v1.2.3


From 351191ad55c8a1eccaf23e4187c62056229c0779 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 3 Nov 2020 10:27:32 +0100
Subject: io-mapping: Cleanup atomic iomap

Switch the atomic iomap implementation over to kmap_local and stick the
preempt/pagefault mechanics into the generic code similar to the
kmap_atomic variants.

Rename the x86 map function in preparation for a non-atomic variant.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Linus Torvalds <torvalds@linuxfoundation.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: https://lore.kernel.org/r/20201103095858.625310005@linutronix.de
---
 arch/x86/include/asm/iomap.h | 9 +--------
 arch/x86/mm/iomap_32.c       | 6 ++----
 include/linux/io-mapping.h   | 8 ++++++--
 3 files changed, 9 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/include/asm/iomap.h b/arch/x86/include/asm/iomap.h
index 0be7a30fd6bc..e2de092fc38c 100644
--- a/arch/x86/include/asm/iomap.h
+++ b/arch/x86/include/asm/iomap.h
@@ -13,14 +13,7 @@
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 
-void __iomem *iomap_atomic_pfn_prot(unsigned long pfn, pgprot_t prot);
-
-static inline void iounmap_atomic(void __iomem *vaddr)
-{
-	kunmap_local_indexed((void __force *)vaddr);
-	pagefault_enable();
-	preempt_enable();
-}
+void __iomem *__iomap_local_pfn_prot(unsigned long pfn, pgprot_t prot);
 
 int iomap_create_wc(resource_size_t base, unsigned long size, pgprot_t *prot);
 
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
index e0a40d7cc66c..9aaa756ddf21 100644
--- a/arch/x86/mm/iomap_32.c
+++ b/arch/x86/mm/iomap_32.c
@@ -44,7 +44,7 @@ void iomap_free(resource_size_t base, unsigned long size)
 }
 EXPORT_SYMBOL_GPL(iomap_free);
 
-void __iomem *iomap_atomic_pfn_prot(unsigned long pfn, pgprot_t prot)
+void __iomem *__iomap_local_pfn_prot(unsigned long pfn, pgprot_t prot)
 {
 	/*
 	 * For non-PAT systems, translate non-WB request to UC- just in
@@ -60,8 +60,6 @@ void __iomem *iomap_atomic_pfn_prot(unsigned long pfn, pgprot_t prot)
 	/* Filter out unsupported __PAGE_KERNEL* bits: */
 	pgprot_val(prot) &= __default_kernel_pte_mask;
 
-	preempt_disable();
-	pagefault_disable();
 	return (void __force __iomem *)__kmap_local_pfn_prot(pfn, prot);
 }
-EXPORT_SYMBOL_GPL(iomap_atomic_pfn_prot);
+EXPORT_SYMBOL_GPL(__iomap_local_pfn_prot);
diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h
index 3b0940be72e9..60e7c83e4904 100644
--- a/include/linux/io-mapping.h
+++ b/include/linux/io-mapping.h
@@ -69,13 +69,17 @@ io_mapping_map_atomic_wc(struct io_mapping *mapping,
 
 	BUG_ON(offset >= mapping->size);
 	phys_addr = mapping->base + offset;
-	return iomap_atomic_pfn_prot(PHYS_PFN(phys_addr), mapping->prot);
+	preempt_disable();
+	pagefault_disable();
+	return __iomap_local_pfn_prot(PHYS_PFN(phys_addr), mapping->prot);
 }
 
 static inline void
 io_mapping_unmap_atomic(void __iomem *vaddr)
 {
-	iounmap_atomic(vaddr);
+	kunmap_local_indexed((void __force *)vaddr);
+	pagefault_enable();
+	preempt_enable();
 }
 
 static inline void __iomem *
-- 
cgit v1.2.3


From 13f876ba77ebd5125799bb042201f22cf73df154 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 3 Nov 2020 10:27:34 +0100
Subject: highmem: High implementation details and document API

Move the gory details of kmap & al into a private header and only document
the interfaces which are usable by drivers.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Linus Torvalds <torvalds@linuxfoundation.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: https://lore.kernel.org/r/20201103095858.827582066@linutronix.de
---
 include/linux/highmem-internal.h | 174 +++++++++++++++++++++++++
 include/linux/highmem.h          | 266 ++++++++++++++-------------------------
 mm/highmem.c                     |  11 +-
 3 files changed, 274 insertions(+), 177 deletions(-)
 create mode 100644 include/linux/highmem-internal.h

(limited to 'include/linux')

diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h
new file mode 100644
index 000000000000..6ceed907b14e
--- /dev/null
+++ b/include/linux/highmem-internal.h
@@ -0,0 +1,174 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_HIGHMEM_INTERNAL_H
+#define _LINUX_HIGHMEM_INTERNAL_H
+
+/*
+ * Outside of CONFIG_HIGHMEM to support X86 32bit iomap_atomic() cruft.
+ */
+#ifdef CONFIG_KMAP_LOCAL
+void *__kmap_local_pfn_prot(unsigned long pfn, pgprot_t prot);
+void *__kmap_local_page_prot(struct page *page, pgprot_t prot);
+void kunmap_local_indexed(void *vaddr);
+#endif
+
+#ifdef CONFIG_HIGHMEM
+#include <asm/highmem.h>
+
+#ifndef ARCH_HAS_KMAP_FLUSH_TLB
+static inline void kmap_flush_tlb(unsigned long addr) { }
+#endif
+
+#ifndef kmap_prot
+#define kmap_prot PAGE_KERNEL
+#endif
+
+void *kmap_high(struct page *page);
+void kunmap_high(struct page *page);
+void __kmap_flush_unused(void);
+struct page *__kmap_to_page(void *addr);
+
+static inline void *kmap(struct page *page)
+{
+	void *addr;
+
+	might_sleep();
+	if (!PageHighMem(page))
+		addr = page_address(page);
+	else
+		addr = kmap_high(page);
+	kmap_flush_tlb((unsigned long)addr);
+	return addr;
+}
+
+static inline void kunmap(struct page *page)
+{
+	might_sleep();
+	if (!PageHighMem(page))
+		return;
+	kunmap_high(page);
+}
+
+static inline struct page *kmap_to_page(void *addr)
+{
+	return __kmap_to_page(addr);
+}
+
+static inline void kmap_flush_unused(void)
+{
+	__kmap_flush_unused();
+}
+
+static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot)
+{
+	preempt_disable();
+	pagefault_disable();
+	return __kmap_local_page_prot(page, prot);
+}
+
+static inline void *kmap_atomic(struct page *page)
+{
+	return kmap_atomic_prot(page, kmap_prot);
+}
+
+static inline void *kmap_atomic_pfn(unsigned long pfn)
+{
+	preempt_disable();
+	pagefault_disable();
+	return __kmap_local_pfn_prot(pfn, kmap_prot);
+}
+
+static inline void __kunmap_atomic(void *addr)
+{
+	kunmap_local_indexed(addr);
+	pagefault_enable();
+	preempt_enable();
+}
+
+unsigned int __nr_free_highpages(void);
+extern atomic_long_t _totalhigh_pages;
+
+static inline unsigned int nr_free_highpages(void)
+{
+	return __nr_free_highpages();
+}
+
+static inline unsigned long totalhigh_pages(void)
+{
+	return (unsigned long)atomic_long_read(&_totalhigh_pages);
+}
+
+static inline void totalhigh_pages_inc(void)
+{
+	atomic_long_inc(&_totalhigh_pages);
+}
+
+static inline void totalhigh_pages_add(long count)
+{
+	atomic_long_add(count, &_totalhigh_pages);
+}
+
+#else /* CONFIG_HIGHMEM */
+
+static inline struct page *kmap_to_page(void *addr)
+{
+	return virt_to_page(addr);
+}
+
+static inline void *kmap(struct page *page)
+{
+	might_sleep();
+	return page_address(page);
+}
+
+static inline void kunmap_high(struct page *page) { }
+static inline void kmap_flush_unused(void) { }
+
+static inline void kunmap(struct page *page)
+{
+#ifdef ARCH_HAS_FLUSH_ON_KUNMAP
+	kunmap_flush_on_unmap(page_address(page));
+#endif
+}
+
+static inline void *kmap_atomic(struct page *page)
+{
+	preempt_disable();
+	pagefault_disable();
+	return page_address(page);
+}
+
+static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot)
+{
+	return kmap_atomic(page);
+}
+
+static inline void *kmap_atomic_pfn(unsigned long pfn)
+{
+	return kmap_atomic(pfn_to_page(pfn));
+}
+
+static inline void __kunmap_atomic(void *addr)
+{
+#ifdef ARCH_HAS_FLUSH_ON_KUNMAP
+	kunmap_flush_on_unmap(addr);
+#endif
+	pagefault_enable();
+	preempt_enable();
+}
+
+static inline unsigned int nr_free_highpages(void) { return 0; }
+static inline unsigned long totalhigh_pages(void) { return 0UL; }
+
+#endif /* CONFIG_HIGHMEM */
+
+/*
+ * Prevent people trying to call kunmap_atomic() as if it were kunmap()
+ * kunmap_atomic() should get the return value of kmap_atomic, not the page.
+ */
+#define kunmap_atomic(__addr)					\
+do {								\
+	BUILD_BUG_ON(__same_type((__addr), struct page *));	\
+	__kunmap_atomic(__addr);				\
+} while (0)
+
+#endif
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 3180a8f7307f..7d098bd621f6 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -11,199 +11,125 @@
 
 #include <asm/cacheflush.h>
 
-#ifndef ARCH_HAS_FLUSH_ANON_PAGE
-static inline void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr)
-{
-}
-#endif
-
-#ifndef ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
-static inline void flush_kernel_dcache_page(struct page *page)
-{
-}
-static inline void flush_kernel_vmap_range(void *vaddr, int size)
-{
-}
-static inline void invalidate_kernel_vmap_range(void *vaddr, int size)
-{
-}
-#endif
+#include "highmem-internal.h"
 
-/*
- * Outside of CONFIG_HIGHMEM to support X86 32bit iomap_atomic() cruft.
+/**
+ * kmap - Map a page for long term usage
+ * @page:	Pointer to the page to be mapped
+ *
+ * Returns: The virtual address of the mapping
+ *
+ * Can only be invoked from preemptible task context because on 32bit
+ * systems with CONFIG_HIGHMEM enabled this function might sleep.
+ *
+ * For systems with CONFIG_HIGHMEM=n and for pages in the low memory area
+ * this returns the virtual address of the direct kernel mapping.
+ *
+ * The returned virtual address is globally visible and valid up to the
+ * point where it is unmapped via kunmap(). The pointer can be handed to
+ * other contexts.
+ *
+ * For highmem pages on 32bit systems this can be slow as the mapping space
+ * is limited and protected by a global lock. In case that there is no
+ * mapping slot available the function blocks until a slot is released via
+ * kunmap().
  */
-#ifdef CONFIG_KMAP_LOCAL
-void *__kmap_local_pfn_prot(unsigned long pfn, pgprot_t prot);
-void *__kmap_local_page_prot(struct page *page, pgprot_t prot);
-void kunmap_local_indexed(void *vaddr);
-#endif
-
-#ifdef CONFIG_HIGHMEM
-#include <asm/highmem.h>
+static inline void *kmap(struct page *page);
 
-#ifndef ARCH_HAS_KMAP_FLUSH_TLB
-static inline void kmap_flush_tlb(unsigned long addr) { }
-#endif
-
-#ifndef kmap_prot
-#define kmap_prot PAGE_KERNEL
-#endif
-
-void *kmap_high(struct page *page);
-static inline void *kmap(struct page *page)
-{
-	void *addr;
-
-	might_sleep();
-	if (!PageHighMem(page))
-		addr = page_address(page);
-	else
-		addr = kmap_high(page);
-	kmap_flush_tlb((unsigned long)addr);
-	return addr;
-}
+/**
+ * kunmap - Unmap the virtual address mapped by kmap()
+ * @addr:	Virtual address to be unmapped
+ *
+ * Counterpart to kmap(). A NOOP for CONFIG_HIGHMEM=n and for mappings of
+ * pages in the low memory area.
+ */
+static inline void kunmap(struct page *page);
 
-void kunmap_high(struct page *page);
+/**
+ * kmap_to_page - Get the page for a kmap'ed address
+ * @addr:	The address to look up
+ *
+ * Returns: The page which is mapped to @addr.
+ */
+static inline struct page *kmap_to_page(void *addr);
 
-static inline void kunmap(struct page *page)
-{
-	might_sleep();
-	if (!PageHighMem(page))
-		return;
-	kunmap_high(page);
-}
+/**
+ * kmap_flush_unused - Flush all unused kmap mappings in order to
+ *		       remove stray mappings
+ */
+static inline void kmap_flush_unused(void);
 
-/*
- * kmap_atomic/kunmap_atomic is significantly faster than kmap/kunmap because
- * no global lock is needed and because the kmap code must perform a global TLB
- * invalidation when the kmap pool wraps.
+/**
+ * kmap_atomic - Atomically map a page for temporary usage
+ * @page:	Pointer to the page to be mapped
+ *
+ * Returns: The virtual address of the mapping
+ *
+ * Side effect: On return pagefaults and preemption are disabled.
+ *
+ * Can be invoked from any context.
  *
- * However when holding an atomic kmap it is not legal to sleep, so atomic
- * kmaps are appropriate for short, tight code paths only.
+ * Requires careful handling when nesting multiple mappings because the map
+ * management is stack based. The unmap has to be in the reverse order of
+ * the map operation:
  *
- * The use of kmap_atomic/kunmap_atomic is discouraged - kmap/kunmap
- * gives a more generic (and caching) interface. But kmap_atomic can
- * be used in IRQ contexts, so in some (very limited) cases we need
- * it.
+ * addr1 = kmap_atomic(page1);
+ * addr2 = kmap_atomic(page2);
+ * ...
+ * kunmap_atomic(addr2);
+ * kunmap_atomic(addr1);
+ *
+ * Unmapping addr1 before addr2 is invalid and causes malfunction.
+ *
+ * Contrary to kmap() mappings the mapping is only valid in the context of
+ * the caller and cannot be handed to other contexts.
+ *
+ * On CONFIG_HIGHMEM=n kernels and for low memory pages this returns the
+ * virtual address of the direct mapping. Only real highmem pages are
+ * temporarily mapped.
+ *
+ * While it is significantly faster than kmap() it comes with restrictions
+ * about the pointer validity and the side effects of disabling page faults
+ * and preemption. Use it only when absolutely necessary, e.g. from non
+ * preemptible contexts.
  */
-static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot)
-{
-	preempt_disable();
-	pagefault_disable();
-	return __kmap_local_page_prot(page, prot);
-}
+static inline void *kmap_atomic(struct page *page);
 
-static inline void *kmap_atomic(struct page *page)
-{
-	return kmap_atomic_prot(page, kmap_prot);
-}
-
-static inline void *kmap_atomic_pfn(unsigned long pfn)
-{
-	preempt_disable();
-	pagefault_disable();
-	return __kmap_local_pfn_prot(pfn, kmap_prot);
-}
-
-static inline void __kunmap_atomic(void *addr)
-{
-	kunmap_local_indexed(addr);
-}
-
-/* declarations for linux/mm/highmem.c */
-unsigned int nr_free_highpages(void);
-extern atomic_long_t _totalhigh_pages;
-static inline unsigned long totalhigh_pages(void)
-{
-	return (unsigned long)atomic_long_read(&_totalhigh_pages);
-}
-
-static inline void totalhigh_pages_inc(void)
-{
-	atomic_long_inc(&_totalhigh_pages);
-}
-
-static inline void totalhigh_pages_add(long count)
-{
-	atomic_long_add(count, &_totalhigh_pages);
-}
-
-void kmap_flush_unused(void);
-
-struct page *kmap_to_page(void *addr);
-
-#else /* CONFIG_HIGHMEM */
-
-static inline unsigned int nr_free_highpages(void) { return 0; }
-
-static inline struct page *kmap_to_page(void *addr)
-{
-	return virt_to_page(addr);
-}
-
-static inline unsigned long totalhigh_pages(void) { return 0UL; }
+/**
+ * kunmap_atomic - Unmap the virtual address mapped by kmap_atomic()
+ * @addr:	Virtual address to be unmapped
+ *
+ * Counterpart to kmap_atomic().
+ *
+ * Undoes the side effects of kmap_atomic(), i.e. reenabling pagefaults and
+ * preemption.
+ *
+ * Other than that a NOOP for CONFIG_HIGHMEM=n and for mappings of pages
+ * in the low memory area. For real highmen pages the mapping which was
+ * established with kmap_atomic() is destroyed.
+ */
 
-static inline void *kmap(struct page *page)
-{
-	might_sleep();
-	return page_address(page);
-}
+/* Highmem related interfaces for management code */
+static inline unsigned int nr_free_highpages(void);
+static inline unsigned long totalhigh_pages(void);
 
-static inline void kunmap_high(struct page *page)
+#ifndef ARCH_HAS_FLUSH_ANON_PAGE
+static inline void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr)
 {
 }
-
-static inline void kunmap(struct page *page)
-{
-#ifdef ARCH_HAS_FLUSH_ON_KUNMAP
-	kunmap_flush_on_unmap(page_address(page));
 #endif
-}
 
-static inline void *kmap_atomic(struct page *page)
+#ifndef ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
+static inline void flush_kernel_dcache_page(struct page *page)
 {
-	preempt_disable();
-	pagefault_disable();
-	return page_address(page);
 }
-
-static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot)
+static inline void flush_kernel_vmap_range(void *vaddr, int size)
 {
-	return kmap_atomic(page);
 }
-
-static inline void *kmap_atomic_pfn(unsigned long pfn)
+static inline void invalidate_kernel_vmap_range(void *vaddr, int size)
 {
-	return kmap_atomic(pfn_to_page(pfn));
 }
-
-static inline void __kunmap_atomic(void *addr)
-{
-	/*
-	 * Mostly nothing to do in the CONFIG_HIGHMEM=n case as kunmap_atomic()
-	 * handles re-enabling faults and preemption
-	 */
-#ifdef ARCH_HAS_FLUSH_ON_KUNMAP
-	kunmap_flush_on_unmap(addr);
 #endif
-}
-
-#define kmap_flush_unused()	do {} while(0)
-
-
-#endif /* CONFIG_HIGHMEM */
-
-/*
- * Prevent people trying to call kunmap_atomic() as if it were kunmap()
- * kunmap_atomic() should get the return value of kmap_atomic, not the page.
- */
-#define kunmap_atomic(__addr)					\
-do {								\
-	BUILD_BUG_ON(__same_type((__addr), struct page *));	\
-	__kunmap_atomic(__addr);				\
-	pagefault_enable();					\
-	preempt_enable();					\
-} while (0)
 
 /* when CONFIG_HIGHMEM is not set these will be plain clear/copy_page */
 #ifndef clear_user_highpage
diff --git a/mm/highmem.c b/mm/highmem.c
index 499dfafd36b7..54bd233846c9 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -104,7 +104,7 @@ static inline wait_queue_head_t *get_pkmap_wait_queue_head(unsigned int color)
 atomic_long_t _totalhigh_pages __read_mostly;
 EXPORT_SYMBOL(_totalhigh_pages);
 
-unsigned int nr_free_highpages (void)
+unsigned int __nr_free_highpages (void)
 {
 	struct zone *zone;
 	unsigned int pages = 0;
@@ -141,7 +141,7 @@ pte_t * pkmap_page_table;
 		do { spin_unlock(&kmap_lock); (void)(flags); } while (0)
 #endif
 
-struct page *kmap_to_page(void *vaddr)
+struct page *__kmap_to_page(void *vaddr)
 {
 	unsigned long addr = (unsigned long)vaddr;
 
@@ -152,7 +152,7 @@ struct page *kmap_to_page(void *vaddr)
 
 	return virt_to_page(addr);
 }
-EXPORT_SYMBOL(kmap_to_page);
+EXPORT_SYMBOL(__kmap_to_page);
 
 static void flush_all_zero_pkmaps(void)
 {
@@ -194,10 +194,7 @@ static void flush_all_zero_pkmaps(void)
 		flush_tlb_kernel_range(PKMAP_ADDR(0), PKMAP_ADDR(LAST_PKMAP));
 }
 
-/**
- * kmap_flush_unused - flush all unused kmap mappings in order to remove stray mappings
- */
-void kmap_flush_unused(void)
+void __kmap_flush_unused(void)
 {
 	lock_kmap();
 	flush_all_zero_pkmaps();
-- 
cgit v1.2.3


From 3fcd6a230fa7d03bffcb831a81b40435c146c12b Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Thu, 3 Sep 2020 15:23:29 -0700
Subject: x86/cpu: Avoid cpuinfo-induced IPIing of idle CPUs

Currently, accessing /proc/cpuinfo sends IPIs to idle CPUs in order to
learn their clock frequency.  Which is a bit strange, given that waking
them from idle likely significantly changes their clock frequency.
This commit therefore avoids sending /proc/cpuinfo-induced IPIs to
idle CPUs.

[ paulmck: Also check for idle in arch_freq_prepare_all(). ]
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <x86@kernel.org>
---
 arch/x86/kernel/cpu/aperfmperf.c | 6 ++++++
 include/linux/rcutiny.h          | 2 ++
 include/linux/rcutree.h          | 1 +
 kernel/rcu/tree.c                | 8 ++++++++
 4 files changed, 17 insertions(+)

(limited to 'include/linux')

diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index dd3261dab0fb..22911deacb6e 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -14,6 +14,7 @@
 #include <linux/cpufreq.h>
 #include <linux/smp.h>
 #include <linux/sched/isolation.h>
+#include <linux/rcupdate.h>
 
 #include "cpu.h"
 
@@ -93,6 +94,9 @@ unsigned int aperfmperf_get_khz(int cpu)
 	if (!housekeeping_cpu(cpu, HK_FLAG_MISC))
 		return 0;
 
+	if (rcu_is_idle_cpu(cpu))
+		return 0; /* Idle CPUs are completely uninteresting. */
+
 	aperfmperf_snapshot_cpu(cpu, ktime_get(), true);
 	return per_cpu(samples.khz, cpu);
 }
@@ -112,6 +116,8 @@ void arch_freq_prepare_all(void)
 	for_each_online_cpu(cpu) {
 		if (!housekeeping_cpu(cpu, HK_FLAG_MISC))
 			continue;
+		if (rcu_is_idle_cpu(cpu))
+			continue; /* Idle CPUs are completely uninteresting. */
 		if (!aperfmperf_snapshot_cpu(cpu, now, false))
 			wait = true;
 	}
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 7c1ecdb356d8..2a97334eb786 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -89,6 +89,8 @@ static inline void rcu_irq_enter_irqson(void) { }
 static inline void rcu_irq_exit(void) { }
 static inline void rcu_irq_exit_preempt(void) { }
 static inline void rcu_irq_exit_check_preempt(void) { }
+#define rcu_is_idle_cpu(cpu) \
+	(is_idle_task(current) && !in_nmi() && !in_irq() && !in_serving_softirq())
 static inline void exit_rcu(void) { }
 static inline bool rcu_preempt_need_deferred_qs(struct task_struct *t)
 {
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 59eb5cd567d7..df578b73960f 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -50,6 +50,7 @@ void rcu_irq_exit(void);
 void rcu_irq_exit_preempt(void);
 void rcu_irq_enter_irqson(void);
 void rcu_irq_exit_irqson(void);
+bool rcu_is_idle_cpu(int cpu);
 
 #ifdef CONFIG_PROVE_RCU
 void rcu_irq_exit_check_preempt(void);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 06895ef85d69..1d84c0b6a9f3 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -341,6 +341,14 @@ static bool rcu_dynticks_in_eqs(int snap)
 	return !(snap & RCU_DYNTICK_CTRL_CTR);
 }
 
+/* Return true if the specified CPU is currently idle from an RCU viewpoint.  */
+bool rcu_is_idle_cpu(int cpu)
+{
+	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+
+	return rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp));
+}
+
 /*
  * Return true if the CPU corresponding to the specified rcu_data
  * structure has spent some time in an extended quiescent state since
-- 
cgit v1.2.3


From ede7dc7fa0af619afc08995776eadb9ff3b0a711 Mon Sep 17 00:00:00 2001
From: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Date: Thu, 5 Nov 2020 19:58:54 -0800
Subject: jbd2: rename j_maxlen to j_total_len and add
 jbd2_journal_max_txn_bufs

The on-disk superblock field sb->s_maxlen represents the total size of
the journal including the fast commit area and is no more the max
number of blocks available for a transaction. The maximum number of
blocks available to a transaction is reduced by the number of fast
commit blocks. So, this patch renames j_maxlen to j_total_len to
better represent its intent. Also, it adds a function to calculate max
number of bufs available for a transaction.

Suggested-by: Jan Kara <jack@suse.cz>
Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Link: https://lore.kernel.org/r/20201106035911.1942128-6-harshadshirwadkar@gmail.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/fsmap.c      |  2 +-
 fs/ext4/super.c      |  2 +-
 fs/jbd2/commit.c     |  2 +-
 fs/jbd2/journal.c    | 12 ++++++------
 fs/jbd2/recovery.c   |  6 +++---
 fs/ocfs2/journal.c   |  2 +-
 include/linux/jbd2.h |  9 +++++++--
 7 files changed, 20 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c
index b232c2767534..4c2a9fe30067 100644
--- a/fs/ext4/fsmap.c
+++ b/fs/ext4/fsmap.c
@@ -280,7 +280,7 @@ static int ext4_getfsmap_logdev(struct super_block *sb, struct ext4_fsmap *keys,
 
 	/* Fabricate an rmap entry for the external log device. */
 	irec.fmr_physical = journal->j_blk_offset;
-	irec.fmr_length = journal->j_maxlen;
+	irec.fmr_length = journal->j_total_len;
 	irec.fmr_owner = EXT4_FMR_OWN_LOG;
 	irec.fmr_flags = 0;
 
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 738a6dd4957d..8a6dd433bb70 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3976,7 +3976,7 @@ int ext4_calculate_overhead(struct super_block *sb)
 	 * loaded or not
 	 */
 	if (sbi->s_journal && !sbi->s_journal_bdev)
-		overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_maxlen);
+		overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_total_len);
 	else if (ext4_has_feature_journal(sb) && !sbi->s_journal && j_inum) {
 		/* j_inum for internal journal is non-zero */
 		j_inode = ext4_get_journal_inode(sb, j_inum);
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index fa688e163a80..ec516490cb35 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -801,7 +801,7 @@ start_journal_io:
 		if (first_block < journal->j_tail)
 			freed += journal->j_last - journal->j_first;
 		/* Update tail only if we free significant amount of space */
-		if (freed < journal->j_maxlen / 4)
+		if (freed < jbd2_journal_get_max_txn_bufs(journal))
 			update_tail = 0;
 	}
 	J_ASSERT(commit_transaction->t_state == T_COMMIT);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 0c7c42bd530f..c3c768248527 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1348,7 +1348,7 @@ static journal_t *journal_init_common(struct block_device *bdev,
 	journal->j_dev = bdev;
 	journal->j_fs_dev = fs_dev;
 	journal->j_blk_offset = start;
-	journal->j_maxlen = len;
+	journal->j_total_len = len;
 	/* We need enough buffers to write out full descriptor block. */
 	n = journal->j_blocksize / jbd2_min_tag_size();
 	journal->j_wbufsize = n;
@@ -1531,7 +1531,7 @@ static int journal_reset(journal_t *journal)
 	journal->j_commit_sequence = journal->j_transaction_sequence - 1;
 	journal->j_commit_request = journal->j_commit_sequence;
 
-	journal->j_max_transaction_buffers = journal->j_maxlen / 4;
+	journal->j_max_transaction_buffers = jbd2_journal_get_max_txn_bufs(journal);
 
 	/*
 	 * As a special case, if the on-disk copy is already marked as needing
@@ -1792,15 +1792,15 @@ static int journal_get_superblock(journal_t *journal)
 		goto out;
 	}
 
-	if (be32_to_cpu(sb->s_maxlen) < journal->j_maxlen)
-		journal->j_maxlen = be32_to_cpu(sb->s_maxlen);
-	else if (be32_to_cpu(sb->s_maxlen) > journal->j_maxlen) {
+	if (be32_to_cpu(sb->s_maxlen) < journal->j_total_len)
+		journal->j_total_len = be32_to_cpu(sb->s_maxlen);
+	else if (be32_to_cpu(sb->s_maxlen) > journal->j_total_len) {
 		printk(KERN_WARNING "JBD2: journal file too short\n");
 		goto out;
 	}
 
 	if (be32_to_cpu(sb->s_first) == 0 ||
-	    be32_to_cpu(sb->s_first) >= journal->j_maxlen) {
+	    be32_to_cpu(sb->s_first) >= journal->j_total_len) {
 		printk(KERN_WARNING
 			"JBD2: Invalid start block of journal: %u\n",
 			be32_to_cpu(sb->s_first));
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index eb2606133cd8..dc0694fcfcd1 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -74,8 +74,8 @@ static int do_readahead(journal_t *journal, unsigned int start)
 
 	/* Do up to 128K of readahead */
 	max = start + (128 * 1024 / journal->j_blocksize);
-	if (max > journal->j_maxlen)
-		max = journal->j_maxlen;
+	if (max > journal->j_total_len)
+		max = journal->j_total_len;
 
 	/* Do the readahead itself.  We'll submit MAXBUF buffer_heads at
 	 * a time to the block device IO layer. */
@@ -134,7 +134,7 @@ static int jread(struct buffer_head **bhp, journal_t *journal,
 
 	*bhp = NULL;
 
-	if (offset >= journal->j_maxlen) {
+	if (offset >= journal->j_total_len) {
 		printk(KERN_ERR "JBD2: corrupted journal superblock\n");
 		return -EFSCORRUPTED;
 	}
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index b9a9d69dde7e..db52e843002a 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -877,7 +877,7 @@ int ocfs2_journal_init(struct ocfs2_journal *journal, int *dirty)
 		goto done;
 	}
 
-	trace_ocfs2_journal_init_maxlen(j_journal->j_maxlen);
+	trace_ocfs2_journal_init_maxlen(j_journal->j_total_len);
 
 	*dirty = (le32_to_cpu(di->id1.journal1.ij_flags) &
 		  OCFS2_JOURNAL_DIRTY_FL);
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 1d5566af48ac..e0b6b53eae64 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -988,9 +988,9 @@ struct journal_s
 	struct block_device	*j_fs_dev;
 
 	/**
-	 * @j_maxlen: Total maximum capacity of the journal region on disk.
+	 * @j_total_len: Total maximum capacity of the journal region on disk.
 	 */
-	unsigned int		j_maxlen;
+	unsigned int		j_total_len;
 
 	/**
 	 * @j_reserved_credits:
@@ -1624,6 +1624,11 @@ int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode);
 int jbd2_fc_wait_bufs(journal_t *journal, int num_blks);
 int jbd2_fc_release_bufs(journal_t *journal);
 
+static inline int jbd2_journal_get_max_txn_bufs(journal_t *journal)
+{
+	return (journal->j_total_len - journal->j_fc_wbufsize) / 4;
+}
+
 /*
  * is_journal_abort
  *
-- 
cgit v1.2.3


From a1e5e465b31d6015fccb359d99053b39e5180466 Mon Sep 17 00:00:00 2001
From: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Date: Thu, 5 Nov 2020 19:58:55 -0800
Subject: ext4: clean up the JBD2 API that initializes fast commits

This patch removes jbd2_fc_init() API and its related functions to
simplify enabling fast commits. With this change, the number of fast
commit blocks to use is solely determined by the JBD2 layer. So, we
move the default value for minimum number of fast commit blocks from
ext4/fast_commit.h to include/linux/jbd2.h. However, whether or not to
use fast commits is determined by the file system. The file system
just sets the fast commit feature using
jbd2_journal_set_features(). JBD2 layer then determines how many
blocks to use for fast commits (based on the value found in the JBD2
superblock).

Note that the JBD2 feature flag of fast commits is just an indication
that there are fast commit blocks present on disk. It doesn't tell
JBD2 layer about the intent of the file system of whether to it wants
to use fast commit or not. That's why, we blindly clear the fast
commit flag in journal_reset() after the recovery is done.

Suggested-by: Jan Kara <jack@suse.cz>
Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Link: https://lore.kernel.org/r/20201106035911.1942128-7-harshadshirwadkar@gmail.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/fast_commit.c | 14 --------
 fs/ext4/fast_commit.h |  3 --
 fs/ext4/super.c       |  8 +++++
 fs/jbd2/journal.c     | 96 ++++++++++++++++++++++++++++++---------------------
 include/linux/jbd2.h  |  2 +-
 5 files changed, 65 insertions(+), 58 deletions(-)

(limited to 'include/linux')

diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index 9399e9cccb7e..bab60c5d5095 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -2091,8 +2091,6 @@ static int ext4_fc_replay(journal_t *journal, struct buffer_head *bh,
 
 void ext4_fc_init(struct super_block *sb, journal_t *journal)
 {
-	int num_fc_blocks;
-
 	/*
 	 * We set replay callback even if fast commit disabled because we may
 	 * could still have fast commit blocks that need to be replayed even if
@@ -2102,18 +2100,6 @@ void ext4_fc_init(struct super_block *sb, journal_t *journal)
 	if (!test_opt2(sb, JOURNAL_FAST_COMMIT))
 		return;
 	journal->j_fc_cleanup_callback = ext4_fc_cleanup;
-	if (!buffer_uptodate(journal->j_sb_buffer)
-		&& ext4_read_bh_lock(journal->j_sb_buffer, REQ_META | REQ_PRIO,
-					true)) {
-		ext4_msg(sb, KERN_ERR, "I/O error on journal");
-		return;
-	}
-	num_fc_blocks = be32_to_cpu(journal->j_superblock->s_num_fc_blks);
-	if (jbd2_fc_init(journal, num_fc_blocks ? num_fc_blocks :
-					EXT4_NUM_FC_BLKS)) {
-		pr_warn("Error while enabling fast commits, turning off.");
-		ext4_clear_feature_fast_commit(sb);
-	}
 }
 
 const char *fc_ineligible_reasons[] = {
diff --git a/fs/ext4/fast_commit.h b/fs/ext4/fast_commit.h
index 140fbb6af19e..1d96e0ac8138 100644
--- a/fs/ext4/fast_commit.h
+++ b/fs/ext4/fast_commit.h
@@ -3,9 +3,6 @@
 #ifndef __FAST_COMMIT_H__
 #define __FAST_COMMIT_H__
 
-/* Number of blocks in journal area to allocate for fast commits */
-#define EXT4_NUM_FC_BLKS		256
-
 /* Fast commit tags */
 #define EXT4_FC_TAG_ADD_RANGE		0x0001
 #define EXT4_FC_TAG_DEL_RANGE		0x0002
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 8a6dd433bb70..ba02d7c86fb3 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -4857,6 +4857,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		goto failed_mount_wq;
 	}
 
+	if (test_opt2(sb, JOURNAL_FAST_COMMIT) &&
+		!jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0,
+					  JBD2_FEATURE_INCOMPAT_FAST_COMMIT)) {
+		ext4_msg(sb, KERN_ERR,
+			"Failed to set fast commit journal feature");
+		goto failed_mount_wq;
+	}
+
 	/* We have now updated the journal if required, so we can
 	 * validate the data journaling mode. */
 	switch (test_opt(sb, DATA_FLAGS)) {
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index c3c768248527..500152f0421a 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1352,19 +1352,12 @@ static journal_t *journal_init_common(struct block_device *bdev,
 	/* We need enough buffers to write out full descriptor block. */
 	n = journal->j_blocksize / jbd2_min_tag_size();
 	journal->j_wbufsize = n;
+	journal->j_fc_wbuf = NULL;
 	journal->j_wbuf = kmalloc_array(n, sizeof(struct buffer_head *),
 					GFP_KERNEL);
 	if (!journal->j_wbuf)
 		goto err_cleanup;
 
-	if (journal->j_fc_wbufsize > 0) {
-		journal->j_fc_wbuf = kmalloc_array(journal->j_fc_wbufsize,
-					sizeof(struct buffer_head *),
-					GFP_KERNEL);
-		if (!journal->j_fc_wbuf)
-			goto err_cleanup;
-	}
-
 	bh = getblk_unmovable(journal->j_dev, start, journal->j_blocksize);
 	if (!bh) {
 		pr_err("%s: Cannot get buffer for journal superblock\n",
@@ -1378,23 +1371,11 @@ static journal_t *journal_init_common(struct block_device *bdev,
 
 err_cleanup:
 	kfree(journal->j_wbuf);
-	kfree(journal->j_fc_wbuf);
 	jbd2_journal_destroy_revoke(journal);
 	kfree(journal);
 	return NULL;
 }
 
-int jbd2_fc_init(journal_t *journal, int num_fc_blks)
-{
-	journal->j_fc_wbufsize = num_fc_blks;
-	journal->j_fc_wbuf = kmalloc_array(journal->j_fc_wbufsize,
-				sizeof(struct buffer_head *), GFP_KERNEL);
-	if (!journal->j_fc_wbuf)
-		return -ENOMEM;
-	return 0;
-}
-EXPORT_SYMBOL(jbd2_fc_init);
-
 /* jbd2_journal_init_dev and jbd2_journal_init_inode:
  *
  * Create a journal structure assigned some fixed set of disk blocks to
@@ -1512,16 +1493,7 @@ static int journal_reset(journal_t *journal)
 	}
 
 	journal->j_first = first;
-
-	if (jbd2_has_feature_fast_commit(journal) &&
-	    journal->j_fc_wbufsize > 0) {
-		journal->j_fc_last = last;
-		journal->j_last = last - journal->j_fc_wbufsize;
-		journal->j_fc_first = journal->j_last + 1;
-		journal->j_fc_off = 0;
-	} else {
-		journal->j_last = last;
-	}
+	journal->j_last = last;
 
 	journal->j_head = journal->j_first;
 	journal->j_tail = journal->j_first;
@@ -1533,6 +1505,13 @@ static int journal_reset(journal_t *journal)
 
 	journal->j_max_transaction_buffers = jbd2_journal_get_max_txn_bufs(journal);
 
+	/*
+	 * Now that journal recovery is done, turn fast commits off here. This
+	 * way, if fast commit was enabled before the crash but if now FS has
+	 * disabled it, we don't enable fast commits.
+	 */
+	jbd2_clear_feature_fast_commit(journal);
+
 	/*
 	 * As a special case, if the on-disk copy is already marked as needing
 	 * no recovery (s_start == 0), then we can safely defer the superblock
@@ -1872,6 +1851,7 @@ static int load_superblock(journal_t *journal)
 {
 	int err;
 	journal_superblock_t *sb;
+	int num_fc_blocks;
 
 	err = journal_get_superblock(journal);
 	if (err)
@@ -1883,15 +1863,17 @@ static int load_superblock(journal_t *journal)
 	journal->j_tail = be32_to_cpu(sb->s_start);
 	journal->j_first = be32_to_cpu(sb->s_first);
 	journal->j_errno = be32_to_cpu(sb->s_errno);
+	journal->j_last = be32_to_cpu(sb->s_maxlen);
 
-	if (jbd2_has_feature_fast_commit(journal) &&
-	    journal->j_fc_wbufsize > 0) {
+	if (jbd2_has_feature_fast_commit(journal)) {
 		journal->j_fc_last = be32_to_cpu(sb->s_maxlen);
-		journal->j_last = journal->j_fc_last - journal->j_fc_wbufsize;
+		num_fc_blocks = be32_to_cpu(sb->s_num_fc_blks);
+		if (!num_fc_blocks)
+			num_fc_blocks = JBD2_MIN_FC_BLOCKS;
+		if (journal->j_last - num_fc_blocks >= JBD2_MIN_JOURNAL_BLOCKS)
+			journal->j_last = journal->j_fc_last - num_fc_blocks;
 		journal->j_fc_first = journal->j_last + 1;
 		journal->j_fc_off = 0;
-	} else {
-		journal->j_last = be32_to_cpu(sb->s_maxlen);
 	}
 
 	return 0;
@@ -1954,9 +1936,6 @@ int jbd2_journal_load(journal_t *journal)
 	 */
 	journal->j_flags &= ~JBD2_ABORT;
 
-	if (journal->j_fc_wbufsize > 0)
-		jbd2_journal_set_features(journal, 0, 0,
-					  JBD2_FEATURE_INCOMPAT_FAST_COMMIT);
 	/* OK, we've finished with the dynamic journal bits:
 	 * reinitialise the dynamic contents of the superblock in memory
 	 * and reset them on disk. */
@@ -2040,8 +2019,7 @@ int jbd2_journal_destroy(journal_t *journal)
 		jbd2_journal_destroy_revoke(journal);
 	if (journal->j_chksum_driver)
 		crypto_free_shash(journal->j_chksum_driver);
-	if (journal->j_fc_wbufsize > 0)
-		kfree(journal->j_fc_wbuf);
+	kfree(journal->j_fc_wbuf);
 	kfree(journal->j_wbuf);
 	kfree(journal);
 
@@ -2116,6 +2094,37 @@ int jbd2_journal_check_available_features(journal_t *journal, unsigned long comp
 	return 0;
 }
 
+static int
+jbd2_journal_initialize_fast_commit(journal_t *journal)
+{
+	journal_superblock_t *sb = journal->j_superblock;
+	unsigned long long num_fc_blks;
+
+	num_fc_blks = be32_to_cpu(sb->s_num_fc_blks);
+	if (num_fc_blks == 0)
+		num_fc_blks = JBD2_MIN_FC_BLOCKS;
+	if (journal->j_last - num_fc_blks < JBD2_MIN_JOURNAL_BLOCKS)
+		return -ENOSPC;
+
+	/* Are we called twice? */
+	WARN_ON(journal->j_fc_wbuf != NULL);
+	journal->j_fc_wbuf = kmalloc_array(num_fc_blks,
+				sizeof(struct buffer_head *), GFP_KERNEL);
+	if (!journal->j_fc_wbuf)
+		return -ENOMEM;
+
+	journal->j_fc_wbufsize = num_fc_blks;
+	journal->j_fc_last = journal->j_last;
+	journal->j_last = journal->j_fc_last - num_fc_blks;
+	journal->j_fc_first = journal->j_last + 1;
+	journal->j_fc_off = 0;
+	journal->j_free = journal->j_last - journal->j_first;
+	journal->j_max_transaction_buffers =
+		jbd2_journal_get_max_txn_bufs(journal);
+
+	return 0;
+}
+
 /**
  * int jbd2_journal_set_features() - Mark a given journal feature in the superblock
  * @journal: Journal to act on.
@@ -2159,6 +2168,13 @@ int jbd2_journal_set_features(journal_t *journal, unsigned long compat,
 
 	sb = journal->j_superblock;
 
+	if (incompat & JBD2_FEATURE_INCOMPAT_FAST_COMMIT) {
+		if (jbd2_journal_initialize_fast_commit(journal)) {
+			pr_err("JBD2: Cannot enable fast commits.\n");
+			return 0;
+		}
+	}
+
 	/* Load the checksum driver if necessary */
 	if ((journal->j_chksum_driver == NULL) &&
 	    INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) {
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index e0b6b53eae64..b2caf7bbd8e5 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -68,6 +68,7 @@ extern void *jbd2_alloc(size_t size, gfp_t flags);
 extern void jbd2_free(void *ptr, size_t size);
 
 #define JBD2_MIN_JOURNAL_BLOCKS 1024
+#define JBD2_MIN_FC_BLOCKS	256
 
 #ifdef __KERNEL__
 
@@ -1614,7 +1615,6 @@ extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *);
 extern int jbd2_cleanup_journal_tail(journal_t *);
 
 /* Fast commit related APIs */
-int jbd2_fc_init(journal_t *journal, int num_fc_blks);
 int jbd2_fc_begin_commit(journal_t *journal, tid_t tid);
 int jbd2_fc_end_commit(journal_t *journal);
 int jbd2_fc_end_commit_fallback(journal_t *journal, tid_t tid);
-- 
cgit v1.2.3


From c460e5edc85a063ec9cb60addff93d00ed378701 Mon Sep 17 00:00:00 2001
From: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Date: Thu, 5 Nov 2020 19:58:57 -0800
Subject: jbd2: don't use state lock during commit path

Variables journal->j_fc_off, journal->j_fc_wbuf are accessed during
commit path. Since today we allow only one process to perform a fast
commit, there is no need take state lock before accessing these
variables. This patch removes these locks and adds comments to
describe this.

Suggested-by: Jan Kara <jack@suse.cz>
Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Link: https://lore.kernel.org/r/20201106035911.1942128-9-harshadshirwadkar@gmail.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/jbd2/journal.c    |  6 ------
 include/linux/jbd2.h | 10 ++++++----
 2 files changed, 6 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 500152f0421a..778ea50fc8d1 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -865,7 +865,6 @@ int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out)
 	int fc_off;
 
 	*bh_out = NULL;
-	write_lock(&journal->j_state_lock);
 
 	if (journal->j_fc_off + journal->j_fc_first < journal->j_fc_last) {
 		fc_off = journal->j_fc_off;
@@ -874,7 +873,6 @@ int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out)
 	} else {
 		ret = -EINVAL;
 	}
-	write_unlock(&journal->j_state_lock);
 
 	if (ret)
 		return ret;
@@ -909,9 +907,7 @@ int jbd2_fc_wait_bufs(journal_t *journal, int num_blks)
 	struct buffer_head *bh;
 	int i, j_fc_off;
 
-	read_lock(&journal->j_state_lock);
 	j_fc_off = journal->j_fc_off;
-	read_unlock(&journal->j_state_lock);
 
 	/*
 	 * Wait in reverse order to minimize chances of us being woken up before
@@ -939,9 +935,7 @@ int jbd2_fc_release_bufs(journal_t *journal)
 	struct buffer_head *bh;
 	int i, j_fc_off;
 
-	read_lock(&journal->j_state_lock);
 	j_fc_off = journal->j_fc_off;
-	read_unlock(&journal->j_state_lock);
 
 	/*
 	 * Wait in reverse order to minimize chances of us being woken up before
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index b2caf7bbd8e5..5f0ef6380b0c 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -945,8 +945,9 @@ struct journal_s
 	/**
 	 * @j_fc_off:
 	 *
-	 * Number of fast commit blocks currently allocated.
-	 * [j_state_lock].
+	 * Number of fast commit blocks currently allocated. Accessed only
+	 * during fast commit. Currently only process can do fast commit, so
+	 * this field is not protected by any lock.
 	 */
 	unsigned long		j_fc_off;
 
@@ -1109,8 +1110,9 @@ struct journal_s
 	struct buffer_head	**j_wbuf;
 
 	/**
-	 * @j_fc_wbuf: Array of fast commit bhs for
-	 * jbd2_journal_commit_transaction.
+	 * @j_fc_wbuf: Array of fast commit bhs for fast commit. Accessed only
+	 * during a fast commit. Currently only process can do fast commit, so
+	 * this field is not protected by any lock.
 	 */
 	struct buffer_head	**j_fc_wbuf;
 
-- 
cgit v1.2.3


From 0bce577bf9cae13ae32d391432d0030e3f67fc1d Mon Sep 17 00:00:00 2001
From: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Date: Thu, 5 Nov 2020 19:58:58 -0800
Subject: jbd2: don't pass tid to jbd2_fc_end_commit_fallback()

In jbd2_fc_end_commit_fallback(), we know which tid to commit. There's
no need for caller to pass it.

Suggested-by: Jan Kara <jack@suse.cz>
Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Link: https://lore.kernel.org/r/20201106035911.1942128-10-harshadshirwadkar@gmail.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/fast_commit.c |  2 +-
 fs/jbd2/journal.c     | 12 +++++++++---
 include/linux/jbd2.h  |  2 +-
 3 files changed, 11 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index bab60c5d5095..e69c580fa91e 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -1143,7 +1143,7 @@ out:
 		"Fast commit ended with blks = %d, reason = %d, subtid - %d",
 		nblks, reason, subtid);
 	if (reason == EXT4_FC_REASON_FC_FAILED)
-		return jbd2_fc_end_commit_fallback(journal, commit_tid);
+		return jbd2_fc_end_commit_fallback(journal);
 	if (reason == EXT4_FC_REASON_FC_START_FAILED ||
 		reason == EXT4_FC_REASON_INELIGIBLE)
 		return jbd2_complete_transaction(journal, commit_tid);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 778ea50fc8d1..59166e299cde 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -777,13 +777,19 @@ static int __jbd2_fc_end_commit(journal_t *journal, tid_t tid, bool fallback)
 
 int jbd2_fc_end_commit(journal_t *journal)
 {
-	return __jbd2_fc_end_commit(journal, 0, 0);
+	return __jbd2_fc_end_commit(journal, 0, false);
 }
 EXPORT_SYMBOL(jbd2_fc_end_commit);
 
-int jbd2_fc_end_commit_fallback(journal_t *journal, tid_t tid)
+int jbd2_fc_end_commit_fallback(journal_t *journal)
 {
-	return __jbd2_fc_end_commit(journal, tid, 1);
+	tid_t tid;
+
+	read_lock(&journal->j_state_lock);
+	tid = journal->j_running_transaction ?
+		journal->j_running_transaction->t_tid : 0;
+	read_unlock(&journal->j_state_lock);
+	return __jbd2_fc_end_commit(journal, tid, true);
 }
 EXPORT_SYMBOL(jbd2_fc_end_commit_fallback);
 
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 5f0ef6380b0c..1c49fd62ff2e 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1619,7 +1619,7 @@ extern int jbd2_cleanup_journal_tail(journal_t *);
 /* Fast commit related APIs */
 int jbd2_fc_begin_commit(journal_t *journal, tid_t tid);
 int jbd2_fc_end_commit(journal_t *journal);
-int jbd2_fc_end_commit_fallback(journal_t *journal, tid_t tid);
+int jbd2_fc_end_commit_fallback(journal_t *journal);
 int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out);
 int jbd2_submit_inode_data(struct jbd2_inode *jinode);
 int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode);
-- 
cgit v1.2.3


From eda2845ae5e0ae466c1aca715d642b4977311747 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 30 Oct 2020 18:59:15 +0200
Subject: irqdomain: Remove unused of_device_id forward declaration

There is no users of of_device_id in irqdomain.h. Drop it.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lore.kernel.org/r/20201030165919.86234-2-andriy.shevchenko@linux.intel.com
---
 include/linux/irqdomain.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index 71535e87109f..56642188ec21 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -38,7 +38,6 @@
 
 struct device_node;
 struct irq_domain;
-struct of_device_id;
 struct irq_chip;
 struct irq_data;
 struct cpumask;
-- 
cgit v1.2.3


From 08219fb1efae451c83281cb6ba4bb6c35ac88fab Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 30 Oct 2020 18:59:16 +0200
Subject: irqdomain: Add forward declaration of fwnode_handle

irqdomain.h is a user of struct fwnode_handle. Add forward declaration of it.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lore.kernel.org/r/20201030165919.86234-3-andriy.shevchenko@linux.intel.com
---
 include/linux/irqdomain.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index 56642188ec21..d21f75d294d7 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -37,6 +37,7 @@
 #include <linux/radix-tree.h>
 
 struct device_node;
+struct fwnode_handle;
 struct irq_domain;
 struct irq_chip;
 struct irq_data;
-- 
cgit v1.2.3


From b6e95788fde8c9bc9da729102085dd36a5a0cda6 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 30 Oct 2020 18:59:18 +0200
Subject: irqdomain: Introduce irq_domain_create_legacy() API

Introduce irq_domain_create_legacy() API which is functional equivalent
to the existing irq_domain_add_legacy(), but takes a pointer to the struct
fwnode_handle as a parameter.

This is useful for non OF systems.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lore.kernel.org/r/20201030165919.86234-5-andriy.shevchenko@linux.intel.com
---
 Documentation/core-api/irq/irq-domain.rst |  6 ++++++
 include/linux/irqdomain.h                 |  6 ++++++
 kernel/irq/irqdomain.c                    | 17 ++++++++++++++---
 3 files changed, 26 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/core-api/irq/irq-domain.rst b/Documentation/core-api/irq/irq-domain.rst
index 096db12f32d5..a77c24c27f7b 100644
--- a/Documentation/core-api/irq/irq-domain.rst
+++ b/Documentation/core-api/irq/irq-domain.rst
@@ -147,6 +147,7 @@ Legacy
 	irq_domain_add_simple()
 	irq_domain_add_legacy()
 	irq_domain_add_legacy_isa()
+	irq_domain_create_legacy()
 
 The Legacy mapping is a special case for drivers that already have a
 range of irq_descs allocated for the hwirqs.  It is used when the
@@ -185,6 +186,11 @@ that the driver using the simple domain call irq_create_mapping()
 before any irq_find_mapping() since the latter will actually work
 for the static IRQ assignment case.
 
+irq_domain_add_legacy() and irq_domain_create_legacy() are functionally
+equivalent, except for the first argument is different - the former
+accepts an Open Firmware specific 'struct device_node', while the latter
+accepts a more general abstraction 'struct fwnode_handle'.
+
 Hierarchy IRQ domain
 --------------------
 
diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index d21f75d294d7..77bf7d84c673 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -271,6 +271,12 @@ struct irq_domain *irq_domain_add_legacy(struct device_node *of_node,
 					 irq_hw_number_t first_hwirq,
 					 const struct irq_domain_ops *ops,
 					 void *host_data);
+struct irq_domain *irq_domain_create_legacy(struct fwnode_handle *fwnode,
+					    unsigned int size,
+					    unsigned int first_irq,
+					    irq_hw_number_t first_hwirq,
+					    const struct irq_domain_ops *ops,
+					    void *host_data);
 extern struct irq_domain *irq_find_matching_fwspec(struct irq_fwspec *fwspec,
 						   enum irq_domain_bus_token bus_token);
 extern bool irq_domain_check_msi_remap(void);
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 831526f2e728..9c9cb8829f7a 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -350,17 +350,28 @@ struct irq_domain *irq_domain_add_legacy(struct device_node *of_node,
 					 irq_hw_number_t first_hwirq,
 					 const struct irq_domain_ops *ops,
 					 void *host_data)
+{
+	return irq_domain_create_legacy(of_node_to_fwnode(of_node), size,
+					first_irq, first_hwirq, ops, host_data);
+}
+EXPORT_SYMBOL_GPL(irq_domain_add_legacy);
+
+struct irq_domain *irq_domain_create_legacy(struct fwnode_handle *fwnode,
+					 unsigned int size,
+					 unsigned int first_irq,
+					 irq_hw_number_t first_hwirq,
+					 const struct irq_domain_ops *ops,
+					 void *host_data)
 {
 	struct irq_domain *domain;
 
-	domain = __irq_domain_add(of_node_to_fwnode(of_node), first_hwirq + size,
-				  first_hwirq + size, 0, ops, host_data);
+	domain = __irq_domain_add(fwnode, first_hwirq + size, first_hwirq + size, 0, ops, host_data);
 	if (domain)
 		irq_domain_associate_many(domain, first_irq, first_hwirq, size);
 
 	return domain;
 }
-EXPORT_SYMBOL_GPL(irq_domain_add_legacy);
+EXPORT_SYMBOL_GPL(irq_domain_create_legacy);
 
 /**
  * irq_find_matching_fwspec() - Locates a domain for a given fwspec
-- 
cgit v1.2.3


From 1d4ef9b39ebecca827642b8897d2d79ea2026682 Mon Sep 17 00:00:00 2001
From: Cristian Pop <cristian.pop@analog.com>
Date: Mon, 28 Sep 2020 12:09:55 +0300
Subject: iio: core: Add optional symbolic label to a device channel

If a label is defined in the device tree for this channel add that
to the channel specific attributes. This is useful for userspace to
be able to identify an individual channel.

Signed-off-by: Cristian Pop <cristian.pop@analog.com>
Link: https://lore.kernel.org/r/20200928090959.88842-1-cristian.pop@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/industrialio-core.c | 41 +++++++++++++++++++++++++++++++++++++++++
 include/linux/iio/iio.h         |  6 ++++++
 2 files changed, 47 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index 9955672fc16a..0402be441ffb 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -673,6 +673,19 @@ ssize_t iio_format_value(char *buf, unsigned int type, int size, int *vals)
 }
 EXPORT_SYMBOL_GPL(iio_format_value);
 
+static ssize_t iio_read_channel_label(struct device *dev,
+				      struct device_attribute *attr,
+				      char *buf)
+{
+	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
+	struct iio_dev_attr *this_attr = to_iio_dev_attr(attr);
+
+	if (!indio_dev->info->read_label)
+		return -EINVAL;
+
+	return indio_dev->info->read_label(indio_dev, this_attr->c, buf);
+}
+
 static ssize_t iio_read_channel_info(struct device *dev,
 				     struct device_attribute *attr,
 				     char *buf)
@@ -1141,6 +1154,29 @@ error_iio_dev_attr_free:
 	return ret;
 }
 
+static int iio_device_add_channel_label(struct iio_dev *indio_dev,
+					 struct iio_chan_spec const *chan)
+{
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
+	int ret;
+
+	if (!indio_dev->info->read_label)
+		return 0;
+
+	ret = __iio_add_chan_devattr("label",
+				     chan,
+				     &iio_read_channel_label,
+				     NULL,
+				     0,
+				     IIO_SEPARATE,
+				     &indio_dev->dev,
+				     &iio_dev_opaque->channel_attr_list);
+	if (ret < 0)
+		return ret;
+
+	return 1;
+}
+
 static int iio_device_add_info_mask_type(struct iio_dev *indio_dev,
 					 struct iio_chan_spec const *chan,
 					 enum iio_shared_by shared_by,
@@ -1274,6 +1310,11 @@ static int iio_device_add_channel_sysfs(struct iio_dev *indio_dev,
 		return ret;
 	attrcount += ret;
 
+	ret = iio_device_add_channel_label(indio_dev, chan);
+	if (ret < 0)
+		return ret;
+	attrcount += ret;
+
 	if (chan->ext_info) {
 		unsigned int i = 0;
 		for (ext_info = chan->ext_info; ext_info->name; ext_info++) {
diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index 2e45b3ceafa7..9a3cf4815148 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -362,6 +362,8 @@ struct iio_trigger; /* forward declaration */
  *			and max. For lists, all possible values are enumerated.
  * @write_raw:		function to write a value to the device.
  *			Parameters are the same as for read_raw.
+ * @read_label:		function to request label name for a specified label,
+ *			for better channel identification.
  * @write_raw_get_fmt:	callback function to query the expected
  *			format/precision. If not set by the driver, write_raw
  *			returns IIO_VAL_INT_PLUS_MICRO.
@@ -420,6 +422,10 @@ struct iio_info {
 			 int val2,
 			 long mask);
 
+	int (*read_label)(struct iio_dev *indio_dev,
+			 struct iio_chan_spec const *chan,
+			 char *label);
+
 	int (*write_raw_get_fmt)(struct iio_dev *indio_dev,
 			 struct iio_chan_spec const *chan,
 			 long mask);
-- 
cgit v1.2.3


From 0e30f47232ab57c685258aa91adc3a3e67bd023e Mon Sep 17 00:00:00 2001
From: Pratyush Yadav <p.yadav@ti.com>
Date: Mon, 5 Oct 2020 21:01:26 +0530
Subject: mtd: spi-nor: add support for DTR protocol

Double Transfer Rate (DTR) is SPI protocol in which data is transferred
on each clock edge as opposed to on each clock cycle. Make
framework-level changes to allow supporting flashes in DTR mode.

Right now, mixed DTR modes are not supported. So, for example a mode
like 4S-4D-4D will not work. All phases need to be either DTR or STR.

The xSPI spec says that "The program commands provide SPI backward
compatible commands for programming data...". So 8D-8D-8D page program
opcodes are populated with using 1S-1S-1S opcodes.

Signed-off-by: Pratyush Yadav <p.yadav@ti.com>
Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com>
Reviewed-by: Tudor Ambarus <tudor.ambarus@microchip.com>
Link: https://lore.kernel.org/r/20201005153138.6437-4-p.yadav@ti.com
---
 drivers/mtd/spi-nor/core.c  | 319 ++++++++++++++++++++++++++++++++------------
 drivers/mtd/spi-nor/core.h  |   7 +
 drivers/mtd/spi-nor/sfdp.c  |   9 +-
 include/linux/mtd/spi-nor.h |  51 +++++--
 4 files changed, 290 insertions(+), 96 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/spi-nor/core.c b/drivers/mtd/spi-nor/core.c
index 2f24bde08c90..3cd025d79a98 100644
--- a/drivers/mtd/spi-nor/core.c
+++ b/drivers/mtd/spi-nor/core.c
@@ -40,6 +40,78 @@
 
 #define SPI_NOR_MAX_ADDR_WIDTH	4
 
+/**
+ * spi_nor_get_cmd_ext() - Get the command opcode extension based on the
+ *			   extension type.
+ * @nor:		pointer to a 'struct spi_nor'
+ * @op:			pointer to the 'struct spi_mem_op' whose properties
+ *			need to be initialized.
+ *
+ * Right now, only "repeat" and "invert" are supported.
+ *
+ * Return: The opcode extension.
+ */
+static u8 spi_nor_get_cmd_ext(const struct spi_nor *nor,
+			      const struct spi_mem_op *op)
+{
+	switch (nor->cmd_ext_type) {
+	case SPI_NOR_EXT_INVERT:
+		return ~op->cmd.opcode;
+
+	case SPI_NOR_EXT_REPEAT:
+		return op->cmd.opcode;
+
+	default:
+		dev_err(nor->dev, "Unknown command extension type\n");
+		return 0;
+	}
+}
+
+/**
+ * spi_nor_spimem_setup_op() - Set up common properties of a spi-mem op.
+ * @nor:		pointer to a 'struct spi_nor'
+ * @op:			pointer to the 'struct spi_mem_op' whose properties
+ *			need to be initialized.
+ * @proto:		the protocol from which the properties need to be set.
+ */
+void spi_nor_spimem_setup_op(const struct spi_nor *nor,
+			     struct spi_mem_op *op,
+			     const enum spi_nor_protocol proto)
+{
+	u8 ext;
+
+	op->cmd.buswidth = spi_nor_get_protocol_inst_nbits(proto);
+
+	if (op->addr.nbytes)
+		op->addr.buswidth = spi_nor_get_protocol_addr_nbits(proto);
+
+	if (op->dummy.nbytes)
+		op->dummy.buswidth = spi_nor_get_protocol_addr_nbits(proto);
+
+	if (op->data.nbytes)
+		op->data.buswidth = spi_nor_get_protocol_data_nbits(proto);
+
+	if (spi_nor_protocol_is_dtr(proto)) {
+		/*
+		 * SPIMEM supports mixed DTR modes, but right now we can only
+		 * have all phases either DTR or STR. IOW, SPIMEM can have
+		 * something like 4S-4D-4D, but SPI NOR can't. So, set all 4
+		 * phases to either DTR or STR.
+		 */
+		op->cmd.dtr = true;
+		op->addr.dtr = true;
+		op->dummy.dtr = true;
+		op->data.dtr = true;
+
+		/* 2 bytes per clock cycle in DTR mode. */
+		op->dummy.nbytes *= 2;
+
+		ext = spi_nor_get_cmd_ext(nor, op);
+		op->cmd.opcode = (op->cmd.opcode << 8) | ext;
+		op->cmd.nbytes = 2;
+	}
+}
+
 /**
  * spi_nor_spimem_bounce() - check if a bounce buffer is needed for the data
  *                           transfer
@@ -85,17 +157,26 @@ static int spi_nor_spimem_exec_op(struct spi_nor *nor, struct spi_mem_op *op)
 static int spi_nor_controller_ops_read_reg(struct spi_nor *nor, u8 opcode,
 					   u8 *buf, size_t len)
 {
+	if (spi_nor_protocol_is_dtr(nor->reg_proto))
+		return -EOPNOTSUPP;
+
 	return nor->controller_ops->read_reg(nor, opcode, buf, len);
 }
 
 static int spi_nor_controller_ops_write_reg(struct spi_nor *nor, u8 opcode,
 					    const u8 *buf, size_t len)
 {
+	if (spi_nor_protocol_is_dtr(nor->reg_proto))
+		return -EOPNOTSUPP;
+
 	return nor->controller_ops->write_reg(nor, opcode, buf, len);
 }
 
 static int spi_nor_controller_ops_erase(struct spi_nor *nor, loff_t offs)
 {
+	if (spi_nor_protocol_is_dtr(nor->write_proto))
+		return -EOPNOTSUPP;
+
 	return nor->controller_ops->erase(nor, offs);
 }
 
@@ -113,22 +194,20 @@ static ssize_t spi_nor_spimem_read_data(struct spi_nor *nor, loff_t from,
 					size_t len, u8 *buf)
 {
 	struct spi_mem_op op =
-		SPI_MEM_OP(SPI_MEM_OP_CMD(nor->read_opcode, 1),
-			   SPI_MEM_OP_ADDR(nor->addr_width, from, 1),
-			   SPI_MEM_OP_DUMMY(nor->read_dummy, 1),
-			   SPI_MEM_OP_DATA_IN(len, buf, 1));
+		SPI_MEM_OP(SPI_MEM_OP_CMD(nor->read_opcode, 0),
+			   SPI_MEM_OP_ADDR(nor->addr_width, from, 0),
+			   SPI_MEM_OP_DUMMY(nor->read_dummy, 0),
+			   SPI_MEM_OP_DATA_IN(len, buf, 0));
 	bool usebouncebuf;
 	ssize_t nbytes;
 	int error;
 
-	/* get transfer protocols. */
-	op.cmd.buswidth = spi_nor_get_protocol_inst_nbits(nor->read_proto);
-	op.addr.buswidth = spi_nor_get_protocol_addr_nbits(nor->read_proto);
-	op.dummy.buswidth = op.addr.buswidth;
-	op.data.buswidth = spi_nor_get_protocol_data_nbits(nor->read_proto);
+	spi_nor_spimem_setup_op(nor, &op, nor->read_proto);
 
 	/* convert the dummy cycles to the number of bytes */
 	op.dummy.nbytes = (nor->read_dummy * op.dummy.buswidth) / 8;
+	if (spi_nor_protocol_is_dtr(nor->read_proto))
+		op.dummy.nbytes *= 2;
 
 	usebouncebuf = spi_nor_spimem_bounce(nor, &op);
 
@@ -179,20 +258,18 @@ static ssize_t spi_nor_spimem_write_data(struct spi_nor *nor, loff_t to,
 					 size_t len, const u8 *buf)
 {
 	struct spi_mem_op op =
-		SPI_MEM_OP(SPI_MEM_OP_CMD(nor->program_opcode, 1),
-			   SPI_MEM_OP_ADDR(nor->addr_width, to, 1),
+		SPI_MEM_OP(SPI_MEM_OP_CMD(nor->program_opcode, 0),
+			   SPI_MEM_OP_ADDR(nor->addr_width, to, 0),
 			   SPI_MEM_OP_NO_DUMMY,
-			   SPI_MEM_OP_DATA_OUT(len, buf, 1));
+			   SPI_MEM_OP_DATA_OUT(len, buf, 0));
 	ssize_t nbytes;
 	int error;
 
-	op.cmd.buswidth = spi_nor_get_protocol_inst_nbits(nor->write_proto);
-	op.addr.buswidth = spi_nor_get_protocol_addr_nbits(nor->write_proto);
-	op.data.buswidth = spi_nor_get_protocol_data_nbits(nor->write_proto);
-
 	if (nor->program_opcode == SPINOR_OP_AAI_WP && nor->sst_write_second)
 		op.addr.nbytes = 0;
 
+	spi_nor_spimem_setup_op(nor, &op, nor->write_proto);
+
 	if (spi_nor_spimem_bounce(nor, &op))
 		memcpy(nor->bouncebuf, buf, op.data.nbytes);
 
@@ -239,11 +316,13 @@ int spi_nor_write_enable(struct spi_nor *nor)
 
 	if (nor->spimem) {
 		struct spi_mem_op op =
-			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WREN, 1),
+			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WREN, 0),
 				   SPI_MEM_OP_NO_ADDR,
 				   SPI_MEM_OP_NO_DUMMY,
 				   SPI_MEM_OP_NO_DATA);
 
+		spi_nor_spimem_setup_op(nor, &op, nor->reg_proto);
+
 		ret = spi_mem_exec_op(nor->spimem, &op);
 	} else {
 		ret = spi_nor_controller_ops_write_reg(nor, SPINOR_OP_WREN,
@@ -268,11 +347,13 @@ int spi_nor_write_disable(struct spi_nor *nor)
 
 	if (nor->spimem) {
 		struct spi_mem_op op =
-			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRDI, 1),
+			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRDI, 0),
 				   SPI_MEM_OP_NO_ADDR,
 				   SPI_MEM_OP_NO_DUMMY,
 				   SPI_MEM_OP_NO_DATA);
 
+		spi_nor_spimem_setup_op(nor, &op, nor->reg_proto);
+
 		ret = spi_mem_exec_op(nor->spimem, &op);
 	} else {
 		ret = spi_nor_controller_ops_write_reg(nor, SPINOR_OP_WRDI,
@@ -299,10 +380,12 @@ static int spi_nor_read_sr(struct spi_nor *nor, u8 *sr)
 
 	if (nor->spimem) {
 		struct spi_mem_op op =
-			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDSR, 1),
+			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDSR, 0),
 				   SPI_MEM_OP_NO_ADDR,
 				   SPI_MEM_OP_NO_DUMMY,
-				   SPI_MEM_OP_DATA_IN(1, sr, 1));
+				   SPI_MEM_OP_DATA_IN(1, sr, 0));
+
+		spi_nor_spimem_setup_op(nor, &op, nor->reg_proto);
 
 		ret = spi_mem_exec_op(nor->spimem, &op);
 	} else {
@@ -330,10 +413,12 @@ static int spi_nor_read_fsr(struct spi_nor *nor, u8 *fsr)
 
 	if (nor->spimem) {
 		struct spi_mem_op op =
-			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDFSR, 1),
+			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDFSR, 0),
 				   SPI_MEM_OP_NO_ADDR,
 				   SPI_MEM_OP_NO_DUMMY,
-				   SPI_MEM_OP_DATA_IN(1, fsr, 1));
+				   SPI_MEM_OP_DATA_IN(1, fsr, 0));
+
+		spi_nor_spimem_setup_op(nor, &op, nor->reg_proto);
 
 		ret = spi_mem_exec_op(nor->spimem, &op);
 	} else {
@@ -362,10 +447,12 @@ static int spi_nor_read_cr(struct spi_nor *nor, u8 *cr)
 
 	if (nor->spimem) {
 		struct spi_mem_op op =
-			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDCR, 1),
+			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDCR, 0),
 				   SPI_MEM_OP_NO_ADDR,
 				   SPI_MEM_OP_NO_DUMMY,
-				   SPI_MEM_OP_DATA_IN(1, cr, 1));
+				   SPI_MEM_OP_DATA_IN(1, cr, 0));
+
+		spi_nor_spimem_setup_op(nor, &op, nor->reg_proto);
 
 		ret = spi_mem_exec_op(nor->spimem, &op);
 	} else {
@@ -396,11 +483,13 @@ int spi_nor_set_4byte_addr_mode(struct spi_nor *nor, bool enable)
 			SPI_MEM_OP(SPI_MEM_OP_CMD(enable ?
 						  SPINOR_OP_EN4B :
 						  SPINOR_OP_EX4B,
-						  1),
+						  0),
 				  SPI_MEM_OP_NO_ADDR,
 				  SPI_MEM_OP_NO_DUMMY,
 				  SPI_MEM_OP_NO_DATA);
 
+		spi_nor_spimem_setup_op(nor, &op, nor->reg_proto);
+
 		ret = spi_mem_exec_op(nor->spimem, &op);
 	} else {
 		ret = spi_nor_controller_ops_write_reg(nor,
@@ -432,10 +521,12 @@ static int spansion_set_4byte_addr_mode(struct spi_nor *nor, bool enable)
 
 	if (nor->spimem) {
 		struct spi_mem_op op =
-			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_BRWR, 1),
+			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_BRWR, 0),
 				   SPI_MEM_OP_NO_ADDR,
 				   SPI_MEM_OP_NO_DUMMY,
-				   SPI_MEM_OP_DATA_OUT(1, nor->bouncebuf, 1));
+				   SPI_MEM_OP_DATA_OUT(1, nor->bouncebuf, 0));
+
+		spi_nor_spimem_setup_op(nor, &op, nor->reg_proto);
 
 		ret = spi_mem_exec_op(nor->spimem, &op);
 	} else {
@@ -464,10 +555,12 @@ int spi_nor_write_ear(struct spi_nor *nor, u8 ear)
 
 	if (nor->spimem) {
 		struct spi_mem_op op =
-			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WREAR, 1),
+			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WREAR, 0),
 				   SPI_MEM_OP_NO_ADDR,
 				   SPI_MEM_OP_NO_DUMMY,
-				   SPI_MEM_OP_DATA_OUT(1, nor->bouncebuf, 1));
+				   SPI_MEM_OP_DATA_OUT(1, nor->bouncebuf, 0));
+
+		spi_nor_spimem_setup_op(nor, &op, nor->reg_proto);
 
 		ret = spi_mem_exec_op(nor->spimem, &op);
 	} else {
@@ -495,10 +588,12 @@ int spi_nor_xread_sr(struct spi_nor *nor, u8 *sr)
 
 	if (nor->spimem) {
 		struct spi_mem_op op =
-			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_XRDSR, 1),
+			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_XRDSR, 0),
 				   SPI_MEM_OP_NO_ADDR,
 				   SPI_MEM_OP_NO_DUMMY,
-				   SPI_MEM_OP_DATA_IN(1, sr, 1));
+				   SPI_MEM_OP_DATA_IN(1, sr, 0));
+
+		spi_nor_spimem_setup_op(nor, &op, nor->reg_proto);
 
 		ret = spi_mem_exec_op(nor->spimem, &op);
 	} else {
@@ -540,11 +635,13 @@ static void spi_nor_clear_sr(struct spi_nor *nor)
 
 	if (nor->spimem) {
 		struct spi_mem_op op =
-			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_CLSR, 1),
+			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_CLSR, 0),
 				   SPI_MEM_OP_NO_ADDR,
 				   SPI_MEM_OP_NO_DUMMY,
 				   SPI_MEM_OP_NO_DATA);
 
+		spi_nor_spimem_setup_op(nor, &op, nor->reg_proto);
+
 		ret = spi_mem_exec_op(nor->spimem, &op);
 	} else {
 		ret = spi_nor_controller_ops_write_reg(nor, SPINOR_OP_CLSR,
@@ -604,11 +701,13 @@ static void spi_nor_clear_fsr(struct spi_nor *nor)
 
 	if (nor->spimem) {
 		struct spi_mem_op op =
-			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_CLFSR, 1),
+			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_CLFSR, 0),
 				   SPI_MEM_OP_NO_ADDR,
 				   SPI_MEM_OP_NO_DUMMY,
 				   SPI_MEM_OP_NO_DATA);
 
+		spi_nor_spimem_setup_op(nor, &op, nor->reg_proto);
+
 		ret = spi_mem_exec_op(nor->spimem, &op);
 	} else {
 		ret = spi_nor_controller_ops_write_reg(nor, SPINOR_OP_CLFSR,
@@ -748,10 +847,12 @@ static int spi_nor_write_sr(struct spi_nor *nor, const u8 *sr, size_t len)
 
 	if (nor->spimem) {
 		struct spi_mem_op op =
-			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRSR, 1),
+			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRSR, 0),
 				   SPI_MEM_OP_NO_ADDR,
 				   SPI_MEM_OP_NO_DUMMY,
-				   SPI_MEM_OP_DATA_OUT(len, sr, 1));
+				   SPI_MEM_OP_DATA_OUT(len, sr, 0));
+
+		spi_nor_spimem_setup_op(nor, &op, nor->reg_proto);
 
 		ret = spi_mem_exec_op(nor->spimem, &op);
 	} else {
@@ -950,10 +1051,12 @@ static int spi_nor_write_sr2(struct spi_nor *nor, const u8 *sr2)
 
 	if (nor->spimem) {
 		struct spi_mem_op op =
-			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRSR2, 1),
+			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRSR2, 0),
 				   SPI_MEM_OP_NO_ADDR,
 				   SPI_MEM_OP_NO_DUMMY,
-				   SPI_MEM_OP_DATA_OUT(1, sr2, 1));
+				   SPI_MEM_OP_DATA_OUT(1, sr2, 0));
+
+		spi_nor_spimem_setup_op(nor, &op, nor->reg_proto);
 
 		ret = spi_mem_exec_op(nor->spimem, &op);
 	} else {
@@ -984,10 +1087,12 @@ static int spi_nor_read_sr2(struct spi_nor *nor, u8 *sr2)
 
 	if (nor->spimem) {
 		struct spi_mem_op op =
-			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDSR2, 1),
+			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_RDSR2, 0),
 				   SPI_MEM_OP_NO_ADDR,
 				   SPI_MEM_OP_NO_DUMMY,
-				   SPI_MEM_OP_DATA_IN(1, sr2, 1));
+				   SPI_MEM_OP_DATA_IN(1, sr2, 0));
+
+		spi_nor_spimem_setup_op(nor, &op, nor->reg_proto);
 
 		ret = spi_mem_exec_op(nor->spimem, &op);
 	} else {
@@ -1015,11 +1120,13 @@ static int spi_nor_erase_chip(struct spi_nor *nor)
 
 	if (nor->spimem) {
 		struct spi_mem_op op =
-			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_CHIP_ERASE, 1),
+			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_CHIP_ERASE, 0),
 				   SPI_MEM_OP_NO_ADDR,
 				   SPI_MEM_OP_NO_DUMMY,
 				   SPI_MEM_OP_NO_DATA);
 
+		spi_nor_spimem_setup_op(nor, &op, nor->write_proto);
+
 		ret = spi_mem_exec_op(nor->spimem, &op);
 	} else {
 		ret = spi_nor_controller_ops_write_reg(nor,
@@ -1158,11 +1265,13 @@ static int spi_nor_erase_sector(struct spi_nor *nor, u32 addr)
 
 	if (nor->spimem) {
 		struct spi_mem_op op =
-			SPI_MEM_OP(SPI_MEM_OP_CMD(nor->erase_opcode, 1),
-				   SPI_MEM_OP_ADDR(nor->addr_width, addr, 1),
+			SPI_MEM_OP(SPI_MEM_OP_CMD(nor->erase_opcode, 0),
+				   SPI_MEM_OP_ADDR(nor->addr_width, addr, 0),
 				   SPI_MEM_OP_NO_DUMMY,
 				   SPI_MEM_OP_NO_DATA);
 
+		spi_nor_spimem_setup_op(nor, &op, nor->write_proto);
+
 		return spi_mem_exec_op(nor->spimem, &op);
 	} else if (nor->controller_ops->erase) {
 		return spi_nor_controller_ops_erase(nor, addr);
@@ -2272,6 +2381,7 @@ int spi_nor_hwcaps_read2cmd(u32 hwcaps)
 		{ SNOR_HWCAPS_READ_1_8_8,	SNOR_CMD_READ_1_8_8 },
 		{ SNOR_HWCAPS_READ_8_8_8,	SNOR_CMD_READ_8_8_8 },
 		{ SNOR_HWCAPS_READ_1_8_8_DTR,	SNOR_CMD_READ_1_8_8_DTR },
+		{ SNOR_HWCAPS_READ_8_8_8_DTR,	SNOR_CMD_READ_8_8_8_DTR },
 	};
 
 	return spi_nor_hwcaps2cmd(hwcaps, hwcaps_read2cmd,
@@ -2288,6 +2398,7 @@ static int spi_nor_hwcaps_pp2cmd(u32 hwcaps)
 		{ SNOR_HWCAPS_PP_1_1_8,		SNOR_CMD_PP_1_1_8 },
 		{ SNOR_HWCAPS_PP_1_8_8,		SNOR_CMD_PP_1_8_8 },
 		{ SNOR_HWCAPS_PP_8_8_8,		SNOR_CMD_PP_8_8_8 },
+		{ SNOR_HWCAPS_PP_8_8_8_DTR,	SNOR_CMD_PP_8_8_8_DTR },
 	};
 
 	return spi_nor_hwcaps2cmd(hwcaps, hwcaps_pp2cmd,
@@ -2336,17 +2447,17 @@ static int spi_nor_spimem_check_op(struct spi_nor *nor,
 static int spi_nor_spimem_check_readop(struct spi_nor *nor,
 				       const struct spi_nor_read_command *read)
 {
-	struct spi_mem_op op = SPI_MEM_OP(SPI_MEM_OP_CMD(read->opcode, 1),
-					  SPI_MEM_OP_ADDR(3, 0, 1),
-					  SPI_MEM_OP_DUMMY(0, 1),
-					  SPI_MEM_OP_DATA_IN(0, NULL, 1));
+	struct spi_mem_op op = SPI_MEM_OP(SPI_MEM_OP_CMD(read->opcode, 0),
+					  SPI_MEM_OP_ADDR(3, 0, 0),
+					  SPI_MEM_OP_DUMMY(1, 0),
+					  SPI_MEM_OP_DATA_IN(1, NULL, 0));
 
-	op.cmd.buswidth = spi_nor_get_protocol_inst_nbits(read->proto);
-	op.addr.buswidth = spi_nor_get_protocol_addr_nbits(read->proto);
-	op.data.buswidth = spi_nor_get_protocol_data_nbits(read->proto);
-	op.dummy.buswidth = op.addr.buswidth;
-	op.dummy.nbytes = (read->num_mode_clocks + read->num_wait_states) *
-			  op.dummy.buswidth / 8;
+	spi_nor_spimem_setup_op(nor, &op, read->proto);
+
+	/* convert the dummy cycles to the number of bytes */
+	op.dummy.nbytes = (nor->read_dummy * op.dummy.buswidth) / 8;
+	if (spi_nor_protocol_is_dtr(nor->read_proto))
+		op.dummy.nbytes *= 2;
 
 	return spi_nor_spimem_check_op(nor, &op);
 }
@@ -2362,14 +2473,12 @@ static int spi_nor_spimem_check_readop(struct spi_nor *nor,
 static int spi_nor_spimem_check_pp(struct spi_nor *nor,
 				   const struct spi_nor_pp_command *pp)
 {
-	struct spi_mem_op op = SPI_MEM_OP(SPI_MEM_OP_CMD(pp->opcode, 1),
-					  SPI_MEM_OP_ADDR(3, 0, 1),
+	struct spi_mem_op op = SPI_MEM_OP(SPI_MEM_OP_CMD(pp->opcode, 0),
+					  SPI_MEM_OP_ADDR(3, 0, 0),
 					  SPI_MEM_OP_NO_DUMMY,
-					  SPI_MEM_OP_DATA_OUT(0, NULL, 1));
+					  SPI_MEM_OP_DATA_OUT(1, NULL, 0));
 
-	op.cmd.buswidth = spi_nor_get_protocol_inst_nbits(pp->proto);
-	op.addr.buswidth = spi_nor_get_protocol_addr_nbits(pp->proto);
-	op.data.buswidth = spi_nor_get_protocol_data_nbits(pp->proto);
+	spi_nor_spimem_setup_op(nor, &op, pp->proto);
 
 	return spi_nor_spimem_check_op(nor, &op);
 }
@@ -2387,12 +2496,16 @@ spi_nor_spimem_adjust_hwcaps(struct spi_nor *nor, u32 *hwcaps)
 	struct spi_nor_flash_parameter *params = nor->params;
 	unsigned int cap;
 
-	/* DTR modes are not supported yet, mask them all. */
-	*hwcaps &= ~SNOR_HWCAPS_DTR;
-
 	/* X-X-X modes are not supported yet, mask them all. */
 	*hwcaps &= ~SNOR_HWCAPS_X_X_X;
 
+	/*
+	 * If the reset line is broken, we do not want to enter a stateful
+	 * mode.
+	 */
+	if (nor->flags & SNOR_F_BROKEN_RESET)
+		*hwcaps &= ~(SNOR_HWCAPS_X_X_X | SNOR_HWCAPS_X_X_X_DTR);
+
 	for (cap = 0; cap < sizeof(*hwcaps) * BITS_PER_BYTE; cap++) {
 		int rdidx, ppidx;
 
@@ -2647,7 +2760,7 @@ static int spi_nor_default_setup(struct spi_nor *nor,
 		 * controller directly implements the spi_nor interface.
 		 * Yet another reason to switch to spi-mem.
 		 */
-		ignored_mask = SNOR_HWCAPS_X_X_X;
+		ignored_mask = SNOR_HWCAPS_X_X_X | SNOR_HWCAPS_X_X_X_DTR;
 		if (shared_mask & ignored_mask) {
 			dev_dbg(nor->dev,
 				"SPI n-n-n protocols are not supported.\n");
@@ -2792,11 +2905,28 @@ static void spi_nor_info_init_params(struct spi_nor *nor)
 					  SNOR_PROTO_1_1_8);
 	}
 
+	if (info->flags & SPI_NOR_OCTAL_DTR_READ) {
+		params->hwcaps.mask |= SNOR_HWCAPS_READ_8_8_8_DTR;
+		spi_nor_set_read_settings(&params->reads[SNOR_CMD_READ_8_8_8_DTR],
+					  0, 20, SPINOR_OP_READ_FAST,
+					  SNOR_PROTO_8_8_8_DTR);
+	}
+
 	/* Page Program settings. */
 	params->hwcaps.mask |= SNOR_HWCAPS_PP;
 	spi_nor_set_pp_settings(&params->page_programs[SNOR_CMD_PP],
 				SPINOR_OP_PP, SNOR_PROTO_1_1_1);
 
+	if (info->flags & SPI_NOR_OCTAL_DTR_PP) {
+		params->hwcaps.mask |= SNOR_HWCAPS_PP_8_8_8_DTR;
+		/*
+		 * Since xSPI Page Program opcode is backward compatible with
+		 * Legacy SPI, use Legacy SPI opcode there as well.
+		 */
+		spi_nor_set_pp_settings(&params->page_programs[SNOR_CMD_PP_8_8_8_DTR],
+					SPINOR_OP_PP, SNOR_PROTO_8_8_8_DTR);
+	}
+
 	/*
 	 * Sector Erase settings. Sort Erase Types in ascending order, with the
 	 * smallest erase size starting at BIT(0).
@@ -2904,7 +3034,8 @@ static int spi_nor_init_params(struct spi_nor *nor)
 
 	spi_nor_manufacturer_init_params(nor);
 
-	if ((nor->info->flags & (SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ)) &&
+	if ((nor->info->flags & (SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ |
+				 SPI_NOR_OCTAL_READ | SPI_NOR_OCTAL_DTR_READ)) &&
 	    !(nor->info->flags & SPI_NOR_SKIP_SFDP))
 		spi_nor_sfdp_init_params(nor);
 
@@ -2966,7 +3097,9 @@ static int spi_nor_init(struct spi_nor *nor)
 		return err;
 	}
 
-	if (nor->addr_width == 4 && !(nor->flags & SNOR_F_4B_OPCODES)) {
+	if (nor->addr_width == 4 &&
+	    nor->read_proto != SNOR_PROTO_8_8_8_DTR &&
+	    !(nor->flags & SNOR_F_4B_OPCODES)) {
 		/*
 		 * If the RESET# pin isn't hooked up properly, or the system
 		 * otherwise doesn't perform a reset command in the boot
@@ -3025,6 +3158,20 @@ static int spi_nor_set_addr_width(struct spi_nor *nor)
 {
 	if (nor->addr_width) {
 		/* already configured from SFDP */
+	} else if (nor->read_proto == SNOR_PROTO_8_8_8_DTR) {
+		/*
+		 * In 8D-8D-8D mode, one byte takes half a cycle to transfer. So
+		 * in this protocol an odd address width cannot be used because
+		 * then the address phase would only span a cycle and a half.
+		 * Half a cycle would be left over. We would then have to start
+		 * the dummy phase in the middle of a cycle and so too the data
+		 * phase, and we will end the transaction with half a cycle left
+		 * over.
+		 *
+		 * Force all 8D-8D-8D flashes to use an address width of 4 to
+		 * avoid this situation.
+		 */
+		nor->addr_width = 4;
 	} else if (nor->info->addr_width) {
 		nor->addr_width = nor->info->addr_width;
 	} else {
@@ -3255,23 +3402,28 @@ EXPORT_SYMBOL_GPL(spi_nor_scan);
 static int spi_nor_create_read_dirmap(struct spi_nor *nor)
 {
 	struct spi_mem_dirmap_info info = {
-		.op_tmpl = SPI_MEM_OP(SPI_MEM_OP_CMD(nor->read_opcode, 1),
-				      SPI_MEM_OP_ADDR(nor->addr_width, 0, 1),
-				      SPI_MEM_OP_DUMMY(nor->read_dummy, 1),
-				      SPI_MEM_OP_DATA_IN(0, NULL, 1)),
+		.op_tmpl = SPI_MEM_OP(SPI_MEM_OP_CMD(nor->read_opcode, 0),
+				      SPI_MEM_OP_ADDR(nor->addr_width, 0, 0),
+				      SPI_MEM_OP_DUMMY(nor->read_dummy, 0),
+				      SPI_MEM_OP_DATA_IN(0, NULL, 0)),
 		.offset = 0,
 		.length = nor->mtd.size,
 	};
 	struct spi_mem_op *op = &info.op_tmpl;
 
-	/* get transfer protocols. */
-	op->cmd.buswidth = spi_nor_get_protocol_inst_nbits(nor->read_proto);
-	op->addr.buswidth = spi_nor_get_protocol_addr_nbits(nor->read_proto);
-	op->dummy.buswidth = op->addr.buswidth;
-	op->data.buswidth = spi_nor_get_protocol_data_nbits(nor->read_proto);
+	spi_nor_spimem_setup_op(nor, op, nor->read_proto);
 
 	/* convert the dummy cycles to the number of bytes */
 	op->dummy.nbytes = (nor->read_dummy * op->dummy.buswidth) / 8;
+	if (spi_nor_protocol_is_dtr(nor->read_proto))
+		op->dummy.nbytes *= 2;
+
+	/*
+	 * Since spi_nor_spimem_setup_op() only sets buswidth when the number
+	 * of data bytes is non-zero, the data buswidth won't be set here. So,
+	 * do it explicitly.
+	 */
+	op->data.buswidth = spi_nor_get_protocol_data_nbits(nor->read_proto);
 
 	nor->dirmap.rdesc = devm_spi_mem_dirmap_create(nor->dev, nor->spimem,
 						       &info);
@@ -3281,24 +3433,27 @@ static int spi_nor_create_read_dirmap(struct spi_nor *nor)
 static int spi_nor_create_write_dirmap(struct spi_nor *nor)
 {
 	struct spi_mem_dirmap_info info = {
-		.op_tmpl = SPI_MEM_OP(SPI_MEM_OP_CMD(nor->program_opcode, 1),
-				      SPI_MEM_OP_ADDR(nor->addr_width, 0, 1),
+		.op_tmpl = SPI_MEM_OP(SPI_MEM_OP_CMD(nor->program_opcode, 0),
+				      SPI_MEM_OP_ADDR(nor->addr_width, 0, 0),
 				      SPI_MEM_OP_NO_DUMMY,
-				      SPI_MEM_OP_DATA_OUT(0, NULL, 1)),
+				      SPI_MEM_OP_DATA_OUT(0, NULL, 0)),
 		.offset = 0,
 		.length = nor->mtd.size,
 	};
 	struct spi_mem_op *op = &info.op_tmpl;
 
-	/* get transfer protocols. */
-	op->cmd.buswidth = spi_nor_get_protocol_inst_nbits(nor->write_proto);
-	op->addr.buswidth = spi_nor_get_protocol_addr_nbits(nor->write_proto);
-	op->dummy.buswidth = op->addr.buswidth;
-	op->data.buswidth = spi_nor_get_protocol_data_nbits(nor->write_proto);
-
 	if (nor->program_opcode == SPINOR_OP_AAI_WP && nor->sst_write_second)
 		op->addr.nbytes = 0;
 
+	spi_nor_spimem_setup_op(nor, op, nor->write_proto);
+
+	/*
+	 * Since spi_nor_spimem_setup_op() only sets buswidth when the number
+	 * of data bytes is non-zero, the data buswidth won't be set here. So,
+	 * do it explicitly.
+	 */
+	op->data.buswidth = spi_nor_get_protocol_data_nbits(nor->write_proto);
+
 	nor->dirmap.wdesc = devm_spi_mem_dirmap_create(nor->dev, nor->spimem,
 						       &info);
 	return PTR_ERR_OR_ZERO(nor->dirmap.wdesc);
diff --git a/drivers/mtd/spi-nor/core.h b/drivers/mtd/spi-nor/core.h
index 6f2f6b27173f..5d95b4183a33 100644
--- a/drivers/mtd/spi-nor/core.h
+++ b/drivers/mtd/spi-nor/core.h
@@ -62,6 +62,7 @@ enum spi_nor_read_command_index {
 	SNOR_CMD_READ_1_8_8,
 	SNOR_CMD_READ_8_8_8,
 	SNOR_CMD_READ_1_8_8_DTR,
+	SNOR_CMD_READ_8_8_8_DTR,
 
 	SNOR_CMD_READ_MAX
 };
@@ -78,6 +79,7 @@ enum spi_nor_pp_command_index {
 	SNOR_CMD_PP_1_1_8,
 	SNOR_CMD_PP_1_8_8,
 	SNOR_CMD_PP_8_8_8,
+	SNOR_CMD_PP_8_8_8_DTR,
 
 	SNOR_CMD_PP_MAX
 };
@@ -311,6 +313,8 @@ struct flash_info {
 					 * BP3 is bit 6 of status register.
 					 * Must be used with SPI_NOR_4BIT_BP.
 					 */
+#define SPI_NOR_OCTAL_DTR_READ	BIT(19) /* Flash supports octal DTR Read. */
+#define SPI_NOR_OCTAL_DTR_PP	BIT(20) /* Flash supports Octal DTR Page Program */
 
 	/* Part specific fixup hooks. */
 	const struct spi_nor_fixups *fixups;
@@ -399,6 +403,9 @@ extern const struct spi_nor_manufacturer spi_nor_winbond;
 extern const struct spi_nor_manufacturer spi_nor_xilinx;
 extern const struct spi_nor_manufacturer spi_nor_xmc;
 
+void spi_nor_spimem_setup_op(const struct spi_nor *nor,
+			     struct spi_mem_op *op,
+			     const enum spi_nor_protocol proto);
 int spi_nor_write_enable(struct spi_nor *nor);
 int spi_nor_write_disable(struct spi_nor *nor);
 int spi_nor_set_4byte_addr_mode(struct spi_nor *nor, bool enable);
diff --git a/drivers/mtd/spi-nor/sfdp.c b/drivers/mtd/spi-nor/sfdp.c
index e2a43d39eb5f..21fa9ab78eae 100644
--- a/drivers/mtd/spi-nor/sfdp.c
+++ b/drivers/mtd/spi-nor/sfdp.c
@@ -1047,9 +1047,16 @@ static int spi_nor_parse_4bait(struct spi_nor *nor,
 	}
 
 	/* 4BAIT is the only SFDP table that indicates page program support. */
-	if (pp_hwcaps & SNOR_HWCAPS_PP)
+	if (pp_hwcaps & SNOR_HWCAPS_PP) {
 		spi_nor_set_pp_settings(&params_pp[SNOR_CMD_PP],
 					SPINOR_OP_PP_4B, SNOR_PROTO_1_1_1);
+		/*
+		 * Since xSPI Page Program opcode is backward compatible with
+		 * Legacy SPI, use Legacy SPI opcode there as well.
+		 */
+		spi_nor_set_pp_settings(&params_pp[SNOR_CMD_PP_8_8_8_DTR],
+					SPINOR_OP_PP_4B, SNOR_PROTO_8_8_8_DTR);
+	}
 	if (pp_hwcaps & SNOR_HWCAPS_PP_1_1_4)
 		spi_nor_set_pp_settings(&params_pp[SNOR_CMD_PP_1_1_4],
 					SPINOR_OP_PP_1_1_4_4B,
diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h
index 60bac2c0ec45..cd549042c53d 100644
--- a/include/linux/mtd/spi-nor.h
+++ b/include/linux/mtd/spi-nor.h
@@ -182,6 +182,7 @@ enum spi_nor_protocol {
 	SNOR_PROTO_1_2_2_DTR = SNOR_PROTO_DTR(1, 2, 2),
 	SNOR_PROTO_1_4_4_DTR = SNOR_PROTO_DTR(1, 4, 4),
 	SNOR_PROTO_1_8_8_DTR = SNOR_PROTO_DTR(1, 8, 8),
+	SNOR_PROTO_8_8_8_DTR = SNOR_PROTO_DTR(8, 8, 8),
 };
 
 static inline bool spi_nor_protocol_is_dtr(enum spi_nor_protocol proto)
@@ -228,7 +229,7 @@ struct spi_nor_hwcaps {
  * then Quad SPI protocols before Dual SPI protocols, Fast Read and lastly
  * (Slow) Read.
  */
-#define SNOR_HWCAPS_READ_MASK		GENMASK(14, 0)
+#define SNOR_HWCAPS_READ_MASK		GENMASK(15, 0)
 #define SNOR_HWCAPS_READ		BIT(0)
 #define SNOR_HWCAPS_READ_FAST		BIT(1)
 #define SNOR_HWCAPS_READ_1_1_1_DTR	BIT(2)
@@ -245,11 +246,12 @@ struct spi_nor_hwcaps {
 #define SNOR_HWCAPS_READ_4_4_4		BIT(9)
 #define SNOR_HWCAPS_READ_1_4_4_DTR	BIT(10)
 
-#define SNOR_HWCAPS_READ_OCTAL		GENMASK(14, 11)
+#define SNOR_HWCAPS_READ_OCTAL		GENMASK(15, 11)
 #define SNOR_HWCAPS_READ_1_1_8		BIT(11)
 #define SNOR_HWCAPS_READ_1_8_8		BIT(12)
 #define SNOR_HWCAPS_READ_8_8_8		BIT(13)
 #define SNOR_HWCAPS_READ_1_8_8_DTR	BIT(14)
+#define SNOR_HWCAPS_READ_8_8_8_DTR	BIT(15)
 
 /*
  * Page Program capabilities.
@@ -260,18 +262,19 @@ struct spi_nor_hwcaps {
  * JEDEC/SFDP standard to define them. Also at this moment no SPI flash memory
  * implements such commands.
  */
-#define SNOR_HWCAPS_PP_MASK	GENMASK(22, 16)
-#define SNOR_HWCAPS_PP		BIT(16)
+#define SNOR_HWCAPS_PP_MASK		GENMASK(23, 16)
+#define SNOR_HWCAPS_PP			BIT(16)
 
-#define SNOR_HWCAPS_PP_QUAD	GENMASK(19, 17)
-#define SNOR_HWCAPS_PP_1_1_4	BIT(17)
-#define SNOR_HWCAPS_PP_1_4_4	BIT(18)
-#define SNOR_HWCAPS_PP_4_4_4	BIT(19)
+#define SNOR_HWCAPS_PP_QUAD		GENMASK(19, 17)
+#define SNOR_HWCAPS_PP_1_1_4		BIT(17)
+#define SNOR_HWCAPS_PP_1_4_4		BIT(18)
+#define SNOR_HWCAPS_PP_4_4_4		BIT(19)
 
-#define SNOR_HWCAPS_PP_OCTAL	GENMASK(22, 20)
-#define SNOR_HWCAPS_PP_1_1_8	BIT(20)
-#define SNOR_HWCAPS_PP_1_8_8	BIT(21)
-#define SNOR_HWCAPS_PP_8_8_8	BIT(22)
+#define SNOR_HWCAPS_PP_OCTAL		GENMASK(23, 20)
+#define SNOR_HWCAPS_PP_1_1_8		BIT(20)
+#define SNOR_HWCAPS_PP_1_8_8		BIT(21)
+#define SNOR_HWCAPS_PP_8_8_8		BIT(22)
+#define SNOR_HWCAPS_PP_8_8_8_DTR	BIT(23)
 
 #define SNOR_HWCAPS_X_X_X	(SNOR_HWCAPS_READ_2_2_2 |	\
 				 SNOR_HWCAPS_READ_4_4_4 |	\
@@ -279,10 +282,14 @@ struct spi_nor_hwcaps {
 				 SNOR_HWCAPS_PP_4_4_4 |		\
 				 SNOR_HWCAPS_PP_8_8_8)
 
+#define SNOR_HWCAPS_X_X_X_DTR	(SNOR_HWCAPS_READ_8_8_8_DTR |	\
+				 SNOR_HWCAPS_PP_8_8_8_DTR)
+
 #define SNOR_HWCAPS_DTR		(SNOR_HWCAPS_READ_1_1_1_DTR |	\
 				 SNOR_HWCAPS_READ_1_2_2_DTR |	\
 				 SNOR_HWCAPS_READ_1_4_4_DTR |	\
-				 SNOR_HWCAPS_READ_1_8_8_DTR)
+				 SNOR_HWCAPS_READ_1_8_8_DTR |	\
+				 SNOR_HWCAPS_READ_8_8_8_DTR)
 
 #define SNOR_HWCAPS_ALL		(SNOR_HWCAPS_READ_MASK |	\
 				 SNOR_HWCAPS_PP_MASK)
@@ -318,6 +325,22 @@ struct spi_nor_controller_ops {
 	int (*erase)(struct spi_nor *nor, loff_t offs);
 };
 
+/**
+ * enum spi_nor_cmd_ext - describes the command opcode extension in DTR mode
+ * @SPI_NOR_EXT_NONE: no extension. This is the default, and is used in Legacy
+ *		      SPI mode
+ * @SPI_NOR_EXT_REPEAT: the extension is same as the opcode
+ * @SPI_NOR_EXT_INVERT: the extension is the bitwise inverse of the opcode
+ * @SPI_NOR_EXT_HEX: the extension is any hex value. The command and opcode
+ *		     combine to form a 16-bit opcode.
+ */
+enum spi_nor_cmd_ext {
+	SPI_NOR_EXT_NONE = 0,
+	SPI_NOR_EXT_REPEAT,
+	SPI_NOR_EXT_INVERT,
+	SPI_NOR_EXT_HEX,
+};
+
 /*
  * Forward declarations that are used internally by the core and manufacturer
  * drivers.
@@ -345,6 +368,7 @@ struct spi_nor_flash_parameter;
  * @program_opcode:	the program opcode
  * @sst_write_second:	used by the SST write operation
  * @flags:		flag options for the current SPI NOR (SNOR_F_*)
+ * @cmd_ext_type:	the command opcode extension type for DTR mode.
  * @read_proto:		the SPI protocol for read operations
  * @write_proto:	the SPI protocol for write operations
  * @reg_proto:		the SPI protocol for read_reg/write_reg/erase operations
@@ -376,6 +400,7 @@ struct spi_nor {
 	enum spi_nor_protocol	reg_proto;
 	bool			sst_write_second;
 	u32			flags;
+	enum spi_nor_cmd_ext	cmd_ext_type;
 
 	const struct spi_nor_controller_ops *controller_ops;
 
-- 
cgit v1.2.3


From d73ee7534cc537b98b61bfd83dbce5bb12aecb80 Mon Sep 17 00:00:00 2001
From: Pratyush Yadav <p.yadav@ti.com>
Date: Mon, 5 Oct 2020 21:01:35 +0530
Subject: mtd: spi-nor: core: perform a Soft Reset on shutdown

Perform a Soft Reset on shutdown on flashes that support it so that the
flash can be reset to its initial state and any configurations made by
spi-nor (given that they're only done in volatile registers) will be
reset. This will hand back the flash in pristine state for any further
operations on it.

Signed-off-by: Pratyush Yadav <p.yadav@ti.com>
Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com>
Reviewed-by: Tudor Ambarus <tudor.ambarus@microchip.com>
Link: https://lore.kernel.org/r/20201005153138.6437-13-p.yadav@ti.com
---
 drivers/mtd/spi-nor/core.c  | 45 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/mtd/spi-nor.h |  2 ++
 2 files changed, 47 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/mtd/spi-nor/core.c b/drivers/mtd/spi-nor/core.c
index 7b9ec02734f2..633a1af8a0fe 100644
--- a/drivers/mtd/spi-nor/core.c
+++ b/drivers/mtd/spi-nor/core.c
@@ -40,6 +40,9 @@
 
 #define SPI_NOR_MAX_ADDR_WIDTH	4
 
+#define SPI_NOR_SRST_SLEEP_MIN 200
+#define SPI_NOR_SRST_SLEEP_MAX 400
+
 /**
  * spi_nor_get_cmd_ext() - Get the command opcode extension based on the
  *			   extension type.
@@ -3174,6 +3177,45 @@ static int spi_nor_init(struct spi_nor *nor)
 	return 0;
 }
 
+static void spi_nor_soft_reset(struct spi_nor *nor)
+{
+	struct spi_mem_op op;
+	int ret;
+
+	op = (struct spi_mem_op)SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_SRSTEN, 0),
+			SPI_MEM_OP_NO_DUMMY,
+			SPI_MEM_OP_NO_ADDR,
+			SPI_MEM_OP_NO_DATA);
+
+	spi_nor_spimem_setup_op(nor, &op, nor->reg_proto);
+
+	ret = spi_mem_exec_op(nor->spimem, &op);
+	if (ret) {
+		dev_warn(nor->dev, "Software reset failed: %d\n", ret);
+		return;
+	}
+
+	op = (struct spi_mem_op)SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_SRST, 0),
+			SPI_MEM_OP_NO_DUMMY,
+			SPI_MEM_OP_NO_ADDR,
+			SPI_MEM_OP_NO_DATA);
+
+	spi_nor_spimem_setup_op(nor, &op, nor->reg_proto);
+
+	ret = spi_mem_exec_op(nor->spimem, &op);
+	if (ret) {
+		dev_warn(nor->dev, "Software reset failed: %d\n", ret);
+		return;
+	}
+
+	/*
+	 * Software Reset is not instant, and the delay varies from flash to
+	 * flash. Looking at a few flashes, most range somewhere below 100
+	 * microseconds. So, sleep for a range of 200-400 us.
+	 */
+	usleep_range(SPI_NOR_SRST_SLEEP_MIN, SPI_NOR_SRST_SLEEP_MAX);
+}
+
 /* mtd resume handler */
 static void spi_nor_resume(struct mtd_info *mtd)
 {
@@ -3193,6 +3235,9 @@ void spi_nor_restore(struct spi_nor *nor)
 	if (nor->addr_width == 4 && !(nor->flags & SNOR_F_4B_OPCODES) &&
 	    nor->flags & SNOR_F_BROKEN_RESET)
 		nor->params->set_4byte_addr_mode(nor, false);
+
+	if (nor->flags & SNOR_F_SOFT_RESET)
+		spi_nor_soft_reset(nor);
 }
 EXPORT_SYMBOL_GPL(spi_nor_restore);
 
diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h
index cd549042c53d..299685d15dc2 100644
--- a/include/linux/mtd/spi-nor.h
+++ b/include/linux/mtd/spi-nor.h
@@ -51,6 +51,8 @@
 #define SPINOR_OP_CLFSR		0x50	/* Clear flag status register */
 #define SPINOR_OP_RDEAR		0xc8	/* Read Extended Address Register */
 #define SPINOR_OP_WREAR		0xc5	/* Write Extended Address Register */
+#define SPINOR_OP_SRSTEN	0x66	/* Software Reset Enable */
+#define SPINOR_OP_SRST		0x99	/* Software Reset */
 
 /* 4-byte address opcodes - used on Spansion and some Macronix flashes. */
 #define SPINOR_OP_READ_4B	0x13	/* Read data bytes (low frequency) */
-- 
cgit v1.2.3


From 43676605f890b218e551f396a55dbaea7799acb4 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Tue, 3 Nov 2020 10:30:10 +0100
Subject: drm/ttm: Add vmap/vunmap to TTM and TTM GEM helpers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The new functions ttm_bo_{vmap,vunmap}() map and unmap a TTM BO in kernel
address space. The mapping's address is returned as struct dma_buf_map.
Each function is a simplified version of TTM's existing kmap code. Both
functions respect the memory's location ani/or writecombine flags.

On top TTM's functions, GEM TTM helpers got drm_gem_ttm_{vmap,vunmap}(),
two helpers that convert a GEM object into the TTM BO and forward the call
to TTM's vmap/vunmap. These helpers can be dropped into the rsp GEM object
callbacks.

v5:
	* use size_t for storing mapping size (Christian)
	* ignore premapped memory areas correctly in ttm_bo_vunmap()
	* rebase onto latest TTM interfaces (Christian)
	* remove BUG() from ttm_bo_vmap() (Christian)
v4:
	* drop ttm_kmap_obj_to_dma_buf() in favor of vmap helpers (Daniel,
	  Christian)

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Christian König <christian.koenig@amd.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Tested-by: Sam Ravnborg <sam@ravnborg.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20201103093015.1063-6-tzimmermann@suse.de
---
 drivers/gpu/drm/drm_gem_ttm_helper.c | 37 ++++++++++++++++++
 drivers/gpu/drm/ttm/ttm_bo_util.c    | 72 ++++++++++++++++++++++++++++++++++++
 include/drm/drm_gem_ttm_helper.h     |  6 +++
 include/drm/ttm/ttm_bo_api.h         | 28 ++++++++++++++
 include/linux/dma-buf-map.h          | 20 ++++++++++
 5 files changed, 163 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/drm_gem_ttm_helper.c b/drivers/gpu/drm/drm_gem_ttm_helper.c
index 0e4fb9ba43ad..de28720757af 100644
--- a/drivers/gpu/drm/drm_gem_ttm_helper.c
+++ b/drivers/gpu/drm/drm_gem_ttm_helper.c
@@ -49,6 +49,43 @@ void drm_gem_ttm_print_info(struct drm_printer *p, unsigned int indent,
 }
 EXPORT_SYMBOL(drm_gem_ttm_print_info);
 
+/**
+ * drm_gem_ttm_vmap() - vmap &ttm_buffer_object
+ * @gem: GEM object.
+ * @map: [out] returns the dma-buf mapping.
+ *
+ * Maps a GEM object with ttm_bo_vmap(). This function can be used as
+ * &drm_gem_object_funcs.vmap callback.
+ *
+ * Returns:
+ * 0 on success, or a negative errno code otherwise.
+ */
+int drm_gem_ttm_vmap(struct drm_gem_object *gem,
+		     struct dma_buf_map *map)
+{
+	struct ttm_buffer_object *bo = drm_gem_ttm_of_gem(gem);
+
+	return ttm_bo_vmap(bo, map);
+}
+EXPORT_SYMBOL(drm_gem_ttm_vmap);
+
+/**
+ * drm_gem_ttm_vunmap() - vunmap &ttm_buffer_object
+ * @gem: GEM object.
+ * @map: dma-buf mapping.
+ *
+ * Unmaps a GEM object with ttm_bo_vunmap(). This function can be used as
+ * &drm_gem_object_funcs.vmap callback.
+ */
+void drm_gem_ttm_vunmap(struct drm_gem_object *gem,
+			struct dma_buf_map *map)
+{
+	struct ttm_buffer_object *bo = drm_gem_ttm_of_gem(gem);
+
+	ttm_bo_vunmap(bo, map);
+}
+EXPORT_SYMBOL(drm_gem_ttm_vunmap);
+
 /**
  * drm_gem_ttm_mmap() - mmap &ttm_buffer_object
  * @gem: GEM object.
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index ecb54415d1ca..7ccb2295cac1 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -32,6 +32,7 @@
 #include <drm/ttm/ttm_bo_driver.h>
 #include <drm/ttm/ttm_placement.h>
 #include <drm/drm_vma_manager.h>
+#include <linux/dma-buf-map.h>
 #include <linux/io.h>
 #include <linux/highmem.h>
 #include <linux/wait.h>
@@ -471,6 +472,77 @@ void ttm_bo_kunmap(struct ttm_bo_kmap_obj *map)
 }
 EXPORT_SYMBOL(ttm_bo_kunmap);
 
+int ttm_bo_vmap(struct ttm_buffer_object *bo, struct dma_buf_map *map)
+{
+	struct ttm_resource *mem = &bo->mem;
+	int ret;
+
+	ret = ttm_mem_io_reserve(bo->bdev, mem);
+	if (ret)
+		return ret;
+
+	if (mem->bus.is_iomem) {
+		void __iomem *vaddr_iomem;
+		size_t size = bo->num_pages << PAGE_SHIFT;
+
+		if (mem->bus.addr)
+			vaddr_iomem = (void __iomem *)mem->bus.addr;
+		else if (mem->bus.caching == ttm_write_combined)
+			vaddr_iomem = ioremap_wc(mem->bus.offset, size);
+		else
+			vaddr_iomem = ioremap(mem->bus.offset, size);
+
+		if (!vaddr_iomem)
+			return -ENOMEM;
+
+		dma_buf_map_set_vaddr_iomem(map, vaddr_iomem);
+
+	} else {
+		struct ttm_operation_ctx ctx = {
+			.interruptible = false,
+			.no_wait_gpu = false
+		};
+		struct ttm_tt *ttm = bo->ttm;
+		pgprot_t prot;
+		void *vaddr;
+
+		ret = ttm_tt_populate(bo->bdev, ttm, &ctx);
+		if (ret)
+			return ret;
+
+		/*
+		 * We need to use vmap to get the desired page protection
+		 * or to make the buffer object look contiguous.
+		 */
+		prot = ttm_io_prot(bo, mem, PAGE_KERNEL);
+		vaddr = vmap(ttm->pages, bo->num_pages, 0, prot);
+		if (!vaddr)
+			return -ENOMEM;
+
+		dma_buf_map_set_vaddr(map, vaddr);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(ttm_bo_vmap);
+
+void ttm_bo_vunmap(struct ttm_buffer_object *bo, struct dma_buf_map *map)
+{
+	struct ttm_resource *mem = &bo->mem;
+
+	if (dma_buf_map_is_null(map))
+		return;
+
+	if (!map->is_iomem)
+		vunmap(map->vaddr);
+	else if (!mem->bus.addr)
+		iounmap(map->vaddr_iomem);
+	dma_buf_map_clear(map);
+
+	ttm_mem_io_free(bo->bdev, &bo->mem);
+}
+EXPORT_SYMBOL(ttm_bo_vunmap);
+
 static int ttm_bo_wait_free_node(struct ttm_buffer_object *bo,
 				 bool dst_use_tt)
 {
diff --git a/include/drm/drm_gem_ttm_helper.h b/include/drm/drm_gem_ttm_helper.h
index 118cef76f84f..7c6d874910b8 100644
--- a/include/drm/drm_gem_ttm_helper.h
+++ b/include/drm/drm_gem_ttm_helper.h
@@ -10,11 +10,17 @@
 #include <drm/ttm/ttm_bo_api.h>
 #include <drm/ttm/ttm_bo_driver.h>
 
+struct dma_buf_map;
+
 #define drm_gem_ttm_of_gem(gem_obj) \
 	container_of(gem_obj, struct ttm_buffer_object, base)
 
 void drm_gem_ttm_print_info(struct drm_printer *p, unsigned int indent,
 			    const struct drm_gem_object *gem);
+int drm_gem_ttm_vmap(struct drm_gem_object *gem,
+		     struct dma_buf_map *map);
+void drm_gem_ttm_vunmap(struct drm_gem_object *gem,
+			struct dma_buf_map *map);
 int drm_gem_ttm_mmap(struct drm_gem_object *gem,
 		     struct vm_area_struct *vma);
 
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index 5ddad88ae6ed..2564e66e67d7 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -48,6 +48,8 @@ struct ttm_bo_global;
 
 struct ttm_bo_device;
 
+struct dma_buf_map;
+
 struct drm_mm_node;
 
 struct ttm_placement;
@@ -495,6 +497,32 @@ int ttm_bo_kmap(struct ttm_buffer_object *bo, unsigned long start_page,
  */
 void ttm_bo_kunmap(struct ttm_bo_kmap_obj *map);
 
+/**
+ * ttm_bo_vmap
+ *
+ * @bo: The buffer object.
+ * @map: pointer to a struct dma_buf_map representing the map.
+ *
+ * Sets up a kernel virtual mapping, using ioremap or vmap to the
+ * data in the buffer object. The parameter @map returns the virtual
+ * address as struct dma_buf_map. Unmap the buffer with ttm_bo_vunmap().
+ *
+ * Returns
+ * -ENOMEM: Out of memory.
+ * -EINVAL: Invalid range.
+ */
+int ttm_bo_vmap(struct ttm_buffer_object *bo, struct dma_buf_map *map);
+
+/**
+ * ttm_bo_vunmap
+ *
+ * @bo: The buffer object.
+ * @map: Object describing the map to unmap.
+ *
+ * Unmaps a kernel map set up by ttm_bo_vmap().
+ */
+void ttm_bo_vunmap(struct ttm_buffer_object *bo, struct dma_buf_map *map);
+
 /**
  * ttm_bo_mmap_obj - mmap memory backed by a ttm buffer object.
  *
diff --git a/include/linux/dma-buf-map.h b/include/linux/dma-buf-map.h
index fd1aba545fdf..2e8bbecb5091 100644
--- a/include/linux/dma-buf-map.h
+++ b/include/linux/dma-buf-map.h
@@ -45,6 +45,12 @@
  *
  *	dma_buf_map_set_vaddr(&map. 0xdeadbeaf);
  *
+ * To set an address in I/O memory, use dma_buf_map_set_vaddr_iomem().
+ *
+ * .. code-block:: c
+ *
+ *	dma_buf_map_set_vaddr_iomem(&map. 0xdeadbeaf);
+ *
  * Test if a mapping is valid with either dma_buf_map_is_set() or
  * dma_buf_map_is_null().
  *
@@ -118,6 +124,20 @@ static inline void dma_buf_map_set_vaddr(struct dma_buf_map *map, void *vaddr)
 	map->is_iomem = false;
 }
 
+/**
+ * dma_buf_map_set_vaddr_iomem - Sets a dma-buf mapping structure to an address in I/O memory
+ * @map:		The dma-buf mapping structure
+ * @vaddr_iomem:	An I/O-memory address
+ *
+ * Sets the address and the I/O-memory flag.
+ */
+static inline void dma_buf_map_set_vaddr_iomem(struct dma_buf_map *map,
+					       void __iomem *vaddr_iomem)
+{
+	map->vaddr_iomem = vaddr_iomem;
+	map->is_iomem = true;
+}
+
 /**
  * dma_buf_map_is_equal - Compares two dma-buf mapping structures for equality
  * @lhs:	The dma-buf mapping structure
-- 
cgit v1.2.3


From b4e7090c242ec64bfa77a69ea7c3cceba21c7a65 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Tue, 3 Nov 2020 10:30:14 +0100
Subject: dma-buf-map: Add memcpy and pointer-increment interfaces

To do framebuffer updates, one needs memcpy from system memory and a
pointer-increment function. Add both interfaces with documentation.

v5:
	* include <linux/string.h> to build on sparc64 (Sam)

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Sam Ravnborg <sam@ravnborg.org>
Tested-by: Sam Ravnborg <sam@ravnborg.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20201103093015.1063-10-tzimmermann@suse.de
---
 include/linux/dma-buf-map.h | 73 ++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 63 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/dma-buf-map.h b/include/linux/dma-buf-map.h
index 2e8bbecb5091..583a3a1f9447 100644
--- a/include/linux/dma-buf-map.h
+++ b/include/linux/dma-buf-map.h
@@ -7,6 +7,7 @@
 #define __DMA_BUF_MAP_H__
 
 #include <linux/io.h>
+#include <linux/string.h>
 
 /**
  * DOC: overview
@@ -32,6 +33,14 @@
  * accessing the buffer. Use the returned instance and the helper functions
  * to access the buffer's memory in the correct way.
  *
+ * The type :c:type:`struct dma_buf_map <dma_buf_map>` and its helpers are
+ * actually independent from the dma-buf infrastructure. When sharing buffers
+ * among devices, drivers have to know the location of the memory to access
+ * the buffers in a safe way. :c:type:`struct dma_buf_map <dma_buf_map>`
+ * solves this problem for dma-buf and its users. If other drivers or
+ * sub-systems require similar functionality, the type could be generalized
+ * and moved to a more prominent header file.
+ *
  * Open-coding access to :c:type:`struct dma_buf_map <dma_buf_map>` is
  * considered bad style. Rather then accessing its fields directly, use one
  * of the provided helper functions, or implement your own. For example,
@@ -51,6 +60,14 @@
  *
  *	dma_buf_map_set_vaddr_iomem(&map. 0xdeadbeaf);
  *
+ * Instances of struct dma_buf_map do not have to be cleaned up, but
+ * can be cleared to NULL with dma_buf_map_clear(). Cleared mappings
+ * always refer to system memory.
+ *
+ * .. code-block:: c
+ *
+ *	dma_buf_map_clear(&map);
+ *
  * Test if a mapping is valid with either dma_buf_map_is_set() or
  * dma_buf_map_is_null().
  *
@@ -73,17 +90,19 @@
  *	if (dma_buf_map_is_equal(&sys_map, &io_map))
  *		// always false
  *
- * Instances of struct dma_buf_map do not have to be cleaned up, but
- * can be cleared to NULL with dma_buf_map_clear(). Cleared mappings
- * always refer to system memory.
+ * A set up instance of struct dma_buf_map can be used to access or manipulate
+ * the buffer memory. Depending on the location of the memory, the provided
+ * helpers will pick the correct operations. Data can be copied into the memory
+ * with dma_buf_map_memcpy_to(). The address can be manipulated with
+ * dma_buf_map_incr().
  *
- * The type :c:type:`struct dma_buf_map <dma_buf_map>` and its helpers are
- * actually independent from the dma-buf infrastructure. When sharing buffers
- * among devices, drivers have to know the location of the memory to access
- * the buffers in a safe way. :c:type:`struct dma_buf_map <dma_buf_map>`
- * solves this problem for dma-buf and its users. If other drivers or
- * sub-systems require similar functionality, the type could be generalized
- * and moved to a more prominent header file.
+ * .. code-block:: c
+ *
+ *	const void *src = ...; // source buffer
+ *	size_t len = ...; // length of src
+ *
+ *	dma_buf_map_memcpy_to(&map, src, len);
+ *	dma_buf_map_incr(&map, len); // go to first byte after the memcpy
  */
 
 /**
@@ -210,4 +229,38 @@ static inline void dma_buf_map_clear(struct dma_buf_map *map)
 	}
 }
 
+/**
+ * dma_buf_map_memcpy_to - Memcpy into dma-buf mapping
+ * @dst:	The dma-buf mapping structure
+ * @src:	The source buffer
+ * @len:	The number of byte in src
+ *
+ * Copies data into a dma-buf mapping. The source buffer is in system
+ * memory. Depending on the buffer's location, the helper picks the correct
+ * method of accessing the memory.
+ */
+static inline void dma_buf_map_memcpy_to(struct dma_buf_map *dst, const void *src, size_t len)
+{
+	if (dst->is_iomem)
+		memcpy_toio(dst->vaddr_iomem, src, len);
+	else
+		memcpy(dst->vaddr, src, len);
+}
+
+/**
+ * dma_buf_map_incr - Increments the address stored in a dma-buf mapping
+ * @map:	The dma-buf mapping structure
+ * @incr:	The number of bytes to increment
+ *
+ * Increments the address stored in a dma-buf mapping. Depending on the
+ * buffer's location, the correct value will be updated.
+ */
+static inline void dma_buf_map_incr(struct dma_buf_map *map, size_t incr)
+{
+	if (map->is_iomem)
+		map->vaddr_iomem += incr;
+	else
+		map->vaddr += incr;
+}
+
 #endif /* __DMA_BUF_MAP_H__ */
-- 
cgit v1.2.3


From 22447a99c97e353bde8f90c2353873f27681d57c Mon Sep 17 00:00:00 2001
From: Pawel Czarnecki <pczarnecki@internships.antmicro.com>
Date: Tue, 13 Oct 2020 16:45:52 +0200
Subject: drivers/soc/litex: add LiteX SoC Controller driver

This commit adds driver for the FPGA-based LiteX SoC
Controller from LiteX SoC builder.

Co-developed-by: Mateusz Holenko <mholenko@antmicro.com>
Signed-off-by: Mateusz Holenko <mholenko@antmicro.com>
Signed-off-by: Pawel Czarnecki <pczarnecki@internships.antmicro.com>
Signed-off-by: Stafford Horne <shorne@gmail.com>
---
 MAINTAINERS                        |   2 +
 drivers/soc/Kconfig                |   1 +
 drivers/soc/Makefile               |   1 +
 drivers/soc/litex/Kconfig          |  19 ++++
 drivers/soc/litex/Makefile         |   3 +
 drivers/soc/litex/litex_soc_ctrl.c | 176 +++++++++++++++++++++++++++++++++++++
 include/linux/litex.h              | 102 +++++++++++++++++++++
 7 files changed, 304 insertions(+)
 create mode 100644 drivers/soc/litex/Kconfig
 create mode 100644 drivers/soc/litex/Makefile
 create mode 100644 drivers/soc/litex/litex_soc_ctrl.c
 create mode 100644 include/linux/litex.h

(limited to 'include/linux')

diff --git a/MAINTAINERS b/MAINTAINERS
index 049af639fdfc..3fde022413f9 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10177,6 +10177,8 @@ M:	Karol Gugala <kgugala@antmicro.com>
 M:	Mateusz Holenko <mholenko@antmicro.com>
 S:	Maintained
 F:	Documentation/devicetree/bindings/*/litex,*.yaml
+F:	drivers/soc/litex/litex_soc_ctrl.c
+F:	include/linux/litex.h
 
 LIVE PATCHING
 M:	Josh Poimboeuf <jpoimboe@redhat.com>
diff --git a/drivers/soc/Kconfig b/drivers/soc/Kconfig
index 425ab6f7e375..d097d070f579 100644
--- a/drivers/soc/Kconfig
+++ b/drivers/soc/Kconfig
@@ -9,6 +9,7 @@ source "drivers/soc/bcm/Kconfig"
 source "drivers/soc/fsl/Kconfig"
 source "drivers/soc/imx/Kconfig"
 source "drivers/soc/ixp4xx/Kconfig"
+source "drivers/soc/litex/Kconfig"
 source "drivers/soc/mediatek/Kconfig"
 source "drivers/soc/qcom/Kconfig"
 source "drivers/soc/renesas/Kconfig"
diff --git a/drivers/soc/Makefile b/drivers/soc/Makefile
index 36452bed86ef..0b16108823ef 100644
--- a/drivers/soc/Makefile
+++ b/drivers/soc/Makefile
@@ -14,6 +14,7 @@ obj-$(CONFIG_ARCH_GEMINI)	+= gemini/
 obj-y				+= imx/
 obj-$(CONFIG_ARCH_IXP4XX)	+= ixp4xx/
 obj-$(CONFIG_SOC_XWAY)		+= lantiq/
+obj-$(CONFIG_LITEX_SOC_CONTROLLER) += litex/
 obj-y				+= mediatek/
 obj-y				+= amlogic/
 obj-y				+= qcom/
diff --git a/drivers/soc/litex/Kconfig b/drivers/soc/litex/Kconfig
new file mode 100644
index 000000000000..7c6b009b6f6c
--- /dev/null
+++ b/drivers/soc/litex/Kconfig
@@ -0,0 +1,19 @@
+# SPDX-License_Identifier: GPL-2.0
+
+menu "Enable LiteX SoC Builder specific drivers"
+
+config LITEX
+	bool
+
+config LITEX_SOC_CONTROLLER
+	tristate "Enable LiteX SoC Controller driver"
+	depends on OF || COMPILE_TEST
+	select LITEX
+	help
+	  This option enables the SoC Controller Driver which verifies
+	  LiteX CSR access and provides common litex_get_reg/litex_set_reg
+	  accessors.
+	  All drivers that use functions from litex.h must depend on
+	  LITEX.
+
+endmenu
diff --git a/drivers/soc/litex/Makefile b/drivers/soc/litex/Makefile
new file mode 100644
index 000000000000..98ff7325b1c0
--- /dev/null
+++ b/drivers/soc/litex/Makefile
@@ -0,0 +1,3 @@
+# SPDX-License_Identifier: GPL-2.0
+
+obj-$(CONFIG_LITEX_SOC_CONTROLLER)	+= litex_soc_ctrl.o
diff --git a/drivers/soc/litex/litex_soc_ctrl.c b/drivers/soc/litex/litex_soc_ctrl.c
new file mode 100644
index 000000000000..1217cafdfd4d
--- /dev/null
+++ b/drivers/soc/litex/litex_soc_ctrl.c
@@ -0,0 +1,176 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * LiteX SoC Controller Driver
+ *
+ * Copyright (C) 2020 Antmicro <www.antmicro.com>
+ *
+ */
+
+#include <linux/litex.h>
+#include <linux/device.h>
+#include <linux/errno.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/printk.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/io.h>
+
+/*
+ * LiteX SoC Generator, depending on the configuration, can split a single
+ * logical CSR (Control&Status Register) into a series of consecutive physical
+ * registers.
+ *
+ * For example, in the configuration with 8-bit CSR Bus, 32-bit aligned (the
+ * default one for 32-bit CPUs) a 32-bit logical CSR will be generated as four
+ * 32-bit physical registers, each one containing one byte of meaningful data.
+ *
+ * For details see: https://github.com/enjoy-digital/litex/wiki/CSR-Bus
+ *
+ * The purpose of `litex_set_reg`/`litex_get_reg` is to implement the logic
+ * of writing to/reading from the LiteX CSR in a single place that can be
+ * then reused by all LiteX drivers.
+ */
+
+/**
+ * litex_set_reg() - Writes the value to the LiteX CSR (Control&Status Register)
+ * @reg: Address of the CSR
+ * @reg_size: The width of the CSR expressed in the number of bytes
+ * @val: Value to be written to the CSR
+ *
+ * In the currently supported LiteX configuration (8-bit CSR Bus, 32-bit aligned),
+ * a 32-bit LiteX CSR is generated as 4 consecutive 32-bit physical registers,
+ * each one containing one byte of meaningful data.
+ *
+ * This function splits a single possibly multi-byte write into a series of
+ * single-byte writes with a proper offset.
+ */
+void litex_set_reg(void __iomem *reg, unsigned long reg_size,
+		    unsigned long val)
+{
+	unsigned long shifted_data, shift, i;
+
+	for (i = 0; i < reg_size; ++i) {
+		shift = ((reg_size - i - 1) * LITEX_SUBREG_SIZE_BIT);
+		shifted_data = val >> shift;
+
+		WRITE_LITEX_SUBREGISTER(shifted_data, reg, i);
+	}
+}
+EXPORT_SYMBOL_GPL(litex_set_reg);
+
+/**
+ * litex_get_reg() - Reads the value of the LiteX CSR (Control&Status Register)
+ * @reg: Address of the CSR
+ * @reg_size: The width of the CSR expressed in the number of bytes
+ *
+ * Return: Value read from the CSR
+ *
+ * In the currently supported LiteX configuration (8-bit CSR Bus, 32-bit aligned),
+ * a 32-bit LiteX CSR is generated as 4 consecutive 32-bit physical registers,
+ * each one containing one byte of meaningful data.
+ *
+ * This function generates a series of single-byte reads with a proper offset
+ * and joins their results into a single multi-byte value.
+ */
+unsigned long litex_get_reg(void __iomem *reg, unsigned long reg_size)
+{
+	unsigned long shifted_data, shift, i;
+	unsigned long result = 0;
+
+	for (i = 0; i < reg_size; ++i) {
+		shifted_data = READ_LITEX_SUBREGISTER(reg, i);
+
+		shift = ((reg_size - i - 1) * LITEX_SUBREG_SIZE_BIT);
+		result |= (shifted_data << shift);
+	}
+
+	return result;
+}
+EXPORT_SYMBOL_GPL(litex_get_reg);
+
+#define SCRATCH_REG_OFF         0x04
+#define SCRATCH_REG_VALUE       0x12345678
+#define SCRATCH_TEST_VALUE      0xdeadbeef
+
+/*
+ * Check LiteX CSR read/write access
+ *
+ * This function reads and writes a scratch register in order to verify if CSR
+ * access works.
+ *
+ * In case any problems are detected, the driver should panic.
+ *
+ * Access to the LiteX CSR is, by design, done in CPU native endianness.
+ * The driver should not dynamically configure access functions when
+ * the endianness mismatch is detected. Such situation indicates problems in
+ * the soft SoC design and should be solved at the LiteX generator level,
+ * not in the software.
+ */
+static int litex_check_csr_access(void __iomem *reg_addr)
+{
+	unsigned long reg;
+
+	reg = litex_read32(reg_addr + SCRATCH_REG_OFF);
+
+	if (reg != SCRATCH_REG_VALUE) {
+		panic("Scratch register read error - the system is probably broken! Expected: 0x%x but got: 0x%lx",
+			SCRATCH_REG_VALUE, reg);
+		return -EINVAL;
+	}
+
+	litex_write32(reg_addr + SCRATCH_REG_OFF, SCRATCH_TEST_VALUE);
+	reg = litex_read32(reg_addr + SCRATCH_REG_OFF);
+
+	if (reg != SCRATCH_TEST_VALUE) {
+		panic("Scratch register write error - the system is probably broken! Expected: 0x%x but got: 0x%lx",
+			SCRATCH_TEST_VALUE, reg);
+		return -EINVAL;
+	}
+
+	/* restore original value of the SCRATCH register */
+	litex_write32(reg_addr + SCRATCH_REG_OFF, SCRATCH_REG_VALUE);
+
+	pr_info("LiteX SoC Controller driver initialized");
+
+	return 0;
+}
+
+struct litex_soc_ctrl_device {
+	void __iomem *base;
+};
+
+static const struct of_device_id litex_soc_ctrl_of_match[] = {
+	{.compatible = "litex,soc-controller"},
+	{},
+};
+
+MODULE_DEVICE_TABLE(of, litex_soc_ctrl_of_match);
+
+static int litex_soc_ctrl_probe(struct platform_device *pdev)
+{
+	struct litex_soc_ctrl_device *soc_ctrl_dev;
+
+	soc_ctrl_dev = devm_kzalloc(&pdev->dev, sizeof(*soc_ctrl_dev), GFP_KERNEL);
+	if (!soc_ctrl_dev)
+		return -ENOMEM;
+
+	soc_ctrl_dev->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(soc_ctrl_dev->base))
+		return PTR_ERR(soc_ctrl_dev->base);
+
+	return litex_check_csr_access(soc_ctrl_dev->base);
+}
+
+static struct platform_driver litex_soc_ctrl_driver = {
+	.driver = {
+		.name = "litex-soc-controller",
+		.of_match_table = of_match_ptr(litex_soc_ctrl_of_match)
+	},
+	.probe = litex_soc_ctrl_probe,
+};
+
+module_platform_driver(litex_soc_ctrl_driver);
+MODULE_DESCRIPTION("LiteX SoC Controller driver");
+MODULE_AUTHOR("Antmicro <www.antmicro.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/litex.h b/include/linux/litex.h
new file mode 100644
index 000000000000..40f5be503593
--- /dev/null
+++ b/include/linux/litex.h
@@ -0,0 +1,102 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Common LiteX header providing
+ * helper functions for accessing CSRs.
+ *
+ * Implementation of the functions is provided by
+ * the LiteX SoC Controller driver.
+ *
+ * Copyright (C) 2019-2020 Antmicro <www.antmicro.com>
+ */
+
+#ifndef _LINUX_LITEX_H
+#define _LINUX_LITEX_H
+
+#include <linux/io.h>
+#include <linux/types.h>
+#include <linux/compiler_types.h>
+
+/*
+ * The parameters below are true for LiteX SoCs configured for 8-bit CSR Bus,
+ * 32-bit aligned.
+ *
+ * Supporting other configurations will require extending the logic in this
+ * header and in the LiteX SoC controller driver.
+ */
+#define LITEX_REG_SIZE	  0x4
+#define LITEX_SUBREG_SIZE	0x1
+#define LITEX_SUBREG_SIZE_BIT	 (LITEX_SUBREG_SIZE * 8)
+
+#define WRITE_LITEX_SUBREGISTER(val, base_offset, subreg_id) \
+	writel((u32 __force)cpu_to_le32(val), base_offset + (LITEX_REG_SIZE * subreg_id))
+
+#define READ_LITEX_SUBREGISTER(base_offset, subreg_id) \
+	le32_to_cpu((__le32 __force)readl(base_offset + (LITEX_REG_SIZE * subreg_id)))
+
+void litex_set_reg(void __iomem *reg, unsigned long reg_sz, unsigned long val);
+
+unsigned long litex_get_reg(void __iomem *reg, unsigned long reg_sz);
+
+static inline void litex_write8(void __iomem *reg, u8 val)
+{
+	WRITE_LITEX_SUBREGISTER(val, reg, 0);
+}
+
+static inline void litex_write16(void __iomem *reg, u16 val)
+{
+	WRITE_LITEX_SUBREGISTER(val >> 8, reg, 0);
+	WRITE_LITEX_SUBREGISTER(val, reg, 1);
+}
+
+static inline void litex_write32(void __iomem *reg, u32 val)
+{
+	WRITE_LITEX_SUBREGISTER(val >> 24, reg, 0);
+	WRITE_LITEX_SUBREGISTER(val >> 16, reg, 1);
+	WRITE_LITEX_SUBREGISTER(val >> 8, reg, 2);
+	WRITE_LITEX_SUBREGISTER(val, reg, 3);
+}
+
+static inline void litex_write64(void __iomem *reg, u64 val)
+{
+	WRITE_LITEX_SUBREGISTER(val >> 56, reg, 0);
+	WRITE_LITEX_SUBREGISTER(val >> 48, reg, 1);
+	WRITE_LITEX_SUBREGISTER(val >> 40, reg, 2);
+	WRITE_LITEX_SUBREGISTER(val >> 32, reg, 3);
+	WRITE_LITEX_SUBREGISTER(val >> 24, reg, 4);
+	WRITE_LITEX_SUBREGISTER(val >> 16, reg, 5);
+	WRITE_LITEX_SUBREGISTER(val >> 8, reg, 6);
+	WRITE_LITEX_SUBREGISTER(val, reg, 7);
+}
+
+static inline u8 litex_read8(void __iomem *reg)
+{
+	return READ_LITEX_SUBREGISTER(reg, 0);
+}
+
+static inline u16 litex_read16(void __iomem *reg)
+{
+	return (READ_LITEX_SUBREGISTER(reg, 0) << 8)
+		| (READ_LITEX_SUBREGISTER(reg, 1));
+}
+
+static inline u32 litex_read32(void __iomem *reg)
+{
+	return (READ_LITEX_SUBREGISTER(reg, 0) << 24)
+		| (READ_LITEX_SUBREGISTER(reg, 1) << 16)
+		| (READ_LITEX_SUBREGISTER(reg, 2) << 8)
+		| (READ_LITEX_SUBREGISTER(reg, 3));
+}
+
+static inline u64 litex_read64(void __iomem *reg)
+{
+	return ((u64)READ_LITEX_SUBREGISTER(reg, 0) << 56)
+		| ((u64)READ_LITEX_SUBREGISTER(reg, 1) << 48)
+		| ((u64)READ_LITEX_SUBREGISTER(reg, 2) << 40)
+		| ((u64)READ_LITEX_SUBREGISTER(reg, 3) << 32)
+		| ((u64)READ_LITEX_SUBREGISTER(reg, 4) << 24)
+		| ((u64)READ_LITEX_SUBREGISTER(reg, 5) << 16)
+		| ((u64)READ_LITEX_SUBREGISTER(reg, 6) << 8)
+		| ((u64)READ_LITEX_SUBREGISTER(reg, 7));
+}
+
+#endif /* _LINUX_LITEX_H */
-- 
cgit v1.2.3


From 267fb27352b6fc9fdbad753127a239f75618ecbc Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 30 Oct 2020 15:50:32 +0100
Subject: perf: Reduce stack usage of perf_output_begin()

__perf_output_begin() has an on-stack struct perf_sample_data in the
unlikely case it needs to generate a LOST record. However, every call
to perf_output_begin() must already have a perf_sample_data on-stack.

Reported-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20201030151954.985416146@infradead.org
---
 arch/powerpc/perf/imc-pmu.c     |  2 +-
 arch/s390/kernel/perf_cpum_sf.c |  2 +-
 arch/x86/events/intel/ds.c      |  4 ++--
 include/linux/perf_event.h      |  7 +++++--
 kernel/events/core.c            | 32 +++++++++++++++++---------------
 kernel/events/ring_buffer.c     | 20 +++++++++++---------
 6 files changed, 37 insertions(+), 30 deletions(-)

(limited to 'include/linux')

diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c
index 9ed4fcccf8a9..7b25548ec42b 100644
--- a/arch/powerpc/perf/imc-pmu.c
+++ b/arch/powerpc/perf/imc-pmu.c
@@ -1336,7 +1336,7 @@ static void dump_trace_imc_data(struct perf_event *event)
 			/* If this is a valid record, create the sample */
 			struct perf_output_handle handle;
 
-			if (perf_output_begin(&handle, event, header.size))
+			if (perf_output_begin(&handle, &data, event, header.size))
 				return;
 
 			perf_output_sample(&handle, &header, &data, event);
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 4f9e4626df55..00255ae3979d 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -672,7 +672,7 @@ static void cpumsf_output_event_pid(struct perf_event *event,
 	rcu_read_lock();
 
 	perf_prepare_sample(&header, data, event, regs);
-	if (perf_output_begin(&handle, event, header.size))
+	if (perf_output_begin(&handle, data, event, header.size))
 		goto out;
 
 	/* Update the process ID (see also kernel/events/core.c) */
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 404315df1e16..cd2ae14a0a98 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -642,8 +642,8 @@ int intel_pmu_drain_bts_buffer(void)
 	rcu_read_lock();
 	perf_prepare_sample(&header, &data, event, &regs);
 
-	if (perf_output_begin(&handle, event, header.size *
-			      (top - base - skip)))
+	if (perf_output_begin(&handle, &data, event,
+			      header.size * (top - base - skip)))
 		goto unlock;
 
 	for (at = base; at < top; at++) {
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 0c19d279b97f..b775ae0a8c87 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1400,11 +1400,14 @@ perf_event_addr_filters(struct perf_event *event)
 extern void perf_event_addr_filters_sync(struct perf_event *event);
 
 extern int perf_output_begin(struct perf_output_handle *handle,
+			     struct perf_sample_data *data,
 			     struct perf_event *event, unsigned int size);
 extern int perf_output_begin_forward(struct perf_output_handle *handle,
-				    struct perf_event *event,
-				    unsigned int size);
+				     struct perf_sample_data *data,
+				     struct perf_event *event,
+				     unsigned int size);
 extern int perf_output_begin_backward(struct perf_output_handle *handle,
+				      struct perf_sample_data *data,
 				      struct perf_event *event,
 				      unsigned int size);
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 5a29ab09e72d..fc681c7c1e03 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7186,6 +7186,7 @@ __perf_event_output(struct perf_event *event,
 		    struct perf_sample_data *data,
 		    struct pt_regs *regs,
 		    int (*output_begin)(struct perf_output_handle *,
+					struct perf_sample_data *,
 					struct perf_event *,
 					unsigned int))
 {
@@ -7198,7 +7199,7 @@ __perf_event_output(struct perf_event *event,
 
 	perf_prepare_sample(&header, data, event, regs);
 
-	err = output_begin(&handle, event, header.size);
+	err = output_begin(&handle, data, event, header.size);
 	if (err)
 		goto exit;
 
@@ -7264,7 +7265,7 @@ perf_event_read_event(struct perf_event *event,
 	int ret;
 
 	perf_event_header__init_id(&read_event.header, &sample, event);
-	ret = perf_output_begin(&handle, event, read_event.header.size);
+	ret = perf_output_begin(&handle, &sample, event, read_event.header.size);
 	if (ret)
 		return;
 
@@ -7533,7 +7534,7 @@ static void perf_event_task_output(struct perf_event *event,
 
 	perf_event_header__init_id(&task_event->event_id.header, &sample, event);
 
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				task_event->event_id.header.size);
 	if (ret)
 		goto out;
@@ -7636,7 +7637,7 @@ static void perf_event_comm_output(struct perf_event *event,
 		return;
 
 	perf_event_header__init_id(&comm_event->event_id.header, &sample, event);
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				comm_event->event_id.header.size);
 
 	if (ret)
@@ -7736,7 +7737,7 @@ static void perf_event_namespaces_output(struct perf_event *event,
 
 	perf_event_header__init_id(&namespaces_event->event_id.header,
 				   &sample, event);
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				namespaces_event->event_id.header.size);
 	if (ret)
 		goto out;
@@ -7863,7 +7864,7 @@ static void perf_event_cgroup_output(struct perf_event *event, void *data)
 
 	perf_event_header__init_id(&cgroup_event->event_id.header,
 				   &sample, event);
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				cgroup_event->event_id.header.size);
 	if (ret)
 		goto out;
@@ -7989,7 +7990,7 @@ static void perf_event_mmap_output(struct perf_event *event,
 	}
 
 	perf_event_header__init_id(&mmap_event->event_id.header, &sample, event);
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				mmap_event->event_id.header.size);
 	if (ret)
 		goto out;
@@ -8299,7 +8300,7 @@ void perf_event_aux_event(struct perf_event *event, unsigned long head,
 	int ret;
 
 	perf_event_header__init_id(&rec.header, &sample, event);
-	ret = perf_output_begin(&handle, event, rec.header.size);
+	ret = perf_output_begin(&handle, &sample, event, rec.header.size);
 
 	if (ret)
 		return;
@@ -8333,7 +8334,7 @@ void perf_log_lost_samples(struct perf_event *event, u64 lost)
 
 	perf_event_header__init_id(&lost_samples_event.header, &sample, event);
 
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				lost_samples_event.header.size);
 	if (ret)
 		return;
@@ -8388,7 +8389,7 @@ static void perf_event_switch_output(struct perf_event *event, void *data)
 
 	perf_event_header__init_id(&se->event_id.header, &sample, event);
 
-	ret = perf_output_begin(&handle, event, se->event_id.header.size);
+	ret = perf_output_begin(&handle, &sample, event, se->event_id.header.size);
 	if (ret)
 		return;
 
@@ -8463,7 +8464,7 @@ static void perf_log_throttle(struct perf_event *event, int enable)
 
 	perf_event_header__init_id(&throttle_event.header, &sample, event);
 
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				throttle_event.header.size);
 	if (ret)
 		return;
@@ -8506,7 +8507,7 @@ static void perf_event_ksymbol_output(struct perf_event *event, void *data)
 
 	perf_event_header__init_id(&ksymbol_event->event_id.header,
 				   &sample, event);
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				ksymbol_event->event_id.header.size);
 	if (ret)
 		return;
@@ -8596,7 +8597,7 @@ static void perf_event_bpf_output(struct perf_event *event, void *data)
 
 	perf_event_header__init_id(&bpf_event->event_id.header,
 				   &sample, event);
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, data, event,
 				bpf_event->event_id.header.size);
 	if (ret)
 		return;
@@ -8705,7 +8706,8 @@ static void perf_event_text_poke_output(struct perf_event *event, void *data)
 
 	perf_event_header__init_id(&text_poke_event->event_id.header, &sample, event);
 
-	ret = perf_output_begin(&handle, event, text_poke_event->event_id.header.size);
+	ret = perf_output_begin(&handle, &sample, event,
+				text_poke_event->event_id.header.size);
 	if (ret)
 		return;
 
@@ -8786,7 +8788,7 @@ static void perf_log_itrace_start(struct perf_event *event)
 	rec.tid	= perf_event_tid(event, current);
 
 	perf_event_header__init_id(&rec.header, &sample, event);
-	ret = perf_output_begin(&handle, event, rec.header.size);
+	ret = perf_output_begin(&handle, &sample, event, rec.header.size);
 
 	if (ret)
 		return;
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 192b8abc6330..ef91ae75ca56 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -147,6 +147,7 @@ ring_buffer_has_space(unsigned long head, unsigned long tail,
 
 static __always_inline int
 __perf_output_begin(struct perf_output_handle *handle,
+		    struct perf_sample_data *data,
 		    struct perf_event *event, unsigned int size,
 		    bool backward)
 {
@@ -237,18 +238,16 @@ __perf_output_begin(struct perf_output_handle *handle,
 	handle->size = (1UL << page_shift) - offset;
 
 	if (unlikely(have_lost)) {
-		struct perf_sample_data sample_data;
-
 		lost_event.header.size = sizeof(lost_event);
 		lost_event.header.type = PERF_RECORD_LOST;
 		lost_event.header.misc = 0;
 		lost_event.id          = event->id;
 		lost_event.lost        = local_xchg(&rb->lost, 0);
 
-		perf_event_header__init_id(&lost_event.header,
-					   &sample_data, event);
+		/* XXX mostly redundant; @data is already fully initializes */
+		perf_event_header__init_id(&lost_event.header, data, event);
 		perf_output_put(handle, lost_event);
-		perf_event__output_id_sample(event, handle, &sample_data);
+		perf_event__output_id_sample(event, handle, data);
 	}
 
 	return 0;
@@ -263,22 +262,25 @@ out:
 }
 
 int perf_output_begin_forward(struct perf_output_handle *handle,
-			     struct perf_event *event, unsigned int size)
+			      struct perf_sample_data *data,
+			      struct perf_event *event, unsigned int size)
 {
-	return __perf_output_begin(handle, event, size, false);
+	return __perf_output_begin(handle, data, event, size, false);
 }
 
 int perf_output_begin_backward(struct perf_output_handle *handle,
+			       struct perf_sample_data *data,
 			       struct perf_event *event, unsigned int size)
 {
-	return __perf_output_begin(handle, event, size, true);
+	return __perf_output_begin(handle, data, event, size, true);
 }
 
 int perf_output_begin(struct perf_output_handle *handle,
+		      struct perf_sample_data *data,
 		      struct perf_event *event, unsigned int size)
 {
 
-	return __perf_output_begin(handle, event, size,
+	return __perf_output_begin(handle, data, event, size,
 				   unlikely(is_write_backward(event)));
 }
 
-- 
cgit v1.2.3


From 76a4efa80900fc40e0fdf243b42aec9fb8c35d24 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 30 Oct 2020 12:14:21 +0100
Subject: perf/arch: Remove perf_sample_data::regs_user_copy

struct perf_sample_data lives on-stack, we should be careful about it's
size. Furthermore, the pt_regs copy in there is only because x86_64 is a
trainwreck, solve it differently.

Reported-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Steven Rostedt <rostedt@goodmis.org>
Link: https://lkml.kernel.org/r/20201030151955.258178461@infradead.org
---
 arch/arm/kernel/perf_regs.c   |  3 +--
 arch/arm64/kernel/perf_regs.c |  3 +--
 arch/csky/kernel/perf_regs.c  |  3 +--
 arch/powerpc/perf/perf_regs.c |  3 +--
 arch/riscv/kernel/perf_regs.c |  3 +--
 arch/s390/kernel/perf_regs.c  |  3 +--
 arch/x86/kernel/perf_regs.c   | 15 +++++++++++----
 include/linux/perf_event.h    |  6 ------
 include/linux/perf_regs.h     |  6 ++----
 kernel/events/core.c          |  8 +++-----
 10 files changed, 22 insertions(+), 31 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/kernel/perf_regs.c b/arch/arm/kernel/perf_regs.c
index 05fe92aa7d98..0529f90395c9 100644
--- a/arch/arm/kernel/perf_regs.c
+++ b/arch/arm/kernel/perf_regs.c
@@ -32,8 +32,7 @@ u64 perf_reg_abi(struct task_struct *task)
 }
 
 void perf_get_regs_user(struct perf_regs *regs_user,
-			struct pt_regs *regs,
-			struct pt_regs *regs_user_copy)
+			struct pt_regs *regs)
 {
 	regs_user->regs = task_pt_regs(current);
 	regs_user->abi = perf_reg_abi(current);
diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c
index 94e8718e7229..f6f58e6265df 100644
--- a/arch/arm64/kernel/perf_regs.c
+++ b/arch/arm64/kernel/perf_regs.c
@@ -73,8 +73,7 @@ u64 perf_reg_abi(struct task_struct *task)
 }
 
 void perf_get_regs_user(struct perf_regs *regs_user,
-			struct pt_regs *regs,
-			struct pt_regs *regs_user_copy)
+			struct pt_regs *regs)
 {
 	regs_user->regs = task_pt_regs(current);
 	regs_user->abi = perf_reg_abi(current);
diff --git a/arch/csky/kernel/perf_regs.c b/arch/csky/kernel/perf_regs.c
index eb32838b8210..09b7f88a2d6a 100644
--- a/arch/csky/kernel/perf_regs.c
+++ b/arch/csky/kernel/perf_regs.c
@@ -32,8 +32,7 @@ u64 perf_reg_abi(struct task_struct *task)
 }
 
 void perf_get_regs_user(struct perf_regs *regs_user,
-			struct pt_regs *regs,
-			struct pt_regs *regs_user_copy)
+			struct pt_regs *regs)
 {
 	regs_user->regs = task_pt_regs(current);
 	regs_user->abi = perf_reg_abi(current);
diff --git a/arch/powerpc/perf/perf_regs.c b/arch/powerpc/perf/perf_regs.c
index 8e53f2fc3fe0..6f681b105eec 100644
--- a/arch/powerpc/perf/perf_regs.c
+++ b/arch/powerpc/perf/perf_regs.c
@@ -144,8 +144,7 @@ u64 perf_reg_abi(struct task_struct *task)
 }
 
 void perf_get_regs_user(struct perf_regs *regs_user,
-			struct pt_regs *regs,
-			struct pt_regs *regs_user_copy)
+			struct pt_regs *regs)
 {
 	regs_user->regs = task_pt_regs(current);
 	regs_user->abi = (regs_user->regs) ? perf_reg_abi(current) :
diff --git a/arch/riscv/kernel/perf_regs.c b/arch/riscv/kernel/perf_regs.c
index 04a38fbeb9c7..fd304a248de6 100644
--- a/arch/riscv/kernel/perf_regs.c
+++ b/arch/riscv/kernel/perf_regs.c
@@ -36,8 +36,7 @@ u64 perf_reg_abi(struct task_struct *task)
 }
 
 void perf_get_regs_user(struct perf_regs *regs_user,
-			struct pt_regs *regs,
-			struct pt_regs *regs_user_copy)
+			struct pt_regs *regs)
 {
 	regs_user->regs = task_pt_regs(current);
 	regs_user->abi = perf_reg_abi(current);
diff --git a/arch/s390/kernel/perf_regs.c b/arch/s390/kernel/perf_regs.c
index 4352a504f235..6e9e5d5e927e 100644
--- a/arch/s390/kernel/perf_regs.c
+++ b/arch/s390/kernel/perf_regs.c
@@ -53,8 +53,7 @@ u64 perf_reg_abi(struct task_struct *task)
 }
 
 void perf_get_regs_user(struct perf_regs *regs_user,
-			struct pt_regs *regs,
-			struct pt_regs *regs_user_copy)
+			struct pt_regs *regs)
 {
 	/*
 	 * Use the regs from the first interruption and let
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index bb7e1132290b..f9e5352b3bef 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -101,8 +101,7 @@ u64 perf_reg_abi(struct task_struct *task)
 }
 
 void perf_get_regs_user(struct perf_regs *regs_user,
-			struct pt_regs *regs,
-			struct pt_regs *regs_user_copy)
+			struct pt_regs *regs)
 {
 	regs_user->regs = task_pt_regs(current);
 	regs_user->abi = perf_reg_abi(current);
@@ -129,12 +128,20 @@ u64 perf_reg_abi(struct task_struct *task)
 		return PERF_SAMPLE_REGS_ABI_64;
 }
 
+static DEFINE_PER_CPU(struct pt_regs, nmi_user_regs);
+
 void perf_get_regs_user(struct perf_regs *regs_user,
-			struct pt_regs *regs,
-			struct pt_regs *regs_user_copy)
+			struct pt_regs *regs)
 {
+	struct pt_regs *regs_user_copy = this_cpu_ptr(&nmi_user_regs);
 	struct pt_regs *user_regs = task_pt_regs(current);
 
+	if (!in_nmi()) {
+		regs_user->regs = user_regs;
+		regs_user->abi = perf_reg_abi(current);
+		return;
+	}
+
 	/*
 	 * If we're in an NMI that interrupted task_pt_regs setup, then
 	 * we can't sample user regs at all.  This check isn't really
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index b775ae0a8c87..96450f6fb1de 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1022,13 +1022,7 @@ struct perf_sample_data {
 	struct perf_callchain_entry	*callchain;
 	u64				aux_size;
 
-	/*
-	 * regs_user may point to task_pt_regs or to regs_user_copy, depending
-	 * on arch details.
-	 */
 	struct perf_regs		regs_user;
-	struct pt_regs			regs_user_copy;
-
 	struct perf_regs		regs_intr;
 	u64				stack_user_size;
 
diff --git a/include/linux/perf_regs.h b/include/linux/perf_regs.h
index 2d12e97d5e7b..f632c5725f16 100644
--- a/include/linux/perf_regs.h
+++ b/include/linux/perf_regs.h
@@ -20,8 +20,7 @@ u64 perf_reg_value(struct pt_regs *regs, int idx);
 int perf_reg_validate(u64 mask);
 u64 perf_reg_abi(struct task_struct *task);
 void perf_get_regs_user(struct perf_regs *regs_user,
-			struct pt_regs *regs,
-			struct pt_regs *regs_user_copy);
+			struct pt_regs *regs);
 #else
 
 #define PERF_REG_EXTENDED_MASK	0
@@ -42,8 +41,7 @@ static inline u64 perf_reg_abi(struct task_struct *task)
 }
 
 static inline void perf_get_regs_user(struct perf_regs *regs_user,
-				      struct pt_regs *regs,
-				      struct pt_regs *regs_user_copy)
+				      struct pt_regs *regs)
 {
 	regs_user->regs = task_pt_regs(current);
 	regs_user->abi = perf_reg_abi(current);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index fc681c7c1e03..d67c9cbb0f6a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6374,14 +6374,13 @@ perf_output_sample_regs(struct perf_output_handle *handle,
 }
 
 static void perf_sample_regs_user(struct perf_regs *regs_user,
-				  struct pt_regs *regs,
-				  struct pt_regs *regs_user_copy)
+				  struct pt_regs *regs)
 {
 	if (user_mode(regs)) {
 		regs_user->abi = perf_reg_abi(current);
 		regs_user->regs = regs;
 	} else if (!(current->flags & PF_KTHREAD)) {
-		perf_get_regs_user(regs_user, regs, regs_user_copy);
+		perf_get_regs_user(regs_user, regs);
 	} else {
 		regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE;
 		regs_user->regs = NULL;
@@ -7083,8 +7082,7 @@ void perf_prepare_sample(struct perf_event_header *header,
 	}
 
 	if (sample_type & (PERF_SAMPLE_REGS_USER | PERF_SAMPLE_STACK_USER))
-		perf_sample_regs_user(&data->regs_user, regs,
-				      &data->regs_user_copy);
+		perf_sample_regs_user(&data->regs_user, regs);
 
 	if (sample_type & PERF_SAMPLE_REGS_USER) {
 		/* regs dump ABI info */
-- 
cgit v1.2.3


From 21774fd81a51ec1eccd59caf922d387977acd2aa Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Thu, 15 Oct 2020 14:57:26 -0400
Subject: kernfs: bring names in comments in line with code

Fix two stragglers in the comments of the below rename operation.

Fixes: adc5e8b58f48 ("kernfs: drop s_ prefix from kernfs_node members")
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/20201015185726.1386868-1-willemdebruijn.kernel@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/kernfs/dir.c        | 2 +-
 include/linux/kernfs.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 9aec80b9d7c6..ea3c95125bf1 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -1599,7 +1599,7 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
 	return error;
 }
 
-/* Relationship between s_mode and the DT_xxx types */
+/* Relationship between mode and the DT_xxx types */
 static inline unsigned char dt_type(struct kernfs_node *kn)
 {
 	return (kn->mode >> 12) & 15;
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 89f6a4214a70..9e8ca8743c26 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -116,7 +116,7 @@ struct kernfs_elem_attr {
  * kernfs node is represented by single kernfs_node.  Most fields are
  * private to kernfs and shouldn't be accessed directly by kernfs users.
  *
- * As long as s_count reference is held, the kernfs_node itself is
+ * As long as count reference is held, the kernfs_node itself is
  * accessible.  Dereferencing elem or any other outer entity requires
  * active reference.
  */
-- 
cgit v1.2.3


From 9f38abefd37af8726d59706b9b84530630b6b620 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Fri, 23 Oct 2020 18:33:17 +0200
Subject: uio: fix some kernel-doc markups

The definitions for (devm_)uio_register_device should be
at the header file, as the macros are there. The ones
inside uio.c refer, instead, to __(devm_)uio_register_device.

Update them and add new kernel-doc markups for the macros.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Link: https://lore.kernel.org/r/82ab7b68d271aeda7396e369ff8a629491b9d628.1603469755.git.mchehab+huawei@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/uio/uio.c          |  4 ++--
 include/linux/uio_driver.h | 16 ++++++++++++++++
 2 files changed, 18 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c
index 6dca744e39e9..01b349c1b923 100644
--- a/drivers/uio/uio.c
+++ b/drivers/uio/uio.c
@@ -906,7 +906,7 @@ static void uio_device_release(struct device *dev)
 }
 
 /**
- * uio_register_device - register a new userspace IO device
+ * __uio_register_device - register a new userspace IO device
  * @owner:	module that creates the new device
  * @parent:	parent device
  * @info:	UIO device capabilities
@@ -1002,7 +1002,7 @@ static void devm_uio_unregister_device(struct device *dev, void *res)
 }
 
 /**
- * devm_uio_register_device - Resource managed uio_register_device()
+ * __devm_uio_register_device - Resource managed uio_register_device()
  * @owner:	module that creates the new device
  * @parent:	parent device
  * @info:	UIO device capabilities
diff --git a/include/linux/uio_driver.h b/include/linux/uio_driver.h
index 54bf6b118401..47c5962b876b 100644
--- a/include/linux/uio_driver.h
+++ b/include/linux/uio_driver.h
@@ -117,6 +117,14 @@ extern int __must_check
 			      struct uio_info *info);
 
 /* use a define to avoid include chaining to get THIS_MODULE */
+
+/**
+ * uio_register_device - register a new userspace IO device
+ * @parent:	parent device
+ * @info:	UIO device capabilities
+ *
+ * returns zero on success or a negative error code.
+ */
 #define uio_register_device(parent, info) \
 	__uio_register_device(THIS_MODULE, parent, info)
 
@@ -129,6 +137,14 @@ extern int __must_check
 				   struct uio_info *info);
 
 /* use a define to avoid include chaining to get THIS_MODULE */
+
+/**
+ * devm_uio_register_device - Resource managed uio_register_device()
+ * @parent:	parent device
+ * @info:	UIO device capabilities
+ *
+ * returns zero on success or a negative error code.
+ */
 #define devm_uio_register_device(parent, info) \
 	__devm_uio_register_device(THIS_MODULE, parent, info)
 
-- 
cgit v1.2.3


From 33c0c9bdf7a59051a654cd98b7d2b48ce0080967 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Fri, 23 Oct 2020 18:32:56 +0200
Subject: drivers: base: fix some kernel-doc markups

class_create is actually defined at the header. Fix the
markup there and add a new one at the right place.

While here, also fix some markups for functions that have
different names between their prototypes and kernel-doc
comments.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Link: https://lore.kernel.org/r/2fb6efd6a1f90d69ff73bf579566079cbb051e15.1603469755.git.mchehab+huawei@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/class.c                    |  2 +-
 drivers/base/devres.c                   |  2 +-
 drivers/base/firmware_loader/fallback.c |  2 +-
 include/linux/device/class.h            | 14 ++++++++++++++
 4 files changed, 17 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/class.c b/drivers/base/class.c
index c3451481194e..7476f393df97 100644
--- a/drivers/base/class.c
+++ b/drivers/base/class.c
@@ -210,7 +210,7 @@ static void class_create_release(struct class *cls)
 }
 
 /**
- * class_create - create a struct class structure
+ * __class_create - create a struct class structure
  * @owner: pointer to the module that is to "own" this struct class
  * @name: pointer to a string for the name of this class.
  * @key: the lock_class_key for this class; used by mutex lock debugging
diff --git a/drivers/base/devres.c b/drivers/base/devres.c
index 586e9a75c840..fb9d5289a620 100644
--- a/drivers/base/devres.c
+++ b/drivers/base/devres.c
@@ -149,7 +149,7 @@ void * __devres_alloc_node(dr_release_t release, size_t size, gfp_t gfp, int nid
 EXPORT_SYMBOL_GPL(__devres_alloc_node);
 #else
 /**
- * devres_alloc - Allocate device resource data
+ * devres_alloc_node - Allocate device resource data
  * @release: Release function devres will be associated with
  * @size: Allocation size
  * @gfp: Allocation flags
diff --git a/drivers/base/firmware_loader/fallback.c b/drivers/base/firmware_loader/fallback.c
index 4dec4b79ae06..91899d185e31 100644
--- a/drivers/base/firmware_loader/fallback.c
+++ b/drivers/base/firmware_loader/fallback.c
@@ -128,7 +128,7 @@ static ssize_t timeout_show(struct class *class, struct class_attribute *attr,
 }
 
 /**
- * firmware_timeout_store() - set number of seconds to wait for firmware
+ * timeout_store() - set number of seconds to wait for firmware
  * @class: device class pointer
  * @attr: device attribute pointer
  * @buf: buffer to scan for timeout value
diff --git a/include/linux/device/class.h b/include/linux/device/class.h
index e8d470c457d1..e61ec5502019 100644
--- a/include/linux/device/class.h
+++ b/include/linux/device/class.h
@@ -256,6 +256,20 @@ extern void class_destroy(struct class *cls);
 
 /* This is a #define to keep the compiler from merging different
  * instances of the __key variable */
+
+/**
+ * class_create - create a struct class structure
+ * @owner: pointer to the module that is to "own" this struct class
+ * @name: pointer to a string for the name of this class.
+ *
+ * This is used to create a struct class pointer that can then be used
+ * in calls to device_create().
+ *
+ * Returns &struct class pointer on success, or ERR_PTR() on error.
+ *
+ * Note, the pointer created here is to be destroyed when finished by
+ * making a call to class_destroy().
+ */
 #define class_create(owner, name)		\
 ({						\
 	static struct lock_class_key __key;	\
-- 
cgit v1.2.3


From a18394269fc87276963e8d965c730900178d7e4b Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 7 Nov 2020 21:49:07 +0100
Subject: net: core: add dev_get_tstats64 as a ndo_get_stats64 implementation

It's a frequent pattern to use netdev->stats for the less frequently
accessed counters and per-cpu counters for the frequently accessed
counters (rx/tx bytes/packets). Add a default ndo_get_stats64()
implementation for this use case.

Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h |  1 +
 net/core/dev.c            | 15 +++++++++++++++
 2 files changed, 16 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index a53ed2d1ed1d..7ce648a564f7 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4527,6 +4527,7 @@ void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64,
 			     const struct net_device_stats *netdev_stats);
 void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s,
 			   const struct pcpu_sw_netstats __percpu *netstats);
+void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s);
 
 extern int		netdev_max_backlog;
 extern int		netdev_tstamp_prequeue;
diff --git a/net/core/dev.c b/net/core/dev.c
index bd6100da66f4..60d325bda0d7 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -10366,6 +10366,21 @@ void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s,
 }
 EXPORT_SYMBOL_GPL(dev_fetch_sw_netstats);
 
+/**
+ *	dev_get_tstats64 - ndo_get_stats64 implementation
+ *	@dev: device to get statistics from
+ *	@s: place to store stats
+ *
+ *	Populate @s from dev->stats and dev->tstats. Can be used as
+ *	ndo_get_stats64() callback.
+ */
+void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s)
+{
+	netdev_stats_to_stats64(s, &dev->stats);
+	dev_fetch_sw_netstats(s, dev->tstats);
+}
+EXPORT_SYMBOL_GPL(dev_get_tstats64);
+
 struct netdev_queue *dev_ingress_queue_create(struct net_device *dev)
 {
 	struct netdev_queue *queue = dev_ingress_queue(dev);
-- 
cgit v1.2.3


From 9a2a9ebc0a758d887ee06e067e9f7f0b36ff7574 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Tue, 10 Nov 2020 18:25:57 +0100
Subject: cpufreq: Introduce governor flags

A new cpufreq governor flag will be added subsequently, so replace
the bool dynamic_switching fleid in struct cpufreq_governor with a
flags field and introduce CPUFREQ_GOV_DYNAMIC_SWITCHING to set for
the "dynamic switching" governors instead of it.

No intentional functional impact.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
---
 drivers/cpufreq/cpufreq.c          | 2 +-
 drivers/cpufreq/cpufreq_governor.h | 2 +-
 include/linux/cpufreq.h            | 9 +++++++--
 kernel/sched/cpufreq_schedutil.c   | 2 +-
 4 files changed, 10 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 336b5e94cbc8..0252903f1b43 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -2254,7 +2254,7 @@ static int cpufreq_init_governor(struct cpufreq_policy *policy)
 		return -EINVAL;
 
 	/* Platform doesn't want dynamic frequency switching ? */
-	if (policy->governor->dynamic_switching &&
+	if (policy->governor->flags & CPUFREQ_GOV_DYNAMIC_SWITCHING &&
 	    cpufreq_driver->flags & CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING) {
 		struct cpufreq_governor *gov = cpufreq_fallback_governor();
 
diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h
index c56773c25757..bab8e6140377 100644
--- a/drivers/cpufreq/cpufreq_governor.h
+++ b/drivers/cpufreq/cpufreq_governor.h
@@ -156,7 +156,7 @@ void cpufreq_dbs_governor_limits(struct cpufreq_policy *policy);
 #define CPUFREQ_DBS_GOVERNOR_INITIALIZER(_name_)			\
 	{								\
 		.name = _name_,						\
-		.dynamic_switching = true,				\
+		.flags = CPUFREQ_GOV_DYNAMIC_SWITCHING,			\
 		.owner = THIS_MODULE,					\
 		.init = cpufreq_dbs_governor_init,			\
 		.exit = cpufreq_dbs_governor_exit,			\
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 1eaa04f1bae6..9bdfcf3c4748 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -570,12 +570,17 @@ struct cpufreq_governor {
 					 char *buf);
 	int	(*store_setspeed)	(struct cpufreq_policy *policy,
 					 unsigned int freq);
-	/* For governors which change frequency dynamically by themselves */
-	bool			dynamic_switching;
 	struct list_head	governor_list;
 	struct module		*owner;
+	u8			flags;
 };
 
+/* Governor flags */
+
+/* For governors which change frequency dynamically by themselves */
+#define CPUFREQ_GOV_DYNAMIC_SWITCHING	BIT(0)
+
+
 /* Pass a target to the cpufreq driver */
 unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy,
 					unsigned int target_freq);
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index d73bccde2720..97d318b0cd0c 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -881,7 +881,7 @@ static void sugov_limits(struct cpufreq_policy *policy)
 struct cpufreq_governor schedutil_gov = {
 	.name			= "schedutil",
 	.owner			= THIS_MODULE,
-	.dynamic_switching	= true,
+	.flags			= CPUFREQ_GOV_DYNAMIC_SWITCHING,
 	.init			= sugov_init,
 	.exit			= sugov_exit,
 	.start			= sugov_start,
-- 
cgit v1.2.3


From 218f66870181bec7aaa6e3c72f346039c590c3c2 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Tue, 10 Nov 2020 18:26:10 +0100
Subject: cpufreq: Introduce CPUFREQ_GOV_STRICT_TARGET

Introduce a new governor flag, CPUFREQ_GOV_STRICT_TARGET, for the
governors that want the target frequency to be set exactly to the
given value without leaving any room for adjustments on the hardware
side and set this flag for the powersave and performance governors.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
---
 drivers/cpufreq/cpufreq_performance.c | 1 +
 drivers/cpufreq/cpufreq_powersave.c   | 1 +
 include/linux/cpufreq.h               | 3 +++
 3 files changed, 5 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/cpufreq/cpufreq_performance.c b/drivers/cpufreq/cpufreq_performance.c
index 71c1d9aba772..addd93f2a420 100644
--- a/drivers/cpufreq/cpufreq_performance.c
+++ b/drivers/cpufreq/cpufreq_performance.c
@@ -20,6 +20,7 @@ static void cpufreq_gov_performance_limits(struct cpufreq_policy *policy)
 static struct cpufreq_governor cpufreq_gov_performance = {
 	.name		= "performance",
 	.owner		= THIS_MODULE,
+	.flags		= CPUFREQ_GOV_STRICT_TARGET,
 	.limits		= cpufreq_gov_performance_limits,
 };
 
diff --git a/drivers/cpufreq/cpufreq_powersave.c b/drivers/cpufreq/cpufreq_powersave.c
index 7749522355b5..8d830d860e91 100644
--- a/drivers/cpufreq/cpufreq_powersave.c
+++ b/drivers/cpufreq/cpufreq_powersave.c
@@ -21,6 +21,7 @@ static struct cpufreq_governor cpufreq_gov_powersave = {
 	.name		= "powersave",
 	.limits		= cpufreq_gov_powersave_limits,
 	.owner		= THIS_MODULE,
+	.flags		= CPUFREQ_GOV_STRICT_TARGET,
 };
 
 MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>");
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 9bdfcf3c4748..6eb9a3b8ec7b 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -580,6 +580,9 @@ struct cpufreq_governor {
 /* For governors which change frequency dynamically by themselves */
 #define CPUFREQ_GOV_DYNAMIC_SWITCHING	BIT(0)
 
+/* For governors wanting the target frequency to be set exactly */
+#define CPUFREQ_GOV_STRICT_TARGET	BIT(1)
+
 
 /* Pass a target to the cpufreq driver */
 unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy,
-- 
cgit v1.2.3


From ea9364bbadf11f0c55802cf11387d74f524cee84 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Tue, 10 Nov 2020 18:26:37 +0100
Subject: cpufreq: Add strict_target to struct cpufreq_policy

Add a new field to be set when the CPUFREQ_GOV_STRICT_TARGET flag is
set for the current governor to struct cpufreq_policy, so that the
drivers needing to check CPUFREQ_GOV_STRICT_TARGET do not have to
access the governor object during every frequency transition.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
---
 drivers/cpufreq/cpufreq.c | 2 ++
 include/linux/cpufreq.h   | 6 ++++++
 2 files changed, 8 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 0252903f1b43..1e7e3f2ff09f 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -2280,6 +2280,8 @@ static int cpufreq_init_governor(struct cpufreq_policy *policy)
 		}
 	}
 
+	policy->strict_target = !!(policy->governor->flags & CPUFREQ_GOV_STRICT_TARGET);
+
 	return 0;
 }
 
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 6eb9a3b8ec7b..acbad3b36322 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -109,6 +109,12 @@ struct cpufreq_policy {
 	bool			fast_switch_possible;
 	bool			fast_switch_enabled;
 
+	/*
+	 * Set if the CPUFREQ_GOV_STRICT_TARGET flag is set for the current
+	 * governor.
+	 */
+	bool			strict_target;
+
 	/*
 	 * Preferred average time interval between consecutive invocations of
 	 * the driver to set the frequency for this policy.  To be set by the
-- 
cgit v1.2.3


From a8b62fd0850503cf1e557d7e5a98d3f1f5c25eef Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 21 Sep 2020 12:58:17 +0200
Subject: stop_machine: Add function and caller debug info

Crashes in stop-machine are hard to connect to the calling code, add a
little something to help with that.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Reviewed-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Link: https://lkml.kernel.org/r/20201023102346.116513635@infradead.org
---
 include/linux/stop_machine.h |  5 +++++
 kernel/sched/core.c          |  1 +
 kernel/stop_machine.c        | 27 ++++++++++++++++++++++++---
 lib/dump_stack.c             |  2 ++
 4 files changed, 32 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h
index 76d8b09384a7..30577c3aecf8 100644
--- a/include/linux/stop_machine.h
+++ b/include/linux/stop_machine.h
@@ -24,6 +24,7 @@ typedef int (*cpu_stop_fn_t)(void *arg);
 struct cpu_stop_work {
 	struct list_head	list;		/* cpu_stopper->works */
 	cpu_stop_fn_t		fn;
+	unsigned long		caller;
 	void			*arg;
 	struct cpu_stop_done	*done;
 };
@@ -36,6 +37,8 @@ void stop_machine_park(int cpu);
 void stop_machine_unpark(int cpu);
 void stop_machine_yield(const struct cpumask *cpumask);
 
+extern void print_stop_info(const char *log_lvl, struct task_struct *task);
+
 #else	/* CONFIG_SMP */
 
 #include <linux/workqueue.h>
@@ -80,6 +83,8 @@ static inline bool stop_one_cpu_nowait(unsigned int cpu,
 	return false;
 }
 
+static inline void print_stop_info(const char *log_lvl, struct task_struct *task) { }
+
 #endif	/* CONFIG_SMP */
 
 /*
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d2003a7d5ab5..5e24104faafd 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6447,6 +6447,7 @@ void sched_show_task(struct task_struct *p)
 		(unsigned long)task_thread_info(p)->flags);
 
 	print_worker_info(KERN_INFO, p);
+	print_stop_info(KERN_INFO, p);
 	show_stack(p, NULL, KERN_INFO);
 	put_task_stack(p);
 }
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 865bb0228ab6..3cf567c2019d 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -42,11 +42,27 @@ struct cpu_stopper {
 	struct list_head	works;		/* list of pending works */
 
 	struct cpu_stop_work	stop_work;	/* for stop_cpus */
+	unsigned long		caller;
+	cpu_stop_fn_t		fn;
 };
 
 static DEFINE_PER_CPU(struct cpu_stopper, cpu_stopper);
 static bool stop_machine_initialized = false;
 
+void print_stop_info(const char *log_lvl, struct task_struct *task)
+{
+	/*
+	 * If @task is a stopper task, it cannot migrate and task_cpu() is
+	 * stable.
+	 */
+	struct cpu_stopper *stopper = per_cpu_ptr(&cpu_stopper, task_cpu(task));
+
+	if (task != stopper->thread)
+		return;
+
+	printk("%sStopper: %pS <- %pS\n", log_lvl, stopper->fn, (void *)stopper->caller);
+}
+
 /* static data for stop_cpus */
 static DEFINE_MUTEX(stop_cpus_mutex);
 static bool stop_cpus_in_progress;
@@ -123,7 +139,7 @@ static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
 int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg)
 {
 	struct cpu_stop_done done;
-	struct cpu_stop_work work = { .fn = fn, .arg = arg, .done = &done };
+	struct cpu_stop_work work = { .fn = fn, .arg = arg, .done = &done, .caller = _RET_IP_ };
 
 	cpu_stop_init_done(&done, 1);
 	if (!cpu_stop_queue_work(cpu, &work))
@@ -331,7 +347,8 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *
 	work1 = work2 = (struct cpu_stop_work){
 		.fn = multi_cpu_stop,
 		.arg = &msdata,
-		.done = &done
+		.done = &done,
+		.caller = _RET_IP_,
 	};
 
 	cpu_stop_init_done(&done, 2);
@@ -367,7 +384,7 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *
 bool stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg,
 			struct cpu_stop_work *work_buf)
 {
-	*work_buf = (struct cpu_stop_work){ .fn = fn, .arg = arg, };
+	*work_buf = (struct cpu_stop_work){ .fn = fn, .arg = arg, .caller = _RET_IP_, };
 	return cpu_stop_queue_work(cpu, work_buf);
 }
 
@@ -487,6 +504,8 @@ repeat:
 		int ret;
 
 		/* cpu stop callbacks must not sleep, make in_atomic() == T */
+		stopper->caller = work->caller;
+		stopper->fn = fn;
 		preempt_count_inc();
 		ret = fn(arg);
 		if (done) {
@@ -495,6 +514,8 @@ repeat:
 			cpu_stop_signal_done(done);
 		}
 		preempt_count_dec();
+		stopper->fn = NULL;
+		stopper->caller = 0;
 		WARN_ONCE(preempt_count(),
 			  "cpu_stop: %ps(%p) leaked preempt count\n", fn, arg);
 		goto repeat;
diff --git a/lib/dump_stack.c b/lib/dump_stack.c
index a00ee6eedc7c..f5a33b6f773f 100644
--- a/lib/dump_stack.c
+++ b/lib/dump_stack.c
@@ -12,6 +12,7 @@
 #include <linux/atomic.h>
 #include <linux/kexec.h>
 #include <linux/utsname.h>
+#include <linux/stop_machine.h>
 
 static char dump_stack_arch_desc_str[128];
 
@@ -57,6 +58,7 @@ void dump_stack_print_info(const char *log_lvl)
 		       log_lvl, dump_stack_arch_desc_str);
 
 	print_worker_info(log_lvl, current);
+	print_stop_info(log_lvl, current);
 }
 
 /**
-- 
cgit v1.2.3


From 1cf12e08bc4d50a76b80c42a3109c53d8794a0c9 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 16 Sep 2020 09:27:18 +0200
Subject: sched/hotplug: Consolidate task migration on CPU unplug

With the new mechanism which kicks tasks off the outgoing CPU at the end of
schedule() the situation on an outgoing CPU right before the stopper thread
brings it down completely is:

 - All user tasks and all unbound kernel threads have either been migrated
   away or are not running and the next wakeup will move them to a online CPU.

 - All per CPU kernel threads, except cpu hotplug thread and the stopper
   thread have either been unbound or parked by the responsible CPU hotplug
   callback.

That means that at the last step before the stopper thread is invoked the
cpu hotplug thread is the last legitimate running task on the outgoing
CPU.

Add a final wait step right before the stopper thread is kicked which
ensures that any still running tasks on the way to park or on the way to
kick themself of the CPU are either sleeping or gone.

This allows to remove the migrate_tasks() crutch in sched_cpu_dying(). If
sched_cpu_dying() detects that there is still another running task aside of
the stopper thread then it will explode with the appropriate fireworks.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Reviewed-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Link: https://lkml.kernel.org/r/20201023102346.547163969@infradead.org
---
 include/linux/cpuhotplug.h    |   1 +
 include/linux/sched/hotplug.h |   2 +
 kernel/cpu.c                  |   9 ++-
 kernel/sched/core.c           | 154 ++++++++++--------------------------------
 4 files changed, 46 insertions(+), 120 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index bc56287a1ed1..0042ef362511 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -152,6 +152,7 @@ enum cpuhp_state {
 	CPUHP_AP_ONLINE,
 	CPUHP_TEARDOWN_CPU,
 	CPUHP_AP_ONLINE_IDLE,
+	CPUHP_AP_SCHED_WAIT_EMPTY,
 	CPUHP_AP_SMPBOOT_THREADS,
 	CPUHP_AP_X86_VDSO_VMA_ONLINE,
 	CPUHP_AP_IRQ_AFFINITY_ONLINE,
diff --git a/include/linux/sched/hotplug.h b/include/linux/sched/hotplug.h
index 9a62ffdd296f..412cdaba33eb 100644
--- a/include/linux/sched/hotplug.h
+++ b/include/linux/sched/hotplug.h
@@ -11,8 +11,10 @@ extern int sched_cpu_activate(unsigned int cpu);
 extern int sched_cpu_deactivate(unsigned int cpu);
 
 #ifdef CONFIG_HOTPLUG_CPU
+extern int sched_cpu_wait_empty(unsigned int cpu);
 extern int sched_cpu_dying(unsigned int cpu);
 #else
+# define sched_cpu_wait_empty	NULL
 # define sched_cpu_dying	NULL
 #endif
 
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 6ff2578ecf17..fa535eaa4826 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1602,7 +1602,7 @@ static struct cpuhp_step cpuhp_hp_states[] = {
 		.name			= "ap:online",
 	},
 	/*
-	 * Handled on controll processor until the plugged processor manages
+	 * Handled on control processor until the plugged processor manages
 	 * this itself.
 	 */
 	[CPUHP_TEARDOWN_CPU] = {
@@ -1611,6 +1611,13 @@ static struct cpuhp_step cpuhp_hp_states[] = {
 		.teardown.single	= takedown_cpu,
 		.cant_stop		= true,
 	},
+
+	[CPUHP_AP_SCHED_WAIT_EMPTY] = {
+		.name			= "sched:waitempty",
+		.startup.single		= NULL,
+		.teardown.single	= sched_cpu_wait_empty,
+	},
+
 	/* Handle smpboot threads park/unpark */
 	[CPUHP_AP_SMPBOOT_THREADS] = {
 		.name			= "smpboot/threads:online",
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e1093c443ff9..6c89806c834b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6741,120 +6741,6 @@ void idle_task_exit(void)
 	/* finish_cpu(), as ran on the BP, will clean up the active_mm state */
 }
 
-/*
- * Since this CPU is going 'away' for a while, fold any nr_active delta
- * we might have. Assumes we're called after migrate_tasks() so that the
- * nr_active count is stable. We need to take the teardown thread which
- * is calling this into account, so we hand in adjust = 1 to the load
- * calculation.
- *
- * Also see the comment "Global load-average calculations".
- */
-static void calc_load_migrate(struct rq *rq)
-{
-	long delta = calc_load_fold_active(rq, 1);
-	if (delta)
-		atomic_long_add(delta, &calc_load_tasks);
-}
-
-static struct task_struct *__pick_migrate_task(struct rq *rq)
-{
-	const struct sched_class *class;
-	struct task_struct *next;
-
-	for_each_class(class) {
-		next = class->pick_next_task(rq);
-		if (next) {
-			next->sched_class->put_prev_task(rq, next);
-			return next;
-		}
-	}
-
-	/* The idle class should always have a runnable task */
-	BUG();
-}
-
-/*
- * Migrate all tasks from the rq, sleeping tasks will be migrated by
- * try_to_wake_up()->select_task_rq().
- *
- * Called with rq->lock held even though we'er in stop_machine() and
- * there's no concurrency possible, we hold the required locks anyway
- * because of lock validation efforts.
- */
-static void migrate_tasks(struct rq *dead_rq, struct rq_flags *rf)
-{
-	struct rq *rq = dead_rq;
-	struct task_struct *next, *stop = rq->stop;
-	struct rq_flags orf = *rf;
-	int dest_cpu;
-
-	/*
-	 * Fudge the rq selection such that the below task selection loop
-	 * doesn't get stuck on the currently eligible stop task.
-	 *
-	 * We're currently inside stop_machine() and the rq is either stuck
-	 * in the stop_machine_cpu_stop() loop, or we're executing this code,
-	 * either way we should never end up calling schedule() until we're
-	 * done here.
-	 */
-	rq->stop = NULL;
-
-	/*
-	 * put_prev_task() and pick_next_task() sched
-	 * class method both need to have an up-to-date
-	 * value of rq->clock[_task]
-	 */
-	update_rq_clock(rq);
-
-	for (;;) {
-		/*
-		 * There's this thread running, bail when that's the only
-		 * remaining thread:
-		 */
-		if (rq->nr_running == 1)
-			break;
-
-		next = __pick_migrate_task(rq);
-
-		/*
-		 * Rules for changing task_struct::cpus_mask are holding
-		 * both pi_lock and rq->lock, such that holding either
-		 * stabilizes the mask.
-		 *
-		 * Drop rq->lock is not quite as disastrous as it usually is
-		 * because !cpu_active at this point, which means load-balance
-		 * will not interfere. Also, stop-machine.
-		 */
-		rq_unlock(rq, rf);
-		raw_spin_lock(&next->pi_lock);
-		rq_relock(rq, rf);
-
-		/*
-		 * Since we're inside stop-machine, _nothing_ should have
-		 * changed the task, WARN if weird stuff happened, because in
-		 * that case the above rq->lock drop is a fail too.
-		 */
-		if (WARN_ON(task_rq(next) != rq || !task_on_rq_queued(next))) {
-			raw_spin_unlock(&next->pi_lock);
-			continue;
-		}
-
-		/* Find suitable destination for @next, with force if needed. */
-		dest_cpu = select_fallback_rq(dead_rq->cpu, next);
-		rq = __migrate_task(rq, rf, next, dest_cpu);
-		if (rq != dead_rq) {
-			rq_unlock(rq, rf);
-			rq = dead_rq;
-			*rf = orf;
-			rq_relock(rq, rf);
-		}
-		raw_spin_unlock(&next->pi_lock);
-	}
-
-	rq->stop = stop;
-}
-
 static int __balance_push_cpu_stop(void *arg)
 {
 	struct task_struct *p = arg;
@@ -7123,10 +7009,6 @@ int sched_cpu_deactivate(unsigned int cpu)
 		return ret;
 	}
 	sched_domains_numa_masks_clear(cpu);
-
-	/* Wait for all non per CPU kernel threads to vanish. */
-	balance_hotplug_wait();
-
 	return 0;
 }
 
@@ -7146,6 +7028,41 @@ int sched_cpu_starting(unsigned int cpu)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
+
+/*
+ * Invoked immediately before the stopper thread is invoked to bring the
+ * CPU down completely. At this point all per CPU kthreads except the
+ * hotplug thread (current) and the stopper thread (inactive) have been
+ * either parked or have been unbound from the outgoing CPU. Ensure that
+ * any of those which might be on the way out are gone.
+ *
+ * If after this point a bound task is being woken on this CPU then the
+ * responsible hotplug callback has failed to do it's job.
+ * sched_cpu_dying() will catch it with the appropriate fireworks.
+ */
+int sched_cpu_wait_empty(unsigned int cpu)
+{
+	balance_hotplug_wait();
+	return 0;
+}
+
+/*
+ * Since this CPU is going 'away' for a while, fold any nr_active delta we
+ * might have. Called from the CPU stopper task after ensuring that the
+ * stopper is the last running task on the CPU, so nr_active count is
+ * stable. We need to take the teardown thread which is calling this into
+ * account, so we hand in adjust = 1 to the load calculation.
+ *
+ * Also see the comment "Global load-average calculations".
+ */
+static void calc_load_migrate(struct rq *rq)
+{
+	long delta = calc_load_fold_active(rq, 1);
+
+	if (delta)
+		atomic_long_add(delta, &calc_load_tasks);
+}
+
 int sched_cpu_dying(unsigned int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
@@ -7159,7 +7076,6 @@ int sched_cpu_dying(unsigned int cpu)
 		BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
 		set_rq_offline(rq);
 	}
-	migrate_tasks(rq, &rf);
 	BUG_ON(rq->nr_running != 1);
 	rq_unlock_irqrestore(rq, &rf);
 
-- 
cgit v1.2.3


From af449901b84c98cbd84a0113223ba3bcfcb12a26 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 17 Sep 2020 10:38:30 +0200
Subject: sched: Add migrate_disable()

Add the base migrate_disable() support (under protest).

While migrate_disable() is (currently) required for PREEMPT_RT, it is
also one of the biggest flaws in the system.

Notably this is just the base implementation, it is broken vs
sched_setaffinity() and hotplug, both solved in additional patches for
ease of review.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Reviewed-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Link: https://lkml.kernel.org/r/20201023102346.818170844@infradead.org
---
 include/linux/preempt.h |  65 ++++++++++++++++++++++++++++
 include/linux/sched.h   |   3 ++
 kernel/sched/core.c     | 112 +++++++++++++++++++++++++++++++++++++++++++++---
 kernel/sched/sched.h    |   6 ++-
 lib/smp_processor_id.c  |   5 +++
 5 files changed, 183 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 7d9c1c0e149c..97ba7c920653 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -322,6 +322,69 @@ static inline void preempt_notifier_init(struct preempt_notifier *notifier,
 
 #endif
 
+#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT)
+
+/*
+ * Migrate-Disable and why it is (strongly) undesired.
+ *
+ * The premise of the Real-Time schedulers we have on Linux
+ * (SCHED_FIFO/SCHED_DEADLINE) is that M CPUs can/will run M tasks
+ * concurrently, provided there are sufficient runnable tasks, also known as
+ * work-conserving. For instance SCHED_DEADLINE tries to schedule the M
+ * earliest deadline threads, and SCHED_FIFO the M highest priority threads.
+ *
+ * The correctness of various scheduling models depends on this, but is it
+ * broken by migrate_disable() that doesn't imply preempt_disable(). Where
+ * preempt_disable() implies an immediate priority ceiling, preemptible
+ * migrate_disable() allows nesting.
+ *
+ * The worst case is that all tasks preempt one another in a migrate_disable()
+ * region and stack on a single CPU. This then reduces the available bandwidth
+ * to a single CPU. And since Real-Time schedulability theory considers the
+ * Worst-Case only, all Real-Time analysis shall revert to single-CPU
+ * (instantly solving the SMP analysis problem).
+ *
+ *
+ * The reason we have it anyway.
+ *
+ * PREEMPT_RT breaks a number of assumptions traditionally held. By forcing a
+ * number of primitives into becoming preemptible, they would also allow
+ * migration. This turns out to break a bunch of per-cpu usage. To this end,
+ * all these primitives employ migirate_disable() to restore this implicit
+ * assumption.
+ *
+ * This is a 'temporary' work-around at best. The correct solution is getting
+ * rid of the above assumptions and reworking the code to employ explicit
+ * per-cpu locking or short preempt-disable regions.
+ *
+ * The end goal must be to get rid of migrate_disable(), alternatively we need
+ * a schedulability theory that does not depend on abritrary migration.
+ *
+ *
+ * Notes on the implementation.
+ *
+ * The implementation is particularly tricky since existing code patterns
+ * dictate neither migrate_disable() nor migrate_enable() is allowed to block.
+ * This means that it cannot use cpus_read_lock() to serialize against hotplug,
+ * nor can it easily migrate itself into a pending affinity mask change on
+ * migrate_enable().
+ *
+ *
+ * Note: even non-work-conserving schedulers like semi-partitioned depends on
+ *       migration, so migrate_disable() is not only a problem for
+ *       work-conserving schedulers.
+ *
+ */
+extern void migrate_disable(void);
+extern void migrate_enable(void);
+
+#elif defined(CONFIG_PREEMPT_RT)
+
+static inline void migrate_disable(void) { }
+static inline void migrate_enable(void) { }
+
+#else /* !CONFIG_PREEMPT_RT */
+
 /**
  * migrate_disable - Prevent migration of the current task
  *
@@ -352,4 +415,6 @@ static __always_inline void migrate_enable(void)
 	preempt_enable();
 }
 
+#endif /* CONFIG_SMP && CONFIG_PREEMPT_RT */
+
 #endif /* __LINUX_PREEMPT_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 063cd120b459..0732356c0eca 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -714,6 +714,9 @@ struct task_struct {
 	int				nr_cpus_allowed;
 	const cpumask_t			*cpus_ptr;
 	cpumask_t			cpus_mask;
+#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT)
+	int				migration_disabled;
+#endif
 
 #ifdef CONFIG_PREEMPT_RCU
 	int				rcu_read_lock_nesting;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 396accb1d69c..6a3f1c2e185b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1696,6 +1696,61 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 
 #ifdef CONFIG_SMP
 
+#ifdef CONFIG_PREEMPT_RT
+
+static void
+__do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask, u32 flags);
+
+static int __set_cpus_allowed_ptr(struct task_struct *p,
+				  const struct cpumask *new_mask,
+				  u32 flags);
+
+static void migrate_disable_switch(struct rq *rq, struct task_struct *p)
+{
+	if (likely(!p->migration_disabled))
+		return;
+
+	if (p->cpus_ptr != &p->cpus_mask)
+		return;
+
+	/*
+	 * Violates locking rules! see comment in __do_set_cpus_allowed().
+	 */
+	__do_set_cpus_allowed(p, cpumask_of(rq->cpu), SCA_MIGRATE_DISABLE);
+}
+
+void migrate_disable(void)
+{
+	if (current->migration_disabled++)
+		return;
+
+	barrier();
+}
+EXPORT_SYMBOL_GPL(migrate_disable);
+
+void migrate_enable(void)
+{
+	struct task_struct *p = current;
+
+	if (--p->migration_disabled)
+		return;
+
+	barrier();
+
+	if (p->cpus_ptr == &p->cpus_mask)
+		return;
+
+	__set_cpus_allowed_ptr(p, &p->cpus_mask, SCA_MIGRATE_ENABLE);
+}
+EXPORT_SYMBOL_GPL(migrate_enable);
+
+static inline bool is_migration_disabled(struct task_struct *p)
+{
+	return p->migration_disabled;
+}
+
+#endif
+
 /*
  * Per-CPU kthreads are allowed to run on !active && online CPUs, see
  * __set_cpus_allowed_ptr() and select_fallback_rq().
@@ -1705,7 +1760,7 @@ static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
 	if (!cpumask_test_cpu(cpu, p->cpus_ptr))
 		return false;
 
-	if (is_per_cpu_kthread(p))
+	if (is_per_cpu_kthread(p) || is_migration_disabled(p))
 		return cpu_online(cpu);
 
 	return cpu_active(cpu);
@@ -1826,6 +1881,11 @@ static int migration_cpu_stop(void *data)
  */
 void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask, u32 flags)
 {
+	if (flags & (SCA_MIGRATE_ENABLE | SCA_MIGRATE_DISABLE)) {
+		p->cpus_ptr = new_mask;
+		return;
+	}
+
 	cpumask_copy(&p->cpus_mask, new_mask);
 	p->nr_cpus_allowed = cpumask_weight(new_mask);
 }
@@ -1836,7 +1896,22 @@ __do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask, u32
 	struct rq *rq = task_rq(p);
 	bool queued, running;
 
-	lockdep_assert_held(&p->pi_lock);
+	/*
+	 * This here violates the locking rules for affinity, since we're only
+	 * supposed to change these variables while holding both rq->lock and
+	 * p->pi_lock.
+	 *
+	 * HOWEVER, it magically works, because ttwu() is the only code that
+	 * accesses these variables under p->pi_lock and only does so after
+	 * smp_cond_load_acquire(&p->on_cpu, !VAL), and we're in __schedule()
+	 * before finish_task().
+	 *
+	 * XXX do further audits, this smells like something putrid.
+	 */
+	if (flags & SCA_MIGRATE_DISABLE)
+		SCHED_WARN_ON(!p->on_cpu);
+	else
+		lockdep_assert_held(&p->pi_lock);
 
 	queued = task_on_rq_queued(p);
 	running = task_current(rq, p);
@@ -1887,9 +1962,14 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 	rq = task_rq_lock(p, &rf);
 	update_rq_clock(rq);
 
-	if (p->flags & PF_KTHREAD) {
+	if (p->flags & PF_KTHREAD || is_migration_disabled(p)) {
 		/*
-		 * Kernel threads are allowed on online && !active CPUs
+		 * Kernel threads are allowed on online && !active CPUs.
+		 *
+		 * Specifically, migration_disabled() tasks must not fail the
+		 * cpumask_any_and_distribute() pick below, esp. so on
+		 * SCA_MIGRATE_ENABLE, otherwise we'll not call
+		 * set_cpus_allowed_common() and actually reset p->cpus_ptr.
 		 */
 		cpu_valid_mask = cpu_online_mask;
 	}
@@ -1903,7 +1983,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 		goto out;
 	}
 
-	if (cpumask_equal(&p->cpus_mask, new_mask))
+	if (!(flags & SCA_MIGRATE_ENABLE) && cpumask_equal(&p->cpus_mask, new_mask))
 		goto out;
 
 	/*
@@ -1995,6 +2075,8 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	 * Clearly, migrating tasks to offline CPUs is a fairly daft thing.
 	 */
 	WARN_ON_ONCE(!cpu_online(new_cpu));
+
+	WARN_ON_ONCE(is_migration_disabled(p));
 #endif
 
 	trace_sched_migrate_task(p, new_cpu);
@@ -2325,6 +2407,12 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 			}
 			fallthrough;
 		case possible:
+			/*
+			 * XXX When called from select_task_rq() we only
+			 * hold p->pi_lock and again violate locking order.
+			 *
+			 * More yuck to audit.
+			 */
 			do_set_cpus_allowed(p, cpu_possible_mask);
 			state = fail;
 			break;
@@ -2359,7 +2447,7 @@ int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags)
 {
 	lockdep_assert_held(&p->pi_lock);
 
-	if (p->nr_cpus_allowed > 1)
+	if (p->nr_cpus_allowed > 1 && !is_migration_disabled(p))
 		cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags);
 	else
 		cpu = cpumask_any(p->cpus_ptr);
@@ -2421,6 +2509,17 @@ static inline int __set_cpus_allowed_ptr(struct task_struct *p,
 
 #endif /* CONFIG_SMP */
 
+#if !defined(CONFIG_SMP) || !defined(CONFIG_PREEMPT_RT)
+
+static inline void migrate_disable_switch(struct rq *rq, struct task_struct *p) { }
+
+static inline bool is_migration_disabled(struct task_struct *p)
+{
+	return false;
+}
+
+#endif
+
 static void
 ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 {
@@ -4570,6 +4669,7 @@ static void __sched notrace __schedule(bool preempt)
 		 */
 		++*switch_count;
 
+		migrate_disable_switch(rq, prev);
 		psi_sched_switch(prev, next, !task_on_rq_queued(prev));
 
 		trace_sched_switch(preempt, prev, next);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 0420d80fb250..72d8e47cf0bb 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1902,14 +1902,16 @@ static inline bool sched_fair_runnable(struct rq *rq)
 extern struct task_struct *pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
 extern struct task_struct *pick_next_task_idle(struct rq *rq);
 
+#define SCA_CHECK		0x01
+#define SCA_MIGRATE_DISABLE	0x02
+#define SCA_MIGRATE_ENABLE	0x04
+
 #ifdef CONFIG_SMP
 
 extern void update_group_capacity(struct sched_domain *sd, int cpu);
 
 extern void trigger_load_balance(struct rq *rq);
 
-#define SCA_CHECK		0x01
-
 extern void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask, u32 flags);
 
 #endif
diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c
index 525222e4f409..faaa927ac2c8 100644
--- a/lib/smp_processor_id.c
+++ b/lib/smp_processor_id.c
@@ -26,6 +26,11 @@ unsigned int check_preemption_disabled(const char *what1, const char *what2)
 	if (current->nr_cpus_allowed == 1)
 		goto out;
 
+#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT)
+	if (current->migration_disabled)
+		goto out;
+#endif
+
 	/*
 	 * It is valid to assume CPU-locality during early bootup:
 	 */
-- 
cgit v1.2.3


From 6d337eab041d56bb8f0e7794f39906c21054c512 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 18 Sep 2020 17:24:31 +0200
Subject: sched: Fix migrate_disable() vs set_cpus_allowed_ptr()

Concurrent migrate_disable() and set_cpus_allowed_ptr() has
interesting features. We rely on set_cpus_allowed_ptr() to not return
until the task runs inside the provided mask. This expectation is
exported to userspace.

This means that any set_cpus_allowed_ptr() caller must wait until
migrate_enable() allows migrations.

At the same time, we don't want migrate_enable() to schedule, due to
patterns like:

	preempt_disable();
	migrate_disable();
	...
	migrate_enable();
	preempt_enable();

And:

	raw_spin_lock(&B);
	spin_unlock(&A);

this means that when migrate_enable() must restore the affinity
mask, it cannot wait for completion thereof. Luck will have it that
that is exactly the case where there is a pending
set_cpus_allowed_ptr(), so let that provide storage for the async stop
machine.

Much thanks to Valentin who used TLA+ most effective and found lots of
'interesting' cases.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Reviewed-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Link: https://lkml.kernel.org/r/20201023102346.921768277@infradead.org
---
 include/linux/sched.h |   1 +
 kernel/sched/core.c   | 236 +++++++++++++++++++++++++++++++++++++++++++-------
 2 files changed, 207 insertions(+), 30 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0732356c0eca..90a0c92741d7 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -714,6 +714,7 @@ struct task_struct {
 	int				nr_cpus_allowed;
 	const cpumask_t			*cpus_ptr;
 	cpumask_t			cpus_mask;
+	void				*migration_pending;
 #if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT)
 	int				migration_disabled;
 #endif
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 6a3f1c2e185b..0efc1e41bb60 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1732,15 +1732,26 @@ void migrate_enable(void)
 {
 	struct task_struct *p = current;
 
-	if (--p->migration_disabled)
+	if (p->migration_disabled > 1) {
+		p->migration_disabled--;
 		return;
+	}
 
+	/*
+	 * Ensure stop_task runs either before or after this, and that
+	 * __set_cpus_allowed_ptr(SCA_MIGRATE_ENABLE) doesn't schedule().
+	 */
+	preempt_disable();
+	if (p->cpus_ptr != &p->cpus_mask)
+		__set_cpus_allowed_ptr(p, &p->cpus_mask, SCA_MIGRATE_ENABLE);
+	/*
+	 * Mustn't clear migration_disabled() until cpus_ptr points back at the
+	 * regular cpus_mask, otherwise things that race (eg.
+	 * select_fallback_rq) get confused.
+	 */
 	barrier();
-
-	if (p->cpus_ptr == &p->cpus_mask)
-		return;
-
-	__set_cpus_allowed_ptr(p, &p->cpus_mask, SCA_MIGRATE_ENABLE);
+	p->migration_disabled = 0;
+	preempt_enable();
 }
 EXPORT_SYMBOL_GPL(migrate_enable);
 
@@ -1805,8 +1816,16 @@ static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf,
 }
 
 struct migration_arg {
-	struct task_struct *task;
-	int dest_cpu;
+	struct task_struct		*task;
+	int				dest_cpu;
+	struct set_affinity_pending	*pending;
+};
+
+struct set_affinity_pending {
+	refcount_t		refs;
+	struct completion	done;
+	struct cpu_stop_work	stop_work;
+	struct migration_arg	arg;
 };
 
 /*
@@ -1838,16 +1857,19 @@ static struct rq *__migrate_task(struct rq *rq, struct rq_flags *rf,
  */
 static int migration_cpu_stop(void *data)
 {
+	struct set_affinity_pending *pending;
 	struct migration_arg *arg = data;
 	struct task_struct *p = arg->task;
+	int dest_cpu = arg->dest_cpu;
 	struct rq *rq = this_rq();
+	bool complete = false;
 	struct rq_flags rf;
 
 	/*
 	 * The original target CPU might have gone down and we might
 	 * be on another CPU but it doesn't matter.
 	 */
-	local_irq_disable();
+	local_irq_save(rf.flags);
 	/*
 	 * We need to explicitly wake pending tasks before running
 	 * __migrate_task() such that we will not miss enforcing cpus_ptr
@@ -1857,21 +1879,83 @@ static int migration_cpu_stop(void *data)
 
 	raw_spin_lock(&p->pi_lock);
 	rq_lock(rq, &rf);
+
+	pending = p->migration_pending;
 	/*
 	 * If task_rq(p) != rq, it cannot be migrated here, because we're
 	 * holding rq->lock, if p->on_rq == 0 it cannot get enqueued because
 	 * we're holding p->pi_lock.
 	 */
 	if (task_rq(p) == rq) {
+		if (is_migration_disabled(p))
+			goto out;
+
+		if (pending) {
+			p->migration_pending = NULL;
+			complete = true;
+		}
+
+		/* migrate_enable() --  we must not race against SCA */
+		if (dest_cpu < 0) {
+			/*
+			 * When this was migrate_enable() but we no longer
+			 * have a @pending, a concurrent SCA 'fixed' things
+			 * and we should be valid again. Nothing to do.
+			 */
+			if (!pending) {
+				WARN_ON_ONCE(!is_cpu_allowed(p, cpu_of(rq)));
+				goto out;
+			}
+
+			dest_cpu = cpumask_any_distribute(&p->cpus_mask);
+		}
+
 		if (task_on_rq_queued(p))
-			rq = __migrate_task(rq, &rf, p, arg->dest_cpu);
+			rq = __migrate_task(rq, &rf, p, dest_cpu);
 		else
-			p->wake_cpu = arg->dest_cpu;
+			p->wake_cpu = dest_cpu;
+
+	} else if (dest_cpu < 0) {
+		/*
+		 * This happens when we get migrated between migrate_enable()'s
+		 * preempt_enable() and scheduling the stopper task. At that
+		 * point we're a regular task again and not current anymore.
+		 *
+		 * A !PREEMPT kernel has a giant hole here, which makes it far
+		 * more likely.
+		 */
+
+		/*
+		 * When this was migrate_enable() but we no longer have an
+		 * @pending, a concurrent SCA 'fixed' things and we should be
+		 * valid again. Nothing to do.
+		 */
+		if (!pending) {
+			WARN_ON_ONCE(!is_cpu_allowed(p, cpu_of(rq)));
+			goto out;
+		}
+
+		/*
+		 * When migrate_enable() hits a rq mis-match we can't reliably
+		 * determine is_migration_disabled() and so have to chase after
+		 * it.
+		 */
+		task_rq_unlock(rq, p, &rf);
+		stop_one_cpu_nowait(task_cpu(p), migration_cpu_stop,
+				    &pending->arg, &pending->stop_work);
+		return 0;
 	}
-	rq_unlock(rq, &rf);
-	raw_spin_unlock(&p->pi_lock);
+out:
+	task_rq_unlock(rq, p, &rf);
+
+	if (complete)
+		complete_all(&pending->done);
+
+	/* For pending->{arg,stop_work} */
+	pending = arg->pending;
+	if (pending && refcount_dec_and_test(&pending->refs))
+		wake_up_var(&pending->refs);
 
-	local_irq_enable();
 	return 0;
 }
 
@@ -1940,6 +2024,112 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 	__do_set_cpus_allowed(p, new_mask, 0);
 }
 
+/*
+ * This function is wildly self concurrent, consider at least 3 times.
+ */
+static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flags *rf,
+			    int dest_cpu, unsigned int flags)
+{
+	struct set_affinity_pending my_pending = { }, *pending = NULL;
+	struct migration_arg arg = {
+		.task = p,
+		.dest_cpu = dest_cpu,
+	};
+	bool complete = false;
+
+	/* Can the task run on the task's current CPU? If so, we're done */
+	if (cpumask_test_cpu(task_cpu(p), &p->cpus_mask)) {
+		pending = p->migration_pending;
+		if (pending) {
+			refcount_inc(&pending->refs);
+			p->migration_pending = NULL;
+			complete = true;
+		}
+		task_rq_unlock(rq, p, rf);
+
+		if (complete)
+			goto do_complete;
+
+		return 0;
+	}
+
+	if (!(flags & SCA_MIGRATE_ENABLE)) {
+		/* serialized by p->pi_lock */
+		if (!p->migration_pending) {
+			refcount_set(&my_pending.refs, 1);
+			init_completion(&my_pending.done);
+			p->migration_pending = &my_pending;
+		} else {
+			pending = p->migration_pending;
+			refcount_inc(&pending->refs);
+		}
+	}
+	pending = p->migration_pending;
+	/*
+	 * - !MIGRATE_ENABLE:
+	 *   we'll have installed a pending if there wasn't one already.
+	 *
+	 * - MIGRATE_ENABLE:
+	 *   we're here because the current CPU isn't matching anymore,
+	 *   the only way that can happen is because of a concurrent
+	 *   set_cpus_allowed_ptr() call, which should then still be
+	 *   pending completion.
+	 *
+	 * Either way, we really should have a @pending here.
+	 */
+	if (WARN_ON_ONCE(!pending)) {
+		task_rq_unlock(rq, p, rf);
+		return -EINVAL;
+	}
+
+	if (flags & SCA_MIGRATE_ENABLE) {
+
+		refcount_inc(&pending->refs); /* pending->{arg,stop_work} */
+		task_rq_unlock(rq, p, rf);
+
+		pending->arg = (struct migration_arg) {
+			.task = p,
+			.dest_cpu = -1,
+			.pending = pending,
+		};
+
+		stop_one_cpu_nowait(cpu_of(rq), migration_cpu_stop,
+				    &pending->arg, &pending->stop_work);
+
+		return 0;
+	}
+
+	if (task_running(rq, p) || p->state == TASK_WAKING) {
+
+		task_rq_unlock(rq, p, rf);
+		stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
+
+	} else {
+
+		if (!is_migration_disabled(p)) {
+			if (task_on_rq_queued(p))
+				rq = move_queued_task(rq, rf, p, dest_cpu);
+
+			p->migration_pending = NULL;
+			complete = true;
+		}
+		task_rq_unlock(rq, p, rf);
+
+do_complete:
+		if (complete)
+			complete_all(&pending->done);
+	}
+
+	wait_for_completion(&pending->done);
+
+	if (refcount_dec_and_test(&pending->refs))
+		wake_up_var(&pending->refs);
+
+	wait_var_event(&my_pending.refs, !refcount_read(&my_pending.refs));
+
+	return 0;
+}
+
 /*
  * Change a given task's CPU affinity. Migrate the thread to a
  * proper CPU and schedule it away if the CPU it's executing on
@@ -2009,23 +2199,8 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 			p->nr_cpus_allowed != 1);
 	}
 
-	/* Can the task run on the task's current CPU? If so, we're done */
-	if (cpumask_test_cpu(task_cpu(p), new_mask))
-		goto out;
+	return affine_move_task(rq, p, &rf, dest_cpu, flags);
 
-	if (task_running(rq, p) || p->state == TASK_WAKING) {
-		struct migration_arg arg = { p, dest_cpu };
-		/* Need help from migration thread: drop lock and wait. */
-		task_rq_unlock(rq, p, &rf);
-		stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
-		return 0;
-	} else if (task_on_rq_queued(p)) {
-		/*
-		 * OK, since we're going to drop the lock immediately
-		 * afterwards anyway.
-		 */
-		rq = move_queued_task(rq, &rf, p, dest_cpu);
-	}
 out:
 	task_rq_unlock(rq, p, &rf);
 
@@ -3205,6 +3380,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	init_numa_balancing(clone_flags, p);
 #ifdef CONFIG_SMP
 	p->wake_entry.u_flags = CSD_TYPE_TTWU;
+	p->migration_pending = NULL;
 #endif
 }
 
-- 
cgit v1.2.3


From 14e292f8d45380c519a83d9b0f37089a17eedcdf Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 1 Oct 2020 15:54:14 +0200
Subject: sched,rt: Use cpumask_any*_distribute()

Replace a bunch of cpumask_any*() instances with
cpumask_any*_distribute(), by injecting this little bit of random in
cpu selection, we reduce the chance two competing balance operations
working off the same lowest_mask pick the same CPU.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Reviewed-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Link: https://lkml.kernel.org/r/20201023102347.190759694@infradead.org
---
 include/linux/cpumask.h |  6 ++++++
 kernel/sched/deadline.c |  6 +++---
 kernel/sched/rt.c       |  6 +++---
 lib/cpumask.c           | 18 ++++++++++++++++++
 4 files changed, 30 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index f0d895d6ac39..383684e30f12 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -199,6 +199,11 @@ static inline int cpumask_any_and_distribute(const struct cpumask *src1p,
 	return cpumask_next_and(-1, src1p, src2p);
 }
 
+static inline int cpumask_any_distribute(const struct cpumask *srcp)
+{
+	return cpumask_first(srcp);
+}
+
 #define for_each_cpu(cpu, mask)			\
 	for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask)
 #define for_each_cpu_not(cpu, mask)		\
@@ -252,6 +257,7 @@ int cpumask_any_but(const struct cpumask *mask, unsigned int cpu);
 unsigned int cpumask_local_spread(unsigned int i, int node);
 int cpumask_any_and_distribute(const struct cpumask *src1p,
 			       const struct cpumask *src2p);
+int cpumask_any_distribute(const struct cpumask *srcp);
 
 /**
  * for_each_cpu - iterate over every cpu in a mask
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index e97c7c2708bc..206a0703fcbc 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2002,8 +2002,8 @@ static int find_later_rq(struct task_struct *task)
 				return this_cpu;
 			}
 
-			best_cpu = cpumask_first_and(later_mask,
-							sched_domain_span(sd));
+			best_cpu = cpumask_any_and_distribute(later_mask,
+							      sched_domain_span(sd));
 			/*
 			 * Last chance: if a CPU being in both later_mask
 			 * and current sd span is valid, that becomes our
@@ -2025,7 +2025,7 @@ static int find_later_rq(struct task_struct *task)
 	if (this_cpu != -1)
 		return this_cpu;
 
-	cpu = cpumask_any(later_mask);
+	cpu = cpumask_any_distribute(later_mask);
 	if (cpu < nr_cpu_ids)
 		return cpu;
 
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 40a46639f78a..2525a1beed26 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1752,8 +1752,8 @@ static int find_lowest_rq(struct task_struct *task)
 				return this_cpu;
 			}
 
-			best_cpu = cpumask_first_and(lowest_mask,
-						     sched_domain_span(sd));
+			best_cpu = cpumask_any_and_distribute(lowest_mask,
+							      sched_domain_span(sd));
 			if (best_cpu < nr_cpu_ids) {
 				rcu_read_unlock();
 				return best_cpu;
@@ -1770,7 +1770,7 @@ static int find_lowest_rq(struct task_struct *task)
 	if (this_cpu != -1)
 		return this_cpu;
 
-	cpu = cpumask_any(lowest_mask);
+	cpu = cpumask_any_distribute(lowest_mask);
 	if (cpu < nr_cpu_ids)
 		return cpu;
 
diff --git a/lib/cpumask.c b/lib/cpumask.c
index 85da6ab4fbb5..35924025097b 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -267,3 +267,21 @@ int cpumask_any_and_distribute(const struct cpumask *src1p,
 	return next;
 }
 EXPORT_SYMBOL(cpumask_any_and_distribute);
+
+int cpumask_any_distribute(const struct cpumask *srcp)
+{
+	int next, prev;
+
+	/* NOTE: our first selection will skip 0. */
+	prev = __this_cpu_read(distribute_cpu_mask_prev);
+
+	next = cpumask_next(prev, srcp);
+	if (next >= nr_cpu_ids)
+		next = cpumask_first(srcp);
+
+	if (next < nr_cpu_ids)
+		__this_cpu_write(distribute_cpu_mask_prev, next);
+
+	return next;
+}
+EXPORT_SYMBOL(cpumask_any_distribute);
-- 
cgit v1.2.3


From a7c81556ec4d341dfdbf2cc478ead89d73e474a7 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 28 Sep 2020 17:06:07 +0200
Subject: sched: Fix migrate_disable() vs rt/dl balancing

In order to minimize the interference of migrate_disable() on lower
priority tasks, which can be deprived of runtime due to being stuck
below a higher priority task. Teach the RT/DL balancers to push away
these higher priority tasks when a lower priority task gets selected
to run on a freshly demoted CPU (pull).

This adds migration interference to the higher priority task, but
restores bandwidth to system that would otherwise be irrevocably lost.
Without this it would be possible to have all tasks on the system
stuck on a single CPU, each task preempted in a migrate_disable()
section with a single high priority task running.

This way we can still approximate running the M highest priority tasks
on the system.

Migrating the top task away is (ofcourse) still subject to
migrate_disable() too, which means the lower task is subject to an
interference equivalent to the worst case migrate_disable() section.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Link: https://lkml.kernel.org/r/20201023102347.499155098@infradead.org
---
 include/linux/preempt.h | 40 ++++++++++++++++-------------
 include/linux/sched.h   |  3 ++-
 kernel/sched/core.c     | 67 +++++++++++++++++++++++++++++++++++++++++--------
 kernel/sched/deadline.c | 29 +++++++++++++++------
 kernel/sched/rt.c       | 63 +++++++++++++++++++++++++++++++++++++---------
 kernel/sched/sched.h    | 32 +++++++++++++++++++++++
 6 files changed, 186 insertions(+), 48 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 97ba7c920653..8b43922e65df 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -325,24 +325,28 @@ static inline void preempt_notifier_init(struct preempt_notifier *notifier,
 #if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT)
 
 /*
- * Migrate-Disable and why it is (strongly) undesired.
- *
- * The premise of the Real-Time schedulers we have on Linux
- * (SCHED_FIFO/SCHED_DEADLINE) is that M CPUs can/will run M tasks
- * concurrently, provided there are sufficient runnable tasks, also known as
- * work-conserving. For instance SCHED_DEADLINE tries to schedule the M
- * earliest deadline threads, and SCHED_FIFO the M highest priority threads.
- *
- * The correctness of various scheduling models depends on this, but is it
- * broken by migrate_disable() that doesn't imply preempt_disable(). Where
- * preempt_disable() implies an immediate priority ceiling, preemptible
- * migrate_disable() allows nesting.
- *
- * The worst case is that all tasks preempt one another in a migrate_disable()
- * region and stack on a single CPU. This then reduces the available bandwidth
- * to a single CPU. And since Real-Time schedulability theory considers the
- * Worst-Case only, all Real-Time analysis shall revert to single-CPU
- * (instantly solving the SMP analysis problem).
+ * Migrate-Disable and why it is undesired.
+ *
+ * When a preempted task becomes elegible to run under the ideal model (IOW it
+ * becomes one of the M highest priority tasks), it might still have to wait
+ * for the preemptee's migrate_disable() section to complete. Thereby suffering
+ * a reduction in bandwidth in the exact duration of the migrate_disable()
+ * section.
+ *
+ * Per this argument, the change from preempt_disable() to migrate_disable()
+ * gets us:
+ *
+ * - a higher priority tasks gains reduced wake-up latency; with preempt_disable()
+ *   it would have had to wait for the lower priority task.
+ *
+ * - a lower priority tasks; which under preempt_disable() could've instantly
+ *   migrated away when another CPU becomes available, is now constrained
+ *   by the ability to push the higher priority task away, which might itself be
+ *   in a migrate_disable() section, reducing it's available bandwidth.
+ *
+ * IOW it trades latency / moves the interference term, but it stays in the
+ * system, and as long as it remains unbounded, the system is not fully
+ * deterministic.
  *
  *
  * The reason we have it anyway.
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 90a0c92741d7..3af9d52fe093 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -716,8 +716,9 @@ struct task_struct {
 	cpumask_t			cpus_mask;
 	void				*migration_pending;
 #if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT)
-	int				migration_disabled;
+	unsigned short			migration_disabled;
 #endif
+	unsigned short			migration_flags;
 
 #ifdef CONFIG_PREEMPT_RCU
 	int				rcu_read_lock_nesting;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9ce2fc7d3d51..e92d7853057c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1763,11 +1763,6 @@ void migrate_enable(void)
 }
 EXPORT_SYMBOL_GPL(migrate_enable);
 
-static inline bool is_migration_disabled(struct task_struct *p)
-{
-	return p->migration_disabled;
-}
-
 static inline bool rq_has_pinned_tasks(struct rq *rq)
 {
 	return rq->nr_pinned;
@@ -1972,6 +1967,49 @@ out:
 	return 0;
 }
 
+int push_cpu_stop(void *arg)
+{
+	struct rq *lowest_rq = NULL, *rq = this_rq();
+	struct task_struct *p = arg;
+
+	raw_spin_lock_irq(&p->pi_lock);
+	raw_spin_lock(&rq->lock);
+
+	if (task_rq(p) != rq)
+		goto out_unlock;
+
+	if (is_migration_disabled(p)) {
+		p->migration_flags |= MDF_PUSH;
+		goto out_unlock;
+	}
+
+	p->migration_flags &= ~MDF_PUSH;
+
+	if (p->sched_class->find_lock_rq)
+		lowest_rq = p->sched_class->find_lock_rq(p, rq);
+
+	if (!lowest_rq)
+		goto out_unlock;
+
+	// XXX validate p is still the highest prio task
+	if (task_rq(p) == rq) {
+		deactivate_task(rq, p, 0);
+		set_task_cpu(p, lowest_rq->cpu);
+		activate_task(lowest_rq, p, 0);
+		resched_curr(lowest_rq);
+	}
+
+	double_unlock_balance(rq, lowest_rq);
+
+out_unlock:
+	rq->push_busy = false;
+	raw_spin_unlock(&rq->lock);
+	raw_spin_unlock_irq(&p->pi_lock);
+
+	put_task_struct(p);
+	return 0;
+}
+
 /*
  * sched_class::set_cpus_allowed must do the below, but is not required to
  * actually call this function.
@@ -2052,6 +2090,14 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag
 
 	/* Can the task run on the task's current CPU? If so, we're done */
 	if (cpumask_test_cpu(task_cpu(p), &p->cpus_mask)) {
+		struct task_struct *push_task = NULL;
+
+		if ((flags & SCA_MIGRATE_ENABLE) &&
+		    (p->migration_flags & MDF_PUSH) && !rq->push_busy) {
+			rq->push_busy = true;
+			push_task = get_task_struct(p);
+		}
+
 		pending = p->migration_pending;
 		if (pending) {
 			refcount_inc(&pending->refs);
@@ -2060,6 +2106,11 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag
 		}
 		task_rq_unlock(rq, p, rf);
 
+		if (push_task) {
+			stop_one_cpu_nowait(rq->cpu, push_cpu_stop,
+					    p, &rq->push_work);
+		}
+
 		if (complete)
 			goto do_complete;
 
@@ -2098,6 +2149,7 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag
 	if (flags & SCA_MIGRATE_ENABLE) {
 
 		refcount_inc(&pending->refs); /* pending->{arg,stop_work} */
+		p->migration_flags &= ~MDF_PUSH;
 		task_rq_unlock(rq, p, rf);
 
 		pending->arg = (struct migration_arg) {
@@ -2716,11 +2768,6 @@ static inline int __set_cpus_allowed_ptr(struct task_struct *p,
 
 static inline void migrate_disable_switch(struct rq *rq, struct task_struct *p) { }
 
-static inline bool is_migration_disabled(struct task_struct *p)
-{
-	return false;
-}
-
 static inline bool rq_has_pinned_tasks(struct rq *rq)
 {
 	return false;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 3d3fd8370447..eed2e449b313 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2129,6 +2129,9 @@ static int push_dl_task(struct rq *rq)
 		return 0;
 
 retry:
+	if (is_migration_disabled(next_task))
+		return 0;
+
 	if (WARN_ON(next_task == rq->curr))
 		return 0;
 
@@ -2206,7 +2209,7 @@ static void push_dl_tasks(struct rq *rq)
 static void pull_dl_task(struct rq *this_rq)
 {
 	int this_cpu = this_rq->cpu, cpu;
-	struct task_struct *p;
+	struct task_struct *p, *push_task;
 	bool resched = false;
 	struct rq *src_rq;
 	u64 dmin = LONG_MAX;
@@ -2236,6 +2239,7 @@ static void pull_dl_task(struct rq *this_rq)
 			continue;
 
 		/* Might drop this_rq->lock */
+		push_task = NULL;
 		double_lock_balance(this_rq, src_rq);
 
 		/*
@@ -2267,17 +2271,27 @@ static void pull_dl_task(struct rq *this_rq)
 					   src_rq->curr->dl.deadline))
 				goto skip;
 
-			resched = true;
-
-			deactivate_task(src_rq, p, 0);
-			set_task_cpu(p, this_cpu);
-			activate_task(this_rq, p, 0);
-			dmin = p->dl.deadline;
+			if (is_migration_disabled(p)) {
+				push_task = get_push_task(src_rq);
+			} else {
+				deactivate_task(src_rq, p, 0);
+				set_task_cpu(p, this_cpu);
+				activate_task(this_rq, p, 0);
+				dmin = p->dl.deadline;
+				resched = true;
+			}
 
 			/* Is there any other task even earlier? */
 		}
 skip:
 		double_unlock_balance(this_rq, src_rq);
+
+		if (push_task) {
+			raw_spin_unlock(&this_rq->lock);
+			stop_one_cpu_nowait(src_rq->cpu, push_cpu_stop,
+					    push_task, &src_rq->push_work);
+			raw_spin_lock(&this_rq->lock);
+		}
 	}
 
 	if (resched)
@@ -2524,6 +2538,7 @@ const struct sched_class dl_sched_class
 	.rq_online              = rq_online_dl,
 	.rq_offline             = rq_offline_dl,
 	.task_woken		= task_woken_dl,
+	.find_lock_rq		= find_lock_later_rq,
 #endif
 
 	.task_tick		= task_tick_dl,
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index cf63346a07e4..c592e47cafed 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1859,7 +1859,7 @@ static struct task_struct *pick_next_pushable_task(struct rq *rq)
  * running task can migrate over to a CPU that is running a task
  * of lesser priority.
  */
-static int push_rt_task(struct rq *rq)
+static int push_rt_task(struct rq *rq, bool pull)
 {
 	struct task_struct *next_task;
 	struct rq *lowest_rq;
@@ -1873,6 +1873,34 @@ static int push_rt_task(struct rq *rq)
 		return 0;
 
 retry:
+	if (is_migration_disabled(next_task)) {
+		struct task_struct *push_task = NULL;
+		int cpu;
+
+		if (!pull || rq->push_busy)
+			return 0;
+
+		cpu = find_lowest_rq(rq->curr);
+		if (cpu == -1 || cpu == rq->cpu)
+			return 0;
+
+		/*
+		 * Given we found a CPU with lower priority than @next_task,
+		 * therefore it should be running. However we cannot migrate it
+		 * to this other CPU, instead attempt to push the current
+		 * running task on this CPU away.
+		 */
+		push_task = get_push_task(rq);
+		if (push_task) {
+			raw_spin_unlock(&rq->lock);
+			stop_one_cpu_nowait(rq->cpu, push_cpu_stop,
+					    push_task, &rq->push_work);
+			raw_spin_lock(&rq->lock);
+		}
+
+		return 0;
+	}
+
 	if (WARN_ON(next_task == rq->curr))
 		return 0;
 
@@ -1927,12 +1955,10 @@ retry:
 	deactivate_task(rq, next_task, 0);
 	set_task_cpu(next_task, lowest_rq->cpu);
 	activate_task(lowest_rq, next_task, 0);
-	ret = 1;
-
 	resched_curr(lowest_rq);
+	ret = 1;
 
 	double_unlock_balance(rq, lowest_rq);
-
 out:
 	put_task_struct(next_task);
 
@@ -1942,7 +1968,7 @@ out:
 static void push_rt_tasks(struct rq *rq)
 {
 	/* push_rt_task will return true if it moved an RT */
-	while (push_rt_task(rq))
+	while (push_rt_task(rq, false))
 		;
 }
 
@@ -2095,7 +2121,8 @@ void rto_push_irq_work_func(struct irq_work *work)
 	 */
 	if (has_pushable_tasks(rq)) {
 		raw_spin_lock(&rq->lock);
-		push_rt_tasks(rq);
+		while (push_rt_task(rq, true))
+			;
 		raw_spin_unlock(&rq->lock);
 	}
 
@@ -2120,7 +2147,7 @@ static void pull_rt_task(struct rq *this_rq)
 {
 	int this_cpu = this_rq->cpu, cpu;
 	bool resched = false;
-	struct task_struct *p;
+	struct task_struct *p, *push_task;
 	struct rq *src_rq;
 	int rt_overload_count = rt_overloaded(this_rq);
 
@@ -2167,6 +2194,7 @@ static void pull_rt_task(struct rq *this_rq)
 		 * double_lock_balance, and another CPU could
 		 * alter this_rq
 		 */
+		push_task = NULL;
 		double_lock_balance(this_rq, src_rq);
 
 		/*
@@ -2194,11 +2222,14 @@ static void pull_rt_task(struct rq *this_rq)
 			if (p->prio < src_rq->curr->prio)
 				goto skip;
 
-			resched = true;
-
-			deactivate_task(src_rq, p, 0);
-			set_task_cpu(p, this_cpu);
-			activate_task(this_rq, p, 0);
+			if (is_migration_disabled(p)) {
+				push_task = get_push_task(src_rq);
+			} else {
+				deactivate_task(src_rq, p, 0);
+				set_task_cpu(p, this_cpu);
+				activate_task(this_rq, p, 0);
+				resched = true;
+			}
 			/*
 			 * We continue with the search, just in
 			 * case there's an even higher prio task
@@ -2208,6 +2239,13 @@ static void pull_rt_task(struct rq *this_rq)
 		}
 skip:
 		double_unlock_balance(this_rq, src_rq);
+
+		if (push_task) {
+			raw_spin_unlock(&this_rq->lock);
+			stop_one_cpu_nowait(src_rq->cpu, push_cpu_stop,
+					    push_task, &src_rq->push_work);
+			raw_spin_lock(&this_rq->lock);
+		}
 	}
 
 	if (resched)
@@ -2449,6 +2487,7 @@ const struct sched_class rt_sched_class
 	.rq_offline             = rq_offline_rt,
 	.task_woken		= task_woken_rt,
 	.switched_from		= switched_from_rt,
+	.find_lock_rq		= find_lock_lowest_rq,
 #endif
 
 	.task_tick		= task_tick_rt,
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 42de1406c0dc..56992aaca48e 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1057,6 +1057,8 @@ struct rq {
 #if defined(CONFIG_PREEMPT_RT) && defined(CONFIG_SMP)
 	unsigned int		nr_pinned;
 #endif
+	unsigned int		push_busy;
+	struct cpu_stop_work	push_work;
 };
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -1084,6 +1086,16 @@ static inline int cpu_of(struct rq *rq)
 #endif
 }
 
+#define MDF_PUSH	0x01
+
+static inline bool is_migration_disabled(struct task_struct *p)
+{
+#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT)
+	return p->migration_disabled;
+#else
+	return false;
+#endif
+}
 
 #ifdef CONFIG_SCHED_SMT
 extern void __update_idle_core(struct rq *rq);
@@ -1823,6 +1835,8 @@ struct sched_class {
 
 	void (*rq_online)(struct rq *rq);
 	void (*rq_offline)(struct rq *rq);
+
+	struct rq *(*find_lock_rq)(struct task_struct *p, struct rq *rq);
 #endif
 
 	void (*task_tick)(struct rq *rq, struct task_struct *p, int queued);
@@ -1918,6 +1932,24 @@ extern void trigger_load_balance(struct rq *rq);
 
 extern void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask, u32 flags);
 
+static inline struct task_struct *get_push_task(struct rq *rq)
+{
+	struct task_struct *p = rq->curr;
+
+	lockdep_assert_held(&rq->lock);
+
+	if (rq->push_busy)
+		return NULL;
+
+	if (p->nr_cpus_allowed == 1)
+		return NULL;
+
+	rq->push_busy = true;
+	return get_task_struct(p);
+}
+
+extern int push_cpu_stop(void *arg);
+
 #endif
 
 #ifdef CONFIG_CPU_IDLE
-- 
cgit v1.2.3


From c250d50fe2ce627ca9805d9c8ac11cbbf922a4a6 Mon Sep 17 00:00:00 2001
From: Lukasz Luba <lukasz.luba@arm.com>
Date: Thu, 5 Nov 2020 12:50:01 +0000
Subject: PM: EM: Add a flag indicating units of power values in Energy Model

There are different platforms and devices which might use different scale
for the power values. Kernel sub-systems might need to check if all
Energy Model (EM) devices are using the same scale. Address that issue and
store the information inside EM for each device. Thanks to that they can
be easily compared and proper action triggered.

Suggested-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Reviewed-by: Quentin Perret <qperret@google.com>
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/scmi-cpufreq.c |  3 ++-
 drivers/opp/of.c               |  2 +-
 include/linux/energy_model.h   |  9 +++++++--
 kernel/power/energy_model.c    | 24 +++++++++++++++++++++++-
 4 files changed, 33 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c
index e855e8612a67..3714a4cd07fa 100644
--- a/drivers/cpufreq/scmi-cpufreq.c
+++ b/drivers/cpufreq/scmi-cpufreq.c
@@ -188,7 +188,8 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy)
 	policy->fast_switch_possible =
 		handle->perf_ops->fast_switch_possible(handle, cpu_dev);
 
-	em_dev_register_perf_domain(cpu_dev, nr_opp, &em_cb, policy->cpus);
+	em_dev_register_perf_domain(cpu_dev, nr_opp, &em_cb, policy->cpus,
+				    false);
 
 	return 0;
 
diff --git a/drivers/opp/of.c b/drivers/opp/of.c
index 9faeb83e4b32..16f39e2127a5 100644
--- a/drivers/opp/of.c
+++ b/drivers/opp/of.c
@@ -1335,7 +1335,7 @@ int dev_pm_opp_of_register_em(struct device *dev, struct cpumask *cpus)
 		goto failed;
 	}
 
-	ret = em_dev_register_perf_domain(dev, nr_opp, &em_cb, cpus);
+	ret = em_dev_register_perf_domain(dev, nr_opp, &em_cb, cpus, true);
 	if (ret)
 		goto failed;
 
diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h
index b67a51c574b9..3a33c738d876 100644
--- a/include/linux/energy_model.h
+++ b/include/linux/energy_model.h
@@ -29,6 +29,8 @@ struct em_perf_state {
  * em_perf_domain - Performance domain
  * @table:		List of performance states, in ascending order
  * @nr_perf_states:	Number of performance states
+ * @milliwatts:		Flag indicating the power values are in milli-Watts
+ *			or some other scale.
  * @cpus:		Cpumask covering the CPUs of the domain. It's here
  *			for performance reasons to avoid potential cache
  *			misses during energy calculations in the scheduler
@@ -43,6 +45,7 @@ struct em_perf_state {
 struct em_perf_domain {
 	struct em_perf_state *table;
 	int nr_perf_states;
+	int milliwatts;
 	unsigned long cpus[];
 };
 
@@ -79,7 +82,8 @@ struct em_data_callback {
 struct em_perf_domain *em_cpu_get(int cpu);
 struct em_perf_domain *em_pd_get(struct device *dev);
 int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
-				struct em_data_callback *cb, cpumask_t *span);
+				struct em_data_callback *cb, cpumask_t *span,
+				bool milliwatts);
 void em_dev_unregister_perf_domain(struct device *dev);
 
 /**
@@ -186,7 +190,8 @@ struct em_data_callback {};
 
 static inline
 int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
-				struct em_data_callback *cb, cpumask_t *span)
+				struct em_data_callback *cb, cpumask_t *span,
+				bool milliwatts)
 {
 	return -EINVAL;
 }
diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c
index c1ff7fa030ab..efe2a595988e 100644
--- a/kernel/power/energy_model.c
+++ b/kernel/power/energy_model.c
@@ -52,6 +52,17 @@ static int em_debug_cpus_show(struct seq_file *s, void *unused)
 }
 DEFINE_SHOW_ATTRIBUTE(em_debug_cpus);
 
+static int em_debug_units_show(struct seq_file *s, void *unused)
+{
+	struct em_perf_domain *pd = s->private;
+	char *units = pd->milliwatts ? "milliWatts" : "bogoWatts";
+
+	seq_printf(s, "%s\n", units);
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(em_debug_units);
+
 static void em_debug_create_pd(struct device *dev)
 {
 	struct dentry *d;
@@ -64,6 +75,8 @@ static void em_debug_create_pd(struct device *dev)
 		debugfs_create_file("cpus", 0444, d, dev->em_pd->cpus,
 				    &em_debug_cpus_fops);
 
+	debugfs_create_file("units", 0444, d, dev->em_pd, &em_debug_units_fops);
+
 	/* Create a sub-directory for each performance state */
 	for (i = 0; i < dev->em_pd->nr_perf_states; i++)
 		em_debug_create_ps(&dev->em_pd->table[i], d);
@@ -250,17 +263,24 @@ EXPORT_SYMBOL_GPL(em_cpu_get);
  * @cpus	: Pointer to cpumask_t, which in case of a CPU device is
  *		obligatory. It can be taken from i.e. 'policy->cpus'. For other
  *		type of devices this should be set to NULL.
+ * @milliwatts	: Flag indicating that the power values are in milliWatts or
+ *		in some other scale. It must be set properly.
  *
  * Create Energy Model tables for a performance domain using the callbacks
  * defined in cb.
  *
+ * The @milliwatts is important to set with correct value. Some kernel
+ * sub-systems might rely on this flag and check if all devices in the EM are
+ * using the same scale.
+ *
  * If multiple clients register the same performance domain, all but the first
  * registration will be ignored.
  *
  * Return 0 on success
  */
 int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
-				struct em_data_callback *cb, cpumask_t *cpus)
+				struct em_data_callback *cb, cpumask_t *cpus,
+				bool milliwatts)
 {
 	unsigned long cap, prev_cap = 0;
 	int cpu, ret;
@@ -313,6 +333,8 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
 	if (ret)
 		goto unlock;
 
+	dev->em_pd->milliwatts = milliwatts;
+
 	em_debug_create_pd(dev);
 	dev_info(dev, "EM: created perf domain\n");
 
-- 
cgit v1.2.3


From f2c90b12e700fff6a0b5a1c32f446f05f9d0890c Mon Sep 17 00:00:00 2001
From: Lukasz Luba <lukasz.luba@arm.com>
Date: Tue, 3 Nov 2020 09:05:59 +0000
Subject: PM: EM: update the comments related to power scale

The Energy Model supports power values expressed in milli-Watts or in an
'abstract scale'. Update the related comments is the code to reflect that
state.

Reviewed-by: Quentin Perret <qperret@google.com>
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/energy_model.h | 11 +++++------
 kernel/power/energy_model.c  |  2 +-
 2 files changed, 6 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h
index 3a33c738d876..9618c0a46ef4 100644
--- a/include/linux/energy_model.h
+++ b/include/linux/energy_model.h
@@ -13,9 +13,8 @@
 /**
  * em_perf_state - Performance state of a performance domain
  * @frequency:	The frequency in KHz, for consistency with CPUFreq
- * @power:	The power consumed at this level, in milli-watts (by 1 CPU or
-		by a registered device). It can be a total power: static and
-		dynamic.
+ * @power:	The power consumed at this level (by 1 CPU or by a registered
+ *		device). It can be a total power: static and dynamic.
  * @cost:	The cost coefficient associated with this level, used during
  *		energy calculation. Equal to: power * max_frequency / frequency
  */
@@ -58,7 +57,7 @@ struct em_data_callback {
 	/**
 	 * active_power() - Provide power at the next performance state of
 	 *		a device
-	 * @power	: Active power at the performance state in mW
+	 * @power	: Active power at the performance state
 	 *		(modified)
 	 * @freq	: Frequency at the performance state in kHz
 	 *		(modified)
@@ -69,8 +68,8 @@ struct em_data_callback {
 	 * and frequency.
 	 *
 	 * In case of CPUs, the power is the one of a single CPU in the domain,
-	 * expressed in milli-watts. It is expected to fit in the
-	 * [0, EM_MAX_POWER] range.
+	 * expressed in milli-Watts or an abstract scale. It is expected to
+	 * fit in the [0, EM_MAX_POWER] range.
 	 *
 	 * Return 0 on success.
 	 */
diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c
index efe2a595988e..1358fa4abfa8 100644
--- a/kernel/power/energy_model.c
+++ b/kernel/power/energy_model.c
@@ -143,7 +143,7 @@ static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd,
 
 		/*
 		 * The power returned by active_state() is expected to be
-		 * positive, in milli-watts and to fit into 16 bits.
+		 * positive and to fit into 16 bits.
 		 */
 		if (!power || power > EM_MAX_POWER) {
 			dev_err(dev, "EM: invalid power: %lu\n",
-- 
cgit v1.2.3


From fc51989062138744b56e47190915ce68484e73f3 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Tue, 3 Nov 2020 16:06:25 +0100
Subject: PM: domains: Rename pm_genpd_syscore_poweroff|poweron()

To better describe what the pm_genpd_syscore_poweroff|poweron() functions
actually do, let's rename them to dev_pm_genpd_suspend|resume() and update
the rather few callers of them accordingly (a couple of clocksource
drivers).

Moreover, let's take the opportunity to add some documentation of these
exported functions, as that is currently missing.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c   | 35 +++++++++++++++++++++--------------
 drivers/clocksource/sh_cmt.c  |  8 ++++----
 drivers/clocksource/sh_mtu2.c |  4 ++--
 drivers/clocksource/sh_tmu.c  |  8 ++++----
 include/linux/pm_domain.h     |  8 ++++----
 5 files changed, 35 insertions(+), 28 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 743268996336..9b4881b67683 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -1363,14 +1363,7 @@ static void genpd_complete(struct device *dev)
 	genpd_unlock(genpd);
 }
 
-/**
- * genpd_syscore_switch - Switch power during system core suspend or resume.
- * @dev: Device that normally is marked as "always on" to switch power for.
- *
- * This routine may only be called during the system core (syscore) suspend or
- * resume phase for devices whose "always on" flags are set.
- */
-static void genpd_syscore_switch(struct device *dev, bool suspend)
+static void genpd_switch_state(struct device *dev, bool suspend)
 {
 	struct generic_pm_domain *genpd;
 
@@ -1387,17 +1380,31 @@ static void genpd_syscore_switch(struct device *dev, bool suspend)
 	}
 }
 
-void pm_genpd_syscore_poweroff(struct device *dev)
+/**
+ * dev_pm_genpd_suspend - Synchronously try to suspend the genpd for @dev
+ * @dev: The device that is attached to the genpd, that can be suspended.
+ *
+ * This routine should typically be called for a device that needs to be
+ * suspended during the syscore suspend phase.
+ */
+void dev_pm_genpd_suspend(struct device *dev)
 {
-	genpd_syscore_switch(dev, true);
+	genpd_switch_state(dev, true);
 }
-EXPORT_SYMBOL_GPL(pm_genpd_syscore_poweroff);
+EXPORT_SYMBOL_GPL(dev_pm_genpd_suspend);
 
-void pm_genpd_syscore_poweron(struct device *dev)
+/**
+ * dev_pm_genpd_resume - Synchronously try to resume the genpd for @dev
+ * @dev: The device that is attached to the genpd, which needs to be resumed.
+ *
+ * This routine should typically be called for a device that needs to be resumed
+ * during the syscore resume phase.
+ */
+void dev_pm_genpd_resume(struct device *dev)
 {
-	genpd_syscore_switch(dev, false);
+	genpd_switch_state(dev, false);
 }
-EXPORT_SYMBOL_GPL(pm_genpd_syscore_poweron);
+EXPORT_SYMBOL_GPL(dev_pm_genpd_resume);
 
 #else /* !CONFIG_PM_SLEEP */
 
diff --git a/drivers/clocksource/sh_cmt.c b/drivers/clocksource/sh_cmt.c
index 760777458a90..7275d95de435 100644
--- a/drivers/clocksource/sh_cmt.c
+++ b/drivers/clocksource/sh_cmt.c
@@ -658,7 +658,7 @@ static void sh_cmt_clocksource_suspend(struct clocksource *cs)
 		return;
 
 	sh_cmt_stop(ch, FLAG_CLOCKSOURCE);
-	pm_genpd_syscore_poweroff(&ch->cmt->pdev->dev);
+	dev_pm_genpd_suspend(&ch->cmt->pdev->dev);
 }
 
 static void sh_cmt_clocksource_resume(struct clocksource *cs)
@@ -668,7 +668,7 @@ static void sh_cmt_clocksource_resume(struct clocksource *cs)
 	if (!ch->cs_enabled)
 		return;
 
-	pm_genpd_syscore_poweron(&ch->cmt->pdev->dev);
+	dev_pm_genpd_resume(&ch->cmt->pdev->dev);
 	sh_cmt_start(ch, FLAG_CLOCKSOURCE);
 }
 
@@ -760,7 +760,7 @@ static void sh_cmt_clock_event_suspend(struct clock_event_device *ced)
 {
 	struct sh_cmt_channel *ch = ced_to_sh_cmt(ced);
 
-	pm_genpd_syscore_poweroff(&ch->cmt->pdev->dev);
+	dev_pm_genpd_suspend(&ch->cmt->pdev->dev);
 	clk_unprepare(ch->cmt->clk);
 }
 
@@ -769,7 +769,7 @@ static void sh_cmt_clock_event_resume(struct clock_event_device *ced)
 	struct sh_cmt_channel *ch = ced_to_sh_cmt(ced);
 
 	clk_prepare(ch->cmt->clk);
-	pm_genpd_syscore_poweron(&ch->cmt->pdev->dev);
+	dev_pm_genpd_resume(&ch->cmt->pdev->dev);
 }
 
 static int sh_cmt_register_clockevent(struct sh_cmt_channel *ch,
diff --git a/drivers/clocksource/sh_mtu2.c b/drivers/clocksource/sh_mtu2.c
index bfccb31e94ad..169a1fccc497 100644
--- a/drivers/clocksource/sh_mtu2.c
+++ b/drivers/clocksource/sh_mtu2.c
@@ -297,12 +297,12 @@ static int sh_mtu2_clock_event_set_periodic(struct clock_event_device *ced)
 
 static void sh_mtu2_clock_event_suspend(struct clock_event_device *ced)
 {
-	pm_genpd_syscore_poweroff(&ced_to_sh_mtu2(ced)->mtu->pdev->dev);
+	dev_pm_genpd_suspend(&ced_to_sh_mtu2(ced)->mtu->pdev->dev);
 }
 
 static void sh_mtu2_clock_event_resume(struct clock_event_device *ced)
 {
-	pm_genpd_syscore_poweron(&ced_to_sh_mtu2(ced)->mtu->pdev->dev);
+	dev_pm_genpd_resume(&ced_to_sh_mtu2(ced)->mtu->pdev->dev);
 }
 
 static void sh_mtu2_register_clockevent(struct sh_mtu2_channel *ch,
diff --git a/drivers/clocksource/sh_tmu.c b/drivers/clocksource/sh_tmu.c
index d41df9ba3725..b00dec0655cb 100644
--- a/drivers/clocksource/sh_tmu.c
+++ b/drivers/clocksource/sh_tmu.c
@@ -292,7 +292,7 @@ static void sh_tmu_clocksource_suspend(struct clocksource *cs)
 
 	if (--ch->enable_count == 0) {
 		__sh_tmu_disable(ch);
-		pm_genpd_syscore_poweroff(&ch->tmu->pdev->dev);
+		dev_pm_genpd_suspend(&ch->tmu->pdev->dev);
 	}
 }
 
@@ -304,7 +304,7 @@ static void sh_tmu_clocksource_resume(struct clocksource *cs)
 		return;
 
 	if (ch->enable_count++ == 0) {
-		pm_genpd_syscore_poweron(&ch->tmu->pdev->dev);
+		dev_pm_genpd_resume(&ch->tmu->pdev->dev);
 		__sh_tmu_enable(ch);
 	}
 }
@@ -394,12 +394,12 @@ static int sh_tmu_clock_event_next(unsigned long delta,
 
 static void sh_tmu_clock_event_suspend(struct clock_event_device *ced)
 {
-	pm_genpd_syscore_poweroff(&ced_to_sh_tmu(ced)->tmu->pdev->dev);
+	dev_pm_genpd_suspend(&ced_to_sh_tmu(ced)->tmu->pdev->dev);
 }
 
 static void sh_tmu_clock_event_resume(struct clock_event_device *ced)
 {
-	pm_genpd_syscore_poweron(&ced_to_sh_tmu(ced)->tmu->pdev->dev);
+	dev_pm_genpd_resume(&ced_to_sh_tmu(ced)->tmu->pdev->dev);
 }
 
 static void sh_tmu_register_clockevent(struct sh_tmu_channel *ch,
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 1ad0ec481416..a8f93328daec 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -280,11 +280,11 @@ static inline int dev_pm_genpd_remove_notifier(struct device *dev)
 #endif
 
 #ifdef CONFIG_PM_GENERIC_DOMAINS_SLEEP
-void pm_genpd_syscore_poweroff(struct device *dev);
-void pm_genpd_syscore_poweron(struct device *dev);
+void dev_pm_genpd_suspend(struct device *dev);
+void dev_pm_genpd_resume(struct device *dev);
 #else
-static inline void pm_genpd_syscore_poweroff(struct device *dev) {}
-static inline void pm_genpd_syscore_poweron(struct device *dev) {}
+static inline void dev_pm_genpd_suspend(struct device *dev) {}
+static inline void dev_pm_genpd_resume(struct device *dev) {}
 #endif
 
 /* OF PM domain providers */
-- 
cgit v1.2.3


From 36e68442d1afd4f720704ee1ea8486331507e834 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Mon, 9 Nov 2020 17:19:31 -0800
Subject: bpf: Load and verify kernel module BTFs

Add kernel module listener that will load/validate and unload module BTF.
Module BTFs gets ID generated for them, which makes it possible to iterate
them with existing BTF iteration API. They are given their respective module's
names, which will get reported through GET_OBJ_INFO API. They are also marked
as in-kernel BTFs for tooling to distinguish them from user-provided BTFs.

Also, similarly to vmlinux BTF, kernel module BTFs are exposed through
sysfs as /sys/kernel/btf/<module-name>. This is convenient for user-space
tools to inspect module BTF contents and dump their types with existing tools:

[vmuser@archvm bpf]$ ls -la /sys/kernel/btf
total 0
drwxr-xr-x  2 root root       0 Nov  4 19:46 .
drwxr-xr-x 13 root root       0 Nov  4 19:46 ..

...

-r--r--r--  1 root root     888 Nov  4 19:46 irqbypass
-r--r--r--  1 root root  100225 Nov  4 19:46 kvm
-r--r--r--  1 root root   35401 Nov  4 19:46 kvm_intel
-r--r--r--  1 root root     120 Nov  4 19:46 pcspkr
-r--r--r--  1 root root     399 Nov  4 19:46 serio_raw
-r--r--r--  1 root root 4094095 Nov  4 19:46 vmlinux

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/bpf/20201110011932.3201430-5-andrii@kernel.org
---
 Documentation/ABI/testing/sysfs-kernel-btf |   8 ++
 include/linux/bpf.h                        |   2 +
 include/linux/module.h                     |   4 +
 kernel/bpf/btf.c                           | 194 +++++++++++++++++++++++++++++
 kernel/bpf/sysfs_btf.c                     |   2 +-
 kernel/module.c                            |  32 +++++
 6 files changed, 241 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/Documentation/ABI/testing/sysfs-kernel-btf b/Documentation/ABI/testing/sysfs-kernel-btf
index 2c9744b2cd59..fe96efdc9b6c 100644
--- a/Documentation/ABI/testing/sysfs-kernel-btf
+++ b/Documentation/ABI/testing/sysfs-kernel-btf
@@ -15,3 +15,11 @@ Description:
 		information with description of all internal kernel types. See
 		Documentation/bpf/btf.rst for detailed description of format
 		itself.
+
+What:		/sys/kernel/btf/<module-name>
+Date:		Nov 2020
+KernelVersion:	5.11
+Contact:	bpf@vger.kernel.org
+Description:
+		Read-only binary attribute exposing kernel module's BTF type
+		information as an add-on to the kernel's BTF (/sys/kernel/btf/vmlinux).
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 73d5381a5d5c..581b2a2e78eb 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -36,9 +36,11 @@ struct seq_operations;
 struct bpf_iter_aux_info;
 struct bpf_local_storage;
 struct bpf_local_storage_map;
+struct kobject;
 
 extern struct idr btf_idr;
 extern spinlock_t btf_idr_lock;
+extern struct kobject *btf_kobj;
 
 typedef int (*bpf_iter_init_seq_priv_t)(void *private_data,
 					struct bpf_iter_aux_info *aux);
diff --git a/include/linux/module.h b/include/linux/module.h
index a29187f7c360..20fce258ffba 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -475,6 +475,10 @@ struct module {
 	unsigned int num_bpf_raw_events;
 	struct bpf_raw_event_map *bpf_raw_events;
 #endif
+#ifdef CONFIG_DEBUG_INFO_BTF_MODULES
+	unsigned int btf_data_size;
+	void *btf_data;
+#endif
 #ifdef CONFIG_JUMP_LABEL
 	struct jump_entry *jump_entries;
 	unsigned int num_jump_entries;
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 856585db7aa7..0f1fd2669d69 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -22,6 +22,8 @@
 #include <linux/skmsg.h>
 #include <linux/perf_event.h>
 #include <linux/bsearch.h>
+#include <linux/kobject.h>
+#include <linux/sysfs.h>
 #include <net/sock.h>
 
 /* BTF (BPF Type Format) is the meta data format which describes
@@ -4476,6 +4478,75 @@ errout:
 	return ERR_PTR(err);
 }
 
+static struct btf *btf_parse_module(const char *module_name, const void *data, unsigned int data_size)
+{
+	struct btf_verifier_env *env = NULL;
+	struct bpf_verifier_log *log;
+	struct btf *btf = NULL, *base_btf;
+	int err;
+
+	base_btf = bpf_get_btf_vmlinux();
+	if (IS_ERR(base_btf))
+		return base_btf;
+	if (!base_btf)
+		return ERR_PTR(-EINVAL);
+
+	env = kzalloc(sizeof(*env), GFP_KERNEL | __GFP_NOWARN);
+	if (!env)
+		return ERR_PTR(-ENOMEM);
+
+	log = &env->log;
+	log->level = BPF_LOG_KERNEL;
+
+	btf = kzalloc(sizeof(*btf), GFP_KERNEL | __GFP_NOWARN);
+	if (!btf) {
+		err = -ENOMEM;
+		goto errout;
+	}
+	env->btf = btf;
+
+	btf->base_btf = base_btf;
+	btf->start_id = base_btf->nr_types;
+	btf->start_str_off = base_btf->hdr.str_len;
+	btf->kernel_btf = true;
+	snprintf(btf->name, sizeof(btf->name), "%s", module_name);
+
+	btf->data = kvmalloc(data_size, GFP_KERNEL | __GFP_NOWARN);
+	if (!btf->data) {
+		err = -ENOMEM;
+		goto errout;
+	}
+	memcpy(btf->data, data, data_size);
+	btf->data_size = data_size;
+
+	err = btf_parse_hdr(env);
+	if (err)
+		goto errout;
+
+	btf->nohdr_data = btf->data + btf->hdr.hdr_len;
+
+	err = btf_parse_str_sec(env);
+	if (err)
+		goto errout;
+
+	err = btf_check_all_metas(env);
+	if (err)
+		goto errout;
+
+	btf_verifier_env_free(env);
+	refcount_set(&btf->refcnt, 1);
+	return btf;
+
+errout:
+	btf_verifier_env_free(env);
+	if (btf) {
+		kvfree(btf->data);
+		kvfree(btf->types);
+		kfree(btf);
+	}
+	return ERR_PTR(err);
+}
+
 struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog)
 {
 	struct bpf_prog *tgt_prog = prog->aux->dst_prog;
@@ -5651,3 +5722,126 @@ bool btf_id_set_contains(const struct btf_id_set *set, u32 id)
 {
 	return bsearch(&id, set->ids, set->cnt, sizeof(u32), btf_id_cmp_func) != NULL;
 }
+
+#ifdef CONFIG_DEBUG_INFO_BTF_MODULES
+struct btf_module {
+	struct list_head list;
+	struct module *module;
+	struct btf *btf;
+	struct bin_attribute *sysfs_attr;
+};
+
+static LIST_HEAD(btf_modules);
+static DEFINE_MUTEX(btf_module_mutex);
+
+static ssize_t
+btf_module_read(struct file *file, struct kobject *kobj,
+		struct bin_attribute *bin_attr,
+		char *buf, loff_t off, size_t len)
+{
+	const struct btf *btf = bin_attr->private;
+
+	memcpy(buf, btf->data + off, len);
+	return len;
+}
+
+static int btf_module_notify(struct notifier_block *nb, unsigned long op,
+			     void *module)
+{
+	struct btf_module *btf_mod, *tmp;
+	struct module *mod = module;
+	struct btf *btf;
+	int err = 0;
+
+	if (mod->btf_data_size == 0 ||
+	    (op != MODULE_STATE_COMING && op != MODULE_STATE_GOING))
+		goto out;
+
+	switch (op) {
+	case MODULE_STATE_COMING:
+		btf_mod = kzalloc(sizeof(*btf_mod), GFP_KERNEL);
+		if (!btf_mod) {
+			err = -ENOMEM;
+			goto out;
+		}
+		btf = btf_parse_module(mod->name, mod->btf_data, mod->btf_data_size);
+		if (IS_ERR(btf)) {
+			pr_warn("failed to validate module [%s] BTF: %ld\n",
+				mod->name, PTR_ERR(btf));
+			kfree(btf_mod);
+			err = PTR_ERR(btf);
+			goto out;
+		}
+		err = btf_alloc_id(btf);
+		if (err) {
+			btf_free(btf);
+			kfree(btf_mod);
+			goto out;
+		}
+
+		mutex_lock(&btf_module_mutex);
+		btf_mod->module = module;
+		btf_mod->btf = btf;
+		list_add(&btf_mod->list, &btf_modules);
+		mutex_unlock(&btf_module_mutex);
+
+		if (IS_ENABLED(CONFIG_SYSFS)) {
+			struct bin_attribute *attr;
+
+			attr = kzalloc(sizeof(*attr), GFP_KERNEL);
+			if (!attr)
+				goto out;
+
+			sysfs_bin_attr_init(attr);
+			attr->attr.name = btf->name;
+			attr->attr.mode = 0444;
+			attr->size = btf->data_size;
+			attr->private = btf;
+			attr->read = btf_module_read;
+
+			err = sysfs_create_bin_file(btf_kobj, attr);
+			if (err) {
+				pr_warn("failed to register module [%s] BTF in sysfs: %d\n",
+					mod->name, err);
+				kfree(attr);
+				err = 0;
+				goto out;
+			}
+
+			btf_mod->sysfs_attr = attr;
+		}
+
+		break;
+	case MODULE_STATE_GOING:
+		mutex_lock(&btf_module_mutex);
+		list_for_each_entry_safe(btf_mod, tmp, &btf_modules, list) {
+			if (btf_mod->module != module)
+				continue;
+
+			list_del(&btf_mod->list);
+			if (btf_mod->sysfs_attr)
+				sysfs_remove_bin_file(btf_kobj, btf_mod->sysfs_attr);
+			btf_put(btf_mod->btf);
+			kfree(btf_mod->sysfs_attr);
+			kfree(btf_mod);
+			break;
+		}
+		mutex_unlock(&btf_module_mutex);
+		break;
+	}
+out:
+	return notifier_from_errno(err);
+}
+
+static struct notifier_block btf_module_nb = {
+	.notifier_call = btf_module_notify,
+};
+
+static int __init btf_module_init(void)
+{
+	register_module_notifier(&btf_module_nb);
+	return 0;
+}
+
+fs_initcall(btf_module_init);
+#endif /* CONFIG_DEBUG_INFO_BTF_MODULES */
diff --git a/kernel/bpf/sysfs_btf.c b/kernel/bpf/sysfs_btf.c
index 11b3380887fa..ef6911aee3bb 100644
--- a/kernel/bpf/sysfs_btf.c
+++ b/kernel/bpf/sysfs_btf.c
@@ -26,7 +26,7 @@ static struct bin_attribute bin_attr_btf_vmlinux __ro_after_init = {
 	.read = btf_vmlinux_read,
 };
 
-static struct kobject *btf_kobj;
+struct kobject *btf_kobj;
 
 static int __init btf_vmlinux_init(void)
 {
diff --git a/kernel/module.c b/kernel/module.c
index a4fa44a652a7..f2996b02ab2e 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -380,6 +380,35 @@ static void *section_objs(const struct load_info *info,
 	return (void *)info->sechdrs[sec].sh_addr;
 }
 
+/* Find a module section: 0 means not found. Ignores SHF_ALLOC flag. */
+static unsigned int find_any_sec(const struct load_info *info, const char *name)
+{
+	unsigned int i;
+
+	for (i = 1; i < info->hdr->e_shnum; i++) {
+		Elf_Shdr *shdr = &info->sechdrs[i];
+		if (strcmp(info->secstrings + shdr->sh_name, name) == 0)
+			return i;
+	}
+	return 0;
+}
+
+/*
+ * Find a module section, or NULL. Fill in number of "objects" in section.
+ * Ignores SHF_ALLOC flag.
+ */
+static __maybe_unused void *any_section_objs(const struct load_info *info,
+					     const char *name,
+					     size_t object_size,
+					     unsigned int *num)
+{
+	unsigned int sec = find_any_sec(info, name);
+
+	/* Section 0 has sh_addr 0 and sh_size 0. */
+	*num = info->sechdrs[sec].sh_size / object_size;
+	return (void *)info->sechdrs[sec].sh_addr;
+}
+
 /* Provided by the linker */
 extern const struct kernel_symbol __start___ksymtab[];
 extern const struct kernel_symbol __stop___ksymtab[];
@@ -3250,6 +3279,9 @@ static int find_module_sections(struct module *mod, struct load_info *info)
 					   sizeof(*mod->bpf_raw_events),
 					   &mod->num_bpf_raw_events);
 #endif
+#ifdef CONFIG_DEBUG_INFO_BTF_MODULES
+	mod->btf_data = any_section_objs(info, ".BTF", 1, &mod->btf_data_size);
+#endif
 #ifdef CONFIG_JUMP_LABEL
 	mod->jump_entries = section_objs(info, "__jump_table",
 					sizeof(*mod->jump_entries),
-- 
cgit v1.2.3


From 8a3c84b649b033024d2349f96234b26cbd6083a6 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Tue, 10 Nov 2020 16:50:21 -0800
Subject: vfs: separate __sb_start_write into blocking and non-blocking helpers

Break this function into two helpers so that it's obvious that the
trylock versions return a value that must be checked, and the blocking
versions don't require that.  While we're at it, clean up the return
type mismatch.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/aio.c           |  2 +-
 fs/io_uring.c      |  3 +--
 fs/super.c         | 18 ++++++++++++------
 include/linux/fs.h | 21 +++++++++++----------
 4 files changed, 25 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/fs/aio.c b/fs/aio.c
index c45c20d87538..6a21d8919409 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1572,7 +1572,7 @@ static int aio_write(struct kiocb *req, const struct iocb *iocb,
 		 * we return to userspace.
 		 */
 		if (S_ISREG(file_inode(file)->i_mode)) {
-			__sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, true);
+			sb_start_write(file_inode(file)->i_sb);
 			__sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE);
 		}
 		req->ki_flags |= IOCB_WRITE;
diff --git a/fs/io_uring.c b/fs/io_uring.c
index b42dfa0243bf..4cbaddfe3d80 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -3532,8 +3532,7 @@ static int io_write(struct io_kiocb *req, bool force_nonblock,
 	 * we return to userspace.
 	 */
 	if (req->flags & REQ_F_ISREG) {
-		__sb_start_write(file_inode(req->file)->i_sb,
-					SB_FREEZE_WRITE, true);
+		sb_start_write(file_inode(req->file)->i_sb);
 		__sb_writers_release(file_inode(req->file)->i_sb,
 					SB_FREEZE_WRITE);
 	}
diff --git a/fs/super.c b/fs/super.c
index e1fd667454d4..59aa59279133 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1645,16 +1645,22 @@ EXPORT_SYMBOL(__sb_end_write);
  * This is an internal function, please use sb_start_{write,pagefault,intwrite}
  * instead.
  */
-int __sb_start_write(struct super_block *sb, int level, bool wait)
+void __sb_start_write(struct super_block *sb, int level)
 {
-	if (!wait)
-		return percpu_down_read_trylock(sb->s_writers.rw_sem + level-1);
-
-	percpu_down_read(sb->s_writers.rw_sem + level-1);
-	return 1;
+	percpu_down_read(sb->s_writers.rw_sem + level - 1);
 }
 EXPORT_SYMBOL(__sb_start_write);
 
+/*
+ * This is an internal function, please use sb_start_{write,pagefault,intwrite}
+ * instead.
+ */
+bool __sb_start_write_trylock(struct super_block *sb, int level)
+{
+	return percpu_down_read_trylock(sb->s_writers.rw_sem + level - 1);
+}
+EXPORT_SYMBOL_GPL(__sb_start_write_trylock);
+
 /**
  * sb_wait_write - wait until all writers to given file system finish
  * @sb: the super for which we wait
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 0bd126418bb6..305989afd49c 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1581,7 +1581,8 @@ extern struct timespec64 current_time(struct inode *inode);
  */
 
 void __sb_end_write(struct super_block *sb, int level);
-int __sb_start_write(struct super_block *sb, int level, bool wait);
+void __sb_start_write(struct super_block *sb, int level);
+bool __sb_start_write_trylock(struct super_block *sb, int level);
 
 #define __sb_writers_acquired(sb, lev)	\
 	percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_)
@@ -1645,12 +1646,12 @@ static inline void sb_end_intwrite(struct super_block *sb)
  */
 static inline void sb_start_write(struct super_block *sb)
 {
-	__sb_start_write(sb, SB_FREEZE_WRITE, true);
+	__sb_start_write(sb, SB_FREEZE_WRITE);
 }
 
-static inline int sb_start_write_trylock(struct super_block *sb)
+static inline bool sb_start_write_trylock(struct super_block *sb)
 {
-	return __sb_start_write(sb, SB_FREEZE_WRITE, false);
+	return __sb_start_write_trylock(sb, SB_FREEZE_WRITE);
 }
 
 /**
@@ -1674,7 +1675,7 @@ static inline int sb_start_write_trylock(struct super_block *sb)
  */
 static inline void sb_start_pagefault(struct super_block *sb)
 {
-	__sb_start_write(sb, SB_FREEZE_PAGEFAULT, true);
+	__sb_start_write(sb, SB_FREEZE_PAGEFAULT);
 }
 
 /*
@@ -1692,12 +1693,12 @@ static inline void sb_start_pagefault(struct super_block *sb)
  */
 static inline void sb_start_intwrite(struct super_block *sb)
 {
-	__sb_start_write(sb, SB_FREEZE_FS, true);
+	__sb_start_write(sb, SB_FREEZE_FS);
 }
 
-static inline int sb_start_intwrite_trylock(struct super_block *sb)
+static inline bool sb_start_intwrite_trylock(struct super_block *sb)
 {
-	return __sb_start_write(sb, SB_FREEZE_FS, false);
+	return __sb_start_write_trylock(sb, SB_FREEZE_FS);
 }
 
 
@@ -2756,14 +2757,14 @@ static inline void file_start_write(struct file *file)
 {
 	if (!S_ISREG(file_inode(file)->i_mode))
 		return;
-	__sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, true);
+	sb_start_write(file_inode(file)->i_sb);
 }
 
 static inline bool file_start_write_trylock(struct file *file)
 {
 	if (!S_ISREG(file_inode(file)->i_mode))
 		return true;
-	return __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, false);
+	return sb_start_write_trylock(file_inode(file)->i_sb);
 }
 
 static inline void file_end_write(struct file *file)
-- 
cgit v1.2.3


From 9b8523423b23ee3dfd88e32f5b7207be56a4e782 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Tue, 10 Nov 2020 16:50:21 -0800
Subject: vfs: move __sb_{start,end}_write* to fs.h

Now that we've straightened out the callers, move these three functions
to fs.h since they're fairly trivial.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
---
 fs/super.c         | 30 ------------------------------
 include/linux/fs.h | 21 ++++++++++++++++++---
 2 files changed, 18 insertions(+), 33 deletions(-)

(limited to 'include/linux')

diff --git a/fs/super.c b/fs/super.c
index 59aa59279133..98bb0629ee10 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1631,36 +1631,6 @@ int super_setup_bdi(struct super_block *sb)
 }
 EXPORT_SYMBOL(super_setup_bdi);
 
-/*
- * This is an internal function, please use sb_end_{write,pagefault,intwrite}
- * instead.
- */
-void __sb_end_write(struct super_block *sb, int level)
-{
-	percpu_up_read(sb->s_writers.rw_sem + level-1);
-}
-EXPORT_SYMBOL(__sb_end_write);
-
-/*
- * This is an internal function, please use sb_start_{write,pagefault,intwrite}
- * instead.
- */
-void __sb_start_write(struct super_block *sb, int level)
-{
-	percpu_down_read(sb->s_writers.rw_sem + level - 1);
-}
-EXPORT_SYMBOL(__sb_start_write);
-
-/*
- * This is an internal function, please use sb_start_{write,pagefault,intwrite}
- * instead.
- */
-bool __sb_start_write_trylock(struct super_block *sb, int level)
-{
-	return percpu_down_read_trylock(sb->s_writers.rw_sem + level - 1);
-}
-EXPORT_SYMBOL_GPL(__sb_start_write_trylock);
-
 /**
  * sb_wait_write - wait until all writers to given file system finish
  * @sb: the super for which we wait
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 305989afd49c..6dabd019cab0 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1580,9 +1580,24 @@ extern struct timespec64 current_time(struct inode *inode);
  * Snapshotting support.
  */
 
-void __sb_end_write(struct super_block *sb, int level);
-void __sb_start_write(struct super_block *sb, int level);
-bool __sb_start_write_trylock(struct super_block *sb, int level);
+/*
+ * These are internal functions, please use sb_start_{write,pagefault,intwrite}
+ * instead.
+ */
+static inline void __sb_end_write(struct super_block *sb, int level)
+{
+	percpu_up_read(sb->s_writers.rw_sem + level-1);
+}
+
+static inline void __sb_start_write(struct super_block *sb, int level)
+{
+	percpu_down_read(sb->s_writers.rw_sem + level - 1);
+}
+
+static inline bool __sb_start_write_trylock(struct super_block *sb, int level)
+{
+	return percpu_down_read_trylock(sb->s_writers.rw_sem + level - 1);
+}
 
 #define __sb_writers_acquired(sb, lev)	\
 	percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_)
-- 
cgit v1.2.3


From 60602cb549f1965a7edbc96026760dfb93911fab Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Wed, 28 Oct 2020 08:19:24 -0400
Subject: fgraph: Make overruns 4 bytes in graph stack structure

Inspecting the data structures of the function graph tracer, I found that
the overrun value is unsigned long, which is 8 bytes on a 64 bit machine,
and not only that, the depth is an int (4 bytes). The overrun can be simply
an unsigned int (4 bytes) and pack the ftrace_graph_ret structure better.

The depth is moved up next to the func, as it is used more often with func,
and improves cache locality.

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/ftrace.h               | 4 ++--
 kernel/trace/trace_entries.h         | 4 ++--
 kernel/trace/trace_functions_graph.c | 2 +-
 3 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 806196345c3f..8dde9c17aaa5 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -864,11 +864,11 @@ struct ftrace_graph_ent {
  */
 struct ftrace_graph_ret {
 	unsigned long func; /* Current function */
+	int depth;
 	/* Number of functions that overran the depth limit for current task */
-	unsigned long overrun;
+	unsigned int overrun;
 	unsigned long long calltime;
 	unsigned long long rettime;
-	int depth;
 } __packed;
 
 /* Type of the callback handlers for tracing function graph*/
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index 18c4a58aff79..ceafe2dc97e1 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -93,10 +93,10 @@ FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry,
 	F_STRUCT(
 		__field_struct(	struct ftrace_graph_ret,	ret	)
 		__field_packed(	unsigned long,	ret,		func	)
-		__field_packed(	unsigned long,	ret,		overrun	)
+		__field_packed(	int,		ret,		depth	)
+		__field_packed(	unsigned int,	ret,		overrun	)
 		__field_packed(	unsigned long long, ret,	calltime)
 		__field_packed(	unsigned long long, ret,	rettime	)
-		__field_packed(	int,		ret,		depth	)
 	),
 
 	F_printk("<-- %ps (%d) (start: %llx  end: %llx) over: %d",
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 60d66278aa0d..d874dec87131 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -957,7 +957,7 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
 
 	/* Overrun */
 	if (flags & TRACE_GRAPH_PRINT_OVERRUN)
-		trace_seq_printf(s, " (Overruns: %lu)\n",
+		trace_seq_printf(s, " (Overruns: %u)\n",
 				 trace->overrun);
 
 	print_graph_irq(iter, trace->func, TRACE_GRAPH_RET,
-- 
cgit v1.2.3


From 7b68621f8d16689cbb4203aceaca86ffb165f1d0 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Fri, 30 Oct 2020 17:21:00 -0400
Subject: ftrace: Clean up the recursion code a bit

In trace_test_and_set_recursion(), current->trace_recursion is placed into a
variable, and that variable should be used for the processing, as there's no
reason to dereference current multiple times.

On trace_clear_recursion(), current->trace_recursion is modified and there's
no reason to copy it over to a variable.

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/trace_recursion.h | 22 +++++++---------------
 1 file changed, 7 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h
index 228cc56ed66e..a9f9c5714e65 100644
--- a/include/linux/trace_recursion.h
+++ b/include/linux/trace_recursion.h
@@ -162,7 +162,7 @@ extern void ftrace_record_recursion(unsigned long ip, unsigned long parent_ip);
 static __always_inline int trace_test_and_set_recursion(unsigned long ip, unsigned long pip,
 							int start, int max)
 {
-	unsigned int val = current->trace_recursion;
+	unsigned int val = READ_ONCE(current->trace_recursion);
 	int bit;
 
 	/* A previous recursion check was made */
@@ -176,18 +176,15 @@ static __always_inline int trace_test_and_set_recursion(unsigned long ip, unsign
 		 * a switch between contexts. Allow for a single recursion.
 		 */
 		bit = TRACE_TRANSITION_BIT;
-		if (trace_recursion_test(bit)) {
+		if (val & (1 << bit)) {
 			do_ftrace_record_recursion(ip, pip);
 			return -1;
 		}
-		trace_recursion_set(bit);
-		barrier();
-		return bit + 1;
+	} else {
+		/* Normal check passed, clear the transition to allow it again */
+		val &= ~(1 << TRACE_TRANSITION_BIT);
 	}
 
-	/* Normal check passed, clear the transition to allow it again */
-	trace_recursion_clear(TRACE_TRANSITION_BIT);
-
 	val |= 1 << bit;
 	current->trace_recursion = val;
 	barrier();
@@ -197,17 +194,12 @@ static __always_inline int trace_test_and_set_recursion(unsigned long ip, unsign
 
 static __always_inline void trace_clear_recursion(int bit)
 {
-	unsigned int val = current->trace_recursion;
-
 	if (!bit)
 		return;
 
-	bit--;
-	bit = 1 << bit;
-	val &= ~bit;
-
 	barrier();
-	current->trace_recursion = val;
+	bit--;
+	trace_recursion_clear(bit);
 }
 
 /**
-- 
cgit v1.2.3


From 4210d50f0b3e423e10a7a254b2a67f5c5318868e Mon Sep 17 00:00:00 2001
From: Isaac Hazan <isaac.hazan@intel.com>
Date: Thu, 24 Sep 2020 11:43:58 +0300
Subject: thunderbolt: Add link_speed and link_width to XDomain

Link speed and link width are needed for checking expected values in
case of using a loopback service.

Signed-off-by: Isaac Hazan <isaac.hazan@intel.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Yehezkel Bernat <YehezkelShB@gmail.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/ABI/testing/sysfs-bus-thunderbolt | 28 +++++++++++
 drivers/thunderbolt/switch.c                    |  9 +++-
 drivers/thunderbolt/tb.h                        |  1 +
 drivers/thunderbolt/xdomain.c                   | 65 +++++++++++++++++++++++++
 include/linux/thunderbolt.h                     |  4 ++
 5 files changed, 106 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/Documentation/ABI/testing/sysfs-bus-thunderbolt b/Documentation/ABI/testing/sysfs-bus-thunderbolt
index 0b4ab9e4b8f4..a91b4b24496e 100644
--- a/Documentation/ABI/testing/sysfs-bus-thunderbolt
+++ b/Documentation/ABI/testing/sysfs-bus-thunderbolt
@@ -1,3 +1,31 @@
+What:		/sys/bus/thunderbolt/devices/<xdomain>/rx_speed
+Date:		Feb 2021
+KernelVersion:	5.11
+Contact:	Isaac Hazan <isaac.hazan@intel.com>
+Description:	This attribute reports the XDomain RX speed per lane.
+		All RX lanes run at the same speed.
+
+What:		/sys/bus/thunderbolt/devices/<xdomain>/rx_lanes
+Date:		Feb 2021
+KernelVersion:	5.11
+Contact:	Isaac Hazan <isaac.hazan@intel.com>
+Description:	This attribute reports the number of RX lanes the XDomain
+		is using simultaneously through its upstream port.
+
+What:		/sys/bus/thunderbolt/devices/<xdomain>/tx_speed
+Date:		Feb 2021
+KernelVersion:	5.11
+Contact:	Isaac Hazan <isaac.hazan@intel.com>
+Description:	This attribute reports the XDomain TX speed per lane.
+		All TX lanes run at the same speed.
+
+What:		/sys/bus/thunderbolt/devices/<xdomain>/tx_lanes
+Date:		Feb 2021
+KernelVersion:	5.11
+Contact:	Isaac Hazan <isaac.hazan@intel.com>
+Description:	This attribute reports number of TX lanes the XDomain
+		is using simultaneously through its upstream port.
+
 What: /sys/bus/thunderbolt/devices/.../domainX/boot_acl
 Date:		Jun 2018
 KernelVersion:	4.17
diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c
index c73bbfe69ba1..05a360901790 100644
--- a/drivers/thunderbolt/switch.c
+++ b/drivers/thunderbolt/switch.c
@@ -932,7 +932,14 @@ int tb_port_get_link_speed(struct tb_port *port)
 	return speed == LANE_ADP_CS_1_CURRENT_SPEED_GEN3 ? 20 : 10;
 }
 
-static int tb_port_get_link_width(struct tb_port *port)
+/**
+ * tb_port_get_link_width() - Get current link width
+ * @port: Port to check (USB4 or CIO)
+ *
+ * Returns link width. Return values can be 1 (Single-Lane), 2 (Dual-Lane)
+ * or negative errno in case of failure.
+ */
+int tb_port_get_link_width(struct tb_port *port)
 {
 	u32 val;
 	int ret;
diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h
index a9995e21b916..3a826315049e 100644
--- a/drivers/thunderbolt/tb.h
+++ b/drivers/thunderbolt/tb.h
@@ -862,6 +862,7 @@ struct tb_port *tb_next_port_on_path(struct tb_port *start, struct tb_port *end,
 	     (p) = tb_next_port_on_path((src), (dst), (p)))
 
 int tb_port_get_link_speed(struct tb_port *port);
+int tb_port_get_link_width(struct tb_port *port);
 
 int tb_switch_find_vse_cap(struct tb_switch *sw, enum tb_switch_vse_cap vsec);
 int tb_switch_find_cap(struct tb_switch *sw, enum tb_switch_cap cap);
diff --git a/drivers/thunderbolt/xdomain.c b/drivers/thunderbolt/xdomain.c
index da229ac4e471..83a315f96934 100644
--- a/drivers/thunderbolt/xdomain.c
+++ b/drivers/thunderbolt/xdomain.c
@@ -942,6 +942,43 @@ static void tb_xdomain_restore_paths(struct tb_xdomain *xd)
 	}
 }
 
+static inline struct tb_switch *tb_xdomain_parent(struct tb_xdomain *xd)
+{
+	return tb_to_switch(xd->dev.parent);
+}
+
+static int tb_xdomain_update_link_attributes(struct tb_xdomain *xd)
+{
+	bool change = false;
+	struct tb_port *port;
+	int ret;
+
+	port = tb_port_at(xd->route, tb_xdomain_parent(xd));
+
+	ret = tb_port_get_link_speed(port);
+	if (ret < 0)
+		return ret;
+
+	if (xd->link_speed != ret)
+		change = true;
+
+	xd->link_speed = ret;
+
+	ret = tb_port_get_link_width(port);
+	if (ret < 0)
+		return ret;
+
+	if (xd->link_width != ret)
+		change = true;
+
+	xd->link_width = ret;
+
+	if (change)
+		kobject_uevent(&xd->dev.kobj, KOBJ_CHANGE);
+
+	return 0;
+}
+
 static void tb_xdomain_get_uuid(struct work_struct *work)
 {
 	struct tb_xdomain *xd = container_of(work, typeof(*xd),
@@ -1053,6 +1090,8 @@ static void tb_xdomain_get_properties(struct work_struct *work)
 	xd->properties = dir;
 	xd->property_block_gen = gen;
 
+	tb_xdomain_update_link_attributes(xd);
+
 	tb_xdomain_restore_paths(xd);
 
 	mutex_unlock(&xd->lock);
@@ -1159,9 +1198,35 @@ static ssize_t unique_id_show(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_RO(unique_id);
 
+static ssize_t speed_show(struct device *dev, struct device_attribute *attr,
+			  char *buf)
+{
+	struct tb_xdomain *xd = container_of(dev, struct tb_xdomain, dev);
+
+	return sprintf(buf, "%u.0 Gb/s\n", xd->link_speed);
+}
+
+static DEVICE_ATTR(rx_speed, 0444, speed_show, NULL);
+static DEVICE_ATTR(tx_speed, 0444, speed_show, NULL);
+
+static ssize_t lanes_show(struct device *dev, struct device_attribute *attr,
+			  char *buf)
+{
+	struct tb_xdomain *xd = container_of(dev, struct tb_xdomain, dev);
+
+	return sprintf(buf, "%u\n", xd->link_width);
+}
+
+static DEVICE_ATTR(rx_lanes, 0444, lanes_show, NULL);
+static DEVICE_ATTR(tx_lanes, 0444, lanes_show, NULL);
+
 static struct attribute *xdomain_attrs[] = {
 	&dev_attr_device.attr,
 	&dev_attr_device_name.attr,
+	&dev_attr_rx_lanes.attr,
+	&dev_attr_rx_speed.attr,
+	&dev_attr_tx_lanes.attr,
+	&dev_attr_tx_speed.attr,
 	&dev_attr_unique_id.attr,
 	&dev_attr_vendor.attr,
 	&dev_attr_vendor_name.attr,
diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h
index 5db2b11ab085..e441af88ed77 100644
--- a/include/linux/thunderbolt.h
+++ b/include/linux/thunderbolt.h
@@ -179,6 +179,8 @@ void tb_unregister_property_dir(const char *key, struct tb_property_dir *dir);
  * @lock: Lock to serialize access to the following fields of this structure
  * @vendor_name: Name of the vendor (or %NULL if not known)
  * @device_name: Name of the device (or %NULL if not known)
+ * @link_speed: Speed of the link in Gb/s
+ * @link_width: Width of the link (1 or 2)
  * @is_unplugged: The XDomain is unplugged
  * @resume: The XDomain is being resumed
  * @needs_uuid: If the XDomain does not have @remote_uuid it will be
@@ -223,6 +225,8 @@ struct tb_xdomain {
 	struct mutex lock;
 	const char *vendor_name;
 	const char *device_name;
+	unsigned int link_speed;
+	unsigned int link_width;
 	bool is_unplugged;
 	bool resume;
 	bool needs_uuid;
-- 
cgit v1.2.3


From 5cc0df9ce10a860aaeac53f8df1cc8754c5c7b03 Mon Sep 17 00:00:00 2001
From: Isaac Hazan <isaac.hazan@intel.com>
Date: Thu, 24 Sep 2020 11:44:01 +0300
Subject: thunderbolt: Add functions for enabling and disabling lane bonding on
 XDomain

These can be used by service drivers to enable and disable lane bonding
as needed.

Signed-off-by: Isaac Hazan <isaac.hazan@intel.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Yehezkel Bernat <YehezkelShB@gmail.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/thunderbolt/switch.c  | 24 ++++++++++++++--
 drivers/thunderbolt/tb.h      |  3 ++
 drivers/thunderbolt/xdomain.c | 66 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/thunderbolt.h   |  2 ++
 4 files changed, 92 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c
index 05a360901790..cdfd8cccfe19 100644
--- a/drivers/thunderbolt/switch.c
+++ b/drivers/thunderbolt/switch.c
@@ -503,12 +503,13 @@ static void tb_dump_port(struct tb *tb, struct tb_regs_port_header *port)
 
 /**
  * tb_port_state() - get connectedness state of a port
+ * @port: the port to check
  *
  * The port must have a TB_CAP_PHY (i.e. it should be a real port).
  *
  * Return: Returns an enum tb_port_state on success or an error code on failure.
  */
-static int tb_port_state(struct tb_port *port)
+int tb_port_state(struct tb_port *port)
 {
 	struct tb_cap_phy phy;
 	int res;
@@ -1008,7 +1009,16 @@ static int tb_port_set_link_width(struct tb_port *port, unsigned int width)
 			     port->cap_phy + LANE_ADP_CS_1, 1);
 }
 
-static int tb_port_lane_bonding_enable(struct tb_port *port)
+/**
+ * tb_port_lane_bonding_enable() - Enable bonding on port
+ * @port: port to enable
+ *
+ * Enable bonding by setting the link width of the port and the
+ * other port in case of dual link port.
+ *
+ * Return: %0 in case of success and negative errno in case of error
+ */
+int tb_port_lane_bonding_enable(struct tb_port *port)
 {
 	int ret;
 
@@ -1038,7 +1048,15 @@ static int tb_port_lane_bonding_enable(struct tb_port *port)
 	return 0;
 }
 
-static void tb_port_lane_bonding_disable(struct tb_port *port)
+/**
+ * tb_port_lane_bonding_disable() - Disable bonding on port
+ * @port: port to disable
+ *
+ * Disable bonding by setting the link width of the port and the
+ * other port in case of dual link port.
+ *
+ */
+void tb_port_lane_bonding_disable(struct tb_port *port)
 {
 	port->dual_link_port->bonded = false;
 	port->bonded = false;
diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h
index 3a826315049e..e98d3561648d 100644
--- a/drivers/thunderbolt/tb.h
+++ b/drivers/thunderbolt/tb.h
@@ -863,6 +863,9 @@ struct tb_port *tb_next_port_on_path(struct tb_port *start, struct tb_port *end,
 
 int tb_port_get_link_speed(struct tb_port *port);
 int tb_port_get_link_width(struct tb_port *port);
+int tb_port_state(struct tb_port *port);
+int tb_port_lane_bonding_enable(struct tb_port *port);
+void tb_port_lane_bonding_disable(struct tb_port *port);
 
 int tb_switch_find_vse_cap(struct tb_switch *sw, enum tb_switch_vse_cap vsec);
 int tb_switch_find_cap(struct tb_switch *sw, enum tb_switch_cap cap);
diff --git a/drivers/thunderbolt/xdomain.c b/drivers/thunderbolt/xdomain.c
index 83a315f96934..65108216bfe3 100644
--- a/drivers/thunderbolt/xdomain.c
+++ b/drivers/thunderbolt/xdomain.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/device.h>
+#include <linux/delay.h>
 #include <linux/kmod.h>
 #include <linux/module.h>
 #include <linux/pm_runtime.h>
@@ -21,6 +22,7 @@
 #define XDOMAIN_UUID_RETRIES			10
 #define XDOMAIN_PROPERTIES_RETRIES		60
 #define XDOMAIN_PROPERTIES_CHANGED_RETRIES	10
+#define XDOMAIN_BONDING_WAIT			100  /* ms */
 
 struct xdomain_request_work {
 	struct work_struct work;
@@ -1443,6 +1445,70 @@ void tb_xdomain_remove(struct tb_xdomain *xd)
 		device_unregister(&xd->dev);
 }
 
+/**
+ * tb_xdomain_lane_bonding_enable() - Enable lane bonding on XDomain
+ * @xd: XDomain connection
+ *
+ * Lane bonding is disabled by default for XDomains. This function tries
+ * to enable bonding by first enabling the port and waiting for the CL0
+ * state.
+ *
+ * Return: %0 in case of success and negative errno in case of error.
+ */
+int tb_xdomain_lane_bonding_enable(struct tb_xdomain *xd)
+{
+	struct tb_port *port;
+	int ret;
+
+	port = tb_port_at(xd->route, tb_xdomain_parent(xd));
+	if (!port->dual_link_port)
+		return -ENODEV;
+
+	ret = tb_port_enable(port->dual_link_port);
+	if (ret)
+		return ret;
+
+	ret = tb_wait_for_port(port->dual_link_port, true);
+	if (ret < 0)
+		return ret;
+	if (!ret)
+		return -ENOTCONN;
+
+	ret = tb_port_lane_bonding_enable(port);
+	if (ret) {
+		tb_port_warn(port, "failed to enable lane bonding\n");
+		return ret;
+	}
+
+	tb_xdomain_update_link_attributes(xd);
+
+	dev_dbg(&xd->dev, "lane bonding enabled\n");
+	return 0;
+}
+EXPORT_SYMBOL_GPL(tb_xdomain_lane_bonding_enable);
+
+/**
+ * tb_xdomain_lane_bonding_disable() - Disable lane bonding
+ * @xd: XDomain connection
+ *
+ * Lane bonding is disabled by default for XDomains. If bonding has been
+ * enabled, this function can be used to disable it.
+ */
+void tb_xdomain_lane_bonding_disable(struct tb_xdomain *xd)
+{
+	struct tb_port *port;
+
+	port = tb_port_at(xd->route, tb_xdomain_parent(xd));
+	if (port->dual_link_port) {
+		tb_port_lane_bonding_disable(port);
+		tb_port_disable(port->dual_link_port);
+		tb_xdomain_update_link_attributes(xd);
+
+		dev_dbg(&xd->dev, "lane bonding disabled\n");
+	}
+}
+EXPORT_SYMBOL_GPL(tb_xdomain_lane_bonding_disable);
+
 /**
  * tb_xdomain_enable_paths() - Enable DMA paths for XDomain connection
  * @xd: XDomain connection
diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h
index e441af88ed77..0a747f92847e 100644
--- a/include/linux/thunderbolt.h
+++ b/include/linux/thunderbolt.h
@@ -247,6 +247,8 @@ struct tb_xdomain {
 	u8 depth;
 };
 
+int tb_xdomain_lane_bonding_enable(struct tb_xdomain *xd);
+void tb_xdomain_lane_bonding_disable(struct tb_xdomain *xd);
 int tb_xdomain_enable_paths(struct tb_xdomain *xd, u16 transmit_path,
 			    u16 transmit_ring, u16 receive_path,
 			    u16 receive_ring);
-- 
cgit v1.2.3


From 407ac931aefda91ac90498c6b6e6893982173613 Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Wed, 7 Oct 2020 17:53:44 +0300
Subject: thunderbolt: Create debugfs directory automatically for services

This allows service drivers to use it as parent directory if they need
to add their own debugfs entries.

Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Yehezkel Bernat <YehezkelShB@gmail.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/thunderbolt/debugfs.c | 24 ++++++++++++++++++++++++
 drivers/thunderbolt/tb.h      |  4 ++++
 drivers/thunderbolt/xdomain.c |  3 +++
 include/linux/thunderbolt.h   |  4 ++++
 4 files changed, 35 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/thunderbolt/debugfs.c b/drivers/thunderbolt/debugfs.c
index 3680b2784ea1..e53ca8270acd 100644
--- a/drivers/thunderbolt/debugfs.c
+++ b/drivers/thunderbolt/debugfs.c
@@ -690,6 +690,30 @@ void tb_switch_debugfs_remove(struct tb_switch *sw)
 	debugfs_remove_recursive(sw->debugfs_dir);
 }
 
+/**
+ * tb_service_debugfs_init() - Add debugfs directory for service
+ * @svc: Thunderbolt service pointer
+ *
+ * Adds debugfs directory for service.
+ */
+void tb_service_debugfs_init(struct tb_service *svc)
+{
+	svc->debugfs_dir = debugfs_create_dir(dev_name(&svc->dev),
+					      tb_debugfs_root);
+}
+
+/**
+ * tb_service_debugfs_remove() - Remove service debugfs directory
+ * @svc: Thunderbolt service pointer
+ *
+ * Removes the previously created debugfs directory for @svc.
+ */
+void tb_service_debugfs_remove(struct tb_service *svc)
+{
+	debugfs_remove_recursive(svc->debugfs_dir);
+	svc->debugfs_dir = NULL;
+}
+
 void tb_debugfs_init(void)
 {
 	tb_debugfs_root = debugfs_create_dir("thunderbolt", NULL);
diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h
index e98d3561648d..a21000649009 100644
--- a/drivers/thunderbolt/tb.h
+++ b/drivers/thunderbolt/tb.h
@@ -1027,11 +1027,15 @@ void tb_debugfs_init(void);
 void tb_debugfs_exit(void);
 void tb_switch_debugfs_init(struct tb_switch *sw);
 void tb_switch_debugfs_remove(struct tb_switch *sw);
+void tb_service_debugfs_init(struct tb_service *svc);
+void tb_service_debugfs_remove(struct tb_service *svc);
 #else
 static inline void tb_debugfs_init(void) { }
 static inline void tb_debugfs_exit(void) { }
 static inline void tb_switch_debugfs_init(struct tb_switch *sw) { }
 static inline void tb_switch_debugfs_remove(struct tb_switch *sw) { }
+static inline void tb_service_debugfs_init(struct tb_service *svc) { }
+static inline void tb_service_debugfs_remove(struct tb_service *svc) { }
 #endif
 
 #ifdef CONFIG_USB4_KUNIT_TEST
diff --git a/drivers/thunderbolt/xdomain.c b/drivers/thunderbolt/xdomain.c
index 65108216bfe3..1a0491b461fd 100644
--- a/drivers/thunderbolt/xdomain.c
+++ b/drivers/thunderbolt/xdomain.c
@@ -779,6 +779,7 @@ static void tb_service_release(struct device *dev)
 	struct tb_service *svc = container_of(dev, struct tb_service, dev);
 	struct tb_xdomain *xd = tb_service_parent(svc);
 
+	tb_service_debugfs_remove(svc);
 	ida_simple_remove(&xd->service_ids, svc->id);
 	kfree(svc->key);
 	kfree(svc);
@@ -892,6 +893,8 @@ static void enumerate_services(struct tb_xdomain *xd)
 		svc->dev.parent = &xd->dev;
 		dev_set_name(&svc->dev, "%s.%d", dev_name(&xd->dev), svc->id);
 
+		tb_service_debugfs_init(svc);
+
 		if (device_register(&svc->dev)) {
 			put_device(&svc->dev);
 			break;
diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h
index 0a747f92847e..a844fd5d96ab 100644
--- a/include/linux/thunderbolt.h
+++ b/include/linux/thunderbolt.h
@@ -350,6 +350,9 @@ void tb_unregister_protocol_handler(struct tb_protocol_handler *handler);
  * @prtcvers: Protocol version from the properties directory
  * @prtcrevs: Protocol software revision from the properties directory
  * @prtcstns: Protocol settings mask from the properties directory
+ * @debugfs_dir: Pointer to the service debugfs directory. Always created
+ *		 when debugfs is enabled. Can be used by service drivers to
+ *		 add their own entries under the service.
  *
  * Each domain exposes set of services it supports as collection of
  * properties. For each service there will be one corresponding
@@ -363,6 +366,7 @@ struct tb_service {
 	u32 prtcvers;
 	u32 prtcrevs;
 	u32 prtcstns;
+	struct dentry *debugfs_dir;
 };
 
 static inline struct tb_service *tb_service_get(struct tb_service *svc)
-- 
cgit v1.2.3


From afe704a2d0618ebdb559b5ddb059f6cdbfc78783 Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Mon, 19 Oct 2020 19:15:20 +0300
Subject: thunderbolt: Add support for end-to-end flow control

USB4 spec defines end-to-end (E2E) flow control that can be used between
hosts to prevent overflow of a RX ring. We previously had this partially
implemented but that code was removed with commit 53f13319d131
("thunderbolt: Get rid of E2E workaround") with the idea that we add it
back properly if there ever is need. Now that we are going to add DMA
traffic test driver (in subsequent patches) this can be useful.

For this reason we modify tb_ring_alloc_rx/tx() so that they accept
RING_FLAG_E2E and configure the hardware ring accordingly. The RX side
also requires passing TX HopID (e2e_tx_hop) used in the credit grant
packets.

Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Yehezkel Bernat <YehezkelShB@gmail.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/net/thunderbolt.c   |  2 +-
 drivers/thunderbolt/ctl.c   |  4 ++--
 drivers/thunderbolt/nhi.c   | 36 ++++++++++++++++++++++++++++++++----
 include/linux/thunderbolt.h |  8 +++++++-
 4 files changed, 42 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/thunderbolt.c b/drivers/net/thunderbolt.c
index 3160443ef3b9..d7b5f87eaa15 100644
--- a/drivers/net/thunderbolt.c
+++ b/drivers/net/thunderbolt.c
@@ -866,7 +866,7 @@ static int tbnet_open(struct net_device *dev)
 	eof_mask = BIT(TBIP_PDF_FRAME_END);
 
 	ring = tb_ring_alloc_rx(xd->tb->nhi, -1, TBNET_RING_SIZE,
-				RING_FLAG_FRAME, sof_mask, eof_mask,
+				RING_FLAG_FRAME, 0, sof_mask, eof_mask,
 				tbnet_start_poll, net);
 	if (!ring) {
 		netdev_err(dev, "failed to allocate Rx ring\n");
diff --git a/drivers/thunderbolt/ctl.c b/drivers/thunderbolt/ctl.c
index 9894b8f63064..1d86e27a0ef3 100644
--- a/drivers/thunderbolt/ctl.c
+++ b/drivers/thunderbolt/ctl.c
@@ -628,8 +628,8 @@ struct tb_ctl *tb_ctl_alloc(struct tb_nhi *nhi, event_cb cb, void *cb_data)
 	if (!ctl->tx)
 		goto err;
 
-	ctl->rx = tb_ring_alloc_rx(nhi, 0, 10, RING_FLAG_NO_SUSPEND, 0xffff,
-				0xffff, NULL, NULL);
+	ctl->rx = tb_ring_alloc_rx(nhi, 0, 10, RING_FLAG_NO_SUSPEND, 0, 0xffff,
+				   0xffff, NULL, NULL);
 	if (!ctl->rx)
 		goto err;
 
diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c
index 3f79baa54829..a69bc6b49405 100644
--- a/drivers/thunderbolt/nhi.c
+++ b/drivers/thunderbolt/nhi.c
@@ -483,7 +483,7 @@ err_unlock:
 
 static struct tb_ring *tb_ring_alloc(struct tb_nhi *nhi, u32 hop, int size,
 				     bool transmit, unsigned int flags,
-				     u16 sof_mask, u16 eof_mask,
+				     int e2e_tx_hop, u16 sof_mask, u16 eof_mask,
 				     void (*start_poll)(void *),
 				     void *poll_data)
 {
@@ -506,6 +506,7 @@ static struct tb_ring *tb_ring_alloc(struct tb_nhi *nhi, u32 hop, int size,
 	ring->is_tx = transmit;
 	ring->size = size;
 	ring->flags = flags;
+	ring->e2e_tx_hop = e2e_tx_hop;
 	ring->sof_mask = sof_mask;
 	ring->eof_mask = eof_mask;
 	ring->head = 0;
@@ -550,7 +551,7 @@ err_free_ring:
 struct tb_ring *tb_ring_alloc_tx(struct tb_nhi *nhi, int hop, int size,
 				 unsigned int flags)
 {
-	return tb_ring_alloc(nhi, hop, size, true, flags, 0, 0, NULL, NULL);
+	return tb_ring_alloc(nhi, hop, size, true, flags, 0, 0, 0, NULL, NULL);
 }
 EXPORT_SYMBOL_GPL(tb_ring_alloc_tx);
 
@@ -560,6 +561,7 @@ EXPORT_SYMBOL_GPL(tb_ring_alloc_tx);
  * @hop: HopID (ring) to allocate. Pass %-1 for automatic allocation.
  * @size: Number of entries in the ring
  * @flags: Flags for the ring
+ * @e2e_tx_hop: Transmit HopID when E2E is enabled in @flags
  * @sof_mask: Mask of PDF values that start a frame
  * @eof_mask: Mask of PDF values that end a frame
  * @start_poll: If not %NULL the ring will call this function when an
@@ -568,10 +570,11 @@ EXPORT_SYMBOL_GPL(tb_ring_alloc_tx);
  * @poll_data: Optional data passed to @start_poll
  */
 struct tb_ring *tb_ring_alloc_rx(struct tb_nhi *nhi, int hop, int size,
-				 unsigned int flags, u16 sof_mask, u16 eof_mask,
+				 unsigned int flags, int e2e_tx_hop,
+				 u16 sof_mask, u16 eof_mask,
 				 void (*start_poll)(void *), void *poll_data)
 {
-	return tb_ring_alloc(nhi, hop, size, false, flags, sof_mask, eof_mask,
+	return tb_ring_alloc(nhi, hop, size, false, flags, e2e_tx_hop, sof_mask, eof_mask,
 			     start_poll, poll_data);
 }
 EXPORT_SYMBOL_GPL(tb_ring_alloc_rx);
@@ -618,6 +621,31 @@ void tb_ring_start(struct tb_ring *ring)
 		ring_iowrite32options(ring, sof_eof_mask, 4);
 		ring_iowrite32options(ring, flags, 0);
 	}
+
+	/*
+	 * Now that the ring valid bit is set we can configure E2E if
+	 * enabled for the ring.
+	 */
+	if (ring->flags & RING_FLAG_E2E) {
+		if (!ring->is_tx) {
+			u32 hop;
+
+			hop = ring->e2e_tx_hop << REG_RX_OPTIONS_E2E_HOP_SHIFT;
+			hop &= REG_RX_OPTIONS_E2E_HOP_MASK;
+			flags |= hop;
+
+			dev_dbg(&ring->nhi->pdev->dev,
+				"enabling E2E for %s %d with TX HopID %d\n",
+				RING_TYPE(ring), ring->hop, ring->e2e_tx_hop);
+		} else {
+			dev_dbg(&ring->nhi->pdev->dev, "enabling E2E for %s %d\n",
+				RING_TYPE(ring), ring->hop);
+		}
+
+		flags |= RING_FLAG_E2E_FLOW_CONTROL;
+		ring_iowrite32options(ring, flags, 0);
+	}
+
 	ring_interrupt_active(ring, true);
 	ring->running = true;
 err:
diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h
index a844fd5d96ab..034dccf93955 100644
--- a/include/linux/thunderbolt.h
+++ b/include/linux/thunderbolt.h
@@ -481,6 +481,8 @@ struct tb_nhi {
  * @irq: MSI-X irq number if the ring uses MSI-X. %0 otherwise.
  * @vector: MSI-X vector number the ring uses (only set if @irq is > 0)
  * @flags: Ring specific flags
+ * @e2e_tx_hop: Transmit HopID when E2E is enabled. Only applicable to
+ *		RX ring. For TX ring this should be set to %0.
  * @sof_mask: Bit mask used to detect start of frame PDF
  * @eof_mask: Bit mask used to detect end of frame PDF
  * @start_poll: Called when ring interrupt is triggered to start
@@ -504,6 +506,7 @@ struct tb_ring {
 	int irq;
 	u8 vector;
 	unsigned int flags;
+	int e2e_tx_hop;
 	u16 sof_mask;
 	u16 eof_mask;
 	void (*start_poll)(void *data);
@@ -514,6 +517,8 @@ struct tb_ring {
 #define RING_FLAG_NO_SUSPEND	BIT(0)
 /* Configure the ring to be in frame mode */
 #define RING_FLAG_FRAME		BIT(1)
+/* Enable end-to-end flow control */
+#define RING_FLAG_E2E		BIT(2)
 
 struct ring_frame;
 typedef void (*ring_cb)(struct tb_ring *, struct ring_frame *, bool canceled);
@@ -562,7 +567,8 @@ struct ring_frame {
 struct tb_ring *tb_ring_alloc_tx(struct tb_nhi *nhi, int hop, int size,
 				 unsigned int flags);
 struct tb_ring *tb_ring_alloc_rx(struct tb_nhi *nhi, int hop, int size,
-				 unsigned int flags, u16 sof_mask, u16 eof_mask,
+				 unsigned int flags, int e2e_tx_hop,
+				 u16 sof_mask, u16 eof_mask,
 				 void (*start_poll)(void *), void *poll_data);
 void tb_ring_start(struct tb_ring *ring);
 void tb_ring_stop(struct tb_ring *ring);
-- 
cgit v1.2.3


From 029b42d8519cef70c4fb5fcaccd08f1053ed2bf0 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Tue, 27 Oct 2020 10:57:23 +0100
Subject: spi: introduce SPI_MODE_X_MASK macro

Provide a macro to filter all SPI_MODE_0,1,2,3 mode in one run.

The latest SPI framework will parse the devicetree in following call
sequence: of_register_spi_device() -> of_spi_parse_dt()
So, driver do not need to pars the devicetree and will get prepared
flags in the probe.

On one hand it is good far most drivers. On other hand some drivers need to
filter flags provide by SPI framework and apply know to work flags. This drivers
may use SPI_MODE_X_MASK to filter MODE flags and set own, known flags:
  spi->flags &= ~SPI_MODE_X_MASK;
  spi->flags |= SPI_MODE_0;

Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://lore.kernel.org/r/20201027095724.18654-2-o.rempel@pengutronix.de
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/spi/spi.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 99380c0825db..8097f27702f3 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -171,6 +171,7 @@ struct spi_device {
 #define	SPI_MODE_1	(0|SPI_CPHA)
 #define	SPI_MODE_2	(SPI_CPOL|0)
 #define	SPI_MODE_3	(SPI_CPOL|SPI_CPHA)
+#define	SPI_MODE_X_MASK	(SPI_CPOL|SPI_CPHA)
 #define	SPI_CS_HIGH	0x04			/* chipselect active high? */
 #define	SPI_LSB_FIRST	0x08			/* per-word bits-on-wire */
 #define	SPI_3WIRE	0x10			/* SI/SO signals shared */
-- 
cgit v1.2.3


From 476b485be03c37212fcf10d85510aae5d34316ef Mon Sep 17 00:00:00 2001
From: Jianxin Xiong <jianxin.xiong@intel.com>
Date: Tue, 10 Nov 2020 13:41:17 -0800
Subject: dma-buf: Document that dma-buf size is fixed

The fact that the size of dma-buf is invariant over the lifetime of the
buffer is mentioned in the comment of 'dma_buf_ops.mmap', but is not
documented at where the info is defined. Add the missing documentation.

Signed-off-by: Jianxin Xiong <jianxin.xiong@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/1605044477-51833-7-git-send-email-jianxin.xiong@intel.com
---
 include/linux/dma-buf.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index 03875eaed51a..cf72699cb2bc 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -273,7 +273,7 @@ struct dma_buf_ops {
 
 /**
  * struct dma_buf - shared buffer object
- * @size: size of the buffer
+ * @size: size of the buffer; invariant over the lifetime of the buffer.
  * @file: file pointer used for sharing buffers across, and for refcounting.
  * @attachments: list of dma_buf_attachment that denotes all devices attached,
  *               protected by dma_resv lock.
@@ -405,7 +405,7 @@ struct dma_buf_attachment {
  * @exp_name:	name of the exporter - useful for debugging.
  * @owner:	pointer to exporter module - used for refcounting kernel module
  * @ops:	Attach allocator-defined dma buf ops to the new buffer
- * @size:	Size of the buffer
+ * @size:	Size of the buffer - invariant over the lifetime of the buffer
  * @flags:	mode flags for the file
  * @resv:	reservation-object, NULL to allocate default one
  * @priv:	Attach private data of allocator to this buffer
-- 
cgit v1.2.3


From c0c5a60f0f1311bcf08bbe735122096d6326fb5b Mon Sep 17 00:00:00 2001
From: Vincent Bernat <vincent@bernat.ch>
Date: Sat, 7 Nov 2020 20:35:13 +0100
Subject: net: evaluate net.ipvX.conf.all.ignore_routes_with_linkdown

Introduced in 0eeb075fad73, the "ignore_routes_with_linkdown" sysctl
ignores a route whose interface is down. It is provided as a
per-interface sysctl. However, while a "all" variant is exposed, it
was a noop since it was never evaluated. We use the usual "or" logic
for this kind of sysctls.

Tested with:

    ip link add type veth # veth0 + veth1
    ip link add type veth # veth1 + veth2
    ip link set up dev veth0
    ip link set up dev veth1 # link-status paired with veth0
    ip link set up dev veth2
    ip link set up dev veth3 # link-status paired with veth2

    # First available path
    ip -4 addr add 203.0.113.${uts#H}/24 dev veth0
    ip -6 addr add 2001:db8:1::${uts#H}/64 dev veth0

    # Second available path
    ip -4 addr add 192.0.2.${uts#H}/24 dev veth2
    ip -6 addr add 2001:db8:2::${uts#H}/64 dev veth2

    # More specific route through first path
    ip -4 route add 198.51.100.0/25 via 203.0.113.254 # via veth0
    ip -6 route add 2001:db8:3::/56 via 2001:db8:1::ff # via veth0

    # Less specific route through second path
    ip -4 route add 198.51.100.0/24 via 192.0.2.254 # via veth2
    ip -6 route add 2001:db8:3::/48 via 2001:db8:2::ff # via veth2

    # H1: enable on "all"
    # H2: enable on "veth0"
    for v in ipv4 ipv6; do
      case $uts in
        H1)
          sysctl -qw net.${v}.conf.all.ignore_routes_with_linkdown=1
          ;;
        H2)
          sysctl -qw net.${v}.conf.veth0.ignore_routes_with_linkdown=1
          ;;
      esac
    done

    set -xe
    # When veth0 is up, best route is through veth0
    ip -o route get 198.51.100.1 | grep -Fw veth0
    ip -o route get 2001:db8:3::1 | grep -Fw veth0

    # When veth0 is down, best route should be through veth2 on H1/H2,
    # but on veth0 on H2
    ip link set down dev veth1 # down veth0
    ip route show
    [ $uts != H3 ] || ip -o route get 198.51.100.1 | grep -Fw veth0
    [ $uts != H3 ] || ip -o route get 2001:db8:3::1 | grep -Fw veth0
    [ $uts = H3 ] || ip -o route get 198.51.100.1 | grep -Fw veth2
    [ $uts = H3 ] || ip -o route get 2001:db8:3::1 | grep -Fw veth2

Without this patch, the two last lines would fail on H1 (the one using
the "all" sysctl). With the patch, everything succeeds as expected.

Also document the sysctl in `ip-sysctl.rst`.

Fixes: 0eeb075fad73 ("net: ipv4 sysctl option to ignore routes when nexthop link is down")
Signed-off-by: Vincent Bernat <vincent@bernat.ch>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/ip-sysctl.rst | 3 +++
 include/linux/inetdevice.h             | 2 +-
 2 files changed, 4 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index 2aaf40b2d2cd..dd2b12a32b73 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -1554,6 +1554,9 @@ igmpv3_unsolicited_report_interval - INTEGER
 
 	Default: 1000 (1 seconds)
 
+ignore_routes_with_linkdown - BOOLEAN
+        Ignore routes whose link is down when performing a FIB lookup.
+
 promote_secondaries - BOOLEAN
 	When a primary IP address is removed from this interface
 	promote a corresponding secondary IP address instead of
diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h
index 3515ca64e638..3bbcddd22df8 100644
--- a/include/linux/inetdevice.h
+++ b/include/linux/inetdevice.h
@@ -126,7 +126,7 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev)
 	  IN_DEV_ORCONF((in_dev), ACCEPT_REDIRECTS)))
 
 #define IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) \
-	IN_DEV_CONF_GET((in_dev), IGNORE_ROUTES_WITH_LINKDOWN)
+	IN_DEV_ORCONF((in_dev), IGNORE_ROUTES_WITH_LINKDOWN)
 
 #define IN_DEV_ARPFILTER(in_dev)	IN_DEV_ORCONF((in_dev), ARPFILTER)
 #define IN_DEV_ARP_ACCEPT(in_dev)	IN_DEV_ORCONF((in_dev), ARP_ACCEPT)
-- 
cgit v1.2.3


From 1af5318c00a8acc33a90537af49b3f23f72a2c4b Mon Sep 17 00:00:00 2001
From: Vincent Bernat <vincent@bernat.ch>
Date: Sat, 7 Nov 2020 20:35:14 +0100
Subject: net: evaluate net.ipv4.conf.all.proxy_arp_pvlan

Introduced in 65324144b50b, the "proxy_arp_vlan" sysctl is a
per-interface sysctl to tune proxy ARP support for private VLANs.
While the "all" variant is exposed, it was a noop and never evaluated.
We use the usual "or" logic for this kind of sysctls.

Fixes: 65324144b50b ("net: RFC3069, private VLAN proxy arp support")
Signed-off-by: Vincent Bernat <vincent@bernat.ch>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/inetdevice.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h
index 3bbcddd22df8..53aa0343bf69 100644
--- a/include/linux/inetdevice.h
+++ b/include/linux/inetdevice.h
@@ -105,7 +105,7 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev)
 
 #define IN_DEV_LOG_MARTIANS(in_dev)	IN_DEV_ORCONF((in_dev), LOG_MARTIANS)
 #define IN_DEV_PROXY_ARP(in_dev)	IN_DEV_ORCONF((in_dev), PROXY_ARP)
-#define IN_DEV_PROXY_ARP_PVLAN(in_dev)	IN_DEV_CONF_GET(in_dev, PROXY_ARP_PVLAN)
+#define IN_DEV_PROXY_ARP_PVLAN(in_dev)	IN_DEV_ORCONF((in_dev), PROXY_ARP_PVLAN)
 #define IN_DEV_SHARED_MEDIA(in_dev)	IN_DEV_ORCONF((in_dev), SHARED_MEDIA)
 #define IN_DEV_TX_REDIRECTS(in_dev)	IN_DEV_ORCONF((in_dev), SEND_REDIRECTS)
 #define IN_DEV_SEC_REDIRECTS(in_dev)	IN_DEV_ORCONF((in_dev), \
-- 
cgit v1.2.3


From 1f78ae99790812481b7944cf40008aed5fd2ef18 Mon Sep 17 00:00:00 2001
From: Fabio Estevam <festevam@gmail.com>
Date: Tue, 10 Nov 2020 18:48:40 -0300
Subject: serial: imx: Remove unused platform data support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since 5.10-rc1 i.MX is a devicetree-only platform and the existing
platform data support in this driver was only useful for old non-devicetree
platforms.

Get rid of the platform data support since it is no longer used.

Reviewed-by: Fugang Duan <fugang.duan@nxp.com>
Acked-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Fabio Estevam <festevam@gmail.com>
Link: https://lore.kernel.org/r/20201110214840.16768-1-festevam@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/imx.c                 | 32 +++-----------------------------
 include/linux/platform_data/serial-imx.h | 15 ---------------
 2 files changed, 3 insertions(+), 44 deletions(-)
 delete mode 100644 include/linux/platform_data/serial-imx.h

(limited to 'include/linux')

diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c
index 1731d9728865..7ce38ade9a8e 100644
--- a/drivers/tty/serial/imx.c
+++ b/drivers/tty/serial/imx.c
@@ -30,7 +30,6 @@
 #include <linux/dma-mapping.h>
 
 #include <asm/irq.h>
-#include <linux/platform_data/serial-imx.h>
 #include <linux/platform_data/dma-imx.h>
 
 #include "serial_mctrl_gpio.h"
@@ -2191,10 +2190,9 @@ static struct uart_driver imx_uart_uart_driver = {
 	.cons           = IMX_CONSOLE,
 };
 
-#ifdef CONFIG_OF
 /*
- * This function returns 1 iff pdev isn't a device instatiated by dt, 0 iff it
- * could successfully get all information from dt or a negative errno.
+ * This function returns 0 iff it could successfully get all information
+ * from dt or a negative errno.
  */
 static int imx_uart_probe_dt(struct imx_port *sport,
 			     struct platform_device *pdev)
@@ -2232,28 +2230,6 @@ static int imx_uart_probe_dt(struct imx_port *sport,
 
 	return 0;
 }
-#else
-static inline int imx_uart_probe_dt(struct imx_port *sport,
-				    struct platform_device *pdev)
-{
-	return 1;
-}
-#endif
-
-static void imx_uart_probe_pdata(struct imx_port *sport,
-				 struct platform_device *pdev)
-{
-	struct imxuart_platform_data *pdata = dev_get_platdata(&pdev->dev);
-
-	sport->port.line = pdev->id;
-	sport->devdata = (struct imx_uart_data	*) pdev->id_entry->driver_data;
-
-	if (!pdata)
-		return;
-
-	if (pdata->flags & IMXUART_HAVE_RTSCTS)
-		sport->have_rtscts = 1;
-}
 
 static enum hrtimer_restart imx_trigger_start_tx(struct hrtimer *t)
 {
@@ -2295,9 +2271,7 @@ static int imx_uart_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	ret = imx_uart_probe_dt(sport, pdev);
-	if (ret > 0)
-		imx_uart_probe_pdata(sport, pdev);
-	else if (ret < 0)
+	if (ret < 0)
 		return ret;
 
 	if (sport->port.line >= ARRAY_SIZE(imx_uart_ports)) {
diff --git a/include/linux/platform_data/serial-imx.h b/include/linux/platform_data/serial-imx.h
deleted file mode 100644
index 0844b21372c7..000000000000
--- a/include/linux/platform_data/serial-imx.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Copyright (C) 2008 by Sascha Hauer <kernel@pengutronix.de>
- */
-
-#ifndef ASMARM_ARCH_UART_H
-#define ASMARM_ARCH_UART_H
-
-#define IMXUART_HAVE_RTSCTS (1<<0)
-
-struct imxuart_platform_data {
-	unsigned int flags;
-};
-
-#endif
-- 
cgit v1.2.3


From 5e844cc37a5cbaa460e68f9a989d321d63088a89 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Wed, 11 Nov 2020 20:07:10 +0100
Subject: spi: Introduce device-managed SPI controller allocation

SPI driver probing currently comprises two steps, whereas removal
comprises only one step:

    spi_alloc_master()
    spi_register_controller()

    spi_unregister_controller()

That's because spi_unregister_controller() calls device_unregister()
instead of device_del(), thereby releasing the reference on the
spi_controller which was obtained by spi_alloc_master().

An SPI driver's private data is contained in the same memory allocation
as the spi_controller struct.  Thus, once spi_unregister_controller()
has been called, the private data is inaccessible.  But some drivers
need to access it after spi_unregister_controller() to perform further
teardown steps.

Introduce devm_spi_alloc_master() and devm_spi_alloc_slave(), which
release a reference on the spi_controller struct only after the driver
has unbound, thereby keeping the memory allocation accessible.  Change
spi_unregister_controller() to not release a reference if the
spi_controller was allocated by one of these new devm functions.

The present commit is small enough to be backportable to stable.
It allows fixing drivers which use the private data in their ->remove()
hook after it's been freed.  It also allows fixing drivers which neglect
to release a reference on the spi_controller in the probe error path.

Long-term, most SPI drivers shall be moved over to the devm functions
introduced herein.  The few that can't shall be changed in a treewide
commit to explicitly release the last reference on the controller.
That commit shall amend spi_unregister_controller() to no longer release
a reference, thereby completing the migration.

As a result, the behaviour will be less surprising and more consistent
with subsystems such as IIO, which also includes the private data in the
allocation of the generic iio_dev struct, but calls device_del() in
iio_device_unregister().

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Link: https://lore.kernel.org/r/272bae2ef08abd21388c98e23729886663d19192.1605121038.git.lukas@wunner.de
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi.c       | 58 ++++++++++++++++++++++++++++++++++++++++++++++++-
 include/linux/spi/spi.h | 19 ++++++++++++++++
 2 files changed, 76 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 7566482c052c..05c75f890ace 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -2442,6 +2442,49 @@ struct spi_controller *__spi_alloc_controller(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(__spi_alloc_controller);
 
+static void devm_spi_release_controller(struct device *dev, void *ctlr)
+{
+	spi_controller_put(*(struct spi_controller **)ctlr);
+}
+
+/**
+ * __devm_spi_alloc_controller - resource-managed __spi_alloc_controller()
+ * @dev: physical device of SPI controller
+ * @size: how much zeroed driver-private data to allocate
+ * @slave: whether to allocate an SPI master (false) or SPI slave (true)
+ * Context: can sleep
+ *
+ * Allocate an SPI controller and automatically release a reference on it
+ * when @dev is unbound from its driver.  Drivers are thus relieved from
+ * having to call spi_controller_put().
+ *
+ * The arguments to this function are identical to __spi_alloc_controller().
+ *
+ * Return: the SPI controller structure on success, else NULL.
+ */
+struct spi_controller *__devm_spi_alloc_controller(struct device *dev,
+						   unsigned int size,
+						   bool slave)
+{
+	struct spi_controller **ptr, *ctlr;
+
+	ptr = devres_alloc(devm_spi_release_controller, sizeof(*ptr),
+			   GFP_KERNEL);
+	if (!ptr)
+		return NULL;
+
+	ctlr = __spi_alloc_controller(dev, size, slave);
+	if (ctlr) {
+		*ptr = ctlr;
+		devres_add(dev, ptr);
+	} else {
+		devres_free(ptr);
+	}
+
+	return ctlr;
+}
+EXPORT_SYMBOL_GPL(__devm_spi_alloc_controller);
+
 #ifdef CONFIG_OF
 static int of_spi_get_gpio_numbers(struct spi_controller *ctlr)
 {
@@ -2778,6 +2821,11 @@ int devm_spi_register_controller(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(devm_spi_register_controller);
 
+static int devm_spi_match_controller(struct device *dev, void *res, void *ctlr)
+{
+	return *(struct spi_controller **)res == ctlr;
+}
+
 static int __unregister(struct device *dev, void *null)
 {
 	spi_unregister_device(to_spi_device(dev));
@@ -2819,7 +2867,15 @@ void spi_unregister_controller(struct spi_controller *ctlr)
 	list_del(&ctlr->list);
 	mutex_unlock(&board_lock);
 
-	device_unregister(&ctlr->dev);
+	device_del(&ctlr->dev);
+
+	/* Release the last reference on the controller if its driver
+	 * has not yet been converted to devm_spi_alloc_master/slave().
+	 */
+	if (!devres_find(ctlr->dev.parent, devm_spi_release_controller,
+			 devm_spi_match_controller, ctlr))
+		put_device(&ctlr->dev);
+
 	/* free bus id */
 	mutex_lock(&board_lock);
 	if (found == ctlr)
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 99380c0825db..b390fdac1587 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -734,6 +734,25 @@ static inline struct spi_controller *spi_alloc_slave(struct device *host,
 	return __spi_alloc_controller(host, size, true);
 }
 
+struct spi_controller *__devm_spi_alloc_controller(struct device *dev,
+						   unsigned int size,
+						   bool slave);
+
+static inline struct spi_controller *devm_spi_alloc_master(struct device *dev,
+							   unsigned int size)
+{
+	return __devm_spi_alloc_controller(dev, size, false);
+}
+
+static inline struct spi_controller *devm_spi_alloc_slave(struct device *dev,
+							  unsigned int size)
+{
+	if (!IS_ENABLED(CONFIG_SPI_SLAVE))
+		return NULL;
+
+	return __devm_spi_alloc_controller(dev, size, true);
+}
+
 extern int spi_register_controller(struct spi_controller *ctlr);
 extern int devm_spi_register_controller(struct device *dev,
 					struct spi_controller *ctlr);
-- 
cgit v1.2.3


From cd2c40ff90b0e385c18f881ab5e17f7137864223 Mon Sep 17 00:00:00 2001
From: Prashant Malani <pmalani@chromium.org>
Date: Thu, 29 Oct 2020 15:27:36 -0700
Subject: platform/chrome: cros_ec: Import Type C host commands

Import the EC_CMD_TYPEC_STATUS and EC_CMD_TYPEC_DISCOVERY Chrome OS EC
host commands from the EC code base [1].

These commands can be used by the application processor to query Power
Delivery (PD) discovery information concerning connected Type C
peripherals.

Also add the EC_FEATURE_TYPEC_CMD feature flag, which is used to
determine whether these commands are supported by the EC.

[1]:
https://chromium.googlesource.com/chromiumos/platform/ec/+/refs/heads/master/include/ec_commands.h

Signed-off-by: Prashant Malani <pmalani@chromium.org>
Signed-off-by: Enric Balletbo i Serra <enric.balletbo@collabora.com>
Link: https://lore.kernel.org/r/20201029222738.482366-5-pmalani@chromium.org
---
 include/linux/platform_data/cros_ec_commands.h | 155 +++++++++++++++++++++++++
 1 file changed, 155 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h
index 1fcfe9e63cb9..7f54fdcdd8cb 100644
--- a/include/linux/platform_data/cros_ec_commands.h
+++ b/include/linux/platform_data/cros_ec_commands.h
@@ -1284,6 +1284,8 @@ enum ec_feature_code {
 	EC_FEATURE_SCP = 39,
 	/* The MCU is an Integrated Sensor Hub */
 	EC_FEATURE_ISH = 40,
+	/* New TCPMv2 TYPEC_ prefaced commands supported */
+	EC_FEATURE_TYPEC_CMD = 41,
 };
 
 #define EC_FEATURE_MASK_0(event_code) BIT(event_code % 32)
@@ -5528,6 +5530,159 @@ struct ec_response_regulator_get_voltage {
 	uint32_t voltage_mv;
 } __ec_align4;
 
+/*
+ * Gather all discovery information for the given port and partner type.
+ *
+ * Note that if discovery has not yet completed, only the currently completed
+ * responses will be filled in.   If the discovery data structures are changed
+ * in the process of the command running, BUSY will be returned.
+ *
+ * VDO field sizes are set to the maximum possible number of VDOs a VDM may
+ * contain, while the number of SVIDs here is selected to fit within the PROTO2
+ * maximum parameter size.
+ */
+#define EC_CMD_TYPEC_DISCOVERY 0x0131
+
+enum typec_partner_type {
+	TYPEC_PARTNER_SOP = 0,
+	TYPEC_PARTNER_SOP_PRIME = 1,
+};
+
+struct ec_params_typec_discovery {
+	uint8_t port;
+	uint8_t partner_type; /* enum typec_partner_type */
+} __ec_align1;
+
+struct svid_mode_info {
+	uint16_t svid;
+	uint16_t mode_count;  /* Number of modes partner sent */
+	uint32_t mode_vdo[6]; /* Max VDOs allowed after VDM header is 6 */
+};
+
+struct ec_response_typec_discovery {
+	uint8_t identity_count;    /* Number of identity VDOs partner sent */
+	uint8_t svid_count;	   /* Number of SVIDs partner sent */
+	uint16_t reserved;
+	uint32_t discovery_vdo[6]; /* Max VDOs allowed after VDM header is 6 */
+	struct svid_mode_info svids[0];
+} __ec_align1;
+
+/*
+ * Gather all status information for a port.
+ *
+ * Note: this covers many of the return fields from the deprecated
+ * EC_CMD_USB_PD_CONTROL command, except those that are redundant with the
+ * discovery data.  The "enum pd_cc_states" is defined with the deprecated
+ * EC_CMD_USB_PD_CONTROL command.
+ *
+ * This also combines in the EC_CMD_USB_PD_MUX_INFO flags.
+ */
+#define EC_CMD_TYPEC_STATUS 0x0133
+
+/*
+ * Power role.
+ *
+ * Note this is also used for PD header creation, and values align to those in
+ * the Power Delivery Specification Revision 3.0 (See
+ * 6.2.1.1.4 Port Power Role).
+ */
+enum pd_power_role {
+	PD_ROLE_SINK = 0,
+	PD_ROLE_SOURCE = 1
+};
+
+/*
+ * Data role.
+ *
+ * Note this is also used for PD header creation, and the first two values
+ * align to those in the Power Delivery Specification Revision 3.0 (See
+ * 6.2.1.1.6 Port Data Role).
+ */
+enum pd_data_role {
+	PD_ROLE_UFP = 0,
+	PD_ROLE_DFP = 1,
+	PD_ROLE_DISCONNECTED = 2,
+};
+
+enum pd_vconn_role {
+	PD_ROLE_VCONN_OFF = 0,
+	PD_ROLE_VCONN_SRC = 1,
+};
+
+/*
+ * Note: BIT(0) may be used to determine whether the polarity is CC1 or CC2,
+ * regardless of whether a debug accessory is connected.
+ */
+enum tcpc_cc_polarity {
+	/*
+	 * _CCx: is used to indicate the polarity while not connected to
+	 * a Debug Accessory.  Only one CC line will assert a resistor and
+	 * the other will be open.
+	 */
+	POLARITY_CC1 = 0,
+	POLARITY_CC2 = 1,
+
+	/*
+	 * _CCx_DTS is used to indicate the polarity while connected to a
+	 * SRC Debug Accessory.  Assert resistors on both lines.
+	 */
+	POLARITY_CC1_DTS = 2,
+	POLARITY_CC2_DTS = 3,
+
+	/*
+	 * The current TCPC code relies on these specific POLARITY values.
+	 * Adding in a check to verify if the list grows for any reason
+	 * that this will give a hint that other places need to be
+	 * adjusted.
+	 */
+	POLARITY_COUNT
+};
+
+#define PD_STATUS_EVENT_SOP_DISC_DONE		BIT(0)
+#define PD_STATUS_EVENT_SOP_PRIME_DISC_DONE	BIT(1)
+
+struct ec_params_typec_status {
+	uint8_t port;
+} __ec_align1;
+
+struct ec_response_typec_status {
+	uint8_t pd_enabled;		/* PD communication enabled - bool */
+	uint8_t dev_connected;		/* Device connected - bool */
+	uint8_t sop_connected;		/* Device is SOP PD capable - bool */
+	uint8_t source_cap_count;	/* Number of Source Cap PDOs */
+
+	uint8_t power_role;		/* enum pd_power_role */
+	uint8_t data_role;		/* enum pd_data_role */
+	uint8_t vconn_role;		/* enum pd_vconn_role */
+	uint8_t sink_cap_count;		/* Number of Sink Cap PDOs */
+
+	uint8_t polarity;		/* enum tcpc_cc_polarity */
+	uint8_t cc_state;		/* enum pd_cc_states */
+	uint8_t dp_pin;			/* DP pin mode (MODE_DP_IN_[A-E]) */
+	uint8_t mux_state;		/* USB_PD_MUX* - encoded mux state */
+
+	char tc_state[32];		/* TC state name */
+
+	uint32_t events;		/* PD_STATUS_EVENT bitmask */
+
+	/*
+	 * BCD PD revisions for partners
+	 *
+	 * The format has the PD major reversion in the upper nibble, and PD
+	 * minor version in the next nibble.  Following two nibbles are
+	 * currently 0.
+	 * ex. PD 3.2 would map to 0x3200
+	 *
+	 * PD major/minor will be 0 if no PD device is connected.
+	 */
+	uint16_t sop_revision;
+	uint16_t sop_prime_revision;
+
+	uint32_t source_cap_pdos[7];	/* Max 7 PDOs can be present */
+
+	uint32_t sink_cap_pdos[7];	/* Max 7 PDOs can be present */
+} __ec_align1;
+
 /*****************************************************************************/
 /* The command range 0x200-0x2FF is reserved for Rotor. */
 
-- 
cgit v1.2.3


From 7e890c37c25c7cbca37ff0ab292873d8146e713b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 12 Nov 2020 17:50:04 +0100
Subject: block: add a return value to set_capacity_revalidate_and_notify

Return if the function ended up sending an uevent or not.

Cc: stable@vger.kernel.org # v5.9
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Petr Vorel <pvorel@suse.cz>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/genhd.c         | 5 ++++-
 include/linux/genhd.h | 2 +-
 2 files changed, 5 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/block/genhd.c b/block/genhd.c
index 0a273211fec2..9387f050c248 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -49,7 +49,7 @@ static void disk_release_events(struct gendisk *disk);
  * Set disk capacity and notify if the size is not currently
  * zero and will not be set to zero
  */
-void set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size,
+bool set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size,
 					bool update_bdev)
 {
 	sector_t capacity = get_capacity(disk);
@@ -62,7 +62,10 @@ void set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size,
 		char *envp[] = { "RESIZE=1", NULL };
 
 		kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp);
+		return true;
 	}
+
+	return false;
 }
 
 EXPORT_SYMBOL_GPL(set_capacity_revalidate_and_notify);
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 38f23d757013..03da3f603d30 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -315,7 +315,7 @@ static inline int get_disk_ro(struct gendisk *disk)
 extern void disk_block_events(struct gendisk *disk);
 extern void disk_unblock_events(struct gendisk *disk);
 extern void disk_flush_events(struct gendisk *disk, unsigned int mask);
-void set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size,
+bool set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size,
 		bool update_bdev);
 
 /* drivers/char/random.c */
-- 
cgit v1.2.3


From af0c351cc34857ad7b254850b9392d99da46be9e Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 10 Nov 2020 20:50:02 +0100
Subject: usbnet: switch to core handling of rx/tx byte/packet counters

Use netdev->tstats instead of a member of usbnet for storing a pointer
to the per-cpu counters. This allows us to use core functionality for
statistics handling.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/usbnet.c   | 23 +++++++----------------
 include/linux/usb/usbnet.h |  6 ++----
 2 files changed, 9 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 6062dc27870e..1447da1d5729 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -304,7 +304,7 @@ static void __usbnet_status_stop_force(struct usbnet *dev)
  */
 void usbnet_skb_return (struct usbnet *dev, struct sk_buff *skb)
 {
-	struct pcpu_sw_netstats *stats64 = this_cpu_ptr(dev->stats64);
+	struct pcpu_sw_netstats *stats64 = this_cpu_ptr(dev->net->tstats);
 	unsigned long flags;
 	int	status;
 
@@ -980,15 +980,6 @@ int usbnet_set_link_ksettings(struct net_device *net,
 }
 EXPORT_SYMBOL_GPL(usbnet_set_link_ksettings);
 
-void usbnet_get_stats64(struct net_device *net, struct rtnl_link_stats64 *stats)
-{
-	struct usbnet *dev = netdev_priv(net);
-
-	netdev_stats_to_stats64(stats, &net->stats);
-	dev_fetch_sw_netstats(stats, dev->stats64);
-}
-EXPORT_SYMBOL_GPL(usbnet_get_stats64);
-
 u32 usbnet_get_link (struct net_device *net)
 {
 	struct usbnet *dev = netdev_priv(net);
@@ -1220,7 +1211,7 @@ static void tx_complete (struct urb *urb)
 	struct usbnet		*dev = entry->dev;
 
 	if (urb->status == 0) {
-		struct pcpu_sw_netstats *stats64 = this_cpu_ptr(dev->stats64);
+		struct pcpu_sw_netstats *stats64 = this_cpu_ptr(dev->net->tstats);
 		unsigned long flags;
 
 		flags = u64_stats_update_begin_irqsave(&stats64->syncp);
@@ -1596,7 +1587,7 @@ void usbnet_disconnect (struct usb_interface *intf)
 	usb_free_urb(dev->interrupt);
 	kfree(dev->padding_pkt);
 
-	free_percpu(dev->stats64);
+	free_percpu(net->tstats);
 	free_netdev(net);
 }
 EXPORT_SYMBOL_GPL(usbnet_disconnect);
@@ -1608,7 +1599,7 @@ static const struct net_device_ops usbnet_netdev_ops = {
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_set_rx_mode	= usbnet_set_rx_mode,
 	.ndo_change_mtu		= usbnet_change_mtu,
-	.ndo_get_stats64	= usbnet_get_stats64,
+	.ndo_get_stats64	= dev_get_tstats64,
 	.ndo_set_mac_address 	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 };
@@ -1671,8 +1662,8 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod)
 	dev->driver_info = info;
 	dev->driver_name = name;
 
-	dev->stats64 = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
-	if (!dev->stats64)
+	net->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
+	if (!net->tstats)
 		goto out0;
 
 	dev->msg_enable = netif_msg_init (msg_level, NETIF_MSG_DRV
@@ -1812,7 +1803,7 @@ out1:
 	 */
 	cancel_work_sync(&dev->kevent);
 	del_timer_sync(&dev->delay);
-	free_percpu(dev->stats64);
+	free_percpu(net->tstats);
 out0:
 	free_netdev(net);
 out:
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index 2e4f7721fc4e..1f6dfa977e7f 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -65,8 +65,6 @@ struct usbnet {
 	struct usb_anchor	deferred;
 	struct tasklet_struct	bh;
 
-	struct pcpu_sw_netstats __percpu *stats64;
-
 	struct work_struct	kevent;
 	unsigned long		flags;
 #		define EVENT_TX_HALT	0
@@ -285,7 +283,7 @@ extern int usbnet_status_start(struct usbnet *dev, gfp_t mem_flags);
 extern void usbnet_status_stop(struct usbnet *dev);
 
 extern void usbnet_update_max_qlen(struct usbnet *dev);
-extern void usbnet_get_stats64(struct net_device *dev,
-			       struct rtnl_link_stats64 *stats);
+
+#define usbnet_get_stats64 dev_get_tstats64
 
 #endif /* __LINUX_USB_USBNET_H */
-- 
cgit v1.2.3


From 323955a0498ccaa1263e369b91efd8f4310768b6 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 10 Nov 2020 20:51:03 +0100
Subject: net: usb: switch to dev_get_tstats64 and remove usbnet_get_stats64
 alias
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Replace usbnet_get_stats64() with new identical core function
dev_get_tstats64() in all users and remove usbnet_get_stats64().

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/aqc111.c          | 2 +-
 drivers/net/usb/asix_devices.c    | 6 +++---
 drivers/net/usb/ax88172a.c        | 2 +-
 drivers/net/usb/ax88179_178a.c    | 2 +-
 drivers/net/usb/cdc_mbim.c        | 2 +-
 drivers/net/usb/cdc_ncm.c         | 2 +-
 drivers/net/usb/dm9601.c          | 2 +-
 drivers/net/usb/int51x1.c         | 2 +-
 drivers/net/usb/mcs7830.c         | 2 +-
 drivers/net/usb/qmi_wwan.c        | 2 +-
 drivers/net/usb/rndis_host.c      | 2 +-
 drivers/net/usb/sierra_net.c      | 2 +-
 drivers/net/usb/smsc75xx.c        | 2 +-
 drivers/net/usb/smsc95xx.c        | 2 +-
 drivers/net/usb/sr9700.c          | 2 +-
 drivers/net/usb/sr9800.c          | 2 +-
 drivers/net/wireless/rndis_wlan.c | 2 +-
 include/linux/usb/usbnet.h        | 2 --
 18 files changed, 19 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index 0717c18015c9..73b97f4cc1ec 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -641,7 +641,7 @@ static const struct net_device_ops aqc111_netdev_ops = {
 	.ndo_stop		= usbnet_stop,
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
-	.ndo_get_stats64	= usbnet_get_stats64,
+	.ndo_get_stats64	= dev_get_tstats64,
 	.ndo_change_mtu		= aqc111_change_mtu,
 	.ndo_set_mac_address	= aqc111_set_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c
index ef548beba684..6e13d8165852 100644
--- a/drivers/net/usb/asix_devices.c
+++ b/drivers/net/usb/asix_devices.c
@@ -194,7 +194,7 @@ static const struct net_device_ops ax88172_netdev_ops = {
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_change_mtu		= usbnet_change_mtu,
-	.ndo_get_stats64	= usbnet_get_stats64,
+	.ndo_get_stats64	= dev_get_tstats64,
 	.ndo_set_mac_address 	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_do_ioctl		= asix_ioctl,
@@ -580,7 +580,7 @@ static const struct net_device_ops ax88772_netdev_ops = {
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_change_mtu		= usbnet_change_mtu,
-	.ndo_get_stats64	= usbnet_get_stats64,
+	.ndo_get_stats64	= dev_get_tstats64,
 	.ndo_set_mac_address 	= asix_set_mac_address,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_do_ioctl		= asix_ioctl,
@@ -1050,7 +1050,7 @@ static const struct net_device_ops ax88178_netdev_ops = {
 	.ndo_stop		= usbnet_stop,
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
-	.ndo_get_stats64	= usbnet_get_stats64,
+	.ndo_get_stats64	= dev_get_tstats64,
 	.ndo_set_mac_address 	= asix_set_mac_address,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_rx_mode	= asix_set_multicast,
diff --git a/drivers/net/usb/ax88172a.c b/drivers/net/usb/ax88172a.c
index fd3a04d98dc1..b404c9462dce 100644
--- a/drivers/net/usb/ax88172a.c
+++ b/drivers/net/usb/ax88172a.c
@@ -120,7 +120,7 @@ static const struct net_device_ops ax88172a_netdev_ops = {
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_change_mtu		= usbnet_change_mtu,
-	.ndo_get_stats64	= usbnet_get_stats64,
+	.ndo_get_stats64	= dev_get_tstats64,
 	.ndo_set_mac_address	= asix_set_mac_address,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_do_ioctl		= phy_do_ioctl_running,
diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c
index 5541f3faedbc..d650b39b6e5d 100644
--- a/drivers/net/usb/ax88179_178a.c
+++ b/drivers/net/usb/ax88179_178a.c
@@ -1031,7 +1031,7 @@ static const struct net_device_ops ax88179_netdev_ops = {
 	.ndo_stop		= usbnet_stop,
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
-	.ndo_get_stats64	= usbnet_get_stats64,
+	.ndo_get_stats64	= dev_get_tstats64,
 	.ndo_change_mtu		= ax88179_change_mtu,
 	.ndo_set_mac_address	= ax88179_set_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c
index eb100eb33de3..5db66272fc82 100644
--- a/drivers/net/usb/cdc_mbim.c
+++ b/drivers/net/usb/cdc_mbim.c
@@ -98,7 +98,7 @@ static const struct net_device_ops cdc_mbim_netdev_ops = {
 	.ndo_stop             = usbnet_stop,
 	.ndo_start_xmit       = usbnet_start_xmit,
 	.ndo_tx_timeout       = usbnet_tx_timeout,
-	.ndo_get_stats64      = usbnet_get_stats64,
+	.ndo_get_stats64      = dev_get_tstats64,
 	.ndo_change_mtu       = cdc_ncm_change_mtu,
 	.ndo_set_mac_address  = eth_mac_addr,
 	.ndo_validate_addr    = eth_validate_addr,
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 746353c51f6d..2bac57d5e8d5 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -793,7 +793,7 @@ static const struct net_device_ops cdc_ncm_netdev_ops = {
 	.ndo_start_xmit	     = usbnet_start_xmit,
 	.ndo_tx_timeout	     = usbnet_tx_timeout,
 	.ndo_set_rx_mode     = usbnet_set_rx_mode,
-	.ndo_get_stats64     = usbnet_get_stats64,
+	.ndo_get_stats64     = dev_get_tstats64,
 	.ndo_change_mtu	     = cdc_ncm_change_mtu,
 	.ndo_set_mac_address = eth_mac_addr,
 	.ndo_validate_addr   = eth_validate_addr,
diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c
index 915ac75b55fc..b5d2ac55a874 100644
--- a/drivers/net/usb/dm9601.c
+++ b/drivers/net/usb/dm9601.c
@@ -343,7 +343,7 @@ static const struct net_device_ops dm9601_netdev_ops = {
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_change_mtu		= usbnet_change_mtu,
-	.ndo_get_stats64	= usbnet_get_stats64,
+	.ndo_get_stats64	= dev_get_tstats64,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_do_ioctl 		= dm9601_ioctl,
 	.ndo_set_rx_mode	= dm9601_set_multicast,
diff --git a/drivers/net/usb/int51x1.c b/drivers/net/usb/int51x1.c
index cb5bc1a7fa5a..ed05f992c612 100644
--- a/drivers/net/usb/int51x1.c
+++ b/drivers/net/usb/int51x1.c
@@ -133,7 +133,7 @@ static const struct net_device_ops int51x1_netdev_ops = {
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_change_mtu		= usbnet_change_mtu,
-	.ndo_get_stats64	= usbnet_get_stats64,
+	.ndo_get_stats64	= dev_get_tstats64,
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_rx_mode	= int51x1_set_multicast,
diff --git a/drivers/net/usb/mcs7830.c b/drivers/net/usb/mcs7830.c
index 09bfa6a4dfbc..fc512b780d15 100644
--- a/drivers/net/usb/mcs7830.c
+++ b/drivers/net/usb/mcs7830.c
@@ -462,7 +462,7 @@ static const struct net_device_ops mcs7830_netdev_ops = {
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_change_mtu		= usbnet_change_mtu,
-	.ndo_get_stats64	= usbnet_get_stats64,
+	.ndo_get_stats64	= dev_get_tstats64,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_do_ioctl 		= mcs7830_ioctl,
 	.ndo_set_rx_mode	= mcs7830_set_multicast,
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index b9d74d9a7301..afeb09b9624e 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -575,7 +575,7 @@ static const struct net_device_ops qmi_wwan_netdev_ops = {
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_change_mtu		= usbnet_change_mtu,
-	.ndo_get_stats64	= usbnet_get_stats64,
+	.ndo_get_stats64	= dev_get_tstats64,
 	.ndo_set_mac_address	= qmi_wwan_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 };
diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c
index 6fa7a009a24a..6609d21ef894 100644
--- a/drivers/net/usb/rndis_host.c
+++ b/drivers/net/usb/rndis_host.c
@@ -279,7 +279,7 @@ static const struct net_device_ops rndis_netdev_ops = {
 	.ndo_stop		= usbnet_stop,
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
-	.ndo_get_stats64	= usbnet_get_stats64,
+	.ndo_get_stats64	= dev_get_tstats64,
 	.ndo_set_mac_address 	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 };
diff --git a/drivers/net/usb/sierra_net.c b/drivers/net/usb/sierra_net.c
index 0abd257b634c..55a244eca5ca 100644
--- a/drivers/net/usb/sierra_net.c
+++ b/drivers/net/usb/sierra_net.c
@@ -184,7 +184,7 @@ static const struct net_device_ops sierra_net_device_ops = {
 	.ndo_start_xmit         = usbnet_start_xmit,
 	.ndo_tx_timeout         = usbnet_tx_timeout,
 	.ndo_change_mtu         = usbnet_change_mtu,
-	.ndo_get_stats64        = usbnet_get_stats64,
+	.ndo_get_stats64        = dev_get_tstats64,
 	.ndo_set_mac_address    = eth_mac_addr,
 	.ndo_validate_addr      = eth_validate_addr,
 };
diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c
index 8689835a5214..4353b370249f 100644
--- a/drivers/net/usb/smsc75xx.c
+++ b/drivers/net/usb/smsc75xx.c
@@ -1435,7 +1435,7 @@ static const struct net_device_ops smsc75xx_netdev_ops = {
 	.ndo_stop		= usbnet_stop,
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
-	.ndo_get_stats64	= usbnet_get_stats64,
+	.ndo_get_stats64	= dev_get_tstats64,
 	.ndo_change_mtu		= smsc75xx_change_mtu,
 	.ndo_set_mac_address 	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index ea0d5f04dc3a..4c8ee1cff4d4 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -1041,7 +1041,7 @@ static const struct net_device_ops smsc95xx_netdev_ops = {
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_change_mtu		= usbnet_change_mtu,
-	.ndo_get_stats64	= usbnet_get_stats64,
+	.ndo_get_stats64	= dev_get_tstats64,
 	.ndo_set_mac_address 	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_do_ioctl 		= smsc95xx_ioctl,
diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c
index e04c8054c2cf..878557ad03ad 100644
--- a/drivers/net/usb/sr9700.c
+++ b/drivers/net/usb/sr9700.c
@@ -308,7 +308,7 @@ static const struct net_device_ops sr9700_netdev_ops = {
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_change_mtu		= usbnet_change_mtu,
-	.ndo_get_stats64	= usbnet_get_stats64,
+	.ndo_get_stats64	= dev_get_tstats64,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_do_ioctl		= sr9700_ioctl,
 	.ndo_set_rx_mode	= sr9700_set_multicast,
diff --git a/drivers/net/usb/sr9800.c b/drivers/net/usb/sr9800.c
index 681e0def6356..da56735d7755 100644
--- a/drivers/net/usb/sr9800.c
+++ b/drivers/net/usb/sr9800.c
@@ -681,7 +681,7 @@ static const struct net_device_ops sr9800_netdev_ops = {
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
 	.ndo_change_mtu		= usbnet_change_mtu,
-	.ndo_get_stats64	= usbnet_get_stats64,
+	.ndo_get_stats64	= dev_get_tstats64,
 	.ndo_set_mac_address	= sr_set_mac_address,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_do_ioctl		= sr_ioctl,
diff --git a/drivers/net/wireless/rndis_wlan.c b/drivers/net/wireless/rndis_wlan.c
index 75b5d545b49e..9fe77556858e 100644
--- a/drivers/net/wireless/rndis_wlan.c
+++ b/drivers/net/wireless/rndis_wlan.c
@@ -3379,7 +3379,7 @@ static const struct net_device_ops rndis_wlan_netdev_ops = {
 	.ndo_stop		= usbnet_stop,
 	.ndo_start_xmit		= usbnet_start_xmit,
 	.ndo_tx_timeout		= usbnet_tx_timeout,
-	.ndo_get_stats64	= usbnet_get_stats64,
+	.ndo_get_stats64	= dev_get_tstats64,
 	.ndo_set_mac_address 	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_rx_mode	= rndis_wlan_set_multicast_list,
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index 1f6dfa977e7f..88a7673894d5 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -284,6 +284,4 @@ extern void usbnet_status_stop(struct usbnet *dev);
 
 extern void usbnet_update_max_qlen(struct usbnet *dev);
 
-#define usbnet_get_stats64 dev_get_tstats64
-
 #endif /* __LINUX_USB_USBNET_H */
-- 
cgit v1.2.3


From 6d94e741a8ff818e5518da8257f5ca0aaed1f269 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Tue, 10 Nov 2020 19:12:11 -0800
Subject: bpf: Support for pointers beyond pkt_end.

This patch adds the verifier support to recognize inlined branch conditions.
The LLVM knows that the branch evaluates to the same value, but the verifier
couldn't track it. Hence causing valid programs to be rejected.
The potential LLVM workaround: https://reviews.llvm.org/D87428
can have undesired side effects, since LLVM doesn't know that
skb->data/data_end are being compared. LLVM has to introduce extra boolean
variable and use inline_asm trick to force easier for the verifier assembly.

Instead teach the verifier to recognize that
r1 = skb->data;
r1 += 10;
r2 = skb->data_end;
if (r1 > r2) {
  here r1 points beyond packet_end and
  subsequent
  if (r1 > r2) // always evaluates to "true".
}

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20201111031213.25109-2-alexei.starovoitov@gmail.com
---
 include/linux/bpf_verifier.h |   2 +-
 kernel/bpf/verifier.c        | 129 +++++++++++++++++++++++++++++++++++--------
 2 files changed, 108 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index e83ef6f6bf43..306869d4743b 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -45,7 +45,7 @@ struct bpf_reg_state {
 	enum bpf_reg_type type;
 	union {
 		/* valid when type == PTR_TO_PACKET */
-		u16 range;
+		int range;
 
 		/* valid when type == CONST_PTR_TO_MAP | PTR_TO_MAP_VALUE |
 		 *   PTR_TO_MAP_VALUE_OR_NULL
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 10da26e55130..7b1f85aa9741 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2739,7 +2739,9 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off,
 			regno);
 		return -EACCES;
 	}
-	err = __check_mem_access(env, regno, off, size, reg->range,
+
+	err = reg->range < 0 ? -EINVAL :
+	      __check_mem_access(env, regno, off, size, reg->range,
 				 zero_size_allowed);
 	if (err) {
 		verbose(env, "R%d offset is outside of the packet\n", regno);
@@ -4697,6 +4699,32 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env)
 		__clear_all_pkt_pointers(env, vstate->frame[i]);
 }
 
+enum {
+	AT_PKT_END = -1,
+	BEYOND_PKT_END = -2,
+};
+
+static void mark_pkt_end(struct bpf_verifier_state *vstate, int regn, bool range_open)
+{
+	struct bpf_func_state *state = vstate->frame[vstate->curframe];
+	struct bpf_reg_state *reg = &state->regs[regn];
+
+	if (reg->type != PTR_TO_PACKET)
+		/* PTR_TO_PACKET_META is not supported yet */
+		return;
+
+	/* The 'reg' is pkt > pkt_end or pkt >= pkt_end.
+	 * How far beyond pkt_end it goes is unknown.
+	 * if (!range_open) it's the case of pkt >= pkt_end
+	 * if (range_open) it's the case of pkt > pkt_end
+	 * hence this pointer is at least 1 byte bigger than pkt_end
+	 */
+	if (range_open)
+		reg->range = BEYOND_PKT_END;
+	else
+		reg->range = AT_PKT_END;
+}
+
 static void release_reg_references(struct bpf_verifier_env *env,
 				   struct bpf_func_state *state,
 				   int ref_obj_id)
@@ -6708,7 +6736,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 
 static void __find_good_pkt_pointers(struct bpf_func_state *state,
 				     struct bpf_reg_state *dst_reg,
-				     enum bpf_reg_type type, u16 new_range)
+				     enum bpf_reg_type type, int new_range)
 {
 	struct bpf_reg_state *reg;
 	int i;
@@ -6733,8 +6761,7 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate,
 				   enum bpf_reg_type type,
 				   bool range_right_open)
 {
-	u16 new_range;
-	int i;
+	int new_range, i;
 
 	if (dst_reg->off < 0 ||
 	    (dst_reg->off == 0 && range_right_open))
@@ -6985,6 +7012,67 @@ static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode,
 	return is_branch64_taken(reg, val, opcode);
 }
 
+static int flip_opcode(u32 opcode)
+{
+	/* How can we transform "a <op> b" into "b <op> a"? */
+	static const u8 opcode_flip[16] = {
+		/* these stay the same */
+		[BPF_JEQ  >> 4] = BPF_JEQ,
+		[BPF_JNE  >> 4] = BPF_JNE,
+		[BPF_JSET >> 4] = BPF_JSET,
+		/* these swap "lesser" and "greater" (L and G in the opcodes) */
+		[BPF_JGE  >> 4] = BPF_JLE,
+		[BPF_JGT  >> 4] = BPF_JLT,
+		[BPF_JLE  >> 4] = BPF_JGE,
+		[BPF_JLT  >> 4] = BPF_JGT,
+		[BPF_JSGE >> 4] = BPF_JSLE,
+		[BPF_JSGT >> 4] = BPF_JSLT,
+		[BPF_JSLE >> 4] = BPF_JSGE,
+		[BPF_JSLT >> 4] = BPF_JSGT
+	};
+	return opcode_flip[opcode >> 4];
+}
+
+static int is_pkt_ptr_branch_taken(struct bpf_reg_state *dst_reg,
+				   struct bpf_reg_state *src_reg,
+				   u8 opcode)
+{
+	struct bpf_reg_state *pkt;
+
+	if (src_reg->type == PTR_TO_PACKET_END) {
+		pkt = dst_reg;
+	} else if (dst_reg->type == PTR_TO_PACKET_END) {
+		pkt = src_reg;
+		opcode = flip_opcode(opcode);
+	} else {
+		return -1;
+	}
+
+	if (pkt->range >= 0)
+		return -1;
+
+	switch (opcode) {
+	case BPF_JLE:
+		/* pkt <= pkt_end */
+		fallthrough;
+	case BPF_JGT:
+		/* pkt > pkt_end */
+		if (pkt->range == BEYOND_PKT_END)
+			/* pkt has at last one extra byte beyond pkt_end */
+			return opcode == BPF_JGT;
+		break;
+	case BPF_JLT:
+		/* pkt < pkt_end */
+		fallthrough;
+	case BPF_JGE:
+		/* pkt >= pkt_end */
+		if (pkt->range == BEYOND_PKT_END || pkt->range == AT_PKT_END)
+			return opcode == BPF_JGE;
+		break;
+	}
+	return -1;
+}
+
 /* Adjusts the register min/max values in the case that the dst_reg is the
  * variable register that we are working on, and src_reg is a constant or we're
  * simply doing a BPF_K check.
@@ -7148,23 +7236,7 @@ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
 				u64 val, u32 val32,
 				u8 opcode, bool is_jmp32)
 {
-	/* How can we transform "a <op> b" into "b <op> a"? */
-	static const u8 opcode_flip[16] = {
-		/* these stay the same */
-		[BPF_JEQ  >> 4] = BPF_JEQ,
-		[BPF_JNE  >> 4] = BPF_JNE,
-		[BPF_JSET >> 4] = BPF_JSET,
-		/* these swap "lesser" and "greater" (L and G in the opcodes) */
-		[BPF_JGE  >> 4] = BPF_JLE,
-		[BPF_JGT  >> 4] = BPF_JLT,
-		[BPF_JLE  >> 4] = BPF_JGE,
-		[BPF_JLT  >> 4] = BPF_JGT,
-		[BPF_JSGE >> 4] = BPF_JSLE,
-		[BPF_JSGT >> 4] = BPF_JSLT,
-		[BPF_JSLE >> 4] = BPF_JSGE,
-		[BPF_JSLT >> 4] = BPF_JSGT
-	};
-	opcode = opcode_flip[opcode >> 4];
+	opcode = flip_opcode(opcode);
 	/* This uses zero as "not present in table"; luckily the zero opcode,
 	 * BPF_JA, can't get here.
 	 */
@@ -7346,6 +7418,7 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn,
 			/* pkt_data' > pkt_end, pkt_meta' > pkt_data */
 			find_good_pkt_pointers(this_branch, dst_reg,
 					       dst_reg->type, false);
+			mark_pkt_end(other_branch, insn->dst_reg, true);
 		} else if ((dst_reg->type == PTR_TO_PACKET_END &&
 			    src_reg->type == PTR_TO_PACKET) ||
 			   (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
@@ -7353,6 +7426,7 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn,
 			/* pkt_end > pkt_data', pkt_data > pkt_meta' */
 			find_good_pkt_pointers(other_branch, src_reg,
 					       src_reg->type, true);
+			mark_pkt_end(this_branch, insn->src_reg, false);
 		} else {
 			return false;
 		}
@@ -7365,6 +7439,7 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn,
 			/* pkt_data' < pkt_end, pkt_meta' < pkt_data */
 			find_good_pkt_pointers(other_branch, dst_reg,
 					       dst_reg->type, true);
+			mark_pkt_end(this_branch, insn->dst_reg, false);
 		} else if ((dst_reg->type == PTR_TO_PACKET_END &&
 			    src_reg->type == PTR_TO_PACKET) ||
 			   (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
@@ -7372,6 +7447,7 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn,
 			/* pkt_end < pkt_data', pkt_data > pkt_meta' */
 			find_good_pkt_pointers(this_branch, src_reg,
 					       src_reg->type, false);
+			mark_pkt_end(other_branch, insn->src_reg, true);
 		} else {
 			return false;
 		}
@@ -7384,6 +7460,7 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn,
 			/* pkt_data' >= pkt_end, pkt_meta' >= pkt_data */
 			find_good_pkt_pointers(this_branch, dst_reg,
 					       dst_reg->type, true);
+			mark_pkt_end(other_branch, insn->dst_reg, false);
 		} else if ((dst_reg->type == PTR_TO_PACKET_END &&
 			    src_reg->type == PTR_TO_PACKET) ||
 			   (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
@@ -7391,6 +7468,7 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn,
 			/* pkt_end >= pkt_data', pkt_data >= pkt_meta' */
 			find_good_pkt_pointers(other_branch, src_reg,
 					       src_reg->type, false);
+			mark_pkt_end(this_branch, insn->src_reg, true);
 		} else {
 			return false;
 		}
@@ -7403,6 +7481,7 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn,
 			/* pkt_data' <= pkt_end, pkt_meta' <= pkt_data */
 			find_good_pkt_pointers(other_branch, dst_reg,
 					       dst_reg->type, false);
+			mark_pkt_end(this_branch, insn->dst_reg, true);
 		} else if ((dst_reg->type == PTR_TO_PACKET_END &&
 			    src_reg->type == PTR_TO_PACKET) ||
 			   (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
@@ -7410,6 +7489,7 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn,
 			/* pkt_end <= pkt_data', pkt_data <= pkt_meta' */
 			find_good_pkt_pointers(this_branch, src_reg,
 					       src_reg->type, true);
+			mark_pkt_end(other_branch, insn->src_reg, false);
 		} else {
 			return false;
 		}
@@ -7509,6 +7589,10 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 				       src_reg->var_off.value,
 				       opcode,
 				       is_jmp32);
+	} else if (reg_is_pkt_pointer_any(dst_reg) &&
+		   reg_is_pkt_pointer_any(src_reg) &&
+		   !is_jmp32) {
+		pred = is_pkt_ptr_branch_taken(dst_reg, src_reg, opcode);
 	}
 
 	if (pred >= 0) {
@@ -7517,7 +7601,8 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 		 */
 		if (!__is_pointer_value(false, dst_reg))
 			err = mark_chain_precision(env, insn->dst_reg);
-		if (BPF_SRC(insn->code) == BPF_X && !err)
+		if (BPF_SRC(insn->code) == BPF_X && !err &&
+		    !__is_pointer_value(false, src_reg))
 			err = mark_chain_precision(env, insn->src_reg);
 		if (err)
 			return err;
-- 
cgit v1.2.3


From 8d0dd23c6c78d140ed2132f523592ddb4cea839f Mon Sep 17 00:00:00 2001
From: Tal Zussman <tz2294@columbia.edu>
Date: Thu, 12 Nov 2020 16:56:57 -0500
Subject: syscalls: Fix file comments for syscalls implemented in kernel/sys.c

The relevant syscalls were previously moved from kernel/timer.c to kernel/sys.c,
but the comments weren't updated to reflect this change.

Fixing these comments messes up the alphabetical ordering of syscalls by
filename. This could be fixed by merging the two groups of kernel/sys.c syscalls,
but that would require reordering the syscalls and renumbering them to maintain
the numerical order in unistd.h.

Signed-off-by: Tal Zussman <tz2294@columbia.edu>
Link: https://lore.kernel.org/r/20201112215657.GA4539@charmander'
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 include/linux/syscalls.h          | 2 +-
 include/uapi/asm-generic/unistd.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 37bea07c12f2..629870fbb2c9 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -744,7 +744,7 @@ asmlinkage long sys_settimeofday(struct __kernel_old_timeval __user *tv,
 asmlinkage long sys_adjtimex(struct __kernel_timex __user *txc_p);
 asmlinkage long sys_adjtimex_time32(struct old_timex32 __user *txc_p);
 
-/* kernel/timer.c */
+/* kernel/sys.c */
 asmlinkage long sys_getpid(void);
 asmlinkage long sys_getppid(void);
 asmlinkage long sys_getuid(void);
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 2056318988f7..fc48c64700eb 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -517,7 +517,7 @@ __SC_COMP(__NR_settimeofday, sys_settimeofday, compat_sys_settimeofday)
 __SC_3264(__NR_adjtimex, sys_adjtimex_time32, sys_adjtimex)
 #endif
 
-/* kernel/timer.c */
+/* kernel/sys.c */
 #define __NR_getpid 172
 __SYSCALL(__NR_getpid, sys_getpid)
 #define __NR_getppid 173
-- 
cgit v1.2.3


From a609c58086e381c13bdad1ba97e6510a13d465e7 Mon Sep 17 00:00:00 2001
From: Lee Jones <lee.jones@linaro.org>
Date: Thu, 12 Nov 2020 10:58:55 +0000
Subject: tty: serial: 8250: 8250_port: Move prototypes to shared location
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fixes the following W=1 kernel build warning(s):

 drivers/tty/serial/8250/8250_port.c:349:14: warning: no previous prototype for ‘au_serial_in’ [-Wmissing-prototypes]
 drivers/tty/serial/8250/8250_port.c:359:6: warning: no previous prototype for ‘au_serial_out’ [-Wmissing-prototypes]

Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jiri Slaby <jirislaby@kernel.org>
Cc: Mike Hudson <Exoray@isys.ca>
Cc: linux-serial@vger.kernel.org
Signed-off-by: Lee Jones <lee.jones@linaro.org>
Link: https://lore.kernel.org/r/20201112105857.2078977-3-lee.jones@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_early.c | 3 ---
 include/linux/serial_8250.h          | 5 +++++
 2 files changed, 5 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/serial/8250/8250_early.c b/drivers/tty/serial/8250/8250_early.c
index 70d7826788f5..c171ce6db691 100644
--- a/drivers/tty/serial/8250/8250_early.c
+++ b/drivers/tty/serial/8250/8250_early.c
@@ -204,9 +204,6 @@ OF_EARLYCON_DECLARE(omap8250, "ti,omap4-uart", early_omap8250_setup);
 
 #ifdef CONFIG_SERIAL_8250_RT288X
 
-unsigned int au_serial_in(struct uart_port *p, int offset);
-void au_serial_out(struct uart_port *p, int offset, int value);
-
 static int __init early_au_setup(struct earlycon_device *dev, const char *opt)
 {
 	dev->port.serial_in = au_serial_in;
diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h
index 2b70f736b091..9e655055112d 100644
--- a/include/linux/serial_8250.h
+++ b/include/linux/serial_8250.h
@@ -187,4 +187,9 @@ extern void serial8250_set_isa_configurator(void (*v)
 					(int port, struct uart_port *up,
 						u32 *capabilities));
 
+#ifdef CONFIG_SERIAL_8250_RT288X
+unsigned int au_serial_in(struct uart_port *p, int offset);
+void au_serial_out(struct uart_port *p, int offset, int value);
+#endif
+
 #endif
-- 
cgit v1.2.3


From 423f16108c9d832bd96059d5c882c8ef6d76eb96 Mon Sep 17 00:00:00 2001
From: KP Singh <kpsingh@google.com>
Date: Fri, 13 Nov 2020 00:59:29 +0000
Subject: bpf: Augment the set of sleepable LSM hooks

Update the set of sleepable hooks with the ones that do not trigger
a warning with might_fault() when exercised with the correct kernel
config options enabled, i.e.

	DEBUG_ATOMIC_SLEEP=y
	LOCKDEP=y
	PROVE_LOCKING=y

This means that a sleepable LSM eBPF program can be attached to these
LSM hooks. A new helper method bpf_lsm_is_sleepable_hook is added and
the set is maintained locally in bpf_lsm.c

Signed-off-by: KP Singh <kpsingh@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20201113005930.541956-2-kpsingh@chromium.org
---
 include/linux/bpf_lsm.h |  7 +++++
 kernel/bpf/bpf_lsm.c    | 81 +++++++++++++++++++++++++++++++++++++++++++++++++
 kernel/bpf/verifier.c   | 16 +---------
 3 files changed, 89 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf_lsm.h b/include/linux/bpf_lsm.h
index 73226181b744..0d1c33ace398 100644
--- a/include/linux/bpf_lsm.h
+++ b/include/linux/bpf_lsm.h
@@ -27,6 +27,8 @@ extern struct lsm_blob_sizes bpf_lsm_blob_sizes;
 int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog,
 			const struct bpf_prog *prog);
 
+bool bpf_lsm_is_sleepable_hook(u32 btf_id);
+
 static inline struct bpf_storage_blob *bpf_inode(
 	const struct inode *inode)
 {
@@ -54,6 +56,11 @@ void bpf_task_storage_free(struct task_struct *task);
 
 #else /* !CONFIG_BPF_LSM */
 
+static inline bool bpf_lsm_is_sleepable_hook(u32 btf_id)
+{
+	return false;
+}
+
 static inline int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog,
 				      const struct bpf_prog *prog)
 {
diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
index e92c51bebb47..aed74b853415 100644
--- a/kernel/bpf/bpf_lsm.c
+++ b/kernel/bpf/bpf_lsm.c
@@ -13,6 +13,7 @@
 #include <linux/bpf_verifier.h>
 #include <net/bpf_sk_storage.h>
 #include <linux/bpf_local_storage.h>
+#include <linux/btf_ids.h>
 
 /* For every LSM hook that allows attachment of BPF programs, declare a nop
  * function where a BPF program can be attached.
@@ -72,6 +73,86 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	}
 }
 
+/* The set of hooks which are called without pagefaults disabled and are allowed
+ * to "sleep" and thus can be used for sleeable BPF programs.
+ */
+BTF_SET_START(sleepable_lsm_hooks)
+BTF_ID(func, bpf_lsm_bpf)
+BTF_ID(func, bpf_lsm_bpf_map)
+BTF_ID(func, bpf_lsm_bpf_map_alloc_security)
+BTF_ID(func, bpf_lsm_bpf_map_free_security)
+BTF_ID(func, bpf_lsm_bpf_prog)
+BTF_ID(func, bpf_lsm_bprm_check_security)
+BTF_ID(func, bpf_lsm_bprm_committed_creds)
+BTF_ID(func, bpf_lsm_bprm_committing_creds)
+BTF_ID(func, bpf_lsm_bprm_creds_for_exec)
+BTF_ID(func, bpf_lsm_bprm_creds_from_file)
+BTF_ID(func, bpf_lsm_capget)
+BTF_ID(func, bpf_lsm_capset)
+BTF_ID(func, bpf_lsm_cred_prepare)
+BTF_ID(func, bpf_lsm_file_ioctl)
+BTF_ID(func, bpf_lsm_file_lock)
+BTF_ID(func, bpf_lsm_file_open)
+BTF_ID(func, bpf_lsm_file_receive)
+BTF_ID(func, bpf_lsm_inet_conn_established)
+BTF_ID(func, bpf_lsm_inode_create)
+BTF_ID(func, bpf_lsm_inode_free_security)
+BTF_ID(func, bpf_lsm_inode_getattr)
+BTF_ID(func, bpf_lsm_inode_getxattr)
+BTF_ID(func, bpf_lsm_inode_mknod)
+BTF_ID(func, bpf_lsm_inode_need_killpriv)
+BTF_ID(func, bpf_lsm_inode_post_setxattr)
+BTF_ID(func, bpf_lsm_inode_readlink)
+BTF_ID(func, bpf_lsm_inode_rename)
+BTF_ID(func, bpf_lsm_inode_rmdir)
+BTF_ID(func, bpf_lsm_inode_setattr)
+BTF_ID(func, bpf_lsm_inode_setxattr)
+BTF_ID(func, bpf_lsm_inode_symlink)
+BTF_ID(func, bpf_lsm_inode_unlink)
+BTF_ID(func, bpf_lsm_kernel_module_request)
+BTF_ID(func, bpf_lsm_kernfs_init_security)
+BTF_ID(func, bpf_lsm_key_free)
+BTF_ID(func, bpf_lsm_mmap_file)
+BTF_ID(func, bpf_lsm_netlink_send)
+BTF_ID(func, bpf_lsm_path_notify)
+BTF_ID(func, bpf_lsm_release_secctx)
+BTF_ID(func, bpf_lsm_sb_alloc_security)
+BTF_ID(func, bpf_lsm_sb_eat_lsm_opts)
+BTF_ID(func, bpf_lsm_sb_kern_mount)
+BTF_ID(func, bpf_lsm_sb_mount)
+BTF_ID(func, bpf_lsm_sb_remount)
+BTF_ID(func, bpf_lsm_sb_set_mnt_opts)
+BTF_ID(func, bpf_lsm_sb_show_options)
+BTF_ID(func, bpf_lsm_sb_statfs)
+BTF_ID(func, bpf_lsm_sb_umount)
+BTF_ID(func, bpf_lsm_settime)
+BTF_ID(func, bpf_lsm_socket_accept)
+BTF_ID(func, bpf_lsm_socket_bind)
+BTF_ID(func, bpf_lsm_socket_connect)
+BTF_ID(func, bpf_lsm_socket_create)
+BTF_ID(func, bpf_lsm_socket_getpeername)
+BTF_ID(func, bpf_lsm_socket_getpeersec_dgram)
+BTF_ID(func, bpf_lsm_socket_getsockname)
+BTF_ID(func, bpf_lsm_socket_getsockopt)
+BTF_ID(func, bpf_lsm_socket_listen)
+BTF_ID(func, bpf_lsm_socket_post_create)
+BTF_ID(func, bpf_lsm_socket_recvmsg)
+BTF_ID(func, bpf_lsm_socket_sendmsg)
+BTF_ID(func, bpf_lsm_socket_shutdown)
+BTF_ID(func, bpf_lsm_socket_socketpair)
+BTF_ID(func, bpf_lsm_syslog)
+BTF_ID(func, bpf_lsm_task_alloc)
+BTF_ID(func, bpf_lsm_task_getsecid)
+BTF_ID(func, bpf_lsm_task_prctl)
+BTF_ID(func, bpf_lsm_task_setscheduler)
+BTF_ID(func, bpf_lsm_task_to_inode)
+BTF_SET_END(sleepable_lsm_hooks)
+
+bool bpf_lsm_is_sleepable_hook(u32 btf_id)
+{
+	return btf_id_set_contains(&sleepable_lsm_hooks, btf_id);
+}
+
 const struct bpf_prog_ops lsm_prog_ops = {
 };
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 7b1f85aa9741..fb2943ea715d 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -11562,20 +11562,6 @@ static int check_attach_modify_return(unsigned long addr, const char *func_name)
 	return -EINVAL;
 }
 
-/* non exhaustive list of sleepable bpf_lsm_*() functions */
-BTF_SET_START(btf_sleepable_lsm_hooks)
-#ifdef CONFIG_BPF_LSM
-BTF_ID(func, bpf_lsm_bprm_committed_creds)
-#else
-BTF_ID_UNUSED
-#endif
-BTF_SET_END(btf_sleepable_lsm_hooks)
-
-static int check_sleepable_lsm_hook(u32 btf_id)
-{
-	return btf_id_set_contains(&btf_sleepable_lsm_hooks, btf_id);
-}
-
 /* list of non-sleepable functions that are otherwise on
  * ALLOW_ERROR_INJECTION list
  */
@@ -11797,7 +11783,7 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
 				/* LSM progs check that they are attached to bpf_lsm_*() funcs.
 				 * Only some of them are sleepable.
 				 */
-				if (check_sleepable_lsm_hook(btf_id))
+				if (bpf_lsm_is_sleepable_hook(btf_id))
 					ret = 0;
 				break;
 			default:
-- 
cgit v1.2.3


From d19ad0775dcd64b49eecf4fa79c17959ebfbd26b Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Wed, 28 Oct 2020 17:42:17 -0400
Subject: ftrace: Have the callbacks receive a struct ftrace_regs instead of
 pt_regs

In preparation to have arguments of a function passed to callbacks attached
to functions as default, change the default callback prototype to receive a
struct ftrace_regs as the forth parameter instead of a pt_regs.

For callbacks that set the FL_SAVE_REGS flag in their ftrace_ops flags, they
will now need to get the pt_regs via a ftrace_get_regs() helper call. If
this is called by a callback that their ftrace_ops did not have a
FL_SAVE_REGS flag set, it that helper function will return NULL.

This will allow the ftrace_regs to hold enough just to get the parameters
and stack pointer, but without the worry that callbacks may have a pt_regs
that is not completely filled.

Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 arch/csky/kernel/probes/ftrace.c     |  4 +++-
 arch/nds32/kernel/ftrace.c           |  4 ++--
 arch/parisc/kernel/ftrace.c          |  8 +++++---
 arch/powerpc/kernel/kprobes-ftrace.c |  4 +++-
 arch/s390/kernel/ftrace.c            |  4 +++-
 arch/x86/kernel/kprobes/ftrace.c     |  3 ++-
 fs/pstore/ftrace.c                   |  2 +-
 include/linux/ftrace.h               | 16 ++++++++++++++--
 include/linux/kprobes.h              |  2 +-
 kernel/livepatch/patch.c             |  3 ++-
 kernel/trace/ftrace.c                | 27 +++++++++++++++------------
 kernel/trace/trace_event_perf.c      |  2 +-
 kernel/trace/trace_events.c          |  2 +-
 kernel/trace/trace_functions.c       |  9 ++++-----
 kernel/trace/trace_irqsoff.c         |  2 +-
 kernel/trace/trace_sched_wakeup.c    |  2 +-
 kernel/trace/trace_selftest.c        | 20 +++++++++++---------
 kernel/trace/trace_stack.c           |  2 +-
 18 files changed, 71 insertions(+), 45 deletions(-)

(limited to 'include/linux')

diff --git a/arch/csky/kernel/probes/ftrace.c b/arch/csky/kernel/probes/ftrace.c
index f30b179924ef..ae2b1c7b3b5c 100644
--- a/arch/csky/kernel/probes/ftrace.c
+++ b/arch/csky/kernel/probes/ftrace.c
@@ -11,17 +11,19 @@ int arch_check_ftrace_location(struct kprobe *p)
 
 /* Ftrace callback handler for kprobes -- called under preepmt disabed */
 void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
-			   struct ftrace_ops *ops, struct pt_regs *regs)
+			   struct ftrace_ops *ops, struct ftrace_regs *fregs)
 {
 	int bit;
 	bool lr_saver = false;
 	struct kprobe *p;
 	struct kprobe_ctlblk *kcb;
+	struct pt_regs *regs;
 
 	bit = ftrace_test_recursion_trylock(ip, parent_ip);
 	if (bit < 0)
 		return;
 
+	regs = ftrace_get_regs(fregs);
 	preempt_disable_notrace();
 	p = get_kprobe((kprobe_opcode_t *)ip);
 	if (!p) {
diff --git a/arch/nds32/kernel/ftrace.c b/arch/nds32/kernel/ftrace.c
index 3763b3f8c3db..414f8a780cc3 100644
--- a/arch/nds32/kernel/ftrace.c
+++ b/arch/nds32/kernel/ftrace.c
@@ -10,7 +10,7 @@ extern void (*ftrace_trace_function)(unsigned long, unsigned long,
 extern void ftrace_graph_caller(void);
 
 noinline void __naked ftrace_stub(unsigned long ip, unsigned long parent_ip,
-				  struct ftrace_ops *op, struct pt_regs *regs)
+				  struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
 	__asm__ ("");  /* avoid to optimize as pure function */
 }
@@ -38,7 +38,7 @@ EXPORT_SYMBOL(_mcount);
 #else /* CONFIG_DYNAMIC_FTRACE */
 
 noinline void __naked ftrace_stub(unsigned long ip, unsigned long parent_ip,
-				  struct ftrace_ops *op, struct pt_regs *regs)
+				  struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
 	__asm__ ("");  /* avoid to optimize as pure function */
 }
diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c
index 1c5d3732bda2..0a1e75af5382 100644
--- a/arch/parisc/kernel/ftrace.c
+++ b/arch/parisc/kernel/ftrace.c
@@ -51,7 +51,7 @@ static void __hot prepare_ftrace_return(unsigned long *parent,
 void notrace __hot ftrace_function_trampoline(unsigned long parent,
 				unsigned long self_addr,
 				unsigned long org_sp_gr3,
-				struct pt_regs *regs)
+				struct ftrace_regs *fregs)
 {
 #ifndef CONFIG_DYNAMIC_FTRACE
 	extern ftrace_func_t ftrace_trace_function;
@@ -61,7 +61,7 @@ void notrace __hot ftrace_function_trampoline(unsigned long parent,
 	if (function_trace_op->flags & FTRACE_OPS_FL_ENABLED &&
 	    ftrace_trace_function != ftrace_stub)
 		ftrace_trace_function(self_addr, parent,
-				function_trace_op, regs);
+				function_trace_op, fregs);
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	if (dereference_function_descriptor(ftrace_graph_return) !=
@@ -204,9 +204,10 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
 
 #ifdef CONFIG_KPROBES_ON_FTRACE
 void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
-			   struct ftrace_ops *ops, struct pt_regs *regs)
+			   struct ftrace_ops *ops, struct ftrace_regs *fregs)
 {
 	struct kprobe_ctlblk *kcb;
+	struct pt_regs *regs;
 	struct kprobe *p;
 	int bit;
 
@@ -214,6 +215,7 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 	if (bit < 0)
 		return;
 
+	regs = ftrace_get_regs(fregs);
 	preempt_disable_notrace();
 	p = get_kprobe((kprobe_opcode_t *)ip);
 	if (unlikely(!p) || kprobe_disabled(p))
diff --git a/arch/powerpc/kernel/kprobes-ftrace.c b/arch/powerpc/kernel/kprobes-ftrace.c
index fdfee39938ea..660138f6c4b2 100644
--- a/arch/powerpc/kernel/kprobes-ftrace.c
+++ b/arch/powerpc/kernel/kprobes-ftrace.c
@@ -14,16 +14,18 @@
 
 /* Ftrace callback handler for kprobes */
 void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip,
-			   struct ftrace_ops *ops, struct pt_regs *regs)
+			   struct ftrace_ops *ops, struct ftrace_regs *fregs)
 {
 	struct kprobe *p;
 	struct kprobe_ctlblk *kcb;
+	struct pt_regs *regs;
 	int bit;
 
 	bit = ftrace_test_recursion_trylock(nip, parent_nip);
 	if (bit < 0)
 		return;
 
+	regs = ftrace_get_regs(fregs);
 	preempt_disable_notrace();
 	p = get_kprobe((kprobe_opcode_t *)nip);
 	if (unlikely(!p) || kprobe_disabled(p))
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 657c1ab45408..67b80f4412f9 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -198,9 +198,10 @@ int ftrace_disable_ftrace_graph_caller(void)
 
 #ifdef CONFIG_KPROBES_ON_FTRACE
 void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
-		struct ftrace_ops *ops, struct pt_regs *regs)
+		struct ftrace_ops *ops, struct ftrace_regs *fregs)
 {
 	struct kprobe_ctlblk *kcb;
+	struct pt_regs *regs;
 	struct kprobe *p;
 	int bit;
 
@@ -208,6 +209,7 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 	if (bit < 0)
 		return;
 
+	regs = ftrace_get_regs(fregs);
 	preempt_disable_notrace();
 	p = get_kprobe((kprobe_opcode_t *)ip);
 	if (unlikely(!p) || kprobe_disabled(p))
diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c
index 954d930a7127..373e5fa3ce1f 100644
--- a/arch/x86/kernel/kprobes/ftrace.c
+++ b/arch/x86/kernel/kprobes/ftrace.c
@@ -14,8 +14,9 @@
 
 /* Ftrace callback handler for kprobes -- called under preepmt disabed */
 void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
-			   struct ftrace_ops *ops, struct pt_regs *regs)
+			   struct ftrace_ops *ops, struct ftrace_regs *fregs)
 {
+	struct pt_regs *regs = ftrace_get_regs(fregs);
 	struct kprobe *p;
 	struct kprobe_ctlblk *kcb;
 	int bit;
diff --git a/fs/pstore/ftrace.c b/fs/pstore/ftrace.c
index adb0935eb062..5939595f0115 100644
--- a/fs/pstore/ftrace.c
+++ b/fs/pstore/ftrace.c
@@ -26,7 +26,7 @@ static u64 pstore_ftrace_stamp;
 static void notrace pstore_ftrace_call(unsigned long ip,
 				       unsigned long parent_ip,
 				       struct ftrace_ops *op,
-				       struct pt_regs *regs)
+				       struct ftrace_regs *fregs)
 {
 	int bit;
 	unsigned long flags;
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 8dde9c17aaa5..24e1fa52337d 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -90,8 +90,20 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 
 struct ftrace_ops;
 
+struct ftrace_regs {
+	struct pt_regs		regs;
+};
+
+static __always_inline struct pt_regs *ftrace_get_regs(struct ftrace_regs *fregs)
+{
+	if (!fregs)
+		return NULL;
+
+	return &fregs->regs;
+}
+
 typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip,
-			      struct ftrace_ops *op, struct pt_regs *regs);
+			      struct ftrace_ops *op, struct ftrace_regs *fregs);
 
 ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops);
 
@@ -259,7 +271,7 @@ int register_ftrace_function(struct ftrace_ops *ops);
 int unregister_ftrace_function(struct ftrace_ops *ops);
 
 extern void ftrace_stub(unsigned long a0, unsigned long a1,
-			struct ftrace_ops *op, struct pt_regs *regs);
+			struct ftrace_ops *op, struct ftrace_regs *fregs);
 
 #else /* !CONFIG_FUNCTION_TRACER */
 /*
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 629abaf25681..be73350955e4 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -345,7 +345,7 @@ static inline void wait_for_kprobe_optimizer(void) { }
 #endif /* CONFIG_OPTPROBES */
 #ifdef CONFIG_KPROBES_ON_FTRACE
 extern void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
-				  struct ftrace_ops *ops, struct pt_regs *regs);
+				  struct ftrace_ops *ops, struct ftrace_regs *fregs);
 extern int arch_prepare_kprobe_ftrace(struct kprobe *p);
 #endif
 
diff --git a/kernel/livepatch/patch.c b/kernel/livepatch/patch.c
index 875c5dbbdd33..f89f9e7e9b07 100644
--- a/kernel/livepatch/patch.c
+++ b/kernel/livepatch/patch.c
@@ -40,8 +40,9 @@ struct klp_ops *klp_find_ops(void *old_func)
 static void notrace klp_ftrace_handler(unsigned long ip,
 				       unsigned long parent_ip,
 				       struct ftrace_ops *fops,
-				       struct pt_regs *regs)
+				       struct ftrace_regs *fregs)
 {
+	struct pt_regs *regs = ftrace_get_regs(fregs);
 	struct klp_ops *ops;
 	struct klp_func *func;
 	int patch_state;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 3db64fb0cce8..67888311784e 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -121,7 +121,7 @@ struct ftrace_ops global_ops;
 
 #if ARCH_SUPPORTS_FTRACE_OPS
 static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
-				 struct ftrace_ops *op, struct pt_regs *regs);
+				 struct ftrace_ops *op, struct ftrace_regs *fregs);
 #else
 /* See comment below, where ftrace_ops_list_func is defined */
 static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip);
@@ -140,7 +140,7 @@ static inline void ftrace_ops_init(struct ftrace_ops *ops)
 }
 
 static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip,
-			    struct ftrace_ops *op, struct pt_regs *regs)
+			    struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
 	struct trace_array *tr = op->private;
 	int pid;
@@ -154,7 +154,7 @@ static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip,
 			return;
 	}
 
-	op->saved_func(ip, parent_ip, op, regs);
+	op->saved_func(ip, parent_ip, op, fregs);
 }
 
 static void ftrace_sync_ipi(void *data)
@@ -754,7 +754,7 @@ ftrace_profile_alloc(struct ftrace_profile_stat *stat, unsigned long ip)
 
 static void
 function_profile_call(unsigned long ip, unsigned long parent_ip,
-		      struct ftrace_ops *ops, struct pt_regs *regs)
+		      struct ftrace_ops *ops, struct ftrace_regs *fregs)
 {
 	struct ftrace_profile_stat *stat;
 	struct ftrace_profile *rec;
@@ -2143,6 +2143,7 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update)
 				else
 					rec->flags &= ~FTRACE_FL_TRAMP_EN;
 			}
+
 			if (flag & FTRACE_FL_DIRECT) {
 				/*
 				 * If there's only one user (direct_ops helper)
@@ -2368,8 +2369,9 @@ unsigned long ftrace_find_rec_direct(unsigned long ip)
 }
 
 static void call_direct_funcs(unsigned long ip, unsigned long pip,
-			      struct ftrace_ops *ops, struct pt_regs *regs)
+			      struct ftrace_ops *ops, struct ftrace_regs *fregs)
 {
+	struct pt_regs *regs = ftrace_get_regs(fregs);
 	unsigned long addr;
 
 	addr = ftrace_find_rec_direct(ip);
@@ -4292,7 +4294,7 @@ static int __init ftrace_mod_cmd_init(void)
 core_initcall(ftrace_mod_cmd_init);
 
 static void function_trace_probe_call(unsigned long ip, unsigned long parent_ip,
-				      struct ftrace_ops *op, struct pt_regs *pt_regs)
+				      struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
 	struct ftrace_probe_ops *probe_ops;
 	struct ftrace_func_probe *probe;
@@ -6911,8 +6913,9 @@ void ftrace_reset_array_ops(struct trace_array *tr)
 
 static nokprobe_inline void
 __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
-		       struct ftrace_ops *ignored, struct pt_regs *regs)
+		       struct ftrace_ops *ignored, struct ftrace_regs *fregs)
 {
+	struct pt_regs *regs = ftrace_get_regs(fregs);
 	struct ftrace_ops *op;
 	int bit;
 
@@ -6945,7 +6948,7 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
 				pr_warn("op=%p %pS\n", op, op);
 				goto out;
 			}
-			op->func(ip, parent_ip, op, regs);
+			op->func(ip, parent_ip, op, fregs);
 		}
 	} while_for_each_ftrace_op(op);
 out:
@@ -6968,9 +6971,9 @@ out:
  */
 #if ARCH_SUPPORTS_FTRACE_OPS
 static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
-				 struct ftrace_ops *op, struct pt_regs *regs)
+				 struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
-	__ftrace_ops_list_func(ip, parent_ip, NULL, regs);
+	__ftrace_ops_list_func(ip, parent_ip, NULL, fregs);
 }
 NOKPROBE_SYMBOL(ftrace_ops_list_func);
 #else
@@ -6987,7 +6990,7 @@ NOKPROBE_SYMBOL(ftrace_ops_no_ops);
  * this function will be called by the mcount trampoline.
  */
 static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip,
-				   struct ftrace_ops *op, struct pt_regs *regs)
+				   struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
 	int bit;
 
@@ -6998,7 +7001,7 @@ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip,
 	preempt_disable_notrace();
 
 	if (!(op->flags & FTRACE_OPS_FL_RCU) || rcu_is_watching())
-		op->func(ip, parent_ip, op, regs);
+		op->func(ip, parent_ip, op, fregs);
 
 	preempt_enable_notrace();
 	trace_clear_recursion(bit);
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 1b202e28dfaa..a71181655958 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -432,7 +432,7 @@ NOKPROBE_SYMBOL(perf_trace_buf_update);
 #ifdef CONFIG_FUNCTION_TRACER
 static void
 perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip,
-			  struct ftrace_ops *ops, struct pt_regs *pt_regs)
+			  struct ftrace_ops *ops,  struct ftrace_regs *fregs)
 {
 	struct ftrace_entry *entry;
 	struct perf_event *event;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index f4b459bb6d33..98d194d8460e 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -3673,7 +3673,7 @@ static struct trace_event_file event_trace_file __initdata;
 
 static void __init
 function_test_events_call(unsigned long ip, unsigned long parent_ip,
-			  struct ftrace_ops *op, struct pt_regs *pt_regs)
+			  struct ftrace_ops *op, struct ftrace_regs *regs)
 {
 	struct trace_buffer *buffer;
 	struct ring_buffer_event *event;
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 646eda6c44a5..c5095dd28e20 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -23,10 +23,10 @@ static void tracing_start_function_trace(struct trace_array *tr);
 static void tracing_stop_function_trace(struct trace_array *tr);
 static void
 function_trace_call(unsigned long ip, unsigned long parent_ip,
-		    struct ftrace_ops *op, struct pt_regs *pt_regs);
+		    struct ftrace_ops *op, struct ftrace_regs *fregs);
 static void
 function_stack_trace_call(unsigned long ip, unsigned long parent_ip,
-			  struct ftrace_ops *op, struct pt_regs *pt_regs);
+			  struct ftrace_ops *op, struct ftrace_regs *fregs);
 static struct tracer_flags func_flags;
 
 /* Our option */
@@ -89,7 +89,6 @@ void ftrace_destroy_function_files(struct trace_array *tr)
 static int function_trace_init(struct trace_array *tr)
 {
 	ftrace_func_t func;
-
 	/*
 	 * Instance trace_arrays get their ops allocated
 	 * at instance creation. Unless it failed
@@ -129,7 +128,7 @@ static void function_trace_start(struct trace_array *tr)
 
 static void
 function_trace_call(unsigned long ip, unsigned long parent_ip,
-		    struct ftrace_ops *op, struct pt_regs *pt_regs)
+		    struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
 	struct trace_array *tr = op->private;
 	struct trace_array_cpu *data;
@@ -178,7 +177,7 @@ function_trace_call(unsigned long ip, unsigned long parent_ip,
 
 static void
 function_stack_trace_call(unsigned long ip, unsigned long parent_ip,
-			  struct ftrace_ops *op, struct pt_regs *pt_regs)
+			  struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
 	struct trace_array *tr = op->private;
 	struct trace_array_cpu *data;
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 10bbb0f381d5..d06aab4dcbb8 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -138,7 +138,7 @@ static int func_prolog_dec(struct trace_array *tr,
  */
 static void
 irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip,
-		    struct ftrace_ops *op, struct pt_regs *pt_regs)
+		    struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
 	struct trace_array *tr = irqsoff_trace;
 	struct trace_array_cpu *data;
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 97b10bb31a1f..c0181066dbe9 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -212,7 +212,7 @@ static void wakeup_print_header(struct seq_file *s)
  */
 static void
 wakeup_tracer_call(unsigned long ip, unsigned long parent_ip,
-		   struct ftrace_ops *op, struct pt_regs *pt_regs)
+		   struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
 	struct trace_array *tr = wakeup_trace;
 	struct trace_array_cpu *data;
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 8ee3c0bb5d8a..5ed081c6471c 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -107,7 +107,7 @@ static int trace_selftest_test_probe1_cnt;
 static void trace_selftest_test_probe1_func(unsigned long ip,
 					    unsigned long pip,
 					    struct ftrace_ops *op,
-					    struct pt_regs *pt_regs)
+					    struct ftrace_regs *fregs)
 {
 	trace_selftest_test_probe1_cnt++;
 }
@@ -116,7 +116,7 @@ static int trace_selftest_test_probe2_cnt;
 static void trace_selftest_test_probe2_func(unsigned long ip,
 					    unsigned long pip,
 					    struct ftrace_ops *op,
-					    struct pt_regs *pt_regs)
+					    struct ftrace_regs *fregs)
 {
 	trace_selftest_test_probe2_cnt++;
 }
@@ -125,7 +125,7 @@ static int trace_selftest_test_probe3_cnt;
 static void trace_selftest_test_probe3_func(unsigned long ip,
 					    unsigned long pip,
 					    struct ftrace_ops *op,
-					    struct pt_regs *pt_regs)
+					    struct ftrace_regs *fregs)
 {
 	trace_selftest_test_probe3_cnt++;
 }
@@ -134,7 +134,7 @@ static int trace_selftest_test_global_cnt;
 static void trace_selftest_test_global_func(unsigned long ip,
 					    unsigned long pip,
 					    struct ftrace_ops *op,
-					    struct pt_regs *pt_regs)
+					    struct ftrace_regs *fregs)
 {
 	trace_selftest_test_global_cnt++;
 }
@@ -143,7 +143,7 @@ static int trace_selftest_test_dyn_cnt;
 static void trace_selftest_test_dyn_func(unsigned long ip,
 					 unsigned long pip,
 					 struct ftrace_ops *op,
-					 struct pt_regs *pt_regs)
+					 struct ftrace_regs *fregs)
 {
 	trace_selftest_test_dyn_cnt++;
 }
@@ -414,7 +414,7 @@ static int trace_selftest_recursion_cnt;
 static void trace_selftest_test_recursion_func(unsigned long ip,
 					       unsigned long pip,
 					       struct ftrace_ops *op,
-					       struct pt_regs *pt_regs)
+					       struct ftrace_regs *fregs)
 {
 	/*
 	 * This function is registered without the recursion safe flag.
@@ -429,7 +429,7 @@ static void trace_selftest_test_recursion_func(unsigned long ip,
 static void trace_selftest_test_recursion_safe_func(unsigned long ip,
 						    unsigned long pip,
 						    struct ftrace_ops *op,
-						    struct pt_regs *pt_regs)
+						    struct ftrace_regs *fregs)
 {
 	/*
 	 * We said we would provide our own recursion. By calling
@@ -548,9 +548,11 @@ static enum {
 static void trace_selftest_test_regs_func(unsigned long ip,
 					  unsigned long pip,
 					  struct ftrace_ops *op,
-					  struct pt_regs *pt_regs)
+					  struct ftrace_regs *fregs)
 {
-	if (pt_regs)
+	struct pt_regs *regs = ftrace_get_regs(fregs);
+
+	if (regs)
 		trace_selftest_regs_stat = TRACE_SELFTEST_REGS_FOUND;
 	else
 		trace_selftest_regs_stat = TRACE_SELFTEST_REGS_NOT_FOUND;
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 969db526a563..63c285042051 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -290,7 +290,7 @@ static void check_stack(unsigned long ip, unsigned long *stack)
 
 static void
 stack_trace_call(unsigned long ip, unsigned long parent_ip,
-		 struct ftrace_ops *op, struct pt_regs *pt_regs)
+		 struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
 	unsigned long stack;
 
-- 
cgit v1.2.3


From 02a474ca266a47ea8f4d5a11f4ffa120f83730ad Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Tue, 27 Oct 2020 10:55:55 -0400
Subject: ftrace/x86: Allow for arguments to be passed in to ftrace_regs by
 default

Currently, the only way to get access to the registers of a function via a
ftrace callback is to set the "FL_SAVE_REGS" bit in the ftrace_ops. But as this
saves all regs as if a breakpoint were to trigger (for use with kprobes), it
is expensive.

The regs are already saved on the stack for the default ftrace callbacks, as
that is required otherwise a function being traced will get the wrong
arguments and possibly crash. And on x86, the arguments are already stored
where they would be on a pt_regs structure to use that code for both the
regs version of a callback, it makes sense to pass that information always
to all functions.

If an architecture does this (as x86_64 now does), it is to set
HAVE_DYNAMIC_FTRACE_WITH_ARGS, and this will let the generic code that it
could have access to arguments without having to set the flags.

This also includes having the stack pointer being saved, which could be used
for accessing arguments on the stack, as well as having the function graph
tracer not require its own trampoline!

Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 arch/x86/Kconfig              |  1 +
 arch/x86/include/asm/ftrace.h | 15 +++++++++++++++
 arch/x86/kernel/ftrace_64.S   | 11 +++++++++--
 include/linux/ftrace.h        |  7 ++++++-
 kernel/trace/Kconfig          |  9 +++++++++
 5 files changed, 40 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index f6946b81f74a..478526aabe5d 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -167,6 +167,7 @@ config X86
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
+	select HAVE_DYNAMIC_FTRACE_WITH_ARGS	if X86_64
 	select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 	select HAVE_EBPF_JIT
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index 84b9449be080..e00fe88146e0 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -41,6 +41,21 @@ static inline void arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned
 	regs->orig_ax = addr;
 }
 
+#ifdef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
+struct ftrace_regs {
+	struct pt_regs		regs;
+};
+
+static __always_inline struct pt_regs *
+arch_ftrace_get_regs(struct ftrace_regs *fregs)
+{
+	/* Only when FL_SAVE_REGS is set, cs will be non zero */
+	if (!fregs->regs.cs)
+		return NULL;
+	return &fregs->regs;
+}
+#endif
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 struct dyn_arch_ftrace {
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index ac3d5f22fe64..60e3b64f5ea6 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -140,12 +140,19 @@ SYM_FUNC_START(ftrace_caller)
 	/* save_mcount_regs fills in first two parameters */
 	save_mcount_regs
 
+	/* Stack - skipping return address of ftrace_caller */
+	leaq MCOUNT_REG_SIZE+8(%rsp), %rcx
+	movq %rcx, RSP(%rsp)
+
 SYM_INNER_LABEL(ftrace_caller_op_ptr, SYM_L_GLOBAL)
 	/* Load the ftrace_ops into the 3rd parameter */
 	movq function_trace_op(%rip), %rdx
 
-	/* regs go into 4th parameter (but make it NULL) */
-	movq $0, %rcx
+	/* regs go into 4th parameter */
+	leaq (%rsp), %rcx
+
+	/* Only ops with REGS flag set should have CS register set */
+	movq $0, CS(%rsp)
 
 SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
 	call ftrace_stub
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 24e1fa52337d..588ea7023a7a 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -90,16 +90,21 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 
 struct ftrace_ops;
 
+#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
+
 struct ftrace_regs {
 	struct pt_regs		regs;
 };
+#define arch_ftrace_get_regs(fregs) (&(fregs)->regs)
+
+#endif /* CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */
 
 static __always_inline struct pt_regs *ftrace_get_regs(struct ftrace_regs *fregs)
 {
 	if (!fregs)
 		return NULL;
 
-	return &fregs->regs;
+	return arch_ftrace_get_regs(fregs);
 }
 
 typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip,
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 6aa36ec73ccb..c9b64dea1216 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -31,6 +31,15 @@ config HAVE_DYNAMIC_FTRACE_WITH_REGS
 config HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 	bool
 
+config HAVE_DYNAMIC_FTRACE_WITH_ARGS
+	bool
+	help
+	 If this is set, then arguments and stack can be found from
+	 the pt_regs passed into the function callback regs parameter
+	 by default, even without setting the REGS flag in the ftrace_ops.
+	 This allows for use of regs_get_kernel_argument() and
+	 kernel_stack_pointer().
+
 config HAVE_FTRACE_MCOUNT_RECORD
 	bool
 	help
-- 
cgit v1.2.3


From 2860cd8a235375df3c8ec8039d9fe5eb2f658b86 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Wed, 28 Oct 2020 17:15:27 -0400
Subject: livepatch: Use the default ftrace_ops instead of REGS when ARGS is
 available

When CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS is available, the ftrace call
will be able to set the ip of the calling function. This will improve the
performance of live kernel patching where it does not need all the regs to
be stored just to change the instruction pointer.

If all archs that support live kernel patching also support
HAVE_DYNAMIC_FTRACE_WITH_ARGS, then the architecture specific function
klp_arch_set_pc() could be made generic.

It is possible that an arch can support HAVE_DYNAMIC_FTRACE_WITH_ARGS but
not HAVE_DYNAMIC_FTRACE_WITH_REGS and then have access to live patching.

Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Jiri Kosina <jikos@kernel.org>
Cc: live-patching@vger.kernel.org
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Miroslav Benes <mbenes@suse.cz>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 arch/powerpc/include/asm/livepatch.h | 4 +++-
 arch/s390/include/asm/livepatch.h    | 5 ++++-
 arch/x86/include/asm/ftrace.h        | 3 +++
 arch/x86/include/asm/livepatch.h     | 4 ++--
 arch/x86/kernel/ftrace_64.S          | 4 ++++
 include/linux/ftrace.h               | 7 +++++++
 kernel/livepatch/Kconfig             | 2 +-
 kernel/livepatch/patch.c             | 9 +++++----
 8 files changed, 29 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/arch/powerpc/include/asm/livepatch.h b/arch/powerpc/include/asm/livepatch.h
index 4a3d5d25fed5..ae25e6e72997 100644
--- a/arch/powerpc/include/asm/livepatch.h
+++ b/arch/powerpc/include/asm/livepatch.h
@@ -12,8 +12,10 @@
 #include <linux/sched/task_stack.h>
 
 #ifdef CONFIG_LIVEPATCH
-static inline void klp_arch_set_pc(struct pt_regs *regs, unsigned long ip)
+static inline void klp_arch_set_pc(struct ftrace_regs *fregs, unsigned long ip)
 {
+	struct pt_regs *regs = ftrace_get_regs(fregs);
+
 	regs->nip = ip;
 }
 
diff --git a/arch/s390/include/asm/livepatch.h b/arch/s390/include/asm/livepatch.h
index 818612b784cd..d578a8c76676 100644
--- a/arch/s390/include/asm/livepatch.h
+++ b/arch/s390/include/asm/livepatch.h
@@ -11,10 +11,13 @@
 #ifndef ASM_LIVEPATCH_H
 #define ASM_LIVEPATCH_H
 
+#include <linux/ftrace.h>
 #include <asm/ptrace.h>
 
-static inline void klp_arch_set_pc(struct pt_regs *regs, unsigned long ip)
+static inline void klp_arch_set_pc(struct ftrace_regs *fregs, unsigned long ip)
 {
+	struct pt_regs *regs = ftrace_get_regs(fregs);
+
 	regs->psw.addr = ip;
 }
 
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index e00fe88146e0..9f3130f40807 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -54,6 +54,9 @@ arch_ftrace_get_regs(struct ftrace_regs *fregs)
 		return NULL;
 	return &fregs->regs;
 }
+
+#define ftrace_instruction_pointer_set(fregs, _ip)	\
+	do { (fregs)->regs.ip = (_ip); } while (0)
 #endif
 
 #ifdef CONFIG_DYNAMIC_FTRACE
diff --git a/arch/x86/include/asm/livepatch.h b/arch/x86/include/asm/livepatch.h
index 1fde1ab6559e..7c5cc6660e4b 100644
--- a/arch/x86/include/asm/livepatch.h
+++ b/arch/x86/include/asm/livepatch.h
@@ -12,9 +12,9 @@
 #include <asm/setup.h>
 #include <linux/ftrace.h>
 
-static inline void klp_arch_set_pc(struct pt_regs *regs, unsigned long ip)
+static inline void klp_arch_set_pc(struct ftrace_regs *fregs, unsigned long ip)
 {
-	regs->ip = ip;
+	ftrace_instruction_pointer_set(fregs, ip);
 }
 
 #endif /* _ASM_X86_LIVEPATCH_H */
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index 60e3b64f5ea6..0d54099c2a3a 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -157,6 +157,10 @@ SYM_INNER_LABEL(ftrace_caller_op_ptr, SYM_L_GLOBAL)
 SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
 	call ftrace_stub
 
+	/* Handlers can change the RIP */
+	movq RIP(%rsp), %rax
+	movq %rax, MCOUNT_REG_SIZE(%rsp)
+
 	restore_mcount_regs
 
 	/*
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 588ea7023a7a..9a8ce28e4485 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -97,6 +97,13 @@ struct ftrace_regs {
 };
 #define arch_ftrace_get_regs(fregs) (&(fregs)->regs)
 
+/*
+ * ftrace_instruction_pointer_set() is to be defined by the architecture
+ * if to allow setting of the instruction pointer from the ftrace_regs
+ * when HAVE_DYNAMIC_FTRACE_WITH_ARGS is set and it supports
+ * live kernel patching.
+ */
+#define ftrace_instruction_pointer_set(fregs, ip) do { } while (0)
 #endif /* CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */
 
 static __always_inline struct pt_regs *ftrace_get_regs(struct ftrace_regs *fregs)
diff --git a/kernel/livepatch/Kconfig b/kernel/livepatch/Kconfig
index 54102deb50ba..53d51ed619a3 100644
--- a/kernel/livepatch/Kconfig
+++ b/kernel/livepatch/Kconfig
@@ -6,7 +6,7 @@ config HAVE_LIVEPATCH
 
 config LIVEPATCH
 	bool "Kernel Live Patching"
-	depends on DYNAMIC_FTRACE_WITH_REGS
+	depends on DYNAMIC_FTRACE_WITH_REGS || DYNAMIC_FTRACE_WITH_ARGS
 	depends on MODULES
 	depends on SYSFS
 	depends on KALLSYMS_ALL
diff --git a/kernel/livepatch/patch.c b/kernel/livepatch/patch.c
index f89f9e7e9b07..e8029aea67f1 100644
--- a/kernel/livepatch/patch.c
+++ b/kernel/livepatch/patch.c
@@ -42,7 +42,6 @@ static void notrace klp_ftrace_handler(unsigned long ip,
 				       struct ftrace_ops *fops,
 				       struct ftrace_regs *fregs)
 {
-	struct pt_regs *regs = ftrace_get_regs(fregs);
 	struct klp_ops *ops;
 	struct klp_func *func;
 	int patch_state;
@@ -118,7 +117,7 @@ static void notrace klp_ftrace_handler(unsigned long ip,
 	if (func->nop)
 		goto unlock;
 
-	klp_arch_set_pc(regs, (unsigned long)func->new_func);
+	klp_arch_set_pc(fregs, (unsigned long)func->new_func);
 
 unlock:
 	preempt_enable_notrace();
@@ -200,8 +199,10 @@ static int klp_patch_func(struct klp_func *func)
 			return -ENOMEM;
 
 		ops->fops.func = klp_ftrace_handler;
-		ops->fops.flags = FTRACE_OPS_FL_SAVE_REGS |
-				  FTRACE_OPS_FL_DYNAMIC |
+		ops->fops.flags = FTRACE_OPS_FL_DYNAMIC |
+#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
+				  FTRACE_OPS_FL_SAVE_REGS |
+#endif
 				  FTRACE_OPS_FL_IPMODIFY |
 				  FTRACE_OPS_FL_PERMANENT;
 
-- 
cgit v1.2.3


From e7018751d2e603381ae6028ba4dd21ec45ce38bb Mon Sep 17 00:00:00 2001
From: Fabio Estevam <festevam@gmail.com>
Date: Fri, 13 Nov 2020 14:12:31 -0300
Subject: usb: host: ehci-mxc: Remove the driver

The ehci-mxc driver was only used by i.MX non-DT platforms.

Since 5.10-rc1, i.MX has been converted to a DT-only platform and all
board files are gone.

Remove the ehci-mxc driver as there are no more users at all.

Acked-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Fabio Estevam <festevam@gmail.com>
Link: https://lore.kernel.org/r/20201113171231.2205-1-festevam@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/Kconfig                   |   7 -
 drivers/usb/host/Makefile                  |   1 -
 drivers/usb/host/ehci-mxc.c                | 213 -----------------------------
 include/linux/platform_data/usb-ehci-mxc.h |  14 --
 4 files changed, 235 deletions(-)
 delete mode 100644 drivers/usb/host/ehci-mxc.c
 delete mode 100644 include/linux/platform_data/usb-ehci-mxc.h

(limited to 'include/linux')

diff --git a/drivers/usb/host/Kconfig b/drivers/usb/host/Kconfig
index a633e9c15f7e..31e59309da1f 100644
--- a/drivers/usb/host/Kconfig
+++ b/drivers/usb/host/Kconfig
@@ -213,13 +213,6 @@ config USB_EHCI_FSL
 	help
 	  Variation of ARC USB block used in some Freescale chips.
 
-config USB_EHCI_MXC
-	tristate "Support for Freescale i.MX on-chip EHCI USB controller"
-	depends on ARCH_MXC || COMPILE_TEST
-	select USB_EHCI_ROOT_HUB_TT
-	help
-	  Variation of ARC USB block used in some Freescale chips.
-
 config USB_EHCI_HCD_NPCM7XX
 	tristate "Support for Nuvoton NPCM7XX on-chip EHCI USB controller"
 	depends on (USB_EHCI_HCD && ARCH_NPCM7XX) || COMPILE_TEST
diff --git a/drivers/usb/host/Makefile b/drivers/usb/host/Makefile
index d03f6f0764d2..c1b08703af10 100644
--- a/drivers/usb/host/Makefile
+++ b/drivers/usb/host/Makefile
@@ -40,7 +40,6 @@ obj-$(CONFIG_USB_PCI)	+= pci-quirks.o
 obj-$(CONFIG_USB_EHCI_HCD)	+= ehci-hcd.o
 obj-$(CONFIG_USB_EHCI_PCI)	+= ehci-pci.o
 obj-$(CONFIG_USB_EHCI_HCD_PLATFORM)	+= ehci-platform.o
-obj-$(CONFIG_USB_EHCI_MXC)	+= ehci-mxc.o
 obj-$(CONFIG_USB_EHCI_HCD_NPCM7XX)	+= ehci-npcm7xx.o
 obj-$(CONFIG_USB_EHCI_HCD_OMAP)	+= ehci-omap.o
 obj-$(CONFIG_USB_EHCI_HCD_ORION)	+= ehci-orion.o
diff --git a/drivers/usb/host/ehci-mxc.c b/drivers/usb/host/ehci-mxc.c
deleted file mode 100644
index dc2676320527..000000000000
--- a/drivers/usb/host/ehci-mxc.c
+++ /dev/null
@@ -1,213 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0+
-/*
- * Copyright (c) 2008 Sascha Hauer <s.hauer@pengutronix.de>, Pengutronix
- * Copyright (c) 2009 Daniel Mack <daniel@caiaq.de>
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/io.h>
-#include <linux/platform_device.h>
-#include <linux/clk.h>
-#include <linux/delay.h>
-#include <linux/usb/otg.h>
-#include <linux/usb/ulpi.h>
-#include <linux/slab.h>
-#include <linux/usb.h>
-#include <linux/usb/hcd.h>
-#include <linux/platform_data/usb-ehci-mxc.h>
-#include "ehci.h"
-
-#define DRIVER_DESC "Freescale On-Chip EHCI Host driver"
-
-static const char hcd_name[] = "ehci-mxc";
-
-#define ULPI_VIEWPORT_OFFSET	0x170
-
-struct ehci_mxc_priv {
-	struct clk *usbclk, *ahbclk, *phyclk;
-};
-
-static struct hc_driver __read_mostly ehci_mxc_hc_driver;
-
-static const struct ehci_driver_overrides ehci_mxc_overrides __initconst = {
-	.extra_priv_size =	sizeof(struct ehci_mxc_priv),
-};
-
-static int ehci_mxc_drv_probe(struct platform_device *pdev)
-{
-	struct device *dev = &pdev->dev;
-	struct mxc_usbh_platform_data *pdata = dev_get_platdata(dev);
-	struct usb_hcd *hcd;
-	struct resource *res;
-	int irq, ret;
-	struct ehci_mxc_priv *priv;
-	struct ehci_hcd *ehci;
-
-	if (!pdata) {
-		dev_err(dev, "No platform data given, bailing out.\n");
-		return -EINVAL;
-	}
-
-	irq = platform_get_irq(pdev, 0);
-	if (irq < 0)
-		return irq;
-
-	hcd = usb_create_hcd(&ehci_mxc_hc_driver, dev, dev_name(dev));
-	if (!hcd)
-		return -ENOMEM;
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	hcd->regs = devm_ioremap_resource(dev, res);
-	if (IS_ERR(hcd->regs)) {
-		ret = PTR_ERR(hcd->regs);
-		goto err_alloc;
-	}
-	hcd->rsrc_start = res->start;
-	hcd->rsrc_len = resource_size(res);
-
-	hcd->has_tt = 1;
-	ehci = hcd_to_ehci(hcd);
-	priv = (struct ehci_mxc_priv *) ehci->priv;
-
-	/* enable clocks */
-	priv->usbclk = devm_clk_get(dev, "ipg");
-	if (IS_ERR(priv->usbclk)) {
-		ret = PTR_ERR(priv->usbclk);
-		goto err_alloc;
-	}
-	clk_prepare_enable(priv->usbclk);
-
-	priv->ahbclk = devm_clk_get(dev, "ahb");
-	if (IS_ERR(priv->ahbclk)) {
-		ret = PTR_ERR(priv->ahbclk);
-		goto err_clk_ahb;
-	}
-	clk_prepare_enable(priv->ahbclk);
-
-	/* "dr" device has its own clock on i.MX51 */
-	priv->phyclk = devm_clk_get(dev, "phy");
-	if (IS_ERR(priv->phyclk))
-		priv->phyclk = NULL;
-	if (priv->phyclk)
-		clk_prepare_enable(priv->phyclk);
-
-	/* call platform specific init function */
-	if (pdata->init) {
-		ret = pdata->init(pdev);
-		if (ret) {
-			dev_err(dev, "platform init failed\n");
-			goto err_init;
-		}
-		/* platforms need some time to settle changed IO settings */
-		mdelay(10);
-	}
-
-	/* EHCI registers start at offset 0x100 */
-	ehci->caps = hcd->regs + 0x100;
-	ehci->regs = hcd->regs + 0x100 +
-		HC_LENGTH(ehci, ehci_readl(ehci, &ehci->caps->hc_capbase));
-
-	/* set up the PORTSCx register */
-	ehci_writel(ehci, pdata->portsc, &ehci->regs->port_status[0]);
-
-	/* is this really needed? */
-	msleep(10);
-
-	/* Initialize the transceiver */
-	if (pdata->otg) {
-		pdata->otg->io_priv = hcd->regs + ULPI_VIEWPORT_OFFSET;
-		ret = usb_phy_init(pdata->otg);
-		if (ret) {
-			dev_err(dev, "unable to init transceiver, probably missing\n");
-			ret = -ENODEV;
-			goto err_add;
-		}
-		ret = otg_set_vbus(pdata->otg->otg, 1);
-		if (ret) {
-			dev_err(dev, "unable to enable vbus on transceiver\n");
-			goto err_add;
-		}
-	}
-
-	platform_set_drvdata(pdev, hcd);
-
-	ret = usb_add_hcd(hcd, irq, IRQF_SHARED);
-	if (ret)
-		goto err_add;
-
-	device_wakeup_enable(hcd->self.controller);
-	return 0;
-
-err_add:
-	if (pdata && pdata->exit)
-		pdata->exit(pdev);
-err_init:
-	if (priv->phyclk)
-		clk_disable_unprepare(priv->phyclk);
-
-	clk_disable_unprepare(priv->ahbclk);
-err_clk_ahb:
-	clk_disable_unprepare(priv->usbclk);
-err_alloc:
-	usb_put_hcd(hcd);
-	return ret;
-}
-
-static int ehci_mxc_drv_remove(struct platform_device *pdev)
-{
-	struct mxc_usbh_platform_data *pdata = dev_get_platdata(&pdev->dev);
-	struct usb_hcd *hcd = platform_get_drvdata(pdev);
-	struct ehci_hcd *ehci = hcd_to_ehci(hcd);
-	struct ehci_mxc_priv *priv = (struct ehci_mxc_priv *) ehci->priv;
-
-	usb_remove_hcd(hcd);
-
-	if (pdata && pdata->exit)
-		pdata->exit(pdev);
-
-	if (pdata && pdata->otg)
-		usb_phy_shutdown(pdata->otg);
-
-	clk_disable_unprepare(priv->usbclk);
-	clk_disable_unprepare(priv->ahbclk);
-
-	if (priv->phyclk)
-		clk_disable_unprepare(priv->phyclk);
-
-	usb_put_hcd(hcd);
-	return 0;
-}
-
-MODULE_ALIAS("platform:mxc-ehci");
-
-static struct platform_driver ehci_mxc_driver = {
-	.probe = ehci_mxc_drv_probe,
-	.remove = ehci_mxc_drv_remove,
-	.shutdown = usb_hcd_platform_shutdown,
-	.driver = {
-		   .name = "mxc-ehci",
-	},
-};
-
-static int __init ehci_mxc_init(void)
-{
-	if (usb_disabled())
-		return -ENODEV;
-
-	pr_info("%s: " DRIVER_DESC "\n", hcd_name);
-
-	ehci_init_driver(&ehci_mxc_hc_driver, &ehci_mxc_overrides);
-	return platform_driver_register(&ehci_mxc_driver);
-}
-module_init(ehci_mxc_init);
-
-static void __exit ehci_mxc_cleanup(void)
-{
-	platform_driver_unregister(&ehci_mxc_driver);
-}
-module_exit(ehci_mxc_cleanup);
-
-MODULE_DESCRIPTION(DRIVER_DESC);
-MODULE_AUTHOR("Sascha Hauer");
-MODULE_LICENSE("GPL");
diff --git a/include/linux/platform_data/usb-ehci-mxc.h b/include/linux/platform_data/usb-ehci-mxc.h
deleted file mode 100644
index ad9794d09bc8..000000000000
--- a/include/linux/platform_data/usb-ehci-mxc.h
+++ /dev/null
@@ -1,14 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __INCLUDE_ASM_ARCH_MXC_EHCI_H
-#define __INCLUDE_ASM_ARCH_MXC_EHCI_H
-
-struct mxc_usbh_platform_data {
-	int (*init)(struct platform_device *pdev);
-	int (*exit)(struct platform_device *pdev);
-
-	unsigned int		 portsc;
-	struct usb_phy		*otg;
-};
-
-#endif /* __INCLUDE_ASM_ARCH_MXC_EHCI_H */
-
-- 
cgit v1.2.3


From 56c62080d5b57dac2c2cdd4a83571450e38ca763 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Fri, 13 Nov 2020 22:27:04 +0100
Subject: usb: hcd.h: Remove RUN_CONTEXT

The last user of RUN_CONTEXT was removed in commit
   97c17beb3b668 ("[PATCH] ehci-hcd (1/2):  portability (2.4), tasklet,")
in the history.git repo.

There are no users of RUN_CONTEXT, remove it.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Link: https://lore.kernel.org/r/20201113212704.2243807-1-bigeasy@linutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/usb/hcd.h | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index 3dbb42c637c1..96281cd50ff6 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -734,10 +734,6 @@ static inline void usbmon_urb_complete(struct usb_bus *bus, struct urb *urb,
 
 /* random stuff */
 
-#define	RUN_CONTEXT (in_irq() ? "in_irq" \
-		: (in_interrupt() ? "in_interrupt" : "can sleep"))
-
-
 /* This rwsem is for use only by the hub driver and ehci-hcd.
  * Nobody else should touch it.
  */
-- 
cgit v1.2.3


From 8dedcc3eee3aceb37832176f0a1b03d5687acda3 Mon Sep 17 00:00:00 2001
From: Alexandru Ardelean <alexandru.ardelean@analog.com>
Date: Thu, 24 Sep 2020 11:41:55 +0300
Subject: iio: core: centralize ioctl() calls to the main chardev

The aim of this is to improve a bit the organization of ioctl() calls in
IIO core. Currently the chardev is split across IIO core sub-modules/files.
The main chardev has to be able to handle ioctl() calls, and if we need to
add buffer ioctl() calls, this would complicate things.

The 'industrialio-core.c' file will provide a 'iio_device_ioctl()' which
will iterate over a list of ioctls registered with the IIO device. These
can be event ioctl() or buffer ioctl() calls, or something else.

Each ioctl() handler will have to return a IIO_IOCTL_UNHANDLED code (which
is positive 1), if the ioctl() did not handle the call in any. This
eliminates any potential ambiguities about negative error codes, which
should fail the call altogether.

If any ioctl() returns 0, it was considered that it was serviced
successfully and the loop will exit.

This change also moves the handling of the IIO_GET_EVENT_FD_IOCTL command
inside 'industrialio-event.c', where this is better suited.

This patch is a combination of 2 other patches from an older series:
Patch 1: iio: core: add simple centralized mechanism for ioctl() handlers
  Link: https://lore.kernel.org/linux-iio/20200427131100.50845-6-alexandru.ardelean@analog.com/
Patch 2: iio: core: use new common ioctl() mechanism
  Link: https://lore.kernel.org/linux-iio/20200427131100.50845-7-alexandru.ardelean@analog.com/

Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Link: https://lore.kernel.org/r/20200924084155.99406-1-alexandru.ardelean@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/iio_core.h           | 15 ++++++++++-
 drivers/iio/industrialio-core.c  | 56 ++++++++++++++++++++++++++++++----------
 drivers/iio/industrialio-event.c | 28 +++++++++++++++++++-
 include/linux/iio/iio-opaque.h   |  2 ++
 4 files changed, 85 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iio/iio_core.h b/drivers/iio/iio_core.h
index fd9a5f1d5e51..fced02cadcc3 100644
--- a/drivers/iio/iio_core.h
+++ b/drivers/iio/iio_core.h
@@ -17,6 +17,20 @@ struct iio_dev;
 
 extern struct device_type iio_device_type;
 
+#define IIO_IOCTL_UNHANDLED	1
+struct iio_ioctl_handler {
+	struct list_head entry;
+	long (*ioctl)(struct iio_dev *indio_dev, struct file *filp,
+		      unsigned int cmd, unsigned long arg);
+};
+
+long iio_device_ioctl(struct iio_dev *indio_dev, struct file *filp,
+		      unsigned int cmd, unsigned long arg);
+
+void iio_device_ioctl_handler_register(struct iio_dev *indio_dev,
+				       struct iio_ioctl_handler *h);
+void iio_device_ioctl_handler_unregister(struct iio_ioctl_handler *h);
+
 int __iio_add_chan_devattr(const char *postfix,
 			   struct iio_chan_spec const *chan,
 			   ssize_t (*func)(struct device *dev,
@@ -74,7 +88,6 @@ static inline void iio_buffer_wakeup_poll(struct iio_dev *indio_dev) {}
 int iio_device_register_eventset(struct iio_dev *indio_dev);
 void iio_device_unregister_eventset(struct iio_dev *indio_dev);
 void iio_device_wakeup_eventset(struct iio_dev *indio_dev);
-int iio_event_getfd(struct iio_dev *indio_dev);
 
 struct iio_event_interface;
 bool iio_event_enabled(const struct iio_event_interface *ev_int);
diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index 0402be441ffb..e53c771d66eb 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -1612,6 +1612,7 @@ struct iio_dev *iio_device_alloc(struct device *parent, int sizeof_priv)
 	}
 	dev_set_name(&dev->dev, "iio:device%d", dev->id);
 	INIT_LIST_HEAD(&iio_dev_opaque->buffer_list);
+	INIT_LIST_HEAD(&iio_dev_opaque->ioctl_handlers);
 
 	return dev;
 }
@@ -1705,26 +1706,47 @@ static int iio_chrdev_release(struct inode *inode, struct file *filp)
 	return 0;
 }
 
-/* Somewhat of a cross file organization violation - ioctls here are actually
- * event related */
+void iio_device_ioctl_handler_register(struct iio_dev *indio_dev,
+				       struct iio_ioctl_handler *h)
+{
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
+
+	list_add_tail(&h->entry, &iio_dev_opaque->ioctl_handlers);
+}
+
+void iio_device_ioctl_handler_unregister(struct iio_ioctl_handler *h)
+{
+	list_del(&h->entry);
+}
+
 static long iio_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	struct iio_dev *indio_dev = filp->private_data;
-	int __user *ip = (int __user *)arg;
-	int fd;
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
+	struct iio_ioctl_handler *h;
+	int ret = -ENODEV;
+
+	mutex_lock(&indio_dev->info_exist_lock);
 
+	/**
+	 * The NULL check here is required to prevent crashing when a device
+	 * is being removed while userspace would still have open file handles
+	 * to try to access this device.
+	 */
 	if (!indio_dev->info)
-		return -ENODEV;
-
-	if (cmd == IIO_GET_EVENT_FD_IOCTL) {
-		fd = iio_event_getfd(indio_dev);
-		if (fd < 0)
-			return fd;
-		if (copy_to_user(ip, &fd, sizeof(fd)))
-			return -EFAULT;
-		return 0;
+		goto out_unlock;
+
+	ret = -EINVAL;
+	list_for_each_entry(h, &iio_dev_opaque->ioctl_handlers, entry) {
+		ret = h->ioctl(indio_dev, filp, cmd, arg);
+		if (ret != IIO_IOCTL_UNHANDLED)
+			break;
 	}
-	return -EINVAL;
+
+out_unlock:
+	mutex_unlock(&indio_dev->info_exist_lock);
+
+	return ret;
 }
 
 static const struct file_operations iio_buffer_fileops = {
@@ -1841,6 +1863,9 @@ EXPORT_SYMBOL(__iio_device_register);
  **/
 void iio_device_unregister(struct iio_dev *indio_dev)
 {
+	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
+	struct iio_ioctl_handler *h, *t;
+
 	cdev_device_del(&indio_dev->chrdev, &indio_dev->dev);
 
 	mutex_lock(&indio_dev->info_exist_lock);
@@ -1851,6 +1876,9 @@ void iio_device_unregister(struct iio_dev *indio_dev)
 
 	indio_dev->info = NULL;
 
+	list_for_each_entry_safe(h, t, &iio_dev_opaque->ioctl_handlers, entry)
+		list_del(&h->entry);
+
 	iio_device_wakeup_eventset(indio_dev);
 	iio_buffer_wakeup_poll(indio_dev);
 
diff --git a/drivers/iio/industrialio-event.c b/drivers/iio/industrialio-event.c
index 99ba657b8568..7e532117ac55 100644
--- a/drivers/iio/industrialio-event.c
+++ b/drivers/iio/industrialio-event.c
@@ -31,6 +31,7 @@
  * @flags:		file operations related flags including busy flag.
  * @group:		event interface sysfs attribute group
  * @read_lock:		lock to protect kfifo read operations
+ * @ioctl_handler:	handler for event ioctl() calls
  */
 struct iio_event_interface {
 	wait_queue_head_t	wait;
@@ -40,6 +41,7 @@ struct iio_event_interface {
 	unsigned long		flags;
 	struct attribute_group	group;
 	struct mutex		read_lock;
+	struct iio_ioctl_handler	ioctl_handler;
 };
 
 bool iio_event_enabled(const struct iio_event_interface *ev_int)
@@ -187,7 +189,7 @@ static const struct file_operations iio_event_chrdev_fileops = {
 	.llseek = noop_llseek,
 };
 
-int iio_event_getfd(struct iio_dev *indio_dev)
+static int iio_event_getfd(struct iio_dev *indio_dev)
 {
 	struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev);
 	struct iio_event_interface *ev_int = iio_dev_opaque->event_interface;
@@ -473,6 +475,24 @@ static void iio_setup_ev_int(struct iio_event_interface *ev_int)
 	mutex_init(&ev_int->read_lock);
 }
 
+static long iio_event_ioctl(struct iio_dev *indio_dev, struct file *filp,
+			    unsigned int cmd, unsigned long arg)
+{
+	int __user *ip = (int __user *)arg;
+	int fd;
+
+	if (cmd == IIO_GET_EVENT_FD_IOCTL) {
+		fd = iio_event_getfd(indio_dev);
+		if (fd < 0)
+			return fd;
+		if (copy_to_user(ip, &fd, sizeof(fd)))
+			return -EFAULT;
+		return 0;
+	}
+
+	return IIO_IOCTL_UNHANDLED;
+}
+
 static const char *iio_event_group_name = "events";
 int iio_device_register_eventset(struct iio_dev *indio_dev)
 {
@@ -526,6 +546,10 @@ int iio_device_register_eventset(struct iio_dev *indio_dev)
 		ev_int->group.attrs[attrn++] = &p->dev_attr.attr;
 	indio_dev->groups[indio_dev->groupcounter++] = &ev_int->group;
 
+	ev_int->ioctl_handler.ioctl = iio_event_ioctl;
+	iio_device_ioctl_handler_register(&iio_dev_opaque->indio_dev,
+					  &ev_int->ioctl_handler);
+
 	return 0;
 
 error_free_setup_event_lines:
@@ -558,6 +582,8 @@ void iio_device_unregister_eventset(struct iio_dev *indio_dev)
 
 	if (ev_int == NULL)
 		return;
+
+	iio_device_ioctl_handler_unregister(&ev_int->ioctl_handler);
 	iio_free_chan_devattr_list(&ev_int->dev_attr_list);
 	kfree(ev_int->group.attrs);
 	kfree(ev_int);
diff --git a/include/linux/iio/iio-opaque.h b/include/linux/iio/iio-opaque.h
index f2e94196d31f..07c5a8e52ca8 100644
--- a/include/linux/iio/iio-opaque.h
+++ b/include/linux/iio/iio-opaque.h
@@ -11,6 +11,7 @@
  * @channel_attr_list:		keep track of automatically created channel
  *				attributes
  * @chan_attr_group:		group for all attrs in base directory
+ * @ioctl_handlers:		ioctl handlers registered with the core handler
  * @debugfs_dentry:		device specific debugfs dentry
  * @cached_reg_addr:		cached register address for debugfs reads
  * @read_buf:			read buffer to be used for the initial reg read
@@ -22,6 +23,7 @@ struct iio_dev_opaque {
 	struct list_head		buffer_list;
 	struct list_head		channel_attr_list;
 	struct attribute_group		chan_attr_group;
+	struct list_head		ioctl_handlers;
 #if defined(CONFIG_DEBUG_FS)
 	struct dentry			*debugfs_dentry;
 	unsigned			cached_reg_addr;
-- 
cgit v1.2.3


From 3347acc6fcd4ee71ad18a9ff9d9dac176b517329 Mon Sep 17 00:00:00 2001
From: Arvind Sankar <nivedita@alum.mit.edu>
Date: Fri, 13 Nov 2020 22:51:59 -0800
Subject: compiler.h: fix barrier_data() on clang

Commit 815f0ddb346c ("include/linux/compiler*.h: make compiler-*.h
mutually exclusive") neglected to copy barrier_data() from
compiler-gcc.h into compiler-clang.h.

The definition in compiler-gcc.h was really to work around clang's more
aggressive optimization, so this broke barrier_data() on clang, and
consequently memzero_explicit() as well.

For example, this results in at least the memzero_explicit() call in
lib/crypto/sha256.c:sha256_transform() being optimized away by clang.

Fix this by moving the definition of barrier_data() into compiler.h.

Also move the gcc/clang definition of barrier() into compiler.h,
__memory_barrier() is icc-specific (and barrier() is already defined
using it in compiler-intel.h) and doesn't belong in compiler.h.

[rdunlap@infradead.org: fix ALPHA builds when SMP is not enabled]

Link: https://lkml.kernel.org/r/20201101231835.4589-1-rdunlap@infradead.org
Fixes: 815f0ddb346c ("include/linux/compiler*.h: make compiler-*.h mutually exclusive")
Signed-off-by: Arvind Sankar <nivedita@alum.mit.edu>
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Nick Desaulniers <ndesaulniers@google.com>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Cc: <stable@vger.kernel.org>
Link: https://lkml.kernel.org/r/20201014212631.207844-1-nivedita@alum.mit.edu
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/asm-generic/barrier.h  |  1 +
 include/linux/compiler-clang.h |  6 ------
 include/linux/compiler-gcc.h   | 19 -------------------
 include/linux/compiler.h       | 18 ++++++++++++++++--
 4 files changed, 17 insertions(+), 27 deletions(-)

(limited to 'include/linux')

diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index 798027bb89be..640f09479bdf 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -13,6 +13,7 @@
 
 #ifndef __ASSEMBLY__
 
+#include <linux/compiler.h>
 #include <asm/rwonce.h>
 
 #ifndef nop
diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index 230604e7f057..dd7233c48bf3 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -60,12 +60,6 @@
 #define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1
 #endif
 
-/* The following are for compatibility with GCC, from compiler-gcc.h,
- * and may be redefined here because they should not be shared with other
- * compilers, like ICC.
- */
-#define barrier() __asm__ __volatile__("" : : : "memory")
-
 #if __has_feature(shadow_call_stack)
 # define __noscs	__attribute__((__no_sanitize__("shadow-call-stack")))
 #endif
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index 5deb37024574..74c6c0486eed 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -15,25 +15,6 @@
 # error Sorry, your version of GCC is too old - please use 4.9 or newer.
 #endif
 
-/* Optimization barrier */
-
-/* The "volatile" is due to gcc bugs */
-#define barrier() __asm__ __volatile__("": : :"memory")
-/*
- * This version is i.e. to prevent dead stores elimination on @ptr
- * where gcc and llvm may behave differently when otherwise using
- * normal barrier(): while gcc behavior gets along with a normal
- * barrier(), llvm needs an explicit input variable to be assumed
- * clobbered. The issue is as follows: while the inline asm might
- * access any memory it wants, the compiler could have fit all of
- * @ptr into memory registers instead, and since @ptr never escaped
- * from that, it proved that the inline asm wasn't touching any of
- * it. This version works well with both compilers, i.e. we're telling
- * the compiler that the inline asm absolutely may see the contents
- * of @ptr. See also: https://llvm.org/bugs/show_bug.cgi?id=15495
- */
-#define barrier_data(ptr) __asm__ __volatile__("": :"r"(ptr) :"memory")
-
 /*
  * This macro obfuscates arithmetic on a variable address so that gcc
  * shouldn't recognize the original var, and make assumptions about it.
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index e512f5505dad..b8fe0c23cfff 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -80,11 +80,25 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 
 /* Optimization barrier */
 #ifndef barrier
-# define barrier() __memory_barrier()
+/* The "volatile" is due to gcc bugs */
+# define barrier() __asm__ __volatile__("": : :"memory")
 #endif
 
 #ifndef barrier_data
-# define barrier_data(ptr) barrier()
+/*
+ * This version is i.e. to prevent dead stores elimination on @ptr
+ * where gcc and llvm may behave differently when otherwise using
+ * normal barrier(): while gcc behavior gets along with a normal
+ * barrier(), llvm needs an explicit input variable to be assumed
+ * clobbered. The issue is as follows: while the inline asm might
+ * access any memory it wants, the compiler could have fit all of
+ * @ptr into memory registers instead, and since @ptr never escaped
+ * from that, it proved that the inline asm wasn't touching any of
+ * it. This version works well with both compilers, i.e. we're telling
+ * the compiler that the inline asm absolutely may see the contents
+ * of @ptr. See also: https://llvm.org/bugs/show_bug.cgi?id=15495
+ */
+# define barrier_data(ptr) __asm__ __volatile__("": :"r"(ptr) :"memory")
 #endif
 
 /* workaround for GCC PR82365 if needed */
-- 
cgit v1.2.3


From 8b21ca0218d29cc6bb7028125c7e5a10dfb4730c Mon Sep 17 00:00:00 2001
From: Muchun Song <songmuchun@bytedance.com>
Date: Fri, 13 Nov 2020 22:52:13 -0800
Subject: mm: memcontrol: fix missing wakeup polling thread

When we poll the swap.events, we can miss being woken up when the swap
event occurs.  Because we didn't notify.

Fixes: f3a53a3a1e5b ("mm, memcontrol: implement memory.swap.events")
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Roman Gushchin <guro@fb.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Yafang Shao <laoar.shao@gmail.com>
Cc: Chris Down <chris@chrisdown.name>
Cc: Tejun Heo <tj@kernel.org>
Link: https://lkml.kernel.org/r/20201105161936.98312-1-songmuchun@bytedance.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index e391e3c56de5..a80c59af2c60 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -900,12 +900,19 @@ static inline void count_memcg_event_mm(struct mm_struct *mm,
 static inline void memcg_memory_event(struct mem_cgroup *memcg,
 				      enum memcg_memory_event event)
 {
+	bool swap_event = event == MEMCG_SWAP_HIGH || event == MEMCG_SWAP_MAX ||
+			  event == MEMCG_SWAP_FAIL;
+
 	atomic_long_inc(&memcg->memory_events_local[event]);
-	cgroup_file_notify(&memcg->events_local_file);
+	if (!swap_event)
+		cgroup_file_notify(&memcg->events_local_file);
 
 	do {
 		atomic_long_inc(&memcg->memory_events[event]);
-		cgroup_file_notify(&memcg->events_file);
+		if (swap_event)
+			cgroup_file_notify(&memcg->swap_events_file);
+		else
+			cgroup_file_notify(&memcg->events_file);
 
 		if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
 			break;
-- 
cgit v1.2.3


From 30d6f8c15d2cd877c1f3d47d8a1064649ebe58e2 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Wed, 21 Oct 2020 18:21:46 +0200
Subject: clk: add api to get clk consumer from clk_hw

clk_register() is deprecated. Using 'clk' member of struct clk_hw is
discouraged. With this constraint, it is difficult for driver to
register clocks using the clk_hw API and then use the clock with
the consumer API

This adds a simple helper, clk_hw_get_clk(), to get a struct clk from
a struct clk_hw. Like other clk_get() variant, each call to this helper
must be balanced with a call to clk_put(). To make life easier on the
consumers, a memory managed version is provided as well.

Cc: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Link: https://lore.kernel.org/r/20201021162147.563655-3-jbrunet@baylibre.com
Tested-by: Kevin Hilman <khilman@baylibre.com>
[sboyd@kernel.org: Fix kernel-doc]
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/clk.c            | 61 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/clk-provider.h |  5 ++++
 2 files changed, 66 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index f70dc0ef1cdd..48931f442de8 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -3667,6 +3667,24 @@ struct clk *clk_hw_create_clk(struct device *dev, struct clk_hw *hw,
 	return clk;
 }
 
+/**
+ * clk_hw_get_clk - get clk consumer given an clk_hw
+ * @hw: clk_hw associated with the clk being consumed
+ * @con_id: connection ID string on device
+ *
+ * Returns: new clk consumer
+ * This is the function to be used by providers which need
+ * to get a consumer clk and act on the clock element
+ * Calls to this function must be balanced with calls clk_put()
+ */
+struct clk *clk_hw_get_clk(struct clk_hw *hw, const char *con_id)
+{
+	struct device *dev = hw->core->dev;
+
+	return clk_hw_create_clk(dev, hw, dev_name(dev), con_id);
+}
+EXPORT_SYMBOL(clk_hw_get_clk);
+
 static int clk_cpy_name(const char **dst_p, const char *src, bool must_exist)
 {
 	const char *dst;
@@ -4187,6 +4205,49 @@ void devm_clk_hw_unregister(struct device *dev, struct clk_hw *hw)
 }
 EXPORT_SYMBOL_GPL(devm_clk_hw_unregister);
 
+static void devm_clk_release(struct device *dev, void *res)
+{
+	clk_put(*(struct clk **)res);
+}
+
+/**
+ * devm_clk_hw_get_clk - resource managed clk_hw_get_clk()
+ * @dev: device that is registering this clock
+ * @hw: clk_hw associated with the clk being consumed
+ * @con_id: connection ID string on device
+ *
+ * Managed clk_hw_get_clk(). Clocks got with this function are
+ * automatically clk_put() on driver detach. See clk_put()
+ * for more information.
+ */
+struct clk *devm_clk_hw_get_clk(struct device *dev, struct clk_hw *hw,
+				const char *con_id)
+{
+	struct clk *clk;
+	struct clk **clkp;
+
+	/* This should not happen because it would mean we have drivers
+	 * passing around clk_hw pointers instead of having the caller use
+	 * proper clk_get() style APIs
+	 */
+	WARN_ON_ONCE(dev != hw->core->dev);
+
+	clkp = devres_alloc(devm_clk_release, sizeof(*clkp), GFP_KERNEL);
+	if (!clkp)
+		return ERR_PTR(-ENOMEM);
+
+	clk = clk_hw_get_clk(hw, con_id);
+	if (!IS_ERR(clk)) {
+		*clkp = clk;
+		devres_add(dev, clkp);
+	} else {
+		devres_free(clkp);
+	}
+
+	return clk;
+}
+EXPORT_SYMBOL_GPL(devm_clk_hw_get_clk);
+
 /*
  * clkdev helpers
  */
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index 03a5de5f99f4..86b707520ec0 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -1088,6 +1088,11 @@ static inline struct clk_hw *__clk_get_hw(struct clk *clk)
 	return (struct clk_hw *)clk;
 }
 #endif
+
+struct clk *clk_hw_get_clk(struct clk_hw *hw, const char *con_id);
+struct clk *devm_clk_hw_get_clk(struct device *dev, struct clk_hw *hw,
+				const char *con_id);
+
 unsigned int clk_hw_get_num_parents(const struct clk_hw *hw);
 struct clk_hw *clk_hw_get_parent(const struct clk_hw *hw);
 struct clk_hw *clk_hw_get_parent_by_index(const struct clk_hw *hw,
-- 
cgit v1.2.3


From 6d30d50d037dfa092f9d5d1fffa348ab4abb7163 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Wed, 21 Oct 2020 18:38:46 +0200
Subject: clk: add devm variant of clk_notifier_register

Add a memory managed variant of clk_notifier_register() to make life easier
on clock consumers using notifiers

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Link: https://lore.kernel.org/r/20201021163847.595189-2-jbrunet@baylibre.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/clk.c   | 36 ++++++++++++++++++++++++++++++++++++
 include/linux/clk.h | 10 ++++++++++
 2 files changed, 46 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 48931f442de8..6cf59e3c31b4 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -4395,6 +4395,42 @@ int clk_notifier_unregister(struct clk *clk, struct notifier_block *nb)
 }
 EXPORT_SYMBOL_GPL(clk_notifier_unregister);
 
+struct clk_notifier_devres {
+	struct clk *clk;
+	struct notifier_block *nb;
+};
+
+static void devm_clk_notifier_release(struct device *dev, void *res)
+{
+	struct clk_notifier_devres *devres = res;
+
+	clk_notifier_unregister(devres->clk, devres->nb);
+}
+
+int devm_clk_notifier_register(struct device *dev, struct clk *clk,
+			       struct notifier_block *nb)
+{
+	struct clk_notifier_devres *devres;
+	int ret;
+
+	devres = devres_alloc(devm_clk_notifier_release,
+			      sizeof(*devres), GFP_KERNEL);
+
+	if (!devres)
+		return -ENOMEM;
+
+	ret = clk_notifier_register(clk, nb);
+	if (!ret) {
+		devres->clk = clk;
+		devres->nb = nb;
+	} else {
+		devres_free(devres);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(devm_clk_notifier_register);
+
 #ifdef CONFIG_OF
 static void clk_core_reparent_orphans(void)
 {
diff --git a/include/linux/clk.h b/include/linux/clk.h
index 7fd6a1febcf4..f53afdf8198b 100644
--- a/include/linux/clk.h
+++ b/include/linux/clk.h
@@ -109,6 +109,16 @@ int clk_notifier_register(struct clk *clk, struct notifier_block *nb);
  */
 int clk_notifier_unregister(struct clk *clk, struct notifier_block *nb);
 
+/**
+ * devm_clk_notifier_register - register a managed rate-change notifier callback
+ * @dev: device for clock "consumer"
+ * @clk: clock whose rate we are interested in
+ * @nb: notifier block with callback function pointer
+ *
+ * Returns 0 on success, -EERROR otherwise
+ */
+int devm_clk_notifier_register(struct device *dev, struct clk *clk, struct notifier_block *nb);
+
 /**
  * clk_get_accuracy - obtain the clock accuracy in ppb (parts per billion)
  *		      for a clock source.
-- 
cgit v1.2.3


From e6fb7aee486c7fbd4d94f4894feaa6f0424c1740 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Wed, 21 Oct 2020 18:38:47 +0200
Subject: clk: meson: g12: use devm variant to register notifiers

Until now, nothing was done to unregister the dvfs clock notifiers of the
Amlogic g12 SoC family. This is not great but this driver was not really
expected to be unloaded. With the ongoing effort to build everything as
module for this platform, this needs to be cleanly handled.

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Link: https://lore.kernel.org/r/20201021163847.595189-3-jbrunet@baylibre.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/meson/g12a.c | 34 ++++++++++++++++++++--------------
 include/linux/clk.h      | 10 +++++++++-
 2 files changed, 29 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/clk/meson/g12a.c b/drivers/clk/meson/g12a.c
index 235dcf72e34a..108e4491b1e2 100644
--- a/drivers/clk/meson/g12a.c
+++ b/drivers/clk/meson/g12a.c
@@ -5171,8 +5171,8 @@ static int meson_g12a_dvfs_setup_common(struct device *dev,
 	g12a_cpu_clk_postmux0_nb_data.xtal = xtal;
 	notifier_clk = devm_clk_hw_get_clk(dev, &g12a_cpu_clk_postmux0.hw,
 					   DVFS_CON_ID);
-	ret = clk_notifier_register(notifier_clk,
-				    &g12a_cpu_clk_postmux0_nb_data.nb);
+	ret = devm_clk_notifier_register(dev, notifier_clk,
+					 &g12a_cpu_clk_postmux0_nb_data.nb);
 	if (ret) {
 		dev_err(dev, "failed to register the cpu_clk_postmux0 notifier\n");
 		return ret;
@@ -5181,7 +5181,8 @@ static int meson_g12a_dvfs_setup_common(struct device *dev,
 	/* Setup clock notifier for cpu_clk_dyn mux */
 	notifier_clk = devm_clk_hw_get_clk(dev, &g12a_cpu_clk_dyn.hw,
 					   DVFS_CON_ID);
-	ret = clk_notifier_register(notifier_clk, &g12a_cpu_clk_mux_nb);
+	ret = devm_clk_notifier_register(dev, notifier_clk,
+					 &g12a_cpu_clk_mux_nb);
 	if (ret) {
 		dev_err(dev, "failed to register the cpu_clk_dyn notifier\n");
 		return ret;
@@ -5207,7 +5208,8 @@ static int meson_g12b_dvfs_setup(struct platform_device *pdev)
 	/* Setup clock notifier for cpu_clk mux */
 	notifier_clk = devm_clk_hw_get_clk(dev, &g12b_cpu_clk.hw,
 					   DVFS_CON_ID);
-	ret = clk_notifier_register(notifier_clk, &g12a_cpu_clk_mux_nb);
+	ret = devm_clk_notifier_register(dev, notifier_clk,
+					 &g12a_cpu_clk_mux_nb);
 	if (ret) {
 		dev_err(dev, "failed to register the cpu_clk notifier\n");
 		return ret;
@@ -5216,8 +5218,8 @@ static int meson_g12b_dvfs_setup(struct platform_device *pdev)
 	/* Setup clock notifier for sys1_pll */
 	notifier_clk = devm_clk_hw_get_clk(dev, &g12b_sys1_pll.hw,
 					   DVFS_CON_ID);
-	ret = clk_notifier_register(notifier_clk,
-				    &g12b_cpu_clk_sys1_pll_nb_data.nb);
+	ret = devm_clk_notifier_register(dev, notifier_clk,
+					 &g12b_cpu_clk_sys1_pll_nb_data.nb);
 	if (ret) {
 		dev_err(dev, "failed to register the sys1_pll notifier\n");
 		return ret;
@@ -5229,8 +5231,8 @@ static int meson_g12b_dvfs_setup(struct platform_device *pdev)
 	g12b_cpub_clk_postmux0_nb_data.xtal = xtal;
 	notifier_clk = devm_clk_hw_get_clk(dev, &g12b_cpub_clk_postmux0.hw,
 					   DVFS_CON_ID);
-	ret = clk_notifier_register(notifier_clk,
-				    &g12b_cpub_clk_postmux0_nb_data.nb);
+	ret = devm_clk_notifier_register(dev, notifier_clk,
+					 &g12b_cpub_clk_postmux0_nb_data.nb);
 	if (ret) {
 		dev_err(dev, "failed to register the cpub_clk_postmux0 notifier\n");
 		return ret;
@@ -5238,7 +5240,8 @@ static int meson_g12b_dvfs_setup(struct platform_device *pdev)
 
 	/* Setup clock notifier for cpub_clk_dyn mux */
 	notifier_clk = devm_clk_hw_get_clk(dev, &g12b_cpub_clk_dyn.hw, "dvfs");
-	ret = clk_notifier_register(notifier_clk, &g12a_cpu_clk_mux_nb);
+	ret = devm_clk_notifier_register(dev, notifier_clk,
+					 &g12a_cpu_clk_mux_nb);
 	if (ret) {
 		dev_err(dev, "failed to register the cpub_clk_dyn notifier\n");
 		return ret;
@@ -5246,7 +5249,8 @@ static int meson_g12b_dvfs_setup(struct platform_device *pdev)
 
 	/* Setup clock notifier for cpub_clk mux */
 	notifier_clk = devm_clk_hw_get_clk(dev, &g12b_cpub_clk.hw, DVFS_CON_ID);
-	ret = clk_notifier_register(notifier_clk, &g12a_cpu_clk_mux_nb);
+	ret = devm_clk_notifier_register(dev, notifier_clk,
+					 &g12a_cpu_clk_mux_nb);
 	if (ret) {
 		dev_err(dev, "failed to register the cpub_clk notifier\n");
 		return ret;
@@ -5254,8 +5258,8 @@ static int meson_g12b_dvfs_setup(struct platform_device *pdev)
 
 	/* Setup clock notifier for sys_pll */
 	notifier_clk = devm_clk_hw_get_clk(dev, &g12a_sys_pll.hw, DVFS_CON_ID);
-	ret = clk_notifier_register(notifier_clk,
-				    &g12b_cpub_clk_sys_pll_nb_data.nb);
+	ret = devm_clk_notifier_register(dev, notifier_clk,
+					 &g12b_cpub_clk_sys_pll_nb_data.nb);
 	if (ret) {
 		dev_err(dev, "failed to register the sys_pll notifier\n");
 		return ret;
@@ -5277,7 +5281,8 @@ static int meson_g12a_dvfs_setup(struct platform_device *pdev)
 
 	/* Setup clock notifier for cpu_clk mux */
 	notifier_clk = devm_clk_hw_get_clk(dev, &g12a_cpu_clk.hw, DVFS_CON_ID);
-	ret = clk_notifier_register(notifier_clk, &g12a_cpu_clk_mux_nb);
+	ret = devm_clk_notifier_register(dev, notifier_clk,
+				    &g12a_cpu_clk_mux_nb);
 	if (ret) {
 		dev_err(dev, "failed to register the cpu_clk notifier\n");
 		return ret;
@@ -5285,7 +5290,8 @@ static int meson_g12a_dvfs_setup(struct platform_device *pdev)
 
 	/* Setup clock notifier for sys_pll */
 	notifier_clk = devm_clk_hw_get_clk(dev, &g12a_sys_pll.hw, DVFS_CON_ID);
-	ret = clk_notifier_register(notifier_clk, &g12a_sys_pll_nb_data.nb);
+	ret = devm_clk_notifier_register(dev, notifier_clk,
+					 &g12a_sys_pll_nb_data.nb);
 	if (ret) {
 		dev_err(dev, "failed to register the sys_pll notifier\n");
 		return ret;
diff --git a/include/linux/clk.h b/include/linux/clk.h
index f53afdf8198b..4ac766dc3daf 100644
--- a/include/linux/clk.h
+++ b/include/linux/clk.h
@@ -117,7 +117,8 @@ int clk_notifier_unregister(struct clk *clk, struct notifier_block *nb);
  *
  * Returns 0 on success, -EERROR otherwise
  */
-int devm_clk_notifier_register(struct device *dev, struct clk *clk, struct notifier_block *nb);
+int devm_clk_notifier_register(struct device *dev, struct clk *clk,
+			       struct notifier_block *nb);
 
 /**
  * clk_get_accuracy - obtain the clock accuracy in ppb (parts per billion)
@@ -196,6 +197,13 @@ static inline int clk_notifier_unregister(struct clk *clk,
 	return -ENOTSUPP;
 }
 
+static inline int devm_clk_notifier_register(struct device *dev,
+					     struct clk *clk,
+					     struct notifier_block *nb)
+{
+	return -ENOTSUPP;
+}
+
 static inline long clk_get_accuracy(struct clk *clk)
 {
 	return -ENOTSUPP;
-- 
cgit v1.2.3


From f296dcd629aa412a80a53215e46087f53af87f08 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sat, 14 Nov 2020 22:01:45 +0100
Subject: genirq: Remove GENERIC_IRQ_LEGACY_ALLOC_HWIRQ

Commit bb9d812643d8 ("arch: remove tile port") removed the last user of
this cruft two years ago...

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/87eekvac06.fsf@nanos.tec.linutronix.de
---
 include/linux/irq.h  | 15 ---------------
 kernel/irq/Kconfig   |  5 -----
 kernel/irq/irqdesc.c | 51 ---------------------------------------------------
 3 files changed, 71 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index c54365309e97..79ce314a603b 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -954,21 +954,6 @@ static inline void irq_free_desc(unsigned int irq)
 	irq_free_descs(irq, 1);
 }
 
-#ifdef CONFIG_GENERIC_IRQ_LEGACY_ALLOC_HWIRQ
-unsigned int irq_alloc_hwirqs(int cnt, int node);
-static inline unsigned int irq_alloc_hwirq(int node)
-{
-	return irq_alloc_hwirqs(1, node);
-}
-void irq_free_hwirqs(unsigned int from, int cnt);
-static inline void irq_free_hwirq(unsigned int irq)
-{
-	return irq_free_hwirqs(irq, 1);
-}
-int arch_setup_hwirq(unsigned int irq, int node);
-void arch_teardown_hwirq(unsigned int irq);
-#endif
-
 #ifdef CONFIG_GENERIC_IRQ_LEGACY
 void irq_init_desc(unsigned int irq);
 #endif
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index 10a5aff4eecc..f2cda6b0057f 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -26,11 +26,6 @@ config GENERIC_IRQ_SHOW_LEVEL
 config GENERIC_IRQ_EFFECTIVE_AFF_MASK
        bool
 
-# Facility to allocate a hardware interrupt. This is legacy support
-# and should not be used in new code. Use irq domains instead.
-config GENERIC_IRQ_LEGACY_ALLOC_HWIRQ
-       bool
-
 # Support for delayed migration from interrupt context
 config GENERIC_PENDING_IRQ
 	bool
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 1a7723604399..e810eb9906ea 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -810,57 +810,6 @@ unlock:
 }
 EXPORT_SYMBOL_GPL(__irq_alloc_descs);
 
-#ifdef CONFIG_GENERIC_IRQ_LEGACY_ALLOC_HWIRQ
-/**
- * irq_alloc_hwirqs - Allocate an irq descriptor and initialize the hardware
- * @cnt:	number of interrupts to allocate
- * @node:	node on which to allocate
- *
- * Returns an interrupt number > 0 or 0, if the allocation fails.
- */
-unsigned int irq_alloc_hwirqs(int cnt, int node)
-{
-	int i, irq = __irq_alloc_descs(-1, 0, cnt, node, NULL, NULL);
-
-	if (irq < 0)
-		return 0;
-
-	for (i = irq; cnt > 0; i++, cnt--) {
-		if (arch_setup_hwirq(i, node))
-			goto err;
-		irq_clear_status_flags(i, _IRQ_NOREQUEST);
-	}
-	return irq;
-
-err:
-	for (i--; i >= irq; i--) {
-		irq_set_status_flags(i, _IRQ_NOREQUEST | _IRQ_NOPROBE);
-		arch_teardown_hwirq(i);
-	}
-	irq_free_descs(irq, cnt);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(irq_alloc_hwirqs);
-
-/**
- * irq_free_hwirqs - Free irq descriptor and cleanup the hardware
- * @from:	Free from irq number
- * @cnt:	number of interrupts to free
- *
- */
-void irq_free_hwirqs(unsigned int from, int cnt)
-{
-	int i, j;
-
-	for (i = from, j = cnt; j > 0; i++, j--) {
-		irq_set_status_flags(i, _IRQ_NOREQUEST | _IRQ_NOPROBE);
-		arch_teardown_hwirq(i);
-	}
-	irq_free_descs(from, cnt);
-}
-EXPORT_SYMBOL_GPL(irq_free_hwirqs);
-#endif
-
 /**
  * irq_get_next_irq - get next allocated irq number
  * @offset:	where to start the search
-- 
cgit v1.2.3


From e906a546bd8653ed2e7a14cb300fd17952d7f862 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sat, 14 Nov 2020 23:36:28 +0100
Subject: genirq/irqdomain: Make irq_domain_disassociate() static

No users outside of the core code.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/87a6vja7mb.fsf@nanos.tec.linutronix.de
---
 include/linux/irqdomain.h | 2 --
 kernel/irq/irqdomain.c    | 2 +-
 2 files changed, 1 insertion(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index 77bf7d84c673..5701a8b01726 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -387,8 +387,6 @@ extern int irq_domain_associate(struct irq_domain *domain, unsigned int irq,
 extern void irq_domain_associate_many(struct irq_domain *domain,
 				      unsigned int irq_base,
 				      irq_hw_number_t hwirq_base, int count);
-extern void irq_domain_disassociate(struct irq_domain *domain,
-				    unsigned int irq);
 
 extern unsigned int irq_create_mapping(struct irq_domain *host,
 				       irq_hw_number_t hwirq);
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 9c9cb8829f7a..3d7463fd6453 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -496,7 +496,7 @@ static void irq_domain_set_mapping(struct irq_domain *domain,
 	}
 }
 
-void irq_domain_disassociate(struct irq_domain *domain, unsigned int irq)
+static void irq_domain_disassociate(struct irq_domain *domain, unsigned int irq)
 {
 	struct irq_data *irq_data = irq_get_irq_data(irq);
 	irq_hw_number_t hwirq;
-- 
cgit v1.2.3


From c4d51a52c67a1e3a0fa3006e5ec21cdc07649cd6 Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw@amazon.co.uk>
Date: Tue, 27 Oct 2020 14:39:43 +0000
Subject: sched/wait: Add add_wait_queue_priority()

This allows an exclusive wait_queue_entry to be added at the head of the
queue, instead of the tail as normal. Thus, it gets to consume events
first without allowing non-exclusive waiters to be woken at all.

The (first) intended use is for KVM IRQFD, which currently has
inconsistent behaviour depending on whether posted interrupts are
available or not. If they are, KVM will bypass the eventfd completely
and deliver interrupts directly to the appropriate vCPU. If not, events
are delivered through the eventfd and userspace will receive them when
polling on the eventfd.

By using add_wait_queue_priority(), KVM will be able to consistently
consume events within the kernel without accidentally exposing them
to userspace when they're supposed to be bypassed. This, in turn, means
that userspace doesn't have to jump through hoops to avoid listening
on the erroneously noisy eventfd and injecting duplicate interrupts.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Message-Id: <20201027143944.648769-2-dwmw2@infradead.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/wait.h | 12 +++++++++++-
 kernel/sched/wait.c  | 17 ++++++++++++++++-
 2 files changed, 27 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/wait.h b/include/linux/wait.h
index 27fb99cfeb02..fe10e8570a52 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -22,6 +22,7 @@ int default_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int
 #define WQ_FLAG_BOOKMARK	0x04
 #define WQ_FLAG_CUSTOM		0x08
 #define WQ_FLAG_DONE		0x10
+#define WQ_FLAG_PRIORITY	0x20
 
 /*
  * A single wait-queue entry structure:
@@ -164,11 +165,20 @@ static inline bool wq_has_sleeper(struct wait_queue_head *wq_head)
 
 extern void add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
 extern void add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
+extern void add_wait_queue_priority(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
 extern void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
 
 static inline void __add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
 {
-	list_add(&wq_entry->entry, &wq_head->head);
+	struct list_head *head = &wq_head->head;
+	struct wait_queue_entry *wq;
+
+	list_for_each_entry(wq, &wq_head->head, entry) {
+		if (!(wq->flags & WQ_FLAG_PRIORITY))
+			break;
+		head = &wq->entry;
+	}
+	list_add(&wq_entry->entry, head);
 }
 
 /*
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 01f5d3020589..183cc6ae68a6 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -37,6 +37,17 @@ void add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue
 }
 EXPORT_SYMBOL(add_wait_queue_exclusive);
 
+void add_wait_queue_priority(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
+{
+	unsigned long flags;
+
+	wq_entry->flags |= WQ_FLAG_EXCLUSIVE | WQ_FLAG_PRIORITY;
+	spin_lock_irqsave(&wq_head->lock, flags);
+	__add_wait_queue(wq_head, wq_entry);
+	spin_unlock_irqrestore(&wq_head->lock, flags);
+}
+EXPORT_SYMBOL_GPL(add_wait_queue_priority);
+
 void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
 {
 	unsigned long flags;
@@ -57,7 +68,11 @@ EXPORT_SYMBOL(remove_wait_queue);
 /*
  * The core wakeup function. Non-exclusive wakeups (nr_exclusive == 0) just
  * wake everything up. If it's an exclusive wakeup (nr_exclusive == small +ve
- * number) then we wake all the non-exclusive tasks and one exclusive task.
+ * number) then we wake that number of exclusive tasks, and potentially all
+ * the non-exclusive tasks. Normally, exclusive tasks will be at the end of
+ * the list and any non-exclusive tasks will be woken first. A priority task
+ * may be at the head of the list, and can consume the event without any other
+ * tasks being woken.
  *
  * There are circumstances in which we can try to wake a task which has already
  * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
-- 
cgit v1.2.3


From 28f1326710555bbe666f64452d08f2d7dd657cae Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw@amazon.co.uk>
Date: Tue, 27 Oct 2020 13:55:21 +0000
Subject: eventfd: Export eventfd_ctx_do_read()

Where events are consumed in the kernel, for example by KVM's
irqfd_wakeup() and VFIO's virqfd_wakeup(), they currently lack a
mechanism to drain the eventfd's counter.

Since the wait queue is already locked while the wakeup functions are
invoked, all they really need to do is call eventfd_ctx_do_read().

Add a check for the lock, and export it for them.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Message-Id: <20201027135523.646811-2-dwmw2@infradead.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 fs/eventfd.c            | 5 ++++-
 include/linux/eventfd.h | 6 ++++++
 2 files changed, 10 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/fs/eventfd.c b/fs/eventfd.c
index df466ef81ddd..e265b6dd4f34 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -182,11 +182,14 @@ static __poll_t eventfd_poll(struct file *file, poll_table *wait)
 	return events;
 }
 
-static void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt)
+void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt)
 {
+	lockdep_assert_held(&ctx->wqh.lock);
+
 	*cnt = (ctx->flags & EFD_SEMAPHORE) ? 1 : ctx->count;
 	ctx->count -= *cnt;
 }
+EXPORT_SYMBOL_GPL(eventfd_ctx_do_read);
 
 /**
  * eventfd_ctx_remove_wait_queue - Read the current counter and removes wait queue.
diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h
index dc4fd8a6644d..fa0a524baed0 100644
--- a/include/linux/eventfd.h
+++ b/include/linux/eventfd.h
@@ -41,6 +41,7 @@ struct eventfd_ctx *eventfd_ctx_fileget(struct file *file);
 __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n);
 int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait,
 				  __u64 *cnt);
+void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt);
 
 DECLARE_PER_CPU(int, eventfd_wake_count);
 
@@ -82,6 +83,11 @@ static inline bool eventfd_signal_count(void)
 	return false;
 }
 
+static inline void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt)
+{
+
+}
+
 #endif
 
 #endif /* _LINUX_EVENTFD_H */
-- 
cgit v1.2.3


From 2f5414423ef577e9e8bdb227f32d0abdd34e4274 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Fri, 6 Nov 2020 05:25:09 -0500
Subject: KVM: remove kvm_clear_guest_page

kvm_clear_guest_page is not used anymore after "KVM: X86: Don't track dirty
for KVM_SET_[TSS_ADDR|IDENTITY_MAP_ADDR]", except from kvm_clear_guest.
We can just inline it in its sole user.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/kvm_host.h |  1 -
 virt/kvm/kvm_main.c      | 11 ++---------
 2 files changed, 2 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 7f2e2a09ebbd..66a4324f329d 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -792,7 +792,6 @@ int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 			offset_in_page(__gpa), v);			\
 })
 
-int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len);
 int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len);
 struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn);
 bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 2541a17ff1c4..1c7514579861 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2616,23 +2616,16 @@ int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 }
 EXPORT_SYMBOL_GPL(kvm_read_guest_cached);
 
-int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len)
-{
-	const void *zero_page = (const void *) __va(page_to_phys(ZERO_PAGE(0)));
-
-	return kvm_write_guest_page(kvm, gfn, zero_page, offset, len);
-}
-EXPORT_SYMBOL_GPL(kvm_clear_guest_page);
-
 int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len)
 {
+	const void *zero_page = (const void *) __va(page_to_phys(ZERO_PAGE(0)));
 	gfn_t gfn = gpa >> PAGE_SHIFT;
 	int seg;
 	int offset = offset_in_page(gpa);
 	int ret;
 
 	while ((seg = next_segment(len, offset)) != 0) {
-		ret = kvm_clear_guest_page(kvm, gfn, offset, seg);
+		ret = kvm_write_guest_page(kvm, gfn, zero_page, offset, len);
 		if (ret < 0)
 			return ret;
 		offset = 0;
-- 
cgit v1.2.3


From 28bd726aa404c0da8fd6852fe69bb4538a103b71 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Wed, 30 Sep 2020 21:20:34 -0400
Subject: KVM: Pass in kvm pointer into mark_page_dirty_in_slot()

The context will be needed to implement the kvm dirty ring.

Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20201001012044.5151-5-peterx@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/kvm_host.h |  2 +-
 virt/kvm/kvm_main.c      | 30 +++++++++++++++++-------------
 2 files changed, 18 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 66a4324f329d..ca7c1459a8e3 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -797,7 +797,7 @@ struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn);
 bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn);
 bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn);
 unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn);
-void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot, gfn_t gfn);
+void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_memory_slot *memslot, gfn_t gfn);
 void mark_page_dirty(struct kvm *kvm, gfn_t gfn);
 
 struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 1c7514579861..68598fdba226 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2196,7 +2196,8 @@ int kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map)
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_map);
 
-static void __kvm_unmap_gfn(struct kvm_memory_slot *memslot,
+static void __kvm_unmap_gfn(struct kvm *kvm,
+			struct kvm_memory_slot *memslot,
 			struct kvm_host_map *map,
 			struct gfn_to_pfn_cache *cache,
 			bool dirty, bool atomic)
@@ -2221,7 +2222,7 @@ static void __kvm_unmap_gfn(struct kvm_memory_slot *memslot,
 #endif
 
 	if (dirty)
-		mark_page_dirty_in_slot(memslot, map->gfn);
+		mark_page_dirty_in_slot(kvm, memslot, map->gfn);
 
 	if (cache)
 		cache->dirty |= dirty;
@@ -2235,7 +2236,7 @@ static void __kvm_unmap_gfn(struct kvm_memory_slot *memslot,
 int kvm_unmap_gfn(struct kvm_vcpu *vcpu, struct kvm_host_map *map, 
 		  struct gfn_to_pfn_cache *cache, bool dirty, bool atomic)
 {
-	__kvm_unmap_gfn(gfn_to_memslot(vcpu->kvm, map->gfn), map,
+	__kvm_unmap_gfn(vcpu->kvm, gfn_to_memslot(vcpu->kvm, map->gfn), map,
 			cache, dirty, atomic);
 	return 0;
 }
@@ -2243,8 +2244,8 @@ EXPORT_SYMBOL_GPL(kvm_unmap_gfn);
 
 void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty)
 {
-	__kvm_unmap_gfn(kvm_vcpu_gfn_to_memslot(vcpu, map->gfn), map, NULL,
-			dirty, false);
+	__kvm_unmap_gfn(vcpu->kvm, kvm_vcpu_gfn_to_memslot(vcpu, map->gfn),
+			map, NULL, dirty, false);
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_unmap);
 
@@ -2418,7 +2419,8 @@ int kvm_vcpu_read_guest_atomic(struct kvm_vcpu *vcpu, gpa_t gpa,
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_read_guest_atomic);
 
-static int __kvm_write_guest_page(struct kvm_memory_slot *memslot, gfn_t gfn,
+static int __kvm_write_guest_page(struct kvm *kvm,
+				  struct kvm_memory_slot *memslot, gfn_t gfn,
 			          const void *data, int offset, int len)
 {
 	int r;
@@ -2430,7 +2432,7 @@ static int __kvm_write_guest_page(struct kvm_memory_slot *memslot, gfn_t gfn,
 	r = __copy_to_user((void __user *)addr + offset, data, len);
 	if (r)
 		return -EFAULT;
-	mark_page_dirty_in_slot(memslot, gfn);
+	mark_page_dirty_in_slot(kvm, memslot, gfn);
 	return 0;
 }
 
@@ -2439,7 +2441,7 @@ int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn,
 {
 	struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
 
-	return __kvm_write_guest_page(slot, gfn, data, offset, len);
+	return __kvm_write_guest_page(kvm, slot, gfn, data, offset, len);
 }
 EXPORT_SYMBOL_GPL(kvm_write_guest_page);
 
@@ -2448,7 +2450,7 @@ int kvm_vcpu_write_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn,
 {
 	struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
 
-	return __kvm_write_guest_page(slot, gfn, data, offset, len);
+	return __kvm_write_guest_page(vcpu->kvm, slot, gfn, data, offset, len);
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_write_guest_page);
 
@@ -2567,7 +2569,7 @@ int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 	r = __copy_to_user((void __user *)ghc->hva + offset, data, len);
 	if (r)
 		return -EFAULT;
-	mark_page_dirty_in_slot(ghc->memslot, gpa >> PAGE_SHIFT);
+	mark_page_dirty_in_slot(kvm, ghc->memslot, gpa >> PAGE_SHIFT);
 
 	return 0;
 }
@@ -2636,7 +2638,9 @@ int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len)
 }
 EXPORT_SYMBOL_GPL(kvm_clear_guest);
 
-void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot, gfn_t gfn)
+void mark_page_dirty_in_slot(struct kvm *kvm,
+			     struct kvm_memory_slot *memslot,
+		 	     gfn_t gfn)
 {
 	if (memslot && memslot->dirty_bitmap) {
 		unsigned long rel_gfn = gfn - memslot->base_gfn;
@@ -2651,7 +2655,7 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn)
 	struct kvm_memory_slot *memslot;
 
 	memslot = gfn_to_memslot(kvm, gfn);
-	mark_page_dirty_in_slot(memslot, gfn);
+	mark_page_dirty_in_slot(kvm, memslot, gfn);
 }
 EXPORT_SYMBOL_GPL(mark_page_dirty);
 
@@ -2660,7 +2664,7 @@ void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn)
 	struct kvm_memory_slot *memslot;
 
 	memslot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
-	mark_page_dirty_in_slot(memslot, gfn);
+	mark_page_dirty_in_slot(vcpu->kvm, memslot, gfn);
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_mark_page_dirty);
 
-- 
cgit v1.2.3


From fb04a1eddb1a65b6588a021bdc132270d5ae48bb Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Wed, 30 Sep 2020 21:22:22 -0400
Subject: KVM: X86: Implement ring-based dirty memory tracking

This patch is heavily based on previous work from Lei Cao
<lei.cao@stratus.com> and Paolo Bonzini <pbonzini@redhat.com>. [1]

KVM currently uses large bitmaps to track dirty memory.  These bitmaps
are copied to userspace when userspace queries KVM for its dirty page
information.  The use of bitmaps is mostly sufficient for live
migration, as large parts of memory are be dirtied from one log-dirty
pass to another.  However, in a checkpointing system, the number of
dirty pages is small and in fact it is often bounded---the VM is
paused when it has dirtied a pre-defined number of pages. Traversing a
large, sparsely populated bitmap to find set bits is time-consuming,
as is copying the bitmap to user-space.

A similar issue will be there for live migration when the guest memory
is huge while the page dirty procedure is trivial.  In that case for
each dirty sync we need to pull the whole dirty bitmap to userspace
and analyse every bit even if it's mostly zeros.

The preferred data structure for above scenarios is a dense list of
guest frame numbers (GFN).  This patch series stores the dirty list in
kernel memory that can be memory mapped into userspace to allow speedy
harvesting.

This patch enables dirty ring for X86 only.  However it should be
easily extended to other archs as well.

[1] https://patchwork.kernel.org/patch/10471409/

Signed-off-by: Lei Cao <lei.cao@stratus.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20201001012222.5767-1-peterx@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virt/kvm/api.rst  |  93 +++++++++++++++++++
 arch/x86/include/asm/kvm_host.h |   3 +
 arch/x86/include/uapi/asm/kvm.h |   1 +
 arch/x86/kvm/Makefile           |   3 +-
 arch/x86/kvm/mmu/mmu.c          |   8 ++
 arch/x86/kvm/mmu/tdp_mmu.c      |   2 +-
 arch/x86/kvm/vmx/vmx.c          |   7 ++
 arch/x86/kvm/x86.c              |   9 ++
 include/linux/kvm_dirty_ring.h  | 103 +++++++++++++++++++++
 include/linux/kvm_host.h        |  13 +++
 include/trace/events/kvm.h      |  63 +++++++++++++
 include/uapi/linux/kvm.h        |  53 +++++++++++
 virt/kvm/dirty_ring.c           | 194 ++++++++++++++++++++++++++++++++++++++++
 virt/kvm/kvm_main.c             | 113 ++++++++++++++++++++++-
 14 files changed, 662 insertions(+), 3 deletions(-)
 create mode 100644 include/linux/kvm_dirty_ring.h
 create mode 100644 virt/kvm/dirty_ring.c

(limited to 'include/linux')

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 81d54fe76a2d..e264ebc35e27 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -262,6 +262,18 @@ The KVM_RUN ioctl (cf.) communicates with userspace via a shared
 memory region.  This ioctl returns the size of that region.  See the
 KVM_RUN documentation for details.
 
+Besides the size of the KVM_RUN communication region, other areas of
+the VCPU file descriptor can be mmap-ed, including:
+
+- if KVM_CAP_COALESCED_MMIO is available, a page at
+  KVM_COALESCED_MMIO_PAGE_OFFSET * PAGE_SIZE; for historical reasons,
+  this page is included in the result of KVM_GET_VCPU_MMAP_SIZE.
+  KVM_CAP_COALESCED_MMIO is not documented yet.
+
+- if KVM_CAP_DIRTY_LOG_RING is available, a number of pages at
+  KVM_DIRTY_LOG_PAGE_OFFSET * PAGE_SIZE.  For more information on
+  KVM_CAP_DIRTY_LOG_RING, see section 8.3.
+
 
 4.6 KVM_SET_MEMORY_REGION
 -------------------------
@@ -6396,3 +6408,84 @@ When enabled, KVM will disable paravirtual features provided to the
 guest according to the bits in the KVM_CPUID_FEATURES CPUID leaf
 (0x40000001). Otherwise, a guest may use the paravirtual features
 regardless of what has actually been exposed through the CPUID leaf.
+
+
+8.29 KVM_CAP_DIRTY_LOG_RING
+---------------------------
+
+:Architectures: x86
+:Parameters: args[0] - size of the dirty log ring
+
+KVM is capable of tracking dirty memory using ring buffers that are
+mmaped into userspace; there is one dirty ring per vcpu.
+
+The dirty ring is available to userspace as an array of
+``struct kvm_dirty_gfn``.  Each dirty entry it's defined as::
+
+  struct kvm_dirty_gfn {
+          __u32 flags;
+          __u32 slot; /* as_id | slot_id */
+          __u64 offset;
+  };
+
+The following values are defined for the flags field to define the
+current state of the entry::
+
+  #define KVM_DIRTY_GFN_F_DIRTY           BIT(0)
+  #define KVM_DIRTY_GFN_F_RESET           BIT(1)
+  #define KVM_DIRTY_GFN_F_MASK            0x3
+
+Userspace should call KVM_ENABLE_CAP ioctl right after KVM_CREATE_VM
+ioctl to enable this capability for the new guest and set the size of
+the rings.  Enabling the capability is only allowed before creating any
+vCPU, and the size of the ring must be a power of two.  The larger the
+ring buffer, the less likely the ring is full and the VM is forced to
+exit to userspace. The optimal size depends on the workload, but it is
+recommended that it be at least 64 KiB (4096 entries).
+
+Just like for dirty page bitmaps, the buffer tracks writes to
+all user memory regions for which the KVM_MEM_LOG_DIRTY_PAGES flag was
+set in KVM_SET_USER_MEMORY_REGION.  Once a memory region is registered
+with the flag set, userspace can start harvesting dirty pages from the
+ring buffer.
+
+An entry in the ring buffer can be unused (flag bits ``00``),
+dirty (flag bits ``01``) or harvested (flag bits ``1X``).  The
+state machine for the entry is as follows::
+
+          dirtied         harvested        reset
+     00 -----------> 01 -------------> 1X -------+
+      ^                                          |
+      |                                          |
+      +------------------------------------------+
+
+To harvest the dirty pages, userspace accesses the mmaped ring buffer
+to read the dirty GFNs.  If the flags has the DIRTY bit set (at this stage
+the RESET bit must be cleared), then it means this GFN is a dirty GFN.
+The userspace should harvest this GFN and mark the flags from state
+``01b`` to ``1Xb`` (bit 0 will be ignored by KVM, but bit 1 must be set
+to show that this GFN is harvested and waiting for a reset), and move
+on to the next GFN.  The userspace should continue to do this until the
+flags of a GFN have the DIRTY bit cleared, meaning that it has harvested
+all the dirty GFNs that were available.
+
+It's not necessary for userspace to harvest the all dirty GFNs at once.
+However it must collect the dirty GFNs in sequence, i.e., the userspace
+program cannot skip one dirty GFN to collect the one next to it.
+
+After processing one or more entries in the ring buffer, userspace
+calls the VM ioctl KVM_RESET_DIRTY_RINGS to notify the kernel about
+it, so that the kernel will reprotect those collected GFNs.
+Therefore, the ioctl must be called *before* reading the content of
+the dirty pages.
+
+The dirty ring can get full.  When it happens, the KVM_RUN of the
+vcpu will return with exit reason KVM_EXIT_DIRTY_LOG_FULL.
+
+The dirty ring interface has a major difference comparing to the
+KVM_GET_DIRTY_LOG interface in that, when reading the dirty ring from
+userspace, it's still possible that the kernel has not yet flushed the
+processor's dirty page buffers into the kernel buffer (with dirty bitmaps, the
+flushing is done by the KVM_GET_DIRTY_LOG ioctl).  To achieve that, one
+needs to kick the vcpu out of KVM_RUN using a signal.  The resulting
+vmexit ensures that all dirty GFNs are flushed to the dirty rings.
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 69e94aa716e9..f002cdb13a0b 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1232,6 +1232,7 @@ struct kvm_x86_ops {
 	void (*enable_log_dirty_pt_masked)(struct kvm *kvm,
 					   struct kvm_memory_slot *slot,
 					   gfn_t offset, unsigned long mask);
+	int (*cpu_dirty_log_size)(void);
 
 	/* pmu operations of sub-arch */
 	const struct kvm_pmu_ops *pmu_ops;
@@ -1744,4 +1745,6 @@ static inline int kvm_cpu_get_apicid(int mps_cpu)
 #define GET_SMSTATE(type, buf, offset)		\
 	(*(type *)((buf) + (offset) - 0x7e00))
 
+int kvm_cpu_dirty_log_size(void);
+
 #endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 89e5f3d1bba8..8e76d3701db3 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -12,6 +12,7 @@
 
 #define KVM_PIO_PAGE_OFFSET 1
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2
+#define KVM_DIRTY_LOG_PAGE_OFFSET 64
 
 #define DE_VECTOR 0
 #define DB_VECTOR 1
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index b804444e16d4..4bd14ab01323 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -10,7 +10,8 @@ endif
 KVM := ../../../virt/kvm
 
 kvm-y			+= $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \
-				$(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o
+				$(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o \
+				$(KVM)/dirty_ring.o
 kvm-$(CONFIG_KVM_ASYNC_PF)	+= $(KVM)/async_pf.o
 
 kvm-y			+= x86.o emulate.o i8259.o irq.o lapic.o \
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 5bb1939b65d8..12e5cfe0995e 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1289,6 +1289,14 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
 		kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
 }
 
+int kvm_cpu_dirty_log_size(void)
+{
+	if (kvm_x86_ops.cpu_dirty_log_size)
+		return kvm_x86_ops.cpu_dirty_log_size();
+
+	return 0;
+}
+
 bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
 				    struct kvm_memory_slot *slot, u64 gfn)
 {
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index ff28a5c6abd6..cffa51c6049e 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -185,7 +185,7 @@ static void handle_changed_spte_dirty_log(struct kvm *kvm, int as_id, gfn_t gfn,
 	if ((!is_writable_pte(old_spte) || pfn_changed) &&
 	    is_writable_pte(new_spte)) {
 		slot = __gfn_to_memslot(__kvm_memslots(kvm, as_id), gfn);
-		mark_page_dirty_in_slot(slot, gfn);
+		mark_page_dirty_in_slot(kvm, slot, gfn);
 	}
 }
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 46b32aa43811..2b6d538454a6 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -7583,6 +7583,11 @@ static bool vmx_check_apicv_inhibit_reasons(ulong bit)
 	return supported & BIT(bit);
 }
 
+static int vmx_cpu_dirty_log_size(void)
+{
+	return enable_pml ? PML_ENTITY_NUM : 0;
+}
+
 static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.hardware_unsetup = hardware_unsetup,
 
@@ -7712,6 +7717,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.migrate_timers = vmx_migrate_timers,
 
 	.msr_filter_changed = vmx_msr_filter_changed,
+	.cpu_dirty_log_size = vmx_cpu_dirty_log_size,
 };
 
 static __init int hardware_setup(void)
@@ -7829,6 +7835,7 @@ static __init int hardware_setup(void)
 		vmx_x86_ops.slot_disable_log_dirty = NULL;
 		vmx_x86_ops.flush_log_dirty = NULL;
 		vmx_x86_ops.enable_log_dirty_pt_masked = NULL;
+		vmx_x86_ops.cpu_dirty_log_size = NULL;
 	}
 
 	if (!cpu_has_vmx_preemption_timer())
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b4ac726526f8..6c704a597b7c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8754,6 +8754,15 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 	bool req_immediate_exit = false;
 
+	/* Forbid vmenter if vcpu dirty ring is soft-full */
+	if (unlikely(vcpu->kvm->dirty_ring_size &&
+		     kvm_dirty_ring_soft_full(&vcpu->dirty_ring))) {
+		vcpu->run->exit_reason = KVM_EXIT_DIRTY_RING_FULL;
+		trace_kvm_dirty_ring_exit(vcpu);
+		r = 0;
+		goto out;
+	}
+
 	if (kvm_request_pending(vcpu)) {
 		if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) {
 			if (unlikely(!kvm_x86_ops.nested_ops->get_nested_state_pages(vcpu))) {
diff --git a/include/linux/kvm_dirty_ring.h b/include/linux/kvm_dirty_ring.h
new file mode 100644
index 000000000000..120e5e90fa1d
--- /dev/null
+++ b/include/linux/kvm_dirty_ring.h
@@ -0,0 +1,103 @@
+#ifndef KVM_DIRTY_RING_H
+#define KVM_DIRTY_RING_H
+
+#include <linux/kvm.h>
+
+/**
+ * kvm_dirty_ring: KVM internal dirty ring structure
+ *
+ * @dirty_index: free running counter that points to the next slot in
+ *               dirty_ring->dirty_gfns, where a new dirty page should go
+ * @reset_index: free running counter that points to the next dirty page
+ *               in dirty_ring->dirty_gfns for which dirty trap needs to
+ *               be reenabled
+ * @size:        size of the compact list, dirty_ring->dirty_gfns
+ * @soft_limit:  when the number of dirty pages in the list reaches this
+ *               limit, vcpu that owns this ring should exit to userspace
+ *               to allow userspace to harvest all the dirty pages
+ * @dirty_gfns:  the array to keep the dirty gfns
+ * @index:       index of this dirty ring
+ */
+struct kvm_dirty_ring {
+	u32 dirty_index;
+	u32 reset_index;
+	u32 size;
+	u32 soft_limit;
+	struct kvm_dirty_gfn *dirty_gfns;
+	int index;
+};
+
+#if (KVM_DIRTY_LOG_PAGE_OFFSET == 0)
+/*
+ * If KVM_DIRTY_LOG_PAGE_OFFSET not defined, kvm_dirty_ring.o should
+ * not be included as well, so define these nop functions for the arch.
+ */
+static inline u32 kvm_dirty_ring_get_rsvd_entries(void)
+{
+	return 0;
+}
+
+static inline int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring,
+				       int index, u32 size)
+{
+	return 0;
+}
+
+static inline struct kvm_dirty_ring *kvm_dirty_ring_get(struct kvm *kvm)
+{
+	return NULL;
+}
+
+static inline int kvm_dirty_ring_reset(struct kvm *kvm,
+				       struct kvm_dirty_ring *ring)
+{
+	return 0;
+}
+
+static inline void kvm_dirty_ring_push(struct kvm_dirty_ring *ring,
+				       u32 slot, u64 offset)
+{
+}
+
+static inline struct page *kvm_dirty_ring_get_page(struct kvm_dirty_ring *ring,
+						   u32 offset)
+{
+	return NULL;
+}
+
+static inline void kvm_dirty_ring_free(struct kvm_dirty_ring *ring)
+{
+}
+
+static inline bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring)
+{
+	return true;
+}
+
+#else /* KVM_DIRTY_LOG_PAGE_OFFSET == 0 */
+
+u32 kvm_dirty_ring_get_rsvd_entries(void);
+int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size);
+struct kvm_dirty_ring *kvm_dirty_ring_get(struct kvm *kvm);
+
+/*
+ * called with kvm->slots_lock held, returns the number of
+ * processed pages.
+ */
+int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring);
+
+/*
+ * returns =0: successfully pushed
+ *         <0: unable to push, need to wait
+ */
+void kvm_dirty_ring_push(struct kvm_dirty_ring *ring, u32 slot, u64 offset);
+
+/* for use in vm_operations_struct */
+struct page *kvm_dirty_ring_get_page(struct kvm_dirty_ring *ring, u32 offset);
+
+void kvm_dirty_ring_free(struct kvm_dirty_ring *ring);
+bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring);
+
+#endif /* KVM_DIRTY_LOG_PAGE_OFFSET == 0 */
+
+#endif	/* KVM_DIRTY_RING_H */
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index ca7c1459a8e3..864b156391c8 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -34,6 +34,7 @@
 #include <linux/kvm_types.h>
 
 #include <asm/kvm_host.h>
+#include <linux/kvm_dirty_ring.h>
 
 #ifndef KVM_MAX_VCPU_ID
 #define KVM_MAX_VCPU_ID KVM_MAX_VCPUS
@@ -319,6 +320,7 @@ struct kvm_vcpu {
 	bool preempted;
 	bool ready;
 	struct kvm_vcpu_arch arch;
+	struct kvm_dirty_ring dirty_ring;
 };
 
 static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu)
@@ -505,6 +507,7 @@ struct kvm {
 	struct srcu_struct irq_srcu;
 	pid_t userspace_pid;
 	unsigned int max_halt_poll_ns;
+	u32 dirty_ring_size;
 };
 
 #define kvm_err(fmt, ...) \
@@ -1477,4 +1480,14 @@ static inline void kvm_handle_signal_exit(struct kvm_vcpu *vcpu)
 }
 #endif /* CONFIG_KVM_XFER_TO_GUEST_WORK */
 
+/*
+ * This defines how many reserved entries we want to keep before we
+ * kick the vcpu to the userspace to avoid dirty ring full.  This
+ * value can be tuned to higher if e.g. PML is enabled on the host.
+ */
+#define  KVM_DIRTY_RING_RSVD_ENTRIES  64
+
+/* Max number of entries allowed for each kvm dirty ring */
+#define  KVM_DIRTY_RING_MAX_ENTRIES  65536
+
 #endif
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index 26cfb0fa8e7e..49d7d0fe29f6 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -399,6 +399,69 @@ TRACE_EVENT(kvm_halt_poll_ns,
 #define trace_kvm_halt_poll_ns_shrink(vcpu_id, new, old) \
 	trace_kvm_halt_poll_ns(false, vcpu_id, new, old)
 
+TRACE_EVENT(kvm_dirty_ring_push,
+	TP_PROTO(struct kvm_dirty_ring *ring, u32 slot, u64 offset),
+	TP_ARGS(ring, slot, offset),
+
+	TP_STRUCT__entry(
+		__field(int, index)
+		__field(u32, dirty_index)
+		__field(u32, reset_index)
+		__field(u32, slot)
+		__field(u64, offset)
+	),
+
+	TP_fast_assign(
+		__entry->index          = ring->index;
+		__entry->dirty_index    = ring->dirty_index;
+		__entry->reset_index    = ring->reset_index;
+		__entry->slot           = slot;
+		__entry->offset         = offset;
+	),
+
+	TP_printk("ring %d: dirty 0x%x reset 0x%x "
+		  "slot %u offset 0x%llx (used %u)",
+		  __entry->index, __entry->dirty_index,
+		  __entry->reset_index,  __entry->slot, __entry->offset,
+		  __entry->dirty_index - __entry->reset_index)
+);
+
+TRACE_EVENT(kvm_dirty_ring_reset,
+	TP_PROTO(struct kvm_dirty_ring *ring),
+	TP_ARGS(ring),
+
+	TP_STRUCT__entry(
+		__field(int, index)
+		__field(u32, dirty_index)
+		__field(u32, reset_index)
+	),
+
+	TP_fast_assign(
+		__entry->index          = ring->index;
+		__entry->dirty_index    = ring->dirty_index;
+		__entry->reset_index    = ring->reset_index;
+	),
+
+	TP_printk("ring %d: dirty 0x%x reset 0x%x (used %u)",
+		  __entry->index, __entry->dirty_index, __entry->reset_index,
+		  __entry->dirty_index - __entry->reset_index)
+);
+
+TRACE_EVENT(kvm_dirty_ring_exit,
+	TP_PROTO(struct kvm_vcpu *vcpu),
+	TP_ARGS(vcpu),
+
+	TP_STRUCT__entry(
+	    __field(int, vcpu_id)
+	),
+
+	TP_fast_assign(
+	    __entry->vcpu_id = vcpu->vcpu_id;
+	),
+
+	TP_printk("vcpu %d", __entry->vcpu_id)
+);
+
 #endif /* _TRACE_KVM_MAIN_H */
 
 /* This part must be outside protection */
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 204afbe1240e..886802b8ffba 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -250,6 +250,7 @@ struct kvm_hyperv_exit {
 #define KVM_EXIT_ARM_NISV         28
 #define KVM_EXIT_X86_RDMSR        29
 #define KVM_EXIT_X86_WRMSR        30
+#define KVM_EXIT_DIRTY_RING_FULL  31
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -1054,6 +1055,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_X86_MSR_FILTER 189
 #define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190
 #define KVM_CAP_SYS_HYPERV_CPUID 191
+#define KVM_CAP_DIRTY_LOG_RING 192
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1558,6 +1560,9 @@ struct kvm_pv_cmd {
 /* Available with KVM_CAP_X86_MSR_FILTER */
 #define KVM_X86_SET_MSR_FILTER	_IOW(KVMIO,  0xc6, struct kvm_msr_filter)
 
+/* Available with KVM_CAP_DIRTY_LOG_RING */
+#define KVM_RESET_DIRTY_RINGS		_IO(KVMIO, 0xc7)
+
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
 	/* Guest initialization commands */
@@ -1711,4 +1716,52 @@ struct kvm_hyperv_eventfd {
 #define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE    (1 << 0)
 #define KVM_DIRTY_LOG_INITIALLY_SET            (1 << 1)
 
+/*
+ * Arch needs to define the macro after implementing the dirty ring
+ * feature.  KVM_DIRTY_LOG_PAGE_OFFSET should be defined as the
+ * starting page offset of the dirty ring structures.
+ */
+#ifndef KVM_DIRTY_LOG_PAGE_OFFSET
+#define KVM_DIRTY_LOG_PAGE_OFFSET 0
+#endif
+
+/*
+ * KVM dirty GFN flags, defined as:
+ *
+ * |---------------+---------------+--------------|
+ * | bit 1 (reset) | bit 0 (dirty) | Status       |
+ * |---------------+---------------+--------------|
+ * |             0 |             0 | Invalid GFN  |
+ * |             0 |             1 | Dirty GFN    |
+ * |             1 |             X | GFN to reset |
+ * |---------------+---------------+--------------|
+ *
+ * Lifecycle of a dirty GFN goes like:
+ *
+ *      dirtied         harvested        reset
+ * 00 -----------> 01 -------------> 1X -------+
+ *  ^                                          |
+ *  |                                          |
+ *  +------------------------------------------+
+ *
+ * The userspace program is only responsible for the 01->1X state
+ * conversion after harvesting an entry.  Also, it must not skip any
+ * dirty bits, so that dirty bits are always harvested in sequence.
+ */
+#define KVM_DIRTY_GFN_F_DIRTY           BIT(0)
+#define KVM_DIRTY_GFN_F_RESET           BIT(1)
+#define KVM_DIRTY_GFN_F_MASK            0x3
+
+/*
+ * KVM dirty rings should be mapped at KVM_DIRTY_LOG_PAGE_OFFSET of
+ * per-vcpu mmaped regions as an array of struct kvm_dirty_gfn.  The
+ * size of the gfn buffer is decided by the first argument when
+ * enabling KVM_CAP_DIRTY_LOG_RING.
+ */
+struct kvm_dirty_gfn {
+	__u32 flags;
+	__u32 slot;
+	__u64 offset;
+};
+
 #endif /* __LINUX_KVM_H */
diff --git a/virt/kvm/dirty_ring.c b/virt/kvm/dirty_ring.c
new file mode 100644
index 000000000000..9d01299563ee
--- /dev/null
+++ b/virt/kvm/dirty_ring.c
@@ -0,0 +1,194 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * KVM dirty ring implementation
+ *
+ * Copyright 2019 Red Hat, Inc.
+ */
+#include <linux/kvm_host.h>
+#include <linux/kvm.h>
+#include <linux/vmalloc.h>
+#include <linux/kvm_dirty_ring.h>
+#include <trace/events/kvm.h>
+
+int __weak kvm_cpu_dirty_log_size(void)
+{
+	return 0;
+}
+
+u32 kvm_dirty_ring_get_rsvd_entries(void)
+{
+	return KVM_DIRTY_RING_RSVD_ENTRIES + kvm_cpu_dirty_log_size();
+}
+
+static u32 kvm_dirty_ring_used(struct kvm_dirty_ring *ring)
+{
+	return READ_ONCE(ring->dirty_index) - READ_ONCE(ring->reset_index);
+}
+
+bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring)
+{
+	return kvm_dirty_ring_used(ring) >= ring->soft_limit;
+}
+
+static bool kvm_dirty_ring_full(struct kvm_dirty_ring *ring)
+{
+	return kvm_dirty_ring_used(ring) >= ring->size;
+}
+
+struct kvm_dirty_ring *kvm_dirty_ring_get(struct kvm *kvm)
+{
+	struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
+
+	WARN_ON_ONCE(vcpu->kvm != kvm);
+
+	return &vcpu->dirty_ring;
+}
+
+static void kvm_reset_dirty_gfn(struct kvm *kvm, u32 slot, u64 offset, u64 mask)
+{
+	struct kvm_memory_slot *memslot;
+	int as_id, id;
+
+	as_id = slot >> 16;
+	id = (u16)slot;
+
+	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
+		return;
+
+	memslot = id_to_memslot(__kvm_memslots(kvm, as_id), id);
+
+	if (!memslot || (offset + __fls(mask)) >= memslot->npages)
+		return;
+
+	spin_lock(&kvm->mmu_lock);
+	kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot, offset, mask);
+	spin_unlock(&kvm->mmu_lock);
+}
+
+int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size)
+{
+	ring->dirty_gfns = vmalloc(size);
+	if (!ring->dirty_gfns)
+		return -ENOMEM;
+	memset(ring->dirty_gfns, 0, size);
+
+	ring->size = size / sizeof(struct kvm_dirty_gfn);
+	ring->soft_limit = ring->size - kvm_dirty_ring_get_rsvd_entries();
+	ring->dirty_index = 0;
+	ring->reset_index = 0;
+	ring->index = index;
+
+	return 0;
+}
+
+static inline void kvm_dirty_gfn_set_invalid(struct kvm_dirty_gfn *gfn)
+{
+	gfn->flags = 0;
+}
+
+static inline void kvm_dirty_gfn_set_dirtied(struct kvm_dirty_gfn *gfn)
+{
+	gfn->flags = KVM_DIRTY_GFN_F_DIRTY;
+}
+
+static inline bool kvm_dirty_gfn_invalid(struct kvm_dirty_gfn *gfn)
+{
+	return gfn->flags == 0;
+}
+
+static inline bool kvm_dirty_gfn_harvested(struct kvm_dirty_gfn *gfn)
+{
+	return gfn->flags & KVM_DIRTY_GFN_F_RESET;
+}
+
+int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring)
+{
+	u32 cur_slot, next_slot;
+	u64 cur_offset, next_offset;
+	unsigned long mask;
+	int count = 0;
+	struct kvm_dirty_gfn *entry;
+	bool first_round = true;
+
+	/* This is only needed to make compilers happy */
+	cur_slot = cur_offset = mask = 0;
+
+	while (true) {
+		entry = &ring->dirty_gfns[ring->reset_index & (ring->size - 1)];
+
+		if (!kvm_dirty_gfn_harvested(entry))
+			break;
+
+		next_slot = READ_ONCE(entry->slot);
+		next_offset = READ_ONCE(entry->offset);
+
+		/* Update the flags to reflect that this GFN is reset */
+		kvm_dirty_gfn_set_invalid(entry);
+
+		ring->reset_index++;
+		count++;
+		/*
+		 * Try to coalesce the reset operations when the guest is
+		 * scanning pages in the same slot.
+		 */
+		if (!first_round && next_slot == cur_slot) {
+			s64 delta = next_offset - cur_offset;
+
+			if (delta >= 0 && delta < BITS_PER_LONG) {
+				mask |= 1ull << delta;
+				continue;
+			}
+
+			/* Backwards visit, careful about overflows!  */
+			if (delta > -BITS_PER_LONG && delta < 0 &&
+			    (mask << -delta >> -delta) == mask) {
+				cur_offset = next_offset;
+				mask = (mask << -delta) | 1;
+				continue;
+			}
+		}
+		kvm_reset_dirty_gfn(kvm, cur_slot, cur_offset, mask);
+		cur_slot = next_slot;
+		cur_offset = next_offset;
+		mask = 1;
+		first_round = false;
+	}
+
+	kvm_reset_dirty_gfn(kvm, cur_slot, cur_offset, mask);
+
+	trace_kvm_dirty_ring_reset(ring);
+
+	return count;
+}
+
+void kvm_dirty_ring_push(struct kvm_dirty_ring *ring, u32 slot, u64 offset)
+{
+	struct kvm_dirty_gfn *entry;
+
+	/* It should never get full */
+	WARN_ON_ONCE(kvm_dirty_ring_full(ring));
+
+	entry = &ring->dirty_gfns[ring->dirty_index & (ring->size - 1)];
+
+	entry->slot = slot;
+	entry->offset = offset;
+	/*
+	 * Make sure the data is filled in before we publish this to
+	 * the userspace program.  There's no paired kernel-side reader.
+	 */
+	smp_wmb();
+	kvm_dirty_gfn_set_dirtied(entry);
+	ring->dirty_index++;
+	trace_kvm_dirty_ring_push(ring, slot, offset);
+}
+
+struct page *kvm_dirty_ring_get_page(struct kvm_dirty_ring *ring, u32 offset)
+{
+	return vmalloc_to_page((void *)ring->dirty_gfns + offset * PAGE_SIZE);
+}
+
+void kvm_dirty_ring_free(struct kvm_dirty_ring *ring)
+{
+	vfree(ring->dirty_gfns);
+	ring->dirty_gfns = NULL;
+}
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 68598fdba226..78ef414512bf 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -63,6 +63,8 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/kvm.h>
 
+#include <linux/kvm_dirty_ring.h>
+
 /* Worst case buffer size needed for holding an integer. */
 #define ITOA_MAX_LEN 12
 
@@ -415,6 +417,7 @@ static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
 
 void kvm_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
+	kvm_dirty_ring_free(&vcpu->dirty_ring);
 	kvm_arch_vcpu_destroy(vcpu);
 
 	/*
@@ -2644,8 +2647,13 @@ void mark_page_dirty_in_slot(struct kvm *kvm,
 {
 	if (memslot && memslot->dirty_bitmap) {
 		unsigned long rel_gfn = gfn - memslot->base_gfn;
+		u32 slot = (memslot->as_id << 16) | memslot->id;
 
-		set_bit_le(rel_gfn, memslot->dirty_bitmap);
+		if (kvm->dirty_ring_size)
+			kvm_dirty_ring_push(kvm_dirty_ring_get(kvm),
+					    slot, rel_gfn);
+		else
+			set_bit_le(rel_gfn, memslot->dirty_bitmap);
 	}
 }
 EXPORT_SYMBOL_GPL(mark_page_dirty_in_slot);
@@ -3005,6 +3013,17 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode)
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_on_spin);
 
+static bool kvm_page_in_dirty_ring(struct kvm *kvm, unsigned long pgoff)
+{
+#if KVM_DIRTY_LOG_PAGE_OFFSET > 0
+	return (pgoff >= KVM_DIRTY_LOG_PAGE_OFFSET) &&
+	    (pgoff < KVM_DIRTY_LOG_PAGE_OFFSET +
+	     kvm->dirty_ring_size / PAGE_SIZE);
+#else
+	return false;
+#endif
+}
+
 static vm_fault_t kvm_vcpu_fault(struct vm_fault *vmf)
 {
 	struct kvm_vcpu *vcpu = vmf->vma->vm_file->private_data;
@@ -3020,6 +3039,10 @@ static vm_fault_t kvm_vcpu_fault(struct vm_fault *vmf)
 	else if (vmf->pgoff == KVM_COALESCED_MMIO_PAGE_OFFSET)
 		page = virt_to_page(vcpu->kvm->coalesced_mmio_ring);
 #endif
+	else if (kvm_page_in_dirty_ring(vcpu->kvm, vmf->pgoff))
+		page = kvm_dirty_ring_get_page(
+		    &vcpu->dirty_ring,
+		    vmf->pgoff - KVM_DIRTY_LOG_PAGE_OFFSET);
 	else
 		return kvm_arch_vcpu_fault(vcpu, vmf);
 	get_page(page);
@@ -3033,6 +3056,14 @@ static const struct vm_operations_struct kvm_vcpu_vm_ops = {
 
 static int kvm_vcpu_mmap(struct file *file, struct vm_area_struct *vma)
 {
+	struct kvm_vcpu *vcpu = file->private_data;
+	unsigned long pages = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+
+	if ((kvm_page_in_dirty_ring(vcpu->kvm, vma->vm_pgoff) ||
+	     kvm_page_in_dirty_ring(vcpu->kvm, vma->vm_pgoff + pages - 1)) &&
+	    ((vma->vm_flags & VM_EXEC) || !(vma->vm_flags & VM_SHARED)))
+		return -EINVAL;
+
 	vma->vm_ops = &kvm_vcpu_vm_ops;
 	return 0;
 }
@@ -3126,6 +3157,13 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 	if (r)
 		goto vcpu_free_run_page;
 
+	if (kvm->dirty_ring_size) {
+		r = kvm_dirty_ring_alloc(&vcpu->dirty_ring,
+					 id, kvm->dirty_ring_size);
+		if (r)
+			goto arch_vcpu_destroy;
+	}
+
 	mutex_lock(&kvm->lock);
 	if (kvm_get_vcpu_by_id(kvm, id)) {
 		r = -EEXIST;
@@ -3159,6 +3197,8 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 
 unlock_vcpu_destroy:
 	mutex_unlock(&kvm->lock);
+	kvm_dirty_ring_free(&vcpu->dirty_ring);
+arch_vcpu_destroy:
 	kvm_arch_vcpu_destroy(vcpu);
 vcpu_free_run_page:
 	free_page((unsigned long)vcpu->run);
@@ -3631,12 +3671,78 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 #endif
 	case KVM_CAP_NR_MEMSLOTS:
 		return KVM_USER_MEM_SLOTS;
+	case KVM_CAP_DIRTY_LOG_RING:
+#if KVM_DIRTY_LOG_PAGE_OFFSET > 0
+		return KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn);
+#else
+		return 0;
+#endif
 	default:
 		break;
 	}
 	return kvm_vm_ioctl_check_extension(kvm, arg);
 }
 
+static int kvm_vm_ioctl_enable_dirty_log_ring(struct kvm *kvm, u32 size)
+{
+	int r;
+
+	if (!KVM_DIRTY_LOG_PAGE_OFFSET)
+		return -EINVAL;
+
+	/* the size should be power of 2 */
+	if (!size || (size & (size - 1)))
+		return -EINVAL;
+
+	/* Should be bigger to keep the reserved entries, or a page */
+	if (size < kvm_dirty_ring_get_rsvd_entries() *
+	    sizeof(struct kvm_dirty_gfn) || size < PAGE_SIZE)
+		return -EINVAL;
+
+	if (size > KVM_DIRTY_RING_MAX_ENTRIES *
+	    sizeof(struct kvm_dirty_gfn))
+		return -E2BIG;
+
+	/* We only allow it to set once */
+	if (kvm->dirty_ring_size)
+		return -EINVAL;
+
+	mutex_lock(&kvm->lock);
+
+	if (kvm->created_vcpus) {
+		/* We don't allow to change this value after vcpu created */
+		r = -EINVAL;
+	} else {
+		kvm->dirty_ring_size = size;
+		r = 0;
+	}
+
+	mutex_unlock(&kvm->lock);
+	return r;
+}
+
+static int kvm_vm_ioctl_reset_dirty_pages(struct kvm *kvm)
+{
+	int i;
+	struct kvm_vcpu *vcpu;
+	int cleared = 0;
+
+	if (!kvm->dirty_ring_size)
+		return -EINVAL;
+
+	mutex_lock(&kvm->slots_lock);
+
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		cleared += kvm_dirty_ring_reset(vcpu->kvm, &vcpu->dirty_ring);
+
+	mutex_unlock(&kvm->slots_lock);
+
+	if (cleared)
+		kvm_flush_remote_tlbs(kvm);
+
+	return cleared;
+}
+
 int __attribute__((weak)) kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 						  struct kvm_enable_cap *cap)
 {
@@ -3667,6 +3773,8 @@ static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm,
 		kvm->max_halt_poll_ns = cap->args[0];
 		return 0;
 	}
+	case KVM_CAP_DIRTY_LOG_RING:
+		return kvm_vm_ioctl_enable_dirty_log_ring(kvm, cap->args[0]);
 	default:
 		return kvm_vm_ioctl_enable_cap(kvm, cap);
 	}
@@ -3851,6 +3959,9 @@ static long kvm_vm_ioctl(struct file *filp,
 	case KVM_CHECK_EXTENSION:
 		r = kvm_vm_ioctl_check_extension_generic(kvm, arg);
 		break;
+	case KVM_RESET_DIRTY_RINGS:
+		r = kvm_vm_ioctl_reset_dirty_pages(kvm);
+		break;
 	default:
 		r = kvm_arch_vm_ioctl(filp, ioctl, arg);
 	}
-- 
cgit v1.2.3


From 044c59c409b7fd753707dc437890e94d2b0bd819 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Wed, 30 Sep 2020 21:22:26 -0400
Subject: KVM: Don't allocate dirty bitmap if dirty ring is enabled

Because kvm dirty rings and kvm dirty log is used in an exclusive way,
Let's avoid creating the dirty_bitmap when kvm dirty ring is enabled.
At the meantime, since the dirty_bitmap will be conditionally created
now, we can't use it as a sign of "whether this memory slot enabled
dirty tracking".  Change users like that to check against the kvm
memory slot flags.

Note that there still can be chances where the kvm memory slot got its
dirty_bitmap allocated, _if_ the memory slots are created before
enabling of the dirty rings and at the same time with the dirty
tracking capability enabled, they'll still with the dirty_bitmap.
However it should not hurt much (e.g., the bitmaps will always be
freed if they are there), and the real users normally won't trigger
this because dirty bit tracking flag should in most cases only be
applied to kvm slots only before migration starts, that should be far
latter than kvm initializes (VM starts).

Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20201001012226.5868-1-peterx@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c   | 2 +-
 include/linux/kvm_host.h | 5 +++++
 virt/kvm/kvm_main.c      | 4 ++--
 3 files changed, 8 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 12e5cfe0995e..5dfe0ede0e81 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -820,7 +820,7 @@ gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn,
 	slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
 	if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
 		return NULL;
-	if (no_dirty_log && slot->dirty_bitmap)
+	if (no_dirty_log && kvm_slot_dirty_track_enabled(slot))
 		return NULL;
 
 	return slot;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 864b156391c8..f3b1013fb22c 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -351,6 +351,11 @@ struct kvm_memory_slot {
 	u16 as_id;
 };
 
+static inline bool kvm_slot_dirty_track_enabled(struct kvm_memory_slot *slot)
+{
+	return slot->flags & KVM_MEM_LOG_DIRTY_PAGES;
+}
+
 static inline unsigned long kvm_dirty_bitmap_bytes(struct kvm_memory_slot *memslot)
 {
 	return ALIGN(memslot->npages, BITS_PER_LONG) / 8;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 110aa5cc0c93..3abcb2ce5b7d 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1365,7 +1365,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	/* Allocate/free page dirty bitmap as needed */
 	if (!(new.flags & KVM_MEM_LOG_DIRTY_PAGES))
 		new.dirty_bitmap = NULL;
-	else if (!new.dirty_bitmap) {
+	else if (!new.dirty_bitmap && !kvm->dirty_ring_size) {
 		r = kvm_alloc_dirty_bitmap(&new);
 		if (r)
 			return r;
@@ -2657,7 +2657,7 @@ void mark_page_dirty_in_slot(struct kvm *kvm,
 			     struct kvm_memory_slot *memslot,
 		 	     gfn_t gfn)
 {
-	if (memslot && memslot->dirty_bitmap) {
+	if (memslot && kvm_slot_dirty_track_enabled(memslot)) {
 		unsigned long rel_gfn = gfn - memslot->base_gfn;
 		u32 slot = (memslot->as_id << 16) | memslot->id;
 
-- 
cgit v1.2.3


From 78a56e0494ad29feccd4c54c2b5682721f8cb988 Mon Sep 17 00:00:00 2001
From: Ira Weiny <ira.weiny@intel.com>
Date: Wed, 4 Nov 2020 15:01:57 -0800
Subject: entry: Fix spelling/typo errors in irq entry code

s/reguired/required/
s/Interupts/Interrupts/
s/quiescient/quiescent/
s/assemenbly/assembly/

Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20201104230157.3378023-1-ira.weiny@intel.com
---
 include/linux/entry-common.h | 4 ++--
 kernel/entry/common.c        | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index 1a128baf3628..aab549026ab8 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -415,7 +415,7 @@ void irqentry_exit_cond_resched(void);
  * @state:	Return value from matching call to irqentry_enter()
  *
  * Depending on the return target (kernel/user) this runs the necessary
- * preemption and work checks if possible and reguired and returns to
+ * preemption and work checks if possible and required and returns to
  * the caller with interrupts disabled and no further work pending.
  *
  * This is the last action before returning to the low level ASM code which
@@ -438,7 +438,7 @@ irqentry_state_t noinstr irqentry_nmi_enter(struct pt_regs *regs);
  * @regs:	Pointer to pt_regs (NMI entry regs)
  * @irq_state:	Return value from matching call to irqentry_nmi_enter()
  *
- * Last action before returning to the low level assmenbly code.
+ * Last action before returning to the low level assembly code.
  *
  * Counterpart to irqentry_nmi_enter().
  */
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index bc75c114c1b3..fa17baadf63e 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -304,7 +304,7 @@ noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
 	 * If this entry hit the idle task invoke rcu_irq_enter() whether
 	 * RCU is watching or not.
 	 *
-	 * Interupts can nest when the first interrupt invokes softirq
+	 * Interrupts can nest when the first interrupt invokes softirq
 	 * processing on return which enables interrupts.
 	 *
 	 * Scheduler ticks in the idle task can mark quiescent state and
@@ -315,7 +315,7 @@ noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
 	 * interrupt to invoke rcu_irq_enter(). If that nested interrupt is
 	 * the tick then rcu_flavor_sched_clock_irq() would wrongfully
 	 * assume that it is the first interupt and eventually claim
-	 * quiescient state and end grace periods prematurely.
+	 * quiescent state and end grace periods prematurely.
 	 *
 	 * Unconditionally invoke rcu_irq_enter() so RCU state stays
 	 * consistent.
-- 
cgit v1.2.3


From 23d89aa0c2192f2d4582198b381d8805492c7925 Mon Sep 17 00:00:00 2001
From: Daniel Baluta <daniel.baluta@nxp.com>
Date: Wed, 11 Nov 2020 13:11:18 +0200
Subject: firmware: imx-dsp: Export functions to request/free channels

In order to save power, we only need to request a channel
when the communication with the DSP active.

For this we export the following functions:
	- imx_dsp_request_channel, gets a channel with a given index
	- imx_dsp_free_channel, frees a channel with a given index

Notice that we still request channels at probe to support devices
that do not have PM callbacks implemented.

More explanations about why requesting a channel has an effect
on power savings:
 - requesting an mailbox channel will call mailbox's startup
   function.
 - startup function calls pm_runtime_get_sync which increments device
   usage count and will keep the device active. Specifically, mailbox
   clock will be always ON when a mailbox channel is requested.

Signed-off-by: Daniel Baluta <daniel.baluta@nxp.com>
Reviewed-by: Paul Olaru <paul.olaru@nxp.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
 drivers/firmware/imx/imx-dsp.c   | 25 +++++++++++++++++++++++++
 include/linux/firmware/imx/dsp.h | 10 ++++++++++
 2 files changed, 35 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/firmware/imx/imx-dsp.c b/drivers/firmware/imx/imx-dsp.c
index b6e95d6d34c0..a6c06d7476c3 100644
--- a/drivers/firmware/imx/imx-dsp.c
+++ b/drivers/firmware/imx/imx-dsp.c
@@ -60,6 +60,31 @@ static void imx_dsp_handle_rx(struct mbox_client *c, void *msg)
 	}
 }
 
+struct mbox_chan *imx_dsp_request_channel(struct imx_dsp_ipc *dsp_ipc, int idx)
+{
+	struct imx_dsp_chan *dsp_chan;
+
+	if (idx >= DSP_MU_CHAN_NUM)
+		return ERR_PTR(-EINVAL);
+
+	dsp_chan = &dsp_ipc->chans[idx];
+	dsp_chan->ch = mbox_request_channel_byname(&dsp_chan->cl, dsp_chan->name);
+	return dsp_chan->ch;
+}
+EXPORT_SYMBOL(imx_dsp_request_channel);
+
+void imx_dsp_free_channel(struct imx_dsp_ipc *dsp_ipc, int idx)
+{
+	struct imx_dsp_chan *dsp_chan;
+
+	if (idx >= DSP_MU_CHAN_NUM)
+		return;
+
+	dsp_chan = &dsp_ipc->chans[idx];
+	mbox_free_channel(dsp_chan->ch);
+}
+EXPORT_SYMBOL(imx_dsp_free_channel);
+
 static int imx_dsp_setup_channels(struct imx_dsp_ipc *dsp_ipc)
 {
 	struct device *dev = dsp_ipc->dev;
diff --git a/include/linux/firmware/imx/dsp.h b/include/linux/firmware/imx/dsp.h
index 7562099c9e46..4f7895a3b73c 100644
--- a/include/linux/firmware/imx/dsp.h
+++ b/include/linux/firmware/imx/dsp.h
@@ -55,6 +55,9 @@ static inline void *imx_dsp_get_data(struct imx_dsp_ipc *ipc)
 
 int imx_dsp_ring_doorbell(struct imx_dsp_ipc *dsp, unsigned int chan_idx);
 
+struct mbox_chan *imx_dsp_request_channel(struct imx_dsp_ipc *ipc, int idx);
+void imx_dsp_free_channel(struct imx_dsp_ipc *ipc, int idx);
+
 #else
 
 static inline int imx_dsp_ring_doorbell(struct imx_dsp_ipc *ipc,
@@ -63,5 +66,12 @@ static inline int imx_dsp_ring_doorbell(struct imx_dsp_ipc *ipc,
 	return -ENOTSUPP;
 }
 
+struct mbox_chan *imx_dsp_request_channel(struct imx_dsp_ipc *ipc, int idx)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
+void imx_dsp_free_channel(struct imx_dsp_ipc *ipc, int idx) { }
+
 #endif
 #endif /* _IMX_DSP_IPC_H */
-- 
cgit v1.2.3


From cfeeea60af2f01c13b94d57a9bb1291e7bc181da Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Mon, 16 Nov 2020 12:57:13 +0200
Subject: bus: ti-sysc: Implement GPMC debug quirk to drop platform data

We need to enable no-reset-on-init quirk for GPMC if the config
option for CONFIG_OMAP_GPMC_DEBUG is set. Otherwise the GPMC
driver code is unable to show the bootloader configured timings.

Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 drivers/bus/ti-sysc.c                 | 10 ++++++++++
 include/linux/platform_data/ti-sysc.h |  1 +
 2 files changed, 11 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c
index 88a5d22091f3..691cc39bfc5c 100644
--- a/drivers/bus/ti-sysc.c
+++ b/drivers/bus/ti-sysc.c
@@ -1383,6 +1383,8 @@ static const struct sysc_revision_quirk sysc_revision_quirks[] = {
 		   SYSC_QUIRK_CLKDM_NOAUTO),
 	SYSC_QUIRK("dwc3", 0x488c0000, 0, 0x10, -ENODEV, 0x500a0200, 0xffffffff,
 		   SYSC_QUIRK_CLKDM_NOAUTO),
+	SYSC_QUIRK("gpmc", 0, 0, 0x10, 0x14, 0x00000060, 0xffffffff,
+		   SYSC_QUIRK_GPMC_DEBUG),
 	SYSC_QUIRK("hdmi", 0, 0, 0x10, -ENODEV, 0x50030200, 0xffffffff,
 		   SYSC_QUIRK_OPT_CLKS_NEEDED),
 	SYSC_QUIRK("hdq1w", 0, 0, 0x14, 0x18, 0x00000006, 0xffffffff,
@@ -1818,6 +1820,14 @@ static void sysc_init_module_quirks(struct sysc *ddata)
 		return;
 	}
 
+#ifdef CONFIG_OMAP_GPMC_DEBUG
+	if (ddata->cfg.quirks & SYSC_QUIRK_GPMC_DEBUG) {
+		ddata->cfg.quirks |= SYSC_QUIRK_NO_RESET_ON_INIT;
+
+		return;
+	}
+#endif
+
 	if (ddata->cfg.quirks & SYSC_MODULE_QUIRK_I2C) {
 		ddata->pre_reset_quirk = sysc_pre_reset_quirk_i2c;
 		ddata->post_reset_quirk = sysc_post_reset_quirk_i2c;
diff --git a/include/linux/platform_data/ti-sysc.h b/include/linux/platform_data/ti-sysc.h
index 240dce553a0b..fafc1beea504 100644
--- a/include/linux/platform_data/ti-sysc.h
+++ b/include/linux/platform_data/ti-sysc.h
@@ -50,6 +50,7 @@ struct sysc_regbits {
 	s8 emufree_shift;
 };
 
+#define SYSC_QUIRK_GPMC_DEBUG		BIT(26)
 #define SYSC_MODULE_QUIRK_ENA_RESETDONE	BIT(25)
 #define SYSC_MODULE_QUIRK_PRUSS		BIT(24)
 #define SYSC_MODULE_QUIRK_DSS_RESET	BIT(23)
-- 
cgit v1.2.3


From ead49373d2916080509f51fc6a4ee8f9bc021b9b Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Thu, 29 Oct 2020 09:57:16 +0800
Subject: mmc: core: Initial support for SD express card/host

In the SD specification v7.10 the SD express card has been added. This new
type of removable SD card, can be managed via a PCIe/NVMe based interface,
while also allowing backwards compatibility towards the legacy SD
interface.

To keep the backwards compatibility, it's required to start the
initialization through the legacy SD interface. If it turns out that the
mmc host and the SD card, both supports the PCIe/NVMe interface, then a
switch should be allowed.

Therefore, let's introduce some basic support for this type of SD cards to
the mmc core. The mmc host, should set MMC_CAP2_SD_EXP if it supports this
interface and MMC_CAP2_SD_EXP_1_2V, if also 1.2V is supported, as to inform
the core about it.

To deal with the switch to the PCIe/NVMe interface, the mmc host is
required to implement a new host ops, ->init_sd_express(). Based on the
initial communication between the host and the card, host->ios.timing is
set to either MMC_TIMING_SD_EXP or MMC_TIMING_SD_EXP_1_2V, depending on if
1.2V is supported or not. In this way, the mmc host can check these values
in its ->init_sd_express() ops, to know how to proceed with the handover.

Note that, to manage card insert/removal, the mmc core sticks with using
the ->get_cd() callback, which means it's the host's responsibility to make
sure it provides valid data, even if the card may be managed by PCIe/NVMe
at the moment. As long as the card seems to be present, the mmc core keeps
the card powered on.

Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Rui Feng <rui_feng@realsil.com.cn>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/1603936636-3126-1-git-send-email-rui_feng@realsil.com.cn
---
 drivers/mmc/core/core.c   | 15 +++++++++++++--
 drivers/mmc/core/host.h   |  6 ++++++
 drivers/mmc/core/sd_ops.c | 49 +++++++++++++++++++++++++++++++++++++++++++++--
 drivers/mmc/core/sd_ops.h |  1 +
 include/linux/mmc/host.h  |  7 +++++++
 5 files changed, 74 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index d42037f0f10d..19f1ee57fb34 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -2147,8 +2147,12 @@ static int mmc_rescan_try_freq(struct mmc_host *host, unsigned freq)
 
 	mmc_go_idle(host);
 
-	if (!(host->caps2 & MMC_CAP2_NO_SD))
-		mmc_send_if_cond(host, host->ocr_avail);
+	if (!(host->caps2 & MMC_CAP2_NO_SD)) {
+		if (mmc_send_if_cond_pcie(host, host->ocr_avail))
+			goto out;
+		if (mmc_card_sd_express(host))
+			return 0;
+	}
 
 	/* Order's important: probe SDIO, then SD, then MMC */
 	if (!(host->caps2 & MMC_CAP2_NO_SDIO))
@@ -2163,6 +2167,7 @@ static int mmc_rescan_try_freq(struct mmc_host *host, unsigned freq)
 		if (!mmc_attach_mmc(host))
 			return 0;
 
+out:
 	mmc_power_off(host);
 	return -EIO;
 }
@@ -2290,6 +2295,12 @@ void mmc_rescan(struct work_struct *work)
 		goto out;
 	}
 
+	/* If an SD express card is present, then leave it as is. */
+	if (mmc_card_sd_express(host)) {
+		mmc_release_host(host);
+		goto out;
+	}
+
 	for (i = 0; i < ARRAY_SIZE(freqs); i++) {
 		unsigned int freq = freqs[i];
 		if (freq > host->f_max) {
diff --git a/drivers/mmc/core/host.h b/drivers/mmc/core/host.h
index 5e3b9534ffb2..ba407617ed23 100644
--- a/drivers/mmc/core/host.h
+++ b/drivers/mmc/core/host.h
@@ -77,5 +77,11 @@ static inline bool mmc_card_hs400es(struct mmc_card *card)
 	return card->host->ios.enhanced_strobe;
 }
 
+static inline bool mmc_card_sd_express(struct mmc_host *host)
+{
+	return host->ios.timing == MMC_TIMING_SD_EXP ||
+		host->ios.timing == MMC_TIMING_SD_EXP_1_2V;
+}
+
 #endif
 
diff --git a/drivers/mmc/core/sd_ops.c b/drivers/mmc/core/sd_ops.c
index 22bf528294b9..d61ff811218c 100644
--- a/drivers/mmc/core/sd_ops.c
+++ b/drivers/mmc/core/sd_ops.c
@@ -158,7 +158,8 @@ int mmc_send_app_op_cond(struct mmc_host *host, u32 ocr, u32 *rocr)
 	return err;
 }
 
-int mmc_send_if_cond(struct mmc_host *host, u32 ocr)
+static int __mmc_send_if_cond(struct mmc_host *host, u32 ocr, u8 pcie_bits,
+			      u32 *resp)
 {
 	struct mmc_command cmd = {};
 	int err;
@@ -171,7 +172,7 @@ int mmc_send_if_cond(struct mmc_host *host, u32 ocr)
 	 * SD 1.0 cards.
 	 */
 	cmd.opcode = SD_SEND_IF_COND;
-	cmd.arg = ((ocr & 0xFF8000) != 0) << 8 | test_pattern;
+	cmd.arg = ((ocr & 0xFF8000) != 0) << 8 | pcie_bits << 8 | test_pattern;
 	cmd.flags = MMC_RSP_SPI_R7 | MMC_RSP_R7 | MMC_CMD_BCR;
 
 	err = mmc_wait_for_cmd(host, &cmd, 0);
@@ -186,6 +187,50 @@ int mmc_send_if_cond(struct mmc_host *host, u32 ocr)
 	if (result_pattern != test_pattern)
 		return -EIO;
 
+	if (resp)
+		*resp = cmd.resp[0];
+
+	return 0;
+}
+
+int mmc_send_if_cond(struct mmc_host *host, u32 ocr)
+{
+	return __mmc_send_if_cond(host, ocr, 0, NULL);
+}
+
+int mmc_send_if_cond_pcie(struct mmc_host *host, u32 ocr)
+{
+	u32 resp = 0;
+	u8 pcie_bits = 0;
+	int ret;
+
+	if (host->caps2 & MMC_CAP2_SD_EXP) {
+		/* Probe card for SD express support via PCIe. */
+		pcie_bits = 0x10;
+		if (host->caps2 & MMC_CAP2_SD_EXP_1_2V)
+			/* Probe also for 1.2V support. */
+			pcie_bits = 0x30;
+	}
+
+	ret = __mmc_send_if_cond(host, ocr, pcie_bits, &resp);
+	if (ret)
+		return 0;
+
+	/* Continue with the SD express init, if the card supports it. */
+	resp &= 0x3000;
+	if (pcie_bits && resp) {
+		if (resp == 0x3000)
+			host->ios.timing = MMC_TIMING_SD_EXP_1_2V;
+		else
+			host->ios.timing = MMC_TIMING_SD_EXP;
+
+		/*
+		 * According to the spec the clock shall also be gated, but
+		 * let's leave this to the host driver for more flexibility.
+		 */
+		return host->ops->init_sd_express(host, &host->ios);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/mmc/core/sd_ops.h b/drivers/mmc/core/sd_ops.h
index 2194cabfcfc5..3ba7b3cf4652 100644
--- a/drivers/mmc/core/sd_ops.h
+++ b/drivers/mmc/core/sd_ops.h
@@ -16,6 +16,7 @@ struct mmc_host;
 int mmc_app_set_bus_width(struct mmc_card *card, int width);
 int mmc_send_app_op_cond(struct mmc_host *host, u32 ocr, u32 *rocr);
 int mmc_send_if_cond(struct mmc_host *host, u32 ocr);
+int mmc_send_if_cond_pcie(struct mmc_host *host, u32 ocr);
 int mmc_send_relative_addr(struct mmc_host *host, unsigned int *rca);
 int mmc_app_send_scr(struct mmc_card *card);
 int mmc_sd_switch(struct mmc_card *card, int mode, int group,
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index c079b932330f..01bba36545c5 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -60,6 +60,8 @@ struct mmc_ios {
 #define MMC_TIMING_MMC_DDR52	8
 #define MMC_TIMING_MMC_HS200	9
 #define MMC_TIMING_MMC_HS400	10
+#define MMC_TIMING_SD_EXP	11
+#define MMC_TIMING_SD_EXP_1_2V	12
 
 	unsigned char	signal_voltage;		/* signalling voltage (1.8V or 3.3V) */
 
@@ -173,6 +175,9 @@ struct mmc_host_ops {
 	 */
 	int	(*multi_io_quirk)(struct mmc_card *card,
 				  unsigned int direction, int blk_size);
+
+	/* Initialize an SD express card, mandatory for MMC_CAP2_SD_EXP. */
+	int	(*init_sd_express)(struct mmc_host *host, struct mmc_ios *ios);
 };
 
 struct mmc_cqe_ops {
@@ -358,6 +363,8 @@ struct mmc_host {
 #define MMC_CAP2_HS200_1_2V_SDR	(1 << 6)        /* can support */
 #define MMC_CAP2_HS200		(MMC_CAP2_HS200_1_8V_SDR | \
 				 MMC_CAP2_HS200_1_2V_SDR)
+#define MMC_CAP2_SD_EXP		(1 << 7)	/* SD express via PCIe */
+#define MMC_CAP2_SD_EXP_1_2V	(1 << 8)	/* SD express 1.2V */
 #define MMC_CAP2_CD_ACTIVE_HIGH	(1 << 10)	/* Card-detect signal active high */
 #define MMC_CAP2_RO_ACTIVE_HIGH	(1 << 11)	/* Write-protect signal active high */
 #define MMC_CAP2_NO_PRESCAN_POWERUP (1 << 14)	/* Don't power up before scan */
-- 
cgit v1.2.3


From 5afe802132f242f5520d2acac09ea05d31e3c7cf Mon Sep 17 00:00:00 2001
From: Rui Feng <rui_feng@realsil.com.cn>
Date: Thu, 29 Oct 2020 09:57:48 +0800
Subject: misc: rtsx: Add SD Express mode support for RTS5261

RTS5261 support SD mode and PCIe/NVMe mode. The workflow is as follows.
1.RTS5261 work in SD mode and set MMC_CAPS2_SD_EXP flag.
2.If card is plugged in, Host send CMD8 to ask card's PCIe availability.
3.If the card has PCIe availability and WP is not set, init_sd_express() will be invoked,
RTS5261 switch to PCIe/NVMe mode.
4.Mmc driver handover it to NVMe driver.
5.If card is unplugged, RTS5261 will switch to SD mode.

Signed-off-by: Rui Feng <rui_feng@realsil.com.cn>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/1603936668-3363-1-git-send-email-rui_feng@realsil.com.cn
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/misc/cardreader/rts5261.c  |  4 ++++
 drivers/misc/cardreader/rts5261.h  | 23 -----------------------
 drivers/misc/cardreader/rtsx_pcr.c |  5 +++++
 include/linux/rtsx_pci.h           | 23 +++++++++++++++++++++++
 4 files changed, 32 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/misc/cardreader/rts5261.c b/drivers/misc/cardreader/rts5261.c
index 471961487ff8..536c90d4fd76 100644
--- a/drivers/misc/cardreader/rts5261.c
+++ b/drivers/misc/cardreader/rts5261.c
@@ -738,8 +738,12 @@ void rts5261_init_params(struct rtsx_pcr *pcr)
 {
 	struct rtsx_cr_option *option = &pcr->option;
 	struct rtsx_hw_param *hw_param = &pcr->hw_param;
+	u8 val;
 
 	pcr->extra_caps = EXTRA_CAPS_SD_SDR50 | EXTRA_CAPS_SD_SDR104;
+	rtsx_pci_read_register(pcr, RTS5261_FW_STATUS, &val);
+	if (!(val & RTS5261_EXPRESS_LINK_FAIL_MASK))
+		pcr->extra_caps |= EXTRA_CAPS_SD_EXPRESS;
 	pcr->num_slots = 1;
 	pcr->ops = &rts5261_pcr_ops;
 
diff --git a/drivers/misc/cardreader/rts5261.h b/drivers/misc/cardreader/rts5261.h
index ebfdd236a553..8d80f0d5d5d6 100644
--- a/drivers/misc/cardreader/rts5261.h
+++ b/drivers/misc/cardreader/rts5261.h
@@ -65,23 +65,6 @@
 #define RTS5261_FW_EXPRESS_TEST_MASK	(0x01<<0)
 #define RTS5261_FW_EA_MODE_MASK		(0x01<<5)
 
-/* FW config register */
-#define RTS5261_FW_CFG0			0xFF54
-#define RTS5261_FW_ENTER_EXPRESS	(0x01<<0)
-
-#define RTS5261_FW_CFG1			0xFF55
-#define RTS5261_SYS_CLK_SEL_MCU_CLK	(0x01<<7)
-#define RTS5261_CRC_CLK_SEL_MCU_CLK	(0x01<<6)
-#define RTS5261_FAKE_MCU_CLOCK_GATING	(0x01<<5)
-/*MCU_bus_mode_sel: 0=real 8051 1=fake mcu*/
-#define RTS5261_MCU_BUS_SEL_MASK	(0x01<<4)
-/*MCU_clock_sel:VerA 00=aux16M 01=aux400K 1x=REFCLK100M*/
-/*MCU_clock_sel:VerB 00=aux400K 01=aux16M 10=REFCLK100M*/
-#define RTS5261_MCU_CLOCK_SEL_MASK	(0x03<<2)
-#define RTS5261_MCU_CLOCK_SEL_16M	(0x01<<2)
-#define RTS5261_MCU_CLOCK_GATING	(0x01<<1)
-#define RTS5261_DRIVER_ENABLE_FW	(0x01<<0)
-
 /* FW status register */
 #define RTS5261_FW_STATUS		0xFF56
 #define RTS5261_EXPRESS_LINK_FAIL_MASK	(0x01<<7)
@@ -121,12 +104,6 @@
 #define RTS5261_DV3318_19		(0x04<<4)
 #define RTS5261_DV3318_33		(0x07<<4)
 
-#define RTS5261_LDO1_CFG0		0xFF72
-#define RTS5261_LDO1_OCP_THD_MASK	(0x07<<5)
-#define RTS5261_LDO1_OCP_EN		(0x01<<4)
-#define RTS5261_LDO1_OCP_LMT_THD_MASK	(0x03<<2)
-#define RTS5261_LDO1_OCP_LMT_EN		(0x01<<1)
-
 /* CRD6603-433 190319 request changed */
 #define RTS5261_LDO1_OCP_THD_740	(0x00<<5)
 #define RTS5261_LDO1_OCP_THD_800	(0x01<<5)
diff --git a/drivers/misc/cardreader/rtsx_pcr.c b/drivers/misc/cardreader/rtsx_pcr.c
index 5d15607027e9..56f63fa7f646 100644
--- a/drivers/misc/cardreader/rtsx_pcr.c
+++ b/drivers/misc/cardreader/rtsx_pcr.c
@@ -990,6 +990,11 @@ static irqreturn_t rtsx_pci_isr(int irq, void *dev_id)
 		} else {
 			pcr->card_removed |= SD_EXIST;
 			pcr->card_inserted &= ~SD_EXIST;
+			if (PCI_PID(pcr) == PID_5261) {
+				rtsx_pci_write_register(pcr, RTS5261_FW_STATUS,
+					RTS5261_EXPRESS_LINK_FAIL_MASK, 0);
+				pcr->extra_caps |= EXTRA_CAPS_SD_EXPRESS;
+			}
 		}
 		pcr->dma_error_count = 0;
 	}
diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h
index 745f5e73f99a..b47959f48ccd 100644
--- a/include/linux/rtsx_pci.h
+++ b/include/linux/rtsx_pci.h
@@ -658,6 +658,19 @@
 #define   PM_WAKE_EN			0x01
 #define PM_CTRL4			0xFF47
 
+#define RTS5261_FW_CFG0			0xFF54
+#define   RTS5261_FW_ENTER_EXPRESS	(0x01 << 0)
+
+#define RTS5261_FW_CFG1			0xFF55
+#define   RTS5261_SYS_CLK_SEL_MCU_CLK	(0x01 << 7)
+#define   RTS5261_CRC_CLK_SEL_MCU_CLK	(0x01 << 6)
+#define   RTS5261_FAKE_MCU_CLOCK_GATING	(0x01 << 5)
+#define   RTS5261_MCU_BUS_SEL_MASK	(0x01 << 4)
+#define   RTS5261_MCU_CLOCK_SEL_MASK	(0x03 << 2)
+#define   RTS5261_MCU_CLOCK_SEL_16M	(0x01 << 2)
+#define   RTS5261_MCU_CLOCK_GATING	(0x01 << 1)
+#define   RTS5261_DRIVER_ENABLE_FW	(0x01 << 0)
+
 #define REG_CFG_OOBS_OFF_TIMER 0xFEA6
 #define REG_CFG_OOBS_ON_TIMER 0xFEA7
 #define REG_CFG_VCM_ON_TIMER 0xFEA8
@@ -701,6 +714,13 @@
 #define   RTS5260_DVCC_TUNE_MASK	0x70
 #define   RTS5260_DVCC_33		0x70
 
+/*RTS5261*/
+#define RTS5261_LDO1_CFG0		0xFF72
+#define   RTS5261_LDO1_OCP_THD_MASK	(0x07 << 5)
+#define   RTS5261_LDO1_OCP_EN		(0x01 << 4)
+#define   RTS5261_LDO1_OCP_LMT_THD_MASK	(0x03 << 2)
+#define   RTS5261_LDO1_OCP_LMT_EN	(0x01 << 1)
+
 #define LDO_VCC_CFG1			0xFF73
 #define   LDO_VCC_REF_TUNE_MASK		0x30
 #define   LDO_VCC_REF_1V2		0x20
@@ -741,6 +761,8 @@
 
 #define RTS5260_AUTOLOAD_CFG4		0xFF7F
 #define   RTS5260_MIMO_DISABLE		0x8A
+/*RTS5261*/
+#define   RTS5261_AUX_CLK_16M_EN		(1 << 5)
 
 #define RTS5260_REG_GPIO_CTL0		0xFC1A
 #define   RTS5260_REG_GPIO_MASK		0x01
@@ -1191,6 +1213,7 @@ struct rtsx_pcr {
 #define EXTRA_CAPS_MMC_HS200		(1 << 4)
 #define EXTRA_CAPS_MMC_8BIT		(1 << 5)
 #define EXTRA_CAPS_NO_MMC		(1 << 7)
+#define EXTRA_CAPS_SD_EXPRESS		(1 << 8)
 	u32				extra_caps;
 
 #define IC_VER_A			0
-- 
cgit v1.2.3


From 6b7b58f425c3359787483479d73c0bb98ffc65b8 Mon Sep 17 00:00:00 2001
From: Rui Feng <rui_feng@realsil.com.cn>
Date: Tue, 3 Nov 2020 17:54:29 +0800
Subject: mmc: rtsx: Add test mode for RTS5261

This patch add test mode for RTS5261.
If test mode is set, reader will switch to SD Express mode
mandatorily, and this mode is used by factory testing only.

Signed-off-by: Rui Feng <rui_feng@realsil.com.cn>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/1604397269-2780-1-git-send-email-rui_feng@realsil.com.cn
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/misc/cardreader/rts5261.h |  5 -----
 drivers/mmc/host/rtsx_pci_sdmmc.c | 19 ++++++++++++++++---
 include/linux/rtsx_pci.h          |  4 ++++
 3 files changed, 20 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/misc/cardreader/rts5261.h b/drivers/misc/cardreader/rts5261.h
index 8d80f0d5d5d6..80179353bc46 100644
--- a/drivers/misc/cardreader/rts5261.h
+++ b/drivers/misc/cardreader/rts5261.h
@@ -60,11 +60,6 @@
 /* DMACTL 0xFE2C */
 #define RTS5261_DMA_PACK_SIZE_MASK	0xF0
 
-/* FW config info register */
-#define RTS5261_FW_CFG_INFO0		0xFF50
-#define RTS5261_FW_EXPRESS_TEST_MASK	(0x01<<0)
-#define RTS5261_FW_EA_MODE_MASK		(0x01<<5)
-
 /* FW status register */
 #define RTS5261_FW_STATUS		0xFF56
 #define RTS5261_EXPRESS_LINK_FAIL_MASK	(0x01<<7)
diff --git a/drivers/mmc/host/rtsx_pci_sdmmc.c b/drivers/mmc/host/rtsx_pci_sdmmc.c
index c584070b39fe..e9ea703f08c5 100644
--- a/drivers/mmc/host/rtsx_pci_sdmmc.c
+++ b/drivers/mmc/host/rtsx_pci_sdmmc.c
@@ -47,6 +47,8 @@ struct realtek_pci_sdmmc {
 	bool			using_cookie;
 };
 
+static int sdmmc_init_sd_express(struct mmc_host *mmc, struct mmc_ios *ios);
+
 static inline struct device *sdmmc_dev(struct realtek_pci_sdmmc *host)
 {
 	return &(host->pdev->dev);
@@ -898,6 +900,7 @@ static int sd_power_on(struct realtek_pci_sdmmc *host)
 	struct mmc_host *mmc = host->mmc;
 	int err;
 	u32 val;
+	u8 test_mode;
 
 	if (host->power_state == SDMMC_POWER_ON)
 		return 0;
@@ -925,6 +928,15 @@ static int sd_power_on(struct realtek_pci_sdmmc *host)
 		return err;
 
 	if (PCI_PID(pcr) == PID_5261) {
+		/*
+		 * If test mode is set switch to SD Express mandatorily,
+		 * this is only for factory testing.
+		 */
+		rtsx_pci_read_register(pcr, RTS5261_FW_CFG_INFO0, &test_mode);
+		if (test_mode & RTS5261_FW_EXPRESS_TEST_MASK) {
+			sdmmc_init_sd_express(mmc, NULL);
+			return 0;
+		}
 		if (pcr->extra_caps & EXTRA_CAPS_SD_EXPRESS)
 			mmc->caps2 |= MMC_CAP2_SD_EXP | MMC_CAP2_SD_EXP_1_2V;
 		/*
@@ -1354,11 +1366,12 @@ static int sdmmc_init_sd_express(struct mmc_host *mmc, struct mmc_ios *ios)
 		RTS5261_AUX_CLK_16M_EN, RTS5261_AUX_CLK_16M_EN);
 	rtsx_pci_write_register(pcr, RTS5261_FW_CFG0,
 		RTS5261_FW_ENTER_EXPRESS, RTS5261_FW_ENTER_EXPRESS);
+	rtsx_pci_write_register(pcr, RTS5261_FW_CFG1,
+		RTS5261_MCU_CLOCK_GATING, RTS5261_MCU_CLOCK_GATING);
 	rtsx_pci_write_register(pcr, RTS5261_FW_CFG1,
 		RTS5261_MCU_BUS_SEL_MASK | RTS5261_MCU_CLOCK_SEL_MASK
-		| RTS5261_MCU_CLOCK_GATING | RTS5261_DRIVER_ENABLE_FW,
-		RTS5261_MCU_CLOCK_SEL_16M | RTS5261_MCU_CLOCK_GATING
-		| RTS5261_DRIVER_ENABLE_FW);
+		| RTS5261_DRIVER_ENABLE_FW,
+		RTS5261_MCU_CLOCK_SEL_16M | RTS5261_DRIVER_ENABLE_FW);
 	host->eject = true;
 	return 0;
 }
diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h
index b47959f48ccd..db249e8707f3 100644
--- a/include/linux/rtsx_pci.h
+++ b/include/linux/rtsx_pci.h
@@ -658,6 +658,10 @@
 #define   PM_WAKE_EN			0x01
 #define PM_CTRL4			0xFF47
 
+/* FW config info register */
+#define RTS5261_FW_CFG_INFO0		0xFF50
+#define   RTS5261_FW_EXPRESS_TEST_MASK	(0x01 << 0)
+#define   RTS5261_FW_EA_MODE_MASK	(0x01 << 5)
 #define RTS5261_FW_CFG0			0xFF54
 #define   RTS5261_FW_ENTER_EXPRESS	(0x01 << 0)
 
-- 
cgit v1.2.3


From 1672617d512880f31d1d43ca0eb0d13d50b8c680 Mon Sep 17 00:00:00 2001
From: Rui Feng <rui_feng@realsil.com.cn>
Date: Tue, 3 Nov 2020 17:55:12 +0800
Subject: misc: rtsx: Add hardware auto power off for RTS5261

This patch enable hardware auto power off when card is removed.

Signed-off-by: Rui Feng <rui_feng@realsil.com.cn>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/1604397312-2991-1-git-send-email-rui_feng@realsil.com.cn
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/misc/cardreader/rts5261.c | 9 +++++++++
 include/linux/rtsx_pci.h          | 3 +++
 2 files changed, 12 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/misc/cardreader/rts5261.c b/drivers/misc/cardreader/rts5261.c
index 0ef6b3e04a8d..2ada973a0f33 100644
--- a/drivers/misc/cardreader/rts5261.c
+++ b/drivers/misc/cardreader/rts5261.c
@@ -176,6 +176,8 @@ static int rts5261_card_power_on(struct rtsx_pcr *pcr, int card)
 	if (option->ocp_en)
 		rtsx_pci_enable_ocp(pcr);
 
+	rtsx_pci_write_register(pcr, REG_CRC_DUMMY_0,
+		CFG_SD_POW_AUTO_PD, CFG_SD_POW_AUTO_PD);
 
 	rtsx_pci_write_register(pcr, RTS5261_LDO1_CFG1,
 			RTS5261_LDO1_TUNE_MASK, RTS5261_LDO1_33);
@@ -303,6 +305,8 @@ static int rts5261_card_power_off(struct rtsx_pcr *pcr, int card)
 	err = rtsx_pci_write_register(pcr, RTS5261_LDO1233318_POW_CTL,
 				RTS5261_LDO_POWERON_MASK, 0);
 
+	rtsx_pci_write_register(pcr, REG_CRC_DUMMY_0,
+		CFG_SD_POW_AUTO_PD, 0);
 	if (pcr->option.ocp_en)
 		rtsx_pci_disable_ocp(pcr);
 
@@ -475,6 +479,7 @@ static void rts5261_init_from_cfg(struct rtsx_pcr *pcr)
 static int rts5261_extra_init_hw(struct rtsx_pcr *pcr)
 {
 	struct rtsx_cr_option *option = &pcr->option;
+	u32 val;
 
 	rtsx_pci_write_register(pcr, RTS5261_AUTOLOAD_CFG1,
 			CD_RESUME_EN_MASK, CD_RESUME_EN_MASK);
@@ -489,6 +494,10 @@ static int rts5261_extra_init_hw(struct rtsx_pcr *pcr)
 			AUX_CLK_ACTIVE_SEL_MASK, MAC_CKSW_DONE);
 	rtsx_pci_write_register(pcr, L1SUB_CONFIG3, 0xFF, 0);
 
+	if (is_version_higher_than(pcr, PID_5261, IC_VER_B)) {
+		val = rtsx_pci_readl(pcr, RTSX_DUM_REG);
+		rtsx_pci_writel(pcr, RTSX_DUM_REG, val | 0x1);
+	}
 	rtsx_pci_write_register(pcr, RTS5261_AUTOLOAD_CFG4,
 			RTS5261_AUX_CLK_16M_EN, 0);
 
diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h
index db249e8707f3..fcaadc7c9df1 100644
--- a/include/linux/rtsx_pci.h
+++ b/include/linux/rtsx_pci.h
@@ -82,6 +82,7 @@
 #define   MS_OC_INT_EN			(1 << 23)
 #define   SD_OC_INT_EN			(1 << 22)
 
+#define RTSX_DUM_REG			0x1C
 
 /*
  * macros for easy use
@@ -1272,6 +1273,8 @@ struct rtsx_pcr {
 #define PCI_PID(pcr)			((pcr)->pci->device)
 #define is_version(pcr, pid, ver)				\
 	(CHK_PCI_PID(pcr, pid) && (pcr)->ic_version == (ver))
+#define is_version_higher_than(pcr, pid, ver)			\
+	(CHK_PCI_PID(pcr, pid) && (pcr)->ic_version > (ver))
 #define pcr_dbg(pcr, fmt, arg...)				\
 	dev_dbg(&(pcr)->pci->dev, fmt, ##arg)
 
-- 
cgit v1.2.3


From 13daf48978280ea8bce38f1e0598b913b09f5395 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 9 Nov 2020 22:53:16 +0200
Subject: gpiolib: Replace unsigned by unsigned int

Replace unsigned by unsigned int in GPIO library code.
Note, legacy API left untouched.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/gpio/gpiolib.c        | 16 ++++++++--------
 include/linux/gpio/consumer.h |  4 ++--
 2 files changed, 10 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index c980ddcda833..fe31e7f1fb6e 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -211,7 +211,7 @@ static int gpiochip_find_base(int ngpio)
 int gpiod_get_direction(struct gpio_desc *desc)
 {
 	struct gpio_chip *gc;
-	unsigned offset;
+	unsigned int offset;
 	int ret;
 
 	gc = gpiod_to_chip(desc);
@@ -1333,7 +1333,7 @@ void gpiochip_irq_domain_deactivate(struct irq_domain *domain,
 }
 EXPORT_SYMBOL_GPL(gpiochip_irq_domain_deactivate);
 
-static int gpiochip_to_irq(struct gpio_chip *gc, unsigned offset)
+static int gpiochip_to_irq(struct gpio_chip *gc, unsigned int offset)
 {
 	struct irq_domain *domain = gc->irq.domain;
 
@@ -1635,7 +1635,7 @@ static inline void gpiochip_irqchip_free_valid_mask(struct gpio_chip *gc)
  * @gc: the gpiochip owning the GPIO
  * @offset: the offset of the GPIO to request for GPIO function
  */
-int gpiochip_generic_request(struct gpio_chip *gc, unsigned offset)
+int gpiochip_generic_request(struct gpio_chip *gc, unsigned int offset)
 {
 #ifdef CONFIG_PINCTRL
 	if (list_empty(&gc->gpiodev->pin_ranges))
@@ -1651,7 +1651,7 @@ EXPORT_SYMBOL_GPL(gpiochip_generic_request);
  * @gc: the gpiochip to request the gpio function for
  * @offset: the offset of the GPIO to free from GPIO function
  */
-void gpiochip_generic_free(struct gpio_chip *gc, unsigned offset)
+void gpiochip_generic_free(struct gpio_chip *gc, unsigned int offset)
 {
 	pinctrl_gpio_free(gc->gpiodev->base + offset);
 }
@@ -1663,7 +1663,7 @@ EXPORT_SYMBOL_GPL(gpiochip_generic_free);
  * @offset: the offset of the GPIO to apply the configuration
  * @config: the configuration to be applied
  */
-int gpiochip_generic_config(struct gpio_chip *gc, unsigned offset,
+int gpiochip_generic_config(struct gpio_chip *gc, unsigned int offset,
 			    unsigned long config)
 {
 	return pinctrl_gpio_set_config(gc->gpiodev->base + offset, config);
@@ -1993,7 +1993,7 @@ void gpiod_free(struct gpio_desc *desc)
  * help with diagnostics, and knowing that the signal is used as a GPIO
  * can help avoid accidentally multiplexing it to another controller.
  */
-const char *gpiochip_is_requested(struct gpio_chip *gc, unsigned offset)
+const char *gpiochip_is_requested(struct gpio_chip *gc, unsigned int offset)
 {
 	struct gpio_desc *desc;
 
@@ -2097,7 +2097,7 @@ static int gpio_set_config(struct gpio_desc *desc, enum pin_config_param mode)
 {
 	struct gpio_chip *gc = desc->gdev->chip;
 	unsigned long config;
-	unsigned arg;
+	unsigned int arg;
 
 	switch (mode) {
 	case PIN_CONFIG_BIAS_PULL_DOWN:
@@ -2353,7 +2353,7 @@ EXPORT_SYMBOL_GPL(gpiod_set_config);
  * 0 on success, %-ENOTSUPP if the controller doesn't support setting the
  * debounce time.
  */
-int gpiod_set_debounce(struct gpio_desc *desc, unsigned debounce)
+int gpiod_set_debounce(struct gpio_desc *desc, unsigned int debounce)
 {
 	unsigned long config;
 
diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h
index 901aab89d025..ef49307611d2 100644
--- a/include/linux/gpio/consumer.h
+++ b/include/linux/gpio/consumer.h
@@ -158,7 +158,7 @@ int gpiod_set_raw_array_value_cansleep(unsigned int array_size,
 				       unsigned long *value_bitmap);
 
 int gpiod_set_config(struct gpio_desc *desc, unsigned long config);
-int gpiod_set_debounce(struct gpio_desc *desc, unsigned debounce);
+int gpiod_set_debounce(struct gpio_desc *desc, unsigned int debounce);
 int gpiod_set_transitory(struct gpio_desc *desc, bool transitory);
 void gpiod_toggle_active_low(struct gpio_desc *desc);
 
@@ -481,7 +481,7 @@ static inline int gpiod_set_config(struct gpio_desc *desc, unsigned long config)
 	return -ENOSYS;
 }
 
-static inline int gpiod_set_debounce(struct gpio_desc *desc, unsigned debounce)
+static inline int gpiod_set_debounce(struct gpio_desc *desc, unsigned int debounce)
 {
 	/* GPIO can never have been requested */
 	WARN_ON(desc);
-- 
cgit v1.2.3


From cc947f2b9c04113d84eeef67cc7c6326e1982019 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 16 Nov 2020 10:53:38 +0100
Subject: timers: Make run_local_timers() static

No users outside of the timer code. Move the caller below this function to
avoid a pointless forward declaration.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/timer.h |  1 -
 kernel/time/timer.c   | 48 ++++++++++++++++++++++++------------------------
 2 files changed, 24 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/timer.h b/include/linux/timer.h
index d10bc7e73b41..fda13c9d1256 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -193,7 +193,6 @@ extern int try_to_del_timer_sync(struct timer_list *timer);
 #define del_singleshot_timer_sync(t) del_timer_sync(t)
 
 extern void init_timers(void);
-extern void run_local_timers(void);
 struct hrtimer;
 extern enum hrtimer_restart it_real_fn(struct hrtimer *);
 
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index af9ddfbd447d..ebf3b26d2501 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1705,29 +1705,6 @@ void timer_clear_idle(void)
 }
 #endif
 
-/*
- * Called from the timer interrupt handler to charge one tick to the current
- * process.  user_tick is 1 if the tick is user time, 0 for system.
- */
-void update_process_times(int user_tick)
-{
-	struct task_struct *p = current;
-
-	PRANDOM_ADD_NOISE(jiffies, user_tick, p, 0);
-
-	/* Note: this timer irq context must be accounted for as well. */
-	account_process_tick(p, user_tick);
-	run_local_timers();
-	rcu_sched_clock_irq(user_tick);
-#ifdef CONFIG_IRQ_WORK
-	if (in_irq())
-		irq_work_tick();
-#endif
-	scheduler_tick();
-	if (IS_ENABLED(CONFIG_POSIX_TIMERS))
-		run_posix_cpu_timers();
-}
-
 /**
  * __run_timers - run all expired timers (if any) on this CPU.
  * @base: the timer vector to be processed.
@@ -1777,7 +1754,7 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h)
 /*
  * Called by the local, per-CPU timer interrupt on SMP.
  */
-void run_local_timers(void)
+static void run_local_timers(void)
 {
 	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
 
@@ -1794,6 +1771,29 @@ void run_local_timers(void)
 	raise_softirq(TIMER_SOFTIRQ);
 }
 
+/*
+ * Called from the timer interrupt handler to charge one tick to the current
+ * process.  user_tick is 1 if the tick is user time, 0 for system.
+ */
+void update_process_times(int user_tick)
+{
+	struct task_struct *p = current;
+
+	PRANDOM_ADD_NOISE(jiffies, user_tick, p, 0);
+
+	/* Note: this timer irq context must be accounted for as well. */
+	account_process_tick(p, user_tick);
+	run_local_timers();
+	rcu_sched_clock_irq(user_tick);
+#ifdef CONFIG_IRQ_WORK
+	if (in_irq())
+		irq_work_tick();
+#endif
+	scheduler_tick();
+	if (IS_ENABLED(CONFIG_POSIX_TIMERS))
+		run_posix_cpu_timers();
+}
+
 /*
  * Since schedule_timeout()'s timer is defined on the stack, it must store
  * the target task on the stack as well.
-- 
cgit v1.2.3


From 66981c37b3199d293c58f84cf2366e86a06e1a3d Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Mon, 16 Nov 2020 11:18:14 +0100
Subject: hrtimer: Fix kernel-doc markups

The hrtimer_get_remaining() markup is documenting, instead,
__hrtimer_get_remaining(), as it is placed at the C file.

In order to properly document it, a kernel-doc markup is needed together
with the function prototype. So, add a new one, while preserving the
existing one, just fixing the function name.

The hrtimer_is_queued prototype has a typo: it is using
'=' instead of '-' to split: identifier - description
as required by kernel-doc markup.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/9dc87808c2fd07b7e050bafcd033c5ef05808fea.1605521731.git.mchehab+huawei@kernel.org
---
 include/linux/hrtimer.h | 6 +++++-
 kernel/time/hrtimer.c   | 2 +-
 2 files changed, 6 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 107cedd7019a..bb5e7b0a4274 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -447,6 +447,10 @@ static inline void hrtimer_restart(struct hrtimer *timer)
 /* Query timers: */
 extern ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust);
 
+/**
+ * hrtimer_get_remaining - get remaining time for the timer
+ * @timer:	the timer to read
+ */
 static inline ktime_t hrtimer_get_remaining(const struct hrtimer *timer)
 {
 	return __hrtimer_get_remaining(timer, false);
@@ -458,7 +462,7 @@ extern u64 hrtimer_next_event_without(const struct hrtimer *exclude);
 extern bool hrtimer_active(const struct hrtimer *timer);
 
 /**
- * hrtimer_is_queued = check, whether the timer is on one of the queues
+ * hrtimer_is_queued - check, whether the timer is on one of the queues
  * @timer:	Timer to check
  *
  * Returns: True if the timer is queued, false otherwise
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 3624b9b5835d..61c39ff68439 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -1289,7 +1289,7 @@ int hrtimer_cancel(struct hrtimer *timer)
 EXPORT_SYMBOL_GPL(hrtimer_cancel);
 
 /**
- * hrtimer_get_remaining - get remaining time for the timer
+ * __hrtimer_get_remaining - get remaining time for the timer
  * @timer:	the timer to read
  * @adjust:	adjust relative timers when CONFIG_TIME_LOW_RES=y
  */
-- 
cgit v1.2.3


From e00adcadf3af7a8335026d71ab9f0e0a922191ac Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 3 Nov 2020 11:00:11 +0100
Subject: block: add a new set_read_only method

Add a new method to allow for driver-specific processing when setting or
clearing the block device read-only state.  This allows to replace the
cumbersome and error-prone override of the whole ioctl implementation.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/ioctl.c          | 5 +++++
 include/linux/blkdev.h | 1 +
 2 files changed, 6 insertions(+)

(limited to 'include/linux')

diff --git a/block/ioctl.c b/block/ioctl.c
index c6d8863f0409..a6fa16b97705 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -389,6 +389,11 @@ static int blkdev_roset(struct block_device *bdev, fmode_t mode,
 		return ret;
 	if (get_user(n, (int __user *)arg))
 		return -EFAULT;
+	if (bdev->bd_disk->fops->set_read_only) {
+		ret = bdev->bd_disk->fops->set_read_only(bdev, n);
+		if (ret)
+			return ret;
+	}
 	set_device_ro(bdev, n);
 	return 0;
 }
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 639cae2c158b..5c1ba8a8d2bc 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1850,6 +1850,7 @@ struct block_device_operations {
 	void (*unlock_native_capacity) (struct gendisk *);
 	int (*revalidate_disk) (struct gendisk *);
 	int (*getgeo)(struct block_device *, struct hd_geometry *);
+	int (*set_read_only)(struct block_device *bdev, bool ro);
 	/* this callback is with swap_lock and sometimes page table lock held */
 	void (*swap_slot_free_notify) (struct block_device *, unsigned long);
 	int (*report_zones)(struct gendisk *, sector_t sector,
-- 
cgit v1.2.3


From 98f49b63e84d4ee1a5c327d0b5f4e8699f6c70fe Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 3 Nov 2020 11:00:17 +0100
Subject: block: remove set_device_ro

Fold set_device_ro into its only remaining caller.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/genhd.c         | 7 -------
 block/ioctl.c         | 2 +-
 include/linux/genhd.h | 1 -
 3 files changed, 1 insertion(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/block/genhd.c b/block/genhd.c
index 9387f050c248..b85db1f2233c 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1846,13 +1846,6 @@ static void set_disk_ro_uevent(struct gendisk *gd, int ro)
 	kobject_uevent_env(&disk_to_dev(gd)->kobj, KOBJ_CHANGE, envp);
 }
 
-void set_device_ro(struct block_device *bdev, int flag)
-{
-	bdev->bd_part->policy = flag;
-}
-
-EXPORT_SYMBOL(set_device_ro);
-
 void set_disk_ro(struct gendisk *disk, int flag)
 {
 	struct disk_part_iter piter;
diff --git a/block/ioctl.c b/block/ioctl.c
index 96cb45447364..04255dc5f3bf 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -371,7 +371,7 @@ static int blkdev_roset(struct block_device *bdev, fmode_t mode,
 		if (ret)
 			return ret;
 	}
-	set_device_ro(bdev, n);
+	bdev->bd_part->policy = n;
 	return 0;
 }
 
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 03da3f603d30..52eb592c874a 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -304,7 +304,6 @@ extern void del_gendisk(struct gendisk *gp);
 extern struct gendisk *get_gendisk(dev_t dev, int *partno);
 extern struct block_device *bdget_disk(struct gendisk *disk, int partno);
 
-extern void set_device_ro(struct block_device *bdev, int flag);
 extern void set_disk_ro(struct gendisk *disk, int flag);
 
 static inline int get_disk_ro(struct gendisk *disk)
-- 
cgit v1.2.3


From a7cb3d2f09c8405aed59d97a7d02cebea43cd3c7 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 3 Nov 2020 11:00:18 +0100
Subject: block: remove __blkdev_driver_ioctl

Just open code it in the few callers.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/ioctl.c               | 25 +++++--------------------
 drivers/block/pktcdvd.c     |  6 ++++--
 drivers/md/bcache/request.c |  5 +++--
 drivers/md/dm.c             |  5 ++++-
 include/linux/blkdev.h      |  2 --
 5 files changed, 16 insertions(+), 27 deletions(-)

(limited to 'include/linux')

diff --git a/block/ioctl.c b/block/ioctl.c
index 04255dc5f3bf..6b785181344f 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -219,23 +219,6 @@ static int compat_put_ulong(compat_ulong_t __user *argp, compat_ulong_t val)
 }
 #endif
 
-int __blkdev_driver_ioctl(struct block_device *bdev, fmode_t mode,
-			unsigned cmd, unsigned long arg)
-{
-	struct gendisk *disk = bdev->bd_disk;
-
-	if (disk->fops->ioctl)
-		return disk->fops->ioctl(bdev, mode, cmd, arg);
-
-	return -ENOTTY;
-}
-/*
- * For the record: _GPL here is only because somebody decided to slap it
- * on the previous export.  Sheer idiocy, since it wasn't copyrightable
- * at all and could be open-coded without any exports by anybody who cares.
- */
-EXPORT_SYMBOL_GPL(__blkdev_driver_ioctl);
-
 #ifdef CONFIG_COMPAT
 /*
  * This is the equivalent of compat_ptr_ioctl(), to be used by block
@@ -594,10 +577,12 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 	}
 
 	ret = blkdev_common_ioctl(bdev, mode, cmd, arg, argp);
-	if (ret == -ENOIOCTLCMD)
-		return __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+	if (ret != -ENOIOCTLCMD)
+		return ret;
 
-	return ret;
+	if (!bdev->bd_disk->fops->ioctl)
+		return -ENOTTY;
+	return bdev->bd_disk->fops->ioctl(bdev, mode, cmd, arg);
 }
 EXPORT_SYMBOL_GPL(blkdev_ioctl); /* for /dev/raw */
 
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 467dbd06b7cd..ef1c1f094ea4 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -2584,9 +2584,11 @@ static int pkt_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd,
 	case CDROM_LAST_WRITTEN:
 	case CDROM_SEND_PACKET:
 	case SCSI_IOCTL_SEND_COMMAND:
-		ret = __blkdev_driver_ioctl(pd->bdev, mode, cmd, arg);
+		if (!bdev->bd_disk->fops->ioctl)
+			ret = -ENOTTY;
+		else
+			ret = bdev->bd_disk->fops->ioctl(bdev, mode, cmd, arg);
 		break;
-
 	default:
 		pkt_dbg(2, pd, "Unknown ioctl (%x)\n", cmd);
 		ret = -ENOTTY;
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 214326383145..afac8d07c1bd 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -1230,8 +1230,9 @@ static int cached_dev_ioctl(struct bcache_device *d, fmode_t mode,
 
 	if (dc->io_disable)
 		return -EIO;
-
-	return __blkdev_driver_ioctl(dc->bdev, mode, cmd, arg);
+	if (!dc->bdev->bd_disk->fops->ioctl)
+		return -ENOTTY;
+	return dc->bdev->bd_disk->fops->ioctl(dc->bdev, mode, cmd, arg);
 }
 
 void bch_cached_dev_request_init(struct cached_dev *dc)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index c18fc2548518..6db395c3d28b 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -570,7 +570,10 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode,
 		}
 	}
 
-	r =  __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+	if (!bdev->bd_disk->fops->ioctl)
+		r = -ENOTTY;
+	else
+		r = bdev->bd_disk->fops->ioctl(bdev, mode, cmd, arg);
 out:
 	dm_unprepare_ioctl(md, srcu_idx);
 	return r;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 5c1ba8a8d2bc..05b346a68c2e 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1867,8 +1867,6 @@ extern int blkdev_compat_ptr_ioctl(struct block_device *, fmode_t,
 #define blkdev_compat_ptr_ioctl NULL
 #endif
 
-extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int,
-				 unsigned long);
 extern int bdev_read_page(struct block_device *, sector_t, struct page *);
 extern int bdev_write_page(struct block_device *, sector_t, struct page *,
 						struct writeback_control *);
-- 
cgit v1.2.3


From a160c6159d4a0cf82f28bc1658a958e278ec3688 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 29 Oct 2020 15:58:28 +0100
Subject: block: add an optional probe callback to major_names

Add a callback to the major_names array that allows a driver to override
how to probe for dev_t that doesn't currently have a gendisk registered.
This will help separating the lookup of the gendisk by dev_t vs probe
action for a not currently registered dev_t.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/genhd.c         | 21 ++++++++++++++++++---
 include/linux/genhd.h |  5 ++++-
 2 files changed, 22 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/block/genhd.c b/block/genhd.c
index 81017bd3b333..20521163fd06 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -402,6 +402,7 @@ static struct blk_major_name {
 	struct blk_major_name *next;
 	int major;
 	char name[16];
+	void (*probe)(dev_t devt);
 } *major_names[BLKDEV_MAJOR_HASH_SIZE];
 static DEFINE_MUTEX(major_names_lock);
 
@@ -444,7 +445,8 @@ void blkdev_show(struct seq_file *seqf, off_t offset)
  * See Documentation/admin-guide/devices.txt for the list of allocated
  * major numbers.
  */
-int register_blkdev(unsigned int major, const char *name)
+int __register_blkdev(unsigned int major, const char *name,
+		void (*probe)(dev_t devt))
 {
 	struct blk_major_name **n, *p;
 	int index, ret = 0;
@@ -483,6 +485,7 @@ int register_blkdev(unsigned int major, const char *name)
 	}
 
 	p->major = major;
+	p->probe = probe;
 	strlcpy(p->name, name, sizeof(p->name));
 	p->next = NULL;
 	index = major_to_index(major);
@@ -505,8 +508,7 @@ out:
 	mutex_unlock(&major_names_lock);
 	return ret;
 }
-
-EXPORT_SYMBOL(register_blkdev);
+EXPORT_SYMBOL(__register_blkdev);
 
 void unregister_blkdev(unsigned int major, const char *name)
 {
@@ -1033,6 +1035,19 @@ static ssize_t disk_badblocks_store(struct device *dev,
 
 static void request_gendisk_module(dev_t devt)
 {
+	unsigned int major = MAJOR(devt);
+	struct blk_major_name **n;
+
+	mutex_lock(&major_names_lock);
+	for (n = &major_names[major_to_index(major)]; *n; n = &(*n)->next) {
+		if ((*n)->major == major && (*n)->probe) {
+			(*n)->probe(devt);
+			mutex_unlock(&major_names_lock);
+			return;
+		}
+	}
+	mutex_unlock(&major_names_lock);
+
 	if (request_module("block-major-%d-%d", MAJOR(devt), MINOR(devt)) > 0)
 		/* Make old-style 2.4 aliases work */
 		request_module("block-major-%d", MAJOR(devt));
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 52eb592c874a..811d0f83c4cf 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -367,7 +367,10 @@ extern void blk_unregister_region(dev_t devt, unsigned long range);
 
 #define alloc_disk(minors) alloc_disk_node(minors, NUMA_NO_NODE)
 
-int register_blkdev(unsigned int major, const char *name);
+int __register_blkdev(unsigned int major, const char *name,
+		void (*probe)(dev_t devt));
+#define register_blkdev(major, name) \
+	__register_blkdev(major, name, NULL)
 void unregister_blkdev(unsigned int major, const char *name);
 
 void revalidate_disk_size(struct gendisk *disk, bool verbose);
-- 
cgit v1.2.3


From d18e8b1bf9e2ee814a7f886a156bf762d52e178b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 29 Oct 2020 15:58:29 +0100
Subject: ide: remove ide_{,un}register_region

There is no need to ever register the fake gendisk used for ide-tape.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/ide/ide-probe.c | 32 --------------------------------
 drivers/ide/ide-tape.c  |  2 --
 include/linux/ide.h     |  3 ---
 3 files changed, 37 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c
index 1ddc45a04418..076d34b38172 100644
--- a/drivers/ide/ide-probe.c
+++ b/drivers/ide/ide-probe.c
@@ -929,38 +929,6 @@ static struct kobject *ata_probe(dev_t dev, int *part, void *data)
 	return NULL;
 }
 
-static struct kobject *exact_match(dev_t dev, int *part, void *data)
-{
-	struct gendisk *p = data;
-	*part &= (1 << PARTN_BITS) - 1;
-	return &disk_to_dev(p)->kobj;
-}
-
-static int exact_lock(dev_t dev, void *data)
-{
-	struct gendisk *p = data;
-
-	if (!get_disk_and_module(p))
-		return -1;
-	return 0;
-}
-
-void ide_register_region(struct gendisk *disk)
-{
-	blk_register_region(MKDEV(disk->major, disk->first_minor),
-			    disk->minors, NULL, exact_match, exact_lock, disk);
-}
-
-EXPORT_SYMBOL_GPL(ide_register_region);
-
-void ide_unregister_region(struct gendisk *disk)
-{
-	blk_unregister_region(MKDEV(disk->major, disk->first_minor),
-			      disk->minors);
-}
-
-EXPORT_SYMBOL_GPL(ide_unregister_region);
-
 void ide_init_disk(struct gendisk *disk, ide_drive_t *drive)
 {
 	ide_hwif_t *hwif = drive->hwif;
diff --git a/drivers/ide/ide-tape.c b/drivers/ide/ide-tape.c
index 6f26634b22bb..88b96437b22e 100644
--- a/drivers/ide/ide-tape.c
+++ b/drivers/ide/ide-tape.c
@@ -1822,7 +1822,6 @@ static void ide_tape_remove(ide_drive_t *drive)
 
 	ide_proc_unregister_driver(drive, tape->driver);
 	device_del(&tape->dev);
-	ide_unregister_region(tape->disk);
 
 	mutex_lock(&idetape_ref_mutex);
 	put_device(&tape->dev);
@@ -2026,7 +2025,6 @@ static int ide_tape_probe(ide_drive_t *drive)
 		      "n%s", tape->name);
 
 	g->fops = &idetape_block_ops;
-	ide_register_region(g);
 
 	return 0;
 
diff --git a/include/linux/ide.h b/include/linux/ide.h
index 62653769509f..2c300689a51a 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -1493,9 +1493,6 @@ static inline void ide_acpi_port_init_devices(ide_hwif_t *hwif) { ; }
 static inline void ide_acpi_set_state(ide_hwif_t *hwif, int on) {}
 #endif
 
-void ide_register_region(struct gendisk *);
-void ide_unregister_region(struct gendisk *);
-
 void ide_check_nien_quirk_list(ide_drive_t *);
 void ide_undecoded_slave(ide_drive_t *);
 
-- 
cgit v1.2.3


From e418de3abcda8b102f737919e830024d1455938f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 29 Oct 2020 15:58:41 +0100
Subject: block: switch gendisk lookup to a simple xarray

Now that bdev_map is only used for finding gendisks, we can use
a simple xarray instead of the regions tracking structure for it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/genhd.c         | 208 +++++++++-----------------------------------------
 include/linux/genhd.h |   7 --
 2 files changed, 37 insertions(+), 178 deletions(-)

(limited to 'include/linux')

diff --git a/block/genhd.c b/block/genhd.c
index 20521163fd06..01d146598fe7 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -27,15 +27,7 @@
 
 static struct kobject *block_depr;
 
-struct bdev_map {
-	struct bdev_map *next;
-	dev_t dev;
-	unsigned long range;
-	struct module *owner;
-	struct kobject *(*probe)(dev_t, int *, void *);
-	int (*lock)(dev_t, void *);
-	void *data;
-} *bdev_map[255];
+static DEFINE_XARRAY(bdev_map);
 static DEFINE_MUTEX(bdev_map_lock);
 
 /* for extended dynamic devt allocation, currently only one major is used */
@@ -649,85 +641,26 @@ static char *bdevt_str(dev_t devt, char *buf)
 	return buf;
 }
 
-/*
- * Register device numbers dev..(dev+range-1)
- * range must be nonzero
- * The hash chain is sorted on range, so that subranges can override.
- */
-void blk_register_region(dev_t devt, unsigned long range, struct module *module,
-			 struct kobject *(*probe)(dev_t, int *, void *),
-			 int (*lock)(dev_t, void *), void *data)
-{
-	unsigned n = MAJOR(devt + range - 1) - MAJOR(devt) + 1;
-	unsigned index = MAJOR(devt);
-	unsigned i;
-	struct bdev_map *p;
-
-	n = min(n, 255u);
-	p = kmalloc_array(n, sizeof(struct bdev_map), GFP_KERNEL);
-	if (p == NULL)
-		return;
-
-	for (i = 0; i < n; i++, p++) {
-		p->owner = module;
-		p->probe = probe;
-		p->lock = lock;
-		p->dev = devt;
-		p->range = range;
-		p->data = data;
-	}
+static void blk_register_region(struct gendisk *disk)
+{
+	int i;
 
 	mutex_lock(&bdev_map_lock);
-	for (i = 0, p -= n; i < n; i++, p++, index++) {
-		struct bdev_map **s = &bdev_map[index % 255];
-		while (*s && (*s)->range < range)
-			s = &(*s)->next;
-		p->next = *s;
-		*s = p;
+	for (i = 0; i < disk->minors; i++) {
+		if (xa_insert(&bdev_map, disk_devt(disk) + i, disk, GFP_KERNEL))
+			WARN_ON_ONCE(1);
 	}
 	mutex_unlock(&bdev_map_lock);
 }
-EXPORT_SYMBOL(blk_register_region);
 
-void blk_unregister_region(dev_t devt, unsigned long range)
+static void blk_unregister_region(struct gendisk *disk)
 {
-	unsigned n = MAJOR(devt + range - 1) - MAJOR(devt) + 1;
-	unsigned index = MAJOR(devt);
-	unsigned i;
-	struct bdev_map *found = NULL;
+	int i;
 
 	mutex_lock(&bdev_map_lock);
-	for (i = 0; i < min(n, 255u); i++, index++) {
-		struct bdev_map **s;
-		for (s = &bdev_map[index % 255]; *s; s = &(*s)->next) {
-			struct bdev_map *p = *s;
-			if (p->dev == devt && p->range == range) {
-				*s = p->next;
-				if (!found)
-					found = p;
-				break;
-			}
-		}
-	}
+	for (i = 0; i < disk->minors; i++)
+		xa_erase(&bdev_map, disk_devt(disk) + i);
 	mutex_unlock(&bdev_map_lock);
-	kfree(found);
-}
-EXPORT_SYMBOL(blk_unregister_region);
-
-static struct kobject *exact_match(dev_t devt, int *partno, void *data)
-{
-	struct gendisk *p = data;
-
-	return &disk_to_dev(p)->kobj;
-}
-
-static int exact_lock(dev_t devt, void *data)
-{
-	struct gendisk *p = data;
-
-	if (!get_disk_and_module(p))
-		return -1;
-	return 0;
 }
 
 static void disk_scan_partitions(struct gendisk *disk)
@@ -873,8 +806,7 @@ static void __device_add_disk(struct device *parent, struct gendisk *disk,
 		ret = bdi_register(bdi, "%u:%u", MAJOR(devt), MINOR(devt));
 		WARN_ON(ret);
 		bdi_set_owner(bdi, dev);
-		blk_register_region(disk_devt(disk), disk->minors, NULL,
-				    exact_match, exact_lock, disk);
+		blk_register_region(disk);
 	}
 	register_disk(parent, disk, groups);
 	if (register_queue)
@@ -987,7 +919,7 @@ void del_gendisk(struct gendisk *disk)
 	blk_unregister_queue(disk);
 	
 	if (!(disk->flags & GENHD_FL_HIDDEN))
-		blk_unregister_region(disk_devt(disk), disk->minors);
+		blk_unregister_region(disk);
 	/*
 	 * Remove gendisk pointer from idr so that it cannot be looked up
 	 * while RCU period before freeing gendisk is running to prevent
@@ -1053,54 +985,22 @@ static void request_gendisk_module(dev_t devt)
 		request_module("block-major-%d", MAJOR(devt));
 }
 
-static struct gendisk *lookup_gendisk(dev_t dev, int *partno)
+static bool get_disk_and_module(struct gendisk *disk)
 {
-	struct kobject *kobj;
-	struct bdev_map *p;
-	unsigned long best = ~0UL;
-
-retry:
-	mutex_lock(&bdev_map_lock);
-	for (p = bdev_map[MAJOR(dev) % 255]; p; p = p->next) {
-		struct kobject *(*probe)(dev_t, int *, void *);
-		struct module *owner;
-		void *data;
-
-		if (p->dev > dev || p->dev + p->range - 1 < dev)
-			continue;
-		if (p->range - 1 >= best)
-			break;
-		if (!try_module_get(p->owner))
-			continue;
-		owner = p->owner;
-		data = p->data;
-		probe = p->probe;
-		best = p->range - 1;
-		*partno = dev - p->dev;
-
-		if (!probe) {
-			mutex_unlock(&bdev_map_lock);
-			module_put(owner);
-			request_gendisk_module(dev);
-			goto retry;
-		}
+	struct module *owner;
 
-		if (p->lock && p->lock(dev, data) < 0) {
-			module_put(owner);
-			continue;
-		}
-		mutex_unlock(&bdev_map_lock);
-		kobj = probe(dev, partno, data);
-		/* Currently ->owner protects _only_ ->probe() itself. */
+	if (!disk->fops)
+		return false;
+	owner = disk->fops->owner;
+	if (owner && !try_module_get(owner))
+		return false;
+	if (!kobject_get_unless_zero(&disk_to_dev(disk)->kobj)) {
 		module_put(owner);
-		if (kobj)
-			return dev_to_disk(kobj_to_dev(kobj));
-		goto retry;
+		return false;
 	}
-	mutex_unlock(&bdev_map_lock);
-	return NULL;
-}
+	return true;
 
+}
 
 /**
  * get_gendisk - get partitioning information for a given device
@@ -1119,7 +1019,19 @@ struct gendisk *get_gendisk(dev_t devt, int *partno)
 	might_sleep();
 
 	if (MAJOR(devt) != BLOCK_EXT_MAJOR) {
-		disk = lookup_gendisk(devt, partno);
+		mutex_lock(&bdev_map_lock);
+		disk = xa_load(&bdev_map, devt);
+		if (!disk) {
+			mutex_unlock(&bdev_map_lock);
+			request_gendisk_module(devt);
+			mutex_lock(&bdev_map_lock);
+			disk = xa_load(&bdev_map, devt);
+		}
+		if (disk && !get_disk_and_module(disk))
+			disk = NULL;
+		if (disk)
+			*partno = devt - disk_devt(disk);
+		mutex_unlock(&bdev_map_lock);
 	} else {
 		struct hd_struct *part;
 
@@ -1323,21 +1235,6 @@ static const struct seq_operations partitions_op = {
 };
 #endif
 
-static void bdev_map_init(void)
-{
-	struct bdev_map *base;
-	int i;
-
-	base = kzalloc(sizeof(*base), GFP_KERNEL);
-	if (!base)
-		panic("cannot allocate bdev_map");
-
-	base->dev = 1;
-	base->range = ~0 ;
-	for (i = 0; i < 255; i++)
-		bdev_map[i] = base;
-}
-
 static int __init genhd_device_init(void)
 {
 	int error;
@@ -1346,7 +1243,6 @@ static int __init genhd_device_init(void)
 	error = class_register(&block_class);
 	if (unlikely(error))
 		return error;
-	bdev_map_init();
 	blk_dev_init();
 
 	register_blkdev(BLOCK_EXT_MAJOR, "blkext");
@@ -1895,35 +1791,6 @@ out_free_disk:
 }
 EXPORT_SYMBOL(__alloc_disk_node);
 
-/**
- * get_disk_and_module - increments the gendisk and gendisk fops module refcount
- * @disk: the struct gendisk to increment the refcount for
- *
- * This increments the refcount for the struct gendisk, and the gendisk's
- * fops module owner.
- *
- * Context: Any context.
- */
-struct kobject *get_disk_and_module(struct gendisk *disk)
-{
-	struct module *owner;
-	struct kobject *kobj;
-
-	if (!disk->fops)
-		return NULL;
-	owner = disk->fops->owner;
-	if (owner && !try_module_get(owner))
-		return NULL;
-	kobj = kobject_get_unless_zero(&disk_to_dev(disk)->kobj);
-	if (kobj == NULL) {
-		module_put(owner);
-		return NULL;
-	}
-	return kobj;
-
-}
-EXPORT_SYMBOL(get_disk_and_module);
-
 /**
  * put_disk - decrements the gendisk refcount
  * @disk: the struct gendisk to decrement the refcount for
@@ -1960,7 +1827,6 @@ void put_disk_and_module(struct gendisk *disk)
 		module_put(owner);
 	}
 }
-EXPORT_SYMBOL(put_disk_and_module);
 
 static void set_disk_ro_uevent(struct gendisk *gd, int ro)
 {
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 811d0f83c4cf..3cbc2781ef34 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -339,15 +339,8 @@ int blk_add_partitions(struct gendisk *disk, struct block_device *bdev);
 int blk_drop_partitions(struct block_device *bdev);
 
 extern struct gendisk *__alloc_disk_node(int minors, int node_id);
-extern struct kobject *get_disk_and_module(struct gendisk *disk);
 extern void put_disk(struct gendisk *disk);
 extern void put_disk_and_module(struct gendisk *disk);
-extern void blk_register_region(dev_t devt, unsigned long range,
-			struct module *module,
-			struct kobject *(*probe)(dev_t, int *, void *),
-			int (*lock)(dev_t, void *),
-			void *data);
-extern void blk_unregister_region(dev_t devt, unsigned long range);
 
 #define alloc_disk_node(minors, node_id)				\
 ({									\
-- 
cgit v1.2.3


From 7a089ec7d77fe7d50f6bb7b178fa25eec9fd822b Mon Sep 17 00:00:00 2001
From: Peilin Ye <yepeilin.cs@gmail.com>
Date: Thu, 12 Nov 2020 07:04:03 -0500
Subject: console: Delete unused con_font_copy() callback implementations

Recently in commit 3c4e0dff2095 ("vt: Disable KD_FONT_OP_COPY") we
disabled the KD_FONT_OP_COPY ioctl() option. Delete all the
con_font_copy() callbacks, since we no longer use them.

Mark KD_FONT_OP_COPY as "obsolete" in include/uapi/linux/kd.h, just like
what we have done for PPPIOCDETACH in commit af8d3c7c001a ("ppp: remove
the PPPIOCDETACH ioctl").

Signed-off-by: Peilin Ye <yepeilin.cs@gmail.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/c8d28007edf50de4387e1532eb3eb736db716f73.1605169912.git.yepeilin.cs@gmail.com
---
 drivers/usb/misc/sisusbvga/sisusb_con.c |  6 ------
 drivers/video/console/dummycon.c        |  6 ------
 drivers/video/fbdev/core/fbcon.c        | 11 -----------
 include/linux/console.h                 |  1 -
 include/uapi/linux/kd.h                 |  2 +-
 5 files changed, 1 insertion(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/usb/misc/sisusbvga/sisusb_con.c b/drivers/usb/misc/sisusbvga/sisusb_con.c
index c63e545fb105..fd9954381fbf 100644
--- a/drivers/usb/misc/sisusbvga/sisusb_con.c
+++ b/drivers/usb/misc/sisusbvga/sisusb_con.c
@@ -1358,11 +1358,6 @@ static int sisusbdummycon_font_default(struct vc_data *vc,
 	return 0;
 }
 
-static int sisusbdummycon_font_copy(struct vc_data *vc, int con)
-{
-	return 0;
-}
-
 static const struct consw sisusb_dummy_con = {
 	.owner =		THIS_MODULE,
 	.con_startup =		sisusbdummycon_startup,
@@ -1377,7 +1372,6 @@ static const struct consw sisusb_dummy_con = {
 	.con_blank =		sisusbdummycon_blank,
 	.con_font_set =		sisusbdummycon_font_set,
 	.con_font_default =	sisusbdummycon_font_default,
-	.con_font_copy =	sisusbdummycon_font_copy,
 };
 
 int
diff --git a/drivers/video/console/dummycon.c b/drivers/video/console/dummycon.c
index 2a0d0bda7faa..ab3df752fb57 100644
--- a/drivers/video/console/dummycon.c
+++ b/drivers/video/console/dummycon.c
@@ -136,11 +136,6 @@ static int dummycon_font_default(struct vc_data *vc,
 	return 0;
 }
 
-static int dummycon_font_copy(struct vc_data *vc, int con)
-{
-	return 0;
-}
-
 /*
  *  The console `switch' structure for the dummy console
  *
@@ -161,6 +156,5 @@ const struct consw dummy_con = {
 	.con_blank =	dummycon_blank,
 	.con_font_set =	dummycon_font_set,
 	.con_font_default =	dummycon_font_default,
-	.con_font_copy =	dummycon_font_copy,
 };
 EXPORT_SYMBOL_GPL(dummy_con);
diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c
index cef437817b0d..26d1b0916692 100644
--- a/drivers/video/fbdev/core/fbcon.c
+++ b/drivers/video/fbdev/core/fbcon.c
@@ -2451,16 +2451,6 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h,
 	return 0;
 }
 
-static int fbcon_copy_font(struct vc_data *vc, int con)
-{
-	struct fbcon_display *od = &fb_display[con];
-	struct console_font *f = &vc->vc_font;
-
-	if (od->fontdata == f->data)
-		return 0;	/* already the same font... */
-	return fbcon_do_set_font(vc, f->width, f->height, od->fontdata, od->userfont);
-}
-
 /*
  *  User asked to set font; we are guaranteed that
  *	a) width and height are in range 1..32
@@ -3111,7 +3101,6 @@ static const struct consw fb_con = {
 	.con_font_set 		= fbcon_set_font,
 	.con_font_get 		= fbcon_get_font,
 	.con_font_default	= fbcon_set_def_font,
-	.con_font_copy 		= fbcon_copy_font,
 	.con_set_palette 	= fbcon_set_palette,
 	.con_invert_region 	= fbcon_invert_region,
 	.con_screen_pos 	= fbcon_screen_pos,
diff --git a/include/linux/console.h b/include/linux/console.h
index 4b1e26c4cb42..20874db50bc8 100644
--- a/include/linux/console.h
+++ b/include/linux/console.h
@@ -62,7 +62,6 @@ struct consw {
 	int	(*con_font_get)(struct vc_data *vc, struct console_font *font);
 	int	(*con_font_default)(struct vc_data *vc,
 			struct console_font *font, char *name);
-	int	(*con_font_copy)(struct vc_data *vc, int con);
 	int     (*con_resize)(struct vc_data *vc, unsigned int width,
 			unsigned int height, unsigned int user);
 	void	(*con_set_palette)(struct vc_data *vc,
diff --git a/include/uapi/linux/kd.h b/include/uapi/linux/kd.h
index 4616b31f84da..ee929ece4112 100644
--- a/include/uapi/linux/kd.h
+++ b/include/uapi/linux/kd.h
@@ -173,7 +173,7 @@ struct console_font {
 #define KD_FONT_OP_SET		0	/* Set font */
 #define KD_FONT_OP_GET		1	/* Get font */
 #define KD_FONT_OP_SET_DEFAULT	2	/* Set font to default, data points to name / NULL */
-#define KD_FONT_OP_COPY		3	/* Copy from another console */
+#define KD_FONT_OP_COPY		3	/* Obsolete, do not use */
 
 #define KD_FONT_FLAG_DONT_RECALC 	1	/* Don't recalculate hw charcell size [compat] */
 
-- 
cgit v1.2.3


From 4ee573086bd88ff3060dda07873bf755d332e9ba Mon Sep 17 00:00:00 2001
From: Peilin Ye <yepeilin.cs@gmail.com>
Date: Thu, 12 Nov 2020 07:13:34 -0500
Subject: Fonts: Add charcount field to font_desc

Subsystems are hard-coding the number of characters of our built-in fonts
as 256. Include that information in our kernel font descriptor, `struct
font_desc`.

Signed-off-by: Peilin Ye <yepeilin.cs@gmail.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/65952296d1d9486093bd955d1536f7dcd11112c6.1605169912.git.yepeilin.cs@gmail.com
---
 include/linux/font.h       | 1 +
 lib/fonts/font_10x18.c     | 1 +
 lib/fonts/font_6x10.c      | 1 +
 lib/fonts/font_6x11.c      | 1 +
 lib/fonts/font_6x8.c       | 1 +
 lib/fonts/font_7x14.c      | 1 +
 lib/fonts/font_8x16.c      | 1 +
 lib/fonts/font_8x8.c       | 1 +
 lib/fonts/font_acorn_8x8.c | 1 +
 lib/fonts/font_mini_4x6.c  | 1 +
 lib/fonts/font_pearl_8x8.c | 1 +
 lib/fonts/font_sun12x22.c  | 1 +
 lib/fonts/font_sun8x16.c   | 1 +
 lib/fonts/font_ter16x32.c  | 1 +
 14 files changed, 14 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/font.h b/include/linux/font.h
index 4f50d736ea72..abf1442ce719 100644
--- a/include/linux/font.h
+++ b/include/linux/font.h
@@ -17,6 +17,7 @@ struct font_desc {
     int idx;
     const char *name;
     unsigned int width, height;
+    unsigned int charcount;
     const void *data;
     int pref;
 };
diff --git a/lib/fonts/font_10x18.c b/lib/fonts/font_10x18.c
index e02f9df24d1e..5d940db626e7 100644
--- a/lib/fonts/font_10x18.c
+++ b/lib/fonts/font_10x18.c
@@ -5137,6 +5137,7 @@ const struct font_desc font_10x18 = {
 	.name	= "10x18",
 	.width	= 10,
 	.height	= 18,
+	.charcount = 256,
 	.data	= fontdata_10x18.data,
 #ifdef __sparc__
 	.pref	= 5,
diff --git a/lib/fonts/font_6x10.c b/lib/fonts/font_6x10.c
index 6e3c4b7691c8..e65df019e0d2 100644
--- a/lib/fonts/font_6x10.c
+++ b/lib/fonts/font_6x10.c
@@ -3083,6 +3083,7 @@ const struct font_desc font_6x10 = {
 	.name	= "6x10",
 	.width	= 6,
 	.height	= 10,
+	.charcount = 256,
 	.data	= fontdata_6x10.data,
 	.pref	= 0,
 };
diff --git a/lib/fonts/font_6x11.c b/lib/fonts/font_6x11.c
index 2d22a24e816f..bd76b3f6b635 100644
--- a/lib/fonts/font_6x11.c
+++ b/lib/fonts/font_6x11.c
@@ -3346,6 +3346,7 @@ const struct font_desc font_vga_6x11 = {
 	.name	= "ProFont6x11",
 	.width	= 6,
 	.height	= 11,
+	.charcount = 256,
 	.data	= fontdata_6x11.data,
 	/* Try avoiding this font if possible unless on MAC */
 	.pref	= -2000,
diff --git a/lib/fonts/font_6x8.c b/lib/fonts/font_6x8.c
index e7442a0d183d..06ace7792521 100644
--- a/lib/fonts/font_6x8.c
+++ b/lib/fonts/font_6x8.c
@@ -2571,6 +2571,7 @@ const struct font_desc font_6x8 = {
 	.name	= "6x8",
 	.width	= 6,
 	.height	= 8,
+	.charcount = 256,
 	.data	= fontdata_6x8.data,
 	.pref	= 0,
 };
diff --git a/lib/fonts/font_7x14.c b/lib/fonts/font_7x14.c
index 9cc7ae2e03f7..a2f561c9fa04 100644
--- a/lib/fonts/font_7x14.c
+++ b/lib/fonts/font_7x14.c
@@ -4113,6 +4113,7 @@ const struct font_desc font_7x14 = {
 	.name	= "7x14",
 	.width	= 7,
 	.height	= 14,
+	.charcount = 256,
 	.data	= fontdata_7x14.data,
 	.pref	= 0,
 };
diff --git a/lib/fonts/font_8x16.c b/lib/fonts/font_8x16.c
index bab25dc59e8d..06ae14088514 100644
--- a/lib/fonts/font_8x16.c
+++ b/lib/fonts/font_8x16.c
@@ -4627,6 +4627,7 @@ const struct font_desc font_vga_8x16 = {
 	.name	= "VGA8x16",
 	.width	= 8,
 	.height	= 16,
+	.charcount = 256,
 	.data	= fontdata_8x16.data,
 	.pref	= 0,
 };
diff --git a/lib/fonts/font_8x8.c b/lib/fonts/font_8x8.c
index 109d0572368f..69570b8c31af 100644
--- a/lib/fonts/font_8x8.c
+++ b/lib/fonts/font_8x8.c
@@ -2578,6 +2578,7 @@ const struct font_desc font_vga_8x8 = {
 	.name	= "VGA8x8",
 	.width	= 8,
 	.height	= 8,
+	.charcount = 256,
 	.data	= fontdata_8x8.data,
 	.pref	= 0,
 };
diff --git a/lib/fonts/font_acorn_8x8.c b/lib/fonts/font_acorn_8x8.c
index fb395f0d4031..18755c33d249 100644
--- a/lib/fonts/font_acorn_8x8.c
+++ b/lib/fonts/font_acorn_8x8.c
@@ -270,6 +270,7 @@ const struct font_desc font_acorn_8x8 = {
 	.name	= "Acorn8x8",
 	.width	= 8,
 	.height	= 8,
+	.charcount = 256,
 	.data	= acorndata_8x8.data,
 #ifdef CONFIG_ARCH_ACORN
 	.pref	= 20,
diff --git a/lib/fonts/font_mini_4x6.c b/lib/fonts/font_mini_4x6.c
index 592774a90917..8d39fd447952 100644
--- a/lib/fonts/font_mini_4x6.c
+++ b/lib/fonts/font_mini_4x6.c
@@ -2152,6 +2152,7 @@ const struct font_desc font_mini_4x6 = {
 	.name	= "MINI4x6",
 	.width	= 4,
 	.height	= 6,
+	.charcount = 256,
 	.data	= fontdata_mini_4x6.data,
 	.pref	= 3,
 };
diff --git a/lib/fonts/font_pearl_8x8.c b/lib/fonts/font_pearl_8x8.c
index a6f95ebce950..b1678ed0017c 100644
--- a/lib/fonts/font_pearl_8x8.c
+++ b/lib/fonts/font_pearl_8x8.c
@@ -2582,6 +2582,7 @@ const struct font_desc font_pearl_8x8 = {
 	.name	= "PEARL8x8",
 	.width	= 8,
 	.height	= 8,
+	.charcount = 256,
 	.data	= fontdata_pearl8x8.data,
 	.pref	= 2,
 };
diff --git a/lib/fonts/font_sun12x22.c b/lib/fonts/font_sun12x22.c
index a5b65bd49604..91daf5ab8b6b 100644
--- a/lib/fonts/font_sun12x22.c
+++ b/lib/fonts/font_sun12x22.c
@@ -6156,6 +6156,7 @@ const struct font_desc font_sun_12x22 = {
 	.name	= "SUN12x22",
 	.width	= 12,
 	.height	= 22,
+	.charcount = 256,
 	.data	= fontdata_sun12x22.data,
 #ifdef __sparc__
 	.pref	= 5,
diff --git a/lib/fonts/font_sun8x16.c b/lib/fonts/font_sun8x16.c
index e577e76a6a7c..81bb4eeae04e 100644
--- a/lib/fonts/font_sun8x16.c
+++ b/lib/fonts/font_sun8x16.c
@@ -268,6 +268,7 @@ const struct font_desc font_sun_8x16 = {
 	.name	= "SUN8x16",
 	.width	= 8,
 	.height	= 16,
+	.charcount = 256,
 	.data	= fontdata_sun8x16.data,
 #ifdef __sparc__
 	.pref	= 10,
diff --git a/lib/fonts/font_ter16x32.c b/lib/fonts/font_ter16x32.c
index f7c3abb6b99e..1955d624177c 100644
--- a/lib/fonts/font_ter16x32.c
+++ b/lib/fonts/font_ter16x32.c
@@ -2062,6 +2062,7 @@ const struct font_desc font_ter_16x32 = {
 	.name	= "TER16x32",
 	.width	= 16,
 	.height = 32,
+	.charcount = 256,
 	.data	= fontdata_ter16x32.data,
 #ifdef __sparc__
 	.pref	= 5,
-- 
cgit v1.2.3


From 449f4ec9892ebc2f37a7eae6d97db2cf7c65e09a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 16 Nov 2020 15:56:56 +0100
Subject: block: remove the update_bdev parameter to
 set_capacity_revalidate_and_notify

The update_bdev argument is always set to true, so remove it.  Also
rename the function to the slighly less verbose set_capacity_and_notify,
as propagating the disk size to the block device isn't really
revalidation.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Petr Vorel <pvorel@suse.cz>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/genhd.c                | 13 +++++--------
 drivers/block/loop.c         |  2 +-
 drivers/block/virtio_blk.c   |  2 +-
 drivers/block/xen-blkfront.c |  2 +-
 drivers/nvme/host/core.c     |  2 +-
 drivers/scsi/sd.c            |  5 ++---
 include/linux/genhd.h        |  3 +--
 7 files changed, 12 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/block/genhd.c b/block/genhd.c
index ec2a24799cd9..4e039524f92b 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -47,17 +47,15 @@ static void disk_del_events(struct gendisk *disk);
 static void disk_release_events(struct gendisk *disk);
 
 /*
- * Set disk capacity and notify if the size is not currently
- * zero and will not be set to zero
+ * Set disk capacity and notify if the size is not currently zero and will not
+ * be set to zero.  Returns true if a uevent was sent, otherwise false.
  */
-bool set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size,
-					bool update_bdev)
+bool set_capacity_and_notify(struct gendisk *disk, sector_t size)
 {
 	sector_t capacity = get_capacity(disk);
 
 	set_capacity(disk, size);
-	if (update_bdev)
-		revalidate_disk_size(disk, true);
+	revalidate_disk_size(disk, true);
 
 	if (capacity != size && capacity != 0 && size != 0) {
 		char *envp[] = { "RESIZE=1", NULL };
@@ -68,8 +66,7 @@ bool set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size,
 
 	return false;
 }
-
-EXPORT_SYMBOL_GPL(set_capacity_revalidate_and_notify);
+EXPORT_SYMBOL_GPL(set_capacity_and_notify);
 
 /*
  * Format the device name of the indicated disk into the supplied buffer and
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index fcc5e32f0993..9a27d4f1c08a 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -251,7 +251,7 @@ loop_validate_block_size(unsigned short bsize)
  */
 static void loop_set_size(struct loop_device *lo, loff_t size)
 {
-	if (!set_capacity_revalidate_and_notify(lo->lo_disk, size, true))
+	if (!set_capacity_and_notify(lo->lo_disk, size))
 		kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE);
 }
 
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index a314b9382442..3e812b4c32e6 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -470,7 +470,7 @@ static void virtblk_update_capacity(struct virtio_blk *vblk, bool resize)
 		   cap_str_10,
 		   cap_str_2);
 
-	set_capacity_revalidate_and_notify(vblk->disk, capacity, true);
+	set_capacity_and_notify(vblk->disk, capacity);
 }
 
 static void virtblk_config_changed_work(struct work_struct *work)
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 48629d3433b4..79521e33d30e 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -2370,7 +2370,7 @@ static void blkfront_connect(struct blkfront_info *info)
 			return;
 		printk(KERN_INFO "Setting capacity to %Lu\n",
 		       sectors);
-		set_capacity_revalidate_and_notify(info->gd, sectors, true);
+		set_capacity_and_notify(info->gd, sectors);
 
 		return;
 	case BLKIF_STATE_SUSPENDED:
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index f6c6479da0e9..6c144e748f8c 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2053,7 +2053,7 @@ static void nvme_update_disk_info(struct gendisk *disk,
 			capacity = 0;
 	}
 
-	set_capacity_revalidate_and_notify(disk, capacity, true);
+	set_capacity_and_notify(disk, capacity);
 
 	nvme_config_discard(disk, ns);
 	nvme_config_write_zeroes(disk, ns);
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index e9b898a1a480..679c2c025047 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -3261,8 +3261,7 @@ static int sd_revalidate_disk(struct gendisk *disk)
 
 	sdkp->first_scan = 0;
 
-	set_capacity_revalidate_and_notify(disk,
-		logical_to_sectors(sdp, sdkp->capacity), true);
+	set_capacity_and_notify(disk, logical_to_sectors(sdp, sdkp->capacity));
 	sd_config_write_same(sdkp);
 	kfree(buffer);
 
@@ -3272,7 +3271,7 @@ static int sd_revalidate_disk(struct gendisk *disk)
 	 * capacity to 0.
 	 */
 	if (sd_zbc_revalidate_zones(sdkp))
-		set_capacity_revalidate_and_notify(disk, 0, true);
+		set_capacity_and_notify(disk, 0);
 
  out:
 	return 0;
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 3cbc2781ef34..46553d6d6025 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -314,8 +314,7 @@ static inline int get_disk_ro(struct gendisk *disk)
 extern void disk_block_events(struct gendisk *disk);
 extern void disk_unblock_events(struct gendisk *disk);
 extern void disk_flush_events(struct gendisk *disk, unsigned int mask);
-bool set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size,
-		bool update_bdev);
+bool set_capacity_and_notify(struct gendisk *disk, sector_t size);
 
 /* drivers/char/random.c */
 extern void add_disk_randomness(struct gendisk *disk) __latent_entropy;
-- 
cgit v1.2.3


From cef397038167ac15d085914493d6c86385773709 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 11 Nov 2020 17:52:58 +0100
Subject: arch: pgtable: define MAX_POSSIBLE_PHYSMEM_BITS where needed

Stefan Agner reported a bug when using zsram on 32-bit Arm machines
with RAM above the 4GB address boundary:

  Unable to handle kernel NULL pointer dereference at virtual address 00000000
  pgd = a27bd01c
  [00000000] *pgd=236a0003, *pmd=1ffa64003
  Internal error: Oops: 207 [#1] SMP ARM
  Modules linked in: mdio_bcm_unimac(+) brcmfmac cfg80211 brcmutil raspberrypi_hwmon hci_uart crc32_arm_ce bcm2711_thermal phy_generic genet
  CPU: 0 PID: 123 Comm: mkfs.ext4 Not tainted 5.9.6 #1
  Hardware name: BCM2711
  PC is at zs_map_object+0x94/0x338
  LR is at zram_bvec_rw.constprop.0+0x330/0xa64
  pc : [<c0602b38>]    lr : [<c0bda6a0>]    psr: 60000013
  sp : e376bbe0  ip : 00000000  fp : c1e2921c
  r10: 00000002  r9 : c1dda730  r8 : 00000000
  r7 : e8ff7a00  r6 : 00000000  r5 : 02f9ffa0  r4 : e3710000
  r3 : 000fdffe  r2 : c1e0ce80  r1 : ebf979a0  r0 : 00000000
  Flags: nZCv  IRQs on  FIQs on  Mode SVC_32  ISA ARM  Segment user
  Control: 30c5383d  Table: 235c2a80  DAC: fffffffd
  Process mkfs.ext4 (pid: 123, stack limit = 0x495a22e6)
  Stack: (0xe376bbe0 to 0xe376c000)

As it turns out, zsram needs to know the maximum memory size, which
is defined in MAX_PHYSMEM_BITS when CONFIG_SPARSEMEM is set, or in
MAX_POSSIBLE_PHYSMEM_BITS on the x86 architecture.

The same problem will be hit on all 32-bit architectures that have a
physical address space larger than 4GB and happen to not enable sparsemem
and include asm/sparsemem.h from asm/pgtable.h.

After the initial discussion, I suggested just always defining
MAX_POSSIBLE_PHYSMEM_BITS whenever CONFIG_PHYS_ADDR_T_64BIT is
set, or provoking a build error otherwise. This addresses all
configurations that can currently have this runtime bug, but
leaves all other configurations unchanged.

I looked up the possible number of bits in source code and
datasheets, here is what I found:

 - on ARC, CONFIG_ARC_HAS_PAE40 controls whether 32 or 40 bits are used
 - on ARM, CONFIG_LPAE enables 40 bit addressing, without it we never
   support more than 32 bits, even though supersections in theory allow
   up to 40 bits as well.
 - on MIPS, some MIPS32r1 or later chips support 36 bits, and MIPS32r5
   XPA supports up to 60 bits in theory, but 40 bits are more than
   anyone will ever ship
 - On PowerPC, there are three different implementations of 36 bit
   addressing, but 32-bit is used without CONFIG_PTE_64BIT
 - On RISC-V, the normal page table format can support 34 bit
   addressing. There is no highmem support on RISC-V, so anything
   above 2GB is unused, but it might be useful to eventually support
   CONFIG_ZRAM for high pages.

Fixes: 61989a80fb3a ("staging: zsmalloc: zsmalloc memory allocation library")
Fixes: 02390b87a945 ("mm/zsmalloc: Prepare to variable MAX_PHYSMEM_BITS")
Acked-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Reviewed-by: Stefan Agner <stefan@agner.ch>
Tested-by: Stefan Agner <stefan@agner.ch>
Acked-by: Mike Rapoport <rppt@linux.ibm.com>
Link: https://lore.kernel.org/linux-mm/bdfa44bf1c570b05d6c70898e2bbb0acf234ecdf.1604762181.git.stefan@agner.ch/
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arc/include/asm/pgtable.h               |  2 ++
 arch/arm/include/asm/pgtable-2level.h        |  2 ++
 arch/arm/include/asm/pgtable-3level.h        |  2 ++
 arch/mips/include/asm/pgtable-32.h           |  3 +++
 arch/powerpc/include/asm/book3s/32/pgtable.h |  2 ++
 arch/powerpc/include/asm/nohash/32/pgtable.h |  2 ++
 arch/riscv/include/asm/pgtable-32.h          |  2 ++
 include/linux/pgtable.h                      | 13 +++++++++++++
 8 files changed, 28 insertions(+)

(limited to 'include/linux')

diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index f1ed17edb085..163641726a2b 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -134,8 +134,10 @@
 
 #ifdef CONFIG_ARC_HAS_PAE40
 #define PTE_BITS_NON_RWX_IN_PD1	(0xff00000000 | PAGE_MASK | _PAGE_CACHEABLE)
+#define MAX_POSSIBLE_PHYSMEM_BITS 40
 #else
 #define PTE_BITS_NON_RWX_IN_PD1	(PAGE_MASK | _PAGE_CACHEABLE)
+#define MAX_POSSIBLE_PHYSMEM_BITS 32
 #endif
 
 /**************************************************************************
diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h
index 3502c2f746ca..baf7d0204eb5 100644
--- a/arch/arm/include/asm/pgtable-2level.h
+++ b/arch/arm/include/asm/pgtable-2level.h
@@ -75,6 +75,8 @@
 #define PTE_HWTABLE_OFF		(PTE_HWTABLE_PTRS * sizeof(pte_t))
 #define PTE_HWTABLE_SIZE	(PTRS_PER_PTE * sizeof(u32))
 
+#define MAX_POSSIBLE_PHYSMEM_BITS	32
+
 /*
  * PMD_SHIFT determines the size of the area a second-level page table can map
  * PGDIR_SHIFT determines what a third-level page table entry can map
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index fbb6693c3352..2b85d175e999 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -25,6 +25,8 @@
 #define PTE_HWTABLE_OFF		(0)
 #define PTE_HWTABLE_SIZE	(PTRS_PER_PTE * sizeof(u64))
 
+#define MAX_POSSIBLE_PHYSMEM_BITS 40
+
 /*
  * PGDIR_SHIFT determines the size a top-level page table entry can map.
  */
diff --git a/arch/mips/include/asm/pgtable-32.h b/arch/mips/include/asm/pgtable-32.h
index a950fc1ddb4d..6c0532d7b211 100644
--- a/arch/mips/include/asm/pgtable-32.h
+++ b/arch/mips/include/asm/pgtable-32.h
@@ -154,6 +154,7 @@ static inline void pmd_clear(pmd_t *pmdp)
 
 #if defined(CONFIG_XPA)
 
+#define MAX_POSSIBLE_PHYSMEM_BITS 40
 #define pte_pfn(x)		(((unsigned long)((x).pte_high >> _PFN_SHIFT)) | (unsigned long)((x).pte_low << _PAGE_PRESENT_SHIFT))
 static inline pte_t
 pfn_pte(unsigned long pfn, pgprot_t prot)
@@ -169,6 +170,7 @@ pfn_pte(unsigned long pfn, pgprot_t prot)
 
 #elif defined(CONFIG_PHYS_ADDR_T_64BIT) && defined(CONFIG_CPU_MIPS32)
 
+#define MAX_POSSIBLE_PHYSMEM_BITS 36
 #define pte_pfn(x)		((unsigned long)((x).pte_high >> 6))
 
 static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot)
@@ -183,6 +185,7 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot)
 
 #else
 
+#define MAX_POSSIBLE_PHYSMEM_BITS 32
 #ifdef CONFIG_CPU_VR41XX
 #define pte_pfn(x)		((unsigned long)((x).pte >> (PAGE_SHIFT + 2)))
 #define pfn_pte(pfn, prot)	__pte(((pfn) << (PAGE_SHIFT + 2)) | pgprot_val(prot))
diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
index 36443cda8dcf..1376be95e975 100644
--- a/arch/powerpc/include/asm/book3s/32/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
@@ -36,8 +36,10 @@ static inline bool pte_user(pte_t pte)
  */
 #ifdef CONFIG_PTE_64BIT
 #define PTE_RPN_MASK	(~((1ULL << PTE_RPN_SHIFT) - 1))
+#define MAX_POSSIBLE_PHYSMEM_BITS 36
 #else
 #define PTE_RPN_MASK	(~((1UL << PTE_RPN_SHIFT) - 1))
+#define MAX_POSSIBLE_PHYSMEM_BITS 32
 #endif
 
 /*
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index ee2243ba96cf..96522f7f0618 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -153,8 +153,10 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot);
  */
 #if defined(CONFIG_PPC32) && defined(CONFIG_PTE_64BIT)
 #define PTE_RPN_MASK	(~((1ULL << PTE_RPN_SHIFT) - 1))
+#define MAX_POSSIBLE_PHYSMEM_BITS 36
 #else
 #define PTE_RPN_MASK	(~((1UL << PTE_RPN_SHIFT) - 1))
+#define MAX_POSSIBLE_PHYSMEM_BITS 32
 #endif
 
 /*
diff --git a/arch/riscv/include/asm/pgtable-32.h b/arch/riscv/include/asm/pgtable-32.h
index b0ab66e5fdb1..5b2e79e5bfa5 100644
--- a/arch/riscv/include/asm/pgtable-32.h
+++ b/arch/riscv/include/asm/pgtable-32.h
@@ -14,4 +14,6 @@
 #define PGDIR_SIZE      (_AC(1, UL) << PGDIR_SHIFT)
 #define PGDIR_MASK      (~(PGDIR_SIZE - 1))
 
+#define MAX_POSSIBLE_PHYSMEM_BITS 34
+
 #endif /* _ASM_RISCV_PGTABLE_32_H */
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 71125a4676c4..e237004d498d 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1427,6 +1427,19 @@ typedef unsigned int pgtbl_mod_mask;
 
 #endif /* !__ASSEMBLY__ */
 
+#if !defined(MAX_POSSIBLE_PHYSMEM_BITS) && !defined(CONFIG_64BIT)
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+/*
+ * ZSMALLOC needs to know the highest PFN on 32-bit architectures
+ * with physical address space extension, but falls back to
+ * BITS_PER_LONG otherwise.
+ */
+#error Missing MAX_POSSIBLE_PHYSMEM_BITS definition
+#else
+#define MAX_POSSIBLE_PHYSMEM_BITS 32
+#endif
+#endif
+
 #ifndef has_transparent_hugepage
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define has_transparent_hugepage() 1
-- 
cgit v1.2.3


From 557acb3d2cd9c82de19f944f6cc967a347735385 Mon Sep 17 00:00:00 2001
From: Amjad Ouled-Ameur <aouledameur@baylibre.com>
Date: Fri, 13 Nov 2020 00:00:43 +0100
Subject: reset: make shared pulsed reset controls re-triggerable

The current reset framework API does not allow to release what is done by
reset_control_reset(), IOW decrement triggered_count. Add the new
reset_control_rearm() call to do so.

When reset_control_reset() has been called once, the counter
triggered_count, in the reset framework, is incremented i.e the resource
under the reset is in-use and the reset should not be done again.
reset_control_rearm() would be the way to state that the resource is
no longer used and, that from the caller's perspective, the reset can be
fired again if necessary.

Signed-off-by: Amjad Ouled-Ameur <aouledameur@baylibre.com>
Reported-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/reset/core.c  | 73 +++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/reset.h |  1 +
 2 files changed, 74 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/reset/core.c b/drivers/reset/core.c
index a2df88e90011..34e89aa0fb5e 100644
--- a/drivers/reset/core.c
+++ b/drivers/reset/core.c
@@ -208,6 +208,39 @@ static int reset_control_array_reset(struct reset_control_array *resets)
 	return 0;
 }
 
+static int reset_control_array_rearm(struct reset_control_array *resets)
+{
+	struct reset_control *rstc;
+	int i;
+
+	for (i = 0; i < resets->num_rstcs; i++) {
+		rstc = resets->rstc[i];
+
+		if (!rstc)
+			continue;
+
+		if (WARN_ON(IS_ERR(rstc)))
+			return -EINVAL;
+
+		if (rstc->shared) {
+			if (WARN_ON(atomic_read(&rstc->deassert_count) != 0))
+				return -EINVAL;
+		} else {
+			if (!rstc->acquired)
+				return -EPERM;
+		}
+	}
+
+	for (i = 0; i < resets->num_rstcs; i++) {
+		rstc = resets->rstc[i];
+
+		if (rstc && rstc->shared)
+			WARN_ON(atomic_dec_return(&rstc->triggered_count) < 0);
+	}
+
+	return 0;
+}
+
 static int reset_control_array_assert(struct reset_control_array *resets)
 {
 	int ret, i;
@@ -325,6 +358,46 @@ int reset_control_reset(struct reset_control *rstc)
 }
 EXPORT_SYMBOL_GPL(reset_control_reset);
 
+/**
+ * reset_control_rearm - allow shared reset line to be re-triggered"
+ * @rstc: reset controller
+ *
+ * On a shared reset line the actual reset pulse is only triggered once for the
+ * lifetime of the reset_control instance, except if this call is used.
+ *
+ * Calls to this function must be balanced with calls to reset_control_reset,
+ * a warning is thrown in case triggered_count ever dips below 0.
+ *
+ * Consumers must not use reset_control_(de)assert on shared reset lines when
+ * reset_control_reset or reset_control_rearm have been used.
+ *
+ * If rstc is NULL the function will just return 0.
+ */
+int reset_control_rearm(struct reset_control *rstc)
+{
+	if (!rstc)
+		return 0;
+
+	if (WARN_ON(IS_ERR(rstc)))
+		return -EINVAL;
+
+	if (reset_control_is_array(rstc))
+		return reset_control_array_rearm(rstc_to_array(rstc));
+
+	if (rstc->shared) {
+		if (WARN_ON(atomic_read(&rstc->deassert_count) != 0))
+			return -EINVAL;
+
+		WARN_ON(atomic_dec_return(&rstc->triggered_count) < 0);
+	} else {
+		if (!rstc->acquired)
+			return -EPERM;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(reset_control_rearm);
+
 /**
  * reset_control_assert - asserts the reset line
  * @rstc: reset controller
diff --git a/include/linux/reset.h b/include/linux/reset.h
index 05aa9f440f48..439fec7112a9 100644
--- a/include/linux/reset.h
+++ b/include/linux/reset.h
@@ -13,6 +13,7 @@ struct reset_control;
 #ifdef CONFIG_RESET_CONTROLLER
 
 int reset_control_reset(struct reset_control *rstc);
+int reset_control_rearm(struct reset_control *rstc);
 int reset_control_assert(struct reset_control *rstc);
 int reset_control_deassert(struct reset_control *rstc);
 int reset_control_status(struct reset_control *rstc);
-- 
cgit v1.2.3


From 872f690341948b502c93318f806d821c56772c42 Mon Sep 17 00:00:00 2001
From: Francis Laniel <laniel_francis@privacyrequired.com>
Date: Sun, 15 Nov 2020 18:08:06 +0100
Subject: treewide: rename nla_strlcpy to nla_strscpy.

Calls to nla_strlcpy are now replaced by calls to nla_strscpy which is the new
name of this function.

Signed-off-by: Francis Laniel <laniel_francis@privacyrequired.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/infiniband/core/nldev.c            | 10 +++++-----
 drivers/net/can/vxcan.c                    |  4 ++--
 drivers/net/veth.c                         |  4 ++--
 include/linux/genl_magic_struct.h          |  2 +-
 include/net/netlink.h                      |  4 ++--
 include/net/pkt_cls.h                      |  2 +-
 kernel/taskstats.c                         |  2 +-
 lib/nlattr.c                               |  6 +++---
 net/core/fib_rules.c                       |  4 ++--
 net/core/rtnetlink.c                       | 12 ++++++------
 net/decnet/dn_dev.c                        |  2 +-
 net/ieee802154/nl-mac.c                    |  2 +-
 net/ipv4/devinet.c                         |  2 +-
 net/ipv4/fib_semantics.c                   |  2 +-
 net/ipv4/metrics.c                         |  2 +-
 net/netfilter/ipset/ip_set_hash_netiface.c |  4 ++--
 net/netfilter/nf_tables_api.c              |  6 +++---
 net/netfilter/nfnetlink_acct.c             |  2 +-
 net/netfilter/nfnetlink_cthelper.c         |  4 ++--
 net/netfilter/nft_ct.c                     |  2 +-
 net/netfilter/nft_log.c                    |  2 +-
 net/netlabel/netlabel_mgmt.c               |  2 +-
 net/nfc/netlink.c                          |  2 +-
 net/sched/act_api.c                        |  2 +-
 net/sched/act_ipt.c                        |  2 +-
 net/sched/act_simple.c                     |  4 ++--
 net/sched/cls_api.c                        |  2 +-
 net/sched/sch_api.c                        |  2 +-
 net/tipc/netlink_compat.c                  |  2 +-
 29 files changed, 49 insertions(+), 49 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 12d29d54a081..08366e254b1d 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -932,7 +932,7 @@ static int nldev_set_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (tb[RDMA_NLDEV_ATTR_DEV_NAME]) {
 		char name[IB_DEVICE_NAME_MAX] = {};
 
-		nla_strlcpy(name, tb[RDMA_NLDEV_ATTR_DEV_NAME],
+		nla_strscpy(name, tb[RDMA_NLDEV_ATTR_DEV_NAME],
 			    IB_DEVICE_NAME_MAX);
 		if (strlen(name) == 0) {
 			err = -EINVAL;
@@ -1529,13 +1529,13 @@ static int nldev_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 	    !tb[RDMA_NLDEV_ATTR_LINK_TYPE] || !tb[RDMA_NLDEV_ATTR_NDEV_NAME])
 		return -EINVAL;
 
-	nla_strlcpy(ibdev_name, tb[RDMA_NLDEV_ATTR_DEV_NAME],
+	nla_strscpy(ibdev_name, tb[RDMA_NLDEV_ATTR_DEV_NAME],
 		    sizeof(ibdev_name));
 	if (strchr(ibdev_name, '%') || strlen(ibdev_name) == 0)
 		return -EINVAL;
 
-	nla_strlcpy(type, tb[RDMA_NLDEV_ATTR_LINK_TYPE], sizeof(type));
-	nla_strlcpy(ndev_name, tb[RDMA_NLDEV_ATTR_NDEV_NAME],
+	nla_strscpy(type, tb[RDMA_NLDEV_ATTR_LINK_TYPE], sizeof(type));
+	nla_strscpy(ndev_name, tb[RDMA_NLDEV_ATTR_NDEV_NAME],
 		    sizeof(ndev_name));
 
 	ndev = dev_get_by_name(sock_net(skb->sk), ndev_name);
@@ -1602,7 +1602,7 @@ static int nldev_get_chardev(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (err || !tb[RDMA_NLDEV_ATTR_CHARDEV_TYPE])
 		return -EINVAL;
 
-	nla_strlcpy(client_name, tb[RDMA_NLDEV_ATTR_CHARDEV_TYPE],
+	nla_strscpy(client_name, tb[RDMA_NLDEV_ATTR_CHARDEV_TYPE],
 		    sizeof(client_name));
 
 	if (tb[RDMA_NLDEV_ATTR_DEV_INDEX]) {
diff --git a/drivers/net/can/vxcan.c b/drivers/net/can/vxcan.c
index d6ba9426be4d..fa47bab510bb 100644
--- a/drivers/net/can/vxcan.c
+++ b/drivers/net/can/vxcan.c
@@ -186,7 +186,7 @@ static int vxcan_newlink(struct net *net, struct net_device *dev,
 	}
 
 	if (ifmp && tbp[IFLA_IFNAME]) {
-		nla_strlcpy(ifname, tbp[IFLA_IFNAME], IFNAMSIZ);
+		nla_strscpy(ifname, tbp[IFLA_IFNAME], IFNAMSIZ);
 		name_assign_type = NET_NAME_USER;
 	} else {
 		snprintf(ifname, IFNAMSIZ, DRV_NAME "%%d");
@@ -223,7 +223,7 @@ static int vxcan_newlink(struct net *net, struct net_device *dev,
 
 	/* register first device */
 	if (tb[IFLA_IFNAME])
-		nla_strlcpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ);
+		nla_strscpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ);
 	else
 		snprintf(dev->name, IFNAMSIZ, DRV_NAME "%%d");
 
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 8c737668008a..359d3ab33c4d 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -1329,7 +1329,7 @@ static int veth_newlink(struct net *src_net, struct net_device *dev,
 	}
 
 	if (ifmp && tbp[IFLA_IFNAME]) {
-		nla_strlcpy(ifname, tbp[IFLA_IFNAME], IFNAMSIZ);
+		nla_strscpy(ifname, tbp[IFLA_IFNAME], IFNAMSIZ);
 		name_assign_type = NET_NAME_USER;
 	} else {
 		snprintf(ifname, IFNAMSIZ, DRV_NAME "%%d");
@@ -1379,7 +1379,7 @@ static int veth_newlink(struct net *src_net, struct net_device *dev,
 		eth_hw_addr_random(dev);
 
 	if (tb[IFLA_IFNAME])
-		nla_strlcpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ);
+		nla_strscpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ);
 	else
 		snprintf(dev->name, IFNAMSIZ, DRV_NAME "%%d");
 
diff --git a/include/linux/genl_magic_struct.h b/include/linux/genl_magic_struct.h
index eeae59d3ceb7..35d21fddaf2d 100644
--- a/include/linux/genl_magic_struct.h
+++ b/include/linux/genl_magic_struct.h
@@ -89,7 +89,7 @@ static inline int nla_put_u64_0pad(struct sk_buff *skb, int attrtype, u64 value)
 			nla_get_u64, nla_put_u64_0pad, false)
 #define __str_field(attr_nr, attr_flag, name, maxlen) \
 	__array(attr_nr, attr_flag, name, NLA_NUL_STRING, char, maxlen, \
-			nla_strlcpy, nla_put, false)
+			nla_strscpy, nla_put, false)
 #define __bin_field(attr_nr, attr_flag, name, maxlen) \
 	__array(attr_nr, attr_flag, name, NLA_BINARY, char, maxlen, \
 			nla_memcpy, nla_put, false)
diff --git a/include/net/netlink.h b/include/net/netlink.h
index 446ca182e13d..1ceec518ab49 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -142,7 +142,7 @@
  * Attribute Misc:
  *   nla_memcpy(dest, nla, count)	copy attribute into memory
  *   nla_memcmp(nla, data, size)	compare attribute with memory area
- *   nla_strlcpy(dst, nla, size)	copy attribute to a sized string
+ *   nla_strscpy(dst, nla, size)	copy attribute to a sized string
  *   nla_strcmp(nla, str)		compare attribute with string
  *
  * Attribute Parsing:
@@ -506,7 +506,7 @@ int __nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head,
 		struct netlink_ext_ack *extack);
 int nla_policy_len(const struct nla_policy *, int);
 struct nlattr *nla_find(const struct nlattr *head, int len, int attrtype);
-ssize_t nla_strlcpy(char *dst, const struct nlattr *nla, size_t dstsize);
+ssize_t nla_strscpy(char *dst, const struct nlattr *nla, size_t dstsize);
 char *nla_strdup(const struct nlattr *nla, gfp_t flags);
 int nla_memcpy(void *dest, const struct nlattr *src, int count);
 int nla_memcmp(const struct nlattr *nla, const void *data, size_t size);
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index db9a828f4f4f..133f9ad4d4f9 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -512,7 +512,7 @@ tcf_change_indev(struct net *net, struct nlattr *indev_tlv,
 	char indev[IFNAMSIZ];
 	struct net_device *dev;
 
-	if (nla_strlcpy(indev, indev_tlv, IFNAMSIZ) < 0) {
+	if (nla_strscpy(indev, indev_tlv, IFNAMSIZ) < 0) {
 		NL_SET_ERR_MSG_ATTR(extack, indev_tlv,
 				    "Interface name too long");
 		return -EINVAL;
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index a2802b6ff4bb..2b4898b4752e 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -346,7 +346,7 @@ static int parse(struct nlattr *na, struct cpumask *mask)
 	data = kmalloc(len, GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
-	nla_strlcpy(data, na, len);
+	nla_strscpy(data, na, len);
 	ret = cpulist_parse(data, mask);
 	kfree(data);
 	return ret;
diff --git a/lib/nlattr.c b/lib/nlattr.c
index 447182543c03..09aa181569e0 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -709,7 +709,7 @@ struct nlattr *nla_find(const struct nlattr *head, int len, int attrtype)
 EXPORT_SYMBOL(nla_find);
 
 /**
- * nla_strlcpy - Copy string attribute payload into a sized buffer
+ * nla_strscpy - Copy string attribute payload into a sized buffer
  * @dst: Where to copy the string to.
  * @nla: Attribute to copy the string from.
  * @dstsize: Size of destination buffer.
@@ -722,7 +722,7 @@ EXPORT_SYMBOL(nla_find);
  * * -E2BIG - If @dstsize is 0 or greater than U16_MAX or @nla length greater
  *            than @dstsize.
  */
-ssize_t nla_strlcpy(char *dst, const struct nlattr *nla, size_t dstsize)
+ssize_t nla_strscpy(char *dst, const struct nlattr *nla, size_t dstsize)
 {
 	size_t srclen = nla_len(nla);
 	char *src = nla_data(nla);
@@ -749,7 +749,7 @@ ssize_t nla_strlcpy(char *dst, const struct nlattr *nla, size_t dstsize)
 
 	return ret;
 }
-EXPORT_SYMBOL(nla_strlcpy);
+EXPORT_SYMBOL(nla_strscpy);
 
 /**
  * nla_strdup - Copy string attribute payload into a newly allocated buffer
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 7bcfb16854cb..cd80ffed6d26 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -563,7 +563,7 @@ static int fib_nl2rule(struct sk_buff *skb, struct nlmsghdr *nlh,
 		struct net_device *dev;
 
 		nlrule->iifindex = -1;
-		nla_strlcpy(nlrule->iifname, tb[FRA_IIFNAME], IFNAMSIZ);
+		nla_strscpy(nlrule->iifname, tb[FRA_IIFNAME], IFNAMSIZ);
 		dev = __dev_get_by_name(net, nlrule->iifname);
 		if (dev)
 			nlrule->iifindex = dev->ifindex;
@@ -573,7 +573,7 @@ static int fib_nl2rule(struct sk_buff *skb, struct nlmsghdr *nlh,
 		struct net_device *dev;
 
 		nlrule->oifindex = -1;
-		nla_strlcpy(nlrule->oifname, tb[FRA_OIFNAME], IFNAMSIZ);
+		nla_strscpy(nlrule->oifname, tb[FRA_OIFNAME], IFNAMSIZ);
 		dev = __dev_get_by_name(net, nlrule->oifname);
 		if (dev)
 			nlrule->oifindex = dev->ifindex;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 7d7223691783..60917ff4a00b 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1939,7 +1939,7 @@ static const struct rtnl_link_ops *linkinfo_to_kind_ops(const struct nlattr *nla
 	if (linfo[IFLA_INFO_KIND]) {
 		char kind[MODULE_NAME_LEN];
 
-		nla_strlcpy(kind, linfo[IFLA_INFO_KIND], sizeof(kind));
+		nla_strscpy(kind, linfo[IFLA_INFO_KIND], sizeof(kind));
 		ops = rtnl_link_ops_get(kind);
 	}
 
@@ -2953,9 +2953,9 @@ static struct net_device *rtnl_dev_get(struct net *net,
 	if (!ifname) {
 		ifname = buffer;
 		if (ifname_attr)
-			nla_strlcpy(ifname, ifname_attr, IFNAMSIZ);
+			nla_strscpy(ifname, ifname_attr, IFNAMSIZ);
 		else if (altifname_attr)
-			nla_strlcpy(ifname, altifname_attr, ALTIFNAMSIZ);
+			nla_strscpy(ifname, altifname_attr, ALTIFNAMSIZ);
 		else
 			return NULL;
 	}
@@ -2983,7 +2983,7 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 		goto errout;
 
 	if (tb[IFLA_IFNAME])
-		nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
+		nla_strscpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
 	else
 		ifname[0] = '\0';
 
@@ -3264,7 +3264,7 @@ replay:
 		return err;
 
 	if (tb[IFLA_IFNAME])
-		nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
+		nla_strscpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
 	else
 		ifname[0] = '\0';
 
@@ -3296,7 +3296,7 @@ replay:
 		memset(linkinfo, 0, sizeof(linkinfo));
 
 	if (linkinfo[IFLA_INFO_KIND]) {
-		nla_strlcpy(kind, linkinfo[IFLA_INFO_KIND], sizeof(kind));
+		nla_strscpy(kind, linkinfo[IFLA_INFO_KIND], sizeof(kind));
 		ops = rtnl_link_ops_get(kind);
 	} else {
 		kind[0] = '\0';
diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c
index 15d42353f1a3..d1c50a48614b 100644
--- a/net/decnet/dn_dev.c
+++ b/net/decnet/dn_dev.c
@@ -658,7 +658,7 @@ static int dn_nl_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
 	ifa->ifa_dev = dn_db;
 
 	if (tb[IFA_LABEL])
-		nla_strlcpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ);
+		nla_strscpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ);
 	else
 		memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
 
diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c
index 6d091e419d3e..9c640d670ffe 100644
--- a/net/ieee802154/nl-mac.c
+++ b/net/ieee802154/nl-mac.c
@@ -149,7 +149,7 @@ static struct net_device *ieee802154_nl_get_dev(struct genl_info *info)
 	if (info->attrs[IEEE802154_ATTR_DEV_NAME]) {
 		char name[IFNAMSIZ + 1];
 
-		nla_strlcpy(name, info->attrs[IEEE802154_ATTR_DEV_NAME],
+		nla_strscpy(name, info->attrs[IEEE802154_ATTR_DEV_NAME],
 			    sizeof(name));
 		dev = dev_get_by_name(&init_net, name);
 	} else if (info->attrs[IEEE802154_ATTR_DEV_INDEX]) {
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 43e04382c593..75f67994fc85 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -880,7 +880,7 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh,
 		ifa->ifa_broadcast = nla_get_in_addr(tb[IFA_BROADCAST]);
 
 	if (tb[IFA_LABEL])
-		nla_strlcpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ);
+		nla_strscpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ);
 	else
 		memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
 
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 7612ff6111a7..b5400cec4f69 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -973,7 +973,7 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi)
 			char tmp[TCP_CA_NAME_MAX];
 			bool ecn_ca = false;
 
-			nla_strlcpy(tmp, nla, sizeof(tmp));
+			nla_strscpy(tmp, nla, sizeof(tmp));
 			val = tcp_ca_get_key_by_name(fi->fib_net, tmp, &ecn_ca);
 		} else {
 			if (nla_len(nla) != sizeof(u32))
diff --git a/net/ipv4/metrics.c b/net/ipv4/metrics.c
index 3205d5f7c8c9..25ea6ac44db9 100644
--- a/net/ipv4/metrics.c
+++ b/net/ipv4/metrics.c
@@ -31,7 +31,7 @@ static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx,
 		if (type == RTAX_CC_ALGO) {
 			char tmp[TCP_CA_NAME_MAX];
 
-			nla_strlcpy(tmp, nla, sizeof(tmp));
+			nla_strscpy(tmp, nla, sizeof(tmp));
 			val = tcp_ca_get_key_by_name(net, tmp, &ecn_ca);
 			if (val == TCP_CA_UNSPEC) {
 				NL_SET_ERR_MSG(extack, "Unknown tcp congestion algorithm");
diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c
index 3d74169b794c..ddd51c2e1cb3 100644
--- a/net/netfilter/ipset/ip_set_hash_netiface.c
+++ b/net/netfilter/ipset/ip_set_hash_netiface.c
@@ -226,7 +226,7 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[],
 		if (e.cidr > HOST_MASK)
 			return -IPSET_ERR_INVALID_CIDR;
 	}
-	nla_strlcpy(e.iface, tb[IPSET_ATTR_IFACE], IFNAMSIZ);
+	nla_strscpy(e.iface, tb[IPSET_ATTR_IFACE], IFNAMSIZ);
 
 	if (tb[IPSET_ATTR_CADT_FLAGS]) {
 		u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
@@ -443,7 +443,7 @@ hash_netiface6_uadt(struct ip_set *set, struct nlattr *tb[],
 
 	ip6_netmask(&e.ip, e.cidr);
 
-	nla_strlcpy(e.iface, tb[IPSET_ATTR_IFACE], IFNAMSIZ);
+	nla_strscpy(e.iface, tb[IPSET_ATTR_IFACE], IFNAMSIZ);
 
 	if (tb[IPSET_ATTR_CADT_FLAGS]) {
 		u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index bd0e12bf5770..65aa98fc5eb6 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1282,7 +1282,7 @@ static struct nft_chain *nft_chain_lookup(struct net *net,
 	if (nla == NULL)
 		return ERR_PTR(-EINVAL);
 
-	nla_strlcpy(search, nla, sizeof(search));
+	nla_strscpy(search, nla, sizeof(search));
 
 	WARN_ON(!rcu_read_lock_held() &&
 		!lockdep_commit_lock_is_held(net));
@@ -1722,7 +1722,7 @@ static struct nft_hook *nft_netdev_hook_alloc(struct net *net,
 		goto err_hook_alloc;
 	}
 
-	nla_strlcpy(ifname, attr, IFNAMSIZ);
+	nla_strscpy(ifname, attr, IFNAMSIZ);
 	dev = __dev_get_by_name(net, ifname);
 	if (!dev) {
 		err = -ENOENT;
@@ -5735,7 +5735,7 @@ struct nft_object *nft_obj_lookup(const struct net *net,
 	struct rhlist_head *tmp, *list;
 	struct nft_object *obj;
 
-	nla_strlcpy(search, nla, sizeof(search));
+	nla_strscpy(search, nla, sizeof(search));
 	k.name = search;
 
 	WARN_ON_ONCE(!rcu_read_lock_held() &&
diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c
index 5bfec829c12f..5e511df8d709 100644
--- a/net/netfilter/nfnetlink_acct.c
+++ b/net/netfilter/nfnetlink_acct.c
@@ -112,7 +112,7 @@ static int nfnl_acct_new(struct net *net, struct sock *nfnl,
 		nfacct->flags = flags;
 	}
 
-	nla_strlcpy(nfacct->name, tb[NFACCT_NAME], NFACCT_NAME_MAX);
+	nla_strscpy(nfacct->name, tb[NFACCT_NAME], NFACCT_NAME_MAX);
 
 	if (tb[NFACCT_BYTES]) {
 		atomic64_set(&nfacct->bytes,
diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c
index 5b0d0a77379c..0f94fce1d3ed 100644
--- a/net/netfilter/nfnetlink_cthelper.c
+++ b/net/netfilter/nfnetlink_cthelper.c
@@ -146,7 +146,7 @@ nfnl_cthelper_expect_policy(struct nf_conntrack_expect_policy *expect_policy,
 	    !tb[NFCTH_POLICY_EXPECT_TIMEOUT])
 		return -EINVAL;
 
-	nla_strlcpy(expect_policy->name,
+	nla_strscpy(expect_policy->name,
 		    tb[NFCTH_POLICY_NAME], NF_CT_HELPER_NAME_LEN);
 	expect_policy->max_expected =
 		ntohl(nla_get_be32(tb[NFCTH_POLICY_EXPECT_MAX]));
@@ -233,7 +233,7 @@ nfnl_cthelper_create(const struct nlattr * const tb[],
 	if (ret < 0)
 		goto err1;
 
-	nla_strlcpy(helper->name,
+	nla_strscpy(helper->name,
 		    tb[NFCTH_NAME], NF_CT_HELPER_NAME_LEN);
 	size = ntohl(nla_get_be32(tb[NFCTH_PRIV_DATA_LEN]));
 	if (size > sizeof_field(struct nf_conn_help, data)) {
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 322bd674963e..a8c4d442231c 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -990,7 +990,7 @@ static int nft_ct_helper_obj_init(const struct nft_ctx *ctx,
 	if (!priv->l4proto)
 		return -ENOENT;
 
-	nla_strlcpy(name, tb[NFTA_CT_HELPER_NAME], sizeof(name));
+	nla_strscpy(name, tb[NFTA_CT_HELPER_NAME], sizeof(name));
 
 	if (tb[NFTA_CT_HELPER_L3PROTO])
 		family = ntohs(nla_get_be16(tb[NFTA_CT_HELPER_L3PROTO]));
diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c
index 57899454a530..a06a46b039c5 100644
--- a/net/netfilter/nft_log.c
+++ b/net/netfilter/nft_log.c
@@ -152,7 +152,7 @@ static int nft_log_init(const struct nft_ctx *ctx,
 		priv->prefix = kmalloc(nla_len(nla) + 1, GFP_KERNEL);
 		if (priv->prefix == NULL)
 			return -ENOMEM;
-		nla_strlcpy(priv->prefix, nla, nla_len(nla) + 1);
+		nla_strscpy(priv->prefix, nla, nla_len(nla) + 1);
 	} else {
 		priv->prefix = (char *)nft_log_null_prefix;
 	}
diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c
index eb1d66d20afb..df1b41ed73fd 100644
--- a/net/netlabel/netlabel_mgmt.c
+++ b/net/netlabel/netlabel_mgmt.c
@@ -95,7 +95,7 @@ static int netlbl_mgmt_add_common(struct genl_info *info,
 			ret_val = -ENOMEM;
 			goto add_free_entry;
 		}
-		nla_strlcpy(entry->domain,
+		nla_strscpy(entry->domain,
 			    info->attrs[NLBL_MGMT_A_DOMAIN], tmp_size);
 	}
 
diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index 8709f3d4e7c4..573b38ad2f8e 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -1226,7 +1226,7 @@ static int nfc_genl_fw_download(struct sk_buff *skb, struct genl_info *info)
 	if (!dev)
 		return -ENODEV;
 
-	nla_strlcpy(firmware_name, info->attrs[NFC_ATTR_FIRMWARE_NAME],
+	nla_strscpy(firmware_name, info->attrs[NFC_ATTR_FIRMWARE_NAME],
 		    sizeof(firmware_name));
 
 	rc = nfc_fw_download(dev, firmware_name);
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index fe540a89b16c..fc23f46a315c 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -939,7 +939,7 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 			NL_SET_ERR_MSG(extack, "TC action kind must be specified");
 			goto err_out;
 		}
-		if (nla_strlcpy(act_name, kind, IFNAMSIZ) < 0) {
+		if (nla_strscpy(act_name, kind, IFNAMSIZ) < 0) {
 			NL_SET_ERR_MSG(extack, "TC action name too long");
 			goto err_out;
 		}
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 8dc3bec0d325..ac7297f42355 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -166,7 +166,7 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla,
 	if (unlikely(!tname))
 		goto err1;
 	if (tb[TCA_IPT_TABLE] == NULL ||
-	    nla_strlcpy(tname, tb[TCA_IPT_TABLE], IFNAMSIZ) >= IFNAMSIZ)
+	    nla_strscpy(tname, tb[TCA_IPT_TABLE], IFNAMSIZ) >= IFNAMSIZ)
 		strcpy(tname, "mangle");
 
 	t = kmemdup(td, td->u.target_size, GFP_KERNEL);
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index a4f3d0f0daa9..726cc956d06f 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -52,7 +52,7 @@ static int alloc_defdata(struct tcf_defact *d, const struct nlattr *defdata)
 	d->tcfd_defdata = kzalloc(SIMP_MAX_DATA, GFP_KERNEL);
 	if (unlikely(!d->tcfd_defdata))
 		return -ENOMEM;
-	nla_strlcpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA);
+	nla_strscpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA);
 	return 0;
 }
 
@@ -71,7 +71,7 @@ static int reset_policy(struct tc_action *a, const struct nlattr *defdata,
 	spin_lock_bh(&d->tcf_lock);
 	goto_ch = tcf_action_set_ctrlact(a, p->action, goto_ch);
 	memset(d->tcfd_defdata, 0, SIMP_MAX_DATA);
-	nla_strlcpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA);
+	nla_strscpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA);
 	spin_unlock_bh(&d->tcf_lock);
 	if (goto_ch)
 		tcf_chain_put_by_act(goto_ch);
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index c2e9661e20d3..ff3e943febaa 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -223,7 +223,7 @@ static inline u32 tcf_auto_prio(struct tcf_proto *tp)
 static bool tcf_proto_check_kind(struct nlattr *kind, char *name)
 {
 	if (kind)
-		return nla_strlcpy(name, kind, IFNAMSIZ) < 0;
+		return nla_strscpy(name, kind, IFNAMSIZ) < 0;
 	memset(name, 0, IFNAMSIZ);
 	return false;
 }
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 05449286d889..1a2d2471b078 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1170,7 +1170,7 @@ static struct Qdisc *qdisc_create(struct net_device *dev,
 #ifdef CONFIG_MODULES
 	if (ops == NULL && kind != NULL) {
 		char name[IFNAMSIZ];
-		if (nla_strlcpy(name, kind, IFNAMSIZ) >= 0) {
+		if (nla_strscpy(name, kind, IFNAMSIZ) >= 0) {
 			/* We dropped the RTNL semaphore in order to
 			 * perform the module load.  So, even if we
 			 * succeeded in loading the module we have to
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 5c6206c9d6a8..82f154989418 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -696,7 +696,7 @@ static int tipc_nl_compat_link_dump(struct tipc_nl_compat_msg *msg,
 
 	link_info.dest = nla_get_flag(link[TIPC_NLA_LINK_DEST]);
 	link_info.up = htonl(nla_get_flag(link[TIPC_NLA_LINK_UP]));
-	nla_strlcpy(link_info.str, link[TIPC_NLA_LINK_NAME],
+	nla_strscpy(link_info.str, link[TIPC_NLA_LINK_NAME],
 		    TIPC_MAX_LINK_NAME);
 
 	return tipc_add_tlv(msg->rep, TIPC_TLV_LINK_INFO,
-- 
cgit v1.2.3


From dd8088d5a8969dc2b42f71d7bc01c25c61a78066 Mon Sep 17 00:00:00 2001
From: Zhang Qilong <zhangqilong3@huawei.com>
Date: Tue, 10 Nov 2020 17:29:32 +0800
Subject: PM: runtime: Add pm_runtime_resume_and_get to deal with usage counter

In many case, we need to check return value of pm_runtime_get_sync, but
it brings a trouble to the usage counter processing. Many callers forget
to decrease the usage counter when it failed, which could resulted in
reference leak. It has been discussed a lot[0][1]. So we add a function
to deal with the usage counter for better coding.

[0]https://lkml.org/lkml/2020/6/14/88
[1]https://patchwork.ozlabs.org/project/linux-tegra/list/?series=178139
Signed-off-by: Zhang Qilong <zhangqilong3@huawei.com>
Acked-by: Rafael J. Wysocki  <rafael.j.wysocki@intel.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/pm_runtime.h | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index 4b708f4e8eed..b492ae00cc90 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -386,6 +386,27 @@ static inline int pm_runtime_get_sync(struct device *dev)
 	return __pm_runtime_resume(dev, RPM_GET_PUT);
 }
 
+/**
+ * pm_runtime_resume_and_get - Bump up usage counter of a device and resume it.
+ * @dev: Target device.
+ *
+ * Resume @dev synchronously and if that is successful, increment its runtime
+ * PM usage counter. Return 0 if the runtime PM usage counter of @dev has been
+ * incremented or a negative error code otherwise.
+ */
+static inline int pm_runtime_resume_and_get(struct device *dev)
+{
+	int ret;
+
+	ret = __pm_runtime_resume(dev, RPM_GET_PUT);
+	if (ret < 0) {
+		pm_runtime_put_noidle(dev);
+		return ret;
+	}
+
+	return 0;
+}
+
 /**
  * pm_runtime_put - Drop device usage counter and queue up "idle check" if 0.
  * @dev: Target device.
-- 
cgit v1.2.3


From 3136b93c3fb2b7c19e853e049203ff8f2b9dd2cd Mon Sep 17 00:00:00 2001
From: Gabriel Krisman Bertazi <krisman@collabora.com>
Date: Mon, 16 Nov 2020 12:41:58 -0500
Subject: entry: Expose helpers to migrate TIF to SYSCALL_WORK flags

With the goal to split the syscall work related flags into a separate
field that is architecture independent, expose transitional helpers that
resolve to either the TIF flags or to the corresponding SYSCALL_WORK
flags.  This will allow architectures to migrate only when they port to
the generic syscall entry code.

Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Andy Lutomirski <luto@kernel.org>
Link: https://lore.kernel.org/r/20201116174206.2639648-3-krisman@collabora.com
---
 include/linux/thread_info.h | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index e93e249a4e9b..0e9fb15d6b42 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -97,6 +97,38 @@ static inline int test_ti_thread_flag(struct thread_info *ti, int flag)
 #define test_thread_flag(flag) \
 	test_ti_thread_flag(current_thread_info(), flag)
 
+#ifdef CONFIG_GENERIC_ENTRY
+#define set_syscall_work(fl) \
+	set_bit(SYSCALL_WORK_BIT_##fl, &current_thread_info()->syscall_work)
+#define test_syscall_work(fl) \
+	test_bit(SYSCALL_WORK_BIT_##fl, &current_thread_info()->syscall_work)
+#define clear_syscall_work(fl) \
+	clear_bit(SYSCALL_WORK_BIT_##fl, &current_thread_info()->syscall_work)
+
+#define set_task_syscall_work(t, fl) \
+	set_bit(SYSCALL_WORK_BIT_##fl, &task_thread_info(t)->syscall_work)
+#define test_task_syscall_work(t, fl) \
+	test_bit(SYSCALL_WORK_BIT_##fl, &task_thread_info(t)->syscall_work)
+#define clear_task_syscall_work(t, fl) \
+	clear_bit(SYSCALL_WORK_BIT_##fl, &task_thread_info(t)->syscall_work)
+
+#else /* CONFIG_GENERIC_ENTRY */
+
+#define set_syscall_work(fl)						\
+	set_ti_thread_flag(current_thread_info(), SYSCALL_WORK_##fl)
+#define test_syscall_work(fl) \
+	test_ti_thread_flag(current_thread_info(), SYSCALL_WORK_##fl)
+#define clear_syscall_work(fl) \
+	clear_ti_thread_flag(current_thread_info(), SYSCALL_WORK_##fl)
+
+#define set_task_syscall_work(t, fl) \
+	set_ti_thread_flag(task_thread_info(t), TIF_##fl)
+#define test_task_syscall_work(t, fl) \
+	test_ti_thread_flag(task_thread_info(t), TIF_##fl)
+#define clear_task_syscall_work(t, fl) \
+	clear_ti_thread_flag(task_thread_info(t), TIF_##fl)
+#endif /* !CONFIG_GENERIC_ENTRY */
+
 #define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED)
 
 #ifndef CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES
-- 
cgit v1.2.3


From b86678cf0f1d76062aa964c5f0c6c89fe5a6dcfd Mon Sep 17 00:00:00 2001
From: Gabriel Krisman Bertazi <krisman@collabora.com>
Date: Mon, 16 Nov 2020 12:41:59 -0500
Subject: entry: Wire up syscall_work in common entry code

Prepare the common entry code to use the SYSCALL_WORK flags. They will
be defined in subsequent patches for each type of syscall
work. SYSCALL_WORK_ENTRY/EXIT are defined for the transition, as they
will replace the TIF_ equivalent defines.

Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Andy Lutomirski <luto@kernel.org>
Link: https://lore.kernel.org/r/20201116174206.2639648-4-krisman@collabora.com
---
 include/linux/entry-common.h |  3 +++
 kernel/entry/common.c        | 15 +++++++++------
 2 files changed, 12 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index aab549026ab8..3fe8f868f15e 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -64,6 +64,9 @@
 	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT |			\
 	 _TIF_SYSCALL_TRACEPOINT | ARCH_SYSCALL_EXIT_WORK)
 
+#define SYSCALL_WORK_ENTER	(0)
+#define SYSCALL_WORK_EXIT	(0)
+
 /*
  * TIF flags handled in exit_to_user_mode_loop()
  */
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index fa17baadf63e..e7a11e38daba 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -42,7 +42,7 @@ static inline void syscall_enter_audit(struct pt_regs *regs, long syscall)
 }
 
 static long syscall_trace_enter(struct pt_regs *regs, long syscall,
-				unsigned long ti_work)
+				unsigned long ti_work, unsigned long work)
 {
 	long ret = 0;
 
@@ -74,11 +74,12 @@ static long syscall_trace_enter(struct pt_regs *regs, long syscall,
 static __always_inline long
 __syscall_enter_from_user_work(struct pt_regs *regs, long syscall)
 {
+	unsigned long work = READ_ONCE(current_thread_info()->syscall_work);
 	unsigned long ti_work;
 
 	ti_work = READ_ONCE(current_thread_info()->flags);
-	if (ti_work & SYSCALL_ENTER_WORK)
-		syscall = syscall_trace_enter(regs, syscall, ti_work);
+	if (work & SYSCALL_WORK_ENTER || ti_work & SYSCALL_ENTER_WORK)
+		syscall = syscall_trace_enter(regs, syscall, ti_work, work);
 
 	return syscall;
 }
@@ -225,7 +226,8 @@ static inline bool report_single_step(unsigned long ti_work)
 }
 #endif
 
-static void syscall_exit_work(struct pt_regs *regs, unsigned long ti_work)
+static void syscall_exit_work(struct pt_regs *regs, unsigned long ti_work,
+			      unsigned long work)
 {
 	bool step;
 
@@ -245,6 +247,7 @@ static void syscall_exit_work(struct pt_regs *regs, unsigned long ti_work)
  */
 static void syscall_exit_to_user_mode_prepare(struct pt_regs *regs)
 {
+	unsigned long work = READ_ONCE(current_thread_info()->syscall_work);
 	u32 cached_flags = READ_ONCE(current_thread_info()->flags);
 	unsigned long nr = syscall_get_nr(current, regs);
 
@@ -262,8 +265,8 @@ static void syscall_exit_to_user_mode_prepare(struct pt_regs *regs)
 	 * enabled, we want to run them exactly once per syscall exit with
 	 * interrupts enabled.
 	 */
-	if (unlikely(cached_flags & SYSCALL_EXIT_WORK))
-		syscall_exit_work(regs, cached_flags);
+	if (unlikely(work & SYSCALL_WORK_EXIT || cached_flags & SYSCALL_EXIT_WORK))
+		syscall_exit_work(regs, cached_flags, work);
 }
 
 __visible noinstr void syscall_exit_to_user_mode(struct pt_regs *regs)
-- 
cgit v1.2.3


From 23d67a54857a768acdb0804cdd6037c324a50ecd Mon Sep 17 00:00:00 2001
From: Gabriel Krisman Bertazi <krisman@collabora.com>
Date: Mon, 16 Nov 2020 12:42:00 -0500
Subject: seccomp: Migrate to use SYSCALL_WORK flag

On architectures using the generic syscall entry code the architecture
independent syscall work is moved to flags in thread_info::syscall_work.
This removes architecture dependencies and frees up TIF bits.

Define SYSCALL_WORK_SECCOMP, use it in the generic entry code and convert
the code which uses the TIF specific helper functions to use the new
*_syscall_work() helpers which either resolve to the new mode for users of
the generic entry code or to the TIF based functions for the other
architectures.

Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Andy Lutomirski <luto@kernel.org>
Link: https://lore.kernel.org/r/20201116174206.2639648-5-krisman@collabora.com
---
 include/asm-generic/syscall.h | 2 +-
 include/linux/entry-common.h  | 8 ++------
 include/linux/seccomp.h       | 2 +-
 include/linux/thread_info.h   | 6 ++++++
 kernel/entry/common.c         | 2 +-
 kernel/fork.c                 | 2 +-
 kernel/seccomp.c              | 6 +++---
 7 files changed, 15 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/include/asm-generic/syscall.h b/include/asm-generic/syscall.h
index f3135e734387..524d8e68ff5e 100644
--- a/include/asm-generic/syscall.h
+++ b/include/asm-generic/syscall.h
@@ -135,7 +135,7 @@ void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
  * Returns the AUDIT_ARCH_* based on the system call convention in use.
  *
  * It's only valid to call this when @task is stopped on entry to a system
- * call, due to %TIF_SYSCALL_TRACE, %TIF_SYSCALL_AUDIT, or %TIF_SECCOMP.
+ * call, due to %TIF_SYSCALL_TRACE, %TIF_SYSCALL_AUDIT, or %SYSCALL_WORK_SECCOMP.
  *
  * Architectures which permit CONFIG_HAVE_ARCH_SECCOMP_FILTER must
  * provide an implementation of this.
diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index 3fe8f868f15e..fa3cdb102dbf 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -21,10 +21,6 @@
 # define _TIF_SYSCALL_TRACEPOINT	(0)
 #endif
 
-#ifndef _TIF_SECCOMP
-# define _TIF_SECCOMP			(0)
-#endif
-
 #ifndef _TIF_SYSCALL_AUDIT
 # define _TIF_SYSCALL_AUDIT		(0)
 #endif
@@ -49,7 +45,7 @@
 #endif
 
 #define SYSCALL_ENTER_WORK						\
-	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP |	\
+	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT  |			\
 	 _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_EMU |			\
 	 ARCH_SYSCALL_ENTER_WORK)
 
@@ -64,7 +60,7 @@
 	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT |			\
 	 _TIF_SYSCALL_TRACEPOINT | ARCH_SYSCALL_EXIT_WORK)
 
-#define SYSCALL_WORK_ENTER	(0)
+#define SYSCALL_WORK_ENTER	(SYSCALL_WORK_SECCOMP)
 #define SYSCALL_WORK_EXIT	(0)
 
 /*
diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index 02aef2844c38..47763f3999f7 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -42,7 +42,7 @@ struct seccomp {
 extern int __secure_computing(const struct seccomp_data *sd);
 static inline int secure_computing(void)
 {
-	if (unlikely(test_thread_flag(TIF_SECCOMP)))
+	if (unlikely(test_syscall_work(SECCOMP)))
 		return  __secure_computing(NULL);
 	return 0;
 }
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index 0e9fb15d6b42..a308ba4ef07b 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -35,6 +35,12 @@ enum {
 	GOOD_STACK,
 };
 
+enum syscall_work_bit {
+	SYSCALL_WORK_BIT_SECCOMP,
+};
+
+#define SYSCALL_WORK_SECCOMP		BIT(SYSCALL_WORK_BIT_SECCOMP)
+
 #include <asm/thread_info.h>
 
 #ifdef __KERNEL__
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index e7a11e38daba..5747a6eb2c48 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -54,7 +54,7 @@ static long syscall_trace_enter(struct pt_regs *regs, long syscall,
 	}
 
 	/* Do seccomp after ptrace, to catch any tracer changes. */
-	if (ti_work & _TIF_SECCOMP) {
+	if (work & SYSCALL_WORK_SECCOMP) {
 		ret = __secure_computing(NULL);
 		if (ret == -1L)
 			return ret;
diff --git a/kernel/fork.c b/kernel/fork.c
index 32083db7a2a2..bc5b1090f415 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1625,7 +1625,7 @@ static void copy_seccomp(struct task_struct *p)
 	 * to manually enable the seccomp thread flag here.
 	 */
 	if (p->seccomp.mode != SECCOMP_MODE_DISABLED)
-		set_tsk_thread_flag(p, TIF_SECCOMP);
+		set_task_syscall_work(p, SECCOMP);
 #endif
 }
 
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 8ad7a293255a..f67e92d11ad7 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -356,14 +356,14 @@ static inline void seccomp_assign_mode(struct task_struct *task,
 
 	task->seccomp.mode = seccomp_mode;
 	/*
-	 * Make sure TIF_SECCOMP cannot be set before the mode (and
+	 * Make sure SYSCALL_WORK_SECCOMP cannot be set before the mode (and
 	 * filter) is set.
 	 */
 	smp_mb__before_atomic();
 	/* Assume default seccomp processes want spec flaw mitigation. */
 	if ((flags & SECCOMP_FILTER_FLAG_SPEC_ALLOW) == 0)
 		arch_seccomp_spec_mitigate(task);
-	set_tsk_thread_flag(task, TIF_SECCOMP);
+	set_task_syscall_work(task, SECCOMP);
 }
 
 #ifdef CONFIG_SECCOMP_FILTER
@@ -929,7 +929,7 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd,
 
 	/*
 	 * Make sure that any changes to mode from another thread have
-	 * been seen after TIF_SECCOMP was seen.
+	 * been seen after SYSCALL_WORK_SECCOMP was seen.
 	 */
 	rmb();
 
-- 
cgit v1.2.3


From 524666cb5de7c38a1925e7401a6e59d68682dd8c Mon Sep 17 00:00:00 2001
From: Gabriel Krisman Bertazi <krisman@collabora.com>
Date: Mon, 16 Nov 2020 12:42:01 -0500
Subject: tracepoints: Migrate to use SYSCALL_WORK flag

On architectures using the generic syscall entry code the architecture
independent syscall work is moved to flags in thread_info::syscall_work.
This removes architecture dependencies and frees up TIF bits.

Define SYSCALL_WORK_SYSCALL_TRACEPOINT, use it in the generic entry code
and convert the code which uses the TIF specific helper functions to use
the new *_syscall_work() helpers which either resolve to the new mode for
users of the generic entry code or to the TIF based functions for the other
architectures.

Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Andy Lutomirski <luto@kernel.org>
Link: https://lore.kernel.org/r/20201116174206.2639648-6-krisman@collabora.com
---
 include/linux/entry-common.h | 13 +++++--------
 include/linux/thread_info.h  |  2 ++
 include/trace/syscall.h      |  6 +++---
 kernel/entry/common.c        |  4 ++--
 kernel/trace/trace_events.c  |  8 ++++----
 kernel/tracepoint.c          |  4 ++--
 6 files changed, 18 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index fa3cdb102dbf..2a01eee2dbba 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -17,10 +17,6 @@
 # define _TIF_SYSCALL_EMU		(0)
 #endif
 
-#ifndef _TIF_SYSCALL_TRACEPOINT
-# define _TIF_SYSCALL_TRACEPOINT	(0)
-#endif
-
 #ifndef _TIF_SYSCALL_AUDIT
 # define _TIF_SYSCALL_AUDIT		(0)
 #endif
@@ -46,7 +42,7 @@
 
 #define SYSCALL_ENTER_WORK						\
 	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT  |			\
-	 _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_EMU |			\
+	 _TIF_SYSCALL_EMU |						\
 	 ARCH_SYSCALL_ENTER_WORK)
 
 /*
@@ -58,10 +54,11 @@
 
 #define SYSCALL_EXIT_WORK						\
 	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT |			\
-	 _TIF_SYSCALL_TRACEPOINT | ARCH_SYSCALL_EXIT_WORK)
+	 ARCH_SYSCALL_EXIT_WORK)
 
-#define SYSCALL_WORK_ENTER	(SYSCALL_WORK_SECCOMP)
-#define SYSCALL_WORK_EXIT	(0)
+#define SYSCALL_WORK_ENTER	(SYSCALL_WORK_SECCOMP |			\
+				 SYSCALL_WORK_SYSCALL_TRACEPOINT)
+#define SYSCALL_WORK_EXIT	(SYSCALL_WORK_SYSCALL_TRACEPOINT)
 
 /*
  * TIF flags handled in exit_to_user_mode_loop()
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index a308ba4ef07b..c232043c12d3 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -37,9 +37,11 @@ enum {
 
 enum syscall_work_bit {
 	SYSCALL_WORK_BIT_SECCOMP,
+	SYSCALL_WORK_BIT_SYSCALL_TRACEPOINT,
 };
 
 #define SYSCALL_WORK_SECCOMP		BIT(SYSCALL_WORK_BIT_SECCOMP)
+#define SYSCALL_WORK_SYSCALL_TRACEPOINT	BIT(SYSCALL_WORK_BIT_SYSCALL_TRACEPOINT)
 
 #include <asm/thread_info.h>
 
diff --git a/include/trace/syscall.h b/include/trace/syscall.h
index dc8ac27d27c1..8e193f3a33b3 100644
--- a/include/trace/syscall.h
+++ b/include/trace/syscall.h
@@ -37,10 +37,10 @@ struct syscall_metadata {
 #if defined(CONFIG_TRACEPOINTS) && defined(CONFIG_HAVE_SYSCALL_TRACEPOINTS)
 static inline void syscall_tracepoint_update(struct task_struct *p)
 {
-	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
-		set_tsk_thread_flag(p, TIF_SYSCALL_TRACEPOINT);
+	if (test_syscall_work(SYSCALL_TRACEPOINT))
+		set_task_syscall_work(p, SYSCALL_TRACEPOINT);
 	else
-		clear_tsk_thread_flag(p, TIF_SYSCALL_TRACEPOINT);
+		clear_task_syscall_work(p, SYSCALL_TRACEPOINT);
 }
 #else
 static inline void syscall_tracepoint_update(struct task_struct *p)
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 5747a6eb2c48..f651967847ec 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -63,7 +63,7 @@ static long syscall_trace_enter(struct pt_regs *regs, long syscall,
 	/* Either of the above might have changed the syscall number */
 	syscall = syscall_get_nr(current, regs);
 
-	if (unlikely(ti_work & _TIF_SYSCALL_TRACEPOINT))
+	if (unlikely(work & SYSCALL_WORK_SYSCALL_TRACEPOINT))
 		trace_sys_enter(regs, syscall);
 
 	syscall_enter_audit(regs, syscall);
@@ -233,7 +233,7 @@ static void syscall_exit_work(struct pt_regs *regs, unsigned long ti_work,
 
 	audit_syscall_exit(regs);
 
-	if (ti_work & _TIF_SYSCALL_TRACEPOINT)
+	if (work & SYSCALL_WORK_SYSCALL_TRACEPOINT)
 		trace_sys_exit(regs, syscall_get_return_value(current, regs));
 
 	step = report_single_step(ti_work);
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 47a71f96e5bc..adf65b502453 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -3428,10 +3428,10 @@ static __init int event_trace_enable(void)
  * initialize events and perhaps start any events that are on the
  * command line. Unfortunately, there are some events that will not
  * start this early, like the system call tracepoints that need
- * to set the TIF_SYSCALL_TRACEPOINT flag of pid 1. But event_trace_enable()
- * is called before pid 1 starts, and this flag is never set, making
- * the syscall tracepoint never get reached, but the event is enabled
- * regardless (and not doing anything).
+ * to set the %SYSCALL_WORK_SYSCALL_TRACEPOINT flag of pid 1. But
+ * event_trace_enable() is called before pid 1 starts, and this flag
+ * is never set, making the syscall tracepoint never get reached, but
+ * the event is enabled regardless (and not doing anything).
  */
 static __init int event_trace_enable_again(void)
 {
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 3f659f855074..7261fa0f5e3c 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -594,7 +594,7 @@ int syscall_regfunc(void)
 	if (!sys_tracepoint_refcount) {
 		read_lock(&tasklist_lock);
 		for_each_process_thread(p, t) {
-			set_tsk_thread_flag(t, TIF_SYSCALL_TRACEPOINT);
+			set_task_syscall_work(t, SYSCALL_TRACEPOINT);
 		}
 		read_unlock(&tasklist_lock);
 	}
@@ -611,7 +611,7 @@ void syscall_unregfunc(void)
 	if (!sys_tracepoint_refcount) {
 		read_lock(&tasklist_lock);
 		for_each_process_thread(p, t) {
-			clear_tsk_thread_flag(t, TIF_SYSCALL_TRACEPOINT);
+			clear_task_syscall_work(t, SYSCALL_TRACEPOINT);
 		}
 		read_unlock(&tasklist_lock);
 	}
-- 
cgit v1.2.3


From 64c19ba29b66e98af9306b4a7525fb22c895d252 Mon Sep 17 00:00:00 2001
From: Gabriel Krisman Bertazi <krisman@collabora.com>
Date: Mon, 16 Nov 2020 12:42:02 -0500
Subject: ptrace: Migrate to use SYSCALL_TRACE flag

On architectures using the generic syscall entry code the architecture
independent syscall work is moved to flags in thread_info::syscall_work.
This removes architecture dependencies and frees up TIF bits.

Define SYSCALL_WORK_SYSCALL_TRACE, use it in the generic entry code and
convert the code which uses the TIF specific helper functions to use the
new *_syscall_work() helpers which either resolve to the new mode for users
of the generic entry code or to the TIF based functions for the other
architectures.

Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Andy Lutomirski <luto@kernel.org>
Link: https://lore.kernel.org/r/20201116174206.2639648-7-krisman@collabora.com
---
 include/asm-generic/syscall.h | 15 ++++++++-------
 include/linux/entry-common.h  | 10 ++++++----
 include/linux/thread_info.h   |  2 ++
 include/linux/tracehook.h     | 17 +++++++++--------
 kernel/entry/common.c         |  4 ++--
 kernel/fork.c                 |  2 +-
 kernel/ptrace.c               |  6 +++---
 7 files changed, 31 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/include/asm-generic/syscall.h b/include/asm-generic/syscall.h
index 524d8e68ff5e..ed94e5658d0c 100644
--- a/include/asm-generic/syscall.h
+++ b/include/asm-generic/syscall.h
@@ -43,7 +43,7 @@ int syscall_get_nr(struct task_struct *task, struct pt_regs *regs);
  * @regs:	task_pt_regs() of @task
  *
  * It's only valid to call this when @task is stopped for system
- * call exit tracing (due to TIF_SYSCALL_TRACE or TIF_SYSCALL_AUDIT),
+ * call exit tracing (due to %SYSCALL_WORK_SYSCALL_TRACE or TIF_SYSCALL_AUDIT),
  * after tracehook_report_syscall_entry() returned nonzero to prevent
  * the system call from taking place.
  *
@@ -63,7 +63,7 @@ void syscall_rollback(struct task_struct *task, struct pt_regs *regs);
  * Returns 0 if the system call succeeded, or -ERRORCODE if it failed.
  *
  * It's only valid to call this when @task is stopped for tracing on exit
- * from a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
+ * from a system call, due to %SYSCALL_WORK_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
  */
 long syscall_get_error(struct task_struct *task, struct pt_regs *regs);
 
@@ -76,7 +76,7 @@ long syscall_get_error(struct task_struct *task, struct pt_regs *regs);
  * This value is meaningless if syscall_get_error() returned nonzero.
  *
  * It's only valid to call this when @task is stopped for tracing on exit
- * from a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
+ * from a system call, due to %SYSCALL_WORK_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
  */
 long syscall_get_return_value(struct task_struct *task, struct pt_regs *regs);
 
@@ -93,7 +93,7 @@ long syscall_get_return_value(struct task_struct *task, struct pt_regs *regs);
  * code; the user sees a failed system call with this errno code.
  *
  * It's only valid to call this when @task is stopped for tracing on exit
- * from a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
+ * from a system call, due to %SYSCALL_WORK_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
  */
 void syscall_set_return_value(struct task_struct *task, struct pt_regs *regs,
 			      int error, long val);
@@ -108,7 +108,7 @@ void syscall_set_return_value(struct task_struct *task, struct pt_regs *regs,
 *  @args[0], and so on.
  *
  * It's only valid to call this when @task is stopped for tracing on
- * entry to a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
+ * entry to a system call, due to %SYSCALL_WORK_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
  */
 void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
 			   unsigned long *args);
@@ -123,7 +123,7 @@ void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
  * The first argument gets value @args[0], and so on.
  *
  * It's only valid to call this when @task is stopped for tracing on
- * entry to a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
+ * entry to a system call, due to %SYSCALL_WORK_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
  */
 void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
 			   const unsigned long *args);
@@ -135,7 +135,8 @@ void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
  * Returns the AUDIT_ARCH_* based on the system call convention in use.
  *
  * It's only valid to call this when @task is stopped on entry to a system
- * call, due to %TIF_SYSCALL_TRACE, %TIF_SYSCALL_AUDIT, or %SYSCALL_WORK_SECCOMP.
+ * call, due to %SYSCALL_WORK_SYSCALL_TRACE, %TIF_SYSCALL_AUDIT, or
+ * %SYSCALL_WORK_SECCOMP.
  *
  * Architectures which permit CONFIG_HAVE_ARCH_SECCOMP_FILTER must
  * provide an implementation of this.
diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index 2a01eee2dbba..ae426ab9c372 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -41,7 +41,7 @@
 #endif
 
 #define SYSCALL_ENTER_WORK						\
-	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT  |			\
+	(_TIF_SYSCALL_AUDIT  |						\
 	 _TIF_SYSCALL_EMU |						\
 	 ARCH_SYSCALL_ENTER_WORK)
 
@@ -53,12 +53,14 @@
 #endif
 
 #define SYSCALL_EXIT_WORK						\
-	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT |			\
+	(_TIF_SYSCALL_AUDIT |						\
 	 ARCH_SYSCALL_EXIT_WORK)
 
 #define SYSCALL_WORK_ENTER	(SYSCALL_WORK_SECCOMP |			\
-				 SYSCALL_WORK_SYSCALL_TRACEPOINT)
-#define SYSCALL_WORK_EXIT	(SYSCALL_WORK_SYSCALL_TRACEPOINT)
+				 SYSCALL_WORK_SYSCALL_TRACEPOINT |	\
+				 SYSCALL_WORK_SYSCALL_TRACE)
+#define SYSCALL_WORK_EXIT	(SYSCALL_WORK_SYSCALL_TRACEPOINT |	\
+				 SYSCALL_WORK_SYSCALL_TRACE)
 
 /*
  * TIF flags handled in exit_to_user_mode_loop()
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index c232043c12d3..761a4590d554 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -38,10 +38,12 @@ enum {
 enum syscall_work_bit {
 	SYSCALL_WORK_BIT_SECCOMP,
 	SYSCALL_WORK_BIT_SYSCALL_TRACEPOINT,
+	SYSCALL_WORK_BIT_SYSCALL_TRACE,
 };
 
 #define SYSCALL_WORK_SECCOMP		BIT(SYSCALL_WORK_BIT_SECCOMP)
 #define SYSCALL_WORK_SYSCALL_TRACEPOINT	BIT(SYSCALL_WORK_BIT_SYSCALL_TRACEPOINT)
+#define SYSCALL_WORK_SYSCALL_TRACE	BIT(SYSCALL_WORK_BIT_SYSCALL_TRACE)
 
 #include <asm/thread_info.h>
 
diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h
index f7d82e4fafd6..3f20368afe9e 100644
--- a/include/linux/tracehook.h
+++ b/include/linux/tracehook.h
@@ -83,11 +83,12 @@ static inline int ptrace_report_syscall(struct pt_regs *regs,
  * tracehook_report_syscall_entry - task is about to attempt a system call
  * @regs:		user register state of current task
  *
- * This will be called if %TIF_SYSCALL_TRACE or %TIF_SYSCALL_EMU have been set,
- * when the current task has just entered the kernel for a system call.
- * Full user register state is available here.  Changing the values
- * in @regs can affect the system call number and arguments to be tried.
- * It is safe to block here, preventing the system call from beginning.
+ * This will be called if %SYSCALL_WORK_SYSCALL_TRACE or
+ * %TIF_SYSCALL_EMU have been set, when the current task has just
+ * entered the kernel for a system call.  Full user register state is
+ * available here.  Changing the values in @regs can affect the system
+ * call number and arguments to be tried.  It is safe to block here,
+ * preventing the system call from beginning.
  *
  * Returns zero normally, or nonzero if the calling arch code should abort
  * the system call.  That must prevent normal entry so no system call is
@@ -109,15 +110,15 @@ static inline __must_check int tracehook_report_syscall_entry(
  * @regs:		user register state of current task
  * @step:		nonzero if simulating single-step or block-step
  *
- * This will be called if %TIF_SYSCALL_TRACE has been set, when the
- * current task has just finished an attempted system call.  Full
+ * This will be called if %SYSCALL_WORK_SYSCALL_TRACE has been set, when
+ * the current task has just finished an attempted system call.  Full
  * user register state is available here.  It is safe to block here,
  * preventing signals from being processed.
  *
  * If @step is nonzero, this report is also in lieu of the normal
  * trap that would follow the system call instruction because
  * user_enable_block_step() or user_enable_single_step() was used.
- * In this case, %TIF_SYSCALL_TRACE might not be set.
+ * In this case, %SYSCALL_WORK_SYSCALL_TRACE might not be set.
  *
  * Called without locks, just before checking for pending signals.
  */
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index f651967847ec..917328a9edaa 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -47,7 +47,7 @@ static long syscall_trace_enter(struct pt_regs *regs, long syscall,
 	long ret = 0;
 
 	/* Handle ptrace */
-	if (ti_work & (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU)) {
+	if (work & SYSCALL_WORK_SYSCALL_TRACE || ti_work & _TIF_SYSCALL_EMU) {
 		ret = arch_syscall_enter_tracehook(regs);
 		if (ret || (ti_work & _TIF_SYSCALL_EMU))
 			return -1L;
@@ -237,7 +237,7 @@ static void syscall_exit_work(struct pt_regs *regs, unsigned long ti_work,
 		trace_sys_exit(regs, syscall_get_return_value(current, regs));
 
 	step = report_single_step(ti_work);
-	if (step || ti_work & _TIF_SYSCALL_TRACE)
+	if (step || work & SYSCALL_WORK_SYSCALL_TRACE)
 		arch_syscall_exit_tracehook(regs, step);
 }
 
diff --git a/kernel/fork.c b/kernel/fork.c
index bc5b1090f415..99f68c20f2ff 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2158,7 +2158,7 @@ static __latent_entropy struct task_struct *copy_process(
 	 * child regardless of CLONE_PTRACE.
 	 */
 	user_disable_single_step(p);
-	clear_tsk_thread_flag(p, TIF_SYSCALL_TRACE);
+	clear_task_syscall_work(p, SYSCALL_TRACE);
 #ifdef TIF_SYSCALL_EMU
 	clear_tsk_thread_flag(p, TIF_SYSCALL_EMU);
 #endif
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 43d6179508d6..55a2bc3186a7 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -117,7 +117,7 @@ void __ptrace_unlink(struct task_struct *child)
 	const struct cred *old_cred;
 	BUG_ON(!child->ptrace);
 
-	clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
+	clear_task_syscall_work(child, SYSCALL_TRACE);
 #ifdef TIF_SYSCALL_EMU
 	clear_tsk_thread_flag(child, TIF_SYSCALL_EMU);
 #endif
@@ -812,9 +812,9 @@ static int ptrace_resume(struct task_struct *child, long request,
 		return -EIO;
 
 	if (request == PTRACE_SYSCALL)
-		set_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
+		set_task_syscall_work(child, SYSCALL_TRACE);
 	else
-		clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
+		clear_task_syscall_work(child, SYSCALL_TRACE);
 
 #ifdef TIF_SYSCALL_EMU
 	if (request == PTRACE_SYSEMU || request == PTRACE_SYSEMU_SINGLESTEP)
-- 
cgit v1.2.3


From 64eb35f701f04b30706e21d1b02636b5d31a37d2 Mon Sep 17 00:00:00 2001
From: Gabriel Krisman Bertazi <krisman@collabora.com>
Date: Mon, 16 Nov 2020 12:42:03 -0500
Subject: ptrace: Migrate TIF_SYSCALL_EMU to use SYSCALL_WORK flag

On architectures using the generic syscall entry code the architecture
independent syscall work is moved to flags in thread_info::syscall_work.
This removes architecture dependencies and frees up TIF bits.

Define SYSCALL_WORK_SYSCALL_EMU, use it in the generic entry code and
convert the code which uses the TIF specific helper functions to use the
new *_syscall_work() helpers which either resolve to the new mode for users
of the generic entry code or to the TIF based functions for the other
architectures.

Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Andy Lutomirski <luto@kernel.org>
Link: https://lore.kernel.org/r/20201116174206.2639648-8-krisman@collabora.com
---
 include/linux/entry-common.h |  8 ++------
 include/linux/thread_info.h  |  2 ++
 include/linux/tracehook.h    |  2 +-
 kernel/entry/common.c        | 19 ++++++++++---------
 kernel/fork.c                |  4 ++--
 kernel/ptrace.c              | 10 +++++-----
 6 files changed, 22 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index ae426ab9c372..b30f82bed92b 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -13,10 +13,6 @@
  * Define dummy _TIF work flags if not defined by the architecture or for
  * disabled functionality.
  */
-#ifndef _TIF_SYSCALL_EMU
-# define _TIF_SYSCALL_EMU		(0)
-#endif
-
 #ifndef _TIF_SYSCALL_AUDIT
 # define _TIF_SYSCALL_AUDIT		(0)
 #endif
@@ -42,7 +38,6 @@
 
 #define SYSCALL_ENTER_WORK						\
 	(_TIF_SYSCALL_AUDIT  |						\
-	 _TIF_SYSCALL_EMU |						\
 	 ARCH_SYSCALL_ENTER_WORK)
 
 /*
@@ -58,7 +53,8 @@
 
 #define SYSCALL_WORK_ENTER	(SYSCALL_WORK_SECCOMP |			\
 				 SYSCALL_WORK_SYSCALL_TRACEPOINT |	\
-				 SYSCALL_WORK_SYSCALL_TRACE)
+				 SYSCALL_WORK_SYSCALL_TRACE |		\
+				 SYSCALL_WORK_SYSCALL_EMU)
 #define SYSCALL_WORK_EXIT	(SYSCALL_WORK_SYSCALL_TRACEPOINT |	\
 				 SYSCALL_WORK_SYSCALL_TRACE)
 
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index 761a4590d554..85b8a4216168 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -39,11 +39,13 @@ enum syscall_work_bit {
 	SYSCALL_WORK_BIT_SECCOMP,
 	SYSCALL_WORK_BIT_SYSCALL_TRACEPOINT,
 	SYSCALL_WORK_BIT_SYSCALL_TRACE,
+	SYSCALL_WORK_BIT_SYSCALL_EMU,
 };
 
 #define SYSCALL_WORK_SECCOMP		BIT(SYSCALL_WORK_BIT_SECCOMP)
 #define SYSCALL_WORK_SYSCALL_TRACEPOINT	BIT(SYSCALL_WORK_BIT_SYSCALL_TRACEPOINT)
 #define SYSCALL_WORK_SYSCALL_TRACE	BIT(SYSCALL_WORK_BIT_SYSCALL_TRACE)
+#define SYSCALL_WORK_SYSCALL_EMU	BIT(SYSCALL_WORK_BIT_SYSCALL_EMU)
 
 #include <asm/thread_info.h>
 
diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h
index 3f20368afe9e..54b925224a13 100644
--- a/include/linux/tracehook.h
+++ b/include/linux/tracehook.h
@@ -84,7 +84,7 @@ static inline int ptrace_report_syscall(struct pt_regs *regs,
  * @regs:		user register state of current task
  *
  * This will be called if %SYSCALL_WORK_SYSCALL_TRACE or
- * %TIF_SYSCALL_EMU have been set, when the current task has just
+ * %SYSCALL_WORK_SYSCALL_EMU have been set, when the current task has just
  * entered the kernel for a system call.  Full user register state is
  * available here.  Changing the values in @regs can affect the system
  * call number and arguments to be tried.  It is safe to block here,
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 917328a9edaa..90533f34ea99 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -47,9 +47,9 @@ static long syscall_trace_enter(struct pt_regs *regs, long syscall,
 	long ret = 0;
 
 	/* Handle ptrace */
-	if (work & SYSCALL_WORK_SYSCALL_TRACE || ti_work & _TIF_SYSCALL_EMU) {
+	if (work & (SYSCALL_WORK_SYSCALL_TRACE | SYSCALL_WORK_SYSCALL_EMU)) {
 		ret = arch_syscall_enter_tracehook(regs);
-		if (ret || (ti_work & _TIF_SYSCALL_EMU))
+		if (ret || (work & SYSCALL_WORK_SYSCALL_EMU))
 			return -1L;
 	}
 
@@ -208,21 +208,22 @@ static void exit_to_user_mode_prepare(struct pt_regs *regs)
 }
 
 #ifndef _TIF_SINGLESTEP
-static inline bool report_single_step(unsigned long ti_work)
+static inline bool report_single_step(unsigned long work)
 {
 	return false;
 }
 #else
 /*
- * If TIF_SYSCALL_EMU is set, then the only reason to report is when
+ * If SYSCALL_EMU is set, then the only reason to report is when
  * TIF_SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP).  This syscall
  * instruction has been already reported in syscall_enter_from_user_mode().
  */
-#define SYSEMU_STEP	(_TIF_SINGLESTEP | _TIF_SYSCALL_EMU)
-
-static inline bool report_single_step(unsigned long ti_work)
+static inline bool report_single_step(unsigned long work)
 {
-	return (ti_work & SYSEMU_STEP) == _TIF_SINGLESTEP;
+	if (!(work & SYSCALL_WORK_SYSCALL_EMU))
+		return false;
+
+	return !!(current_thread_info()->flags & _TIF_SINGLESTEP);
 }
 #endif
 
@@ -236,7 +237,7 @@ static void syscall_exit_work(struct pt_regs *regs, unsigned long ti_work,
 	if (work & SYSCALL_WORK_SYSCALL_TRACEPOINT)
 		trace_sys_exit(regs, syscall_get_return_value(current, regs));
 
-	step = report_single_step(ti_work);
+	step = report_single_step(work);
 	if (step || work & SYSCALL_WORK_SYSCALL_TRACE)
 		arch_syscall_exit_tracehook(regs, step);
 }
diff --git a/kernel/fork.c b/kernel/fork.c
index 99f68c20f2ff..02b689a23457 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2159,8 +2159,8 @@ static __latent_entropy struct task_struct *copy_process(
 	 */
 	user_disable_single_step(p);
 	clear_task_syscall_work(p, SYSCALL_TRACE);
-#ifdef TIF_SYSCALL_EMU
-	clear_tsk_thread_flag(p, TIF_SYSCALL_EMU);
+#if defined(CONFIG_GENERIC_ENTRY) || defined(TIF_SYSCALL_EMU)
+	clear_task_syscall_work(p, SYSCALL_EMU);
 #endif
 	clear_tsk_latency_tracing(p);
 
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 55a2bc3186a7..237bcd6d255c 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -118,8 +118,8 @@ void __ptrace_unlink(struct task_struct *child)
 	BUG_ON(!child->ptrace);
 
 	clear_task_syscall_work(child, SYSCALL_TRACE);
-#ifdef TIF_SYSCALL_EMU
-	clear_tsk_thread_flag(child, TIF_SYSCALL_EMU);
+#if defined(CONFIG_GENERIC_ENTRY) || defined(TIF_SYSCALL_EMU)
+	clear_task_syscall_work(child, SYSCALL_EMU);
 #endif
 
 	child->parent = child->real_parent;
@@ -816,11 +816,11 @@ static int ptrace_resume(struct task_struct *child, long request,
 	else
 		clear_task_syscall_work(child, SYSCALL_TRACE);
 
-#ifdef TIF_SYSCALL_EMU
+#if defined(CONFIG_GENERIC_ENTRY) || defined(TIF_SYSCALL_EMU)
 	if (request == PTRACE_SYSEMU || request == PTRACE_SYSEMU_SINGLESTEP)
-		set_tsk_thread_flag(child, TIF_SYSCALL_EMU);
+		set_task_syscall_work(child, SYSCALL_EMU);
 	else
-		clear_tsk_thread_flag(child, TIF_SYSCALL_EMU);
+		clear_task_syscall_work(child, SYSCALL_EMU);
 #endif
 
 	if (is_singleblock(request)) {
-- 
cgit v1.2.3


From 785dc4eb7fd74e3b7f4eac468457b633117e1aea Mon Sep 17 00:00:00 2001
From: Gabriel Krisman Bertazi <krisman@collabora.com>
Date: Mon, 16 Nov 2020 12:42:04 -0500
Subject: audit: Migrate to use SYSCALL_WORK flag

On architectures using the generic syscall entry code the architecture
independent syscall work is moved to flags in thread_info::syscall_work.
This removes architecture dependencies and frees up TIF bits.

Define SYSCALL_WORK_SYSCALL_AUDIT, use it in the generic entry code and
convert the code which uses the TIF specific helper functions to use the
new *_syscall_work() helpers which either resolve to the new mode for users
of the generic entry code or to the TIF based functions for the other
architectures.

Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Andy Lutomirski <luto@kernel.org>
Link: https://lore.kernel.org/r/20201116174206.2639648-9-krisman@collabora.com
---
 include/asm-generic/syscall.h | 23 ++++++++++++++---------
 include/linux/entry-common.h  | 18 ++++++------------
 include/linux/thread_info.h   |  2 ++
 kernel/auditsc.c              |  4 ++--
 4 files changed, 24 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/include/asm-generic/syscall.h b/include/asm-generic/syscall.h
index ed94e5658d0c..524218ae3825 100644
--- a/include/asm-generic/syscall.h
+++ b/include/asm-generic/syscall.h
@@ -43,9 +43,9 @@ int syscall_get_nr(struct task_struct *task, struct pt_regs *regs);
  * @regs:	task_pt_regs() of @task
  *
  * It's only valid to call this when @task is stopped for system
- * call exit tracing (due to %SYSCALL_WORK_SYSCALL_TRACE or TIF_SYSCALL_AUDIT),
- * after tracehook_report_syscall_entry() returned nonzero to prevent
- * the system call from taking place.
+ * call exit tracing (due to %SYSCALL_WORK_SYSCALL_TRACE or
+ * %SYSCALL_WORK_SYSCALL_AUDIT), after tracehook_report_syscall_entry()
+ * returned nonzero to prevent the system call from taking place.
  *
  * This rolls back the register state in @regs so it's as if the
  * system call instruction was a no-op.  The registers containing
@@ -63,7 +63,8 @@ void syscall_rollback(struct task_struct *task, struct pt_regs *regs);
  * Returns 0 if the system call succeeded, or -ERRORCODE if it failed.
  *
  * It's only valid to call this when @task is stopped for tracing on exit
- * from a system call, due to %SYSCALL_WORK_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
+ * from a system call, due to %SYSCALL_WORK_SYSCALL_TRACE or
+ * %SYSCALL_WORK_SYSCALL_AUDIT.
  */
 long syscall_get_error(struct task_struct *task, struct pt_regs *regs);
 
@@ -76,7 +77,8 @@ long syscall_get_error(struct task_struct *task, struct pt_regs *regs);
  * This value is meaningless if syscall_get_error() returned nonzero.
  *
  * It's only valid to call this when @task is stopped for tracing on exit
- * from a system call, due to %SYSCALL_WORK_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
+ * from a system call, due to %SYSCALL_WORK_SYSCALL_TRACE or
+ * %SYSCALL_WORK_SYSCALL_AUDIT.
  */
 long syscall_get_return_value(struct task_struct *task, struct pt_regs *regs);
 
@@ -93,7 +95,8 @@ long syscall_get_return_value(struct task_struct *task, struct pt_regs *regs);
  * code; the user sees a failed system call with this errno code.
  *
  * It's only valid to call this when @task is stopped for tracing on exit
- * from a system call, due to %SYSCALL_WORK_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
+ * from a system call, due to %SYSCALL_WORK_SYSCALL_TRACE or
+ * %SYSCALL_WORK_SYSCALL_AUDIT.
  */
 void syscall_set_return_value(struct task_struct *task, struct pt_regs *regs,
 			      int error, long val);
@@ -108,7 +111,8 @@ void syscall_set_return_value(struct task_struct *task, struct pt_regs *regs,
 *  @args[0], and so on.
  *
  * It's only valid to call this when @task is stopped for tracing on
- * entry to a system call, due to %SYSCALL_WORK_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
+ * entry to a system call, due to %SYSCALL_WORK_SYSCALL_TRACE or
+ * %SYSCALL_WORK_SYSCALL_AUDIT.
  */
 void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
 			   unsigned long *args);
@@ -123,7 +127,8 @@ void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
  * The first argument gets value @args[0], and so on.
  *
  * It's only valid to call this when @task is stopped for tracing on
- * entry to a system call, due to %SYSCALL_WORK_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
+ * entry to a system call, due to %SYSCALL_WORK_SYSCALL_TRACE or
+ * %SYSCALL_WORK_SYSCALL_AUDIT.
  */
 void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
 			   const unsigned long *args);
@@ -135,7 +140,7 @@ void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
  * Returns the AUDIT_ARCH_* based on the system call convention in use.
  *
  * It's only valid to call this when @task is stopped on entry to a system
- * call, due to %SYSCALL_WORK_SYSCALL_TRACE, %TIF_SYSCALL_AUDIT, or
+ * call, due to %SYSCALL_WORK_SYSCALL_TRACE, %SYSCALL_WORK_SYSCALL_AUDIT, or
  * %SYSCALL_WORK_SECCOMP.
  *
  * Architectures which permit CONFIG_HAVE_ARCH_SECCOMP_FILTER must
diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index b30f82bed92b..d7b96f42817f 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -13,10 +13,6 @@
  * Define dummy _TIF work flags if not defined by the architecture or for
  * disabled functionality.
  */
-#ifndef _TIF_SYSCALL_AUDIT
-# define _TIF_SYSCALL_AUDIT		(0)
-#endif
-
 #ifndef _TIF_PATCH_PENDING
 # define _TIF_PATCH_PENDING		(0)
 #endif
@@ -36,9 +32,7 @@
 # define ARCH_SYSCALL_ENTER_WORK	(0)
 #endif
 
-#define SYSCALL_ENTER_WORK						\
-	(_TIF_SYSCALL_AUDIT  |						\
-	 ARCH_SYSCALL_ENTER_WORK)
+#define SYSCALL_ENTER_WORK ARCH_SYSCALL_ENTER_WORK
 
 /*
  * TIF flags handled in syscall_exit_to_user_mode()
@@ -47,16 +41,16 @@
 # define ARCH_SYSCALL_EXIT_WORK		(0)
 #endif
 
-#define SYSCALL_EXIT_WORK						\
-	(_TIF_SYSCALL_AUDIT |						\
-	 ARCH_SYSCALL_EXIT_WORK)
+#define SYSCALL_EXIT_WORK ARCH_SYSCALL_EXIT_WORK
 
 #define SYSCALL_WORK_ENTER	(SYSCALL_WORK_SECCOMP |			\
 				 SYSCALL_WORK_SYSCALL_TRACEPOINT |	\
 				 SYSCALL_WORK_SYSCALL_TRACE |		\
-				 SYSCALL_WORK_SYSCALL_EMU)
+				 SYSCALL_WORK_SYSCALL_EMU |		\
+				 SYSCALL_WORK_SYSCALL_AUDIT)
 #define SYSCALL_WORK_EXIT	(SYSCALL_WORK_SYSCALL_TRACEPOINT |	\
-				 SYSCALL_WORK_SYSCALL_TRACE)
+				 SYSCALL_WORK_SYSCALL_TRACE |		\
+				 SYSCALL_WORK_SYSCALL_AUDIT)
 
 /*
  * TIF flags handled in exit_to_user_mode_loop()
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index 85b8a4216168..317363212ae9 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -40,12 +40,14 @@ enum syscall_work_bit {
 	SYSCALL_WORK_BIT_SYSCALL_TRACEPOINT,
 	SYSCALL_WORK_BIT_SYSCALL_TRACE,
 	SYSCALL_WORK_BIT_SYSCALL_EMU,
+	SYSCALL_WORK_BIT_SYSCALL_AUDIT,
 };
 
 #define SYSCALL_WORK_SECCOMP		BIT(SYSCALL_WORK_BIT_SECCOMP)
 #define SYSCALL_WORK_SYSCALL_TRACEPOINT	BIT(SYSCALL_WORK_BIT_SYSCALL_TRACEPOINT)
 #define SYSCALL_WORK_SYSCALL_TRACE	BIT(SYSCALL_WORK_BIT_SYSCALL_TRACE)
 #define SYSCALL_WORK_SYSCALL_EMU	BIT(SYSCALL_WORK_BIT_SYSCALL_EMU)
+#define SYSCALL_WORK_SYSCALL_AUDIT	BIT(SYSCALL_WORK_BIT_SYSCALL_AUDIT)
 
 #include <asm/thread_info.h>
 
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 8dba8f0983b5..c00aa5837965 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -952,7 +952,7 @@ int audit_alloc(struct task_struct *tsk)
 
 	state = audit_filter_task(tsk, &key);
 	if (state == AUDIT_DISABLED) {
-		clear_tsk_thread_flag(tsk, TIF_SYSCALL_AUDIT);
+		clear_task_syscall_work(tsk, SYSCALL_AUDIT);
 		return 0;
 	}
 
@@ -964,7 +964,7 @@ int audit_alloc(struct task_struct *tsk)
 	context->filterkey = key;
 
 	audit_set_context(tsk, context);
-	set_tsk_thread_flag(tsk, TIF_SYSCALL_AUDIT);
+	set_task_syscall_work(tsk, SYSCALL_AUDIT);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 2991552447707d791d9d81a5dc161f9e9e90b163 Mon Sep 17 00:00:00 2001
From: Gabriel Krisman Bertazi <krisman@collabora.com>
Date: Mon, 16 Nov 2020 12:42:05 -0500
Subject: entry: Drop usage of TIF flags in the generic syscall code

Now that the flags migration in the common syscall entry code is complete
and the code relies exclusively on thread_info::syscall_work, clean up the
accesses to TI flags in that path.

Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Andy Lutomirski <luto@kernel.org>
Link: https://lore.kernel.org/r/20201116174206.2639648-10-krisman@collabora.com
---
 include/linux/entry-common.h | 26 ++++++++++++--------------
 kernel/entry/common.c        | 17 +++++++----------
 2 files changed, 19 insertions(+), 24 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index d7b96f42817f..49b26b216e4e 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -26,31 +26,29 @@
 #endif
 
 /*
- * TIF flags handled in syscall_enter_from_user_mode()
+ * SYSCALL_WORK flags handled in syscall_enter_from_user_mode()
  */
-#ifndef ARCH_SYSCALL_ENTER_WORK
-# define ARCH_SYSCALL_ENTER_WORK	(0)
+#ifndef ARCH_SYSCALL_WORK_ENTER
+# define ARCH_SYSCALL_WORK_ENTER	(0)
 #endif
 
-#define SYSCALL_ENTER_WORK ARCH_SYSCALL_ENTER_WORK
-
 /*
- * TIF flags handled in syscall_exit_to_user_mode()
+ * SYSCALL_WORK flags handled in syscall_exit_to_user_mode()
  */
-#ifndef ARCH_SYSCALL_EXIT_WORK
-# define ARCH_SYSCALL_EXIT_WORK		(0)
+#ifndef ARCH_SYSCALL_WORK_EXIT
+# define ARCH_SYSCALL_WORK_EXIT		(0)
 #endif
 
-#define SYSCALL_EXIT_WORK ARCH_SYSCALL_EXIT_WORK
-
 #define SYSCALL_WORK_ENTER	(SYSCALL_WORK_SECCOMP |			\
 				 SYSCALL_WORK_SYSCALL_TRACEPOINT |	\
 				 SYSCALL_WORK_SYSCALL_TRACE |		\
 				 SYSCALL_WORK_SYSCALL_EMU |		\
-				 SYSCALL_WORK_SYSCALL_AUDIT)
+				 SYSCALL_WORK_SYSCALL_AUDIT |		\
+				 ARCH_SYSCALL_WORK_ENTER)
 #define SYSCALL_WORK_EXIT	(SYSCALL_WORK_SYSCALL_TRACEPOINT |	\
 				 SYSCALL_WORK_SYSCALL_TRACE |		\
-				 SYSCALL_WORK_SYSCALL_AUDIT)
+				 SYSCALL_WORK_SYSCALL_AUDIT |		\
+				 ARCH_SYSCALL_WORK_EXIT)
 
 /*
  * TIF flags handled in exit_to_user_mode_loop()
@@ -136,8 +134,8 @@ void syscall_enter_from_user_mode_prepare(struct pt_regs *regs);
  *
  * It handles the following work items:
  *
- *  1) TIF flag dependent invocations of arch_syscall_enter_tracehook(),
- *     __secure_computing(), trace_sys_enter()
+ *  1) syscall_work flag dependent invocations of
+ *     arch_syscall_enter_tracehook(), __secure_computing(), trace_sys_enter()
  *  2) Invocation of audit_syscall_entry()
  */
 long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall);
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 90533f34ea99..91e8fd50adf4 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -42,7 +42,7 @@ static inline void syscall_enter_audit(struct pt_regs *regs, long syscall)
 }
 
 static long syscall_trace_enter(struct pt_regs *regs, long syscall,
-				unsigned long ti_work, unsigned long work)
+				unsigned long work)
 {
 	long ret = 0;
 
@@ -75,11 +75,9 @@ static __always_inline long
 __syscall_enter_from_user_work(struct pt_regs *regs, long syscall)
 {
 	unsigned long work = READ_ONCE(current_thread_info()->syscall_work);
-	unsigned long ti_work;
 
-	ti_work = READ_ONCE(current_thread_info()->flags);
-	if (work & SYSCALL_WORK_ENTER || ti_work & SYSCALL_ENTER_WORK)
-		syscall = syscall_trace_enter(regs, syscall, ti_work, work);
+	if (work & SYSCALL_WORK_ENTER)
+		syscall = syscall_trace_enter(regs, syscall, work);
 
 	return syscall;
 }
@@ -227,8 +225,8 @@ static inline bool report_single_step(unsigned long work)
 }
 #endif
 
-static void syscall_exit_work(struct pt_regs *regs, unsigned long ti_work,
-			      unsigned long work)
+
+static void syscall_exit_work(struct pt_regs *regs, unsigned long work)
 {
 	bool step;
 
@@ -249,7 +247,6 @@ static void syscall_exit_work(struct pt_regs *regs, unsigned long ti_work,
 static void syscall_exit_to_user_mode_prepare(struct pt_regs *regs)
 {
 	unsigned long work = READ_ONCE(current_thread_info()->syscall_work);
-	u32 cached_flags = READ_ONCE(current_thread_info()->flags);
 	unsigned long nr = syscall_get_nr(current, regs);
 
 	CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
@@ -266,8 +263,8 @@ static void syscall_exit_to_user_mode_prepare(struct pt_regs *regs)
 	 * enabled, we want to run them exactly once per syscall exit with
 	 * interrupts enabled.
 	 */
-	if (unlikely(work & SYSCALL_WORK_EXIT || cached_flags & SYSCALL_EXIT_WORK))
-		syscall_exit_work(regs, cached_flags, work);
+	if (unlikely(work & SYSCALL_WORK_EXIT))
+		syscall_exit_work(regs, work);
 }
 
 __visible noinstr void syscall_exit_to_user_mode(struct pt_regs *regs)
-- 
cgit v1.2.3


From e8b7db38449ac5b950a3f00519171c4be3e226ff Mon Sep 17 00:00:00 2001
From: Andres Beltran <lkmlabelt@gmail.com>
Date: Mon, 9 Nov 2020 11:04:00 +0100
Subject: Drivers: hv: vmbus: Add vmbus_requestor data structure for VMBus
 hardening

Currently, VMbus drivers use pointers into guest memory as request IDs
for interactions with Hyper-V. To be more robust in the face of errors
or malicious behavior from a compromised Hyper-V, avoid exposing
guest memory addresses to Hyper-V. Also avoid Hyper-V giving back a
bad request ID that is then treated as the address of a guest data
structure with no validation. Instead, encapsulate these memory
addresses and provide small integers as request IDs.

Signed-off-by: Andres Beltran <lkmlabelt@gmail.com>
Co-developed-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com>
Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Reviewed-by: Wei Liu <wei.liu@kernel.org>
Link: https://lore.kernel.org/r/20201109100402.8946-2-parri.andrea@gmail.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 drivers/hv/channel.c      | 174 ++++++++++++++++++++++++++++++++++++++++++++--
 drivers/hv/hyperv_vmbus.h |   3 +-
 drivers/hv/ring_buffer.c  |  29 +++++++-
 include/linux/hyperv.h    |  22 ++++++
 4 files changed, 219 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index fbdda9938039..6fb0c76bfbf8 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -503,6 +503,70 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer,
 }
 EXPORT_SYMBOL_GPL(vmbus_establish_gpadl);
 
+/**
+ * request_arr_init - Allocates memory for the requestor array. Each slot
+ * keeps track of the next available slot in the array. Initially, each
+ * slot points to the next one (as in a Linked List). The last slot
+ * does not point to anything, so its value is U64_MAX by default.
+ * @size The size of the array
+ */
+static u64 *request_arr_init(u32 size)
+{
+	int i;
+	u64 *req_arr;
+
+	req_arr = kcalloc(size, sizeof(u64), GFP_KERNEL);
+	if (!req_arr)
+		return NULL;
+
+	for (i = 0; i < size - 1; i++)
+		req_arr[i] = i + 1;
+
+	/* Last slot (no more available slots) */
+	req_arr[i] = U64_MAX;
+
+	return req_arr;
+}
+
+/*
+ * vmbus_alloc_requestor - Initializes @rqstor's fields.
+ * Index 0 is the first free slot
+ * @size: Size of the requestor array
+ */
+static int vmbus_alloc_requestor(struct vmbus_requestor *rqstor, u32 size)
+{
+	u64 *rqst_arr;
+	unsigned long *bitmap;
+
+	rqst_arr = request_arr_init(size);
+	if (!rqst_arr)
+		return -ENOMEM;
+
+	bitmap = bitmap_zalloc(size, GFP_KERNEL);
+	if (!bitmap) {
+		kfree(rqst_arr);
+		return -ENOMEM;
+	}
+
+	rqstor->req_arr = rqst_arr;
+	rqstor->req_bitmap = bitmap;
+	rqstor->size = size;
+	rqstor->next_request_id = 0;
+	spin_lock_init(&rqstor->req_lock);
+
+	return 0;
+}
+
+/*
+ * vmbus_free_requestor - Frees memory allocated for @rqstor
+ * @rqstor: Pointer to the requestor struct
+ */
+static void vmbus_free_requestor(struct vmbus_requestor *rqstor)
+{
+	kfree(rqstor->req_arr);
+	bitmap_free(rqstor->req_bitmap);
+}
+
 static int __vmbus_open(struct vmbus_channel *newchannel,
 		       void *userdata, u32 userdatalen,
 		       void (*onchannelcallback)(void *context), void *context)
@@ -523,6 +587,12 @@ static int __vmbus_open(struct vmbus_channel *newchannel,
 	if (newchannel->state != CHANNEL_OPEN_STATE)
 		return -EINVAL;
 
+	/* Create and init requestor */
+	if (newchannel->rqstor_size) {
+		if (vmbus_alloc_requestor(&newchannel->requestor, newchannel->rqstor_size))
+			return -ENOMEM;
+	}
+
 	newchannel->state = CHANNEL_OPENING_STATE;
 	newchannel->onchannel_callback = onchannelcallback;
 	newchannel->channel_callback_context = context;
@@ -626,6 +696,7 @@ error_free_gpadl:
 error_clean_ring:
 	hv_ringbuffer_cleanup(&newchannel->outbound);
 	hv_ringbuffer_cleanup(&newchannel->inbound);
+	vmbus_free_requestor(&newchannel->requestor);
 	newchannel->state = CHANNEL_OPEN_STATE;
 	return err;
 }
@@ -808,6 +879,9 @@ static int vmbus_close_internal(struct vmbus_channel *channel)
 		channel->ringbuffer_gpadlhandle = 0;
 	}
 
+	if (!ret)
+		vmbus_free_requestor(&channel->requestor);
+
 	return ret;
 }
 
@@ -888,7 +962,7 @@ int vmbus_sendpacket(struct vmbus_channel *channel, void *buffer,
 	/* in 8-bytes granularity */
 	desc.offset8 = sizeof(struct vmpacket_descriptor) >> 3;
 	desc.len8 = (u16)(packetlen_aligned >> 3);
-	desc.trans_id = requestid;
+	desc.trans_id = VMBUS_RQST_ERROR; /* will be updated in hv_ringbuffer_write() */
 
 	bufferlist[0].iov_base = &desc;
 	bufferlist[0].iov_len = sizeof(struct vmpacket_descriptor);
@@ -897,7 +971,7 @@ int vmbus_sendpacket(struct vmbus_channel *channel, void *buffer,
 	bufferlist[2].iov_base = &aligned_data;
 	bufferlist[2].iov_len = (packetlen_aligned - packetlen);
 
-	return hv_ringbuffer_write(channel, bufferlist, num_vecs);
+	return hv_ringbuffer_write(channel, bufferlist, num_vecs, requestid);
 }
 EXPORT_SYMBOL(vmbus_sendpacket);
 
@@ -939,7 +1013,7 @@ int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel,
 	desc.flags = VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED;
 	desc.dataoffset8 = descsize >> 3; /* in 8-bytes granularity */
 	desc.length8 = (u16)(packetlen_aligned >> 3);
-	desc.transactionid = requestid;
+	desc.transactionid = VMBUS_RQST_ERROR; /* will be updated in hv_ringbuffer_write() */
 	desc.reserved = 0;
 	desc.rangecount = pagecount;
 
@@ -956,7 +1030,7 @@ int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel,
 	bufferlist[2].iov_base = &aligned_data;
 	bufferlist[2].iov_len = (packetlen_aligned - packetlen);
 
-	return hv_ringbuffer_write(channel, bufferlist, 3);
+	return hv_ringbuffer_write(channel, bufferlist, 3, requestid);
 }
 EXPORT_SYMBOL_GPL(vmbus_sendpacket_pagebuffer);
 
@@ -983,7 +1057,7 @@ int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel,
 	desc->flags = VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED;
 	desc->dataoffset8 = desc_size >> 3; /* in 8-bytes granularity */
 	desc->length8 = (u16)(packetlen_aligned >> 3);
-	desc->transactionid = requestid;
+	desc->transactionid = VMBUS_RQST_ERROR; /* will be updated in hv_ringbuffer_write() */
 	desc->reserved = 0;
 	desc->rangecount = 1;
 
@@ -994,7 +1068,7 @@ int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel,
 	bufferlist[2].iov_base = &aligned_data;
 	bufferlist[2].iov_len = (packetlen_aligned - packetlen);
 
-	return hv_ringbuffer_write(channel, bufferlist, 3);
+	return hv_ringbuffer_write(channel, bufferlist, 3, requestid);
 }
 EXPORT_SYMBOL_GPL(vmbus_sendpacket_mpb_desc);
 
@@ -1042,3 +1116,91 @@ int vmbus_recvpacket_raw(struct vmbus_channel *channel, void *buffer,
 				  buffer_actual_len, requestid, true);
 }
 EXPORT_SYMBOL_GPL(vmbus_recvpacket_raw);
+
+/*
+ * vmbus_next_request_id - Returns a new request id. It is also
+ * the index at which the guest memory address is stored.
+ * Uses a spin lock to avoid race conditions.
+ * @rqstor: Pointer to the requestor struct
+ * @rqst_add: Guest memory address to be stored in the array
+ */
+u64 vmbus_next_request_id(struct vmbus_requestor *rqstor, u64 rqst_addr)
+{
+	unsigned long flags;
+	u64 current_id;
+	const struct vmbus_channel *channel =
+		container_of(rqstor, const struct vmbus_channel, requestor);
+
+	/* Check rqstor has been initialized */
+	if (!channel->rqstor_size)
+		return VMBUS_NO_RQSTOR;
+
+	spin_lock_irqsave(&rqstor->req_lock, flags);
+	current_id = rqstor->next_request_id;
+
+	/* Requestor array is full */
+	if (current_id >= rqstor->size) {
+		spin_unlock_irqrestore(&rqstor->req_lock, flags);
+		return VMBUS_RQST_ERROR;
+	}
+
+	rqstor->next_request_id = rqstor->req_arr[current_id];
+	rqstor->req_arr[current_id] = rqst_addr;
+
+	/* The already held spin lock provides atomicity */
+	bitmap_set(rqstor->req_bitmap, current_id, 1);
+
+	spin_unlock_irqrestore(&rqstor->req_lock, flags);
+
+	/*
+	 * Cannot return an ID of 0, which is reserved for an unsolicited
+	 * message from Hyper-V.
+	 */
+	return current_id + 1;
+}
+EXPORT_SYMBOL_GPL(vmbus_next_request_id);
+
+/*
+ * vmbus_request_addr - Returns the memory address stored at @trans_id
+ * in @rqstor. Uses a spin lock to avoid race conditions.
+ * @rqstor: Pointer to the requestor struct
+ * @trans_id: Request id sent back from Hyper-V. Becomes the requestor's
+ * next request id.
+ */
+u64 vmbus_request_addr(struct vmbus_requestor *rqstor, u64 trans_id)
+{
+	unsigned long flags;
+	u64 req_addr;
+	const struct vmbus_channel *channel =
+		container_of(rqstor, const struct vmbus_channel, requestor);
+
+	/* Check rqstor has been initialized */
+	if (!channel->rqstor_size)
+		return VMBUS_NO_RQSTOR;
+
+	/* Hyper-V can send an unsolicited message with ID of 0 */
+	if (!trans_id)
+		return trans_id;
+
+	spin_lock_irqsave(&rqstor->req_lock, flags);
+
+	/* Data corresponding to trans_id is stored at trans_id - 1 */
+	trans_id--;
+
+	/* Invalid trans_id */
+	if (trans_id >= rqstor->size || !test_bit(trans_id, rqstor->req_bitmap)) {
+		spin_unlock_irqrestore(&rqstor->req_lock, flags);
+		return VMBUS_RQST_ERROR;
+	}
+
+	req_addr = rqstor->req_arr[trans_id];
+	rqstor->req_arr[trans_id] = rqstor->next_request_id;
+	rqstor->next_request_id = trans_id;
+
+	/* The already held spin lock provides atomicity */
+	bitmap_clear(rqstor->req_bitmap, trans_id, 1);
+
+	spin_unlock_irqrestore(&rqstor->req_lock, flags);
+	return req_addr;
+}
+EXPORT_SYMBOL_GPL(vmbus_request_addr);
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index 40e2b9f91163..02f3e8988836 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -179,7 +179,8 @@ int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info,
 void hv_ringbuffer_cleanup(struct hv_ring_buffer_info *ring_info);
 
 int hv_ringbuffer_write(struct vmbus_channel *channel,
-			const struct kvec *kv_list, u32 kv_count);
+			const struct kvec *kv_list, u32 kv_count,
+			u64 requestid);
 
 int hv_ringbuffer_read(struct vmbus_channel *channel,
 		       void *buffer, u32 buflen, u32 *buffer_actual_len,
diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c
index 356e22159e83..35833d4d1a1d 100644
--- a/drivers/hv/ring_buffer.c
+++ b/drivers/hv/ring_buffer.c
@@ -248,7 +248,8 @@ void hv_ringbuffer_cleanup(struct hv_ring_buffer_info *ring_info)
 
 /* Write to the ring buffer. */
 int hv_ringbuffer_write(struct vmbus_channel *channel,
-			const struct kvec *kv_list, u32 kv_count)
+			const struct kvec *kv_list, u32 kv_count,
+			u64 requestid)
 {
 	int i;
 	u32 bytes_avail_towrite;
@@ -258,6 +259,8 @@ int hv_ringbuffer_write(struct vmbus_channel *channel,
 	u64 prev_indices;
 	unsigned long flags;
 	struct hv_ring_buffer_info *outring_info = &channel->outbound;
+	struct vmpacket_descriptor *desc = kv_list[0].iov_base;
+	u64 rqst_id = VMBUS_NO_RQSTOR;
 
 	if (channel->rescind)
 		return -ENODEV;
@@ -300,6 +303,23 @@ int hv_ringbuffer_write(struct vmbus_channel *channel,
 						     kv_list[i].iov_len);
 	}
 
+	/*
+	 * Allocate the request ID after the data has been copied into the
+	 * ring buffer.  Once this request ID is allocated, the completion
+	 * path could find the data and free it.
+	 */
+
+	if (desc->flags == VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED) {
+		rqst_id = vmbus_next_request_id(&channel->requestor, requestid);
+		if (rqst_id == VMBUS_RQST_ERROR) {
+			spin_unlock_irqrestore(&outring_info->ring_lock, flags);
+			pr_err("No request id available\n");
+			return -EAGAIN;
+		}
+	}
+	desc = hv_get_ring_buffer(outring_info) + old_write;
+	desc->trans_id = (rqst_id == VMBUS_NO_RQSTOR) ? requestid : rqst_id;
+
 	/* Set previous packet start */
 	prev_indices = hv_get_ring_bufferindices(outring_info);
 
@@ -319,8 +339,13 @@ int hv_ringbuffer_write(struct vmbus_channel *channel,
 
 	hv_signal_on_write(old_write, channel);
 
-	if (channel->rescind)
+	if (channel->rescind) {
+		if (rqst_id != VMBUS_NO_RQSTOR) {
+			/* Reclaim request ID to avoid leak of IDs */
+			vmbus_request_addr(&channel->requestor, rqst_id);
+		}
 		return -ENODEV;
+	}
 
 	return 0;
 }
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 1ce131f29f3b..5b6d5c4e3711 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -764,6 +764,22 @@ enum vmbus_device_type {
 	HV_UNKNOWN,
 };
 
+/*
+ * Provides request ids for VMBus. Encapsulates guest memory
+ * addresses and stores the next available slot in req_arr
+ * to generate new ids in constant time.
+ */
+struct vmbus_requestor {
+	u64 *req_arr;
+	unsigned long *req_bitmap; /* is a given slot available? */
+	u32 size;
+	u64 next_request_id;
+	spinlock_t req_lock; /* provides atomicity */
+};
+
+#define VMBUS_NO_RQSTOR U64_MAX
+#define VMBUS_RQST_ERROR (U64_MAX - 1)
+
 struct vmbus_device {
 	u16  dev_type;
 	guid_t guid;
@@ -988,8 +1004,14 @@ struct vmbus_channel {
 	u32 fuzz_testing_interrupt_delay;
 	u32 fuzz_testing_message_delay;
 
+	/* request/transaction ids for VMBus */
+	struct vmbus_requestor requestor;
+	u32 rqstor_size;
 };
 
+u64 vmbus_next_request_id(struct vmbus_requestor *rqstor, u64 rqst_addr);
+u64 vmbus_request_addr(struct vmbus_requestor *rqstor, u64 trans_id);
+
 static inline bool is_hvsock_channel(const struct vmbus_channel *c)
 {
 	return !!(c->offermsg.offer.chn_flags &
-- 
cgit v1.2.3


From 4d18fcc95f50950a99bd940d4e61a983f91d267a Mon Sep 17 00:00:00 2001
From: Andres Beltran <lkmlabelt@gmail.com>
Date: Mon, 9 Nov 2020 11:04:02 +0100
Subject: hv_netvsc: Use vmbus_requestor to generate transaction IDs for VMBus
 hardening

Currently, pointers to guest memory are passed to Hyper-V as
transaction IDs in netvsc. In the face of errors or malicious
behavior in Hyper-V, netvsc should not expose or trust the transaction
IDs returned by Hyper-V to be valid guest memory addresses. Instead,
use small integers generated by vmbus_requestor as requests
(transaction) IDs.

Signed-off-by: Andres Beltran <lkmlabelt@gmail.com>
Co-developed-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com>
Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Wei Liu <wei.liu@kernel.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: netdev@vger.kernel.org
Link: https://lore.kernel.org/r/20201109100402.8946-4-parri.andrea@gmail.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 drivers/net/hyperv/hyperv_net.h   | 13 +++++++++++++
 drivers/net/hyperv/netvsc.c       | 22 ++++++++++++++++------
 drivers/net/hyperv/rndis_filter.c |  1 +
 include/linux/hyperv.h            |  1 +
 4 files changed, 31 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index a0f338cf1424..2a87cfa27ac0 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -847,6 +847,19 @@ struct nvsp_message {
 
 #define NETVSC_XDP_HDRM 256
 
+#define NETVSC_MIN_OUT_MSG_SIZE (sizeof(struct vmpacket_descriptor) + \
+				 sizeof(struct nvsp_message))
+#define NETVSC_MIN_IN_MSG_SIZE sizeof(struct vmpacket_descriptor)
+
+/* Estimated requestor size:
+ * out_ring_size/min_out_msg_size + in_ring_size/min_in_msg_size
+ */
+static inline u32 netvsc_rqstor_size(unsigned long ringbytes)
+{
+	return ringbytes / NETVSC_MIN_OUT_MSG_SIZE +
+		ringbytes / NETVSC_MIN_IN_MSG_SIZE;
+}
+
 #define NETVSC_XFER_HEADER_SIZE(rng_cnt) \
 		(offsetof(struct vmtransfer_page_packet_header, ranges) + \
 		(rng_cnt) * sizeof(struct vmtransfer_page_range))
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 0c3de94b5178..4dbc0055aed0 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -50,7 +50,7 @@ void netvsc_switch_datapath(struct net_device *ndev, bool vf)
 
 	vmbus_sendpacket(dev->channel, init_pkt,
 			       sizeof(struct nvsp_message),
-			       (unsigned long)init_pkt,
+			       VMBUS_RQST_ID_NO_RESPONSE,
 			       VM_PKT_DATA_INBAND, 0);
 }
 
@@ -163,7 +163,7 @@ static void netvsc_revoke_recv_buf(struct hv_device *device,
 		ret = vmbus_sendpacket(device->channel,
 				       revoke_packet,
 				       sizeof(struct nvsp_message),
-				       (unsigned long)revoke_packet,
+				       VMBUS_RQST_ID_NO_RESPONSE,
 				       VM_PKT_DATA_INBAND, 0);
 		/* If the failure is because the channel is rescinded;
 		 * ignore the failure since we cannot send on a rescinded
@@ -213,7 +213,7 @@ static void netvsc_revoke_send_buf(struct hv_device *device,
 		ret = vmbus_sendpacket(device->channel,
 				       revoke_packet,
 				       sizeof(struct nvsp_message),
-				       (unsigned long)revoke_packet,
+				       VMBUS_RQST_ID_NO_RESPONSE,
 				       VM_PKT_DATA_INBAND, 0);
 
 		/* If the failure is because the channel is rescinded;
@@ -557,7 +557,7 @@ static int negotiate_nvsp_ver(struct hv_device *device,
 
 	ret = vmbus_sendpacket(device->channel, init_packet,
 				sizeof(struct nvsp_message),
-				(unsigned long)init_packet,
+				VMBUS_RQST_ID_NO_RESPONSE,
 				VM_PKT_DATA_INBAND, 0);
 
 	return ret;
@@ -614,7 +614,7 @@ static int netvsc_connect_vsp(struct hv_device *device,
 	/* Send the init request */
 	ret = vmbus_sendpacket(device->channel, init_packet,
 				sizeof(struct nvsp_message),
-				(unsigned long)init_packet,
+				VMBUS_RQST_ID_NO_RESPONSE,
 				VM_PKT_DATA_INBAND, 0);
 	if (ret != 0)
 		goto cleanup;
@@ -695,10 +695,19 @@ static void netvsc_send_tx_complete(struct net_device *ndev,
 				    const struct vmpacket_descriptor *desc,
 				    int budget)
 {
-	struct sk_buff *skb = (struct sk_buff *)(unsigned long)desc->trans_id;
 	struct net_device_context *ndev_ctx = netdev_priv(ndev);
+	struct sk_buff *skb;
 	u16 q_idx = 0;
 	int queue_sends;
+	u64 cmd_rqst;
+
+	cmd_rqst = vmbus_request_addr(&channel->requestor, (u64)desc->trans_id);
+	if (cmd_rqst == VMBUS_RQST_ERROR) {
+		netdev_err(ndev, "Incorrect transaction id\n");
+		return;
+	}
+
+	skb = (struct sk_buff *)(unsigned long)cmd_rqst;
 
 	/* Notify the layer above us */
 	if (likely(skb)) {
@@ -1520,6 +1529,7 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device,
 		       netvsc_poll, NAPI_POLL_WEIGHT);
 
 	/* Open the channel */
+	device->channel->rqstor_size = netvsc_rqstor_size(netvsc_ring_bytes);
 	ret = vmbus_open(device->channel, netvsc_ring_bytes,
 			 netvsc_ring_bytes,  NULL, 0,
 			 netvsc_channel_cb, net_device->chan_table);
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index b22e47bcfeca..6ae43319ece6 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -1172,6 +1172,7 @@ static void netvsc_sc_open(struct vmbus_channel *new_sc)
 	/* Set the channel before opening.*/
 	nvchan->channel = new_sc;
 
+	new_sc->rqstor_size = netvsc_rqstor_size(netvsc_ring_bytes);
 	ret = vmbus_open(new_sc, netvsc_ring_bytes,
 			 netvsc_ring_bytes, NULL, 0,
 			 netvsc_channel_cb, nvchan);
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 5b6d5c4e3711..5ddb479c4d4c 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -779,6 +779,7 @@ struct vmbus_requestor {
 
 #define VMBUS_NO_RQSTOR U64_MAX
 #define VMBUS_RQST_ERROR (U64_MAX - 1)
+#define VMBUS_RQST_ID_NO_RESPONSE (U64_MAX - 2)
 
 struct vmbus_device {
 	u16  dev_type;
-- 
cgit v1.2.3


From f97bb5272d9e95d400d6c8643ebb146b3e3e7842 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 17 Nov 2020 09:08:41 +0100
Subject: sched: Fix data-race in wakeup

Mel reported that on some ARM64 platforms loadavg goes bananas and
Will tracked it down to the following race:

  CPU0					CPU1

  schedule()
    prev->sched_contributes_to_load = X;
    deactivate_task(prev);

					try_to_wake_up()
					  if (p->on_rq &&) // false
					  if (smp_load_acquire(&p->on_cpu) && // true
					      ttwu_queue_wakelist())
					        p->sched_remote_wakeup = Y;

    smp_store_release(prev->on_cpu, 0);

where both p->sched_contributes_to_load and p->sched_remote_wakeup are
in the same word, and thus the stores X and Y race (and can clobber
one another's data).

Whereas prior to commit c6e7bd7afaeb ("sched/core: Optimize ttwu()
spinning on p->on_cpu") the p->on_cpu handoff serialized access to
p->sched_remote_wakeup (just as it still does with
p->sched_contributes_to_load) that commit broke that by calling
ttwu_queue_wakelist() with p->on_cpu != 0.

However, due to

  p->XXX = X			ttwu()
  schedule()			  if (p->on_rq && ...) // false
    smp_mb__after_spinlock()	  if (smp_load_acquire(&p->on_cpu) &&
    deactivate_task()		      ttwu_queue_wakelist())
      p->on_rq = 0;		        p->sched_remote_wakeup = Y;

We can be sure any 'current' store is complete and 'current' is
guaranteed asleep. Therefore we can move p->sched_remote_wakeup into
the current flags word.

Note: while the observed failure was loadavg accounting gone wrong due
to ttwu() cobbering p->sched_contributes_to_load, the reverse problem
is also possible where schedule() clobbers p->sched_remote_wakeup,
this could result in enqueue_entity() wrecking ->vruntime and causing
scheduling artifacts.

Fixes: c6e7bd7afaeb ("sched/core: Optimize ttwu() spinning on p->on_cpu")
Reported-by: Mel Gorman <mgorman@techsingularity.net>
Debugged-by: Will Deacon <will@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20201117083016.GK3121392@hirez.programming.kicks-ass.net
---
 include/linux/sched.h | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index d383cf09e78f..0e91b451d2a2 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -769,7 +769,6 @@ struct task_struct {
 	unsigned			sched_reset_on_fork:1;
 	unsigned			sched_contributes_to_load:1;
 	unsigned			sched_migrated:1;
-	unsigned			sched_remote_wakeup:1;
 #ifdef CONFIG_PSI
 	unsigned			sched_psi_wake_requeue:1;
 #endif
@@ -779,6 +778,21 @@ struct task_struct {
 
 	/* Unserialized, strictly 'current' */
 
+	/*
+	 * This field must not be in the scheduler word above due to wakelist
+	 * queueing no longer being serialized by p->on_cpu. However:
+	 *
+	 * p->XXX = X;			ttwu()
+	 * schedule()			  if (p->on_rq && ..) // false
+	 *   smp_mb__after_spinlock();	  if (smp_load_acquire(&p->on_cpu) && //true
+	 *   deactivate_task()		      ttwu_queue_wakelist())
+	 *     p->on_rq = 0;			p->sched_remote_wakeup = Y;
+	 *
+	 * guarantees all stores of 'current' are visible before
+	 * ->sched_remote_wakeup gets used, so it can be in this word.
+	 */
+	unsigned			sched_remote_wakeup:1;
+
 	/* Bit to tell LSMs we're in execve(): */
 	unsigned			in_execve:1;
 	unsigned			in_iowait:1;
-- 
cgit v1.2.3


From 2279f540ea7d05f22d2f0c4224319330228586bc Mon Sep 17 00:00:00 2001
From: Juri Lelli <juri.lelli@redhat.com>
Date: Tue, 17 Nov 2020 07:14:32 +0100
Subject: sched/deadline: Fix priority inheritance with multiple scheduling
 classes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Glenn reported that "an application [he developed produces] a BUG in
deadline.c when a SCHED_DEADLINE task contends with CFS tasks on nested
PTHREAD_PRIO_INHERIT mutexes.  I believe the bug is triggered when a CFS
task that was boosted by a SCHED_DEADLINE task boosts another CFS task
(nested priority inheritance).

 ------------[ cut here ]------------
 kernel BUG at kernel/sched/deadline.c:1462!
 invalid opcode: 0000 [#1] PREEMPT SMP
 CPU: 12 PID: 19171 Comm: dl_boost_bug Tainted: ...
 Hardware name: ...
 RIP: 0010:enqueue_task_dl+0x335/0x910
 Code: ...
 RSP: 0018:ffffc9000c2bbc68 EFLAGS: 00010002
 RAX: 0000000000000009 RBX: ffff888c0af94c00 RCX: ffffffff81e12500
 RDX: 000000000000002e RSI: ffff888c0af94c00 RDI: ffff888c10b22600
 RBP: ffffc9000c2bbd08 R08: 0000000000000009 R09: 0000000000000078
 R10: ffffffff81e12440 R11: ffffffff81e1236c R12: ffff888bc8932600
 R13: ffff888c0af94eb8 R14: ffff888c10b22600 R15: ffff888bc8932600
 FS:  00007fa58ac55700(0000) GS:ffff888c10b00000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 00007fa58b523230 CR3: 0000000bf44ab003 CR4: 00000000007606e0
 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
 PKRU: 55555554
 Call Trace:
  ? intel_pstate_update_util_hwp+0x13/0x170
  rt_mutex_setprio+0x1cc/0x4b0
  task_blocks_on_rt_mutex+0x225/0x260
  rt_spin_lock_slowlock_locked+0xab/0x2d0
  rt_spin_lock_slowlock+0x50/0x80
  hrtimer_grab_expiry_lock+0x20/0x30
  hrtimer_cancel+0x13/0x30
  do_nanosleep+0xa0/0x150
  hrtimer_nanosleep+0xe1/0x230
  ? __hrtimer_init_sleeper+0x60/0x60
  __x64_sys_nanosleep+0x8d/0xa0
  do_syscall_64+0x4a/0x100
  entry_SYSCALL_64_after_hwframe+0x49/0xbe
 RIP: 0033:0x7fa58b52330d
 ...
 ---[ end trace 0000000000000002 ]—

He also provided a simple reproducer creating the situation below:

 So the execution order of locking steps are the following
 (N1 and N2 are non-deadline tasks. D1 is a deadline task. M1 and M2
 are mutexes that are enabled * with priority inheritance.)

 Time moves forward as this timeline goes down:

 N1              N2               D1
 |               |                |
 |               |                |
 Lock(M1)        |                |
 |               |                |
 |             Lock(M2)           |
 |               |                |
 |               |              Lock(M2)
 |               |                |
 |             Lock(M1)           |
 |             (!!bug triggered!) |

Daniel reported a similar situation as well, by just letting ksoftirqd
run with DEADLINE (and eventually block on a mutex).

Problem is that boosted entities (Priority Inheritance) use static
DEADLINE parameters of the top priority waiter. However, there might be
cases where top waiter could be a non-DEADLINE entity that is currently
boosted by a DEADLINE entity from a different lock chain (i.e., nested
priority chains involving entities of non-DEADLINE classes). In this
case, top waiter static DEADLINE parameters could be null (initialized
to 0 at fork()) and replenish_dl_entity() would hit a BUG().

Fix this by keeping track of the original donor and using its parameters
when a task is boosted.

Reported-by: Glenn Elliott <glenn@aurora.tech>
Reported-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Link: https://lkml.kernel.org/r/20201117061432.517340-1-juri.lelli@redhat.com
---
 include/linux/sched.h   | 10 ++++-
 kernel/sched/core.c     | 11 +++---
 kernel/sched/deadline.c | 97 +++++++++++++++++++++++++++----------------------
 3 files changed, 68 insertions(+), 50 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0e91b451d2a2..095fdec07b38 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -551,7 +551,6 @@ struct sched_dl_entity {
 	 * overruns.
 	 */
 	unsigned int			dl_throttled      : 1;
-	unsigned int			dl_boosted        : 1;
 	unsigned int			dl_yielded        : 1;
 	unsigned int			dl_non_contending : 1;
 	unsigned int			dl_overrun	  : 1;
@@ -570,6 +569,15 @@ struct sched_dl_entity {
 	 * time.
 	 */
 	struct hrtimer inactive_timer;
+
+#ifdef CONFIG_RT_MUTEXES
+	/*
+	 * Priority Inheritance. When a DEADLINE scheduling entity is boosted
+	 * pi_se points to the donor, otherwise points to the dl_se it belongs
+	 * to (the original one/itself).
+	 */
+	struct sched_dl_entity *pi_se;
+#endif
 };
 
 #ifdef CONFIG_UCLAMP_TASK
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9f0ebfb0d17b..e7e453492cff 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4912,20 +4912,21 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
 		if (!dl_prio(p->normal_prio) ||
 		    (pi_task && dl_prio(pi_task->prio) &&
 		     dl_entity_preempt(&pi_task->dl, &p->dl))) {
-			p->dl.dl_boosted = 1;
+			p->dl.pi_se = pi_task->dl.pi_se;
 			queue_flag |= ENQUEUE_REPLENISH;
-		} else
-			p->dl.dl_boosted = 0;
+		} else {
+			p->dl.pi_se = &p->dl;
+		}
 		p->sched_class = &dl_sched_class;
 	} else if (rt_prio(prio)) {
 		if (dl_prio(oldprio))
-			p->dl.dl_boosted = 0;
+			p->dl.pi_se = &p->dl;
 		if (oldprio < prio)
 			queue_flag |= ENQUEUE_HEAD;
 		p->sched_class = &rt_sched_class;
 	} else {
 		if (dl_prio(oldprio))
-			p->dl.dl_boosted = 0;
+			p->dl.pi_se = &p->dl;
 		if (rt_prio(oldprio))
 			p->rt.timeout = 0;
 		p->sched_class = &fair_sched_class;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 6d93f4518734..949bc5c083c1 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -43,6 +43,28 @@ static inline int on_dl_rq(struct sched_dl_entity *dl_se)
 	return !RB_EMPTY_NODE(&dl_se->rb_node);
 }
 
+#ifdef CONFIG_RT_MUTEXES
+static inline struct sched_dl_entity *pi_of(struct sched_dl_entity *dl_se)
+{
+	return dl_se->pi_se;
+}
+
+static inline bool is_dl_boosted(struct sched_dl_entity *dl_se)
+{
+	return pi_of(dl_se) != dl_se;
+}
+#else
+static inline struct sched_dl_entity *pi_of(struct sched_dl_entity *dl_se)
+{
+	return dl_se;
+}
+
+static inline bool is_dl_boosted(struct sched_dl_entity *dl_se)
+{
+	return false;
+}
+#endif
+
 #ifdef CONFIG_SMP
 static inline struct dl_bw *dl_bw_of(int i)
 {
@@ -698,7 +720,7 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se)
 	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
 	struct rq *rq = rq_of_dl_rq(dl_rq);
 
-	WARN_ON(dl_se->dl_boosted);
+	WARN_ON(is_dl_boosted(dl_se));
 	WARN_ON(dl_time_before(rq_clock(rq), dl_se->deadline));
 
 	/*
@@ -736,21 +758,20 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se)
  * could happen are, typically, a entity voluntarily trying to overcome its
  * runtime, or it just underestimated it during sched_setattr().
  */
-static void replenish_dl_entity(struct sched_dl_entity *dl_se,
-				struct sched_dl_entity *pi_se)
+static void replenish_dl_entity(struct sched_dl_entity *dl_se)
 {
 	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
 	struct rq *rq = rq_of_dl_rq(dl_rq);
 
-	BUG_ON(pi_se->dl_runtime <= 0);
+	BUG_ON(pi_of(dl_se)->dl_runtime <= 0);
 
 	/*
 	 * This could be the case for a !-dl task that is boosted.
 	 * Just go with full inherited parameters.
 	 */
 	if (dl_se->dl_deadline == 0) {
-		dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
-		dl_se->runtime = pi_se->dl_runtime;
+		dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline;
+		dl_se->runtime = pi_of(dl_se)->dl_runtime;
 	}
 
 	if (dl_se->dl_yielded && dl_se->runtime > 0)
@@ -763,8 +784,8 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
 	 * arbitrary large.
 	 */
 	while (dl_se->runtime <= 0) {
-		dl_se->deadline += pi_se->dl_period;
-		dl_se->runtime += pi_se->dl_runtime;
+		dl_se->deadline += pi_of(dl_se)->dl_period;
+		dl_se->runtime += pi_of(dl_se)->dl_runtime;
 	}
 
 	/*
@@ -778,8 +799,8 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
 	 */
 	if (dl_time_before(dl_se->deadline, rq_clock(rq))) {
 		printk_deferred_once("sched: DL replenish lagged too much\n");
-		dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
-		dl_se->runtime = pi_se->dl_runtime;
+		dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline;
+		dl_se->runtime = pi_of(dl_se)->dl_runtime;
 	}
 
 	if (dl_se->dl_yielded)
@@ -812,8 +833,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
  * task with deadline equal to period this is the same of using
  * dl_period instead of dl_deadline in the equation above.
  */
-static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
-			       struct sched_dl_entity *pi_se, u64 t)
+static bool dl_entity_overflow(struct sched_dl_entity *dl_se, u64 t)
 {
 	u64 left, right;
 
@@ -835,9 +855,9 @@ static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
 	 * of anything below microseconds resolution is actually fiction
 	 * (but still we want to give the user that illusion >;).
 	 */
-	left = (pi_se->dl_deadline >> DL_SCALE) * (dl_se->runtime >> DL_SCALE);
+	left = (pi_of(dl_se)->dl_deadline >> DL_SCALE) * (dl_se->runtime >> DL_SCALE);
 	right = ((dl_se->deadline - t) >> DL_SCALE) *
-		(pi_se->dl_runtime >> DL_SCALE);
+		(pi_of(dl_se)->dl_runtime >> DL_SCALE);
 
 	return dl_time_before(right, left);
 }
@@ -922,24 +942,23 @@ static inline bool dl_is_implicit(struct sched_dl_entity *dl_se)
  * Please refer to the comments update_dl_revised_wakeup() function to find
  * more about the Revised CBS rule.
  */
-static void update_dl_entity(struct sched_dl_entity *dl_se,
-			     struct sched_dl_entity *pi_se)
+static void update_dl_entity(struct sched_dl_entity *dl_se)
 {
 	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
 	struct rq *rq = rq_of_dl_rq(dl_rq);
 
 	if (dl_time_before(dl_se->deadline, rq_clock(rq)) ||
-	    dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) {
+	    dl_entity_overflow(dl_se, rq_clock(rq))) {
 
 		if (unlikely(!dl_is_implicit(dl_se) &&
 			     !dl_time_before(dl_se->deadline, rq_clock(rq)) &&
-			     !dl_se->dl_boosted)){
+			     !is_dl_boosted(dl_se))) {
 			update_dl_revised_wakeup(dl_se, rq);
 			return;
 		}
 
-		dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
-		dl_se->runtime = pi_se->dl_runtime;
+		dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline;
+		dl_se->runtime = pi_of(dl_se)->dl_runtime;
 	}
 }
 
@@ -1038,7 +1057,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 	 * The task might have been boosted by someone else and might be in the
 	 * boosting/deboosting path, its not throttled.
 	 */
-	if (dl_se->dl_boosted)
+	if (is_dl_boosted(dl_se))
 		goto unlock;
 
 	/*
@@ -1066,7 +1085,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 	 * but do not enqueue -- wait for our wakeup to do that.
 	 */
 	if (!task_on_rq_queued(p)) {
-		replenish_dl_entity(dl_se, dl_se);
+		replenish_dl_entity(dl_se);
 		goto unlock;
 	}
 
@@ -1156,7 +1175,7 @@ static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se)
 
 	if (dl_time_before(dl_se->deadline, rq_clock(rq)) &&
 	    dl_time_before(rq_clock(rq), dl_next_period(dl_se))) {
-		if (unlikely(dl_se->dl_boosted || !start_dl_timer(p)))
+		if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(p)))
 			return;
 		dl_se->dl_throttled = 1;
 		if (dl_se->runtime > 0)
@@ -1287,7 +1306,7 @@ throttle:
 			dl_se->dl_overrun = 1;
 
 		__dequeue_task_dl(rq, curr, 0);
-		if (unlikely(dl_se->dl_boosted || !start_dl_timer(curr)))
+		if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(curr)))
 			enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH);
 
 		if (!is_leftmost(curr, &rq->dl))
@@ -1481,8 +1500,7 @@ static void __dequeue_dl_entity(struct sched_dl_entity *dl_se)
 }
 
 static void
-enqueue_dl_entity(struct sched_dl_entity *dl_se,
-		  struct sched_dl_entity *pi_se, int flags)
+enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags)
 {
 	BUG_ON(on_dl_rq(dl_se));
 
@@ -1493,9 +1511,9 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se,
 	 */
 	if (flags & ENQUEUE_WAKEUP) {
 		task_contending(dl_se, flags);
-		update_dl_entity(dl_se, pi_se);
+		update_dl_entity(dl_se);
 	} else if (flags & ENQUEUE_REPLENISH) {
-		replenish_dl_entity(dl_se, pi_se);
+		replenish_dl_entity(dl_se);
 	} else if ((flags & ENQUEUE_RESTORE) &&
 		  dl_time_before(dl_se->deadline,
 				 rq_clock(rq_of_dl_rq(dl_rq_of_se(dl_se))))) {
@@ -1512,19 +1530,7 @@ static void dequeue_dl_entity(struct sched_dl_entity *dl_se)
 
 static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 {
-	struct task_struct *pi_task = rt_mutex_get_top_task(p);
-	struct sched_dl_entity *pi_se = &p->dl;
-
-	/*
-	 * Use the scheduling parameters of the top pi-waiter task if:
-	 * - we have a top pi-waiter which is a SCHED_DEADLINE task AND
-	 * - our dl_boosted is set (i.e. the pi-waiter's (absolute) deadline is
-	 *   smaller than our deadline OR we are a !SCHED_DEADLINE task getting
-	 *   boosted due to a SCHED_DEADLINE pi-waiter).
-	 * Otherwise we keep our runtime and deadline.
-	 */
-	if (pi_task && dl_prio(pi_task->normal_prio) && p->dl.dl_boosted) {
-		pi_se = &pi_task->dl;
+	if (is_dl_boosted(&p->dl)) {
 		/*
 		 * Because of delays in the detection of the overrun of a
 		 * thread's runtime, it might be the case that a thread
@@ -1557,7 +1563,7 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 		 * the throttle.
 		 */
 		p->dl.dl_throttled = 0;
-		BUG_ON(!p->dl.dl_boosted || flags != ENQUEUE_REPLENISH);
+		BUG_ON(!is_dl_boosted(&p->dl) || flags != ENQUEUE_REPLENISH);
 		return;
 	}
 
@@ -1594,7 +1600,7 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 		return;
 	}
 
-	enqueue_dl_entity(&p->dl, pi_se, flags);
+	enqueue_dl_entity(&p->dl, flags);
 
 	if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
 		enqueue_pushable_dl_task(rq, p);
@@ -2787,11 +2793,14 @@ void __dl_clear_params(struct task_struct *p)
 	dl_se->dl_bw			= 0;
 	dl_se->dl_density		= 0;
 
-	dl_se->dl_boosted		= 0;
 	dl_se->dl_throttled		= 0;
 	dl_se->dl_yielded		= 0;
 	dl_se->dl_non_contending	= 0;
 	dl_se->dl_overrun		= 0;
+
+#ifdef CONFIG_RT_MUTEXES
+	dl_se->pi_se			= dl_se;
+#endif
 }
 
 bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr)
-- 
cgit v1.2.3


From 95bb7c42ac8a94ce3d0eb059ad64430390351ccb Mon Sep 17 00:00:00 2001
From: Sean Christopherson <sean.j.christopherson@intel.com>
Date: Fri, 13 Nov 2020 00:01:21 +0200
Subject: mm: Add 'mprotect' hook to struct vm_operations_struct
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Background
==========

1. SGX enclave pages are populated with data by copying from normal memory
   via ioctl() (SGX_IOC_ENCLAVE_ADD_PAGES), which will be added later in
   this series.
2. It is desirable to be able to restrict those normal memory data sources.
   For instance, to ensure that the source data is executable before
   copying data to an executable enclave page.
3. Enclave page permissions are dynamic (just like normal permissions) and
   can be adjusted at runtime with mprotect().

This creates a problem because the original data source may have long since
vanished at the time when enclave page permissions are established (mmap()
or mprotect()).

The solution (elsewhere in this series) is to force enclave creators to
declare their paging permission *intent* up front to the ioctl().  This
intent can be immediately compared to the source data’s mapping and
rejected if necessary.

The “intent” is also stashed off for later comparison with enclave
PTEs. This ensures that any future mmap()/mprotect() operations
performed by the enclave creator or done on behalf of the enclave
can be compared with the earlier declared permissions.

Problem
=======

There is an existing mmap() hook which allows SGX to perform this
permission comparison at mmap() time.  However, there is no corresponding
->mprotect() hook.

Solution
========

Add a vm_ops->mprotect() hook so that mprotect() operations which are
inconsistent with any page's stashed intent can be rejected by the driver.

Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Co-developed-by: Jarkko Sakkinen <jarkko@kernel.org>
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Jethro Beekman <jethro@fortanix.com>
Acked-by: Dave Hansen <dave.hansen@intel.com>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Hillf Danton <hdanton@sina.com>
Cc: linux-mm@kvack.org
Link: https://lkml.kernel.org/r/20201112220135.165028-11-jarkko@kernel.org
---
 include/linux/mm.h | 7 +++++++
 mm/mprotect.c      | 7 +++++++
 2 files changed, 14 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index db6ae4d3fb4e..1813fa86b981 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -559,6 +559,13 @@ struct vm_operations_struct {
 	void (*close)(struct vm_area_struct * area);
 	int (*split)(struct vm_area_struct * area, unsigned long addr);
 	int (*mremap)(struct vm_area_struct * area);
+	/*
+	 * Called by mprotect() to make driver-specific permission
+	 * checks before mprotect() is finalised.   The VMA must not
+	 * be modified.  Returns 0 if eprotect() can proceed.
+	 */
+	int (*mprotect)(struct vm_area_struct *vma, unsigned long start,
+			unsigned long end, unsigned long newflags);
 	vm_fault_t (*fault)(struct vm_fault *vmf);
 	vm_fault_t (*huge_fault)(struct vm_fault *vmf,
 			enum page_entry_size pe_size);
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 56c02beb6041..ab709023e9aa 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -616,9 +616,16 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
 		tmp = vma->vm_end;
 		if (tmp > end)
 			tmp = end;
+
+		if (vma->vm_ops && vma->vm_ops->mprotect)
+			error = vma->vm_ops->mprotect(vma, nstart, tmp, newflags);
+		if (error)
+			goto out;
+
 		error = mprotect_fixup(vma, &prev, nstart, tmp, newflags);
 		if (error)
 			goto out;
+
 		nstart = tmp;
 
 		if (nstart < prev->vm_end)
-- 
cgit v1.2.3


From 5bdba520c1b318578caffd325515b35d187f8a0e Mon Sep 17 00:00:00 2001
From: Faiyaz Mohammed <faiyazm@codeaurora.org>
Date: Mon, 16 Nov 2020 17:05:37 +0530
Subject: mm: memblock: drop __init from memblock functions to make it inline

__init is used with inline due to which memblock wraper functions are
not getting inline.
for example:
[    0.000000] memblock_alloc_try_nid: 1490 bytes align=0x40 nid=-1 from=0x0000000000000000 max_addr=0x0000000000000000 memblock_alloc+0x20/0x2c
[    0.000000] memblock_reserve: [0x000000023f09a3c0-0x000000023f09a991] memblock_alloc_range_nid+0xc0/0x188

Dropping __init from memblock wrapper functions to make it inline and it
increase the debugability.
After:
[    0.000000] memblock_alloc_try_nid: 1490 bytes align=0x40 nid=-1 from=0x0000000000000000 max_addr=0x0000000000000000 start_kernel+0xa4/0x568
[    0.000000] memblock_reserve: [0x000000023f09a3c0-0x000000023f09a991] memblock_alloc_range_nid+0xc0/0x188

Signed-off-by: Faiyaz Mohammed <faiyazm@codeaurora.org>
Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
---
 include/linux/memblock.h | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index ef131255cedc..b93c44b9121e 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -404,13 +404,13 @@ void *memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align,
 			     phys_addr_t min_addr, phys_addr_t max_addr,
 			     int nid);
 
-static inline void * __init memblock_alloc(phys_addr_t size,  phys_addr_t align)
+static __always_inline void *memblock_alloc(phys_addr_t size, phys_addr_t align)
 {
 	return memblock_alloc_try_nid(size, align, MEMBLOCK_LOW_LIMIT,
 				      MEMBLOCK_ALLOC_ACCESSIBLE, NUMA_NO_NODE);
 }
 
-static inline void * __init memblock_alloc_raw(phys_addr_t size,
+static inline void *memblock_alloc_raw(phys_addr_t size,
 					       phys_addr_t align)
 {
 	return memblock_alloc_try_nid_raw(size, align, MEMBLOCK_LOW_LIMIT,
@@ -418,7 +418,7 @@ static inline void * __init memblock_alloc_raw(phys_addr_t size,
 					  NUMA_NO_NODE);
 }
 
-static inline void * __init memblock_alloc_from(phys_addr_t size,
+static inline void *memblock_alloc_from(phys_addr_t size,
 						phys_addr_t align,
 						phys_addr_t min_addr)
 {
@@ -426,33 +426,33 @@ static inline void * __init memblock_alloc_from(phys_addr_t size,
 				      MEMBLOCK_ALLOC_ACCESSIBLE, NUMA_NO_NODE);
 }
 
-static inline void * __init memblock_alloc_low(phys_addr_t size,
+static inline void *memblock_alloc_low(phys_addr_t size,
 					       phys_addr_t align)
 {
 	return memblock_alloc_try_nid(size, align, MEMBLOCK_LOW_LIMIT,
 				      ARCH_LOW_ADDRESS_LIMIT, NUMA_NO_NODE);
 }
 
-static inline void * __init memblock_alloc_node(phys_addr_t size,
+static inline void *memblock_alloc_node(phys_addr_t size,
 						phys_addr_t align, int nid)
 {
 	return memblock_alloc_try_nid(size, align, MEMBLOCK_LOW_LIMIT,
 				      MEMBLOCK_ALLOC_ACCESSIBLE, nid);
 }
 
-static inline void __init memblock_free_early(phys_addr_t base,
+static inline void memblock_free_early(phys_addr_t base,
 					      phys_addr_t size)
 {
 	memblock_free(base, size);
 }
 
-static inline void __init memblock_free_early_nid(phys_addr_t base,
+static inline void memblock_free_early_nid(phys_addr_t base,
 						  phys_addr_t size, int nid)
 {
 	memblock_free(base, size);
 }
 
-static inline void __init memblock_free_late(phys_addr_t base, phys_addr_t size)
+static inline void memblock_free_late(phys_addr_t base, phys_addr_t size)
 {
 	__memblock_free_late(base, size);
 }
@@ -460,7 +460,7 @@ static inline void __init memblock_free_late(phys_addr_t base, phys_addr_t size)
 /*
  * Set the allocation direction to bottom-up or top-down.
  */
-static inline void __init memblock_set_bottom_up(bool enable)
+static inline void memblock_set_bottom_up(bool enable)
 {
 	memblock.bottom_up = enable;
 }
-- 
cgit v1.2.3


From 1f90f6a835514cb69bfede0b2752b0cb7a351bbd Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 3 Nov 2020 22:45:05 +0200
Subject: resource: Group resource_overlaps() with other inline helpers

For better maintenance group resource_overlaps() with other inline helpers.
While at it, drop extra parentheses.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Hanjun Guo <guohanjun@huawei.com>
Tested-by: Hanjun Guo <guohanjun@huawei.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/ioport.h | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index 5135d4b86cd6..df4581107536 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -229,6 +229,11 @@ static inline bool resource_contains(struct resource *r1, struct resource *r2)
 	return r1->start <= r2->start && r1->end >= r2->end;
 }
 
+/* True if any part of r1 overlaps r2 */
+static inline bool resource_overlaps(struct resource *r1, struct resource *r2)
+{
+       return r1->start <= r2->end && r1->end >= r2->start;
+}
 
 /* Convenience shorthand with allocation */
 #define request_region(start,n,name)		__request_region(&ioport_resource, (start), (n), (name), 0)
@@ -296,12 +301,6 @@ extern int
 walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start, u64 end,
 		    void *arg, int (*func)(struct resource *, void *));
 
-/* True if any part of r1 overlaps r2 */
-static inline bool resource_overlaps(struct resource *r1, struct resource *r2)
-{
-       return (r1->start <= r2->end && r1->end >= r2->start);
-}
-
 struct resource *devm_request_free_mem_region(struct device *dev,
 		struct resource *base, unsigned long size);
 struct resource *request_free_mem_region(struct resource *base,
-- 
cgit v1.2.3


From 5562f35d7feabfd68cd58a1ee28b451f90e82417 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 3 Nov 2020 22:45:06 +0200
Subject: resource: Introduce resource_union() for overlapping resources

Some already present users may utilize resource_union() helper.
Provide it for them and for wider use in the future.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Hanjun Guo <guohanjun@huawei.com>
Tested-by: Hanjun Guo <guohanjun@huawei.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/ioport.h | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index df4581107536..40320eb5bc0e 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -10,9 +10,10 @@
 #define _LINUX_IOPORT_H
 
 #ifndef __ASSEMBLY__
+#include <linux/bits.h>
 #include <linux/compiler.h>
+#include <linux/minmax.h>
 #include <linux/types.h>
-#include <linux/bits.h>
 /*
  * Resources are tree-like, allowing
  * nesting etc..
@@ -235,6 +236,16 @@ static inline bool resource_overlaps(struct resource *r1, struct resource *r2)
        return r1->start <= r2->end && r1->end >= r2->start;
 }
 
+static inline bool
+resource_union(struct resource *r1, struct resource *r2, struct resource *r)
+{
+	if (!resource_overlaps(r1, r2))
+		return false;
+	r->start = min(r1->start, r2->start);
+	r->end = max(r1->end, r2->end);
+	return true;
+}
+
 /* Convenience shorthand with allocation */
 #define request_region(start,n,name)		__request_region(&ioport_resource, (start), (n), (name), 0)
 #define request_muxed_region(start,n,name)	__request_region(&ioport_resource, (start), (n), (name), IORESOURCE_MUXED)
-- 
cgit v1.2.3


From f65674df1b23cdcb6f656a14f659ffea83e7acaa Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 3 Nov 2020 22:45:07 +0200
Subject: resource: Introduce resource_intersection() for overlapping resources

There will be at least one user that can utilize new helper.
Provide the helper for future user and for wider use.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Hanjun Guo <guohanjun@huawei.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/ioport.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index 40320eb5bc0e..ece1a8db309c 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -236,6 +236,16 @@ static inline bool resource_overlaps(struct resource *r1, struct resource *r2)
        return r1->start <= r2->end && r1->end >= r2->start;
 }
 
+static inline bool
+resource_intersection(struct resource *r1, struct resource *r2, struct resource *r)
+{
+	if (!resource_overlaps(r1, r2))
+		return false;
+	r->start = max(r1->start, r2->start);
+	r->end = min(r1->end, r2->end);
+	return true;
+}
+
 static inline bool
 resource_union(struct resource *r1, struct resource *r2, struct resource *r)
 {
-- 
cgit v1.2.3


From 97f53a08cba128a724ebbbf34778d3553d559816 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Mon, 16 Nov 2020 13:21:08 -0800
Subject: net: linux/skbuff.h: combine SKB_EXTENSIONS + KCOV handling

The previous Kconfig patch led to some other build errors as
reported by the 0day bot and my own overnight build testing.

These are all in <linux/skbuff.h> when KCOV is enabled but
SKB_EXTENSIONS is not enabled, so fix those by combining those conditions
in the header file.

Fixes: 6370cc3bbd8a ("net: add kcov handle to skb extensions")
Fixes: 85ce50d337d1 ("net: kcov: don't select SKB_EXTENSIONS when there is no NET")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reported-by: kernel test robot <lkp@intel.com>
Cc: Aleksandr Nogikh <nogikh@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Acked-by: Florian Westphal <fw@strlen.de>
Link: https://lore.kernel.org/r/20201116212108.32465-1-rdunlap@infradead.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/skbuff.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 2d01b2bbb746..0a1239819fd2 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -4608,7 +4608,7 @@ static inline void skb_reset_redirect(struct sk_buff *skb)
 #endif
 }
 
-#ifdef CONFIG_KCOV
+#if IS_ENABLED(CONFIG_KCOV) && IS_ENABLED(CONFIG_SKB_EXTENSIONS)
 static inline void skb_set_kcov_handle(struct sk_buff *skb,
 				       const u64 kcov_handle)
 {
@@ -4636,7 +4636,7 @@ static inline u64 skb_get_kcov_handle(struct sk_buff *skb)
 static inline void skb_set_kcov_handle(struct sk_buff *skb,
 				       const u64 kcov_handle) { }
 static inline u64 skb_get_kcov_handle(struct sk_buff *skb) { return 0; }
-#endif /* CONFIG_KCOV */
+#endif /* CONFIG_KCOV && CONFIG_SKB_EXTENSIONS */
 
 #endif	/* __KERNEL__ */
 #endif	/* _LINUX_SKBUFF_H */
-- 
cgit v1.2.3


From 172292be01dbd6c26aba23f62e8ec090f31cdb71 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 6 Nov 2020 19:19:41 +0100
Subject: dma-mapping: remove dma_virt_ops

Now that the RDMA core deals with devices that only do DMA mapping in
lower layers properly, there is no user for dma_virt_ops and it can be
removed.

Link: https://lore.kernel.org/r/20201106181941.1878556-11-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 include/linux/dma-mapping.h |  2 --
 kernel/dma/Kconfig          |  5 ----
 kernel/dma/Makefile         |  1 -
 kernel/dma/virt.c           | 61 ---------------------------------------------
 4 files changed, 69 deletions(-)
 delete mode 100644 kernel/dma/virt.c

(limited to 'include/linux')

diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 956151052d45..2aaed35b556d 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -565,6 +565,4 @@ static inline int dma_mmap_wc(struct device *dev,
 int dma_direct_set_offset(struct device *dev, phys_addr_t cpu_start,
 		dma_addr_t dma_start, u64 size);
 
-extern const struct dma_map_ops dma_virt_ops;
-
 #endif /* _LINUX_DMA_MAPPING_H */
diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index c99de4a21458..fd2db2665fc6 100644
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@ -75,11 +75,6 @@ config ARCH_HAS_DMA_PREP_COHERENT
 config ARCH_HAS_FORCE_DMA_UNENCRYPTED
 	bool
 
-config DMA_VIRT_OPS
-	bool
-	depends on HAS_DMA
-	select DMA_OPS
-
 config SWIOTLB
 	bool
 	select NEED_DMA_MAP_STATE
diff --git a/kernel/dma/Makefile b/kernel/dma/Makefile
index dc755ab68aab..cd1d86358a7a 100644
--- a/kernel/dma/Makefile
+++ b/kernel/dma/Makefile
@@ -5,7 +5,6 @@ obj-$(CONFIG_DMA_OPS)			+= ops_helpers.o
 obj-$(CONFIG_DMA_OPS)			+= dummy.o
 obj-$(CONFIG_DMA_CMA)			+= contiguous.o
 obj-$(CONFIG_DMA_DECLARE_COHERENT)	+= coherent.o
-obj-$(CONFIG_DMA_VIRT_OPS)		+= virt.o
 obj-$(CONFIG_DMA_API_DEBUG)		+= debug.o
 obj-$(CONFIG_SWIOTLB)			+= swiotlb.o
 obj-$(CONFIG_DMA_COHERENT_POOL)		+= pool.o
diff --git a/kernel/dma/virt.c b/kernel/dma/virt.c
deleted file mode 100644
index 59d32317dd57..000000000000
--- a/kernel/dma/virt.c
+++ /dev/null
@@ -1,61 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * DMA operations that map to virtual addresses without flushing memory.
- */
-#include <linux/export.h>
-#include <linux/mm.h>
-#include <linux/dma-map-ops.h>
-#include <linux/scatterlist.h>
-
-static void *dma_virt_alloc(struct device *dev, size_t size,
-			    dma_addr_t *dma_handle, gfp_t gfp,
-			    unsigned long attrs)
-{
-	void *ret;
-
-	ret = (void *)__get_free_pages(gfp | __GFP_ZERO, get_order(size));
-	if (ret)
-		*dma_handle = (uintptr_t)ret;
-	return ret;
-}
-
-static void dma_virt_free(struct device *dev, size_t size,
-			  void *cpu_addr, dma_addr_t dma_addr,
-			  unsigned long attrs)
-{
-	free_pages((unsigned long)cpu_addr, get_order(size));
-}
-
-static dma_addr_t dma_virt_map_page(struct device *dev, struct page *page,
-				    unsigned long offset, size_t size,
-				    enum dma_data_direction dir,
-				    unsigned long attrs)
-{
-	return (uintptr_t)(page_address(page) + offset);
-}
-
-static int dma_virt_map_sg(struct device *dev, struct scatterlist *sgl,
-			   int nents, enum dma_data_direction dir,
-			   unsigned long attrs)
-{
-	int i;
-	struct scatterlist *sg;
-
-	for_each_sg(sgl, sg, nents, i) {
-		BUG_ON(!sg_page(sg));
-		sg_dma_address(sg) = (uintptr_t)sg_virt(sg);
-		sg_dma_len(sg) = sg->length;
-	}
-
-	return nents;
-}
-
-const struct dma_map_ops dma_virt_ops = {
-	.alloc			= dma_virt_alloc,
-	.free			= dma_virt_free,
-	.map_page		= dma_virt_map_page,
-	.map_sg			= dma_virt_map_sg,
-	.alloc_pages		= dma_common_alloc_pages,
-	.free_pages		= dma_common_free_pages,
-};
-EXPORT_SYMBOL(dma_virt_ops);
-- 
cgit v1.2.3


From f73659192b0bdf7bad826587b3530cef43cc048d Mon Sep 17 00:00:00 2001
From: Xie He <xie.he.0141@gmail.com>
Date: Sat, 14 Nov 2020 07:09:21 -0800
Subject: net: wan: Delete the DLCI / SDLA drivers

The DLCI driver (dlci.c) implements the Frame Relay protocol. However,
we already have another newer and better implementation of Frame Relay
provided by the HDLC_FR driver (hdlc_fr.c).

The DLCI driver's implementation of Frame Relay is used by only one
hardware driver in the kernel - the SDLA driver (sdla.c).

The SDLA driver provides Frame Relay support for the Sangoma S50x devices.
However, the vendor provides their own driver (along with their own
multi-WAN-protocol implementations including Frame Relay), called WANPIPE.
I believe most users of the hardware would use the vendor-provided WANPIPE
driver instead.

(The WANPIPE driver was even once in the kernel, but was deleted in
commit 8db60bcf3021 ("[WAN]: Remove broken and unmaintained Sangoma
drivers.") because the vendor no longer updated the in-kernel WANPIPE
driver.)

Cc: Mike McLagan <mike.mclagan@linux.org>
Signed-off-by: Xie He <xie.he.0141@gmail.com>
Link: https://lore.kernel.org/r/20201114150921.685594-1-xie.he.0141@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 CREDITS                                 |    9 -
 Documentation/networking/framerelay.rst |   44 -
 MAINTAINERS                             |    6 -
 arch/arm/configs/ixp4xx_defconfig       |    1 -
 arch/mips/configs/gpr_defconfig         |    1 -
 arch/mips/configs/mtx1_defconfig        |    1 -
 drivers/net/wan/Kconfig                 |   45 -
 drivers/net/wan/Makefile                |    2 -
 drivers/net/wan/dlci.c                  |  541 ----------
 drivers/net/wan/sdla.c                  | 1655 -------------------------------
 include/linux/if_frad.h                 |   92 --
 include/linux/sdla.h                    |  240 -----
 include/uapi/linux/if_frad.h            |  123 ---
 include/uapi/linux/sdla.h               |  117 ---
 net/socket.c                            |   25 -
 15 files changed, 2902 deletions(-)
 delete mode 100644 Documentation/networking/framerelay.rst
 delete mode 100644 drivers/net/wan/dlci.c
 delete mode 100644 drivers/net/wan/sdla.c
 delete mode 100644 include/linux/if_frad.h
 delete mode 100644 include/linux/sdla.h
 delete mode 100644 include/uapi/linux/if_frad.h
 delete mode 100644 include/uapi/linux/sdla.h

(limited to 'include/linux')

diff --git a/CREDITS b/CREDITS
index 8592e45e3932..67421adb747c 100644
--- a/CREDITS
+++ b/CREDITS
@@ -2499,15 +2499,6 @@ W: http://www.rdrop.com/users/paulmck/
 D: RCU and variants
 D: rcutorture module
 
-N: Mike McLagan
-E: mike.mclagan@linux.org
-W: http://www.invlogic.com/~mmclagan
-D: DLCI/FRAD drivers for Sangoma SDLAs
-S: Innovative Logic Corp
-S: Post Office Box 1068
-S: Laurel, Maryland 20732
-S: USA
-
 N: Bradley McLean
 E: brad@bradpc.gaylord.com
 D: Device driver hacker
diff --git a/Documentation/networking/framerelay.rst b/Documentation/networking/framerelay.rst
deleted file mode 100644
index 6d904399ec6d..000000000000
--- a/Documentation/networking/framerelay.rst
+++ /dev/null
@@ -1,44 +0,0 @@
-.. SPDX-License-Identifier: GPL-2.0
-
-================
-Frame Relay (FR)
-================
-
-Frame Relay (FR) support for linux is built into a two tiered system of device
-drivers.  The upper layer implements RFC1490 FR specification, and uses the
-Data Link Connection Identifier (DLCI) as its hardware address.  Usually these
-are assigned by your network supplier, they give you the number/numbers of
-the Virtual Connections (VC) assigned to you.
-
-Each DLCI is a point-to-point link between your machine and a remote one.
-As such, a separate device is needed to accommodate the routing.  Within the
-net-tools archives is 'dlcicfg'.  This program will communicate with the
-base "DLCI" device, and create new net devices named 'dlci00', 'dlci01'...
-The configuration script will ask you how many DLCIs you need, as well as
-how many DLCIs you want to assign to each Frame Relay Access Device (FRAD).
-
-The DLCI uses a number of function calls to communicate with the FRAD, all
-of which are stored in the FRAD's private data area.  assoc/deassoc,
-activate/deactivate and dlci_config.  The DLCI supplies a receive function
-to the FRAD to accept incoming packets.
-
-With this initial offering, only 1 FRAD driver is available.  With many thanks
-to Sangoma Technologies, David Mandelstam & Gene Kozin, the S502A, S502E &
-S508 are supported.  This driver is currently set up for only FR, but as
-Sangoma makes more firmware modules available, it can be updated to provide
-them as well.
-
-Configuration of the FRAD makes use of another net-tools program, 'fradcfg'.
-This program makes use of a configuration file (which dlcicfg can also read)
-to specify the types of boards to be configured as FRADs, as well as perform
-any board specific configuration.  The Sangoma module of fradcfg loads the
-FR firmware into the card, sets the irq/port/memory information, and provides
-an initial configuration.
-
-Additional FRAD device drivers can be added as hardware is available.
-
-At this time, the dlcicfg and fradcfg programs have not been incorporated into
-the net-tools distribution.  They can be found at ftp.invlogic.com, in
-/pub/linux.  Note that with OS/2 FTPD, you end up in /pub by default, so just
-use 'cd linux'.  v0.10 is for use on pre-2.0.3 and earlier, v0.15 is for
-pre-2.0.4 and later.
diff --git a/MAINTAINERS b/MAINTAINERS
index af9f6a3ab100..3341959af0c7 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6905,12 +6905,6 @@ S:	Maintained
 W:	http://floatingpoint.sourceforge.net/emulator/index.html
 F:	arch/x86/math-emu/
 
-FRAME RELAY DLCI/FRAD (Sangoma drivers too)
-L:	netdev@vger.kernel.org
-S:	Orphan
-F:	drivers/net/wan/dlci.c
-F:	drivers/net/wan/sdla.c
-
 FRAMEBUFFER LAYER
 M:	Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
 L:	dri-devel@lists.freedesktop.org
diff --git a/arch/arm/configs/ixp4xx_defconfig b/arch/arm/configs/ixp4xx_defconfig
index 27e7c0714b96..0d6edeb27659 100644
--- a/arch/arm/configs/ixp4xx_defconfig
+++ b/arch/arm/configs/ixp4xx_defconfig
@@ -141,7 +141,6 @@ CONFIG_HDLC_CISCO=m
 CONFIG_HDLC_FR=m
 CONFIG_HDLC_PPP=m
 CONFIG_HDLC_X25=m
-CONFIG_DLCI=m
 CONFIG_WAN_ROUTER_DRIVERS=m
 CONFIG_ATM_TCP=m
 # CONFIG_INPUT_KEYBOARD is not set
diff --git a/arch/mips/configs/gpr_defconfig b/arch/mips/configs/gpr_defconfig
index 599d5604aabe..8a921c8ac233 100644
--- a/arch/mips/configs/gpr_defconfig
+++ b/arch/mips/configs/gpr_defconfig
@@ -228,7 +228,6 @@ CONFIG_FARSYNC=m
 CONFIG_DSCC4=m
 CONFIG_DSCC4_PCISYNC=y
 CONFIG_DSCC4_PCI_RST=y
-CONFIG_DLCI=m
 CONFIG_LAPBETHER=m
 # CONFIG_INPUT_KEYBOARD is not set
 # CONFIG_INPUT_MOUSE is not set
diff --git a/arch/mips/configs/mtx1_defconfig b/arch/mips/configs/mtx1_defconfig
index dc69b054181c..30dacce94198 100644
--- a/arch/mips/configs/mtx1_defconfig
+++ b/arch/mips/configs/mtx1_defconfig
@@ -378,7 +378,6 @@ CONFIG_FARSYNC=m
 CONFIG_DSCC4=m
 CONFIG_DSCC4_PCISYNC=y
 CONFIG_DSCC4_PCI_RST=y
-CONFIG_DLCI=m
 CONFIG_LAPBETHER=m
 # CONFIG_KEYBOARD_ATKBD is not set
 CONFIG_KEYBOARD_GPIO=y
diff --git a/drivers/net/wan/Kconfig b/drivers/net/wan/Kconfig
index 2cf98a732a26..4029fde71a9e 100644
--- a/drivers/net/wan/Kconfig
+++ b/drivers/net/wan/Kconfig
@@ -321,51 +321,6 @@ config IXP4XX_HSS
 	  Say Y here if you want to use built-in HSS ports
 	  on IXP4xx processor.
 
-config DLCI
-	tristate "Frame Relay DLCI support"
-	help
-	  Support for the Frame Relay protocol.
-
-	  Frame Relay is a fast low-cost way to connect to a remote Internet
-	  access provider or to form a private wide area network. The one
-	  physical line from your box to the local "switch" (i.e. the entry
-	  point to the Frame Relay network, usually at the phone company) can
-	  carry several logical point-to-point connections to other computers
-	  connected to the Frame Relay network. For a general explanation of
-	  the protocol, check out <http://www.mplsforum.org/>.
-
-	  To use frame relay, you need supporting hardware (called FRAD) and
-	  certain programs from the net-tools package as explained in
-	  <file:Documentation/networking/framerelay.rst>.
-
-	  To compile this driver as a module, choose M here: the
-	  module will be called dlci.
-
-config DLCI_MAX
-	int "Max DLCI per device"
-	depends on DLCI
-	default "8"
-	help
-	  How many logical point-to-point frame relay connections (the
-	  identifiers of which are called DCLIs) should be handled by each
-	  of your hardware frame relay access devices.
-
-	  Go with the default.
-
-config SDLA
-	tristate "SDLA (Sangoma S502/S508) support"
-	depends on DLCI && ISA
-	help
-	  Driver for the Sangoma S502A, S502E, and S508 Frame Relay Access
-	  Devices.
-
-	  These are multi-protocol cards, but only Frame Relay is supported
-	  by the driver at this time. Please read
-	  <file:Documentation/networking/framerelay.rst>.
-
-	  To compile this driver as a module, choose M here: the
-	  module will be called sdla.
-
 # X.25 network drivers
 config LAPBETHER
 	tristate "LAPB over Ethernet driver"
diff --git a/drivers/net/wan/Makefile b/drivers/net/wan/Makefile
index 5b9dc85eae34..081666c36ca2 100644
--- a/drivers/net/wan/Makefile
+++ b/drivers/net/wan/Makefile
@@ -21,8 +21,6 @@ obj-$(CONFIG_FARSYNC)		+= farsync.o
 
 obj-$(CONFIG_LANMEDIA)		+= lmc/
 
-obj-$(CONFIG_DLCI)		+= dlci.o 
-obj-$(CONFIG_SDLA)		+= sdla.o
 obj-$(CONFIG_LAPBETHER)		+= lapbether.o
 obj-$(CONFIG_SBNI)		+= sbni.o
 obj-$(CONFIG_N2)		+= n2.o
diff --git a/drivers/net/wan/dlci.c b/drivers/net/wan/dlci.c
deleted file mode 100644
index 3ca4daf63389..000000000000
--- a/drivers/net/wan/dlci.c
+++ /dev/null
@@ -1,541 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * DLCI		Implementation of Frame Relay protocol for Linux, according to
- *		RFC 1490.  This generic device provides en/decapsulation for an
- *		underlying hardware driver.  Routes & IPs are assigned to these
- *		interfaces.  Requires 'dlcicfg' program to create usable 
- *		interfaces, the initial one, 'dlci' is for IOCTL use only.
- *
- * Version:	@(#)dlci.c	0.35	4 Jan 1997
- *
- * Author:	Mike McLagan <mike.mclagan@linux.org>
- *
- * Changes:
- *
- *		0.15	Mike Mclagan	Packet freeing, bug in kmalloc call
- *					DLCI_RET handling
- *		0.20	Mike McLagan	More conservative on which packets
- *					are returned for retry and which are
- *					are dropped.  If DLCI_RET_DROP is
- *					returned from the FRAD, the packet is
- *				 	sent back to Linux for re-transmission
- *		0.25	Mike McLagan	Converted to use SIOC IOCTL calls
- *		0.30	Jim Freeman	Fixed to allow IPX traffic
- *		0.35	Michael Elizabeth	Fixed incorrect memcpy_fromfs
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/fcntl.h>
-#include <linux/interrupt.h>
-#include <linux/ptrace.h>
-#include <linux/ioport.h>
-#include <linux/in.h>
-#include <linux/init.h>
-#include <linux/slab.h>
-#include <linux/string.h>
-#include <linux/errno.h>
-#include <linux/netdevice.h>
-#include <linux/skbuff.h>
-#include <linux/if_arp.h>
-#include <linux/if_frad.h>
-#include <linux/bitops.h>
-
-#include <net/sock.h>
-
-#include <asm/io.h>
-#include <asm/dma.h>
-#include <linux/uaccess.h>
-
-static const char version[] = "DLCI driver v0.35, 4 Jan 1997, mike.mclagan@linux.org";
-
-static LIST_HEAD(dlci_devs);
-
-static void dlci_setup(struct net_device *);
-
-/* 
- * these encapsulate the RFC 1490 requirements as well as 
- * deal with packet transmission and reception, working with
- * the upper network layers 
- */
-
-static int dlci_header(struct sk_buff *skb, struct net_device *dev, 
-		       unsigned short type, const void *daddr,
-		       const void *saddr, unsigned len)
-{
-	struct frhdr		hdr;
-	unsigned int		hlen;
-	char			*dest;
-
-	hdr.control = FRAD_I_UI;
-	switch (type)
-	{
-		case ETH_P_IP:
-			hdr.IP_NLPID = FRAD_P_IP;
-			hlen = sizeof(hdr.control) + sizeof(hdr.IP_NLPID);
-			break;
-
-		/* feel free to add other types, if necessary */
-
-		default:
-			hdr.pad = FRAD_P_PADDING;
-			hdr.NLPID = FRAD_P_SNAP;
-			memset(hdr.OUI, 0, sizeof(hdr.OUI));
-			hdr.PID = htons(type);
-			hlen = sizeof(hdr);
-			break;
-	}
-
-	dest = skb_push(skb, hlen);
-	if (!dest)
-		return 0;
-
-	memcpy(dest, &hdr, hlen);
-
-	return hlen;
-}
-
-static void dlci_receive(struct sk_buff *skb, struct net_device *dev)
-{
-	struct frhdr		*hdr;
-	int					process, header;
-
-	if (!pskb_may_pull(skb, sizeof(*hdr))) {
-		netdev_notice(dev, "invalid data no header\n");
-		dev->stats.rx_errors++;
-		kfree_skb(skb);
-		return;
-	}
-
-	hdr = (struct frhdr *) skb->data;
-	process = 0;
-	header = 0;
-	skb->dev = dev;
-
-	if (hdr->control != FRAD_I_UI)
-	{
-		netdev_notice(dev, "Invalid header flag 0x%02X\n",
-			      hdr->control);
-		dev->stats.rx_errors++;
-	}
-	else
-		switch (hdr->IP_NLPID)
-		{
-			case FRAD_P_PADDING:
-				if (hdr->NLPID != FRAD_P_SNAP)
-				{
-					netdev_notice(dev, "Unsupported NLPID 0x%02X\n",
-						      hdr->NLPID);
-					dev->stats.rx_errors++;
-					break;
-				}
-	 
-				if (hdr->OUI[0] + hdr->OUI[1] + hdr->OUI[2] != 0)
-				{
-					netdev_notice(dev, "Unsupported organizationally unique identifier 0x%02X-%02X-%02X\n",
-						      hdr->OUI[0],
-						      hdr->OUI[1],
-						      hdr->OUI[2]);
-					dev->stats.rx_errors++;
-					break;
-				}
-
-				/* at this point, it's an EtherType frame */
-				header = sizeof(struct frhdr);
-				/* Already in network order ! */
-				skb->protocol = hdr->PID;
-				process = 1;
-				break;
-
-			case FRAD_P_IP:
-				header = sizeof(hdr->control) + sizeof(hdr->IP_NLPID);
-				skb->protocol = htons(ETH_P_IP);
-				process = 1;
-				break;
-
-			case FRAD_P_SNAP:
-			case FRAD_P_Q933:
-			case FRAD_P_CLNP:
-				netdev_notice(dev, "Unsupported NLPID 0x%02X\n",
-					      hdr->pad);
-				dev->stats.rx_errors++;
-				break;
-
-			default:
-				netdev_notice(dev, "Invalid pad byte 0x%02X\n",
-					      hdr->pad);
-				dev->stats.rx_errors++;
-				break;				
-		}
-
-	if (process)
-	{
-		/* we've set up the protocol, so discard the header */
-		skb_reset_mac_header(skb);
-		skb_pull(skb, header);
-		dev->stats.rx_bytes += skb->len;
-		netif_rx(skb);
-		dev->stats.rx_packets++;
-	}
-	else
-		dev_kfree_skb(skb);
-}
-
-static netdev_tx_t dlci_transmit(struct sk_buff *skb, struct net_device *dev)
-{
-	struct dlci_local *dlp = netdev_priv(dev);
-
-	if (skb) {
-		struct netdev_queue *txq = skb_get_tx_queue(dev, skb);
-		netdev_start_xmit(skb, dlp->slave, txq, false);
-	}
-	return NETDEV_TX_OK;
-}
-
-static int dlci_config(struct net_device *dev, struct dlci_conf __user *conf, int get)
-{
-	struct dlci_conf	config;
-	struct dlci_local	*dlp;
-	struct frad_local	*flp;
-	int			err;
-
-	dlp = netdev_priv(dev);
-
-	flp = netdev_priv(dlp->slave);
-
-	if (!get)
-	{
-		if (copy_from_user(&config, conf, sizeof(struct dlci_conf)))
-			return -EFAULT;
-		if (config.flags & ~DLCI_VALID_FLAGS)
-			return -EINVAL;
-		memcpy(&dlp->config, &config, sizeof(struct dlci_conf));
-		dlp->configured = 1;
-	}
-
-	err = (*flp->dlci_conf)(dlp->slave, dev, get);
-	if (err)
-		return err;
-
-	if (get)
-	{
-		if (copy_to_user(conf, &dlp->config, sizeof(struct dlci_conf)))
-			return -EFAULT;
-	}
-
-	return 0;
-}
-
-static int dlci_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
-{
-	struct dlci_local *dlp;
-
-	if (!capable(CAP_NET_ADMIN))
-		return -EPERM;
-
-	dlp = netdev_priv(dev);
-
-	switch (cmd)
-	{
-		case DLCI_GET_SLAVE:
-			if (!*(short *)(dev->dev_addr))
-				return -EINVAL;
-
-			strncpy(ifr->ifr_slave, dlp->slave->name, sizeof(ifr->ifr_slave));
-			break;
-
-		case DLCI_GET_CONF:
-		case DLCI_SET_CONF:
-			if (!*(short *)(dev->dev_addr))
-				return -EINVAL;
-
-			return dlci_config(dev, ifr->ifr_data, cmd == DLCI_GET_CONF);
-
-		default: 
-			return -EOPNOTSUPP;
-	}
-	return 0;
-}
-
-static int dlci_change_mtu(struct net_device *dev, int new_mtu)
-{
-	struct dlci_local *dlp = netdev_priv(dev);
-
-	return dev_set_mtu(dlp->slave, new_mtu);
-}
-
-static int dlci_open(struct net_device *dev)
-{
-	struct dlci_local	*dlp;
-	struct frad_local	*flp;
-	int			err;
-
-	dlp = netdev_priv(dev);
-
-	if (!*(short *)(dev->dev_addr))
-		return -EINVAL;
-
-	if (!netif_running(dlp->slave))
-		return -ENOTCONN;
-
-	flp = netdev_priv(dlp->slave);
-	err = (*flp->activate)(dlp->slave, dev);
-	if (err)
-		return err;
-
-	netif_start_queue(dev);
-
-	return 0;
-}
-
-static int dlci_close(struct net_device *dev)
-{
-	struct dlci_local	*dlp;
-	struct frad_local	*flp;
-
-	netif_stop_queue(dev);
-
-	dlp = netdev_priv(dev);
-
-	flp = netdev_priv(dlp->slave);
-	(*flp->deactivate)(dlp->slave, dev);
-
-	return 0;
-}
-
-static int dlci_add(struct dlci_add *dlci)
-{
-	struct net_device	*master, *slave;
-	struct dlci_local	*dlp;
-	struct frad_local	*flp;
-	int			err = -EINVAL;
-
-
-	/* validate slave device */
-	slave = dev_get_by_name(&init_net, dlci->devname);
-	if (!slave)
-		return -ENODEV;
-
-	if (slave->type != ARPHRD_FRAD || netdev_priv(slave) == NULL)
-		goto err1;
-
-	/* create device name */
-	master = alloc_netdev(sizeof(struct dlci_local), "dlci%d",
-			      NET_NAME_UNKNOWN, dlci_setup);
-	if (!master) {
-		err = -ENOMEM;
-		goto err1;
-	}
-
-	/* make sure same slave not already registered */
-	rtnl_lock();
-	list_for_each_entry(dlp, &dlci_devs, list) {
-		if (dlp->slave == slave) {
-			err = -EBUSY;
-			goto err2;
-		}
-	}
-
-	*(short *)(master->dev_addr) = dlci->dlci;
-
-	dlp = netdev_priv(master);
-	dlp->slave = slave;
-	dlp->master = master;
-
-	flp = netdev_priv(slave);
-	err = (*flp->assoc)(slave, master);
-	if (err < 0)
-		goto err2;
-
-	err = register_netdevice(master);
-	if (err < 0) 
-		goto err2;
-
-	strcpy(dlci->devname, master->name);
-
-	list_add(&dlp->list, &dlci_devs);
-	rtnl_unlock();
-
-	return 0;
-
- err2:
-	rtnl_unlock();
-	free_netdev(master);
- err1:
-	dev_put(slave);
-	return err;
-}
-
-static int dlci_del(struct dlci_add *dlci)
-{
-	struct dlci_local	*dlp;
-	struct frad_local	*flp;
-	struct net_device	*master, *slave;
-	int			err;
-	bool			found = false;
-
-	rtnl_lock();
-
-	/* validate slave device */
-	master = __dev_get_by_name(&init_net, dlci->devname);
-	if (!master) {
-		err = -ENODEV;
-		goto out;
-	}
-
-	list_for_each_entry(dlp, &dlci_devs, list) {
-		if (dlp->master == master) {
-			found = true;
-			break;
-		}
-	}
-	if (!found) {
-		err = -ENODEV;
-		goto out;
-	}
-
-	if (netif_running(master)) {
-		err = -EBUSY;
-		goto out;
-	}
-
-	dlp = netdev_priv(master);
-	slave = dlp->slave;
-	flp = netdev_priv(slave);
-
-	err = (*flp->deassoc)(slave, master);
-	if (!err) {
-		list_del(&dlp->list);
-
-		unregister_netdevice(master);
-
-		dev_put(slave);
-	}
-out:
-	rtnl_unlock();
-	return err;
-}
-
-static int dlci_ioctl(unsigned int cmd, void __user *arg)
-{
-	struct dlci_add add;
-	int err;
-	
-	if (!capable(CAP_NET_ADMIN))
-		return -EPERM;
-
-	if (copy_from_user(&add, arg, sizeof(struct dlci_add)))
-		return -EFAULT;
-
-	switch (cmd)
-	{
-		case SIOCADDDLCI:
-			err = dlci_add(&add);
-
-			if (!err)
-				if (copy_to_user(arg, &add, sizeof(struct dlci_add)))
-					return -EFAULT;
-			break;
-
-		case SIOCDELDLCI:
-			err = dlci_del(&add);
-			break;
-
-		default:
-			err = -EINVAL;
-	}
-
-	return err;
-}
-
-static const struct header_ops dlci_header_ops = {
-	.create	= dlci_header,
-};
-
-static const struct net_device_ops dlci_netdev_ops = {
-	.ndo_open	= dlci_open,
-	.ndo_stop	= dlci_close,
-	.ndo_do_ioctl	= dlci_dev_ioctl,
-	.ndo_start_xmit	= dlci_transmit,
-	.ndo_change_mtu	= dlci_change_mtu,
-};
-
-static void dlci_setup(struct net_device *dev)
-{
-	struct dlci_local *dlp = netdev_priv(dev);
-
-	dev->flags		= 0;
-	dev->header_ops		= &dlci_header_ops;
-	dev->netdev_ops		= &dlci_netdev_ops;
-	dev->needs_free_netdev	= true;
-
-	dlp->receive		= dlci_receive;
-
-	dev->type		= ARPHRD_DLCI;
-	dev->hard_header_len	= sizeof(struct frhdr);
-	dev->addr_len		= sizeof(short);
-
-}
-
-/* if slave is unregistering, then cleanup master */
-static int dlci_dev_event(struct notifier_block *unused,
-			  unsigned long event, void *ptr)
-{
-	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
-
-	if (dev_net(dev) != &init_net)
-		return NOTIFY_DONE;
-
-	if (event == NETDEV_UNREGISTER) {
-		struct dlci_local *dlp;
-
-		list_for_each_entry(dlp, &dlci_devs, list) {
-			if (dlp->slave == dev) {
-				list_del(&dlp->list);
-				unregister_netdevice(dlp->master);
-				dev_put(dlp->slave);
-				break;
-			}
-		}
-	}
-	return NOTIFY_DONE;
-}
-
-static struct notifier_block dlci_notifier = {
-	.notifier_call = dlci_dev_event,
-};
-
-static int __init init_dlci(void)
-{
-	dlci_ioctl_set(dlci_ioctl);
-	register_netdevice_notifier(&dlci_notifier);
-
-	printk("%s.\n", version);
-
-	return 0;
-}
-
-static void __exit dlci_exit(void)
-{
-	struct dlci_local	*dlp, *nxt;
-	
-	dlci_ioctl_set(NULL);
-	unregister_netdevice_notifier(&dlci_notifier);
-
-	rtnl_lock();
-	list_for_each_entry_safe(dlp, nxt, &dlci_devs, list) {
-		unregister_netdevice(dlp->master);
-		dev_put(dlp->slave);
-	}
-	rtnl_unlock();
-}
-
-module_init(init_dlci);
-module_exit(dlci_exit);
-
-MODULE_AUTHOR("Mike McLagan");
-MODULE_DESCRIPTION("Frame Relay DLCI layer");
-MODULE_LICENSE("GPL");
diff --git a/drivers/net/wan/sdla.c b/drivers/net/wan/sdla.c
deleted file mode 100644
index bc2c1c7fb1a4..000000000000
--- a/drivers/net/wan/sdla.c
+++ /dev/null
@@ -1,1655 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * SDLA		An implementation of a driver for the Sangoma S502/S508 series
- *		multi-protocol PC interface card.  Initial offering is with 
- *		the DLCI driver, providing Frame Relay support for linux.
- *
- *		Global definitions for the Frame relay interface.
- *
- * Version:	@(#)sdla.c   0.30	12 Sep 1996
- *
- * Credits:	Sangoma Technologies, for the use of 2 cards for an extended
- *			period of time.
- *		David Mandelstam <dm@sangoma.com> for getting me started on 
- *			this project, and incentive to complete it.
- *		Gene Kozen <74604.152@compuserve.com> for providing me with
- *			important information about the cards.
- *
- * Author:	Mike McLagan <mike.mclagan@linux.org>
- *
- * Changes:
- *		0.15	Mike McLagan	Improved error handling, packet dropping
- *		0.20	Mike McLagan	New transmit/receive flags for config
- *					If in FR mode, don't accept packets from
- *					non DLCI devices.
- *		0.25	Mike McLagan	Fixed problem with rejecting packets
- *					from non DLCI devices.
- *		0.30	Mike McLagan	Fixed kernel panic when used with modified
- *					ifconfig
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/fcntl.h>
-#include <linux/interrupt.h>
-#include <linux/ptrace.h>
-#include <linux/ioport.h>
-#include <linux/in.h>
-#include <linux/slab.h>
-#include <linux/string.h>
-#include <linux/timer.h>
-#include <linux/errno.h>
-#include <linux/init.h>
-#include <linux/netdevice.h>
-#include <linux/skbuff.h>
-#include <linux/if_arp.h>
-#include <linux/if_frad.h>
-#include <linux/sdla.h>
-#include <linux/bitops.h>
-
-#include <asm/io.h>
-#include <asm/dma.h>
-#include <linux/uaccess.h>
-
-static const char* version = "SDLA driver v0.30, 12 Sep 1996, mike.mclagan@linux.org";
-
-static unsigned int valid_port[] = { 0x250, 0x270, 0x280, 0x300, 0x350, 0x360, 0x380, 0x390};
-
-static unsigned int valid_mem[] = {
-				    0xA0000, 0xA2000, 0xA4000, 0xA6000, 0xA8000, 0xAA000, 0xAC000, 0xAE000, 
-                                    0xB0000, 0xB2000, 0xB4000, 0xB6000, 0xB8000, 0xBA000, 0xBC000, 0xBE000,
-                                    0xC0000, 0xC2000, 0xC4000, 0xC6000, 0xC8000, 0xCA000, 0xCC000, 0xCE000,
-                                    0xD0000, 0xD2000, 0xD4000, 0xD6000, 0xD8000, 0xDA000, 0xDC000, 0xDE000,
-                                    0xE0000, 0xE2000, 0xE4000, 0xE6000, 0xE8000, 0xEA000, 0xEC000, 0xEE000}; 
-
-static DEFINE_SPINLOCK(sdla_lock);
-
-/*********************************************************
- *
- * these are the core routines that access the card itself 
- *
- *********************************************************/
-
-#define SDLA_WINDOW(dev,addr) outb((((addr) >> 13) & 0x1F), (dev)->base_addr + SDLA_REG_Z80_WINDOW)
-
-static void __sdla_read(struct net_device *dev, int addr, void *buf, short len)
-{
-	char          *temp;
-	const void    *base;
-	int           offset, bytes;
-
-	temp = buf;
-	while(len)
-	{	
-		offset = addr & SDLA_ADDR_MASK;
-		bytes = offset + len > SDLA_WINDOW_SIZE ? SDLA_WINDOW_SIZE - offset : len;
-		base = (const void *) (dev->mem_start + offset);
-
-		SDLA_WINDOW(dev, addr);
-		memcpy(temp, base, bytes);
-
-		addr += bytes;
-		temp += bytes;
-		len  -= bytes;
-	}  
-}
-
-static void sdla_read(struct net_device *dev, int addr, void *buf, short len)
-{
-	unsigned long flags;
-	spin_lock_irqsave(&sdla_lock, flags);
-	__sdla_read(dev, addr, buf, len);
-	spin_unlock_irqrestore(&sdla_lock, flags);
-}
-
-static void __sdla_write(struct net_device *dev, int addr, 
-			 const void *buf, short len)
-{
-	const char    *temp;
-	void 	      *base;
-	int           offset, bytes;
-
-	temp = buf;
-	while(len)
-	{
-		offset = addr & SDLA_ADDR_MASK;
-		bytes = offset + len > SDLA_WINDOW_SIZE ? SDLA_WINDOW_SIZE - offset : len;
-		base = (void *) (dev->mem_start + offset);
-
-		SDLA_WINDOW(dev, addr);
-		memcpy(base, temp, bytes);
-
-		addr += bytes;
-		temp += bytes;
-		len  -= bytes;
-	}
-}
-
-static void sdla_write(struct net_device *dev, int addr, 
-		       const void *buf, short len)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&sdla_lock, flags);
-	__sdla_write(dev, addr, buf, len);
-	spin_unlock_irqrestore(&sdla_lock, flags);
-}
-
-
-static void sdla_clear(struct net_device *dev)
-{
-	unsigned long flags;
-	char          *base;
-	int           len, addr, bytes;
-
-	len = 65536;	
-	addr = 0;
-	bytes = SDLA_WINDOW_SIZE;
-	base = (void *) dev->mem_start;
-
-	spin_lock_irqsave(&sdla_lock, flags);
-	while(len)
-	{
-		SDLA_WINDOW(dev, addr);
-		memset(base, 0, bytes);
-
-		addr += bytes;
-		len  -= bytes;
-	}
-	spin_unlock_irqrestore(&sdla_lock, flags);
-
-}
-
-static char sdla_byte(struct net_device *dev, int addr)
-{
-	unsigned long flags;
-	char          byte, *temp;
-
-	temp = (void *) (dev->mem_start + (addr & SDLA_ADDR_MASK));
-
-	spin_lock_irqsave(&sdla_lock, flags);
-	SDLA_WINDOW(dev, addr);
-	byte = *temp;
-	spin_unlock_irqrestore(&sdla_lock, flags);
-
-	return byte;
-}
-
-static void sdla_stop(struct net_device *dev)
-{
-	struct frad_local *flp;
-
-	flp = netdev_priv(dev);
-	switch(flp->type)
-	{
-		case SDLA_S502A:
-			outb(SDLA_S502A_HALT, dev->base_addr + SDLA_REG_CONTROL);
-			flp->state = SDLA_HALT;
-			break;
-		case SDLA_S502E:
-			outb(SDLA_HALT, dev->base_addr + SDLA_REG_Z80_CONTROL);
-			outb(SDLA_S502E_ENABLE, dev->base_addr + SDLA_REG_CONTROL);
-			flp->state = SDLA_S502E_ENABLE;
-			break;
-		case SDLA_S507:
-			flp->state &= ~SDLA_CPUEN;
-			outb(flp->state, dev->base_addr + SDLA_REG_CONTROL);
-			break;
-		case SDLA_S508:
-			flp->state &= ~SDLA_CPUEN;
-			outb(flp->state, dev->base_addr + SDLA_REG_CONTROL);
-			break;
-	}
-}
-
-static void sdla_start(struct net_device *dev)
-{
-	struct frad_local *flp;
-
-	flp = netdev_priv(dev);
-	switch(flp->type)
-	{
-		case SDLA_S502A:
-			outb(SDLA_S502A_NMI, dev->base_addr + SDLA_REG_CONTROL);
-			outb(SDLA_S502A_START, dev->base_addr + SDLA_REG_CONTROL);
-			flp->state = SDLA_S502A_START;
-			break;
-		case SDLA_S502E:
-			outb(SDLA_S502E_CPUEN, dev->base_addr + SDLA_REG_Z80_CONTROL);
-			outb(0x00, dev->base_addr + SDLA_REG_CONTROL);
-			flp->state = 0;
-			break;
-		case SDLA_S507:
-			flp->state |= SDLA_CPUEN;
-			outb(flp->state, dev->base_addr + SDLA_REG_CONTROL);
-			break;
-		case SDLA_S508:
-			flp->state |= SDLA_CPUEN;
-			outb(flp->state, dev->base_addr + SDLA_REG_CONTROL);
-			break;
-	}
-}
-
-/****************************************************
- *
- * this is used for the S502A/E cards to determine
- * the speed of the onboard CPU.  Calibration is
- * necessary for the Frame Relay code uploaded 
- * later.  Incorrect results cause timing problems
- * with link checks & status messages
- *
- ***************************************************/
-
-static int sdla_z80_poll(struct net_device *dev, int z80_addr, int jiffs, char resp1, char resp2)
-{
-	unsigned long start, done, now;
-	char          resp, *temp;
-
-	start = now = jiffies;
-	done = jiffies + jiffs;
-
-	temp = (void *)dev->mem_start;
-	temp += z80_addr & SDLA_ADDR_MASK;
-	
-	resp = ~resp1;
-	while (time_before(jiffies, done) && (resp != resp1) && (!resp2 || (resp != resp2)))
-	{
-		if (jiffies != now)
-		{
-			SDLA_WINDOW(dev, z80_addr);
-			now = jiffies;
-			resp = *temp;
-		}
-	}
-	return time_before(jiffies, done) ? jiffies - start : -1;
-}
-
-/* constants for Z80 CPU speed */
-#define Z80_READY 		'1'	/* Z80 is ready to begin */
-#define LOADER_READY 		'2'	/* driver is ready to begin */
-#define Z80_SCC_OK 		'3'	/* SCC is on board */
-#define Z80_SCC_BAD	 	'4'	/* SCC was not found */
-
-static int sdla_cpuspeed(struct net_device *dev, struct ifreq *ifr)
-{
-	int  jiffs;
-	char data;
-
-	sdla_start(dev);
-	if (sdla_z80_poll(dev, 0, 3*HZ, Z80_READY, 0) < 0)
-		return -EIO;
-
-	data = LOADER_READY;
-	sdla_write(dev, 0, &data, 1);
-
-	if ((jiffs = sdla_z80_poll(dev, 0, 8*HZ, Z80_SCC_OK, Z80_SCC_BAD)) < 0)
-		return -EIO;
-
-	sdla_stop(dev);
-	sdla_read(dev, 0, &data, 1);
-
-	if (data == Z80_SCC_BAD)
-	{
-		printk("%s: SCC bad\n", dev->name);
-		return -EIO;
-	}
-
-	if (data != Z80_SCC_OK)
-		return -EINVAL;
-
-	if (jiffs < 165)
-		ifr->ifr_mtu = SDLA_CPU_16M;
-	else if (jiffs < 220)
-		ifr->ifr_mtu = SDLA_CPU_10M;
-	else if (jiffs < 258)
-		ifr->ifr_mtu = SDLA_CPU_8M;
-	else if (jiffs < 357)
-		ifr->ifr_mtu = SDLA_CPU_7M;
-	else if (jiffs < 467)
-		ifr->ifr_mtu = SDLA_CPU_5M;
-	else
-		ifr->ifr_mtu = SDLA_CPU_3M;
- 
-	return 0;
-}
-
-/************************************************
- *
- *  Direct interaction with the Frame Relay code 
- *  starts here.
- *
- ************************************************/
-
-struct _dlci_stat 
-{
-	short dlci;
-	char  flags;
-} __packed;
-
-struct _frad_stat 
-{
-	char    flags;
-	struct _dlci_stat dlcis[SDLA_MAX_DLCI];
-};
-
-static void sdla_errors(struct net_device *dev, int cmd, int dlci, int ret, int len, void *data) 
-{
-	struct _dlci_stat *pstatus;
-	short             *pdlci;
-	int               i;
-	char              *state, line[30];
-
-	switch (ret)
-	{
-		case SDLA_RET_MODEM:
-			state = data;
-			if (*state & SDLA_MODEM_DCD_LOW)
-				netdev_info(dev, "Modem DCD unexpectedly low!\n");
-			if (*state & SDLA_MODEM_CTS_LOW)
-				netdev_info(dev, "Modem CTS unexpectedly low!\n");
-			/* I should probably do something about this! */
-			break;
-
-		case SDLA_RET_CHANNEL_OFF:
-			netdev_info(dev, "Channel became inoperative!\n");
-			/* same here */
-			break;
-
-		case SDLA_RET_CHANNEL_ON:
-			netdev_info(dev, "Channel became operative!\n");
-			/* same here */
-			break;
-
-		case SDLA_RET_DLCI_STATUS:
-			netdev_info(dev, "Status change reported by Access Node\n");
-			len /= sizeof(struct _dlci_stat);
-			for(pstatus = data, i=0;i < len;i++,pstatus++)
-			{
-				if (pstatus->flags & SDLA_DLCI_NEW)
-					state = "new";
-				else if (pstatus->flags & SDLA_DLCI_DELETED)
-					state = "deleted";
-				else if (pstatus->flags & SDLA_DLCI_ACTIVE)
-					state = "active";
-				else
-				{
-					sprintf(line, "unknown status: %02X", pstatus->flags);
-					state = line;
-				}
-				netdev_info(dev, "DLCI %i: %s\n",
-					    pstatus->dlci, state);
-				/* same here */
-			}
-			break;
-
-		case SDLA_RET_DLCI_UNKNOWN:
-			netdev_info(dev, "Received unknown DLCIs:");
-			len /= sizeof(short);
-			for(pdlci = data,i=0;i < len;i++,pdlci++)
-				pr_cont(" %i", *pdlci);
-			pr_cont("\n");
-			break;
-
-		case SDLA_RET_TIMEOUT:
-			netdev_err(dev, "Command timed out!\n");
-			break;
-
-		case SDLA_RET_BUF_OVERSIZE:
-			netdev_info(dev, "Bc/CIR overflow, acceptable size is %i\n",
-				    len);
-			break;
-
-		case SDLA_RET_BUF_TOO_BIG:
-			netdev_info(dev, "Buffer size over specified max of %i\n",
-				    len);
-			break;
-
-		case SDLA_RET_CHANNEL_INACTIVE:
-		case SDLA_RET_DLCI_INACTIVE:
-		case SDLA_RET_CIR_OVERFLOW:
-		case SDLA_RET_NO_BUFS:
-			if (cmd == SDLA_INFORMATION_WRITE)
-				break;
-			fallthrough;
-
-		default: 
-			netdev_dbg(dev, "Cmd 0x%02X generated return code 0x%02X\n",
-				   cmd, ret);
-			/* Further processing could be done here */
-			break;
-	}
-}
-
-static int sdla_cmd(struct net_device *dev, int cmd, short dlci, short flags, 
-                        void *inbuf, short inlen, void *outbuf, short *outlen)
-{
-	static struct _frad_stat status;
-	struct frad_local        *flp;
-	struct sdla_cmd          *cmd_buf;
-	unsigned long            pflags;
-	unsigned long		 jiffs;
-	int                      ret, waiting, len;
-	long                     window;
-
-	flp = netdev_priv(dev);
-	window = flp->type == SDLA_S508 ? SDLA_508_CMD_BUF : SDLA_502_CMD_BUF;
-	cmd_buf = (struct sdla_cmd *)(dev->mem_start + (window & SDLA_ADDR_MASK));
-	ret = 0;
-	len = 0;
-	jiffs = jiffies + HZ;  /* 1 second is plenty */
-
-	spin_lock_irqsave(&sdla_lock, pflags);
-	SDLA_WINDOW(dev, window);
-	cmd_buf->cmd = cmd;
-	cmd_buf->dlci = dlci;
-	cmd_buf->flags = flags;
-
-	if (inbuf)
-		memcpy(cmd_buf->data, inbuf, inlen);
-
-	cmd_buf->length = inlen;
-
-	cmd_buf->opp_flag = 1;
-	spin_unlock_irqrestore(&sdla_lock, pflags);
-
-	waiting = 1;
-	len = 0;
-	while (waiting && time_before_eq(jiffies, jiffs))
-	{
-		if (waiting++ % 3) 
-		{
-			spin_lock_irqsave(&sdla_lock, pflags);
-			SDLA_WINDOW(dev, window);
-			waiting = ((volatile int)(cmd_buf->opp_flag));
-			spin_unlock_irqrestore(&sdla_lock, pflags);
-		}
-	}
-	
-	if (!waiting)
-	{
-
-		spin_lock_irqsave(&sdla_lock, pflags);
-		SDLA_WINDOW(dev, window);
-		ret = cmd_buf->retval;
-		len = cmd_buf->length;
-		if (outbuf && outlen)
-		{
-			*outlen = *outlen >= len ? len : *outlen;
-
-			if (*outlen)
-				memcpy(outbuf, cmd_buf->data, *outlen);
-		}
-
-		/* This is a local copy that's used for error handling */
-		if (ret)
-			memcpy(&status, cmd_buf->data, len > sizeof(status) ? sizeof(status) : len);
-
-		spin_unlock_irqrestore(&sdla_lock, pflags);
-	}
-	else
-		ret = SDLA_RET_TIMEOUT;
-
-	if (ret != SDLA_RET_OK)
-	   	sdla_errors(dev, cmd, dlci, ret, len, &status);
-
-	return ret;
-}
-
-/***********************************************
- *
- * these functions are called by the DLCI driver 
- *
- ***********************************************/
-
-static int sdla_reconfig(struct net_device *dev);
-
-static int sdla_activate(struct net_device *slave, struct net_device *master)
-{
-	struct frad_local *flp;
-	int i;
-
-	flp = netdev_priv(slave);
-
-	for(i=0;i<CONFIG_DLCI_MAX;i++)
-		if (flp->master[i] == master)
-			break;
-
-	if (i == CONFIG_DLCI_MAX)
-		return -ENODEV;
-
-	flp->dlci[i] = abs(flp->dlci[i]);
-
-	if (netif_running(slave) && (flp->config.station == FRAD_STATION_NODE))
-		sdla_cmd(slave, SDLA_ACTIVATE_DLCI, 0, 0, &flp->dlci[i], sizeof(short), NULL, NULL);
-
-	return 0;
-}
-
-static int sdla_deactivate(struct net_device *slave, struct net_device *master)
-{
-	struct frad_local *flp;
-	int               i;
-
-	flp = netdev_priv(slave);
-
-	for(i=0;i<CONFIG_DLCI_MAX;i++)
-		if (flp->master[i] == master)
-			break;
-
-	if (i == CONFIG_DLCI_MAX)
-		return -ENODEV;
-
-	flp->dlci[i] = -abs(flp->dlci[i]);
-
-	if (netif_running(slave) && (flp->config.station == FRAD_STATION_NODE))
-		sdla_cmd(slave, SDLA_DEACTIVATE_DLCI, 0, 0, &flp->dlci[i], sizeof(short), NULL, NULL);
-
-	return 0;
-}
-
-static int sdla_assoc(struct net_device *slave, struct net_device *master)
-{
-	struct frad_local *flp;
-	int               i;
-
-	if (master->type != ARPHRD_DLCI)
-		return -EINVAL;
-
-	flp = netdev_priv(slave);
-
-	for(i=0;i<CONFIG_DLCI_MAX;i++)
-	{
-		if (!flp->master[i])
-			break;
-		if (abs(flp->dlci[i]) == *(short *)(master->dev_addr))
-			return -EADDRINUSE;
-	} 
-
-	if (i == CONFIG_DLCI_MAX)
-		return -EMLINK;  /* #### Alan: Comments on this ?? */
-
-
-	flp->master[i] = master;
-	flp->dlci[i] = -*(short *)(master->dev_addr);
-	master->mtu = slave->mtu;
-
-	if (netif_running(slave)) {
-		if (flp->config.station == FRAD_STATION_CPE)
-			sdla_reconfig(slave);
-		else
-			sdla_cmd(slave, SDLA_ADD_DLCI, 0, 0, master->dev_addr, sizeof(short), NULL, NULL);
-	}
-
-	return 0;
-}
-
-static int sdla_deassoc(struct net_device *slave, struct net_device *master)
-{
-	struct frad_local *flp;
-	int               i;
-
-	flp = netdev_priv(slave);
-
-	for(i=0;i<CONFIG_DLCI_MAX;i++)
-		if (flp->master[i] == master)
-			break;
-
-	if (i == CONFIG_DLCI_MAX)
-		return -ENODEV;
-
-	flp->master[i] = NULL;
-	flp->dlci[i] = 0;
-
-
-	if (netif_running(slave)) {
-		if (flp->config.station == FRAD_STATION_CPE)
-			sdla_reconfig(slave);
-		else
-			sdla_cmd(slave, SDLA_DELETE_DLCI, 0, 0, master->dev_addr, sizeof(short), NULL, NULL);
-	}
-
-	return 0;
-}
-
-static int sdla_dlci_conf(struct net_device *slave, struct net_device *master, int get)
-{
-	struct frad_local *flp;
-	struct dlci_local *dlp;
-	int               i;
-	short             len, ret;
-
-	flp = netdev_priv(slave);
-
-	for(i=0;i<CONFIG_DLCI_MAX;i++)
-		if (flp->master[i] == master)
-			break;
-
-	if (i == CONFIG_DLCI_MAX)
-		return -ENODEV;
-
-	dlp = netdev_priv(master);
-
-	ret = SDLA_RET_OK;
-	len = sizeof(struct dlci_conf);
-	if (netif_running(slave)) {
-		if (get)
-			ret = sdla_cmd(slave, SDLA_READ_DLCI_CONFIGURATION, abs(flp->dlci[i]), 0,  
-			            NULL, 0, &dlp->config, &len);
-		else
-			ret = sdla_cmd(slave, SDLA_SET_DLCI_CONFIGURATION, abs(flp->dlci[i]), 0,  
-			            &dlp->config, sizeof(struct dlci_conf) - 4 * sizeof(short), NULL, NULL);
-	}
-
-	return ret == SDLA_RET_OK ? 0 : -EIO;
-}
-
-/**************************
- *
- * now for the Linux driver 
- *
- **************************/
-
-/* NOTE: the DLCI driver deals with freeing the SKB!! */
-static netdev_tx_t sdla_transmit(struct sk_buff *skb,
-				 struct net_device *dev)
-{
-	struct frad_local *flp;
-	int               ret, addr, accept, i;
-	short             size;
-	unsigned long     flags;
-	struct buf_entry  *pbuf;
-
-	flp = netdev_priv(dev);
-	ret = 0;
-	accept = 1;
-
-	netif_stop_queue(dev);
-
-	/*
-	 * stupid GateD insists on setting up the multicast router thru us
-	 * and we're ill equipped to handle a non Frame Relay packet at this
-	 * time!
-	 */
-
-	accept = 1;
-	switch (dev->type)
-	{
-		case ARPHRD_FRAD:
-			if (skb->dev->type != ARPHRD_DLCI)
-			{
-				netdev_warn(dev, "Non DLCI device, type %i, tried to send on FRAD module\n",
-					    skb->dev->type);
-				accept = 0;
-			}
-			break;
-		default:
-			netdev_warn(dev, "unknown firmware type 0x%04X\n",
-				    dev->type);
-			accept = 0;
-			break;
-	}
-	if (accept)
-	{
-		/* this is frame specific, but till there's a PPP module, it's the default */
-		switch (flp->type)
-		{
-			case SDLA_S502A:
-			case SDLA_S502E:
-				ret = sdla_cmd(dev, SDLA_INFORMATION_WRITE, *(short *)(skb->dev->dev_addr), 0, skb->data, skb->len, NULL, NULL);
-				break;
-				case SDLA_S508:
-				size = sizeof(addr);
-				ret = sdla_cmd(dev, SDLA_INFORMATION_WRITE, *(short *)(skb->dev->dev_addr), 0, NULL, skb->len, &addr, &size);
-				if (ret == SDLA_RET_OK)
-				{
-
-					spin_lock_irqsave(&sdla_lock, flags);
-					SDLA_WINDOW(dev, addr);
-					pbuf = (void *)(dev->mem_start + (addr & SDLA_ADDR_MASK));
-					__sdla_write(dev, pbuf->buf_addr, skb->data, skb->len);
-					SDLA_WINDOW(dev, addr);
-					pbuf->opp_flag = 1;
-					spin_unlock_irqrestore(&sdla_lock, flags);
-				}
-				break;
-		}
-
-		switch (ret)
-		{
-			case SDLA_RET_OK:
-				dev->stats.tx_packets++;
-				break;
-
-			case SDLA_RET_CIR_OVERFLOW:
-			case SDLA_RET_BUF_OVERSIZE:
-			case SDLA_RET_NO_BUFS:
-				dev->stats.tx_dropped++;
-				break;
-
-			default:
-				dev->stats.tx_errors++;
-				break;
-		}
-	}
-	netif_wake_queue(dev);
-	for(i=0;i<CONFIG_DLCI_MAX;i++)
-	{
-		if(flp->master[i]!=NULL)
-			netif_wake_queue(flp->master[i]);
-	}		
-
-	dev_kfree_skb(skb);
-	return NETDEV_TX_OK;
-}
-
-static void sdla_receive(struct net_device *dev)
-{
-	struct net_device	  *master;
-	struct frad_local *flp;
-	struct dlci_local *dlp;
-	struct sk_buff	 *skb;
-
-	struct sdla_cmd	*cmd;
-	struct buf_info	*pbufi;
-	struct buf_entry  *pbuf;
-
-	unsigned long	  flags;
-	int               i=0, received, success, addr, buf_base, buf_top;
-	short             dlci, len, len2, split;
-
-	flp = netdev_priv(dev);
-	success = 1;
-	received = addr = buf_top = buf_base = 0;
-	len = dlci = 0;
-	skb = NULL;
-	master = NULL;
-	cmd = NULL;
-	pbufi = NULL;
-	pbuf = NULL;
-
-	spin_lock_irqsave(&sdla_lock, flags);
-
-	switch (flp->type)
-	{
-		case SDLA_S502A:
-		case SDLA_S502E:
-			cmd = (void *) (dev->mem_start + (SDLA_502_RCV_BUF & SDLA_ADDR_MASK));
-			SDLA_WINDOW(dev, SDLA_502_RCV_BUF);
-			success = cmd->opp_flag;
-			if (!success)
-				break;
-
-			dlci = cmd->dlci;
-			len = cmd->length;
-			break;
-
-		case SDLA_S508:
-			pbufi = (void *) (dev->mem_start + (SDLA_508_RXBUF_INFO & SDLA_ADDR_MASK));
-			SDLA_WINDOW(dev, SDLA_508_RXBUF_INFO);
-			pbuf = (void *) (dev->mem_start + ((pbufi->rse_base + flp->buffer * sizeof(struct buf_entry)) & SDLA_ADDR_MASK));
-			success = pbuf->opp_flag;
-			if (!success)
-				break;
-
-			buf_top = pbufi->buf_top;
-			buf_base = pbufi->buf_base;
-			dlci = pbuf->dlci;
-			len = pbuf->length;
-			addr = pbuf->buf_addr;
-			break;
-	}
-
-	/* common code, find the DLCI and get the SKB */
-	if (success)
-	{
-		for (i=0;i<CONFIG_DLCI_MAX;i++)
-			if (flp->dlci[i] == dlci)
-				break;
-
-		if (i == CONFIG_DLCI_MAX)
-		{
-			netdev_notice(dev, "Received packet from invalid DLCI %i, ignoring\n",
-				      dlci);
-			dev->stats.rx_errors++;
-			success = 0;
-		}
-	}
-
-	if (success)
-	{
-		master = flp->master[i];
-		skb = dev_alloc_skb(len + sizeof(struct frhdr));
-		if (skb == NULL) 
-		{
-			netdev_notice(dev, "Memory squeeze, dropping packet\n");
-			dev->stats.rx_dropped++;
-			success = 0;
-		}
-		else
-			skb_reserve(skb, sizeof(struct frhdr));
-	}
-
-	/* pick up the data */
-	switch (flp->type)
-	{
-		case SDLA_S502A:
-		case SDLA_S502E:
-			if (success)
-				__sdla_read(dev, SDLA_502_RCV_BUF + SDLA_502_DATA_OFS, skb_put(skb,len), len);
-
-			SDLA_WINDOW(dev, SDLA_502_RCV_BUF);
-			cmd->opp_flag = 0;
-			break;
-
-		case SDLA_S508:
-			if (success)
-			{
-				/* is this buffer split off the end of the internal ring buffer */
-				split = addr + len > buf_top + 1 ? len - (buf_top - addr + 1) : 0;
-				len2 = len - split;
-
-				__sdla_read(dev, addr, skb_put(skb, len2), len2);
-				if (split)
-					__sdla_read(dev, buf_base, skb_put(skb, split), split);
-			}
-
-			/* increment the buffer we're looking at */
-			SDLA_WINDOW(dev, SDLA_508_RXBUF_INFO);
-			flp->buffer = (flp->buffer + 1) % pbufi->rse_num;
-			pbuf->opp_flag = 0;
-			break;
-	}
-
-	if (success)
-	{
-		dev->stats.rx_packets++;
-		dlp = netdev_priv(master);
-		(*dlp->receive)(skb, master);
-	}
-
-	spin_unlock_irqrestore(&sdla_lock, flags);
-}
-
-static irqreturn_t sdla_isr(int dummy, void *dev_id)
-{
-	struct net_device     *dev;
-	struct frad_local *flp;
-	char              byte;
-
-	dev = dev_id;
-
-	flp = netdev_priv(dev);
-
-	if (!flp->initialized)
-	{
-		netdev_warn(dev, "irq %d for uninitialized device\n", dev->irq);
-		return IRQ_NONE;
-	}
-
-	byte = sdla_byte(dev, flp->type == SDLA_S508 ? SDLA_508_IRQ_INTERFACE : SDLA_502_IRQ_INTERFACE);
-	switch (byte)
-	{
-		case SDLA_INTR_RX:
-			sdla_receive(dev);
-			break;
-
-		/* the command will get an error return, which is processed above */
-		case SDLA_INTR_MODEM:
-		case SDLA_INTR_STATUS:
-			sdla_cmd(dev, SDLA_READ_DLC_STATUS, 0, 0, NULL, 0, NULL, NULL);
-			break;
-
-		case SDLA_INTR_TX:
-		case SDLA_INTR_COMPLETE:
-		case SDLA_INTR_TIMER:
-			netdev_warn(dev, "invalid irq flag 0x%02X\n", byte);
-			break;
-	}
-
-	/* the S502E requires a manual acknowledgement of the interrupt */ 
-	if (flp->type == SDLA_S502E)
-	{
-		flp->state &= ~SDLA_S502E_INTACK;
-		outb(flp->state, dev->base_addr + SDLA_REG_CONTROL);
-		flp->state |= SDLA_S502E_INTACK;
-		outb(flp->state, dev->base_addr + SDLA_REG_CONTROL);
-	}
-
-	/* this clears the byte, informing the Z80 we're done */
-	byte = 0;
-	sdla_write(dev, flp->type == SDLA_S508 ? SDLA_508_IRQ_INTERFACE : SDLA_502_IRQ_INTERFACE, &byte, sizeof(byte));
-	return IRQ_HANDLED;
-}
-
-static void sdla_poll(struct timer_list *t)
-{
-	struct frad_local *flp = from_timer(flp, t, timer);
-	struct net_device *dev = flp->dev;
-
-	if (sdla_byte(dev, SDLA_502_RCV_BUF))
-		sdla_receive(dev);
-
-	flp->timer.expires = 1;
-	add_timer(&flp->timer);
-}
-
-static int sdla_close(struct net_device *dev)
-{
-	struct frad_local *flp;
-	struct intr_info  intr;
-	int               len, i;
-	short             dlcis[CONFIG_DLCI_MAX];
-
-	flp = netdev_priv(dev);
-
-	len = 0;
-	for(i=0;i<CONFIG_DLCI_MAX;i++)
-		if (flp->dlci[i])
-			dlcis[len++] = abs(flp->dlci[i]);
-	len *= 2;
-
-	if (flp->config.station == FRAD_STATION_NODE)
-	{
-		for(i=0;i<CONFIG_DLCI_MAX;i++)
-			if (flp->dlci[i] > 0) 
-				sdla_cmd(dev, SDLA_DEACTIVATE_DLCI, 0, 0, dlcis, len, NULL, NULL);
-		sdla_cmd(dev, SDLA_DELETE_DLCI, 0, 0, &flp->dlci[i], sizeof(flp->dlci[i]), NULL, NULL);
-	}
-
-	memset(&intr, 0, sizeof(intr));
-	/* let's start up the reception */
-	switch(flp->type)
-	{
-		case SDLA_S502A:
-			del_timer(&flp->timer); 
-			break;
-
-		case SDLA_S502E:
-			sdla_cmd(dev, SDLA_SET_IRQ_TRIGGER, 0, 0, &intr, sizeof(char) + sizeof(short), NULL, NULL);
-			flp->state &= ~SDLA_S502E_INTACK;
-			outb(flp->state, dev->base_addr + SDLA_REG_CONTROL);
-			break;
-
-		case SDLA_S507:
-			break;
-
-		case SDLA_S508:
-			sdla_cmd(dev, SDLA_SET_IRQ_TRIGGER, 0, 0, &intr, sizeof(struct intr_info), NULL, NULL);
-			flp->state &= ~SDLA_S508_INTEN;
-			outb(flp->state, dev->base_addr + SDLA_REG_CONTROL);
-			break;
-	}
-
-	sdla_cmd(dev, SDLA_DISABLE_COMMUNICATIONS, 0, 0, NULL, 0, NULL, NULL);
-
-	netif_stop_queue(dev);
-	
-	return 0;
-}
-
-struct conf_data {
-	struct frad_conf config;
-	short            dlci[CONFIG_DLCI_MAX];
-};
-
-static int sdla_open(struct net_device *dev)
-{
-	struct frad_local *flp;
-	struct dlci_local *dlp;
-	struct conf_data  data;
-	struct intr_info  intr;
-	int               len, i;
-	char              byte;
-
-	flp = netdev_priv(dev);
-
-	if (!flp->initialized)
-		return -EPERM;
-
-	if (!flp->configured)
-		return -EPERM;
-
-	/* time to send in the configuration */
-	len = 0;
-	for(i=0;i<CONFIG_DLCI_MAX;i++)
-		if (flp->dlci[i])
-			data.dlci[len++] = abs(flp->dlci[i]);
-	len *= 2;
-
-	memcpy(&data.config, &flp->config, sizeof(struct frad_conf));
-	len += sizeof(struct frad_conf);
-
-	sdla_cmd(dev, SDLA_DISABLE_COMMUNICATIONS, 0, 0, NULL, 0, NULL, NULL);
-	sdla_cmd(dev, SDLA_SET_DLCI_CONFIGURATION, 0, 0, &data, len, NULL, NULL);
-
-	if (flp->type == SDLA_S508)
-		flp->buffer = 0;
-
-	sdla_cmd(dev, SDLA_ENABLE_COMMUNICATIONS, 0, 0, NULL, 0, NULL, NULL);
-
-	/* let's start up the reception */
-	memset(&intr, 0, sizeof(intr));
-	switch(flp->type)
-	{
-		case SDLA_S502A:
-			flp->timer.expires = 1;
-			add_timer(&flp->timer);
-			break;
-
-		case SDLA_S502E:
-			flp->state |= SDLA_S502E_ENABLE;
-			outb(flp->state, dev->base_addr + SDLA_REG_CONTROL);
-			flp->state |= SDLA_S502E_INTACK;
-			outb(flp->state, dev->base_addr + SDLA_REG_CONTROL);
-			byte = 0;
-			sdla_write(dev, SDLA_502_IRQ_INTERFACE, &byte, sizeof(byte));
-			intr.flags = SDLA_INTR_RX | SDLA_INTR_STATUS | SDLA_INTR_MODEM;
-			sdla_cmd(dev, SDLA_SET_IRQ_TRIGGER, 0, 0, &intr, sizeof(char) + sizeof(short), NULL, NULL);
-			break;
-
-		case SDLA_S507:
-			break;
-
-		case SDLA_S508:
-			flp->state |= SDLA_S508_INTEN;
-			outb(flp->state, dev->base_addr + SDLA_REG_CONTROL);
-			byte = 0;
-			sdla_write(dev, SDLA_508_IRQ_INTERFACE, &byte, sizeof(byte));
-			intr.flags = SDLA_INTR_RX | SDLA_INTR_STATUS | SDLA_INTR_MODEM;
-			intr.irq = dev->irq;
-			sdla_cmd(dev, SDLA_SET_IRQ_TRIGGER, 0, 0, &intr, sizeof(struct intr_info), NULL, NULL);
-			break;
-	}
-
-	if (flp->config.station == FRAD_STATION_CPE)
-	{
-		byte = SDLA_ICS_STATUS_ENQ;
-		sdla_cmd(dev, SDLA_ISSUE_IN_CHANNEL_SIGNAL, 0, 0, &byte, sizeof(byte), NULL, NULL);
-	}
-	else
-	{
-		sdla_cmd(dev, SDLA_ADD_DLCI, 0, 0, data.dlci, len - sizeof(struct frad_conf), NULL, NULL);
-		for(i=0;i<CONFIG_DLCI_MAX;i++)
-			if (flp->dlci[i] > 0)
-				sdla_cmd(dev, SDLA_ACTIVATE_DLCI, 0, 0, &flp->dlci[i], 2*sizeof(flp->dlci[i]), NULL, NULL);
-	}
-
-	/* configure any specific DLCI settings */
-	for(i=0;i<CONFIG_DLCI_MAX;i++)
-		if (flp->dlci[i])
-		{
-			dlp = netdev_priv(flp->master[i]);
-			if (dlp->configured)
-				sdla_cmd(dev, SDLA_SET_DLCI_CONFIGURATION, abs(flp->dlci[i]), 0, &dlp->config, sizeof(struct dlci_conf), NULL, NULL);
-		}
-
-	netif_start_queue(dev);
-	
-	return 0;
-}
-
-static int sdla_config(struct net_device *dev, struct frad_conf __user *conf, int get)
-{
-	struct frad_local *flp;
-	struct conf_data  data;
-	int               i;
-	short             size;
-
-	if (dev->type == 0xFFFF)
-		return -EUNATCH;
-
-	flp = netdev_priv(dev);
-
-	if (!get)
-	{
-		if (netif_running(dev))
-			return -EBUSY;
-
-		if(copy_from_user(&data.config, conf, sizeof(struct frad_conf)))
-			return -EFAULT;
-
-		if (data.config.station & ~FRAD_STATION_NODE)
-			return -EINVAL;
-
-		if (data.config.flags & ~FRAD_VALID_FLAGS)
-			return -EINVAL;
-
-		if ((data.config.kbaud < 0) || 
-			 ((data.config.kbaud > 128) && (flp->type != SDLA_S508)))
-			return -EINVAL;
-
-		if (data.config.clocking & ~(FRAD_CLOCK_INT | SDLA_S508_PORT_RS232))
-			return -EINVAL;
-
-		if ((data.config.mtu < 0) || (data.config.mtu > SDLA_MAX_MTU))
-			return -EINVAL;
-
-		if ((data.config.T391 < 5) || (data.config.T391 > 30))
-			return -EINVAL;
-
-		if ((data.config.T392 < 5) || (data.config.T392 > 30))
-			return -EINVAL;
-
-		if ((data.config.N391 < 1) || (data.config.N391 > 255))
-			return -EINVAL;
-
-		if ((data.config.N392 < 1) || (data.config.N392 > 10))
-			return -EINVAL;
-
-		if ((data.config.N393 < 1) || (data.config.N393 > 10))
-			return -EINVAL;
-
-		memcpy(&flp->config, &data.config, sizeof(struct frad_conf));
-		flp->config.flags |= SDLA_DIRECT_RECV;
-
-		if (flp->type == SDLA_S508)
-			flp->config.flags |= SDLA_TX70_RX30;
-
-		if (dev->mtu != flp->config.mtu)
-		{
-			/* this is required to change the MTU */
-			dev->mtu = flp->config.mtu;
-			for(i=0;i<CONFIG_DLCI_MAX;i++)
-				if (flp->master[i])
-					flp->master[i]->mtu = flp->config.mtu;
-		}
-
-		flp->config.mtu += sizeof(struct frhdr);
-
-		/* off to the races! */
-		if (!flp->configured)
-			sdla_start(dev);
-
-		flp->configured = 1;
-	}
-	else
-	{
-		/* no sense reading if the CPU isn't started */
-		if (netif_running(dev))
-		{
-			size = sizeof(data);
-			if (sdla_cmd(dev, SDLA_READ_DLCI_CONFIGURATION, 0, 0, NULL, 0, &data, &size) != SDLA_RET_OK)
-				return -EIO;
-		}
-		else
-			if (flp->configured)
-				memcpy(&data.config, &flp->config, sizeof(struct frad_conf));
-			else
-				memset(&data.config, 0, sizeof(struct frad_conf));
-
-		memcpy(&flp->config, &data.config, sizeof(struct frad_conf));
-		data.config.flags &= FRAD_VALID_FLAGS;
-		data.config.mtu -= data.config.mtu > sizeof(struct frhdr) ? sizeof(struct frhdr) : data.config.mtu;
-		return copy_to_user(conf, &data.config, sizeof(struct frad_conf))?-EFAULT:0;
-	}
-
-	return 0;
-}
-
-static int sdla_xfer(struct net_device *dev, struct sdla_mem __user *info, int read)
-{
-	struct sdla_mem mem;
-	char	*temp;
-
-	if(copy_from_user(&mem, info, sizeof(mem)))
-		return -EFAULT;
-		
-	if (read)
-	{	
-		temp = kzalloc(mem.len, GFP_KERNEL);
-		if (!temp)
-			return -ENOMEM;
-		sdla_read(dev, mem.addr, temp, mem.len);
-		if(copy_to_user(mem.data, temp, mem.len))
-		{
-			kfree(temp);
-			return -EFAULT;
-		}
-		kfree(temp);
-	}
-	else
-	{
-		temp = memdup_user(mem.data, mem.len);
-		if (IS_ERR(temp))
-			return PTR_ERR(temp);
-		sdla_write(dev, mem.addr, temp, mem.len);
-		kfree(temp);
-	}
-	return 0;
-}
-
-static int sdla_reconfig(struct net_device *dev)
-{
-	struct frad_local *flp;
-	struct conf_data  data;
-	int               i, len;
-
-	flp = netdev_priv(dev);
-
-	len = 0;
-	for(i=0;i<CONFIG_DLCI_MAX;i++)
-		if (flp->dlci[i])
-			data.dlci[len++] = flp->dlci[i];
-	len *= 2;
-
-	memcpy(&data, &flp->config, sizeof(struct frad_conf));
-	len += sizeof(struct frad_conf);
-
-	sdla_cmd(dev, SDLA_DISABLE_COMMUNICATIONS, 0, 0, NULL, 0, NULL, NULL);
-	sdla_cmd(dev, SDLA_SET_DLCI_CONFIGURATION, 0, 0, &data, len, NULL, NULL);
-	sdla_cmd(dev, SDLA_ENABLE_COMMUNICATIONS, 0, 0, NULL, 0, NULL, NULL);
-
-	return 0;
-}
-
-static int sdla_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
-{
-	struct frad_local *flp;
-
-	if(!capable(CAP_NET_ADMIN))
-		return -EPERM;
-		
-	flp = netdev_priv(dev);
-
-	if (!flp->initialized)
-		return -EINVAL;
-
-	switch (cmd)
-	{
-		case FRAD_GET_CONF:
-		case FRAD_SET_CONF:
-			return sdla_config(dev, ifr->ifr_data, cmd == FRAD_GET_CONF);
-
-		case SDLA_IDENTIFY:
-			ifr->ifr_flags = flp->type;
-			break;
-
-		case SDLA_CPUSPEED:
-			return sdla_cpuspeed(dev, ifr);
-
-/* ==========================================================
-NOTE:  This is rather a useless action right now, as the
-       current driver does not support protocols other than
-       FR.  However, Sangoma has modules for a number of
-       other protocols in the works.
-============================================================*/
-		case SDLA_PROTOCOL:
-			if (flp->configured)
-				return -EALREADY;
-
-			switch (ifr->ifr_flags)
-			{
-				case ARPHRD_FRAD:
-					dev->type = ifr->ifr_flags;
-					break;
-				default:
-					return -ENOPROTOOPT;
-			}
-			break;
-
-		case SDLA_CLEARMEM:
-			sdla_clear(dev);
-			break;
-
-		case SDLA_WRITEMEM:
-		case SDLA_READMEM:
-			if(!capable(CAP_SYS_RAWIO))
-				return -EPERM;
-			return sdla_xfer(dev, ifr->ifr_data, cmd == SDLA_READMEM);
-
-		case SDLA_START:
-			sdla_start(dev);
-			break;
-
-		case SDLA_STOP:
-			sdla_stop(dev);
-			break;
-
-		default:
-			return -EOPNOTSUPP;
-	}
-	return 0;
-}
-
-static int sdla_change_mtu(struct net_device *dev, int new_mtu)
-{
-	if (netif_running(dev))
-		return -EBUSY;
-
-	/* for now, you can't change the MTU! */
-	return -EOPNOTSUPP;
-}
-
-static int sdla_set_config(struct net_device *dev, struct ifmap *map)
-{
-	struct frad_local *flp;
-	int               i;
-	char              byte;
-	unsigned base;
-	int err = -EINVAL;
-
-	flp = netdev_priv(dev);
-
-	if (flp->initialized)
-		return -EINVAL;
-
-	for(i=0; i < ARRAY_SIZE(valid_port); i++)
-		if (valid_port[i] == map->base_addr)
-			break;   
-
-	if (i == ARRAY_SIZE(valid_port))
-		return -EINVAL;
-
-	if (!request_region(map->base_addr, SDLA_IO_EXTENTS, dev->name)){
-		pr_warn("io-port 0x%04lx in use\n", dev->base_addr);
-		return -EINVAL;
-	}
-	base = map->base_addr;
-
-	/* test for card types, S502A, S502E, S507, S508                 */
-	/* these tests shut down the card completely, so clear the state */
-	flp->type = SDLA_UNKNOWN;
-	flp->state = 0;
-   
-	for(i=1;i<SDLA_IO_EXTENTS;i++)
-		if (inb(base + i) != 0xFF)
-			break;
-
-	if (i == SDLA_IO_EXTENTS) {   
-		outb(SDLA_HALT, base + SDLA_REG_Z80_CONTROL);
-		if ((inb(base + SDLA_S502_STS) & 0x0F) == 0x08) {
-			outb(SDLA_S502E_INTACK, base + SDLA_REG_CONTROL);
-			if ((inb(base + SDLA_S502_STS) & 0x0F) == 0x0C) {
-				outb(SDLA_HALT, base + SDLA_REG_CONTROL);
-				flp->type = SDLA_S502E;
-				goto got_type;
-			}
-		}
-	}
-
-	for(byte=inb(base),i=0;i<SDLA_IO_EXTENTS;i++)
-		if (inb(base + i) != byte)
-			break;
-
-	if (i == SDLA_IO_EXTENTS) {
-		outb(SDLA_HALT, base + SDLA_REG_CONTROL);
-		if ((inb(base + SDLA_S502_STS) & 0x7E) == 0x30) {
-			outb(SDLA_S507_ENABLE, base + SDLA_REG_CONTROL);
-			if ((inb(base + SDLA_S502_STS) & 0x7E) == 0x32) {
-				outb(SDLA_HALT, base + SDLA_REG_CONTROL);
-				flp->type = SDLA_S507;
-				goto got_type;
-			}
-		}
-	}
-
-	outb(SDLA_HALT, base + SDLA_REG_CONTROL);
-	if ((inb(base + SDLA_S508_STS) & 0x3F) == 0x00) {
-		outb(SDLA_S508_INTEN, base + SDLA_REG_CONTROL);
-		if ((inb(base + SDLA_S508_STS) & 0x3F) == 0x10) {
-			outb(SDLA_HALT, base + SDLA_REG_CONTROL);
-			flp->type = SDLA_S508;
-			goto got_type;
-		}
-	}
-
-	outb(SDLA_S502A_HALT, base + SDLA_REG_CONTROL);
-	if (inb(base + SDLA_S502_STS) == 0x40) {
-		outb(SDLA_S502A_START, base + SDLA_REG_CONTROL);
-		if (inb(base + SDLA_S502_STS) == 0x40) {
-			outb(SDLA_S502A_INTEN, base + SDLA_REG_CONTROL);
-			if (inb(base + SDLA_S502_STS) == 0x44) {
-				outb(SDLA_S502A_START, base + SDLA_REG_CONTROL);
-				flp->type = SDLA_S502A;
-				goto got_type;
-			}
-		}
-	}
-
-	netdev_notice(dev, "Unknown card type\n");
-	err = -ENODEV;
-	goto fail;
-
-got_type:
-	switch(base) {
-		case 0x270:
-		case 0x280:
-		case 0x380: 
-		case 0x390:
-			if (flp->type != SDLA_S508 && flp->type != SDLA_S507)
-				goto fail;
-	}
-
-	switch (map->irq) {
-		case 2:
-			if (flp->type != SDLA_S502E)
-				goto fail;
-			break;
-
-		case 10:
-		case 11:
-		case 12:
-		case 15:
-		case 4:
-			if (flp->type != SDLA_S508 && flp->type != SDLA_S507)
-				goto fail;
-			break;
-		case 3:
-		case 5:
-		case 7:
-			if (flp->type == SDLA_S502A)
-				goto fail;
-			break;
-
-		default:
-			goto fail;
-	}
-
-	err = -EAGAIN;
-	if (request_irq(dev->irq, sdla_isr, 0, dev->name, dev)) 
-		goto fail;
-
-	if (flp->type == SDLA_S507) {
-		switch(dev->irq) {
-			case 3:
-				flp->state = SDLA_S507_IRQ3;
-				break;
-			case 4:
-				flp->state = SDLA_S507_IRQ4;
-				break;
-			case 5:
-				flp->state = SDLA_S507_IRQ5;
-				break;
-			case 7:
-				flp->state = SDLA_S507_IRQ7;
-				break;
-			case 10:
-				flp->state = SDLA_S507_IRQ10;
-				break;
-			case 11:
-				flp->state = SDLA_S507_IRQ11;
-				break;
-			case 12:
-				flp->state = SDLA_S507_IRQ12;
-				break;
-			case 15:
-				flp->state = SDLA_S507_IRQ15;
-				break;
-		}
-	}
-
-	for(i=0; i < ARRAY_SIZE(valid_mem); i++)
-		if (valid_mem[i] == map->mem_start)
-			break;   
-
-	err = -EINVAL;
-	if (i == ARRAY_SIZE(valid_mem))
-		goto fail2;
-
-	if (flp->type == SDLA_S502A && (map->mem_start & 0xF000) >> 12 == 0x0E)
-		goto fail2;
-
-	if (flp->type != SDLA_S507 && map->mem_start >> 16 == 0x0B)
-		goto fail2;
-
-	if (flp->type == SDLA_S507 && map->mem_start >> 16 == 0x0D)
-		goto fail2;
-
-	byte = flp->type != SDLA_S508 ? SDLA_8K_WINDOW : 0;
-	byte |= (map->mem_start & 0xF000) >> (12 + (flp->type == SDLA_S508 ? 1 : 0));
-	switch(flp->type) {
-		case SDLA_S502A:
-		case SDLA_S502E:
-			switch (map->mem_start >> 16) {
-				case 0x0A:
-					byte |= SDLA_S502_SEG_A;
-					break;
-				case 0x0C:
-					byte |= SDLA_S502_SEG_C;
-					break;
-				case 0x0D:
-					byte |= SDLA_S502_SEG_D;
-					break;
-				case 0x0E:
-					byte |= SDLA_S502_SEG_E;
-					break;
-			}
-			break;
-		case SDLA_S507:
-			switch (map->mem_start >> 16) {
-				case 0x0A:
-					byte |= SDLA_S507_SEG_A;
-					break;
-				case 0x0B:
-					byte |= SDLA_S507_SEG_B;
-					break;
-				case 0x0C:
-					byte |= SDLA_S507_SEG_C;
-					break;
-				case 0x0E:
-					byte |= SDLA_S507_SEG_E;
-					break;
-			}
-			break;
-		case SDLA_S508:
-			switch (map->mem_start >> 16) {
-				case 0x0A:
-					byte |= SDLA_S508_SEG_A;
-					break;
-				case 0x0C:
-					byte |= SDLA_S508_SEG_C;
-					break;
-				case 0x0D:
-					byte |= SDLA_S508_SEG_D;
-					break;
-				case 0x0E:
-					byte |= SDLA_S508_SEG_E;
-					break;
-			}
-			break;
-	}
-
-	/* set the memory bits, and enable access */
-	outb(byte, base + SDLA_REG_PC_WINDOW);
-
-	switch(flp->type)
-	{
-		case SDLA_S502E:
-			flp->state = SDLA_S502E_ENABLE;
-			break;
-		case SDLA_S507:
-			flp->state |= SDLA_MEMEN;
-			break;
-		case SDLA_S508:
-			flp->state = SDLA_MEMEN;
-			break;
-	}
-	outb(flp->state, base + SDLA_REG_CONTROL);
-
-	dev->irq = map->irq;
-	dev->base_addr = base;
-	dev->mem_start = map->mem_start;
-	dev->mem_end = dev->mem_start + 0x2000;
-	flp->initialized = 1;
-	return 0;
-
-fail2:
-	free_irq(map->irq, dev);
-fail:
-	release_region(base, SDLA_IO_EXTENTS);
-	return err;
-}
- 
-static const struct net_device_ops sdla_netdev_ops = {
-	.ndo_open	= sdla_open,
-	.ndo_stop	= sdla_close,
-	.ndo_do_ioctl	= sdla_ioctl,
-	.ndo_set_config	= sdla_set_config,
-	.ndo_start_xmit	= sdla_transmit,
-	.ndo_change_mtu	= sdla_change_mtu,
-};
-
-static void setup_sdla(struct net_device *dev)
-{
-	struct frad_local *flp = netdev_priv(dev);
-
-	netdev_boot_setup_check(dev);
-
-	dev->netdev_ops		= &sdla_netdev_ops;
-	dev->flags		= 0;
-	dev->type		= 0xFFFF;
-	dev->hard_header_len	= 0;
-	dev->addr_len		= 0;
-	dev->mtu		= SDLA_MAX_MTU;
-
-	flp->activate		= sdla_activate;
-	flp->deactivate		= sdla_deactivate;
-	flp->assoc		= sdla_assoc;
-	flp->deassoc		= sdla_deassoc;
-	flp->dlci_conf		= sdla_dlci_conf;
-	flp->dev		= dev;
-
-	timer_setup(&flp->timer, sdla_poll, 0);
-	flp->timer.expires	= 1;
-}
-
-static struct net_device *sdla;
-
-static int __init init_sdla(void)
-{
-	int err;
-
-	printk("%s.\n", version);
-
-	sdla = alloc_netdev(sizeof(struct frad_local), "sdla0",
-			    NET_NAME_UNKNOWN, setup_sdla);
-	if (!sdla) 
-		return -ENOMEM;
-
-	err = register_netdev(sdla);
-	if (err) 
-		free_netdev(sdla);
-
-	return err;
-}
-
-static void __exit exit_sdla(void)
-{
-	struct frad_local *flp = netdev_priv(sdla);
-
-	unregister_netdev(sdla);
-	if (flp->initialized) {
-		free_irq(sdla->irq, sdla);
-		release_region(sdla->base_addr, SDLA_IO_EXTENTS);
-	}
-	del_timer_sync(&flp->timer);
-	free_netdev(sdla);
-}
-
-MODULE_LICENSE("GPL");
-
-module_init(init_sdla);
-module_exit(exit_sdla);
diff --git a/include/linux/if_frad.h b/include/linux/if_frad.h
deleted file mode 100644
index 52224de798aa..000000000000
--- a/include/linux/if_frad.h
+++ /dev/null
@@ -1,92 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * DLCI/FRAD	Definitions for Frame Relay Access Devices.  DLCI devices are
- *		created for each DLCI associated with a FRAD.  The FRAD driver
- *		is not truly a network device, but the lower level device
- *		handler.  This allows other FRAD manufacturers to use the DLCI
- *		code, including its RFC1490 encapsulation alongside the current
- *		implementation for the Sangoma cards.
- *
- * Version:	@(#)if_ifrad.h	0.15	31 Mar 96
- *
- * Author:	Mike McLagan <mike.mclagan@linux.org>
- *
- * Changes:
- *		0.15	Mike McLagan	changed structure defs (packed)
- *					re-arranged flags
- *					added DLCI_RET vars
- */
-#ifndef _FRAD_H_
-#define _FRAD_H_
-
-#include <uapi/linux/if_frad.h>
-
-
-#if defined(CONFIG_DLCI) || defined(CONFIG_DLCI_MODULE)
-
-/* these are the fields of an RFC 1490 header */
-struct frhdr
-{
-   unsigned char  control;
-
-   /* for IP packets, this can be the NLPID */
-   unsigned char  pad;
-
-   unsigned char  NLPID;
-   unsigned char  OUI[3];
-   __be16 PID;
-
-#define IP_NLPID pad 
-} __packed;
-
-/* see RFC 1490 for the definition of the following */
-#define FRAD_I_UI		0x03
-
-#define FRAD_P_PADDING		0x00
-#define FRAD_P_Q933		0x08
-#define FRAD_P_SNAP		0x80
-#define FRAD_P_CLNP		0x81
-#define FRAD_P_IP		0xCC
-
-struct dlci_local
-{
-   struct net_device      *master;
-   struct net_device      *slave;
-   struct dlci_conf       config;
-   int                    configured;
-   struct list_head	  list;
-
-   /* callback function */
-   void              (*receive)(struct sk_buff *skb, struct net_device *);
-};
-
-struct frad_local
-{
-   /* devices which this FRAD is slaved to */
-   struct net_device     *master[CONFIG_DLCI_MAX];
-   short             dlci[CONFIG_DLCI_MAX];
-
-   struct frad_conf  config;
-   int               configured;	/* has this device been configured */
-   int               initialized;	/* mem_start, port, irq set ? */
-
-   /* callback functions */
-   int               (*activate)(struct net_device *, struct net_device *);
-   int               (*deactivate)(struct net_device *, struct net_device *);
-   int               (*assoc)(struct net_device *, struct net_device *);
-   int               (*deassoc)(struct net_device *, struct net_device *);
-   int               (*dlci_conf)(struct net_device *, struct net_device *, int get);
-
-   /* fields that are used by the Sangoma SDLA cards */
-   struct timer_list timer;
-   struct net_device *dev;
-   int               type;		/* adapter type */
-   int               state;		/* state of the S502/8 control latch */
-   int               buffer;		/* current buffer for S508 firmware */
-};
-
-#endif /* CONFIG_DLCI || CONFIG_DLCI_MODULE */
-
-extern void dlci_ioctl_set(int (*hook)(unsigned int, void __user *));
-
-#endif
diff --git a/include/linux/sdla.h b/include/linux/sdla.h
deleted file mode 100644
index 00e8b3b614f0..000000000000
--- a/include/linux/sdla.h
+++ /dev/null
@@ -1,240 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * INET		An implementation of the TCP/IP protocol suite for the LINUX
- *		operating system.  INET is implemented using the  BSD Socket
- *		interface as the means of communication with the user level.
- *
- *		Global definitions for the Frame relay interface.
- *
- * Version:	@(#)if_ifrad.h	0.20	13 Apr 96
- *
- * Author:	Mike McLagan <mike.mclagan@linux.org>
- *
- * Changes:
- *		0.15	Mike McLagan	Structure packing
- *
- *		0.20	Mike McLagan	New flags for S508 buffer handling
- */
-#ifndef SDLA_H
-#define SDLA_H
-
-#include <uapi/linux/sdla.h>
-
-
-/* important Z80 window addresses */
-#define SDLA_CONTROL_WND		0xE000
-
-#define SDLA_502_CMD_BUF		0xEF60
-#define SDLA_502_RCV_BUF		0xA900
-#define	SDLA_502_TXN_AVAIL		0xFFF1
-#define SDLA_502_RCV_AVAIL		0xFFF2
-#define SDLA_502_EVENT_FLAGS		0xFFF3
-#define SDLA_502_MDM_STATUS		0xFFF4
-#define SDLA_502_IRQ_INTERFACE		0xFFFD
-#define SDLA_502_IRQ_PERMISSION		0xFFFE
-#define SDLA_502_DATA_OFS		0x0010
-
-#define SDLA_508_CMD_BUF		0xE000
-#define SDLA_508_TXBUF_INFO		0xF100
-#define SDLA_508_RXBUF_INFO		0xF120
-#define SDLA_508_EVENT_FLAGS		0xF003
-#define SDLA_508_MDM_STATUS		0xF004
-#define SDLA_508_IRQ_INTERFACE		0xF010
-#define SDLA_508_IRQ_PERMISSION		0xF011
-#define SDLA_508_TSE_OFFSET		0xF012
-
-/* Event flags */
-#define SDLA_EVENT_STATUS		0x01
-#define SDLA_EVENT_DLCI_STATUS		0x02
-#define SDLA_EVENT_BAD_DLCI		0x04
-#define SDLA_EVENT_LINK_DOWN		0x40
-
-/* IRQ Trigger flags */
-#define SDLA_INTR_RX			0x01
-#define SDLA_INTR_TX			0x02
-#define SDLA_INTR_MODEM			0x04
-#define SDLA_INTR_COMPLETE		0x08
-#define SDLA_INTR_STATUS		0x10
-#define SDLA_INTR_TIMER			0x20
-
-/* DLCI status bits */
-#define SDLA_DLCI_DELETED		0x01
-#define SDLA_DLCI_ACTIVE		0x02
-#define SDLA_DLCI_WAITING		0x04
-#define SDLA_DLCI_NEW			0x08
-#define SDLA_DLCI_INCLUDED		0x40
-
-/* valid command codes */
-#define	SDLA_INFORMATION_WRITE		0x01
-#define	SDLA_INFORMATION_READ		0x02
-#define SDLA_ISSUE_IN_CHANNEL_SIGNAL	0x03
-#define	SDLA_SET_DLCI_CONFIGURATION	0x10
-#define	SDLA_READ_DLCI_CONFIGURATION	0x11
-#define	SDLA_DISABLE_COMMUNICATIONS	0x12
-#define	SDLA_ENABLE_COMMUNICATIONS	0x13
-#define	SDLA_READ_DLC_STATUS		0x14
-#define	SDLA_READ_DLC_STATISTICS	0x15
-#define	SDLA_FLUSH_DLC_STATISTICS	0x16
-#define	SDLA_LIST_ACTIVE_DLCI		0x17
-#define	SDLA_FLUSH_INFORMATION_BUFFERS	0x18
-#define	SDLA_ADD_DLCI			0x20
-#define	SDLA_DELETE_DLCI		0x21
-#define	SDLA_ACTIVATE_DLCI		0x22
-#define	SDLA_DEACTIVATE_DLCI		0x23
-#define	SDLA_READ_MODEM_STATUS		0x30
-#define	SDLA_SET_MODEM_STATUS		0x31
-#define	SDLA_READ_COMMS_ERR_STATS	0x32
-#define SDLA_FLUSH_COMMS_ERR_STATS	0x33
-#define	SDLA_READ_CODE_VERSION		0x40
-#define SDLA_SET_IRQ_TRIGGER		0x50
-#define SDLA_GET_IRQ_TRIGGER		0x51
-
-/* In channel signal types */
-#define SDLA_ICS_LINK_VERIFY		0x02
-#define SDLA_ICS_STATUS_ENQ		0x03
-
-/* modem status flags */
-#define SDLA_MODEM_DTR_HIGH		0x01
-#define SDLA_MODEM_RTS_HIGH		0x02
-#define SDLA_MODEM_DCD_HIGH		0x08
-#define SDLA_MODEM_CTS_HIGH		0x20
-
-/* used for RET_MODEM interpretation */
-#define SDLA_MODEM_DCD_LOW		0x01
-#define SDLA_MODEM_CTS_LOW		0x02
-
-/* return codes */
-#define SDLA_RET_OK			0x00
-#define SDLA_RET_COMMUNICATIONS		0x01
-#define SDLA_RET_CHANNEL_INACTIVE	0x02
-#define SDLA_RET_DLCI_INACTIVE		0x03
-#define SDLA_RET_DLCI_CONFIG		0x04
-#define SDLA_RET_BUF_TOO_BIG		0x05
-#define SDLA_RET_NO_DATA		0x05
-#define SDLA_RET_BUF_OVERSIZE		0x06
-#define SDLA_RET_CIR_OVERFLOW		0x07
-#define SDLA_RET_NO_BUFS		0x08
-#define SDLA_RET_TIMEOUT		0x0A
-#define SDLA_RET_MODEM			0x10
-#define SDLA_RET_CHANNEL_OFF		0x11
-#define SDLA_RET_CHANNEL_ON		0x12
-#define SDLA_RET_DLCI_STATUS		0x13
-#define SDLA_RET_DLCI_UNKNOWN       	0x14
-#define SDLA_RET_COMMAND_INVALID    	0x1F
-
-/* Configuration flags */
-#define SDLA_DIRECT_RECV		0x0080
-#define SDLA_TX_NO_EXCEPT		0x0020
-#define SDLA_NO_ICF_MSGS		0x1000
-#define SDLA_TX50_RX50			0x0000
-#define SDLA_TX70_RX30			0x2000
-#define SDLA_TX30_RX70			0x4000
-
-/* IRQ selection flags */
-#define SDLA_IRQ_RECEIVE		0x01
-#define SDLA_IRQ_TRANSMIT		0x02
-#define SDLA_IRQ_MODEM_STAT		0x04
-#define SDLA_IRQ_COMMAND		0x08
-#define SDLA_IRQ_CHANNEL		0x10
-#define SDLA_IRQ_TIMER			0x20
-
-/* definitions for PC memory mapping */
-#define SDLA_8K_WINDOW			0x01
-#define SDLA_S502_SEG_A			0x10
-#define SDLA_S502_SEG_C			0x20
-#define SDLA_S502_SEG_D			0x00
-#define SDLA_S502_SEG_E			0x30
-#define SDLA_S507_SEG_A			0x00
-#define SDLA_S507_SEG_B			0x40
-#define SDLA_S507_SEG_C			0x80
-#define SDLA_S507_SEG_E			0xC0
-#define SDLA_S508_SEG_A			0x00
-#define SDLA_S508_SEG_C			0x10
-#define SDLA_S508_SEG_D			0x08
-#define SDLA_S508_SEG_E			0x18
-
-/* SDLA adapter port constants */
-#define SDLA_IO_EXTENTS			0x04
-	
-#define SDLA_REG_CONTROL		0x00
-#define SDLA_REG_PC_WINDOW		0x01	/* offset for PC window select latch */
-#define SDLA_REG_Z80_WINDOW 		0x02	/* offset for Z80 window select latch */
-#define SDLA_REG_Z80_CONTROL		0x03	/* offset for Z80 control latch */
-	
-#define SDLA_S502_STS			0x00	/* status reg for 502, 502E, 507 */
-#define SDLA_S508_GNRL			0x00	/* general purp. reg for 508 */
-#define SDLA_S508_STS			0x01	/* status reg for 508 */
-#define SDLA_S508_IDR			0x02	/* ID reg for 508 */
-	
-/* control register flags */
-#define SDLA_S502A_START		0x00	/* start the CPU */
-#define SDLA_S502A_INTREQ		0x02
-#define SDLA_S502A_INTEN		0x04
-#define SDLA_S502A_HALT			0x08	/* halt the CPU */	
-#define SDLA_S502A_NMI			0x10	/* issue an NMI to the CPU */
-
-#define SDLA_S502E_CPUEN		0x01
-#define SDLA_S502E_ENABLE		0x02
-#define SDLA_S502E_INTACK		0x04
-	
-#define SDLA_S507_ENABLE		0x01
-#define SDLA_S507_IRQ3			0x00
-#define SDLA_S507_IRQ4			0x20
-#define SDLA_S507_IRQ5			0x40
-#define SDLA_S507_IRQ7			0x60
-#define SDLA_S507_IRQ10			0x80
-#define SDLA_S507_IRQ11			0xA0
-#define SDLA_S507_IRQ12			0xC0
-#define SDLA_S507_IRQ15			0xE0
-	
-#define SDLA_HALT			0x00
-#define SDLA_CPUEN			0x02
-#define SDLA_MEMEN			0x04
-#define SDLA_S507_EPROMWR		0x08
-#define SDLA_S507_EPROMCLK		0x10
-#define SDLA_S508_INTRQ			0x08
-#define SDLA_S508_INTEN			0x10
-
-struct sdla_cmd {
-   char  opp_flag;
-   char  cmd;
-   short length;
-   char  retval;
-   short dlci;
-   char  flags;
-   short rxlost_int;
-   long  rxlost_app;
-   char  reserve[2];
-   char  data[SDLA_MAX_DATA];	/* transfer data buffer */
-} __attribute__((packed));
-
-struct intr_info {
-   char  flags;
-   short txlen;
-   char  irq;
-   char  flags2;
-   short timeout;
-} __attribute__((packed));
-
-/* found in the 508's control window at RXBUF_INFO */
-struct buf_info {
-   unsigned short rse_num;
-   unsigned long  rse_base;
-   unsigned long  rse_next;
-   unsigned long  buf_base;
-   unsigned short reserved;
-   unsigned long  buf_top;
-} __attribute__((packed));
-
-/* structure pointed to by rse_base in RXBUF_INFO struct */
-struct buf_entry {
-   char  opp_flag;
-   short length;
-   short dlci;
-   char  flags;
-   short timestamp;
-   short reserved[2];
-   long  buf_addr;
-} __attribute__((packed));
-
-#endif
diff --git a/include/uapi/linux/if_frad.h b/include/uapi/linux/if_frad.h
deleted file mode 100644
index 3c6ee85f6262..000000000000
--- a/include/uapi/linux/if_frad.h
+++ /dev/null
@@ -1,123 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
-/*
- * DLCI/FRAD	Definitions for Frame Relay Access Devices.  DLCI devices are
- *		created for each DLCI associated with a FRAD.  The FRAD driver
- *		is not truly a network device, but the lower level device
- *		handler.  This allows other FRAD manufacturers to use the DLCI
- *		code, including its RFC1490 encapsulation alongside the current
- *		implementation for the Sangoma cards.
- *
- * Version:	@(#)if_ifrad.h	0.15	31 Mar 96
- *
- * Author:	Mike McLagan <mike.mclagan@linux.org>
- *
- * Changes:
- *		0.15	Mike McLagan	changed structure defs (packed)
- *					re-arranged flags
- *					added DLCI_RET vars
- *
- *		This program is free software; you can redistribute it and/or
- *		modify it under the terms of the GNU General Public License
- *		as published by the Free Software Foundation; either version
- *		2 of the License, or (at your option) any later version.
- */
-
-#ifndef _UAPI_FRAD_H_
-#define _UAPI_FRAD_H_
-
-#include <linux/if.h>
-
-/* Structures and constants associated with the DLCI device driver */
-
-struct dlci_add
-{
-   char  devname[IFNAMSIZ];
-   short dlci;
-};
-
-#define DLCI_GET_CONF	(SIOCDEVPRIVATE + 2)
-#define DLCI_SET_CONF	(SIOCDEVPRIVATE + 3)
-
-/* 
- * These are related to the Sangoma SDLA and should remain in order. 
- * Code within the SDLA module is based on the specifics of this 
- * structure.  Change at your own peril.
- */
-struct dlci_conf {
-   short flags;
-   short CIR_fwd;
-   short Bc_fwd;
-   short Be_fwd;
-   short CIR_bwd;
-   short Bc_bwd;
-   short Be_bwd; 
-
-/* these are part of the status read */
-   short Tc_fwd;
-   short Tc_bwd;
-   short Tf_max;
-   short Tb_max;
-
-/* add any new fields here above is a mirror of sdla_dlci_conf */
-};
-
-#define DLCI_GET_SLAVE	(SIOCDEVPRIVATE + 4)
-
-/* configuration flags for DLCI */
-#define DLCI_IGNORE_CIR_OUT	0x0001
-#define DLCI_ACCOUNT_CIR_IN	0x0002
-#define DLCI_BUFFER_IF		0x0008
-
-#define DLCI_VALID_FLAGS	0x000B
-
-/* defines for the actual Frame Relay hardware */
-#define FRAD_GET_CONF	(SIOCDEVPRIVATE)
-#define FRAD_SET_CONF	(SIOCDEVPRIVATE + 1)
-
-#define FRAD_LAST_IOCTL	FRAD_SET_CONF
-
-/*
- * Based on the setup for the Sangoma SDLA.  If changes are 
- * necessary to this structure, a routine will need to be 
- * added to that module to copy fields.
- */
-struct frad_conf 
-{
-   short station;
-   short flags;
-   short kbaud;
-   short clocking;
-   short mtu;
-   short T391;
-   short T392;
-   short N391;
-   short N392;
-   short N393;
-   short CIR_fwd;
-   short Bc_fwd;
-   short Be_fwd;
-   short CIR_bwd;
-   short Bc_bwd;
-   short Be_bwd;
-
-/* Add new fields here, above is a mirror of the sdla_conf */
-
-};
-
-#define FRAD_STATION_CPE	0x0000
-#define FRAD_STATION_NODE	0x0001
-
-#define FRAD_TX_IGNORE_CIR	0x0001
-#define FRAD_RX_ACCOUNT_CIR	0x0002
-#define FRAD_DROP_ABORTED	0x0004
-#define FRAD_BUFFERIF		0x0008
-#define FRAD_STATS		0x0010
-#define FRAD_MCI		0x0100
-#define FRAD_AUTODLCI		0x8000
-#define FRAD_VALID_FLAGS	0x811F
-
-#define FRAD_CLOCK_INT		0x0001
-#define FRAD_CLOCK_EXT		0x0000
-
-
-#endif /* _UAPI_FRAD_H_ */
diff --git a/include/uapi/linux/sdla.h b/include/uapi/linux/sdla.h
deleted file mode 100644
index 1e3735be6511..000000000000
--- a/include/uapi/linux/sdla.h
+++ /dev/null
@@ -1,117 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
-/*
- * INET		An implementation of the TCP/IP protocol suite for the LINUX
- *		operating system.  INET is implemented using the  BSD Socket
- *		interface as the means of communication with the user level.
- *
- *		Global definitions for the Frame relay interface.
- *
- * Version:	@(#)if_ifrad.h	0.20	13 Apr 96
- *
- * Author:	Mike McLagan <mike.mclagan@linux.org>
- *
- * Changes:
- *		0.15	Mike McLagan	Structure packing
- *
- *		0.20	Mike McLagan	New flags for S508 buffer handling
- *
- *		This program is free software; you can redistribute it and/or
- *		modify it under the terms of the GNU General Public License
- *		as published by the Free Software Foundation; either version
- *		2 of the License, or (at your option) any later version.
- */
-
-#ifndef _UAPISDLA_H
-#define _UAPISDLA_H
-
-/* adapter type */
-#define SDLA_TYPES
-#define SDLA_S502A			5020
-#define SDLA_S502E			5021
-#define SDLA_S503			5030
-#define SDLA_S507			5070
-#define SDLA_S508			5080
-#define SDLA_S509			5090
-#define SDLA_UNKNOWN			-1
-
-/* port selection flags for the S508 */
-#define SDLA_S508_PORT_V35		0x00
-#define SDLA_S508_PORT_RS232		0x02
-
-/* Z80 CPU speeds */
-#define SDLA_CPU_3M			0x00
-#define SDLA_CPU_5M			0x01
-#define SDLA_CPU_7M			0x02
-#define SDLA_CPU_8M			0x03
-#define SDLA_CPU_10M			0x04
-#define SDLA_CPU_16M			0x05
-#define SDLA_CPU_12M			0x06
-
-/* some private IOCTLs */
-#define SDLA_IDENTIFY			(FRAD_LAST_IOCTL + 1)
-#define SDLA_CPUSPEED			(FRAD_LAST_IOCTL + 2)
-#define SDLA_PROTOCOL			(FRAD_LAST_IOCTL + 3)
-
-#define SDLA_CLEARMEM			(FRAD_LAST_IOCTL + 4)
-#define SDLA_WRITEMEM			(FRAD_LAST_IOCTL + 5)
-#define SDLA_READMEM			(FRAD_LAST_IOCTL + 6)
-
-struct sdla_mem {
-   int  addr;
-   int  len;
-   void __user *data;
-};
-
-#define SDLA_START			(FRAD_LAST_IOCTL + 7)
-#define SDLA_STOP			(FRAD_LAST_IOCTL + 8)
-
-/* some offsets in the Z80's memory space */
-#define SDLA_NMIADDR			0x0000
-#define SDLA_CONF_ADDR			0x0010
-#define SDLA_S502A_NMIADDR		0x0066
-#define SDLA_CODE_BASEADDR		0x0100
-#define SDLA_WINDOW_SIZE		0x2000
-#define SDLA_ADDR_MASK			0x1FFF
-
-/* largest handleable block of data */
-#define SDLA_MAX_DATA			4080
-#define SDLA_MAX_MTU			4072	/* MAX_DATA - sizeof(fradhdr) */
-#define SDLA_MAX_DLCI			24
-
-/* this should be the same as frad_conf */
-struct sdla_conf {
-   short station;
-   short config;
-   short kbaud;
-   short clocking;
-   short max_frm;
-   short T391;
-   short T392;
-   short N391;
-   short N392;
-   short N393;
-   short CIR_fwd;
-   short Bc_fwd;
-   short Be_fwd;
-   short CIR_bwd;
-   short Bc_bwd;
-   short Be_bwd;
-};
-
-/* this should be the same as dlci_conf */
-struct sdla_dlci_conf {
-   short config;
-   short CIR_fwd;
-   short Bc_fwd;
-   short Be_fwd;
-   short CIR_bwd;
-   short Bc_bwd;
-   short Be_bwd; 
-   short Tc_fwd;
-   short Tc_bwd;
-   short Tf_max;
-   short Tb_max;
-};
-
-
-#endif /* _UAPISDLA_H */
diff --git a/net/socket.c b/net/socket.c
index 6e6cccc2104f..152b1dcf93c6 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -64,7 +64,6 @@
 #include <linux/seq_file.h>
 #include <linux/mutex.h>
 #include <linux/if_bridge.h>
-#include <linux/if_frad.h>
 #include <linux/if_vlan.h>
 #include <linux/ptp_classify.h>
 #include <linux/init.h>
@@ -1027,17 +1026,6 @@ void vlan_ioctl_set(int (*hook) (struct net *, void __user *))
 }
 EXPORT_SYMBOL(vlan_ioctl_set);
 
-static DEFINE_MUTEX(dlci_ioctl_mutex);
-static int (*dlci_ioctl_hook) (unsigned int, void __user *);
-
-void dlci_ioctl_set(int (*hook) (unsigned int, void __user *))
-{
-	mutex_lock(&dlci_ioctl_mutex);
-	dlci_ioctl_hook = hook;
-	mutex_unlock(&dlci_ioctl_mutex);
-}
-EXPORT_SYMBOL(dlci_ioctl_set);
-
 static long sock_do_ioctl(struct net *net, struct socket *sock,
 			  unsigned int cmd, unsigned long arg)
 {
@@ -1156,17 +1144,6 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 				err = vlan_ioctl_hook(net, argp);
 			mutex_unlock(&vlan_ioctl_mutex);
 			break;
-		case SIOCADDDLCI:
-		case SIOCDELDLCI:
-			err = -ENOPKG;
-			if (!dlci_ioctl_hook)
-				request_module("dlci");
-
-			mutex_lock(&dlci_ioctl_mutex);
-			if (dlci_ioctl_hook)
-				err = dlci_ioctl_hook(cmd, argp);
-			mutex_unlock(&dlci_ioctl_mutex);
-			break;
 		case SIOCGSKNS:
 			err = -EPERM;
 			if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
@@ -3427,8 +3404,6 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
 	case SIOCBRDELBR:
 	case SIOCGIFVLAN:
 	case SIOCSIFVLAN:
-	case SIOCADDDLCI:
-	case SIOCDELDLCI:
 	case SIOCGSKNS:
 	case SIOCGSTAMP_NEW:
 	case SIOCGSTAMPNS_NEW:
-- 
cgit v1.2.3


From 270f3385cddf5db3799b393459476bd9abff89f1 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Mon, 16 Nov 2020 11:17:59 +0100
Subject: net: core: fix some kernel-doc markups

Some identifiers have different names between their prototypes
and the kernel-doc markup.

In the specific case of netif_subqueue_stopped(), keep the
current markup for __netif_subqueue_stopped(), adding a
new one for netif_subqueue_stopped().

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7ce648a564f7..03433a4c929e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1490,7 +1490,7 @@ struct net_device_ops {
 };
 
 /**
- * enum net_device_priv_flags - &struct net_device priv_flags
+ * enum netdev_priv_flags - &struct net_device priv_flags
  *
  * These are the &struct net_device, they are only set internally
  * by drivers and used in the kernel. These flags are invisible to
@@ -3602,7 +3602,7 @@ static inline void netif_stop_subqueue(struct net_device *dev, u16 queue_index)
 }
 
 /**
- *	netif_subqueue_stopped - test status of subqueue
+ *	__netif_subqueue_stopped - test status of subqueue
  *	@dev: network device
  *	@queue_index: sub queue index
  *
@@ -3616,6 +3616,13 @@ static inline bool __netif_subqueue_stopped(const struct net_device *dev,
 	return netif_tx_queue_stopped(txq);
 }
 
+/**
+ *	netif_subqueue_stopped - test status of subqueue
+ *	@dev: network device
+ *	@skb: sub queue buffer pointer
+ *
+ * Check individual transmit queue of a device with multiple transmit queues.
+ */
 static inline bool netif_subqueue_stopped(const struct net_device *dev,
 					  struct sk_buff *skb)
 {
-- 
cgit v1.2.3


From ed5298c7d500abaf34ed7783969e953a1f028e5b Mon Sep 17 00:00:00 2001
From: Loic Poulain <loic.poulain@linaro.org>
Date: Mon, 28 Sep 2020 09:39:50 +0530
Subject: bus: mhi: Remove auto-start option

There is really no point having an auto-start for channels.
This is confusing for the device drivers, some have to enable the
channels, others don't have... and waste resources (e.g. pre allocated
buffers) that may never be used.

This is really up to the MHI device(channel) driver to manage the state
of its channels.

While at it, let's also remove the auto-start option from ath11k mhi
controller.

Signed-off-by: Loic Poulain <loic.poulain@linaro.org>
Acked-by: Kalle Valo <kvalo@codeaurora.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
[mani: clubbed ath11k change]
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/bus/mhi/core/init.c           | 9 ---------
 drivers/bus/mhi/core/internal.h       | 1 -
 drivers/net/wireless/ath/ath11k/mhi.c | 4 ----
 include/linux/mhi.h                   | 2 --
 4 files changed, 16 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/bus/mhi/core/init.c b/drivers/bus/mhi/core/init.c
index 0ffdebde8265..381fdea2eb9f 100644
--- a/drivers/bus/mhi/core/init.c
+++ b/drivers/bus/mhi/core/init.c
@@ -758,7 +758,6 @@ static int parse_ch_cfg(struct mhi_controller *mhi_cntrl,
 		mhi_chan->offload_ch = ch_cfg->offload_channel;
 		mhi_chan->db_cfg.reset_req = ch_cfg->doorbell_mode_switch;
 		mhi_chan->pre_alloc = ch_cfg->auto_queue;
-		mhi_chan->auto_start = ch_cfg->auto_start;
 
 		/*
 		 * If MHI host allocates buffers, then the channel direction
@@ -1160,11 +1159,6 @@ static int mhi_driver_probe(struct device *dev)
 			goto exit_probe;
 
 		ul_chan->xfer_cb = mhi_drv->ul_xfer_cb;
-		if (ul_chan->auto_start) {
-			ret = mhi_prepare_channel(mhi_cntrl, ul_chan);
-			if (ret)
-				goto exit_probe;
-		}
 	}
 
 	ret = -EINVAL;
@@ -1198,9 +1192,6 @@ static int mhi_driver_probe(struct device *dev)
 	if (ret)
 		goto exit_probe;
 
-	if (dl_chan && dl_chan->auto_start)
-		mhi_prepare_channel(mhi_cntrl, dl_chan);
-
 	mhi_device_put(mhi_dev);
 
 	return ret;
diff --git a/drivers/bus/mhi/core/internal.h b/drivers/bus/mhi/core/internal.h
index 7989269ddd96..33c23203c531 100644
--- a/drivers/bus/mhi/core/internal.h
+++ b/drivers/bus/mhi/core/internal.h
@@ -563,7 +563,6 @@ struct mhi_chan {
 	bool configured;
 	bool offload_ch;
 	bool pre_alloc;
-	bool auto_start;
 	bool wake_capable;
 };
 
diff --git a/drivers/net/wireless/ath/ath11k/mhi.c b/drivers/net/wireless/ath/ath11k/mhi.c
index aded9a719d51..47a1ce1bee4f 100644
--- a/drivers/net/wireless/ath/ath11k/mhi.c
+++ b/drivers/net/wireless/ath/ath11k/mhi.c
@@ -24,7 +24,6 @@ static struct mhi_channel_config ath11k_mhi_channels[] = {
 		.offload_channel = false,
 		.doorbell_mode_switch = false,
 		.auto_queue = false,
-		.auto_start = false,
 	},
 	{
 		.num = 1,
@@ -39,7 +38,6 @@ static struct mhi_channel_config ath11k_mhi_channels[] = {
 		.offload_channel = false,
 		.doorbell_mode_switch = false,
 		.auto_queue = false,
-		.auto_start = false,
 	},
 	{
 		.num = 20,
@@ -54,7 +52,6 @@ static struct mhi_channel_config ath11k_mhi_channels[] = {
 		.offload_channel = false,
 		.doorbell_mode_switch = false,
 		.auto_queue = false,
-		.auto_start = true,
 	},
 	{
 		.num = 21,
@@ -69,7 +66,6 @@ static struct mhi_channel_config ath11k_mhi_channels[] = {
 		.offload_channel = false,
 		.doorbell_mode_switch = false,
 		.auto_queue = true,
-		.auto_start = true,
 	},
 };
 
diff --git a/include/linux/mhi.h b/include/linux/mhi.h
index d4841e5a5f45..6522a4adc794 100644
--- a/include/linux/mhi.h
+++ b/include/linux/mhi.h
@@ -214,7 +214,6 @@ enum mhi_db_brst_mode {
  * @offload_channel: The client manages the channel completely
  * @doorbell_mode_switch: Channel switches to doorbell mode on M0 transition
  * @auto_queue: Framework will automatically queue buffers for DL traffic
- * @auto_start: Automatically start (open) this channel
  * @wake-capable: Channel capable of waking up the system
  */
 struct mhi_channel_config {
@@ -232,7 +231,6 @@ struct mhi_channel_config {
 	bool offload_channel;
 	bool doorbell_mode_switch;
 	bool auto_queue;
-	bool auto_start;
 	bool wake_capable;
 };
 
-- 
cgit v1.2.3


From 16fee29b07358293f135759d9fdbf1267da57ebd Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 6 Nov 2020 17:02:17 +0100
Subject: dma-mapping: remove the dma_direct_set_offset export

Drop the dma_direct_set_offset export and move the declaration to
dma-map-ops.h now that the Allwinner drivers have stopped calling it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
---
 arch/arm/mach-keystone/keystone.c | 2 +-
 arch/arm/mach-omap1/usb.c         | 2 +-
 arch/sh/drivers/pci/pcie-sh7786.c | 2 +-
 arch/x86/pci/sta2x11-fixup.c      | 3 ++-
 include/linux/dma-map-ops.h       | 3 +++
 include/linux/dma-mapping.h       | 7 -------
 kernel/dma/direct.c               | 1 -
 7 files changed, 8 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/mach-keystone/keystone.c b/arch/arm/mach-keystone/keystone.c
index 09a65c2dfd73..cd711bfc591f 100644
--- a/arch/arm/mach-keystone/keystone.c
+++ b/arch/arm/mach-keystone/keystone.c
@@ -8,7 +8,7 @@
  */
 #include <linux/io.h>
 #include <linux/of.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/init.h>
 #include <linux/of_platform.h>
 #include <linux/of_address.h>
diff --git a/arch/arm/mach-omap1/usb.c b/arch/arm/mach-omap1/usb.c
index ba8566204ea9..86d3b3c157af 100644
--- a/arch/arm/mach-omap1/usb.c
+++ b/arch/arm/mach-omap1/usb.c
@@ -9,7 +9,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/platform_device.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/io.h>
 
 #include <asm/irq.h>
diff --git a/arch/sh/drivers/pci/pcie-sh7786.c b/arch/sh/drivers/pci/pcie-sh7786.c
index 4468289ab2ca..4d499476c33a 100644
--- a/arch/sh/drivers/pci/pcie-sh7786.c
+++ b/arch/sh/drivers/pci/pcie-sh7786.c
@@ -12,7 +12,7 @@
 #include <linux/io.h>
 #include <linux/async.h>
 #include <linux/delay.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/slab.h>
 #include <linux/clk.h>
 #include <linux/sh_clk.h>
diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c
index 5701d5ba3df4..7d2525691854 100644
--- a/arch/x86/pci/sta2x11-fixup.c
+++ b/arch/x86/pci/sta2x11-fixup.c
@@ -11,7 +11,8 @@
 #include <linux/pci_ids.h>
 #include <linux/export.h>
 #include <linux/list.h>
-#include <linux/dma-direct.h>
+#include <linux/dma-map-ops.h>
+#include <linux/swiotlb.h>
 #include <asm/iommu.h>
 
 #define STA2X11_SWIOTLB_SIZE (4*1024*1024)
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index a5f89fc4d6df..03925e438ec3 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -226,6 +226,9 @@ struct page *dma_alloc_from_pool(struct device *dev, size_t size,
 		bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t));
 bool dma_free_from_pool(struct device *dev, void *start, size_t size);
 
+int dma_direct_set_offset(struct device *dev, phys_addr_t cpu_start,
+		dma_addr_t dma_start, u64 size);
+
 #ifdef CONFIG_ARCH_HAS_DMA_COHERENCE_H
 #include <asm/dma-coherence.h>
 #elif defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 956151052d45..199d85285246 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -558,13 +558,6 @@ static inline int dma_mmap_wc(struct device *dev,
 #define dma_unmap_len_set(PTR, LEN_NAME, VAL)    do { } while (0)
 #endif
 
-/*
- * Legacy interface to set up the dma offset map.  Drivers really should not
- * actually use it, but we have a few legacy cases left.
- */
-int dma_direct_set_offset(struct device *dev, phys_addr_t cpu_start,
-		dma_addr_t dma_start, u64 size);
-
 extern const struct dma_map_ops dma_virt_ops;
 
 #endif /* _LINUX_DMA_MAPPING_H */
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 06c111544f61..002268262c9a 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -547,4 +547,3 @@ int dma_direct_set_offset(struct device *dev, phys_addr_t cpu_start,
 	dev->dma_range_map = map;
 	return 0;
 }
-EXPORT_SYMBOL_GPL(dma_direct_set_offset);
-- 
cgit v1.2.3


From 78e1d22687ff1fd320abac12e8a607ea79782c48 Mon Sep 17 00:00:00 2001
From: Bhaumik Bhatt <bbhatt@codeaurora.org>
Date: Fri, 6 Nov 2020 09:44:47 -0800
Subject: bus: mhi: core: Expose mhi_get_exec_env() API for controllers

The mhi_get_exec_env() APIs can be used by the controller drivers
to query the execution environment of the MHI device. Expose it
so it can be used in some scenarios to determine behavior of
controllers.

Signed-off-by: Bhaumik Bhatt <bbhatt@codeaurora.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/bus/mhi/core/internal.h | 1 -
 drivers/bus/mhi/core/main.c     | 1 +
 include/linux/mhi.h             | 6 ++++++
 3 files changed, 7 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/bus/mhi/core/internal.h b/drivers/bus/mhi/core/internal.h
index 78e4e84d6743..d8af8a702493 100644
--- a/drivers/bus/mhi/core/internal.h
+++ b/drivers/bus/mhi/core/internal.h
@@ -609,7 +609,6 @@ enum mhi_pm_state __must_check mhi_tryset_pm_state(
 					struct mhi_controller *mhi_cntrl,
 					enum mhi_pm_state state);
 const char *to_mhi_pm_state_str(enum mhi_pm_state state);
-enum mhi_ee_type mhi_get_exec_env(struct mhi_controller *mhi_cntrl);
 int mhi_queue_state_transition(struct mhi_controller *mhi_cntrl,
 			       enum dev_st_transition state);
 void mhi_pm_st_worker(struct work_struct *work);
diff --git a/drivers/bus/mhi/core/main.c b/drivers/bus/mhi/core/main.c
index 6ecaacaa8b54..f953e2a6d58a 100644
--- a/drivers/bus/mhi/core/main.c
+++ b/drivers/bus/mhi/core/main.c
@@ -123,6 +123,7 @@ enum mhi_ee_type mhi_get_exec_env(struct mhi_controller *mhi_cntrl)
 
 	return (ret) ? MHI_EE_MAX : exec;
 }
+EXPORT_SYMBOL_GPL(mhi_get_exec_env);
 
 enum mhi_state mhi_get_mhi_state(struct mhi_controller *mhi_cntrl)
 {
diff --git a/include/linux/mhi.h b/include/linux/mhi.h
index d4841e5a5f45..9225d5551d69 100644
--- a/include/linux/mhi.h
+++ b/include/linux/mhi.h
@@ -658,6 +658,12 @@ int mhi_download_rddm_img(struct mhi_controller *mhi_cntrl, bool in_panic);
  */
 int mhi_force_rddm_mode(struct mhi_controller *mhi_cntrl);
 
+/**
+ * mhi_get_exec_env - Get BHI execution environment of the device
+ * @mhi_cntrl: MHI controller
+ */
+enum mhi_ee_type mhi_get_exec_env(struct mhi_controller *mhi_cntrl);
+
 /**
  * mhi_get_mhi_state - Get MHI state of the device
  * @mhi_cntrl: MHI controller
-- 
cgit v1.2.3


From 9e1660e5c396ee081907386d0b95b8e0804a6c86 Mon Sep 17 00:00:00 2001
From: Bhaumik Bhatt <bbhatt@codeaurora.org>
Date: Fri, 6 Nov 2020 09:44:49 -0800
Subject: bus: mhi: core: Rename RDDM download function to use proper words

mhi_download_rddm_img() uses a shorter version of the word image.
Expand it and rename the function to mhi_download_rddm_image().

Signed-off-by: Bhaumik Bhatt <bbhatt@codeaurora.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/bus/mhi/core/boot.c | 4 ++--
 include/linux/mhi.h         | 6 +++---
 2 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/bus/mhi/core/boot.c b/drivers/bus/mhi/core/boot.c
index 6b6fd9668c3b..16244cc8fbe7 100644
--- a/drivers/bus/mhi/core/boot.c
+++ b/drivers/bus/mhi/core/boot.c
@@ -147,7 +147,7 @@ static int __mhi_download_rddm_in_panic(struct mhi_controller *mhi_cntrl)
 }
 
 /* Download RDDM image from device */
-int mhi_download_rddm_img(struct mhi_controller *mhi_cntrl, bool in_panic)
+int mhi_download_rddm_image(struct mhi_controller *mhi_cntrl, bool in_panic)
 {
 	void __iomem *base = mhi_cntrl->bhie;
 	struct device *dev = &mhi_cntrl->mhi_dev->dev;
@@ -169,7 +169,7 @@ int mhi_download_rddm_img(struct mhi_controller *mhi_cntrl, bool in_panic)
 
 	return (rx_status == BHIE_RXVECSTATUS_STATUS_XFER_COMPL) ? 0 : -EIO;
 }
-EXPORT_SYMBOL_GPL(mhi_download_rddm_img);
+EXPORT_SYMBOL_GPL(mhi_download_rddm_image);
 
 static int mhi_fw_load_amss(struct mhi_controller *mhi_cntrl,
 			    const struct mhi_buf *mhi_buf)
diff --git a/include/linux/mhi.h b/include/linux/mhi.h
index 9225d5551d69..52b3c60bf9bb 100644
--- a/include/linux/mhi.h
+++ b/include/linux/mhi.h
@@ -645,12 +645,12 @@ int mhi_pm_suspend(struct mhi_controller *mhi_cntrl);
 int mhi_pm_resume(struct mhi_controller *mhi_cntrl);
 
 /**
- * mhi_download_rddm_img - Download ramdump image from device for
- *                         debugging purpose.
+ * mhi_download_rddm_image - Download ramdump image from device for
+ *                           debugging purpose.
  * @mhi_cntrl: MHI controller
  * @in_panic: Download rddm image during kernel panic
  */
-int mhi_download_rddm_img(struct mhi_controller *mhi_cntrl, bool in_panic);
+int mhi_download_rddm_image(struct mhi_controller *mhi_cntrl, bool in_panic);
 
 /**
  * mhi_force_rddm_mode - Force device into rddm mode
-- 
cgit v1.2.3


From 8f70397876872789b2a5deba804eb6216fb5deb7 Mon Sep 17 00:00:00 2001
From: Bhaumik Bhatt <bbhatt@codeaurora.org>
Date: Mon, 9 Nov 2020 12:47:21 -0800
Subject: bus: mhi: core: Move to using high priority workqueue

MHI work is currently scheduled on the global/system workqueue and can
encounter delays on a stressed system. To avoid those unforeseen
delays which can hamper bootup or shutdown times, use a dedicated high
priority workqueue instead of the global/system workqueue.

Signed-off-by: Bhaumik Bhatt <bbhatt@codeaurora.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/bus/mhi/core/init.c | 9 +++++++++
 drivers/bus/mhi/core/pm.c   | 2 +-
 include/linux/mhi.h         | 2 ++
 3 files changed, 12 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/bus/mhi/core/init.c b/drivers/bus/mhi/core/init.c
index 8cefa359fccd..877e40c86801 100644
--- a/drivers/bus/mhi/core/init.c
+++ b/drivers/bus/mhi/core/init.c
@@ -880,6 +880,13 @@ int mhi_register_controller(struct mhi_controller *mhi_cntrl,
 	INIT_WORK(&mhi_cntrl->st_worker, mhi_pm_st_worker);
 	init_waitqueue_head(&mhi_cntrl->state_event);
 
+	mhi_cntrl->hiprio_wq = alloc_ordered_workqueue
+				("mhi_hiprio_wq", WQ_MEM_RECLAIM | WQ_HIGHPRI);
+	if (!mhi_cntrl->hiprio_wq) {
+		dev_err(mhi_cntrl->cntrl_dev, "Failed to allocate workqueue\n");
+		goto error_alloc_cmd;
+	}
+
 	mhi_cmd = mhi_cntrl->mhi_cmd;
 	for (i = 0; i < NR_OF_CMD_RINGS; i++, mhi_cmd++)
 		spin_lock_init(&mhi_cmd->lock);
@@ -969,6 +976,7 @@ error_alloc_dev:
 error_alloc_cmd:
 	vfree(mhi_cntrl->mhi_chan);
 	kfree(mhi_cntrl->mhi_event);
+	destroy_workqueue(mhi_cntrl->hiprio_wq);
 
 	return ret;
 }
@@ -982,6 +990,7 @@ void mhi_unregister_controller(struct mhi_controller *mhi_cntrl)
 
 	mhi_destroy_debugfs(mhi_cntrl);
 
+	destroy_workqueue(mhi_cntrl->hiprio_wq);
 	kfree(mhi_cntrl->mhi_cmd);
 	kfree(mhi_cntrl->mhi_event);
 
diff --git a/drivers/bus/mhi/core/pm.c b/drivers/bus/mhi/core/pm.c
index 3de7b1639ec6..805b6fa748f0 100644
--- a/drivers/bus/mhi/core/pm.c
+++ b/drivers/bus/mhi/core/pm.c
@@ -597,7 +597,7 @@ int mhi_queue_state_transition(struct mhi_controller *mhi_cntrl,
 	list_add_tail(&item->node, &mhi_cntrl->transition_list);
 	spin_unlock_irqrestore(&mhi_cntrl->transition_lock, flags);
 
-	schedule_work(&mhi_cntrl->st_worker);
+	queue_work(mhi_cntrl->hiprio_wq, &mhi_cntrl->st_worker);
 
 	return 0;
 }
diff --git a/include/linux/mhi.h b/include/linux/mhi.h
index 52b3c60bf9bb..1ed5f2aa224b 100644
--- a/include/linux/mhi.h
+++ b/include/linux/mhi.h
@@ -337,6 +337,7 @@ struct mhi_controller_config {
  * @wlock: Lock for protecting device wakeup
  * @mhi_link_info: Device bandwidth info
  * @st_worker: State transition worker
+ * @hiprio_wq: High priority workqueue for MHI work such as state transitions
  * @state_event: State change event
  * @status_cb: CB function to notify power states of the device (required)
  * @wake_get: CB function to assert device wake (optional)
@@ -419,6 +420,7 @@ struct mhi_controller {
 	spinlock_t wlock;
 	struct mhi_link_info mhi_link_info;
 	struct work_struct st_worker;
+	struct workqueue_struct *hiprio_wq;
 	wait_queue_head_t state_event;
 
 	void (*status_cb)(struct mhi_controller *mhi_cntrl,
-- 
cgit v1.2.3


From 5c62634fc65101d350cbd47722fb76f02693059d Mon Sep 17 00:00:00 2001
From: Hui Su <sh_def@163.com>
Date: Wed, 18 Nov 2020 00:17:50 +0800
Subject: namespace: make timens_on_fork() return nothing

timens_on_fork() always return 0, and maybe not
need to judge the return value in copy_namespaces().

So make timens_on_fork() return nothing and do not
judge its return val in copy_namespaces().

Signed-off-by: Hui Su <sh_def@163.com>
Link: https://lore.kernel.org/r/20201117161750.GA45121@rlk
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 include/linux/time_namespace.h | 6 +++---
 kernel/nsproxy.c               | 7 +------
 kernel/time/namespace.c        | 6 ++----
 3 files changed, 6 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/time_namespace.h b/include/linux/time_namespace.h
index 68770ac9ba89..30312166e70a 100644
--- a/include/linux/time_namespace.h
+++ b/include/linux/time_namespace.h
@@ -45,7 +45,7 @@ struct time_namespace *copy_time_ns(unsigned long flags,
 				    struct user_namespace *user_ns,
 				    struct time_namespace *old_ns);
 void free_time_ns(struct kref *kref);
-int timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk);
+void timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk);
 struct vdso_data *arch_get_vdso_data(void *vvar_page);
 
 static inline void put_time_ns(struct time_namespace *ns)
@@ -136,10 +136,10 @@ struct time_namespace *copy_time_ns(unsigned long flags,
 	return old_ns;
 }
 
-static inline int timens_on_fork(struct nsproxy *nsproxy,
+static inline void timens_on_fork(struct nsproxy *nsproxy,
 				 struct task_struct *tsk)
 {
-	return 0;
+	return;
 }
 
 static inline void timens_add_monotonic(struct timespec64 *ts) { }
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index 12dd41b39a7f..e2e6c5dc433f 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -153,7 +153,6 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk)
 	struct nsproxy *old_ns = tsk->nsproxy;
 	struct user_namespace *user_ns = task_cred_xxx(tsk, user_ns);
 	struct nsproxy *new_ns;
-	int ret;
 
 	if (likely(!(flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
 			      CLONE_NEWPID | CLONE_NEWNET |
@@ -180,11 +179,7 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk)
 	if (IS_ERR(new_ns))
 		return  PTR_ERR(new_ns);
 
-	ret = timens_on_fork(new_ns, tsk);
-	if (ret) {
-		free_nsproxy(new_ns);
-		return ret;
-	}
+	timens_on_fork(new_ns, tsk);
 
 	tsk->nsproxy = new_ns;
 	return 0;
diff --git a/kernel/time/namespace.c b/kernel/time/namespace.c
index afc65e6be33e..e0f9509b17c3 100644
--- a/kernel/time/namespace.c
+++ b/kernel/time/namespace.c
@@ -308,22 +308,20 @@ static int timens_install(struct nsset *nsset, struct ns_common *new)
 	return 0;
 }
 
-int timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk)
+void timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk)
 {
 	struct ns_common *nsc = &nsproxy->time_ns_for_children->ns;
 	struct time_namespace *ns = to_time_ns(nsc);
 
 	/* create_new_namespaces() already incremented the ref counter */
 	if (nsproxy->time_ns == nsproxy->time_ns_for_children)
-		return 0;
+		return;
 
 	get_time_ns(ns);
 	put_time_ns(nsproxy->time_ns);
 	nsproxy->time_ns = ns;
 
 	timens_commit(tsk, ns);
-
-	return 0;
 }
 
 static struct user_namespace *timens_owner(struct ns_common *ns)
-- 
cgit v1.2.3


From 13d40ff85da8a85935e3fd47061dee71a02af0d4 Mon Sep 17 00:00:00 2001
From: Utkarsh Patel <utkarsh.h.patel@intel.com>
Date: Fri, 13 Nov 2020 12:24:56 -0800
Subject: usb: typec: Correct the bit values for the Thunderbolt
 rounded/non-rounded cable support

Rounded and non-rounded Thunderbolt cables are represented by two bits as
per USB Type-C Connector specification v2.0 section F.2.6.
Corrected that in the Thunderbolt 3 cable discover mode VDO.

Signed-off-by: Utkarsh Patel <utkarsh.h.patel@intel.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
--
Changes in v2:
- Removed the fixes tag as there is no functional implication.
--
Link: https://lore.kernel.org/r/20201113202503.6559-2-utkarsh.h.patel@intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/usb/typec_tbt.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/usb/typec_tbt.h b/include/linux/usb/typec_tbt.h
index 47c2d501ddce..aad648d14bb3 100644
--- a/include/linux/usb/typec_tbt.h
+++ b/include/linux/usb/typec_tbt.h
@@ -40,11 +40,16 @@ struct typec_thunderbolt_data {
 #define   TBT_CABLE_USB3_PASSIVE	2
 #define   TBT_CABLE_10_AND_20GBPS	3
 #define TBT_CABLE_ROUNDED		BIT(19)
+#define TBT_CABLE_ROUNDED_SUPPORT(_vdo_) \
+					(((_vdo_) & GENMASK(20, 19)) >> 19)
+#define   TBT_GEN3_NON_ROUNDED                 0
+#define   TBT_GEN3_GEN4_ROUNDED_NON_ROUNDED    1
 #define TBT_CABLE_OPTICAL		BIT(21)
 #define TBT_CABLE_RETIMER		BIT(22)
 #define TBT_CABLE_LINK_TRAINING		BIT(23)
 
 #define TBT_SET_CABLE_SPEED(_s_)	(((_s_) & GENMASK(2, 0)) << 16)
+#define TBT_SET_CABLE_ROUNDED(_g_)	(((_g_) & GENMASK(1, 0)) << 19)
 
 /* TBT3 Device Enter Mode VDO bits */
 #define TBT_ENTER_MODE_CABLE_SPEED(s)	TBT_SET_CABLE_SPEED(s)
-- 
cgit v1.2.3


From 523a97aa3b756c1e0efe33ae48d450f8b0052073 Mon Sep 17 00:00:00 2001
From: Utkarsh Patel <utkarsh.h.patel@intel.com>
Date: Fri, 13 Nov 2020 12:24:59 -0800
Subject: usb: typec: Remove one bit support for the Thunderbolt
 rounded/non-rounded cable

Two bits support for the Thunderbolt rounded/non-rounded cable has been
added to the header file.
Hence, removing unused TBT_CABLE_ROUNDED definition from the header file.

Signed-off-by: Utkarsh Patel <utkarsh.h.patel@intel.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
--
changes in v2:
- Removed the fixes tag as there is no functional implication.
--
Link: https://lore.kernel.org/r/20201113202503.6559-5-utkarsh.h.patel@intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/usb/typec_tbt.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/usb/typec_tbt.h b/include/linux/usb/typec_tbt.h
index aad648d14bb3..63dd44b72e0c 100644
--- a/include/linux/usb/typec_tbt.h
+++ b/include/linux/usb/typec_tbt.h
@@ -39,7 +39,6 @@ struct typec_thunderbolt_data {
 #define   TBT_CABLE_USB3_GEN1		1
 #define   TBT_CABLE_USB3_PASSIVE	2
 #define   TBT_CABLE_10_AND_20GBPS	3
-#define TBT_CABLE_ROUNDED		BIT(19)
 #define TBT_CABLE_ROUNDED_SUPPORT(_vdo_) \
 					(((_vdo_) & GENMASK(20, 19)) >> 19)
 #define   TBT_GEN3_NON_ROUNDED                 0
-- 
cgit v1.2.3


From 8a5ca78f603977d6b9b2d7dcb3b1b6ef601d3cc7 Mon Sep 17 00:00:00 2001
From: Prashant Malani <pmalani@chromium.org>
Date: Mon, 16 Nov 2020 12:11:38 -0800
Subject: usb: pd: Add captive Type C cable type

The USB Power Delivery Specification R3.0 adds a captive cable type
to the "USB Type-C plug to USB Type-C/Captive" field (Bits 19-18,
Passive/Active Cable VDO, Table 6-38 & 6-39).

Add the corresponding definition to the Cable VDO header. Also add a
helper macro to get the Type C cable connector type, when provided
the cable VDO.

Cc: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Signed-off-by: Prashant Malani <pmalani@chromium.org>
Reviewed-by: Benson Leung <bleung@chromium.org>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20201116201150.2919178-2-pmalani@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/usb/pd_vdo.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/usb/pd_vdo.h b/include/linux/usb/pd_vdo.h
index 68bdc4e2f5a9..8c5cb5830754 100644
--- a/include/linux/usb/pd_vdo.h
+++ b/include/linux/usb/pd_vdo.h
@@ -177,7 +177,7 @@
  * <31:28> :: Cable HW version
  * <27:24> :: Cable FW version
  * <23:20> :: Reserved, Shall be set to zero
- * <19:18> :: type-C to Type-A/B/C (00b == A, 01 == B, 10 == C)
+ * <19:18> :: type-C to Type-A/B/C/Captive (00b == A, 01 == B, 10 == C, 11 == Captive)
  * <17>    :: Type-C to Plug/Receptacle (0b == plug, 1b == receptacle)
  * <16:13> :: cable latency (0001 == <10ns(~1m length))
  * <12:11> :: cable termination type (11b == both ends active VCONN req)
@@ -193,6 +193,7 @@
 #define CABLE_ATYPE		0
 #define CABLE_BTYPE		1
 #define CABLE_CTYPE		2
+#define CABLE_CAPTIVE		3
 #define CABLE_PLUG		0
 #define CABLE_RECEPTACLE	1
 #define CABLE_CURR_1A5		0
@@ -208,6 +209,7 @@
 	 | (tx1d) << 10 | (tx2d) << 9 | (rx1d) << 8 | (rx2d) << 7	\
 	 | ((cur) & 0x3) << 5 | (vps) << 4 | (sopp) << 3		\
 	 | ((usbss) & 0x7))
+#define VDO_TYPEC_CABLE_TYPE(vdo)	(((vdo) >> 18) & 0x3)
 
 /*
  * AMA VDO
-- 
cgit v1.2.3


From a0ccdc4a77a1b36b682ae60361879eca0a0f88d6 Mon Sep 17 00:00:00 2001
From: Prashant Malani <pmalani@chromium.org>
Date: Mon, 16 Nov 2020 12:11:40 -0800
Subject: usb: typec: Add number of altmodes partner attr

Add a user-visible attribute for the number of alternate modes available
in a partner. This allows userspace to determine whether there are any
remaining alternate modes left to be registered by the kernel driver. It
can begin executing any policy state machine after all available
alternate modes have been registered with the connector class framework.

This value is set to "-1" initially, signifying that a valid number of
alternate modes haven't been set for the partner.

Also add a sysfs file which exposes this attribute. The file remains
hidden as long as the attribute value is -1.

Cc: Benson Leung <bleung@chromium.org>
Cc: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Signed-off-by: Prashant Malani <pmalani@chromium.org>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20201116201150.2919178-3-pmalani@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/ABI/testing/sysfs-class-typec |  8 ++++
 drivers/usb/typec/class.c                   | 66 ++++++++++++++++++++++++++++-
 include/linux/usb/typec.h                   |  1 +
 3 files changed, 74 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/Documentation/ABI/testing/sysfs-class-typec b/Documentation/ABI/testing/sysfs-class-typec
index b7794e02ad20..a195247d83ee 100644
--- a/Documentation/ABI/testing/sysfs-class-typec
+++ b/Documentation/ABI/testing/sysfs-class-typec
@@ -139,6 +139,14 @@ Description:
 		Shows if the partner supports USB Power Delivery communication:
 		Valid values: yes, no
 
+What:		/sys/class/typec/<port>-partner/number_of_alternate_modes
+Date:		November 2020
+Contact:	Prashant Malani <pmalani@chromium.org>
+Description:
+		Shows the number of alternate modes which are advertised by the partner
+		during Power Delivery discovery. This file remains hidden until a value
+		greater than or equal to 0 is set by Type C port driver.
+
 What:		/sys/class/typec/<port>-partner>/identity/
 Date:		April 2017
 Contact:	Heikki Krogerus <heikki.krogerus@linux.intel.com>
diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c
index 35eec707cb51..c7412ddbd311 100644
--- a/drivers/usb/typec/class.c
+++ b/drivers/usb/typec/class.c
@@ -33,6 +33,7 @@ struct typec_partner {
 	struct usb_pd_identity		*identity;
 	enum typec_accessory		accessory;
 	struct ida			mode_ids;
+	int				num_altmodes;
 };
 
 struct typec_port {
@@ -532,12 +533,43 @@ static ssize_t supports_usb_power_delivery_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(supports_usb_power_delivery);
 
+static ssize_t number_of_alternate_modes_show(struct device *dev, struct device_attribute *attr,
+					      char *buf)
+{
+	struct typec_partner *p = to_typec_partner(dev);
+
+	return sysfs_emit(buf, "%d\n", p->num_altmodes);
+}
+static DEVICE_ATTR_RO(number_of_alternate_modes);
+
 static struct attribute *typec_partner_attrs[] = {
 	&dev_attr_accessory_mode.attr,
 	&dev_attr_supports_usb_power_delivery.attr,
+	&dev_attr_number_of_alternate_modes.attr,
+	NULL
+};
+
+static umode_t typec_partner_attr_is_visible(struct kobject *kobj, struct attribute *attr, int n)
+{
+	struct typec_partner *partner = to_typec_partner(kobj_to_dev(kobj));
+
+	if (attr == &dev_attr_number_of_alternate_modes.attr) {
+		if (partner->num_altmodes < 0)
+			return 0;
+	}
+
+	return attr->mode;
+}
+
+static struct attribute_group typec_partner_group = {
+	.is_visible = typec_partner_attr_is_visible,
+	.attrs = typec_partner_attrs
+};
+
+static const struct attribute_group *typec_partner_groups[] = {
+	&typec_partner_group,
 	NULL
 };
-ATTRIBUTE_GROUPS(typec_partner);
 
 static void typec_partner_release(struct device *dev)
 {
@@ -570,6 +602,37 @@ int typec_partner_set_identity(struct typec_partner *partner)
 }
 EXPORT_SYMBOL_GPL(typec_partner_set_identity);
 
+/**
+ * typec_partner_set_num_altmodes - Set the number of available partner altmodes
+ * @partner: The partner to be updated.
+ * @num_alt_modes: The number of altmodes we want to specify as available.
+ *
+ * This routine is used to report the number of alternate modes supported by the
+ * partner. This value is *not* enforced in alternate mode registration routines.
+ *
+ * @partner.num_altmodes is set to -1 on partner registration, denoting that
+ * a valid value has not been set for it yet.
+ *
+ * Returns 0 on success or negative error number on failure.
+ */
+int typec_partner_set_num_altmodes(struct typec_partner *partner, int num_altmodes)
+{
+	int ret;
+
+	if (num_altmodes < 0)
+		return -EINVAL;
+
+	partner->num_altmodes = num_altmodes;
+	ret = sysfs_update_group(&partner->dev.kobj, &typec_partner_group);
+	if (ret < 0)
+		return ret;
+
+	sysfs_notify(&partner->dev.kobj, NULL, "number_of_alternate_modes");
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(typec_partner_set_num_altmodes);
+
 /**
  * typec_partner_register_altmode - Register USB Type-C Partner Alternate Mode
  * @partner: USB Type-C Partner that supports the alternate mode
@@ -612,6 +675,7 @@ struct typec_partner *typec_register_partner(struct typec_port *port,
 	ida_init(&partner->mode_ids);
 	partner->usb_pd = desc->usb_pd;
 	partner->accessory = desc->accessory;
+	partner->num_altmodes = -1;
 
 	if (desc->identity) {
 		/*
diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h
index 6be558045942..bc6b1a71cb8a 100644
--- a/include/linux/usb/typec.h
+++ b/include/linux/usb/typec.h
@@ -126,6 +126,7 @@ struct typec_altmode_desc {
 	enum typec_port_data	roles;
 };
 
+int typec_partner_set_num_altmodes(struct typec_partner *partner, int num_altmodes);
 struct typec_altmode
 *typec_partner_register_altmode(struct typec_partner *partner,
 				const struct typec_altmode_desc *desc);
-- 
cgit v1.2.3


From a30a00e37ceb094f949e4d96c2c586e6503b5d1d Mon Sep 17 00:00:00 2001
From: Badhri Jagan Sridharan <badhri@google.com>
Date: Wed, 28 Oct 2020 23:31:32 -0700
Subject: usb: typec: tcpm: frs sourcing vbus callback

During FRS hardware autonomously starts to source vbus. Provide
callback to perform chip specific operations.

Signed-off-by: Badhri Jagan Sridharan <badhri@google.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20201029063138.1429760-5-badhri@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/tcpm.c | 9 +++++++++
 include/linux/usb/tcpm.h      | 4 ++++
 2 files changed, 13 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index a091a63758f4..c196bd4b8a37 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -4091,7 +4091,16 @@ static void _tcpm_pd_vbus_on(struct tcpm_port *port)
 	case SRC_TRY_DEBOUNCE:
 		/* Do nothing, waiting for sink detection */
 		break;
+	case FR_SWAP_SEND:
+	case FR_SWAP_SEND_TIMEOUT:
+	case FR_SWAP_SNK_SRC_TRANSITION_TO_OFF:
+	case FR_SWAP_SNK_SRC_SOURCE_VBUS_APPLIED:
+		if (port->tcpc->frs_sourcing_vbus)
+			port->tcpc->frs_sourcing_vbus(port->tcpc);
+		break;
 	case FR_SWAP_SNK_SRC_NEW_SINK_READY:
+		if (port->tcpc->frs_sourcing_vbus)
+			port->tcpc->frs_sourcing_vbus(port->tcpc);
 		tcpm_set_state(port, FR_SWAP_SNK_SRC_SOURCE_VBUS_APPLIED, 0);
 		break;
 
diff --git a/include/linux/usb/tcpm.h b/include/linux/usb/tcpm.h
index 09762d26fa0c..7303f518ba49 100644
--- a/include/linux/usb/tcpm.h
+++ b/include/linux/usb/tcpm.h
@@ -83,6 +83,9 @@ enum tcpm_transmit_type {
  *		Optional; Called to enable/disable PD 3.0 fast role swap.
  *		Enabling frs is accessory dependent as not all PD3.0
  *		accessories support fast role swap.
+ * @frs_sourcing_vbus:
+ *		Optional; Called to notify that vbus is now being sourced.
+ *		Low level drivers can perform chip specific operations, if any.
  */
 struct tcpc_dev {
 	struct fwnode_handle *fwnode;
@@ -109,6 +112,7 @@ struct tcpc_dev {
 			   const struct pd_message *msg);
 	int (*set_bist_data)(struct tcpc_dev *dev, bool on);
 	int (*enable_frs)(struct tcpc_dev *dev, bool enable);
+	void (*frs_sourcing_vbus)(struct tcpc_dev *dev);
 };
 
 struct tcpm_port;
-- 
cgit v1.2.3


From f321a02caebdd0c56e167610cda2fa148cd96e8b Mon Sep 17 00:00:00 2001
From: Badhri Jagan Sridharan <badhri@google.com>
Date: Wed, 28 Oct 2020 23:31:35 -0700
Subject: usb: typec: tcpm: Implement enabling Auto Discharge disconnect
 support

TCPCI spec allows TCPC hardware to autonomously discharge the vbus
capacitance upon disconnect. The expectation is that the TCPM enables
AutoDischargeDisconnect while entering SNK/SRC_ATTACHED states. Hardware
then automously discharges vbus when the vbus falls below a certain
threshold i.e. VBUS_SINK_DISCONNECT_THRESHOLD.

Apart from enabling the vbus discharge circuit, AutoDischargeDisconnect
is also used a flag to move TCPCI based TCPC implementations into
Attached.Snk/Attached.Src state as mentioned in
Figure 4-15. TCPC State Diagram before a Connection of the
USB Type-C Port Controller Interface Specification.
In such TCPC implementations, setting AutoDischargeDisconnect would
prevent TCPC into entering "Connection_Invalid" state as well.

Signed-off-by: Badhri Jagan Sridharan <badhri@google.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20201029063138.1429760-8-badhri@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/tcpm.c | 60 ++++++++++++++++++++++++++++++++++++++++---
 include/linux/usb/tcpm.h      | 15 +++++++++++
 2 files changed, 71 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index c196bd4b8a37..4aac0efdb720 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -1706,6 +1706,24 @@ static void tcpm_handle_alert(struct tcpm_port *port, const __le32 *payload,
 	}
 }
 
+static int tcpm_set_auto_vbus_discharge_threshold(struct tcpm_port *port,
+						  enum typec_pwr_opmode mode, bool pps_active,
+						  u32 requested_vbus_voltage)
+{
+	int ret;
+
+	if (!port->tcpc->set_auto_vbus_discharge_threshold)
+		return 0;
+
+	ret = port->tcpc->set_auto_vbus_discharge_threshold(port->tcpc, mode, pps_active,
+							    requested_vbus_voltage);
+	tcpm_log_force(port,
+		       "set_auto_vbus_discharge_threshold mode:%d pps_active:%c vbus:%u ret:%d",
+		       mode, pps_active ? 'y' : 'n', requested_vbus_voltage, ret);
+
+	return ret;
+}
+
 static void tcpm_pd_data_request(struct tcpm_port *port,
 				 const struct pd_message *msg)
 {
@@ -1876,6 +1894,10 @@ static void tcpm_pd_ctrl_request(struct tcpm_port *port,
 						       port->current_limit,
 						       port->supply_voltage);
 				port->explicit_contract = true;
+				tcpm_set_auto_vbus_discharge_threshold(port,
+								       TYPEC_PWR_MODE_PD,
+								       port->pps_data.active,
+								       port->supply_voltage);
 				tcpm_set_state(port, SNK_READY, 0);
 			} else {
 				/*
@@ -2790,8 +2812,12 @@ static int tcpm_src_attach(struct tcpm_port *port)
 	if (ret < 0)
 		return ret;
 
-	ret = tcpm_set_roles(port, true, TYPEC_SOURCE,
-			     tcpm_data_role_for_source(port));
+	if (port->tcpc->enable_auto_vbus_discharge) {
+		ret = port->tcpc->enable_auto_vbus_discharge(port->tcpc, true);
+		tcpm_log_force(port, "enable vbus discharge ret:%d", ret);
+	}
+
+	ret = tcpm_set_roles(port, true, TYPEC_SOURCE, tcpm_data_role_for_source(port));
 	if (ret < 0)
 		return ret;
 
@@ -2858,6 +2884,12 @@ static void tcpm_unregister_altmodes(struct tcpm_port *port)
 
 static void tcpm_reset_port(struct tcpm_port *port)
 {
+	int ret;
+
+	if (port->tcpc->enable_auto_vbus_discharge) {
+		ret = port->tcpc->enable_auto_vbus_discharge(port->tcpc, false);
+		tcpm_log_force(port, "Disable vbus discharge ret:%d", ret);
+	}
 	tcpm_unregister_altmodes(port);
 	tcpm_typec_disconnect(port);
 	port->attached = false;
@@ -2922,8 +2954,13 @@ static int tcpm_snk_attach(struct tcpm_port *port)
 	if (ret < 0)
 		return ret;
 
-	ret = tcpm_set_roles(port, true, TYPEC_SINK,
-			     tcpm_data_role_for_sink(port));
+	if (port->tcpc->enable_auto_vbus_discharge) {
+		tcpm_set_auto_vbus_discharge_threshold(port, TYPEC_PWR_MODE_USB, false, VSAFE5V);
+		ret = port->tcpc->enable_auto_vbus_discharge(port->tcpc, true);
+		tcpm_log_force(port, "enable vbus discharge ret:%d", ret);
+	}
+
+	ret = tcpm_set_roles(port, true, TYPEC_SINK, tcpm_data_role_for_sink(port));
 	if (ret < 0)
 		return ret;
 
@@ -3507,6 +3544,8 @@ static void run_state_machine(struct tcpm_port *port)
 		tcpm_set_state(port, SRC_UNATTACHED, PD_T_PS_SOURCE_ON);
 		break;
 	case SNK_HARD_RESET_SINK_OFF:
+		/* Do not discharge/disconnect during hard reseet */
+		tcpm_set_auto_vbus_discharge_threshold(port, TYPEC_PWR_MODE_USB, false, 0);
 		memset(&port->pps_data, 0, sizeof(port->pps_data));
 		tcpm_set_vconn(port, false);
 		if (port->pd_capable)
@@ -3549,6 +3588,7 @@ static void run_state_machine(struct tcpm_port *port)
 			tcpm_set_charge(port, true);
 		}
 		tcpm_set_attached_state(port, true);
+		tcpm_set_auto_vbus_discharge_threshold(port, TYPEC_PWR_MODE_USB, false, VSAFE5V);
 		tcpm_set_state(port, SNK_STARTUP, 0);
 		break;
 
@@ -3650,6 +3690,10 @@ static void run_state_machine(struct tcpm_port *port)
 			tcpm_set_state(port, PR_SWAP_SNK_SRC_SINK_OFF, 0);
 		break;
 	case PR_SWAP_SRC_SNK_TRANSITION_OFF:
+		/*
+		 * Prevent vbus discharge circuit from turning on during PR_SWAP
+		 * as this is not a disconnect.
+		 */
 		tcpm_set_vbus(port, false);
 		port->explicit_contract = false;
 		/* allow time for Vbus discharge, must be < tSrcSwapStdby */
@@ -3678,9 +3722,17 @@ static void run_state_machine(struct tcpm_port *port)
 		tcpm_set_state_cond(port, SNK_UNATTACHED, PD_T_PS_SOURCE_ON);
 		break;
 	case PR_SWAP_SRC_SNK_SINK_ON:
+		/* Set the vbus disconnect threshold for implicit contract */
+		tcpm_set_auto_vbus_discharge_threshold(port, TYPEC_PWR_MODE_USB, false, VSAFE5V);
 		tcpm_set_state(port, SNK_STARTUP, 0);
 		break;
 	case PR_SWAP_SNK_SRC_SINK_OFF:
+		/*
+		 * Prevent vbus discharge circuit from turning on during PR_SWAP
+		 * as this is not a disconnect.
+		 */
+		tcpm_set_auto_vbus_discharge_threshold(port, TYPEC_PWR_MODE_USB,
+						       port->pps_data.active, 0);
 		tcpm_set_charge(port, false);
 		tcpm_set_state(port, hard_reset_state(port),
 			       PD_T_PS_SOURCE_OFF);
diff --git a/include/linux/usb/tcpm.h b/include/linux/usb/tcpm.h
index 7303f518ba49..e68aaa12886f 100644
--- a/include/linux/usb/tcpm.h
+++ b/include/linux/usb/tcpm.h
@@ -86,6 +86,18 @@ enum tcpm_transmit_type {
  * @frs_sourcing_vbus:
  *		Optional; Called to notify that vbus is now being sourced.
  *		Low level drivers can perform chip specific operations, if any.
+ * @enable_auto_vbus_discharge:
+ *		Optional; TCPCI spec based TCPC implementations can optionally
+ *		support hardware to autonomously dischrge vbus upon disconnecting
+ *		as sink or source. TCPM signals TCPC to enable the mechanism upon
+ *		entering connected state and signals disabling upon disconnect.
+ * @set_auto_vbus_discharge_threshold:
+ *		Mandatory when enable_auto_vbus_discharge is implemented. TCPM
+ *		calls this function to allow lower levels drivers to program the
+ *		vbus threshold voltage below which the vbus discharge circuit
+ *		will be turned on. requested_vbus_voltage is set to 0 when vbus
+ *		is going to disappear knowingly i.e. during PR_SWAP and
+ *		HARD_RESET etc.
  */
 struct tcpc_dev {
 	struct fwnode_handle *fwnode;
@@ -113,6 +125,9 @@ struct tcpc_dev {
 	int (*set_bist_data)(struct tcpc_dev *dev, bool on);
 	int (*enable_frs)(struct tcpc_dev *dev, bool enable);
 	void (*frs_sourcing_vbus)(struct tcpc_dev *dev);
+	int (*enable_auto_vbus_discharge)(struct tcpc_dev *dev, bool enable);
+	int (*set_auto_vbus_discharge_threshold)(struct tcpc_dev *dev, enum typec_pwr_opmode mode,
+						 bool pps_active, u32 requested_vbus_voltage);
 };
 
 struct tcpm_port;
-- 
cgit v1.2.3


From e1e52361c61afdf81d81cfbbfa3ce08971e60f50 Mon Sep 17 00:00:00 2001
From: Prashant Malani <pmalani@chromium.org>
Date: Mon, 16 Nov 2020 12:11:42 -0800
Subject: usb: typec: Add plug num_altmodes sysfs attr

Add a field to the typec_plug struct to record the number of available
altmodes as well as the corresponding sysfs attribute to expose this to
userspace.

This allows userspace to determine whether there are any
remaining alternate modes left to be registered by the kernel driver. It
can begin executing any policy state machine after all available
alternate modes have been registered with the connector class framework.

This value is set to "-1" initially, signifying that a valid number of
alternate modes haven't been set for the plug. The sysfs file remains
hidden as long as the attribute value is -1.

We re-use the partner attribute for number_of_alternate_modes since the
usage and name is similar, and update the corresponding *_show() command
to support both partner and plugs.

Signed-off-by: Prashant Malani <pmalani@chromium.org>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20201116201150.2919178-4-pmalani@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/ABI/testing/sysfs-class-typec |  9 ++++
 drivers/usb/typec/class.c                   | 77 ++++++++++++++++++++++++++++-
 include/linux/usb/typec.h                   |  1 +
 3 files changed, 85 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/ABI/testing/sysfs-class-typec b/Documentation/ABI/testing/sysfs-class-typec
index a195247d83ee..4eccb343fc7b 100644
--- a/Documentation/ABI/testing/sysfs-class-typec
+++ b/Documentation/ABI/testing/sysfs-class-typec
@@ -210,6 +210,15 @@ Description:
 		- type-c
 		- captive
 
+What:		/sys/class/typec/<port>-<plug>/number_of_alternate_modes
+Date:		November 2020
+Contact:	Prashant Malani <pmalani@chromium.org>
+Description:
+		Shows the number of alternate modes which are advertised by the plug
+		associated with a particular cable during Power Delivery discovery.
+		This file remains hidden until a value greater than or equal to 0
+		is set by Type C port driver.
+
 What:		/sys/class/typec/<port>-cable/identity/
 Date:		April 2017
 Contact:	Heikki Krogerus <heikki.krogerus@linux.intel.com>
diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c
index c7412ddbd311..e68798599ca8 100644
--- a/drivers/usb/typec/class.c
+++ b/drivers/usb/typec/class.c
@@ -18,6 +18,7 @@ struct typec_plug {
 	struct device			dev;
 	enum typec_plug_index		index;
 	struct ida			mode_ids;
+	int				num_altmodes;
 };
 
 struct typec_cable {
@@ -536,9 +537,21 @@ static DEVICE_ATTR_RO(supports_usb_power_delivery);
 static ssize_t number_of_alternate_modes_show(struct device *dev, struct device_attribute *attr,
 					      char *buf)
 {
-	struct typec_partner *p = to_typec_partner(dev);
+	struct typec_partner *partner;
+	struct typec_plug *plug;
+	int num_altmodes;
+
+	if (is_typec_partner(dev)) {
+		partner = to_typec_partner(dev);
+		num_altmodes = partner->num_altmodes;
+	} else if (is_typec_plug(dev)) {
+		plug = to_typec_plug(dev);
+		num_altmodes = plug->num_altmodes;
+	} else {
+		return 0;
+	}
 
-	return sysfs_emit(buf, "%d\n", p->num_altmodes);
+	return sysfs_emit(buf, "%d\n", num_altmodes);
 }
 static DEVICE_ATTR_RO(number_of_alternate_modes);
 
@@ -726,11 +739,70 @@ static void typec_plug_release(struct device *dev)
 	kfree(plug);
 }
 
+static struct attribute *typec_plug_attrs[] = {
+	&dev_attr_number_of_alternate_modes.attr,
+	NULL
+};
+
+static umode_t typec_plug_attr_is_visible(struct kobject *kobj, struct attribute *attr, int n)
+{
+	struct typec_plug *plug = to_typec_plug(kobj_to_dev(kobj));
+
+	if (attr == &dev_attr_number_of_alternate_modes.attr) {
+		if (plug->num_altmodes < 0)
+			return 0;
+	}
+
+	return attr->mode;
+}
+
+static struct attribute_group typec_plug_group = {
+	.is_visible = typec_plug_attr_is_visible,
+	.attrs = typec_plug_attrs
+};
+
+static const struct attribute_group *typec_plug_groups[] = {
+	&typec_plug_group,
+	NULL
+};
+
 static const struct device_type typec_plug_dev_type = {
 	.name = "typec_plug",
+	.groups = typec_plug_groups,
 	.release = typec_plug_release,
 };
 
+/**
+ * typec_plug_set_num_altmodes - Set the number of available plug altmodes
+ * @plug: The plug to be updated.
+ * @num_altmodes: The number of altmodes we want to specify as available.
+ *
+ * This routine is used to report the number of alternate modes supported by the
+ * plug. This value is *not* enforced in alternate mode registration routines.
+ *
+ * @plug.num_altmodes is set to -1 on plug registration, denoting that
+ * a valid value has not been set for it yet.
+ *
+ * Returns 0 on success or negative error number on failure.
+ */
+int typec_plug_set_num_altmodes(struct typec_plug *plug, int num_altmodes)
+{
+	int ret;
+
+	if (num_altmodes < 0)
+		return -EINVAL;
+
+	plug->num_altmodes = num_altmodes;
+	ret = sysfs_update_group(&plug->dev.kobj, &typec_plug_group);
+	if (ret < 0)
+		return ret;
+
+	sysfs_notify(&plug->dev.kobj, NULL, "number_of_alternate_modes");
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(typec_plug_set_num_altmodes);
+
 /**
  * typec_plug_register_altmode - Register USB Type-C Cable Plug Alternate Mode
  * @plug: USB Type-C Cable Plug that supports the alternate mode
@@ -776,6 +848,7 @@ struct typec_plug *typec_register_plug(struct typec_cable *cable,
 	sprintf(name, "plug%d", desc->index);
 
 	ida_init(&plug->mode_ids);
+	plug->num_altmodes = -1;
 	plug->index = desc->index;
 	plug->dev.class = typec_class;
 	plug->dev.parent = &cable->dev;
diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h
index bc6b1a71cb8a..54475323f83b 100644
--- a/include/linux/usb/typec.h
+++ b/include/linux/usb/typec.h
@@ -130,6 +130,7 @@ int typec_partner_set_num_altmodes(struct typec_partner *partner, int num_altmod
 struct typec_altmode
 *typec_partner_register_altmode(struct typec_partner *partner,
 				const struct typec_altmode_desc *desc);
+int typec_plug_set_num_altmodes(struct typec_plug *plug, int num_altmodes);
 struct typec_altmode
 *typec_plug_register_altmode(struct typec_plug *plug,
 			     const struct typec_altmode_desc *desc);
-- 
cgit v1.2.3


From 4d213e76a359e540ca786ee937da7f35faa8e5f8 Mon Sep 17 00:00:00 2001
From: Zhenzhong Duan <zhenzhong.duan@gmail.com>
Date: Tue, 10 Nov 2020 15:19:08 +0800
Subject: iommu/vt-d: Avoid panic if iommu init fails in tboot system

"intel_iommu=off" command line is used to disable iommu but iommu is force
enabled in a tboot system for security reason.

However for better performance on high speed network device, a new option
"intel_iommu=tboot_noforce" is introduced to disable the force on.

By default kernel should panic if iommu init fail in tboot for security
reason, but it's unnecessory if we use "intel_iommu=tboot_noforce,off".

Fix the code setting force_on and move intel_iommu_tboot_noforce
from tboot code to intel iommu code.

Fixes: 7304e8f28bb2 ("iommu/vt-d: Correctly disable Intel IOMMU force on")
Signed-off-by: Zhenzhong Duan <zhenzhong.duan@gmail.com>
Tested-by: Lukasz Hawrylko <lukasz.hawrylko@linux.intel.com>
Acked-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20201110071908.3133-1-zhenzhong.duan@gmail.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/x86/kernel/tboot.c     | 3 ---
 drivers/iommu/intel/iommu.c | 5 +++--
 include/linux/intel-iommu.h | 1 -
 3 files changed, 3 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index 992fb1415c0f..420be871d9d4 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -514,9 +514,6 @@ int tboot_force_iommu(void)
 	if (!tboot_enabled())
 		return 0;
 
-	if (intel_iommu_tboot_noforce)
-		return 1;
-
 	if (no_iommu || swiotlb || dmar_disabled)
 		pr_warn("Forcing Intel-IOMMU to enabled\n");
 
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 1b1ca63e6bbe..4d9b298002f0 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -179,7 +179,7 @@ static int rwbf_quirk;
  * (used when kernel is launched w/ TXT)
  */
 static int force_on = 0;
-int intel_iommu_tboot_noforce;
+static int intel_iommu_tboot_noforce;
 static int no_platform_optin;
 
 #define ROOT_ENTRY_NR (VTD_PAGE_SIZE/sizeof(struct root_entry))
@@ -4885,7 +4885,8 @@ int __init intel_iommu_init(void)
 	 * Intel IOMMU is required for a TXT/tboot launch or platform
 	 * opt in, so enforce that.
 	 */
-	force_on = tboot_force_iommu() || platform_optin_force_iommu();
+	force_on = (!intel_iommu_tboot_noforce && tboot_force_iommu()) ||
+		    platform_optin_force_iommu();
 
 	if (iommu_init_mempool()) {
 		if (force_on)
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index fbf5b3e7707e..d956987ed032 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -798,7 +798,6 @@ extern int iommu_calculate_agaw(struct intel_iommu *iommu);
 extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu);
 extern int dmar_disabled;
 extern int intel_iommu_enabled;
-extern int intel_iommu_tboot_noforce;
 extern int intel_iommu_gfx_mapped;
 #else
 static inline int iommu_calculate_agaw(struct intel_iommu *iommu)
-- 
cgit v1.2.3


From d04a53b1c48766665806eb75b73137734abdaa95 Mon Sep 17 00:00:00 2001
From: Ahmad Fatoum <a.fatoum@pengutronix.de>
Date: Tue, 17 Nov 2020 22:38:26 +0100
Subject: ptp: document struct ptp_clock_request members

It's arguable most people interested in configuring a PPS signal
want it as external output, not as kernel input. PTP_CLK_REQ_PPS
is for input though. Add documentation to nudge readers into
the correct direction.

Signed-off-by: Ahmad Fatoum <a.fatoum@pengutronix.de>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Link: https://lore.kernel.org/r/20201117213826.18235-1-a.fatoum@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/ptp_clock_kernel.h | 13 +++++++++++++
 1 file changed, 13 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h
index d3e8ba5c7125..0d47fd33b228 100644
--- a/include/linux/ptp_clock_kernel.h
+++ b/include/linux/ptp_clock_kernel.h
@@ -12,6 +12,19 @@
 #include <linux/pps_kernel.h>
 #include <linux/ptp_clock.h>
 
+/**
+ * struct ptp_clock_request - request PTP clock event
+ *
+ * @type:   The type of the request.
+ *	    EXTTS:  Configure external trigger timestamping
+ *	    PEROUT: Configure periodic output signal (e.g. PPS)
+ *	    PPS:    trigger internal PPS event for input
+ *	            into kernel PPS subsystem
+ * @extts:  describes configuration for external trigger timestamping.
+ *          This is only valid when event == PTP_CLK_REQ_EXTTS.
+ * @perout: describes configuration for periodic output.
+ *	    This is only valid when event == PTP_CLK_REQ_PEROUT.
+ */
 
 struct ptp_clock_request {
 	enum {
-- 
cgit v1.2.3


From d055126180564a57fe533728a4e93d0cb53d49b3 Mon Sep 17 00:00:00 2001
From: Dmitrii Banshchikov <me@ubique.spb.ru>
Date: Tue, 17 Nov 2020 18:45:49 +0000
Subject: bpf: Add bpf_ktime_get_coarse_ns helper

The helper uses CLOCK_MONOTONIC_COARSE source of time that is less
accurate but more performant.

We have a BPF CGROUP_SKB firewall that supports event logging through
bpf_perf_event_output(). Each event has a timestamp and currently we use
bpf_ktime_get_ns() for it. Use of bpf_ktime_get_coarse_ns() saves ~15-20
ns in time required for event logging.

bpf_ktime_get_ns():
EgressLogByRemoteEndpoint                              113.82ns    8.79M

bpf_ktime_get_coarse_ns():
EgressLogByRemoteEndpoint                               95.40ns   10.48M

Signed-off-by: Dmitrii Banshchikov <me@ubique.spb.ru>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20201117184549.257280-1-me@ubique.spb.ru
---
 include/linux/bpf.h            |  1 +
 include/uapi/linux/bpf.h       | 11 +++++++++++
 kernel/bpf/core.c              |  1 +
 kernel/bpf/helpers.c           | 13 +++++++++++++
 kernel/trace/bpf_trace.c       |  2 ++
 tools/include/uapi/linux/bpf.h | 11 +++++++++++
 6 files changed, 39 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 581b2a2e78eb..e1bcb6d7345c 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1842,6 +1842,7 @@ extern const struct bpf_func_proto bpf_copy_from_user_proto;
 extern const struct bpf_func_proto bpf_snprintf_btf_proto;
 extern const struct bpf_func_proto bpf_per_cpu_ptr_proto;
 extern const struct bpf_func_proto bpf_this_cpu_ptr_proto;
+extern const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto;
 
 const struct bpf_func_proto *bpf_tracing_func_proto(
 	enum bpf_func_id func_id, const struct bpf_prog *prog);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index a52299b80b9d..3ca6146f001a 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3797,6 +3797,16 @@ union bpf_attr {
  *		is cleared if the flag is not specified.
  *	Return
  *		**-EINVAL** if invalid *flags* are passed, zero otherwise.
+ *
+ * u64 bpf_ktime_get_coarse_ns(void)
+ * 	Description
+ * 		Return a coarse-grained version of the time elapsed since
+ * 		system boot, in nanoseconds. Does not include time the system
+ * 		was suspended.
+ *
+ * 		See: **clock_gettime**\ (**CLOCK_MONOTONIC_COARSE**)
+ * 	Return
+ * 		Current *ktime*.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3959,6 +3969,7 @@ union bpf_attr {
 	FN(task_storage_delete),	\
 	FN(get_current_task_btf),	\
 	FN(bprm_opts_set),		\
+	FN(ktime_get_coarse_ns),	\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 55454d2278b1..ff55cbcfbab4 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2211,6 +2211,7 @@ const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak;
 const struct bpf_func_proto bpf_get_numa_node_id_proto __weak;
 const struct bpf_func_proto bpf_ktime_get_ns_proto __weak;
 const struct bpf_func_proto bpf_ktime_get_boot_ns_proto __weak;
+const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto __weak;
 
 const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak;
 const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak;
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 25520f5eeaf6..2c395deae279 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -167,6 +167,17 @@ const struct bpf_func_proto bpf_ktime_get_boot_ns_proto = {
 	.ret_type	= RET_INTEGER,
 };
 
+BPF_CALL_0(bpf_ktime_get_coarse_ns)
+{
+	return ktime_get_coarse_ns();
+}
+
+const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto = {
+	.func		= bpf_ktime_get_coarse_ns,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+};
+
 BPF_CALL_0(bpf_get_current_pid_tgid)
 {
 	struct task_struct *task = current;
@@ -685,6 +696,8 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_ktime_get_ns_proto;
 	case BPF_FUNC_ktime_get_boot_ns:
 		return &bpf_ktime_get_boot_ns_proto;
+	case BPF_FUNC_ktime_get_coarse_ns:
+		return &bpf_ktime_get_coarse_ns_proto;
 	case BPF_FUNC_ringbuf_output:
 		return &bpf_ringbuf_output_proto;
 	case BPF_FUNC_ringbuf_reserve:
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 02986c7b90eb..d255bc9b2bfa 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1280,6 +1280,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_ktime_get_ns_proto;
 	case BPF_FUNC_ktime_get_boot_ns:
 		return &bpf_ktime_get_boot_ns_proto;
+	case BPF_FUNC_ktime_get_coarse_ns:
+		return &bpf_ktime_get_coarse_ns_proto;
 	case BPF_FUNC_tail_call:
 		return &bpf_tail_call_proto;
 	case BPF_FUNC_get_current_pid_tgid:
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index a52299b80b9d..3ca6146f001a 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3797,6 +3797,16 @@ union bpf_attr {
  *		is cleared if the flag is not specified.
  *	Return
  *		**-EINVAL** if invalid *flags* are passed, zero otherwise.
+ *
+ * u64 bpf_ktime_get_coarse_ns(void)
+ * 	Description
+ * 		Return a coarse-grained version of the time elapsed since
+ * 		system boot, in nanoseconds. Does not include time the system
+ * 		was suspended.
+ *
+ * 		See: **clock_gettime**\ (**CLOCK_MONOTONIC_COARSE**)
+ * 	Return
+ * 		Current *ktime*.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3959,6 +3969,7 @@ union bpf_attr {
 	FN(task_storage_delete),	\
 	FN(get_current_task_btf),	\
 	FN(bprm_opts_set),		\
+	FN(ktime_get_coarse_ns),	\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
-- 
cgit v1.2.3


From f2bcc2fa275b913093ff5b403be5d11342fdb055 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Mon, 16 Nov 2020 17:21:15 +0100
Subject: atm: nicstar: Replace in_interrupt() usage

push_scqe() uses in_interrupt() to figure out if it is allowed to sleep.

The usage of in_interrupt() in drivers is phased out and Linus clearly
requested that code which changes behaviour depending on context should
either be separated or the context be conveyed in an argument passed by the
caller, which usually knows the context.

Aside of that in_interrupt() is not correct as it does not catch preempt
disabled regions which neither can sleep.

ns_send() (the only caller of push_scqe()) has the following callers:

- vcc_sendmsg() used as proto_ops::sendmsg is expected to be invoked in
  preemtible context.
  -> vcc->dev->ops->send() (ns_send())

- atm_vcc::send via atmdev_ops::send either directly (pointer copied by
  atm_init_aal34() or atm_init_aal5()) or via atm_send_aal0().
  This is invoked by drivers (like br2684, clip, pppoatm, ...) which are
  called from net_device_ops::ndo_start_xmit with BH disabled.

Add atmdev_ops::send_bh which is used by callers from BH context
(atm_send_aal*()) and if this callback missing then ::send is used
instead.
Implement this callback in nicstar and use it to replace in_interrupt().

Cc: Chas Williams <3chas3@gmail.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/atm/nicstar.c  | 24 ++++++++++++++++++------
 include/linux/atmdev.h |  1 +
 net/atm/raw.c          | 12 ++++++++++--
 3 files changed, 29 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/atm/nicstar.c b/drivers/atm/nicstar.c
index 7af74fb450a0..a602e6b96ff7 100644
--- a/drivers/atm/nicstar.c
+++ b/drivers/atm/nicstar.c
@@ -130,8 +130,9 @@ static int ns_open(struct atm_vcc *vcc);
 static void ns_close(struct atm_vcc *vcc);
 static void fill_tst(ns_dev * card, int n, vc_map * vc);
 static int ns_send(struct atm_vcc *vcc, struct sk_buff *skb);
+static int ns_send_bh(struct atm_vcc *vcc, struct sk_buff *skb);
 static int push_scqe(ns_dev * card, vc_map * vc, scq_info * scq, ns_scqe * tbd,
-		     struct sk_buff *skb);
+		     struct sk_buff *skb, bool may_sleep);
 static void process_tsq(ns_dev * card);
 static void drain_scq(ns_dev * card, scq_info * scq, int pos);
 static void process_rsq(ns_dev * card);
@@ -160,6 +161,7 @@ static const struct atmdev_ops atm_ops = {
 	.close = ns_close,
 	.ioctl = ns_ioctl,
 	.send = ns_send,
+	.send_bh = ns_send_bh,
 	.phy_put = ns_phy_put,
 	.phy_get = ns_phy_get,
 	.proc_read = ns_proc_read,
@@ -1620,7 +1622,7 @@ static void fill_tst(ns_dev * card, int n, vc_map * vc)
 	card->tst_addr = new_tst;
 }
 
-static int ns_send(struct atm_vcc *vcc, struct sk_buff *skb)
+static int _ns_send(struct atm_vcc *vcc, struct sk_buff *skb, bool may_sleep)
 {
 	ns_dev *card;
 	vc_map *vc;
@@ -1704,7 +1706,7 @@ static int ns_send(struct atm_vcc *vcc, struct sk_buff *skb)
 		scq = card->scq0;
 	}
 
-	if (push_scqe(card, vc, scq, &scqe, skb) != 0) {
+	if (push_scqe(card, vc, scq, &scqe, skb, may_sleep) != 0) {
 		atomic_inc(&vcc->stats->tx_err);
 		dev_kfree_skb_any(skb);
 		return -EIO;
@@ -1714,8 +1716,18 @@ static int ns_send(struct atm_vcc *vcc, struct sk_buff *skb)
 	return 0;
 }
 
+static int ns_send(struct atm_vcc *vcc, struct sk_buff *skb)
+{
+	return _ns_send(vcc, skb, true);
+}
+
+static int ns_send_bh(struct atm_vcc *vcc, struct sk_buff *skb)
+{
+	return _ns_send(vcc, skb, false);
+}
+
 static int push_scqe(ns_dev * card, vc_map * vc, scq_info * scq, ns_scqe * tbd,
-		     struct sk_buff *skb)
+		     struct sk_buff *skb, bool may_sleep)
 {
 	unsigned long flags;
 	ns_scqe tsr;
@@ -1726,7 +1738,7 @@ static int push_scqe(ns_dev * card, vc_map * vc, scq_info * scq, ns_scqe * tbd,
 
 	spin_lock_irqsave(&scq->lock, flags);
 	while (scq->tail == scq->next) {
-		if (in_interrupt()) {
+		if (!may_sleep) {
 			spin_unlock_irqrestore(&scq->lock, flags);
 			printk("nicstar%d: Error pushing TBD.\n", card->index);
 			return 1;
@@ -1771,7 +1783,7 @@ static int push_scqe(ns_dev * card, vc_map * vc, scq_info * scq, ns_scqe * tbd,
 		int has_run = 0;
 
 		while (scq->tail == scq->next) {
-			if (in_interrupt()) {
+			if (!may_sleep) {
 				data = scq_virt_to_bus(scq, scq->next);
 				ns_write_sram(card, scq->scd, &data, 1);
 				spin_unlock_irqrestore(&scq->lock, flags);
diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h
index 5d5ff2203fa2..d7493016cd46 100644
--- a/include/linux/atmdev.h
+++ b/include/linux/atmdev.h
@@ -186,6 +186,7 @@ struct atmdev_ops { /* only send is required */
 			    void __user *arg);
 #endif
 	int (*send)(struct atm_vcc *vcc,struct sk_buff *skb);
+	int (*send_bh)(struct atm_vcc *vcc, struct sk_buff *skb);
 	int (*send_oam)(struct atm_vcc *vcc,void *cell,int flags);
 	void (*phy_put)(struct atm_dev *dev,unsigned char value,
 	    unsigned long addr);
diff --git a/net/atm/raw.c b/net/atm/raw.c
index b3ba44aab0ee..2b5f78a7ec3e 100644
--- a/net/atm/raw.c
+++ b/net/atm/raw.c
@@ -54,6 +54,8 @@ static int atm_send_aal0(struct atm_vcc *vcc, struct sk_buff *skb)
 		kfree_skb(skb);
 		return -EADDRNOTAVAIL;
 	}
+	if (vcc->dev->ops->send_bh)
+		return vcc->dev->ops->send_bh(vcc, skb);
 	return vcc->dev->ops->send(vcc, skb);
 }
 
@@ -71,7 +73,10 @@ int atm_init_aal34(struct atm_vcc *vcc)
 	vcc->push = atm_push_raw;
 	vcc->pop = atm_pop_raw;
 	vcc->push_oam = NULL;
-	vcc->send = vcc->dev->ops->send;
+	if (vcc->dev->ops->send_bh)
+		vcc->send = vcc->dev->ops->send_bh;
+	else
+		vcc->send = vcc->dev->ops->send;
 	return 0;
 }
 
@@ -80,7 +85,10 @@ int atm_init_aal5(struct atm_vcc *vcc)
 	vcc->push = atm_push_raw;
 	vcc->pop = atm_pop_raw;
 	vcc->push_oam = NULL;
-	vcc->send = vcc->dev->ops->send;
+	if (vcc->dev->ops->send_bh)
+		vcc->send = vcc->dev->ops->send_bh;
+	else
+		vcc->send = vcc->dev->ops->send;
 	return 0;
 }
 EXPORT_SYMBOL(atm_init_aal5);
-- 
cgit v1.2.3


From 4abb1e5b63ac3281275315fc6b0cde0b9c2e2e42 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Wed, 11 Nov 2020 15:53:17 +0100
Subject: powerpc/mm: factor out creating/removing linear mapping

We want to stop abusing memory hotplug infrastructure in memtrace code
to perform allocations and remove the linear mapping. Instead we will use
alloc_contig_pages() and remove the linear mapping manually.

Let's factor out creating/removing the linear mapping into
arch_create_linear_mapping() / arch_remove_linear_mapping() - so in the
future, we might be able to have whole arch_add_memory() /
arch_remove_memory() be implemented in common code.

Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201111145322.15793-4-david@redhat.com
---
 arch/powerpc/mm/mem.c          | 41 ++++++++++++++++++++++++++++-------------
 include/linux/memory_hotplug.h |  3 +++
 2 files changed, 31 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 01ec2a252f09..8a86d81f8df0 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -120,34 +120,26 @@ static void flush_dcache_range_chunked(unsigned long start, unsigned long stop,
 	}
 }
 
-int __ref arch_add_memory(int nid, u64 start, u64 size,
-			  struct mhp_params *params)
+int __ref arch_create_linear_mapping(int nid, u64 start, u64 size,
+				     struct mhp_params *params)
 {
-	unsigned long start_pfn = start >> PAGE_SHIFT;
-	unsigned long nr_pages = size >> PAGE_SHIFT;
 	int rc;
 
 	start = (unsigned long)__va(start);
 	rc = create_section_mapping(start, start + size, nid,
 				    params->pgprot);
 	if (rc) {
-		pr_warn("Unable to create mapping for hot added memory 0x%llx..0x%llx: %d\n",
+		pr_warn("Unable to create linear mapping for 0x%llx..0x%llx: %d\n",
 			start, start + size, rc);
 		return -EFAULT;
 	}
-
-	return __add_pages(nid, start_pfn, nr_pages, params);
+	return 0;
 }
 
-void __ref arch_remove_memory(int nid, u64 start, u64 size,
-			     struct vmem_altmap *altmap)
+void __ref arch_remove_linear_mapping(u64 start, u64 size)
 {
-	unsigned long start_pfn = start >> PAGE_SHIFT;
-	unsigned long nr_pages = size >> PAGE_SHIFT;
 	int ret;
 
-	__remove_pages(start_pfn, nr_pages, altmap);
-
 	/* Remove htab bolted mappings for this section of memory */
 	start = (unsigned long)__va(start);
 	flush_dcache_range_chunked(start, start + size, FLUSH_CHUNK_SIZE);
@@ -160,6 +152,29 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size,
 	 */
 	vm_unmap_aliases();
 }
+
+int __ref arch_add_memory(int nid, u64 start, u64 size,
+			  struct mhp_params *params)
+{
+	unsigned long start_pfn = start >> PAGE_SHIFT;
+	unsigned long nr_pages = size >> PAGE_SHIFT;
+	int rc;
+
+	rc = arch_create_linear_mapping(nid, start, size, params);
+	if (rc)
+		return rc;
+	return __add_pages(nid, start_pfn, nr_pages, params);
+}
+
+void __ref arch_remove_memory(int nid, u64 start, u64 size,
+			      struct vmem_altmap *altmap)
+{
+	unsigned long start_pfn = start >> PAGE_SHIFT;
+	unsigned long nr_pages = size >> PAGE_SHIFT;
+
+	__remove_pages(start_pfn, nr_pages, altmap);
+	arch_remove_linear_mapping(start, size);
+}
 #endif
 
 #ifndef CONFIG_NEED_MULTIPLE_NODES
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index d65c6fdc5cfc..00b9e9bd3850 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -375,6 +375,9 @@ extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
 					  unsigned long pnum);
 extern struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_pfn,
 		unsigned long nr_pages);
+extern int arch_create_linear_mapping(int nid, u64 start, u64 size,
+				      struct mhp_params *params);
+void arch_remove_linear_mapping(u64 start, u64 size);
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
 #endif /* __LINUX_MEMORY_HOTPLUG_H */
-- 
cgit v1.2.3


From 86b9d170da98bae13b307d621638954aef645331 Mon Sep 17 00:00:00 2001
From: Enric Balletbo i Serra <enric.balletbo@collabora.com>
Date: Tue, 10 Nov 2020 17:13:37 +0100
Subject: mfd: syscon: Add syscon_regmap_lookup_by_phandle_optional() function.

This adds syscon_regmap_lookup_by_phandle_optional() function to get an
optional regmap.

It behaves the same as syscon_regmap_lookup_by_phandle() except where
there is no regmap phandle. In this case, instead of returning -ENODEV,
the function returns NULL. This makes error checking simpler when the
regmap phandle is optional.

Suggested-by: Nicolas Boichat <drinkcat@chromium.org>
Signed-off-by: Enric Balletbo i Serra <enric.balletbo@collabora.com>
Reviewed-by: Matthias Brugger <matthias.bgg@gmail.com>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/syscon.c       | 18 ++++++++++++++++++
 include/linux/mfd/syscon.h | 11 +++++++++++
 2 files changed, 29 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/mfd/syscon.c b/drivers/mfd/syscon.c
index ca465794ea9c..c6f139b2e0c0 100644
--- a/drivers/mfd/syscon.c
+++ b/drivers/mfd/syscon.c
@@ -255,6 +255,24 @@ struct regmap *syscon_regmap_lookup_by_phandle_args(struct device_node *np,
 }
 EXPORT_SYMBOL_GPL(syscon_regmap_lookup_by_phandle_args);
 
+/*
+ * It behaves the same as syscon_regmap_lookup_by_phandle() except where
+ * there is no regmap phandle. In this case, instead of returning -ENODEV,
+ * the function returns NULL.
+ */
+struct regmap *syscon_regmap_lookup_by_phandle_optional(struct device_node *np,
+					const char *property)
+{
+	struct regmap *regmap;
+
+	regmap = syscon_regmap_lookup_by_phandle(np, property);
+	if (IS_ERR(regmap) && PTR_ERR(regmap) == -ENODEV)
+		return NULL;
+
+	return regmap;
+}
+EXPORT_SYMBOL_GPL(syscon_regmap_lookup_by_phandle_optional);
+
 static int syscon_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
diff --git a/include/linux/mfd/syscon.h b/include/linux/mfd/syscon.h
index 7f20e9b502a5..fecc2fa2a364 100644
--- a/include/linux/mfd/syscon.h
+++ b/include/linux/mfd/syscon.h
@@ -28,6 +28,9 @@ extern struct regmap *syscon_regmap_lookup_by_phandle_args(
 					const char *property,
 					int arg_count,
 					unsigned int *out_args);
+extern struct regmap *syscon_regmap_lookup_by_phandle_optional(
+					struct device_node *np,
+					const char *property);
 #else
 static inline struct regmap *device_node_to_regmap(struct device_node *np)
 {
@@ -59,6 +62,14 @@ static inline struct regmap *syscon_regmap_lookup_by_phandle_args(
 {
 	return ERR_PTR(-ENOTSUPP);
 }
+
+static inline struct regmap *syscon_regmap_lookup_by_phandle_optional(
+					struct device_node *np,
+					const char *property)
+{
+	return NULL;
+}
+
 #endif
 
 #endif /* __LINUX_MFD_SYSCON_H__ */
-- 
cgit v1.2.3


From 68a90a6c6443b07036ae4a878f6d85bf141471fd Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Fri, 25 Sep 2020 10:14:46 +0100
Subject: mfd: madera: Delete register field xxx_WIDTH defines

The register field xxx_WIDTH defines are not used in current code.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/mfd/madera/registers.h | 635 -----------------------------------
 1 file changed, 635 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mfd/madera/registers.h b/include/linux/mfd/madera/registers.h
index fe909d177762..b44aeb461d0c 100644
--- a/include/linux/mfd/madera/registers.h
+++ b/include/linux/mfd/madera/registers.h
@@ -1286,566 +1286,438 @@
 /* (0x0000)  Software_Reset */
 #define MADERA_SW_RST_DEV_ID1_MASK			0xFFFF
 #define MADERA_SW_RST_DEV_ID1_SHIFT			     0
-#define MADERA_SW_RST_DEV_ID1_WIDTH			    16
 
 /* (0x0001)  Hardware_Revision */
 #define MADERA_HW_REVISION_MASK				0x00FF
 #define MADERA_HW_REVISION_SHIFT			     0
-#define MADERA_HW_REVISION_WIDTH			     8
 
 /* (0x0020)  Tone_Generator_1 */
 #define MADERA_TONE2_ENA				0x0002
 #define MADERA_TONE2_ENA_MASK				0x0002
 #define MADERA_TONE2_ENA_SHIFT				     1
-#define MADERA_TONE2_ENA_WIDTH				     1
 #define MADERA_TONE1_ENA				0x0001
 #define MADERA_TONE1_ENA_MASK				0x0001
 #define MADERA_TONE1_ENA_SHIFT				     0
-#define MADERA_TONE1_ENA_WIDTH				     1
 
 /* (0x0021)  Tone_Generator_2 */
 #define MADERA_TONE1_LVL_0_MASK				0xFFFF
 #define MADERA_TONE1_LVL_0_SHIFT			     0
-#define MADERA_TONE1_LVL_0_WIDTH			    16
 
 /* (0x0022)  Tone_Generator_3 */
 #define MADERA_TONE1_LVL_MASK				0x00FF
 #define MADERA_TONE1_LVL_SHIFT				     0
-#define MADERA_TONE1_LVL_WIDTH				     8
 
 /* (0x0023)  Tone_Generator_4 */
 #define MADERA_TONE2_LVL_0_MASK				0xFFFF
 #define MADERA_TONE2_LVL_0_SHIFT			     0
-#define MADERA_TONE2_LVL_0_WIDTH			    16
 
 /* (0x0024)  Tone_Generator_5 */
 #define MADERA_TONE2_LVL_MASK				0x00FF
 #define MADERA_TONE2_LVL_SHIFT				     0
-#define MADERA_TONE2_LVL_WIDTH				     8
 
 /* (0x0030)  PWM_Drive_1 */
 #define MADERA_PWM2_ENA					0x0002
 #define MADERA_PWM2_ENA_MASK				0x0002
 #define MADERA_PWM2_ENA_SHIFT				     1
-#define MADERA_PWM2_ENA_WIDTH				     1
 #define MADERA_PWM1_ENA					0x0001
 #define MADERA_PWM1_ENA_MASK				0x0001
 #define MADERA_PWM1_ENA_SHIFT				     0
-#define MADERA_PWM1_ENA_WIDTH				     1
 
 /* (0x00A0)  Comfort_Noise_Generator */
 #define MADERA_NOISE_GEN_ENA				0x0020
 #define MADERA_NOISE_GEN_ENA_MASK			0x0020
 #define MADERA_NOISE_GEN_ENA_SHIFT			     5
-#define MADERA_NOISE_GEN_ENA_WIDTH			     1
 #define MADERA_NOISE_GEN_GAIN_MASK			0x001F
 #define MADERA_NOISE_GEN_GAIN_SHIFT			     0
-#define MADERA_NOISE_GEN_GAIN_WIDTH			     5
 
 /* (0x0100)  Clock_32k_1 */
 #define MADERA_CLK_32K_ENA				0x0040
 #define MADERA_CLK_32K_ENA_MASK				0x0040
 #define MADERA_CLK_32K_ENA_SHIFT			     6
-#define MADERA_CLK_32K_ENA_WIDTH			     1
 #define MADERA_CLK_32K_SRC_MASK				0x0003
 #define MADERA_CLK_32K_SRC_SHIFT			     0
-#define MADERA_CLK_32K_SRC_WIDTH			     2
 
 /* (0x0101)  System_Clock_1 */
 #define MADERA_SYSCLK_FRAC				0x8000
 #define MADERA_SYSCLK_FRAC_MASK				0x8000
 #define MADERA_SYSCLK_FRAC_SHIFT			    15
-#define MADERA_SYSCLK_FRAC_WIDTH			     1
 #define MADERA_SYSCLK_FREQ_MASK				0x0700
 #define MADERA_SYSCLK_FREQ_SHIFT			     8
-#define MADERA_SYSCLK_FREQ_WIDTH			     3
 #define MADERA_SYSCLK_ENA				0x0040
 #define MADERA_SYSCLK_ENA_MASK				0x0040
 #define MADERA_SYSCLK_ENA_SHIFT				     6
-#define MADERA_SYSCLK_ENA_WIDTH				     1
 #define MADERA_SYSCLK_SRC_MASK				0x000F
 #define MADERA_SYSCLK_SRC_SHIFT				     0
-#define MADERA_SYSCLK_SRC_WIDTH				     4
 
 /* (0x0102)  Sample_rate_1 */
 #define MADERA_SAMPLE_RATE_1_MASK			0x001F
 #define MADERA_SAMPLE_RATE_1_SHIFT			     0
-#define MADERA_SAMPLE_RATE_1_WIDTH			     5
 
 /* (0x0103)  Sample_rate_2 */
 #define MADERA_SAMPLE_RATE_2_MASK			0x001F
 #define MADERA_SAMPLE_RATE_2_SHIFT			     0
-#define MADERA_SAMPLE_RATE_2_WIDTH			     5
 
 /* (0x0104)  Sample_rate_3 */
 #define MADERA_SAMPLE_RATE_3_MASK			0x001F
 #define MADERA_SAMPLE_RATE_3_SHIFT			     0
-#define MADERA_SAMPLE_RATE_3_WIDTH			     5
 
 /* (0x0112)  Async_clock_1 */
 #define MADERA_ASYNC_CLK_FREQ_MASK			0x0700
 #define MADERA_ASYNC_CLK_FREQ_SHIFT			     8
-#define MADERA_ASYNC_CLK_FREQ_WIDTH			     3
 #define MADERA_ASYNC_CLK_ENA				0x0040
 #define MADERA_ASYNC_CLK_ENA_MASK			0x0040
 #define MADERA_ASYNC_CLK_ENA_SHIFT			     6
-#define MADERA_ASYNC_CLK_ENA_WIDTH			     1
 #define MADERA_ASYNC_CLK_SRC_MASK			0x000F
 #define MADERA_ASYNC_CLK_SRC_SHIFT			     0
-#define MADERA_ASYNC_CLK_SRC_WIDTH			     4
 
 /* (0x0113)  Async_sample_rate_1 */
 #define MADERA_ASYNC_SAMPLE_RATE_1_MASK			0x001F
 #define MADERA_ASYNC_SAMPLE_RATE_1_SHIFT		     0
-#define MADERA_ASYNC_SAMPLE_RATE_1_WIDTH		     5
 
 /* (0x0114)  Async_sample_rate_2 */
 #define MADERA_ASYNC_SAMPLE_RATE_2_MASK			0x001F
 #define MADERA_ASYNC_SAMPLE_RATE_2_SHIFT		     0
-#define MADERA_ASYNC_SAMPLE_RATE_2_WIDTH		     5
 
 /* (0x0120)  DSP_Clock_1 */
 #define MADERA_DSP_CLK_FREQ_LEGACY			0x0700
 #define MADERA_DSP_CLK_FREQ_LEGACY_MASK			0x0700
 #define MADERA_DSP_CLK_FREQ_LEGACY_SHIFT		     8
-#define MADERA_DSP_CLK_FREQ_LEGACY_WIDTH		     3
 #define MADERA_DSP_CLK_ENA				0x0040
 #define MADERA_DSP_CLK_ENA_MASK				0x0040
 #define MADERA_DSP_CLK_ENA_SHIFT			     6
-#define MADERA_DSP_CLK_ENA_WIDTH			     1
 #define MADERA_DSP_CLK_SRC				0x000F
 #define MADERA_DSP_CLK_SRC_MASK				0x000F
 #define MADERA_DSP_CLK_SRC_SHIFT			     0
-#define MADERA_DSP_CLK_SRC_WIDTH			     4
 
 /* (0x0122)  DSP_Clock_2 */
 #define MADERA_DSP_CLK_FREQ_MASK			0x03FF
 #define MADERA_DSP_CLK_FREQ_SHIFT			     0
-#define MADERA_DSP_CLK_FREQ_WIDTH			    10
 
 /* (0x0149)  Output_system_clock */
 #define MADERA_OPCLK_ENA				0x8000
 #define MADERA_OPCLK_ENA_MASK				0x8000
 #define MADERA_OPCLK_ENA_SHIFT				    15
-#define MADERA_OPCLK_ENA_WIDTH				     1
 #define MADERA_OPCLK_DIV_MASK				0x00F8
 #define MADERA_OPCLK_DIV_SHIFT				     3
-#define MADERA_OPCLK_DIV_WIDTH				     5
 #define MADERA_OPCLK_SEL_MASK				0x0007
 #define MADERA_OPCLK_SEL_SHIFT				     0
-#define MADERA_OPCLK_SEL_WIDTH				     3
 
 /* (0x014A)  Output_async_clock */
 #define MADERA_OPCLK_ASYNC_ENA				0x8000
 #define MADERA_OPCLK_ASYNC_ENA_MASK			0x8000
 #define MADERA_OPCLK_ASYNC_ENA_SHIFT			    15
-#define MADERA_OPCLK_ASYNC_ENA_WIDTH			     1
 #define MADERA_OPCLK_ASYNC_DIV_MASK			0x00F8
 #define MADERA_OPCLK_ASYNC_DIV_SHIFT			     3
-#define MADERA_OPCLK_ASYNC_DIV_WIDTH			     5
 #define MADERA_OPCLK_ASYNC_SEL_MASK			0x0007
 #define MADERA_OPCLK_ASYNC_SEL_SHIFT			     0
-#define MADERA_OPCLK_ASYNC_SEL_WIDTH			     3
 
 /* (0x0171)  FLL1_Control_1 */
 #define CS47L92_FLL1_REFCLK_SRC_MASK			0xF000
 #define CS47L92_FLL1_REFCLK_SRC_SHIFT			    12
-#define CS47L92_FLL1_REFCLK_SRC_WIDTH			     4
 #define MADERA_FLL1_HOLD_MASK				0x0004
 #define MADERA_FLL1_HOLD_SHIFT				     2
-#define MADERA_FLL1_HOLD_WIDTH				     1
 #define MADERA_FLL1_FREERUN				0x0002
 #define MADERA_FLL1_FREERUN_MASK			0x0002
 #define MADERA_FLL1_FREERUN_SHIFT			     1
-#define MADERA_FLL1_FREERUN_WIDTH			     1
 #define MADERA_FLL1_ENA					0x0001
 #define MADERA_FLL1_ENA_MASK				0x0001
 #define MADERA_FLL1_ENA_SHIFT				     0
-#define MADERA_FLL1_ENA_WIDTH				     1
 
 /* (0x0172)  FLL1_Control_2 */
 #define MADERA_FLL1_CTRL_UPD				0x8000
 #define MADERA_FLL1_CTRL_UPD_MASK			0x8000
 #define MADERA_FLL1_CTRL_UPD_SHIFT			    15
-#define MADERA_FLL1_CTRL_UPD_WIDTH			     1
 #define MADERA_FLL1_N_MASK				0x03FF
 #define MADERA_FLL1_N_SHIFT				     0
-#define MADERA_FLL1_N_WIDTH				    10
 
 /* (0x0173)  FLL1_Control_3 */
 #define MADERA_FLL1_THETA_MASK				0xFFFF
 #define MADERA_FLL1_THETA_SHIFT				     0
-#define MADERA_FLL1_THETA_WIDTH				    16
 
 /* (0x0174)  FLL1_Control_4 */
 #define MADERA_FLL1_LAMBDA_MASK				0xFFFF
 #define MADERA_FLL1_LAMBDA_SHIFT			     0
-#define MADERA_FLL1_LAMBDA_WIDTH			    16
 
 /* (0x0175)  FLL1_Control_5 */
 #define MADERA_FLL1_FRATIO_MASK				0x0F00
 #define MADERA_FLL1_FRATIO_SHIFT			     8
-#define MADERA_FLL1_FRATIO_WIDTH			     4
 #define MADERA_FLL1_FB_DIV_MASK				0x03FF
 #define MADERA_FLL1_FB_DIV_SHIFT			     0
-#define MADERA_FLL1_FB_DIV_WIDTH			    10
 
 /* (0x0176)  FLL1_Control_6 */
 #define MADERA_FLL1_REFCLK_DIV_MASK			0x00C0
 #define MADERA_FLL1_REFCLK_DIV_SHIFT			     6
-#define MADERA_FLL1_REFCLK_DIV_WIDTH			     2
 #define MADERA_FLL1_REFCLK_SRC_MASK			0x000F
 #define MADERA_FLL1_REFCLK_SRC_SHIFT			     0
-#define MADERA_FLL1_REFCLK_SRC_WIDTH			     4
 
 /* (0x0179)  FLL1_Control_7 */
 #define MADERA_FLL1_GAIN_MASK				0x003c
 #define MADERA_FLL1_GAIN_SHIFT				     2
-#define MADERA_FLL1_GAIN_WIDTH				     4
 
 /* (0x017A)  FLL1_EFS_2 */
 #define MADERA_FLL1_PHASE_GAIN_MASK			0xF000
 #define MADERA_FLL1_PHASE_GAIN_SHIFT			    12
-#define MADERA_FLL1_PHASE_GAIN_WIDTH			     4
 #define MADERA_FLL1_PHASE_ENA_MASK			0x0800
 #define MADERA_FLL1_PHASE_ENA_SHIFT			    11
-#define MADERA_FLL1_PHASE_ENA_WIDTH			     1
 
 /* (0x017A)  FLL1_Control_10 */
 #define MADERA_FLL1_HP_MASK				0xC000
 #define MADERA_FLL1_HP_SHIFT				    14
-#define MADERA_FLL1_HP_WIDTH				     2
 #define MADERA_FLL1_PHASEDET_ENA_MASK			0x1000
 #define MADERA_FLL1_PHASEDET_ENA_SHIFT			    12
-#define MADERA_FLL1_PHASEDET_ENA_WIDTH			     1
 
 /* (0x017B)  FLL1_Control_11 */
 #define MADERA_FLL1_LOCKDET_THR_MASK			0x001E
 #define MADERA_FLL1_LOCKDET_THR_SHIFT			     1
-#define MADERA_FLL1_LOCKDET_THR_WIDTH			     4
 #define MADERA_FLL1_LOCKDET_MASK			0x0001
 #define MADERA_FLL1_LOCKDET_SHIFT			     0
-#define MADERA_FLL1_LOCKDET_WIDTH			     1
 
 /* (0x017D)  FLL1_Digital_Test_1 */
 #define MADERA_FLL1_SYNC_EFS_ENA_MASK			0x0100
 #define MADERA_FLL1_SYNC_EFS_ENA_SHIFT			     8
-#define MADERA_FLL1_SYNC_EFS_ENA_WIDTH			     1
 #define MADERA_FLL1_CLK_VCO_FAST_SRC_MASK		0x0003
 #define MADERA_FLL1_CLK_VCO_FAST_SRC_SHIFT		     0
-#define MADERA_FLL1_CLK_VCO_FAST_SRC_WIDTH		     2
 
 /* (0x0181)  FLL1_Synchroniser_1 */
 #define MADERA_FLL1_SYNC_ENA				0x0001
 #define MADERA_FLL1_SYNC_ENA_MASK			0x0001
 #define MADERA_FLL1_SYNC_ENA_SHIFT			     0
-#define MADERA_FLL1_SYNC_ENA_WIDTH			     1
 
 /* (0x0182)  FLL1_Synchroniser_2 */
 #define MADERA_FLL1_SYNC_N_MASK				0x03FF
 #define MADERA_FLL1_SYNC_N_SHIFT			     0
-#define MADERA_FLL1_SYNC_N_WIDTH			    10
 
 /* (0x0183)  FLL1_Synchroniser_3 */
 #define MADERA_FLL1_SYNC_THETA_MASK			0xFFFF
 #define MADERA_FLL1_SYNC_THETA_SHIFT			     0
-#define MADERA_FLL1_SYNC_THETA_WIDTH			    16
 
 /* (0x0184)  FLL1_Synchroniser_4 */
 #define MADERA_FLL1_SYNC_LAMBDA_MASK			0xFFFF
 #define MADERA_FLL1_SYNC_LAMBDA_SHIFT			     0
-#define MADERA_FLL1_SYNC_LAMBDA_WIDTH			    16
 
 /* (0x0185)  FLL1_Synchroniser_5 */
 #define MADERA_FLL1_SYNC_FRATIO_MASK			0x0700
 #define MADERA_FLL1_SYNC_FRATIO_SHIFT			     8
-#define MADERA_FLL1_SYNC_FRATIO_WIDTH			     3
 
 /* (0x0186)  FLL1_Synchroniser_6 */
 #define MADERA_FLL1_SYNCCLK_DIV_MASK			0x00C0
 #define MADERA_FLL1_SYNCCLK_DIV_SHIFT			     6
-#define MADERA_FLL1_SYNCCLK_DIV_WIDTH			     2
 #define MADERA_FLL1_SYNCCLK_SRC_MASK			0x000F
 #define MADERA_FLL1_SYNCCLK_SRC_SHIFT			     0
-#define MADERA_FLL1_SYNCCLK_SRC_WIDTH			     4
 
 /* (0x0187)  FLL1_Synchroniser_7 */
 #define MADERA_FLL1_SYNC_GAIN_MASK			0x003c
 #define MADERA_FLL1_SYNC_GAIN_SHIFT			     2
-#define MADERA_FLL1_SYNC_GAIN_WIDTH			     4
 #define MADERA_FLL1_SYNC_DFSAT				0x0001
 #define MADERA_FLL1_SYNC_DFSAT_MASK			0x0001
 #define MADERA_FLL1_SYNC_DFSAT_SHIFT			     0
-#define MADERA_FLL1_SYNC_DFSAT_WIDTH			     1
 
 /* (0x01D1)  FLL_AO_Control_1 */
 #define MADERA_FLL_AO_HOLD				0x0004
 #define MADERA_FLL_AO_HOLD_MASK				0x0004
 #define MADERA_FLL_AO_HOLD_SHIFT			     2
-#define MADERA_FLL_AO_HOLD_WIDTH			     1
 #define MADERA_FLL_AO_FREERUN				0x0002
 #define MADERA_FLL_AO_FREERUN_MASK			0x0002
 #define MADERA_FLL_AO_FREERUN_SHIFT			     1
-#define MADERA_FLL_AO_FREERUN_WIDTH			     1
 #define MADERA_FLL_AO_ENA				0x0001
 #define MADERA_FLL_AO_ENA_MASK				0x0001
 #define MADERA_FLL_AO_ENA_SHIFT				     0
-#define MADERA_FLL_AO_ENA_WIDTH				     1
 
 /* (0x01D2)  FLL_AO_Control_2 */
 #define MADERA_FLL_AO_CTRL_UPD				0x8000
 #define MADERA_FLL_AO_CTRL_UPD_MASK			0x8000
 #define MADERA_FLL_AO_CTRL_UPD_SHIFT			    15
-#define MADERA_FLL_AO_CTRL_UPD_WIDTH			     1
 
 /* (0x01D6)  FLL_AO_Control_6 */
 #define MADERA_FLL_AO_REFCLK_SRC_MASK			0x000F
 #define MADERA_FLL_AO_REFCLK_SRC_SHIFT			     0
-#define MADERA_FLL_AO_REFCLK_SRC_WIDTH			     4
 
 /* (0x0200)  Mic_Charge_Pump_1 */
 #define MADERA_CPMIC_BYPASS				0x0002
 #define MADERA_CPMIC_BYPASS_MASK			0x0002
 #define MADERA_CPMIC_BYPASS_SHIFT			     1
-#define MADERA_CPMIC_BYPASS_WIDTH			     1
 #define MADERA_CPMIC_ENA				0x0001
 #define MADERA_CPMIC_ENA_MASK				0x0001
 #define MADERA_CPMIC_ENA_SHIFT				     0
-#define MADERA_CPMIC_ENA_WIDTH				     1
 
 /* (0x0210)  LDO1_Control_1 */
 #define MADERA_LDO1_VSEL_MASK				0x07E0
 #define MADERA_LDO1_VSEL_SHIFT				     5
-#define MADERA_LDO1_VSEL_WIDTH				     6
 #define MADERA_LDO1_FAST				0x0010
 #define MADERA_LDO1_FAST_MASK				0x0010
 #define MADERA_LDO1_FAST_SHIFT				     4
-#define MADERA_LDO1_FAST_WIDTH				     1
 #define MADERA_LDO1_DISCH				0x0004
 #define MADERA_LDO1_DISCH_MASK				0x0004
 #define MADERA_LDO1_DISCH_SHIFT				     2
-#define MADERA_LDO1_DISCH_WIDTH				     1
 #define MADERA_LDO1_BYPASS				0x0002
 #define MADERA_LDO1_BYPASS_MASK				0x0002
 #define MADERA_LDO1_BYPASS_SHIFT			     1
-#define MADERA_LDO1_BYPASS_WIDTH			     1
 #define MADERA_LDO1_ENA					0x0001
 #define MADERA_LDO1_ENA_MASK				0x0001
 #define MADERA_LDO1_ENA_SHIFT				     0
-#define MADERA_LDO1_ENA_WIDTH				     1
 
 /* (0x0213)  LDO2_Control_1 */
 #define MADERA_LDO2_VSEL_MASK				0x07E0
 #define MADERA_LDO2_VSEL_SHIFT				     5
-#define MADERA_LDO2_VSEL_WIDTH				     6
 #define MADERA_LDO2_FAST				0x0010
 #define MADERA_LDO2_FAST_MASK				0x0010
 #define MADERA_LDO2_FAST_SHIFT				     4
-#define MADERA_LDO2_FAST_WIDTH				     1
 #define MADERA_LDO2_DISCH				0x0004
 #define MADERA_LDO2_DISCH_MASK				0x0004
 #define MADERA_LDO2_DISCH_SHIFT				     2
-#define MADERA_LDO2_DISCH_WIDTH				     1
 #define MADERA_LDO2_BYPASS				0x0002
 #define MADERA_LDO2_BYPASS_MASK				0x0002
 #define MADERA_LDO2_BYPASS_SHIFT			     1
-#define MADERA_LDO2_BYPASS_WIDTH			     1
 #define MADERA_LDO2_ENA					0x0001
 #define MADERA_LDO2_ENA_MASK				0x0001
 #define MADERA_LDO2_ENA_SHIFT				     0
-#define MADERA_LDO2_ENA_WIDTH				     1
 
 /* (0x0218)  Mic_Bias_Ctrl_1 */
 #define MADERA_MICB1_EXT_CAP				0x8000
 #define MADERA_MICB1_EXT_CAP_MASK			0x8000
 #define MADERA_MICB1_EXT_CAP_SHIFT			    15
-#define MADERA_MICB1_EXT_CAP_WIDTH			     1
 #define MADERA_MICB1_LVL_MASK				0x01E0
 #define MADERA_MICB1_LVL_SHIFT				     5
-#define MADERA_MICB1_LVL_WIDTH				     4
 #define MADERA_MICB1_ENA				0x0001
 #define MADERA_MICB1_ENA_MASK				0x0001
 #define MADERA_MICB1_ENA_SHIFT				     0
-#define MADERA_MICB1_ENA_WIDTH				     1
 
 /* (0x021C)  Mic_Bias_Ctrl_5 */
 #define MADERA_MICB1D_ENA				0x1000
 #define MADERA_MICB1D_ENA_MASK				0x1000
 #define MADERA_MICB1D_ENA_SHIFT				    12
-#define MADERA_MICB1D_ENA_WIDTH				     1
 #define MADERA_MICB1C_ENA				0x0100
 #define MADERA_MICB1C_ENA_MASK				0x0100
 #define MADERA_MICB1C_ENA_SHIFT				     8
-#define MADERA_MICB1C_ENA_WIDTH				     1
 #define MADERA_MICB1B_ENA				0x0010
 #define MADERA_MICB1B_ENA_MASK				0x0010
 #define MADERA_MICB1B_ENA_SHIFT				     4
-#define MADERA_MICB1B_ENA_WIDTH				     1
 #define MADERA_MICB1A_ENA				0x0001
 #define MADERA_MICB1A_ENA_MASK				0x0001
 #define MADERA_MICB1A_ENA_SHIFT				     0
-#define MADERA_MICB1A_ENA_WIDTH				     1
 
 /* (0x021E)  Mic_Bias_Ctrl_6 */
 #define MADERA_MICB2D_ENA				0x1000
 #define MADERA_MICB2D_ENA_MASK				0x1000
 #define MADERA_MICB2D_ENA_SHIFT				    12
-#define MADERA_MICB2D_ENA_WIDTH				     1
 #define MADERA_MICB2C_ENA				0x0100
 #define MADERA_MICB2C_ENA_MASK				0x0100
 #define MADERA_MICB2C_ENA_SHIFT				     8
-#define MADERA_MICB2C_ENA_WIDTH				     1
 #define MADERA_MICB2B_ENA				0x0010
 #define MADERA_MICB2B_ENA_MASK				0x0010
 #define MADERA_MICB2B_ENA_SHIFT				     4
-#define MADERA_MICB2B_ENA_WIDTH				     1
 #define MADERA_MICB2A_ENA				0x0001
 #define MADERA_MICB2A_ENA_MASK				0x0001
 #define MADERA_MICB2A_ENA_SHIFT				     0
-#define MADERA_MICB2A_ENA_WIDTH				     1
 
 /* (0x0225) - HP Ctrl 1L */
 #define MADERA_RMV_SHRT_HP1L				0x4000
 #define MADERA_RMV_SHRT_HP1L_MASK			0x4000
 #define MADERA_RMV_SHRT_HP1L_SHIFT			    14
-#define MADERA_RMV_SHRT_HP1L_WIDTH			     1
 #define MADERA_HP1L_FLWR				0x0004
 #define MADERA_HP1L_FLWR_MASK				0x0004
 #define MADERA_HP1L_FLWR_SHIFT				     2
-#define MADERA_HP1L_FLWR_WIDTH				     1
 #define MADERA_HP1L_SHRTI				0x0002
 #define MADERA_HP1L_SHRTI_MASK				0x0002
 #define MADERA_HP1L_SHRTI_SHIFT				     1
-#define MADERA_HP1L_SHRTI_WIDTH				     1
 #define MADERA_HP1L_SHRTO				0x0001
 #define MADERA_HP1L_SHRTO_MASK				0x0001
 #define MADERA_HP1L_SHRTO_SHIFT				     0
-#define MADERA_HP1L_SHRTO_WIDTH				     1
 
 /* (0x0226) - HP Ctrl 1R */
 #define MADERA_RMV_SHRT_HP1R				0x4000
 #define MADERA_RMV_SHRT_HP1R_MASK			0x4000
 #define MADERA_RMV_SHRT_HP1R_SHIFT			    14
-#define MADERA_RMV_SHRT_HP1R_WIDTH			     1
 #define MADERA_HP1R_FLWR				0x0004
 #define MADERA_HP1R_FLWR_MASK				0x0004
 #define MADERA_HP1R_FLWR_SHIFT				     2
-#define MADERA_HP1R_FLWR_WIDTH				     1
 #define MADERA_HP1R_SHRTI				0x0002
 #define MADERA_HP1R_SHRTI_MASK				0x0002
 #define MADERA_HP1R_SHRTI_SHIFT				     1
-#define MADERA_HP1R_SHRTI_WIDTH				     1
 #define MADERA_HP1R_SHRTO				0x0001
 #define MADERA_HP1R_SHRTO_MASK				0x0001
 #define MADERA_HP1R_SHRTO_SHIFT				     0
-#define MADERA_HP1R_SHRTO_WIDTH				     1
 
 /* (0x0293)  Accessory_Detect_Mode_1 */
 #define MADERA_ACCDET_SRC				0x2000
 #define MADERA_ACCDET_SRC_MASK				0x2000
 #define MADERA_ACCDET_SRC_SHIFT				    13
-#define MADERA_ACCDET_SRC_WIDTH				     1
 #define MADERA_ACCDET_POLARITY_INV_ENA			0x0080
 #define MADERA_ACCDET_POLARITY_INV_ENA_MASK		0x0080
 #define MADERA_ACCDET_POLARITY_INV_ENA_SHIFT		     7
-#define MADERA_ACCDET_POLARITY_INV_ENA_WIDTH		     1
 #define MADERA_ACCDET_MODE_MASK				0x0007
 #define MADERA_ACCDET_MODE_SHIFT			     0
-#define MADERA_ACCDET_MODE_WIDTH			     3
 
 /* (0x0299)  Headphone_Detect_0 */
 #define MADERA_HPD_GND_SEL				0x0007
 #define MADERA_HPD_GND_SEL_MASK				0x0007
 #define MADERA_HPD_GND_SEL_SHIFT			     0
-#define MADERA_HPD_GND_SEL_WIDTH			     3
 #define MADERA_HPD_SENSE_SEL				0x00F0
 #define MADERA_HPD_SENSE_SEL_MASK			0x00F0
 #define MADERA_HPD_SENSE_SEL_SHIFT			     4
-#define MADERA_HPD_SENSE_SEL_WIDTH			     4
 #define MADERA_HPD_FRC_SEL				0x0F00
 #define MADERA_HPD_FRC_SEL_MASK				0x0F00
 #define MADERA_HPD_FRC_SEL_SHIFT			     8
-#define MADERA_HPD_FRC_SEL_WIDTH			     4
 #define MADERA_HPD_OUT_SEL				0x7000
 #define MADERA_HPD_OUT_SEL_MASK				0x7000
 #define MADERA_HPD_OUT_SEL_SHIFT			    12
-#define MADERA_HPD_OUT_SEL_WIDTH			     3
 #define MADERA_HPD_OVD_ENA_SEL				0x8000
 #define MADERA_HPD_OVD_ENA_SEL_MASK			0x8000
 #define MADERA_HPD_OVD_ENA_SEL_SHIFT			    15
-#define MADERA_HPD_OVD_ENA_SEL_WIDTH			     1
 
 /* (0x029B)  Headphone_Detect_1 */
 #define MADERA_HP_IMPEDANCE_RANGE_MASK			0x0600
 #define MADERA_HP_IMPEDANCE_RANGE_SHIFT			     9
-#define MADERA_HP_IMPEDANCE_RANGE_WIDTH			     2
 #define MADERA_HP_STEP_SIZE				0x0100
 #define MADERA_HP_STEP_SIZE_MASK			0x0100
 #define MADERA_HP_STEP_SIZE_SHIFT			     8
-#define MADERA_HP_STEP_SIZE_WIDTH			     1
 #define MADERA_HP_CLK_DIV_MASK				0x0018
 #define MADERA_HP_CLK_DIV_SHIFT				     3
-#define MADERA_HP_CLK_DIV_WIDTH				     2
 #define MADERA_HP_RATE_MASK				0x0006
 #define MADERA_HP_RATE_SHIFT				     1
-#define MADERA_HP_RATE_WIDTH				     2
 #define MADERA_HP_POLL					0x0001
 #define MADERA_HP_POLL_MASK				0x0001
 #define MADERA_HP_POLL_SHIFT				     0
-#define MADERA_HP_POLL_WIDTH				     1
 
 /* (0x029C)  Headphone_Detect_2 */
 #define MADERA_HP_DONE_MASK				0x8000
 #define MADERA_HP_DONE_SHIFT				    15
-#define MADERA_HP_DONE_WIDTH				     1
 #define MADERA_HP_LVL_MASK				0x7FFF
 #define MADERA_HP_LVL_SHIFT				     0
-#define MADERA_HP_LVL_WIDTH				    15
 
 /* (0x029D)  Headphone_Detect_3 */
 #define MADERA_HP_DACVAL_MASK				0x03FF
 #define MADERA_HP_DACVAL_SHIFT				     0
-#define MADERA_HP_DACVAL_WIDTH				    10
 
 /* (0x029F) - Headphone Detect 5 */
 #define MADERA_HP_DACVAL_DOWN_MASK			0x03FF
 #define MADERA_HP_DACVAL_DOWN_SHIFT			     0
-#define MADERA_HP_DACVAL_DOWN_WIDTH			    10
 
 /* (0x02A2)  Mic_Detect_1_Control_0 */
 #define MADERA_MICD1_GND_MASK				0x0007
 #define MADERA_MICD1_GND_SHIFT				     0
-#define MADERA_MICD1_GND_WIDTH				     3
 #define MADERA_MICD1_SENSE_MASK				0x00F0
 #define MADERA_MICD1_SENSE_SHIFT			     4
-#define MADERA_MICD1_SENSE_WIDTH			     4
 #define MADERA_MICD1_ADC_MODE_MASK			0x8000
 #define MADERA_MICD1_ADC_MODE_SHIFT			    15
-#define MADERA_MICD1_ADC_MODE_WIDTH			     1
 
 /* (0x02A3)  Mic_Detect_1_Control_1 */
 #define MADERA_MICD_BIAS_STARTTIME_MASK			0xF000
 #define MADERA_MICD_BIAS_STARTTIME_SHIFT		    12
-#define MADERA_MICD_BIAS_STARTTIME_WIDTH		     4
 #define MADERA_MICD_RATE_MASK				0x0F00
 #define MADERA_MICD_RATE_SHIFT				     8
-#define MADERA_MICD_RATE_WIDTH				     4
 #define MADERA_MICD_BIAS_SRC_MASK			0x00F0
 #define MADERA_MICD_BIAS_SRC_SHIFT			     4
-#define MADERA_MICD_BIAS_SRC_WIDTH			     4
 #define MADERA_MICD_DBTIME				0x0002
 #define MADERA_MICD_DBTIME_MASK				0x0002
 #define MADERA_MICD_DBTIME_SHIFT			     1
-#define MADERA_MICD_DBTIME_WIDTH			     1
 #define MADERA_MICD_ENA					0x0001
 #define MADERA_MICD_ENA_MASK				0x0001
 #define MADERA_MICD_ENA_SHIFT				     0
-#define MADERA_MICD_ENA_WIDTH				     1
 
 /* (0x02A4)  Mic_Detect_1_Control_2 */
 #define MADERA_MICD_LVL_SEL_MASK			0x00FF
 #define MADERA_MICD_LVL_SEL_SHIFT			     0
-#define MADERA_MICD_LVL_SEL_WIDTH			     8
 
 /* (0x02A5)  Mic_Detect_1_Control_3 */
 #define MADERA_MICD_LVL_0				0x0004
@@ -1859,1746 +1731,1341 @@
 #define MADERA_MICD_LVL_8				0x0400
 #define MADERA_MICD_LVL_MASK				0x07FC
 #define MADERA_MICD_LVL_SHIFT				     2
-#define MADERA_MICD_LVL_WIDTH				     9
 #define MADERA_MICD_VALID				0x0002
 #define MADERA_MICD_VALID_MASK				0x0002
 #define MADERA_MICD_VALID_SHIFT				     1
-#define MADERA_MICD_VALID_WIDTH				     1
 #define MADERA_MICD_STS					0x0001
 #define MADERA_MICD_STS_MASK				0x0001
 #define MADERA_MICD_STS_SHIFT				     0
-#define MADERA_MICD_STS_WIDTH				     1
 
 /* (0x02AB)  Mic_Detect_1_Control_4 */
 #define MADERA_MICDET_ADCVAL_DIFF_MASK			0xFF00
 #define MADERA_MICDET_ADCVAL_DIFF_SHIFT			     8
-#define MADERA_MICDET_ADCVAL_DIFF_WIDTH			     8
 #define MADERA_MICDET_ADCVAL_MASK			0x007F
 #define MADERA_MICDET_ADCVAL_SHIFT			     0
-#define MADERA_MICDET_ADCVAL_WIDTH			     7
 
 /* (0x02C6)  Micd_Clamp_control */
 #define MADERA_MICD_CLAMP_OVD				0x0010
 #define MADERA_MICD_CLAMP_OVD_MASK			0x0010
 #define MADERA_MICD_CLAMP_OVD_SHIFT			     4
-#define MADERA_MICD_CLAMP_OVD_WIDTH			     1
 #define MADERA_MICD_CLAMP_MODE_MASK			0x000F
 #define MADERA_MICD_CLAMP_MODE_SHIFT			     0
-#define MADERA_MICD_CLAMP_MODE_WIDTH			     4
 
 /* (0x02C8)  GP_Switch_1 */
 #define MADERA_SW2_MODE_MASK				0x000C
 #define MADERA_SW2_MODE_SHIFT				     2
-#define MADERA_SW2_MODE_WIDTH				     2
 #define MADERA_SW1_MODE_MASK				0x0003
 #define MADERA_SW1_MODE_SHIFT				     0
-#define MADERA_SW1_MODE_WIDTH				     2
 
 /* (0x02D3)  Jack_detect_analogue */
 #define MADERA_JD2_ENA					0x0002
 #define MADERA_JD2_ENA_MASK				0x0002
 #define MADERA_JD2_ENA_SHIFT				     1
-#define MADERA_JD2_ENA_WIDTH				     1
 #define MADERA_JD1_ENA					0x0001
 #define MADERA_JD1_ENA_MASK				0x0001
 #define MADERA_JD1_ENA_SHIFT				     0
-#define MADERA_JD1_ENA_WIDTH				     1
 
 /* (0x0300)  Input_Enables */
 #define MADERA_IN6L_ENA					0x0800
 #define MADERA_IN6L_ENA_MASK				0x0800
 #define MADERA_IN6L_ENA_SHIFT				    11
-#define MADERA_IN6L_ENA_WIDTH				     1
 #define MADERA_IN6R_ENA					0x0400
 #define MADERA_IN6R_ENA_MASK				0x0400
 #define MADERA_IN6R_ENA_SHIFT				    10
-#define MADERA_IN6R_ENA_WIDTH				     1
 #define MADERA_IN5L_ENA					0x0200
 #define MADERA_IN5L_ENA_MASK				0x0200
 #define MADERA_IN5L_ENA_SHIFT				     9
-#define MADERA_IN5L_ENA_WIDTH				     1
 #define MADERA_IN5R_ENA					0x0100
 #define MADERA_IN5R_ENA_MASK				0x0100
 #define MADERA_IN5R_ENA_SHIFT				     8
-#define MADERA_IN5R_ENA_WIDTH				     1
 #define MADERA_IN4L_ENA					0x0080
 #define MADERA_IN4L_ENA_MASK				0x0080
 #define MADERA_IN4L_ENA_SHIFT				     7
-#define MADERA_IN4L_ENA_WIDTH				     1
 #define MADERA_IN4R_ENA					0x0040
 #define MADERA_IN4R_ENA_MASK				0x0040
 #define MADERA_IN4R_ENA_SHIFT				     6
-#define MADERA_IN4R_ENA_WIDTH				     1
 #define MADERA_IN3L_ENA					0x0020
 #define MADERA_IN3L_ENA_MASK				0x0020
 #define MADERA_IN3L_ENA_SHIFT				     5
-#define MADERA_IN3L_ENA_WIDTH				     1
 #define MADERA_IN3R_ENA					0x0010
 #define MADERA_IN3R_ENA_MASK				0x0010
 #define MADERA_IN3R_ENA_SHIFT				     4
-#define MADERA_IN3R_ENA_WIDTH				     1
 #define MADERA_IN2L_ENA					0x0008
 #define MADERA_IN2L_ENA_MASK				0x0008
 #define MADERA_IN2L_ENA_SHIFT				     3
-#define MADERA_IN2L_ENA_WIDTH				     1
 #define MADERA_IN2R_ENA					0x0004
 #define MADERA_IN2R_ENA_MASK				0x0004
 #define MADERA_IN2R_ENA_SHIFT				     2
-#define MADERA_IN2R_ENA_WIDTH				     1
 #define MADERA_IN1L_ENA					0x0002
 #define MADERA_IN1L_ENA_MASK				0x0002
 #define MADERA_IN1L_ENA_SHIFT				     1
-#define MADERA_IN1L_ENA_WIDTH				     1
 #define MADERA_IN1R_ENA					0x0001
 #define MADERA_IN1R_ENA_MASK				0x0001
 #define MADERA_IN1R_ENA_SHIFT				     0
-#define MADERA_IN1R_ENA_WIDTH				     1
 
 /* (0x0308)  Input_Rate */
 #define MADERA_IN_RATE_MASK				0xF800
 #define MADERA_IN_RATE_SHIFT				    11
-#define MADERA_IN_RATE_WIDTH				     5
 #define MADERA_IN_MODE_MASK				0x0400
 #define MADERA_IN_MODE_SHIFT				    10
-#define MADERA_IN_MODE_WIDTH				     1
 
 /* (0x0309)  Input_Volume_Ramp */
 #define MADERA_IN_VD_RAMP_MASK				0x0070
 #define MADERA_IN_VD_RAMP_SHIFT				     4
-#define MADERA_IN_VD_RAMP_WIDTH				     3
 #define MADERA_IN_VI_RAMP_MASK				0x0007
 #define MADERA_IN_VI_RAMP_SHIFT				     0
-#define MADERA_IN_VI_RAMP_WIDTH				     3
 
 /* (0x030C)  HPF_Control */
 #define MADERA_IN_HPF_CUT_MASK				0x0007
 #define MADERA_IN_HPF_CUT_SHIFT				     0
-#define MADERA_IN_HPF_CUT_WIDTH				     3
 
 /* (0x0310)  IN1L_Control */
 #define MADERA_IN1L_HPF_MASK				0x8000
 #define MADERA_IN1L_HPF_SHIFT				    15
-#define MADERA_IN1L_HPF_WIDTH				     1
 #define MADERA_IN1_DMIC_SUP_MASK			0x1800
 #define MADERA_IN1_DMIC_SUP_SHIFT			    11
-#define MADERA_IN1_DMIC_SUP_WIDTH			     2
 #define MADERA_IN1_MODE_MASK				0x0400
 #define MADERA_IN1_MODE_SHIFT				    10
-#define MADERA_IN1_MODE_WIDTH				     1
 #define MADERA_IN1L_PGA_VOL_MASK			0x00FE
 #define MADERA_IN1L_PGA_VOL_SHIFT			     1
-#define MADERA_IN1L_PGA_VOL_WIDTH			     7
 
 /* (0x0311)  ADC_Digital_Volume_1L */
 #define MADERA_IN1L_SRC_MASK				0x4000
 #define MADERA_IN1L_SRC_SHIFT				    14
-#define MADERA_IN1L_SRC_WIDTH				     1
 #define MADERA_IN1L_SRC_SE_MASK				0x2000
 #define MADERA_IN1L_SRC_SE_SHIFT			    13
-#define MADERA_IN1L_SRC_SE_WIDTH			     1
 #define MADERA_IN1L_LP_MODE				0x0800
 #define MADERA_IN1L_LP_MODE_MASK			0x0800
 #define MADERA_IN1L_LP_MODE_SHIFT			    11
-#define MADERA_IN1L_LP_MODE_WIDTH			     1
 #define MADERA_IN_VU					0x0200
 #define MADERA_IN_VU_MASK				0x0200
 #define MADERA_IN_VU_SHIFT				     9
-#define MADERA_IN_VU_WIDTH				     1
 #define MADERA_IN1L_MUTE				0x0100
 #define MADERA_IN1L_MUTE_MASK				0x0100
 #define MADERA_IN1L_MUTE_SHIFT				     8
-#define MADERA_IN1L_MUTE_WIDTH				     1
 #define MADERA_IN1L_DIG_VOL_MASK			0x00FF
 #define MADERA_IN1L_DIG_VOL_SHIFT			     0
-#define MADERA_IN1L_DIG_VOL_WIDTH			     8
 
 /* (0x0312)  DMIC1L_Control */
 #define MADERA_IN1_OSR_MASK				0x0700
 #define MADERA_IN1_OSR_SHIFT				     8
-#define MADERA_IN1_OSR_WIDTH				     3
 
 /* (0x0313)  IN1L_Rate_Control */
 #define MADERA_IN1L_RATE_MASK				0xF800
 #define MADERA_IN1L_RATE_SHIFT				    11
-#define MADERA_IN1L_RATE_WIDTH				     5
 
 /* (0x0314)  IN1R_Control */
 #define MADERA_IN1R_HPF_MASK				0x8000
 #define MADERA_IN1R_HPF_SHIFT				    15
-#define MADERA_IN1R_HPF_WIDTH				     1
 #define MADERA_IN1R_PGA_VOL_MASK			0x00FE
 #define MADERA_IN1R_PGA_VOL_SHIFT			     1
-#define MADERA_IN1R_PGA_VOL_WIDTH			     7
 #define MADERA_IN1_DMICCLK_SRC_MASK			0x1800
 #define MADERA_IN1_DMICCLK_SRC_SHIFT			    11
-#define MADERA_IN1_DMICCLK_SRC_WIDTH			     2
 
 /* (0x0315)  ADC_Digital_Volume_1R */
 #define MADERA_IN1R_SRC_MASK				0x4000
 #define MADERA_IN1R_SRC_SHIFT				    14
-#define MADERA_IN1R_SRC_WIDTH				     1
 #define MADERA_IN1R_SRC_SE_MASK				0x2000
 #define MADERA_IN1R_SRC_SE_SHIFT			    13
-#define MADERA_IN1R_SRC_SE_WIDTH			     1
 #define MADERA_IN1R_LP_MODE				0x0800
 #define MADERA_IN1R_LP_MODE_MASK			0x0800
 #define MADERA_IN1R_LP_MODE_SHIFT			    11
-#define MADERA_IN1R_LP_MODE_WIDTH			     1
 #define MADERA_IN1R_MUTE				0x0100
 #define MADERA_IN1R_MUTE_MASK				0x0100
 #define MADERA_IN1R_MUTE_SHIFT				     8
-#define MADERA_IN1R_MUTE_WIDTH				     1
 #define MADERA_IN1R_DIG_VOL_MASK			0x00FF
 #define MADERA_IN1R_DIG_VOL_SHIFT			     0
-#define MADERA_IN1R_DIG_VOL_WIDTH			     8
 
 /* (0x0317)  IN1R_Rate_Control */
 #define MADERA_IN1R_RATE_MASK				0xF800
 #define MADERA_IN1R_RATE_SHIFT				    11
-#define MADERA_IN1R_RATE_WIDTH				     5
 
 /* (0x0318)  IN2L_Control */
 #define MADERA_IN2L_HPF_MASK				0x8000
 #define MADERA_IN2L_HPF_SHIFT				    15
-#define MADERA_IN2L_HPF_WIDTH				     1
 #define MADERA_IN2_DMIC_SUP_MASK			0x1800
 #define MADERA_IN2_DMIC_SUP_SHIFT			    11
-#define MADERA_IN2_DMIC_SUP_WIDTH			     2
 #define MADERA_IN2_MODE_MASK				0x0400
 #define MADERA_IN2_MODE_SHIFT				    10
-#define MADERA_IN2_MODE_WIDTH				     1
 #define MADERA_IN2L_PGA_VOL_MASK			0x00FE
 #define MADERA_IN2L_PGA_VOL_SHIFT			     1
-#define MADERA_IN2L_PGA_VOL_WIDTH			     7
 
 /* (0x0319)  ADC_Digital_Volume_2L */
 #define MADERA_IN2L_SRC_MASK				0x4000
 #define MADERA_IN2L_SRC_SHIFT				    14
-#define MADERA_IN2L_SRC_WIDTH				     1
 #define MADERA_IN2L_SRC_SE_MASK				0x2000
 #define MADERA_IN2L_SRC_SE_SHIFT			    13
-#define MADERA_IN2L_SRC_SE_WIDTH			     1
 #define MADERA_IN2L_LP_MODE				0x0800
 #define MADERA_IN2L_LP_MODE_MASK			0x0800
 #define MADERA_IN2L_LP_MODE_SHIFT			    11
-#define MADERA_IN2L_LP_MODE_WIDTH			     1
 #define MADERA_IN2L_MUTE				0x0100
 #define MADERA_IN2L_MUTE_MASK				0x0100
 #define MADERA_IN2L_MUTE_SHIFT				     8
-#define MADERA_IN2L_MUTE_WIDTH				     1
 #define MADERA_IN2L_DIG_VOL_MASK			0x00FF
 #define MADERA_IN2L_DIG_VOL_SHIFT			     0
-#define MADERA_IN2L_DIG_VOL_WIDTH			     8
 
 /* (0x031A)  DMIC2L_Control */
 #define MADERA_IN2_OSR_MASK				0x0700
 #define MADERA_IN2_OSR_SHIFT				     8
-#define MADERA_IN2_OSR_WIDTH				     3
 
 /* (0x031C)  IN2R_Control */
 #define MADERA_IN2R_HPF_MASK				0x8000
 #define MADERA_IN2R_HPF_SHIFT				    15
-#define MADERA_IN2R_HPF_WIDTH				     1
 #define MADERA_IN2R_PGA_VOL_MASK			0x00FE
 #define MADERA_IN2R_PGA_VOL_SHIFT			     1
-#define MADERA_IN2R_PGA_VOL_WIDTH			     7
 #define MADERA_IN2_DMICCLK_SRC_MASK			0x1800
 #define MADERA_IN2_DMICCLK_SRC_SHIFT			    11
-#define MADERA_IN2_DMICCLK_SRC_WIDTH			     2
 
 /* (0x031D)  ADC_Digital_Volume_2R */
 #define MADERA_IN2R_SRC_MASK				0x4000
 #define MADERA_IN2R_SRC_SHIFT				    14
-#define MADERA_IN2R_SRC_WIDTH				     1
 #define MADERA_IN2R_SRC_SE_MASK				0x2000
 #define MADERA_IN2R_SRC_SE_SHIFT			    13
-#define MADERA_IN2R_SRC_SE_WIDTH			     1
 #define MADERA_IN2R_LP_MODE				0x0800
 #define MADERA_IN2R_LP_MODE_MASK			0x0800
 #define MADERA_IN2R_LP_MODE_SHIFT			    11
-#define MADERA_IN2R_LP_MODE_WIDTH			     1
 #define MADERA_IN2R_MUTE				0x0100
 #define MADERA_IN2R_MUTE_MASK				0x0100
 #define MADERA_IN2R_MUTE_SHIFT				     8
-#define MADERA_IN2R_MUTE_WIDTH				     1
 #define MADERA_IN2R_DIG_VOL_MASK			0x00FF
 #define MADERA_IN2R_DIG_VOL_SHIFT			     0
-#define MADERA_IN2R_DIG_VOL_WIDTH			     8
 
 /* (0x0320)  IN3L_Control */
 #define MADERA_IN3L_HPF_MASK				0x8000
 #define MADERA_IN3L_HPF_SHIFT				    15
-#define MADERA_IN3L_HPF_WIDTH				     1
 #define MADERA_IN3_DMIC_SUP_MASK			0x1800
 #define MADERA_IN3_DMIC_SUP_SHIFT			    11
-#define MADERA_IN3_DMIC_SUP_WIDTH			     2
 #define MADERA_IN3_MODE_MASK				0x0400
 #define MADERA_IN3_MODE_SHIFT				    10
-#define MADERA_IN3_MODE_WIDTH				     1
 #define MADERA_IN3L_PGA_VOL_MASK			0x00FE
 #define MADERA_IN3L_PGA_VOL_SHIFT			     1
-#define MADERA_IN3L_PGA_VOL_WIDTH			     7
 
 /* (0x0321)  ADC_Digital_Volume_3L */
 #define MADERA_IN3L_MUTE				0x0100
 #define MADERA_IN3L_MUTE_MASK				0x0100
 #define MADERA_IN3L_MUTE_SHIFT				     8
-#define MADERA_IN3L_MUTE_WIDTH				     1
 #define MADERA_IN3L_DIG_VOL_MASK			0x00FF
 #define MADERA_IN3L_DIG_VOL_SHIFT			     0
-#define MADERA_IN3L_DIG_VOL_WIDTH			     8
 
 /* (0x0322)  DMIC3L_Control */
 #define MADERA_IN3_OSR_MASK				0x0700
 #define MADERA_IN3_OSR_SHIFT				     8
-#define MADERA_IN3_OSR_WIDTH				     3
 
 /* (0x0324)  IN3R_Control */
 #define MADERA_IN3R_HPF_MASK				0x8000
 #define MADERA_IN3R_HPF_SHIFT				    15
-#define MADERA_IN3R_HPF_WIDTH				     1
 #define MADERA_IN3R_PGA_VOL_MASK			0x00FE
 #define MADERA_IN3R_PGA_VOL_SHIFT			     1
-#define MADERA_IN3R_PGA_VOL_WIDTH			     7
 #define MADERA_IN3_DMICCLK_SRC_MASK			0x1800
 #define MADERA_IN3_DMICCLK_SRC_SHIFT			    11
-#define MADERA_IN3_DMICCLK_SRC_WIDTH			     2
 
 /* (0x0325)  ADC_Digital_Volume_3R */
 #define MADERA_IN3R_MUTE				0x0100
 #define MADERA_IN3R_MUTE_MASK				0x0100
 #define MADERA_IN3R_MUTE_SHIFT				     8
-#define MADERA_IN3R_MUTE_WIDTH				     1
 #define MADERA_IN3R_DIG_VOL_MASK			0x00FF
 #define MADERA_IN3R_DIG_VOL_SHIFT			     0
-#define MADERA_IN3R_DIG_VOL_WIDTH			     8
 
 /* (0x0328)  IN4L_Control */
 #define MADERA_IN4L_HPF_MASK				0x8000
 #define MADERA_IN4L_HPF_SHIFT				    15
-#define MADERA_IN4L_HPF_WIDTH				     1
 #define MADERA_IN4_DMIC_SUP_MASK			0x1800
 #define MADERA_IN4_DMIC_SUP_SHIFT			    11
-#define MADERA_IN4_DMIC_SUP_WIDTH			     2
 
 /* (0x0329)  ADC_Digital_Volume_4L */
 #define MADERA_IN4L_MUTE				0x0100
 #define MADERA_IN4L_MUTE_MASK				0x0100
 #define MADERA_IN4L_MUTE_SHIFT				     8
-#define MADERA_IN4L_MUTE_WIDTH				     1
 #define MADERA_IN4L_DIG_VOL_MASK			0x00FF
 #define MADERA_IN4L_DIG_VOL_SHIFT			     0
-#define MADERA_IN4L_DIG_VOL_WIDTH			     8
 
 /* (0x032A)  DMIC4L_Control */
 #define MADERA_IN4_OSR_MASK				0x0700
 #define MADERA_IN4_OSR_SHIFT				     8
-#define MADERA_IN4_OSR_WIDTH				     3
 
 /* (0x032C)  IN4R_Control */
 #define MADERA_IN4R_HPF_MASK				0x8000
 #define MADERA_IN4R_HPF_SHIFT				    15
-#define MADERA_IN4R_HPF_WIDTH				     1
 #define MADERA_IN4_DMICCLK_SRC_MASK			0x1800
 #define MADERA_IN4_DMICCLK_SRC_SHIFT			    11
-#define MADERA_IN4_DMICCLK_SRC_WIDTH			     2
 
 /* (0x032D)  ADC_Digital_Volume_4R */
 #define MADERA_IN4R_MUTE				0x0100
 #define MADERA_IN4R_MUTE_MASK				0x0100
 #define MADERA_IN4R_MUTE_SHIFT				     8
-#define MADERA_IN4R_MUTE_WIDTH				     1
 #define MADERA_IN4R_DIG_VOL_MASK			0x00FF
 #define MADERA_IN4R_DIG_VOL_SHIFT			     0
-#define MADERA_IN4R_DIG_VOL_WIDTH			     8
 
 /* (0x0330)  IN5L_Control */
 #define MADERA_IN5L_HPF_MASK				0x8000
 #define MADERA_IN5L_HPF_SHIFT				    15
-#define MADERA_IN5L_HPF_WIDTH				     1
 #define MADERA_IN5_DMIC_SUP_MASK			0x1800
 #define MADERA_IN5_DMIC_SUP_SHIFT			    11
-#define MADERA_IN5_DMIC_SUP_WIDTH			     2
 
 /* (0x0331)  ADC_Digital_Volume_5L */
 #define MADERA_IN5L_MUTE				0x0100
 #define MADERA_IN5L_MUTE_MASK				0x0100
 #define MADERA_IN5L_MUTE_SHIFT				     8
-#define MADERA_IN5L_MUTE_WIDTH				     1
 #define MADERA_IN5L_DIG_VOL_MASK			0x00FF
 #define MADERA_IN5L_DIG_VOL_SHIFT			     0
-#define MADERA_IN5L_DIG_VOL_WIDTH			     8
 
 /* (0x0332)  DMIC5L_Control */
 #define MADERA_IN5_OSR_MASK				0x0700
 #define MADERA_IN5_OSR_SHIFT				     8
-#define MADERA_IN5_OSR_WIDTH				     3
 
 /* (0x0334)  IN5R_Control */
 #define MADERA_IN5R_HPF_MASK				0x8000
 #define MADERA_IN5R_HPF_SHIFT				    15
-#define MADERA_IN5R_HPF_WIDTH				     1
 #define MADERA_IN5_DMICCLK_SRC_MASK			0x1800
 #define MADERA_IN5_DMICCLK_SRC_SHIFT			    11
-#define MADERA_IN5_DMICCLK_SRC_WIDTH			     2
 
 /* (0x0335)  ADC_Digital_Volume_5R */
 #define MADERA_IN5R_MUTE				0x0100
 #define MADERA_IN5R_MUTE_MASK				0x0100
 #define MADERA_IN5R_MUTE_SHIFT				     8
-#define MADERA_IN5R_MUTE_WIDTH				     1
 #define MADERA_IN5R_DIG_VOL_MASK			0x00FF
 #define MADERA_IN5R_DIG_VOL_SHIFT			     0
-#define MADERA_IN5R_DIG_VOL_WIDTH			     8
 
 /* (0x0338)  IN6L_Control */
 #define MADERA_IN6L_HPF_MASK				0x8000
 #define MADERA_IN6L_HPF_SHIFT				    15
-#define MADERA_IN6L_HPF_WIDTH				     1
 #define MADERA_IN6_DMIC_SUP_MASK			0x1800
 #define MADERA_IN6_DMIC_SUP_SHIFT			    11
-#define MADERA_IN6_DMIC_SUP_WIDTH			     2
 
 /* (0x0339)  ADC_Digital_Volume_6L */
 #define MADERA_IN6L_MUTE				0x0100
 #define MADERA_IN6L_MUTE_MASK				0x0100
 #define MADERA_IN6L_MUTE_SHIFT				     8
-#define MADERA_IN6L_MUTE_WIDTH				     1
 #define MADERA_IN6L_DIG_VOL_MASK			0x00FF
 #define MADERA_IN6L_DIG_VOL_SHIFT			     0
-#define MADERA_IN6L_DIG_VOL_WIDTH			     8
 
 /* (0x033A)  DMIC6L_Control */
 #define MADERA_IN6_OSR_MASK				0x0700
 #define MADERA_IN6_OSR_SHIFT				     8
-#define MADERA_IN6_OSR_WIDTH				     3
 
 /* (0x033C)  IN6R_Control */
 #define MADERA_IN6R_HPF_MASK				0x8000
 #define MADERA_IN6R_HPF_SHIFT				    15
-#define MADERA_IN6R_HPF_WIDTH				     1
 
 /* (0x033D)  ADC_Digital_Volume_6R */
 #define MADERA_IN6R_MUTE				0x0100
 #define MADERA_IN6R_MUTE_MASK				0x0100
 #define MADERA_IN6R_MUTE_SHIFT				     8
-#define MADERA_IN6R_MUTE_WIDTH				     1
 #define MADERA_IN6R_DIG_VOL_MASK			0x00FF
 #define MADERA_IN6R_DIG_VOL_SHIFT			     0
-#define MADERA_IN6R_DIG_VOL_WIDTH			     8
 
 /* (0x033E)  DMIC6R_Control */
 #define MADERA_IN6_DMICCLK_SRC_MASK			0x1800
 #define MADERA_IN6_DMICCLK_SRC_SHIFT			    11
-#define MADERA_IN6_DMICCLK_SRC_WIDTH			     2
 
 /* (0x0400)  Output_Enables_1 */
 #define MADERA_EP_SEL					0x8000
 #define MADERA_EP_SEL_MASK				0x8000
 #define MADERA_EP_SEL_SHIFT				    15
-#define MADERA_EP_SEL_WIDTH				     1
 #define MADERA_OUT6L_ENA				0x0800
 #define MADERA_OUT6L_ENA_MASK				0x0800
 #define MADERA_OUT6L_ENA_SHIFT				    11
-#define MADERA_OUT6L_ENA_WIDTH				     1
 #define MADERA_OUT6R_ENA				0x0400
 #define MADERA_OUT6R_ENA_MASK				0x0400
 #define MADERA_OUT6R_ENA_SHIFT				    10
-#define MADERA_OUT6R_ENA_WIDTH				     1
 #define MADERA_OUT5L_ENA				0x0200
 #define MADERA_OUT5L_ENA_MASK				0x0200
 #define MADERA_OUT5L_ENA_SHIFT				     9
-#define MADERA_OUT5L_ENA_WIDTH				     1
 #define MADERA_OUT5R_ENA				0x0100
 #define MADERA_OUT5R_ENA_MASK				0x0100
 #define MADERA_OUT5R_ENA_SHIFT				     8
-#define MADERA_OUT5R_ENA_WIDTH				     1
 #define MADERA_OUT4L_ENA				0x0080
 #define MADERA_OUT4L_ENA_MASK				0x0080
 #define MADERA_OUT4L_ENA_SHIFT				     7
-#define MADERA_OUT4L_ENA_WIDTH				     1
 #define MADERA_OUT4R_ENA				0x0040
 #define MADERA_OUT4R_ENA_MASK				0x0040
 #define MADERA_OUT4R_ENA_SHIFT				     6
-#define MADERA_OUT4R_ENA_WIDTH				     1
 #define MADERA_OUT3L_ENA				0x0020
 #define MADERA_OUT3L_ENA_MASK				0x0020
 #define MADERA_OUT3L_ENA_SHIFT				     5
-#define MADERA_OUT3L_ENA_WIDTH				     1
 #define MADERA_OUT3R_ENA				0x0010
 #define MADERA_OUT3R_ENA_MASK				0x0010
 #define MADERA_OUT3R_ENA_SHIFT				     4
-#define MADERA_OUT3R_ENA_WIDTH				     1
 #define MADERA_OUT2L_ENA				0x0008
 #define MADERA_OUT2L_ENA_MASK				0x0008
 #define MADERA_OUT2L_ENA_SHIFT				     3
-#define MADERA_OUT2L_ENA_WIDTH				     1
 #define MADERA_OUT2R_ENA				0x0004
 #define MADERA_OUT2R_ENA_MASK				0x0004
 #define MADERA_OUT2R_ENA_SHIFT				     2
-#define MADERA_OUT2R_ENA_WIDTH				     1
 #define MADERA_OUT1L_ENA				0x0002
 #define MADERA_OUT1L_ENA_MASK				0x0002
 #define MADERA_OUT1L_ENA_SHIFT				     1
-#define MADERA_OUT1L_ENA_WIDTH				     1
 #define MADERA_OUT1R_ENA				0x0001
 #define MADERA_OUT1R_ENA_MASK				0x0001
 #define MADERA_OUT1R_ENA_SHIFT				     0
-#define MADERA_OUT1R_ENA_WIDTH				     1
 
 /* (0x0408)  Output_Rate_1 */
 #define MADERA_CP_DAC_MODE_MASK				0x0040
 #define MADERA_CP_DAC_MODE_SHIFT			     6
-#define MADERA_CP_DAC_MODE_WIDTH			     1
 #define MADERA_OUT_EXT_CLK_DIV_MASK			0x0030
 #define MADERA_OUT_EXT_CLK_DIV_SHIFT			     4
-#define MADERA_OUT_EXT_CLK_DIV_WIDTH			     2
 #define MADERA_OUT_CLK_SRC_MASK				0x0007
 #define MADERA_OUT_CLK_SRC_SHIFT			     0
-#define MADERA_OUT_CLK_SRC_WIDTH			     3
 
 /* (0x0409)  Output_Volume_Ramp */
 #define MADERA_OUT_VD_RAMP_MASK				0x0070
 #define MADERA_OUT_VD_RAMP_SHIFT			     4
-#define MADERA_OUT_VD_RAMP_WIDTH			     3
 #define MADERA_OUT_VI_RAMP_MASK				0x0007
 #define MADERA_OUT_VI_RAMP_SHIFT			     0
-#define MADERA_OUT_VI_RAMP_WIDTH			     3
 
 /* (0x0410)  Output_Path_Config_1L */
 #define MADERA_OUT1_MONO				0x1000
 #define MADERA_OUT1_MONO_MASK				0x1000
 #define MADERA_OUT1_MONO_SHIFT				    12
-#define MADERA_OUT1_MONO_WIDTH				     1
 #define MADERA_OUT1L_ANC_SRC_MASK			0x0C00
 #define MADERA_OUT1L_ANC_SRC_SHIFT			    10
-#define MADERA_OUT1L_ANC_SRC_WIDTH			     2
 
 /* (0x0411)  DAC_Digital_Volume_1L */
 #define MADERA_OUT1L_VU					0x0200
 #define MADERA_OUT1L_VU_MASK				0x0200
 #define MADERA_OUT1L_VU_SHIFT				     9
-#define MADERA_OUT1L_VU_WIDTH				     1
 #define MADERA_OUT1L_MUTE				0x0100
 #define MADERA_OUT1L_MUTE_MASK				0x0100
 #define MADERA_OUT1L_MUTE_SHIFT				     8
-#define MADERA_OUT1L_MUTE_WIDTH				     1
 #define MADERA_OUT1L_VOL_MASK				0x00FF
 #define MADERA_OUT1L_VOL_SHIFT				     0
-#define MADERA_OUT1L_VOL_WIDTH				     8
 
 /* (0x0412)  Output_Path_Config_1 */
 #define MADERA_HP1_GND_SEL_MASK				0x0007
 #define MADERA_HP1_GND_SEL_SHIFT			     0
-#define MADERA_HP1_GND_SEL_WIDTH			     3
 
 /* (0x0414)  Output_Path_Config_1R */
 #define MADERA_OUT1R_ANC_SRC_MASK			0x0C00
 #define MADERA_OUT1R_ANC_SRC_SHIFT			    10
-#define MADERA_OUT1R_ANC_SRC_WIDTH			     2
 
 /* (0x0415)  DAC_Digital_Volume_1R */
 #define MADERA_OUT1R_MUTE				0x0100
 #define MADERA_OUT1R_MUTE_MASK				0x0100
 #define MADERA_OUT1R_MUTE_SHIFT				     8
-#define MADERA_OUT1R_MUTE_WIDTH				     1
 #define MADERA_OUT1R_VOL_MASK				0x00FF
 #define MADERA_OUT1R_VOL_SHIFT				     0
-#define MADERA_OUT1R_VOL_WIDTH				     8
 
 /* (0x0418)  Output_Path_Config_2L */
 #define MADERA_OUT2L_ANC_SRC_MASK			0x0C00
 #define MADERA_OUT2L_ANC_SRC_SHIFT			    10
-#define MADERA_OUT2L_ANC_SRC_WIDTH			     2
 
 /* (0x0419)  DAC_Digital_Volume_2L */
 #define MADERA_OUT2L_MUTE				0x0100
 #define MADERA_OUT2L_MUTE_MASK				0x0100
 #define MADERA_OUT2L_MUTE_SHIFT				     8
-#define MADERA_OUT2L_MUTE_WIDTH				     1
 #define MADERA_OUT2L_VOL_MASK				0x00FF
 #define MADERA_OUT2L_VOL_SHIFT				     0
-#define MADERA_OUT2L_VOL_WIDTH				     8
 
 /* (0x041A)  Output_Path_Config_2 */
 #define MADERA_HP2_GND_SEL_MASK				0x0007
 #define MADERA_HP2_GND_SEL_SHIFT			     0
-#define MADERA_HP2_GND_SEL_WIDTH			     3
 
 /* (0x041C)  Output_Path_Config_2R */
 #define MADERA_OUT2R_ANC_SRC_MASK			0x0C00
 #define MADERA_OUT2R_ANC_SRC_SHIFT			    10
-#define MADERA_OUT2R_ANC_SRC_WIDTH			     2
 
 /* (0x041D)  DAC_Digital_Volume_2R */
 #define MADERA_OUT2R_MUTE				0x0100
 #define MADERA_OUT2R_MUTE_MASK				0x0100
 #define MADERA_OUT2R_MUTE_SHIFT				     8
-#define MADERA_OUT2R_MUTE_WIDTH				     1
 #define MADERA_OUT2R_VOL_MASK				0x00FF
 #define MADERA_OUT2R_VOL_SHIFT				     0
-#define MADERA_OUT2R_VOL_WIDTH				     8
 
 /* (0x0420)  Output_Path_Config_3L */
 #define MADERA_OUT3L_ANC_SRC_MASK			0x0C00
 #define MADERA_OUT3L_ANC_SRC_SHIFT			    10
-#define MADERA_OUT3L_ANC_SRC_WIDTH			     2
 
 /* (0x0421)  DAC_Digital_Volume_3L */
 #define MADERA_OUT3L_MUTE				0x0100
 #define MADERA_OUT3L_MUTE_MASK				0x0100
 #define MADERA_OUT3L_MUTE_SHIFT				     8
-#define MADERA_OUT3L_MUTE_WIDTH				     1
 #define MADERA_OUT3L_VOL_MASK				0x00FF
 #define MADERA_OUT3L_VOL_SHIFT				     0
-#define MADERA_OUT3L_VOL_WIDTH				     8
 
 /* (0x0424)  Output_Path_Config_3R */
 #define MADERA_OUT3R_ANC_SRC_MASK			0x0C00
 #define MADERA_OUT3R_ANC_SRC_SHIFT			    10
-#define MADERA_OUT3R_ANC_SRC_WIDTH			     2
 
 /* (0x0425)  DAC_Digital_Volume_3R */
 #define MADERA_OUT3R_MUTE				0x0100
 #define MADERA_OUT3R_MUTE_MASK				0x0100
 #define MADERA_OUT3R_MUTE_SHIFT				     8
-#define MADERA_OUT3R_MUTE_WIDTH				     1
 #define MADERA_OUT3R_VOL_MASK				0x00FF
 #define MADERA_OUT3R_VOL_SHIFT				     0
-#define MADERA_OUT3R_VOL_WIDTH				     8
 
 /* (0x0428)  Output_Path_Config_4L */
 #define MADERA_OUT4L_ANC_SRC_MASK			0x0C00
 #define MADERA_OUT4L_ANC_SRC_SHIFT			    10
-#define MADERA_OUT4L_ANC_SRC_WIDTH			     2
 
 /* (0x0429)  DAC_Digital_Volume_4L */
 #define MADERA_OUT4L_MUTE				0x0100
 #define MADERA_OUT4L_MUTE_MASK				0x0100
 #define MADERA_OUT4L_MUTE_SHIFT				     8
-#define MADERA_OUT4L_MUTE_WIDTH				     1
 #define MADERA_OUT4L_VOL_MASK				0x00FF
 #define MADERA_OUT4L_VOL_SHIFT				     0
-#define MADERA_OUT4L_VOL_WIDTH				     8
 
 /* (0x042C)  Output_Path_Config_4R */
 #define MADERA_OUT4R_ANC_SRC_MASK			0x0C00
 #define MADERA_OUT4R_ANC_SRC_SHIFT			    10
-#define MADERA_OUT4R_ANC_SRC_WIDTH			     2
 
 /* (0x042D)  DAC_Digital_Volume_4R */
 #define MADERA_OUT4R_MUTE				0x0100
 #define MADERA_OUT4R_MUTE_MASK				0x0100
 #define MADERA_OUT4R_MUTE_SHIFT				     8
-#define MADERA_OUT4R_MUTE_WIDTH				     1
 #define MADERA_OUT4R_VOL_MASK				0x00FF
 #define MADERA_OUT4R_VOL_SHIFT				     0
-#define MADERA_OUT4R_VOL_WIDTH				     8
 
 /* (0x0430)  Output_Path_Config_5L */
 #define MADERA_OUT5_OSR					0x2000
 #define MADERA_OUT5_OSR_MASK				0x2000
 #define MADERA_OUT5_OSR_SHIFT				    13
-#define MADERA_OUT5_OSR_WIDTH				     1
 #define MADERA_OUT5L_ANC_SRC_MASK			0x0C00
 #define MADERA_OUT5L_ANC_SRC_SHIFT			    10
-#define MADERA_OUT5L_ANC_SRC_WIDTH			     2
 
 /* (0x0431)  DAC_Digital_Volume_5L */
 #define MADERA_OUT5L_MUTE				0x0100
 #define MADERA_OUT5L_MUTE_MASK				0x0100
 #define MADERA_OUT5L_MUTE_SHIFT				     8
-#define MADERA_OUT5L_MUTE_WIDTH				     1
 #define MADERA_OUT5L_VOL_MASK				0x00FF
 #define MADERA_OUT5L_VOL_SHIFT				     0
-#define MADERA_OUT5L_VOL_WIDTH				     8
 
 /* (0x0434)  Output_Path_Config_5R */
 #define MADERA_OUT5R_ANC_SRC_MASK			0x0C00
 #define MADERA_OUT5R_ANC_SRC_SHIFT			    10
-#define MADERA_OUT5R_ANC_SRC_WIDTH			     2
 
 /* (0x0435)  DAC_Digital_Volume_5R */
 #define MADERA_OUT5R_MUTE				0x0100
 #define MADERA_OUT5R_MUTE_MASK				0x0100
 #define MADERA_OUT5R_MUTE_SHIFT				     8
-#define MADERA_OUT5R_MUTE_WIDTH				     1
 #define MADERA_OUT5R_VOL_MASK				0x00FF
 #define MADERA_OUT5R_VOL_SHIFT				     0
-#define MADERA_OUT5R_VOL_WIDTH				     8
 
 /* (0x0438)  Output_Path_Config_6L */
 #define MADERA_OUT6_OSR					0x2000
 #define MADERA_OUT6_OSR_MASK				0x2000
 #define MADERA_OUT6_OSR_SHIFT				    13
-#define MADERA_OUT6_OSR_WIDTH				     1
 #define MADERA_OUT6L_ANC_SRC_MASK			0x0C00
 #define MADERA_OUT6L_ANC_SRC_SHIFT			    10
-#define MADERA_OUT6L_ANC_SRC_WIDTH			     2
 
 /* (0x0439)  DAC_Digital_Volume_6L */
 #define MADERA_OUT6L_MUTE				0x0100
 #define MADERA_OUT6L_MUTE_MASK				0x0100
 #define MADERA_OUT6L_MUTE_SHIFT				     8
-#define MADERA_OUT6L_MUTE_WIDTH				     1
 #define MADERA_OUT6L_VOL_MASK				0x00FF
 #define MADERA_OUT6L_VOL_SHIFT				     0
-#define MADERA_OUT6L_VOL_WIDTH				     8
 
 /* (0x043C)  Output_Path_Config_6R */
 #define MADERA_OUT6R_ANC_SRC_MASK			0x0C00
 #define MADERA_OUT6R_ANC_SRC_SHIFT			    10
-#define MADERA_OUT6R_ANC_SRC_WIDTH			     2
 
 /* (0x043D)  DAC_Digital_Volume_6R */
 #define MADERA_OUT6R_MUTE				0x0100
 #define MADERA_OUT6R_MUTE_MASK				0x0100
 #define MADERA_OUT6R_MUTE_SHIFT				     8
-#define MADERA_OUT6R_MUTE_WIDTH				     1
 #define MADERA_OUT6R_VOL_MASK				0x00FF
 #define MADERA_OUT6R_VOL_SHIFT				     0
-#define MADERA_OUT6R_VOL_WIDTH				     8
 
 /* (0x0450) - DAC AEC Control 1 */
 #define MADERA_AEC1_LOOPBACK_SRC_MASK			0x003C
 #define MADERA_AEC1_LOOPBACK_SRC_SHIFT			     2
-#define MADERA_AEC1_LOOPBACK_SRC_WIDTH			     4
 #define MADERA_AEC1_ENA_STS				0x0002
 #define MADERA_AEC1_ENA_STS_MASK			0x0002
 #define MADERA_AEC1_ENA_STS_SHIFT			     1
-#define MADERA_AEC1_ENA_STS_WIDTH			     1
 #define MADERA_AEC1_LOOPBACK_ENA			0x0001
 #define MADERA_AEC1_LOOPBACK_ENA_MASK			0x0001
 #define MADERA_AEC1_LOOPBACK_ENA_SHIFT			     0
-#define MADERA_AEC1_LOOPBACK_ENA_WIDTH			     1
 
 /* (0x0451)  DAC_AEC_Control_2 */
 #define MADERA_AEC2_LOOPBACK_SRC_MASK			0x003C
 #define MADERA_AEC2_LOOPBACK_SRC_SHIFT			     2
-#define MADERA_AEC2_LOOPBACK_SRC_WIDTH			     4
 #define MADERA_AEC2_ENA_STS				0x0002
 #define MADERA_AEC2_ENA_STS_MASK			0x0002
 #define MADERA_AEC2_ENA_STS_SHIFT			     1
-#define MADERA_AEC2_ENA_STS_WIDTH			     1
 #define MADERA_AEC2_LOOPBACK_ENA			0x0001
 #define MADERA_AEC2_LOOPBACK_ENA_MASK			0x0001
 #define MADERA_AEC2_LOOPBACK_ENA_SHIFT			     0
-#define MADERA_AEC2_LOOPBACK_ENA_WIDTH			     1
 
 /* (0x0458)  Noise_Gate_Control */
 #define MADERA_NGATE_HOLD_MASK				0x0030
 #define MADERA_NGATE_HOLD_SHIFT				     4
-#define MADERA_NGATE_HOLD_WIDTH				     2
 #define MADERA_NGATE_THR_MASK				0x000E
 #define MADERA_NGATE_THR_SHIFT				     1
-#define MADERA_NGATE_THR_WIDTH				     3
 #define MADERA_NGATE_ENA				0x0001
 #define MADERA_NGATE_ENA_MASK				0x0001
 #define MADERA_NGATE_ENA_SHIFT				     0
-#define MADERA_NGATE_ENA_WIDTH				     1
 
 /* (0x0490)  PDM_SPK1_CTRL_1 */
 #define MADERA_SPK1R_MUTE				0x2000
 #define MADERA_SPK1R_MUTE_MASK				0x2000
 #define MADERA_SPK1R_MUTE_SHIFT				    13
-#define MADERA_SPK1R_MUTE_WIDTH				     1
 #define MADERA_SPK1L_MUTE				0x1000
 #define MADERA_SPK1L_MUTE_MASK				0x1000
 #define MADERA_SPK1L_MUTE_SHIFT				    12
-#define MADERA_SPK1L_MUTE_WIDTH				     1
 #define MADERA_SPK1_MUTE_ENDIAN				0x0100
 #define MADERA_SPK1_MUTE_ENDIAN_MASK			0x0100
 #define MADERA_SPK1_MUTE_ENDIAN_SHIFT			     8
-#define MADERA_SPK1_MUTE_ENDIAN_WIDTH			     1
 #define MADERA_SPK1_MUTE_SEQ1_MASK			0x00FF
 #define MADERA_SPK1_MUTE_SEQ1_SHIFT			     0
-#define MADERA_SPK1_MUTE_SEQ1_WIDTH			     8
 
 /* (0x0491)  PDM_SPK1_CTRL_2 */
 #define MADERA_SPK1_FMT					0x0001
 #define MADERA_SPK1_FMT_MASK				0x0001
 #define MADERA_SPK1_FMT_SHIFT				     0
-#define MADERA_SPK1_FMT_WIDTH				     1
 
 /* (0x0492)  PDM_SPK2_CTRL_1 */
 #define MADERA_SPK2R_MUTE				0x2000
 #define MADERA_SPK2R_MUTE_MASK				0x2000
 #define MADERA_SPK2R_MUTE_SHIFT				    13
-#define MADERA_SPK2R_MUTE_WIDTH				     1
 #define MADERA_SPK2L_MUTE				0x1000
 #define MADERA_SPK2L_MUTE_MASK				0x1000
 #define MADERA_SPK2L_MUTE_SHIFT				    12
-#define MADERA_SPK2L_MUTE_WIDTH				     1
 
 /* (0x04A0) - HP1 Short Circuit Ctrl */
 #define MADERA_HP1_SC_ENA				0x1000
 #define MADERA_HP1_SC_ENA_MASK				0x1000
 #define MADERA_HP1_SC_ENA_SHIFT				    12
-#define MADERA_HP1_SC_ENA_WIDTH				     1
 
 /* (0x04A1) - HP2 Short Circuit Ctrl */
 #define MADERA_HP2_SC_ENA				0x1000
 #define MADERA_HP2_SC_ENA_MASK				0x1000
 #define MADERA_HP2_SC_ENA_SHIFT				    12
-#define MADERA_HP2_SC_ENA_WIDTH				     1
 
 /* (0x04A2) - HP3 Short Circuit Ctrl */
 #define MADERA_HP3_SC_ENA				0x1000
 #define MADERA_HP3_SC_ENA_MASK				0x1000
 #define MADERA_HP3_SC_ENA_SHIFT				    12
-#define MADERA_HP3_SC_ENA_WIDTH				     1
 
 /* (0x04A8) - HP_Test_Ctrl_5 */
 #define MADERA_HP1L_ONEFLT				0x0100
 #define MADERA_HP1L_ONEFLT_MASK				0x0100
 #define MADERA_HP1L_ONEFLT_SHIFT			     8
-#define MADERA_HP1L_ONEFLT_WIDTH			     1
 
 /* (0x04A9) - HP_Test_Ctrl_6 */
 #define MADERA_HP1R_ONEFLT				0x0100
 #define MADERA_HP1R_ONEFLT_MASK				0x0100
 #define MADERA_HP1R_ONEFLT_SHIFT			     8
-#define MADERA_HP1R_ONEFLT_WIDTH			     1
 
 /* (0x0500)  AIF1_BCLK_Ctrl */
 #define MADERA_AIF1_BCLK_INV				0x0080
 #define MADERA_AIF1_BCLK_INV_MASK			0x0080
 #define MADERA_AIF1_BCLK_INV_SHIFT			     7
-#define MADERA_AIF1_BCLK_INV_WIDTH			     1
 #define MADERA_AIF1_BCLK_MSTR				0x0020
 #define MADERA_AIF1_BCLK_MSTR_MASK			0x0020
 #define MADERA_AIF1_BCLK_MSTR_SHIFT			     5
-#define MADERA_AIF1_BCLK_MSTR_WIDTH			     1
 #define MADERA_AIF1_BCLK_FREQ_MASK			0x001F
 #define MADERA_AIF1_BCLK_FREQ_SHIFT			     0
-#define MADERA_AIF1_BCLK_FREQ_WIDTH			     5
 
 /* (0x0501)  AIF1_Tx_Pin_Ctrl */
 #define MADERA_AIF1TX_LRCLK_SRC				0x0008
 #define MADERA_AIF1TX_LRCLK_SRC_MASK			0x0008
 #define MADERA_AIF1TX_LRCLK_SRC_SHIFT			     3
-#define MADERA_AIF1TX_LRCLK_SRC_WIDTH			     1
 #define MADERA_AIF1TX_LRCLK_INV				0x0004
 #define MADERA_AIF1TX_LRCLK_INV_MASK			0x0004
 #define MADERA_AIF1TX_LRCLK_INV_SHIFT			     2
-#define MADERA_AIF1TX_LRCLK_INV_WIDTH			     1
 #define MADERA_AIF1TX_LRCLK_MSTR			0x0001
 #define MADERA_AIF1TX_LRCLK_MSTR_MASK			0x0001
 #define MADERA_AIF1TX_LRCLK_MSTR_SHIFT			     0
-#define MADERA_AIF1TX_LRCLK_MSTR_WIDTH			     1
 
 /* (0x0502)  AIF1_Rx_Pin_Ctrl */
 #define MADERA_AIF1RX_LRCLK_INV				0x0004
 #define MADERA_AIF1RX_LRCLK_INV_MASK			0x0004
 #define MADERA_AIF1RX_LRCLK_INV_SHIFT			     2
-#define MADERA_AIF1RX_LRCLK_INV_WIDTH			     1
 #define MADERA_AIF1RX_LRCLK_FRC				0x0002
 #define MADERA_AIF1RX_LRCLK_FRC_MASK			0x0002
 #define MADERA_AIF1RX_LRCLK_FRC_SHIFT			     1
-#define MADERA_AIF1RX_LRCLK_FRC_WIDTH			     1
 #define MADERA_AIF1RX_LRCLK_MSTR			0x0001
 #define MADERA_AIF1RX_LRCLK_MSTR_MASK			0x0001
 #define MADERA_AIF1RX_LRCLK_MSTR_SHIFT			     0
-#define MADERA_AIF1RX_LRCLK_MSTR_WIDTH			     1
 
 /* (0x0503)  AIF1_Rate_Ctrl */
 #define MADERA_AIF1_RATE_MASK				0xF800
 #define MADERA_AIF1_RATE_SHIFT				    11
-#define MADERA_AIF1_RATE_WIDTH				     5
 #define MADERA_AIF1_TRI					0x0040
 #define MADERA_AIF1_TRI_MASK				0x0040
 #define MADERA_AIF1_TRI_SHIFT				     6
-#define MADERA_AIF1_TRI_WIDTH				     1
 
 /* (0x0504)  AIF1_Format */
 #define MADERA_AIF1_FMT_MASK				0x0007
 #define MADERA_AIF1_FMT_SHIFT				     0
-#define MADERA_AIF1_FMT_WIDTH				     3
 
 /* (0x0506)  AIF1_Rx_BCLK_Rate */
 #define MADERA_AIF1RX_BCPF_MASK				0x1FFF
 #define MADERA_AIF1RX_BCPF_SHIFT			     0
-#define MADERA_AIF1RX_BCPF_WIDTH			    13
 
 /* (0x0507)  AIF1_Frame_Ctrl_1 */
 #define MADERA_AIF1TX_WL_MASK				0x3F00
 #define MADERA_AIF1TX_WL_SHIFT				     8
-#define MADERA_AIF1TX_WL_WIDTH				     6
 #define MADERA_AIF1TX_SLOT_LEN_MASK			0x00FF
 #define MADERA_AIF1TX_SLOT_LEN_SHIFT			     0
-#define MADERA_AIF1TX_SLOT_LEN_WIDTH			     8
 
 /* (0x0508)  AIF1_Frame_Ctrl_2 */
 #define MADERA_AIF1RX_WL_MASK				0x3F00
 #define MADERA_AIF1RX_WL_SHIFT				     8
-#define MADERA_AIF1RX_WL_WIDTH				     6
 #define MADERA_AIF1RX_SLOT_LEN_MASK			0x00FF
 #define MADERA_AIF1RX_SLOT_LEN_SHIFT			     0
-#define MADERA_AIF1RX_SLOT_LEN_WIDTH			     8
 
 /* (0x0509)  AIF1_Frame_Ctrl_3 */
 #define MADERA_AIF1TX1_SLOT_MASK			0x003F
 #define MADERA_AIF1TX1_SLOT_SHIFT			     0
-#define MADERA_AIF1TX1_SLOT_WIDTH			     6
 
 /* (0x0519)  AIF1_Tx_Enables */
 #define MADERA_AIF1TX8_ENA				0x0080
 #define MADERA_AIF1TX8_ENA_MASK				0x0080
 #define MADERA_AIF1TX8_ENA_SHIFT			     7
-#define MADERA_AIF1TX8_ENA_WIDTH			     1
 #define MADERA_AIF1TX7_ENA				0x0040
 #define MADERA_AIF1TX7_ENA_MASK				0x0040
 #define MADERA_AIF1TX7_ENA_SHIFT			     6
-#define MADERA_AIF1TX7_ENA_WIDTH			     1
 #define MADERA_AIF1TX6_ENA				0x0020
 #define MADERA_AIF1TX6_ENA_MASK				0x0020
 #define MADERA_AIF1TX6_ENA_SHIFT			     5
-#define MADERA_AIF1TX6_ENA_WIDTH			     1
 #define MADERA_AIF1TX5_ENA				0x0010
 #define MADERA_AIF1TX5_ENA_MASK				0x0010
 #define MADERA_AIF1TX5_ENA_SHIFT			     4
-#define MADERA_AIF1TX5_ENA_WIDTH			     1
 #define MADERA_AIF1TX4_ENA				0x0008
 #define MADERA_AIF1TX4_ENA_MASK				0x0008
 #define MADERA_AIF1TX4_ENA_SHIFT			     3
-#define MADERA_AIF1TX4_ENA_WIDTH			     1
 #define MADERA_AIF1TX3_ENA				0x0004
 #define MADERA_AIF1TX3_ENA_MASK				0x0004
 #define MADERA_AIF1TX3_ENA_SHIFT			     2
-#define MADERA_AIF1TX3_ENA_WIDTH			     1
 #define MADERA_AIF1TX2_ENA				0x0002
 #define MADERA_AIF1TX2_ENA_MASK				0x0002
 #define MADERA_AIF1TX2_ENA_SHIFT			     1
-#define MADERA_AIF1TX2_ENA_WIDTH			     1
 #define MADERA_AIF1TX1_ENA				0x0001
 #define MADERA_AIF1TX1_ENA_MASK				0x0001
 #define MADERA_AIF1TX1_ENA_SHIFT			     0
-#define MADERA_AIF1TX1_ENA_WIDTH			     1
 
 /* (0x051A)  AIF1_Rx_Enables */
 #define MADERA_AIF1RX8_ENA				0x0080
 #define MADERA_AIF1RX8_ENA_MASK				0x0080
 #define MADERA_AIF1RX8_ENA_SHIFT			     7
-#define MADERA_AIF1RX8_ENA_WIDTH			     1
 #define MADERA_AIF1RX7_ENA				0x0040
 #define MADERA_AIF1RX7_ENA_MASK				0x0040
 #define MADERA_AIF1RX7_ENA_SHIFT			     6
-#define MADERA_AIF1RX7_ENA_WIDTH			     1
 #define MADERA_AIF1RX6_ENA				0x0020
 #define MADERA_AIF1RX6_ENA_MASK				0x0020
 #define MADERA_AIF1RX6_ENA_SHIFT			     5
-#define MADERA_AIF1RX6_ENA_WIDTH			     1
 #define MADERA_AIF1RX5_ENA				0x0010
 #define MADERA_AIF1RX5_ENA_MASK				0x0010
 #define MADERA_AIF1RX5_ENA_SHIFT			     4
-#define MADERA_AIF1RX5_ENA_WIDTH			     1
 #define MADERA_AIF1RX4_ENA				0x0008
 #define MADERA_AIF1RX4_ENA_MASK				0x0008
 #define MADERA_AIF1RX4_ENA_SHIFT			     3
-#define MADERA_AIF1RX4_ENA_WIDTH			     1
 #define MADERA_AIF1RX3_ENA				0x0004
 #define MADERA_AIF1RX3_ENA_MASK				0x0004
 #define MADERA_AIF1RX3_ENA_SHIFT			     2
-#define MADERA_AIF1RX3_ENA_WIDTH			     1
 #define MADERA_AIF1RX2_ENA				0x0002
 #define MADERA_AIF1RX2_ENA_MASK				0x0002
 #define MADERA_AIF1RX2_ENA_SHIFT			     1
-#define MADERA_AIF1RX2_ENA_WIDTH			     1
 #define MADERA_AIF1RX1_ENA				0x0001
 #define MADERA_AIF1RX1_ENA_MASK				0x0001
 #define MADERA_AIF1RX1_ENA_SHIFT			     0
-#define MADERA_AIF1RX1_ENA_WIDTH			     1
 
 /* (0x0559)  AIF2_Tx_Enables */
 #define MADERA_AIF2TX8_ENA				0x0080
 #define MADERA_AIF2TX8_ENA_MASK				0x0080
 #define MADERA_AIF2TX8_ENA_SHIFT			     7
-#define MADERA_AIF2TX8_ENA_WIDTH			     1
 #define MADERA_AIF2TX7_ENA				0x0040
 #define MADERA_AIF2TX7_ENA_MASK				0x0040
 #define MADERA_AIF2TX7_ENA_SHIFT			     6
-#define MADERA_AIF2TX7_ENA_WIDTH			     1
 #define MADERA_AIF2TX6_ENA				0x0020
 #define MADERA_AIF2TX6_ENA_MASK				0x0020
 #define MADERA_AIF2TX6_ENA_SHIFT			     5
-#define MADERA_AIF2TX6_ENA_WIDTH			     1
 #define MADERA_AIF2TX5_ENA				0x0010
 #define MADERA_AIF2TX5_ENA_MASK				0x0010
 #define MADERA_AIF2TX5_ENA_SHIFT			     4
-#define MADERA_AIF2TX5_ENA_WIDTH			     1
 #define MADERA_AIF2TX4_ENA				0x0008
 #define MADERA_AIF2TX4_ENA_MASK				0x0008
 #define MADERA_AIF2TX4_ENA_SHIFT			     3
-#define MADERA_AIF2TX4_ENA_WIDTH			     1
 #define MADERA_AIF2TX3_ENA				0x0004
 #define MADERA_AIF2TX3_ENA_MASK				0x0004
 #define MADERA_AIF2TX3_ENA_SHIFT			     2
-#define MADERA_AIF2TX3_ENA_WIDTH			     1
 #define MADERA_AIF2TX2_ENA				0x0002
 #define MADERA_AIF2TX2_ENA_MASK				0x0002
 #define MADERA_AIF2TX2_ENA_SHIFT			     1
-#define MADERA_AIF2TX2_ENA_WIDTH			     1
 #define MADERA_AIF2TX1_ENA				0x0001
 #define MADERA_AIF2TX1_ENA_MASK				0x0001
 #define MADERA_AIF2TX1_ENA_SHIFT			     0
-#define MADERA_AIF2TX1_ENA_WIDTH			     1
 
 /* (0x055A)  AIF2_Rx_Enables */
 #define MADERA_AIF2RX8_ENA				0x0080
 #define MADERA_AIF2RX8_ENA_MASK				0x0080
 #define MADERA_AIF2RX8_ENA_SHIFT			     7
-#define MADERA_AIF2RX8_ENA_WIDTH			     1
 #define MADERA_AIF2RX7_ENA				0x0040
 #define MADERA_AIF2RX7_ENA_MASK				0x0040
 #define MADERA_AIF2RX7_ENA_SHIFT			     6
-#define MADERA_AIF2RX7_ENA_WIDTH			     1
 #define MADERA_AIF2RX6_ENA				0x0020
 #define MADERA_AIF2RX6_ENA_MASK				0x0020
 #define MADERA_AIF2RX6_ENA_SHIFT			     5
-#define MADERA_AIF2RX6_ENA_WIDTH			     1
 #define MADERA_AIF2RX5_ENA				0x0010
 #define MADERA_AIF2RX5_ENA_MASK				0x0010
 #define MADERA_AIF2RX5_ENA_SHIFT			     4
-#define MADERA_AIF2RX5_ENA_WIDTH			     1
 #define MADERA_AIF2RX4_ENA				0x0008
 #define MADERA_AIF2RX4_ENA_MASK				0x0008
 #define MADERA_AIF2RX4_ENA_SHIFT			     3
-#define MADERA_AIF2RX4_ENA_WIDTH			     1
 #define MADERA_AIF2RX3_ENA				0x0004
 #define MADERA_AIF2RX3_ENA_MASK				0x0004
 #define MADERA_AIF2RX3_ENA_SHIFT			     2
-#define MADERA_AIF2RX3_ENA_WIDTH			     1
 #define MADERA_AIF2RX2_ENA				0x0002
 #define MADERA_AIF2RX2_ENA_MASK				0x0002
 #define MADERA_AIF2RX2_ENA_SHIFT			     1
-#define MADERA_AIF2RX2_ENA_WIDTH			     1
 #define MADERA_AIF2RX1_ENA				0x0001
 #define MADERA_AIF2RX1_ENA_MASK				0x0001
 #define MADERA_AIF2RX1_ENA_SHIFT			     0
-#define MADERA_AIF2RX1_ENA_WIDTH			     1
 
 /* (0x0599)  AIF3_Tx_Enables */
 #define MADERA_AIF3TX8_ENA				0x0080
 #define MADERA_AIF3TX8_ENA_MASK				0x0080
 #define MADERA_AIF3TX8_ENA_SHIFT			     7
-#define MADERA_AIF3TX8_ENA_WIDTH			     1
 #define MADERA_AIF3TX7_ENA				0x0040
 #define MADERA_AIF3TX7_ENA_MASK				0x0040
 #define MADERA_AIF3TX7_ENA_SHIFT			     6
-#define MADERA_AIF3TX7_ENA_WIDTH			     1
 #define MADERA_AIF3TX6_ENA				0x0020
 #define MADERA_AIF3TX6_ENA_MASK				0x0020
 #define MADERA_AIF3TX6_ENA_SHIFT			     5
-#define MADERA_AIF3TX6_ENA_WIDTH			     1
 #define MADERA_AIF3TX5_ENA				0x0010
 #define MADERA_AIF3TX5_ENA_MASK				0x0010
 #define MADERA_AIF3TX5_ENA_SHIFT			     4
-#define MADERA_AIF3TX5_ENA_WIDTH			     1
 #define MADERA_AIF3TX4_ENA				0x0008
 #define MADERA_AIF3TX4_ENA_MASK				0x0008
 #define MADERA_AIF3TX4_ENA_SHIFT			     3
-#define MADERA_AIF3TX4_ENA_WIDTH			     1
 #define MADERA_AIF3TX3_ENA				0x0004
 #define MADERA_AIF3TX3_ENA_MASK				0x0004
 #define MADERA_AIF3TX3_ENA_SHIFT			     2
-#define MADERA_AIF3TX3_ENA_WIDTH			     1
 #define MADERA_AIF3TX2_ENA				0x0002
 #define MADERA_AIF3TX2_ENA_MASK				0x0002
 #define MADERA_AIF3TX2_ENA_SHIFT			     1
-#define MADERA_AIF3TX2_ENA_WIDTH			     1
 #define MADERA_AIF3TX1_ENA				0x0001
 #define MADERA_AIF3TX1_ENA_MASK				0x0001
 #define MADERA_AIF3TX1_ENA_SHIFT			     0
-#define MADERA_AIF3TX1_ENA_WIDTH			     1
 
 /* (0x059A)  AIF3_Rx_Enables */
 #define MADERA_AIF3RX8_ENA				0x0080
 #define MADERA_AIF3RX8_ENA_MASK				0x0080
 #define MADERA_AIF3RX8_ENA_SHIFT			     7
-#define MADERA_AIF3RX8_ENA_WIDTH			     1
 #define MADERA_AIF3RX7_ENA				0x0040
 #define MADERA_AIF3RX7_ENA_MASK				0x0040
 #define MADERA_AIF3RX7_ENA_SHIFT			     6
-#define MADERA_AIF3RX7_ENA_WIDTH			     1
 #define MADERA_AIF3RX6_ENA				0x0020
 #define MADERA_AIF3RX6_ENA_MASK				0x0020
 #define MADERA_AIF3RX6_ENA_SHIFT			     5
-#define MADERA_AIF3RX6_ENA_WIDTH			     1
 #define MADERA_AIF3RX5_ENA				0x0010
 #define MADERA_AIF3RX5_ENA_MASK				0x0010
 #define MADERA_AIF3RX5_ENA_SHIFT			     4
-#define MADERA_AIF3RX5_ENA_WIDTH			     1
 #define MADERA_AIF3RX4_ENA				0x0008
 #define MADERA_AIF3RX4_ENA_MASK				0x0008
 #define MADERA_AIF3RX4_ENA_SHIFT			     3
-#define MADERA_AIF3RX4_ENA_WIDTH			     1
 #define MADERA_AIF3RX3_ENA				0x0004
 #define MADERA_AIF3RX3_ENA_MASK				0x0004
 #define MADERA_AIF3RX3_ENA_SHIFT			     2
-#define MADERA_AIF3RX3_ENA_WIDTH			     1
 #define MADERA_AIF3RX2_ENA				0x0002
 #define MADERA_AIF3RX2_ENA_MASK				0x0002
 #define MADERA_AIF3RX2_ENA_SHIFT			     1
-#define MADERA_AIF3RX2_ENA_WIDTH			     1
 #define MADERA_AIF3RX1_ENA				0x0001
 #define MADERA_AIF3RX1_ENA_MASK				0x0001
 #define MADERA_AIF3RX1_ENA_SHIFT			     0
-#define MADERA_AIF3RX1_ENA_WIDTH			     1
 
 /* (0x05B9)  AIF4_Tx_Enables */
 #define MADERA_AIF4TX2_ENA				0x0002
 #define MADERA_AIF4TX2_ENA_MASK				0x0002
 #define MADERA_AIF4TX2_ENA_SHIFT			     1
-#define MADERA_AIF4TX2_ENA_WIDTH			     1
 #define MADERA_AIF4TX1_ENA				0x0001
 #define MADERA_AIF4TX1_ENA_MASK				0x0001
 #define MADERA_AIF4TX1_ENA_SHIFT			     0
-#define MADERA_AIF4TX1_ENA_WIDTH			     1
 
 /* (0x05BA)  AIF4_Rx_Enables */
 #define MADERA_AIF4RX2_ENA				0x0002
 #define MADERA_AIF4RX2_ENA_MASK				0x0002
 #define MADERA_AIF4RX2_ENA_SHIFT			     1
-#define MADERA_AIF4RX2_ENA_WIDTH			     1
 #define MADERA_AIF4RX1_ENA				0x0001
 #define MADERA_AIF4RX1_ENA_MASK				0x0001
 #define MADERA_AIF4RX1_ENA_SHIFT			     0
-#define MADERA_AIF4RX1_ENA_WIDTH			     1
 
 /* (0x05C2)  SPD1_TX_Control */
 #define MADERA_SPD1_VAL2				0x2000
 #define MADERA_SPD1_VAL2_MASK				0x2000
 #define MADERA_SPD1_VAL2_SHIFT				    13
-#define MADERA_SPD1_VAL2_WIDTH				     1
 #define MADERA_SPD1_VAL1				0x1000
 #define MADERA_SPD1_VAL1_MASK				0x1000
 #define MADERA_SPD1_VAL1_SHIFT				    12
-#define MADERA_SPD1_VAL1_WIDTH				     1
 #define MADERA_SPD1_RATE_MASK				0x00F0
 #define MADERA_SPD1_RATE_SHIFT				     4
-#define MADERA_SPD1_RATE_WIDTH				     4
 #define MADERA_SPD1_ENA					0x0001
 #define MADERA_SPD1_ENA_MASK				0x0001
 #define MADERA_SPD1_ENA_SHIFT				     0
-#define MADERA_SPD1_ENA_WIDTH				     1
 
 /* (0x05F5)  SLIMbus_RX_Channel_Enable */
 #define MADERA_SLIMRX8_ENA				0x0080
 #define MADERA_SLIMRX8_ENA_MASK				0x0080
 #define MADERA_SLIMRX8_ENA_SHIFT			     7
-#define MADERA_SLIMRX8_ENA_WIDTH			     1
 #define MADERA_SLIMRX7_ENA				0x0040
 #define MADERA_SLIMRX7_ENA_MASK				0x0040
 #define MADERA_SLIMRX7_ENA_SHIFT			     6
-#define MADERA_SLIMRX7_ENA_WIDTH			     1
 #define MADERA_SLIMRX6_ENA				0x0020
 #define MADERA_SLIMRX6_ENA_MASK				0x0020
 #define MADERA_SLIMRX6_ENA_SHIFT			     5
-#define MADERA_SLIMRX6_ENA_WIDTH			     1
 #define MADERA_SLIMRX5_ENA				0x0010
 #define MADERA_SLIMRX5_ENA_MASK				0x0010
 #define MADERA_SLIMRX5_ENA_SHIFT			     4
-#define MADERA_SLIMRX5_ENA_WIDTH			     1
 #define MADERA_SLIMRX4_ENA				0x0008
 #define MADERA_SLIMRX4_ENA_MASK				0x0008
 #define MADERA_SLIMRX4_ENA_SHIFT			     3
-#define MADERA_SLIMRX4_ENA_WIDTH			     1
 #define MADERA_SLIMRX3_ENA				0x0004
 #define MADERA_SLIMRX3_ENA_MASK				0x0004
 #define MADERA_SLIMRX3_ENA_SHIFT			     2
-#define MADERA_SLIMRX3_ENA_WIDTH			     1
 #define MADERA_SLIMRX2_ENA				0x0002
 #define MADERA_SLIMRX2_ENA_MASK				0x0002
 #define MADERA_SLIMRX2_ENA_SHIFT			     1
-#define MADERA_SLIMRX2_ENA_WIDTH			     1
 #define MADERA_SLIMRX1_ENA				0x0001
 #define MADERA_SLIMRX1_ENA_MASK				0x0001
 #define MADERA_SLIMRX1_ENA_SHIFT			     0
-#define MADERA_SLIMRX1_ENA_WIDTH			     1
 
 /* (0x05F6)  SLIMbus_TX_Channel_Enable */
 #define MADERA_SLIMTX8_ENA				0x0080
 #define MADERA_SLIMTX8_ENA_MASK				0x0080
 #define MADERA_SLIMTX8_ENA_SHIFT			     7
-#define MADERA_SLIMTX8_ENA_WIDTH			     1
 #define MADERA_SLIMTX7_ENA				0x0040
 #define MADERA_SLIMTX7_ENA_MASK				0x0040
 #define MADERA_SLIMTX7_ENA_SHIFT			     6
-#define MADERA_SLIMTX7_ENA_WIDTH			     1
 #define MADERA_SLIMTX6_ENA				0x0020
 #define MADERA_SLIMTX6_ENA_MASK				0x0020
 #define MADERA_SLIMTX6_ENA_SHIFT			     5
-#define MADERA_SLIMTX6_ENA_WIDTH			     1
 #define MADERA_SLIMTX5_ENA				0x0010
 #define MADERA_SLIMTX5_ENA_MASK				0x0010
 #define MADERA_SLIMTX5_ENA_SHIFT			     4
-#define MADERA_SLIMTX5_ENA_WIDTH			     1
 #define MADERA_SLIMTX4_ENA				0x0008
 #define MADERA_SLIMTX4_ENA_MASK				0x0008
 #define MADERA_SLIMTX4_ENA_SHIFT			     3
-#define MADERA_SLIMTX4_ENA_WIDTH			     1
 #define MADERA_SLIMTX3_ENA				0x0004
 #define MADERA_SLIMTX3_ENA_MASK				0x0004
 #define MADERA_SLIMTX3_ENA_SHIFT			     2
-#define MADERA_SLIMTX3_ENA_WIDTH			     1
 #define MADERA_SLIMTX2_ENA				0x0002
 #define MADERA_SLIMTX2_ENA_MASK				0x0002
 #define MADERA_SLIMTX2_ENA_SHIFT			     1
-#define MADERA_SLIMTX2_ENA_WIDTH			     1
 #define MADERA_SLIMTX1_ENA				0x0001
 #define MADERA_SLIMTX1_ENA_MASK				0x0001
 #define MADERA_SLIMTX1_ENA_SHIFT			     0
-#define MADERA_SLIMTX1_ENA_WIDTH			     1
 
 /* (0x0E10)  EQ1_1 */
 #define MADERA_EQ1_B1_GAIN_MASK				0xF800
 #define MADERA_EQ1_B1_GAIN_SHIFT			    11
-#define MADERA_EQ1_B1_GAIN_WIDTH			     5
 #define MADERA_EQ1_B2_GAIN_MASK				0x07C0
 #define MADERA_EQ1_B2_GAIN_SHIFT			     6
-#define MADERA_EQ1_B2_GAIN_WIDTH			     5
 #define MADERA_EQ1_B3_GAIN_MASK				0x003E
 #define MADERA_EQ1_B3_GAIN_SHIFT			     1
-#define MADERA_EQ1_B3_GAIN_WIDTH			     5
 #define MADERA_EQ1_ENA					0x0001
 #define MADERA_EQ1_ENA_MASK				0x0001
 #define MADERA_EQ1_ENA_SHIFT				     0
-#define MADERA_EQ1_ENA_WIDTH				     1
 
 /* (0x0E11)  EQ1_2 */
 #define MADERA_EQ1_B4_GAIN_MASK				0xF800
 #define MADERA_EQ1_B4_GAIN_SHIFT			    11
-#define MADERA_EQ1_B4_GAIN_WIDTH			     5
 #define MADERA_EQ1_B5_GAIN_MASK				0x07C0
 #define MADERA_EQ1_B5_GAIN_SHIFT			     6
-#define MADERA_EQ1_B5_GAIN_WIDTH			     5
 #define MADERA_EQ1_B1_MODE				0x0001
 #define MADERA_EQ1_B1_MODE_MASK				0x0001
 #define MADERA_EQ1_B1_MODE_SHIFT			     0
-#define MADERA_EQ1_B1_MODE_WIDTH			     1
 
 /* (0x0E26)  EQ2_1 */
 #define MADERA_EQ2_B1_GAIN_MASK				0xF800
 #define MADERA_EQ2_B1_GAIN_SHIFT			    11
-#define MADERA_EQ2_B1_GAIN_WIDTH			     5
 #define MADERA_EQ2_B2_GAIN_MASK				0x07C0
 #define MADERA_EQ2_B2_GAIN_SHIFT			     6
-#define MADERA_EQ2_B2_GAIN_WIDTH			     5
 #define MADERA_EQ2_B3_GAIN_MASK				0x003E
 #define MADERA_EQ2_B3_GAIN_SHIFT			     1
-#define MADERA_EQ2_B3_GAIN_WIDTH			     5
 #define MADERA_EQ2_ENA					0x0001
 #define MADERA_EQ2_ENA_MASK				0x0001
 #define MADERA_EQ2_ENA_SHIFT				     0
-#define MADERA_EQ2_ENA_WIDTH				     1
 
 /* (0x0E27)  EQ2_2 */
 #define MADERA_EQ2_B4_GAIN_MASK				0xF800
 #define MADERA_EQ2_B4_GAIN_SHIFT			    11
-#define MADERA_EQ2_B4_GAIN_WIDTH			     5
 #define MADERA_EQ2_B5_GAIN_MASK				0x07C0
 #define MADERA_EQ2_B5_GAIN_SHIFT			     6
-#define MADERA_EQ2_B5_GAIN_WIDTH			     5
 #define MADERA_EQ2_B1_MODE				0x0001
 #define MADERA_EQ2_B1_MODE_MASK				0x0001
 #define MADERA_EQ2_B1_MODE_SHIFT			     0
-#define MADERA_EQ2_B1_MODE_WIDTH			     1
 
 /* (0x0E3C)  EQ3_1 */
 #define MADERA_EQ3_B1_GAIN_MASK				0xF800
 #define MADERA_EQ3_B1_GAIN_SHIFT			    11
-#define MADERA_EQ3_B1_GAIN_WIDTH			     5
 #define MADERA_EQ3_B2_GAIN_MASK				0x07C0
 #define MADERA_EQ3_B2_GAIN_SHIFT			     6
-#define MADERA_EQ3_B2_GAIN_WIDTH			     5
 #define MADERA_EQ3_B3_GAIN_MASK				0x003E
 #define MADERA_EQ3_B3_GAIN_SHIFT			     1
-#define MADERA_EQ3_B3_GAIN_WIDTH			     5
 #define MADERA_EQ3_ENA					0x0001
 #define MADERA_EQ3_ENA_MASK				0x0001
 #define MADERA_EQ3_ENA_SHIFT				     0
-#define MADERA_EQ3_ENA_WIDTH				     1
 
 /* (0x0E3D)  EQ3_2 */
 #define MADERA_EQ3_B4_GAIN_MASK				0xF800
 #define MADERA_EQ3_B4_GAIN_SHIFT			    11
-#define MADERA_EQ3_B4_GAIN_WIDTH			     5
 #define MADERA_EQ3_B5_GAIN_MASK				0x07C0
 #define MADERA_EQ3_B5_GAIN_SHIFT			     6
-#define MADERA_EQ3_B5_GAIN_WIDTH			     5
 #define MADERA_EQ3_B1_MODE				0x0001
 #define MADERA_EQ3_B1_MODE_MASK				0x0001
 #define MADERA_EQ3_B1_MODE_SHIFT			     0
-#define MADERA_EQ3_B1_MODE_WIDTH			     1
 
 /* (0x0E52)  EQ4_1 */
 #define MADERA_EQ4_B1_GAIN_MASK				0xF800
 #define MADERA_EQ4_B1_GAIN_SHIFT			    11
-#define MADERA_EQ4_B1_GAIN_WIDTH			     5
 #define MADERA_EQ4_B2_GAIN_MASK				0x07C0
 #define MADERA_EQ4_B2_GAIN_SHIFT			     6
-#define MADERA_EQ4_B2_GAIN_WIDTH			     5
 #define MADERA_EQ4_B3_GAIN_MASK				0x003E
 #define MADERA_EQ4_B3_GAIN_SHIFT			     1
-#define MADERA_EQ4_B3_GAIN_WIDTH			     5
 #define MADERA_EQ4_ENA					0x0001
 #define MADERA_EQ4_ENA_MASK				0x0001
 #define MADERA_EQ4_ENA_SHIFT				     0
-#define MADERA_EQ4_ENA_WIDTH				     1
 
 /* (0x0E53)  EQ4_2 */
 #define MADERA_EQ4_B4_GAIN_MASK				0xF800
 #define MADERA_EQ4_B4_GAIN_SHIFT			    11
-#define MADERA_EQ4_B4_GAIN_WIDTH			     5
 #define MADERA_EQ4_B5_GAIN_MASK				0x07C0
 #define MADERA_EQ4_B5_GAIN_SHIFT			     6
-#define MADERA_EQ4_B5_GAIN_WIDTH			     5
 #define MADERA_EQ4_B1_MODE				0x0001
 #define MADERA_EQ4_B1_MODE_MASK				0x0001
 #define MADERA_EQ4_B1_MODE_SHIFT			     0
-#define MADERA_EQ4_B1_MODE_WIDTH			     1
 
 /* (0x0E80)  DRC1_ctrl1 */
 #define MADERA_DRC1L_ENA				0x0002
 #define MADERA_DRC1L_ENA_MASK				0x0002
 #define MADERA_DRC1L_ENA_SHIFT				     1
-#define MADERA_DRC1L_ENA_WIDTH				     1
 #define MADERA_DRC1R_ENA				0x0001
 #define MADERA_DRC1R_ENA_MASK				0x0001
 #define MADERA_DRC1R_ENA_SHIFT				     0
-#define MADERA_DRC1R_ENA_WIDTH				     1
 
 /* (0x0E88)  DRC2_ctrl1 */
 #define MADERA_DRC2L_ENA				0x0002
 #define MADERA_DRC2L_ENA_MASK				0x0002
 #define MADERA_DRC2L_ENA_SHIFT				     1
-#define MADERA_DRC2L_ENA_WIDTH				     1
 #define MADERA_DRC2R_ENA				0x0001
 #define MADERA_DRC2R_ENA_MASK				0x0001
 #define MADERA_DRC2R_ENA_SHIFT				     0
-#define MADERA_DRC2R_ENA_WIDTH				     1
 
 /* (0x0EC0)  HPLPF1_1 */
 #define MADERA_LHPF1_MODE				0x0002
 #define MADERA_LHPF1_MODE_MASK				0x0002
 #define MADERA_LHPF1_MODE_SHIFT				     1
-#define MADERA_LHPF1_MODE_WIDTH				     1
 #define MADERA_LHPF1_ENA				0x0001
 #define MADERA_LHPF1_ENA_MASK				0x0001
 #define MADERA_LHPF1_ENA_SHIFT				     0
-#define MADERA_LHPF1_ENA_WIDTH				     1
 
 /* (0x0EC1)  HPLPF1_2 */
 #define MADERA_LHPF1_COEFF_MASK				0xFFFF
 #define MADERA_LHPF1_COEFF_SHIFT			     0
-#define MADERA_LHPF1_COEFF_WIDTH			    16
 
 /* (0x0EC4)  HPLPF2_1 */
 #define MADERA_LHPF2_MODE				0x0002
 #define MADERA_LHPF2_MODE_MASK				0x0002
 #define MADERA_LHPF2_MODE_SHIFT				     1
-#define MADERA_LHPF2_MODE_WIDTH				     1
 #define MADERA_LHPF2_ENA				0x0001
 #define MADERA_LHPF2_ENA_MASK				0x0001
 #define MADERA_LHPF2_ENA_SHIFT				     0
-#define MADERA_LHPF2_ENA_WIDTH				     1
 
 /* (0x0EC5)  HPLPF2_2 */
 #define MADERA_LHPF2_COEFF_MASK				0xFFFF
 #define MADERA_LHPF2_COEFF_SHIFT			     0
-#define MADERA_LHPF2_COEFF_WIDTH			    16
 
 /* (0x0EC8)  HPLPF3_1 */
 #define MADERA_LHPF3_MODE				0x0002
 #define MADERA_LHPF3_MODE_MASK				0x0002
 #define MADERA_LHPF3_MODE_SHIFT				     1
-#define MADERA_LHPF3_MODE_WIDTH				     1
 #define MADERA_LHPF3_ENA				0x0001
 #define MADERA_LHPF3_ENA_MASK				0x0001
 #define MADERA_LHPF3_ENA_SHIFT				     0
-#define MADERA_LHPF3_ENA_WIDTH				     1
 
 /* (0x0EC9)  HPLPF3_2 */
 #define MADERA_LHPF3_COEFF_MASK				0xFFFF
 #define MADERA_LHPF3_COEFF_SHIFT			     0
-#define MADERA_LHPF3_COEFF_WIDTH			    16
 
 /* (0x0ECC)  HPLPF4_1 */
 #define MADERA_LHPF4_MODE				0x0002
 #define MADERA_LHPF4_MODE_MASK				0x0002
 #define MADERA_LHPF4_MODE_SHIFT				     1
-#define MADERA_LHPF4_MODE_WIDTH				     1
 #define MADERA_LHPF4_ENA				0x0001
 #define MADERA_LHPF4_ENA_MASK				0x0001
 #define MADERA_LHPF4_ENA_SHIFT				     0
-#define MADERA_LHPF4_ENA_WIDTH				     1
 
 /* (0x0ECD)  HPLPF4_2 */
 #define MADERA_LHPF4_COEFF_MASK				0xFFFF
 #define MADERA_LHPF4_COEFF_SHIFT			     0
-#define MADERA_LHPF4_COEFF_WIDTH			    16
 
 /* (0x0ED0)  ASRC2_ENABLE */
 #define MADERA_ASRC2_IN2L_ENA				0x0008
 #define MADERA_ASRC2_IN2L_ENA_MASK			0x0008
 #define MADERA_ASRC2_IN2L_ENA_SHIFT			     3
-#define MADERA_ASRC2_IN2L_ENA_WIDTH			     1
 #define MADERA_ASRC2_IN2R_ENA				0x0004
 #define MADERA_ASRC2_IN2R_ENA_MASK			0x0004
 #define MADERA_ASRC2_IN2R_ENA_SHIFT			     2
-#define MADERA_ASRC2_IN2R_ENA_WIDTH			     1
 #define MADERA_ASRC2_IN1L_ENA				0x0002
 #define MADERA_ASRC2_IN1L_ENA_MASK			0x0002
 #define MADERA_ASRC2_IN1L_ENA_SHIFT			     1
-#define MADERA_ASRC2_IN1L_ENA_WIDTH			     1
 #define MADERA_ASRC2_IN1R_ENA				0x0001
 #define MADERA_ASRC2_IN1R_ENA_MASK			0x0001
 #define MADERA_ASRC2_IN1R_ENA_SHIFT			     0
-#define MADERA_ASRC2_IN1R_ENA_WIDTH			     1
 
 /* (0x0ED2)  ASRC2_RATE1 */
 #define MADERA_ASRC2_RATE1_MASK				0xF800
 #define MADERA_ASRC2_RATE1_SHIFT			    11
-#define MADERA_ASRC2_RATE1_WIDTH			     5
 
 /* (0x0ED3)  ASRC2_RATE2 */
 #define MADERA_ASRC2_RATE2_MASK				0xF800
 #define MADERA_ASRC2_RATE2_SHIFT			    11
-#define MADERA_ASRC2_RATE2_WIDTH			     5
 
 /* (0x0EE0)  ASRC1_ENABLE */
 #define MADERA_ASRC1_IN2L_ENA				0x0008
 #define MADERA_ASRC1_IN2L_ENA_MASK			0x0008
 #define MADERA_ASRC1_IN2L_ENA_SHIFT			     3
-#define MADERA_ASRC1_IN2L_ENA_WIDTH			     1
 #define MADERA_ASRC1_IN2R_ENA				0x0004
 #define MADERA_ASRC1_IN2R_ENA_MASK			0x0004
 #define MADERA_ASRC1_IN2R_ENA_SHIFT			     2
-#define MADERA_ASRC1_IN2R_ENA_WIDTH			     1
 #define MADERA_ASRC1_IN1L_ENA				0x0002
 #define MADERA_ASRC1_IN1L_ENA_MASK			0x0002
 #define MADERA_ASRC1_IN1L_ENA_SHIFT			     1
-#define MADERA_ASRC1_IN1L_ENA_WIDTH			     1
 #define MADERA_ASRC1_IN1R_ENA				0x0001
 #define MADERA_ASRC1_IN1R_ENA_MASK			0x0001
 #define MADERA_ASRC1_IN1R_ENA_SHIFT			     0
-#define MADERA_ASRC1_IN1R_ENA_WIDTH			     1
 
 /* (0x0EE2)  ASRC1_RATE1 */
 #define MADERA_ASRC1_RATE1_MASK				0xF800
 #define MADERA_ASRC1_RATE1_SHIFT			    11
-#define MADERA_ASRC1_RATE1_WIDTH			     5
 
 /* (0x0EE3)  ASRC1_RATE2 */
 #define MADERA_ASRC1_RATE2_MASK				0xF800
 #define MADERA_ASRC1_RATE2_SHIFT			    11
-#define MADERA_ASRC1_RATE2_WIDTH			     5
 
 /* (0x0EF0) - ISRC1 CTRL 1 */
 #define MADERA_ISRC1_FSH_MASK				0xF800
 #define MADERA_ISRC1_FSH_SHIFT				    11
-#define MADERA_ISRC1_FSH_WIDTH				     5
 #define MADERA_ISRC1_CLK_SEL_MASK			0x0700
 #define MADERA_ISRC1_CLK_SEL_SHIFT			     8
-#define MADERA_ISRC1_CLK_SEL_WIDTH			     3
 
 /* (0x0EF1)  ISRC1_CTRL_2 */
 #define MADERA_ISRC1_FSL_MASK				0xF800
 #define MADERA_ISRC1_FSL_SHIFT				    11
-#define MADERA_ISRC1_FSL_WIDTH				     5
 
 /* (0x0EF2)  ISRC1_CTRL_3 */
 #define MADERA_ISRC1_INT1_ENA				0x8000
 #define MADERA_ISRC1_INT1_ENA_MASK			0x8000
 #define MADERA_ISRC1_INT1_ENA_SHIFT			    15
-#define MADERA_ISRC1_INT1_ENA_WIDTH			     1
 #define MADERA_ISRC1_INT2_ENA				0x4000
 #define MADERA_ISRC1_INT2_ENA_MASK			0x4000
 #define MADERA_ISRC1_INT2_ENA_SHIFT			    14
-#define MADERA_ISRC1_INT2_ENA_WIDTH			     1
 #define MADERA_ISRC1_INT3_ENA				0x2000
 #define MADERA_ISRC1_INT3_ENA_MASK			0x2000
 #define MADERA_ISRC1_INT3_ENA_SHIFT			    13
-#define MADERA_ISRC1_INT3_ENA_WIDTH			     1
 #define MADERA_ISRC1_INT4_ENA				0x1000
 #define MADERA_ISRC1_INT4_ENA_MASK			0x1000
 #define MADERA_ISRC1_INT4_ENA_SHIFT			    12
-#define MADERA_ISRC1_INT4_ENA_WIDTH			     1
 #define MADERA_ISRC1_DEC1_ENA				0x0200
 #define MADERA_ISRC1_DEC1_ENA_MASK			0x0200
 #define MADERA_ISRC1_DEC1_ENA_SHIFT			     9
-#define MADERA_ISRC1_DEC1_ENA_WIDTH			     1
 #define MADERA_ISRC1_DEC2_ENA				0x0100
 #define MADERA_ISRC1_DEC2_ENA_MASK			0x0100
 #define MADERA_ISRC1_DEC2_ENA_SHIFT			     8
-#define MADERA_ISRC1_DEC2_ENA_WIDTH			     1
 #define MADERA_ISRC1_DEC3_ENA				0x0080
 #define MADERA_ISRC1_DEC3_ENA_MASK			0x0080
 #define MADERA_ISRC1_DEC3_ENA_SHIFT			     7
-#define MADERA_ISRC1_DEC3_ENA_WIDTH			     1
 #define MADERA_ISRC1_DEC4_ENA				0x0040
 #define MADERA_ISRC1_DEC4_ENA_MASK			0x0040
 #define MADERA_ISRC1_DEC4_ENA_SHIFT			     6
-#define MADERA_ISRC1_DEC4_ENA_WIDTH			     1
 #define MADERA_ISRC1_NOTCH_ENA				0x0001
 #define MADERA_ISRC1_NOTCH_ENA_MASK			0x0001
 #define MADERA_ISRC1_NOTCH_ENA_SHIFT			     0
-#define MADERA_ISRC1_NOTCH_ENA_WIDTH			     1
 
 /* (0x0EF3)  ISRC2_CTRL_1 */
 #define MADERA_ISRC2_FSH_MASK				0xF800
 #define MADERA_ISRC2_FSH_SHIFT				    11
-#define MADERA_ISRC2_FSH_WIDTH				     5
 #define MADERA_ISRC2_CLK_SEL_MASK			0x0700
 #define MADERA_ISRC2_CLK_SEL_SHIFT			     8
-#define MADERA_ISRC2_CLK_SEL_WIDTH			     3
 
 /* (0x0EF4)  ISRC2_CTRL_2 */
 #define MADERA_ISRC2_FSL_MASK				0xF800
 #define MADERA_ISRC2_FSL_SHIFT				    11
-#define MADERA_ISRC2_FSL_WIDTH				     5
 
 /* (0x0EF5)  ISRC2_CTRL_3 */
 #define MADERA_ISRC2_INT1_ENA				0x8000
 #define MADERA_ISRC2_INT1_ENA_MASK			0x8000
 #define MADERA_ISRC2_INT1_ENA_SHIFT			    15
-#define MADERA_ISRC2_INT1_ENA_WIDTH			     1
 #define MADERA_ISRC2_INT2_ENA				0x4000
 #define MADERA_ISRC2_INT2_ENA_MASK			0x4000
 #define MADERA_ISRC2_INT2_ENA_SHIFT			    14
-#define MADERA_ISRC2_INT2_ENA_WIDTH			     1
 #define MADERA_ISRC2_INT3_ENA				0x2000
 #define MADERA_ISRC2_INT3_ENA_MASK			0x2000
 #define MADERA_ISRC2_INT3_ENA_SHIFT			    13
-#define MADERA_ISRC2_INT3_ENA_WIDTH			     1
 #define MADERA_ISRC2_INT4_ENA				0x1000
 #define MADERA_ISRC2_INT4_ENA_MASK			0x1000
 #define MADERA_ISRC2_INT4_ENA_SHIFT			    12
-#define MADERA_ISRC2_INT4_ENA_WIDTH			     1
 #define MADERA_ISRC2_DEC1_ENA				0x0200
 #define MADERA_ISRC2_DEC1_ENA_MASK			0x0200
 #define MADERA_ISRC2_DEC1_ENA_SHIFT			     9
-#define MADERA_ISRC2_DEC1_ENA_WIDTH			     1
 #define MADERA_ISRC2_DEC2_ENA				0x0100
 #define MADERA_ISRC2_DEC2_ENA_MASK			0x0100
 #define MADERA_ISRC2_DEC2_ENA_SHIFT			     8
-#define MADERA_ISRC2_DEC2_ENA_WIDTH			     1
 #define MADERA_ISRC2_DEC3_ENA				0x0080
 #define MADERA_ISRC2_DEC3_ENA_MASK			0x0080
 #define MADERA_ISRC2_DEC3_ENA_SHIFT			     7
-#define MADERA_ISRC2_DEC3_ENA_WIDTH			     1
 #define MADERA_ISRC2_DEC4_ENA				0x0040
 #define MADERA_ISRC2_DEC4_ENA_MASK			0x0040
 #define MADERA_ISRC2_DEC4_ENA_SHIFT			     6
-#define MADERA_ISRC2_DEC4_ENA_WIDTH			     1
 #define MADERA_ISRC2_NOTCH_ENA				0x0001
 #define MADERA_ISRC2_NOTCH_ENA_MASK			0x0001
 #define MADERA_ISRC2_NOTCH_ENA_SHIFT			     0
-#define MADERA_ISRC2_NOTCH_ENA_WIDTH			     1
 
 /* (0x0EF6)  ISRC3_CTRL_1 */
 #define MADERA_ISRC3_FSH_MASK				0xF800
 #define MADERA_ISRC3_FSH_SHIFT				    11
-#define MADERA_ISRC3_FSH_WIDTH				     5
 #define MADERA_ISRC3_CLK_SEL_MASK			0x0700
 #define MADERA_ISRC3_CLK_SEL_SHIFT			     8
-#define MADERA_ISRC3_CLK_SEL_WIDTH			     3
 
 /* (0x0EF7)  ISRC3_CTRL_2 */
 #define MADERA_ISRC3_FSL_MASK				0xF800
 #define MADERA_ISRC3_FSL_SHIFT				    11
-#define MADERA_ISRC3_FSL_WIDTH				     5
 
 /* (0x0EF8)  ISRC3_CTRL_3 */
 #define MADERA_ISRC3_INT1_ENA				0x8000
 #define MADERA_ISRC3_INT1_ENA_MASK			0x8000
 #define MADERA_ISRC3_INT1_ENA_SHIFT			    15
-#define MADERA_ISRC3_INT1_ENA_WIDTH			     1
 #define MADERA_ISRC3_INT2_ENA				0x4000
 #define MADERA_ISRC3_INT2_ENA_MASK			0x4000
 #define MADERA_ISRC3_INT2_ENA_SHIFT			    14
-#define MADERA_ISRC3_INT2_ENA_WIDTH			     1
 #define MADERA_ISRC3_INT3_ENA				0x2000
 #define MADERA_ISRC3_INT3_ENA_MASK			0x2000
 #define MADERA_ISRC3_INT3_ENA_SHIFT			    13
-#define MADERA_ISRC3_INT3_ENA_WIDTH			     1
 #define MADERA_ISRC3_INT4_ENA				0x1000
 #define MADERA_ISRC3_INT4_ENA_MASK			0x1000
 #define MADERA_ISRC3_INT4_ENA_SHIFT			    12
-#define MADERA_ISRC3_INT4_ENA_WIDTH			     1
 #define MADERA_ISRC3_DEC1_ENA				0x0200
 #define MADERA_ISRC3_DEC1_ENA_MASK			0x0200
 #define MADERA_ISRC3_DEC1_ENA_SHIFT			     9
-#define MADERA_ISRC3_DEC1_ENA_WIDTH			     1
 #define MADERA_ISRC3_DEC2_ENA				0x0100
 #define MADERA_ISRC3_DEC2_ENA_MASK			0x0100
 #define MADERA_ISRC3_DEC2_ENA_SHIFT			     8
-#define MADERA_ISRC3_DEC2_ENA_WIDTH			     1
 #define MADERA_ISRC3_DEC3_ENA				0x0080
 #define MADERA_ISRC3_DEC3_ENA_MASK			0x0080
 #define MADERA_ISRC3_DEC3_ENA_SHIFT			     7
-#define MADERA_ISRC3_DEC3_ENA_WIDTH			     1
 #define MADERA_ISRC3_DEC4_ENA				0x0040
 #define MADERA_ISRC3_DEC4_ENA_MASK			0x0040
 #define MADERA_ISRC3_DEC4_ENA_SHIFT			     6
-#define MADERA_ISRC3_DEC4_ENA_WIDTH			     1
 #define MADERA_ISRC3_NOTCH_ENA				0x0001
 #define MADERA_ISRC3_NOTCH_ENA_MASK			0x0001
 #define MADERA_ISRC3_NOTCH_ENA_SHIFT			     0
-#define MADERA_ISRC3_NOTCH_ENA_WIDTH			     1
 
 /* (0x0EF9)  ISRC4_CTRL_1 */
 #define MADERA_ISRC4_FSH_MASK				0xF800
 #define MADERA_ISRC4_FSH_SHIFT				    11
-#define MADERA_ISRC4_FSH_WIDTH				     5
 #define MADERA_ISRC4_CLK_SEL_MASK			0x0700
 #define MADERA_ISRC4_CLK_SEL_SHIFT			     8
-#define MADERA_ISRC4_CLK_SEL_WIDTH			     3
 
 /* (0x0EFA)  ISRC4_CTRL_2 */
 #define MADERA_ISRC4_FSL_MASK				0xF800
 #define MADERA_ISRC4_FSL_SHIFT				    11
-#define MADERA_ISRC4_FSL_WIDTH				     5
 
 /* (0x0EFB)  ISRC4_CTRL_3 */
 #define MADERA_ISRC4_INT1_ENA				0x8000
 #define MADERA_ISRC4_INT1_ENA_MASK			0x8000
 #define MADERA_ISRC4_INT1_ENA_SHIFT			    15
-#define MADERA_ISRC4_INT1_ENA_WIDTH			     1
 #define MADERA_ISRC4_INT2_ENA				0x4000
 #define MADERA_ISRC4_INT2_ENA_MASK			0x4000
 #define MADERA_ISRC4_INT2_ENA_SHIFT			    14
-#define MADERA_ISRC4_INT2_ENA_WIDTH			     1
 #define MADERA_ISRC4_INT3_ENA				0x2000
 #define MADERA_ISRC4_INT3_ENA_MASK			0x2000
 #define MADERA_ISRC4_INT3_ENA_SHIFT			    13
-#define MADERA_ISRC4_INT3_ENA_WIDTH			     1
 #define MADERA_ISRC4_INT4_ENA				0x1000
 #define MADERA_ISRC4_INT4_ENA_MASK			0x1000
 #define MADERA_ISRC4_INT4_ENA_SHIFT			    12
-#define MADERA_ISRC4_INT4_ENA_WIDTH			     1
 #define MADERA_ISRC4_DEC1_ENA				0x0200
 #define MADERA_ISRC4_DEC1_ENA_MASK			0x0200
 #define MADERA_ISRC4_DEC1_ENA_SHIFT			     9
-#define MADERA_ISRC4_DEC1_ENA_WIDTH			     1
 #define MADERA_ISRC4_DEC2_ENA				0x0100
 #define MADERA_ISRC4_DEC2_ENA_MASK			0x0100
 #define MADERA_ISRC4_DEC2_ENA_SHIFT			     8
-#define MADERA_ISRC4_DEC2_ENA_WIDTH			     1
 #define MADERA_ISRC4_DEC3_ENA				0x0080
 #define MADERA_ISRC4_DEC3_ENA_MASK			0x0080
 #define MADERA_ISRC4_DEC3_ENA_SHIFT			     7
-#define MADERA_ISRC4_DEC3_ENA_WIDTH			     1
 #define MADERA_ISRC4_DEC4_ENA				0x0040
 #define MADERA_ISRC4_DEC4_ENA_MASK			0x0040
 #define MADERA_ISRC4_DEC4_ENA_SHIFT			     6
-#define MADERA_ISRC4_DEC4_ENA_WIDTH			     1
 #define MADERA_ISRC4_NOTCH_ENA				0x0001
 #define MADERA_ISRC4_NOTCH_ENA_MASK			0x0001
 #define MADERA_ISRC4_NOTCH_ENA_SHIFT			     0
-#define MADERA_ISRC4_NOTCH_ENA_WIDTH			     1
 
 /* (0x0F00)  Clock_Control */
 #define MADERA_EXT_NG_SEL_CLR				0x0080
 #define MADERA_EXT_NG_SEL_CLR_MASK			0x0080
 #define MADERA_EXT_NG_SEL_CLR_SHIFT			     7
-#define MADERA_EXT_NG_SEL_CLR_WIDTH			     1
 #define MADERA_EXT_NG_SEL_SET				0x0040
 #define MADERA_EXT_NG_SEL_SET_MASK			0x0040
 #define MADERA_EXT_NG_SEL_SET_SHIFT			     6
-#define MADERA_EXT_NG_SEL_SET_WIDTH			     1
 #define MADERA_CLK_R_ENA_CLR				0x0020
 #define MADERA_CLK_R_ENA_CLR_MASK			0x0020
 #define MADERA_CLK_R_ENA_CLR_SHIFT			     5
-#define MADERA_CLK_R_ENA_CLR_WIDTH			     1
 #define MADERA_CLK_R_ENA_SET				0x0010
 #define MADERA_CLK_R_ENA_SET_MASK			0x0010
 #define MADERA_CLK_R_ENA_SET_SHIFT			     4
-#define MADERA_CLK_R_ENA_SET_WIDTH			     1
 #define MADERA_CLK_NG_ENA_CLR				0x0008
 #define MADERA_CLK_NG_ENA_CLR_MASK			0x0008
 #define MADERA_CLK_NG_ENA_CLR_SHIFT			     3
-#define MADERA_CLK_NG_ENA_CLR_WIDTH			     1
 #define MADERA_CLK_NG_ENA_SET				0x0004
 #define MADERA_CLK_NG_ENA_SET_MASK			0x0004
 #define MADERA_CLK_NG_ENA_SET_SHIFT			     2
-#define MADERA_CLK_NG_ENA_SET_WIDTH			     1
 #define MADERA_CLK_L_ENA_CLR				0x0002
 #define MADERA_CLK_L_ENA_CLR_MASK			0x0002
 #define MADERA_CLK_L_ENA_CLR_SHIFT			     1
-#define MADERA_CLK_L_ENA_CLR_WIDTH			     1
 #define MADERA_CLK_L_ENA_SET				0x0001
 #define MADERA_CLK_L_ENA_SET_MASK			0x0001
 #define MADERA_CLK_L_ENA_SET_SHIFT			     0
-#define MADERA_CLK_L_ENA_SET_WIDTH			     1
 
 /* (0x0F01)  ANC_SRC */
 #define MADERA_IN_RXANCR_SEL_MASK			0x0070
 #define MADERA_IN_RXANCR_SEL_SHIFT			     4
-#define MADERA_IN_RXANCR_SEL_WIDTH			     3
 #define MADERA_IN_RXANCL_SEL_MASK			0x0007
 #define MADERA_IN_RXANCL_SEL_SHIFT			     0
-#define MADERA_IN_RXANCL_SEL_WIDTH			     3
 
 /* (0x0F17)  FCL_ADC_reformatter_control */
 #define MADERA_FCL_MIC_MODE_SEL				0x000C
 #define MADERA_FCL_MIC_MODE_SEL_SHIFT			     2
-#define MADERA_FCL_MIC_MODE_SEL_WIDTH			     2
 
 /* (0x0F73)  FCR_ADC_reformatter_control */
 #define MADERA_FCR_MIC_MODE_SEL				0x000C
 #define MADERA_FCR_MIC_MODE_SEL_SHIFT			     2
-#define MADERA_FCR_MIC_MODE_SEL_WIDTH			     2
 
 /* (0x10C0)  AUXPDM1_CTRL_0 */
 #define MADERA_AUXPDM1_SRC_MASK				0x0F00
 #define MADERA_AUXPDM1_SRC_SHIFT			     8
-#define MADERA_AUXPDM1_SRC_WIDTH			     4
 #define MADERA_AUXPDM1_TXEDGE_MASK			0x0010
 #define MADERA_AUXPDM1_TXEDGE_SHIFT			     4
-#define MADERA_AUXPDM1_TXEDGE_WIDTH			     1
 #define MADERA_AUXPDM1_MSTR_MASK			0x0008
 #define MADERA_AUXPDM1_MSTR_SHIFT			     3
-#define MADERA_AUXPDM1_MSTR_WIDTH			     1
 #define MADERA_AUXPDM1_ENABLE_MASK			0x0001
 #define MADERA_AUXPDM1_ENABLE_SHIFT			     0
-#define MADERA_AUXPDM1_ENABLE_WIDTH			     1
 
 /* (0x10C1)  AUXPDM1_CTRL_1 */
 #define MADERA_AUXPDM1_CLK_FREQ_MASK			0xC000
 #define MADERA_AUXPDM1_CLK_FREQ_SHIFT			    14
-#define MADERA_AUXPDM1_CLK_FREQ_WIDTH			     2
 
 /* (0x1480)  DFC1_CTRL_W0 */
 #define MADERA_DFC1_RATE_MASK				0x007C
 #define MADERA_DFC1_RATE_SHIFT				     2
-#define MADERA_DFC1_RATE_WIDTH				     5
 #define MADERA_DFC1_DITH_ENA				0x0002
 #define MADERA_DFC1_DITH_ENA_MASK			0x0002
 #define MADERA_DFC1_DITH_ENA_SHIFT			     1
-#define MADERA_DFC1_DITH_ENA_WIDTH			     1
 #define MADERA_DFC1_ENA					0x0001
 #define MADERA_DFC1_ENA_MASK				0x0001
 #define MADERA_DFC1_ENA_SHIFT				     0
-#define MADERA_DFC1_ENA_WIDTH				     1
 
 /* (0x1482)  DFC1_RX_W0 */
 #define MADERA_DFC1_RX_DATA_WIDTH_MASK			0x1F00
 #define MADERA_DFC1_RX_DATA_WIDTH_SHIFT			     8
-#define MADERA_DFC1_RX_DATA_WIDTH_WIDTH			     5
 
 #define MADERA_DFC1_RX_DATA_TYPE_MASK			0x0007
 #define MADERA_DFC1_RX_DATA_TYPE_SHIFT			     0
-#define MADERA_DFC1_RX_DATA_TYPE_WIDTH			     3
 
 /* (0x1484)  DFC1_TX_W0 */
 #define MADERA_DFC1_TX_DATA_WIDTH_MASK			0x1F00
 #define MADERA_DFC1_TX_DATA_WIDTH_SHIFT			     8
-#define MADERA_DFC1_TX_DATA_WIDTH_WIDTH			     5
 
 #define MADERA_DFC1_TX_DATA_TYPE_MASK			0x0007
 #define MADERA_DFC1_TX_DATA_TYPE_SHIFT			     0
-#define MADERA_DFC1_TX_DATA_TYPE_WIDTH			     3
 
 /* (0x1600)  ADSP2_IRQ0 */
 #define MADERA_DSP_IRQ2					0x0002
@@ -3636,449 +3103,347 @@
 #define MADERA_GP1_LVL					0x8000
 #define MADERA_GP1_LVL_MASK				0x8000
 #define MADERA_GP1_LVL_SHIFT				    15
-#define MADERA_GP1_LVL_WIDTH				     1
 #define MADERA_GP1_OP_CFG				0x4000
 #define MADERA_GP1_OP_CFG_MASK				0x4000
 #define MADERA_GP1_OP_CFG_SHIFT				    14
-#define MADERA_GP1_OP_CFG_WIDTH				     1
 #define MADERA_GP1_DB					0x2000
 #define MADERA_GP1_DB_MASK				0x2000
 #define MADERA_GP1_DB_SHIFT				    13
-#define MADERA_GP1_DB_WIDTH				     1
 #define MADERA_GP1_POL					0x1000
 #define MADERA_GP1_POL_MASK				0x1000
 #define MADERA_GP1_POL_SHIFT				    12
-#define MADERA_GP1_POL_WIDTH				     1
 #define MADERA_GP1_IP_CFG				0x0800
 #define MADERA_GP1_IP_CFG_MASK				0x0800
 #define MADERA_GP1_IP_CFG_SHIFT				    11
-#define MADERA_GP1_IP_CFG_WIDTH				     1
 #define MADERA_GP1_FN_MASK				0x03FF
 #define MADERA_GP1_FN_SHIFT				     0
-#define MADERA_GP1_FN_WIDTH				    10
 
 /* (0x1701)  GPIO1_CTRL_2 */
 #define MADERA_GP1_DIR					0x8000
 #define MADERA_GP1_DIR_MASK				0x8000
 #define MADERA_GP1_DIR_SHIFT				    15
-#define MADERA_GP1_DIR_WIDTH				     1
 #define MADERA_GP1_PU					0x4000
 #define MADERA_GP1_PU_MASK				0x4000
 #define MADERA_GP1_PU_SHIFT				    14
-#define MADERA_GP1_PU_WIDTH				     1
 #define MADERA_GP1_PD					0x2000
 #define MADERA_GP1_PD_MASK				0x2000
 #define MADERA_GP1_PD_SHIFT				    13
-#define MADERA_GP1_PD_WIDTH				     1
 #define MADERA_GP1_DRV_STR_MASK				0x1800
 #define MADERA_GP1_DRV_STR_SHIFT			    11
-#define MADERA_GP1_DRV_STR_WIDTH			     2
 
 /* (0x1800)  IRQ1_Status_1 */
 #define MADERA_CTRLIF_ERR_EINT1				0x1000
 #define MADERA_CTRLIF_ERR_EINT1_MASK			0x1000
 #define MADERA_CTRLIF_ERR_EINT1_SHIFT			    12
-#define MADERA_CTRLIF_ERR_EINT1_WIDTH			     1
 #define MADERA_SYSCLK_FAIL_EINT1			0x0200
 #define MADERA_SYSCLK_FAIL_EINT1_MASK			0x0200
 #define MADERA_SYSCLK_FAIL_EINT1_SHIFT			     9
-#define MADERA_SYSCLK_FAIL_EINT1_WIDTH			     1
 #define MADERA_CLOCK_DETECT_EINT1			0x0100
 #define MADERA_CLOCK_DETECT_EINT1_MASK			0x0100
 #define MADERA_CLOCK_DETECT_EINT1_SHIFT			     8
-#define MADERA_CLOCK_DETECT_EINT1_WIDTH			     1
 #define MADERA_BOOT_DONE_EINT1				0x0080
 #define MADERA_BOOT_DONE_EINT1_MASK			0x0080
 #define MADERA_BOOT_DONE_EINT1_SHIFT			     7
-#define MADERA_BOOT_DONE_EINT1_WIDTH			     1
 
 /* (0x1801)  IRQ1_Status_2 */
 #define MADERA_FLLAO_LOCK_EINT1				0x0800
 #define MADERA_FLLAO_LOCK_EINT1_MASK			0x0800
 #define MADERA_FLLAO_LOCK_EINT1_SHIFT			    11
-#define MADERA_FLLAO_LOCK_EINT1_WIDTH			     1
 #define MADERA_FLL3_LOCK_EINT1				0x0400
 #define MADERA_FLL3_LOCK_EINT1_MASK			0x0400
 #define MADERA_FLL3_LOCK_EINT1_SHIFT			    10
-#define MADERA_FLL3_LOCK_EINT1_WIDTH			     1
 #define MADERA_FLL2_LOCK_EINT1				0x0200
 #define MADERA_FLL2_LOCK_EINT1_MASK			0x0200
 #define MADERA_FLL2_LOCK_EINT1_SHIFT			     9
-#define MADERA_FLL2_LOCK_EINT1_WIDTH			     1
 #define MADERA_FLL1_LOCK_EINT1				0x0100
 #define MADERA_FLL1_LOCK_EINT1_MASK			0x0100
 #define MADERA_FLL1_LOCK_EINT1_SHIFT			     8
-#define MADERA_FLL1_LOCK_EINT1_WIDTH			     1
 
 /* (0x1805)  IRQ1_Status_6 */
 #define MADERA_MICDET2_EINT1				0x0200
 #define MADERA_MICDET2_EINT1_MASK			0x0200
 #define MADERA_MICDET2_EINT1_SHIFT			     9
-#define MADERA_MICDET2_EINT1_WIDTH			     1
 #define MADERA_MICDET1_EINT1				0x0100
 #define MADERA_MICDET1_EINT1_MASK			0x0100
 #define MADERA_MICDET1_EINT1_SHIFT			     8
-#define MADERA_MICDET1_EINT1_WIDTH			     1
 #define MADERA_HPDET_EINT1				0x0001
 #define MADERA_HPDET_EINT1_MASK				0x0001
 #define MADERA_HPDET_EINT1_SHIFT			     0
-#define MADERA_HPDET_EINT1_WIDTH			     1
 
 /* (0x1806)  IRQ1_Status_7 */
 #define MADERA_MICD_CLAMP_FALL_EINT1			0x0020
 #define MADERA_MICD_CLAMP_FALL_EINT1_MASK		0x0020
 #define MADERA_MICD_CLAMP_FALL_EINT1_SHIFT		     5
-#define MADERA_MICD_CLAMP_FALL_EINT1_WIDTH		     1
 #define MADERA_MICD_CLAMP_RISE_EINT1			0x0010
 #define MADERA_MICD_CLAMP_RISE_EINT1_MASK		0x0010
 #define MADERA_MICD_CLAMP_RISE_EINT1_SHIFT		     4
-#define MADERA_MICD_CLAMP_RISE_EINT1_WIDTH		     1
 #define MADERA_JD2_FALL_EINT1				0x0008
 #define MADERA_JD2_FALL_EINT1_MASK			0x0008
 #define MADERA_JD2_FALL_EINT1_SHIFT			     3
-#define MADERA_JD2_FALL_EINT1_WIDTH			     1
 #define MADERA_JD2_RISE_EINT1				0x0004
 #define MADERA_JD2_RISE_EINT1_MASK			0x0004
 #define MADERA_JD2_RISE_EINT1_SHIFT			     2
-#define MADERA_JD2_RISE_EINT1_WIDTH			     1
 #define MADERA_JD1_FALL_EINT1				0x0002
 #define MADERA_JD1_FALL_EINT1_MASK			0x0002
 #define MADERA_JD1_FALL_EINT1_SHIFT			     1
-#define MADERA_JD1_FALL_EINT1_WIDTH			     1
 #define MADERA_JD1_RISE_EINT1				0x0001
 #define MADERA_JD1_RISE_EINT1_MASK			0x0001
 #define MADERA_JD1_RISE_EINT1_SHIFT			     0
-#define MADERA_JD1_RISE_EINT1_WIDTH			     1
 
 /* (0x1808)  IRQ1_Status_9 */
 #define MADERA_ASRC2_IN2_LOCK_EINT1			0x0800
 #define MADERA_ASRC2_IN2_LOCK_EINT1_MASK		0x0800
 #define MADERA_ASRC2_IN2_LOCK_EINT1_SHIFT		    11
-#define MADERA_ASRC2_IN2_LOCK_EINT1_WIDTH		     1
 #define MADERA_ASRC2_IN1_LOCK_EINT1			0x0400
 #define MADERA_ASRC2_IN1_LOCK_EINT1_MASK		0x0400
 #define MADERA_ASRC2_IN1_LOCK_EINT1_SHIFT		    10
-#define MADERA_ASRC2_IN1_LOCK_EINT1_WIDTH		     1
 #define MADERA_ASRC1_IN2_LOCK_EINT1			0x0200
 #define MADERA_ASRC1_IN2_LOCK_EINT1_MASK		0x0200
 #define MADERA_ASRC1_IN2_LOCK_EINT1_SHIFT		     9
-#define MADERA_ASRC1_IN2_LOCK_EINT1_WIDTH		     1
 #define MADERA_ASRC1_IN1_LOCK_EINT1			0x0100
 #define MADERA_ASRC1_IN1_LOCK_EINT1_MASK		0x0100
 #define MADERA_ASRC1_IN1_LOCK_EINT1_SHIFT		     8
-#define MADERA_ASRC1_IN1_LOCK_EINT1_WIDTH		     1
 #define MADERA_DRC2_SIG_DET_EINT1			0x0002
 #define MADERA_DRC2_SIG_DET_EINT1_MASK			0x0002
 #define MADERA_DRC2_SIG_DET_EINT1_SHIFT			     1
-#define MADERA_DRC2_SIG_DET_EINT1_WIDTH			     1
 #define MADERA_DRC1_SIG_DET_EINT1			0x0001
 #define MADERA_DRC1_SIG_DET_EINT1_MASK			0x0001
 #define MADERA_DRC1_SIG_DET_EINT1_SHIFT			     0
-#define MADERA_DRC1_SIG_DET_EINT1_WIDTH			     1
 
 /* (0x180A)  IRQ1_Status_11 */
 #define MADERA_DSP_IRQ16_EINT1				0x8000
 #define MADERA_DSP_IRQ16_EINT1_MASK			0x8000
 #define MADERA_DSP_IRQ16_EINT1_SHIFT			    15
-#define MADERA_DSP_IRQ16_EINT1_WIDTH			     1
 #define MADERA_DSP_IRQ15_EINT1				0x4000
 #define MADERA_DSP_IRQ15_EINT1_MASK			0x4000
 #define MADERA_DSP_IRQ15_EINT1_SHIFT			    14
-#define MADERA_DSP_IRQ15_EINT1_WIDTH			     1
 #define MADERA_DSP_IRQ14_EINT1				0x2000
 #define MADERA_DSP_IRQ14_EINT1_MASK			0x2000
 #define MADERA_DSP_IRQ14_EINT1_SHIFT			    13
-#define MADERA_DSP_IRQ14_EINT1_WIDTH			     1
 #define MADERA_DSP_IRQ13_EINT1				0x1000
 #define MADERA_DSP_IRQ13_EINT1_MASK			0x1000
 #define MADERA_DSP_IRQ13_EINT1_SHIFT			    12
-#define MADERA_DSP_IRQ13_EINT1_WIDTH			     1
 #define MADERA_DSP_IRQ12_EINT1				0x0800
 #define MADERA_DSP_IRQ12_EINT1_MASK			0x0800
 #define MADERA_DSP_IRQ12_EINT1_SHIFT			    11
-#define MADERA_DSP_IRQ12_EINT1_WIDTH			     1
 #define MADERA_DSP_IRQ11_EINT1				0x0400
 #define MADERA_DSP_IRQ11_EINT1_MASK			0x0400
 #define MADERA_DSP_IRQ11_EINT1_SHIFT			    10
-#define MADERA_DSP_IRQ11_EINT1_WIDTH			     1
 #define MADERA_DSP_IRQ10_EINT1				0x0200
 #define MADERA_DSP_IRQ10_EINT1_MASK			0x0200
 #define MADERA_DSP_IRQ10_EINT1_SHIFT			     9
-#define MADERA_DSP_IRQ10_EINT1_WIDTH			     1
 #define MADERA_DSP_IRQ9_EINT1				0x0100
 #define MADERA_DSP_IRQ9_EINT1_MASK			0x0100
 #define MADERA_DSP_IRQ9_EINT1_SHIFT			     8
-#define MADERA_DSP_IRQ9_EINT1_WIDTH			     1
 #define MADERA_DSP_IRQ8_EINT1				0x0080
 #define MADERA_DSP_IRQ8_EINT1_MASK			0x0080
 #define MADERA_DSP_IRQ8_EINT1_SHIFT			     7
-#define MADERA_DSP_IRQ8_EINT1_WIDTH			     1
 #define MADERA_DSP_IRQ7_EINT1				0x0040
 #define MADERA_DSP_IRQ7_EINT1_MASK			0x0040
 #define MADERA_DSP_IRQ7_EINT1_SHIFT			     6
-#define MADERA_DSP_IRQ7_EINT1_WIDTH			     1
 #define MADERA_DSP_IRQ6_EINT1				0x0020
 #define MADERA_DSP_IRQ6_EINT1_MASK			0x0020
 #define MADERA_DSP_IRQ6_EINT1_SHIFT			     5
-#define MADERA_DSP_IRQ6_EINT1_WIDTH			     1
 #define MADERA_DSP_IRQ5_EINT1				0x0010
 #define MADERA_DSP_IRQ5_EINT1_MASK			0x0010
 #define MADERA_DSP_IRQ5_EINT1_SHIFT			     4
-#define MADERA_DSP_IRQ5_EINT1_WIDTH			     1
 #define MADERA_DSP_IRQ4_EINT1				0x0008
 #define MADERA_DSP_IRQ4_EINT1_MASK			0x0008
 #define MADERA_DSP_IRQ4_EINT1_SHIFT			     3
-#define MADERA_DSP_IRQ4_EINT1_WIDTH			     1
 #define MADERA_DSP_IRQ3_EINT1				0x0004
 #define MADERA_DSP_IRQ3_EINT1_MASK			0x0004
 #define MADERA_DSP_IRQ3_EINT1_SHIFT			     2
-#define MADERA_DSP_IRQ3_EINT1_WIDTH			     1
 #define MADERA_DSP_IRQ2_EINT1				0x0002
 #define MADERA_DSP_IRQ2_EINT1_MASK			0x0002
 #define MADERA_DSP_IRQ2_EINT1_SHIFT			     1
-#define MADERA_DSP_IRQ2_EINT1_WIDTH			     1
 #define MADERA_DSP_IRQ1_EINT1				0x0001
 #define MADERA_DSP_IRQ1_EINT1_MASK			0x0001
 #define MADERA_DSP_IRQ1_EINT1_SHIFT			     0
-#define MADERA_DSP_IRQ1_EINT1_WIDTH			     1
 
 /* (0x180B)  IRQ1_Status_12 */
 #define MADERA_SPKOUTR_SC_EINT1				0x0080
 #define MADERA_SPKOUTR_SC_EINT1_MASK			0x0080
 #define MADERA_SPKOUTR_SC_EINT1_SHIFT			     7
-#define MADERA_SPKOUTR_SC_EINT1_WIDTH			     1
 #define MADERA_SPKOUTL_SC_EINT1				0x0040
 #define MADERA_SPKOUTL_SC_EINT1_MASK			0x0040
 #define MADERA_SPKOUTL_SC_EINT1_SHIFT			     6
-#define MADERA_SPKOUTL_SC_EINT1_WIDTH			     1
 #define MADERA_HP3R_SC_EINT1				0x0020
 #define MADERA_HP3R_SC_EINT1_MASK			0x0020
 #define MADERA_HP3R_SC_EINT1_SHIFT			     5
-#define MADERA_HP3R_SC_EINT1_WIDTH			     1
 #define MADERA_HP3L_SC_EINT1				0x0010
 #define MADERA_HP3L_SC_EINT1_MASK			0x0010
 #define MADERA_HP3L_SC_EINT1_SHIFT			     4
-#define MADERA_HP3L_SC_EINT1_WIDTH			     1
 #define MADERA_HP2R_SC_EINT1				0x0008
 #define MADERA_HP2R_SC_EINT1_MASK			0x0008
 #define MADERA_HP2R_SC_EINT1_SHIFT			     3
-#define MADERA_HP2R_SC_EINT1_WIDTH			     1
 #define MADERA_HP2L_SC_EINT1				0x0004
 #define MADERA_HP2L_SC_EINT1_MASK			0x0004
 #define MADERA_HP2L_SC_EINT1_SHIFT			     2
-#define MADERA_HP2L_SC_EINT1_WIDTH			     1
 #define MADERA_HP1R_SC_EINT1				0x0002
 #define MADERA_HP1R_SC_EINT1_MASK			0x0002
 #define MADERA_HP1R_SC_EINT1_SHIFT			     1
-#define MADERA_HP1R_SC_EINT1_WIDTH			     1
 #define MADERA_HP1L_SC_EINT1				0x0001
 #define MADERA_HP1L_SC_EINT1_MASK			0x0001
 #define MADERA_HP1L_SC_EINT1_SHIFT			     0
-#define MADERA_HP1L_SC_EINT1_WIDTH			     1
 
 /* (0x180E)  IRQ1_Status_15 */
 #define MADERA_SPK_OVERHEAT_WARN_EINT1			0x0004
 #define MADERA_SPK_OVERHEAT_WARN_EINT1_MASK		0x0004
 #define MADERA_SPK_OVERHEAT_WARN_EINT1_SHIFT		     2
-#define MADERA_SPK_OVERHEAT_WARN_EINT1_WIDTH		     1
 #define MADERA_SPK_OVERHEAT_EINT1			0x0002
 #define MADERA_SPK_OVERHEAT_EINT1_MASK			0x0002
 #define MADERA_SPK_OVERHEAT_EINT1_SHIFT			     1
-#define MADERA_SPK_OVERHEAT_EINT1_WIDTH			     1
 #define MADERA_SPK_SHUTDOWN_EINT1			0x0001
 #define MADERA_SPK_SHUTDOWN_EINT1_MASK			0x0001
 #define MADERA_SPK_SHUTDOWN_EINT1_SHIFT			     0
-#define MADERA_SPK_SHUTDOWN_EINT1_WIDTH			     1
 
 /* (0x1820) - IRQ1 Status 33 */
 #define MADERA_DSP7_BUS_ERR_EINT1			0x0040
 #define MADERA_DSP7_BUS_ERR_EINT1_MASK			0x0040
 #define MADERA_DSP7_BUS_ERR_EINT1_SHIFT			     6
-#define MADERA_DSP7_BUS_ERR_EINT1_WIDTH			     1
 #define MADERA_DSP6_BUS_ERR_EINT1			0x0020
 #define MADERA_DSP6_BUS_ERR_EINT1_MASK			0x0020
 #define MADERA_DSP6_BUS_ERR_EINT1_SHIFT			     5
-#define MADERA_DSP6_BUS_ERR_EINT1_WIDTH			     1
 #define MADERA_DSP5_BUS_ERR_EINT1			0x0010
 #define MADERA_DSP5_BUS_ERR_EINT1_MASK			0x0010
 #define MADERA_DSP5_BUS_ERR_EINT1_SHIFT			     4
-#define MADERA_DSP5_BUS_ERR_EINT1_WIDTH			     1
 #define MADERA_DSP4_BUS_ERR_EINT1			0x0008
 #define MADERA_DSP4_BUS_ERR_EINT1_MASK			0x0008
 #define MADERA_DSP4_BUS_ERR_EINT1_SHIFT			     3
-#define MADERA_DSP4_BUS_ERR_EINT1_WIDTH			     1
 #define MADERA_DSP3_BUS_ERR_EINT1			0x0004
 #define MADERA_DSP3_BUS_ERR_EINT1_MASK			0x0004
 #define MADERA_DSP3_BUS_ERR_EINT1_SHIFT			     2
-#define MADERA_DSP3_BUS_ERR_EINT1_WIDTH			     1
 #define MADERA_DSP2_BUS_ERR_EINT1			0x0002
 #define MADERA_DSP2_BUS_ERR_EINT1_MASK			0x0002
 #define MADERA_DSP2_BUS_ERR_EINT1_SHIFT			     1
-#define MADERA_DSP2_BUS_ERR_EINT1_WIDTH			     1
 #define MADERA_DSP1_BUS_ERR_EINT1			0x0001
 #define MADERA_DSP1_BUS_ERR_EINT1_MASK			0x0001
 #define MADERA_DSP1_BUS_ERR_EINT1_SHIFT			     0
-#define MADERA_DSP1_BUS_ERR_EINT1_WIDTH			     1
 
 /* (0x1845)  IRQ1_Mask_6 */
 #define MADERA_IM_MICDET2_EINT1				0x0200
 #define MADERA_IM_MICDET2_EINT1_MASK			0x0200
 #define MADERA_IM_MICDET2_EINT1_SHIFT			     9
-#define MADERA_IM_MICDET2_EINT1_WIDTH			     1
 #define MADERA_IM_MICDET1_EINT1				0x0100
 #define MADERA_IM_MICDET1_EINT1_MASK			0x0100
 #define MADERA_IM_MICDET1_EINT1_SHIFT			     8
-#define MADERA_IM_MICDET1_EINT1_WIDTH			     1
 #define MADERA_IM_HPDET_EINT1				0x0001
 #define MADERA_IM_HPDET_EINT1_MASK			0x0001
 #define MADERA_IM_HPDET_EINT1_SHIFT			     0
-#define MADERA_IM_HPDET_EINT1_WIDTH			     1
 /* (0x184E)  IRQ1_Mask_15 */
 #define MADERA_IM_SPK_OVERHEAT_WARN_EINT1		0x0004
 #define MADERA_IM_SPK_OVERHEAT_WARN_EINT1_MASK		0x0004
 #define MADERA_IM_SPK_OVERHEAT_WARN_EINT1_SHIFT		     2
-#define MADERA_IM_SPK_OVERHEAT_WARN_EINT1_WIDTH		     1
 #define MADERA_IM_SPK_OVERHEAT_EINT1			0x0002
 #define MADERA_IM_SPK_OVERHEAT_EINT1_MASK		0x0002
 #define MADERA_IM_SPK_OVERHEAT_EINT1_SHIFT		     1
-#define MADERA_IM_SPK_OVERHEAT_EINT1_WIDTH		     1
 #define MADERA_IM_SPK_SHUTDOWN_EINT1			0x0001
 #define MADERA_IM_SPK_SHUTDOWN_EINT1_MASK		0x0001
 #define MADERA_IM_SPK_SHUTDOWN_EINT1_SHIFT		     0
-#define MADERA_IM_SPK_SHUTDOWN_EINT1_WIDTH		     1
 
 /* (0x1880) - IRQ1 Raw Status 1 */
 #define MADERA_CTRLIF_ERR_STS1				0x1000
 #define MADERA_CTRLIF_ERR_STS1_MASK			0x1000
 #define MADERA_CTRLIF_ERR_STS1_SHIFT			    12
-#define MADERA_CTRLIF_ERR_STS1_WIDTH			     1
 #define MADERA_SYSCLK_FAIL_STS1				0x0200
 #define MADERA_SYSCLK_FAIL_STS1_MASK			0x0200
 #define MADERA_SYSCLK_FAIL_STS1_SHIFT			     9
-#define MADERA_SYSCLK_FAIL_STS1_WIDTH			     1
 #define MADERA_CLOCK_DETECT_STS1			0x0100
 #define MADERA_CLOCK_DETECT_STS1_MASK			0x0100
 #define MADERA_CLOCK_DETECT_STS1_SHIFT			     8
-#define MADERA_CLOCK_DETECT_STS1_WIDTH			     1
 #define MADERA_BOOT_DONE_STS1				0x0080
 #define MADERA_BOOT_DONE_STS1_MASK			0x0080
 #define MADERA_BOOT_DONE_STS1_SHIFT			     7
-#define MADERA_BOOT_DONE_STS1_WIDTH			     1
 
 /* (0x1881) - IRQ1 Raw Status 2 */
 #define MADERA_FLL3_LOCK_STS1				0x0400
 #define MADERA_FLL3_LOCK_STS1_MASK			0x0400
 #define MADERA_FLL3_LOCK_STS1_SHIFT			    10
-#define MADERA_FLL3_LOCK_STS1_WIDTH			     1
 #define MADERA_FLL2_LOCK_STS1				0x0200
 #define MADERA_FLL2_LOCK_STS1_MASK			0x0200
 #define MADERA_FLL2_LOCK_STS1_SHIFT			     9
-#define MADERA_FLL2_LOCK_STS1_WIDTH			     1
 #define MADERA_FLL1_LOCK_STS1				0x0100
 #define MADERA_FLL1_LOCK_STS1_MASK			0x0100
 #define MADERA_FLL1_LOCK_STS1_SHIFT			     8
-#define MADERA_FLL1_LOCK_STS1_WIDTH			     1
 
 /* (0x1886) - IRQ1 Raw Status 7 */
 #define MADERA_MICD_CLAMP_FALL_STS1			0x0020
 #define MADERA_MICD_CLAMP_FALL_STS1_MASK		0x0020
 #define MADERA_MICD_CLAMP_FALL_STS1_SHIFT		     5
-#define MADERA_MICD_CLAMP_FALL_STS1_WIDTH		     1
 #define MADERA_MICD_CLAMP_RISE_STS1			0x0010
 #define MADERA_MICD_CLAMP_RISE_STS1_MASK		0x0010
 #define MADERA_MICD_CLAMP_RISE_STS1_SHIFT		     4
-#define MADERA_MICD_CLAMP_RISE_STS1_WIDTH		     1
 #define MADERA_JD2_FALL_STS1				0x0008
 #define MADERA_JD2_FALL_STS1_MASK			0x0008
 #define MADERA_JD2_FALL_STS1_SHIFT			     3
-#define MADERA_JD2_FALL_STS1_WIDTH			     1
 #define MADERA_JD2_RISE_STS1				0x0004
 #define MADERA_JD2_RISE_STS1_MASK			0x0004
 #define MADERA_JD2_RISE_STS1_SHIFT			     2
-#define MADERA_JD2_RISE_STS1_WIDTH			     1
 #define MADERA_JD1_FALL_STS1				0x0002
 #define MADERA_JD1_FALL_STS1_MASK			0x0002
 #define MADERA_JD1_FALL_STS1_SHIFT			     1
-#define MADERA_JD1_FALL_STS1_WIDTH			     1
 #define MADERA_JD1_RISE_STS1				0x0001
 #define MADERA_JD1_RISE_STS1_MASK			0x0001
 #define MADERA_JD1_RISE_STS1_SHIFT			     0
-#define MADERA_JD1_RISE_STS1_WIDTH			     1
 
 /* (0x188E) - IRQ1 Raw Status 15 */
 #define MADERA_SPK_OVERHEAT_WARN_STS1			0x0004
 #define MADERA_SPK_OVERHEAT_WARN_STS1_MASK		0x0004
 #define MADERA_SPK_OVERHEAT_WARN_STS1_SHIFT		     2
-#define MADERA_SPK_OVERHEAT_WARN_STS1_WIDTH		     1
 #define MADERA_SPK_OVERHEAT_STS1			0x0002
 #define MADERA_SPK_OVERHEAT_STS1_MASK			0x0002
 #define MADERA_SPK_OVERHEAT_STS1_SHIFT			     1
-#define MADERA_SPK_OVERHEAT_STS1_WIDTH			     1
 #define MADERA_SPK_SHUTDOWN_STS1			0x0001
 #define MADERA_SPK_SHUTDOWN_STS1_MASK			0x0001
 #define MADERA_SPK_SHUTDOWN_STS1_SHIFT			     0
-#define MADERA_SPK_SHUTDOWN_STS1_WIDTH			     1
 
 /* (0x1A06)  Interrupt_Debounce_7 */
 #define MADERA_MICD_CLAMP_DB				0x0010
 #define MADERA_MICD_CLAMP_DB_MASK			0x0010
 #define MADERA_MICD_CLAMP_DB_SHIFT			     4
-#define MADERA_MICD_CLAMP_DB_WIDTH			     1
 #define MADERA_JD2_DB					0x0004
 #define MADERA_JD2_DB_MASK				0x0004
 #define MADERA_JD2_DB_SHIFT				     2
-#define MADERA_JD2_DB_WIDTH				     1
 #define MADERA_JD1_DB					0x0001
 #define MADERA_JD1_DB_MASK				0x0001
 #define MADERA_JD1_DB_SHIFT				     0
-#define MADERA_JD1_DB_WIDTH				     1
 
 /* (0x1A0E)  Interrupt_Debounce_15 */
 #define MADERA_SPK_OVERHEAT_WARN_DB			0x0004
 #define MADERA_SPK_OVERHEAT_WARN_DB_MASK		0x0004
 #define MADERA_SPK_OVERHEAT_WARN_DB_SHIFT		     2
-#define MADERA_SPK_OVERHEAT_WARN_DB_WIDTH		     1
 #define MADERA_SPK_OVERHEAT_DB				0x0002
 #define MADERA_SPK_OVERHEAT_DB_MASK			0x0002
 #define MADERA_SPK_OVERHEAT_DB_SHIFT			     1
-#define MADERA_SPK_OVERHEAT_DB_WIDTH			     1
 
 /* (0x1A80)  IRQ1_CTRL */
 #define MADERA_IM_IRQ1					0x0800
 #define MADERA_IM_IRQ1_MASK				0x0800
 #define MADERA_IM_IRQ1_SHIFT				    11
-#define MADERA_IM_IRQ1_WIDTH				     1
 #define MADERA_IRQ_POL					0x0400
 #define MADERA_IRQ_POL_MASK				0x0400
 #define MADERA_IRQ_POL_SHIFT				    10
-#define MADERA_IRQ_POL_WIDTH				     1
 
 /* (0x20004)  OTP_HPDET_Cal_1 */
 #define MADERA_OTP_HPDET_CALIB_OFFSET_11	    0xFF000000
 #define MADERA_OTP_HPDET_CALIB_OFFSET_11_MASK	    0xFF000000
 #define MADERA_OTP_HPDET_CALIB_OFFSET_11_SHIFT		    24
-#define MADERA_OTP_HPDET_CALIB_OFFSET_11_WIDTH		     8
 #define MADERA_OTP_HPDET_CALIB_OFFSET_10	    0x00FF0000
 #define MADERA_OTP_HPDET_CALIB_OFFSET_10_MASK	    0x00FF0000
 #define MADERA_OTP_HPDET_CALIB_OFFSET_10_SHIFT		    16
-#define MADERA_OTP_HPDET_CALIB_OFFSET_10_WIDTH		     8
 #define MADERA_OTP_HPDET_CALIB_OFFSET_01	    0x0000FF00
 #define MADERA_OTP_HPDET_CALIB_OFFSET_01_MASK	    0x0000FF00
 #define MADERA_OTP_HPDET_CALIB_OFFSET_01_SHIFT		     8
-#define MADERA_OTP_HPDET_CALIB_OFFSET_01_WIDTH		     8
 #define MADERA_OTP_HPDET_CALIB_OFFSET_00	    0x000000FF
 #define MADERA_OTP_HPDET_CALIB_OFFSET_00_MASK	    0x000000FF
 #define MADERA_OTP_HPDET_CALIB_OFFSET_00_SHIFT		     0
-#define MADERA_OTP_HPDET_CALIB_OFFSET_00_WIDTH		     8
 
 /* (0x20006)  OTP_HPDET_Cal_2 */
 #define MADERA_OTP_HPDET_GRADIENT_1X		    0x0000FF00
 #define MADERA_OTP_HPDET_GRADIENT_1X_MASK	    0x0000FF00
 #define MADERA_OTP_HPDET_GRADIENT_1X_SHIFT		     8
-#define MADERA_OTP_HPDET_GRADIENT_1X_WIDTH		     8
 #define MADERA_OTP_HPDET_GRADIENT_0X		    0x000000FF
 #define MADERA_OTP_HPDET_GRADIENT_0X_MASK	    0x000000FF
 #define MADERA_OTP_HPDET_GRADIENT_0X_SHIFT		     0
-#define MADERA_OTP_HPDET_GRADIENT_0X_WIDTH		     8
 
 #endif
-- 
cgit v1.2.3


From 28faad777c2d1480dfdda6697e58c06cf9011ebc Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Sun, 27 Sep 2020 01:59:17 +0200
Subject: mfd: tps65910: Clean up after switching to regmap
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove wrappers around regmap calls to remove now-useless indirection.

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/tps65910.c       | 16 ++++++++--------
 include/linux/mfd/tps65910.h | 35 -----------------------------------
 2 files changed, 8 insertions(+), 43 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mfd/tps65910.c b/drivers/mfd/tps65910.c
index a6c28df7aa38..cbfc6afb3928 100644
--- a/drivers/mfd/tps65910.c
+++ b/drivers/mfd/tps65910.c
@@ -292,7 +292,7 @@ static int tps65910_ck32k_init(struct tps65910 *tps65910,
 	if (!pmic_pdata->en_ck32k_xtal)
 		return 0;
 
-	ret = tps65910_reg_clear_bits(tps65910, TPS65910_DEVCTRL,
+	ret = regmap_clear_bits(tps65910->regmap, TPS65910_DEVCTRL,
 						DEVCTRL_CK32K_CTRL_MASK);
 	if (ret < 0) {
 		dev_err(tps65910->dev, "clear ck32k_ctrl failed: %d\n", ret);
@@ -314,7 +314,7 @@ static int tps65910_sleepinit(struct tps65910 *tps65910,
 	dev = tps65910->dev;
 
 	/* enabling SLEEP device state */
-	ret = tps65910_reg_set_bits(tps65910, TPS65910_DEVCTRL,
+	ret = regmap_set_bits(tps65910->regmap, TPS65910_DEVCTRL,
 				DEVCTRL_DEV_SLP_MASK);
 	if (ret < 0) {
 		dev_err(dev, "set dev_slp failed: %d\n", ret);
@@ -322,7 +322,7 @@ static int tps65910_sleepinit(struct tps65910 *tps65910,
 	}
 
 	if (pmic_pdata->slp_keepon.therm_keepon) {
-		ret = tps65910_reg_set_bits(tps65910,
+		ret = regmap_set_bits(tps65910->regmap,
 				TPS65910_SLEEP_KEEP_RES_ON,
 				SLEEP_KEEP_RES_ON_THERM_KEEPON_MASK);
 		if (ret < 0) {
@@ -332,7 +332,7 @@ static int tps65910_sleepinit(struct tps65910 *tps65910,
 	}
 
 	if (pmic_pdata->slp_keepon.clkout32k_keepon) {
-		ret = tps65910_reg_set_bits(tps65910,
+		ret = regmap_set_bits(tps65910->regmap,
 				TPS65910_SLEEP_KEEP_RES_ON,
 				SLEEP_KEEP_RES_ON_CLKOUT32K_KEEPON_MASK);
 		if (ret < 0) {
@@ -342,7 +342,7 @@ static int tps65910_sleepinit(struct tps65910 *tps65910,
 	}
 
 	if (pmic_pdata->slp_keepon.i2chs_keepon) {
-		ret = tps65910_reg_set_bits(tps65910,
+		ret = regmap_set_bits(tps65910->regmap,
 				TPS65910_SLEEP_KEEP_RES_ON,
 				SLEEP_KEEP_RES_ON_I2CHS_KEEPON_MASK);
 		if (ret < 0) {
@@ -354,7 +354,7 @@ static int tps65910_sleepinit(struct tps65910 *tps65910,
 	return 0;
 
 disable_dev_slp:
-	tps65910_reg_clear_bits(tps65910, TPS65910_DEVCTRL,
+	regmap_clear_bits(tps65910->regmap, TPS65910_DEVCTRL,
 				DEVCTRL_DEV_SLP_MASK);
 
 err_sleep_init:
@@ -436,11 +436,11 @@ static void tps65910_power_off(void)
 
 	tps65910 = dev_get_drvdata(&tps65910_i2c_client->dev);
 
-	if (tps65910_reg_set_bits(tps65910, TPS65910_DEVCTRL,
+	if (regmap_set_bits(tps65910->regmap, TPS65910_DEVCTRL,
 			DEVCTRL_PWR_OFF_MASK) < 0)
 		return;
 
-	tps65910_reg_clear_bits(tps65910, TPS65910_DEVCTRL,
+	regmap_clear_bits(tps65910->regmap, TPS65910_DEVCTRL,
 			DEVCTRL_DEV_ON_MASK);
 }
 
diff --git a/include/linux/mfd/tps65910.h b/include/linux/mfd/tps65910.h
index ce4b9e743f7c..f7398d982f23 100644
--- a/include/linux/mfd/tps65910.h
+++ b/include/linux/mfd/tps65910.h
@@ -913,39 +913,4 @@ static inline int tps65910_chip_id(struct tps65910 *tps65910)
 	return tps65910->id;
 }
 
-static inline int tps65910_reg_read(struct tps65910 *tps65910, u8 reg,
-		unsigned int *val)
-{
-	return regmap_read(tps65910->regmap, reg, val);
-}
-
-static inline int tps65910_reg_write(struct tps65910 *tps65910, u8 reg,
-		unsigned int val)
-{
-	return regmap_write(tps65910->regmap, reg, val);
-}
-
-static inline int tps65910_reg_set_bits(struct tps65910 *tps65910, u8 reg,
-		u8 mask)
-{
-	return regmap_update_bits(tps65910->regmap, reg, mask, mask);
-}
-
-static inline int tps65910_reg_clear_bits(struct tps65910 *tps65910, u8 reg,
-		u8 mask)
-{
-	return regmap_update_bits(tps65910->regmap, reg, mask, 0);
-}
-
-static inline int tps65910_reg_update_bits(struct tps65910 *tps65910, u8 reg,
-					   u8 mask, u8 val)
-{
-	return regmap_update_bits(tps65910->regmap, reg, mask, val);
-}
-
-static inline int tps65910_irq_get_virq(struct tps65910 *tps65910, int irq)
-{
-	return regmap_irq_get_virq(tps65910->irq_data, irq);
-}
-
 #endif /*  __LINUX_MFD_TPS65910_H */
-- 
cgit v1.2.3


From 9f5b98f3f4149a10c315ddb4d0bed033f398e8ec Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Sun, 27 Sep 2020 01:59:18 +0200
Subject: mfd: tps65910: Remove unused pointers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Client pointers in tps65910 data are not used in the drivers.
Remove those fields.

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/mfd/tps65910.h | 5 -----
 1 file changed, 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mfd/tps65910.h b/include/linux/mfd/tps65910.h
index f7398d982f23..701925db75b3 100644
--- a/include/linux/mfd/tps65910.h
+++ b/include/linux/mfd/tps65910.h
@@ -890,11 +890,6 @@ struct tps65910 {
 	struct regmap *regmap;
 	unsigned long id;
 
-	/* Client devices */
-	struct tps65910_pmic *pmic;
-	struct tps65910_rtc *rtc;
-	struct tps65910_power *power;
-
 	/* Device node parsed board data */
 	struct tps65910_board *of_plat_data;
 
-- 
cgit v1.2.3


From f594d01bb4aff35dc582f5418e6823f79e28834b Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.cirrus.com>
Date: Tue, 27 Oct 2020 09:41:32 +0000
Subject: mfd: madera: Add special errata reset handling for cs47l15

An errata exists for cs47l15 where the reset must be handled
differently and removed before DCVDD is applied. A soft reset is used
for situations where a reset is required to reset state. This does
however, make this part unsuitable for DCVDD supplies with a rise time
greater than 2mS.

Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/madera-core.c       | 25 ++++++++++++++++++++-----
 include/linux/mfd/madera/core.h |  1 +
 2 files changed, 21 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mfd/madera-core.c b/drivers/mfd/madera-core.c
index a9c6f0833f32..a2abc0094def 100644
--- a/drivers/mfd/madera-core.c
+++ b/drivers/mfd/madera-core.c
@@ -38,6 +38,9 @@
 #define MADERA_RESET_MIN_US	2000
 #define MADERA_RESET_MAX_US	3000
 
+#define ERRATA_DCVDD_MIN_US	10000
+#define ERRATA_DCVDD_MAX_US	15000
+
 static const char * const madera_core_supplies[] = {
 	"AVDD",
 	"DBVDD1",
@@ -291,7 +294,8 @@ static int __maybe_unused madera_runtime_resume(struct device *dev)
 
 	dev_dbg(dev, "Leaving sleep mode\n");
 
-	madera_enable_hard_reset(madera);
+	if (!madera->reset_errata)
+		madera_enable_hard_reset(madera);
 
 	ret = regulator_enable(madera->dcvdd);
 	if (ret) {
@@ -302,9 +306,12 @@ static int __maybe_unused madera_runtime_resume(struct device *dev)
 	regcache_cache_only(madera->regmap, false);
 	regcache_cache_only(madera->regmap_32bit, false);
 
-	madera_disable_hard_reset(madera);
+	if (madera->reset_errata)
+		usleep_range(ERRATA_DCVDD_MIN_US, ERRATA_DCVDD_MAX_US);
+	else
+		madera_disable_hard_reset(madera);
 
-	if (!madera->pdata.reset) {
+	if (!madera->pdata.reset || madera->reset_errata) {
 		ret = madera_wait_for_boot(madera);
 		if (ret)
 			goto err;
@@ -503,6 +510,8 @@ int madera_dev_init(struct madera *madera)
 	 */
 	switch (madera->type) {
 	case CS47L15:
+		madera->reset_errata = true;
+		break;
 	case CS47L35:
 	case CS47L90:
 	case CS47L91:
@@ -553,13 +562,19 @@ int madera_dev_init(struct madera *madera)
 		goto err_dcvdd;
 	}
 
+	if (madera->reset_errata)
+		madera_disable_hard_reset(madera);
+
 	ret = regulator_enable(madera->dcvdd);
 	if (ret) {
 		dev_err(dev, "Failed to enable DCVDD: %d\n", ret);
 		goto err_enable;
 	}
 
-	madera_disable_hard_reset(madera);
+	if (madera->reset_errata)
+		usleep_range(ERRATA_DCVDD_MIN_US, ERRATA_DCVDD_MAX_US);
+	else
+		madera_disable_hard_reset(madera);
 
 	regcache_cache_only(madera->regmap, false);
 	regcache_cache_only(madera->regmap_32bit, false);
@@ -667,7 +682,7 @@ int madera_dev_init(struct madera *madera)
 	 * It looks like a device we support. If we don't have a hard reset
 	 * we can now attempt a soft reset.
 	 */
-	if (!madera->pdata.reset) {
+	if (!madera->pdata.reset || madera->reset_errata) {
 		ret = madera_soft_reset(madera);
 		if (ret)
 			goto err_reset;
diff --git a/include/linux/mfd/madera/core.h b/include/linux/mfd/madera/core.h
index ad2c138105d4..03a8a788424a 100644
--- a/include/linux/mfd/madera/core.h
+++ b/include/linux/mfd/madera/core.h
@@ -186,6 +186,7 @@ struct madera {
 	struct regulator_bulk_data core_supplies[MADERA_MAX_CORE_SUPPLIES];
 	struct regulator *dcvdd;
 	bool internal_dcvdd;
+	bool reset_errata;
 
 	struct madera_pdata pdata;
 
-- 
cgit v1.2.3


From 4556fe8f16e0225f5df7a57d123e0d55717bf2aa Mon Sep 17 00:00:00 2001
From: Michael Srba <Michael.Srba@seznam.cz>
Date: Tue, 10 Nov 2020 14:00:47 +0100
Subject: mfd: rt5033: Fix errorneous defines

Fix regulators on rt5033 by converting some values to bitmasks which were
errorneously not defined as such in the header file.

Cc: Beomho Seo <beomho.seo@samsung.com>
Fixes: 0b271258544b ("mfd: rt5033: Add Richtek RT5033 driver core.")
Signed-off-by: Michael Srba <Michael.Srba@seznam.cz>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/mfd/rt5033-private.h | 28 ++++++++++++++--------------
 1 file changed, 14 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mfd/rt5033-private.h b/include/linux/mfd/rt5033-private.h
index f812105c538c..2d1895c3efbf 100644
--- a/include/linux/mfd/rt5033-private.h
+++ b/include/linux/mfd/rt5033-private.h
@@ -91,14 +91,14 @@ enum rt5033_reg {
 #define RT5033_RT_HZ_MASK		0x01
 
 /* RT5033 control register */
-#define RT5033_CTRL_FCCM_BUCK_MASK		0x00
-#define RT5033_CTRL_BUCKOMS_MASK		0x01
-#define RT5033_CTRL_LDOOMS_MASK			0x02
-#define RT5033_CTRL_SLDOOMS_MASK		0x03
-#define RT5033_CTRL_EN_BUCK_MASK		0x04
-#define RT5033_CTRL_EN_LDO_MASK			0x05
-#define RT5033_CTRL_EN_SAFE_LDO_MASK		0x06
-#define RT5033_CTRL_LDO_SLEEP_MASK		0x07
+#define RT5033_CTRL_FCCM_BUCK_MASK		BIT(0)
+#define RT5033_CTRL_BUCKOMS_MASK		BIT(1)
+#define RT5033_CTRL_LDOOMS_MASK			BIT(2)
+#define RT5033_CTRL_SLDOOMS_MASK		BIT(3)
+#define RT5033_CTRL_EN_BUCK_MASK		BIT(4)
+#define RT5033_CTRL_EN_LDO_MASK			BIT(5)
+#define RT5033_CTRL_EN_SAFE_LDO_MASK		BIT(6)
+#define RT5033_CTRL_LDO_SLEEP_MASK		BIT(7)
 
 /* RT5033 BUCK control register */
 #define RT5033_BUCK_CTRL_MASK			0x1f
@@ -247,11 +247,11 @@ enum rt5033_fuel_reg {
 #define RT5033_FUEL_BAT_PRESENT		0x02
 
 /* RT5033 PMIC interrupts */
-#define RT5033_PMIC_IRQ_BUCKOCP		2
-#define RT5033_PMIC_IRQ_BUCKLV		3
-#define RT5033_PMIC_IRQ_SAFELDOLV	4
-#define RT5033_PMIC_IRQ_LDOLV		5
-#define RT5033_PMIC_IRQ_OT		6
-#define RT5033_PMIC_IRQ_VDDA_UV		7
+#define RT5033_PMIC_IRQ_BUCKOCP		BIT(2)
+#define RT5033_PMIC_IRQ_BUCKLV		BIT(3)
+#define RT5033_PMIC_IRQ_SAFELDOLV	BIT(4)
+#define RT5033_PMIC_IRQ_LDOLV		BIT(5)
+#define RT5033_PMIC_IRQ_OT		BIT(6)
+#define RT5033_PMIC_IRQ_VDDA_UV		BIT(7)
 
 #endif /* __RT5033_PRIVATE_H__ */
-- 
cgit v1.2.3


From 295992fb815e791d14b18ef7cdbbaf1a76211a31 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Mon, 14 Sep 2020 15:09:33 +0200
Subject: mm: introduce vma_set_file function v5
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add the new vma_set_file() function to allow changing
vma->vm_file with the necessary refcount dance.

v2: add more users of this.
v3: add missing EXPORT_SYMBOL, rebase on mmap cleanup,
    add comments why we drop the reference on two occasions.
v4: make it clear that changing an anonymous vma is illegal.
v5: move vma_set_file to mm/util.c

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> (v2)
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
Link: https://patchwork.freedesktop.org/patch/399360/
---
 drivers/dma-buf/dma-buf.c                  |  3 +--
 drivers/gpu/drm/etnaviv/etnaviv_gem.c      |  4 +---
 drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c |  3 +--
 drivers/gpu/drm/i915/gem/i915_gem_mman.c   |  5 +++--
 drivers/gpu/drm/msm/msm_gem.c              |  4 +---
 drivers/gpu/drm/omapdrm/omap_gem.c         |  3 +--
 drivers/gpu/drm/vgem/vgem_drv.c            |  3 +--
 drivers/staging/android/ashmem.c           |  6 +++---
 include/linux/mm.h                         |  2 ++
 mm/util.c                                  | 12 ++++++++++++
 10 files changed, 26 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index 282bd8b84170..e63684d4cd90 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -1183,8 +1183,7 @@ int dma_buf_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma,
 		return -EINVAL;
 
 	/* readjust the vma */
-	fput(vma->vm_file);
-	vma->vm_file = get_file(dmabuf->file);
+	vma_set_file(vma, dmabuf->file);
 	vma->vm_pgoff = pgoff;
 
 	return dmabuf->ops->mmap(dmabuf, vma);
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
index bbd235473645..6d38c5c17f23 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
@@ -145,10 +145,8 @@ static int etnaviv_gem_mmap_obj(struct etnaviv_gem_object *etnaviv_obj,
 		 * address_space (so unmap_mapping_range does what we want,
 		 * in particular in the case of mmap'd dmabufs)
 		 */
-		fput(vma->vm_file);
-		get_file(etnaviv_obj->base.filp);
 		vma->vm_pgoff = 0;
-		vma->vm_file  = etnaviv_obj->base.filp;
+		vma_set_file(vma, etnaviv_obj->base.filp);
 
 		vma->vm_page_prot = vm_page_prot;
 	}
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
index 0dd477e56573..04e9c04545ad 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
@@ -114,8 +114,7 @@ static int i915_gem_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struct *
 	if (ret)
 		return ret;
 
-	fput(vma->vm_file);
-	vma->vm_file = get_file(obj->base.filp);
+	vma_set_file(vma, obj->base.filp);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index 3d69e51f3e4d..ec28a6cde49b 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -893,8 +893,9 @@ int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma)
 	 * requires avoiding extraneous references to their filp, hence why
 	 * we prefer to use an anonymous file for their mmaps.
 	 */
-	fput(vma->vm_file);
-	vma->vm_file = anon;
+	vma_set_file(vma, anon);
+	/* Drop the initial creation reference, the vma is now holding one. */
+	fput(anon);
 
 	switch (mmo->mmap_type) {
 	case I915_MMAP_TYPE_WC:
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 2e1bce7c0b19..311721ceee50 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -212,10 +212,8 @@ int msm_gem_mmap_obj(struct drm_gem_object *obj,
 		 * address_space (so unmap_mapping_range does what we want,
 		 * in particular in the case of mmap'd dmabufs)
 		 */
-		fput(vma->vm_file);
-		get_file(obj->filp);
 		vma->vm_pgoff = 0;
-		vma->vm_file  = obj->filp;
+		vma_set_file(vma, obj->filp);
 
 		vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
 	}
diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index 68c271f4250b..30d299ca8795 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem.c
@@ -564,9 +564,8 @@ int omap_gem_mmap_obj(struct drm_gem_object *obj,
 		 * address_space (so unmap_mapping_range does what we want,
 		 * in particular in the case of mmap'd dmabufs)
 		 */
-		fput(vma->vm_file);
 		vma->vm_pgoff = 0;
-		vma->vm_file  = get_file(obj->filp);
+		vma_set_file(vma, obj->filp);
 
 		vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
 	}
diff --git a/drivers/gpu/drm/vgem/vgem_drv.c b/drivers/gpu/drm/vgem/vgem_drv.c
index 9a413091abb6..f8635ccaf9a1 100644
--- a/drivers/gpu/drm/vgem/vgem_drv.c
+++ b/drivers/gpu/drm/vgem/vgem_drv.c
@@ -403,8 +403,7 @@ static int vgem_prime_mmap(struct drm_gem_object *obj,
 	if (ret)
 		return ret;
 
-	fput(vma->vm_file);
-	vma->vm_file = get_file(obj->filp);
+	vma_set_file(vma, obj->filp);
 	vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP;
 	vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags));
 
diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c
index 10b4be1f3e78..4789d36ddfd3 100644
--- a/drivers/staging/android/ashmem.c
+++ b/drivers/staging/android/ashmem.c
@@ -450,9 +450,9 @@ static int ashmem_mmap(struct file *file, struct vm_area_struct *vma)
 		vma_set_anonymous(vma);
 	}
 
-	if (vma->vm_file)
-		fput(vma->vm_file);
-	vma->vm_file = asma->file;
+	vma_set_file(vma, asma->file);
+	/* XXX: merge this with the get_file() above if possible */
+	fput(asma->file);
 
 out:
 	mutex_unlock(&ashmem_mutex);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index db6ae4d3fb4e..47bff16c182d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2719,6 +2719,8 @@ static inline void vma_set_page_prot(struct vm_area_struct *vma)
 }
 #endif
 
+void vma_set_file(struct vm_area_struct *vma, struct file *file);
+
 #ifdef CONFIG_NUMA_BALANCING
 unsigned long change_prot_numa(struct vm_area_struct *vma,
 			unsigned long start, unsigned long end);
diff --git a/mm/util.c b/mm/util.c
index 4ddb6e186dd5..8c9b7d1e7c49 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -311,6 +311,18 @@ int vma_is_stack_for_current(struct vm_area_struct *vma)
 	return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t));
 }
 
+/*
+ * Change backing file, only valid to use during initial VMA setup.
+ */
+void vma_set_file(struct vm_area_struct *vma, struct file *file)
+{
+	/* Changing an anonymous vma with this is illegal */
+	get_file(file);
+	swap(vma->vm_file, file);
+	fput(file);
+}
+EXPORT_SYMBOL(vma_set_file);
+
 #ifndef STACK_RND_MASK
 #define STACK_RND_MASK (0x7ff >> (PAGE_SHIFT - 12))     /* 8MB of VA */
 #endif
-- 
cgit v1.2.3


From 179a9cf79212bb3b96fb69a314583189cd863c5b Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <frederic@kernel.org>
Date: Tue, 17 Nov 2020 16:16:34 +0100
Subject: context_tracking: Don't implement exception_enter/exit() on
 CONFIG_HAVE_CONTEXT_TRACKING_OFFSTACK

The typical steps with context tracking are:

1) Task runs in userspace
2) Task enters the kernel (syscall/exception/IRQ)
3) Task switches from context tracking state CONTEXT_USER to
   CONTEXT_KERNEL (user_exit())
4) Task does stuff in kernel
5) Task switches from context tracking state CONTEXT_KERNEL to
   CONTEXT_USER (user_enter())
6) Task exits the kernel

If an exception fires between 5) and 6), the pt_regs and the context
tracking disagree on the context of the faulted/trapped instruction.
CONTEXT_KERNEL must be set before the exception handler, that's
unconditional for those handlers that want to be able to call into
schedule(), but CONTEXT_USER must be restored when the exception exits
whereas pt_regs tells that we are resuming to kernel space.

This can't be fixed with storing the context tracking state in a per-cpu
or per-task variable since another exception may fire onto the current
one and overwrite the saved state. Also the task can schedule. So it
has to be stored in a per task stack.

This is how exception_enter()/exception_exit() paper over the problem:

5) Task switches from context tracking state CONTEXT_KERNEL to
   CONTEXT_USER (user_enter())
5.1) Exception fires
5.2) prev_state = exception_enter() // save CONTEXT_USER to prev_state
                                    // and set CONTEXT_KERNEL
5.3) Exception handler
5.4) exception_enter(prev_state) // restore CONTEXT_USER
5.5) Exception resumes
6) Task exits the kernel

The condition to live without exception_enter()/exception_exit() is to
forbid exceptions and IRQs between 2) and 3) and between 5) and 6), or if
any is allowed to trigger, it won't call into context tracking, eg: NMIs,
and it won't schedule. These requirements are met by architectures
supporting CONFIG_HAVE_CONTEXT_TRACKING_OFFSTACK and those can
therefore afford not to implement this hack.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20201117151637.259084-3-frederic@kernel.org
---
 include/linux/context_tracking.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h
index d53cd331c4dd..bceb06498521 100644
--- a/include/linux/context_tracking.h
+++ b/include/linux/context_tracking.h
@@ -51,7 +51,8 @@ static inline enum ctx_state exception_enter(void)
 {
 	enum ctx_state prev_ctx;
 
-	if (!context_tracking_enabled())
+	if (IS_ENABLED(CONFIG_HAVE_CONTEXT_TRACKING_OFFSTACK) ||
+	    !context_tracking_enabled())
 		return 0;
 
 	prev_ctx = this_cpu_read(context_tracking.state);
@@ -63,7 +64,8 @@ static inline enum ctx_state exception_enter(void)
 
 static inline void exception_exit(enum ctx_state prev_ctx)
 {
-	if (context_tracking_enabled()) {
+	if (!IS_ENABLED(CONFIG_HAVE_CONTEXT_TRACKING_OFFSTACK) &&
+	    context_tracking_enabled()) {
 		if (prev_ctx != CONTEXT_KERNEL)
 			context_tracking_enter(prev_ctx);
 	}
-- 
cgit v1.2.3


From 31f6a8c0a471be7d7d05c93eac50fcb729e79b9d Mon Sep 17 00:00:00 2001
From: Ionela Voinescu <ionela.voinescu@arm.com>
Date: Tue, 27 Oct 2020 18:07:11 +0000
Subject: sched/topology,schedutil: Wrap sched domains rebuild

Add the rebuild_sched_domains_energy() function to wrap the functionality
that rebuilds the scheduling domains if any of the Energy Aware Scheduling
(EAS) initialisation conditions change. This functionality is used when
schedutil is added or removed or when EAS is enabled or disabled
through the sched_energy_aware sysctl.

Therefore, create a single function that is used in both these cases and
that can be later reused.

Signed-off-by: Ionela Voinescu <ionela.voinescu@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Quentin Perret <qperret@google.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lkml.kernel.org/r/20201027180713.7642-2-ionela.voinescu@arm.com
---
 include/linux/sched/topology.h   |  8 ++++++++
 kernel/sched/cpufreq_schedutil.c |  9 +--------
 kernel/sched/topology.c          | 18 +++++++++++-------
 3 files changed, 20 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 9ef7bf686a9f..8f0f778b7c91 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -225,6 +225,14 @@ static inline bool cpus_share_cache(int this_cpu, int that_cpu)
 
 #endif	/* !CONFIG_SMP */
 
+#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
+extern void rebuild_sched_domains_energy(void);
+#else
+static inline void rebuild_sched_domains_energy(void)
+{
+}
+#endif
+
 #ifndef arch_scale_cpu_capacity
 /**
  * arch_scale_cpu_capacity - get the capacity scale factor of a given CPU.
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index e254745a82cb..37b303890336 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -899,16 +899,9 @@ struct cpufreq_governor *cpufreq_default_governor(void)
 cpufreq_governor_init(schedutil_gov);
 
 #ifdef CONFIG_ENERGY_MODEL
-extern bool sched_energy_update;
-extern struct mutex sched_energy_mutex;
-
 static void rebuild_sd_workfn(struct work_struct *work)
 {
-	mutex_lock(&sched_energy_mutex);
-	sched_energy_update = true;
-	rebuild_sched_domains();
-	sched_energy_update = false;
-	mutex_unlock(&sched_energy_mutex);
+	rebuild_sched_domains_energy();
 }
 static DECLARE_WORK(rebuild_sd_work, rebuild_sd_workfn);
 
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index b296c1c6b961..04d9ebfaedd6 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -211,6 +211,15 @@ unsigned int sysctl_sched_energy_aware = 1;
 DEFINE_MUTEX(sched_energy_mutex);
 bool sched_energy_update;
 
+void rebuild_sched_domains_energy(void)
+{
+	mutex_lock(&sched_energy_mutex);
+	sched_energy_update = true;
+	rebuild_sched_domains();
+	sched_energy_update = false;
+	mutex_unlock(&sched_energy_mutex);
+}
+
 #ifdef CONFIG_PROC_SYSCTL
 int sched_energy_aware_handler(struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
@@ -223,13 +232,8 @@ int sched_energy_aware_handler(struct ctl_table *table, int write,
 	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	if (!ret && write) {
 		state = static_branch_unlikely(&sched_energy_present);
-		if (state != sysctl_sched_energy_aware) {
-			mutex_lock(&sched_energy_mutex);
-			sched_energy_update = 1;
-			rebuild_sched_domains();
-			sched_energy_update = 0;
-			mutex_unlock(&sched_energy_mutex);
-		}
+		if (state != sysctl_sched_energy_aware)
+			rebuild_sched_domains_energy();
 	}
 
 	return ret;
-- 
cgit v1.2.3


From 25ece30561d247b2931b0d11d92e9c976a668771 Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Mon, 9 Nov 2020 17:34:05 +0100
Subject: rtc: nvmem: remove nvram ABI

The nvram sysfs attributes have been deprecated at least since v4.13, more
than 3 years ago and nobody ever complained about the deprecation warning.

Remove the sysfs attributes now.

[Bartosz: remove the declaration of rtc_nvmem_unregister()]

Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Link: https://lore.kernel.org/r/20201109163409.24301-5-brgl@bgdev.pl
---
 drivers/rtc/class.c        |  2 --
 drivers/rtc/nvmem.c        | 82 +---------------------------------------------
 drivers/rtc/rtc-cmos.c     |  1 -
 drivers/rtc/rtc-ds1305.c   |  1 -
 drivers/rtc/rtc-ds1307.c   |  1 -
 drivers/rtc/rtc-ds1343.c   |  1 -
 drivers/rtc/rtc-ds1511.c   |  2 --
 drivers/rtc/rtc-ds1553.c   |  1 -
 drivers/rtc/rtc-ds1685.c   |  1 -
 drivers/rtc/rtc-ds1742.c   |  1 -
 drivers/rtc/rtc-m48t59.c   |  1 -
 drivers/rtc/rtc-m48t86.c   |  1 -
 drivers/rtc/rtc-rp5c01.c   |  1 -
 drivers/rtc/rtc-rv8803.c   |  1 -
 drivers/rtc/rtc-stk17ta8.c |  1 -
 drivers/rtc/rtc-tx4939.c   |  1 -
 include/linux/rtc.h        |  6 ----
 17 files changed, 1 insertion(+), 104 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c
index 7c88d190c51f..a99b7d24b77c 100644
--- a/drivers/rtc/class.c
+++ b/drivers/rtc/class.c
@@ -339,8 +339,6 @@ static void devm_rtc_release_device(struct device *dev, void *res)
 {
 	struct rtc_device *rtc = *(struct rtc_device **)res;
 
-	rtc_nvmem_unregister(rtc);
-
 	if (rtc->registered)
 		rtc_device_unregister(rtc);
 	else
diff --git a/drivers/rtc/nvmem.c b/drivers/rtc/nvmem.c
index 4312096c7738..5e0b178a3b65 100644
--- a/drivers/rtc/nvmem.c
+++ b/drivers/rtc/nvmem.c
@@ -9,74 +9,7 @@
 #include <linux/types.h>
 #include <linux/nvmem-consumer.h>
 #include <linux/rtc.h>
-#include <linux/slab.h>
-#include <linux/sysfs.h>
 
-/*
- * Deprecated ABI compatibility, this should be removed at some point
- */
-
-static const char nvram_warning[] = "Deprecated ABI, please use nvmem";
-
-static ssize_t
-rtc_nvram_read(struct file *filp, struct kobject *kobj,
-	       struct bin_attribute *attr,
-	       char *buf, loff_t off, size_t count)
-{
-	dev_warn_once(kobj_to_dev(kobj), nvram_warning);
-
-	return nvmem_device_read(attr->private, off, count, buf);
-}
-
-static ssize_t
-rtc_nvram_write(struct file *filp, struct kobject *kobj,
-		struct bin_attribute *attr,
-		char *buf, loff_t off, size_t count)
-{
-	dev_warn_once(kobj_to_dev(kobj), nvram_warning);
-
-	return nvmem_device_write(attr->private, off, count, buf);
-}
-
-static int rtc_nvram_register(struct rtc_device *rtc,
-			      struct nvmem_device *nvmem, size_t size)
-{
-	int err;
-
-	rtc->nvram = kzalloc(sizeof(*rtc->nvram), GFP_KERNEL);
-	if (!rtc->nvram)
-		return -ENOMEM;
-
-	rtc->nvram->attr.name = "nvram";
-	rtc->nvram->attr.mode = 0644;
-	rtc->nvram->private = nvmem;
-
-	sysfs_bin_attr_init(rtc->nvram);
-
-	rtc->nvram->read = rtc_nvram_read;
-	rtc->nvram->write = rtc_nvram_write;
-	rtc->nvram->size = size;
-
-	err = sysfs_create_bin_file(&rtc->dev.parent->kobj,
-				    rtc->nvram);
-	if (err) {
-		kfree(rtc->nvram);
-		rtc->nvram = NULL;
-	}
-
-	return err;
-}
-
-static void rtc_nvram_unregister(struct rtc_device *rtc)
-{
-	sysfs_remove_bin_file(&rtc->dev.parent->kobj, rtc->nvram);
-	kfree(rtc->nvram);
-	rtc->nvram = NULL;
-}
-
-/*
- * New ABI, uses nvmem
- */
 int rtc_nvmem_register(struct rtc_device *rtc,
 		       struct nvmem_config *nvmem_config)
 {
@@ -88,20 +21,7 @@ int rtc_nvmem_register(struct rtc_device *rtc,
 	nvmem_config->dev = rtc->dev.parent;
 	nvmem_config->owner = rtc->owner;
 	nvmem = devm_nvmem_register(rtc->dev.parent, nvmem_config);
-	if (IS_ERR(nvmem))
-		return PTR_ERR(nvmem);
-
-	/* Register the old ABI */
-	if (rtc->nvram_old_abi)
-		rtc_nvram_register(rtc, nvmem, nvmem_config->size);
 
-	return 0;
+	return PTR_ERR_OR_ZERO(nvmem);
 }
 EXPORT_SYMBOL_GPL(rtc_nvmem_register);
-
-void rtc_nvmem_unregister(struct rtc_device *rtc)
-{
-	/* unregister the old ABI */
-	if (rtc->nvram)
-		rtc_nvram_unregister(rtc);
-}
diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index c633319cdb91..adca0de76e53 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -863,7 +863,6 @@ cmos_do_probe(struct device *dev, struct resource *ports, int rtc_irq)
 		cmos_rtc.rtc->ops = &cmos_rtc_ops_no_alarm;
 	}
 
-	cmos_rtc.rtc->nvram_old_abi = true;
 	retval = rtc_register_device(cmos_rtc.rtc);
 	if (retval)
 		goto cleanup2;
diff --git a/drivers/rtc/rtc-ds1305.c b/drivers/rtc/rtc-ds1305.c
index a3d790889eea..a1ed539d41b4 100644
--- a/drivers/rtc/rtc-ds1305.c
+++ b/drivers/rtc/rtc-ds1305.c
@@ -694,7 +694,6 @@ static int ds1305_probe(struct spi_device *spi)
 	ds1305->rtc->range_max = RTC_TIMESTAMP_END_2099;
 
 	ds1305_nvmem_cfg.priv = ds1305;
-	ds1305->rtc->nvram_old_abi = true;
 	status = rtc_register_device(ds1305->rtc);
 	if (status)
 		return status;
diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c
index fdf25db1b1b3..e359cbf7882b 100644
--- a/drivers/rtc/rtc-ds1307.c
+++ b/drivers/rtc/rtc-ds1307.c
@@ -2016,7 +2016,6 @@ static int ds1307_probe(struct i2c_client *client,
 			.priv = ds1307,
 		};
 
-		ds1307->rtc->nvram_old_abi = true;
 		rtc_nvmem_register(ds1307->rtc, &nvmem_cfg);
 	}
 
diff --git a/drivers/rtc/rtc-ds1343.c b/drivers/rtc/rtc-ds1343.c
index ba143423875b..e7604e844cbd 100644
--- a/drivers/rtc/rtc-ds1343.c
+++ b/drivers/rtc/rtc-ds1343.c
@@ -399,7 +399,6 @@ static int ds1343_probe(struct spi_device *spi)
 	if (IS_ERR(priv->rtc))
 		return PTR_ERR(priv->rtc);
 
-	priv->rtc->nvram_old_abi = true;
 	priv->rtc->ops = &ds1343_rtc_ops;
 	priv->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	priv->rtc->range_max = RTC_TIMESTAMP_END_2099;
diff --git a/drivers/rtc/rtc-ds1511.c b/drivers/rtc/rtc-ds1511.c
index a63872c4c76d..33c483d759c8 100644
--- a/drivers/rtc/rtc-ds1511.c
+++ b/drivers/rtc/rtc-ds1511.c
@@ -466,8 +466,6 @@ static int ds1511_rtc_probe(struct platform_device *pdev)
 
 	pdata->rtc->ops = &ds1511_rtc_ops;
 
-	pdata->rtc->nvram_old_abi = true;
-
 	ret = rtc_register_device(pdata->rtc);
 	if (ret)
 		return ret;
diff --git a/drivers/rtc/rtc-ds1553.c b/drivers/rtc/rtc-ds1553.c
index cdf5e05b9489..c6a5563504e5 100644
--- a/drivers/rtc/rtc-ds1553.c
+++ b/drivers/rtc/rtc-ds1553.c
@@ -294,7 +294,6 @@ static int ds1553_rtc_probe(struct platform_device *pdev)
 		return PTR_ERR(pdata->rtc);
 
 	pdata->rtc->ops = &ds1553_rtc_ops;
-	pdata->rtc->nvram_old_abi = true;
 
 	ret = rtc_register_device(pdata->rtc);
 	if (ret)
diff --git a/drivers/rtc/rtc-ds1685.c b/drivers/rtc/rtc-ds1685.c
index dfbd7b88b2b9..9043c96e8845 100644
--- a/drivers/rtc/rtc-ds1685.c
+++ b/drivers/rtc/rtc-ds1685.c
@@ -1316,7 +1316,6 @@ ds1685_rtc_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	rtc_dev->nvram_old_abi = true;
 	nvmem_cfg.priv = rtc;
 	ret = rtc_nvmem_register(rtc_dev, &nvmem_cfg);
 	if (ret)
diff --git a/drivers/rtc/rtc-ds1742.c b/drivers/rtc/rtc-ds1742.c
index 2b949f0dbaa9..291bbed90ef8 100644
--- a/drivers/rtc/rtc-ds1742.c
+++ b/drivers/rtc/rtc-ds1742.c
@@ -190,7 +190,6 @@ static int ds1742_rtc_probe(struct platform_device *pdev)
 		return PTR_ERR(rtc);
 
 	rtc->ops = &ds1742_rtc_ops;
-	rtc->nvram_old_abi = true;
 
 	ret = rtc_register_device(rtc);
 	if (ret)
diff --git a/drivers/rtc/rtc-m48t59.c b/drivers/rtc/rtc-m48t59.c
index 67e218758a8b..ee1d8f0146fd 100644
--- a/drivers/rtc/rtc-m48t59.c
+++ b/drivers/rtc/rtc-m48t59.c
@@ -463,7 +463,6 @@ static int m48t59_rtc_probe(struct platform_device *pdev)
 	if (IS_ERR(m48t59->rtc))
 		return PTR_ERR(m48t59->rtc);
 
-	m48t59->rtc->nvram_old_abi = true;
 	m48t59->rtc->ops = ops;
 
 	nvmem_cfg.size = pdata->offset;
diff --git a/drivers/rtc/rtc-m48t86.c b/drivers/rtc/rtc-m48t86.c
index 75a0e73071d8..2b1135590dd5 100644
--- a/drivers/rtc/rtc-m48t86.c
+++ b/drivers/rtc/rtc-m48t86.c
@@ -254,7 +254,6 @@ static int m48t86_rtc_probe(struct platform_device *pdev)
 		return PTR_ERR(info->rtc);
 
 	info->rtc->ops = &m48t86_rtc_ops;
-	info->rtc->nvram_old_abi = true;
 
 	err = rtc_register_device(info->rtc);
 	if (err)
diff --git a/drivers/rtc/rtc-rp5c01.c b/drivers/rtc/rtc-rp5c01.c
index 8776eadbdd3a..a69e8adcc4a1 100644
--- a/drivers/rtc/rtc-rp5c01.c
+++ b/drivers/rtc/rtc-rp5c01.c
@@ -251,7 +251,6 @@ static int __init rp5c01_rtc_probe(struct platform_device *dev)
 		return PTR_ERR(rtc);
 
 	rtc->ops = &rp5c01_rtc_ops;
-	rtc->nvram_old_abi = true;
 
 	priv->rtc = rtc;
 
diff --git a/drivers/rtc/rtc-rv8803.c b/drivers/rtc/rtc-rv8803.c
index c6d8e3425688..1d888da48c7c 100644
--- a/drivers/rtc/rtc-rv8803.c
+++ b/drivers/rtc/rtc-rv8803.c
@@ -585,7 +585,6 @@ static int rv8803_probe(struct i2c_client *client,
 	}
 
 	rv8803->rtc->ops = &rv8803_rtc_ops;
-	rv8803->rtc->nvram_old_abi = true;
 	rv8803->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	rv8803->rtc->range_max = RTC_TIMESTAMP_END_2099;
 	err = rtc_register_device(rv8803->rtc);
diff --git a/drivers/rtc/rtc-stk17ta8.c b/drivers/rtc/rtc-stk17ta8.c
index 01a45044f468..1ccf0d5d05b4 100644
--- a/drivers/rtc/rtc-stk17ta8.c
+++ b/drivers/rtc/rtc-stk17ta8.c
@@ -311,7 +311,6 @@ static int stk17ta8_rtc_probe(struct platform_device *pdev)
 		return PTR_ERR(pdata->rtc);
 
 	pdata->rtc->ops = &stk17ta8_rtc_ops;
-	pdata->rtc->nvram_old_abi = true;
 
 	nvmem_cfg.priv = pdata;
 	ret = rtc_nvmem_register(pdata->rtc, &nvmem_cfg);
diff --git a/drivers/rtc/rtc-tx4939.c b/drivers/rtc/rtc-tx4939.c
index 715b82981279..abbb62b14d7a 100644
--- a/drivers/rtc/rtc-tx4939.c
+++ b/drivers/rtc/rtc-tx4939.c
@@ -266,7 +266,6 @@ static int __init tx4939_rtc_probe(struct platform_device *pdev)
 		return PTR_ERR(rtc);
 
 	rtc->ops = &tx4939_rtc_ops;
-	rtc->nvram_old_abi = true;
 	rtc->range_max = U32_MAX;
 
 	pdata->rtc = rtc;
diff --git a/include/linux/rtc.h b/include/linux/rtc.h
index 22d1575e4991..0983ab9faffb 100644
--- a/include/linux/rtc.h
+++ b/include/linux/rtc.h
@@ -120,10 +120,6 @@ struct rtc_device {
 
 	bool registered;
 
-	/* Old ABI support */
-	bool nvram_old_abi;
-	struct bin_attribute *nvram;
-
 	time64_t range_min;
 	timeu64_t range_max;
 	time64_t start_secs;
@@ -250,14 +246,12 @@ extern int rtc_hctosys_ret;
 #ifdef CONFIG_RTC_NVMEM
 int rtc_nvmem_register(struct rtc_device *rtc,
 		       struct nvmem_config *nvmem_config);
-void rtc_nvmem_unregister(struct rtc_device *rtc);
 #else
 static inline int rtc_nvmem_register(struct rtc_device *rtc,
 				     struct nvmem_config *nvmem_config)
 {
 	return 0;
 }
-static inline void rtc_nvmem_unregister(struct rtc_device *rtc) {}
 #endif
 
 #ifdef CONFIG_RTC_INTF_SYSFS
-- 
cgit v1.2.3


From 3a905c2d9544a418953d6c18668f0f853fbd9be9 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Mon, 9 Nov 2020 17:34:06 +0100
Subject: rtc: add devm_ prefix to rtc_nvmem_register()

rtc_nvmem_register() is a managed interface. It doesn't require any
release function to be called at driver detach. To avoid confusing
driver authors, let's rename it to devm_rtc_nvmem_register() and add it
to the list of managed interfaces in Documentation/.

Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Link: https://lore.kernel.org/r/20201109163409.24301-6-brgl@bgdev.pl
---
 Documentation/driver-api/driver-model/devres.rst | 1 +
 drivers/rtc/nvmem.c                              | 4 ++--
 drivers/rtc/rtc-cmos.c                           | 2 +-
 drivers/rtc/rtc-ds1305.c                         | 2 +-
 drivers/rtc/rtc-ds1307.c                         | 2 +-
 drivers/rtc/rtc-ds1343.c                         | 2 +-
 drivers/rtc/rtc-ds1511.c                         | 2 +-
 drivers/rtc/rtc-ds1553.c                         | 2 +-
 drivers/rtc/rtc-ds1685.c                         | 2 +-
 drivers/rtc/rtc-ds1742.c                         | 2 +-
 drivers/rtc/rtc-ds3232.c                         | 2 +-
 drivers/rtc/rtc-isl12026.c                       | 2 +-
 drivers/rtc/rtc-isl1208.c                        | 2 +-
 drivers/rtc/rtc-m48t59.c                         | 2 +-
 drivers/rtc/rtc-m48t86.c                         | 2 +-
 drivers/rtc/rtc-meson.c                          | 2 +-
 drivers/rtc/rtc-omap.c                           | 2 +-
 drivers/rtc/rtc-pcf2127.c                        | 2 +-
 drivers/rtc/rtc-pcf85063.c                       | 2 +-
 drivers/rtc/rtc-pcf85363.c                       | 2 +-
 drivers/rtc/rtc-rp5c01.c                         | 2 +-
 drivers/rtc/rtc-rv3028.c                         | 4 ++--
 drivers/rtc/rtc-rv3029c2.c                       | 2 +-
 drivers/rtc/rtc-rv3032.c                         | 4 ++--
 drivers/rtc/rtc-rv8803.c                         | 2 +-
 drivers/rtc/rtc-rx8581.c                         | 2 +-
 drivers/rtc/rtc-stk17ta8.c                       | 2 +-
 drivers/rtc/rtc-tx4939.c                         | 2 +-
 include/linux/rtc.h                              | 8 ++++----
 29 files changed, 35 insertions(+), 34 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/driver-api/driver-model/devres.rst b/Documentation/driver-api/driver-model/devres.rst
index 6ffc0f07404f..5df7ba54a4ba 100644
--- a/Documentation/driver-api/driver-model/devres.rst
+++ b/Documentation/driver-api/driver-model/devres.rst
@@ -414,6 +414,7 @@ RESET
 RTC
   devm_rtc_device_register()
   devm_rtc_allocate_device()
+  devm_rtc_nvmem_register()
 
 SERDEV
   devm_serdev_device_open()
diff --git a/drivers/rtc/nvmem.c b/drivers/rtc/nvmem.c
index 5e0b178a3b65..7502deb6390e 100644
--- a/drivers/rtc/nvmem.c
+++ b/drivers/rtc/nvmem.c
@@ -10,7 +10,7 @@
 #include <linux/nvmem-consumer.h>
 #include <linux/rtc.h>
 
-int rtc_nvmem_register(struct rtc_device *rtc,
+int devm_rtc_nvmem_register(struct rtc_device *rtc,
 		       struct nvmem_config *nvmem_config)
 {
 	struct nvmem_device *nvmem;
@@ -24,4 +24,4 @@ int rtc_nvmem_register(struct rtc_device *rtc,
 
 	return PTR_ERR_OR_ZERO(nvmem);
 }
-EXPORT_SYMBOL_GPL(rtc_nvmem_register);
+EXPORT_SYMBOL_GPL(devm_rtc_nvmem_register);
diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index adca0de76e53..eea91c1538aa 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -869,7 +869,7 @@ cmos_do_probe(struct device *dev, struct resource *ports, int rtc_irq)
 
 	/* export at least the first block of NVRAM */
 	nvmem_cfg.size = address_space - NVRAM_OFFSET;
-	if (rtc_nvmem_register(cmos_rtc.rtc, &nvmem_cfg))
+	if (devm_rtc_nvmem_register(cmos_rtc.rtc, &nvmem_cfg))
 		dev_err(dev, "nvmem registration failed\n");
 
 	dev_info(dev, "%s%s, %d bytes nvram%s\n",
diff --git a/drivers/rtc/rtc-ds1305.c b/drivers/rtc/rtc-ds1305.c
index a1ed539d41b4..a4e768261b43 100644
--- a/drivers/rtc/rtc-ds1305.c
+++ b/drivers/rtc/rtc-ds1305.c
@@ -698,7 +698,7 @@ static int ds1305_probe(struct spi_device *spi)
 	if (status)
 		return status;
 
-	rtc_nvmem_register(ds1305->rtc, &ds1305_nvmem_cfg);
+	devm_rtc_nvmem_register(ds1305->rtc, &ds1305_nvmem_cfg);
 
 	/* Maybe set up alarm IRQ; be ready to handle it triggering right
 	 * away.  NOTE that we don't share this.  The signal is active low,
diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c
index e359cbf7882b..216bc5d9b716 100644
--- a/drivers/rtc/rtc-ds1307.c
+++ b/drivers/rtc/rtc-ds1307.c
@@ -2016,7 +2016,7 @@ static int ds1307_probe(struct i2c_client *client,
 			.priv = ds1307,
 		};
 
-		rtc_nvmem_register(ds1307->rtc, &nvmem_cfg);
+		devm_rtc_nvmem_register(ds1307->rtc, &nvmem_cfg);
 	}
 
 	ds1307_hwmon_register(ds1307);
diff --git a/drivers/rtc/rtc-ds1343.c b/drivers/rtc/rtc-ds1343.c
index e7604e844cbd..ea663e24a34c 100644
--- a/drivers/rtc/rtc-ds1343.c
+++ b/drivers/rtc/rtc-ds1343.c
@@ -413,7 +413,7 @@ static int ds1343_probe(struct spi_device *spi)
 		return res;
 
 	nvmem_cfg.priv = priv;
-	rtc_nvmem_register(priv->rtc, &nvmem_cfg);
+	devm_rtc_nvmem_register(priv->rtc, &nvmem_cfg);
 
 	priv->irq = spi->irq;
 
diff --git a/drivers/rtc/rtc-ds1511.c b/drivers/rtc/rtc-ds1511.c
index 33c483d759c8..d5f48216e851 100644
--- a/drivers/rtc/rtc-ds1511.c
+++ b/drivers/rtc/rtc-ds1511.c
@@ -470,7 +470,7 @@ static int ds1511_rtc_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	rtc_nvmem_register(pdata->rtc, &ds1511_nvmem_cfg);
+	devm_rtc_nvmem_register(pdata->rtc, &ds1511_nvmem_cfg);
 
 	/*
 	 * if the platform has an interrupt in mind for this device,
diff --git a/drivers/rtc/rtc-ds1553.c b/drivers/rtc/rtc-ds1553.c
index c6a5563504e5..2d2eb739d92b 100644
--- a/drivers/rtc/rtc-ds1553.c
+++ b/drivers/rtc/rtc-ds1553.c
@@ -309,7 +309,7 @@ static int ds1553_rtc_probe(struct platform_device *pdev)
 		}
 	}
 
-	if (rtc_nvmem_register(pdata->rtc, &nvmem_cfg))
+	if (devm_rtc_nvmem_register(pdata->rtc, &nvmem_cfg))
 		dev_err(&pdev->dev, "unable to register nvmem\n");
 
 	return 0;
diff --git a/drivers/rtc/rtc-ds1685.c b/drivers/rtc/rtc-ds1685.c
index 9043c96e8845..bef588fce266 100644
--- a/drivers/rtc/rtc-ds1685.c
+++ b/drivers/rtc/rtc-ds1685.c
@@ -1317,7 +1317,7 @@ ds1685_rtc_probe(struct platform_device *pdev)
 		return ret;
 
 	nvmem_cfg.priv = rtc;
-	ret = rtc_nvmem_register(rtc_dev, &nvmem_cfg);
+	ret = devm_rtc_nvmem_register(rtc_dev, &nvmem_cfg);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-ds1742.c b/drivers/rtc/rtc-ds1742.c
index 291bbed90ef8..29792a8cce97 100644
--- a/drivers/rtc/rtc-ds1742.c
+++ b/drivers/rtc/rtc-ds1742.c
@@ -195,7 +195,7 @@ static int ds1742_rtc_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	if (rtc_nvmem_register(rtc, &nvmem_cfg))
+	if (devm_rtc_nvmem_register(rtc, &nvmem_cfg))
 		dev_err(&pdev->dev, "Unable to register nvmem\n");
 
 	return 0;
diff --git a/drivers/rtc/rtc-ds3232.c b/drivers/rtc/rtc-ds3232.c
index 69c37ab64352..16b89035d135 100644
--- a/drivers/rtc/rtc-ds3232.c
+++ b/drivers/rtc/rtc-ds3232.c
@@ -518,7 +518,7 @@ static int ds3232_probe(struct device *dev, struct regmap *regmap, int irq,
 	if (IS_ERR(ds3232->rtc))
 		return PTR_ERR(ds3232->rtc);
 
-	ret = rtc_nvmem_register(ds3232->rtc, &nvmem_cfg);
+	ret = devm_rtc_nvmem_register(ds3232->rtc, &nvmem_cfg);
 	if(ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-isl12026.c b/drivers/rtc/rtc-isl12026.c
index 5b6b17fb6d62..fff8d8253669 100644
--- a/drivers/rtc/rtc-isl12026.c
+++ b/drivers/rtc/rtc-isl12026.c
@@ -465,7 +465,7 @@ static int isl12026_probe_new(struct i2c_client *client)
 
 	priv->rtc->ops = &isl12026_rtc_ops;
 	nvm_cfg.priv = priv;
-	ret = rtc_nvmem_register(priv->rtc, &nvm_cfg);
+	ret = devm_rtc_nvmem_register(priv->rtc, &nvm_cfg);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-isl1208.c b/drivers/rtc/rtc-isl1208.c
index ebb691fa48a6..08d778b10e9e 100644
--- a/drivers/rtc/rtc-isl1208.c
+++ b/drivers/rtc/rtc-isl1208.c
@@ -890,7 +890,7 @@ isl1208_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	if (rc)
 		return rc;
 
-	rc = rtc_nvmem_register(isl1208->rtc, &isl1208->nvmem_config);
+	rc = devm_rtc_nvmem_register(isl1208->rtc, &isl1208->nvmem_config);
 	if (rc)
 		return rc;
 
diff --git a/drivers/rtc/rtc-m48t59.c b/drivers/rtc/rtc-m48t59.c
index ee1d8f0146fd..e966a66ab2d3 100644
--- a/drivers/rtc/rtc-m48t59.c
+++ b/drivers/rtc/rtc-m48t59.c
@@ -466,7 +466,7 @@ static int m48t59_rtc_probe(struct platform_device *pdev)
 	m48t59->rtc->ops = ops;
 
 	nvmem_cfg.size = pdata->offset;
-	ret = rtc_nvmem_register(m48t59->rtc, &nvmem_cfg);
+	ret = devm_rtc_nvmem_register(m48t59->rtc, &nvmem_cfg);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-m48t86.c b/drivers/rtc/rtc-m48t86.c
index 2b1135590dd5..182cfe59e4e0 100644
--- a/drivers/rtc/rtc-m48t86.c
+++ b/drivers/rtc/rtc-m48t86.c
@@ -259,7 +259,7 @@ static int m48t86_rtc_probe(struct platform_device *pdev)
 	if (err)
 		return err;
 
-	rtc_nvmem_register(info->rtc, &m48t86_nvmem_cfg);
+	devm_rtc_nvmem_register(info->rtc, &m48t86_nvmem_cfg);
 
 	/* read battery status */
 	reg = m48t86_readb(&pdev->dev, M48T86_D);
diff --git a/drivers/rtc/rtc-meson.c b/drivers/rtc/rtc-meson.c
index 47ebcf834cc2..938267713a4d 100644
--- a/drivers/rtc/rtc-meson.c
+++ b/drivers/rtc/rtc-meson.c
@@ -365,7 +365,7 @@ static int meson_rtc_probe(struct platform_device *pdev)
 	}
 
 	meson_rtc_nvmem_config.priv = rtc;
-	ret = rtc_nvmem_register(rtc->rtc, &meson_rtc_nvmem_config);
+	ret = devm_rtc_nvmem_register(rtc->rtc, &meson_rtc_nvmem_config);
 	if (ret)
 		goto out_disable_vdd;
 
diff --git a/drivers/rtc/rtc-omap.c b/drivers/rtc/rtc-omap.c
index 606fa80ad6e0..e65f79fc7718 100644
--- a/drivers/rtc/rtc-omap.c
+++ b/drivers/rtc/rtc-omap.c
@@ -890,7 +890,7 @@ static int omap_rtc_probe(struct platform_device *pdev)
 	if (ret)
 		goto err;
 
-	rtc_nvmem_register(rtc->rtc, &omap_rtc_nvmem_config);
+	devm_rtc_nvmem_register(rtc->rtc, &omap_rtc_nvmem_config);
 
 	if (rtc->is_pmic_controller) {
 		if (!pm_power_off) {
diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index fd46860152e1..432cd627359b 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -608,7 +608,7 @@ static int pcf2127_probe(struct device *dev, struct regmap *regmap,
 			.size = 512,
 		};
 
-		ret = rtc_nvmem_register(pcf2127->rtc, &nvmem_cfg);
+		ret = devm_rtc_nvmem_register(pcf2127->rtc, &nvmem_cfg);
 	}
 
 	/*
diff --git a/drivers/rtc/rtc-pcf85063.c b/drivers/rtc/rtc-pcf85063.c
index f8b99cb72959..c19f139e9b8d 100644
--- a/drivers/rtc/rtc-pcf85063.c
+++ b/drivers/rtc/rtc-pcf85063.c
@@ -607,7 +607,7 @@ static int pcf85063_probe(struct i2c_client *client)
 	}
 
 	nvmem_cfg.priv = pcf85063->regmap;
-	rtc_nvmem_register(pcf85063->rtc, &nvmem_cfg);
+	devm_rtc_nvmem_register(pcf85063->rtc, &nvmem_cfg);
 
 #ifdef CONFIG_COMMON_CLK
 	/* register clk in common clk framework */
diff --git a/drivers/rtc/rtc-pcf85363.c b/drivers/rtc/rtc-pcf85363.c
index 3450d615974d..23cf14ca2c96 100644
--- a/drivers/rtc/rtc-pcf85363.c
+++ b/drivers/rtc/rtc-pcf85363.c
@@ -422,7 +422,7 @@ static int pcf85363_probe(struct i2c_client *client,
 
 	for (i = 0; i < config->num_nvram; i++) {
 		nvmem_cfg[i].priv = pcf85363;
-		rtc_nvmem_register(pcf85363->rtc, &nvmem_cfg[i]);
+		devm_rtc_nvmem_register(pcf85363->rtc, &nvmem_cfg[i]);
 	}
 
 	return ret;
diff --git a/drivers/rtc/rtc-rp5c01.c b/drivers/rtc/rtc-rp5c01.c
index a69e8adcc4a1..8bc476c0905f 100644
--- a/drivers/rtc/rtc-rp5c01.c
+++ b/drivers/rtc/rtc-rp5c01.c
@@ -255,7 +255,7 @@ static int __init rp5c01_rtc_probe(struct platform_device *dev)
 	priv->rtc = rtc;
 
 	nvmem_cfg.priv = priv;
-	error = rtc_nvmem_register(rtc, &nvmem_cfg);
+	error = devm_rtc_nvmem_register(rtc, &nvmem_cfg);
 	if (error)
 		return error;
 
diff --git a/drivers/rtc/rtc-rv3028.c b/drivers/rtc/rtc-rv3028.c
index fa226f0fe67d..f788df979750 100644
--- a/drivers/rtc/rtc-rv3028.c
+++ b/drivers/rtc/rtc-rv3028.c
@@ -891,9 +891,9 @@ static int rv3028_probe(struct i2c_client *client)
 		return ret;
 
 	nvmem_cfg.priv = rv3028->regmap;
-	rtc_nvmem_register(rv3028->rtc, &nvmem_cfg);
+	devm_rtc_nvmem_register(rv3028->rtc, &nvmem_cfg);
 	eeprom_cfg.priv = rv3028;
-	rtc_nvmem_register(rv3028->rtc, &eeprom_cfg);
+	devm_rtc_nvmem_register(rv3028->rtc, &eeprom_cfg);
 
 	rv3028->rtc->max_user_freq = 1;
 
diff --git a/drivers/rtc/rtc-rv3029c2.c b/drivers/rtc/rtc-rv3029c2.c
index 62718231731b..ad359b3b74b2 100644
--- a/drivers/rtc/rtc-rv3029c2.c
+++ b/drivers/rtc/rtc-rv3029c2.c
@@ -755,7 +755,7 @@ static int rv3029_probe(struct device *dev, struct regmap *regmap, int irq,
 		return rc;
 
 	nvmem_cfg.priv = rv3029->regmap;
-	rtc_nvmem_register(rv3029->rtc, &nvmem_cfg);
+	devm_rtc_nvmem_register(rv3029->rtc, &nvmem_cfg);
 
 	return 0;
 }
diff --git a/drivers/rtc/rtc-rv3032.c b/drivers/rtc/rtc-rv3032.c
index 14e931d6f9c6..ed9cba3292e6 100644
--- a/drivers/rtc/rtc-rv3032.c
+++ b/drivers/rtc/rtc-rv3032.c
@@ -890,9 +890,9 @@ static int rv3032_probe(struct i2c_client *client)
 		return ret;
 
 	nvmem_cfg.priv = rv3032->regmap;
-	rtc_nvmem_register(rv3032->rtc, &nvmem_cfg);
+	devm_rtc_nvmem_register(rv3032->rtc, &nvmem_cfg);
 	eeprom_cfg.priv = rv3032;
-	rtc_nvmem_register(rv3032->rtc, &eeprom_cfg);
+	devm_rtc_nvmem_register(rv3032->rtc, &eeprom_cfg);
 
 	rv3032->rtc->max_user_freq = 1;
 
diff --git a/drivers/rtc/rtc-rv8803.c b/drivers/rtc/rtc-rv8803.c
index 1d888da48c7c..44e1818a751c 100644
--- a/drivers/rtc/rtc-rv8803.c
+++ b/drivers/rtc/rtc-rv8803.c
@@ -591,7 +591,7 @@ static int rv8803_probe(struct i2c_client *client,
 	if (err)
 		return err;
 
-	rtc_nvmem_register(rv8803->rtc, &nvmem_cfg);
+	devm_rtc_nvmem_register(rv8803->rtc, &nvmem_cfg);
 
 	rv8803->rtc->max_user_freq = 1;
 
diff --git a/drivers/rtc/rtc-rx8581.c b/drivers/rtc/rtc-rx8581.c
index 490f70f57636..017f74721cc0 100644
--- a/drivers/rtc/rtc-rx8581.c
+++ b/drivers/rtc/rtc-rx8581.c
@@ -302,7 +302,7 @@ static int rx8581_probe(struct i2c_client *client,
 
 	for (i = 0; i < config->num_nvram; i++) {
 		nvmem_cfg[i].priv = rx8581;
-		rtc_nvmem_register(rx8581->rtc, &nvmem_cfg[i]);
+		devm_rtc_nvmem_register(rx8581->rtc, &nvmem_cfg[i]);
 	}
 
 	return ret;
diff --git a/drivers/rtc/rtc-stk17ta8.c b/drivers/rtc/rtc-stk17ta8.c
index 1ccf0d5d05b4..ad616bce7bca 100644
--- a/drivers/rtc/rtc-stk17ta8.c
+++ b/drivers/rtc/rtc-stk17ta8.c
@@ -313,7 +313,7 @@ static int stk17ta8_rtc_probe(struct platform_device *pdev)
 	pdata->rtc->ops = &stk17ta8_rtc_ops;
 
 	nvmem_cfg.priv = pdata;
-	ret = rtc_nvmem_register(pdata->rtc, &nvmem_cfg);
+	ret = devm_rtc_nvmem_register(pdata->rtc, &nvmem_cfg);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-tx4939.c b/drivers/rtc/rtc-tx4939.c
index abbb62b14d7a..11f46272bad3 100644
--- a/drivers/rtc/rtc-tx4939.c
+++ b/drivers/rtc/rtc-tx4939.c
@@ -271,7 +271,7 @@ static int __init tx4939_rtc_probe(struct platform_device *pdev)
 	pdata->rtc = rtc;
 
 	nvmem_cfg.priv = pdata;
-	ret = rtc_nvmem_register(rtc, &nvmem_cfg);
+	ret = devm_rtc_nvmem_register(rtc, &nvmem_cfg);
 	if (ret)
 		return ret;
 
diff --git a/include/linux/rtc.h b/include/linux/rtc.h
index 0983ab9faffb..cbca651d8ca4 100644
--- a/include/linux/rtc.h
+++ b/include/linux/rtc.h
@@ -244,11 +244,11 @@ extern int rtc_hctosys_ret;
 #endif
 
 #ifdef CONFIG_RTC_NVMEM
-int rtc_nvmem_register(struct rtc_device *rtc,
-		       struct nvmem_config *nvmem_config);
+int devm_rtc_nvmem_register(struct rtc_device *rtc,
+			    struct nvmem_config *nvmem_config);
 #else
-static inline int rtc_nvmem_register(struct rtc_device *rtc,
-				     struct nvmem_config *nvmem_config)
+static inline int devm_rtc_nvmem_register(struct rtc_device *rtc,
+					  struct nvmem_config *nvmem_config)
 {
 	return 0;
 }
-- 
cgit v1.2.3


From fdcfd854333be5b30377dc5daa9cd0fa1643a979 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Mon, 9 Nov 2020 17:34:08 +0100
Subject: rtc: rework rtc_register_device() resource management

rtc_register_device() is a managed interface but it doesn't use devres
by itself - instead it marks an rtc_device as "registered" and the devres
callback for devm_rtc_allocate_device() takes care of resource release.

This doesn't correspond with the design behind devres where managed
structures should not be aware of being managed. The correct solution
here is to register a separate devres callback for unregistering the
device.

While at it: rename rtc_register_device() to devm_rtc_register_device()
and add it to the list of managed interfaces in devres.rst. This way we
can avoid any potential confusion of driver developers who may expect
there to exist a corresponding unregister function.

Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Link: https://lore.kernel.org/r/20201109163409.24301-8-brgl@bgdev.pl
---
 Documentation/driver-api/driver-model/devres.rst |  1 +
 arch/alpha/kernel/rtc.c                          |  2 +-
 drivers/mfd/menelaus.c                           |  2 +-
 drivers/rtc/class.c                              | 19 +++++++++----------
 drivers/rtc/rtc-88pm80x.c                        |  2 +-
 drivers/rtc/rtc-88pm860x.c                       |  2 +-
 drivers/rtc/rtc-ab-b5ze-s3.c                     |  2 +-
 drivers/rtc/rtc-ab-eoz9.c                        |  2 +-
 drivers/rtc/rtc-ab3100.c                         |  2 +-
 drivers/rtc/rtc-ab8500.c                         |  2 +-
 drivers/rtc/rtc-abx80x.c                         |  2 +-
 drivers/rtc/rtc-ac100.c                          |  2 +-
 drivers/rtc/rtc-armada38x.c                      |  2 +-
 drivers/rtc/rtc-aspeed.c                         |  2 +-
 drivers/rtc/rtc-at91rm9200.c                     |  2 +-
 drivers/rtc/rtc-at91sam9.c                       |  2 +-
 drivers/rtc/rtc-au1xxx.c                         |  2 +-
 drivers/rtc/rtc-bd70528.c                        |  2 +-
 drivers/rtc/rtc-brcmstb-waketimer.c              |  2 +-
 drivers/rtc/rtc-cadence.c                        |  2 +-
 drivers/rtc/rtc-cmos.c                           |  2 +-
 drivers/rtc/rtc-coh901331.c                      |  2 +-
 drivers/rtc/rtc-cpcap.c                          |  2 +-
 drivers/rtc/rtc-cros-ec.c                        |  2 +-
 drivers/rtc/rtc-da9052.c                         |  2 +-
 drivers/rtc/rtc-da9063.c                         |  2 +-
 drivers/rtc/rtc-davinci.c                        |  2 +-
 drivers/rtc/rtc-digicolor.c                      |  2 +-
 drivers/rtc/rtc-dm355evm.c                       |  2 +-
 drivers/rtc/rtc-ds1305.c                         |  2 +-
 drivers/rtc/rtc-ds1307.c                         |  2 +-
 drivers/rtc/rtc-ds1343.c                         |  2 +-
 drivers/rtc/rtc-ds1347.c                         |  2 +-
 drivers/rtc/rtc-ds1374.c                         |  2 +-
 drivers/rtc/rtc-ds1511.c                         |  2 +-
 drivers/rtc/rtc-ds1553.c                         |  2 +-
 drivers/rtc/rtc-ds1672.c                         |  2 +-
 drivers/rtc/rtc-ds1685.c                         |  2 +-
 drivers/rtc/rtc-ds1742.c                         |  2 +-
 drivers/rtc/rtc-ds2404.c                         |  2 +-
 drivers/rtc/rtc-ep93xx.c                         |  2 +-
 drivers/rtc/rtc-fsl-ftm-alarm.c                  |  2 +-
 drivers/rtc/rtc-ftrtc010.c                       |  2 +-
 drivers/rtc/rtc-goldfish.c                       |  2 +-
 drivers/rtc/rtc-imx-sc.c                         |  2 +-
 drivers/rtc/rtc-imxdi.c                          |  2 +-
 drivers/rtc/rtc-isl12026.c                       |  2 +-
 drivers/rtc/rtc-isl1208.c                        |  2 +-
 drivers/rtc/rtc-jz4740.c                         |  2 +-
 drivers/rtc/rtc-lpc32xx.c                        |  2 +-
 drivers/rtc/rtc-ls1x.c                           |  2 +-
 drivers/rtc/rtc-m41t80.c                         |  2 +-
 drivers/rtc/rtc-m48t59.c                         |  2 +-
 drivers/rtc/rtc-m48t86.c                         |  2 +-
 drivers/rtc/rtc-mc13xxx.c                        |  2 +-
 drivers/rtc/rtc-meson-vrtc.c                     |  2 +-
 drivers/rtc/rtc-meson.c                          |  2 +-
 drivers/rtc/rtc-mpc5121.c                        |  2 +-
 drivers/rtc/rtc-mrst.c                           |  2 +-
 drivers/rtc/rtc-mt2712.c                         |  2 +-
 drivers/rtc/rtc-mt6397.c                         |  2 +-
 drivers/rtc/rtc-mv.c                             |  2 +-
 drivers/rtc/rtc-mxc.c                            |  2 +-
 drivers/rtc/rtc-mxc_v2.c                         |  2 +-
 drivers/rtc/rtc-omap.c                           |  2 +-
 drivers/rtc/rtc-pcap.c                           |  2 +-
 drivers/rtc/rtc-pcf2123.c                        |  2 +-
 drivers/rtc/rtc-pcf2127.c                        |  2 +-
 drivers/rtc/rtc-pcf85063.c                       |  2 +-
 drivers/rtc/rtc-pcf85363.c                       |  2 +-
 drivers/rtc/rtc-pcf8563.c                        |  2 +-
 drivers/rtc/rtc-pic32.c                          |  2 +-
 drivers/rtc/rtc-pl030.c                          |  2 +-
 drivers/rtc/rtc-pl031.c                          |  2 +-
 drivers/rtc/rtc-pm8xxx.c                         |  2 +-
 drivers/rtc/rtc-ps3.c                            |  2 +-
 drivers/rtc/rtc-r9701.c                          |  2 +-
 drivers/rtc/rtc-rc5t619.c                        |  2 +-
 drivers/rtc/rtc-rk808.c                          |  2 +-
 drivers/rtc/rtc-rp5c01.c                         |  2 +-
 drivers/rtc/rtc-rs5c348.c                        |  2 +-
 drivers/rtc/rtc-rv3028.c                         |  2 +-
 drivers/rtc/rtc-rv3029c2.c                       |  2 +-
 drivers/rtc/rtc-rv3032.c                         |  2 +-
 drivers/rtc/rtc-rv8803.c                         |  2 +-
 drivers/rtc/rtc-rx8010.c                         |  2 +-
 drivers/rtc/rtc-rx8581.c                         |  2 +-
 drivers/rtc/rtc-s35390a.c                        |  2 +-
 drivers/rtc/rtc-sa1100.c                         |  2 +-
 drivers/rtc/rtc-sc27xx.c                         |  2 +-
 drivers/rtc/rtc-sd3078.c                         |  2 +-
 drivers/rtc/rtc-sh.c                             |  2 +-
 drivers/rtc/rtc-sirfsoc.c                        |  2 +-
 drivers/rtc/rtc-snvs.c                           |  2 +-
 drivers/rtc/rtc-st-lpc.c                         |  2 +-
 drivers/rtc/rtc-starfire.c                       |  2 +-
 drivers/rtc/rtc-stk17ta8.c                       |  2 +-
 drivers/rtc/rtc-stmp3xxx.c                       |  2 +-
 drivers/rtc/rtc-sun4v.c                          |  2 +-
 drivers/rtc/rtc-sun6i.c                          |  2 +-
 drivers/rtc/rtc-sunxi.c                          |  2 +-
 drivers/rtc/rtc-tegra.c                          |  2 +-
 drivers/rtc/rtc-test.c                           |  2 +-
 drivers/rtc/rtc-tps6586x.c                       |  2 +-
 drivers/rtc/rtc-tps65910.c                       |  2 +-
 drivers/rtc/rtc-tx4939.c                         |  2 +-
 drivers/rtc/rtc-vr41xx.c                         |  2 +-
 drivers/rtc/rtc-vt8500.c                         |  2 +-
 drivers/rtc/rtc-wilco-ec.c                       |  2 +-
 drivers/rtc/rtc-wm831x.c                         |  2 +-
 drivers/rtc/rtc-xgene.c                          |  2 +-
 drivers/rtc/rtc-zynqmp.c                         |  2 +-
 drivers/rtc/sysfs.c                              |  2 --
 include/linux/rtc.h                              |  8 +++-----
 114 files changed, 123 insertions(+), 127 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/driver-api/driver-model/devres.rst b/Documentation/driver-api/driver-model/devres.rst
index 5df7ba54a4ba..cd8b6e657b94 100644
--- a/Documentation/driver-api/driver-model/devres.rst
+++ b/Documentation/driver-api/driver-model/devres.rst
@@ -414,6 +414,7 @@ RESET
 RTC
   devm_rtc_device_register()
   devm_rtc_allocate_device()
+  devm_rtc_register_device()
   devm_rtc_nvmem_register()
 
 SERDEV
diff --git a/arch/alpha/kernel/rtc.c b/arch/alpha/kernel/rtc.c
index 1b1d5963ac55..ce3077946e1d 100644
--- a/arch/alpha/kernel/rtc.c
+++ b/arch/alpha/kernel/rtc.c
@@ -216,6 +216,6 @@ alpha_rtc_init(void)
 		rtc->ops = &remote_rtc_ops;
 #endif
 
-	return rtc_register_device(rtc);
+	return devm_rtc_register_device(rtc);
 }
 device_initcall(alpha_rtc_init);
diff --git a/drivers/mfd/menelaus.c b/drivers/mfd/menelaus.c
index b64d3315a5e1..07e0ca2e467c 100644
--- a/drivers/mfd/menelaus.c
+++ b/drivers/mfd/menelaus.c
@@ -1119,7 +1119,7 @@ static inline void menelaus_rtc_init(struct menelaus_chip *m)
 		menelaus_write_reg(MENELAUS_RTC_CTRL, m->rtc_control);
 	}
 
-	err = rtc_register_device(m->rtc);
+	err = devm_rtc_register_device(m->rtc);
 	if (err) {
 		if (alarm) {
 			menelaus_remove_irq_work(MENELAUS_RTCALM_IRQ);
diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c
index a99b7d24b77c..b8a34ee039ad 100644
--- a/drivers/rtc/class.c
+++ b/drivers/rtc/class.c
@@ -321,8 +321,10 @@ static void rtc_device_get_offset(struct rtc_device *rtc)
  *
  * @rtc: the RTC class device to destroy
  */
-static void rtc_device_unregister(struct rtc_device *rtc)
+static void devm_rtc_unregister_device(void *data)
 {
+	struct rtc_device *rtc = data;
+
 	mutex_lock(&rtc->ops_lock);
 	/*
 	 * Remove innards of this RTC, then disable it, before
@@ -339,10 +341,7 @@ static void devm_rtc_release_device(struct device *dev, void *res)
 {
 	struct rtc_device *rtc = *(struct rtc_device **)res;
 
-	if (rtc->registered)
-		rtc_device_unregister(rtc);
-	else
-		put_device(&rtc->dev);
+	put_device(&rtc->dev);
 }
 
 struct rtc_device *devm_rtc_allocate_device(struct device *dev)
@@ -383,7 +382,7 @@ exit_ida:
 }
 EXPORT_SYMBOL_GPL(devm_rtc_allocate_device);
 
-int __rtc_register_device(struct module *owner, struct rtc_device *rtc)
+int __devm_rtc_register_device(struct module *owner, struct rtc_device *rtc)
 {
 	struct rtc_wkalrm alrm;
 	int err;
@@ -413,7 +412,6 @@ int __rtc_register_device(struct module *owner, struct rtc_device *rtc)
 
 	rtc_proc_add_device(rtc);
 
-	rtc->registered = true;
 	dev_info(rtc->dev.parent, "registered as %s\n",
 		 dev_name(&rtc->dev));
 
@@ -422,9 +420,10 @@ int __rtc_register_device(struct module *owner, struct rtc_device *rtc)
 		rtc_hctosys(rtc);
 #endif
 
-	return 0;
+	return devm_add_action_or_reset(rtc->dev.parent,
+					devm_rtc_unregister_device, rtc);
 }
-EXPORT_SYMBOL_GPL(__rtc_register_device);
+EXPORT_SYMBOL_GPL(__devm_rtc_register_device);
 
 /**
  * devm_rtc_device_register - resource managed rtc_device_register()
@@ -454,7 +453,7 @@ struct rtc_device *devm_rtc_device_register(struct device *dev,
 
 	rtc->ops = ops;
 
-	err = __rtc_register_device(owner, rtc);
+	err = __devm_rtc_register_device(owner, rtc);
 	if (err)
 		return ERR_PTR(err);
 
diff --git a/drivers/rtc/rtc-88pm80x.c b/drivers/rtc/rtc-88pm80x.c
index 75779e8501a3..6a3f44cf6ebe 100644
--- a/drivers/rtc/rtc-88pm80x.c
+++ b/drivers/rtc/rtc-88pm80x.c
@@ -294,7 +294,7 @@ static int pm80x_rtc_probe(struct platform_device *pdev)
 	info->rtc_dev->ops = &pm80x_rtc_ops;
 	info->rtc_dev->range_max = U32_MAX;
 
-	ret = rtc_register_device(info->rtc_dev);
+	ret = devm_rtc_register_device(info->rtc_dev);
 	if (ret)
 		goto out_rtc;
 
diff --git a/drivers/rtc/rtc-88pm860x.c b/drivers/rtc/rtc-88pm860x.c
index c90457d001e9..2c809a1a445e 100644
--- a/drivers/rtc/rtc-88pm860x.c
+++ b/drivers/rtc/rtc-88pm860x.c
@@ -307,7 +307,7 @@ static int pm860x_rtc_probe(struct platform_device *pdev)
 	info->rtc_dev->ops = &pm860x_rtc_ops;
 	info->rtc_dev->range_max = U32_MAX;
 
-	ret = rtc_register_device(info->rtc_dev);
+	ret = devm_rtc_register_device(info->rtc_dev);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-ab-b5ze-s3.c b/drivers/rtc/rtc-ab-b5ze-s3.c
index 2370ac0cdb5f..6e3e320dc727 100644
--- a/drivers/rtc/rtc-ab-b5ze-s3.c
+++ b/drivers/rtc/rtc-ab-b5ze-s3.c
@@ -892,7 +892,7 @@ static int abb5zes3_probe(struct i2c_client *client,
 		}
 	}
 
-	ret = rtc_register_device(data->rtc);
+	ret = devm_rtc_register_device(data->rtc);
 
 err:
 	if (ret && data->irq)
diff --git a/drivers/rtc/rtc-ab-eoz9.c b/drivers/rtc/rtc-ab-eoz9.c
index d690985caa4c..b20d8f26dcdb 100644
--- a/drivers/rtc/rtc-ab-eoz9.c
+++ b/drivers/rtc/rtc-ab-eoz9.c
@@ -420,7 +420,7 @@ static int abeoz9_probe(struct i2c_client *client,
 	data->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	data->rtc->range_max = RTC_TIMESTAMP_END_2099;
 
-	ret = rtc_register_device(data->rtc);
+	ret = devm_rtc_register_device(data->rtc);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-ab3100.c b/drivers/rtc/rtc-ab3100.c
index 2ed6def90975..e4fd961e8bf6 100644
--- a/drivers/rtc/rtc-ab3100.c
+++ b/drivers/rtc/rtc-ab3100.c
@@ -238,7 +238,7 @@ static int __init ab3100_rtc_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, rtc);
 
-	return rtc_register_device(rtc);
+	return devm_rtc_register_device(rtc);
 }
 
 static struct platform_driver ab3100_rtc_driver = {
diff --git a/drivers/rtc/rtc-ab8500.c b/drivers/rtc/rtc-ab8500.c
index 3d60f3283f11..b40048871295 100644
--- a/drivers/rtc/rtc-ab8500.c
+++ b/drivers/rtc/rtc-ab8500.c
@@ -404,7 +404,7 @@ static int ab8500_rtc_probe(struct platform_device *pdev)
 	if (err)
 		return err;
 
-	return rtc_register_device(rtc);
+	return devm_rtc_register_device(rtc);
 }
 
 static int ab8500_rtc_remove(struct platform_device *pdev)
diff --git a/drivers/rtc/rtc-abx80x.c b/drivers/rtc/rtc-abx80x.c
index 803725b3a02c..6733bb0df674 100644
--- a/drivers/rtc/rtc-abx80x.c
+++ b/drivers/rtc/rtc-abx80x.c
@@ -851,7 +851,7 @@ static int abx80x_probe(struct i2c_client *client,
 		return err;
 	}
 
-	return rtc_register_device(priv->rtc);
+	return devm_rtc_register_device(priv->rtc);
 }
 
 static const struct i2c_device_id abx80x_id[] = {
diff --git a/drivers/rtc/rtc-ac100.c b/drivers/rtc/rtc-ac100.c
index 29223931aba7..1ddbef99e38f 100644
--- a/drivers/rtc/rtc-ac100.c
+++ b/drivers/rtc/rtc-ac100.c
@@ -610,7 +610,7 @@ static int ac100_rtc_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	return rtc_register_device(chip->rtc);
+	return devm_rtc_register_device(chip->rtc);
 }
 
 static int ac100_rtc_remove(struct platform_device *pdev)
diff --git a/drivers/rtc/rtc-armada38x.c b/drivers/rtc/rtc-armada38x.c
index 94d7c22fc4f3..807a79c07f08 100644
--- a/drivers/rtc/rtc-armada38x.c
+++ b/drivers/rtc/rtc-armada38x.c
@@ -556,7 +556,7 @@ static __init int armada38x_rtc_probe(struct platform_device *pdev)
 
 	rtc->rtc_dev->range_max = U32_MAX;
 
-	return rtc_register_device(rtc->rtc_dev);
+	return devm_rtc_register_device(rtc->rtc_dev);
 }
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/rtc/rtc-aspeed.c b/drivers/rtc/rtc-aspeed.c
index eacdd0637cce..a93352ed3aec 100644
--- a/drivers/rtc/rtc-aspeed.c
+++ b/drivers/rtc/rtc-aspeed.c
@@ -104,7 +104,7 @@ static int aspeed_rtc_probe(struct platform_device *pdev)
 	rtc->rtc_dev->range_min = RTC_TIMESTAMP_BEGIN_1900;
 	rtc->rtc_dev->range_max = 38814989399LL; /* 3199-12-31 23:59:59 */
 
-	return rtc_register_device(rtc->rtc_dev);
+	return devm_rtc_register_device(rtc->rtc_dev);
 }
 
 static const struct of_device_id aspeed_rtc_match[] = {
diff --git a/drivers/rtc/rtc-at91rm9200.c b/drivers/rtc/rtc-at91rm9200.c
index da24e68adcca..fe396d27ebb7 100644
--- a/drivers/rtc/rtc-at91rm9200.c
+++ b/drivers/rtc/rtc-at91rm9200.c
@@ -538,7 +538,7 @@ static int __init at91_rtc_probe(struct platform_device *pdev)
 
 	rtc->range_min = RTC_TIMESTAMP_BEGIN_1900;
 	rtc->range_max = RTC_TIMESTAMP_END_2099;
-	ret = rtc_register_device(rtc);
+	ret = devm_rtc_register_device(rtc);
 	if (ret)
 		goto err_clk;
 
diff --git a/drivers/rtc/rtc-at91sam9.c b/drivers/rtc/rtc-at91sam9.c
index e39e89867d29..2216be429ab7 100644
--- a/drivers/rtc/rtc-at91sam9.c
+++ b/drivers/rtc/rtc-at91sam9.c
@@ -431,7 +431,7 @@ static int at91_rtc_probe(struct platform_device *pdev)
 		dev_warn(&pdev->dev, "%s: SET TIME!\n",
 			 dev_name(&rtc->rtcdev->dev));
 
-	return rtc_register_device(rtc->rtcdev);
+	return devm_rtc_register_device(rtc->rtcdev);
 
 err_clk:
 	clk_disable_unprepare(rtc->sclk);
diff --git a/drivers/rtc/rtc-au1xxx.c b/drivers/rtc/rtc-au1xxx.c
index 791bebcb6f47..e6428b27b5d4 100644
--- a/drivers/rtc/rtc-au1xxx.c
+++ b/drivers/rtc/rtc-au1xxx.c
@@ -104,7 +104,7 @@ static int au1xtoy_rtc_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, rtcdev);
 
-	return rtc_register_device(rtcdev);
+	return devm_rtc_register_device(rtcdev);
 }
 
 static struct platform_driver au1xrtc_driver = {
diff --git a/drivers/rtc/rtc-bd70528.c b/drivers/rtc/rtc-bd70528.c
index 4492b770422c..17cb67f5bf6e 100644
--- a/drivers/rtc/rtc-bd70528.c
+++ b/drivers/rtc/rtc-bd70528.c
@@ -604,7 +604,7 @@ static int bd70528_probe(struct platform_device *pdev)
 		}
 	}
 
-	return rtc_register_device(rtc);
+	return devm_rtc_register_device(rtc);
 }
 
 static const struct platform_device_id bd718x7_rtc_id[] = {
diff --git a/drivers/rtc/rtc-brcmstb-waketimer.c b/drivers/rtc/rtc-brcmstb-waketimer.c
index 375a9987a1d6..0366e2ff04ae 100644
--- a/drivers/rtc/rtc-brcmstb-waketimer.c
+++ b/drivers/rtc/rtc-brcmstb-waketimer.c
@@ -252,7 +252,7 @@ static int brcmstb_waketmr_probe(struct platform_device *pdev)
 	timer->rtc->ops = &brcmstb_waketmr_ops;
 	timer->rtc->range_max = U32_MAX;
 
-	ret = rtc_register_device(timer->rtc);
+	ret = devm_rtc_register_device(timer->rtc);
 	if (ret)
 		goto err_notifier;
 
diff --git a/drivers/rtc/rtc-cadence.c b/drivers/rtc/rtc-cadence.c
index 595d5d252850..1edf7f16d73a 100644
--- a/drivers/rtc/rtc-cadence.c
+++ b/drivers/rtc/rtc-cadence.c
@@ -336,7 +336,7 @@ static int cdns_rtc_probe(struct platform_device *pdev)
 	writel(0, crtc->regs + CDNS_RTC_HMR);
 	writel(CDNS_RTC_KRTCR_KRTC, crtc->regs + CDNS_RTC_KRTCR);
 
-	ret = rtc_register_device(crtc->rtc_dev);
+	ret = devm_rtc_register_device(crtc->rtc_dev);
 	if (ret)
 		goto err_disable_wakeup;
 
diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index 766074c04b53..83415600185c 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -863,7 +863,7 @@ cmos_do_probe(struct device *dev, struct resource *ports, int rtc_irq)
 		cmos_rtc.rtc->ops = &cmos_rtc_ops_no_alarm;
 	}
 
-	retval = rtc_register_device(cmos_rtc.rtc);
+	retval = devm_rtc_register_device(cmos_rtc.rtc);
 	if (retval)
 		goto cleanup2;
 
diff --git a/drivers/rtc/rtc-coh901331.c b/drivers/rtc/rtc-coh901331.c
index da59917c9ee8..168ced87d93a 100644
--- a/drivers/rtc/rtc-coh901331.c
+++ b/drivers/rtc/rtc-coh901331.c
@@ -203,7 +203,7 @@ static int __init coh901331_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, rtap);
 
-	ret = rtc_register_device(rtap->rtc);
+	ret = devm_rtc_register_device(rtap->rtc);
 	if (ret)
 		goto out_no_rtc;
 
diff --git a/drivers/rtc/rtc-cpcap.c b/drivers/rtc/rtc-cpcap.c
index 38d576b0c4fa..afc8fcba8f88 100644
--- a/drivers/rtc/rtc-cpcap.c
+++ b/drivers/rtc/rtc-cpcap.c
@@ -301,7 +301,7 @@ static int cpcap_rtc_probe(struct platform_device *pdev)
 		/* ignore error and continue without wakeup support */
 	}
 
-	return rtc_register_device(rtc->rtc_dev);
+	return devm_rtc_register_device(rtc->rtc_dev);
 }
 
 static const struct of_device_id cpcap_rtc_of_match[] = {
diff --git a/drivers/rtc/rtc-cros-ec.c b/drivers/rtc/rtc-cros-ec.c
index f7343c289cab..70626793ca69 100644
--- a/drivers/rtc/rtc-cros-ec.c
+++ b/drivers/rtc/rtc-cros-ec.c
@@ -350,7 +350,7 @@ static int cros_ec_rtc_probe(struct platform_device *pdev)
 	cros_ec_rtc->rtc->ops = &cros_ec_rtc_ops;
 	cros_ec_rtc->rtc->range_max = U32_MAX;
 
-	ret = rtc_register_device(cros_ec_rtc->rtc);
+	ret = devm_rtc_register_device(cros_ec_rtc->rtc);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-da9052.c b/drivers/rtc/rtc-da9052.c
index 58de10da37b1..9ca99bd35702 100644
--- a/drivers/rtc/rtc-da9052.c
+++ b/drivers/rtc/rtc-da9052.c
@@ -304,7 +304,7 @@ static int da9052_rtc_probe(struct platform_device *pdev)
 	rtc->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	rtc->rtc->range_max = RTC_TIMESTAMP_END_2063;
 
-	ret = rtc_register_device(rtc->rtc);
+	ret = devm_rtc_register_device(rtc->rtc);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-da9063.c b/drivers/rtc/rtc-da9063.c
index 6f0a3a711135..d4b72a9fa2ba 100644
--- a/drivers/rtc/rtc-da9063.c
+++ b/drivers/rtc/rtc-da9063.c
@@ -494,7 +494,7 @@ static int da9063_rtc_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev, "Failed to request ALARM IRQ %d: %d\n",
 			irq_alarm, ret);
 
-	return rtc_register_device(rtc->rtc_dev);
+	return devm_rtc_register_device(rtc->rtc_dev);
 }
 
 static struct platform_driver da9063_rtc_driver = {
diff --git a/drivers/rtc/rtc-davinci.c b/drivers/rtc/rtc-davinci.c
index 73f87a17cdf3..6bef0f2353da 100644
--- a/drivers/rtc/rtc-davinci.c
+++ b/drivers/rtc/rtc-davinci.c
@@ -484,7 +484,7 @@ static int __init davinci_rtc_probe(struct platform_device *pdev)
 
 	device_init_wakeup(&pdev->dev, 0);
 
-	return rtc_register_device(davinci_rtc->rtc);
+	return devm_rtc_register_device(davinci_rtc->rtc);
 }
 
 static int __exit davinci_rtc_remove(struct platform_device *pdev)
diff --git a/drivers/rtc/rtc-digicolor.c b/drivers/rtc/rtc-digicolor.c
index 200d85b01e8b..4fdfa5b6feb2 100644
--- a/drivers/rtc/rtc-digicolor.c
+++ b/drivers/rtc/rtc-digicolor.c
@@ -202,7 +202,7 @@ static int __init dc_rtc_probe(struct platform_device *pdev)
 	rtc->rtc_dev->ops = &dc_rtc_ops;
 	rtc->rtc_dev->range_max = U32_MAX;
 
-	return rtc_register_device(rtc->rtc_dev);
+	return devm_rtc_register_device(rtc->rtc_dev);
 }
 
 static const struct of_device_id dc_dt_ids[] = {
diff --git a/drivers/rtc/rtc-dm355evm.c b/drivers/rtc/rtc-dm355evm.c
index cd947a20843b..94fb16ac3e0f 100644
--- a/drivers/rtc/rtc-dm355evm.c
+++ b/drivers/rtc/rtc-dm355evm.c
@@ -132,7 +132,7 @@ static int dm355evm_rtc_probe(struct platform_device *pdev)
 	rtc->ops = &dm355evm_rtc_ops;
 	rtc->range_max = U32_MAX;
 
-	return rtc_register_device(rtc);
+	return devm_rtc_register_device(rtc);
 }
 
 /*
diff --git a/drivers/rtc/rtc-ds1305.c b/drivers/rtc/rtc-ds1305.c
index a4e768261b43..8c2ab29c3d91 100644
--- a/drivers/rtc/rtc-ds1305.c
+++ b/drivers/rtc/rtc-ds1305.c
@@ -694,7 +694,7 @@ static int ds1305_probe(struct spi_device *spi)
 	ds1305->rtc->range_max = RTC_TIMESTAMP_END_2099;
 
 	ds1305_nvmem_cfg.priv = ds1305;
-	status = rtc_register_device(ds1305->rtc);
+	status = devm_rtc_register_device(ds1305->rtc);
 	if (status)
 		return status;
 
diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c
index 216bc5d9b716..183cf7c01364 100644
--- a/drivers/rtc/rtc-ds1307.c
+++ b/drivers/rtc/rtc-ds1307.c
@@ -2001,7 +2001,7 @@ static int ds1307_probe(struct i2c_client *client,
 	if (err)
 		return err;
 
-	err = rtc_register_device(ds1307->rtc);
+	err = devm_rtc_register_device(ds1307->rtc);
 	if (err)
 		return err;
 
diff --git a/drivers/rtc/rtc-ds1343.c b/drivers/rtc/rtc-ds1343.c
index ea663e24a34c..f14ed6c96437 100644
--- a/drivers/rtc/rtc-ds1343.c
+++ b/drivers/rtc/rtc-ds1343.c
@@ -408,7 +408,7 @@ static int ds1343_probe(struct spi_device *spi)
 		dev_err(&spi->dev,
 			"unable to create sysfs entries for rtc ds1343\n");
 
-	res = rtc_register_device(priv->rtc);
+	res = devm_rtc_register_device(priv->rtc);
 	if (res)
 		return res;
 
diff --git a/drivers/rtc/rtc-ds1347.c b/drivers/rtc/rtc-ds1347.c
index 7025cf3fb9f8..157bf5209ac4 100644
--- a/drivers/rtc/rtc-ds1347.c
+++ b/drivers/rtc/rtc-ds1347.c
@@ -166,7 +166,7 @@ static int ds1347_probe(struct spi_device *spi)
 	rtc->range_min = RTC_TIMESTAMP_BEGIN_0000;
 	rtc->range_max = RTC_TIMESTAMP_END_9999;
 
-	return rtc_register_device(rtc);
+	return devm_rtc_register_device(rtc);
 }
 
 static struct spi_driver ds1347_driver = {
diff --git a/drivers/rtc/rtc-ds1374.c b/drivers/rtc/rtc-ds1374.c
index 177d870bda0d..fab79921a712 100644
--- a/drivers/rtc/rtc-ds1374.c
+++ b/drivers/rtc/rtc-ds1374.c
@@ -508,7 +508,7 @@ static int ds1374_probe(struct i2c_client *client,
 	ds1374->rtc->ops = &ds1374_rtc_ops;
 	ds1374->rtc->range_max = U32_MAX;
 
-	ret = rtc_register_device(ds1374->rtc);
+	ret = devm_rtc_register_device(ds1374->rtc);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-ds1511.c b/drivers/rtc/rtc-ds1511.c
index d5f48216e851..bda884333082 100644
--- a/drivers/rtc/rtc-ds1511.c
+++ b/drivers/rtc/rtc-ds1511.c
@@ -466,7 +466,7 @@ static int ds1511_rtc_probe(struct platform_device *pdev)
 
 	pdata->rtc->ops = &ds1511_rtc_ops;
 
-	ret = rtc_register_device(pdata->rtc);
+	ret = devm_rtc_register_device(pdata->rtc);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-ds1553.c b/drivers/rtc/rtc-ds1553.c
index bb40ea8b6373..dbff5b621ef5 100644
--- a/drivers/rtc/rtc-ds1553.c
+++ b/drivers/rtc/rtc-ds1553.c
@@ -295,7 +295,7 @@ static int ds1553_rtc_probe(struct platform_device *pdev)
 
 	pdata->rtc->ops = &ds1553_rtc_ops;
 
-	ret = rtc_register_device(pdata->rtc);
+	ret = devm_rtc_register_device(pdata->rtc);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-ds1672.c b/drivers/rtc/rtc-ds1672.c
index 9da84df9f152..630493759d15 100644
--- a/drivers/rtc/rtc-ds1672.c
+++ b/drivers/rtc/rtc-ds1672.c
@@ -124,7 +124,7 @@ static int ds1672_probe(struct i2c_client *client,
 	rtc->ops = &ds1672_rtc_ops;
 	rtc->range_max = U32_MAX;
 
-	err = rtc_register_device(rtc);
+	err = devm_rtc_register_device(rtc);
 	if (err)
 		return err;
 
diff --git a/drivers/rtc/rtc-ds1685.c b/drivers/rtc/rtc-ds1685.c
index bef588fce266..d69c807af29b 100644
--- a/drivers/rtc/rtc-ds1685.c
+++ b/drivers/rtc/rtc-ds1685.c
@@ -1321,7 +1321,7 @@ ds1685_rtc_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	return rtc_register_device(rtc_dev);
+	return devm_rtc_register_device(rtc_dev);
 }
 
 /**
diff --git a/drivers/rtc/rtc-ds1742.c b/drivers/rtc/rtc-ds1742.c
index 39c6c3a85b34..13d45c697da6 100644
--- a/drivers/rtc/rtc-ds1742.c
+++ b/drivers/rtc/rtc-ds1742.c
@@ -191,7 +191,7 @@ static int ds1742_rtc_probe(struct platform_device *pdev)
 
 	rtc->ops = &ds1742_rtc_ops;
 
-	ret = rtc_register_device(rtc);
+	ret = devm_rtc_register_device(rtc);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-ds2404.c b/drivers/rtc/rtc-ds2404.c
index 9df0c44512b8..0480f592307e 100644
--- a/drivers/rtc/rtc-ds2404.c
+++ b/drivers/rtc/rtc-ds2404.c
@@ -234,7 +234,7 @@ static int rtc_probe(struct platform_device *pdev)
 	chip->rtc->ops = &ds2404_rtc_ops;
 	chip->rtc->range_max = U32_MAX;
 
-	retval = rtc_register_device(chip->rtc);
+	retval = devm_rtc_register_device(chip->rtc);
 	if (retval)
 		return retval;
 
diff --git a/drivers/rtc/rtc-ep93xx.c b/drivers/rtc/rtc-ep93xx.c
index 8ec9ea1ca72e..9a5a15cbcd9b 100644
--- a/drivers/rtc/rtc-ep93xx.c
+++ b/drivers/rtc/rtc-ep93xx.c
@@ -145,7 +145,7 @@ static int ep93xx_rtc_probe(struct platform_device *pdev)
 	if (err)
 		return err;
 
-	return rtc_register_device(ep93xx_rtc->rtc);
+	return devm_rtc_register_device(ep93xx_rtc->rtc);
 }
 
 static struct platform_driver ep93xx_rtc_driver = {
diff --git a/drivers/rtc/rtc-fsl-ftm-alarm.c b/drivers/rtc/rtc-fsl-ftm-alarm.c
index 48d3b38ea348..57cc09d0a806 100644
--- a/drivers/rtc/rtc-fsl-ftm-alarm.c
+++ b/drivers/rtc/rtc-fsl-ftm-alarm.c
@@ -290,7 +290,7 @@ static int ftm_rtc_probe(struct platform_device *pdev)
 	if (ret)
 		dev_err(&pdev->dev, "failed to enable irq wake\n");
 
-	ret = rtc_register_device(rtc->rtc_dev);
+	ret = devm_rtc_register_device(rtc->rtc_dev);
 	if (ret) {
 		dev_err(&pdev->dev, "can't register rtc device\n");
 		return ret;
diff --git a/drivers/rtc/rtc-ftrtc010.c b/drivers/rtc/rtc-ftrtc010.c
index 0919f7dc94a3..ad3add5db4c8 100644
--- a/drivers/rtc/rtc-ftrtc010.c
+++ b/drivers/rtc/rtc-ftrtc010.c
@@ -176,7 +176,7 @@ static int ftrtc010_rtc_probe(struct platform_device *pdev)
 	if (unlikely(ret))
 		return ret;
 
-	return rtc_register_device(rtc->rtc_dev);
+	return devm_rtc_register_device(rtc->rtc_dev);
 }
 
 static int ftrtc010_rtc_remove(struct platform_device *pdev)
diff --git a/drivers/rtc/rtc-goldfish.c b/drivers/rtc/rtc-goldfish.c
index 6349d2cd3680..7ab95d052644 100644
--- a/drivers/rtc/rtc-goldfish.c
+++ b/drivers/rtc/rtc-goldfish.c
@@ -194,7 +194,7 @@ static int goldfish_rtc_probe(struct platform_device *pdev)
 	if (err)
 		return err;
 
-	return rtc_register_device(rtcdrv->rtc);
+	return devm_rtc_register_device(rtcdrv->rtc);
 }
 
 static const struct of_device_id goldfish_rtc_of_match[] = {
diff --git a/drivers/rtc/rtc-imx-sc.c b/drivers/rtc/rtc-imx-sc.c
index a5f59e6f862e..cc9fbab49999 100644
--- a/drivers/rtc/rtc-imx-sc.c
+++ b/drivers/rtc/rtc-imx-sc.c
@@ -166,7 +166,7 @@ static int imx_sc_rtc_probe(struct platform_device *pdev)
 	imx_sc_rtc->range_min = 0;
 	imx_sc_rtc->range_max = U32_MAX;
 
-	ret = rtc_register_device(imx_sc_rtc);
+	ret = devm_rtc_register_device(imx_sc_rtc);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-imxdi.c b/drivers/rtc/rtc-imxdi.c
index 8d141d8a5490..c2692da74e09 100644
--- a/drivers/rtc/rtc-imxdi.c
+++ b/drivers/rtc/rtc-imxdi.c
@@ -814,7 +814,7 @@ static int __init dryice_rtc_probe(struct platform_device *pdev)
 	imxdi->rtc->ops = &dryice_rtc_ops;
 	imxdi->rtc->range_max = U32_MAX;
 
-	rc = rtc_register_device(imxdi->rtc);
+	rc = devm_rtc_register_device(imxdi->rtc);
 	if (rc)
 		goto err;
 
diff --git a/drivers/rtc/rtc-isl12026.c b/drivers/rtc/rtc-isl12026.c
index fff8d8253669..1fc6627d854d 100644
--- a/drivers/rtc/rtc-isl12026.c
+++ b/drivers/rtc/rtc-isl12026.c
@@ -469,7 +469,7 @@ static int isl12026_probe_new(struct i2c_client *client)
 	if (ret)
 		return ret;
 
-	return rtc_register_device(priv->rtc);
+	return devm_rtc_register_device(priv->rtc);
 }
 
 static int isl12026_remove(struct i2c_client *client)
diff --git a/drivers/rtc/rtc-isl1208.c b/drivers/rtc/rtc-isl1208.c
index 08d778b10e9e..563a6d9c9fcf 100644
--- a/drivers/rtc/rtc-isl1208.c
+++ b/drivers/rtc/rtc-isl1208.c
@@ -894,7 +894,7 @@ isl1208_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	if (rc)
 		return rc;
 
-	return rtc_register_device(isl1208->rtc);
+	return devm_rtc_register_device(isl1208->rtc);
 }
 
 static struct i2c_driver isl1208_driver = {
diff --git a/drivers/rtc/rtc-jz4740.c b/drivers/rtc/rtc-jz4740.c
index 9607e6b6e0b3..6e51df72fd65 100644
--- a/drivers/rtc/rtc-jz4740.c
+++ b/drivers/rtc/rtc-jz4740.c
@@ -375,7 +375,7 @@ static int jz4740_rtc_probe(struct platform_device *pdev)
 	/* Each 1 Hz pulse should happen after (rate) ticks */
 	jz4740_rtc_reg_write(rtc, JZ_REG_RTC_REGULATOR, rate - 1);
 
-	ret = rtc_register_device(rtc->rtc);
+	ret = devm_rtc_register_device(rtc->rtc);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-lpc32xx.c b/drivers/rtc/rtc-lpc32xx.c
index 15d8abda81fe..76ad7031a13d 100644
--- a/drivers/rtc/rtc-lpc32xx.c
+++ b/drivers/rtc/rtc-lpc32xx.c
@@ -239,7 +239,7 @@ static int lpc32xx_rtc_probe(struct platform_device *pdev)
 	rtc->rtc->ops = &lpc32xx_rtc_ops;
 	rtc->rtc->range_max = U32_MAX;
 
-	err = rtc_register_device(rtc->rtc);
+	err = devm_rtc_register_device(rtc->rtc);
 	if (err)
 		return err;
 
diff --git a/drivers/rtc/rtc-ls1x.c b/drivers/rtc/rtc-ls1x.c
index 8bd34056fea0..5af26dc5c2a3 100644
--- a/drivers/rtc/rtc-ls1x.c
+++ b/drivers/rtc/rtc-ls1x.c
@@ -176,7 +176,7 @@ static int ls1x_rtc_probe(struct platform_device *pdev)
 	rtcdev->range_min = RTC_TIMESTAMP_BEGIN_1900;
 	rtcdev->range_max = RTC_TIMESTAMP_END_2099;
 
-	return rtc_register_device(rtcdev);
+	return devm_rtc_register_device(rtcdev);
 }
 
 static struct platform_driver  ls1x_rtc_driver = {
diff --git a/drivers/rtc/rtc-m41t80.c b/drivers/rtc/rtc-m41t80.c
index 8a89bc52b0d4..160dcf68e64e 100644
--- a/drivers/rtc/rtc-m41t80.c
+++ b/drivers/rtc/rtc-m41t80.c
@@ -977,7 +977,7 @@ static int m41t80_probe(struct i2c_client *client,
 		m41t80_sqw_register_clk(m41t80_data);
 #endif
 
-	rc = rtc_register_device(m41t80_data->rtc);
+	rc = devm_rtc_register_device(m41t80_data->rtc);
 	if (rc)
 		return rc;
 
diff --git a/drivers/rtc/rtc-m48t59.c b/drivers/rtc/rtc-m48t59.c
index e966a66ab2d3..5f5898d3b055 100644
--- a/drivers/rtc/rtc-m48t59.c
+++ b/drivers/rtc/rtc-m48t59.c
@@ -470,7 +470,7 @@ static int m48t59_rtc_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	ret = rtc_register_device(m48t59->rtc);
+	ret = devm_rtc_register_device(m48t59->rtc);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-m48t86.c b/drivers/rtc/rtc-m48t86.c
index 182cfe59e4e0..481c9525b1dd 100644
--- a/drivers/rtc/rtc-m48t86.c
+++ b/drivers/rtc/rtc-m48t86.c
@@ -255,7 +255,7 @@ static int m48t86_rtc_probe(struct platform_device *pdev)
 
 	info->rtc->ops = &m48t86_rtc_ops;
 
-	err = rtc_register_device(info->rtc);
+	err = devm_rtc_register_device(info->rtc);
 	if (err)
 		return err;
 
diff --git a/drivers/rtc/rtc-mc13xxx.c b/drivers/rtc/rtc-mc13xxx.c
index d6802e6191cb..d4234e78497e 100644
--- a/drivers/rtc/rtc-mc13xxx.c
+++ b/drivers/rtc/rtc-mc13xxx.c
@@ -307,7 +307,7 @@ static int __init mc13xxx_rtc_probe(struct platform_device *pdev)
 
 	mc13xxx_unlock(mc13xxx);
 
-	ret = rtc_register_device(priv->rtc);
+	ret = devm_rtc_register_device(priv->rtc);
 	if (ret) {
 		mc13xxx_lock(mc13xxx);
 		goto err_irq_request;
diff --git a/drivers/rtc/rtc-meson-vrtc.c b/drivers/rtc/rtc-meson-vrtc.c
index e6bd0808a092..1463c8621561 100644
--- a/drivers/rtc/rtc-meson-vrtc.c
+++ b/drivers/rtc/rtc-meson-vrtc.c
@@ -83,7 +83,7 @@ static int meson_vrtc_probe(struct platform_device *pdev)
 		return PTR_ERR(vrtc->rtc);
 
 	vrtc->rtc->ops = &meson_vrtc_ops;
-	return rtc_register_device(vrtc->rtc);
+	return devm_rtc_register_device(vrtc->rtc);
 }
 
 static int __maybe_unused meson_vrtc_suspend(struct device *dev)
diff --git a/drivers/rtc/rtc-meson.c b/drivers/rtc/rtc-meson.c
index 938267713a4d..8642c06565ea 100644
--- a/drivers/rtc/rtc-meson.c
+++ b/drivers/rtc/rtc-meson.c
@@ -369,7 +369,7 @@ static int meson_rtc_probe(struct platform_device *pdev)
 	if (ret)
 		goto out_disable_vdd;
 
-	ret = rtc_register_device(rtc->rtc);
+	ret = devm_rtc_register_device(rtc->rtc);
 	if (ret)
 		goto out_disable_vdd;
 
diff --git a/drivers/rtc/rtc-mpc5121.c b/drivers/rtc/rtc-mpc5121.c
index 5c2ce71aa044..bb2ea9bc56f2 100644
--- a/drivers/rtc/rtc-mpc5121.c
+++ b/drivers/rtc/rtc-mpc5121.c
@@ -371,7 +371,7 @@ static int mpc5121_rtc_probe(struct platform_device *op)
 		rtc->rtc->range_max = U32_MAX;
 	}
 
-	err = rtc_register_device(rtc->rtc);
+	err = devm_rtc_register_device(rtc->rtc);
 	if (err)
 		goto out_dispose2;
 
diff --git a/drivers/rtc/rtc-mrst.c b/drivers/rtc/rtc-mrst.c
index 17bf5394e1e5..421b3b6071b6 100644
--- a/drivers/rtc/rtc-mrst.c
+++ b/drivers/rtc/rtc-mrst.c
@@ -361,7 +361,7 @@ static int vrtc_mrst_do_probe(struct device *dev, struct resource *iomem,
 		}
 	}
 
-	retval = rtc_register_device(mrst_rtc.rtc);
+	retval = devm_rtc_register_device(mrst_rtc.rtc);
 	if (retval)
 		goto cleanup0;
 
diff --git a/drivers/rtc/rtc-mt2712.c b/drivers/rtc/rtc-mt2712.c
index d5f691c8a035..cd92a9788351 100644
--- a/drivers/rtc/rtc-mt2712.c
+++ b/drivers/rtc/rtc-mt2712.c
@@ -352,7 +352,7 @@ static int mt2712_rtc_probe(struct platform_device *pdev)
 	mt2712_rtc->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	mt2712_rtc->rtc->range_max = MT2712_RTC_TIMESTAMP_END_2127;
 
-	return rtc_register_device(mt2712_rtc->rtc);
+	return devm_rtc_register_device(mt2712_rtc->rtc);
 }
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/rtc/rtc-mt6397.c b/drivers/rtc/rtc-mt6397.c
index 1894aded4c85..6655035e5164 100644
--- a/drivers/rtc/rtc-mt6397.c
+++ b/drivers/rtc/rtc-mt6397.c
@@ -301,7 +301,7 @@ static int mtk_rtc_probe(struct platform_device *pdev)
 
 	rtc->rtc_dev->ops = &mtk_rtc_ops;
 
-	return rtc_register_device(rtc->rtc_dev);
+	return devm_rtc_register_device(rtc->rtc_dev);
 }
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/rtc/rtc-mv.c b/drivers/rtc/rtc-mv.c
index d5f190e578e4..f8e2ecea1d8d 100644
--- a/drivers/rtc/rtc-mv.c
+++ b/drivers/rtc/rtc-mv.c
@@ -278,7 +278,7 @@ static int __init mv_rtc_probe(struct platform_device *pdev)
 	pdata->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	pdata->rtc->range_max = RTC_TIMESTAMP_END_2099;
 
-	ret = rtc_register_device(pdata->rtc);
+	ret = devm_rtc_register_device(pdata->rtc);
 	if (!ret)
 		return 0;
 out:
diff --git a/drivers/rtc/rtc-mxc.c b/drivers/rtc/rtc-mxc.c
index 0d253ce3a8f5..65b29b0fa548 100644
--- a/drivers/rtc/rtc-mxc.c
+++ b/drivers/rtc/rtc-mxc.c
@@ -408,7 +408,7 @@ static int mxc_rtc_probe(struct platform_device *pdev)
 			dev_err(&pdev->dev, "failed to enable irq wake\n");
 	}
 
-	ret = rtc_register_device(rtc);
+	ret = devm_rtc_register_device(rtc);
 
 	return ret;
 }
diff --git a/drivers/rtc/rtc-mxc_v2.c b/drivers/rtc/rtc-mxc_v2.c
index 91534560fe2a..0d73f6f0cf9e 100644
--- a/drivers/rtc/rtc-mxc_v2.c
+++ b/drivers/rtc/rtc-mxc_v2.c
@@ -354,7 +354,7 @@ static int mxc_rtc_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	ret = rtc_register_device(pdata->rtc);
+	ret = devm_rtc_register_device(pdata->rtc);
 	if (ret < 0)
 		clk_unprepare(pdata->clk);
 
diff --git a/drivers/rtc/rtc-omap.c b/drivers/rtc/rtc-omap.c
index e65f79fc7718..dc7db2477f88 100644
--- a/drivers/rtc/rtc-omap.c
+++ b/drivers/rtc/rtc-omap.c
@@ -886,7 +886,7 @@ static int omap_rtc_probe(struct platform_device *pdev)
 		goto err;
 	}
 
-	ret = rtc_register_device(rtc->rtc);
+	ret = devm_rtc_register_device(rtc->rtc);
 	if (ret)
 		goto err;
 
diff --git a/drivers/rtc/rtc-pcap.c b/drivers/rtc/rtc-pcap.c
index 178bfb1dea21..8c7a98a5452c 100644
--- a/drivers/rtc/rtc-pcap.c
+++ b/drivers/rtc/rtc-pcap.c
@@ -163,7 +163,7 @@ static int __init pcap_rtc_probe(struct platform_device *pdev)
 	if (err)
 		return err;
 
-	return rtc_register_device(pcap_rtc->rtc);
+	return devm_rtc_register_device(pcap_rtc->rtc);
 }
 
 static int __exit pcap_rtc_remove(struct platform_device *pdev)
diff --git a/drivers/rtc/rtc-pcf2123.c b/drivers/rtc/rtc-pcf2123.c
index c3691fa4210e..534ffc91eec1 100644
--- a/drivers/rtc/rtc-pcf2123.c
+++ b/drivers/rtc/rtc-pcf2123.c
@@ -434,7 +434,7 @@ static int pcf2123_probe(struct spi_device *spi)
 	rtc->range_max = RTC_TIMESTAMP_END_2099;
 	rtc->set_start_time = true;
 
-	ret = rtc_register_device(rtc);
+	ret = devm_rtc_register_device(rtc);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index 432cd627359b..33fa8b17b79c 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -682,7 +682,7 @@ static int pcf2127_probe(struct device *dev, struct regmap *regmap,
 		return ret;
 	}
 
-	return rtc_register_device(pcf2127->rtc);
+	return devm_rtc_register_device(pcf2127->rtc);
 }
 
 #ifdef CONFIG_OF
diff --git a/drivers/rtc/rtc-pcf85063.c b/drivers/rtc/rtc-pcf85063.c
index c19f139e9b8d..e19cf2adbc35 100644
--- a/drivers/rtc/rtc-pcf85063.c
+++ b/drivers/rtc/rtc-pcf85063.c
@@ -614,7 +614,7 @@ static int pcf85063_probe(struct i2c_client *client)
 	pcf85063_clkout_register_clk(pcf85063);
 #endif
 
-	return rtc_register_device(pcf85063->rtc);
+	return devm_rtc_register_device(pcf85063->rtc);
 }
 
 #ifdef CONFIG_OF
diff --git a/drivers/rtc/rtc-pcf85363.c b/drivers/rtc/rtc-pcf85363.c
index 23cf14ca2c96..a574c8d15a5c 100644
--- a/drivers/rtc/rtc-pcf85363.c
+++ b/drivers/rtc/rtc-pcf85363.c
@@ -418,7 +418,7 @@ static int pcf85363_probe(struct i2c_client *client,
 			pcf85363->rtc->ops = &rtc_ops_alarm;
 	}
 
-	ret = rtc_register_device(pcf85363->rtc);
+	ret = devm_rtc_register_device(pcf85363->rtc);
 
 	for (i = 0; i < config->num_nvram; i++) {
 		nvmem_cfg[i].priv = pcf85363;
diff --git a/drivers/rtc/rtc-pcf8563.c b/drivers/rtc/rtc-pcf8563.c
index 2dc30eafa639..de3e6c355f2e 100644
--- a/drivers/rtc/rtc-pcf8563.c
+++ b/drivers/rtc/rtc-pcf8563.c
@@ -582,7 +582,7 @@ static int pcf8563_probe(struct i2c_client *client,
 		}
 	}
 
-	err = rtc_register_device(pcf8563->rtc);
+	err = devm_rtc_register_device(pcf8563->rtc);
 	if (err)
 		return err;
 
diff --git a/drivers/rtc/rtc-pic32.c b/drivers/rtc/rtc-pic32.c
index 2b6946744654..7fb9145c43bd 100644
--- a/drivers/rtc/rtc-pic32.c
+++ b/drivers/rtc/rtc-pic32.c
@@ -338,7 +338,7 @@ static int pic32_rtc_probe(struct platform_device *pdev)
 	pdata->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	pdata->rtc->range_max = RTC_TIMESTAMP_END_2099;
 
-	ret = rtc_register_device(pdata->rtc);
+	ret = devm_rtc_register_device(pdata->rtc);
 	if (ret)
 		goto err_nortc;
 
diff --git a/drivers/rtc/rtc-pl030.c b/drivers/rtc/rtc-pl030.c
index ebe03eba8f5f..5a880516f3e8 100644
--- a/drivers/rtc/rtc-pl030.c
+++ b/drivers/rtc/rtc-pl030.c
@@ -121,7 +121,7 @@ static int pl030_probe(struct amba_device *dev, const struct amba_id *id)
 	if (ret)
 		goto err_irq;
 
-	ret = rtc_register_device(rtc->rtc);
+	ret = devm_rtc_register_device(rtc->rtc);
 	if (ret)
 		goto err_reg;
 
diff --git a/drivers/rtc/rtc-pl031.c b/drivers/rtc/rtc-pl031.c
index d4b2ab786126..224bbf096262 100644
--- a/drivers/rtc/rtc-pl031.c
+++ b/drivers/rtc/rtc-pl031.c
@@ -370,7 +370,7 @@ static int pl031_probe(struct amba_device *adev, const struct amba_id *id)
 	ldata->rtc->range_min = vendor->range_min;
 	ldata->rtc->range_max = vendor->range_max;
 
-	ret = rtc_register_device(ldata->rtc);
+	ret = devm_rtc_register_device(ldata->rtc);
 	if (ret)
 		goto out;
 
diff --git a/drivers/rtc/rtc-pm8xxx.c b/drivers/rtc/rtc-pm8xxx.c
index b45ee2cb2c04..0d9dd6faabba 100644
--- a/drivers/rtc/rtc-pm8xxx.c
+++ b/drivers/rtc/rtc-pm8xxx.c
@@ -508,7 +508,7 @@ static int pm8xxx_rtc_probe(struct platform_device *pdev)
 		return rc;
 	}
 
-	return rtc_register_device(rtc_dd->rtc);
+	return devm_rtc_register_device(rtc_dd->rtc);
 }
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/rtc/rtc-ps3.c b/drivers/rtc/rtc-ps3.c
index f0336d691e6c..6b098734c715 100644
--- a/drivers/rtc/rtc-ps3.c
+++ b/drivers/rtc/rtc-ps3.c
@@ -56,7 +56,7 @@ static int __init ps3_rtc_probe(struct platform_device *dev)
 
 	platform_set_drvdata(dev, rtc);
 
-	return rtc_register_device(rtc);
+	return devm_rtc_register_device(rtc);
 }
 
 static struct platform_driver ps3_rtc_driver = {
diff --git a/drivers/rtc/rtc-r9701.c b/drivers/rtc/rtc-r9701.c
index 7ceb968f0e44..60a3c3d7499b 100644
--- a/drivers/rtc/rtc-r9701.c
+++ b/drivers/rtc/rtc-r9701.c
@@ -127,7 +127,7 @@ static int r9701_probe(struct spi_device *spi)
 	rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	rtc->range_max = RTC_TIMESTAMP_END_2099;
 
-	return rtc_register_device(rtc);
+	return devm_rtc_register_device(rtc);
 }
 
 static struct spi_driver r9701_driver = {
diff --git a/drivers/rtc/rtc-rc5t619.c b/drivers/rtc/rtc-rc5t619.c
index dd1a20977478..e73102a39f1b 100644
--- a/drivers/rtc/rtc-rc5t619.c
+++ b/drivers/rtc/rtc-rc5t619.c
@@ -426,7 +426,7 @@ static int rc5t619_rtc_probe(struct platform_device *pdev)
 		dev_warn(&pdev->dev, "rc5t619 interrupt is disabled\n");
 	}
 
-	return rtc_register_device(rtc->rtc);
+	return devm_rtc_register_device(rtc->rtc);
 }
 
 static struct platform_driver rc5t619_rtc_driver = {
diff --git a/drivers/rtc/rtc-rk808.c b/drivers/rtc/rtc-rk808.c
index c0334c602e88..e920da8c08da 100644
--- a/drivers/rtc/rtc-rk808.c
+++ b/drivers/rtc/rtc-rk808.c
@@ -447,7 +447,7 @@ static int rk808_rtc_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	return rtc_register_device(rk808_rtc->rtc);
+	return devm_rtc_register_device(rk808_rtc->rtc);
 }
 
 static struct platform_driver rk808_rtc_driver = {
diff --git a/drivers/rtc/rtc-rp5c01.c b/drivers/rtc/rtc-rp5c01.c
index 8bc476c0905f..44afa6d996e7 100644
--- a/drivers/rtc/rtc-rp5c01.c
+++ b/drivers/rtc/rtc-rp5c01.c
@@ -259,7 +259,7 @@ static int __init rp5c01_rtc_probe(struct platform_device *dev)
 	if (error)
 		return error;
 
-	return rtc_register_device(rtc);
+	return devm_rtc_register_device(rtc);
 }
 
 static struct platform_driver rp5c01_rtc_driver = {
diff --git a/drivers/rtc/rtc-rs5c348.c b/drivers/rtc/rtc-rs5c348.c
index 47c13678449e..fec633f80789 100644
--- a/drivers/rtc/rtc-rs5c348.c
+++ b/drivers/rtc/rtc-rs5c348.c
@@ -197,7 +197,7 @@ static int rs5c348_probe(struct spi_device *spi)
 
 	rtc->ops = &rs5c348_rtc_ops;
 
-	return rtc_register_device(rtc);
+	return devm_rtc_register_device(rtc);
 }
 
 static struct spi_driver rs5c348_driver = {
diff --git a/drivers/rtc/rtc-rv3028.c b/drivers/rtc/rtc-rv3028.c
index f788df979750..979407a51c7a 100644
--- a/drivers/rtc/rtc-rv3028.c
+++ b/drivers/rtc/rtc-rv3028.c
@@ -886,7 +886,7 @@ static int rv3028_probe(struct i2c_client *client)
 	rv3028->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	rv3028->rtc->range_max = RTC_TIMESTAMP_END_2099;
 	rv3028->rtc->ops = &rv3028_rtc_ops;
-	ret = rtc_register_device(rv3028->rtc);
+	ret = devm_rtc_register_device(rv3028->rtc);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-rv3029c2.c b/drivers/rtc/rtc-rv3029c2.c
index ad359b3b74b2..dc1bda62095e 100644
--- a/drivers/rtc/rtc-rv3029c2.c
+++ b/drivers/rtc/rtc-rv3029c2.c
@@ -750,7 +750,7 @@ static int rv3029_probe(struct device *dev, struct regmap *regmap, int irq,
 	rv3029->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	rv3029->rtc->range_max = RTC_TIMESTAMP_END_2079;
 
-	rc = rtc_register_device(rv3029->rtc);
+	rc = devm_rtc_register_device(rv3029->rtc);
 	if (rc)
 		return rc;
 
diff --git a/drivers/rtc/rtc-rv3032.c b/drivers/rtc/rtc-rv3032.c
index ed9cba3292e6..c9bcea727757 100644
--- a/drivers/rtc/rtc-rv3032.c
+++ b/drivers/rtc/rtc-rv3032.c
@@ -885,7 +885,7 @@ static int rv3032_probe(struct i2c_client *client)
 	rv3032->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	rv3032->rtc->range_max = RTC_TIMESTAMP_END_2099;
 	rv3032->rtc->ops = &rv3032_rtc_ops;
-	ret = rtc_register_device(rv3032->rtc);
+	ret = devm_rtc_register_device(rv3032->rtc);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-rv8803.c b/drivers/rtc/rtc-rv8803.c
index 44e1818a751c..d4ea6db51b26 100644
--- a/drivers/rtc/rtc-rv8803.c
+++ b/drivers/rtc/rtc-rv8803.c
@@ -587,7 +587,7 @@ static int rv8803_probe(struct i2c_client *client,
 	rv8803->rtc->ops = &rv8803_rtc_ops;
 	rv8803->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	rv8803->rtc->range_max = RTC_TIMESTAMP_END_2099;
-	err = rtc_register_device(rv8803->rtc);
+	err = devm_rtc_register_device(rv8803->rtc);
 	if (err)
 		return err;
 
diff --git a/drivers/rtc/rtc-rx8010.c b/drivers/rtc/rtc-rx8010.c
index dca41a2a39b2..8340ab47a059 100644
--- a/drivers/rtc/rtc-rx8010.c
+++ b/drivers/rtc/rtc-rx8010.c
@@ -419,7 +419,7 @@ static int rx8010_probe(struct i2c_client *client)
 	rx8010->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	rx8010->rtc->range_max = RTC_TIMESTAMP_END_2099;
 
-	return rtc_register_device(rx8010->rtc);
+	return devm_rtc_register_device(rx8010->rtc);
 }
 
 static struct i2c_driver rx8010_driver = {
diff --git a/drivers/rtc/rtc-rx8581.c b/drivers/rtc/rtc-rx8581.c
index 017f74721cc0..de109139529b 100644
--- a/drivers/rtc/rtc-rx8581.c
+++ b/drivers/rtc/rtc-rx8581.c
@@ -298,7 +298,7 @@ static int rx8581_probe(struct i2c_client *client,
 	rx8581->rtc->start_secs = 0;
 	rx8581->rtc->set_start_time = true;
 
-	ret = rtc_register_device(rx8581->rtc);
+	ret = devm_rtc_register_device(rx8581->rtc);
 
 	for (i = 0; i < config->num_nvram; i++) {
 		nvmem_cfg[i].priv = rx8581;
diff --git a/drivers/rtc/rtc-s35390a.c b/drivers/rtc/rtc-s35390a.c
index 03672a246356..ea15d0392bb9 100644
--- a/drivers/rtc/rtc-s35390a.c
+++ b/drivers/rtc/rtc-s35390a.c
@@ -497,7 +497,7 @@ static int s35390a_probe(struct i2c_client *client,
 	if (status1 & S35390A_FLAG_INT2)
 		rtc_update_irq(s35390a->rtc, 1, RTC_AF);
 
-	return rtc_register_device(s35390a->rtc);
+	return devm_rtc_register_device(s35390a->rtc);
 }
 
 static struct i2c_driver s35390a_driver = {
diff --git a/drivers/rtc/rtc-sa1100.c b/drivers/rtc/rtc-sa1100.c
index 9ccc97cf5e09..1250887e4382 100644
--- a/drivers/rtc/rtc-sa1100.c
+++ b/drivers/rtc/rtc-sa1100.c
@@ -205,7 +205,7 @@ int sa1100_rtc_init(struct platform_device *pdev, struct sa1100_rtc *info)
 	info->rtc->max_user_freq = RTC_FREQ;
 	info->rtc->range_max = U32_MAX;
 
-	ret = rtc_register_device(info->rtc);
+	ret = devm_rtc_register_device(info->rtc);
 	if (ret) {
 		clk_disable_unprepare(info->clk);
 		return ret;
diff --git a/drivers/rtc/rtc-sc27xx.c b/drivers/rtc/rtc-sc27xx.c
index a953bc0a5a5b..187aa955b79c 100644
--- a/drivers/rtc/rtc-sc27xx.c
+++ b/drivers/rtc/rtc-sc27xx.c
@@ -618,7 +618,7 @@ static int sprd_rtc_probe(struct platform_device *pdev)
 	rtc->rtc->ops = &sprd_rtc_ops;
 	rtc->rtc->range_min = 0;
 	rtc->rtc->range_max = 5662310399LL;
-	ret = rtc_register_device(rtc->rtc);
+	ret = devm_rtc_register_device(rtc->rtc);
 	if (ret) {
 		device_init_wakeup(&pdev->dev, 0);
 		return ret;
diff --git a/drivers/rtc/rtc-sd3078.c b/drivers/rtc/rtc-sd3078.c
index a7aa943c1183..f6bee69ba017 100644
--- a/drivers/rtc/rtc-sd3078.c
+++ b/drivers/rtc/rtc-sd3078.c
@@ -192,7 +192,7 @@ static int sd3078_probe(struct i2c_client *client,
 	sd3078->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	sd3078->rtc->range_max = RTC_TIMESTAMP_END_2099;
 
-	ret = rtc_register_device(sd3078->rtc);
+	ret = devm_rtc_register_device(sd3078->rtc);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-sh.c b/drivers/rtc/rtc-sh.c
index 9167b48014a1..cd146b574143 100644
--- a/drivers/rtc/rtc-sh.c
+++ b/drivers/rtc/rtc-sh.c
@@ -607,7 +607,7 @@ static int __init sh_rtc_probe(struct platform_device *pdev)
 		rtc->rtc_dev->range_max = mktime64(2098, 12, 31, 23, 59, 59);
 	}
 
-	ret = rtc_register_device(rtc->rtc_dev);
+	ret = devm_rtc_register_device(rtc->rtc_dev);
 	if (ret)
 		goto err_unmap;
 
diff --git a/drivers/rtc/rtc-sirfsoc.c b/drivers/rtc/rtc-sirfsoc.c
index abf19435dbad..03a6cca23201 100644
--- a/drivers/rtc/rtc-sirfsoc.c
+++ b/drivers/rtc/rtc-sirfsoc.c
@@ -356,7 +356,7 @@ static int sirfsoc_rtc_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	return rtc_register_device(rtcdrv->rtc);
+	return devm_rtc_register_device(rtcdrv->rtc);
 }
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/rtc/rtc-snvs.c b/drivers/rtc/rtc-snvs.c
index a7d39a49b748..bd929b0e7d7d 100644
--- a/drivers/rtc/rtc-snvs.c
+++ b/drivers/rtc/rtc-snvs.c
@@ -387,7 +387,7 @@ static int snvs_rtc_probe(struct platform_device *pdev)
 	data->rtc->ops = &snvs_rtc_ops;
 	data->rtc->range_max = U32_MAX;
 
-	return rtc_register_device(data->rtc);
+	return devm_rtc_register_device(data->rtc);
 }
 
 static int __maybe_unused snvs_rtc_suspend_noirq(struct device *dev)
diff --git a/drivers/rtc/rtc-st-lpc.c b/drivers/rtc/rtc-st-lpc.c
index 0c65448b85ee..bdb20f63254e 100644
--- a/drivers/rtc/rtc-st-lpc.c
+++ b/drivers/rtc/rtc-st-lpc.c
@@ -250,7 +250,7 @@ static int st_rtc_probe(struct platform_device *pdev)
 	rtc->rtc_dev->range_max = U64_MAX;
 	do_div(rtc->rtc_dev->range_max, rtc->clkrate);
 
-	ret = rtc_register_device(rtc->rtc_dev);
+	ret = devm_rtc_register_device(rtc->rtc_dev);
 	if (ret) {
 		clk_disable_unprepare(rtc->clk);
 		return ret;
diff --git a/drivers/rtc/rtc-starfire.c b/drivers/rtc/rtc-starfire.c
index 37a26279e107..fbd1ed41cbf1 100644
--- a/drivers/rtc/rtc-starfire.c
+++ b/drivers/rtc/rtc-starfire.c
@@ -48,7 +48,7 @@ static int __init starfire_rtc_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, rtc);
 
-	return rtc_register_device(rtc);
+	return devm_rtc_register_device(rtc);
 }
 
 static struct platform_driver starfire_rtc_driver = {
diff --git a/drivers/rtc/rtc-stk17ta8.c b/drivers/rtc/rtc-stk17ta8.c
index ad616bce7bca..7cb6be1b7815 100644
--- a/drivers/rtc/rtc-stk17ta8.c
+++ b/drivers/rtc/rtc-stk17ta8.c
@@ -317,7 +317,7 @@ static int stk17ta8_rtc_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	return rtc_register_device(pdata->rtc);
+	return devm_rtc_register_device(pdata->rtc);
 }
 
 /* work with hotplug and coldplug */
diff --git a/drivers/rtc/rtc-stmp3xxx.c b/drivers/rtc/rtc-stmp3xxx.c
index 0a969af80af7..40c0f7ed36e0 100644
--- a/drivers/rtc/rtc-stmp3xxx.c
+++ b/drivers/rtc/rtc-stmp3xxx.c
@@ -366,7 +366,7 @@ static int stmp3xxx_rtc_probe(struct platform_device *pdev)
 	rtc_data->rtc->ops = &stmp3xxx_rtc_ops;
 	rtc_data->rtc->range_max = U32_MAX;
 
-	err = rtc_register_device(rtc_data->rtc);
+	err = devm_rtc_register_device(rtc_data->rtc);
 	if (err)
 		return err;
 
diff --git a/drivers/rtc/rtc-sun4v.c b/drivers/rtc/rtc-sun4v.c
index 036463dfa103..a86e27de8c06 100644
--- a/drivers/rtc/rtc-sun4v.c
+++ b/drivers/rtc/rtc-sun4v.c
@@ -86,7 +86,7 @@ static int __init sun4v_rtc_probe(struct platform_device *pdev)
 	rtc->range_max = U64_MAX;
 	platform_set_drvdata(pdev, rtc);
 
-	return rtc_register_device(rtc);
+	return devm_rtc_register_device(rtc);
 }
 
 static struct platform_driver sun4v_rtc_driver = {
diff --git a/drivers/rtc/rtc-sun6i.c b/drivers/rtc/rtc-sun6i.c
index f2818cdd11d8..adec1b14a8de 100644
--- a/drivers/rtc/rtc-sun6i.c
+++ b/drivers/rtc/rtc-sun6i.c
@@ -726,7 +726,7 @@ static int sun6i_rtc_probe(struct platform_device *pdev)
 	chip->rtc->ops = &sun6i_rtc_ops;
 	chip->rtc->range_max = 2019686399LL; /* 2033-12-31 23:59:59 */
 
-	ret = rtc_register_device(chip->rtc);
+	ret = devm_rtc_register_device(chip->rtc);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-sunxi.c b/drivers/rtc/rtc-sunxi.c
index f5d7f44550ce..5d019e3a835a 100644
--- a/drivers/rtc/rtc-sunxi.c
+++ b/drivers/rtc/rtc-sunxi.c
@@ -470,7 +470,7 @@ static int sunxi_rtc_probe(struct platform_device *pdev)
 
 	chip->rtc->ops = &sunxi_rtc_ops;
 
-	return rtc_register_device(chip->rtc);
+	return devm_rtc_register_device(chip->rtc);
 }
 
 static struct platform_driver sunxi_rtc_driver = {
diff --git a/drivers/rtc/rtc-tegra.c b/drivers/rtc/rtc-tegra.c
index 7fbb1741692f..8925015cc698 100644
--- a/drivers/rtc/rtc-tegra.c
+++ b/drivers/rtc/rtc-tegra.c
@@ -329,7 +329,7 @@ static int tegra_rtc_probe(struct platform_device *pdev)
 		goto disable_clk;
 	}
 
-	ret = rtc_register_device(info->rtc);
+	ret = devm_rtc_register_device(info->rtc);
 	if (ret)
 		goto disable_clk;
 
diff --git a/drivers/rtc/rtc-test.c b/drivers/rtc/rtc-test.c
index 74b3a0603b73..b092a1648513 100644
--- a/drivers/rtc/rtc-test.c
+++ b/drivers/rtc/rtc-test.c
@@ -139,7 +139,7 @@ static int test_probe(struct platform_device *plat_dev)
 	timer_setup(&rtd->alarm, test_rtc_alarm_handler, 0);
 	rtd->alarm.expires = 0;
 
-	return rtc_register_device(rtd->rtc);
+	return devm_rtc_register_device(rtd->rtc);
 }
 
 static struct platform_driver test_driver = {
diff --git a/drivers/rtc/rtc-tps6586x.c b/drivers/rtc/rtc-tps6586x.c
index e39af2d67051..a980337c3065 100644
--- a/drivers/rtc/rtc-tps6586x.c
+++ b/drivers/rtc/rtc-tps6586x.c
@@ -280,7 +280,7 @@ static int tps6586x_rtc_probe(struct platform_device *pdev)
 		goto fail_rtc_register;
 	}
 
-	ret = rtc_register_device(rtc->rtc);
+	ret = devm_rtc_register_device(rtc->rtc);
 	if (ret)
 		goto fail_rtc_register;
 
diff --git a/drivers/rtc/rtc-tps65910.c b/drivers/rtc/rtc-tps65910.c
index e3840386f430..2d87b62826a8 100644
--- a/drivers/rtc/rtc-tps65910.c
+++ b/drivers/rtc/rtc-tps65910.c
@@ -434,7 +434,7 @@ static int tps65910_rtc_probe(struct platform_device *pdev)
 	tps_rtc->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	tps_rtc->rtc->range_max = RTC_TIMESTAMP_END_2099;
 
-	return rtc_register_device(tps_rtc->rtc);
+	return devm_rtc_register_device(tps_rtc->rtc);
 }
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/rtc/rtc-tx4939.c b/drivers/rtc/rtc-tx4939.c
index 11f46272bad3..c3309db5448d 100644
--- a/drivers/rtc/rtc-tx4939.c
+++ b/drivers/rtc/rtc-tx4939.c
@@ -275,7 +275,7 @@ static int __init tx4939_rtc_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	return rtc_register_device(rtc);
+	return devm_rtc_register_device(rtc);
 }
 
 static int __exit tx4939_rtc_remove(struct platform_device *pdev)
diff --git a/drivers/rtc/rtc-vr41xx.c b/drivers/rtc/rtc-vr41xx.c
index c3671043ace7..5a9f9ad86d32 100644
--- a/drivers/rtc/rtc-vr41xx.c
+++ b/drivers/rtc/rtc-vr41xx.c
@@ -335,7 +335,7 @@ static int rtc_probe(struct platform_device *pdev)
 
 	dev_info(&pdev->dev, "Real Time Clock of NEC VR4100 series\n");
 
-	retval = rtc_register_device(rtc);
+	retval = devm_rtc_register_device(rtc);
 	if (retval)
 		goto err_iounmap_all;
 
diff --git a/drivers/rtc/rtc-vt8500.c b/drivers/rtc/rtc-vt8500.c
index e2588625025f..197b649cd629 100644
--- a/drivers/rtc/rtc-vt8500.c
+++ b/drivers/rtc/rtc-vt8500.c
@@ -232,7 +232,7 @@ static int vt8500_rtc_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	return rtc_register_device(vt8500_rtc->rtc);
+	return devm_rtc_register_device(vt8500_rtc->rtc);
 }
 
 static int vt8500_rtc_remove(struct platform_device *pdev)
diff --git a/drivers/rtc/rtc-wilco-ec.c b/drivers/rtc/rtc-wilco-ec.c
index ff46066a68a4..2a205a646452 100644
--- a/drivers/rtc/rtc-wilco-ec.c
+++ b/drivers/rtc/rtc-wilco-ec.c
@@ -176,7 +176,7 @@ static int wilco_ec_rtc_probe(struct platform_device *pdev)
 	rtc->range_max = RTC_TIMESTAMP_END_2099;
 	rtc->owner = THIS_MODULE;
 
-	return rtc_register_device(rtc);
+	return devm_rtc_register_device(rtc);
 }
 
 static struct platform_driver wilco_ec_rtc_driver = {
diff --git a/drivers/rtc/rtc-wm831x.c b/drivers/rtc/rtc-wm831x.c
index ccef887d2690..640833e21057 100644
--- a/drivers/rtc/rtc-wm831x.c
+++ b/drivers/rtc/rtc-wm831x.c
@@ -429,7 +429,7 @@ static int wm831x_rtc_probe(struct platform_device *pdev)
 	wm831x_rtc->rtc->ops = &wm831x_rtc_ops;
 	wm831x_rtc->rtc->range_max = U32_MAX;
 
-	ret = rtc_register_device(wm831x_rtc->rtc);
+	ret = devm_rtc_register_device(wm831x_rtc->rtc);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-xgene.c b/drivers/rtc/rtc-xgene.c
index 96db441f92b3..cf68a9b1c9eb 100644
--- a/drivers/rtc/rtc-xgene.c
+++ b/drivers/rtc/rtc-xgene.c
@@ -185,7 +185,7 @@ static int xgene_rtc_probe(struct platform_device *pdev)
 	pdata->rtc->ops = &xgene_rtc_ops;
 	pdata->rtc->range_max = U32_MAX;
 
-	ret = rtc_register_device(pdata->rtc);
+	ret = devm_rtc_register_device(pdata->rtc);
 	if (ret) {
 		clk_disable_unprepare(pdata->clk);
 		return ret;
diff --git a/drivers/rtc/rtc-zynqmp.c b/drivers/rtc/rtc-zynqmp.c
index 4b1077e2f826..f440bb52be92 100644
--- a/drivers/rtc/rtc-zynqmp.c
+++ b/drivers/rtc/rtc-zynqmp.c
@@ -264,7 +264,7 @@ static int xlnx_rtc_probe(struct platform_device *pdev)
 
 	device_init_wakeup(&pdev->dev, 1);
 
-	return rtc_register_device(xrtcdev->rtc);
+	return devm_rtc_register_device(xrtcdev->rtc);
 }
 
 static int xlnx_rtc_remove(struct platform_device *pdev)
diff --git a/drivers/rtc/sysfs.c b/drivers/rtc/sysfs.c
index 950fac0d41ff..8a957d31a1a4 100644
--- a/drivers/rtc/sysfs.c
+++ b/drivers/rtc/sysfs.c
@@ -317,8 +317,6 @@ int rtc_add_groups(struct rtc_device *rtc, const struct attribute_group **grps)
 	size_t old_cnt = 0, add_cnt = 0, new_cnt;
 	const struct attribute_group **groups, **old;
 
-	if (rtc->registered)
-		return -EINVAL;
 	if (!grps)
 		return -EINVAL;
 
diff --git a/include/linux/rtc.h b/include/linux/rtc.h
index cbca651d8ca4..55e7beed066c 100644
--- a/include/linux/rtc.h
+++ b/include/linux/rtc.h
@@ -118,8 +118,6 @@ struct rtc_device {
 	 */
 	long set_offset_nsec;
 
-	bool registered;
-
 	time64_t range_min;
 	timeu64_t range_max;
 	time64_t start_secs;
@@ -157,7 +155,7 @@ extern struct rtc_device *devm_rtc_device_register(struct device *dev,
 					const struct rtc_class_ops *ops,
 					struct module *owner);
 struct rtc_device *devm_rtc_allocate_device(struct device *dev);
-int __rtc_register_device(struct module *owner, struct rtc_device *rtc);
+int __devm_rtc_register_device(struct module *owner, struct rtc_device *rtc);
 
 extern int rtc_read_time(struct rtc_device *rtc, struct rtc_time *tm);
 extern int rtc_set_time(struct rtc_device *rtc, struct rtc_time *tm);
@@ -234,8 +232,8 @@ static inline bool rtc_tv_nsec_ok(s64 set_offset_nsec,
 	return false;
 }
 
-#define rtc_register_device(device) \
-	__rtc_register_device(THIS_MODULE, device)
+#define devm_rtc_register_device(device) \
+	__devm_rtc_register_device(THIS_MODULE, device)
 
 #ifdef CONFIG_RTC_HCTOSYS_DEVICE
 extern int rtc_hctosys_ret;
-- 
cgit v1.2.3


From e1cef2d4c379b2aab43a7dc9601f645048209090 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 19 Nov 2020 14:53:40 +0900
Subject: tools/bootconfig: Align the bootconfig applied initrd image size to 4

Align the bootconfig applied initrd image size to 4. To fill the gap,
the bootconfig command uses null characters in between the bootconfig
data and the footer. This will expands the footer size but don't change
the checksum.
Thus the block image of the initrd file with bootconfig is as follows.

[initrd][bootconfig][(pad)][size][csum]["#BOOTCONFIG\n"]

Link: https://lkml.kernel.org/r/160576522046.320071.8550680670010950634.stgit@devnote2

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/bootconfig.h          |  3 ++
 tools/bootconfig/main.c             | 57 ++++++++++++++++++++++---------------
 tools/bootconfig/test-bootconfig.sh |  6 +++-
 3 files changed, 42 insertions(+), 24 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h
index 9903088891fa..2696eb0fc149 100644
--- a/include/linux/bootconfig.h
+++ b/include/linux/bootconfig.h
@@ -12,6 +12,9 @@
 
 #define BOOTCONFIG_MAGIC	"#BOOTCONFIG\n"
 #define BOOTCONFIG_MAGIC_LEN	12
+#define BOOTCONFIG_ALIGN_SHIFT	2
+#define BOOTCONFIG_ALIGN	(1 << BOOTCONFIG_ALIGN_SHIFT)
+#define BOOTCONFIG_ALIGN_MASK	(BOOTCONFIG_ALIGN - 1)
 
 /* XBC tree node */
 struct xbc_node {
diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c
index a0733cbb3c49..4a445b6304bb 100644
--- a/tools/bootconfig/main.c
+++ b/tools/bootconfig/main.c
@@ -337,12 +337,13 @@ static int delete_xbc(const char *path)
 
 static int apply_xbc(const char *path, const char *xbc_path)
 {
+	char *buf, *data, *p;
+	size_t total_size;
 	struct stat stat;
+	const char *msg;
 	u32 size, csum;
-	char *buf, *data;
+	int pos, pad;
 	int ret, fd;
-	const char *msg;
-	int pos;
 
 	ret = load_xbc_file(xbc_path, &buf);
 	if (ret < 0) {
@@ -352,13 +353,12 @@ static int apply_xbc(const char *path, const char *xbc_path)
 	size = strlen(buf) + 1;
 	csum = checksum((unsigned char *)buf, size);
 
-	/* Prepare xbc_path data */
-	data = malloc(size + 8);
+	/* Backup the bootconfig data */
+	data = calloc(size + BOOTCONFIG_ALIGN +
+		      sizeof(u32) + sizeof(u32) + BOOTCONFIG_MAGIC_LEN, 1);
 	if (!data)
 		return -ENOMEM;
-	strcpy(data, buf);
-	*(u32 *)(data + size) = size;
-	*(u32 *)(data + size + 4) = csum;
+	memcpy(data, buf, size);
 
 	/* Check the data format */
 	ret = xbc_init(buf, &msg, &pos);
@@ -399,24 +399,35 @@ static int apply_xbc(const char *path, const char *xbc_path)
 		pr_err("Failed to get the size of %s\n", path);
 		goto out;
 	}
-	ret = write(fd, data, size + 8);
-	if (ret < size + 8) {
+
+	/* To align up the total size to BOOTCONFIG_ALIGN, get padding size */
+	total_size = stat.st_size + size + sizeof(u32) * 2 + BOOTCONFIG_MAGIC_LEN;
+	pad = ((total_size + BOOTCONFIG_ALIGN - 1) & (~BOOTCONFIG_ALIGN_MASK)) - total_size;
+	size += pad;
+
+	/* Add a footer */
+	p = data + size;
+	*(u32 *)p = size;
+	p += sizeof(u32);
+
+	*(u32 *)p = csum;
+	p += sizeof(u32);
+
+	memcpy(p, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN);
+	p += BOOTCONFIG_MAGIC_LEN;
+
+	total_size = p - data;
+
+	ret = write(fd, data, total_size);
+	if (ret < total_size) {
 		if (ret < 0)
 			ret = -errno;
 		pr_err("Failed to apply a boot config: %d\n", ret);
-		if (ret < 0)
-			goto out;
-		goto out_rollback;
-	}
-	/* Write a magic word of the bootconfig */
-	ret = write(fd, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN);
-	if (ret < BOOTCONFIG_MAGIC_LEN) {
-		if (ret < 0)
-			ret = -errno;
-		pr_err("Failed to apply a boot config magic: %d\n", ret);
-		goto out_rollback;
-	}
-	ret = 0;
+		if (ret >= 0)
+			goto out_rollback;
+	} else
+		ret = 0;
+
 out:
 	close(fd);
 	free(data);
diff --git a/tools/bootconfig/test-bootconfig.sh b/tools/bootconfig/test-bootconfig.sh
index d295e406a756..baed891d0ba4 100755
--- a/tools/bootconfig/test-bootconfig.sh
+++ b/tools/bootconfig/test-bootconfig.sh
@@ -9,6 +9,7 @@ else
   TESTDIR=.
 fi
 BOOTCONF=${TESTDIR}/bootconfig
+ALIGN=4
 
 INITRD=`mktemp ${TESTDIR}/initrd-XXXX`
 TEMPCONF=`mktemp ${TESTDIR}/temp-XXXX.bconf`
@@ -59,7 +60,10 @@ echo "Show command test"
 xpass $BOOTCONF $INITRD
 
 echo "File size check"
-xpass test $new_size -eq $(expr $bconf_size + $initrd_size + 9 + 12)
+total_size=$(expr $bconf_size + $initrd_size + 9 + 12 + $ALIGN - 1 )
+total_size=$(expr $total_size / $ALIGN)
+total_size=$(expr $total_size \* $ALIGN)
+xpass test $new_size -eq $total_size
 
 echo "Apply command repeat test"
 xpass $BOOTCONF -a $TEMPCONF $INITRD
-- 
cgit v1.2.3


From bc1c99a5971aa7571e8b9731c28fa32abe12cab8 Mon Sep 17 00:00:00 2001
From: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
Date: Tue, 17 Nov 2020 20:49:52 +0800
Subject: EDAC: Add DDR5 new memory type

Add a new entry to 'enum mem_type' and a new string to
'edac_mem_types[]' for DDR5 new memory type.

Signed-off-by: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
---
 drivers/edac/edac_mc.c | 1 +
 include/linux/edac.h   | 3 +++
 2 files changed, 4 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index eef8724faae0..f6d462d0be2d 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -163,6 +163,7 @@ const char * const edac_mem_types[] = {
 	[MEM_RDDR4]	= "Registered-DDR4",
 	[MEM_LPDDR4]	= "Low-Power-DDR4-RAM",
 	[MEM_LRDDR4]	= "Load-Reduced-DDR4-RAM",
+	[MEM_DDR5]	= "Unbuffered-DDR5",
 	[MEM_NVDIMM]	= "Non-volatile-RAM",
 	[MEM_WIO2]	= "Wide-IO-2",
 };
diff --git a/include/linux/edac.h b/include/linux/edac.h
index 8f63245f7f7c..e64b73b556eb 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -181,6 +181,7 @@ static inline char *mc_event_error_type(const unsigned int err_type)
  *			This is a variant of the DDR4 memories.
  * @MEM_LRDDR4:		Load-Reduced DDR4 memory.
  * @MEM_LPDDR4:		Low-Power DDR4 memory.
+ * @MEM_DDR5:		Unbuffered DDR5 RAM
  * @MEM_NVDIMM:		Non-volatile RAM
  * @MEM_WIO2:		Wide I/O 2.
  */
@@ -208,6 +209,7 @@ enum mem_type {
 	MEM_RDDR4,
 	MEM_LRDDR4,
 	MEM_LPDDR4,
+	MEM_DDR5,
 	MEM_NVDIMM,
 	MEM_WIO2,
 };
@@ -234,6 +236,7 @@ enum mem_type {
 #define MEM_FLAG_RDDR4          BIT(MEM_RDDR4)
 #define MEM_FLAG_LRDDR4         BIT(MEM_LRDDR4)
 #define MEM_FLAG_LPDDR4         BIT(MEM_LPDDR4)
+#define MEM_FLAG_DDR5           BIT(MEM_DDR5)
 #define MEM_FLAG_NVDIMM         BIT(MEM_NVDIMM)
 #define MEM_FLAG_WIO2		BIT(MEM_WIO2)
 
-- 
cgit v1.2.3


From dfe564045c653d9e6969ccca57a8a04771d333f7 Mon Sep 17 00:00:00 2001
From: chao <chao@eero.com>
Date: Sun, 30 Aug 2020 23:41:17 -0700
Subject: rcu: Panic after fixed number of stalls

Some stalls are transient, so that system fully recovers.  This commit
therefore allows users to configure the number of stalls that must happen
in order to trigger kernel panic.

Signed-off-by: chao <chao@eero.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/kernel.h  |  1 +
 kernel/rcu/tree_stall.h |  6 ++++++
 kernel/sysctl.c         | 11 +++++++++++
 3 files changed, 18 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 2f05e9128201..4b5fd3da5fe8 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -536,6 +536,7 @@ extern int panic_on_warn;
 extern unsigned long panic_on_taint;
 extern bool panic_on_taint_nousertaint;
 extern int sysctl_panic_on_rcu_stall;
+extern int sysctl_max_rcu_stall_to_panic;
 extern int sysctl_panic_on_stackoverflow;
 
 extern bool crash_kexec_post_notifiers;
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index ca21d28a0f98..70d48c52fabc 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -13,6 +13,7 @@
 
 /* panic() on RCU Stall sysctl. */
 int sysctl_panic_on_rcu_stall __read_mostly;
+int sysctl_max_rcu_stall_to_panic __read_mostly;
 
 #ifdef CONFIG_PROVE_RCU
 #define RCU_STALL_DELAY_DELTA		(5 * HZ)
@@ -106,6 +107,11 @@ early_initcall(check_cpu_stall_init);
 /* If so specified via sysctl, panic, yielding cleaner stall-warning output. */
 static void panic_on_rcu_stall(void)
 {
+	static int cpu_stall;
+
+	if (++cpu_stall < sysctl_max_rcu_stall_to_panic)
+		return;
+
 	if (sysctl_panic_on_rcu_stall)
 		panic("RCU Stall\n");
 }
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index afad085960b8..c9fbdd848138 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2650,6 +2650,17 @@ static struct ctl_table kern_table[] = {
 		.extra2		= SYSCTL_ONE,
 	},
 #endif
+#if defined(CONFIG_TREE_RCU)
+	{
+		.procname	= "max_rcu_stall_to_panic",
+		.data		= &sysctl_max_rcu_stall_to_panic,
+		.maxlen		= sizeof(sysctl_max_rcu_stall_to_panic),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ONE,
+		.extra2		= SYSCTL_INT_MAX,
+	},
+#endif
 #ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE
 	{
 		.procname	= "stack_erasing",
-- 
cgit v1.2.3


From 1eafe075bf9cb4db575be4ddf1b1c8256758714a Mon Sep 17 00:00:00 2001
From: Asif Rasheed <b00073877@aus.edu>
Date: Sun, 20 Sep 2020 17:31:54 +0400
Subject: list.h: Update comment to explicitly note circular lists

The students in the Operating System Lecture Section at the
American University of Sharjah were confused by the header comment
in include/linux/list.h, which says "Simple doubly linked list
implementation".  This comment means "simple" as in "not complex",
but "simple" is often used in this context to mean "not circular".
This commit therefore avoids this ambiguity by explicitly calling out
"circular".

Signed-off-by: Asif Rasheed <b00073877@aus.edu>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/list.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/list.h b/include/linux/list.h
index a18c87b63376..89bdc92e75c3 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -9,7 +9,7 @@
 #include <linux/kernel.h>
 
 /*
- * Simple doubly linked list implementation.
+ * Circular doubly linked list implementation.
  *
  * Some of the internal functions ("__xxx") are useful when
  * manipulating whole lists rather than single entries, as
-- 
cgit v1.2.3


From 2bf31d94423c8ae3ff58e38a115b177df6940399 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Mon, 16 Nov 2020 11:18:08 +0100
Subject: jbd2: fix kernel-doc markups

Kernel-doc markup should use this format:
        identifier - description

They should not have any type before that, as otherwise
the parser won't do the right thing.

Also, some identifiers have different names between their
prototypes and the kernel-doc markup.

Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Link: https://lore.kernel.org/r/72f5c6628f5f278d67625f60893ffbc2ca28d46e.1605521731.git.mchehab+huawei@kernel.org
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/jbd2/journal.c     | 34 ++++++++++++++++++----------------
 fs/jbd2/transaction.c | 31 ++++++++++++++++---------------
 include/linux/jbd2.h  |  2 +-
 3 files changed, 35 insertions(+), 32 deletions(-)

(limited to 'include/linux')

diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 0c3d5e3b24b2..188f79d76988 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -566,12 +566,14 @@ static int __jbd2_journal_force_commit(journal_t *journal)
 }
 
 /**
- * Force and wait upon a commit if the calling process is not within
- * transaction.  This is used for forcing out undo-protected data which contains
- * bitmaps, when the fs is running out of space.
+ * jbd2_journal_force_commit_nested - Force and wait upon a commit if the
+ * calling process is not within transaction.
  *
  * @journal: journal to force
  * Returns true if progress was made.
+ *
+ * This is used for forcing out undo-protected data which contains
+ * bitmaps, when the fs is running out of space.
  */
 int jbd2_journal_force_commit_nested(journal_t *journal)
 {
@@ -582,7 +584,7 @@ int jbd2_journal_force_commit_nested(journal_t *journal)
 }
 
 /**
- * int journal_force_commit() - force any uncommitted transactions
+ * jbd2_journal_force_commit() - force any uncommitted transactions
  * @journal: journal to force
  *
  * Caller want unconditional commit. We can only force the running transaction
@@ -1881,7 +1883,7 @@ static int load_superblock(journal_t *journal)
 
 
 /**
- * int jbd2_journal_load() - Read journal from disk.
+ * jbd2_journal_load() - Read journal from disk.
  * @journal: Journal to act on.
  *
  * Given a journal_t structure which tells us which disk blocks contain
@@ -1951,7 +1953,7 @@ recovery_error:
 }
 
 /**
- * void jbd2_journal_destroy() - Release a journal_t structure.
+ * jbd2_journal_destroy() - Release a journal_t structure.
  * @journal: Journal to act on.
  *
  * Release a journal_t structure once it is no longer in use by the
@@ -2028,7 +2030,7 @@ int jbd2_journal_destroy(journal_t *journal)
 
 
 /**
- *int jbd2_journal_check_used_features() - Check if features specified are used.
+ * jbd2_journal_check_used_features() - Check if features specified are used.
  * @journal: Journal to check.
  * @compat: bitmask of compatible features
  * @ro: bitmask of features that force read-only mount
@@ -2063,7 +2065,7 @@ int jbd2_journal_check_used_features(journal_t *journal, unsigned long compat,
 }
 
 /**
- * int jbd2_journal_check_available_features() - Check feature set in journalling layer
+ * jbd2_journal_check_available_features() - Check feature set in journalling layer
  * @journal: Journal to check.
  * @compat: bitmask of compatible features
  * @ro: bitmask of features that force read-only mount
@@ -2126,7 +2128,7 @@ jbd2_journal_initialize_fast_commit(journal_t *journal)
 }
 
 /**
- * int jbd2_journal_set_features() - Mark a given journal feature in the superblock
+ * jbd2_journal_set_features() - Mark a given journal feature in the superblock
  * @journal: Journal to act on.
  * @compat: bitmask of compatible features
  * @ro: bitmask of features that force read-only mount
@@ -2217,7 +2219,7 @@ int jbd2_journal_set_features(journal_t *journal, unsigned long compat,
 }
 
 /*
- * jbd2_journal_clear_features () - Clear a given journal feature in the
+ * jbd2_journal_clear_features() - Clear a given journal feature in the
  * 				    superblock
  * @journal: Journal to act on.
  * @compat: bitmask of compatible features
@@ -2246,7 +2248,7 @@ void jbd2_journal_clear_features(journal_t *journal, unsigned long compat,
 EXPORT_SYMBOL(jbd2_journal_clear_features);
 
 /**
- * int jbd2_journal_flush () - Flush journal
+ * jbd2_journal_flush() - Flush journal
  * @journal: Journal to act on.
  *
  * Flush all data for a given journal to disk and empty the journal.
@@ -2321,7 +2323,7 @@ out:
 }
 
 /**
- * int jbd2_journal_wipe() - Wipe journal contents
+ * jbd2_journal_wipe() - Wipe journal contents
  * @journal: Journal to act on.
  * @write: flag (see below)
  *
@@ -2362,7 +2364,7 @@ int jbd2_journal_wipe(journal_t *journal, int write)
 }
 
 /**
- * void jbd2_journal_abort () - Shutdown the journal immediately.
+ * jbd2_journal_abort () - Shutdown the journal immediately.
  * @journal: the journal to shutdown.
  * @errno:   an error number to record in the journal indicating
  *           the reason for the shutdown.
@@ -2453,7 +2455,7 @@ void jbd2_journal_abort(journal_t *journal, int errno)
 }
 
 /**
- * int jbd2_journal_errno () - returns the journal's error state.
+ * jbd2_journal_errno() - returns the journal's error state.
  * @journal: journal to examine.
  *
  * This is the errno number set with jbd2_journal_abort(), the last
@@ -2477,7 +2479,7 @@ int jbd2_journal_errno(journal_t *journal)
 }
 
 /**
- * int jbd2_journal_clear_err () - clears the journal's error state
+ * jbd2_journal_clear_err() - clears the journal's error state
  * @journal: journal to act on.
  *
  * An error must be cleared or acked to take a FS out of readonly
@@ -2497,7 +2499,7 @@ int jbd2_journal_clear_err(journal_t *journal)
 }
 
 /**
- * void jbd2_journal_ack_err() - Ack journal err.
+ * jbd2_journal_ack_err() - Ack journal err.
  * @journal: journal to act on.
  *
  * An error must be cleared or acked to take a FS out of readonly
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index d54f04674e8e..9396666b7314 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -519,7 +519,7 @@ EXPORT_SYMBOL(jbd2__journal_start);
 
 
 /**
- * handle_t *jbd2_journal_start() - Obtain a new handle.
+ * jbd2_journal_start() - Obtain a new handle.
  * @journal: Journal to start transaction on.
  * @nblocks: number of block buffer we might modify
  *
@@ -566,7 +566,7 @@ void jbd2_journal_free_reserved(handle_t *handle)
 EXPORT_SYMBOL(jbd2_journal_free_reserved);
 
 /**
- * int jbd2_journal_start_reserved() - start reserved handle
+ * jbd2_journal_start_reserved() - start reserved handle
  * @handle: handle to start
  * @type: for handle statistics
  * @line_no: for handle statistics
@@ -620,7 +620,7 @@ int jbd2_journal_start_reserved(handle_t *handle, unsigned int type,
 EXPORT_SYMBOL(jbd2_journal_start_reserved);
 
 /**
- * int jbd2_journal_extend() - extend buffer credits.
+ * jbd2_journal_extend() - extend buffer credits.
  * @handle:  handle to 'extend'
  * @nblocks: nr blocks to try to extend by.
  * @revoke_records: number of revoke records to try to extend by.
@@ -745,7 +745,7 @@ static void stop_this_handle(handle_t *handle)
 }
 
 /**
- * int jbd2_journal_restart() - restart a handle .
+ * jbd2__journal_restart() - restart a handle .
  * @handle:  handle to restart
  * @nblocks: nr credits requested
  * @revoke_records: number of revoke record credits requested
@@ -815,7 +815,7 @@ int jbd2_journal_restart(handle_t *handle, int nblocks)
 EXPORT_SYMBOL(jbd2_journal_restart);
 
 /**
- * void jbd2_journal_lock_updates () - establish a transaction barrier.
+ * jbd2_journal_lock_updates () - establish a transaction barrier.
  * @journal:  Journal to establish a barrier on.
  *
  * This locks out any further updates from being started, and blocks
@@ -874,7 +874,7 @@ void jbd2_journal_lock_updates(journal_t *journal)
 }
 
 /**
- * void jbd2_journal_unlock_updates (journal_t* journal) - release barrier
+ * jbd2_journal_unlock_updates () - release barrier
  * @journal:  Journal to release the barrier on.
  *
  * Release a transaction barrier obtained with jbd2_journal_lock_updates().
@@ -1182,7 +1182,8 @@ out:
 }
 
 /**
- * int jbd2_journal_get_write_access() - notify intent to modify a buffer for metadata (not data) update.
+ * jbd2_journal_get_write_access() - notify intent to modify a buffer
+ *				     for metadata (not data) update.
  * @handle: transaction to add buffer modifications to
  * @bh:     bh to be used for metadata writes
  *
@@ -1226,7 +1227,7 @@ int jbd2_journal_get_write_access(handle_t *handle, struct buffer_head *bh)
  * unlocked buffer beforehand. */
 
 /**
- * int jbd2_journal_get_create_access () - notify intent to use newly created bh
+ * jbd2_journal_get_create_access () - notify intent to use newly created bh
  * @handle: transaction to new buffer to
  * @bh: new buffer.
  *
@@ -1306,7 +1307,7 @@ out:
 }
 
 /**
- * int jbd2_journal_get_undo_access() -  Notify intent to modify metadata with
+ * jbd2_journal_get_undo_access() -  Notify intent to modify metadata with
  *     non-rewindable consequences
  * @handle: transaction
  * @bh: buffer to undo
@@ -1383,7 +1384,7 @@ out:
 }
 
 /**
- * void jbd2_journal_set_triggers() - Add triggers for commit writeout
+ * jbd2_journal_set_triggers() - Add triggers for commit writeout
  * @bh: buffer to trigger on
  * @type: struct jbd2_buffer_trigger_type containing the trigger(s).
  *
@@ -1425,7 +1426,7 @@ void jbd2_buffer_abort_trigger(struct journal_head *jh,
 }
 
 /**
- * int jbd2_journal_dirty_metadata() -  mark a buffer as containing dirty metadata
+ * jbd2_journal_dirty_metadata() -  mark a buffer as containing dirty metadata
  * @handle: transaction to add buffer to.
  * @bh: buffer to mark
  *
@@ -1593,7 +1594,7 @@ out:
 }
 
 /**
- * void jbd2_journal_forget() - bforget() for potentially-journaled buffers.
+ * jbd2_journal_forget() - bforget() for potentially-journaled buffers.
  * @handle: transaction handle
  * @bh:     bh to 'forget'
  *
@@ -1762,7 +1763,7 @@ drop:
 }
 
 /**
- * int jbd2_journal_stop() - complete a transaction
+ * jbd2_journal_stop() - complete a transaction
  * @handle: transaction to complete.
  *
  * All done for a particular handle.
@@ -2080,7 +2081,7 @@ out:
 }
 
 /**
- * int jbd2_journal_try_to_free_buffers() - try to free page buffers.
+ * jbd2_journal_try_to_free_buffers() - try to free page buffers.
  * @journal: journal for operation
  * @page: to try and free
  *
@@ -2411,7 +2412,7 @@ zap_buffer_unlocked:
 }
 
 /**
- * void jbd2_journal_invalidatepage()
+ * jbd2_journal_invalidatepage()
  * @journal: journal to use for flush...
  * @page:    page to flush
  * @offset:  start of the range to invalidate
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 1c49fd62ff2e..578ff196b3ce 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -401,7 +401,7 @@ static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh)
 #define JI_WAIT_DATA (1 << __JI_WAIT_DATA)
 
 /**
- * struct jbd_inode - The jbd_inode type is the structure linking inodes in
+ * struct jbd2_inode - The jbd_inode type is the structure linking inodes in
  * ordered mode present in a transaction so that we can sync them during commit.
  */
 struct jbd2_inode {
-- 
cgit v1.2.3


From a24d22b225ce158651378869a6b88105c4bdb887 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Thu, 12 Nov 2020 21:20:21 -0800
Subject: crypto: sha - split sha.h into sha1.h and sha2.h

Currently <crypto/sha.h> contains declarations for both SHA-1 and SHA-2,
and <crypto/sha3.h> contains declarations for SHA-3.

This organization is inconsistent, but more importantly SHA-1 is no
longer considered to be cryptographically secure.  So to the extent
possible, SHA-1 shouldn't be grouped together with any of the other SHA
versions, and usage of it should be phased out.

Therefore, split <crypto/sha.h> into two headers <crypto/sha1.h> and
<crypto/sha2.h>, and make everyone explicitly specify whether they want
the declarations for SHA-1, SHA-2, or both.

This avoids making the SHA-1 declarations visible to files that don't
want anything to do with SHA-1.  It also prepares for potentially moving
sha1.h into a new insecure/ or dangerous/ directory.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Acked-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 arch/arm/crypto/sha1-ce-glue.c                     |   2 +-
 arch/arm/crypto/sha1.h                             |   2 +-
 arch/arm/crypto/sha1_glue.c                        |   2 +-
 arch/arm/crypto/sha1_neon_glue.c                   |   2 +-
 arch/arm/crypto/sha2-ce-glue.c                     |   2 +-
 arch/arm/crypto/sha256_glue.c                      |   2 +-
 arch/arm/crypto/sha256_neon_glue.c                 |   2 +-
 arch/arm/crypto/sha512-glue.c                      |   2 +-
 arch/arm/crypto/sha512-neon-glue.c                 |   2 +-
 arch/arm64/crypto/aes-glue.c                       |   2 +-
 arch/arm64/crypto/sha1-ce-glue.c                   |   2 +-
 arch/arm64/crypto/sha2-ce-glue.c                   |   2 +-
 arch/arm64/crypto/sha256-glue.c                    |   2 +-
 arch/arm64/crypto/sha512-ce-glue.c                 |   2 +-
 arch/arm64/crypto/sha512-glue.c                    |   2 +-
 arch/mips/cavium-octeon/crypto/octeon-sha1.c       |   2 +-
 arch/mips/cavium-octeon/crypto/octeon-sha256.c     |   2 +-
 arch/mips/cavium-octeon/crypto/octeon-sha512.c     |   2 +-
 arch/powerpc/crypto/sha1-spe-glue.c                |   2 +-
 arch/powerpc/crypto/sha1.c                         |   2 +-
 arch/powerpc/crypto/sha256-spe-glue.c              |   2 +-
 arch/s390/crypto/sha.h                             |   3 +-
 arch/s390/crypto/sha1_s390.c                       |   2 +-
 arch/s390/crypto/sha256_s390.c                     |   2 +-
 arch/s390/crypto/sha3_256_s390.c                   |   1 -
 arch/s390/crypto/sha3_512_s390.c                   |   1 -
 arch/s390/crypto/sha512_s390.c                     |   2 +-
 arch/s390/purgatory/purgatory.c                    |   2 +-
 arch/sparc/crypto/sha1_glue.c                      |   2 +-
 arch/sparc/crypto/sha256_glue.c                    |   2 +-
 arch/sparc/crypto/sha512_glue.c                    |   2 +-
 arch/x86/crypto/sha1_ssse3_glue.c                  |   2 +-
 arch/x86/crypto/sha256_ssse3_glue.c                |   2 +-
 arch/x86/crypto/sha512_ssse3_glue.c                |   2 +-
 arch/x86/purgatory/purgatory.c                     |   2 +-
 crypto/asymmetric_keys/asym_tpm.c                  |   2 +-
 crypto/sha1_generic.c                              |   2 +-
 crypto/sha256_generic.c                            |   2 +-
 crypto/sha512_generic.c                            |   2 +-
 drivers/char/random.c                              |   2 +-
 drivers/crypto/allwinner/sun4i-ss/sun4i-ss.h       |   2 +-
 drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c  |   3 +-
 drivers/crypto/allwinner/sun8i-ce/sun8i-ce.h       |   3 +-
 drivers/crypto/allwinner/sun8i-ss/sun8i-ss-hash.c  |   3 +-
 drivers/crypto/allwinner/sun8i-ss/sun8i-ss.h       |   3 +-
 drivers/crypto/amcc/crypto4xx_alg.c                |   2 +-
 drivers/crypto/amcc/crypto4xx_core.c               |   2 +-
 drivers/crypto/atmel-authenc.h                     |   3 +-
 drivers/crypto/atmel-sha.c                         |   3 +-
 drivers/crypto/axis/artpec6_crypto.c               |   3 +-
 drivers/crypto/bcm/cipher.c                        |   3 +-
 drivers/crypto/bcm/cipher.h                        |   3 +-
 drivers/crypto/bcm/spu.h                           |   3 +-
 drivers/crypto/caam/compat.h                       |   3 +-
 drivers/crypto/cavium/nitrox/nitrox_aead.c         |   1 -
 drivers/crypto/ccp/ccp-crypto-sha.c                |   3 +-
 drivers/crypto/ccp/ccp-crypto.h                    |   3 +-
 drivers/crypto/ccree/cc_driver.h                   |   3 +-
 drivers/crypto/chelsio/chcr_algo.c                 |   3 +-
 drivers/crypto/hisilicon/sec2/sec_crypto.c         |   3 +-
 drivers/crypto/img-hash.c                          |   3 +-
 drivers/crypto/inside-secure/safexcel.h            |   3 +-
 drivers/crypto/inside-secure/safexcel_cipher.c     |   3 +-
 drivers/crypto/inside-secure/safexcel_hash.c       |   3 +-
 drivers/crypto/ixp4xx_crypto.c                     |   2 +-
 drivers/crypto/marvell/cesa/hash.c                 |   3 +-
 drivers/crypto/marvell/octeontx/otx_cptvf_algs.c   |   3 +-
 drivers/crypto/mediatek/mtk-sha.c                  |   3 +-
 drivers/crypto/mxs-dcp.c                           |   3 +-
 drivers/crypto/n2_core.c                           |   3 +-
 drivers/crypto/nx/nx-sha256.c                      |   2 +-
 drivers/crypto/nx/nx-sha512.c                      |   2 +-
 drivers/crypto/nx/nx.c                             |   2 +-
 drivers/crypto/omap-sham.c                         |   3 +-
 drivers/crypto/padlock-sha.c                       |   3 +-
 drivers/crypto/picoxcell_crypto.c                  |   3 +-
 drivers/crypto/qat/qat_common/qat_algs.c           |   3 +-
 drivers/crypto/qce/common.c                        |   3 +-
 drivers/crypto/qce/core.c                          |   1 -
 drivers/crypto/qce/sha.h                           |   3 +-
 drivers/crypto/rockchip/rk3288_crypto.h            |   3 +-
 drivers/crypto/s5p-sss.c                           |   3 +-
 drivers/crypto/sa2ul.c                             |   3 +-
 drivers/crypto/sa2ul.h                             |   3 +-
 drivers/crypto/sahara.c                            |   3 +-
 drivers/crypto/stm32/stm32-hash.c                  |   3 +-
 drivers/crypto/talitos.c                           |   3 +-
 drivers/crypto/ux500/hash/hash_core.c              |   3 +-
 drivers/firmware/efi/embedded-firmware.c           |   2 +-
 .../chelsio/inline_crypto/ch_ipsec/chcr_ipsec.c    |   3 +-
 .../ethernet/chelsio/inline_crypto/chtls/chtls.h   |   3 +-
 drivers/nfc/s3fwrn5/firmware.c                     |   2 +-
 drivers/tee/tee_core.c                             |   2 +-
 fs/crypto/fname.c                                  |   2 +-
 fs/crypto/hkdf.c                                   |   2 +-
 fs/ubifs/auth.c                                    |   1 -
 fs/verity/fsverity_private.h                       |   2 +-
 include/crypto/hash_info.h                         |   3 +-
 include/crypto/sha.h                               | 167 ---------------------
 include/crypto/sha1.h                              |  46 ++++++
 include/crypto/sha1_base.h                         |   2 +-
 include/crypto/sha2.h                              | 134 +++++++++++++++++
 include/crypto/sha256_base.h                       |   2 +-
 include/crypto/sha512_base.h                       |   2 +-
 include/linux/ccp.h                                |   3 +-
 include/linux/filter.h                             |   2 +-
 include/linux/purgatory.h                          |   2 +-
 kernel/crash_core.c                                |   2 +-
 kernel/kexec_core.c                                |   1 -
 kernel/kexec_file.c                                |   2 +-
 lib/crypto/sha256.c                                |   2 +-
 lib/digsig.c                                       |   2 +-
 lib/sha1.c                                         |   2 +-
 net/ipv6/seg6_hmac.c                               |   1 -
 net/mptcp/crypto.c                                 |   2 +-
 net/mptcp/options.c                                |   2 +-
 net/mptcp/subflow.c                                |   2 +-
 security/integrity/integrity.h                     |   2 +-
 security/keys/encrypted-keys/encrypted.c           |   2 +-
 security/keys/trusted-keys/trusted_tpm1.c          |   2 +-
 sound/soc/codecs/cros_ec_codec.c                   |   2 +-
 121 files changed, 335 insertions(+), 285 deletions(-)
 delete mode 100644 include/crypto/sha.h
 create mode 100644 include/crypto/sha1.h
 create mode 100644 include/crypto/sha2.h

(limited to 'include/linux')

diff --git a/arch/arm/crypto/sha1-ce-glue.c b/arch/arm/crypto/sha1-ce-glue.c
index e79b1fb4b4dc..de9100c67b37 100644
--- a/arch/arm/crypto/sha1-ce-glue.c
+++ b/arch/arm/crypto/sha1-ce-glue.c
@@ -7,7 +7,7 @@
 
 #include <crypto/internal/hash.h>
 #include <crypto/internal/simd.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
 #include <crypto/sha1_base.h>
 #include <linux/cpufeature.h>
 #include <linux/crypto.h>
diff --git a/arch/arm/crypto/sha1.h b/arch/arm/crypto/sha1.h
index 758db3e9ff0a..b1b7e21da2c3 100644
--- a/arch/arm/crypto/sha1.h
+++ b/arch/arm/crypto/sha1.h
@@ -3,7 +3,7 @@
 #define ASM_ARM_CRYPTO_SHA1_H
 
 #include <linux/crypto.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
 
 extern int sha1_update_arm(struct shash_desc *desc, const u8 *data,
 			   unsigned int len);
diff --git a/arch/arm/crypto/sha1_glue.c b/arch/arm/crypto/sha1_glue.c
index 4e954b3f7ecd..6c2b849e459d 100644
--- a/arch/arm/crypto/sha1_glue.c
+++ b/arch/arm/crypto/sha1_glue.c
@@ -15,7 +15,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/types.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
 #include <crypto/sha1_base.h>
 #include <asm/byteorder.h>
 
diff --git a/arch/arm/crypto/sha1_neon_glue.c b/arch/arm/crypto/sha1_neon_glue.c
index 0071e5e4411a..cfe36ae0f3f5 100644
--- a/arch/arm/crypto/sha1_neon_glue.c
+++ b/arch/arm/crypto/sha1_neon_glue.c
@@ -19,7 +19,7 @@
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/types.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
 #include <crypto/sha1_base.h>
 #include <asm/neon.h>
 #include <asm/simd.h>
diff --git a/arch/arm/crypto/sha2-ce-glue.c b/arch/arm/crypto/sha2-ce-glue.c
index 87f0b62386c6..c62ce89dd3e0 100644
--- a/arch/arm/crypto/sha2-ce-glue.c
+++ b/arch/arm/crypto/sha2-ce-glue.c
@@ -7,7 +7,7 @@
 
 #include <crypto/internal/hash.h>
 #include <crypto/internal/simd.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <crypto/sha256_base.h>
 #include <linux/cpufeature.h>
 #include <linux/crypto.h>
diff --git a/arch/arm/crypto/sha256_glue.c b/arch/arm/crypto/sha256_glue.c
index b8a4f79020cf..433ee4ddce6c 100644
--- a/arch/arm/crypto/sha256_glue.c
+++ b/arch/arm/crypto/sha256_glue.c
@@ -17,7 +17,7 @@
 #include <linux/mm.h>
 #include <linux/types.h>
 #include <linux/string.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <crypto/sha256_base.h>
 #include <asm/simd.h>
 #include <asm/neon.h>
diff --git a/arch/arm/crypto/sha256_neon_glue.c b/arch/arm/crypto/sha256_neon_glue.c
index 79820b9e2541..701706262ef3 100644
--- a/arch/arm/crypto/sha256_neon_glue.c
+++ b/arch/arm/crypto/sha256_neon_glue.c
@@ -13,7 +13,7 @@
 #include <crypto/internal/simd.h>
 #include <linux/types.h>
 #include <linux/string.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <crypto/sha256_base.h>
 #include <asm/byteorder.h>
 #include <asm/simd.h>
diff --git a/arch/arm/crypto/sha512-glue.c b/arch/arm/crypto/sha512-glue.c
index 8775aa42bbbe..0635a65aa488 100644
--- a/arch/arm/crypto/sha512-glue.c
+++ b/arch/arm/crypto/sha512-glue.c
@@ -6,7 +6,7 @@
  */
 
 #include <crypto/internal/hash.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <crypto/sha512_base.h>
 #include <linux/crypto.h>
 #include <linux/module.h>
diff --git a/arch/arm/crypto/sha512-neon-glue.c b/arch/arm/crypto/sha512-neon-glue.c
index 96cb94403540..c879ad32db51 100644
--- a/arch/arm/crypto/sha512-neon-glue.c
+++ b/arch/arm/crypto/sha512-neon-glue.c
@@ -7,7 +7,7 @@
 
 #include <crypto/internal/hash.h>
 #include <crypto/internal/simd.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <crypto/sha512_base.h>
 #include <linux/crypto.h>
 #include <linux/module.h>
diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
index 395bbf64b2ab..34b8a89197be 100644
--- a/arch/arm64/crypto/aes-glue.c
+++ b/arch/arm64/crypto/aes-glue.c
@@ -10,7 +10,7 @@
 #include <asm/simd.h>
 #include <crypto/aes.h>
 #include <crypto/ctr.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <crypto/internal/hash.h>
 #include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c
index c63b99211db3..c93121bcfdeb 100644
--- a/arch/arm64/crypto/sha1-ce-glue.c
+++ b/arch/arm64/crypto/sha1-ce-glue.c
@@ -10,7 +10,7 @@
 #include <asm/unaligned.h>
 #include <crypto/internal/hash.h>
 #include <crypto/internal/simd.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
 #include <crypto/sha1_base.h>
 #include <linux/cpufeature.h>
 #include <linux/crypto.h>
diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c
index 5e956d7582a5..31ba3da5e61b 100644
--- a/arch/arm64/crypto/sha2-ce-glue.c
+++ b/arch/arm64/crypto/sha2-ce-glue.c
@@ -10,7 +10,7 @@
 #include <asm/unaligned.h>
 #include <crypto/internal/hash.h>
 #include <crypto/internal/simd.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <crypto/sha256_base.h>
 #include <linux/cpufeature.h>
 #include <linux/crypto.h>
diff --git a/arch/arm64/crypto/sha256-glue.c b/arch/arm64/crypto/sha256-glue.c
index 77bc6e72abae..9462f6088b3f 100644
--- a/arch/arm64/crypto/sha256-glue.c
+++ b/arch/arm64/crypto/sha256-glue.c
@@ -10,7 +10,7 @@
 #include <asm/simd.h>
 #include <crypto/internal/hash.h>
 #include <crypto/internal/simd.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <crypto/sha256_base.h>
 #include <linux/types.h>
 #include <linux/string.h>
diff --git a/arch/arm64/crypto/sha512-ce-glue.c b/arch/arm64/crypto/sha512-ce-glue.c
index dc890a719f54..faa83f6cf376 100644
--- a/arch/arm64/crypto/sha512-ce-glue.c
+++ b/arch/arm64/crypto/sha512-ce-glue.c
@@ -14,7 +14,7 @@
 #include <asm/unaligned.h>
 #include <crypto/internal/hash.h>
 #include <crypto/internal/simd.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <crypto/sha512_base.h>
 #include <linux/cpufeature.h>
 #include <linux/crypto.h>
diff --git a/arch/arm64/crypto/sha512-glue.c b/arch/arm64/crypto/sha512-glue.c
index 370ccb29602f..2acff1c7df5d 100644
--- a/arch/arm64/crypto/sha512-glue.c
+++ b/arch/arm64/crypto/sha512-glue.c
@@ -8,7 +8,7 @@
 #include <crypto/internal/hash.h>
 #include <linux/types.h>
 #include <linux/string.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <crypto/sha512_base.h>
 #include <asm/neon.h>
 
diff --git a/arch/mips/cavium-octeon/crypto/octeon-sha1.c b/arch/mips/cavium-octeon/crypto/octeon-sha1.c
index 75e79b47abfe..30f1d75208a5 100644
--- a/arch/mips/cavium-octeon/crypto/octeon-sha1.c
+++ b/arch/mips/cavium-octeon/crypto/octeon-sha1.c
@@ -14,7 +14,7 @@
  */
 
 #include <linux/mm.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
 #include <linux/init.h>
 #include <linux/types.h>
 #include <linux/module.h>
diff --git a/arch/mips/cavium-octeon/crypto/octeon-sha256.c b/arch/mips/cavium-octeon/crypto/octeon-sha256.c
index a682ce76716a..36cb92895d72 100644
--- a/arch/mips/cavium-octeon/crypto/octeon-sha256.c
+++ b/arch/mips/cavium-octeon/crypto/octeon-sha256.c
@@ -15,7 +15,7 @@
  */
 
 #include <linux/mm.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <linux/init.h>
 #include <linux/types.h>
 #include <linux/module.h>
diff --git a/arch/mips/cavium-octeon/crypto/octeon-sha512.c b/arch/mips/cavium-octeon/crypto/octeon-sha512.c
index 50722a0cfb53..359f039820d8 100644
--- a/arch/mips/cavium-octeon/crypto/octeon-sha512.c
+++ b/arch/mips/cavium-octeon/crypto/octeon-sha512.c
@@ -14,7 +14,7 @@
  */
 
 #include <linux/mm.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <linux/init.h>
 #include <linux/types.h>
 #include <linux/module.h>
diff --git a/arch/powerpc/crypto/sha1-spe-glue.c b/arch/powerpc/crypto/sha1-spe-glue.c
index cb57be4ada61..b1e577cbf00c 100644
--- a/arch/powerpc/crypto/sha1-spe-glue.c
+++ b/arch/powerpc/crypto/sha1-spe-glue.c
@@ -12,7 +12,7 @@
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/types.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
 #include <asm/byteorder.h>
 #include <asm/switch_to.h>
 #include <linux/hardirq.h>
diff --git a/arch/powerpc/crypto/sha1.c b/arch/powerpc/crypto/sha1.c
index b40dc50a6908..7a55d790cdb1 100644
--- a/arch/powerpc/crypto/sha1.c
+++ b/arch/powerpc/crypto/sha1.c
@@ -17,7 +17,7 @@
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/types.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
 #include <asm/byteorder.h>
 
 void powerpc_sha_transform(u32 *state, const u8 *src);
diff --git a/arch/powerpc/crypto/sha256-spe-glue.c b/arch/powerpc/crypto/sha256-spe-glue.c
index ceb0b6c980b3..88530ae0791f 100644
--- a/arch/powerpc/crypto/sha256-spe-glue.c
+++ b/arch/powerpc/crypto/sha256-spe-glue.c
@@ -13,7 +13,7 @@
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/types.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <asm/byteorder.h>
 #include <asm/switch_to.h>
 #include <linux/hardirq.h>
diff --git a/arch/s390/crypto/sha.h b/arch/s390/crypto/sha.h
index ada2f98c27b7..65ea12fc87a1 100644
--- a/arch/s390/crypto/sha.h
+++ b/arch/s390/crypto/sha.h
@@ -11,7 +11,8 @@
 #define _CRYPTO_ARCH_S390_SHA_H
 
 #include <linux/crypto.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 #include <crypto/sha3.h>
 
 /* must be big enough for the largest SHA variant */
diff --git a/arch/s390/crypto/sha1_s390.c b/arch/s390/crypto/sha1_s390.c
index 698b1e6d3c14..a3fabf310a38 100644
--- a/arch/s390/crypto/sha1_s390.c
+++ b/arch/s390/crypto/sha1_s390.c
@@ -22,7 +22,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/cpufeature.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
 #include <asm/cpacf.h>
 
 #include "sha.h"
diff --git a/arch/s390/crypto/sha256_s390.c b/arch/s390/crypto/sha256_s390.c
index b52c87e44939..24983f175676 100644
--- a/arch/s390/crypto/sha256_s390.c
+++ b/arch/s390/crypto/sha256_s390.c
@@ -12,7 +12,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/cpufeature.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <asm/cpacf.h>
 
 #include "sha.h"
diff --git a/arch/s390/crypto/sha3_256_s390.c b/arch/s390/crypto/sha3_256_s390.c
index 460cbbbaa44a..30ac49b635bf 100644
--- a/arch/s390/crypto/sha3_256_s390.c
+++ b/arch/s390/crypto/sha3_256_s390.c
@@ -12,7 +12,6 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/cpufeature.h>
-#include <crypto/sha.h>
 #include <crypto/sha3.h>
 #include <asm/cpacf.h>
 
diff --git a/arch/s390/crypto/sha3_512_s390.c b/arch/s390/crypto/sha3_512_s390.c
index 72cf460a53e5..e70d50f7620f 100644
--- a/arch/s390/crypto/sha3_512_s390.c
+++ b/arch/s390/crypto/sha3_512_s390.c
@@ -11,7 +11,6 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/cpufeature.h>
-#include <crypto/sha.h>
 #include <crypto/sha3.h>
 #include <asm/cpacf.h>
 
diff --git a/arch/s390/crypto/sha512_s390.c b/arch/s390/crypto/sha512_s390.c
index ad29db085a18..29a6bd404c59 100644
--- a/arch/s390/crypto/sha512_s390.c
+++ b/arch/s390/crypto/sha512_s390.c
@@ -8,7 +8,7 @@
  * Author(s): Jan Glauber (jang@de.ibm.com)
  */
 #include <crypto/internal/hash.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
diff --git a/arch/s390/purgatory/purgatory.c b/arch/s390/purgatory/purgatory.c
index 0a423bcf6746..030efda05dbe 100644
--- a/arch/s390/purgatory/purgatory.c
+++ b/arch/s390/purgatory/purgatory.c
@@ -9,7 +9,7 @@
 
 #include <linux/kexec.h>
 #include <linux/string.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <asm/purgatory.h>
 
 int verify_sha256_digest(void)
diff --git a/arch/sparc/crypto/sha1_glue.c b/arch/sparc/crypto/sha1_glue.c
index dc017782be52..86a654cce5ab 100644
--- a/arch/sparc/crypto/sha1_glue.c
+++ b/arch/sparc/crypto/sha1_glue.c
@@ -16,7 +16,7 @@
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/types.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
 
 #include <asm/pstate.h>
 #include <asm/elf.h>
diff --git a/arch/sparc/crypto/sha256_glue.c b/arch/sparc/crypto/sha256_glue.c
index ca2547df9652..60ec524cf9ca 100644
--- a/arch/sparc/crypto/sha256_glue.c
+++ b/arch/sparc/crypto/sha256_glue.c
@@ -16,7 +16,7 @@
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/types.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 
 #include <asm/pstate.h>
 #include <asm/elf.h>
diff --git a/arch/sparc/crypto/sha512_glue.c b/arch/sparc/crypto/sha512_glue.c
index 3b2ca732ff7a..273ce21918c1 100644
--- a/arch/sparc/crypto/sha512_glue.c
+++ b/arch/sparc/crypto/sha512_glue.c
@@ -15,7 +15,7 @@
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/types.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 
 #include <asm/pstate.h>
 #include <asm/elf.h>
diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c
index 18200135603f..44340a1139e0 100644
--- a/arch/x86/crypto/sha1_ssse3_glue.c
+++ b/arch/x86/crypto/sha1_ssse3_glue.c
@@ -22,7 +22,7 @@
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/types.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
 #include <crypto/sha1_base.h>
 #include <asm/simd.h>
 
diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c
index dd06249229e1..3a5f6be7dbba 100644
--- a/arch/x86/crypto/sha256_ssse3_glue.c
+++ b/arch/x86/crypto/sha256_ssse3_glue.c
@@ -35,7 +35,7 @@
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/types.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <crypto/sha256_base.h>
 #include <linux/string.h>
 #include <asm/simd.h>
diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c
index b0b05c93409e..30e70f4fe2f7 100644
--- a/arch/x86/crypto/sha512_ssse3_glue.c
+++ b/arch/x86/crypto/sha512_ssse3_glue.c
@@ -34,7 +34,7 @@
 #include <linux/mm.h>
 #include <linux/string.h>
 #include <linux/types.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <crypto/sha512_base.h>
 #include <asm/simd.h>
 
diff --git a/arch/x86/purgatory/purgatory.c b/arch/x86/purgatory/purgatory.c
index 7b37a412f829..f03b64d9cb51 100644
--- a/arch/x86/purgatory/purgatory.c
+++ b/arch/x86/purgatory/purgatory.c
@@ -9,7 +9,7 @@
  */
 
 #include <linux/bug.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <asm/purgatory.h>
 
 #include "../boot/string.h"
diff --git a/crypto/asymmetric_keys/asym_tpm.c b/crypto/asymmetric_keys/asym_tpm.c
index 378b18b9bc34..511932aa94a6 100644
--- a/crypto/asymmetric_keys/asym_tpm.c
+++ b/crypto/asymmetric_keys/asym_tpm.c
@@ -10,7 +10,7 @@
 #include <linux/tpm_command.h>
 #include <crypto/akcipher.h>
 #include <crypto/hash.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
 #include <asm/unaligned.h>
 #include <keys/asymmetric-subtype.h>
 #include <keys/trusted_tpm.h>
diff --git a/crypto/sha1_generic.c b/crypto/sha1_generic.c
index 1d43472fecbd..325b57fe28dc 100644
--- a/crypto/sha1_generic.c
+++ b/crypto/sha1_generic.c
@@ -16,7 +16,7 @@
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/types.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
 #include <crypto/sha1_base.h>
 #include <asm/byteorder.h>
 
diff --git a/crypto/sha256_generic.c b/crypto/sha256_generic.c
index 88156e3e2a33..3b377197236e 100644
--- a/crypto/sha256_generic.c
+++ b/crypto/sha256_generic.c
@@ -12,7 +12,7 @@
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/types.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <crypto/sha256_base.h>
 #include <asm/byteorder.h>
 #include <asm/unaligned.h>
diff --git a/crypto/sha512_generic.c b/crypto/sha512_generic.c
index e34d09dd9971..c72d72ad828e 100644
--- a/crypto/sha512_generic.c
+++ b/crypto/sha512_generic.c
@@ -12,7 +12,7 @@
 #include <linux/init.h>
 #include <linux/crypto.h>
 #include <linux/types.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <crypto/sha512_base.h>
 #include <linux/percpu.h>
 #include <asm/byteorder.h>
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 2a41b21623ae..5f3b8ac9d97b 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -336,7 +336,7 @@
 #include <linux/completion.h>
 #include <linux/uuid.h>
 #include <crypto/chacha.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
 
 #include <asm/processor.h>
 #include <linux/uaccess.h>
diff --git a/drivers/crypto/allwinner/sun4i-ss/sun4i-ss.h b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss.h
index 163962f9e284..5c291e4a6857 100644
--- a/drivers/crypto/allwinner/sun4i-ss/sun4i-ss.h
+++ b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss.h
@@ -25,7 +25,7 @@
 #include <linux/pm_runtime.h>
 #include <crypto/md5.h>
 #include <crypto/skcipher.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
 #include <crypto/hash.h>
 #include <crypto/internal/hash.h>
 #include <crypto/internal/skcipher.h>
diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c
index fa2f1b4fad7b..4927a6c82d32 100644
--- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c
+++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c
@@ -13,7 +13,8 @@
 #include <linux/pm_runtime.h>
 #include <linux/scatterlist.h>
 #include <crypto/internal/hash.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 #include <crypto/md5.h>
 #include "sun8i-ce.h"
 
diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce.h b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce.h
index 558027516aed..cec781d5063c 100644
--- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce.h
+++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce.h
@@ -16,7 +16,8 @@
 #include <crypto/internal/hash.h>
 #include <crypto/md5.h>
 #include <crypto/rng.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 
 /* CE Registers */
 #define CE_TDQ	0x00
diff --git a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-hash.c b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-hash.c
index b6ab2054f217..11cbcbc83a7b 100644
--- a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-hash.c
+++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-hash.c
@@ -13,7 +13,8 @@
 #include <linux/pm_runtime.h>
 #include <linux/scatterlist.h>
 #include <crypto/internal/hash.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 #include <crypto/md5.h>
 #include "sun8i-ss.h"
 
diff --git a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss.h b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss.h
index 1a66457f4a20..28188685b910 100644
--- a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss.h
+++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss.h
@@ -15,7 +15,8 @@
 #include <linux/crypto.h>
 #include <crypto/internal/hash.h>
 #include <crypto/md5.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 
 #define SS_START	1
 
diff --git a/drivers/crypto/amcc/crypto4xx_alg.c b/drivers/crypto/amcc/crypto4xx_alg.c
index 7729a637fb02..a3fa849b139a 100644
--- a/drivers/crypto/amcc/crypto4xx_alg.c
+++ b/drivers/crypto/amcc/crypto4xx_alg.c
@@ -20,7 +20,7 @@
 #include <crypto/aead.h>
 #include <crypto/aes.h>
 #include <crypto/gcm.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
 #include <crypto/ctr.h>
 #include <crypto/skcipher.h>
 #include "crypto4xx_reg_def.h"
diff --git a/drivers/crypto/amcc/crypto4xx_core.c b/drivers/crypto/amcc/crypto4xx_core.c
index 2e3690f65786..8d1b918a0533 100644
--- a/drivers/crypto/amcc/crypto4xx_core.c
+++ b/drivers/crypto/amcc/crypto4xx_core.c
@@ -30,7 +30,7 @@
 #include <crypto/aes.h>
 #include <crypto/ctr.h>
 #include <crypto/gcm.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
 #include <crypto/rng.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/skcipher.h>
diff --git a/drivers/crypto/atmel-authenc.h b/drivers/crypto/atmel-authenc.h
index c6530a1c8c20..45171e89a7d2 100644
--- a/drivers/crypto/atmel-authenc.h
+++ b/drivers/crypto/atmel-authenc.h
@@ -16,7 +16,8 @@
 
 #include <crypto/authenc.h>
 #include <crypto/hash.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 #include "atmel-sha-regs.h"
 
 struct atmel_aes_dev;
diff --git a/drivers/crypto/atmel-sha.c b/drivers/crypto/atmel-sha.c
index 0eb6f54e3b66..352d80cb5ae9 100644
--- a/drivers/crypto/atmel-sha.c
+++ b/drivers/crypto/atmel-sha.c
@@ -33,7 +33,8 @@
 #include <linux/crypto.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/algapi.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 #include <crypto/hash.h>
 #include <crypto/internal/hash.h>
 #include "atmel-sha-regs.h"
diff --git a/drivers/crypto/axis/artpec6_crypto.c b/drivers/crypto/axis/artpec6_crypto.c
index 809c3033ca74..9ad188cffd0d 100644
--- a/drivers/crypto/axis/artpec6_crypto.c
+++ b/drivers/crypto/axis/artpec6_crypto.c
@@ -28,7 +28,8 @@
 #include <crypto/internal/hash.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 #include <crypto/xts.h>
 
 /* Max length of a line in all cache levels for Artpec SoCs. */
diff --git a/drivers/crypto/bcm/cipher.c b/drivers/crypto/bcm/cipher.c
index 50d169e61b41..30390a7324b2 100644
--- a/drivers/crypto/bcm/cipher.c
+++ b/drivers/crypto/bcm/cipher.c
@@ -26,11 +26,12 @@
 #include <crypto/aes.h>
 #include <crypto/internal/des.h>
 #include <crypto/hmac.h>
-#include <crypto/sha.h>
 #include <crypto/md5.h>
 #include <crypto/authenc.h>
 #include <crypto/skcipher.h>
 #include <crypto/hash.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 #include <crypto/sha3.h>
 
 #include "util.h"
diff --git a/drivers/crypto/bcm/cipher.h b/drivers/crypto/bcm/cipher.h
index 035c8389cb3d..0ad5892b445d 100644
--- a/drivers/crypto/bcm/cipher.h
+++ b/drivers/crypto/bcm/cipher.h
@@ -16,7 +16,8 @@
 #include <crypto/aead.h>
 #include <crypto/arc4.h>
 #include <crypto/gcm.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 #include <crypto/sha3.h>
 
 #include "spu.h"
diff --git a/drivers/crypto/bcm/spu.h b/drivers/crypto/bcm/spu.h
index dd132389bcaa..1c386a2d5506 100644
--- a/drivers/crypto/bcm/spu.h
+++ b/drivers/crypto/bcm/spu.h
@@ -17,7 +17,8 @@
 
 #include <linux/types.h>
 #include <linux/scatterlist.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 
 enum spu_cipher_alg {
 	CIPHER_ALG_NONE = 0x0,
diff --git a/drivers/crypto/caam/compat.h b/drivers/crypto/caam/compat.h
index c3c22a8de4c0..c4f79764172b 100644
--- a/drivers/crypto/caam/compat.h
+++ b/drivers/crypto/caam/compat.h
@@ -34,7 +34,8 @@
 #include <crypto/ctr.h>
 #include <crypto/internal/des.h>
 #include <crypto/gcm.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 #include <crypto/md5.h>
 #include <crypto/chacha.h>
 #include <crypto/poly1305.h>
diff --git a/drivers/crypto/cavium/nitrox/nitrox_aead.c b/drivers/crypto/cavium/nitrox/nitrox_aead.c
index e5d8607ecb1d..c93c4e41d267 100644
--- a/drivers/crypto/cavium/nitrox/nitrox_aead.c
+++ b/drivers/crypto/cavium/nitrox/nitrox_aead.c
@@ -7,7 +7,6 @@
 #include <crypto/aead.h>
 #include <crypto/authenc.h>
 #include <crypto/des.h>
-#include <crypto/sha.h>
 #include <crypto/internal/aead.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/gcm.h>
diff --git a/drivers/crypto/ccp/ccp-crypto-sha.c b/drivers/crypto/ccp/ccp-crypto-sha.c
index 8fbfdb9e8cd3..74fa5360e722 100644
--- a/drivers/crypto/ccp/ccp-crypto-sha.c
+++ b/drivers/crypto/ccp/ccp-crypto-sha.c
@@ -17,7 +17,8 @@
 #include <crypto/hash.h>
 #include <crypto/hmac.h>
 #include <crypto/internal/hash.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 #include <crypto/scatterwalk.h>
 #include <linux/string.h>
 
diff --git a/drivers/crypto/ccp/ccp-crypto.h b/drivers/crypto/ccp/ccp-crypto.h
index aed3d2192d01..e42450d07168 100644
--- a/drivers/crypto/ccp/ccp-crypto.h
+++ b/drivers/crypto/ccp/ccp-crypto.h
@@ -19,7 +19,8 @@
 #include <crypto/aead.h>
 #include <crypto/ctr.h>
 #include <crypto/hash.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 #include <crypto/akcipher.h>
 #include <crypto/skcipher.h>
 #include <crypto/internal/rsa.h>
diff --git a/drivers/crypto/ccree/cc_driver.h b/drivers/crypto/ccree/cc_driver.h
index af77b2020350..ed2b2f13a256 100644
--- a/drivers/crypto/ccree/cc_driver.h
+++ b/drivers/crypto/ccree/cc_driver.h
@@ -17,7 +17,8 @@
 #include <crypto/algapi.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/aes.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 #include <crypto/aead.h>
 #include <crypto/authenc.h>
 #include <crypto/hash.h>
diff --git a/drivers/crypto/chelsio/chcr_algo.c b/drivers/crypto/chelsio/chcr_algo.c
index 13b908ea4873..f5a336634daa 100644
--- a/drivers/crypto/chelsio/chcr_algo.c
+++ b/drivers/crypto/chelsio/chcr_algo.c
@@ -53,7 +53,8 @@
 #include <crypto/algapi.h>
 #include <crypto/hash.h>
 #include <crypto/gcm.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 #include <crypto/authenc.h>
 #include <crypto/ctr.h>
 #include <crypto/gf128mul.h>
diff --git a/drivers/crypto/hisilicon/sec2/sec_crypto.c b/drivers/crypto/hisilicon/sec2/sec_crypto.c
index 891e04914615..2eaa516b3231 100644
--- a/drivers/crypto/hisilicon/sec2/sec_crypto.c
+++ b/drivers/crypto/hisilicon/sec2/sec_crypto.c
@@ -7,7 +7,8 @@
 #include <crypto/des.h>
 #include <crypto/hash.h>
 #include <crypto/internal/aead.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 #include <crypto/skcipher.h>
 #include <crypto/xts.h>
 #include <linux/crypto.h>
diff --git a/drivers/crypto/img-hash.c b/drivers/crypto/img-hash.c
index 91f555ccbb31..e813115d5432 100644
--- a/drivers/crypto/img-hash.c
+++ b/drivers/crypto/img-hash.c
@@ -19,7 +19,8 @@
 
 #include <crypto/internal/hash.h>
 #include <crypto/md5.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 
 #define CR_RESET			0
 #define CR_RESET_SET			1
diff --git a/drivers/crypto/inside-secure/safexcel.h b/drivers/crypto/inside-secure/safexcel.h
index 9045f2d7f4c6..ce1e611a163e 100644
--- a/drivers/crypto/inside-secure/safexcel.h
+++ b/drivers/crypto/inside-secure/safexcel.h
@@ -11,7 +11,8 @@
 #include <crypto/aead.h>
 #include <crypto/algapi.h>
 #include <crypto/internal/hash.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 #include <crypto/sha3.h>
 #include <crypto/skcipher.h>
 #include <linux/types.h>
diff --git a/drivers/crypto/inside-secure/safexcel_cipher.c b/drivers/crypto/inside-secure/safexcel_cipher.c
index 9bcfb79a030f..d68ef16650d4 100644
--- a/drivers/crypto/inside-secure/safexcel_cipher.c
+++ b/drivers/crypto/inside-secure/safexcel_cipher.c
@@ -18,7 +18,8 @@
 #include <crypto/gcm.h>
 #include <crypto/ghash.h>
 #include <crypto/poly1305.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 #include <crypto/sm3.h>
 #include <crypto/sm4.h>
 #include <crypto/xts.h>
diff --git a/drivers/crypto/inside-secure/safexcel_hash.c b/drivers/crypto/inside-secure/safexcel_hash.c
index 56d5ccb5cc00..50fb6d90a2e0 100644
--- a/drivers/crypto/inside-secure/safexcel_hash.c
+++ b/drivers/crypto/inside-secure/safexcel_hash.c
@@ -8,7 +8,8 @@
 #include <crypto/aes.h>
 #include <crypto/hmac.h>
 #include <crypto/md5.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 #include <crypto/sha3.h>
 #include <crypto/skcipher.h>
 #include <crypto/sm3.h>
diff --git a/drivers/crypto/ixp4xx_crypto.c b/drivers/crypto/ixp4xx_crypto.c
index 276012e7c482..8b0f17fc09fb 100644
--- a/drivers/crypto/ixp4xx_crypto.c
+++ b/drivers/crypto/ixp4xx_crypto.c
@@ -20,7 +20,7 @@
 #include <crypto/internal/des.h>
 #include <crypto/aes.h>
 #include <crypto/hmac.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
 #include <crypto/algapi.h>
 #include <crypto/internal/aead.h>
 #include <crypto/internal/skcipher.h>
diff --git a/drivers/crypto/marvell/cesa/hash.c b/drivers/crypto/marvell/cesa/hash.c
index add7ea011c98..8cf9fd518d86 100644
--- a/drivers/crypto/marvell/cesa/hash.c
+++ b/drivers/crypto/marvell/cesa/hash.c
@@ -11,7 +11,8 @@
 
 #include <crypto/hmac.h>
 #include <crypto/md5.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
 
diff --git a/drivers/crypto/marvell/octeontx/otx_cptvf_algs.c b/drivers/crypto/marvell/octeontx/otx_cptvf_algs.c
index 90bb31329d4b..ccbef01888d4 100644
--- a/drivers/crypto/marvell/octeontx/otx_cptvf_algs.c
+++ b/drivers/crypto/marvell/octeontx/otx_cptvf_algs.c
@@ -13,7 +13,8 @@
 #include <crypto/cryptd.h>
 #include <crypto/des.h>
 #include <crypto/internal/aead.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 #include <crypto/xts.h>
 #include <crypto/scatterwalk.h>
 #include <linux/rtnetlink.h>
diff --git a/drivers/crypto/mediatek/mtk-sha.c b/drivers/crypto/mediatek/mtk-sha.c
index 3d5d7d68b03b..f55aacdafbef 100644
--- a/drivers/crypto/mediatek/mtk-sha.c
+++ b/drivers/crypto/mediatek/mtk-sha.c
@@ -10,7 +10,8 @@
  */
 
 #include <crypto/hmac.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 #include "mtk-platform.h"
 
 #define SHA_ALIGN_MSK		(sizeof(u32) - 1)
diff --git a/drivers/crypto/mxs-dcp.c b/drivers/crypto/mxs-dcp.c
index 909a7eb748e3..d6a7784d2988 100644
--- a/drivers/crypto/mxs-dcp.c
+++ b/drivers/crypto/mxs-dcp.c
@@ -17,7 +17,8 @@
 #include <linux/clk.h>
 
 #include <crypto/aes.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 #include <crypto/internal/hash.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
diff --git a/drivers/crypto/n2_core.c b/drivers/crypto/n2_core.c
index 3642bf83d809..3b0bf6fea491 100644
--- a/drivers/crypto/n2_core.c
+++ b/drivers/crypto/n2_core.c
@@ -15,7 +15,8 @@
 #include <linux/interrupt.h>
 #include <linux/crypto.h>
 #include <crypto/md5.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 #include <crypto/aes.h>
 #include <crypto/internal/des.h>
 #include <linux/mutex.h>
diff --git a/drivers/crypto/nx/nx-sha256.c b/drivers/crypto/nx/nx-sha256.c
index 02fb53453195..90d9a37a57f6 100644
--- a/drivers/crypto/nx/nx-sha256.c
+++ b/drivers/crypto/nx/nx-sha256.c
@@ -8,7 +8,7 @@
  */
 
 #include <crypto/internal/hash.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <linux/module.h>
 #include <asm/vio.h>
 #include <asm/byteorder.h>
diff --git a/drivers/crypto/nx/nx-sha512.c b/drivers/crypto/nx/nx-sha512.c
index 4c7a3e3eeebf..eb8627a0f317 100644
--- a/drivers/crypto/nx/nx-sha512.c
+++ b/drivers/crypto/nx/nx-sha512.c
@@ -8,7 +8,7 @@
  */
 
 #include <crypto/internal/hash.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <linux/module.h>
 #include <asm/vio.h>
 
diff --git a/drivers/crypto/nx/nx.c b/drivers/crypto/nx/nx.c
index 40882d6d52c1..0d2dc5be7f19 100644
--- a/drivers/crypto/nx/nx.c
+++ b/drivers/crypto/nx/nx.c
@@ -10,7 +10,7 @@
 #include <crypto/internal/aead.h>
 #include <crypto/internal/hash.h>
 #include <crypto/aes.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <crypto/algapi.h>
 #include <crypto/scatterwalk.h>
 #include <linux/module.h>
diff --git a/drivers/crypto/omap-sham.c b/drivers/crypto/omap-sham.c
index a3b38d2c92e7..ae0d320d3c60 100644
--- a/drivers/crypto/omap-sham.c
+++ b/drivers/crypto/omap-sham.c
@@ -35,7 +35,8 @@
 #include <linux/crypto.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/algapi.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 #include <crypto/hash.h>
 #include <crypto/hmac.h>
 #include <crypto/internal/hash.h>
diff --git a/drivers/crypto/padlock-sha.c b/drivers/crypto/padlock-sha.c
index a697a4a3f2d0..6865c7f1fc1a 100644
--- a/drivers/crypto/padlock-sha.c
+++ b/drivers/crypto/padlock-sha.c
@@ -9,7 +9,8 @@
 
 #include <crypto/internal/hash.h>
 #include <crypto/padlock.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 #include <linux/err.h>
 #include <linux/module.h>
 #include <linux/init.h>
diff --git a/drivers/crypto/picoxcell_crypto.c b/drivers/crypto/picoxcell_crypto.c
index fb34bf92861d..84f9c16d984c 100644
--- a/drivers/crypto/picoxcell_crypto.c
+++ b/drivers/crypto/picoxcell_crypto.c
@@ -8,7 +8,8 @@
 #include <crypto/authenc.h>
 #include <crypto/internal/des.h>
 #include <crypto/md5.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/clk.h>
 #include <linux/crypto.h>
diff --git a/drivers/crypto/qat/qat_common/qat_algs.c b/drivers/crypto/qat/qat_common/qat_algs.c
index 0fab8bb8ca59..b3a68d986417 100644
--- a/drivers/crypto/qat/qat_common/qat_algs.c
+++ b/drivers/crypto/qat/qat_common/qat_algs.c
@@ -6,7 +6,8 @@
 #include <crypto/internal/aead.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/aes.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 #include <crypto/hash.h>
 #include <crypto/hmac.h>
 #include <crypto/algapi.h>
diff --git a/drivers/crypto/qce/common.c b/drivers/crypto/qce/common.c
index 5006e74c40cd..a73db2a5637f 100644
--- a/drivers/crypto/qce/common.c
+++ b/drivers/crypto/qce/common.c
@@ -7,7 +7,8 @@
 #include <linux/interrupt.h>
 #include <linux/types.h>
 #include <crypto/scatterwalk.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 
 #include "cipher.h"
 #include "common.h"
diff --git a/drivers/crypto/qce/core.c b/drivers/crypto/qce/core.c
index ea616b7259ae..5e6717f9bbda 100644
--- a/drivers/crypto/qce/core.c
+++ b/drivers/crypto/qce/core.c
@@ -13,7 +13,6 @@
 #include <linux/types.h>
 #include <crypto/algapi.h>
 #include <crypto/internal/hash.h>
-#include <crypto/sha.h>
 
 #include "core.h"
 #include "cipher.h"
diff --git a/drivers/crypto/qce/sha.h b/drivers/crypto/qce/sha.h
index d63526e3804d..a22695361f16 100644
--- a/drivers/crypto/qce/sha.h
+++ b/drivers/crypto/qce/sha.h
@@ -7,7 +7,8 @@
 #define _SHA_H_
 
 #include <crypto/scatterwalk.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 
 #include "common.h"
 #include "core.h"
diff --git a/drivers/crypto/rockchip/rk3288_crypto.h b/drivers/crypto/rockchip/rk3288_crypto.h
index 3db595570c9c..97278c2574ff 100644
--- a/drivers/crypto/rockchip/rk3288_crypto.h
+++ b/drivers/crypto/rockchip/rk3288_crypto.h
@@ -12,7 +12,8 @@
 #include <crypto/internal/skcipher.h>
 
 #include <crypto/md5.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 
 #define _SBF(v, f)			((v) << (f))
 
diff --git a/drivers/crypto/s5p-sss.c b/drivers/crypto/s5p-sss.c
index 88a6c853ffd7..682c8a450a57 100644
--- a/drivers/crypto/s5p-sss.c
+++ b/drivers/crypto/s5p-sss.c
@@ -30,7 +30,8 @@
 
 #include <crypto/hash.h>
 #include <crypto/md5.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 #include <crypto/internal/hash.h>
 
 #define _SBF(s, v)			((v) << (s))
diff --git a/drivers/crypto/sa2ul.c b/drivers/crypto/sa2ul.c
index c357010a159e..f300b0a5958a 100644
--- a/drivers/crypto/sa2ul.c
+++ b/drivers/crypto/sa2ul.c
@@ -25,7 +25,8 @@
 #include <crypto/internal/hash.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 
 #include "sa2ul.h"
 
diff --git a/drivers/crypto/sa2ul.h b/drivers/crypto/sa2ul.h
index bb40df3876e5..f597ddecde34 100644
--- a/drivers/crypto/sa2ul.h
+++ b/drivers/crypto/sa2ul.h
@@ -13,7 +13,8 @@
 #define _K3_SA2UL_
 
 #include <crypto/aes.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 
 #define SA_ENGINE_ENABLE_CONTROL	0x1000
 
diff --git a/drivers/crypto/sahara.c b/drivers/crypto/sahara.c
index d60679c79822..8b5be29cb4dc 100644
--- a/drivers/crypto/sahara.c
+++ b/drivers/crypto/sahara.c
@@ -15,7 +15,8 @@
 #include <crypto/internal/hash.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 
 #include <linux/clk.h>
 #include <linux/dma-mapping.h>
diff --git a/drivers/crypto/stm32/stm32-hash.c b/drivers/crypto/stm32/stm32-hash.c
index e3e25278a970..7ac0573ef663 100644
--- a/drivers/crypto/stm32/stm32-hash.c
+++ b/drivers/crypto/stm32/stm32-hash.c
@@ -25,7 +25,8 @@
 #include <crypto/hash.h>
 #include <crypto/md5.h>
 #include <crypto/scatterwalk.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 #include <crypto/internal/hash.h>
 
 #define HASH_CR				0x00
diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c
index a713a35dc502..4fd85f31630a 100644
--- a/drivers/crypto/talitos.c
+++ b/drivers/crypto/talitos.c
@@ -31,7 +31,8 @@
 #include <crypto/algapi.h>
 #include <crypto/aes.h>
 #include <crypto/internal/des.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 #include <crypto/md5.h>
 #include <crypto/internal/aead.h>
 #include <crypto/authenc.h>
diff --git a/drivers/crypto/ux500/hash/hash_core.c b/drivers/crypto/ux500/hash/hash_core.c
index 3d407eebb2ba..da284b0ea1b2 100644
--- a/drivers/crypto/ux500/hash/hash_core.c
+++ b/drivers/crypto/ux500/hash/hash_core.c
@@ -31,7 +31,8 @@
 #include <linux/bitops.h>
 
 #include <crypto/internal/hash.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/algapi.h>
 
diff --git a/drivers/firmware/efi/embedded-firmware.c b/drivers/firmware/efi/embedded-firmware.c
index 21ae0c48232a..f5be8e22305b 100644
--- a/drivers/firmware/efi/embedded-firmware.c
+++ b/drivers/firmware/efi/embedded-firmware.c
@@ -12,7 +12,7 @@
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/vmalloc.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 
 /* Exported for use by lib/test_firmware.c only */
 LIST_HEAD(efi_embedded_fw_list);
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/chcr_ipsec.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/chcr_ipsec.c
index 072299b14b8d..47d9268a7e3c 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/chcr_ipsec.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/chcr_ipsec.c
@@ -51,7 +51,8 @@
 #include <crypto/aes.h>
 #include <crypto/algapi.h>
 #include <crypto/hash.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 #include <crypto/authenc.h>
 #include <crypto/internal/aead.h>
 #include <crypto/null.h>
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h
index 2d3dfdd2a716..65617752c630 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h
+++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h
@@ -9,7 +9,8 @@
 #include <crypto/aes.h>
 #include <crypto/algapi.h>
 #include <crypto/hash.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 #include <crypto/authenc.h>
 #include <crypto/ctr.h>
 #include <crypto/gf128mul.h>
diff --git a/drivers/nfc/s3fwrn5/firmware.c b/drivers/nfc/s3fwrn5/firmware.c
index ec930ee2c847..5d5ad8307211 100644
--- a/drivers/nfc/s3fwrn5/firmware.c
+++ b/drivers/nfc/s3fwrn5/firmware.c
@@ -9,7 +9,7 @@
 #include <linux/completion.h>
 #include <linux/firmware.h>
 #include <crypto/hash.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
 
 #include "s3fwrn5.h"
 #include "firmware.h"
diff --git a/drivers/tee/tee_core.c b/drivers/tee/tee_core.c
index f53bf336c0a2..d70d4be91096 100644
--- a/drivers/tee/tee_core.c
+++ b/drivers/tee/tee_core.c
@@ -14,7 +14,7 @@
 #include <linux/tee_drv.h>
 #include <linux/uaccess.h>
 #include <crypto/hash.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
 #include "tee_private.h"
 
 #define TEE_NUM_DEVICES	32
diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c
index 1fbe6c24d705..cf06ea3870eb 100644
--- a/fs/crypto/fname.c
+++ b/fs/crypto/fname.c
@@ -14,7 +14,7 @@
 #include <linux/namei.h>
 #include <linux/scatterlist.h>
 #include <crypto/hash.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <crypto/skcipher.h>
 #include "fscrypt_private.h"
 
diff --git a/fs/crypto/hkdf.c b/fs/crypto/hkdf.c
index 0cba7928446d..e0ec21055505 100644
--- a/fs/crypto/hkdf.c
+++ b/fs/crypto/hkdf.c
@@ -10,7 +10,7 @@
  */
 
 #include <crypto/hash.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 
 #include "fscrypt_private.h"
 
diff --git a/fs/ubifs/auth.c b/fs/ubifs/auth.c
index b93b3cd10bfd..0886d835f597 100644
--- a/fs/ubifs/auth.c
+++ b/fs/ubifs/auth.c
@@ -12,7 +12,6 @@
 #include <linux/crypto.h>
 #include <linux/verification.h>
 #include <crypto/hash.h>
-#include <crypto/sha.h>
 #include <crypto/algapi.h>
 #include <keys/user-type.h>
 #include <keys/asymmetric-type.h>
diff --git a/fs/verity/fsverity_private.h b/fs/verity/fsverity_private.h
index e96d99d5145e..6a8f2e3cce6c 100644
--- a/fs/verity/fsverity_private.h
+++ b/fs/verity/fsverity_private.h
@@ -14,7 +14,7 @@
 
 #define pr_fmt(fmt) "fs-verity: " fmt
 
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <linux/fsverity.h>
 #include <linux/mempool.h>
 
diff --git a/include/crypto/hash_info.h b/include/crypto/hash_info.h
index eb9d2e368969..dd4f06785049 100644
--- a/include/crypto/hash_info.h
+++ b/include/crypto/hash_info.h
@@ -8,7 +8,8 @@
 #ifndef _CRYPTO_HASH_INFO_H
 #define _CRYPTO_HASH_INFO_H
 
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 #include <crypto/md5.h>
 #include <crypto/streebog.h>
 
diff --git a/include/crypto/sha.h b/include/crypto/sha.h
deleted file mode 100644
index 4ff3da816630..000000000000
--- a/include/crypto/sha.h
+++ /dev/null
@@ -1,167 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Common values for SHA algorithms
- */
-
-#ifndef _CRYPTO_SHA_H
-#define _CRYPTO_SHA_H
-
-#include <linux/types.h>
-
-#define SHA1_DIGEST_SIZE        20
-#define SHA1_BLOCK_SIZE         64
-
-#define SHA224_DIGEST_SIZE	28
-#define SHA224_BLOCK_SIZE	64
-
-#define SHA256_DIGEST_SIZE      32
-#define SHA256_BLOCK_SIZE       64
-
-#define SHA384_DIGEST_SIZE      48
-#define SHA384_BLOCK_SIZE       128
-
-#define SHA512_DIGEST_SIZE      64
-#define SHA512_BLOCK_SIZE       128
-
-#define SHA1_H0		0x67452301UL
-#define SHA1_H1		0xefcdab89UL
-#define SHA1_H2		0x98badcfeUL
-#define SHA1_H3		0x10325476UL
-#define SHA1_H4		0xc3d2e1f0UL
-
-#define SHA224_H0	0xc1059ed8UL
-#define SHA224_H1	0x367cd507UL
-#define SHA224_H2	0x3070dd17UL
-#define SHA224_H3	0xf70e5939UL
-#define SHA224_H4	0xffc00b31UL
-#define SHA224_H5	0x68581511UL
-#define SHA224_H6	0x64f98fa7UL
-#define SHA224_H7	0xbefa4fa4UL
-
-#define SHA256_H0	0x6a09e667UL
-#define SHA256_H1	0xbb67ae85UL
-#define SHA256_H2	0x3c6ef372UL
-#define SHA256_H3	0xa54ff53aUL
-#define SHA256_H4	0x510e527fUL
-#define SHA256_H5	0x9b05688cUL
-#define SHA256_H6	0x1f83d9abUL
-#define SHA256_H7	0x5be0cd19UL
-
-#define SHA384_H0	0xcbbb9d5dc1059ed8ULL
-#define SHA384_H1	0x629a292a367cd507ULL
-#define SHA384_H2	0x9159015a3070dd17ULL
-#define SHA384_H3	0x152fecd8f70e5939ULL
-#define SHA384_H4	0x67332667ffc00b31ULL
-#define SHA384_H5	0x8eb44a8768581511ULL
-#define SHA384_H6	0xdb0c2e0d64f98fa7ULL
-#define SHA384_H7	0x47b5481dbefa4fa4ULL
-
-#define SHA512_H0	0x6a09e667f3bcc908ULL
-#define SHA512_H1	0xbb67ae8584caa73bULL
-#define SHA512_H2	0x3c6ef372fe94f82bULL
-#define SHA512_H3	0xa54ff53a5f1d36f1ULL
-#define SHA512_H4	0x510e527fade682d1ULL
-#define SHA512_H5	0x9b05688c2b3e6c1fULL
-#define SHA512_H6	0x1f83d9abfb41bd6bULL
-#define SHA512_H7	0x5be0cd19137e2179ULL
-
-extern const u8 sha1_zero_message_hash[SHA1_DIGEST_SIZE];
-
-extern const u8 sha224_zero_message_hash[SHA224_DIGEST_SIZE];
-
-extern const u8 sha256_zero_message_hash[SHA256_DIGEST_SIZE];
-
-extern const u8 sha384_zero_message_hash[SHA384_DIGEST_SIZE];
-
-extern const u8 sha512_zero_message_hash[SHA512_DIGEST_SIZE];
-
-struct sha1_state {
-	u32 state[SHA1_DIGEST_SIZE / 4];
-	u64 count;
-	u8 buffer[SHA1_BLOCK_SIZE];
-};
-
-struct sha256_state {
-	u32 state[SHA256_DIGEST_SIZE / 4];
-	u64 count;
-	u8 buf[SHA256_BLOCK_SIZE];
-};
-
-struct sha512_state {
-	u64 state[SHA512_DIGEST_SIZE / 8];
-	u64 count[2];
-	u8 buf[SHA512_BLOCK_SIZE];
-};
-
-struct shash_desc;
-
-extern int crypto_sha1_update(struct shash_desc *desc, const u8 *data,
-			      unsigned int len);
-
-extern int crypto_sha1_finup(struct shash_desc *desc, const u8 *data,
-			     unsigned int len, u8 *hash);
-
-extern int crypto_sha256_update(struct shash_desc *desc, const u8 *data,
-			      unsigned int len);
-
-extern int crypto_sha256_finup(struct shash_desc *desc, const u8 *data,
-			       unsigned int len, u8 *hash);
-
-extern int crypto_sha512_update(struct shash_desc *desc, const u8 *data,
-			      unsigned int len);
-
-extern int crypto_sha512_finup(struct shash_desc *desc, const u8 *data,
-			       unsigned int len, u8 *hash);
-
-/*
- * An implementation of SHA-1's compression function.  Don't use in new code!
- * You shouldn't be using SHA-1, and even if you *have* to use SHA-1, this isn't
- * the correct way to hash something with SHA-1 (use crypto_shash instead).
- */
-#define SHA1_DIGEST_WORDS	(SHA1_DIGEST_SIZE / 4)
-#define SHA1_WORKSPACE_WORDS	16
-void sha1_init(__u32 *buf);
-void sha1_transform(__u32 *digest, const char *data, __u32 *W);
-
-/*
- * Stand-alone implementation of the SHA256 algorithm. It is designed to
- * have as little dependencies as possible so it can be used in the
- * kexec_file purgatory. In other cases you should generally use the
- * hash APIs from include/crypto/hash.h. Especially when hashing large
- * amounts of data as those APIs may be hw-accelerated.
- *
- * For details see lib/crypto/sha256.c
- */
-
-static inline void sha256_init(struct sha256_state *sctx)
-{
-	sctx->state[0] = SHA256_H0;
-	sctx->state[1] = SHA256_H1;
-	sctx->state[2] = SHA256_H2;
-	sctx->state[3] = SHA256_H3;
-	sctx->state[4] = SHA256_H4;
-	sctx->state[5] = SHA256_H5;
-	sctx->state[6] = SHA256_H6;
-	sctx->state[7] = SHA256_H7;
-	sctx->count = 0;
-}
-void sha256_update(struct sha256_state *sctx, const u8 *data, unsigned int len);
-void sha256_final(struct sha256_state *sctx, u8 *out);
-void sha256(const u8 *data, unsigned int len, u8 *out);
-
-static inline void sha224_init(struct sha256_state *sctx)
-{
-	sctx->state[0] = SHA224_H0;
-	sctx->state[1] = SHA224_H1;
-	sctx->state[2] = SHA224_H2;
-	sctx->state[3] = SHA224_H3;
-	sctx->state[4] = SHA224_H4;
-	sctx->state[5] = SHA224_H5;
-	sctx->state[6] = SHA224_H6;
-	sctx->state[7] = SHA224_H7;
-	sctx->count = 0;
-}
-void sha224_update(struct sha256_state *sctx, const u8 *data, unsigned int len);
-void sha224_final(struct sha256_state *sctx, u8 *out);
-
-#endif
diff --git a/include/crypto/sha1.h b/include/crypto/sha1.h
new file mode 100644
index 000000000000..044ecea60ac8
--- /dev/null
+++ b/include/crypto/sha1.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Common values for SHA-1 algorithms
+ */
+
+#ifndef _CRYPTO_SHA1_H
+#define _CRYPTO_SHA1_H
+
+#include <linux/types.h>
+
+#define SHA1_DIGEST_SIZE        20
+#define SHA1_BLOCK_SIZE         64
+
+#define SHA1_H0		0x67452301UL
+#define SHA1_H1		0xefcdab89UL
+#define SHA1_H2		0x98badcfeUL
+#define SHA1_H3		0x10325476UL
+#define SHA1_H4		0xc3d2e1f0UL
+
+extern const u8 sha1_zero_message_hash[SHA1_DIGEST_SIZE];
+
+struct sha1_state {
+	u32 state[SHA1_DIGEST_SIZE / 4];
+	u64 count;
+	u8 buffer[SHA1_BLOCK_SIZE];
+};
+
+struct shash_desc;
+
+extern int crypto_sha1_update(struct shash_desc *desc, const u8 *data,
+			      unsigned int len);
+
+extern int crypto_sha1_finup(struct shash_desc *desc, const u8 *data,
+			     unsigned int len, u8 *hash);
+
+/*
+ * An implementation of SHA-1's compression function.  Don't use in new code!
+ * You shouldn't be using SHA-1, and even if you *have* to use SHA-1, this isn't
+ * the correct way to hash something with SHA-1 (use crypto_shash instead).
+ */
+#define SHA1_DIGEST_WORDS	(SHA1_DIGEST_SIZE / 4)
+#define SHA1_WORKSPACE_WORDS	16
+void sha1_init(__u32 *buf);
+void sha1_transform(__u32 *digest, const char *data, __u32 *W);
+
+#endif /* _CRYPTO_SHA1_H */
diff --git a/include/crypto/sha1_base.h b/include/crypto/sha1_base.h
index a5d6033efef7..2e0e7c3827d1 100644
--- a/include/crypto/sha1_base.h
+++ b/include/crypto/sha1_base.h
@@ -9,7 +9,7 @@
 #define _CRYPTO_SHA1_BASE_H
 
 #include <crypto/internal/hash.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
 #include <linux/crypto.h>
 #include <linux/module.h>
 #include <linux/string.h>
diff --git a/include/crypto/sha2.h b/include/crypto/sha2.h
new file mode 100644
index 000000000000..2838f529f31e
--- /dev/null
+++ b/include/crypto/sha2.h
@@ -0,0 +1,134 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Common values for SHA-2 algorithms
+ */
+
+#ifndef _CRYPTO_SHA2_H
+#define _CRYPTO_SHA2_H
+
+#include <linux/types.h>
+
+#define SHA224_DIGEST_SIZE	28
+#define SHA224_BLOCK_SIZE	64
+
+#define SHA256_DIGEST_SIZE      32
+#define SHA256_BLOCK_SIZE       64
+
+#define SHA384_DIGEST_SIZE      48
+#define SHA384_BLOCK_SIZE       128
+
+#define SHA512_DIGEST_SIZE      64
+#define SHA512_BLOCK_SIZE       128
+
+#define SHA224_H0	0xc1059ed8UL
+#define SHA224_H1	0x367cd507UL
+#define SHA224_H2	0x3070dd17UL
+#define SHA224_H3	0xf70e5939UL
+#define SHA224_H4	0xffc00b31UL
+#define SHA224_H5	0x68581511UL
+#define SHA224_H6	0x64f98fa7UL
+#define SHA224_H7	0xbefa4fa4UL
+
+#define SHA256_H0	0x6a09e667UL
+#define SHA256_H1	0xbb67ae85UL
+#define SHA256_H2	0x3c6ef372UL
+#define SHA256_H3	0xa54ff53aUL
+#define SHA256_H4	0x510e527fUL
+#define SHA256_H5	0x9b05688cUL
+#define SHA256_H6	0x1f83d9abUL
+#define SHA256_H7	0x5be0cd19UL
+
+#define SHA384_H0	0xcbbb9d5dc1059ed8ULL
+#define SHA384_H1	0x629a292a367cd507ULL
+#define SHA384_H2	0x9159015a3070dd17ULL
+#define SHA384_H3	0x152fecd8f70e5939ULL
+#define SHA384_H4	0x67332667ffc00b31ULL
+#define SHA384_H5	0x8eb44a8768581511ULL
+#define SHA384_H6	0xdb0c2e0d64f98fa7ULL
+#define SHA384_H7	0x47b5481dbefa4fa4ULL
+
+#define SHA512_H0	0x6a09e667f3bcc908ULL
+#define SHA512_H1	0xbb67ae8584caa73bULL
+#define SHA512_H2	0x3c6ef372fe94f82bULL
+#define SHA512_H3	0xa54ff53a5f1d36f1ULL
+#define SHA512_H4	0x510e527fade682d1ULL
+#define SHA512_H5	0x9b05688c2b3e6c1fULL
+#define SHA512_H6	0x1f83d9abfb41bd6bULL
+#define SHA512_H7	0x5be0cd19137e2179ULL
+
+extern const u8 sha224_zero_message_hash[SHA224_DIGEST_SIZE];
+
+extern const u8 sha256_zero_message_hash[SHA256_DIGEST_SIZE];
+
+extern const u8 sha384_zero_message_hash[SHA384_DIGEST_SIZE];
+
+extern const u8 sha512_zero_message_hash[SHA512_DIGEST_SIZE];
+
+struct sha256_state {
+	u32 state[SHA256_DIGEST_SIZE / 4];
+	u64 count;
+	u8 buf[SHA256_BLOCK_SIZE];
+};
+
+struct sha512_state {
+	u64 state[SHA512_DIGEST_SIZE / 8];
+	u64 count[2];
+	u8 buf[SHA512_BLOCK_SIZE];
+};
+
+struct shash_desc;
+
+extern int crypto_sha256_update(struct shash_desc *desc, const u8 *data,
+			      unsigned int len);
+
+extern int crypto_sha256_finup(struct shash_desc *desc, const u8 *data,
+			       unsigned int len, u8 *hash);
+
+extern int crypto_sha512_update(struct shash_desc *desc, const u8 *data,
+			      unsigned int len);
+
+extern int crypto_sha512_finup(struct shash_desc *desc, const u8 *data,
+			       unsigned int len, u8 *hash);
+
+/*
+ * Stand-alone implementation of the SHA256 algorithm. It is designed to
+ * have as little dependencies as possible so it can be used in the
+ * kexec_file purgatory. In other cases you should generally use the
+ * hash APIs from include/crypto/hash.h. Especially when hashing large
+ * amounts of data as those APIs may be hw-accelerated.
+ *
+ * For details see lib/crypto/sha256.c
+ */
+
+static inline void sha256_init(struct sha256_state *sctx)
+{
+	sctx->state[0] = SHA256_H0;
+	sctx->state[1] = SHA256_H1;
+	sctx->state[2] = SHA256_H2;
+	sctx->state[3] = SHA256_H3;
+	sctx->state[4] = SHA256_H4;
+	sctx->state[5] = SHA256_H5;
+	sctx->state[6] = SHA256_H6;
+	sctx->state[7] = SHA256_H7;
+	sctx->count = 0;
+}
+void sha256_update(struct sha256_state *sctx, const u8 *data, unsigned int len);
+void sha256_final(struct sha256_state *sctx, u8 *out);
+void sha256(const u8 *data, unsigned int len, u8 *out);
+
+static inline void sha224_init(struct sha256_state *sctx)
+{
+	sctx->state[0] = SHA224_H0;
+	sctx->state[1] = SHA224_H1;
+	sctx->state[2] = SHA224_H2;
+	sctx->state[3] = SHA224_H3;
+	sctx->state[4] = SHA224_H4;
+	sctx->state[5] = SHA224_H5;
+	sctx->state[6] = SHA224_H6;
+	sctx->state[7] = SHA224_H7;
+	sctx->count = 0;
+}
+void sha224_update(struct sha256_state *sctx, const u8 *data, unsigned int len);
+void sha224_final(struct sha256_state *sctx, u8 *out);
+
+#endif /* _CRYPTO_SHA2_H */
diff --git a/include/crypto/sha256_base.h b/include/crypto/sha256_base.h
index 93f9fd21cc06..76173c613058 100644
--- a/include/crypto/sha256_base.h
+++ b/include/crypto/sha256_base.h
@@ -9,7 +9,7 @@
 #define _CRYPTO_SHA256_BASE_H
 
 #include <crypto/internal/hash.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <linux/crypto.h>
 #include <linux/module.h>
 #include <linux/string.h>
diff --git a/include/crypto/sha512_base.h b/include/crypto/sha512_base.h
index 93ab73baa38e..b370b3340b16 100644
--- a/include/crypto/sha512_base.h
+++ b/include/crypto/sha512_base.h
@@ -9,7 +9,7 @@
 #define _CRYPTO_SHA512_BASE_H
 
 #include <crypto/internal/hash.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <linux/crypto.h>
 #include <linux/module.h>
 #include <linux/string.h>
diff --git a/include/linux/ccp.h b/include/linux/ccp.h
index a5dfbaf2470d..868924dec5a1 100644
--- a/include/linux/ccp.h
+++ b/include/linux/ccp.h
@@ -15,7 +15,8 @@
 #include <linux/workqueue.h>
 #include <linux/list.h>
 #include <crypto/aes.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
+#include <crypto/sha2.h>
 
 struct ccp_device;
 struct ccp_cmd;
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 72d62cbc1578..6c00140538b9 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -21,7 +21,7 @@
 #include <linux/if_vlan.h>
 #include <linux/vmalloc.h>
 #include <linux/sockptr.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
 
 #include <net/sch_generic.h>
 
diff --git a/include/linux/purgatory.h b/include/linux/purgatory.h
index b950e961cfa8..d7dc1559427f 100644
--- a/include/linux/purgatory.h
+++ b/include/linux/purgatory.h
@@ -3,7 +3,7 @@
 #define _LINUX_PURGATORY_H
 
 #include <linux/types.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <uapi/linux/kexec.h>
 
 struct kexec_sha_region {
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index 106e4500fd53..4fcfe0b70c4e 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -11,7 +11,7 @@
 #include <asm/page.h>
 #include <asm/sections.h>
 
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
 
 /* vmcoreinfo stuff */
 unsigned char *vmcoreinfo_data;
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index 8798a8183974..4f8efc278aa7 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -42,7 +42,6 @@
 #include <asm/sections.h>
 
 #include <crypto/hash.h>
-#include <crypto/sha.h>
 #include "kexec_internal.h"
 
 DEFINE_MUTEX(kexec_mutex);
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index e21f6b9234f7..b02086d70492 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -20,7 +20,7 @@
 #include <linux/fs.h>
 #include <linux/ima.h>
 #include <crypto/hash.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <linux/elf.h>
 #include <linux/elfcore.h>
 #include <linux/kernel.h>
diff --git a/lib/crypto/sha256.c b/lib/crypto/sha256.c
index cdef37c05972..72a4b0b1df28 100644
--- a/lib/crypto/sha256.c
+++ b/lib/crypto/sha256.c
@@ -15,7 +15,7 @@
 #include <linux/export.h>
 #include <linux/module.h>
 #include <linux/string.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <asm/unaligned.h>
 
 static const u32 SHA256_K[] = {
diff --git a/lib/digsig.c b/lib/digsig.c
index e0627c3e53b2..04b5e55ed95f 100644
--- a/lib/digsig.c
+++ b/lib/digsig.c
@@ -20,7 +20,7 @@
 #include <linux/key.h>
 #include <linux/crypto.h>
 #include <crypto/hash.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
 #include <keys/user-type.h>
 #include <linux/mpi.h>
 #include <linux/digsig.h>
diff --git a/lib/sha1.c b/lib/sha1.c
index 49257a915bb6..9bd1935a1472 100644
--- a/lib/sha1.c
+++ b/lib/sha1.c
@@ -9,7 +9,7 @@
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/bitops.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
 #include <asm/unaligned.h>
 
 /*
diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c
index 85dddfe3a2c6..687d95dce085 100644
--- a/net/ipv6/seg6_hmac.c
+++ b/net/ipv6/seg6_hmac.c
@@ -35,7 +35,6 @@
 #include <net/xfrm.h>
 
 #include <crypto/hash.h>
-#include <crypto/sha.h>
 #include <net/seg6.h>
 #include <net/genetlink.h>
 #include <net/seg6_hmac.h>
diff --git a/net/mptcp/crypto.c b/net/mptcp/crypto.c
index 05d398d3fde4..b472dc149856 100644
--- a/net/mptcp/crypto.c
+++ b/net/mptcp/crypto.c
@@ -21,7 +21,7 @@
  */
 
 #include <linux/kernel.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <asm/unaligned.h>
 
 #include "protocol.h"
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index a044dd43411d..90cd52df99a6 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -7,7 +7,7 @@
 #define pr_fmt(fmt) "MPTCP: " fmt
 
 #include <linux/kernel.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <net/tcp.h>
 #include <net/mptcp.h>
 #include "protocol.h"
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index ac4a1fe3550b..b229ae914d76 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -10,7 +10,7 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <crypto/algapi.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <net/sock.h>
 #include <net/inet_common.h>
 #include <net/inet_hashtables.h>
diff --git a/security/integrity/integrity.h b/security/integrity/integrity.h
index 413c803c5208..547425c20e11 100644
--- a/security/integrity/integrity.h
+++ b/security/integrity/integrity.h
@@ -14,7 +14,7 @@
 
 #include <linux/types.h>
 #include <linux/integrity.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
 #include <linux/key.h>
 #include <linux/audit.h>
 
diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c
index 192e531c146f..87432b35d771 100644
--- a/security/keys/encrypted-keys/encrypted.c
+++ b/security/keys/encrypted-keys/encrypted.c
@@ -29,7 +29,7 @@
 #include <crypto/aes.h>
 #include <crypto/algapi.h>
 #include <crypto/hash.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <crypto/skcipher.h>
 
 #include "encrypted.h"
diff --git a/security/keys/trusted-keys/trusted_tpm1.c b/security/keys/trusted-keys/trusted_tpm1.c
index b9fe02e5f84f..74d82093cbaa 100644
--- a/security/keys/trusted-keys/trusted_tpm1.c
+++ b/security/keys/trusted-keys/trusted_tpm1.c
@@ -22,7 +22,7 @@
 #include <linux/rcupdate.h>
 #include <linux/crypto.h>
 #include <crypto/hash.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
 #include <linux/capability.h>
 #include <linux/tpm.h>
 #include <linux/tpm_command.h>
diff --git a/sound/soc/codecs/cros_ec_codec.c b/sound/soc/codecs/cros_ec_codec.c
index 28f039adfa13..58894bf47514 100644
--- a/sound/soc/codecs/cros_ec_codec.c
+++ b/sound/soc/codecs/cros_ec_codec.c
@@ -8,7 +8,7 @@
  * EC for audio function.
  */
 
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <linux/acpi.h>
 #include <linux/delay.h>
 #include <linux/device.h>
-- 
cgit v1.2.3


From ded5ed04d85e299770dcb7e82c2127b8054a00c8 Mon Sep 17 00:00:00 2001
From: Souradeep Chowdhury <schowdhu@codeaurora.org>
Date: Wed, 30 Sep 2020 13:44:13 +0530
Subject: soc: qcom: llcc: Add configuration data for SM8150

Add LLCC configuration data for SM8150 SoC which controls
LLCC behaviour.

Signed-off-by: Souradeep Chowdhury <schowdhu@codeaurora.org>
Link: https://lore.kernel.org/r/957e3ae50c75720ef6227529d5ce3d4b457802e9.1601452132.git.schowdhu@codeaurora.org
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 drivers/soc/qcom/llcc-qcom.c       | 30 ++++++++++++++++++++++++++++++
 include/linux/soc/qcom/llcc-qcom.h |  6 ++++++
 2 files changed, 36 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/soc/qcom/llcc-qcom.c b/drivers/soc/qcom/llcc-qcom.c
index 96c20e673436..16b421608e9c 100644
--- a/drivers/soc/qcom/llcc-qcom.c
+++ b/drivers/soc/qcom/llcc-qcom.c
@@ -123,6 +123,30 @@ static const struct llcc_slice_config sdm845_data[] =  {
 	{ LLCC_AUDHW,    22, 1024, 1, 1, 0xffc, 0x2,   0, 0, 1, 1, 0 },
 };
 
+static const struct llcc_slice_config sm8150_data[] =  {
+	{  LLCC_CPUSS,    1, 3072, 1, 1, 0xFFF, 0x0,   0, 0, 0, 1, 1 },
+	{  LLCC_VIDSC0,   2, 512,  2, 1, 0xFFF, 0x0,   0, 0, 0, 1, 0 },
+	{  LLCC_VIDSC1,   3, 512,  2, 1, 0xFFF, 0x0,   0, 0, 0, 1, 0 },
+	{  LLCC_AUDIO,    6, 1024, 1, 1, 0xFFF, 0x0,   0, 0, 0, 1, 0 },
+	{  LLCC_MDMHPGRW, 7, 3072, 1, 0, 0xFF,  0xF00, 0, 0, 0, 1, 0 },
+	{  LLCC_MDM,      8, 3072, 1, 1, 0xFFF, 0x0,   0, 0, 0, 1, 0 },
+	{  LLCC_MODHW,    9, 1024, 1, 1, 0xFFF, 0x0,   0, 0, 0, 1, 0 },
+	{  LLCC_CMPT,    10, 3072, 1, 1, 0xFFF, 0x0,   0, 0, 0, 1, 0 },
+	{  LLCC_GPUHTW , 11, 512,  1, 1, 0xFFF, 0x0,   0, 0, 0, 1, 0 },
+	{  LLCC_GPU,     12, 2560, 1, 1, 0xFFF, 0x0,   0, 0, 0, 1, 0 },
+	{  LLCC_MMUHWT,  13, 1024, 1, 1, 0xFFF, 0x0,   0, 0, 0, 0, 1 },
+	{  LLCC_CMPTDMA, 15, 3072, 1, 1, 0xFFF, 0x0,   0, 0, 0, 1, 0 },
+	{  LLCC_DISP,    16, 3072, 1, 1, 0xFFF, 0x0,   0, 0, 0, 1, 0 },
+	{  LLCC_MDMHPFX, 20, 1024, 2, 1, 0xFFF, 0x0,   0, 0, 0, 1, 0 },
+	{  LLCC_MDMHPFX, 21, 1024, 0, 1, 0xF,   0x0,   0, 0, 0, 1, 0 },
+	{  LLCC_AUDHW,   22, 1024, 1, 1, 0xFFF, 0x0,   0, 0, 0, 1, 0 },
+	{  LLCC_NPU,     23, 3072, 1, 1, 0xFFF, 0x0,   0, 0, 0, 1, 0 },
+	{  LLCC_WLHW,    24, 3072, 1, 1, 0xFFF, 0x0,   0, 0, 0, 1, 0 },
+	{  LLCC_MODPE,   29, 256,  1, 1, 0xF,   0x0,   0, 0, 0, 1, 0 },
+	{  LLCC_APTCM,   30, 256,  3, 1, 0x0,   0x1,   1, 0, 0, 1, 0 },
+	{  LLCC_WRCACHE, 31, 128,  1, 1, 0xFFF, 0x0,   0, 0, 0, 0, 0 },
+};
+
 static const struct qcom_llcc_config sc7180_cfg = {
 	.sct_data	= sc7180_data,
 	.size		= ARRAY_SIZE(sc7180_data),
@@ -135,6 +159,11 @@ static const struct qcom_llcc_config sdm845_cfg = {
 	.need_llcc_cfg	= false,
 };
 
+static const struct qcom_llcc_config sm8150_cfg = {
+	.sct_data       = sm8150_data,
+	.size           = ARRAY_SIZE(sm8150_data),
+};
+
 static struct llcc_drv_data *drv_data = (void *) -EPROBE_DEFER;
 
 /**
@@ -529,6 +558,7 @@ err:
 static const struct of_device_id qcom_llcc_of_match[] = {
 	{ .compatible = "qcom,sc7180-llcc", .data = &sc7180_cfg },
 	{ .compatible = "qcom,sdm845-llcc", .data = &sdm845_cfg },
+	{ .compatible = "qcom,sm8150-llcc", .data = &sm8150_cfg },
 	{ }
 };
 
diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h
index 90b864655822..3db6797ba6ff 100644
--- a/include/linux/soc/qcom/llcc-qcom.h
+++ b/include/linux/soc/qcom/llcc-qcom.h
@@ -16,6 +16,7 @@
 #define LLCC_AUDIO       6
 #define LLCC_MDMHPGRW    7
 #define LLCC_MDM         8
+#define LLCC_MODHW       9
 #define LLCC_CMPT        10
 #define LLCC_GPUHTW      11
 #define LLCC_GPU         12
@@ -26,6 +27,11 @@
 #define LLCC_MDMHPFX     20
 #define LLCC_MDMPNG      21
 #define LLCC_AUDHW       22
+#define LLCC_NPU         23
+#define LLCC_WLHW        24
+#define LLCC_MODPE       29
+#define LLCC_APTCM       30
+#define LLCC_WRCACHE     31
 
 /**
  * llcc_slice_desc - Cache slice descriptor
-- 
cgit v1.2.3


From 69d98969a0540039fc04e0f22bbe9f41b0a13d66 Mon Sep 17 00:00:00 2001
From: Oliver Hartkopp <socketcan@hartkopp.net>
Date: Tue, 10 Nov 2020 11:18:46 +0100
Subject: can: rename get_can_dlc() macro with can_cc_dlc2len()

The get_can_dlc() macro is used to ensure the payload length information of
the Classical CAN frame to be max 8 bytes (the CAN_MAX_DLEN).

Rename the macro and use the correct constant in preparation of the len/dlc
cleanup for Classical CAN frames.

Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Link: https://lore.kernel.org/r/20201110101852.1973-3-socketcan@hartkopp.net
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/at91_can.c                        | 2 +-
 drivers/net/can/c_can/c_can.c                     | 2 +-
 drivers/net/can/cc770/cc770.c                     | 2 +-
 drivers/net/can/flexcan.c                         | 2 +-
 drivers/net/can/grcan.c                           | 2 +-
 drivers/net/can/ifi_canfd/ifi_canfd.c             | 2 +-
 drivers/net/can/janz-ican3.c                      | 4 ++--
 drivers/net/can/m_can/m_can.c                     | 2 +-
 drivers/net/can/mscan/mscan.c                     | 2 +-
 drivers/net/can/pch_can.c                         | 4 ++--
 drivers/net/can/peak_canfd/peak_canfd.c           | 2 +-
 drivers/net/can/rcar/rcar_can.c                   | 2 +-
 drivers/net/can/rcar/rcar_canfd.c                 | 4 ++--
 drivers/net/can/sja1000/sja1000.c                 | 2 +-
 drivers/net/can/softing/softing_main.c            | 2 +-
 drivers/net/can/spi/hi311x.c                      | 2 +-
 drivers/net/can/spi/mcp251x.c                     | 4 ++--
 drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c    | 2 +-
 drivers/net/can/sun4i_can.c                       | 2 +-
 drivers/net/can/ti_hecc.c                         | 2 +-
 drivers/net/can/usb/ems_usb.c                     | 2 +-
 drivers/net/can/usb/esd_usb2.c                    | 2 +-
 drivers/net/can/usb/gs_usb.c                      | 2 +-
 drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c | 4 ++--
 drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c  | 4 ++--
 drivers/net/can/usb/mcba_usb.c                    | 2 +-
 drivers/net/can/usb/peak_usb/pcan_usb.c           | 2 +-
 drivers/net/can/usb/peak_usb/pcan_usb_fd.c        | 2 +-
 drivers/net/can/usb/ucan.c                        | 8 ++++----
 drivers/net/can/usb/usb_8dev.c                    | 2 +-
 drivers/net/can/xilinx_can.c                      | 4 ++--
 include/linux/can/dev.h                           | 8 ++++----
 32 files changed, 45 insertions(+), 45 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c
index c14de95d2ca7..db06254f8eb7 100644
--- a/drivers/net/can/at91_can.c
+++ b/drivers/net/can/at91_can.c
@@ -580,7 +580,7 @@ static void at91_read_mb(struct net_device *dev, unsigned int mb,
 		cf->can_id = (reg_mid >> 18) & CAN_SFF_MASK;
 
 	reg_msr = at91_read(priv, AT91_MSR(mb));
-	cf->can_dlc = get_can_dlc((reg_msr >> 16) & 0xf);
+	cf->can_dlc = can_cc_dlc2len((reg_msr >> 16) & 0xf);
 
 	if (reg_msr & AT91_MSR_MRTR)
 		cf->can_id |= CAN_RTR_FLAG;
diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c
index 1ccdbe89585b..56cc705959ea 100644
--- a/drivers/net/can/c_can/c_can.c
+++ b/drivers/net/can/c_can/c_can.c
@@ -397,7 +397,7 @@ static int c_can_read_msg_object(struct net_device *dev, int iface, u32 ctrl)
 		return -ENOMEM;
 	}
 
-	frame->can_dlc = get_can_dlc(ctrl & 0x0F);
+	frame->can_dlc = can_cc_dlc2len(ctrl & 0x0F);
 
 	arb = priv->read_reg32(priv, C_CAN_IFACE(ARB1_REG, iface));
 
diff --git a/drivers/net/can/cc770/cc770.c b/drivers/net/can/cc770/cc770.c
index 07e2b8df5153..3fd2a276dd93 100644
--- a/drivers/net/can/cc770/cc770.c
+++ b/drivers/net/can/cc770/cc770.c
@@ -486,7 +486,7 @@ static void cc770_rx(struct net_device *dev, unsigned int mo, u8 ctrl1)
 		}
 
 		cf->can_id = id;
-		cf->can_dlc = get_can_dlc((config & 0xf0) >> 4);
+		cf->can_dlc = can_cc_dlc2len((config & 0xf0) >> 4);
 		for (i = 0; i < cf->can_dlc; i++)
 			cf->data[i] = cc770_read_reg(priv, msgobj[mo].data[i]);
 	}
diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index 99e5f272205d..50ccd18170c8 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -1005,7 +1005,7 @@ static struct sk_buff *flexcan_mailbox_read(struct can_rx_offload *offload,
 		if (reg_ctrl & FLEXCAN_MB_CNT_BRS)
 			cfd->flags |= CANFD_BRS;
 	} else {
-		cfd->len = get_can_dlc((reg_ctrl >> 16) & 0xf);
+		cfd->len = can_cc_dlc2len((reg_ctrl >> 16) & 0xf);
 
 		if (reg_ctrl & FLEXCAN_MB_CNT_RTR)
 			cfd->can_id |= CAN_RTR_FLAG;
diff --git a/drivers/net/can/grcan.c b/drivers/net/can/grcan.c
index 39802f107eb1..c71c9b8683d5 100644
--- a/drivers/net/can/grcan.c
+++ b/drivers/net/can/grcan.c
@@ -1201,7 +1201,7 @@ static int grcan_receive(struct net_device *dev, int budget)
 			cf->can_id = ((slot[0] & GRCAN_MSG_BID)
 				      >> GRCAN_MSG_BID_BIT);
 		}
-		cf->can_dlc = get_can_dlc((slot[1] & GRCAN_MSG_DLC)
+		cf->can_dlc = can_cc_dlc2len((slot[1] & GRCAN_MSG_DLC)
 					  >> GRCAN_MSG_DLC_BIT);
 		if (rtr) {
 			cf->can_id |= CAN_RTR_FLAG;
diff --git a/drivers/net/can/ifi_canfd/ifi_canfd.c b/drivers/net/can/ifi_canfd/ifi_canfd.c
index 74503cacf594..cc790354a8ee 100644
--- a/drivers/net/can/ifi_canfd/ifi_canfd.c
+++ b/drivers/net/can/ifi_canfd/ifi_canfd.c
@@ -273,7 +273,7 @@ static void ifi_canfd_read_fifo(struct net_device *ndev)
 	if (rxdlc & IFI_CANFD_RXFIFO_DLC_EDL)
 		cf->len = can_dlc2len(dlc);
 	else
-		cf->len = get_can_dlc(dlc);
+		cf->len = can_cc_dlc2len(dlc);
 
 	rxid = readl(priv->base + IFI_CANFD_RXFIFO_ID);
 	id = (rxid >> IFI_CANFD_RXFIFO_ID_ID_OFFSET);
diff --git a/drivers/net/can/janz-ican3.c b/drivers/net/can/janz-ican3.c
index f929db893957..6a21af05ba27 100644
--- a/drivers/net/can/janz-ican3.c
+++ b/drivers/net/can/janz-ican3.c
@@ -916,10 +916,10 @@ static void ican3_to_can_frame(struct ican3_dev *mod,
 
 		cf->can_id |= desc->data[0] << 3;
 		cf->can_id |= (desc->data[1] & 0xe0) >> 5;
-		cf->can_dlc = get_can_dlc(desc->data[1] & ICAN3_CAN_DLC_MASK);
+		cf->can_dlc = can_cc_dlc2len(desc->data[1] & ICAN3_CAN_DLC_MASK);
 		memcpy(cf->data, &desc->data[2], cf->can_dlc);
 	} else {
-		cf->can_dlc = get_can_dlc(desc->data[0] & ICAN3_CAN_DLC_MASK);
+		cf->can_dlc = can_cc_dlc2len(desc->data[0] & ICAN3_CAN_DLC_MASK);
 		if (desc->data[0] & ICAN3_EFF_RTR)
 			cf->can_id |= CAN_RTR_FLAG;
 
diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index f3fc37e96b08..2e46a5916656 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -459,7 +459,7 @@ static void m_can_read_fifo(struct net_device *dev, u32 rxfs)
 	if (dlc & RX_BUF_FDF)
 		cf->len = can_dlc2len((dlc >> 16) & 0x0F);
 	else
-		cf->len = get_can_dlc((dlc >> 16) & 0x0F);
+		cf->len = can_cc_dlc2len((dlc >> 16) & 0x0F);
 
 	id = m_can_fifo_read(cdev, fgi, M_CAN_FIFO_ID);
 	if (id & RX_BUF_XTD)
diff --git a/drivers/net/can/mscan/mscan.c b/drivers/net/can/mscan/mscan.c
index 640ba1b356ec..95bf7338b358 100644
--- a/drivers/net/can/mscan/mscan.c
+++ b/drivers/net/can/mscan/mscan.c
@@ -312,7 +312,7 @@ static void mscan_get_rx_frame(struct net_device *dev, struct can_frame *frame)
 	if (can_id & 1)
 		frame->can_id |= CAN_RTR_FLAG;
 
-	frame->can_dlc = get_can_dlc(in_8(&regs->rx.dlr) & 0xf);
+	frame->can_dlc = can_cc_dlc2len(in_8(&regs->rx.dlr) & 0xf);
 
 	if (!(frame->can_id & CAN_RTR_FLAG)) {
 		void __iomem *data = &regs->rx.dsr1_0;
diff --git a/drivers/net/can/pch_can.c b/drivers/net/can/pch_can.c
index 5c180d2f3c3c..9509bac8352d 100644
--- a/drivers/net/can/pch_can.c
+++ b/drivers/net/can/pch_can.c
@@ -683,7 +683,7 @@ static int pch_can_rx_normal(struct net_device *ndev, u32 obj_num, int quota)
 		if (id2 & PCH_ID2_DIR)
 			cf->can_id |= CAN_RTR_FLAG;
 
-		cf->can_dlc = get_can_dlc((ioread32(&priv->regs->
+		cf->can_dlc = can_cc_dlc2len((ioread32(&priv->regs->
 						    ifregs[0].mcont)) & 0xF);
 
 		for (i = 0; i < cf->can_dlc; i += 2) {
@@ -715,7 +715,7 @@ static void pch_can_tx_complete(struct net_device *ndev, u32 int_stat)
 	iowrite32(PCH_CMASK_RX_TX_GET | PCH_CMASK_CLRINTPND,
 		  &priv->regs->ifregs[1].cmask);
 	pch_can_rw_msg_obj(&priv->regs->ifregs[1].creq, int_stat);
-	dlc = get_can_dlc(ioread32(&priv->regs->ifregs[1].mcont) &
+	dlc = can_cc_dlc2len(ioread32(&priv->regs->ifregs[1].mcont) &
 			  PCH_IF_MCONT_DLC);
 	stats->tx_bytes += dlc;
 	stats->tx_packets++;
diff --git a/drivers/net/can/peak_canfd/peak_canfd.c b/drivers/net/can/peak_canfd/peak_canfd.c
index 40c33b8a5fda..9ea2adea3f0f 100644
--- a/drivers/net/can/peak_canfd/peak_canfd.c
+++ b/drivers/net/can/peak_canfd/peak_canfd.c
@@ -259,7 +259,7 @@ static int pucan_handle_can_rx(struct peak_canfd_priv *priv,
 	if (rx_msg_flags & PUCAN_MSG_EXT_DATA_LEN)
 		cf_len = can_dlc2len(get_canfd_dlc(pucan_msg_get_dlc(msg)));
 	else
-		cf_len = get_can_dlc(pucan_msg_get_dlc(msg));
+		cf_len = can_cc_dlc2len(pucan_msg_get_dlc(msg));
 
 	/* if this frame is an echo, */
 	if (rx_msg_flags & PUCAN_MSG_LOOPED_BACK) {
diff --git a/drivers/net/can/rcar/rcar_can.c b/drivers/net/can/rcar/rcar_can.c
index 48575900adb7..711ef4996b48 100644
--- a/drivers/net/can/rcar/rcar_can.c
+++ b/drivers/net/can/rcar/rcar_can.c
@@ -659,7 +659,7 @@ static void rcar_can_rx_pkt(struct rcar_can_priv *priv)
 		cf->can_id = (data >> RCAR_CAN_SID_SHIFT) & CAN_SFF_MASK;
 
 	dlc = readb(&priv->regs->mb[RCAR_CAN_RX_FIFO_MBX].dlc);
-	cf->can_dlc = get_can_dlc(dlc);
+	cf->can_dlc = can_cc_dlc2len(dlc);
 	if (data & RCAR_CAN_RTR) {
 		cf->can_id |= CAN_RTR_FLAG;
 	} else {
diff --git a/drivers/net/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c
index de59dd6aad29..899a3218ce5e 100644
--- a/drivers/net/can/rcar/rcar_canfd.c
+++ b/drivers/net/can/rcar/rcar_canfd.c
@@ -1448,7 +1448,7 @@ static void rcar_canfd_rx_pkt(struct rcar_canfd_channel *priv)
 		if (sts & RCANFD_RFFDSTS_RFFDF)
 			cf->len = can_dlc2len(RCANFD_RFPTR_RFDLC(dlc));
 		else
-			cf->len = get_can_dlc(RCANFD_RFPTR_RFDLC(dlc));
+			cf->len = can_cc_dlc2len(RCANFD_RFPTR_RFDLC(dlc));
 
 		if (sts & RCANFD_RFFDSTS_RFESI) {
 			cf->flags |= CANFD_ESI;
@@ -1464,7 +1464,7 @@ static void rcar_canfd_rx_pkt(struct rcar_canfd_channel *priv)
 			rcar_canfd_get_data(priv, cf, RCANFD_F_RFDF(ridx, 0));
 		}
 	} else {
-		cf->len = get_can_dlc(RCANFD_RFPTR_RFDLC(dlc));
+		cf->len = can_cc_dlc2len(RCANFD_RFPTR_RFDLC(dlc));
 		if (id & RCANFD_RFID_RFRTR)
 			cf->can_id |= CAN_RTR_FLAG;
 		else
diff --git a/drivers/net/can/sja1000/sja1000.c b/drivers/net/can/sja1000/sja1000.c
index 9f107798f904..1f188f2d126e 100644
--- a/drivers/net/can/sja1000/sja1000.c
+++ b/drivers/net/can/sja1000/sja1000.c
@@ -367,7 +367,7 @@ static void sja1000_rx(struct net_device *dev)
 		    | (priv->read_reg(priv, SJA1000_ID2) >> 5);
 	}
 
-	cf->can_dlc = get_can_dlc(fi & 0x0F);
+	cf->can_dlc = can_cc_dlc2len(fi & 0x0F);
 	if (fi & SJA1000_FI_RTR) {
 		id |= CAN_RTR_FLAG;
 	} else {
diff --git a/drivers/net/can/softing/softing_main.c b/drivers/net/can/softing/softing_main.c
index 9d2faaa39ce4..39e8275ee7ba 100644
--- a/drivers/net/can/softing/softing_main.c
+++ b/drivers/net/can/softing/softing_main.c
@@ -261,7 +261,7 @@ static int softing_handle_1(struct softing *card)
 	} else {
 		if (cmd & CMD_RTR)
 			msg.can_id |= CAN_RTR_FLAG;
-		msg.can_dlc = get_can_dlc(*ptr++);
+		msg.can_dlc = can_cc_dlc2len(*ptr++);
 		if (cmd & CMD_XTD) {
 			msg.can_id |= CAN_EFF_FLAG;
 			msg.can_id |= le32_to_cpup((void *)ptr);
diff --git a/drivers/net/can/spi/hi311x.c b/drivers/net/can/spi/hi311x.c
index 73d48c3b8ded..728f34b696a7 100644
--- a/drivers/net/can/spi/hi311x.c
+++ b/drivers/net/can/spi/hi311x.c
@@ -341,7 +341,7 @@ static void hi3110_hw_rx(struct spi_device *spi)
 	}
 
 	/* Data length */
-	frame->can_dlc = get_can_dlc(buf[HI3110_FIFO_WOTIME_DLC_OFF] & 0x0F);
+	frame->can_dlc = can_cc_dlc2len(buf[HI3110_FIFO_WOTIME_DLC_OFF] & 0x0F);
 
 	if (buf[HI3110_FIFO_WOTIME_ID_OFF + 3] & HI3110_FIFO_WOTIME_ID_RTR)
 		frame->can_id |= CAN_RTR_FLAG;
diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c
index 22d814ae4edc..6ddebb1c4a24 100644
--- a/drivers/net/can/spi/mcp251x.c
+++ b/drivers/net/can/spi/mcp251x.c
@@ -664,7 +664,7 @@ static void mcp251x_hw_rx_frame(struct spi_device *spi, u8 *buf,
 		for (i = 1; i < RXBDAT_OFF; i++)
 			buf[i] = mcp251x_read_reg(spi, RXBCTRL(buf_idx) + i);
 
-		len = get_can_dlc(buf[RXBDLC_OFF] & RXBDLC_LEN_MASK);
+		len = can_cc_dlc2len(buf[RXBDLC_OFF] & RXBDLC_LEN_MASK);
 		for (; i < (RXBDAT_OFF + len); i++)
 			buf[i] = mcp251x_read_reg(spi, RXBCTRL(buf_idx) + i);
 	} else {
@@ -720,7 +720,7 @@ static void mcp251x_hw_rx(struct spi_device *spi, int buf_idx)
 			frame->can_id |= CAN_RTR_FLAG;
 	}
 	/* Data length */
-	frame->can_dlc = get_can_dlc(buf[RXBDLC_OFF] & RXBDLC_LEN_MASK);
+	frame->can_dlc = can_cc_dlc2len(buf[RXBDLC_OFF] & RXBDLC_LEN_MASK);
 	memcpy(frame->data, buf + RXBDAT_OFF, frame->can_dlc);
 
 	priv->net->stats.rx_packets++;
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
index 9c215f7c5f81..c0a08400f444 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
@@ -1410,7 +1410,7 @@ mcp251xfd_hw_rx_obj_to_skb(const struct mcp251xfd_priv *priv,
 		if (hw_rx_obj->flags & MCP251XFD_OBJ_FLAGS_RTR)
 			cfd->can_id |= CAN_RTR_FLAG;
 
-		cfd->len = get_can_dlc(FIELD_GET(MCP251XFD_OBJ_FLAGS_DLC,
+		cfd->len = can_cc_dlc2len(FIELD_GET(MCP251XFD_OBJ_FLAGS_DLC,
 						 hw_rx_obj->flags));
 	}
 
diff --git a/drivers/net/can/sun4i_can.c b/drivers/net/can/sun4i_can.c
index e2c6cf4b2228..0e2569779895 100644
--- a/drivers/net/can/sun4i_can.c
+++ b/drivers/net/can/sun4i_can.c
@@ -475,7 +475,7 @@ static void sun4i_can_rx(struct net_device *dev)
 		return;
 
 	fi = readl(priv->base + SUN4I_REG_BUF0_ADDR);
-	cf->can_dlc = get_can_dlc(fi & 0x0F);
+	cf->can_dlc = can_cc_dlc2len(fi & 0x0F);
 	if (fi & SUN4I_MSG_EFF_FLAG) {
 		dreg = SUN4I_REG_BUF5_ADDR;
 		id = (readl(priv->base + SUN4I_REG_BUF1_ADDR) << 21) |
diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c
index 2c22f40e12bd..0b1fd34f4c83 100644
--- a/drivers/net/can/ti_hecc.c
+++ b/drivers/net/can/ti_hecc.c
@@ -566,7 +566,7 @@ static struct sk_buff *ti_hecc_mailbox_read(struct can_rx_offload *offload,
 	data = hecc_read_mbx(priv, mbxno, HECC_CANMCF);
 	if (data & HECC_CANMCF_RTR)
 		cf->can_id |= CAN_RTR_FLAG;
-	cf->can_dlc = get_can_dlc(data & 0xF);
+	cf->can_dlc = can_cc_dlc2len(data & 0xF);
 
 	data = hecc_read_mbx(priv, mbxno, HECC_CANMDL);
 	*(__be32 *)(cf->data) = cpu_to_be32(data);
diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c
index 4f52810bebf8..288781934149 100644
--- a/drivers/net/can/usb/ems_usb.c
+++ b/drivers/net/can/usb/ems_usb.c
@@ -306,7 +306,7 @@ static void ems_usb_rx_can_msg(struct ems_usb *dev, struct ems_cpc_msg *msg)
 		return;
 
 	cf->can_id = le32_to_cpu(msg->msg.can_msg.id);
-	cf->can_dlc = get_can_dlc(msg->msg.can_msg.length & 0xF);
+	cf->can_dlc = can_cc_dlc2len(msg->msg.can_msg.length & 0xF);
 
 	if (msg->type == CPC_MSG_TYPE_EXT_CAN_FRAME ||
 	    msg->type == CPC_MSG_TYPE_EXT_RTR_FRAME)
diff --git a/drivers/net/can/usb/esd_usb2.c b/drivers/net/can/usb/esd_usb2.c
index b5d7ed21d7d9..72999de550d1 100644
--- a/drivers/net/can/usb/esd_usb2.c
+++ b/drivers/net/can/usb/esd_usb2.c
@@ -321,7 +321,7 @@ static void esd_usb2_rx_can_msg(struct esd_usb2_net_priv *priv,
 		}
 
 		cf->can_id = id & ESD_IDMASK;
-		cf->can_dlc = get_can_dlc(msg->msg.rx.dlc & ~ESD_RTR);
+		cf->can_dlc = can_cc_dlc2len(msg->msg.rx.dlc & ~ESD_RTR);
 
 		if (id & ESD_EXTID)
 			cf->can_id |= CAN_EFF_FLAG;
diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index 3005157059ca..b1729b208788 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -331,7 +331,7 @@ static void gs_usb_receive_bulk_callback(struct urb *urb)
 
 		cf->can_id = hf->can_id;
 
-		cf->can_dlc = get_can_dlc(hf->can_dlc);
+		cf->can_dlc = can_cc_dlc2len(hf->can_dlc);
 		memcpy(cf->data, hf->data, 8);
 
 		/* ERROR frames tell us information about the controller */
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
index 218fadc91155..493a614bf333 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
@@ -1180,7 +1180,7 @@ static void kvaser_usb_hydra_rx_msg_std(const struct kvaser_usb *dev,
 	if (flags & KVASER_USB_HYDRA_CF_FLAG_OVERRUN)
 		kvaser_usb_can_rx_over_error(priv->netdev);
 
-	cf->can_dlc = get_can_dlc(cmd->rx_can.dlc);
+	cf->can_dlc = can_cc_dlc2len(cmd->rx_can.dlc);
 
 	if (flags & KVASER_USB_HYDRA_CF_FLAG_REMOTE_FRAME)
 		cf->can_id |= CAN_RTR_FLAG;
@@ -1257,7 +1257,7 @@ static void kvaser_usb_hydra_rx_msg_ext(const struct kvaser_usb *dev,
 		if (flags & KVASER_USB_HYDRA_CF_FLAG_ESI)
 			cf->flags |= CANFD_ESI;
 	} else {
-		cf->len = get_can_dlc(dlc);
+		cf->len = can_cc_dlc2len(dlc);
 	}
 
 	if (flags & KVASER_USB_HYDRA_CF_FLAG_REMOTE_FRAME)
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
index 1b9957f12459..916ab994cce4 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
@@ -978,7 +978,7 @@ static void kvaser_usb_leaf_rx_can_msg(const struct kvaser_usb *dev,
 		else
 			cf->can_id &= CAN_SFF_MASK;
 
-		cf->can_dlc = get_can_dlc(cmd->u.leaf.log_message.dlc);
+		cf->can_dlc = can_cc_dlc2len(cmd->u.leaf.log_message.dlc);
 
 		if (cmd->u.leaf.log_message.flags & MSG_FLAG_REMOTE_FRAME)
 			cf->can_id |= CAN_RTR_FLAG;
@@ -996,7 +996,7 @@ static void kvaser_usb_leaf_rx_can_msg(const struct kvaser_usb *dev,
 			cf->can_id |= CAN_EFF_FLAG;
 		}
 
-		cf->can_dlc = get_can_dlc(rx_data[5]);
+		cf->can_dlc = can_cc_dlc2len(rx_data[5]);
 
 		if (cmd->u.rx_can_header.flag & MSG_FLAG_REMOTE_FRAME)
 			cf->can_id |= CAN_RTR_FLAG;
diff --git a/drivers/net/can/usb/mcba_usb.c b/drivers/net/can/usb/mcba_usb.c
index e97f2e0da6b0..295886c6b565 100644
--- a/drivers/net/can/usb/mcba_usb.c
+++ b/drivers/net/can/usb/mcba_usb.c
@@ -451,7 +451,7 @@ static void mcba_usb_process_can(struct mcba_priv *priv,
 	if (msg->dlc & MCBA_DLC_RTR_MASK)
 		cf->can_id |= CAN_RTR_FLAG;
 
-	cf->can_dlc = get_can_dlc(msg->dlc & MCBA_DLC_MASK);
+	cf->can_dlc = can_cc_dlc2len(msg->dlc & MCBA_DLC_MASK);
 
 	memcpy(cf->data, msg->data, cf->can_dlc);
 
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c
index 63bd2ed96697..f7fc82203489 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb.c
@@ -734,7 +734,7 @@ static int pcan_usb_decode_data(struct pcan_usb_msg_context *mc, u8 status_len)
 		cf->can_id = le16_to_cpu(tmp16) >> 5;
 	}
 
-	cf->can_dlc = get_can_dlc(rec_len);
+	cf->can_dlc = can_cc_dlc2len(rec_len);
 
 	/* Only first packet timestamp is a word */
 	if (pcan_usb_decode_ts(mc, !mc->rec_ts_idx))
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
index d29d20525588..1f08dd22b3d5 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
@@ -499,7 +499,7 @@ static int pcan_usb_fd_decode_canmsg(struct pcan_usb_fd_if *usb_if,
 		if (!skb)
 			return -ENOMEM;
 
-		cfd->len = get_can_dlc(pucan_msg_get_dlc(rm));
+		cfd->len = can_cc_dlc2len(pucan_msg_get_dlc(rm));
 	}
 
 	cfd->can_id = le32_to_cpu(rm->can_id);
diff --git a/drivers/net/can/usb/ucan.c b/drivers/net/can/usb/ucan.c
index dc5290b36598..072058c6f6e8 100644
--- a/drivers/net/can/usb/ucan.c
+++ b/drivers/net/can/usb/ucan.c
@@ -303,12 +303,12 @@ struct ucan_priv {
 	struct ucan_urb_context *context_array;
 };
 
-static u8 ucan_get_can_dlc(struct ucan_can_msg *msg, u16 len)
+static u8 ucan_can_cc_dlc2len(struct ucan_can_msg *msg, u16 len)
 {
 	if (le32_to_cpu(msg->id) & CAN_RTR_FLAG)
-		return get_can_dlc(msg->dlc);
+		return can_cc_dlc2len(msg->dlc);
 	else
-		return get_can_dlc(len - (UCAN_IN_HDR_SIZE + sizeof(msg->id)));
+		return can_cc_dlc2len(len - (UCAN_IN_HDR_SIZE + sizeof(msg->id)));
 }
 
 static void ucan_release_context_array(struct ucan_priv *up)
@@ -614,7 +614,7 @@ static void ucan_rx_can_msg(struct ucan_priv *up, struct ucan_message_in *m)
 	cf->can_id = canid;
 
 	/* compute DLC taking RTR_FLAG into account */
-	cf->can_dlc = ucan_get_can_dlc(&m->msg.can_msg, len);
+	cf->can_dlc = ucan_can_cc_dlc2len(&m->msg.can_msg, len);
 
 	/* copy the payload of non RTR frames */
 	if (!(cf->can_id & CAN_RTR_FLAG) || (cf->can_id & CAN_ERR_FLAG))
diff --git a/drivers/net/can/usb/usb_8dev.c b/drivers/net/can/usb/usb_8dev.c
index 62749c67c959..216c58f8df6e 100644
--- a/drivers/net/can/usb/usb_8dev.c
+++ b/drivers/net/can/usb/usb_8dev.c
@@ -470,7 +470,7 @@ static void usb_8dev_rx_can_msg(struct usb_8dev_priv *priv,
 			return;
 
 		cf->can_id = be32_to_cpu(msg->id);
-		cf->can_dlc = get_can_dlc(msg->dlc & 0xF);
+		cf->can_dlc = can_cc_dlc2len(msg->dlc & 0xF);
 
 		if (msg->flags & USB_8DEV_EXTID)
 			cf->can_id |= CAN_EFF_FLAG;
diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index 48d746e18f30..73e8b1df1071 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -759,7 +759,7 @@ static int xcan_rx(struct net_device *ndev, int frame_base)
 				   XCAN_DLCR_DLC_SHIFT;
 
 	/* Change Xilinx CAN data length format to socketCAN data format */
-	cf->can_dlc = get_can_dlc(dlc);
+	cf->can_dlc = can_cc_dlc2len(dlc);
 
 	/* Change Xilinx CAN ID format to socketCAN ID format */
 	if (id_xcan & XCAN_IDR_IDE_MASK) {
@@ -835,7 +835,7 @@ static int xcanfd_rx(struct net_device *ndev, int frame_base)
 		cf->len = can_dlc2len((dlc & XCAN_DLCR_DLC_MASK) >>
 				  XCAN_DLCR_DLC_SHIFT);
 	else
-		cf->len = get_can_dlc((dlc & XCAN_DLCR_DLC_MASK) >>
+		cf->len = can_cc_dlc2len((dlc & XCAN_DLCR_DLC_MASK) >>
 					  XCAN_DLCR_DLC_SHIFT);
 
 	/* Change Xilinx CAN ID format to socketCAN ID format */
diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h
index 41ff31795320..9bc84c6978ec 100644
--- a/include/linux/can/dev.h
+++ b/include/linux/can/dev.h
@@ -98,14 +98,14 @@ static inline unsigned int can_bit_time(const struct can_bittiming *bt)
 }
 
 /*
- * get_can_dlc(value) - helper macro to cast a given data length code (dlc)
- * to u8 and ensure the dlc value to be max. 8 bytes.
+ * can_cc_dlc2len(value) - convert a given data length code (dlc) of a
+ * Classical CAN frame into a valid data length of max. 8 bytes.
  *
  * To be used in the CAN netdriver receive path to ensure conformance with
  * ISO 11898-1 Chapter 8.4.2.3 (DLC field)
  */
-#define get_can_dlc(i)		(min_t(u8, (i), CAN_MAX_DLC))
-#define get_canfd_dlc(i)	(min_t(u8, (i), CANFD_MAX_DLC))
+#define can_cc_dlc2len(dlc)	(min_t(u8, (dlc), CAN_MAX_DLEN))
+#define get_canfd_dlc(dlc)	(min_t(u8, (dlc), CANFD_MAX_DLC))
 
 /* Check for outgoing skbs that have not been created by the CAN subsystem */
 static inline bool can_skb_headroom_valid(struct net_device *dev,
-- 
cgit v1.2.3


From cd1124e76d740327be5d8f9ce3785ce1119daf4b Mon Sep 17 00:00:00 2001
From: Oliver Hartkopp <socketcan@hartkopp.net>
Date: Tue, 10 Nov 2020 11:18:47 +0100
Subject: can: remove obsolete get_canfd_dlc() macro

The macro was always used together with can_dlc2len() which sanitizes the
given dlc value on its own.

Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Link: https://lore.kernel.org/r/20201110101852.1973-4-socketcan@hartkopp.net
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/flexcan.c                         | 2 +-
 drivers/net/can/peak_canfd/peak_canfd.c           | 2 +-
 drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c    | 2 +-
 drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c | 2 +-
 drivers/net/can/usb/peak_usb/pcan_usb_fd.c        | 2 +-
 include/linux/can/dev.h                           | 1 -
 include/linux/can/dev/peak_canfd.h                | 2 +-
 7 files changed, 6 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index 50ccd18170c8..985569f946e5 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -1000,7 +1000,7 @@ static struct sk_buff *flexcan_mailbox_read(struct can_rx_offload *offload,
 		cfd->can_id = (reg_id >> 18) & CAN_SFF_MASK;
 
 	if (reg_ctrl & FLEXCAN_MB_CNT_EDL) {
-		cfd->len = can_dlc2len(get_canfd_dlc((reg_ctrl >> 16) & 0xf));
+		cfd->len = can_dlc2len((reg_ctrl >> 16) & 0xf);
 
 		if (reg_ctrl & FLEXCAN_MB_CNT_BRS)
 			cfd->flags |= CANFD_BRS;
diff --git a/drivers/net/can/peak_canfd/peak_canfd.c b/drivers/net/can/peak_canfd/peak_canfd.c
index 9ea2adea3f0f..c6077e07214e 100644
--- a/drivers/net/can/peak_canfd/peak_canfd.c
+++ b/drivers/net/can/peak_canfd/peak_canfd.c
@@ -257,7 +257,7 @@ static int pucan_handle_can_rx(struct peak_canfd_priv *priv,
 	u8 cf_len;
 
 	if (rx_msg_flags & PUCAN_MSG_EXT_DATA_LEN)
-		cf_len = can_dlc2len(get_canfd_dlc(pucan_msg_get_dlc(msg)));
+		cf_len = can_dlc2len(pucan_msg_get_dlc(msg));
 	else
 		cf_len = can_cc_dlc2len(pucan_msg_get_dlc(msg));
 
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
index c0a08400f444..3bac7274ee5b 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
@@ -1405,7 +1405,7 @@ mcp251xfd_hw_rx_obj_to_skb(const struct mcp251xfd_priv *priv,
 			cfd->flags |= CANFD_BRS;
 
 		dlc = FIELD_GET(MCP251XFD_OBJ_FLAGS_DLC, hw_rx_obj->flags);
-		cfd->len = can_dlc2len(get_canfd_dlc(dlc));
+		cfd->len = can_dlc2len(dlc);
 	} else {
 		if (hw_rx_obj->flags & MCP251XFD_OBJ_FLAGS_RTR)
 			cfd->can_id |= CAN_RTR_FLAG;
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
index 493a614bf333..843e2e1392e8 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
@@ -1251,7 +1251,7 @@ static void kvaser_usb_hydra_rx_msg_ext(const struct kvaser_usb *dev,
 		kvaser_usb_can_rx_over_error(priv->netdev);
 
 	if (flags & KVASER_USB_HYDRA_CF_FLAG_FDF) {
-		cf->len = can_dlc2len(get_canfd_dlc(dlc));
+		cf->len = can_dlc2len(dlc);
 		if (flags & KVASER_USB_HYDRA_CF_FLAG_BRS)
 			cf->flags |= CANFD_BRS;
 		if (flags & KVASER_USB_HYDRA_CF_FLAG_ESI)
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
index 1f08dd22b3d5..1233ef20646a 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
@@ -492,7 +492,7 @@ static int pcan_usb_fd_decode_canmsg(struct pcan_usb_fd_if *usb_if,
 		if (rx_msg_flags & PUCAN_MSG_ERROR_STATE_IND)
 			cfd->flags |= CANFD_ESI;
 
-		cfd->len = can_dlc2len(get_canfd_dlc(pucan_msg_get_dlc(rm)));
+		cfd->len = can_dlc2len(pucan_msg_get_dlc(rm));
 	} else {
 		/* CAN 2.0 frame case */
 		skb = alloc_can_skb(netdev, (struct can_frame **)&cfd);
diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h
index 9bc84c6978ec..802606e36b58 100644
--- a/include/linux/can/dev.h
+++ b/include/linux/can/dev.h
@@ -105,7 +105,6 @@ static inline unsigned int can_bit_time(const struct can_bittiming *bt)
  * ISO 11898-1 Chapter 8.4.2.3 (DLC field)
  */
 #define can_cc_dlc2len(dlc)	(min_t(u8, (dlc), CAN_MAX_DLEN))
-#define get_canfd_dlc(dlc)	(min_t(u8, (dlc), CANFD_MAX_DLC))
 
 /* Check for outgoing skbs that have not been created by the CAN subsystem */
 static inline bool can_skb_headroom_valid(struct net_device *dev,
diff --git a/include/linux/can/dev/peak_canfd.h b/include/linux/can/dev/peak_canfd.h
index 5fd627e9da19..f38772fd0c07 100644
--- a/include/linux/can/dev/peak_canfd.h
+++ b/include/linux/can/dev/peak_canfd.h
@@ -282,7 +282,7 @@ static inline int pucan_msg_get_channel(const struct pucan_rx_msg *msg)
 }
 
 /* return the dlc value from any received message channel_dlc field */
-static inline int pucan_msg_get_dlc(const struct pucan_rx_msg *msg)
+static inline u8 pucan_msg_get_dlc(const struct pucan_rx_msg *msg)
 {
 	return msg->channel_dlc >> 4;
 }
-- 
cgit v1.2.3


From 964db79d6c186cc2ecc6ae46f98eed7e0ea8cf71 Mon Sep 17 00:00:00 2001
From: Nicolas Saenz Julienne <nsaenzjulienne@suse.de>
Date: Thu, 19 Nov 2020 18:53:55 +0100
Subject: of/address: Introduce of_dma_get_max_cpu_address()

Introduce of_dma_get_max_cpu_address(), which provides the highest CPU
physical address addressable by all DMA masters in the system. It's
specially useful for setting memory zones sizes at early boot time.

Signed-off-by: Nicolas Saenz Julienne <nsaenzjulienne@suse.de>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20201119175400.9995-4-nsaenzjulienne@suse.de
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 drivers/of/address.c | 42 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/of.h   |  7 +++++++
 2 files changed, 49 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/of/address.c b/drivers/of/address.c
index eb9ab4f1e80b..09c0af7fd1c4 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -1024,6 +1024,48 @@ out:
 }
 #endif /* CONFIG_HAS_DMA */
 
+/**
+ * of_dma_get_max_cpu_address - Gets highest CPU address suitable for DMA
+ * @np: The node to start searching from or NULL to start from the root
+ *
+ * Gets the highest CPU physical address that is addressable by all DMA masters
+ * in the sub-tree pointed by np, or the whole tree if NULL is passed. If no
+ * DMA constrained device is found, it returns PHYS_ADDR_MAX.
+ */
+phys_addr_t __init of_dma_get_max_cpu_address(struct device_node *np)
+{
+	phys_addr_t max_cpu_addr = PHYS_ADDR_MAX;
+	struct of_range_parser parser;
+	phys_addr_t subtree_max_addr;
+	struct device_node *child;
+	struct of_range range;
+	const __be32 *ranges;
+	u64 cpu_end = 0;
+	int len;
+
+	if (!np)
+		np = of_root;
+
+	ranges = of_get_property(np, "dma-ranges", &len);
+	if (ranges && len) {
+		of_dma_range_parser_init(&parser, np);
+		for_each_of_range(&parser, &range)
+			if (range.cpu_addr + range.size > cpu_end)
+				cpu_end = range.cpu_addr + range.size - 1;
+
+		if (max_cpu_addr > cpu_end)
+			max_cpu_addr = cpu_end;
+	}
+
+	for_each_available_child_of_node(np, child) {
+		subtree_max_addr = of_dma_get_max_cpu_address(child);
+		if (max_cpu_addr > subtree_max_addr)
+			max_cpu_addr = subtree_max_addr;
+	}
+
+	return max_cpu_addr;
+}
+
 /**
  * of_dma_is_coherent - Check if device is coherent
  * @np:	device node
diff --git a/include/linux/of.h b/include/linux/of.h
index 5d51891cbf1a..9ed5b8532c30 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -558,6 +558,8 @@ int of_map_id(struct device_node *np, u32 id,
 	       const char *map_name, const char *map_mask_name,
 	       struct device_node **target, u32 *id_out);
 
+phys_addr_t of_dma_get_max_cpu_address(struct device_node *np);
+
 #else /* CONFIG_OF */
 
 static inline void of_core_init(void)
@@ -995,6 +997,11 @@ static inline int of_map_id(struct device_node *np, u32 id,
 	return -EINVAL;
 }
 
+static inline phys_addr_t of_dma_get_max_cpu_address(struct device_node *np)
+{
+	return PHYS_ADDR_MAX;
+}
+
 #define of_match_ptr(_ptr)	NULL
 #define of_match_node(_matches, _node)	NULL
 #endif /* CONFIG_OF */
-- 
cgit v1.2.3


From 2b8652936f0ca9ca2e6c984ae76c7bfcda1b3f22 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Thu, 19 Nov 2020 18:53:58 +0100
Subject: arm64: mm: Set ZONE_DMA size based on early IORT scan

We recently introduced a 1 GB sized ZONE_DMA to cater for platforms
incorporating masters that can address less than 32 bits of DMA, in
particular the Raspberry Pi 4, which has 4 or 8 GB of DRAM, but has
peripherals that can only address up to 1 GB (and its PCIe host
bridge can only access the bottom 3 GB)

Instructing the DMA layer about these limitations is straight-forward,
even though we had to fix some issues regarding memory limits set in
the IORT for named components, and regarding the handling of ACPI _DMA
methods. However, the DMA layer also needs to be able to allocate
memory that is guaranteed to meet those DMA constraints, for bounce
buffering as well as allocating the backing for consistent mappings.

This is why the 1 GB ZONE_DMA was introduced recently. Unfortunately,
it turns out the having a 1 GB ZONE_DMA as well as a ZONE_DMA32 causes
problems with kdump, and potentially in other places where allocations
cannot cross zone boundaries. Therefore, we should avoid having two
separate DMA zones when possible.

So let's do an early scan of the IORT, and only create the ZONE_DMA
if we encounter any devices that need it. This puts the burden on
the firmware to describe such limitations in the IORT, which may be
redundant (and less precise) if _DMA methods are also being provided.
However, it should be noted that this situation is highly unusual for
arm64 ACPI machines. Also, the DMA subsystem still gives precedence to
the _DMA method if implemented, and so we will not lose the ability to
perform streaming DMA outside the ZONE_DMA if the _DMA method permits
it.

[nsaenz: unified implementation with DT's counterpart]

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Nicolas Saenz Julienne <nsaenzjulienne@suse.de>
Tested-by: Jeremy Linton <jeremy.linton@arm.com>
Acked-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: Hanjun Guo <guohanjun@huawei.com>
Cc: Jeremy Linton <jeremy.linton@arm.com>
Cc: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Cc: Nicolas Saenz Julienne <nsaenzjulienne@suse.de>
Cc: Rob Herring <robh+dt@kernel.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: Hanjun Guo <guohanjun@huawei.com>
Cc: Sudeep Holla <sudeep.holla@arm.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Link: https://lore.kernel.org/r/20201119175400.9995-7-nsaenzjulienne@suse.de
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/mm/init.c      |  5 ++++-
 drivers/acpi/arm64/iort.c | 55 +++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/acpi_iort.h |  4 ++++
 3 files changed, 63 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index b736890ad3d3..5e534d674c9c 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -29,6 +29,7 @@
 #include <linux/kexec.h>
 #include <linux/crash_dump.h>
 #include <linux/hugetlb.h>
+#include <linux/acpi_iort.h>
 
 #include <asm/boot.h>
 #include <asm/fixmap.h>
@@ -193,11 +194,13 @@ static phys_addr_t __init max_zone_phys(unsigned int zone_bits)
 static void __init zone_sizes_init(unsigned long min, unsigned long max)
 {
 	unsigned long max_zone_pfns[MAX_NR_ZONES]  = {0};
+	unsigned int __maybe_unused acpi_zone_dma_bits;
 	unsigned int __maybe_unused dt_zone_dma_bits;
 
 #ifdef CONFIG_ZONE_DMA
+	acpi_zone_dma_bits = fls64(acpi_iort_dma_get_max_cpu_address());
 	dt_zone_dma_bits = fls64(of_dma_get_max_cpu_address(NULL));
-	zone_dma_bits = min(32U, dt_zone_dma_bits);
+	zone_dma_bits = min3(32U, dt_zone_dma_bits, acpi_zone_dma_bits);
 	arm64_dma_phys_limit = max_zone_phys(zone_dma_bits);
 	max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit);
 #endif
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index 9929ff50c0c0..1787406684aa 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -1718,3 +1718,58 @@ void __init acpi_iort_init(void)
 
 	iort_init_platform_devices();
 }
+
+#ifdef CONFIG_ZONE_DMA
+/*
+ * Extract the highest CPU physical address accessible to all DMA masters in
+ * the system. PHYS_ADDR_MAX is returned when no constrained device is found.
+ */
+phys_addr_t __init acpi_iort_dma_get_max_cpu_address(void)
+{
+	phys_addr_t limit = PHYS_ADDR_MAX;
+	struct acpi_iort_node *node, *end;
+	struct acpi_table_iort *iort;
+	acpi_status status;
+	int i;
+
+	if (acpi_disabled)
+		return limit;
+
+	status = acpi_get_table(ACPI_SIG_IORT, 0,
+				(struct acpi_table_header **)&iort);
+	if (ACPI_FAILURE(status))
+		return limit;
+
+	node = ACPI_ADD_PTR(struct acpi_iort_node, iort, iort->node_offset);
+	end = ACPI_ADD_PTR(struct acpi_iort_node, iort, iort->header.length);
+
+	for (i = 0; i < iort->node_count; i++) {
+		if (node >= end)
+			break;
+
+		switch (node->type) {
+			struct acpi_iort_named_component *ncomp;
+			struct acpi_iort_root_complex *rc;
+			phys_addr_t local_limit;
+
+		case ACPI_IORT_NODE_NAMED_COMPONENT:
+			ncomp = (struct acpi_iort_named_component *)node->node_data;
+			local_limit = DMA_BIT_MASK(ncomp->memory_address_limit);
+			limit = min_not_zero(limit, local_limit);
+			break;
+
+		case ACPI_IORT_NODE_PCI_ROOT_COMPLEX:
+			if (node->revision < 1)
+				break;
+
+			rc = (struct acpi_iort_root_complex *)node->node_data;
+			local_limit = DMA_BIT_MASK(rc->memory_address_limit);
+			limit = min_not_zero(limit, local_limit);
+			break;
+		}
+		node = ACPI_ADD_PTR(struct acpi_iort_node, node, node->length);
+	}
+	acpi_put_table(&iort->header);
+	return limit;
+}
+#endif
diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h
index 20a32120bb88..1a12baa58e40 100644
--- a/include/linux/acpi_iort.h
+++ b/include/linux/acpi_iort.h
@@ -38,6 +38,7 @@ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *size);
 const struct iommu_ops *iort_iommu_configure_id(struct device *dev,
 						const u32 *id_in);
 int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head);
+phys_addr_t acpi_iort_dma_get_max_cpu_address(void);
 #else
 static inline void acpi_iort_init(void) { }
 static inline u32 iort_msi_map_id(struct device *dev, u32 id)
@@ -55,6 +56,9 @@ static inline const struct iommu_ops *iort_iommu_configure_id(
 static inline
 int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head)
 { return 0; }
+
+static inline phys_addr_t acpi_iort_dma_get_max_cpu_address(void)
+{ return PHYS_ADDR_MAX; }
 #endif
 
 #endif /* __ACPI_IORT_H__ */
-- 
cgit v1.2.3


From 04435217f96869ac3a8f055ff68c5237a60bcd7e Mon Sep 17 00:00:00 2001
From: Nicolas Saenz Julienne <nsaenzjulienne@suse.de>
Date: Thu, 19 Nov 2020 18:53:59 +0100
Subject: mm: Remove examples from enum zone_type comment

We can't really list every setup in common code. On top of that they are
unlikely to stay true for long as things change in the arch trees
independently of this comment.

Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicolas Saenz Julienne <nsaenzjulienne@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20201119175400.9995-8-nsaenzjulienne@suse.de
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 include/linux/mmzone.h | 20 --------------------
 1 file changed, 20 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index fb3bf696c05e..9d0c454d23cd 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -354,26 +354,6 @@ enum zone_type {
 	 * DMA mask is assumed when ZONE_DMA32 is defined. Some 64-bit
 	 * platforms may need both zones as they support peripherals with
 	 * different DMA addressing limitations.
-	 *
-	 * Some examples:
-	 *
-	 *  - i386 and x86_64 have a fixed 16M ZONE_DMA and ZONE_DMA32 for the
-	 *    rest of the lower 4G.
-	 *
-	 *  - arm only uses ZONE_DMA, the size, up to 4G, may vary depending on
-	 *    the specific device.
-	 *
-	 *  - arm64 has a fixed 1G ZONE_DMA and ZONE_DMA32 for the rest of the
-	 *    lower 4G.
-	 *
-	 *  - powerpc only uses ZONE_DMA, the size, up to 2G, may vary
-	 *    depending on the specific device.
-	 *
-	 *  - s390 uses ZONE_DMA fixed to the lower 2G.
-	 *
-	 *  - ia64 and riscv only use ZONE_DMA32.
-	 *
-	 *  - parisc uses neither.
 	 */
 #ifdef CONFIG_ZONE_DMA
 	ZONE_DMA,
-- 
cgit v1.2.3


From 607a4672b458b12674b96724e2f9bd42a5e928c6 Mon Sep 17 00:00:00 2001
From: Sudeep Holla <sudeep.holla@arm.com>
Date: Fri, 20 Nov 2020 10:55:17 +0000
Subject: firmware: arm_scmi: Add full list of sensor type enumeration

SCMI v2.0 provides a big list of sensor type enumeration from the
sensorUnits enumeration table of Distributed Management Task Force(DMTF)
specification number DSP 0248 (Platform Level Data Model for Platform
Monitoring and Control Specification). It is however not an exact
replica of the sensorUnits enumeration table.

Let us just update the table as per SCMI v2.0 specification.

Link: https://lore.kernel.org/r/20201119174906.43862-3-cristian.marussi@arm.com
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 include/linux/scmi_protocol.h | 81 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 81 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h
index 9cd312a1ff92..13d75956aa91 100644
--- a/include/linux/scmi_protocol.h
+++ b/include/linux/scmi_protocol.h
@@ -163,11 +163,92 @@ struct scmi_sensor_info {
  */
 enum scmi_sensor_class {
 	NONE = 0x0,
+	UNSPEC = 0x1,
 	TEMPERATURE_C = 0x2,
+	TEMPERATURE_F = 0x3,
+	TEMPERATURE_K = 0x4,
 	VOLTAGE = 0x5,
 	CURRENT = 0x6,
 	POWER = 0x7,
 	ENERGY = 0x8,
+	CHARGE = 0x9,
+	VOLTAMPERE = 0xA,
+	NITS = 0xB,
+	LUMENS = 0xC,
+	LUX = 0xD,
+	CANDELAS = 0xE,
+	KPA = 0xF,
+	PSI = 0x10,
+	NEWTON = 0x11,
+	CFM = 0x12,
+	RPM = 0x13,
+	HERTZ = 0x14,
+	SECS = 0x15,
+	MINS = 0x16,
+	HOURS = 0x17,
+	DAYS = 0x18,
+	WEEKS = 0x19,
+	MILS = 0x1A,
+	INCHES = 0x1B,
+	FEET = 0x1C,
+	CUBIC_INCHES = 0x1D,
+	CUBIC_FEET = 0x1E,
+	METERS = 0x1F,
+	CUBIC_CM = 0x20,
+	CUBIC_METERS = 0x21,
+	LITERS = 0x22,
+	FLUID_OUNCES = 0x23,
+	RADIANS = 0x24,
+	STERADIANS = 0x25,
+	REVOLUTIONS = 0x26,
+	CYCLES = 0x27,
+	GRAVITIES = 0x28,
+	OUNCES = 0x29,
+	POUNDS = 0x2A,
+	FOOT_POUNDS = 0x2B,
+	OUNCE_INCHES = 0x2C,
+	GAUSS = 0x2D,
+	GILBERTS = 0x2E,
+	HENRIES = 0x2F,
+	FARADS = 0x30,
+	OHMS = 0x31,
+	SIEMENS = 0x32,
+	MOLES = 0x33,
+	BECQUERELS = 0x34,
+	PPM = 0x35,
+	DECIBELS = 0x36,
+	DBA = 0x37,
+	DBC = 0x38,
+	GRAYS = 0x39,
+	SIEVERTS = 0x3A,
+	COLOR_TEMP_K = 0x3B,
+	BITS = 0x3C,
+	BYTES = 0x3D,
+	WORDS = 0x3E,
+	DWORDS = 0x3F,
+	QWORDS = 0x40,
+	PERCENTAGE = 0x41,
+	PASCALS = 0x42,
+	COUNTS = 0x43,
+	GRAMS = 0x44,
+	NEWTON_METERS = 0x45,
+	HITS = 0x46,
+	MISSES = 0x47,
+	RETRIES = 0x48,
+	OVERRUNS = 0x49,
+	UNDERRUNS = 0x4A,
+	COLLISIONS = 0x4B,
+	PACKETS = 0x4C,
+	MESSAGES = 0x4D,
+	CHARS = 0x4E,
+	ERRORS = 0x4F,
+	CORRECTED_ERRS = 0x50,
+	UNCORRECTABLE_ERRS = 0x51,
+	SQ_MILS = 0x52,
+	SQ_INCHES = 0x53,
+	SQ_FEET = 0x54,
+	SQ_CM = 0x55,
+	SQ_METERS = 0x56,
 };
 
 /**
-- 
cgit v1.2.3


From 1fe00b8b4276ddf335216f884cb719edbea129e1 Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Thu, 19 Nov 2020 17:49:02 +0000
Subject: firmware: arm_scmi: Add SCMI v3.0 sensors descriptors extensions

Add support for new SCMI v3.0 Sensors extensions related to new sensors'
features, like multiple axis and update intervals, while keeping
compatibility with SCMI v2.0 features.

While at that, refactor and simplify all the internal helpers macros and
move struct scmi_sensor_info to use only non-fixed-size typing.

Link: https://lore.kernel.org/r/20201119174906.43862-3-cristian.marussi@arm.com
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_scmi/sensors.c | 390 ++++++++++++++++++++++++++++++++++--
 include/linux/scmi_protocol.h       | 139 ++++++++++++-
 2 files changed, 504 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/arm_scmi/sensors.c b/drivers/firmware/arm_scmi/sensors.c
index 6aaff478d032..a85827f60a02 100644
--- a/drivers/firmware/arm_scmi/sensors.c
+++ b/drivers/firmware/arm_scmi/sensors.c
@@ -7,16 +7,22 @@
 
 #define pr_fmt(fmt) "SCMI Notifications SENSOR - " fmt
 
+#include <linux/bitfield.h>
 #include <linux/scmi_protocol.h>
 
 #include "common.h"
 #include "notify.h"
 
+#define SCMI_MAX_NUM_SENSOR_AXIS	63
+#define	SCMIv2_SENSOR_PROTOCOL		0x10000
+
 enum scmi_sensor_protocol_cmd {
 	SENSOR_DESCRIPTION_GET = 0x3,
 	SENSOR_TRIP_POINT_NOTIFY = 0x4,
 	SENSOR_TRIP_POINT_CONFIG = 0x5,
 	SENSOR_READING_GET = 0x6,
+	SENSOR_AXIS_DESCRIPTION_GET = 0x7,
+	SENSOR_LIST_UPDATE_INTERVALS = 0x8,
 };
 
 struct scmi_msg_resp_sensor_attributes {
@@ -28,23 +34,100 @@ struct scmi_msg_resp_sensor_attributes {
 	__le32 reg_size;
 };
 
+/* v3 attributes_low macros */
+#define SUPPORTS_UPDATE_NOTIFY(x)	FIELD_GET(BIT(30), (x))
+#define SENSOR_TSTAMP_EXP(x)		FIELD_GET(GENMASK(14, 10), (x))
+#define SUPPORTS_TIMESTAMP(x)		FIELD_GET(BIT(9), (x))
+#define SUPPORTS_EXTEND_ATTRS(x)	FIELD_GET(BIT(8), (x))
+
+/* v2 attributes_high macros */
+#define SENSOR_UPDATE_BASE(x)		FIELD_GET(GENMASK(31, 27), (x))
+#define SENSOR_UPDATE_SCALE(x)		FIELD_GET(GENMASK(26, 22), (x))
+
+/* v3 attributes_high macros */
+#define SENSOR_AXIS_NUMBER(x)		FIELD_GET(GENMASK(21, 16), (x))
+#define SUPPORTS_AXIS(x)		FIELD_GET(BIT(8), (x))
+
+/* v3 resolution macros */
+#define SENSOR_RES(x)			FIELD_GET(GENMASK(26, 0), (x))
+#define SENSOR_RES_EXP(x)		FIELD_GET(GENMASK(31, 27), (x))
+
+struct scmi_msg_resp_attrs {
+	__le32 min_range_low;
+	__le32 min_range_high;
+	__le32 max_range_low;
+	__le32 max_range_high;
+};
+
 struct scmi_msg_resp_sensor_description {
 	__le16 num_returned;
 	__le16 num_remaining;
-	struct {
+	struct scmi_sensor_descriptor {
+		__le32 id;
+		__le32 attributes_low;
+/* Common attributes_low macros */
+#define SUPPORTS_ASYNC_READ(x)		FIELD_GET(BIT(31), (x))
+#define NUM_TRIP_POINTS(x)		FIELD_GET(GENMASK(7, 0), (x))
+		__le32 attributes_high;
+/* Common attributes_high macros */
+#define SENSOR_SCALE(x)			FIELD_GET(GENMASK(15, 11), (x))
+#define SENSOR_SCALE_SIGN		BIT(4)
+#define SENSOR_SCALE_EXTEND		GENMASK(31, 5)
+#define SENSOR_TYPE(x)			FIELD_GET(GENMASK(7, 0), (x))
+		u8 name[SCMI_MAX_STR_SIZE];
+		/* only for version > 2.0 */
+		__le32 power;
+		__le32 resolution;
+		struct scmi_msg_resp_attrs scalar_attrs;
+	} desc[];
+};
+
+/* Base scmi_sensor_descriptor size excluding extended attrs after name */
+#define SCMI_MSG_RESP_SENS_DESCR_BASE_SZ	28
+
+/* Sign extend to a full s32 */
+#define	S32_EXT(v)							\
+	({								\
+		int __v = (v);						\
+									\
+		if (__v & SENSOR_SCALE_SIGN)				\
+			__v |= SENSOR_SCALE_EXTEND;			\
+		__v;							\
+	})
+
+struct scmi_msg_sensor_axis_description_get {
+	__le32 id;
+	__le32 axis_desc_index;
+};
+
+struct scmi_msg_resp_sensor_axis_description {
+	__le32 num_axis_flags;
+#define NUM_AXIS_RETURNED(x)		FIELD_GET(GENMASK(5, 0), (x))
+#define NUM_AXIS_REMAINING(x)		FIELD_GET(GENMASK(31, 26), (x))
+	struct scmi_axis_descriptor {
 		__le32 id;
 		__le32 attributes_low;
-#define SUPPORTS_ASYNC_READ(x)	((x) & BIT(31))
-#define NUM_TRIP_POINTS(x)	((x) & 0xff)
 		__le32 attributes_high;
-#define SENSOR_TYPE(x)		((x) & 0xff)
-#define SENSOR_SCALE(x)		(((x) >> 11) & 0x1f)
-#define SENSOR_SCALE_SIGN	BIT(4)
-#define SENSOR_SCALE_EXTEND	GENMASK(7, 5)
-#define SENSOR_UPDATE_SCALE(x)	(((x) >> 22) & 0x1f)
-#define SENSOR_UPDATE_BASE(x)	(((x) >> 27) & 0x1f)
-		    u8 name[SCMI_MAX_STR_SIZE];
-	} desc[0];
+		u8 name[SCMI_MAX_STR_SIZE];
+		__le32 resolution;
+		struct scmi_msg_resp_attrs attrs;
+	} desc[];
+};
+
+/* Base scmi_axis_descriptor size excluding extended attrs after name */
+#define SCMI_MSG_RESP_AXIS_DESCR_BASE_SZ	28
+
+struct scmi_msg_sensor_list_update_intervals {
+	__le32 id;
+	__le32 index;
+};
+
+struct scmi_msg_resp_sensor_list_update_intervals {
+	__le32 num_intervals_flags;
+#define NUM_INTERVALS_RETURNED(x)	FIELD_GET(GENMASK(11, 0), (x))
+#define SEGMENTED_INTVL_FORMAT(x)	FIELD_GET(BIT(12), (x))
+#define NUM_INTERVALS_REMAINING(x)	FIELD_GET(GENMASK(31, 16), (x))
+	__le32 intervals[];
 };
 
 struct scmi_msg_sensor_trip_point_notify {
@@ -114,6 +197,194 @@ static int scmi_sensor_attributes_get(const struct scmi_handle *handle,
 	return ret;
 }
 
+static inline void scmi_parse_range_attrs(struct scmi_range_attrs *out,
+					  struct scmi_msg_resp_attrs *in)
+{
+	out->min_range = get_unaligned_le64((void *)&in->min_range_low);
+	out->max_range = get_unaligned_le64((void *)&in->max_range_low);
+}
+
+static int scmi_sensor_update_intervals(const struct scmi_handle *handle,
+					struct scmi_sensor_info *s)
+{
+	int ret, cnt;
+	u32 desc_index = 0;
+	u16 num_returned, num_remaining;
+	struct scmi_xfer *ti;
+	struct scmi_msg_resp_sensor_list_update_intervals *buf;
+	struct scmi_msg_sensor_list_update_intervals *msg;
+
+	ret = scmi_xfer_get_init(handle, SENSOR_LIST_UPDATE_INTERVALS,
+				 SCMI_PROTOCOL_SENSOR, sizeof(*msg), 0, &ti);
+	if (ret)
+		return ret;
+
+	buf = ti->rx.buf;
+	do {
+		u32 flags;
+
+		msg = ti->tx.buf;
+		/* Set the number of sensors to be skipped/already read */
+		msg->id = cpu_to_le32(s->id);
+		msg->index = cpu_to_le32(desc_index);
+
+		ret = scmi_do_xfer(handle, ti);
+		if (ret)
+			break;
+
+		flags = le32_to_cpu(buf->num_intervals_flags);
+		num_returned = NUM_INTERVALS_RETURNED(flags);
+		num_remaining = NUM_INTERVALS_REMAINING(flags);
+
+		/*
+		 * Max intervals is not declared previously anywhere so we
+		 * assume it's returned+remaining.
+		 */
+		if (!s->intervals.count) {
+			s->intervals.segmented = SEGMENTED_INTVL_FORMAT(flags);
+			s->intervals.count = num_returned + num_remaining;
+			/* segmented intervals are reported in one triplet */
+			if (s->intervals.segmented &&
+			    (num_remaining || num_returned != 3)) {
+				dev_err(handle->dev,
+					"Sensor ID:%d advertises an invalid segmented interval (%d)\n",
+					s->id, s->intervals.count);
+				s->intervals.segmented = false;
+				s->intervals.count = 0;
+				ret = -EINVAL;
+				break;
+			}
+			/* Direct allocation when exceeding pre-allocated */
+			if (s->intervals.count >= SCMI_MAX_PREALLOC_POOL) {
+				s->intervals.desc =
+					devm_kcalloc(handle->dev,
+						     s->intervals.count,
+						     sizeof(*s->intervals.desc),
+						     GFP_KERNEL);
+				if (!s->intervals.desc) {
+					s->intervals.segmented = false;
+					s->intervals.count = 0;
+					ret = -ENOMEM;
+					break;
+				}
+			}
+		} else if (desc_index + num_returned > s->intervals.count) {
+			dev_err(handle->dev,
+				"No. of update intervals can't exceed %d\n",
+				s->intervals.count);
+			ret = -EINVAL;
+			break;
+		}
+
+		for (cnt = 0; cnt < num_returned; cnt++)
+			s->intervals.desc[desc_index + cnt] =
+					le32_to_cpu(buf->intervals[cnt]);
+
+		desc_index += num_returned;
+
+		scmi_reset_rx_to_maxsz(handle, ti);
+		/*
+		 * check for both returned and remaining to avoid infinite
+		 * loop due to buggy firmware
+		 */
+	} while (num_returned && num_remaining);
+
+	scmi_xfer_put(handle, ti);
+	return ret;
+}
+
+static int scmi_sensor_axis_description(const struct scmi_handle *handle,
+					struct scmi_sensor_info *s)
+{
+	int ret, cnt;
+	u32 desc_index = 0;
+	u16 num_returned, num_remaining;
+	struct scmi_xfer *te;
+	struct scmi_msg_resp_sensor_axis_description *buf;
+	struct scmi_msg_sensor_axis_description_get *msg;
+
+	s->axis = devm_kcalloc(handle->dev, s->num_axis,
+			       sizeof(*s->axis), GFP_KERNEL);
+	if (!s->axis)
+		return -ENOMEM;
+
+	ret = scmi_xfer_get_init(handle, SENSOR_AXIS_DESCRIPTION_GET,
+				 SCMI_PROTOCOL_SENSOR, sizeof(*msg), 0, &te);
+	if (ret)
+		return ret;
+
+	buf = te->rx.buf;
+	do {
+		u32 flags;
+		struct scmi_axis_descriptor *adesc;
+
+		msg = te->tx.buf;
+		/* Set the number of sensors to be skipped/already read */
+		msg->id = cpu_to_le32(s->id);
+		msg->axis_desc_index = cpu_to_le32(desc_index);
+
+		ret = scmi_do_xfer(handle, te);
+		if (ret)
+			break;
+
+		flags = le32_to_cpu(buf->num_axis_flags);
+		num_returned = NUM_AXIS_RETURNED(flags);
+		num_remaining = NUM_AXIS_REMAINING(flags);
+
+		if (desc_index + num_returned > s->num_axis) {
+			dev_err(handle->dev, "No. of axis can't exceed %d\n",
+				s->num_axis);
+			break;
+		}
+
+		adesc = &buf->desc[0];
+		for (cnt = 0; cnt < num_returned; cnt++) {
+			u32 attrh, attrl;
+			struct scmi_sensor_axis_info *a;
+			size_t dsize = SCMI_MSG_RESP_AXIS_DESCR_BASE_SZ;
+
+			attrl = le32_to_cpu(adesc->attributes_low);
+
+			a = &s->axis[desc_index + cnt];
+
+			a->id = le32_to_cpu(adesc->id);
+			a->extended_attrs = SUPPORTS_EXTEND_ATTRS(attrl);
+
+			attrh = le32_to_cpu(adesc->attributes_high);
+			a->scale = S32_EXT(SENSOR_SCALE(attrh));
+			a->type = SENSOR_TYPE(attrh);
+			strlcpy(a->name, adesc->name, SCMI_MAX_STR_SIZE);
+
+			if (a->extended_attrs) {
+				unsigned int ares =
+					le32_to_cpu(adesc->resolution);
+
+				a->resolution = SENSOR_RES(ares);
+				a->exponent =
+					S32_EXT(SENSOR_RES_EXP(ares));
+				dsize += sizeof(adesc->resolution);
+
+				scmi_parse_range_attrs(&a->attrs,
+						       &adesc->attrs);
+				dsize += sizeof(adesc->attrs);
+			}
+
+			adesc = (typeof(adesc))((u8 *)adesc + dsize);
+		}
+
+		desc_index += num_returned;
+
+		scmi_reset_rx_to_maxsz(handle, te);
+		/*
+		 * check for both returned and remaining to avoid infinite
+		 * loop due to buggy firmware
+		 */
+	} while (num_returned && num_remaining);
+
+	scmi_xfer_put(handle, te);
+	return ret;
+}
+
 static int scmi_sensor_description_get(const struct scmi_handle *handle,
 				       struct sensors_info *si)
 {
@@ -131,9 +402,10 @@ static int scmi_sensor_description_get(const struct scmi_handle *handle,
 	buf = t->rx.buf;
 
 	do {
+		struct scmi_sensor_descriptor *sdesc;
+
 		/* Set the number of sensors to be skipped/already read */
 		put_unaligned_le32(desc_index, t->tx.buf);
-
 		ret = scmi_do_xfer(handle, t);
 		if (ret)
 			break;
@@ -147,22 +419,97 @@ static int scmi_sensor_description_get(const struct scmi_handle *handle,
 			break;
 		}
 
+		sdesc = &buf->desc[0];
 		for (cnt = 0; cnt < num_returned; cnt++) {
 			u32 attrh, attrl;
 			struct scmi_sensor_info *s;
+			size_t dsize = SCMI_MSG_RESP_SENS_DESCR_BASE_SZ;
 
-			attrl = le32_to_cpu(buf->desc[cnt].attributes_low);
-			attrh = le32_to_cpu(buf->desc[cnt].attributes_high);
 			s = &si->sensors[desc_index + cnt];
-			s->id = le32_to_cpu(buf->desc[cnt].id);
-			s->type = SENSOR_TYPE(attrh);
-			s->scale = SENSOR_SCALE(attrh);
-			/* Sign extend to a full s8 */
-			if (s->scale & SENSOR_SCALE_SIGN)
-				s->scale |= SENSOR_SCALE_EXTEND;
+			s->id = le32_to_cpu(sdesc->id);
+
+			attrl = le32_to_cpu(sdesc->attributes_low);
+			/* common bitfields parsing */
 			s->async = SUPPORTS_ASYNC_READ(attrl);
 			s->num_trip_points = NUM_TRIP_POINTS(attrl);
-			strlcpy(s->name, buf->desc[cnt].name, SCMI_MAX_STR_SIZE);
+			/**
+			 * only SCMIv3.0 specific bitfield below.
+			 * Such bitfields are assumed to be zeroed on non
+			 * relevant fw versions...assuming fw not buggy !
+			 */
+			s->update = SUPPORTS_UPDATE_NOTIFY(attrl);
+			s->timestamped = SUPPORTS_TIMESTAMP(attrl);
+			if (s->timestamped)
+				s->tstamp_scale =
+					S32_EXT(SENSOR_TSTAMP_EXP(attrl));
+			s->extended_scalar_attrs =
+				SUPPORTS_EXTEND_ATTRS(attrl);
+
+			attrh = le32_to_cpu(sdesc->attributes_high);
+			/* common bitfields parsing */
+			s->scale = S32_EXT(SENSOR_SCALE(attrh));
+			s->type = SENSOR_TYPE(attrh);
+			/* Use pre-allocated pool wherever possible */
+			s->intervals.desc = s->intervals.prealloc_pool;
+			if (si->version == SCMIv2_SENSOR_PROTOCOL) {
+				s->intervals.segmented = false;
+				s->intervals.count = 1;
+				/*
+				 * Convert SCMIv2.0 update interval format to
+				 * SCMIv3.0 to be used as the common exposed
+				 * descriptor, accessible via common macros.
+				 */
+				s->intervals.desc[0] =
+					(SENSOR_UPDATE_BASE(attrh) << 5) |
+					 SENSOR_UPDATE_SCALE(attrh);
+			} else {
+				/*
+				 * From SCMIv3.0 update intervals are retrieved
+				 * via a dedicated (optional) command.
+				 * Since the command is optional, on error carry
+				 * on without any update interval.
+				 */
+				if (scmi_sensor_update_intervals(handle, s))
+					dev_dbg(handle->dev,
+						"Update Intervals not available for sensor ID:%d\n",
+						s->id);
+			}
+			/**
+			 * only > SCMIv2.0 specific bitfield below.
+			 * Such bitfields are assumed to be zeroed on non
+			 * relevant fw versions...assuming fw not buggy !
+			 */
+			s->num_axis = min_t(unsigned int,
+					    SUPPORTS_AXIS(attrh) ?
+					    SENSOR_AXIS_NUMBER(attrh) : 0,
+					    SCMI_MAX_NUM_SENSOR_AXIS);
+			strlcpy(s->name, sdesc->name, SCMI_MAX_STR_SIZE);
+
+			if (s->extended_scalar_attrs) {
+				s->sensor_power = le32_to_cpu(sdesc->power);
+				dsize += sizeof(sdesc->power);
+				/* Only for sensors reporting scalar values */
+				if (s->num_axis == 0) {
+					unsigned int sres =
+						le32_to_cpu(sdesc->resolution);
+
+					s->resolution = SENSOR_RES(sres);
+					s->exponent =
+						S32_EXT(SENSOR_RES_EXP(sres));
+					dsize += sizeof(sdesc->resolution);
+
+					scmi_parse_range_attrs(&s->scalar_attrs,
+							       &sdesc->scalar_attrs);
+					dsize += sizeof(sdesc->scalar_attrs);
+				}
+			}
+			if (s->num_axis > 0) {
+				ret = scmi_sensor_axis_description(handle, s);
+				if (ret)
+					goto out;
+			}
+
+			sdesc = (typeof(sdesc))((u8 *)sdesc + dsize);
 		}
 
 		desc_index += num_returned;
@@ -174,6 +521,7 @@ static int scmi_sensor_description_get(const struct scmi_handle *handle,
 		 */
 	} while (num_returned && num_remaining);
 
+out:
 	scmi_xfer_put(handle, t);
 	return ret;
 }
diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h
index 13d75956aa91..0792b0be25a3 100644
--- a/include/linux/scmi_protocol.h
+++ b/include/linux/scmi_protocol.h
@@ -8,6 +8,7 @@
 #ifndef _LINUX_SCMI_PROTOCOL_H
 #define _LINUX_SCMI_PROTOCOL_H
 
+#include <linux/bitfield.h>
 #include <linux/device.h>
 #include <linux/notifier.h>
 #include <linux/types.h>
@@ -148,13 +149,135 @@ struct scmi_power_ops {
 			 u32 *state);
 };
 
+/**
+ * scmi_range_attrs  - specifies a sensor or axis values' range
+ * @min_range: The minimum value which can be represented by the sensor/axis.
+ * @max_range: The maximum value which can be represented by the sensor/axis.
+ */
+struct scmi_range_attrs {
+	long long min_range;
+	long long max_range;
+};
+
+/**
+ * scmi_sensor_axis_info  - describes one sensor axes
+ * @id: The axes ID.
+ * @type: Axes type. Chosen amongst one of @enum scmi_sensor_class.
+ * @scale: Power-of-10 multiplier applied to the axis unit.
+ * @name: NULL-terminated string representing axes name as advertised by
+ *	  SCMI platform.
+ * @extended_attrs: Flag to indicate the presence of additional extended
+ *		    attributes for this axes.
+ * @resolution: Extended attribute representing the resolution of the axes.
+ *		Set to 0 if not reported by this axes.
+ * @exponent: Extended attribute representing the power-of-10 multiplier that
+ *	      is applied to the resolution field. Set to 0 if not reported by
+ *	      this axes.
+ * @attrs: Extended attributes representing minimum and maximum values
+ *	   measurable by this axes. Set to 0 if not reported by this sensor.
+ */
+struct scmi_sensor_axis_info {
+	unsigned int id;
+	unsigned int type;
+	int scale;
+	char name[SCMI_MAX_STR_SIZE];
+	bool extended_attrs;
+	unsigned int resolution;
+	int exponent;
+	struct scmi_range_attrs attrs;
+};
+
+/**
+ * scmi_sensor_intervals_info  - describes number and type of available update
+ * intervals
+ * @segmented: Flag for segmented intervals' representation. When True there
+ *	       will be exactly 3 intervals in @desc, with each entry
+ *	       representing a member of a segment in this order:
+ *	       {lowest update interval, highest update interval, step size}
+ * @count: Number of intervals described in @desc.
+ * @desc: Array of @count interval descriptor bitmask represented as detailed in
+ *	  the SCMI specification: it can be accessed using the accompanying
+ *	  macros.
+ * @prealloc_pool: A minimal preallocated pool of desc entries used to avoid
+ *		   lesser-than-64-bytes dynamic allocation for small @count
+ *		   values.
+ */
+struct scmi_sensor_intervals_info {
+	bool segmented;
+	unsigned int count;
+#define SCMI_SENS_INTVL_SEGMENT_LOW	0
+#define SCMI_SENS_INTVL_SEGMENT_HIGH	1
+#define SCMI_SENS_INTVL_SEGMENT_STEP	2
+	unsigned int *desc;
+#define SCMI_SENS_INTVL_GET_SECS(x)		FIELD_GET(GENMASK(20, 5), (x))
+#define SCMI_SENS_INTVL_GET_EXP(x)					\
+	({								\
+		int __signed_exp = FIELD_GET(GENMASK(4, 0), (x));	\
+									\
+		if (__signed_exp & BIT(4))				\
+			__signed_exp |= GENMASK(31, 5);			\
+		__signed_exp;						\
+	})
+#define SCMI_MAX_PREALLOC_POOL			16
+	unsigned int prealloc_pool[SCMI_MAX_PREALLOC_POOL];
+};
+
+/**
+ * struct scmi_sensor_info - represents information related to one of the
+ * available sensors.
+ * @id: Sensor ID.
+ * @type: Sensor type. Chosen amongst one of @enum scmi_sensor_class.
+ * @scale: Power-of-10 multiplier applied to the sensor unit.
+ * @num_trip_points: Number of maximum configurable trip points.
+ * @async: Flag for asynchronous read support.
+ * @update: Flag for continuouos update notification support.
+ * @timestamped: Flag for timestamped read support.
+ * @tstamp_scale: Power-of-10 multiplier applied to the sensor timestamps to
+ *		  represent it in seconds.
+ * @num_axis: Number of supported axis if any. Reported as 0 for scalar sensors.
+ * @axis: Pointer to an array of @num_axis descriptors.
+ * @intervals: Descriptor of available update intervals.
+ * @sensor_config: A bitmask reporting the current sensor configuration as
+ *		   detailed in the SCMI specification: it can accessed and
+ *		   modified through the accompanying macros.
+ * @name: NULL-terminated string representing sensor name as advertised by
+ *	  SCMI platform.
+ * @extended_scalar_attrs: Flag to indicate the presence of additional extended
+ *			   attributes for this sensor.
+ * @sensor_power: Extended attribute representing the average power
+ *		  consumed by the sensor in microwatts (uW) when it is active.
+ *		  Reported here only for scalar sensors.
+ *		  Set to 0 if not reported by this sensor.
+ * @resolution: Extended attribute representing the resolution of the sensor.
+ *		Reported here only for scalar sensors.
+ *		Set to 0 if not reported by this sensor.
+ * @exponent: Extended attribute representing the power-of-10 multiplier that is
+ *	      applied to the resolution field.
+ *	      Reported here only for scalar sensors.
+ *	      Set to 0 if not reported by this sensor.
+ * @scalar_attrs: Extended attributes representing minimum and maximum
+ *		  measurable values by this sensor.
+ *		  Reported here only for scalar sensors.
+ *		  Set to 0 if not reported by this sensor.
+ */
 struct scmi_sensor_info {
-	u32 id;
-	u8 type;
-	s8 scale;
-	u8 num_trip_points;
+	unsigned int id;
+	unsigned int type;
+	int scale;
+	unsigned int num_trip_points;
 	bool async;
+	bool update;
+	bool timestamped;
+	int tstamp_scale;
+	unsigned int num_axis;
+	struct scmi_sensor_axis_info *axis;
+	struct scmi_sensor_intervals_info intervals;
 	char name[SCMI_MAX_STR_SIZE];
+	bool extended_scalar_attrs;
+	unsigned int sensor_power;
+	unsigned int resolution;
+	int exponent;
+	struct scmi_range_attrs scalar_attrs;
 };
 
 /*
@@ -249,6 +372,14 @@ enum scmi_sensor_class {
 	SQ_FEET = 0x54,
 	SQ_CM = 0x55,
 	SQ_METERS = 0x56,
+	RADIANS_SEC = 0x57,
+	BPM = 0x58,
+	METERS_SEC_SQUARED = 0x59,
+	METERS_SEC = 0x5A,
+	CUBIC_METERS_SEC = 0x5B,
+	MM_MERCURY = 0x5C,
+	RADIANS_SEC_SQUARED = 0x5D,
+	OEM_UNIT = 0xFF
 };
 
 /**
-- 
cgit v1.2.3


From c7b74967799b1af52b3045d69d4c26836b2d41de Mon Sep 17 00:00:00 2001
From: Oliver Hartkopp <socketcan@hartkopp.net>
Date: Fri, 20 Nov 2020 11:04:44 +0100
Subject: can: replace can_dlc as variable/element for payload length

The naming of can_dlc as element of struct can_frame and also as variable
name is misleading as it claims to be a 'data length CODE' but in reality
it always was a plain data length.

With the indroduction of a new 'len' element in struct can_frame we can now
remove can_dlc as name and make clear which of the former uses was a plain
length (-> 'len') or a data length code (-> 'dlc') value.

Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Link: https://lore.kernel.org/r/20201120100444.3199-1-socketcan@hartkopp.net
[mkl: gs_usb: keep struct gs_host_frame::can_dlc as is]
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/at91_can.c                        | 14 +++++-----
 drivers/net/can/c_can/c_can.c                     | 20 +++++++-------
 drivers/net/can/cc770/cc770.c                     | 14 +++++-----
 drivers/net/can/dev.c                             | 10 +++----
 drivers/net/can/grcan.c                           | 10 +++----
 drivers/net/can/ifi_canfd/ifi_canfd.c             |  4 +--
 drivers/net/can/janz-ican3.c                      | 20 +++++++-------
 drivers/net/can/kvaser_pciefd.c                   |  4 +--
 drivers/net/can/m_can/m_can.c                     |  4 +--
 drivers/net/can/mscan/mscan.c                     | 20 +++++++-------
 drivers/net/can/pch_can.c                         | 12 ++++-----
 drivers/net/can/peak_canfd/peak_canfd.c           | 12 ++++-----
 drivers/net/can/rcar/rcar_can.c                   | 14 +++++-----
 drivers/net/can/rcar/rcar_canfd.c                 |  4 +--
 drivers/net/can/rx-offload.c                      |  2 +-
 drivers/net/can/sja1000/sja1000.c                 | 10 +++----
 drivers/net/can/slcan.c                           | 32 +++++++++++------------
 drivers/net/can/softing/softing_fw.c              |  2 +-
 drivers/net/can/softing/softing_main.c            | 14 +++++-----
 drivers/net/can/spi/hi311x.c                      | 20 +++++++-------
 drivers/net/can/spi/mcp251x.c                     | 18 ++++++-------
 drivers/net/can/sun4i_can.c                       | 10 +++----
 drivers/net/can/ti_hecc.c                         |  8 +++---
 drivers/net/can/usb/ems_usb.c                     | 16 ++++++------
 drivers/net/can/usb/esd_usb2.c                    | 16 ++++++------
 drivers/net/can/usb/gs_usb.c                      |  8 +++---
 drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c  |  2 +-
 drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c | 16 ++++++------
 drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c  | 22 ++++++++--------
 drivers/net/can/usb/mcba_usb.c                    | 10 +++----
 drivers/net/can/usb/peak_usb/pcan_usb.c           | 14 +++++-----
 drivers/net/can/usb/peak_usb/pcan_usb_fd.c        | 10 +++----
 drivers/net/can/usb/peak_usb/pcan_usb_pro.c       | 14 +++++-----
 drivers/net/can/usb/ucan.c                        | 14 +++++-----
 drivers/net/can/usb/usb_8dev.c                    | 14 +++++-----
 drivers/net/can/xilinx_can.c                      | 10 +++----
 include/linux/can/dev.h                           |  4 +--
 net/can/af_can.c                                  |  2 +-
 net/can/gw.c                                      |  2 +-
 net/can/j1939/main.c                              |  4 +--
 40 files changed, 228 insertions(+), 228 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c
index db06254f8eb7..5284f0ab3b06 100644
--- a/drivers/net/can/at91_can.c
+++ b/drivers/net/can/at91_can.c
@@ -468,7 +468,7 @@ static netdev_tx_t at91_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 	reg_mid = at91_can_id_to_reg_mid(cf->can_id);
 	reg_mcr = ((cf->can_id & CAN_RTR_FLAG) ? AT91_MCR_MRTR : 0) |
-		(cf->can_dlc << 16) | AT91_MCR_MTCR;
+		(cf->len << 16) | AT91_MCR_MTCR;
 
 	/* disable MB while writing ID (see datasheet) */
 	set_mb_mode(priv, mb, AT91_MB_MODE_DISABLED);
@@ -481,7 +481,7 @@ static netdev_tx_t at91_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* This triggers transmission */
 	at91_write(priv, AT91_MCR(mb), reg_mcr);
 
-	stats->tx_bytes += cf->can_dlc;
+	stats->tx_bytes += cf->len;
 
 	/* _NOTE_: subtract AT91_MB_TX_FIRST offset from mb! */
 	can_put_echo_skb(skb, dev, mb - get_mb_tx_first(priv));
@@ -554,7 +554,7 @@ static void at91_rx_overflow_err(struct net_device *dev)
 	cf->data[1] = CAN_ERR_CRTL_RX_OVERFLOW;
 
 	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 	netif_receive_skb(skb);
 }
 
@@ -580,7 +580,7 @@ static void at91_read_mb(struct net_device *dev, unsigned int mb,
 		cf->can_id = (reg_mid >> 18) & CAN_SFF_MASK;
 
 	reg_msr = at91_read(priv, AT91_MSR(mb));
-	cf->can_dlc = can_cc_dlc2len((reg_msr >> 16) & 0xf);
+	cf->len = can_cc_dlc2len((reg_msr >> 16) & 0xf);
 
 	if (reg_msr & AT91_MSR_MRTR)
 		cf->can_id |= CAN_RTR_FLAG;
@@ -619,7 +619,7 @@ static void at91_read_msg(struct net_device *dev, unsigned int mb)
 	at91_read_mb(dev, mb, cf);
 
 	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 	netif_receive_skb(skb);
 
 	can_led_event(dev, CAN_LED_EVENT_RX);
@@ -780,7 +780,7 @@ static int at91_poll_err(struct net_device *dev, int quota, u32 reg_sr)
 	at91_poll_err_frame(dev, cf, reg_sr);
 
 	dev->stats.rx_packets++;
-	dev->stats.rx_bytes += cf->can_dlc;
+	dev->stats.rx_bytes += cf->len;
 	netif_receive_skb(skb);
 
 	return 1;
@@ -1047,7 +1047,7 @@ static void at91_irq_err(struct net_device *dev)
 	at91_irq_err_state(dev, cf, new_state);
 
 	dev->stats.rx_packets++;
-	dev->stats.rx_bytes += cf->can_dlc;
+	dev->stats.rx_bytes += cf->len;
 	netif_rx(skb);
 
 	priv->can.state = new_state;
diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c
index 56cc705959ea..0420f09f2b70 100644
--- a/drivers/net/can/c_can/c_can.c
+++ b/drivers/net/can/c_can/c_can.c
@@ -306,7 +306,7 @@ static void c_can_setup_tx_object(struct net_device *dev, int iface,
 				  struct can_frame *frame, int idx)
 {
 	struct c_can_priv *priv = netdev_priv(dev);
-	u16 ctrl = IF_MCONT_TX | frame->can_dlc;
+	u16 ctrl = IF_MCONT_TX | frame->len;
 	bool rtr = frame->can_id & CAN_RTR_FLAG;
 	u32 arb = IF_ARB_MSGVAL;
 	int i;
@@ -339,7 +339,7 @@ static void c_can_setup_tx_object(struct net_device *dev, int iface,
 	if (priv->type == BOSCH_D_CAN) {
 		u32 data = 0, dreg = C_CAN_IFACE(DATA1_REG, iface);
 
-		for (i = 0; i < frame->can_dlc; i += 4, dreg += 2) {
+		for (i = 0; i < frame->len; i += 4, dreg += 2) {
 			data = (u32)frame->data[i];
 			data |= (u32)frame->data[i + 1] << 8;
 			data |= (u32)frame->data[i + 2] << 16;
@@ -347,7 +347,7 @@ static void c_can_setup_tx_object(struct net_device *dev, int iface,
 			priv->write_reg32(priv, dreg, data);
 		}
 	} else {
-		for (i = 0; i < frame->can_dlc; i += 2) {
+		for (i = 0; i < frame->len; i += 2) {
 			priv->write_reg(priv,
 					C_CAN_IFACE(DATA1_REG, iface) + i / 2,
 					frame->data[i] |
@@ -397,7 +397,7 @@ static int c_can_read_msg_object(struct net_device *dev, int iface, u32 ctrl)
 		return -ENOMEM;
 	}
 
-	frame->can_dlc = can_cc_dlc2len(ctrl & 0x0F);
+	frame->len = can_cc_dlc2len(ctrl & 0x0F);
 
 	arb = priv->read_reg32(priv, C_CAN_IFACE(ARB1_REG, iface));
 
@@ -412,7 +412,7 @@ static int c_can_read_msg_object(struct net_device *dev, int iface, u32 ctrl)
 		int i, dreg = C_CAN_IFACE(DATA1_REG, iface);
 
 		if (priv->type == BOSCH_D_CAN) {
-			for (i = 0; i < frame->can_dlc; i += 4, dreg += 2) {
+			for (i = 0; i < frame->len; i += 4, dreg += 2) {
 				data = priv->read_reg32(priv, dreg);
 				frame->data[i] = data;
 				frame->data[i + 1] = data >> 8;
@@ -420,7 +420,7 @@ static int c_can_read_msg_object(struct net_device *dev, int iface, u32 ctrl)
 				frame->data[i + 3] = data >> 24;
 			}
 		} else {
-			for (i = 0; i < frame->can_dlc; i += 2, dreg++) {
+			for (i = 0; i < frame->len; i += 2, dreg++) {
 				data = priv->read_reg(priv, dreg);
 				frame->data[i] = data;
 				frame->data[i + 1] = data >> 8;
@@ -429,7 +429,7 @@ static int c_can_read_msg_object(struct net_device *dev, int iface, u32 ctrl)
 	}
 
 	stats->rx_packets++;
-	stats->rx_bytes += frame->can_dlc;
+	stats->rx_bytes += frame->len;
 
 	netif_receive_skb(skb);
 	return 0;
@@ -475,7 +475,7 @@ static netdev_tx_t c_can_start_xmit(struct sk_buff *skb,
 	 * transmit as we might race against do_tx().
 	 */
 	c_can_setup_tx_object(dev, IF_TX, frame, idx);
-	priv->dlc[idx] = frame->can_dlc;
+	priv->dlc[idx] = frame->len;
 	can_put_echo_skb(skb, dev, idx);
 
 	/* Update the active bits */
@@ -977,7 +977,7 @@ static int c_can_handle_state_change(struct net_device *dev,
 	}
 
 	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 	netif_receive_skb(skb);
 
 	return 1;
@@ -1047,7 +1047,7 @@ static int c_can_handle_bus_err(struct net_device *dev,
 	}
 
 	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 	netif_receive_skb(skb);
 	return 1;
 }
diff --git a/drivers/net/can/cc770/cc770.c b/drivers/net/can/cc770/cc770.c
index 3fd2a276dd93..8d9f332c35e0 100644
--- a/drivers/net/can/cc770/cc770.c
+++ b/drivers/net/can/cc770/cc770.c
@@ -390,7 +390,7 @@ static void cc770_tx(struct net_device *dev, int mo)
 	u32 id;
 	int i;
 
-	dlc = cf->can_dlc;
+	dlc = cf->len;
 	id = cf->can_id;
 	rtr = cf->can_id & CAN_RTR_FLAG ? 0 : MSGCFG_DIR;
 
@@ -470,7 +470,7 @@ static void cc770_rx(struct net_device *dev, unsigned int mo, u8 ctrl1)
 		cf->can_id = CAN_RTR_FLAG;
 		if (config & MSGCFG_XTD)
 			cf->can_id |= CAN_EFF_FLAG;
-		cf->can_dlc = 0;
+		cf->len = 0;
 	} else {
 		if (config & MSGCFG_XTD) {
 			id = cc770_read_reg(priv, msgobj[mo].id[3]);
@@ -486,13 +486,13 @@ static void cc770_rx(struct net_device *dev, unsigned int mo, u8 ctrl1)
 		}
 
 		cf->can_id = id;
-		cf->can_dlc = can_cc_dlc2len((config & 0xf0) >> 4);
-		for (i = 0; i < cf->can_dlc; i++)
+		cf->len = can_cc_dlc2len((config & 0xf0) >> 4);
+		for (i = 0; i < cf->len; i++)
 			cf->data[i] = cc770_read_reg(priv, msgobj[mo].data[i]);
 	}
 
 	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 	netif_rx(skb);
 }
 
@@ -572,7 +572,7 @@ static int cc770_err(struct net_device *dev, u8 status)
 
 
 	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 	netif_rx(skb);
 
 	return 0;
@@ -699,7 +699,7 @@ static void cc770_tx_interrupt(struct net_device *dev, unsigned int o)
 	}
 
 	cf = (struct can_frame *)priv->tx_skb->data;
-	stats->tx_bytes += cf->can_dlc;
+	stats->tx_bytes += cf->len;
 	stats->tx_packets++;
 
 	can_put_echo_skb(priv->tx_skb, dev, 0);
diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index 81e39d7507d8..806e8b646b12 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -30,10 +30,10 @@ MODULE_AUTHOR("Wolfgang Grandegger <wg@grandegger.com>");
 static const u8 dlc2len[] = {0, 1, 2, 3, 4, 5, 6, 7,
 			     8, 12, 16, 20, 24, 32, 48, 64};
 
-/* get data length from can_dlc with sanitized can_dlc */
-u8 can_dlc2len(u8 can_dlc)
+/* get data length from raw data length code (DLC) */
+u8 can_dlc2len(u8 dlc)
 {
-	return dlc2len[can_dlc & 0x0F];
+	return dlc2len[dlc & 0x0F];
 }
 EXPORT_SYMBOL_GPL(can_dlc2len);
 
@@ -595,7 +595,7 @@ static void can_restart(struct net_device *dev)
 	netif_rx_ni(skb);
 
 	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 
 restart:
 	netdev_dbg(dev, "restarted\n");
@@ -737,7 +737,7 @@ struct sk_buff *alloc_can_err_skb(struct net_device *dev, struct can_frame **cf)
 		return NULL;
 
 	(*cf)->can_id = CAN_ERR_FLAG;
-	(*cf)->can_dlc = CAN_ERR_DLC;
+	(*cf)->len = CAN_ERR_DLC;
 
 	return skb;
 }
diff --git a/drivers/net/can/grcan.c b/drivers/net/can/grcan.c
index c71c9b8683d5..f5d94a692576 100644
--- a/drivers/net/can/grcan.c
+++ b/drivers/net/can/grcan.c
@@ -1201,12 +1201,12 @@ static int grcan_receive(struct net_device *dev, int budget)
 			cf->can_id = ((slot[0] & GRCAN_MSG_BID)
 				      >> GRCAN_MSG_BID_BIT);
 		}
-		cf->can_dlc = can_cc_dlc2len((slot[1] & GRCAN_MSG_DLC)
+		cf->len = can_cc_dlc2len((slot[1] & GRCAN_MSG_DLC)
 					  >> GRCAN_MSG_DLC_BIT);
 		if (rtr) {
 			cf->can_id |= CAN_RTR_FLAG;
 		} else {
-			for (i = 0; i < cf->can_dlc; i++) {
+			for (i = 0; i < cf->len; i++) {
 				j = GRCAN_MSG_DATA_SLOT_INDEX(i);
 				shift = GRCAN_MSG_DATA_SHIFT(i);
 				cf->data[i] = (u8)(slot[j] >> shift);
@@ -1215,7 +1215,7 @@ static int grcan_receive(struct net_device *dev, int budget)
 
 		/* Update statistics and read pointer */
 		stats->rx_packets++;
-		stats->rx_bytes += cf->can_dlc;
+		stats->rx_bytes += cf->len;
 		netif_receive_skb(skb);
 
 		rd = grcan_ring_add(rd, GRCAN_MSG_SIZE, dma->rx.size);
@@ -1399,7 +1399,7 @@ static netdev_tx_t grcan_start_xmit(struct sk_buff *skb,
 	eff = cf->can_id & CAN_EFF_FLAG;
 	rtr = cf->can_id & CAN_RTR_FLAG;
 	id = cf->can_id & (eff ? CAN_EFF_MASK : CAN_SFF_MASK);
-	dlc = cf->can_dlc;
+	dlc = cf->len;
 	if (eff)
 		tmp = (id << GRCAN_MSG_EID_BIT) & GRCAN_MSG_EID;
 	else
@@ -1447,7 +1447,7 @@ static netdev_tx_t grcan_start_xmit(struct sk_buff *skb,
 	 * can_put_echo_skb would be an error unless other measures are
 	 * taken.
 	 */
-	priv->txdlc[slotindex] = cf->can_dlc; /* Store dlc for statistics */
+	priv->txdlc[slotindex] = cf->len; /* Store dlc for statistics */
 	can_put_echo_skb(skb, dev, slotindex);
 
 	/* Make sure everything is written before allowing hardware to
diff --git a/drivers/net/can/ifi_canfd/ifi_canfd.c b/drivers/net/can/ifi_canfd/ifi_canfd.c
index cc790354a8ee..3df55b0e4ef3 100644
--- a/drivers/net/can/ifi_canfd/ifi_canfd.c
+++ b/drivers/net/can/ifi_canfd/ifi_canfd.c
@@ -431,7 +431,7 @@ static int ifi_canfd_handle_lec_err(struct net_device *ndev)
 	writel(IFI_CANFD_ERROR_CTR_ER_ENABLE, priv->base + IFI_CANFD_ERROR_CTR);
 
 	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 	netif_receive_skb(skb);
 
 	return 1;
@@ -523,7 +523,7 @@ static int ifi_canfd_handle_state_change(struct net_device *ndev,
 	}
 
 	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 	netif_receive_skb(skb);
 
 	return 1;
diff --git a/drivers/net/can/janz-ican3.c b/drivers/net/can/janz-ican3.c
index 6a21af05ba27..2a6c918186c0 100644
--- a/drivers/net/can/janz-ican3.c
+++ b/drivers/net/can/janz-ican3.c
@@ -916,10 +916,10 @@ static void ican3_to_can_frame(struct ican3_dev *mod,
 
 		cf->can_id |= desc->data[0] << 3;
 		cf->can_id |= (desc->data[1] & 0xe0) >> 5;
-		cf->can_dlc = can_cc_dlc2len(desc->data[1] & ICAN3_CAN_DLC_MASK);
-		memcpy(cf->data, &desc->data[2], cf->can_dlc);
+		cf->len = can_cc_dlc2len(desc->data[1] & ICAN3_CAN_DLC_MASK);
+		memcpy(cf->data, &desc->data[2], cf->len);
 	} else {
-		cf->can_dlc = can_cc_dlc2len(desc->data[0] & ICAN3_CAN_DLC_MASK);
+		cf->len = can_cc_dlc2len(desc->data[0] & ICAN3_CAN_DLC_MASK);
 		if (desc->data[0] & ICAN3_EFF_RTR)
 			cf->can_id |= CAN_RTR_FLAG;
 
@@ -934,7 +934,7 @@ static void ican3_to_can_frame(struct ican3_dev *mod,
 			cf->can_id |= desc->data[3] >> 5;  /* 2-0   */
 		}
 
-		memcpy(cf->data, &desc->data[6], cf->can_dlc);
+		memcpy(cf->data, &desc->data[6], cf->len);
 	}
 }
 
@@ -947,7 +947,7 @@ static void can_frame_to_ican3(struct ican3_dev *mod,
 
 	/* we always use the extended format, with the ECHO flag set */
 	desc->command = ICAN3_CAN_TYPE_EFF;
-	desc->data[0] |= cf->can_dlc;
+	desc->data[0] |= cf->len;
 	desc->data[1] |= ICAN3_ECHO;
 
 	/* support single transmission (no retries) mode */
@@ -970,7 +970,7 @@ static void can_frame_to_ican3(struct ican3_dev *mod,
 	}
 
 	/* copy the data bits into the descriptor */
-	memcpy(&desc->data[6], cf->data, cf->can_dlc);
+	memcpy(&desc->data[6], cf->data, cf->len);
 }
 
 /*
@@ -1294,7 +1294,7 @@ static unsigned int ican3_get_echo_skb(struct ican3_dev *mod)
 	}
 
 	cf = (struct can_frame *)skb->data;
-	dlc = cf->can_dlc;
+	dlc = cf->len;
 
 	/* check flag whether this packet has to be looped back */
 	if (skb->pkt_type != PACKET_LOOPBACK) {
@@ -1332,10 +1332,10 @@ static bool ican3_echo_skb_matches(struct ican3_dev *mod, struct sk_buff *skb)
 	if (cf->can_id != echo_cf->can_id)
 		return false;
 
-	if (cf->can_dlc != echo_cf->can_dlc)
+	if (cf->len != echo_cf->len)
 		return false;
 
-	return memcmp(cf->data, echo_cf->data, cf->can_dlc) == 0;
+	return memcmp(cf->data, echo_cf->data, cf->len) == 0;
 }
 
 /*
@@ -1421,7 +1421,7 @@ static int ican3_recv_skb(struct ican3_dev *mod)
 
 	/* update statistics, receive the skb */
 	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 	netif_receive_skb(skb);
 
 err_noalloc:
diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c
index 72acd1ba162d..de268a344fcf 100644
--- a/drivers/net/can/kvaser_pciefd.c
+++ b/drivers/net/can/kvaser_pciefd.c
@@ -1299,7 +1299,7 @@ static int kvaser_pciefd_rx_error_frame(struct kvaser_pciefd_can *can,
 	cf->data[7] = bec.rxerr;
 
 	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 
 	netif_rx(skb);
 	return 0;
@@ -1498,7 +1498,7 @@ static void kvaser_pciefd_handle_nack_packet(struct kvaser_pciefd_can *can,
 
 	if (skb) {
 		cf->can_id |= CAN_ERR_BUSERROR;
-		stats->rx_bytes += cf->can_dlc;
+		stats->rx_bytes += cf->len;
 		stats->rx_packets++;
 		netif_rx(skb);
 	} else {
diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index 2e46a5916656..b7df90ceee4b 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -596,7 +596,7 @@ static int m_can_handle_lec_err(struct net_device *dev,
 	}
 
 	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 	netif_receive_skb(skb);
 
 	return 1;
@@ -723,7 +723,7 @@ static int m_can_handle_state_change(struct net_device *dev,
 	}
 
 	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 	netif_receive_skb(skb);
 
 	return 1;
diff --git a/drivers/net/can/mscan/mscan.c b/drivers/net/can/mscan/mscan.c
index 95bf7338b358..5ed00a1558e1 100644
--- a/drivers/net/can/mscan/mscan.c
+++ b/drivers/net/can/mscan/mscan.c
@@ -250,16 +250,16 @@ static netdev_tx_t mscan_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		void __iomem *data = &regs->tx.dsr1_0;
 		u16 *payload = (u16 *)frame->data;
 
-		for (i = 0; i < frame->can_dlc / 2; i++) {
+		for (i = 0; i < frame->len / 2; i++) {
 			out_be16(data, *payload++);
 			data += 2 + _MSCAN_RESERVED_DSR_SIZE;
 		}
 		/* write remaining byte if necessary */
-		if (frame->can_dlc & 1)
-			out_8(data, frame->data[frame->can_dlc - 1]);
+		if (frame->len & 1)
+			out_8(data, frame->data[frame->len - 1]);
 	}
 
-	out_8(&regs->tx.dlr, frame->can_dlc);
+	out_8(&regs->tx.dlr, frame->len);
 	out_8(&regs->tx.tbpr, priv->cur_pri);
 
 	/* Start transmission. */
@@ -312,19 +312,19 @@ static void mscan_get_rx_frame(struct net_device *dev, struct can_frame *frame)
 	if (can_id & 1)
 		frame->can_id |= CAN_RTR_FLAG;
 
-	frame->can_dlc = can_cc_dlc2len(in_8(&regs->rx.dlr) & 0xf);
+	frame->len = can_cc_dlc2len(in_8(&regs->rx.dlr) & 0xf);
 
 	if (!(frame->can_id & CAN_RTR_FLAG)) {
 		void __iomem *data = &regs->rx.dsr1_0;
 		u16 *payload = (u16 *)frame->data;
 
-		for (i = 0; i < frame->can_dlc / 2; i++) {
+		for (i = 0; i < frame->len / 2; i++) {
 			*payload++ = in_be16(data);
 			data += 2 + _MSCAN_RESERVED_DSR_SIZE;
 		}
 		/* read remaining byte if necessary */
-		if (frame->can_dlc & 1)
-			frame->data[frame->can_dlc - 1] = in_8(data);
+		if (frame->len & 1)
+			frame->data[frame->len - 1] = in_8(data);
 	}
 
 	out_8(&regs->canrflg, MSCAN_RXF);
@@ -372,7 +372,7 @@ static void mscan_get_err_frame(struct net_device *dev, struct can_frame *frame,
 		}
 	}
 	priv->shadow_statflg = canrflg & MSCAN_STAT_MSK;
-	frame->can_dlc = CAN_ERR_DLC;
+	frame->len = CAN_ERR_DLC;
 	out_8(&regs->canrflg, MSCAN_ERR_IF);
 }
 
@@ -407,7 +407,7 @@ static int mscan_rx_poll(struct napi_struct *napi, int quota)
 			mscan_get_err_frame(dev, frame, canrflg);
 
 		stats->rx_packets++;
-		stats->rx_bytes += frame->can_dlc;
+		stats->rx_bytes += frame->len;
 		work_done++;
 		netif_receive_skb(skb);
 	}
diff --git a/drivers/net/can/pch_can.c b/drivers/net/can/pch_can.c
index 9509bac8352d..4f9e7ec192aa 100644
--- a/drivers/net/can/pch_can.c
+++ b/drivers/net/can/pch_can.c
@@ -563,7 +563,7 @@ static void pch_can_error(struct net_device *ndev, u32 status)
 	netif_receive_skb(skb);
 
 	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 }
 
 static irqreturn_t pch_can_interrupt(int irq, void *dev_id)
@@ -683,10 +683,10 @@ static int pch_can_rx_normal(struct net_device *ndev, u32 obj_num, int quota)
 		if (id2 & PCH_ID2_DIR)
 			cf->can_id |= CAN_RTR_FLAG;
 
-		cf->can_dlc = can_cc_dlc2len((ioread32(&priv->regs->
+		cf->len = can_cc_dlc2len((ioread32(&priv->regs->
 						    ifregs[0].mcont)) & 0xF);
 
-		for (i = 0; i < cf->can_dlc; i += 2) {
+		for (i = 0; i < cf->len; i += 2) {
 			data_reg = ioread16(&priv->regs->ifregs[0].data[i / 2]);
 			cf->data[i] = data_reg;
 			cf->data[i + 1] = data_reg >> 8;
@@ -696,7 +696,7 @@ static int pch_can_rx_normal(struct net_device *ndev, u32 obj_num, int quota)
 		rcv_pkts++;
 		stats->rx_packets++;
 		quota--;
-		stats->rx_bytes += cf->can_dlc;
+		stats->rx_bytes += cf->len;
 
 		pch_fifo_thresh(priv, obj_num);
 		obj_num++;
@@ -919,7 +919,7 @@ static netdev_tx_t pch_xmit(struct sk_buff *skb, struct net_device *ndev)
 	iowrite32(id2, &priv->regs->ifregs[1].id2);
 
 	/* Copy data to register */
-	for (i = 0; i < cf->can_dlc; i += 2) {
+	for (i = 0; i < cf->len; i += 2) {
 		iowrite16(cf->data[i] | (cf->data[i + 1] << 8),
 			  &priv->regs->ifregs[1].data[i / 2]);
 	}
@@ -927,7 +927,7 @@ static netdev_tx_t pch_xmit(struct sk_buff *skb, struct net_device *ndev)
 	can_put_echo_skb(skb, ndev, tx_obj_no - PCH_RX_OBJ_END - 1);
 
 	/* Set the size of the data. Update if2_mcont */
-	iowrite32(cf->can_dlc | PCH_IF_MCONT_NEWDAT | PCH_IF_MCONT_TXRQXT |
+	iowrite32(cf->len | PCH_IF_MCONT_NEWDAT | PCH_IF_MCONT_TXRQXT |
 		  PCH_IF_MCONT_TXIE, &priv->regs->ifregs[1].mcont);
 
 	pch_can_rw_msg_obj(&priv->regs->ifregs[1].creq, tx_obj_no);
diff --git a/drivers/net/can/peak_canfd/peak_canfd.c b/drivers/net/can/peak_canfd/peak_canfd.c
index c6077e07214e..fff3a35276aa 100644
--- a/drivers/net/can/peak_canfd/peak_canfd.c
+++ b/drivers/net/can/peak_canfd/peak_canfd.c
@@ -410,7 +410,7 @@ static int pucan_handle_status(struct peak_canfd_priv *priv,
 	}
 
 	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 	pucan_netif_rx(skb, msg->ts_low, msg->ts_high);
 
 	return 0;
@@ -438,7 +438,7 @@ static int pucan_handle_cache_critical(struct peak_canfd_priv *priv)
 	cf->data[6] = priv->bec.txerr;
 	cf->data[7] = priv->bec.rxerr;
 
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 	stats->rx_packets++;
 	netif_rx(skb);
 
@@ -652,7 +652,7 @@ static netdev_tx_t peak_canfd_start_xmit(struct sk_buff *skb,
 	unsigned long flags;
 	bool should_stop_tx_queue;
 	int room_left;
-	u8 can_dlc;
+	u8 len;
 
 	if (can_dropped_invalid_skb(ndev, skb))
 		return NETDEV_TX_OK;
@@ -682,7 +682,7 @@ static netdev_tx_t peak_canfd_start_xmit(struct sk_buff *skb,
 
 	if (can_is_canfd_skb(skb)) {
 		/* CAN FD frame format */
-		can_dlc = can_len2dlc(cf->len);
+		len = can_len2dlc(cf->len);
 
 		msg_flags |= PUCAN_MSG_EXT_DATA_LEN;
 
@@ -693,7 +693,7 @@ static netdev_tx_t peak_canfd_start_xmit(struct sk_buff *skb,
 			msg_flags |= PUCAN_MSG_ERROR_STATE_IND;
 	} else {
 		/* CAN 2.0 frame format */
-		can_dlc = cf->len;
+		len = cf->len;
 
 		if (cf->can_id & CAN_RTR_FLAG)
 			msg_flags |= PUCAN_MSG_RTR;
@@ -707,7 +707,7 @@ static netdev_tx_t peak_canfd_start_xmit(struct sk_buff *skb,
 		msg_flags |= PUCAN_MSG_SELF_RECEIVE;
 
 	msg->flags = cpu_to_le16(msg_flags);
-	msg->channel_dlc = PUCAN_MSG_CHANNEL_DLC(priv->index, can_dlc);
+	msg->channel_dlc = PUCAN_MSG_CHANNEL_DLC(priv->index, len);
 	memcpy(msg->d, cf->data, cf->len);
 
 	/* struct msg client field is used as an index in the echo skbs ring */
diff --git a/drivers/net/can/rcar/rcar_can.c b/drivers/net/can/rcar/rcar_can.c
index 711ef4996b48..c803327f8f79 100644
--- a/drivers/net/can/rcar/rcar_can.c
+++ b/drivers/net/can/rcar/rcar_can.c
@@ -364,7 +364,7 @@ static void rcar_can_error(struct net_device *ndev)
 
 	if (skb) {
 		stats->rx_packets++;
-		stats->rx_bytes += cf->can_dlc;
+		stats->rx_bytes += cf->len;
 		netif_rx(skb);
 	}
 }
@@ -607,16 +607,16 @@ static netdev_tx_t rcar_can_start_xmit(struct sk_buff *skb,
 	if (cf->can_id & CAN_RTR_FLAG) { /* Remote transmission request */
 		data |= RCAR_CAN_RTR;
 	} else {
-		for (i = 0; i < cf->can_dlc; i++)
+		for (i = 0; i < cf->len; i++)
 			writeb(cf->data[i],
 			       &priv->regs->mb[RCAR_CAN_TX_FIFO_MBX].data[i]);
 	}
 
 	writel(data, &priv->regs->mb[RCAR_CAN_TX_FIFO_MBX].id);
 
-	writeb(cf->can_dlc, &priv->regs->mb[RCAR_CAN_TX_FIFO_MBX].dlc);
+	writeb(cf->len, &priv->regs->mb[RCAR_CAN_TX_FIFO_MBX].dlc);
 
-	priv->tx_dlc[priv->tx_head % RCAR_CAN_FIFO_DEPTH] = cf->can_dlc;
+	priv->tx_dlc[priv->tx_head % RCAR_CAN_FIFO_DEPTH] = cf->len;
 	can_put_echo_skb(skb, ndev, priv->tx_head % RCAR_CAN_FIFO_DEPTH);
 	priv->tx_head++;
 	/* Start Tx: write 0xff to the TFPCR register to increment
@@ -659,18 +659,18 @@ static void rcar_can_rx_pkt(struct rcar_can_priv *priv)
 		cf->can_id = (data >> RCAR_CAN_SID_SHIFT) & CAN_SFF_MASK;
 
 	dlc = readb(&priv->regs->mb[RCAR_CAN_RX_FIFO_MBX].dlc);
-	cf->can_dlc = can_cc_dlc2len(dlc);
+	cf->len = can_cc_dlc2len(dlc);
 	if (data & RCAR_CAN_RTR) {
 		cf->can_id |= CAN_RTR_FLAG;
 	} else {
-		for (dlc = 0; dlc < cf->can_dlc; dlc++)
+		for (dlc = 0; dlc < cf->len; dlc++)
 			cf->data[dlc] =
 			readb(&priv->regs->mb[RCAR_CAN_RX_FIFO_MBX].data[dlc]);
 	}
 
 	can_led_event(priv->ndev, CAN_LED_EVENT_RX);
 
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 	stats->rx_packets++;
 	netif_receive_skb(skb);
 }
diff --git a/drivers/net/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c
index 899a3218ce5e..86c6cbdb7e53 100644
--- a/drivers/net/can/rcar/rcar_canfd.c
+++ b/drivers/net/can/rcar/rcar_canfd.c
@@ -1025,7 +1025,7 @@ static void rcar_canfd_error(struct net_device *ndev, u32 cerfl,
 	rcar_canfd_write(priv->base, RCANFD_CERFL(ch),
 			 RCANFD_CERFL_ERR(~cerfl));
 	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 	netif_rx(skb);
 }
 
@@ -1134,7 +1134,7 @@ static void rcar_canfd_state_change(struct net_device *ndev,
 
 		can_change_state(ndev, cf, tx_state, rx_state);
 		stats->rx_packets++;
-		stats->rx_bytes += cf->can_dlc;
+		stats->rx_bytes += cf->len;
 		netif_rx(skb);
 	}
 }
diff --git a/drivers/net/can/rx-offload.c b/drivers/net/can/rx-offload.c
index 6e95193b215b..450c5cfcb3fc 100644
--- a/drivers/net/can/rx-offload.c
+++ b/drivers/net/can/rx-offload.c
@@ -55,7 +55,7 @@ static int can_rx_offload_napi_poll(struct napi_struct *napi, int quota)
 
 		work_done++;
 		stats->rx_packets++;
-		stats->rx_bytes += cf->can_dlc;
+		stats->rx_bytes += cf->len;
 		netif_receive_skb(skb);
 	}
 
diff --git a/drivers/net/can/sja1000/sja1000.c b/drivers/net/can/sja1000/sja1000.c
index 1f188f2d126e..d55394aa0b95 100644
--- a/drivers/net/can/sja1000/sja1000.c
+++ b/drivers/net/can/sja1000/sja1000.c
@@ -295,7 +295,7 @@ static netdev_tx_t sja1000_start_xmit(struct sk_buff *skb,
 
 	netif_stop_queue(dev);
 
-	fi = dlc = cf->can_dlc;
+	fi = dlc = cf->len;
 	id = cf->can_id;
 
 	if (id & CAN_RTR_FLAG)
@@ -367,11 +367,11 @@ static void sja1000_rx(struct net_device *dev)
 		    | (priv->read_reg(priv, SJA1000_ID2) >> 5);
 	}
 
-	cf->can_dlc = can_cc_dlc2len(fi & 0x0F);
+	cf->len = can_cc_dlc2len(fi & 0x0F);
 	if (fi & SJA1000_FI_RTR) {
 		id |= CAN_RTR_FLAG;
 	} else {
-		for (i = 0; i < cf->can_dlc; i++)
+		for (i = 0; i < cf->len; i++)
 			cf->data[i] = priv->read_reg(priv, dreg++);
 	}
 
@@ -381,7 +381,7 @@ static void sja1000_rx(struct net_device *dev)
 	sja1000_write_cmdreg(priv, CMD_RRB);
 
 	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 	netif_rx(skb);
 
 	can_led_event(dev, CAN_LED_EVENT_RX);
@@ -490,7 +490,7 @@ static int sja1000_err(struct net_device *dev, uint8_t isrc, uint8_t status)
 	}
 
 	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 	netif_rx(skb);
 
 	return 0;
diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c
index b4a39f0449ba..a1bd1be09548 100644
--- a/drivers/net/can/slcan.c
+++ b/drivers/net/can/slcan.c
@@ -106,8 +106,8 @@ static struct net_device **slcan_devs;
 
 /*
  * A CAN frame has a can_id (11 bit standard frame format OR 29 bit extended
- * frame format) a data length code (can_dlc) which can be from 0 to 8
- * and up to <can_dlc> data bytes as payload.
+ * frame format) a data length code (len) which can be from 0 to 8
+ * and up to <len> data bytes as payload.
  * Additionally a CAN frame may become a remote transmission frame if the
  * RTR-bit is set. This causes another ECU to send a CAN frame with the
  * given can_id.
@@ -128,10 +128,10 @@ static struct net_device **slcan_devs;
  *
  * Examples:
  *
- * t1230 : can_id 0x123, can_dlc 0, no data
- * t4563112233 : can_id 0x456, can_dlc 3, data 0x11 0x22 0x33
- * T12ABCDEF2AA55 : extended can_id 0x12ABCDEF, can_dlc 2, data 0xAA 0x55
- * r1230 : can_id 0x123, can_dlc 0, no data, remote transmission request
+ * t1230 : can_id 0x123, len 0, no data
+ * t4563112233 : can_id 0x456, len 3, data 0x11 0x22 0x33
+ * T12ABCDEF2AA55 : extended can_id 0x12ABCDEF, len 2, data 0xAA 0x55
+ * r1230 : can_id 0x123, len 0, no data, remote transmission request
  *
  */
 
@@ -156,7 +156,7 @@ static void slc_bump(struct slcan *sl)
 		fallthrough;
 	case 't':
 		/* store dlc ASCII value and terminate SFF CAN ID string */
-		cf.can_dlc = sl->rbuff[SLC_CMD_LEN + SLC_SFF_ID_LEN];
+		cf.len = sl->rbuff[SLC_CMD_LEN + SLC_SFF_ID_LEN];
 		sl->rbuff[SLC_CMD_LEN + SLC_SFF_ID_LEN] = 0;
 		/* point to payload data behind the dlc */
 		cmd += SLC_CMD_LEN + SLC_SFF_ID_LEN + 1;
@@ -167,7 +167,7 @@ static void slc_bump(struct slcan *sl)
 	case 'T':
 		cf.can_id |= CAN_EFF_FLAG;
 		/* store dlc ASCII value and terminate EFF CAN ID string */
-		cf.can_dlc = sl->rbuff[SLC_CMD_LEN + SLC_EFF_ID_LEN];
+		cf.len = sl->rbuff[SLC_CMD_LEN + SLC_EFF_ID_LEN];
 		sl->rbuff[SLC_CMD_LEN + SLC_EFF_ID_LEN] = 0;
 		/* point to payload data behind the dlc */
 		cmd += SLC_CMD_LEN + SLC_EFF_ID_LEN + 1;
@@ -181,15 +181,15 @@ static void slc_bump(struct slcan *sl)
 
 	cf.can_id |= tmpid;
 
-	/* get can_dlc from sanitized ASCII value */
-	if (cf.can_dlc >= '0' && cf.can_dlc < '9')
-		cf.can_dlc -= '0';
+	/* get len from sanitized ASCII value */
+	if (cf.len >= '0' && cf.len < '9')
+		cf.len -= '0';
 	else
 		return;
 
 	/* RTR frames may have a dlc > 0 but they never have any data bytes */
 	if (!(cf.can_id & CAN_RTR_FLAG)) {
-		for (i = 0; i < cf.can_dlc; i++) {
+		for (i = 0; i < cf.len; i++) {
 			tmp = hex_to_bin(*cmd++);
 			if (tmp < 0)
 				return;
@@ -218,7 +218,7 @@ static void slc_bump(struct slcan *sl)
 	skb_put_data(skb, &cf, sizeof(struct can_frame));
 
 	sl->dev->stats.rx_packets++;
-	sl->dev->stats.rx_bytes += cf.can_dlc;
+	sl->dev->stats.rx_bytes += cf.len;
 	netif_rx_ni(skb);
 }
 
@@ -282,11 +282,11 @@ static void slc_encaps(struct slcan *sl, struct can_frame *cf)
 
 	pos += (cf->can_id & CAN_EFF_FLAG) ? SLC_EFF_ID_LEN : SLC_SFF_ID_LEN;
 
-	*pos++ = cf->can_dlc + '0';
+	*pos++ = cf->len + '0';
 
 	/* RTR frames may have a dlc > 0 but they never have any data bytes */
 	if (!(cf->can_id & CAN_RTR_FLAG)) {
-		for (i = 0; i < cf->can_dlc; i++)
+		for (i = 0; i < cf->len; i++)
 			pos = hex_byte_pack_upper(pos, cf->data[i]);
 	}
 
@@ -304,7 +304,7 @@ static void slc_encaps(struct slcan *sl, struct can_frame *cf)
 	actual = sl->tty->ops->write(sl->tty, sl->xbuff, pos - sl->xbuff);
 	sl->xleft = (pos - sl->xbuff) - actual;
 	sl->xhead = sl->xbuff + actual;
-	sl->dev->stats.tx_bytes += cf->can_dlc;
+	sl->dev->stats.tx_bytes += cf->len;
 }
 
 /* Write out any remaining transmit buffer. Scheduled when tty is writable */
diff --git a/drivers/net/can/softing/softing_fw.c b/drivers/net/can/softing/softing_fw.c
index ccd649a8e37b..7e1536877993 100644
--- a/drivers/net/can/softing/softing_fw.c
+++ b/drivers/net/can/softing/softing_fw.c
@@ -624,7 +624,7 @@ int softing_startstop(struct net_device *dev, int up)
 	 */
 	memset(&msg, 0, sizeof(msg));
 	msg.can_id = CAN_ERR_FLAG | CAN_ERR_RESTARTED;
-	msg.can_dlc = CAN_ERR_DLC;
+	msg.len = CAN_ERR_DLC;
 	for (j = 0; j < ARRAY_SIZE(card->net); ++j) {
 		if (!(bus_bitmask_start & (1 << j)))
 			continue;
diff --git a/drivers/net/can/softing/softing_main.c b/drivers/net/can/softing/softing_main.c
index 39e8275ee7ba..03a68bb486fd 100644
--- a/drivers/net/can/softing/softing_main.c
+++ b/drivers/net/can/softing/softing_main.c
@@ -84,7 +84,7 @@ static netdev_tx_t softing_netdev_start_xmit(struct sk_buff *skb,
 	if (priv->index)
 		*ptr |= CMD_BUS2;
 	++ptr;
-	*ptr++ = cf->can_dlc;
+	*ptr++ = cf->len;
 	*ptr++ = (cf->can_id >> 0);
 	*ptr++ = (cf->can_id >> 8);
 	if (cf->can_id & CAN_EFF_FLAG) {
@@ -95,7 +95,7 @@ static netdev_tx_t softing_netdev_start_xmit(struct sk_buff *skb,
 		ptr += 1;
 	}
 	if (!(cf->can_id & CAN_RTR_FLAG))
-		memcpy(ptr, &cf->data[0], cf->can_dlc);
+		memcpy(ptr, &cf->data[0], cf->len);
 	memcpy_toio(&card->dpram[DPRAM_TX + DPRAM_TX_SIZE * fifo_wr],
 			buf, DPRAM_TX_SIZE);
 	if (++fifo_wr >= DPRAM_TX_CNT)
@@ -167,7 +167,7 @@ static int softing_handle_1(struct softing *card)
 		iowrite8(0, &card->dpram[DPRAM_RX_LOST]);
 		/* prepare msg */
 		msg.can_id = CAN_ERR_FLAG | CAN_ERR_CRTL;
-		msg.can_dlc = CAN_ERR_DLC;
+		msg.len = CAN_ERR_DLC;
 		msg.data[1] = CAN_ERR_CRTL_RX_OVERFLOW;
 		/*
 		 * service to all buses, we don't know which it was applicable
@@ -218,7 +218,7 @@ static int softing_handle_1(struct softing *card)
 		state = *ptr++;
 
 		msg.can_id = CAN_ERR_FLAG;
-		msg.can_dlc = CAN_ERR_DLC;
+		msg.len = CAN_ERR_DLC;
 
 		if (state & SF_MASK_BUSOFF) {
 			can_state = CAN_STATE_BUS_OFF;
@@ -261,7 +261,7 @@ static int softing_handle_1(struct softing *card)
 	} else {
 		if (cmd & CMD_RTR)
 			msg.can_id |= CAN_RTR_FLAG;
-		msg.can_dlc = can_cc_dlc2len(*ptr++);
+		msg.len = can_cc_dlc2len(*ptr++);
 		if (cmd & CMD_XTD) {
 			msg.can_id |= CAN_EFF_FLAG;
 			msg.can_id |= le32_to_cpup((void *)ptr);
@@ -294,7 +294,7 @@ static int softing_handle_1(struct softing *card)
 				--card->tx.pending;
 			++netdev->stats.tx_packets;
 			if (!(msg.can_id & CAN_RTR_FLAG))
-				netdev->stats.tx_bytes += msg.can_dlc;
+				netdev->stats.tx_bytes += msg.len;
 		} else {
 			int ret;
 
@@ -302,7 +302,7 @@ static int softing_handle_1(struct softing *card)
 			if (ret == NET_RX_SUCCESS) {
 				++netdev->stats.rx_packets;
 				if (!(msg.can_id & CAN_RTR_FLAG))
-					netdev->stats.rx_bytes += msg.can_dlc;
+					netdev->stats.rx_bytes += msg.len;
 			} else {
 				++netdev->stats.rx_dropped;
 			}
diff --git a/drivers/net/can/spi/hi311x.c b/drivers/net/can/spi/hi311x.c
index 728f34b696a7..f9455de94786 100644
--- a/drivers/net/can/spi/hi311x.c
+++ b/drivers/net/can/spi/hi311x.c
@@ -277,13 +277,13 @@ static void hi3110_hw_tx(struct spi_device *spi, struct can_frame *frame)
 			((frame->can_id & CAN_EFF_MASK) << 1) |
 			((frame->can_id & CAN_RTR_FLAG) ? 1 : 0);
 
-		buf[HI3110_FIFO_EXT_DLC_OFF] = frame->can_dlc;
+		buf[HI3110_FIFO_EXT_DLC_OFF] = frame->len;
 
 		memcpy(buf + HI3110_FIFO_EXT_DATA_OFF,
-		       frame->data, frame->can_dlc);
+		       frame->data, frame->len);
 
 		hi3110_hw_tx_frame(spi, buf, HI3110_TX_EXT_BUF_LEN -
-				   (HI3110_CAN_MAX_DATA_LEN - frame->can_dlc));
+				   (HI3110_CAN_MAX_DATA_LEN - frame->len));
 	} else {
 		/* Standard frame */
 		buf[HI3110_FIFO_ID_OFF] =   (frame->can_id & CAN_SFF_MASK) >> 3;
@@ -291,13 +291,13 @@ static void hi3110_hw_tx(struct spi_device *spi, struct can_frame *frame)
 			((frame->can_id & CAN_SFF_MASK) << 5) |
 			((frame->can_id & CAN_RTR_FLAG) ? (1 << 4) : 0);
 
-		buf[HI3110_FIFO_STD_DLC_OFF] = frame->can_dlc;
+		buf[HI3110_FIFO_STD_DLC_OFF] = frame->len;
 
 		memcpy(buf + HI3110_FIFO_STD_DATA_OFF,
-		       frame->data, frame->can_dlc);
+		       frame->data, frame->len);
 
 		hi3110_hw_tx_frame(spi, buf, HI3110_TX_STD_BUF_LEN -
-				   (HI3110_CAN_MAX_DATA_LEN - frame->can_dlc));
+				   (HI3110_CAN_MAX_DATA_LEN - frame->len));
 	}
 }
 
@@ -341,16 +341,16 @@ static void hi3110_hw_rx(struct spi_device *spi)
 	}
 
 	/* Data length */
-	frame->can_dlc = can_cc_dlc2len(buf[HI3110_FIFO_WOTIME_DLC_OFF] & 0x0F);
+	frame->len = can_cc_dlc2len(buf[HI3110_FIFO_WOTIME_DLC_OFF] & 0x0F);
 
 	if (buf[HI3110_FIFO_WOTIME_ID_OFF + 3] & HI3110_FIFO_WOTIME_ID_RTR)
 		frame->can_id |= CAN_RTR_FLAG;
 	else
 		memcpy(frame->data, buf + HI3110_FIFO_WOTIME_DAT_OFF,
-		       frame->can_dlc);
+		       frame->len);
 
 	priv->net->stats.rx_packets++;
-	priv->net->stats.rx_bytes += frame->can_dlc;
+	priv->net->stats.rx_bytes += frame->len;
 
 	can_led_event(priv->net, CAN_LED_EVENT_RX);
 
@@ -585,7 +585,7 @@ static void hi3110_tx_work_handler(struct work_struct *ws)
 		} else {
 			frame = (struct can_frame *)priv->tx_skb->data;
 			hi3110_hw_tx(spi, frame);
-			priv->tx_len = 1 + frame->can_dlc;
+			priv->tx_len = 1 + frame->len;
 			can_put_echo_skb(priv->tx_skb, net, 0);
 			priv->tx_skb = NULL;
 		}
diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c
index 6ddebb1c4a24..25859d16d06f 100644
--- a/drivers/net/can/spi/mcp251x.c
+++ b/drivers/net/can/spi/mcp251x.c
@@ -644,9 +644,9 @@ static void mcp251x_hw_tx(struct spi_device *spi, struct can_frame *frame,
 		((eid >> SIDL_EID_SHIFT) & SIDL_EID_MASK);
 	buf[TXBEID8_OFF] = GET_BYTE(eid, 1);
 	buf[TXBEID0_OFF] = GET_BYTE(eid, 0);
-	buf[TXBDLC_OFF] = (rtr << DLC_RTR_SHIFT) | frame->can_dlc;
-	memcpy(buf + TXBDAT_OFF, frame->data, frame->can_dlc);
-	mcp251x_hw_tx_frame(spi, buf, frame->can_dlc, tx_buf_idx);
+	buf[TXBDLC_OFF] = (rtr << DLC_RTR_SHIFT) | frame->len;
+	memcpy(buf + TXBDAT_OFF, frame->data, frame->len);
+	mcp251x_hw_tx_frame(spi, buf, frame->len, tx_buf_idx);
 
 	/* use INSTRUCTION_RTS, to avoid "repeated frame problem" */
 	priv->spi_tx_buf[0] = INSTRUCTION_RTS(1 << tx_buf_idx);
@@ -720,11 +720,11 @@ static void mcp251x_hw_rx(struct spi_device *spi, int buf_idx)
 			frame->can_id |= CAN_RTR_FLAG;
 	}
 	/* Data length */
-	frame->can_dlc = can_cc_dlc2len(buf[RXBDLC_OFF] & RXBDLC_LEN_MASK);
-	memcpy(frame->data, buf + RXBDAT_OFF, frame->can_dlc);
+	frame->len = can_cc_dlc2len(buf[RXBDLC_OFF] & RXBDLC_LEN_MASK);
+	memcpy(frame->data, buf + RXBDAT_OFF, frame->len);
 
 	priv->net->stats.rx_packets++;
-	priv->net->stats.rx_bytes += frame->can_dlc;
+	priv->net->stats.rx_bytes += frame->len;
 
 	can_led_event(priv->net, CAN_LED_EVENT_RX);
 
@@ -998,10 +998,10 @@ static void mcp251x_tx_work_handler(struct work_struct *ws)
 		} else {
 			frame = (struct can_frame *)priv->tx_skb->data;
 
-			if (frame->can_dlc > CAN_FRAME_MAX_DATA_LEN)
-				frame->can_dlc = CAN_FRAME_MAX_DATA_LEN;
+			if (frame->len > CAN_FRAME_MAX_DATA_LEN)
+				frame->len = CAN_FRAME_MAX_DATA_LEN;
 			mcp251x_hw_tx(spi, frame, 0);
-			priv->tx_len = 1 + frame->can_dlc;
+			priv->tx_len = 1 + frame->len;
 			can_put_echo_skb(priv->tx_skb, net, 0);
 			priv->tx_skb = NULL;
 		}
diff --git a/drivers/net/can/sun4i_can.c b/drivers/net/can/sun4i_can.c
index 0e2569779895..098cc9670f0f 100644
--- a/drivers/net/can/sun4i_can.c
+++ b/drivers/net/can/sun4i_can.c
@@ -424,7 +424,7 @@ static netdev_tx_t sun4ican_start_xmit(struct sk_buff *skb, struct net_device *d
 	netif_stop_queue(dev);
 
 	id = cf->can_id;
-	dlc = cf->can_dlc;
+	dlc = cf->len;
 	msg_flag_n = dlc;
 
 	if (id & CAN_RTR_FLAG)
@@ -475,7 +475,7 @@ static void sun4i_can_rx(struct net_device *dev)
 		return;
 
 	fi = readl(priv->base + SUN4I_REG_BUF0_ADDR);
-	cf->can_dlc = can_cc_dlc2len(fi & 0x0F);
+	cf->len = can_cc_dlc2len(fi & 0x0F);
 	if (fi & SUN4I_MSG_EFF_FLAG) {
 		dreg = SUN4I_REG_BUF5_ADDR;
 		id = (readl(priv->base + SUN4I_REG_BUF1_ADDR) << 21) |
@@ -493,7 +493,7 @@ static void sun4i_can_rx(struct net_device *dev)
 	if (fi & SUN4I_MSG_RTR_FLAG)
 		id |= CAN_RTR_FLAG;
 	else
-		for (i = 0; i < cf->can_dlc; i++)
+		for (i = 0; i < cf->len; i++)
 			cf->data[i] = readl(priv->base + dreg + i * 4);
 
 	cf->can_id = id;
@@ -501,7 +501,7 @@ static void sun4i_can_rx(struct net_device *dev)
 	sun4i_can_write_cmdreg(priv, SUN4I_CMD_RELEASE_RBUF);
 
 	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 	netif_rx(skb);
 
 	can_led_event(dev, CAN_LED_EVENT_RX);
@@ -625,7 +625,7 @@ static int sun4i_can_err(struct net_device *dev, u8 isrc, u8 status)
 
 	if (likely(skb)) {
 		stats->rx_packets++;
-		stats->rx_bytes += cf->can_dlc;
+		stats->rx_bytes += cf->len;
 		netif_rx(skb);
 	} else {
 		return -ENOMEM;
diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c
index 0b1fd34f4c83..a6850ff0b55b 100644
--- a/drivers/net/can/ti_hecc.c
+++ b/drivers/net/can/ti_hecc.c
@@ -496,7 +496,7 @@ static netdev_tx_t ti_hecc_xmit(struct sk_buff *skb, struct net_device *ndev)
 	spin_unlock_irqrestore(&priv->mbx_lock, flags);
 
 	/* Prepare mailbox for transmission */
-	data = cf->can_dlc | (get_tx_head_prio(priv) << 8);
+	data = cf->len | (get_tx_head_prio(priv) << 8);
 	if (cf->can_id & CAN_RTR_FLAG) /* Remote transmission request */
 		data |= HECC_CANMCF_RTR;
 	hecc_write_mbx(priv, mbxno, HECC_CANMCF, data);
@@ -508,7 +508,7 @@ static netdev_tx_t ti_hecc_xmit(struct sk_buff *skb, struct net_device *ndev)
 	hecc_write_mbx(priv, mbxno, HECC_CANMID, data);
 	hecc_write_mbx(priv, mbxno, HECC_CANMDL,
 		       be32_to_cpu(*(__be32 *)(cf->data)));
-	if (cf->can_dlc > 4)
+	if (cf->len > 4)
 		hecc_write_mbx(priv, mbxno, HECC_CANMDH,
 			       be32_to_cpu(*(__be32 *)(cf->data + 4)));
 	else
@@ -566,11 +566,11 @@ static struct sk_buff *ti_hecc_mailbox_read(struct can_rx_offload *offload,
 	data = hecc_read_mbx(priv, mbxno, HECC_CANMCF);
 	if (data & HECC_CANMCF_RTR)
 		cf->can_id |= CAN_RTR_FLAG;
-	cf->can_dlc = can_cc_dlc2len(data & 0xF);
+	cf->len = can_cc_dlc2len(data & 0xF);
 
 	data = hecc_read_mbx(priv, mbxno, HECC_CANMDL);
 	*(__be32 *)(cf->data) = cpu_to_be32(data);
-	if (cf->can_dlc > 4) {
+	if (cf->len > 4) {
 		data = hecc_read_mbx(priv, mbxno, HECC_CANMDH);
 		*(__be32 *)(cf->data + 4) = cpu_to_be32(data);
 	}
diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c
index 288781934149..25eee4466364 100644
--- a/drivers/net/can/usb/ems_usb.c
+++ b/drivers/net/can/usb/ems_usb.c
@@ -306,7 +306,7 @@ static void ems_usb_rx_can_msg(struct ems_usb *dev, struct ems_cpc_msg *msg)
 		return;
 
 	cf->can_id = le32_to_cpu(msg->msg.can_msg.id);
-	cf->can_dlc = can_cc_dlc2len(msg->msg.can_msg.length & 0xF);
+	cf->len = can_cc_dlc2len(msg->msg.can_msg.length & 0xF);
 
 	if (msg->type == CPC_MSG_TYPE_EXT_CAN_FRAME ||
 	    msg->type == CPC_MSG_TYPE_EXT_RTR_FRAME)
@@ -316,12 +316,12 @@ static void ems_usb_rx_can_msg(struct ems_usb *dev, struct ems_cpc_msg *msg)
 	    msg->type == CPC_MSG_TYPE_EXT_RTR_FRAME) {
 		cf->can_id |= CAN_RTR_FLAG;
 	} else {
-		for (i = 0; i < cf->can_dlc; i++)
+		for (i = 0; i < cf->len; i++)
 			cf->data[i] = msg->msg.can_msg.msg[i];
 	}
 
 	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 	netif_rx(skb);
 }
 
@@ -396,7 +396,7 @@ static void ems_usb_rx_err(struct ems_usb *dev, struct ems_cpc_msg *msg)
 	}
 
 	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 	netif_rx(skb);
 }
 
@@ -755,7 +755,7 @@ static netdev_tx_t ems_usb_start_xmit(struct sk_buff *skb, struct net_device *ne
 	msg = (struct ems_cpc_msg *)&buf[CPC_HEADER_SIZE];
 
 	msg->msg.can_msg.id = cpu_to_le32(cf->can_id & CAN_ERR_MASK);
-	msg->msg.can_msg.length = cf->can_dlc;
+	msg->msg.can_msg.length = cf->len;
 
 	if (cf->can_id & CAN_RTR_FLAG) {
 		msg->type = cf->can_id & CAN_EFF_FLAG ?
@@ -766,10 +766,10 @@ static netdev_tx_t ems_usb_start_xmit(struct sk_buff *skb, struct net_device *ne
 		msg->type = cf->can_id & CAN_EFF_FLAG ?
 			CPC_CMD_TYPE_EXT_CAN_FRAME : CPC_CMD_TYPE_CAN_FRAME;
 
-		for (i = 0; i < cf->can_dlc; i++)
+		for (i = 0; i < cf->len; i++)
 			msg->msg.can_msg.msg[i] = cf->data[i];
 
-		msg->length = CPC_CAN_MSG_MIN_SIZE + cf->can_dlc;
+		msg->length = CPC_CAN_MSG_MIN_SIZE + cf->len;
 	}
 
 	for (i = 0; i < MAX_TX_URBS; i++) {
@@ -794,7 +794,7 @@ static netdev_tx_t ems_usb_start_xmit(struct sk_buff *skb, struct net_device *ne
 
 	context->dev = dev;
 	context->echo_index = i;
-	context->dlc = cf->can_dlc;
+	context->dlc = cf->len;
 
 	usb_fill_bulk_urb(urb, dev->udev, usb_sndbulkpipe(dev->udev, 2), buf,
 			  size, ems_usb_write_bulk_callback, context);
diff --git a/drivers/net/can/usb/esd_usb2.c b/drivers/net/can/usb/esd_usb2.c
index 72999de550d1..3643a8ee03cf 100644
--- a/drivers/net/can/usb/esd_usb2.c
+++ b/drivers/net/can/usb/esd_usb2.c
@@ -292,7 +292,7 @@ static void esd_usb2_rx_event(struct esd_usb2_net_priv *priv,
 		priv->bec.rxerr = rxerr;
 
 		stats->rx_packets++;
-		stats->rx_bytes += cf->can_dlc;
+		stats->rx_bytes += cf->len;
 		netif_rx(skb);
 	}
 }
@@ -321,7 +321,7 @@ static void esd_usb2_rx_can_msg(struct esd_usb2_net_priv *priv,
 		}
 
 		cf->can_id = id & ESD_IDMASK;
-		cf->can_dlc = can_cc_dlc2len(msg->msg.rx.dlc & ~ESD_RTR);
+		cf->len = can_cc_dlc2len(msg->msg.rx.dlc & ~ESD_RTR);
 
 		if (id & ESD_EXTID)
 			cf->can_id |= CAN_EFF_FLAG;
@@ -329,12 +329,12 @@ static void esd_usb2_rx_can_msg(struct esd_usb2_net_priv *priv,
 		if (msg->msg.rx.dlc & ESD_RTR) {
 			cf->can_id |= CAN_RTR_FLAG;
 		} else {
-			for (i = 0; i < cf->can_dlc; i++)
+			for (i = 0; i < cf->len; i++)
 				cf->data[i] = msg->msg.rx.data[i];
 		}
 
 		stats->rx_packets++;
-		stats->rx_bytes += cf->can_dlc;
+		stats->rx_bytes += cf->len;
 		netif_rx(skb);
 	}
 
@@ -737,7 +737,7 @@ static netdev_tx_t esd_usb2_start_xmit(struct sk_buff *skb,
 	msg->msg.hdr.len = 3; /* minimal length */
 	msg->msg.hdr.cmd = CMD_CAN_TX;
 	msg->msg.tx.net = priv->index;
-	msg->msg.tx.dlc = cf->can_dlc;
+	msg->msg.tx.dlc = cf->len;
 	msg->msg.tx.id = cpu_to_le32(cf->can_id & CAN_ERR_MASK);
 
 	if (cf->can_id & CAN_RTR_FLAG)
@@ -746,10 +746,10 @@ static netdev_tx_t esd_usb2_start_xmit(struct sk_buff *skb,
 	if (cf->can_id & CAN_EFF_FLAG)
 		msg->msg.tx.id |= cpu_to_le32(ESD_EXTID);
 
-	for (i = 0; i < cf->can_dlc; i++)
+	for (i = 0; i < cf->len; i++)
 		msg->msg.tx.data[i] = cf->data[i];
 
-	msg->msg.hdr.len += (cf->can_dlc + 3) >> 2;
+	msg->msg.hdr.len += (cf->len + 3) >> 2;
 
 	for (i = 0; i < MAX_TX_URBS; i++) {
 		if (priv->tx_contexts[i].echo_index == MAX_TX_URBS) {
@@ -769,7 +769,7 @@ static netdev_tx_t esd_usb2_start_xmit(struct sk_buff *skb,
 
 	context->priv = priv;
 	context->echo_index = i;
-	context->dlc = cf->can_dlc;
+	context->dlc = cf->len;
 
 	/* hnd must not be 0 - MSB is stripped in txdone handling */
 	msg->msg.tx.hnd = 0x80000000 | i; /* returned in TX done message */
diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index b1729b208788..d6a68b7046eb 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -331,7 +331,7 @@ static void gs_usb_receive_bulk_callback(struct urb *urb)
 
 		cf->can_id = hf->can_id;
 
-		cf->can_dlc = can_cc_dlc2len(hf->can_dlc);
+		cf->len = can_cc_dlc2len(hf->can_dlc);
 		memcpy(cf->data, hf->data, 8);
 
 		/* ERROR frames tell us information about the controller */
@@ -378,7 +378,7 @@ static void gs_usb_receive_bulk_callback(struct urb *urb)
 			goto resubmit_urb;
 
 		cf->can_id |= CAN_ERR_CRTL;
-		cf->can_dlc = CAN_ERR_DLC;
+		cf->len = CAN_ERR_DLC;
 		cf->data[1] = CAN_ERR_CRTL_RX_OVERFLOW;
 		stats->rx_over_errors++;
 		stats->rx_errors++;
@@ -504,8 +504,8 @@ static netdev_tx_t gs_can_start_xmit(struct sk_buff *skb,
 	cf = (struct can_frame *)skb->data;
 
 	hf->can_id = cf->can_id;
-	hf->can_dlc = cf->can_dlc;
-	memcpy(hf->data, cf->data, cf->can_dlc);
+	hf->can_dlc = cf->len;
+	memcpy(hf->data, cf->data, cf->len);
 
 	usb_fill_bulk_urb(urb, dev->udev,
 			  usb_sndbulkpipe(dev->udev, GSUSB_ENDPOINT_OUT),
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
index 0f1d3e807d63..d6e18bcb1a7f 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
@@ -258,7 +258,7 @@ int kvaser_usb_can_rx_over_error(struct net_device *netdev)
 	cf->data[1] = CAN_ERR_CRTL_RX_OVERFLOW;
 
 	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 	netif_rx(skb);
 
 	return 0;
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
index 843e2e1392e8..c6d5f3f656c3 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
@@ -895,7 +895,7 @@ static void kvaser_usb_hydra_update_state(struct kvaser_usb_net_priv *priv,
 
 	stats = &netdev->stats;
 	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 	netif_rx(skb);
 }
 
@@ -1049,7 +1049,7 @@ kvaser_usb_hydra_error_frame(struct kvaser_usb_net_priv *priv,
 	cf->data[7] = bec.rxerr;
 
 	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 	netif_rx(skb);
 
 	priv->bec.txerr = bec.txerr;
@@ -1084,7 +1084,7 @@ static void kvaser_usb_hydra_one_shot_fail(struct kvaser_usb_net_priv *priv,
 
 	stats->tx_errors++;
 	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 	netif_rx(skb);
 }
 
@@ -1180,15 +1180,15 @@ static void kvaser_usb_hydra_rx_msg_std(const struct kvaser_usb *dev,
 	if (flags & KVASER_USB_HYDRA_CF_FLAG_OVERRUN)
 		kvaser_usb_can_rx_over_error(priv->netdev);
 
-	cf->can_dlc = can_cc_dlc2len(cmd->rx_can.dlc);
+	cf->len = can_cc_dlc2len(cmd->rx_can.dlc);
 
 	if (flags & KVASER_USB_HYDRA_CF_FLAG_REMOTE_FRAME)
 		cf->can_id |= CAN_RTR_FLAG;
 	else
-		memcpy(cf->data, cmd->rx_can.data, cf->can_dlc);
+		memcpy(cf->data, cmd->rx_can.data, cf->len);
 
 	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 	netif_rx(skb);
 }
 
@@ -1434,7 +1434,7 @@ kvaser_usb_hydra_frame_to_cmd_std(const struct kvaser_usb_net_priv *priv,
 	u32 flags;
 	u32 id;
 
-	*frame_len = cf->can_dlc;
+	*frame_len = cf->len;
 
 	cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_ATOMIC);
 	if (!cmd)
@@ -1455,7 +1455,7 @@ kvaser_usb_hydra_frame_to_cmd_std(const struct kvaser_usb_net_priv *priv,
 		id = cf->can_id & CAN_SFF_MASK;
 	}
 
-	cmd->tx_can.dlc = cf->can_dlc;
+	cmd->tx_can.dlc = cf->len;
 
 	flags = (cf->can_id & CAN_EFF_FLAG ?
 		 KVASER_USB_HYDRA_CF_FLAG_EXTENDED_ID : 0);
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
index 916ab994cce4..98c016ef0607 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
@@ -350,7 +350,7 @@ kvaser_usb_leaf_frame_to_cmd(const struct kvaser_usb_net_priv *priv,
 	u8 *cmd_tx_can_flags = NULL;		/* GCC */
 	struct can_frame *cf = (struct can_frame *)skb->data;
 
-	*frame_len = cf->can_dlc;
+	*frame_len = cf->len;
 
 	cmd = kmalloc(sizeof(*cmd), GFP_ATOMIC);
 	if (cmd) {
@@ -383,8 +383,8 @@ kvaser_usb_leaf_frame_to_cmd(const struct kvaser_usb_net_priv *priv,
 			cmd->u.tx_can.data[1] = cf->can_id & 0x3f;
 		}
 
-		cmd->u.tx_can.data[5] = cf->can_dlc;
-		memcpy(&cmd->u.tx_can.data[6], cf->data, cf->can_dlc);
+		cmd->u.tx_can.data[5] = cf->len;
+		memcpy(&cmd->u.tx_can.data[6], cf->data, cf->len);
 
 		if (cf->can_id & CAN_RTR_FLAG)
 			*cmd_tx_can_flags |= MSG_FLAG_REMOTE_FRAME;
@@ -576,7 +576,7 @@ static void kvaser_usb_leaf_tx_acknowledge(const struct kvaser_usb *dev,
 			cf->can_id |= CAN_ERR_RESTARTED;
 
 			stats->rx_packets++;
-			stats->rx_bytes += cf->can_dlc;
+			stats->rx_bytes += cf->len;
 			netif_rx(skb);
 		} else {
 			netdev_err(priv->netdev,
@@ -694,7 +694,7 @@ static void kvaser_usb_leaf_rx_error(const struct kvaser_usb *dev,
 {
 	struct can_frame *cf;
 	struct can_frame tmp_cf = { .can_id = CAN_ERR_FLAG,
-				    .can_dlc = CAN_ERR_DLC };
+				    .len = CAN_ERR_DLC };
 	struct sk_buff *skb;
 	struct net_device_stats *stats;
 	struct kvaser_usb_net_priv *priv;
@@ -778,7 +778,7 @@ static void kvaser_usb_leaf_rx_error(const struct kvaser_usb *dev,
 	cf->data[7] = es->rxerr;
 
 	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 	netif_rx(skb);
 }
 
@@ -978,13 +978,13 @@ static void kvaser_usb_leaf_rx_can_msg(const struct kvaser_usb *dev,
 		else
 			cf->can_id &= CAN_SFF_MASK;
 
-		cf->can_dlc = can_cc_dlc2len(cmd->u.leaf.log_message.dlc);
+		cf->len = can_cc_dlc2len(cmd->u.leaf.log_message.dlc);
 
 		if (cmd->u.leaf.log_message.flags & MSG_FLAG_REMOTE_FRAME)
 			cf->can_id |= CAN_RTR_FLAG;
 		else
 			memcpy(cf->data, &cmd->u.leaf.log_message.data,
-			       cf->can_dlc);
+			       cf->len);
 	} else {
 		cf->can_id = ((rx_data[0] & 0x1f) << 6) | (rx_data[1] & 0x3f);
 
@@ -996,16 +996,16 @@ static void kvaser_usb_leaf_rx_can_msg(const struct kvaser_usb *dev,
 			cf->can_id |= CAN_EFF_FLAG;
 		}
 
-		cf->can_dlc = can_cc_dlc2len(rx_data[5]);
+		cf->len = can_cc_dlc2len(rx_data[5]);
 
 		if (cmd->u.rx_can_header.flag & MSG_FLAG_REMOTE_FRAME)
 			cf->can_id |= CAN_RTR_FLAG;
 		else
-			memcpy(cf->data, &rx_data[6], cf->can_dlc);
+			memcpy(cf->data, &rx_data[6], cf->len);
 	}
 
 	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 	netif_rx(skb);
 }
 
diff --git a/drivers/net/can/usb/mcba_usb.c b/drivers/net/can/usb/mcba_usb.c
index 295886c6b565..df54eb7d4b36 100644
--- a/drivers/net/can/usb/mcba_usb.c
+++ b/drivers/net/can/usb/mcba_usb.c
@@ -184,7 +184,7 @@ static inline struct mcba_usb_ctx *mcba_usb_get_free_ctx(struct mcba_priv *priv,
 
 			if (cf) {
 				ctx->can = true;
-				ctx->dlc = cf->can_dlc;
+				ctx->dlc = cf->len;
 			} else {
 				ctx->can = false;
 				ctx->dlc = 0;
@@ -348,7 +348,7 @@ static netdev_tx_t mcba_usb_start_xmit(struct sk_buff *skb,
 		usb_msg.eid = 0;
 	}
 
-	usb_msg.dlc = cf->can_dlc;
+	usb_msg.dlc = cf->len;
 
 	memcpy(usb_msg.data, cf->data, usb_msg.dlc);
 
@@ -451,12 +451,12 @@ static void mcba_usb_process_can(struct mcba_priv *priv,
 	if (msg->dlc & MCBA_DLC_RTR_MASK)
 		cf->can_id |= CAN_RTR_FLAG;
 
-	cf->can_dlc = can_cc_dlc2len(msg->dlc & MCBA_DLC_MASK);
+	cf->len = can_cc_dlc2len(msg->dlc & MCBA_DLC_MASK);
 
-	memcpy(cf->data, msg->data, cf->can_dlc);
+	memcpy(cf->data, msg->data, cf->len);
 
 	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 
 	can_led_event(priv->netdev, CAN_LED_EVENT_RX);
 	netif_rx(skb);
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c
index f7fc82203489..ec34f87cc02c 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb.c
@@ -596,7 +596,7 @@ static int pcan_usb_decode_error(struct pcan_usb_msg_context *mc, u8 n,
 	}
 
 	mc->netdev->stats.rx_packets++;
-	mc->netdev->stats.rx_bytes += cf->can_dlc;
+	mc->netdev->stats.rx_bytes += cf->len;
 	netif_rx(skb);
 
 	return 0;
@@ -734,7 +734,7 @@ static int pcan_usb_decode_data(struct pcan_usb_msg_context *mc, u8 status_len)
 		cf->can_id = le16_to_cpu(tmp16) >> 5;
 	}
 
-	cf->can_dlc = can_cc_dlc2len(rec_len);
+	cf->len = can_cc_dlc2len(rec_len);
 
 	/* Only first packet timestamp is a word */
 	if (pcan_usb_decode_ts(mc, !mc->rec_ts_idx))
@@ -751,7 +751,7 @@ static int pcan_usb_decode_data(struct pcan_usb_msg_context *mc, u8 status_len)
 		if ((mc->ptr + rec_len) > mc->end)
 			goto decode_failed;
 
-		memcpy(cf->data, mc->ptr, cf->can_dlc);
+		memcpy(cf->data, mc->ptr, cf->len);
 		mc->ptr += rec_len;
 	}
 
@@ -761,7 +761,7 @@ static int pcan_usb_decode_data(struct pcan_usb_msg_context *mc, u8 status_len)
 
 	/* update statistics */
 	mc->netdev->stats.rx_packets++;
-	mc->netdev->stats.rx_bytes += cf->can_dlc;
+	mc->netdev->stats.rx_bytes += cf->len;
 	/* push the skb */
 	netif_rx(skb);
 
@@ -838,7 +838,7 @@ static int pcan_usb_encode_msg(struct peak_usb_device *dev, struct sk_buff *skb,
 	pc = obuf + PCAN_USB_MSG_HEADER_LEN;
 
 	/* status/len byte */
-	*pc = cf->can_dlc;
+	*pc = cf->len;
 	if (cf->can_id & CAN_RTR_FLAG)
 		*pc |= PCAN_USB_STATUSLEN_RTR;
 
@@ -858,8 +858,8 @@ static int pcan_usb_encode_msg(struct peak_usb_device *dev, struct sk_buff *skb,
 
 	/* can data */
 	if (!(cf->can_id & CAN_RTR_FLAG)) {
-		memcpy(pc, cf->data, cf->can_dlc);
-		pc += cf->can_dlc;
+		memcpy(pc, cf->data, cf->len);
+		pc += cf->len;
 	}
 
 	obuf[(*size)-1] = (u8)(stats->tx_packets & 0xff);
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
index 1233ef20646a..922280692a8f 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
@@ -581,7 +581,7 @@ static int pcan_usb_fd_decode_status(struct pcan_usb_fd_if *usb_if,
 	peak_usb_netif_rx(skb, &usb_if->time_ref, le32_to_cpu(sm->ts_low));
 
 	netdev->stats.rx_packets++;
-	netdev->stats.rx_bytes += cf->can_dlc;
+	netdev->stats.rx_bytes += cf->len;
 
 	return 0;
 }
@@ -737,7 +737,7 @@ static int pcan_usb_fd_encode_msg(struct peak_usb_device *dev,
 	struct pucan_tx_msg *tx_msg = (struct pucan_tx_msg *)obuf;
 	struct canfd_frame *cfd = (struct canfd_frame *)skb->data;
 	u16 tx_msg_size, tx_msg_flags;
-	u8 can_dlc;
+	u8 len;
 
 	if (cfd->len > CANFD_MAX_DLEN)
 		return -EINVAL;
@@ -756,7 +756,7 @@ static int pcan_usb_fd_encode_msg(struct peak_usb_device *dev,
 
 	if (can_is_canfd_skb(skb)) {
 		/* considering a CANFD frame */
-		can_dlc = can_len2dlc(cfd->len);
+		len = can_len2dlc(cfd->len);
 
 		tx_msg_flags |= PUCAN_MSG_EXT_DATA_LEN;
 
@@ -767,14 +767,14 @@ static int pcan_usb_fd_encode_msg(struct peak_usb_device *dev,
 			tx_msg_flags |= PUCAN_MSG_ERROR_STATE_IND;
 	} else {
 		/* CAND 2.0 frames */
-		can_dlc = cfd->len;
+		len = cfd->len;
 
 		if (cfd->can_id & CAN_RTR_FLAG)
 			tx_msg_flags |= PUCAN_MSG_RTR;
 	}
 
 	tx_msg->flags = cpu_to_le16(tx_msg_flags);
-	tx_msg->channel_dlc = PUCAN_MSG_CHANNEL_DLC(dev->ctrl_idx, can_dlc);
+	tx_msg->channel_dlc = PUCAN_MSG_CHANNEL_DLC(dev->ctrl_idx, len);
 	memcpy(tx_msg->d, cfd->data, cfd->len);
 
 	/* add null size message to tag the end (messages are 32-bits aligned)
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
index c7564773fb2b..275087c39602 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
@@ -532,7 +532,7 @@ static int pcan_usb_pro_handle_canmsg(struct pcan_usb_pro_interface *usb_if,
 		return -ENOMEM;
 
 	can_frame->can_id = le32_to_cpu(rx->id);
-	can_frame->can_dlc = rx->len & 0x0f;
+	can_frame->len = rx->len & 0x0f;
 
 	if (rx->flags & PCAN_USBPRO_EXT)
 		can_frame->can_id |= CAN_EFF_FLAG;
@@ -540,14 +540,14 @@ static int pcan_usb_pro_handle_canmsg(struct pcan_usb_pro_interface *usb_if,
 	if (rx->flags & PCAN_USBPRO_RTR)
 		can_frame->can_id |= CAN_RTR_FLAG;
 	else
-		memcpy(can_frame->data, rx->data, can_frame->can_dlc);
+		memcpy(can_frame->data, rx->data, can_frame->len);
 
 	hwts = skb_hwtstamps(skb);
 	peak_usb_get_ts_time(&usb_if->time_ref, le32_to_cpu(rx->ts32),
 			     &hwts->hwtstamp);
 
 	netdev->stats.rx_packets++;
-	netdev->stats.rx_bytes += can_frame->can_dlc;
+	netdev->stats.rx_bytes += can_frame->len;
 	netif_rx(skb);
 
 	return 0;
@@ -662,7 +662,7 @@ static int pcan_usb_pro_handle_error(struct pcan_usb_pro_interface *usb_if,
 	hwts = skb_hwtstamps(skb);
 	peak_usb_get_ts_time(&usb_if->time_ref, le32_to_cpu(er->ts32), &hwts->hwtstamp);
 	netdev->stats.rx_packets++;
-	netdev->stats.rx_bytes += can_frame->can_dlc;
+	netdev->stats.rx_bytes += can_frame->len;
 	netif_rx(skb);
 
 	return 0;
@@ -767,14 +767,14 @@ static int pcan_usb_pro_encode_msg(struct peak_usb_device *dev,
 
 	pcan_msg_init_empty(&usb_msg, obuf, *size);
 
-	if ((cf->can_id & CAN_RTR_FLAG) || (cf->can_dlc == 0))
+	if ((cf->can_id & CAN_RTR_FLAG) || (cf->len == 0))
 		data_type = PCAN_USBPRO_TXMSG0;
-	else if (cf->can_dlc <= 4)
+	else if (cf->len <= 4)
 		data_type = PCAN_USBPRO_TXMSG4;
 	else
 		data_type = PCAN_USBPRO_TXMSG8;
 
-	len = (dev->ctrl_idx << 4) | (cf->can_dlc & 0x0f);
+	len = (dev->ctrl_idx << 4) | (cf->len & 0x0f);
 
 	flags = 0;
 	if (cf->can_id & CAN_EFF_FLAG)
diff --git a/drivers/net/can/usb/ucan.c b/drivers/net/can/usb/ucan.c
index 072058c6f6e8..7d92da8954fe 100644
--- a/drivers/net/can/usb/ucan.c
+++ b/drivers/net/can/usb/ucan.c
@@ -614,15 +614,15 @@ static void ucan_rx_can_msg(struct ucan_priv *up, struct ucan_message_in *m)
 	cf->can_id = canid;
 
 	/* compute DLC taking RTR_FLAG into account */
-	cf->can_dlc = ucan_can_cc_dlc2len(&m->msg.can_msg, len);
+	cf->len = ucan_can_cc_dlc2len(&m->msg.can_msg, len);
 
 	/* copy the payload of non RTR frames */
 	if (!(cf->can_id & CAN_RTR_FLAG) || (cf->can_id & CAN_ERR_FLAG))
-		memcpy(cf->data, m->msg.can_msg.data, cf->can_dlc);
+		memcpy(cf->data, m->msg.can_msg.data, cf->len);
 
 	/* don't count error frames as real packets */
 	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 
 	/* pass it to Linux */
 	netif_rx(skb);
@@ -1078,15 +1078,15 @@ static struct urb *ucan_prepare_tx_urb(struct ucan_priv *up,
 		mlen = UCAN_OUT_HDR_SIZE +
 			offsetof(struct ucan_can_msg, dlc) +
 			sizeof(m->msg.can_msg.dlc);
-		m->msg.can_msg.dlc = cf->can_dlc;
+		m->msg.can_msg.dlc = cf->len;
 	} else {
 		mlen = UCAN_OUT_HDR_SIZE +
-			sizeof(m->msg.can_msg.id) + cf->can_dlc;
-		memcpy(m->msg.can_msg.data, cf->data, cf->can_dlc);
+			sizeof(m->msg.can_msg.id) + cf->len;
+		memcpy(m->msg.can_msg.data, cf->data, cf->len);
 	}
 	m->len = cpu_to_le16(mlen);
 
-	context->dlc = cf->can_dlc;
+	context->dlc = cf->len;
 
 	m->subtype = echo_index;
 
diff --git a/drivers/net/can/usb/usb_8dev.c b/drivers/net/can/usb/usb_8dev.c
index 216c58f8df6e..6517aaeb4bc0 100644
--- a/drivers/net/can/usb/usb_8dev.c
+++ b/drivers/net/can/usb/usb_8dev.c
@@ -449,7 +449,7 @@ static void usb_8dev_rx_err_msg(struct usb_8dev_priv *priv,
 	priv->bec.rxerr = rxerr;
 
 	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 	netif_rx(skb);
 }
 
@@ -470,7 +470,7 @@ static void usb_8dev_rx_can_msg(struct usb_8dev_priv *priv,
 			return;
 
 		cf->can_id = be32_to_cpu(msg->id);
-		cf->can_dlc = can_cc_dlc2len(msg->dlc & 0xF);
+		cf->len = can_cc_dlc2len(msg->dlc & 0xF);
 
 		if (msg->flags & USB_8DEV_EXTID)
 			cf->can_id |= CAN_EFF_FLAG;
@@ -478,10 +478,10 @@ static void usb_8dev_rx_can_msg(struct usb_8dev_priv *priv,
 		if (msg->flags & USB_8DEV_RTR)
 			cf->can_id |= CAN_RTR_FLAG;
 		else
-			memcpy(cf->data, msg->data, cf->can_dlc);
+			memcpy(cf->data, msg->data, cf->len);
 
 		stats->rx_packets++;
-		stats->rx_bytes += cf->can_dlc;
+		stats->rx_bytes += cf->len;
 		netif_rx(skb);
 
 		can_led_event(priv->netdev, CAN_LED_EVENT_RX);
@@ -637,8 +637,8 @@ static netdev_tx_t usb_8dev_start_xmit(struct sk_buff *skb,
 		msg->flags |= USB_8DEV_EXTID;
 
 	msg->id = cpu_to_be32(cf->can_id & CAN_ERR_MASK);
-	msg->dlc = cf->can_dlc;
-	memcpy(msg->data, cf->data, cf->can_dlc);
+	msg->dlc = cf->len;
+	memcpy(msg->data, cf->data, cf->len);
 	msg->end = USB_8DEV_DATA_END;
 
 	for (i = 0; i < MAX_TX_URBS; i++) {
@@ -656,7 +656,7 @@ static netdev_tx_t usb_8dev_start_xmit(struct sk_buff *skb,
 
 	context->priv = priv;
 	context->echo_index = i;
-	context->dlc = cf->can_dlc;
+	context->dlc = cf->len;
 
 	usb_fill_bulk_urb(urb, priv->udev,
 			  usb_sndbulkpipe(priv->udev, USB_8DEV_ENDP_DATA_TX),
diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index 73e8b1df1071..88831ce0f2f8 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -759,7 +759,7 @@ static int xcan_rx(struct net_device *ndev, int frame_base)
 				   XCAN_DLCR_DLC_SHIFT;
 
 	/* Change Xilinx CAN data length format to socketCAN data format */
-	cf->can_dlc = can_cc_dlc2len(dlc);
+	cf->len = can_cc_dlc2len(dlc);
 
 	/* Change Xilinx CAN ID format to socketCAN ID format */
 	if (id_xcan & XCAN_IDR_IDE_MASK) {
@@ -784,13 +784,13 @@ static int xcan_rx(struct net_device *ndev, int frame_base)
 
 	if (!(cf->can_id & CAN_RTR_FLAG)) {
 		/* Change Xilinx CAN data format to socketCAN data format */
-		if (cf->can_dlc > 0)
+		if (cf->len > 0)
 			*(__be32 *)(cf->data) = cpu_to_be32(data[0]);
-		if (cf->can_dlc > 4)
+		if (cf->len > 4)
 			*(__be32 *)(cf->data + 4) = cpu_to_be32(data[1]);
 	}
 
-	stats->rx_bytes += cf->can_dlc;
+	stats->rx_bytes += cf->len;
 	stats->rx_packets++;
 	netif_receive_skb(skb);
 
@@ -970,7 +970,7 @@ static void xcan_update_error_state_after_rxtx(struct net_device *ndev)
 			struct net_device_stats *stats = &ndev->stats;
 
 			stats->rx_packets++;
-			stats->rx_bytes += cf->can_dlc;
+			stats->rx_bytes += cf->len;
 			netif_rx(skb);
 		}
 	}
diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h
index 802606e36b58..77da061c21c9 100644
--- a/include/linux/can/dev.h
+++ b/include/linux/can/dev.h
@@ -185,8 +185,8 @@ static inline void can_set_static_ctrlmode(struct net_device *dev,
 		dev->mtu = CANFD_MTU;
 }
 
-/* get data length from can_dlc with sanitized can_dlc */
-u8 can_dlc2len(u8 can_dlc);
+/* get data length from raw data length code (DLC) */
+u8 can_dlc2len(u8 dlc);
 
 /* map the sanitized data length to an appropriate data length code */
 u8 can_len2dlc(u8 len);
diff --git a/net/can/af_can.c b/net/can/af_can.c
index 5d124c155904..963bd7145517 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -888,7 +888,7 @@ static __init int can_init(void)
 	int err;
 
 	/* check for correct padding to be able to use the structs similarly */
-	BUILD_BUG_ON(offsetof(struct can_frame, can_dlc) !=
+	BUILD_BUG_ON(offsetof(struct can_frame, len) !=
 		     offsetof(struct canfd_frame, len) ||
 		     offsetof(struct can_frame, data) !=
 		     offsetof(struct canfd_frame, data));
diff --git a/net/can/gw.c b/net/can/gw.c
index 6b790b6ff8d2..de5e8859ec9b 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -207,7 +207,7 @@ static void canframecpy(struct canfd_frame *dst, struct can_frame *src)
 	 */
 
 	dst->can_id = src->can_id;
-	dst->len = src->can_dlc;
+	dst->len = src->len;
 	*(u64 *)dst->data = *(u64 *)src->data;
 }
 
diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c
index 137054bff9ec..bb914d8b4216 100644
--- a/net/can/j1939/main.c
+++ b/net/can/j1939/main.c
@@ -62,7 +62,7 @@ static void j1939_can_recv(struct sk_buff *iskb, void *data)
 	skb_pull(skb, J1939_CAN_HDR);
 
 	/* fix length, set to dlc, with 8 maximum */
-	skb_trim(skb, min_t(uint8_t, cf->can_dlc, 8));
+	skb_trim(skb, min_t(uint8_t, cf->len, 8));
 
 	/* set addr */
 	skcb = j1939_skb_to_cb(skb);
@@ -335,7 +335,7 @@ int j1939_send_one(struct j1939_priv *priv, struct sk_buff *skb)
 		canid |= skcb->addr.da << 8;
 
 	cf->can_id = canid;
-	cf->can_dlc = dlc;
+	cf->len = dlc;
 
 	return can_send(skb, 1);
 
-- 
cgit v1.2.3


From 3ab4ce0d6fa8c93d41df4a74ec8d2c9198be2109 Mon Sep 17 00:00:00 2001
From: Oliver Hartkopp <socketcan@hartkopp.net>
Date: Tue, 10 Nov 2020 11:18:49 +0100
Subject: can: rename CAN FD related can_len2dlc and can_dlc2len helpers

The helper functions can_len2dlc and can_dlc2len are only relevant for
CAN FD data length code (DLC) conversion.

To fit the introduced can_cc_dlc2len for Classical CAN we rename:

can_dlc2len -> can_fd_dlc2len to get the payload length from the DLC
can_len2dlc -> can_fd_len2dlc to get the DLC from the payload length

Suggested-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Link: https://lore.kernel.org/r/20201110101852.1973-6-socketcan@hartkopp.net
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 Documentation/networking/can.rst                  | 2 +-
 drivers/net/can/dev.c                             | 8 ++++----
 drivers/net/can/flexcan.c                         | 4 ++--
 drivers/net/can/ifi_canfd/ifi_canfd.c             | 4 ++--
 drivers/net/can/kvaser_pciefd.c                   | 6 +++---
 drivers/net/can/m_can/m_can.c                     | 6 +++---
 drivers/net/can/peak_canfd/peak_canfd.c           | 4 ++--
 drivers/net/can/rcar/rcar_canfd.c                 | 4 ++--
 drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c    | 8 ++++----
 drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c | 6 +++---
 drivers/net/can/usb/peak_usb/pcan_usb_fd.c        | 4 ++--
 drivers/net/can/xilinx_can.c                      | 4 ++--
 include/linux/can/dev.h                           | 4 ++--
 13 files changed, 32 insertions(+), 32 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/networking/can.rst b/Documentation/networking/can.rst
index ff05cbd05e0d..4895b0dd2714 100644
--- a/Documentation/networking/can.rst
+++ b/Documentation/networking/can.rst
@@ -1332,7 +1332,7 @@ layer is a plain value from 0 .. 64 instead of the CAN 'data length code'.
 The data length code was a 1:1 mapping to the payload length in the legacy
 CAN frames anyway. The payload length to the bus-relevant DLC mapping is
 only performed inside the CAN drivers, preferably with the helper
-functions can_dlc2len() and can_len2dlc().
+functions can_fd_dlc2len() and can_fd_len2dlc().
 
 The CAN netdevice driver capabilities can be distinguished by the network
 devices maximum transfer unit (MTU)::
diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index 806e8b646b12..3486704c8a95 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -31,11 +31,11 @@ static const u8 dlc2len[] = {0, 1, 2, 3, 4, 5, 6, 7,
 			     8, 12, 16, 20, 24, 32, 48, 64};
 
 /* get data length from raw data length code (DLC) */
-u8 can_dlc2len(u8 dlc)
+u8 can_fd_dlc2len(u8 dlc)
 {
 	return dlc2len[dlc & 0x0F];
 }
-EXPORT_SYMBOL_GPL(can_dlc2len);
+EXPORT_SYMBOL_GPL(can_fd_dlc2len);
 
 static const u8 len2dlc[] = {0, 1, 2, 3, 4, 5, 6, 7, 8,		/* 0 - 8 */
 			     9, 9, 9, 9,			/* 9 - 12 */
@@ -49,14 +49,14 @@ static const u8 len2dlc[] = {0, 1, 2, 3, 4, 5, 6, 7, 8,		/* 0 - 8 */
 			     15, 15, 15, 15, 15, 15, 15, 15};	/* 57 - 64 */
 
 /* map the sanitized data length to an appropriate data length code */
-u8 can_len2dlc(u8 len)
+u8 can_fd_len2dlc(u8 len)
 {
 	if (unlikely(len > 64))
 		return 0xF;
 
 	return len2dlc[len];
 }
-EXPORT_SYMBOL_GPL(can_len2dlc);
+EXPORT_SYMBOL_GPL(can_fd_len2dlc);
 
 #ifdef CONFIG_CAN_CALC_BITTIMING
 #define CAN_CALC_MAX_ERROR 50 /* in one-tenth of a percent */
diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index 985569f946e5..6f3555381230 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -746,7 +746,7 @@ static netdev_tx_t flexcan_start_xmit(struct sk_buff *skb, struct net_device *de
 	struct canfd_frame *cfd = (struct canfd_frame *)skb->data;
 	u32 can_id;
 	u32 data;
-	u32 ctrl = FLEXCAN_MB_CODE_TX_DATA | ((can_len2dlc(cfd->len)) << 16);
+	u32 ctrl = FLEXCAN_MB_CODE_TX_DATA | ((can_fd_len2dlc(cfd->len)) << 16);
 	int i;
 
 	if (can_dropped_invalid_skb(dev, skb))
@@ -1000,7 +1000,7 @@ static struct sk_buff *flexcan_mailbox_read(struct can_rx_offload *offload,
 		cfd->can_id = (reg_id >> 18) & CAN_SFF_MASK;
 
 	if (reg_ctrl & FLEXCAN_MB_CNT_EDL) {
-		cfd->len = can_dlc2len((reg_ctrl >> 16) & 0xf);
+		cfd->len = can_fd_dlc2len((reg_ctrl >> 16) & 0xf);
 
 		if (reg_ctrl & FLEXCAN_MB_CNT_BRS)
 			cfd->flags |= CANFD_BRS;
diff --git a/drivers/net/can/ifi_canfd/ifi_canfd.c b/drivers/net/can/ifi_canfd/ifi_canfd.c
index 3df55b0e4ef3..86b0e1406a21 100644
--- a/drivers/net/can/ifi_canfd/ifi_canfd.c
+++ b/drivers/net/can/ifi_canfd/ifi_canfd.c
@@ -271,7 +271,7 @@ static void ifi_canfd_read_fifo(struct net_device *ndev)
 	dlc = (rxdlc >> IFI_CANFD_RXFIFO_DLC_DLC_OFFSET) &
 	      IFI_CANFD_RXFIFO_DLC_DLC_MASK;
 	if (rxdlc & IFI_CANFD_RXFIFO_DLC_EDL)
-		cf->len = can_dlc2len(dlc);
+		cf->len = can_fd_dlc2len(dlc);
 	else
 		cf->len = can_cc_dlc2len(dlc);
 
@@ -900,7 +900,7 @@ static netdev_tx_t ifi_canfd_start_xmit(struct sk_buff *skb,
 		txid = cf->can_id & CAN_SFF_MASK;
 	}
 
-	txdlc = can_len2dlc(cf->len);
+	txdlc = can_fd_len2dlc(cf->len);
 	if ((priv->can.ctrlmode & CAN_CTRLMODE_FD) && can_is_canfd_skb(skb)) {
 		txdlc |= IFI_CANFD_TXFIFO_DLC_EDL;
 		if (cf->flags & CANFD_BRS)
diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c
index de268a344fcf..1bafa614950e 100644
--- a/drivers/net/can/kvaser_pciefd.c
+++ b/drivers/net/can/kvaser_pciefd.c
@@ -740,7 +740,7 @@ static int kvaser_pciefd_prepare_tx_packet(struct kvaser_pciefd_tx_packet *p,
 		p->header[0] |= KVASER_PCIEFD_RPACKET_IDE;
 
 	p->header[0] |= cf->can_id & CAN_EFF_MASK;
-	p->header[1] |= can_len2dlc(cf->len) << KVASER_PCIEFD_RPACKET_DLC_SHIFT;
+	p->header[1] |= can_fd_len2dlc(cf->len) << KVASER_PCIEFD_RPACKET_DLC_SHIFT;
 	p->header[1] |= KVASER_PCIEFD_TPACKET_AREQ;
 
 	if (can_is_canfd_skb(skb)) {
@@ -1174,7 +1174,7 @@ static int kvaser_pciefd_handle_data_packet(struct kvaser_pciefd *pcie,
 	if (p->header[0] & KVASER_PCIEFD_RPACKET_IDE)
 		cf->can_id |= CAN_EFF_FLAG;
 
-	cf->len = can_dlc2len(p->header[1] >> KVASER_PCIEFD_RPACKET_DLC_SHIFT);
+	cf->len = can_fd_dlc2len(p->header[1] >> KVASER_PCIEFD_RPACKET_DLC_SHIFT);
 
 	if (p->header[0] & KVASER_PCIEFD_RPACKET_RTR)
 		cf->can_id |= CAN_RTR_FLAG;
@@ -1600,7 +1600,7 @@ static int kvaser_pciefd_read_packet(struct kvaser_pciefd *pcie, int *start_pos,
 		if (!(p->header[0] & KVASER_PCIEFD_RPACKET_RTR)) {
 			u8 data_len;
 
-			data_len = can_dlc2len(p->header[1] >>
+			data_len = can_fd_dlc2len(p->header[1] >>
 					       KVASER_PCIEFD_RPACKET_DLC_SHIFT);
 			pos += DIV_ROUND_UP(data_len, 4);
 		}
diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index b7df90ceee4b..a345e22f545e 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -457,7 +457,7 @@ static void m_can_read_fifo(struct net_device *dev, u32 rxfs)
 	}
 
 	if (dlc & RX_BUF_FDF)
-		cf->len = can_dlc2len((dlc >> 16) & 0x0F);
+		cf->len = can_fd_dlc2len((dlc >> 16) & 0x0F);
 	else
 		cf->len = can_cc_dlc2len((dlc >> 16) & 0x0F);
 
@@ -1489,7 +1489,7 @@ static netdev_tx_t m_can_tx_handler(struct m_can_classdev *cdev)
 		/* message ram configuration */
 		m_can_fifo_write(cdev, 0, M_CAN_FIFO_ID, id);
 		m_can_fifo_write(cdev, 0, M_CAN_FIFO_DLC,
-				 can_len2dlc(cf->len) << 16);
+				 can_fd_len2dlc(cf->len) << 16);
 
 		for (i = 0; i < cf->len; i += 4)
 			m_can_fifo_write(cdev, 0,
@@ -1557,7 +1557,7 @@ static netdev_tx_t m_can_tx_handler(struct m_can_classdev *cdev)
 		m_can_fifo_write(cdev, putidx, M_CAN_FIFO_DLC,
 				 ((putidx << TX_BUF_MM_SHIFT) &
 				  TX_BUF_MM_MASK) |
-				 (can_len2dlc(cf->len) << 16) |
+				 (can_fd_len2dlc(cf->len) << 16) |
 				 fdflags | TX_BUF_EFC);
 
 		for (i = 0; i < cf->len; i += 4)
diff --git a/drivers/net/can/peak_canfd/peak_canfd.c b/drivers/net/can/peak_canfd/peak_canfd.c
index fff3a35276aa..c5334b0c3038 100644
--- a/drivers/net/can/peak_canfd/peak_canfd.c
+++ b/drivers/net/can/peak_canfd/peak_canfd.c
@@ -257,7 +257,7 @@ static int pucan_handle_can_rx(struct peak_canfd_priv *priv,
 	u8 cf_len;
 
 	if (rx_msg_flags & PUCAN_MSG_EXT_DATA_LEN)
-		cf_len = can_dlc2len(pucan_msg_get_dlc(msg));
+		cf_len = can_fd_dlc2len(pucan_msg_get_dlc(msg));
 	else
 		cf_len = can_cc_dlc2len(pucan_msg_get_dlc(msg));
 
@@ -682,7 +682,7 @@ static netdev_tx_t peak_canfd_start_xmit(struct sk_buff *skb,
 
 	if (can_is_canfd_skb(skb)) {
 		/* CAN FD frame format */
-		len = can_len2dlc(cf->len);
+		len = can_fd_len2dlc(cf->len);
 
 		msg_flags |= PUCAN_MSG_EXT_DATA_LEN;
 
diff --git a/drivers/net/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c
index 86c6cbdb7e53..2778ed5c61d1 100644
--- a/drivers/net/can/rcar/rcar_canfd.c
+++ b/drivers/net/can/rcar/rcar_canfd.c
@@ -1357,7 +1357,7 @@ static netdev_tx_t rcar_canfd_start_xmit(struct sk_buff *skb,
 	if (cf->can_id & CAN_RTR_FLAG)
 		id |= RCANFD_CFID_CFRTR;
 
-	dlc = RCANFD_CFPTR_CFDLC(can_len2dlc(cf->len));
+	dlc = RCANFD_CFPTR_CFDLC(can_fd_len2dlc(cf->len));
 
 	if (priv->can.ctrlmode & CAN_CTRLMODE_FD) {
 		rcar_canfd_write(priv->base,
@@ -1446,7 +1446,7 @@ static void rcar_canfd_rx_pkt(struct rcar_canfd_channel *priv)
 
 	if (priv->can.ctrlmode & CAN_CTRLMODE_FD) {
 		if (sts & RCANFD_RFFDSTS_RFFDF)
-			cf->len = can_dlc2len(RCANFD_RFPTR_RFDLC(dlc));
+			cf->len = can_fd_dlc2len(RCANFD_RFPTR_RFDLC(dlc));
 		else
 			cf->len = can_cc_dlc2len(RCANFD_RFPTR_RFDLC(dlc));
 
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
index 3bac7274ee5b..afa8cfc729b5 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
@@ -1405,7 +1405,7 @@ mcp251xfd_hw_rx_obj_to_skb(const struct mcp251xfd_priv *priv,
 			cfd->flags |= CANFD_BRS;
 
 		dlc = FIELD_GET(MCP251XFD_OBJ_FLAGS_DLC, hw_rx_obj->flags);
-		cfd->len = can_dlc2len(dlc);
+		cfd->len = can_fd_dlc2len(dlc);
 	} else {
 		if (hw_rx_obj->flags & MCP251XFD_OBJ_FLAGS_RTR)
 			cfd->can_id |= CAN_RTR_FLAG;
@@ -2244,7 +2244,7 @@ mcp251xfd_tx_obj_from_skb(const struct mcp251xfd_priv *priv,
 	 * harm, only the lower 7 bits will be transferred into the
 	 * TEF object.
 	 */
-	dlc = can_len2dlc(cfd->len);
+	dlc = can_fd_len2dlc(cfd->len);
 	flags |= FIELD_PREP(MCP251XFD_OBJ_FLAGS_SEQ_MCP2518FD_MASK, seq) |
 		FIELD_PREP(MCP251XFD_OBJ_FLAGS_DLC, dlc);
 
@@ -2273,7 +2273,7 @@ mcp251xfd_tx_obj_from_skb(const struct mcp251xfd_priv *priv,
 
 	/* Clear data at end of CAN frame */
 	offset = round_down(cfd->len, sizeof(u32));
-	len = round_up(can_dlc2len(dlc), sizeof(u32)) - offset;
+	len = round_up(can_fd_dlc2len(dlc), sizeof(u32)) - offset;
 	if (MCP251XFD_SANITIZE_CAN && len)
 		memset(hw_tx_obj->data + offset, 0x0, len);
 	memcpy(hw_tx_obj->data, cfd->data, cfd->len);
@@ -2281,7 +2281,7 @@ mcp251xfd_tx_obj_from_skb(const struct mcp251xfd_priv *priv,
 	/* Number of bytes to be written into the RAM of the controller */
 	len = sizeof(hw_tx_obj->id) + sizeof(hw_tx_obj->flags);
 	if (MCP251XFD_SANITIZE_CAN)
-		len += round_up(can_dlc2len(dlc), sizeof(u32));
+		len += round_up(can_fd_dlc2len(dlc), sizeof(u32));
 	else
 		len += round_up(cfd->len, sizeof(u32));
 
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
index c6d5f3f656c3..107b205b77ab 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
@@ -1120,7 +1120,7 @@ static void kvaser_usb_hydra_tx_acknowledge(const struct kvaser_usb *dev,
 		struct net_device_stats *stats = &priv->netdev->stats;
 
 		stats->tx_packets++;
-		stats->tx_bytes += can_dlc2len(context->dlc);
+		stats->tx_bytes += can_fd_dlc2len(context->dlc);
 	}
 
 	spin_lock_irqsave(&priv->tx_contexts_lock, irq_flags);
@@ -1251,7 +1251,7 @@ static void kvaser_usb_hydra_rx_msg_ext(const struct kvaser_usb *dev,
 		kvaser_usb_can_rx_over_error(priv->netdev);
 
 	if (flags & KVASER_USB_HYDRA_CF_FLAG_FDF) {
-		cf->len = can_dlc2len(dlc);
+		cf->len = can_fd_dlc2len(dlc);
 		if (flags & KVASER_USB_HYDRA_CF_FLAG_BRS)
 			cf->flags |= CANFD_BRS;
 		if (flags & KVASER_USB_HYDRA_CF_FLAG_ESI)
@@ -1351,7 +1351,7 @@ kvaser_usb_hydra_frame_to_cmd_ext(const struct kvaser_usb_net_priv *priv,
 	struct kvaser_usb *dev = priv->dev;
 	struct kvaser_cmd_ext *cmd;
 	struct canfd_frame *cf = (struct canfd_frame *)skb->data;
-	u8 dlc = can_len2dlc(cf->len);
+	u8 dlc = can_fd_len2dlc(cf->len);
 	u8 nbr_of_bytes = cf->len;
 	u32 flags;
 	u32 id;
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
index 922280692a8f..761e78d8e647 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
@@ -492,7 +492,7 @@ static int pcan_usb_fd_decode_canmsg(struct pcan_usb_fd_if *usb_if,
 		if (rx_msg_flags & PUCAN_MSG_ERROR_STATE_IND)
 			cfd->flags |= CANFD_ESI;
 
-		cfd->len = can_dlc2len(pucan_msg_get_dlc(rm));
+		cfd->len = can_fd_dlc2len(pucan_msg_get_dlc(rm));
 	} else {
 		/* CAN 2.0 frame case */
 		skb = alloc_can_skb(netdev, (struct can_frame **)&cfd);
@@ -756,7 +756,7 @@ static int pcan_usb_fd_encode_msg(struct peak_usb_device *dev,
 
 	if (can_is_canfd_skb(skb)) {
 		/* considering a CANFD frame */
-		len = can_len2dlc(cfd->len);
+		len = can_fd_len2dlc(cfd->len);
 
 		tx_msg_flags |= PUCAN_MSG_EXT_DATA_LEN;
 
diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index 88831ce0f2f8..3f54edee92eb 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -583,7 +583,7 @@ static void xcan_write_frame(struct net_device *ndev, struct sk_buff *skb,
 			id |= XCAN_IDR_SRR_MASK;
 	}
 
-	dlc = can_len2dlc(cf->len) << XCAN_DLCR_DLC_SHIFT;
+	dlc = can_fd_len2dlc(cf->len) << XCAN_DLCR_DLC_SHIFT;
 	if (can_is_canfd_skb(skb)) {
 		if (cf->flags & CANFD_BRS)
 			dlc |= XCAN_DLCR_BRS_MASK;
@@ -832,7 +832,7 @@ static int xcanfd_rx(struct net_device *ndev, int frame_base)
 	 * format
 	 */
 	if (dlc & XCAN_DLCR_EDL_MASK)
-		cf->len = can_dlc2len((dlc & XCAN_DLCR_DLC_MASK) >>
+		cf->len = can_fd_dlc2len((dlc & XCAN_DLCR_DLC_MASK) >>
 				  XCAN_DLCR_DLC_SHIFT);
 	else
 		cf->len = can_cc_dlc2len((dlc & XCAN_DLCR_DLC_MASK) >>
diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h
index 77da061c21c9..e767a96ae075 100644
--- a/include/linux/can/dev.h
+++ b/include/linux/can/dev.h
@@ -186,10 +186,10 @@ static inline void can_set_static_ctrlmode(struct net_device *dev,
 }
 
 /* get data length from raw data length code (DLC) */
-u8 can_dlc2len(u8 dlc);
+u8 can_fd_dlc2len(u8 dlc);
 
 /* map the sanitized data length to an appropriate data length code */
-u8 can_len2dlc(u8 len);
+u8 can_fd_len2dlc(u8 len);
 
 struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max,
 				    unsigned int txqs, unsigned int rxqs);
-- 
cgit v1.2.3


From e8e73562ce0b24d691ad35df3de34b324248458f Mon Sep 17 00:00:00 2001
From: Oliver Hartkopp <socketcan@hartkopp.net>
Date: Tue, 10 Nov 2020 16:49:12 +0100
Subject: can: drivers: introduce helpers to access Classical CAN DLC values

This patch adds the following helper to functions to access Classical CAN DLC
values.

can_get_cc_dlc(): get the data length code for Classical CAN raw DLC access
can_frame_set_cc_len(): set len and len8_dlc value for Classical CAN raw DLC access

Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Link: https://lore.kernel.org/r/20201110154913.1404582-2-mkl@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 include/linux/can/dev.h | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h
index e767a96ae075..197a79535cc2 100644
--- a/include/linux/can/dev.h
+++ b/include/linux/can/dev.h
@@ -170,6 +170,31 @@ static inline bool can_is_canfd_skb(const struct sk_buff *skb)
 	return skb->len == CANFD_MTU;
 }
 
+/* helper to get the data length code (DLC) for Classical CAN raw DLC access */
+static inline u8 can_get_cc_dlc(const struct can_frame *cf, const u32 ctrlmode)
+{
+	/* return len8_dlc as dlc value only if all conditions apply */
+	if ((ctrlmode & CAN_CTRLMODE_CC_LEN8_DLC) &&
+	    (cf->len == CAN_MAX_DLEN) &&
+	    (cf->len8_dlc > CAN_MAX_DLEN && cf->len8_dlc <= CAN_MAX_RAW_DLC))
+		return cf->len8_dlc;
+
+	/* return the payload length as dlc value */
+	return cf->len;
+}
+
+/* helper to set len and len8_dlc value for Classical CAN raw DLC access */
+static inline void can_frame_set_cc_len(struct can_frame *cf, const u8 dlc,
+					const u32 ctrlmode)
+{
+	/* the caller already ensured that dlc is a value from 0 .. 15 */
+	if (ctrlmode & CAN_CTRLMODE_CC_LEN8_DLC && dlc > CAN_MAX_DLEN)
+		cf->len8_dlc = dlc;
+
+	/* limit the payload length 'len' to CAN_MAX_DLEN */
+	cf->len = can_cc_dlc2len(dlc);
+}
+
 /* helper to define static CAN controller features at device creation time */
 static inline void can_set_static_ctrlmode(struct net_device *dev,
 					   u32 static_mode)
-- 
cgit v1.2.3


From 757055ae8dedf5333af17b3b5b4b70ba9bc9da4e Mon Sep 17 00:00:00 2001
From: Petr Mladek <pmladek@suse.com>
Date: Wed, 11 Nov 2020 14:54:49 +0100
Subject: init/console: Use ttynull as a fallback when there is no console

stdin, stdout, and stderr standard I/O stream are created for the init
process. They are not available when there is no console registered
for /dev/console. It might lead to a crash when the init process
tries to use them, see the commit 48021f98130880dd742 ("printk: handle
blank console arguments passed in.").

Normally, ttySX and ttyX consoles are used as a fallback when no consoles
are defined via the command line, device tree, or SPCR. But there
will be no console registered when an invalid console name is configured
or when the configured consoles do not exist on the system.

Users even try to avoid the console intentionally, for example,
by using console="" or console=null. It is used on production
systems where the serial port or terminal are not visible to
users. Pushing messages to these consoles would just unnecessary
slowdown the system.

Make sure that stdin, stdout, stderr, and /dev/console are always
available by a fallback to the existing ttynull driver. It has
been implemented for exactly this purpose but it was used only
when explicitly configured.

Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Tested-by: Guenter Roeck <linux@roeck-us.net>
Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Signed-off-by: Petr Mladek <pmladek@suse.com>
Link: https://lore.kernel.org/r/20201111135450.11214-2-pmladek@suse.com
---
 drivers/tty/Kconfig     | 14 --------------
 drivers/tty/Makefile    |  3 +--
 drivers/tty/ttynull.c   | 18 ++++++++++++++++++
 include/linux/console.h |  3 +++
 init/main.c             | 10 ++++++++--
 5 files changed, 30 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/Kconfig b/drivers/tty/Kconfig
index 93fd984eb2f5..ca359bbd62f5 100644
--- a/drivers/tty/Kconfig
+++ b/drivers/tty/Kconfig
@@ -428,20 +428,6 @@ config MIPS_EJTAG_FDC_KGDB_CHAN
 	help
 	  FDC channel number to use for KGDB.
 
-config NULL_TTY
-	tristate "NULL TTY driver"
-	help
-	  Say Y here if you want a NULL TTY which simply discards messages.
-
-	  This is useful to allow userspace applications which expect a console
-	  device to work without modifications even when no console is
-	  available or desired.
-
-	  In order to use this driver, you should redirect the console to this
-	  TTY, or boot the kernel with console=ttynull.
-
-	  If unsure, say N.
-
 config TRACE_ROUTER
 	tristate "Trace data router for MIPI P1149.7 cJTAG standard"
 	depends on TRACE_SINK
diff --git a/drivers/tty/Makefile b/drivers/tty/Makefile
index 020b1cd9294f..f6b6bee0422d 100644
--- a/drivers/tty/Makefile
+++ b/drivers/tty/Makefile
@@ -2,7 +2,7 @@
 obj-$(CONFIG_TTY)		+= tty_io.o n_tty.o tty_ioctl.o tty_ldisc.o \
 				   tty_buffer.o tty_port.o tty_mutex.o \
 				   tty_ldsem.o tty_baudrate.o tty_jobctrl.o \
-				   n_null.o
+				   n_null.o ttynull.o
 obj-$(CONFIG_LEGACY_PTYS)	+= pty.o
 obj-$(CONFIG_UNIX98_PTYS)	+= pty.o
 obj-$(CONFIG_AUDIT)		+= tty_audit.o
@@ -25,7 +25,6 @@ obj-$(CONFIG_ISI)		+= isicom.o
 obj-$(CONFIG_MOXA_INTELLIO)	+= moxa.o
 obj-$(CONFIG_MOXA_SMARTIO)	+= mxser.o
 obj-$(CONFIG_NOZOMI)		+= nozomi.o
-obj-$(CONFIG_NULL_TTY)	        += ttynull.o
 obj-$(CONFIG_ROCKETPORT)	+= rocket.o
 obj-$(CONFIG_SYNCLINK_GT)	+= synclink_gt.o
 obj-$(CONFIG_SYNCLINKMP)	+= synclinkmp.o
diff --git a/drivers/tty/ttynull.c b/drivers/tty/ttynull.c
index 17f05b7eb6d3..eced70ec54e1 100644
--- a/drivers/tty/ttynull.c
+++ b/drivers/tty/ttynull.c
@@ -2,6 +2,13 @@
 /*
  * Copyright (C) 2019 Axis Communications AB
  *
+ * The console is useful for userspace applications which expect a console
+ * device to work without modifications even when no console is available
+ * or desired.
+ *
+ * In order to use this driver, you should redirect the console to this
+ * TTY, or boot the kernel with console=ttynull.
+ *
  * Based on ttyprintk.c:
  *  Copyright (C) 2010 Samo Pogacnik
  */
@@ -59,6 +66,17 @@ static struct console ttynull_console = {
 	.device = ttynull_device,
 };
 
+void __init register_ttynull_console(void)
+{
+	if (!ttynull_driver)
+		return;
+
+	if (add_preferred_console(ttynull_console.name, 0, NULL))
+		return;
+
+	register_console(&ttynull_console);
+}
+
 static int __init ttynull_init(void)
 {
 	struct tty_driver *driver;
diff --git a/include/linux/console.h b/include/linux/console.h
index 4b1e26c4cb42..9c662e41cde5 100644
--- a/include/linux/console.h
+++ b/include/linux/console.h
@@ -187,9 +187,12 @@ extern int braille_register_console(struct console *, int index,
 extern int braille_unregister_console(struct console *);
 #ifdef CONFIG_TTY
 extern void console_sysfs_notify(void);
+extern void register_ttynull_console(void);
 #else
 static inline void console_sysfs_notify(void)
 { }
+static inline void register_ttynull_console(void)
+{ }
 #endif
 extern bool console_suspend_enabled;
 
diff --git a/init/main.c b/init/main.c
index 1af84337cb18..b3fcf446f99e 100644
--- a/init/main.c
+++ b/init/main.c
@@ -1468,8 +1468,14 @@ void __init console_on_rootfs(void)
 	struct file *file = filp_open("/dev/console", O_RDWR, 0);
 
 	if (IS_ERR(file)) {
-		pr_err("Warning: unable to open an initial console.\n");
-		return;
+		pr_err("Warning: unable to open an initial console. Fallback to ttynull.\n");
+		register_ttynull_console();
+
+		file = filp_open("/dev/console", O_RDWR, 0);
+		if (IS_ERR(file)) {
+			pr_err("Warning: Failed to add ttynull console. No stdin, stdout, and stderr for the init process!\n");
+			return;
+		}
 	}
 	init_dup(file);
 	init_dup(file);
-- 
cgit v1.2.3


From 2add5cacff3531e54c50b0832128299faa9f0563 Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Thu, 19 Nov 2020 19:10:47 +0000
Subject: firmware: arm_scmi: Add voltage domain management protocol support

SCMI v3.0 introduces voltage domain protocol which provides commands to:
 - Discover the voltage levels supported by a domain
 - Get the configuration and voltage level of a domain
 - Set the configuration and voltage level of a domain

Let us add support for the same.

Link: https://lore.kernel.org/r/20201119191051.46363-2-cristian.marussi@arm.com
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_scmi/Makefile  |   2 +-
 drivers/firmware/arm_scmi/common.h  |   1 +
 drivers/firmware/arm_scmi/driver.c  |   2 +
 drivers/firmware/arm_scmi/voltage.c | 380 ++++++++++++++++++++++++++++++++++++
 include/linux/scmi_protocol.h       |  64 ++++++
 5 files changed, 448 insertions(+), 1 deletion(-)
 create mode 100644 drivers/firmware/arm_scmi/voltage.c

(limited to 'include/linux')

diff --git a/drivers/firmware/arm_scmi/Makefile b/drivers/firmware/arm_scmi/Makefile
index bc0d54f8e861..6a2ef63306d6 100644
--- a/drivers/firmware/arm_scmi/Makefile
+++ b/drivers/firmware/arm_scmi/Makefile
@@ -4,7 +4,7 @@ scmi-driver-y = driver.o notify.o
 scmi-transport-y = shmem.o
 scmi-transport-$(CONFIG_MAILBOX) += mailbox.o
 scmi-transport-$(CONFIG_HAVE_ARM_SMCCC_DISCOVERY) += smc.o
-scmi-protocols-y = base.o clock.o perf.o power.o reset.o sensors.o system.o
+scmi-protocols-y = base.o clock.o perf.o power.o reset.o sensors.o system.o voltage.o
 scmi-module-objs := $(scmi-bus-y) $(scmi-driver-y) $(scmi-protocols-y) \
 		    $(scmi-transport-y)
 obj-$(CONFIG_ARM_SCMI_PROTOCOL) += scmi-module.o
diff --git a/drivers/firmware/arm_scmi/common.h b/drivers/firmware/arm_scmi/common.h
index 65063fa948d4..c0fb45e7c3e8 100644
--- a/drivers/firmware/arm_scmi/common.h
+++ b/drivers/firmware/arm_scmi/common.h
@@ -169,6 +169,7 @@ DECLARE_SCMI_REGISTER_UNREGISTER(perf);
 DECLARE_SCMI_REGISTER_UNREGISTER(power);
 DECLARE_SCMI_REGISTER_UNREGISTER(reset);
 DECLARE_SCMI_REGISTER_UNREGISTER(sensors);
+DECLARE_SCMI_REGISTER_UNREGISTER(voltage);
 DECLARE_SCMI_REGISTER_UNREGISTER(system);
 
 #define DEFINE_SCMI_PROTOCOL_REGISTER_UNREGISTER(id, name) \
diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c
index 3dfd8b6a0ebf..ada35e63feae 100644
--- a/drivers/firmware/arm_scmi/driver.c
+++ b/drivers/firmware/arm_scmi/driver.c
@@ -946,6 +946,7 @@ static int __init scmi_driver_init(void)
 	scmi_power_register();
 	scmi_reset_register();
 	scmi_sensors_register();
+	scmi_voltage_register();
 	scmi_system_register();
 
 	return platform_driver_register(&scmi_driver);
@@ -961,6 +962,7 @@ static void __exit scmi_driver_exit(void)
 	scmi_power_unregister();
 	scmi_reset_unregister();
 	scmi_sensors_unregister();
+	scmi_voltage_unregister();
 	scmi_system_unregister();
 
 	platform_driver_unregister(&scmi_driver);
diff --git a/drivers/firmware/arm_scmi/voltage.c b/drivers/firmware/arm_scmi/voltage.c
new file mode 100644
index 000000000000..e794e4349ae6
--- /dev/null
+++ b/drivers/firmware/arm_scmi/voltage.c
@@ -0,0 +1,380 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * System Control and Management Interface (SCMI) Voltage Protocol
+ *
+ * Copyright (C) 2020 ARM Ltd.
+ */
+
+#include <linux/scmi_protocol.h>
+
+#include "common.h"
+
+#define VOLTAGE_DOMS_NUM_MASK		GENMASK(15, 0)
+#define REMAINING_LEVELS_MASK		GENMASK(31, 16)
+#define RETURNED_LEVELS_MASK		GENMASK(11, 0)
+
+enum scmi_voltage_protocol_cmd {
+	VOLTAGE_DOMAIN_ATTRIBUTES = 0x3,
+	VOLTAGE_DESCRIBE_LEVELS = 0x4,
+	VOLTAGE_CONFIG_SET = 0x5,
+	VOLTAGE_CONFIG_GET = 0x6,
+	VOLTAGE_LEVEL_SET = 0x7,
+	VOLTAGE_LEVEL_GET = 0x8,
+};
+
+#define NUM_VOLTAGE_DOMAINS(x)	((u16)(FIELD_GET(VOLTAGE_DOMS_NUM_MASK, (x))))
+
+struct scmi_msg_resp_domain_attributes {
+	__le32 attr;
+	u8 name[SCMI_MAX_STR_SIZE];
+};
+
+struct scmi_msg_cmd_describe_levels {
+	__le32 domain_id;
+	__le32 level_index;
+};
+
+struct scmi_msg_resp_describe_levels {
+	__le32 flags;
+#define NUM_REMAINING_LEVELS(f)	((u16)(FIELD_GET(REMAINING_LEVELS_MASK, (f))))
+#define NUM_RETURNED_LEVELS(f)	((u16)(FIELD_GET(RETURNED_LEVELS_MASK, (f))))
+#define SUPPORTS_SEGMENTED_LEVELS(f)	((f) & BIT(12))
+	__le32 voltage[];
+};
+
+struct scmi_msg_cmd_config_set {
+	__le32 domain_id;
+	__le32 config;
+};
+
+struct scmi_msg_cmd_level_set {
+	__le32 domain_id;
+	__le32 flags;
+	__le32 voltage_level;
+};
+
+struct voltage_info {
+	unsigned int version;
+	unsigned int num_domains;
+	struct scmi_voltage_info *domains;
+};
+
+static int scmi_protocol_attributes_get(const struct scmi_handle *handle,
+					struct voltage_info *vinfo)
+{
+	int ret;
+	struct scmi_xfer *t;
+
+	ret = scmi_xfer_get_init(handle, PROTOCOL_ATTRIBUTES,
+				 SCMI_PROTOCOL_VOLTAGE, 0, sizeof(__le32), &t);
+	if (ret)
+		return ret;
+
+	ret = scmi_do_xfer(handle, t);
+	if (!ret)
+		vinfo->num_domains =
+			NUM_VOLTAGE_DOMAINS(get_unaligned_le32(t->rx.buf));
+
+	scmi_xfer_put(handle, t);
+	return ret;
+}
+
+static int scmi_init_voltage_levels(struct device *dev,
+				    struct scmi_voltage_info *v,
+				    u32 num_returned, u32 num_remaining,
+				    bool segmented)
+{
+	u32 num_levels;
+
+	num_levels = num_returned + num_remaining;
+	/*
+	 * segmented levels entries are represented by a single triplet
+	 * returned all in one go.
+	 */
+	if (!num_levels ||
+	    (segmented && (num_remaining || num_returned != 3))) {
+		dev_err(dev,
+			"Invalid level descriptor(%d/%d/%d) for voltage dom %d\n",
+			num_levels, num_returned, num_remaining, v->id);
+		return -EINVAL;
+	}
+
+	v->levels_uv = devm_kcalloc(dev, num_levels, sizeof(u32), GFP_KERNEL);
+	if (!v->levels_uv)
+		return -ENOMEM;
+
+	v->num_levels = num_levels;
+	v->segmented = segmented;
+
+	return 0;
+}
+
+static int scmi_voltage_descriptors_get(const struct scmi_handle *handle,
+					struct voltage_info *vinfo)
+{
+	int ret, dom;
+	struct scmi_xfer *td, *tl;
+	struct device *dev = handle->dev;
+	struct scmi_msg_resp_domain_attributes *resp_dom;
+	struct scmi_msg_resp_describe_levels *resp_levels;
+
+	ret = scmi_xfer_get_init(handle, VOLTAGE_DOMAIN_ATTRIBUTES,
+				 SCMI_PROTOCOL_VOLTAGE, sizeof(__le32),
+				 sizeof(*resp_dom), &td);
+	if (ret)
+		return ret;
+	resp_dom = td->rx.buf;
+
+	ret = scmi_xfer_get_init(handle, VOLTAGE_DESCRIBE_LEVELS,
+				 SCMI_PROTOCOL_VOLTAGE, sizeof(__le64), 0, &tl);
+	if (ret)
+		goto outd;
+	resp_levels = tl->rx.buf;
+
+	for (dom = 0; dom < vinfo->num_domains; dom++) {
+		u32 desc_index = 0;
+		u16 num_returned = 0, num_remaining = 0;
+		struct scmi_msg_cmd_describe_levels *cmd;
+		struct scmi_voltage_info *v;
+
+		/* Retrieve domain attributes at first ... */
+		put_unaligned_le32(dom, td->tx.buf);
+		ret = scmi_do_xfer(handle, td);
+		/* Skip domain on comms error */
+		if (ret)
+			continue;
+
+		v = vinfo->domains + dom;
+		v->id = dom;
+		v->attributes = le32_to_cpu(resp_dom->attr);
+		strlcpy(v->name, resp_dom->name, SCMI_MAX_STR_SIZE);
+
+		cmd = tl->tx.buf;
+		/* ...then retrieve domain levels descriptions */
+		do {
+			u32 flags;
+			int cnt;
+
+			cmd->domain_id = cpu_to_le32(v->id);
+			cmd->level_index = desc_index;
+			ret = scmi_do_xfer(handle, tl);
+			if (ret)
+				break;
+
+			flags = le32_to_cpu(resp_levels->flags);
+			num_returned = NUM_RETURNED_LEVELS(flags);
+			num_remaining = NUM_REMAINING_LEVELS(flags);
+
+			/* Allocate space for num_levels if not already done */
+			if (!v->num_levels) {
+				ret = scmi_init_voltage_levels(dev, v,
+							       num_returned,
+							       num_remaining,
+					      SUPPORTS_SEGMENTED_LEVELS(flags));
+				if (ret)
+					break;
+			}
+
+			if (desc_index + num_returned > v->num_levels) {
+				dev_err(handle->dev,
+					"No. of voltage levels can't exceed %d\n",
+					v->num_levels);
+				ret = -EINVAL;
+				break;
+			}
+
+			for (cnt = 0; cnt < num_returned; cnt++) {
+				s32 val;
+
+				val =
+				    (s32)le32_to_cpu(resp_levels->voltage[cnt]);
+				v->levels_uv[desc_index + cnt] = val;
+				if (val < 0)
+					v->negative_volts_allowed = true;
+			}
+
+			desc_index += num_returned;
+
+			scmi_reset_rx_to_maxsz(handle, tl);
+			/* check both to avoid infinite loop due to buggy fw */
+		} while (num_returned && num_remaining);
+
+		if (ret) {
+			v->num_levels = 0;
+			devm_kfree(dev, v->levels_uv);
+		}
+
+		scmi_reset_rx_to_maxsz(handle, td);
+	}
+
+	scmi_xfer_put(handle, tl);
+outd:
+	scmi_xfer_put(handle, td);
+
+	return ret;
+}
+
+static int __scmi_voltage_get_u32(const struct scmi_handle *handle,
+				  u8 cmd_id, u32 domain_id, u32 *value)
+{
+	int ret;
+	struct scmi_xfer *t;
+	struct voltage_info *vinfo = handle->voltage_priv;
+
+	if (domain_id >= vinfo->num_domains)
+		return -EINVAL;
+
+	ret = scmi_xfer_get_init(handle, cmd_id,
+				 SCMI_PROTOCOL_VOLTAGE,
+				 sizeof(__le32), 0, &t);
+	if (ret)
+		return ret;
+
+	put_unaligned_le32(domain_id, t->tx.buf);
+	ret = scmi_do_xfer(handle, t);
+	if (!ret)
+		*value = get_unaligned_le32(t->rx.buf);
+
+	scmi_xfer_put(handle, t);
+	return ret;
+}
+
+static int scmi_voltage_config_set(const struct scmi_handle *handle,
+				   u32 domain_id, u32 config)
+{
+	int ret;
+	struct scmi_xfer *t;
+	struct voltage_info *vinfo = handle->voltage_priv;
+	struct scmi_msg_cmd_config_set *cmd;
+
+	if (domain_id >= vinfo->num_domains)
+		return -EINVAL;
+
+	ret = scmi_xfer_get_init(handle, VOLTAGE_CONFIG_SET,
+				 SCMI_PROTOCOL_VOLTAGE,
+				 sizeof(*cmd), 0, &t);
+	if (ret)
+		return ret;
+
+	cmd = t->tx.buf;
+	cmd->domain_id = cpu_to_le32(domain_id);
+	cmd->config = cpu_to_le32(config & GENMASK(3, 0));
+
+	ret = scmi_do_xfer(handle, t);
+
+	scmi_xfer_put(handle, t);
+	return ret;
+}
+
+static int scmi_voltage_config_get(const struct scmi_handle *handle,
+				   u32 domain_id, u32 *config)
+{
+	return __scmi_voltage_get_u32(handle, VOLTAGE_CONFIG_GET,
+				      domain_id, config);
+}
+
+static int scmi_voltage_level_set(const struct scmi_handle *handle,
+				  u32 domain_id, u32 flags, s32 volt_uV)
+{
+	int ret;
+	struct scmi_xfer *t;
+	struct voltage_info *vinfo = handle->voltage_priv;
+	struct scmi_msg_cmd_level_set *cmd;
+
+	if (domain_id >= vinfo->num_domains)
+		return -EINVAL;
+
+	ret = scmi_xfer_get_init(handle, VOLTAGE_LEVEL_SET,
+				 SCMI_PROTOCOL_VOLTAGE,
+				 sizeof(*cmd), 0, &t);
+	if (ret)
+		return ret;
+
+	cmd = t->tx.buf;
+	cmd->domain_id = cpu_to_le32(domain_id);
+	cmd->flags = cpu_to_le32(flags);
+	cmd->voltage_level = cpu_to_le32(volt_uV);
+
+	ret = scmi_do_xfer(handle, t);
+
+	scmi_xfer_put(handle, t);
+	return ret;
+}
+
+static int scmi_voltage_level_get(const struct scmi_handle *handle,
+				  u32 domain_id, s32 *volt_uV)
+{
+	return __scmi_voltage_get_u32(handle, VOLTAGE_LEVEL_GET,
+				      domain_id, (u32 *)volt_uV);
+}
+
+static const struct scmi_voltage_info * __must_check
+scmi_voltage_info_get(const struct scmi_handle *handle, u32 domain_id)
+{
+	struct voltage_info *vinfo = handle->voltage_priv;
+
+	if (domain_id >= vinfo->num_domains ||
+	    !vinfo->domains[domain_id].num_levels)
+		return NULL;
+
+	return vinfo->domains + domain_id;
+}
+
+static int scmi_voltage_domains_num_get(const struct scmi_handle *handle)
+{
+	struct voltage_info *vinfo = handle->voltage_priv;
+
+	return vinfo->num_domains;
+}
+
+static struct scmi_voltage_ops voltage_ops = {
+	.num_domains_get = scmi_voltage_domains_num_get,
+	.info_get = scmi_voltage_info_get,
+	.config_set = scmi_voltage_config_set,
+	.config_get = scmi_voltage_config_get,
+	.level_set = scmi_voltage_level_set,
+	.level_get = scmi_voltage_level_get,
+};
+
+static int scmi_voltage_protocol_init(struct scmi_handle *handle)
+{
+	int ret;
+	u32 version;
+	struct voltage_info *vinfo;
+
+	ret = scmi_version_get(handle, SCMI_PROTOCOL_VOLTAGE, &version);
+	if (ret)
+		return ret;
+
+	dev_dbg(handle->dev, "Voltage Version %d.%d\n",
+		PROTOCOL_REV_MAJOR(version), PROTOCOL_REV_MINOR(version));
+
+	vinfo = devm_kzalloc(handle->dev, sizeof(*vinfo), GFP_KERNEL);
+	if (!vinfo)
+		return -ENOMEM;
+	vinfo->version = version;
+
+	ret = scmi_protocol_attributes_get(handle, vinfo);
+	if (ret)
+		return ret;
+
+	if (vinfo->num_domains) {
+		vinfo->domains = devm_kcalloc(handle->dev, vinfo->num_domains,
+					      sizeof(*vinfo->domains),
+					      GFP_KERNEL);
+		if (!vinfo->domains)
+			return -ENOMEM;
+		ret = scmi_voltage_descriptors_get(handle, vinfo);
+		if (ret)
+			return ret;
+	} else {
+		dev_warn(handle->dev, "No Voltage domains found.\n");
+	}
+
+	handle->voltage_ops = &voltage_ops;
+	handle->voltage_priv = vinfo;
+
+	return 0;
+}
+
+DEFINE_SCMI_PROTOCOL_REGISTER_UNREGISTER(SCMI_PROTOCOL_VOLTAGE, voltage)
diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h
index 9cd312a1ff92..b11ca01e2393 100644
--- a/include/linux/scmi_protocol.h
+++ b/include/linux/scmi_protocol.h
@@ -209,6 +209,64 @@ struct scmi_reset_ops {
 	int (*deassert)(const struct scmi_handle *handle, u32 domain);
 };
 
+/**
+ * struct scmi_voltage_info - describe one available SCMI Voltage Domain
+ *
+ * @id: the domain ID as advertised by the platform
+ * @segmented: defines the layout of the entries of array @levels_uv.
+ *	       - when True the entries are to be interpreted as triplets,
+ *	         each defining a segment representing a range of equally
+ *	         space voltages: <lowest_volts>, <highest_volt>, <step_uV>
+ *	       - when False the entries simply represent a single discrete
+ *	         supported voltage level
+ * @negative_volts_allowed: True if any of the entries of @levels_uv represent
+ *			    a negative voltage.
+ * @attributes: represents Voltage Domain advertised attributes
+ * @name: name assigned to the Voltage Domain by platform
+ * @num_levels: number of total entries in @levels_uv.
+ * @levels_uv: array of entries describing the available voltage levels for
+ *	       this domain.
+ */
+struct scmi_voltage_info {
+	unsigned int id;
+	bool segmented;
+	bool negative_volts_allowed;
+	unsigned int attributes;
+	char name[SCMI_MAX_STR_SIZE];
+	unsigned int num_levels;
+#define SCMI_VOLTAGE_SEGMENT_LOW	0
+#define SCMI_VOLTAGE_SEGMENT_HIGH	1
+#define SCMI_VOLTAGE_SEGMENT_STEP	2
+	int *levels_uv;
+};
+
+/**
+ * struct scmi_voltage_ops - represents the various operations provided
+ * by SCMI Voltage Protocol
+ *
+ * @num_domains_get: get the count of voltage domains provided by SCMI
+ * @info_get: get the information of the specified domain
+ * @config_set: set the config for the specified domain
+ * @config_get: get the config of the specified domain
+ * @level_set: set the voltage level for the specified domain
+ * @level_get: get the voltage level of the specified domain
+ */
+struct scmi_voltage_ops {
+	int (*num_domains_get)(const struct scmi_handle *handle);
+	const struct scmi_voltage_info __must_check *(*info_get)
+		(const struct scmi_handle *handle, u32 domain_id);
+	int (*config_set)(const struct scmi_handle *handle, u32 domain_id,
+			  u32 config);
+#define	SCMI_VOLTAGE_ARCH_STATE_OFF		0x0
+#define	SCMI_VOLTAGE_ARCH_STATE_ON		0x7
+	int (*config_get)(const struct scmi_handle *handle, u32 domain_id,
+			  u32 *config);
+	int (*level_set)(const struct scmi_handle *handle, u32 domain_id,
+			 u32 flags, s32 volt_uV);
+	int (*level_get)(const struct scmi_handle *handle, u32 domain_id,
+			 s32 *volt_uV);
+};
+
 /**
  * struct scmi_notify_ops  - represents notifications' operations provided by
  * SCMI core
@@ -262,6 +320,7 @@ struct scmi_notify_ops {
  * @clk_ops: pointer to set of clock protocol operations
  * @sensor_ops: pointer to set of sensor protocol operations
  * @reset_ops: pointer to set of reset protocol operations
+ * @voltage_ops: pointer to set of voltage protocol operations
  * @notify_ops: pointer to set of notifications related operations
  * @perf_priv: pointer to private data structure specific to performance
  *	protocol(for internal use only)
@@ -273,6 +332,8 @@ struct scmi_notify_ops {
  *	protocol(for internal use only)
  * @reset_priv: pointer to private data structure specific to reset
  *	protocol(for internal use only)
+ * @voltage_priv: pointer to private data structure specific to voltage
+ *	protocol(for internal use only)
  * @notify_priv: pointer to private data structure specific to notifications
  *	(for internal use only)
  */
@@ -284,6 +345,7 @@ struct scmi_handle {
 	const struct scmi_power_ops *power_ops;
 	const struct scmi_sensor_ops *sensor_ops;
 	const struct scmi_reset_ops *reset_ops;
+	const struct scmi_voltage_ops *voltage_ops;
 	const struct scmi_notify_ops *notify_ops;
 	/* for protocol internal use */
 	void *perf_priv;
@@ -291,6 +353,7 @@ struct scmi_handle {
 	void *power_priv;
 	void *sensor_priv;
 	void *reset_priv;
+	void *voltage_priv;
 	void *notify_priv;
 	void *system_priv;
 };
@@ -303,6 +366,7 @@ enum scmi_std_protocol {
 	SCMI_PROTOCOL_CLOCK = 0x14,
 	SCMI_PROTOCOL_SENSOR = 0x15,
 	SCMI_PROTOCOL_RESET = 0x16,
+	SCMI_PROTOCOL_VOLTAGE = 0x17,
 };
 
 enum scmi_system_events {
-- 
cgit v1.2.3


From 341917490d7d68d2f7267a265b8820fc3f8ead1b Mon Sep 17 00:00:00 2001
From: Gustavo Pimentel <Gustavo.Pimentel@synopsys.com>
Date: Wed, 18 Nov 2020 23:49:20 +0100
Subject: PCI: Decode PCIe 64 GT/s link speed
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

PCIe r6.0, sec 7.5.3.18, defines a new 64.0 GT/s bit in the Supported Link
Speeds Vector of Link Capabilities 2.

This patch does not affect the speed of the link, which should be
negotiated automatically by the hardware; it only adds decoding when
showing the speed to the user.

Decode this new speed.  Previously, reading the speed of a link operating
at this speed showed "Unknown speed" instead of "64.0 GT/s".

Link: https://lore.kernel.org/r/aaaab33fe18975e123a84aebce2adb85f44e2bbe.1605739760.git.gustavo.pimentel@synopsys.com
Signed-off-by: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Krzysztof Wilczyński <kw@linux.com>
---
 drivers/pci/pci.h             | 6 ++++--
 drivers/pci/probe.c           | 3 ++-
 include/linux/pci.h           | 1 +
 include/uapi/linux/pci_regs.h | 4 ++++
 4 files changed, 11 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index f86cae9aa1f4..81bf905b545c 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -294,7 +294,8 @@ void pci_bus_put(struct pci_bus *bus);
 
 /* PCIe link information from Link Capabilities 2 */
 #define PCIE_LNKCAP2_SLS2SPEED(lnkcap2) \
-	((lnkcap2) & PCI_EXP_LNKCAP2_SLS_32_0GB ? PCIE_SPEED_32_0GT : \
+	((lnkcap2) & PCI_EXP_LNKCAP2_SLS_64_0GB ? PCIE_SPEED_64_0GT : \
+	 (lnkcap2) & PCI_EXP_LNKCAP2_SLS_32_0GB ? PCIE_SPEED_32_0GT : \
 	 (lnkcap2) & PCI_EXP_LNKCAP2_SLS_16_0GB ? PCIE_SPEED_16_0GT : \
 	 (lnkcap2) & PCI_EXP_LNKCAP2_SLS_8_0GB ? PCIE_SPEED_8_0GT : \
 	 (lnkcap2) & PCI_EXP_LNKCAP2_SLS_5_0GB ? PCIE_SPEED_5_0GT : \
@@ -303,7 +304,8 @@ void pci_bus_put(struct pci_bus *bus);
 
 /* PCIe speed to Mb/s reduced by encoding overhead */
 #define PCIE_SPEED2MBS_ENC(speed) \
-	((speed) == PCIE_SPEED_32_0GT ? 32000*128/130 : \
+	((speed) == PCIE_SPEED_64_0GT ? 64000*128/130 : \
+	 (speed) == PCIE_SPEED_32_0GT ? 32000*128/130 : \
 	 (speed) == PCIE_SPEED_16_0GT ? 16000*128/130 : \
 	 (speed) == PCIE_SPEED_8_0GT  ?  8000*128/130 : \
 	 (speed) == PCIE_SPEED_5_0GT  ?  5000*8/10 : \
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 4289030b0fff..fe2e00f5fc4c 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -677,7 +677,7 @@ const unsigned char pcie_link_speed[] = {
 	PCIE_SPEED_8_0GT,		/* 3 */
 	PCIE_SPEED_16_0GT,		/* 4 */
 	PCIE_SPEED_32_0GT,		/* 5 */
-	PCI_SPEED_UNKNOWN,		/* 6 */
+	PCIE_SPEED_64_0GT,		/* 6 */
 	PCI_SPEED_UNKNOWN,		/* 7 */
 	PCI_SPEED_UNKNOWN,		/* 8 */
 	PCI_SPEED_UNKNOWN,		/* 9 */
@@ -719,6 +719,7 @@ const char *pci_speed_string(enum pci_bus_speed speed)
 	    "8.0 GT/s PCIe",		/* 0x16 */
 	    "16.0 GT/s PCIe",		/* 0x17 */
 	    "32.0 GT/s PCIe",		/* 0x18 */
+	    "64.0 GT/s PCIe",		/* 0x19 */
 	};
 
 	if (speed < ARRAY_SIZE(speed_strings))
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 22207a79762c..e007bc3e8b6e 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -281,6 +281,7 @@ enum pci_bus_speed {
 	PCIE_SPEED_8_0GT		= 0x16,
 	PCIE_SPEED_16_0GT		= 0x17,
 	PCIE_SPEED_32_0GT		= 0x18,
+	PCIE_SPEED_64_0GT		= 0x19,
 	PCI_SPEED_UNKNOWN		= 0xff,
 };
 
diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index a95d55f9f257..fe9d5dba2ba1 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -531,6 +531,7 @@
 #define  PCI_EXP_LNKCAP_SLS_8_0GB 0x00000003 /* LNKCAP2 SLS Vector bit 2 */
 #define  PCI_EXP_LNKCAP_SLS_16_0GB 0x00000004 /* LNKCAP2 SLS Vector bit 3 */
 #define  PCI_EXP_LNKCAP_SLS_32_0GB 0x00000005 /* LNKCAP2 SLS Vector bit 4 */
+#define  PCI_EXP_LNKCAP_SLS_64_0GB 0x00000006 /* LNKCAP2 SLS Vector bit 5 */
 #define  PCI_EXP_LNKCAP_MLW	0x000003f0 /* Maximum Link Width */
 #define  PCI_EXP_LNKCAP_ASPMS	0x00000c00 /* ASPM Support */
 #define  PCI_EXP_LNKCAP_ASPM_L0S 0x00000400 /* ASPM L0s Support */
@@ -562,6 +563,7 @@
 #define  PCI_EXP_LNKSTA_CLS_8_0GB 0x0003 /* Current Link Speed 8.0GT/s */
 #define  PCI_EXP_LNKSTA_CLS_16_0GB 0x0004 /* Current Link Speed 16.0GT/s */
 #define  PCI_EXP_LNKSTA_CLS_32_0GB 0x0005 /* Current Link Speed 32.0GT/s */
+#define  PCI_EXP_LNKSTA_CLS_64_0GB 0x0006 /* Current Link Speed 64.0GT/s */
 #define  PCI_EXP_LNKSTA_NLW	0x03f0	/* Negotiated Link Width */
 #define  PCI_EXP_LNKSTA_NLW_X1	0x0010	/* Current Link Width x1 */
 #define  PCI_EXP_LNKSTA_NLW_X2	0x0020	/* Current Link Width x2 */
@@ -670,6 +672,7 @@
 #define  PCI_EXP_LNKCAP2_SLS_8_0GB	0x00000008 /* Supported Speed 8GT/s */
 #define  PCI_EXP_LNKCAP2_SLS_16_0GB	0x00000010 /* Supported Speed 16GT/s */
 #define  PCI_EXP_LNKCAP2_SLS_32_0GB	0x00000020 /* Supported Speed 32GT/s */
+#define  PCI_EXP_LNKCAP2_SLS_64_0GB	0x00000040 /* Supported Speed 64GT/s */
 #define  PCI_EXP_LNKCAP2_CROSSLINK	0x00000100 /* Crosslink supported */
 #define PCI_EXP_LNKCTL2		48	/* Link Control 2 */
 #define  PCI_EXP_LNKCTL2_TLS		0x000f
@@ -678,6 +681,7 @@
 #define  PCI_EXP_LNKCTL2_TLS_8_0GT	0x0003 /* Supported Speed 8GT/s */
 #define  PCI_EXP_LNKCTL2_TLS_16_0GT	0x0004 /* Supported Speed 16GT/s */
 #define  PCI_EXP_LNKCTL2_TLS_32_0GT	0x0005 /* Supported Speed 32GT/s */
+#define  PCI_EXP_LNKCTL2_TLS_64_0GT	0x0006 /* Supported Speed 64GT/s */
 #define  PCI_EXP_LNKCTL2_ENTER_COMP	0x0010 /* Enter Compliance */
 #define  PCI_EXP_LNKCTL2_TX_MARGIN	0x0380 /* Transmit Margin */
 #define  PCI_EXP_LNKCTL2_HASD		0x0020 /* HW Autonomous Speed Disable */
-- 
cgit v1.2.3


From 956fb852181e4e4b16ccad62511e0038d3ed4928 Mon Sep 17 00:00:00 2001
From: Srujana Challa <schalla@marvell.com>
Date: Wed, 18 Nov 2020 17:14:14 +0530
Subject: octeontx2-pf: move lmt flush to include/linux/soc

On OcteonTX2 platform CPT instruction enqueue and NIX
packet send are only possible via LMTST operations which
uses LDEOR instruction. This patch moves lmt flush
function from OcteonTX2 nic driver to include/linux/soc
since it will be used by OcteonTX2 CPT and NIC driver for
LMTST.

Signed-off-by: Suheil Chandran <schandran@marvell.com>
Signed-off-by: Srujana Challa <schalla@marvell.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS                                        |  2 ++
 .../ethernet/marvell/octeontx2/nic/otx2_common.h   | 13 +---------
 include/linux/soc/marvell/octeontx2/asm.h          | 29 ++++++++++++++++++++++
 3 files changed, 32 insertions(+), 12 deletions(-)
 create mode 100644 include/linux/soc/marvell/octeontx2/asm.h

(limited to 'include/linux')

diff --git a/MAINTAINERS b/MAINTAINERS
index a7e0f11def8e..d36bee3f1f04 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10453,6 +10453,7 @@ M:	Srujana Challa <schalla@marvell.com>
 L:	linux-crypto@vger.kernel.org
 S:	Maintained
 F:	drivers/crypto/marvell/
+F:	include/linux/soc/marvell/octeontx2/
 
 MARVELL GIGABIT ETHERNET DRIVERS (skge/sky2)
 M:	Mirko Lindner <mlindner@marvell.com>
@@ -10525,6 +10526,7 @@ M:	hariprasad <hkelam@marvell.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/marvell/octeontx2/nic/
+F:	include/linux/soc/marvell/octeontx2/
 
 MARVELL OCTEONTX2 RVU ADMIN FUNCTION DRIVER
 M:	Sunil Goutham <sgoutham@marvell.com>
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index b18b45d02165..ceec649bdd13 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -16,6 +16,7 @@
 #include <linux/net_tstamp.h>
 #include <linux/ptp_clock_kernel.h>
 #include <linux/timecounter.h>
+#include <linux/soc/marvell/octeontx2/asm.h>
 
 #include <mbox.h>
 #include <npc.h>
@@ -462,21 +463,9 @@ static inline u64 otx2_atomic64_add(u64 incr, u64 *ptr)
 	return result;
 }
 
-static inline u64 otx2_lmt_flush(uint64_t addr)
-{
-	u64 result = 0;
-
-	__asm__ volatile(".cpu  generic+lse\n"
-			 "ldeor xzr,%x[rf],[%[rs]]"
-			 : [rf]"=r"(result)
-			 : [rs]"r"(addr));
-	return result;
-}
-
 #else
 #define otx2_write128(lo, hi, addr)
 #define otx2_atomic64_add(incr, ptr)		({ *ptr += incr; })
-#define otx2_lmt_flush(addr)			({ 0; })
 #endif
 
 /* Alloc pointer from pool/aura */
diff --git a/include/linux/soc/marvell/octeontx2/asm.h b/include/linux/soc/marvell/octeontx2/asm.h
new file mode 100644
index 000000000000..ae2279fe830a
--- /dev/null
+++ b/include/linux/soc/marvell/octeontx2/asm.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ * Copyright (C) 2020 Marvell.
+ */
+
+#ifndef __SOC_OTX2_ASM_H
+#define __SOC_OTX2_ASM_H
+
+#if defined(CONFIG_ARM64)
+/*
+ * otx2_lmt_flush is used for LMT store operation.
+ * On octeontx2 platform CPT instruction enqueue and
+ * NIX packet send are only possible via LMTST
+ * operations and it uses LDEOR instruction targeting
+ * the coprocessor address.
+ */
+#define otx2_lmt_flush(ioaddr)                          \
+({                                                      \
+	u64 result = 0;                                 \
+	__asm__ volatile(".cpu  generic+lse\n"          \
+			 "ldeor xzr, %x[rf], [%[rs]]"   \
+			 : [rf]"=r" (result)            \
+			 : [rs]"r" (ioaddr));           \
+	(result);                                       \
+})
+#else
+#define otx2_lmt_flush(ioaddr)          ({ 0; })
+#endif
+
+#endif /* __SOC_OTX2_ASM_H */
-- 
cgit v1.2.3


From 0d8315dddd2899f519fe1ca3d4d5cdaf44ea421e Mon Sep 17 00:00:00 2001
From: YiFei Zhu <yifeifz2@illinois.edu>
Date: Wed, 11 Nov 2020 07:33:54 -0600
Subject: seccomp/cache: Report cache data through /proc/pid/seccomp_cache

Currently the kernel does not provide an infrastructure to translate
architecture numbers to a human-readable name. Translating syscall
numbers to syscall names is possible through FTRACE_SYSCALL
infrastructure but it does not provide support for compat syscalls.

This will create a file for each PID as /proc/pid/seccomp_cache.
The file will be empty when no seccomp filters are loaded, or be
in the format of:
<arch name> <decimal syscall number> <ALLOW | FILTER>
where ALLOW means the cache is guaranteed to allow the syscall,
and filter means the cache will pass the syscall to the BPF filter.

For the docker default profile on x86_64 it looks like:
x86_64 0 ALLOW
x86_64 1 ALLOW
x86_64 2 ALLOW
x86_64 3 ALLOW
[...]
x86_64 132 ALLOW
x86_64 133 ALLOW
x86_64 134 FILTER
x86_64 135 FILTER
x86_64 136 FILTER
x86_64 137 ALLOW
x86_64 138 ALLOW
x86_64 139 FILTER
x86_64 140 ALLOW
x86_64 141 ALLOW
[...]

This file is guarded by CONFIG_SECCOMP_CACHE_DEBUG with a default
of N because I think certain users of seccomp might not want the
application to know which syscalls are definitely usable. For
the same reason, it is also guarded by CAP_SYS_ADMIN.

Suggested-by: Jann Horn <jannh@google.com>
Link: https://lore.kernel.org/lkml/CAG48ez3Ofqp4crXGksLmZY6=fGrF_tWyUCg7PBkAetvbbOPeOA@mail.gmail.com/
Signed-off-by: YiFei Zhu <yifeifz2@illinois.edu>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/94e663fa53136f5a11f432c661794d1ee7060779.1605101222.git.yifeifz2@illinois.edu
---
 arch/Kconfig            | 17 ++++++++++++++
 fs/proc/base.c          |  6 +++++
 include/linux/seccomp.h |  7 ++++++
 kernel/seccomp.c        | 59 +++++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 89 insertions(+)

(limited to 'include/linux')

diff --git a/arch/Kconfig b/arch/Kconfig
index 56b6ccc0e32d..35c9463b7d10 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -486,6 +486,9 @@ config HAVE_ARCH_SECCOMP_FILTER
 	  - secure_computing return value is checked and a return value of -1
 	    results in the system call being skipped immediately.
 	  - seccomp syscall wired up
+	  - if !HAVE_SPARSE_SYSCALL_NR, have SECCOMP_ARCH_NATIVE,
+	    SECCOMP_ARCH_NATIVE_NR, SECCOMP_ARCH_NATIVE_NAME defined. If
+	    COMPAT is supported, have the SECCOMP_ARCH_COMPAT* defines too.
 
 config SECCOMP
 	prompt "Enable seccomp to safely execute untrusted bytecode"
@@ -514,6 +517,20 @@ config SECCOMP_FILTER
 
 	  See Documentation/userspace-api/seccomp_filter.rst for details.
 
+config SECCOMP_CACHE_DEBUG
+	bool "Show seccomp filter cache status in /proc/pid/seccomp_cache"
+	depends on SECCOMP_FILTER && !HAVE_SPARSE_SYSCALL_NR
+	depends on PROC_FS
+	help
+	  This enables the /proc/pid/seccomp_cache interface to monitor
+	  seccomp cache data. The file format is subject to change. Reading
+	  the file requires CAP_SYS_ADMIN.
+
+	  This option is for debugging only. Enabling presents the risk that
+	  an adversary may be able to infer the seccomp filter logic.
+
+	  If unsure, say N.
+
 config HAVE_ARCH_STACKLEAK
 	bool
 	help
diff --git a/fs/proc/base.c b/fs/proc/base.c
index b362523a9829..8a7d682ba881 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -3263,6 +3263,9 @@ static const struct pid_entry tgid_base_stuff[] = {
 #ifdef CONFIG_PROC_PID_ARCH_STATUS
 	ONE("arch_status", S_IRUGO, proc_pid_arch_status),
 #endif
+#ifdef CONFIG_SECCOMP_CACHE_DEBUG
+	ONE("seccomp_cache", S_IRUSR, proc_pid_seccomp_cache),
+#endif
 };
 
 static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx)
@@ -3592,6 +3595,9 @@ static const struct pid_entry tid_base_stuff[] = {
 #ifdef CONFIG_PROC_PID_ARCH_STATUS
 	ONE("arch_status", S_IRUGO, proc_pid_arch_status),
 #endif
+#ifdef CONFIG_SECCOMP_CACHE_DEBUG
+	ONE("seccomp_cache", S_IRUSR, proc_pid_seccomp_cache),
+#endif
 };
 
 static int proc_tid_base_readdir(struct file *file, struct dir_context *ctx)
diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index 02aef2844c38..76963ec4641a 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -121,4 +121,11 @@ static inline long seccomp_get_metadata(struct task_struct *task,
 	return -EINVAL;
 }
 #endif /* CONFIG_SECCOMP_FILTER && CONFIG_CHECKPOINT_RESTORE */
+
+#ifdef CONFIG_SECCOMP_CACHE_DEBUG
+struct seq_file;
+
+int proc_pid_seccomp_cache(struct seq_file *m, struct pid_namespace *ns,
+			   struct pid *pid, struct task_struct *task);
+#endif
 #endif /* _LINUX_SECCOMP_H */
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index d8cf468dbe1e..76f524e320b1 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -553,6 +553,9 @@ void seccomp_filter_release(struct task_struct *tsk)
 {
 	struct seccomp_filter *orig = tsk->seccomp.filter;
 
+	/* We are effectively holding the siglock by not having any sighand. */
+	WARN_ON(tsk->sighand != NULL);
+
 	/* Detach task from its filter tree. */
 	tsk->seccomp.filter = NULL;
 	__seccomp_filter_release(orig);
@@ -2335,3 +2338,59 @@ static int __init seccomp_sysctl_init(void)
 device_initcall(seccomp_sysctl_init)
 
 #endif /* CONFIG_SYSCTL */
+
+#ifdef CONFIG_SECCOMP_CACHE_DEBUG
+/* Currently CONFIG_SECCOMP_CACHE_DEBUG implies SECCOMP_ARCH_NATIVE */
+static void proc_pid_seccomp_cache_arch(struct seq_file *m, const char *name,
+					const void *bitmap, size_t bitmap_size)
+{
+	int nr;
+
+	for (nr = 0; nr < bitmap_size; nr++) {
+		bool cached = test_bit(nr, bitmap);
+		char *status = cached ? "ALLOW" : "FILTER";
+
+		seq_printf(m, "%s %d %s\n", name, nr, status);
+	}
+}
+
+int proc_pid_seccomp_cache(struct seq_file *m, struct pid_namespace *ns,
+			   struct pid *pid, struct task_struct *task)
+{
+	struct seccomp_filter *f;
+	unsigned long flags;
+
+	/*
+	 * We don't want some sandboxed process to know what their seccomp
+	 * filters consist of.
+	 */
+	if (!file_ns_capable(m->file, &init_user_ns, CAP_SYS_ADMIN))
+		return -EACCES;
+
+	if (!lock_task_sighand(task, &flags))
+		return -ESRCH;
+
+	f = READ_ONCE(task->seccomp.filter);
+	if (!f) {
+		unlock_task_sighand(task, &flags);
+		return 0;
+	}
+
+	/* prevent filter from being freed while we are printing it */
+	__get_seccomp_filter(f);
+	unlock_task_sighand(task, &flags);
+
+	proc_pid_seccomp_cache_arch(m, SECCOMP_ARCH_NATIVE_NAME,
+				    f->cache.allow_native,
+				    SECCOMP_ARCH_NATIVE_NR);
+
+#ifdef SECCOMP_ARCH_COMPAT
+	proc_pid_seccomp_cache_arch(m, SECCOMP_ARCH_COMPAT_NAME,
+				    f->cache.allow_compat,
+				    SECCOMP_ARCH_COMPAT_NR);
+#endif /* SECCOMP_ARCH_COMPAT */
+
+	__put_seccomp_filter(f);
+	return 0;
+}
+#endif /* CONFIG_SECCOMP_CACHE_DEBUG */
-- 
cgit v1.2.3


From 4ae21993f07422ec1cb83e9530f87fa61bff02bd Mon Sep 17 00:00:00 2001
From: Antonio Cardace <acardace@redhat.com>
Date: Wed, 18 Nov 2020 21:45:17 +0100
Subject: ethtool: add ETHTOOL_COALESCE_ALL_PARAMS define

This bitmask represents all existing coalesce parameters.

Signed-off-by: Antonio Cardace <acardace@redhat.com>
Reviewed-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/ethtool.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 6408b446051f..e3da25b51ae4 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -215,6 +215,7 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32,
 #define ETHTOOL_COALESCE_TX_USECS_HIGH		BIT(19)
 #define ETHTOOL_COALESCE_TX_MAX_FRAMES_HIGH	BIT(20)
 #define ETHTOOL_COALESCE_RATE_SAMPLE_INTERVAL	BIT(21)
+#define ETHTOOL_COALESCE_ALL_PARAMS		GENMASK(21, 0)
 
 #define ETHTOOL_COALESCE_USECS						\
 	(ETHTOOL_COALESCE_RX_USECS | ETHTOOL_COALESCE_TX_USECS)
-- 
cgit v1.2.3


From 5164c788985702ad94fa4ce6adca29bf280876df Mon Sep 17 00:00:00 2001
From: Alexandru Ardelean <alexandru.ardelean@analog.com>
Date: Tue, 29 Sep 2020 15:59:43 +0300
Subject: iio: triggered-buffer: add {devm_}iio_triggered_buffer_setup_ext
 variants

This change adds a parameter to the {devm_}iio_triggered_buffer_setup()
functions to assign the extra sysfs buffer attributes that are typically
assigned via iio_buffer_set_attrs().

The functions also get renamed to iio_triggered_buffer_setup_ext() &
devm_iio_triggered_buffer_setup_ext().
For backwards compatibility the old {devm_}iio_triggered_buffer_setup()
functions are now macros wrap the new (renamed) functions with NULL for the
buffer attrs.

The aim is to remove iio_buffer_set_attrs(), so in the
iio_triggered_buffer_setup_ext() function the attributes are assigned
directly to 'buffer->attrs'.

When adding multiple IIO buffers per IIO device, it can be pretty
cumbersome to first allocate a set of buffers, then to dig them out of IIO
to assign extra attributes (with iio_buffer_set_attrs()).

Naturally, the best way would be to provide them at allocation time, which
is what this change does.

At this moment, buffers allocated with {devm_}iio_triggered_buffer_setup()
are the only ones in mainline IIO to call iio_buffer_set_attrs().

Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20200929125949.69934-4-alexandru.ardelean@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/buffer/industrialio-triggered-buffer.c | 31 +++++++++++++---------
 include/linux/iio/triggered_buffer.h               | 23 +++++++++++-----
 2 files changed, 35 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iio/buffer/industrialio-triggered-buffer.c b/drivers/iio/buffer/industrialio-triggered-buffer.c
index 6c20a83f887e..92b8aea3e063 100644
--- a/drivers/iio/buffer/industrialio-triggered-buffer.c
+++ b/drivers/iio/buffer/industrialio-triggered-buffer.c
@@ -9,18 +9,20 @@
 #include <linux/module.h>
 #include <linux/iio/iio.h>
 #include <linux/iio/buffer.h>
+#include <linux/iio/buffer_impl.h>
 #include <linux/iio/kfifo_buf.h>
 #include <linux/iio/triggered_buffer.h>
 #include <linux/iio/trigger_consumer.h>
 
 /**
- * iio_triggered_buffer_setup() - Setup triggered buffer and pollfunc
+ * iio_triggered_buffer_setup_ext() - Setup triggered buffer and pollfunc
  * @indio_dev:		IIO device structure
  * @h:			Function which will be used as pollfunc top half
  * @thread:		Function which will be used as pollfunc bottom half
  * @setup_ops:		Buffer setup functions to use for this device.
  *			If NULL the default setup functions for triggered
  *			buffers will be used.
+ * @buffer_attrs:	Extra sysfs buffer attributes for this IIO buffer
  *
  * This function combines some common tasks which will normally be performed
  * when setting up a triggered buffer. It will allocate the buffer and the
@@ -33,10 +35,11 @@
  * To free the resources allocated by this function call
  * iio_triggered_buffer_cleanup().
  */
-int iio_triggered_buffer_setup(struct iio_dev *indio_dev,
+int iio_triggered_buffer_setup_ext(struct iio_dev *indio_dev,
 	irqreturn_t (*h)(int irq, void *p),
 	irqreturn_t (*thread)(int irq, void *p),
-	const struct iio_buffer_setup_ops *setup_ops)
+	const struct iio_buffer_setup_ops *setup_ops,
+	const struct attribute **buffer_attrs)
 {
 	struct iio_buffer *buffer;
 	int ret;
@@ -67,6 +70,8 @@ int iio_triggered_buffer_setup(struct iio_dev *indio_dev,
 	/* Flag that polled ring buffering is possible */
 	indio_dev->modes |= INDIO_BUFFER_TRIGGERED;
 
+	buffer->attrs = buffer_attrs;
+
 	return 0;
 
 error_kfifo_free:
@@ -74,10 +79,10 @@ error_kfifo_free:
 error_ret:
 	return ret;
 }
-EXPORT_SYMBOL(iio_triggered_buffer_setup);
+EXPORT_SYMBOL(iio_triggered_buffer_setup_ext);
 
 /**
- * iio_triggered_buffer_cleanup() - Free resources allocated by iio_triggered_buffer_setup()
+ * iio_triggered_buffer_cleanup() - Free resources allocated by iio_triggered_buffer_setup_ext()
  * @indio_dev: IIO device structure
  */
 void iio_triggered_buffer_cleanup(struct iio_dev *indio_dev)
@@ -92,11 +97,12 @@ static void devm_iio_triggered_buffer_clean(struct device *dev, void *res)
 	iio_triggered_buffer_cleanup(*(struct iio_dev **)res);
 }
 
-int devm_iio_triggered_buffer_setup(struct device *dev,
-				    struct iio_dev *indio_dev,
-				    irqreturn_t (*h)(int irq, void *p),
-				    irqreturn_t (*thread)(int irq, void *p),
-				    const struct iio_buffer_setup_ops *ops)
+int devm_iio_triggered_buffer_setup_ext(struct device *dev,
+					struct iio_dev *indio_dev,
+					irqreturn_t (*h)(int irq, void *p),
+					irqreturn_t (*thread)(int irq, void *p),
+					const struct iio_buffer_setup_ops *ops,
+					const struct attribute **buffer_attrs)
 {
 	struct iio_dev **ptr;
 	int ret;
@@ -108,7 +114,8 @@ int devm_iio_triggered_buffer_setup(struct device *dev,
 
 	*ptr = indio_dev;
 
-	ret = iio_triggered_buffer_setup(indio_dev, h, thread, ops);
+	ret = iio_triggered_buffer_setup_ext(indio_dev, h, thread, ops,
+					     buffer_attrs);
 	if (!ret)
 		devres_add(dev, ptr);
 	else
@@ -116,7 +123,7 @@ int devm_iio_triggered_buffer_setup(struct device *dev,
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(devm_iio_triggered_buffer_setup);
+EXPORT_SYMBOL_GPL(devm_iio_triggered_buffer_setup_ext);
 
 MODULE_AUTHOR("Lars-Peter Clausen <lars@metafoo.de>");
 MODULE_DESCRIPTION("IIO helper functions for setting up triggered buffers");
diff --git a/include/linux/iio/triggered_buffer.h b/include/linux/iio/triggered_buffer.h
index e99c91799359..7f154d1f8739 100644
--- a/include/linux/iio/triggered_buffer.h
+++ b/include/linux/iio/triggered_buffer.h
@@ -4,19 +4,28 @@
 
 #include <linux/interrupt.h>
 
+struct attribute;
 struct iio_dev;
 struct iio_buffer_setup_ops;
 
-int iio_triggered_buffer_setup(struct iio_dev *indio_dev,
+int iio_triggered_buffer_setup_ext(struct iio_dev *indio_dev,
 	irqreturn_t (*h)(int irq, void *p),
 	irqreturn_t (*thread)(int irq, void *p),
-	const struct iio_buffer_setup_ops *setup_ops);
+	const struct iio_buffer_setup_ops *setup_ops,
+	const struct attribute **buffer_attrs);
 void iio_triggered_buffer_cleanup(struct iio_dev *indio_dev);
 
-int devm_iio_triggered_buffer_setup(struct device *dev,
-				    struct iio_dev *indio_dev,
-				    irqreturn_t (*h)(int irq, void *p),
-				    irqreturn_t (*thread)(int irq, void *p),
-				    const struct iio_buffer_setup_ops *ops);
+#define iio_triggered_buffer_setup(indio_dev, h, thread, setup_ops)		\
+	iio_triggered_buffer_setup_ext((indio_dev), (h), (thread), (setup_ops), NULL)
+
+int devm_iio_triggered_buffer_setup_ext(struct device *dev,
+					struct iio_dev *indio_dev,
+					irqreturn_t (*h)(int irq, void *p),
+					irqreturn_t (*thread)(int irq, void *p),
+					const struct iio_buffer_setup_ops *ops,
+					const struct attribute **buffer_attrs);
+
+#define devm_iio_triggered_buffer_setup(dev, indio_dev, h, thread, setup_ops)	\
+	devm_iio_triggered_buffer_setup_ext((dev), (indio_dev), (h), (thread), (setup_ops), NULL)
 
 #endif
-- 
cgit v1.2.3


From 21232b4456ba5e1eea7385bd3c4b1994994fd409 Mon Sep 17 00:00:00 2001
From: Alexandru Ardelean <alexandru.ardelean@analog.com>
Date: Tue, 29 Sep 2020 15:59:49 +0300
Subject: iio: buffer: remove iio_buffer_set_attrs() helper

The iio_buffer_set_attrs() is no longer used in the drivers, so it can be
removed now.

Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20200929125949.69934-10-alexandru.ardelean@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/industrialio-buffer.c | 12 ------------
 include/linux/iio/buffer.h        |  3 ---
 2 files changed, 15 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c
index a4f6bb96d4f4..9663dec3dcf3 100644
--- a/drivers/iio/industrialio-buffer.c
+++ b/drivers/iio/industrialio-buffer.c
@@ -210,18 +210,6 @@ void iio_buffer_init(struct iio_buffer *buffer)
 }
 EXPORT_SYMBOL(iio_buffer_init);
 
-/**
- * iio_buffer_set_attrs - Set buffer specific attributes
- * @buffer: The buffer for which we are setting attributes
- * @attrs: Pointer to a null terminated list of pointers to attributes
- */
-void iio_buffer_set_attrs(struct iio_buffer *buffer,
-			 const struct attribute **attrs)
-{
-	buffer->attrs = attrs;
-}
-EXPORT_SYMBOL_GPL(iio_buffer_set_attrs);
-
 static ssize_t iio_show_scan_index(struct device *dev,
 				   struct device_attribute *attr,
 				   char *buf)
diff --git a/include/linux/iio/buffer.h b/include/linux/iio/buffer.h
index fbba4093f06c..8febc23f5f26 100644
--- a/include/linux/iio/buffer.h
+++ b/include/linux/iio/buffer.h
@@ -11,9 +11,6 @@
 
 struct iio_buffer;
 
-void iio_buffer_set_attrs(struct iio_buffer *buffer,
-			 const struct attribute **attrs);
-
 int iio_push_to_buffers(struct iio_dev *indio_dev, const void *data);
 
 /**
-- 
cgit v1.2.3


From e2083d36739168f7b612312160cf7bb45b251408 Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Thu, 19 Nov 2020 17:49:04 +0000
Subject: firmware: arm_scmi: Add SCMI v3.0 sensors timestamped reads

Add new .reading_get_timestamped() method to sensor_ops to support SCMI v3.0
timestamped reads.

Link: https://lore.kernel.org/r/20201119174906.43862-5-cristian.marussi@arm.com
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_scmi/sensors.c | 127 ++++++++++++++++++++++++++++++++++--
 include/linux/scmi_protocol.h       |  22 +++++++
 2 files changed, 143 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/arm_scmi/sensors.c b/drivers/firmware/arm_scmi/sensors.c
index a85827f60a02..2239af5f9e6e 100644
--- a/drivers/firmware/arm_scmi/sensors.c
+++ b/drivers/firmware/arm_scmi/sensors.c
@@ -155,6 +155,23 @@ struct scmi_msg_sensor_reading_get {
 #define SENSOR_READ_ASYNC	BIT(0)
 };
 
+struct scmi_resp_sensor_reading_complete {
+	__le32 id;
+	__le64 readings;
+};
+
+struct scmi_sensor_reading_le {
+	__le32 sensor_value_low;
+	__le32 sensor_value_high;
+	__le32 timestamp_low;
+	__le32 timestamp_high;
+};
+
+struct scmi_resp_sensor_reading_complete_v3 {
+	__le32 id;
+	struct scmi_sensor_reading_le readings[];
+};
+
 struct scmi_sensor_trip_notify_payld {
 	__le32 agent_id;
 	__le32 sensor_id;
@@ -575,6 +592,21 @@ scmi_sensor_trip_point_config(const struct scmi_handle *handle, u32 sensor_id,
 	return ret;
 }
 
+/**
+ * scmi_sensor_reading_get  - Read scalar sensor value
+ * @handle: Platform handle
+ * @sensor_id: Sensor ID
+ * @value: The 64bit value sensor reading
+ *
+ * This function returns a single 64 bit reading value representing the sensor
+ * value; if the platform SCMI Protocol implementation and the sensor support
+ * multiple axis and timestamped-reads, this just returns the first axis while
+ * dropping the timestamp value.
+ * Use instead the @scmi_sensor_reading_get_timestamped to retrieve the array of
+ * timestamped multi-axis values.
+ *
+ * Return: 0 on Success
+ */
 static int scmi_sensor_reading_get(const struct scmi_handle *handle,
 				   u32 sensor_id, u64 *value)
 {
@@ -585,20 +617,24 @@ static int scmi_sensor_reading_get(const struct scmi_handle *handle,
 	struct scmi_sensor_info *s = si->sensors + sensor_id;
 
 	ret = scmi_xfer_get_init(handle, SENSOR_READING_GET,
-				 SCMI_PROTOCOL_SENSOR, sizeof(*sensor),
-				 sizeof(u64), &t);
+				 SCMI_PROTOCOL_SENSOR, sizeof(*sensor), 0, &t);
 	if (ret)
 		return ret;
 
 	sensor = t->tx.buf;
 	sensor->id = cpu_to_le32(sensor_id);
-
 	if (s->async) {
 		sensor->flags = cpu_to_le32(SENSOR_READ_ASYNC);
 		ret = scmi_do_xfer_with_response(handle, t);
-		if (!ret)
-			*value = get_unaligned_le64((void *)
-						    ((__le32 *)t->rx.buf + 1));
+		if (!ret) {
+			struct scmi_resp_sensor_reading_complete *resp;
+
+			resp = t->rx.buf;
+			if (le32_to_cpu(resp->id) == sensor_id)
+				*value = get_unaligned_le64(&resp->readings);
+			else
+				ret = -EPROTO;
+		}
 	} else {
 		sensor->flags = cpu_to_le32(0);
 		ret = scmi_do_xfer(handle, t);
@@ -610,6 +646,84 @@ static int scmi_sensor_reading_get(const struct scmi_handle *handle,
 	return ret;
 }
 
+static inline void
+scmi_parse_sensor_readings(struct scmi_sensor_reading *out,
+			   const struct scmi_sensor_reading_le *in)
+{
+	out->value = get_unaligned_le64((void *)&in->sensor_value_low);
+	out->timestamp = get_unaligned_le64((void *)&in->timestamp_low);
+}
+
+/**
+ * scmi_sensor_reading_get_timestamped  - Read multiple-axis timestamped values
+ * @handle: Platform handle
+ * @sensor_id: Sensor ID
+ * @count: The length of the provided @readings array
+ * @readings: An array of elements each representing a timestamped per-axis
+ *	      reading of type @struct scmi_sensor_reading.
+ *	      Returned readings are ordered as the @axis descriptors array
+ *	      included in @struct scmi_sensor_info and the max number of
+ *	      returned elements is min(@count, @num_axis); ideally the provided
+ *	      array should be of length @count equal to @num_axis.
+ *
+ * Return: 0 on Success
+ */
+static int
+scmi_sensor_reading_get_timestamped(const struct scmi_handle *handle,
+				    u32 sensor_id, u8 count,
+				    struct scmi_sensor_reading *readings)
+{
+	int ret;
+	struct scmi_xfer *t;
+	struct scmi_msg_sensor_reading_get *sensor;
+	struct sensors_info *si = handle->sensor_priv;
+	struct scmi_sensor_info *s = si->sensors + sensor_id;
+
+	if (!count || !readings ||
+	    (!s->num_axis && count > 1) || (s->num_axis && count > s->num_axis))
+		return -EINVAL;
+
+	ret = scmi_xfer_get_init(handle, SENSOR_READING_GET,
+				 SCMI_PROTOCOL_SENSOR, sizeof(*sensor), 0, &t);
+	if (ret)
+		return ret;
+
+	sensor = t->tx.buf;
+	sensor->id = cpu_to_le32(sensor_id);
+	if (s->async) {
+		sensor->flags = cpu_to_le32(SENSOR_READ_ASYNC);
+		ret = scmi_do_xfer_with_response(handle, t);
+		if (!ret) {
+			int i;
+			struct scmi_resp_sensor_reading_complete_v3 *resp;
+
+			resp = t->rx.buf;
+			/* Retrieve only the number of requested axis anyway */
+			if (le32_to_cpu(resp->id) == sensor_id)
+				for (i = 0; i < count; i++)
+					scmi_parse_sensor_readings(&readings[i],
+								   &resp->readings[i]);
+			else
+				ret = -EPROTO;
+		}
+	} else {
+		sensor->flags = cpu_to_le32(0);
+		ret = scmi_do_xfer(handle, t);
+		if (!ret) {
+			int i;
+			struct scmi_sensor_reading_le *resp_readings;
+
+			resp_readings = t->rx.buf;
+			for (i = 0; i < count; i++)
+				scmi_parse_sensor_readings(&readings[i],
+							   &resp_readings[i]);
+		}
+	}
+
+	scmi_xfer_put(handle, t);
+	return ret;
+}
+
 static const struct scmi_sensor_info *
 scmi_sensor_info_get(const struct scmi_handle *handle, u32 sensor_id)
 {
@@ -630,6 +744,7 @@ static const struct scmi_sensor_ops sensor_ops = {
 	.info_get = scmi_sensor_info_get,
 	.trip_point_config = scmi_sensor_trip_point_config,
 	.reading_get = scmi_sensor_reading_get,
+	.reading_get_timestamped = scmi_sensor_reading_get_timestamped,
 };
 
 static int scmi_sensor_set_notify_enabled(const struct scmi_handle *handle,
diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h
index 0792b0be25a3..0c52bf0cbee4 100644
--- a/include/linux/scmi_protocol.h
+++ b/include/linux/scmi_protocol.h
@@ -149,6 +149,20 @@ struct scmi_power_ops {
 			 u32 *state);
 };
 
+/**
+ * scmi_sensor_reading  - represent a timestamped read
+ *
+ * Used by @reading_get_timestamped method.
+ *
+ * @value: The signed value sensor read.
+ * @timestamp: An unsigned timestamp for the sensor read, as provided by
+ *	       SCMI platform. Set to zero when not available.
+ */
+struct scmi_sensor_reading {
+	long long value;
+	unsigned long long timestamp;
+};
+
 /**
  * scmi_range_attrs  - specifies a sensor or axis values' range
  * @min_range: The minimum value which can be represented by the sensor/axis.
@@ -390,6 +404,11 @@ enum scmi_sensor_class {
  * @info_get: get the information of the specified sensor
  * @trip_point_config: selects and configures a trip-point of interest
  * @reading_get: gets the current value of the sensor
+ * @reading_get_timestamped: gets the current value and timestamp, when
+ *			     available, of the sensor. (as of v3.0 spec)
+ *			     Supports multi-axis sensors for sensors which
+ *			     supports it and if the @reading array size of
+ *			     @count entry equals the sensor num_axis
  */
 struct scmi_sensor_ops {
 	int (*count_get)(const struct scmi_handle *handle);
@@ -399,6 +418,9 @@ struct scmi_sensor_ops {
 				 u32 sensor_id, u8 trip_id, u64 trip_value);
 	int (*reading_get)(const struct scmi_handle *handle, u32 sensor_id,
 			   u64 *value);
+	int (*reading_get_timestamped)(const struct scmi_handle *handle,
+				       u32 sensor_id, u8 count,
+				       struct scmi_sensor_reading *readings);
 };
 
 /**
-- 
cgit v1.2.3


From 7b83c5f41088987d04e24c3af0e1fb9f43b747b5 Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Thu, 19 Nov 2020 17:49:05 +0000
Subject: firmware: arm_scmi: Add SCMI v3.0 sensor configuration support

Add SCMI v3.0 sensor support for CONFIG_GET/CONFIG_SET commands.

Link: https://lore.kernel.org/r/20201119174906.43862-6-cristian.marussi@arm.com
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_scmi/sensors.c | 63 +++++++++++++++++++++++++++++++++++++
 include/linux/scmi_protocol.h       | 37 ++++++++++++++++++++++
 2 files changed, 100 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/firmware/arm_scmi/sensors.c b/drivers/firmware/arm_scmi/sensors.c
index 2239af5f9e6e..10c271d430e7 100644
--- a/drivers/firmware/arm_scmi/sensors.c
+++ b/drivers/firmware/arm_scmi/sensors.c
@@ -23,6 +23,8 @@ enum scmi_sensor_protocol_cmd {
 	SENSOR_READING_GET = 0x6,
 	SENSOR_AXIS_DESCRIPTION_GET = 0x7,
 	SENSOR_LIST_UPDATE_INTERVALS = 0x8,
+	SENSOR_CONFIG_GET = 0x9,
+	SENSOR_CONFIG_SET = 0xA,
 };
 
 struct scmi_msg_resp_sensor_attributes {
@@ -149,6 +151,11 @@ struct scmi_msg_set_sensor_trip_point {
 	__le32 value_high;
 };
 
+struct scmi_msg_sensor_config_set {
+	__le32 id;
+	__le32 sensor_config;
+};
+
 struct scmi_msg_sensor_reading_get {
 	__le32 id;
 	__le32 flags;
@@ -592,6 +599,60 @@ scmi_sensor_trip_point_config(const struct scmi_handle *handle, u32 sensor_id,
 	return ret;
 }
 
+static int scmi_sensor_config_get(const struct scmi_handle *handle,
+				  u32 sensor_id, u32 *sensor_config)
+{
+	int ret;
+	struct scmi_xfer *t;
+
+	ret = scmi_xfer_get_init(handle, SENSOR_CONFIG_GET,
+				 SCMI_PROTOCOL_SENSOR, sizeof(__le32),
+				 sizeof(__le32), &t);
+	if (ret)
+		return ret;
+
+	put_unaligned_le32(cpu_to_le32(sensor_id), t->tx.buf);
+	ret = scmi_do_xfer(handle, t);
+	if (!ret) {
+		struct sensors_info *si = handle->sensor_priv;
+		struct scmi_sensor_info *s = si->sensors + sensor_id;
+
+		*sensor_config = get_unaligned_le64(t->rx.buf);
+		s->sensor_config = *sensor_config;
+	}
+
+	scmi_xfer_put(handle, t);
+	return ret;
+}
+
+static int scmi_sensor_config_set(const struct scmi_handle *handle,
+				  u32 sensor_id, u32 sensor_config)
+{
+	int ret;
+	struct scmi_xfer *t;
+	struct scmi_msg_sensor_config_set *msg;
+
+	ret = scmi_xfer_get_init(handle, SENSOR_CONFIG_SET,
+				 SCMI_PROTOCOL_SENSOR, sizeof(*msg), 0, &t);
+	if (ret)
+		return ret;
+
+	msg = t->tx.buf;
+	msg->id = cpu_to_le32(sensor_id);
+	msg->sensor_config = cpu_to_le32(sensor_config);
+
+	ret = scmi_do_xfer(handle, t);
+	if (!ret) {
+		struct sensors_info *si = handle->sensor_priv;
+		struct scmi_sensor_info *s = si->sensors + sensor_id;
+
+		s->sensor_config = sensor_config;
+	}
+
+	scmi_xfer_put(handle, t);
+	return ret;
+}
+
 /**
  * scmi_sensor_reading_get  - Read scalar sensor value
  * @handle: Platform handle
@@ -745,6 +806,8 @@ static const struct scmi_sensor_ops sensor_ops = {
 	.trip_point_config = scmi_sensor_trip_point_config,
 	.reading_get = scmi_sensor_reading_get,
 	.reading_get_timestamped = scmi_sensor_reading_get_timestamped,
+	.config_get = scmi_sensor_config_get,
+	.config_set = scmi_sensor_config_set,
 };
 
 static int scmi_sensor_set_notify_enabled(const struct scmi_handle *handle,
diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h
index 0c52bf0cbee4..7e9e2cd3d46b 100644
--- a/include/linux/scmi_protocol.h
+++ b/include/linux/scmi_protocol.h
@@ -286,7 +286,38 @@ struct scmi_sensor_info {
 	unsigned int num_axis;
 	struct scmi_sensor_axis_info *axis;
 	struct scmi_sensor_intervals_info intervals;
+	unsigned int sensor_config;
+#define SCMI_SENS_CFG_UPDATE_SECS_MASK		GENMASK(31, 16)
+#define SCMI_SENS_CFG_GET_UPDATE_SECS(x)				\
+	FIELD_GET(SCMI_SENS_CFG_UPDATE_SECS_MASK, (x))
+
+#define SCMI_SENS_CFG_UPDATE_EXP_MASK		GENMASK(15, 11)
+#define SCMI_SENS_CFG_GET_UPDATE_EXP(x)					\
+	({								\
+		int __signed_exp =					\
+			FIELD_GET(SCMI_SENS_CFG_UPDATE_EXP_MASK, (x));	\
+									\
+		if (__signed_exp & BIT(4))				\
+			__signed_exp |= GENMASK(31, 5);			\
+		__signed_exp;						\
+	})
+
+#define SCMI_SENS_CFG_ROUND_MASK		GENMASK(10, 9)
+#define SCMI_SENS_CFG_ROUND_AUTO		2
+#define SCMI_SENS_CFG_ROUND_UP			1
+#define SCMI_SENS_CFG_ROUND_DOWN		0
+
+#define SCMI_SENS_CFG_TSTAMP_ENABLED_MASK	BIT(1)
+#define SCMI_SENS_CFG_TSTAMP_ENABLE		1
+#define SCMI_SENS_CFG_TSTAMP_DISABLE		0
+#define SCMI_SENS_CFG_IS_TSTAMP_ENABLED(x)				\
+	FIELD_GET(SCMI_SENS_CFG_TSTAMP_ENABLED_MASK, (x))
+
+#define SCMI_SENS_CFG_SENSOR_ENABLED_MASK	BIT(0)
+#define SCMI_SENS_CFG_SENSOR_ENABLE		1
+#define SCMI_SENS_CFG_SENSOR_DISABLE		0
 	char name[SCMI_MAX_STR_SIZE];
+#define SCMI_SENS_CFG_IS_ENABLED(x)		FIELD_GET(BIT(0), (x))
 	bool extended_scalar_attrs;
 	unsigned int sensor_power;
 	unsigned int resolution;
@@ -409,6 +440,8 @@ enum scmi_sensor_class {
  *			     Supports multi-axis sensors for sensors which
  *			     supports it and if the @reading array size of
  *			     @count entry equals the sensor num_axis
+ * @config_get: Get sensor current configuration
+ * @config_set: Set sensor current configuration
  */
 struct scmi_sensor_ops {
 	int (*count_get)(const struct scmi_handle *handle);
@@ -421,6 +454,10 @@ struct scmi_sensor_ops {
 	int (*reading_get_timestamped)(const struct scmi_handle *handle,
 				       u32 sensor_id, u8 count,
 				       struct scmi_sensor_reading *readings);
+	int (*config_get)(const struct scmi_handle *handle,
+			  u32 sensor_id, u32 *sensor_config);
+	int (*config_set)(const struct scmi_handle *handle,
+			  u32 sensor_id, u32 sensor_config);
 };
 
 /**
-- 
cgit v1.2.3


From e3811190acf85c63518fbddaa28bcbfab2baa58d Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Thu, 19 Nov 2020 17:49:06 +0000
Subject: firmware: arm_scmi: Add SCMI v3.0 sensor notifications

Add support for new SCMI v3.0 SENSOR_UPDATE notification.

Link: https://lore.kernel.org/r/20201119174906.43862-7-cristian.marussi@arm.com
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_scmi/sensors.c | 124 ++++++++++++++++++++++++++++++------
 include/linux/scmi_protocol.h       |   9 +++
 2 files changed, 114 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/arm_scmi/sensors.c b/drivers/firmware/arm_scmi/sensors.c
index 10c271d430e7..b3d7c08c09a0 100644
--- a/drivers/firmware/arm_scmi/sensors.c
+++ b/drivers/firmware/arm_scmi/sensors.c
@@ -25,6 +25,7 @@ enum scmi_sensor_protocol_cmd {
 	SENSOR_LIST_UPDATE_INTERVALS = 0x8,
 	SENSOR_CONFIG_GET = 0x9,
 	SENSOR_CONFIG_SET = 0xA,
+	SENSOR_CONTINUOUS_UPDATE_NOTIFY = 0xB,
 };
 
 struct scmi_msg_resp_sensor_attributes {
@@ -132,10 +133,10 @@ struct scmi_msg_resp_sensor_list_update_intervals {
 	__le32 intervals[];
 };
 
-struct scmi_msg_sensor_trip_point_notify {
+struct scmi_msg_sensor_request_notify {
 	__le32 id;
 	__le32 event_control;
-#define SENSOR_TP_NOTIFY_ALL	BIT(0)
+#define SENSOR_NOTIFY_ALL	BIT(0)
 };
 
 struct scmi_msg_set_sensor_trip_point {
@@ -185,6 +186,12 @@ struct scmi_sensor_trip_notify_payld {
 	__le32 trip_point_desc;
 };
 
+struct scmi_sensor_update_notify_payld {
+	__le32 agent_id;
+	__le32 sensor_id;
+	struct scmi_sensor_reading_le readings[];
+};
+
 struct sensors_info {
 	u32 version;
 	int num_sensors;
@@ -550,15 +557,16 @@ out:
 	return ret;
 }
 
-static int scmi_sensor_trip_point_notify(const struct scmi_handle *handle,
-					 u32 sensor_id, bool enable)
+static inline int
+scmi_sensor_request_notify(const struct scmi_handle *handle, u32 sensor_id,
+			   u8 message_id, bool enable)
 {
 	int ret;
-	u32 evt_cntl = enable ? SENSOR_TP_NOTIFY_ALL : 0;
+	u32 evt_cntl = enable ? SENSOR_NOTIFY_ALL : 0;
 	struct scmi_xfer *t;
-	struct scmi_msg_sensor_trip_point_notify *cfg;
+	struct scmi_msg_sensor_request_notify *cfg;
 
-	ret = scmi_xfer_get_init(handle, SENSOR_TRIP_POINT_NOTIFY,
+	ret = scmi_xfer_get_init(handle, message_id,
 				 SCMI_PROTOCOL_SENSOR, sizeof(*cfg), 0, &t);
 	if (ret)
 		return ret;
@@ -573,6 +581,23 @@ static int scmi_sensor_trip_point_notify(const struct scmi_handle *handle,
 	return ret;
 }
 
+static int scmi_sensor_trip_point_notify(const struct scmi_handle *handle,
+					 u32 sensor_id, bool enable)
+{
+	return scmi_sensor_request_notify(handle, sensor_id,
+					  SENSOR_TRIP_POINT_NOTIFY,
+					  enable);
+}
+
+static int
+scmi_sensor_continuous_update_notify(const struct scmi_handle *handle,
+				     u32 sensor_id, bool enable)
+{
+	return scmi_sensor_request_notify(handle, sensor_id,
+					  SENSOR_CONTINUOUS_UPDATE_NOTIFY,
+					  enable);
+}
+
 static int
 scmi_sensor_trip_point_config(const struct scmi_handle *handle, u32 sensor_id,
 			      u8 trip_id, u64 trip_value)
@@ -815,7 +840,19 @@ static int scmi_sensor_set_notify_enabled(const struct scmi_handle *handle,
 {
 	int ret;
 
-	ret = scmi_sensor_trip_point_notify(handle, src_id, enable);
+	switch (evt_id) {
+	case SCMI_EVENT_SENSOR_TRIP_POINT_EVENT:
+		ret = scmi_sensor_trip_point_notify(handle, src_id, enable);
+		break;
+	case SCMI_EVENT_SENSOR_UPDATE:
+		ret = scmi_sensor_continuous_update_notify(handle, src_id,
+							   enable);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
 	if (ret)
 		pr_debug("FAIL_ENABLED - evt[%X] dom[%d] - ret:%d\n",
 			 evt_id, src_id, ret);
@@ -828,20 +865,59 @@ static void *scmi_sensor_fill_custom_report(const struct scmi_handle *handle,
 					    const void *payld, size_t payld_sz,
 					    void *report, u32 *src_id)
 {
-	const struct scmi_sensor_trip_notify_payld *p = payld;
-	struct scmi_sensor_trip_point_report *r = report;
+	void *rep = NULL;
 
-	if (evt_id != SCMI_EVENT_SENSOR_TRIP_POINT_EVENT ||
-	    sizeof(*p) != payld_sz)
-		return NULL;
+	switch (evt_id) {
+	case SCMI_EVENT_SENSOR_TRIP_POINT_EVENT:
+	{
+		const struct scmi_sensor_trip_notify_payld *p = payld;
+		struct scmi_sensor_trip_point_report *r = report;
 
-	r->timestamp = timestamp;
-	r->agent_id = le32_to_cpu(p->agent_id);
-	r->sensor_id = le32_to_cpu(p->sensor_id);
-	r->trip_point_desc = le32_to_cpu(p->trip_point_desc);
-	*src_id = r->sensor_id;
+		if (sizeof(*p) != payld_sz)
+			break;
 
-	return r;
+		r->timestamp = timestamp;
+		r->agent_id = le32_to_cpu(p->agent_id);
+		r->sensor_id = le32_to_cpu(p->sensor_id);
+		r->trip_point_desc = le32_to_cpu(p->trip_point_desc);
+		*src_id = r->sensor_id;
+		rep = r;
+		break;
+	}
+	case SCMI_EVENT_SENSOR_UPDATE:
+	{
+		int i;
+		struct scmi_sensor_info *s;
+		const struct scmi_sensor_update_notify_payld *p = payld;
+		struct scmi_sensor_update_report *r = report;
+		struct sensors_info *sinfo = handle->sensor_priv;
+
+		/* payld_sz is variable for this event */
+		r->sensor_id = le32_to_cpu(p->sensor_id);
+		if (r->sensor_id >= sinfo->num_sensors)
+			break;
+		r->timestamp = timestamp;
+		r->agent_id = le32_to_cpu(p->agent_id);
+		s = &sinfo->sensors[r->sensor_id];
+		/*
+		 * The generated report r (@struct scmi_sensor_update_report)
+		 * was pre-allocated to contain up to SCMI_MAX_NUM_SENSOR_AXIS
+		 * readings: here it is filled with the effective @num_axis
+		 * readings defined for this sensor or 1 for scalar sensors.
+		 */
+		r->readings_count = s->num_axis ?: 1;
+		for (i = 0; i < r->readings_count; i++)
+			scmi_parse_sensor_readings(&r->readings[i],
+						   &p->readings[i]);
+		*src_id = r->sensor_id;
+		rep = r;
+		break;
+	}
+	default:
+		break;
+	}
+
+	return rep;
 }
 
 static const struct scmi_event sensor_events[] = {
@@ -850,6 +926,16 @@ static const struct scmi_event sensor_events[] = {
 		.max_payld_sz = sizeof(struct scmi_sensor_trip_notify_payld),
 		.max_report_sz = sizeof(struct scmi_sensor_trip_point_report),
 	},
+	{
+		.id = SCMI_EVENT_SENSOR_UPDATE,
+		.max_payld_sz =
+			sizeof(struct scmi_sensor_update_notify_payld) +
+			 SCMI_MAX_NUM_SENSOR_AXIS *
+			 sizeof(struct scmi_sensor_reading_le),
+		.max_report_sz = sizeof(struct scmi_sensor_update_report) +
+				  SCMI_MAX_NUM_SENSOR_AXIS *
+				  sizeof(struct scmi_sensor_reading),
+	},
 };
 
 static const struct scmi_event_ops sensor_event_ops = {
diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h
index 7e9e2cd3d46b..be0be5ff7514 100644
--- a/include/linux/scmi_protocol.h
+++ b/include/linux/scmi_protocol.h
@@ -657,6 +657,7 @@ enum scmi_notification_events {
 	SCMI_EVENT_PERFORMANCE_LIMITS_CHANGED = 0x0,
 	SCMI_EVENT_PERFORMANCE_LEVEL_CHANGED = 0x1,
 	SCMI_EVENT_SENSOR_TRIP_POINT_EVENT = 0x0,
+	SCMI_EVENT_SENSOR_UPDATE = 0x1,
 	SCMI_EVENT_RESET_ISSUED = 0x0,
 	SCMI_EVENT_BASE_ERROR_EVENT = 0x0,
 	SCMI_EVENT_SYSTEM_POWER_STATE_NOTIFIER = 0x0,
@@ -698,6 +699,14 @@ struct scmi_sensor_trip_point_report {
 	unsigned int	trip_point_desc;
 };
 
+struct scmi_sensor_update_report {
+	ktime_t				timestamp;
+	unsigned int			agent_id;
+	unsigned int			sensor_id;
+	unsigned int			readings_count;
+	struct scmi_sensor_reading	readings[];
+};
+
 struct scmi_reset_issued_report {
 	ktime_t		timestamp;
 	unsigned int	agent_id;
-- 
cgit v1.2.3


From bc2dc4406c463174613047d8b7946e12c8808cda Mon Sep 17 00:00:00 2001
From: Nick Desaulniers <ndesaulniers@google.com>
Date: Sat, 21 Nov 2020 22:17:01 -0800
Subject: compiler-clang: remove version check for BPF Tracing

bpftrace parses the kernel headers and uses Clang under the hood.

Remove the version check when __BPF_TRACING__ is defined (as bpftrace
does) so that this tool can continue to parse kernel headers, even with
older clang sources.

Fixes: commit 1f7a44f63e6c ("compiler-clang: add build check for clang 10.0.1")
Reported-by: Chen Yu <yu.chen.surf@gmail.com>
Reported-by: Jarkko Sakkinen <jarkko@kernel.org>
Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Jarkko Sakkinen <jarkko@kernel.org>
Acked-by: Jarkko Sakkinen <jarkko@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Acked-by: Nathan Chancellor <natechancellor@gmail.com>
Acked-by: Miguel Ojeda <ojeda@kernel.org>
Link: https://lkml.kernel.org/r/20201104191052.390657-1-ndesaulniers@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/compiler-clang.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index dd7233c48bf3..98cff1b4b088 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -8,8 +8,10 @@
 		     + __clang_patchlevel__)
 
 #if CLANG_VERSION < 100001
+#ifndef __BPF_TRACING__
 # error Sorry, your version of Clang is too old - please use 10.0.1 or newer.
 #endif
+#endif
 
 /* Compiler specific definitions for Clang compiler */
 
-- 
cgit v1.2.3


From a927bd6ba952d13c52b8b385030943032f659a3e Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Sat, 21 Nov 2020 22:17:05 -0800
Subject: mm: fix phys_to_target_node() and memory_add_physaddr_to_nid()
 exports

The core-mm has a default __weak implementation of phys_to_target_node()
to mirror the weak definition of memory_add_physaddr_to_nid().  That
symbol is exported for modules.  However, while the export in
mm/memory_hotplug.c exported the symbol in the configuration cases of:

	CONFIG_NUMA_KEEP_MEMINFO=y
	CONFIG_MEMORY_HOTPLUG=y

...and:

	CONFIG_NUMA_KEEP_MEMINFO=n
	CONFIG_MEMORY_HOTPLUG=y

...it failed to export the symbol in the case of:

	CONFIG_NUMA_KEEP_MEMINFO=y
	CONFIG_MEMORY_HOTPLUG=n

Not only is that broken, but Christoph points out that the kernel should
not be exporting any __weak symbol, which means that
memory_add_physaddr_to_nid() example that phys_to_target_node() copied
is broken too.

Rework the definition of phys_to_target_node() and
memory_add_physaddr_to_nid() to not require weak symbols.  Move to the
common arch override design-pattern of an asm header defining a symbol
to replace the default implementation.

The only common header that all memory_add_physaddr_to_nid() producing
architectures implement is asm/sparsemem.h.  In fact, powerpc already
defines its memory_add_physaddr_to_nid() helper in sparsemem.h.
Double-down on that observation and define phys_to_target_node() where
necessary in asm/sparsemem.h.  An alternate consideration that was
discarded was to put this override in asm/numa.h, but that entangles
with the definition of MAX_NUMNODES relative to the inclusion of
linux/nodemask.h, and requires powerpc to grow a new header.

The dependency on NUMA_KEEP_MEMINFO for DEV_DAX_HMEM_DEVICES is invalid
now that the symbol is properly exported / stubbed in all combinations
of CONFIG_NUMA_KEEP_MEMINFO and CONFIG_MEMORY_HOTPLUG.

[dan.j.williams@intel.com: v4]
  Link: https://lkml.kernel.org/r/160461461867.1505359.5301571728749534585.stgit@dwillia2-desk3.amr.corp.intel.com
[dan.j.williams@intel.com: powerpc: fix create_section_mapping compile warning]
  Link: https://lkml.kernel.org/r/160558386174.2948926.2740149041249041764.stgit@dwillia2-desk3.amr.corp.intel.com

Fixes: a035b6bf863e ("mm/memory_hotplug: introduce default phys_to_target_node() implementation")
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Reported-by: Thomas Gleixner <tglx@linutronix.de>
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Tested-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Link: https://lkml.kernel.org/r/160447639846.1133764.7044090803980177548.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/ia64/include/asm/sparsemem.h    |  6 ++++++
 arch/powerpc/include/asm/mmzone.h    |  5 +++++
 arch/powerpc/include/asm/sparsemem.h |  5 ++---
 arch/powerpc/mm/mem.c                |  1 +
 arch/x86/include/asm/sparsemem.h     | 10 ++++++++++
 arch/x86/mm/numa.c                   |  2 ++
 drivers/dax/Kconfig                  |  1 -
 include/linux/memory_hotplug.h       | 14 --------------
 include/linux/numa.h                 | 30 +++++++++++++++++++++++++++++-
 mm/memory_hotplug.c                  | 18 ------------------
 10 files changed, 55 insertions(+), 37 deletions(-)

(limited to 'include/linux')

diff --git a/arch/ia64/include/asm/sparsemem.h b/arch/ia64/include/asm/sparsemem.h
index 336d0570e1fa..dd8c166ffd7b 100644
--- a/arch/ia64/include/asm/sparsemem.h
+++ b/arch/ia64/include/asm/sparsemem.h
@@ -18,4 +18,10 @@
 #endif
 
 #endif /* CONFIG_SPARSEMEM */
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+int memory_add_physaddr_to_nid(u64 addr);
+#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid
+#endif
+
 #endif /* _ASM_IA64_SPARSEMEM_H */
diff --git a/arch/powerpc/include/asm/mmzone.h b/arch/powerpc/include/asm/mmzone.h
index 91c69ff53a8a..6cda76b57c5d 100644
--- a/arch/powerpc/include/asm/mmzone.h
+++ b/arch/powerpc/include/asm/mmzone.h
@@ -46,5 +46,10 @@ u64 memory_hotplug_max(void);
 #define __HAVE_ARCH_RESERVED_KERNEL_PAGES
 #endif
 
+#ifdef CONFIG_MEMORY_HOTPLUG
+extern int create_section_mapping(unsigned long start, unsigned long end,
+				  int nid, pgprot_t prot);
+#endif
+
 #endif /* __KERNEL__ */
 #endif /* _ASM_MMZONE_H_ */
diff --git a/arch/powerpc/include/asm/sparsemem.h b/arch/powerpc/include/asm/sparsemem.h
index 1e6fa371cc38..d072866842e4 100644
--- a/arch/powerpc/include/asm/sparsemem.h
+++ b/arch/powerpc/include/asm/sparsemem.h
@@ -13,9 +13,9 @@
 #endif /* CONFIG_SPARSEMEM */
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-extern int create_section_mapping(unsigned long start, unsigned long end,
-				  int nid, pgprot_t prot);
 extern int remove_section_mapping(unsigned long start, unsigned long end);
+extern int memory_add_physaddr_to_nid(u64 start);
+#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid
 
 #ifdef CONFIG_NUMA
 extern int hot_add_scn_to_nid(unsigned long scn_addr);
@@ -26,6 +26,5 @@ static inline int hot_add_scn_to_nid(unsigned long scn_addr)
 }
 #endif /* CONFIG_NUMA */
 #endif /* CONFIG_MEMORY_HOTPLUG */
-
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_SPARSEMEM_H */
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 01ec2a252f09..3fc325bebe4d 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -50,6 +50,7 @@
 #include <asm/rtas.h>
 #include <asm/kasan.h>
 #include <asm/svm.h>
+#include <asm/mmzone.h>
 
 #include <mm/mmu_decl.h>
 
diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h
index 6bfc878f6771..6a9ccc1b2be5 100644
--- a/arch/x86/include/asm/sparsemem.h
+++ b/arch/x86/include/asm/sparsemem.h
@@ -28,4 +28,14 @@
 #endif
 
 #endif /* CONFIG_SPARSEMEM */
+
+#ifndef __ASSEMBLY__
+#ifdef CONFIG_NUMA_KEEP_MEMINFO
+extern int phys_to_target_node(phys_addr_t start);
+#define phys_to_target_node phys_to_target_node
+extern int memory_add_physaddr_to_nid(u64 start);
+#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid
+#endif
+#endif /* __ASSEMBLY__ */
+
 #endif /* _ASM_X86_SPARSEMEM_H */
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 44148691d78b..5eb4dc2b97da 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -938,6 +938,7 @@ int phys_to_target_node(phys_addr_t start)
 
 	return meminfo_to_nid(&numa_reserved_meminfo, start);
 }
+EXPORT_SYMBOL_GPL(phys_to_target_node);
 
 int memory_add_physaddr_to_nid(u64 start)
 {
@@ -947,4 +948,5 @@ int memory_add_physaddr_to_nid(u64 start)
 		nid = numa_meminfo.blk[0].nid;
 	return nid;
 }
+EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
 #endif
diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig
index 567428e10b7b..d2834c2cfa10 100644
--- a/drivers/dax/Kconfig
+++ b/drivers/dax/Kconfig
@@ -50,7 +50,6 @@ config DEV_DAX_HMEM
 	  Say M if unsure.
 
 config DEV_DAX_HMEM_DEVICES
-	depends on NUMA_KEEP_MEMINFO # for phys_to_target_node()
 	depends on DEV_DAX_HMEM && DAX=y
 	def_bool y
 
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index d65c6fdc5cfc..551093b74596 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -281,20 +281,6 @@ static inline bool movable_node_is_enabled(void)
 }
 #endif /* ! CONFIG_MEMORY_HOTPLUG */
 
-#ifdef CONFIG_NUMA
-extern int memory_add_physaddr_to_nid(u64 start);
-extern int phys_to_target_node(u64 start);
-#else
-static inline int memory_add_physaddr_to_nid(u64 start)
-{
-	return 0;
-}
-static inline int phys_to_target_node(u64 start)
-{
-	return 0;
-}
-#endif
-
 #if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT)
 /*
  * pgdat resizing functions
diff --git a/include/linux/numa.h b/include/linux/numa.h
index 8cb33ccfb671..cb44cfe2b725 100644
--- a/include/linux/numa.h
+++ b/include/linux/numa.h
@@ -21,13 +21,41 @@
 #endif
 
 #ifdef CONFIG_NUMA
+#include <linux/printk.h>
+#include <asm/sparsemem.h>
+
 /* Generic implementation available */
 int numa_map_to_online_node(int node);
-#else
+
+#ifndef memory_add_physaddr_to_nid
+static inline int memory_add_physaddr_to_nid(u64 start)
+{
+	pr_info_once("Unknown online node for memory at 0x%llx, assuming node 0\n",
+			start);
+	return 0;
+}
+#endif
+#ifndef phys_to_target_node
+static inline int phys_to_target_node(u64 start)
+{
+	pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n",
+			start);
+	return 0;
+}
+#endif
+#else /* !CONFIG_NUMA */
 static inline int numa_map_to_online_node(int node)
 {
 	return NUMA_NO_NODE;
 }
+static inline int memory_add_physaddr_to_nid(u64 start)
+{
+	return 0;
+}
+static inline int phys_to_target_node(u64 start)
+{
+	return 0;
+}
 #endif
 
 #endif /* _LINUX_NUMA_H */
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index b44d4c7ba73b..63b2e46b6555 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -350,24 +350,6 @@ int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages,
 	return err;
 }
 
-#ifdef CONFIG_NUMA
-int __weak memory_add_physaddr_to_nid(u64 start)
-{
-	pr_info_once("Unknown online node for memory at 0x%llx, assuming node 0\n",
-			start);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
-
-int __weak phys_to_target_node(u64 start)
-{
-	pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n",
-			start);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(phys_to_target_node);
-#endif
-
 /* find the smallest valid pfn in the range [start_pfn, end_pfn) */
 static unsigned long find_smallest_section_pfn(int nid, struct zone *zone,
 				     unsigned long start_pfn,
-- 
cgit v1.2.3


From 4349a83a3190c1d4414371161b0f4a4c3ccd3f9d Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Sat, 21 Nov 2020 22:17:08 -0800
Subject: mm: fix readahead_page_batch for retry entries

Both btrfs and fuse have reported faults caused by seeing a retry entry
instead of the page they were looking for.  This was caused by a missing
check in the iterator.

As can be seen in the below panic log, the accessing 0x402 causes a
panic.  In the xarray.h, 0x402 means RETRY_ENTRY.

  BUG: kernel NULL pointer dereference, address: 0000000000000402
  CPU: 14 PID: 306003 Comm: as Not tainted 5.9.0-1-amd64 #1 Debian 5.9.1-1
  Hardware name: Lenovo ThinkSystem SR665/7D2VCTO1WW, BIOS D8E106Q-1.01 05/30/2020
  RIP: 0010:fuse_readahead+0x152/0x470 [fuse]
  Code: 41 8b 57 18 4c 8d 54 10 ff 4c 89 d6 48 8d 7c 24 10 e8 d2 e3 28 f9 48 85 c0 0f 84 fe 00 00 00 44 89 f2 49 89 04 d4 44 8d 72 01 <48> 8b 10 41 8b 4f 1c 48 c1 ea 10 83 e2 01 80 fa 01 19 d2 81 e2 01
  RSP: 0018:ffffad99ceaebc50 EFLAGS: 00010246
  RAX: 0000000000000402 RBX: 0000000000000001 RCX: 0000000000000002
  RDX: 0000000000000000 RSI: ffff94c5af90bd98 RDI: ffffad99ceaebc60
  RBP: ffff94ddc1749a00 R08: 0000000000000402 R09: 0000000000000000
  R10: 0000000000000000 R11: 0000000000000100 R12: ffff94de6c429ce0
  R13: ffff94de6c4d3700 R14: 0000000000000001 R15: ffffad99ceaebd68
  FS:  00007f228c5c7040(0000) GS:ffff94de8ed80000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 0000000000000402 CR3: 0000001dbd9b4000 CR4: 0000000000350ee0
  Call Trace:
    read_pages+0x83/0x270
    page_cache_readahead_unbounded+0x197/0x230
    generic_file_buffered_read+0x57a/0xa20
    new_sync_read+0x112/0x1a0
    vfs_read+0xf8/0x180
    ksys_read+0x5f/0xe0
    do_syscall_64+0x33/0x80
    entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 042124cc64c3 ("mm: add new readahead_control API")
Reported-by: David Sterba <dsterba@suse.com>
Reported-by: Wonhyuk Yang <vvghjk1234@gmail.com>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: <stable@vger.kernel.org>
Link: https://lkml.kernel.org/r/20201103142852.8543-1-willy@infradead.org
Link: https://lkml.kernel.org/r/20201103124349.16722-1-vvghjk1234@gmail.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/pagemap.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index e1e19c1f9ec9..d5570deff400 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -906,6 +906,8 @@ static inline unsigned int __readahead_batch(struct readahead_control *rac,
 	xas_set(&xas, rac->_index);
 	rcu_read_lock();
 	xas_for_each(&xas, page, rac->_index + rac->_nr_pages - 1) {
+		if (xas_retry(&xas, page))
+			continue;
 		VM_BUG_ON_PAGE(!PageLocked(page), page);
 		VM_BUG_ON_PAGE(PageTail(page), page);
 		array[i++] = page;
-- 
cgit v1.2.3


From e44cdff05145b84293e3f424daa17e4f3ce0109c Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Thu, 19 Nov 2020 17:45:09 +0100
Subject: clk: samsung: Allow compile testing of Exynos, S3C64xx and S5Pv210

So far all Exynos, S3C64xx and S5Pv210 clock units were selected by
respective SOC/ARCH Kconfig option.  On a kernel built for selected
SoCs, this allowed to build only limited set of matching clock drivers.
However compile testing was not possible in such case as Makefile object
depends on SOC/ARCH option.

Add separate Kconfig options for each of them to be able to compile
test.

Link: https://lore.kernel.org/r/20201119164509.754851-1-krzk@kernel.org
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Acked-by: Chanwoo Choi <cw00.choi@samsung.com>
Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
---
 drivers/clk/samsung/Kconfig  | 67 ++++++++++++++++++++++++++++++++++++++++++--
 drivers/clk/samsung/Makefile | 22 +++++++--------
 include/linux/clk/samsung.h  |  4 +--
 3 files changed, 78 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/clk/samsung/Kconfig b/drivers/clk/samsung/Kconfig
index 57d4b3f20417..9323fcfac6cc 100644
--- a/drivers/clk/samsung/Kconfig
+++ b/drivers/clk/samsung/Kconfig
@@ -2,10 +2,73 @@
 # Recent Exynos platforms should just select COMMON_CLK_SAMSUNG:
 config COMMON_CLK_SAMSUNG
 	bool "Samsung Exynos clock controller support" if COMPILE_TEST
-	# Clocks on ARM64 SoCs (e.g. Exynos5433, Exynos7) are chosen by
-	# EXYNOS_ARM64_COMMON_CLK to avoid building them on ARMv7:
+	select S3C64XX_COMMON_CLK if ARM && ARCH_S3C64XX
+	select S5PV210_COMMON_CLK if ARM && ARCH_S5PV210
+	select EXYNOS_3250_COMMON_CLK if ARM && SOC_EXYNOS3250
+	select EXYNOS_4_COMMON_CLK if ARM && ARCH_EXYNOS4
+	select EXYNOS_5250_COMMON_CLK if ARM && SOC_EXYNOS5250
+	select EXYNOS_5260_COMMON_CLK if ARM && SOC_EXYNOS5260
+	select EXYNOS_5410_COMMON_CLK if ARM && SOC_EXYNOS5410
+	select EXYNOS_5420_COMMON_CLK if ARM && SOC_EXYNOS5420
 	select EXYNOS_ARM64_COMMON_CLK if ARM64 && ARCH_EXYNOS
 
+config S3C64XX_COMMON_CLK
+	bool "Samsung S3C64xx clock controller support" if COMPILE_TEST
+	depends on COMMON_CLK_SAMSUNG
+	help
+	  Support for the clock controller present on the Samsung S3C64xx SoCs.
+	  Choose Y here only if you build for this SoC.
+
+config S5PV210_COMMON_CLK
+	bool "Samsung S5Pv210 clock controller support" if COMPILE_TEST
+	depends on COMMON_CLK_SAMSUNG
+	help
+	  Support for the clock controller present on the Samsung S5Pv210 SoCs.
+	  Choose Y here only if you build for this SoC.
+
+config EXYNOS_3250_COMMON_CLK
+	bool "Samsung Exynos3250 clock controller support" if COMPILE_TEST
+	depends on COMMON_CLK_SAMSUNG
+	help
+	  Support for the clock controller present on the Samsung
+	  Exynos3250 SoCs. Choose Y here only if you build for this SoC.
+
+config EXYNOS_4_COMMON_CLK
+	bool "Samsung Exynos4 clock controller support" if COMPILE_TEST
+	depends on COMMON_CLK_SAMSUNG
+	help
+	  Support for the clock controller present on the Samsung
+	  Exynos4212 and Exynos4412 SoCs. Choose Y here only if you build for
+	  this SoC.
+
+config EXYNOS_5250_COMMON_CLK
+	bool "Samsung Exynos5250 clock controller support" if COMPILE_TEST
+	depends on COMMON_CLK_SAMSUNG
+	help
+	  Support for the clock controller present on the Samsung
+	  Exynos5250 SoCs. Choose Y here only if you build for this SoC.
+
+config EXYNOS_5260_COMMON_CLK
+	bool "Samsung Exynos5260 clock controller support" if COMPILE_TEST
+	depends on COMMON_CLK_SAMSUNG
+	help
+	  Support for the clock controller present on the Samsung
+	  Exynos5260 SoCs. Choose Y here only if you build for this SoC.
+
+config EXYNOS_5410_COMMON_CLK
+	bool "Samsung Exynos5410 clock controller support" if COMPILE_TEST
+	depends on COMMON_CLK_SAMSUNG
+	help
+	  Support for the clock controller present on the Samsung
+	  Exynos5410 SoCs. Choose Y here only if you build for this SoC.
+
+config EXYNOS_5420_COMMON_CLK
+	bool "Samsung Exynos5420 clock controller support" if COMPILE_TEST
+	depends on COMMON_CLK_SAMSUNG
+	help
+	  Support for the clock controller present on the Samsung
+	  Exynos5420 SoCs. Choose Y here only if you build for this SoC.
+
 config EXYNOS_ARM64_COMMON_CLK
 	bool "Samsung Exynos ARMv8-family clock controller support" if COMPILE_TEST
 	depends on COMMON_CLK_SAMSUNG
diff --git a/drivers/clk/samsung/Makefile b/drivers/clk/samsung/Makefile
index 1a4e6b787978..bb1433f11c88 100644
--- a/drivers/clk/samsung/Makefile
+++ b/drivers/clk/samsung/Makefile
@@ -4,15 +4,15 @@
 #
 
 obj-$(CONFIG_COMMON_CLK)	+= clk.o clk-pll.o clk-cpu.o
-obj-$(CONFIG_SOC_EXYNOS3250)	+= clk-exynos3250.o
-obj-$(CONFIG_ARCH_EXYNOS4)	+= clk-exynos4.o
-obj-$(CONFIG_ARCH_EXYNOS4)	+= clk-exynos4412-isp.o
-obj-$(CONFIG_SOC_EXYNOS5250)	+= clk-exynos5250.o
-obj-$(CONFIG_SOC_EXYNOS5250)	+= clk-exynos5-subcmu.o
-obj-$(CONFIG_SOC_EXYNOS5260)	+= clk-exynos5260.o
-obj-$(CONFIG_SOC_EXYNOS5410)	+= clk-exynos5410.o
-obj-$(CONFIG_SOC_EXYNOS5420)	+= clk-exynos5420.o
-obj-$(CONFIG_SOC_EXYNOS5420)	+= clk-exynos5-subcmu.o
+obj-$(CONFIG_EXYNOS_3250_COMMON_CLK)	+= clk-exynos3250.o
+obj-$(CONFIG_EXYNOS_4_COMMON_CLK)	+= clk-exynos4.o
+obj-$(CONFIG_EXYNOS_4_COMMON_CLK)	+= clk-exynos4412-isp.o
+obj-$(CONFIG_EXYNOS_5250_COMMON_CLK)	+= clk-exynos5250.o
+obj-$(CONFIG_EXYNOS_5250_COMMON_CLK)	+= clk-exynos5-subcmu.o
+obj-$(CONFIG_EXYNOS_5260_COMMON_CLK)	+= clk-exynos5260.o
+obj-$(CONFIG_EXYNOS_5410_COMMON_CLK)	+= clk-exynos5410.o
+obj-$(CONFIG_EXYNOS_5420_COMMON_CLK)	+= clk-exynos5420.o
+obj-$(CONFIG_EXYNOS_5420_COMMON_CLK)	+= clk-exynos5-subcmu.o
 obj-$(CONFIG_EXYNOS_ARM64_COMMON_CLK)	+= clk-exynos5433.o
 obj-$(CONFIG_EXYNOS_AUDSS_CLK_CON) += clk-exynos-audss.o
 obj-$(CONFIG_ARCH_EXYNOS)	+= clk-exynos-clkout.o
@@ -21,5 +21,5 @@ obj-$(CONFIG_S3C2410_COMMON_CLK)+= clk-s3c2410.o
 obj-$(CONFIG_S3C2410_COMMON_DCLK)+= clk-s3c2410-dclk.o
 obj-$(CONFIG_S3C2412_COMMON_CLK)+= clk-s3c2412.o
 obj-$(CONFIG_S3C2443_COMMON_CLK)+= clk-s3c2443.o
-obj-$(CONFIG_ARCH_S3C64XX)	+= clk-s3c64xx.o
-obj-$(CONFIG_ARCH_S5PV210)	+= clk-s5pv210.o clk-s5pv210-audss.o
+obj-$(CONFIG_S3C64XX_COMMON_CLK)	+= clk-s3c64xx.o
+obj-$(CONFIG_S5PV210_COMMON_CLK)	+= clk-s5pv210.o clk-s5pv210-audss.o
diff --git a/include/linux/clk/samsung.h b/include/linux/clk/samsung.h
index 79097e365f7f..38b774001712 100644
--- a/include/linux/clk/samsung.h
+++ b/include/linux/clk/samsung.h
@@ -10,7 +10,7 @@
 
 struct device_node;
 
-#ifdef CONFIG_ARCH_S3C64XX
+#ifdef CONFIG_S3C64XX_COMMON_CLK
 void s3c64xx_clk_init(struct device_node *np, unsigned long xtal_f,
 		      unsigned long xusbxti_f, bool s3c6400,
 		      void __iomem *base);
@@ -19,7 +19,7 @@ static inline void s3c64xx_clk_init(struct device_node *np,
 				    unsigned long xtal_f,
 				    unsigned long xusbxti_f,
 				    bool s3c6400, void __iomem *base) { }
-#endif /* CONFIG_ARCH_S3C64XX */
+#endif /* CONFIG_S3C64XX_COMMON_CLK */
 
 #ifdef CONFIG_S3C2410_COMMON_CLK
 void s3c2410_common_clk_init(struct device_node *np, unsigned long xti_f,
-- 
cgit v1.2.3


From 769dda58d1f647a45270db2f02efe2e2de856709 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 13 Nov 2020 15:02:10 +0100
Subject: irqstat: Get rid of nmi_count() and __IRQ_STAT()

Nothing uses this anymore.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://lore.kernel.org/r/20201113141733.005212732@linutronix.de
---
 include/linux/irq_cpustat.h | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/irq_cpustat.h b/include/linux/irq_cpustat.h
index 6e8895cd4d92..78fb2de3ea4d 100644
--- a/include/linux/irq_cpustat.h
+++ b/include/linux/irq_cpustat.h
@@ -19,10 +19,6 @@
 
 #ifndef __ARCH_IRQ_STAT
 DECLARE_PER_CPU_ALIGNED(irq_cpustat_t, irq_stat);	/* defined in asm/hardirq.h */
-#define __IRQ_STAT(cpu, member)	(per_cpu(irq_stat.member, cpu))
 #endif
 
-/* arch dependent irq_stat fields */
-#define nmi_count(cpu)		__IRQ_STAT((cpu), __nmi_count)	/* i386 */
-
 #endif	/* __irq_cpustat_h */
-- 
cgit v1.2.3


From e091bc90cd2d65f48e4688faead2911558d177d7 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 13 Nov 2020 15:02:16 +0100
Subject: irqstat: Move declaration into asm-generic/hardirq.h

Move the declaration of the irq_cpustat per cpu variable to
asm-generic/hardirq.h and remove the now empty linux/irq_cpustat.h header.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://lore.kernel.org/r/20201113141733.737377332@linutronix.de
---
 include/asm-generic/hardirq.h |  3 ++-
 include/linux/irq_cpustat.h   | 24 ------------------------
 2 files changed, 2 insertions(+), 25 deletions(-)
 delete mode 100644 include/linux/irq_cpustat.h

(limited to 'include/linux')

diff --git a/include/asm-generic/hardirq.h b/include/asm-generic/hardirq.h
index f5dd99781e3c..7317e8258b48 100644
--- a/include/asm-generic/hardirq.h
+++ b/include/asm-generic/hardirq.h
@@ -12,7 +12,8 @@ typedef struct {
 #endif
 } ____cacheline_aligned irq_cpustat_t;
 
-#include <linux/irq_cpustat.h>	/* Standard mappings for irq_cpustat_t above */
+DECLARE_PER_CPU_ALIGNED(irq_cpustat_t, irq_stat);
+
 #include <linux/irq.h>
 
 #ifndef ack_bad_irq
diff --git a/include/linux/irq_cpustat.h b/include/linux/irq_cpustat.h
deleted file mode 100644
index 78fb2de3ea4d..000000000000
--- a/include/linux/irq_cpustat.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __irq_cpustat_h
-#define __irq_cpustat_h
-
-/*
- * Contains default mappings for irq_cpustat_t, used by almost every
- * architecture.  Some arch (like s390) have per cpu hardware pages and
- * they define their own mappings for irq_stat.
- *
- * Keith Owens <kaos@ocs.com.au> July 2000.
- */
-
-
-/*
- * Simple wrappers reducing source bloat.  Define all irq_stat fields
- * here, even ones that are arch dependent.  That way we get common
- * definitions instead of differing sets for each arch.
- */
-
-#ifndef __ARCH_IRQ_STAT
-DECLARE_PER_CPU_ALIGNED(irq_cpustat_t, irq_stat);	/* defined in asm/hardirq.h */
-#endif
-
-#endif	/* __irq_cpustat_h */
-- 
cgit v1.2.3


From 15115830c88751ba83068aa37da996602ddc6a61 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 13 Nov 2020 15:02:17 +0100
Subject: preempt: Cleanup the macro maze a bit

Make the macro maze consistent and prepare it for adding the RT variant for
BH accounting.

 - Use nmi_count() for the NMI portion of preempt count
 - Introduce in_hardirq() to make the naming consistent and non-ambiguos
 - Use the macros to create combined checks (e.g. in_task()) so the
   softirq representation for RT just falls into place.
 - Update comments and move the deprecated macros aside

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://lore.kernel.org/r/20201113141733.864469886@linutronix.de
---
 include/linux/preempt.h | 30 ++++++++++++++++--------------
 1 file changed, 16 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 7d9c1c0e149c..7547857516d5 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -77,31 +77,33 @@
 /* preempt_count() and related functions, depends on PREEMPT_NEED_RESCHED */
 #include <asm/preempt.h>
 
+#define nmi_count()	(preempt_count() & NMI_MASK)
 #define hardirq_count()	(preempt_count() & HARDIRQ_MASK)
 #define softirq_count()	(preempt_count() & SOFTIRQ_MASK)
-#define irq_count()	(preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \
-				 | NMI_MASK))
+#define irq_count()	(nmi_count() | hardirq_count() | softirq_count())
 
 /*
- * Are we doing bottom half or hardware interrupt processing?
+ * Macros to retrieve the current execution context:
  *
- * in_irq()       - We're in (hard) IRQ context
+ * in_nmi()		- We're in NMI context
+ * in_hardirq()		- We're in hard IRQ context
+ * in_serving_softirq()	- We're in softirq context
+ * in_task()		- We're in task context
+ */
+#define in_nmi()		(nmi_count())
+#define in_hardirq()		(hardirq_count())
+#define in_serving_softirq()	(softirq_count() & SOFTIRQ_OFFSET)
+#define in_task()		(!(in_nmi() | in_hardirq() | in_serving_softirq()))
+
+/*
+ * The following macros are deprecated and should not be used in new code:
+ * in_irq()       - Obsolete version of in_hardirq()
  * in_softirq()   - We have BH disabled, or are processing softirqs
  * in_interrupt() - We're in NMI,IRQ,SoftIRQ context or have BH disabled
- * in_serving_softirq() - We're in softirq context
- * in_nmi()       - We're in NMI context
- * in_task()	  - We're in task context
- *
- * Note: due to the BH disabled confusion: in_softirq(),in_interrupt() really
- *       should not be used in new code.
  */
 #define in_irq()		(hardirq_count())
 #define in_softirq()		(softirq_count())
 #define in_interrupt()		(irq_count())
-#define in_serving_softirq()	(softirq_count() & SOFTIRQ_OFFSET)
-#define in_nmi()		(preempt_count() & NMI_MASK)
-#define in_task()		(!(preempt_count() & \
-				   (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET)))
 
 /*
  * The preempt_count offset after preempt_disable();
-- 
cgit v1.2.3


From cb4789b0d19ff231ce9f73376a023341300aed96 Mon Sep 17 00:00:00 2001
From: Jean-Philippe Brucker <jean-philippe@linaro.org>
Date: Fri, 6 Nov 2020 16:50:47 +0100
Subject: iommu/ioasid: Add ioasid references

Let IOASID users take references to existing ioasids with ioasid_get().
ioasid_put() drops a reference and only frees the ioasid when its
reference number is zero. It returns true if the ioasid was freed.
For drivers that don't call ioasid_get(), ioasid_put() is the same as
ioasid_free().

Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20201106155048.997886-2-jean-philippe@linaro.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/intel/iommu.c |  4 ++--
 drivers/iommu/intel/svm.c   |  6 +++---
 drivers/iommu/ioasid.c      | 38 ++++++++++++++++++++++++++++++++++----
 include/linux/ioasid.h      | 10 ++++++++--
 4 files changed, 47 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 1b1ca63e6bbe..8b26223979a2 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -5198,7 +5198,7 @@ static void auxiliary_unlink_device(struct dmar_domain *domain,
 	domain->auxd_refcnt--;
 
 	if (!domain->auxd_refcnt && domain->default_pasid > 0)
-		ioasid_free(domain->default_pasid);
+		ioasid_put(domain->default_pasid);
 }
 
 static int aux_domain_add_dev(struct dmar_domain *domain,
@@ -5259,7 +5259,7 @@ attach_failed:
 	spin_unlock(&iommu->lock);
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 	if (!domain->auxd_refcnt && domain->default_pasid > 0)
-		ioasid_free(domain->default_pasid);
+		ioasid_put(domain->default_pasid);
 
 	return ret;
 }
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index 3242ebd0bca3..4fa248b98031 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -598,7 +598,7 @@ intel_svm_bind_mm(struct device *dev, unsigned int flags,
 		if (mm) {
 			ret = mmu_notifier_register(&svm->notifier, mm);
 			if (ret) {
-				ioasid_free(svm->pasid);
+				ioasid_put(svm->pasid);
 				kfree(svm);
 				kfree(sdev);
 				goto out;
@@ -616,7 +616,7 @@ intel_svm_bind_mm(struct device *dev, unsigned int flags,
 		if (ret) {
 			if (mm)
 				mmu_notifier_unregister(&svm->notifier, mm);
-			ioasid_free(svm->pasid);
+			ioasid_put(svm->pasid);
 			kfree(svm);
 			kfree(sdev);
 			goto out;
@@ -689,7 +689,7 @@ static int intel_svm_unbind_mm(struct device *dev, u32 pasid)
 			kfree_rcu(sdev, rcu);
 
 			if (list_empty(&svm->devs)) {
-				ioasid_free(svm->pasid);
+				ioasid_put(svm->pasid);
 				if (svm->mm) {
 					mmu_notifier_unregister(&svm->notifier, svm->mm);
 					/* Clear mm's pasid. */
diff --git a/drivers/iommu/ioasid.c b/drivers/iommu/ioasid.c
index 0f8dd377aada..50ee27bbd04e 100644
--- a/drivers/iommu/ioasid.c
+++ b/drivers/iommu/ioasid.c
@@ -2,7 +2,7 @@
 /*
  * I/O Address Space ID allocator. There is one global IOASID space, split into
  * subsets. Users create a subset with DECLARE_IOASID_SET, then allocate and
- * free IOASIDs with ioasid_alloc and ioasid_free.
+ * free IOASIDs with ioasid_alloc and ioasid_put.
  */
 #include <linux/ioasid.h>
 #include <linux/module.h>
@@ -15,6 +15,7 @@ struct ioasid_data {
 	struct ioasid_set *set;
 	void *private;
 	struct rcu_head rcu;
+	refcount_t refs;
 };
 
 /*
@@ -314,6 +315,7 @@ ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, ioasid_t max,
 
 	data->set = set;
 	data->private = private;
+	refcount_set(&data->refs, 1);
 
 	/*
 	 * Custom allocator needs allocator data to perform platform specific
@@ -346,11 +348,34 @@ exit_free:
 EXPORT_SYMBOL_GPL(ioasid_alloc);
 
 /**
- * ioasid_free - Free an IOASID
+ * ioasid_get - obtain a reference to the IOASID
+ */
+void ioasid_get(ioasid_t ioasid)
+{
+	struct ioasid_data *ioasid_data;
+
+	spin_lock(&ioasid_allocator_lock);
+	ioasid_data = xa_load(&active_allocator->xa, ioasid);
+	if (ioasid_data)
+		refcount_inc(&ioasid_data->refs);
+	else
+		WARN_ON(1);
+	spin_unlock(&ioasid_allocator_lock);
+}
+EXPORT_SYMBOL_GPL(ioasid_get);
+
+/**
+ * ioasid_put - Release a reference to an ioasid
  * @ioasid: the ID to remove
+ *
+ * Put a reference to the IOASID, free it when the number of references drops to
+ * zero.
+ *
+ * Return: %true if the IOASID was freed, %false otherwise.
  */
-void ioasid_free(ioasid_t ioasid)
+bool ioasid_put(ioasid_t ioasid)
 {
+	bool free = false;
 	struct ioasid_data *ioasid_data;
 
 	spin_lock(&ioasid_allocator_lock);
@@ -360,6 +385,10 @@ void ioasid_free(ioasid_t ioasid)
 		goto exit_unlock;
 	}
 
+	free = refcount_dec_and_test(&ioasid_data->refs);
+	if (!free)
+		goto exit_unlock;
+
 	active_allocator->ops->free(ioasid, active_allocator->ops->pdata);
 	/* Custom allocator needs additional steps to free the xa element */
 	if (active_allocator->flags & IOASID_ALLOCATOR_CUSTOM) {
@@ -369,8 +398,9 @@ void ioasid_free(ioasid_t ioasid)
 
 exit_unlock:
 	spin_unlock(&ioasid_allocator_lock);
+	return free;
 }
-EXPORT_SYMBOL_GPL(ioasid_free);
+EXPORT_SYMBOL_GPL(ioasid_put);
 
 /**
  * ioasid_find - Find IOASID data
diff --git a/include/linux/ioasid.h b/include/linux/ioasid.h
index 6f000d7a0ddc..e9dacd4b9f6b 100644
--- a/include/linux/ioasid.h
+++ b/include/linux/ioasid.h
@@ -34,7 +34,8 @@ struct ioasid_allocator_ops {
 #if IS_ENABLED(CONFIG_IOASID)
 ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, ioasid_t max,
 		      void *private);
-void ioasid_free(ioasid_t ioasid);
+void ioasid_get(ioasid_t ioasid);
+bool ioasid_put(ioasid_t ioasid);
 void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid,
 		  bool (*getter)(void *));
 int ioasid_register_allocator(struct ioasid_allocator_ops *allocator);
@@ -48,10 +49,15 @@ static inline ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min,
 	return INVALID_IOASID;
 }
 
-static inline void ioasid_free(ioasid_t ioasid)
+static inline void ioasid_get(ioasid_t ioasid)
 {
 }
 
+static inline bool ioasid_put(ioasid_t ioasid)
+{
+	return false;
+}
+
 static inline void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid,
 				bool (*getter)(void *))
 {
-- 
cgit v1.2.3


From b713c195d59332277a31a59c91f755e53b5b302b Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Sat, 5 Sep 2020 11:13:35 -0600
Subject: net: provide __sys_shutdown_sock() that takes a socket

No functional changes in this patch, needed to provide io_uring support
for shutdown(2).

Cc: netdev@vger.kernel.org
Cc: David S. Miller <davem@davemloft.net>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/socket.h |  1 +
 net/socket.c           | 15 ++++++++++++---
 2 files changed, 13 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/socket.h b/include/linux/socket.h
index e9cb30d8cbfb..385894b4a8bb 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -436,6 +436,7 @@ extern int __sys_getpeername(int fd, struct sockaddr __user *usockaddr,
 			     int __user *usockaddr_len);
 extern int __sys_socketpair(int family, int type, int protocol,
 			    int __user *usockvec);
+extern int __sys_shutdown_sock(struct socket *sock, int how);
 extern int __sys_shutdown(int fd, int how);
 
 extern struct ns_common *get_net_ns(struct ns_common *ns);
diff --git a/net/socket.c b/net/socket.c
index 6e6cccc2104f..4b615c719765 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2192,6 +2192,17 @@ SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname,
  *	Shutdown a socket.
  */
 
+int __sys_shutdown_sock(struct socket *sock, int how)
+{
+	int err;
+
+	err = security_socket_shutdown(sock, how);
+	if (!err)
+		err = sock->ops->shutdown(sock, how);
+
+	return err;
+}
+
 int __sys_shutdown(int fd, int how)
 {
 	int err, fput_needed;
@@ -2199,9 +2210,7 @@ int __sys_shutdown(int fd, int how)
 
 	sock = sockfd_lookup_light(fd, &err, &fput_needed);
 	if (sock != NULL) {
-		err = security_socket_shutdown(sock, how);
-		if (!err)
-			err = sock->ops->shutdown(sock, how);
+		err = __sys_shutdown_sock(sock, how);
 		fput_light(sock->file, fput_needed);
 	}
 	return err;
-- 
cgit v1.2.3


From 23acdc76f1798b090bb9dcc90671cd29d929834e Mon Sep 17 00:00:00 2001
From: Peter Collingbourne <pcc@google.com>
Date: Thu, 12 Nov 2020 18:53:34 -0800
Subject: signal: clear non-uapi flag bits when passing/returning sa_flags

Previously we were not clearing non-uapi flag bits in
sigaction.sa_flags when storing the userspace-provided sa_flags or
when returning them via oldact. Start doing so.

This allows userspace to detect missing support for flag bits and
allows the kernel to use non-uapi bits internally, as we are already
doing in arch/x86 for two flag bits. Now that this change is in
place, we no longer need the code in arch/x86 that was hiding these
bits from userspace, so remove it.

This is technically a userspace-visible behavior change for sigaction, as
the unknown bits returned via oldact.sa_flags are no longer set. However,
we are free to define the behavior for unknown bits exactly because
their behavior is currently undefined, so for now we can define the
meaning of each of them to be "clear the bit in oldact.sa_flags unless
the bit becomes known in the future". Furthermore, this behavior is
consistent with OpenBSD [1], illumos [2] and XNU [3] (FreeBSD [4] and
NetBSD [5] fail the syscall if unknown bits are set). So there is some
precedent for this behavior in other kernels, and in particular in XNU,
which is probably the most popular kernel among those that I looked at,
which means that this change is less likely to be a compatibility issue.

Link: [1] https://github.com/openbsd/src/blob/f634a6a4b5bf832e9c1de77f7894ae2625e74484/sys/kern/kern_sig.c#L278
Link: [2] https://github.com/illumos/illumos-gate/blob/76f19f5fdc974fe5be5c82a556e43a4df93f1de1/usr/src/uts/common/syscall/sigaction.c#L86
Link: [3] https://github.com/apple/darwin-xnu/blob/a449c6a3b8014d9406c2ddbdc81795da24aa7443/bsd/kern/kern_sig.c#L480
Link: [4] https://github.com/freebsd/freebsd/blob/eded70c37057857c6e23fae51f86b8f8f43cd2d0/sys/kern/kern_sig.c#L699
Link: [5] https://github.com/NetBSD/src/blob/3365779becdcedfca206091a645a0e8e22b2946e/sys/kern/sys_sig.c#L473
Signed-off-by: Peter Collingbourne <pcc@google.com>
Reviewed-by: Dave Martin <Dave.Martin@arm.com>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Link: https://linux-review.googlesource.com/id/I35aab6f5be932505d90f3b3450c083b4db1eca86
Link: https://lkml.kernel.org/r/878dbcb5f47bc9b11881c81f745c0bef5c23f97f.1605235762.git.pcc@google.com
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
---
 arch/arm/include/asm/signal.h    |  2 ++
 arch/parisc/include/asm/signal.h |  2 ++
 arch/x86/kernel/signal_compat.c  |  7 -------
 include/linux/signal_types.h     | 12 ++++++++++++
 kernel/signal.c                  | 10 ++++++++++
 5 files changed, 26 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/include/asm/signal.h b/arch/arm/include/asm/signal.h
index 65530a042009..430be7774402 100644
--- a/arch/arm/include/asm/signal.h
+++ b/arch/arm/include/asm/signal.h
@@ -17,6 +17,8 @@ typedef struct {
 	unsigned long sig[_NSIG_WORDS];
 } sigset_t;
 
+#define __ARCH_UAPI_SA_FLAGS	(SA_THIRTYTWO | SA_RESTORER)
+
 #define __ARCH_HAS_SA_RESTORER
 
 #include <asm/sigcontext.h>
diff --git a/arch/parisc/include/asm/signal.h b/arch/parisc/include/asm/signal.h
index 715c96ba2ec8..30dd1e43ef88 100644
--- a/arch/parisc/include/asm/signal.h
+++ b/arch/parisc/include/asm/signal.h
@@ -21,6 +21,8 @@ typedef struct {
 	unsigned long sig[_NSIG_WORDS];
 } sigset_t;
 
+#define __ARCH_UAPI_SA_FLAGS	_SA_SIGGFAULT
+
 #include <asm/sigcontext.h>
 
 #endif /* !__ASSEMBLY */
diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c
index a7f3e12cfbdb..ddfd919be46c 100644
--- a/arch/x86/kernel/signal_compat.c
+++ b/arch/x86/kernel/signal_compat.c
@@ -165,16 +165,9 @@ void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact)
 {
 	signal_compat_build_tests();
 
-	/* Don't leak in-kernel non-uapi flags to user-space */
-	if (oact)
-		oact->sa.sa_flags &= ~(SA_IA32_ABI | SA_X32_ABI);
-
 	if (!act)
 		return;
 
-	/* Don't let flags to be set from userspace */
-	act->sa.sa_flags &= ~(SA_IA32_ABI | SA_X32_ABI);
-
 	if (in_ia32_syscall())
 		act->sa.sa_flags |= SA_IA32_ABI;
 	if (in_x32_syscall())
diff --git a/include/linux/signal_types.h b/include/linux/signal_types.h
index f8a90ae9c6ec..a7887ad84d36 100644
--- a/include/linux/signal_types.h
+++ b/include/linux/signal_types.h
@@ -68,4 +68,16 @@ struct ksignal {
 	int sig;
 };
 
+#ifndef __ARCH_UAPI_SA_FLAGS
+#ifdef SA_RESTORER
+#define __ARCH_UAPI_SA_FLAGS	SA_RESTORER
+#else
+#define __ARCH_UAPI_SA_FLAGS	0
+#endif
+#endif
+
+#define UAPI_SA_FLAGS                                                          \
+	(SA_NOCLDSTOP | SA_NOCLDWAIT | SA_SIGINFO | SA_ONSTACK | SA_RESTART |  \
+	 SA_NODEFER | SA_RESETHAND | __ARCH_UAPI_SA_FLAGS)
+
 #endif /* _LINUX_SIGNAL_TYPES_H */
diff --git a/kernel/signal.c b/kernel/signal.c
index ef8f2a28d37c..8f5bd12ee41b 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -3985,6 +3985,16 @@ int do_sigaction(int sig, struct k_sigaction *act, struct k_sigaction *oact)
 	if (oact)
 		*oact = *k;
 
+	/*
+	 * Clear unknown flag bits in order to allow userspace to detect missing
+	 * support for flag bits and to allow the kernel to use non-uapi bits
+	 * internally.
+	 */
+	if (act)
+		act->sa.sa_flags &= UAPI_SA_FLAGS;
+	if (oact)
+		oact->sa.sa_flags &= UAPI_SA_FLAGS;
+
 	sigaction_compat_abi(act, oact);
 
 	if (act) {
-- 
cgit v1.2.3


From 6ac05e832a9e96f9b1c42a8917cdd317d7b6c8fa Mon Sep 17 00:00:00 2001
From: Peter Collingbourne <pcc@google.com>
Date: Fri, 20 Nov 2020 12:33:45 -0800
Subject: signal: define the SA_EXPOSE_TAGBITS bit in sa_flags

Architectures that support address tagging, such as arm64, may want to
expose fault address tag bits to the signal handler to help diagnose
memory errors. However, these bits have not been previously set,
and their presence may confuse unaware user applications. Therefore,
introduce a SA_EXPOSE_TAGBITS flag bit in sa_flags that a signal
handler may use to explicitly request that the bits are set.

The generic signal handler APIs expect to receive tagged addresses.
Architectures may specify how to untag addresses in the case where
SA_EXPOSE_TAGBITS is clear by defining the arch_untagged_si_addr
function.

Signed-off-by: Peter Collingbourne <pcc@google.com>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Link: https://linux-review.googlesource.com/id/I16dd0ed2081f091fce97be0190cb8caa874c26cb
Link: https://lkml.kernel.org/r/13cf24d00ebdd8e1f55caf1821c7c29d54100191.1605904350.git.pcc@google.com
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
---
 include/linux/signal.h                 | 14 ++++++++++++++
 include/linux/signal_types.h           |  2 +-
 include/uapi/asm-generic/signal-defs.h |  3 +++
 kernel/signal.c                        | 24 ++++++++++++++++++++++++
 4 files changed, 42 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/signal.h b/include/linux/signal.h
index b256f9c65661..205526c4003a 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -469,4 +469,18 @@ struct seq_file;
 extern void render_sigset_t(struct seq_file *, const char *, sigset_t *);
 #endif
 
+#ifndef arch_untagged_si_addr
+/*
+ * Given a fault address and a signal and si_code which correspond to the
+ * _sigfault union member, returns the address that must appear in si_addr if
+ * the signal handler does not have SA_EXPOSE_TAGBITS enabled in sa_flags.
+ */
+static inline void __user *arch_untagged_si_addr(void __user *addr,
+						 unsigned long sig,
+						 unsigned long si_code)
+{
+	return addr;
+}
+#endif
+
 #endif /* _LINUX_SIGNAL_H */
diff --git a/include/linux/signal_types.h b/include/linux/signal_types.h
index a7887ad84d36..68e06c75c5b2 100644
--- a/include/linux/signal_types.h
+++ b/include/linux/signal_types.h
@@ -78,6 +78,6 @@ struct ksignal {
 
 #define UAPI_SA_FLAGS                                                          \
 	(SA_NOCLDSTOP | SA_NOCLDWAIT | SA_SIGINFO | SA_ONSTACK | SA_RESTART |  \
-	 SA_NODEFER | SA_RESETHAND | __ARCH_UAPI_SA_FLAGS)
+	 SA_NODEFER | SA_RESETHAND | SA_EXPOSE_TAGBITS | __ARCH_UAPI_SA_FLAGS)
 
 #endif /* _LINUX_SIGNAL_TYPES_H */
diff --git a/include/uapi/asm-generic/signal-defs.h b/include/uapi/asm-generic/signal-defs.h
index c790f67304ba..fe929e7b77ca 100644
--- a/include/uapi/asm-generic/signal-defs.h
+++ b/include/uapi/asm-generic/signal-defs.h
@@ -20,6 +20,8 @@
  * so this bit allows flag bit support to be detected from userspace while
  * allowing an old kernel to be distinguished from a kernel that supports every
  * flag bit.
+ * SA_EXPOSE_TAGBITS exposes an architecture-defined set of tag bits in
+ * siginfo.si_addr.
  *
  * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single
  * Unix names RESETHAND and NODEFER respectively.
@@ -41,6 +43,7 @@
 /* 0x00000100 used on sparc */
 /* 0x00000200 used on sparc */
 #define SA_UNSUPPORTED	0x00000400
+#define SA_EXPOSE_TAGBITS	0x00000800
 /* 0x00010000 used on mips */
 /* 0x01000000 used on x86 */
 /* 0x02000000 used on x86 */
diff --git a/kernel/signal.c b/kernel/signal.c
index 8f34819e80de..26018c59821d 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2524,6 +2524,26 @@ static int ptrace_signal(int signr, kernel_siginfo_t *info)
 	return signr;
 }
 
+static void hide_si_addr_tag_bits(struct ksignal *ksig)
+{
+	switch (siginfo_layout(ksig->sig, ksig->info.si_code)) {
+	case SIL_FAULT:
+	case SIL_FAULT_MCEERR:
+	case SIL_FAULT_BNDERR:
+	case SIL_FAULT_PKUERR:
+		ksig->info.si_addr = arch_untagged_si_addr(
+			ksig->info.si_addr, ksig->sig, ksig->info.si_code);
+		break;
+	case SIL_KILL:
+	case SIL_TIMER:
+	case SIL_POLL:
+	case SIL_CHLD:
+	case SIL_RT:
+	case SIL_SYS:
+		break;
+	}
+}
+
 bool get_signal(struct ksignal *ksig)
 {
 	struct sighand_struct *sighand = current->sighand;
@@ -2761,6 +2781,10 @@ relock:
 	spin_unlock_irq(&sighand->siglock);
 
 	ksig->sig = signr;
+
+	if (!(ksig->ka.sa.sa_flags & SA_EXPOSE_TAGBITS))
+		hide_si_addr_tag_bits(ksig);
+
 	return ksig->sig > 0;
 }
 
-- 
cgit v1.2.3


From 4e1d9a737d00f2cc811dc5654f82c92c7d80e98c Mon Sep 17 00:00:00 2001
From: Patrice Chotard <patrice.chotard@st.com>
Date: Thu, 19 Nov 2020 08:25:39 +0100
Subject: PM: sleep: Add dev_wakeup_path() helper

Add dev_wakeup_path() helper to avoid to spread
dev->power.wakeup_path test in drivers.

Signed-off-by: Patrice Chotard <patrice.chotard@st.com>
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c      |  4 ++--
 drivers/base/power/main.c        |  4 ++--
 drivers/i2c/busses/i2c-stm32f7.c |  4 ++--
 include/linux/pm_wakeup.h        | 10 ++++++++++
 4 files changed, 16 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 743268996336..e0894ef8457c 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -1142,7 +1142,7 @@ static int genpd_finish_suspend(struct device *dev, bool poweroff)
 	if (ret)
 		return ret;
 
-	if (dev->power.wakeup_path && genpd_is_active_wakeup(genpd))
+	if (device_wakeup_path(dev) && genpd_is_active_wakeup(genpd))
 		return 0;
 
 	if (genpd->dev_ops.stop && genpd->dev_ops.start &&
@@ -1196,7 +1196,7 @@ static int genpd_resume_noirq(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	if (dev->power.wakeup_path && genpd_is_active_wakeup(genpd))
+	if (device_wakeup_path(dev) && genpd_is_active_wakeup(genpd))
 		return pm_generic_resume_noirq(dev);
 
 	genpd_lock(genpd);
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 2b4255dc101e..46793276598d 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -1359,7 +1359,7 @@ static void dpm_propagate_wakeup_to_parent(struct device *dev)
 
 	spin_lock_irq(&parent->power.lock);
 
-	if (dev->power.wakeup_path && !parent->power.ignore_children)
+	if (device_wakeup_path(dev) && !parent->power.ignore_children)
 		parent->power.wakeup_path = true;
 
 	spin_unlock_irq(&parent->power.lock);
@@ -1627,7 +1627,7 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 		goto Complete;
 
 	/* Avoid direct_complete to let wakeup_path propagate. */
-	if (device_may_wakeup(dev) || dev->power.wakeup_path)
+	if (device_may_wakeup(dev) || device_wakeup_path(dev))
 		dev->power.direct_complete = false;
 
 	if (dev->power.direct_complete) {
diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c
index f41f51a176a1..9aa8e65b511e 100644
--- a/drivers/i2c/busses/i2c-stm32f7.c
+++ b/drivers/i2c/busses/i2c-stm32f7.c
@@ -2322,7 +2322,7 @@ static int stm32f7_i2c_suspend(struct device *dev)
 
 	i2c_mark_adapter_suspended(&i2c_dev->adap);
 
-	if (!device_may_wakeup(dev) && !dev->power.wakeup_path) {
+	if (!device_may_wakeup(dev) && !device_wakeup_path(dev)) {
 		ret = stm32f7_i2c_regs_backup(i2c_dev);
 		if (ret < 0) {
 			i2c_mark_adapter_resumed(&i2c_dev->adap);
@@ -2341,7 +2341,7 @@ static int stm32f7_i2c_resume(struct device *dev)
 	struct stm32f7_i2c_dev *i2c_dev = dev_get_drvdata(dev);
 	int ret;
 
-	if (!device_may_wakeup(dev) && !dev->power.wakeup_path) {
+	if (!device_may_wakeup(dev) && !device_wakeup_path(dev)) {
 		ret = pm_runtime_force_resume(dev);
 		if (ret < 0)
 			return ret;
diff --git a/include/linux/pm_wakeup.h b/include/linux/pm_wakeup.h
index aa3da6611533..196a157456aa 100644
--- a/include/linux/pm_wakeup.h
+++ b/include/linux/pm_wakeup.h
@@ -84,6 +84,11 @@ static inline bool device_may_wakeup(struct device *dev)
 	return dev->power.can_wakeup && !!dev->power.wakeup;
 }
 
+static inline bool device_wakeup_path(struct device *dev)
+{
+	return dev->power.wakeup_path;
+}
+
 static inline void device_set_wakeup_path(struct device *dev)
 {
 	dev->power.wakeup_path = true;
@@ -174,6 +179,11 @@ static inline bool device_may_wakeup(struct device *dev)
 	return dev->power.can_wakeup && dev->power.should_wakeup;
 }
 
+static inline bool device_wakeup_path(struct device *dev)
+{
+	return false;
+}
+
 static inline void device_set_wakeup_path(struct device *dev) {}
 
 static inline void __pm_stay_awake(struct wakeup_source *ws) {}
-- 
cgit v1.2.3


From a94ef811f7c3748736b85db0406da8e4ea391ac6 Mon Sep 17 00:00:00 2001
From: Lina Iyer <ilina@codeaurora.org>
Date: Thu, 19 Nov 2020 09:43:25 -0700
Subject: PM: domains: replace -ENOTSUPP with -EOPNOTSUPP

While submitting a patch to add next_wakeup, checkpatch reported this -

WARNING: ENOTSUPP is not a SUSV4 error code, prefer EOPNOTSUPP
+       return -ENOTSUPP;

Address the above warning in other functions in pm_domain.h.

Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Lina Iyer <ilina@codeaurora.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/pm_domain.h | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 1ad0ec481416..5fd20d117cbe 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -255,24 +255,24 @@ static inline int pm_genpd_init(struct generic_pm_domain *genpd,
 }
 static inline int pm_genpd_remove(struct generic_pm_domain *genpd)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 static inline int dev_pm_genpd_set_performance_state(struct device *dev,
 						     unsigned int state)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 static inline int dev_pm_genpd_add_notifier(struct device *dev,
 					    struct notifier_block *nb)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 static inline int dev_pm_genpd_remove_notifier(struct device *dev)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 #define simple_qos_governor		(*(struct dev_power_governor *)(NULL))
@@ -325,13 +325,13 @@ struct device *genpd_dev_pm_attach_by_name(struct device *dev,
 static inline int of_genpd_add_provider_simple(struct device_node *np,
 					struct generic_pm_domain *genpd)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 static inline int of_genpd_add_provider_onecell(struct device_node *np,
 					struct genpd_onecell_data *data)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 static inline void of_genpd_del_provider(struct device_node *np) {}
@@ -387,7 +387,7 @@ static inline struct device *genpd_dev_pm_attach_by_name(struct device *dev,
 static inline
 struct generic_pm_domain *of_genpd_remove_last(struct device_node *np)
 {
-	return ERR_PTR(-ENOTSUPP);
+	return ERR_PTR(-EOPNOTSUPP);
 }
 #endif /* CONFIG_PM_GENERIC_DOMAINS_OF */
 
-- 
cgit v1.2.3


From 8eb621698fd4c49703d512fe437d84ab822bc59e Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 16 Sep 2020 11:12:03 +0100
Subject: keys: Provide the original description to the key preparser

Provide the proposed description (add key) or the original description
(update/instantiate key) when preparsing a key so that the key type can
validate it against the data.

This is important for rxrpc server keys as we need to check that they have
the right amount of key material present - and it's better to do that when
the key is loaded rather than deep in trying to process a response packet.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
cc: keyrings@vger.kernel.org
---
 include/linux/key-type.h | 1 +
 security/keys/key.c      | 2 ++
 2 files changed, 3 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/key-type.h b/include/linux/key-type.h
index 2ab2d6d6aeab..7d985a1dfe4a 100644
--- a/include/linux/key-type.h
+++ b/include/linux/key-type.h
@@ -29,6 +29,7 @@ struct kernel_pkey_params;
  * clear the contents.
  */
 struct key_preparsed_payload {
+	const char	*orig_description; /* Actual or proposed description (maybe NULL) */
 	char		*description;	/* Proposed key description (or NULL) */
 	union key_payload payload;	/* Proposed payload */
 	const void	*data;		/* Raw data */
diff --git a/security/keys/key.c b/security/keys/key.c
index e282c6179b21..ebe752b137aa 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -504,6 +504,7 @@ int key_instantiate_and_link(struct key *key,
 	int ret;
 
 	memset(&prep, 0, sizeof(prep));
+	prep.orig_description = key->description;
 	prep.data = data;
 	prep.datalen = datalen;
 	prep.quotalen = key->type->def_datalen;
@@ -854,6 +855,7 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 		goto error_put_type;
 
 	memset(&prep, 0, sizeof(prep));
+	prep.orig_description = description;
 	prep.data = payload;
 	prep.datalen = plen;
 	prep.quotalen = index_key.type->def_datalen;
-- 
cgit v1.2.3


From e7095c35abfc5a5d566941a87434c0fd5ffb570f Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Thu, 19 Nov 2020 19:10:49 +0000
Subject: regulator: core: add of_match_full_name boolean flag

During regulators registration, if .of_match and .regulators_node are
defined as non-null strings in struct regulator_desc the core searches the
DT subtree rooted at .regulators_node trying to match, at first, .of_match
against the 'regulator-compatible' property and, then, falling back to use
the name of the node itself to determine a good match.

Property 'regulator-compatible', though, is now deprecated and falling back
to match against the node name, works fine only as long as the involved
nodes are named in an unique way across the searched subtree; if that's not
the case, like when using <common-name>@<unit> style naming for properties
indexed via 'reg' property (as advised by the standard), the above matching
mechanism based on the simple common name will lead to multiple matches and
the only viable alternative would be to properly define the now deprecated
'regulator-compatible' as the node full name, i.e. <common-name>@<unit>.

In order to address this case without using such deprecated binding, define
a new boolean flag .of_match_full_name in struct regulator_desc to force
the core to match against the node full-name instead of the plain name.

Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Link: https://lore.kernel.org/r/20201119191051.46363-4-cristian.marussi@arm.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/of_regulator.c | 8 ++++++--
 include/linux/regulator/driver.h | 3 +++
 2 files changed, 9 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c
index 06c0b15fe4c0..564f928eb1db 100644
--- a/drivers/regulator/of_regulator.c
+++ b/drivers/regulator/of_regulator.c
@@ -413,8 +413,12 @@ device_node *regulator_of_get_init_node(struct device *dev,
 
 	for_each_available_child_of_node(search, child) {
 		name = of_get_property(child, "regulator-compatible", NULL);
-		if (!name)
-			name = child->name;
+		if (!name) {
+			if (!desc->of_match_full_name)
+				name = child->name;
+			else
+				name = child->full_name;
+		}
 
 		if (!strcmp(desc->of_match, name)) {
 			of_node_put(search);
diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index 11cade73726c..d7c77ee370f3 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -223,6 +223,8 @@ enum regulator_type {
  * @name: Identifying name for the regulator.
  * @supply_name: Identifying the regulator supply
  * @of_match: Name used to identify regulator in DT.
+ * @of_match_full_name: A flag to indicate that the of_match string, if
+ *			present, should be matched against the node full_name.
  * @regulators_node: Name of node containing regulator definitions in DT.
  * @of_parse_cb: Optional callback called only if of_match is present.
  *               Will be called for each regulator parsed from DT, during
@@ -314,6 +316,7 @@ struct regulator_desc {
 	const char *name;
 	const char *supply_name;
 	const char *of_match;
+	bool of_match_full_name;
 	const char *regulators_node;
 	int (*of_parse_cb)(struct device_node *,
 			    const struct regulator_desc *,
-- 
cgit v1.2.3


From 076d38b88c4146fd5506933d440b881741b6ab60 Mon Sep 17 00:00:00 2001
From: Christian Eggers <ceggers@arri.de>
Date: Fri, 20 Nov 2020 09:41:04 +0100
Subject: net: ptp: introduce common defines for PTP message types

Using PTP wide defines will obsolete different driver internal defines
and uses of magic numbers.

Signed-off-by: Christian Eggers <ceggers@arri.de>
Cc: Kurt Kanzenbach <kurt@linutronix.de>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Reviewed-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/ptp_classify.h | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h
index c6487b7ab026..ae04968a3a47 100644
--- a/include/linux/ptp_classify.h
+++ b/include/linux/ptp_classify.h
@@ -31,6 +31,11 @@
 #define PTP_CLASS_V2_VLAN (PTP_CLASS_V2 | PTP_CLASS_VLAN)
 #define PTP_CLASS_L4      (PTP_CLASS_IPV4 | PTP_CLASS_IPV6)
 
+#define PTP_MSGTYPE_SYNC        0x0
+#define PTP_MSGTYPE_DELAY_REQ   0x1
+#define PTP_MSGTYPE_PDELAY_REQ  0x2
+#define PTP_MSGTYPE_PDELAY_RESP 0x3
+
 #define PTP_EV_PORT 319
 #define PTP_GEN_BIT 0x08 /* indicates general message, if set in message type */
 
@@ -140,7 +145,7 @@ static inline u8 ptp_get_msgtype(const struct ptp_header *hdr,
 	/* The return is meaningless. The stub function would not be
 	 * executed since no available header from ptp_parse_header.
 	 */
-	return 0;
+	return PTP_MSGTYPE_SYNC;
 }
 #endif
 #endif /* _PTP_CLASSIFY_H_ */
-- 
cgit v1.2.3


From 3df98d79215ace13d1e91ddfc5a67a0f5acbd83f Mon Sep 17 00:00:00 2001
From: Paul Moore <paul@paul-moore.com>
Date: Sun, 27 Sep 2020 22:38:26 -0400
Subject: lsm,selinux: pass flowi_common instead of flowi to the LSM hooks

As pointed out by Herbert in a recent related patch, the LSM hooks do
not have the necessary address family information to use the flowi
struct safely.  As none of the LSMs currently use any of the protocol
specific flowi information, replace the flowi pointers with pointers
to the address family independent flowi_common struct.

Reported-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: James Morris <jamorris@linux.microsoft.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 .../chelsio/inline_crypto/chtls/chtls_cm.c         |  2 +-
 drivers/net/wireguard/socket.c                     |  4 ++--
 include/linux/lsm_hook_defs.h                      |  4 ++--
 include/linux/lsm_hooks.h                          |  2 +-
 include/linux/security.h                           | 23 +++++++++++++---------
 include/net/flow.h                                 | 10 ++++++++++
 include/net/route.h                                |  6 +++---
 net/dccp/ipv4.c                                    |  2 +-
 net/dccp/ipv6.c                                    |  6 +++---
 net/ipv4/icmp.c                                    |  4 ++--
 net/ipv4/inet_connection_sock.c                    |  4 ++--
 net/ipv4/ip_output.c                               |  2 +-
 net/ipv4/ping.c                                    |  2 +-
 net/ipv4/raw.c                                     |  2 +-
 net/ipv4/syncookies.c                              |  2 +-
 net/ipv4/udp.c                                     |  2 +-
 net/ipv6/af_inet6.c                                |  2 +-
 net/ipv6/datagram.c                                |  2 +-
 net/ipv6/icmp.c                                    |  6 +++---
 net/ipv6/inet6_connection_sock.c                   |  4 ++--
 net/ipv6/netfilter/nf_reject_ipv6.c                |  2 +-
 net/ipv6/ping.c                                    |  2 +-
 net/ipv6/raw.c                                     |  2 +-
 net/ipv6/syncookies.c                              |  2 +-
 net/ipv6/tcp_ipv6.c                                |  4 ++--
 net/ipv6/udp.c                                     |  2 +-
 net/l2tp/l2tp_ip6.c                                |  2 +-
 net/netfilter/nf_synproxy_core.c                   |  2 +-
 net/xfrm/xfrm_state.c                              |  6 ++++--
 security/security.c                                | 17 ++++++++--------
 security/selinux/hooks.c                           |  4 ++--
 security/selinux/include/xfrm.h                    |  2 +-
 security/selinux/xfrm.c                            | 13 ++++++------
 33 files changed, 85 insertions(+), 66 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c
index ec4f79049a06..42e4e43cdd91 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c
@@ -1148,7 +1148,7 @@ static struct sock *chtls_recv_sock(struct sock *lsk,
 		fl6.daddr = ip6h->saddr;
 		fl6.fl6_dport = inet_rsk(oreq)->ir_rmt_port;
 		fl6.fl6_sport = htons(inet_rsk(oreq)->ir_num);
-		security_req_classify_flow(oreq, flowi6_to_flowi(&fl6));
+		security_req_classify_flow(oreq, flowi6_to_flowi_common(&fl6));
 		dst = ip6_dst_lookup_flow(sock_net(lsk), lsk, &fl6, NULL);
 		if (IS_ERR(dst))
 			goto free_sk;
diff --git a/drivers/net/wireguard/socket.c b/drivers/net/wireguard/socket.c
index c33e2c81635f..410b318e57fb 100644
--- a/drivers/net/wireguard/socket.c
+++ b/drivers/net/wireguard/socket.c
@@ -49,7 +49,7 @@ static int send4(struct wg_device *wg, struct sk_buff *skb,
 		rt = dst_cache_get_ip4(cache, &fl.saddr);
 
 	if (!rt) {
-		security_sk_classify_flow(sock, flowi4_to_flowi(&fl));
+		security_sk_classify_flow(sock, flowi4_to_flowi_common(&fl));
 		if (unlikely(!inet_confirm_addr(sock_net(sock), NULL, 0,
 						fl.saddr, RT_SCOPE_HOST))) {
 			endpoint->src4.s_addr = 0;
@@ -129,7 +129,7 @@ static int send6(struct wg_device *wg, struct sk_buff *skb,
 		dst = dst_cache_get_ip6(cache, &fl.saddr);
 
 	if (!dst) {
-		security_sk_classify_flow(sock, flowi6_to_flowi(&fl));
+		security_sk_classify_flow(sock, flowi6_to_flowi_common(&fl));
 		if (unlikely(!ipv6_addr_any(&fl.saddr) &&
 			     !ipv6_chk_addr(sock_net(sock), &fl.saddr, NULL, 0))) {
 			endpoint->src6 = fl.saddr = in6addr_any;
diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index 32a940117e7a..f70984c8318b 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -311,7 +311,7 @@ LSM_HOOK(int, 0, secmark_relabel_packet, u32 secid)
 LSM_HOOK(void, LSM_RET_VOID, secmark_refcount_inc, void)
 LSM_HOOK(void, LSM_RET_VOID, secmark_refcount_dec, void)
 LSM_HOOK(void, LSM_RET_VOID, req_classify_flow, const struct request_sock *req,
-	 struct flowi *fl)
+	 struct flowi_common *flic)
 LSM_HOOK(int, 0, tun_dev_alloc_security, void **security)
 LSM_HOOK(void, LSM_RET_VOID, tun_dev_free_security, void *security)
 LSM_HOOK(int, 0, tun_dev_create, void)
@@ -351,7 +351,7 @@ LSM_HOOK(int, 0, xfrm_state_delete_security, struct xfrm_state *x)
 LSM_HOOK(int, 0, xfrm_policy_lookup, struct xfrm_sec_ctx *ctx, u32 fl_secid,
 	 u8 dir)
 LSM_HOOK(int, 1, xfrm_state_pol_flow_match, struct xfrm_state *x,
-	 struct xfrm_policy *xp, const struct flowi *fl)
+	 struct xfrm_policy *xp, const struct flowi_common *flic)
 LSM_HOOK(int, 0, xfrm_decode_session, struct sk_buff *skb, u32 *secid,
 	 int ckall)
 #endif /* CONFIG_SECURITY_NETWORK_XFRM */
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index c503f7ab8afb..a19adef1f088 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -1105,7 +1105,7 @@
  * @xfrm_state_pol_flow_match:
  *	@x contains the state to match.
  *	@xp contains the policy to check for a match.
- *	@fl contains the flow to check for a match.
+ *	@flic contains the flowi_common struct to check for a match.
  *	Return 1 if there is a match.
  * @xfrm_decode_session:
  *	@skb points to skb to decode.
diff --git a/include/linux/security.h b/include/linux/security.h
index bc2725491560..469273e8b46d 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -167,7 +167,7 @@ struct sk_buff;
 struct sock;
 struct sockaddr;
 struct socket;
-struct flowi;
+struct flowi_common;
 struct dst_entry;
 struct xfrm_selector;
 struct xfrm_policy;
@@ -1355,8 +1355,9 @@ int security_socket_getpeersec_dgram(struct socket *sock, struct sk_buff *skb, u
 int security_sk_alloc(struct sock *sk, int family, gfp_t priority);
 void security_sk_free(struct sock *sk);
 void security_sk_clone(const struct sock *sk, struct sock *newsk);
-void security_sk_classify_flow(struct sock *sk, struct flowi *fl);
-void security_req_classify_flow(const struct request_sock *req, struct flowi *fl);
+void security_sk_classify_flow(struct sock *sk, struct flowi_common *flic);
+void security_req_classify_flow(const struct request_sock *req,
+				struct flowi_common *flic);
 void security_sock_graft(struct sock*sk, struct socket *parent);
 int security_inet_conn_request(struct sock *sk,
 			struct sk_buff *skb, struct request_sock *req);
@@ -1507,11 +1508,13 @@ static inline void security_sk_clone(const struct sock *sk, struct sock *newsk)
 {
 }
 
-static inline void security_sk_classify_flow(struct sock *sk, struct flowi *fl)
+static inline void security_sk_classify_flow(struct sock *sk,
+					     struct flowi_common *flic)
 {
 }
 
-static inline void security_req_classify_flow(const struct request_sock *req, struct flowi *fl)
+static inline void security_req_classify_flow(const struct request_sock *req,
+					      struct flowi_common *flic)
 {
 }
 
@@ -1638,9 +1641,9 @@ void security_xfrm_state_free(struct xfrm_state *x);
 int security_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir);
 int security_xfrm_state_pol_flow_match(struct xfrm_state *x,
 				       struct xfrm_policy *xp,
-				       const struct flowi *fl);
+				       const struct flowi_common *flic);
 int security_xfrm_decode_session(struct sk_buff *skb, u32 *secid);
-void security_skb_classify_flow(struct sk_buff *skb, struct flowi *fl);
+void security_skb_classify_flow(struct sk_buff *skb, struct flowi_common *flic);
 
 #else	/* CONFIG_SECURITY_NETWORK_XFRM */
 
@@ -1692,7 +1695,8 @@ static inline int security_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_s
 }
 
 static inline int security_xfrm_state_pol_flow_match(struct xfrm_state *x,
-			struct xfrm_policy *xp, const struct flowi *fl)
+						     struct xfrm_policy *xp,
+						     const struct flowi_common *flic)
 {
 	return 1;
 }
@@ -1702,7 +1706,8 @@ static inline int security_xfrm_decode_session(struct sk_buff *skb, u32 *secid)
 	return 0;
 }
 
-static inline void security_skb_classify_flow(struct sk_buff *skb, struct flowi *fl)
+static inline void security_skb_classify_flow(struct sk_buff *skb,
+					      struct flowi_common *flic)
 {
 }
 
diff --git a/include/net/flow.h b/include/net/flow.h
index b2531df3f65f..39d0cedcddee 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -195,11 +195,21 @@ static inline struct flowi *flowi4_to_flowi(struct flowi4 *fl4)
 	return container_of(fl4, struct flowi, u.ip4);
 }
 
+static inline struct flowi_common *flowi4_to_flowi_common(struct flowi4 *fl4)
+{
+	return &(flowi4_to_flowi(fl4)->u.__fl_common);
+}
+
 static inline struct flowi *flowi6_to_flowi(struct flowi6 *fl6)
 {
 	return container_of(fl6, struct flowi, u.ip6);
 }
 
+static inline struct flowi_common *flowi6_to_flowi_common(struct flowi6 *fl6)
+{
+	return &(flowi6_to_flowi(fl6)->u.__fl_common);
+}
+
 static inline struct flowi *flowidn_to_flowi(struct flowidn *fldn)
 {
 	return container_of(fldn, struct flowi, u.dn);
diff --git a/include/net/route.h b/include/net/route.h
index ff021cab657e..2e6c0e153e3a 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -165,7 +165,7 @@ static inline struct rtable *ip_route_output_ports(struct net *net, struct flowi
 			   sk ? inet_sk_flowi_flags(sk) : 0,
 			   daddr, saddr, dport, sport, sock_net_uid(net, sk));
 	if (sk)
-		security_sk_classify_flow(sk, flowi4_to_flowi(fl4));
+		security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4));
 	return ip_route_output_flow(net, fl4, sk);
 }
 
@@ -322,7 +322,7 @@ static inline struct rtable *ip_route_connect(struct flowi4 *fl4,
 		ip_rt_put(rt);
 		flowi4_update_output(fl4, oif, tos, fl4->daddr, fl4->saddr);
 	}
-	security_sk_classify_flow(sk, flowi4_to_flowi(fl4));
+	security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4));
 	return ip_route_output_flow(net, fl4, sk);
 }
 
@@ -338,7 +338,7 @@ static inline struct rtable *ip_route_newports(struct flowi4 *fl4, struct rtable
 		flowi4_update_output(fl4, sk->sk_bound_dev_if,
 				     RT_CONN_FLAGS(sk), fl4->daddr,
 				     fl4->saddr);
-		security_sk_classify_flow(sk, flowi4_to_flowi(fl4));
+		security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4));
 		return ip_route_output_flow(sock_net(sk), fl4, sk);
 	}
 	return rt;
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index bb3d70664dde..3d0b58d7bf3f 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -464,7 +464,7 @@ static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk,
 		.fl4_dport = dccp_hdr(skb)->dccph_sport,
 	};
 
-	security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
+	security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4));
 	rt = ip_route_output_flow(net, &fl4, sk);
 	if (IS_ERR(rt)) {
 		IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index ef4ab28cfde0..179dcf02a572 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -203,7 +203,7 @@ static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req
 	fl6.flowi6_oif = ireq->ir_iif;
 	fl6.fl6_dport = ireq->ir_rmt_port;
 	fl6.fl6_sport = htons(ireq->ir_num);
-	security_req_classify_flow(req, flowi6_to_flowi(&fl6));
+	security_req_classify_flow(req, flowi6_to_flowi_common(&fl6));
 
 
 	rcu_read_lock();
@@ -279,7 +279,7 @@ static void dccp_v6_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb)
 	fl6.flowi6_oif = inet6_iif(rxskb);
 	fl6.fl6_dport = dccp_hdr(skb)->dccph_dport;
 	fl6.fl6_sport = dccp_hdr(skb)->dccph_sport;
-	security_skb_classify_flow(rxskb, flowi6_to_flowi(&fl6));
+	security_skb_classify_flow(rxskb, flowi6_to_flowi_common(&fl6));
 
 	/* sk = NULL, but it is safe for now. RST socket required. */
 	dst = ip6_dst_lookup_flow(sock_net(ctl_sk), ctl_sk, &fl6, NULL);
@@ -907,7 +907,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	fl6.flowi6_oif = sk->sk_bound_dev_if;
 	fl6.fl6_dport = usin->sin6_port;
 	fl6.fl6_sport = inet->inet_sport;
-	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
+	security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6));
 
 	opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk));
 	final_p = fl6_update_dst(&fl6, opt, &final);
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 005faea415a4..396b492c804f 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -447,7 +447,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 	fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
 	fl4.flowi4_proto = IPPROTO_ICMP;
 	fl4.flowi4_oif = l3mdev_master_ifindex(skb->dev);
-	security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
+	security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4));
 	rt = ip_route_output_key(net, &fl4);
 	if (IS_ERR(rt))
 		goto out_unlock;
@@ -503,7 +503,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
 	route_lookup_dev = icmp_get_route_lookup_dev(skb_in);
 	fl4->flowi4_oif = l3mdev_master_ifindex(route_lookup_dev);
 
-	security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4));
+	security_skb_classify_flow(skb_in, flowi4_to_flowi_common(fl4));
 	rt = ip_route_output_key_hash(net, fl4, skb_in);
 	if (IS_ERR(rt))
 		return rt;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 4148f5f78f31..1b7801371f7d 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -602,7 +602,7 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk,
 			   (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
 			   ireq->ir_loc_addr, ireq->ir_rmt_port,
 			   htons(ireq->ir_num), sk->sk_uid);
-	security_req_classify_flow(req, flowi4_to_flowi(fl4));
+	security_req_classify_flow(req, flowi4_to_flowi_common(fl4));
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))
 		goto no_route;
@@ -640,7 +640,7 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
 			   (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
 			   ireq->ir_loc_addr, ireq->ir_rmt_port,
 			   htons(ireq->ir_num), sk->sk_uid);
-	security_req_classify_flow(req, flowi4_to_flowi(fl4));
+	security_req_classify_flow(req, flowi4_to_flowi_common(fl4));
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))
 		goto no_route;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 879b76ae4435..89fff5f59eea 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1700,7 +1700,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 			   daddr, saddr,
 			   tcp_hdr(skb)->source, tcp_hdr(skb)->dest,
 			   arg->uid);
-	security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
+	security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4));
 	rt = ip_route_output_key(net, &fl4);
 	if (IS_ERR(rt))
 		return;
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 248856b301c4..8b943f85fff9 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -778,7 +778,7 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	fl4.fl4_icmp_type = user_icmph.type;
 	fl4.fl4_icmp_code = user_icmph.code;
 
-	security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
+	security_sk_classify_flow(sk, flowi4_to_flowi_common(&fl4));
 	rt = ip_route_output_flow(net, &fl4, sk);
 	if (IS_ERR(rt)) {
 		err = PTR_ERR(rt);
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 7d26e0f8bdae..50a73178d63a 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -640,7 +640,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 			goto done;
 	}
 
-	security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
+	security_sk_classify_flow(sk, flowi4_to_flowi_common(&fl4));
 	rt = ip_route_output_flow(net, &fl4, sk);
 	if (IS_ERR(rt)) {
 		err = PTR_ERR(rt);
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 6ac473b47f30..36b3b9b72b75 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -418,7 +418,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 			   inet_sk_flowi_flags(sk),
 			   opt->srr ? opt->faddr : ireq->ir_rmt_addr,
 			   ireq->ir_loc_addr, th->source, th->dest, sk->sk_uid);
-	security_req_classify_flow(req, flowi4_to_flowi(&fl4));
+	security_req_classify_flow(req, flowi4_to_flowi_common(&fl4));
 	rt = ip_route_output_key(sock_net(sk), &fl4);
 	if (IS_ERR(rt)) {
 		reqsk_free(req);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 09f0a23d1a01..594632ff094f 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1197,7 +1197,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 				   faddr, saddr, dport, inet->inet_sport,
 				   sk->sk_uid);
 
-		security_sk_classify_flow(sk, flowi4_to_flowi(fl4));
+		security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4));
 		rt = ip_route_output_flow(net, fl4, sk);
 		if (IS_ERR(rt)) {
 			err = PTR_ERR(rt);
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index e648fbebb167..b8e491d3acf0 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -819,7 +819,7 @@ int inet6_sk_rebuild_header(struct sock *sk)
 		fl6.fl6_dport = inet->inet_dport;
 		fl6.fl6_sport = inet->inet_sport;
 		fl6.flowi6_uid = sk->sk_uid;
-		security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
+		security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6));
 
 		rcu_read_lock();
 		final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt),
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index cc8ad7ddecda..206f66310a88 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -60,7 +60,7 @@ static void ip6_datagram_flow_key_init(struct flowi6 *fl6, struct sock *sk)
 	if (!fl6->flowi6_oif && ipv6_addr_is_multicast(&fl6->daddr))
 		fl6->flowi6_oif = np->mcast_oif;
 
-	security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
+	security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6));
 }
 
 int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr)
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index ec448b71bf9a..91d9136b6e9c 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -567,7 +567,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 	fl6.fl6_icmp_code = code;
 	fl6.flowi6_uid = sock_net_uid(net, NULL);
 	fl6.mp_hash = rt6_multipath_hash(net, &fl6, skb, NULL);
-	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
+	security_skb_classify_flow(skb, flowi6_to_flowi_common(&fl6));
 
 	np = inet6_sk(sk);
 
@@ -749,7 +749,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	fl6.fl6_icmp_type = ICMPV6_ECHO_REPLY;
 	fl6.flowi6_mark = mark;
 	fl6.flowi6_uid = sock_net_uid(net, NULL);
-	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
+	security_skb_classify_flow(skb, flowi6_to_flowi_common(&fl6));
 
 	local_bh_disable();
 	sk = icmpv6_xmit_lock(net);
@@ -1002,7 +1002,7 @@ void icmpv6_flow_init(struct sock *sk, struct flowi6 *fl6,
 	fl6->fl6_icmp_type	= type;
 	fl6->fl6_icmp_code	= 0;
 	fl6->flowi6_oif		= oif;
-	security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
+	security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6));
 }
 
 static void __net_exit icmpv6_sk_exit(struct net *net)
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index e315526fa244..5a9f4d722f35 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -46,7 +46,7 @@ struct dst_entry *inet6_csk_route_req(const struct sock *sk,
 	fl6->fl6_dport = ireq->ir_rmt_port;
 	fl6->fl6_sport = htons(ireq->ir_num);
 	fl6->flowi6_uid = sk->sk_uid;
-	security_req_classify_flow(req, flowi6_to_flowi(fl6));
+	security_req_classify_flow(req, flowi6_to_flowi_common(fl6));
 
 	dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p);
 	if (IS_ERR(dst))
@@ -95,7 +95,7 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk,
 	fl6->fl6_sport = inet->inet_sport;
 	fl6->fl6_dport = inet->inet_dport;
 	fl6->flowi6_uid = sk->sk_uid;
-	security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
+	security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6));
 
 	rcu_read_lock();
 	final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c
index 4aef6baaa55e..bf95513736c9 100644
--- a/net/ipv6/netfilter/nf_reject_ipv6.c
+++ b/net/ipv6/netfilter/nf_reject_ipv6.c
@@ -179,7 +179,7 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook)
 
 	fl6.flowi6_oif = l3mdev_master_ifindex(skb_dst(oldskb)->dev);
 	fl6.flowi6_mark = IP6_REPLY_MARK(net, oldskb->mark);
-	security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6));
+	security_skb_classify_flow(oldskb, flowi6_to_flowi_common(&fl6));
 	dst = ip6_route_output(net, NULL, &fl6);
 	if (dst->error) {
 		dst_release(dst);
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 6caa062f68e7..6ac88fe24a8e 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -111,7 +111,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	fl6.flowi6_uid = sk->sk_uid;
 	fl6.fl6_icmp_type = user_icmph.icmp6_type;
 	fl6.fl6_icmp_code = user_icmph.icmp6_code;
-	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
+	security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6));
 
 	ipcm6_init_sk(&ipc6, np);
 	ipc6.sockc.mark = sk->sk_mark;
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 6e4ab80a3b94..1f56d9aae589 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -915,7 +915,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		fl6.flowi6_oif = np->mcast_oif;
 	else if (!fl6.flowi6_oif)
 		fl6.flowi6_oif = np->ucast_oif;
-	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
+	security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6));
 
 	if (hdrincl)
 		fl6.flowi6_flags |= FLOWI_FLAG_KNOWN_NH;
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index e796a64be308..0351e2ffc707 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -233,7 +233,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 		fl6.fl6_dport = ireq->ir_rmt_port;
 		fl6.fl6_sport = inet_sk(sk)->inet_sport;
 		fl6.flowi6_uid = sk->sk_uid;
-		security_req_classify_flow(req, flowi6_to_flowi(&fl6));
+		security_req_classify_flow(req, flowi6_to_flowi_common(&fl6));
 
 		dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
 		if (IS_ERR(dst))
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 8db59f4e5f13..e5f75bbcc66f 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -278,7 +278,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk));
 	final_p = fl6_update_dst(&fl6, opt, &final);
 
-	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
+	security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6));
 
 	dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
@@ -954,7 +954,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
 	fl6.fl6_dport = t1->dest;
 	fl6.fl6_sport = t1->source;
 	fl6.flowi6_uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL);
-	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
+	security_skb_classify_flow(skb, flowi6_to_flowi_common(&fl6));
 
 	/* Pass a socket to ip6_dst_lookup either it is for RST
 	 * Underlying function will use this to retrieve the network
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 29d9691359b9..724942afc035 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1496,7 +1496,7 @@ do_udp_sendmsg:
 	} else if (!fl6.flowi6_oif)
 		fl6.flowi6_oif = np->ucast_oif;
 
-	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
+	security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6));
 
 	if (ipc6.tclass < 0)
 		ipc6.tclass = np->tclass;
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index e5e5036257b0..96f975777438 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -606,7 +606,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	else if (!fl6.flowi6_oif)
 		fl6.flowi6_oif = np->ucast_oif;
 
-	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
+	security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6));
 
 	if (ipc6.tclass < 0)
 		ipc6.tclass = np->tclass;
diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c
index 9cca35d22927..fb64e8515f7d 100644
--- a/net/netfilter/nf_synproxy_core.c
+++ b/net/netfilter/nf_synproxy_core.c
@@ -849,7 +849,7 @@ synproxy_send_tcp_ipv6(struct net *net,
 	fl6.fl6_sport = nth->source;
 	fl6.fl6_dport = nth->dest;
 	security_skb_classify_flow((struct sk_buff *)skb,
-				   flowi6_to_flowi(&fl6));
+				   flowi6_to_flowi_common(&fl6));
 	err = nf_ip6_route(net, &dst, flowi6_to_flowi(&fl6), false);
 	if (err) {
 		goto free_nskb;
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index bbd4643d7e82..ac25b0c2d87e 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -1021,7 +1021,8 @@ static void xfrm_state_look_at(struct xfrm_policy *pol, struct xfrm_state *x,
 		if ((x->sel.family &&
 		     (x->sel.family != family ||
 		      !xfrm_selector_match(&x->sel, fl, family))) ||
-		    !security_xfrm_state_pol_flow_match(x, pol, fl))
+		    !security_xfrm_state_pol_flow_match(x, pol,
+							&fl->u.__fl_common))
 			return;
 
 		if (!*best ||
@@ -1036,7 +1037,8 @@ static void xfrm_state_look_at(struct xfrm_policy *pol, struct xfrm_state *x,
 		if ((!x->sel.family ||
 		     (x->sel.family == family &&
 		      xfrm_selector_match(&x->sel, fl, family))) &&
-		    security_xfrm_state_pol_flow_match(x, pol, fl))
+		    security_xfrm_state_pol_flow_match(x, pol,
+						       &fl->u.__fl_common))
 			*error = -ESRCH;
 	}
 }
diff --git a/security/security.c b/security/security.c
index a28045dc9e7f..c08e0eec8b9e 100644
--- a/security/security.c
+++ b/security/security.c
@@ -2207,15 +2207,16 @@ void security_sk_clone(const struct sock *sk, struct sock *newsk)
 }
 EXPORT_SYMBOL(security_sk_clone);
 
-void security_sk_classify_flow(struct sock *sk, struct flowi *fl)
+void security_sk_classify_flow(struct sock *sk, struct flowi_common *flic)
 {
-	call_void_hook(sk_getsecid, sk, &fl->flowi_secid);
+	call_void_hook(sk_getsecid, sk, &flic->flowic_secid);
 }
 EXPORT_SYMBOL(security_sk_classify_flow);
 
-void security_req_classify_flow(const struct request_sock *req, struct flowi *fl)
+void security_req_classify_flow(const struct request_sock *req,
+				struct flowi_common *flic)
 {
-	call_void_hook(req_classify_flow, req, fl);
+	call_void_hook(req_classify_flow, req, flic);
 }
 EXPORT_SYMBOL(security_req_classify_flow);
 
@@ -2407,7 +2408,7 @@ int security_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir)
 
 int security_xfrm_state_pol_flow_match(struct xfrm_state *x,
 				       struct xfrm_policy *xp,
-				       const struct flowi *fl)
+				       const struct flowi_common *flic)
 {
 	struct security_hook_list *hp;
 	int rc = LSM_RET_DEFAULT(xfrm_state_pol_flow_match);
@@ -2423,7 +2424,7 @@ int security_xfrm_state_pol_flow_match(struct xfrm_state *x,
 	 */
 	hlist_for_each_entry(hp, &security_hook_heads.xfrm_state_pol_flow_match,
 				list) {
-		rc = hp->hook.xfrm_state_pol_flow_match(x, xp, fl);
+		rc = hp->hook.xfrm_state_pol_flow_match(x, xp, flic);
 		break;
 	}
 	return rc;
@@ -2434,9 +2435,9 @@ int security_xfrm_decode_session(struct sk_buff *skb, u32 *secid)
 	return call_int_hook(xfrm_decode_session, 0, skb, secid, 1);
 }
 
-void security_skb_classify_flow(struct sk_buff *skb, struct flowi *fl)
+void security_skb_classify_flow(struct sk_buff *skb, struct flowi_common *flic)
 {
-	int rc = call_int_hook(xfrm_decode_session, 0, skb, &fl->flowi_secid,
+	int rc = call_int_hook(xfrm_decode_session, 0, skb, &flic->flowic_secid,
 				0);
 
 	BUG_ON(rc);
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 943c2693cec7..a515abdf115b 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -5437,9 +5437,9 @@ static void selinux_secmark_refcount_dec(void)
 }
 
 static void selinux_req_classify_flow(const struct request_sock *req,
-				      struct flowi *fl)
+				      struct flowi_common *flic)
 {
-	fl->flowi_secid = req->secid;
+	flic->flowic_secid = req->secid;
 }
 
 static int selinux_tun_dev_alloc_security(void **security)
diff --git a/security/selinux/include/xfrm.h b/security/selinux/include/xfrm.h
index a0b465316292..0a6f34a7a971 100644
--- a/security/selinux/include/xfrm.h
+++ b/security/selinux/include/xfrm.h
@@ -26,7 +26,7 @@ int selinux_xfrm_state_delete(struct xfrm_state *x);
 int selinux_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir);
 int selinux_xfrm_state_pol_flow_match(struct xfrm_state *x,
 				      struct xfrm_policy *xp,
-				      const struct flowi *fl);
+				      const struct flowi_common *flic);
 
 #ifdef CONFIG_SECURITY_NETWORK_XFRM
 extern atomic_t selinux_xfrm_refcount;
diff --git a/security/selinux/xfrm.c b/security/selinux/xfrm.c
index 7314196185d1..c367d36965d4 100644
--- a/security/selinux/xfrm.c
+++ b/security/selinux/xfrm.c
@@ -175,9 +175,10 @@ int selinux_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir)
  */
 int selinux_xfrm_state_pol_flow_match(struct xfrm_state *x,
 				      struct xfrm_policy *xp,
-				      const struct flowi *fl)
+				      const struct flowi_common *flic)
 {
 	u32 state_sid;
+	u32 flic_sid;
 
 	if (!xp->security)
 		if (x->security)
@@ -196,17 +197,17 @@ int selinux_xfrm_state_pol_flow_match(struct xfrm_state *x,
 				return 0;
 
 	state_sid = x->security->ctx_sid;
+	flic_sid = flic->flowic_secid;
 
-	if (fl->flowi_secid != state_sid)
+	if (flic_sid != state_sid)
 		return 0;
 
 	/* We don't need a separate SA Vs. policy polmatch check since the SA
 	 * is now of the same label as the flow and a flow Vs. policy polmatch
 	 * check had already happened in selinux_xfrm_policy_lookup() above. */
-	return (avc_has_perm(&selinux_state,
-			     fl->flowi_secid, state_sid,
-			    SECCLASS_ASSOCIATION, ASSOCIATION__SENDTO,
-			    NULL) ? 0 : 1);
+	return (avc_has_perm(&selinux_state, flic_sid, state_sid,
+			     SECCLASS_ASSOCIATION, ASSOCIATION__SENDTO,
+			     NULL) ? 0 : 1);
 }
 
 static u32 selinux_xfrm_skb_sid_egress(struct sk_buff *skb)
-- 
cgit v1.2.3


From cc69837fcaf467426ca19e5790085c26146a2300 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 20 Nov 2020 14:50:52 -0800
Subject: net: don't include ethtool.h from netdevice.h

linux/netdevice.h is included in very many places, touching any
of its dependecies causes large incremental builds.

Drop the linux/ethtool.h include, linux/netdevice.h just needs
a forward declaration of struct ethtool_ops.

Fix all the places which made use of this implicit include.

Acked-by: Johannes Berg <johannes@sipsolutions.net>
Acked-by: Shannon Nelson <snelson@pensando.io>
Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Link: https://lore.kernel.org/r/20201120225052.1427503-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/isdn/capi/capi.c                                 | 1 +
 drivers/media/pci/ttpci/av7110_av.c                      | 1 +
 drivers/net/bonding/bond_procfs.c                        | 1 +
 drivers/net/can/usb/gs_usb.c                             | 1 +
 drivers/net/ethernet/amazon/ena/ena_ethtool.c            | 1 +
 drivers/net/ethernet/aquantia/atlantic/aq_nic.h          | 2 ++
 drivers/net/ethernet/broadcom/bnxt/bnxt.h                | 1 +
 drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c          | 1 +
 drivers/net/ethernet/cavium/liquidio/lio_ethtool.c       | 1 +
 drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c      | 1 +
 drivers/net/ethernet/chelsio/cxgb4/cxgb4.h               | 1 +
 drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c           | 1 +
 drivers/net/ethernet/google/gve/gve_ethtool.c            | 1 +
 drivers/net/ethernet/hisilicon/hns3/hnae3.h              | 1 +
 drivers/net/ethernet/huawei/hinic/hinic_port.h           | 1 +
 drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c         | 1 +
 drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h | 1 +
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h             | 1 +
 drivers/net/ethernet/mellanox/mlxsw/core_env.h           | 3 +++
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h           | 1 +
 drivers/net/ethernet/mellanox/mlxsw/switchx2.c           | 1 +
 drivers/net/ethernet/pensando/ionic/ionic_lif.c          | 1 +
 drivers/net/ethernet/pensando/ionic/ionic_stats.c        | 1 +
 drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c          | 1 +
 drivers/net/geneve.c                                     | 1 +
 drivers/net/hyperv/netvsc_drv.c                          | 1 +
 drivers/net/hyperv/rndis_filter.c                        | 1 +
 drivers/net/ipvlan/ipvlan_main.c                         | 2 ++
 drivers/net/nlmon.c                                      | 1 +
 drivers/net/team/team.c                                  | 1 +
 drivers/net/vrf.c                                        | 1 +
 drivers/net/vsockmon.c                                   | 1 +
 drivers/scsi/bnx2fc/bnx2fc_fcoe.c                        | 2 ++
 drivers/scsi/fcoe/fcoe_transport.c                       | 1 +
 drivers/staging/fsl-dpaa2/ethsw/ethsw-ethtool.c          | 2 ++
 drivers/staging/wimax/i2400m/usb.c                       | 1 +
 include/linux/netdevice.h                                | 2 +-
 include/linux/qed/qed_if.h                               | 1 +
 include/net/cfg80211.h                                   | 1 +
 include/rdma/ib_addr.h                                   | 1 +
 include/rdma/ib_verbs.h                                  | 1 +
 net/packet/af_packet.c                                   | 1 +
 net/sched/sch_cbs.c                                      | 1 +
 net/sched/sch_taprio.c                                   | 1 +
 net/socket.c                                             | 1 +
 45 files changed, 51 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/isdn/capi/capi.c b/drivers/isdn/capi/capi.c
index 85767f52fe3c..fdf87acccd06 100644
--- a/drivers/isdn/capi/capi.c
+++ b/drivers/isdn/capi/capi.c
@@ -11,6 +11,7 @@
 
 #include <linux/compiler.h>
 #include <linux/module.h>
+#include <linux/ethtool.h>
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/major.h>
diff --git a/drivers/media/pci/ttpci/av7110_av.c b/drivers/media/pci/ttpci/av7110_av.c
index ea9f7d0058a2..91f4866c7e59 100644
--- a/drivers/media/pci/ttpci/av7110_av.c
+++ b/drivers/media/pci/ttpci/av7110_av.c
@@ -11,6 +11,7 @@
  * the project's page is at https://linuxtv.org
  */
 
+#include <linux/ethtool.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c
index fd5c9cbe45b1..56d34be5e797 100644
--- a/drivers/net/bonding/bond_procfs.c
+++ b/drivers/net/bonding/bond_procfs.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/proc_fs.h>
+#include <linux/ethtool.h>
 #include <linux/export.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index b3431c3feba1..a0336e895d94 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -9,6 +9,7 @@
  * Many thanks to all socketcan devs!
  */
 
+#include <linux/ethtool.h>
 #include <linux/init.h>
 #include <linux/signal.h>
 #include <linux/module.h>
diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
index 3b2cd28f962d..6cdd9efe8df3 100644
--- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c
+++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
@@ -3,6 +3,7 @@
  * Copyright 2015-2020 Amazon.com, Inc. or its affiliates. All rights reserved.
  */
 
+#include <linux/ethtool.h>
 #include <linux/pci.h>
 
 #include "ena_netdev.h"
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
index 926cca9a0c83..1a7148041e3d 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
@@ -10,6 +10,8 @@
 #ifndef AQ_NIC_H
 #define AQ_NIC_H
 
+#include <linux/ethtool.h>
+
 #include "aq_common.h"
 #include "aq_rss.h"
 #include "aq_hw.h"
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 47b3c3127879..950ea26ae0d2 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -20,6 +20,7 @@
 #define DRV_VER_MIN	10
 #define DRV_VER_UPD	1
 
+#include <linux/ethtool.h>
 #include <linux/interrupt.h>
 #include <linux/rhashtable.h>
 #include <linux/crash_dump.h>
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index 23b80aa171dd..a217316228f4 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -8,6 +8,7 @@
  * the Free Software Foundation.
  */
 
+#include <linux/ethtool.h>
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/netdevice.h>
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
index 16eebfc52109..66f2c553370c 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
@@ -15,6 +15,7 @@
  * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
  * NONINFRINGEMENT.  See the GNU General Public License for more details.
  ***********************************************************************/
+#include <linux/ethtool.h>
 #include <linux/netdevice.h>
 #include <linux/net_tstamp.h>
 #include <linux/pci.h>
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
index c7bdac79299a..2f218fbfed06 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
@@ -5,6 +5,7 @@
 
 /* ETHTOOL Support for VNIC_VF Device*/
 
+#include <linux/ethtool.h>
 #include <linux/pci.h>
 #include <linux/net_tstamp.h>
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index 27308600da15..8e681ce72d62 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -39,6 +39,7 @@
 
 #include <linux/bitops.h>
 #include <linux/cache.h>
+#include <linux/ethtool.h>
 #include <linux/interrupt.h>
 #include <linux/list.h>
 #include <linux/netdevice.h>
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
index cd8f9a481d73..d546993bda09 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
@@ -33,6 +33,7 @@
  * SOFTWARE.
  */
 
+#include <linux/ethtool.h>
 #include <linux/pci.h>
 
 #include "t4vf_common.h"
diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c
index 7b44769bd87c..2fb197fd3daf 100644
--- a/drivers/net/ethernet/google/gve/gve_ethtool.c
+++ b/drivers/net/ethernet/google/gve/gve_ethtool.c
@@ -4,6 +4,7 @@
  * Copyright (C) 2015-2019 Google, Inc.
  */
 
+#include <linux/ethtool.h>
 #include <linux/rtnetlink.h>
 #include "gve.h"
 #include "gve_adminq.h"
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 5bae5e859c81..f6fac2418648 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -25,6 +25,7 @@
 #include <linux/dcbnl.h>
 #include <linux/delay.h>
 #include <linux/device.h>
+#include <linux/ethtool.h>
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/pci.h>
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.h b/drivers/net/ethernet/huawei/hinic/hinic_port.h
index 9c3cbe45c9ec..c9ae3d4dc547 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_port.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_port.h
@@ -8,6 +8,7 @@
 #define HINIC_PORT_H
 
 #include <linux/types.h>
+#include <linux/ethtool.h>
 #include <linux/etherdevice.h>
 #include <linux/bitops.h>
 
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
index 908fefaa6b85..66776ba7bfb6 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2013 - 2019 Intel Corporation. */
 
+#include <linux/ethtool.h>
 #include <linux/vmalloc.h>
 
 #include "fm10k.h"
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index ceec649bdd13..103430400a8a 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -11,6 +11,7 @@
 #ifndef OTX2_COMMON_H
 #define OTX2_COMMON_H
 
+#include <linux/ethtool.h>
 #include <linux/pci.h>
 #include <linux/iommu.h>
 #include <linux/net_tstamp.h>
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 014ce8d3d97b..1c50d0f22199 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -36,6 +36,7 @@
 
 #include <linux/bitops.h>
 #include <linux/compiler.h>
+#include <linux/ethtool.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
 #include <linux/netdevice.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.h b/drivers/net/ethernet/mellanox/mlxsw/core_env.h
index 8e36a2634ef5..2b23f8a87862 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_env.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.h
@@ -4,6 +4,9 @@
 #ifndef _MLXSW_CORE_ENV_H
 #define _MLXSW_CORE_ENV_H
 
+struct ethtool_modinfo;
+struct ethtool_eeprom;
+
 int mlxsw_env_module_temp_thresholds_get(struct mlxsw_core *core, int module,
 					 int off, int *temp);
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 74b3959b36d4..642099fee380 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -4,6 +4,7 @@
 #ifndef _MLXSW_SPECTRUM_H
 #define _MLXSW_SPECTRUM_H
 
+#include <linux/ethtool.h>
 #include <linux/types.h>
 #include <linux/netdevice.h>
 #include <linux/rhashtable.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
index 5023d91269f4..40e2e79d4517 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
@@ -6,6 +6,7 @@
 #include <linux/types.h>
 #include <linux/pci.h>
 #include <linux/netdevice.h>
+#include <linux/ethtool.h>
 #include <linux/etherdevice.h>
 #include <linux/slab.h>
 #include <linux/device.h>
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index deabd813e3fe..0afec2fa572d 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2017 - 2019 Pensando Systems, Inc */
 
+#include <linux/ethtool.h>
 #include <linux/printk.h>
 #include <linux/dynamic_debug.h>
 #include <linux/netdevice.h>
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_stats.c b/drivers/net/ethernet/pensando/ionic/ionic_stats.c
index ff20a2ac4c2f..6ae75b771a15 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_stats.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_stats.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2017 - 2019 Pensando Systems, Inc */
 
+#include <linux/ethtool.h>
 #include <linux/kernel.h>
 #include <linux/mutex.h>
 #include <linux/netdevice.h>
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
index d58b51d277f1..ca1535ebb6e7 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
@@ -5,6 +5,7 @@
  */
 
 #include <linux/etherdevice.h>
+#include <linux/ethtool.h>
 #include <linux/if_arp.h>
 #include <net/pkt_sched.h>
 #include "rmnet_config.h"
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index ef9b5ea9073b..5523f069b9a5 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -7,6 +7,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/ethtool.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/etherdevice.h>
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 261e6e55a907..d17bbc75f5e7 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -10,6 +10,7 @@
 
 #include <linux/init.h>
 #include <linux/atomic.h>
+#include <linux/ethtool.h>
 #include <linux/module.h>
 #include <linux/highmem.h>
 #include <linux/device.h>
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index b22e47bcfeca..2c2b55c32a7a 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -6,6 +6,7 @@
  *   Haiyang Zhang <haiyangz@microsoft.com>
  *   Hank Janssen  <hjanssen@microsoft.com>
  */
+#include <linux/ethtool.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/wait.h>
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 60b7d93bb834..a707502a0c0f 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -2,6 +2,8 @@
 /* Copyright (c) 2014 Mahesh Bandewar <maheshb@google.com>
  */
 
+#include <linux/ethtool.h>
+
 #include "ipvlan.h"
 
 static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval,
diff --git a/drivers/net/nlmon.c b/drivers/net/nlmon.c
index afb119f38325..5e19a6839dea 100644
--- a/drivers/net/nlmon.c
+++ b/drivers/net/nlmon.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
+#include <linux/ethtool.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/netdevice.h>
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index b4092127a92c..c19dac21c468 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -4,6 +4,7 @@
  * Copyright (c) 2011 Jiri Pirko <jpirko@redhat.com>
  */
 
+#include <linux/ethtool.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/module.h>
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index f2793ffde191..f8d711a84763 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -9,6 +9,7 @@
  * Based on dummy, team and ipvlan drivers
  */
 
+#include <linux/ethtool.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/netdevice.h>
diff --git a/drivers/net/vsockmon.c b/drivers/net/vsockmon.c
index e8563acf98e8..b1bb1b04b664 100644
--- a/drivers/net/vsockmon.c
+++ b/drivers/net/vsockmon.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
+#include <linux/ethtool.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/if_arp.h>
diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
index 6890bbe04a8c..08fb7d5d08b3 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
@@ -16,6 +16,8 @@
 
 #include "bnx2fc.h"
 
+#include <linux/ethtool.h>
+
 static struct list_head adapter_list;
 static struct list_head if_list;
 static u32 adapter_count;
diff --git a/drivers/scsi/fcoe/fcoe_transport.c b/drivers/scsi/fcoe/fcoe_transport.c
index 6e187d0e71fd..b927b3d84523 100644
--- a/drivers/scsi/fcoe/fcoe_transport.c
+++ b/drivers/scsi/fcoe/fcoe_transport.c
@@ -10,6 +10,7 @@
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/netdevice.h>
+#include <linux/ethtool.h>
 #include <linux/errno.h>
 #include <linux/crc32.h>
 #include <scsi/libfcoe.h>
diff --git a/drivers/staging/fsl-dpaa2/ethsw/ethsw-ethtool.c b/drivers/staging/fsl-dpaa2/ethsw/ethsw-ethtool.c
index ace4a6d28562..ad55cd738847 100644
--- a/drivers/staging/fsl-dpaa2/ethsw/ethsw-ethtool.c
+++ b/drivers/staging/fsl-dpaa2/ethsw/ethsw-ethtool.c
@@ -7,6 +7,8 @@
  *
  */
 
+#include <linux/ethtool.h>
+
 #include "ethsw.h"
 
 static struct {
diff --git a/drivers/staging/wimax/i2400m/usb.c b/drivers/staging/wimax/i2400m/usb.c
index 3b84dd7b5567..f250d03ce7c7 100644
--- a/drivers/staging/wimax/i2400m/usb.c
+++ b/drivers/staging/wimax/i2400m/usb.c
@@ -51,6 +51,7 @@
 #include "i2400m-usb.h"
 #include "linux-wimax-i2400m.h"
 #include <linux/debugfs.h>
+#include <linux/ethtool.h>
 #include <linux/slab.h>
 #include <linux/module.h>
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 03433a4c929e..0049e8fe4905 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -34,7 +34,6 @@
 #include <linux/workqueue.h>
 #include <linux/dynamic_queue_limits.h>
 
-#include <linux/ethtool.h>
 #include <net/net_namespace.h>
 #ifdef CONFIG_DCB
 #include <net/dcbnl.h>
@@ -51,6 +50,7 @@
 
 struct netpoll_info;
 struct device;
+struct ethtool_ops;
 struct phy_device;
 struct dsa_port;
 struct ip_tunnel_parm;
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index 57fb295ea41a..68d17a4fbf20 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -7,6 +7,7 @@
 #ifndef _QED_IF_H
 #define _QED_IF_H
 
+#include <linux/ethtool.h>
 #include <linux/types.h>
 #include <linux/interrupt.h>
 #include <linux/netdevice.h>
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index ab249ca5d5d1..78c763dfc99a 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -10,6 +10,7 @@
  * Copyright (C) 2018-2020 Intel Corporation
  */
 
+#include <linux/ethtool.h>
 #include <linux/netdevice.h>
 #include <linux/debugfs.h>
 #include <linux/list.h>
diff --git a/include/rdma/ib_addr.h b/include/rdma/ib_addr.h
index b0e636ac6690..d808dc3d239e 100644
--- a/include/rdma/ib_addr.h
+++ b/include/rdma/ib_addr.h
@@ -7,6 +7,7 @@
 #ifndef IB_ADDR_H
 #define IB_ADDR_H
 
+#include <linux/ethtool.h>
 #include <linux/in.h>
 #include <linux/in6.h>
 #include <linux/if_arp.h>
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 9bf6c319a670..3883efd588aa 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -12,6 +12,7 @@
 #ifndef IB_VERBS_H
 #define IB_VERBS_H
 
+#include <linux/ethtool.h>
 #include <linux/types.h>
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 62ebfaa7adcb..48a0ed836b46 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -46,6 +46,7 @@
  *					Copyright (C) 2011, <lokec@ccs.neu.edu>
  */
 
+#include <linux/ethtool.h>
 #include <linux/types.h>
 #include <linux/mm.h>
 #include <linux/capability.h>
diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c
index 2eaac2ff380f..459cc240eda9 100644
--- a/net/sched/sch_cbs.c
+++ b/net/sched/sch_cbs.c
@@ -50,6 +50,7 @@
  *	locredit = max_frame_size * (sendslope / port_transmit_rate)
  */
 
+#include <linux/ethtool.h>
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index b0ad7687ee2c..26fb8a62996b 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -6,6 +6,7 @@
  *
  */
 
+#include <linux/ethtool.h>
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/kernel.h>
diff --git a/net/socket.c b/net/socket.c
index 152b1dcf93c6..bfef11ba35b8 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -52,6 +52,7 @@
  *	Based upon Swansea University Computer Society NET3.039
  */
 
+#include <linux/ethtool.h>
 #include <linux/mm.h>
 #include <linux/socket.h>
 #include <linux/file.h>
-- 
cgit v1.2.3


From d549699048b4b5c22dd710455bcdb76966e55aa3 Mon Sep 17 00:00:00 2001
From: Eyal Birger <eyal.birger@gmail.com>
Date: Sat, 21 Nov 2020 08:28:17 +0200
Subject: net/packet: fix packet receive on L3 devices without visible hard
 header

In the patchset merged by commit b9fcf0a0d826
("Merge branch 'support-AF_PACKET-for-layer-3-devices'") L3 devices which
did not have header_ops were given one for the purpose of protocol parsing
on af_packet transmit path.

That change made af_packet receive path regard these devices as having a
visible L3 header and therefore aligned incoming skb->data to point to the
skb's mac_header. Some devices, such as ipip, xfrmi, and others, do not
reset their mac_header prior to ingress and therefore their incoming
packets became malformed.

Ideally these devices would reset their mac headers, or af_packet would be
able to rely on dev->hard_header_len being 0 for such cases, but it seems
this is not the case.

Fix by changing af_packet RX ll visibility criteria to include the
existence of a '.create()' header operation, which is used when creating
a device hard header - via dev_hard_header() - by upper layers, and does
not exist in these L3 devices.

As this predicate may be useful in other situations, add it as a common
dev_has_header() helper in netdevice.h.

Fixes: b9fcf0a0d826 ("Merge branch 'support-AF_PACKET-for-layer-3-devices'")
Signed-off-by: Eyal Birger <eyal.birger@gmail.com>
Acked-by: Jason A. Donenfeld <Jason@zx2c4.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/20201121062817.3178900-1-eyal.birger@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h |  5 +++++
 net/packet/af_packet.c    | 18 +++++++++---------
 2 files changed, 14 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 964b494b0e8d..fa275a054f46 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3137,6 +3137,11 @@ static inline bool dev_validate_header(const struct net_device *dev,
 	return false;
 }
 
+static inline bool dev_has_header(const struct net_device *dev)
+{
+	return dev->header_ops && dev->header_ops->create;
+}
+
 typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr,
 			   int len, int size);
 int register_gifconf(unsigned int family, gifconf_func_t *gifconf);
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index cefbd50c1090..7a18ffff8551 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -93,8 +93,8 @@
 
 /*
    Assumptions:
-   - If the device has no dev->header_ops, there is no LL header visible
-     above the device. In this case, its hard_header_len should be 0.
+   - If the device has no dev->header_ops->create, there is no LL header
+     visible above the device. In this case, its hard_header_len should be 0.
      The device may prepend its own header internally. In this case, its
      needed_headroom should be set to the space needed for it to add its
      internal header.
@@ -108,26 +108,26 @@
 On receive:
 -----------
 
-Incoming, dev->header_ops != NULL
+Incoming, dev_has_header(dev) == true
    mac_header -> ll header
    data       -> data
 
-Outgoing, dev->header_ops != NULL
+Outgoing, dev_has_header(dev) == true
    mac_header -> ll header
    data       -> ll header
 
-Incoming, dev->header_ops == NULL
+Incoming, dev_has_header(dev) == false
    mac_header -> data
      However drivers often make it point to the ll header.
      This is incorrect because the ll header should be invisible to us.
    data       -> data
 
-Outgoing, dev->header_ops == NULL
+Outgoing, dev_has_header(dev) == false
    mac_header -> data. ll header is invisible to us.
    data       -> data
 
 Resume
-  If dev->header_ops == NULL we are unable to restore the ll header,
+  If dev_has_header(dev) == false we are unable to restore the ll header,
     because it is invisible to us.
 
 
@@ -2069,7 +2069,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev,
 
 	skb->dev = dev;
 
-	if (dev->header_ops) {
+	if (dev_has_header(dev)) {
 		/* The device has an explicit notion of ll header,
 		 * exported to higher levels.
 		 *
@@ -2198,7 +2198,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	if (!net_eq(dev_net(dev), sock_net(sk)))
 		goto drop;
 
-	if (dev->header_ops) {
+	if (dev_has_header(dev)) {
 		if (sk->sk_type != SOCK_DGRAM)
 			skb_push(skb, skb->data - skb_mac_header(skb));
 		else if (skb->pkt_type == PACKET_OUTGOING) {
-- 
cgit v1.2.3


From b7cab9be7c16128a0de21ed7ae67211838813437 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Wed, 4 Nov 2020 23:23:58 +0800
Subject: soundwire: SDCA: detect sdca_cascade interrupt

The SoundWire 1.2 specification defines an "SDCA cascade" bit which
handles a logical OR of all SDCA interrupt sources (up to 30 defined).

Due to limitations of the addressing space, this bit is located in the
SDW_DP0_INT register when DP0 is used, or alternatively in the
DP0_SDCA_Support_INTSTAT register when DP0 is not used.

To allow for both cases to be handled, this bit will be checked in the
main device-level interrupt handling code. This will result in the
register being read twice if DP0 is enabled, but it's not clear how to
optimize this case. It's also more logical to deal with this interrupt
at the device than the port level, this bit is really not DP0 specific
and its location in the DP0_INTSTAT bit is only due to the lack of
free space in SCP_INTSTAT_1.

The SDCA_Cascade bit cannot be masked or cleared, so the interrupt
handling only forwards the detection to the Slave driver, which will
deal with reading the relevant SDCA status bits and clearing them. The
bus driver only signals the detection.

The communication with the Slave driver is based on the same interrupt
callback, with only an extension to provide the status of the
sdca_cascade bit.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Rander Wang <rander.wang@linux.intel.com>
Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20201104152358.9518-1-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/bus.c       | 28 +++++++++++++++++++++++++++-
 include/linux/soundwire/sdw.h |  4 ++++
 2 files changed, 31 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c
index 8eaf31e76677..ffe4600fd95b 100644
--- a/drivers/soundwire/bus.c
+++ b/drivers/soundwire/bus.c
@@ -1424,6 +1424,7 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave)
 	int port_num, stat, ret, count = 0;
 	unsigned long port;
 	bool slave_notify = false;
+	u8 sdca_cascade = 0;
 	u8 buf, buf2[2], _buf, _buf2[2];
 	bool parity_check;
 	bool parity_quirk;
@@ -1453,6 +1454,16 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave)
 		goto io_err;
 	}
 
+	if (slave->prop.is_sdca) {
+		ret = sdw_read(slave, SDW_DP0_INT);
+		if (ret < 0) {
+			dev_err(slave->bus->dev,
+				"SDW_DP0_INT read failed:%d\n", ret);
+			goto io_err;
+		}
+		sdca_cascade = ret & SDW_DP0_SDCA_CASCADE;
+	}
+
 	do {
 		/*
 		 * Check parity, bus clash and Slave (impl defined)
@@ -1489,6 +1500,10 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave)
 			clear |= SDW_SCP_INT1_IMPL_DEF;
 		}
 
+		/* the SDCA interrupts are cleared in the codec driver .interrupt_callback() */
+		if (sdca_cascade)
+			slave_notify = true;
+
 		/* Check port 0 - 3 interrupts */
 		port = buf & SDW_SCP_INT1_PORT0_3;
 
@@ -1526,6 +1541,7 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave)
 		/* Update the Slave driver */
 		if (slave_notify && slave->ops &&
 		    slave->ops->interrupt_callback) {
+			slave_intr.sdca_cascade = sdca_cascade;
 			slave_intr.control_port = clear;
 			memcpy(slave_intr.port, &port_status,
 			       sizeof(slave_intr.port));
@@ -1563,11 +1579,21 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave)
 			goto io_err;
 		}
 
+		if (slave->prop.is_sdca) {
+			ret = sdw_read(slave, SDW_DP0_INT);
+			if (ret < 0) {
+				dev_err(slave->bus->dev,
+					"SDW_DP0_INT read failed:%d\n", ret);
+				goto io_err;
+			}
+			sdca_cascade = ret & SDW_DP0_SDCA_CASCADE;
+		}
+
 		/* Make sure no interrupts are pending */
 		buf &= _buf;
 		buf2[0] &= _buf2[0];
 		buf2[1] &= _buf2[1];
-		stat = buf || buf2[0] || buf2[1];
+		stat = buf || buf2[0] || buf2[1] || sdca_cascade;
 
 		/*
 		 * Exit loop if Slave is continuously in ALERT state even
diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 41cc1192f9aa..f0b01b728640 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -359,6 +359,7 @@ struct sdw_dpn_prop {
  * @sink_dpn_prop: Sink Data Port N properties
  * @scp_int1_mask: SCP_INT1_MASK desired settings
  * @quirks: bitmask identifying deltas from the MIPI specification
+ * @is_sdca: the Slave supports the SDCA specification
  */
 struct sdw_slave_prop {
 	u32 mipi_revision;
@@ -382,6 +383,7 @@ struct sdw_slave_prop {
 	struct sdw_dpn_prop *sink_dpn_prop;
 	u8 scp_int1_mask;
 	u32 quirks;
+	bool is_sdca;
 };
 
 #define SDW_SLAVE_QUIRKS_INVALID_INITIAL_PARITY	BIT(0)
@@ -479,10 +481,12 @@ struct sdw_slave_id {
 
 /**
  * struct sdw_slave_intr_status - Slave interrupt status
+ * @sdca_cascade: set if the Slave device reports an SDCA interrupt
  * @control_port: control port status
  * @port: data port status
  */
 struct sdw_slave_intr_status {
+	bool sdca_cascade;
 	u8 control_port;
 	u8 port[15];
 };
-- 
cgit v1.2.3


From 74d862b682f51e45d25b95b1ecf212428a4967b0 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 18 Nov 2020 20:48:42 +0100
Subject: sched: Make migrate_disable/enable() independent of RT

Now that the scheduler can deal with migrate disable properly, there is no
real compelling reason to make it only available for RT.

There are quite some code pathes which needlessly disable preemption in
order to prevent migration and some constructs like kmap_atomic() enforce
it implicitly.

Making it available independent of RT allows to provide a preemptible
variant of kmap_atomic() and makes the code more consistent in general.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Grudgingly-Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20201118204007.269943012@linutronix.de
---
 include/linux/kernel.h  | 21 ++++++++++++++-------
 include/linux/preempt.h | 38 +++-----------------------------------
 include/linux/sched.h   |  2 +-
 kernel/sched/core.c     | 45 +++++++++++++++++++++++++++++++++++----------
 kernel/sched/sched.h    |  4 ++--
 lib/smp_processor_id.c  |  2 +-
 6 files changed, 56 insertions(+), 56 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 2f05e9128201..665837f9a831 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -204,6 +204,7 @@ extern int _cond_resched(void);
 extern void ___might_sleep(const char *file, int line, int preempt_offset);
 extern void __might_sleep(const char *file, int line, int preempt_offset);
 extern void __cant_sleep(const char *file, int line, int preempt_offset);
+extern void __cant_migrate(const char *file, int line);
 
 /**
  * might_sleep - annotation for functions that can sleep
@@ -227,6 +228,18 @@ extern void __cant_sleep(const char *file, int line, int preempt_offset);
 # define cant_sleep() \
 	do { __cant_sleep(__FILE__, __LINE__, 0); } while (0)
 # define sched_annotate_sleep()	(current->task_state_change = 0)
+
+/**
+ * cant_migrate - annotation for functions that cannot migrate
+ *
+ * Will print a stack trace if executed in code which is migratable
+ */
+# define cant_migrate()							\
+	do {								\
+		if (IS_ENABLED(CONFIG_SMP))				\
+			__cant_migrate(__FILE__, __LINE__);		\
+	} while (0)
+
 /**
  * non_block_start - annotate the start of section where sleeping is prohibited
  *
@@ -251,6 +264,7 @@ extern void __cant_sleep(const char *file, int line, int preempt_offset);
 				   int preempt_offset) { }
 # define might_sleep() do { might_resched(); } while (0)
 # define cant_sleep() do { } while (0)
+# define cant_migrate()		do { } while (0)
 # define sched_annotate_sleep() do { } while (0)
 # define non_block_start() do { } while (0)
 # define non_block_end() do { } while (0)
@@ -258,13 +272,6 @@ extern void __cant_sleep(const char *file, int line, int preempt_offset);
 
 #define might_sleep_if(cond) do { if (cond) might_sleep(); } while (0)
 
-#ifndef CONFIG_PREEMPT_RT
-# define cant_migrate()		cant_sleep()
-#else
-  /* Placeholder for now */
-# define cant_migrate()		do { } while (0)
-#endif
-
 /**
  * abs - return absolute value of an argument
  * @x: the value.  If it is unsigned type, it is converted to signed type first.
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 8b43922e65df..6df63cbe8bb0 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -322,7 +322,7 @@ static inline void preempt_notifier_init(struct preempt_notifier *notifier,
 
 #endif
 
-#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT)
+#ifdef CONFIG_SMP
 
 /*
  * Migrate-Disable and why it is undesired.
@@ -382,43 +382,11 @@ static inline void preempt_notifier_init(struct preempt_notifier *notifier,
 extern void migrate_disable(void);
 extern void migrate_enable(void);
 
-#elif defined(CONFIG_PREEMPT_RT)
+#else
 
 static inline void migrate_disable(void) { }
 static inline void migrate_enable(void) { }
 
-#else /* !CONFIG_PREEMPT_RT */
-
-/**
- * migrate_disable - Prevent migration of the current task
- *
- * Maps to preempt_disable() which also disables preemption. Use
- * migrate_disable() to annotate that the intent is to prevent migration,
- * but not necessarily preemption.
- *
- * Can be invoked nested like preempt_disable() and needs the corresponding
- * number of migrate_enable() invocations.
- */
-static __always_inline void migrate_disable(void)
-{
-	preempt_disable();
-}
-
-/**
- * migrate_enable - Allow migration of the current task
- *
- * Counterpart to migrate_disable().
- *
- * As migrate_disable() can be invoked nested, only the outermost invocation
- * reenables migration.
- *
- * Currently mapped to preempt_enable().
- */
-static __always_inline void migrate_enable(void)
-{
-	preempt_enable();
-}
-
-#endif /* CONFIG_SMP && CONFIG_PREEMPT_RT */
+#endif /* CONFIG_SMP */
 
 #endif /* __LINUX_PREEMPT_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 3af9d52fe093..a33f35f68060 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -715,7 +715,7 @@ struct task_struct {
 	const cpumask_t			*cpus_ptr;
 	cpumask_t			cpus_mask;
 	void				*migration_pending;
-#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT)
+#ifdef CONFIG_SMP
 	unsigned short			migration_disabled;
 #endif
 	unsigned short			migration_flags;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e6473ecaab3c..c962922784d1 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1728,8 +1728,6 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 
 #ifdef CONFIG_SMP
 
-#ifdef CONFIG_PREEMPT_RT
-
 static void
 __do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask, u32 flags);
 
@@ -1800,8 +1798,6 @@ static inline bool rq_has_pinned_tasks(struct rq *rq)
 	return rq->nr_pinned;
 }
 
-#endif
-
 /*
  * Per-CPU kthreads are allowed to run on !active && online CPUs, see
  * __set_cpus_allowed_ptr() and select_fallback_rq().
@@ -2882,7 +2878,7 @@ void sched_set_stop_task(int cpu, struct task_struct *stop)
 	}
 }
 
-#else
+#else /* CONFIG_SMP */
 
 static inline int __set_cpus_allowed_ptr(struct task_struct *p,
 					 const struct cpumask *new_mask,
@@ -2891,10 +2887,6 @@ static inline int __set_cpus_allowed_ptr(struct task_struct *p,
 	return set_cpus_allowed_ptr(p, new_mask);
 }
 
-#endif /* CONFIG_SMP */
-
-#if !defined(CONFIG_SMP) || !defined(CONFIG_PREEMPT_RT)
-
 static inline void migrate_disable_switch(struct rq *rq, struct task_struct *p) { }
 
 static inline bool rq_has_pinned_tasks(struct rq *rq)
@@ -2902,7 +2894,7 @@ static inline bool rq_has_pinned_tasks(struct rq *rq)
 	return false;
 }
 
-#endif
+#endif /* !CONFIG_SMP */
 
 static void
 ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
@@ -7924,6 +7916,39 @@ void __cant_sleep(const char *file, int line, int preempt_offset)
 	add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
 }
 EXPORT_SYMBOL_GPL(__cant_sleep);
+
+#ifdef CONFIG_SMP
+void __cant_migrate(const char *file, int line)
+{
+	static unsigned long prev_jiffy;
+
+	if (irqs_disabled())
+		return;
+
+	if (is_migration_disabled(current))
+		return;
+
+	if (!IS_ENABLED(CONFIG_PREEMPT_COUNT))
+		return;
+
+	if (preempt_count() > 0)
+		return;
+
+	if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
+		return;
+	prev_jiffy = jiffies;
+
+	pr_err("BUG: assuming non migratable context at %s:%d\n", file, line);
+	pr_err("in_atomic(): %d, irqs_disabled(): %d, migration_disabled() %u pid: %d, name: %s\n",
+	       in_atomic(), irqs_disabled(), is_migration_disabled(current),
+	       current->pid, current->comm);
+
+	debug_show_held_locks(current);
+	dump_stack();
+	add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
+}
+EXPORT_SYMBOL_GPL(__cant_migrate);
+#endif
 #endif
 
 #ifdef CONFIG_MAGIC_SYSRQ
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 590e6f27068c..f5acb6c5ce49 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1056,7 +1056,7 @@ struct rq {
 	struct cpuidle_state	*idle_state;
 #endif
 
-#if defined(CONFIG_PREEMPT_RT) && defined(CONFIG_SMP)
+#ifdef CONFIG_SMP
 	unsigned int		nr_pinned;
 #endif
 	unsigned int		push_busy;
@@ -1092,7 +1092,7 @@ static inline int cpu_of(struct rq *rq)
 
 static inline bool is_migration_disabled(struct task_struct *p)
 {
-#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT)
+#ifdef CONFIG_SMP
 	return p->migration_disabled;
 #else
 	return false;
diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c
index faaa927ac2c8..1c1dbd300325 100644
--- a/lib/smp_processor_id.c
+++ b/lib/smp_processor_id.c
@@ -26,7 +26,7 @@ unsigned int check_preemption_disabled(const char *what1, const char *what2)
 	if (current->nr_cpus_allowed == 1)
 		goto out;
 
-#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT)
+#ifdef CONFIG_SMP
 	if (current->migration_disabled)
 		goto out;
 #endif
-- 
cgit v1.2.3


From 5fbda3ecd14a5343644979c98d6eb65b7e7de9d8 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 18 Nov 2020 20:48:43 +0100
Subject: sched: highmem: Store local kmaps in task struct

Instead of storing the map per CPU provide and use per task storage. That
prepares for local kmaps which are preemptible.

The context switch code is preparatory and not yet in use because
kmap_atomic() runs with preemption disabled. Will be made usable in the
next step.

The context switch logic is safe even when an interrupt happens after
clearing or before restoring the kmaps. The kmap index in task struct is
not modified so any nesting kmap in an interrupt will use unused indices
and on return the counter is the same as before.

Also add an assert into the return to user space code. Going back to user
space with an active kmap local is a nono.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20201118204007.372935758@linutronix.de
---
 include/linux/highmem-internal.h | 10 ++++
 include/linux/sched.h            |  9 ++++
 kernel/entry/common.c            |  2 +
 kernel/fork.c                    |  1 +
 kernel/sched/core.c              | 25 ++++++++++
 mm/highmem.c                     | 99 ++++++++++++++++++++++++++++++++++++----
 6 files changed, 136 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h
index 6ceed907b14e..c5a22177db85 100644
--- a/include/linux/highmem-internal.h
+++ b/include/linux/highmem-internal.h
@@ -9,6 +9,16 @@
 void *__kmap_local_pfn_prot(unsigned long pfn, pgprot_t prot);
 void *__kmap_local_page_prot(struct page *page, pgprot_t prot);
 void kunmap_local_indexed(void *vaddr);
+void kmap_local_fork(struct task_struct *tsk);
+void __kmap_local_sched_out(void);
+void __kmap_local_sched_in(void);
+static inline void kmap_assert_nomap(void)
+{
+	DEBUG_LOCKS_WARN_ON(current->kmap_ctrl.idx);
+}
+#else
+static inline void kmap_local_fork(struct task_struct *tsk) { }
+static inline void kmap_assert_nomap(void) { }
 #endif
 
 #ifdef CONFIG_HIGHMEM
diff --git a/include/linux/sched.h b/include/linux/sched.h
index a33f35f68060..8946911cee9f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -34,6 +34,7 @@
 #include <linux/rseq.h>
 #include <linux/seqlock.h>
 #include <linux/kcsan.h>
+#include <asm/kmap_size.h>
 
 /* task_struct member predeclarations (sorted alphabetically): */
 struct audit_context;
@@ -629,6 +630,13 @@ struct wake_q_node {
 	struct wake_q_node *next;
 };
 
+struct kmap_ctrl {
+#ifdef CONFIG_KMAP_LOCAL
+	int				idx;
+	pte_t				pteval[KM_MAX_IDX];
+#endif
+};
+
 struct task_struct {
 #ifdef CONFIG_THREAD_INFO_IN_TASK
 	/*
@@ -1294,6 +1302,7 @@ struct task_struct {
 	unsigned int			sequential_io;
 	unsigned int			sequential_io_avg;
 #endif
+	struct kmap_ctrl		kmap_ctrl;
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
 	unsigned long			task_state_change;
 #endif
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 2b8366693d5c..4ae1fe0898e9 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -2,6 +2,7 @@
 
 #include <linux/context_tracking.h>
 #include <linux/entry-common.h>
+#include <linux/highmem.h>
 #include <linux/livepatch.h>
 #include <linux/audit.h>
 
@@ -194,6 +195,7 @@ static void exit_to_user_mode_prepare(struct pt_regs *regs)
 
 	/* Ensure that the address limit is intact and no locks are held */
 	addr_limit_user_check();
+	kmap_assert_nomap();
 	lockdep_assert_irqs_disabled();
 	lockdep_sys_exit();
 }
diff --git a/kernel/fork.c b/kernel/fork.c
index 32083db7a2a2..17dcd1817799 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -930,6 +930,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 	account_kernel_stack(tsk, 1);
 
 	kcov_task_init(tsk);
+	kmap_local_fork(tsk);
 
 #ifdef CONFIG_FAULT_INJECTION
 	tsk->fail_nth = 0;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c962922784d1..953abdbe1472 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4094,6 +4094,22 @@ static inline void finish_lock_switch(struct rq *rq)
 # define finish_arch_post_lock_switch()	do { } while (0)
 #endif
 
+static inline void kmap_local_sched_out(void)
+{
+#ifdef CONFIG_KMAP_LOCAL
+	if (unlikely(current->kmap_ctrl.idx))
+		__kmap_local_sched_out();
+#endif
+}
+
+static inline void kmap_local_sched_in(void)
+{
+#ifdef CONFIG_KMAP_LOCAL
+	if (unlikely(current->kmap_ctrl.idx))
+		__kmap_local_sched_in();
+#endif
+}
+
 /**
  * prepare_task_switch - prepare to switch tasks
  * @rq: the runqueue preparing to switch
@@ -4116,6 +4132,7 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev,
 	perf_event_task_sched_out(prev, next);
 	rseq_preempt(prev);
 	fire_sched_out_preempt_notifiers(prev, next);
+	kmap_local_sched_out();
 	prepare_task(next);
 	prepare_arch_switch(next);
 }
@@ -4182,6 +4199,14 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 	finish_lock_switch(rq);
 	finish_arch_post_lock_switch();
 	kcov_finish_switch(current);
+	/*
+	 * kmap_local_sched_out() is invoked with rq::lock held and
+	 * interrupts disabled. There is no requirement for that, but the
+	 * sched out code does not have an interrupt enabled section.
+	 * Restoring the maps on sched in does not require interrupts being
+	 * disabled either.
+	 */
+	kmap_local_sched_in();
 
 	fire_sched_in_preempt_notifiers(current);
 	/*
diff --git a/mm/highmem.c b/mm/highmem.c
index 39aaca1a1ece..d1ef06aa6de6 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -365,8 +365,6 @@ EXPORT_SYMBOL(kunmap_high);
 
 #include <asm/kmap_size.h>
 
-static DEFINE_PER_CPU(int, __kmap_local_idx);
-
 /*
  * With DEBUG_KMAP_LOCAL the stack depth is doubled and every second
  * slot is unused which acts as a guard page
@@ -379,23 +377,21 @@ static DEFINE_PER_CPU(int, __kmap_local_idx);
 
 static inline int kmap_local_idx_push(void)
 {
-	int idx = __this_cpu_add_return(__kmap_local_idx, KM_INCR) - 1;
-
 	WARN_ON_ONCE(in_irq() && !irqs_disabled());
-	BUG_ON(idx >= KM_MAX_IDX);
-	return idx;
+	current->kmap_ctrl.idx += KM_INCR;
+	BUG_ON(current->kmap_ctrl.idx >= KM_MAX_IDX);
+	return current->kmap_ctrl.idx - 1;
 }
 
 static inline int kmap_local_idx(void)
 {
-	return __this_cpu_read(__kmap_local_idx) - 1;
+	return current->kmap_ctrl.idx - 1;
 }
 
 static inline void kmap_local_idx_pop(void)
 {
-	int idx = __this_cpu_sub_return(__kmap_local_idx, KM_INCR);
-
-	BUG_ON(idx < 0);
+	current->kmap_ctrl.idx -= KM_INCR;
+	BUG_ON(current->kmap_ctrl.idx < 0);
 }
 
 #ifndef arch_kmap_local_post_map
@@ -464,6 +460,7 @@ void *__kmap_local_pfn_prot(unsigned long pfn, pgprot_t prot)
 	pteval = pfn_pte(pfn, prot);
 	set_pte_at(&init_mm, vaddr, kmap_pte - idx, pteval);
 	arch_kmap_local_post_map(vaddr, pteval);
+	current->kmap_ctrl.pteval[kmap_local_idx()] = pteval;
 	preempt_enable();
 
 	return (void *)vaddr;
@@ -522,10 +519,92 @@ void kunmap_local_indexed(void *vaddr)
 	arch_kmap_local_pre_unmap(addr);
 	pte_clear(&init_mm, addr, kmap_pte - idx);
 	arch_kmap_local_post_unmap(addr);
+	current->kmap_ctrl.pteval[kmap_local_idx()] = __pte(0);
 	kmap_local_idx_pop();
 	preempt_enable();
 }
 EXPORT_SYMBOL(kunmap_local_indexed);
+
+/*
+ * Invoked before switch_to(). This is safe even when during or after
+ * clearing the maps an interrupt which needs a kmap_local happens because
+ * the task::kmap_ctrl.idx is not modified by the unmapping code so a
+ * nested kmap_local will use the next unused index and restore the index
+ * on unmap. The already cleared kmaps of the outgoing task are irrelevant
+ * because the interrupt context does not know about them. The same applies
+ * when scheduling back in for an interrupt which happens before the
+ * restore is complete.
+ */
+void __kmap_local_sched_out(void)
+{
+	struct task_struct *tsk = current;
+	pte_t *kmap_pte = kmap_get_pte();
+	int i;
+
+	/* Clear kmaps */
+	for (i = 0; i < tsk->kmap_ctrl.idx; i++) {
+		pte_t pteval = tsk->kmap_ctrl.pteval[i];
+		unsigned long addr;
+		int idx;
+
+		/* With debug all even slots are unmapped and act as guard */
+		if (IS_ENABLED(CONFIG_DEBUG_HIGHMEM) && !(i & 0x01)) {
+			WARN_ON_ONCE(!pte_none(pteval));
+			continue;
+		}
+		if (WARN_ON_ONCE(pte_none(pteval)))
+			continue;
+
+		/*
+		 * This is a horrible hack for XTENSA to calculate the
+		 * coloured PTE index. Uses the PFN encoded into the pteval
+		 * and the map index calculation because the actual mapped
+		 * virtual address is not stored in task::kmap_ctrl.
+		 * For any sane architecture this is optimized out.
+		 */
+		idx = arch_kmap_local_map_idx(i, pte_pfn(pteval));
+
+		addr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
+		arch_kmap_local_pre_unmap(addr);
+		pte_clear(&init_mm, addr, kmap_pte - idx);
+		arch_kmap_local_post_unmap(addr);
+	}
+}
+
+void __kmap_local_sched_in(void)
+{
+	struct task_struct *tsk = current;
+	pte_t *kmap_pte = kmap_get_pte();
+	int i;
+
+	/* Restore kmaps */
+	for (i = 0; i < tsk->kmap_ctrl.idx; i++) {
+		pte_t pteval = tsk->kmap_ctrl.pteval[i];
+		unsigned long addr;
+		int idx;
+
+		/* With debug all even slots are unmapped and act as guard */
+		if (IS_ENABLED(CONFIG_DEBUG_HIGHMEM) && !(i & 0x01)) {
+			WARN_ON_ONCE(!pte_none(pteval));
+			continue;
+		}
+		if (WARN_ON_ONCE(pte_none(pteval)))
+			continue;
+
+		/* See comment in __kmap_local_sched_out() */
+		idx = arch_kmap_local_map_idx(i, pte_pfn(pteval));
+		addr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
+		set_pte_at(&init_mm, addr, kmap_pte - idx, pteval);
+		arch_kmap_local_post_map(addr, pteval);
+	}
+}
+
+void kmap_local_fork(struct task_struct *tsk)
+{
+	if (WARN_ON_ONCE(tsk->kmap_ctrl.idx))
+		memset(&tsk->kmap_ctrl, 0, sizeof(tsk->kmap_ctrl));
+}
+
 #endif
 
 #if defined(HASHED_PAGE_VIRTUAL)
-- 
cgit v1.2.3


From f3ba3c710ac5a30cd058615a9eb62d2ad95bb782 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 18 Nov 2020 20:48:44 +0100
Subject: mm/highmem: Provide kmap_local*

Now that the kmap atomic index is stored in task struct provide a
preemptible variant. On context switch the maps of an outgoing task are
removed and the map of the incoming task are restored. That's obviously
slow, but highmem is slow anyway.

The kmap_local.*() functions can be invoked from both preemptible and
atomic context. kmap local sections disable migration to keep the resulting
virtual mapping address correct, but disable neither pagefaults nor
preemption.

A wholesale conversion of kmap_atomic to be fully preemptible is not
possible because some of the usage sites might rely on the preemption
disable for serialization or on the implicit pagefault disable. Needs to be
done on a case by case basis.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20201118204007.468533059@linutronix.de
---
 include/linux/highmem-internal.h | 48 ++++++++++++++++++++++++++++++++++++++++
 include/linux/highmem.h          | 43 +++++++++++++++++++++--------------
 mm/highmem.c                     |  6 +++++
 3 files changed, 81 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h
index c5a22177db85..1bbe96dc8be6 100644
--- a/include/linux/highmem-internal.h
+++ b/include/linux/highmem-internal.h
@@ -68,6 +68,26 @@ static inline void kmap_flush_unused(void)
 	__kmap_flush_unused();
 }
 
+static inline void *kmap_local_page(struct page *page)
+{
+	return __kmap_local_page_prot(page, kmap_prot);
+}
+
+static inline void *kmap_local_page_prot(struct page *page, pgprot_t prot)
+{
+	return __kmap_local_page_prot(page, prot);
+}
+
+static inline void *kmap_local_pfn(unsigned long pfn)
+{
+	return __kmap_local_pfn_prot(pfn, kmap_prot);
+}
+
+static inline void __kunmap_local(void *vaddr)
+{
+	kunmap_local_indexed(vaddr);
+}
+
 static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot)
 {
 	preempt_disable();
@@ -140,6 +160,28 @@ static inline void kunmap(struct page *page)
 #endif
 }
 
+static inline void *kmap_local_page(struct page *page)
+{
+	return page_address(page);
+}
+
+static inline void *kmap_local_page_prot(struct page *page, pgprot_t prot)
+{
+	return kmap_local_page(page);
+}
+
+static inline void *kmap_local_pfn(unsigned long pfn)
+{
+	return kmap_local_page(pfn_to_page(pfn));
+}
+
+static inline void __kunmap_local(void *addr)
+{
+#ifdef ARCH_HAS_FLUSH_ON_KUNMAP
+	kunmap_flush_on_unmap(addr);
+#endif
+}
+
 static inline void *kmap_atomic(struct page *page)
 {
 	preempt_disable();
@@ -181,4 +223,10 @@ do {								\
 	__kunmap_atomic(__addr);				\
 } while (0)
 
+#define kunmap_local(__addr)					\
+do {								\
+	BUILD_BUG_ON(__same_type((__addr), struct page *));	\
+	__kunmap_local(__addr);					\
+} while (0)
+
 #endif
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 7d098bd621f6..f597830f26b4 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -60,24 +60,22 @@ static inline struct page *kmap_to_page(void *addr);
 static inline void kmap_flush_unused(void);
 
 /**
- * kmap_atomic - Atomically map a page for temporary usage
+ * kmap_local_page - Map a page for temporary usage
  * @page:	Pointer to the page to be mapped
  *
  * Returns: The virtual address of the mapping
  *
- * Side effect: On return pagefaults and preemption are disabled.
- *
  * Can be invoked from any context.
  *
  * Requires careful handling when nesting multiple mappings because the map
  * management is stack based. The unmap has to be in the reverse order of
  * the map operation:
  *
- * addr1 = kmap_atomic(page1);
- * addr2 = kmap_atomic(page2);
+ * addr1 = kmap_local_page(page1);
+ * addr2 = kmap_local_page(page2);
  * ...
- * kunmap_atomic(addr2);
- * kunmap_atomic(addr1);
+ * kunmap_local(addr2);
+ * kunmap_local(addr1);
  *
  * Unmapping addr1 before addr2 is invalid and causes malfunction.
  *
@@ -88,10 +86,26 @@ static inline void kmap_flush_unused(void);
  * virtual address of the direct mapping. Only real highmem pages are
  * temporarily mapped.
  *
- * While it is significantly faster than kmap() it comes with restrictions
- * about the pointer validity and the side effects of disabling page faults
- * and preemption. Use it only when absolutely necessary, e.g. from non
- * preemptible contexts.
+ * While it is significantly faster than kmap() for the higmem case it
+ * comes with restrictions about the pointer validity. Only use when really
+ * necessary.
+ *
+ * On HIGHMEM enabled systems mapping a highmem page has the side effect of
+ * disabling migration in order to keep the virtual address stable across
+ * preemption. No caller of kmap_local_page() can rely on this side effect.
+ */
+static inline void *kmap_local_page(struct page *page);
+
+/**
+ * kmap_atomic - Atomically map a page for temporary usage - Deprecated!
+ * @page:	Pointer to the page to be mapped
+ *
+ * Returns: The virtual address of the mapping
+ *
+ * Effectively a wrapper around kmap_local_page() which disables pagefaults
+ * and preemption.
+ *
+ * Do not use in new code. Use kmap_local_page() instead.
  */
 static inline void *kmap_atomic(struct page *page);
 
@@ -101,12 +115,9 @@ static inline void *kmap_atomic(struct page *page);
  *
  * Counterpart to kmap_atomic().
  *
- * Undoes the side effects of kmap_atomic(), i.e. reenabling pagefaults and
+ * Effectively a wrapper around kunmap_local() which additionally undoes
+ * the side effects of kmap_atomic(), i.e. reenabling pagefaults and
  * preemption.
- *
- * Other than that a NOOP for CONFIG_HIGHMEM=n and for mappings of pages
- * in the low memory area. For real highmen pages the mapping which was
- * established with kmap_atomic() is destroyed.
  */
 
 /* Highmem related interfaces for management code */
diff --git a/mm/highmem.c b/mm/highmem.c
index d1ef06aa6de6..83f9660f168f 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -453,6 +453,11 @@ void *__kmap_local_pfn_prot(unsigned long pfn, pgprot_t prot)
 	unsigned long vaddr;
 	int idx;
 
+	/*
+	 * Disable migration so resulting virtual address is stable
+	 * accross preemption.
+	 */
+	migrate_disable();
 	preempt_disable();
 	idx = arch_kmap_local_map_idx(kmap_local_idx_push(), pfn);
 	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
@@ -522,6 +527,7 @@ void kunmap_local_indexed(void *vaddr)
 	current->kmap_ctrl.pteval[kmap_local_idx()] = __pte(0);
 	kmap_local_idx_pop();
 	preempt_enable();
+	migrate_enable();
 }
 EXPORT_SYMBOL(kunmap_local_indexed);
 
-- 
cgit v1.2.3


From e66f6e095486f0210fcf3c5eb3ecf13fa348be4c Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 18 Nov 2020 20:48:45 +0100
Subject: io-mapping: Provide iomap_local variant

Similar to kmap local provide a iomap local variant which only disables
migration, but neither disables pagefaults nor preemption.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20201118204007.561220818@linutronix.de
---
 Documentation/driver-api/io-mapping.rst | 74 ++++++++++++++++++++-------------
 include/linux/io-mapping.h              | 30 ++++++++++++-
 2 files changed, 73 insertions(+), 31 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/driver-api/io-mapping.rst b/Documentation/driver-api/io-mapping.rst
index e33b88268554..a0cfb15988df 100644
--- a/Documentation/driver-api/io-mapping.rst
+++ b/Documentation/driver-api/io-mapping.rst
@@ -20,55 +20,71 @@ A mapping object is created during driver initialization using::
 mappable, while 'size' indicates how large a mapping region to
 enable. Both are in bytes.
 
-This _wc variant provides a mapping which may only be used
-with the io_mapping_map_atomic_wc or io_mapping_map_wc.
+This _wc variant provides a mapping which may only be used with
+io_mapping_map_atomic_wc(), io_mapping_map_local_wc() or
+io_mapping_map_wc().
 
-With this mapping object, individual pages can be mapped either atomically
-or not, depending on the necessary scheduling environment. Of course, atomic
-maps are more efficient::
+With this mapping object, individual pages can be mapped either temporarily
+or long term, depending on the requirements. Of course, temporary maps are
+more efficient. They come in two flavours::
+
+	void *io_mapping_map_local_wc(struct io_mapping *mapping,
+				      unsigned long offset)
 
 	void *io_mapping_map_atomic_wc(struct io_mapping *mapping,
 				       unsigned long offset)
 
-'offset' is the offset within the defined mapping region.
-Accessing addresses beyond the region specified in the
-creation function yields undefined results. Using an offset
-which is not page aligned yields an undefined result. The
-return value points to a single page in CPU address space.
+'offset' is the offset within the defined mapping region.  Accessing
+addresses beyond the region specified in the creation function yields
+undefined results. Using an offset which is not page aligned yields an
+undefined result. The return value points to a single page in CPU address
+space.
 
-This _wc variant returns a write-combining map to the
-page and may only be used with mappings created by
-io_mapping_create_wc
+This _wc variant returns a write-combining map to the page and may only be
+used with mappings created by io_mapping_create_wc()
 
-Note that the task may not sleep while holding this page
-mapped.
+Temporary mappings are only valid in the context of the caller. The mapping
+is not guaranteed to be globaly visible.
 
-::
+io_mapping_map_local_wc() has a side effect on X86 32bit as it disables
+migration to make the mapping code work. No caller can rely on this side
+effect.
 
-	void io_mapping_unmap_atomic(void *vaddr)
+io_mapping_map_atomic_wc() has the side effect of disabling preemption and
+pagefaults. Don't use in new code. Use io_mapping_map_local_wc() instead.
 
-'vaddr' must be the value returned by the last
-io_mapping_map_atomic_wc call. This unmaps the specified
-page and allows the task to sleep once again.
+Nested mappings need to be undone in reverse order because the mapping
+code uses a stack for keeping track of them::
 
-If you need to sleep while holding the lock, you can use the non-atomic
-variant, although they may be significantly slower.
+ addr1 = io_mapping_map_local_wc(map1, offset1);
+ addr2 = io_mapping_map_local_wc(map2, offset2);
+ ...
+ io_mapping_unmap_local(addr2);
+ io_mapping_unmap_local(addr1);
 
-::
+The mappings are released with::
+
+	void io_mapping_unmap_local(void *vaddr)
+	void io_mapping_unmap_atomic(void *vaddr)
+
+'vaddr' must be the value returned by the last io_mapping_map_local_wc() or
+io_mapping_map_atomic_wc() call. This unmaps the specified mapping and
+undoes the side effects of the mapping functions.
+
+If you need to sleep while holding a mapping, you can use the regular
+variant, although this may be significantly slower::
 
 	void *io_mapping_map_wc(struct io_mapping *mapping,
 				unsigned long offset)
 
-This works like io_mapping_map_atomic_wc except it allows
-the task to sleep while holding the page mapped.
-
+This works like io_mapping_map_atomic/local_wc() except it has no side
+effects and the pointer is globaly visible.
 
-::
+The mappings are released with::
 
 	void io_mapping_unmap(void *vaddr)
 
-This works like io_mapping_unmap_atomic, except it is used
-for pages mapped with io_mapping_map_wc.
+Use for pages mapped with io_mapping_map_wc().
 
 At driver close time, the io_mapping object must be freed::
 
diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h
index 60e7c83e4904..c093e81310a9 100644
--- a/include/linux/io-mapping.h
+++ b/include/linux/io-mapping.h
@@ -82,6 +82,21 @@ io_mapping_unmap_atomic(void __iomem *vaddr)
 	preempt_enable();
 }
 
+static inline void __iomem *
+io_mapping_map_local_wc(struct io_mapping *mapping, unsigned long offset)
+{
+	resource_size_t phys_addr;
+
+	BUG_ON(offset >= mapping->size);
+	phys_addr = mapping->base + offset;
+	return __iomap_local_pfn_prot(PHYS_PFN(phys_addr), mapping->prot);
+}
+
+static inline void io_mapping_unmap_local(void __iomem *vaddr)
+{
+	kunmap_local_indexed((void __force *)vaddr);
+}
+
 static inline void __iomem *
 io_mapping_map_wc(struct io_mapping *mapping,
 		  unsigned long offset,
@@ -101,7 +116,7 @@ io_mapping_unmap(void __iomem *vaddr)
 	iounmap(vaddr);
 }
 
-#else
+#else  /* HAVE_ATOMIC_IOMAP */
 
 #include <linux/uaccess.h>
 
@@ -166,7 +181,18 @@ io_mapping_unmap_atomic(void __iomem *vaddr)
 	preempt_enable();
 }
 
-#endif /* HAVE_ATOMIC_IOMAP */
+static inline void __iomem *
+io_mapping_map_local_wc(struct io_mapping *mapping, unsigned long offset)
+{
+	return io_mapping_map_wc(mapping, offset, PAGE_SIZE);
+}
+
+static inline void io_mapping_unmap_local(void __iomem *vaddr)
+{
+	io_mapping_unmap(vaddr);
+}
+
+#endif /* !HAVE_ATOMIC_IOMAP */
 
 static inline struct io_mapping *
 io_mapping_create_wc(resource_size_t base,
-- 
cgit v1.2.3


From acfdd18591eaac25446e976a0c0d190f8b3dbfb1 Mon Sep 17 00:00:00 2001
From: Amit Sunil Dhamne <amit.sunil.dhamne@xilinx.com>
Date: Mon, 23 Nov 2020 21:52:41 -0800
Subject: firmware: xilinx: Use hash-table for api feature check
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently array of fix length PM_API_MAX is used to cache
the pm_api version (valid or invalid). However ATF based
PM APIs values are much higher then PM_API_MAX.
So to include ATF based PM APIs also, use hash-table to
store the pm_api version status.

Signed-off-by: Amit Sunil Dhamne <amit.sunil.dhamne@xilinx.com>
Reported-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Ravi Patel <ravi.patel@xilinx.com>
Signed-off-by: Rajan Vaja <rajan.vaja@xilinx.com>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Tested-by: Michal Simek <michal.simek@xilinx.com>
Fixes: f3217d6f2f7a ("firmware: xilinx: fix out-of-bounds access")
Cc: stable <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/1606197161-25976-1-git-send-email-rajan.vaja@xilinx.com
Signed-off-by: Michal Simek <michal.simek@xilinx.com>
---
 drivers/firmware/xilinx/zynqmp.c     | 63 ++++++++++++++++++++++++++++--------
 include/linux/firmware/xlnx-zynqmp.h |  4 ---
 2 files changed, 49 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c
index 5828302c7c5c..d08ac824c993 100644
--- a/drivers/firmware/xilinx/zynqmp.c
+++ b/drivers/firmware/xilinx/zynqmp.c
@@ -20,12 +20,28 @@
 #include <linux/of_platform.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
+#include <linux/hashtable.h>
 
 #include <linux/firmware/xlnx-zynqmp.h>
 #include "zynqmp-debug.h"
 
+/* Max HashMap Order for PM API feature check (1<<7 = 128) */
+#define PM_API_FEATURE_CHECK_MAX_ORDER  7
+
 static bool feature_check_enabled;
-static u32 zynqmp_pm_features[PM_API_MAX];
+DEFINE_HASHTABLE(pm_api_features_map, PM_API_FEATURE_CHECK_MAX_ORDER);
+
+/**
+ * struct pm_api_feature_data - PM API Feature data
+ * @pm_api_id:		PM API Id, used as key to index into hashmap
+ * @feature_status:	status of PM API feature: valid, invalid
+ * @hentry:		hlist_node that hooks this entry into hashtable
+ */
+struct pm_api_feature_data {
+	u32 pm_api_id;
+	int feature_status;
+	struct hlist_node hentry;
+};
 
 static const struct mfd_cell firmware_devs[] = {
 	{
@@ -142,29 +158,37 @@ static int zynqmp_pm_feature(u32 api_id)
 	int ret;
 	u32 ret_payload[PAYLOAD_ARG_CNT];
 	u64 smc_arg[2];
+	struct pm_api_feature_data *feature_data;
 
 	if (!feature_check_enabled)
 		return 0;
 
-	/* Return value if feature is already checked */
-	if (api_id > ARRAY_SIZE(zynqmp_pm_features))
-		return PM_FEATURE_INVALID;
+	/* Check for existing entry in hash table for given api */
+	hash_for_each_possible(pm_api_features_map, feature_data, hentry,
+			       api_id) {
+		if (feature_data->pm_api_id == api_id)
+			return feature_data->feature_status;
+	}
 
-	if (zynqmp_pm_features[api_id] != PM_FEATURE_UNCHECKED)
-		return zynqmp_pm_features[api_id];
+	/* Add new entry if not present */
+	feature_data = kmalloc(sizeof(*feature_data), GFP_KERNEL);
+	if (!feature_data)
+		return -ENOMEM;
 
+	feature_data->pm_api_id = api_id;
 	smc_arg[0] = PM_SIP_SVC | PM_FEATURE_CHECK;
 	smc_arg[1] = api_id;
 
 	ret = do_fw_call(smc_arg[0], smc_arg[1], 0, ret_payload);
-	if (ret) {
-		zynqmp_pm_features[api_id] = PM_FEATURE_INVALID;
-		return PM_FEATURE_INVALID;
-	}
+	if (ret)
+		ret = -EOPNOTSUPP;
+	else
+		ret = ret_payload[1];
 
-	zynqmp_pm_features[api_id] = ret_payload[1];
+	feature_data->feature_status = ret;
+	hash_add(pm_api_features_map, &feature_data->hentry, api_id);
 
-	return zynqmp_pm_features[api_id];
+	return ret;
 }
 
 /**
@@ -200,9 +224,12 @@ int zynqmp_pm_invoke_fn(u32 pm_api_id, u32 arg0, u32 arg1,
 	 * Make sure to stay in x0 register
 	 */
 	u64 smc_arg[4];
+	int ret;
 
-	if (zynqmp_pm_feature(pm_api_id) == PM_FEATURE_INVALID)
-		return -ENOTSUPP;
+	/* Check if feature is supported or not */
+	ret = zynqmp_pm_feature(pm_api_id);
+	if (ret < 0)
+		return ret;
 
 	smc_arg[0] = PM_SIP_SVC | pm_api_id;
 	smc_arg[1] = ((u64)arg1 << 32) | arg0;
@@ -1252,9 +1279,17 @@ static int zynqmp_firmware_probe(struct platform_device *pdev)
 
 static int zynqmp_firmware_remove(struct platform_device *pdev)
 {
+	struct pm_api_feature_data *feature_data;
+	int i;
+
 	mfd_remove_devices(&pdev->dev);
 	zynqmp_pm_api_debugfs_exit();
 
+	hash_for_each(pm_api_features_map, i, feature_data, hentry) {
+		hash_del(&feature_data->hentry);
+		kfree(feature_data);
+	}
+
 	return 0;
 }
 
diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h
index 5968df82b991..41a1bab98b7e 100644
--- a/include/linux/firmware/xlnx-zynqmp.h
+++ b/include/linux/firmware/xlnx-zynqmp.h
@@ -50,10 +50,6 @@
 #define	ZYNQMP_PM_CAPABILITY_WAKEUP	0x4U
 #define	ZYNQMP_PM_CAPABILITY_UNUSABLE	0x8U
 
-/* Feature check status */
-#define PM_FEATURE_INVALID		-1
-#define PM_FEATURE_UNCHECKED		0
-
 /*
  * Firmware FPGA Manager flags
  * XILINX_ZYNQMP_PM_FPGA_FULL:	FPGA full reconfiguration
-- 
cgit v1.2.3


From 7a9f50a05843fee8366bd3a65addbebaa7cf7f07 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 15 Jun 2020 11:51:29 +0200
Subject: irq_work: Cleanup

Get rid of the __call_single_node union and clean up the API a little
to avoid external code relying on the structure layout as much.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
---
 drivers/gpu/drm/i915/i915_request.c |  4 ++--
 include/linux/irq_work.h            | 33 +++++++++++++++++++++------------
 include/linux/irqflags.h            |  4 ++--
 kernel/bpf/stackmap.c               |  2 +-
 kernel/irq_work.c                   | 18 +++++++++---------
 kernel/printk/printk.c              |  6 ++----
 kernel/rcu/tree.c                   |  3 +--
 kernel/time/tick-sched.c            |  6 ++----
 kernel/trace/bpf_trace.c            |  2 +-
 9 files changed, 41 insertions(+), 37 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 0e813819b041..5385b081a376 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -197,7 +197,7 @@ __notify_execute_cb(struct i915_request *rq, bool (*fn)(struct irq_work *wrk))
 
 	llist_for_each_entry_safe(cb, cn,
 				  llist_del_all(&rq->execute_cb),
-				  work.llnode)
+				  work.node.llist)
 		fn(&cb->work);
 }
 
@@ -460,7 +460,7 @@ __await_execution(struct i915_request *rq,
 	 * callback first, then checking the ACTIVE bit, we serialise with
 	 * the completed/retired request.
 	 */
-	if (llist_add(&cb->work.llnode, &signal->execute_cb)) {
+	if (llist_add(&cb->work.node.llist, &signal->execute_cb)) {
 		if (i915_request_is_active(signal) ||
 		    __request_in_flight(signal))
 			__notify_execute_cb_imm(signal);
diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h
index 30823780c192..ec2a47a81e42 100644
--- a/include/linux/irq_work.h
+++ b/include/linux/irq_work.h
@@ -14,28 +14,37 @@
  */
 
 struct irq_work {
-	union {
-		struct __call_single_node node;
-		struct {
-			struct llist_node llnode;
-			atomic_t flags;
-		};
-	};
+	struct __call_single_node node;
 	void (*func)(struct irq_work *);
 };
 
+#define __IRQ_WORK_INIT(_func, _flags) (struct irq_work){	\
+	.node = { .u_flags = (_flags), },			\
+	.func = (_func),					\
+}
+
+#define IRQ_WORK_INIT(_func) __IRQ_WORK_INIT(_func, 0)
+#define IRQ_WORK_INIT_LAZY(_func) __IRQ_WORK_INIT(_func, IRQ_WORK_LAZY)
+#define IRQ_WORK_INIT_HARD(_func) __IRQ_WORK_INIT(_func, IRQ_WORK_HARD_IRQ)
+
+#define DEFINE_IRQ_WORK(name, _f)				\
+	struct irq_work name = IRQ_WORK_INIT(_f)
+
 static inline
 void init_irq_work(struct irq_work *work, void (*func)(struct irq_work *))
 {
-	atomic_set(&work->flags, 0);
-	work->func = func;
+	*work = IRQ_WORK_INIT(func);
 }
 
-#define DEFINE_IRQ_WORK(name, _f) struct irq_work name = {	\
-		.flags = ATOMIC_INIT(0),			\
-		.func  = (_f)					\
+static inline bool irq_work_is_pending(struct irq_work *work)
+{
+	return atomic_read(&work->node.a_flags) & IRQ_WORK_PENDING;
 }
 
+static inline bool irq_work_is_busy(struct irq_work *work)
+{
+	return atomic_read(&work->node.a_flags) & IRQ_WORK_BUSY;
+}
 
 bool irq_work_queue(struct irq_work *work);
 bool irq_work_queue_on(struct irq_work *work, int cpu);
diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h
index 3ed4e8771b64..fef2d43a7a1d 100644
--- a/include/linux/irqflags.h
+++ b/include/linux/irqflags.h
@@ -109,12 +109,12 @@ do {						\
 
 # define lockdep_irq_work_enter(__work)					\
 	  do {								\
-		  if (!(atomic_read(&__work->flags) & IRQ_WORK_HARD_IRQ))\
+		  if (!(atomic_read(&__work->node.a_flags) & IRQ_WORK_HARD_IRQ))\
 			current->irq_config = 1;			\
 	  } while (0)
 # define lockdep_irq_work_exit(__work)					\
 	  do {								\
-		  if (!(atomic_read(&__work->flags) & IRQ_WORK_HARD_IRQ))\
+		  if (!(atomic_read(&__work->node.a_flags) & IRQ_WORK_HARD_IRQ))\
 			current->irq_config = 0;			\
 	  } while (0)
 
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 06065fa27124..599041cd0c8a 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -298,7 +298,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 	if (irqs_disabled()) {
 		if (!IS_ENABLED(CONFIG_PREEMPT_RT)) {
 			work = this_cpu_ptr(&up_read_work);
-			if (atomic_read(&work->irq_work.flags) & IRQ_WORK_BUSY) {
+			if (irq_work_is_busy(&work->irq_work)) {
 				/* cannot queue more up_read, fallback */
 				irq_work_busy = true;
 			}
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index eca83965b631..fbff25adb574 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -31,7 +31,7 @@ static bool irq_work_claim(struct irq_work *work)
 {
 	int oflags;
 
-	oflags = atomic_fetch_or(IRQ_WORK_CLAIMED | CSD_TYPE_IRQ_WORK, &work->flags);
+	oflags = atomic_fetch_or(IRQ_WORK_CLAIMED | CSD_TYPE_IRQ_WORK, &work->node.a_flags);
 	/*
 	 * If the work is already pending, no need to raise the IPI.
 	 * The pairing atomic_fetch_andnot() in irq_work_run() makes sure
@@ -53,12 +53,12 @@ void __weak arch_irq_work_raise(void)
 static void __irq_work_queue_local(struct irq_work *work)
 {
 	/* If the work is "lazy", handle it from next tick if any */
-	if (atomic_read(&work->flags) & IRQ_WORK_LAZY) {
-		if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) &&
+	if (atomic_read(&work->node.a_flags) & IRQ_WORK_LAZY) {
+		if (llist_add(&work->node.llist, this_cpu_ptr(&lazy_list)) &&
 		    tick_nohz_tick_stopped())
 			arch_irq_work_raise();
 	} else {
-		if (llist_add(&work->llnode, this_cpu_ptr(&raised_list)))
+		if (llist_add(&work->node.llist, this_cpu_ptr(&raised_list)))
 			arch_irq_work_raise();
 	}
 }
@@ -102,7 +102,7 @@ bool irq_work_queue_on(struct irq_work *work, int cpu)
 	if (cpu != smp_processor_id()) {
 		/* Arch remote IPI send/receive backend aren't NMI safe */
 		WARN_ON_ONCE(in_nmi());
-		__smp_call_single_queue(cpu, &work->llnode);
+		__smp_call_single_queue(cpu, &work->node.llist);
 	} else {
 		__irq_work_queue_local(work);
 	}
@@ -142,7 +142,7 @@ void irq_work_single(void *arg)
 	 * to claim that work don't rely on us to handle their data
 	 * while we are in the middle of the func.
 	 */
-	flags = atomic_fetch_andnot(IRQ_WORK_PENDING, &work->flags);
+	flags = atomic_fetch_andnot(IRQ_WORK_PENDING, &work->node.a_flags);
 
 	lockdep_irq_work_enter(work);
 	work->func(work);
@@ -152,7 +152,7 @@ void irq_work_single(void *arg)
 	 * no-one else claimed it meanwhile.
 	 */
 	flags &= ~IRQ_WORK_PENDING;
-	(void)atomic_cmpxchg(&work->flags, flags, flags & ~IRQ_WORK_BUSY);
+	(void)atomic_cmpxchg(&work->node.a_flags, flags, flags & ~IRQ_WORK_BUSY);
 }
 
 static void irq_work_run_list(struct llist_head *list)
@@ -166,7 +166,7 @@ static void irq_work_run_list(struct llist_head *list)
 		return;
 
 	llnode = llist_del_all(list);
-	llist_for_each_entry_safe(work, tmp, llnode, llnode)
+	llist_for_each_entry_safe(work, tmp, llnode, node.llist)
 		irq_work_single(work);
 }
 
@@ -198,7 +198,7 @@ void irq_work_sync(struct irq_work *work)
 {
 	lockdep_assert_irqs_enabled();
 
-	while (atomic_read(&work->flags) & IRQ_WORK_BUSY)
+	while (irq_work_is_busy(work))
 		cpu_relax();
 }
 EXPORT_SYMBOL_GPL(irq_work_sync);
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index fe64a49344bf..9ef23d4b07c7 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -3025,10 +3025,8 @@ static void wake_up_klogd_work_func(struct irq_work *irq_work)
 		wake_up_interruptible(&log_wait);
 }
 
-static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = {
-	.func = wake_up_klogd_work_func,
-	.flags = ATOMIC_INIT(IRQ_WORK_LAZY),
-};
+static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) =
+	IRQ_WORK_INIT_LAZY(wake_up_klogd_work_func);
 
 void wake_up_klogd(void)
 {
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 06895ef85d69..a41e84f1b55a 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1311,8 +1311,6 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 		if (IS_ENABLED(CONFIG_IRQ_WORK) &&
 		    !rdp->rcu_iw_pending && rdp->rcu_iw_gp_seq != rnp->gp_seq &&
 		    (rnp->ffmask & rdp->grpmask)) {
-			init_irq_work(&rdp->rcu_iw, rcu_iw_handler);
-			atomic_set(&rdp->rcu_iw.flags, IRQ_WORK_HARD_IRQ);
 			rdp->rcu_iw_pending = true;
 			rdp->rcu_iw_gp_seq = rnp->gp_seq;
 			irq_work_queue_on(&rdp->rcu_iw, rdp->cpu);
@@ -3964,6 +3962,7 @@ int rcutree_prepare_cpu(unsigned int cpu)
 	rdp->cpu_no_qs.b.norm = true;
 	rdp->core_needs_qs = false;
 	rdp->rcu_iw_pending = false;
+	rdp->rcu_iw = IRQ_WORK_INIT_HARD(rcu_iw_handler);
 	rdp->rcu_iw_gp_seq = rdp->gp_seq - 1;
 	trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("cpuonl"));
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 81632cd5e3b7..1b734070f028 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -243,10 +243,8 @@ static void nohz_full_kick_func(struct irq_work *work)
 	/* Empty, the tick restart happens on tick_nohz_irq_exit() */
 }
 
-static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = {
-	.func = nohz_full_kick_func,
-	.flags = ATOMIC_INIT(IRQ_WORK_HARD_IRQ),
-};
+static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) =
+	IRQ_WORK_INIT_HARD(nohz_full_kick_func);
 
 /*
  * Kick this CPU if it's full dynticks in order to force it to
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 4517c8b66518..a6903912f7a0 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1086,7 +1086,7 @@ static int bpf_send_signal_common(u32 sig, enum pid_type type)
 			return -EINVAL;
 
 		work = this_cpu_ptr(&send_signal_work);
-		if (atomic_read(&work->irq_work.flags) & IRQ_WORK_BUSY)
+		if (irq_work_is_busy(&work->irq_work))
 			return -EBUSY;
 
 		/* Add the current task, which is the target of sending signal,
-- 
cgit v1.2.3


From 545b8c8df41f9ecbaf806332d4095bc4bc7c14e8 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 15 Jun 2020 11:29:31 +0200
Subject: smp: Cleanup smp_call_function*()

Get rid of the __call_single_node union and cleanup the API a little
to avoid external code relying on the structure layout as much.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
---
 arch/mips/kernel/process.c                      |  5 ++-
 arch/mips/kernel/smp.c                          | 25 +++----------
 arch/s390/pci/pci_irq.c                         |  4 +-
 arch/x86/kernel/cpuid.c                         |  7 ++--
 arch/x86/lib/msr-smp.c                          |  7 ++--
 block/blk-mq.c                                  |  4 +-
 drivers/cpuidle/coupled.c                       |  3 +-
 drivers/net/ethernet/cavium/liquidio/lio_core.c |  9 +----
 include/linux/smp.h                             | 19 +++++-----
 kernel/debug/debug_core.c                       |  6 +--
 kernel/sched/core.c                             | 12 +-----
 kernel/smp.c                                    | 50 ++++++++++++-------------
 net/core/dev.c                                  |  3 +-
 13 files changed, 60 insertions(+), 94 deletions(-)

(limited to 'include/linux')

diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 75ebd8d7bd5d..d7e288f3a1e7 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -702,7 +702,6 @@ unsigned long arch_align_stack(unsigned long sp)
 	return sp & ALMASK;
 }
 
-static DEFINE_PER_CPU(call_single_data_t, backtrace_csd);
 static struct cpumask backtrace_csd_busy;
 
 static void handle_backtrace(void *info)
@@ -711,6 +710,9 @@ static void handle_backtrace(void *info)
 	cpumask_clear_cpu(smp_processor_id(), &backtrace_csd_busy);
 }
 
+static DEFINE_PER_CPU(call_single_data_t, backtrace_csd) =
+	CSD_INIT(handle_backtrace, NULL);
+
 static void raise_backtrace(cpumask_t *mask)
 {
 	call_single_data_t *csd;
@@ -730,7 +732,6 @@ static void raise_backtrace(cpumask_t *mask)
 		}
 
 		csd = &per_cpu(backtrace_csd, cpu);
-		csd->func = handle_backtrace;
 		smp_call_function_single_async(cpu, csd);
 	}
 }
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index 48d84d5fcc36..74b9102fd06e 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -687,36 +687,23 @@ EXPORT_SYMBOL(flush_tlb_one);
 
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 
-static DEFINE_PER_CPU(call_single_data_t, tick_broadcast_csd);
-
-void tick_broadcast(const struct cpumask *mask)
-{
-	call_single_data_t *csd;
-	int cpu;
-
-	for_each_cpu(cpu, mask) {
-		csd = &per_cpu(tick_broadcast_csd, cpu);
-		smp_call_function_single_async(cpu, csd);
-	}
-}
-
 static void tick_broadcast_callee(void *info)
 {
 	tick_receive_broadcast();
 }
 
-static int __init tick_broadcast_init(void)
+static DEFINE_PER_CPU(call_single_data_t, tick_broadcast_csd) =
+	CSD_INIT(tick_broadcast_callee, NULL);
+
+void tick_broadcast(const struct cpumask *mask)
 {
 	call_single_data_t *csd;
 	int cpu;
 
-	for (cpu = 0; cpu < NR_CPUS; cpu++) {
+	for_each_cpu(cpu, mask) {
 		csd = &per_cpu(tick_broadcast_csd, cpu);
-		csd->func = tick_broadcast_callee;
+		smp_call_function_single_async(cpu, csd);
 	}
-
-	return 0;
 }
-early_initcall(tick_broadcast_init);
 
 #endif /* CONFIG_GENERIC_CLOCKEVENTS_BROADCAST */
diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c
index 743f257cf2cb..1311b6f9d6dd 100644
--- a/arch/s390/pci/pci_irq.c
+++ b/arch/s390/pci/pci_irq.c
@@ -178,9 +178,7 @@ static void zpci_handle_fallback_irq(void)
 		if (atomic_inc_return(&cpu_data->scheduled) > 1)
 			continue;
 
-		cpu_data->csd.func = zpci_handle_remote_irq;
-		cpu_data->csd.info = &cpu_data->scheduled;
-		cpu_data->csd.flags = 0;
+		INIT_CSD(&cpu_data->csd, zpci_handle_remote_irq, &cpu_data->scheduled);
 		smp_call_function_single_async(cpu, &cpu_data->csd);
 	}
 }
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index 3492aa36bf09..6f7b8cc1bc9f 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -74,10 +74,9 @@ static ssize_t cpuid_read(struct file *file, char __user *buf,
 
 	init_completion(&cmd.done);
 	for (; count; count -= 16) {
-		call_single_data_t csd = {
-			.func = cpuid_smp_cpuid,
-			.info = &cmd,
-		};
+		call_single_data_t csd;
+
+		INIT_CSD(&csd, cpuid_smp_cpuid, &cmd);
 
 		cmd.regs.eax = pos;
 		cmd.regs.ecx = pos >> 32;
diff --git a/arch/x86/lib/msr-smp.c b/arch/x86/lib/msr-smp.c
index fee8b9c0520c..75a0915b0d01 100644
--- a/arch/x86/lib/msr-smp.c
+++ b/arch/x86/lib/msr-smp.c
@@ -169,12 +169,11 @@ static void __wrmsr_safe_on_cpu(void *info)
 int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
 {
 	struct msr_info_completion rv;
-	call_single_data_t csd = {
-		.func	= __rdmsr_safe_on_cpu,
-		.info	= &rv,
-	};
+	call_single_data_t csd;
 	int err;
 
+	INIT_CSD(&csd, __rdmsr_safe_on_cpu, &rv);
+
 	memset(&rv, 0, sizeof(rv));
 	init_completion(&rv.done);
 	rv.msr.msr_no = msr_no;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 55bcee5dc032..d35b3c0c876a 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -671,9 +671,7 @@ bool blk_mq_complete_request_remote(struct request *rq)
 		return false;
 
 	if (blk_mq_complete_need_ipi(rq)) {
-		rq->csd.func = __blk_mq_complete_request_remote;
-		rq->csd.info = rq;
-		rq->csd.flags = 0;
+		INIT_CSD(&rq->csd, __blk_mq_complete_request_remote, rq);
 		smp_call_function_single_async(rq->mq_ctx->cpu, &rq->csd);
 	} else {
 		if (rq->q->nr_hw_queues > 1)
diff --git a/drivers/cpuidle/coupled.c b/drivers/cpuidle/coupled.c
index 04003b90dc49..74068742cef3 100644
--- a/drivers/cpuidle/coupled.c
+++ b/drivers/cpuidle/coupled.c
@@ -674,8 +674,7 @@ have_coupled:
 	coupled->refcnt++;
 
 	csd = &per_cpu(cpuidle_coupled_poke_cb, dev->cpu);
-	csd->func = cpuidle_coupled_handle_poke;
-	csd->info = (void *)(unsigned long)dev->cpu;
+	INIT_CSD(csd, cpuidle_coupled_handle_poke, (void *)(unsigned long)dev->cpu);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c
index 9ef172976b35..37d064193f0f 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_core.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c
@@ -729,13 +729,8 @@ static void liquidio_napi_drv_callback(void *arg)
 	    droq->cpu_id == this_cpu) {
 		napi_schedule_irqoff(&droq->napi);
 	} else {
-		call_single_data_t *csd = &droq->csd;
-
-		csd->func = napi_schedule_wrapper;
-		csd->info = &droq->napi;
-		csd->flags = 0;
-
-		smp_call_function_single_async(droq->cpu_id, csd);
+		INIT_CSD(&droq->csd, napi_schedule_wrapper, &droq->napi);
+		smp_call_function_single_async(droq->cpu_id, &droq->csd);
 	}
 }
 
diff --git a/include/linux/smp.h b/include/linux/smp.h
index 9f13966d3d92..70c6f6284dcf 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -21,24 +21,23 @@ typedef bool (*smp_cond_func_t)(int cpu, void *info);
  * structure shares (partial) layout with struct irq_work
  */
 struct __call_single_data {
-	union {
-		struct __call_single_node node;
-		struct {
-			struct llist_node llist;
-			unsigned int flags;
-#ifdef CONFIG_64BIT
-			u16 src, dst;
-#endif
-		};
-	};
+	struct __call_single_node node;
 	smp_call_func_t func;
 	void *info;
 };
 
+#define CSD_INIT(_func, _info) \
+	(struct __call_single_data){ .func = (_func), .info = (_info), }
+
 /* Use __aligned() to avoid to use 2 cache lines for 1 csd */
 typedef struct __call_single_data call_single_data_t
 	__aligned(sizeof(struct __call_single_data));
 
+#define INIT_CSD(_csd, _func, _info)		\
+do {						\
+	*(_csd) = CSD_INIT((_func), (_info));	\
+} while (0)
+
 /*
  * Enqueue a llist_node on the call_single_queue; be very careful, read
  * flush_smp_call_function_queue() in detail.
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index 1e75a8923a8d..af6e8b4fb359 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -225,8 +225,6 @@ NOKPROBE_SYMBOL(kgdb_skipexception);
  * Default (weak) implementation for kgdb_roundup_cpus
  */
 
-static DEFINE_PER_CPU(call_single_data_t, kgdb_roundup_csd);
-
 void __weak kgdb_call_nmi_hook(void *ignored)
 {
 	/*
@@ -241,6 +239,9 @@ void __weak kgdb_call_nmi_hook(void *ignored)
 }
 NOKPROBE_SYMBOL(kgdb_call_nmi_hook);
 
+static DEFINE_PER_CPU(call_single_data_t, kgdb_roundup_csd) =
+	CSD_INIT(kgdb_call_nmi_hook, NULL);
+
 void __weak kgdb_roundup_cpus(void)
 {
 	call_single_data_t *csd;
@@ -267,7 +268,6 @@ void __weak kgdb_roundup_cpus(void)
 			continue;
 		kgdb_info[cpu].rounding_up = true;
 
-		csd->func = kgdb_call_nmi_hook;
 		ret = smp_call_function_single_async(cpu, csd);
 		if (ret)
 			kgdb_info[cpu].rounding_up = false;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c962922784d1..b943b459b77a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -320,14 +320,6 @@ void update_rq_clock(struct rq *rq)
 	update_rq_clock_task(rq, delta);
 }
 
-static inline void
-rq_csd_init(struct rq *rq, call_single_data_t *csd, smp_call_func_t func)
-{
-	csd->flags = 0;
-	csd->func = func;
-	csd->info = rq;
-}
-
 #ifdef CONFIG_SCHED_HRTICK
 /*
  * Use HR-timers to deliver accurate preemption points.
@@ -428,7 +420,7 @@ void hrtick_start(struct rq *rq, u64 delay)
 static void hrtick_rq_init(struct rq *rq)
 {
 #ifdef CONFIG_SMP
-	rq_csd_init(rq, &rq->hrtick_csd, __hrtick_start);
+	INIT_CSD(&rq->hrtick_csd, __hrtick_start, rq);
 #endif
 	hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
 	rq->hrtick_timer.function = hrtick;
@@ -7774,7 +7766,7 @@ void __init sched_init(void)
 		rq->last_blocked_load_update_tick = jiffies;
 		atomic_set(&rq->nohz_flags, 0);
 
-		rq_csd_init(rq, &rq->nohz_csd, nohz_csd_func);
+		INIT_CSD(&rq->nohz_csd, nohz_csd_func, rq);
 #endif
 #ifdef CONFIG_HOTPLUG_CPU
 		rcuwait_init(&rq->hotplug_wait);
diff --git a/kernel/smp.c b/kernel/smp.c
index 4d17501433be..faf1a3ace6a9 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -27,7 +27,7 @@
 #include "smpboot.h"
 #include "sched/smp.h"
 
-#define CSD_TYPE(_csd)	((_csd)->flags & CSD_FLAG_TYPE_MASK)
+#define CSD_TYPE(_csd)	((_csd)->node.u_flags & CSD_FLAG_TYPE_MASK)
 
 struct call_function_data {
 	call_single_data_t	__percpu *csd;
@@ -146,7 +146,7 @@ static __always_inline bool csd_lock_wait_toolong(call_single_data_t *csd, u64 t
 	bool firsttime;
 	u64 ts2, ts_delta;
 	call_single_data_t *cpu_cur_csd;
-	unsigned int flags = READ_ONCE(csd->flags);
+	unsigned int flags = READ_ONCE(csd->node.u_flags);
 
 	if (!(flags & CSD_FLAG_LOCK)) {
 		if (!unlikely(*bug_id))
@@ -224,14 +224,14 @@ static void csd_lock_record(call_single_data_t *csd)
 
 static __always_inline void csd_lock_wait(call_single_data_t *csd)
 {
-	smp_cond_load_acquire(&csd->flags, !(VAL & CSD_FLAG_LOCK));
+	smp_cond_load_acquire(&csd->node.u_flags, !(VAL & CSD_FLAG_LOCK));
 }
 #endif
 
 static __always_inline void csd_lock(call_single_data_t *csd)
 {
 	csd_lock_wait(csd);
-	csd->flags |= CSD_FLAG_LOCK;
+	csd->node.u_flags |= CSD_FLAG_LOCK;
 
 	/*
 	 * prevent CPU from reordering the above assignment
@@ -243,12 +243,12 @@ static __always_inline void csd_lock(call_single_data_t *csd)
 
 static __always_inline void csd_unlock(call_single_data_t *csd)
 {
-	WARN_ON(!(csd->flags & CSD_FLAG_LOCK));
+	WARN_ON(!(csd->node.u_flags & CSD_FLAG_LOCK));
 
 	/*
 	 * ensure we're all done before releasing data:
 	 */
-	smp_store_release(&csd->flags, 0);
+	smp_store_release(&csd->node.u_flags, 0);
 }
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(call_single_data_t, csd_data);
@@ -300,7 +300,7 @@ static int generic_exec_single(int cpu, call_single_data_t *csd)
 		return -ENXIO;
 	}
 
-	__smp_call_single_queue(cpu, &csd->llist);
+	__smp_call_single_queue(cpu, &csd->node.llist);
 
 	return 0;
 }
@@ -353,7 +353,7 @@ static void flush_smp_call_function_queue(bool warn_cpu_offline)
 		 * We don't have to use the _safe() variant here
 		 * because we are not invoking the IPI handlers yet.
 		 */
-		llist_for_each_entry(csd, entry, llist) {
+		llist_for_each_entry(csd, entry, node.llist) {
 			switch (CSD_TYPE(csd)) {
 			case CSD_TYPE_ASYNC:
 			case CSD_TYPE_SYNC:
@@ -378,16 +378,16 @@ static void flush_smp_call_function_queue(bool warn_cpu_offline)
 	 * First; run all SYNC callbacks, people are waiting for us.
 	 */
 	prev = NULL;
-	llist_for_each_entry_safe(csd, csd_next, entry, llist) {
+	llist_for_each_entry_safe(csd, csd_next, entry, node.llist) {
 		/* Do we wait until *after* callback? */
 		if (CSD_TYPE(csd) == CSD_TYPE_SYNC) {
 			smp_call_func_t func = csd->func;
 			void *info = csd->info;
 
 			if (prev) {
-				prev->next = &csd_next->llist;
+				prev->next = &csd_next->node.llist;
 			} else {
-				entry = &csd_next->llist;
+				entry = &csd_next->node.llist;
 			}
 
 			csd_lock_record(csd);
@@ -395,7 +395,7 @@ static void flush_smp_call_function_queue(bool warn_cpu_offline)
 			csd_unlock(csd);
 			csd_lock_record(NULL);
 		} else {
-			prev = &csd->llist;
+			prev = &csd->node.llist;
 		}
 	}
 
@@ -406,14 +406,14 @@ static void flush_smp_call_function_queue(bool warn_cpu_offline)
 	 * Second; run all !SYNC callbacks.
 	 */
 	prev = NULL;
-	llist_for_each_entry_safe(csd, csd_next, entry, llist) {
+	llist_for_each_entry_safe(csd, csd_next, entry, node.llist) {
 		int type = CSD_TYPE(csd);
 
 		if (type != CSD_TYPE_TTWU) {
 			if (prev) {
-				prev->next = &csd_next->llist;
+				prev->next = &csd_next->node.llist;
 			} else {
-				entry = &csd_next->llist;
+				entry = &csd_next->node.llist;
 			}
 
 			if (type == CSD_TYPE_ASYNC) {
@@ -429,7 +429,7 @@ static void flush_smp_call_function_queue(bool warn_cpu_offline)
 			}
 
 		} else {
-			prev = &csd->llist;
+			prev = &csd->node.llist;
 		}
 	}
 
@@ -465,7 +465,7 @@ int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
 {
 	call_single_data_t *csd;
 	call_single_data_t csd_stack = {
-		.flags = CSD_FLAG_LOCK | CSD_TYPE_SYNC,
+		.node = { .u_flags = CSD_FLAG_LOCK | CSD_TYPE_SYNC, },
 	};
 	int this_cpu;
 	int err;
@@ -502,8 +502,8 @@ int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
 	csd->func = func;
 	csd->info = info;
 #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG
-	csd->src = smp_processor_id();
-	csd->dst = cpu;
+	csd->node.src = smp_processor_id();
+	csd->node.dst = cpu;
 #endif
 
 	err = generic_exec_single(cpu, csd);
@@ -544,12 +544,12 @@ int smp_call_function_single_async(int cpu, call_single_data_t *csd)
 
 	preempt_disable();
 
-	if (csd->flags & CSD_FLAG_LOCK) {
+	if (csd->node.u_flags & CSD_FLAG_LOCK) {
 		err = -EBUSY;
 		goto out;
 	}
 
-	csd->flags = CSD_FLAG_LOCK;
+	csd->node.u_flags = CSD_FLAG_LOCK;
 	smp_wmb();
 
 	err = generic_exec_single(cpu, csd);
@@ -667,14 +667,14 @@ static void smp_call_function_many_cond(const struct cpumask *mask,
 
 		csd_lock(csd);
 		if (wait)
-			csd->flags |= CSD_TYPE_SYNC;
+			csd->node.u_flags |= CSD_TYPE_SYNC;
 		csd->func = func;
 		csd->info = info;
 #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG
-		csd->src = smp_processor_id();
-		csd->dst = cpu;
+		csd->node.src = smp_processor_id();
+		csd->node.dst = cpu;
 #endif
-		if (llist_add(&csd->llist, &per_cpu(call_single_queue, cpu)))
+		if (llist_add(&csd->node.llist, &per_cpu(call_single_queue, cpu)))
 			__cpumask_set_cpu(cpu, cfd->cpumask_ipi);
 	}
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 82dc6b48e45f..57352605f82c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -11165,8 +11165,7 @@ static int __init net_dev_init(void)
 		INIT_LIST_HEAD(&sd->poll_list);
 		sd->output_queue_tailp = &sd->output_queue;
 #ifdef CONFIG_RPS
-		sd->csd.func = rps_trigger_softirq;
-		sd->csd.info = sd;
+		INIT_CSD(&sd->csd, rps_trigger_softirq, sd);
 		sd->cpu = i;
 #endif
 
-- 
cgit v1.2.3


From 2914b0ba61a9d253535e51af16c7122a8148995d Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 18 Jun 2020 22:28:37 +0200
Subject: irq_work: Optimize irq_work_single()

Trade one atomic op for a full memory barrier.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
---
 include/linux/irqflags.h |  8 ++++----
 kernel/irq_work.c        | 29 +++++++++++++++++------------
 2 files changed, 21 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h
index fef2d43a7a1d..8de0e1373de7 100644
--- a/include/linux/irqflags.h
+++ b/include/linux/irqflags.h
@@ -107,14 +107,14 @@ do {						\
 		  current->irq_config = 0;			\
 	  } while (0)
 
-# define lockdep_irq_work_enter(__work)					\
+# define lockdep_irq_work_enter(_flags)					\
 	  do {								\
-		  if (!(atomic_read(&__work->node.a_flags) & IRQ_WORK_HARD_IRQ))\
+		  if (!((_flags) & IRQ_WORK_HARD_IRQ))			\
 			current->irq_config = 1;			\
 	  } while (0)
-# define lockdep_irq_work_exit(__work)					\
+# define lockdep_irq_work_exit(_flags)					\
 	  do {								\
-		  if (!(atomic_read(&__work->node.a_flags) & IRQ_WORK_HARD_IRQ))\
+		  if (!((_flags) & IRQ_WORK_HARD_IRQ))			\
 			current->irq_config = 0;			\
 	  } while (0)
 
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index fbff25adb574..e8da1e71583a 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -34,7 +34,7 @@ static bool irq_work_claim(struct irq_work *work)
 	oflags = atomic_fetch_or(IRQ_WORK_CLAIMED | CSD_TYPE_IRQ_WORK, &work->node.a_flags);
 	/*
 	 * If the work is already pending, no need to raise the IPI.
-	 * The pairing atomic_fetch_andnot() in irq_work_run() makes sure
+	 * The pairing smp_mb() in irq_work_single() makes sure
 	 * everything we did before is visible.
 	 */
 	if (oflags & IRQ_WORK_PENDING)
@@ -136,22 +136,27 @@ void irq_work_single(void *arg)
 	int flags;
 
 	/*
-	 * Clear the PENDING bit, after this point the @work
-	 * can be re-used.
-	 * Make it immediately visible so that other CPUs trying
-	 * to claim that work don't rely on us to handle their data
-	 * while we are in the middle of the func.
+	 * Clear the PENDING bit, after this point the @work can be re-used.
+	 * The PENDING bit acts as a lock, and we own it, so we can clear it
+	 * without atomic ops.
 	 */
-	flags = atomic_fetch_andnot(IRQ_WORK_PENDING, &work->node.a_flags);
+	flags = atomic_read(&work->node.a_flags);
+	flags &= ~IRQ_WORK_PENDING;
+	atomic_set(&work->node.a_flags, flags);
+
+	/*
+	 * See irq_work_claim().
+	 */
+	smp_mb();
 
-	lockdep_irq_work_enter(work);
+	lockdep_irq_work_enter(flags);
 	work->func(work);
-	lockdep_irq_work_exit(work);
+	lockdep_irq_work_exit(flags);
+
 	/*
-	 * Clear the BUSY bit and return to the free state if
-	 * no-one else claimed it meanwhile.
+	 * Clear the BUSY bit, if set, and return to the free state if no-one
+	 * else claimed it meanwhile.
 	 */
-	flags &= ~IRQ_WORK_PENDING;
 	(void)atomic_cmpxchg(&work->node.a_flags, flags, flags & ~IRQ_WORK_BUSY);
 }
 
-- 
cgit v1.2.3


From 6bef038011a023db41f1b33f0776224729d52344 Mon Sep 17 00:00:00 2001
From: Mathieu Poirier <mathieu.poirier@linaro.org>
Date: Fri, 20 Nov 2020 14:42:38 -0700
Subject: rpmsg: Introduce __rpmsg{16|32|64} types

Introduce __rpmsg{16|32|64} types along with byte order conversion
functions based on an rpmsg_device operation as a foundation to
make RPMSG modular and transport agnostic.

Tested-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Suggested-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Reviewed-by: Arnaud Pouliquen <arnaud.pouliquen@st.com>
Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Link: https://lore.kernel.org/r/20201120214245.172963-2-mathieu.poirier@linaro.org
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 include/linux/rpmsg.h            | 51 ++++++++++++++++++++++++++++++
 include/linux/rpmsg/byteorder.h  | 67 ++++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/rpmsg_types.h | 11 +++++++
 3 files changed, 129 insertions(+)
 create mode 100644 include/linux/rpmsg/byteorder.h
 create mode 100644 include/uapi/linux/rpmsg_types.h

(limited to 'include/linux')

diff --git a/include/linux/rpmsg.h b/include/linux/rpmsg.h
index 9fe156d1c018..faf2daff6238 100644
--- a/include/linux/rpmsg.h
+++ b/include/linux/rpmsg.h
@@ -17,6 +17,7 @@
 #include <linux/kref.h>
 #include <linux/mutex.h>
 #include <linux/poll.h>
+#include <linux/rpmsg/byteorder.h>
 
 #define RPMSG_ADDR_ANY		0xFFFFFFFF
 
@@ -46,6 +47,7 @@ struct rpmsg_channel_info {
  * @dst: destination address
  * @ept: the rpmsg endpoint of this channel
  * @announce: if set, rpmsg will announce the creation/removal of this channel
+ * @little_endian: True if transport is using little endian byte representation
  */
 struct rpmsg_device {
 	struct device dev;
@@ -55,6 +57,7 @@ struct rpmsg_device {
 	u32 dst;
 	struct rpmsg_endpoint *ept;
 	bool announce;
+	bool little_endian;
 
 	const struct rpmsg_device_ops *ops;
 };
@@ -111,6 +114,54 @@ struct rpmsg_driver {
 	int (*callback)(struct rpmsg_device *, void *, int, void *, u32);
 };
 
+static inline u16 rpmsg16_to_cpu(struct rpmsg_device *rpdev, __rpmsg16 val)
+{
+	if (!rpdev)
+		return __rpmsg16_to_cpu(rpmsg_is_little_endian(), val);
+	else
+		return __rpmsg16_to_cpu(rpdev->little_endian, val);
+}
+
+static inline __rpmsg16 cpu_to_rpmsg16(struct rpmsg_device *rpdev, u16 val)
+{
+	if (!rpdev)
+		return __cpu_to_rpmsg16(rpmsg_is_little_endian(), val);
+	else
+		return __cpu_to_rpmsg16(rpdev->little_endian, val);
+}
+
+static inline u32 rpmsg32_to_cpu(struct rpmsg_device *rpdev, __rpmsg32 val)
+{
+	if (!rpdev)
+		return __rpmsg32_to_cpu(rpmsg_is_little_endian(), val);
+	else
+		return __rpmsg32_to_cpu(rpdev->little_endian, val);
+}
+
+static inline __rpmsg32 cpu_to_rpmsg32(struct rpmsg_device *rpdev, u32 val)
+{
+	if (!rpdev)
+		return __cpu_to_rpmsg32(rpmsg_is_little_endian(), val);
+	else
+		return __cpu_to_rpmsg32(rpdev->little_endian, val);
+}
+
+static inline u64 rpmsg64_to_cpu(struct rpmsg_device *rpdev, __rpmsg64 val)
+{
+	if (!rpdev)
+		return __rpmsg64_to_cpu(rpmsg_is_little_endian(), val);
+	else
+		return __rpmsg64_to_cpu(rpdev->little_endian, val);
+}
+
+static inline __rpmsg64 cpu_to_rpmsg64(struct rpmsg_device *rpdev, u64 val)
+{
+	if (!rpdev)
+		return __cpu_to_rpmsg64(rpmsg_is_little_endian(), val);
+	else
+		return __cpu_to_rpmsg64(rpdev->little_endian, val);
+}
+
 #if IS_ENABLED(CONFIG_RPMSG)
 
 int register_rpmsg_device(struct rpmsg_device *dev);
diff --git a/include/linux/rpmsg/byteorder.h b/include/linux/rpmsg/byteorder.h
new file mode 100644
index 000000000000..c0f565dbad6d
--- /dev/null
+++ b/include/linux/rpmsg/byteorder.h
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Follows implementation found in linux/virtio_byteorder.h
+ */
+#ifndef _LINUX_RPMSG_BYTEORDER_H
+#define _LINUX_RPMSG_BYTEORDER_H
+#include <linux/types.h>
+#include <uapi/linux/rpmsg_types.h>
+
+static inline bool rpmsg_is_little_endian(void)
+{
+#ifdef __LITTLE_ENDIAN
+	return true;
+#else
+	return false;
+#endif
+}
+
+static inline u16 __rpmsg16_to_cpu(bool little_endian, __rpmsg16 val)
+{
+	if (little_endian)
+		return le16_to_cpu((__force __le16)val);
+	else
+		return be16_to_cpu((__force __be16)val);
+}
+
+static inline __rpmsg16 __cpu_to_rpmsg16(bool little_endian, u16 val)
+{
+	if (little_endian)
+		return (__force __rpmsg16)cpu_to_le16(val);
+	else
+		return (__force __rpmsg16)cpu_to_be16(val);
+}
+
+static inline u32 __rpmsg32_to_cpu(bool little_endian, __rpmsg32 val)
+{
+	if (little_endian)
+		return le32_to_cpu((__force __le32)val);
+	else
+		return be32_to_cpu((__force __be32)val);
+}
+
+static inline __rpmsg32 __cpu_to_rpmsg32(bool little_endian, u32 val)
+{
+	if (little_endian)
+		return (__force __rpmsg32)cpu_to_le32(val);
+	else
+		return (__force __rpmsg32)cpu_to_be32(val);
+}
+
+static inline u64 __rpmsg64_to_cpu(bool little_endian, __rpmsg64 val)
+{
+	if (little_endian)
+		return le64_to_cpu((__force __le64)val);
+	else
+		return be64_to_cpu((__force __be64)val);
+}
+
+static inline __rpmsg64 __cpu_to_rpmsg64(bool little_endian, u64 val)
+{
+	if (little_endian)
+		return (__force __rpmsg64)cpu_to_le64(val);
+	else
+		return (__force __rpmsg64)cpu_to_be64(val);
+}
+
+#endif /* _LINUX_RPMSG_BYTEORDER_H */
diff --git a/include/uapi/linux/rpmsg_types.h b/include/uapi/linux/rpmsg_types.h
new file mode 100644
index 000000000000..36e3b9404391
--- /dev/null
+++ b/include/uapi/linux/rpmsg_types.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_RPMSG_TYPES_H
+#define _UAPI_LINUX_RPMSG_TYPES_H
+
+#include <linux/types.h>
+
+typedef __u16 __bitwise __rpmsg16;
+typedef __u32 __bitwise __rpmsg32;
+typedef __u64 __bitwise __rpmsg64;
+
+#endif /* _UAPI_LINUX_RPMSG_TYPES_H */
-- 
cgit v1.2.3


From c435a04189de372ba9ae72076b18185a884108d6 Mon Sep 17 00:00:00 2001
From: Mathieu Poirier <mathieu.poirier@linaro.org>
Date: Fri, 20 Nov 2020 14:42:40 -0700
Subject: rpmsg: Move structure rpmsg_ns_msg to header file

Move structure rpmsg_ns_msg to its own header file so that
it can be used by other entities.

Tested-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Reviewed-by: Arnaud Pouliquen <arnaud.pouliquen@st.com>
Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Link: https://lore.kernel.org/r/20201120214245.172963-4-mathieu.poirier@linaro.org
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 drivers/rpmsg/virtio_rpmsg_bus.c | 32 +-----------------------------
 include/linux/rpmsg/ns.h         | 42 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 43 insertions(+), 31 deletions(-)
 create mode 100644 include/linux/rpmsg/ns.h

(limited to 'include/linux')

diff --git a/drivers/rpmsg/virtio_rpmsg_bus.c b/drivers/rpmsg/virtio_rpmsg_bus.c
index 5259fbbc8e68..20d0cf909bea 100644
--- a/drivers/rpmsg/virtio_rpmsg_bus.c
+++ b/drivers/rpmsg/virtio_rpmsg_bus.c
@@ -20,6 +20,7 @@
 #include <linux/of_device.h>
 #include <linux/rpmsg.h>
 #include <linux/rpmsg/byteorder.h>
+#include <linux/rpmsg/ns.h>
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
@@ -93,34 +94,6 @@ struct rpmsg_hdr {
 	u8 data[];
 } __packed;
 
-/**
- * struct rpmsg_ns_msg - dynamic name service announcement message
- * @name: name of remote service that is published
- * @addr: address of remote service that is published
- * @flags: indicates whether service is created or destroyed
- *
- * This message is sent across to publish a new service, or announce
- * about its removal. When we receive these messages, an appropriate
- * rpmsg channel (i.e device) is created/destroyed. In turn, the ->probe()
- * or ->remove() handler of the appropriate rpmsg driver will be invoked
- * (if/as-soon-as one is registered).
- */
-struct rpmsg_ns_msg {
-	char name[RPMSG_NAME_SIZE];
-	__rpmsg32 addr;
-	__rpmsg32 flags;
-} __packed;
-
-/**
- * enum rpmsg_ns_flags - dynamic name service announcement flags
- *
- * @RPMSG_NS_CREATE: a new remote service was just created
- * @RPMSG_NS_DESTROY: a known remote service was just destroyed
- */
-enum rpmsg_ns_flags {
-	RPMSG_NS_CREATE		= 0,
-	RPMSG_NS_DESTROY	= 1,
-};
 
 /**
  * struct virtio_rpmsg_channel - rpmsg channel descriptor
@@ -167,9 +140,6 @@ struct virtio_rpmsg_channel {
  */
 #define RPMSG_RESERVED_ADDRESSES	(1024)
 
-/* Address 53 is reserved for advertising remote services */
-#define RPMSG_NS_ADDR			(53)
-
 static void virtio_rpmsg_destroy_ept(struct rpmsg_endpoint *ept);
 static int virtio_rpmsg_send(struct rpmsg_endpoint *ept, void *data, int len);
 static int virtio_rpmsg_sendto(struct rpmsg_endpoint *ept, void *data, int len,
diff --git a/include/linux/rpmsg/ns.h b/include/linux/rpmsg/ns.h
new file mode 100644
index 000000000000..73ecc91dc26f
--- /dev/null
+++ b/include/linux/rpmsg/ns.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _LINUX_RPMSG_NS_H
+#define _LINUX_RPMSG_NS_H
+
+#include <linux/mod_devicetable.h>
+#include <linux/rpmsg/byteorder.h>
+#include <linux/types.h>
+
+/**
+ * struct rpmsg_ns_msg - dynamic name service announcement message
+ * @name: name of remote service that is published
+ * @addr: address of remote service that is published
+ * @flags: indicates whether service is created or destroyed
+ *
+ * This message is sent across to publish a new service, or announce
+ * about its removal. When we receive these messages, an appropriate
+ * rpmsg channel (i.e device) is created/destroyed. In turn, the ->probe()
+ * or ->remove() handler of the appropriate rpmsg driver will be invoked
+ * (if/as-soon-as one is registered).
+ */
+struct rpmsg_ns_msg {
+	char name[RPMSG_NAME_SIZE];
+	__rpmsg32 addr;
+	__rpmsg32 flags;
+} __packed;
+
+/**
+ * enum rpmsg_ns_flags - dynamic name service announcement flags
+ *
+ * @RPMSG_NS_CREATE: a new remote service was just created
+ * @RPMSG_NS_DESTROY: a known remote service was just destroyed
+ */
+enum rpmsg_ns_flags {
+	RPMSG_NS_CREATE		= 0,
+	RPMSG_NS_DESTROY	= 1,
+};
+
+/* Address 53 is reserved for advertising remote services */
+#define RPMSG_NS_ADDR			(53)
+
+#endif
-- 
cgit v1.2.3


From 55488110acc1560b4599e3d509b13f2731a6fee1 Mon Sep 17 00:00:00 2001
From: Mathieu Poirier <mathieu.poirier@linaro.org>
Date: Fri, 20 Nov 2020 14:42:44 -0700
Subject: rpmsg: Make rpmsg_{register|unregister}_device() public

Make function rpmsg_register_device() and rpmsg_unregister_device()
functions public so that they can be used by other clients.  While
doing so get rid of two obsolete function, i.e register_rpmsg_device()
and unregister_rpmsg_device(), to prevent confusion.

Tested-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Reviewed-by: Arnaud Pouliquen <arnaud.pouliquen@st.com>
Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Link: https://lore.kernel.org/r/20201120214245.172963-8-mathieu.poirier@linaro.org
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 drivers/rpmsg/rpmsg_internal.h |  4 ----
 include/linux/rpmsg.h          | 12 ++++++++----
 2 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/rpmsg/rpmsg_internal.h b/drivers/rpmsg/rpmsg_internal.h
index f1de73e0f2d6..a76c344253bf 100644
--- a/drivers/rpmsg/rpmsg_internal.h
+++ b/drivers/rpmsg/rpmsg_internal.h
@@ -74,10 +74,6 @@ struct rpmsg_endpoint_ops {
 			     poll_table *wait);
 };
 
-int rpmsg_register_device(struct rpmsg_device *rpdev);
-int rpmsg_unregister_device(struct device *parent,
-			    struct rpmsg_channel_info *chinfo);
-
 struct device *rpmsg_find_device(struct device *parent,
 				 struct rpmsg_channel_info *chinfo);
 
diff --git a/include/linux/rpmsg.h b/include/linux/rpmsg.h
index faf2daff6238..a5db828b2420 100644
--- a/include/linux/rpmsg.h
+++ b/include/linux/rpmsg.h
@@ -164,8 +164,9 @@ static inline __rpmsg64 cpu_to_rpmsg64(struct rpmsg_device *rpdev, u64 val)
 
 #if IS_ENABLED(CONFIG_RPMSG)
 
-int register_rpmsg_device(struct rpmsg_device *dev);
-void unregister_rpmsg_device(struct rpmsg_device *dev);
+int rpmsg_register_device(struct rpmsg_device *rpdev);
+int rpmsg_unregister_device(struct device *parent,
+			    struct rpmsg_channel_info *chinfo);
 int __register_rpmsg_driver(struct rpmsg_driver *drv, struct module *owner);
 void unregister_rpmsg_driver(struct rpmsg_driver *drv);
 void rpmsg_destroy_ept(struct rpmsg_endpoint *);
@@ -188,15 +189,18 @@ __poll_t rpmsg_poll(struct rpmsg_endpoint *ept, struct file *filp,
 
 #else
 
-static inline int register_rpmsg_device(struct rpmsg_device *dev)
+static inline int rpmsg_register_device(struct rpmsg_device *rpdev)
 {
 	return -ENXIO;
 }
 
-static inline void unregister_rpmsg_device(struct rpmsg_device *dev)
+static inline int rpmsg_unregister_device(struct device *parent,
+					  struct rpmsg_channel_info *chinfo)
 {
 	/* This shouldn't be possible */
 	WARN_ON(1);
+
+	return -ENXIO;
 }
 
 static inline int __register_rpmsg_driver(struct rpmsg_driver *drv,
-- 
cgit v1.2.3


From 950a7388f02bf775515d13dc508cb9d749bd6d91 Mon Sep 17 00:00:00 2001
From: Arnaud Pouliquen <arnaud.pouliquen@st.com>
Date: Fri, 20 Nov 2020 14:42:45 -0700
Subject: rpmsg: Turn name service into a stand alone driver

Make the RPMSG name service announcement a stand alone driver so that it
can be reused by other subsystems.  It is also the first step in making the
functionatlity transport independent, i.e that is not tied to virtIO.

Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Tested-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Co-developed-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Co-developed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Signed-off-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Signed-off-by: Arnaud Pouliquen <arnaud.pouliquen@st.com>
Link: https://lore.kernel.org/r/20201120214245.172963-9-mathieu.poirier@linaro.org
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 drivers/rpmsg/Kconfig            |   9 +++
 drivers/rpmsg/Makefile           |   1 +
 drivers/rpmsg/rpmsg_ns.c         | 126 +++++++++++++++++++++++++++++++++++++++
 drivers/rpmsg/virtio_rpmsg_bus.c |  87 +++++++--------------------
 include/linux/rpmsg/ns.h         |   3 +
 5 files changed, 159 insertions(+), 67 deletions(-)
 create mode 100644 drivers/rpmsg/rpmsg_ns.c

(limited to 'include/linux')

diff --git a/drivers/rpmsg/Kconfig b/drivers/rpmsg/Kconfig
index f96716893c2a..0b4407abdf13 100644
--- a/drivers/rpmsg/Kconfig
+++ b/drivers/rpmsg/Kconfig
@@ -15,6 +15,14 @@ config RPMSG_CHAR
 	  in /dev. They make it possible for user-space programs to send and
 	  receive rpmsg packets.
 
+config RPMSG_NS
+	tristate "RPMSG name service announcement"
+	depends on RPMSG
+	help
+	  Say Y here to enable the support of the name service announcement
+	  channel that probes the associated RPMsg device on remote endpoint
+	  service announcement.
+
 config RPMSG_MTK_SCP
 	tristate "MediaTek SCP"
 	depends on MTK_SCP
@@ -62,6 +70,7 @@ config RPMSG_VIRTIO
 	tristate "Virtio RPMSG bus driver"
 	depends on HAS_DMA
 	select RPMSG
+	select RPMSG_NS
 	select VIRTIO
 
 endmenu
diff --git a/drivers/rpmsg/Makefile b/drivers/rpmsg/Makefile
index ffe932ef6050..8d452656f0ee 100644
--- a/drivers/rpmsg/Makefile
+++ b/drivers/rpmsg/Makefile
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_RPMSG)		+= rpmsg_core.o
 obj-$(CONFIG_RPMSG_CHAR)	+= rpmsg_char.o
+obj-$(CONFIG_RPMSG_NS)		+= rpmsg_ns.o
 obj-$(CONFIG_RPMSG_MTK_SCP)	+= mtk_rpmsg.o
 qcom_glink-objs			:= qcom_glink_native.o qcom_glink_ssr.o
 obj-$(CONFIG_RPMSG_QCOM_GLINK) += qcom_glink.o
diff --git a/drivers/rpmsg/rpmsg_ns.c b/drivers/rpmsg/rpmsg_ns.c
new file mode 100644
index 000000000000..762ff1ae279f
--- /dev/null
+++ b/drivers/rpmsg/rpmsg_ns.c
@@ -0,0 +1,126 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) STMicroelectronics 2020 - All Rights Reserved
+ */
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/rpmsg.h>
+#include <linux/rpmsg/ns.h>
+#include <linux/slab.h>
+
+#include "rpmsg_internal.h"
+
+/**
+ * rpmsg_ns_register_device() - register name service device based on rpdev
+ * @rpdev: prepared rpdev to be used for creating endpoints
+ *
+ * This function wraps rpmsg_register_device() preparing the rpdev for use as
+ * basis for the rpmsg name service device.
+ */
+int rpmsg_ns_register_device(struct rpmsg_device *rpdev)
+{
+	strcpy(rpdev->id.name, "rpmsg_ns");
+	rpdev->driver_override = "rpmsg_ns";
+	rpdev->src = RPMSG_NS_ADDR;
+	rpdev->dst = RPMSG_NS_ADDR;
+
+	return rpmsg_register_device(rpdev);
+}
+EXPORT_SYMBOL(rpmsg_ns_register_device);
+
+/* invoked when a name service announcement arrives */
+static int rpmsg_ns_cb(struct rpmsg_device *rpdev, void *data, int len,
+		       void *priv, u32 src)
+{
+	struct rpmsg_ns_msg *msg = data;
+	struct rpmsg_device *newch;
+	struct rpmsg_channel_info chinfo;
+	struct device *dev = rpdev->dev.parent;
+	int ret;
+
+#if defined(CONFIG_DYNAMIC_DEBUG)
+	dynamic_hex_dump("NS announcement: ", DUMP_PREFIX_NONE, 16, 1,
+			 data, len, true);
+#endif
+
+	if (len != sizeof(*msg)) {
+		dev_err(dev, "malformed ns msg (%d)\n", len);
+		return -EINVAL;
+	}
+
+	/* don't trust the remote processor for null terminating the name */
+	msg->name[RPMSG_NAME_SIZE - 1] = '\0';
+
+	strncpy(chinfo.name, msg->name, sizeof(chinfo.name));
+	chinfo.src = RPMSG_ADDR_ANY;
+	chinfo.dst = rpmsg32_to_cpu(rpdev, msg->addr);
+
+	dev_info(dev, "%sing channel %s addr 0x%x\n",
+		 rpmsg32_to_cpu(rpdev, msg->flags) & RPMSG_NS_DESTROY ?
+		 "destroy" : "creat", msg->name, chinfo.dst);
+
+	if (rpmsg32_to_cpu(rpdev, msg->flags) & RPMSG_NS_DESTROY) {
+		ret = rpmsg_release_channel(rpdev, &chinfo);
+		if (ret)
+			dev_err(dev, "rpmsg_destroy_channel failed: %d\n", ret);
+	} else {
+		newch = rpmsg_create_channel(rpdev, &chinfo);
+		if (!newch)
+			dev_err(dev, "rpmsg_create_channel failed\n");
+	}
+
+	return 0;
+}
+
+static int rpmsg_ns_probe(struct rpmsg_device *rpdev)
+{
+	struct rpmsg_endpoint *ns_ept;
+	struct rpmsg_channel_info ns_chinfo = {
+		.src = RPMSG_NS_ADDR,
+		.dst = RPMSG_NS_ADDR,
+		.name = "name_service",
+	};
+
+	/*
+	 * Create the NS announcement service endpoint associated to the RPMsg
+	 * device. The endpoint will be automatically destroyed when the RPMsg
+	 * device will be deleted.
+	 */
+	ns_ept = rpmsg_create_ept(rpdev, rpmsg_ns_cb, NULL, ns_chinfo);
+	if (!ns_ept) {
+		dev_err(&rpdev->dev, "failed to create the ns ept\n");
+		return -ENOMEM;
+	}
+	rpdev->ept = ns_ept;
+
+	return 0;
+}
+
+static struct rpmsg_driver rpmsg_ns_driver = {
+	.drv.name = KBUILD_MODNAME,
+	.probe = rpmsg_ns_probe,
+};
+
+static int rpmsg_ns_init(void)
+{
+	int ret;
+
+	ret = register_rpmsg_driver(&rpmsg_ns_driver);
+	if (ret < 0)
+		pr_err("%s: Failed to register rpmsg driver\n", __func__);
+
+	return ret;
+}
+postcore_initcall(rpmsg_ns_init);
+
+static void rpmsg_ns_exit(void)
+{
+	unregister_rpmsg_driver(&rpmsg_ns_driver);
+}
+module_exit(rpmsg_ns_exit);
+
+MODULE_DESCRIPTION("Name service announcement rpmsg driver");
+MODULE_AUTHOR("Arnaud Pouliquen <arnaud.pouliquen@st.com>");
+MODULE_ALIAS("rpmsg:" KBUILD_MODNAME);
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/rpmsg/virtio_rpmsg_bus.c b/drivers/rpmsg/virtio_rpmsg_bus.c
index 6ec299f7f790..e87d4cf926eb 100644
--- a/drivers/rpmsg/virtio_rpmsg_bus.c
+++ b/drivers/rpmsg/virtio_rpmsg_bus.c
@@ -49,7 +49,6 @@
  * @endpoints_lock: lock of the endpoints set
  * @sendq:	wait queue of sending contexts waiting for a tx buffers
  * @sleepers:	number of senders that are waiting for a tx buffer
- * @ns_ept:	the bus's name service endpoint
  *
  * This structure stores the rpmsg state of a given virtio remote processor
  * device (there might be several virtio proc devices for each physical
@@ -68,7 +67,6 @@ struct virtproc_info {
 	struct mutex endpoints_lock;
 	wait_queue_head_t sendq;
 	atomic_t sleepers;
-	struct rpmsg_endpoint *ns_ept;
 };
 
 /* The feature bitmap for virtio rpmsg */
@@ -815,69 +813,14 @@ static void rpmsg_xmit_done(struct virtqueue *svq)
 	wake_up_interruptible(&vrp->sendq);
 }
 
-/* invoked when a name service announcement arrives */
-static int rpmsg_ns_cb(struct rpmsg_device *rpdev, void *data, int len,
-		       void *priv, u32 src)
-{
-	struct rpmsg_ns_msg *msg = data;
-	struct rpmsg_device *newch;
-	struct rpmsg_channel_info chinfo;
-	struct virtproc_info *vrp = priv;
-	struct device *dev = &vrp->vdev->dev;
-	bool little_endian = virtio_is_little_endian(vrp->vdev);
-	int ret;
-
-#if defined(CONFIG_DYNAMIC_DEBUG)
-	dynamic_hex_dump("NS announcement: ", DUMP_PREFIX_NONE, 16, 1,
-			 data, len, true);
-#endif
-
-	if (len != sizeof(*msg)) {
-		dev_err(dev, "malformed ns msg (%d)\n", len);
-		return -EINVAL;
-	}
-
-	/*
-	 * the name service ept does _not_ belong to a real rpmsg channel,
-	 * and is handled by the rpmsg bus itself.
-	 * for sanity reasons, make sure a valid rpdev has _not_ sneaked
-	 * in somehow.
-	 */
-	if (rpdev) {
-		dev_err(dev, "anomaly: ns ept has an rpdev handle\n");
-		return -EINVAL;
-	}
-
-	/* don't trust the remote processor for null terminating the name */
-	msg->name[RPMSG_NAME_SIZE - 1] = '\0';
-
-	strncpy(chinfo.name, msg->name, sizeof(chinfo.name));
-	chinfo.src = RPMSG_ADDR_ANY;
-	chinfo.dst = __rpmsg32_to_cpu(little_endian, msg->addr);
-
-	dev_info(dev, "%sing channel %s addr 0x%x\n",
-		 __rpmsg32_to_cpu(little_endian, msg->flags) & RPMSG_NS_DESTROY ?
-		 "destroy" : "creat", msg->name, chinfo.dst);
-
-	if (__rpmsg32_to_cpu(little_endian, msg->flags) & RPMSG_NS_DESTROY) {
-		ret = rpmsg_unregister_device(&vrp->vdev->dev, &chinfo);
-		if (ret)
-			dev_err(dev, "rpmsg_destroy_channel failed: %d\n", ret);
-	} else {
-		newch = __rpmsg_create_channel(vrp, &chinfo);
-		if (!newch)
-			dev_err(dev, "rpmsg_create_channel failed\n");
-	}
-
-	return 0;
-}
-
 static int rpmsg_probe(struct virtio_device *vdev)
 {
 	vq_callback_t *vq_cbs[] = { rpmsg_recv_done, rpmsg_xmit_done };
 	static const char * const names[] = { "input", "output" };
 	struct virtqueue *vqs[2];
 	struct virtproc_info *vrp;
+	struct virtio_rpmsg_channel *vch;
+	struct rpmsg_device *rpdev_ns;
 	void *bufs_va;
 	int err = 0, i;
 	size_t total_buf_space;
@@ -953,14 +896,26 @@ static int rpmsg_probe(struct virtio_device *vdev)
 
 	/* if supported by the remote processor, enable the name service */
 	if (virtio_has_feature(vdev, VIRTIO_RPMSG_F_NS)) {
-		/* a dedicated endpoint handles the name service msgs */
-		vrp->ns_ept = __rpmsg_create_ept(vrp, NULL, rpmsg_ns_cb,
-						vrp, RPMSG_NS_ADDR);
-		if (!vrp->ns_ept) {
-			dev_err(&vdev->dev, "failed to create the ns ept\n");
+		vch = kzalloc(sizeof(*vch), GFP_KERNEL);
+		if (!vch) {
 			err = -ENOMEM;
 			goto free_coherent;
 		}
+
+		/* Link the channel to our vrp */
+		vch->vrp = vrp;
+
+		/* Assign public information to the rpmsg_device */
+		rpdev_ns = &vch->rpdev;
+		rpdev_ns->ops = &virtio_rpmsg_ops;
+		rpdev_ns->little_endian = virtio_is_little_endian(vrp->vdev);
+
+		rpdev_ns->dev.parent = &vrp->vdev->dev;
+		rpdev_ns->dev.release = virtio_rpmsg_release_device;
+
+		err = rpmsg_ns_register_device(rpdev_ns);
+		if (err)
+			goto free_coherent;
 	}
 
 	/*
@@ -985,6 +940,7 @@ static int rpmsg_probe(struct virtio_device *vdev)
 	return 0;
 
 free_coherent:
+	kfree(vch);
 	dma_free_coherent(vdev->dev.parent, total_buf_space,
 			  bufs_va, vrp->bufs_dma);
 vqs_del:
@@ -1013,9 +969,6 @@ static void rpmsg_remove(struct virtio_device *vdev)
 	if (ret)
 		dev_warn(&vdev->dev, "can't remove rpmsg device: %d\n", ret);
 
-	if (vrp->ns_ept)
-		__rpmsg_destroy_ept(vrp, vrp->ns_ept);
-
 	idr_destroy(&vrp->endpoints);
 
 	vdev->config->del_vqs(vrp->vdev);
diff --git a/include/linux/rpmsg/ns.h b/include/linux/rpmsg/ns.h
index 73ecc91dc26f..a7804edd6d58 100644
--- a/include/linux/rpmsg/ns.h
+++ b/include/linux/rpmsg/ns.h
@@ -4,6 +4,7 @@
 #define _LINUX_RPMSG_NS_H
 
 #include <linux/mod_devicetable.h>
+#include <linux/rpmsg.h>
 #include <linux/rpmsg/byteorder.h>
 #include <linux/types.h>
 
@@ -39,4 +40,6 @@ enum rpmsg_ns_flags {
 /* Address 53 is reserved for advertising remote services */
 #define RPMSG_NS_ADDR			(53)
 
+int rpmsg_ns_register_device(struct rpmsg_device *rpdev);
+
 #endif
-- 
cgit v1.2.3


From e7bbb7acabf47d74672e0e314bed4d452d2097b4 Mon Sep 17 00:00:00 2001
From: Vinod Koul <vkoul@kernel.org>
Date: Mon, 9 Nov 2020 14:24:49 +0530
Subject: dmaengine: add peripheral configuration

Some complex dmaengine controllers have capability to program the
peripheral device, so pass on the peripheral configuration as part of
dma_slave_config

Link: https://lore.kernel.org/r/20201109085450.24843-3-vkoul@kernel.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/dmaengine.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index dd357a747780..493a047ed0a2 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -418,6 +418,9 @@ enum dma_slave_buswidth {
  * @slave_id: Slave requester id. Only valid for slave channels. The dma
  * slave peripheral will have unique id as dma requester which need to be
  * pass as slave config.
+ * @peripheral_config: peripheral configuration for programming peripheral
+ * for dmaengine transfer
+ * @peripheral_size: peripheral configuration buffer size
  *
  * This struct is passed in as configuration data to a DMA engine
  * in order to set up a certain channel for DMA transport at runtime.
@@ -443,6 +446,8 @@ struct dma_slave_config {
 	u32 dst_port_window_size;
 	bool device_fc;
 	unsigned int slave_id;
+	void *peripheral_config;
+	size_t peripheral_size;
 };
 
 /**
-- 
cgit v1.2.3


From 5d0c3533a19f48e5e7e73806a3e4b29cd4364130 Mon Sep 17 00:00:00 2001
From: Vinod Koul <vkoul@kernel.org>
Date: Mon, 9 Nov 2020 14:24:50 +0530
Subject: dmaengine: qcom: Add GPI dma driver

This controller provides DMAengine capabilities for a variety of peripheral
buses such as I2C, UART, and SPI. By using GPI dmaengine driver, bus
drivers can use a standardize interface that is protocol independent to
transfer data between memory and peripheral.

Link: https://lore.kernel.org/r/20201109085450.24843-4-vkoul@kernel.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/qcom/Kconfig         |   12 +
 drivers/dma/qcom/Makefile        |    1 +
 drivers/dma/qcom/gpi.c           | 2303 ++++++++++++++++++++++++++++++++++++++
 include/linux/dma/qcom-gpi-dma.h |   83 ++
 4 files changed, 2399 insertions(+)
 create mode 100644 drivers/dma/qcom/gpi.c
 create mode 100644 include/linux/dma/qcom-gpi-dma.h

(limited to 'include/linux')

diff --git a/drivers/dma/qcom/Kconfig b/drivers/dma/qcom/Kconfig
index 0389d60d2604..365f94eb3b08 100644
--- a/drivers/dma/qcom/Kconfig
+++ b/drivers/dma/qcom/Kconfig
@@ -19,6 +19,18 @@ config QCOM_BAM_DMA
 	  Enable support for the QCOM BAM DMA controller.  This controller
 	  provides DMA capabilities for a variety of on-chip devices.
 
+config QCOM_GPI_DMA
+        tristate "Qualcomm Technologies GPI DMA support"
+        depends on ARCH_QCOM
+        select DMA_ENGINE
+        select DMA_VIRTUAL_CHANNELS
+        help
+          Enable support for the QCOM GPI DMA controller. This controller
+          provides DMA capabilities for a variety of peripheral buses such
+          as I2C, UART, and SPI. By using GPI dmaengine driver, bus drivers
+          can use a standardize interface that is protocol independent to
+          transfer data between DDR and peripheral.
+
 config QCOM_HIDMA_MGMT
 	tristate "Qualcomm Technologies HIDMA Management support"
 	select DMA_ENGINE
diff --git a/drivers/dma/qcom/Makefile b/drivers/dma/qcom/Makefile
index 346e643fbb6d..50f1e7014693 100644
--- a/drivers/dma/qcom/Makefile
+++ b/drivers/dma/qcom/Makefile
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_QCOM_ADM) += qcom_adm.o
 obj-$(CONFIG_QCOM_BAM_DMA) += bam_dma.o
+obj-$(CONFIG_QCOM_GPI_DMA) += gpi.o
 obj-$(CONFIG_QCOM_HIDMA_MGMT) += hdma_mgmt.o
 hdma_mgmt-objs	 := hidma_mgmt.o hidma_mgmt_sys.o
 obj-$(CONFIG_QCOM_HIDMA) +=  hdma.o
diff --git a/drivers/dma/qcom/gpi.c b/drivers/dma/qcom/gpi.c
new file mode 100644
index 000000000000..d2334f535de2
--- /dev/null
+++ b/drivers/dma/qcom/gpi.c
@@ -0,0 +1,2303 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2017-2020, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2020, Linaro Limited
+ */
+
+#include <dt-bindings/dma/qcom-gpi.h>
+#include <linux/bitfield.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmaengine.h>
+#include <linux/module.h>
+#include <linux/of_dma.h>
+#include <linux/platform_device.h>
+#include <linux/dma/qcom-gpi-dma.h>
+#include <linux/scatterlist.h>
+#include <linux/slab.h>
+#include "../dmaengine.h"
+#include "../virt-dma.h"
+
+#define TRE_TYPE_DMA		0x10
+#define TRE_TYPE_GO		0x20
+#define TRE_TYPE_CONFIG0	0x22
+
+/* TRE flags */
+#define TRE_FLAGS_CHAIN		BIT(0)
+#define TRE_FLAGS_IEOB		BIT(8)
+#define TRE_FLAGS_IEOT		BIT(9)
+#define TRE_FLAGS_BEI		BIT(10)
+#define TRE_FLAGS_LINK		BIT(11)
+#define TRE_FLAGS_TYPE		GENMASK(23, 16)
+
+/* SPI CONFIG0 WD0 */
+#define TRE_SPI_C0_WORD_SZ	GENMASK(4, 0)
+#define TRE_SPI_C0_LOOPBACK	BIT(8)
+#define TRE_SPI_C0_CS		BIT(11)
+#define TRE_SPI_C0_CPHA		BIT(12)
+#define TRE_SPI_C0_CPOL		BIT(13)
+#define TRE_SPI_C0_TX_PACK	BIT(24)
+#define TRE_SPI_C0_RX_PACK	BIT(25)
+
+/* CONFIG0 WD2 */
+#define TRE_C0_CLK_DIV		GENMASK(11, 0)
+#define TRE_C0_CLK_SRC		GENMASK(19, 16)
+
+/* SPI GO WD0 */
+#define TRE_SPI_GO_CMD		GENMASK(4, 0)
+#define TRE_SPI_GO_CS		GENMASK(10, 8)
+#define TRE_SPI_GO_FRAG		BIT(26)
+
+/* GO WD2 */
+#define TRE_RX_LEN		GENMASK(23, 0)
+
+/* I2C Config0 WD0 */
+#define TRE_I2C_C0_TLOW		GENMASK(7, 0)
+#define TRE_I2C_C0_THIGH	GENMASK(15, 8)
+#define TRE_I2C_C0_TCYL		GENMASK(23, 16)
+#define TRE_I2C_C0_TX_PACK	BIT(24)
+#define TRE_I2C_C0_RX_PACK      BIT(25)
+
+/* I2C GO WD0 */
+#define TRE_I2C_GO_CMD          GENMASK(4, 0)
+#define TRE_I2C_GO_ADDR		GENMASK(14, 8)
+#define TRE_I2C_GO_STRETCH	BIT(26)
+
+/* DMA TRE */
+#define TRE_DMA_LEN		GENMASK(23, 0)
+
+/* Register offsets from gpi-top */
+#define GPII_n_CH_k_CNTXT_0_OFFS(n, k)	(0x20000 + (0x4000 * (n)) + (0x80 * (k)))
+#define GPII_n_CH_k_CNTXT_0_EL_SIZE	GENMASK(31, 24)
+#define GPII_n_CH_k_CNTXT_0_CHSTATE	GENMASK(23, 20)
+#define GPII_n_CH_k_CNTXT_0_ERIDX	GENMASK(18, 14)
+#define GPII_n_CH_k_CNTXT_0_DIR		BIT(3)
+#define GPII_n_CH_k_CNTXT_0_PROTO	GENMASK(2, 0)
+
+#define GPII_n_CH_k_CNTXT_0(el_size, erindex, dir, chtype_proto)  \
+	(FIELD_PREP(GPII_n_CH_k_CNTXT_0_EL_SIZE, el_size)	| \
+	 FIELD_PREP(GPII_n_CH_k_CNTXT_0_ERIDX, erindex)		| \
+	 FIELD_PREP(GPII_n_CH_k_CNTXT_0_DIR, dir)		| \
+	 FIELD_PREP(GPII_n_CH_k_CNTXT_0_PROTO, chtype_proto))
+
+#define GPI_CHTYPE_DIR_IN	(0)
+#define GPI_CHTYPE_DIR_OUT	(1)
+
+#define GPI_CHTYPE_PROTO_GPI	(0x2)
+
+#define GPII_n_CH_k_DOORBELL_0_OFFS(n, k)	(0x22000 + (0x4000 * (n)) + (0x8 * (k)))
+#define GPII_n_CH_CMD_OFFS(n)			(0x23008 + (0x4000 * (n)))
+#define GPII_n_CH_CMD_OPCODE			GENMASK(31, 24)
+#define GPII_n_CH_CMD_CHID			GENMASK(7, 0)
+#define GPII_n_CH_CMD(opcode, chid)				 \
+		     (FIELD_PREP(GPII_n_CH_CMD_OPCODE, opcode) | \
+		      FIELD_PREP(GPII_n_CH_CMD_CHID, chid))
+
+#define GPII_n_CH_CMD_ALLOCATE		(0)
+#define GPII_n_CH_CMD_START		(1)
+#define GPII_n_CH_CMD_STOP		(2)
+#define GPII_n_CH_CMD_RESET		(9)
+#define GPII_n_CH_CMD_DE_ALLOC		(10)
+#define GPII_n_CH_CMD_UART_SW_STALE	(32)
+#define GPII_n_CH_CMD_UART_RFR_READY	(33)
+#define GPII_n_CH_CMD_UART_RFR_NOT_READY (34)
+
+/* EV Context Array */
+#define GPII_n_EV_CH_k_CNTXT_0_OFFS(n, k) (0x21000 + (0x4000 * (n)) + (0x80 * (k)))
+#define GPII_n_EV_k_CNTXT_0_EL_SIZE	GENMASK(31, 24)
+#define GPII_n_EV_k_CNTXT_0_CHSTATE	GENMASK(23, 20)
+#define GPII_n_EV_k_CNTXT_0_INTYPE	BIT(16)
+#define GPII_n_EV_k_CNTXT_0_CHTYPE	GENMASK(3, 0)
+
+#define GPII_n_EV_k_CNTXT_0(el_size, inttype, chtype)		\
+	(FIELD_PREP(GPII_n_EV_k_CNTXT_0_EL_SIZE, el_size) |	\
+	 FIELD_PREP(GPII_n_EV_k_CNTXT_0_INTYPE, inttype)  |	\
+	 FIELD_PREP(GPII_n_EV_k_CNTXT_0_CHTYPE, chtype))
+
+#define GPI_INTTYPE_IRQ		(1)
+#define GPI_CHTYPE_GPI_EV	(0x2)
+
+enum CNTXT_OFFS {
+	CNTXT_0_CONFIG = 0x0,
+	CNTXT_1_R_LENGTH = 0x4,
+	CNTXT_2_RING_BASE_LSB = 0x8,
+	CNTXT_3_RING_BASE_MSB = 0xC,
+	CNTXT_4_RING_RP_LSB = 0x10,
+	CNTXT_5_RING_RP_MSB = 0x14,
+	CNTXT_6_RING_WP_LSB = 0x18,
+	CNTXT_7_RING_WP_MSB = 0x1C,
+	CNTXT_8_RING_INT_MOD = 0x20,
+	CNTXT_9_RING_INTVEC = 0x24,
+	CNTXT_10_RING_MSI_LSB = 0x28,
+	CNTXT_11_RING_MSI_MSB = 0x2C,
+	CNTXT_12_RING_RP_UPDATE_LSB = 0x30,
+	CNTXT_13_RING_RP_UPDATE_MSB = 0x34,
+};
+
+#define GPII_n_EV_CH_k_DOORBELL_0_OFFS(n, k)	(0x22100 + (0x4000 * (n)) + (0x8 * (k)))
+#define GPII_n_EV_CH_CMD_OFFS(n)		(0x23010 + (0x4000 * (n)))
+#define GPII_n_EV_CMD_OPCODE			GENMASK(31, 24)
+#define GPII_n_EV_CMD_CHID			GENMASK(7, 0)
+#define GPII_n_EV_CMD(opcode, chid)				 \
+		     (FIELD_PREP(GPII_n_EV_CMD_OPCODE, opcode) | \
+		      FIELD_PREP(GPII_n_EV_CMD_CHID, chid))
+
+#define GPII_n_EV_CH_CMD_ALLOCATE		(0x00)
+#define GPII_n_EV_CH_CMD_RESET			(0x09)
+#define GPII_n_EV_CH_CMD_DE_ALLOC		(0x0A)
+
+#define GPII_n_CNTXT_TYPE_IRQ_OFFS(n)		(0x23080 + (0x4000 * (n)))
+
+/* mask type register */
+#define GPII_n_CNTXT_TYPE_IRQ_MSK_OFFS(n)	(0x23088 + (0x4000 * (n)))
+#define GPII_n_CNTXT_TYPE_IRQ_MSK_BMSK		GENMASK(6, 0)
+#define GPII_n_CNTXT_TYPE_IRQ_MSK_GENERAL	BIT(6)
+#define GPII_n_CNTXT_TYPE_IRQ_MSK_IEOB		BIT(3)
+#define GPII_n_CNTXT_TYPE_IRQ_MSK_GLOB		BIT(2)
+#define GPII_n_CNTXT_TYPE_IRQ_MSK_EV_CTRL	BIT(1)
+#define GPII_n_CNTXT_TYPE_IRQ_MSK_CH_CTRL	BIT(0)
+
+#define GPII_n_CNTXT_SRC_GPII_CH_IRQ_OFFS(n)	(0x23090 + (0x4000 * (n)))
+#define GPII_n_CNTXT_SRC_EV_CH_IRQ_OFFS(n)	(0x23094 + (0x4000 * (n)))
+
+/* Mask channel control interrupt register */
+#define GPII_n_CNTXT_SRC_CH_IRQ_MSK_OFFS(n)	(0x23098 + (0x4000 * (n)))
+#define GPII_n_CNTXT_SRC_CH_IRQ_MSK_BMSK	GENMASK(1, 0)
+
+/* Mask event control interrupt register */
+#define GPII_n_CNTXT_SRC_EV_CH_IRQ_MSK_OFFS(n)	(0x2309C + (0x4000 * (n)))
+#define GPII_n_CNTXT_SRC_EV_CH_IRQ_MSK_BMSK	BIT(0)
+
+#define GPII_n_CNTXT_SRC_CH_IRQ_CLR_OFFS(n)	(0x230A0 + (0x4000 * (n)))
+#define GPII_n_CNTXT_SRC_EV_CH_IRQ_CLR_OFFS(n)	(0x230A4 + (0x4000 * (n)))
+
+/* Mask event interrupt register */
+#define GPII_n_CNTXT_SRC_IEOB_IRQ_MSK_OFFS(n)	(0x230B8 + (0x4000 * (n)))
+#define GPII_n_CNTXT_SRC_IEOB_IRQ_MSK_BMSK	BIT(0)
+
+#define GPII_n_CNTXT_SRC_IEOB_IRQ_CLR_OFFS(n)	(0x230C0 + (0x4000 * (n)))
+#define GPII_n_CNTXT_GLOB_IRQ_STTS_OFFS(n)	(0x23100 + (0x4000 * (n)))
+#define GPI_GLOB_IRQ_ERROR_INT_MSK		BIT(0)
+
+/* GPII specific Global - Enable bit register */
+#define GPII_n_CNTXT_GLOB_IRQ_EN_OFFS(n)	(0x23108 + (0x4000 * (n)))
+#define GPII_n_CNTXT_GLOB_IRQ_CLR_OFFS(n)	(0x23110 + (0x4000 * (n)))
+#define GPII_n_CNTXT_GPII_IRQ_STTS_OFFS(n)	(0x23118 + (0x4000 * (n)))
+
+/* GPII general interrupt - Enable bit register */
+#define GPII_n_CNTXT_GPII_IRQ_EN_OFFS(n)	(0x23120 + (0x4000 * (n)))
+#define GPII_n_CNTXT_GPII_IRQ_EN_BMSK		GENMASK(3, 0)
+
+#define GPII_n_CNTXT_GPII_IRQ_CLR_OFFS(n)	(0x23128 + (0x4000 * (n)))
+
+/* GPII Interrupt Type register */
+#define GPII_n_CNTXT_INTSET_OFFS(n)		(0x23180 + (0x4000 * (n)))
+#define GPII_n_CNTXT_INTSET_BMSK		BIT(0)
+
+#define GPII_n_CNTXT_MSI_BASE_LSB_OFFS(n)	(0x23188 + (0x4000 * (n)))
+#define GPII_n_CNTXT_MSI_BASE_MSB_OFFS(n)	(0x2318C + (0x4000 * (n)))
+#define GPII_n_CNTXT_SCRATCH_0_OFFS(n)		(0x23400 + (0x4000 * (n)))
+#define GPII_n_CNTXT_SCRATCH_1_OFFS(n)		(0x23404 + (0x4000 * (n)))
+
+#define GPII_n_ERROR_LOG_OFFS(n)		(0x23200 + (0x4000 * (n)))
+
+/* QOS Registers */
+#define GPII_n_CH_k_QOS_OFFS(n, k)		(0x2005C + (0x4000 * (n)) + (0x80 * (k)))
+
+/* Scratch registers */
+#define GPII_n_CH_k_SCRATCH_0_OFFS(n, k)	(0x20060 + (0x4000 * (n)) + (0x80 * (k)))
+#define GPII_n_CH_k_SCRATCH_0_SEID		GENMASK(2, 0)
+#define GPII_n_CH_k_SCRATCH_0_PROTO		GENMASK(7, 4)
+#define GPII_n_CH_k_SCRATCH_0_PAIR		GENMASK(20, 16)
+#define GPII_n_CH_k_SCRATCH_0(pair, proto, seid)		\
+			     (FIELD_PREP(GPII_n_CH_k_SCRATCH_0_PAIR, pair)	| \
+			      FIELD_PREP(GPII_n_CH_k_SCRATCH_0_PROTO, proto)	| \
+			      FIELD_PREP(GPII_n_CH_k_SCRATCH_0_SEID, seid))
+#define GPII_n_CH_k_SCRATCH_1_OFFS(n, k)	(0x20064 + (0x4000 * (n)) + (0x80 * (k)))
+#define GPII_n_CH_k_SCRATCH_2_OFFS(n, k)	(0x20068 + (0x4000 * (n)) + (0x80 * (k)))
+#define GPII_n_CH_k_SCRATCH_3_OFFS(n, k)	(0x2006C + (0x4000 * (n)) + (0x80 * (k)))
+
+struct __packed gpi_tre {
+	u32 dword[4];
+};
+
+enum msm_gpi_tce_code {
+	MSM_GPI_TCE_SUCCESS = 1,
+	MSM_GPI_TCE_EOT = 2,
+	MSM_GPI_TCE_EOB = 4,
+	MSM_GPI_TCE_UNEXP_ERR = 16,
+};
+
+#define CMD_TIMEOUT_MS		(250)
+
+#define MAX_CHANNELS_PER_GPII	(2)
+#define GPI_TX_CHAN		(0)
+#define GPI_RX_CHAN		(1)
+#define STATE_IGNORE		(U32_MAX)
+#define EV_FACTOR		(2)
+#define REQ_OF_DMA_ARGS		(5) /* # of arguments required from client */
+#define CHAN_TRES		64
+
+struct __packed xfer_compl_event {
+	u64 ptr;
+	u32 length:24;
+	u8 code;
+	u16 status;
+	u8 type;
+	u8 chid;
+};
+
+struct __packed immediate_data_event {
+	u8 data_bytes[8];
+	u8 length:4;
+	u8 resvd:4;
+	u16 tre_index;
+	u8 code;
+	u16 status;
+	u8 type;
+	u8 chid;
+};
+
+struct __packed qup_notif_event {
+	u32 status;
+	u32 time;
+	u32 count:24;
+	u8 resvd;
+	u16 resvd1;
+	u8 type;
+	u8 chid;
+};
+
+struct __packed gpi_ere {
+	u32 dword[4];
+};
+
+enum GPI_EV_TYPE {
+	XFER_COMPLETE_EV_TYPE = 0x22,
+	IMMEDIATE_DATA_EV_TYPE = 0x30,
+	QUP_NOTIF_EV_TYPE = 0x31,
+	STALE_EV_TYPE = 0xFF,
+};
+
+union __packed gpi_event {
+	struct __packed xfer_compl_event xfer_compl_event;
+	struct __packed immediate_data_event immediate_data_event;
+	struct __packed qup_notif_event qup_notif_event;
+	struct __packed gpi_ere gpi_ere;
+};
+
+enum gpii_irq_settings {
+	DEFAULT_IRQ_SETTINGS,
+	MASK_IEOB_SETTINGS,
+};
+
+enum gpi_ev_state {
+	DEFAULT_EV_CH_STATE = 0,
+	EV_STATE_NOT_ALLOCATED = DEFAULT_EV_CH_STATE,
+	EV_STATE_ALLOCATED,
+	MAX_EV_STATES
+};
+
+static const char *const gpi_ev_state_str[MAX_EV_STATES] = {
+	[EV_STATE_NOT_ALLOCATED] = "NOT ALLOCATED",
+	[EV_STATE_ALLOCATED] = "ALLOCATED",
+};
+
+#define TO_GPI_EV_STATE_STR(_state) (((_state) >= MAX_EV_STATES) ? \
+				    "INVALID" : gpi_ev_state_str[(_state)])
+
+enum gpi_ch_state {
+	DEFAULT_CH_STATE = 0x0,
+	CH_STATE_NOT_ALLOCATED = DEFAULT_CH_STATE,
+	CH_STATE_ALLOCATED = 0x1,
+	CH_STATE_STARTED = 0x2,
+	CH_STATE_STOPPED = 0x3,
+	CH_STATE_STOP_IN_PROC = 0x4,
+	CH_STATE_ERROR = 0xf,
+	MAX_CH_STATES
+};
+
+enum gpi_cmd {
+	GPI_CH_CMD_BEGIN,
+	GPI_CH_CMD_ALLOCATE = GPI_CH_CMD_BEGIN,
+	GPI_CH_CMD_START,
+	GPI_CH_CMD_STOP,
+	GPI_CH_CMD_RESET,
+	GPI_CH_CMD_DE_ALLOC,
+	GPI_CH_CMD_UART_SW_STALE,
+	GPI_CH_CMD_UART_RFR_READY,
+	GPI_CH_CMD_UART_RFR_NOT_READY,
+	GPI_CH_CMD_END = GPI_CH_CMD_UART_RFR_NOT_READY,
+	GPI_EV_CMD_BEGIN,
+	GPI_EV_CMD_ALLOCATE = GPI_EV_CMD_BEGIN,
+	GPI_EV_CMD_RESET,
+	GPI_EV_CMD_DEALLOC,
+	GPI_EV_CMD_END = GPI_EV_CMD_DEALLOC,
+	GPI_MAX_CMD,
+};
+
+#define IS_CHAN_CMD(_cmd) ((_cmd) <= GPI_CH_CMD_END)
+
+static const char *const gpi_cmd_str[GPI_MAX_CMD] = {
+	[GPI_CH_CMD_ALLOCATE] = "CH ALLOCATE",
+	[GPI_CH_CMD_START] = "CH START",
+	[GPI_CH_CMD_STOP] = "CH STOP",
+	[GPI_CH_CMD_RESET] = "CH_RESET",
+	[GPI_CH_CMD_DE_ALLOC] = "DE ALLOC",
+	[GPI_CH_CMD_UART_SW_STALE] = "UART SW STALE",
+	[GPI_CH_CMD_UART_RFR_READY] = "UART RFR READY",
+	[GPI_CH_CMD_UART_RFR_NOT_READY] = "UART RFR NOT READY",
+	[GPI_EV_CMD_ALLOCATE] = "EV ALLOCATE",
+	[GPI_EV_CMD_RESET] = "EV RESET",
+	[GPI_EV_CMD_DEALLOC] = "EV DEALLOC",
+};
+
+#define TO_GPI_CMD_STR(_cmd) (((_cmd) >= GPI_MAX_CMD) ? "INVALID" : \
+				  gpi_cmd_str[(_cmd)])
+
+/*
+ * @DISABLE_STATE: no register access allowed
+ * @CONFIG_STATE:  client has configured the channel
+ * @PREP_HARDWARE: register access is allowed
+ *		   however, no processing EVENTS
+ * @ACTIVE_STATE: channels are fully operational
+ * @PREPARE_TERMINATE: graceful termination of channels
+ *		       register access is allowed
+ * @PAUSE_STATE: channels are active, but not processing any events
+ */
+enum gpi_pm_state {
+	DISABLE_STATE,
+	CONFIG_STATE,
+	PREPARE_HARDWARE,
+	ACTIVE_STATE,
+	PREPARE_TERMINATE,
+	PAUSE_STATE,
+	MAX_PM_STATE
+};
+
+#define REG_ACCESS_VALID(_pm_state) ((_pm_state) >= PREPARE_HARDWARE)
+
+static const char *const gpi_pm_state_str[MAX_PM_STATE] = {
+	[DISABLE_STATE] = "DISABLE",
+	[CONFIG_STATE] = "CONFIG",
+	[PREPARE_HARDWARE] = "PREPARE HARDWARE",
+	[ACTIVE_STATE] = "ACTIVE",
+	[PREPARE_TERMINATE] = "PREPARE TERMINATE",
+	[PAUSE_STATE] = "PAUSE",
+};
+
+#define TO_GPI_PM_STR(_state) (((_state) >= MAX_PM_STATE) ? \
+			      "INVALID" : gpi_pm_state_str[(_state)])
+
+static const struct {
+	enum gpi_cmd gpi_cmd;
+	u32 opcode;
+	u32 state;
+} gpi_cmd_info[GPI_MAX_CMD] = {
+	{
+		GPI_CH_CMD_ALLOCATE,
+		GPII_n_CH_CMD_ALLOCATE,
+		CH_STATE_ALLOCATED,
+	},
+	{
+		GPI_CH_CMD_START,
+		GPII_n_CH_CMD_START,
+		CH_STATE_STARTED,
+	},
+	{
+		GPI_CH_CMD_STOP,
+		GPII_n_CH_CMD_STOP,
+		CH_STATE_STOPPED,
+	},
+	{
+		GPI_CH_CMD_RESET,
+		GPII_n_CH_CMD_RESET,
+		CH_STATE_ALLOCATED,
+	},
+	{
+		GPI_CH_CMD_DE_ALLOC,
+		GPII_n_CH_CMD_DE_ALLOC,
+		CH_STATE_NOT_ALLOCATED,
+	},
+	{
+		GPI_CH_CMD_UART_SW_STALE,
+		GPII_n_CH_CMD_UART_SW_STALE,
+		STATE_IGNORE,
+	},
+	{
+		GPI_CH_CMD_UART_RFR_READY,
+		GPII_n_CH_CMD_UART_RFR_READY,
+		STATE_IGNORE,
+	},
+	{
+		GPI_CH_CMD_UART_RFR_NOT_READY,
+		GPII_n_CH_CMD_UART_RFR_NOT_READY,
+		STATE_IGNORE,
+	},
+	{
+		GPI_EV_CMD_ALLOCATE,
+		GPII_n_EV_CH_CMD_ALLOCATE,
+		EV_STATE_ALLOCATED,
+	},
+	{
+		GPI_EV_CMD_RESET,
+		GPII_n_EV_CH_CMD_RESET,
+		EV_STATE_ALLOCATED,
+	},
+	{
+		GPI_EV_CMD_DEALLOC,
+		GPII_n_EV_CH_CMD_DE_ALLOC,
+		EV_STATE_NOT_ALLOCATED,
+	},
+};
+
+struct gpi_ring {
+	void *pre_aligned;
+	size_t alloc_size;
+	phys_addr_t phys_addr;
+	dma_addr_t dma_handle;
+	void *base;
+	void *wp;
+	void *rp;
+	u32 len;
+	u32 el_size;
+	u32 elements;
+	bool configured;
+};
+
+struct gpi_dev {
+	struct dma_device dma_device;
+	struct device *dev;
+	struct resource *res;
+	void __iomem *regs;
+	void __iomem *ee_base; /*ee register base address*/
+	u32 max_gpii; /* maximum # of gpii instances available per gpi block */
+	u32 gpii_mask; /* gpii instances available for apps */
+	u32 ev_factor; /* ev ring length factor */
+	struct gpii *gpiis;
+};
+
+struct reg_info {
+	char *name;
+	u32 offset;
+	u32 val;
+};
+
+struct gchan {
+	struct virt_dma_chan vc;
+	u32 chid;
+	u32 seid;
+	u32 protocol;
+	struct gpii *gpii;
+	enum gpi_ch_state ch_state;
+	enum gpi_pm_state pm_state;
+	void __iomem *ch_cntxt_base_reg;
+	void __iomem *ch_cntxt_db_reg;
+	void __iomem *ch_cmd_reg;
+	u32 dir;
+	struct gpi_ring ch_ring;
+	void *config;
+};
+
+struct gpii {
+	u32 gpii_id;
+	struct gchan gchan[MAX_CHANNELS_PER_GPII];
+	struct gpi_dev *gpi_dev;
+	int irq;
+	void __iomem *regs; /* points to gpi top */
+	void __iomem *ev_cntxt_base_reg;
+	void __iomem *ev_cntxt_db_reg;
+	void __iomem *ev_ring_rp_lsb_reg;
+	void __iomem *ev_cmd_reg;
+	void __iomem *ieob_clr_reg;
+	struct mutex ctrl_lock;
+	enum gpi_ev_state ev_state;
+	bool configured_irq;
+	enum gpi_pm_state pm_state;
+	rwlock_t pm_lock;
+	struct gpi_ring ev_ring;
+	struct tasklet_struct ev_task; /* event processing tasklet */
+	struct completion cmd_completion;
+	enum gpi_cmd gpi_cmd;
+	u32 cntxt_type_irq_msk;
+	bool ieob_set;
+};
+
+#define MAX_TRE 3
+
+struct gpi_desc {
+	struct virt_dma_desc vd;
+	size_t len;
+	void *db; /* DB register to program */
+	struct gchan *gchan;
+	struct gpi_tre tre[MAX_TRE];
+	u32 num_tre;
+};
+
+static const u32 GPII_CHAN_DIR[MAX_CHANNELS_PER_GPII] = {
+	GPI_CHTYPE_DIR_OUT, GPI_CHTYPE_DIR_IN
+};
+
+static irqreturn_t gpi_handle_irq(int irq, void *data);
+static void gpi_ring_recycle_ev_element(struct gpi_ring *ring);
+static int gpi_ring_add_element(struct gpi_ring *ring, void **wp);
+static void gpi_process_events(struct gpii *gpii);
+
+static inline struct gchan *to_gchan(struct dma_chan *dma_chan)
+{
+	return container_of(dma_chan, struct gchan, vc.chan);
+}
+
+static inline struct gpi_desc *to_gpi_desc(struct virt_dma_desc *vd)
+{
+	return container_of(vd, struct gpi_desc, vd);
+}
+
+static inline phys_addr_t to_physical(const struct gpi_ring *const ring,
+				      void *addr)
+{
+	return ring->phys_addr + (addr - ring->base);
+}
+
+static inline void *to_virtual(const struct gpi_ring *const ring, phys_addr_t addr)
+{
+	return ring->base + (addr - ring->phys_addr);
+}
+
+static inline u32 gpi_read_reg(struct gpii *gpii, void __iomem *addr)
+{
+	return readl_relaxed(addr);
+}
+
+static inline void gpi_write_reg(struct gpii *gpii, void __iomem *addr, u32 val)
+{
+	writel_relaxed(val, addr);
+}
+
+/* gpi_write_reg_field - write to specific bit field */
+static inline void gpi_write_reg_field(struct gpii *gpii, void __iomem *addr,
+				       u32 mask, u32 shift, u32 val)
+{
+	u32 tmp = gpi_read_reg(gpii, addr);
+
+	tmp &= ~mask;
+	val = tmp | ((val << shift) & mask);
+	gpi_write_reg(gpii, addr, val);
+}
+
+static inline void
+gpi_update_reg(struct gpii *gpii, u32 offset, u32 mask, u32 val)
+{
+	void __iomem *addr = gpii->regs + offset;
+	u32 tmp = gpi_read_reg(gpii, addr);
+
+	tmp &= ~mask;
+	tmp |= u32_encode_bits(val, mask);
+
+	gpi_write_reg(gpii, addr, tmp);
+}
+
+static void gpi_disable_interrupts(struct gpii *gpii)
+{
+	gpi_update_reg(gpii, GPII_n_CNTXT_TYPE_IRQ_MSK_OFFS(gpii->gpii_id),
+		       GPII_n_CNTXT_TYPE_IRQ_MSK_BMSK, 0);
+	gpi_update_reg(gpii, GPII_n_CNTXT_SRC_IEOB_IRQ_MSK_OFFS(gpii->gpii_id),
+		       GPII_n_CNTXT_SRC_IEOB_IRQ_MSK_BMSK, 0);
+	gpi_update_reg(gpii, GPII_n_CNTXT_SRC_CH_IRQ_MSK_OFFS(gpii->gpii_id),
+		       GPII_n_CNTXT_SRC_CH_IRQ_MSK_BMSK, 0);
+	gpi_update_reg(gpii, GPII_n_CNTXT_SRC_EV_CH_IRQ_MSK_OFFS(gpii->gpii_id),
+		       GPII_n_CNTXT_SRC_EV_CH_IRQ_MSK_BMSK, 0);
+	gpi_update_reg(gpii, GPII_n_CNTXT_GLOB_IRQ_EN_OFFS(gpii->gpii_id),
+		       GPII_n_CNTXT_GPII_IRQ_EN_BMSK, 0);
+	gpi_update_reg(gpii, GPII_n_CNTXT_GPII_IRQ_EN_OFFS(gpii->gpii_id),
+		       GPII_n_CNTXT_GPII_IRQ_EN_BMSK, 0);
+	gpi_update_reg(gpii, GPII_n_CNTXT_INTSET_OFFS(gpii->gpii_id),
+		       GPII_n_CNTXT_INTSET_BMSK, 0);
+
+	gpii->cntxt_type_irq_msk = 0;
+	devm_free_irq(gpii->gpi_dev->dev, gpii->irq, gpii);
+	gpii->configured_irq = false;
+}
+
+/* configure and enable interrupts */
+static int gpi_config_interrupts(struct gpii *gpii, enum gpii_irq_settings settings, bool mask)
+{
+	const u32 enable = (GPII_n_CNTXT_TYPE_IRQ_MSK_GENERAL |
+			      GPII_n_CNTXT_TYPE_IRQ_MSK_IEOB |
+			      GPII_n_CNTXT_TYPE_IRQ_MSK_GLOB |
+			      GPII_n_CNTXT_TYPE_IRQ_MSK_EV_CTRL |
+			      GPII_n_CNTXT_TYPE_IRQ_MSK_CH_CTRL);
+	int ret;
+
+	if (!gpii->configured_irq) {
+		ret = devm_request_irq(gpii->gpi_dev->dev, gpii->irq,
+				       gpi_handle_irq, IRQF_TRIGGER_HIGH,
+				       "gpi-dma", gpii);
+		if (ret < 0) {
+			dev_err(gpii->gpi_dev->dev, "error request irq:%d ret:%d\n",
+				gpii->irq, ret);
+			return ret;
+		}
+	}
+
+	if (settings == MASK_IEOB_SETTINGS) {
+		/*
+		 * GPII only uses one EV ring per gpii so we can globally
+		 * enable/disable IEOB interrupt
+		 */
+		if (mask)
+			gpii->cntxt_type_irq_msk |= GPII_n_CNTXT_TYPE_IRQ_MSK_IEOB;
+		else
+			gpii->cntxt_type_irq_msk &= ~(GPII_n_CNTXT_TYPE_IRQ_MSK_IEOB);
+		gpi_update_reg(gpii, GPII_n_CNTXT_TYPE_IRQ_MSK_OFFS(gpii->gpii_id),
+			       GPII_n_CNTXT_TYPE_IRQ_MSK_BMSK, gpii->cntxt_type_irq_msk);
+	} else {
+		gpi_update_reg(gpii, GPII_n_CNTXT_TYPE_IRQ_MSK_OFFS(gpii->gpii_id),
+			       GPII_n_CNTXT_TYPE_IRQ_MSK_BMSK, enable);
+		gpi_update_reg(gpii, GPII_n_CNTXT_SRC_IEOB_IRQ_MSK_OFFS(gpii->gpii_id),
+			       GPII_n_CNTXT_SRC_IEOB_IRQ_MSK_BMSK,
+			       GPII_n_CNTXT_SRC_IEOB_IRQ_MSK_BMSK);
+		gpi_update_reg(gpii, GPII_n_CNTXT_SRC_CH_IRQ_MSK_OFFS(gpii->gpii_id),
+			       GPII_n_CNTXT_SRC_CH_IRQ_MSK_BMSK,
+			       GPII_n_CNTXT_SRC_CH_IRQ_MSK_BMSK);
+		gpi_update_reg(gpii, GPII_n_CNTXT_SRC_EV_CH_IRQ_MSK_OFFS(gpii->gpii_id),
+			       GPII_n_CNTXT_SRC_EV_CH_IRQ_MSK_BMSK,
+			       GPII_n_CNTXT_SRC_EV_CH_IRQ_MSK_BMSK);
+		gpi_update_reg(gpii, GPII_n_CNTXT_GLOB_IRQ_EN_OFFS(gpii->gpii_id),
+			       GPII_n_CNTXT_GPII_IRQ_EN_BMSK,
+			       GPII_n_CNTXT_GPII_IRQ_EN_BMSK);
+		gpi_update_reg(gpii, GPII_n_CNTXT_GPII_IRQ_EN_OFFS(gpii->gpii_id),
+			       GPII_n_CNTXT_GPII_IRQ_EN_BMSK, GPII_n_CNTXT_GPII_IRQ_EN_BMSK);
+		gpi_update_reg(gpii, GPII_n_CNTXT_MSI_BASE_LSB_OFFS(gpii->gpii_id), U32_MAX, 0);
+		gpi_update_reg(gpii, GPII_n_CNTXT_MSI_BASE_MSB_OFFS(gpii->gpii_id), U32_MAX, 0);
+		gpi_update_reg(gpii, GPII_n_CNTXT_SCRATCH_0_OFFS(gpii->gpii_id), U32_MAX, 0);
+		gpi_update_reg(gpii, GPII_n_CNTXT_SCRATCH_1_OFFS(gpii->gpii_id), U32_MAX, 0);
+		gpi_update_reg(gpii, GPII_n_CNTXT_INTSET_OFFS(gpii->gpii_id),
+			       GPII_n_CNTXT_INTSET_BMSK, 1);
+		gpi_update_reg(gpii, GPII_n_ERROR_LOG_OFFS(gpii->gpii_id), U32_MAX, 0);
+
+		gpii->cntxt_type_irq_msk = enable;
+	}
+
+	gpii->configured_irq = true;
+	return 0;
+}
+
+/* Sends gpii event or channel command */
+static int gpi_send_cmd(struct gpii *gpii, struct gchan *gchan,
+			enum gpi_cmd gpi_cmd)
+{
+	u32 chid = MAX_CHANNELS_PER_GPII;
+	unsigned long timeout;
+	void __iomem *cmd_reg;
+	u32 cmd;
+
+	if (gpi_cmd >= GPI_MAX_CMD)
+		return -EINVAL;
+	if (IS_CHAN_CMD(gpi_cmd))
+		chid = gchan->chid;
+
+	dev_dbg(gpii->gpi_dev->dev,
+		"sending cmd: %s:%u\n", TO_GPI_CMD_STR(gpi_cmd), chid);
+
+	/* send opcode and wait for completion */
+	reinit_completion(&gpii->cmd_completion);
+	gpii->gpi_cmd = gpi_cmd;
+
+	cmd_reg = IS_CHAN_CMD(gpi_cmd) ? gchan->ch_cmd_reg : gpii->ev_cmd_reg;
+	cmd = IS_CHAN_CMD(gpi_cmd) ? GPII_n_CH_CMD(gpi_cmd_info[gpi_cmd].opcode, chid) :
+				     GPII_n_EV_CMD(gpi_cmd_info[gpi_cmd].opcode, 0);
+	gpi_write_reg(gpii, cmd_reg, cmd);
+	timeout = wait_for_completion_timeout(&gpii->cmd_completion,
+					      msecs_to_jiffies(CMD_TIMEOUT_MS));
+	if (!timeout) {
+		dev_err(gpii->gpi_dev->dev, "cmd: %s completion timeout:%u\n",
+			TO_GPI_CMD_STR(gpi_cmd), chid);
+		return -EIO;
+	}
+
+	/* confirm new ch state is correct , if the cmd is a state change cmd */
+	if (gpi_cmd_info[gpi_cmd].state == STATE_IGNORE)
+		return 0;
+
+	if (IS_CHAN_CMD(gpi_cmd) && gchan->ch_state == gpi_cmd_info[gpi_cmd].state)
+		return 0;
+
+	if (!IS_CHAN_CMD(gpi_cmd) && gpii->ev_state == gpi_cmd_info[gpi_cmd].state)
+		return 0;
+
+	return -EIO;
+}
+
+/* program transfer ring DB register */
+static inline void gpi_write_ch_db(struct gchan *gchan,
+				   struct gpi_ring *ring, void *wp)
+{
+	struct gpii *gpii = gchan->gpii;
+	phys_addr_t p_wp;
+
+	p_wp = to_physical(ring, wp);
+	gpi_write_reg(gpii, gchan->ch_cntxt_db_reg, p_wp);
+}
+
+/* program event ring DB register */
+static inline void gpi_write_ev_db(struct gpii *gpii,
+				   struct gpi_ring *ring, void *wp)
+{
+	phys_addr_t p_wp;
+
+	p_wp = ring->phys_addr + (wp - ring->base);
+	gpi_write_reg(gpii, gpii->ev_cntxt_db_reg, p_wp);
+}
+
+/* process transfer completion interrupt */
+static void gpi_process_ieob(struct gpii *gpii)
+{
+	gpi_write_reg(gpii, gpii->ieob_clr_reg, BIT(0));
+
+	gpi_config_interrupts(gpii, MASK_IEOB_SETTINGS, 0);
+	tasklet_hi_schedule(&gpii->ev_task);
+}
+
+/* process channel control interrupt */
+static void gpi_process_ch_ctrl_irq(struct gpii *gpii)
+{
+	u32 gpii_id = gpii->gpii_id;
+	u32 offset = GPII_n_CNTXT_SRC_GPII_CH_IRQ_OFFS(gpii_id);
+	u32 ch_irq = gpi_read_reg(gpii, gpii->regs + offset);
+	struct gchan *gchan;
+	u32 chid, state;
+
+	/* clear the status */
+	offset = GPII_n_CNTXT_SRC_CH_IRQ_CLR_OFFS(gpii_id);
+	gpi_write_reg(gpii, gpii->regs + offset, (u32)ch_irq);
+
+	for (chid = 0; chid < MAX_CHANNELS_PER_GPII; chid++) {
+		if (!(BIT(chid) & ch_irq))
+			continue;
+
+		gchan = &gpii->gchan[chid];
+		state = gpi_read_reg(gpii, gchan->ch_cntxt_base_reg +
+				     CNTXT_0_CONFIG);
+		state = FIELD_GET(GPII_n_CH_k_CNTXT_0_CHSTATE, state);
+
+		/*
+		 * CH_CMD_DEALLOC cmd always successful. However cmd does
+		 * not change hardware status. So overwriting software state
+		 * to default state.
+		 */
+		if (gpii->gpi_cmd == GPI_CH_CMD_DE_ALLOC)
+			state = DEFAULT_CH_STATE;
+		gchan->ch_state = state;
+
+		/*
+		 * Triggering complete all if ch_state is not a stop in process.
+		 * Stop in process is a transition state and we will wait for
+		 * stop interrupt before notifying.
+		 */
+		if (gchan->ch_state != CH_STATE_STOP_IN_PROC)
+			complete_all(&gpii->cmd_completion);
+	}
+}
+
+/* processing gpi general error interrupts */
+static void gpi_process_gen_err_irq(struct gpii *gpii)
+{
+	u32 gpii_id = gpii->gpii_id;
+	u32 offset = GPII_n_CNTXT_GPII_IRQ_STTS_OFFS(gpii_id);
+	u32 irq_stts = gpi_read_reg(gpii, gpii->regs + offset);
+
+	/* clear the status */
+	dev_dbg(gpii->gpi_dev->dev, "irq_stts:0x%x\n", irq_stts);
+
+	/* Clear the register */
+	offset = GPII_n_CNTXT_GPII_IRQ_CLR_OFFS(gpii_id);
+	gpi_write_reg(gpii, gpii->regs + offset, irq_stts);
+}
+
+/* processing gpi level error interrupts */
+static void gpi_process_glob_err_irq(struct gpii *gpii)
+{
+	u32 gpii_id = gpii->gpii_id;
+	u32 offset = GPII_n_CNTXT_GLOB_IRQ_STTS_OFFS(gpii_id);
+	u32 irq_stts = gpi_read_reg(gpii, gpii->regs + offset);
+
+	offset = GPII_n_CNTXT_GLOB_IRQ_CLR_OFFS(gpii_id);
+	gpi_write_reg(gpii, gpii->regs + offset, irq_stts);
+
+	/* only error interrupt should be set */
+	if (irq_stts & ~GPI_GLOB_IRQ_ERROR_INT_MSK) {
+		dev_err(gpii->gpi_dev->dev, "invalid error status:0x%x\n", irq_stts);
+		return;
+	}
+
+	offset = GPII_n_ERROR_LOG_OFFS(gpii_id);
+	gpi_write_reg(gpii, gpii->regs + offset, 0);
+}
+
+/* gpii interrupt handler */
+static irqreturn_t gpi_handle_irq(int irq, void *data)
+{
+	struct gpii *gpii = data;
+	u32 gpii_id = gpii->gpii_id;
+	u32 type, offset;
+	unsigned long flags;
+
+	read_lock_irqsave(&gpii->pm_lock, flags);
+
+	/*
+	 * States are out of sync to receive interrupt
+	 * while software state is in DISABLE state, bailing out.
+	 */
+	if (!REG_ACCESS_VALID(gpii->pm_state)) {
+		dev_err(gpii->gpi_dev->dev, "receive interrupt while in %s state\n",
+			TO_GPI_PM_STR(gpii->pm_state));
+		goto exit_irq;
+	}
+
+	offset = GPII_n_CNTXT_TYPE_IRQ_OFFS(gpii->gpii_id);
+	type = gpi_read_reg(gpii, gpii->regs + offset);
+
+	do {
+		/* global gpii error */
+		if (type & GPII_n_CNTXT_TYPE_IRQ_MSK_GLOB) {
+			gpi_process_glob_err_irq(gpii);
+			type &= ~(GPII_n_CNTXT_TYPE_IRQ_MSK_GLOB);
+		}
+
+		/* transfer complete interrupt */
+		if (type & GPII_n_CNTXT_TYPE_IRQ_MSK_IEOB) {
+			gpi_process_ieob(gpii);
+			type &= ~GPII_n_CNTXT_TYPE_IRQ_MSK_IEOB;
+		}
+
+		/* event control irq */
+		if (type & GPII_n_CNTXT_TYPE_IRQ_MSK_EV_CTRL) {
+			u32 ev_state;
+			u32 ev_ch_irq;
+
+			dev_dbg(gpii->gpi_dev->dev,
+				"processing EV CTRL interrupt\n");
+			offset = GPII_n_CNTXT_SRC_EV_CH_IRQ_OFFS(gpii_id);
+			ev_ch_irq = gpi_read_reg(gpii, gpii->regs + offset);
+
+			offset = GPII_n_CNTXT_SRC_EV_CH_IRQ_CLR_OFFS
+				(gpii_id);
+			gpi_write_reg(gpii, gpii->regs + offset, ev_ch_irq);
+			ev_state = gpi_read_reg(gpii, gpii->ev_cntxt_base_reg +
+						CNTXT_0_CONFIG);
+			ev_state = FIELD_GET(GPII_n_EV_k_CNTXT_0_CHSTATE, ev_state);
+
+			/*
+			 * CMD EV_CMD_DEALLOC is always successful. However
+			 * cmd does not change hardware status. So overwriting
+			 * software state to default state.
+			 */
+			if (gpii->gpi_cmd == GPI_EV_CMD_DEALLOC)
+				ev_state = DEFAULT_EV_CH_STATE;
+
+			gpii->ev_state = ev_state;
+			dev_dbg(gpii->gpi_dev->dev, "setting EV state to %s\n",
+				TO_GPI_EV_STATE_STR(gpii->ev_state));
+			complete_all(&gpii->cmd_completion);
+			type &= ~(GPII_n_CNTXT_TYPE_IRQ_MSK_EV_CTRL);
+		}
+
+		/* channel control irq */
+		if (type & GPII_n_CNTXT_TYPE_IRQ_MSK_CH_CTRL) {
+			dev_dbg(gpii->gpi_dev->dev, "process CH CTRL interrupts\n");
+			gpi_process_ch_ctrl_irq(gpii);
+			type &= ~(GPII_n_CNTXT_TYPE_IRQ_MSK_CH_CTRL);
+		}
+
+		if (type) {
+			dev_err(gpii->gpi_dev->dev, "Unhandled interrupt status:0x%x\n", type);
+			gpi_process_gen_err_irq(gpii);
+			goto exit_irq;
+		}
+
+		offset = GPII_n_CNTXT_TYPE_IRQ_OFFS(gpii->gpii_id);
+		type = gpi_read_reg(gpii, gpii->regs + offset);
+	} while (type);
+
+exit_irq:
+	read_unlock_irqrestore(&gpii->pm_lock, flags);
+
+	return IRQ_HANDLED;
+}
+
+/* process DMA Immediate completion data events */
+static void gpi_process_imed_data_event(struct gchan *gchan,
+					struct immediate_data_event *imed_event)
+{
+	struct gpii *gpii = gchan->gpii;
+	struct gpi_ring *ch_ring = &gchan->ch_ring;
+	void *tre = ch_ring->base + (ch_ring->el_size * imed_event->tre_index);
+	struct dmaengine_result result;
+	struct gpi_desc *gpi_desc;
+	struct virt_dma_desc *vd;
+	unsigned long flags;
+	u32 chid;
+
+	/*
+	 * If channel not active don't process event
+	 */
+	if (gchan->pm_state != ACTIVE_STATE) {
+		dev_err(gpii->gpi_dev->dev, "skipping processing event because ch @ %s state\n",
+			TO_GPI_PM_STR(gchan->pm_state));
+		return;
+	}
+
+	spin_lock_irqsave(&gchan->vc.lock, flags);
+	vd = vchan_next_desc(&gchan->vc);
+	if (!vd) {
+		struct gpi_ere *gpi_ere;
+		struct gpi_tre *gpi_tre;
+
+		spin_unlock_irqrestore(&gchan->vc.lock, flags);
+		dev_dbg(gpii->gpi_dev->dev, "event without a pending descriptor!\n");
+		gpi_ere = (struct gpi_ere *)imed_event;
+		dev_dbg(gpii->gpi_dev->dev,
+			"Event: %08x %08x %08x %08x\n",
+			gpi_ere->dword[0], gpi_ere->dword[1],
+			gpi_ere->dword[2], gpi_ere->dword[3]);
+		gpi_tre = tre;
+		dev_dbg(gpii->gpi_dev->dev,
+			"Pending TRE: %08x %08x %08x %08x\n",
+			gpi_tre->dword[0], gpi_tre->dword[1],
+			gpi_tre->dword[2], gpi_tre->dword[3]);
+		return;
+	}
+	gpi_desc = to_gpi_desc(vd);
+	spin_unlock_irqrestore(&gchan->vc.lock, flags);
+
+	/*
+	 * RP pointed by Event is to last TRE processed,
+	 * we need to update ring rp to tre + 1
+	 */
+	tre += ch_ring->el_size;
+	if (tre >= (ch_ring->base + ch_ring->len))
+		tre = ch_ring->base;
+	ch_ring->rp = tre;
+
+	/* make sure rp updates are immediately visible to all cores */
+	smp_wmb();
+
+	chid = imed_event->chid;
+	if (imed_event->code == MSM_GPI_TCE_EOT && gpii->ieob_set) {
+		if (chid == GPI_RX_CHAN)
+			goto gpi_free_desc;
+		else
+			return;
+	}
+
+	if (imed_event->code == MSM_GPI_TCE_UNEXP_ERR)
+		result.result = DMA_TRANS_ABORTED;
+	else
+		result.result = DMA_TRANS_NOERROR;
+	result.residue = gpi_desc->len - imed_event->length;
+
+	dma_cookie_complete(&vd->tx);
+	dmaengine_desc_get_callback_invoke(&vd->tx, &result);
+
+gpi_free_desc:
+	spin_lock_irqsave(&gchan->vc.lock, flags);
+	list_del(&vd->node);
+	spin_unlock_irqrestore(&gchan->vc.lock, flags);
+	kfree(gpi_desc);
+	gpi_desc = NULL;
+}
+
+/* processing transfer completion events */
+static void gpi_process_xfer_compl_event(struct gchan *gchan,
+					 struct xfer_compl_event *compl_event)
+{
+	struct gpii *gpii = gchan->gpii;
+	struct gpi_ring *ch_ring = &gchan->ch_ring;
+	void *ev_rp = to_virtual(ch_ring, compl_event->ptr);
+	struct virt_dma_desc *vd;
+	struct gpi_desc *gpi_desc;
+	struct dmaengine_result result;
+	unsigned long flags;
+	u32 chid;
+
+	/* only process events on active channel */
+	if (unlikely(gchan->pm_state != ACTIVE_STATE)) {
+		dev_err(gpii->gpi_dev->dev, "skipping processing event because ch @ %s state\n",
+			TO_GPI_PM_STR(gchan->pm_state));
+		return;
+	}
+
+	spin_lock_irqsave(&gchan->vc.lock, flags);
+	vd = vchan_next_desc(&gchan->vc);
+	if (!vd) {
+		struct gpi_ere *gpi_ere;
+
+		spin_unlock_irqrestore(&gchan->vc.lock, flags);
+		dev_err(gpii->gpi_dev->dev, "Event without a pending descriptor!\n");
+		gpi_ere = (struct gpi_ere *)compl_event;
+		dev_err(gpii->gpi_dev->dev,
+			"Event: %08x %08x %08x %08x\n",
+			gpi_ere->dword[0], gpi_ere->dword[1],
+			gpi_ere->dword[2], gpi_ere->dword[3]);
+		return;
+	}
+
+	gpi_desc = to_gpi_desc(vd);
+	spin_unlock_irqrestore(&gchan->vc.lock, flags);
+
+	/*
+	 * RP pointed by Event is to last TRE processed,
+	 * we need to update ring rp to ev_rp + 1
+	 */
+	ev_rp += ch_ring->el_size;
+	if (ev_rp >= (ch_ring->base + ch_ring->len))
+		ev_rp = ch_ring->base;
+	ch_ring->rp = ev_rp;
+
+	/* update must be visible to other cores */
+	smp_wmb();
+
+	chid = compl_event->chid;
+	if (compl_event->code == MSM_GPI_TCE_EOT && gpii->ieob_set) {
+		if (chid == GPI_RX_CHAN)
+			goto gpi_free_desc;
+		else
+			return;
+	}
+
+	if (compl_event->code == MSM_GPI_TCE_UNEXP_ERR) {
+		dev_err(gpii->gpi_dev->dev, "Error in Transaction\n");
+		result.result = DMA_TRANS_ABORTED;
+	} else {
+		dev_dbg(gpii->gpi_dev->dev, "Transaction Success\n");
+		result.result = DMA_TRANS_NOERROR;
+	}
+	result.residue = gpi_desc->len - compl_event->length;
+	dev_dbg(gpii->gpi_dev->dev, "Residue %d\n", result.residue);
+
+	dma_cookie_complete(&vd->tx);
+	dmaengine_desc_get_callback_invoke(&vd->tx, &result);
+
+gpi_free_desc:
+	spin_lock_irqsave(&gchan->vc.lock, flags);
+	list_del(&vd->node);
+	spin_unlock_irqrestore(&gchan->vc.lock, flags);
+	kfree(gpi_desc);
+	gpi_desc = NULL;
+}
+
+/* process all events */
+static void gpi_process_events(struct gpii *gpii)
+{
+	struct gpi_ring *ev_ring = &gpii->ev_ring;
+	phys_addr_t cntxt_rp;
+	void *rp;
+	union gpi_event *gpi_event;
+	struct gchan *gchan;
+	u32 chid, type;
+
+	cntxt_rp = gpi_read_reg(gpii, gpii->ev_ring_rp_lsb_reg);
+	rp = to_virtual(ev_ring, cntxt_rp);
+
+	do {
+		while (rp != ev_ring->rp) {
+			gpi_event = ev_ring->rp;
+			chid = gpi_event->xfer_compl_event.chid;
+			type = gpi_event->xfer_compl_event.type;
+
+			dev_dbg(gpii->gpi_dev->dev,
+				"Event: CHID:%u, type:%x %08x %08x %08x %08x\n",
+				chid, type, gpi_event->gpi_ere.dword[0],
+				gpi_event->gpi_ere.dword[1], gpi_event->gpi_ere.dword[2],
+				gpi_event->gpi_ere.dword[3]);
+
+			switch (type) {
+			case XFER_COMPLETE_EV_TYPE:
+				gchan = &gpii->gchan[chid];
+				gpi_process_xfer_compl_event(gchan,
+							     &gpi_event->xfer_compl_event);
+				break;
+			case STALE_EV_TYPE:
+				dev_dbg(gpii->gpi_dev->dev, "stale event, not processing\n");
+				break;
+			case IMMEDIATE_DATA_EV_TYPE:
+				gchan = &gpii->gchan[chid];
+				gpi_process_imed_data_event(gchan,
+							    &gpi_event->immediate_data_event);
+				break;
+			case QUP_NOTIF_EV_TYPE:
+				dev_dbg(gpii->gpi_dev->dev, "QUP_NOTIF_EV_TYPE\n");
+				break;
+			default:
+				dev_dbg(gpii->gpi_dev->dev,
+					"not supported event type:0x%x\n", type);
+			}
+			gpi_ring_recycle_ev_element(ev_ring);
+		}
+		gpi_write_ev_db(gpii, ev_ring, ev_ring->wp);
+
+		/* clear pending IEOB events */
+		gpi_write_reg(gpii, gpii->ieob_clr_reg, BIT(0));
+
+		cntxt_rp = gpi_read_reg(gpii, gpii->ev_ring_rp_lsb_reg);
+		rp = to_virtual(ev_ring, cntxt_rp);
+
+	} while (rp != ev_ring->rp);
+}
+
+/* processing events using tasklet */
+static void gpi_ev_tasklet(unsigned long data)
+{
+	struct gpii *gpii = (struct gpii *)data;
+
+	read_lock_bh(&gpii->pm_lock);
+	if (!REG_ACCESS_VALID(gpii->pm_state)) {
+		read_unlock_bh(&gpii->pm_lock);
+		dev_err(gpii->gpi_dev->dev, "not processing any events, pm_state:%s\n",
+			TO_GPI_PM_STR(gpii->pm_state));
+		return;
+	}
+
+	/* process the events */
+	gpi_process_events(gpii);
+
+	/* enable IEOB, switching back to interrupts */
+	gpi_config_interrupts(gpii, MASK_IEOB_SETTINGS, 1);
+	read_unlock_bh(&gpii->pm_lock);
+}
+
+/* marks all pending events for the channel as stale */
+static void gpi_mark_stale_events(struct gchan *gchan)
+{
+	struct gpii *gpii = gchan->gpii;
+	struct gpi_ring *ev_ring = &gpii->ev_ring;
+	u32 cntxt_rp, local_rp;
+	void *ev_rp;
+
+	cntxt_rp = gpi_read_reg(gpii, gpii->ev_ring_rp_lsb_reg);
+
+	ev_rp = ev_ring->rp;
+	local_rp = (u32)to_physical(ev_ring, ev_rp);
+	while (local_rp != cntxt_rp) {
+		union gpi_event *gpi_event = ev_rp;
+		u32 chid = gpi_event->xfer_compl_event.chid;
+
+		if (chid == gchan->chid)
+			gpi_event->xfer_compl_event.type = STALE_EV_TYPE;
+		ev_rp += ev_ring->el_size;
+		if (ev_rp >= (ev_ring->base + ev_ring->len))
+			ev_rp = ev_ring->base;
+		cntxt_rp = gpi_read_reg(gpii, gpii->ev_ring_rp_lsb_reg);
+		local_rp = (u32)to_physical(ev_ring, ev_rp);
+	}
+}
+
+/* reset sw state and issue channel reset or de-alloc */
+static int gpi_reset_chan(struct gchan *gchan, enum gpi_cmd gpi_cmd)
+{
+	struct gpii *gpii = gchan->gpii;
+	struct gpi_ring *ch_ring = &gchan->ch_ring;
+	unsigned long flags;
+	LIST_HEAD(list);
+	int ret;
+
+	ret = gpi_send_cmd(gpii, gchan, gpi_cmd);
+	if (ret) {
+		dev_err(gpii->gpi_dev->dev, "Error with cmd:%s ret:%d\n",
+			TO_GPI_CMD_STR(gpi_cmd), ret);
+		return ret;
+	}
+
+	/* initialize the local ring ptrs */
+	ch_ring->rp = ch_ring->base;
+	ch_ring->wp = ch_ring->base;
+
+	/* visible to other cores */
+	smp_wmb();
+
+	/* check event ring for any stale events */
+	write_lock_irq(&gpii->pm_lock);
+	gpi_mark_stale_events(gchan);
+
+	/* remove all async descriptors */
+	spin_lock_irqsave(&gchan->vc.lock, flags);
+	vchan_get_all_descriptors(&gchan->vc, &list);
+	spin_unlock_irqrestore(&gchan->vc.lock, flags);
+	write_unlock_irq(&gpii->pm_lock);
+	vchan_dma_desc_free_list(&gchan->vc, &list);
+
+	return 0;
+}
+
+static int gpi_start_chan(struct gchan *gchan)
+{
+	struct gpii *gpii = gchan->gpii;
+	int ret;
+
+	ret = gpi_send_cmd(gpii, gchan, GPI_CH_CMD_START);
+	if (ret) {
+		dev_err(gpii->gpi_dev->dev, "Error with cmd:%s ret:%d\n",
+			TO_GPI_CMD_STR(GPI_CH_CMD_START), ret);
+		return ret;
+	}
+
+	/* gpii CH is active now */
+	write_lock_irq(&gpii->pm_lock);
+	gchan->pm_state = ACTIVE_STATE;
+	write_unlock_irq(&gpii->pm_lock);
+
+	return 0;
+}
+
+static int gpi_stop_chan(struct gchan *gchan)
+{
+	struct gpii *gpii = gchan->gpii;
+	int ret;
+
+	ret = gpi_send_cmd(gpii, gchan, GPI_CH_CMD_STOP);
+	if (ret) {
+		dev_err(gpii->gpi_dev->dev, "Error with cmd:%s ret:%d\n",
+			TO_GPI_CMD_STR(GPI_CH_CMD_STOP), ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+/* allocate and configure the transfer channel */
+static int gpi_alloc_chan(struct gchan *chan, bool send_alloc_cmd)
+{
+	struct gpii *gpii = chan->gpii;
+	struct gpi_ring *ring = &chan->ch_ring;
+	int ret;
+	u32 id = gpii->gpii_id;
+	u32 chid = chan->chid;
+	u32 pair_chid = !chid;
+
+	if (send_alloc_cmd) {
+		ret = gpi_send_cmd(gpii, chan, GPI_CH_CMD_ALLOCATE);
+		if (ret) {
+			dev_err(gpii->gpi_dev->dev, "Error with cmd:%s ret:%d\n",
+				TO_GPI_CMD_STR(GPI_CH_CMD_ALLOCATE), ret);
+			return ret;
+		}
+	}
+
+	gpi_write_reg(gpii, chan->ch_cntxt_base_reg + CNTXT_0_CONFIG,
+		      GPII_n_CH_k_CNTXT_0(ring->el_size, 0, chan->dir, GPI_CHTYPE_PROTO_GPI));
+	gpi_write_reg(gpii, chan->ch_cntxt_base_reg + CNTXT_1_R_LENGTH, ring->len);
+	gpi_write_reg(gpii, chan->ch_cntxt_base_reg + CNTXT_2_RING_BASE_LSB, ring->phys_addr);
+	gpi_write_reg(gpii, chan->ch_cntxt_base_reg + CNTXT_3_RING_BASE_MSB,
+		      upper_32_bits(ring->phys_addr));
+	gpi_write_reg(gpii, chan->ch_cntxt_db_reg + CNTXT_5_RING_RP_MSB - CNTXT_4_RING_RP_LSB,
+		      upper_32_bits(ring->phys_addr));
+	gpi_write_reg(gpii, gpii->regs + GPII_n_CH_k_SCRATCH_0_OFFS(id, chid),
+		      GPII_n_CH_k_SCRATCH_0(pair_chid, chan->protocol, chan->seid));
+	gpi_write_reg(gpii, gpii->regs + GPII_n_CH_k_SCRATCH_1_OFFS(id, chid), 0);
+	gpi_write_reg(gpii, gpii->regs + GPII_n_CH_k_SCRATCH_2_OFFS(id, chid), 0);
+	gpi_write_reg(gpii, gpii->regs + GPII_n_CH_k_SCRATCH_3_OFFS(id, chid), 0);
+	gpi_write_reg(gpii, gpii->regs + GPII_n_CH_k_QOS_OFFS(id, chid), 1);
+
+	/* flush all the writes */
+	wmb();
+	return 0;
+}
+
+/* allocate and configure event ring */
+static int gpi_alloc_ev_chan(struct gpii *gpii)
+{
+	struct gpi_ring *ring = &gpii->ev_ring;
+	void __iomem *base = gpii->ev_cntxt_base_reg;
+	int ret;
+
+	ret = gpi_send_cmd(gpii, NULL, GPI_EV_CMD_ALLOCATE);
+	if (ret) {
+		dev_err(gpii->gpi_dev->dev, "error with cmd:%s ret:%d\n",
+			TO_GPI_CMD_STR(GPI_EV_CMD_ALLOCATE), ret);
+		return ret;
+	}
+
+	/* program event context */
+	gpi_write_reg(gpii, base + CNTXT_0_CONFIG,
+		      GPII_n_EV_k_CNTXT_0(ring->el_size, GPI_INTTYPE_IRQ, GPI_CHTYPE_GPI_EV));
+	gpi_write_reg(gpii, base + CNTXT_1_R_LENGTH, ring->len);
+	gpi_write_reg(gpii, base + CNTXT_2_RING_BASE_LSB, lower_32_bits(ring->phys_addr));
+	gpi_write_reg(gpii, base + CNTXT_3_RING_BASE_MSB, upper_32_bits(ring->phys_addr));
+	gpi_write_reg(gpii, gpii->ev_cntxt_db_reg + CNTXT_5_RING_RP_MSB - CNTXT_4_RING_RP_LSB,
+		      upper_32_bits(ring->phys_addr));
+	gpi_write_reg(gpii, base + CNTXT_8_RING_INT_MOD, 0);
+	gpi_write_reg(gpii, base + CNTXT_10_RING_MSI_LSB, 0);
+	gpi_write_reg(gpii, base + CNTXT_11_RING_MSI_MSB, 0);
+	gpi_write_reg(gpii, base + CNTXT_8_RING_INT_MOD, 0);
+	gpi_write_reg(gpii, base + CNTXT_12_RING_RP_UPDATE_LSB, 0);
+	gpi_write_reg(gpii, base + CNTXT_13_RING_RP_UPDATE_MSB, 0);
+
+	/* add events to ring */
+	ring->wp = (ring->base + ring->len - ring->el_size);
+
+	/* flush all the writes */
+	wmb();
+
+	/* gpii is active now */
+	write_lock_irq(&gpii->pm_lock);
+	gpii->pm_state = ACTIVE_STATE;
+	write_unlock_irq(&gpii->pm_lock);
+	gpi_write_ev_db(gpii, ring, ring->wp);
+
+	return 0;
+}
+
+/* calculate # of ERE/TRE available to queue */
+static int gpi_ring_num_elements_avail(const struct gpi_ring * const ring)
+{
+	int elements = 0;
+
+	if (ring->wp < ring->rp) {
+		elements = ((ring->rp - ring->wp) / ring->el_size) - 1;
+	} else {
+		elements = (ring->rp - ring->base) / ring->el_size;
+		elements += ((ring->base + ring->len - ring->wp) / ring->el_size) - 1;
+	}
+
+	return elements;
+}
+
+static int gpi_ring_add_element(struct gpi_ring *ring, void **wp)
+{
+	if (gpi_ring_num_elements_avail(ring) <= 0)
+		return -ENOMEM;
+
+	*wp = ring->wp;
+	ring->wp += ring->el_size;
+	if (ring->wp  >= (ring->base + ring->len))
+		ring->wp = ring->base;
+
+	/* visible to other cores */
+	smp_wmb();
+
+	return 0;
+}
+
+static void gpi_ring_recycle_ev_element(struct gpi_ring *ring)
+{
+	/* Update the WP */
+	ring->wp += ring->el_size;
+	if (ring->wp  >= (ring->base + ring->len))
+		ring->wp = ring->base;
+
+	/* Update the RP */
+	ring->rp += ring->el_size;
+	if (ring->rp  >= (ring->base + ring->len))
+		ring->rp = ring->base;
+
+	/* visible to other cores */
+	smp_wmb();
+}
+
+static void gpi_free_ring(struct gpi_ring *ring,
+			  struct gpii *gpii)
+{
+	dma_free_coherent(gpii->gpi_dev->dev, ring->alloc_size,
+			  ring->pre_aligned, ring->dma_handle);
+	memset(ring, 0, sizeof(*ring));
+}
+
+/* allocate memory for transfer and event rings */
+static int gpi_alloc_ring(struct gpi_ring *ring, u32 elements,
+			  u32 el_size, struct gpii *gpii)
+{
+	u64 len = elements * el_size;
+	int bit;
+
+	/* ring len must be power of 2 */
+	bit = find_last_bit((unsigned long *)&len, 32);
+	if (((1 << bit) - 1) & len)
+		bit++;
+	len = 1 << bit;
+	ring->alloc_size = (len + (len - 1));
+	dev_dbg(gpii->gpi_dev->dev,
+		"#el:%u el_size:%u len:%u actual_len:%llu alloc_size:%lu\n",
+		  elements, el_size, (elements * el_size), len,
+		  ring->alloc_size);
+
+	ring->pre_aligned = dma_alloc_coherent(gpii->gpi_dev->dev,
+					       ring->alloc_size,
+					       &ring->dma_handle, GFP_KERNEL);
+	if (!ring->pre_aligned) {
+		dev_err(gpii->gpi_dev->dev, "could not alloc size:%lu mem for ring\n",
+			ring->alloc_size);
+		return -ENOMEM;
+	}
+
+	/* align the physical mem */
+	ring->phys_addr = (ring->dma_handle + (len - 1)) & ~(len - 1);
+	ring->base = ring->pre_aligned + (ring->phys_addr - ring->dma_handle);
+	ring->rp = ring->base;
+	ring->wp = ring->base;
+	ring->len = len;
+	ring->el_size = el_size;
+	ring->elements = ring->len / ring->el_size;
+	memset(ring->base, 0, ring->len);
+	ring->configured = true;
+
+	/* update to other cores */
+	smp_wmb();
+
+	dev_dbg(gpii->gpi_dev->dev,
+		"phy_pre:0x%0llx phy_alig:0x%0llx len:%u el_size:%u elements:%u\n",
+		ring->dma_handle, ring->phys_addr, ring->len,
+		ring->el_size, ring->elements);
+
+	return 0;
+}
+
+/* copy tre into transfer ring */
+static void gpi_queue_xfer(struct gpii *gpii, struct gchan *gchan,
+			   struct gpi_tre *gpi_tre, void **wp)
+{
+	struct gpi_tre *ch_tre;
+	int ret;
+
+	/* get next tre location we can copy */
+	ret = gpi_ring_add_element(&gchan->ch_ring, (void **)&ch_tre);
+	if (unlikely(ret)) {
+		dev_err(gpii->gpi_dev->dev, "Error adding ring element to xfer ring\n");
+		return;
+	}
+
+	/* copy the tre info */
+	memcpy(ch_tre, gpi_tre, sizeof(*ch_tre));
+	*wp = ch_tre;
+}
+
+/* reset and restart transfer channel */
+static int gpi_terminate_all(struct dma_chan *chan)
+{
+	struct gchan *gchan = to_gchan(chan);
+	struct gpii *gpii = gchan->gpii;
+	int schid, echid, i;
+	int ret = 0;
+
+	mutex_lock(&gpii->ctrl_lock);
+
+	/*
+	 * treat both channels as a group if its protocol is not UART
+	 * STOP, RESET, or START needs to be in lockstep
+	 */
+	schid = (gchan->protocol == QCOM_GPI_UART) ? gchan->chid : 0;
+	echid = (gchan->protocol == QCOM_GPI_UART) ? schid + 1 : MAX_CHANNELS_PER_GPII;
+
+	/* stop the channel */
+	for (i = schid; i < echid; i++) {
+		gchan = &gpii->gchan[i];
+
+		/* disable ch state so no more TRE processing */
+		write_lock_irq(&gpii->pm_lock);
+		gchan->pm_state = PREPARE_TERMINATE;
+		write_unlock_irq(&gpii->pm_lock);
+
+		/* send command to Stop the channel */
+		ret = gpi_stop_chan(gchan);
+	}
+
+	/* reset the channels (clears any pending tre) */
+	for (i = schid; i < echid; i++) {
+		gchan = &gpii->gchan[i];
+
+		ret = gpi_reset_chan(gchan, GPI_CH_CMD_RESET);
+		if (ret) {
+			dev_err(gpii->gpi_dev->dev, "Error resetting channel ret:%d\n", ret);
+			goto terminate_exit;
+		}
+
+		/* reprogram channel CNTXT */
+		ret = gpi_alloc_chan(gchan, false);
+		if (ret) {
+			dev_err(gpii->gpi_dev->dev, "Error alloc_channel ret:%d\n", ret);
+			goto terminate_exit;
+		}
+	}
+
+	/* restart the channels */
+	for (i = schid; i < echid; i++) {
+		gchan = &gpii->gchan[i];
+
+		ret = gpi_start_chan(gchan);
+		if (ret) {
+			dev_err(gpii->gpi_dev->dev, "Error Starting Channel ret:%d\n", ret);
+			goto terminate_exit;
+		}
+	}
+
+terminate_exit:
+	mutex_unlock(&gpii->ctrl_lock);
+	return ret;
+}
+
+/* pause dma transfer for all channels */
+static int gpi_pause(struct dma_chan *chan)
+{
+	struct gchan *gchan = to_gchan(chan);
+	struct gpii *gpii = gchan->gpii;
+	int i, ret;
+
+	mutex_lock(&gpii->ctrl_lock);
+
+	/*
+	 * pause/resume are per gpii not per channel, so
+	 * client needs to call pause only once
+	 */
+	if (gpii->pm_state == PAUSE_STATE) {
+		dev_dbg(gpii->gpi_dev->dev, "channel is already paused\n");
+		mutex_unlock(&gpii->ctrl_lock);
+		return 0;
+	}
+
+	/* send stop command to stop the channels */
+	for (i = 0; i < MAX_CHANNELS_PER_GPII; i++) {
+		ret = gpi_stop_chan(&gpii->gchan[i]);
+		if (ret) {
+			mutex_unlock(&gpii->ctrl_lock);
+			return ret;
+		}
+	}
+
+	disable_irq(gpii->irq);
+
+	/* Wait for threads to complete out */
+	tasklet_kill(&gpii->ev_task);
+
+	write_lock_irq(&gpii->pm_lock);
+	gpii->pm_state = PAUSE_STATE;
+	write_unlock_irq(&gpii->pm_lock);
+	mutex_unlock(&gpii->ctrl_lock);
+
+	return 0;
+}
+
+/* resume dma transfer */
+static int gpi_resume(struct dma_chan *chan)
+{
+	struct gchan *gchan = to_gchan(chan);
+	struct gpii *gpii = gchan->gpii;
+	int i, ret;
+
+	mutex_lock(&gpii->ctrl_lock);
+	if (gpii->pm_state == ACTIVE_STATE) {
+		dev_dbg(gpii->gpi_dev->dev, "channel is already active\n");
+		mutex_unlock(&gpii->ctrl_lock);
+		return 0;
+	}
+
+	enable_irq(gpii->irq);
+
+	/* send start command to start the channels */
+	for (i = 0; i < MAX_CHANNELS_PER_GPII; i++) {
+		ret = gpi_send_cmd(gpii, &gpii->gchan[i], GPI_CH_CMD_START);
+		if (ret) {
+			dev_err(gpii->gpi_dev->dev, "Error starting chan, ret:%d\n", ret);
+			mutex_unlock(&gpii->ctrl_lock);
+			return ret;
+		}
+	}
+
+	write_lock_irq(&gpii->pm_lock);
+	gpii->pm_state = ACTIVE_STATE;
+	write_unlock_irq(&gpii->pm_lock);
+	mutex_unlock(&gpii->ctrl_lock);
+
+	return 0;
+}
+
+static void gpi_desc_free(struct virt_dma_desc *vd)
+{
+	struct gpi_desc *gpi_desc = to_gpi_desc(vd);
+
+	kfree(gpi_desc);
+	gpi_desc = NULL;
+}
+
+static int
+gpi_peripheral_config(struct dma_chan *chan, struct dma_slave_config *config)
+{
+	struct gchan *gchan = to_gchan(chan);
+
+	if (!config->peripheral_config)
+		return -EINVAL;
+
+	gchan->config = krealloc(gchan->config, config->peripheral_size, GFP_NOWAIT);
+	if (!gchan->config)
+		return -ENOMEM;
+
+	memcpy(gchan->config, config->peripheral_config, config->peripheral_size);
+
+	return 0;
+}
+
+static int gpi_create_i2c_tre(struct gchan *chan, struct gpi_desc *desc,
+			      struct scatterlist *sgl, enum dma_transfer_direction direction)
+{
+	struct gpi_i2c_config *i2c = chan->config;
+	struct device *dev = chan->gpii->gpi_dev->dev;
+	unsigned int tre_idx = 0;
+	dma_addr_t address;
+	struct gpi_tre *tre;
+	unsigned int i;
+
+	/* first create config tre if applicable */
+	if (i2c->set_config) {
+		tre = &desc->tre[tre_idx];
+		tre_idx++;
+
+		tre->dword[0] = u32_encode_bits(i2c->low_count, TRE_I2C_C0_TLOW);
+		tre->dword[0] |= u32_encode_bits(i2c->high_count, TRE_I2C_C0_THIGH);
+		tre->dword[0] |= u32_encode_bits(i2c->cycle_count, TRE_I2C_C0_TCYL);
+		tre->dword[0] |= u32_encode_bits(i2c->pack_enable, TRE_I2C_C0_TX_PACK);
+		tre->dword[0] |= u32_encode_bits(i2c->pack_enable, TRE_I2C_C0_RX_PACK);
+
+		tre->dword[1] = 0;
+
+		tre->dword[2] = u32_encode_bits(i2c->clk_div, TRE_C0_CLK_DIV);
+
+		tre->dword[3] = u32_encode_bits(TRE_TYPE_CONFIG0, TRE_FLAGS_TYPE);
+		tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_CHAIN);
+	}
+
+	/* create the GO tre for Tx */
+	if (i2c->op == I2C_WRITE) {
+		tre = &desc->tre[tre_idx];
+		tre_idx++;
+
+		if (i2c->multi_msg)
+			tre->dword[0] = u32_encode_bits(I2C_READ, TRE_I2C_GO_CMD);
+		else
+			tre->dword[0] = u32_encode_bits(i2c->op, TRE_I2C_GO_CMD);
+
+		tre->dword[0] |= u32_encode_bits(i2c->addr, TRE_I2C_GO_ADDR);
+		tre->dword[0] |= u32_encode_bits(i2c->stretch, TRE_I2C_GO_STRETCH);
+
+		tre->dword[1] = 0;
+		tre->dword[2] = u32_encode_bits(i2c->rx_len, TRE_RX_LEN);
+
+		tre->dword[3] = u32_encode_bits(TRE_TYPE_GO, TRE_FLAGS_TYPE);
+
+		if (i2c->multi_msg)
+			tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_LINK);
+		else
+			tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_CHAIN);
+	}
+
+	if (i2c->op == I2C_READ || i2c->multi_msg == false) {
+		/* create the DMA TRE */
+		tre = &desc->tre[tre_idx];
+		tre_idx++;
+
+		address = sg_dma_address(sgl);
+		tre->dword[0] = lower_32_bits(address);
+		tre->dword[1] = upper_32_bits(address);
+
+		tre->dword[2] = u32_encode_bits(sg_dma_len(sgl), TRE_DMA_LEN);
+
+		tre->dword[3] = u32_encode_bits(TRE_TYPE_DMA, TRE_FLAGS_TYPE);
+		tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_IEOT);
+	};
+
+	for (i = 0; i < tre_idx; i++)
+		dev_dbg(dev, "TRE:%d %x:%x:%x:%x\n", i, desc->tre[i].dword[0],
+			desc->tre[i].dword[1], desc->tre[i].dword[2], desc->tre[i].dword[3]);
+
+	return tre_idx;
+}
+
+static int gpi_create_spi_tre(struct gchan *chan, struct gpi_desc *desc,
+			      struct scatterlist *sgl, enum dma_transfer_direction direction)
+{
+	struct gpi_spi_config *spi = chan->config;
+	struct device *dev = chan->gpii->gpi_dev->dev;
+	unsigned int tre_idx = 0;
+	dma_addr_t address;
+	struct gpi_tre *tre;
+	unsigned int i;
+
+	/* first create config tre if applicable */
+	if (direction == DMA_MEM_TO_DEV && spi->set_config) {
+		tre = &desc->tre[tre_idx];
+		tre_idx++;
+
+		tre->dword[0] = u32_encode_bits(spi->word_len, TRE_SPI_C0_WORD_SZ);
+		tre->dword[0] |= u32_encode_bits(spi->loopback_en, TRE_SPI_C0_LOOPBACK);
+		tre->dword[0] |= u32_encode_bits(spi->clock_pol_high, TRE_SPI_C0_CPOL);
+		tre->dword[0] |= u32_encode_bits(spi->data_pol_high, TRE_SPI_C0_CPHA);
+		tre->dword[0] |= u32_encode_bits(spi->pack_en, TRE_SPI_C0_TX_PACK);
+		tre->dword[0] |= u32_encode_bits(spi->pack_en, TRE_SPI_C0_RX_PACK);
+
+		tre->dword[1] = 0;
+
+		tre->dword[2] = u32_encode_bits(spi->clk_div, TRE_C0_CLK_DIV);
+		tre->dword[2] |= u32_encode_bits(spi->clk_src, TRE_C0_CLK_SRC);
+
+		tre->dword[3] = u32_encode_bits(TRE_TYPE_CONFIG0, TRE_FLAGS_TYPE);
+		tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_CHAIN);
+	}
+
+	/* create the GO tre for Tx */
+	if (direction == DMA_MEM_TO_DEV) {
+		tre = &desc->tre[tre_idx];
+		tre_idx++;
+
+		tre->dword[0] = u32_encode_bits(spi->fragmentation, TRE_SPI_GO_FRAG);
+		tre->dword[0] |= u32_encode_bits(spi->cs, TRE_SPI_GO_CS);
+		tre->dword[0] |= u32_encode_bits(spi->cmd, TRE_SPI_GO_CMD);
+
+		tre->dword[1] = 0;
+
+		tre->dword[2] = u32_encode_bits(spi->rx_len, TRE_RX_LEN);
+
+		tre->dword[3] = u32_encode_bits(TRE_TYPE_GO, TRE_FLAGS_TYPE);
+		if (spi->cmd == SPI_RX)
+			tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_IEOB);
+		else
+			tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_CHAIN);
+	}
+
+	/* create the dma tre */
+	tre = &desc->tre[tre_idx];
+	tre_idx++;
+
+	address = sg_dma_address(sgl);
+	tre->dword[0] = lower_32_bits(address);
+	tre->dword[1] = upper_32_bits(address);
+
+	tre->dword[2] = u32_encode_bits(sg_dma_len(sgl), TRE_DMA_LEN);
+
+	tre->dword[3] = u32_encode_bits(TRE_TYPE_DMA, TRE_FLAGS_TYPE);
+	if (direction == DMA_MEM_TO_DEV)
+		tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_IEOT);
+
+	for (i = 0; i < tre_idx; i++)
+		dev_dbg(dev, "TRE:%d %x:%x:%x:%x\n", i, desc->tre[i].dword[0],
+			desc->tre[i].dword[1], desc->tre[i].dword[2], desc->tre[i].dword[3]);
+
+	return tre_idx;
+}
+
+/* copy tre into transfer ring */
+static struct dma_async_tx_descriptor *
+gpi_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
+		  unsigned int sg_len, enum dma_transfer_direction direction,
+		  unsigned long flags, void *context)
+{
+	struct gchan *gchan = to_gchan(chan);
+	struct gpii *gpii = gchan->gpii;
+	struct device *dev = gpii->gpi_dev->dev;
+	struct gpi_ring *ch_ring = &gchan->ch_ring;
+	struct gpi_desc *gpi_desc;
+	u32 nr, nr_tre = 0;
+	u8 set_config;
+	int i;
+
+	gpii->ieob_set = false;
+	if (!is_slave_direction(direction)) {
+		dev_err(gpii->gpi_dev->dev, "invalid dma direction: %d\n", direction);
+		return NULL;
+	}
+
+	if (sg_len > 1) {
+		dev_err(dev, "Multi sg sent, we support only one atm: %d\n", sg_len);
+		return NULL;
+	}
+
+	nr_tre = 3;
+	set_config = *(u32 *)gchan->config;
+	if (!set_config)
+		nr_tre = 2;
+	if (direction == DMA_DEV_TO_MEM) /* rx */
+		nr_tre = 1;
+
+	/* calculate # of elements required & available */
+	nr = gpi_ring_num_elements_avail(ch_ring);
+	if (nr < nr_tre) {
+		dev_err(dev, "not enough space in ring, avail:%u required:%u\n", nr, nr_tre);
+		return NULL;
+	}
+
+	gpi_desc = kzalloc(sizeof(*gpi_desc), GFP_NOWAIT);
+	if (!gpi_desc)
+		return NULL;
+
+	/* create TREs for xfer */
+	if (gchan->protocol == QCOM_GPI_SPI) {
+		i = gpi_create_spi_tre(gchan, gpi_desc, sgl, direction);
+	} else if (gchan->protocol == QCOM_GPI_I2C) {
+		i = gpi_create_i2c_tre(gchan, gpi_desc, sgl, direction);
+	} else {
+		dev_err(dev, "invalid peripheral: %d\n", gchan->protocol);
+		kfree(gpi_desc);
+		return NULL;
+	}
+
+	/* set up the descriptor */
+	gpi_desc->gchan = gchan;
+	gpi_desc->len = sg_dma_len(sgl);
+	gpi_desc->num_tre  = i;
+
+	return vchan_tx_prep(&gchan->vc, &gpi_desc->vd, flags);
+}
+
+/* rings transfer ring db to being transfer */
+static void gpi_issue_pending(struct dma_chan *chan)
+{
+	struct gchan *gchan = to_gchan(chan);
+	struct gpii *gpii = gchan->gpii;
+	unsigned long flags, pm_lock_flags;
+	struct virt_dma_desc *vd = NULL;
+	struct gpi_desc *gpi_desc;
+	struct gpi_ring *ch_ring = &gchan->ch_ring;
+	void *tre, *wp = NULL;
+	int i;
+
+	read_lock_irqsave(&gpii->pm_lock, pm_lock_flags);
+
+	/* move all submitted discriptors to issued list */
+	spin_lock_irqsave(&gchan->vc.lock, flags);
+	if (vchan_issue_pending(&gchan->vc))
+		vd = list_last_entry(&gchan->vc.desc_issued,
+				     struct virt_dma_desc, node);
+	spin_unlock_irqrestore(&gchan->vc.lock, flags);
+
+	/* nothing to do list is empty */
+	if (!vd) {
+		read_unlock_irqrestore(&gpii->pm_lock, pm_lock_flags);
+		return;
+	}
+
+	gpi_desc = to_gpi_desc(vd);
+	for (i = 0; i < gpi_desc->num_tre; i++) {
+		tre = &gpi_desc->tre[i];
+		gpi_queue_xfer(gpii, gchan, tre, &wp);
+	}
+
+	gpi_desc->db = ch_ring->wp;
+	gpi_write_ch_db(gchan, &gchan->ch_ring, gpi_desc->db);
+	read_unlock_irqrestore(&gpii->pm_lock, pm_lock_flags);
+}
+
+static int gpi_ch_init(struct gchan *gchan)
+{
+	struct gpii *gpii = gchan->gpii;
+	const int ev_factor = gpii->gpi_dev->ev_factor;
+	u32 elements;
+	int i = 0, ret = 0;
+
+	gchan->pm_state = CONFIG_STATE;
+
+	/* check if both channels are configured before continue */
+	for (i = 0; i < MAX_CHANNELS_PER_GPII; i++)
+		if (gpii->gchan[i].pm_state != CONFIG_STATE)
+			goto exit_gpi_init;
+
+	/* protocol must be same for both channels */
+	if (gpii->gchan[0].protocol != gpii->gchan[1].protocol) {
+		dev_err(gpii->gpi_dev->dev, "protocol did not match protocol %u != %u\n",
+			gpii->gchan[0].protocol, gpii->gchan[1].protocol);
+		ret = -EINVAL;
+		goto exit_gpi_init;
+	}
+
+	/* allocate memory for event ring */
+	elements = CHAN_TRES << ev_factor;
+	ret = gpi_alloc_ring(&gpii->ev_ring, elements,
+			     sizeof(union gpi_event), gpii);
+	if (ret)
+		goto exit_gpi_init;
+
+	/* configure interrupts */
+	write_lock_irq(&gpii->pm_lock);
+	gpii->pm_state = PREPARE_HARDWARE;
+	write_unlock_irq(&gpii->pm_lock);
+	ret = gpi_config_interrupts(gpii, DEFAULT_IRQ_SETTINGS, 0);
+	if (ret) {
+		dev_err(gpii->gpi_dev->dev, "error config. interrupts, ret:%d\n", ret);
+		goto error_config_int;
+	}
+
+	/* allocate event rings */
+	ret = gpi_alloc_ev_chan(gpii);
+	if (ret) {
+		dev_err(gpii->gpi_dev->dev, "error alloc_ev_chan:%d\n", ret);
+		goto error_alloc_ev_ring;
+	}
+
+	/* Allocate all channels */
+	for (i = 0; i < MAX_CHANNELS_PER_GPII; i++) {
+		ret = gpi_alloc_chan(&gpii->gchan[i], true);
+		if (ret) {
+			dev_err(gpii->gpi_dev->dev, "Error allocating chan:%d\n", ret);
+			goto error_alloc_chan;
+		}
+	}
+
+	/* start channels  */
+	for (i = 0; i < MAX_CHANNELS_PER_GPII; i++) {
+		ret = gpi_start_chan(&gpii->gchan[i]);
+		if (ret) {
+			dev_err(gpii->gpi_dev->dev, "Error start chan:%d\n", ret);
+			goto error_start_chan;
+		}
+	}
+	return ret;
+
+error_start_chan:
+	for (i = i - 1; i >= 0; i++) {
+		gpi_stop_chan(&gpii->gchan[i]);
+		gpi_send_cmd(gpii, gchan, GPI_CH_CMD_RESET);
+	}
+	i = 2;
+error_alloc_chan:
+	for (i = i - 1; i >= 0; i--)
+		gpi_reset_chan(gchan, GPI_CH_CMD_DE_ALLOC);
+error_alloc_ev_ring:
+	gpi_disable_interrupts(gpii);
+error_config_int:
+	gpi_free_ring(&gpii->ev_ring, gpii);
+exit_gpi_init:
+	mutex_unlock(&gpii->ctrl_lock);
+	return ret;
+}
+
+/* release all channel resources */
+static void gpi_free_chan_resources(struct dma_chan *chan)
+{
+	struct gchan *gchan = to_gchan(chan);
+	struct gpii *gpii = gchan->gpii;
+	enum gpi_pm_state cur_state;
+	int ret, i;
+
+	mutex_lock(&gpii->ctrl_lock);
+
+	cur_state = gchan->pm_state;
+
+	/* disable ch state so no more TRE processing for this channel */
+	write_lock_irq(&gpii->pm_lock);
+	gchan->pm_state = PREPARE_TERMINATE;
+	write_unlock_irq(&gpii->pm_lock);
+
+	/* attempt to do graceful hardware shutdown */
+	if (cur_state == ACTIVE_STATE) {
+		gpi_stop_chan(gchan);
+
+		ret = gpi_send_cmd(gpii, gchan, GPI_CH_CMD_RESET);
+		if (ret)
+			dev_err(gpii->gpi_dev->dev, "error resetting channel:%d\n", ret);
+
+		gpi_reset_chan(gchan, GPI_CH_CMD_DE_ALLOC);
+	}
+
+	/* free all allocated memory */
+	gpi_free_ring(&gchan->ch_ring, gpii);
+	vchan_free_chan_resources(&gchan->vc);
+	kfree(gchan->config);
+
+	write_lock_irq(&gpii->pm_lock);
+	gchan->pm_state = DISABLE_STATE;
+	write_unlock_irq(&gpii->pm_lock);
+
+	/* if other rings are still active exit */
+	for (i = 0; i < MAX_CHANNELS_PER_GPII; i++)
+		if (gpii->gchan[i].ch_ring.configured)
+			goto exit_free;
+
+	/* deallocate EV Ring */
+	cur_state = gpii->pm_state;
+	write_lock_irq(&gpii->pm_lock);
+	gpii->pm_state = PREPARE_TERMINATE;
+	write_unlock_irq(&gpii->pm_lock);
+
+	/* wait for threads to complete out */
+	tasklet_kill(&gpii->ev_task);
+
+	/* send command to de allocate event ring */
+	if (cur_state == ACTIVE_STATE)
+		gpi_send_cmd(gpii, NULL, GPI_EV_CMD_DEALLOC);
+
+	gpi_free_ring(&gpii->ev_ring, gpii);
+
+	/* disable interrupts */
+	if (cur_state == ACTIVE_STATE)
+		gpi_disable_interrupts(gpii);
+
+	/* set final state to disable */
+	write_lock_irq(&gpii->pm_lock);
+	gpii->pm_state = DISABLE_STATE;
+	write_unlock_irq(&gpii->pm_lock);
+
+exit_free:
+	mutex_unlock(&gpii->ctrl_lock);
+}
+
+/* allocate channel resources */
+static int gpi_alloc_chan_resources(struct dma_chan *chan)
+{
+	struct gchan *gchan = to_gchan(chan);
+	struct gpii *gpii = gchan->gpii;
+	int ret;
+
+	mutex_lock(&gpii->ctrl_lock);
+
+	/* allocate memory for transfer ring */
+	ret = gpi_alloc_ring(&gchan->ch_ring, CHAN_TRES,
+			     sizeof(struct gpi_tre), gpii);
+	if (ret)
+		goto xfer_alloc_err;
+
+	ret = gpi_ch_init(gchan);
+
+	mutex_unlock(&gpii->ctrl_lock);
+
+	return ret;
+xfer_alloc_err:
+	mutex_unlock(&gpii->ctrl_lock);
+
+	return ret;
+}
+
+static int gpi_find_avail_gpii(struct gpi_dev *gpi_dev, u32 seid)
+{
+	struct gchan *tx_chan, *rx_chan;
+	unsigned int gpii;
+
+	/* check if same seid is already configured for another chid */
+	for (gpii = 0; gpii < gpi_dev->max_gpii; gpii++) {
+		if (!((1 << gpii) & gpi_dev->gpii_mask))
+			continue;
+
+		tx_chan = &gpi_dev->gpiis[gpii].gchan[GPI_TX_CHAN];
+		rx_chan = &gpi_dev->gpiis[gpii].gchan[GPI_RX_CHAN];
+
+		if (rx_chan->vc.chan.client_count && rx_chan->seid == seid)
+			return gpii;
+		if (tx_chan->vc.chan.client_count && tx_chan->seid == seid)
+			return gpii;
+	}
+
+	/* no channels configured with same seid, return next avail gpii */
+	for (gpii = 0; gpii < gpi_dev->max_gpii; gpii++) {
+		if (!((1 << gpii) & gpi_dev->gpii_mask))
+			continue;
+
+		tx_chan = &gpi_dev->gpiis[gpii].gchan[GPI_TX_CHAN];
+		rx_chan = &gpi_dev->gpiis[gpii].gchan[GPI_RX_CHAN];
+
+		/* check if gpii is configured */
+		if (tx_chan->vc.chan.client_count ||
+		    rx_chan->vc.chan.client_count)
+			continue;
+
+		/* found a free gpii */
+		return gpii;
+	}
+
+	/* no gpii instance available to use */
+	return -EIO;
+}
+
+/* gpi_of_dma_xlate: open client requested channel */
+static struct dma_chan *gpi_of_dma_xlate(struct of_phandle_args *args,
+					 struct of_dma *of_dma)
+{
+	struct gpi_dev *gpi_dev = (struct gpi_dev *)of_dma->of_dma_data;
+	u32 seid, chid;
+	int gpii;
+	struct gchan *gchan;
+
+	if (args->args_count < 3) {
+		dev_err(gpi_dev->dev, "gpii require minimum 2 args, client passed:%d args\n",
+			args->args_count);
+		return NULL;
+	}
+
+	chid = args->args[0];
+	if (chid >= MAX_CHANNELS_PER_GPII) {
+		dev_err(gpi_dev->dev, "gpii channel:%d not valid\n", chid);
+		return NULL;
+	}
+
+	seid = args->args[1];
+
+	/* find next available gpii to use */
+	gpii = gpi_find_avail_gpii(gpi_dev, seid);
+	if (gpii < 0) {
+		dev_err(gpi_dev->dev, "no available gpii instances\n");
+		return NULL;
+	}
+
+	gchan = &gpi_dev->gpiis[gpii].gchan[chid];
+	if (gchan->vc.chan.client_count) {
+		dev_err(gpi_dev->dev, "gpii:%d chid:%d seid:%d already configured\n",
+			gpii, chid, gchan->seid);
+		return NULL;
+	}
+
+	gchan->seid = seid;
+	gchan->protocol = args->args[2];
+
+	return dma_get_slave_channel(&gchan->vc.chan);
+}
+
+static int gpi_probe(struct platform_device *pdev)
+{
+	struct gpi_dev *gpi_dev;
+	unsigned int i;
+	int ret;
+
+	gpi_dev = devm_kzalloc(&pdev->dev, sizeof(*gpi_dev), GFP_KERNEL);
+	if (!gpi_dev)
+		return -ENOMEM;
+
+	gpi_dev->dev = &pdev->dev;
+	gpi_dev->res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	gpi_dev->regs = devm_ioremap_resource(gpi_dev->dev, gpi_dev->res);
+	if (IS_ERR(gpi_dev->regs))
+		return PTR_ERR(gpi_dev->regs);
+	gpi_dev->ee_base = gpi_dev->regs;
+
+	ret = of_property_read_u32(gpi_dev->dev->of_node, "dma-channels",
+				   &gpi_dev->max_gpii);
+	if (ret) {
+		dev_err(gpi_dev->dev, "missing 'max-no-gpii' DT node\n");
+		return ret;
+	}
+
+	ret = of_property_read_u32(gpi_dev->dev->of_node, "dma-channel-mask",
+				   &gpi_dev->gpii_mask);
+	if (ret) {
+		dev_err(gpi_dev->dev, "missing 'gpii-mask' DT node\n");
+		return ret;
+	}
+
+	gpi_dev->ev_factor = EV_FACTOR;
+
+	ret = dma_set_mask(gpi_dev->dev, DMA_BIT_MASK(64));
+	if (ret) {
+		dev_err(gpi_dev->dev, "Error setting dma_mask to 64, ret:%d\n", ret);
+		return ret;
+	}
+
+	gpi_dev->gpiis = devm_kzalloc(gpi_dev->dev, sizeof(*gpi_dev->gpiis) *
+				      gpi_dev->max_gpii, GFP_KERNEL);
+	if (!gpi_dev->gpiis)
+		return -ENOMEM;
+
+	/* setup all the supported gpii */
+	INIT_LIST_HEAD(&gpi_dev->dma_device.channels);
+	for (i = 0; i < gpi_dev->max_gpii; i++) {
+		struct gpii *gpii = &gpi_dev->gpiis[i];
+		int chan;
+
+		if (!((1 << i) & gpi_dev->gpii_mask))
+			continue;
+
+		/* set up ev cntxt register map */
+		gpii->ev_cntxt_base_reg = gpi_dev->ee_base + GPII_n_EV_CH_k_CNTXT_0_OFFS(i, 0);
+		gpii->ev_cntxt_db_reg = gpi_dev->ee_base + GPII_n_EV_CH_k_DOORBELL_0_OFFS(i, 0);
+		gpii->ev_ring_rp_lsb_reg = gpii->ev_cntxt_base_reg + CNTXT_4_RING_RP_LSB;
+		gpii->ev_cmd_reg = gpi_dev->ee_base + GPII_n_EV_CH_CMD_OFFS(i);
+		gpii->ieob_clr_reg = gpi_dev->ee_base + GPII_n_CNTXT_SRC_IEOB_IRQ_CLR_OFFS(i);
+
+		/* set up irq */
+		ret = platform_get_irq(pdev, i);
+		if (ret < 0) {
+			dev_err(gpi_dev->dev, "platform_get_irq failed for %d:%d\n", i, ret);
+			return ret;
+		}
+		gpii->irq = ret;
+
+		/* set up channel specific register info */
+		for (chan = 0; chan < MAX_CHANNELS_PER_GPII; chan++) {
+			struct gchan *gchan = &gpii->gchan[chan];
+
+			/* set up ch cntxt register map */
+			gchan->ch_cntxt_base_reg = gpi_dev->ee_base +
+				GPII_n_CH_k_CNTXT_0_OFFS(i, chan);
+			gchan->ch_cntxt_db_reg = gpi_dev->ee_base +
+				GPII_n_CH_k_DOORBELL_0_OFFS(i, chan);
+			gchan->ch_cmd_reg = gpi_dev->ee_base + GPII_n_CH_CMD_OFFS(i);
+
+			/* vchan setup */
+			vchan_init(&gchan->vc, &gpi_dev->dma_device);
+			gchan->vc.desc_free = gpi_desc_free;
+			gchan->chid = chan;
+			gchan->gpii = gpii;
+			gchan->dir = GPII_CHAN_DIR[chan];
+		}
+		mutex_init(&gpii->ctrl_lock);
+		rwlock_init(&gpii->pm_lock);
+		tasklet_init(&gpii->ev_task, gpi_ev_tasklet,
+			     (unsigned long)gpii);
+		init_completion(&gpii->cmd_completion);
+		gpii->gpii_id = i;
+		gpii->regs = gpi_dev->ee_base;
+		gpii->gpi_dev = gpi_dev;
+	}
+
+	platform_set_drvdata(pdev, gpi_dev);
+
+	/* clear and Set capabilities */
+	dma_cap_zero(gpi_dev->dma_device.cap_mask);
+	dma_cap_set(DMA_SLAVE, gpi_dev->dma_device.cap_mask);
+
+	/* configure dmaengine apis */
+	gpi_dev->dma_device.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
+	gpi_dev->dma_device.residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR;
+	gpi_dev->dma_device.src_addr_widths = DMA_SLAVE_BUSWIDTH_8_BYTES;
+	gpi_dev->dma_device.dst_addr_widths = DMA_SLAVE_BUSWIDTH_8_BYTES;
+	gpi_dev->dma_device.device_alloc_chan_resources = gpi_alloc_chan_resources;
+	gpi_dev->dma_device.device_free_chan_resources = gpi_free_chan_resources;
+	gpi_dev->dma_device.device_tx_status = dma_cookie_status;
+	gpi_dev->dma_device.device_issue_pending = gpi_issue_pending;
+	gpi_dev->dma_device.device_prep_slave_sg = gpi_prep_slave_sg;
+	gpi_dev->dma_device.device_config = gpi_peripheral_config;
+	gpi_dev->dma_device.device_terminate_all = gpi_terminate_all;
+	gpi_dev->dma_device.dev = gpi_dev->dev;
+	gpi_dev->dma_device.device_pause = gpi_pause;
+	gpi_dev->dma_device.device_resume = gpi_resume;
+
+	/* register with dmaengine framework */
+	ret = dma_async_device_register(&gpi_dev->dma_device);
+	if (ret) {
+		dev_err(gpi_dev->dev, "async_device_register failed ret:%d", ret);
+		return ret;
+	}
+
+	ret = of_dma_controller_register(gpi_dev->dev->of_node,
+					 gpi_of_dma_xlate, gpi_dev);
+	if (ret) {
+		dev_err(gpi_dev->dev, "of_dma_controller_reg failed ret:%d", ret);
+		return ret;
+	}
+
+	return ret;
+}
+
+static const struct of_device_id gpi_of_match[] = {
+	{ .compatible = "qcom,sdm845-gpi-dma" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, gpi_of_match);
+
+static struct platform_driver gpi_driver = {
+	.probe = gpi_probe,
+	.driver = {
+		.name = KBUILD_MODNAME,
+		.of_match_table = gpi_of_match,
+	},
+};
+
+static int __init gpi_init(void)
+{
+	return platform_driver_register(&gpi_driver);
+}
+subsys_initcall(gpi_init)
+
+MODULE_DESCRIPTION("QCOM GPI DMA engine driver");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/dma/qcom-gpi-dma.h b/include/linux/dma/qcom-gpi-dma.h
new file mode 100644
index 000000000000..f46dc3372f11
--- /dev/null
+++ b/include/linux/dma/qcom-gpi-dma.h
@@ -0,0 +1,83 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2020, Linaro Limited
+ */
+
+#ifndef QCOM_GPI_DMA_H
+#define QCOM_GPI_DMA_H
+
+/**
+ * enum spi_transfer_cmd - spi transfer commands
+ */
+enum spi_transfer_cmd {
+	SPI_TX = 1,
+	SPI_RX,
+	SPI_DUPLEX,
+};
+
+/**
+ * struct gpi_spi_config - spi config for peripheral
+ *
+ * @loopback_en: spi loopback enable when set
+ * @clock_pol_high: clock polarity
+ * @data_pol_high: data polarity
+ * @pack_en: process tx/rx buffers as packed
+ * @word_len: spi word length
+ * @clk_div: source clock divider
+ * @clk_src: serial clock
+ * @cmd: spi cmd
+ * @fragmentation: keep CS assserted at end of sequence
+ * @cs: chip select toggle
+ * @set_config: set peripheral config
+ * @rx_len: receive length for buffer
+ */
+struct gpi_spi_config {
+	u8 set_config;
+	u8 loopback_en;
+	u8 clock_pol_high;
+	u8 data_pol_high;
+	u8 pack_en;
+	u8 word_len;
+	u8 fragmentation;
+	u8 cs;
+	u32 clk_div;
+	u32 clk_src;
+	enum spi_transfer_cmd cmd;
+	u32 rx_len;
+};
+
+enum i2c_op {
+	I2C_WRITE = 1,
+	I2C_READ,
+};
+
+/**
+ * struct gpi_i2c_config - i2c config for peripheral
+ *
+ * @pack_enable: process tx/rx buffers as packed
+ * @cycle_count: clock cycles to be sent
+ * @high_count: high period of clock
+ * @low_count: low period of clock
+ * @clk_div: source clock divider
+ * @addr: i2c bus address
+ * @stretch: stretch the clock at eot
+ * @set_config: set peripheral config
+ * @rx_len: receive length for buffer
+ * @op: i2c cmd
+ * @muli-msg: is part of multi i2c r-w msgs
+ */
+struct gpi_i2c_config {
+	u8 set_config;
+	u8 pack_enable;
+	u8 cycle_count;
+	u8 high_count;
+	u8 low_count;
+	u8 addr;
+	u8 stretch;
+	u16 clk_div;
+	u32 rx_len;
+	enum i2c_op op;
+	bool multi_msg;
+};
+
+#endif /* QCOM_GPI_DMA_H */
-- 
cgit v1.2.3


From 36ccdf85829a7dd6936dba5d02fa50138471f0d3 Mon Sep 17 00:00:00 2001
From: Björn Töpel <bjorn.topel@intel.com>
Date: Mon, 23 Nov 2020 18:56:00 +0100
Subject: net, xsk: Avoid taking multiple skbuff references
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 642e450b6b59 ("xsk: Do not discard packet when NETDEV_TX_BUSY")
addressed the problem that packets were discarded from the Tx AF_XDP
ring, when the driver returned NETDEV_TX_BUSY. Part of the fix was
bumping the skbuff reference count, so that the buffer would not be
freed by dev_direct_xmit(). A reference count larger than one means
that the skbuff is "shared", which is not the case.

If the "shared" skbuff is sent to the generic XDP receive path,
netif_receive_generic_xdp(), and pskb_expand_head() is entered the
BUG_ON(skb_shared(skb)) will trigger.

This patch adds a variant to dev_direct_xmit(), __dev_direct_xmit(),
where a user can select the skbuff free policy. This allows AF_XDP to
avoid bumping the reference count, but still keep the NETDEV_TX_BUSY
behavior.

Fixes: 642e450b6b59 ("xsk: Do not discard packet when NETDEV_TX_BUSY")
Reported-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20201123175600.146255-1-bjorn.topel@gmail.com
---
 include/linux/netdevice.h | 14 +++++++++++++-
 net/core/dev.c            |  8 ++------
 net/xdp/xsk.c             |  8 +-------
 3 files changed, 16 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 964b494b0e8d..76775abf259d 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2813,9 +2813,21 @@ u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb,
 		     struct net_device *sb_dev);
 u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb,
 		       struct net_device *sb_dev);
+
 int dev_queue_xmit(struct sk_buff *skb);
 int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev);
-int dev_direct_xmit(struct sk_buff *skb, u16 queue_id);
+int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id);
+
+static inline int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
+{
+	int ret;
+
+	ret = __dev_direct_xmit(skb, queue_id);
+	if (!dev_xmit_complete(ret))
+		kfree_skb(skb);
+	return ret;
+}
+
 int register_netdevice(struct net_device *dev);
 void unregister_netdevice_queue(struct net_device *dev, struct list_head *head);
 void unregister_netdevice_many(struct list_head *head);
diff --git a/net/core/dev.c b/net/core/dev.c
index 82dc6b48e45f..8588ade790cb 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4180,7 +4180,7 @@ int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev)
 }
 EXPORT_SYMBOL(dev_queue_xmit_accel);
 
-int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
+int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
 {
 	struct net_device *dev = skb->dev;
 	struct sk_buff *orig_skb = skb;
@@ -4210,17 +4210,13 @@ int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
 	dev_xmit_recursion_dec();
 
 	local_bh_enable();
-
-	if (!dev_xmit_complete(ret))
-		kfree_skb(skb);
-
 	return ret;
 drop:
 	atomic_long_inc(&dev->tx_dropped);
 	kfree_skb_list(skb);
 	return NET_XMIT_DROP;
 }
-EXPORT_SYMBOL(dev_direct_xmit);
+EXPORT_SYMBOL(__dev_direct_xmit);
 
 /*************************************************************************
  *			Receiver routines
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 5a6cdf7b320d..b7b039bd9d03 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -411,11 +411,7 @@ static int xsk_generic_xmit(struct sock *sk)
 		skb_shinfo(skb)->destructor_arg = (void *)(long)desc.addr;
 		skb->destructor = xsk_destruct_skb;
 
-		/* Hinder dev_direct_xmit from freeing the packet and
-		 * therefore completing it in the destructor
-		 */
-		refcount_inc(&skb->users);
-		err = dev_direct_xmit(skb, xs->queue_id);
+		err = __dev_direct_xmit(skb, xs->queue_id);
 		if  (err == NETDEV_TX_BUSY) {
 			/* Tell user-space to retry the send */
 			skb->destructor = sock_wfree;
@@ -429,12 +425,10 @@ static int xsk_generic_xmit(struct sock *sk)
 		/* Ignore NET_XMIT_CN as packet might have been sent */
 		if (err == NET_XMIT_DROP) {
 			/* SKB completed but not sent */
-			kfree_skb(skb);
 			err = -EBUSY;
 			goto out;
 		}
 
-		consume_skb(skb);
 		sent_frame = true;
 	}
 
-- 
cgit v1.2.3


From 159e1de201b6fca10bfec50405a3b53a561096a8 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Tue, 17 Nov 2020 23:56:05 -0800
Subject: fscrypt: add fscrypt_is_nokey_name()

It's possible to create a duplicate filename in an encrypted directory
by creating a file concurrently with adding the encryption key.

Specifically, sys_open(O_CREAT) (or sys_mkdir(), sys_mknod(), or
sys_symlink()) can lookup the target filename while the directory's
encryption key hasn't been added yet, resulting in a negative no-key
dentry.  The VFS then calls ->create() (or ->mkdir(), ->mknod(), or
->symlink()) because the dentry is negative.  Normally, ->create() would
return -ENOKEY due to the directory's key being unavailable.  However,
if the key was added between the dentry lookup and ->create(), then the
filesystem will go ahead and try to create the file.

If the target filename happens to already exist as a normal name (not a
no-key name), a duplicate filename may be added to the directory.

In order to fix this, we need to fix the filesystems to prevent
->create(), ->mkdir(), ->mknod(), and ->symlink() on no-key names.
(->rename() and ->link() need it too, but those are already handled
correctly by fscrypt_prepare_rename() and fscrypt_prepare_link().)

In preparation for this, add a helper function fscrypt_is_nokey_name()
that filesystems can use to do this check.  Use this helper function for
the existing checks that fs/crypto/ does for rename and link.

Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20201118075609.120337-2-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 fs/crypto/hooks.c       |  5 +++--
 include/linux/fscrypt.h | 34 ++++++++++++++++++++++++++++++++++
 2 files changed, 37 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c
index 20b0df47fe6a..061418be4b08 100644
--- a/fs/crypto/hooks.c
+++ b/fs/crypto/hooks.c
@@ -61,7 +61,7 @@ int __fscrypt_prepare_link(struct inode *inode, struct inode *dir,
 		return err;
 
 	/* ... in case we looked up no-key name before key was added */
-	if (dentry->d_flags & DCACHE_NOKEY_NAME)
+	if (fscrypt_is_nokey_name(dentry))
 		return -ENOKEY;
 
 	if (!fscrypt_has_permitted_context(dir, inode))
@@ -86,7 +86,8 @@ int __fscrypt_prepare_rename(struct inode *old_dir, struct dentry *old_dentry,
 		return err;
 
 	/* ... in case we looked up no-key name(s) before key was added */
-	if ((old_dentry->d_flags | new_dentry->d_flags) & DCACHE_NOKEY_NAME)
+	if (fscrypt_is_nokey_name(old_dentry) ||
+	    fscrypt_is_nokey_name(new_dentry))
 		return -ENOKEY;
 
 	if (old_dir != new_dir) {
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index a8f7a43f031b..8e1d31c959bf 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -111,6 +111,35 @@ static inline void fscrypt_handle_d_move(struct dentry *dentry)
 	dentry->d_flags &= ~DCACHE_NOKEY_NAME;
 }
 
+/**
+ * fscrypt_is_nokey_name() - test whether a dentry is a no-key name
+ * @dentry: the dentry to check
+ *
+ * This returns true if the dentry is a no-key dentry.  A no-key dentry is a
+ * dentry that was created in an encrypted directory that hasn't had its
+ * encryption key added yet.  Such dentries may be either positive or negative.
+ *
+ * When a filesystem is asked to create a new filename in an encrypted directory
+ * and the new filename's dentry is a no-key dentry, it must fail the operation
+ * with ENOKEY.  This includes ->create(), ->mkdir(), ->mknod(), ->symlink(),
+ * ->rename(), and ->link().  (However, ->rename() and ->link() are already
+ * handled by fscrypt_prepare_rename() and fscrypt_prepare_link().)
+ *
+ * This is necessary because creating a filename requires the directory's
+ * encryption key, but just checking for the key on the directory inode during
+ * the final filesystem operation doesn't guarantee that the key was available
+ * during the preceding dentry lookup.  And the key must have already been
+ * available during the dentry lookup in order for it to have been checked
+ * whether the filename already exists in the directory and for the new file's
+ * dentry not to be invalidated due to it incorrectly having the no-key flag.
+ *
+ * Return: %true if the dentry is a no-key name
+ */
+static inline bool fscrypt_is_nokey_name(const struct dentry *dentry)
+{
+	return dentry->d_flags & DCACHE_NOKEY_NAME;
+}
+
 /* crypto.c */
 void fscrypt_enqueue_decrypt_work(struct work_struct *);
 
@@ -244,6 +273,11 @@ static inline void fscrypt_handle_d_move(struct dentry *dentry)
 {
 }
 
+static inline bool fscrypt_is_nokey_name(const struct dentry *dentry)
+{
+	return false;
+}
+
 /* crypto.c */
 static inline void fscrypt_enqueue_decrypt_work(struct work_struct *work)
 {
-- 
cgit v1.2.3


From 234f1b7f8daf112655c87f75ae8932564f871225 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Tue, 17 Nov 2020 23:56:09 -0800
Subject: fscrypt: remove unnecessary calls to fscrypt_require_key()

In an encrypted directory, a regular dentry (one that doesn't have the
no-key name flag) can only be created if the directory's encryption key
is available.

Therefore the calls to fscrypt_require_key() in __fscrypt_prepare_link()
and __fscrypt_prepare_rename() are unnecessary, as these functions
already check that the dentries they're given aren't no-key names.

Remove these unnecessary calls to fscrypt_require_key().

Link: https://lore.kernel.org/r/20201118075609.120337-6-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 fs/crypto/hooks.c       | 26 ++++++++------------------
 include/linux/fscrypt.h |  3 +--
 2 files changed, 9 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c
index 061418be4b08..c582e2ddb39c 100644
--- a/fs/crypto/hooks.c
+++ b/fs/crypto/hooks.c
@@ -54,15 +54,12 @@ EXPORT_SYMBOL_GPL(fscrypt_file_open);
 int __fscrypt_prepare_link(struct inode *inode, struct inode *dir,
 			   struct dentry *dentry)
 {
-	int err;
-
-	err = fscrypt_require_key(dir);
-	if (err)
-		return err;
-
-	/* ... in case we looked up no-key name before key was added */
 	if (fscrypt_is_nokey_name(dentry))
 		return -ENOKEY;
+	/*
+	 * We don't need to separately check that the directory inode's key is
+	 * available, as it's implied by the dentry not being a no-key name.
+	 */
 
 	if (!fscrypt_has_permitted_context(dir, inode))
 		return -EXDEV;
@@ -75,20 +72,13 @@ int __fscrypt_prepare_rename(struct inode *old_dir, struct dentry *old_dentry,
 			     struct inode *new_dir, struct dentry *new_dentry,
 			     unsigned int flags)
 {
-	int err;
-
-	err = fscrypt_require_key(old_dir);
-	if (err)
-		return err;
-
-	err = fscrypt_require_key(new_dir);
-	if (err)
-		return err;
-
-	/* ... in case we looked up no-key name(s) before key was added */
 	if (fscrypt_is_nokey_name(old_dentry) ||
 	    fscrypt_is_nokey_name(new_dentry))
 		return -ENOKEY;
+	/*
+	 * We don't need to separately check that the directory inodes' keys are
+	 * available, as it's implied by the dentries not being no-key names.
+	 */
 
 	if (old_dir != new_dir) {
 		if (IS_ENCRYPTED(new_dir) &&
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index 8e1d31c959bf..0c9e64969b73 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -710,8 +710,7 @@ static inline int fscrypt_require_key(struct inode *inode)
  *
  * A new link can only be added to an encrypted directory if the directory's
  * encryption key is available --- since otherwise we'd have no way to encrypt
- * the filename.  Therefore, we first set up the directory's encryption key (if
- * not already done) and return an error if it's unavailable.
+ * the filename.
  *
  * We also verify that the link will not violate the constraint that all files
  * in an encrypted directory tree use the same encryption policy.
-- 
cgit v1.2.3


From 5903f61e035320104394f721f74cd22171636f63 Mon Sep 17 00:00:00 2001
From: Gabriel Krisman Bertazi <krisman@collabora.com>
Date: Mon, 23 Nov 2020 10:54:58 -0500
Subject: entry: Fix boot for !CONFIG_GENERIC_ENTRY

A copy-pasta mistake tries to set SYSCALL_WORK flags instead of TIF
flags for !CONFIG_GENERIC_ENTRY.  Also, add safeguards to catch this at
compilation time.

Fixes: 3136b93c3fb2 ("entry: Expose helpers to migrate TIF to SYSCALL_WORK flags")
Reported-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Suggested-by: Jann Horn <jannh@google.com>
Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/87a6v8qd9p.fsf_-_@collabora.com
---
 include/linux/thread_info.h | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index 317363212ae9..ca80a214df09 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -35,6 +35,7 @@ enum {
 	GOOD_STACK,
 };
 
+#ifdef CONFIG_GENERIC_ENTRY
 enum syscall_work_bit {
 	SYSCALL_WORK_BIT_SECCOMP,
 	SYSCALL_WORK_BIT_SYSCALL_TRACEPOINT,
@@ -48,6 +49,7 @@ enum syscall_work_bit {
 #define SYSCALL_WORK_SYSCALL_TRACE	BIT(SYSCALL_WORK_BIT_SYSCALL_TRACE)
 #define SYSCALL_WORK_SYSCALL_EMU	BIT(SYSCALL_WORK_BIT_SYSCALL_EMU)
 #define SYSCALL_WORK_SYSCALL_AUDIT	BIT(SYSCALL_WORK_BIT_SYSCALL_AUDIT)
+#endif
 
 #include <asm/thread_info.h>
 
@@ -129,11 +131,11 @@ static inline int test_ti_thread_flag(struct thread_info *ti, int flag)
 #else /* CONFIG_GENERIC_ENTRY */
 
 #define set_syscall_work(fl)						\
-	set_ti_thread_flag(current_thread_info(), SYSCALL_WORK_##fl)
+	set_ti_thread_flag(current_thread_info(), TIF_##fl)
 #define test_syscall_work(fl) \
-	test_ti_thread_flag(current_thread_info(), SYSCALL_WORK_##fl)
+	test_ti_thread_flag(current_thread_info(), TIF_##fl)
 #define clear_syscall_work(fl) \
-	clear_ti_thread_flag(current_thread_info(), SYSCALL_WORK_##fl)
+	clear_ti_thread_flag(current_thread_info(), TIF_##fl)
 
 #define set_task_syscall_work(t, fl) \
 	set_ti_thread_flag(task_thread_info(t), TIF_##fl)
-- 
cgit v1.2.3


From 2fb94784952e4b290c392b74c2c67b4afa672523 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Tue, 24 Nov 2020 09:33:16 +0800
Subject: soundwire: registers: add definitions for clearable interrupt fields

DP0 has reserved fields and the read-only SDCA_CASCADE bit. We should
not try to write values in these fields, so add a formal definition
for clearable interrupts to be used in DP0 interrupt handling.

DPN also has reserved fields so add definitions for clearable
interrupts as well.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20201124013318.8963-4-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/soundwire/sdw_registers.h | 11 +++++++++++
 1 file changed, 11 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/soundwire/sdw_registers.h b/include/linux/soundwire/sdw_registers.h
index f420e8059779..0cb1a22685b8 100644
--- a/include/linux/soundwire/sdw_registers.h
+++ b/include/linux/soundwire/sdw_registers.h
@@ -41,6 +41,12 @@
 #define SDW_DP0_INT_IMPDEF1			BIT(5)
 #define SDW_DP0_INT_IMPDEF2			BIT(6)
 #define SDW_DP0_INT_IMPDEF3			BIT(7)
+#define SDW_DP0_INTERRUPTS			(SDW_DP0_INT_TEST_FAIL | \
+						 SDW_DP0_INT_PORT_READY | \
+						 SDW_DP0_INT_BRA_FAILURE | \
+						 SDW_DP0_INT_IMPDEF1 | \
+						 SDW_DP0_INT_IMPDEF2 | \
+						 SDW_DP0_INT_IMPDEF3)
 
 #define SDW_DP0_PORTCTRL_DATAMODE		GENMASK(3, 2)
 #define SDW_DP0_PORTCTRL_NXTINVBANK		BIT(4)
@@ -241,6 +247,11 @@
 #define SDW_DPN_INT_IMPDEF1			BIT(5)
 #define SDW_DPN_INT_IMPDEF2			BIT(6)
 #define SDW_DPN_INT_IMPDEF3			BIT(7)
+#define SDW_DPN_INTERRUPTS			(SDW_DPN_INT_TEST_FAIL | \
+						 SDW_DPN_INT_PORT_READY | \
+						 SDW_DPN_INT_IMPDEF1 | \
+						 SDW_DPN_INT_IMPDEF2 | \
+						 SDW_DPN_INT_IMPDEF3)
 
 #define SDW_DPN_PORTCTRL_FLOWMODE		GENMASK(1, 0)
 #define SDW_DPN_PORTCTRL_DATAMODE		GENMASK(3, 2)
-- 
cgit v1.2.3


From 2a2b8eaa5b25668a6f717f94b55f4e3aaf87629d Mon Sep 17 00:00:00 2001
From: Tom Murphy <murphyt7@tcd.ie>
Date: Tue, 24 Nov 2020 16:20:51 +0800
Subject: iommu: Handle freelists when using deferred flushing in iommu drivers

Allow the iommu_unmap_fast to return newly freed page table pages and
pass the freelist to queue_iova in the dma-iommu ops path.

This is useful for iommu drivers (in this case the intel iommu driver)
which need to wait for the ioTLB to be flushed before newly
free/unmapped page table pages can be freed. This way we can still batch
ioTLB free operations and handle the freelists.

Signed-off-by: Tom Murphy <murphyt7@tcd.ie>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Tested-by: Logan Gunthorpe <logang@deltatee.com>
Link: https://lore.kernel.org/r/20201124082057.2614359-2-baolu.lu@linux.intel.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/dma-iommu.c   | 29 +++++++++++++++++-------
 drivers/iommu/intel/iommu.c | 55 +++++++++++++++++++++++++++++----------------
 include/linux/iommu.h       |  1 +
 3 files changed, 58 insertions(+), 27 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 0cbcd3fc3e7e..9c827a4d2207 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -49,6 +49,18 @@ struct iommu_dma_cookie {
 	struct iommu_domain		*fq_domain;
 };
 
+static void iommu_dma_entry_dtor(unsigned long data)
+{
+	struct page *freelist = (struct page *)data;
+
+	while (freelist) {
+		unsigned long p = (unsigned long)page_address(freelist);
+
+		freelist = freelist->freelist;
+		free_page(p);
+	}
+}
+
 static inline size_t cookie_msi_granule(struct iommu_dma_cookie *cookie)
 {
 	if (cookie->type == IOMMU_DMA_IOVA_COOKIE)
@@ -343,7 +355,7 @@ static int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 	if (!cookie->fq_domain && !iommu_domain_get_attr(domain,
 			DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE, &attr) && attr) {
 		if (init_iova_flush_queue(iovad, iommu_dma_flush_iotlb_all,
-					NULL))
+					  iommu_dma_entry_dtor))
 			pr_warn("iova flush queue initialization failed\n");
 		else
 			cookie->fq_domain = domain;
@@ -440,7 +452,7 @@ static dma_addr_t iommu_dma_alloc_iova(struct iommu_domain *domain,
 }
 
 static void iommu_dma_free_iova(struct iommu_dma_cookie *cookie,
-		dma_addr_t iova, size_t size)
+		dma_addr_t iova, size_t size, struct page *freelist)
 {
 	struct iova_domain *iovad = &cookie->iovad;
 
@@ -449,7 +461,8 @@ static void iommu_dma_free_iova(struct iommu_dma_cookie *cookie,
 		cookie->msi_iova -= size;
 	else if (cookie->fq_domain)	/* non-strict mode */
 		queue_iova(iovad, iova_pfn(iovad, iova),
-				size >> iova_shift(iovad), 0);
+				size >> iova_shift(iovad),
+				(unsigned long)freelist);
 	else
 		free_iova_fast(iovad, iova_pfn(iovad, iova),
 				size >> iova_shift(iovad));
@@ -474,7 +487,7 @@ static void __iommu_dma_unmap(struct device *dev, dma_addr_t dma_addr,
 
 	if (!cookie->fq_domain)
 		iommu_iotlb_sync(domain, &iotlb_gather);
-	iommu_dma_free_iova(cookie, dma_addr, size);
+	iommu_dma_free_iova(cookie, dma_addr, size, iotlb_gather.freelist);
 }
 
 static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
@@ -496,7 +509,7 @@ static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
 		return DMA_MAPPING_ERROR;
 
 	if (iommu_map_atomic(domain, iova, phys - iova_off, size, prot)) {
-		iommu_dma_free_iova(cookie, iova, size);
+		iommu_dma_free_iova(cookie, iova, size, NULL);
 		return DMA_MAPPING_ERROR;
 	}
 	return iova + iova_off;
@@ -649,7 +662,7 @@ out_unmap:
 out_free_sg:
 	sg_free_table(&sgt);
 out_free_iova:
-	iommu_dma_free_iova(cookie, iova, size);
+	iommu_dma_free_iova(cookie, iova, size, NULL);
 out_free_pages:
 	__iommu_dma_free_pages(pages, count);
 	return NULL;
@@ -900,7 +913,7 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 	return __finalise_sg(dev, sg, nents, iova);
 
 out_free_iova:
-	iommu_dma_free_iova(cookie, iova, iova_len);
+	iommu_dma_free_iova(cookie, iova, iova_len, NULL);
 out_restore_sg:
 	__invalidate_sg(sg, nents);
 	return 0;
@@ -1228,7 +1241,7 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
 	return msi_page;
 
 out_free_iova:
-	iommu_dma_free_iova(cookie, iova, size);
+	iommu_dma_free_iova(cookie, iova, size, NULL);
 out_free_page:
 	kfree(msi_page);
 	return NULL;
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 7b32703c0b47..fed0b3f0e25b 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -1243,17 +1243,17 @@ next:
    pages can only be freed after the IOTLB flush has been done. */
 static struct page *domain_unmap(struct dmar_domain *domain,
 				 unsigned long start_pfn,
-				 unsigned long last_pfn)
+				 unsigned long last_pfn,
+				 struct page *freelist)
 {
-	struct page *freelist;
-
 	BUG_ON(!domain_pfn_supported(domain, start_pfn));
 	BUG_ON(!domain_pfn_supported(domain, last_pfn));
 	BUG_ON(start_pfn > last_pfn);
 
 	/* we don't need lock here; nobody else touches the iova range */
 	freelist = dma_pte_clear_level(domain, agaw_to_level(domain->agaw),
-				       domain->pgd, 0, start_pfn, last_pfn, NULL);
+				       domain->pgd, 0, start_pfn, last_pfn,
+				       freelist);
 
 	/* free pgd */
 	if (start_pfn == 0 && last_pfn == DOMAIN_MAX_PFN(domain->gaw)) {
@@ -2011,7 +2011,8 @@ static void domain_exit(struct dmar_domain *domain)
 	if (domain->pgd) {
 		struct page *freelist;
 
-		freelist = domain_unmap(domain, 0, DOMAIN_MAX_PFN(domain->gaw));
+		freelist = domain_unmap(domain, 0,
+					DOMAIN_MAX_PFN(domain->gaw), NULL);
 		dma_free_pagelist(freelist);
 	}
 
@@ -3570,7 +3571,7 @@ static void intel_unmap(struct device *dev, dma_addr_t dev_addr, size_t size)
 	if (dev_is_pci(dev))
 		pdev = to_pci_dev(dev);
 
-	freelist = domain_unmap(domain, start_pfn, last_pfn);
+	freelist = domain_unmap(domain, start_pfn, last_pfn, NULL);
 	if (intel_iommu_strict || (pdev && pdev->untrusted) ||
 			!has_iova_flush_queue(&domain->iovad)) {
 		iommu_flush_iotlb_psi(iommu, domain, start_pfn,
@@ -4636,7 +4637,8 @@ static int intel_iommu_memory_notifier(struct notifier_block *nb,
 			struct page *freelist;
 
 			freelist = domain_unmap(si_domain,
-						start_vpfn, last_vpfn);
+						start_vpfn, last_vpfn,
+						NULL);
 
 			rcu_read_lock();
 			for_each_active_iommu(iommu, drhd)
@@ -5608,10 +5610,8 @@ static size_t intel_iommu_unmap(struct iommu_domain *domain,
 				struct iommu_iotlb_gather *gather)
 {
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
-	struct page *freelist = NULL;
 	unsigned long start_pfn, last_pfn;
-	unsigned int npages;
-	int iommu_id, level = 0;
+	int level = 0;
 
 	/* Cope with horrid API which requires us to unmap more than the
 	   size argument if it happens to be a large-page mapping. */
@@ -5623,22 +5623,38 @@ static size_t intel_iommu_unmap(struct iommu_domain *domain,
 	start_pfn = iova >> VTD_PAGE_SHIFT;
 	last_pfn = (iova + size - 1) >> VTD_PAGE_SHIFT;
 
-	freelist = domain_unmap(dmar_domain, start_pfn, last_pfn);
-
-	npages = last_pfn - start_pfn + 1;
-
-	for_each_domain_iommu(iommu_id, dmar_domain)
-		iommu_flush_iotlb_psi(g_iommus[iommu_id], dmar_domain,
-				      start_pfn, npages, !freelist, 0);
-
-	dma_free_pagelist(freelist);
+	gather->freelist = domain_unmap(dmar_domain, start_pfn,
+					last_pfn, gather->freelist);
 
 	if (dmar_domain->max_addr == iova + size)
 		dmar_domain->max_addr = iova;
 
+	iommu_iotlb_gather_add_page(domain, gather, iova, size);
+
 	return size;
 }
 
+static void intel_iommu_tlb_sync(struct iommu_domain *domain,
+				 struct iommu_iotlb_gather *gather)
+{
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+	unsigned long iova_pfn = IOVA_PFN(gather->start);
+	size_t size = gather->end - gather->start;
+	unsigned long start_pfn, last_pfn;
+	unsigned long nrpages;
+	int iommu_id;
+
+	nrpages = aligned_nrpages(gather->start, size);
+	start_pfn = mm_to_dma_pfn(iova_pfn);
+	last_pfn = start_pfn + nrpages - 1;
+
+	for_each_domain_iommu(iommu_id, dmar_domain)
+		iommu_flush_iotlb_psi(g_iommus[iommu_id], dmar_domain,
+				      start_pfn, nrpages, !gather->freelist, 0);
+
+	dma_free_pagelist(gather->freelist);
+}
+
 static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
 					    dma_addr_t iova)
 {
@@ -6098,6 +6114,7 @@ const struct iommu_ops intel_iommu_ops = {
 	.aux_get_pasid		= intel_iommu_aux_get_pasid,
 	.map			= intel_iommu_map,
 	.unmap			= intel_iommu_unmap,
+	.iotlb_sync		= intel_iommu_tlb_sync,
 	.iova_to_phys		= intel_iommu_iova_to_phys,
 	.probe_device		= intel_iommu_probe_device,
 	.probe_finalize		= intel_iommu_probe_finalize,
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index b95a6f8db6ff..e56bae327e35 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -180,6 +180,7 @@ struct iommu_iotlb_gather {
 	unsigned long		start;
 	unsigned long		end;
 	size_t			pgsize;
+	struct page		*freelist;
 };
 
 /**
-- 
cgit v1.2.3


From 230309d08b871e439f8618db3610f2cc9b5f7c72 Mon Sep 17 00:00:00 2001
From: Tom Murphy <murphyt7@tcd.ie>
Date: Tue, 24 Nov 2020 16:20:52 +0800
Subject: iommu: Add iommu_dma_free_cpu_cached_iovas()

Add a iommu_dma_free_cpu_cached_iovas function to allow drivers which
use the dma-iommu ops to free cached cpu iovas.

Signed-off-by: Tom Murphy <murphyt7@tcd.ie>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Tested-by: Logan Gunthorpe <logang@deltatee.com>
Link: https://lore.kernel.org/r/20201124082057.2614359-3-baolu.lu@linux.intel.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/dma-iommu.c | 9 +++++++++
 include/linux/dma-iommu.h | 8 ++++++++
 2 files changed, 17 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 9c827a4d2207..de521e22bafb 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -49,6 +49,15 @@ struct iommu_dma_cookie {
 	struct iommu_domain		*fq_domain;
 };
 
+void iommu_dma_free_cpu_cached_iovas(unsigned int cpu,
+		struct iommu_domain *domain)
+{
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct iova_domain *iovad = &cookie->iovad;
+
+	free_cpu_cached_iovas(cpu, iovad);
+}
+
 static void iommu_dma_entry_dtor(unsigned long data)
 {
 	struct page *freelist = (struct page *)data;
diff --git a/include/linux/dma-iommu.h b/include/linux/dma-iommu.h
index 2112f21f73d8..706b68d1359b 100644
--- a/include/linux/dma-iommu.h
+++ b/include/linux/dma-iommu.h
@@ -37,6 +37,9 @@ void iommu_dma_compose_msi_msg(struct msi_desc *desc,
 
 void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list);
 
+void iommu_dma_free_cpu_cached_iovas(unsigned int cpu,
+		struct iommu_domain *domain);
+
 #else /* CONFIG_IOMMU_DMA */
 
 struct iommu_domain;
@@ -78,5 +81,10 @@ static inline void iommu_dma_get_resv_regions(struct device *dev, struct list_he
 {
 }
 
+static inline void iommu_dma_free_cpu_cached_iovas(unsigned int cpu,
+		struct iommu_domain *domain)
+{
+}
+
 #endif	/* CONFIG_IOMMU_DMA */
 #endif	/* __DMA_IOMMU_H */
-- 
cgit v1.2.3


From a7656ecf825ac0434a5e7bf108ec1a56b65ee5e4 Mon Sep 17 00:00:00 2001
From: Sai Prakash Ranjan <saiprakash.ranjan@codeaurora.org>
Date: Wed, 25 Nov 2020 12:30:10 +0530
Subject: iommu/io-pgtable: Add a domain attribute for pagetable configuration

Add a new iommu domain attribute DOMAIN_ATTR_IO_PGTABLE_CFG
for pagetable configuration which initially will be used to
set quirks like for system cache aka last level cache to be
used by client drivers like GPU to set right attributes for
caching the hardware pagetables into the system cache and
later can be extended to include other page table configuration
data.

Signed-off-by: Sai Prakash Ranjan <saiprakash.ranjan@codeaurora.org>
Link: https://lore.kernel.org/r/9190aa16f378fc0a7f8e57b2b9f60b033e7eeb4f.1606287059.git.saiprakash.ranjan@codeaurora.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 include/linux/io-pgtable.h | 4 ++++
 include/linux/iommu.h      | 1 +
 2 files changed, 5 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 4cde111e425b..215fd9d69540 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -208,6 +208,10 @@ struct io_pgtable {
 
 #define io_pgtable_ops_to_pgtable(x) container_of((x), struct io_pgtable, ops)
 
+struct io_pgtable_domain_attr {
+	unsigned long quirks;
+};
+
 static inline void io_pgtable_tlb_flush_all(struct io_pgtable *iop)
 {
 	iop->cfg.tlb->tlb_flush_all(iop->cookie);
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index b95a6f8db6ff..ffaa389ea128 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -118,6 +118,7 @@ enum iommu_attr {
 	DOMAIN_ATTR_FSL_PAMUV1,
 	DOMAIN_ATTR_NESTING,	/* two stages of translation */
 	DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE,
+	DOMAIN_ATTR_IO_PGTABLE_CFG,
 	DOMAIN_ATTR_MAX,
 };
 
-- 
cgit v1.2.3


From e67890c97944b9962cf8c140a7f8077ed643b7d7 Mon Sep 17 00:00:00 2001
From: Sai Prakash Ranjan <saiprakash.ranjan@codeaurora.org>
Date: Wed, 25 Nov 2020 12:30:11 +0530
Subject: iommu/io-pgtable-arm: Add support to use system cache

Add a quirk IO_PGTABLE_QUIRK_ARM_OUTER_WBWA to override
the outer-cacheability attributes set in the TCR for a
non-coherent page table walker when using system cache.

Signed-off-by: Sai Prakash Ranjan <saiprakash.ranjan@codeaurora.org>
Link: https://lore.kernel.org/r/f818676b4a2a9ad1edb92721947d47db41ed6a7c.1606287059.git.saiprakash.ranjan@codeaurora.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/io-pgtable-arm.c | 10 ++++++++--
 include/linux/io-pgtable.h     |  4 ++++
 2 files changed, 12 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index a7a9bc08dcd1..7c9ea9d7874a 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -761,7 +761,8 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 
 	if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS |
 			    IO_PGTABLE_QUIRK_NON_STRICT |
-			    IO_PGTABLE_QUIRK_ARM_TTBR1))
+			    IO_PGTABLE_QUIRK_ARM_TTBR1 |
+			    IO_PGTABLE_QUIRK_ARM_OUTER_WBWA))
 		return NULL;
 
 	data = arm_lpae_alloc_pgtable(cfg);
@@ -773,10 +774,15 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 		tcr->sh = ARM_LPAE_TCR_SH_IS;
 		tcr->irgn = ARM_LPAE_TCR_RGN_WBWA;
 		tcr->orgn = ARM_LPAE_TCR_RGN_WBWA;
+		if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_OUTER_WBWA)
+			goto out_free_data;
 	} else {
 		tcr->sh = ARM_LPAE_TCR_SH_OS;
 		tcr->irgn = ARM_LPAE_TCR_RGN_NC;
-		tcr->orgn = ARM_LPAE_TCR_RGN_NC;
+		if (!(cfg->quirks & IO_PGTABLE_QUIRK_ARM_OUTER_WBWA))
+			tcr->orgn = ARM_LPAE_TCR_RGN_NC;
+		else
+			tcr->orgn = ARM_LPAE_TCR_RGN_WBWA;
 	}
 
 	tg1 = cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1;
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 215fd9d69540..fb4d5a763e0c 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -86,6 +86,9 @@ struct io_pgtable_cfg {
 	 *
 	 * IO_PGTABLE_QUIRK_ARM_TTBR1: (ARM LPAE format) Configure the table
 	 *	for use in the upper half of a split address space.
+	 *
+	 * IO_PGTABLE_QUIRK_ARM_OUTER_WBWA: Override the outer-cacheability
+	 *	attributes set in the TCR for a non-coherent page-table walker.
 	 */
 	#define IO_PGTABLE_QUIRK_ARM_NS		BIT(0)
 	#define IO_PGTABLE_QUIRK_NO_PERMS	BIT(1)
@@ -93,6 +96,7 @@ struct io_pgtable_cfg {
 	#define IO_PGTABLE_QUIRK_ARM_MTK_EXT	BIT(3)
 	#define IO_PGTABLE_QUIRK_NON_STRICT	BIT(4)
 	#define IO_PGTABLE_QUIRK_ARM_TTBR1	BIT(5)
+	#define IO_PGTABLE_QUIRK_ARM_OUTER_WBWA	BIT(6)
 	unsigned long			quirks;
 	unsigned long			pgsize_bitmap;
 	unsigned int			ias;
-- 
cgit v1.2.3


From 0801a0073f86e020987acbbd96b50f9c85d79de8 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 23 Nov 2020 11:23:14 +0100
Subject: module: drop version-attribute alignment

Commit 98562ad8cb03 ("module: explicitly align module_version_attribute
structure") added an alignment attribute to the struct
module_version_attribute type in order to fix an alignment issue on m68k
where the structure is 2-byte aligned while MODULE_VERSION() forced the
__modver section entries to be 4-byte aligned (sizeof(void *)).

This was essentially an alternative fix to the problem addressed by
b4bc842802db ("module: deal with alignment issues in built-in module
versions") which used the array-of-pointer trick to prevent gcc from
increasing alignment of the version attribute entries. And with the
pointer indirection in place there's no need to increase the alignment
of the type.

Link: https://lore.kernel.org/lkml/20201103175711.10731-1-johan@kernel.org
Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: Jessica Yu <jeyu@kernel.org>
---
 include/linux/module.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/module.h b/include/linux/module.h
index 7ccdf87f376f..293250958512 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -66,7 +66,7 @@ struct module_version_attribute {
 	struct module_attribute mattr;
 	const char *module_name;
 	const char *version;
-} __attribute__ ((__aligned__(sizeof(void *))));
+};
 
 extern ssize_t __modver_version_show(struct module_attribute *,
 				     struct module_kobject *, char *);
-- 
cgit v1.2.3


From b112082c8930e7aa72422484b2d31d3aa06f58bc Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 23 Nov 2020 11:23:15 +0100
Subject: module: simplify version-attribute handling

Instead of using the array-of-pointers trick to avoid having gcc mess up
the built-in module-version array stride, specify type alignment when
declaring entries to prevent gcc from increasing alignment.

This is essentially an alternative (one-line) fix to the problem
addressed by commit b4bc842802db ("module: deal with alignment issues in
built-in module versions").

gcc can increase the alignment of larger objects with static extent as
an optimisation, but this can be suppressed by using the aligned
attribute when declaring variables.

Note that we have been relying on this behaviour for kernel parameters
for 16 years and it indeed hasn't changed since the introduction of the
aligned attribute in gcc-3.1.

Link: https://lore.kernel.org/lkml/20201103175711.10731-1-johan@kernel.org
Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: Jessica Yu <jeyu@kernel.org>
---
 include/linux/module.h | 26 +++++++++++++-------------
 kernel/params.c        | 10 ++++------
 2 files changed, 17 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/module.h b/include/linux/module.h
index 293250958512..5958075ea3f4 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -266,20 +266,20 @@ extern typeof(name) __mod_##type##__##name##_device_table		\
 #else
 #define MODULE_VERSION(_version)					\
 	MODULE_INFO(version, _version);					\
-	static struct module_version_attribute ___modver_attr = {	\
-		.mattr	= {						\
-			.attr	= {					\
-				.name	= "version",			\
-				.mode	= S_IRUGO,			\
+	static struct module_version_attribute __modver_attr		\
+		__used __section("__modver")				\
+		__aligned(__alignof__(struct module_version_attribute)) \
+		= {							\
+			.mattr	= {					\
+				.attr	= {				\
+					.name	= "version",		\
+					.mode	= S_IRUGO,		\
+				},					\
+				.show	= __modver_version_show,	\
 			},						\
-			.show	= __modver_version_show,		\
-		},							\
-		.module_name	= KBUILD_MODNAME,			\
-		.version	= _version,				\
-	};								\
-	static const struct module_version_attribute			\
-	__used __section("__modver")					\
-	* __moduleparam_const __modver_attr = &___modver_attr
+			.module_name	= KBUILD_MODNAME,		\
+			.version	= _version,			\
+		};
 #endif
 
 /* Optional firmware file (or files) needed by the module
diff --git a/kernel/params.c b/kernel/params.c
index 3835fb82c64b..aa7d6f2213f1 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -843,18 +843,16 @@ ssize_t __modver_version_show(struct module_attribute *mattr,
 	return scnprintf(buf, PAGE_SIZE, "%s\n", vattr->version);
 }
 
-extern const struct module_version_attribute *__start___modver[];
-extern const struct module_version_attribute *__stop___modver[];
+extern const struct module_version_attribute __start___modver[];
+extern const struct module_version_attribute __stop___modver[];
 
 static void __init version_sysfs_builtin(void)
 {
-	const struct module_version_attribute **p;
+	const struct module_version_attribute *vattr;
 	struct module_kobject *mk;
 	int err;
 
-	for (p = __start___modver; p < __stop___modver; p++) {
-		const struct module_version_attribute *vattr = *p;
-
+	for (vattr = __start___modver; vattr < __stop___modver; vattr++) {
 		mk = locate_module_kobject(vattr->module_name);
 		if (mk) {
 			err = sysfs_create_file(&mk->kobj, &vattr->mattr.attr);
-- 
cgit v1.2.3


From 8d6615f1fccc4f39d7d3dcf286b33e8a1e833d2b Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 23 Nov 2020 11:23:17 +0100
Subject: params: drop redundant "unused" attributes

Drop the redundant "unused" attributes from module-parameter structures
already marked "used".

Link: https://lore.kernel.org/lkml/20201103175711.10731-1-johan@kernel.org
Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: Jessica Yu <jeyu@kernel.org>
---
 include/linux/moduleparam.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index 6388eb9734a5..742074ad9f6e 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -22,7 +22,7 @@
 
 #define __MODULE_INFO(tag, name, info)					  \
 static const char __UNIQUE_ID(name)[]					  \
-  __used __section(".modinfo") __attribute__((unused, aligned(1)))	  \
+  __used __section(".modinfo") __attribute__((aligned(1)))		  \
   = __MODULE_INFO_PREFIX __stringify(tag) "=" info
 
 #define __MODULE_PARM_TYPE(name, _type)					  \
@@ -289,7 +289,7 @@ struct kparam_array
 	static const char __param_str_##name[] = prefix #name;		\
 	static struct kernel_param __moduleparam_const __param_##name	\
 	__used								\
-    __section("__param") __attribute__ ((unused, aligned(sizeof(void *)))) \
+	__section("__param") __attribute__ ((aligned(sizeof(void *))))  \
 	= { __param_str_##name, THIS_MODULE, ops,			\
 	    VERIFY_OCTAL_PERMISSIONS(perm), level, flags, { arg } }
 
-- 
cgit v1.2.3


From fe2f4fe139b321a38daafc715aeb7d21d9e8e5ad Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 23 Nov 2020 11:23:18 +0100
Subject: params: use type alignment for kernel parameters

Specify type alignment for kernel parameters instead of sizeof(void *).

The alignment attribute is used to prevent gcc from increasing the
alignment of objects with static extent as an optimisation, something
which would mess up the __param array stride.

Using __alignof__(struct kernel_param) rather than sizeof(void *) is
preferred since it better indicates why it is there and doesn't break
should the type size or alignment change.

Note that on m68k the alignment of struct kernel_param is actually two
and that adding a 1- or 2-byte field to the 20-byte struct would cause a
breakage with the current 4-byte alignment.

Link: https://lore.kernel.org/lkml/20201103175711.10731-1-johan@kernel.org
Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: Jessica Yu <jeyu@kernel.org>
---
 include/linux/moduleparam.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index 742074ad9f6e..15ecc6cc3a3b 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -288,8 +288,8 @@ struct kparam_array
 	/* Default value instead of permissions? */			\
 	static const char __param_str_##name[] = prefix #name;		\
 	static struct kernel_param __moduleparam_const __param_##name	\
-	__used								\
-	__section("__param") __attribute__ ((aligned(sizeof(void *))))  \
+	__used __section("__param")					\
+	__aligned(__alignof__(struct kernel_param))			\
 	= { __param_str_##name, THIS_MODULE, ops,			\
 	    VERIFY_OCTAL_PERMISSIONS(perm), level, flags, { arg } }
 
-- 
cgit v1.2.3


From 2aec389e19150ed3bf67ab708f2435563f76050f Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 23 Nov 2020 11:23:19 +0100
Subject: params: clean up module-param macros

Clean up the module-param macros by adding some indentation and using
the __aligned() macro to improve readability.

Link: https://lore.kernel.org/lkml/20201103175711.10731-1-johan@kernel.org
Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: Jessica Yu <jeyu@kernel.org>
---
 include/linux/moduleparam.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index 15ecc6cc3a3b..eed280fae433 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -21,12 +21,12 @@
 #define MAX_PARAM_PREFIX_LEN (64 - sizeof(unsigned long))
 
 #define __MODULE_INFO(tag, name, info)					  \
-static const char __UNIQUE_ID(name)[]					  \
-  __used __section(".modinfo") __attribute__((aligned(1)))		  \
-  = __MODULE_INFO_PREFIX __stringify(tag) "=" info
+	static const char __UNIQUE_ID(name)[]				  \
+		__used __section(".modinfo") __aligned(1)		  \
+		= __MODULE_INFO_PREFIX __stringify(tag) "=" info
 
 #define __MODULE_PARM_TYPE(name, _type)					  \
-  __MODULE_INFO(parmtype, name##type, #name ":" _type)
+	__MODULE_INFO(parmtype, name##type, #name ":" _type)
 
 /* One for each parameter, describing how to use it.  Some files do
    multiple of these per line, so can't just use MODULE_INFO. */
-- 
cgit v1.2.3


From 367c820ef08082e68df8a3bc12e62393af21e4b5 Mon Sep 17 00:00:00 2001
From: Sumit Garg <sumit.garg@linaro.org>
Date: Wed, 7 Oct 2020 14:21:43 +0530
Subject: arm64: Enable perf events based hard lockup detector

With the recent feature added to enable perf events to use pseudo NMIs
as interrupts on platforms which support GICv3 or later, its now been
possible to enable hard lockup detector (or NMI watchdog) on arm64
platforms. So enable corresponding support.

One thing to note here is that normally lockup detector is initialized
just after the early initcalls but PMU on arm64 comes up much later as
device_initcall(). So we need to re-initialize lockup detection once
PMU has been initialized.

Signed-off-by: Sumit Garg <sumit.garg@linaro.org>
Acked-by: Alexandru Elisei <alexandru.elisei@arm.com>
Link: https://lore.kernel.org/r/1602060704-10921-1-git-send-email-sumit.garg@linaro.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/Kconfig             |  2 ++
 arch/arm64/kernel/perf_event.c | 41 +++++++++++++++++++++++++++++++++++++++--
 drivers/perf/arm_pmu.c         |  5 +++++
 include/linux/perf/arm_pmu.h   |  2 ++
 4 files changed, 48 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 1515f6f153a0..7d3440770b14 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -170,6 +170,8 @@ config ARM64
 	select HAVE_NMI
 	select HAVE_PATA_PLATFORM
 	select HAVE_PERF_EVENTS
+	select HAVE_PERF_EVENTS_NMI if ARM64_PSEUDO_NMI
+	select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_REGS_AND_STACK_ACCESS_API
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 3605f77ad4df..38bb07eff872 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -23,6 +23,8 @@
 #include <linux/platform_device.h>
 #include <linux/sched_clock.h>
 #include <linux/smp.h>
+#include <linux/nmi.h>
+#include <linux/cpufreq.h>
 
 /* ARMv8 Cortex-A53 specific event types. */
 #define ARMV8_A53_PERFCTR_PREF_LINEFILL				0xC2
@@ -1248,10 +1250,21 @@ static struct platform_driver armv8_pmu_driver = {
 
 static int __init armv8_pmu_driver_init(void)
 {
+	int ret;
+
 	if (acpi_disabled)
-		return platform_driver_register(&armv8_pmu_driver);
+		ret = platform_driver_register(&armv8_pmu_driver);
 	else
-		return arm_pmu_acpi_probe(armv8_pmuv3_init);
+		ret = arm_pmu_acpi_probe(armv8_pmuv3_init);
+
+	/*
+	 * Try to re-initialize lockup detector after PMU init in
+	 * case PMU events are triggered via NMIs.
+	 */
+	if (ret == 0 && arm_pmu_irq_is_nmi())
+		lockup_detector_init();
+
+	return ret;
 }
 device_initcall(armv8_pmu_driver_init)
 
@@ -1309,3 +1322,27 @@ void arch_perf_update_userpage(struct perf_event *event,
 	userpg->cap_user_time_zero = 1;
 	userpg->cap_user_time_short = 1;
 }
+
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF
+/*
+ * Safe maximum CPU frequency in case a particular platform doesn't implement
+ * cpufreq driver. Although, architecture doesn't put any restrictions on
+ * maximum frequency but 5 GHz seems to be safe maximum given the available
+ * Arm CPUs in the market which are clocked much less than 5 GHz. On the other
+ * hand, we can't make it much higher as it would lead to a large hard-lockup
+ * detection timeout on parts which are running slower (eg. 1GHz on
+ * Developerbox) and doesn't possess a cpufreq driver.
+ */
+#define SAFE_MAX_CPU_FREQ	5000000000UL // 5 GHz
+u64 hw_nmi_get_sample_period(int watchdog_thresh)
+{
+	unsigned int cpu = smp_processor_id();
+	unsigned long max_cpu_freq;
+
+	max_cpu_freq = cpufreq_get_hw_max_freq(cpu) * 1000UL;
+	if (!max_cpu_freq)
+		max_cpu_freq = SAFE_MAX_CPU_FREQ;
+
+	return (u64)max_cpu_freq * watchdog_thresh;
+}
+#endif
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index cb2f55f450e4..794a37d50853 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -726,6 +726,11 @@ static int armpmu_get_cpu_irq(struct arm_pmu *pmu, int cpu)
 	return per_cpu(hw_events->irq, cpu);
 }
 
+bool arm_pmu_irq_is_nmi(void)
+{
+	return has_nmi;
+}
+
 /*
  * PMU hardware loses all context when a CPU goes offline.
  * When a CPU is hotplugged back in, since some hardware registers are
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index 505480217cf1..bf7966776c55 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -163,6 +163,8 @@ int arm_pmu_acpi_probe(armpmu_init_fn init_fn);
 static inline int arm_pmu_acpi_probe(armpmu_init_fn init_fn) { return 0; }
 #endif
 
+bool arm_pmu_irq_is_nmi(void);
+
 /* Internal functions only for core arm_pmu code */
 struct arm_pmu *armpmu_alloc(void);
 struct arm_pmu *armpmu_alloc_atomic(void);
-- 
cgit v1.2.3


From 63653368c25ff0b1b1aaf045c97ea87bd8c16123 Mon Sep 17 00:00:00 2001
From: Jeffle Xu <jefflexu@linux.alibaba.com>
Date: Wed, 25 Nov 2020 14:58:17 +0800
Subject: block: remove unused BIO_SPLIT_ENTRIES

Since commit 4b1faf931650 ("block: Kill bio_pair_split()"), there's
no user of BIO_SPLIT_ENTRIES anymore.

Signed-off-by: Jeffle Xu <jefflexu@linux.alibaba.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/bio.h | 6 ------
 1 file changed, 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bio.h b/include/linux/bio.h
index c6d765382926..ecf67108f091 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -711,12 +711,6 @@ static inline bool bioset_initialized(struct bio_set *bs)
 	return bs->bio_slab != NULL;
 }
 
-/*
- * a small number of entries is fine, not going to be performance critical.
- * basically we just need to survive
- */
-#define BIO_SPLIT_ENTRIES 2
-
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 
 #define bip_for_each_vec(bvl, bip, iter)				\
-- 
cgit v1.2.3


From 6527b938426f7fa66051273568d234b1fe01a15b Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Mon, 23 Nov 2020 17:38:17 +0200
Subject: net: phy: remove the .did_interrupt() and .ack_interrupt() callback

Now that all the PHY drivers have been migrated to directly implement
the generic .handle_interrupt() callback for a seamless support of
shared IRQs and all the .config_inter() implementations clear any
pending interrupts, we can safely remove the two callbacks.

With this patch, phylib has a proper support for shared IRQs (and not
just for multi-PHY devices. A PHY driver must implement both the
.handle_interrupt() and .config_intr() callbacks for the IRQs to be
actually used.

Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy.c        | 48 ++------------------------------------------
 drivers/net/phy/phy_device.c |  2 +-
 include/linux/phy.h          | 19 ++++--------------
 3 files changed, 7 insertions(+), 62 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index dce86bad8231..45f75533c47c 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -113,23 +113,6 @@ void phy_print_status(struct phy_device *phydev)
 }
 EXPORT_SYMBOL(phy_print_status);
 
-/**
- * phy_clear_interrupt - Ack the phy device's interrupt
- * @phydev: the phy_device struct
- *
- * If the @phydev driver has an ack_interrupt function, call it to
- * ack and clear the phy device's interrupt.
- *
- * Returns 0 on success or < 0 on error.
- */
-static int phy_clear_interrupt(struct phy_device *phydev)
-{
-	if (phydev->drv->ack_interrupt)
-		return phydev->drv->ack_interrupt(phydev);
-
-	return 0;
-}
-
 /**
  * phy_config_interrupt - configure the PHY device for the requested interrupts
  * @phydev: the phy_device struct
@@ -943,15 +926,8 @@ EXPORT_SYMBOL(phy_error);
  */
 int phy_disable_interrupts(struct phy_device *phydev)
 {
-	int err;
-
 	/* Disable PHY interrupts */
-	err = phy_config_interrupt(phydev, PHY_INTERRUPT_DISABLED);
-	if (err)
-		return err;
-
-	/* Clear the interrupt */
-	return phy_clear_interrupt(phydev);
+	return phy_config_interrupt(phydev, PHY_INTERRUPT_DISABLED);
 }
 
 /**
@@ -966,22 +942,7 @@ static irqreturn_t phy_interrupt(int irq, void *phy_dat)
 	struct phy_device *phydev = phy_dat;
 	struct phy_driver *drv = phydev->drv;
 
-	if (drv->handle_interrupt)
-		return drv->handle_interrupt(phydev);
-
-	if (drv->did_interrupt && !drv->did_interrupt(phydev))
-		return IRQ_NONE;
-
-	/* reschedule state queue work to run as soon as possible */
-	phy_trigger_machine(phydev);
-
-	/* did_interrupt() may have cleared the interrupt already */
-	if (!drv->did_interrupt && phy_clear_interrupt(phydev)) {
-		phy_error(phydev);
-		return IRQ_NONE;
-	}
-
-	return IRQ_HANDLED;
+	return drv->handle_interrupt(phydev);
 }
 
 /**
@@ -990,11 +951,6 @@ static irqreturn_t phy_interrupt(int irq, void *phy_dat)
  */
 static int phy_enable_interrupts(struct phy_device *phydev)
 {
-	int err = phy_clear_interrupt(phydev);
-
-	if (err < 0)
-		return err;
-
 	return phy_config_interrupt(phydev, PHY_INTERRUPT_ENABLED);
 }
 
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 81f672911305..80c2e646c093 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -2826,7 +2826,7 @@ EXPORT_SYMBOL(phy_get_internal_delay);
 
 static bool phy_drv_supports_irq(struct phy_driver *phydrv)
 {
-	return phydrv->config_intr && (phydrv->ack_interrupt || phydrv->handle_interrupt);
+	return phydrv->config_intr && phydrv->handle_interrupt;
 }
 
 /**
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 8849a00a093f..381a95732b6a 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -743,18 +743,11 @@ struct phy_driver {
 	/** @read_status: Determines the negotiated speed and duplex */
 	int (*read_status)(struct phy_device *phydev);
 
-	/** @ack_interrupt: Clears any pending interrupts */
-	int (*ack_interrupt)(struct phy_device *phydev);
-
-	/** @config_intr: Enables or disables interrupts */
-	int (*config_intr)(struct phy_device *phydev);
-
-	/**
-	 * @did_interrupt: Checks if the PHY generated an interrupt.
-	 * For multi-PHY devices with shared PHY interrupt pin
-	 * Set interrupt bits have to be cleared.
+	/** @config_intr: Enables or disables interrupts.
+	 * It should also clear any pending interrupts prior to enabling the
+	 * IRQs and after disabling them.
 	 */
-	int (*did_interrupt)(struct phy_device *phydev);
+	int (*config_intr)(struct phy_device *phydev);
 
 	/** @handle_interrupt: Override default interrupt handling */
 	irqreturn_t (*handle_interrupt)(struct phy_device *phydev);
@@ -1487,10 +1480,6 @@ static inline int genphy_config_aneg(struct phy_device *phydev)
 	return __genphy_config_aneg(phydev, false);
 }
 
-static inline int genphy_no_ack_interrupt(struct phy_device *phydev)
-{
-	return 0;
-}
 static inline int genphy_no_config_intr(struct phy_device *phydev)
 {
 	return 0;
-- 
cgit v1.2.3


From 403319be5de51167cd70ddf594b76c95e6d26844 Mon Sep 17 00:00:00 2001
From: KP Singh <kpsingh@google.com>
Date: Tue, 24 Nov 2020 15:12:08 +0000
Subject: ima: Implement ima_inode_hash

This is in preparation to add a helper for BPF LSM programs to use
IMA hashes when attached to LSM hooks. There are LSM hooks like
inode_unlink which do not have a struct file * argument and cannot
use the existing ima_file_hash API.

An inode based API is, therefore, useful in LSM based detections like an
executable trying to delete itself which rely on the inode_unlink LSM
hook.

Moreover, the ima_file_hash function does nothing with the struct file
pointer apart from calling file_inode on it and converting it to an
inode.

Signed-off-by: KP Singh <kpsingh@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yhs@fb.com>
Acked-by: Mimi Zohar <zohar@linux.ibm.com>
Link: https://lore.kernel.org/bpf/20201124151210.1081188-2-kpsingh@chromium.org
---
 include/linux/ima.h               |  6 +++
 security/integrity/ima/ima_main.c | 78 +++++++++++++++++++++++++++------------
 2 files changed, 60 insertions(+), 24 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ima.h b/include/linux/ima.h
index 8fa7bcfb2da2..7233a2751754 100644
--- a/include/linux/ima.h
+++ b/include/linux/ima.h
@@ -29,6 +29,7 @@ extern int ima_post_read_file(struct file *file, void *buf, loff_t size,
 			      enum kernel_read_file_id id);
 extern void ima_post_path_mknod(struct dentry *dentry);
 extern int ima_file_hash(struct file *file, char *buf, size_t buf_size);
+extern int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size);
 extern void ima_kexec_cmdline(int kernel_fd, const void *buf, int size);
 
 #ifdef CONFIG_IMA_KEXEC
@@ -115,6 +116,11 @@ static inline int ima_file_hash(struct file *file, char *buf, size_t buf_size)
 	return -EOPNOTSUPP;
 }
 
+static inline int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline void ima_kexec_cmdline(int kernel_fd, const void *buf, int size) {}
 #endif /* CONFIG_IMA */
 
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index 2d1af8899cab..cb2deaa188e7 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -501,37 +501,14 @@ int ima_file_check(struct file *file, int mask)
 }
 EXPORT_SYMBOL_GPL(ima_file_check);
 
-/**
- * ima_file_hash - return the stored measurement if a file has been hashed and
- * is in the iint cache.
- * @file: pointer to the file
- * @buf: buffer in which to store the hash
- * @buf_size: length of the buffer
- *
- * On success, return the hash algorithm (as defined in the enum hash_algo).
- * If buf is not NULL, this function also outputs the hash into buf.
- * If the hash is larger than buf_size, then only buf_size bytes will be copied.
- * It generally just makes sense to pass a buffer capable of holding the largest
- * possible hash: IMA_MAX_DIGEST_SIZE.
- * The file hash returned is based on the entire file, including the appended
- * signature.
- *
- * If IMA is disabled or if no measurement is available, return -EOPNOTSUPP.
- * If the parameters are incorrect, return -EINVAL.
- */
-int ima_file_hash(struct file *file, char *buf, size_t buf_size)
+static int __ima_inode_hash(struct inode *inode, char *buf, size_t buf_size)
 {
-	struct inode *inode;
 	struct integrity_iint_cache *iint;
 	int hash_algo;
 
-	if (!file)
-		return -EINVAL;
-
 	if (!ima_policy_flag)
 		return -EOPNOTSUPP;
 
-	inode = file_inode(file);
 	iint = integrity_iint_find(inode);
 	if (!iint)
 		return -EOPNOTSUPP;
@@ -558,8 +535,61 @@ int ima_file_hash(struct file *file, char *buf, size_t buf_size)
 
 	return hash_algo;
 }
+
+/**
+ * ima_file_hash - return the stored measurement if a file has been hashed and
+ * is in the iint cache.
+ * @file: pointer to the file
+ * @buf: buffer in which to store the hash
+ * @buf_size: length of the buffer
+ *
+ * On success, return the hash algorithm (as defined in the enum hash_algo).
+ * If buf is not NULL, this function also outputs the hash into buf.
+ * If the hash is larger than buf_size, then only buf_size bytes will be copied.
+ * It generally just makes sense to pass a buffer capable of holding the largest
+ * possible hash: IMA_MAX_DIGEST_SIZE.
+ * The file hash returned is based on the entire file, including the appended
+ * signature.
+ *
+ * If IMA is disabled or if no measurement is available, return -EOPNOTSUPP.
+ * If the parameters are incorrect, return -EINVAL.
+ */
+int ima_file_hash(struct file *file, char *buf, size_t buf_size)
+{
+	if (!file)
+		return -EINVAL;
+
+	return __ima_inode_hash(file_inode(file), buf, buf_size);
+}
 EXPORT_SYMBOL_GPL(ima_file_hash);
 
+/**
+ * ima_inode_hash - return the stored measurement if the inode has been hashed
+ * and is in the iint cache.
+ * @inode: pointer to the inode
+ * @buf: buffer in which to store the hash
+ * @buf_size: length of the buffer
+ *
+ * On success, return the hash algorithm (as defined in the enum hash_algo).
+ * If buf is not NULL, this function also outputs the hash into buf.
+ * If the hash is larger than buf_size, then only buf_size bytes will be copied.
+ * It generally just makes sense to pass a buffer capable of holding the largest
+ * possible hash: IMA_MAX_DIGEST_SIZE.
+ * The hash returned is based on the entire contents, including the appended
+ * signature.
+ *
+ * If IMA is disabled or if no measurement is available, return -EOPNOTSUPP.
+ * If the parameters are incorrect, return -EINVAL.
+ */
+int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size)
+{
+	if (!inode)
+		return -EINVAL;
+
+	return __ima_inode_hash(inode, buf, buf_size);
+}
+EXPORT_SYMBOL_GPL(ima_inode_hash);
+
 /**
  * ima_post_create_tmpfile - mark newly created tmpfile as new
  * @file : newly created tmpfile
-- 
cgit v1.2.3


From 8b5536ad1216c47fb9b37ef2cd0cfa70d79d4645 Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Tue, 24 Nov 2020 18:49:28 +0800
Subject: lockdep: Introduce in_softirq lockdep assert

The current semantic for napi_consume_skb() is that caller need
to provide non-zero budget when calling from NAPI context, and
breaking this semantic will cause hard to debug problem, because
_kfree_skb_defer() need to run in atomic context in order to push
the skb to the particular cpu' napi_alloc_cache atomically.

So add the lockdep_assert_in_softirq() to assert when the running
context is not in_softirq, in_softirq means softirq is serving or
BH is disabled, which has a ambiguous semantics due to the BH
disabled confusion, so add a comment to emphasize that.

And the softirq context can be interrupted by hard IRQ or NMI
context, lockdep_assert_in_softirq() need to assert about hard
IRQ or NMI context too.

Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/lockdep.h | 11 +++++++++++
 1 file changed, 11 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index f5594879175a..92771bc1791f 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -594,6 +594,16 @@ do {									\
 		      this_cpu_read(hardirqs_enabled)));		\
 } while (0)
 
+/*
+ * Acceptable for protecting per-CPU resources accessed from BH.
+ * Much like in_softirq() - semantics are ambiguous, use carefully.
+ */
+#define lockdep_assert_in_softirq()					\
+do {									\
+	WARN_ON_ONCE(__lockdep_enabled			&&		\
+		     (!in_softirq() || in_irq() || in_nmi()));		\
+} while (0)
+
 #else
 # define might_lock(lock) do { } while (0)
 # define might_lock_read(lock) do { } while (0)
@@ -605,6 +615,7 @@ do {									\
 
 # define lockdep_assert_preemption_enabled() do { } while (0)
 # define lockdep_assert_preemption_disabled() do { } while (0)
+# define lockdep_assert_in_softirq() do { } while (0)
 #endif
 
 #ifdef CONFIG_PROVE_RAW_LOCK_NESTING
-- 
cgit v1.2.3


From 4c1ad562d303526b5d9b49f5e0d72da13ef78dec Mon Sep 17 00:00:00 2001
From: Suman Anna <s-anna@ti.com>
Date: Fri, 20 Nov 2020 21:20:42 -0600
Subject: remoteproc: Add a rproc_set_firmware() API

A new API, rproc_set_firmware() is added to allow the remoteproc platform
drivers and remoteproc client drivers to be able to configure a custom
firmware name that is different from the default name used during
remoteproc registration. This function is being introduced to provide
a kernel-level equivalent of the current sysfs interface to remoteproc
client drivers, and can only change firmwares when the remoteproc is
offline. This allows some remoteproc drivers to choose different firmwares
at runtime based on the functionality the remote processor is providing.
The TI PRU Ethernet driver will be an example of such usage as it
requires to use different firmwares for different supported protocols.

Also, update the firmware_store() function used by the sysfs interface
to reuse this function to avoid code duplication.

Reviewed-by: Rishabh Bhatnagar <rishabhb@codeaurora.org>
Signed-off-by: Suman Anna <s-anna@ti.com>
Link: https://lore.kernel.org/r/20201121032042.6195-1-s-anna@ti.com
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 drivers/remoteproc/remoteproc_core.c  | 63 +++++++++++++++++++++++++++++++++++
 drivers/remoteproc/remoteproc_sysfs.c | 33 ++----------------
 include/linux/remoteproc.h            |  1 +
 3 files changed, 66 insertions(+), 31 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c
index dab2c0f5caf0..46c2937ebea9 100644
--- a/drivers/remoteproc/remoteproc_core.c
+++ b/drivers/remoteproc/remoteproc_core.c
@@ -1934,6 +1934,69 @@ struct rproc *rproc_get_by_phandle(phandle phandle)
 #endif
 EXPORT_SYMBOL(rproc_get_by_phandle);
 
+/**
+ * rproc_set_firmware() - assign a new firmware
+ * @rproc: rproc handle to which the new firmware is being assigned
+ * @fw_name: new firmware name to be assigned
+ *
+ * This function allows remoteproc drivers or clients to configure a custom
+ * firmware name that is different from the default name used during remoteproc
+ * registration. The function does not trigger a remote processor boot,
+ * only sets the firmware name used for a subsequent boot. This function
+ * should also be called only when the remote processor is offline.
+ *
+ * This allows either the userspace to configure a different name through
+ * sysfs or a kernel-level remoteproc or a remoteproc client driver to set
+ * a specific firmware when it is controlling the boot and shutdown of the
+ * remote processor.
+ *
+ * Return: 0 on success or a negative value upon failure
+ */
+int rproc_set_firmware(struct rproc *rproc, const char *fw_name)
+{
+	struct device *dev;
+	int ret, len;
+	char *p;
+
+	if (!rproc || !fw_name)
+		return -EINVAL;
+
+	dev = rproc->dev.parent;
+
+	ret = mutex_lock_interruptible(&rproc->lock);
+	if (ret) {
+		dev_err(dev, "can't lock rproc %s: %d\n", rproc->name, ret);
+		return -EINVAL;
+	}
+
+	if (rproc->state != RPROC_OFFLINE) {
+		dev_err(dev, "can't change firmware while running\n");
+		ret = -EBUSY;
+		goto out;
+	}
+
+	len = strcspn(fw_name, "\n");
+	if (!len) {
+		dev_err(dev, "can't provide empty string for firmware name\n");
+		ret = -EINVAL;
+		goto out;
+	}
+
+	p = kstrndup(fw_name, len, GFP_KERNEL);
+	if (!p) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	kfree(rproc->firmware);
+	rproc->firmware = p;
+
+out:
+	mutex_unlock(&rproc->lock);
+	return ret;
+}
+EXPORT_SYMBOL(rproc_set_firmware);
+
 static int rproc_validate(struct rproc *rproc)
 {
 	switch (rproc->state) {
diff --git a/drivers/remoteproc/remoteproc_sysfs.c b/drivers/remoteproc/remoteproc_sysfs.c
index d1cf7bf277c4..1dbef895e65e 100644
--- a/drivers/remoteproc/remoteproc_sysfs.c
+++ b/drivers/remoteproc/remoteproc_sysfs.c
@@ -154,38 +154,9 @@ static ssize_t firmware_store(struct device *dev,
 			      const char *buf, size_t count)
 {
 	struct rproc *rproc = to_rproc(dev);
-	char *p;
-	int err, len = count;
+	int err;
 
-	err = mutex_lock_interruptible(&rproc->lock);
-	if (err) {
-		dev_err(dev, "can't lock rproc %s: %d\n", rproc->name, err);
-		return -EINVAL;
-	}
-
-	if (rproc->state != RPROC_OFFLINE) {
-		dev_err(dev, "can't change firmware while running\n");
-		err = -EBUSY;
-		goto out;
-	}
-
-	len = strcspn(buf, "\n");
-	if (!len) {
-		dev_err(dev, "can't provide a NULL firmware\n");
-		err = -EINVAL;
-		goto out;
-	}
-
-	p = kstrndup(buf, len, GFP_KERNEL);
-	if (!p) {
-		err = -ENOMEM;
-		goto out;
-	}
-
-	kfree(rproc->firmware);
-	rproc->firmware = p;
-out:
-	mutex_unlock(&rproc->lock);
+	err = rproc_set_firmware(rproc, buf);
 
 	return err ? err : count;
 }
diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h
index 3fa3ba6498e8..e8ac041c64d9 100644
--- a/include/linux/remoteproc.h
+++ b/include/linux/remoteproc.h
@@ -653,6 +653,7 @@ rproc_of_resm_mem_entry_init(struct device *dev, u32 of_resm_idx, size_t len,
 
 int rproc_boot(struct rproc *rproc);
 void rproc_shutdown(struct rproc *rproc);
+int rproc_set_firmware(struct rproc *rproc, const char *fw_name);
 void rproc_report_crash(struct rproc *rproc, enum rproc_crash_type type);
 int rproc_coredump_add_segment(struct rproc *rproc, dma_addr_t da, size_t size);
 int rproc_coredump_add_custom_segment(struct rproc *rproc,
-- 
cgit v1.2.3


From 7656ca71b0ba04ae7437afe3d046e9134442678e Mon Sep 17 00:00:00 2001
From: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Date: Wed, 25 Nov 2020 15:06:41 +0300
Subject: usb: pd: DFP product types

USB Power Delivery Specification R3.0 introduced separate
field for the DFP product type to the ID Header VDO.

Signed-off-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20201125120642.37156-2-heikki.krogerus@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/usb/pd_vdo.h | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/usb/pd_vdo.h b/include/linux/usb/pd_vdo.h
index 8c5cb5830754..8c08eeb9a74b 100644
--- a/include/linux/usb/pd_vdo.h
+++ b/include/linux/usb/pd_vdo.h
@@ -103,17 +103,25 @@
  * --------------------
  * <31>     :: data capable as a USB host
  * <30>     :: data capable as a USB device
- * <29:27>  :: product type
+ * <29:27>  :: product type (UFP / Cable)
  * <26>     :: modal operation supported (1b == yes)
- * <25:16>  :: Reserved, Shall be set to zero
+ * <25:16>  :: product type (DFP)
  * <15:0>   :: USB-IF assigned VID for this cable vendor
  */
 #define IDH_PTYPE_UNDEF		0
 #define IDH_PTYPE_HUB		1
 #define IDH_PTYPE_PERIPH	2
+#define IDH_PTYPE_PSD		3
+#define IDH_PTYPE_AMA		5
+
 #define IDH_PTYPE_PCABLE	3
 #define IDH_PTYPE_ACABLE	4
-#define IDH_PTYPE_AMA		5
+
+#define IDH_PTYPE_DFP_UNDEF	0
+#define IDH_PTYPE_DFP_HUB	1
+#define IDH_PTYPE_DFP_HOST	2
+#define IDH_PTYPE_DFP_PB	3
+#define IDH_PTYPE_DFP_AMC	4
 
 #define VDO_IDH(usbh, usbd, ptype, is_modal, vid)		\
 	((usbh) << 31 | (usbd) << 30 | ((ptype) & 0x7) << 27	\
@@ -122,6 +130,7 @@
 #define PD_IDH_PTYPE(vdo)	(((vdo) >> 27) & 0x7)
 #define PD_IDH_VID(vdo)		((vdo) & 0xffff)
 #define PD_IDH_MODAL_SUPP(vdo)	((vdo) & (1 << 26))
+#define PD_IDH_DFP_PTYPE(vdo)	(((vdo) >> 23) & 0x7)
 
 /*
  * Cert Stat VDO
-- 
cgit v1.2.3


From 640586f8af356096e084d69a9909d217852bde48 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Thu, 19 Nov 2020 17:02:21 +0100
Subject: powerpc/ptrace: Simplify gpr_get()/tm_cgpr_get()

gpr_get() does membuf_write() twice to override pt_regs->msr in
between. We can call membuf_write() once and change ->msr in the
kernel buffer, this simplifies the code and the next fix.

The patch adds a new simple helper, membuf_at(offs), it returns the
new membuf which can be safely used after membuf_write().

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
[mpe: Fixup some minor whitespace issues noticed by Christophe]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201119160221.GA5188@redhat.com
---
 arch/powerpc/kernel/ptrace/ptrace-tm.c   | 12 ++++--------
 arch/powerpc/kernel/ptrace/ptrace-view.c | 10 +++-------
 include/linux/regset.h                   | 12 ++++++++++++
 3 files changed, 19 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/arch/powerpc/kernel/ptrace/ptrace-tm.c b/arch/powerpc/kernel/ptrace/ptrace-tm.c
index 54f2d076206f..f15cbbab45b7 100644
--- a/arch/powerpc/kernel/ptrace/ptrace-tm.c
+++ b/arch/powerpc/kernel/ptrace/ptrace-tm.c
@@ -86,6 +86,8 @@ int tm_cgpr_active(struct task_struct *target, const struct user_regset *regset)
 int tm_cgpr_get(struct task_struct *target, const struct user_regset *regset,
 		struct membuf to)
 {
+	struct membuf to_msr = membuf_at(&to, offsetof(struct pt_regs, msr));
+
 	if (!cpu_has_feature(CPU_FTR_TM))
 		return -ENODEV;
 
@@ -96,16 +98,10 @@ int tm_cgpr_get(struct task_struct *target, const struct user_regset *regset,
 	flush_fp_to_thread(target);
 	flush_altivec_to_thread(target);
 
-	membuf_write(&to, &target->thread.ckpt_regs,
-			offsetof(struct pt_regs, msr));
-	membuf_store(&to, get_user_ckpt_msr(target));
+	membuf_write(&to, &target->thread.ckpt_regs, sizeof(struct user_pt_regs));
 
-	BUILD_BUG_ON(offsetof(struct pt_regs, orig_gpr3) !=
-		     offsetof(struct pt_regs, msr) + sizeof(long));
+	membuf_store(&to_msr, get_user_ckpt_msr(target));
 
-	membuf_write(&to, &target->thread.ckpt_regs.orig_gpr3,
-			sizeof(struct user_pt_regs) -
-			offsetof(struct pt_regs, orig_gpr3));
 	return membuf_zero(&to, ELF_NGREG * sizeof(unsigned long) -
 			sizeof(struct user_pt_regs));
 }
diff --git a/arch/powerpc/kernel/ptrace/ptrace-view.c b/arch/powerpc/kernel/ptrace/ptrace-view.c
index 7e6478e7ed07..299e0b6d709d 100644
--- a/arch/powerpc/kernel/ptrace/ptrace-view.c
+++ b/arch/powerpc/kernel/ptrace/ptrace-view.c
@@ -217,6 +217,7 @@ int ptrace_put_reg(struct task_struct *task, int regno, unsigned long data)
 static int gpr_get(struct task_struct *target, const struct user_regset *regset,
 		   struct membuf to)
 {
+	struct membuf to_msr = membuf_at(&to, offsetof(struct pt_regs, msr));
 	int i;
 
 	if (target->thread.regs == NULL)
@@ -228,15 +229,10 @@ static int gpr_get(struct task_struct *target, const struct user_regset *regset,
 			target->thread.regs->gpr[i] = NV_REG_POISON;
 	}
 
-	membuf_write(&to, target->thread.regs, offsetof(struct pt_regs, msr));
-	membuf_store(&to, get_user_msr(target));
+	membuf_write(&to, target->thread.regs, sizeof(struct user_pt_regs));
 
-	BUILD_BUG_ON(offsetof(struct pt_regs, orig_gpr3) !=
-		     offsetof(struct pt_regs, msr) + sizeof(long));
+	membuf_store(&to_msr, get_user_msr(target));
 
-	membuf_write(&to, &target->thread.regs->orig_gpr3,
-			sizeof(struct user_pt_regs) -
-			offsetof(struct pt_regs, orig_gpr3));
 	return membuf_zero(&to, ELF_NGREG * sizeof(unsigned long) -
 				 sizeof(struct user_pt_regs));
 }
diff --git a/include/linux/regset.h b/include/linux/regset.h
index c3403f328257..a00765f0e8cf 100644
--- a/include/linux/regset.h
+++ b/include/linux/regset.h
@@ -46,6 +46,18 @@ static inline int membuf_write(struct membuf *s, const void *v, size_t size)
 	return s->left;
 }
 
+static inline struct membuf membuf_at(const struct membuf *s, size_t offs)
+{
+	struct membuf n = *s;
+
+	if (offs > n.left)
+		offs = n.left;
+	n.p += offs;
+	n.left -= offs;
+
+	return n;
+}
+
 /* current s->p must be aligned for v; v must be a scalar */
 #define membuf_store(s, v)				\
 ({							\
-- 
cgit v1.2.3


From 11e5e568ceed7c8c570313a14fa96c72f21dad31 Mon Sep 17 00:00:00 2001
From: Badhri Jagan Sridharan <badhri@google.com>
Date: Tue, 24 Nov 2020 17:48:04 -0800
Subject: usb: typec: tcpm: Stay in SNK_TRY_WAIT_DEBOUNCE_CHECK_VBUS till Rp is
 seen

TD.4.7.3. Try SNK DRP Connect Try.SRC DRP fails. The compliance
tester mimics being a Try.SRC USB-C port.
The failure is due to TCPM exiting SNK_TRY_WAIT_DEBOUNCE_CHECK_VBUS
when VBUS is not present eventhough when SNK.Rp is seen. Exit to
SRC_TRYWAIT from SNK_TRY_WAIT_DEBOUNCE_CHECK_VBUS only when SNK.Rp
is not seen for PD_T_TRY_CC_DEBOUNCE.

>From the spec:
The port shall then transition to Attached.SNK when the SNK.Rp state
is detected on exactly one of the CC1 or CC2 pins for at least
tTryCCDebounce and VBUS is detected. Alternatively, the port shall
transition to TryWait.SRC if SNK.Rp state is not detected for
tTryCCDebounce.

Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Badhri Jagan Sridharan <badhri@google.com>
Link: https://lore.kernel.org/r/20201125014804.1596719-1-badhri@google.com
Acked-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/tcpm.c | 18 +++++++++++++-----
 include/linux/usb/pd.h        |  1 +
 2 files changed, 14 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 277b9d4d9c84..3bbc1f10af49 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -3124,15 +3124,13 @@ static void run_state_machine(struct tcpm_port *port)
 		break;
 	case SNK_TRY_WAIT_DEBOUNCE:
 		tcpm_set_state(port, SNK_TRY_WAIT_DEBOUNCE_CHECK_VBUS,
-			       PD_T_PD_DEBOUNCE);
+			       PD_T_TRY_CC_DEBOUNCE);
 		break;
 	case SNK_TRY_WAIT_DEBOUNCE_CHECK_VBUS:
-		if (port->vbus_present && tcpm_port_is_sink(port)) {
+		if (port->vbus_present && tcpm_port_is_sink(port))
 			tcpm_set_state(port, SNK_ATTACHED, 0);
-		} else {
-			tcpm_set_state(port, SRC_TRYWAIT, 0);
+		else
 			port->max_wait = 0;
-		}
 		break;
 	case SRC_TRYWAIT:
 		tcpm_set_cc(port, tcpm_rp_cc(port));
@@ -4053,6 +4051,12 @@ static void _tcpm_cc_change(struct tcpm_port *port, enum typec_cc_status cc1,
 		if (!tcpm_port_is_sink(port))
 			tcpm_set_state(port, SNK_TRYWAIT_DEBOUNCE, 0);
 		break;
+	case SNK_TRY_WAIT_DEBOUNCE_CHECK_VBUS:
+		if (!tcpm_port_is_sink(port))
+			tcpm_set_state(port, SRC_TRYWAIT, PD_T_TRY_CC_DEBOUNCE);
+		else
+			tcpm_set_state(port, SNK_TRY_WAIT_DEBOUNCE_CHECK_VBUS, 0);
+		break;
 	case SNK_TRYWAIT:
 		/* Do nothing, waiting for tCCDebounce */
 		break;
@@ -4139,6 +4143,10 @@ static void _tcpm_pd_vbus_on(struct tcpm_port *port)
 	case SNK_TRYWAIT_DEBOUNCE:
 		/* Do nothing, waiting for Rp */
 		break;
+	case SNK_TRY_WAIT_DEBOUNCE_CHECK_VBUS:
+		if (port->vbus_present && tcpm_port_is_sink(port))
+			tcpm_set_state(port, SNK_ATTACHED, 0);
+		break;
 	case SRC_TRY_WAIT:
 	case SRC_TRY_DEBOUNCE:
 		/* Do nothing, waiting for sink detection */
diff --git a/include/linux/usb/pd.h b/include/linux/usb/pd.h
index 3a805e2ecbc9..63a66dd5d832 100644
--- a/include/linux/usb/pd.h
+++ b/include/linux/usb/pd.h
@@ -484,6 +484,7 @@ static inline unsigned int rdo_max_power(u32 rdo)
 
 #define PD_T_CC_DEBOUNCE	200	/* 100 - 200 ms */
 #define PD_T_PD_DEBOUNCE	20	/* 10 - 20 ms */
+#define PD_T_TRY_CC_DEBOUNCE	15	/* 10 - 20 ms */
 
 #define PD_N_CAPS_COUNT		(PD_T_NO_RESPONSE / PD_T_SEND_SOURCE_CAP)
 #define PD_N_HARD_RESET_COUNT	2
-- 
cgit v1.2.3


From 07e21d4d96493fd0a8220ab134855253a34a9c84 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Wed, 4 Nov 2020 01:22:22 +0800
Subject: soundwire: SDCA: add helper macro to access controls

The upcoming SDCA (SoundWire Device Class Audio) specification defines
a hierarchical encoding to interface with Class-defined capabilities.

The specification is not yet accessible to the general public but this
information is released with explicit permission from the MIPI Board
to avoid delays with SDCA support on Linux platforms.

A block of 64 MBytes of register addresses are allocated to SDCA
controls, starting at address 0x40000000. The 26 LSBs which identify
individual controls are set based on the following variables:

- Function Number. An SCDA device can be split in up to 8 independent
  Functions. Each of these Functions is described in the SDCA
  specification, e.g. Smart Amplifier, Smart Microphone, Simple
  Microphone, Jack codec, HID, etc.

- Entity Number.  Within each Function,  an Entity is  an identifiable
  block.  Up   to  127  Entities   are  connected  in   a  pre-defined
  graph  (similar to  USB), with  Entity0 reserved  for Function-level
  configurations.  In  contrast  to  USB, the  SDCA  spec  pre-defines
  Function Types, topologies, and allowed  options, i.e. the degree of
  freedom  is not  unlimited to  limit  the possibility  of errors  in
  descriptors leading to software quirks.

- Control Selector. Within each Entity, the SDCA specification defines
  48 controls such as Mute, Gain, AGC, etc, and 16 implementation
  defined ones. Some Control Selectors might be used for low-level
  platform setup, and other exposed to applications and users. Note
  that the same Control Selector capability, e.g. Latency control,
  might be located at different offsets in different entities, the
  Control Selector mapping is Entity-specific.

- Control Number. Some Control Selectors allow channel-specific values
  to be set, with up to 64 channels allowed. This is mostly used for
  volume control.

- Current/Next values. Some Control Selectors are
  'Dual-Ranked'. Software may either update the Current value directly
  for immediate effect. Alternatively, software may write into the
  'Next' values and update the SoundWire 1.2 'Commit Groups' register
  to copy 'Next' values into 'Current' ones in a synchronized
  manner. This is different from bank switching which is typically
  used to change the bus configuration only.

- MBQ. the Multi-Byte Quantity bit is used to provide atomic updates
  when accessing more that one byte, for example a 16-bit volume
  control would be updated consistently, the intermediate values
  mixing old MSB with new LSB are not applied.

These 6 parameters are used to build a 32-bit address to access the
desired Controls. Because of address range, paging is required, but
the most often used parameter values are placed in the lower 16 bits
of the address. This helps to keep the paging registers constant while
updating Controls for a specific Device/Function.

Reviewed-by: Rander Wang <rander.wang@linux.intel.com>
Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Reviewed-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Acked-By: Vinod Koul <vkoul@kernel.org>
Link: https://lore.kernel.org/r/20201103172226.4278-2-yung-chuan.liao@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/soundwire/sdw_registers.h | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/soundwire/sdw_registers.h b/include/linux/soundwire/sdw_registers.h
index f420e8059779..e14dff9a9c7f 100644
--- a/include/linux/soundwire/sdw_registers.h
+++ b/include/linux/soundwire/sdw_registers.h
@@ -298,4 +298,36 @@
 #define SDW_CASC_PORT_MASK_INTSTAT3		1
 #define SDW_CASC_PORT_REG_OFFSET_INTSTAT3	2
 
+/*
+ * v1.2 device - SDCA address mapping
+ *
+ * Spec definition
+ *	Bits		Contents
+ *	31		0 (required by addressing range)
+ *	30:26		0b10000 (Control Prefix)
+ *	25		0 (Reserved)
+ *	24:22		Function Number [2:0]
+ *	21		Entity[6]
+ *	20:19		Control Selector[5:4]
+ *	18		0 (Reserved)
+ *	17:15		Control Number[5:3]
+ *	14		Next
+ *	13		MBQ
+ *	12:7		Entity[5:0]
+ *	6:3		Control Selector[3:0]
+ *	2:0		Control Number[2:0]
+ */
+
+#define SDW_SDCA_CTL(fun, ent, ctl, ch)		(BIT(30) |			\
+						 (((fun) & 0x7) << 22) |	\
+						 (((ent) & 0x40) << 15) |	\
+						 (((ent) & 0x3f) << 7) |	\
+						 (((ctl) & 0x30) << 15) |	\
+						 (((ctl) & 0x0f) << 3) |	\
+						 (((ch) & 0x38) << 12) |	\
+						 ((ch) & 0x07))
+
+#define SDW_SDCA_MBQ_CTL(reg)			((reg) | BIT(13))
+#define SDW_SDCA_NEXT_CTL(reg)			((reg) | BIT(14))
+
 #endif /* __SDW_REGISTERS_H */
-- 
cgit v1.2.3


From fb5103f9d6ce197b4d0b67b4e60e68470f5293d1 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Wed, 4 Nov 2020 01:22:23 +0800
Subject: regmap/SoundWire: sdw: add support for SoundWire 1.2 MBQ

The SoundWire 1.1 specification only allowed for reads and writes of
bytes. The SoundWire 1.2 specification adds a new capability to
transfer "Multi-Byte Quantities" (MBQ) across the bus. The transfers
still happens one-byte-at-a-time, but the update is atomic.

For example when writing a 16-bit volume, the first byte transferred
is only taken into account when the second byte is successfully
transferred.

The mechanism is symmetrical for read and writes:
- On a read, the address of the last byte to be read is modified by
setting the MBQ bit
- On a write, the address of all but the last byte to be written are
modified by setting the MBQ bit. The address for the last byte relies
on the MBQ bit being cleared.

The current definitions for MBQ-based controls in the SDCA draft
standard are limited to 16 bits for volumes, so for now this is the
only supported format. An update will be provided if and when support
for 24-bit and 32-bit values is specified by the SDCA standard.

One possible objection is that this code could have been handled with
regmap-sdw.c. However this is a new spec addition not handled by every
SoundWire 1.1 and non-SDCA device, so there's no reason to load code
that will never be used.

Also in practice it's extremely unlikely that CONFIG_REGMAP would not
be selected with CONFIG_REGMAP_MBQ selected. However there's no
functional dependency between the two modules so they can be selected
separately.

Reviewed-by: Rander Wang <rander.wang@linux.intel.com>
Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Reviewed-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Vinod Koul <vkoul@kernel.org>
Link: https://lore.kernel.org/r/20201103172226.4278-3-yung-chuan.liao@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/base/regmap/Kconfig          |   6 ++-
 drivers/base/regmap/Makefile         |   1 +
 drivers/base/regmap/regmap-sdw-mbq.c | 101 +++++++++++++++++++++++++++++++++++
 include/linux/regmap.h               |  35 ++++++++++++
 4 files changed, 142 insertions(+), 1 deletion(-)
 create mode 100644 drivers/base/regmap/regmap-sdw-mbq.c

(limited to 'include/linux')

diff --git a/drivers/base/regmap/Kconfig b/drivers/base/regmap/Kconfig
index bcb90d8c3960..50b1e2d06a25 100644
--- a/drivers/base/regmap/Kconfig
+++ b/drivers/base/regmap/Kconfig
@@ -4,7 +4,7 @@
 # subsystems should select the appropriate symbols.
 
 config REGMAP
-	default y if (REGMAP_I2C || REGMAP_SPI || REGMAP_SPMI || REGMAP_W1 || REGMAP_AC97 || REGMAP_MMIO || REGMAP_IRQ || REGMAP_SOUNDWIRE || REGMAP_SCCB || REGMAP_I3C || REGMAP_SPI_AVMM)
+	default y if (REGMAP_I2C || REGMAP_SPI || REGMAP_SPMI || REGMAP_W1 || REGMAP_AC97 || REGMAP_MMIO || REGMAP_IRQ || REGMAP_SOUNDWIRE || REGMAP_SOUNDWIRE_MBQ || REGMAP_SCCB || REGMAP_I3C || REGMAP_SPI_AVMM)
 	select IRQ_DOMAIN if REGMAP_IRQ
 	bool
 
@@ -46,6 +46,10 @@ config REGMAP_SOUNDWIRE
 	tristate
 	depends on SOUNDWIRE
 
+config REGMAP_SOUNDWIRE_MBQ
+	tristate
+	depends on SOUNDWIRE
+
 config REGMAP_SCCB
 	tristate
 	depends on I2C
diff --git a/drivers/base/regmap/Makefile b/drivers/base/regmap/Makefile
index ac1b69ee4051..33f63adb5b3d 100644
--- a/drivers/base/regmap/Makefile
+++ b/drivers/base/regmap/Makefile
@@ -15,6 +15,7 @@ obj-$(CONFIG_REGMAP_MMIO) += regmap-mmio.o
 obj-$(CONFIG_REGMAP_IRQ) += regmap-irq.o
 obj-$(CONFIG_REGMAP_W1) += regmap-w1.o
 obj-$(CONFIG_REGMAP_SOUNDWIRE) += regmap-sdw.o
+obj-$(CONFIG_REGMAP_SOUNDWIRE_MBQ) += regmap-sdw-mbq.o
 obj-$(CONFIG_REGMAP_SCCB) += regmap-sccb.o
 obj-$(CONFIG_REGMAP_I3C) += regmap-i3c.o
 obj-$(CONFIG_REGMAP_SPI_AVMM) += regmap-spi-avmm.o
diff --git a/drivers/base/regmap/regmap-sdw-mbq.c b/drivers/base/regmap/regmap-sdw-mbq.c
new file mode 100644
index 000000000000..8ce30650b97c
--- /dev/null
+++ b/drivers/base/regmap/regmap-sdw-mbq.c
@@ -0,0 +1,101 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright(c) 2020 Intel Corporation.
+
+#include <linux/device.h>
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+#include <linux/soundwire/sdw.h>
+#include <linux/soundwire/sdw_registers.h>
+#include "internal.h"
+
+static int regmap_sdw_mbq_write(void *context, unsigned int reg, unsigned int val)
+{
+	struct device *dev = context;
+	struct sdw_slave *slave = dev_to_sdw_dev(dev);
+	int ret;
+
+	ret = sdw_write(slave, SDW_SDCA_MBQ_CTL(reg), (val >> 8) & 0xff);
+	if (ret < 0)
+		return ret;
+
+	return sdw_write(slave, reg, val & 0xff);
+}
+
+static int regmap_sdw_mbq_read(void *context, unsigned int reg, unsigned int *val)
+{
+	struct device *dev = context;
+	struct sdw_slave *slave = dev_to_sdw_dev(dev);
+	int read0;
+	int read1;
+
+	read0 = sdw_read(slave, reg);
+	if (read0 < 0)
+		return read0;
+
+	read1 = sdw_read(slave, SDW_SDCA_MBQ_CTL(reg));
+	if (read1 < 0)
+		return read1;
+
+	*val = (read1 << 8) | read0;
+
+	return 0;
+}
+
+static struct regmap_bus regmap_sdw_mbq = {
+	.reg_read = regmap_sdw_mbq_read,
+	.reg_write = regmap_sdw_mbq_write,
+	.reg_format_endian_default = REGMAP_ENDIAN_LITTLE,
+	.val_format_endian_default = REGMAP_ENDIAN_LITTLE,
+};
+
+static int regmap_sdw_mbq_config_check(const struct regmap_config *config)
+{
+	/* MBQ-based controls are only 16-bits for now */
+	if (config->val_bits != 16)
+		return -ENOTSUPP;
+
+	/* Registers are 32 bits wide */
+	if (config->reg_bits != 32)
+		return -ENOTSUPP;
+
+	if (config->pad_bits != 0)
+		return -ENOTSUPP;
+
+	return 0;
+}
+
+struct regmap *__regmap_init_sdw_mbq(struct sdw_slave *sdw,
+				     const struct regmap_config *config,
+				     struct lock_class_key *lock_key,
+				     const char *lock_name)
+{
+	int ret;
+
+	ret = regmap_sdw_mbq_config_check(config);
+	if (ret)
+		return ERR_PTR(ret);
+
+	return __regmap_init(&sdw->dev, &regmap_sdw_mbq,
+			&sdw->dev, config, lock_key, lock_name);
+}
+EXPORT_SYMBOL_GPL(__regmap_init_sdw_mbq);
+
+struct regmap *__devm_regmap_init_sdw_mbq(struct sdw_slave *sdw,
+					  const struct regmap_config *config,
+					  struct lock_class_key *lock_key,
+					  const char *lock_name)
+{
+	int ret;
+
+	ret = regmap_sdw_mbq_config_check(config);
+	if (ret)
+		return ERR_PTR(ret);
+
+	return __devm_regmap_init(&sdw->dev, &regmap_sdw_mbq,
+			&sdw->dev, config, lock_key, lock_name);
+}
+EXPORT_SYMBOL_GPL(__devm_regmap_init_sdw_mbq);
+
+MODULE_DESCRIPTION("Regmap SoundWire MBQ Module");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index e7834d98207f..a652d1474d6a 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -570,6 +570,10 @@ struct regmap *__regmap_init_sdw(struct sdw_slave *sdw,
 				 const struct regmap_config *config,
 				 struct lock_class_key *lock_key,
 				 const char *lock_name);
+struct regmap *__regmap_init_sdw_mbq(struct sdw_slave *sdw,
+				     const struct regmap_config *config,
+				     struct lock_class_key *lock_key,
+				     const char *lock_name);
 struct regmap *__regmap_init_spi_avmm(struct spi_device *spi,
 				      const struct regmap_config *config,
 				      struct lock_class_key *lock_key,
@@ -619,6 +623,10 @@ struct regmap *__devm_regmap_init_sdw(struct sdw_slave *sdw,
 				 const struct regmap_config *config,
 				 struct lock_class_key *lock_key,
 				 const char *lock_name);
+struct regmap *__devm_regmap_init_sdw_mbq(struct sdw_slave *sdw,
+					  const struct regmap_config *config,
+					  struct lock_class_key *lock_key,
+					  const char *lock_name);
 struct regmap *__devm_regmap_init_slimbus(struct slim_device *slimbus,
 				 const struct regmap_config *config,
 				 struct lock_class_key *lock_key,
@@ -817,6 +825,19 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg);
 	__regmap_lockdep_wrapper(__regmap_init_sdw, #config,		\
 				sdw, config)
 
+/**
+ * regmap_init_sdw_mbq() - Initialise register map
+ *
+ * @sdw: Device that will be interacted with
+ * @config: Configuration for register map
+ *
+ * The return value will be an ERR_PTR() on error or a valid pointer to
+ * a struct regmap.
+ */
+#define regmap_init_sdw_mbq(sdw, config)					\
+	__regmap_lockdep_wrapper(__regmap_init_sdw_mbq, #config,		\
+				sdw, config)
+
 /**
  * regmap_init_spi_avmm() - Initialize register map for Intel SPI Slave
  * to AVMM Bus Bridge
@@ -989,6 +1010,20 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg);
 	__regmap_lockdep_wrapper(__devm_regmap_init_sdw, #config,	\
 				sdw, config)
 
+/**
+ * devm_regmap_init_sdw_mbq() - Initialise managed register map
+ *
+ * @sdw: Device that will be interacted with
+ * @config: Configuration for register map
+ *
+ * The return value will be an ERR_PTR() on error or a valid pointer
+ * to a struct regmap. The regmap will be automatically freed by the
+ * device management code.
+ */
+#define devm_regmap_init_sdw_mbq(sdw, config)			\
+	__regmap_lockdep_wrapper(__devm_regmap_init_sdw_mbq, #config,   \
+				sdw, config)
+
 /**
  * devm_regmap_init_slimbus() - Initialise managed register map
  *
-- 
cgit v1.2.3


From 4df910620bebb5cfe234af16ac8f6474b60215fd Mon Sep 17 00:00:00 2001
From: Feng Tang <feng.tang@intel.com>
Date: Wed, 25 Nov 2020 13:22:21 +0800
Subject: mm: memcg: relayout structure mem_cgroup to avoid cache interference

0day reported one -22.7% regression for will-it-scale page_fault2
case [1] on a 4 sockets 144 CPU platform, and bisected to it to be
caused by Waiman's optimization (commit bd0b230fe1) of saving one
'struct page_counter' space for 'struct mem_cgroup'.

Initially we thought it was due to the cache alignment change introduced
by the patch, but further debug shows that it is due to some hot data
members ('vmstats_local', 'vmstats_percpu', 'vmstats') sit in 2 adjacent
cacheline (2N and 2N+1 cacheline), and when adjacent cache line prefetch
is enabled, it triggers an "extended level" of cache false sharing for
2 adjacent cache lines.

So exchange the 2 member blocks, while keeping mostly the original
cache alignment, which can restore and even enhance the performance,
and save 64 bytes of space for 'struct mem_cgroup' (from 2880 to 2816,
with 0day's default RHEL-8.3 kernel config)

[1]. https://lore.kernel.org/lkml/20201102091543.GM31092@shao2-debian/

Fixes: bd0b230fe145 ("mm/memcg: unify swap and memsw page counters")
Reported-by: kernel test robot <rong.a.chen@intel.com>
Signed-off-by: Feng Tang <feng.tang@intel.com>
Acked-by: Waiman Long <longman@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 28 ++++++++++++++--------------
 1 file changed, 14 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index a80c59af2c60..922a7f600465 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -282,20 +282,6 @@ struct mem_cgroup {
 
 	MEMCG_PADDING(_pad1_);
 
-	/*
-	 * set > 0 if pages under this cgroup are moving to other cgroup.
-	 */
-	atomic_t		moving_account;
-	struct task_struct	*move_lock_task;
-
-	/* Legacy local VM stats and events */
-	struct memcg_vmstats_percpu __percpu *vmstats_local;
-
-	/* Subtree VM stats and events (batched updates) */
-	struct memcg_vmstats_percpu __percpu *vmstats_percpu;
-
-	MEMCG_PADDING(_pad2_);
-
 	atomic_long_t		vmstats[MEMCG_NR_STAT];
 	atomic_long_t		vmevents[NR_VM_EVENT_ITEMS];
 
@@ -317,6 +303,20 @@ struct mem_cgroup {
 	struct list_head objcg_list; /* list of inherited objcgs */
 #endif
 
+	MEMCG_PADDING(_pad2_);
+
+	/*
+	 * set > 0 if pages under this cgroup are moving to other cgroup.
+	 */
+	atomic_t		moving_account;
+	struct task_struct	*move_lock_task;
+
+	/* Legacy local VM stats and events */
+	struct memcg_vmstats_percpu __percpu *vmstats_local;
+
+	/* Subtree VM stats and events (batched updates) */
+	struct memcg_vmstats_percpu __percpu *vmstats_percpu;
+
 #ifdef CONFIG_CGROUP_WRITEBACK
 	struct list_head cgwb_list;
 	struct wb_domain cgwb_domain;
-- 
cgit v1.2.3


From 2a2970891647fee7e7ea767425f895140faffaa8 Mon Sep 17 00:00:00 2001
From: Chris Mi <cmi@nvidia.com>
Date: Fri, 20 Nov 2020 15:03:24 -0800
Subject: net/mlx5: Add sample offload hardware bits and structures

Hardware introduces flow sampler object for packet sampling.
Add the offload hardware bits and structures.

Signed-off-by: Chris Mi <cmi@nvidia.com>
Reviewed-by: Oz Shlomo <ozsh@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 include/linux/mlx5/mlx5_ifc.h | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 651591a2965d..65ea35af0527 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -10657,11 +10657,13 @@ struct mlx5_ifc_affiliated_event_header_bits {
 enum {
 	MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY = BIT(0xc),
 	MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_IPSEC = BIT(0x13),
+	MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_SAMPLER = BIT(0x20),
 };
 
 enum {
 	MLX5_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY = 0xc,
 	MLX5_GENERAL_OBJECT_TYPES_IPSEC = 0x13,
+	MLX5_GENERAL_OBJECT_TYPES_SAMPLER = 0x20,
 };
 
 enum {
@@ -10736,6 +10738,33 @@ struct mlx5_ifc_create_encryption_key_in_bits {
 	struct mlx5_ifc_encryption_key_obj_bits encryption_key_object;
 };
 
+struct mlx5_ifc_sampler_obj_bits {
+	u8         modify_field_select[0x40];
+
+	u8         table_type[0x8];
+	u8         level[0x8];
+	u8         reserved_at_50[0xf];
+	u8         ignore_flow_level[0x1];
+
+	u8         sample_ratio[0x20];
+
+	u8         reserved_at_80[0x8];
+	u8         sample_table_id[0x18];
+
+	u8         reserved_at_a0[0x8];
+	u8         default_table_id[0x18];
+
+	u8         sw_steering_icm_address_rx[0x40];
+	u8         sw_steering_icm_address_tx[0x40];
+
+	u8         reserved_at_140[0xa0];
+};
+
+struct mlx5_ifc_create_sampler_obj_in_bits {
+	struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr;
+	struct mlx5_ifc_sampler_obj_bits sampler_object;
+};
+
 enum {
 	MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_KEY_SIZE_128 = 0x0,
 	MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_KEY_SIZE_256 = 0x1,
-- 
cgit v1.2.3


From 38730630880c6f47ad73dd90524ff52443b8bc48 Mon Sep 17 00:00:00 2001
From: Chris Mi <cmi@nvidia.com>
Date: Fri, 20 Nov 2020 15:03:25 -0800
Subject: net/mlx5: Add sampler destination type

The flow sampler object is a new destination type. Add a new member
for the flow destination.

Signed-off-by: Chris Mi <cmi@nvidia.com>
Reviewed-by: Oz Shlomo <ozsh@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c | 3 +++
 drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c             | 3 +++
 include/linux/mlx5/fs.h                                      | 1 +
 include/linux/mlx5/mlx5_ifc.h                                | 1 +
 4 files changed, 8 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c
index a700f3c86899..87d65f6b5310 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c
@@ -247,6 +247,9 @@ const char *parse_fs_dst(struct trace_seq *p,
 	case MLX5_FLOW_DESTINATION_TYPE_TIR:
 		trace_seq_printf(p, "tir=%u\n", dst->tir_num);
 		break;
+	case MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER:
+		trace_seq_printf(p, "sampler_id=%u\n", dst->sampler_id);
+		break;
 	case MLX5_FLOW_DESTINATION_TYPE_COUNTER:
 		trace_seq_printf(p, "counter_id=%u\n", counter_id);
 		break;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index babe3405132a..c2fed9c3d75c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -515,6 +515,9 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 						 dst->dest_attr.vport.pkt_reformat->id);
 				}
 				break;
+			case MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER:
+				id = dst->dest_attr.sampler_id;
+				break;
 			default:
 				id = dst->dest_attr.tir_num;
 			}
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 846d94ad04bc..35d2cc1646d3 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -132,6 +132,7 @@ struct mlx5_flow_destination {
 			struct mlx5_pkt_reformat *pkt_reformat;
 			u8		flags;
 		} vport;
+		u32			sampler_id;
 	};
 };
 
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 65ea35af0527..2f2add4bd5e1 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1616,6 +1616,7 @@ enum mlx5_flow_destination_type {
 	MLX5_FLOW_DESTINATION_TYPE_VPORT        = 0x0,
 	MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE   = 0x1,
 	MLX5_FLOW_DESTINATION_TYPE_TIR          = 0x2,
+	MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER = 0x6,
 
 	MLX5_FLOW_DESTINATION_TYPE_PORT         = 0x99,
 	MLX5_FLOW_DESTINATION_TYPE_COUNTER      = 0x100,
-- 
cgit v1.2.3


From 7da3ad6c26f41f403fe6823c3de242551db09c37 Mon Sep 17 00:00:00 2001
From: Muhammad Sammar <muhammads@nvidia.com>
Date: Fri, 20 Nov 2020 15:03:27 -0800
Subject: net/mlx5: Add misc4 to mlx5_ifc_fte_match_param_bits

Add misc4 match params to enable matching on prog_sample_fields.

Signed-off-by: Muhammad Sammar <muhammads@nvidia.com>
Reviewed-by: Alex Vesker <valex@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.h |  2 +-
 include/linux/mlx5/device.h                       |  1 +
 include/linux/mlx5/mlx5_ifc.h                     | 25 ++++++++++++++++++++++-
 include/uapi/rdma/mlx5_user_ioctl_cmds.h          |  2 +-
 4 files changed, 27 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index afe7f0bffb93..b24a9849c45e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -194,7 +194,7 @@ struct mlx5_ft_underlay_qp {
 	u32 qpn;
 };
 
-#define MLX5_FTE_MATCH_PARAM_RESERVED	reserved_at_a00
+#define MLX5_FTE_MATCH_PARAM_RESERVED	reserved_at_c00
 /* Calculate the fte_match_param length and without the reserved length.
  * Make sure the reserved field is the last.
  */
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index cf824366a7d1..e9639c4cf2ed 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -1076,6 +1076,7 @@ enum {
 	MLX5_MATCH_INNER_HEADERS	= 1 << 2,
 	MLX5_MATCH_MISC_PARAMETERS_2	= 1 << 3,
 	MLX5_MATCH_MISC_PARAMETERS_3	= 1 << 4,
+	MLX5_MATCH_MISC_PARAMETERS_4	= 1 << 5,
 };
 
 enum {
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 2f2add4bd5e1..11c24fafd7f2 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -623,6 +623,26 @@ struct mlx5_ifc_fte_match_set_misc3_bits {
 	u8         reserved_at_140[0xc0];
 };
 
+struct mlx5_ifc_fte_match_set_misc4_bits {
+	u8         prog_sample_field_value_0[0x20];
+
+	u8         prog_sample_field_id_0[0x20];
+
+	u8         prog_sample_field_value_1[0x20];
+
+	u8         prog_sample_field_id_1[0x20];
+
+	u8         prog_sample_field_value_2[0x20];
+
+	u8         prog_sample_field_id_2[0x20];
+
+	u8         prog_sample_field_value_3[0x20];
+
+	u8         prog_sample_field_id_3[0x20];
+
+	u8         reserved_at_100[0x100];
+};
+
 struct mlx5_ifc_cmd_pas_bits {
 	u8         pa_h[0x20];
 
@@ -1669,7 +1689,9 @@ struct mlx5_ifc_fte_match_param_bits {
 
 	struct mlx5_ifc_fte_match_set_misc3_bits misc_parameters_3;
 
-	u8         reserved_at_a00[0x600];
+	struct mlx5_ifc_fte_match_set_misc4_bits misc_parameters_4;
+
+	u8         reserved_at_c00[0x400];
 };
 
 enum {
@@ -5462,6 +5484,7 @@ enum {
 	MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_INNER_HEADERS    = 0x2,
 	MLX5_QUERY_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS_2 = 0x3,
 	MLX5_QUERY_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS_3 = 0x4,
+	MLX5_QUERY_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS_4 = 0x5,
 };
 
 struct mlx5_ifc_query_flow_group_out_bits {
diff --git a/include/uapi/rdma/mlx5_user_ioctl_cmds.h b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
index e24d66d278cf..3fd9b380a091 100644
--- a/include/uapi/rdma/mlx5_user_ioctl_cmds.h
+++ b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
@@ -232,7 +232,7 @@ enum mlx5_ib_device_query_context_attrs {
 	MLX5_IB_ATTR_QUERY_CONTEXT_RESP_UCTX = (1U << UVERBS_ID_NS_SHIFT),
 };
 
-#define MLX5_IB_DW_MATCH_PARAM 0x80
+#define MLX5_IB_DW_MATCH_PARAM 0x90
 
 struct mlx5_ib_match_params {
 	__u32	match_params[MLX5_IB_DW_MATCH_PARAM];
-- 
cgit v1.2.3


From 59d2ae1db89f5a491d48f798ffccef36cc69ca65 Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@nvidia.com>
Date: Fri, 20 Nov 2020 15:03:28 -0800
Subject: net/mlx5: Add ts_cqe_to_dest_cqn related bits

Add a bit in HCA capabilities layout to indicate if ts_cqe_to_dest_cqn is
supported.

In addition, add ts_cqe_to_dest_cqn field to SQ context, for driver to
set the actual CQN.

Signed-off-by: Eran Ben Elisha <eranbe@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 include/linux/mlx5/mlx5_ifc.h | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 11c24fafd7f2..632b9a61fda5 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1261,7 +1261,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8	   ece_support[0x1];
 	u8	   reserved_at_a4[0x7];
 	u8         log_max_srq[0x5];
-	u8         reserved_at_b0[0x10];
+	u8         reserved_at_b0[0x2];
+	u8         ts_cqe_to_dest_cqn[0x1];
+	u8         reserved_at_b3[0xd];
 
 	u8         max_sgl_for_optimized_performance[0x8];
 	u8         log_max_cq_sz[0x8];
@@ -3312,8 +3314,12 @@ struct mlx5_ifc_sqc_bits {
 	u8         reserved_at_80[0x10];
 	u8         hairpin_peer_vhca[0x10];
 
-	u8         reserved_at_a0[0x50];
+	u8         reserved_at_a0[0x20];
 
+	u8         reserved_at_c0[0x8];
+	u8         ts_cqe_to_dest_cqn[0x18];
+
+	u8         reserved_at_e0[0x10];
 	u8         packet_pacing_rate_limit_index[0x10];
 	u8         tis_lst_sz[0x10];
 	u8         reserved_at_110[0x10];
-- 
cgit v1.2.3


From e5dfe6b57e8eada1c238dd2c7020345b0d8f6454 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@nvidia.com>
Date: Fri, 20 Nov 2020 15:03:29 -0800
Subject: net/mlx5: Avoid exposing driver internal command helpers

mlx5 command init and cleanup routines are internal to mlx5_core driver.
Hence, avoid exporting them and move their definition to mlx5_core
driver's internal file mlx5_core.h

Signed-off-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c       | 3 ---
 drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h | 4 ++++
 include/linux/mlx5/driver.h                         | 4 ----
 3 files changed, 4 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index e49387dbef98..50c7b9ee80c3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -2142,7 +2142,6 @@ dma_pool_err:
 	kvfree(cmd->stats);
 	return err;
 }
-EXPORT_SYMBOL(mlx5_cmd_init);
 
 void mlx5_cmd_cleanup(struct mlx5_core_dev *dev)
 {
@@ -2155,11 +2154,9 @@ void mlx5_cmd_cleanup(struct mlx5_core_dev *dev)
 	dma_pool_destroy(cmd->pool);
 	kvfree(cmd->stats);
 }
-EXPORT_SYMBOL(mlx5_cmd_cleanup);
 
 void mlx5_cmd_set_state(struct mlx5_core_dev *dev,
 			enum mlx5_cmdif_state cmdif_state)
 {
 	dev->cmd.state = cmdif_state;
 }
-EXPORT_SYMBOL(mlx5_cmd_set_state);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 8cec85ab419d..9d00efa9e6bc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -122,6 +122,10 @@ enum mlx5_semaphore_space_address {
 
 int mlx5_query_hca_caps(struct mlx5_core_dev *dev);
 int mlx5_query_board_id(struct mlx5_core_dev *dev);
+int mlx5_cmd_init(struct mlx5_core_dev *dev);
+void mlx5_cmd_cleanup(struct mlx5_core_dev *dev);
+void mlx5_cmd_set_state(struct mlx5_core_dev *dev,
+			enum mlx5_cmdif_state cmdif_state);
 int mlx5_cmd_init_hca(struct mlx5_core_dev *dev, uint32_t *sw_owner_id);
 int mlx5_cmd_teardown_hca(struct mlx5_core_dev *dev);
 int mlx5_cmd_force_teardown_hca(struct mlx5_core_dev *dev);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index add85094f9a5..5e84b1d53650 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -888,10 +888,6 @@ enum {
 	CMD_ALLOWED_OPCODE_ALL,
 };
 
-int mlx5_cmd_init(struct mlx5_core_dev *dev);
-void mlx5_cmd_cleanup(struct mlx5_core_dev *dev);
-void mlx5_cmd_set_state(struct mlx5_core_dev *dev,
-			enum mlx5_cmdif_state cmdif_state);
 void mlx5_cmd_use_events(struct mlx5_core_dev *dev);
 void mlx5_cmd_use_polling(struct mlx5_core_dev *dev);
 void mlx5_cmd_allowed_opcode(struct mlx5_core_dev *dev, u16 opcode);
-- 
cgit v1.2.3


From 349125ba232ea53d71a57c65c81f109c323cc369 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@nvidia.com>
Date: Fri, 20 Nov 2020 15:03:31 -0800
Subject: net/mlx5: Update the hardware interface definition for vhca state

Update the hardware interface definitions to query and modify vhca
state, related EQE and event code.

Signed-off-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 include/linux/mlx5/device.h   |  7 +++++++
 include/linux/mlx5/mlx5_ifc.h | 17 ++++++++++++++---
 2 files changed, 21 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index e9639c4cf2ed..f1de49d64a98 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -346,6 +346,7 @@ enum mlx5_event {
 	MLX5_EVENT_TYPE_NIC_VPORT_CHANGE   = 0xd,
 
 	MLX5_EVENT_TYPE_ESW_FUNCTIONS_CHANGED = 0xe,
+	MLX5_EVENT_TYPE_VHCA_STATE_CHANGE = 0xf,
 
 	MLX5_EVENT_TYPE_DCT_DRAINED        = 0x1c,
 	MLX5_EVENT_TYPE_DCT_KEY_VIOLATION  = 0x1d,
@@ -717,6 +718,11 @@ struct mlx5_eqe_sync_fw_update {
 	u8 sync_rst_state;
 };
 
+struct mlx5_eqe_vhca_state {
+	__be16 ec_function;
+	__be16 function_id;
+} __packed;
+
 union ev_data {
 	__be32				raw[7];
 	struct mlx5_eqe_cmd		cmd;
@@ -736,6 +742,7 @@ union ev_data {
 	struct mlx5_eqe_temp_warning	temp_warning;
 	struct mlx5_eqe_xrq_err		xrq_err;
 	struct mlx5_eqe_sync_fw_update	sync_fw_update;
+	struct mlx5_eqe_vhca_state	vhca_state;
 } __packed;
 
 struct mlx5_eqe {
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 632b9a61fda5..3ace1976514c 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -299,6 +299,8 @@ enum {
 	MLX5_CMD_OP_CREATE_UMEM                   = 0xa08,
 	MLX5_CMD_OP_DESTROY_UMEM                  = 0xa0a,
 	MLX5_CMD_OP_SYNC_STEERING                 = 0xb00,
+	MLX5_CMD_OP_QUERY_VHCA_STATE              = 0xb0d,
+	MLX5_CMD_OP_MODIFY_VHCA_STATE             = 0xb0e,
 	MLX5_CMD_OP_MAX
 };
 
@@ -1244,7 +1246,15 @@ enum mlx5_fc_bulk_alloc_bitmask {
 #define MLX5_FC_BULK_NUM_FCS(fc_enum) (MLX5_FC_BULK_SIZE_FACTOR * (fc_enum))
 
 struct mlx5_ifc_cmd_hca_cap_bits {
-	u8         reserved_at_0[0x30];
+	u8         reserved_at_0[0x20];
+
+	u8         reserved_at_20[0x3];
+	u8         event_on_vhca_state_teardown_request[0x1];
+	u8         event_on_vhca_state_in_use[0x1];
+	u8         event_on_vhca_state_active[0x1];
+	u8         event_on_vhca_state_allocated[0x1];
+	u8         event_on_vhca_state_invalid[0x1];
+	u8         reserved_at_28[0x8];
 	u8         vhca_id[0x10];
 
 	u8         reserved_at_40[0x40];
@@ -1534,7 +1544,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         disable_local_lb_uc[0x1];
 	u8         disable_local_lb_mc[0x1];
 	u8         log_min_hairpin_wq_data_sz[0x5];
-	u8         reserved_at_3e8[0x3];
+	u8         reserved_at_3e8[0x2];
+	u8         vhca_state[0x1];
 	u8         log_max_vlan_list[0x5];
 	u8         reserved_at_3f0[0x3];
 	u8         log_max_current_mc_list[0x5];
@@ -1602,7 +1613,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         max_num_of_monitor_counters[0x10];
 	u8         num_ppcnt_monitor_counters[0x10];
 
-	u8         reserved_at_640[0x10];
+	u8         max_num_sf[0x10];
 	u8         num_q_monitor_counters[0x10];
 
 	u8         reserved_at_660[0x20];
-- 
cgit v1.2.3


From 21adf05d4584c99a07a604224b9cfeddcc6bc47c Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@nvidia.com>
Date: Fri, 20 Nov 2020 15:03:32 -0800
Subject: net/mlx5: Expose IP-in-IP TX and RX capability bits

Expose FW indication that it supports stateless offloads for IP over IP
tunneled packets per direction. In some HW like ConnectX-4 IP-in-IP
support is not symmetric, it supports steering on the inner header but
it doesn't TX-Checksum and TSO. Add IP-in-IP capability per direction to
cover this case as well.

Note: only if both indications are turned on, the global
tunnel_stateless_ip_over_ip is on too.

Signed-off-by: Aya Levin <ayal@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 include/linux/mlx5/mlx5_ifc.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 3ace1976514c..96888f9f822d 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -913,7 +913,10 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits {
 	u8         tunnel_stateless_ipv4_over_vxlan[0x1];
 	u8         tunnel_stateless_ip_over_ip[0x1];
 	u8         insert_trailer[0x1];
-	u8         reserved_at_2b[0x5];
+	u8         reserved_at_2b[0x1];
+	u8         tunnel_stateless_ip_over_ip_rx[0x1];
+	u8         tunnel_stateless_ip_over_ip_tx[0x1];
+	u8         reserved_at_2e[0x2];
 	u8         max_vxlan_udp_ports[0x8];
 	u8         reserved_at_38[0x6];
 	u8         max_geneve_opt_len[0x1];
-- 
cgit v1.2.3


From 959af5569f57d189b5c4fccae45f16d5ff01aa39 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Fri, 20 Nov 2020 15:03:33 -0800
Subject: net/mlx5: Expose other function ifc bits

Expose other function ifc bits to enable setting HCA caps on behalf of
other function.

In addition, expose vhca_resource_manager bit to control whether the
other function functionality is supported by firmware.

Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 include/linux/mlx5/mlx5_ifc.h | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 96888f9f822d..3e337386faa8 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1249,7 +1249,8 @@ enum mlx5_fc_bulk_alloc_bitmask {
 #define MLX5_FC_BULK_NUM_FCS(fc_enum) (MLX5_FC_BULK_SIZE_FACTOR * (fc_enum))
 
 struct mlx5_ifc_cmd_hca_cap_bits {
-	u8         reserved_at_0[0x20];
+	u8         reserved_at_0[0x1f];
+	u8         vhca_resource_manager[0x1];
 
 	u8         reserved_at_20[0x3];
 	u8         event_on_vhca_state_teardown_request[0x1];
@@ -4247,7 +4248,11 @@ struct mlx5_ifc_set_hca_cap_in_bits {
 	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_at_40[0x40];
+	u8         other_function[0x1];
+	u8         reserved_at_41[0xf];
+	u8         function_id[0x10];
+
+	u8         reserved_at_60[0x20];
 
 	union mlx5_ifc_hca_cap_union_bits capability;
 };
-- 
cgit v1.2.3


From 3b1e58aa832ed537289be6a51a2015309688a90c Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@nvidia.com>
Date: Fri, 20 Nov 2020 15:03:36 -0800
Subject: net/mlx5: Make API mlx5_core_is_ecpf accept const pointer

Subsequent patch implements helper API which has mlx5_core_dev
as const pointer, make its caller API too const *.

Signed-off-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Bodong Wang <bodong@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 include/linux/mlx5/driver.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 5e84b1d53650..d6ef3068d7d3 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1133,7 +1133,7 @@ static inline bool mlx5_core_is_vf(const struct mlx5_core_dev *dev)
 	return dev->coredev_type == MLX5_COREDEV_VF;
 }
 
-static inline bool mlx5_core_is_ecpf(struct mlx5_core_dev *dev)
+static inline bool mlx5_core_is_ecpf(const struct mlx5_core_dev *dev)
 {
 	return dev->caps.embedded_cpu;
 }
-- 
cgit v1.2.3


From 8a90f2fc67826a3876df1cb72e42d4a9a135f4fa Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@nvidia.com>
Date: Fri, 20 Nov 2020 15:03:37 -0800
Subject: net/mlx5: Rename peer_pf to host_pf

To match the hardware spec, rename peer_pf to host_pf.

Signed-off-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Bodong Wang <bodong@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/ecpf.c     | 51 ++++++++++++++--------
 .../net/ethernet/mellanox/mlx5/core/pagealloc.c    | 12 ++---
 include/linux/mlx5/driver.h                        |  2 +-
 3 files changed, 40 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c
index 3dc9dd3f24dc..68ca0e2b26cd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c
@@ -8,37 +8,52 @@ bool mlx5_read_embedded_cpu(struct mlx5_core_dev *dev)
 	return (ioread32be(&dev->iseg->initializing) >> MLX5_ECPU_BIT_NUM) & 1;
 }
 
-static int mlx5_peer_pf_init(struct mlx5_core_dev *dev)
+static int mlx5_cmd_host_pf_enable_hca(struct mlx5_core_dev *dev)
 {
-	u32 in[MLX5_ST_SZ_DW(enable_hca_in)] = {};
-	int err;
+	u32 out[MLX5_ST_SZ_DW(enable_hca_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(enable_hca_in)]   = {};
 
 	MLX5_SET(enable_hca_in, in, opcode, MLX5_CMD_OP_ENABLE_HCA);
-	err = mlx5_cmd_exec_in(dev, enable_hca, in);
+	MLX5_SET(enable_hca_in, in, function_id, 0);
+	MLX5_SET(enable_hca_in, in, embedded_cpu_function, 0);
+	return mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out));
+}
+
+static int mlx5_cmd_host_pf_disable_hca(struct mlx5_core_dev *dev)
+{
+	u32 out[MLX5_ST_SZ_DW(disable_hca_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(disable_hca_in)]   = {};
+
+	MLX5_SET(disable_hca_in, in, opcode, MLX5_CMD_OP_DISABLE_HCA);
+	MLX5_SET(disable_hca_in, in, function_id, 0);
+	MLX5_SET(disable_hca_in, in, embedded_cpu_function, 0);
+	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+}
+
+static int mlx5_host_pf_init(struct mlx5_core_dev *dev)
+{
+	int err;
+
+	err = mlx5_cmd_host_pf_enable_hca(dev);
 	if (err)
-		mlx5_core_err(dev, "Failed to enable peer PF HCA err(%d)\n",
-			      err);
+		mlx5_core_err(dev, "Failed to enable external host PF HCA err(%d)\n", err);
 
 	return err;
 }
 
-static void mlx5_peer_pf_cleanup(struct mlx5_core_dev *dev)
+static void mlx5_host_pf_cleanup(struct mlx5_core_dev *dev)
 {
-	u32 in[MLX5_ST_SZ_DW(disable_hca_in)] = {};
 	int err;
 
-	MLX5_SET(disable_hca_in, in, opcode, MLX5_CMD_OP_DISABLE_HCA);
-	err = mlx5_cmd_exec_in(dev, disable_hca, in);
+	err = mlx5_cmd_host_pf_disable_hca(dev);
 	if (err) {
-		mlx5_core_err(dev, "Failed to disable peer PF HCA err(%d)\n",
-			      err);
+		mlx5_core_err(dev, "Failed to disable external host PF HCA err(%d)\n", err);
 		return;
 	}
 
-	err = mlx5_wait_for_pages(dev, &dev->priv.peer_pf_pages);
+	err = mlx5_wait_for_pages(dev, &dev->priv.host_pf_pages);
 	if (err)
-		mlx5_core_warn(dev, "Timeout reclaiming peer PF pages err(%d)\n",
-			       err);
+		mlx5_core_warn(dev, "Timeout reclaiming external host PF pages err(%d)\n", err);
 }
 
 int mlx5_ec_init(struct mlx5_core_dev *dev)
@@ -46,10 +61,10 @@ int mlx5_ec_init(struct mlx5_core_dev *dev)
 	if (!mlx5_core_is_ecpf(dev))
 		return 0;
 
-	/* ECPF shall enable HCA for peer PF in the same way a PF
+	/* ECPF shall enable HCA for host PF in the same way a PF
 	 * does this for its VFs.
 	 */
-	return mlx5_peer_pf_init(dev);
+	return mlx5_host_pf_init(dev);
 }
 
 void mlx5_ec_cleanup(struct mlx5_core_dev *dev)
@@ -57,5 +72,5 @@ void mlx5_ec_cleanup(struct mlx5_core_dev *dev)
 	if (!mlx5_core_is_ecpf(dev))
 		return;
 
-	mlx5_peer_pf_cleanup(dev);
+	mlx5_host_pf_cleanup(dev);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index 150638814517..539baea358bf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -374,7 +374,7 @@ retry:
 	if (func_id)
 		dev->priv.vfs_pages += npages;
 	else if (mlx5_core_is_ecpf(dev) && !ec_function)
-		dev->priv.peer_pf_pages += npages;
+		dev->priv.host_pf_pages += npages;
 
 	mlx5_core_dbg(dev, "npages %d, ec_function %d, func_id 0x%x, err %d\n",
 		      npages, ec_function, func_id, err);
@@ -416,7 +416,7 @@ static void release_all_pages(struct mlx5_core_dev *dev, u32 func_id,
 	if (func_id)
 		dev->priv.vfs_pages -= npages;
 	else if (mlx5_core_is_ecpf(dev) && !ec_function)
-		dev->priv.peer_pf_pages -= npages;
+		dev->priv.host_pf_pages -= npages;
 
 	mlx5_core_dbg(dev, "npages %d, ec_function %d, func_id 0x%x\n",
 		      npages, ec_function, func_id);
@@ -506,7 +506,7 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
 	if (func_id)
 		dev->priv.vfs_pages -= num_claimed;
 	else if (mlx5_core_is_ecpf(dev) && !ec_function)
-		dev->priv.peer_pf_pages -= num_claimed;
+		dev->priv.host_pf_pages -= num_claimed;
 
 out_free:
 	kvfree(out);
@@ -661,9 +661,9 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev)
 	WARN(dev->priv.vfs_pages,
 	     "VFs FW pages counter is %d after reclaiming all pages\n",
 	     dev->priv.vfs_pages);
-	WARN(dev->priv.peer_pf_pages,
-	     "Peer PF FW pages counter is %d after reclaiming all pages\n",
-	     dev->priv.peer_pf_pages);
+	WARN(dev->priv.host_pf_pages,
+	     "External host PF FW pages counter is %d after reclaiming all pages\n",
+	     dev->priv.host_pf_pages);
 
 	return 0;
 }
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index d6ef3068d7d3..8e9bcb3bfd77 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -547,7 +547,7 @@ struct mlx5_priv {
 	atomic_t		reg_pages;
 	struct list_head	free_list;
 	int			vfs_pages;
-	int			peer_pf_pages;
+	int			host_pf_pages;
 
 	struct mlx5_core_health health;
 
-- 
cgit v1.2.3


From 617b860c1875842d9cc3338d7dabd2b3538038f1 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@nvidia.com>
Date: Fri, 20 Nov 2020 15:03:39 -0800
Subject: net/mlx5: Treat host PF vport as other (non eswitch manager) vport

When eswitch manager is running on ECPF, host PF should be treated
as non eswitch manager port, similar to other VF vports.
Fail to do so, results in firmware treating PF's vport as ECPF
vport for eswitch ACL tables.
Non zero check to figure out if a given vport is other vport or not
is not sufficient becase PF vport number = 0 on ECPF.
Hence, create esw acl tables with an attribute of other vport.

Signed-off-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../ethernet/mellanox/mlx5/core/esw/acl/helper.c   |  5 +-
 drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c   | 54 ++++++++++------------
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c  | 14 ++----
 include/linux/mlx5/fs.h                            |  5 +-
 4 files changed, 34 insertions(+), 44 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c
index 22f4c1c28006..4a369669e51e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c
@@ -8,6 +8,7 @@
 struct mlx5_flow_table *
 esw_acl_table_create(struct mlx5_eswitch *esw, u16 vport_num, int ns, int size)
 {
+	struct mlx5_flow_table_attr ft_attr = {};
 	struct mlx5_core_dev *dev = esw->dev;
 	struct mlx5_flow_namespace *root_ns;
 	struct mlx5_flow_table *acl;
@@ -33,7 +34,9 @@ esw_acl_table_create(struct mlx5_eswitch *esw, u16 vport_num, int ns, int size)
 		return ERR_PTR(-EOPNOTSUPP);
 	}
 
-	acl = mlx5_create_vport_flow_table(root_ns, 0, size, 0, vport_num);
+	ft_attr.max_fte = size;
+	ft_attr.flags = MLX5_FLOW_TABLE_OTHER_VPORT;
+	acl = mlx5_create_vport_flow_table(root_ns, &ft_attr, vport_num);
 	if (IS_ERR(acl)) {
 		err = PTR_ERR(acl);
 		esw_warn(dev, "vport[%d] create %s ACL table, err(%d)\n", vport_num,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index c2fed9c3d75c..8e06731d3cb3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -172,10 +172,9 @@ static int mlx5_cmd_update_root_ft(struct mlx5_flow_root_namespace *ns,
 		MLX5_SET(set_flow_table_root_in, in, table_id, ft->id);
 
 	MLX5_SET(set_flow_table_root_in, in, underlay_qpn, underlay_qpn);
-	if (ft->vport) {
-		MLX5_SET(set_flow_table_root_in, in, vport_number, ft->vport);
-		MLX5_SET(set_flow_table_root_in, in, other_vport, 1);
-	}
+	MLX5_SET(set_flow_table_root_in, in, vport_number, ft->vport);
+	MLX5_SET(set_flow_table_root_in, in, other_vport,
+		 !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT));
 
 	return mlx5_cmd_exec_in(dev, set_flow_table_root, in);
 }
@@ -199,10 +198,9 @@ static int mlx5_cmd_create_flow_table(struct mlx5_flow_root_namespace *ns,
 	MLX5_SET(create_flow_table_in, in, table_type, ft->type);
 	MLX5_SET(create_flow_table_in, in, flow_table_context.level, ft->level);
 	MLX5_SET(create_flow_table_in, in, flow_table_context.log_size, log_size);
-	if (ft->vport) {
-		MLX5_SET(create_flow_table_in, in, vport_number, ft->vport);
-		MLX5_SET(create_flow_table_in, in, other_vport, 1);
-	}
+	MLX5_SET(create_flow_table_in, in, vport_number, ft->vport);
+	MLX5_SET(create_flow_table_in, in, other_vport,
+		 !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT));
 
 	MLX5_SET(create_flow_table_in, in, flow_table_context.decap_en,
 		 en_decap);
@@ -252,10 +250,9 @@ static int mlx5_cmd_destroy_flow_table(struct mlx5_flow_root_namespace *ns,
 		 MLX5_CMD_OP_DESTROY_FLOW_TABLE);
 	MLX5_SET(destroy_flow_table_in, in, table_type, ft->type);
 	MLX5_SET(destroy_flow_table_in, in, table_id, ft->id);
-	if (ft->vport) {
-		MLX5_SET(destroy_flow_table_in, in, vport_number, ft->vport);
-		MLX5_SET(destroy_flow_table_in, in, other_vport, 1);
-	}
+	MLX5_SET(destroy_flow_table_in, in, vport_number, ft->vport);
+	MLX5_SET(destroy_flow_table_in, in, other_vport,
+		 !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT));
 
 	return mlx5_cmd_exec_in(dev, destroy_flow_table, in);
 }
@@ -283,11 +280,9 @@ static int mlx5_cmd_modify_flow_table(struct mlx5_flow_root_namespace *ns,
 				 flow_table_context.lag_master_next_table_id, 0);
 		}
 	} else {
-		if (ft->vport) {
-			MLX5_SET(modify_flow_table_in, in, vport_number,
-				 ft->vport);
-			MLX5_SET(modify_flow_table_in, in, other_vport, 1);
-		}
+		MLX5_SET(modify_flow_table_in, in, vport_number, ft->vport);
+		MLX5_SET(modify_flow_table_in, in, other_vport,
+			 !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT));
 		MLX5_SET(modify_flow_table_in, in, modify_field_select,
 			 MLX5_MODIFY_FLOW_TABLE_MISS_TABLE_ID);
 		if (next_ft) {
@@ -325,6 +320,9 @@ static int mlx5_cmd_create_flow_group(struct mlx5_flow_root_namespace *ns,
 		MLX5_SET(create_flow_group_in, in, other_vport, 1);
 	}
 
+	MLX5_SET(create_flow_group_in, in, vport_number, ft->vport);
+	MLX5_SET(create_flow_group_in, in, other_vport,
+		 !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT));
 	err = mlx5_cmd_exec_inout(dev, create_flow_group, in, out);
 	if (!err)
 		fg->id = MLX5_GET(create_flow_group_out, out,
@@ -344,11 +342,9 @@ static int mlx5_cmd_destroy_flow_group(struct mlx5_flow_root_namespace *ns,
 	MLX5_SET(destroy_flow_group_in, in, table_type, ft->type);
 	MLX5_SET(destroy_flow_group_in, in, table_id, ft->id);
 	MLX5_SET(destroy_flow_group_in, in, group_id, fg->id);
-	if (ft->vport) {
-		MLX5_SET(destroy_flow_group_in, in, vport_number, ft->vport);
-		MLX5_SET(destroy_flow_group_in, in, other_vport, 1);
-	}
-
+	MLX5_SET(destroy_flow_group_in, in, vport_number, ft->vport);
+	MLX5_SET(destroy_flow_group_in, in, other_vport,
+		 !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT));
 	return mlx5_cmd_exec_in(dev, destroy_flow_group, in);
 }
 
@@ -427,10 +423,9 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 	MLX5_SET(set_fte_in, in, ignore_flow_level,
 		 !!(fte->action.flags & FLOW_ACT_IGNORE_FLOW_LEVEL));
 
-	if (ft->vport) {
-		MLX5_SET(set_fte_in, in, vport_number, ft->vport);
-		MLX5_SET(set_fte_in, in, other_vport, 1);
-	}
+	MLX5_SET(set_fte_in, in, vport_number, ft->vport);
+	MLX5_SET(set_fte_in, in, other_vport,
+		 !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT));
 
 	in_flow_context = MLX5_ADDR_OF(set_fte_in, in, flow_context);
 	MLX5_SET(flow_context, in_flow_context, group_id, group_id);
@@ -604,10 +599,9 @@ static int mlx5_cmd_delete_fte(struct mlx5_flow_root_namespace *ns,
 	MLX5_SET(delete_fte_in, in, table_type, ft->type);
 	MLX5_SET(delete_fte_in, in, table_id, ft->id);
 	MLX5_SET(delete_fte_in, in, flow_index, fte->index);
-	if (ft->vport) {
-		MLX5_SET(delete_fte_in, in, vport_number, ft->vport);
-		MLX5_SET(delete_fte_in, in, other_vport, 1);
-	}
+	MLX5_SET(delete_fte_in, in, vport_number, ft->vport);
+	MLX5_SET(delete_fte_in, in, other_vport,
+		 !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT));
 
 	return mlx5_cmd_exec_in(dev, delete_fte, in);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 951f8041fb62..2df8b298d381 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -1147,17 +1147,11 @@ struct mlx5_flow_table *mlx5_create_flow_table(struct mlx5_flow_namespace *ns,
 }
 EXPORT_SYMBOL(mlx5_create_flow_table);
 
-struct mlx5_flow_table *mlx5_create_vport_flow_table(struct mlx5_flow_namespace *ns,
-						     int prio, int max_fte,
-						     u32 level, u16 vport)
+struct mlx5_flow_table *
+mlx5_create_vport_flow_table(struct mlx5_flow_namespace *ns,
+			     struct mlx5_flow_table_attr *ft_attr, u16 vport)
 {
-	struct mlx5_flow_table_attr ft_attr = {};
-
-	ft_attr.max_fte = max_fte;
-	ft_attr.level   = level;
-	ft_attr.prio    = prio;
-
-	return __mlx5_create_flow_table(ns, &ft_attr, FS_FT_OP_MOD_NORMAL, vport);
+	return __mlx5_create_flow_table(ns, ft_attr, FS_FT_OP_MOD_NORMAL, vport);
 }
 
 struct mlx5_flow_table*
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 35d2cc1646d3..1f51f4c3b1af 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -50,6 +50,7 @@ enum {
 	MLX5_FLOW_TABLE_TUNNEL_EN_DECAP = BIT(1),
 	MLX5_FLOW_TABLE_TERMINATION = BIT(2),
 	MLX5_FLOW_TABLE_UNMANAGED = BIT(3),
+	MLX5_FLOW_TABLE_OTHER_VPORT = BIT(4),
 };
 
 #define LEFTOVERS_RULE_NUM	 2
@@ -174,9 +175,7 @@ mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns,
 
 struct mlx5_flow_table *
 mlx5_create_vport_flow_table(struct mlx5_flow_namespace *ns,
-			     int prio,
-			     int num_flow_table_entries,
-			     u32 level, u16 vport);
+			     struct mlx5_flow_table_attr *ft_attr, u16 vport);
 struct mlx5_flow_table *mlx5_create_lag_demux_flow_table(
 					       struct mlx5_flow_namespace *ns,
 					       int prio, u32 level);
-- 
cgit v1.2.3


From 8d8d53cf8fd028310b1189165b939cde124895d7 Mon Sep 17 00:00:00 2001
From: Alexey Kardashevskiy <aik@ozlabs.ru>
Date: Thu, 29 Oct 2020 12:52:40 +1100
Subject: dma-mapping: Allow mixing bypass and mapped DMA operation

At the moment we allow bypassing DMA ops only when we can do this for
the entire RAM. However there are configs with mixed type memory
where we could still allow bypassing IOMMU in most cases;
POWERPC with persistent memory is one example.

This adds an arch hook to determine where bypass can still work and
we invoke direct DMA API. The following patch checks the bus limit
on POWERPC to allow or disallow direct mapping.

This adds a ARCH_HAS_DMA_MAP_DIRECT config option to make the arch_xxxx
hooks no-op by default.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/dma-map-ops.h | 14 ++++++++++++++
 kernel/dma/Kconfig          |  4 ++++
 kernel/dma/mapping.c        | 12 ++++++++----
 3 files changed, 26 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index a5f89fc4d6df..38c8a4558e08 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -314,6 +314,20 @@ static inline void arch_dma_mark_clean(phys_addr_t paddr, size_t size)
 void *arch_dma_set_uncached(void *addr, size_t size);
 void arch_dma_clear_uncached(void *addr, size_t size);
 
+#ifdef CONFIG_ARCH_HAS_DMA_MAP_DIRECT
+bool arch_dma_map_page_direct(struct device *dev, phys_addr_t addr);
+bool arch_dma_unmap_page_direct(struct device *dev, dma_addr_t dma_handle);
+bool arch_dma_map_sg_direct(struct device *dev, struct scatterlist *sg,
+		int nents);
+bool arch_dma_unmap_sg_direct(struct device *dev, struct scatterlist *sg,
+		int nents);
+#else
+#define arch_dma_map_page_direct(d, a)		(false)
+#define arch_dma_unmap_page_direct(d, a)	(false)
+#define arch_dma_map_sg_direct(d, s, n)		(false)
+#define arch_dma_unmap_sg_direct(d, s, n)	(false)
+#endif
+
 #ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 		const struct iommu_ops *iommu, bool coherent);
diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index c99de4a21458..43d106598e82 100644
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@ -20,6 +20,10 @@ config DMA_OPS
 config DMA_OPS_BYPASS
 	bool
 
+# Lets platform IOMMU driver choose between bypass and IOMMU
+config ARCH_HAS_DMA_MAP_DIRECT
+	bool
+
 config NEED_SG_DMA_LENGTH
 	bool
 
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 51bb8fa8eb89..f87a89d08654 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -149,7 +149,8 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
 	if (WARN_ON_ONCE(!dev->dma_mask))
 		return DMA_MAPPING_ERROR;
 
-	if (dma_map_direct(dev, ops))
+	if (dma_map_direct(dev, ops) ||
+	    arch_dma_map_page_direct(dev, page_to_phys(page) + offset + size))
 		addr = dma_direct_map_page(dev, page, offset, size, dir, attrs);
 	else
 		addr = ops->map_page(dev, page, offset, size, dir, attrs);
@@ -165,7 +166,8 @@ void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size,
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	BUG_ON(!valid_dma_direction(dir));
-	if (dma_map_direct(dev, ops))
+	if (dma_map_direct(dev, ops) ||
+	    arch_dma_unmap_page_direct(dev, addr + size))
 		dma_direct_unmap_page(dev, addr, size, dir, attrs);
 	else if (ops->unmap_page)
 		ops->unmap_page(dev, addr, size, dir, attrs);
@@ -188,7 +190,8 @@ int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, int nents,
 	if (WARN_ON_ONCE(!dev->dma_mask))
 		return 0;
 
-	if (dma_map_direct(dev, ops))
+	if (dma_map_direct(dev, ops) ||
+	    arch_dma_map_sg_direct(dev, sg, nents))
 		ents = dma_direct_map_sg(dev, sg, nents, dir, attrs);
 	else
 		ents = ops->map_sg(dev, sg, nents, dir, attrs);
@@ -207,7 +210,8 @@ void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg,
 
 	BUG_ON(!valid_dma_direction(dir));
 	debug_dma_unmap_sg(dev, sg, nents, dir);
-	if (dma_map_direct(dev, ops))
+	if (dma_map_direct(dev, ops) ||
+	    arch_dma_unmap_sg_direct(dev, sg, nents))
 		dma_direct_unmap_sg(dev, sg, nents, dir, attrs);
 	else if (ops->unmap_sg)
 		ops->unmap_sg(dev, sg, nents, dir, attrs);
-- 
cgit v1.2.3


From c7a5899eb26e2a4d516d53f65b6dd67be2228041 Mon Sep 17 00:00:00 2001
From: Antony Antony <antony.antony@secunet.com>
Date: Tue, 17 Nov 2020 17:47:23 +0100
Subject: xfrm: redact SA secret with lockdown confidentiality

redact XFRM SA secret in the netlink response to xfrm_get_sa()
or dumpall sa.
Enable lockdown, confidentiality mode, at boot or at run time.

e.g. when enabled:
cat /sys/kernel/security/lockdown
none integrity [confidentiality]

ip xfrm state
src 172.16.1.200 dst 172.16.1.100
	proto esp spi 0x00000002 reqid 2 mode tunnel
	replay-window 0
	aead rfc4106(gcm(aes)) 0x0000000000000000000000000000000000000000 96

note: the aead secret is redacted.
Redacting secret is also a FIPS 140-2 requirement.

v1->v2
 - add size checks before memset calls
v2->v3
 - replace spaces with tabs for consistency
v3->v4
 - use kernel lockdown instead of a /proc setting
v4->v5
 - remove kconfig option

Reviewed-by: Stephan Mueller <smueller@chronox.de>
Signed-off-by: Antony Antony <antony.antony@secunet.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/linux/security.h |  1 +
 net/xfrm/xfrm_user.c     | 74 +++++++++++++++++++++++++++++++++++++++++++-----
 security/security.c      |  1 +
 3 files changed, 69 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/security.h b/include/linux/security.h
index bc2725491560..1112a79a7dba 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -127,6 +127,7 @@ enum lockdown_reason {
 	LOCKDOWN_PERF,
 	LOCKDOWN_TRACEFS,
 	LOCKDOWN_XMON_RW,
+	LOCKDOWN_XFRM_SECRET,
 	LOCKDOWN_CONFIDENTIALITY_MAX,
 };
 
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index d0c32a8fcc4a..0727ac853b55 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -848,21 +848,84 @@ static int copy_user_offload(struct xfrm_state_offload *xso, struct sk_buff *skb
 	return 0;
 }
 
+static bool xfrm_redact(void)
+{
+	return IS_ENABLED(CONFIG_SECURITY) &&
+		security_locked_down(LOCKDOWN_XFRM_SECRET);
+}
+
 static int copy_to_user_auth(struct xfrm_algo_auth *auth, struct sk_buff *skb)
 {
 	struct xfrm_algo *algo;
+	struct xfrm_algo_auth *ap;
 	struct nlattr *nla;
+	bool redact_secret = xfrm_redact();
 
 	nla = nla_reserve(skb, XFRMA_ALG_AUTH,
 			  sizeof(*algo) + (auth->alg_key_len + 7) / 8);
 	if (!nla)
 		return -EMSGSIZE;
-
 	algo = nla_data(nla);
 	strncpy(algo->alg_name, auth->alg_name, sizeof(algo->alg_name));
-	memcpy(algo->alg_key, auth->alg_key, (auth->alg_key_len + 7) / 8);
+
+	if (redact_secret && auth->alg_key_len)
+		memset(algo->alg_key, 0, (auth->alg_key_len + 7) / 8);
+	else
+		memcpy(algo->alg_key, auth->alg_key,
+		       (auth->alg_key_len + 7) / 8);
 	algo->alg_key_len = auth->alg_key_len;
 
+	nla = nla_reserve(skb, XFRMA_ALG_AUTH_TRUNC, xfrm_alg_auth_len(auth));
+	if (!nla)
+		return -EMSGSIZE;
+	ap = nla_data(nla);
+	memcpy(ap, auth, sizeof(struct xfrm_algo_auth));
+	if (redact_secret && auth->alg_key_len)
+		memset(ap->alg_key, 0, (auth->alg_key_len + 7) / 8);
+	else
+		memcpy(ap->alg_key, auth->alg_key,
+		       (auth->alg_key_len + 7) / 8);
+	return 0;
+}
+
+static int copy_to_user_aead(struct xfrm_algo_aead *aead, struct sk_buff *skb)
+{
+	struct nlattr *nla = nla_reserve(skb, XFRMA_ALG_AEAD, aead_len(aead));
+	struct xfrm_algo_aead *ap;
+	bool redact_secret = xfrm_redact();
+
+	if (!nla)
+		return -EMSGSIZE;
+
+	ap = nla_data(nla);
+	memcpy(ap, aead, sizeof(*aead));
+
+	if (redact_secret && aead->alg_key_len)
+		memset(ap->alg_key, 0, (aead->alg_key_len + 7) / 8);
+	else
+		memcpy(ap->alg_key, aead->alg_key,
+		       (aead->alg_key_len + 7) / 8);
+	return 0;
+}
+
+static int copy_to_user_ealg(struct xfrm_algo *ealg, struct sk_buff *skb)
+{
+	struct xfrm_algo *ap;
+	bool redact_secret = xfrm_redact();
+	struct nlattr *nla = nla_reserve(skb, XFRMA_ALG_CRYPT,
+					 xfrm_alg_len(ealg));
+	if (!nla)
+		return -EMSGSIZE;
+
+	ap = nla_data(nla);
+	memcpy(ap, ealg, sizeof(*ealg));
+
+	if (redact_secret && ealg->alg_key_len)
+		memset(ap->alg_key, 0, (ealg->alg_key_len + 7) / 8);
+	else
+		memcpy(ap->alg_key, ealg->alg_key,
+		       (ealg->alg_key_len + 7) / 8);
+
 	return 0;
 }
 
@@ -906,20 +969,17 @@ static int copy_to_user_state_extra(struct xfrm_state *x,
 			goto out;
 	}
 	if (x->aead) {
-		ret = nla_put(skb, XFRMA_ALG_AEAD, aead_len(x->aead), x->aead);
+		ret = copy_to_user_aead(x->aead, skb);
 		if (ret)
 			goto out;
 	}
 	if (x->aalg) {
 		ret = copy_to_user_auth(x->aalg, skb);
-		if (!ret)
-			ret = nla_put(skb, XFRMA_ALG_AUTH_TRUNC,
-				      xfrm_alg_auth_len(x->aalg), x->aalg);
 		if (ret)
 			goto out;
 	}
 	if (x->ealg) {
-		ret = nla_put(skb, XFRMA_ALG_CRYPT, xfrm_alg_len(x->ealg), x->ealg);
+		ret = copy_to_user_ealg(x->ealg, skb);
 		if (ret)
 			goto out;
 	}
diff --git a/security/security.c b/security/security.c
index a28045dc9e7f..abff77c1c8a7 100644
--- a/security/security.c
+++ b/security/security.c
@@ -65,6 +65,7 @@ const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX+1] = {
 	[LOCKDOWN_PERF] = "unsafe use of perf",
 	[LOCKDOWN_TRACEFS] = "use of tracefs",
 	[LOCKDOWN_XMON_RW] = "xmon read and write access",
+	[LOCKDOWN_XFRM_SECRET] = "xfrm SA secret",
 	[LOCKDOWN_CONFIDENTIALITY_MAX] = "confidentiality",
 };
 
-- 
cgit v1.2.3


From 928296ea5da37838d7127de4b10f47cd97401b13 Mon Sep 17 00:00:00 2001
From: Matthias Brugger <mbrugger@suse.com>
Date: Fri, 30 Oct 2020 12:36:11 +0100
Subject: soc: mediatek: pm_domains: Make bus protection generic

Bus protection is not exclusively done by calling the infracfg misc driver.
Make the calls for setting and clearing the bus protection generic so
that we can use other blocks for it as well.

Signed-off-by: Matthias Brugger <mbrugger@suse.com>
Signed-off-by: Enric Balletbo i Serra <enric.balletbo@collabora.com>
Link: https://lore.kernel.org/r/20201030113622.201188-6-enric.balletbo@collabora.com
Signed-off-by: Matthias Brugger <matthias.bgg@gmail.com>
---
 drivers/soc/mediatek/Kconfig          |  1 -
 drivers/soc/mediatek/mtk-infracfg.c   |  5 ---
 drivers/soc/mediatek/mtk-pm-domains.c | 57 +++++++++++++++++++++++++++--------
 include/linux/soc/mediatek/infracfg.h |  5 +++
 4 files changed, 49 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/soc/mediatek/Kconfig b/drivers/soc/mediatek/Kconfig
index 68d800f9e4a5..67cef12dc585 100644
--- a/drivers/soc/mediatek/Kconfig
+++ b/drivers/soc/mediatek/Kconfig
@@ -48,7 +48,6 @@ config MTK_SCPSYS_PM_DOMAINS
 	bool "MediaTek SCPSYS generic power domain"
 	default ARCH_MEDIATEK
 	depends on PM
-	depends on MTK_INFRACFG
 	select PM_GENERIC_DOMAINS
 	select REGMAP
 	help
diff --git a/drivers/soc/mediatek/mtk-infracfg.c b/drivers/soc/mediatek/mtk-infracfg.c
index 4a123796aad3..0590b68e0d78 100644
--- a/drivers/soc/mediatek/mtk-infracfg.c
+++ b/drivers/soc/mediatek/mtk-infracfg.c
@@ -12,11 +12,6 @@
 #define MTK_POLL_DELAY_US   10
 #define MTK_POLL_TIMEOUT    (jiffies_to_usecs(HZ))
 
-#define INFRA_TOPAXI_PROTECTEN		0x0220
-#define INFRA_TOPAXI_PROTECTSTA1	0x0228
-#define INFRA_TOPAXI_PROTECTEN_SET	0x0260
-#define INFRA_TOPAXI_PROTECTEN_CLR	0x0264
-
 /**
  * mtk_infracfg_set_bus_protection - enable bus protection
  * @infracfg: The infracfg regmap
diff --git a/drivers/soc/mediatek/mtk-pm-domains.c b/drivers/soc/mediatek/mtk-pm-domains.c
index 06a16e45356a..6122701d018f 100644
--- a/drivers/soc/mediatek/mtk-pm-domains.c
+++ b/drivers/soc/mediatek/mtk-pm-domains.c
@@ -86,18 +86,24 @@ static int scpsys_sram_disable(struct scpsys_domain *pd)
 					MTK_POLL_TIMEOUT);
 }
 
-static int scpsys_bus_protect_enable(struct scpsys_domain *pd)
+static int _scpsys_bus_protect_enable(const struct scpsys_bus_prot_data *bpd, struct regmap *regmap)
 {
-	const struct scpsys_bus_prot_data *bpd = pd->data->bp_infracfg;
 	int i, ret;
 
 	for (i = 0; i < SPM_MAX_BUS_PROT_DATA; i++) {
-		if (!bpd[i].bus_prot_mask)
+		u32 val, mask = bpd[i].bus_prot_mask;
+
+		if (!mask)
 			break;
 
-		ret = mtk_infracfg_set_bus_protection(pd->infracfg,
-						      bpd[i].bus_prot_mask,
-						      bpd[i].bus_prot_reg_update);
+		if (bpd[i].bus_prot_reg_update)
+			regmap_set_bits(regmap, bpd[i].bus_prot_set, mask);
+		else
+			regmap_write(regmap, INFRA_TOPAXI_PROTECTEN_SET, mask);
+
+		ret = regmap_read_poll_timeout(regmap, INFRA_TOPAXI_PROTECTSTA1,
+					       val, (val & mask) == mask,
+					       MTK_POLL_DELAY_US, MTK_POLL_TIMEOUT);
 		if (ret)
 			return ret;
 	}
@@ -105,18 +111,34 @@ static int scpsys_bus_protect_enable(struct scpsys_domain *pd)
 	return 0;
 }
 
-static int scpsys_bus_protect_disable(struct scpsys_domain *pd)
+static int scpsys_bus_protect_enable(struct scpsys_domain *pd)
+{
+	int ret;
+
+	ret = _scpsys_bus_protect_enable(pd->data->bp_infracfg, pd->infracfg);
+
+	return ret;
+}
+
+static int _scpsys_bus_protect_disable(const struct scpsys_bus_prot_data *bpd,
+				       struct regmap *regmap)
 {
-	const struct scpsys_bus_prot_data *bpd = pd->data->bp_infracfg;
 	int i, ret;
 
-	for (i = SPM_MAX_BUS_PROT_DATA; i > 0; i--) {
-		if (!bpd[i].bus_prot_mask)
+	for (i = SPM_MAX_BUS_PROT_DATA - 1; i >= 0; i--) {
+		u32 val, mask = bpd[i].bus_prot_mask;
+
+		if (!mask)
 			continue;
 
-		ret = mtk_infracfg_clear_bus_protection(pd->infracfg,
-							bpd[i].bus_prot_mask,
-							bpd[i].bus_prot_reg_update);
+		if (bpd[i].bus_prot_reg_update)
+			regmap_clear_bits(regmap, bpd[i].bus_prot_clr, mask);
+		else
+			regmap_write(regmap, INFRA_TOPAXI_PROTECTEN_CLR, mask);
+
+		ret = regmap_read_poll_timeout(regmap, INFRA_TOPAXI_PROTECTSTA1,
+					       val, !(val & mask),
+					       MTK_POLL_DELAY_US, MTK_POLL_TIMEOUT);
 		if (ret)
 			return ret;
 	}
@@ -124,6 +146,15 @@ static int scpsys_bus_protect_disable(struct scpsys_domain *pd)
 	return 0;
 }
 
+static int scpsys_bus_protect_disable(struct scpsys_domain *pd)
+{
+	int ret;
+
+	ret = _scpsys_bus_protect_disable(pd->data->bp_infracfg, pd->infracfg);
+
+	return ret;
+}
+
 static int scpsys_power_on(struct generic_pm_domain *genpd)
 {
 	struct scpsys_domain *pd = container_of(genpd, struct scpsys_domain, genpd);
diff --git a/include/linux/soc/mediatek/infracfg.h b/include/linux/soc/mediatek/infracfg.h
index 233463d789c6..5bcaab767f6a 100644
--- a/include/linux/soc/mediatek/infracfg.h
+++ b/include/linux/soc/mediatek/infracfg.h
@@ -32,6 +32,11 @@
 #define MT7622_TOP_AXI_PROT_EN_WB		(BIT(2) | BIT(6) | \
 						 BIT(7) | BIT(8))
 
+#define INFRA_TOPAXI_PROTECTEN			0x0220
+#define INFRA_TOPAXI_PROTECTSTA1		0x0228
+#define INFRA_TOPAXI_PROTECTEN_SET		0x0260
+#define INFRA_TOPAXI_PROTECTEN_CLR		0x0264
+
 #define REG_INFRA_MISC				0xf00
 #define F_DDR_4GB_SUPPORT_EN			BIT(13)
 
-- 
cgit v1.2.3


From eb9fa767fbe19d3db7d303e9fde7f3056221ffe1 Mon Sep 17 00:00:00 2001
From: Matthias Brugger <mbrugger@suse.com>
Date: Fri, 30 Oct 2020 12:36:17 +0100
Subject: soc: mediatek: pm-domains: Add support for mt8183

Add the needed board data to support mt8183 SoC.

Signed-off-by: Matthias Brugger <mbrugger@suse.com>
Signed-off-by: Enric Balletbo i Serra <enric.balletbo@collabora.com>
Link: https://lore.kernel.org/r/20201030113622.201188-12-enric.balletbo@collabora.com
Signed-off-by: Matthias Brugger <matthias.bgg@gmail.com>
---
 drivers/soc/mediatek/mt8183-pm-domains.h | 221 +++++++++++++++++++++++++++++++
 drivers/soc/mediatek/mtk-pm-domains.c    |   5 +
 drivers/soc/mediatek/mtk-pm-domains.h    |   1 +
 include/linux/soc/mediatek/infracfg.h    |  46 +++++++
 4 files changed, 273 insertions(+)
 create mode 100644 drivers/soc/mediatek/mt8183-pm-domains.h

(limited to 'include/linux')

diff --git a/drivers/soc/mediatek/mt8183-pm-domains.h b/drivers/soc/mediatek/mt8183-pm-domains.h
new file mode 100644
index 000000000000..8d996c5d2682
--- /dev/null
+++ b/drivers/soc/mediatek/mt8183-pm-domains.h
@@ -0,0 +1,221 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __SOC_MEDIATEK_MT8183_PM_DOMAINS_H
+#define __SOC_MEDIATEK_MT8183_PM_DOMAINS_H
+
+#include "mtk-pm-domains.h"
+#include <dt-bindings/power/mt8183-power.h>
+
+/*
+ * MT8183 power domain support
+ */
+
+static const struct scpsys_domain_data scpsys_domain_data_mt8183[] = {
+	[MT8183_POWER_DOMAIN_AUDIO] = {
+		.sta_mask = PWR_STATUS_AUDIO,
+		.ctl_offs = 0x0314,
+		.sram_pdn_bits = GENMASK(11, 8),
+		.sram_pdn_ack_bits = GENMASK(15, 12),
+	},
+	[MT8183_POWER_DOMAIN_CONN] = {
+		.sta_mask = PWR_STATUS_CONN,
+		.ctl_offs = 0x032c,
+		.sram_pdn_bits = 0,
+		.sram_pdn_ack_bits = 0,
+		.bp_infracfg = {
+			BUS_PROT_WR(MT8183_TOP_AXI_PROT_EN_CONN, MT8183_TOP_AXI_PROT_EN_SET,
+				    MT8183_TOP_AXI_PROT_EN_CLR, MT8183_TOP_AXI_PROT_EN_STA1),
+		},
+	},
+	[MT8183_POWER_DOMAIN_MFG_ASYNC] = {
+		.sta_mask = PWR_STATUS_MFG_ASYNC,
+		.ctl_offs = 0x0334,
+		.sram_pdn_bits = 0,
+		.sram_pdn_ack_bits = 0,
+	},
+	[MT8183_POWER_DOMAIN_MFG] = {
+		.sta_mask = PWR_STATUS_MFG,
+		.ctl_offs = 0x0338,
+		.sram_pdn_bits = GENMASK(8, 8),
+		.sram_pdn_ack_bits = GENMASK(12, 12),
+	},
+	[MT8183_POWER_DOMAIN_MFG_CORE0] = {
+		.sta_mask = BIT(7),
+		.ctl_offs = 0x034c,
+		.sram_pdn_bits = GENMASK(8, 8),
+		.sram_pdn_ack_bits = GENMASK(12, 12),
+	},
+	[MT8183_POWER_DOMAIN_MFG_CORE1] = {
+		.sta_mask = BIT(20),
+		.ctl_offs = 0x0310,
+		.sram_pdn_bits = GENMASK(8, 8),
+		.sram_pdn_ack_bits = GENMASK(12, 12),
+	},
+	[MT8183_POWER_DOMAIN_MFG_2D] = {
+		.sta_mask = PWR_STATUS_MFG_2D,
+		.ctl_offs = 0x0348,
+		.sram_pdn_bits = GENMASK(8, 8),
+		.sram_pdn_ack_bits = GENMASK(12, 12),
+		.bp_infracfg = {
+			BUS_PROT_WR(MT8183_TOP_AXI_PROT_EN_1_MFG, MT8183_TOP_AXI_PROT_EN_1_SET,
+				    MT8183_TOP_AXI_PROT_EN_1_CLR, MT8183_TOP_AXI_PROT_EN_STA1_1),
+			BUS_PROT_WR(MT8183_TOP_AXI_PROT_EN_MFG, MT8183_TOP_AXI_PROT_EN_SET,
+				    MT8183_TOP_AXI_PROT_EN_CLR, MT8183_TOP_AXI_PROT_EN_STA1),
+		},
+	},
+	[MT8183_POWER_DOMAIN_DISP] = {
+		.sta_mask = PWR_STATUS_DISP,
+		.ctl_offs = 0x030c,
+		.sram_pdn_bits = GENMASK(8, 8),
+		.sram_pdn_ack_bits = GENMASK(12, 12),
+		.bp_infracfg = {
+			BUS_PROT_WR(MT8183_TOP_AXI_PROT_EN_1_DISP, MT8183_TOP_AXI_PROT_EN_1_SET,
+				    MT8183_TOP_AXI_PROT_EN_1_CLR, MT8183_TOP_AXI_PROT_EN_STA1_1),
+			BUS_PROT_WR(MT8183_TOP_AXI_PROT_EN_DISP, MT8183_TOP_AXI_PROT_EN_SET,
+				    MT8183_TOP_AXI_PROT_EN_CLR, MT8183_TOP_AXI_PROT_EN_STA1),
+		},
+		.bp_smi = {
+			BUS_PROT_WR(MT8183_SMI_COMMON_SMI_CLAMP_DISP,
+				    MT8183_SMI_COMMON_CLAMP_EN_SET,
+				    MT8183_SMI_COMMON_CLAMP_EN_CLR,
+				    MT8183_SMI_COMMON_CLAMP_EN),
+		},
+	},
+	[MT8183_POWER_DOMAIN_CAM] = {
+		.sta_mask = BIT(25),
+		.ctl_offs = 0x0344,
+		.sram_pdn_bits = GENMASK(9, 8),
+		.sram_pdn_ack_bits = GENMASK(13, 12),
+		.bp_infracfg = {
+			BUS_PROT_WR(MT8183_TOP_AXI_PROT_EN_MM_CAM, MT8183_TOP_AXI_PROT_EN_MM_SET,
+				    MT8183_TOP_AXI_PROT_EN_MM_CLR, MT8183_TOP_AXI_PROT_EN_MM_STA1),
+			BUS_PROT_WR(MT8183_TOP_AXI_PROT_EN_CAM, MT8183_TOP_AXI_PROT_EN_SET,
+				    MT8183_TOP_AXI_PROT_EN_CLR, MT8183_TOP_AXI_PROT_EN_STA1),
+			BUS_PROT_WR_IGN(MT8183_TOP_AXI_PROT_EN_MM_CAM_2ND,
+					MT8183_TOP_AXI_PROT_EN_MM_SET,
+					MT8183_TOP_AXI_PROT_EN_MM_CLR,
+					MT8183_TOP_AXI_PROT_EN_MM_STA1),
+		},
+		.bp_smi = {
+			BUS_PROT_WR(MT8183_SMI_COMMON_SMI_CLAMP_CAM,
+				    MT8183_SMI_COMMON_CLAMP_EN_SET,
+				    MT8183_SMI_COMMON_CLAMP_EN_CLR,
+				    MT8183_SMI_COMMON_CLAMP_EN),
+		},
+	},
+	[MT8183_POWER_DOMAIN_ISP] = {
+		.sta_mask = PWR_STATUS_ISP,
+		.ctl_offs = 0x0308,
+		.sram_pdn_bits = GENMASK(9, 8),
+		.sram_pdn_ack_bits = GENMASK(13, 12),
+		.bp_infracfg = {
+			BUS_PROT_WR(MT8183_TOP_AXI_PROT_EN_MM_ISP,
+				    MT8183_TOP_AXI_PROT_EN_MM_SET,
+				    MT8183_TOP_AXI_PROT_EN_MM_CLR,
+				    MT8183_TOP_AXI_PROT_EN_MM_STA1),
+			BUS_PROT_WR_IGN(MT8183_TOP_AXI_PROT_EN_MM_ISP_2ND,
+					MT8183_TOP_AXI_PROT_EN_MM_SET,
+					MT8183_TOP_AXI_PROT_EN_MM_CLR,
+					MT8183_TOP_AXI_PROT_EN_MM_STA1),
+		},
+		.bp_smi = {
+			BUS_PROT_WR(MT8183_SMI_COMMON_SMI_CLAMP_ISP,
+				    MT8183_SMI_COMMON_CLAMP_EN_SET,
+				    MT8183_SMI_COMMON_CLAMP_EN_CLR,
+				    MT8183_SMI_COMMON_CLAMP_EN),
+		},
+	},
+	[MT8183_POWER_DOMAIN_VDEC] = {
+		.sta_mask = BIT(31),
+		.ctl_offs = 0x0300,
+		.sram_pdn_bits = GENMASK(8, 8),
+		.sram_pdn_ack_bits = GENMASK(12, 12),
+		.bp_smi = {
+			BUS_PROT_WR(MT8183_SMI_COMMON_SMI_CLAMP_VDEC,
+				    MT8183_SMI_COMMON_CLAMP_EN_SET,
+				    MT8183_SMI_COMMON_CLAMP_EN_CLR,
+				    MT8183_SMI_COMMON_CLAMP_EN),
+		},
+	},
+	[MT8183_POWER_DOMAIN_VENC] = {
+		.sta_mask = PWR_STATUS_VENC,
+		.ctl_offs = 0x0304,
+		.sram_pdn_bits = GENMASK(11, 8),
+		.sram_pdn_ack_bits = GENMASK(15, 12),
+		.bp_smi = {
+			BUS_PROT_WR(MT8183_SMI_COMMON_SMI_CLAMP_VENC,
+				    MT8183_SMI_COMMON_CLAMP_EN_SET,
+				    MT8183_SMI_COMMON_CLAMP_EN_CLR,
+				    MT8183_SMI_COMMON_CLAMP_EN),
+		},
+	},
+	[MT8183_POWER_DOMAIN_VPU_TOP] = {
+		.sta_mask = BIT(26),
+		.ctl_offs = 0x0324,
+		.sram_pdn_bits = GENMASK(8, 8),
+		.sram_pdn_ack_bits = GENMASK(12, 12),
+		.bp_infracfg = {
+			BUS_PROT_WR(MT8183_TOP_AXI_PROT_EN_MM_VPU_TOP,
+				    MT8183_TOP_AXI_PROT_EN_MM_SET,
+				    MT8183_TOP_AXI_PROT_EN_MM_CLR,
+				    MT8183_TOP_AXI_PROT_EN_MM_STA1),
+			BUS_PROT_WR(MT8183_TOP_AXI_PROT_EN_VPU_TOP,
+				    MT8183_TOP_AXI_PROT_EN_SET,
+				    MT8183_TOP_AXI_PROT_EN_CLR,
+				    MT8183_TOP_AXI_PROT_EN_STA1),
+			BUS_PROT_WR(MT8183_TOP_AXI_PROT_EN_MM_VPU_TOP_2ND,
+				    MT8183_TOP_AXI_PROT_EN_MM_SET,
+				    MT8183_TOP_AXI_PROT_EN_MM_CLR,
+				    MT8183_TOP_AXI_PROT_EN_MM_STA1),
+		},
+		.bp_smi = {
+			BUS_PROT_WR(MT8183_SMI_COMMON_SMI_CLAMP_VPU_TOP,
+				    MT8183_SMI_COMMON_CLAMP_EN_SET,
+				    MT8183_SMI_COMMON_CLAMP_EN_CLR,
+				    MT8183_SMI_COMMON_CLAMP_EN),
+		},
+	},
+	[MT8183_POWER_DOMAIN_VPU_CORE0] = {
+		.sta_mask = BIT(27),
+		.ctl_offs = 0x33c,
+		.sram_pdn_bits = GENMASK(11, 8),
+		.sram_pdn_ack_bits = GENMASK(13, 12),
+		.bp_infracfg = {
+			BUS_PROT_WR(MT8183_TOP_AXI_PROT_EN_MCU_VPU_CORE0,
+				    MT8183_TOP_AXI_PROT_EN_MCU_SET,
+				    MT8183_TOP_AXI_PROT_EN_MCU_CLR,
+				    MT8183_TOP_AXI_PROT_EN_MCU_STA1),
+			BUS_PROT_WR(MT8183_TOP_AXI_PROT_EN_MCU_VPU_CORE0_2ND,
+				    MT8183_TOP_AXI_PROT_EN_MCU_SET,
+				    MT8183_TOP_AXI_PROT_EN_MCU_CLR,
+				    MT8183_TOP_AXI_PROT_EN_MCU_STA1),
+		},
+		.caps = MTK_SCPD_SRAM_ISO,
+	},
+	[MT8183_POWER_DOMAIN_VPU_CORE1] = {
+		.sta_mask = BIT(28),
+		.ctl_offs = 0x0340,
+		.sram_pdn_bits = GENMASK(11, 8),
+		.sram_pdn_ack_bits = GENMASK(13, 12),
+		.bp_infracfg = {
+			BUS_PROT_WR(MT8183_TOP_AXI_PROT_EN_MCU_VPU_CORE1,
+				    MT8183_TOP_AXI_PROT_EN_MCU_SET,
+				    MT8183_TOP_AXI_PROT_EN_MCU_CLR,
+				    MT8183_TOP_AXI_PROT_EN_MCU_STA1),
+			BUS_PROT_WR(MT8183_TOP_AXI_PROT_EN_MCU_VPU_CORE1_2ND,
+				    MT8183_TOP_AXI_PROT_EN_MCU_SET,
+				    MT8183_TOP_AXI_PROT_EN_MCU_CLR,
+				    MT8183_TOP_AXI_PROT_EN_MCU_STA1),
+		},
+		.caps = MTK_SCPD_SRAM_ISO,
+	},
+};
+
+static const struct scpsys_soc_data mt8183_scpsys_data = {
+	.domains_data = scpsys_domain_data_mt8183,
+	.num_domains = ARRAY_SIZE(scpsys_domain_data_mt8183),
+	.pwr_sta_offs = 0x0180,
+	.pwr_sta2nd_offs = 0x0184
+};
+
+#endif /* __SOC_MEDIATEK_MT8183_PM_DOMAINS_H */
diff --git a/drivers/soc/mediatek/mtk-pm-domains.c b/drivers/soc/mediatek/mtk-pm-domains.c
index 03279a999dfc..8703d50cd2b7 100644
--- a/drivers/soc/mediatek/mtk-pm-domains.c
+++ b/drivers/soc/mediatek/mtk-pm-domains.c
@@ -16,6 +16,7 @@
 #include <linux/soc/mediatek/infracfg.h>
 
 #include "mt8173-pm-domains.h"
+#include "mt8183-pm-domains.h"
 
 #define MTK_POLL_DELAY_US		10
 #define MTK_POLL_TIMEOUT		USEC_PER_SEC
@@ -505,6 +506,10 @@ static const struct of_device_id scpsys_of_match[] = {
 		.compatible = "mediatek,mt8173-power-controller",
 		.data = &mt8173_scpsys_data,
 	},
+	{
+		.compatible = "mediatek,mt8183-power-controller",
+		.data = &mt8183_scpsys_data,
+	},
 	{ }
 };
 
diff --git a/drivers/soc/mediatek/mtk-pm-domains.h b/drivers/soc/mediatek/mtk-pm-domains.h
index 809d2d43f01d..2c745f11b422 100644
--- a/drivers/soc/mediatek/mtk-pm-domains.h
+++ b/drivers/soc/mediatek/mtk-pm-domains.h
@@ -22,6 +22,7 @@
 #define SPM_PWR_STATUS			0x060c
 #define SPM_PWR_STATUS_2ND		0x0610
 
+#define PWR_STATUS_CONN			BIT(1)
 #define PWR_STATUS_DISP			BIT(3)
 #define PWR_STATUS_MFG			BIT(4)
 #define PWR_STATUS_ISP			BIT(5)
diff --git a/include/linux/soc/mediatek/infracfg.h b/include/linux/soc/mediatek/infracfg.h
index 5bcaab767f6a..9d01e32e19bc 100644
--- a/include/linux/soc/mediatek/infracfg.h
+++ b/include/linux/soc/mediatek/infracfg.h
@@ -2,6 +2,52 @@
 #ifndef __SOC_MEDIATEK_INFRACFG_H
 #define __SOC_MEDIATEK_INFRACFG_H
 
+#define MT8183_TOP_AXI_PROT_EN_STA1			0x228
+#define MT8183_TOP_AXI_PROT_EN_STA1_1			0x258
+#define MT8183_TOP_AXI_PROT_EN_SET			0x2a0
+#define MT8183_TOP_AXI_PROT_EN_CLR			0x2a4
+#define MT8183_TOP_AXI_PROT_EN_1_SET			0x2a8
+#define MT8183_TOP_AXI_PROT_EN_1_CLR			0x2ac
+#define MT8183_TOP_AXI_PROT_EN_MCU_SET			0x2c4
+#define MT8183_TOP_AXI_PROT_EN_MCU_CLR			0x2c8
+#define MT8183_TOP_AXI_PROT_EN_MCU_STA1			0x2e4
+#define MT8183_TOP_AXI_PROT_EN_MM_SET			0x2d4
+#define MT8183_TOP_AXI_PROT_EN_MM_CLR			0x2d8
+#define MT8183_TOP_AXI_PROT_EN_MM_STA1			0x2ec
+
+#define MT8183_TOP_AXI_PROT_EN_DISP			(BIT(10) | BIT(11))
+#define MT8183_TOP_AXI_PROT_EN_CONN			(BIT(13) | BIT(14))
+#define MT8183_TOP_AXI_PROT_EN_MFG			(BIT(21) | BIT(22))
+#define MT8183_TOP_AXI_PROT_EN_CAM			BIT(28)
+#define MT8183_TOP_AXI_PROT_EN_VPU_TOP			BIT(27)
+#define MT8183_TOP_AXI_PROT_EN_1_DISP			(BIT(16) | BIT(17))
+#define MT8183_TOP_AXI_PROT_EN_1_MFG			GENMASK(21, 19)
+#define MT8183_TOP_AXI_PROT_EN_MM_ISP			(BIT(3) | BIT(8))
+#define MT8183_TOP_AXI_PROT_EN_MM_ISP_2ND		BIT(10)
+#define MT8183_TOP_AXI_PROT_EN_MM_CAM			(BIT(4) | BIT(5) | \
+							 BIT(9) | BIT(13))
+#define MT8183_TOP_AXI_PROT_EN_MM_VPU_TOP		(GENMASK(9, 6) | \
+							 BIT(12))
+#define MT8183_TOP_AXI_PROT_EN_MM_VPU_TOP_2ND		(BIT(10) | BIT(11))
+#define MT8183_TOP_AXI_PROT_EN_MM_CAM_2ND		BIT(11)
+#define MT8183_TOP_AXI_PROT_EN_MCU_VPU_CORE0_2ND	(BIT(0) | BIT(2) | \
+							 BIT(4))
+#define MT8183_TOP_AXI_PROT_EN_MCU_VPU_CORE1_2ND	(BIT(1) | BIT(3) | \
+							 BIT(5))
+#define MT8183_TOP_AXI_PROT_EN_MCU_VPU_CORE0		BIT(6)
+#define MT8183_TOP_AXI_PROT_EN_MCU_VPU_CORE1		BIT(7)
+
+#define MT8183_SMI_COMMON_CLAMP_EN			0x3c0
+#define MT8183_SMI_COMMON_CLAMP_EN_SET			0x3c4
+#define MT8183_SMI_COMMON_CLAMP_EN_CLR			0x3c8
+
+#define MT8183_SMI_COMMON_SMI_CLAMP_DISP		GENMASK(7, 0)
+#define MT8183_SMI_COMMON_SMI_CLAMP_VENC		BIT(1)
+#define MT8183_SMI_COMMON_SMI_CLAMP_ISP			BIT(2)
+#define MT8183_SMI_COMMON_SMI_CLAMP_CAM			(BIT(3) | BIT(4))
+#define MT8183_SMI_COMMON_SMI_CLAMP_VPU_TOP		(BIT(5) | BIT(6))
+#define MT8183_SMI_COMMON_SMI_CLAMP_VDEC		BIT(7)
+
 #define MT8173_TOP_AXI_PROT_EN_MCI_M2		BIT(0)
 #define MT8173_TOP_AXI_PROT_EN_MM_M0		BIT(1)
 #define MT8173_TOP_AXI_PROT_EN_MM_M1		BIT(2)
-- 
cgit v1.2.3


From a49d5e7a89d644a5c0ddc851be4bbf08614e6015 Mon Sep 17 00:00:00 2001
From: Weiyi Lu <weiyi.lu@mediatek.com>
Date: Fri, 30 Oct 2020 12:36:22 +0100
Subject: soc: mediatek: pm-domains: Add support for mt8192

Add the needed board data to support mt8192 SoC.

Signed-off-by: Weiyi Lu <weiyi.lu@mediatek.com>
Signed-off-by: Enric Balletbo i Serra <enric.balletbo@collabora.com>
Tested-by: Weiyi Lu <weiyi.lu@mediatek.com>
Link: https://lore.kernel.org/r/20201030113622.201188-17-enric.balletbo@collabora.com
Signed-off-by: Matthias Brugger <matthias.bgg@gmail.com>
---
 drivers/soc/mediatek/mt8192-pm-domains.h | 292 +++++++++++++++++++++++++++++++
 drivers/soc/mediatek/mtk-pm-domains.c    |   5 +
 include/linux/soc/mediatek/infracfg.h    |  56 ++++++
 3 files changed, 353 insertions(+)
 create mode 100644 drivers/soc/mediatek/mt8192-pm-domains.h

(limited to 'include/linux')

diff --git a/drivers/soc/mediatek/mt8192-pm-domains.h b/drivers/soc/mediatek/mt8192-pm-domains.h
new file mode 100644
index 000000000000..0fdf6dc6231f
--- /dev/null
+++ b/drivers/soc/mediatek/mt8192-pm-domains.h
@@ -0,0 +1,292 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __SOC_MEDIATEK_MT8192_PM_DOMAINS_H
+#define __SOC_MEDIATEK_MT8192_PM_DOMAINS_H
+
+#include "mtk-pm-domains.h"
+#include <dt-bindings/power/mt8192-power.h>
+
+/*
+ * MT8192 power domain support
+ */
+
+static const struct scpsys_domain_data scpsys_domain_data_mt8192[] = {
+	[MT8192_POWER_DOMAIN_AUDIO] = {
+		.sta_mask = BIT(21),
+		.ctl_offs = 0x0354,
+		.sram_pdn_bits = GENMASK(8, 8),
+		.sram_pdn_ack_bits = GENMASK(12, 12),
+		.bp_infracfg = {
+			BUS_PROT_WR(MT8192_TOP_AXI_PROT_EN_2_AUDIO,
+				    MT8192_TOP_AXI_PROT_EN_2_SET,
+				    MT8192_TOP_AXI_PROT_EN_2_CLR,
+				    MT8192_TOP_AXI_PROT_EN_2_STA1),
+		},
+	},
+	[MT8192_POWER_DOMAIN_CONN] = {
+		.sta_mask = PWR_STATUS_CONN,
+		.ctl_offs = 0x0304,
+		.sram_pdn_bits = 0,
+		.sram_pdn_ack_bits = 0,
+		.bp_infracfg = {
+			BUS_PROT_WR(MT8192_TOP_AXI_PROT_EN_CONN,
+				    MT8192_TOP_AXI_PROT_EN_SET,
+				    MT8192_TOP_AXI_PROT_EN_CLR,
+				    MT8192_TOP_AXI_PROT_EN_STA1),
+			BUS_PROT_WR(MT8192_TOP_AXI_PROT_EN_CONN_2ND,
+				    MT8192_TOP_AXI_PROT_EN_SET,
+				    MT8192_TOP_AXI_PROT_EN_CLR,
+				    MT8192_TOP_AXI_PROT_EN_STA1),
+			BUS_PROT_WR(MT8192_TOP_AXI_PROT_EN_1_CONN,
+				    MT8192_TOP_AXI_PROT_EN_1_SET,
+				    MT8192_TOP_AXI_PROT_EN_1_CLR,
+				    MT8192_TOP_AXI_PROT_EN_1_STA1),
+		},
+		.caps = MTK_SCPD_KEEP_DEFAULT_OFF,
+	},
+	[MT8192_POWER_DOMAIN_MFG0] = {
+		.sta_mask = BIT(2),
+		.ctl_offs = 0x0308,
+		.sram_pdn_bits = GENMASK(8, 8),
+		.sram_pdn_ack_bits = GENMASK(12, 12),
+	},
+	[MT8192_POWER_DOMAIN_MFG1] = {
+		.sta_mask = BIT(3),
+		.ctl_offs = 0x030c,
+		.sram_pdn_bits = GENMASK(8, 8),
+		.sram_pdn_ack_bits = GENMASK(12, 12),
+		.bp_infracfg = {
+			BUS_PROT_WR(MT8192_TOP_AXI_PROT_EN_1_MFG1,
+				    MT8192_TOP_AXI_PROT_EN_1_SET,
+				    MT8192_TOP_AXI_PROT_EN_1_CLR,
+				    MT8192_TOP_AXI_PROT_EN_1_STA1),
+			BUS_PROT_WR(MT8192_TOP_AXI_PROT_EN_2_MFG1,
+				    MT8192_TOP_AXI_PROT_EN_2_SET,
+				    MT8192_TOP_AXI_PROT_EN_2_CLR,
+				    MT8192_TOP_AXI_PROT_EN_2_STA1),
+			BUS_PROT_WR(MT8192_TOP_AXI_PROT_EN_MFG1,
+				    MT8192_TOP_AXI_PROT_EN_SET,
+				    MT8192_TOP_AXI_PROT_EN_CLR,
+				    MT8192_TOP_AXI_PROT_EN_STA1),
+			BUS_PROT_WR(MT8192_TOP_AXI_PROT_EN_2_MFG1_2ND,
+				    MT8192_TOP_AXI_PROT_EN_2_SET,
+				    MT8192_TOP_AXI_PROT_EN_2_CLR,
+				    MT8192_TOP_AXI_PROT_EN_2_STA1),
+		},
+	},
+	[MT8192_POWER_DOMAIN_MFG2] = {
+		.sta_mask = BIT(4),
+		.ctl_offs = 0x0310,
+		.sram_pdn_bits = GENMASK(8, 8),
+		.sram_pdn_ack_bits = GENMASK(12, 12),
+	},
+	[MT8192_POWER_DOMAIN_MFG3] = {
+		.sta_mask = BIT(5),
+		.ctl_offs = 0x0314,
+		.sram_pdn_bits = GENMASK(8, 8),
+		.sram_pdn_ack_bits = GENMASK(12, 12),
+	},
+	[MT8192_POWER_DOMAIN_MFG4] = {
+		.sta_mask = BIT(6),
+		.ctl_offs = 0x0318,
+		.sram_pdn_bits = GENMASK(8, 8),
+		.sram_pdn_ack_bits = GENMASK(12, 12),
+	},
+	[MT8192_POWER_DOMAIN_MFG5] = {
+		.sta_mask = BIT(7),
+		.ctl_offs = 0x031c,
+		.sram_pdn_bits = GENMASK(8, 8),
+		.sram_pdn_ack_bits = GENMASK(12, 12),
+	},
+	[MT8192_POWER_DOMAIN_MFG6] = {
+		.sta_mask = BIT(8),
+		.ctl_offs = 0x0320,
+		.sram_pdn_bits = GENMASK(8, 8),
+		.sram_pdn_ack_bits = GENMASK(12, 12),
+	},
+	[MT8192_POWER_DOMAIN_DISP] = {
+		.sta_mask = BIT(20),
+		.ctl_offs = 0x0350,
+		.sram_pdn_bits = GENMASK(8, 8),
+		.sram_pdn_ack_bits = GENMASK(12, 12),
+		.bp_infracfg = {
+			BUS_PROT_WR_IGN(MT8192_TOP_AXI_PROT_EN_MM_DISP,
+					MT8192_TOP_AXI_PROT_EN_MM_SET,
+					MT8192_TOP_AXI_PROT_EN_MM_CLR,
+					MT8192_TOP_AXI_PROT_EN_MM_STA1),
+			BUS_PROT_WR_IGN(MT8192_TOP_AXI_PROT_EN_MM_2_DISP,
+					MT8192_TOP_AXI_PROT_EN_MM_2_SET,
+					MT8192_TOP_AXI_PROT_EN_MM_2_CLR,
+					MT8192_TOP_AXI_PROT_EN_MM_2_STA1),
+			BUS_PROT_WR(MT8192_TOP_AXI_PROT_EN_DISP,
+				    MT8192_TOP_AXI_PROT_EN_SET,
+				    MT8192_TOP_AXI_PROT_EN_CLR,
+				    MT8192_TOP_AXI_PROT_EN_STA1),
+			BUS_PROT_WR(MT8192_TOP_AXI_PROT_EN_MM_DISP_2ND,
+				    MT8192_TOP_AXI_PROT_EN_MM_SET,
+				    MT8192_TOP_AXI_PROT_EN_MM_CLR,
+				    MT8192_TOP_AXI_PROT_EN_MM_STA1),
+			BUS_PROT_WR(MT8192_TOP_AXI_PROT_EN_MM_2_DISP_2ND,
+				    MT8192_TOP_AXI_PROT_EN_MM_2_SET,
+				    MT8192_TOP_AXI_PROT_EN_MM_2_CLR,
+				    MT8192_TOP_AXI_PROT_EN_MM_2_STA1),
+		},
+	},
+	[MT8192_POWER_DOMAIN_IPE] = {
+		.sta_mask = BIT(14),
+		.ctl_offs = 0x0338,
+		.sram_pdn_bits = GENMASK(8, 8),
+		.sram_pdn_ack_bits = GENMASK(12, 12),
+		.bp_infracfg = {
+			BUS_PROT_WR(MT8192_TOP_AXI_PROT_EN_MM_IPE,
+				    MT8192_TOP_AXI_PROT_EN_MM_SET,
+				    MT8192_TOP_AXI_PROT_EN_MM_CLR,
+				    MT8192_TOP_AXI_PROT_EN_MM_STA1),
+			BUS_PROT_WR(MT8192_TOP_AXI_PROT_EN_MM_IPE_2ND,
+				    MT8192_TOP_AXI_PROT_EN_MM_SET,
+				    MT8192_TOP_AXI_PROT_EN_MM_CLR,
+				    MT8192_TOP_AXI_PROT_EN_MM_STA1),
+		},
+	},
+	[MT8192_POWER_DOMAIN_ISP] = {
+		.sta_mask = BIT(12),
+		.ctl_offs = 0x0330,
+		.sram_pdn_bits = GENMASK(8, 8),
+		.sram_pdn_ack_bits = GENMASK(12, 12),
+		.bp_infracfg = {
+			BUS_PROT_WR(MT8192_TOP_AXI_PROT_EN_MM_2_ISP,
+				    MT8192_TOP_AXI_PROT_EN_MM_2_SET,
+				    MT8192_TOP_AXI_PROT_EN_MM_2_CLR,
+				    MT8192_TOP_AXI_PROT_EN_MM_2_STA1),
+			BUS_PROT_WR(MT8192_TOP_AXI_PROT_EN_MM_2_ISP_2ND,
+				    MT8192_TOP_AXI_PROT_EN_MM_2_SET,
+				    MT8192_TOP_AXI_PROT_EN_MM_2_CLR,
+				    MT8192_TOP_AXI_PROT_EN_MM_2_STA1),
+		},
+	},
+	[MT8192_POWER_DOMAIN_ISP2] = {
+		.sta_mask = BIT(13),
+		.ctl_offs = 0x0334,
+		.sram_pdn_bits = GENMASK(8, 8),
+		.sram_pdn_ack_bits = GENMASK(12, 12),
+		.bp_infracfg = {
+			BUS_PROT_WR(MT8192_TOP_AXI_PROT_EN_MM_ISP2,
+				    MT8192_TOP_AXI_PROT_EN_MM_SET,
+				    MT8192_TOP_AXI_PROT_EN_MM_CLR,
+				    MT8192_TOP_AXI_PROT_EN_MM_STA1),
+			BUS_PROT_WR(MT8192_TOP_AXI_PROT_EN_MM_ISP2_2ND,
+				    MT8192_TOP_AXI_PROT_EN_MM_SET,
+				    MT8192_TOP_AXI_PROT_EN_MM_CLR,
+				    MT8192_TOP_AXI_PROT_EN_MM_STA1),
+		},
+	},
+	[MT8192_POWER_DOMAIN_MDP] = {
+		.sta_mask = BIT(19),
+		.ctl_offs = 0x034c,
+		.sram_pdn_bits = GENMASK(8, 8),
+		.sram_pdn_ack_bits = GENMASK(12, 12),
+		.bp_infracfg = {
+			BUS_PROT_WR(MT8192_TOP_AXI_PROT_EN_MM_2_MDP,
+				    MT8192_TOP_AXI_PROT_EN_MM_2_SET,
+				    MT8192_TOP_AXI_PROT_EN_MM_2_CLR,
+				    MT8192_TOP_AXI_PROT_EN_MM_2_STA1),
+			BUS_PROT_WR(MT8192_TOP_AXI_PROT_EN_MM_2_MDP_2ND,
+				    MT8192_TOP_AXI_PROT_EN_MM_2_SET,
+				    MT8192_TOP_AXI_PROT_EN_MM_2_CLR,
+				    MT8192_TOP_AXI_PROT_EN_MM_2_STA1),
+		},
+	},
+	[MT8192_POWER_DOMAIN_VENC] = {
+		.sta_mask = BIT(17),
+		.ctl_offs = 0x0344,
+		.sram_pdn_bits = GENMASK(8, 8),
+		.sram_pdn_ack_bits = GENMASK(12, 12),
+		.bp_infracfg = {
+			BUS_PROT_WR(MT8192_TOP_AXI_PROT_EN_MM_VENC,
+				    MT8192_TOP_AXI_PROT_EN_MM_SET,
+				    MT8192_TOP_AXI_PROT_EN_MM_CLR,
+				    MT8192_TOP_AXI_PROT_EN_MM_STA1),
+			BUS_PROT_WR(MT8192_TOP_AXI_PROT_EN_MM_VENC_2ND,
+				    MT8192_TOP_AXI_PROT_EN_MM_SET,
+				    MT8192_TOP_AXI_PROT_EN_MM_CLR,
+				    MT8192_TOP_AXI_PROT_EN_MM_STA1),
+		},
+	},
+	[MT8192_POWER_DOMAIN_VDEC] = {
+		.sta_mask = BIT(15),
+		.ctl_offs = 0x033c,
+		.sram_pdn_bits = GENMASK(8, 8),
+		.sram_pdn_ack_bits = GENMASK(12, 12),
+		.bp_infracfg = {
+			BUS_PROT_WR(MT8192_TOP_AXI_PROT_EN_MM_VDEC,
+				    MT8192_TOP_AXI_PROT_EN_MM_SET,
+				    MT8192_TOP_AXI_PROT_EN_MM_CLR,
+				    MT8192_TOP_AXI_PROT_EN_MM_STA1),
+			BUS_PROT_WR(MT8192_TOP_AXI_PROT_EN_MM_VDEC_2ND,
+				    MT8192_TOP_AXI_PROT_EN_MM_SET,
+				    MT8192_TOP_AXI_PROT_EN_MM_CLR,
+				    MT8192_TOP_AXI_PROT_EN_MM_STA1),
+		},
+	},
+	[MT8192_POWER_DOMAIN_VDEC2] = {
+		.sta_mask = BIT(16),
+		.ctl_offs = 0x0340,
+		.sram_pdn_bits = GENMASK(8, 8),
+		.sram_pdn_ack_bits = GENMASK(12, 12),
+	},
+	[MT8192_POWER_DOMAIN_CAM] = {
+		.sta_mask = BIT(23),
+		.ctl_offs = 0x035c,
+		.sram_pdn_bits = GENMASK(8, 8),
+		.sram_pdn_ack_bits = GENMASK(12, 12),
+		.bp_infracfg = {
+			BUS_PROT_WR(MT8192_TOP_AXI_PROT_EN_2_CAM,
+				    MT8192_TOP_AXI_PROT_EN_2_SET,
+				    MT8192_TOP_AXI_PROT_EN_2_CLR,
+				    MT8192_TOP_AXI_PROT_EN_2_STA1),
+			BUS_PROT_WR(MT8192_TOP_AXI_PROT_EN_MM_CAM,
+				    MT8192_TOP_AXI_PROT_EN_MM_SET,
+				    MT8192_TOP_AXI_PROT_EN_MM_CLR,
+				    MT8192_TOP_AXI_PROT_EN_MM_STA1),
+			BUS_PROT_WR(MT8192_TOP_AXI_PROT_EN_1_CAM,
+				    MT8192_TOP_AXI_PROT_EN_1_SET,
+				    MT8192_TOP_AXI_PROT_EN_1_CLR,
+				    MT8192_TOP_AXI_PROT_EN_1_STA1),
+			BUS_PROT_WR(MT8192_TOP_AXI_PROT_EN_MM_CAM_2ND,
+				    MT8192_TOP_AXI_PROT_EN_MM_SET,
+				    MT8192_TOP_AXI_PROT_EN_MM_CLR,
+				    MT8192_TOP_AXI_PROT_EN_MM_STA1),
+			BUS_PROT_WR(MT8192_TOP_AXI_PROT_EN_VDNR_CAM,
+				    MT8192_TOP_AXI_PROT_EN_VDNR_SET,
+				    MT8192_TOP_AXI_PROT_EN_VDNR_CLR,
+				    MT8192_TOP_AXI_PROT_EN_VDNR_STA1),
+		},
+	},
+	[MT8192_POWER_DOMAIN_CAM_RAWA] = {
+		.sta_mask = BIT(24),
+		.ctl_offs = 0x0360,
+		.sram_pdn_bits = GENMASK(8, 8),
+		.sram_pdn_ack_bits = GENMASK(12, 12),
+	},
+	[MT8192_POWER_DOMAIN_CAM_RAWB] = {
+		.sta_mask = BIT(25),
+		.ctl_offs = 0x0364,
+		.sram_pdn_bits = GENMASK(8, 8),
+		.sram_pdn_ack_bits = GENMASK(12, 12),
+	},
+	[MT8192_POWER_DOMAIN_CAM_RAWC] = {
+		.sta_mask = BIT(26),
+		.ctl_offs = 0x0368,
+		.sram_pdn_bits = GENMASK(8, 8),
+		.sram_pdn_ack_bits = GENMASK(12, 12),
+	},
+};
+
+static const struct scpsys_soc_data mt8192_scpsys_data = {
+	.domains_data = scpsys_domain_data_mt8192,
+	.num_domains = ARRAY_SIZE(scpsys_domain_data_mt8192),
+	.pwr_sta_offs = 0x016c,
+	.pwr_sta2nd_offs = 0x0170,
+};
+
+#endif /* __SOC_MEDIATEK_MT8192_PM_DOMAINS_H */
diff --git a/drivers/soc/mediatek/mtk-pm-domains.c b/drivers/soc/mediatek/mtk-pm-domains.c
index c3b85b69f2f7..fb70cb3b07b3 100644
--- a/drivers/soc/mediatek/mtk-pm-domains.c
+++ b/drivers/soc/mediatek/mtk-pm-domains.c
@@ -17,6 +17,7 @@
 
 #include "mt8173-pm-domains.h"
 #include "mt8183-pm-domains.h"
+#include "mt8192-pm-domains.h"
 
 #define MTK_POLL_DELAY_US		10
 #define MTK_POLL_TIMEOUT		USEC_PER_SEC
@@ -521,6 +522,10 @@ static const struct of_device_id scpsys_of_match[] = {
 		.compatible = "mediatek,mt8183-power-controller",
 		.data = &mt8183_scpsys_data,
 	},
+	{
+		.compatible = "mediatek,mt8192-power-controller",
+		.data = &mt8192_scpsys_data,
+	},
 	{ }
 };
 
diff --git a/include/linux/soc/mediatek/infracfg.h b/include/linux/soc/mediatek/infracfg.h
index 9d01e32e19bc..e7842debc05d 100644
--- a/include/linux/soc/mediatek/infracfg.h
+++ b/include/linux/soc/mediatek/infracfg.h
@@ -2,6 +2,62 @@
 #ifndef __SOC_MEDIATEK_INFRACFG_H
 #define __SOC_MEDIATEK_INFRACFG_H
 
+#define MT8192_TOP_AXI_PROT_EN_STA1			0x228
+#define MT8192_TOP_AXI_PROT_EN_1_STA1			0x258
+#define MT8192_TOP_AXI_PROT_EN_SET			0x2a0
+#define MT8192_TOP_AXI_PROT_EN_CLR			0x2a4
+#define MT8192_TOP_AXI_PROT_EN_1_SET			0x2a8
+#define MT8192_TOP_AXI_PROT_EN_1_CLR			0x2ac
+#define MT8192_TOP_AXI_PROT_EN_MM_SET			0x2d4
+#define MT8192_TOP_AXI_PROT_EN_MM_CLR			0x2d8
+#define MT8192_TOP_AXI_PROT_EN_MM_STA1			0x2ec
+#define MT8192_TOP_AXI_PROT_EN_2_SET			0x714
+#define MT8192_TOP_AXI_PROT_EN_2_CLR			0x718
+#define MT8192_TOP_AXI_PROT_EN_2_STA1			0x724
+#define MT8192_TOP_AXI_PROT_EN_VDNR_SET			0xb84
+#define MT8192_TOP_AXI_PROT_EN_VDNR_CLR			0xb88
+#define MT8192_TOP_AXI_PROT_EN_VDNR_STA1		0xb90
+#define MT8192_TOP_AXI_PROT_EN_MM_2_SET			0xdcc
+#define MT8192_TOP_AXI_PROT_EN_MM_2_CLR			0xdd0
+#define MT8192_TOP_AXI_PROT_EN_MM_2_STA1		0xdd8
+
+#define MT8192_TOP_AXI_PROT_EN_DISP			(BIT(6) | BIT(23))
+#define MT8192_TOP_AXI_PROT_EN_CONN			(BIT(13) | BIT(18))
+#define MT8192_TOP_AXI_PROT_EN_CONN_2ND			BIT(14)
+#define MT8192_TOP_AXI_PROT_EN_MFG1			GENMASK(22, 21)
+#define MT8192_TOP_AXI_PROT_EN_1_CONN			BIT(10)
+#define MT8192_TOP_AXI_PROT_EN_1_MFG1			BIT(21)
+#define MT8192_TOP_AXI_PROT_EN_1_CAM			BIT(22)
+#define MT8192_TOP_AXI_PROT_EN_2_CAM			BIT(0)
+#define MT8192_TOP_AXI_PROT_EN_2_ADSP			BIT(3)
+#define MT8192_TOP_AXI_PROT_EN_2_AUDIO			BIT(4)
+#define MT8192_TOP_AXI_PROT_EN_2_MFG1			GENMASK(6, 5)
+#define MT8192_TOP_AXI_PROT_EN_2_MFG1_2ND		BIT(7)
+#define MT8192_TOP_AXI_PROT_EN_MM_CAM			(BIT(0) | BIT(2))
+#define MT8192_TOP_AXI_PROT_EN_MM_DISP			(BIT(0) | BIT(2) | \
+							BIT(10) | BIT(12) | \
+							BIT(14) | BIT(16) | \
+							BIT(24) | BIT(26))
+#define MT8192_TOP_AXI_PROT_EN_MM_CAM_2ND		(BIT(1) | BIT(3))
+#define MT8192_TOP_AXI_PROT_EN_MM_DISP_2ND		(BIT(1) | BIT(3) | \
+							BIT(15) | BIT(17) | \
+							BIT(25) | BIT(27))
+#define MT8192_TOP_AXI_PROT_EN_MM_ISP2			BIT(14)
+#define MT8192_TOP_AXI_PROT_EN_MM_ISP2_2ND		BIT(15)
+#define MT8192_TOP_AXI_PROT_EN_MM_IPE			BIT(16)
+#define MT8192_TOP_AXI_PROT_EN_MM_IPE_2ND		BIT(17)
+#define MT8192_TOP_AXI_PROT_EN_MM_VDEC			BIT(24)
+#define MT8192_TOP_AXI_PROT_EN_MM_VDEC_2ND		BIT(25)
+#define MT8192_TOP_AXI_PROT_EN_MM_VENC			BIT(26)
+#define MT8192_TOP_AXI_PROT_EN_MM_VENC_2ND		BIT(27)
+#define MT8192_TOP_AXI_PROT_EN_MM_2_ISP			BIT(8)
+#define MT8192_TOP_AXI_PROT_EN_MM_2_DISP		(BIT(8) | BIT(12))
+#define MT8192_TOP_AXI_PROT_EN_MM_2_ISP_2ND		BIT(9)
+#define MT8192_TOP_AXI_PROT_EN_MM_2_DISP_2ND		(BIT(9) | BIT(13))
+#define MT8192_TOP_AXI_PROT_EN_MM_2_MDP			BIT(12)
+#define MT8192_TOP_AXI_PROT_EN_MM_2_MDP_2ND		BIT(13)
+#define MT8192_TOP_AXI_PROT_EN_VDNR_CAM			BIT(21)
+
 #define MT8183_TOP_AXI_PROT_EN_STA1			0x228
 #define MT8183_TOP_AXI_PROT_EN_STA1_1			0x258
 #define MT8183_TOP_AXI_PROT_EN_SET			0x2a0
-- 
cgit v1.2.3


From 431ec7bd4d52caa2fc20fbe87744f522e3d1efad Mon Sep 17 00:00:00 2001
From: Michael Klein <michael@fossekall.de>
Date: Fri, 27 Nov 2020 13:52:01 +0100
Subject: mfd: si476x-core.h: Fix "regulator" spelling in comment

"regualtor" -> "regulator"

Signed-off-by: Michael Klein <michael@fossekall.de>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/mfd/si476x-core.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/mfd/si476x-core.h b/include/linux/mfd/si476x-core.h
index 4708c2b8512a..dd95c37ca134 100644
--- a/include/linux/mfd/si476x-core.h
+++ b/include/linux/mfd/si476x-core.h
@@ -57,7 +57,7 @@ enum si476x_mfd_cells {
  * @SI476X_POWER_DOWN: In this state all regulators are turned off
  * and the reset line is pulled low. The device is completely
  * inactive.
- * @SI476X_POWER_UP_FULL: In this state all the power regualtors are
+ * @SI476X_POWER_UP_FULL: In this state all the power regulators are
  * turned on, reset line pulled high, IRQ line is enabled(polling is
  * active for polling use scenario) and device is turned on with
  * POWER_UP command. The device is ready to be used.
-- 
cgit v1.2.3


From 6a0eaf5123e0e1223252b88cd5775f74105e27bd Mon Sep 17 00:00:00 2001
From: Dean Camera <dean@fourwalledcubicle.com>
Date: Thu, 26 Nov 2020 09:39:34 +1100
Subject: HID: Increase HID maximum report size to 16KB

Currently the maximum HID report size which can be buffered by the kernel is
8KB. This is sufficient for the vast majority of HID devices on the market, as
most HID reports are fairly small.

However, some unusual devices such as the Elgate Stream Deck exist which use a
report size slightly over 8KB for the image data that is sent to the device.
Reports these large cannot be buffered by the regular HID subsystem currently,
thus the only way to use such device is to bypass the HID subsystem entirely.

This increases the maximum HID report size to 16KB, which should cover all
sanely designed HID devices.

Signed-off-by: Dean Camera <dean@fourwalledcubicle.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 include/linux/hid.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/hid.h b/include/linux/hid.h
index b079146850e6..c39d71eb1fd0 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -494,7 +494,7 @@ struct hid_report_enum {
 };
 
 #define HID_MIN_BUFFER_SIZE	64		/* make sure there is at least a packet size of space */
-#define HID_MAX_BUFFER_SIZE	8192		/* 8kb */
+#define HID_MAX_BUFFER_SIZE	16384		/* 16kb */
 #define HID_CONTROL_FIFO_SIZE	256		/* to init devices with >100 reports */
 #define HID_OUTPUT_FIFO_SIZE	64
 
-- 
cgit v1.2.3


From fd3bb8f54a88107570334c156efb0c724a261003 Mon Sep 17 00:00:00 2001
From: Evan Green <evgreen@chromium.org>
Date: Fri, 27 Nov 2020 10:28:34 +0000
Subject: nvmem: core: Add support for keepout regions

Introduce support into the nvmem core for arrays of register ranges
that should not result in actual device access. For these regions a
constant byte (repeated) is returned instead on read, and writes are
quietly ignored and returned as successful.

This is useful for instance if certain efuse regions are protected
from access by Linux because they contain secret info to another part
of the system (like an integrated modem).

Signed-off-by: Evan Green <evgreen@chromium.org>
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20201127102837.19366-3-srinivas.kandagatla@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/nvmem/core.c           | 153 +++++++++++++++++++++++++++++++++++++++--
 include/linux/nvmem-provider.h |  17 +++++
 2 files changed, 166 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index a09ff8409f60..177f5bf27c6d 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -34,6 +34,8 @@ struct nvmem_device {
 	struct bin_attribute	eeprom;
 	struct device		*base_dev;
 	struct list_head	cells;
+	const struct nvmem_keepout *keepout;
+	unsigned int		nkeepout;
 	nvmem_reg_read_t	reg_read;
 	nvmem_reg_write_t	reg_write;
 	struct gpio_desc	*wp_gpio;
@@ -66,8 +68,8 @@ static LIST_HEAD(nvmem_lookup_list);
 
 static BLOCKING_NOTIFIER_HEAD(nvmem_notifier);
 
-static int nvmem_reg_read(struct nvmem_device *nvmem, unsigned int offset,
-			  void *val, size_t bytes)
+static int __nvmem_reg_read(struct nvmem_device *nvmem, unsigned int offset,
+			    void *val, size_t bytes)
 {
 	if (nvmem->reg_read)
 		return nvmem->reg_read(nvmem->priv, offset, val, bytes);
@@ -75,8 +77,8 @@ static int nvmem_reg_read(struct nvmem_device *nvmem, unsigned int offset,
 	return -EINVAL;
 }
 
-static int nvmem_reg_write(struct nvmem_device *nvmem, unsigned int offset,
-			   void *val, size_t bytes)
+static int __nvmem_reg_write(struct nvmem_device *nvmem, unsigned int offset,
+			     void *val, size_t bytes)
 {
 	int ret;
 
@@ -90,6 +92,88 @@ static int nvmem_reg_write(struct nvmem_device *nvmem, unsigned int offset,
 	return -EINVAL;
 }
 
+static int nvmem_access_with_keepouts(struct nvmem_device *nvmem,
+				      unsigned int offset, void *val,
+				      size_t bytes, int write)
+{
+
+	unsigned int end = offset + bytes;
+	unsigned int kend, ksize;
+	const struct nvmem_keepout *keepout = nvmem->keepout;
+	const struct nvmem_keepout *keepoutend = keepout + nvmem->nkeepout;
+	int rc;
+
+	/*
+	 * Skip all keepouts before the range being accessed.
+	 * Keepouts are sorted.
+	 */
+	while ((keepout < keepoutend) && (keepout->end <= offset))
+		keepout++;
+
+	while ((offset < end) && (keepout < keepoutend)) {
+		/* Access the valid portion before the keepout. */
+		if (offset < keepout->start) {
+			kend = min(end, keepout->start);
+			ksize = kend - offset;
+			if (write)
+				rc = __nvmem_reg_write(nvmem, offset, val, ksize);
+			else
+				rc = __nvmem_reg_read(nvmem, offset, val, ksize);
+
+			if (rc)
+				return rc;
+
+			offset += ksize;
+			val += ksize;
+		}
+
+		/*
+		 * Now we're aligned to the start of this keepout zone. Go
+		 * through it.
+		 */
+		kend = min(end, keepout->end);
+		ksize = kend - offset;
+		if (!write)
+			memset(val, keepout->value, ksize);
+
+		val += ksize;
+		offset += ksize;
+		keepout++;
+	}
+
+	/*
+	 * If we ran out of keepouts but there's still stuff to do, send it
+	 * down directly
+	 */
+	if (offset < end) {
+		ksize = end - offset;
+		if (write)
+			return __nvmem_reg_write(nvmem, offset, val, ksize);
+		else
+			return __nvmem_reg_read(nvmem, offset, val, ksize);
+	}
+
+	return 0;
+}
+
+static int nvmem_reg_read(struct nvmem_device *nvmem, unsigned int offset,
+			  void *val, size_t bytes)
+{
+	if (!nvmem->nkeepout)
+		return __nvmem_reg_read(nvmem, offset, val, bytes);
+
+	return nvmem_access_with_keepouts(nvmem, offset, val, bytes, false);
+}
+
+static int nvmem_reg_write(struct nvmem_device *nvmem, unsigned int offset,
+			   void *val, size_t bytes)
+{
+	if (!nvmem->nkeepout)
+		return __nvmem_reg_write(nvmem, offset, val, bytes);
+
+	return nvmem_access_with_keepouts(nvmem, offset, val, bytes, true);
+}
+
 #ifdef CONFIG_NVMEM_SYSFS
 static const char * const nvmem_type_str[] = {
 	[NVMEM_TYPE_UNKNOWN] = "Unknown",
@@ -533,6 +617,59 @@ nvmem_find_cell_by_name(struct nvmem_device *nvmem, const char *cell_id)
 	return cell;
 }
 
+static int nvmem_validate_keepouts(struct nvmem_device *nvmem)
+{
+	unsigned int cur = 0;
+	const struct nvmem_keepout *keepout = nvmem->keepout;
+	const struct nvmem_keepout *keepoutend = keepout + nvmem->nkeepout;
+
+	while (keepout < keepoutend) {
+		/* Ensure keepouts are sorted and don't overlap. */
+		if (keepout->start < cur) {
+			dev_err(&nvmem->dev,
+				"Keepout regions aren't sorted or overlap.\n");
+
+			return -ERANGE;
+		}
+
+		if (keepout->end < keepout->start) {
+			dev_err(&nvmem->dev,
+				"Invalid keepout region.\n");
+
+			return -EINVAL;
+		}
+
+		/*
+		 * Validate keepouts (and holes between) don't violate
+		 * word_size constraints.
+		 */
+		if ((keepout->end - keepout->start < nvmem->word_size) ||
+		    ((keepout->start != cur) &&
+		     (keepout->start - cur < nvmem->word_size))) {
+
+			dev_err(&nvmem->dev,
+				"Keepout regions violate word_size constraints.\n");
+
+			return -ERANGE;
+		}
+
+		/* Validate keepouts don't violate stride (alignment). */
+		if (!IS_ALIGNED(keepout->start, nvmem->stride) ||
+		    !IS_ALIGNED(keepout->end, nvmem->stride)) {
+
+			dev_err(&nvmem->dev,
+				"Keepout regions violate stride.\n");
+
+			return -EINVAL;
+		}
+
+		cur = keepout->end;
+		keepout++;
+	}
+
+	return 0;
+}
+
 static int nvmem_add_cells_from_of(struct nvmem_device *nvmem)
 {
 	struct device_node *parent, *child;
@@ -647,6 +784,8 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config)
 	nvmem->type = config->type;
 	nvmem->reg_read = config->reg_read;
 	nvmem->reg_write = config->reg_write;
+	nvmem->keepout = config->keepout;
+	nvmem->nkeepout = config->nkeepout;
 	if (!config->no_of_node)
 		nvmem->dev.of_node = config->dev->of_node;
 
@@ -671,6 +810,12 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config)
 	nvmem->dev.groups = nvmem_dev_groups;
 #endif
 
+	if (nvmem->nkeepout) {
+		rval = nvmem_validate_keepouts(nvmem);
+		if (rval)
+			goto err_put_device;
+	}
+
 	dev_dbg(&nvmem->dev, "Registering nvmem device %s\n", config->name);
 
 	rval = device_register(&nvmem->dev);
diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h
index 06409a6c40bc..e162b757b6d5 100644
--- a/include/linux/nvmem-provider.h
+++ b/include/linux/nvmem-provider.h
@@ -30,6 +30,19 @@ enum nvmem_type {
 #define NVMEM_DEVID_NONE	(-1)
 #define NVMEM_DEVID_AUTO	(-2)
 
+/**
+ * struct nvmem_keepout - NVMEM register keepout range.
+ *
+ * @start:	The first byte offset to avoid.
+ * @end:	One beyond the last byte offset to avoid.
+ * @value:	The byte to fill reads with for this region.
+ */
+struct nvmem_keepout {
+	unsigned int start;
+	unsigned int end;
+	unsigned char value;
+};
+
 /**
  * struct nvmem_config - NVMEM device configuration
  *
@@ -39,6 +52,8 @@ enum nvmem_type {
  * @owner:	Pointer to exporter module. Used for refcounting.
  * @cells:	Optional array of pre-defined NVMEM cells.
  * @ncells:	Number of elements in cells.
+ * @keepout:	Optional array of keepout ranges (sorted ascending by start).
+ * @nkeepout:	Number of elements in the keepout array.
  * @type:	Type of the nvmem storage
  * @read_only:	Device is read-only.
  * @root_only:	Device is accessibly to root only.
@@ -66,6 +81,8 @@ struct nvmem_config {
 	struct gpio_desc	*wp_gpio;
 	const struct nvmem_cell_info	*cells;
 	int			ncells;
+	const struct nvmem_keepout *keepout;
+	unsigned int		nkeepout;
 	enum nvmem_type		type;
 	bool			read_only;
 	bool			root_only;
-- 
cgit v1.2.3


From 24c8a743336a1fdf42c0c768b4435633069c6a39 Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Wed, 30 Sep 2020 20:48:02 +0200
Subject: pcmcia: at91_cf: move definitions locally

struct at91_cf_data is only used in the driver since all the platforms moved
to device tree, move its definition locally.

Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Link: https://lore.kernel.org/r/20200930184804.3127757-1-alexandre.belloni@bootlin.com
---
 drivers/pcmcia/at91_cf.c            | 12 +++++++++++-
 include/linux/platform_data/atmel.h | 12 ------------
 2 files changed, 11 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/pcmcia/at91_cf.c b/drivers/pcmcia/at91_cf.c
index 7db0e9c74dfc..ed60c4dffecb 100644
--- a/drivers/pcmcia/at91_cf.c
+++ b/drivers/pcmcia/at91_cf.c
@@ -13,7 +13,6 @@
 #include <linux/interrupt.h>
 #include <linux/slab.h>
 #include <linux/gpio.h>
-#include <linux/platform_data/atmel.h>
 #include <linux/io.h>
 #include <linux/sizes.h>
 #include <linux/mfd/syscon.h>
@@ -35,6 +34,17 @@
 #define	CF_IO_PHYS	(1 << 23)
 #define	CF_MEM_PHYS	(0x017ff800)
 
+struct at91_cf_data {
+	int	irq_pin;		/* I/O IRQ */
+	int	det_pin;		/* Card detect */
+	int	vcc_pin;		/* power switching */
+	int	rst_pin;		/* card reset */
+	u8	chipselect;		/* EBI Chip Select number */
+	u8	flags;
+#define AT91_CF_TRUE_IDE	0x01
+#define AT91_IDE_SWAP_A0_A2	0x02
+};
+
 struct regmap *mc;
 
 /*--------------------------------------------------------------------------*/
diff --git a/include/linux/platform_data/atmel.h b/include/linux/platform_data/atmel.h
index 99e6069c5fd8..73f63be509c4 100644
--- a/include/linux/platform_data/atmel.h
+++ b/include/linux/platform_data/atmel.h
@@ -6,18 +6,6 @@
 #ifndef __ATMEL_H__
 #define __ATMEL_H__
 
- /* Compact Flash */
-struct at91_cf_data {
-	int	irq_pin;		/* I/O IRQ */
-	int	det_pin;		/* Card detect */
-	int	vcc_pin;		/* power switching */
-	int	rst_pin;		/* card reset */
-	u8	chipselect;		/* EBI Chip Select number */
-	u8	flags;
-#define AT91_CF_TRUE_IDE	0x01
-#define AT91_IDE_SWAP_A0_A2	0x02
-};
-
 /* FIXME: this needs a better location, but gets stuff building again */
 #ifdef CONFIG_ATMEL_PM
 extern int at91_suspend_entering_slow_clock(void);
-- 
cgit v1.2.3


From a69dcdfc2dd21f86cb1f79f98fc94c52f96cff64 Mon Sep 17 00:00:00 2001
From: Chun-Kuang Hu <chunkuang.hu@kernel.org>
Date: Mon, 2 Nov 2020 08:04:38 +0800
Subject: soc / drm: mediatek: cmdq: Remove timeout handler in helper function

For each client driver, its timeout handler need to dump hardware register
or its state machine information, and their way to detect timeout are
also different, so remove timeout handler in helper function and
let client driver implement its own timeout handler.

Signed-off-by: Chun-Kuang Hu <chunkuang.hu@kernel.org>
Acked-by: Matthias Brugger <matthias.bgg@gmail.com>
Link: https://lore.kernel.org/r/20201102000438.29225-1-chunkuang.hu@kernel.org
Signed-off-by: Matthias Brugger <matthias.bgg@gmail.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_crtc.c |  3 +--
 drivers/soc/mediatek/mtk-cmdq-helper.c  | 41 +--------------------------------
 include/linux/soc/mediatek/mtk-cmdq.h   | 10 +-------
 3 files changed, 3 insertions(+), 51 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
index ac038572164d..4be5d1fccf2e 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
@@ -824,8 +824,7 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 #if IS_REACHABLE(CONFIG_MTK_CMDQ)
 	mtk_crtc->cmdq_client =
 			cmdq_mbox_create(mtk_crtc->mmsys_dev,
-					 drm_crtc_index(&mtk_crtc->base),
-					 2000);
+					 drm_crtc_index(&mtk_crtc->base));
 	if (IS_ERR(mtk_crtc->cmdq_client)) {
 		dev_dbg(dev, "mtk_crtc %d failed to create mailbox client, writing register by CPU now\n",
 			drm_crtc_index(&mtk_crtc->base));
diff --git a/drivers/soc/mediatek/mtk-cmdq-helper.c b/drivers/soc/mediatek/mtk-cmdq-helper.c
index 505651b0d715..280d3bd9f675 100644
--- a/drivers/soc/mediatek/mtk-cmdq-helper.c
+++ b/drivers/soc/mediatek/mtk-cmdq-helper.c
@@ -70,14 +70,7 @@ int cmdq_dev_get_client_reg(struct device *dev,
 }
 EXPORT_SYMBOL(cmdq_dev_get_client_reg);
 
-static void cmdq_client_timeout(struct timer_list *t)
-{
-	struct cmdq_client *client = from_timer(client, t, timer);
-
-	dev_err(client->client.dev, "cmdq timeout!\n");
-}
-
-struct cmdq_client *cmdq_mbox_create(struct device *dev, int index, u32 timeout)
+struct cmdq_client *cmdq_mbox_create(struct device *dev, int index)
 {
 	struct cmdq_client *client;
 
@@ -85,12 +78,6 @@ struct cmdq_client *cmdq_mbox_create(struct device *dev, int index, u32 timeout)
 	if (!client)
 		return (struct cmdq_client *)-ENOMEM;
 
-	client->timeout_ms = timeout;
-	if (timeout != CMDQ_NO_TIMEOUT) {
-		spin_lock_init(&client->lock);
-		timer_setup(&client->timer, cmdq_client_timeout, 0);
-	}
-	client->pkt_cnt = 0;
 	client->client.dev = dev;
 	client->client.tx_block = false;
 	client->client.knows_txdone = true;
@@ -112,11 +99,6 @@ EXPORT_SYMBOL(cmdq_mbox_create);
 
 void cmdq_mbox_destroy(struct cmdq_client *client)
 {
-	if (client->timeout_ms != CMDQ_NO_TIMEOUT) {
-		spin_lock(&client->lock);
-		del_timer_sync(&client->timer);
-		spin_unlock(&client->lock);
-	}
 	mbox_free_channel(client->chan);
 	kfree(client);
 }
@@ -449,18 +431,6 @@ static void cmdq_pkt_flush_async_cb(struct cmdq_cb_data data)
 	struct cmdq_task_cb *cb = &pkt->cb;
 	struct cmdq_client *client = (struct cmdq_client *)pkt->cl;
 
-	if (client->timeout_ms != CMDQ_NO_TIMEOUT) {
-		unsigned long flags = 0;
-
-		spin_lock_irqsave(&client->lock, flags);
-		if (--client->pkt_cnt == 0)
-			del_timer(&client->timer);
-		else
-			mod_timer(&client->timer, jiffies +
-				  msecs_to_jiffies(client->timeout_ms));
-		spin_unlock_irqrestore(&client->lock, flags);
-	}
-
 	dma_sync_single_for_cpu(client->chan->mbox->dev, pkt->pa_base,
 				pkt->cmd_buf_size, DMA_TO_DEVICE);
 	if (cb->cb) {
@@ -473,7 +443,6 @@ int cmdq_pkt_flush_async(struct cmdq_pkt *pkt, cmdq_async_flush_cb cb,
 			 void *data)
 {
 	int err;
-	unsigned long flags = 0;
 	struct cmdq_client *client = (struct cmdq_client *)pkt->cl;
 
 	pkt->cb.cb = cb;
@@ -484,14 +453,6 @@ int cmdq_pkt_flush_async(struct cmdq_pkt *pkt, cmdq_async_flush_cb cb,
 	dma_sync_single_for_device(client->chan->mbox->dev, pkt->pa_base,
 				   pkt->cmd_buf_size, DMA_TO_DEVICE);
 
-	if (client->timeout_ms != CMDQ_NO_TIMEOUT) {
-		spin_lock_irqsave(&client->lock, flags);
-		if (client->pkt_cnt++ == 0)
-			mod_timer(&client->timer, jiffies +
-				  msecs_to_jiffies(client->timeout_ms));
-		spin_unlock_irqrestore(&client->lock, flags);
-	}
-
 	err = mbox_send_message(client->chan, pkt);
 	if (err < 0)
 		return err;
diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h
index 960704d75994..8e9996610978 100644
--- a/include/linux/soc/mediatek/mtk-cmdq.h
+++ b/include/linux/soc/mediatek/mtk-cmdq.h
@@ -11,7 +11,6 @@
 #include <linux/mailbox/mtk-cmdq-mailbox.h>
 #include <linux/timer.h>
 
-#define CMDQ_NO_TIMEOUT		0xffffffffu
 #define CMDQ_ADDR_HIGH(addr)	((u32)(((addr) >> 16) & GENMASK(31, 0)))
 #define CMDQ_ADDR_LOW(addr)	((u16)(addr) | BIT(1))
 
@@ -24,12 +23,8 @@ struct cmdq_client_reg {
 };
 
 struct cmdq_client {
-	spinlock_t lock;
-	u32 pkt_cnt;
 	struct mbox_client client;
 	struct mbox_chan *chan;
-	struct timer_list timer;
-	u32 timeout_ms; /* in unit of microsecond */
 };
 
 /**
@@ -51,13 +46,10 @@ int cmdq_dev_get_client_reg(struct device *dev,
  * cmdq_mbox_create() - create CMDQ mailbox client and channel
  * @dev:	device of CMDQ mailbox client
  * @index:	index of CMDQ mailbox channel
- * @timeout:	timeout of a pkt execution by GCE, in unit of microsecond, set
- *		CMDQ_NO_TIMEOUT if a timer is not used.
  *
  * Return: CMDQ mailbox client pointer
  */
-struct cmdq_client *cmdq_mbox_create(struct device *dev, int index,
-				     u32 timeout);
+struct cmdq_client *cmdq_mbox_create(struct device *dev, int index);
 
 /**
  * cmdq_mbox_destroy() - destroy CMDQ mailbox client and channel
-- 
cgit v1.2.3


From 51c0e618b219c025ddaaf14baea8942cb7e2105b Mon Sep 17 00:00:00 2001
From: Yongqiang Niu <yongqiang.niu@mediatek.com>
Date: Tue, 6 Oct 2020 21:33:17 +0200
Subject: soc / drm: mediatek: Move DDP component defines into mtk-mmsys.h

MMSYS is the driver which controls the routing of these DDP components,
so the definition of the mtk_ddp_comp_id enum should be placed in mtk-mmsys.h

Signed-off-by: Yongqiang Niu <yongqiang.niu@mediatek.com>
Signed-off-by: Enric Balletbo i Serra <enric.balletbo@collabora.com>
Reviewed-by: Chun-Kuang Hu <chunkuang.hu@kernel.org>
Link: https://lore.kernel.org/r/20201006193320.405529-2-enric.balletbo@collabora.com
Signed-off-by: Matthias Brugger <matthias.bgg@gmail.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h | 34 +----------------------------
 drivers/soc/mediatek/mtk-mmsys.c            |  4 +---
 include/linux/soc/mediatek/mtk-mmsys.h      | 33 ++++++++++++++++++++++++++++
 3 files changed, 35 insertions(+), 36 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
index 1d9e00b69462..5aa52b7afeec 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
@@ -7,6 +7,7 @@
 #define MTK_DRM_DDP_COMP_H
 
 #include <linux/io.h>
+#include <linux/soc/mediatek/mtk-mmsys.h>
 
 struct device;
 struct device_node;
@@ -35,39 +36,6 @@ enum mtk_ddp_comp_type {
 	MTK_DDP_COMP_TYPE_MAX,
 };
 
-enum mtk_ddp_comp_id {
-	DDP_COMPONENT_AAL0,
-	DDP_COMPONENT_AAL1,
-	DDP_COMPONENT_BLS,
-	DDP_COMPONENT_CCORR,
-	DDP_COMPONENT_COLOR0,
-	DDP_COMPONENT_COLOR1,
-	DDP_COMPONENT_DITHER,
-	DDP_COMPONENT_DPI0,
-	DDP_COMPONENT_DPI1,
-	DDP_COMPONENT_DSI0,
-	DDP_COMPONENT_DSI1,
-	DDP_COMPONENT_DSI2,
-	DDP_COMPONENT_DSI3,
-	DDP_COMPONENT_GAMMA,
-	DDP_COMPONENT_OD0,
-	DDP_COMPONENT_OD1,
-	DDP_COMPONENT_OVL0,
-	DDP_COMPONENT_OVL_2L0,
-	DDP_COMPONENT_OVL_2L1,
-	DDP_COMPONENT_OVL1,
-	DDP_COMPONENT_PWM0,
-	DDP_COMPONENT_PWM1,
-	DDP_COMPONENT_PWM2,
-	DDP_COMPONENT_RDMA0,
-	DDP_COMPONENT_RDMA1,
-	DDP_COMPONENT_RDMA2,
-	DDP_COMPONENT_UFOE,
-	DDP_COMPONENT_WDMA0,
-	DDP_COMPONENT_WDMA1,
-	DDP_COMPONENT_ID_MAX,
-};
-
 struct mtk_ddp_comp;
 struct cmdq_pkt;
 struct mtk_ddp_comp_funcs {
diff --git a/drivers/soc/mediatek/mtk-mmsys.c b/drivers/soc/mediatek/mtk-mmsys.c
index a55f25511173..36ad66bb221b 100644
--- a/drivers/soc/mediatek/mtk-mmsys.c
+++ b/drivers/soc/mediatek/mtk-mmsys.c
@@ -5,13 +5,11 @@
  */
 
 #include <linux/device.h>
+#include <linux/io.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/soc/mediatek/mtk-mmsys.h>
 
-#include "../../gpu/drm/mediatek/mtk_drm_ddp.h"
-#include "../../gpu/drm/mediatek/mtk_drm_ddp_comp.h"
-
 #define DISP_REG_CONFIG_DISP_OVL0_MOUT_EN	0x040
 #define DISP_REG_CONFIG_DISP_OVL1_MOUT_EN	0x044
 #define DISP_REG_CONFIG_DISP_OD_MOUT_EN		0x048
diff --git a/include/linux/soc/mediatek/mtk-mmsys.h b/include/linux/soc/mediatek/mtk-mmsys.h
index 7bab5d9a3d31..2228bf6133da 100644
--- a/include/linux/soc/mediatek/mtk-mmsys.h
+++ b/include/linux/soc/mediatek/mtk-mmsys.h
@@ -9,6 +9,39 @@
 enum mtk_ddp_comp_id;
 struct device;
 
+enum mtk_ddp_comp_id {
+	DDP_COMPONENT_AAL0,
+	DDP_COMPONENT_AAL1,
+	DDP_COMPONENT_BLS,
+	DDP_COMPONENT_CCORR,
+	DDP_COMPONENT_COLOR0,
+	DDP_COMPONENT_COLOR1,
+	DDP_COMPONENT_DITHER,
+	DDP_COMPONENT_DPI0,
+	DDP_COMPONENT_DPI1,
+	DDP_COMPONENT_DSI0,
+	DDP_COMPONENT_DSI1,
+	DDP_COMPONENT_DSI2,
+	DDP_COMPONENT_DSI3,
+	DDP_COMPONENT_GAMMA,
+	DDP_COMPONENT_OD0,
+	DDP_COMPONENT_OD1,
+	DDP_COMPONENT_OVL0,
+	DDP_COMPONENT_OVL_2L0,
+	DDP_COMPONENT_OVL_2L1,
+	DDP_COMPONENT_OVL1,
+	DDP_COMPONENT_PWM0,
+	DDP_COMPONENT_PWM1,
+	DDP_COMPONENT_PWM2,
+	DDP_COMPONENT_RDMA0,
+	DDP_COMPONENT_RDMA1,
+	DDP_COMPONENT_RDMA2,
+	DDP_COMPONENT_UFOE,
+	DDP_COMPONENT_WDMA0,
+	DDP_COMPONENT_WDMA1,
+	DDP_COMPONENT_ID_MAX,
+};
+
 void mtk_mmsys_ddp_connect(struct device *dev,
 			   enum mtk_ddp_comp_id cur,
 			   enum mtk_ddp_comp_id next);
-- 
cgit v1.2.3


From 206e7383b34316cf56cdde96eab9d97e9a1dbd70 Mon Sep 17 00:00:00 2001
From: Loic Poulain <loic.poulain@linaro.org>
Date: Thu, 26 Nov 2020 11:20:35 +0100
Subject: bus: mhi: core: Indexed MHI controller name

Today the MHI controller name is simply cloned from the underlying
bus device (its parent), that gives the following device structure
for e.g. a MHI/PCI controller:
devices/pci0000:00/0000:00:01.2/0000:02:00.0/0000:02:00.0
devices/pci0000:00/0000:00:01.2/0000:02:00.0/0000:02:00.0/0000:02:00.0_IPCR
...

That's quite misleading/confusing and can cause device registering
issues because of duplicate dev name (e.g. if a PCI device register
two different MHI instances).

This patch changes MHI core to create indexed mhi controller names
(mhi0, mhi1...) in the same way as other busses (i2c0, usb0...).

The previous example becomes:
devices/pci0000:00/0000:00:01.2/0000:02:00.0/mhi0
devices/pci0000:00/0000:00:01.2/0000:02:00.0/mhi0/mhi0_IPCR
...
 v2: move index field at the end of mhi_controller struct (before bool)
     to avoid breaking well packed alignment.

Signed-off-by: Loic Poulain <loic.poulain@linaro.org>
Reviewed-by: Jeffrey Hugo <jhugo@codeaurora.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/bus/mhi/core/init.c | 18 ++++++++++++++++--
 drivers/bus/mhi/core/main.c |  2 +-
 include/linux/mhi.h         |  2 ++
 3 files changed, 19 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/bus/mhi/core/init.c b/drivers/bus/mhi/core/init.c
index 655d539c6808..1d6f7b6c1fcd 100644
--- a/drivers/bus/mhi/core/init.c
+++ b/drivers/bus/mhi/core/init.c
@@ -8,6 +8,7 @@
 #include <linux/device.h>
 #include <linux/dma-direction.h>
 #include <linux/dma-mapping.h>
+#include <linux/idr.h>
 #include <linux/interrupt.h>
 #include <linux/list.h>
 #include <linux/mhi.h>
@@ -18,6 +19,8 @@
 #include <linux/wait.h>
 #include "internal.h"
 
+static DEFINE_IDA(mhi_controller_ida);
+
 const char * const mhi_ee_str[MHI_EE_MAX] = {
 	[MHI_EE_PBL] = "PBL",
 	[MHI_EE_SBL] = "SBL",
@@ -940,6 +943,12 @@ int mhi_register_controller(struct mhi_controller *mhi_cntrl,
 	mhi_cntrl->minor_version = (soc_info & SOC_HW_VERSION_MINOR_VER_BMSK) >>
 					SOC_HW_VERSION_MINOR_VER_SHFT;
 
+	mhi_cntrl->index = ida_alloc(&mhi_controller_ida, GFP_KERNEL);
+	if (mhi_cntrl->index < 0) {
+		ret = mhi_cntrl->index;
+		goto error_ida_alloc;
+	}
+
 	/* Register controller with MHI bus */
 	mhi_dev = mhi_alloc_device(mhi_cntrl);
 	if (IS_ERR(mhi_dev)) {
@@ -950,8 +959,8 @@ int mhi_register_controller(struct mhi_controller *mhi_cntrl,
 
 	mhi_dev->dev_type = MHI_DEVICE_CONTROLLER;
 	mhi_dev->mhi_cntrl = mhi_cntrl;
-	dev_set_name(&mhi_dev->dev, "%s", dev_name(mhi_cntrl->cntrl_dev));
-	mhi_dev->name = dev_name(mhi_cntrl->cntrl_dev);
+	dev_set_name(&mhi_dev->dev, "mhi%d", mhi_cntrl->index);
+	mhi_dev->name = dev_name(&mhi_dev->dev);
 
 	/* Init wakeup source */
 	device_init_wakeup(&mhi_dev->dev, true);
@@ -970,6 +979,9 @@ error_add_dev:
 	put_device(&mhi_dev->dev);
 
 error_alloc_dev:
+	ida_free(&mhi_controller_ida, mhi_cntrl->index);
+
+error_ida_alloc:
 	kfree(mhi_cntrl->mhi_cmd);
 
 error_alloc_cmd:
@@ -1004,6 +1016,8 @@ void mhi_unregister_controller(struct mhi_controller *mhi_cntrl)
 
 	device_del(&mhi_dev->dev);
 	put_device(&mhi_dev->dev);
+
+	ida_free(&mhi_controller_ida, mhi_cntrl->index);
 }
 EXPORT_SYMBOL_GPL(mhi_unregister_controller);
 
diff --git a/drivers/bus/mhi/core/main.c b/drivers/bus/mhi/core/main.c
index 4eb93d8bea1d..702c31b6aefa 100644
--- a/drivers/bus/mhi/core/main.c
+++ b/drivers/bus/mhi/core/main.c
@@ -331,7 +331,7 @@ void mhi_create_devices(struct mhi_controller *mhi_cntrl)
 		/* Channel name is same for both UL and DL */
 		mhi_dev->name = mhi_chan->name;
 		dev_set_name(&mhi_dev->dev, "%s_%s",
-			     dev_name(mhi_cntrl->cntrl_dev),
+			     dev_name(&mhi_cntrl->mhi_dev->dev),
 			     mhi_dev->name);
 
 		/* Init wakeup source if available */
diff --git a/include/linux/mhi.h b/include/linux/mhi.h
index d31efcf02ae7..aa9757e71f1f 100644
--- a/include/linux/mhi.h
+++ b/include/linux/mhi.h
@@ -348,6 +348,7 @@ struct mhi_controller_config {
  * @read_reg: Read a MHI register via the physical link (required)
  * @write_reg: Write a MHI register via the physical link (required)
  * @buffer_len: Bounce buffer length
+ * @index: Index of the MHI controller instance
  * @bounce_buf: Use of bounce buffer
  * @fbc_download: MHI host needs to do complete image transfer (optional)
  * @pre_init: MHI host needs to do pre-initialization before power up
@@ -438,6 +439,7 @@ struct mhi_controller {
 			  u32 val);
 
 	size_t buffer_len;
+	int index;
 	bool bounce_buf;
 	bool fbc_download;
 	bool pre_init;
-- 
cgit v1.2.3


From 7776bcd241e08e13ef009926c6dea84dc3b2f8ff Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Tue, 3 Nov 2020 00:48:44 +0100
Subject: power: supply: s3c-adc-battery: Convert to GPIO descriptors

This converts the S3C ADC battery to use GPIO descriptors
instead of a global GPIO number for the charging completed
GPIO. Using the pattern from the GPIO charger we name this
GPIO line "charge-status" in the board file.

Cc: linux-samsung-soc@vger.kernel.org
Cc: Sergiy Kibrik <sakib@darkstar.site>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 arch/arm/mach-s3c/mach-h1940.c         | 12 +++++--
 arch/arm/mach-s3c/mach-rx1950.c        | 11 ++++++-
 drivers/power/supply/s3c_adc_battery.c | 57 +++++++++++++++++-----------------
 include/linux/s3c_adc_battery.h        |  3 --
 4 files changed, 49 insertions(+), 34 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/mach-s3c/mach-h1940.c b/arch/arm/mach-s3c/mach-h1940.c
index 53d51aa83200..8a43ed1c4c4d 100644
--- a/arch/arm/mach-s3c/mach-h1940.c
+++ b/arch/arm/mach-s3c/mach-h1940.c
@@ -297,6 +297,15 @@ static const struct s3c_adc_bat_thresh bat_lut_acin[] = {
 	{ .volt = 3841, .cur = 0, .level = 0},
 };
 
+static struct gpiod_lookup_table h1940_bat_gpio_table = {
+	.dev_id = "s3c-adc-battery",
+	.table = {
+		/* Charge status S3C2410_GPF(3) */
+		GPIO_LOOKUP("GPIOF", 3, "charge-status", GPIO_ACTIVE_LOW),
+		{ },
+	},
+};
+
 static int h1940_bat_init(void)
 {
 	int ret;
@@ -330,8 +339,6 @@ static struct s3c_adc_bat_pdata h1940_bat_cfg = {
 	.exit = h1940_bat_exit,
 	.enable_charger = h1940_enable_charger,
 	.disable_charger = h1940_disable_charger,
-	.gpio_charge_finished = S3C2410_GPF(3),
-	.gpio_inverted = 1,
 	.lut_noac = bat_lut_noac,
 	.lut_noac_cnt = ARRAY_SIZE(bat_lut_noac),
 	.lut_acin = bat_lut_acin,
@@ -720,6 +727,7 @@ static void __init h1940_init(void)
 	s3c24xx_fb_set_platdata(&h1940_fb_info);
 	gpiod_add_lookup_table(&h1940_mmc_gpio_table);
 	gpiod_add_lookup_table(&h1940_audio_gpio_table);
+	gpiod_add_lookup_table(&h1940_bat_gpio_table);
 	/* Configure the I2S pins (GPE0...GPE4) in correct mode */
 	s3c_gpio_cfgall_range(S3C2410_GPE(0), 5, S3C_GPIO_SFN(2),
 			      S3C_GPIO_PULL_NONE);
diff --git a/arch/arm/mach-s3c/mach-rx1950.c b/arch/arm/mach-s3c/mach-rx1950.c
index b9758f0a9a14..6e19add158a9 100644
--- a/arch/arm/mach-s3c/mach-rx1950.c
+++ b/arch/arm/mach-s3c/mach-rx1950.c
@@ -206,6 +206,15 @@ static const struct s3c_adc_bat_thresh bat_lut_acin[] = {
 	{ .volt = 3820, .cur = 0, .level = 0},
 };
 
+static struct gpiod_lookup_table rx1950_bat_gpio_table = {
+	.dev_id = "s3c-adc-battery",
+	.table = {
+		/* Charge status S3C2410_GPF(3) */
+		GPIO_LOOKUP("GPIOF", 3, "charge-status", GPIO_ACTIVE_HIGH),
+		{ },
+	},
+};
+
 static int rx1950_bat_init(void)
 {
 	int ret;
@@ -331,7 +340,6 @@ static struct s3c_adc_bat_pdata rx1950_bat_cfg = {
 	.exit = rx1950_bat_exit,
 	.enable_charger = rx1950_enable_charger,
 	.disable_charger = rx1950_disable_charger,
-	.gpio_charge_finished = S3C2410_GPF(3),
 	.lut_noac = bat_lut_noac,
 	.lut_noac_cnt = ARRAY_SIZE(bat_lut_noac),
 	.lut_acin = bat_lut_acin,
@@ -840,6 +848,7 @@ static void __init rx1950_init_machine(void)
 
 	pwm_add_table(rx1950_pwm_lookup, ARRAY_SIZE(rx1950_pwm_lookup));
 	gpiod_add_lookup_table(&rx1950_audio_gpio_table);
+	gpiod_add_lookup_table(&rx1950_bat_gpio_table);
 	/* Configure the I2S pins (GPE0...GPE4) in correct mode */
 	s3c_gpio_cfgall_range(S3C2410_GPE(0), 5, S3C_GPIO_SFN(2),
 			      S3C_GPIO_PULL_NONE);
diff --git a/drivers/power/supply/s3c_adc_battery.c b/drivers/power/supply/s3c_adc_battery.c
index 60b7f41ab063..a2addc24ee8b 100644
--- a/drivers/power/supply/s3c_adc_battery.c
+++ b/drivers/power/supply/s3c_adc_battery.c
@@ -13,7 +13,7 @@
 #include <linux/platform_device.h>
 #include <linux/power_supply.h>
 #include <linux/leds.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/err.h>
 #include <linux/timer.h>
 #include <linux/jiffies.h>
@@ -31,6 +31,7 @@ struct s3c_adc_bat {
 	struct power_supply		*psy;
 	struct s3c_adc_client		*client;
 	struct s3c_adc_bat_pdata	*pdata;
+	struct gpio_desc		*charge_finished;
 	int				volt_value;
 	int				cur_value;
 	unsigned int			timestamp;
@@ -132,9 +133,7 @@ static int calc_full_volt(int volt_val, int cur_val, int impedance)
 
 static int charge_finished(struct s3c_adc_bat *bat)
 {
-	return bat->pdata->gpio_inverted ?
-		!gpio_get_value(bat->pdata->gpio_charge_finished) :
-		gpio_get_value(bat->pdata->gpio_charge_finished);
+	return gpiod_get_value(bat->charge_finished);
 }
 
 static int s3c_adc_bat_get_property(struct power_supply *psy,
@@ -169,7 +168,7 @@ static int s3c_adc_bat_get_property(struct power_supply *psy,
 	}
 
 	if (bat->cable_plugged &&
-		((bat->pdata->gpio_charge_finished < 0) ||
+		(!bat->charge_finished ||
 		!charge_finished(bat))) {
 		lut = bat->pdata->lut_acin;
 		lut_size = bat->pdata->lut_acin_cnt;
@@ -206,7 +205,7 @@ static int s3c_adc_bat_get_property(struct power_supply *psy,
 
 	switch (psp) {
 	case POWER_SUPPLY_PROP_STATUS:
-		if (bat->pdata->gpio_charge_finished < 0)
+		if (!bat->charge_finished)
 			val->intval = bat->level == 100000 ?
 				POWER_SUPPLY_STATUS_FULL : bat->status;
 		else
@@ -265,7 +264,7 @@ static void s3c_adc_bat_work(struct work_struct *work)
 			bat->status = POWER_SUPPLY_STATUS_DISCHARGING;
 		}
 	} else {
-		if ((bat->pdata->gpio_charge_finished >= 0) && is_plugged) {
+		if (bat->charge_finished && is_plugged) {
 			is_charged = charge_finished(&main_bat);
 			if (is_charged) {
 				if (bat->pdata->disable_charger)
@@ -294,6 +293,7 @@ static int s3c_adc_bat_probe(struct platform_device *pdev)
 	struct s3c_adc_client	*client;
 	struct s3c_adc_bat_pdata *pdata = pdev->dev.platform_data;
 	struct power_supply_config psy_cfg = {};
+	struct gpio_desc *gpiod;
 	int ret;
 
 	client = s3c_adc_register(pdev, NULL, NULL, 0);
@@ -304,8 +304,17 @@ static int s3c_adc_bat_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, client);
 
+	gpiod = devm_gpiod_get_optional(&pdev->dev, "charge-status", GPIOD_IN);
+	if (IS_ERR(gpiod)) {
+		/* Could be probe deferral etc */
+		ret = PTR_ERR(gpiod);
+		dev_err(&pdev->dev, "no GPIO %d\n", ret);
+		return ret;
+	}
+
 	main_bat.client = client;
 	main_bat.pdata = pdata;
+	main_bat.charge_finished = gpiod;
 	main_bat.volt_value = -1;
 	main_bat.cur_value = -1;
 	main_bat.cable_plugged = 0;
@@ -323,6 +332,7 @@ static int s3c_adc_bat_probe(struct platform_device *pdev)
 
 		backup_bat.client = client;
 		backup_bat.pdata = pdev->dev.platform_data;
+		backup_bat.charge_finished = gpiod;
 		backup_bat.volt_value = -1;
 		backup_bat.psy = power_supply_register(&pdev->dev,
 						       &backup_bat_desc,
@@ -335,12 +345,8 @@ static int s3c_adc_bat_probe(struct platform_device *pdev)
 
 	INIT_DELAYED_WORK(&bat_work, s3c_adc_bat_work);
 
-	if (pdata->gpio_charge_finished >= 0) {
-		ret = gpio_request(pdata->gpio_charge_finished, "charged");
-		if (ret)
-			goto err_gpio;
-
-		ret = request_irq(gpio_to_irq(pdata->gpio_charge_finished),
+	if (gpiod) {
+		ret = request_irq(gpiod_to_irq(gpiod),
 				s3c_adc_bat_charged,
 				IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING,
 				"battery charged", NULL);
@@ -364,12 +370,9 @@ static int s3c_adc_bat_probe(struct platform_device *pdev)
 	return 0;
 
 err_platform:
-	if (pdata->gpio_charge_finished >= 0)
-		free_irq(gpio_to_irq(pdata->gpio_charge_finished), NULL);
+	if (gpiod)
+		free_irq(gpiod_to_irq(gpiod), NULL);
 err_irq:
-	if (pdata->gpio_charge_finished >= 0)
-		gpio_free(pdata->gpio_charge_finished);
-err_gpio:
 	if (pdata->backup_volt_mult)
 		power_supply_unregister(backup_bat.psy);
 err_reg_backup:
@@ -389,10 +392,8 @@ static int s3c_adc_bat_remove(struct platform_device *pdev)
 
 	s3c_adc_release(client);
 
-	if (pdata->gpio_charge_finished >= 0) {
-		free_irq(gpio_to_irq(pdata->gpio_charge_finished), NULL);
-		gpio_free(pdata->gpio_charge_finished);
-	}
+	if (main_bat.charge_finished)
+		free_irq(gpiod_to_irq(main_bat.charge_finished), NULL);
 
 	cancel_delayed_work(&bat_work);
 
@@ -408,12 +409,12 @@ static int s3c_adc_bat_suspend(struct platform_device *pdev,
 {
 	struct s3c_adc_bat_pdata *pdata = pdev->dev.platform_data;
 
-	if (pdata->gpio_charge_finished >= 0) {
+	if (main_bat.charge_finished) {
 		if (device_may_wakeup(&pdev->dev))
 			enable_irq_wake(
-				gpio_to_irq(pdata->gpio_charge_finished));
+				gpiod_to_irq(main_bat.charge_finished));
 		else {
-			disable_irq(gpio_to_irq(pdata->gpio_charge_finished));
+			disable_irq(gpiod_to_irq(main_bat.charge_finished));
 			main_bat.pdata->disable_charger();
 		}
 	}
@@ -425,12 +426,12 @@ static int s3c_adc_bat_resume(struct platform_device *pdev)
 {
 	struct s3c_adc_bat_pdata *pdata = pdev->dev.platform_data;
 
-	if (pdata->gpio_charge_finished >= 0) {
+	if (main_bat.charge_finished) {
 		if (device_may_wakeup(&pdev->dev))
 			disable_irq_wake(
-				gpio_to_irq(pdata->gpio_charge_finished));
+				gpiod_to_irq(main_bat.charge_finished));
 		else
-			enable_irq(gpio_to_irq(pdata->gpio_charge_finished));
+			enable_irq(gpiod_to_irq(main_bat.charge_finished));
 	}
 
 	/* Schedule timer to check current status */
diff --git a/include/linux/s3c_adc_battery.h b/include/linux/s3c_adc_battery.h
index 833871dcf6fd..57f982c375f8 100644
--- a/include/linux/s3c_adc_battery.h
+++ b/include/linux/s3c_adc_battery.h
@@ -14,9 +14,6 @@ struct s3c_adc_bat_pdata {
 	void (*enable_charger)(void);
 	void (*disable_charger)(void);
 
-	int gpio_charge_finished;
-	int gpio_inverted;
-
 	const struct s3c_adc_bat_thresh *lut_noac;
 	unsigned int lut_noac_cnt;
 	const struct s3c_adc_bat_thresh *lut_acin;
-- 
cgit v1.2.3


From b0327ffb133fb2148fc3bc2afb39af2871ab21cb Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Fri, 30 Oct 2020 13:24:24 +0100
Subject: power: supply: generic-adc-battery: Use GPIO descriptors

This driver uses platform data to pass GPIO lines using the
deprecated global GPIO numbers. There are no in-tree users
of this platform data.

Any out-of-tree or coming users of this driver can easily be
migrated to use machine descriptor tables as described in
Documentation/driver-api/gpio/board.rst
section "platform data".

Cc: Anish Kumar <anish198519851985@gmail.com>
Cc: H. Nikolaus Schaller <hns@goldelico.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/generic-adc-battery.c | 31 +++++++++++-------------------
 include/linux/power/generic-adc-battery.h  |  4 ----
 2 files changed, 11 insertions(+), 24 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/power/supply/generic-adc-battery.c b/drivers/power/supply/generic-adc-battery.c
index caa829738ef7..0032069fbc2b 100644
--- a/drivers/power/supply/generic-adc-battery.c
+++ b/drivers/power/supply/generic-adc-battery.c
@@ -12,7 +12,7 @@
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
 #include <linux/power_supply.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/err.h>
 #include <linux/timer.h>
 #include <linux/jiffies.h>
@@ -52,6 +52,7 @@ struct gab {
 	int	level;
 	int	status;
 	bool cable_plugged;
+	struct gpio_desc *charge_finished;
 };
 
 static struct gab *to_generic_bat(struct power_supply *psy)
@@ -91,13 +92,9 @@ static const enum power_supply_property gab_dyn_props[] = {
 
 static bool gab_charge_finished(struct gab *adc_bat)
 {
-	struct gab_platform_data *pdata = adc_bat->pdata;
-	bool ret = gpio_get_value(pdata->gpio_charge_finished);
-	bool inv = pdata->gpio_inverted;
-
-	if (!gpio_is_valid(pdata->gpio_charge_finished))
+	if (!adc_bat->charge_finished)
 		return false;
-	return ret ^ inv;
+	return gpiod_get_value(adc_bat->charge_finished);
 }
 
 static int gab_get_status(struct gab *adc_bat)
@@ -327,18 +324,17 @@ static int gab_probe(struct platform_device *pdev)
 
 	INIT_DELAYED_WORK(&adc_bat->bat_work, gab_work);
 
-	if (gpio_is_valid(pdata->gpio_charge_finished)) {
+	adc_bat->charge_finished = devm_gpiod_get_optional(&pdev->dev,
+							   "charged", GPIOD_IN);
+	if (adc_bat->charge_finished) {
 		int irq;
-		ret = gpio_request(pdata->gpio_charge_finished, "charged");
-		if (ret)
-			goto gpio_req_fail;
 
-		irq = gpio_to_irq(pdata->gpio_charge_finished);
+		irq = gpiod_to_irq(adc_bat->charge_finished);
 		ret = request_any_context_irq(irq, gab_charged,
 				IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING,
 				"battery charged", adc_bat);
 		if (ret < 0)
-			goto err_gpio;
+			goto gpio_req_fail;
 	}
 
 	platform_set_drvdata(pdev, adc_bat);
@@ -348,8 +344,6 @@ static int gab_probe(struct platform_device *pdev)
 			msecs_to_jiffies(0));
 	return 0;
 
-err_gpio:
-	gpio_free(pdata->gpio_charge_finished);
 gpio_req_fail:
 	power_supply_unregister(adc_bat->psy);
 err_reg_fail:
@@ -367,14 +361,11 @@ static int gab_remove(struct platform_device *pdev)
 {
 	int chan;
 	struct gab *adc_bat = platform_get_drvdata(pdev);
-	struct gab_platform_data *pdata = adc_bat->pdata;
 
 	power_supply_unregister(adc_bat->psy);
 
-	if (gpio_is_valid(pdata->gpio_charge_finished)) {
-		free_irq(gpio_to_irq(pdata->gpio_charge_finished), adc_bat);
-		gpio_free(pdata->gpio_charge_finished);
-	}
+	if (adc_bat->charge_finished)
+		free_irq(gpiod_to_irq(adc_bat->charge_finished), adc_bat);
 
 	for (chan = 0; chan < ARRAY_SIZE(gab_chan_name); chan++) {
 		if (adc_bat->channel[chan])
diff --git a/include/linux/power/generic-adc-battery.h b/include/linux/power/generic-adc-battery.h
index 40f9c7628f7b..c68cbf34cd34 100644
--- a/include/linux/power/generic-adc-battery.h
+++ b/include/linux/power/generic-adc-battery.h
@@ -11,16 +11,12 @@
  * @battery_info:         recommended structure to specify static power supply
  *			   parameters
  * @cal_charge:           calculate charge level.
- * @gpio_charge_finished: gpio for the charger.
- * @gpio_inverted:        Should be 1 if the GPIO is active low otherwise 0
  * @jitter_delay:         delay required after the interrupt to check battery
  *			  status.Default set is 10ms.
  */
 struct gab_platform_data {
 	struct power_supply_info battery_info;
 	int	(*cal_charge)(long value);
-	int	gpio_charge_finished;
-	bool	gpio_inverted;
 	int     jitter_delay;
 };
 
-- 
cgit v1.2.3


From 51e7bf4534da678da27c0f51e7ff21804fae88ca Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 30 Sep 2020 01:01:05 +0200
Subject: mtd: nand: ecc: Add an I/O request tweaking mechanism

Currently, BCH and Hamming engine are sharing the same
tweaking/restoring I/O mechanism: they need the I/O request to fully
cover the main/OOB area. Let's make this code generic as sharing the
code between two drivers is already a win. Maybe other ECC engine
drivers will need it too.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200929230124.31491-2-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/ecc.c   | 106 +++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/mtd/nand.h |  32 ++++++++++++++
 2 files changed, 138 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/ecc.c b/drivers/mtd/nand/ecc.c
index 4a56e6c0da67..541137736fd3 100644
--- a/drivers/mtd/nand/ecc.c
+++ b/drivers/mtd/nand/ecc.c
@@ -95,6 +95,7 @@
 
 #include <linux/module.h>
 #include <linux/mtd/nand.h>
+#include <linux/slab.h>
 
 /**
  * nand_ecc_init_ctx - Init the ECC engine context
@@ -479,6 +480,111 @@ bool nand_ecc_is_strong_enough(struct nand_device *nand)
 }
 EXPORT_SYMBOL(nand_ecc_is_strong_enough);
 
+/* ECC engine driver internal helpers */
+int nand_ecc_init_req_tweaking(struct nand_ecc_req_tweak_ctx *ctx,
+			       struct nand_device *nand)
+{
+	unsigned int total_buffer_size;
+
+	ctx->nand = nand;
+
+	/* Let the user decide the exact length of each buffer */
+	if (!ctx->page_buffer_size)
+		ctx->page_buffer_size = nanddev_page_size(nand);
+	if (!ctx->oob_buffer_size)
+		ctx->oob_buffer_size = nanddev_per_page_oobsize(nand);
+
+	total_buffer_size = ctx->page_buffer_size + ctx->oob_buffer_size;
+
+	ctx->spare_databuf = kzalloc(total_buffer_size, GFP_KERNEL);
+	if (!ctx->spare_databuf)
+		return -ENOMEM;
+
+	ctx->spare_oobbuf = ctx->spare_databuf + ctx->page_buffer_size;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nand_ecc_init_req_tweaking);
+
+void nand_ecc_cleanup_req_tweaking(struct nand_ecc_req_tweak_ctx *ctx)
+{
+	kfree(ctx->spare_databuf);
+}
+EXPORT_SYMBOL_GPL(nand_ecc_cleanup_req_tweaking);
+
+/*
+ * Ensure data and OOB area is fully read/written otherwise the correction might
+ * not work as expected.
+ */
+void nand_ecc_tweak_req(struct nand_ecc_req_tweak_ctx *ctx,
+			struct nand_page_io_req *req)
+{
+	struct nand_device *nand = ctx->nand;
+	struct nand_page_io_req *orig, *tweak;
+
+	/* Save the original request */
+	ctx->orig_req = *req;
+	ctx->bounce_data = false;
+	ctx->bounce_oob = false;
+	orig = &ctx->orig_req;
+	tweak = req;
+
+	/* Ensure the request covers the entire page */
+	if (orig->datalen < nanddev_page_size(nand)) {
+		ctx->bounce_data = true;
+		tweak->dataoffs = 0;
+		tweak->datalen = nanddev_page_size(nand);
+		tweak->databuf.in = ctx->spare_databuf;
+		memset(tweak->databuf.in, 0xFF, ctx->page_buffer_size);
+	}
+
+	if (orig->ooblen < nanddev_per_page_oobsize(nand)) {
+		ctx->bounce_oob = true;
+		tweak->ooboffs = 0;
+		tweak->ooblen = nanddev_per_page_oobsize(nand);
+		tweak->oobbuf.in = ctx->spare_oobbuf;
+		memset(tweak->oobbuf.in, 0xFF, ctx->oob_buffer_size);
+	}
+
+	/* Copy the data that must be writen in the bounce buffers, if needed */
+	if (orig->type == NAND_PAGE_WRITE) {
+		if (ctx->bounce_data)
+			memcpy((void *)tweak->databuf.out + orig->dataoffs,
+			       orig->databuf.out, orig->datalen);
+
+		if (ctx->bounce_oob)
+			memcpy((void *)tweak->oobbuf.out + orig->ooboffs,
+			       orig->oobbuf.out, orig->ooblen);
+	}
+}
+EXPORT_SYMBOL_GPL(nand_ecc_tweak_req);
+
+void nand_ecc_restore_req(struct nand_ecc_req_tweak_ctx *ctx,
+			  struct nand_page_io_req *req)
+{
+	struct nand_page_io_req *orig, *tweak;
+
+	orig = &ctx->orig_req;
+	tweak = req;
+
+	/* Restore the data read from the bounce buffers, if needed */
+	if (orig->type == NAND_PAGE_READ) {
+		if (ctx->bounce_data)
+			memcpy(orig->databuf.in,
+			       tweak->databuf.in + orig->dataoffs,
+			       orig->datalen);
+
+		if (ctx->bounce_oob)
+			memcpy(orig->oobbuf.in,
+			       tweak->oobbuf.in + orig->ooboffs,
+			       orig->ooblen);
+	}
+
+	/* Ensure the original request is restored */
+	*req = *orig;
+}
+EXPORT_SYMBOL_GPL(nand_ecc_restore_req);
+
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Miquel Raynal <miquel.raynal@bootlin.com>");
 MODULE_DESCRIPTION("Generic ECC engine");
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 697ea2474a7c..36e4fe08d0ea 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -278,6 +278,38 @@ int nand_ecc_finish_io_req(struct nand_device *nand,
 			   struct nand_page_io_req *req);
 bool nand_ecc_is_strong_enough(struct nand_device *nand);
 
+/**
+ * struct nand_ecc_req_tweak_ctx - Help for automatically tweaking requests
+ * @orig_req: Pointer to the original IO request
+ * @nand: Related NAND device, to have access to its memory organization
+ * @page_buffer_size: Real size of the page buffer to use (can be set by the
+ *                    user before the tweaking mechanism initialization)
+ * @oob_buffer_size: Real size of the OOB buffer to use (can be set by the
+ *                   user before the tweaking mechanism initialization)
+ * @spare_databuf: Data bounce buffer
+ * @spare_oobbuf: OOB bounce buffer
+ * @bounce_data: Flag indicating a data bounce buffer is used
+ * @bounce_oob: Flag indicating an OOB bounce buffer is used
+ */
+struct nand_ecc_req_tweak_ctx {
+	struct nand_page_io_req orig_req;
+	struct nand_device *nand;
+	unsigned int page_buffer_size;
+	unsigned int oob_buffer_size;
+	void *spare_databuf;
+	void *spare_oobbuf;
+	bool bounce_data;
+	bool bounce_oob;
+};
+
+int nand_ecc_init_req_tweaking(struct nand_ecc_req_tweak_ctx *ctx,
+			       struct nand_device *nand);
+void nand_ecc_cleanup_req_tweaking(struct nand_ecc_req_tweak_ctx *ctx);
+void nand_ecc_tweak_req(struct nand_ecc_req_tweak_ctx *ctx,
+			struct nand_page_io_req *req);
+void nand_ecc_restore_req(struct nand_ecc_req_tweak_ctx *ctx,
+			  struct nand_page_io_req *req);
+
 /**
  * struct nand_ecc - Information relative to the ECC
  * @defaults: Default values, depend on the underlying subsystem
-- 
cgit v1.2.3


From cdbe8df5e28e452c232c0c16b205edfd390d28e5 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 30 Sep 2020 01:01:06 +0200
Subject: mtd: nand: ecc-bch: Move BCH code to the generic NAND layer

BCH ECC code might be later re-used by the SPI NAND layer.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200929230124.31491-3-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/Kconfig            |  11 ++
 drivers/mtd/nand/Makefile           |   1 +
 drivers/mtd/nand/ecc-sw-bch.c       | 219 ++++++++++++++++++++++++++++++++++++
 drivers/mtd/nand/raw/Kconfig        |  10 --
 drivers/mtd/nand/raw/Makefile       |   1 -
 drivers/mtd/nand/raw/nand_base.c    |   2 +-
 drivers/mtd/nand/raw/nand_bch.c     | 219 ------------------------------------
 drivers/mtd/nand/raw/nandsim.c      |   2 +-
 drivers/mtd/nand/raw/omap2.c        |   2 +-
 include/linux/mtd/nand-ecc-sw-bch.h |  66 +++++++++++
 include/linux/mtd/nand_bch.h        |  66 -----------
 11 files changed, 300 insertions(+), 299 deletions(-)
 create mode 100644 drivers/mtd/nand/ecc-sw-bch.c
 delete mode 100644 drivers/mtd/nand/raw/nand_bch.c
 create mode 100644 include/linux/mtd/nand-ecc-sw-bch.h
 delete mode 100644 include/linux/mtd/nand_bch.h

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig
index 4a9aed4f0104..55c17fb0dee1 100644
--- a/drivers/mtd/nand/Kconfig
+++ b/drivers/mtd/nand/Kconfig
@@ -15,6 +15,17 @@ config MTD_NAND_ECC
        bool
        depends on MTD_NAND_CORE
 
+config MTD_NAND_ECC_SW_BCH
+	bool "Software BCH ECC engine"
+	select BCH
+	select MTD_NAND_ECC
+	default n
+	help
+	  This enables support for software BCH error correction. Binary BCH
+	  codes are more powerful and cpu intensive than traditional Hamming
+	  ECC codes. They are used with NAND devices requiring more than 1 bit
+	  of error correction.
+
 endmenu
 
 endmenu
diff --git a/drivers/mtd/nand/Makefile b/drivers/mtd/nand/Makefile
index 981372953b56..c7179ff23753 100644
--- a/drivers/mtd/nand/Makefile
+++ b/drivers/mtd/nand/Makefile
@@ -8,3 +8,4 @@ obj-y	+= raw/
 obj-y	+= spi/
 
 nandcore-$(CONFIG_MTD_NAND_ECC) += ecc.o
+nandcore-$(CONFIG_MTD_NAND_ECC_SW_BCH) += ecc-sw-bch.o
diff --git a/drivers/mtd/nand/ecc-sw-bch.c b/drivers/mtd/nand/ecc-sw-bch.c
new file mode 100644
index 000000000000..6da14d0263d9
--- /dev/null
+++ b/drivers/mtd/nand/ecc-sw-bch.c
@@ -0,0 +1,219 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * This file provides ECC correction for more than 1 bit per block of data,
+ * using binary BCH codes. It relies on the generic BCH library lib/bch.c.
+ *
+ * Copyright © 2011 Ivan Djelic <ivan.djelic@parrot.com>
+ */
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/bitops.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/rawnand.h>
+#include <linux/mtd/nand-ecc-sw-bch.h>
+#include <linux/bch.h>
+
+/**
+ * struct nand_bch_control - private NAND BCH control structure
+ * @bch:       BCH control structure
+ * @errloc:    error location array
+ * @eccmask:   XOR ecc mask, allows erased pages to be decoded as valid
+ */
+struct nand_bch_control {
+	struct bch_control   *bch;
+	unsigned int         *errloc;
+	unsigned char        *eccmask;
+};
+
+/**
+ * nand_bch_calculate_ecc - [NAND Interface] Calculate ECC for data block
+ * @chip:	NAND chip object
+ * @buf:	input buffer with raw data
+ * @code:	output buffer with ECC
+ */
+int nand_bch_calculate_ecc(struct nand_chip *chip, const unsigned char *buf,
+			   unsigned char *code)
+{
+	struct nand_bch_control *nbc = chip->ecc.priv;
+	unsigned int i;
+
+	memset(code, 0, chip->ecc.bytes);
+	bch_encode(nbc->bch, buf, chip->ecc.size, code);
+
+	/* apply mask so that an erased page is a valid codeword */
+	for (i = 0; i < chip->ecc.bytes; i++)
+		code[i] ^= nbc->eccmask[i];
+
+	return 0;
+}
+EXPORT_SYMBOL(nand_bch_calculate_ecc);
+
+/**
+ * nand_bch_correct_data - [NAND Interface] Detect and correct bit error(s)
+ * @chip:	NAND chip object
+ * @buf:	raw data read from the chip
+ * @read_ecc:	ECC from the chip
+ * @calc_ecc:	the ECC calculated from raw data
+ *
+ * Detect and correct bit errors for a data byte block
+ */
+int nand_bch_correct_data(struct nand_chip *chip, unsigned char *buf,
+			  unsigned char *read_ecc, unsigned char *calc_ecc)
+{
+	struct nand_bch_control *nbc = chip->ecc.priv;
+	unsigned int *errloc = nbc->errloc;
+	int i, count;
+
+	count = bch_decode(nbc->bch, NULL, chip->ecc.size, read_ecc, calc_ecc,
+			   NULL, errloc);
+	if (count > 0) {
+		for (i = 0; i < count; i++) {
+			if (errloc[i] < (chip->ecc.size*8))
+				/* error is located in data, correct it */
+				buf[errloc[i] >> 3] ^= (1 << (errloc[i] & 7));
+			/* else error in ecc, no action needed */
+
+			pr_debug("%s: corrected bitflip %u\n", __func__,
+					errloc[i]);
+		}
+	} else if (count < 0) {
+		pr_err("ecc unrecoverable error\n");
+		count = -EBADMSG;
+	}
+	return count;
+}
+EXPORT_SYMBOL(nand_bch_correct_data);
+
+/**
+ * nand_bch_init - [NAND Interface] Initialize NAND BCH error correction
+ * @mtd:	MTD block structure
+ *
+ * Returns:
+ *  a pointer to a new NAND BCH control structure, or NULL upon failure
+ *
+ * Initialize NAND BCH error correction. Parameters @eccsize and @eccbytes
+ * are used to compute BCH parameters m (Galois field order) and t (error
+ * correction capability). @eccbytes should be equal to the number of bytes
+ * required to store m*t bits, where m is such that 2^m-1 > @eccsize*8.
+ *
+ * Example: to configure 4 bit correction per 512 bytes, you should pass
+ * @eccsize = 512  (thus, m=13 is the smallest integer such that 2^m-1 > 512*8)
+ * @eccbytes = 7   (7 bytes are required to store m*t = 13*4 = 52 bits)
+ */
+struct nand_bch_control *nand_bch_init(struct mtd_info *mtd)
+{
+	struct nand_chip *nand = mtd_to_nand(mtd);
+	unsigned int m, t, eccsteps, i;
+	struct nand_bch_control *nbc = NULL;
+	unsigned char *erased_page;
+	unsigned int eccsize = nand->ecc.size;
+	unsigned int eccbytes = nand->ecc.bytes;
+	unsigned int eccstrength = nand->ecc.strength;
+
+	if (!eccbytes && eccstrength) {
+		eccbytes = DIV_ROUND_UP(eccstrength * fls(8 * eccsize), 8);
+		nand->ecc.bytes = eccbytes;
+	}
+
+	if (!eccsize || !eccbytes) {
+		pr_warn("ecc parameters not supplied\n");
+		goto fail;
+	}
+
+	m = fls(1+8*eccsize);
+	t = (eccbytes*8)/m;
+
+	nbc = kzalloc(sizeof(*nbc), GFP_KERNEL);
+	if (!nbc)
+		goto fail;
+
+	nbc->bch = bch_init(m, t, 0, false);
+	if (!nbc->bch)
+		goto fail;
+
+	/* verify that eccbytes has the expected value */
+	if (nbc->bch->ecc_bytes != eccbytes) {
+		pr_warn("invalid eccbytes %u, should be %u\n",
+			eccbytes, nbc->bch->ecc_bytes);
+		goto fail;
+	}
+
+	eccsteps = mtd->writesize/eccsize;
+
+	/* Check that we have an oob layout description. */
+	if (!mtd->ooblayout) {
+		pr_warn("missing oob scheme");
+		goto fail;
+	}
+
+	/* sanity checks */
+	if (8*(eccsize+eccbytes) >= (1 << m)) {
+		pr_warn("eccsize %u is too large\n", eccsize);
+		goto fail;
+	}
+
+	/*
+	 * ecc->steps and ecc->total might be used by mtd->ooblayout->ecc(),
+	 * which is called by mtd_ooblayout_count_eccbytes().
+	 * Make sure they are properly initialized before calling
+	 * mtd_ooblayout_count_eccbytes().
+	 * FIXME: we should probably rework the sequencing in nand_scan_tail()
+	 * to avoid setting those fields twice.
+	 */
+	nand->ecc.steps = eccsteps;
+	nand->ecc.total = eccsteps * eccbytes;
+	nand->base.ecc.ctx.total = nand->ecc.total;
+	if (mtd_ooblayout_count_eccbytes(mtd) != (eccsteps*eccbytes)) {
+		pr_warn("invalid ecc layout\n");
+		goto fail;
+	}
+
+	nbc->eccmask = kzalloc(eccbytes, GFP_KERNEL);
+	nbc->errloc = kmalloc_array(t, sizeof(*nbc->errloc), GFP_KERNEL);
+	if (!nbc->eccmask || !nbc->errloc)
+		goto fail;
+	/*
+	 * compute and store the inverted ecc of an erased ecc block
+	 */
+	erased_page = kmalloc(eccsize, GFP_KERNEL);
+	if (!erased_page)
+		goto fail;
+
+	memset(erased_page, 0xff, eccsize);
+	bch_encode(nbc->bch, erased_page, eccsize, nbc->eccmask);
+	kfree(erased_page);
+
+	for (i = 0; i < eccbytes; i++)
+		nbc->eccmask[i] ^= 0xff;
+
+	if (!eccstrength)
+		nand->ecc.strength = (eccbytes * 8) / fls(8 * eccsize);
+
+	return nbc;
+fail:
+	nand_bch_free(nbc);
+	return NULL;
+}
+EXPORT_SYMBOL(nand_bch_init);
+
+/**
+ * nand_bch_free - [NAND Interface] Release NAND BCH ECC resources
+ * @nbc:	NAND BCH control structure
+ */
+void nand_bch_free(struct nand_bch_control *nbc)
+{
+	if (nbc) {
+		bch_free(nbc->bch);
+		kfree(nbc->errloc);
+		kfree(nbc->eccmask);
+		kfree(nbc);
+	}
+}
+EXPORT_SYMBOL(nand_bch_free);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Ivan Djelic <ivan.djelic@parrot.com>");
+MODULE_DESCRIPTION("NAND software BCH ECC support");
diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
index 6c46f25b57e2..b73860aa77c6 100644
--- a/drivers/mtd/nand/raw/Kconfig
+++ b/drivers/mtd/nand/raw/Kconfig
@@ -22,16 +22,6 @@ menuconfig MTD_RAW_NAND
 
 if MTD_RAW_NAND
 
-config MTD_NAND_ECC_SW_BCH
-	bool "Support software BCH ECC"
-	select BCH
-	default n
-	help
-	  This enables support for software BCH error correction. Binary BCH
-	  codes are more powerful and cpu intensive than traditional Hamming
-	  ECC codes. They are used with NAND devices requiring more than 1 bit
-	  of error correction.
-
 comment "Raw/parallel NAND flash controllers"
 
 config MTD_NAND_DENALI
diff --git a/drivers/mtd/nand/raw/Makefile b/drivers/mtd/nand/raw/Makefile
index 2930f5b9015d..76904305d091 100644
--- a/drivers/mtd/nand/raw/Makefile
+++ b/drivers/mtd/nand/raw/Makefile
@@ -2,7 +2,6 @@
 
 obj-$(CONFIG_MTD_RAW_NAND)		+= nand.o
 obj-$(CONFIG_MTD_NAND_ECC_SW_HAMMING)	+= nand_ecc.o
-nand-$(CONFIG_MTD_NAND_ECC_SW_BCH)	+= nand_bch.o
 obj-$(CONFIG_MTD_SM_COMMON) 		+= sm_common.o
 
 obj-$(CONFIG_MTD_NAND_CAFE)		+= cafe_nand.o
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 1f0d542d5923..7edcf08a2e81 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -36,7 +36,7 @@
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/nand.h>
 #include <linux/mtd/nand_ecc.h>
-#include <linux/mtd/nand_bch.h>
+#include <linux/mtd/nand-ecc-sw-bch.h>
 #include <linux/interrupt.h>
 #include <linux/bitops.h>
 #include <linux/io.h>
diff --git a/drivers/mtd/nand/raw/nand_bch.c b/drivers/mtd/nand/raw/nand_bch.c
deleted file mode 100644
index 9d19ac14c196..000000000000
--- a/drivers/mtd/nand/raw/nand_bch.c
+++ /dev/null
@@ -1,219 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * This file provides ECC correction for more than 1 bit per block of data,
- * using binary BCH codes. It relies on the generic BCH library lib/bch.c.
- *
- * Copyright © 2011 Ivan Djelic <ivan.djelic@parrot.com>
- */
-
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/slab.h>
-#include <linux/bitops.h>
-#include <linux/mtd/mtd.h>
-#include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand_bch.h>
-#include <linux/bch.h>
-
-/**
- * struct nand_bch_control - private NAND BCH control structure
- * @bch:       BCH control structure
- * @errloc:    error location array
- * @eccmask:   XOR ecc mask, allows erased pages to be decoded as valid
- */
-struct nand_bch_control {
-	struct bch_control   *bch;
-	unsigned int         *errloc;
-	unsigned char        *eccmask;
-};
-
-/**
- * nand_bch_calculate_ecc - [NAND Interface] Calculate ECC for data block
- * @chip:	NAND chip object
- * @buf:	input buffer with raw data
- * @code:	output buffer with ECC
- */
-int nand_bch_calculate_ecc(struct nand_chip *chip, const unsigned char *buf,
-			   unsigned char *code)
-{
-	struct nand_bch_control *nbc = chip->ecc.priv;
-	unsigned int i;
-
-	memset(code, 0, chip->ecc.bytes);
-	bch_encode(nbc->bch, buf, chip->ecc.size, code);
-
-	/* apply mask so that an erased page is a valid codeword */
-	for (i = 0; i < chip->ecc.bytes; i++)
-		code[i] ^= nbc->eccmask[i];
-
-	return 0;
-}
-EXPORT_SYMBOL(nand_bch_calculate_ecc);
-
-/**
- * nand_bch_correct_data - [NAND Interface] Detect and correct bit error(s)
- * @chip:	NAND chip object
- * @buf:	raw data read from the chip
- * @read_ecc:	ECC from the chip
- * @calc_ecc:	the ECC calculated from raw data
- *
- * Detect and correct bit errors for a data byte block
- */
-int nand_bch_correct_data(struct nand_chip *chip, unsigned char *buf,
-			  unsigned char *read_ecc, unsigned char *calc_ecc)
-{
-	struct nand_bch_control *nbc = chip->ecc.priv;
-	unsigned int *errloc = nbc->errloc;
-	int i, count;
-
-	count = bch_decode(nbc->bch, NULL, chip->ecc.size, read_ecc, calc_ecc,
-			   NULL, errloc);
-	if (count > 0) {
-		for (i = 0; i < count; i++) {
-			if (errloc[i] < (chip->ecc.size*8))
-				/* error is located in data, correct it */
-				buf[errloc[i] >> 3] ^= (1 << (errloc[i] & 7));
-			/* else error in ecc, no action needed */
-
-			pr_debug("%s: corrected bitflip %u\n", __func__,
-					errloc[i]);
-		}
-	} else if (count < 0) {
-		pr_err("ecc unrecoverable error\n");
-		count = -EBADMSG;
-	}
-	return count;
-}
-EXPORT_SYMBOL(nand_bch_correct_data);
-
-/**
- * nand_bch_init - [NAND Interface] Initialize NAND BCH error correction
- * @mtd:	MTD block structure
- *
- * Returns:
- *  a pointer to a new NAND BCH control structure, or NULL upon failure
- *
- * Initialize NAND BCH error correction. Parameters @eccsize and @eccbytes
- * are used to compute BCH parameters m (Galois field order) and t (error
- * correction capability). @eccbytes should be equal to the number of bytes
- * required to store m*t bits, where m is such that 2^m-1 > @eccsize*8.
- *
- * Example: to configure 4 bit correction per 512 bytes, you should pass
- * @eccsize = 512  (thus, m=13 is the smallest integer such that 2^m-1 > 512*8)
- * @eccbytes = 7   (7 bytes are required to store m*t = 13*4 = 52 bits)
- */
-struct nand_bch_control *nand_bch_init(struct mtd_info *mtd)
-{
-	struct nand_chip *nand = mtd_to_nand(mtd);
-	unsigned int m, t, eccsteps, i;
-	struct nand_bch_control *nbc = NULL;
-	unsigned char *erased_page;
-	unsigned int eccsize = nand->ecc.size;
-	unsigned int eccbytes = nand->ecc.bytes;
-	unsigned int eccstrength = nand->ecc.strength;
-
-	if (!eccbytes && eccstrength) {
-		eccbytes = DIV_ROUND_UP(eccstrength * fls(8 * eccsize), 8);
-		nand->ecc.bytes = eccbytes;
-	}
-
-	if (!eccsize || !eccbytes) {
-		pr_warn("ecc parameters not supplied\n");
-		goto fail;
-	}
-
-	m = fls(1+8*eccsize);
-	t = (eccbytes*8)/m;
-
-	nbc = kzalloc(sizeof(*nbc), GFP_KERNEL);
-	if (!nbc)
-		goto fail;
-
-	nbc->bch = bch_init(m, t, 0, false);
-	if (!nbc->bch)
-		goto fail;
-
-	/* verify that eccbytes has the expected value */
-	if (nbc->bch->ecc_bytes != eccbytes) {
-		pr_warn("invalid eccbytes %u, should be %u\n",
-			eccbytes, nbc->bch->ecc_bytes);
-		goto fail;
-	}
-
-	eccsteps = mtd->writesize/eccsize;
-
-	/* Check that we have an oob layout description. */
-	if (!mtd->ooblayout) {
-		pr_warn("missing oob scheme");
-		goto fail;
-	}
-
-	/* sanity checks */
-	if (8*(eccsize+eccbytes) >= (1 << m)) {
-		pr_warn("eccsize %u is too large\n", eccsize);
-		goto fail;
-	}
-
-	/*
-	 * ecc->steps and ecc->total might be used by mtd->ooblayout->ecc(),
-	 * which is called by mtd_ooblayout_count_eccbytes().
-	 * Make sure they are properly initialized before calling
-	 * mtd_ooblayout_count_eccbytes().
-	 * FIXME: we should probably rework the sequencing in nand_scan_tail()
-	 * to avoid setting those fields twice.
-	 */
-	nand->ecc.steps = eccsteps;
-	nand->ecc.total = eccsteps * eccbytes;
-	nand->base.ecc.ctx.total = nand->ecc.total;
-	if (mtd_ooblayout_count_eccbytes(mtd) != (eccsteps*eccbytes)) {
-		pr_warn("invalid ecc layout\n");
-		goto fail;
-	}
-
-	nbc->eccmask = kzalloc(eccbytes, GFP_KERNEL);
-	nbc->errloc = kmalloc_array(t, sizeof(*nbc->errloc), GFP_KERNEL);
-	if (!nbc->eccmask || !nbc->errloc)
-		goto fail;
-	/*
-	 * compute and store the inverted ecc of an erased ecc block
-	 */
-	erased_page = kmalloc(eccsize, GFP_KERNEL);
-	if (!erased_page)
-		goto fail;
-
-	memset(erased_page, 0xff, eccsize);
-	bch_encode(nbc->bch, erased_page, eccsize, nbc->eccmask);
-	kfree(erased_page);
-
-	for (i = 0; i < eccbytes; i++)
-		nbc->eccmask[i] ^= 0xff;
-
-	if (!eccstrength)
-		nand->ecc.strength = (eccbytes * 8) / fls(8 * eccsize);
-
-	return nbc;
-fail:
-	nand_bch_free(nbc);
-	return NULL;
-}
-EXPORT_SYMBOL(nand_bch_init);
-
-/**
- * nand_bch_free - [NAND Interface] Release NAND BCH ECC resources
- * @nbc:	NAND BCH control structure
- */
-void nand_bch_free(struct nand_bch_control *nbc)
-{
-	if (nbc) {
-		bch_free(nbc->bch);
-		kfree(nbc->errloc);
-		kfree(nbc->eccmask);
-		kfree(nbc);
-	}
-}
-EXPORT_SYMBOL(nand_bch_free);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Ivan Djelic <ivan.djelic@parrot.com>");
-MODULE_DESCRIPTION("NAND software BCH ECC support");
diff --git a/drivers/mtd/nand/raw/nandsim.c b/drivers/mtd/nand/raw/nandsim.c
index a8048cb8d220..9c940ead66fd 100644
--- a/drivers/mtd/nand/raw/nandsim.c
+++ b/drivers/mtd/nand/raw/nandsim.c
@@ -23,7 +23,7 @@
 #include <linux/string.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand_bch.h>
+#include <linux/mtd/nand-ecc-sw-bch.h>
 #include <linux/mtd/partitions.h>
 #include <linux/delay.h>
 #include <linux/list.h>
diff --git a/drivers/mtd/nand/raw/omap2.c b/drivers/mtd/nand/raw/omap2.c
index 512f60780a50..0ef209e1cd87 100644
--- a/drivers/mtd/nand/raw/omap2.c
+++ b/drivers/mtd/nand/raw/omap2.c
@@ -23,7 +23,7 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 
-#include <linux/mtd/nand_bch.h>
+#include <linux/mtd/nand-ecc-sw-bch.h>
 #include <linux/platform_data/elm.h>
 
 #include <linux/omap-gpmc.h>
diff --git a/include/linux/mtd/nand-ecc-sw-bch.h b/include/linux/mtd/nand-ecc-sw-bch.h
new file mode 100644
index 000000000000..1e1ee3af82b1
--- /dev/null
+++ b/include/linux/mtd/nand-ecc-sw-bch.h
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright © 2011 Ivan Djelic <ivan.djelic@parrot.com>
+ *
+ * This file is the header for the NAND BCH ECC implementation.
+ */
+
+#ifndef __MTD_NAND_ECC_SW_BCH_H__
+#define __MTD_NAND_ECC_SW_BCH_H__
+
+struct mtd_info;
+struct nand_chip;
+struct nand_bch_control;
+
+#if IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_BCH)
+
+static inline int mtd_nand_has_bch(void) { return 1; }
+
+/*
+ * Calculate BCH ecc code
+ */
+int nand_bch_calculate_ecc(struct nand_chip *chip, const u_char *dat,
+			   u_char *ecc_code);
+
+/*
+ * Detect and correct bit errors
+ */
+int nand_bch_correct_data(struct nand_chip *chip, u_char *dat,
+			  u_char *read_ecc, u_char *calc_ecc);
+/*
+ * Initialize BCH encoder/decoder
+ */
+struct nand_bch_control *nand_bch_init(struct mtd_info *mtd);
+/*
+ * Release BCH encoder/decoder resources
+ */
+void nand_bch_free(struct nand_bch_control *nbc);
+
+#else /* !CONFIG_MTD_NAND_ECC_SW_BCH */
+
+static inline int mtd_nand_has_bch(void) { return 0; }
+
+static inline int
+nand_bch_calculate_ecc(struct nand_chip *chip, const u_char *dat,
+		       u_char *ecc_code)
+{
+	return -1;
+}
+
+static inline int
+nand_bch_correct_data(struct nand_chip *chip, unsigned char *buf,
+		      unsigned char *read_ecc, unsigned char *calc_ecc)
+{
+	return -ENOTSUPP;
+}
+
+static inline struct nand_bch_control *nand_bch_init(struct mtd_info *mtd)
+{
+	return NULL;
+}
+
+static inline void nand_bch_free(struct nand_bch_control *nbc) {}
+
+#endif /* CONFIG_MTD_NAND_ECC_SW_BCH */
+
+#endif /* __MTD_NAND_ECC_SW_BCH_H__ */
diff --git a/include/linux/mtd/nand_bch.h b/include/linux/mtd/nand_bch.h
deleted file mode 100644
index d5956cc48ba9..000000000000
--- a/include/linux/mtd/nand_bch.h
+++ /dev/null
@@ -1,66 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright © 2011 Ivan Djelic <ivan.djelic@parrot.com>
- *
- * This file is the header for the NAND BCH ECC implementation.
- */
-
-#ifndef __MTD_NAND_BCH_H__
-#define __MTD_NAND_BCH_H__
-
-struct mtd_info;
-struct nand_chip;
-struct nand_bch_control;
-
-#if IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_BCH)
-
-static inline int mtd_nand_has_bch(void) { return 1; }
-
-/*
- * Calculate BCH ecc code
- */
-int nand_bch_calculate_ecc(struct nand_chip *chip, const u_char *dat,
-			   u_char *ecc_code);
-
-/*
- * Detect and correct bit errors
- */
-int nand_bch_correct_data(struct nand_chip *chip, u_char *dat,
-			  u_char *read_ecc, u_char *calc_ecc);
-/*
- * Initialize BCH encoder/decoder
- */
-struct nand_bch_control *nand_bch_init(struct mtd_info *mtd);
-/*
- * Release BCH encoder/decoder resources
- */
-void nand_bch_free(struct nand_bch_control *nbc);
-
-#else /* !CONFIG_MTD_NAND_ECC_SW_BCH */
-
-static inline int mtd_nand_has_bch(void) { return 0; }
-
-static inline int
-nand_bch_calculate_ecc(struct nand_chip *chip, const u_char *dat,
-		       u_char *ecc_code)
-{
-	return -1;
-}
-
-static inline int
-nand_bch_correct_data(struct nand_chip *chip, unsigned char *buf,
-		      unsigned char *read_ecc, unsigned char *calc_ecc)
-{
-	return -ENOTSUPP;
-}
-
-static inline struct nand_bch_control *nand_bch_init(struct mtd_info *mtd)
-{
-	return NULL;
-}
-
-static inline void nand_bch_free(struct nand_bch_control *nbc) {}
-
-#endif /* CONFIG_MTD_NAND_ECC_SW_BCH */
-
-#endif /* __MTD_NAND_BCH_H__ */
-- 
cgit v1.2.3


From 3c0fe36abebee55821badaa9d6cecd03799f7843 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 30 Sep 2020 01:01:08 +0200
Subject: mtd: nand: ecc-bch: Stop exporting the private structure

The NAND BCH control structure has nothing to do outside of this
driver, all users of the nand_bch_init/free() functions just save it
to chip->ecc.priv so do it in this driver directly and return a
regular error code instead.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200929230124.31491-5-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/ecc-sw-bch.c       | 38 ++++++++++++++++++++-----------------
 drivers/mtd/nand/raw/fsmc_nand.c    |  2 +-
 drivers/mtd/nand/raw/nand_base.c    | 12 +++++++-----
 drivers/mtd/nand/raw/omap2.c        | 16 ++++++++--------
 include/linux/mtd/nand-ecc-sw-bch.h | 11 +++++------
 5 files changed, 42 insertions(+), 37 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/ecc-sw-bch.c b/drivers/mtd/nand/ecc-sw-bch.c
index f98a03e8efae..b6bfee9805ae 100644
--- a/drivers/mtd/nand/ecc-sw-bch.c
+++ b/drivers/mtd/nand/ecc-sw-bch.c
@@ -90,7 +90,7 @@ EXPORT_SYMBOL(nand_bch_correct_data);
 
 /**
  * nand_bch_init - Initialize software BCH ECC engine
- * @mtd: MTD device
+ * @chip: NAND chip object
  *
  * Returns: a pointer to a new NAND BCH control structure, or NULL upon failure
  *
@@ -105,24 +105,24 @@ EXPORT_SYMBOL(nand_bch_correct_data);
  * @eccsize = 512 (thus, m = 13 is the smallest integer such that 2^m - 1 > 512 * 8)
  * @eccbytes = 7 (7 bytes are required to store m * t = 13 * 4 = 52 bits)
  */
-struct nand_bch_control *nand_bch_init(struct mtd_info *mtd)
+int nand_bch_init(struct nand_chip *chip)
 {
-	struct nand_chip *nand = mtd_to_nand(mtd);
+	struct mtd_info *mtd = nand_to_mtd(chip);
 	unsigned int m, t, eccsteps, i;
 	struct nand_bch_control *nbc = NULL;
 	unsigned char *erased_page;
-	unsigned int eccsize = nand->ecc.size;
-	unsigned int eccbytes = nand->ecc.bytes;
-	unsigned int eccstrength = nand->ecc.strength;
+	unsigned int eccsize = chip->ecc.size;
+	unsigned int eccbytes = chip->ecc.bytes;
+	unsigned int eccstrength = chip->ecc.strength;
 
 	if (!eccbytes && eccstrength) {
 		eccbytes = DIV_ROUND_UP(eccstrength * fls(8 * eccsize), 8);
-		nand->ecc.bytes = eccbytes;
+		chip->ecc.bytes = eccbytes;
 	}
 
 	if (!eccsize || !eccbytes) {
 		pr_warn("ecc parameters not supplied\n");
-		goto fail;
+		return -EINVAL;
 	}
 
 	m = fls(1+8*eccsize);
@@ -130,7 +130,9 @@ struct nand_bch_control *nand_bch_init(struct mtd_info *mtd)
 
 	nbc = kzalloc(sizeof(*nbc), GFP_KERNEL);
 	if (!nbc)
-		goto fail;
+		return -ENOMEM;
+
+	chip->ecc.priv = nbc;
 
 	nbc->bch = bch_init(m, t, 0, false);
 	if (!nbc->bch)
@@ -165,9 +167,9 @@ struct nand_bch_control *nand_bch_init(struct mtd_info *mtd)
 	 * FIXME: we should probably rework the sequencing in nand_scan_tail()
 	 * to avoid setting those fields twice.
 	 */
-	nand->ecc.steps = eccsteps;
-	nand->ecc.total = eccsteps * eccbytes;
-	nand->base.ecc.ctx.total = nand->ecc.total;
+	chip->ecc.steps = eccsteps;
+	chip->ecc.total = eccsteps * eccbytes;
+	nand->base.ecc.ctx.total = chip->ecc.total;
 	if (mtd_ooblayout_count_eccbytes(mtd) != (eccsteps*eccbytes)) {
 		pr_warn("invalid ecc layout\n");
 		goto fail;
@@ -193,12 +195,12 @@ struct nand_bch_control *nand_bch_init(struct mtd_info *mtd)
 		nbc->eccmask[i] ^= 0xff;
 
 	if (!eccstrength)
-		nand->ecc.strength = (eccbytes * 8) / fls(8 * eccsize);
+		chip->ecc.strength = (eccbytes * 8) / fls(8 * eccsize);
 
-	return nbc;
+	return 0;
 fail:
-	nand_bch_free(nbc);
-	return NULL;
+	nand_bch_free(chip);
+	return -EINVAL;
 }
 EXPORT_SYMBOL(nand_bch_init);
 
@@ -206,8 +208,10 @@ EXPORT_SYMBOL(nand_bch_init);
  * nand_bch_free - Release NAND BCH ECC resources
  * @nbc: NAND BCH control structure
  */
-void nand_bch_free(struct nand_bch_control *nbc)
+void nand_bch_free(struct nand_chip *chip)
 {
+	struct nand_bch_control *nbc = chip->ecc.priv;
+
 	if (nbc) {
 		bch_free(nbc->bch);
 		kfree(nbc->errloc);
diff --git a/drivers/mtd/nand/raw/fsmc_nand.c b/drivers/mtd/nand/raw/fsmc_nand.c
index c88421a1c078..984b05e6bd38 100644
--- a/drivers/mtd/nand/raw/fsmc_nand.c
+++ b/drivers/mtd/nand/raw/fsmc_nand.c
@@ -942,7 +942,7 @@ static int fsmc_nand_attach_chip(struct nand_chip *nand)
 
 	/*
 	 * Don't set layout for BCH4 SW ECC. This will be
-	 * generated later in nand_bch_init() later.
+	 * generated later during BCH initialization.
 	 */
 	if (nand->ecc.engine_type == NAND_ECC_ENGINE_TYPE_ON_HOST) {
 		switch (mtd->oobsize) {
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 7edcf08a2e81..287c521a3d43 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -5203,6 +5203,7 @@ static int nand_set_ecc_soft_ops(struct nand_chip *chip)
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct nand_device *nanddev = mtd_to_nanddev(mtd);
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
+	int ret;
 
 	if (WARN_ON(ecc->engine_type != NAND_ECC_ENGINE_TYPE_SOFT))
 		return -EINVAL;
@@ -5289,13 +5290,14 @@ static int nand_set_ecc_soft_ops(struct nand_chip *chip)
 			ecc->strength = bytes * 8 / fls(8 * ecc->size);
 		}
 
-		/* See nand_bch_init() for details. */
+		/* See the software BCH ECC initialization for details */
 		ecc->bytes = 0;
-		ecc->priv = nand_bch_init(mtd);
-		if (!ecc->priv) {
+		ret = nand_bch_init(chip);
+		if (ret) {
 			WARN(1, "BCH ECC initialization failed!\n");
-			return -EINVAL;
+			return ret;
 		}
+
 		return 0;
 	default:
 		WARN(1, "Unsupported ECC algorithm!\n");
@@ -5955,7 +5957,7 @@ void nand_cleanup(struct nand_chip *chip)
 {
 	if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_SOFT &&
 	    chip->ecc.algo == NAND_ECC_ALGO_BCH)
-		nand_bch_free((struct nand_bch_control *)chip->ecc.priv);
+		nand_bch_free(chip);
 
 	nanddev_cleanup(&chip->base);
 
diff --git a/drivers/mtd/nand/raw/omap2.c b/drivers/mtd/nand/raw/omap2.c
index 0ef209e1cd87..6aab57336690 100644
--- a/drivers/mtd/nand/raw/omap2.c
+++ b/drivers/mtd/nand/raw/omap2.c
@@ -2047,10 +2047,10 @@ static int omap_nand_attach_chip(struct nand_chip *chip)
 		/* Reserve one byte for the OMAP marker */
 		oobbytes_per_step	= chip->ecc.bytes + 1;
 		/* Software BCH library is used for locating errors */
-		chip->ecc.priv		= nand_bch_init(mtd);
-		if (!chip->ecc.priv) {
+		err = nand_bch_init(chip);
+		if (err) {
 			dev_err(dev, "Unable to use BCH library\n");
-			return -EINVAL;
+			return err;
 		}
 		break;
 
@@ -2089,10 +2089,10 @@ static int omap_nand_attach_chip(struct nand_chip *chip)
 		/* Reserve one byte for the OMAP marker */
 		oobbytes_per_step	= chip->ecc.bytes + 1;
 		/* Software BCH library is used for locating errors */
-		chip->ecc.priv		= nand_bch_init(mtd);
-		if (!chip->ecc.priv) {
+		err = nand_bch_init(chip);
+		if (err) {
 			dev_err(dev, "unable to use BCH library\n");
-			return -EINVAL;
+			return err;
 		}
 		break;
 
@@ -2272,7 +2272,7 @@ return_error:
 	if (!IS_ERR_OR_NULL(info->dma))
 		dma_release_channel(info->dma);
 	if (nand_chip->ecc.priv) {
-		nand_bch_free(nand_chip->ecc.priv);
+		nand_bch_free(nand_chip);
 		nand_chip->ecc.priv = NULL;
 	}
 	return err;
@@ -2286,7 +2286,7 @@ static int omap_nand_remove(struct platform_device *pdev)
 	int ret;
 
 	if (nand_chip->ecc.priv) {
-		nand_bch_free(nand_chip->ecc.priv);
+		nand_bch_free(nand_chip);
 		nand_chip->ecc.priv = NULL;
 	}
 	if (info->dma)
diff --git a/include/linux/mtd/nand-ecc-sw-bch.h b/include/linux/mtd/nand-ecc-sw-bch.h
index 1e1ee3af82b1..b62b8bd4669f 100644
--- a/include/linux/mtd/nand-ecc-sw-bch.h
+++ b/include/linux/mtd/nand-ecc-sw-bch.h
@@ -10,7 +10,6 @@
 
 struct mtd_info;
 struct nand_chip;
-struct nand_bch_control;
 
 #if IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_BCH)
 
@@ -30,11 +29,11 @@ int nand_bch_correct_data(struct nand_chip *chip, u_char *dat,
 /*
  * Initialize BCH encoder/decoder
  */
-struct nand_bch_control *nand_bch_init(struct mtd_info *mtd);
+int nand_bch_init(struct nand_chip *chip);
 /*
  * Release BCH encoder/decoder resources
  */
-void nand_bch_free(struct nand_bch_control *nbc);
+void nand_bch_free(struct nand_chip *chip);
 
 #else /* !CONFIG_MTD_NAND_ECC_SW_BCH */
 
@@ -54,12 +53,12 @@ nand_bch_correct_data(struct nand_chip *chip, unsigned char *buf,
 	return -ENOTSUPP;
 }
 
-static inline struct nand_bch_control *nand_bch_init(struct mtd_info *mtd)
+static inline int nand_bch_init(struct nand_chip *chip)
 {
-	return NULL;
+	return -ENOTSUPP;
 }
 
-static inline void nand_bch_free(struct nand_bch_control *nbc) {}
+static inline void nand_bch_free(struct nand_chip *chip) {}
 
 #endif /* CONFIG_MTD_NAND_ECC_SW_BCH */
 
-- 
cgit v1.2.3


From e3010bd3ef1eda13f08155fe43846a64d0990a86 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 30 Sep 2020 01:01:09 +0200
Subject: mtd: nand: ecc-bch: Return only valid error codes

When a function is not available, returning -ENOTSUPP makes much more
sense than returning -1.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200929230124.31491-6-miquel.raynal@bootlin.com
---
 include/linux/mtd/nand-ecc-sw-bch.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/mtd/nand-ecc-sw-bch.h b/include/linux/mtd/nand-ecc-sw-bch.h
index b62b8bd4669f..d92d2abcfcef 100644
--- a/include/linux/mtd/nand-ecc-sw-bch.h
+++ b/include/linux/mtd/nand-ecc-sw-bch.h
@@ -43,7 +43,7 @@ static inline int
 nand_bch_calculate_ecc(struct nand_chip *chip, const u_char *dat,
 		       u_char *ecc_code)
 {
-	return -1;
+	return -ENOTSUPP;
 }
 
 static inline int
-- 
cgit v1.2.3


From 127aae6077562e3926ebad7c782123c2afe95846 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 30 Sep 2020 01:01:10 +0200
Subject: mtd: nand: ecc-bch: Drop mtd_nand_has_bch()

Like for any other compilation option, use the IS_ENABLED() macro
instead of hardcoding it.

By droping this helper we can get rid of the BCH header in nandsim.c.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200929230124.31491-7-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/raw/nand_base.c    | 2 +-
 drivers/mtd/nand/raw/nandsim.c      | 3 +--
 include/linux/mtd/nand-ecc-sw-bch.h | 4 ----
 3 files changed, 2 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 287c521a3d43..b49483d04755 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -5231,7 +5231,7 @@ static int nand_set_ecc_soft_ops(struct nand_chip *chip)
 
 		return 0;
 	case NAND_ECC_ALGO_BCH:
-		if (!mtd_nand_has_bch()) {
+		if (!IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_BCH)) {
 			WARN(1, "CONFIG_MTD_NAND_ECC_SW_BCH not enabled\n");
 			return -EINVAL;
 		}
diff --git a/drivers/mtd/nand/raw/nandsim.c b/drivers/mtd/nand/raw/nandsim.c
index 9c940ead66fd..f2b9250c0ea8 100644
--- a/drivers/mtd/nand/raw/nandsim.c
+++ b/drivers/mtd/nand/raw/nandsim.c
@@ -23,7 +23,6 @@
 #include <linux/string.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand-ecc-sw-bch.h>
 #include <linux/mtd/partitions.h>
 #include <linux/delay.h>
 #include <linux/list.h>
@@ -2214,7 +2213,7 @@ static int ns_attach_chip(struct nand_chip *chip)
 	if (!bch)
 		return 0;
 
-	if (!mtd_nand_has_bch()) {
+	if (!IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_BCH)) {
 		NS_ERR("BCH ECC support is disabled\n");
 		return -EINVAL;
 	}
diff --git a/include/linux/mtd/nand-ecc-sw-bch.h b/include/linux/mtd/nand-ecc-sw-bch.h
index d92d2abcfcef..7b62996d9e01 100644
--- a/include/linux/mtd/nand-ecc-sw-bch.h
+++ b/include/linux/mtd/nand-ecc-sw-bch.h
@@ -13,8 +13,6 @@ struct nand_chip;
 
 #if IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_BCH)
 
-static inline int mtd_nand_has_bch(void) { return 1; }
-
 /*
  * Calculate BCH ecc code
  */
@@ -37,8 +35,6 @@ void nand_bch_free(struct nand_chip *chip);
 
 #else /* !CONFIG_MTD_NAND_ECC_SW_BCH */
 
-static inline int mtd_nand_has_bch(void) { return 0; }
-
 static inline int
 nand_bch_calculate_ecc(struct nand_chip *chip, const u_char *dat,
 		       u_char *ecc_code)
-- 
cgit v1.2.3


From ea146d7fbf5081b5eb2777df5e30ed70ca68985b Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 30 Sep 2020 01:01:11 +0200
Subject: mtd: nand: ecc-bch: Update the prototypes to be more generic

These functions must be usable by the main NAND core, so their names
must be technology-agnostic as well as the parameters. Hence, we pass
a generic nand_device instead of a raw nand_chip structure.

As it seems that changing the raw NAND functions to always pass a
generic NAND device is a lost of time, we prefer to create dedicated
raw NAND wrappers that will be useful in the near future to do the
translation.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200929230124.31491-8-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/ecc-sw-bch.c       | 47 +++++++++++++++++++++----------------
 drivers/mtd/nand/raw/nand_base.c    | 44 ++++++++++++++++++++++++++++++----
 drivers/mtd/nand/raw/omap2.c        | 23 +++++++-----------
 include/linux/mtd/nand-ecc-sw-bch.h | 45 +++++++++++++----------------------
 include/linux/mtd/rawnand.h         |  5 ++++
 5 files changed, 97 insertions(+), 67 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/ecc-sw-bch.c b/drivers/mtd/nand/ecc-sw-bch.c
index b6bfee9805ae..eae81bace01c 100644
--- a/drivers/mtd/nand/ecc-sw-bch.c
+++ b/drivers/mtd/nand/ecc-sw-bch.c
@@ -13,6 +13,7 @@
 #include <linux/bitops.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
+#include <linux/mtd/nand.h>
 #include <linux/mtd/nand-ecc-sw-bch.h>
 #include <linux/bch.h>
 
@@ -29,14 +30,15 @@ struct nand_bch_control {
 };
 
 /**
- * nand_bch_calcuate_ecc - Calculate the ECC corresponding to a data block
- * @chip: NAND chip object
+ * nand_ecc_sw_bch_calculate - Calculate the ECC corresponding to a data block
+ * @nand: NAND device
  * @buf: Input buffer with raw data
  * @code: Output buffer with ECC
  */
-int nand_bch_calculate_ecc(struct nand_chip *chip, const unsigned char *buf,
-			   unsigned char *code)
+int nand_ecc_sw_bch_calculate(struct nand_device *nand,
+			      const unsigned char *buf, unsigned char *code)
 {
+	struct nand_chip *chip = mtd_to_nand(nanddev_to_mtd(nand));
 	struct nand_bch_control *nbc = chip->ecc.priv;
 	unsigned int i;
 
@@ -49,20 +51,21 @@ int nand_bch_calculate_ecc(struct nand_chip *chip, const unsigned char *buf,
 
 	return 0;
 }
-EXPORT_SYMBOL(nand_bch_calculate_ecc);
+EXPORT_SYMBOL(nand_ecc_sw_bch_calculate);
 
 /**
- * nand_bch_correct_data - Detect, correct and report bit error(s)
- * @chip: NAND chip object
+ * nand_ecc_sw_bch_correct - Detect, correct and report bit error(s)
+ * @nand: NAND device
  * @buf: Raw data read from the chip
  * @read_ecc: ECC bytes from the chip
  * @calc_ecc: ECC calculated from the raw data
  *
  * Detect and correct bit errors for a data block.
  */
-int nand_bch_correct_data(struct nand_chip *chip, unsigned char *buf,
-			  unsigned char *read_ecc, unsigned char *calc_ecc)
+int nand_ecc_sw_bch_correct(struct nand_device *nand, unsigned char *buf,
+			    unsigned char *read_ecc, unsigned char *calc_ecc)
 {
+	struct nand_chip *chip = mtd_to_nand(nanddev_to_mtd(nand));
 	struct nand_bch_control *nbc = chip->ecc.priv;
 	unsigned int *errloc = nbc->errloc;
 	int i, count;
@@ -86,11 +89,11 @@ int nand_bch_correct_data(struct nand_chip *chip, unsigned char *buf,
 
 	return count;
 }
-EXPORT_SYMBOL(nand_bch_correct_data);
+EXPORT_SYMBOL(nand_ecc_sw_bch_correct);
 
 /**
- * nand_bch_init - Initialize software BCH ECC engine
- * @chip: NAND chip object
+ * nand_ecc_sw_bch_init - Initialize software BCH ECC engine
+ * @nand: NAND device
  *
  * Returns: a pointer to a new NAND BCH control structure, or NULL upon failure
  *
@@ -105,9 +108,10 @@ EXPORT_SYMBOL(nand_bch_correct_data);
  * @eccsize = 512 (thus, m = 13 is the smallest integer such that 2^m - 1 > 512 * 8)
  * @eccbytes = 7 (7 bytes are required to store m * t = 13 * 4 = 52 bits)
  */
-int nand_bch_init(struct nand_chip *chip)
+int nand_ecc_sw_bch_init(struct nand_device *nand)
 {
-	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct mtd_info *mtd = nanddev_to_mtd(nand);
+	struct nand_chip *chip = mtd_to_nand(mtd);
 	unsigned int m, t, eccsteps, i;
 	struct nand_bch_control *nbc = NULL;
 	unsigned char *erased_page;
@@ -198,18 +202,21 @@ int nand_bch_init(struct nand_chip *chip)
 		chip->ecc.strength = (eccbytes * 8) / fls(8 * eccsize);
 
 	return 0;
+
 fail:
-	nand_bch_free(chip);
+	nand_ecc_sw_bch_cleanup(nand);
+
 	return -EINVAL;
 }
-EXPORT_SYMBOL(nand_bch_init);
+EXPORT_SYMBOL(nand_ecc_sw_bch_init);
 
 /**
- * nand_bch_free - Release NAND BCH ECC resources
- * @nbc: NAND BCH control structure
+ * nand_ecc_sw_bch_cleanup - Cleanup software BCH ECC resources
+ * @nand: NAND device
  */
-void nand_bch_free(struct nand_chip *chip)
+void nand_ecc_sw_bch_cleanup(struct nand_device *nand)
 {
+	struct nand_chip *chip = mtd_to_nand(nanddev_to_mtd(nand));
 	struct nand_bch_control *nbc = chip->ecc.priv;
 
 	if (nbc) {
@@ -219,7 +226,7 @@ void nand_bch_free(struct nand_chip *chip)
 		kfree(nbc);
 	}
 }
-EXPORT_SYMBOL(nand_bch_free);
+EXPORT_SYMBOL(nand_ecc_sw_bch_cleanup);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Ivan Djelic <ivan.djelic@parrot.com>");
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index b49483d04755..2ef674c10ac8 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -5139,6 +5139,42 @@ static void nand_scan_ident_cleanup(struct nand_chip *chip)
 	kfree(chip->parameters.onfi);
 }
 
+int rawnand_sw_bch_init(struct nand_chip *chip)
+{
+	struct nand_device *base = &chip->base;
+
+	return nand_ecc_sw_bch_init(base);
+}
+EXPORT_SYMBOL(rawnand_sw_bch_init);
+
+static int rawnand_sw_bch_calculate(struct nand_chip *chip,
+				    const unsigned char *buf,
+				    unsigned char *code)
+{
+	struct nand_device *base = &chip->base;
+
+	return nand_ecc_sw_bch_calculate(base, buf, code);
+}
+
+int rawnand_sw_bch_correct(struct nand_chip *chip, unsigned char *buf,
+			   unsigned char *read_ecc, unsigned char *calc_ecc)
+{
+	struct nand_device *base = &chip->base;
+
+	return nand_ecc_sw_bch_correct(base, buf, read_ecc, calc_ecc);
+}
+EXPORT_SYMBOL(rawnand_sw_bch_correct);
+
+void rawnand_sw_bch_cleanup(struct nand_chip *chip)
+{
+	struct nand_device *base = &chip->base;
+
+	nand_ecc_sw_bch_cleanup(base);
+
+	chip->ecc.priv = NULL;
+}
+EXPORT_SYMBOL(rawnand_sw_bch_cleanup);
+
 static int nand_set_ecc_on_host_ops(struct nand_chip *chip)
 {
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
@@ -5235,8 +5271,8 @@ static int nand_set_ecc_soft_ops(struct nand_chip *chip)
 			WARN(1, "CONFIG_MTD_NAND_ECC_SW_BCH not enabled\n");
 			return -EINVAL;
 		}
-		ecc->calculate = nand_bch_calculate_ecc;
-		ecc->correct = nand_bch_correct_data;
+		ecc->calculate = rawnand_sw_bch_calculate;
+		ecc->correct = rawnand_sw_bch_correct;
 		ecc->read_page = nand_read_page_swecc;
 		ecc->read_subpage = nand_read_subpage;
 		ecc->write_page = nand_write_page_swecc;
@@ -5292,7 +5328,7 @@ static int nand_set_ecc_soft_ops(struct nand_chip *chip)
 
 		/* See the software BCH ECC initialization for details */
 		ecc->bytes = 0;
-		ret = nand_bch_init(chip);
+		ret = rawnand_sw_bch_init(chip);
 		if (ret) {
 			WARN(1, "BCH ECC initialization failed!\n");
 			return ret;
@@ -5957,7 +5993,7 @@ void nand_cleanup(struct nand_chip *chip)
 {
 	if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_SOFT &&
 	    chip->ecc.algo == NAND_ECC_ALGO_BCH)
-		nand_bch_free(chip);
+		rawnand_sw_bch_cleanup(chip);
 
 	nanddev_cleanup(&chip->base);
 
diff --git a/drivers/mtd/nand/raw/omap2.c b/drivers/mtd/nand/raw/omap2.c
index 6aab57336690..4cc47ab7f01a 100644
--- a/drivers/mtd/nand/raw/omap2.c
+++ b/drivers/mtd/nand/raw/omap2.c
@@ -23,7 +23,6 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 
-#include <linux/mtd/nand-ecc-sw-bch.h>
 #include <linux/platform_data/elm.h>
 
 #include <linux/omap-gpmc.h>
@@ -2041,13 +2040,13 @@ static int omap_nand_attach_chip(struct nand_chip *chip)
 		chip->ecc.bytes		= 7;
 		chip->ecc.strength	= 4;
 		chip->ecc.hwctl		= omap_enable_hwecc_bch;
-		chip->ecc.correct	= nand_bch_correct_data;
+		chip->ecc.correct	= rawnand_sw_bch_correct;
 		chip->ecc.calculate	= omap_calculate_ecc_bch_sw;
 		mtd_set_ooblayout(mtd, &omap_sw_ooblayout_ops);
 		/* Reserve one byte for the OMAP marker */
 		oobbytes_per_step	= chip->ecc.bytes + 1;
 		/* Software BCH library is used for locating errors */
-		err = nand_bch_init(chip);
+		err = rawnand_sw_bch_init(chip);
 		if (err) {
 			dev_err(dev, "Unable to use BCH library\n");
 			return err;
@@ -2083,13 +2082,13 @@ static int omap_nand_attach_chip(struct nand_chip *chip)
 		chip->ecc.bytes		= 13;
 		chip->ecc.strength	= 8;
 		chip->ecc.hwctl		= omap_enable_hwecc_bch;
-		chip->ecc.correct	= nand_bch_correct_data;
+		chip->ecc.correct	= rawnand_sw_bch_correct;
 		chip->ecc.calculate	= omap_calculate_ecc_bch_sw;
 		mtd_set_ooblayout(mtd, &omap_sw_ooblayout_ops);
 		/* Reserve one byte for the OMAP marker */
 		oobbytes_per_step	= chip->ecc.bytes + 1;
 		/* Software BCH library is used for locating errors */
-		err = nand_bch_init(chip);
+		err = rawnand_sw_bch_init(chip);
 		if (err) {
 			dev_err(dev, "unable to use BCH library\n");
 			return err;
@@ -2195,7 +2194,6 @@ static int omap_nand_probe(struct platform_device *pdev)
 	nand_chip		= &info->nand;
 	mtd			= nand_to_mtd(nand_chip);
 	mtd->dev.parent		= &pdev->dev;
-	nand_chip->ecc.priv	= NULL;
 	nand_set_flash_node(nand_chip, dev->of_node);
 
 	if (!mtd->name) {
@@ -2271,10 +2269,9 @@ cleanup_nand:
 return_error:
 	if (!IS_ERR_OR_NULL(info->dma))
 		dma_release_channel(info->dma);
-	if (nand_chip->ecc.priv) {
-		nand_bch_free(nand_chip);
-		nand_chip->ecc.priv = NULL;
-	}
+
+	rawnand_sw_bch_cleanup(nand_chip);
+
 	return err;
 }
 
@@ -2285,10 +2282,8 @@ static int omap_nand_remove(struct platform_device *pdev)
 	struct omap_nand_info *info = mtd_to_omap(mtd);
 	int ret;
 
-	if (nand_chip->ecc.priv) {
-		nand_bch_free(nand_chip);
-		nand_chip->ecc.priv = NULL;
-	}
+	rawnand_sw_bch_cleanup(nand_chip);
+
 	if (info->dma)
 		dma_release_channel(info->dma);
 	ret = mtd_device_unregister(mtd);
diff --git a/include/linux/mtd/nand-ecc-sw-bch.h b/include/linux/mtd/nand-ecc-sw-bch.h
index 7b62996d9e01..f0caee3b03d0 100644
--- a/include/linux/mtd/nand-ecc-sw-bch.h
+++ b/include/linux/mtd/nand-ecc-sw-bch.h
@@ -8,53 +8,40 @@
 #ifndef __MTD_NAND_ECC_SW_BCH_H__
 #define __MTD_NAND_ECC_SW_BCH_H__
 
-struct mtd_info;
-struct nand_chip;
+#include <linux/mtd/nand.h>
 
 #if IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_BCH)
 
-/*
- * Calculate BCH ecc code
- */
-int nand_bch_calculate_ecc(struct nand_chip *chip, const u_char *dat,
-			   u_char *ecc_code);
-
-/*
- * Detect and correct bit errors
- */
-int nand_bch_correct_data(struct nand_chip *chip, u_char *dat,
-			  u_char *read_ecc, u_char *calc_ecc);
-/*
- * Initialize BCH encoder/decoder
- */
-int nand_bch_init(struct nand_chip *chip);
-/*
- * Release BCH encoder/decoder resources
- */
-void nand_bch_free(struct nand_chip *chip);
+int nand_ecc_sw_bch_calculate(struct nand_device *nand,
+			      const unsigned char *buf, unsigned char *code);
+int nand_ecc_sw_bch_correct(struct nand_device *nand, unsigned char *buf,
+			    unsigned char *read_ecc, unsigned char *calc_ecc);
+int nand_ecc_sw_bch_init(struct nand_device *nand);
+void nand_ecc_sw_bch_cleanup(struct nand_device *nand);
 
 #else /* !CONFIG_MTD_NAND_ECC_SW_BCH */
 
-static inline int
-nand_bch_calculate_ecc(struct nand_chip *chip, const u_char *dat,
-		       u_char *ecc_code)
+static inline int nand_ecc_sw_bch_calculate(struct nand_device *nand,
+					    const unsigned char *buf,
+					    unsigned char *code)
 {
 	return -ENOTSUPP;
 }
 
-static inline int
-nand_bch_correct_data(struct nand_chip *chip, unsigned char *buf,
-		      unsigned char *read_ecc, unsigned char *calc_ecc)
+static inline int nand_ecc_sw_bch_correct(struct nand_device *nand,
+					  unsigned char *buf,
+					  unsigned char *read_ecc,
+					  unsigned char *calc_ecc)
 {
 	return -ENOTSUPP;
 }
 
-static inline int nand_bch_init(struct nand_chip *chip)
+static inline int nand_ecc_sw_bch_init(struct nand_device *nand)
 {
 	return -ENOTSUPP;
 }
 
-static inline void nand_bch_free(struct nand_chip *chip) {}
+static inline void nand_ecc_sw_bch_cleanup(struct nand_device *nand) {}
 
 #endif /* CONFIG_MTD_NAND_ECC_SW_BCH */
 
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index aac07940de09..23623beaad1d 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -1303,6 +1303,11 @@ static inline int nand_opcode_8bits(unsigned int command)
 	return 0;
 }
 
+int rawnand_sw_bch_init(struct nand_chip *chip);
+int rawnand_sw_bch_correct(struct nand_chip *chip, unsigned char *buf,
+			   unsigned char *read_ecc, unsigned char *calc_ecc);
+void rawnand_sw_bch_cleanup(struct nand_chip *chip);
+
 int nand_check_erased_ecc_chunk(void *data, int datalen,
 				void *ecc, int ecclen,
 				void *extraoob, int extraooblen,
-- 
cgit v1.2.3


From 80fe603160a4732a08f0f08f3e3312a3f3a79eee Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 30 Sep 2020 01:01:12 +0200
Subject: mtd: nand: ecc-bch: Stop using raw NAND structures

This code is meant to be reused by the SPI-NAND core. Now that the
driver has been cleaned and reorganized, use a generic ECC engine
object to store the driver's data instead of accessing members of the
nand_chip structure.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200929230124.31491-9-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/ecc-sw-bch.c       | 114 +++++++++++++-----------------------
 drivers/mtd/nand/raw/nand_base.c    |  38 ++++++++++--
 include/linux/mtd/nand-ecc-sw-bch.h |  25 ++++++++
 3 files changed, 98 insertions(+), 79 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/ecc-sw-bch.c b/drivers/mtd/nand/ecc-sw-bch.c
index eae81bace01c..16a54bd2ca31 100644
--- a/drivers/mtd/nand/ecc-sw-bch.c
+++ b/drivers/mtd/nand/ecc-sw-bch.c
@@ -11,23 +11,8 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/bitops.h>
-#include <linux/mtd/mtd.h>
-#include <linux/mtd/rawnand.h>
 #include <linux/mtd/nand.h>
 #include <linux/mtd/nand-ecc-sw-bch.h>
-#include <linux/bch.h>
-
-/**
- * struct nand_bch_control - private NAND BCH control structure
- * @bch:       BCH control structure
- * @errloc:    error location array
- * @eccmask:   XOR ecc mask, allows erased pages to be decoded as valid
- */
-struct nand_bch_control {
-	struct bch_control   *bch;
-	unsigned int         *errloc;
-	unsigned char        *eccmask;
-};
 
 /**
  * nand_ecc_sw_bch_calculate - Calculate the ECC corresponding to a data block
@@ -38,16 +23,15 @@ struct nand_bch_control {
 int nand_ecc_sw_bch_calculate(struct nand_device *nand,
 			      const unsigned char *buf, unsigned char *code)
 {
-	struct nand_chip *chip = mtd_to_nand(nanddev_to_mtd(nand));
-	struct nand_bch_control *nbc = chip->ecc.priv;
+	struct nand_ecc_sw_bch_conf *engine_conf = nand->ecc.ctx.priv;
 	unsigned int i;
 
-	memset(code, 0, chip->ecc.bytes);
-	bch_encode(nbc->bch, buf, chip->ecc.size, code);
+	memset(code, 0, engine_conf->code_size);
+	bch_encode(engine_conf->bch, buf, nand->ecc.ctx.conf.step_size, code);
 
 	/* apply mask so that an erased page is a valid codeword */
-	for (i = 0; i < chip->ecc.bytes; i++)
-		code[i] ^= nbc->eccmask[i];
+	for (i = 0; i < engine_conf->code_size; i++)
+		code[i] ^= engine_conf->eccmask[i];
 
 	return 0;
 }
@@ -65,16 +49,16 @@ EXPORT_SYMBOL(nand_ecc_sw_bch_calculate);
 int nand_ecc_sw_bch_correct(struct nand_device *nand, unsigned char *buf,
 			    unsigned char *read_ecc, unsigned char *calc_ecc)
 {
-	struct nand_chip *chip = mtd_to_nand(nanddev_to_mtd(nand));
-	struct nand_bch_control *nbc = chip->ecc.priv;
-	unsigned int *errloc = nbc->errloc;
+	struct nand_ecc_sw_bch_conf *engine_conf = nand->ecc.ctx.priv;
+	unsigned int step_size = nand->ecc.ctx.conf.step_size;
+	unsigned int *errloc = engine_conf->errloc;
 	int i, count;
 
-	count = bch_decode(nbc->bch, NULL, chip->ecc.size, read_ecc, calc_ecc,
-			   NULL, errloc);
+	count = bch_decode(engine_conf->bch, NULL, step_size, read_ecc,
+			   calc_ecc, NULL, errloc);
 	if (count > 0) {
 		for (i = 0; i < count; i++) {
-			if (errloc[i] < (chip->ecc.size * 8))
+			if (errloc[i] < (step_size * 8))
 				/* The error is in the data area: correct it */
 				buf[errloc[i] >> 3] ^= (1 << (errloc[i] & 7));
 
@@ -97,31 +81,30 @@ EXPORT_SYMBOL(nand_ecc_sw_bch_correct);
  *
  * Returns: a pointer to a new NAND BCH control structure, or NULL upon failure
  *
- * Initialize NAND BCH error correction. Parameters @eccsize and @eccbytes
- * are used to compute the following BCH parameters:
+ * Initialize NAND BCH error correction. @nand.ecc parameters 'step_size' and
+ * 'bytes' are used to compute the following BCH parameters:
  *     m, the Galois field order
  *     t, the error correction capability
- * @eccbytes should be equal to the number of bytes required to store m * t
+ * 'bytes' should be equal to the number of bytes required to store m * t
  * bits, where m is such that 2^m - 1 > step_size * 8.
  *
  * Example: to configure 4 bit correction per 512 bytes, you should pass
- * @eccsize = 512 (thus, m = 13 is the smallest integer such that 2^m - 1 > 512 * 8)
- * @eccbytes = 7 (7 bytes are required to store m * t = 13 * 4 = 52 bits)
+ * step_size = 512 (thus, m = 13 is the smallest integer such that 2^m - 1 > 512 * 8)
+ * bytes = 7 (7 bytes are required to store m * t = 13 * 4 = 52 bits)
  */
 int nand_ecc_sw_bch_init(struct nand_device *nand)
 {
 	struct mtd_info *mtd = nanddev_to_mtd(nand);
-	struct nand_chip *chip = mtd_to_nand(mtd);
 	unsigned int m, t, eccsteps, i;
-	struct nand_bch_control *nbc = NULL;
+	struct nand_ecc_sw_bch_conf *engine_conf = nand->ecc.ctx.priv;
 	unsigned char *erased_page;
-	unsigned int eccsize = chip->ecc.size;
-	unsigned int eccbytes = chip->ecc.bytes;
-	unsigned int eccstrength = chip->ecc.strength;
+	unsigned int eccsize = nand->ecc.ctx.conf.step_size;
+	unsigned int eccbytes = engine_conf->code_size;
+	unsigned int eccstrength = nand->ecc.ctx.conf.strength;
 
 	if (!eccbytes && eccstrength) {
 		eccbytes = DIV_ROUND_UP(eccstrength * fls(8 * eccsize), 8);
-		chip->ecc.bytes = eccbytes;
+		engine_conf->code_size = eccbytes;
 	}
 
 	if (!eccsize || !eccbytes) {
@@ -132,20 +115,14 @@ int nand_ecc_sw_bch_init(struct nand_device *nand)
 	m = fls(1+8*eccsize);
 	t = (eccbytes*8)/m;
 
-	nbc = kzalloc(sizeof(*nbc), GFP_KERNEL);
-	if (!nbc)
-		return -ENOMEM;
-
-	chip->ecc.priv = nbc;
-
-	nbc->bch = bch_init(m, t, 0, false);
-	if (!nbc->bch)
-		goto fail;
+	engine_conf->bch = bch_init(m, t, 0, false);
+	if (!engine_conf->bch)
+		return -EINVAL;
 
 	/* verify that eccbytes has the expected value */
-	if (nbc->bch->ecc_bytes != eccbytes) {
+	if (engine_conf->bch->ecc_bytes != eccbytes) {
 		pr_warn("invalid eccbytes %u, should be %u\n",
-			eccbytes, nbc->bch->ecc_bytes);
+			eccbytes, engine_conf->bch->ecc_bytes);
 		goto fail;
 	}
 
@@ -163,25 +140,15 @@ int nand_ecc_sw_bch_init(struct nand_device *nand)
 		goto fail;
 	}
 
-	/*
-	 * ecc->steps and ecc->total might be used by mtd->ooblayout->ecc(),
-	 * which is called by mtd_ooblayout_count_eccbytes().
-	 * Make sure they are properly initialized before calling
-	 * mtd_ooblayout_count_eccbytes().
-	 * FIXME: we should probably rework the sequencing in nand_scan_tail()
-	 * to avoid setting those fields twice.
-	 */
-	chip->ecc.steps = eccsteps;
-	chip->ecc.total = eccsteps * eccbytes;
-	nand->base.ecc.ctx.total = chip->ecc.total;
 	if (mtd_ooblayout_count_eccbytes(mtd) != (eccsteps*eccbytes)) {
 		pr_warn("invalid ecc layout\n");
 		goto fail;
 	}
 
-	nbc->eccmask = kzalloc(eccbytes, GFP_KERNEL);
-	nbc->errloc = kmalloc_array(t, sizeof(*nbc->errloc), GFP_KERNEL);
-	if (!nbc->eccmask || !nbc->errloc)
+	engine_conf->eccmask = kzalloc(eccbytes, GFP_KERNEL);
+	engine_conf->errloc = kmalloc_array(t, sizeof(*engine_conf->errloc),
+					    GFP_KERNEL);
+	if (!engine_conf->eccmask || !engine_conf->errloc)
 		goto fail;
 
 	/*
@@ -192,14 +159,15 @@ int nand_ecc_sw_bch_init(struct nand_device *nand)
 		goto fail;
 
 	memset(erased_page, 0xff, eccsize);
-	bch_encode(nbc->bch, erased_page, eccsize, nbc->eccmask);
+	bch_encode(engine_conf->bch, erased_page, eccsize,
+		   engine_conf->eccmask);
 	kfree(erased_page);
 
 	for (i = 0; i < eccbytes; i++)
-		nbc->eccmask[i] ^= 0xff;
+		engine_conf->eccmask[i] ^= 0xff;
 
 	if (!eccstrength)
-		chip->ecc.strength = (eccbytes * 8) / fls(8 * eccsize);
+		nand->ecc.ctx.conf.strength = (eccbytes * 8) / fls(8 * eccsize);
 
 	return 0;
 
@@ -216,14 +184,12 @@ EXPORT_SYMBOL(nand_ecc_sw_bch_init);
  */
 void nand_ecc_sw_bch_cleanup(struct nand_device *nand)
 {
-	struct nand_chip *chip = mtd_to_nand(nanddev_to_mtd(nand));
-	struct nand_bch_control *nbc = chip->ecc.priv;
-
-	if (nbc) {
-		bch_free(nbc->bch);
-		kfree(nbc->errloc);
-		kfree(nbc->eccmask);
-		kfree(nbc);
+	struct nand_ecc_sw_bch_conf *engine_conf = nand->ecc.ctx.priv;
+
+	if (engine_conf) {
+		bch_free(engine_conf->bch);
+		kfree(engine_conf->errloc);
+		kfree(engine_conf->eccmask);
 	}
 }
 EXPORT_SYMBOL(nand_ecc_sw_bch_cleanup);
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 2ef674c10ac8..03106bf629dd 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -5142,8 +5142,33 @@ static void nand_scan_ident_cleanup(struct nand_chip *chip)
 int rawnand_sw_bch_init(struct nand_chip *chip)
 {
 	struct nand_device *base = &chip->base;
+	struct nand_ecc_sw_bch_conf *engine_conf;
+	int ret;
+
+	base->ecc.user_conf.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
+	base->ecc.user_conf.algo = NAND_ECC_ALGO_BCH;
+	base->ecc.user_conf.step_size = chip->ecc.size;
+	base->ecc.user_conf.strength = chip->ecc.strength;
+
+	engine_conf = kzalloc(sizeof(*engine_conf), GFP_KERNEL);
+	if (!engine_conf)
+		return -ENOMEM;
+
+	engine_conf->code_size = chip->ecc.bytes;
+
+	base->ecc.ctx.priv = engine_conf;
 
-	return nand_ecc_sw_bch_init(base);
+	ret = nand_ecc_sw_bch_init(base);
+	if (ret)
+		kfree(base->ecc.ctx.priv);
+
+	chip->ecc.size = base->ecc.ctx.conf.step_size;
+	chip->ecc.strength = base->ecc.ctx.conf.strength;
+	chip->ecc.total = base->ecc.ctx.total;
+	chip->ecc.steps = engine_conf->nsteps;
+	chip->ecc.bytes = engine_conf->code_size;
+
+	return ret;
 }
 EXPORT_SYMBOL(rawnand_sw_bch_init);
 
@@ -5171,7 +5196,7 @@ void rawnand_sw_bch_cleanup(struct nand_chip *chip)
 
 	nand_ecc_sw_bch_cleanup(base);
 
-	chip->ecc.priv = NULL;
+	kfree(base->ecc.ctx.priv);
 }
 EXPORT_SYMBOL(rawnand_sw_bch_cleanup);
 
@@ -5794,15 +5819,18 @@ static int nand_scan_tail(struct nand_chip *chip)
 	 * Set the number of read / write steps for one page depending on ECC
 	 * mode.
 	 */
-	ecc->steps = mtd->writesize / ecc->size;
+	if (!ecc->steps)
+		ecc->steps = mtd->writesize / ecc->size;
 	if (ecc->steps * ecc->size != mtd->writesize) {
 		WARN(1, "Invalid ECC parameters\n");
 		ret = -EINVAL;
 		goto err_nand_manuf_cleanup;
 	}
 
-	ecc->total = ecc->steps * ecc->bytes;
-	chip->base.ecc.ctx.total = ecc->total;
+	if (!ecc->total) {
+		ecc->total = ecc->steps * ecc->bytes;
+		chip->base.ecc.ctx.total = ecc->total;
+	}
 
 	if (ecc->total > mtd->oobsize) {
 		WARN(1, "Total number of ECC bytes exceeded oobsize\n");
diff --git a/include/linux/mtd/nand-ecc-sw-bch.h b/include/linux/mtd/nand-ecc-sw-bch.h
index f0caee3b03d0..ce005528e55f 100644
--- a/include/linux/mtd/nand-ecc-sw-bch.h
+++ b/include/linux/mtd/nand-ecc-sw-bch.h
@@ -9,6 +9,31 @@
 #define __MTD_NAND_ECC_SW_BCH_H__
 
 #include <linux/mtd/nand.h>
+#include <linux/bch.h>
+
+/**
+ * struct nand_ecc_sw_bch_conf - private software BCH ECC engine structure
+ * @reqooblen: Save the actual user OOB length requested before overwriting it
+ * @spare_oobbuf: Spare OOB buffer if none is provided
+ * @code_size: Number of bytes needed to store a code (one code per step)
+ * @nsteps: Number of steps
+ * @calc_buf: Buffer to use when calculating ECC bytes
+ * @code_buf: Buffer to use when reading (raw) ECC bytes from the chip
+ * @bch: BCH control structure
+ * @errloc: error location array
+ * @eccmask: XOR ecc mask, allows erased pages to be decoded as valid
+ */
+struct nand_ecc_sw_bch_conf {
+	unsigned int reqooblen;
+	void *spare_oobbuf;
+	unsigned int code_size;
+	unsigned int nsteps;
+	u8 *calc_buf;
+	u8 *code_buf;
+	struct bch_control *bch;
+	unsigned int *errloc;
+	unsigned char *eccmask;
+};
 
 #if IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_BCH)
 
-- 
cgit v1.2.3


From 57e3cebd022fbc035dcf190ac789fd2ffc747f5b Mon Sep 17 00:00:00 2001
From: Shenming Lu <lushenming@huawei.com>
Date: Sat, 28 Nov 2020 22:18:57 +0800
Subject: KVM: arm64: Delay the polling of the GICR_VPENDBASER.Dirty bit

In order to reduce the impact of the VPT parsing happening on the GIC,
we can split the vcpu reseidency in two phases:

- programming GICR_VPENDBASER: this still happens in vcpu_load()
- checking for the VPT parsing to be complete: this can happen
  on vcpu entry (in kvm_vgic_flush_hwstate())

This allows the GIC and the CPU to work in parallel, rewmoving some
of the entry overhead.

Suggested-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Shenming Lu <lushenming@huawei.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20201128141857.983-3-lushenming@huawei.com
---
 arch/arm64/kvm/vgic/vgic-v4.c      | 12 ++++++++++++
 arch/arm64/kvm/vgic/vgic.c         |  3 +++
 drivers/irqchip/irq-gic-v3-its.c   | 12 ++++++++----
 drivers/irqchip/irq-gic-v4.c       | 19 +++++++++++++++++++
 include/kvm/arm_vgic.h             |  1 +
 include/linux/irqchip/arm-gic-v4.h |  4 ++++
 6 files changed, 47 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c
index b5fa73c9fd35..66508b03094f 100644
--- a/arch/arm64/kvm/vgic/vgic-v4.c
+++ b/arch/arm64/kvm/vgic/vgic-v4.c
@@ -353,6 +353,18 @@ int vgic_v4_load(struct kvm_vcpu *vcpu)
 	return err;
 }
 
+void vgic_v4_commit(struct kvm_vcpu *vcpu)
+{
+	struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe;
+
+	/*
+	 * No need to wait for the vPE to be ready across a shallow guest
+	 * exit, as only a vcpu_put will invalidate it.
+	 */
+	if (!vpe->ready)
+		its_commit_vpe(vpe);
+}
+
 static struct vgic_its *vgic_get_its(struct kvm *kvm,
 				     struct kvm_kernel_irq_routing_entry *irq_entry)
 {
diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c
index c3643b7f101b..1c597c9885fa 100644
--- a/arch/arm64/kvm/vgic/vgic.c
+++ b/arch/arm64/kvm/vgic/vgic.c
@@ -915,6 +915,9 @@ void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
 
 	if (can_access_vgic_from_kernel())
 		vgic_restore_state(vcpu);
+
+	if (vgic_supports_direct_msis(vcpu->kvm))
+		vgic_v4_commit(vcpu);
 }
 
 void kvm_vgic_load(struct kvm_vcpu *vcpu)
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 0fec31931e11..7db602434ac5 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -3842,8 +3842,6 @@ static void its_vpe_schedule(struct its_vpe *vpe)
 	val |= vpe->idai ? GICR_VPENDBASER_IDAI : 0;
 	val |= GICR_VPENDBASER_Valid;
 	gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER);
-
-	its_wait_vpt_parse_complete();
 }
 
 static void its_vpe_deschedule(struct its_vpe *vpe)
@@ -3891,6 +3889,10 @@ static int its_vpe_set_vcpu_affinity(struct irq_data *d, void *vcpu_info)
 		its_vpe_deschedule(vpe);
 		return 0;
 
+	case COMMIT_VPE:
+		its_wait_vpt_parse_complete();
+		return 0;
+
 	case INVALL_VPE:
 		its_vpe_invall(vpe);
 		return 0;
@@ -4052,8 +4054,6 @@ static void its_vpe_4_1_schedule(struct its_vpe *vpe,
 	val |= FIELD_PREP(GICR_VPENDBASER_4_1_VPEID, vpe->vpe_id);
 
 	gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER);
-
-	its_wait_vpt_parse_complete();
 }
 
 static void its_vpe_4_1_deschedule(struct its_vpe *vpe,
@@ -4128,6 +4128,10 @@ static int its_vpe_4_1_set_vcpu_affinity(struct irq_data *d, void *vcpu_info)
 		its_vpe_4_1_deschedule(vpe, info);
 		return 0;
 
+	case COMMIT_VPE:
+		its_wait_vpt_parse_complete();
+		return 0;
+
 	case INVALL_VPE:
 		its_vpe_4_1_invall(vpe);
 		return 0;
diff --git a/drivers/irqchip/irq-gic-v4.c b/drivers/irqchip/irq-gic-v4.c
index 0c18714ae13e..5d1dc9915272 100644
--- a/drivers/irqchip/irq-gic-v4.c
+++ b/drivers/irqchip/irq-gic-v4.c
@@ -232,6 +232,8 @@ int its_make_vpe_non_resident(struct its_vpe *vpe, bool db)
 	if (!ret)
 		vpe->resident = false;
 
+	vpe->ready = false;
+
 	return ret;
 }
 
@@ -258,6 +260,23 @@ int its_make_vpe_resident(struct its_vpe *vpe, bool g0en, bool g1en)
 	return ret;
 }
 
+int its_commit_vpe(struct its_vpe *vpe)
+{
+	struct its_cmd_info info = {
+		.cmd_type = COMMIT_VPE,
+	};
+	int ret;
+
+	WARN_ON(preemptible());
+
+	ret = its_send_vpe_cmd(vpe, &info);
+	if (!ret)
+		vpe->ready = true;
+
+	return ret;
+}
+
+
 int its_invall_vpe(struct its_vpe *vpe)
 {
 	struct its_cmd_info info = {
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index a8d8fdcd3723..3d74f1060bd1 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -402,6 +402,7 @@ int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int irq,
 				 struct kvm_kernel_irq_routing_entry *irq_entry);
 
 int vgic_v4_load(struct kvm_vcpu *vcpu);
+void vgic_v4_commit(struct kvm_vcpu *vcpu);
 int vgic_v4_put(struct kvm_vcpu *vcpu, bool need_db);
 
 #endif /* __KVM_ARM_VGIC_H */
diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h
index 6976b8331b60..943c3411ca10 100644
--- a/include/linux/irqchip/arm-gic-v4.h
+++ b/include/linux/irqchip/arm-gic-v4.h
@@ -39,6 +39,8 @@ struct its_vpe {
 	irq_hw_number_t		vpe_db_lpi;
 	/* VPE resident */
 	bool			resident;
+	/* VPT parse complete */
+	bool			ready;
 	union {
 		/* GICv4.0 implementations */
 		struct {
@@ -104,6 +106,7 @@ enum its_vcpu_info_cmd_type {
 	PROP_UPDATE_AND_INV_VLPI,
 	SCHEDULE_VPE,
 	DESCHEDULE_VPE,
+	COMMIT_VPE,
 	INVALL_VPE,
 	PROP_UPDATE_VSGI,
 };
@@ -129,6 +132,7 @@ int its_alloc_vcpu_irqs(struct its_vm *vm);
 void its_free_vcpu_irqs(struct its_vm *vm);
 int its_make_vpe_resident(struct its_vpe *vpe, bool g0en, bool g1en);
 int its_make_vpe_non_resident(struct its_vpe *vpe, bool db);
+int its_commit_vpe(struct its_vpe *vpe);
 int its_invall_vpe(struct its_vpe *vpe);
 int its_map_vlpi(int irq, struct its_vlpi_map *map);
 int its_get_vlpi(int irq, struct its_vlpi_map *map);
-- 
cgit v1.2.3


From bb4c6910c8b41623104c2e64a30615682689a54d Mon Sep 17 00:00:00 2001
From: Laurent Vivier <lvivier@redhat.com>
Date: Thu, 26 Nov 2020 09:28:51 +0100
Subject: genirq/irqdomain: Add an irq_create_mapping_affinity() function

There is currently no way to convey the affinity of an interrupt
via irq_create_mapping(), which creates issues for devices that
expect that affinity to be managed by the kernel.

In order to sort this out, rename irq_create_mapping() to
irq_create_mapping_affinity() with an additional affinity parameter that
can be passed down to irq_domain_alloc_descs().

irq_create_mapping() is re-implemented as a wrapper around
irq_create_mapping_affinity().

No functional change.

Fixes: e75eafb9b039 ("genirq/msi: Switch to new irq spreading infrastructure")
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Greg Kurz <groug@kaod.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20201126082852.1178497-2-lvivier@redhat.com
---
 include/linux/irqdomain.h | 12 ++++++++++--
 kernel/irq/irqdomain.c    | 13 ++++++++-----
 2 files changed, 18 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index 71535e87109f..ea5a337e0f8b 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -384,11 +384,19 @@ extern void irq_domain_associate_many(struct irq_domain *domain,
 extern void irq_domain_disassociate(struct irq_domain *domain,
 				    unsigned int irq);
 
-extern unsigned int irq_create_mapping(struct irq_domain *host,
-				       irq_hw_number_t hwirq);
+extern unsigned int irq_create_mapping_affinity(struct irq_domain *host,
+				      irq_hw_number_t hwirq,
+				      const struct irq_affinity_desc *affinity);
 extern unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec);
 extern void irq_dispose_mapping(unsigned int virq);
 
+static inline unsigned int irq_create_mapping(struct irq_domain *host,
+					      irq_hw_number_t hwirq)
+{
+	return irq_create_mapping_affinity(host, hwirq, NULL);
+}
+
+
 /**
  * irq_linear_revmap() - Find a linux irq from a hw irq number.
  * @domain: domain owning this hardware interrupt
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index cf8b374b892d..e4ca69608f3b 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -624,17 +624,19 @@ unsigned int irq_create_direct_mapping(struct irq_domain *domain)
 EXPORT_SYMBOL_GPL(irq_create_direct_mapping);
 
 /**
- * irq_create_mapping() - Map a hardware interrupt into linux irq space
+ * irq_create_mapping_affinity() - Map a hardware interrupt into linux irq space
  * @domain: domain owning this hardware interrupt or NULL for default domain
  * @hwirq: hardware irq number in that domain space
+ * @affinity: irq affinity
  *
  * Only one mapping per hardware interrupt is permitted. Returns a linux
  * irq number.
  * If the sense/trigger is to be specified, set_irq_type() should be called
  * on the number returned from that call.
  */
-unsigned int irq_create_mapping(struct irq_domain *domain,
-				irq_hw_number_t hwirq)
+unsigned int irq_create_mapping_affinity(struct irq_domain *domain,
+				       irq_hw_number_t hwirq,
+				       const struct irq_affinity_desc *affinity)
 {
 	struct device_node *of_node;
 	int virq;
@@ -660,7 +662,8 @@ unsigned int irq_create_mapping(struct irq_domain *domain,
 	}
 
 	/* Allocate a virtual interrupt number */
-	virq = irq_domain_alloc_descs(-1, 1, hwirq, of_node_to_nid(of_node), NULL);
+	virq = irq_domain_alloc_descs(-1, 1, hwirq, of_node_to_nid(of_node),
+				      affinity);
 	if (virq <= 0) {
 		pr_debug("-> virq allocation failed\n");
 		return 0;
@@ -676,7 +679,7 @@ unsigned int irq_create_mapping(struct irq_domain *domain,
 
 	return virq;
 }
-EXPORT_SYMBOL_GPL(irq_create_mapping);
+EXPORT_SYMBOL_GPL(irq_create_mapping_affinity);
 
 /**
  * irq_create_strict_mappings() - Map a range of hw irqs to fixed linux irqs
-- 
cgit v1.2.3


From 63e2fffa59a9dd91e443b08832656399fd80b7f0 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Sun, 15 Nov 2020 17:37:37 -0500
Subject: pNFS/flexfiles: Fix array overflow when flexfiles mirroring is
 enabled

If the flexfiles mirroring is enabled, then the read code expects to be
able to set pgio->pg_mirror_idx to point to the data server that is
being used for this particular read. However it does not change the
pg_mirror_count because we only need to send a single read.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/flexfilelayout/flexfilelayout.c | 27 +++++++++++++++++++------
 fs/nfs/pagelist.c                      | 36 +++++++++++++++++++++++++---------
 include/linux/nfs_page.h               |  4 ++++
 3 files changed, 52 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index a163533446fa..24bf5797f88a 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -838,7 +838,7 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio,
 	struct nfs_pgio_mirror *pgm;
 	struct nfs4_ff_layout_mirror *mirror;
 	struct nfs4_pnfs_ds *ds;
-	u32 ds_idx, i;
+	u32 ds_idx;
 
 retry:
 	ff_layout_pg_check_layout(pgio, req);
@@ -864,11 +864,9 @@ retry:
 		goto retry;
 	}
 
-	for (i = 0; i < pgio->pg_mirror_count; i++) {
-		mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i);
-		pgm = &pgio->pg_mirrors[i];
-		pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].rsize;
-	}
+	mirror = FF_LAYOUT_COMP(pgio->pg_lseg, ds_idx);
+	pgm = &pgio->pg_mirrors[0];
+	pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].rsize;
 
 	pgio->pg_mirror_idx = ds_idx;
 
@@ -985,6 +983,21 @@ out:
 	return 1;
 }
 
+static u32
+ff_layout_pg_set_mirror_write(struct nfs_pageio_descriptor *desc, u32 idx)
+{
+	u32 old = desc->pg_mirror_idx;
+
+	desc->pg_mirror_idx = idx;
+	return old;
+}
+
+static struct nfs_pgio_mirror *
+ff_layout_pg_get_mirror_write(struct nfs_pageio_descriptor *desc, u32 idx)
+{
+	return &desc->pg_mirrors[idx];
+}
+
 static const struct nfs_pageio_ops ff_layout_pg_read_ops = {
 	.pg_init = ff_layout_pg_init_read,
 	.pg_test = pnfs_generic_pg_test,
@@ -998,6 +1011,8 @@ static const struct nfs_pageio_ops ff_layout_pg_write_ops = {
 	.pg_doio = pnfs_generic_pg_writepages,
 	.pg_get_mirror_count = ff_layout_pg_get_mirror_count_write,
 	.pg_cleanup = pnfs_generic_pg_cleanup,
+	.pg_get_mirror = ff_layout_pg_get_mirror_write,
+	.pg_set_mirror = ff_layout_pg_set_mirror_write,
 };
 
 static void ff_layout_reset_write(struct nfs_pgio_header *hdr, bool retry_pnfs)
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 6985cacf4700..78c9c4bdef2b 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -31,13 +31,29 @@
 static struct kmem_cache *nfs_page_cachep;
 static const struct rpc_call_ops nfs_pgio_common_ops;
 
+static struct nfs_pgio_mirror *
+nfs_pgio_get_mirror(struct nfs_pageio_descriptor *desc, u32 idx)
+{
+	if (desc->pg_ops->pg_get_mirror)
+		return desc->pg_ops->pg_get_mirror(desc, idx);
+	return &desc->pg_mirrors[0];
+}
+
 struct nfs_pgio_mirror *
 nfs_pgio_current_mirror(struct nfs_pageio_descriptor *desc)
 {
-	return &desc->pg_mirrors[desc->pg_mirror_idx];
+	return nfs_pgio_get_mirror(desc, desc->pg_mirror_idx);
 }
 EXPORT_SYMBOL_GPL(nfs_pgio_current_mirror);
 
+static u32
+nfs_pgio_set_current_mirror(struct nfs_pageio_descriptor *desc, u32 idx)
+{
+	if (desc->pg_ops->pg_set_mirror)
+		return desc->pg_ops->pg_set_mirror(desc, idx);
+	return desc->pg_mirror_idx;
+}
+
 void nfs_pgheader_init(struct nfs_pageio_descriptor *desc,
 		       struct nfs_pgio_header *hdr,
 		       void (*release)(struct nfs_pgio_header *hdr))
@@ -1259,7 +1275,7 @@ static void nfs_pageio_error_cleanup(struct nfs_pageio_descriptor *desc)
 		return;
 
 	for (midx = 0; midx < desc->pg_mirror_count; midx++) {
-		mirror = &desc->pg_mirrors[midx];
+		mirror = nfs_pgio_get_mirror(desc, midx);
 		desc->pg_completion_ops->error_cleanup(&mirror->pg_list,
 				desc->pg_error);
 	}
@@ -1293,12 +1309,12 @@ int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
 			goto out_failed;
 		}
 
-		desc->pg_mirror_idx = midx;
+		nfs_pgio_set_current_mirror(desc, midx);
 		if (!nfs_pageio_add_request_mirror(desc, dupreq))
 			goto out_cleanup_subreq;
 	}
 
-	desc->pg_mirror_idx = 0;
+	nfs_pgio_set_current_mirror(desc, 0);
 	if (!nfs_pageio_add_request_mirror(desc, req))
 		goto out_failed;
 
@@ -1320,10 +1336,12 @@ out_failed:
 static void nfs_pageio_complete_mirror(struct nfs_pageio_descriptor *desc,
 				       u32 mirror_idx)
 {
-	struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[mirror_idx];
-	u32 restore_idx = desc->pg_mirror_idx;
+	struct nfs_pgio_mirror *mirror;
+	u32 restore_idx;
+
+	restore_idx = nfs_pgio_set_current_mirror(desc, mirror_idx);
+	mirror = nfs_pgio_current_mirror(desc);
 
-	desc->pg_mirror_idx = mirror_idx;
 	for (;;) {
 		nfs_pageio_doio(desc);
 		if (desc->pg_error < 0 || !mirror->pg_recoalesce)
@@ -1331,7 +1349,7 @@ static void nfs_pageio_complete_mirror(struct nfs_pageio_descriptor *desc,
 		if (!nfs_do_recoalesce(desc))
 			break;
 	}
-	desc->pg_mirror_idx = restore_idx;
+	nfs_pgio_set_current_mirror(desc, restore_idx);
 }
 
 /*
@@ -1405,7 +1423,7 @@ void nfs_pageio_cond_complete(struct nfs_pageio_descriptor *desc, pgoff_t index)
 	u32 midx;
 
 	for (midx = 0; midx < desc->pg_mirror_count; midx++) {
-		mirror = &desc->pg_mirrors[midx];
+		mirror = nfs_pgio_get_mirror(desc, midx);
 		if (!list_empty(&mirror->pg_list)) {
 			prev = nfs_list_entry(mirror->pg_list.prev);
 			if (index != prev->wb_index + 1) {
diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h
index c32c15216da3..f0373a6cb5fb 100644
--- a/include/linux/nfs_page.h
+++ b/include/linux/nfs_page.h
@@ -55,6 +55,7 @@ struct nfs_page {
 	unsigned short		wb_nio;		/* Number of I/O attempts */
 };
 
+struct nfs_pgio_mirror;
 struct nfs_pageio_descriptor;
 struct nfs_pageio_ops {
 	void	(*pg_init)(struct nfs_pageio_descriptor *, struct nfs_page *);
@@ -64,6 +65,9 @@ struct nfs_pageio_ops {
 	unsigned int	(*pg_get_mirror_count)(struct nfs_pageio_descriptor *,
 				       struct nfs_page *);
 	void	(*pg_cleanup)(struct nfs_pageio_descriptor *);
+	struct nfs_pgio_mirror *
+		(*pg_get_mirror)(struct nfs_pageio_descriptor *, u32);
+	u32	(*pg_set_mirror)(struct nfs_pageio_descriptor *, u32);
 };
 
 struct nfs_rw_ops {
-- 
cgit v1.2.3


From 5a7e702670adc368caa1b64c2138956d8cba0d4f Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 13 Mar 2020 10:42:09 -0400
Subject: SUNRPC: Adjust synopsis of xdr_buf_subsegment()

Clean up: This enables xdr_buf_subsegment()'s callers to pass in a
const pointer to that buffer.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/xdr.h | 3 ++-
 net/sunrpc/xdr.c           | 5 ++---
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 9548d075e06d..ec2a22ccdc2a 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -183,7 +183,8 @@ xdr_adjust_iovec(struct kvec *iov, __be32 *p)
  */
 extern void xdr_shift_buf(struct xdr_buf *, size_t);
 extern void xdr_buf_from_iov(struct kvec *, struct xdr_buf *);
-extern int xdr_buf_subsegment(struct xdr_buf *, struct xdr_buf *, unsigned int, unsigned int);
+extern int xdr_buf_subsegment(const struct xdr_buf *buf, struct xdr_buf *subbuf,
+			      unsigned int base, unsigned int len);
 extern void xdr_buf_trim(struct xdr_buf *, unsigned int);
 extern int read_bytes_from_xdr_buf(struct xdr_buf *, unsigned int, void *, unsigned int);
 extern int write_bytes_to_xdr_buf(struct xdr_buf *, unsigned int, void *, unsigned int);
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 71e03b930b70..28f81769a27c 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -1379,9 +1379,8 @@ EXPORT_SYMBOL_GPL(xdr_buf_from_iov);
  *
  * Returns -1 if base of length are out of bounds.
  */
-int
-xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf,
-			unsigned int base, unsigned int len)
+int xdr_buf_subsegment(const struct xdr_buf *buf, struct xdr_buf *subbuf,
+		       unsigned int base, unsigned int len)
 {
 	subbuf->buflen = subbuf->len = len;
 	if (base < buf->head[0].iov_len) {
-- 
cgit v1.2.3


From 03493bca084fdca48abc59b00e06ce733aa9eb7d Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 10 Jun 2020 10:36:42 -0400
Subject: SUNRPC: Rename svc_encode_read_payload()

Clean up: "result payload" is a less confusing name for these
payloads. "READ payload" reflects only the NFS usage.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4xdr.c                        |  2 +-
 include/linux/sunrpc/svc.h               |  6 +++---
 include/linux/sunrpc/svc_rdma.h          |  4 ++--
 include/linux/sunrpc/svc_xprt.h          |  4 ++--
 net/sunrpc/svc.c                         | 11 ++++++-----
 net/sunrpc/svcsock.c                     |  8 ++++----
 net/sunrpc/xprtrdma/svc_rdma_sendto.c    |  8 ++++----
 net/sunrpc/xprtrdma/svc_rdma_transport.c |  2 +-
 8 files changed, 23 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 833a2c64dfe8..7e24fb3ca36e 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -3829,7 +3829,7 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp,
 	read->rd_length = maxcount;
 	if (nfserr)
 		return nfserr;
-	if (svc_encode_read_payload(resp->rqstp, starting_len + 8, maxcount))
+	if (svc_encode_result_payload(resp->rqstp, starting_len + 8, maxcount))
 		return nfserr_io;
 	xdr_truncate_encode(xdr, starting_len + 8 + xdr_align_size(maxcount));
 
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 386628b36bc7..c220b734fa69 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -519,9 +519,9 @@ void		   svc_wake_up(struct svc_serv *);
 void		   svc_reserve(struct svc_rqst *rqstp, int space);
 struct svc_pool *  svc_pool_for_cpu(struct svc_serv *serv, int cpu);
 char *		   svc_print_addr(struct svc_rqst *, char *, size_t);
-int		   svc_encode_read_payload(struct svc_rqst *rqstp,
-					   unsigned int offset,
-					   unsigned int length);
+int		   svc_encode_result_payload(struct svc_rqst *rqstp,
+					     unsigned int offset,
+					     unsigned int length);
 unsigned int	   svc_fill_write_vector(struct svc_rqst *rqstp,
 					 struct page **pages,
 					 struct kvec *first, size_t total);
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 9dc3a3b88391..2b870a3f391b 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -207,8 +207,8 @@ extern void svc_rdma_send_error_msg(struct svcxprt_rdma *rdma,
 				    struct svc_rdma_recv_ctxt *rctxt,
 				    int status);
 extern int svc_rdma_sendto(struct svc_rqst *);
-extern int svc_rdma_read_payload(struct svc_rqst *rqstp, unsigned int offset,
-				 unsigned int length);
+extern int svc_rdma_result_payload(struct svc_rqst *rqstp, unsigned int offset,
+				   unsigned int length);
 
 /* svc_rdma_transport.c */
 extern struct svc_xprt_class svc_rdma_class;
diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h
index aca35ab5cff2..92455e0d5244 100644
--- a/include/linux/sunrpc/svc_xprt.h
+++ b/include/linux/sunrpc/svc_xprt.h
@@ -21,8 +21,8 @@ struct svc_xprt_ops {
 	int		(*xpo_has_wspace)(struct svc_xprt *);
 	int		(*xpo_recvfrom)(struct svc_rqst *);
 	int		(*xpo_sendto)(struct svc_rqst *);
-	int		(*xpo_read_payload)(struct svc_rqst *, unsigned int,
-					    unsigned int);
+	int		(*xpo_result_payload)(struct svc_rqst *, unsigned int,
+					      unsigned int);
 	void		(*xpo_release_rqst)(struct svc_rqst *);
 	void		(*xpo_detach)(struct svc_xprt *);
 	void		(*xpo_free)(struct svc_xprt *);
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index c211b607239e..b41500645c3f 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1622,7 +1622,7 @@ u32 svc_max_payload(const struct svc_rqst *rqstp)
 EXPORT_SYMBOL_GPL(svc_max_payload);
 
 /**
- * svc_encode_read_payload - mark a range of bytes as a READ payload
+ * svc_encode_result_payload - mark a range of bytes as a result payload
  * @rqstp: svc_rqst to operate on
  * @offset: payload's byte offset in rqstp->rq_res
  * @length: size of payload, in bytes
@@ -1630,12 +1630,13 @@ EXPORT_SYMBOL_GPL(svc_max_payload);
  * Returns zero on success, or a negative errno if a permanent
  * error occurred.
  */
-int svc_encode_read_payload(struct svc_rqst *rqstp, unsigned int offset,
-			    unsigned int length)
+int svc_encode_result_payload(struct svc_rqst *rqstp, unsigned int offset,
+			      unsigned int length)
 {
-	return rqstp->rq_xprt->xpt_ops->xpo_read_payload(rqstp, offset, length);
+	return rqstp->rq_xprt->xpt_ops->xpo_result_payload(rqstp, offset,
+							   length);
 }
-EXPORT_SYMBOL_GPL(svc_encode_read_payload);
+EXPORT_SYMBOL_GPL(svc_encode_result_payload);
 
 /**
  * svc_fill_write_vector - Construct data argument for VFS write call
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index c2752e2b9ce3..b248f2349437 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -181,8 +181,8 @@ static void svc_set_cmsg_data(struct svc_rqst *rqstp, struct cmsghdr *cmh)
 	}
 }
 
-static int svc_sock_read_payload(struct svc_rqst *rqstp, unsigned int offset,
-				 unsigned int length)
+static int svc_sock_result_payload(struct svc_rqst *rqstp, unsigned int offset,
+				   unsigned int length)
 {
 	return 0;
 }
@@ -635,7 +635,7 @@ static const struct svc_xprt_ops svc_udp_ops = {
 	.xpo_create = svc_udp_create,
 	.xpo_recvfrom = svc_udp_recvfrom,
 	.xpo_sendto = svc_udp_sendto,
-	.xpo_read_payload = svc_sock_read_payload,
+	.xpo_result_payload = svc_sock_result_payload,
 	.xpo_release_rqst = svc_udp_release_rqst,
 	.xpo_detach = svc_sock_detach,
 	.xpo_free = svc_sock_free,
@@ -1123,7 +1123,7 @@ static const struct svc_xprt_ops svc_tcp_ops = {
 	.xpo_create = svc_tcp_create,
 	.xpo_recvfrom = svc_tcp_recvfrom,
 	.xpo_sendto = svc_tcp_sendto,
-	.xpo_read_payload = svc_sock_read_payload,
+	.xpo_result_payload = svc_sock_result_payload,
 	.xpo_release_rqst = svc_tcp_release_rqst,
 	.xpo_detach = svc_tcp_sock_detach,
 	.xpo_free = svc_sock_free,
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index c3d588b149aa..c8411b4f3492 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -979,19 +979,19 @@ int svc_rdma_sendto(struct svc_rqst *rqstp)
 }
 
 /**
- * svc_rdma_read_payload - special processing for a READ payload
+ * svc_rdma_result_payload - special processing for a result payload
  * @rqstp: svc_rqst to operate on
  * @offset: payload's byte offset in @xdr
  * @length: size of payload, in bytes
  *
  * Returns zero on success.
  *
- * For the moment, just record the xdr_buf location of the READ
+ * For the moment, just record the xdr_buf location of the result
  * payload. svc_rdma_sendto will use that location later when
  * we actually send the payload.
  */
-int svc_rdma_read_payload(struct svc_rqst *rqstp, unsigned int offset,
-			  unsigned int length)
+int svc_rdma_result_payload(struct svc_rqst *rqstp, unsigned int offset,
+			    unsigned int length)
 {
 	struct svc_rdma_recv_ctxt *rctxt = rqstp->rq_xprt_ctxt;
 
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index fb044792b571..afba4e9d5425 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -80,7 +80,7 @@ static const struct svc_xprt_ops svc_rdma_ops = {
 	.xpo_create = svc_rdma_create,
 	.xpo_recvfrom = svc_rdma_recvfrom,
 	.xpo_sendto = svc_rdma_sendto,
-	.xpo_read_payload = svc_rdma_read_payload,
+	.xpo_result_payload = svc_rdma_result_payload,
 	.xpo_release_rqst = svc_rdma_release_rqst,
 	.xpo_detach = svc_rdma_detach,
 	.xpo_free = svc_rdma_free,
-- 
cgit v1.2.3


From f6ad77590a5d432589a5d8a211c4e8e50cd8bb63 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 13 Mar 2020 10:42:10 -0400
Subject: svcrdma: Post RDMA Writes while XDR encoding replies

The only RPC/RDMA ordering requirement between RDMA Writes and RDMA
Sends is that the responder must post the Writes on the Send queue
before posting the Send that conveys the RPC Reply for that Write
payload.

The Linux NFS server implementation now has a transport method that
can post result Payload Writes earlier than svc_rdma_sendto:

   ->xpo_result_payload()

This gets RDMA Writes going earlier so they are more likely to be
complete at the remote end before the Send completes.

Some care must be taken with pulled-up Replies. We don't want to
push the Write chunk and then send the same payload data via Send.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svc_rdma.h       |  4 +--
 net/sunrpc/xprtrdma/svc_rdma_rw.c     | 52 ++++++++++++++++++++++++------
 net/sunrpc/xprtrdma/svc_rdma_sendto.c | 60 ++++++++++++++++++++---------------
 3 files changed, 77 insertions(+), 39 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 2b870a3f391b..f5a3c852bb90 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -183,9 +183,7 @@ extern int svc_rdma_recv_read_chunk(struct svcxprt_rdma *rdma,
 				    struct svc_rqst *rqstp,
 				    struct svc_rdma_recv_ctxt *head, __be32 *p);
 extern int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma,
-				     __be32 *wr_ch, struct xdr_buf *xdr,
-				     unsigned int offset,
-				     unsigned long length);
+				     __be32 *wr_ch, const struct xdr_buf *xdr);
 extern int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma,
 				     const struct svc_rdma_recv_ctxt *rctxt,
 				     struct xdr_buf *xdr);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c
index a75f8a133bef..f2ed1bf50251 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_rw.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c
@@ -538,13 +538,49 @@ static int svc_rdma_pages_write(struct svc_rdma_write_info *info,
 				     length);
 }
 
+/**
+ * svc_rdma_xb_write - Construct RDMA Writes to write an xdr_buf
+ * @xdr: xdr_buf to write
+ * @info: pointer to write arguments
+ *
+ * Returns:
+ *   On succes, returns zero
+ *   %-E2BIG if the client-provided Write chunk is too small
+ *   %-ENOMEM if a resource has been exhausted
+ *   %-EIO if an rdma-rw error occurred
+ */
+static int svc_rdma_xb_write(const struct xdr_buf *xdr,
+			     struct svc_rdma_write_info *info)
+{
+	int ret;
+
+	if (xdr->head[0].iov_len) {
+		ret = svc_rdma_iov_write(info, &xdr->head[0]);
+		if (ret < 0)
+			return ret;
+	}
+
+	if (xdr->page_len) {
+		ret = svc_rdma_pages_write(info, xdr, xdr->head[0].iov_len,
+					   xdr->page_len);
+		if (ret < 0)
+			return ret;
+	}
+
+	if (xdr->tail[0].iov_len) {
+		ret = svc_rdma_iov_write(info, &xdr->tail[0]);
+		if (ret < 0)
+			return ret;
+	}
+
+	return xdr->len;
+}
+
 /**
  * svc_rdma_send_write_chunk - Write all segments in a Write chunk
  * @rdma: controlling RDMA transport
  * @wr_ch: Write chunk provided by client
  * @xdr: xdr_buf containing the data payload
- * @offset: payload's byte offset in @xdr
- * @length: size of payload, in bytes
  *
  * Returns a non-negative number of bytes the chunk consumed, or
  *	%-E2BIG if the payload was larger than the Write chunk,
@@ -554,21 +590,17 @@ static int svc_rdma_pages_write(struct svc_rdma_write_info *info,
  *	%-EIO if rdma_rw initialization failed (DMA mapping, etc).
  */
 int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma, __be32 *wr_ch,
-			      struct xdr_buf *xdr,
-			      unsigned int offset, unsigned long length)
+			      const struct xdr_buf *xdr)
 {
 	struct svc_rdma_write_info *info;
 	int ret;
 
-	if (!length)
-		return 0;
-
 	info = svc_rdma_write_info_alloc(rdma, wr_ch);
 	if (!info)
 		return -ENOMEM;
 
-	ret = svc_rdma_pages_write(info, xdr, offset, length);
-	if (ret < 0)
+	ret = svc_rdma_xb_write(xdr, info);
+	if (ret != xdr->len)
 		goto out_err;
 
 	ret = svc_rdma_post_chunk_ctxt(&info->wi_cc);
@@ -576,7 +608,7 @@ int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma, __be32 *wr_ch,
 		goto out_err;
 
 	trace_svcrdma_send_write_chunk(xdr->page_len);
-	return length;
+	return xdr->len;
 
 out_err:
 	svc_rdma_write_info_free(info);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index d6436c13d5c4..e8b0d030e1e6 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -468,11 +468,14 @@ svc_rdma_encode_write_list(const struct svc_rdma_recv_ctxt *rctxt,
 {
 	ssize_t len, ret;
 
-	ret = svc_rdma_encode_write_chunk(rctxt->rc_write_list, sctxt,
-					  rctxt->rc_read_payload_length);
-	if (ret < 0)
-		return ret;
-	len = ret;
+	len = 0;
+	if (rctxt->rc_write_list) {
+		ret = svc_rdma_encode_write_chunk(rctxt->rc_write_list, sctxt,
+						  rctxt->rc_read_payload_length);
+		if (ret < 0)
+			return ret;
+		len = ret;
+	}
 
 	/* Terminate the Write list */
 	ret = xdr_stream_encode_item_absent(&sctxt->sc_stream);
@@ -556,11 +559,13 @@ static bool svc_rdma_pull_up_needed(struct svcxprt_rdma *rdma,
 				    const struct svc_rdma_recv_ctxt *rctxt,
 				    struct xdr_buf *xdr)
 {
+	bool write_chunk_present = rctxt && rctxt->rc_write_list;
 	int elements;
 
 	/* For small messages, copying bytes is cheaper than DMA mapping.
 	 */
-	if (sctxt->sc_hdrbuf.len + xdr->len < RPCRDMA_PULLUP_THRESH)
+	if (!write_chunk_present &&
+	    sctxt->sc_hdrbuf.len + xdr->len < RPCRDMA_PULLUP_THRESH)
 		return true;
 
 	/* Check whether the xdr_buf has more elements than can
@@ -893,9 +898,7 @@ int svc_rdma_sendto(struct svc_rqst *rqstp)
 		container_of(xprt, struct svcxprt_rdma, sc_xprt);
 	struct svc_rdma_recv_ctxt *rctxt = rqstp->rq_xprt_ctxt;
 	__be32 *rdma_argp = rctxt->rc_recv_buf;
-	__be32 *wr_lst = rctxt->rc_write_list;
 	__be32 *rp_ch = rctxt->rc_reply_chunk;
-	struct xdr_buf *xdr = &rqstp->rq_res;
 	struct svc_rdma_send_ctxt *sctxt;
 	__be32 *p;
 	int ret;
@@ -920,19 +923,8 @@ int svc_rdma_sendto(struct svc_rqst *rqstp)
 
 	if (svc_rdma_encode_read_list(sctxt) < 0)
 		goto err0;
-	if (wr_lst) {
-		/* XXX: Presume the client sent only one Write chunk */
-		ret = svc_rdma_send_write_chunk(rdma, wr_lst, xdr,
-						rctxt->rc_read_payload_offset,
-						rctxt->rc_read_payload_length);
-		if (ret < 0)
-			goto err2;
-		if (svc_rdma_encode_write_list(rctxt, sctxt) < 0)
-			goto err0;
-	} else {
-		if (xdr_stream_encode_item_absent(&sctxt->sc_stream) < 0)
-			goto err0;
-	}
+	if (svc_rdma_encode_write_list(rctxt, sctxt) < 0)
+		goto err0;
 	if (rp_ch) {
 		ret = svc_rdma_send_reply_chunk(rdma, rctxt, &rqstp->rq_res);
 		if (ret < 0)
@@ -974,16 +966,25 @@ int svc_rdma_sendto(struct svc_rqst *rqstp)
  * @offset: payload's byte offset in @xdr
  * @length: size of payload, in bytes
  *
- * Returns zero on success.
- *
- * For the moment, just record the xdr_buf location of the result
- * payload. svc_rdma_sendto will use that location later when
- * we actually send the payload.
+ * Return values:
+ *   %0 if successful or nothing needed to be done
+ *   %-EMSGSIZE on XDR buffer overflow
+ *   %-E2BIG if the payload was larger than the Write chunk
+ *   %-EINVAL if client provided too many segments
+ *   %-ENOMEM if rdma_rw context pool was exhausted
+ *   %-ENOTCONN if posting failed (connection is lost)
+ *   %-EIO if rdma_rw initialization failed (DMA mapping, etc)
  */
 int svc_rdma_result_payload(struct svc_rqst *rqstp, unsigned int offset,
 			    unsigned int length)
 {
 	struct svc_rdma_recv_ctxt *rctxt = rqstp->rq_xprt_ctxt;
+	struct svcxprt_rdma *rdma;
+	struct xdr_buf subbuf;
+	int ret;
+
+	if (!rctxt->rc_write_list || !length)
+		return 0;
 
 	/* XXX: Just one READ payload slot for now, since our
 	 * transport implementation currently supports only one
@@ -992,5 +993,12 @@ int svc_rdma_result_payload(struct svc_rqst *rqstp, unsigned int offset,
 	rctxt->rc_read_payload_offset = offset;
 	rctxt->rc_read_payload_length = length;
 
+	if (xdr_buf_subsegment(&rqstp->rq_res, &subbuf, offset, length))
+		return -EMSGSIZE;
+
+	rdma = container_of(rqstp->rq_xprt, struct svcxprt_rdma, sc_xprt);
+	ret = svc_rdma_send_write_chunk(rdma, rctxt->rc_write_list, &subbuf);
+	if (ret < 0)
+		return ret;
 	return 0;
 }
-- 
cgit v1.2.3


From 78147ca8b4a9b6cf0e597ddd6bf17959e08376c2 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Mon, 22 Jun 2020 10:15:41 -0400
Subject: svcrdma: Add a "parsed chunk list" data structure

This simple data structure binds the location of each data payload
inside of an RPC message to the chunk that will be used to push it
to or pull it from the client.

There are several benefits to this small additional overhead:

 * It enables support for more than one chunk in incoming Read and
   Write lists.

 * It translates the version-specific on-the-wire format into a
   generic in-memory structure, enabling support for multiple
   versions of the RPC/RDMA transport protocol.

 * It enables the server to re-organize a chunk list if it needs to
   adjust where Read chunk data lands in server memory without
   altering the contents of the XDR-encoded Receive buffer.

Construction of these lists is done while sanity checking each
incoming RPC/RDMA header. Subsequent patches will make use of the
generated data structures.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svc_rdma.h         |  12 ++
 include/linux/sunrpc/svc_rdma_pcl.h     | 128 +++++++++++++
 include/trace/events/rpcrdma.h          |  75 +++++++-
 net/sunrpc/xprtrdma/Makefile            |   2 +-
 net/sunrpc/xprtrdma/svc_rdma_pcl.c      | 306 ++++++++++++++++++++++++++++++++
 net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 196 +++++++++++---------
 6 files changed, 635 insertions(+), 84 deletions(-)
 create mode 100644 include/linux/sunrpc/svc_rdma_pcl.h
 create mode 100644 net/sunrpc/xprtrdma/svc_rdma_pcl.c

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index f5a3c852bb90..a89d4209fe2a 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -47,6 +47,8 @@
 #include <linux/sunrpc/svcsock.h>
 #include <linux/sunrpc/rpc_rdma.h>
 #include <linux/sunrpc/rpc_rdma_cid.h>
+#include <linux/sunrpc/svc_rdma_pcl.h>
+
 #include <rdma/ib_verbs.h>
 #include <rdma/rdma_cm.h>
 
@@ -142,8 +144,18 @@ struct svc_rdma_recv_ctxt {
 	unsigned int		rc_page_count;
 	unsigned int		rc_hdr_count;
 	u32			rc_inv_rkey;
+
+	struct svc_rdma_pcl	rc_call_pcl;
+
+	struct svc_rdma_pcl	rc_read_pcl;
+
 	__be32			*rc_write_list;
+	struct svc_rdma_chunk	*rc_cur_result_payload;
+	struct svc_rdma_pcl	rc_write_pcl;
+
 	__be32			*rc_reply_chunk;
+	struct svc_rdma_pcl	rc_reply_pcl;
+
 	unsigned int		rc_read_payload_offset;
 	unsigned int		rc_read_payload_length;
 	struct page		*rc_pages[RPCSVC_MAXPAGES];
diff --git a/include/linux/sunrpc/svc_rdma_pcl.h b/include/linux/sunrpc/svc_rdma_pcl.h
new file mode 100644
index 000000000000..7516ad0fae80
--- /dev/null
+++ b/include/linux/sunrpc/svc_rdma_pcl.h
@@ -0,0 +1,128 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2020, Oracle and/or its affiliates
+ */
+
+#ifndef SVC_RDMA_PCL_H
+#define SVC_RDMA_PCL_H
+
+#include <linux/list.h>
+
+struct svc_rdma_segment {
+	u32			rs_handle;
+	u32			rs_length;
+	u64			rs_offset;
+};
+
+struct svc_rdma_chunk {
+	struct list_head	ch_list;
+
+	u32			ch_position;
+	u32			ch_length;
+	u32			ch_payload_length;
+
+	u32			ch_segcount;
+	struct svc_rdma_segment	ch_segments[];
+};
+
+struct svc_rdma_pcl {
+	unsigned int		cl_count;
+	struct list_head	cl_chunks;
+};
+
+/**
+ * pcl_init - Initialize a parsed chunk list
+ * @pcl: parsed chunk list to initialize
+ *
+ */
+static inline void pcl_init(struct svc_rdma_pcl *pcl)
+{
+	INIT_LIST_HEAD(&pcl->cl_chunks);
+}
+
+/**
+ * pcl_is_empty - Return true if parsed chunk list is empty
+ * @pcl: parsed chunk list
+ *
+ */
+static inline bool pcl_is_empty(const struct svc_rdma_pcl *pcl)
+{
+	return list_empty(&pcl->cl_chunks);
+}
+
+/**
+ * pcl_first_chunk - Return first chunk in a parsed chunk list
+ * @pcl: parsed chunk list
+ *
+ * Returns the first chunk in the list, or NULL if the list is empty.
+ */
+static inline struct svc_rdma_chunk *
+pcl_first_chunk(const struct svc_rdma_pcl *pcl)
+{
+	if (pcl_is_empty(pcl))
+		return NULL;
+	return list_first_entry(&pcl->cl_chunks, struct svc_rdma_chunk,
+				ch_list);
+}
+
+/**
+ * pcl_next_chunk - Return next chunk in a parsed chunk list
+ * @pcl: a parsed chunk list
+ * @chunk: chunk in @pcl
+ *
+ * Returns the next chunk in the list, or NULL if @chunk is already last.
+ */
+static inline struct svc_rdma_chunk *
+pcl_next_chunk(const struct svc_rdma_pcl *pcl, struct svc_rdma_chunk *chunk)
+{
+	if (list_is_last(&chunk->ch_list, &pcl->cl_chunks))
+		return NULL;
+	return list_next_entry(chunk, ch_list);
+}
+
+/**
+ * pcl_for_each_chunk - Iterate over chunks in a parsed chunk list
+ * @pos: the loop cursor
+ * @pcl: a parsed chunk list
+ */
+#define pcl_for_each_chunk(pos, pcl) \
+	for (pos = list_first_entry(&(pcl)->cl_chunks, struct svc_rdma_chunk, ch_list); \
+	     &pos->ch_list != &(pcl)->cl_chunks; \
+	     pos = list_next_entry(pos, ch_list))
+
+/**
+ * pcl_for_each_segment - Iterate over segments in a parsed chunk
+ * @pos: the loop cursor
+ * @chunk: a parsed chunk
+ */
+#define pcl_for_each_segment(pos, chunk) \
+	for (pos = &(chunk)->ch_segments[0]; \
+	     pos <= &(chunk)->ch_segments[(chunk)->ch_segcount - 1]; \
+	     pos++)
+
+/**
+ * pcl_chunk_end_offset - Return offset of byte range following @chunk
+ * @chunk: chunk in @pcl
+ *
+ * Returns starting offset of the region just after @chunk
+ */
+static inline unsigned int
+pcl_chunk_end_offset(const struct svc_rdma_chunk *chunk)
+{
+	return xdr_align_size(chunk->ch_position + chunk->ch_payload_length);
+}
+
+struct svc_rdma_recv_ctxt;
+
+extern void pcl_free(struct svc_rdma_pcl *pcl);
+extern bool pcl_alloc_call(struct svc_rdma_recv_ctxt *rctxt, __be32 *p);
+extern bool pcl_alloc_read(struct svc_rdma_recv_ctxt *rctxt, __be32 *p);
+extern bool pcl_alloc_write(struct svc_rdma_recv_ctxt *rctxt,
+			    struct svc_rdma_pcl *pcl, __be32 *p);
+extern int pcl_process_nonpayloads(const struct svc_rdma_pcl *pcl,
+				   const struct xdr_buf *xdr,
+				   int (*actor)(const struct xdr_buf *,
+						void *),
+				   void *data);
+
+#endif	/* SVC_RDMA_PCL_H */
diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index bf1065772228..72b941aef43b 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -1446,12 +1446,83 @@ DECLARE_EVENT_CLASS(svcrdma_segment_event,
 				),					\
 				TP_ARGS(handle, length, offset))
 
-DEFINE_SEGMENT_EVENT(decode_wseg);
-DEFINE_SEGMENT_EVENT(encode_rseg);
 DEFINE_SEGMENT_EVENT(send_rseg);
 DEFINE_SEGMENT_EVENT(encode_wseg);
 DEFINE_SEGMENT_EVENT(send_wseg);
 
+TRACE_EVENT(svcrdma_decode_rseg,
+	TP_PROTO(
+		const struct rpc_rdma_cid *cid,
+		const struct svc_rdma_chunk *chunk,
+		const struct svc_rdma_segment *segment
+	),
+
+	TP_ARGS(cid, chunk, segment),
+
+	TP_STRUCT__entry(
+		__field(u32, cq_id)
+		__field(int, completion_id)
+		__field(u32, segno)
+		__field(u32, position)
+		__field(u32, handle)
+		__field(u32, length)
+		__field(u64, offset)
+	),
+
+	TP_fast_assign(
+		__entry->cq_id = cid->ci_queue_id;
+		__entry->completion_id = cid->ci_completion_id;
+		__entry->segno = chunk->ch_segcount;
+		__entry->position = chunk->ch_position;
+		__entry->handle = segment->rs_handle;
+		__entry->length = segment->rs_length;
+		__entry->offset = segment->rs_offset;
+	),
+
+	TP_printk("cq_id=%u cid=%d segno=%u position=%u %u@0x%016llx:0x%08x",
+		__entry->cq_id, __entry->completion_id,
+		__entry->segno, __entry->position, __entry->length,
+		(unsigned long long)__entry->offset, __entry->handle
+	)
+);
+
+TRACE_EVENT(svcrdma_decode_wseg,
+	TP_PROTO(
+		const struct rpc_rdma_cid *cid,
+		const struct svc_rdma_chunk *chunk,
+		u32 segno
+	),
+
+	TP_ARGS(cid, chunk, segno),
+
+	TP_STRUCT__entry(
+		__field(u32, cq_id)
+		__field(int, completion_id)
+		__field(u32, segno)
+		__field(u32, handle)
+		__field(u32, length)
+		__field(u64, offset)
+	),
+
+	TP_fast_assign(
+		const struct svc_rdma_segment *segment =
+			&chunk->ch_segments[segno];
+
+		__entry->cq_id = cid->ci_queue_id;
+		__entry->completion_id = cid->ci_completion_id;
+		__entry->segno = segno;
+		__entry->handle = segment->rs_handle;
+		__entry->length = segment->rs_length;
+		__entry->offset = segment->rs_offset;
+	),
+
+	TP_printk("cq_id=%u cid=%d segno=%u %u@0x%016llx:0x%08x",
+		__entry->cq_id, __entry->completion_id,
+		__entry->segno, __entry->length,
+		(unsigned long long)__entry->offset, __entry->handle
+	)
+);
+
 DECLARE_EVENT_CLASS(svcrdma_chunk_event,
 	TP_PROTO(
 		u32 length
diff --git a/net/sunrpc/xprtrdma/Makefile b/net/sunrpc/xprtrdma/Makefile
index 8ed0377d7a18..55b21bae866d 100644
--- a/net/sunrpc/xprtrdma/Makefile
+++ b/net/sunrpc/xprtrdma/Makefile
@@ -4,5 +4,5 @@ obj-$(CONFIG_SUNRPC_XPRT_RDMA) += rpcrdma.o
 rpcrdma-y := transport.o rpc_rdma.o verbs.o frwr_ops.o \
 	svc_rdma.o svc_rdma_backchannel.o svc_rdma_transport.o \
 	svc_rdma_sendto.o svc_rdma_recvfrom.o svc_rdma_rw.o \
-	module.o
+	svc_rdma_pcl.o module.o
 rpcrdma-$(CONFIG_SUNRPC_BACKCHANNEL) += backchannel.o
diff --git a/net/sunrpc/xprtrdma/svc_rdma_pcl.c b/net/sunrpc/xprtrdma/svc_rdma_pcl.c
new file mode 100644
index 000000000000..b63cfeaa2923
--- /dev/null
+++ b/net/sunrpc/xprtrdma/svc_rdma_pcl.c
@@ -0,0 +1,306 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2020 Oracle. All rights reserved.
+ */
+
+#include <linux/sunrpc/svc_rdma.h>
+#include <linux/sunrpc/rpc_rdma.h>
+
+#include "xprt_rdma.h"
+#include <trace/events/rpcrdma.h>
+
+/**
+ * pcl_free - Release all memory associated with a parsed chunk list
+ * @pcl: parsed chunk list
+ *
+ */
+void pcl_free(struct svc_rdma_pcl *pcl)
+{
+	while (!list_empty(&pcl->cl_chunks)) {
+		struct svc_rdma_chunk *chunk;
+
+		chunk = pcl_first_chunk(pcl);
+		list_del(&chunk->ch_list);
+		kfree(chunk);
+	}
+}
+
+static struct svc_rdma_chunk *pcl_alloc_chunk(u32 segcount, u32 position)
+{
+	struct svc_rdma_chunk *chunk;
+
+	chunk = kmalloc(struct_size(chunk, ch_segments, segcount), GFP_KERNEL);
+	if (!chunk)
+		return NULL;
+
+	chunk->ch_position = position;
+	chunk->ch_length = 0;
+	chunk->ch_payload_length = 0;
+	chunk->ch_segcount = 0;
+	return chunk;
+}
+
+static struct svc_rdma_chunk *
+pcl_lookup_position(struct svc_rdma_pcl *pcl, u32 position)
+{
+	struct svc_rdma_chunk *pos;
+
+	pcl_for_each_chunk(pos, pcl) {
+		if (pos->ch_position == position)
+			return pos;
+	}
+	return NULL;
+}
+
+static void pcl_insert_position(struct svc_rdma_pcl *pcl,
+				struct svc_rdma_chunk *chunk)
+{
+	struct svc_rdma_chunk *pos;
+
+	pcl_for_each_chunk(pos, pcl) {
+		if (pos->ch_position > chunk->ch_position)
+			break;
+	}
+	__list_add(&chunk->ch_list, pos->ch_list.prev, &pos->ch_list);
+	pcl->cl_count++;
+}
+
+static void pcl_set_read_segment(const struct svc_rdma_recv_ctxt *rctxt,
+				 struct svc_rdma_chunk *chunk,
+				 u32 handle, u32 length, u64 offset)
+{
+	struct svc_rdma_segment *segment;
+
+	segment = &chunk->ch_segments[chunk->ch_segcount];
+	segment->rs_handle = handle;
+	segment->rs_length = length;
+	segment->rs_offset = offset;
+
+	trace_svcrdma_decode_rseg(&rctxt->rc_cid, chunk, segment);
+
+	chunk->ch_length += length;
+	chunk->ch_segcount++;
+}
+
+/**
+ * pcl_alloc_call - Construct a parsed chunk list for the Call body
+ * @rctxt: Ingress receive context
+ * @p: Start of an un-decoded Read list
+ *
+ * Assumptions:
+ * - The incoming Read list has already been sanity checked.
+ * - cl_count is already set to the number of segments in
+ *   the un-decoded list.
+ * - The list might not be in order by position.
+ *
+ * Return values:
+ *       %true: Parsed chunk list was successfully constructed, and
+ *              cl_count is updated to be the number of chunks (ie.
+ *              unique positions) in the Read list.
+ *      %false: Memory allocation failed.
+ */
+bool pcl_alloc_call(struct svc_rdma_recv_ctxt *rctxt, __be32 *p)
+{
+	struct svc_rdma_pcl *pcl = &rctxt->rc_call_pcl;
+	unsigned int i, segcount = pcl->cl_count;
+
+	pcl->cl_count = 0;
+	for (i = 0; i < segcount; i++) {
+		struct svc_rdma_chunk *chunk;
+		u32 position, handle, length;
+		u64 offset;
+
+		p++;	/* skip the list discriminator */
+		p = xdr_decode_read_segment(p, &position, &handle,
+					    &length, &offset);
+		if (position != 0)
+			continue;
+
+		if (pcl_is_empty(pcl)) {
+			chunk = pcl_alloc_chunk(segcount, position);
+			if (!chunk)
+				return false;
+			pcl_insert_position(pcl, chunk);
+		} else {
+			chunk = list_first_entry(&pcl->cl_chunks,
+						 struct svc_rdma_chunk,
+						 ch_list);
+		}
+
+		pcl_set_read_segment(rctxt, chunk, handle, length, offset);
+	}
+
+	return true;
+}
+
+/**
+ * pcl_alloc_read - Construct a parsed chunk list for normal Read chunks
+ * @rctxt: Ingress receive context
+ * @p: Start of an un-decoded Read list
+ *
+ * Assumptions:
+ * - The incoming Read list has already been sanity checked.
+ * - cl_count is already set to the number of segments in
+ *   the un-decoded list.
+ * - The list might not be in order by position.
+ *
+ * Return values:
+ *       %true: Parsed chunk list was successfully constructed, and
+ *              cl_count is updated to be the number of chunks (ie.
+ *              unique position values) in the Read list.
+ *      %false: Memory allocation failed.
+ *
+ * TODO:
+ * - Check for chunk range overlaps
+ */
+bool pcl_alloc_read(struct svc_rdma_recv_ctxt *rctxt, __be32 *p)
+{
+	struct svc_rdma_pcl *pcl = &rctxt->rc_read_pcl;
+	unsigned int i, segcount = pcl->cl_count;
+
+	pcl->cl_count = 0;
+	for (i = 0; i < segcount; i++) {
+		struct svc_rdma_chunk *chunk;
+		u32 position, handle, length;
+		u64 offset;
+
+		p++;	/* skip the list discriminator */
+		p = xdr_decode_read_segment(p, &position, &handle,
+					    &length, &offset);
+		if (position == 0)
+			continue;
+
+		chunk = pcl_lookup_position(pcl, position);
+		if (!chunk) {
+			chunk = pcl_alloc_chunk(segcount, position);
+			if (!chunk)
+				return false;
+			pcl_insert_position(pcl, chunk);
+		}
+
+		pcl_set_read_segment(rctxt, chunk, handle, length, offset);
+	}
+
+	return true;
+}
+
+/**
+ * pcl_alloc_write - Construct a parsed chunk list from a Write list
+ * @rctxt: Ingress receive context
+ * @pcl: Parsed chunk list to populate
+ * @p: Start of an un-decoded Write list
+ *
+ * Assumptions:
+ * - The incoming Write list has already been sanity checked, and
+ * - cl_count is set to the number of chunks in the un-decoded list.
+ *
+ * Return values:
+ *       %true: Parsed chunk list was successfully constructed.
+ *      %false: Memory allocation failed.
+ */
+bool pcl_alloc_write(struct svc_rdma_recv_ctxt *rctxt,
+		     struct svc_rdma_pcl *pcl, __be32 *p)
+{
+	struct svc_rdma_segment *segment;
+	struct svc_rdma_chunk *chunk;
+	unsigned int i, j;
+	u32 segcount;
+
+	for (i = 0; i < pcl->cl_count; i++) {
+		p++;	/* skip the list discriminator */
+		segcount = be32_to_cpup(p++);
+
+		chunk = pcl_alloc_chunk(segcount, 0);
+		if (!chunk)
+			return false;
+		list_add_tail(&chunk->ch_list, &pcl->cl_chunks);
+
+		for (j = 0; j < segcount; j++) {
+			segment = &chunk->ch_segments[j];
+			p = xdr_decode_rdma_segment(p, &segment->rs_handle,
+						    &segment->rs_length,
+						    &segment->rs_offset);
+			trace_svcrdma_decode_wseg(&rctxt->rc_cid, chunk, j);
+
+			chunk->ch_length += segment->rs_length;
+			chunk->ch_segcount++;
+		}
+	}
+	return true;
+}
+
+static int pcl_process_region(const struct xdr_buf *xdr,
+			      unsigned int offset, unsigned int length,
+			      int (*actor)(const struct xdr_buf *, void *),
+			      void *data)
+{
+	struct xdr_buf subbuf;
+
+	if (!length)
+		return 0;
+	if (xdr_buf_subsegment(xdr, &subbuf, offset, length))
+		return -EMSGSIZE;
+	return actor(&subbuf, data);
+}
+
+/**
+ * pcl_process_nonpayloads - Process non-payload regions inside @xdr
+ * @pcl: Chunk list to process
+ * @xdr: xdr_buf to process
+ * @actor: Function to invoke on each non-payload region
+ * @data: Arguments for @actor
+ *
+ * This mechanism must ignore not only result payloads that were already
+ * sent via RDMA Write, but also XDR padding for those payloads that
+ * the upper layer has added.
+ *
+ * Assumptions:
+ *  The xdr->len and ch_position fields are aligned to 4-byte multiples.
+ *
+ * Returns:
+ *   On success, zero,
+ *   %-EMSGSIZE on XDR buffer overflow, or
+ *   The return value of @actor
+ */
+int pcl_process_nonpayloads(const struct svc_rdma_pcl *pcl,
+			    const struct xdr_buf *xdr,
+			    int (*actor)(const struct xdr_buf *, void *),
+			    void *data)
+{
+	struct svc_rdma_chunk *chunk, *next;
+	unsigned int start;
+	int ret;
+
+	chunk = pcl_first_chunk(pcl);
+
+	/* No result payloads were generated */
+	if (!chunk || !chunk->ch_payload_length)
+		return actor(xdr, data);
+
+	/* Process the region before the first result payload */
+	ret = pcl_process_region(xdr, 0, chunk->ch_position, actor, data);
+	if (ret < 0)
+		return ret;
+
+	/* Process the regions between each middle result payload */
+	while ((next = pcl_next_chunk(pcl, chunk))) {
+		if (!next->ch_payload_length)
+			break;
+
+		start = pcl_chunk_end_offset(chunk);
+		ret = pcl_process_region(xdr, start, next->ch_position - start,
+					 actor, data);
+		if (ret < 0)
+			return ret;
+
+		chunk = next;
+	}
+
+	/* Process the region after the last result payload */
+	start = pcl_chunk_end_offset(chunk);
+	ret = pcl_process_region(xdr, start, xdr->len - start, actor, data);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index c6ea2903c21a..ec9d259b149c 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -93,6 +93,7 @@
  * (see rdma_read_complete() below).
  */
 
+#include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <asm/unaligned.h>
 #include <rdma/ib_verbs.h>
@@ -143,6 +144,10 @@ svc_rdma_recv_ctxt_alloc(struct svcxprt_rdma *rdma)
 		goto fail2;
 
 	svc_rdma_recv_cid_init(rdma, &ctxt->rc_cid);
+	pcl_init(&ctxt->rc_call_pcl);
+	pcl_init(&ctxt->rc_read_pcl);
+	pcl_init(&ctxt->rc_write_pcl);
+	pcl_init(&ctxt->rc_reply_pcl);
 
 	ctxt->rc_recv_wr.next = NULL;
 	ctxt->rc_recv_wr.wr_cqe = &ctxt->rc_cqe;
@@ -226,6 +231,11 @@ void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma,
 	for (i = 0; i < ctxt->rc_page_count; i++)
 		put_page(ctxt->rc_pages[i]);
 
+	pcl_free(&ctxt->rc_call_pcl);
+	pcl_free(&ctxt->rc_read_pcl);
+	pcl_free(&ctxt->rc_write_pcl);
+	pcl_free(&ctxt->rc_reply_pcl);
+
 	if (!ctxt->rc_temp)
 		llist_add(&ctxt->rc_node, &rdma->sc_recv_ctxts);
 	else
@@ -385,100 +395,123 @@ static void svc_rdma_build_arg_xdr(struct svc_rqst *rqstp,
 	arg->len = ctxt->rc_byte_len;
 }
 
-/* This accommodates the largest possible Write chunk.
- */
-#define MAX_BYTES_WRITE_CHUNK ((u32)(RPCSVC_MAXPAGES << PAGE_SHIFT))
-
-/* This accommodates the largest possible Position-Zero
- * Read chunk or Reply chunk.
- */
-#define MAX_BYTES_SPECIAL_CHUNK ((u32)((RPCSVC_MAXPAGES + 2) << PAGE_SHIFT))
-
-/* Sanity check the Read list.
+/**
+ * xdr_count_read_segments - Count number of Read segments in Read list
+ * @rctxt: Ingress receive context
+ * @p: Start of an un-decoded Read list
  *
- * Implementation limits:
- * - This implementation supports only one Read chunk.
+ * Before allocating anything, ensure the ingress Read list is safe
+ * to use.
  *
- * Sanity checks:
- * - Read list does not overflow Receive buffer.
- * - Segment size limited by largest NFS data payload.
- *
- * The segment count is limited to how many segments can
- * fit in the transport header without overflowing the
- * buffer. That's about 40 Read segments for a 1KB inline
- * threshold.
+ * The segment count is limited to how many segments can fit in the
+ * transport header without overflowing the buffer. That's about 40
+ * Read segments for a 1KB inline threshold.
  *
  * Return values:
- *       %true: Read list is valid. @rctxt's xdr_stream is updated
- *		to point to the first byte past the Read list.
- *      %false: Read list is corrupt. @rctxt's xdr_stream is left
- *		in an unknown state.
+ *   %true: Read list is valid. @rctxt's xdr_stream is updated to point
+ *	    to the first byte past the Read list. rc_read_pcl and
+ *	    rc_call_pcl cl_count fields are set to the number of
+ *	    Read segments in the list.
+ *  %false: Read list is corrupt. @rctxt's xdr_stream is left in an
+ *	    unknown state.
  */
-static bool xdr_check_read_list(struct svc_rdma_recv_ctxt *rctxt)
+static bool xdr_count_read_segments(struct svc_rdma_recv_ctxt *rctxt, __be32 *p)
 {
-	u32 position, len;
-	bool first;
-	__be32 *p;
-
-	p = xdr_inline_decode(&rctxt->rc_stream, sizeof(*p));
-	if (!p)
-		return false;
-
-	len = 0;
-	first = true;
+	rctxt->rc_call_pcl.cl_count = 0;
+	rctxt->rc_read_pcl.cl_count = 0;
 	while (xdr_item_is_present(p)) {
+		u32 position, handle, length;
+		u64 offset;
+
 		p = xdr_inline_decode(&rctxt->rc_stream,
 				      rpcrdma_readseg_maxsz * sizeof(*p));
 		if (!p)
 			return false;
 
-		if (first) {
-			position = be32_to_cpup(p);
-			first = false;
-		} else if (be32_to_cpup(p) != position) {
-			return false;
+		xdr_decode_read_segment(p, &position, &handle,
+					    &length, &offset);
+		if (position) {
+			if (position & 3)
+				return false;
+			++rctxt->rc_read_pcl.cl_count;
+		} else {
+			++rctxt->rc_call_pcl.cl_count;
 		}
-		p += 2;
-		len += be32_to_cpup(p);
 
 		p = xdr_inline_decode(&rctxt->rc_stream, sizeof(*p));
 		if (!p)
 			return false;
 	}
-	return len <= MAX_BYTES_SPECIAL_CHUNK;
+	return true;
 }
 
-/* The segment count is limited to how many segments can
- * fit in the transport header without overflowing the
- * buffer. That's about 60 Write segments for a 1KB inline
- * threshold.
+/* Sanity check the Read list.
+ *
+ * Sanity checks:
+ * - Read list does not overflow Receive buffer.
+ * - Chunk size limited by largest NFS data payload.
+ *
+ * Return values:
+ *   %true: Read list is valid. @rctxt's xdr_stream is updated
+ *	    to point to the first byte past the Read list.
+ *  %false: Read list is corrupt. @rctxt's xdr_stream is left
+ *	    in an unknown state.
  */
-static bool xdr_check_write_chunk(struct svc_rdma_recv_ctxt *rctxt, u32 maxlen)
+static bool xdr_check_read_list(struct svc_rdma_recv_ctxt *rctxt)
 {
-	u32 i, segcount, total;
 	__be32 *p;
 
 	p = xdr_inline_decode(&rctxt->rc_stream, sizeof(*p));
 	if (!p)
 		return false;
-	segcount = be32_to_cpup(p);
+	if (!xdr_count_read_segments(rctxt, p))
+		return false;
+	if (!pcl_alloc_call(rctxt, p))
+		return false;
+	return pcl_alloc_read(rctxt, p);
+}
 
-	total = 0;
-	for (i = 0; i < segcount; i++) {
-		u32 handle, length;
-		u64 offset;
+static bool xdr_check_write_chunk(struct svc_rdma_recv_ctxt *rctxt)
+{
+	u32 segcount;
+	__be32 *p;
 
-		p = xdr_inline_decode(&rctxt->rc_stream,
-				      rpcrdma_segment_maxsz * sizeof(*p));
-		if (!p)
-			return false;
+	if (xdr_stream_decode_u32(&rctxt->rc_stream, &segcount))
+		return false;
 
-		xdr_decode_rdma_segment(p, &handle, &length, &offset);
-		trace_svcrdma_decode_wseg(handle, length, offset);
+	/* A bogus segcount causes this buffer overflow check to fail. */
+	p = xdr_inline_decode(&rctxt->rc_stream,
+			      segcount * rpcrdma_segment_maxsz * sizeof(*p));
+	return p != NULL;
+}
 
-		total += length;
+/**
+ * xdr_count_write_chunks - Count number of Write chunks in Write list
+ * @rctxt: Received header and decoding state
+ * @p: start of an un-decoded Write list
+ *
+ * Before allocating anything, ensure the ingress Write list is
+ * safe to use.
+ *
+ * Return values:
+ *       %true: Write list is valid. @rctxt's xdr_stream is updated
+ *		to point to the first byte past the Write list, and
+ *		the number of Write chunks is in rc_write_pcl.cl_count.
+ *      %false: Write list is corrupt. @rctxt's xdr_stream is left
+ *		in an indeterminate state.
+ */
+static bool xdr_count_write_chunks(struct svc_rdma_recv_ctxt *rctxt, __be32 *p)
+{
+	rctxt->rc_write_pcl.cl_count = 0;
+	while (xdr_item_is_present(p)) {
+		if (!xdr_check_write_chunk(rctxt))
+			return false;
+		++rctxt->rc_write_pcl.cl_count;
+		p = xdr_inline_decode(&rctxt->rc_stream, sizeof(*p));
+		if (!p)
+			return false;
 	}
-	return total <= maxlen;
+	return true;
 }
 
 /* Sanity check the Write list.
@@ -498,24 +531,22 @@ static bool xdr_check_write_chunk(struct svc_rdma_recv_ctxt *rctxt, u32 maxlen)
  */
 static bool xdr_check_write_list(struct svc_rdma_recv_ctxt *rctxt)
 {
-	u32 chcount = 0;
 	__be32 *p;
 
 	p = xdr_inline_decode(&rctxt->rc_stream, sizeof(*p));
 	if (!p)
 		return false;
-	rctxt->rc_write_list = p;
-	while (xdr_item_is_present(p)) {
-		if (!xdr_check_write_chunk(rctxt, MAX_BYTES_WRITE_CHUNK))
-			return false;
-		++chcount;
-		p = xdr_inline_decode(&rctxt->rc_stream, sizeof(*p));
-		if (!p)
-			return false;
-	}
-	if (!chcount)
-		rctxt->rc_write_list = NULL;
-	return chcount < 2;
+
+	rctxt->rc_write_list = NULL;
+	if (!xdr_count_write_chunks(rctxt, p))
+		return false;
+	if (!pcl_alloc_write(rctxt, &rctxt->rc_write_pcl, p))
+		return false;
+
+	if (!pcl_is_empty(&rctxt->rc_write_pcl))
+		rctxt->rc_write_list = p;
+	rctxt->rc_cur_result_payload = pcl_first_chunk(&rctxt->rc_write_pcl);
+	return rctxt->rc_write_pcl.cl_count < 2;
 }
 
 /* Sanity check the Reply chunk.
@@ -537,13 +568,16 @@ static bool xdr_check_reply_chunk(struct svc_rdma_recv_ctxt *rctxt)
 	p = xdr_inline_decode(&rctxt->rc_stream, sizeof(*p));
 	if (!p)
 		return false;
+
 	rctxt->rc_reply_chunk = NULL;
-	if (xdr_item_is_present(p)) {
-		if (!xdr_check_write_chunk(rctxt, MAX_BYTES_SPECIAL_CHUNK))
-			return false;
-		rctxt->rc_reply_chunk = p;
-	}
-	return true;
+	if (!xdr_item_is_present(p))
+		return true;
+	if (!xdr_check_write_chunk(rctxt))
+		return false;
+
+	rctxt->rc_reply_chunk = p;
+	rctxt->rc_reply_pcl.cl_count = 1;
+	return pcl_alloc_write(rctxt, &rctxt->rc_reply_pcl, p);
 }
 
 /* RPC-over-RDMA Version One private extension: Remote Invalidation.
-- 
cgit v1.2.3


From 58b2e0fefa891c99f297120c8c062a35005dc562 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Sun, 22 Mar 2020 13:06:55 -0400
Subject: svcrdma: Use parsed chunk lists to detect reverse direction replies

Refactor: Don't duplicate header decoding smarts here. Instead, use
the new parsed chunk lists.

Note that the XID sanity test is also removed. The XID is already
looked up by the cb handler, and is rejected if it's not recognized.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svc_rdma.h         |  1 +
 net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 29 ++++++++++++++---------------
 2 files changed, 15 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index a89d4209fe2a..74247a33b6c6 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -144,6 +144,7 @@ struct svc_rdma_recv_ctxt {
 	unsigned int		rc_page_count;
 	unsigned int		rc_hdr_count;
 	u32			rc_inv_rkey;
+	__be32			rc_msgtype;
 
 	struct svc_rdma_pcl	rc_call_pcl;
 
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 2755ca178b09..72b07e8aa3c9 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -668,7 +668,8 @@ static int svc_rdma_xdr_decode_req(struct xdr_buf *rq_arg,
 	if (*p != rpcrdma_version)
 		goto out_version;
 	p += 2;
-	switch (*p) {
+	rctxt->rc_msgtype = *p;
+	switch (rctxt->rc_msgtype) {
 	case rdma_msg:
 		break;
 	case rdma_nomsg:
@@ -762,30 +763,28 @@ static void svc_rdma_send_error(struct svcxprt_rdma *rdma,
  * the RPC/RDMA header small and fixed in size, so it is
  * straightforward to check the RPC header's direction field.
  */
-static bool svc_rdma_is_backchannel_reply(struct svc_xprt *xprt,
-					  __be32 *rdma_resp)
+static bool svc_rdma_is_reverse_direction_reply(struct svc_xprt *xprt,
+						struct svc_rdma_recv_ctxt *rctxt)
 {
-	__be32 *p;
+	__be32 *p = rctxt->rc_recv_buf;
 
 	if (!xprt->xpt_bc_xprt)
 		return false;
 
-	p = rdma_resp + 3;
-	if (*p++ != rdma_msg)
+	if (rctxt->rc_msgtype != rdma_msg)
 		return false;
 
-	if (*p++ != xdr_zero)
+	if (!pcl_is_empty(&rctxt->rc_call_pcl))
+		return false;
+	if (!pcl_is_empty(&rctxt->rc_read_pcl))
 		return false;
-	if (*p++ != xdr_zero)
+	if (!pcl_is_empty(&rctxt->rc_write_pcl))
 		return false;
-	if (*p++ != xdr_zero)
+	if (!pcl_is_empty(&rctxt->rc_reply_pcl))
 		return false;
 
-	/* XID sanity */
-	if (*p++ != *rdma_resp)
-		return false;
-	/* call direction */
-	if (*p == cpu_to_be32(RPC_CALL))
+	/* RPC call direction */
+	if (*(p + 8) == cpu_to_be32(RPC_CALL))
 		return false;
 
 	return true;
@@ -868,7 +867,7 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 		goto out_drop;
 	rqstp->rq_xprt_hlen = ret;
 
-	if (svc_rdma_is_backchannel_reply(xprt, p))
+	if (svc_rdma_is_reverse_direction_reply(xprt, ctxt))
 		goto out_backchannel;
 
 	svc_rdma_get_inv_rkey(rdma_xprt, ctxt);
-- 
cgit v1.2.3


From 7a1cbfa18059a40d4752dab057384c3ca2de326c Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 17 Jun 2020 11:07:00 -0400
Subject: svcrdma: Use parsed chunk lists to construct RDMA Writes

Refactor: Instead of re-parsing the ingress RPC Call transport
header when constructing RDMA Writes, use the new parsed chunk lists
for the Write list and Reply chunk, which are version-agnostic and
already XDR-decoded.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svc_rdma.h         |  5 ++--
 net/sunrpc/xprtrdma/svc_rdma_recvfrom.c |  1 -
 net/sunrpc/xprtrdma/svc_rdma_rw.c       | 47 ++++++++++++++++-----------------
 net/sunrpc/xprtrdma/svc_rdma_sendto.c   | 22 ++++++++-------
 4 files changed, 38 insertions(+), 37 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 74247a33b6c6..d9148787efff 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -157,8 +157,6 @@ struct svc_rdma_recv_ctxt {
 	__be32			*rc_reply_chunk;
 	struct svc_rdma_pcl	rc_reply_pcl;
 
-	unsigned int		rc_read_payload_offset;
-	unsigned int		rc_read_payload_length;
 	struct page		*rc_pages[RPCSVC_MAXPAGES];
 };
 
@@ -196,7 +194,8 @@ extern int svc_rdma_recv_read_chunk(struct svcxprt_rdma *rdma,
 				    struct svc_rqst *rqstp,
 				    struct svc_rdma_recv_ctxt *head, __be32 *p);
 extern int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma,
-				     __be32 *wr_ch, const struct xdr_buf *xdr);
+				     const struct svc_rdma_chunk *chunk,
+				     const struct xdr_buf *xdr);
 extern int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma,
 				     const struct svc_rdma_recv_ctxt *rctxt,
 				     struct xdr_buf *xdr);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 72b07e8aa3c9..7d44e9d2e7a3 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -207,7 +207,6 @@ svc_rdma_recv_ctxt_get(struct svcxprt_rdma *rdma)
 
 out:
 	ctxt->rc_page_count = 0;
-	ctxt->rc_read_payload_length = 0;
 	return ctxt;
 
 out_empty:
diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c
index e6050230b49f..ed7def7b801b 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_rw.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c
@@ -190,11 +190,11 @@ static void svc_rdma_cc_release(struct svc_rdma_chunk_ctxt *cc,
  *  - Stores arguments for the SGL constructor functions
  */
 struct svc_rdma_write_info {
+	const struct svc_rdma_chunk	*wi_chunk;
+
 	/* write state of this chunk */
 	unsigned int		wi_seg_off;
 	unsigned int		wi_seg_no;
-	unsigned int		wi_nsegs;
-	__be32			*wi_segs;
 
 	/* SGL constructor arguments */
 	const struct xdr_buf	*wi_xdr;
@@ -205,7 +205,8 @@ struct svc_rdma_write_info {
 };
 
 static struct svc_rdma_write_info *
-svc_rdma_write_info_alloc(struct svcxprt_rdma *rdma, __be32 *chunk)
+svc_rdma_write_info_alloc(struct svcxprt_rdma *rdma,
+			  const struct svc_rdma_chunk *chunk)
 {
 	struct svc_rdma_write_info *info;
 
@@ -213,10 +214,9 @@ svc_rdma_write_info_alloc(struct svcxprt_rdma *rdma, __be32 *chunk)
 	if (!info)
 		return info;
 
+	info->wi_chunk = chunk;
 	info->wi_seg_off = 0;
 	info->wi_seg_no = 0;
-	info->wi_nsegs = be32_to_cpup(++chunk);
-	info->wi_segs = ++chunk;
 	svc_rdma_cc_init(rdma, &info->wi_cc);
 	info->wi_cc.cc_cqe.done = svc_rdma_write_done;
 	return info;
@@ -443,23 +443,19 @@ svc_rdma_build_writes(struct svc_rdma_write_info *info,
 {
 	struct svc_rdma_chunk_ctxt *cc = &info->wi_cc;
 	struct svcxprt_rdma *rdma = cc->cc_rdma;
+	const struct svc_rdma_segment *seg;
 	struct svc_rdma_rw_ctxt *ctxt;
-	__be32 *seg;
 	int ret;
 
-	seg = info->wi_segs + info->wi_seg_no * rpcrdma_segment_maxsz;
 	do {
 		unsigned int write_len;
-		u32 handle, length;
 		u64 offset;
 
-		if (info->wi_seg_no >= info->wi_nsegs)
+		seg = &info->wi_chunk->ch_segments[info->wi_seg_no];
+		if (!seg)
 			goto out_overflow;
 
-		xdr_decode_rdma_segment(seg, &handle, &length, &offset);
-		offset += info->wi_seg_off;
-
-		write_len = min(remaining, length - info->wi_seg_off);
+		write_len = min(remaining, seg->rs_length - info->wi_seg_off);
 		if (!write_len)
 			goto out_overflow;
 		ctxt = svc_rdma_get_rw_ctxt(rdma,
@@ -468,17 +464,17 @@ svc_rdma_build_writes(struct svc_rdma_write_info *info,
 			return -ENOMEM;
 
 		constructor(info, write_len, ctxt);
-		ret = svc_rdma_rw_ctx_init(rdma, ctxt, offset, handle,
+		offset = seg->rs_offset + info->wi_seg_off;
+		ret = svc_rdma_rw_ctx_init(rdma, ctxt, offset, seg->rs_handle,
 					   DMA_TO_DEVICE);
 		if (ret < 0)
 			return -EIO;
 
-		trace_svcrdma_send_wseg(handle, write_len, offset);
+		trace_svcrdma_send_wseg(seg->rs_handle, write_len, offset);
 
 		list_add(&ctxt->rw_list, &cc->cc_rwctxts);
 		cc->cc_sqecount += ret;
-		if (write_len == length - info->wi_seg_off) {
-			seg += 4;
+		if (write_len == seg->rs_length - info->wi_seg_off) {
 			info->wi_seg_no++;
 			info->wi_seg_off = 0;
 		} else {
@@ -491,7 +487,7 @@ svc_rdma_build_writes(struct svc_rdma_write_info *info,
 
 out_overflow:
 	trace_svcrdma_small_wrch_err(rdma, remaining, info->wi_seg_no,
-				     info->wi_nsegs);
+				     info->wi_chunk->ch_segcount);
 	return -E2BIG;
 }
 
@@ -579,7 +575,7 @@ static int svc_rdma_xb_write(const struct xdr_buf *xdr,
 /**
  * svc_rdma_send_write_chunk - Write all segments in a Write chunk
  * @rdma: controlling RDMA transport
- * @wr_ch: Write chunk provided by client
+ * @chunk: Write chunk provided by the client
  * @xdr: xdr_buf containing the data payload
  *
  * Returns a non-negative number of bytes the chunk consumed, or
@@ -589,13 +585,14 @@ static int svc_rdma_xb_write(const struct xdr_buf *xdr,
  *	%-ENOTCONN if posting failed (connection is lost),
  *	%-EIO if rdma_rw initialization failed (DMA mapping, etc).
  */
-int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma, __be32 *wr_ch,
+int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma,
+			      const struct svc_rdma_chunk *chunk,
 			      const struct xdr_buf *xdr)
 {
 	struct svc_rdma_write_info *info;
 	int ret;
 
-	info = svc_rdma_write_info_alloc(rdma, wr_ch);
+	info = svc_rdma_write_info_alloc(rdma, chunk);
 	if (!info)
 		return -ENOMEM;
 
@@ -633,12 +630,14 @@ int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma,
 			      struct xdr_buf *xdr)
 {
 	struct svc_rdma_write_info *info;
+	struct svc_rdma_chunk *chunk;
 	int consumed, ret;
 
-	if (!rctxt->rc_reply_chunk)
+	if (pcl_is_empty(&rctxt->rc_reply_pcl))
 		return 0;
 
-	info = svc_rdma_write_info_alloc(rdma, rctxt->rc_reply_chunk);
+	chunk = pcl_first_chunk(&rctxt->rc_reply_pcl);
+	info = svc_rdma_write_info_alloc(rdma, chunk);
 	if (!info)
 		return -ENOMEM;
 
@@ -650,7 +649,7 @@ int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma,
 	/* Send the page list in the Reply chunk only if the
 	 * client did not provide Write chunks.
 	 */
-	if (!rctxt->rc_write_list && xdr->page_len) {
+	if (pcl_is_empty(&rctxt->rc_write_pcl) && xdr->page_len) {
 		ret = svc_rdma_pages_write(info, xdr, xdr->head[0].iov_len,
 					   xdr->page_len);
 		if (ret < 0)
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 922dbe573570..9a6d3dee69ed 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -466,12 +466,14 @@ static ssize_t
 svc_rdma_encode_write_list(const struct svc_rdma_recv_ctxt *rctxt,
 			   struct svc_rdma_send_ctxt *sctxt)
 {
+	struct svc_rdma_chunk *chunk;
 	ssize_t len, ret;
 
 	len = 0;
 	if (rctxt->rc_write_list) {
+		chunk = pcl_first_chunk(&rctxt->rc_write_pcl);
 		ret = svc_rdma_encode_write_chunk(rctxt->rc_write_list, sctxt,
-						  rctxt->rc_read_payload_length);
+						  chunk->ch_payload_length);
 		if (ret < 0)
 			return ret;
 		len = ret;
@@ -978,25 +980,27 @@ int svc_rdma_result_payload(struct svc_rqst *rqstp, unsigned int offset,
 			    unsigned int length)
 {
 	struct svc_rdma_recv_ctxt *rctxt = rqstp->rq_xprt_ctxt;
+	struct svc_rdma_chunk *chunk;
 	struct svcxprt_rdma *rdma;
 	struct xdr_buf subbuf;
 	int ret;
 
-	if (!rctxt->rc_write_list || !length)
+	chunk = rctxt->rc_cur_result_payload;
+	if (!length || !chunk)
 		return 0;
+	rctxt->rc_cur_result_payload =
+		pcl_next_chunk(&rctxt->rc_write_pcl, chunk);
+	if (length > chunk->ch_length)
+		return -E2BIG;
 
-	/* XXX: Just one READ payload slot for now, since our
-	 * transport implementation currently supports only one
-	 * Write chunk.
-	 */
-	rctxt->rc_read_payload_offset = offset;
-	rctxt->rc_read_payload_length = length;
+	chunk->ch_position = offset;
+	chunk->ch_payload_length = length;
 
 	if (xdr_buf_subsegment(&rqstp->rq_res, &subbuf, offset, length))
 		return -EMSGSIZE;
 
 	rdma = container_of(rqstp->rq_xprt, struct svcxprt_rdma, sc_xprt);
-	ret = svc_rdma_send_write_chunk(rdma, rctxt->rc_write_list, &subbuf);
+	ret = svc_rdma_send_write_chunk(rdma, chunk, &subbuf);
 	if (ret < 0)
 		return ret;
 	return 0;
-- 
cgit v1.2.3


From 9d0b09d5ef0c842592a5df3a5b8b59124485ff1b Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 13 Mar 2020 10:42:11 -0400
Subject: svcrdma: Support multiple write chunks when pulling up

When counting the number of SGEs needed to construct a Send request,
do not count result payloads. And, when copying the Reply message
into the pull-up buffer, result payloads are not to be copied to the
Send buffer.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svc_rdma.h            |   2 +
 include/trace/events/rpcrdma.h             |  20 ++-
 net/sunrpc/xprtrdma/svc_rdma_backchannel.c |  14 ++-
 net/sunrpc/xprtrdma/svc_rdma_recvfrom.c    |   9 +-
 net/sunrpc/xprtrdma/svc_rdma_sendto.c      | 188 +++++++++++++++++------------
 5 files changed, 146 insertions(+), 87 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index d9148787efff..7090af1a9791 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -182,6 +182,8 @@ extern void svc_rdma_handle_bc_reply(struct svc_rqst *rqstp,
 /* svc_rdma_recvfrom.c */
 extern void svc_rdma_recv_ctxts_destroy(struct svcxprt_rdma *rdma);
 extern bool svc_rdma_post_recvs(struct svcxprt_rdma *rdma);
+extern struct svc_rdma_recv_ctxt *
+		svc_rdma_recv_ctxt_get(struct svcxprt_rdma *rdma);
 extern void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma,
 				   struct svc_rdma_recv_ctxt *ctxt);
 extern void svc_rdma_flush_recv_queues(struct svcxprt_rdma *rdma);
diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index 5218e0f9596a..afc58accb9cf 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -1805,20 +1805,30 @@ TRACE_EVENT(svcrdma_small_wrch_err,
 
 TRACE_EVENT(svcrdma_send_pullup,
 	TP_PROTO(
-		unsigned int len
+		const struct svc_rdma_send_ctxt *ctxt,
+		unsigned int msglen
 	),
 
-	TP_ARGS(len),
+	TP_ARGS(ctxt, msglen),
 
 	TP_STRUCT__entry(
-		__field(unsigned int, len)
+		__field(u32, cq_id)
+		__field(int, completion_id)
+		__field(unsigned int, hdrlen)
+		__field(unsigned int, msglen)
 	),
 
 	TP_fast_assign(
-		__entry->len = len;
+		__entry->cq_id = ctxt->sc_cid.ci_queue_id;
+		__entry->completion_id = ctxt->sc_cid.ci_completion_id;
+		__entry->hdrlen = ctxt->sc_hdrbuf.len,
+		__entry->msglen = msglen;
 	),
 
-	TP_printk("len=%u", __entry->len)
+	TP_printk("cq_id=%u cid=%d hdr=%u msg=%u (total %u)",
+		__entry->cq_id, __entry->completion_id,
+		__entry->hdrlen, __entry->msglen,
+		__entry->hdrlen + __entry->msglen)
 );
 
 TRACE_EVENT(svcrdma_send_err,
diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
index 5e7c4ba9e147..63f8be974df2 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
@@ -74,11 +74,17 @@ out_unlock:
  */
 static int svc_rdma_bc_sendto(struct svcxprt_rdma *rdma,
 			      struct rpc_rqst *rqst,
-			      struct svc_rdma_send_ctxt *ctxt)
+			      struct svc_rdma_send_ctxt *sctxt)
 {
+	struct svc_rdma_recv_ctxt *rctxt;
 	int ret;
 
-	ret = svc_rdma_map_reply_msg(rdma, ctxt, NULL, &rqst->rq_snd_buf);
+	rctxt = svc_rdma_recv_ctxt_get(rdma);
+	if (!rctxt)
+		return -EIO;
+
+	ret = svc_rdma_map_reply_msg(rdma, sctxt, rctxt, &rqst->rq_snd_buf);
+	svc_rdma_recv_ctxt_put(rdma, rctxt);
 	if (ret < 0)
 		return -EIO;
 
@@ -86,8 +92,8 @@ static int svc_rdma_bc_sendto(struct svcxprt_rdma *rdma,
 	 * the rq_buffer before all retransmits are complete.
 	 */
 	get_page(virt_to_page(rqst->rq_buffer));
-	ctxt->sc_send_wr.opcode = IB_WR_SEND;
-	return svc_rdma_send(rdma, ctxt);
+	sctxt->sc_send_wr.opcode = IB_WR_SEND;
+	return svc_rdma_send(rdma, sctxt);
 }
 
 /* Server-side transport endpoint wants a whole page for its send
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 7d44e9d2e7a3..af32c3ad45a6 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -194,8 +194,13 @@ void svc_rdma_recv_ctxts_destroy(struct svcxprt_rdma *rdma)
 	}
 }
 
-static struct svc_rdma_recv_ctxt *
-svc_rdma_recv_ctxt_get(struct svcxprt_rdma *rdma)
+/**
+ * svc_rdma_recv_ctxt_get - Allocate a recv_ctxt
+ * @rdma: controlling svcxprt_rdma
+ *
+ * Returns a recv_ctxt or (rarely) NULL if none are available.
+ */
+struct svc_rdma_recv_ctxt *svc_rdma_recv_ctxt_get(struct svcxprt_rdma *rdma)
 {
 	struct svc_rdma_recv_ctxt *ctxt;
 	struct llist_node *node;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 1fdbbad3f7dc..50f0216fb08c 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -531,6 +531,45 @@ static int svc_rdma_dma_map_buf(struct svcxprt_rdma *rdma,
 				     offset_in_page(base), len);
 }
 
+struct svc_rdma_pullup_data {
+	u8		*pd_dest;
+	unsigned int	pd_length;
+	unsigned int	pd_num_sges;
+};
+
+/**
+ * svc_rdma_xb_count_sges - Count how many SGEs will be needed
+ * @xdr: xdr_buf containing portion of an RPC message to transmit
+ * @data: pointer to arguments
+ *
+ * Returns:
+ *   Number of SGEs needed to Send the contents of @xdr inline
+ */
+static int svc_rdma_xb_count_sges(const struct xdr_buf *xdr,
+				  void *data)
+{
+	struct svc_rdma_pullup_data *args = data;
+	unsigned int remaining;
+	unsigned long offset;
+
+	if (xdr->head[0].iov_len)
+		++args->pd_num_sges;
+
+	offset = offset_in_page(xdr->page_base);
+	remaining = xdr->page_len;
+	while (remaining) {
+		++args->pd_num_sges;
+		remaining -= min_t(u32, PAGE_SIZE - offset, remaining);
+		offset = 0;
+	}
+
+	if (xdr->tail[0].iov_len)
+		++args->pd_num_sges;
+
+	args->pd_length += xdr->len;
+	return 0;
+}
+
 /**
  * svc_rdma_pull_up_needed - Determine whether to use pull-up
  * @rdma: controlling transport
@@ -539,50 +578,71 @@ static int svc_rdma_dma_map_buf(struct svcxprt_rdma *rdma,
  * @xdr: xdr_buf containing RPC message to transmit
  *
  * Returns:
- *	%true if pull-up must be used
- *	%false otherwise
+ *   %true if pull-up must be used
+ *   %false otherwise
  */
-static bool svc_rdma_pull_up_needed(struct svcxprt_rdma *rdma,
-				    struct svc_rdma_send_ctxt *sctxt,
+static bool svc_rdma_pull_up_needed(const struct svcxprt_rdma *rdma,
+				    const struct svc_rdma_send_ctxt *sctxt,
 				    const struct svc_rdma_recv_ctxt *rctxt,
-				    struct xdr_buf *xdr)
+				    const struct xdr_buf *xdr)
 {
-	bool write_chunk_present = rctxt && rctxt->rc_write_list;
-	int elements;
+	/* Resources needed for the transport header */
+	struct svc_rdma_pullup_data args = {
+		.pd_length	= sctxt->sc_hdrbuf.len,
+		.pd_num_sges	= 1,
+	};
+	int ret;
 
-	/* For small messages, copying bytes is cheaper than DMA mapping.
-	 */
-	if (!write_chunk_present &&
-	    sctxt->sc_hdrbuf.len + xdr->len < RPCRDMA_PULLUP_THRESH)
+	ret = pcl_process_nonpayloads(&rctxt->rc_write_pcl, xdr,
+				      svc_rdma_xb_count_sges, &args);
+	if (ret < 0)
+		return false;
+
+	if (args.pd_length < RPCRDMA_PULLUP_THRESH)
 		return true;
+	return args.pd_num_sges >= rdma->sc_max_send_sges;
+}
 
-	/* Check whether the xdr_buf has more elements than can
-	 * fit in a single RDMA Send.
-	 */
-	/* xdr->head */
-	elements = 1;
-
-	/* xdr->pages */
-	if (!rctxt || !rctxt->rc_write_list) {
-		unsigned int remaining;
-		unsigned long pageoff;
-
-		pageoff = xdr->page_base & ~PAGE_MASK;
-		remaining = xdr->page_len;
-		while (remaining) {
-			++elements;
-			remaining -= min_t(u32, PAGE_SIZE - pageoff,
-					   remaining);
-			pageoff = 0;
-		}
+/**
+ * svc_rdma_xb_linearize - Copy region of xdr_buf to flat buffer
+ * @xdr: xdr_buf containing portion of an RPC message to copy
+ * @data: pointer to arguments
+ *
+ * Returns:
+ *   Always zero.
+ */
+static int svc_rdma_xb_linearize(const struct xdr_buf *xdr,
+				 void *data)
+{
+	struct svc_rdma_pullup_data *args = data;
+	unsigned int len, remaining;
+	unsigned long pageoff;
+	struct page **ppages;
+
+	if (xdr->head[0].iov_len) {
+		memcpy(args->pd_dest, xdr->head[0].iov_base, xdr->head[0].iov_len);
+		args->pd_dest += xdr->head[0].iov_len;
 	}
 
-	/* xdr->tail */
-	if (xdr->tail[0].iov_len)
-		++elements;
+	ppages = xdr->pages + (xdr->page_base >> PAGE_SHIFT);
+	pageoff = offset_in_page(xdr->page_base);
+	remaining = xdr->page_len;
+	while (remaining) {
+		len = min_t(u32, PAGE_SIZE - pageoff, remaining);
+		memcpy(args->pd_dest, page_address(*ppages) + pageoff, len);
+		remaining -= len;
+		args->pd_dest += len;
+		pageoff = 0;
+		ppages++;
+	}
 
-	/* assume 1 SGE is needed for the transport header */
-	return elements >= rdma->sc_max_send_sges;
+	if (xdr->tail[0].iov_len) {
+		memcpy(args->pd_dest, xdr->tail[0].iov_base, xdr->tail[0].iov_len);
+		args->pd_dest += xdr->tail[0].iov_len;
+	}
+
+	args->pd_length += xdr->len;
+	return 0;
 }
 
 /**
@@ -595,54 +655,30 @@ static bool svc_rdma_pull_up_needed(struct svcxprt_rdma *rdma,
  * The device is not capable of sending the reply directly.
  * Assemble the elements of @xdr into the transport header buffer.
  *
- * Returns zero on success, or a negative errno on failure.
+ * Assumptions:
+ *  pull_up_needed has determined that @xdr will fit in the buffer.
+ *
+ * Returns:
+ *   %0 if pull-up was successful
+ *   %-EMSGSIZE if a buffer manipulation problem occurred
  */
-static int svc_rdma_pull_up_reply_msg(struct svcxprt_rdma *rdma,
+static int svc_rdma_pull_up_reply_msg(const struct svcxprt_rdma *rdma,
 				      struct svc_rdma_send_ctxt *sctxt,
 				      const struct svc_rdma_recv_ctxt *rctxt,
 				      const struct xdr_buf *xdr)
 {
-	unsigned char *dst, *tailbase;
-	unsigned int taillen;
-
-	dst = sctxt->sc_xprt_buf + sctxt->sc_hdrbuf.len;
-	memcpy(dst, xdr->head[0].iov_base, xdr->head[0].iov_len);
-	dst += xdr->head[0].iov_len;
-
-	tailbase = xdr->tail[0].iov_base;
-	taillen = xdr->tail[0].iov_len;
-	if (rctxt && rctxt->rc_write_list) {
-		u32 xdrpad;
-
-		xdrpad = xdr_pad_size(xdr->page_len);
-		if (taillen && xdrpad) {
-			tailbase += xdrpad;
-			taillen -= xdrpad;
-		}
-	} else {
-		unsigned int len, remaining;
-		unsigned long pageoff;
-		struct page **ppages;
-
-		ppages = xdr->pages + (xdr->page_base >> PAGE_SHIFT);
-		pageoff = xdr->page_base & ~PAGE_MASK;
-		remaining = xdr->page_len;
-		while (remaining) {
-			len = min_t(u32, PAGE_SIZE - pageoff, remaining);
-
-			memcpy(dst, page_address(*ppages) + pageoff, len);
-			remaining -= len;
-			dst += len;
-			pageoff = 0;
-			ppages++;
-		}
-	}
+	struct svc_rdma_pullup_data args = {
+		.pd_dest	= sctxt->sc_xprt_buf + sctxt->sc_hdrbuf.len,
+	};
+	int ret;
 
-	if (taillen)
-		memcpy(dst, tailbase, taillen);
+	ret = pcl_process_nonpayloads(&rctxt->rc_write_pcl, xdr,
+				      svc_rdma_xb_linearize, &args);
+	if (ret < 0)
+		return ret;
 
-	sctxt->sc_sges[0].length += xdr->len;
-	trace_svcrdma_send_pullup(sctxt->sc_sges[0].length);
+	sctxt->sc_sges[0].length = sctxt->sc_hdrbuf.len + args.pd_length;
+	trace_svcrdma_send_pullup(sctxt, args.pd_length);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 2371bcc056647327445150d6df0502d92ad68439 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Mon, 9 Mar 2020 13:29:27 -0400
Subject: svcrdma: Support multiple Write chunks in svc_rdma_map_reply_msg()

Refactor: svc_rdma_map_reply_msg() is restructured to DMA map only
the parts of rq_res that do not contain a result payload.

This change has been tested to confirm that it does not cause a
regression in the no Write chunk and single Write chunk cases.
Multiple Write chunks have not been tested.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svc_rdma.h       |   2 +-
 include/trace/events/rpcrdma.h        |   1 +
 net/sunrpc/xprtrdma/svc_rdma_sendto.c | 174 +++++++++++++++++++---------------
 3 files changed, 100 insertions(+), 77 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 7090af1a9791..e09fafba00d7 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -213,7 +213,7 @@ extern int svc_rdma_send(struct svcxprt_rdma *rdma,
 extern int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
 				  struct svc_rdma_send_ctxt *sctxt,
 				  const struct svc_rdma_recv_ctxt *rctxt,
-				  struct xdr_buf *xdr);
+				  const struct xdr_buf *xdr);
 extern void svc_rdma_send_error_msg(struct svcxprt_rdma *rdma,
 				    struct svc_rdma_send_ctxt *sctxt,
 				    struct svc_rdma_recv_ctxt *rctxt,
diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index afc58accb9cf..054dedd0280c 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -1687,6 +1687,7 @@ DECLARE_EVENT_CLASS(svcrdma_dma_map_class,
 				TP_ARGS(rdma, dma_addr, length))
 
 DEFINE_SVC_DMA_EVENT(dma_map_page);
+DEFINE_SVC_DMA_EVENT(dma_map_err);
 DEFINE_SVC_DMA_EVENT(dma_unmap_page);
 
 TRACE_EVENT(svcrdma_dma_map_rw_err,
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 50f0216fb08c..78fa57ce424f 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -496,39 +496,111 @@ svc_rdma_encode_reply_chunk(struct svc_rdma_recv_ctxt *rctxt,
 	return svc_rdma_encode_write_chunk(sctxt, chunk);
 }
 
-static int svc_rdma_dma_map_page(struct svcxprt_rdma *rdma,
-				 struct svc_rdma_send_ctxt *ctxt,
-				 struct page *page,
-				 unsigned long offset,
-				 unsigned int len)
+struct svc_rdma_map_data {
+	struct svcxprt_rdma		*md_rdma;
+	struct svc_rdma_send_ctxt	*md_ctxt;
+};
+
+/**
+ * svc_rdma_page_dma_map - DMA map one page
+ * @data: pointer to arguments
+ * @page: struct page to DMA map
+ * @offset: offset into the page
+ * @len: number of bytes to map
+ *
+ * Returns:
+ *   %0 if DMA mapping was successful
+ *   %-EIO if the page cannot be DMA mapped
+ */
+static int svc_rdma_page_dma_map(void *data, struct page *page,
+				 unsigned long offset, unsigned int len)
 {
+	struct svc_rdma_map_data *args = data;
+	struct svcxprt_rdma *rdma = args->md_rdma;
+	struct svc_rdma_send_ctxt *ctxt = args->md_ctxt;
 	struct ib_device *dev = rdma->sc_cm_id->device;
 	dma_addr_t dma_addr;
 
+	++ctxt->sc_cur_sge_no;
+
 	dma_addr = ib_dma_map_page(dev, page, offset, len, DMA_TO_DEVICE);
-	trace_svcrdma_dma_map_page(rdma, dma_addr, len);
 	if (ib_dma_mapping_error(dev, dma_addr))
 		goto out_maperr;
 
+	trace_svcrdma_dma_map_page(rdma, dma_addr, len);
 	ctxt->sc_sges[ctxt->sc_cur_sge_no].addr = dma_addr;
 	ctxt->sc_sges[ctxt->sc_cur_sge_no].length = len;
 	ctxt->sc_send_wr.num_sge++;
 	return 0;
 
 out_maperr:
+	trace_svcrdma_dma_map_err(rdma, dma_addr, len);
 	return -EIO;
 }
 
-/* ib_dma_map_page() is used here because svc_rdma_dma_unmap()
+/**
+ * svc_rdma_iov_dma_map - DMA map an iovec
+ * @data: pointer to arguments
+ * @iov: kvec to DMA map
+ *
+ * ib_dma_map_page() is used here because svc_rdma_dma_unmap()
  * handles DMA-unmap and it uses ib_dma_unmap_page() exclusively.
+ *
+ * Returns:
+ *   %0 if DMA mapping was successful
+ *   %-EIO if the iovec cannot be DMA mapped
  */
-static int svc_rdma_dma_map_buf(struct svcxprt_rdma *rdma,
-				struct svc_rdma_send_ctxt *ctxt,
-				unsigned char *base,
-				unsigned int len)
+static int svc_rdma_iov_dma_map(void *data, const struct kvec *iov)
 {
-	return svc_rdma_dma_map_page(rdma, ctxt, virt_to_page(base),
-				     offset_in_page(base), len);
+	if (!iov->iov_len)
+		return 0;
+	return svc_rdma_page_dma_map(data, virt_to_page(iov->iov_base),
+				     offset_in_page(iov->iov_base),
+				     iov->iov_len);
+}
+
+/**
+ * svc_rdma_xb_dma_map - DMA map all segments of an xdr_buf
+ * @xdr: xdr_buf containing portion of an RPC message to transmit
+ * @data: pointer to arguments
+ *
+ * Returns:
+ *   %0 if DMA mapping was successful
+ *   %-EIO if DMA mapping failed
+ *
+ * On failure, any DMA mappings that have been already done must be
+ * unmapped by the caller.
+ */
+static int svc_rdma_xb_dma_map(const struct xdr_buf *xdr, void *data)
+{
+	unsigned int len, remaining;
+	unsigned long pageoff;
+	struct page **ppages;
+	int ret;
+
+	ret = svc_rdma_iov_dma_map(data, &xdr->head[0]);
+	if (ret < 0)
+		return ret;
+
+	ppages = xdr->pages + (xdr->page_base >> PAGE_SHIFT);
+	pageoff = offset_in_page(xdr->page_base);
+	remaining = xdr->page_len;
+	while (remaining) {
+		len = min_t(u32, PAGE_SIZE - pageoff, remaining);
+
+		ret = svc_rdma_page_dma_map(data, *ppages++, pageoff, len);
+		if (ret < 0)
+			return ret;
+
+		remaining -= len;
+		pageoff = 0;
+	}
+
+	ret = svc_rdma_iov_dma_map(data, &xdr->tail[0]);
+	if (ret < 0)
+		return ret;
+
+	return xdr->len;
 }
 
 struct svc_rdma_pullup_data {
@@ -688,22 +760,22 @@ static int svc_rdma_pull_up_reply_msg(const struct svcxprt_rdma *rdma,
  * @rctxt: Write and Reply chunks provided by client
  * @xdr: prepared xdr_buf containing RPC message
  *
- * Load the xdr_buf into the ctxt's sge array, and DMA map each
- * element as it is added. The Send WR's num_sge field is set.
+ * Returns:
+ *   %0 if DMA mapping was successful.
+ *   %-EMSGSIZE if a buffer manipulation problem occurred
+ *   %-EIO if DMA mapping failed
  *
- * Returns zero on success, or a negative errno on failure.
+ * The Send WR's num_sge field is set in all cases.
  */
 int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
 			   struct svc_rdma_send_ctxt *sctxt,
 			   const struct svc_rdma_recv_ctxt *rctxt,
-			   struct xdr_buf *xdr)
+			   const struct xdr_buf *xdr)
 {
-	unsigned int len, remaining;
-	unsigned long page_off;
-	struct page **ppages;
-	unsigned char *base;
-	u32 xdr_pad;
-	int ret;
+	struct svc_rdma_map_data args = {
+		.md_rdma	= rdma,
+		.md_ctxt	= sctxt,
+	};
 
 	/* Set up the (persistently-mapped) transport header SGE. */
 	sctxt->sc_send_wr.num_sge = 1;
@@ -712,7 +784,7 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
 	/* If there is a Reply chunk, nothing follows the transport
 	 * header, and we're done here.
 	 */
-	if (rctxt && rctxt->rc_reply_chunk)
+	if (!pcl_is_empty(&rctxt->rc_reply_pcl))
 		return 0;
 
 	/* For pull-up, svc_rdma_send() will sync the transport header.
@@ -721,58 +793,8 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
 	if (svc_rdma_pull_up_needed(rdma, sctxt, rctxt, xdr))
 		return svc_rdma_pull_up_reply_msg(rdma, sctxt, rctxt, xdr);
 
-	++sctxt->sc_cur_sge_no;
-	ret = svc_rdma_dma_map_buf(rdma, sctxt,
-				   xdr->head[0].iov_base,
-				   xdr->head[0].iov_len);
-	if (ret < 0)
-		return ret;
-
-	/* If a Write chunk is present, the xdr_buf's page list
-	 * is not included inline. However the Upper Layer may
-	 * have added XDR padding in the tail buffer, and that
-	 * should not be included inline.
-	 */
-	if (rctxt && rctxt->rc_write_list) {
-		base = xdr->tail[0].iov_base;
-		len = xdr->tail[0].iov_len;
-		xdr_pad = xdr_pad_size(xdr->page_len);
-
-		if (len && xdr_pad) {
-			base += xdr_pad;
-			len -= xdr_pad;
-		}
-
-		goto tail;
-	}
-
-	ppages = xdr->pages + (xdr->page_base >> PAGE_SHIFT);
-	page_off = xdr->page_base & ~PAGE_MASK;
-	remaining = xdr->page_len;
-	while (remaining) {
-		len = min_t(u32, PAGE_SIZE - page_off, remaining);
-
-		++sctxt->sc_cur_sge_no;
-		ret = svc_rdma_dma_map_page(rdma, sctxt, *ppages++,
-					    page_off, len);
-		if (ret < 0)
-			return ret;
-
-		remaining -= len;
-		page_off = 0;
-	}
-
-	base = xdr->tail[0].iov_base;
-	len = xdr->tail[0].iov_len;
-tail:
-	if (len) {
-		++sctxt->sc_cur_sge_no;
-		ret = svc_rdma_dma_map_buf(rdma, sctxt, base, len);
-		if (ret < 0)
-			return ret;
-	}
-
-	return 0;
+	return pcl_process_nonpayloads(&rctxt->rc_write_pcl, xdr,
+				       svc_rdma_xb_dma_map, &args);
 }
 
 /* The svc_rqst and all resources it owns are released as soon as
-- 
cgit v1.2.3


From 41bc163ffe0fe67cba3fff2f5e8c58caa9e46a1e Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Mon, 9 Mar 2020 13:29:28 -0400
Subject: svcrdma: Support multiple Write chunks in svc_rdma_send_reply_chunk

Refactor svc_rdma_send_reply_chunk() so that it Sends only the parts
of rq_res that do not contain a result payload.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svc_rdma.h   |  2 +-
 net/sunrpc/xprtrdma/svc_rdma_rw.c | 36 +++++++++---------------------------
 2 files changed, 10 insertions(+), 28 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index e09fafba00d7..85fbec47d4b5 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -200,7 +200,7 @@ extern int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma,
 				     const struct xdr_buf *xdr);
 extern int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma,
 				     const struct svc_rdma_recv_ctxt *rctxt,
-				     struct xdr_buf *xdr);
+				     const struct xdr_buf *xdr);
 
 /* svc_rdma_sendto.c */
 extern void svc_rdma_send_ctxts_destroy(struct svcxprt_rdma *rdma);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c
index ed7def7b801b..4a0ece9aa385 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_rw.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c
@@ -537,7 +537,7 @@ static int svc_rdma_pages_write(struct svc_rdma_write_info *info,
 /**
  * svc_rdma_xb_write - Construct RDMA Writes to write an xdr_buf
  * @xdr: xdr_buf to write
- * @info: pointer to write arguments
+ * @data: pointer to write arguments
  *
  * Returns:
  *   On succes, returns zero
@@ -545,9 +545,9 @@ static int svc_rdma_pages_write(struct svc_rdma_write_info *info,
  *   %-ENOMEM if a resource has been exhausted
  *   %-EIO if an rdma-rw error occurred
  */
-static int svc_rdma_xb_write(const struct xdr_buf *xdr,
-			     struct svc_rdma_write_info *info)
+static int svc_rdma_xb_write(const struct xdr_buf *xdr, void *data)
 {
+	struct svc_rdma_write_info *info = data;
 	int ret;
 
 	if (xdr->head[0].iov_len) {
@@ -627,11 +627,11 @@ out_err:
  */
 int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma,
 			      const struct svc_rdma_recv_ctxt *rctxt,
-			      struct xdr_buf *xdr)
+			      const struct xdr_buf *xdr)
 {
 	struct svc_rdma_write_info *info;
 	struct svc_rdma_chunk *chunk;
-	int consumed, ret;
+	int ret;
 
 	if (pcl_is_empty(&rctxt->rc_reply_pcl))
 		return 0;
@@ -641,35 +641,17 @@ int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma,
 	if (!info)
 		return -ENOMEM;
 
-	ret = svc_rdma_iov_write(info, &xdr->head[0]);
+	ret = pcl_process_nonpayloads(&rctxt->rc_write_pcl, xdr,
+				      svc_rdma_xb_write, info);
 	if (ret < 0)
 		goto out_err;
-	consumed = xdr->head[0].iov_len;
-
-	/* Send the page list in the Reply chunk only if the
-	 * client did not provide Write chunks.
-	 */
-	if (pcl_is_empty(&rctxt->rc_write_pcl) && xdr->page_len) {
-		ret = svc_rdma_pages_write(info, xdr, xdr->head[0].iov_len,
-					   xdr->page_len);
-		if (ret < 0)
-			goto out_err;
-		consumed += xdr->page_len;
-	}
-
-	if (xdr->tail[0].iov_len) {
-		ret = svc_rdma_iov_write(info, &xdr->tail[0]);
-		if (ret < 0)
-			goto out_err;
-		consumed += xdr->tail[0].iov_len;
-	}
 
 	ret = svc_rdma_post_chunk_ctxt(&info->wi_cc);
 	if (ret < 0)
 		goto out_err;
 
-	trace_svcrdma_send_reply_chunk(consumed);
-	return consumed;
+	trace_svcrdma_send_reply_chunk(xdr->len);
+	return xdr->len;
 
 out_err:
 	svc_rdma_write_info_free(info);
-- 
cgit v1.2.3


From 7954c8503b8709660d93505a40f1847634d9c3ba Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 17 Jun 2020 15:19:36 -0400
Subject: svcrdma: Remove chunk list pointers

Clean up: These pointers are no longer used.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svc_rdma.h         | 4 ----
 net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 8 +-------
 2 files changed, 1 insertion(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 85fbec47d4b5..6f247d043731 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -149,12 +149,8 @@ struct svc_rdma_recv_ctxt {
 	struct svc_rdma_pcl	rc_call_pcl;
 
 	struct svc_rdma_pcl	rc_read_pcl;
-
-	__be32			*rc_write_list;
 	struct svc_rdma_chunk	*rc_cur_result_payload;
 	struct svc_rdma_pcl	rc_write_pcl;
-
-	__be32			*rc_reply_chunk;
 	struct svc_rdma_pcl	rc_reply_pcl;
 
 	struct page		*rc_pages[RPCSVC_MAXPAGES];
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index af32c3ad45a6..dd10b1de227d 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -540,17 +540,13 @@ static bool xdr_check_write_list(struct svc_rdma_recv_ctxt *rctxt)
 	p = xdr_inline_decode(&rctxt->rc_stream, sizeof(*p));
 	if (!p)
 		return false;
-
-	rctxt->rc_write_list = NULL;
 	if (!xdr_count_write_chunks(rctxt, p))
 		return false;
 	if (!pcl_alloc_write(rctxt, &rctxt->rc_write_pcl, p))
 		return false;
 
-	if (!pcl_is_empty(&rctxt->rc_write_pcl))
-		rctxt->rc_write_list = p;
 	rctxt->rc_cur_result_payload = pcl_first_chunk(&rctxt->rc_write_pcl);
-	return rctxt->rc_write_pcl.cl_count < 2;
+	return true;
 }
 
 /* Sanity check the Reply chunk.
@@ -573,13 +569,11 @@ static bool xdr_check_reply_chunk(struct svc_rdma_recv_ctxt *rctxt)
 	if (!p)
 		return false;
 
-	rctxt->rc_reply_chunk = NULL;
 	if (!xdr_item_is_present(p))
 		return true;
 	if (!xdr_check_write_chunk(rctxt))
 		return false;
 
-	rctxt->rc_reply_chunk = p;
 	rctxt->rc_reply_pcl.cl_count = 1;
 	return pcl_alloc_write(rctxt, &rctxt->rc_reply_pcl, p);
 }
-- 
cgit v1.2.3


From d96962e6d0e281bab6a48e83b42f5dce6eb28bf4 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 17 Sep 2020 13:04:17 -0400
Subject: svcrdma: Use the new parsed chunk list when pulling Read chunks

As a pre-requisite for handling multiple Read chunks in each Read
list, convert svc_rdma_recv_read_chunk() to use the new parsed Read
chunk list.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svc_rdma.h         |   6 +-
 net/sunrpc/xprtrdma/svc_rdma_recvfrom.c |  16 ++--
 net/sunrpc/xprtrdma/svc_rdma_rw.c       | 160 ++++++++++++++++++++------------
 3 files changed, 111 insertions(+), 71 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 6f247d043731..294b56e61522 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -188,15 +188,15 @@ extern int svc_rdma_recvfrom(struct svc_rqst *);
 
 /* svc_rdma_rw.c */
 extern void svc_rdma_destroy_rw_ctxts(struct svcxprt_rdma *rdma);
-extern int svc_rdma_recv_read_chunk(struct svcxprt_rdma *rdma,
-				    struct svc_rqst *rqstp,
-				    struct svc_rdma_recv_ctxt *head, __be32 *p);
 extern int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma,
 				     const struct svc_rdma_chunk *chunk,
 				     const struct xdr_buf *xdr);
 extern int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma,
 				     const struct svc_rdma_recv_ctxt *rctxt,
 				     const struct xdr_buf *xdr);
+extern int svc_rdma_process_read_list(struct svcxprt_rdma *rdma,
+				      struct svc_rqst *rqstp,
+				      struct svc_rdma_recv_ctxt *head);
 
 /* svc_rdma_sendto.c */
 extern void svc_rdma_send_ctxts_destroy(struct svcxprt_rdma *rdma);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index dd10b1de227d..cbdb71247755 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -824,7 +824,6 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 	struct svcxprt_rdma *rdma_xprt =
 		container_of(xprt, struct svcxprt_rdma, sc_xprt);
 	struct svc_rdma_recv_ctxt *ctxt;
-	__be32 *p;
 	int ret;
 
 	rqstp->rq_xprt_ctxt = NULL;
@@ -857,7 +856,6 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 	rqstp->rq_respages = rqstp->rq_pages;
 	rqstp->rq_next_page = rqstp->rq_respages;
 
-	p = (__be32 *)rqstp->rq_arg.head[0].iov_base;
 	ret = svc_rdma_xdr_decode_req(&rqstp->rq_arg, ctxt);
 	if (ret < 0)
 		goto out_err;
@@ -870,9 +868,9 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 
 	svc_rdma_get_inv_rkey(rdma_xprt, ctxt);
 
-	p += rpcrdma_fixed_maxsz;
-	if (*p != xdr_zero)
-		goto out_readchunk;
+	if (!pcl_is_empty(&ctxt->rc_read_pcl) ||
+	    !pcl_is_empty(&ctxt->rc_call_pcl))
+		goto out_readlist;
 
 complete:
 	rqstp->rq_xprt_ctxt = ctxt;
@@ -880,10 +878,10 @@ complete:
 	svc_xprt_copy_addrs(rqstp, xprt);
 	return rqstp->rq_arg.len;
 
-out_readchunk:
-	ret = svc_rdma_recv_read_chunk(rdma_xprt, rqstp, ctxt, p);
+out_readlist:
+	ret = svc_rdma_process_read_list(rdma_xprt, rqstp, ctxt);
 	if (ret < 0)
-		goto out_postfail;
+		goto out_readfail;
 	return 0;
 
 out_err:
@@ -891,7 +889,7 @@ out_err:
 	svc_rdma_recv_ctxt_put(rdma_xprt, ctxt);
 	return 0;
 
-out_postfail:
+out_readfail:
 	if (ret == -EINVAL)
 		svc_rdma_send_error(rdma_xprt, ctxt, ret);
 	svc_rdma_recv_ctxt_put(rdma_xprt, ctxt);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c
index 3154c7ab1ca8..2d454e37b2fe 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_rw.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c
@@ -258,8 +258,8 @@ static void svc_rdma_write_done(struct ib_cq *cq, struct ib_wc *wc)
 /* State for pulling a Read chunk.
  */
 struct svc_rdma_read_info {
+	struct svc_rqst			*ri_rqst;
 	struct svc_rdma_recv_ctxt	*ri_readctxt;
-	unsigned int			ri_position;
 	unsigned int			ri_pageno;
 	unsigned int			ri_pageoff;
 	unsigned int			ri_totalbytes;
@@ -658,17 +658,29 @@ out_err:
 	return ret;
 }
 
+/**
+ * svc_rdma_build_read_segment - Build RDMA Read WQEs to pull one RDMA segment
+ * @info: context for ongoing I/O
+ * @segment: co-ordinates of remote memory to be read
+ *
+ * Returns:
+ *   %0: the Read WR chain was constructed successfully
+ *   %-EINVAL: there were not enough rq_pages to finish
+ *   %-ENOMEM: allocating a local resources failed
+ *   %-EIO: a DMA mapping error occurred
+ */
 static int svc_rdma_build_read_segment(struct svc_rdma_read_info *info,
-				       struct svc_rqst *rqstp,
-				       u32 rkey, u32 len, u64 offset)
+				       const struct svc_rdma_segment *segment)
 {
 	struct svc_rdma_recv_ctxt *head = info->ri_readctxt;
 	struct svc_rdma_chunk_ctxt *cc = &info->ri_cc;
+	struct svc_rqst *rqstp = info->ri_rqst;
 	struct svc_rdma_rw_ctxt *ctxt;
-	unsigned int sge_no, seg_len;
+	unsigned int sge_no, seg_len, len;
 	struct scatterlist *sg;
 	int ret;
 
+	len = segment->rs_length;
 	sge_no = PAGE_ALIGN(info->ri_pageoff + len) >> PAGE_SHIFT;
 	ctxt = svc_rdma_get_rw_ctxt(cc->cc_rdma, sge_no);
 	if (!ctxt)
@@ -702,8 +714,8 @@ static int svc_rdma_build_read_segment(struct svc_rdma_read_info *info,
 			goto out_overrun;
 	}
 
-	ret = svc_rdma_rw_ctx_init(cc->cc_rdma, ctxt, offset, rkey,
-				   DMA_FROM_DEVICE);
+	ret = svc_rdma_rw_ctx_init(cc->cc_rdma, ctxt, segment->rs_offset,
+				   segment->rs_handle, DMA_FROM_DEVICE);
 	if (ret < 0)
 		return -EIO;
 
@@ -716,48 +728,63 @@ out_overrun:
 	return -EINVAL;
 }
 
-/* Walk the segments in the Read chunk starting at @p and construct
- * RDMA Read operations to pull the chunk to the server.
+/**
+ * svc_rdma_build_read_chunk - Build RDMA Read WQEs to pull one RDMA chunk
+ * @info: context for ongoing I/O
+ * @chunk: Read chunk to pull
+ *
+ * Return values:
+ *   %0: the Read WR chain was constructed successfully
+ *   %-EINVAL: there were not enough resources to finish
+ *   %-ENOMEM: allocating a local resources failed
+ *   %-EIO: a DMA mapping error occurred
  */
-static int svc_rdma_build_read_chunk(struct svc_rqst *rqstp,
-				     struct svc_rdma_read_info *info,
-				     __be32 *p)
+static int svc_rdma_build_read_chunk(struct svc_rdma_read_info *info,
+				     const struct svc_rdma_chunk *chunk)
 {
+	const struct svc_rdma_segment *segment;
 	int ret;
 
 	ret = -EINVAL;
-	while (*p++ != xdr_zero && be32_to_cpup(p++) == info->ri_position) {
-		u32 handle, length;
-		u64 offset;
-
-		p = xdr_decode_rdma_segment(p, &handle, &length, &offset);
-		ret = svc_rdma_build_read_segment(info, rqstp, handle, length,
-						  offset);
+	pcl_for_each_segment(segment, chunk) {
+		ret = svc_rdma_build_read_segment(info, segment);
 		if (ret < 0)
 			break;
-
-		info->ri_totalbytes += length;
+		info->ri_totalbytes += segment->rs_length;
 	}
 	return ret;
 }
 
-/* Construct RDMA Reads to pull over a normal Read chunk. The chunk
- * data lands in the page list of head->rc_arg.pages.
+/**
+ * svc_rdma_read_data_items - Construct RDMA Reads to pull data item Read chunks
+ * @info: context for RDMA Reads
+ *
+ * The chunk data lands in the page list of head->rc_arg.pages.
  *
  * Currently NFSD does not look at the head->rc_arg.tail[0] iovec.
  * Therefore, XDR round-up of the Read chunk and trailing
  * inline content must both be added at the end of the pagelist.
+ *
+ * Return values:
+ *   %0: RDMA Read WQEs were successfully built
+ *   %-EINVAL: client provided too many chunks or segments,
+ *   %-ENOMEM: rdma_rw context pool was exhausted,
+ *   %-ENOTCONN: posting failed (connection is lost),
+ *   %-EIO: rdma_rw initialization failed (DMA mapping, etc).
  */
-static int svc_rdma_build_normal_read_chunk(struct svc_rqst *rqstp,
-					    struct svc_rdma_read_info *info,
-					    __be32 *p)
+static int svc_rdma_read_data_items(struct svc_rdma_read_info *info)
 {
 	struct svc_rdma_recv_ctxt *head = info->ri_readctxt;
 	struct xdr_buf *buf = &head->rc_arg;
+	struct svc_rdma_chunk *chunk;
 	unsigned int length;
 	int ret;
 
-	ret = svc_rdma_build_read_chunk(rqstp, info, p);
+	if (head->rc_read_pcl.cl_count > 1)
+		return -EINVAL;
+
+	chunk = pcl_first_chunk(&head->rc_read_pcl);
+	ret = svc_rdma_build_read_chunk(info, chunk);
 	if (ret < 0)
 		goto out;
 
@@ -768,11 +795,9 @@ static int svc_rdma_build_normal_read_chunk(struct svc_rqst *rqstp,
 	 * chunk is not included in either the pagelist or in
 	 * the tail.
 	 */
-	head->rc_arg.tail[0].iov_base =
-		head->rc_arg.head[0].iov_base + info->ri_position;
-	head->rc_arg.tail[0].iov_len =
-		head->rc_arg.head[0].iov_len - info->ri_position;
-	head->rc_arg.head[0].iov_len = info->ri_position;
+	buf->tail[0].iov_base = buf->head[0].iov_base + chunk->ch_position;
+	buf->tail[0].iov_len = buf->head[0].iov_len - chunk->ch_position;
+	buf->head[0].iov_len = chunk->ch_position;
 
 	/* Read chunk may need XDR roundup (see RFC 8166, s. 3.4.5.2).
 	 *
@@ -792,26 +817,36 @@ out:
 	return ret;
 }
 
-/* Construct RDMA Reads to pull over a Position Zero Read chunk.
- * The start of the data lands in the first page just after
- * the Transport header, and the rest lands in the page list of
+/**
+ * svc_rdma_read_special - Build RDMA Read WQEs to pull a Long Message
+ * @info: context for RDMA Reads
+ *
+ * The start of the data lands in the first page just after the
+ * Transport header, and the rest lands in the page list of
  * head->rc_arg.pages.
  *
  * Assumptions:
- *	- A PZRC has an XDR-aligned length (no implicit round-up).
- *	- There can be no trailing inline content (IOW, we assume
- *	  a PZRC is never sent in an RDMA_MSG message, though it's
- *	  allowed by spec).
+ *	- A PZRC is never sent in an RDMA_MSG message, though it's
+ *	  allowed by spec.
+ *
+ * Return values:
+ *   %0: RDMA Read WQEs were successfully built
+ *   %-EINVAL: client provided too many chunks or segments,
+ *   %-ENOMEM: rdma_rw context pool was exhausted,
+ *   %-ENOTCONN: posting failed (connection is lost),
+ *   %-EIO: rdma_rw initialization failed (DMA mapping, etc).
  */
-static int svc_rdma_build_pz_read_chunk(struct svc_rqst *rqstp,
-					struct svc_rdma_read_info *info,
-					__be32 *p)
+static int svc_rdma_read_special(struct svc_rdma_read_info *info)
 {
 	struct svc_rdma_recv_ctxt *head = info->ri_readctxt;
 	struct xdr_buf *buf = &head->rc_arg;
 	int ret;
 
-	ret = svc_rdma_build_read_chunk(rqstp, info, p);
+	if (head->rc_call_pcl.cl_count > 1)
+		return -EINVAL;
+
+	ret = svc_rdma_build_read_chunk(info,
+					pcl_first_chunk(&head->rc_call_pcl));
 	if (ret < 0)
 		goto out;
 
@@ -848,24 +883,31 @@ static void svc_rdma_save_io_pages(struct svc_rqst *rqstp,
 }
 
 /**
- * svc_rdma_recv_read_chunk - Pull a Read chunk from the client
+ * svc_rdma_process_read_list - Pull list of Read chunks from the client
  * @rdma: controlling RDMA transport
  * @rqstp: set of pages to use as Read sink buffers
  * @head: pages under I/O collect here
- * @p: pointer to start of Read chunk
  *
- * Returns:
- *	%0 if all needed RDMA Reads were posted successfully,
- *	%-EINVAL if client provided too many segments,
- *	%-ENOMEM if rdma_rw context pool was exhausted,
- *	%-ENOTCONN if posting failed (connection is lost),
- *	%-EIO if rdma_rw initialization failed (DMA mapping, etc).
+ * The RPC/RDMA protocol assumes that the upper layer's XDR decoders
+ * pull each Read chunk as they decode an incoming RPC message.
  *
- * Assumptions:
- * - All Read segments in @p have the same Position value.
+ * On Linux, however, the server needs to have a fully-constructed RPC
+ * message in rqstp->rq_arg when there is a positive return code from
+ * ->xpo_recvfrom. So the Read list is safety-checked immediately when
+ * it is received, then here the whole Read list is pulled all at once.
+ * The ingress RPC message is fully reconstructed once all associated
+ * RDMA Reads have completed.
+ *
+ * Return values:
+ *   %1: all needed RDMA Reads were posted successfully,
+ *   %-EINVAL: client provided too many chunks or segments,
+ *   %-ENOMEM: rdma_rw context pool was exhausted,
+ *   %-ENOTCONN: posting failed (connection is lost),
+ *   %-EIO: rdma_rw initialization failed (DMA mapping, etc).
  */
-int svc_rdma_recv_read_chunk(struct svcxprt_rdma *rdma, struct svc_rqst *rqstp,
-			     struct svc_rdma_recv_ctxt *head, __be32 *p)
+int svc_rdma_process_read_list(struct svcxprt_rdma *rdma,
+			       struct svc_rqst *rqstp,
+			       struct svc_rdma_recv_ctxt *head)
 {
 	struct svc_rdma_read_info *info;
 	struct svc_rdma_chunk_ctxt *cc;
@@ -887,16 +929,16 @@ int svc_rdma_recv_read_chunk(struct svcxprt_rdma *rdma, struct svc_rqst *rqstp,
 	if (!info)
 		return -ENOMEM;
 	cc = &info->ri_cc;
+	info->ri_rqst = rqstp;
 	info->ri_readctxt = head;
 	info->ri_pageno = 0;
 	info->ri_pageoff = 0;
 	info->ri_totalbytes = 0;
 
-	info->ri_position = be32_to_cpup(p + 1);
-	if (info->ri_position)
-		ret = svc_rdma_build_normal_read_chunk(rqstp, info, p);
+	if (pcl_is_empty(&head->rc_call_pcl))
+		ret = svc_rdma_read_data_items(info);
 	else
-		ret = svc_rdma_build_pz_read_chunk(rqstp, info, p);
+		ret = svc_rdma_read_special(info);
 	if (ret < 0)
 		goto out_err;
 
@@ -905,7 +947,7 @@ int svc_rdma_recv_read_chunk(struct svcxprt_rdma *rdma, struct svc_rqst *rqstp,
 	if (ret < 0)
 		goto out_err;
 	svc_rdma_save_io_pages(rqstp, 0, head->rc_page_count);
-	return 0;
+	return 1;
 
 out_err:
 	svc_rdma_read_info_free(info);
-- 
cgit v1.2.3


From 0ae4c3e8a64ace1b8d7de033b0751afe43024416 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 11 Nov 2020 15:52:47 -0500
Subject: SUNRPC: Add xdr_set_scratch_page() and xdr_reset_scratch_buffer()

Clean up: De-duplicate some frequently-used code.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfs/blocklayout/blocklayout.c          |  2 +-
 fs/nfs/blocklayout/dev.c                  |  2 +-
 fs/nfs/dir.c                              |  2 +-
 fs/nfs/filelayout/filelayout.c            |  2 +-
 fs/nfs/filelayout/filelayoutdev.c         |  2 +-
 fs/nfs/flexfilelayout/flexfilelayout.c    |  2 +-
 fs/nfs/flexfilelayout/flexfilelayoutdev.c |  2 +-
 fs/nfs/nfs42xdr.c                         |  2 +-
 fs/nfs/nfs4xdr.c                          |  6 ++---
 fs/nfsd/nfs4proc.c                        |  2 +-
 include/linux/sunrpc/xdr.h                | 44 ++++++++++++++++++++++++++++++-
 net/sunrpc/auth_gss/gss_rpc_xdr.c         |  2 +-
 net/sunrpc/xdr.c                          | 28 +++-----------------
 13 files changed, 59 insertions(+), 39 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 08108b6d2fa1..3be6836074ae 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -697,7 +697,7 @@ bl_alloc_lseg(struct pnfs_layout_hdr *lo, struct nfs4_layoutget_res *lgr,
 
 	xdr_init_decode_pages(&xdr, &buf,
 			lgr->layoutp->pages, lgr->layoutp->len);
-	xdr_set_scratch_buffer(&xdr, page_address(scratch), PAGE_SIZE);
+	xdr_set_scratch_page(&xdr, scratch);
 
 	status = -EIO;
 	p = xdr_inline_decode(&xdr, 4);
diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c
index dec5880ac6de..acb1d22907da 100644
--- a/fs/nfs/blocklayout/dev.c
+++ b/fs/nfs/blocklayout/dev.c
@@ -510,7 +510,7 @@ bl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 		goto out;
 
 	xdr_init_decode_pages(&xdr, &buf, pdev->pages, pdev->pglen);
-	xdr_set_scratch_buffer(&xdr, page_address(scratch), PAGE_SIZE);
+	xdr_set_scratch_page(&xdr, scratch);
 
 	p = xdr_inline_decode(&xdr, sizeof(__be32));
 	if (!p)
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 4e011adaf967..8a24fe20dccf 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -576,7 +576,7 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en
 		goto out_nopages;
 
 	xdr_init_decode_pages(&stream, &buf, xdr_pages, buflen);
-	xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
+	xdr_set_scratch_page(&stream, scratch);
 
 	do {
 		if (entry->label)
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index 7f5aa0403e16..d158a500c25c 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -666,7 +666,7 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo,
 		return -ENOMEM;
 
 	xdr_init_decode_pages(&stream, &buf, lgr->layoutp->pages, lgr->layoutp->len);
-	xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
+	xdr_set_scratch_page(&stream, scratch);
 
 	/* 20 = ufl_util (4), first_stripe_index (4), pattern_offset (8),
 	 * num_fh (4) */
diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c
index d913e818858f..86c3f7e69ec4 100644
--- a/fs/nfs/filelayout/filelayoutdev.c
+++ b/fs/nfs/filelayout/filelayoutdev.c
@@ -82,7 +82,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 		goto out_err;
 
 	xdr_init_decode_pages(&stream, &buf, pdev->pages, pdev->pglen);
-	xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
+	xdr_set_scratch_page(&stream, scratch);
 
 	/* Get the stripe count (number of stripe index) */
 	p = xdr_inline_decode(&stream, 4);
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index a163533446fa..d7010686d39a 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -378,7 +378,7 @@ ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh,
 
 	xdr_init_decode_pages(&stream, &buf, lgr->layoutp->pages,
 			      lgr->layoutp->len);
-	xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
+	xdr_set_scratch_page(&stream, scratch);
 
 	/* stripe unit and mirror_array_cnt */
 	rc = -EIO;
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
index 3eda40a320a5..c9b61b818ec1 100644
--- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -69,7 +69,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 	INIT_LIST_HEAD(&dsaddrs);
 
 	xdr_init_decode_pages(&stream, &buf, pdev->pages, pdev->pglen);
-	xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
+	xdr_set_scratch_page(&stream, scratch);
 
 	/* multipath count */
 	p = xdr_inline_decode(&stream, 4);
diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index 6e060a88f98c..cb5d4da2308f 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -1540,7 +1540,7 @@ static int nfs4_xdr_dec_listxattrs(struct rpc_rqst *rqstp,
 	struct compound_hdr hdr;
 	int status;
 
-	xdr_set_scratch_buffer(xdr, page_address(res->scratch), PAGE_SIZE);
+	xdr_set_scratch_page(xdr, res->scratch);
 
 	status = decode_compound_hdr(xdr, &hdr);
 	if (status)
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index c6dbfcae7517..2eabe5add344 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -6403,10 +6403,8 @@ nfs4_xdr_dec_getacl(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	struct compound_hdr hdr;
 	int status;
 
-	if (res->acl_scratch != NULL) {
-		void *p = page_address(res->acl_scratch);
-		xdr_set_scratch_buffer(xdr, p, PAGE_SIZE);
-	}
+	if (res->acl_scratch != NULL)
+		xdr_set_scratch_page(xdr, res->acl_scratch);
 	status = decode_compound_hdr(xdr, &hdr);
 	if (status)
 		goto out;
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index e83b21778816..20772f6b0b2d 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -2276,7 +2276,7 @@ static void svcxdr_init_encode(struct svc_rqst *rqstp,
 	xdr->end = head->iov_base + PAGE_SIZE - rqstp->rq_auth_slack;
 	/* Tail and page_len should be zero at this point: */
 	buf->len = buf->head[0].iov_len;
-	xdr->scratch.iov_len = 0;
+	xdr_reset_scratch_buffer(xdr);
 	xdr->page_ptr = buf->pages - 1;
 	buf->buflen = PAGE_SIZE * (1 + rqstp->rq_page_end - buf->pages)
 		- rqstp->rq_auth_slack;
diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index ec2a22ccdc2a..2729d2d6efce 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -248,7 +248,6 @@ extern void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf,
 			    __be32 *p, struct rpc_rqst *rqst);
 extern void xdr_init_decode_pages(struct xdr_stream *xdr, struct xdr_buf *buf,
 		struct page **pages, unsigned int len);
-extern void xdr_set_scratch_buffer(struct xdr_stream *xdr, void *buf, size_t buflen);
 extern __be32 *xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes);
 extern unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len);
 extern void xdr_enter_page(struct xdr_stream *xdr, unsigned int len);
@@ -256,6 +255,49 @@ extern int xdr_process_buf(struct xdr_buf *buf, unsigned int offset, unsigned in
 extern uint64_t xdr_align_data(struct xdr_stream *, uint64_t, uint32_t);
 extern uint64_t xdr_expand_hole(struct xdr_stream *, uint64_t, uint64_t);
 
+/**
+ * xdr_set_scratch_buffer - Attach a scratch buffer for decoding data.
+ * @xdr: pointer to xdr_stream struct
+ * @buf: pointer to an empty buffer
+ * @buflen: size of 'buf'
+ *
+ * The scratch buffer is used when decoding from an array of pages.
+ * If an xdr_inline_decode() call spans across page boundaries, then
+ * we copy the data into the scratch buffer in order to allow linear
+ * access.
+ */
+static inline void
+xdr_set_scratch_buffer(struct xdr_stream *xdr, void *buf, size_t buflen)
+{
+	xdr->scratch.iov_base = buf;
+	xdr->scratch.iov_len = buflen;
+}
+
+/**
+ * xdr_set_scratch_page - Attach a scratch buffer for decoding data
+ * @xdr: pointer to xdr_stream struct
+ * @page: an anonymous page
+ *
+ * See xdr_set_scratch_buffer().
+ */
+static inline void
+xdr_set_scratch_page(struct xdr_stream *xdr, struct page *page)
+{
+	xdr_set_scratch_buffer(xdr, page_address(page), PAGE_SIZE);
+}
+
+/**
+ * xdr_reset_scratch_buffer - Clear scratch buffer information
+ * @xdr: pointer to xdr_stream struct
+ *
+ * See xdr_set_scratch_buffer().
+ */
+static inline void
+xdr_reset_scratch_buffer(struct xdr_stream *xdr)
+{
+	xdr_set_scratch_buffer(xdr, NULL, 0);
+}
+
 /**
  * xdr_stream_remaining - Return the number of bytes remaining in the stream
  * @xdr: pointer to struct xdr_stream
diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c
index 2ff7b7083eba..c636c648849b 100644
--- a/net/sunrpc/auth_gss/gss_rpc_xdr.c
+++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c
@@ -789,7 +789,7 @@ int gssx_dec_accept_sec_context(struct rpc_rqst *rqstp,
 	scratch = alloc_page(GFP_KERNEL);
 	if (!scratch)
 		return -ENOMEM;
-	xdr_set_scratch_buffer(xdr, page_address(scratch), PAGE_SIZE);
+	xdr_set_scratch_page(xdr, scratch);
 
 	/* res->status */
 	err = gssx_dec_status(xdr, &res->status);
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 28f81769a27c..c607744b3ea8 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -669,7 +669,7 @@ void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p,
 	struct kvec *iov = buf->head;
 	int scratch_len = buf->buflen - buf->page_len - buf->tail[0].iov_len;
 
-	xdr_set_scratch_buffer(xdr, NULL, 0);
+	xdr_reset_scratch_buffer(xdr);
 	BUG_ON(scratch_len < 0);
 	xdr->buf = buf;
 	xdr->iov = iov;
@@ -713,7 +713,7 @@ inline void xdr_commit_encode(struct xdr_stream *xdr)
 	page = page_address(*xdr->page_ptr);
 	memcpy(xdr->scratch.iov_base, page, shift);
 	memmove(page, page + shift, (void *)xdr->p - page);
-	xdr->scratch.iov_len = 0;
+	xdr_reset_scratch_buffer(xdr);
 }
 EXPORT_SYMBOL_GPL(xdr_commit_encode);
 
@@ -743,8 +743,7 @@ static __be32 *xdr_get_next_encode_buffer(struct xdr_stream *xdr,
 	 * the "scratch" iov to track any temporarily unused fragment of
 	 * space at the end of the previous buffer:
 	 */
-	xdr->scratch.iov_base = xdr->p;
-	xdr->scratch.iov_len = frag1bytes;
+	xdr_set_scratch_buffer(xdr, xdr->p, frag1bytes);
 	p = page_address(*xdr->page_ptr);
 	/*
 	 * Note this is where the next encode will start after we've
@@ -1052,8 +1051,7 @@ void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p,
 		     struct rpc_rqst *rqst)
 {
 	xdr->buf = buf;
-	xdr->scratch.iov_base = NULL;
-	xdr->scratch.iov_len = 0;
+	xdr_reset_scratch_buffer(xdr);
 	xdr->nwords = XDR_QUADLEN(buf->len);
 	if (buf->head[0].iov_len != 0)
 		xdr_set_iov(xdr, buf->head, buf->len);
@@ -1101,24 +1099,6 @@ static __be32 * __xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes)
 	return p;
 }
 
-/**
- * xdr_set_scratch_buffer - Attach a scratch buffer for decoding data.
- * @xdr: pointer to xdr_stream struct
- * @buf: pointer to an empty buffer
- * @buflen: size of 'buf'
- *
- * The scratch buffer is used when decoding from an array of pages.
- * If an xdr_inline_decode() call spans across page boundaries, then
- * we copy the data into the scratch buffer in order to allow linear
- * access.
- */
-void xdr_set_scratch_buffer(struct xdr_stream *xdr, void *buf, size_t buflen)
-{
-	xdr->scratch.iov_base = buf;
-	xdr->scratch.iov_len = buflen;
-}
-EXPORT_SYMBOL_GPL(xdr_set_scratch_buffer);
-
 static __be32 *xdr_copy_to_scratch(struct xdr_stream *xdr, size_t nbytes)
 {
 	__be32 *p;
-- 
cgit v1.2.3


From 5191955d6fc65e6d4efe8f4f10a6028298f57281 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 5 Nov 2020 11:19:42 -0500
Subject: SUNRPC: Prepare for xdr_stream-style decoding on the server-side

A "permanent" struct xdr_stream is allocated in struct svc_rqst so
that it is usable by all server-side decoders. A per-rqst scratch
buffer is also allocated to handle decoding XDR data items that
cross page boundaries.

To demonstrate how it will be used, add the first call site for the
new svcxdr_init_decode() API.

As an additional part of the overall conversion, add symbolic
constants for successful and failed XDR operations. Returning "0" is
overloaded. Sometimes it means something failed, but sometimes it
means success. To make it more clear when XDR decoding functions
succeed or fail, introduce symbolic constants.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfssvc.c           |  2 ++
 include/linux/sunrpc/svc.h | 16 ++++++++++++++++
 net/sunrpc/svc.c           |  5 +++++
 3 files changed, 23 insertions(+)

(limited to 'include/linux')

diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 27b1ad136150..74d5e58eadb0 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -1020,6 +1020,8 @@ int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 	 * (necessary in the NFSv4.0 compound case)
 	 */
 	rqstp->rq_cachetype = proc->pc_cachetype;
+
+	svcxdr_init_decode(rqstp);
 	if (!proc->pc_decode(rqstp, argv->iov_base))
 		goto out_decode_err;
 
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index c220b734fa69..34c2a69820e9 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -247,6 +247,8 @@ struct svc_rqst {
 
 	size_t			rq_xprt_hlen;	/* xprt header len */
 	struct xdr_buf		rq_arg;
+	struct xdr_stream	rq_arg_stream;
+	struct page		*rq_scratch_page;
 	struct xdr_buf		rq_res;
 	struct page		*rq_pages[RPCSVC_MAXPAGES + 1];
 	struct page *		*rq_respages;	/* points into rq_pages */
@@ -557,4 +559,18 @@ static inline void svc_reserve_auth(struct svc_rqst *rqstp, int space)
 	svc_reserve(rqstp, space + rqstp->rq_auth_slack);
 }
 
+/**
+ * svcxdr_init_decode - Prepare an xdr_stream for svc Call decoding
+ * @rqstp: controlling server RPC transaction context
+ *
+ */
+static inline void svcxdr_init_decode(struct svc_rqst *rqstp)
+{
+	struct xdr_stream *xdr = &rqstp->rq_arg_stream;
+	struct kvec *argv = rqstp->rq_arg.head;
+
+	xdr_init_decode(xdr, &rqstp->rq_arg, argv->iov_base, NULL);
+	xdr_set_scratch_page(xdr, rqstp->rq_scratch_page);
+}
+
 #endif /* SUNRPC_SVC_H */
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index b41500645c3f..4187745887f0 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -614,6 +614,10 @@ svc_rqst_alloc(struct svc_serv *serv, struct svc_pool *pool, int node)
 	rqstp->rq_server = serv;
 	rqstp->rq_pool = pool;
 
+	rqstp->rq_scratch_page = alloc_pages_node(node, GFP_KERNEL, 0);
+	if (!rqstp->rq_scratch_page)
+		goto out_enomem;
+
 	rqstp->rq_argp = kmalloc_node(serv->sv_xdrsize, GFP_KERNEL, node);
 	if (!rqstp->rq_argp)
 		goto out_enomem;
@@ -842,6 +846,7 @@ void
 svc_rqst_free(struct svc_rqst *rqstp)
 {
 	svc_release_buffer(rqstp);
+	put_page(rqstp->rq_scratch_page);
 	kfree(rqstp->rq_resp);
 	kfree(rqstp->rq_argp);
 	kfree(rqstp->rq_auth_data);
-- 
cgit v1.2.3


From c1346a1216ab5cb04a265380ac9035d91b16b6d5 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Tue, 3 Nov 2020 11:54:23 -0500
Subject: NFSD: Replace the internals of the READ_BUF() macro

Convert the READ_BUF macro in nfs4xdr.c from open code to instead
use the new xdr_stream-style decoders already in use by the encode
side (and by the in-kernel NFS client implementation). Once this
conversion is done, each individual NFSv4 argument decoder can be
independently cleaned up to replace these macros with C code.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4proc.c         |   4 +-
 fs/nfsd/nfs4xdr.c          | 181 +++++++--------------------------------------
 fs/nfsd/xdr4.h             |  10 +--
 include/linux/sunrpc/xdr.h |   2 +
 net/sunrpc/xdr.c           |  45 +++++++++++
 5 files changed, 77 insertions(+), 165 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 76300b0441f0..df2d6f70c8d4 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1023,8 +1023,8 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	write->wr_how_written = write->wr_stable_how;
 
-	nvecs = svc_fill_write_vector(rqstp, write->wr_pagelist,
-				      &write->wr_head, write->wr_buflen);
+	nvecs = svc_fill_write_vector(rqstp, write->wr_payload.pages,
+				      write->wr_payload.head, write->wr_buflen);
 	WARN_ON_ONCE(nvecs > ARRAY_SIZE(rqstp->rq_vec));
 
 	status = nfsd_vfs_write(rqstp, &cstate->current_fh, nf,
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 66edac748272..e3a2912c5e56 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -131,90 +131,13 @@ xdr_error:					\
 	memcpy((x), p, nbytes);			\
 	p += XDR_QUADLEN(nbytes);		\
 } while (0)
-
-/* READ_BUF, read_buf(): nbytes must be <= PAGE_SIZE */
-#define READ_BUF(nbytes)  do {			\
-	if (nbytes <= (u32)((char *)argp->end - (char *)argp->p)) {	\
-		p = argp->p;			\
-		argp->p += XDR_QUADLEN(nbytes);	\
-	} else if (!(p = read_buf(argp, nbytes))) { \
-		dprintk("NFSD: xdr error (%s:%d)\n", \
-				__FILE__, __LINE__); \
-		goto xdr_error;			\
-	}					\
-} while (0)
-
-static void next_decode_page(struct nfsd4_compoundargs *argp)
-{
-	argp->p = page_address(argp->pagelist[0]);
-	argp->pagelist++;
-	if (argp->pagelen < PAGE_SIZE) {
-		argp->end = argp->p + XDR_QUADLEN(argp->pagelen);
-		argp->pagelen = 0;
-	} else {
-		argp->end = argp->p + (PAGE_SIZE>>2);
-		argp->pagelen -= PAGE_SIZE;
-	}
-}
-
-static __be32 *read_buf(struct nfsd4_compoundargs *argp, u32 nbytes)
-{
-	/* We want more bytes than seem to be available.
-	 * Maybe we need a new page, maybe we have just run out
-	 */
-	unsigned int avail = (char *)argp->end - (char *)argp->p;
-	__be32 *p;
-
-	if (argp->pagelen == 0) {
-		struct kvec *vec = &argp->rqstp->rq_arg.tail[0];
-
-		if (!argp->tail) {
-			argp->tail = true;
-			avail = vec->iov_len;
-			argp->p = vec->iov_base;
-			argp->end = vec->iov_base + avail;
-		}
-
-		if (avail < nbytes)
-			return NULL;
-
-		p = argp->p;
-		argp->p += XDR_QUADLEN(nbytes);
-		return p;
-	}
-
-	if (avail + argp->pagelen < nbytes)
-		return NULL;
-	if (avail + PAGE_SIZE < nbytes) /* need more than a page !! */
-		return NULL;
-	/* ok, we can do it with the current plus the next page */
-	if (nbytes <= sizeof(argp->tmp))
-		p = argp->tmp;
-	else {
-		kfree(argp->tmpp);
-		p = argp->tmpp = kmalloc(nbytes, GFP_KERNEL);
-		if (!p)
-			return NULL;
-		
-	}
-	/*
-	 * The following memcpy is safe because read_buf is always
-	 * called with nbytes > avail, and the two cases above both
-	 * guarantee p points to at least nbytes bytes.
-	 */
-	memcpy(p, argp->p, avail);
-	next_decode_page(argp);
-	memcpy(((char*)p)+avail, argp->p, (nbytes - avail));
-	argp->p += XDR_QUADLEN(nbytes - avail);
-	return p;
-}
-
-static unsigned int compoundargs_bytes_left(struct nfsd4_compoundargs *argp)
-{
-	unsigned int this = (char *)argp->end - (char *)argp->p;
-
-	return this + argp->pagelen;
-}
+#define READ_BUF(nbytes)			\
+	do {					\
+		p = xdr_inline_decode(argp->xdr,\
+				      nbytes);	\
+		if (!p)				\
+			goto xdr_error;		\
+	} while (0)
 
 static int zero_clientid(clientid_t *clid)
 {
@@ -261,44 +184,6 @@ svcxdr_dupstr(struct nfsd4_compoundargs *argp, void *buf, u32 len)
 	return p;
 }
 
-static __be32
-svcxdr_construct_vector(struct nfsd4_compoundargs *argp, struct kvec *head,
-			struct page ***pagelist, u32 buflen)
-{
-	int avail;
-	int len;
-	int pages;
-
-	/* Sorry .. no magic macros for this.. *
-	 * READ_BUF(write->wr_buflen);
-	 * SAVEMEM(write->wr_buf, write->wr_buflen);
-	 */
-	avail = (char *)argp->end - (char *)argp->p;
-	if (avail + argp->pagelen < buflen) {
-		dprintk("NFSD: xdr error (%s:%d)\n",
-			       __FILE__, __LINE__);
-		return nfserr_bad_xdr;
-	}
-	head->iov_base = argp->p;
-	head->iov_len = avail;
-	*pagelist = argp->pagelist;
-
-	len = XDR_QUADLEN(buflen) << 2;
-	if (len >= avail) {
-		len -= avail;
-
-		pages = len >> PAGE_SHIFT;
-		argp->pagelist += pages;
-		argp->pagelen -= pages * PAGE_SIZE;
-		len -= pages * PAGE_SIZE;
-
-		next_decode_page(argp);
-	}
-	argp->p += XDR_QUADLEN(len);
-
-	return 0;
-}
-
 /**
  * savemem - duplicate a chunk of memory for later processing
  * @argp: NFSv4 compound argument structure to be freed with
@@ -398,7 +283,7 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
 		READ_BUF(4); len += 4;
 		nace = be32_to_cpup(p++);
 
-		if (nace > compoundargs_bytes_left(argp)/20)
+		if (nace > xdr_stream_remaining(argp->xdr) / sizeof(struct nfs4_ace))
 			/*
 			 * Even with 4-byte names there wouldn't be
 			 * space for that many aces; something fishy is
@@ -929,7 +814,7 @@ xdr_error:
 
 static __be32 nfsd4_decode_opaque(struct nfsd4_compoundargs *argp, struct xdr_netobj *o)
 {
-	__be32 *p;
+	DECODE_HEAD;
 
 	READ_BUF(4);
 	o->len = be32_to_cpup(p++);
@@ -939,9 +824,8 @@ static __be32 nfsd4_decode_opaque(struct nfsd4_compoundargs *argp, struct xdr_ne
 
 	READ_BUF(o->len);
 	SAVEMEM(o->data, o->len);
-	return nfs_ok;
-xdr_error:
-	return nfserr_bad_xdr;
+
+	DECODE_TAIL;
 }
 
 static __be32
@@ -1319,10 +1203,8 @@ nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write)
 		goto xdr_error;
 	write->wr_buflen = be32_to_cpup(p++);
 
-	status = svcxdr_construct_vector(argp, &write->wr_head,
-					 &write->wr_pagelist, write->wr_buflen);
-	if (status)
-		return status;
+	if (!xdr_stream_subsegment(argp->xdr, &write->wr_payload, write->wr_buflen))
+		goto xdr_error;
 
 	DECODE_TAIL;
 }
@@ -1891,13 +1773,14 @@ nfsd4_decode_seek(struct nfsd4_compoundargs *argp, struct nfsd4_seek *seek)
  */
 
 /*
- * Decode data into buffer. Uses head and pages constructed by
- * svcxdr_construct_vector.
+ * Decode data into buffer.
  */
 static __be32
-nfsd4_vbuf_from_vector(struct nfsd4_compoundargs *argp, struct kvec *head,
-		       struct page **pages, char **bufp, u32 buflen)
+nfsd4_vbuf_from_vector(struct nfsd4_compoundargs *argp, struct xdr_buf *xdr,
+		       char **bufp, u32 buflen)
 {
+	struct page **pages = xdr->pages;
+	struct kvec *head = xdr->head;
 	char *tmp, *dp;
 	u32 len;
 
@@ -2012,8 +1895,6 @@ nfsd4_decode_setxattr(struct nfsd4_compoundargs *argp,
 {
 	DECODE_HEAD;
 	u32 flags, maxcount, size;
-	struct kvec head;
-	struct page **pagelist;
 
 	READ_BUF(4);
 	flags = be32_to_cpup(p++);
@@ -2036,12 +1917,12 @@ nfsd4_decode_setxattr(struct nfsd4_compoundargs *argp,
 
 	setxattr->setxa_len = size;
 	if (size > 0) {
-		status = svcxdr_construct_vector(argp, &head, &pagelist, size);
-		if (status)
-			return status;
+		struct xdr_buf payload;
 
-		status = nfsd4_vbuf_from_vector(argp, &head, pagelist,
-		    &setxattr->setxa_buf, size);
+		if (!xdr_stream_subsegment(argp->xdr, &payload, size))
+			goto xdr_error;
+		status = nfsd4_vbuf_from_vector(argp, &payload,
+						&setxattr->setxa_buf, size);
 	}
 
 	DECODE_TAIL;
@@ -5288,8 +5169,6 @@ void nfsd4_release_compoundargs(struct svc_rqst *rqstp)
 		kfree(args->ops);
 		args->ops = args->iops;
 	}
-	kfree(args->tmpp);
-	args->tmpp = NULL;
 	while (args->to_free) {
 		struct svcxdr_tmpbuf *tb = args->to_free;
 		args->to_free = tb->next;
@@ -5302,19 +5181,11 @@ nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, __be32 *p)
 {
 	struct nfsd4_compoundargs *args = rqstp->rq_argp;
 
-	if (rqstp->rq_arg.head[0].iov_len % 4) {
-		/* client is nuts */
-		dprintk("%s: compound not properly padded! (peeraddr=%pISc xid=0x%x)",
-			__func__, svc_addr(rqstp), be32_to_cpu(rqstp->rq_xid));
-		return 0;
-	}
-	args->p = p;
-	args->end = rqstp->rq_arg.head[0].iov_base + rqstp->rq_arg.head[0].iov_len;
-	args->pagelist = rqstp->rq_arg.pages;
-	args->pagelen = rqstp->rq_arg.page_len;
-	args->tail = false;
+	/* svcxdr_tmp_alloc */
 	args->tmpp = NULL;
 	args->to_free = NULL;
+
+	args->xdr = &rqstp->rq_arg_stream;
 	args->ops = args->iops;
 	args->rqstp = rqstp;
 
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 37f89ad5e992..0eb13bd603ea 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -419,8 +419,7 @@ struct nfsd4_write {
 	u64		wr_offset;          /* request */
 	u32		wr_stable_how;      /* request */
 	u32		wr_buflen;          /* request */
-	struct kvec	wr_head;
-	struct page **	wr_pagelist;        /* request */
+	struct xdr_buf	wr_payload;         /* request */
 
 	u32		wr_bytes_written;   /* response */
 	u32		wr_how_written;     /* response */
@@ -696,15 +695,10 @@ struct svcxdr_tmpbuf {
 
 struct nfsd4_compoundargs {
 	/* scratch variables for XDR decode */
-	__be32 *			p;
-	__be32 *			end;
-	struct page **			pagelist;
-	int				pagelen;
-	bool				tail;
 	__be32				tmp[8];
 	__be32 *			tmpp;
+	struct xdr_stream		*xdr;
 	struct svcxdr_tmpbuf		*to_free;
-
 	struct svc_rqst			*rqstp;
 
 	u32				taglen;
diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 2729d2d6efce..cc64cd0891f1 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -254,6 +254,8 @@ extern void xdr_enter_page(struct xdr_stream *xdr, unsigned int len);
 extern int xdr_process_buf(struct xdr_buf *buf, unsigned int offset, unsigned int len, int (*actor)(struct scatterlist *, void *), void *data);
 extern uint64_t xdr_align_data(struct xdr_stream *, uint64_t, uint32_t);
 extern uint64_t xdr_expand_hole(struct xdr_stream *, uint64_t, uint64_t);
+extern bool xdr_stream_subsegment(struct xdr_stream *xdr, struct xdr_buf *subbuf,
+				  unsigned int len);
 
 /**
  * xdr_set_scratch_buffer - Attach a scratch buffer for decoding data.
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index c607744b3ea8..757560a3b06b 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -1407,6 +1407,51 @@ int xdr_buf_subsegment(const struct xdr_buf *buf, struct xdr_buf *subbuf,
 }
 EXPORT_SYMBOL_GPL(xdr_buf_subsegment);
 
+/**
+ * xdr_stream_subsegment - set @subbuf to a portion of @xdr
+ * @xdr: an xdr_stream set up for decoding
+ * @subbuf: the result buffer
+ * @nbytes: length of @xdr to extract, in bytes
+ *
+ * Sets up @subbuf to represent a portion of @xdr. The portion
+ * starts at the current offset in @xdr, and extends for a length
+ * of @nbytes. If this is successful, @xdr is advanced to the next
+ * position following that portion.
+ *
+ * Return values:
+ *   %true: @subbuf has been initialized, and @xdr has been advanced.
+ *   %false: a bounds error has occurred
+ */
+bool xdr_stream_subsegment(struct xdr_stream *xdr, struct xdr_buf *subbuf,
+			   unsigned int nbytes)
+{
+	unsigned int remaining, offset, len;
+
+	if (xdr_buf_subsegment(xdr->buf, subbuf, xdr_stream_pos(xdr), nbytes))
+		return false;
+
+	if (subbuf->head[0].iov_len)
+		if (!__xdr_inline_decode(xdr, subbuf->head[0].iov_len))
+			return false;
+
+	remaining = subbuf->page_len;
+	offset = subbuf->page_base;
+	while (remaining) {
+		len = min_t(unsigned int, remaining, PAGE_SIZE) - offset;
+
+		if (xdr->p == xdr->end && !xdr_set_next_buffer(xdr))
+			return false;
+		if (!__xdr_inline_decode(xdr, len))
+			return false;
+
+		remaining -= len;
+		offset = 0;
+	}
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(xdr_stream_subsegment);
+
 /**
  * xdr_buf_trim - lop at most "len" bytes off the end of "buf"
  * @buf: buf to be trimmed
-- 
cgit v1.2.3


From cbd9abb3706e96563b36af67595707a7054ab693 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Tue, 3 Nov 2020 13:19:51 -0500
Subject: NFSD: Replace READ* macros in nfsd4_decode_commit()

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4xdr.c          | 12 +++++-------
 include/linux/sunrpc/xdr.h | 21 +++++++++++++++++++++
 2 files changed, 26 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 1e5188b2f943..ff1e3621d977 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -581,13 +581,11 @@ nfsd4_decode_close(struct nfsd4_compoundargs *argp, struct nfsd4_close *close)
 static __be32
 nfsd4_decode_commit(struct nfsd4_compoundargs *argp, struct nfsd4_commit *commit)
 {
-	DECODE_HEAD;
-
-	READ_BUF(12);
-	p = xdr_decode_hyper(p, &commit->co_offset);
-	commit->co_count = be32_to_cpup(p++);
-
-	DECODE_TAIL;
+	if (xdr_stream_decode_u64(argp->xdr, &commit->co_offset) < 0)
+		return nfserr_bad_xdr;
+	if (xdr_stream_decode_u32(argp->xdr, &commit->co_count) < 0)
+		return nfserr_bad_xdr;
+	return nfs_ok;
 }
 
 static __be32
diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index cc64cd0891f1..cc669d95c484 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -571,6 +571,27 @@ xdr_stream_decode_u32(struct xdr_stream *xdr, __u32 *ptr)
 	return 0;
 }
 
+/**
+ * xdr_stream_decode_u64 - Decode a 64-bit integer
+ * @xdr: pointer to xdr_stream
+ * @ptr: location to store 64-bit integer
+ *
+ * Return values:
+ *   %0 on success
+ *   %-EBADMSG on XDR buffer overflow
+ */
+static inline ssize_t
+xdr_stream_decode_u64(struct xdr_stream *xdr, __u64 *ptr)
+{
+	const size_t count = sizeof(*ptr);
+	__be32 *p = xdr_inline_decode(xdr, count);
+
+	if (unlikely(!p))
+		return -EBADMSG;
+	xdr_decode_hyper(p, ptr);
+	return 0;
+}
+
 /**
  * xdr_stream_decode_opaque_fixed - Decode fixed length opaque xdr data
  * @xdr: pointer to xdr_stream
-- 
cgit v1.2.3


From 8918cc0d2b72db9997390626010b182c4500d749 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Mon, 16 Nov 2020 17:16:52 -0500
Subject: NFSD: Add helper for decoding locker4

Refactor for clarity.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4xdr.c          | 64 +++++++++++++++++++++++++++++++---------------
 include/linux/sunrpc/xdr.h | 21 +++++++++++++++
 2 files changed, 64 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 1b214b475d68..b85ccc94bfe0 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -833,6 +833,48 @@ nfsd4_decode_link(struct nfsd4_compoundargs *argp, struct nfsd4_link *link)
 	return nfsd4_decode_component4(argp, &link->li_name, &link->li_namelen);
 }
 
+static __be32
+nfsd4_decode_open_to_lock_owner4(struct nfsd4_compoundargs *argp,
+				 struct nfsd4_lock *lock)
+{
+	__be32 status;
+
+	if (xdr_stream_decode_u32(argp->xdr, &lock->lk_new_open_seqid) < 0)
+		return nfserr_bad_xdr;
+	status = nfsd4_decode_stateid4(argp, &lock->lk_new_open_stateid);
+	if (status)
+		return status;
+	if (xdr_stream_decode_u32(argp->xdr, &lock->lk_new_lock_seqid) < 0)
+		return nfserr_bad_xdr;
+	return nfsd4_decode_state_owner4(argp, &lock->lk_new_clientid,
+					 &lock->lk_new_owner);
+}
+
+static __be32
+nfsd4_decode_exist_lock_owner4(struct nfsd4_compoundargs *argp,
+			       struct nfsd4_lock *lock)
+{
+	__be32 status;
+
+	status = nfsd4_decode_stateid4(argp, &lock->lk_old_lock_stateid);
+	if (status)
+		return status;
+	if (xdr_stream_decode_u32(argp->xdr, &lock->lk_old_lock_seqid) < 0)
+		return nfserr_bad_xdr;
+
+	return nfs_ok;
+}
+
+static __be32
+nfsd4_decode_locker4(struct nfsd4_compoundargs *argp, struct nfsd4_lock *lock)
+{
+	if (xdr_stream_decode_bool(argp->xdr, &lock->lk_is_new) < 0)
+		return nfserr_bad_xdr;
+	if (lock->lk_is_new)
+		return nfsd4_decode_open_to_lock_owner4(argp, lock);
+	return nfsd4_decode_exist_lock_owner4(argp, lock);
+}
+
 static __be32
 nfsd4_decode_lock(struct nfsd4_compoundargs *argp, struct nfsd4_lock *lock)
 {
@@ -848,27 +890,7 @@ nfsd4_decode_lock(struct nfsd4_compoundargs *argp, struct nfsd4_lock *lock)
 	lock->lk_reclaim = be32_to_cpup(p++);
 	p = xdr_decode_hyper(p, &lock->lk_offset);
 	p = xdr_decode_hyper(p, &lock->lk_length);
-	lock->lk_is_new = be32_to_cpup(p++);
-
-	if (lock->lk_is_new) {
-		READ_BUF(4);
-		lock->lk_new_open_seqid = be32_to_cpup(p++);
-		status = nfsd4_decode_stateid(argp, &lock->lk_new_open_stateid);
-		if (status)
-			return status;
-		READ_BUF(4);
-		lock->lk_new_lock_seqid = be32_to_cpup(p++);
-		status = nfsd4_decode_state_owner4(argp, &lock->lk_new_clientid,
-						   &lock->lk_new_owner);
-		if (status)
-			return status;
-	} else {
-		status = nfsd4_decode_stateid(argp, &lock->lk_old_lock_stateid);
-		if (status)
-			return status;
-		READ_BUF(4);
-		lock->lk_old_lock_seqid = be32_to_cpup(p++);
-	}
+	status = nfsd4_decode_locker4(argp, lock);
 
 	DECODE_TAIL;
 }
diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index cc669d95c484..9b35ce50cf2b 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -550,6 +550,27 @@ static inline bool xdr_item_is_present(const __be32 *p)
 	return *p != xdr_zero;
 }
 
+/**
+ * xdr_stream_decode_bool - Decode a boolean
+ * @xdr: pointer to xdr_stream
+ * @ptr: pointer to a u32 in which to store the result
+ *
+ * Return values:
+ *   %0 on success
+ *   %-EBADMSG on XDR buffer overflow
+ */
+static inline ssize_t
+xdr_stream_decode_bool(struct xdr_stream *xdr, __u32 *ptr)
+{
+	const size_t count = sizeof(*ptr);
+	__be32 *p = xdr_inline_decode(xdr, count);
+
+	if (unlikely(!p))
+		return -EBADMSG;
+	*ptr = (*p != xdr_zero);
+	return 0;
+}
+
 /**
  * xdr_stream_decode_u32 - Decode a 32-bit integer
  * @xdr: pointer to xdr_stream
-- 
cgit v1.2.3


From 7fd3253a7de6a317a0683f83739479fb880bffc8 Mon Sep 17 00:00:00 2001
From: Björn Töpel <bjorn.topel@intel.com>
Date: Mon, 30 Nov 2020 19:51:56 +0100
Subject: net: Introduce preferred busy-polling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The existing busy-polling mode, enabled by the SO_BUSY_POLL socket
option or system-wide using the /proc/sys/net/core/busy_read knob, is
an opportunistic. That means that if the NAPI context is not
scheduled, it will poll it. If, after busy-polling, the budget is
exceeded the busy-polling logic will schedule the NAPI onto the
regular softirq handling.

One implication of the behavior above is that a busy/heavy loaded NAPI
context will never enter/allow for busy-polling. Some applications
prefer that most NAPI processing would be done by busy-polling.

This series adds a new socket option, SO_PREFER_BUSY_POLL, that works
in concert with the napi_defer_hard_irqs and gro_flush_timeout
knobs. The napi_defer_hard_irqs and gro_flush_timeout knobs were
introduced in commit 6f8b12d661d0 ("net: napi: add hard irqs deferral
feature"), and allows for a user to defer interrupts to be enabled and
instead schedule the NAPI context from a watchdog timer. When a user
enables the SO_PREFER_BUSY_POLL, again with the other knobs enabled,
and the NAPI context is being processed by a softirq, the softirq NAPI
processing will exit early to allow the busy-polling to be performed.

If the application stops performing busy-polling via a system call,
the watchdog timer defined by gro_flush_timeout will timeout, and
regular softirq handling will resume.

In summary; Heavy traffic applications that prefer busy-polling over
softirq processing should use this option.

Example usage:

  $ echo 2 | sudo tee /sys/class/net/ens785f1/napi_defer_hard_irqs
  $ echo 200000 | sudo tee /sys/class/net/ens785f1/gro_flush_timeout

Note that the timeout should be larger than the userspace processing
window, otherwise the watchdog will timeout and fall back to regular
softirq processing.

Enable the SO_BUSY_POLL/SO_PREFER_BUSY_POLL options on your socket.

Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/bpf/20201130185205.196029-2-bjorn.topel@gmail.com
---
 arch/alpha/include/uapi/asm/socket.h  |  2 +
 arch/mips/include/uapi/asm/socket.h   |  2 +
 arch/parisc/include/uapi/asm/socket.h |  2 +
 arch/sparc/include/uapi/asm/socket.h  |  2 +
 fs/eventpoll.c                        |  2 +-
 include/linux/netdevice.h             | 35 +++++++++-------
 include/net/busy_poll.h               |  5 ++-
 include/net/sock.h                    |  4 ++
 include/uapi/asm-generic/socket.h     |  2 +
 net/core/dev.c                        | 78 ++++++++++++++++++++++++++++-------
 net/core/sock.c                       |  9 ++++
 11 files changed, 111 insertions(+), 32 deletions(-)

(limited to 'include/linux')

diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h
index de6c4df61082..538359642554 100644
--- a/arch/alpha/include/uapi/asm/socket.h
+++ b/arch/alpha/include/uapi/asm/socket.h
@@ -124,6 +124,8 @@
 
 #define SO_DETACH_REUSEPORT_BPF 68
 
+#define SO_PREFER_BUSY_POLL	69
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64
diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h
index d0a9ed2ca2d6..e406e73b5e6e 100644
--- a/arch/mips/include/uapi/asm/socket.h
+++ b/arch/mips/include/uapi/asm/socket.h
@@ -135,6 +135,8 @@
 
 #define SO_DETACH_REUSEPORT_BPF 68
 
+#define SO_PREFER_BUSY_POLL	69
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index 10173c32195e..1bc46200889d 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -116,6 +116,8 @@
 
 #define SO_DETACH_REUSEPORT_BPF 0x4042
 
+#define SO_PREFER_BUSY_POLL	0x4043
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64
diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h
index 8029b681fc7c..99688cf673a4 100644
--- a/arch/sparc/include/uapi/asm/socket.h
+++ b/arch/sparc/include/uapi/asm/socket.h
@@ -117,6 +117,8 @@
 
 #define SO_DETACH_REUSEPORT_BPF  0x0047
 
+#define SO_PREFER_BUSY_POLL	 0x0048
+
 #if !defined(__KERNEL__)
 
 
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 4df61129566d..e11fab3a0b9e 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -397,7 +397,7 @@ static void ep_busy_loop(struct eventpoll *ep, int nonblock)
 	unsigned int napi_id = READ_ONCE(ep->napi_id);
 
 	if ((napi_id >= MIN_NAPI_ID) && net_busy_loop_on())
-		napi_busy_loop(napi_id, nonblock ? NULL : ep_busy_loop_end, ep);
+		napi_busy_loop(napi_id, nonblock ? NULL : ep_busy_loop_end, ep, false);
 }
 
 static inline void ep_reset_busy_poll_napi_id(struct eventpoll *ep)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7ce648a564f7..52d1cc2bd8a7 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -350,23 +350,25 @@ struct napi_struct {
 };
 
 enum {
-	NAPI_STATE_SCHED,	/* Poll is scheduled */
-	NAPI_STATE_MISSED,	/* reschedule a napi */
-	NAPI_STATE_DISABLE,	/* Disable pending */
-	NAPI_STATE_NPSVC,	/* Netpoll - don't dequeue from poll_list */
-	NAPI_STATE_LISTED,	/* NAPI added to system lists */
-	NAPI_STATE_NO_BUSY_POLL,/* Do not add in napi_hash, no busy polling */
-	NAPI_STATE_IN_BUSY_POLL,/* sk_busy_loop() owns this NAPI */
+	NAPI_STATE_SCHED,		/* Poll is scheduled */
+	NAPI_STATE_MISSED,		/* reschedule a napi */
+	NAPI_STATE_DISABLE,		/* Disable pending */
+	NAPI_STATE_NPSVC,		/* Netpoll - don't dequeue from poll_list */
+	NAPI_STATE_LISTED,		/* NAPI added to system lists */
+	NAPI_STATE_NO_BUSY_POLL,	/* Do not add in napi_hash, no busy polling */
+	NAPI_STATE_IN_BUSY_POLL,	/* sk_busy_loop() owns this NAPI */
+	NAPI_STATE_PREFER_BUSY_POLL,	/* prefer busy-polling over softirq processing*/
 };
 
 enum {
-	NAPIF_STATE_SCHED	 = BIT(NAPI_STATE_SCHED),
-	NAPIF_STATE_MISSED	 = BIT(NAPI_STATE_MISSED),
-	NAPIF_STATE_DISABLE	 = BIT(NAPI_STATE_DISABLE),
-	NAPIF_STATE_NPSVC	 = BIT(NAPI_STATE_NPSVC),
-	NAPIF_STATE_LISTED	 = BIT(NAPI_STATE_LISTED),
-	NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL),
-	NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL),
+	NAPIF_STATE_SCHED		= BIT(NAPI_STATE_SCHED),
+	NAPIF_STATE_MISSED		= BIT(NAPI_STATE_MISSED),
+	NAPIF_STATE_DISABLE		= BIT(NAPI_STATE_DISABLE),
+	NAPIF_STATE_NPSVC		= BIT(NAPI_STATE_NPSVC),
+	NAPIF_STATE_LISTED		= BIT(NAPI_STATE_LISTED),
+	NAPIF_STATE_NO_BUSY_POLL	= BIT(NAPI_STATE_NO_BUSY_POLL),
+	NAPIF_STATE_IN_BUSY_POLL	= BIT(NAPI_STATE_IN_BUSY_POLL),
+	NAPIF_STATE_PREFER_BUSY_POLL	= BIT(NAPI_STATE_PREFER_BUSY_POLL),
 };
 
 enum gro_result {
@@ -437,6 +439,11 @@ static inline bool napi_disable_pending(struct napi_struct *n)
 	return test_bit(NAPI_STATE_DISABLE, &n->state);
 }
 
+static inline bool napi_prefer_busy_poll(struct napi_struct *n)
+{
+	return test_bit(NAPI_STATE_PREFER_BUSY_POLL, &n->state);
+}
+
 bool napi_schedule_prep(struct napi_struct *n);
 
 /**
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index b001fa91c14e..0292b8353d7e 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -43,7 +43,7 @@ bool sk_busy_loop_end(void *p, unsigned long start_time);
 
 void napi_busy_loop(unsigned int napi_id,
 		    bool (*loop_end)(void *, unsigned long),
-		    void *loop_end_arg);
+		    void *loop_end_arg, bool prefer_busy_poll);
 
 #else /* CONFIG_NET_RX_BUSY_POLL */
 static inline unsigned long net_busy_loop_on(void)
@@ -105,7 +105,8 @@ static inline void sk_busy_loop(struct sock *sk, int nonblock)
 	unsigned int napi_id = READ_ONCE(sk->sk_napi_id);
 
 	if (napi_id >= MIN_NAPI_ID)
-		napi_busy_loop(napi_id, nonblock ? NULL : sk_busy_loop_end, sk);
+		napi_busy_loop(napi_id, nonblock ? NULL : sk_busy_loop_end, sk,
+			       READ_ONCE(sk->sk_prefer_busy_poll));
 #endif
 }
 
diff --git a/include/net/sock.h b/include/net/sock.h
index a5c6ae78df77..d49b89b071b6 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -301,6 +301,7 @@ struct bpf_local_storage;
   *	@sk_ack_backlog: current listen backlog
   *	@sk_max_ack_backlog: listen backlog set in listen()
   *	@sk_uid: user id of owner
+  *	@sk_prefer_busy_poll: prefer busypolling over softirq processing
   *	@sk_priority: %SO_PRIORITY setting
   *	@sk_type: socket type (%SOCK_STREAM, etc)
   *	@sk_protocol: which protocol this socket belongs in this network family
@@ -479,6 +480,9 @@ struct sock {
 	u32			sk_ack_backlog;
 	u32			sk_max_ack_backlog;
 	kuid_t			sk_uid;
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	u8			sk_prefer_busy_poll;
+#endif
 	struct pid		*sk_peer_pid;
 	const struct cred	*sk_peer_cred;
 	long			sk_rcvtimeo;
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index 77f7c1638eb1..7dd02408b7ce 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -119,6 +119,8 @@
 
 #define SO_DETACH_REUSEPORT_BPF 68
 
+#define SO_PREFER_BUSY_POLL	69
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))
diff --git a/net/core/dev.c b/net/core/dev.c
index 60d325bda0d7..6f8d2cffb7c5 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6458,7 +6458,8 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 
 		WARN_ON_ONCE(!(val & NAPIF_STATE_SCHED));
 
-		new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED);
+		new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED |
+			      NAPIF_STATE_PREFER_BUSY_POLL);
 
 		/* If STATE_MISSED was set, leave STATE_SCHED set,
 		 * because we will call napi->poll() one more time.
@@ -6497,8 +6498,29 @@ static struct napi_struct *napi_by_id(unsigned int napi_id)
 
 #define BUSY_POLL_BUDGET 8
 
-static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock)
+static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule)
 {
+	if (!skip_schedule) {
+		gro_normal_list(napi);
+		__napi_schedule(napi);
+		return;
+	}
+
+	if (napi->gro_bitmask) {
+		/* flush too old packets
+		 * If HZ < 1000, flush all packets.
+		 */
+		napi_gro_flush(napi, HZ >= 1000);
+	}
+
+	gro_normal_list(napi);
+	clear_bit(NAPI_STATE_SCHED, &napi->state);
+}
+
+static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, bool prefer_busy_poll)
+{
+	bool skip_schedule = false;
+	unsigned long timeout;
 	int rc;
 
 	/* Busy polling means there is a high chance device driver hard irq
@@ -6515,6 +6537,15 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock)
 
 	local_bh_disable();
 
+	if (prefer_busy_poll) {
+		napi->defer_hard_irqs_count = READ_ONCE(napi->dev->napi_defer_hard_irqs);
+		timeout = READ_ONCE(napi->dev->gro_flush_timeout);
+		if (napi->defer_hard_irqs_count && timeout) {
+			hrtimer_start(&napi->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED);
+			skip_schedule = true;
+		}
+	}
+
 	/* All we really want here is to re-enable device interrupts.
 	 * Ideally, a new ndo_busy_poll_stop() could avoid another round.
 	 */
@@ -6525,19 +6556,14 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock)
 	 */
 	trace_napi_poll(napi, rc, BUSY_POLL_BUDGET);
 	netpoll_poll_unlock(have_poll_lock);
-	if (rc == BUSY_POLL_BUDGET) {
-		/* As the whole budget was spent, we still own the napi so can
-		 * safely handle the rx_list.
-		 */
-		gro_normal_list(napi);
-		__napi_schedule(napi);
-	}
+	if (rc == BUSY_POLL_BUDGET)
+		__busy_poll_stop(napi, skip_schedule);
 	local_bh_enable();
 }
 
 void napi_busy_loop(unsigned int napi_id,
 		    bool (*loop_end)(void *, unsigned long),
-		    void *loop_end_arg)
+		    void *loop_end_arg, bool prefer_busy_poll)
 {
 	unsigned long start_time = loop_end ? busy_loop_current_time() : 0;
 	int (*napi_poll)(struct napi_struct *napi, int budget);
@@ -6565,12 +6591,18 @@ restart:
 			 * we avoid dirtying napi->state as much as we can.
 			 */
 			if (val & (NAPIF_STATE_DISABLE | NAPIF_STATE_SCHED |
-				   NAPIF_STATE_IN_BUSY_POLL))
+				   NAPIF_STATE_IN_BUSY_POLL)) {
+				if (prefer_busy_poll)
+					set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state);
 				goto count;
+			}
 			if (cmpxchg(&napi->state, val,
 				    val | NAPIF_STATE_IN_BUSY_POLL |
-					  NAPIF_STATE_SCHED) != val)
+					  NAPIF_STATE_SCHED) != val) {
+				if (prefer_busy_poll)
+					set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state);
 				goto count;
+			}
 			have_poll_lock = netpoll_poll_lock(napi);
 			napi_poll = napi->poll;
 		}
@@ -6588,7 +6620,7 @@ count:
 
 		if (unlikely(need_resched())) {
 			if (napi_poll)
-				busy_poll_stop(napi, have_poll_lock);
+				busy_poll_stop(napi, have_poll_lock, prefer_busy_poll);
 			preempt_enable();
 			rcu_read_unlock();
 			cond_resched();
@@ -6599,7 +6631,7 @@ count:
 		cpu_relax();
 	}
 	if (napi_poll)
-		busy_poll_stop(napi, have_poll_lock);
+		busy_poll_stop(napi, have_poll_lock, prefer_busy_poll);
 	preempt_enable();
 out:
 	rcu_read_unlock();
@@ -6650,8 +6682,10 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer)
 	 * NAPI_STATE_MISSED, since we do not react to a device IRQ.
 	 */
 	if (!napi_disable_pending(napi) &&
-	    !test_and_set_bit(NAPI_STATE_SCHED, &napi->state))
+	    !test_and_set_bit(NAPI_STATE_SCHED, &napi->state)) {
+		clear_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state);
 		__napi_schedule_irqoff(napi);
+	}
 
 	return HRTIMER_NORESTART;
 }
@@ -6709,6 +6743,7 @@ void napi_disable(struct napi_struct *n)
 
 	hrtimer_cancel(&n->timer);
 
+	clear_bit(NAPI_STATE_PREFER_BUSY_POLL, &n->state);
 	clear_bit(NAPI_STATE_DISABLE, &n->state);
 }
 EXPORT_SYMBOL(napi_disable);
@@ -6781,6 +6816,19 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll)
 		goto out_unlock;
 	}
 
+	/* The NAPI context has more processing work, but busy-polling
+	 * is preferred. Exit early.
+	 */
+	if (napi_prefer_busy_poll(n)) {
+		if (napi_complete_done(n, work)) {
+			/* If timeout is not set, we need to make sure
+			 * that the NAPI is re-scheduled.
+			 */
+			napi_schedule(n);
+		}
+		goto out_unlock;
+	}
+
 	if (n->gro_bitmask) {
 		/* flush too old packets
 		 * If HZ < 1000, flush all packets.
diff --git a/net/core/sock.c b/net/core/sock.c
index 727ea1cc633c..e05f2e52b5a8 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1159,6 +1159,12 @@ set_sndbuf:
 				sk->sk_ll_usec = val;
 		}
 		break;
+	case SO_PREFER_BUSY_POLL:
+		if (valbool && !capable(CAP_NET_ADMIN))
+			ret = -EPERM;
+		else
+			WRITE_ONCE(sk->sk_prefer_busy_poll, valbool);
+		break;
 #endif
 
 	case SO_MAX_PACING_RATE:
@@ -1523,6 +1529,9 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 	case SO_BUSY_POLL:
 		v.val = sk->sk_ll_usec;
 		break;
+	case SO_PREFER_BUSY_POLL:
+		v.val = READ_ONCE(sk->sk_prefer_busy_poll);
+		break;
 #endif
 
 	case SO_MAX_PACING_RATE:
-- 
cgit v1.2.3


From 147ad605dc12c515c97136899ccb5c70e6c674e1 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 23 Nov 2020 11:23:16 +0100
Subject: init: use type alignment for kernel parameters

Specify type alignment for kernel parameters instead of sizeof(long).

The alignment attribute is used to prevent gcc from increasing the
alignment of objects with static extent as an optimisation, something
which would mess up the __setup array stride.

Using __alignof__(struct obs_kernel_param) rather than sizeof(long) is
preferred since it better indicates why it is there and doesn't break
should the type size or alignment change.

Note that on m68k the alignment of struct obs_kernel_param is actually
two and that adding a 1- or 2-byte field to the 12-byte struct would
cause a breakage with the current 4-byte alignment.

Link: https://lore.kernel.org/lkml/20201103175711.10731-1-johan@kernel.org
Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: Jessica Yu <jeyu@kernel.org>
---
 include/linux/init.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/init.h b/include/linux/init.h
index 7b53cb3092ee..e668832ef66a 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -255,7 +255,7 @@ struct obs_kernel_param {
 		__aligned(1) = str; 					\
 	static struct obs_kernel_param __setup_##unique_id		\
 		__used __section(".init.setup")				\
-		__attribute__((aligned((sizeof(long)))))		\
+		__aligned(__alignof__(struct obs_kernel_param))		\
 		= { __setup_str_##unique_id, fn, early }
 
 #define __setup(str, fn)						\
-- 
cgit v1.2.3


From a2abe7cbd8fe2db5ff386c968e2273d9dc6c468d Mon Sep 17 00:00:00 2001
From: Sami Tolvanen <samitolvanen@google.com>
Date: Mon, 30 Nov 2020 15:34:41 -0800
Subject: scs: switch to vmapped shadow stacks

The kernel currently uses kmem_cache to allocate shadow call stacks,
which means an overflows may not be immediately detected and can
potentially result in another task's shadow stack to be overwritten.

This change switches SCS to use virtually mapped shadow stacks for
tasks, which increases shadow stack size to a full page and provides
more robust overflow detection, similarly to VMAP_STACK.

Signed-off-by: Sami Tolvanen <samitolvanen@google.com>
Acked-by: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20201130233442.2562064-2-samitolvanen@google.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 include/linux/scs.h | 12 ++++-----
 kernel/scs.c        | 71 ++++++++++++++++++++++++++++++++++++++++++++---------
 2 files changed, 66 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/scs.h b/include/linux/scs.h
index 6dec390cf154..2a506c2a16f4 100644
--- a/include/linux/scs.h
+++ b/include/linux/scs.h
@@ -15,12 +15,8 @@
 
 #ifdef CONFIG_SHADOW_CALL_STACK
 
-/*
- * In testing, 1 KiB shadow stack size (i.e. 128 stack frames on a 64-bit
- * architecture) provided ~40% safety margin on stack usage while keeping
- * memory allocation overhead reasonable.
- */
-#define SCS_SIZE		SZ_1K
+#define SCS_ORDER		0
+#define SCS_SIZE		(PAGE_SIZE << SCS_ORDER)
 #define GFP_SCS			(GFP_KERNEL | __GFP_ZERO)
 
 /* An illegal pointer value to mark the end of the shadow stack. */
@@ -33,6 +29,8 @@
 #define task_scs(tsk)		(task_thread_info(tsk)->scs_base)
 #define task_scs_sp(tsk)	(task_thread_info(tsk)->scs_sp)
 
+void *scs_alloc(int node);
+void scs_free(void *s);
 void scs_init(void);
 int scs_prepare(struct task_struct *tsk, int node);
 void scs_release(struct task_struct *tsk);
@@ -61,6 +59,8 @@ static inline bool task_scs_end_corrupted(struct task_struct *tsk)
 
 #else /* CONFIG_SHADOW_CALL_STACK */
 
+static inline void *scs_alloc(int node) { return NULL; }
+static inline void scs_free(void *s) {}
 static inline void scs_init(void) {}
 static inline void scs_task_reset(struct task_struct *tsk) {}
 static inline int scs_prepare(struct task_struct *tsk, int node) { return 0; }
diff --git a/kernel/scs.c b/kernel/scs.c
index 4ff4a7ba0094..e2a71fc82fa0 100644
--- a/kernel/scs.c
+++ b/kernel/scs.c
@@ -5,26 +5,49 @@
  * Copyright (C) 2019 Google LLC
  */
 
+#include <linux/cpuhotplug.h>
 #include <linux/kasan.h>
 #include <linux/mm.h>
 #include <linux/scs.h>
-#include <linux/slab.h>
+#include <linux/vmalloc.h>
 #include <linux/vmstat.h>
 
-static struct kmem_cache *scs_cache;
-
 static void __scs_account(void *s, int account)
 {
-	struct page *scs_page = virt_to_page(s);
+	struct page *scs_page = vmalloc_to_page(s);
 
 	mod_node_page_state(page_pgdat(scs_page), NR_KERNEL_SCS_KB,
 			    account * (SCS_SIZE / SZ_1K));
 }
 
-static void *scs_alloc(int node)
+/* Matches NR_CACHED_STACKS for VMAP_STACK */
+#define NR_CACHED_SCS 2
+static DEFINE_PER_CPU(void *, scs_cache[NR_CACHED_SCS]);
+
+static void *__scs_alloc(int node)
 {
-	void *s = kmem_cache_alloc_node(scs_cache, GFP_SCS, node);
+	int i;
+	void *s;
+
+	for (i = 0; i < NR_CACHED_SCS; i++) {
+		s = this_cpu_xchg(scs_cache[i], NULL);
+		if (s) {
+			kasan_unpoison_vmalloc(s, SCS_SIZE);
+			memset(s, 0, SCS_SIZE);
+			return s;
+		}
+	}
+
+	return __vmalloc_node_range(SCS_SIZE, 1, VMALLOC_START, VMALLOC_END,
+				    GFP_SCS, PAGE_KERNEL, 0, node,
+				    __builtin_return_address(0));
+}
 
+void *scs_alloc(int node)
+{
+	void *s;
+
+	s = __scs_alloc(node);
 	if (!s)
 		return NULL;
 
@@ -34,21 +57,47 @@ static void *scs_alloc(int node)
 	 * Poison the allocation to catch unintentional accesses to
 	 * the shadow stack when KASAN is enabled.
 	 */
-	kasan_poison_object_data(scs_cache, s);
+	kasan_poison_vmalloc(s, SCS_SIZE);
 	__scs_account(s, 1);
 	return s;
 }
 
-static void scs_free(void *s)
+void scs_free(void *s)
 {
+	int i;
+
 	__scs_account(s, -1);
-	kasan_unpoison_object_data(scs_cache, s);
-	kmem_cache_free(scs_cache, s);
+
+	/*
+	 * We cannot sleep as this can be called in interrupt context,
+	 * so use this_cpu_cmpxchg to update the cache, and vfree_atomic
+	 * to free the stack.
+	 */
+
+	for (i = 0; i < NR_CACHED_SCS; i++)
+		if (this_cpu_cmpxchg(scs_cache[i], 0, s) == NULL)
+			return;
+
+	vfree_atomic(s);
+}
+
+static int scs_cleanup(unsigned int cpu)
+{
+	int i;
+	void **cache = per_cpu_ptr(scs_cache, cpu);
+
+	for (i = 0; i < NR_CACHED_SCS; i++) {
+		vfree(cache[i]);
+		cache[i] = NULL;
+	}
+
+	return 0;
 }
 
 void __init scs_init(void)
 {
-	scs_cache = kmem_cache_create("scs_cache", SCS_SIZE, 0, 0, NULL);
+	cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "scs:scs_cache", NULL,
+			  scs_cleanup);
 }
 
 int scs_prepare(struct task_struct *tsk, int node)
-- 
cgit v1.2.3


From ac20ffbb0279aae7be48567fb734eae7d050769e Mon Sep 17 00:00:00 2001
From: Sami Tolvanen <samitolvanen@google.com>
Date: Mon, 30 Nov 2020 15:34:42 -0800
Subject: arm64: scs: use vmapped IRQ and SDEI shadow stacks

Use scs_alloc() to allocate also IRQ and SDEI shadow stacks instead of
using statically allocated stacks.

Signed-off-by: Sami Tolvanen <samitolvanen@google.com>
Acked-by: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20201130233442.2562064-3-samitolvanen@google.com
[will: Move CONFIG_SHADOW_CALL_STACK check into init_irq_scs()]
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/Makefile |  1 -
 arch/arm64/kernel/entry.S  |  6 ++--
 arch/arm64/kernel/irq.c    | 21 ++++++++++++++
 arch/arm64/kernel/scs.c    | 16 -----------
 arch/arm64/kernel/sdei.c   | 70 ++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/scs.h        |  4 ---
 6 files changed, 94 insertions(+), 24 deletions(-)
 delete mode 100644 arch/arm64/kernel/scs.c

(limited to 'include/linux')

diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index bbaf0bc4ad60..86364ab6f13f 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -58,7 +58,6 @@ obj-$(CONFIG_CRASH_DUMP)		+= crash_dump.o
 obj-$(CONFIG_CRASH_CORE)		+= crash_core.o
 obj-$(CONFIG_ARM_SDE_INTERFACE)		+= sdei.o
 obj-$(CONFIG_ARM64_PTR_AUTH)		+= pointer_auth.o
-obj-$(CONFIG_SHADOW_CALL_STACK)		+= scs.o
 obj-$(CONFIG_ARM64_MTE)			+= mte.o
 
 obj-y					+= vdso/ probes/
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index b295fb912b12..5c2ac4b5b2da 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -441,7 +441,7 @@ SYM_CODE_END(__swpan_exit_el0)
 
 #ifdef CONFIG_SHADOW_CALL_STACK
 	/* also switch to the irq shadow stack */
-	adr_this_cpu scs_sp, irq_shadow_call_stack, x26
+	ldr_this_cpu scs_sp, irq_shadow_call_stack_ptr, x26
 #endif
 
 9998:
@@ -1097,9 +1097,9 @@ SYM_CODE_START(__sdei_asm_handler)
 #ifdef CONFIG_SHADOW_CALL_STACK
 	/* Use a separate shadow call stack for normal and critical events */
 	cbnz	w4, 3f
-	adr_this_cpu dst=scs_sp, sym=sdei_shadow_call_stack_normal, tmp=x6
+	ldr_this_cpu dst=scs_sp, sym=sdei_shadow_call_stack_normal_ptr, tmp=x6
 	b	4f
-3:	adr_this_cpu dst=scs_sp, sym=sdei_shadow_call_stack_critical, tmp=x6
+3:	ldr_this_cpu dst=scs_sp, sym=sdei_shadow_call_stack_critical_ptr, tmp=x6
 4:
 #endif
 
diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index 9cf2fb87584a..ac54c21140d4 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -17,6 +17,7 @@
 #include <linux/init.h>
 #include <linux/irqchip.h>
 #include <linux/kprobes.h>
+#include <linux/scs.h>
 #include <linux/seq_file.h>
 #include <linux/vmalloc.h>
 #include <asm/daifflags.h>
@@ -27,6 +28,25 @@ DEFINE_PER_CPU(struct nmi_ctx, nmi_contexts);
 
 DEFINE_PER_CPU(unsigned long *, irq_stack_ptr);
 
+
+DECLARE_PER_CPU(unsigned long *, irq_shadow_call_stack_ptr);
+
+#ifdef CONFIG_SHADOW_CALL_STACK
+DEFINE_PER_CPU(unsigned long *, irq_shadow_call_stack_ptr);
+#endif
+
+static void init_irq_scs(void)
+{
+	int cpu;
+
+	if (!IS_ENABLED(CONFIG_SHADOW_CALL_STACK))
+		return;
+
+	for_each_possible_cpu(cpu)
+		per_cpu(irq_shadow_call_stack_ptr, cpu) =
+			scs_alloc(cpu_to_node(cpu));
+}
+
 #ifdef CONFIG_VMAP_STACK
 static void init_irq_stacks(void)
 {
@@ -54,6 +74,7 @@ static void init_irq_stacks(void)
 void __init init_IRQ(void)
 {
 	init_irq_stacks();
+	init_irq_scs();
 	irqchip_init();
 	if (!handle_arch_irq)
 		panic("No interrupt controller found.");
diff --git a/arch/arm64/kernel/scs.c b/arch/arm64/kernel/scs.c
deleted file mode 100644
index e8f7ff45dd8f..000000000000
--- a/arch/arm64/kernel/scs.c
+++ /dev/null
@@ -1,16 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Shadow Call Stack support.
- *
- * Copyright (C) 2019 Google LLC
- */
-
-#include <linux/percpu.h>
-#include <linux/scs.h>
-
-DEFINE_SCS(irq_shadow_call_stack);
-
-#ifdef CONFIG_ARM_SDE_INTERFACE
-DEFINE_SCS(sdei_shadow_call_stack_normal);
-DEFINE_SCS(sdei_shadow_call_stack_critical);
-#endif
diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c
index 7689f2031c0c..d12fd786b267 100644
--- a/arch/arm64/kernel/sdei.c
+++ b/arch/arm64/kernel/sdei.c
@@ -7,6 +7,7 @@
 #include <linux/hardirq.h>
 #include <linux/irqflags.h>
 #include <linux/sched/task_stack.h>
+#include <linux/scs.h>
 #include <linux/uaccess.h>
 
 #include <asm/alternative.h>
@@ -37,6 +38,14 @@ DEFINE_PER_CPU(unsigned long *, sdei_stack_normal_ptr);
 DEFINE_PER_CPU(unsigned long *, sdei_stack_critical_ptr);
 #endif
 
+DECLARE_PER_CPU(unsigned long *, sdei_shadow_call_stack_normal_ptr);
+DECLARE_PER_CPU(unsigned long *, sdei_shadow_call_stack_critical_ptr);
+
+#ifdef CONFIG_SHADOW_CALL_STACK
+DEFINE_PER_CPU(unsigned long *, sdei_shadow_call_stack_normal_ptr);
+DEFINE_PER_CPU(unsigned long *, sdei_shadow_call_stack_critical_ptr);
+#endif
+
 static void _free_sdei_stack(unsigned long * __percpu *ptr, int cpu)
 {
 	unsigned long *p;
@@ -90,6 +99,59 @@ static int init_sdei_stacks(void)
 	return err;
 }
 
+static void _free_sdei_scs(unsigned long * __percpu *ptr, int cpu)
+{
+	void *s;
+
+	s = per_cpu(*ptr, cpu);
+	if (s) {
+		per_cpu(*ptr, cpu) = NULL;
+		scs_free(s);
+	}
+}
+
+static void free_sdei_scs(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		_free_sdei_scs(&sdei_shadow_call_stack_normal_ptr, cpu);
+		_free_sdei_scs(&sdei_shadow_call_stack_critical_ptr, cpu);
+	}
+}
+
+static int _init_sdei_scs(unsigned long * __percpu *ptr, int cpu)
+{
+	void *s;
+
+	s = scs_alloc(cpu_to_node(cpu));
+	if (!s)
+		return -ENOMEM;
+	per_cpu(*ptr, cpu) = s;
+
+	return 0;
+}
+
+static int init_sdei_scs(void)
+{
+	int cpu;
+	int err = 0;
+
+	for_each_possible_cpu(cpu) {
+		err = _init_sdei_scs(&sdei_shadow_call_stack_normal_ptr, cpu);
+		if (err)
+			break;
+		err = _init_sdei_scs(&sdei_shadow_call_stack_critical_ptr, cpu);
+		if (err)
+			break;
+	}
+
+	if (err)
+		free_sdei_scs();
+
+	return err;
+}
+
 static bool on_sdei_normal_stack(unsigned long sp, struct stack_info *info)
 {
 	unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_normal_ptr);
@@ -138,6 +200,14 @@ unsigned long sdei_arch_get_entry_point(int conduit)
 			return 0;
 	}
 
+	if (IS_ENABLED(CONFIG_SHADOW_CALL_STACK)) {
+		if (init_sdei_scs()) {
+			if (IS_ENABLED(CONFIG_VMAP_STACK))
+				free_sdei_stacks();
+			return 0;
+		}
+	}
+
 	sdei_exit_mode = (conduit == SMCCC_CONDUIT_HVC) ? SDEI_EXIT_HVC : SDEI_EXIT_SMC;
 
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
diff --git a/include/linux/scs.h b/include/linux/scs.h
index 2a506c2a16f4..18122d9e17ff 100644
--- a/include/linux/scs.h
+++ b/include/linux/scs.h
@@ -22,10 +22,6 @@
 /* An illegal pointer value to mark the end of the shadow stack. */
 #define SCS_END_MAGIC		(0x5f6UL + POISON_POINTER_DELTA)
 
-/* Allocate a static per-CPU shadow stack */
-#define DEFINE_SCS(name)						\
-	DEFINE_PER_CPU(unsigned long [SCS_SIZE/sizeof(long)], name)	\
-
 #define task_scs(tsk)		(task_thread_info(tsk)->scs_base)
 #define task_scs_sp(tsk)	(task_thread_info(tsk)->scs_sp)
 
-- 
cgit v1.2.3


From c860476b9e3a420192b28e580cb749e024d032eb Mon Sep 17 00:00:00 2001
From: Adam Ward <Adam.Ward.opensource@diasemi.com>
Date: Mon, 30 Nov 2020 16:59:08 +0000
Subject: regulator: da9121: Add device variant regmaps

Add ability to probe device and validate configuration, then apply a regmap
configuration for a single or dual buck device accordingly.

Signed-off-by: Adam Ward <Adam.Ward.opensource@diasemi.com>
Link: https://lore.kernel.org/r/068c6b8d5e1b4e221e899e4c914c429429a2ec7d.1606755367.git.Adam.Ward.opensource@diasemi.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/Kconfig            |  14 +-
 drivers/regulator/da9121-regulator.c | 244 ++++++++++++++++++++++++++++++++---
 include/linux/regulator/da9121.h     |  25 ++++
 3 files changed, 262 insertions(+), 21 deletions(-)
 create mode 100644 include/linux/regulator/da9121.h

(limited to 'include/linux')

diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index a497a3729091..7faedb05b7a6 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -313,13 +313,21 @@ config REGULATOR_DA9063
 	  will be called da9063-regulator.
 
 config REGULATOR_DA9121
-	tristate "Dialog Semiconductor DA9121 regulator"
+	tristate "Dialog Semiconductor DA9121/DA9122/DA9220/DA9217/DA9130/DA9131/DA9132 regulator"
 	depends on I2C && OF
 	select REGMAP_I2C
 	help
 	  Say y here to support for the Dialog Semiconductor DA9121.  The
-	  DA9210 is a dual-phase buck converter controlled through an I2C
-	  interface.
+	  DA9121 is a single channel dual-phase buck converter controlled
+	  through an I2C interface.
+
+	  DA9121 Single-channel dual-phase 10A buck converter
+	  DA9130 Single-channel dual-phase 10A buck converter (Automotive)
+	  DA9217 Single-channel dual-phase  6A buck converter
+	  DA9122 Dual-channel single-phase  5A buck converter
+	  DA9131 Dual-channel single-phase  5A buck converter (Automotive)
+	  DA9220 Dual-channel single-phase  3A buck converter
+	  DA9132 Dual-channel single-phase  3A buck converter (Automotive)
 
 	  This driver can also be built as a module. If so, the module
 	  will be called da9121-regulator.
diff --git a/drivers/regulator/da9121-regulator.c b/drivers/regulator/da9121-regulator.c
index 5bebdb2a480d..137b1dfbcfbb 100644
--- a/drivers/regulator/da9121-regulator.c
+++ b/drivers/regulator/da9121-regulator.c
@@ -1,5 +1,17 @@
 // SPDX-License-Identifier: GPL-2.0-only
-/* Copyright (C) 2020 Axis Communications AB */
+//
+// DA9121 Single-channel dual-phase 10A buck converter
+//
+// Copyright (C) 2020 Axis Communications AB
+//
+// DA9130 Single-channel dual-phase 10A buck converter (Automotive)
+// DA9217 Single-channel dual-phase  6A buck converter
+// DA9122 Dual-channel single-phase  5A buck converter
+// DA9131 Dual-channel single-phase  5A buck converter (Automotive)
+// DA9220 Dual-channel single-phase  3A buck converter
+// DA9132 Dual-channel single-phase  3A buck converter (Automotive)
+//
+// Copyright (C) 2020 Dialog Semiconductor
 
 #include <linux/of_device.h>
 #include <linux/regulator/of_regulator.h>
@@ -9,26 +21,17 @@
 #include <linux/regmap.h>
 #include <linux/err.h>
 #include <linux/i2c.h>
+#include <linux/regulator/da9121.h>
+
 #include "da9121-regulator.h"
 
 /* Chip data */
 struct da9121 {
 	struct device *dev;
+	struct regmap *regmap;
 	int variant_id;
 };
 
-#define DA9121_MIN_MV		300
-#define DA9121_MAX_MV		1900
-#define DA9121_STEP_MV		10
-#define DA9121_MIN_SEL		(DA9121_MIN_MV / DA9121_STEP_MV)
-#define DA9121_N_VOLTAGES	(((DA9121_MAX_MV - DA9121_MIN_MV) / DA9121_STEP_MV) \
-				 + 1 + DA9121_MIN_SEL)
-
-static const struct regmap_config da9121_regmap_config = {
-	.reg_bits = 8,
-	.val_bits = 8,
-};
-
 static const struct regulator_ops da9121_buck_ops = {
 	.enable = regulator_enable_regmap,
 	.disable = regulator_disable_regmap,
@@ -38,6 +41,13 @@ static const struct regulator_ops da9121_buck_ops = {
 	.list_voltage = regulator_list_voltage_linear,
 };
 
+#define DA9121_MIN_MV		300
+#define DA9121_MAX_MV		1900
+#define DA9121_STEP_MV		10
+#define DA9121_MIN_SEL		(DA9121_MIN_MV / DA9121_STEP_MV)
+#define DA9121_N_VOLTAGES	(((DA9121_MAX_MV - DA9121_MIN_MV) / DA9121_STEP_MV) \
+				 + 1 + DA9121_MIN_SEL)
+
 static const struct regulator_desc da9121_reg = {
 	.name = "da9121",
 	.of_match = "buck1",
@@ -58,6 +68,205 @@ static const struct regulator_desc da9121_reg = {
 	.enable_time = 20,
 };
 
+/* DA9121 chip register model */
+static const struct regmap_range da9121_1ch_readable_ranges[] = {
+	regmap_reg_range(DA9121_REG_SYS_STATUS_0, DA9121_REG_SYS_MASK_3),
+	regmap_reg_range(DA9121_REG_SYS_CONFIG_2, DA9121_REG_SYS_CONFIG_3),
+	regmap_reg_range(DA9121_REG_SYS_GPIO0_0, DA9121_REG_SYS_GPIO2_1),
+	regmap_reg_range(DA9121_REG_BUCK_BUCK1_0, DA9121_REG_BUCK_BUCK1_6),
+	regmap_reg_range(DA9121_REG_OTP_DEVICE_ID, DA9121_REG_OTP_CONFIG_ID),
+};
+
+static const struct regmap_access_table da9121_1ch_readable_table = {
+	.yes_ranges = da9121_1ch_readable_ranges,
+	.n_yes_ranges = ARRAY_SIZE(da9121_1ch_readable_ranges),
+};
+
+static const struct regmap_range da9121_2ch_readable_ranges[] = {
+	regmap_reg_range(DA9121_REG_SYS_STATUS_0, DA9121_REG_SYS_MASK_3),
+	regmap_reg_range(DA9121_REG_SYS_CONFIG_2, DA9121_REG_SYS_CONFIG_3),
+	regmap_reg_range(DA9121_REG_SYS_GPIO0_0, DA9121_REG_SYS_GPIO2_1),
+	regmap_reg_range(DA9121_REG_BUCK_BUCK1_0, DA9121_REG_BUCK_BUCK1_7),
+	regmap_reg_range(DA9xxx_REG_BUCK_BUCK2_0, DA9xxx_REG_BUCK_BUCK2_7),
+	regmap_reg_range(DA9121_REG_OTP_DEVICE_ID, DA9121_REG_OTP_CONFIG_ID),
+};
+
+static const struct regmap_access_table da9121_2ch_readable_table = {
+	.yes_ranges = da9121_2ch_readable_ranges,
+	.n_yes_ranges = ARRAY_SIZE(da9121_2ch_readable_ranges),
+};
+
+static const struct regmap_range da9121_1ch_writeable_ranges[] = {
+	regmap_reg_range(DA9121_REG_SYS_EVENT_0, DA9121_REG_SYS_MASK_3),
+	regmap_reg_range(DA9121_REG_SYS_CONFIG_2, DA9121_REG_SYS_CONFIG_3),
+	regmap_reg_range(DA9121_REG_SYS_GPIO0_0, DA9121_REG_SYS_GPIO2_1),
+	regmap_reg_range(DA9121_REG_BUCK_BUCK1_0, DA9121_REG_BUCK_BUCK1_2),
+	regmap_reg_range(DA9121_REG_BUCK_BUCK1_4, DA9121_REG_BUCK_BUCK1_6),
+};
+
+static const struct regmap_access_table da9121_1ch_writeable_table = {
+	.yes_ranges = da9121_1ch_writeable_ranges,
+	.n_yes_ranges = ARRAY_SIZE(da9121_1ch_writeable_ranges),
+};
+
+static const struct regmap_range da9121_2ch_writeable_ranges[] = {
+	regmap_reg_range(DA9121_REG_SYS_EVENT_0, DA9121_REG_SYS_MASK_3),
+	regmap_reg_range(DA9121_REG_SYS_CONFIG_2, DA9121_REG_SYS_CONFIG_3),
+	regmap_reg_range(DA9121_REG_SYS_GPIO0_0, DA9121_REG_SYS_GPIO2_1),
+	regmap_reg_range(DA9121_REG_BUCK_BUCK1_0, DA9121_REG_BUCK_BUCK1_2),
+	regmap_reg_range(DA9121_REG_BUCK_BUCK1_4, DA9121_REG_BUCK_BUCK1_7),
+	regmap_reg_range(DA9xxx_REG_BUCK_BUCK2_0, DA9xxx_REG_BUCK_BUCK2_2),
+	regmap_reg_range(DA9xxx_REG_BUCK_BUCK2_4, DA9xxx_REG_BUCK_BUCK2_7),
+};
+
+static const struct regmap_access_table da9121_2ch_writeable_table = {
+	.yes_ranges = da9121_2ch_writeable_ranges,
+	.n_yes_ranges = ARRAY_SIZE(da9121_2ch_writeable_ranges),
+};
+
+
+static const struct regmap_range da9121_volatile_ranges[] = {
+	regmap_reg_range(DA9121_REG_SYS_STATUS_0, DA9121_REG_SYS_EVENT_2),
+	regmap_reg_range(DA9121_REG_SYS_GPIO0_0, DA9121_REG_SYS_GPIO2_1),
+	regmap_reg_range(DA9121_REG_BUCK_BUCK1_0, DA9121_REG_BUCK_BUCK1_6),
+};
+
+static const struct regmap_access_table da9121_volatile_table = {
+	.yes_ranges = da9121_volatile_ranges,
+	.n_yes_ranges = ARRAY_SIZE(da9121_volatile_ranges),
+};
+
+/* DA9121 regmap config for 1 channel variants */
+static struct regmap_config da9121_1ch_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.max_register = DA9121_REG_OTP_CONFIG_ID,
+	.rd_table = &da9121_1ch_readable_table,
+	.wr_table = &da9121_1ch_writeable_table,
+	.volatile_table = &da9121_volatile_table,
+	.cache_type = REGCACHE_RBTREE,
+};
+
+/* DA9121 regmap config for 2 channel variants */
+static struct regmap_config da9121_2ch_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.max_register = DA9121_REG_OTP_CONFIG_ID,
+	.rd_table = &da9121_2ch_readable_table,
+	.wr_table = &da9121_2ch_writeable_table,
+	.volatile_table = &da9121_volatile_table,
+	.cache_type = REGCACHE_RBTREE,
+};
+
+static int da9121_check_device_type(struct i2c_client *i2c, struct da9121 *chip)
+{
+	u32 device_id;
+	u8 chip_id = chip->variant_id;
+	u32 variant_id;
+	u8 variant_mrc, variant_vrc;
+	char *type;
+	const char *name;
+	bool config_match = false;
+	int ret = 0;
+
+	ret = regmap_read(chip->regmap, DA9121_REG_OTP_DEVICE_ID, &device_id);
+	if (ret < 0) {
+		dev_err(chip->dev, "Cannot read device ID: %d\n", ret);
+		goto error;
+	}
+
+	ret = regmap_read(chip->regmap, DA9121_REG_OTP_VARIANT_ID, &variant_id);
+	if (ret < 0) {
+		dev_err(chip->dev, "Cannot read variant ID: %d\n", ret);
+		goto error;
+	}
+
+	if (device_id != DA9121_DEVICE_ID) {
+		dev_err(chip->dev, "Invalid device ID: 0x%02x\n", device_id);
+		ret = -ENODEV;
+		goto error;
+	}
+
+	variant_vrc = variant_id & DA9121_MASK_OTP_VARIANT_ID_VRC;
+
+	switch (variant_vrc) {
+	case DA9121_VARIANT_VRC:
+		type = "DA9121/DA9130";
+		config_match = (chip_id == DA9121_TYPE_DA9121_DA9130);
+		break;
+	case DA9220_VARIANT_VRC:
+		type = "DA9220/DA9132";
+		config_match = (chip_id == DA9121_TYPE_DA9220_DA9132);
+		break;
+	case DA9122_VARIANT_VRC:
+		type = "DA9122/DA9131";
+		config_match = (chip_id == DA9121_TYPE_DA9122_DA9131);
+		break;
+	case DA9217_VARIANT_VRC:
+		type = "DA9217";
+		config_match = (chip_id == DA9121_TYPE_DA9217);
+		break;
+	default:
+		type = "Unknown";
+		break;
+	}
+
+	dev_info(chip->dev,
+		 "Device detected (device-ID: 0x%02X, var-ID: 0x%02X, %s)\n",
+		 device_id, variant_id, type);
+
+	if (!config_match) {
+		dev_err(chip->dev, "Device tree configuration '%s' does not match detected device.\n", name);
+		ret = -EINVAL;
+		goto error;
+	}
+
+	variant_mrc = (variant_id & DA9121_MASK_OTP_VARIANT_ID_MRC)
+			>> DA9121_SHIFT_OTP_VARIANT_ID_MRC;
+
+	if ((device_id == DA9121_DEVICE_ID) &&
+	    (variant_mrc < DA9121_VARIANT_MRC_BASE)) {
+		dev_err(chip->dev,
+			"Cannot support variant MRC: 0x%02X\n", variant_mrc);
+		ret = -EINVAL;
+	}
+error:
+	return ret;
+}
+
+static int da9121_assign_chip_model(struct i2c_client *i2c,
+			struct da9121 *chip)
+{
+	struct regmap_config *regmap;
+	int ret = 0;
+
+	chip->dev = &i2c->dev;
+
+	switch (chip->variant_id) {
+	case DA9121_TYPE_DA9121_DA9130:
+		fallthrough;
+	case DA9121_TYPE_DA9217:
+		regmap = &da9121_1ch_regmap_config;
+		break;
+	case DA9121_TYPE_DA9122_DA9131:
+		fallthrough;
+	case DA9121_TYPE_DA9220_DA9132:
+		regmap = &da9121_2ch_regmap_config;
+		break;
+	}
+
+	chip->regmap = devm_regmap_init_i2c(i2c, regmap);
+	if (IS_ERR(chip->regmap)) {
+		ret = PTR_ERR(chip->regmap);
+		dev_err(chip->dev, "Failed to configure a register map: %d\n",
+			ret);
+	}
+
+	ret = da9121_check_device_type(i2c, chip);
+
+	return ret;
+}
+
 static const struct of_device_id da9121_dt_ids[] = {
 	{ .compatible = "dlg,da9121", .data = (void *) DA9121_TYPE_DA9121_DA9130 },
 	{ .compatible = "dlg,da9130", .data = (void *) DA9121_TYPE_DA9121_DA9130 },
@@ -89,7 +298,6 @@ static int da9121_i2c_probe(struct i2c_client *i2c,
 	struct device *dev = &i2c->dev;
 	struct regulator_config config = {};
 	struct regulator_dev *rdev;
-	struct regmap *regmap;
 
 	chip = devm_kzalloc(&i2c->dev, sizeof(struct da9121), GFP_KERNEL);
 	if (!chip) {
@@ -99,13 +307,13 @@ static int da9121_i2c_probe(struct i2c_client *i2c,
 
 	chip->variant_id = da9121_of_get_id(&i2c->dev);
 
-	regmap = devm_regmap_init_i2c(i2c, &da9121_regmap_config);
-	if (IS_ERR(regmap))
-		return PTR_ERR(regmap);
+	ret = da9121_assign_chip_model(i2c, chip);
+	if (ret < 0)
+		goto error;
 
 	config.dev = &i2c->dev;
 	config.of_node = dev->of_node;
-	config.regmap = regmap;
+	config.regmap = chip->regmap;
 
 	rdev = devm_regulator_register(&i2c->dev, &da9121_reg, &config);
 	if (IS_ERR(rdev)) {
diff --git a/include/linux/regulator/da9121.h b/include/linux/regulator/da9121.h
new file mode 100644
index 000000000000..c31180d886cc
--- /dev/null
+++ b/include/linux/regulator/da9121.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * DA9121 Single-channel dual-phase 10A buck converter
+ * DA9130 Single-channel dual-phase 10A buck converter (Automotive)
+ * DA9217 Single-channel dual-phase  6A buck converter
+ * DA9122 Dual-channel single-phase  5A buck converter
+ * DA9131 Dual-channel single-phase  5A buck converter (Automotive)
+ * DA9220 Dual-channel single-phase  3A buck converter
+ * DA9132 Dual-channel single-phase  3A buck converter (Automotive)
+ *
+ * Copyright (C) 2020  Dialog Semiconductor
+ *
+ * Authors: Adam Ward, Dialog Semiconductor
+ */
+
+#ifndef __LINUX_REGULATOR_DA9121_H
+#define __LINUX_REGULATOR_DA9121_H
+
+enum {
+	DA9121_IDX_BUCK1,
+	DA9121_IDX_BUCK2,
+	DA9121_IDX_MAX
+};
+
+#endif
-- 
cgit v1.2.3


From 46c413d5bb239769e6f1de706adf422c807c7a5f Mon Sep 17 00:00:00 2001
From: Adam Ward <Adam.Ward.opensource@diasemi.com>
Date: Mon, 30 Nov 2020 16:59:10 +0000
Subject: regulator: da9121: Add support for device variants via devicetree

Add devicetree configuration and device variant parameters. Use the latter
to enable the check and use of parameters specific to dual buck variants.

Signed-off-by: Adam Ward <Adam.Ward.opensource@diasemi.com>
Link: https://lore.kernel.org/r/5849ce60595aef1018bdde7dcfb54a7397597545.1606755367.git.Adam.Ward.opensource@diasemi.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/da9121-regulator.c | 119 +++++++++++++++++++++++++++++++++++
 include/linux/regulator/da9121.h     |  11 ++++
 2 files changed, 130 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/regulator/da9121-regulator.c b/drivers/regulator/da9121-regulator.c
index a717e2b1da33..1f74371eebad 100644
--- a/drivers/regulator/da9121-regulator.c
+++ b/drivers/regulator/da9121-regulator.c
@@ -14,6 +14,7 @@
 // Copyright (C) 2020 Dialog Semiconductor
 
 #include <linux/of_device.h>
+#include <linux/of_gpio.h>
 #include <linux/regulator/of_regulator.h>
 #include <linux/regulator/machine.h>
 #include <linux/regulator/driver.h>
@@ -28,10 +29,67 @@
 /* Chip data */
 struct da9121 {
 	struct device *dev;
+	struct da9121_pdata *pdata;
 	struct regmap *regmap;
 	int variant_id;
 };
 
+/* Define ranges for different variants, enabling translation to/from
+ * registers. Maximums give scope to allow for transients.
+ */
+struct da9121_range {
+	int val_min;
+	int val_max;
+	int val_stp;
+	int reg_min;
+	int reg_max;
+};
+
+struct da9121_range da9121_10A_2phase_current = {
+	.val_min =  7000000,
+	.val_max = 20000000,
+	.val_stp =  1000000,
+	.reg_min = 1,
+	.reg_max = 14,
+};
+
+struct da9121_range da9121_6A_2phase_current = {
+	.val_min =  7000000,
+	.val_max = 12000000,
+	.val_stp =  1000000,
+	.reg_min = 1,
+	.reg_max = 6,
+};
+
+struct da9121_range da9121_5A_1phase_current = {
+	.val_min =  3500000,
+	.val_max = 10000000,
+	.val_stp =   500000,
+	.reg_min = 1,
+	.reg_max = 14,
+};
+
+struct da9121_range da9121_3A_1phase_current = {
+	.val_min = 3500000,
+	.val_max = 6000000,
+	.val_stp =  500000,
+	.reg_min = 1,
+	.reg_max = 6,
+};
+
+struct da9121_variant_info {
+	int num_bucks;
+	int num_phases;
+	struct da9121_range *current_range;
+};
+
+static const struct da9121_variant_info variant_parameters[] = {
+	{ 1, 2, &da9121_10A_2phase_current },	//DA9121_TYPE_DA9121_DA9130
+	{ 2, 1, &da9121_3A_1phase_current  },	//DA9121_TYPE_DA9220_DA9132
+	{ 2, 1, &da9121_5A_1phase_current  },	//DA9121_TYPE_DA9122_DA9131
+	{ 1, 2, &da9121_6A_2phase_current  },	//DA9121_TYPE_DA9217
+};
+
 static const struct regulator_ops da9121_buck_ops = {
 	.enable = regulator_enable_regmap,
 	.disable = regulator_disable_regmap,
@@ -46,6 +104,59 @@ static struct of_regulator_match da9121_matches[] = {
 	[DA9121_IDX_BUCK2] = { .name = "buck2" },
 };
 
+static int da9121_of_parse_cb(struct device_node *np,
+				const struct regulator_desc *desc,
+				struct regulator_config *config)
+{
+	struct da9121 *chip = config->driver_data;
+	struct da9121_pdata *pdata;
+	struct gpio_desc *ena_gpiod;
+
+	if (chip->pdata == NULL) {
+		pdata = devm_kzalloc(chip->dev, sizeof(*pdata), GFP_KERNEL);
+		if (!pdata)
+			return -ENOMEM;
+	} else {
+		pdata = chip->pdata;
+	}
+
+	pdata->num_buck++;
+
+	if (pdata->num_buck > variant_parameters[chip->variant_id].num_bucks) {
+		dev_err(chip->dev, "Error: excessive regulators for device\n");
+		return -ENODEV;
+	}
+
+	ena_gpiod = fwnode_gpiod_get_index(of_fwnode_handle(np), "enable", 0,
+						GPIOD_OUT_HIGH |
+						GPIOD_FLAGS_BIT_NONEXCLUSIVE,
+						"da9121-enable");
+	if (!IS_ERR(ena_gpiod))
+		config->ena_gpiod = ena_gpiod;
+
+	if (variant_parameters[chip->variant_id].num_bucks == 2) {
+		uint32_t ripple_cancel;
+		uint32_t ripple_reg;
+		int ret;
+
+		if (of_property_read_u32(da9121_matches[pdata->num_buck].of_node,
+				"dlg,ripple-cancel", &ripple_cancel)) {
+			if (pdata->num_buck > 1)
+				ripple_reg = DA9xxx_REG_BUCK_BUCK2_7;
+			else
+				ripple_reg = DA9121_REG_BUCK_BUCK1_7;
+
+			ret = regmap_update_bits(chip->regmap, ripple_reg,
+				DA9xxx_MASK_BUCK_BUCKx_7_CHx_RIPPLE_CANCEL,
+				ripple_cancel);
+			if (ret < 0)
+				dev_err(chip->dev, "Cannot set ripple mode, err: %d\n", ret);
+		}
+	}
+
+	return 0;
+}
+
 #define DA9121_MIN_MV		300
 #define DA9121_MAX_MV		1900
 #define DA9121_STEP_MV		10
@@ -57,6 +168,7 @@ static const struct regulator_desc da9121_reg = {
 	.id = DA9121_IDX_BUCK1,
 	.name = "da9121",
 	.of_match = "buck1",
+	.of_parse_cb = da9121_of_parse_cb,
 	.owner = THIS_MODULE,
 	.regulators_node = of_match_ptr("regulators"),
 	.ops = &da9121_buck_ops,
@@ -80,6 +192,7 @@ static const struct regulator_desc da9220_reg[2] = {
 		.id = DA9121_IDX_BUCK1,
 		.name = "DA9220/DA9132 BUCK1",
 		.of_match = "buck1",
+		.of_parse_cb = da9121_of_parse_cb,
 		.owner = THIS_MODULE,
 		.regulators_node = of_match_ptr("regulators"),
 		.ops = &da9121_buck_ops,
@@ -97,6 +210,7 @@ static const struct regulator_desc da9220_reg[2] = {
 		.id = DA9121_IDX_BUCK2,
 		.name = "DA9220/DA9132 BUCK2",
 		.of_match = "buck2",
+		.of_parse_cb = da9121_of_parse_cb,
 		.owner = THIS_MODULE,
 		.regulators_node = of_match_ptr("regulators"),
 		.ops = &da9121_buck_ops,
@@ -117,6 +231,7 @@ static const struct regulator_desc da9122_reg[2] = {
 		.id = DA9121_IDX_BUCK1,
 		.name = "DA9122/DA9131 BUCK1",
 		.of_match = "buck1",
+		.of_parse_cb = da9121_of_parse_cb,
 		.owner = THIS_MODULE,
 		.regulators_node = of_match_ptr("regulators"),
 		.ops = &da9121_buck_ops,
@@ -134,6 +249,7 @@ static const struct regulator_desc da9122_reg[2] = {
 		.id = DA9121_IDX_BUCK2,
 		.name = "DA9122/DA9131 BUCK2",
 		.of_match = "buck2",
+		.of_parse_cb = da9121_of_parse_cb,
 		.owner = THIS_MODULE,
 		.regulators_node = of_match_ptr("regulators"),
 		.ops = &da9121_buck_ops,
@@ -153,6 +269,7 @@ static const struct regulator_desc da9217_reg = {
 	.id = DA9121_IDX_BUCK1,
 	.name = "DA9217 BUCK1",
 	.of_match = "buck1",
+	.of_parse_cb = da9121_of_parse_cb,
 	.owner = THIS_MODULE,
 	.regulators_node = of_match_ptr("regulators"),
 	.ops = &da9121_buck_ops,
@@ -415,6 +532,7 @@ static int da9121_i2c_probe(struct i2c_client *i2c,
 		goto error;
 	}
 
+	chip->pdata = i2c->dev.platform_data;
 	chip->variant_id = da9121_of_get_id(&i2c->dev);
 
 	ret = da9121_assign_chip_model(i2c, chip);
@@ -422,6 +540,7 @@ static int da9121_i2c_probe(struct i2c_client *i2c,
 		goto error;
 
 	config.dev = &i2c->dev;
+	config.driver_data = chip;
 	config.of_node = dev->of_node;
 	config.regmap = chip->regmap;
 
diff --git a/include/linux/regulator/da9121.h b/include/linux/regulator/da9121.h
index c31180d886cc..62d9d257dc25 100644
--- a/include/linux/regulator/da9121.h
+++ b/include/linux/regulator/da9121.h
@@ -16,10 +16,21 @@
 #ifndef __LINUX_REGULATOR_DA9121_H
 #define __LINUX_REGULATOR_DA9121_H
 
+#include <linux/regulator/machine.h>
+
+struct gpio_desc;
+
 enum {
 	DA9121_IDX_BUCK1,
 	DA9121_IDX_BUCK2,
 	DA9121_IDX_MAX
 };
 
+struct da9121_pdata {
+	int num_buck;
+	struct gpio_desc *gpiod_ren[DA9121_IDX_MAX];
+	struct device_node *reg_node[DA9121_IDX_MAX];
+	struct regulator_init_data *init_data[DA9121_IDX_MAX];
+};
+
 #endif
-- 
cgit v1.2.3


From 57d9352b6c651b090179f8b223b6681275c64a4f Mon Sep 17 00:00:00 2001
From: Moritz Fischer <mdf@kernel.org>
Date: Sun, 15 Nov 2020 11:51:18 -0800
Subject: fpga: fpga-mgr: Add devm_fpga_mgr_register() API

Add a devm_fpga_mgr_register() API that can be used to register a FPGA
Manager that was created using devm_fpga_mgr_create().

Introduce a struct fpga_mgr_devres that makes the devres
allocation a little bit more readable and gets reused for
devm_fpga_mgr_create() devm_fpga_mgr_register().

Reviewed-by: Tom Rix <trix@redhat.com>
Signed-off-by: Moritz Fischer <mdf@kernel.org>
Link: https://lore.kernel.org/r/20201115195127.284487-2-mdf@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/fpga/fpga-mgr.c       | 81 ++++++++++++++++++++++++++++++++++++-------
 include/linux/fpga/fpga-mgr.h |  2 ++
 2 files changed, 71 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/fpga/fpga-mgr.c b/drivers/fpga/fpga-mgr.c
index f38bab01432e..b85bc47c91a9 100644
--- a/drivers/fpga/fpga-mgr.c
+++ b/drivers/fpga/fpga-mgr.c
@@ -21,6 +21,10 @@
 static DEFINE_IDA(fpga_mgr_ida);
 static struct class *fpga_mgr_class;
 
+struct fpga_mgr_devres {
+	struct fpga_manager *mgr;
+};
+
 /**
  * fpga_image_info_alloc - Allocate a FPGA image info struct
  * @dev: owning device
@@ -625,9 +629,9 @@ EXPORT_SYMBOL_GPL(fpga_mgr_free);
 
 static void devm_fpga_mgr_release(struct device *dev, void *res)
 {
-	struct fpga_manager *mgr = *(struct fpga_manager **)res;
+	struct fpga_mgr_devres *dr = res;
 
-	fpga_mgr_free(mgr);
+	fpga_mgr_free(dr->mgr);
 }
 
 /**
@@ -651,21 +655,21 @@ struct fpga_manager *devm_fpga_mgr_create(struct device *dev, const char *name,
 					  const struct fpga_manager_ops *mops,
 					  void *priv)
 {
-	struct fpga_manager **ptr, *mgr;
+	struct fpga_mgr_devres *dr;
 
-	ptr = devres_alloc(devm_fpga_mgr_release, sizeof(*ptr), GFP_KERNEL);
-	if (!ptr)
+	dr = devres_alloc(devm_fpga_mgr_release, sizeof(*dr), GFP_KERNEL);
+	if (!dr)
 		return NULL;
 
-	mgr = fpga_mgr_create(dev, name, mops, priv);
-	if (!mgr) {
-		devres_free(ptr);
-	} else {
-		*ptr = mgr;
-		devres_add(dev, ptr);
+	dr->mgr = fpga_mgr_create(dev, name, mops, priv);
+	if (!dr->mgr) {
+		devres_free(dr);
+		return NULL;
 	}
 
-	return mgr;
+	devres_add(dev, dr);
+
+	return dr->mgr;
 }
 EXPORT_SYMBOL_GPL(devm_fpga_mgr_create);
 
@@ -722,6 +726,59 @@ void fpga_mgr_unregister(struct fpga_manager *mgr)
 }
 EXPORT_SYMBOL_GPL(fpga_mgr_unregister);
 
+static int fpga_mgr_devres_match(struct device *dev, void *res,
+				 void *match_data)
+{
+	struct fpga_mgr_devres *dr = res;
+
+	return match_data == dr->mgr;
+}
+
+static void devm_fpga_mgr_unregister(struct device *dev, void *res)
+{
+	struct fpga_mgr_devres *dr = res;
+
+	fpga_mgr_unregister(dr->mgr);
+}
+
+/**
+ * devm_fpga_mgr_register - resource managed variant of fpga_mgr_register()
+ * @dev: managing device for this FPGA manager
+ * @mgr: fpga manager struct
+ *
+ * This is the devres variant of fpga_mgr_register() for which the unregister
+ * function will be called automatically when the managing device is detached.
+ */
+int devm_fpga_mgr_register(struct device *dev, struct fpga_manager *mgr)
+{
+	struct fpga_mgr_devres *dr;
+	int ret;
+
+	/*
+	 * Make sure that the struct fpga_manager * that is passed in is
+	 * managed itself.
+	 */
+	if (WARN_ON(!devres_find(dev, devm_fpga_mgr_release,
+				 fpga_mgr_devres_match, mgr)))
+		return -EINVAL;
+
+	dr = devres_alloc(devm_fpga_mgr_unregister, sizeof(*dr), GFP_KERNEL);
+	if (!dr)
+		return -ENOMEM;
+
+	ret = fpga_mgr_register(mgr);
+	if (ret) {
+		devres_free(dr);
+		return ret;
+	}
+
+	dr->mgr = mgr;
+	devres_add(dev, dr);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devm_fpga_mgr_register);
+
 static void fpga_mgr_dev_release(struct device *dev)
 {
 }
diff --git a/include/linux/fpga/fpga-mgr.h b/include/linux/fpga/fpga-mgr.h
index e8ca62b2cb5b..2bc3030a69e5 100644
--- a/include/linux/fpga/fpga-mgr.h
+++ b/include/linux/fpga/fpga-mgr.h
@@ -198,6 +198,8 @@ void fpga_mgr_free(struct fpga_manager *mgr);
 int fpga_mgr_register(struct fpga_manager *mgr);
 void fpga_mgr_unregister(struct fpga_manager *mgr);
 
+int devm_fpga_mgr_register(struct device *dev, struct fpga_manager *mgr);
+
 struct fpga_manager *devm_fpga_mgr_create(struct device *dev, const char *name,
 					  const struct fpga_manager_ops *mops,
 					  void *priv);
-- 
cgit v1.2.3


From fa69ee5aa48b5b52e8028c2eb486906e9998d081 Mon Sep 17 00:00:00 2001
From: Marco Elver <elver@google.com>
Date: Wed, 25 Nov 2020 23:48:40 +0100
Subject: net: switch to storing KCOV handle directly in sk_buff

It turns out that usage of skb extensions can cause memory leaks. Ido
Schimmel reported: "[...] there are instances that blindly overwrite
'skb->extensions' by invoking skb_copy_header() after __alloc_skb()."

Therefore, give up on using skb extensions for KCOV handle, and instead
directly store kcov_handle in sk_buff.

Fixes: 6370cc3bbd8a ("net: add kcov handle to skb extensions")
Fixes: 85ce50d337d1 ("net: kcov: don't select SKB_EXTENSIONS when there is no NET")
Fixes: 97f53a08cba1 ("net: linux/skbuff.h: combine SKB_EXTENSIONS + KCOV handling")
Link: https://lore.kernel.org/linux-wireless/20201121160941.GA485907@shredder.lan/
Reported-by: Ido Schimmel <idosch@idosch.org>
Signed-off-by: Marco Elver <elver@google.com>
Link: https://lore.kernel.org/r/20201125224840.2014773-1-elver@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/skbuff.h | 37 +++++++++++++------------------------
 lib/Kconfig.debug      |  1 -
 net/core/skbuff.c      |  6 ------
 3 files changed, 13 insertions(+), 31 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 0a1239819fd2..333bcdc39635 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -701,6 +701,7 @@ typedef unsigned char *sk_buff_data_t;
  *	@transport_header: Transport layer header
  *	@network_header: Network layer header
  *	@mac_header: Link layer header
+ *	@kcov_handle: KCOV remote handle for remote coverage collection
  *	@tail: Tail pointer
  *	@end: End pointer
  *	@head: Head of buffer
@@ -904,6 +905,10 @@ struct sk_buff {
 	__u16			network_header;
 	__u16			mac_header;
 
+#ifdef CONFIG_KCOV
+	u64			kcov_handle;
+#endif
+
 	/* private: */
 	__u32			headers_end[0];
 	/* public: */
@@ -4150,9 +4155,6 @@ enum skb_ext_id {
 #endif
 #if IS_ENABLED(CONFIG_MPTCP)
 	SKB_EXT_MPTCP,
-#endif
-#if IS_ENABLED(CONFIG_KCOV)
-	SKB_EXT_KCOV_HANDLE,
 #endif
 	SKB_EXT_NUM, /* must be last */
 };
@@ -4608,35 +4610,22 @@ static inline void skb_reset_redirect(struct sk_buff *skb)
 #endif
 }
 
-#if IS_ENABLED(CONFIG_KCOV) && IS_ENABLED(CONFIG_SKB_EXTENSIONS)
 static inline void skb_set_kcov_handle(struct sk_buff *skb,
 				       const u64 kcov_handle)
 {
-	/* Do not allocate skb extensions only to set kcov_handle to zero
-	 * (as it is zero by default). However, if the extensions are
-	 * already allocated, update kcov_handle anyway since
-	 * skb_set_kcov_handle can be called to zero a previously set
-	 * value.
-	 */
-	if (skb_has_extensions(skb) || kcov_handle) {
-		u64 *kcov_handle_ptr = skb_ext_add(skb, SKB_EXT_KCOV_HANDLE);
-
-		if (kcov_handle_ptr)
-			*kcov_handle_ptr = kcov_handle;
-	}
+#ifdef CONFIG_KCOV
+	skb->kcov_handle = kcov_handle;
+#endif
 }
 
 static inline u64 skb_get_kcov_handle(struct sk_buff *skb)
 {
-	u64 *kcov_handle = skb_ext_find(skb, SKB_EXT_KCOV_HANDLE);
-
-	return kcov_handle ? *kcov_handle : 0;
-}
+#ifdef CONFIG_KCOV
+	return skb->kcov_handle;
 #else
-static inline void skb_set_kcov_handle(struct sk_buff *skb,
-				       const u64 kcov_handle) { }
-static inline u64 skb_get_kcov_handle(struct sk_buff *skb) { return 0; }
-#endif /* CONFIG_KCOV && CONFIG_SKB_EXTENSIONS */
+	return 0;
+#endif
+}
 
 #endif	/* __KERNEL__ */
 #endif	/* _LINUX_SKBUFF_H */
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 826a205ffd1c..1d15cdaf1b89 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1879,7 +1879,6 @@ config KCOV
 	depends on CC_HAS_SANCOV_TRACE_PC || GCC_PLUGINS
 	select DEBUG_FS
 	select GCC_PLUGIN_SANCOV if !CC_HAS_SANCOV_TRACE_PC
-	select SKB_EXTENSIONS if NET
 	help
 	  KCOV exposes kernel code coverage information in a form suitable
 	  for coverage-guided fuzzing (randomized testing).
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index ad98265f1dd1..90d3423e6017 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4210,9 +4210,6 @@ static const u8 skb_ext_type_len[] = {
 #if IS_ENABLED(CONFIG_MPTCP)
 	[SKB_EXT_MPTCP] = SKB_EXT_CHUNKSIZEOF(struct mptcp_ext),
 #endif
-#if IS_ENABLED(CONFIG_KCOV)
-	[SKB_EXT_KCOV_HANDLE] = SKB_EXT_CHUNKSIZEOF(u64),
-#endif
 };
 
 static __always_inline unsigned int skb_ext_total_length(void)
@@ -4229,9 +4226,6 @@ static __always_inline unsigned int skb_ext_total_length(void)
 #endif
 #if IS_ENABLED(CONFIG_MPTCP)
 		skb_ext_type_len[SKB_EXT_MPTCP] +
-#endif
-#if IS_ENABLED(CONFIG_KCOV)
-		skb_ext_type_len[SKB_EXT_KCOV_HANDLE] +
 #endif
 		0;
 }
-- 
cgit v1.2.3


From 53ffabfd4ddb3a24c5603ae82eefb5537ecb5c20 Mon Sep 17 00:00:00 2001
From: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Date: Mon, 9 Nov 2020 18:24:03 -0800
Subject: block: move blk_rq_bio_prep() to linux/blk-mq.h

This is a preparation patch to have minimal block layer request bio
append functionality in the context of the NVMeOF Passthru driver which
falls in the fast path and doesn't need calls from blk_rq_append_bio().

Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 block/blk.h            | 12 ------------
 include/linux/blk-mq.h | 12 ++++++++++++
 2 files changed, 12 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk.h b/block/blk.h
index dfab98465db9..e05507a8d1e3 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -91,18 +91,6 @@ static inline bool bvec_gap_to_prev(struct request_queue *q,
 	return __bvec_gap_to_prev(q, bprv, offset);
 }
 
-static inline void blk_rq_bio_prep(struct request *rq, struct bio *bio,
-		unsigned int nr_segs)
-{
-	rq->nr_phys_segments = nr_segs;
-	rq->__data_len = bio->bi_iter.bi_size;
-	rq->bio = rq->biotail = bio;
-	rq->ioprio = bio_prio(bio);
-
-	if (bio->bi_disk)
-		rq->rq_disk = bio->bi_disk;
-}
-
 #ifdef CONFIG_BLK_DEV_INTEGRITY
 void blk_flush_integrity(void);
 bool __bio_integrity_endio(struct bio *);
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 794b2a33a2c3..e7482e6ad3ec 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -593,6 +593,18 @@ static inline void blk_mq_cleanup_rq(struct request *rq)
 		rq->q->mq_ops->cleanup_rq(rq);
 }
 
+static inline void blk_rq_bio_prep(struct request *rq, struct bio *bio,
+		unsigned int nr_segs)
+{
+	rq->nr_phys_segments = nr_segs;
+	rq->__data_len = bio->bi_iter.bi_size;
+	rq->bio = rq->biotail = bio;
+	rq->ioprio = bio_prio(bio);
+
+	if (bio->bi_disk)
+		rq->rq_disk = bio->bi_disk;
+}
+
 blk_qc_t blk_mq_submit_bio(struct bio *bio);
 
 #endif
-- 
cgit v1.2.3


From b6f8ed33ab2bbc58e40fb1e2fb0f9c90cab04baf Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 16 Oct 2020 15:20:41 +0200
Subject: pstore/blk: remove {un,}register_pstore_blk

This interface is entirely unused, so remove them and various bits of
unreachable code.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20201016132047.3068029-4-hch@lst.de
---
 Documentation/admin-guide/pstore-blk.rst |  5 +-
 fs/pstore/blk.c                          | 83 ++++----------------------------
 include/linux/pstore_blk.h               | 42 ----------------
 3 files changed, 11 insertions(+), 119 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/admin-guide/pstore-blk.rst b/Documentation/admin-guide/pstore-blk.rst
index 83543cb3daa1..49d8149f8d32 100644
--- a/Documentation/admin-guide/pstore-blk.rst
+++ b/Documentation/admin-guide/pstore-blk.rst
@@ -151,10 +151,7 @@ otherwise KMSG_DUMP_MAX.
 Configurations for driver
 -------------------------
 
-Only a block device driver cares about these configurations. A block device
-driver uses ``register_pstore_blk`` to register to pstore/blk.
-
-A non-block device driver uses ``register_pstore_device`` with
+A device driver uses ``register_pstore_device`` with
 ``struct pstore_device_info`` to register to pstore/blk.
 
 .. kernel-doc:: fs/pstore/blk.c
diff --git a/fs/pstore/blk.c b/fs/pstore/blk.c
index fcd5563dde06..882d0bc0cfd7 100644
--- a/fs/pstore/blk.c
+++ b/fs/pstore/blk.c
@@ -90,7 +90,6 @@ MODULE_PARM_DESC(blkdev, "block device for pstore storage");
 static DEFINE_MUTEX(pstore_blk_lock);
 static struct block_device *psblk_bdev;
 static struct pstore_zone_info *pstore_zone_info;
-static pstore_blk_panic_write_op blkdev_panic_write;
 
 struct bdev_info {
 	dev_t devt;
@@ -341,24 +340,11 @@ static ssize_t psblk_generic_blk_write(const char *buf, size_t bytes,
 	return ret;
 }
 
-static ssize_t psblk_blk_panic_write(const char *buf, size_t size,
-		loff_t off)
-{
-	int ret;
-
-	if (!blkdev_panic_write)
-		return -EOPNOTSUPP;
-
-	/* size and off must align to SECTOR_SIZE for block device */
-	ret = blkdev_panic_write(buf, off >> SECTOR_SHIFT,
-			size >> SECTOR_SHIFT);
-	/* try next zone */
-	if (ret == -ENOMSG)
-		return ret;
-	return ret ? -EIO : size;
-}
-
-static int __register_pstore_blk(struct pstore_blk_info *info)
+/*
+ * This takes its configuration only from the module parameters now.
+ * See psblk_get_bdev() and blkdev.
+ */
+static int __register_pstore_blk(void)
 {
 	char bdev_name[BDEVNAME_SIZE];
 	struct block_device *bdev;
@@ -378,68 +364,34 @@ static int __register_pstore_blk(struct pstore_blk_info *info)
 	}
 
 	/* only allow driver matching the @blkdev */
-	if (!binfo.devt || (!best_effort &&
-			    MAJOR(binfo.devt) != info->major)) {
-		pr_debug("invalid major %u (expect %u)\n",
-				info->major, MAJOR(binfo.devt));
+	if (!binfo.devt) {
+		pr_debug("no major\n");
 		ret = -ENODEV;
 		goto err_put_bdev;
 	}
 
 	/* psblk_bdev must be assigned before register to pstore/blk */
 	psblk_bdev = bdev;
-	blkdev_panic_write = info->panic_write;
-
-	/* Copy back block device details. */
-	info->devt = binfo.devt;
-	info->nr_sects = binfo.nr_sects;
-	info->start_sect = binfo.start_sect;
 
 	memset(&dev, 0, sizeof(dev));
-	dev.total_size = info->nr_sects << SECTOR_SHIFT;
-	dev.flags = info->flags;
+	dev.total_size = binfo.nr_sects << SECTOR_SHIFT;
 	dev.read = psblk_generic_blk_read;
 	dev.write = psblk_generic_blk_write;
-	dev.erase = NULL;
-	dev.panic_write = info->panic_write ? psblk_blk_panic_write : NULL;
 
 	ret = __register_pstore_device(&dev);
 	if (ret)
 		goto err_put_bdev;
 
 	bdevname(bdev, bdev_name);
-	pr_info("attached %s%s\n", bdev_name,
-		info->panic_write ? "" : " (no dedicated panic_write!)");
+	pr_info("attached %s (no dedicated panic_write!)\n", bdev_name);
 	return 0;
 
 err_put_bdev:
 	psblk_bdev = NULL;
-	blkdev_panic_write = NULL;
 	psblk_put_bdev(bdev, holder);
 	return ret;
 }
 
-/**
- * register_pstore_blk() - register block device to pstore/blk
- *
- * @info: details on the desired block device interface
- *
- * Return:
- * * 0		- OK
- * * Others	- something error.
- */
-int register_pstore_blk(struct pstore_blk_info *info)
-{
-	int ret;
-
-	mutex_lock(&pstore_blk_lock);
-	ret = __register_pstore_blk(info);
-	mutex_unlock(&pstore_blk_lock);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(register_pstore_blk);
-
 static void __unregister_pstore_blk(unsigned int major)
 {
 	struct pstore_device_info dev = { .read = psblk_generic_blk_read };
@@ -449,24 +401,10 @@ static void __unregister_pstore_blk(unsigned int major)
 	if (psblk_bdev && MAJOR(psblk_bdev->bd_dev) == major) {
 		__unregister_pstore_device(&dev);
 		psblk_put_bdev(psblk_bdev, holder);
-		blkdev_panic_write = NULL;
 		psblk_bdev = NULL;
 	}
 }
 
-/**
- * unregister_pstore_blk() - unregister block device from pstore/blk
- *
- * @major: the major device number of device
- */
-void unregister_pstore_blk(unsigned int major)
-{
-	mutex_lock(&pstore_blk_lock);
-	__unregister_pstore_blk(major);
-	mutex_unlock(&pstore_blk_lock);
-}
-EXPORT_SYMBOL_GPL(unregister_pstore_blk);
-
 /* get information of pstore/blk */
 int pstore_blk_get_config(struct pstore_blk_config *info)
 {
@@ -483,12 +421,11 @@ EXPORT_SYMBOL_GPL(pstore_blk_get_config);
 
 static int __init pstore_blk_init(void)
 {
-	struct pstore_blk_info info = { };
 	int ret = 0;
 
 	mutex_lock(&pstore_blk_lock);
 	if (!pstore_zone_info && best_effort && blkdev[0])
-		ret = __register_pstore_blk(&info);
+		ret = __register_pstore_blk();
 	mutex_unlock(&pstore_blk_lock);
 
 	return ret;
diff --git a/include/linux/pstore_blk.h b/include/linux/pstore_blk.h
index 61e914522b01..99564f93d774 100644
--- a/include/linux/pstore_blk.h
+++ b/include/linux/pstore_blk.h
@@ -7,48 +7,6 @@
 #include <linux/pstore.h>
 #include <linux/pstore_zone.h>
 
-/**
- * typedef pstore_blk_panic_write_op - panic write operation to block device
- *
- * @buf: the data to write
- * @start_sect: start sector to block device
- * @sects: sectors count on buf
- *
- * Return: On success, zero should be returned. Others excluding -ENOMSG
- * mean error. -ENOMSG means to try next zone.
- *
- * Panic write to block device must be aligned to SECTOR_SIZE.
- */
-typedef int (*pstore_blk_panic_write_op)(const char *buf, sector_t start_sect,
-		sector_t sects);
-
-/**
- * struct pstore_blk_info - pstore/blk registration details
- *
- * @major:	Which major device number to support with pstore/blk
- * @flags:	The supported PSTORE_FLAGS_* from linux/pstore.h.
- * @panic_write:The write operation only used for the panic case.
- *		This can be NULL, but is recommended to avoid losing
- *		crash data if the kernel's IO path or work queues are
- *		broken during a panic.
- * @devt:	The dev_t that pstore/blk has attached to.
- * @nr_sects:	Number of sectors on @devt.
- * @start_sect:	Starting sector on @devt.
- */
-struct pstore_blk_info {
-	unsigned int major;
-	unsigned int flags;
-	pstore_blk_panic_write_op panic_write;
-
-	/* Filled in by pstore/blk after registration. */
-	dev_t devt;
-	sector_t nr_sects;
-	sector_t start_sect;
-};
-
-int  register_pstore_blk(struct pstore_blk_info *info);
-void unregister_pstore_blk(unsigned int major);
-
 /**
  * struct pstore_device_info - back-end pstore/blk driver structure.
  *
-- 
cgit v1.2.3


From 60b498852bf219c0bf2b0864c69972840978ca43 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 16 Nov 2020 15:21:18 +0100
Subject: fs: remove get_super_thawed and get_super_exclusive_thawed

Just open code the wait in the only caller of both functions.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/internal.h      |  2 ++
 fs/quota/quota.c   | 31 ++++++++++++++++++++++++-------
 fs/super.c         | 51 ++-------------------------------------------------
 include/linux/fs.h |  4 +---
 4 files changed, 29 insertions(+), 59 deletions(-)

(limited to 'include/linux')

diff --git a/fs/internal.h b/fs/internal.h
index a7cd0f64faa4..47be21dfeebe 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -114,7 +114,9 @@ extern struct file *alloc_empty_file_noaccount(int, const struct cred *);
  */
 extern int reconfigure_super(struct fs_context *);
 extern bool trylock_super(struct super_block *sb);
+struct super_block *__get_super(struct block_device *bdev, bool excl);
 extern struct super_block *user_get_super(dev_t);
+void put_super(struct super_block *sb);
 extern bool mount_capable(struct fs_context *);
 
 /*
diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index 9af95c7a0bbe..f3d32b0d9008 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -20,6 +20,7 @@
 #include <linux/writeback.h>
 #include <linux/nospec.h>
 #include "compat.h"
+#include "../internal.h"
 
 static int check_quotactl_permission(struct super_block *sb, int type, int cmd,
 				     qid_t id)
@@ -868,6 +869,7 @@ static struct super_block *quotactl_block(const char __user *special, int cmd)
 	struct block_device *bdev;
 	struct super_block *sb;
 	struct filename *tmp = getname(special);
+	bool excl = false, thawed = false;
 
 	if (IS_ERR(tmp))
 		return ERR_CAST(tmp);
@@ -875,17 +877,32 @@ static struct super_block *quotactl_block(const char __user *special, int cmd)
 	putname(tmp);
 	if (IS_ERR(bdev))
 		return ERR_CAST(bdev);
-	if (quotactl_cmd_onoff(cmd))
-		sb = get_super_exclusive_thawed(bdev);
-	else if (quotactl_cmd_write(cmd))
-		sb = get_super_thawed(bdev);
-	else
-		sb = get_super(bdev);
+
+	if (quotactl_cmd_onoff(cmd)) {
+		excl = true;
+		thawed = true;
+	} else if (quotactl_cmd_write(cmd)) {
+		thawed = true;
+	}
+
+retry:
+	sb = __get_super(bdev, excl);
+	if (thawed && sb && sb->s_writers.frozen != SB_UNFROZEN) {
+		if (excl)
+			up_write(&sb->s_umount);
+		else
+			up_read(&sb->s_umount);
+		wait_event(sb->s_writers.wait_unfrozen,
+			   sb->s_writers.frozen == SB_UNFROZEN);
+		put_super(sb);
+		goto retry;
+	}
+
 	bdput(bdev);
 	if (!sb)
 		return ERR_PTR(-ENODEV);
-
 	return sb;
+
 #else
 	return ERR_PTR(-ENODEV);
 #endif
diff --git a/fs/super.c b/fs/super.c
index 98bb0629ee10..343e5c1e538d 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -307,7 +307,7 @@ static void __put_super(struct super_block *s)
  *	Drops a temporary reference, frees superblock if there's no
  *	references left.
  */
-static void put_super(struct super_block *sb)
+void put_super(struct super_block *sb)
 {
 	spin_lock(&sb_lock);
 	__put_super(sb);
@@ -740,7 +740,7 @@ void iterate_supers_type(struct file_system_type *type,
 
 EXPORT_SYMBOL(iterate_supers_type);
 
-static struct super_block *__get_super(struct block_device *bdev, bool excl)
+struct super_block *__get_super(struct block_device *bdev, bool excl)
 {
 	struct super_block *sb;
 
@@ -789,53 +789,6 @@ struct super_block *get_super(struct block_device *bdev)
 }
 EXPORT_SYMBOL(get_super);
 
-static struct super_block *__get_super_thawed(struct block_device *bdev,
-					      bool excl)
-{
-	while (1) {
-		struct super_block *s = __get_super(bdev, excl);
-		if (!s || s->s_writers.frozen == SB_UNFROZEN)
-			return s;
-		if (!excl)
-			up_read(&s->s_umount);
-		else
-			up_write(&s->s_umount);
-		wait_event(s->s_writers.wait_unfrozen,
-			   s->s_writers.frozen == SB_UNFROZEN);
-		put_super(s);
-	}
-}
-
-/**
- *	get_super_thawed - get thawed superblock of a device
- *	@bdev: device to get the superblock for
- *
- *	Scans the superblock list and finds the superblock of the file system
- *	mounted on the device. The superblock is returned once it is thawed
- *	(or immediately if it was not frozen). %NULL is returned if no match
- *	is found.
- */
-struct super_block *get_super_thawed(struct block_device *bdev)
-{
-	return __get_super_thawed(bdev, false);
-}
-EXPORT_SYMBOL(get_super_thawed);
-
-/**
- *	get_super_exclusive_thawed - get thawed superblock of a device
- *	@bdev: device to get the superblock for
- *
- *	Scans the superblock list and finds the superblock of the file system
- *	mounted on the device. The superblock is returned once it is thawed
- *	(or immediately if it was not frozen) and s_umount semaphore is held
- *	in exclusive mode. %NULL is returned if no match is found.
- */
-struct super_block *get_super_exclusive_thawed(struct block_device *bdev)
-{
-	return __get_super_thawed(bdev, true);
-}
-EXPORT_SYMBOL(get_super_exclusive_thawed);
-
 /**
  * get_active_super - get an active reference to the superblock of a device
  * @bdev: device to get the superblock for
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 8667d0cdc71e..a61df0dd4f19 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1409,7 +1409,7 @@ enum {
 
 struct sb_writers {
 	int				frozen;		/* Is sb frozen? */
-	wait_queue_head_t		wait_unfrozen;	/* for get_super_thawed() */
+	wait_queue_head_t		wait_unfrozen;	/* wait for thaw */
 	struct percpu_rw_semaphore	rw_sem[SB_FREEZE_LEVELS];
 };
 
@@ -3132,8 +3132,6 @@ extern struct file_system_type *get_filesystem(struct file_system_type *fs);
 extern void put_filesystem(struct file_system_type *fs);
 extern struct file_system_type *get_fs_type(const char *name);
 extern struct super_block *get_super(struct block_device *);
-extern struct super_block *get_super_thawed(struct block_device *);
-extern struct super_block *get_super_exclusive_thawed(struct block_device *bdev);
 extern struct super_block *get_active_super(struct block_device *bdev);
 extern void drop_super(struct super_block *sb);
 extern void drop_super_exclusive(struct super_block *sb);
-- 
cgit v1.2.3


From 040f04bd2e825f1d80b14a0e0ac3d830339eb779 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 24 Nov 2020 11:54:06 +0100
Subject: fs: simplify freeze_bdev/thaw_bdev

Store the frozen superblock in struct block_device to avoid the awkward
interface that can return a sb only used a cookie, an ERR_PTR or NULL.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Acked-by: Chao Yu <yuchao0@huawei.com>		[f2fs]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/dm-core.h      |  5 -----
 drivers/md/dm.c           | 20 ++++++--------------
 fs/block_dev.c            | 37 +++++++++++++++----------------------
 fs/buffer.c               |  2 +-
 fs/ext4/ioctl.c           |  2 +-
 fs/f2fs/file.c            | 14 +++++---------
 fs/xfs/xfs_fsops.c        |  7 ++-----
 include/linux/blk_types.h |  1 +
 include/linux/blkdev.h    |  4 ++--
 9 files changed, 33 insertions(+), 59 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h
index d522093cb39d..aace147effca 100644
--- a/drivers/md/dm-core.h
+++ b/drivers/md/dm-core.h
@@ -96,11 +96,6 @@ struct mapped_device {
 	 */
 	struct workqueue_struct *wq;
 
-	/*
-	 * freeze/thaw support require holding onto a super block
-	 */
-	struct super_block *frozen_sb;
-
 	/* forced geometry settings */
 	struct hd_geometry geometry;
 
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 54739f1b579b..50541d336c71 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -2392,27 +2392,19 @@ static int lock_fs(struct mapped_device *md)
 {
 	int r;
 
-	WARN_ON(md->frozen_sb);
+	WARN_ON(test_bit(DMF_FROZEN, &md->flags));
 
-	md->frozen_sb = freeze_bdev(md->bdev);
-	if (IS_ERR(md->frozen_sb)) {
-		r = PTR_ERR(md->frozen_sb);
-		md->frozen_sb = NULL;
-		return r;
-	}
-
-	set_bit(DMF_FROZEN, &md->flags);
-
-	return 0;
+	r = freeze_bdev(md->bdev);
+	if (!r)
+		set_bit(DMF_FROZEN, &md->flags);
+	return r;
 }
 
 static void unlock_fs(struct mapped_device *md)
 {
 	if (!test_bit(DMF_FROZEN, &md->flags))
 		return;
-
-	thaw_bdev(md->bdev, md->frozen_sb);
-	md->frozen_sb = NULL;
+	thaw_bdev(md->bdev);
 	clear_bit(DMF_FROZEN, &md->flags);
 }
 
diff --git a/fs/block_dev.c b/fs/block_dev.c
index d8664f5c1ff6..33c29106c989 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -548,55 +548,47 @@ EXPORT_SYMBOL(fsync_bdev);
  * count down in thaw_bdev(). When it becomes 0, thaw_bdev() will unfreeze
  * actually.
  */
-struct super_block *freeze_bdev(struct block_device *bdev)
+int freeze_bdev(struct block_device *bdev)
 {
 	struct super_block *sb;
 	int error = 0;
 
 	mutex_lock(&bdev->bd_fsfreeze_mutex);
-	if (++bdev->bd_fsfreeze_count > 1) {
-		/*
-		 * We don't even need to grab a reference - the first call
-		 * to freeze_bdev grab an active reference and only the last
-		 * thaw_bdev drops it.
-		 */
-		sb = get_super(bdev);
-		if (sb)
-			drop_super(sb);
-		mutex_unlock(&bdev->bd_fsfreeze_mutex);
-		return sb;
-	}
+	if (++bdev->bd_fsfreeze_count > 1)
+		goto done;
 
 	sb = get_active_super(bdev);
 	if (!sb)
-		goto out;
+		goto sync;
 	if (sb->s_op->freeze_super)
 		error = sb->s_op->freeze_super(sb);
 	else
 		error = freeze_super(sb);
+	deactivate_super(sb);
+
 	if (error) {
-		deactivate_super(sb);
 		bdev->bd_fsfreeze_count--;
-		mutex_unlock(&bdev->bd_fsfreeze_mutex);
-		return ERR_PTR(error);
+		goto done;
 	}
-	deactivate_super(sb);
- out:
+	bdev->bd_fsfreeze_sb = sb;
+
+sync:
 	sync_blockdev(bdev);
+done:
 	mutex_unlock(&bdev->bd_fsfreeze_mutex);
-	return sb;	/* thaw_bdev releases s->s_umount */
+	return error;
 }
 EXPORT_SYMBOL(freeze_bdev);
 
 /**
  * thaw_bdev  -- unlock filesystem
  * @bdev:	blockdevice to unlock
- * @sb:		associated superblock
  *
  * Unlocks the filesystem and marks it writeable again after freeze_bdev().
  */
-int thaw_bdev(struct block_device *bdev, struct super_block *sb)
+int thaw_bdev(struct block_device *bdev)
 {
+	struct super_block *sb;
 	int error = -EINVAL;
 
 	mutex_lock(&bdev->bd_fsfreeze_mutex);
@@ -607,6 +599,7 @@ int thaw_bdev(struct block_device *bdev, struct super_block *sb)
 	if (--bdev->bd_fsfreeze_count > 0)
 		goto out;
 
+	sb = bdev->bd_fsfreeze_sb;
 	if (!sb)
 		goto out;
 
diff --git a/fs/buffer.c b/fs/buffer.c
index 23f645657488..a7595ada9400 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -523,7 +523,7 @@ repeat:
 
 void emergency_thaw_bdev(struct super_block *sb)
 {
-	while (sb->s_bdev && !thaw_bdev(sb->s_bdev, sb))
+	while (sb->s_bdev && !thaw_bdev(sb->s_bdev))
 		printk(KERN_WARNING "Emergency Thaw on %pg\n", sb->s_bdev);
 }
 
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index f0381876a7e5..524e13432447 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -624,7 +624,7 @@ static int ext4_shutdown(struct super_block *sb, unsigned long arg)
 	case EXT4_GOING_FLAGS_DEFAULT:
 		freeze_bdev(sb->s_bdev);
 		set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
-		thaw_bdev(sb->s_bdev, sb);
+		thaw_bdev(sb->s_bdev);
 		break;
 	case EXT4_GOING_FLAGS_LOGFLUSH:
 		set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index ee861c6d9ff0..a9fc482a0e60 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -2230,16 +2230,12 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
 
 	switch (in) {
 	case F2FS_GOING_DOWN_FULLSYNC:
-		sb = freeze_bdev(sb->s_bdev);
-		if (IS_ERR(sb)) {
-			ret = PTR_ERR(sb);
+		ret = freeze_bdev(sb->s_bdev);
+		if (ret)
 			goto out;
-		}
-		if (sb) {
-			f2fs_stop_checkpoint(sbi, false);
-			set_sbi_flag(sbi, SBI_IS_SHUTDOWN);
-			thaw_bdev(sb->s_bdev, sb);
-		}
+		f2fs_stop_checkpoint(sbi, false);
+		set_sbi_flag(sbi, SBI_IS_SHUTDOWN);
+		thaw_bdev(sb->s_bdev);
 		break;
 	case F2FS_GOING_DOWN_METASYNC:
 		/* do checkpoint only */
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index ef1d5bb88b93..b7c5783a031c 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -433,13 +433,10 @@ xfs_fs_goingdown(
 {
 	switch (inflags) {
 	case XFS_FSOP_GOING_FLAGS_DEFAULT: {
-		struct super_block *sb = freeze_bdev(mp->m_super->s_bdev);
-
-		if (sb && !IS_ERR(sb)) {
+		if (!freeze_bdev(mp->m_super->s_bdev)) {
 			xfs_force_shutdown(mp, SHUTDOWN_FORCE_UMOUNT);
-			thaw_bdev(sb->s_bdev, sb);
+			thaw_bdev(mp->m_super->s_bdev);
 		}
-
 		break;
 	}
 	case XFS_FSOP_GOING_FLAGS_LOGFLUSH:
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index d9b69bbde5cc..ebfb4e7c1fd1 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -46,6 +46,7 @@ struct block_device {
 	int			bd_fsfreeze_count;
 	/* Mutex for freeze */
 	struct mutex		bd_fsfreeze_mutex;
+	struct super_block	*bd_fsfreeze_sb;
 } __randomize_layout;
 
 /*
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 05b346a68c2e..12810a19edeb 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -2020,7 +2020,7 @@ static inline int sync_blockdev(struct block_device *bdev)
 #endif
 int fsync_bdev(struct block_device *bdev);
 
-struct super_block *freeze_bdev(struct block_device *bdev);
-int thaw_bdev(struct block_device *bdev, struct super_block *sb);
+int freeze_bdev(struct block_device *bdev);
+int thaw_bdev(struct block_device *bdev);
 
 #endif /* _LINUX_BLKDEV_H */
-- 
cgit v1.2.3


From b601d148a16ea16dfbaf3600be35ee175847a09b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 27 Nov 2020 16:21:52 +0100
Subject: block: remove a duplicate __disk_get_part prototype

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/genhd.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 46553d6d6025..22f5b9fd96f8 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -250,7 +250,6 @@ static inline dev_t part_devt(struct hd_struct *part)
 	return part_to_dev(part)->devt;
 }
 
-extern struct hd_struct *__disk_get_part(struct gendisk *disk, int partno);
 extern struct hd_struct *disk_get_part(struct gendisk *disk, int partno);
 
 static inline void disk_put_part(struct hd_struct *part)
-- 
cgit v1.2.3


From 8d65269fe8065fee889bca5b204d711b0695a8f6 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 17 Nov 2020 08:18:55 +0100
Subject: block: add a bdev_kobj helper

Add a little helper to find the kobject for a struct block_device.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Acked-by: Tejun Heo <tj@kernel.org>
Acked-by: Coly Li <colyli@suse.de>		[bcache]
Acked-by: David Sterba <dsterba@suse.com>	[btrfs]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/bcache/super.c |  7 ++-----
 drivers/md/md.c           |  4 +---
 fs/block_dev.c            |  6 +++---
 fs/btrfs/sysfs.c          | 15 +++------------
 include/linux/blk_types.h |  3 +++
 5 files changed, 12 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 46a00134a36a..a6a5e21e4fd1 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1447,8 +1447,7 @@ static int register_bdev(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
 		goto err;
 
 	err = "error creating kobject";
-	if (kobject_add(&dc->disk.kobj, &part_to_dev(bdev->bd_part)->kobj,
-			"bcache"))
+	if (kobject_add(&dc->disk.kobj, bdev_kobj(bdev), "bcache"))
 		goto err;
 	if (bch_cache_accounting_add_kobjs(&dc->accounting, &dc->disk.kobj))
 		goto err;
@@ -2342,9 +2341,7 @@ static int register_cache(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
 		goto err;
 	}
 
-	if (kobject_add(&ca->kobj,
-			&part_to_dev(bdev->bd_part)->kobj,
-			"bcache")) {
+	if (kobject_add(&ca->kobj, bdev_kobj(bdev), "bcache")) {
 		err = "error calling kobject_add";
 		ret = -ENOMEM;
 		goto out;
diff --git a/drivers/md/md.c b/drivers/md/md.c
index b2edf5e0f965..7ce6047c856e 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -2414,7 +2414,6 @@ EXPORT_SYMBOL(md_integrity_add_rdev);
 static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev)
 {
 	char b[BDEVNAME_SIZE];
-	struct kobject *ko;
 	int err;
 
 	/* prevent duplicates */
@@ -2477,9 +2476,8 @@ static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev)
 	if ((err = kobject_add(&rdev->kobj, &mddev->kobj, "dev-%s", b)))
 		goto fail;
 
-	ko = &part_to_dev(rdev->bdev->bd_part)->kobj;
 	/* failure here is OK */
-	err = sysfs_create_link(&rdev->kobj, ko, "block");
+	err = sysfs_create_link(&rdev->kobj, bdev_kobj(rdev->bdev), "block");
 	rdev->sysfs_state = sysfs_get_dirent_safe(rdev->kobj.sd, "state");
 	rdev->sysfs_unack_badblocks =
 		sysfs_get_dirent_safe(rdev->kobj.sd, "unacknowledged_bad_blocks");
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 33c29106c989..c5755150c6be 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1242,7 +1242,7 @@ int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk)
 	holder->disk = disk;
 	holder->refcnt = 1;
 
-	ret = add_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj);
+	ret = add_symlink(disk->slave_dir, bdev_kobj(bdev));
 	if (ret)
 		goto out_free;
 
@@ -1259,7 +1259,7 @@ int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk)
 	goto out_unlock;
 
 out_del:
-	del_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj);
+	del_symlink(disk->slave_dir, bdev_kobj(bdev));
 out_free:
 	kfree(holder);
 out_unlock:
@@ -1287,7 +1287,7 @@ void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk)
 	holder = bd_find_holder_disk(bdev, disk);
 
 	if (!WARN_ON_ONCE(holder == NULL) && !--holder->refcnt) {
-		del_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj);
+		del_symlink(disk->slave_dir, bdev_kobj(bdev));
 		del_symlink(bdev->bd_part->holder_dir,
 			    &disk_to_dev(disk)->kobj);
 		kobject_put(bdev->bd_part->holder_dir);
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 279d9262b676..24b6c6dc6900 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -1232,8 +1232,6 @@ int btrfs_sysfs_add_space_info_type(struct btrfs_fs_info *fs_info,
 
 void btrfs_sysfs_remove_device(struct btrfs_device *device)
 {
-	struct hd_struct *disk;
-	struct kobject *disk_kobj;
 	struct kobject *devices_kobj;
 
 	/*
@@ -1243,11 +1241,8 @@ void btrfs_sysfs_remove_device(struct btrfs_device *device)
 	devices_kobj = device->fs_info->fs_devices->devices_kobj;
 	ASSERT(devices_kobj);
 
-	if (device->bdev) {
-		disk = device->bdev->bd_part;
-		disk_kobj = &part_to_dev(disk)->kobj;
-		sysfs_remove_link(devices_kobj, disk_kobj->name);
-	}
+	if (device->bdev)
+		sysfs_remove_link(devices_kobj, bdev_kobj(device->bdev)->name);
 
 	if (device->devid_kobj.state_initialized) {
 		kobject_del(&device->devid_kobj);
@@ -1353,11 +1348,7 @@ int btrfs_sysfs_add_device(struct btrfs_device *device)
 	nofs_flag = memalloc_nofs_save();
 
 	if (device->bdev) {
-		struct hd_struct *disk;
-		struct kobject *disk_kobj;
-
-		disk = device->bdev->bd_part;
-		disk_kobj = &part_to_dev(disk)->kobj;
+		struct kobject *disk_kobj = bdev_kobj(device->bdev);
 
 		ret = sysfs_create_link(devices_kobj, disk_kobj, disk_kobj->name);
 		if (ret) {
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index ebfb4e7c1fd1..9698f459cc65 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -49,6 +49,9 @@ struct block_device {
 	struct super_block	*bd_fsfreeze_sb;
 } __randomize_layout;
 
+#define bdev_kobj(_bdev) \
+	(&part_to_dev((_bdev)->bd_part)->kobj)
+
 /*
  * Block error status values.  See block/blk-core:blk_errors for the details.
  * Alpha cannot write a byte atomically, so we need to use 32-bit value.
-- 
cgit v1.2.3


From c2637e80a09e0d6c698d2771d7230f59c2138122 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 14 Nov 2020 19:19:57 +0100
Subject: init: refactor name_to_dev_t

Split each case into a self-contained helper, and move the block
dependent code entirely under the pre-existing #ifdef CONFIG_BLOCK.
This allows to remove the blk_lookup_devt stub in genhd.h.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/genhd.h |   7 +-
 init/do_mounts.c      | 183 +++++++++++++++++++++++++-------------------------
 2 files changed, 91 insertions(+), 99 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 22f5b9fd96f8..ca5e356084c3 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -388,18 +388,13 @@ static inline void bd_unlink_disk_holder(struct block_device *bdev,
 }
 #endif /* CONFIG_SYSFS */
 
+dev_t blk_lookup_devt(const char *name, int partno);
 #ifdef CONFIG_BLOCK
 void printk_all_partitions(void);
-dev_t blk_lookup_devt(const char *name, int partno);
 #else /* CONFIG_BLOCK */
 static inline void printk_all_partitions(void)
 {
 }
-static inline dev_t blk_lookup_devt(const char *name, int partno)
-{
-	dev_t devt = MKDEV(0, 0);
-	return devt;
-}
 #endif /* CONFIG_BLOCK */
 
 #endif /* _LINUX_GENHD_H */
diff --git a/init/do_mounts.c b/init/do_mounts.c
index b5f9604d0c98..aef2f24461c7 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -90,7 +90,6 @@ no_match:
 	return 0;
 }
 
-
 /**
  * devt_from_partuuid - looks up the dev_t of a partition by its UUID
  * @uuid_str:	char array containing ascii UUID
@@ -186,7 +185,83 @@ static int match_dev_by_label(struct device *dev, const void *data)
 
 	return 0;
 }
-#endif
+
+static dev_t devt_from_partlabel(const char *label)
+{
+	struct device *dev;
+	dev_t devt = 0;
+
+	dev = class_find_device(&block_class, NULL, label, &match_dev_by_label);
+	if (dev) {
+		devt = dev->devt;
+		put_device(dev);
+	}
+
+	return devt;
+}
+
+static dev_t devt_from_devname(const char *name)
+{
+	dev_t devt = 0;
+	int part;
+	char s[32];
+	char *p;
+
+	if (strlen(name) > 31)
+		return 0;
+	strcpy(s, name);
+	for (p = s; *p; p++) {
+		if (*p == '/')
+			*p = '!';
+	}
+
+	devt = blk_lookup_devt(s, 0);
+	if (devt)
+		return devt;
+
+	/*
+	 * Try non-existent, but valid partition, which may only exist after
+	 * opening the device, like partitioned md devices.
+	 */
+	while (p > s && isdigit(p[-1]))
+		p--;
+	if (p == s || !*p || *p == '0')
+		return 0;
+
+	/* try disk name without <part number> */
+	part = simple_strtoul(p, NULL, 10);
+	*p = '\0';
+	devt = blk_lookup_devt(s, part);
+	if (devt)
+		return devt;
+
+	/* try disk name without p<part number> */
+	if (p < s + 2 || !isdigit(p[-2]) || p[-1] != 'p')
+		return 0;
+	p[-1] = '\0';
+	return blk_lookup_devt(s, part);
+}
+#endif /* CONFIG_BLOCK */
+
+static dev_t devt_from_devnum(const char *name)
+{
+	unsigned maj, min, offset;
+	dev_t devt = 0;
+	char *p, dummy;
+
+	if (sscanf(name, "%u:%u%c", &maj, &min, &dummy) == 2 ||
+	    sscanf(name, "%u:%u:%u:%c", &maj, &min, &offset, &dummy) == 3) {
+		devt = MKDEV(maj, min);
+		if (maj != MAJOR(devt) || min != MINOR(devt))
+			return 0;
+	} else {
+		devt = new_decode_dev(simple_strtoul(name, &p, 16));
+		if (*p)
+			return 0;
+	}
+
+	return devt;
+}
 
 /*
  *	Convert a name into device number.  We accept the following variants:
@@ -218,101 +293,23 @@ static int match_dev_by_label(struct device *dev, const void *data)
  *	name contains slashes, the device name has them replaced with
  *	bangs.
  */
-
 dev_t name_to_dev_t(const char *name)
 {
-	char s[32];
-	char *p;
-	dev_t res = 0;
-	int part;
-
+	if (strcmp(name, "/dev/nfs") == 0)
+		return Root_NFS;
+	if (strcmp(name, "/dev/cifs") == 0)
+		return Root_CIFS;
+	if (strcmp(name, "/dev/ram") == 0)
+		return Root_RAM0;
 #ifdef CONFIG_BLOCK
-	if (strncmp(name, "PARTUUID=", 9) == 0) {
-		name += 9;
-		res = devt_from_partuuid(name);
-		if (!res)
-			goto fail;
-		goto done;
-	} else if (strncmp(name, "PARTLABEL=", 10) == 0) {
-		struct device *dev;
-
-		dev = class_find_device(&block_class, NULL, name + 10,
-					&match_dev_by_label);
-		if (!dev)
-			goto fail;
-
-		res = dev->devt;
-		put_device(dev);
-		goto done;
-	}
+	if (strncmp(name, "PARTUUID=", 9) == 0)
+		return devt_from_partuuid(name + 9);
+	if (strncmp(name, "PARTLABEL=", 10) == 0)
+		return devt_from_partlabel(name + 10);
+	if (strncmp(name, "/dev/", 5) == 0)
+		return devt_from_devname(name + 5);
 #endif
-
-	if (strncmp(name, "/dev/", 5) != 0) {
-		unsigned maj, min, offset;
-		char dummy;
-
-		if ((sscanf(name, "%u:%u%c", &maj, &min, &dummy) == 2) ||
-		    (sscanf(name, "%u:%u:%u:%c", &maj, &min, &offset, &dummy) == 3)) {
-			res = MKDEV(maj, min);
-			if (maj != MAJOR(res) || min != MINOR(res))
-				goto fail;
-		} else {
-			res = new_decode_dev(simple_strtoul(name, &p, 16));
-			if (*p)
-				goto fail;
-		}
-		goto done;
-	}
-
-	name += 5;
-	res = Root_NFS;
-	if (strcmp(name, "nfs") == 0)
-		goto done;
-	res = Root_CIFS;
-	if (strcmp(name, "cifs") == 0)
-		goto done;
-	res = Root_RAM0;
-	if (strcmp(name, "ram") == 0)
-		goto done;
-
-	if (strlen(name) > 31)
-		goto fail;
-	strcpy(s, name);
-	for (p = s; *p; p++)
-		if (*p == '/')
-			*p = '!';
-	res = blk_lookup_devt(s, 0);
-	if (res)
-		goto done;
-
-	/*
-	 * try non-existent, but valid partition, which may only exist
-	 * after revalidating the disk, like partitioned md devices
-	 */
-	while (p > s && isdigit(p[-1]))
-		p--;
-	if (p == s || !*p || *p == '0')
-		goto fail;
-
-	/* try disk name without <part number> */
-	part = simple_strtoul(p, NULL, 10);
-	*p = '\0';
-	res = blk_lookup_devt(s, part);
-	if (res)
-		goto done;
-
-	/* try disk name without p<part number> */
-	if (p < s + 2 || !isdigit(p[-2]) || p[-1] != 'p')
-		goto fail;
-	p[-1] = '\0';
-	res = blk_lookup_devt(s, part);
-	if (res)
-		goto done;
-
-fail:
-	return 0;
-done:
-	return res;
+	return devt_from_devnum(name);
 }
 EXPORT_SYMBOL_GPL(name_to_dev_t);
 
-- 
cgit v1.2.3


From 4e7b5671c6a883d94b5428e1a9c141bbd56cb2a6 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 23 Nov 2020 13:38:40 +0100
Subject: block: remove i_bdev

Switch the block device lookup interfaces to directly work with a dev_t
so that struct block_device references are only acquired by the
blkdev_get variants (and the blk-cgroup special case).  This means that
we now don't need an extra reference in the inode and can generally
simplify handling of struct block_device to keep the lookups contained
in the core block layer code.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Acked-by: Tejun Heo <tj@kernel.org>
Acked-by: Coly Li <colyli@suse.de>		[bcache]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/ioctl.c                                |   3 +-
 drivers/block/loop.c                         |   8 +-
 drivers/md/bcache/super.c                    |  20 +--
 drivers/md/dm-table.c                        |   9 +-
 drivers/mtd/mtdsuper.c                       |  17 +--
 drivers/target/target_core_file.c            |   6 +-
 drivers/usb/gadget/function/storage_common.c |   8 +-
 fs/block_dev.c                               | 196 +++++++--------------------
 fs/btrfs/volumes.c                           |  13 +-
 fs/inode.c                                   |   3 -
 fs/internal.h                                |   7 +-
 fs/io_uring.c                                |  10 +-
 fs/pipe.c                                    |   5 +-
 fs/quota/quota.c                             |  19 ++-
 fs/statfs.c                                  |   2 +-
 fs/super.c                                   |  44 +++---
 include/linux/blkdev.h                       |   2 +-
 include/linux/fs.h                           |   1 -
 18 files changed, 121 insertions(+), 252 deletions(-)

(limited to 'include/linux')

diff --git a/block/ioctl.c b/block/ioctl.c
index 0c09bb7a6ff3..a6d8171221c7 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -590,8 +590,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 {
 	int ret;
 	void __user *argp = compat_ptr(arg);
-	struct inode *inode = file->f_mapping->host;
-	struct block_device *bdev = inode->i_bdev;
+	struct block_device *bdev = I_BDEV(file->f_mapping->host);
 	struct gendisk *disk = bdev->bd_disk;
 	fmode_t mode = file->f_mode;
 	loff_t size;
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index b42c728620c9..26c7aafba7c5 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -675,10 +675,10 @@ static int loop_validate_file(struct file *file, struct block_device *bdev)
 	while (is_loop_device(f)) {
 		struct loop_device *l;
 
-		if (f->f_mapping->host->i_bdev == bdev)
+		if (f->f_mapping->host->i_rdev == bdev->bd_dev)
 			return -EBADF;
 
-		l = f->f_mapping->host->i_bdev->bd_disk->private_data;
+		l = I_BDEV(f->f_mapping->host)->bd_disk->private_data;
 		if (l->lo_state != Lo_bound) {
 			return -EINVAL;
 		}
@@ -885,9 +885,7 @@ static void loop_config_discard(struct loop_device *lo)
 	 * file-backed loop devices: discarded regions read back as zero.
 	 */
 	if (S_ISBLK(inode->i_mode) && !lo->lo_encrypt_key_size) {
-		struct request_queue *backingq;
-
-		backingq = bdev_get_queue(inode->i_bdev);
+		struct request_queue *backingq = bdev_get_queue(I_BDEV(inode));
 
 		max_discard_sectors = backingq->limits.max_write_zeroes_sectors;
 		granularity = backingq->limits.discard_granularity ?:
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index a6a5e21e4fd1..c55d3c58a7ef 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -2380,38 +2380,38 @@ kobj_attribute_write(register,		register_bcache);
 kobj_attribute_write(register_quiet,	register_bcache);
 kobj_attribute_write(pendings_cleanup,	bch_pending_bdevs_cleanup);
 
-static bool bch_is_open_backing(struct block_device *bdev)
+static bool bch_is_open_backing(dev_t dev)
 {
 	struct cache_set *c, *tc;
 	struct cached_dev *dc, *t;
 
 	list_for_each_entry_safe(c, tc, &bch_cache_sets, list)
 		list_for_each_entry_safe(dc, t, &c->cached_devs, list)
-			if (dc->bdev == bdev)
+			if (dc->bdev->bd_dev == dev)
 				return true;
 	list_for_each_entry_safe(dc, t, &uncached_devices, list)
-		if (dc->bdev == bdev)
+		if (dc->bdev->bd_dev == dev)
 			return true;
 	return false;
 }
 
-static bool bch_is_open_cache(struct block_device *bdev)
+static bool bch_is_open_cache(dev_t dev)
 {
 	struct cache_set *c, *tc;
 
 	list_for_each_entry_safe(c, tc, &bch_cache_sets, list) {
 		struct cache *ca = c->cache;
 
-		if (ca->bdev == bdev)
+		if (ca->bdev->bd_dev == dev)
 			return true;
 	}
 
 	return false;
 }
 
-static bool bch_is_open(struct block_device *bdev)
+static bool bch_is_open(dev_t dev)
 {
-	return bch_is_open_cache(bdev) || bch_is_open_backing(bdev);
+	return bch_is_open_cache(dev) || bch_is_open_backing(dev);
 }
 
 struct async_reg_args {
@@ -2535,9 +2535,11 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 				  sb);
 	if (IS_ERR(bdev)) {
 		if (bdev == ERR_PTR(-EBUSY)) {
-			bdev = lookup_bdev(strim(path));
+			dev_t dev;
+
 			mutex_lock(&bch_register_lock);
-			if (!IS_ERR(bdev) && bch_is_open(bdev))
+			if (lookup_bdev(strim(path), &dev) == 0 &&
+			    bch_is_open(dev))
 				err = "device already registered";
 			else
 				err = "device busy";
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index ce543b761be7..dea677721710 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -348,16 +348,9 @@ static int upgrade_mode(struct dm_dev_internal *dd, fmode_t new_mode,
 dev_t dm_get_dev_t(const char *path)
 {
 	dev_t dev;
-	struct block_device *bdev;
 
-	bdev = lookup_bdev(path);
-	if (IS_ERR(bdev))
+	if (lookup_bdev(path, &dev))
 		dev = name_to_dev_t(path);
-	else {
-		dev = bdev->bd_dev;
-		bdput(bdev);
-	}
-
 	return dev;
 }
 EXPORT_SYMBOL_GPL(dm_get_dev_t);
diff --git a/drivers/mtd/mtdsuper.c b/drivers/mtd/mtdsuper.c
index c3e2098372f2..38b6aa849c63 100644
--- a/drivers/mtd/mtdsuper.c
+++ b/drivers/mtd/mtdsuper.c
@@ -120,8 +120,8 @@ int get_tree_mtd(struct fs_context *fc,
 				struct fs_context *fc))
 {
 #ifdef CONFIG_BLOCK
-	struct block_device *bdev;
-	int ret, major;
+	dev_t dev;
+	int ret;
 #endif
 	int mtdnr;
 
@@ -169,20 +169,15 @@ int get_tree_mtd(struct fs_context *fc,
 	/* try the old way - the hack where we allowed users to mount
 	 * /dev/mtdblock$(n) but didn't actually _use_ the blockdev
 	 */
-	bdev = lookup_bdev(fc->source);
-	if (IS_ERR(bdev)) {
-		ret = PTR_ERR(bdev);
+	ret = lookup_bdev(fc->source, &dev);
+	if (ret) {
 		errorf(fc, "MTD: Couldn't look up '%s': %d", fc->source, ret);
 		return ret;
 	}
 	pr_debug("MTDSB: lookup_bdev() returned 0\n");
 
-	major = MAJOR(bdev->bd_dev);
-	mtdnr = MINOR(bdev->bd_dev);
-	bdput(bdev);
-
-	if (major == MTD_BLOCK_MAJOR)
-		return mtd_get_sb_by_nr(fc, mtdnr, fill_super);
+	if (MAJOR(dev) == MTD_BLOCK_MAJOR)
+		return mtd_get_sb_by_nr(fc, MINOR(dev), fill_super);
 
 #endif /* CONFIG_BLOCK */
 
diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c
index 7143d03f0e02..b0cb5b95e892 100644
--- a/drivers/target/target_core_file.c
+++ b/drivers/target/target_core_file.c
@@ -133,10 +133,10 @@ static int fd_configure_device(struct se_device *dev)
 	 */
 	inode = file->f_mapping->host;
 	if (S_ISBLK(inode->i_mode)) {
-		struct request_queue *q = bdev_get_queue(inode->i_bdev);
+		struct request_queue *q = bdev_get_queue(I_BDEV(inode));
 		unsigned long long dev_size;
 
-		fd_dev->fd_block_size = bdev_logical_block_size(inode->i_bdev);
+		fd_dev->fd_block_size = bdev_logical_block_size(I_BDEV(inode));
 		/*
 		 * Determine the number of bytes from i_size_read() minus
 		 * one (1) logical sector from underlying struct block_device
@@ -559,7 +559,7 @@ fd_execute_unmap(struct se_cmd *cmd, sector_t lba, sector_t nolb)
 
 	if (S_ISBLK(inode->i_mode)) {
 		/* The backend is block device, use discard */
-		struct block_device *bdev = inode->i_bdev;
+		struct block_device *bdev = I_BDEV(inode);
 		struct se_device *dev = cmd->se_dev;
 
 		ret = blkdev_issue_discard(bdev,
diff --git a/drivers/usb/gadget/function/storage_common.c b/drivers/usb/gadget/function/storage_common.c
index f7e6c42558eb..b859a158a414 100644
--- a/drivers/usb/gadget/function/storage_common.c
+++ b/drivers/usb/gadget/function/storage_common.c
@@ -204,7 +204,7 @@ int fsg_lun_open(struct fsg_lun *curlun, const char *filename)
 	if (!(filp->f_mode & FMODE_WRITE))
 		ro = 1;
 
-	inode = file_inode(filp);
+	inode = filp->f_mapping->host;
 	if ((!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))) {
 		LINFO(curlun, "invalid file type: %s\n", filename);
 		goto out;
@@ -221,7 +221,7 @@ int fsg_lun_open(struct fsg_lun *curlun, const char *filename)
 	if (!(filp->f_mode & FMODE_CAN_WRITE))
 		ro = 1;
 
-	size = i_size_read(inode->i_mapping->host);
+	size = i_size_read(inode);
 	if (size < 0) {
 		LINFO(curlun, "unable to find file size: %s\n", filename);
 		rc = (int) size;
@@ -231,8 +231,8 @@ int fsg_lun_open(struct fsg_lun *curlun, const char *filename)
 	if (curlun->cdrom) {
 		blksize = 2048;
 		blkbits = 11;
-	} else if (inode->i_bdev) {
-		blksize = bdev_logical_block_size(inode->i_bdev);
+	} else if (S_ISBLK(inode->i_mode)) {
+		blksize = bdev_logical_block_size(I_BDEV(inode));
 		blkbits = blksize_bits(blksize);
 	} else {
 		blksize = 512;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 2b8c0586314f..6d6e4d50834c 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -883,7 +883,6 @@ static struct block_device *bdget(dev_t dev)
 		bdev->bd_dev = dev;
 		inode->i_mode = S_IFBLK;
 		inode->i_rdev = dev;
-		inode->i_bdev = bdev;
 		inode->i_data.a_ops = &def_blk_aops;
 		mapping_set_gfp_mask(&inode->i_data, GFP_USER);
 		unlock_new_inode(inode);
@@ -928,67 +927,8 @@ void bdput(struct block_device *bdev)
 {
 	iput(bdev->bd_inode);
 }
-
 EXPORT_SYMBOL(bdput);
  
-static struct block_device *bd_acquire(struct inode *inode)
-{
-	struct block_device *bdev;
-
-	spin_lock(&bdev_lock);
-	bdev = inode->i_bdev;
-	if (bdev && !inode_unhashed(bdev->bd_inode)) {
-		bdgrab(bdev);
-		spin_unlock(&bdev_lock);
-		return bdev;
-	}
-	spin_unlock(&bdev_lock);
-
-	/*
-	 * i_bdev references block device inode that was already shut down
-	 * (corresponding device got removed).  Remove the reference and look
-	 * up block device inode again just in case new device got
-	 * reestablished under the same device number.
-	 */
-	if (bdev)
-		bd_forget(inode);
-
-	bdev = bdget(inode->i_rdev);
-	if (bdev) {
-		spin_lock(&bdev_lock);
-		if (!inode->i_bdev) {
-			/*
-			 * We take an additional reference to bd_inode,
-			 * and it's released in clear_inode() of inode.
-			 * So, we can access it via ->i_mapping always
-			 * without igrab().
-			 */
-			bdgrab(bdev);
-			inode->i_bdev = bdev;
-			inode->i_mapping = bdev->bd_inode->i_mapping;
-		}
-		spin_unlock(&bdev_lock);
-	}
-	return bdev;
-}
-
-/* Call when you free inode */
-
-void bd_forget(struct inode *inode)
-{
-	struct block_device *bdev = NULL;
-
-	spin_lock(&bdev_lock);
-	if (!sb_is_blkdev_sb(inode->i_sb))
-		bdev = inode->i_bdev;
-	inode->i_bdev = NULL;
-	inode->i_mapping = &inode->i_data;
-	spin_unlock(&bdev_lock);
-
-	if (bdev)
-		bdput(bdev);
-}
-
 /**
  * bd_may_claim - test whether a block device can be claimed
  * @bdev: block device of interest
@@ -1497,38 +1437,45 @@ static int __blkdev_get(struct block_device *bdev, struct gendisk *disk,
 }
 
 /**
- * blkdev_get - open a block device
- * @bdev: block_device to open
+ * blkdev_get_by_dev - open a block device by device number
+ * @dev: device number of block device to open
  * @mode: FMODE_* mask
  * @holder: exclusive holder identifier
  *
- * Open @bdev with @mode.  If @mode includes %FMODE_EXCL, @bdev is
- * open with exclusive access.  Specifying %FMODE_EXCL with %NULL
- * @holder is invalid.  Exclusive opens may nest for the same @holder.
+ * Open the block device described by device number @dev. If @mode includes
+ * %FMODE_EXCL, the block device is opened with exclusive access.  Specifying
+ * %FMODE_EXCL with a %NULL @holder is invalid.  Exclusive opens may nest for
+ * the same @holder.
  *
- * On success, the reference count of @bdev is unchanged.  On failure,
- * @bdev is put.
+ * Use this interface ONLY if you really do not have anything better - i.e. when
+ * you are behind a truly sucky interface and all you are given is a device
+ * number.  Everything else should use blkdev_get_by_path().
  *
  * CONTEXT:
  * Might sleep.
  *
  * RETURNS:
- * 0 on success, -errno on failure.
+ * Reference to the block_device on success, ERR_PTR(-errno) on failure.
  */
-static int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder)
+struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
 {
 	struct block_device *claiming;
 	bool unblock_events = true;
+	struct block_device *bdev;
 	struct gendisk *disk;
 	int partno;
 	int ret;
 
 	ret = devcgroup_check_permission(DEVCG_DEV_BLOCK,
-			imajor(bdev->bd_inode), iminor(bdev->bd_inode),
+			MAJOR(dev), MINOR(dev),
 			((mode & FMODE_READ) ? DEVCG_ACC_READ : 0) |
 			((mode & FMODE_WRITE) ? DEVCG_ACC_WRITE : 0));
 	if (ret)
-		goto bdput;
+		return ERR_PTR(ret);
+
+	bdev = bdget(dev);
+	if (!bdev)
+		return ERR_PTR(-ENOMEM);
 
 	/*
 	 * If we lost a race with 'disk' being deleted, try again.  See md.c.
@@ -1589,10 +1536,13 @@ put_disk:
 	if (ret == -ERESTARTSYS)
 		goto retry;
 bdput:
-	if (ret)
+	if (ret) {
 		bdput(bdev);
-	return ret;
+		return ERR_PTR(ret);
+	}
+	return bdev;
 }
+EXPORT_SYMBOL(blkdev_get_by_dev);
 
 /**
  * blkdev_get_by_path - open a block device by name
@@ -1600,32 +1550,30 @@ bdput:
  * @mode: FMODE_* mask
  * @holder: exclusive holder identifier
  *
- * Open the blockdevice described by the device file at @path.  @mode
- * and @holder are identical to blkdev_get().
- *
- * On success, the returned block_device has reference count of one.
+ * Open the block device described by the device file at @path.  If @mode
+ * includes %FMODE_EXCL, the block device is opened with exclusive access.
+ * Specifying %FMODE_EXCL with a %NULL @holder is invalid.  Exclusive opens may
+ * nest for the same @holder.
  *
  * CONTEXT:
  * Might sleep.
  *
  * RETURNS:
- * Pointer to block_device on success, ERR_PTR(-errno) on failure.
+ * Reference to the block_device on success, ERR_PTR(-errno) on failure.
  */
 struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
 					void *holder)
 {
 	struct block_device *bdev;
-	int err;
-
-	bdev = lookup_bdev(path);
-	if (IS_ERR(bdev))
-		return bdev;
+	dev_t dev;
+	int error;
 
-	err = blkdev_get(bdev, mode, holder);
-	if (err)
-		return ERR_PTR(err);
+	error = lookup_bdev(path, &dev);
+	if (error)
+		return ERR_PTR(error);
 
-	if ((mode & FMODE_WRITE) && bdev_read_only(bdev)) {
+	bdev = blkdev_get_by_dev(dev, mode, holder);
+	if (!IS_ERR(bdev) && (mode & FMODE_WRITE) && bdev_read_only(bdev)) {
 		blkdev_put(bdev, mode);
 		return ERR_PTR(-EACCES);
 	}
@@ -1634,45 +1582,6 @@ struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
 }
 EXPORT_SYMBOL(blkdev_get_by_path);
 
-/**
- * blkdev_get_by_dev - open a block device by device number
- * @dev: device number of block device to open
- * @mode: FMODE_* mask
- * @holder: exclusive holder identifier
- *
- * Open the blockdevice described by device number @dev.  @mode and
- * @holder are identical to blkdev_get().
- *
- * Use it ONLY if you really do not have anything better - i.e. when
- * you are behind a truly sucky interface and all you are given is a
- * device number.  _Never_ to be used for internal purposes.  If you
- * ever need it - reconsider your API.
- *
- * On success, the returned block_device has reference count of one.
- *
- * CONTEXT:
- * Might sleep.
- *
- * RETURNS:
- * Pointer to block_device on success, ERR_PTR(-errno) on failure.
- */
-struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
-{
-	struct block_device *bdev;
-	int err;
-
-	bdev = bdget(dev);
-	if (!bdev)
-		return ERR_PTR(-ENOMEM);
-
-	err = blkdev_get(bdev, mode, holder);
-	if (err)
-		return ERR_PTR(err);
-
-	return bdev;
-}
-EXPORT_SYMBOL(blkdev_get_by_dev);
-
 static int blkdev_open(struct inode * inode, struct file * filp)
 {
 	struct block_device *bdev;
@@ -1694,14 +1603,12 @@ static int blkdev_open(struct inode * inode, struct file * filp)
 	if ((filp->f_flags & O_ACCMODE) == 3)
 		filp->f_mode |= FMODE_WRITE_IOCTL;
 
-	bdev = bd_acquire(inode);
-	if (bdev == NULL)
-		return -ENOMEM;
-
+	bdev = blkdev_get_by_dev(inode->i_rdev, filp->f_mode, filp);
+	if (IS_ERR(bdev))
+		return PTR_ERR(bdev);
 	filp->f_mapping = bdev->bd_inode->i_mapping;
 	filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping);
-
-	return blkdev_get(bdev, filp->f_mode, filp);
+	return 0;
 }
 
 static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
@@ -2010,37 +1917,32 @@ const struct file_operations def_blk_fops = {
  * namespace if possible and return it.  Return ERR_PTR(error)
  * otherwise.
  */
-struct block_device *lookup_bdev(const char *pathname)
+int lookup_bdev(const char *pathname, dev_t *dev)
 {
-	struct block_device *bdev;
 	struct inode *inode;
 	struct path path;
 	int error;
 
 	if (!pathname || !*pathname)
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	error = kern_path(pathname, LOOKUP_FOLLOW, &path);
 	if (error)
-		return ERR_PTR(error);
+		return error;
 
 	inode = d_backing_inode(path.dentry);
 	error = -ENOTBLK;
 	if (!S_ISBLK(inode->i_mode))
-		goto fail;
+		goto out_path_put;
 	error = -EACCES;
 	if (!may_open_dev(&path))
-		goto fail;
-	error = -ENOMEM;
-	bdev = bd_acquire(inode);
-	if (!bdev)
-		goto fail;
-out:
+		goto out_path_put;
+
+	*dev = inode->i_rdev;
+	error = 0;
+out_path_put:
 	path_put(&path);
-	return bdev;
-fail:
-	bdev = ERR_PTR(error);
-	goto out;
+	return error;
 }
 EXPORT_SYMBOL(lookup_bdev);
 
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index a6406b3b8c2b..fbc4b58228f7 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -929,16 +929,16 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 		 * make sure it's the same device if the device is mounted
 		 */
 		if (device->bdev) {
-			struct block_device *path_bdev;
+			int error;
+			dev_t path_dev;
 
-			path_bdev = lookup_bdev(path);
-			if (IS_ERR(path_bdev)) {
+			error = lookup_bdev(path, &path_dev);
+			if (error) {
 				mutex_unlock(&fs_devices->device_list_mutex);
-				return ERR_CAST(path_bdev);
+				return ERR_PTR(error);
 			}
 
-			if (device->bdev != path_bdev) {
-				bdput(path_bdev);
+			if (device->bdev->bd_dev != path_dev) {
 				mutex_unlock(&fs_devices->device_list_mutex);
 				btrfs_warn_in_rcu(device->fs_info,
 	"duplicate device %s devid %llu generation %llu scanned by %s (%d)",
@@ -947,7 +947,6 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 						  task_pid_nr(current));
 				return ERR_PTR(-EEXIST);
 			}
-			bdput(path_bdev);
 			btrfs_info_in_rcu(device->fs_info,
 	"devid %llu device path %s changed to %s scanned by %s (%d)",
 					  devid, rcu_str_deref(device->name),
diff --git a/fs/inode.c b/fs/inode.c
index 9d78c37b00b8..cb008acf0efd 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -155,7 +155,6 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 	inode->i_bytes = 0;
 	inode->i_generation = 0;
 	inode->i_pipe = NULL;
-	inode->i_bdev = NULL;
 	inode->i_cdev = NULL;
 	inode->i_link = NULL;
 	inode->i_dir_seq = 0;
@@ -580,8 +579,6 @@ static void evict(struct inode *inode)
 		truncate_inode_pages_final(&inode->i_data);
 		clear_inode(inode);
 	}
-	if (S_ISBLK(inode->i_mode) && inode->i_bdev)
-		bd_forget(inode);
 	if (S_ISCHR(inode->i_mode) && inode->i_cdev)
 		cd_forget(inode);
 
diff --git a/fs/internal.h b/fs/internal.h
index 47be21dfeebe..53f890446e75 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -25,7 +25,6 @@ extern void __init bdev_cache_init(void);
 extern int __sync_blockdev(struct block_device *bdev, int wait);
 void iterate_bdevs(void (*)(struct block_device *, void *), void *);
 void emergency_thaw_bdev(struct super_block *sb);
-void bd_forget(struct inode *inode);
 #else
 static inline void bdev_cache_init(void)
 {
@@ -43,9 +42,6 @@ static inline int emergency_thaw_bdev(struct super_block *sb)
 {
 	return 0;
 }
-static inline void bd_forget(struct inode *inode)
-{
-}
 #endif /* CONFIG_BLOCK */
 
 /*
@@ -114,8 +110,7 @@ extern struct file *alloc_empty_file_noaccount(int, const struct cred *);
  */
 extern int reconfigure_super(struct fs_context *);
 extern bool trylock_super(struct super_block *sb);
-struct super_block *__get_super(struct block_device *bdev, bool excl);
-extern struct super_block *user_get_super(dev_t);
+struct super_block *user_get_super(dev_t, bool excl);
 void put_super(struct super_block *sb);
 extern bool mount_capable(struct fs_context *);
 
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 4ead291b2976..8f13c0417f94 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -2716,11 +2716,7 @@ static struct file *__io_file_get(struct io_submit_state *state, int fd)
 
 static bool io_bdev_nowait(struct block_device *bdev)
 {
-#ifdef CONFIG_BLOCK
 	return !bdev || blk_queue_nowait(bdev_get_queue(bdev));
-#else
-	return true;
-#endif
 }
 
 /*
@@ -2733,14 +2729,16 @@ static bool io_file_supports_async(struct file *file, int rw)
 	umode_t mode = file_inode(file)->i_mode;
 
 	if (S_ISBLK(mode)) {
-		if (io_bdev_nowait(file->f_inode->i_bdev))
+		if (IS_ENABLED(CONFIG_BLOCK) &&
+		    io_bdev_nowait(I_BDEV(file->f_mapping->host)))
 			return true;
 		return false;
 	}
 	if (S_ISCHR(mode) || S_ISSOCK(mode))
 		return true;
 	if (S_ISREG(mode)) {
-		if (io_bdev_nowait(file->f_inode->i_sb->s_bdev) &&
+		if (IS_ENABLED(CONFIG_BLOCK) &&
+		    io_bdev_nowait(file->f_inode->i_sb->s_bdev) &&
 		    file->f_op != &io_uring_fops)
 			return true;
 		return false;
diff --git a/fs/pipe.c b/fs/pipe.c
index 0ac197658a2d..c5989cfd564d 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -1342,9 +1342,8 @@ out_revert_acct:
 }
 
 /*
- * After the inode slimming patch, i_pipe/i_bdev/i_cdev share the same
- * location, so checking ->i_pipe is not enough to verify that this is a
- * pipe.
+ * Note that i_pipe and i_cdev share the same location, so checking ->i_pipe is
+ * not enough to verify that this is a pipe.
  */
 struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice)
 {
diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index f3d32b0d9008..6d16b2be5ac4 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -866,17 +866,18 @@ static bool quotactl_cmd_onoff(int cmd)
 static struct super_block *quotactl_block(const char __user *special, int cmd)
 {
 #ifdef CONFIG_BLOCK
-	struct block_device *bdev;
 	struct super_block *sb;
 	struct filename *tmp = getname(special);
 	bool excl = false, thawed = false;
+	int error;
+	dev_t dev;
 
 	if (IS_ERR(tmp))
 		return ERR_CAST(tmp);
-	bdev = lookup_bdev(tmp->name);
+	error = lookup_bdev(tmp->name, &dev);
 	putname(tmp);
-	if (IS_ERR(bdev))
-		return ERR_CAST(bdev);
+	if (error)
+		return ERR_PTR(error);
 
 	if (quotactl_cmd_onoff(cmd)) {
 		excl = true;
@@ -886,8 +887,10 @@ static struct super_block *quotactl_block(const char __user *special, int cmd)
 	}
 
 retry:
-	sb = __get_super(bdev, excl);
-	if (thawed && sb && sb->s_writers.frozen != SB_UNFROZEN) {
+	sb = user_get_super(dev, excl);
+	if (!sb)
+		return ERR_PTR(-ENODEV);
+	if (thawed && sb->s_writers.frozen != SB_UNFROZEN) {
 		if (excl)
 			up_write(&sb->s_umount);
 		else
@@ -897,10 +900,6 @@ retry:
 		put_super(sb);
 		goto retry;
 	}
-
-	bdput(bdev);
-	if (!sb)
-		return ERR_PTR(-ENODEV);
 	return sb;
 
 #else
diff --git a/fs/statfs.c b/fs/statfs.c
index 59f33752c131..68cb07788750 100644
--- a/fs/statfs.c
+++ b/fs/statfs.c
@@ -235,7 +235,7 @@ SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, size_t, sz, struct statfs64 __user
 
 static int vfs_ustat(dev_t dev, struct kstatfs *sbuf)
 {
-	struct super_block *s = user_get_super(dev);
+	struct super_block *s = user_get_super(dev, false);
 	int err;
 	if (!s)
 		return -EINVAL;
diff --git a/fs/super.c b/fs/super.c
index 343e5c1e538d..2c6cdea2ab2d 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -740,7 +740,14 @@ void iterate_supers_type(struct file_system_type *type,
 
 EXPORT_SYMBOL(iterate_supers_type);
 
-struct super_block *__get_super(struct block_device *bdev, bool excl)
+/**
+ * get_super - get the superblock of a device
+ * @bdev: device to get the superblock for
+ *
+ * Scans the superblock list and finds the superblock of the file system
+ * mounted on the device given. %NULL is returned if no match is found.
+ */
+struct super_block *get_super(struct block_device *bdev)
 {
 	struct super_block *sb;
 
@@ -755,17 +762,11 @@ rescan:
 		if (sb->s_bdev == bdev) {
 			sb->s_count++;
 			spin_unlock(&sb_lock);
-			if (!excl)
-				down_read(&sb->s_umount);
-			else
-				down_write(&sb->s_umount);
+			down_read(&sb->s_umount);
 			/* still alive? */
 			if (sb->s_root && (sb->s_flags & SB_BORN))
 				return sb;
-			if (!excl)
-				up_read(&sb->s_umount);
-			else
-				up_write(&sb->s_umount);
+			up_read(&sb->s_umount);
 			/* nope, got unmounted */
 			spin_lock(&sb_lock);
 			__put_super(sb);
@@ -776,19 +777,6 @@ rescan:
 	return NULL;
 }
 
-/**
- *	get_super - get the superblock of a device
- *	@bdev: device to get the superblock for
- *
- *	Scans the superblock list and finds the superblock of the file system
- *	mounted on the device given. %NULL is returned if no match is found.
- */
-struct super_block *get_super(struct block_device *bdev)
-{
-	return __get_super(bdev, false);
-}
-EXPORT_SYMBOL(get_super);
-
 /**
  * get_active_super - get an active reference to the superblock of a device
  * @bdev: device to get the superblock for
@@ -820,7 +808,7 @@ restart:
 	return NULL;
 }
 
-struct super_block *user_get_super(dev_t dev)
+struct super_block *user_get_super(dev_t dev, bool excl)
 {
 	struct super_block *sb;
 
@@ -832,11 +820,17 @@ rescan:
 		if (sb->s_dev ==  dev) {
 			sb->s_count++;
 			spin_unlock(&sb_lock);
-			down_read(&sb->s_umount);
+			if (excl)
+				down_write(&sb->s_umount);
+			else
+				down_read(&sb->s_umount);
 			/* still alive? */
 			if (sb->s_root && (sb->s_flags & SB_BORN))
 				return sb;
-			up_read(&sb->s_umount);
+			if (excl)
+				up_write(&sb->s_umount);
+			else
+				up_read(&sb->s_umount);
 			/* nope, got unmounted */
 			spin_lock(&sb_lock);
 			__put_super(sb);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 12810a19edeb..bdd7339bcda4 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1973,7 +1973,7 @@ int bdev_read_only(struct block_device *bdev);
 int set_blocksize(struct block_device *bdev, int size);
 
 const char *bdevname(struct block_device *bdev, char *buffer);
-struct block_device *lookup_bdev(const char *);
+int lookup_bdev(const char *pathname, dev_t *dev);
 
 void blkdev_show(struct seq_file *seqf, off_t offset);
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index a61df0dd4f19..b0b358309657 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -696,7 +696,6 @@ struct inode {
 	struct list_head	i_devices;
 	union {
 		struct pipe_inode_info	*i_pipe;
-		struct block_device	*i_bdev;
 		struct cdev		*i_cdev;
 		char			*i_link;
 		unsigned		i_dir_seq;
-- 
cgit v1.2.3


From 22ae8ce8b89241c94ac00c237752c0ffa37ba5ae Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 26 Nov 2020 09:23:26 +0100
Subject: block: simplify bdev/disk lookup in blkdev_get

To simplify block device lookup and a few other upcoming areas, make sure
that we always have a struct block_device available for each disk and
each partition, and only find existing block devices in bdget.  The only
downside of this is that each device and partition uses a little more
memory.  The upside will be that a lot of code can be simplified.

With that all we need to look up the block device is to lookup the inode
and do a few sanity checks on the gendisk, instead of the separate lookup
for the gendisk.  For blk-cgroup which wants to access a gendisk without
opening it, a new blkdev_{get,put}_no_open low-level interface is added
to replace the previous get_gendisk use.

Note that the change to look up block device directly instead of the two
step lookup using struct gendisk causes a subtile change in behavior:
accessing a non-existing partition on an existing block device can now
cause a call to request_module.  That call is harmless, and in practice
no recent system will access these nodes as they aren't created by udev
and static /dev/ setups are unusual.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-cgroup.c         |  42 ++++-----
 block/blk-iocost.c         |  36 ++++----
 block/blk.h                |   2 +-
 block/genhd.c              | 210 ++++++---------------------------------------
 block/partitions/core.c    |  29 ++++---
 fs/block_dev.c             | 177 ++++++++++++++++++++++----------------
 include/linux/blk-cgroup.h |   4 +-
 include/linux/blkdev.h     |   6 ++
 include/linux/genhd.h      |   7 +-
 9 files changed, 194 insertions(+), 319 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index c68bdf58c9a6..ad02289a4f7f 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -556,22 +556,22 @@ static struct blkcg_gq *blkg_lookup_check(struct blkcg *blkcg,
 }
 
 /**
- * blkg_conf_prep - parse and prepare for per-blkg config update
+ * blkcg_conf_open_bdev - parse and open bdev for per-blkg config update
  * @inputp: input string pointer
  *
  * Parse the device node prefix part, MAJ:MIN, of per-blkg config update
- * from @input and get and return the matching gendisk.  *@inputp is
+ * from @input and get and return the matching bdev.  *@inputp is
  * updated to point past the device node prefix.  Returns an ERR_PTR()
  * value on error.
  *
  * Use this function iff blkg_conf_prep() can't be used for some reason.
  */
-struct gendisk *blkcg_conf_get_disk(char **inputp)
+struct block_device *blkcg_conf_open_bdev(char **inputp)
 {
 	char *input = *inputp;
 	unsigned int major, minor;
-	struct gendisk *disk;
-	int key_len, part;
+	struct block_device *bdev;
+	int key_len;
 
 	if (sscanf(input, "%u:%u%n", &major, &minor, &key_len) != 2)
 		return ERR_PTR(-EINVAL);
@@ -581,16 +581,16 @@ struct gendisk *blkcg_conf_get_disk(char **inputp)
 		return ERR_PTR(-EINVAL);
 	input = skip_spaces(input);
 
-	disk = get_gendisk(MKDEV(major, minor), &part);
-	if (!disk)
+	bdev = blkdev_get_no_open(MKDEV(major, minor));
+	if (!bdev)
 		return ERR_PTR(-ENODEV);
-	if (part) {
-		put_disk_and_module(disk);
+	if (bdev_is_partition(bdev)) {
+		blkdev_put_no_open(bdev);
 		return ERR_PTR(-ENODEV);
 	}
 
 	*inputp = input;
-	return disk;
+	return bdev;
 }
 
 /**
@@ -607,18 +607,18 @@ struct gendisk *blkcg_conf_get_disk(char **inputp)
  */
 int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 		   char *input, struct blkg_conf_ctx *ctx)
-	__acquires(rcu) __acquires(&disk->queue->queue_lock)
+	__acquires(rcu) __acquires(&bdev->bd_disk->queue->queue_lock)
 {
-	struct gendisk *disk;
+	struct block_device *bdev;
 	struct request_queue *q;
 	struct blkcg_gq *blkg;
 	int ret;
 
-	disk = blkcg_conf_get_disk(&input);
-	if (IS_ERR(disk))
-		return PTR_ERR(disk);
+	bdev = blkcg_conf_open_bdev(&input);
+	if (IS_ERR(bdev))
+		return PTR_ERR(bdev);
 
-	q = disk->queue;
+	q = bdev->bd_disk->queue;
 
 	rcu_read_lock();
 	spin_lock_irq(&q->queue_lock);
@@ -689,7 +689,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 			goto success;
 	}
 success:
-	ctx->disk = disk;
+	ctx->bdev = bdev;
 	ctx->blkg = blkg;
 	ctx->body = input;
 	return 0;
@@ -700,7 +700,7 @@ fail_unlock:
 	spin_unlock_irq(&q->queue_lock);
 	rcu_read_unlock();
 fail:
-	put_disk_and_module(disk);
+	blkdev_put_no_open(bdev);
 	/*
 	 * If queue was bypassing, we should retry.  Do so after a
 	 * short msleep().  It isn't strictly necessary but queue
@@ -723,11 +723,11 @@ EXPORT_SYMBOL_GPL(blkg_conf_prep);
  * with blkg_conf_prep().
  */
 void blkg_conf_finish(struct blkg_conf_ctx *ctx)
-	__releases(&ctx->disk->queue->queue_lock) __releases(rcu)
+	__releases(&ctx->bdev->bd_disk->queue->queue_lock) __releases(rcu)
 {
-	spin_unlock_irq(&ctx->disk->queue->queue_lock);
+	spin_unlock_irq(&ctx->bdev->bd_disk->queue->queue_lock);
 	rcu_read_unlock();
-	put_disk_and_module(ctx->disk);
+	blkdev_put_no_open(ctx->bdev);
 }
 EXPORT_SYMBOL_GPL(blkg_conf_finish);
 
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index bbe86d1199dc..8e20fe4bddec 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -3120,23 +3120,23 @@ static const match_table_t qos_tokens = {
 static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input,
 			     size_t nbytes, loff_t off)
 {
-	struct gendisk *disk;
+	struct block_device *bdev;
 	struct ioc *ioc;
 	u32 qos[NR_QOS_PARAMS];
 	bool enable, user;
 	char *p;
 	int ret;
 
-	disk = blkcg_conf_get_disk(&input);
-	if (IS_ERR(disk))
-		return PTR_ERR(disk);
+	bdev = blkcg_conf_open_bdev(&input);
+	if (IS_ERR(bdev))
+		return PTR_ERR(bdev);
 
-	ioc = q_to_ioc(disk->queue);
+	ioc = q_to_ioc(bdev->bd_disk->queue);
 	if (!ioc) {
-		ret = blk_iocost_init(disk->queue);
+		ret = blk_iocost_init(bdev->bd_disk->queue);
 		if (ret)
 			goto err;
-		ioc = q_to_ioc(disk->queue);
+		ioc = q_to_ioc(bdev->bd_disk->queue);
 	}
 
 	spin_lock_irq(&ioc->lock);
@@ -3231,12 +3231,12 @@ static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input,
 	ioc_refresh_params(ioc, true);
 	spin_unlock_irq(&ioc->lock);
 
-	put_disk_and_module(disk);
+	blkdev_put_no_open(bdev);
 	return nbytes;
 einval:
 	ret = -EINVAL;
 err:
-	put_disk_and_module(disk);
+	blkdev_put_no_open(bdev);
 	return ret;
 }
 
@@ -3287,23 +3287,23 @@ static const match_table_t i_lcoef_tokens = {
 static ssize_t ioc_cost_model_write(struct kernfs_open_file *of, char *input,
 				    size_t nbytes, loff_t off)
 {
-	struct gendisk *disk;
+	struct block_device *bdev;
 	struct ioc *ioc;
 	u64 u[NR_I_LCOEFS];
 	bool user;
 	char *p;
 	int ret;
 
-	disk = blkcg_conf_get_disk(&input);
-	if (IS_ERR(disk))
-		return PTR_ERR(disk);
+	bdev = blkcg_conf_open_bdev(&input);
+	if (IS_ERR(bdev))
+		return PTR_ERR(bdev);
 
-	ioc = q_to_ioc(disk->queue);
+	ioc = q_to_ioc(bdev->bd_disk->queue);
 	if (!ioc) {
-		ret = blk_iocost_init(disk->queue);
+		ret = blk_iocost_init(bdev->bd_disk->queue);
 		if (ret)
 			goto err;
-		ioc = q_to_ioc(disk->queue);
+		ioc = q_to_ioc(bdev->bd_disk->queue);
 	}
 
 	spin_lock_irq(&ioc->lock);
@@ -3356,13 +3356,13 @@ static ssize_t ioc_cost_model_write(struct kernfs_open_file *of, char *input,
 	ioc_refresh_params(ioc, true);
 	spin_unlock_irq(&ioc->lock);
 
-	put_disk_and_module(disk);
+	blkdev_put_no_open(bdev);
 	return nbytes;
 
 einval:
 	ret = -EINVAL;
 err:
-	put_disk_and_module(disk);
+	blkdev_put_no_open(bdev);
 	return ret;
 }
 
diff --git a/block/blk.h b/block/blk.h
index dfab98465db9..c4839abcfa27 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -352,7 +352,6 @@ struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector);
 
 int blk_alloc_devt(struct hd_struct *part, dev_t *devt);
 void blk_free_devt(dev_t devt);
-void blk_invalidate_devt(dev_t devt);
 char *disk_name(struct gendisk *hd, int partno, char *buf);
 #define ADDPART_FLAG_NONE	0
 #define ADDPART_FLAG_RAID	1
@@ -384,6 +383,7 @@ static inline void hd_free_part(struct hd_struct *part)
 {
 	free_percpu(part->dkstats);
 	kfree(part->info);
+	bdput(part->bdev);
 	percpu_ref_exit(&part->ref);
 }
 
diff --git a/block/genhd.c b/block/genhd.c
index f46e89226fdf..bf8fa82f135f 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -27,17 +27,11 @@
 
 static struct kobject *block_depr;
 
-static DEFINE_XARRAY(bdev_map);
-static DEFINE_MUTEX(bdev_map_lock);
+DECLARE_RWSEM(bdev_lookup_sem);
 
 /* for extended dynamic devt allocation, currently only one major is used */
 #define NR_EXT_DEVT		(1 << MINORBITS)
-
-/* For extended devt allocation.  ext_devt_lock prevents look up
- * results from going away underneath its user.
- */
-static DEFINE_SPINLOCK(ext_devt_lock);
-static DEFINE_IDR(ext_devt_idr);
+static DEFINE_IDA(ext_devt_ida);
 
 static void disk_check_events(struct disk_events *ev,
 			      unsigned int *clearing_ptr);
@@ -580,14 +574,7 @@ int blk_alloc_devt(struct hd_struct *part, dev_t *devt)
 		return 0;
 	}
 
-	/* allocate ext devt */
-	idr_preload(GFP_KERNEL);
-
-	spin_lock_bh(&ext_devt_lock);
-	idx = idr_alloc(&ext_devt_idr, part, 0, NR_EXT_DEVT, GFP_NOWAIT);
-	spin_unlock_bh(&ext_devt_lock);
-
-	idr_preload_end();
+	idx = ida_alloc_range(&ext_devt_ida, 0, NR_EXT_DEVT, GFP_KERNEL);
 	if (idx < 0)
 		return idx == -ENOSPC ? -EBUSY : idx;
 
@@ -606,26 +593,8 @@ int blk_alloc_devt(struct hd_struct *part, dev_t *devt)
  */
 void blk_free_devt(dev_t devt)
 {
-	if (devt == MKDEV(0, 0))
-		return;
-
-	if (MAJOR(devt) == BLOCK_EXT_MAJOR) {
-		spin_lock_bh(&ext_devt_lock);
-		idr_remove(&ext_devt_idr, blk_mangle_minor(MINOR(devt)));
-		spin_unlock_bh(&ext_devt_lock);
-	}
-}
-
-/*
- * We invalidate devt by assigning NULL pointer for devt in idr.
- */
-void blk_invalidate_devt(dev_t devt)
-{
-	if (MAJOR(devt) == BLOCK_EXT_MAJOR) {
-		spin_lock_bh(&ext_devt_lock);
-		idr_replace(&ext_devt_idr, NULL, blk_mangle_minor(MINOR(devt)));
-		spin_unlock_bh(&ext_devt_lock);
-	}
+	if (MAJOR(devt) == BLOCK_EXT_MAJOR)
+		ida_free(&ext_devt_ida, blk_mangle_minor(MINOR(devt)));
 }
 
 static char *bdevt_str(dev_t devt, char *buf)
@@ -640,28 +609,6 @@ static char *bdevt_str(dev_t devt, char *buf)
 	return buf;
 }
 
-static void blk_register_region(struct gendisk *disk)
-{
-	int i;
-
-	mutex_lock(&bdev_map_lock);
-	for (i = 0; i < disk->minors; i++) {
-		if (xa_insert(&bdev_map, disk_devt(disk) + i, disk, GFP_KERNEL))
-			WARN_ON_ONCE(1);
-	}
-	mutex_unlock(&bdev_map_lock);
-}
-
-static void blk_unregister_region(struct gendisk *disk)
-{
-	int i;
-
-	mutex_lock(&bdev_map_lock);
-	for (i = 0; i < disk->minors; i++)
-		xa_erase(&bdev_map, disk_devt(disk) + i);
-	mutex_unlock(&bdev_map_lock);
-}
-
 static void disk_scan_partitions(struct gendisk *disk)
 {
 	struct block_device *bdev;
@@ -805,7 +752,7 @@ static void __device_add_disk(struct device *parent, struct gendisk *disk,
 		ret = bdi_register(bdi, "%u:%u", MAJOR(devt), MINOR(devt));
 		WARN_ON(ret);
 		bdi_set_owner(bdi, dev);
-		blk_register_region(disk);
+		bdev_add(disk->part0.bdev, devt);
 	}
 	register_disk(parent, disk, groups);
 	if (register_queue)
@@ -847,8 +794,8 @@ static void invalidate_partition(struct gendisk *disk, int partno)
 	__invalidate_device(bdev, true);
 
 	/*
-	 * Unhash the bdev inode for this device so that it gets evicted as soon
-	 * as last inode reference is dropped.
+	 * Unhash the bdev inode for this device so that it can't be looked
+	 * up any more even if openers still hold references to it.
 	 */
 	remove_inode_hash(bdev->bd_inode);
 	bdput(bdev);
@@ -890,7 +837,8 @@ void del_gendisk(struct gendisk *disk)
 	 * Block lookups of the disk until all bdevs are unhashed and the
 	 * disk is marked as dead (GENHD_FL_UP cleared).
 	 */
-	down_write(&disk->lookup_sem);
+	down_write(&bdev_lookup_sem);
+
 	/* invalidate stuff */
 	disk_part_iter_init(&piter, disk,
 			     DISK_PITER_INCL_EMPTY | DISK_PITER_REVERSE);
@@ -903,7 +851,7 @@ void del_gendisk(struct gendisk *disk)
 	invalidate_partition(disk, 0);
 	set_capacity(disk, 0);
 	disk->flags &= ~GENHD_FL_UP;
-	up_write(&disk->lookup_sem);
+	up_write(&bdev_lookup_sem);
 
 	if (!(disk->flags & GENHD_FL_HIDDEN)) {
 		sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi");
@@ -916,16 +864,6 @@ void del_gendisk(struct gendisk *disk)
 	}
 
 	blk_unregister_queue(disk);
-	
-	if (!(disk->flags & GENHD_FL_HIDDEN))
-		blk_unregister_region(disk);
-	/*
-	 * Remove gendisk pointer from idr so that it cannot be looked up
-	 * while RCU period before freeing gendisk is running to prevent
-	 * use-after-free issues. Note that the device number stays
-	 * "in-use" until we really free the gendisk.
-	 */
-	blk_invalidate_devt(disk_devt(disk));
 
 	kobject_put(disk->part0.holder_dir);
 	kobject_put(disk->slave_dir);
@@ -964,7 +902,7 @@ static ssize_t disk_badblocks_store(struct device *dev,
 	return badblocks_store(disk->bb, page, len, 0);
 }
 
-static void request_gendisk_module(dev_t devt)
+void blk_request_module(dev_t devt)
 {
 	unsigned int major = MAJOR(devt);
 	struct blk_major_name **n;
@@ -984,84 +922,6 @@ static void request_gendisk_module(dev_t devt)
 		request_module("block-major-%d", MAJOR(devt));
 }
 
-static bool get_disk_and_module(struct gendisk *disk)
-{
-	struct module *owner;
-
-	if (!disk->fops)
-		return false;
-	owner = disk->fops->owner;
-	if (owner && !try_module_get(owner))
-		return false;
-	if (!kobject_get_unless_zero(&disk_to_dev(disk)->kobj)) {
-		module_put(owner);
-		return false;
-	}
-	return true;
-
-}
-
-/**
- * get_gendisk - get partitioning information for a given device
- * @devt: device to get partitioning information for
- * @partno: returned partition index
- *
- * This function gets the structure containing partitioning
- * information for the given device @devt.
- *
- * Context: can sleep
- */
-struct gendisk *get_gendisk(dev_t devt, int *partno)
-{
-	struct gendisk *disk = NULL;
-
-	might_sleep();
-
-	if (MAJOR(devt) != BLOCK_EXT_MAJOR) {
-		mutex_lock(&bdev_map_lock);
-		disk = xa_load(&bdev_map, devt);
-		if (!disk) {
-			mutex_unlock(&bdev_map_lock);
-			request_gendisk_module(devt);
-			mutex_lock(&bdev_map_lock);
-			disk = xa_load(&bdev_map, devt);
-		}
-		if (disk && !get_disk_and_module(disk))
-			disk = NULL;
-		if (disk)
-			*partno = devt - disk_devt(disk);
-		mutex_unlock(&bdev_map_lock);
-	} else {
-		struct hd_struct *part;
-
-		spin_lock_bh(&ext_devt_lock);
-		part = idr_find(&ext_devt_idr, blk_mangle_minor(MINOR(devt)));
-		if (part && get_disk_and_module(part_to_disk(part))) {
-			*partno = part->partno;
-			disk = part_to_disk(part);
-		}
-		spin_unlock_bh(&ext_devt_lock);
-	}
-
-	if (!disk)
-		return NULL;
-
-	/*
-	 * Synchronize with del_gendisk() to not return disk that is being
-	 * destroyed.
-	 */
-	down_read(&disk->lookup_sem);
-	if (unlikely((disk->flags & GENHD_FL_HIDDEN) ||
-		     !(disk->flags & GENHD_FL_UP))) {
-		up_read(&disk->lookup_sem);
-		put_disk_and_module(disk);
-		disk = NULL;
-	} else {
-		up_read(&disk->lookup_sem);
-	}
-	return disk;
-}
-
 /**
  * bdget_disk - do bdget() by gendisk and partition number
  * @disk: gendisk of interest
@@ -1559,11 +1419,6 @@ int disk_expand_part_tbl(struct gendisk *disk, int partno)
  *
  * This function releases all allocated resources of the gendisk.
  *
- * The struct gendisk refcount is incremented with get_gendisk() or
- * get_disk_and_module(), and its refcount is decremented with
- * put_disk_and_module() or put_disk(). Once the refcount reaches 0 this
- * function is called.
- *
  * Drivers which used __device_add_disk() have a gendisk with a request_queue
  * assigned. Since the request_queue sits on top of the gendisk for these
  * drivers we also call blk_put_queue() for them, and we expect the
@@ -1748,16 +1603,17 @@ struct gendisk *__alloc_disk_node(int minors, int node_id)
 	if (!disk)
 		return NULL;
 
+	disk->part0.bdev = bdev_alloc(disk, 0);
+	if (!disk->part0.bdev)
+		goto out_free_disk;
+
 	disk->part0.dkstats = alloc_percpu(struct disk_stats);
 	if (!disk->part0.dkstats)
-		goto out_free_disk;
+		goto out_bdput;
 
-	init_rwsem(&disk->lookup_sem);
 	disk->node_id = node_id;
-	if (disk_expand_part_tbl(disk, 0)) {
-		free_percpu(disk->part0.dkstats);
-		goto out_free_disk;
-	}
+	if (disk_expand_part_tbl(disk, 0))
+		goto out_free_bdstats;
 
 	ptbl = rcu_dereference_protected(disk->part_tbl, 1);
 	rcu_assign_pointer(ptbl->part[0], &disk->part0);
@@ -1773,7 +1629,7 @@ struct gendisk *__alloc_disk_node(int minors, int node_id)
 	 */
 	hd_sects_seq_init(&disk->part0);
 	if (hd_ref_init(&disk->part0))
-		goto out_free_part0;
+		goto out_free_bdstats;
 
 	disk->minors = minors;
 	rand_initialize_disk(disk);
@@ -1782,8 +1638,10 @@ struct gendisk *__alloc_disk_node(int minors, int node_id)
 	device_initialize(disk_to_dev(disk));
 	return disk;
 
-out_free_part0:
-	hd_free_part(&disk->part0);
+out_free_bdstats:
+	free_percpu(disk->part0.dkstats);
+out_bdput:
+	bdput(disk->part0.bdev);
 out_free_disk:
 	kfree(disk);
 	return NULL;
@@ -1807,26 +1665,6 @@ void put_disk(struct gendisk *disk)
 }
 EXPORT_SYMBOL(put_disk);
 
-/**
- * put_disk_and_module - decrements the module and gendisk refcount
- * @disk: the struct gendisk to decrement the refcount for
- *
- * This is a counterpart of get_disk_and_module() and thus also of
- * get_gendisk().
- *
- * Context: Any context, but the last reference must not be dropped from
- *          atomic context.
- */
-void put_disk_and_module(struct gendisk *disk)
-{
-	if (disk) {
-		struct module *owner = disk->fops->owner;
-
-		put_disk(disk);
-		module_put(owner);
-	}
-}
-
 static void set_disk_ro_uevent(struct gendisk *gd, int ro)
 {
 	char event[] = "DISK_RO=1";
diff --git a/block/partitions/core.c b/block/partitions/core.c
index a02e22411594..696bd9ff63c6 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -340,12 +340,11 @@ void delete_partition(struct hd_struct *part)
 	device_del(part_to_dev(part));
 
 	/*
-	 * Remove gendisk pointer from idr so that it cannot be looked up
-	 * while RCU period before freeing gendisk is running to prevent
-	 * use-after-free issues. Note that the device number stays
-	 * "in-use" until we really free the gendisk.
+	 * Remove the block device from the inode hash, so that it cannot be
+	 * looked up any more even when openers still hold references.
 	 */
-	blk_invalidate_devt(part_devt(part));
+	remove_inode_hash(part->bdev->bd_inode);
+
 	percpu_ref_kill(&part->ref);
 }
 
@@ -368,6 +367,7 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 	dev_t devt = MKDEV(0, 0);
 	struct device *ddev = disk_to_dev(disk);
 	struct device *pdev;
+	struct block_device *bdev;
 	struct disk_part_tbl *ptbl;
 	const char *dname;
 	int err;
@@ -402,11 +402,15 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 	if (!p)
 		return ERR_PTR(-EBUSY);
 
+	err = -ENOMEM;
 	p->dkstats = alloc_percpu(struct disk_stats);
-	if (!p->dkstats) {
-		err = -ENOMEM;
+	if (!p->dkstats)
 		goto out_free;
-	}
+
+	bdev = bdev_alloc(disk, partno);
+	if (!bdev)
+		goto out_free_stats;
+	p->bdev = bdev;
 
 	hd_sects_seq_init(p);
 	pdev = part_to_dev(p);
@@ -420,10 +424,8 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 		struct partition_meta_info *pinfo;
 
 		pinfo = kzalloc_node(sizeof(*pinfo), GFP_KERNEL, disk->node_id);
-		if (!pinfo) {
-			err = -ENOMEM;
-			goto out_free_stats;
-		}
+		if (!pinfo)
+			goto out_bdput;
 		memcpy(pinfo, info, sizeof(*info));
 		p->info = pinfo;
 	}
@@ -470,6 +472,7 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 	}
 
 	/* everything is up and running, commence */
+	bdev_add(bdev, devt);
 	rcu_assign_pointer(ptbl->part[partno], p);
 
 	/* suppress uevent if the disk suppresses it */
@@ -479,6 +482,8 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 
 out_free_info:
 	kfree(p->info);
+out_bdput:
+	bdput(bdev);
 out_free_stats:
 	free_percpu(p->dkstats);
 out_free:
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 6d6e4d50834c..b350ed3af83b 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -863,31 +863,46 @@ void __init bdev_cache_init(void)
 	blockdev_superblock = bd_mnt->mnt_sb;   /* For writeback */
 }
 
-static struct block_device *bdget(dev_t dev)
+struct block_device *bdev_alloc(struct gendisk *disk, u8 partno)
 {
 	struct block_device *bdev;
 	struct inode *inode;
 
-	inode = iget_locked(blockdev_superblock, dev);
+	inode = new_inode(blockdev_superblock);
 	if (!inode)
 		return NULL;
+	inode->i_mode = S_IFBLK;
+	inode->i_rdev = 0;
+	inode->i_data.a_ops = &def_blk_aops;
+	mapping_set_gfp_mask(&inode->i_data, GFP_USER);
+
+	bdev = I_BDEV(inode);
+	spin_lock_init(&bdev->bd_size_lock);
+	bdev->bd_disk = disk;
+	bdev->bd_partno = partno;
+	bdev->bd_contains = NULL;
+	bdev->bd_super = NULL;
+	bdev->bd_inode = inode;
+	bdev->bd_part_count = 0;
+	return bdev;
+}
 
-	bdev = &BDEV_I(inode)->bdev;
+void bdev_add(struct block_device *bdev, dev_t dev)
+{
+	bdev->bd_dev = dev;
+	bdev->bd_inode->i_rdev = dev;
+	bdev->bd_inode->i_ino = dev;
+	insert_inode_hash(bdev->bd_inode);
+}
 
-	if (inode->i_state & I_NEW) {
-		spin_lock_init(&bdev->bd_size_lock);
-		bdev->bd_contains = NULL;
-		bdev->bd_super = NULL;
-		bdev->bd_inode = inode;
-		bdev->bd_part_count = 0;
-		bdev->bd_dev = dev;
-		inode->i_mode = S_IFBLK;
-		inode->i_rdev = dev;
-		inode->i_data.a_ops = &def_blk_aops;
-		mapping_set_gfp_mask(&inode->i_data, GFP_USER);
-		unlock_new_inode(inode);
-	}
-	return bdev;
+static struct block_device *bdget(dev_t dev)
+{
+	struct inode *inode;
+
+	inode = ilookup(blockdev_superblock, dev);
+	if (!inode)
+		return NULL;
+	return &BDEV_I(inode)->bdev;
 }
 
 /**
@@ -1004,27 +1019,6 @@ retry:
 }
 EXPORT_SYMBOL_GPL(bd_prepare_to_claim); /* only for the loop driver */
 
-static struct gendisk *bdev_get_gendisk(struct block_device *bdev, int *partno)
-{
-	struct gendisk *disk = get_gendisk(bdev->bd_dev, partno);
-
-	if (!disk)
-		return NULL;
-	/*
-	 * Now that we hold gendisk reference we make sure bdev we looked up is
-	 * not stale. If it is, it means device got removed and created before
-	 * we looked up gendisk and we fail open in such case. Associating
-	 * unhashed bdev with newly created gendisk could lead to two bdevs
-	 * (and thus two independent caches) being associated with one device
-	 * which is bad.
-	 */
-	if (inode_unhashed(bdev->bd_inode)) {
-		put_disk_and_module(disk);
-		return NULL;
-	}
-	return disk;
-}
-
 static void bd_clear_claiming(struct block_device *whole, void *holder)
 {
 	lockdep_assert_held(&bdev_lock);
@@ -1347,19 +1341,17 @@ EXPORT_SYMBOL_GPL(bdev_disk_changed);
  *  mutex_lock(part->bd_mutex)
  *    mutex_lock_nested(whole->bd_mutex, 1)
  */
-static int __blkdev_get(struct block_device *bdev, struct gendisk *disk,
-		int partno, fmode_t mode)
+static int __blkdev_get(struct block_device *bdev, fmode_t mode)
 {
+	struct gendisk *disk = bdev->bd_disk;
 	int ret;
 
 	if (!bdev->bd_openers) {
-		bdev->bd_disk = disk;
 		bdev->bd_contains = bdev;
-		bdev->bd_partno = partno;
 
-		if (!partno) {
+		if (!bdev->bd_partno) {
 			ret = -ENXIO;
-			bdev->bd_part = disk_get_part(disk, partno);
+			bdev->bd_part = disk_get_part(disk, 0);
 			if (!bdev->bd_part)
 				goto out_clear;
 
@@ -1388,7 +1380,7 @@ static int __blkdev_get(struct block_device *bdev, struct gendisk *disk,
 			struct block_device *whole = bdget_disk(disk, 0);
 
 			mutex_lock_nested(&whole->bd_mutex, 1);
-			ret = __blkdev_get(whole, disk, 0, mode);
+			ret = __blkdev_get(whole, mode);
 			if (ret) {
 				mutex_unlock(&whole->bd_mutex);
 				bdput(whole);
@@ -1398,7 +1390,7 @@ static int __blkdev_get(struct block_device *bdev, struct gendisk *disk,
 			mutex_unlock(&whole->bd_mutex);
 
 			bdev->bd_contains = whole;
-			bdev->bd_part = disk_get_part(disk, partno);
+			bdev->bd_part = disk_get_part(disk, bdev->bd_partno);
 			if (!(disk->flags & GENHD_FL_UP) ||
 			    !bdev->bd_part || !bdev->bd_part->nr_sects) {
 				__blkdev_put(whole, mode, 1);
@@ -1430,12 +1422,53 @@ static int __blkdev_get(struct block_device *bdev, struct gendisk *disk,
 
  out_clear:
 	disk_put_part(bdev->bd_part);
-	bdev->bd_disk = NULL;
 	bdev->bd_part = NULL;
 	bdev->bd_contains = NULL;
 	return ret;
 }
 
+struct block_device *blkdev_get_no_open(dev_t dev)
+{
+	struct block_device *bdev;
+	struct gendisk *disk;
+
+	down_read(&bdev_lookup_sem);
+	bdev = bdget(dev);
+	if (!bdev) {
+		up_read(&bdev_lookup_sem);
+		blk_request_module(dev);
+		down_read(&bdev_lookup_sem);
+
+		bdev = bdget(dev);
+		if (!bdev)
+			goto unlock;
+	}
+
+	disk = bdev->bd_disk;
+	if (!kobject_get_unless_zero(&disk_to_dev(disk)->kobj))
+		goto bdput;
+	if ((disk->flags & (GENHD_FL_UP | GENHD_FL_HIDDEN)) != GENHD_FL_UP)
+		goto put_disk;
+	if (!try_module_get(bdev->bd_disk->fops->owner))
+		goto put_disk;
+	up_read(&bdev_lookup_sem);
+	return bdev;
+put_disk:
+	put_disk(disk);
+bdput:
+	bdput(bdev);
+unlock:
+	up_read(&bdev_lookup_sem);
+	return NULL;
+}
+
+void blkdev_put_no_open(struct block_device *bdev)
+{
+	module_put(bdev->bd_disk->fops->owner);
+	put_disk(bdev->bd_disk);
+	bdput(bdev);
+}
+
 /**
  * blkdev_get_by_dev - open a block device by device number
  * @dev: device number of block device to open
@@ -1463,7 +1496,6 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
 	bool unblock_events = true;
 	struct block_device *bdev;
 	struct gendisk *disk;
-	int partno;
 	int ret;
 
 	ret = devcgroup_check_permission(DEVCG_DEV_BLOCK,
@@ -1473,18 +1505,14 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
 	if (ret)
 		return ERR_PTR(ret);
 
-	bdev = bdget(dev);
-	if (!bdev)
-		return ERR_PTR(-ENOMEM);
-
 	/*
 	 * If we lost a race with 'disk' being deleted, try again.  See md.c.
 	 */
 retry:
-	ret = -ENXIO;
-	disk = bdev_get_gendisk(bdev, &partno);
-	if (!disk)
-		goto bdput;
+	bdev = blkdev_get_no_open(dev);
+	if (!bdev)
+		return ERR_PTR(-ENXIO);
+	disk = bdev->bd_disk;
 
 	if (mode & FMODE_EXCL) {
 		WARN_ON_ONCE(!holder);
@@ -1492,7 +1520,7 @@ retry:
 		ret = -ENOMEM;
 		claiming = bdget_disk(disk, 0);
 		if (!claiming)
-			goto put_disk;
+			goto put_blkdev;
 		ret = bd_prepare_to_claim(bdev, claiming, holder);
 		if (ret)
 			goto put_claiming;
@@ -1501,12 +1529,10 @@ retry:
 	disk_block_events(disk);
 
 	mutex_lock(&bdev->bd_mutex);
-	ret =__blkdev_get(bdev, disk, partno, mode);
-	if (!(mode & FMODE_EXCL)) {
-		; /* nothing to do here */
-	} else if (ret) {
-		bd_abort_claiming(bdev, claiming, holder);
-	} else {
+	ret =__blkdev_get(bdev, mode);
+	if (ret)
+		goto abort_claiming;
+	if (mode & FMODE_EXCL) {
 		bd_finish_claiming(bdev, claiming, holder);
 
 		/*
@@ -1526,21 +1552,23 @@ retry:
 
 	if (unblock_events)
 		disk_unblock_events(disk);
+	if (mode & FMODE_EXCL)
+		bdput(claiming);
+	return bdev;
 
+abort_claiming:
+	if (mode & FMODE_EXCL)
+		bd_abort_claiming(bdev, claiming, holder);
+	mutex_unlock(&bdev->bd_mutex);
+	disk_unblock_events(disk);
 put_claiming:
 	if (mode & FMODE_EXCL)
 		bdput(claiming);
-put_disk:
-	if (ret)
-		put_disk_and_module(disk);
+put_blkdev:
+	blkdev_put_no_open(bdev);
 	if (ret == -ERESTARTSYS)
 		goto retry;
-bdput:
-	if (ret) {
-		bdput(bdev);
-		return ERR_PTR(ret);
-	}
-	return bdev;
+	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL(blkdev_get_by_dev);
 
@@ -1641,7 +1669,6 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
 
 		disk_put_part(bdev->bd_part);
 		bdev->bd_part = NULL;
-		bdev->bd_disk = NULL;
 		if (bdev_is_partition(bdev))
 			victim = bdev->bd_contains;
 		bdev->bd_contains = NULL;
@@ -1699,12 +1726,10 @@ void blkdev_put(struct block_device *bdev, fmode_t mode)
 	 * from userland - e.g. eject(1).
 	 */
 	disk_flush_events(disk, DISK_EVENT_MEDIA_CHANGE);
-
 	mutex_unlock(&bdev->bd_mutex);
 
 	__blkdev_put(bdev, mode, 0);
-	bdput(bdev);
-	put_disk_and_module(disk);
+	blkdev_put_no_open(bdev);
 }
 EXPORT_SYMBOL(blkdev_put);
 
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index c8fc9792ac77..b9f3c246c3c9 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -197,12 +197,12 @@ void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg,
 u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v);
 
 struct blkg_conf_ctx {
-	struct gendisk			*disk;
+	struct block_device		*bdev;
 	struct blkcg_gq			*blkg;
 	char				*body;
 };
 
-struct gendisk *blkcg_conf_get_disk(char **inputp);
+struct block_device *blkcg_conf_open_bdev(char **inputp);
 int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 		   char *input, struct blkg_conf_ctx *ctx);
 void blkg_conf_finish(struct blkg_conf_ctx *ctx);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index bdd7339bcda4..5d48b92f5e43 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1994,6 +1994,12 @@ void bd_abort_claiming(struct block_device *bdev, struct block_device *whole,
 		void *holder);
 void blkdev_put(struct block_device *bdev, fmode_t mode);
 
+/* just for blk-cgroup, don't use elsewhere */
+struct block_device *blkdev_get_no_open(dev_t dev);
+void blkdev_put_no_open(struct block_device *bdev);
+
+struct block_device *bdev_alloc(struct gendisk *disk, u8 partno);
+void bdev_add(struct block_device *bdev, dev_t dev);
 struct block_device *I_BDEV(struct inode *inode);
 struct block_device *bdget_part(struct hd_struct *part);
 struct block_device *bdgrab(struct block_device *bdev);
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index ca5e356084c3..42a51653c730 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -65,6 +65,7 @@ struct hd_struct {
 	struct disk_stats __percpu *dkstats;
 	struct percpu_ref ref;
 
+	struct block_device *bdev;
 	struct device __dev;
 	struct kobject *holder_dir;
 	int policy, partno;
@@ -193,7 +194,6 @@ struct gendisk {
 	int flags;
 	unsigned long state;
 #define GD_NEED_PART_SCAN		0
-	struct rw_semaphore lookup_sem;
 	struct kobject *slave_dir;
 
 	struct timer_rand_state *random;
@@ -300,7 +300,6 @@ static inline void add_disk_no_queue_reg(struct gendisk *disk)
 }
 
 extern void del_gendisk(struct gendisk *gp);
-extern struct gendisk *get_gendisk(dev_t dev, int *partno);
 extern struct block_device *bdget_disk(struct gendisk *disk, int partno);
 
 extern void set_disk_ro(struct gendisk *disk, int flag);
@@ -338,7 +337,6 @@ int blk_drop_partitions(struct block_device *bdev);
 
 extern struct gendisk *__alloc_disk_node(int minors, int node_id);
 extern void put_disk(struct gendisk *disk);
-extern void put_disk_and_module(struct gendisk *disk);
 
 #define alloc_disk_node(minors, node_id)				\
 ({									\
@@ -388,7 +386,10 @@ static inline void bd_unlink_disk_holder(struct block_device *bdev,
 }
 #endif /* CONFIG_SYSFS */
 
+extern struct rw_semaphore bdev_lookup_sem;
+
 dev_t blk_lookup_devt(const char *name, int partno);
+void blk_request_module(dev_t devt);
 #ifdef CONFIG_BLOCK
 void printk_all_partitions(void);
 #else /* CONFIG_BLOCK */
-- 
cgit v1.2.3


From a954ea812018a84d350b316c39a2be3edc4b7ca8 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 23 Nov 2020 13:29:55 +0100
Subject: block: remove ->bd_contains

Now that each hd_struct has a reference to the corresponding
block_device, there is no need for the bd_contains pointer.  Add
a bdev_whole() helper to look up the whole device block_device
struture instead.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/loop.c      |  2 +-
 drivers/scsi/scsicam.c    |  2 +-
 fs/block_dev.c            | 22 ++++++++--------------
 include/linux/blk_types.h |  4 +++-
 4 files changed, 13 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 26c7aafba7c5..c0df88b3300c 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1088,7 +1088,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode,
 	 * here to avoid changing device under exclusive owner.
 	 */
 	if (!(mode & FMODE_EXCL)) {
-		claimed_bdev = bdev->bd_contains;
+		claimed_bdev = bdev_whole(bdev);
 		error = bd_prepare_to_claim(bdev, claimed_bdev, loop_configure);
 		if (error)
 			goto out_putf;
diff --git a/drivers/scsi/scsicam.c b/drivers/scsi/scsicam.c
index 682cf08ab041..f1553a453616 100644
--- a/drivers/scsi/scsicam.c
+++ b/drivers/scsi/scsicam.c
@@ -32,7 +32,7 @@
  */
 unsigned char *scsi_bios_ptable(struct block_device *dev)
 {
-	struct address_space *mapping = dev->bd_contains->bd_inode->i_mapping;
+	struct address_space *mapping = bdev_whole(dev)->bd_inode->i_mapping;
 	unsigned char *res = NULL;
 	struct page *page;
 
diff --git a/fs/block_dev.c b/fs/block_dev.c
index b350ed3af83b..94baee369d26 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -119,7 +119,7 @@ int truncate_bdev_range(struct block_device *bdev, fmode_t mode,
 	 * under live filesystem.
 	 */
 	if (!(mode & FMODE_EXCL)) {
-		claimed_bdev = bdev->bd_contains;
+		claimed_bdev = bdev_whole(bdev);
 		err = bd_prepare_to_claim(bdev, claimed_bdev,
 					  truncate_bdev_range);
 		if (err)
@@ -880,7 +880,6 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno)
 	spin_lock_init(&bdev->bd_size_lock);
 	bdev->bd_disk = disk;
 	bdev->bd_partno = partno;
-	bdev->bd_contains = NULL;
 	bdev->bd_super = NULL;
 	bdev->bd_inode = inode;
 	bdev->bd_part_count = 0;
@@ -1347,9 +1346,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode)
 	int ret;
 
 	if (!bdev->bd_openers) {
-		bdev->bd_contains = bdev;
-
-		if (!bdev->bd_partno) {
+		if (!bdev_is_partition(bdev)) {
 			ret = -ENXIO;
 			bdev->bd_part = disk_get_part(disk, 0);
 			if (!bdev->bd_part)
@@ -1389,7 +1386,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode)
 			whole->bd_part_count++;
 			mutex_unlock(&whole->bd_mutex);
 
-			bdev->bd_contains = whole;
 			bdev->bd_part = disk_get_part(disk, bdev->bd_partno);
 			if (!(disk->flags & GENHD_FL_UP) ||
 			    !bdev->bd_part || !bdev->bd_part->nr_sects) {
@@ -1405,7 +1401,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode)
 		if (bdev->bd_bdi == &noop_backing_dev_info)
 			bdev->bd_bdi = bdi_get(disk->queue->backing_dev_info);
 	} else {
-		if (bdev->bd_contains == bdev) {
+		if (!bdev_is_partition(bdev)) {
 			ret = 0;
 			if (bdev->bd_disk->fops->open)
 				ret = bdev->bd_disk->fops->open(bdev, mode);
@@ -1423,7 +1419,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode)
  out_clear:
 	disk_put_part(bdev->bd_part);
 	bdev->bd_part = NULL;
-	bdev->bd_contains = NULL;
 	return ret;
 }
 
@@ -1670,8 +1665,7 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
 		disk_put_part(bdev->bd_part);
 		bdev->bd_part = NULL;
 		if (bdev_is_partition(bdev))
-			victim = bdev->bd_contains;
-		bdev->bd_contains = NULL;
+			victim = bdev_whole(bdev);
 	} else {
 		if (!bdev_is_partition(bdev) && disk->fops->release)
 			disk->fops->release(disk, mode);
@@ -1690,6 +1684,7 @@ void blkdev_put(struct block_device *bdev, fmode_t mode)
 	mutex_lock(&bdev->bd_mutex);
 
 	if (mode & FMODE_EXCL) {
+		struct block_device *whole = bdev_whole(bdev);
 		bool bdev_free;
 
 		/*
@@ -1700,13 +1695,12 @@ void blkdev_put(struct block_device *bdev, fmode_t mode)
 		spin_lock(&bdev_lock);
 
 		WARN_ON_ONCE(--bdev->bd_holders < 0);
-		WARN_ON_ONCE(--bdev->bd_contains->bd_holders < 0);
+		WARN_ON_ONCE(--whole->bd_holders < 0);
 
-		/* bd_contains might point to self, check in a separate step */
 		if ((bdev_free = !bdev->bd_holders))
 			bdev->bd_holder = NULL;
-		if (!bdev->bd_contains->bd_holders)
-			bdev->bd_contains->bd_holder = NULL;
+		if (!whole->bd_holders)
+			whole->bd_holder = NULL;
 
 		spin_unlock(&bdev_lock);
 
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 9698f459cc65..2e0a9bd9688d 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -32,7 +32,6 @@ struct block_device {
 #ifdef CONFIG_SYSFS
 	struct list_head	bd_holder_disks;
 #endif
-	struct block_device *	bd_contains;
 	u8			bd_partno;
 	struct hd_struct *	bd_part;
 	/* number of times partitions within this device have been opened. */
@@ -49,6 +48,9 @@ struct block_device {
 	struct super_block	*bd_fsfreeze_sb;
 } __randomize_layout;
 
+#define bdev_whole(_bdev) \
+	((_bdev)->bd_disk->part0.bdev)
+
 #define bdev_kobj(_bdev) \
 	(&part_to_dev((_bdev)->bd_part)->kobj)
 
-- 
cgit v1.2.3


From 37c3fc9abb25cd767ad5b048358336ac89488c16 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 25 Nov 2020 21:20:08 +0100
Subject: block: simplify the block device claiming interface

Stop passing the whole device as a separate argument given that it
can be trivially deducted and cleanup the !holder debug check.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/loop.c   | 12 +++++-------
 fs/block_dev.c         | 51 ++++++++++++++++++--------------------------------
 include/linux/blkdev.h |  6 ++----
 3 files changed, 25 insertions(+), 44 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index c0df88b3300c..d643c67be6ac 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1069,7 +1069,6 @@ static int loop_configure(struct loop_device *lo, fmode_t mode,
 	struct file	*file;
 	struct inode	*inode;
 	struct address_space *mapping;
-	struct block_device *claimed_bdev = NULL;
 	int		error;
 	loff_t		size;
 	bool		partscan;
@@ -1088,8 +1087,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode,
 	 * here to avoid changing device under exclusive owner.
 	 */
 	if (!(mode & FMODE_EXCL)) {
-		claimed_bdev = bdev_whole(bdev);
-		error = bd_prepare_to_claim(bdev, claimed_bdev, loop_configure);
+		error = bd_prepare_to_claim(bdev, loop_configure);
 		if (error)
 			goto out_putf;
 	}
@@ -1176,15 +1174,15 @@ static int loop_configure(struct loop_device *lo, fmode_t mode,
 	mutex_unlock(&loop_ctl_mutex);
 	if (partscan)
 		loop_reread_partitions(lo, bdev);
-	if (claimed_bdev)
-		bd_abort_claiming(bdev, claimed_bdev, loop_configure);
+	if (!(mode & FMODE_EXCL))
+		bd_abort_claiming(bdev, loop_configure);
 	return 0;
 
 out_unlock:
 	mutex_unlock(&loop_ctl_mutex);
 out_bdev:
-	if (claimed_bdev)
-		bd_abort_claiming(bdev, claimed_bdev, loop_configure);
+	if (!(mode & FMODE_EXCL))
+		bd_abort_claiming(bdev, loop_configure);
 out_putf:
 	fput(file);
 out:
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 94baee369d26..0569f5ebeb6f 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -110,24 +110,20 @@ EXPORT_SYMBOL(invalidate_bdev);
 int truncate_bdev_range(struct block_device *bdev, fmode_t mode,
 			loff_t lstart, loff_t lend)
 {
-	struct block_device *claimed_bdev = NULL;
-	int err;
-
 	/*
 	 * If we don't hold exclusive handle for the device, upgrade to it
 	 * while we discard the buffer cache to avoid discarding buffers
 	 * under live filesystem.
 	 */
 	if (!(mode & FMODE_EXCL)) {
-		claimed_bdev = bdev_whole(bdev);
-		err = bd_prepare_to_claim(bdev, claimed_bdev,
-					  truncate_bdev_range);
+		int err = bd_prepare_to_claim(bdev, truncate_bdev_range);
 		if (err)
 			return err;
 	}
+
 	truncate_inode_pages_range(bdev->bd_inode->i_mapping, lstart, lend);
-	if (claimed_bdev)
-		bd_abort_claiming(bdev, claimed_bdev, truncate_bdev_range);
+	if (!(mode & FMODE_EXCL))
+		bd_abort_claiming(bdev, truncate_bdev_range);
 	return 0;
 }
 EXPORT_SYMBOL(truncate_bdev_range);
@@ -978,7 +974,6 @@ static bool bd_may_claim(struct block_device *bdev, struct block_device *whole,
 /**
  * bd_prepare_to_claim - claim a block device
  * @bdev: block device of interest
- * @whole: the whole device containing @bdev, may equal @bdev
  * @holder: holder trying to claim @bdev
  *
  * Claim @bdev.  This function fails if @bdev is already claimed by another
@@ -988,9 +983,12 @@ static bool bd_may_claim(struct block_device *bdev, struct block_device *whole,
  * RETURNS:
  * 0 if @bdev can be claimed, -EBUSY otherwise.
  */
-int bd_prepare_to_claim(struct block_device *bdev, struct block_device *whole,
-		void *holder)
+int bd_prepare_to_claim(struct block_device *bdev, void *holder)
 {
+	struct block_device *whole = bdev_whole(bdev);
+
+	if (WARN_ON_ONCE(!holder))
+		return -EINVAL;
 retry:
 	spin_lock(&bdev_lock);
 	/* if someone else claimed, fail */
@@ -1030,15 +1028,15 @@ static void bd_clear_claiming(struct block_device *whole, void *holder)
 /**
  * bd_finish_claiming - finish claiming of a block device
  * @bdev: block device of interest
- * @whole: whole block device
  * @holder: holder that has claimed @bdev
  *
  * Finish exclusive open of a block device. Mark the device as exlusively
  * open by the holder and wake up all waiters for exclusive open to finish.
  */
-static void bd_finish_claiming(struct block_device *bdev,
-		struct block_device *whole, void *holder)
+static void bd_finish_claiming(struct block_device *bdev, void *holder)
 {
+	struct block_device *whole = bdev_whole(bdev);
+
 	spin_lock(&bdev_lock);
 	BUG_ON(!bd_may_claim(bdev, whole, holder));
 	/*
@@ -1063,11 +1061,10 @@ static void bd_finish_claiming(struct block_device *bdev,
  * also used when exclusive open is not actually desired and we just needed
  * to block other exclusive openers for a while.
  */
-void bd_abort_claiming(struct block_device *bdev, struct block_device *whole,
-		       void *holder)
+void bd_abort_claiming(struct block_device *bdev, void *holder)
 {
 	spin_lock(&bdev_lock);
-	bd_clear_claiming(whole, holder);
+	bd_clear_claiming(bdev_whole(bdev), holder);
 	spin_unlock(&bdev_lock);
 }
 EXPORT_SYMBOL(bd_abort_claiming);
@@ -1487,7 +1484,6 @@ void blkdev_put_no_open(struct block_device *bdev)
  */
 struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
 {
-	struct block_device *claiming;
 	bool unblock_events = true;
 	struct block_device *bdev;
 	struct gendisk *disk;
@@ -1510,15 +1506,9 @@ retry:
 	disk = bdev->bd_disk;
 
 	if (mode & FMODE_EXCL) {
-		WARN_ON_ONCE(!holder);
-	
-		ret = -ENOMEM;
-		claiming = bdget_disk(disk, 0);
-		if (!claiming)
-			goto put_blkdev;
-		ret = bd_prepare_to_claim(bdev, claiming, holder);
+		ret = bd_prepare_to_claim(bdev, holder);
 		if (ret)
-			goto put_claiming;
+			goto put_blkdev;
 	}
 
 	disk_block_events(disk);
@@ -1528,7 +1518,7 @@ retry:
 	if (ret)
 		goto abort_claiming;
 	if (mode & FMODE_EXCL) {
-		bd_finish_claiming(bdev, claiming, holder);
+		bd_finish_claiming(bdev, holder);
 
 		/*
 		 * Block event polling for write claims if requested.  Any write
@@ -1547,18 +1537,13 @@ retry:
 
 	if (unblock_events)
 		disk_unblock_events(disk);
-	if (mode & FMODE_EXCL)
-		bdput(claiming);
 	return bdev;
 
 abort_claiming:
 	if (mode & FMODE_EXCL)
-		bd_abort_claiming(bdev, claiming, holder);
+		bd_abort_claiming(bdev, holder);
 	mutex_unlock(&bdev->bd_mutex);
 	disk_unblock_events(disk);
-put_claiming:
-	if (mode & FMODE_EXCL)
-		bdput(claiming);
 put_blkdev:
 	blkdev_put_no_open(bdev);
 	if (ret == -ERESTARTSYS)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 5d48b92f5e43..43a25d855e04 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1988,10 +1988,8 @@ void blkdev_show(struct seq_file *seqf, off_t offset);
 struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
 		void *holder);
 struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder);
-int bd_prepare_to_claim(struct block_device *bdev, struct block_device *whole,
-		void *holder);
-void bd_abort_claiming(struct block_device *bdev, struct block_device *whole,
-		void *holder);
+int bd_prepare_to_claim(struct block_device *bdev, void *holder);
+void bd_abort_claiming(struct block_device *bdev, void *holder);
 void blkdev_put(struct block_device *bdev, fmode_t mode);
 
 /* just for blk-cgroup, don't use elsewhere */
-- 
cgit v1.2.3


From c64dc3bd87097e7f08b9437819440f8bfddef995 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 23 Nov 2020 16:38:15 +0100
Subject: block: simplify part_to_disk

Now that struct hd_struct has a block_device pointer use that to
find the disk.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/genhd.h | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 42a51653c730..6ba91ee54cb2 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -218,13 +218,9 @@ struct gendisk {
 
 static inline struct gendisk *part_to_disk(struct hd_struct *part)
 {
-	if (likely(part)) {
-		if (part->partno)
-			return dev_to_disk(part_to_dev(part)->parent);
-		else
-			return dev_to_disk(part_to_dev(part));
-	}
-	return NULL;
+	if (unlikely(!part))
+		return NULL;
+	return part->bdev->bd_disk;
 }
 
 static inline int disk_max_parts(struct gendisk *disk)
-- 
cgit v1.2.3


From a782483cc1f875355690625d8253a232f2581418 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 26 Nov 2020 18:43:37 +0100
Subject: block: remove the nr_sects field in struct hd_struct

Now that the hd_struct always has a block device attached to it, there is
no need for having two size field that just get out of sync.

Additionally the field in hd_struct did not use proper serialization,
possibly allowing for torn writes.  By only using the block_device field
this problem also gets fixed.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Acked-by: Coly Li <colyli@suse.de>			[bcache]
Acked-by: Chao Yu <yuchao0@huawei.com>			[f2fs]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio.c                        |  4 +--
 block/blk-core.c                   |  2 +-
 block/blk.h                        | 53 ---------------------------
 block/genhd.c                      | 59 +++++++++++++++++-------------
 block/partitions/core.c            | 17 +++++----
 drivers/block/loop.c               |  1 -
 drivers/block/nbd.c                |  2 +-
 drivers/block/xen-blkback/common.h |  4 +--
 drivers/md/bcache/super.c          |  2 +-
 drivers/s390/block/dasd_ioctl.c    |  4 +--
 drivers/target/target_core_pscsi.c |  5 ++-
 fs/block_dev.c                     | 73 ++------------------------------------
 fs/f2fs/super.c                    |  2 +-
 fs/pstore/blk.c                    |  2 +-
 include/linux/genhd.h              | 29 ++++-----------
 kernel/trace/blktrace.c            |  2 +-
 16 files changed, 67 insertions(+), 194 deletions(-)

(limited to 'include/linux')

diff --git a/block/bio.c b/block/bio.c
index fa01bef35bb1..669bb47a3198 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -613,8 +613,8 @@ void guard_bio_eod(struct bio *bio)
 	rcu_read_lock();
 	part = __disk_get_part(bio->bi_disk, bio->bi_partno);
 	if (part)
-		maxsector = part_nr_sects_read(part);
-	else
+		maxsector = bdev_nr_sectors(part->bdev);
+	else	
 		maxsector = get_capacity(bio->bi_disk);
 	rcu_read_unlock();
 
diff --git a/block/blk-core.c b/block/blk-core.c
index 2db8bda43b6e..988f45094a38 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -755,7 +755,7 @@ static inline int blk_partition_remap(struct bio *bio)
 		goto out;
 
 	if (bio_sectors(bio)) {
-		if (bio_check_eod(bio, part_nr_sects_read(p)))
+		if (bio_check_eod(bio, bdev_nr_sectors(p->bdev)))
 			goto out;
 		bio->bi_iter.bi_sector += p->start_sect;
 		trace_block_bio_remap(bio->bi_disk->queue, bio, part_devt(p),
diff --git a/block/blk.h b/block/blk.h
index c4839abcfa27..09cee7024fb4 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -387,59 +387,6 @@ static inline void hd_free_part(struct hd_struct *part)
 	percpu_ref_exit(&part->ref);
 }
 
-/*
- * Any access of part->nr_sects which is not protected by partition
- * bd_mutex or gendisk bdev bd_mutex, should be done using this
- * accessor function.
- *
- * Code written along the lines of i_size_read() and i_size_write().
- * CONFIG_PREEMPTION case optimizes the case of UP kernel with preemption
- * on.
- */
-static inline sector_t part_nr_sects_read(struct hd_struct *part)
-{
-#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
-	sector_t nr_sects;
-	unsigned seq;
-	do {
-		seq = read_seqcount_begin(&part->nr_sects_seq);
-		nr_sects = part->nr_sects;
-	} while (read_seqcount_retry(&part->nr_sects_seq, seq));
-	return nr_sects;
-#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
-	sector_t nr_sects;
-
-	preempt_disable();
-	nr_sects = part->nr_sects;
-	preempt_enable();
-	return nr_sects;
-#else
-	return part->nr_sects;
-#endif
-}
-
-/*
- * Should be called with mutex lock held (typically bd_mutex) of partition
- * to provide mutual exlusion among writers otherwise seqcount might be
- * left in wrong state leaving the readers spinning infinitely.
- */
-static inline void part_nr_sects_write(struct hd_struct *part, sector_t size)
-{
-#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
-	preempt_disable();
-	write_seqcount_begin(&part->nr_sects_seq);
-	part->nr_sects = size;
-	write_seqcount_end(&part->nr_sects_seq);
-	preempt_enable();
-#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
-	preempt_disable();
-	part->nr_sects = size;
-	preempt_enable();
-#else
-	part->nr_sects = size;
-#endif
-}
-
 int bio_add_hw_page(struct request_queue *q, struct bio *bio,
 		struct page *page, unsigned int len, unsigned int offset,
 		unsigned int max_sectors, bool *same_page);
diff --git a/block/genhd.c b/block/genhd.c
index bf8fa82f135f..c65f485b9db5 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -40,6 +40,16 @@ static void disk_add_events(struct gendisk *disk);
 static void disk_del_events(struct gendisk *disk);
 static void disk_release_events(struct gendisk *disk);
 
+void set_capacity(struct gendisk *disk, sector_t sectors)
+{
+	struct block_device *bdev = disk->part0.bdev;
+
+	spin_lock(&bdev->bd_size_lock);
+	i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT);
+	spin_unlock(&bdev->bd_size_lock);
+}
+EXPORT_SYMBOL(set_capacity);
+
 /*
  * Set disk capacity and notify if the size is not currently zero and will not
  * be set to zero.  Returns true if a uevent was sent, otherwise false.
@@ -47,18 +57,30 @@ static void disk_release_events(struct gendisk *disk);
 bool set_capacity_and_notify(struct gendisk *disk, sector_t size)
 {
 	sector_t capacity = get_capacity(disk);
+	char *envp[] = { "RESIZE=1", NULL };
 
 	set_capacity(disk, size);
-	revalidate_disk_size(disk, true);
 
-	if (capacity != size && capacity != 0 && size != 0) {
-		char *envp[] = { "RESIZE=1", NULL };
+	/*
+	 * Only print a message and send a uevent if the gendisk is user visible
+	 * and alive.  This avoids spamming the log and udev when setting the
+	 * initial capacity during probing.
+	 */
+	if (size == capacity ||
+	    (disk->flags & (GENHD_FL_UP | GENHD_FL_HIDDEN)) != GENHD_FL_UP)
+		return false;
 
-		kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp);
-		return true;
-	}
+	pr_info("%s: detected capacity change from %lld to %lld\n",
+		disk->disk_name, size, capacity);
 
-	return false;
+	/*
+	 * Historically we did not send a uevent for changes to/from an empty
+	 * device.
+	 */
+	if (!capacity || !size)
+		return false;
+	kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp);
+	return true;
 }
 EXPORT_SYMBOL_GPL(set_capacity_and_notify);
 
@@ -247,7 +269,7 @@ struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter)
 		part = rcu_dereference(ptbl->part[piter->idx]);
 		if (!part)
 			continue;
-		if (!part_nr_sects_read(part) &&
+		if (!bdev_nr_sectors(part->bdev) &&
 		    !(piter->flags & DISK_PITER_INCL_EMPTY) &&
 		    !(piter->flags & DISK_PITER_INCL_EMPTY_PART0 &&
 		      piter->idx == 0))
@@ -284,7 +306,7 @@ EXPORT_SYMBOL_GPL(disk_part_iter_exit);
 static inline int sector_in_part(struct hd_struct *part, sector_t sector)
 {
 	return part->start_sect <= sector &&
-		sector < part->start_sect + part_nr_sects_read(part);
+		sector < part->start_sect + bdev_nr_sectors(part->bdev);
 }
 
 /**
@@ -986,8 +1008,8 @@ void __init printk_all_partitions(void)
 
 			printk("%s%s %10llu %s %s", is_part0 ? "" : "  ",
 			       bdevt_str(part_devt(part), devt_buf),
-			       (unsigned long long)part_nr_sects_read(part) >> 1
-			       , disk_name(disk, part->partno, name_buf),
+			       bdev_nr_sectors(part->bdev) >> 1,
+			       disk_name(disk, part->partno, name_buf),
 			       part->info ? part->info->uuid : "");
 			if (is_part0) {
 				if (dev->parent && dev->parent->driver)
@@ -1079,7 +1101,7 @@ static int show_partition(struct seq_file *seqf, void *v)
 	while ((part = disk_part_iter_next(&piter)))
 		seq_printf(seqf, "%4d  %7d %10llu %s\n",
 			   MAJOR(part_devt(part)), MINOR(part_devt(part)),
-			   (unsigned long long)part_nr_sects_read(part) >> 1,
+			   bdev_nr_sectors(part->bdev) >> 1,
 			   disk_name(sgp, part->partno, buf));
 	disk_part_iter_exit(&piter);
 
@@ -1161,8 +1183,7 @@ ssize_t part_size_show(struct device *dev,
 {
 	struct hd_struct *p = dev_to_part(dev);
 
-	return sprintf(buf, "%llu\n",
-		(unsigned long long)part_nr_sects_read(p));
+	return sprintf(buf, "%llu\n", bdev_nr_sectors(p->bdev));
 }
 
 ssize_t part_stat_show(struct device *dev,
@@ -1618,16 +1639,6 @@ struct gendisk *__alloc_disk_node(int minors, int node_id)
 	ptbl = rcu_dereference_protected(disk->part_tbl, 1);
 	rcu_assign_pointer(ptbl->part[0], &disk->part0);
 
-	/*
-	 * set_capacity() and get_capacity() currently don't use
-	 * seqcounter to read/update the part0->nr_sects. Still init
-	 * the counter as we can read the sectors in IO submission
-	 * patch using seqence counters.
-	 *
-	 * TODO: Ideally set_capacity() and get_capacity() should be
-	 * converted to make use of bd_mutex and sequence counters.
-	 */
-	hd_sects_seq_init(&disk->part0);
 	if (hd_ref_init(&disk->part0))
 		goto out_free_bdstats;
 
diff --git a/block/partitions/core.c b/block/partitions/core.c
index 696bd9ff63c6..bcfa8215bd5e 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -85,6 +85,13 @@ static int (*check_part[])(struct parsed_partitions *) = {
 	NULL
 };
 
+static void bdev_set_nr_sectors(struct block_device *bdev, sector_t sectors)
+{
+	spin_lock(&bdev->bd_size_lock);
+	i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT);
+	spin_unlock(&bdev->bd_size_lock);
+}
+
 static struct parsed_partitions *allocate_partitions(struct gendisk *hd)
 {
 	struct parsed_partitions *state;
@@ -295,7 +302,7 @@ static void hd_struct_free_work(struct work_struct *work)
 	put_device(disk_to_dev(disk));
 
 	part->start_sect = 0;
-	part->nr_sects = 0;
+	bdev_set_nr_sectors(part->bdev, 0);
 	part_stat_set_all(part, 0);
 	put_device(part_to_dev(part));
 }
@@ -412,11 +419,10 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 		goto out_free_stats;
 	p->bdev = bdev;
 
-	hd_sects_seq_init(p);
 	pdev = part_to_dev(p);
 
 	p->start_sect = start;
-	p->nr_sects = len;
+	bdev_set_nr_sectors(bdev, len);
 	p->partno = partno;
 	p->policy = get_disk_ro(disk);
 
@@ -509,7 +515,7 @@ static bool partition_overlaps(struct gendisk *disk, sector_t start,
 	disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY);
 	while ((part = disk_part_iter_next(&piter))) {
 		if (part->partno == skip_partno ||
-		    start >= part->start_sect + part->nr_sects ||
+		    start >= part->start_sect + bdev_nr_sectors(part->bdev) ||
 		    start + length <= part->start_sect)
 			continue;
 		overlap = true;
@@ -600,8 +606,7 @@ int bdev_resize_partition(struct block_device *bdev, int partno,
 	if (partition_overlaps(bdev->bd_disk, start, length, partno))
 		goto out_unlock;
 
-	part_nr_sects_write(part, length);
-	bd_set_nr_sectors(bdevp, length);
+	bdev_set_nr_sectors(bdevp, length);
 
 	ret = 0;
 out_unlock:
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index d643c67be6ac..d2ce1ddc192d 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1241,7 +1241,6 @@ static int __loop_clr_fd(struct loop_device *lo, bool release)
 	set_capacity(lo->lo_disk, 0);
 	loop_sysfs_exit(lo);
 	if (bdev) {
-		bd_set_nr_sectors(bdev, 0);
 		/* let user-space know about this change */
 		kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE);
 	}
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 45b0423ef2c5..014683968ce1 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -1132,7 +1132,7 @@ static void nbd_bdev_reset(struct block_device *bdev)
 {
 	if (bdev->bd_openers > 1)
 		return;
-	bd_set_nr_sectors(bdev, 0);
+	set_capacity(bdev->bd_disk, 0);
 }
 
 static void nbd_parse_flags(struct nbd_device *nbd)
diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h
index c6ea5d38c509..0762db247b41 100644
--- a/drivers/block/xen-blkback/common.h
+++ b/drivers/block/xen-blkback/common.h
@@ -358,9 +358,7 @@ struct pending_req {
 };
 
 
-#define vbd_sz(_v)	((_v)->bdev->bd_part ? \
-			 (_v)->bdev->bd_part->nr_sects : \
-			  get_capacity((_v)->bdev->bd_disk))
+#define vbd_sz(_v)	bdev_nr_sectors((_v)->bdev)
 
 #define xen_blkif_get(_b) (atomic_inc(&(_b)->refcnt))
 #define xen_blkif_put(_b)				\
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index c55d3c58a7ef..04fa40868fbe 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1408,7 +1408,7 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size)
 			q->limits.raid_partial_stripes_expensive;
 
 	ret = bcache_device_init(&dc->disk, block_size,
-			 dc->bdev->bd_part->nr_sects - dc->sb.data_offset,
+			 bdev_nr_sectors(dc->bdev) - dc->sb.data_offset,
 			 dc->bdev, &bcache_cached_ops);
 	if (ret)
 		return ret;
diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c
index 3359559517bf..304eba1acf16 100644
--- a/drivers/s390/block/dasd_ioctl.c
+++ b/drivers/s390/block/dasd_ioctl.c
@@ -54,8 +54,6 @@ dasd_ioctl_enable(struct block_device *bdev)
 		return -ENODEV;
 
 	dasd_enable_device(base);
-	/* Formatting the dasd device can change the capacity. */
-	bd_set_nr_sectors(bdev, get_capacity(base->block->gdp));
 	dasd_put_device(base);
 	return 0;
 }
@@ -88,7 +86,7 @@ dasd_ioctl_disable(struct block_device *bdev)
 	 * Set i_size to zero, since read, write, etc. check against this
 	 * value.
 	 */
-	bd_set_nr_sectors(bdev, 0);
+	set_capacity(bdev->bd_disk, 0);
 	dasd_put_device(base);
 	return 0;
 }
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index 4e37fa9b409d..7994f27e4527 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -1029,9 +1029,8 @@ static sector_t pscsi_get_blocks(struct se_device *dev)
 {
 	struct pscsi_dev_virt *pdv = PSCSI_DEV(dev);
 
-	if (pdv->pdv_bd && pdv->pdv_bd->bd_part)
-		return pdv->pdv_bd->bd_part->nr_sects;
-
+	if (pdv->pdv_bd)
+		return bdev_nr_sectors(pdv->pdv_bd);
 	return 0;
 }
 
diff --git a/fs/block_dev.c b/fs/block_dev.c
index a5b6955a841f..31ee5a857f71 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1208,70 +1208,6 @@ void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk)
 EXPORT_SYMBOL_GPL(bd_unlink_disk_holder);
 #endif
 
-/**
- * check_disk_size_change - checks for disk size change and adjusts bdev size.
- * @disk: struct gendisk to check
- * @bdev: struct bdev to adjust.
- * @verbose: if %true log a message about a size change if there is any
- *
- * This routine checks to see if the bdev size does not match the disk size
- * and adjusts it if it differs. When shrinking the bdev size, its all caches
- * are freed.
- */
-static void check_disk_size_change(struct gendisk *disk,
-		struct block_device *bdev, bool verbose)
-{
-	loff_t disk_size, bdev_size;
-
-	spin_lock(&bdev->bd_size_lock);
-	disk_size = (loff_t)get_capacity(disk) << 9;
-	bdev_size = i_size_read(bdev->bd_inode);
-	if (disk_size != bdev_size) {
-		if (verbose) {
-			printk(KERN_INFO
-			       "%s: detected capacity change from %lld to %lld\n",
-			       disk->disk_name, bdev_size, disk_size);
-		}
-		i_size_write(bdev->bd_inode, disk_size);
-	}
-	spin_unlock(&bdev->bd_size_lock);
-}
-
-/**
- * revalidate_disk_size - checks for disk size change and adjusts bdev size.
- * @disk: struct gendisk to check
- * @verbose: if %true log a message about a size change if there is any
- *
- * This routine checks to see if the bdev size does not match the disk size
- * and adjusts it if it differs. When shrinking the bdev size, its all caches
- * are freed.
- */
-void revalidate_disk_size(struct gendisk *disk, bool verbose)
-{
-	struct block_device *bdev;
-
-	/*
-	 * Hidden disks don't have associated bdev so there's no point in
-	 * revalidating them.
-	 */
-	if (disk->flags & GENHD_FL_HIDDEN)
-		return;
-
-	bdev = bdget_disk(disk, 0);
-	if (bdev) {
-		check_disk_size_change(disk, bdev, verbose);
-		bdput(bdev);
-	}
-}
-
-void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors)
-{
-	spin_lock(&bdev->bd_size_lock);
-	i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT);
-	spin_unlock(&bdev->bd_size_lock);
-}
-EXPORT_SYMBOL(bd_set_nr_sectors);
-
 static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
 
 int bdev_disk_changed(struct block_device *bdev, bool invalidate)
@@ -1305,8 +1241,6 @@ rescan:
 			disk->fops->revalidate_disk(disk);
 	}
 
-	check_disk_size_change(disk, bdev, !invalidate);
-
 	if (get_capacity(disk)) {
 		ret = blk_add_partitions(disk, bdev);
 		if (ret == -EAGAIN)
@@ -1349,10 +1283,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode)
 			if (disk->fops->open)
 				ret = disk->fops->open(bdev, mode);
 
-			if (!ret) {
-				bd_set_nr_sectors(bdev, get_capacity(disk));
+			if (!ret)
 				set_init_blocksize(bdev);
-			}
 
 			/*
 			 * If the device is invalidated, rescan partition
@@ -1381,13 +1313,12 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode)
 
 			bdev->bd_part = disk_get_part(disk, bdev->bd_partno);
 			if (!(disk->flags & GENHD_FL_UP) ||
-			    !bdev->bd_part || !bdev->bd_part->nr_sects) {
+			    !bdev->bd_part || !bdev_nr_sectors(bdev)) {
 				__blkdev_put(whole, mode, 1);
 				bdput(whole);
 				ret = -ENXIO;
 				goto out_clear;
 			}
-			bd_set_nr_sectors(bdev, bdev->bd_part->nr_sects);
 			set_init_blocksize(bdev);
 		}
 
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 00eff2f51807..d4e7fab352ba 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -3151,7 +3151,7 @@ static int f2fs_report_zone_cb(struct blk_zone *zone, unsigned int idx,
 static int init_blkz_info(struct f2fs_sb_info *sbi, int devi)
 {
 	struct block_device *bdev = FDEV(devi).bdev;
-	sector_t nr_sectors = bdev->bd_part->nr_sects;
+	sector_t nr_sectors = bdev_nr_sectors(bdev);
 	struct f2fs_report_zones_args rep_zone_arg;
 	int ret;
 
diff --git a/fs/pstore/blk.c b/fs/pstore/blk.c
index fcd5563dde06..777a26f7bbe2 100644
--- a/fs/pstore/blk.c
+++ b/fs/pstore/blk.c
@@ -245,7 +245,7 @@ static struct block_device *psblk_get_bdev(void *holder,
 			return bdev;
 	}
 
-	nr_sects = part_nr_sects_read(bdev->bd_part);
+	nr_sects = bdev_nr_sectors(bdev);
 	if (!nr_sects) {
 		pr_err("not enough space for '%s'\n", blkdev);
 		blkdev_put(bdev, mode);
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 6ba91ee54cb2..30d4785b7df8 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -52,15 +52,6 @@ struct partition_meta_info {
 
 struct hd_struct {
 	sector_t start_sect;
-	/*
-	 * nr_sects is protected by sequence counter. One might extend a
-	 * partition while IO is happening to it and update of nr_sects
-	 * can be non-atomic on 32bit machines with 64bit sector_t.
-	 */
-	sector_t nr_sects;
-#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
-	seqcount_t nr_sects_seq;
-#endif
 	unsigned long stamp;
 	struct disk_stats __percpu *dkstats;
 	struct percpu_ref ref;
@@ -254,13 +245,6 @@ static inline void disk_put_part(struct hd_struct *part)
 		put_device(part_to_dev(part));
 }
 
-static inline void hd_sects_seq_init(struct hd_struct *p)
-{
-#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
-	seqcount_init(&p->nr_sects_seq);
-#endif
-}
-
 /*
  * Smarter partition iterator without context limits.
  */
@@ -318,13 +302,15 @@ static inline sector_t get_start_sect(struct block_device *bdev)
 {
 	return bdev->bd_part->start_sect;
 }
-static inline sector_t get_capacity(struct gendisk *disk)
+
+static inline sector_t bdev_nr_sectors(struct block_device *bdev)
 {
-	return disk->part0.nr_sects;
+	return i_size_read(bdev->bd_inode) >> 9;
 }
-static inline void set_capacity(struct gendisk *disk, sector_t size)
+
+static inline sector_t get_capacity(struct gendisk *disk)
 {
-	disk->part0.nr_sects = size;
+	return bdev_nr_sectors(disk->part0.bdev);
 }
 
 int bdev_disk_changed(struct block_device *bdev, bool invalidate);
@@ -358,10 +344,9 @@ int __register_blkdev(unsigned int major, const char *name,
 	__register_blkdev(major, name, NULL)
 void unregister_blkdev(unsigned int major, const char *name);
 
-void revalidate_disk_size(struct gendisk *disk, bool verbose);
 bool bdev_check_media_change(struct block_device *bdev);
 int __invalidate_device(struct block_device *bdev, bool kill_dirty);
-void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors);
+void set_capacity(struct gendisk *disk, sector_t size);
 
 /* for drivers/char/raw.c: */
 int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long);
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index f1022945e346..7076d588a50d 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -465,7 +465,7 @@ static void blk_trace_setup_lba(struct blk_trace *bt,
 
 	if (part) {
 		bt->start_lba = part->start_sect;
-		bt->end_lba = part->start_sect + part->nr_sects;
+		bt->end_lba = part->start_sect + bdev_nr_sectors(bdev);
 	} else {
 		bt->start_lba = 0;
 		bt->end_lba = -1ULL;
-- 
cgit v1.2.3


From 15e3d2c5cd53298272e59ad9072d3468f9dd3781 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 24 Nov 2020 09:34:00 +0100
Subject: block: move disk stat accounting to struct block_device

Move the dkstats and stamp field to struct block_device in preparation
of killing struct hd_struct.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-cgroup.c        |  2 +-
 block/blk-core.c          |  4 ++--
 block/blk.h               |  1 -
 block/genhd.c             | 14 ++++----------
 block/partitions/core.c   |  9 +--------
 fs/block_dev.c            | 10 ++++++++++
 include/linux/blk_types.h |  2 ++
 include/linux/genhd.h     |  2 --
 include/linux/part_stat.h | 38 +++++++++++++++++++-------------------
 9 files changed, 39 insertions(+), 43 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index ad02289a4f7f..79aa96240cec 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -830,7 +830,7 @@ static void blkcg_fill_root_iostats(void)
 		for_each_possible_cpu(cpu) {
 			struct disk_stats *cpu_dkstats;
 
-			cpu_dkstats = per_cpu_ptr(part->dkstats, cpu);
+			cpu_dkstats = per_cpu_ptr(part->bdev->bd_stats, cpu);
 			tmp.ios[BLKG_IOSTAT_READ] +=
 				cpu_dkstats->ios[STAT_READ];
 			tmp.ios[BLKG_IOSTAT_WRITE] +=
diff --git a/block/blk-core.c b/block/blk-core.c
index 988f45094a38..d2c9cb24e087 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1264,9 +1264,9 @@ static void update_io_ticks(struct hd_struct *part, unsigned long now, bool end)
 {
 	unsigned long stamp;
 again:
-	stamp = READ_ONCE(part->stamp);
+	stamp = READ_ONCE(part->bdev->bd_stamp);
 	if (unlikely(stamp != now)) {
-		if (likely(cmpxchg(&part->stamp, stamp, now) == stamp))
+		if (likely(cmpxchg(&part->bdev->bd_stamp, stamp, now) == stamp))
 			__part_stat_add(part, io_ticks, end ? now - stamp : 1);
 	}
 	if (part->partno) {
diff --git a/block/blk.h b/block/blk.h
index 09cee7024fb4..3f801f6e86f8 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -381,7 +381,6 @@ static inline void hd_struct_put(struct hd_struct *part)
 
 static inline void hd_free_part(struct hd_struct *part)
 {
-	free_percpu(part->dkstats);
 	kfree(part->info);
 	bdput(part->bdev);
 	percpu_ref_exit(&part->ref);
diff --git a/block/genhd.c b/block/genhd.c
index c65f485b9db5..2cbda8139556 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -112,7 +112,7 @@ static void part_stat_read_all(struct hd_struct *part, struct disk_stats *stat)
 
 	memset(stat, 0, sizeof(struct disk_stats));
 	for_each_possible_cpu(cpu) {
-		struct disk_stats *ptr = per_cpu_ptr(part->dkstats, cpu);
+		struct disk_stats *ptr = per_cpu_ptr(part->bdev->bd_stats, cpu);
 		int group;
 
 		for (group = 0; group < NR_STAT_GROUPS; group++) {
@@ -891,7 +891,7 @@ void del_gendisk(struct gendisk *disk)
 	kobject_put(disk->slave_dir);
 
 	part_stat_set_all(&disk->part0, 0);
-	disk->part0.stamp = 0;
+	disk->part0.bdev->bd_stamp = 0;
 	if (!sysfs_deprecated)
 		sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk)));
 	pm_runtime_set_memalloc_noio(disk_to_dev(disk), false);
@@ -1628,19 +1628,15 @@ struct gendisk *__alloc_disk_node(int minors, int node_id)
 	if (!disk->part0.bdev)
 		goto out_free_disk;
 
-	disk->part0.dkstats = alloc_percpu(struct disk_stats);
-	if (!disk->part0.dkstats)
-		goto out_bdput;
-
 	disk->node_id = node_id;
 	if (disk_expand_part_tbl(disk, 0))
-		goto out_free_bdstats;
+		goto out_bdput;
 
 	ptbl = rcu_dereference_protected(disk->part_tbl, 1);
 	rcu_assign_pointer(ptbl->part[0], &disk->part0);
 
 	if (hd_ref_init(&disk->part0))
-		goto out_free_bdstats;
+		goto out_bdput;
 
 	disk->minors = minors;
 	rand_initialize_disk(disk);
@@ -1649,8 +1645,6 @@ struct gendisk *__alloc_disk_node(int minors, int node_id)
 	device_initialize(disk_to_dev(disk));
 	return disk;
 
-out_free_bdstats:
-	free_percpu(disk->part0.dkstats);
 out_bdput:
 	bdput(disk->part0.bdev);
 out_free_disk:
diff --git a/block/partitions/core.c b/block/partitions/core.c
index bcfa8215bd5e..8924e1ea8b2a 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -409,14 +409,9 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 	if (!p)
 		return ERR_PTR(-EBUSY);
 
-	err = -ENOMEM;
-	p->dkstats = alloc_percpu(struct disk_stats);
-	if (!p->dkstats)
-		goto out_free;
-
 	bdev = bdev_alloc(disk, partno);
 	if (!bdev)
-		goto out_free_stats;
+		goto out_free;
 	p->bdev = bdev;
 
 	pdev = part_to_dev(p);
@@ -490,8 +485,6 @@ out_free_info:
 	kfree(p->info);
 out_bdput:
 	bdput(bdev);
-out_free_stats:
-	free_percpu(p->dkstats);
 out_free:
 	kfree(p);
 	return ERR_PTR(err);
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 31ee5a857f71..0832c7830f3a 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -32,6 +32,7 @@
 #include <linux/cleancache.h>
 #include <linux/task_io_accounting_ops.h>
 #include <linux/falloc.h>
+#include <linux/part_stat.h>
 #include <linux/uaccess.h>
 #include <linux/suspend.h>
 #include "internal.h"
@@ -781,6 +782,10 @@ static struct inode *bdev_alloc_inode(struct super_block *sb)
 
 static void bdev_free_inode(struct inode *inode)
 {
+	struct block_device *bdev = I_BDEV(inode);
+
+	free_percpu(bdev->bd_stats);
+
 	kmem_cache_free(bdev_cachep, BDEV_I(inode));
 }
 
@@ -875,6 +880,11 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno)
 #ifdef CONFIG_SYSFS
 	INIT_LIST_HEAD(&bdev->bd_holder_disks);
 #endif
+	bdev->bd_stats = alloc_percpu(struct disk_stats);
+	if (!bdev->bd_stats) {
+		iput(inode);
+		return NULL;
+	}
 	return bdev;
 }
 
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 2e0a9bd9688d..520011b95276 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -20,6 +20,8 @@ typedef void (bio_end_io_t) (struct bio *);
 struct bio_crypt_ctx;
 
 struct block_device {
+	struct disk_stats __percpu *bd_stats;
+	unsigned long		bd_stamp;
 	dev_t			bd_dev;
 	int			bd_openers;
 	struct inode *		bd_inode;	/* will die */
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 30d4785b7df8..804ac45fbfbc 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -52,8 +52,6 @@ struct partition_meta_info {
 
 struct hd_struct {
 	sector_t start_sect;
-	unsigned long stamp;
-	struct disk_stats __percpu *dkstats;
 	struct percpu_ref ref;
 
 	struct block_device *bdev;
diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h
index 24125778ef3e..87ad60106e1d 100644
--- a/include/linux/part_stat.h
+++ b/include/linux/part_stat.h
@@ -25,17 +25,17 @@ struct disk_stats {
 #define part_stat_unlock()	preempt_enable()
 
 #define part_stat_get_cpu(part, field, cpu)				\
-	(per_cpu_ptr((part)->dkstats, (cpu))->field)
+	(per_cpu_ptr((part)->bdev->bd_stats, (cpu))->field)
 
 #define part_stat_get(part, field)					\
 	part_stat_get_cpu(part, field, smp_processor_id())
 
 #define part_stat_read(part, field)					\
 ({									\
-	typeof((part)->dkstats->field) res = 0;				\
+	typeof((part)->bdev->bd_stats->field) res = 0;			\
 	unsigned int _cpu;						\
 	for_each_possible_cpu(_cpu)					\
-		res += per_cpu_ptr((part)->dkstats, _cpu)->field;	\
+		res += per_cpu_ptr((part)->bdev->bd_stats, _cpu)->field; \
 	res;								\
 })
 
@@ -44,7 +44,7 @@ static inline void part_stat_set_all(struct hd_struct *part, int value)
 	int i;
 
 	for_each_possible_cpu(i)
-		memset(per_cpu_ptr(part->dkstats, i), value,
+		memset(per_cpu_ptr(part->bdev->bd_stats, i), value,
 				sizeof(struct disk_stats));
 }
 
@@ -54,7 +54,7 @@ static inline void part_stat_set_all(struct hd_struct *part, int value)
 	 part_stat_read(part, field[STAT_DISCARD]))
 
 #define __part_stat_add(part, field, addnd)				\
-	__this_cpu_add((part)->dkstats->field, addnd)
+	__this_cpu_add((part)->bdev->bd_stats->field, addnd)
 
 #define part_stat_add(part, field, addnd)	do {			\
 	__part_stat_add((part), field, addnd);				\
@@ -63,20 +63,20 @@ static inline void part_stat_set_all(struct hd_struct *part, int value)
 				field, addnd);				\
 } while (0)
 
-#define part_stat_dec(gendiskp, field)					\
-	part_stat_add(gendiskp, field, -1)
-#define part_stat_inc(gendiskp, field)					\
-	part_stat_add(gendiskp, field, 1)
-#define part_stat_sub(gendiskp, field, subnd)				\
-	part_stat_add(gendiskp, field, -subnd)
+#define part_stat_dec(part, field)					\
+	part_stat_add(part, field, -1)
+#define part_stat_inc(part, field)					\
+	part_stat_add(part, field, 1)
+#define part_stat_sub(part, field, subnd)				\
+	part_stat_add(part, field, -subnd)
 
-#define part_stat_local_dec(gendiskp, field)				\
-	local_dec(&(part_stat_get(gendiskp, field)))
-#define part_stat_local_inc(gendiskp, field)				\
-	local_inc(&(part_stat_get(gendiskp, field)))
-#define part_stat_local_read(gendiskp, field)				\
-	local_read(&(part_stat_get(gendiskp, field)))
-#define part_stat_local_read_cpu(gendiskp, field, cpu)			\
-	local_read(&(part_stat_get_cpu(gendiskp, field, cpu)))
+#define part_stat_local_dec(part, field)				\
+	local_dec(&(part_stat_get(part, field)))
+#define part_stat_local_inc(part, field)				\
+	local_inc(&(part_stat_get(part, field)))
+#define part_stat_local_read(part, field)				\
+	local_read(&(part_stat_get(part, field)))
+#define part_stat_local_read_cpu(part, field, cpu)			\
+	local_read(&(part_stat_get_cpu(part, field, cpu)))
 
 #endif /* _LINUX_PART_STAT_H */
-- 
cgit v1.2.3


From 29ff57c61094e7bbd921ab10b5a99dce9a0132e0 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 24 Nov 2020 09:34:24 +0100
Subject: block: move the start_sect field to struct block_device

Move the start_sect field to struct block_device in preparation
of killing struct hd_struct.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c          |  5 +++--
 block/blk-lib.c           |  2 +-
 block/genhd.c             |  4 ++--
 block/partitions/core.c   | 17 +++++++++--------
 include/linux/blk_types.h |  1 +
 include/linux/blkdev.h    |  4 ++--
 include/linux/genhd.h     |  3 +--
 kernel/trace/blktrace.c   | 11 +++--------
 8 files changed, 22 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-core.c b/block/blk-core.c
index d2c9cb24e087..9a3793d5ce38 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -757,9 +757,10 @@ static inline int blk_partition_remap(struct bio *bio)
 	if (bio_sectors(bio)) {
 		if (bio_check_eod(bio, bdev_nr_sectors(p->bdev)))
 			goto out;
-		bio->bi_iter.bi_sector += p->start_sect;
+		bio->bi_iter.bi_sector += p->bdev->bd_start_sect;
 		trace_block_bio_remap(bio->bi_disk->queue, bio, part_devt(p),
-				      bio->bi_iter.bi_sector - p->start_sect);
+				      bio->bi_iter.bi_sector -
+				      p->bdev->bd_start_sect);
 	}
 	bio->bi_partno = 0;
 	ret = 0;
diff --git a/block/blk-lib.c b/block/blk-lib.c
index e90614fd8d6a..752f9c722062 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -65,7 +65,7 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 
 	/* In case the discard request is in a partition */
 	if (bdev_is_partition(bdev))
-		part_offset = bdev->bd_part->start_sect;
+		part_offset = bdev->bd_start_sect;
 
 	while (nr_sects) {
 		sector_t granularity_aligned_lba, req_sects;
diff --git a/block/genhd.c b/block/genhd.c
index 2cbda8139556..5efb2df1f079 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -305,8 +305,8 @@ EXPORT_SYMBOL_GPL(disk_part_iter_exit);
 
 static inline int sector_in_part(struct hd_struct *part, sector_t sector)
 {
-	return part->start_sect <= sector &&
-		sector < part->start_sect + bdev_nr_sectors(part->bdev);
+	return part->bdev->bd_start_sect <= sector &&
+		sector < part->bdev->bd_start_sect + bdev_nr_sectors(part->bdev);
 }
 
 /**
diff --git a/block/partitions/core.c b/block/partitions/core.c
index 8924e1ea8b2a..460a745812c6 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -192,7 +192,7 @@ static ssize_t part_start_show(struct device *dev,
 {
 	struct hd_struct *p = dev_to_part(dev);
 
-	return sprintf(buf, "%llu\n",(unsigned long long)p->start_sect);
+	return sprintf(buf, "%llu\n", p->bdev->bd_start_sect);
 }
 
 static ssize_t part_ro_show(struct device *dev,
@@ -209,7 +209,7 @@ static ssize_t part_alignment_offset_show(struct device *dev,
 
 	return sprintf(buf, "%u\n",
 		queue_limit_alignment_offset(&part_to_disk(p)->queue->limits,
-				p->start_sect));
+				p->bdev->bd_start_sect));
 }
 
 static ssize_t part_discard_alignment_show(struct device *dev,
@@ -219,7 +219,7 @@ static ssize_t part_discard_alignment_show(struct device *dev,
 
 	return sprintf(buf, "%u\n",
 		queue_limit_discard_alignment(&part_to_disk(p)->queue->limits,
-				p->start_sect));
+				p->bdev->bd_start_sect));
 }
 
 static DEVICE_ATTR(partition, 0444, part_partition_show, NULL);
@@ -301,7 +301,7 @@ static void hd_struct_free_work(struct work_struct *work)
 	 */
 	put_device(disk_to_dev(disk));
 
-	part->start_sect = 0;
+	part->bdev->bd_start_sect = 0;
 	bdev_set_nr_sectors(part->bdev, 0);
 	part_stat_set_all(part, 0);
 	put_device(part_to_dev(part));
@@ -416,7 +416,7 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 
 	pdev = part_to_dev(p);
 
-	p->start_sect = start;
+	bdev->bd_start_sect = start;
 	bdev_set_nr_sectors(bdev, len);
 	p->partno = partno;
 	p->policy = get_disk_ro(disk);
@@ -508,8 +508,9 @@ static bool partition_overlaps(struct gendisk *disk, sector_t start,
 	disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY);
 	while ((part = disk_part_iter_next(&piter))) {
 		if (part->partno == skip_partno ||
-		    start >= part->start_sect + bdev_nr_sectors(part->bdev) ||
-		    start + length <= part->start_sect)
+		    start >= part->bdev->bd_start_sect +
+			bdev_nr_sectors(part->bdev) ||
+		    start + length <= part->bdev->bd_start_sect)
 			continue;
 		overlap = true;
 		break;
@@ -592,7 +593,7 @@ int bdev_resize_partition(struct block_device *bdev, int partno,
 	mutex_lock_nested(&bdev->bd_mutex, 1);
 
 	ret = -EINVAL;
-	if (start != part->start_sect)
+	if (start != part->bdev->bd_start_sect)
 		goto out_unlock;
 
 	ret = -EBUSY;
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 520011b95276..a690008f60cd 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -20,6 +20,7 @@ typedef void (bio_end_io_t) (struct bio *);
 struct bio_crypt_ctx;
 
 struct block_device {
+	sector_t		bd_start_sect;
 	struct disk_stats __percpu *bd_stats;
 	unsigned long		bd_stamp;
 	dev_t			bd_dev;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 43a25d855e04..619adea57098 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1488,7 +1488,7 @@ static inline int bdev_alignment_offset(struct block_device *bdev)
 		return -1;
 	if (bdev_is_partition(bdev))
 		return queue_limit_alignment_offset(&q->limits,
-				bdev->bd_part->start_sect);
+				bdev->bd_start_sect);
 	return q->limits.alignment_offset;
 }
 
@@ -1529,7 +1529,7 @@ static inline int bdev_discard_alignment(struct block_device *bdev)
 
 	if (bdev_is_partition(bdev))
 		return queue_limit_discard_alignment(&q->limits,
-				bdev->bd_part->start_sect);
+				bdev->bd_start_sect);
 	return q->limits.discard_alignment;
 }
 
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 804ac45fbfbc..50d27f5d38e2 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -51,7 +51,6 @@ struct partition_meta_info {
 };
 
 struct hd_struct {
-	sector_t start_sect;
 	struct percpu_ref ref;
 
 	struct block_device *bdev;
@@ -298,7 +297,7 @@ extern void rand_initialize_disk(struct gendisk *disk);
 
 static inline sector_t get_start_sect(struct block_device *bdev)
 {
-	return bdev->bd_part->start_sect;
+	return bdev->bd_start_sect;
 }
 
 static inline sector_t bdev_nr_sectors(struct block_device *bdev)
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 7076d588a50d..8a723a91ec5a 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -458,14 +458,9 @@ static struct rchan_callbacks blk_relay_callbacks = {
 static void blk_trace_setup_lba(struct blk_trace *bt,
 				struct block_device *bdev)
 {
-	struct hd_struct *part = NULL;
-
-	if (bdev)
-		part = bdev->bd_part;
-
-	if (part) {
-		bt->start_lba = part->start_sect;
-		bt->end_lba = part->start_sect + bdev_nr_sectors(bdev);
+	if (bdev) {
+		bt->start_lba = bdev->bd_start_sect;
+		bt->end_lba = bdev->bd_start_sect + bdev_nr_sectors(bdev);
 	} else {
 		bt->start_lba = 0;
 		bt->end_lba = -1ULL;
-- 
cgit v1.2.3


From 231926dbf0f084211e4ec4f4c006f0bf1f47809a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 24 Nov 2020 12:01:45 +0100
Subject: block: move the partition_meta_info to struct block_device

Move the partition_meta_info to struct block_device in preparation for
killing struct hd_struct.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk.h               |  1 -
 block/genhd.c             |  3 ++-
 block/partitions/core.c   | 18 +++++++-----------
 fs/block_dev.c            |  1 +
 include/linux/blk_types.h |  2 ++
 include/linux/genhd.h     |  1 -
 init/do_mounts.c          |  7 ++++---
 7 files changed, 16 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk.h b/block/blk.h
index 3f801f6e86f8..0bd4b58bcbaf 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -381,7 +381,6 @@ static inline void hd_struct_put(struct hd_struct *part)
 
 static inline void hd_free_part(struct hd_struct *part)
 {
-	kfree(part->info);
 	bdput(part->bdev);
 	percpu_ref_exit(&part->ref);
 }
diff --git a/block/genhd.c b/block/genhd.c
index 5efb2df1f079..4273e89f07e8 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1010,7 +1010,8 @@ void __init printk_all_partitions(void)
 			       bdevt_str(part_devt(part), devt_buf),
 			       bdev_nr_sectors(part->bdev) >> 1,
 			       disk_name(disk, part->partno, name_buf),
-			       part->info ? part->info->uuid : "");
+			       part->bdev->bd_meta_info ?
+					part->bdev->bd_meta_info->uuid : "");
 			if (is_part0) {
 				if (dev->parent && dev->parent->driver)
 					printk(" driver: %s\n",
diff --git a/block/partitions/core.c b/block/partitions/core.c
index 460a745812c6..07df9ff55462 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -275,8 +275,9 @@ static int part_uevent(struct device *dev, struct kobj_uevent_env *env)
 	struct hd_struct *part = dev_to_part(dev);
 
 	add_uevent_var(env, "PARTN=%u", part->partno);
-	if (part->info && part->info->volname[0])
-		add_uevent_var(env, "PARTNAME=%s", part->info->volname);
+	if (part->bdev->bd_meta_info && part->bdev->bd_meta_info->volname[0])
+		add_uevent_var(env, "PARTNAME=%s",
+			       part->bdev->bd_meta_info->volname);
 	return 0;
 }
 
@@ -422,13 +423,10 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 	p->policy = get_disk_ro(disk);
 
 	if (info) {
-		struct partition_meta_info *pinfo;
-
-		pinfo = kzalloc_node(sizeof(*pinfo), GFP_KERNEL, disk->node_id);
-		if (!pinfo)
+		err = -ENOMEM;
+		bdev->bd_meta_info = kmemdup(info, sizeof(*info), GFP_KERNEL);
+		if (!bdev->bd_meta_info)
 			goto out_bdput;
-		memcpy(pinfo, info, sizeof(*info));
-		p->info = pinfo;
 	}
 
 	dname = dev_name(ddev);
@@ -444,7 +442,7 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 
 	err = blk_alloc_devt(p, &devt);
 	if (err)
-		goto out_free_info;
+		goto out_bdput;
 	pdev->devt = devt;
 
 	/* delay uevent until 'holders' subdir is created */
@@ -481,8 +479,6 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 		kobject_uevent(&pdev->kobj, KOBJ_ADD);
 	return p;
 
-out_free_info:
-	kfree(p->info);
 out_bdput:
 	bdput(bdev);
 out_free:
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 0832c7830f3a..0770f654b09c 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -785,6 +785,7 @@ static void bdev_free_inode(struct inode *inode)
 	struct block_device *bdev = I_BDEV(inode);
 
 	free_percpu(bdev->bd_stats);
+	kfree(bdev->bd_meta_info);
 
 	kmem_cache_free(bdev_cachep, BDEV_I(inode));
 }
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index a690008f60cd..2f8ede04e5a9 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -49,6 +49,8 @@ struct block_device {
 	/* Mutex for freeze */
 	struct mutex		bd_fsfreeze_mutex;
 	struct super_block	*bd_fsfreeze_sb;
+
+	struct partition_meta_info *bd_meta_info;
 } __randomize_layout;
 
 #define bdev_whole(_bdev) \
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 50d27f5d38e2..30d7076155b4 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -57,7 +57,6 @@ struct hd_struct {
 	struct device __dev;
 	struct kobject *holder_dir;
 	int policy, partno;
-	struct partition_meta_info *info;
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 	int make_it_fail;
 #endif
diff --git a/init/do_mounts.c b/init/do_mounts.c
index 5879edf083b3..368ccb718501 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -79,8 +79,8 @@ static int match_dev_by_uuid(struct device *dev, const void *data)
 	const struct uuidcmp *cmp = data;
 	struct hd_struct *part = dev_to_part(dev);
 
-	if (!part->info ||
-	    strncasecmp(cmp->uuid, part->info->uuid, cmp->len))
+	if (!part->bdev->bd_meta_info ||
+	    strncasecmp(cmp->uuid, part->bdev->bd_meta_info->uuid, cmp->len))
 		return 0;
 	return 1;
 }
@@ -169,7 +169,8 @@ static int match_dev_by_label(struct device *dev, const void *data)
 	const char *label = data;
 	struct hd_struct *part = dev_to_part(dev);
 
-	if (!part->info || strcmp(label, part->info->volname))
+	if (!part->bdev->bd_meta_info ||
+	    strcmp(label, part->bdev->bd_meta_info->volname))
 		return 0;
 	return 1;
 }
-- 
cgit v1.2.3


From 1bdd5ae0251d678488dffcf455d4633c2beef1bc Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 23 Nov 2020 19:00:13 +0100
Subject: block: move holder_dir to struct block_device

Move the holder_dir field to struct block_device in preparation for
kill struct hd_struct.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/genhd.c             |  5 +++--
 block/partitions/core.c   |  8 ++++----
 fs/block_dev.c            | 11 +++++------
 include/linux/blk_types.h |  1 +
 include/linux/genhd.h     |  1 -
 5 files changed, 13 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/block/genhd.c b/block/genhd.c
index 4273e89f07e8..0bd7026cee62 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -681,7 +681,8 @@ static void register_disk(struct device *parent, struct gendisk *disk,
 	 */
 	pm_runtime_set_memalloc_noio(ddev, true);
 
-	disk->part0.holder_dir = kobject_create_and_add("holders", &ddev->kobj);
+	disk->part0.bdev->bd_holder_dir =
+			kobject_create_and_add("holders", &ddev->kobj);
 	disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj);
 
 	if (disk->flags & GENHD_FL_HIDDEN) {
@@ -887,7 +888,7 @@ void del_gendisk(struct gendisk *disk)
 
 	blk_unregister_queue(disk);
 
-	kobject_put(disk->part0.holder_dir);
+	kobject_put(disk->part0.bdev->bd_holder_dir);
 	kobject_put(disk->slave_dir);
 
 	part_stat_set_all(&disk->part0, 0);
diff --git a/block/partitions/core.c b/block/partitions/core.c
index 07df9ff55462..c068471fa654 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -344,7 +344,7 @@ void delete_partition(struct hd_struct *part)
 	 */
 	get_device(disk_to_dev(disk));
 	rcu_assign_pointer(ptbl->part[part->partno], NULL);
-	kobject_put(part->holder_dir);
+	kobject_put(part->bdev->bd_holder_dir);
 	device_del(part_to_dev(part));
 
 	/*
@@ -452,8 +452,8 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 		goto out_put;
 
 	err = -ENOMEM;
-	p->holder_dir = kobject_create_and_add("holders", &pdev->kobj);
-	if (!p->holder_dir)
+	bdev->bd_holder_dir = kobject_create_and_add("holders", &pdev->kobj);
+	if (!bdev->bd_holder_dir)
 		goto out_del;
 
 	dev_set_uevent_suppress(pdev, 0);
@@ -487,7 +487,7 @@ out_free:
 out_remove_file:
 	device_remove_file(pdev, &dev_attr_whole_disk);
 out_del:
-	kobject_put(p->holder_dir);
+	kobject_put(bdev->bd_holder_dir);
 	device_del(pdev);
 out_put:
 	put_device(pdev);
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 0770f654b09c..381c22426f43 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1142,7 +1142,7 @@ int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk)
 	WARN_ON_ONCE(!bdev->bd_holder);
 
 	/* FIXME: remove the following once add_disk() handles errors */
-	if (WARN_ON(!disk->slave_dir || !bdev->bd_part->holder_dir))
+	if (WARN_ON(!disk->slave_dir || !bdev->bd_holder_dir))
 		goto out_unlock;
 
 	holder = bd_find_holder_disk(bdev, disk);
@@ -1165,14 +1165,14 @@ int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk)
 	if (ret)
 		goto out_free;
 
-	ret = add_symlink(bdev->bd_part->holder_dir, &disk_to_dev(disk)->kobj);
+	ret = add_symlink(bdev->bd_holder_dir, &disk_to_dev(disk)->kobj);
 	if (ret)
 		goto out_del;
 	/*
 	 * bdev could be deleted beneath us which would implicitly destroy
 	 * the holder directory.  Hold on to it.
 	 */
-	kobject_get(bdev->bd_part->holder_dir);
+	kobject_get(bdev->bd_holder_dir);
 
 	list_add(&holder->list, &bdev->bd_holder_disks);
 	goto out_unlock;
@@ -1207,9 +1207,8 @@ void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk)
 
 	if (!WARN_ON_ONCE(holder == NULL) && !--holder->refcnt) {
 		del_symlink(disk->slave_dir, bdev_kobj(bdev));
-		del_symlink(bdev->bd_part->holder_dir,
-			    &disk_to_dev(disk)->kobj);
-		kobject_put(bdev->bd_part->holder_dir);
+		del_symlink(bdev->bd_holder_dir, &disk_to_dev(disk)->kobj);
+		kobject_put(bdev->bd_holder_dir);
 		list_del_init(&holder->list);
 		kfree(holder);
 	}
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 2f8ede04e5a9..c0591e52d7d7 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -35,6 +35,7 @@ struct block_device {
 #ifdef CONFIG_SYSFS
 	struct list_head	bd_holder_disks;
 #endif
+	struct kobject		*bd_holder_dir;
 	u8			bd_partno;
 	struct hd_struct *	bd_part;
 	/* number of times partitions within this device have been opened. */
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 30d7076155b4..b4a5c05593b9 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -55,7 +55,6 @@ struct hd_struct {
 
 	struct block_device *bdev;
 	struct device __dev;
-	struct kobject *holder_dir;
 	int policy, partno;
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 	int make_it_fail;
-- 
cgit v1.2.3


From b309e9936347232c724eaa13f70533128b4864e9 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 23 Nov 2020 16:28:47 +0100
Subject: block: move make_it_fail to struct block_device

Move the make_it_fail flag to struct block_device an turn it into a bool
in preparation of killing struct hd_struct.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c          | 3 ++-
 block/genhd.c             | 4 ++--
 include/linux/blk_types.h | 3 +++
 include/linux/genhd.h     | 3 ---
 4 files changed, 7 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-core.c b/block/blk-core.c
index 9a3793d5ce38..9121390be97a 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -668,7 +668,8 @@ __setup("fail_make_request=", setup_fail_make_request);
 
 static bool should_fail_request(struct hd_struct *part, unsigned int bytes)
 {
-	return part->make_it_fail && should_fail(&fail_make_request, bytes);
+	return part->bdev->bd_make_it_fail &&
+		should_fail(&fail_make_request, bytes);
 }
 
 static int __init fail_make_request_debugfs(void)
diff --git a/block/genhd.c b/block/genhd.c
index 0bd7026cee62..f9c957739d4b 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1292,7 +1292,7 @@ ssize_t part_fail_show(struct device *dev,
 {
 	struct hd_struct *p = dev_to_part(dev);
 
-	return sprintf(buf, "%d\n", p->make_it_fail);
+	return sprintf(buf, "%d\n", p->bdev->bd_make_it_fail);
 }
 
 ssize_t part_fail_store(struct device *dev,
@@ -1303,7 +1303,7 @@ ssize_t part_fail_store(struct device *dev,
 	int i;
 
 	if (count > 0 && sscanf(buf, "%d", &i) > 0)
-		p->make_it_fail = (i == 0) ? 0 : 1;
+		p->bdev->bd_make_it_fail = i;
 
 	return count;
 }
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index c0591e52d7d7..b237f1e40814 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -52,6 +52,9 @@ struct block_device {
 	struct super_block	*bd_fsfreeze_sb;
 
 	struct partition_meta_info *bd_meta_info;
+#ifdef CONFIG_FAIL_MAKE_REQUEST
+	bool			bd_make_it_fail;
+#endif
 } __randomize_layout;
 
 #define bdev_whole(_bdev) \
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index b4a5c05593b9..349cf6403ccd 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -56,9 +56,6 @@ struct hd_struct {
 	struct block_device *bdev;
 	struct device __dev;
 	int policy, partno;
-#ifdef CONFIG_FAIL_MAKE_REQUEST
-	int make_it_fail;
-#endif
 	struct rcu_work rcu_work;
 };
 
-- 
cgit v1.2.3


From 83950d359010a493462d58c712b1124c877d1b3b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 23 Nov 2020 16:36:02 +0100
Subject: block: move the policy field to struct block_device

Move the policy field to struct block_device and rename it to the
more descriptive bd_read_only.  Also turn the field into a bool as it
is used as such.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c          | 2 +-
 block/genhd.c             | 8 ++++----
 block/ioctl.c             | 2 +-
 block/partitions/core.c   | 4 ++--
 include/linux/blk_types.h | 1 +
 include/linux/genhd.h     | 4 ++--
 6 files changed, 11 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-core.c b/block/blk-core.c
index 9121390be97a..d64ffcb6f9ae 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -696,7 +696,7 @@ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part)
 {
 	const int op = bio_op(bio);
 
-	if (part->policy && op_is_write(op)) {
+	if (part->bdev->bd_read_only && op_is_write(op)) {
 		char b[BDEVNAME_SIZE];
 
 		if (op_is_flush(bio->bi_opf) && !bio_sectors(bio))
diff --git a/block/genhd.c b/block/genhd.c
index f9c957739d4b..2db1204920a9 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1687,14 +1687,14 @@ void set_disk_ro(struct gendisk *disk, int flag)
 	struct disk_part_iter piter;
 	struct hd_struct *part;
 
-	if (disk->part0.policy != flag) {
+	if (disk->part0.bdev->bd_read_only != flag) {
 		set_disk_ro_uevent(disk, flag);
-		disk->part0.policy = flag;
+		disk->part0.bdev->bd_read_only = flag;
 	}
 
 	disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY);
 	while ((part = disk_part_iter_next(&piter)))
-		part->policy = flag;
+		part->bdev->bd_read_only = flag;
 	disk_part_iter_exit(&piter);
 }
 
@@ -1704,7 +1704,7 @@ int bdev_read_only(struct block_device *bdev)
 {
 	if (!bdev)
 		return 0;
-	return bdev->bd_part->policy;
+	return bdev->bd_read_only;
 }
 
 EXPORT_SYMBOL(bdev_read_only);
diff --git a/block/ioctl.c b/block/ioctl.c
index a6d8171221c7..d61d652078f4 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -345,7 +345,7 @@ static int blkdev_roset(struct block_device *bdev, fmode_t mode,
 		if (ret)
 			return ret;
 	}
-	bdev->bd_part->policy = n;
+	bdev->bd_read_only = n;
 	return 0;
 }
 
diff --git a/block/partitions/core.c b/block/partitions/core.c
index c068471fa654..060c1be13cd8 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -199,7 +199,7 @@ static ssize_t part_ro_show(struct device *dev,
 			    struct device_attribute *attr, char *buf)
 {
 	struct hd_struct *p = dev_to_part(dev);
-	return sprintf(buf, "%d\n", p->policy ? 1 : 0);
+	return sprintf(buf, "%d\n", p->bdev->bd_read_only);
 }
 
 static ssize_t part_alignment_offset_show(struct device *dev,
@@ -420,7 +420,7 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 	bdev->bd_start_sect = start;
 	bdev_set_nr_sectors(bdev, len);
 	p->partno = partno;
-	p->policy = get_disk_ro(disk);
+	bdev->bd_read_only = get_disk_ro(disk);
 
 	if (info) {
 		err = -ENOMEM;
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index b237f1e40814..758cf71c9aa2 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -23,6 +23,7 @@ struct block_device {
 	sector_t		bd_start_sect;
 	struct disk_stats __percpu *bd_stats;
 	unsigned long		bd_stamp;
+	bool			bd_read_only;	/* read-only policy */
 	dev_t			bd_dev;
 	int			bd_openers;
 	struct inode *		bd_inode;	/* will die */
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 349cf6403ccd..dcbf9ef7610e 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -55,7 +55,7 @@ struct hd_struct {
 
 	struct block_device *bdev;
 	struct device __dev;
-	int policy, partno;
+	int partno;
 	struct rcu_work rcu_work;
 };
 
@@ -278,7 +278,7 @@ extern void set_disk_ro(struct gendisk *disk, int flag);
 
 static inline int get_disk_ro(struct gendisk *disk)
 {
-	return disk->part0.policy;
+	return disk->part0.bdev->bd_read_only;
 }
 
 extern void disk_block_events(struct gendisk *disk);
-- 
cgit v1.2.3


From cb8432d650fe3be58bb962bc8e602dc405510327 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 26 Nov 2020 18:47:17 +0100
Subject: block: allocate struct hd_struct as part of struct bdev_inode

Allocate hd_struct together with struct block_device to pre-load
the lifetime rule changes in preparation of merging the two structures.

Note that part0 was previously embedded into struct gendisk, but is
a separate allocation now, and already points to the block_device instead
of the hd_struct.  The lifetime of struct gendisk is still controlled by
the struct device embedded in the part0 hd_struct.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c                   | 16 ++++-----
 block/blk-flush.c                  |  2 +-
 block/blk-merge.c                  |  2 --
 block/blk.h                        | 21 ------------
 block/genhd.c                      | 50 +++++++++++-----------------
 block/partitions/core.c            | 67 ++++----------------------------------
 drivers/block/drbd/drbd_receiver.c |  2 +-
 drivers/block/drbd/drbd_worker.c   |  3 +-
 drivers/block/zram/zram_drv.c      |  2 +-
 drivers/md/dm.c                    |  4 +--
 drivers/md/md.c                    |  2 +-
 fs/block_dev.c                     | 39 +++++++---------------
 include/linux/blk_types.h          |  2 +-
 include/linux/genhd.h              | 14 ++++----
 include/linux/part_stat.h          |  4 +--
 15 files changed, 61 insertions(+), 169 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-core.c b/block/blk-core.c
index d64ffcb6f9ae..9ea70275fc1c 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -714,7 +714,8 @@ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part)
 
 static noinline int should_fail_bio(struct bio *bio)
 {
-	if (should_fail_request(&bio->bi_disk->part0, bio->bi_iter.bi_size))
+	if (should_fail_request(bio->bi_disk->part0->bd_part,
+			bio->bi_iter.bi_size))
 		return -EIO;
 	return 0;
 }
@@ -831,7 +832,7 @@ static noinline_for_stack bool submit_bio_checks(struct bio *bio)
 		if (unlikely(blk_partition_remap(bio)))
 			goto end_io;
 	} else {
-		if (unlikely(bio_check_ro(bio, &bio->bi_disk->part0)))
+		if (unlikely(bio_check_ro(bio, bio->bi_disk->part0->bd_part)))
 			goto end_io;
 		if (unlikely(bio_check_eod(bio, get_capacity(bio->bi_disk))))
 			goto end_io;
@@ -1203,7 +1204,7 @@ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *
 		return ret;
 
 	if (rq->rq_disk &&
-	    should_fail_request(&rq->rq_disk->part0, blk_rq_bytes(rq)))
+	    should_fail_request(rq->rq_disk->part0->bd_part, blk_rq_bytes(rq)))
 		return BLK_STS_IOERR;
 
 	if (blk_crypto_insert_cloned_request(rq))
@@ -1272,7 +1273,7 @@ again:
 			__part_stat_add(part, io_ticks, end ? now - stamp : 1);
 	}
 	if (part->partno) {
-		part = &part_to_disk(part)->part0;
+		part = part_to_disk(part)->part0->bd_part;
 		goto again;
 	}
 }
@@ -1309,8 +1310,6 @@ void blk_account_io_done(struct request *req, u64 now)
 		part_stat_inc(part, ios[sgrp]);
 		part_stat_add(part, nsecs[sgrp], now - req->start_time_ns);
 		part_stat_unlock();
-
-		hd_struct_put(part);
 	}
 }
 
@@ -1354,7 +1353,7 @@ EXPORT_SYMBOL_GPL(part_start_io_acct);
 unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
 				 unsigned int op)
 {
-	return __part_start_io_acct(&disk->part0, sectors, op);
+	return __part_start_io_acct(disk->part0->bd_part, sectors, op);
 }
 EXPORT_SYMBOL(disk_start_io_acct);
 
@@ -1376,14 +1375,13 @@ void part_end_io_acct(struct hd_struct *part, struct bio *bio,
 		      unsigned long start_time)
 {
 	__part_end_io_acct(part, bio_op(bio), start_time);
-	hd_struct_put(part);
 }
 EXPORT_SYMBOL_GPL(part_end_io_acct);
 
 void disk_end_io_acct(struct gendisk *disk, unsigned int op,
 		      unsigned long start_time)
 {
-	__part_end_io_acct(&disk->part0, op, start_time);
+	__part_end_io_acct(disk->part0->bd_part, op, start_time);
 }
 EXPORT_SYMBOL(disk_end_io_acct);
 
diff --git a/block/blk-flush.c b/block/blk-flush.c
index e32958f0b687..fcd0a60574df 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -139,7 +139,7 @@ static void blk_flush_queue_rq(struct request *rq, bool add_front)
 
 static void blk_account_io_flush(struct request *rq)
 {
-	struct hd_struct *part = &rq->rq_disk->part0;
+	struct hd_struct *part = rq->rq_disk->part0->bd_part;
 
 	part_stat_lock();
 	part_stat_inc(part, ios[STAT_FLUSH]);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index bcf5e4580603..cb351ab9b77d 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -683,8 +683,6 @@ static void blk_account_io_merge_request(struct request *req)
 		part_stat_lock();
 		part_stat_inc(req->part, merges[op_stat_group(req_op(req))]);
 		part_stat_unlock();
-
-		hd_struct_put(req->part);
 	}
 }
 
diff --git a/block/blk.h b/block/blk.h
index 0bd4b58bcbaf..32ac41f7557f 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -363,27 +363,6 @@ int bdev_del_partition(struct block_device *bdev, int partno);
 int bdev_resize_partition(struct block_device *bdev, int partno,
 		sector_t start, sector_t length);
 int disk_expand_part_tbl(struct gendisk *disk, int target);
-int hd_ref_init(struct hd_struct *part);
-
-/* no need to get/put refcount of part0 */
-static inline int hd_struct_try_get(struct hd_struct *part)
-{
-	if (part->partno)
-		return percpu_ref_tryget_live(&part->ref);
-	return 1;
-}
-
-static inline void hd_struct_put(struct hd_struct *part)
-{
-	if (part->partno)
-		percpu_ref_put(&part->ref);
-}
-
-static inline void hd_free_part(struct hd_struct *part)
-{
-	bdput(part->bdev);
-	percpu_ref_exit(&part->ref);
-}
 
 int bio_add_hw_page(struct request_queue *q, struct bio *bio,
 		struct page *page, unsigned int len, unsigned int offset,
diff --git a/block/genhd.c b/block/genhd.c
index 2db1204920a9..c35b03dac5e5 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -42,7 +42,7 @@ static void disk_release_events(struct gendisk *disk);
 
 void set_capacity(struct gendisk *disk, sector_t sectors)
 {
-	struct block_device *bdev = disk->part0.bdev;
+	struct block_device *bdev = disk->part0;
 
 	spin_lock(&bdev->bd_size_lock);
 	i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT);
@@ -318,9 +318,7 @@ static inline int sector_in_part(struct hd_struct *part, sector_t sector)
  * primarily used for stats accounting.
  *
  * CONTEXT:
- * RCU read locked.  The returned partition pointer is always valid
- * because its refcount is grabbed except for part0, which lifetime
- * is same with the disk.
+ * RCU read locked.
  *
  * RETURNS:
  * Found partition on success, part0 is returned if no partition matches
@@ -336,26 +334,19 @@ struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector)
 	ptbl = rcu_dereference(disk->part_tbl);
 
 	part = rcu_dereference(ptbl->last_lookup);
-	if (part && sector_in_part(part, sector) && hd_struct_try_get(part))
+	if (part && sector_in_part(part, sector))
 		goto out_unlock;
 
 	for (i = 1; i < ptbl->len; i++) {
 		part = rcu_dereference(ptbl->part[i]);
 
 		if (part && sector_in_part(part, sector)) {
-			/*
-			 * only live partition can be cached for lookup,
-			 * so use-after-free on cached & deleting partition
-			 * can be avoided
-			 */
-			if (!hd_struct_try_get(part))
-				break;
 			rcu_assign_pointer(ptbl->last_lookup, part);
 			goto out_unlock;
 		}
 	}
 
-	part = &disk->part0;
+	part = disk->part0->bd_part;
 out_unlock:
 	rcu_read_unlock();
 	return part;
@@ -681,8 +672,8 @@ static void register_disk(struct device *parent, struct gendisk *disk,
 	 */
 	pm_runtime_set_memalloc_noio(ddev, true);
 
-	disk->part0.bdev->bd_holder_dir =
-			kobject_create_and_add("holders", &ddev->kobj);
+	disk->part0->bd_holder_dir =
+		kobject_create_and_add("holders", &ddev->kobj);
 	disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj);
 
 	if (disk->flags & GENHD_FL_HIDDEN) {
@@ -748,7 +739,7 @@ static void __device_add_disk(struct device *parent, struct gendisk *disk,
 
 	disk->flags |= GENHD_FL_UP;
 
-	retval = blk_alloc_devt(&disk->part0, &devt);
+	retval = blk_alloc_devt(disk->part0->bd_part, &devt);
 	if (retval) {
 		WARN_ON(1);
 		return;
@@ -775,7 +766,7 @@ static void __device_add_disk(struct device *parent, struct gendisk *disk,
 		ret = bdi_register(bdi, "%u:%u", MAJOR(devt), MINOR(devt));
 		WARN_ON(ret);
 		bdi_set_owner(bdi, dev);
-		bdev_add(disk->part0.bdev, devt);
+		bdev_add(disk->part0, devt);
 	}
 	register_disk(parent, disk, groups);
 	if (register_queue)
@@ -888,11 +879,11 @@ void del_gendisk(struct gendisk *disk)
 
 	blk_unregister_queue(disk);
 
-	kobject_put(disk->part0.bdev->bd_holder_dir);
+	kobject_put(disk->part0->bd_holder_dir);
 	kobject_put(disk->slave_dir);
 
-	part_stat_set_all(&disk->part0, 0);
-	disk->part0.bdev->bd_stamp = 0;
+	part_stat_set_all(disk->part0->bd_part, 0);
+	disk->part0->bd_stamp = 0;
 	if (!sysfs_deprecated)
 		sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk)));
 	pm_runtime_set_memalloc_noio(disk_to_dev(disk), false);
@@ -1005,7 +996,7 @@ void __init printk_all_partitions(void)
 		 */
 		disk_part_iter_init(&piter, disk, DISK_PITER_INCL_PART0);
 		while ((part = disk_part_iter_next(&piter))) {
-			bool is_part0 = part == &disk->part0;
+			bool is_part0 = part == disk->part0->bd_part;
 
 			printk("%s%s %10llu %s %s", is_part0 ? "" : "  ",
 			       bdevt_str(part_devt(part), devt_buf),
@@ -1460,7 +1451,7 @@ static void disk_release(struct device *dev)
 	disk_release_events(disk);
 	kfree(disk->random);
 	disk_replace_part_tbl(disk, NULL);
-	hd_free_part(&disk->part0);
+	bdput(disk->part0);
 	if (disk->queue)
 		blk_put_queue(disk->queue);
 	kfree(disk);
@@ -1626,8 +1617,8 @@ struct gendisk *__alloc_disk_node(int minors, int node_id)
 	if (!disk)
 		return NULL;
 
-	disk->part0.bdev = bdev_alloc(disk, 0);
-	if (!disk->part0.bdev)
+	disk->part0 = bdev_alloc(disk, 0);
+	if (!disk->part0)
 		goto out_free_disk;
 
 	disk->node_id = node_id;
@@ -1635,10 +1626,7 @@ struct gendisk *__alloc_disk_node(int minors, int node_id)
 		goto out_bdput;
 
 	ptbl = rcu_dereference_protected(disk->part_tbl, 1);
-	rcu_assign_pointer(ptbl->part[0], &disk->part0);
-
-	if (hd_ref_init(&disk->part0))
-		goto out_bdput;
+	rcu_assign_pointer(ptbl->part[0], disk->part0->bd_part);
 
 	disk->minors = minors;
 	rand_initialize_disk(disk);
@@ -1648,7 +1636,7 @@ struct gendisk *__alloc_disk_node(int minors, int node_id)
 	return disk;
 
 out_bdput:
-	bdput(disk->part0.bdev);
+	bdput(disk->part0);
 out_free_disk:
 	kfree(disk);
 	return NULL;
@@ -1687,9 +1675,9 @@ void set_disk_ro(struct gendisk *disk, int flag)
 	struct disk_part_iter piter;
 	struct hd_struct *part;
 
-	if (disk->part0.bdev->bd_read_only != flag) {
+	if (disk->part0->bd_read_only != flag) {
 		set_disk_ro_uevent(disk, flag);
-		disk->part0.bdev->bd_read_only = flag;
+		disk->part0->bd_read_only = flag;
 	}
 
 	disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY);
diff --git a/block/partitions/core.c b/block/partitions/core.c
index 060c1be13cd8..6d1fca193cbd 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -265,9 +265,9 @@ static const struct attribute_group *part_attr_groups[] = {
 static void part_release(struct device *dev)
 {
 	struct hd_struct *p = dev_to_part(dev);
+
 	blk_free_devt(dev->devt);
-	hd_free_part(p);
-	kfree(p);
+	bdput(p->bdev);
 }
 
 static int part_uevent(struct device *dev, struct kobj_uevent_env *env)
@@ -288,46 +288,6 @@ struct device_type part_type = {
 	.uevent		= part_uevent,
 };
 
-static void hd_struct_free_work(struct work_struct *work)
-{
-	struct hd_struct *part =
-		container_of(to_rcu_work(work), struct hd_struct, rcu_work);
-	struct gendisk *disk = part_to_disk(part);
-
-	/*
-	 * Release the disk reference acquired in delete_partition here.
-	 * We can't release it in hd_struct_free because the final put_device
-	 * needs process context and thus can't be run directly from a
-	 * percpu_ref ->release handler.
-	 */
-	put_device(disk_to_dev(disk));
-
-	part->bdev->bd_start_sect = 0;
-	bdev_set_nr_sectors(part->bdev, 0);
-	part_stat_set_all(part, 0);
-	put_device(part_to_dev(part));
-}
-
-static void hd_struct_free(struct percpu_ref *ref)
-{
-	struct hd_struct *part = container_of(ref, struct hd_struct, ref);
-	struct gendisk *disk = part_to_disk(part);
-	struct disk_part_tbl *ptbl =
-		rcu_dereference_protected(disk->part_tbl, 1);
-
-	rcu_assign_pointer(ptbl->last_lookup, NULL);
-
-	INIT_RCU_WORK(&part->rcu_work, hd_struct_free_work);
-	queue_rcu_work(system_wq, &part->rcu_work);
-}
-
-int hd_ref_init(struct hd_struct *part)
-{
-	if (percpu_ref_init(&part->ref, hd_struct_free, 0, GFP_KERNEL))
-		return -ENOMEM;
-	return 0;
-}
-
 /*
  * Must be called either with bd_mutex held, before a disk can be opened or
  * after all disk users are gone.
@@ -342,8 +302,8 @@ void delete_partition(struct hd_struct *part)
 	 * ->part_tbl is referenced in this part's release handler, so
 	 *  we have to hold the disk device
 	 */
-	get_device(disk_to_dev(disk));
 	rcu_assign_pointer(ptbl->part[part->partno], NULL);
+	rcu_assign_pointer(ptbl->last_lookup, NULL);
 	kobject_put(part->bdev->bd_holder_dir);
 	device_del(part_to_dev(part));
 
@@ -353,7 +313,7 @@ void delete_partition(struct hd_struct *part)
 	 */
 	remove_inode_hash(part->bdev->bd_inode);
 
-	percpu_ref_kill(&part->ref);
+	put_device(part_to_dev(part));
 }
 
 static ssize_t whole_disk_show(struct device *dev,
@@ -406,15 +366,11 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 	if (ptbl->part[partno])
 		return ERR_PTR(-EBUSY);
 
-	p = kzalloc(sizeof(*p), GFP_KERNEL);
-	if (!p)
-		return ERR_PTR(-EBUSY);
-
 	bdev = bdev_alloc(disk, partno);
 	if (!bdev)
-		goto out_free;
-	p->bdev = bdev;
+		return ERR_PTR(-ENOMEM);
 
+	p = bdev->bd_part;
 	pdev = part_to_dev(p);
 
 	bdev->bd_start_sect = start;
@@ -463,13 +419,6 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 			goto out_del;
 	}
 
-	err = hd_ref_init(p);
-	if (err) {
-		if (flags & ADDPART_FLAG_WHOLEDISK)
-			goto out_remove_file;
-		goto out_del;
-	}
-
 	/* everything is up and running, commence */
 	bdev_add(bdev, devt);
 	rcu_assign_pointer(ptbl->part[partno], p);
@@ -481,11 +430,7 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 
 out_bdput:
 	bdput(bdev);
-out_free:
-	kfree(p);
 	return ERR_PTR(err);
-out_remove_file:
-	device_remove_file(pdev, &dev_attr_whole_disk);
 out_del:
 	kobject_put(bdev->bd_holder_dir);
 	device_del(pdev);
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index dc333dbe5232..9e5c2fdfda36 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -2802,7 +2802,7 @@ bool drbd_rs_c_min_rate_throttle(struct drbd_device *device)
 	if (c_min_rate == 0)
 		return false;
 
-	curr_events = (int)part_stat_read_accum(&disk->part0, sectors) -
+	curr_events = (int)part_stat_read_accum(disk->part0->bd_part, sectors) -
 			atomic_read(&device->rs_sect_ev);
 
 	if (atomic_read(&device->ap_actlog_cnt)
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index ba56f3f05312..343f56b86bb7 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -1678,7 +1678,8 @@ void drbd_rs_controller_reset(struct drbd_device *device)
 	atomic_set(&device->rs_sect_in, 0);
 	atomic_set(&device->rs_sect_ev, 0);
 	device->rs_in_flight = 0;
-	device->rs_last_events = (int)part_stat_read_accum(&disk->part0, sectors);
+	device->rs_last_events =
+		(int)part_stat_read_accum(disk->part0->bd_part, sectors);
 
 	/* Updating the RCU protected object in place is necessary since
 	   this function gets called from atomic context.
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index b5f68951c9d2..6d84876a9cd0 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -1687,7 +1687,7 @@ static void zram_reset_device(struct zram *zram)
 	zram->disksize = 0;
 
 	set_capacity_and_notify(zram->disk, 0);
-	part_stat_set_all(&zram->disk->part0, 0);
+	part_stat_set_all(zram->disk->part0->bd_part, 0);
 
 	up_write(&zram->init_lock);
 	/* I/O operation under all of CPU are done so let's free */
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 48051db006f3..1b2db4d530ea 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1607,7 +1607,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md,
 				 * (by eliminating DM's splitting and just using bio_split)
 				 */
 				part_stat_lock();
-				__dm_part_stat_sub(&dm_disk(md)->part0,
+				__dm_part_stat_sub(dm_disk(md)->part0->bd_part,
 						   sectors[op_stat_group(bio_op(bio))], ci.sector_count);
 				part_stat_unlock();
 
@@ -2242,7 +2242,7 @@ EXPORT_SYMBOL_GPL(dm_put);
 static bool md_in_flight_bios(struct mapped_device *md)
 {
 	int cpu;
-	struct hd_struct *part = &dm_disk(md)->part0;
+	struct hd_struct *part = dm_disk(md)->part0->bd_part;
 	long sum = 0;
 
 	for_each_possible_cpu(cpu) {
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 7ce6047c856e..3696c2d77a4d 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -8441,7 +8441,7 @@ static int is_mddev_idle(struct mddev *mddev, int init)
 	rcu_read_lock();
 	rdev_for_each_rcu(rdev, mddev) {
 		struct gendisk *disk = rdev->bdev->bd_disk;
-		curr_events = (int)part_stat_read_accum(&disk->part0, sectors) -
+		curr_events = (int)part_stat_read_accum(disk->part0->bd_part, sectors) -
 			      atomic_read(&disk->sync_io);
 		/* sync IO will cause sync_io to increase before the disk_stats
 		 * as sync_io is counted when a request starts, and
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 381c22426f43..61cf33b6284f 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -39,6 +39,7 @@
 
 struct bdev_inode {
 	struct block_device bdev;
+	struct hd_struct hd;
 	struct inode vfs_inode;
 };
 
@@ -886,6 +887,9 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno)
 		iput(inode);
 		return NULL;
 	}
+	bdev->bd_part = &BDEV_I(inode)->hd;
+	memset(bdev->bd_part, 0, sizeof(*bdev->bd_part));
+	bdev->bd_part->bdev = bdev;
 	return bdev;
 }
 
@@ -1280,15 +1284,10 @@ EXPORT_SYMBOL_GPL(bdev_disk_changed);
 static int __blkdev_get(struct block_device *bdev, fmode_t mode)
 {
 	struct gendisk *disk = bdev->bd_disk;
-	int ret;
+	int ret = 0;
 
 	if (!bdev->bd_openers) {
 		if (!bdev_is_partition(bdev)) {
-			ret = -ENXIO;
-			bdev->bd_part = disk_get_part(disk, 0);
-			if (!bdev->bd_part)
-				goto out_clear;
-
 			ret = 0;
 			if (disk->fops->open)
 				ret = disk->fops->open(bdev, mode);
@@ -1307,7 +1306,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode)
 				bdev_disk_changed(bdev, ret == -ENOMEDIUM);
 
 			if (ret)
-				goto out_clear;
+				return ret;
 		} else {
 			struct block_device *whole = bdget_disk(disk, 0);
 
@@ -1316,18 +1315,16 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode)
 			if (ret) {
 				mutex_unlock(&whole->bd_mutex);
 				bdput(whole);
-				goto out_clear;
+				return ret;
 			}
 			whole->bd_part_count++;
 			mutex_unlock(&whole->bd_mutex);
 
-			bdev->bd_part = disk_get_part(disk, bdev->bd_partno);
 			if (!(disk->flags & GENHD_FL_UP) ||
-			    !bdev->bd_part || !bdev_nr_sectors(bdev)) {
+			    !bdev_nr_sectors(bdev)) {
 				__blkdev_put(whole, mode, 1);
 				bdput(whole);
-				ret = -ENXIO;
-				goto out_clear;
+				return -ENXIO;
 			}
 			set_init_blocksize(bdev);
 		}
@@ -1336,7 +1333,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode)
 			bdev->bd_bdi = bdi_get(disk->queue->backing_dev_info);
 	} else {
 		if (!bdev_is_partition(bdev)) {
-			ret = 0;
 			if (bdev->bd_disk->fops->open)
 				ret = bdev->bd_disk->fops->open(bdev, mode);
 			/* the same as first opener case, read comment there */
@@ -1349,11 +1345,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode)
 	}
 	bdev->bd_openers++;
 	return 0;
-
- out_clear:
-	disk_put_part(bdev->bd_part);
-	bdev->bd_part = NULL;
-	return ret;
 }
 
 struct block_device *blkdev_get_no_open(dev_t dev)
@@ -1580,18 +1571,12 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
 		sync_blockdev(bdev);
 		kill_bdev(bdev);
 		bdev_write_inode(bdev);
-
-		if (!bdev_is_partition(bdev) && disk->fops->release)
-			disk->fops->release(disk, mode);
-
-		disk_put_part(bdev->bd_part);
-		bdev->bd_part = NULL;
 		if (bdev_is_partition(bdev))
 			victim = bdev_whole(bdev);
-	} else {
-		if (!bdev_is_partition(bdev) && disk->fops->release)
-			disk->fops->release(disk, mode);
 	}
+
+	if (!bdev_is_partition(bdev) && disk->fops->release)
+		disk->fops->release(disk, mode);
 	mutex_unlock(&bdev->bd_mutex);
 	if (victim) {
 		__blkdev_put(victim, mode, 1);
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 758cf71c9aa2..6edea5c16259 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -59,7 +59,7 @@ struct block_device {
 } __randomize_layout;
 
 #define bdev_whole(_bdev) \
-	((_bdev)->bd_disk->part0.bdev)
+	((_bdev)->bd_disk->part0)
 
 #define bdev_kobj(_bdev) \
 	(&part_to_dev((_bdev)->bd_part)->kobj)
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index dcbf9ef7610e..df7319da013c 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -19,11 +19,12 @@
 #include <linux/blk_types.h>
 #include <asm/local.h>
 
-#define dev_to_disk(device)	container_of((device), struct gendisk, part0.__dev)
 #define dev_to_part(device)	container_of((device), struct hd_struct, __dev)
-#define disk_to_dev(disk)	(&(disk)->part0.__dev)
 #define part_to_dev(part)	(&((part)->__dev))
 
+#define dev_to_disk(device)	(dev_to_part(device)->bdev->bd_disk)
+#define disk_to_dev(disk)	(part_to_dev((disk)->part0->bd_part))
+
 extern const struct device_type disk_type;
 extern struct device_type part_type;
 extern struct class block_class;
@@ -51,12 +52,9 @@ struct partition_meta_info {
 };
 
 struct hd_struct {
-	struct percpu_ref ref;
-
 	struct block_device *bdev;
 	struct device __dev;
 	int partno;
-	struct rcu_work rcu_work;
 };
 
 /**
@@ -168,7 +166,7 @@ struct gendisk {
 	 * helpers.
 	 */
 	struct disk_part_tbl __rcu *part_tbl;
-	struct hd_struct part0;
+	struct block_device *part0;
 
 	const struct block_device_operations *fops;
 	struct request_queue *queue;
@@ -278,7 +276,7 @@ extern void set_disk_ro(struct gendisk *disk, int flag);
 
 static inline int get_disk_ro(struct gendisk *disk)
 {
-	return disk->part0.bdev->bd_read_only;
+	return disk->part0->bd_read_only;
 }
 
 extern void disk_block_events(struct gendisk *disk);
@@ -302,7 +300,7 @@ static inline sector_t bdev_nr_sectors(struct block_device *bdev)
 
 static inline sector_t get_capacity(struct gendisk *disk)
 {
-	return bdev_nr_sectors(disk->part0.bdev);
+	return bdev_nr_sectors(disk->part0);
 }
 
 int bdev_disk_changed(struct block_device *bdev, bool invalidate);
diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h
index 87ad60106e1d..680de036691e 100644
--- a/include/linux/part_stat.h
+++ b/include/linux/part_stat.h
@@ -59,8 +59,8 @@ static inline void part_stat_set_all(struct hd_struct *part, int value)
 #define part_stat_add(part, field, addnd)	do {			\
 	__part_stat_add((part), field, addnd);				\
 	if ((part)->partno)						\
-		__part_stat_add(&part_to_disk((part))->part0,		\
-				field, addnd);				\
+		__part_stat_add(part_to_disk((part))->part0->bd_part,	\
+			field, addnd); \
 } while (0)
 
 #define part_stat_dec(part, field)					\
-- 
cgit v1.2.3


From 8446fe9255be821cb38ffd306d7e8edc4b9ea662 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 24 Nov 2020 09:36:54 +0100
Subject: block: switch partition lookup to use struct block_device

Use struct block_device to lookup partitions on a disk.  This removes
all usage of struct hd_struct from the I/O path.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Acked-by: Coly Li <colyli@suse.de>			[bcache]
Acked-by: Chao Yu <yuchao0@huawei.com>			[f2fs]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio.c                        |  4 +--
 block/blk-core.c                   | 66 +++++++++++++++++---------------------
 block/blk-flush.c                  |  2 +-
 block/blk-mq.c                     |  9 +++---
 block/blk-mq.h                     |  7 ++--
 block/blk.h                        |  4 +--
 block/genhd.c                      | 57 +++++++++++++++++---------------
 block/partitions/core.c            |  7 ++--
 drivers/block/drbd/drbd_receiver.c |  2 +-
 drivers/block/drbd/drbd_worker.c   |  2 +-
 drivers/block/zram/zram_drv.c      |  2 +-
 drivers/md/bcache/request.c        |  4 +--
 drivers/md/dm.c                    |  4 +--
 drivers/md/md.c                    |  4 +--
 drivers/nvme/target/admin-cmd.c    | 20 ++++++------
 fs/ext4/super.c                    | 18 ++++-------
 fs/ext4/sysfs.c                    | 10 ++----
 fs/f2fs/f2fs.h                     |  2 +-
 fs/f2fs/super.c                    |  6 ++--
 include/linux/blkdev.h             |  8 ++---
 include/linux/genhd.h              |  4 +--
 include/linux/part_stat.h          | 17 +++++-----
 22 files changed, 122 insertions(+), 137 deletions(-)

(limited to 'include/linux')

diff --git a/block/bio.c b/block/bio.c
index 669bb47a3198..ebb18136b86f 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -608,12 +608,12 @@ void bio_truncate(struct bio *bio, unsigned new_size)
 void guard_bio_eod(struct bio *bio)
 {
 	sector_t maxsector;
-	struct hd_struct *part;
+	struct block_device *part;
 
 	rcu_read_lock();
 	part = __disk_get_part(bio->bi_disk, bio->bi_partno);
 	if (part)
-		maxsector = bdev_nr_sectors(part->bdev);
+		maxsector = bdev_nr_sectors(part);
 	else	
 		maxsector = get_capacity(bio->bi_disk);
 	rcu_read_unlock();
diff --git a/block/blk-core.c b/block/blk-core.c
index 9ea70275fc1c..cee568389b7e 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -666,10 +666,9 @@ static int __init setup_fail_make_request(char *str)
 }
 __setup("fail_make_request=", setup_fail_make_request);
 
-static bool should_fail_request(struct hd_struct *part, unsigned int bytes)
+static bool should_fail_request(struct block_device *part, unsigned int bytes)
 {
-	return part->bdev->bd_make_it_fail &&
-		should_fail(&fail_make_request, bytes);
+	return part->bd_make_it_fail && should_fail(&fail_make_request, bytes);
 }
 
 static int __init fail_make_request_debugfs(void)
@@ -684,7 +683,7 @@ late_initcall(fail_make_request_debugfs);
 
 #else /* CONFIG_FAIL_MAKE_REQUEST */
 
-static inline bool should_fail_request(struct hd_struct *part,
+static inline bool should_fail_request(struct block_device *part,
 					unsigned int bytes)
 {
 	return false;
@@ -692,11 +691,11 @@ static inline bool should_fail_request(struct hd_struct *part,
 
 #endif /* CONFIG_FAIL_MAKE_REQUEST */
 
-static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part)
+static inline bool bio_check_ro(struct bio *bio, struct block_device *part)
 {
 	const int op = bio_op(bio);
 
-	if (part->bdev->bd_read_only && op_is_write(op)) {
+	if (part->bd_read_only && op_is_write(op)) {
 		char b[BDEVNAME_SIZE];
 
 		if (op_is_flush(bio->bi_opf) && !bio_sectors(bio))
@@ -704,7 +703,7 @@ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part)
 
 		WARN_ONCE(1,
 		       "Trying to write to read-only block-device %s (partno %d)\n",
-			bio_devname(bio, b), part->partno);
+			bio_devname(bio, b), part->bd_partno);
 		/* Older lvm-tools actually trigger this */
 		return false;
 	}
@@ -714,8 +713,7 @@ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part)
 
 static noinline int should_fail_bio(struct bio *bio)
 {
-	if (should_fail_request(bio->bi_disk->part0->bd_part,
-			bio->bi_iter.bi_size))
+	if (should_fail_request(bio->bi_disk->part0, bio->bi_iter.bi_size))
 		return -EIO;
 	return 0;
 }
@@ -744,7 +742,7 @@ static inline int bio_check_eod(struct bio *bio, sector_t maxsector)
  */
 static inline int blk_partition_remap(struct bio *bio)
 {
-	struct hd_struct *p;
+	struct block_device *p;
 	int ret = -EIO;
 
 	rcu_read_lock();
@@ -757,12 +755,12 @@ static inline int blk_partition_remap(struct bio *bio)
 		goto out;
 
 	if (bio_sectors(bio)) {
-		if (bio_check_eod(bio, bdev_nr_sectors(p->bdev)))
+		if (bio_check_eod(bio, bdev_nr_sectors(p)))
 			goto out;
-		bio->bi_iter.bi_sector += p->bdev->bd_start_sect;
-		trace_block_bio_remap(bio->bi_disk->queue, bio, part_devt(p),
+		bio->bi_iter.bi_sector += p->bd_start_sect;
+		trace_block_bio_remap(bio->bi_disk->queue, bio, p->bd_dev,
 				      bio->bi_iter.bi_sector -
-				      p->bdev->bd_start_sect);
+				      p->bd_start_sect);
 	}
 	bio->bi_partno = 0;
 	ret = 0;
@@ -832,7 +830,7 @@ static noinline_for_stack bool submit_bio_checks(struct bio *bio)
 		if (unlikely(blk_partition_remap(bio)))
 			goto end_io;
 	} else {
-		if (unlikely(bio_check_ro(bio, bio->bi_disk->part0->bd_part)))
+		if (unlikely(bio_check_ro(bio, bio->bi_disk->part0)))
 			goto end_io;
 		if (unlikely(bio_check_eod(bio, get_capacity(bio->bi_disk))))
 			goto end_io;
@@ -1204,7 +1202,7 @@ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *
 		return ret;
 
 	if (rq->rq_disk &&
-	    should_fail_request(rq->rq_disk->part0->bd_part, blk_rq_bytes(rq)))
+	    should_fail_request(rq->rq_disk->part0, blk_rq_bytes(rq)))
 		return BLK_STS_IOERR;
 
 	if (blk_crypto_insert_cloned_request(rq))
@@ -1263,17 +1261,18 @@ unsigned int blk_rq_err_bytes(const struct request *rq)
 }
 EXPORT_SYMBOL_GPL(blk_rq_err_bytes);
 
-static void update_io_ticks(struct hd_struct *part, unsigned long now, bool end)
+static void update_io_ticks(struct block_device *part, unsigned long now,
+		bool end)
 {
 	unsigned long stamp;
 again:
-	stamp = READ_ONCE(part->bdev->bd_stamp);
+	stamp = READ_ONCE(part->bd_stamp);
 	if (unlikely(stamp != now)) {
-		if (likely(cmpxchg(&part->bdev->bd_stamp, stamp, now) == stamp))
+		if (likely(cmpxchg(&part->bd_stamp, stamp, now) == stamp))
 			__part_stat_add(part, io_ticks, end ? now - stamp : 1);
 	}
-	if (part->partno) {
-		part = part_to_disk(part)->part0->bd_part;
+	if (part->bd_partno) {
+		part = bdev_whole(part);
 		goto again;
 	}
 }
@@ -1282,11 +1281,9 @@ static void blk_account_io_completion(struct request *req, unsigned int bytes)
 {
 	if (req->part && blk_do_io_stat(req)) {
 		const int sgrp = op_stat_group(req_op(req));
-		struct hd_struct *part;
 
 		part_stat_lock();
-		part = req->part;
-		part_stat_add(part, sectors[sgrp], bytes >> 9);
+		part_stat_add(req->part, sectors[sgrp], bytes >> 9);
 		part_stat_unlock();
 	}
 }
@@ -1301,14 +1298,11 @@ void blk_account_io_done(struct request *req, u64 now)
 	if (req->part && blk_do_io_stat(req) &&
 	    !(req->rq_flags & RQF_FLUSH_SEQ)) {
 		const int sgrp = op_stat_group(req_op(req));
-		struct hd_struct *part;
 
 		part_stat_lock();
-		part = req->part;
-
-		update_io_ticks(part, jiffies, true);
-		part_stat_inc(part, ios[sgrp]);
-		part_stat_add(part, nsecs[sgrp], now - req->start_time_ns);
+		update_io_ticks(req->part, jiffies, true);
+		part_stat_inc(req->part, ios[sgrp]);
+		part_stat_add(req->part, nsecs[sgrp], now - req->start_time_ns);
 		part_stat_unlock();
 	}
 }
@@ -1325,7 +1319,7 @@ void blk_account_io_start(struct request *rq)
 	part_stat_unlock();
 }
 
-static unsigned long __part_start_io_acct(struct hd_struct *part,
+static unsigned long __part_start_io_acct(struct block_device *part,
 					  unsigned int sectors, unsigned int op)
 {
 	const int sgrp = op_stat_group(op);
@@ -1341,7 +1335,7 @@ static unsigned long __part_start_io_acct(struct hd_struct *part,
 	return now;
 }
 
-unsigned long part_start_io_acct(struct gendisk *disk, struct hd_struct **part,
+unsigned long part_start_io_acct(struct gendisk *disk, struct block_device **part,
 				 struct bio *bio)
 {
 	*part = disk_map_sector_rcu(disk, bio->bi_iter.bi_sector);
@@ -1353,11 +1347,11 @@ EXPORT_SYMBOL_GPL(part_start_io_acct);
 unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
 				 unsigned int op)
 {
-	return __part_start_io_acct(disk->part0->bd_part, sectors, op);
+	return __part_start_io_acct(disk->part0, sectors, op);
 }
 EXPORT_SYMBOL(disk_start_io_acct);
 
-static void __part_end_io_acct(struct hd_struct *part, unsigned int op,
+static void __part_end_io_acct(struct block_device *part, unsigned int op,
 			       unsigned long start_time)
 {
 	const int sgrp = op_stat_group(op);
@@ -1371,7 +1365,7 @@ static void __part_end_io_acct(struct hd_struct *part, unsigned int op,
 	part_stat_unlock();
 }
 
-void part_end_io_acct(struct hd_struct *part, struct bio *bio,
+void part_end_io_acct(struct block_device *part, struct bio *bio,
 		      unsigned long start_time)
 {
 	__part_end_io_acct(part, bio_op(bio), start_time);
@@ -1381,7 +1375,7 @@ EXPORT_SYMBOL_GPL(part_end_io_acct);
 void disk_end_io_acct(struct gendisk *disk, unsigned int op,
 		      unsigned long start_time)
 {
-	__part_end_io_acct(disk->part0->bd_part, op, start_time);
+	__part_end_io_acct(disk->part0, op, start_time);
 }
 EXPORT_SYMBOL(disk_end_io_acct);
 
diff --git a/block/blk-flush.c b/block/blk-flush.c
index fcd0a60574df..9507dcdd5881 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -139,7 +139,7 @@ static void blk_flush_queue_rq(struct request *rq, bool add_front)
 
 static void blk_account_io_flush(struct request *rq)
 {
-	struct hd_struct *part = rq->rq_disk->part0->bd_part;
+	struct block_device *part = rq->rq_disk->part0;
 
 	part_stat_lock();
 	part_stat_inc(part, ios[STAT_FLUSH]);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 55bcee5dc032..a2593748fa53 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -95,7 +95,7 @@ static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx,
 }
 
 struct mq_inflight {
-	struct hd_struct *part;
+	struct block_device *part;
 	unsigned int inflight[2];
 };
 
@@ -111,7 +111,8 @@ static bool blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx,
 	return true;
 }
 
-unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part)
+unsigned int blk_mq_in_flight(struct request_queue *q,
+		struct block_device *part)
 {
 	struct mq_inflight mi = { .part = part };
 
@@ -120,8 +121,8 @@ unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part)
 	return mi.inflight[0] + mi.inflight[1];
 }
 
-void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part,
-			 unsigned int inflight[2])
+void blk_mq_in_flight_rw(struct request_queue *q, struct block_device *part,
+		unsigned int inflight[2])
 {
 	struct mq_inflight mi = { .part = part };
 
diff --git a/block/blk-mq.h b/block/blk-mq.h
index a52703c98b77..c696515766c7 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -182,9 +182,10 @@ static inline bool blk_mq_hw_queue_mapped(struct blk_mq_hw_ctx *hctx)
 	return hctx->nr_ctx && hctx->tags;
 }
 
-unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part);
-void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part,
-			 unsigned int inflight[2]);
+unsigned int blk_mq_in_flight(struct request_queue *q,
+		struct block_device *part);
+void blk_mq_in_flight_rw(struct request_queue *q, struct block_device *part,
+		unsigned int inflight[2]);
 
 static inline void blk_mq_put_dispatch_budget(struct request_queue *q)
 {
diff --git a/block/blk.h b/block/blk.h
index 32ac41f7557f..d5bf8f3a0781 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -215,7 +215,7 @@ static inline void elevator_exit(struct request_queue *q,
 	__elevator_exit(q, e);
 }
 
-struct hd_struct *__disk_get_part(struct gendisk *disk, int partno);
+struct block_device *__disk_get_part(struct gendisk *disk, int partno);
 
 ssize_t part_size_show(struct device *dev, struct device_attribute *attr,
 		char *buf);
@@ -348,7 +348,7 @@ void blk_queue_free_zone_bitmaps(struct request_queue *q);
 static inline void blk_queue_free_zone_bitmaps(struct request_queue *q) {}
 #endif
 
-struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector);
+struct block_device *disk_map_sector_rcu(struct gendisk *disk, sector_t sector);
 
 int blk_alloc_devt(struct hd_struct *part, dev_t *devt);
 void blk_free_devt(dev_t devt);
diff --git a/block/genhd.c b/block/genhd.c
index c35b03dac5e5..ed06466b305d 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -126,7 +126,7 @@ static void part_stat_read_all(struct hd_struct *part, struct disk_stats *stat)
 	}
 }
 
-static unsigned int part_in_flight(struct hd_struct *part)
+static unsigned int part_in_flight(struct block_device *part)
 {
 	unsigned int inflight = 0;
 	int cpu;
@@ -141,7 +141,8 @@ static unsigned int part_in_flight(struct hd_struct *part)
 	return inflight;
 }
 
-static void part_in_flight_rw(struct hd_struct *part, unsigned int inflight[2])
+static void part_in_flight_rw(struct block_device *part,
+		unsigned int inflight[2])
 {
 	int cpu;
 
@@ -157,7 +158,7 @@ static void part_in_flight_rw(struct hd_struct *part, unsigned int inflight[2])
 		inflight[1] = 0;
 }
 
-struct hd_struct *__disk_get_part(struct gendisk *disk, int partno)
+struct block_device *__disk_get_part(struct gendisk *disk, int partno)
 {
 	struct disk_part_tbl *ptbl = rcu_dereference(disk->part_tbl);
 
@@ -182,15 +183,21 @@ struct hd_struct *__disk_get_part(struct gendisk *disk, int partno)
  */
 struct hd_struct *disk_get_part(struct gendisk *disk, int partno)
 {
+	struct block_device *bdev;
 	struct hd_struct *part;
 
 	rcu_read_lock();
-	part = __disk_get_part(disk, partno);
-	if (part)
-		get_device(part_to_dev(part));
+	bdev = __disk_get_part(disk, partno);
+	if (!bdev)
+		goto fail;
+	part = bdev->bd_part;
+	if (!kobject_get_unless_zero(&part_to_dev(part)->kobj))
+		goto fail;
 	rcu_read_unlock();
-
 	return part;
+fail:
+	rcu_read_unlock();
+	return NULL;
 }
 
 /**
@@ -264,19 +271,19 @@ struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter)
 
 	/* iterate to the next partition */
 	for (; piter->idx != end; piter->idx += inc) {
-		struct hd_struct *part;
+		struct block_device *part;
 
 		part = rcu_dereference(ptbl->part[piter->idx]);
 		if (!part)
 			continue;
-		if (!bdev_nr_sectors(part->bdev) &&
+		if (!bdev_nr_sectors(part) &&
 		    !(piter->flags & DISK_PITER_INCL_EMPTY) &&
 		    !(piter->flags & DISK_PITER_INCL_EMPTY_PART0 &&
 		      piter->idx == 0))
 			continue;
 
-		get_device(part_to_dev(part));
-		piter->part = part;
+		get_device(part_to_dev(part->bd_part));
+		piter->part = part->bd_part;
 		piter->idx += inc;
 		break;
 	}
@@ -303,10 +310,10 @@ void disk_part_iter_exit(struct disk_part_iter *piter)
 }
 EXPORT_SYMBOL_GPL(disk_part_iter_exit);
 
-static inline int sector_in_part(struct hd_struct *part, sector_t sector)
+static inline int sector_in_part(struct block_device *part, sector_t sector)
 {
-	return part->bdev->bd_start_sect <= sector &&
-		sector < part->bdev->bd_start_sect + bdev_nr_sectors(part->bdev);
+	return part->bd_start_sect <= sector &&
+		sector < part->bd_start_sect + bdev_nr_sectors(part);
 }
 
 /**
@@ -324,10 +331,10 @@ static inline int sector_in_part(struct hd_struct *part, sector_t sector)
  * Found partition on success, part0 is returned if no partition matches
  * or the matched partition is being deleted.
  */
-struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector)
+struct block_device *disk_map_sector_rcu(struct gendisk *disk, sector_t sector)
 {
 	struct disk_part_tbl *ptbl;
-	struct hd_struct *part;
+	struct block_device *part;
 	int i;
 
 	rcu_read_lock();
@@ -346,7 +353,7 @@ struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector)
 		}
 	}
 
-	part = disk->part0->bd_part;
+	part = disk->part0;
 out_unlock:
 	rcu_read_unlock();
 	return part;
@@ -882,7 +889,7 @@ void del_gendisk(struct gendisk *disk)
 	kobject_put(disk->part0->bd_holder_dir);
 	kobject_put(disk->slave_dir);
 
-	part_stat_set_all(disk->part0->bd_part, 0);
+	part_stat_set_all(disk->part0, 0);
 	disk->part0->bd_stamp = 0;
 	if (!sysfs_deprecated)
 		sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk)));
@@ -1189,9 +1196,9 @@ ssize_t part_stat_show(struct device *dev,
 
 	part_stat_read_all(p, &stat);
 	if (queue_is_mq(q))
-		inflight = blk_mq_in_flight(q, p);
+		inflight = blk_mq_in_flight(q, p->bdev);
 	else
-		inflight = part_in_flight(p);
+		inflight = part_in_flight(p->bdev);
 
 	return sprintf(buf,
 		"%8lu %8lu %8llu %8u "
@@ -1231,9 +1238,9 @@ ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr,
 	unsigned int inflight[2];
 
 	if (queue_is_mq(q))
-		blk_mq_in_flight_rw(q, p, inflight);
+		blk_mq_in_flight_rw(q, p->bdev, inflight);
 	else
-		part_in_flight_rw(p, inflight);
+		part_in_flight_rw(p->bdev, inflight);
 
 	return sprintf(buf, "%8u %8u\n", inflight[0], inflight[1]);
 }
@@ -1506,9 +1513,9 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 	while ((hd = disk_part_iter_next(&piter))) {
 		part_stat_read_all(hd, &stat);
 		if (queue_is_mq(gp->queue))
-			inflight = blk_mq_in_flight(gp->queue, hd);
+			inflight = blk_mq_in_flight(gp->queue, hd->bdev);
 		else
-			inflight = part_in_flight(hd);
+			inflight = part_in_flight(hd->bdev);
 
 		seq_printf(seqf, "%4d %7d %s "
 			   "%lu %lu %lu %u "
@@ -1626,7 +1633,7 @@ struct gendisk *__alloc_disk_node(int minors, int node_id)
 		goto out_bdput;
 
 	ptbl = rcu_dereference_protected(disk->part_tbl, 1);
-	rcu_assign_pointer(ptbl->part[0], disk->part0->bd_part);
+	rcu_assign_pointer(ptbl->part[0], disk->part0);
 
 	disk->minors = minors;
 	rand_initialize_disk(disk);
diff --git a/block/partitions/core.c b/block/partitions/core.c
index 6d1fca193cbd..c2f6721633b8 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -298,12 +298,9 @@ void delete_partition(struct hd_struct *part)
 	struct disk_part_tbl *ptbl =
 		rcu_dereference_protected(disk->part_tbl, 1);
 
-	/*
-	 * ->part_tbl is referenced in this part's release handler, so
-	 *  we have to hold the disk device
-	 */
 	rcu_assign_pointer(ptbl->part[part->partno], NULL);
 	rcu_assign_pointer(ptbl->last_lookup, NULL);
+
 	kobject_put(part->bdev->bd_holder_dir);
 	device_del(part_to_dev(part));
 
@@ -421,7 +418,7 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 
 	/* everything is up and running, commence */
 	bdev_add(bdev, devt);
-	rcu_assign_pointer(ptbl->part[partno], p);
+	rcu_assign_pointer(ptbl->part[partno], bdev);
 
 	/* suppress uevent if the disk suppresses it */
 	if (!dev_get_uevent_suppress(ddev))
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 9e5c2fdfda36..09c86ef3f0fd 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -2802,7 +2802,7 @@ bool drbd_rs_c_min_rate_throttle(struct drbd_device *device)
 	if (c_min_rate == 0)
 		return false;
 
-	curr_events = (int)part_stat_read_accum(disk->part0->bd_part, sectors) -
+	curr_events = (int)part_stat_read_accum(disk->part0, sectors) -
 			atomic_read(&device->rs_sect_ev);
 
 	if (atomic_read(&device->ap_actlog_cnt)
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index 343f56b86bb7..02044ab7f767 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -1679,7 +1679,7 @@ void drbd_rs_controller_reset(struct drbd_device *device)
 	atomic_set(&device->rs_sect_ev, 0);
 	device->rs_in_flight = 0;
 	device->rs_last_events =
-		(int)part_stat_read_accum(disk->part0->bd_part, sectors);
+		(int)part_stat_read_accum(disk->part0, sectors);
 
 	/* Updating the RCU protected object in place is necessary since
 	   this function gets called from atomic context.
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 6d84876a9cd0..dc8957d173d3 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -1687,7 +1687,7 @@ static void zram_reset_device(struct zram *zram)
 	zram->disksize = 0;
 
 	set_capacity_and_notify(zram->disk, 0);
-	part_stat_set_all(zram->disk->part0->bd_part, 0);
+	part_stat_set_all(zram->disk->part0, 0);
 
 	up_write(&zram->init_lock);
 	/* I/O operation under all of CPU are done so let's free */
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index afac8d07c1bd..85b1f2a9b72d 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -475,7 +475,7 @@ struct search {
 	unsigned int		read_dirty_data:1;
 	unsigned int		cache_missed:1;
 
-	struct hd_struct	*part;
+	struct block_device	*part;
 	unsigned long		start_time;
 
 	struct btree_op		op;
@@ -1073,7 +1073,7 @@ struct detached_dev_io_private {
 	unsigned long		start_time;
 	bio_end_io_t		*bi_end_io;
 	void			*bi_private;
-	struct hd_struct	*part;
+	struct block_device	*part;
 };
 
 static void detached_dev_end_io(struct bio *bio)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 1b2db4d530ea..176adcff56b3 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1607,7 +1607,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md,
 				 * (by eliminating DM's splitting and just using bio_split)
 				 */
 				part_stat_lock();
-				__dm_part_stat_sub(dm_disk(md)->part0->bd_part,
+				__dm_part_stat_sub(dm_disk(md)->part0,
 						   sectors[op_stat_group(bio_op(bio))], ci.sector_count);
 				part_stat_unlock();
 
@@ -2242,7 +2242,7 @@ EXPORT_SYMBOL_GPL(dm_put);
 static bool md_in_flight_bios(struct mapped_device *md)
 {
 	int cpu;
-	struct hd_struct *part = dm_disk(md)->part0->bd_part;
+	struct block_device *part = dm_disk(md)->part0;
 	long sum = 0;
 
 	for_each_possible_cpu(cpu) {
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 3696c2d77a4d..0065736f05b4 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -464,7 +464,7 @@ struct md_io {
 	bio_end_io_t *orig_bi_end_io;
 	void *orig_bi_private;
 	unsigned long start_time;
-	struct hd_struct *part;
+	struct block_device *part;
 };
 
 static void md_end_io(struct bio *bio)
@@ -8441,7 +8441,7 @@ static int is_mddev_idle(struct mddev *mddev, int init)
 	rcu_read_lock();
 	rdev_for_each_rcu(rdev, mddev) {
 		struct gendisk *disk = rdev->bdev->bd_disk;
-		curr_events = (int)part_stat_read_accum(disk->part0->bd_part, sectors) -
+		curr_events = (int)part_stat_read_accum(disk->part0, sectors) -
 			      atomic_read(&disk->sync_io);
 		/* sync IO will cause sync_io to increase before the disk_stats
 		 * as sync_io is counted when a request starts, and
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index dca34489a1dc..8d90235e4fcc 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -89,12 +89,12 @@ static u16 nvmet_get_smart_log_nsid(struct nvmet_req *req,
 	if (!ns->bdev)
 		goto out;
 
-	host_reads = part_stat_read(ns->bdev->bd_part, ios[READ]);
-	data_units_read = DIV_ROUND_UP(part_stat_read(ns->bdev->bd_part,
-		sectors[READ]), 1000);
-	host_writes = part_stat_read(ns->bdev->bd_part, ios[WRITE]);
-	data_units_written = DIV_ROUND_UP(part_stat_read(ns->bdev->bd_part,
-		sectors[WRITE]), 1000);
+	host_reads = part_stat_read(ns->bdev, ios[READ]);
+	data_units_read =
+		DIV_ROUND_UP(part_stat_read(ns->bdev, sectors[READ]), 1000);
+	host_writes = part_stat_read(ns->bdev, ios[WRITE]);
+	data_units_written =
+		DIV_ROUND_UP(part_stat_read(ns->bdev, sectors[WRITE]), 1000);
 
 	put_unaligned_le64(host_reads, &slog->host_reads[0]);
 	put_unaligned_le64(data_units_read, &slog->data_units_read[0]);
@@ -120,12 +120,12 @@ static u16 nvmet_get_smart_log_all(struct nvmet_req *req,
 		/* we don't have the right data for file backed ns */
 		if (!ns->bdev)
 			continue;
-		host_reads += part_stat_read(ns->bdev->bd_part, ios[READ]);
+		host_reads += part_stat_read(ns->bdev, ios[READ]);
 		data_units_read += DIV_ROUND_UP(
-			part_stat_read(ns->bdev->bd_part, sectors[READ]), 1000);
-		host_writes += part_stat_read(ns->bdev->bd_part, ios[WRITE]);
+			part_stat_read(ns->bdev, sectors[READ]), 1000);
+		host_writes += part_stat_read(ns->bdev, ios[WRITE]);
 		data_units_written += DIV_ROUND_UP(
-			part_stat_read(ns->bdev->bd_part, sectors[WRITE]), 1000);
+			part_stat_read(ns->bdev, sectors[WRITE]), 1000);
 	}
 
 	put_unaligned_le64(host_reads, &slog->host_reads[0]);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 6633b20224d5..c303a0ff0b17 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -4048,9 +4048,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_sb = sb;
 	sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS;
 	sbi->s_sb_block = sb_block;
-	if (sb->s_bdev->bd_part)
-		sbi->s_sectors_written_start =
-			part_stat_read(sb->s_bdev->bd_part, sectors[STAT_WRITE]);
+	sbi->s_sectors_written_start =
+		part_stat_read(sb->s_bdev, sectors[STAT_WRITE]);
 
 	/* Cleanup superblock name */
 	strreplace(sb->s_id, '/', '!');
@@ -5509,15 +5508,10 @@ static int ext4_commit_super(struct super_block *sb, int sync)
 	 */
 	if (!(sb->s_flags & SB_RDONLY))
 		ext4_update_tstamp(es, s_wtime);
-	if (sb->s_bdev->bd_part)
-		es->s_kbytes_written =
-			cpu_to_le64(EXT4_SB(sb)->s_kbytes_written +
-			    ((part_stat_read(sb->s_bdev->bd_part,
-					     sectors[STAT_WRITE]) -
-			      EXT4_SB(sb)->s_sectors_written_start) >> 1));
-	else
-		es->s_kbytes_written =
-			cpu_to_le64(EXT4_SB(sb)->s_kbytes_written);
+	es->s_kbytes_written =
+		cpu_to_le64(EXT4_SB(sb)->s_kbytes_written +
+		    ((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) -
+		      EXT4_SB(sb)->s_sectors_written_start) >> 1));
 	if (percpu_counter_initialized(&EXT4_SB(sb)->s_freeclusters_counter))
 		ext4_free_blocks_count_set(es,
 			EXT4_C2B(EXT4_SB(sb), percpu_counter_sum_positive(
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index 4e27fe6ed3ae..075aa3a19ff5 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -62,11 +62,8 @@ static ssize_t session_write_kbytes_show(struct ext4_sb_info *sbi, char *buf)
 {
 	struct super_block *sb = sbi->s_buddy_cache->i_sb;
 
-	if (!sb->s_bdev->bd_part)
-		return snprintf(buf, PAGE_SIZE, "0\n");
 	return snprintf(buf, PAGE_SIZE, "%lu\n",
-			(part_stat_read(sb->s_bdev->bd_part,
-					sectors[STAT_WRITE]) -
+			(part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) -
 			 sbi->s_sectors_written_start) >> 1);
 }
 
@@ -74,12 +71,9 @@ static ssize_t lifetime_write_kbytes_show(struct ext4_sb_info *sbi, char *buf)
 {
 	struct super_block *sb = sbi->s_buddy_cache->i_sb;
 
-	if (!sb->s_bdev->bd_part)
-		return snprintf(buf, PAGE_SIZE, "0\n");
 	return snprintf(buf, PAGE_SIZE, "%llu\n",
 			(unsigned long long)(sbi->s_kbytes_written +
-			((part_stat_read(sb->s_bdev->bd_part,
-					 sectors[STAT_WRITE]) -
+			((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) -
 			  EXT4_SB(sb)->s_sectors_written_start) >> 1)));
 }
 
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index cb700d797296..49681a8d2b14 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1675,7 +1675,7 @@ static inline bool f2fs_is_multi_device(struct f2fs_sb_info *sbi)
  * and the return value is in kbytes. s is of struct f2fs_sb_info.
  */
 #define BD_PART_WRITTEN(s)						 \
-(((u64)part_stat_read((s)->sb->s_bdev->bd_part, sectors[STAT_WRITE]) -   \
+	(((u64)part_stat_read((s)->sb->s_bdev, sectors[STAT_WRITE]) -   \
 		(s)->sectors_written_start) >> 1)
 
 static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type)
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index d4e7fab352ba..af9f449da64b 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -3700,10 +3700,8 @@ try_onemore:
 	}
 
 	/* For write statistics */
-	if (sb->s_bdev->bd_part)
-		sbi->sectors_written_start =
-			(u64)part_stat_read(sb->s_bdev->bd_part,
-					    sectors[STAT_WRITE]);
+	sbi->sectors_written_start =
+		(u64)part_stat_read(sb->s_bdev, sectors[STAT_WRITE]);
 
 	/* Read accumulated write IO statistics if exists */
 	seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 619adea57098..1d4be1fc6007 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -191,7 +191,7 @@ struct request {
 	};
 
 	struct gendisk *rq_disk;
-	struct hd_struct *part;
+	struct block_device *part;
 #ifdef CONFIG_BLK_RQ_ALLOC_TIME
 	/* Time that the first bio started allocating this request. */
 	u64 alloc_time_ns;
@@ -1943,9 +1943,9 @@ unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
 void disk_end_io_acct(struct gendisk *disk, unsigned int op,
 		unsigned long start_time);
 
-unsigned long part_start_io_acct(struct gendisk *disk, struct hd_struct **part,
-				 struct bio *bio);
-void part_end_io_acct(struct hd_struct *part, struct bio *bio,
+unsigned long part_start_io_acct(struct gendisk *disk,
+		struct block_device **part, struct bio *bio);
+void part_end_io_acct(struct block_device *part, struct bio *bio,
 		      unsigned long start_time);
 
 /**
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index df7319da013c..fe6fee77e2b9 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -131,8 +131,8 @@ enum {
 struct disk_part_tbl {
 	struct rcu_head rcu_head;
 	int len;
-	struct hd_struct __rcu *last_lookup;
-	struct hd_struct __rcu *part[];
+	struct block_device __rcu *last_lookup;
+	struct block_device __rcu *part[];
 };
 
 struct disk_events;
diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h
index 680de036691e..d2558121d48c 100644
--- a/include/linux/part_stat.h
+++ b/include/linux/part_stat.h
@@ -25,26 +25,26 @@ struct disk_stats {
 #define part_stat_unlock()	preempt_enable()
 
 #define part_stat_get_cpu(part, field, cpu)				\
-	(per_cpu_ptr((part)->bdev->bd_stats, (cpu))->field)
+	(per_cpu_ptr((part)->bd_stats, (cpu))->field)
 
 #define part_stat_get(part, field)					\
 	part_stat_get_cpu(part, field, smp_processor_id())
 
 #define part_stat_read(part, field)					\
 ({									\
-	typeof((part)->bdev->bd_stats->field) res = 0;			\
+	typeof((part)->bd_stats->field) res = 0;			\
 	unsigned int _cpu;						\
 	for_each_possible_cpu(_cpu)					\
-		res += per_cpu_ptr((part)->bdev->bd_stats, _cpu)->field; \
+		res += per_cpu_ptr((part)->bd_stats, _cpu)->field; \
 	res;								\
 })
 
-static inline void part_stat_set_all(struct hd_struct *part, int value)
+static inline void part_stat_set_all(struct block_device *part, int value)
 {
 	int i;
 
 	for_each_possible_cpu(i)
-		memset(per_cpu_ptr(part->bdev->bd_stats, i), value,
+		memset(per_cpu_ptr(part->bd_stats, i), value,
 				sizeof(struct disk_stats));
 }
 
@@ -54,13 +54,12 @@ static inline void part_stat_set_all(struct hd_struct *part, int value)
 	 part_stat_read(part, field[STAT_DISCARD]))
 
 #define __part_stat_add(part, field, addnd)				\
-	__this_cpu_add((part)->bdev->bd_stats->field, addnd)
+	__this_cpu_add((part)->bd_stats->field, addnd)
 
 #define part_stat_add(part, field, addnd)	do {			\
 	__part_stat_add((part), field, addnd);				\
-	if ((part)->partno)						\
-		__part_stat_add(part_to_disk((part))->part0->bd_part,	\
-			field, addnd); \
+	if ((part)->bd_partno)						\
+		__part_stat_add(bdev_whole(part), field, addnd);	\
 } while (0)
 
 #define part_stat_dec(part, field)					\
-- 
cgit v1.2.3


From 41e5c81984eac8ce87f2b4f57fec0bd90a049b2b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 24 Nov 2020 09:37:14 +0100
Subject: block: remove the partno field from struct hd_struct

Just use the bd_partno field in struct block_device everywhere.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/genhd.c           | 12 ++++++------
 block/partitions/core.c |  9 ++++-----
 include/linux/genhd.h   |  1 -
 init/do_mounts.c        |  2 +-
 4 files changed, 11 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/block/genhd.c b/block/genhd.c
index ed06466b305d..b7e39b41a275 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -589,8 +589,8 @@ int blk_alloc_devt(struct hd_struct *part, dev_t *devt)
 	int idx;
 
 	/* in consecutive minor range? */
-	if (part->partno < disk->minors) {
-		*devt = MKDEV(disk->major, disk->first_minor + part->partno);
+	if (part->bdev->bd_partno < disk->minors) {
+		*devt = MKDEV(disk->major, disk->first_minor + part->bdev->bd_partno);
 		return 0;
 	}
 
@@ -864,7 +864,7 @@ void del_gendisk(struct gendisk *disk)
 	disk_part_iter_init(&piter, disk,
 			     DISK_PITER_INCL_EMPTY | DISK_PITER_REVERSE);
 	while ((part = disk_part_iter_next(&piter))) {
-		invalidate_partition(disk, part->partno);
+		invalidate_partition(disk, part->bdev->bd_partno);
 		delete_partition(part);
 	}
 	disk_part_iter_exit(&piter);
@@ -1008,7 +1008,7 @@ void __init printk_all_partitions(void)
 			printk("%s%s %10llu %s %s", is_part0 ? "" : "  ",
 			       bdevt_str(part_devt(part), devt_buf),
 			       bdev_nr_sectors(part->bdev) >> 1,
-			       disk_name(disk, part->partno, name_buf),
+			       disk_name(disk, part->bdev->bd_partno, name_buf),
 			       part->bdev->bd_meta_info ?
 					part->bdev->bd_meta_info->uuid : "");
 			if (is_part0) {
@@ -1102,7 +1102,7 @@ static int show_partition(struct seq_file *seqf, void *v)
 		seq_printf(seqf, "%4d  %7d %10llu %s\n",
 			   MAJOR(part_devt(part)), MINOR(part_devt(part)),
 			   bdev_nr_sectors(part->bdev) >> 1,
-			   disk_name(sgp, part->partno, buf));
+			   disk_name(sgp, part->bdev->bd_partno, buf));
 	disk_part_iter_exit(&piter);
 
 	return 0;
@@ -1525,7 +1525,7 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 			   "%lu %u"
 			   "\n",
 			   MAJOR(part_devt(hd)), MINOR(part_devt(hd)),
-			   disk_name(gp, hd->partno, buf),
+			   disk_name(gp, hd->bdev->bd_partno, buf),
 			   stat.ios[STAT_READ],
 			   stat.merges[STAT_READ],
 			   stat.sectors[STAT_READ],
diff --git a/block/partitions/core.c b/block/partitions/core.c
index c2f6721633b8..6db9ca8b722d 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -184,7 +184,7 @@ static ssize_t part_partition_show(struct device *dev,
 {
 	struct hd_struct *p = dev_to_part(dev);
 
-	return sprintf(buf, "%d\n", p->partno);
+	return sprintf(buf, "%d\n", p->bdev->bd_partno);
 }
 
 static ssize_t part_start_show(struct device *dev,
@@ -274,7 +274,7 @@ static int part_uevent(struct device *dev, struct kobj_uevent_env *env)
 {
 	struct hd_struct *part = dev_to_part(dev);
 
-	add_uevent_var(env, "PARTN=%u", part->partno);
+	add_uevent_var(env, "PARTN=%u", part->bdev->bd_partno);
 	if (part->bdev->bd_meta_info && part->bdev->bd_meta_info->volname[0])
 		add_uevent_var(env, "PARTNAME=%s",
 			       part->bdev->bd_meta_info->volname);
@@ -298,7 +298,7 @@ void delete_partition(struct hd_struct *part)
 	struct disk_part_tbl *ptbl =
 		rcu_dereference_protected(disk->part_tbl, 1);
 
-	rcu_assign_pointer(ptbl->part[part->partno], NULL);
+	rcu_assign_pointer(ptbl->part[part->bdev->bd_partno], NULL);
 	rcu_assign_pointer(ptbl->last_lookup, NULL);
 
 	kobject_put(part->bdev->bd_holder_dir);
@@ -372,7 +372,6 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 
 	bdev->bd_start_sect = start;
 	bdev_set_nr_sectors(bdev, len);
-	p->partno = partno;
 	bdev->bd_read_only = get_disk_ro(disk);
 
 	if (info) {
@@ -445,7 +444,7 @@ static bool partition_overlaps(struct gendisk *disk, sector_t start,
 
 	disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY);
 	while ((part = disk_part_iter_next(&piter))) {
-		if (part->partno == skip_partno ||
+		if (part->bdev->bd_partno == skip_partno ||
 		    start >= part->bdev->bd_start_sect +
 			bdev_nr_sectors(part->bdev) ||
 		    start + length <= part->bdev->bd_start_sect)
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index fe6fee77e2b9..3c13d4708e3f 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -54,7 +54,6 @@ struct partition_meta_info {
 struct hd_struct {
 	struct block_device *bdev;
 	struct device __dev;
-	int partno;
 };
 
 /**
diff --git a/init/do_mounts.c b/init/do_mounts.c
index 368ccb718501..86bef93e72eb 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -136,7 +136,7 @@ static dev_t devt_from_partuuid(const char *uuid_str)
 		struct hd_struct *part;
 
 		part = disk_get_part(dev_to_disk(dev),
-				     dev_to_part(dev)->partno + offset);
+				     dev_to_part(dev)->bdev->bd_partno + offset);
 		if (part) {
 			devt = part_devt(part);
 			put_device(part_to_dev(part));
-- 
cgit v1.2.3


From ad1eaa5344b293552b6ba43f5709c76a9aa14d17 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 24 Nov 2020 09:52:59 +0100
Subject: block: switch disk_part_iter_* to use a struct block_device

Switch the partition iter infrastructure to iterate over block_device
references instead of hd_struct ones mostly used to get at the
block_device.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/genhd.c             | 59 ++++++++++++++++++++++++-----------------------
 block/partitions/core.c   | 13 +++++------
 drivers/s390/block/dasd.c |  8 +++----
 include/linux/genhd.h     |  4 ++--
 4 files changed, 42 insertions(+), 42 deletions(-)

(limited to 'include/linux')

diff --git a/block/genhd.c b/block/genhd.c
index 452f7c646e02..2d34dd2da4e9 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -244,7 +244,7 @@ EXPORT_SYMBOL_GPL(disk_part_iter_init);
  * CONTEXT:
  * Don't care.
  */
-struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter)
+struct block_device *disk_part_iter_next(struct disk_part_iter *piter)
 {
 	struct disk_part_tbl *ptbl;
 	int inc, end;
@@ -282,8 +282,9 @@ struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter)
 		      piter->idx == 0))
 			continue;
 
-		get_device(part_to_dev(part->bd_part));
-		piter->part = part->bd_part;
+		piter->part = bdgrab(part);
+		if (!piter->part)
+			continue;
 		piter->idx += inc;
 		break;
 	}
@@ -305,7 +306,8 @@ EXPORT_SYMBOL_GPL(disk_part_iter_next);
  */
 void disk_part_iter_exit(struct disk_part_iter *piter)
 {
-	disk_put_part(piter->part);
+	if (piter->part)
+		bdput(piter->part);
 	piter->part = NULL;
 }
 EXPORT_SYMBOL_GPL(disk_part_iter_exit);
@@ -346,7 +348,6 @@ struct block_device *disk_map_sector_rcu(struct gendisk *disk, sector_t sector)
 
 	for (i = 1; i < ptbl->len; i++) {
 		part = rcu_dereference(ptbl->part[i]);
-
 		if (part && sector_in_part(part, sector)) {
 			rcu_assign_pointer(ptbl->last_lookup, part);
 			goto out_unlock;
@@ -647,7 +648,7 @@ static void register_disk(struct device *parent, struct gendisk *disk,
 {
 	struct device *ddev = disk_to_dev(disk);
 	struct disk_part_iter piter;
-	struct hd_struct *part;
+	struct block_device *part;
 	int err;
 
 	ddev->parent = parent;
@@ -697,7 +698,7 @@ static void register_disk(struct device *parent, struct gendisk *disk,
 	/* announce possible partitions */
 	disk_part_iter_init(&piter, disk, 0);
 	while ((part = disk_part_iter_next(&piter)))
-		kobject_uevent(&part_to_dev(part)->kobj, KOBJ_ADD);
+		kobject_uevent(bdev_kobj(part), KOBJ_ADD);
 	disk_part_iter_exit(&piter);
 
 	if (disk->queue->backing_dev_info->dev) {
@@ -837,7 +838,7 @@ static void invalidate_partition(struct block_device *bdev)
 void del_gendisk(struct gendisk *disk)
 {
 	struct disk_part_iter piter;
-	struct hd_struct *part;
+	struct block_device *part;
 
 	might_sleep();
 
@@ -857,8 +858,8 @@ void del_gendisk(struct gendisk *disk)
 	disk_part_iter_init(&piter, disk,
 			     DISK_PITER_INCL_EMPTY | DISK_PITER_REVERSE);
 	while ((part = disk_part_iter_next(&piter))) {
-		invalidate_partition(part->bdev);
-		delete_partition(part);
+		invalidate_partition(part);
+		delete_partition(part->bd_part);
 	}
 	disk_part_iter_exit(&piter);
 
@@ -977,7 +978,7 @@ void __init printk_all_partitions(void)
 	while ((dev = class_dev_iter_next(&iter))) {
 		struct gendisk *disk = dev_to_disk(dev);
 		struct disk_part_iter piter;
-		struct hd_struct *part;
+		struct block_device *part;
 		char name_buf[BDEVNAME_SIZE];
 		char devt_buf[BDEVT_SIZE];
 
@@ -996,14 +997,14 @@ void __init printk_all_partitions(void)
 		 */
 		disk_part_iter_init(&piter, disk, DISK_PITER_INCL_PART0);
 		while ((part = disk_part_iter_next(&piter))) {
-			bool is_part0 = part == disk->part0->bd_part;
+			bool is_part0 = part == disk->part0;
 
 			printk("%s%s %10llu %s %s", is_part0 ? "" : "  ",
-			       bdevt_str(part_devt(part), devt_buf),
-			       bdev_nr_sectors(part->bdev) >> 1,
-			       disk_name(disk, part->bdev->bd_partno, name_buf),
-			       part->bdev->bd_meta_info ?
-					part->bdev->bd_meta_info->uuid : "");
+			       bdevt_str(part->bd_dev, devt_buf),
+			       bdev_nr_sectors(part) >> 1,
+			       disk_name(disk, part->bd_partno, name_buf),
+			       part->bd_meta_info ?
+					part->bd_meta_info->uuid : "");
 			if (is_part0) {
 				if (dev->parent && dev->parent->driver)
 					printk(" driver: %s\n",
@@ -1079,7 +1080,7 @@ static int show_partition(struct seq_file *seqf, void *v)
 {
 	struct gendisk *sgp = v;
 	struct disk_part_iter piter;
-	struct hd_struct *part;
+	struct block_device *part;
 	char buf[BDEVNAME_SIZE];
 
 	/* Don't show non-partitionable removeable devices or empty devices */
@@ -1093,9 +1094,9 @@ static int show_partition(struct seq_file *seqf, void *v)
 	disk_part_iter_init(&piter, sgp, DISK_PITER_INCL_PART0);
 	while ((part = disk_part_iter_next(&piter)))
 		seq_printf(seqf, "%4d  %7d %10llu %s\n",
-			   MAJOR(part_devt(part)), MINOR(part_devt(part)),
-			   bdev_nr_sectors(part->bdev) >> 1,
-			   disk_name(sgp, part->bdev->bd_partno, buf));
+			   MAJOR(part->bd_dev), MINOR(part->bd_dev),
+			   bdev_nr_sectors(part) >> 1,
+			   disk_name(sgp, part->bd_partno, buf));
 	disk_part_iter_exit(&piter);
 
 	return 0;
@@ -1489,7 +1490,7 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 {
 	struct gendisk *gp = v;
 	struct disk_part_iter piter;
-	struct hd_struct *hd;
+	struct block_device *hd;
 	char buf[BDEVNAME_SIZE];
 	unsigned int inflight;
 	struct disk_stats stat;
@@ -1504,11 +1505,11 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 
 	disk_part_iter_init(&piter, gp, DISK_PITER_INCL_EMPTY_PART0);
 	while ((hd = disk_part_iter_next(&piter))) {
-		part_stat_read_all(hd, &stat);
+		part_stat_read_all(hd->bd_part, &stat);
 		if (queue_is_mq(gp->queue))
-			inflight = blk_mq_in_flight(gp->queue, hd->bdev);
+			inflight = blk_mq_in_flight(gp->queue, hd);
 		else
-			inflight = part_in_flight(hd->bdev);
+			inflight = part_in_flight(hd);
 
 		seq_printf(seqf, "%4d %7d %s "
 			   "%lu %lu %lu %u "
@@ -1517,8 +1518,8 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 			   "%lu %lu %lu %u "
 			   "%lu %u"
 			   "\n",
-			   MAJOR(part_devt(hd)), MINOR(part_devt(hd)),
-			   disk_name(gp, hd->bdev->bd_partno, buf),
+			   MAJOR(hd->bd_dev), MINOR(hd->bd_dev),
+			   disk_name(gp, hd->bd_partno, buf),
 			   stat.ios[STAT_READ],
 			   stat.merges[STAT_READ],
 			   stat.sectors[STAT_READ],
@@ -1673,7 +1674,7 @@ static void set_disk_ro_uevent(struct gendisk *gd, int ro)
 void set_disk_ro(struct gendisk *disk, int flag)
 {
 	struct disk_part_iter piter;
-	struct hd_struct *part;
+	struct block_device *part;
 
 	if (disk->part0->bd_read_only != flag) {
 		set_disk_ro_uevent(disk, flag);
@@ -1682,7 +1683,7 @@ void set_disk_ro(struct gendisk *disk, int flag)
 
 	disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY);
 	while ((part = disk_part_iter_next(&piter)))
-		part->bdev->bd_read_only = flag;
+		part->bd_read_only = flag;
 	disk_part_iter_exit(&piter);
 }
 
diff --git a/block/partitions/core.c b/block/partitions/core.c
index 3d8243334c7c..4cb6df175f90 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -439,15 +439,14 @@ static bool partition_overlaps(struct gendisk *disk, sector_t start,
 		sector_t length, int skip_partno)
 {
 	struct disk_part_iter piter;
-	struct hd_struct *part;
+	struct block_device *part;
 	bool overlap = false;
 
 	disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY);
 	while ((part = disk_part_iter_next(&piter))) {
-		if (part->bdev->bd_partno == skip_partno ||
-		    start >= part->bdev->bd_start_sect +
-			bdev_nr_sectors(part->bdev) ||
-		    start + length <= part->bdev->bd_start_sect)
+		if (part->bd_partno == skip_partno ||
+		    start >= part->bd_start_sect + bdev_nr_sectors(part) ||
+		    start + length <= part->bd_start_sect)
 			continue;
 		overlap = true;
 		break;
@@ -568,7 +567,7 @@ static bool disk_unlock_native_capacity(struct gendisk *disk)
 int blk_drop_partitions(struct block_device *bdev)
 {
 	struct disk_part_iter piter;
-	struct hd_struct *part;
+	struct block_device *part;
 
 	if (bdev->bd_part_count)
 		return -EBUSY;
@@ -578,7 +577,7 @@ int blk_drop_partitions(struct block_device *bdev)
 
 	disk_part_iter_init(&piter, bdev->bd_disk, DISK_PITER_INCL_EMPTY);
 	while ((part = disk_part_iter_next(&piter)))
-		delete_partition(part);
+		delete_partition(part->bd_part);
 	disk_part_iter_exit(&piter);
 
 	return 0;
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index db24e04ee978..1825fa8d05a7 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -432,7 +432,7 @@ dasd_state_ready_to_online(struct dasd_device * device)
 {
 	struct gendisk *disk;
 	struct disk_part_iter piter;
-	struct hd_struct *part;
+	struct block_device *part;
 
 	device->state = DASD_STATE_ONLINE;
 	if (device->block) {
@@ -445,7 +445,7 @@ dasd_state_ready_to_online(struct dasd_device * device)
 		disk = device->block->bdev->bd_disk;
 		disk_part_iter_init(&piter, disk, DISK_PITER_INCL_PART0);
 		while ((part = disk_part_iter_next(&piter)))
-			kobject_uevent(&part_to_dev(part)->kobj, KOBJ_CHANGE);
+			kobject_uevent(bdev_kobj(part), KOBJ_CHANGE);
 		disk_part_iter_exit(&piter);
 	}
 	return 0;
@@ -459,7 +459,7 @@ static int dasd_state_online_to_ready(struct dasd_device *device)
 	int rc;
 	struct gendisk *disk;
 	struct disk_part_iter piter;
-	struct hd_struct *part;
+	struct block_device *part;
 
 	if (device->discipline->online_to_ready) {
 		rc = device->discipline->online_to_ready(device);
@@ -472,7 +472,7 @@ static int dasd_state_online_to_ready(struct dasd_device *device)
 		disk = device->block->bdev->bd_disk;
 		disk_part_iter_init(&piter, disk, DISK_PITER_INCL_PART0);
 		while ((part = disk_part_iter_next(&piter)))
-			kobject_uevent(&part_to_dev(part)->kobj, KOBJ_CHANGE);
+			kobject_uevent(bdev_kobj(part), KOBJ_CHANGE);
 		disk_part_iter_exit(&piter);
 	}
 	return 0;
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 3c13d4708e3f..cd23c80265b2 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -244,14 +244,14 @@ static inline void disk_put_part(struct hd_struct *part)
 
 struct disk_part_iter {
 	struct gendisk		*disk;
-	struct hd_struct	*part;
+	struct block_device	*part;
 	int			idx;
 	unsigned int		flags;
 };
 
 extern void disk_part_iter_init(struct disk_part_iter *piter,
 				 struct gendisk *disk, unsigned int flags);
-extern struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter);
+struct block_device *disk_part_iter_next(struct disk_part_iter *piter);
 extern void disk_part_iter_exit(struct disk_part_iter *piter);
 extern bool disk_has_partitions(struct gendisk *disk);
 
-- 
cgit v1.2.3


From 0d02129e76edf91cf04fabf1efbc3a9a1f1d729a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 27 Nov 2020 16:43:51 +0100
Subject: block: merge struct block_device and struct hd_struct

Instead of having two structures that represent each block device with
different life time rules, merge them into a single one.  This also
greatly simplifies the reference counting rules, as we can use the inode
reference count as the main reference count for the new struct
block_device, with the device model reference front ending it for device
model interaction.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-cgroup.c        |   8 ++--
 block/blk.h               |   2 +-
 block/genhd.c             |  90 +++++++++++------------------------
 block/partitions/core.c   | 116 ++++++++++++++++++----------------------------
 fs/block_dev.c            |   9 ----
 include/linux/blk_types.h |   8 +++-
 include/linux/blkdev.h    |   1 -
 include/linux/genhd.h     |  40 ++++------------
 init/do_mounts.c          |  21 ++++-----
 kernel/trace/blktrace.c   |  43 ++++-------------
 10 files changed, 108 insertions(+), 230 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 79aa96240cec..031114d454a6 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -820,9 +820,9 @@ static void blkcg_fill_root_iostats(void)
 
 	class_dev_iter_init(&iter, &block_class, NULL, &disk_type);
 	while ((dev = class_dev_iter_next(&iter))) {
-		struct gendisk *disk = dev_to_disk(dev);
-		struct hd_struct *part = disk_get_part(disk, 0);
-		struct blkcg_gq *blkg = blk_queue_root_blkg(disk->queue);
+		struct block_device *bdev = dev_to_bdev(dev);
+		struct blkcg_gq *blkg =
+			blk_queue_root_blkg(bdev->bd_disk->queue);
 		struct blkg_iostat tmp;
 		int cpu;
 
@@ -830,7 +830,7 @@ static void blkcg_fill_root_iostats(void)
 		for_each_possible_cpu(cpu) {
 			struct disk_stats *cpu_dkstats;
 
-			cpu_dkstats = per_cpu_ptr(part->bdev->bd_stats, cpu);
+			cpu_dkstats = per_cpu_ptr(bdev->bd_stats, cpu);
 			tmp.ios[BLKG_IOSTAT_READ] +=
 				cpu_dkstats->ios[STAT_READ];
 			tmp.ios[BLKG_IOSTAT_WRITE] +=
diff --git a/block/blk.h b/block/blk.h
index 9657c6da7c77..98f0b1ae2641 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -356,7 +356,7 @@ char *disk_name(struct gendisk *hd, int partno, char *buf);
 #define ADDPART_FLAG_NONE	0
 #define ADDPART_FLAG_RAID	1
 #define ADDPART_FLAG_WHOLEDISK	2
-void delete_partition(struct hd_struct *part);
+void delete_partition(struct block_device *part);
 int bdev_add_partition(struct block_device *bdev, int partno,
 		sector_t start, sector_t length);
 int bdev_del_partition(struct block_device *bdev, int partno);
diff --git a/block/genhd.c b/block/genhd.c
index 2d34dd2da4e9..0fabfc90b8e4 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -106,13 +106,14 @@ const char *bdevname(struct block_device *bdev, char *buf)
 }
 EXPORT_SYMBOL(bdevname);
 
-static void part_stat_read_all(struct hd_struct *part, struct disk_stats *stat)
+static void part_stat_read_all(struct block_device *part,
+		struct disk_stats *stat)
 {
 	int cpu;
 
 	memset(stat, 0, sizeof(struct disk_stats));
 	for_each_possible_cpu(cpu) {
-		struct disk_stats *ptr = per_cpu_ptr(part->bdev->bd_stats, cpu);
+		struct disk_stats *ptr = per_cpu_ptr(part->bd_stats, cpu);
 		int group;
 
 		for (group = 0; group < NR_STAT_GROUPS; group++) {
@@ -167,39 +168,6 @@ struct block_device *__disk_get_part(struct gendisk *disk, int partno)
 	return rcu_dereference(ptbl->part[partno]);
 }
 
-/**
- * disk_get_part - get partition
- * @disk: disk to look partition from
- * @partno: partition number
- *
- * Look for partition @partno from @disk.  If found, increment
- * reference count and return it.
- *
- * CONTEXT:
- * Don't care.
- *
- * RETURNS:
- * Pointer to the found partition on success, NULL if not found.
- */
-struct hd_struct *disk_get_part(struct gendisk *disk, int partno)
-{
-	struct block_device *bdev;
-	struct hd_struct *part;
-
-	rcu_read_lock();
-	bdev = __disk_get_part(disk, partno);
-	if (!bdev)
-		goto fail;
-	part = bdev->bd_part;
-	if (!kobject_get_unless_zero(&part_to_dev(part)->kobj))
-		goto fail;
-	rcu_read_unlock();
-	return part;
-fail:
-	rcu_read_unlock();
-	return NULL;
-}
-
 /**
  * disk_part_iter_init - initialize partition iterator
  * @piter: iterator to initialize
@@ -859,7 +827,7 @@ void del_gendisk(struct gendisk *disk)
 			     DISK_PITER_INCL_EMPTY | DISK_PITER_REVERSE);
 	while ((part = disk_part_iter_next(&piter))) {
 		invalidate_partition(part);
-		delete_partition(part->bd_part);
+		delete_partition(part);
 	}
 	disk_part_iter_exit(&piter);
 
@@ -952,13 +920,13 @@ void blk_request_module(dev_t devt)
  */
 struct block_device *bdget_disk(struct gendisk *disk, int partno)
 {
-	struct hd_struct *part;
 	struct block_device *bdev = NULL;
 
-	part = disk_get_part(disk, partno);
-	if (part)
-		bdev = bdget_part(part);
-	disk_put_part(part);
+	rcu_read_lock();
+	bdev = __disk_get_part(disk, partno);
+	if (bdev && !bdgrab(bdev))
+		bdev = NULL;
+	rcu_read_unlock();
 
 	return bdev;
 }
@@ -1175,24 +1143,22 @@ static ssize_t disk_ro_show(struct device *dev,
 ssize_t part_size_show(struct device *dev,
 		       struct device_attribute *attr, char *buf)
 {
-	struct hd_struct *p = dev_to_part(dev);
-
-	return sprintf(buf, "%llu\n", bdev_nr_sectors(p->bdev));
+	return sprintf(buf, "%llu\n", bdev_nr_sectors(dev_to_bdev(dev)));
 }
 
 ssize_t part_stat_show(struct device *dev,
 		       struct device_attribute *attr, char *buf)
 {
-	struct hd_struct *p = dev_to_part(dev);
-	struct request_queue *q = part_to_disk(p)->queue;
+	struct block_device *bdev = dev_to_bdev(dev);
+	struct request_queue *q = bdev->bd_disk->queue;
 	struct disk_stats stat;
 	unsigned int inflight;
 
-	part_stat_read_all(p, &stat);
+	part_stat_read_all(bdev, &stat);
 	if (queue_is_mq(q))
-		inflight = blk_mq_in_flight(q, p->bdev);
+		inflight = blk_mq_in_flight(q, bdev);
 	else
-		inflight = part_in_flight(p->bdev);
+		inflight = part_in_flight(bdev);
 
 	return sprintf(buf,
 		"%8lu %8lu %8llu %8u "
@@ -1227,14 +1193,14 @@ ssize_t part_stat_show(struct device *dev,
 ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr,
 			   char *buf)
 {
-	struct hd_struct *p = dev_to_part(dev);
-	struct request_queue *q = part_to_disk(p)->queue;
+	struct block_device *bdev = dev_to_bdev(dev);
+	struct request_queue *q = bdev->bd_disk->queue;
 	unsigned int inflight[2];
 
 	if (queue_is_mq(q))
-		blk_mq_in_flight_rw(q, p->bdev, inflight);
+		blk_mq_in_flight_rw(q, bdev, inflight);
 	else
-		part_in_flight_rw(p->bdev, inflight);
+		part_in_flight_rw(bdev, inflight);
 
 	return sprintf(buf, "%8u %8u\n", inflight[0], inflight[1]);
 }
@@ -1282,20 +1248,17 @@ static DEVICE_ATTR(badblocks, 0644, disk_badblocks_show, disk_badblocks_store);
 ssize_t part_fail_show(struct device *dev,
 		       struct device_attribute *attr, char *buf)
 {
-	struct hd_struct *p = dev_to_part(dev);
-
-	return sprintf(buf, "%d\n", p->bdev->bd_make_it_fail);
+	return sprintf(buf, "%d\n", dev_to_bdev(dev)->bd_make_it_fail);
 }
 
 ssize_t part_fail_store(struct device *dev,
 			struct device_attribute *attr,
 			const char *buf, size_t count)
 {
-	struct hd_struct *p = dev_to_part(dev);
 	int i;
 
 	if (count > 0 && sscanf(buf, "%d", &i) > 0)
-		p->bdev->bd_make_it_fail = i;
+		dev_to_bdev(dev)->bd_make_it_fail = i;
 
 	return count;
 }
@@ -1505,7 +1468,7 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 
 	disk_part_iter_init(&piter, gp, DISK_PITER_INCL_EMPTY_PART0);
 	while ((hd = disk_part_iter_next(&piter))) {
-		part_stat_read_all(hd->bd_part, &stat);
+		part_stat_read_all(hd, &stat);
 		if (queue_is_mq(gp->queue))
 			inflight = blk_mq_in_flight(gp->queue, hd);
 		else
@@ -1577,7 +1540,7 @@ dev_t blk_lookup_devt(const char *name, int partno)
 	class_dev_iter_init(&iter, &block_class, NULL, &disk_type);
 	while ((dev = class_dev_iter_next(&iter))) {
 		struct gendisk *disk = dev_to_disk(dev);
-		struct hd_struct *part;
+		struct block_device *part;
 
 		if (strcmp(dev_name(dev), name))
 			continue;
@@ -1590,13 +1553,12 @@ dev_t blk_lookup_devt(const char *name, int partno)
 				     MINOR(dev->devt) + partno);
 			break;
 		}
-		part = disk_get_part(disk, partno);
+		part = bdget_disk(disk, partno);
 		if (part) {
-			devt = part_devt(part);
-			disk_put_part(part);
+			devt = part->bd_dev;
+			bdput(part);
 			break;
 		}
-		disk_put_part(part);
 	}
 	class_dev_iter_exit(&iter);
 	return devt;
diff --git a/block/partitions/core.c b/block/partitions/core.c
index 4cb6df175f90..deca253583bd 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -182,44 +182,39 @@ static struct parsed_partitions *check_partition(struct gendisk *hd,
 static ssize_t part_partition_show(struct device *dev,
 				   struct device_attribute *attr, char *buf)
 {
-	struct hd_struct *p = dev_to_part(dev);
-
-	return sprintf(buf, "%d\n", p->bdev->bd_partno);
+	return sprintf(buf, "%d\n", dev_to_bdev(dev)->bd_partno);
 }
 
 static ssize_t part_start_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
 {
-	struct hd_struct *p = dev_to_part(dev);
-
-	return sprintf(buf, "%llu\n", p->bdev->bd_start_sect);
+	return sprintf(buf, "%llu\n", dev_to_bdev(dev)->bd_start_sect);
 }
 
 static ssize_t part_ro_show(struct device *dev,
 			    struct device_attribute *attr, char *buf)
 {
-	struct hd_struct *p = dev_to_part(dev);
-	return sprintf(buf, "%d\n", p->bdev->bd_read_only);
+	return sprintf(buf, "%d\n", dev_to_bdev(dev)->bd_read_only);
 }
 
 static ssize_t part_alignment_offset_show(struct device *dev,
 					  struct device_attribute *attr, char *buf)
 {
-	struct hd_struct *p = dev_to_part(dev);
+	struct block_device *bdev = dev_to_bdev(dev);
 
 	return sprintf(buf, "%u\n",
-		queue_limit_alignment_offset(&part_to_disk(p)->queue->limits,
-				p->bdev->bd_start_sect));
+		queue_limit_alignment_offset(&bdev->bd_disk->queue->limits,
+				bdev->bd_start_sect));
 }
 
 static ssize_t part_discard_alignment_show(struct device *dev,
 					   struct device_attribute *attr, char *buf)
 {
-	struct hd_struct *p = dev_to_part(dev);
+	struct block_device *bdev = dev_to_bdev(dev);
 
 	return sprintf(buf, "%u\n",
-		queue_limit_discard_alignment(&part_to_disk(p)->queue->limits,
-				p->bdev->bd_start_sect));
+		queue_limit_discard_alignment(&bdev->bd_disk->queue->limits,
+				bdev->bd_start_sect));
 }
 
 static DEVICE_ATTR(partition, 0444, part_partition_show, NULL);
@@ -264,20 +259,17 @@ static const struct attribute_group *part_attr_groups[] = {
 
 static void part_release(struct device *dev)
 {
-	struct hd_struct *p = dev_to_part(dev);
-
 	blk_free_devt(dev->devt);
-	bdput(p->bdev);
+	bdput(dev_to_bdev(dev));
 }
 
 static int part_uevent(struct device *dev, struct kobj_uevent_env *env)
 {
-	struct hd_struct *part = dev_to_part(dev);
+	struct block_device *part = dev_to_bdev(dev);
 
-	add_uevent_var(env, "PARTN=%u", part->bdev->bd_partno);
-	if (part->bdev->bd_meta_info && part->bdev->bd_meta_info->volname[0])
-		add_uevent_var(env, "PARTNAME=%s",
-			       part->bdev->bd_meta_info->volname);
+	add_uevent_var(env, "PARTN=%u", part->bd_partno);
+	if (part->bd_meta_info && part->bd_meta_info->volname[0])
+		add_uevent_var(env, "PARTNAME=%s", part->bd_meta_info->volname);
 	return 0;
 }
 
@@ -292,25 +284,25 @@ struct device_type part_type = {
  * Must be called either with bd_mutex held, before a disk can be opened or
  * after all disk users are gone.
  */
-void delete_partition(struct hd_struct *part)
+void delete_partition(struct block_device *part)
 {
-	struct gendisk *disk = part_to_disk(part);
+	struct gendisk *disk = part->bd_disk;
 	struct disk_part_tbl *ptbl =
 		rcu_dereference_protected(disk->part_tbl, 1);
 
-	rcu_assign_pointer(ptbl->part[part->bdev->bd_partno], NULL);
+	rcu_assign_pointer(ptbl->part[part->bd_partno], NULL);
 	rcu_assign_pointer(ptbl->last_lookup, NULL);
 
-	kobject_put(part->bdev->bd_holder_dir);
-	device_del(part_to_dev(part));
+	kobject_put(part->bd_holder_dir);
+	device_del(&part->bd_device);
 
 	/*
 	 * Remove the block device from the inode hash, so that it cannot be
 	 * looked up any more even when openers still hold references.
 	 */
-	remove_inode_hash(part->bdev->bd_inode);
+	remove_inode_hash(part->bd_inode);
 
-	put_device(part_to_dev(part));
+	put_device(&part->bd_device);
 }
 
 static ssize_t whole_disk_show(struct device *dev,
@@ -324,11 +316,10 @@ static DEVICE_ATTR(whole_disk, 0444, whole_disk_show, NULL);
  * Must be called either with bd_mutex held, before a disk can be opened or
  * after all disk users are gone.
  */
-static struct hd_struct *add_partition(struct gendisk *disk, int partno,
+static struct block_device *add_partition(struct gendisk *disk, int partno,
 				sector_t start, sector_t len, int flags,
 				struct partition_meta_info *info)
 {
-	struct hd_struct *p;
 	dev_t devt = MKDEV(0, 0);
 	struct device *ddev = disk_to_dev(disk);
 	struct device *pdev;
@@ -367,9 +358,6 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 	if (!bdev)
 		return ERR_PTR(-ENOMEM);
 
-	p = bdev->bd_part;
-	pdev = part_to_dev(p);
-
 	bdev->bd_start_sect = start;
 	bdev_set_nr_sectors(bdev, len);
 	bdev->bd_read_only = get_disk_ro(disk);
@@ -381,6 +369,7 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 			goto out_bdput;
 	}
 
+	pdev = &bdev->bd_device;
 	dname = dev_name(ddev);
 	if (isdigit(dname[strlen(dname) - 1]))
 		dev_set_name(pdev, "%sp%d", dname, partno);
@@ -422,7 +411,7 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 	/* suppress uevent if the disk suppresses it */
 	if (!dev_get_uevent_suppress(ddev))
 		kobject_uevent(&pdev->kobj, KOBJ_ADD);
-	return p;
+	return bdev;
 
 out_bdput:
 	bdput(bdev);
@@ -459,7 +448,7 @@ static bool partition_overlaps(struct gendisk *disk, sector_t start,
 int bdev_add_partition(struct block_device *bdev, int partno,
 		sector_t start, sector_t length)
 {
-	struct hd_struct *part;
+	struct block_device *part;
 
 	mutex_lock(&bdev->bd_mutex);
 	if (partition_overlaps(bdev->bd_disk, start, length, -1)) {
@@ -475,76 +464,59 @@ int bdev_add_partition(struct block_device *bdev, int partno,
 
 int bdev_del_partition(struct block_device *bdev, int partno)
 {
-	struct block_device *bdevp;
-	struct hd_struct *part = NULL;
+	struct block_device *part;
 	int ret;
 
-	bdevp = bdget_disk(bdev->bd_disk, partno);
-	if (!bdevp)
+	part = bdget_disk(bdev->bd_disk, partno);
+	if (!part)
 		return -ENXIO;
 
-	mutex_lock(&bdevp->bd_mutex);
+	mutex_lock(&part->bd_mutex);
 	mutex_lock_nested(&bdev->bd_mutex, 1);
 
-	ret = -ENXIO;
-	part = disk_get_part(bdev->bd_disk, partno);
-	if (!part)
-		goto out_unlock;
-
 	ret = -EBUSY;
-	if (bdevp->bd_openers)
+	if (part->bd_openers)
 		goto out_unlock;
 
-	sync_blockdev(bdevp);
-	invalidate_bdev(bdevp);
+	sync_blockdev(part);
+	invalidate_bdev(part);
 
 	delete_partition(part);
 	ret = 0;
 out_unlock:
 	mutex_unlock(&bdev->bd_mutex);
-	mutex_unlock(&bdevp->bd_mutex);
-	bdput(bdevp);
-	if (part)
-		disk_put_part(part);
+	mutex_unlock(&part->bd_mutex);
+	bdput(part);
 	return ret;
 }
 
 int bdev_resize_partition(struct block_device *bdev, int partno,
 		sector_t start, sector_t length)
 {
-	struct block_device *bdevp;
-	struct hd_struct *part;
+	struct block_device *part;
 	int ret = 0;
 
-	part = disk_get_part(bdev->bd_disk, partno);
+	part = bdget_disk(bdev->bd_disk, partno);
 	if (!part)
 		return -ENXIO;
 
-	ret = -ENOMEM;
-	bdevp = bdget_part(part);
-	if (!bdevp)
-		goto out_put_part;
-
-	mutex_lock(&bdevp->bd_mutex);
+	mutex_lock(&part->bd_mutex);
 	mutex_lock_nested(&bdev->bd_mutex, 1);
-
 	ret = -EINVAL;
-	if (start != part->bdev->bd_start_sect)
+	if (start != part->bd_start_sect)
 		goto out_unlock;
 
 	ret = -EBUSY;
 	if (partition_overlaps(bdev->bd_disk, start, length, partno))
 		goto out_unlock;
 
-	bdev_set_nr_sectors(bdevp, length);
+	bdev_set_nr_sectors(part, length);
 
 	ret = 0;
 out_unlock:
-	mutex_unlock(&bdevp->bd_mutex);
+	mutex_unlock(&part->bd_mutex);
 	mutex_unlock(&bdev->bd_mutex);
-	bdput(bdevp);
-out_put_part:
-	disk_put_part(part);
+	bdput(part);
 	return ret;
 }
 
@@ -577,7 +549,7 @@ int blk_drop_partitions(struct block_device *bdev)
 
 	disk_part_iter_init(&piter, bdev->bd_disk, DISK_PITER_INCL_EMPTY);
 	while ((part = disk_part_iter_next(&piter)))
-		delete_partition(part->bd_part);
+		delete_partition(part);
 	disk_part_iter_exit(&piter);
 
 	return 0;
@@ -592,7 +564,7 @@ static bool blk_add_partition(struct gendisk *disk, struct block_device *bdev,
 {
 	sector_t size = state->parts[p].size;
 	sector_t from = state->parts[p].from;
-	struct hd_struct *part;
+	struct block_device *part;
 
 	if (!size)
 		return true;
@@ -632,7 +604,7 @@ static bool blk_add_partition(struct gendisk *disk, struct block_device *bdev,
 
 	if (IS_BUILTIN(CONFIG_BLK_DEV_MD) &&
 	    (state->parts[p].flags & ADDPART_FLAG_RAID))
-		md_autodetect_dev(part_to_dev(part)->devt);
+		md_autodetect_dev(part->bd_dev);
 
 	return true;
 }
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 61cf33b6284f..a9905d8fd02b 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -39,7 +39,6 @@
 
 struct bdev_inode {
 	struct block_device bdev;
-	struct hd_struct hd;
 	struct inode vfs_inode;
 };
 
@@ -887,9 +886,6 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno)
 		iput(inode);
 		return NULL;
 	}
-	bdev->bd_part = &BDEV_I(inode)->hd;
-	memset(bdev->bd_part, 0, sizeof(*bdev->bd_part));
-	bdev->bd_part->bdev = bdev;
 	return bdev;
 }
 
@@ -926,11 +922,6 @@ struct block_device *bdgrab(struct block_device *bdev)
 }
 EXPORT_SYMBOL(bdgrab);
 
-struct block_device *bdget_part(struct hd_struct *part)
-{
-	return bdget(part_devt(part));
-}
-
 long nr_blockdev_pages(void)
 {
 	struct inode *inode;
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 6edea5c16259..866f74261b3b 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -8,6 +8,7 @@
 
 #include <linux/types.h>
 #include <linux/bvec.h>
+#include <linux/device.h>
 #include <linux/ktime.h>
 
 struct bio_set;
@@ -30,6 +31,7 @@ struct block_device {
 	struct super_block *	bd_super;
 	struct mutex		bd_mutex;	/* open/close mutex */
 	void *			bd_claiming;
+	struct device		bd_device;
 	void *			bd_holder;
 	int			bd_holders;
 	bool			bd_write_holder;
@@ -38,7 +40,6 @@ struct block_device {
 #endif
 	struct kobject		*bd_holder_dir;
 	u8			bd_partno;
-	struct hd_struct *	bd_part;
 	/* number of times partitions within this device have been opened. */
 	unsigned		bd_part_count;
 
@@ -61,8 +62,11 @@ struct block_device {
 #define bdev_whole(_bdev) \
 	((_bdev)->bd_disk->part0)
 
+#define dev_to_bdev(device) \
+	container_of((device), struct block_device, bd_device)
+
 #define bdev_kobj(_bdev) \
-	(&part_to_dev((_bdev)->bd_part)->kobj)
+	(&((_bdev)->bd_device.kobj))
 
 /*
  * Block error status values.  See block/blk-core:blk_errors for the details.
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 1d4be1fc6007..17cedf0dc83d 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1999,7 +1999,6 @@ void blkdev_put_no_open(struct block_device *bdev);
 struct block_device *bdev_alloc(struct gendisk *disk, u8 partno);
 void bdev_add(struct block_device *bdev, dev_t dev);
 struct block_device *I_BDEV(struct inode *inode);
-struct block_device *bdget_part(struct hd_struct *part);
 struct block_device *bdgrab(struct block_device *bdev);
 void bdput(struct block_device *);
 
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index cd23c80265b2..809aaa32d53c 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -19,12 +19,6 @@
 #include <linux/blk_types.h>
 #include <asm/local.h>
 
-#define dev_to_part(device)	container_of((device), struct hd_struct, __dev)
-#define part_to_dev(part)	(&((part)->__dev))
-
-#define dev_to_disk(device)	(dev_to_part(device)->bdev->bd_disk)
-#define disk_to_dev(disk)	(part_to_dev((disk)->part0->bd_part))
-
 extern const struct device_type disk_type;
 extern struct device_type part_type;
 extern struct class block_class;
@@ -51,11 +45,6 @@ struct partition_meta_info {
 	u8 volname[PARTITION_META_INFO_VOLNAMELTH];
 };
 
-struct hd_struct {
-	struct block_device *bdev;
-	struct device __dev;
-};
-
 /**
  * DOC: genhd capability flags
  *
@@ -190,19 +179,21 @@ struct gendisk {
 	struct lockdep_map lockdep_map;
 };
 
+/*
+ * The gendisk is refcounted by the part0 block_device, and the bd_device
+ * therein is also used for device model presentation in sysfs.
+ */
+#define dev_to_disk(device) \
+	(dev_to_bdev(device)->bd_disk)
+#define disk_to_dev(disk) \
+	(&((disk)->part0->bd_device))
+
 #if IS_REACHABLE(CONFIG_CDROM)
 #define disk_to_cdi(disk)	((disk)->cdi)
 #else
 #define disk_to_cdi(disk)	NULL
 #endif
 
-static inline struct gendisk *part_to_disk(struct hd_struct *part)
-{
-	if (unlikely(!part))
-		return NULL;
-	return part->bdev->bd_disk;
-}
-
 static inline int disk_max_parts(struct gendisk *disk)
 {
 	if (disk->flags & GENHD_FL_EXT_DEVT)
@@ -221,19 +212,6 @@ static inline dev_t disk_devt(struct gendisk *disk)
 	return MKDEV(disk->major, disk->first_minor);
 }
 
-static inline dev_t part_devt(struct hd_struct *part)
-{
-	return part_to_dev(part)->devt;
-}
-
-extern struct hd_struct *disk_get_part(struct gendisk *disk, int partno);
-
-static inline void disk_put_part(struct hd_struct *part)
-{
-	if (likely(part))
-		put_device(part_to_dev(part));
-}
-
 /*
  * Smarter partition iterator without context limits.
  */
diff --git a/init/do_mounts.c b/init/do_mounts.c
index 86bef93e72eb..a78e44ee6adb 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -76,11 +76,11 @@ struct uuidcmp {
  */
 static int match_dev_by_uuid(struct device *dev, const void *data)
 {
+	struct block_device *bdev = dev_to_bdev(dev);
 	const struct uuidcmp *cmp = data;
-	struct hd_struct *part = dev_to_part(dev);
 
-	if (!part->bdev->bd_meta_info ||
-	    strncasecmp(cmp->uuid, part->bdev->bd_meta_info->uuid, cmp->len))
+	if (!bdev->bd_meta_info ||
+	    strncasecmp(cmp->uuid, bdev->bd_meta_info->uuid, cmp->len))
 		return 0;
 	return 1;
 }
@@ -133,13 +133,13 @@ static dev_t devt_from_partuuid(const char *uuid_str)
 		 * Attempt to find the requested partition by adding an offset
 		 * to the partition number found by UUID.
 		 */
-		struct hd_struct *part;
+		struct block_device *part;
 
-		part = disk_get_part(dev_to_disk(dev),
-				     dev_to_part(dev)->bdev->bd_partno + offset);
+		part = bdget_disk(dev_to_disk(dev),
+				  dev_to_bdev(dev)->bd_partno + offset);
 		if (part) {
-			devt = part_devt(part);
-			put_device(part_to_dev(part));
+			devt = part->bd_dev;
+			bdput(part);
 		}
 	} else {
 		devt = dev->devt;
@@ -166,11 +166,10 @@ clear_root_wait:
  */
 static int match_dev_by_label(struct device *dev, const void *data)
 {
+	struct block_device *bdev = dev_to_bdev(dev);
 	const char *label = data;
-	struct hd_struct *part = dev_to_part(dev);
 
-	if (!part->bdev->bd_meta_info ||
-	    strcmp(label, part->bdev->bd_meta_info->volname))
+	if (!bdev->bd_meta_info || strcmp(label, bdev->bd_meta_info->volname))
 		return 0;
 	return 1;
 }
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 8a723a91ec5a..a482a37848bf 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -1810,30 +1810,15 @@ static ssize_t blk_trace_mask2str(char *buf, int mask)
 	return p - buf;
 }
 
-static struct request_queue *blk_trace_get_queue(struct block_device *bdev)
-{
-	if (bdev->bd_disk == NULL)
-		return NULL;
-
-	return bdev_get_queue(bdev);
-}
-
 static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
 					 struct device_attribute *attr,
 					 char *buf)
 {
-	struct block_device *bdev = bdget_part(dev_to_part(dev));
-	struct request_queue *q;
+	struct block_device *bdev = dev_to_bdev(dev);
+	struct request_queue *q = bdev_get_queue(bdev);
 	struct blk_trace *bt;
 	ssize_t ret = -ENXIO;
 
-	if (bdev == NULL)
-		goto out;
-
-	q = blk_trace_get_queue(bdev);
-	if (q == NULL)
-		goto out_bdput;
-
 	mutex_lock(&q->debugfs_mutex);
 
 	bt = rcu_dereference_protected(q->blk_trace,
@@ -1856,9 +1841,6 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
 
 out_unlock_bdev:
 	mutex_unlock(&q->debugfs_mutex);
-out_bdput:
-	bdput(bdev);
-out:
 	return ret;
 }
 
@@ -1866,8 +1848,8 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 					  struct device_attribute *attr,
 					  const char *buf, size_t count)
 {
-	struct block_device *bdev;
-	struct request_queue *q;
+	struct block_device *bdev = dev_to_bdev(dev);
+	struct request_queue *q = bdev_get_queue(bdev);
 	struct blk_trace *bt;
 	u64 value;
 	ssize_t ret = -EINVAL;
@@ -1883,17 +1865,10 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 				goto out;
 			value = ret;
 		}
-	} else if (kstrtoull(buf, 0, &value))
-		goto out;
-
-	ret = -ENXIO;
-	bdev = bdget_part(dev_to_part(dev));
-	if (bdev == NULL)
-		goto out;
-
-	q = blk_trace_get_queue(bdev);
-	if (q == NULL)
-		goto out_bdput;
+	} else {
+		if (kstrtoull(buf, 0, &value))
+			goto out;
+	}
 
 	mutex_lock(&q->debugfs_mutex);
 
@@ -1931,8 +1906,6 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 
 out_unlock_bdev:
 	mutex_unlock(&q->debugfs_mutex);
-out_bdput:
-	bdput(bdev);
 out:
 	return ret ? ret : count;
 }
-- 
cgit v1.2.3


From c214550ff8eae9623605149fa4e3da3ba43df145 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Sun, 29 Nov 2020 22:05:50 +0200
Subject: net: delete __dev_getfirstbyhwtype

The last user of the RTNL brother of dev_getfirstbyhwtype (the latter
being synchronized under RCU) has been deleted in commit b4db2b35fc44
("afs: Use core kernel UUID generation").

Cc: Arnd Bergmann <arnd@arndb.de>
Cc: David Howells <dhowells@redhat.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://lore.kernel.org/r/20201129200550.2433401-1-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h |  1 -
 net/core/dev.c            | 13 -------------
 2 files changed, 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 8eeb73ac58bd..2e077e289e75 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2815,7 +2815,6 @@ unsigned long netdev_boot_base(const char *prefix, int unit);
 struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type,
 				       const char *hwaddr);
 struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type);
-struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type);
 void dev_add_pack(struct packet_type *pt);
 void dev_remove_pack(struct packet_type *pt);
 void __dev_remove_pack(struct packet_type *pt);
diff --git a/net/core/dev.c b/net/core/dev.c
index 51b263076124..b5130fd1cdaa 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1069,19 +1069,6 @@ struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type,
 }
 EXPORT_SYMBOL(dev_getbyhwaddr_rcu);
 
-struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type)
-{
-	struct net_device *dev;
-
-	ASSERT_RTNL();
-	for_each_netdev(net, dev)
-		if (dev->type == type)
-			return dev;
-
-	return NULL;
-}
-EXPORT_SYMBOL(__dev_getfirstbyhwtype);
-
 struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type)
 {
 	struct net_device *dev, *ret = NULL;
-- 
cgit v1.2.3


From 1967939462641d8b36bcb3fcf06d48e66cd67a4f Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sun, 29 Nov 2020 04:33:35 +0900
Subject: Compiler Attributes: remove CONFIG_ENABLE_MUST_CHECK

Revert commit cebc04ba9aeb ("add CONFIG_ENABLE_MUST_CHECK").

A lot of warn_unused_result warnings existed in 2006, but until now
they have been fixed thanks to people doing allmodconfig tests.

Our goal is to always enable __must_check where appropriate, so this
CONFIG option is no longer needed.

I see a lot of defconfig (arch/*/configs/*_defconfig) files having:

    # CONFIG_ENABLE_MUST_CHECK is not set

I did not touch them for now since it would be a big churn. If arch
maintainers want to clean them up, please go ahead.

While I was here, I also moved __must_check to compiler_attributes.h
from compiler_types.h

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Acked-by: Jason A. Donenfeld <Jason@zx2c4.com>
Acked-by: Nathan Chancellor <natechancellor@gmail.com>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
[Moved addition in compiler_attributes.h to keep it sorted]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 include/linux/compiler_attributes.h                 | 6 ++++++
 include/linux/compiler_types.h                      | 6 ------
 lib/Kconfig.debug                                   | 8 --------
 tools/testing/selftests/wireguard/qemu/debug.config | 1 -
 4 files changed, 6 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h
index b2a3f4f641a7..ea5e04e75845 100644
--- a/include/linux/compiler_attributes.h
+++ b/include/linux/compiler_attributes.h
@@ -272,6 +272,12 @@
  */
 #define __used                          __attribute__((__used__))
 
+/*
+ *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-warn_005funused_005fresult-function-attribute
+ * clang: https://clang.llvm.org/docs/AttributeReference.html#nodiscard-warn-unused-result
+ */
+#define __must_check                    __attribute__((__warn_unused_result__))
+
 /*
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-weak-function-attribute
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-weak-variable-attribute
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index ac3fa37a84f9..7ef20d1a6c28 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -110,12 +110,6 @@ struct ftrace_likely_data {
 	unsigned long			constant;
 };
 
-#ifdef CONFIG_ENABLE_MUST_CHECK
-#define __must_check		__attribute__((__warn_unused_result__))
-#else
-#define __must_check
-#endif
-
 #if defined(CC_USING_HOTPATCH)
 #define notrace			__attribute__((hotpatch(0, 0)))
 #elif defined(CC_USING_PATCHABLE_FUNCTION_ENTRY)
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index c789b39ed527..cb8ef4fd0d02 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -286,14 +286,6 @@ config GDB_SCRIPTS
 
 endif # DEBUG_INFO
 
-config ENABLE_MUST_CHECK
-	bool "Enable __must_check logic"
-	default y
-	help
-	  Enable the __must_check logic in the kernel build.  Disable this to
-	  suppress the "warning: ignoring return value of 'foo', declared with
-	  attribute warn_unused_result" messages.
-
 config FRAME_WARN
 	int "Warn for stack frames larger than"
 	range 0 8192
diff --git a/tools/testing/selftests/wireguard/qemu/debug.config b/tools/testing/selftests/wireguard/qemu/debug.config
index b50c2085c1ac..fe07d97df9fa 100644
--- a/tools/testing/selftests/wireguard/qemu/debug.config
+++ b/tools/testing/selftests/wireguard/qemu/debug.config
@@ -1,5 +1,4 @@
 CONFIG_LOCALVERSION="-debug"
-CONFIG_ENABLE_MUST_CHECK=y
 CONFIG_FRAME_POINTER=y
 CONFIG_STACK_VALIDATION=y
 CONFIG_DEBUG_KERNEL=y
-- 
cgit v1.2.3


From 1446e1df9eb183fdf81c3f0715402f1d7595d4cb Mon Sep 17 00:00:00 2001
From: Gabriel Krisman Bertazi <krisman@collabora.com>
Date: Fri, 27 Nov 2020 14:32:34 -0500
Subject: kernel: Implement selective syscall userspace redirection

Introduce a mechanism to quickly disable/enable syscall handling for a
specific process and redirect to userspace via SIGSYS.  This is useful
for processes with parts that require syscall redirection and parts that
don't, but who need to perform this boundary crossing really fast,
without paying the cost of a system call to reconfigure syscall handling
on each boundary transition.  This is particularly important for Windows
games running over Wine.

The proposed interface looks like this:

  prctl(PR_SET_SYSCALL_USER_DISPATCH, <op>, <off>, <length>, [selector])

The range [<offset>,<offset>+<length>) is a part of the process memory
map that is allowed to by-pass the redirection code and dispatch
syscalls directly, such that in fast paths a process doesn't need to
disable the trap nor the kernel has to check the selector.  This is
essential to return from SIGSYS to a blocked area without triggering
another SIGSYS from rt_sigreturn.

selector is an optional pointer to a char-sized userspace memory region
that has a key switch for the mechanism. This key switch is set to
either PR_SYS_DISPATCH_ON, PR_SYS_DISPATCH_OFF to enable and disable the
redirection without calling the kernel.

The feature is meant to be set per-thread and it is disabled on
fork/clone/execv.

Internally, this doesn't add overhead to the syscall hot path, and it
requires very little per-architecture support.  I avoided using seccomp,
even though it duplicates some functionality, due to previous feedback
that maybe it shouldn't mix with seccomp since it is not a security
mechanism.  And obviously, this should never be considered a security
mechanism, since any part of the program can by-pass it by using the
syscall dispatcher.

For the sysinfo benchmark, which measures the overhead added to
executing a native syscall that doesn't require interception, the
overhead using only the direct dispatcher region to issue syscalls is
pretty much irrelevant.  The overhead of using the selector goes around
40ns for a native (unredirected) syscall in my system, and it is (as
expected) dominated by the supervisor-mode user-address access.  In
fact, with SMAP off, the overhead is consistently less than 5ns on my
test box.

Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Andy Lutomirski <luto@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20201127193238.821364-4-krisman@collabora.com
---
 fs/exec.c                             |   3 +
 include/linux/sched.h                 |   2 +
 include/linux/syscall_user_dispatch.h |  40 +++++++++++++
 include/linux/thread_info.h           |   2 +
 include/uapi/linux/prctl.h            |   5 ++
 kernel/entry/Makefile                 |   2 +-
 kernel/entry/common.h                 |   7 +++
 kernel/entry/syscall_user_dispatch.c  | 104 ++++++++++++++++++++++++++++++++++
 kernel/fork.c                         |   1 +
 kernel/sys.c                          |   5 ++
 10 files changed, 170 insertions(+), 1 deletion(-)
 create mode 100644 include/linux/syscall_user_dispatch.h
 create mode 100644 kernel/entry/common.h
 create mode 100644 kernel/entry/syscall_user_dispatch.c

(limited to 'include/linux')

diff --git a/fs/exec.c b/fs/exec.c
index 547a2390baf5..aee36e5733ce 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -64,6 +64,7 @@
 #include <linux/compat.h>
 #include <linux/vmalloc.h>
 #include <linux/io_uring.h>
+#include <linux/syscall_user_dispatch.h>
 
 #include <linux/uaccess.h>
 #include <asm/mmu_context.h>
@@ -1302,6 +1303,8 @@ int begin_new_exec(struct linux_binprm * bprm)
 	flush_thread();
 	me->personality &= ~bprm->per_clear;
 
+	clear_syscall_work_syscall_user_dispatch(me);
+
 	/*
 	 * We have to apply CLOEXEC before we change whether the process is
 	 * dumpable (in setup_new_exec) to avoid a race with a process in userspace
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 063cd120b459..5a24a033b3f8 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -28,6 +28,7 @@
 #include <linux/sched/prio.h>
 #include <linux/sched/types.h>
 #include <linux/signal_types.h>
+#include <linux/syscall_user_dispatch.h>
 #include <linux/mm_types_task.h>
 #include <linux/task_io_accounting.h>
 #include <linux/posix-timers.h>
@@ -965,6 +966,7 @@ struct task_struct {
 	unsigned int			sessionid;
 #endif
 	struct seccomp			seccomp;
+	struct syscall_user_dispatch	syscall_dispatch;
 
 	/* Thread group tracking: */
 	u64				parent_exec_id;
diff --git a/include/linux/syscall_user_dispatch.h b/include/linux/syscall_user_dispatch.h
new file mode 100644
index 000000000000..a0ae443fb7df
--- /dev/null
+++ b/include/linux/syscall_user_dispatch.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020 Collabora Ltd.
+ */
+#ifndef _SYSCALL_USER_DISPATCH_H
+#define _SYSCALL_USER_DISPATCH_H
+
+#include <linux/thread_info.h>
+
+#ifdef CONFIG_GENERIC_ENTRY
+
+struct syscall_user_dispatch {
+	char __user	*selector;
+	unsigned long	offset;
+	unsigned long	len;
+	bool		on_dispatch;
+};
+
+int set_syscall_user_dispatch(unsigned long mode, unsigned long offset,
+			      unsigned long len, char __user *selector);
+
+#define clear_syscall_work_syscall_user_dispatch(tsk) \
+	clear_task_syscall_work(tsk, SYSCALL_USER_DISPATCH)
+
+#else
+struct syscall_user_dispatch {};
+
+static inline int set_syscall_user_dispatch(unsigned long mode, unsigned long offset,
+					    unsigned long len, char __user *selector)
+{
+	return -EINVAL;
+}
+
+static inline void clear_syscall_work_syscall_user_dispatch(struct task_struct *tsk)
+{
+}
+
+#endif /* CONFIG_GENERIC_ENTRY */
+
+#endif /* _SYSCALL_USER_DISPATCH_H */
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index ca80a214df09..c8a974cead73 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -42,6 +42,7 @@ enum syscall_work_bit {
 	SYSCALL_WORK_BIT_SYSCALL_TRACE,
 	SYSCALL_WORK_BIT_SYSCALL_EMU,
 	SYSCALL_WORK_BIT_SYSCALL_AUDIT,
+	SYSCALL_WORK_BIT_SYSCALL_USER_DISPATCH,
 };
 
 #define SYSCALL_WORK_SECCOMP		BIT(SYSCALL_WORK_BIT_SECCOMP)
@@ -49,6 +50,7 @@ enum syscall_work_bit {
 #define SYSCALL_WORK_SYSCALL_TRACE	BIT(SYSCALL_WORK_BIT_SYSCALL_TRACE)
 #define SYSCALL_WORK_SYSCALL_EMU	BIT(SYSCALL_WORK_BIT_SYSCALL_EMU)
 #define SYSCALL_WORK_SYSCALL_AUDIT	BIT(SYSCALL_WORK_BIT_SYSCALL_AUDIT)
+#define SYSCALL_WORK_SYSCALL_USER_DISPATCH BIT(SYSCALL_WORK_BIT_SYSCALL_USER_DISPATCH)
 #endif
 
 #include <asm/thread_info.h>
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index 7f0827705c9a..90deb41c8a34 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -247,4 +247,9 @@ struct prctl_mm_map {
 #define PR_SET_IO_FLUSHER		57
 #define PR_GET_IO_FLUSHER		58
 
+/* Dispatch syscalls to a userspace handler */
+#define PR_SET_SYSCALL_USER_DISPATCH	59
+# define PR_SYS_DISPATCH_OFF		0
+# define PR_SYS_DISPATCH_ON		1
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/kernel/entry/Makefile b/kernel/entry/Makefile
index 34c8a3f1c735..095c775e001e 100644
--- a/kernel/entry/Makefile
+++ b/kernel/entry/Makefile
@@ -9,5 +9,5 @@ KCOV_INSTRUMENT := n
 CFLAGS_REMOVE_common.o	 = -fstack-protector -fstack-protector-strong
 CFLAGS_common.o		+= -fno-stack-protector
 
-obj-$(CONFIG_GENERIC_ENTRY) 		+= common.o
+obj-$(CONFIG_GENERIC_ENTRY) 		+= common.o syscall_user_dispatch.o
 obj-$(CONFIG_KVM_XFER_TO_GUEST_WORK)	+= kvm.o
diff --git a/kernel/entry/common.h b/kernel/entry/common.h
new file mode 100644
index 000000000000..f6e6d02f07fe
--- /dev/null
+++ b/kernel/entry/common.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _COMMON_H
+#define _COMMON_H
+
+bool syscall_user_dispatch(struct pt_regs *regs);
+
+#endif
diff --git a/kernel/entry/syscall_user_dispatch.c b/kernel/entry/syscall_user_dispatch.c
new file mode 100644
index 000000000000..b0338a5625d9
--- /dev/null
+++ b/kernel/entry/syscall_user_dispatch.c
@@ -0,0 +1,104 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020 Collabora Ltd.
+ */
+#include <linux/sched.h>
+#include <linux/prctl.h>
+#include <linux/syscall_user_dispatch.h>
+#include <linux/uaccess.h>
+#include <linux/signal.h>
+#include <linux/elf.h>
+
+#include <linux/sched/signal.h>
+#include <linux/sched/task_stack.h>
+
+#include <asm/syscall.h>
+
+#include "common.h"
+
+static void trigger_sigsys(struct pt_regs *regs)
+{
+	struct kernel_siginfo info;
+
+	clear_siginfo(&info);
+	info.si_signo = SIGSYS;
+	info.si_code = SYS_USER_DISPATCH;
+	info.si_call_addr = (void __user *)KSTK_EIP(current);
+	info.si_errno = 0;
+	info.si_arch = syscall_get_arch(current);
+	info.si_syscall = syscall_get_nr(current, regs);
+
+	force_sig_info(&info);
+}
+
+bool syscall_user_dispatch(struct pt_regs *regs)
+{
+	struct syscall_user_dispatch *sd = &current->syscall_dispatch;
+	char state;
+
+	if (likely(instruction_pointer(regs) - sd->offset < sd->len))
+		return false;
+
+	if (unlikely(arch_syscall_is_vdso_sigreturn(regs)))
+		return false;
+
+	if (likely(sd->selector)) {
+		/*
+		 * access_ok() is performed once, at prctl time, when
+		 * the selector is loaded by userspace.
+		 */
+		if (unlikely(__get_user(state, sd->selector)))
+			do_exit(SIGSEGV);
+
+		if (likely(state == PR_SYS_DISPATCH_OFF))
+			return false;
+
+		if (state != PR_SYS_DISPATCH_ON)
+			do_exit(SIGSYS);
+	}
+
+	sd->on_dispatch = true;
+	syscall_rollback(current, regs);
+	trigger_sigsys(regs);
+
+	return true;
+}
+
+int set_syscall_user_dispatch(unsigned long mode, unsigned long offset,
+			      unsigned long len, char __user *selector)
+{
+	switch (mode) {
+	case PR_SYS_DISPATCH_OFF:
+		if (offset || len || selector)
+			return -EINVAL;
+		break;
+	case PR_SYS_DISPATCH_ON:
+		/*
+		 * Validate the direct dispatcher region just for basic
+		 * sanity against overflow and a 0-sized dispatcher
+		 * region.  If the user is able to submit a syscall from
+		 * an address, that address is obviously valid.
+		 */
+		if (offset && offset + len <= offset)
+			return -EINVAL;
+
+		if (selector && !access_ok(selector, sizeof(*selector)))
+			return -EFAULT;
+
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	current->syscall_dispatch.selector = selector;
+	current->syscall_dispatch.offset = offset;
+	current->syscall_dispatch.len = len;
+	current->syscall_dispatch.on_dispatch = false;
+
+	if (mode == PR_SYS_DISPATCH_ON)
+		set_syscall_work(SYSCALL_USER_DISPATCH);
+	else
+		clear_syscall_work(SYSCALL_USER_DISPATCH);
+
+	return 0;
+}
diff --git a/kernel/fork.c b/kernel/fork.c
index 02b689a23457..4a5ecb41f440 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -906,6 +906,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 	clear_user_return_notifier(tsk);
 	clear_tsk_need_resched(tsk);
 	set_task_stack_end_magic(tsk);
+	clear_syscall_work_syscall_user_dispatch(tsk);
 
 #ifdef CONFIG_STACKPROTECTOR
 	tsk->stack_canary = get_random_canary();
diff --git a/kernel/sys.c b/kernel/sys.c
index a730c03ee607..51f00fe20e4d 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -42,6 +42,7 @@
 #include <linux/syscore_ops.h>
 #include <linux/version.h>
 #include <linux/ctype.h>
+#include <linux/syscall_user_dispatch.h>
 
 #include <linux/compat.h>
 #include <linux/syscalls.h>
@@ -2530,6 +2531,10 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 
 		error = (current->flags & PR_IO_FLUSHER) == PR_IO_FLUSHER;
 		break;
+	case PR_SET_SYSCALL_USER_DISPATCH:
+		error = set_syscall_user_dispatch(arg2, arg3, arg4,
+						  (char __user *) arg5);
+		break;
 	default:
 		error = -EINVAL;
 		break;
-- 
cgit v1.2.3


From 11894468e39def270199f845b76df6c36d4ed133 Mon Sep 17 00:00:00 2001
From: Gabriel Krisman Bertazi <krisman@collabora.com>
Date: Fri, 27 Nov 2020 14:32:35 -0500
Subject: entry: Support Syscall User Dispatch on common syscall entry

Syscall User Dispatch (SUD) must take precedence over seccomp and
ptrace, since the use case is emulation (it can be invoked with a
different ABI) such that seccomp filtering by syscall number doesn't
make sense in the first place.  In addition, either the syscall is
dispatched back to userspace, in which case there is no resource for to
trace, or the syscall will be executed, and seccomp/ptrace will execute
next.

Since SUD runs before tracepoints, it needs to be a SYSCALL_WORK_EXIT as
well, just to prevent a trace exit event when dispatch was triggered.
For that, the on_syscall_dispatch() examines context to skip the
tracepoint, audit and other work.

[ tglx: Add a comment on the exit side ]

Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Andy Lutomirski <luto@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20201127193238.821364-5-krisman@collabora.com
---
 include/linux/entry-common.h |  2 ++
 kernel/entry/common.c        | 25 +++++++++++++++++++++++++
 2 files changed, 27 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index 49b26b216e4e..a6e98b4ba8e9 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -44,10 +44,12 @@
 				 SYSCALL_WORK_SYSCALL_TRACE |		\
 				 SYSCALL_WORK_SYSCALL_EMU |		\
 				 SYSCALL_WORK_SYSCALL_AUDIT |		\
+				 SYSCALL_WORK_SYSCALL_USER_DISPATCH |	\
 				 ARCH_SYSCALL_WORK_ENTER)
 #define SYSCALL_WORK_EXIT	(SYSCALL_WORK_SYSCALL_TRACEPOINT |	\
 				 SYSCALL_WORK_SYSCALL_TRACE |		\
 				 SYSCALL_WORK_SYSCALL_AUDIT |		\
+				 SYSCALL_WORK_SYSCALL_USER_DISPATCH |	\
 				 ARCH_SYSCALL_WORK_EXIT)
 
 /*
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 91e8fd50adf4..e661e70ffcf3 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -5,6 +5,8 @@
 #include <linux/livepatch.h>
 #include <linux/audit.h>
 
+#include "common.h"
+
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
 
@@ -46,6 +48,16 @@ static long syscall_trace_enter(struct pt_regs *regs, long syscall,
 {
 	long ret = 0;
 
+	/*
+	 * Handle Syscall User Dispatch.  This must comes first, since
+	 * the ABI here can be something that doesn't make sense for
+	 * other syscall_work features.
+	 */
+	if (work & SYSCALL_WORK_SYSCALL_USER_DISPATCH) {
+		if (syscall_user_dispatch(regs))
+			return -1L;
+	}
+
 	/* Handle ptrace */
 	if (work & (SYSCALL_WORK_SYSCALL_TRACE | SYSCALL_WORK_SYSCALL_EMU)) {
 		ret = arch_syscall_enter_tracehook(regs);
@@ -230,6 +242,19 @@ static void syscall_exit_work(struct pt_regs *regs, unsigned long work)
 {
 	bool step;
 
+	/*
+	 * If the syscall was rolled back due to syscall user dispatching,
+	 * then the tracers below are not invoked for the same reason as
+	 * the entry side was not invoked in syscall_trace_enter(): The ABI
+	 * of these syscalls is unknown.
+	 */
+	if (work & SYSCALL_WORK_SYSCALL_USER_DISPATCH) {
+		if (unlikely(current->syscall_dispatch.on_dispatch)) {
+			current->syscall_dispatch.on_dispatch = false;
+			return;
+		}
+	}
+
 	audit_syscall_exit(regs);
 
 	if (work & SYSCALL_WORK_SYSCALL_TRACEPOINT)
-- 
cgit v1.2.3


From 96e2fbccd0fc806364a964fdf072bfc858a66109 Mon Sep 17 00:00:00 2001
From: Sven Schnelle <svens@linux.ibm.com>
Date: Tue, 1 Dec 2020 15:27:53 +0100
Subject: entry_Add_enter_from_user_mode_wrapper

To be called from architecture specific code if the combo interfaces are
not suitable. It simply calls __enter_from_user_mode(). This way
__enter_from_user_mode will still be inlined because it is declared static
__always_inline.

[ tglx: Amend comments and move it to a different location in the header ]

Signed-off-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20201201142755.31931-4-svens@linux.ibm.com
---
 include/linux/entry-common.h | 24 +++++++++++++++++++++++-
 kernel/entry/common.c        | 16 ++++++----------
 2 files changed, 29 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index a6e98b4ba8e9..da60980a2e7b 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -101,6 +101,27 @@ static inline __must_check int arch_syscall_enter_tracehook(struct pt_regs *regs
 }
 #endif
 
+/**
+ * enter_from_user_mode - Establish state when coming from user mode
+ *
+ * Syscall/interrupt entry disables interrupts, but user mode is traced as
+ * interrupts enabled. Also with NO_HZ_FULL RCU might be idle.
+ *
+ * 1) Tell lockdep that interrupts are disabled
+ * 2) Invoke context tracking if enabled to reactivate RCU
+ * 3) Trace interrupts off state
+ *
+ * Invoked from architecture specific syscall entry code with interrupts
+ * disabled. The calling code has to be non-instrumentable. When the
+ * function returns all state is correct and interrupts are still
+ * disabled. The subsequent functions can be instrumented.
+ *
+ * This is invoked when there is architecture specific functionality to be
+ * done between establishing state and enabling interrupts. The caller must
+ * enable interrupts before invoking syscall_enter_from_user_mode_work().
+ */
+void enter_from_user_mode(struct pt_regs *regs);
+
 /**
  * syscall_enter_from_user_mode_prepare - Establish state and enable interrupts
  * @regs:	Pointer to currents pt_regs
@@ -110,7 +131,8 @@ static inline __must_check int arch_syscall_enter_tracehook(struct pt_regs *regs
  * function returns all state is correct, interrupts are enabled and the
  * subsequent functions can be instrumented.
  *
- * This handles lockdep, RCU (context tracking) and tracing state.
+ * This handles lockdep, RCU (context tracking) and tracing state, i.e.
+ * the functionality provided by enter_from_user_mode().
  *
  * This is invoked when there is extra architecture specific functionality
  * to be done between establishing state and handling user mode entry work.
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index dff07b4ce6ec..17b1e032afe7 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -10,16 +10,7 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
 
-/**
- * __enter_from_user_mode - Establish state when coming from user mode
- *
- * Syscall/interrupt entry disables interrupts, but user mode is traced as
- * interrupts enabled. Also with NO_HZ_FULL RCU might be idle.
- *
- * 1) Tell lockdep that interrupts are disabled
- * 2) Invoke context tracking if enabled to reactivate RCU
- * 3) Trace interrupts off state
- */
+/* See comment for enter_from_user_mode() in entry-common.h */
 static __always_inline void __enter_from_user_mode(struct pt_regs *regs)
 {
 	arch_check_user_regs(regs);
@@ -33,6 +24,11 @@ static __always_inline void __enter_from_user_mode(struct pt_regs *regs)
 	instrumentation_end();
 }
 
+void noinstr enter_from_user_mode(struct pt_regs *regs)
+{
+	__enter_from_user_mode(regs);
+}
+
 static inline void syscall_enter_audit(struct pt_regs *regs, long syscall)
 {
 	if (unlikely(audit_context())) {
-- 
cgit v1.2.3


From 310de1a678b2184c078c593dae343cb79c807f8d Mon Sep 17 00:00:00 2001
From: Sven Schnelle <svens@linux.ibm.com>
Date: Tue, 1 Dec 2020 15:27:54 +0100
Subject: entry: Add exit_to_user_mode() wrapper

Called from architecture specific code when syscall_exit_to_user_mode() is
not suitable. It simply calls __exit_to_user_mode().

This way __exit_to_user_mode() can still be inlined because it is declared
static __always_inline.

[ tglx: Amended comments and moved it to a different place in the header ]

Signed-off-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20201201142755.31931-5-svens@linux.ibm.com
---
 include/linux/entry-common.h | 23 +++++++++++++++++++++--
 kernel/entry/common.c        | 18 ++++++------------
 2 files changed, 27 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index da60980a2e7b..e370be8121aa 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -300,6 +300,25 @@ static inline void arch_syscall_exit_tracehook(struct pt_regs *regs, bool step)
 }
 #endif
 
+/**
+ * exit_to_user_mode - Fixup state when exiting to user mode
+ *
+ * Syscall/interrupt exit enables interrupts, but the kernel state is
+ * interrupts disabled when this is invoked. Also tell RCU about it.
+ *
+ * 1) Trace interrupts on state
+ * 2) Invoke context tracking if enabled to adjust RCU state
+ * 3) Invoke architecture specific last minute exit code, e.g. speculation
+ *    mitigations, etc.: arch_exit_to_user_mode()
+ * 4) Tell lockdep that interrupts are enabled
+ *
+ * Invoked from architecture specific code when syscall_exit_to_user_mode()
+ * is not suitable as the last step before returning to userspace. Must be
+ * invoked with interrupts disabled and the caller must be
+ * non-instrumentable.
+ */
+void exit_to_user_mode(void);
+
 /**
  * syscall_exit_to_user_mode - Handle work before returning to user mode
  * @regs:	Pointer to currents pt_regs
@@ -322,8 +341,8 @@ static inline void arch_syscall_exit_tracehook(struct pt_regs *regs, bool step)
  *	- Architecture specific one time work arch_exit_to_user_mode_prepare()
  *	- Address limit and lockdep checks
  *
- *  3) Final transition (lockdep, tracing, context tracking, RCU). Invokes
- *     arch_exit_to_user_mode() to handle e.g. speculation mitigations
+ *  3) Final transition (lockdep, tracing, context tracking, RCU), i.e. the
+ *     functionality in exit_to_user_mode().
  */
 void syscall_exit_to_user_mode(struct pt_regs *regs);
 
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 17b1e032afe7..48d30ce2e00e 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -117,18 +117,7 @@ noinstr void syscall_enter_from_user_mode_prepare(struct pt_regs *regs)
 	instrumentation_end();
 }
 
-/**
- * __exit_to_user_mode - Fixup state when exiting to user mode
- *
- * Syscall/interupt exit enables interrupts, but the kernel state is
- * interrupts disabled when this is invoked. Also tell RCU about it.
- *
- * 1) Trace interrupts on state
- * 2) Invoke context tracking if enabled to adjust RCU state
- * 3) Invoke architecture specific last minute exit code, e.g. speculation
- *    mitigations, etc.
- * 4) Tell lockdep that interrupts are enabled
- */
+/* See comment for exit_to_user_mode() in entry-common.h */
 static __always_inline void __exit_to_user_mode(void)
 {
 	instrumentation_begin();
@@ -141,6 +130,11 @@ static __always_inline void __exit_to_user_mode(void)
 	lockdep_hardirqs_on(CALLER_ADDR0);
 }
 
+void noinstr exit_to_user_mode(void)
+{
+	__exit_to_user_mode();
+}
+
 /* Workaround to allow gradual conversion of architecture code */
 void __weak arch_do_signal_or_restart(struct pt_regs *regs, bool has_signal) { }
 
-- 
cgit v1.2.3


From c6156e1da633f241e132eaea3b676d674376d770 Mon Sep 17 00:00:00 2001
From: Sven Schnelle <svens@linux.ibm.com>
Date: Tue, 1 Dec 2020 15:27:55 +0100
Subject: entry: Add syscall_exit_to_user_mode_work()

This is the same as syscall_exit_to_user_mode() but without calling
exit_to_user_mode(). This can be used if there is an architectural reason
to avoid the combo function, e.g. restarting a syscall without returning to
userspace. Before returning to user space the caller has to invoke
exit_to_user_mode().

[ tglx: Amended comments ]

Signed-off-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20201201142755.31931-6-svens@linux.ibm.com
---
 include/linux/entry-common.h | 20 ++++++++++++++++++++
 kernel/entry/common.c        | 14 ++++++++++++--
 2 files changed, 32 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index e370be8121aa..7c581a4c3797 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -316,9 +316,25 @@ static inline void arch_syscall_exit_tracehook(struct pt_regs *regs, bool step)
  * is not suitable as the last step before returning to userspace. Must be
  * invoked with interrupts disabled and the caller must be
  * non-instrumentable.
+ * The caller has to invoke syscall_exit_to_user_mode_work() before this.
  */
 void exit_to_user_mode(void);
 
+/**
+ * syscall_exit_to_user_mode_work - Handle work before returning to user mode
+ * @regs:	Pointer to currents pt_regs
+ *
+ * Same as step 1 and 2 of syscall_exit_to_user_mode() but without calling
+ * exit_to_user_mode() to perform the final transition to user mode.
+ *
+ * Calling convention is the same as for syscall_exit_to_user_mode() and it
+ * returns with all work handled and interrupts disabled. The caller must
+ * invoke exit_to_user_mode() before actually switching to user mode to
+ * make the final state transitions. Interrupts must stay disabled between
+ * return from this function and the invocation of exit_to_user_mode().
+ */
+void syscall_exit_to_user_mode_work(struct pt_regs *regs);
+
 /**
  * syscall_exit_to_user_mode - Handle work before returning to user mode
  * @regs:	Pointer to currents pt_regs
@@ -343,6 +359,10 @@ void exit_to_user_mode(void);
  *
  *  3) Final transition (lockdep, tracing, context tracking, RCU), i.e. the
  *     functionality in exit_to_user_mode().
+ *
+ * This is a combination of syscall_exit_to_user_mode_work() (1,2) and
+ * exit_to_user_mode(). This function is preferred unless there is a
+ * compelling architectural reason to use the seperate functions.
  */
 void syscall_exit_to_user_mode(struct pt_regs *regs);
 
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 48d30ce2e00e..d6b73937dab3 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -282,12 +282,22 @@ static void syscall_exit_to_user_mode_prepare(struct pt_regs *regs)
 		syscall_exit_work(regs, work);
 }
 
-__visible noinstr void syscall_exit_to_user_mode(struct pt_regs *regs)
+static __always_inline void __syscall_exit_to_user_mode_work(struct pt_regs *regs)
 {
-	instrumentation_begin();
 	syscall_exit_to_user_mode_prepare(regs);
 	local_irq_disable_exit_to_user();
 	exit_to_user_mode_prepare(regs);
+}
+
+void syscall_exit_to_user_mode_work(struct pt_regs *regs)
+{
+	__syscall_exit_to_user_mode_work(regs);
+}
+
+__visible noinstr void syscall_exit_to_user_mode(struct pt_regs *regs)
+{
+	instrumentation_begin();
+	__syscall_exit_to_user_mode_work(regs);
 	instrumentation_end();
 	__exit_to_user_mode();
 }
-- 
cgit v1.2.3


From 6b6667aa4d1e0866f00b62d35a9be3875c7551f8 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Tue, 24 Nov 2020 17:58:12 +0000
Subject: block: optimise for_each_bvec() advance

Because of how for_each_bvec() works it never advances across multiple
entries at a time, so bvec_iter_advance() is an overkill. Add
specialised bvec_iter_advance_single() that is faster. It also handles
zero-len bvecs, so can kill bvec_iter_skip_zero_bvec().

   text    data     bss     dec     hex filename
before:
  23977     805       0   24782    60ce lib/iov_iter.o
before, bvec_iter_advance() w/o WARN_ONCE()
  22886     600       0   23486    5bbe ./lib/iov_iter.o
after:
  21862     600       0   22462    57be lib/iov_iter.o

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/bvec.h | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bvec.h b/include/linux/bvec.h
index 2efec10bf792..ff832e698efb 100644
--- a/include/linux/bvec.h
+++ b/include/linux/bvec.h
@@ -121,18 +121,28 @@ static inline bool bvec_iter_advance(const struct bio_vec *bv,
 	return true;
 }
 
-static inline void bvec_iter_skip_zero_bvec(struct bvec_iter *iter)
+/*
+ * A simpler version of bvec_iter_advance(), @bytes should not span
+ * across multiple bvec entries, i.e. bytes <= bv[i->bi_idx].bv_len
+ */
+static inline void bvec_iter_advance_single(const struct bio_vec *bv,
+				struct bvec_iter *iter, unsigned int bytes)
 {
-	iter->bi_bvec_done = 0;
-	iter->bi_idx++;
+	unsigned int done = iter->bi_bvec_done + bytes;
+
+	if (done == bv[iter->bi_idx].bv_len) {
+		done = 0;
+		iter->bi_idx++;
+	}
+	iter->bi_bvec_done = done;
+	iter->bi_size -= bytes;
 }
 
 #define for_each_bvec(bvl, bio_vec, iter, start)			\
 	for (iter = (start);						\
 	     (iter).bi_size &&						\
 		((bvl = bvec_iter_bvec((bio_vec), (iter))), 1);	\
-	     (bvl).bv_len ? (void)bvec_iter_advance((bio_vec), &(iter),	\
-		     (bvl).bv_len) : bvec_iter_skip_zero_bvec(&(iter)))
+	     bvec_iter_advance_single((bio_vec), &(iter), (bvl).bv_len))
 
 /* for iterating one bio from start to end */
 #define BVEC_ITER_ALL_INIT (struct bvec_iter)				\
-- 
cgit v1.2.3


From 22b56c2964386ddced252be407150b22f85e209e Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Tue, 24 Nov 2020 17:58:13 +0000
Subject: bio: optimise bvec iteration

__bio_for_each_bvec(), __bio_for_each_segment() and bio_copy_data_iter()
fall under conditions of bvec_iter_advance_single(), which is a faster
and slimmer version of bvec_iter_advance(). Add
bio_advance_iter_single() and convert them.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio.c         |  4 ++--
 include/linux/bio.h | 17 +++++++++++++++--
 2 files changed, 17 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/block/bio.c b/block/bio.c
index ebb18136b86f..1f2cc1fbe283 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1212,8 +1212,8 @@ void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter,
 
 		flush_dcache_page(dst_bv.bv_page);
 
-		bio_advance_iter(src, src_iter, bytes);
-		bio_advance_iter(dst, dst_iter, bytes);
+		bio_advance_iter_single(src, src_iter, bytes);
+		bio_advance_iter_single(dst, dst_iter, bytes);
 	}
 }
 EXPORT_SYMBOL(bio_copy_data_iter);
diff --git a/include/linux/bio.h b/include/linux/bio.h
index ecf67108f091..1edda614f7ce 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -148,11 +148,24 @@ static inline void bio_advance_iter(const struct bio *bio,
 		/* TODO: It is reasonable to complete bio with error here. */
 }
 
+/* @bytes should be less or equal to bvec[i->bi_idx].bv_len */
+static inline void bio_advance_iter_single(const struct bio *bio,
+					   struct bvec_iter *iter,
+					   unsigned int bytes)
+{
+	iter->bi_sector += bytes >> 9;
+
+	if (bio_no_advance_iter(bio))
+		iter->bi_size -= bytes;
+	else
+		bvec_iter_advance_single(bio->bi_io_vec, iter, bytes);
+}
+
 #define __bio_for_each_segment(bvl, bio, iter, start)			\
 	for (iter = (start);						\
 	     (iter).bi_size &&						\
 		((bvl = bio_iter_iovec((bio), (iter))), 1);		\
-	     bio_advance_iter((bio), &(iter), (bvl).bv_len))
+	     bio_advance_iter_single((bio), &(iter), (bvl).bv_len))
 
 #define bio_for_each_segment(bvl, bio, iter)				\
 	__bio_for_each_segment(bvl, bio, iter, (bio)->bi_iter)
@@ -161,7 +174,7 @@ static inline void bio_advance_iter(const struct bio *bio,
 	for (iter = (start);						\
 	     (iter).bi_size &&						\
 		((bvl = mp_bvec_iter_bvec((bio)->bi_io_vec, (iter))), 1); \
-	     bio_advance_iter((bio), &(iter), (bvl).bv_len))
+	     bio_advance_iter_single((bio), &(iter), (bvl).bv_len))
 
 /* iterate over multi-page bvec */
 #define bio_for_each_bvec(bvl, bio, iter)			\
-- 
cgit v1.2.3


From 93b8959a0a8cf1b1a493efee9e8328681e111862 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Sun, 1 Nov 2020 15:24:41 -0500
Subject: NFS: More readdir cleanups

Remove the redundant caching of the credential in struct
nfs_open_dir_context.
Pass the buffer size as an argument to nfs_readdir_xdr_filler().

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Reviewed-by: Benjamin Coddington <bcodding@redhat.com>
Tested-by: Benjamin Coddington <bcodding@redhat.com>
Tested-by: Dave Wysochanski <dwysocha@redhat.com>
---
 fs/nfs/dir.c           | 25 +++++++++++--------------
 include/linux/nfs_fs.h |  1 -
 2 files changed, 11 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 438906dae083..bc366bd8e8f3 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -68,7 +68,7 @@ const struct address_space_operations nfs_dir_aops = {
 	.freepage = nfs_readdir_clear_array,
 };
 
-static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir, const struct cred *cred)
+static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir)
 {
 	struct nfs_inode *nfsi = NFS_I(dir);
 	struct nfs_open_dir_context *ctx;
@@ -78,7 +78,6 @@ static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir
 		ctx->attr_gencount = nfsi->attr_gencount;
 		ctx->dir_cookie = 0;
 		ctx->dup_cookie = 0;
-		ctx->cred = get_cred(cred);
 		spin_lock(&dir->i_lock);
 		if (list_empty(&nfsi->open_files) &&
 		    (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER))
@@ -96,7 +95,6 @@ static void put_nfs_open_dir_context(struct inode *dir, struct nfs_open_dir_cont
 	spin_lock(&dir->i_lock);
 	list_del(&ctx->list);
 	spin_unlock(&dir->i_lock);
-	put_cred(ctx->cred);
 	kfree(ctx);
 }
 
@@ -113,7 +111,7 @@ nfs_opendir(struct inode *inode, struct file *filp)
 
 	nfs_inc_stats(inode, NFSIOS_VFSOPEN);
 
-	ctx = alloc_nfs_open_dir_context(inode, current_cred());
+	ctx = alloc_nfs_open_dir_context(inode);
 	if (IS_ERR(ctx)) {
 		res = PTR_ERR(ctx);
 		goto out;
@@ -468,12 +466,12 @@ int nfs_readdir_search_array(nfs_readdir_descriptor_t *desc)
 }
 
 /* Fill a page with xdr information before transferring to the cache page */
-static
-int nfs_readdir_xdr_filler(struct page **pages, nfs_readdir_descriptor_t *desc,
-			struct nfs_entry *entry, struct file *file, struct inode *inode)
+static int nfs_readdir_xdr_filler(struct nfs_readdir_descriptor *desc,
+				  u64 cookie, struct page **pages,
+				  size_t bufsize)
 {
-	struct nfs_open_dir_context *ctx = file->private_data;
-	const struct cred *cred = ctx->cred;
+	struct file *file = desc->file;
+	struct inode *inode = file_inode(file);
 	unsigned long	timestamp, gencount;
 	int		error;
 
@@ -481,8 +479,8 @@ int nfs_readdir_xdr_filler(struct page **pages, nfs_readdir_descriptor_t *desc,
 	timestamp = jiffies;
 	gencount = nfs_inc_attr_generation_counter();
 	desc->dir_verifier = nfs_save_change_attribute(inode);
-	error = NFS_PROTO(inode)->readdir(file_dentry(file), cred, entry->cookie, pages,
-					  NFS_SERVER(inode)->dtsize, desc->plus);
+	error = NFS_PROTO(inode)->readdir(file_dentry(file), file->f_cred,
+					  cookie, pages, bufsize, desc->plus);
 	if (error < 0) {
 		/* We requested READDIRPLUS, but the server doesn't grok it */
 		if (error == -ENOTSUPP && desc->plus) {
@@ -764,7 +762,6 @@ int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page,
 {
 	struct page **pages;
 	struct nfs_entry entry;
-	struct file	*file = desc->file;
 	size_t array_size;
 	size_t dtsize = NFS_SERVER(inode)->dtsize;
 	int status = -ENOMEM;
@@ -791,8 +788,8 @@ int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page,
 
 	do {
 		unsigned int pglen;
-		status = nfs_readdir_xdr_filler(pages, desc, &entry, file, inode);
-
+		status = nfs_readdir_xdr_filler(desc, entry.cookie,
+						pages, dtsize);
 		if (status < 0)
 			break;
 
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index a2c6455ea3fa..dd6b463dda80 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -88,7 +88,6 @@ struct nfs_open_context {
 
 struct nfs_open_dir_context {
 	struct list_head list;
-	const struct cred *cred;
 	unsigned long attr_gencount;
 	__u64 dir_cookie;
 	__u64 dup_cookie;
-- 
cgit v1.2.3


From 82e22a5e6245873779db1607d3b0fec6f9ca07d0 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Mon, 2 Nov 2020 17:34:23 -0500
Subject: NFS: Allow the NFS generic code to pass in a verifier to readdir

If we're ever going to allow support for servers that use the readdir
verifier, then that use needs to be managed by the middle layers as
those need to be able to reject cookies from other verifiers.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Reviewed-by: Benjamin Coddington <bcodding@redhat.com>
Tested-by: Benjamin Coddington <bcodding@redhat.com>
Tested-by: Dave Wysochanski <dwysocha@redhat.com>
---
 fs/nfs/dir.c            | 23 ++++++++++++++++++-----
 fs/nfs/nfs3proc.c       | 35 +++++++++++++++++------------------
 fs/nfs/nfs4proc.c       | 36 +++++++++++++++++-------------------
 fs/nfs/proc.c           | 18 +++++++++---------
 include/linux/nfs_xdr.h | 17 +++++++++++++++--
 5 files changed, 76 insertions(+), 53 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index b226f6f3ae96..3ee0668a9719 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -469,8 +469,20 @@ static int nfs_readdir_xdr_filler(struct nfs_readdir_descriptor *desc,
 				  u64 cookie, struct page **pages,
 				  size_t bufsize)
 {
-	struct file *file = desc->file;
-	struct inode *inode = file_inode(file);
+	struct inode *inode = file_inode(desc->file);
+	__be32 verf_res[2];
+	struct nfs_readdir_arg arg = {
+		.dentry = file_dentry(desc->file),
+		.cred = desc->file->f_cred,
+		.verf = NFS_I(inode)->cookieverf,
+		.cookie = cookie,
+		.pages = pages,
+		.page_len = bufsize,
+		.plus = desc->plus,
+	};
+	struct nfs_readdir_res res = {
+		.verf = verf_res,
+	};
 	unsigned long	timestamp, gencount;
 	int		error;
 
@@ -478,20 +490,21 @@ static int nfs_readdir_xdr_filler(struct nfs_readdir_descriptor *desc,
 	timestamp = jiffies;
 	gencount = nfs_inc_attr_generation_counter();
 	desc->dir_verifier = nfs_save_change_attribute(inode);
-	error = NFS_PROTO(inode)->readdir(file_dentry(file), file->f_cred,
-					  cookie, pages, bufsize, desc->plus);
+	error = NFS_PROTO(inode)->readdir(&arg, &res);
 	if (error < 0) {
 		/* We requested READDIRPLUS, but the server doesn't grok it */
 		if (error == -ENOTSUPP && desc->plus) {
 			NFS_SERVER(inode)->caps &= ~NFS_CAP_READDIRPLUS;
 			clear_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags);
-			desc->plus = false;
+			desc->plus = arg.plus = false;
 			goto again;
 		}
 		goto error;
 	}
 	desc->timestamp = timestamp;
 	desc->gencount = gencount;
+	memcpy(NFS_I(inode)->cookieverf, res.verf,
+	       sizeof(NFS_I(inode)->cookieverf));
 error:
 	return error;
 }
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 6b66b73a50eb..5c4e23abc345 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -662,37 +662,36 @@ out:
  * Also note that this implementation handles both plain readdir and
  * readdirplus.
  */
-static int
-nfs3_proc_readdir(struct dentry *dentry, const struct cred *cred,
-		  u64 cookie, struct page **pages, unsigned int count, bool plus)
+static int nfs3_proc_readdir(struct nfs_readdir_arg *nr_arg,
+			     struct nfs_readdir_res *nr_res)
 {
-	struct inode		*dir = d_inode(dentry);
-	__be32			*verf = NFS_I(dir)->cookieverf;
+	struct inode		*dir = d_inode(nr_arg->dentry);
 	struct nfs3_readdirargs	arg = {
 		.fh		= NFS_FH(dir),
-		.cookie		= cookie,
-		.verf		= {verf[0], verf[1]},
-		.plus		= plus,
-		.count		= count,
-		.pages		= pages
+		.cookie		= nr_arg->cookie,
+		.plus		= nr_arg->plus,
+		.count		= nr_arg->page_len,
+		.pages		= nr_arg->pages
 	};
 	struct nfs3_readdirres	res = {
-		.verf		= verf,
-		.plus		= plus
+		.verf		= nr_res->verf,
+		.plus		= nr_arg->plus,
 	};
 	struct rpc_message	msg = {
 		.rpc_proc	= &nfs3_procedures[NFS3PROC_READDIR],
 		.rpc_argp	= &arg,
 		.rpc_resp	= &res,
-		.rpc_cred	= cred,
+		.rpc_cred	= nr_arg->cred,
 	};
 	int status = -ENOMEM;
 
-	if (plus)
+	if (nr_arg->plus)
 		msg.rpc_proc = &nfs3_procedures[NFS3PROC_READDIRPLUS];
+	if (arg.cookie)
+		memcpy(arg.verf, nr_arg->verf, sizeof(arg.verf));
 
-	dprintk("NFS call  readdir%s %d\n",
-			plus? "plus" : "", (unsigned int) cookie);
+	dprintk("NFS call  readdir%s %llu\n", nr_arg->plus ? "plus" : "",
+		(unsigned long long)nr_arg->cookie);
 
 	res.dir_attr = nfs_alloc_fattr();
 	if (res.dir_attr == NULL)
@@ -705,8 +704,8 @@ nfs3_proc_readdir(struct dentry *dentry, const struct cred *cred,
 
 	nfs_free_fattr(res.dir_attr);
 out:
-	dprintk("NFS reply readdir%s: %d\n",
-			plus? "plus" : "", status);
+	dprintk("NFS reply readdir%s: %d\n", nr_arg->plus ? "plus" : "",
+		status);
 	return status;
 }
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 66f1f4a5c74c..adcaba68eaed 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -4961,41 +4961,40 @@ static int nfs4_proc_mkdir(struct inode *dir, struct dentry *dentry,
 	return err;
 }
 
-static int _nfs4_proc_readdir(struct dentry *dentry, const struct cred *cred,
-		u64 cookie, struct page **pages, unsigned int count, bool plus)
+static int _nfs4_proc_readdir(struct nfs_readdir_arg *nr_arg,
+			      struct nfs_readdir_res *nr_res)
 {
-	struct inode		*dir = d_inode(dentry);
+	struct inode		*dir = d_inode(nr_arg->dentry);
 	struct nfs_server	*server = NFS_SERVER(dir);
 	struct nfs4_readdir_arg args = {
 		.fh = NFS_FH(dir),
-		.pages = pages,
+		.pages = nr_arg->pages,
 		.pgbase = 0,
-		.count = count,
-		.plus = plus,
+		.count = nr_arg->page_len,
+		.plus = nr_arg->plus,
 	};
 	struct nfs4_readdir_res res;
 	struct rpc_message msg = {
 		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READDIR],
 		.rpc_argp = &args,
 		.rpc_resp = &res,
-		.rpc_cred = cred,
+		.rpc_cred = nr_arg->cred,
 	};
 	int			status;
 
-	dprintk("%s: dentry = %pd2, cookie = %Lu\n", __func__,
-			dentry,
-			(unsigned long long)cookie);
+	dprintk("%s: dentry = %pd2, cookie = %llu\n", __func__,
+		nr_arg->dentry, (unsigned long long)nr_arg->cookie);
 	if (!(server->caps & NFS_CAP_SECURITY_LABEL))
 		args.bitmask = server->attr_bitmask_nl;
 	else
 		args.bitmask = server->attr_bitmask;
 
-	nfs4_setup_readdir(cookie, NFS_I(dir)->cookieverf, dentry, &args);
+	nfs4_setup_readdir(nr_arg->cookie, nr_arg->verf, nr_arg->dentry, &args);
 	res.pgbase = args.pgbase;
 	status = nfs4_call_sync(server->client, server, &msg, &args.seq_args,
 			&res.seq_res, 0);
 	if (status >= 0) {
-		memcpy(NFS_I(dir)->cookieverf, res.verifier.data, NFS4_VERIFIER_SIZE);
+		memcpy(nr_res->verf, res.verifier.data, NFS4_VERIFIER_SIZE);
 		status += args.pgbase;
 	}
 
@@ -5005,19 +5004,18 @@ static int _nfs4_proc_readdir(struct dentry *dentry, const struct cred *cred,
 	return status;
 }
 
-static int nfs4_proc_readdir(struct dentry *dentry, const struct cred *cred,
-		u64 cookie, struct page **pages, unsigned int count, bool plus)
+static int nfs4_proc_readdir(struct nfs_readdir_arg *arg,
+			     struct nfs_readdir_res *res)
 {
 	struct nfs4_exception exception = {
 		.interruptible = true,
 	};
 	int err;
 	do {
-		err = _nfs4_proc_readdir(dentry, cred, cookie,
-				pages, count, plus);
-		trace_nfs4_readdir(d_inode(dentry), err);
-		err = nfs4_handle_exception(NFS_SERVER(d_inode(dentry)), err,
-				&exception);
+		err = _nfs4_proc_readdir(arg, res);
+		trace_nfs4_readdir(d_inode(arg->dentry), err);
+		err = nfs4_handle_exception(NFS_SERVER(d_inode(arg->dentry)),
+					    err, &exception);
 	} while (exception.retry);
 	return err;
 }
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index 15c865cc837f..73ab7c59d3a7 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -499,26 +499,26 @@ nfs_proc_rmdir(struct inode *dir, const struct qstr *name)
  * sure it is syntactically correct; the entries itself are decoded
  * from nfs_readdir by calling the decode_entry function directly.
  */
-static int
-nfs_proc_readdir(struct dentry *dentry, const struct cred *cred,
-		 u64 cookie, struct page **pages, unsigned int count, bool plus)
+static int nfs_proc_readdir(struct nfs_readdir_arg *nr_arg,
+			    struct nfs_readdir_res *nr_res)
 {
-	struct inode		*dir = d_inode(dentry);
+	struct inode		*dir = d_inode(nr_arg->dentry);
 	struct nfs_readdirargs	arg = {
 		.fh		= NFS_FH(dir),
-		.cookie		= cookie,
-		.count		= count,
-		.pages		= pages,
+		.cookie		= nr_arg->cookie,
+		.count		= nr_arg->page_len,
+		.pages		= nr_arg->pages,
 	};
 	struct rpc_message	msg = {
 		.rpc_proc	= &nfs_procedures[NFSPROC_READDIR],
 		.rpc_argp	= &arg,
-		.rpc_cred	= cred,
+		.rpc_cred	= nr_arg->cred,
 	};
 	int			status;
 
-	dprintk("NFS call  readdir %d\n", (unsigned int)cookie);
+	dprintk("NFS call  readdir %llu\n", (unsigned long long)nr_arg->cookie);
 	status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
+	nr_res->verf[0] = nr_res->verf[1] = 0;
 
 	nfs_invalidate_atime(dir);
 
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index d63cb862d58e..3327239fa2f9 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -750,6 +750,20 @@ struct nfs_entry {
 	struct nfs_server *	server;
 };
 
+struct nfs_readdir_arg {
+	struct dentry		*dentry;
+	const struct cred	*cred;
+	__be32			*verf;
+	u64			cookie;
+	struct page		**pages;
+	unsigned int		page_len;
+	bool			plus;
+};
+
+struct nfs_readdir_res {
+	__be32			*verf;
+};
+
 /*
  * The following types are for NFSv2 only.
  */
@@ -1744,8 +1758,7 @@ struct nfs_rpc_ops {
 			    unsigned int, struct iattr *);
 	int	(*mkdir)   (struct inode *, struct dentry *, struct iattr *);
 	int	(*rmdir)   (struct inode *, const struct qstr *);
-	int	(*readdir) (struct dentry *, const struct cred *,
-			    u64, struct page **, unsigned int, bool);
+	int	(*readdir) (struct nfs_readdir_arg *, struct nfs_readdir_res *);
 	int	(*mknod)   (struct inode *, struct dentry *, struct iattr *,
 			    dev_t);
 	int	(*statfs)  (struct nfs_server *, struct nfs_fh *,
-- 
cgit v1.2.3


From b593c09f83a2732a0f0298c8f3468236a83cdd9f Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Mon, 2 Nov 2020 20:06:12 -0500
Subject: NFS: Improve handling of directory verifiers

If the server insists on using the readdir verifiers in order to allow
cookies to expire, then we should ensure that we cache the verifier
with the cookie, so that we can return an error if the application
tries to use the expired cookie.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Reviewed-by: Benjamin Coddington <bcodding@redhat.com>
Tested-by: Benjamin Coddington <bcodding@redhat.com>
Tested-by: Dave Wysochanski <dwysocha@redhat.com>
---
 fs/nfs/dir.c           | 35 +++++++++++++++++++++++------------
 fs/nfs/inode.c         |  7 -------
 include/linux/nfs_fs.h |  8 +++++++-
 3 files changed, 30 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 3b44bef3a1b4..454377228167 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -155,6 +155,7 @@ struct nfs_readdir_descriptor {
 	loff_t		current_index;
 	loff_t		prev_index;
 
+	__be32		verf[NFS_DIR_VERIFIER_SIZE];
 	unsigned long	dir_verifier;
 	unsigned long	timestamp;
 	unsigned long	gencount;
@@ -466,15 +467,15 @@ static int nfs_readdir_search_array(struct nfs_readdir_descriptor *desc)
 
 /* Fill a page with xdr information before transferring to the cache page */
 static int nfs_readdir_xdr_filler(struct nfs_readdir_descriptor *desc,
-				  u64 cookie, struct page **pages,
-				  size_t bufsize)
+				  __be32 *verf, u64 cookie,
+				  struct page **pages, size_t bufsize,
+				  __be32 *verf_res)
 {
 	struct inode *inode = file_inode(desc->file);
-	__be32 verf_res[2];
 	struct nfs_readdir_arg arg = {
 		.dentry = file_dentry(desc->file),
 		.cred = desc->file->f_cred,
-		.verf = NFS_I(inode)->cookieverf,
+		.verf = verf,
 		.cookie = cookie,
 		.pages = pages,
 		.page_len = bufsize,
@@ -503,8 +504,6 @@ static int nfs_readdir_xdr_filler(struct nfs_readdir_descriptor *desc,
 	}
 	desc->timestamp = timestamp;
 	desc->gencount = gencount;
-	memcpy(NFS_I(inode)->cookieverf, res.verf,
-	       sizeof(NFS_I(inode)->cookieverf));
 error:
 	return error;
 }
@@ -770,11 +769,13 @@ out_freepages:
 }
 
 static int nfs_readdir_xdr_to_array(struct nfs_readdir_descriptor *desc,
-				    struct page *page, struct inode *inode)
+				    struct page *page, __be32 *verf_arg,
+				    __be32 *verf_res)
 {
 	struct page **pages;
 	struct nfs_entry *entry;
 	size_t array_size;
+	struct inode *inode = file_inode(desc->file);
 	size_t dtsize = NFS_SERVER(inode)->dtsize;
 	int status = -ENOMEM;
 
@@ -801,8 +802,9 @@ static int nfs_readdir_xdr_to_array(struct nfs_readdir_descriptor *desc,
 
 	do {
 		unsigned int pglen;
-		status = nfs_readdir_xdr_filler(desc, entry->cookie,
-						pages, dtsize);
+		status = nfs_readdir_xdr_filler(desc, verf_arg, entry->cookie,
+						pages, dtsize,
+						verf_res);
 		if (status < 0)
 			break;
 
@@ -854,13 +856,15 @@ static int find_and_lock_cache_page(struct nfs_readdir_descriptor *desc)
 {
 	struct inode *inode = file_inode(desc->file);
 	struct nfs_inode *nfsi = NFS_I(inode);
+	__be32 verf[NFS_DIR_VERIFIER_SIZE];
 	int res;
 
 	desc->page = nfs_readdir_page_get_cached(desc);
 	if (!desc->page)
 		return -ENOMEM;
 	if (nfs_readdir_page_needs_filling(desc->page)) {
-		res = nfs_readdir_xdr_to_array(desc, desc->page, inode);
+		res = nfs_readdir_xdr_to_array(desc, desc->page,
+					       nfsi->cookieverf, verf);
 		if (res < 0) {
 			nfs_readdir_page_unlock_and_put_cached(desc);
 			if (res == -EBADCOOKIE || res == -ENOTSYNC) {
@@ -870,6 +874,7 @@ static int find_and_lock_cache_page(struct nfs_readdir_descriptor *desc)
 			}
 			return res;
 		}
+		memcpy(nfsi->cookieverf, verf, sizeof(nfsi->cookieverf));
 	}
 	res = nfs_readdir_search_array(desc);
 	if (res == 0) {
@@ -902,6 +907,7 @@ static int readdir_search_pagecache(struct nfs_readdir_descriptor *desc)
 static void nfs_do_filldir(struct nfs_readdir_descriptor *desc)
 {
 	struct file	*file = desc->file;
+	struct nfs_inode *nfsi = NFS_I(file_inode(file));
 	struct nfs_cache_array *array;
 	unsigned int i = 0;
 
@@ -915,6 +921,7 @@ static void nfs_do_filldir(struct nfs_readdir_descriptor *desc)
 			desc->eof = true;
 			break;
 		}
+		memcpy(desc->verf, nfsi->cookieverf, sizeof(desc->verf));
 		if (i < (array->size-1))
 			desc->dir_cookie = array->array[i+1].cookie;
 		else
@@ -949,8 +956,8 @@ static void nfs_do_filldir(struct nfs_readdir_descriptor *desc)
 static int uncached_readdir(struct nfs_readdir_descriptor *desc)
 {
 	struct page	*page = NULL;
+	__be32		verf[NFS_DIR_VERIFIER_SIZE];
 	int		status;
-	struct inode *inode = file_inode(desc->file);
 
 	dfprintk(DIRCACHE, "NFS: uncached_readdir() searching for cookie %Lu\n",
 			(unsigned long long)desc->dir_cookie);
@@ -967,7 +974,7 @@ static int uncached_readdir(struct nfs_readdir_descriptor *desc)
 	desc->duped = 0;
 
 	nfs_readdir_page_init_array(page, desc->dir_cookie);
-	status = nfs_readdir_xdr_to_array(desc, page, inode);
+	status = nfs_readdir_xdr_to_array(desc, page, desc->verf, verf);
 	if (status < 0)
 		goto out_release;
 
@@ -1023,6 +1030,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 	desc->dup_cookie = dir_ctx->dup_cookie;
 	desc->duped = dir_ctx->duped;
 	desc->attr_gencount = dir_ctx->attr_gencount;
+	memcpy(desc->verf, dir_ctx->verf, sizeof(desc->verf));
 	spin_unlock(&file->f_lock);
 
 	do {
@@ -1061,6 +1069,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 	dir_ctx->dup_cookie = desc->dup_cookie;
 	dir_ctx->duped = desc->duped;
 	dir_ctx->attr_gencount = desc->attr_gencount;
+	memcpy(dir_ctx->verf, desc->verf, sizeof(dir_ctx->verf));
 	spin_unlock(&file->f_lock);
 
 	kfree(desc);
@@ -1101,6 +1110,8 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence)
 			dir_ctx->dir_cookie = offset;
 		else
 			dir_ctx->dir_cookie = 0;
+		if (offset == 0)
+			memset(dir_ctx->verf, 0, sizeof(dir_ctx->verf));
 		dir_ctx->duped = 0;
 	}
 	spin_unlock(&filp->f_lock);
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index aa6493905bbe..9b765a900b28 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -229,7 +229,6 @@ static void nfs_zap_caches_locked(struct inode *inode)
 	nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
 	nfsi->attrtimeo_timestamp = jiffies;
 
-	memset(NFS_I(inode)->cookieverf, 0, sizeof(NFS_I(inode)->cookieverf));
 	if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) {
 		nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR
 					| NFS_INO_INVALID_DATA
@@ -1237,7 +1236,6 @@ EXPORT_SYMBOL_GPL(nfs_revalidate_inode);
 
 static int nfs_invalidate_mapping(struct inode *inode, struct address_space *mapping)
 {
-	struct nfs_inode *nfsi = NFS_I(inode);
 	int ret;
 
 	if (mapping->nrpages != 0) {
@@ -1250,11 +1248,6 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map
 		if (ret < 0)
 			return ret;
 	}
-	if (S_ISDIR(inode->i_mode)) {
-		spin_lock(&inode->i_lock);
-		memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
-		spin_unlock(&inode->i_lock);
-	}
 	nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE);
 	nfs_fscache_wait_on_invalidate(inode);
 
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index dd6b463dda80..681ed98e4ba8 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -45,6 +45,11 @@
  */
 #define NFS_RPC_SWAPFLAGS		(RPC_TASK_SWAPPER|RPC_TASK_ROOTCREDS)
 
+/*
+ * Size of the NFS directory verifier
+ */
+#define NFS_DIR_VERIFIER_SIZE		2
+
 /*
  * NFSv3/v4 Access mode cache entry
  */
@@ -89,6 +94,7 @@ struct nfs_open_context {
 struct nfs_open_dir_context {
 	struct list_head list;
 	unsigned long attr_gencount;
+	__be32	verf[NFS_DIR_VERIFIER_SIZE];
 	__u64 dir_cookie;
 	__u64 dup_cookie;
 	signed char duped;
@@ -156,7 +162,7 @@ struct nfs_inode {
 	 * This is the cookie verifier used for NFSv3 readdir
 	 * operations
 	 */
-	__be32			cookieverf[2];
+	__be32			cookieverf[NFS_DIR_VERIFIER_SIZE];
 
 	atomic_long_t		nrequests;
 	struct nfs_mds_commit_info commit_info;
-- 
cgit v1.2.3


From d5aa6b22e2258f05317313ecc02efbb988ed6d38 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Fri, 6 Nov 2020 16:33:38 -0500
Subject: SUNRPC: xprt_load_transport() needs to support the netid "rdma6"

According to RFC5666, the correct netid for an IPv6 addressed RDMA
transport is "rdma6", which we've supported as a mount option since
Linux-4.7. The problem is when we try to load the module "xprtrdma6",
that will fail, since there is no modulealias of that name.

Fixes: 181342c5ebe8 ("xprtrdma: Add rdma6 option to support NFS/RDMA IPv6")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 include/linux/sunrpc/xprt.h     |  1 +
 net/sunrpc/xprt.c               | 65 +++++++++++++++++++++++++++++++----------
 net/sunrpc/xprtrdma/module.c    |  1 +
 net/sunrpc/xprtrdma/transport.c |  1 +
 net/sunrpc/xprtsock.c           |  4 +++
 5 files changed, 56 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index a603d48d2b2c..3ac5037d1c3d 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -330,6 +330,7 @@ struct xprt_class {
 	struct rpc_xprt *	(*setup)(struct xprt_create *);
 	struct module		*owner;
 	char			name[32];
+	const char *		netid[];
 };
 
 /*
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index f6c17e75f20e..57f09ea3ef2a 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -151,31 +151,64 @@ out:
 }
 EXPORT_SYMBOL_GPL(xprt_unregister_transport);
 
+static void
+xprt_class_release(const struct xprt_class *t)
+{
+	module_put(t->owner);
+}
+
+static const struct xprt_class *
+xprt_class_find_by_netid_locked(const char *netid)
+{
+	const struct xprt_class *t;
+	unsigned int i;
+
+	list_for_each_entry(t, &xprt_list, list) {
+		for (i = 0; t->netid[i][0] != '\0'; i++) {
+			if (strcmp(t->netid[i], netid) != 0)
+				continue;
+			if (!try_module_get(t->owner))
+				continue;
+			return t;
+		}
+	}
+	return NULL;
+}
+
+static const struct xprt_class *
+xprt_class_find_by_netid(const char *netid)
+{
+	const struct xprt_class *t;
+
+	spin_lock(&xprt_list_lock);
+	t = xprt_class_find_by_netid_locked(netid);
+	if (!t) {
+		spin_unlock(&xprt_list_lock);
+		request_module("rpc%s", netid);
+		spin_lock(&xprt_list_lock);
+		t = xprt_class_find_by_netid_locked(netid);
+	}
+	spin_unlock(&xprt_list_lock);
+	return t;
+}
+
 /**
  * xprt_load_transport - load a transport implementation
- * @transport_name: transport to load
+ * @netid: transport to load
  *
  * Returns:
  * 0:		transport successfully loaded
  * -ENOENT:	transport module not available
  */
-int xprt_load_transport(const char *transport_name)
+int xprt_load_transport(const char *netid)
 {
-	struct xprt_class *t;
-	int result;
+	const struct xprt_class *t;
 
-	result = 0;
-	spin_lock(&xprt_list_lock);
-	list_for_each_entry(t, &xprt_list, list) {
-		if (strcmp(t->name, transport_name) == 0) {
-			spin_unlock(&xprt_list_lock);
-			goto out;
-		}
-	}
-	spin_unlock(&xprt_list_lock);
-	result = request_module("xprt%s", transport_name);
-out:
-	return result;
+	t = xprt_class_find_by_netid(netid);
+	if (!t)
+		return -ENOENT;
+	xprt_class_release(t);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(xprt_load_transport);
 
diff --git a/net/sunrpc/xprtrdma/module.c b/net/sunrpc/xprtrdma/module.c
index 620327c01302..45c5b41ac8dc 100644
--- a/net/sunrpc/xprtrdma/module.c
+++ b/net/sunrpc/xprtrdma/module.c
@@ -24,6 +24,7 @@ MODULE_DESCRIPTION("RPC/RDMA Transport");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_ALIAS("svcrdma");
 MODULE_ALIAS("xprtrdma");
+MODULE_ALIAS("rpcrdma6");
 
 static void __exit rpc_rdma_cleanup(void)
 {
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 8915e42240d3..035060c05fd5 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -768,6 +768,7 @@ static struct xprt_class xprt_rdma = {
 	.owner			= THIS_MODULE,
 	.ident			= XPRT_TRANSPORT_RDMA,
 	.setup			= xprt_setup_rdma,
+	.netid			= { "rdma", "rdma6", "" },
 };
 
 void xprt_rdma_cleanup(void)
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 7090bbee0ec5..c93ff70da3f9 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -3059,6 +3059,7 @@ static struct xprt_class	xs_local_transport = {
 	.owner		= THIS_MODULE,
 	.ident		= XPRT_TRANSPORT_LOCAL,
 	.setup		= xs_setup_local,
+	.netid		= { "" },
 };
 
 static struct xprt_class	xs_udp_transport = {
@@ -3067,6 +3068,7 @@ static struct xprt_class	xs_udp_transport = {
 	.owner		= THIS_MODULE,
 	.ident		= XPRT_TRANSPORT_UDP,
 	.setup		= xs_setup_udp,
+	.netid		= { "udp", "udp6", "" },
 };
 
 static struct xprt_class	xs_tcp_transport = {
@@ -3075,6 +3077,7 @@ static struct xprt_class	xs_tcp_transport = {
 	.owner		= THIS_MODULE,
 	.ident		= XPRT_TRANSPORT_TCP,
 	.setup		= xs_setup_tcp,
+	.netid		= { "tcp", "tcp6", "" },
 };
 
 static struct xprt_class	xs_bc_tcp_transport = {
@@ -3083,6 +3086,7 @@ static struct xprt_class	xs_bc_tcp_transport = {
 	.owner		= THIS_MODULE,
 	.ident		= XPRT_TRANSPORT_BC_TCP,
 	.setup		= xs_setup_bc_tcp,
+	.netid		= { "" },
 };
 
 /**
-- 
cgit v1.2.3


From 1fc5f13186440973e1aa1d85aa263326756af431 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Tue, 10 Nov 2020 09:41:21 -0500
Subject: SUNRPC: Add a helper to return the transport identifier given a netid

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 include/linux/sunrpc/xprt.h |  1 +
 net/sunrpc/xprt.c           | 25 +++++++++++++++++++++----
 2 files changed, 22 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index 3ac5037d1c3d..f7b75c72f80e 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -386,6 +386,7 @@ xprt_disable_swap(struct rpc_xprt *xprt)
 int			xprt_register_transport(struct xprt_class *type);
 int			xprt_unregister_transport(struct xprt_class *type);
 int			xprt_load_transport(const char *);
+int			xprt_find_transport_ident(const char *);
 void			xprt_wait_for_reply_request_def(struct rpc_task *task);
 void			xprt_wait_for_reply_request_rtt(struct rpc_task *task);
 void			xprt_wake_pending_tasks(struct rpc_xprt *xprt, int status);
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index bf490d0c98c6..23452f57d369 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -219,22 +219,39 @@ xprt_class_find_by_netid(const char *netid)
 }
 
 /**
- * xprt_load_transport - load a transport implementation
+ * xprt_find_transport_ident - convert a netid into a transport identifier
  * @netid: transport to load
  *
  * Returns:
- * 0:		transport successfully loaded
+ * > 0:		transport identifier
  * -ENOENT:	transport module not available
  */
-int xprt_load_transport(const char *netid)
+int xprt_find_transport_ident(const char *netid)
 {
 	const struct xprt_class *t;
+	int ret;
 
 	t = xprt_class_find_by_netid(netid);
 	if (!t)
 		return -ENOENT;
+	ret = t->ident;
 	xprt_class_release(t);
-	return 0;
+	return ret;
+}
+EXPORT_SYMBOL_GPL(xprt_find_transport_ident);
+
+/**
+ * xprt_load_transport - load a transport implementation
+ * @netid: transport to load
+ *
+ * Returns:
+ * 0:		transport successfully loaded
+ * -ENOENT:	transport module not available
+ */
+int xprt_load_transport(const char *netid)
+{
+	int ret = xprt_find_transport_ident(netid);
+	return ret < 0 ? ret : 0;
 }
 EXPORT_SYMBOL_GPL(xprt_load_transport);
 
-- 
cgit v1.2.3


From c87b056e58e71ba7a3f603700618f8da9742aa29 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Tue, 10 Nov 2020 10:32:14 -0500
Subject: SUNRPC: Remove unused function xprt_load_transport()

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 include/linux/sunrpc/xprt.h |  1 -
 net/sunrpc/xprt.c           | 15 ---------------
 2 files changed, 16 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index f7b75c72f80e..d2e97ee802af 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -385,7 +385,6 @@ xprt_disable_swap(struct rpc_xprt *xprt)
  */
 int			xprt_register_transport(struct xprt_class *type);
 int			xprt_unregister_transport(struct xprt_class *type);
-int			xprt_load_transport(const char *);
 int			xprt_find_transport_ident(const char *);
 void			xprt_wait_for_reply_request_def(struct rpc_task *task);
 void			xprt_wait_for_reply_request_rtt(struct rpc_task *task);
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 23452f57d369..691ccf8049a4 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -240,21 +240,6 @@ int xprt_find_transport_ident(const char *netid)
 }
 EXPORT_SYMBOL_GPL(xprt_find_transport_ident);
 
-/**
- * xprt_load_transport - load a transport implementation
- * @netid: transport to load
- *
- * Returns:
- * 0:		transport successfully loaded
- * -ENOENT:	transport module not available
- */
-int xprt_load_transport(const char *netid)
-{
-	int ret = xprt_find_transport_ident(netid);
-	return ret < 0 ? ret : 0;
-}
-EXPORT_SYMBOL_GPL(xprt_load_transport);
-
 static void xprt_clear_locked(struct rpc_xprt *xprt)
 {
 	xprt->snd_task = NULL;
-- 
cgit v1.2.3


From 8a6a5920d3286eb0eae9f36a4ec4fc9df511eccb Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <frederic@kernel.org>
Date: Wed, 2 Dec 2020 12:57:30 +0100
Subject: sched/vtime: Consolidate IRQ time accounting

The 3 architectures implementing CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
all have their own version of irq time accounting that dispatch the
cputime to the appropriate index: hardirq, softirq, system, idle,
guest... from an all-in-one function.

Instead of having these ad-hoc versions, move the cputime destination
dispatch decision to the core code and leave only the actual per-index
cputime accounting to the architecture.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20201202115732.27827-4-frederic@kernel.org
---
 arch/ia64/kernel/time.c    | 20 ++++++++++++-----
 arch/powerpc/kernel/time.c | 56 +++++++++++++++++++++++++++++++++-------------
 arch/s390/kernel/vtime.c   | 45 ++++++++++++++++++++++++++-----------
 include/linux/vtime.h      | 16 +++++--------
 kernel/sched/cputime.c     | 13 +++++++----
 5 files changed, 102 insertions(+), 48 deletions(-)

(limited to 'include/linux')

diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index 7abc5f37bfaf..733e0e3324b8 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -138,12 +138,8 @@ void vtime_account_kernel(struct task_struct *tsk)
 	struct thread_info *ti = task_thread_info(tsk);
 	__u64 stime = vtime_delta(tsk);
 
-	if ((tsk->flags & PF_VCPU) && !irq_count())
+	if (tsk->flags & PF_VCPU)
 		ti->gtime += stime;
-	else if (hardirq_count())
-		ti->hardirq_time += stime;
-	else if (in_serving_softirq())
-		ti->softirq_time += stime;
 	else
 		ti->stime += stime;
 }
@@ -156,6 +152,20 @@ void vtime_account_idle(struct task_struct *tsk)
 	ti->idle_time += vtime_delta(tsk);
 }
 
+void vtime_account_softirq(struct task_struct *tsk)
+{
+	struct thread_info *ti = task_thread_info(tsk);
+
+	ti->softirq_time += vtime_delta(tsk);
+}
+
+void vtime_account_hardirq(struct task_struct *tsk)
+{
+	struct thread_info *ti = task_thread_info(tsk);
+
+	ti->hardirq_time += vtime_delta(tsk);
+}
+
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 
 static irqreturn_t
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 74efe46f5532..cf3f8db7e0e3 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -311,12 +311,11 @@ static unsigned long vtime_delta_scaled(struct cpu_accounting_data *acct,
 	return stime_scaled;
 }
 
-static unsigned long vtime_delta(struct task_struct *tsk,
+static unsigned long vtime_delta(struct cpu_accounting_data *acct,
 				 unsigned long *stime_scaled,
 				 unsigned long *steal_time)
 {
 	unsigned long now, stime;
-	struct cpu_accounting_data *acct = get_accounting(tsk);
 
 	WARN_ON_ONCE(!irqs_disabled());
 
@@ -331,29 +330,30 @@ static unsigned long vtime_delta(struct task_struct *tsk,
 	return stime;
 }
 
+static void vtime_delta_kernel(struct cpu_accounting_data *acct,
+			       unsigned long *stime, unsigned long *stime_scaled)
+{
+	unsigned long steal_time;
+
+	*stime = vtime_delta(acct, stime_scaled, &steal_time);
+	*stime -= min(*stime, steal_time);
+	acct->steal_time += steal_time;
+}
+
 void vtime_account_kernel(struct task_struct *tsk)
 {
-	unsigned long stime, stime_scaled, steal_time;
 	struct cpu_accounting_data *acct = get_accounting(tsk);
+	unsigned long stime, stime_scaled;
 
-	stime = vtime_delta(tsk, &stime_scaled, &steal_time);
-
-	stime -= min(stime, steal_time);
-	acct->steal_time += steal_time;
+	vtime_delta_kernel(acct, &stime, &stime_scaled);
 
-	if ((tsk->flags & PF_VCPU) && !irq_count()) {
+	if (tsk->flags & PF_VCPU) {
 		acct->gtime += stime;
 #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
 		acct->utime_scaled += stime_scaled;
 #endif
 	} else {
-		if (hardirq_count())
-			acct->hardirq_time += stime;
-		else if (in_serving_softirq())
-			acct->softirq_time += stime;
-		else
-			acct->stime += stime;
-
+		acct->stime += stime;
 #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
 		acct->stime_scaled += stime_scaled;
 #endif
@@ -366,10 +366,34 @@ void vtime_account_idle(struct task_struct *tsk)
 	unsigned long stime, stime_scaled, steal_time;
 	struct cpu_accounting_data *acct = get_accounting(tsk);
 
-	stime = vtime_delta(tsk, &stime_scaled, &steal_time);
+	stime = vtime_delta(acct, &stime_scaled, &steal_time);
 	acct->idle_time += stime + steal_time;
 }
 
+static void vtime_account_irq_field(struct cpu_accounting_data *acct,
+				    unsigned long *field)
+{
+	unsigned long stime, stime_scaled;
+
+	vtime_delta_kernel(acct, &stime, &stime_scaled);
+	*field += stime;
+#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
+	acct->stime_scaled += stime_scaled;
+#endif
+}
+
+void vtime_account_softirq(struct task_struct *tsk)
+{
+	struct cpu_accounting_data *acct = get_accounting(tsk);
+	vtime_account_irq_field(acct, &acct->softirq_time);
+}
+
+void vtime_account_hardirq(struct task_struct *tsk)
+{
+	struct cpu_accounting_data *acct = get_accounting(tsk);
+	vtime_account_irq_field(acct, &acct->hardirq_time);
+}
+
 static void vtime_flush_scaled(struct task_struct *tsk,
 			       struct cpu_accounting_data *acct)
 {
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index ebd8e5655789..5aaa2ca6a928 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -222,31 +222,50 @@ void vtime_flush(struct task_struct *tsk)
 	S390_lowcore.avg_steal_timer = avg_steal;
 }
 
+static u64 vtime_delta(void)
+{
+	u64 timer = S390_lowcore.last_update_timer;
+
+	S390_lowcore.last_update_timer = get_vtimer();
+
+	return timer - S390_lowcore.last_update_timer;
+}
+
 /*
  * Update process times based on virtual cpu times stored by entry.S
  * to the lowcore fields user_timer, system_timer & steal_clock.
  */
 void vtime_account_kernel(struct task_struct *tsk)
 {
-	u64 timer;
-
-	timer = S390_lowcore.last_update_timer;
-	S390_lowcore.last_update_timer = get_vtimer();
-	timer -= S390_lowcore.last_update_timer;
+	u64 delta = vtime_delta();
 
-	if ((tsk->flags & PF_VCPU) && (irq_count() == 0))
-		S390_lowcore.guest_timer += timer;
-	else if (hardirq_count())
-		S390_lowcore.hardirq_timer += timer;
-	else if (in_serving_softirq())
-		S390_lowcore.softirq_timer += timer;
+	if (tsk->flags & PF_VCPU)
+		S390_lowcore.guest_timer += delta;
 	else
-		S390_lowcore.system_timer += timer;
+		S390_lowcore.system_timer += delta;
 
-	virt_timer_forward(timer);
+	virt_timer_forward(delta);
 }
 EXPORT_SYMBOL_GPL(vtime_account_kernel);
 
+void vtime_account_softirq(struct task_struct *tsk)
+{
+	u64 delta = vtime_delta();
+
+	S390_lowcore.softirq_timer += delta;
+
+	virt_timer_forward(delta);
+}
+
+void vtime_account_hardirq(struct task_struct *tsk)
+{
+	u64 delta = vtime_delta();
+
+	S390_lowcore.hardirq_timer += delta;
+
+	virt_timer_forward(delta);
+}
+
 /*
  * Sorted add to a list. List is linear searched until first bigger
  * element is found.
diff --git a/include/linux/vtime.h b/include/linux/vtime.h
index 2cdeca062db3..6c9867419615 100644
--- a/include/linux/vtime.h
+++ b/include/linux/vtime.h
@@ -83,16 +83,12 @@ static inline void vtime_init_idle(struct task_struct *tsk, int cpu) { }
 #endif
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-extern void vtime_account_irq_enter(struct task_struct *tsk);
-static inline void vtime_account_irq_exit(struct task_struct *tsk)
-{
-	/* On hard|softirq exit we always account to hard|softirq cputime */
-	vtime_account_kernel(tsk);
-}
+extern void vtime_account_irq(struct task_struct *tsk);
+extern void vtime_account_softirq(struct task_struct *tsk);
+extern void vtime_account_hardirq(struct task_struct *tsk);
 extern void vtime_flush(struct task_struct *tsk);
 #else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
-static inline void vtime_account_irq_enter(struct task_struct *tsk) { }
-static inline void vtime_account_irq_exit(struct task_struct *tsk) { }
+static inline void vtime_account_irq(struct task_struct *tsk) { }
 static inline void vtime_flush(struct task_struct *tsk) { }
 #endif
 
@@ -105,13 +101,13 @@ static inline void irqtime_account_irq(struct task_struct *tsk) { }
 
 static inline void account_irq_enter_time(struct task_struct *tsk)
 {
-	vtime_account_irq_enter(tsk);
+	vtime_account_irq(tsk);
 	irqtime_account_irq(tsk);
 }
 
 static inline void account_irq_exit_time(struct task_struct *tsk)
 {
-	vtime_account_irq_exit(tsk);
+	vtime_account_irq(tsk);
 	irqtime_account_irq(tsk);
 }
 
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 2783162542b1..02163d4260d7 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -417,13 +417,18 @@ void vtime_task_switch(struct task_struct *prev)
 }
 # endif
 
-void vtime_account_irq_enter(struct task_struct *tsk)
+void vtime_account_irq(struct task_struct *tsk)
 {
-	if (!IS_ENABLED(CONFIG_HAVE_VIRT_CPU_ACCOUNTING_IDLE) &&
-	    !in_interrupt() && is_idle_task(tsk))
+	if (hardirq_count()) {
+		vtime_account_hardirq(tsk);
+	} else if (in_serving_softirq()) {
+		vtime_account_softirq(tsk);
+	} else if (!IS_ENABLED(CONFIG_HAVE_VIRT_CPU_ACCOUNTING_IDLE) &&
+		   is_idle_task(tsk)) {
 		vtime_account_idle(tsk);
-	else
+	} else {
 		vtime_account_kernel(tsk);
+	}
 }
 
 void cputime_adjust(struct task_cputime *curr, struct prev_cputime *prev,
-- 
cgit v1.2.3


From d3759e7184f8f6187e62f8c4e7dcb1f6c47c075a Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <frederic@kernel.org>
Date: Wed, 2 Dec 2020 12:57:31 +0100
Subject: irqtime: Move irqtime entry accounting after irq offset
 incrementation

IRQ time entry is currently accounted before HARDIRQ_OFFSET or
SOFTIRQ_OFFSET are incremented. This is convenient to decide to which
index the cputime to account is dispatched.

Unfortunately it prevents tick_irq_enter() from being called under
HARDIRQ_OFFSET because tick_irq_enter() has to be called before the IRQ
entry accounting due to the necessary clock catch up. As a result we
don't benefit from appropriate lockdep coverage on tick_irq_enter().

To prepare for fixing this, move the IRQ entry cputime accounting after
the preempt offset is incremented. This requires the cputime dispatch
code to handle the extra offset.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20201202115732.27827-5-frederic@kernel.org
---
 include/linux/hardirq.h |  4 ++--
 include/linux/vtime.h   | 34 ++++++++++++++++++++++++----------
 kernel/sched/cputime.c  | 18 +++++++++++-------
 kernel/softirq.c        |  6 +++---
 4 files changed, 40 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index 754f67ac4326..7c9d6a2d7e90 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -32,9 +32,9 @@ static __always_inline void rcu_irq_enter_check_tick(void)
  */
 #define __irq_enter()					\
 	do {						\
-		account_irq_enter_time(current);	\
 		preempt_count_add(HARDIRQ_OFFSET);	\
 		lockdep_hardirq_enter();		\
+		account_hardirq_enter(current);		\
 	} while (0)
 
 /*
@@ -62,8 +62,8 @@ void irq_enter_rcu(void);
  */
 #define __irq_exit()					\
 	do {						\
+		account_hardirq_exit(current);		\
 		lockdep_hardirq_exit();			\
-		account_irq_exit_time(current);		\
 		preempt_count_sub(HARDIRQ_OFFSET);	\
 	} while (0)
 
diff --git a/include/linux/vtime.h b/include/linux/vtime.h
index 6c9867419615..041d6524d144 100644
--- a/include/linux/vtime.h
+++ b/include/linux/vtime.h
@@ -83,32 +83,46 @@ static inline void vtime_init_idle(struct task_struct *tsk, int cpu) { }
 #endif
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-extern void vtime_account_irq(struct task_struct *tsk);
+extern void vtime_account_irq(struct task_struct *tsk, unsigned int offset);
 extern void vtime_account_softirq(struct task_struct *tsk);
 extern void vtime_account_hardirq(struct task_struct *tsk);
 extern void vtime_flush(struct task_struct *tsk);
 #else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
-static inline void vtime_account_irq(struct task_struct *tsk) { }
+static inline void vtime_account_irq(struct task_struct *tsk, unsigned int offset) { }
+static inline void vtime_account_softirq(struct task_struct *tsk) { }
+static inline void vtime_account_hardirq(struct task_struct *tsk) { }
 static inline void vtime_flush(struct task_struct *tsk) { }
 #endif
 
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
-extern void irqtime_account_irq(struct task_struct *tsk);
+extern void irqtime_account_irq(struct task_struct *tsk, unsigned int offset);
 #else
-static inline void irqtime_account_irq(struct task_struct *tsk) { }
+static inline void irqtime_account_irq(struct task_struct *tsk, unsigned int offset) { }
 #endif
 
-static inline void account_irq_enter_time(struct task_struct *tsk)
+static inline void account_softirq_enter(struct task_struct *tsk)
 {
-	vtime_account_irq(tsk);
-	irqtime_account_irq(tsk);
+	vtime_account_irq(tsk, SOFTIRQ_OFFSET);
+	irqtime_account_irq(tsk, SOFTIRQ_OFFSET);
 }
 
-static inline void account_irq_exit_time(struct task_struct *tsk)
+static inline void account_softirq_exit(struct task_struct *tsk)
 {
-	vtime_account_irq(tsk);
-	irqtime_account_irq(tsk);
+	vtime_account_softirq(tsk);
+	irqtime_account_irq(tsk, 0);
+}
+
+static inline void account_hardirq_enter(struct task_struct *tsk)
+{
+	vtime_account_irq(tsk, HARDIRQ_OFFSET);
+	irqtime_account_irq(tsk, HARDIRQ_OFFSET);
+}
+
+static inline void account_hardirq_exit(struct task_struct *tsk)
+{
+	vtime_account_hardirq(tsk);
+	irqtime_account_irq(tsk, 0);
 }
 
 #endif /* _LINUX_KERNEL_VTIME_H */
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 02163d4260d7..5f611658eeab 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -44,12 +44,13 @@ static void irqtime_account_delta(struct irqtime *irqtime, u64 delta,
 }
 
 /*
- * Called before incrementing preempt_count on {soft,}irq_enter
+ * Called after incrementing preempt_count on {soft,}irq_enter
  * and before decrementing preempt_count on {soft,}irq_exit.
  */
-void irqtime_account_irq(struct task_struct *curr)
+void irqtime_account_irq(struct task_struct *curr, unsigned int offset)
 {
 	struct irqtime *irqtime = this_cpu_ptr(&cpu_irqtime);
+	unsigned int pc;
 	s64 delta;
 	int cpu;
 
@@ -59,6 +60,7 @@ void irqtime_account_irq(struct task_struct *curr)
 	cpu = smp_processor_id();
 	delta = sched_clock_cpu(cpu) - irqtime->irq_start_time;
 	irqtime->irq_start_time += delta;
+	pc = preempt_count() - offset;
 
 	/*
 	 * We do not account for softirq time from ksoftirqd here.
@@ -66,9 +68,9 @@ void irqtime_account_irq(struct task_struct *curr)
 	 * in that case, so as not to confuse scheduler with a special task
 	 * that do not consume any time, but still wants to run.
 	 */
-	if (hardirq_count())
+	if (pc & HARDIRQ_MASK)
 		irqtime_account_delta(irqtime, delta, CPUTIME_IRQ);
-	else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
+	else if ((pc & SOFTIRQ_OFFSET) && curr != this_cpu_ksoftirqd())
 		irqtime_account_delta(irqtime, delta, CPUTIME_SOFTIRQ);
 }
 
@@ -417,11 +419,13 @@ void vtime_task_switch(struct task_struct *prev)
 }
 # endif
 
-void vtime_account_irq(struct task_struct *tsk)
+void vtime_account_irq(struct task_struct *tsk, unsigned int offset)
 {
-	if (hardirq_count()) {
+	unsigned int pc = preempt_count() - offset;
+
+	if (pc & HARDIRQ_OFFSET) {
 		vtime_account_hardirq(tsk);
-	} else if (in_serving_softirq()) {
+	} else if (pc & SOFTIRQ_OFFSET) {
 		vtime_account_softirq(tsk);
 	} else if (!IS_ENABLED(CONFIG_HAVE_VIRT_CPU_ACCOUNTING_IDLE) &&
 		   is_idle_task(tsk)) {
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 617009ccd82c..b8f42b3ba8ca 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -315,10 +315,10 @@ asmlinkage __visible void __softirq_entry __do_softirq(void)
 	current->flags &= ~PF_MEMALLOC;
 
 	pending = local_softirq_pending();
-	account_irq_enter_time(current);
 
 	__local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
 	in_hardirq = lockdep_softirq_start();
+	account_softirq_enter(current);
 
 restart:
 	/* Reset the pending bitmask before enabling irqs */
@@ -365,8 +365,8 @@ restart:
 		wakeup_softirqd();
 	}
 
+	account_softirq_exit(current);
 	lockdep_softirq_end(in_hardirq);
-	account_irq_exit_time(current);
 	__local_bh_enable(SOFTIRQ_OFFSET);
 	WARN_ON_ONCE(in_interrupt());
 	current_restore_flags(old_flags, PF_MEMALLOC);
@@ -418,7 +418,7 @@ static inline void __irq_exit_rcu(void)
 #else
 	lockdep_assert_irqs_disabled();
 #endif
-	account_irq_exit_time(current);
+	account_hardirq_exit(current);
 	preempt_count_sub(HARDIRQ_OFFSET);
 	if (!in_interrupt() && local_softirq_pending())
 		invoke_softirq();
-- 
cgit v1.2.3


From 427167c0b064ed898b848209add62b4322ec7840 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Wed, 2 Dec 2020 09:25:15 -0800
Subject: bpf: Allow bpf_{s,g}etsockopt from cgroup bind{4,6} hooks

I have to now lock/unlock socket for the bind hook execution.
That shouldn't cause any overhead because the socket is unbound
and shouldn't receive any traffic.

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrey Ignatov <rdna@fb.com>
Link: https://lore.kernel.org/bpf/20201202172516.3483656-3-sdf@google.com
---
 include/linux/bpf-cgroup.h | 12 ++++++------
 net/core/filter.c          |  4 ++++
 net/ipv4/af_inet.c         |  2 +-
 net/ipv6/af_inet6.c        |  2 +-
 4 files changed, 12 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index ed71bd1a0825..72e69a0e1e8c 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -246,11 +246,11 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
 	__ret;								       \
 })
 
-#define BPF_CGROUP_RUN_PROG_INET4_BIND(sk, uaddr)			       \
-	BPF_CGROUP_RUN_SA_PROG(sk, uaddr, BPF_CGROUP_INET4_BIND)
+#define BPF_CGROUP_RUN_PROG_INET4_BIND_LOCK(sk, uaddr)			       \
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET4_BIND, NULL)
 
-#define BPF_CGROUP_RUN_PROG_INET6_BIND(sk, uaddr)			       \
-	BPF_CGROUP_RUN_SA_PROG(sk, uaddr, BPF_CGROUP_INET6_BIND)
+#define BPF_CGROUP_RUN_PROG_INET6_BIND_LOCK(sk, uaddr)			       \
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET6_BIND, NULL)
 
 #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (cgroup_bpf_enabled && \
 					    sk->sk_prot->pre_connect)
@@ -434,8 +434,8 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
 #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk) ({ 0; })
-#define BPF_CGROUP_RUN_PROG_INET4_BIND(sk, uaddr) ({ 0; })
-#define BPF_CGROUP_RUN_PROG_INET6_BIND(sk, uaddr) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_INET4_BIND_LOCK(sk, uaddr) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_INET6_BIND_LOCK(sk, uaddr) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr) ({ 0; })
diff --git a/net/core/filter.c b/net/core/filter.c
index 2ca5eecebacf..21d91dcf0260 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -6995,6 +6995,8 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sk_storage_delete_proto;
 	case BPF_FUNC_setsockopt:
 		switch (prog->expected_attach_type) {
+		case BPF_CGROUP_INET4_BIND:
+		case BPF_CGROUP_INET6_BIND:
 		case BPF_CGROUP_INET4_CONNECT:
 		case BPF_CGROUP_INET6_CONNECT:
 			return &bpf_sock_addr_setsockopt_proto;
@@ -7003,6 +7005,8 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		}
 	case BPF_FUNC_getsockopt:
 		switch (prog->expected_attach_type) {
+		case BPF_CGROUP_INET4_BIND:
+		case BPF_CGROUP_INET6_BIND:
 		case BPF_CGROUP_INET4_CONNECT:
 		case BPF_CGROUP_INET6_CONNECT:
 			return &bpf_sock_addr_getsockopt_proto;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index b7260c8cef2e..b94fa8eb831b 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -450,7 +450,7 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	/* BPF prog is run before any checks are done so that if the prog
 	 * changes context in a wrong way it will be caught.
 	 */
-	err = BPF_CGROUP_RUN_PROG_INET4_BIND(sk, uaddr);
+	err = BPF_CGROUP_RUN_PROG_INET4_BIND_LOCK(sk, uaddr);
 	if (err)
 		return err;
 
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index e648fbebb167..a7e3d170af51 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -451,7 +451,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	/* BPF prog is run before any checks are done so that if the prog
 	 * changes context in a wrong way it will be caught.
 	 */
-	err = BPF_CGROUP_RUN_PROG_INET6_BIND(sk, uaddr);
+	err = BPF_CGROUP_RUN_PROG_INET6_BIND_LOCK(sk, uaddr);
 	if (err)
 		return err;
 
-- 
cgit v1.2.3


From ec0caa974cd092549ab282deb8ec7ea73b36eba0 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Wed, 2 Dec 2020 18:20:37 -0800
Subject: fscrypt: introduce fscrypt_prepare_readdir()

The last remaining use of fscrypt_get_encryption_info() from filesystems
is for readdir (->iterate_shared()).  Every other call is now in
fs/crypto/ as part of some other higher-level operation.

We need to add a new argument to fscrypt_get_encryption_info() to
indicate whether the encryption policy is allowed to be unrecognized or
not.  Doing this is easier if we can work with high-level operations
rather than direct filesystem use of fscrypt_get_encryption_info().

So add a function fscrypt_prepare_readdir() which wraps the call to
fscrypt_get_encryption_info() for the readdir use case.

Reviewed-by: Andreas Dilger <adilger@dilger.ca>
Link: https://lore.kernel.org/r/20201203022041.230976-6-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 fs/crypto/hooks.c       |  6 ++++++
 fs/ext4/dir.c           |  8 +++-----
 fs/ext4/namei.c         |  2 +-
 fs/f2fs/dir.c           |  2 +-
 fs/ubifs/dir.c          |  2 +-
 include/linux/fscrypt.h | 24 ++++++++++++++++++++++++
 6 files changed, 36 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c
index c809a4afa057..82f351d3113a 100644
--- a/fs/crypto/hooks.c
+++ b/fs/crypto/hooks.c
@@ -114,6 +114,12 @@ int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry,
 }
 EXPORT_SYMBOL_GPL(__fscrypt_prepare_lookup);
 
+int __fscrypt_prepare_readdir(struct inode *dir)
+{
+	return fscrypt_get_encryption_info(dir);
+}
+EXPORT_SYMBOL_GPL(__fscrypt_prepare_readdir);
+
 /**
  * fscrypt_prepare_setflags() - prepare to change flags with FS_IOC_SETFLAGS
  * @inode: the inode on which flags are being changed
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 16bfbdd5007c..c6d16353326a 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -118,11 +118,9 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 	struct buffer_head *bh = NULL;
 	struct fscrypt_str fstr = FSTR_INIT(NULL, 0);
 
-	if (IS_ENCRYPTED(inode)) {
-		err = fscrypt_get_encryption_info(inode);
-		if (err)
-			return err;
-	}
+	err = fscrypt_prepare_readdir(inode);
+	if (err)
+		return err;
 
 	if (is_dx_dir(inode)) {
 		err = ext4_dx_readdir(file, ctx);
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 7b31aea3e025..5fa8436cd5fa 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1004,7 +1004,7 @@ static int htree_dirblock_to_tree(struct file *dir_file,
 					   EXT4_DIR_REC_LEN(0));
 	/* Check if the directory is encrypted */
 	if (IS_ENCRYPTED(dir)) {
-		err = fscrypt_get_encryption_info(dir);
+		err = fscrypt_prepare_readdir(dir);
 		if (err < 0) {
 			brelse(bh);
 			return err;
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 47bee953fc8d..049500f1e764 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -1022,7 +1022,7 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
 	int err = 0;
 
 	if (IS_ENCRYPTED(inode)) {
-		err = fscrypt_get_encryption_info(inode);
+		err = fscrypt_prepare_readdir(inode);
 		if (err)
 			goto out;
 
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index 009fbf844d3e..1f33a5598b93 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -514,7 +514,7 @@ static int ubifs_readdir(struct file *file, struct dir_context *ctx)
 		return 0;
 
 	if (encrypted) {
-		err = fscrypt_get_encryption_info(dir);
+		err = fscrypt_prepare_readdir(dir);
 		if (err)
 			return err;
 
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index 0c9e64969b73..8cbb26f55695 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -242,6 +242,7 @@ int __fscrypt_prepare_rename(struct inode *old_dir, struct dentry *old_dentry,
 			     unsigned int flags);
 int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry,
 			     struct fscrypt_name *fname);
+int __fscrypt_prepare_readdir(struct inode *dir);
 int fscrypt_prepare_setflags(struct inode *inode,
 			     unsigned int oldflags, unsigned int flags);
 int fscrypt_prepare_symlink(struct inode *dir, const char *target,
@@ -537,6 +538,11 @@ static inline int __fscrypt_prepare_lookup(struct inode *dir,
 	return -EOPNOTSUPP;
 }
 
+static inline int __fscrypt_prepare_readdir(struct inode *dir)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline int fscrypt_prepare_setflags(struct inode *inode,
 					   unsigned int oldflags,
 					   unsigned int flags)
@@ -795,6 +801,24 @@ static inline int fscrypt_prepare_lookup(struct inode *dir,
 	return 0;
 }
 
+/**
+ * fscrypt_prepare_readdir() - prepare to read a possibly-encrypted directory
+ * @dir: the directory inode
+ *
+ * If the directory is encrypted and it doesn't already have its encryption key
+ * set up, try to set it up so that the filenames will be listed in plaintext
+ * form rather than in no-key form.
+ *
+ * Return: 0 on success; -errno on error.  Note that the encryption key being
+ *	   unavailable is not considered an error.
+ */
+static inline int fscrypt_prepare_readdir(struct inode *dir)
+{
+	if (IS_ENCRYPTED(dir))
+		return __fscrypt_prepare_readdir(dir);
+	return 0;
+}
+
 /**
  * fscrypt_prepare_setattr() - prepare to change a possibly-encrypted inode's
  *			       attributes
-- 
cgit v1.2.3


From 7622350e5eda2cc57a72c6b27f1405d8b4f94670 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Wed, 2 Dec 2020 18:20:38 -0800
Subject: fscrypt: move body of fscrypt_prepare_setattr() out-of-line

In preparation for reducing the visibility of fscrypt_require_key() by
moving it to fscrypt_private.h, move the call to it from
fscrypt_prepare_setattr() to an out-of-line function.

Reviewed-by: Andreas Dilger <adilger@dilger.ca>
Link: https://lore.kernel.org/r/20201203022041.230976-7-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 fs/crypto/hooks.c       |  8 ++++++++
 include/linux/fscrypt.h | 11 +++++++++--
 2 files changed, 17 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c
index 82f351d3113a..1c16dba222d9 100644
--- a/fs/crypto/hooks.c
+++ b/fs/crypto/hooks.c
@@ -120,6 +120,14 @@ int __fscrypt_prepare_readdir(struct inode *dir)
 }
 EXPORT_SYMBOL_GPL(__fscrypt_prepare_readdir);
 
+int __fscrypt_prepare_setattr(struct dentry *dentry, struct iattr *attr)
+{
+	if (attr->ia_valid & ATTR_SIZE)
+		return fscrypt_require_key(d_inode(dentry));
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__fscrypt_prepare_setattr);
+
 /**
  * fscrypt_prepare_setflags() - prepare to change flags with FS_IOC_SETFLAGS
  * @inode: the inode on which flags are being changed
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index 8cbb26f55695..b20900bb829f 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -243,6 +243,7 @@ int __fscrypt_prepare_rename(struct inode *old_dir, struct dentry *old_dentry,
 int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry,
 			     struct fscrypt_name *fname);
 int __fscrypt_prepare_readdir(struct inode *dir);
+int __fscrypt_prepare_setattr(struct dentry *dentry, struct iattr *attr);
 int fscrypt_prepare_setflags(struct inode *inode,
 			     unsigned int oldflags, unsigned int flags);
 int fscrypt_prepare_symlink(struct inode *dir, const char *target,
@@ -543,6 +544,12 @@ static inline int __fscrypt_prepare_readdir(struct inode *dir)
 	return -EOPNOTSUPP;
 }
 
+static inline int __fscrypt_prepare_setattr(struct dentry *dentry,
+					    struct iattr *attr)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline int fscrypt_prepare_setflags(struct inode *inode,
 					   unsigned int oldflags,
 					   unsigned int flags)
@@ -840,8 +847,8 @@ static inline int fscrypt_prepare_readdir(struct inode *dir)
 static inline int fscrypt_prepare_setattr(struct dentry *dentry,
 					  struct iattr *attr)
 {
-	if (attr->ia_valid & ATTR_SIZE)
-		return fscrypt_require_key(d_inode(dentry));
+	if (IS_ENCRYPTED(d_inode(dentry)))
+		return __fscrypt_prepare_setattr(dentry, attr);
 	return 0;
 }
 
-- 
cgit v1.2.3


From de3cdc6e75179a2324c23400b21483a1372c95e1 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Wed, 2 Dec 2020 18:20:39 -0800
Subject: fscrypt: move fscrypt_require_key() to fscrypt_private.h

fscrypt_require_key() is now only used by files in fs/crypto/.  So
reduce its visibility to fscrypt_private.h.  This is also a prerequsite
for unexporting fscrypt_get_encryption_info().

Reviewed-by: Andreas Dilger <adilger@dilger.ca>
Link: https://lore.kernel.org/r/20201203022041.230976-8-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 fs/crypto/fscrypt_private.h | 26 ++++++++++++++++++++++++++
 include/linux/fscrypt.h     | 26 --------------------------
 2 files changed, 26 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h
index a61d4dbf0a0b..16dd55080127 100644
--- a/fs/crypto/fscrypt_private.h
+++ b/fs/crypto/fscrypt_private.h
@@ -571,6 +571,32 @@ int fscrypt_derive_dirhash_key(struct fscrypt_info *ci,
 void fscrypt_hash_inode_number(struct fscrypt_info *ci,
 			       const struct fscrypt_master_key *mk);
 
+/**
+ * fscrypt_require_key() - require an inode's encryption key
+ * @inode: the inode we need the key for
+ *
+ * If the inode is encrypted, set up its encryption key if not already done.
+ * Then require that the key be present and return -ENOKEY otherwise.
+ *
+ * No locks are needed, and the key will live as long as the struct inode --- so
+ * it won't go away from under you.
+ *
+ * Return: 0 on success, -ENOKEY if the key is missing, or another -errno code
+ * if a problem occurred while setting up the encryption key.
+ */
+static inline int fscrypt_require_key(struct inode *inode)
+{
+	if (IS_ENCRYPTED(inode)) {
+		int err = fscrypt_get_encryption_info(inode);
+
+		if (err)
+			return err;
+		if (!fscrypt_has_encryption_key(inode))
+			return -ENOKEY;
+	}
+	return 0;
+}
+
 /* keysetup_v1.c */
 
 void fscrypt_put_direct_key(struct fscrypt_direct_key *dk);
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index b20900bb829f..a07610f27926 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -688,32 +688,6 @@ static inline bool fscrypt_has_encryption_key(const struct inode *inode)
 	return fscrypt_get_info(inode) != NULL;
 }
 
-/**
- * fscrypt_require_key() - require an inode's encryption key
- * @inode: the inode we need the key for
- *
- * If the inode is encrypted, set up its encryption key if not already done.
- * Then require that the key be present and return -ENOKEY otherwise.
- *
- * No locks are needed, and the key will live as long as the struct inode --- so
- * it won't go away from under you.
- *
- * Return: 0 on success, -ENOKEY if the key is missing, or another -errno code
- * if a problem occurred while setting up the encryption key.
- */
-static inline int fscrypt_require_key(struct inode *inode)
-{
-	if (IS_ENCRYPTED(inode)) {
-		int err = fscrypt_get_encryption_info(inode);
-
-		if (err)
-			return err;
-		if (!fscrypt_has_encryption_key(inode))
-			return -ENOKEY;
-	}
-	return 0;
-}
-
 /**
  * fscrypt_prepare_link() - prepare to link an inode into a possibly-encrypted
  *			    directory
-- 
cgit v1.2.3


From 5b421f08801fe8247dec368b3d323958f419e769 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Wed, 2 Dec 2020 18:20:40 -0800
Subject: fscrypt: unexport fscrypt_get_encryption_info()

Now that fscrypt_get_encryption_info() is only called from files in
fs/crypto/ (due to all key setup now being handled by higher-level
helper functions instead of directly by filesystems), unexport it and
move its declaration to fscrypt_private.h.

Reviewed-by: Andreas Dilger <adilger@dilger.ca>
Link: https://lore.kernel.org/r/20201203022041.230976-9-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 fs/crypto/fscrypt_private.h | 2 ++
 fs/crypto/keysetup.c        | 1 -
 include/linux/fscrypt.h     | 7 +------
 3 files changed, 3 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h
index 16dd55080127..c1c302656c34 100644
--- a/fs/crypto/fscrypt_private.h
+++ b/fs/crypto/fscrypt_private.h
@@ -571,6 +571,8 @@ int fscrypt_derive_dirhash_key(struct fscrypt_info *ci,
 void fscrypt_hash_inode_number(struct fscrypt_info *ci,
 			       const struct fscrypt_master_key *mk);
 
+int fscrypt_get_encryption_info(struct inode *inode);
+
 /**
  * fscrypt_require_key() - require an inode's encryption key
  * @inode: the inode we need the key for
diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c
index 50675b42d5b7..6339b3069a40 100644
--- a/fs/crypto/keysetup.c
+++ b/fs/crypto/keysetup.c
@@ -589,7 +589,6 @@ int fscrypt_get_encryption_info(struct inode *inode)
 		res = 0;
 	return res;
 }
-EXPORT_SYMBOL(fscrypt_get_encryption_info);
 
 /**
  * fscrypt_prepare_new_inode() - prepare to create a new inode in a directory
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index a07610f27926..4b163f5e58e9 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -75,7 +75,7 @@ struct fscrypt_operations {
 static inline struct fscrypt_info *fscrypt_get_info(const struct inode *inode)
 {
 	/*
-	 * Pairs with the cmpxchg_release() in fscrypt_get_encryption_info().
+	 * Pairs with the cmpxchg_release() in fscrypt_setup_encryption_info().
 	 * I.e., another task may publish ->i_crypt_info concurrently, executing
 	 * a RELEASE barrier.  We need to use smp_load_acquire() here to safely
 	 * ACQUIRE the memory the other task published.
@@ -200,7 +200,6 @@ int fscrypt_ioctl_remove_key_all_users(struct file *filp, void __user *arg);
 int fscrypt_ioctl_get_key_status(struct file *filp, void __user *arg);
 
 /* keysetup.c */
-int fscrypt_get_encryption_info(struct inode *inode);
 int fscrypt_prepare_new_inode(struct inode *dir, struct inode *inode,
 			      bool *encrypt_ret);
 void fscrypt_put_encryption_info(struct inode *inode);
@@ -408,10 +407,6 @@ static inline int fscrypt_ioctl_get_key_status(struct file *filp,
 }
 
 /* keysetup.c */
-static inline int fscrypt_get_encryption_info(struct inode *inode)
-{
-	return -EOPNOTSUPP;
-}
 
 static inline int fscrypt_prepare_new_inode(struct inode *dir,
 					    struct inode *inode,
-- 
cgit v1.2.3


From a14d0b6764917b21ee6fdfd2a8a4c2920fbefcce Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Wed, 2 Dec 2020 18:20:41 -0800
Subject: fscrypt: allow deleting files with unsupported encryption policy

Currently it's impossible to delete files that use an unsupported
encryption policy, as the kernel will just return an error when
performing any operation on the top-level encrypted directory, even just
a path lookup into the directory or opening the directory for readdir.

More specifically, this occurs in any of the following cases:

- The encryption context has an unrecognized version number.  Current
  kernels know about v1 and v2, but there could be more versions in the
  future.

- The encryption context has unrecognized encryption modes
  (FSCRYPT_MODE_*) or flags (FSCRYPT_POLICY_FLAG_*), an unrecognized
  combination of modes, or reserved bits set.

- The encryption key has been added and the encryption modes are
  recognized but aren't available in the crypto API -- for example, a
  directory is encrypted with FSCRYPT_MODE_ADIANTUM but the kernel
  doesn't have CONFIG_CRYPTO_ADIANTUM enabled.

It's desirable to return errors for most operations on files that use an
unsupported encryption policy, but the current behavior is too strict.
We need to allow enough to delete files, so that people can't be stuck
with undeletable files when downgrading kernel versions.  That includes
allowing directories to be listed and allowing dentries to be looked up.

Fix this by modifying the key setup logic to treat an unsupported
encryption policy in the same way as "key unavailable" in the cases that
are required for a recursive delete to work: preparing for a readdir or
a dentry lookup, revalidating a dentry, or checking whether an inode has
the same encryption policy as its parent directory.

Reviewed-by: Andreas Dilger <adilger@dilger.ca>
Link: https://lore.kernel.org/r/20201203022041.230976-10-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 fs/crypto/fname.c           |  8 ++++++--
 fs/crypto/fscrypt_private.h |  4 ++--
 fs/crypto/hooks.c           |  4 ++--
 fs/crypto/keysetup.c        | 19 +++++++++++++++++--
 fs/crypto/policy.c          | 22 ++++++++++++++--------
 include/linux/fscrypt.h     |  9 ++++++---
 6 files changed, 47 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c
index 1fbe6c24d705..988dadf7a94d 100644
--- a/fs/crypto/fname.c
+++ b/fs/crypto/fname.c
@@ -404,7 +404,7 @@ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname,
 		fname->disk_name.len = iname->len;
 		return 0;
 	}
-	ret = fscrypt_get_encryption_info(dir);
+	ret = fscrypt_get_encryption_info(dir, lookup);
 	if (ret)
 		return ret;
 
@@ -560,7 +560,11 @@ int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
 		return -ECHILD;
 
 	dir = dget_parent(dentry);
-	err = fscrypt_get_encryption_info(d_inode(dir));
+	/*
+	 * Pass allow_unsupported=true, so that files with an unsupported
+	 * encryption policy can be deleted.
+	 */
+	err = fscrypt_get_encryption_info(d_inode(dir), true);
 	valid = !fscrypt_has_encryption_key(d_inode(dir));
 	dput(dir);
 
diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h
index c1c302656c34..f0bed6b06fa6 100644
--- a/fs/crypto/fscrypt_private.h
+++ b/fs/crypto/fscrypt_private.h
@@ -571,7 +571,7 @@ int fscrypt_derive_dirhash_key(struct fscrypt_info *ci,
 void fscrypt_hash_inode_number(struct fscrypt_info *ci,
 			       const struct fscrypt_master_key *mk);
 
-int fscrypt_get_encryption_info(struct inode *inode);
+int fscrypt_get_encryption_info(struct inode *inode, bool allow_unsupported);
 
 /**
  * fscrypt_require_key() - require an inode's encryption key
@@ -589,7 +589,7 @@ int fscrypt_get_encryption_info(struct inode *inode);
 static inline int fscrypt_require_key(struct inode *inode)
 {
 	if (IS_ENCRYPTED(inode)) {
-		int err = fscrypt_get_encryption_info(inode);
+		int err = fscrypt_get_encryption_info(inode, false);
 
 		if (err)
 			return err;
diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c
index 1c16dba222d9..79570e0e8e61 100644
--- a/fs/crypto/hooks.c
+++ b/fs/crypto/hooks.c
@@ -116,7 +116,7 @@ EXPORT_SYMBOL_GPL(__fscrypt_prepare_lookup);
 
 int __fscrypt_prepare_readdir(struct inode *dir)
 {
-	return fscrypt_get_encryption_info(dir);
+	return fscrypt_get_encryption_info(dir, true);
 }
 EXPORT_SYMBOL_GPL(__fscrypt_prepare_readdir);
 
@@ -332,7 +332,7 @@ const char *fscrypt_get_symlink(struct inode *inode, const void *caddr,
 	 * Try to set up the symlink's encryption key, but we can continue
 	 * regardless of whether the key is available or not.
 	 */
-	err = fscrypt_get_encryption_info(inode);
+	err = fscrypt_get_encryption_info(inode, false);
 	if (err)
 		return ERR_PTR(err);
 	has_key = fscrypt_has_encryption_key(inode);
diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c
index 6339b3069a40..261293fb7097 100644
--- a/fs/crypto/keysetup.c
+++ b/fs/crypto/keysetup.c
@@ -546,6 +546,11 @@ out:
 /**
  * fscrypt_get_encryption_info() - set up an inode's encryption key
  * @inode: the inode to set up the key for.  Must be encrypted.
+ * @allow_unsupported: if %true, treat an unsupported encryption policy (or
+ *		       unrecognized encryption context) the same way as the key
+ *		       being unavailable, instead of returning an error.  Use
+ *		       %false unless the operation being performed is needed in
+ *		       order for files (or directories) to be deleted.
  *
  * Set up ->i_crypt_info, if it hasn't already been done.
  *
@@ -556,7 +561,7 @@ out:
  *	   encryption key is unavailable.  (Use fscrypt_has_encryption_key() to
  *	   distinguish these cases.)  Also can return another -errno code.
  */
-int fscrypt_get_encryption_info(struct inode *inode)
+int fscrypt_get_encryption_info(struct inode *inode, bool allow_unsupported)
 {
 	int res;
 	union fscrypt_context ctx;
@@ -567,24 +572,34 @@ int fscrypt_get_encryption_info(struct inode *inode)
 
 	res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
 	if (res < 0) {
+		if (res == -ERANGE && allow_unsupported)
+			return 0;
 		fscrypt_warn(inode, "Error %d getting encryption context", res);
 		return res;
 	}
 
 	res = fscrypt_policy_from_context(&policy, &ctx, res);
 	if (res) {
+		if (allow_unsupported)
+			return 0;
 		fscrypt_warn(inode,
 			     "Unrecognized or corrupt encryption context");
 		return res;
 	}
 
-	if (!fscrypt_supported_policy(&policy, inode))
+	if (!fscrypt_supported_policy(&policy, inode)) {
+		if (allow_unsupported)
+			return 0;
 		return -EINVAL;
+	}
 
 	res = fscrypt_setup_encryption_info(inode, &policy,
 					    fscrypt_context_nonce(&ctx),
 					    IS_CASEFOLDED(inode) &&
 					    S_ISDIR(inode->i_mode));
+
+	if (res == -ENOPKG && allow_unsupported) /* Algorithm unavailable? */
+		res = 0;
 	if (res == -ENOKEY)
 		res = 0;
 	return res;
diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
index faa0f21daa68..a51cef6bd27f 100644
--- a/fs/crypto/policy.c
+++ b/fs/crypto/policy.c
@@ -590,7 +590,7 @@ EXPORT_SYMBOL_GPL(fscrypt_ioctl_get_nonce);
 int fscrypt_has_permitted_context(struct inode *parent, struct inode *child)
 {
 	union fscrypt_policy parent_policy, child_policy;
-	int err;
+	int err, err1, err2;
 
 	/* No restrictions on file types which are never encrypted */
 	if (!S_ISREG(child->i_mode) && !S_ISDIR(child->i_mode) &&
@@ -620,19 +620,25 @@ int fscrypt_has_permitted_context(struct inode *parent, struct inode *child)
 	 * In any case, if an unexpected error occurs, fall back to "forbidden".
 	 */
 
-	err = fscrypt_get_encryption_info(parent);
+	err = fscrypt_get_encryption_info(parent, true);
 	if (err)
 		return 0;
-	err = fscrypt_get_encryption_info(child);
+	err = fscrypt_get_encryption_info(child, true);
 	if (err)
 		return 0;
 
-	err = fscrypt_get_policy(parent, &parent_policy);
-	if (err)
-		return 0;
+	err1 = fscrypt_get_policy(parent, &parent_policy);
+	err2 = fscrypt_get_policy(child, &child_policy);
 
-	err = fscrypt_get_policy(child, &child_policy);
-	if (err)
+	/*
+	 * Allow the case where the parent and child both have an unrecognized
+	 * encryption policy, so that files with an unrecognized encryption
+	 * policy can be deleted.
+	 */
+	if (err1 == -EINVAL && err2 == -EINVAL)
+		return 1;
+
+	if (err1 || err2)
 		return 0;
 
 	return fscrypt_policies_equal(&parent_policy, &child_policy);
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index 4b163f5e58e9..d23156d1ac94 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -753,8 +753,9 @@ static inline int fscrypt_prepare_rename(struct inode *old_dir,
  *
  * Prepare for ->lookup() in a directory which may be encrypted by determining
  * the name that will actually be used to search the directory on-disk.  If the
- * directory's encryption key is available, then the lookup is assumed to be by
- * plaintext name; otherwise, it is assumed to be by no-key name.
+ * directory's encryption policy is supported by this kernel and its encryption
+ * key is available, then the lookup is assumed to be by plaintext name;
+ * otherwise, it is assumed to be by no-key name.
  *
  * This also installs a custom ->d_revalidate() method which will invalidate the
  * dentry if it was created without the key and the key is later added.
@@ -786,7 +787,9 @@ static inline int fscrypt_prepare_lookup(struct inode *dir,
  * form rather than in no-key form.
  *
  * Return: 0 on success; -errno on error.  Note that the encryption key being
- *	   unavailable is not considered an error.
+ *	   unavailable is not considered an error.  It is also not an error if
+ *	   the encryption policy is unsupported by this kernel; that is treated
+ *	   like the key being unavailable, so that files can still be deleted.
  */
 static inline int fscrypt_prepare_readdir(struct inode *dir)
 {
-- 
cgit v1.2.3


From bcfe06bf2622f7c4899468e427683aec49070687 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Tue, 1 Dec 2020 13:58:27 -0800
Subject: mm: memcontrol: Use helpers to read page's memcg data

Patch series "mm: allow mapping accounted kernel pages to userspace", v6.

Currently a non-slab kernel page which has been charged to a memory cgroup
can't be mapped to userspace.  The underlying reason is simple: PageKmemcg
flag is defined as a page type (like buddy, offline, etc), so it takes a
bit from a page->mapped counter.  Pages with a type set can't be mapped to
userspace.

But in general the kmemcg flag has nothing to do with mapping to
userspace.  It only means that the page has been accounted by the page
allocator, so it has to be properly uncharged on release.

Some bpf maps are mapping the vmalloc-based memory to userspace, and their
memory can't be accounted because of this implementation detail.

This patchset removes this limitation by moving the PageKmemcg flag into
one of the free bits of the page->mem_cgroup pointer.  Also it formalizes
accesses to the page->mem_cgroup and page->obj_cgroups using new helpers,
adds several checks and removes a couple of obsolete functions.  As the
result the code became more robust with fewer open-coded bit tricks.

This patch (of 4):

Currently there are many open-coded reads of the page->mem_cgroup pointer,
as well as a couple of read helpers, which are barely used.

It creates an obstacle on a way to reuse some bits of the pointer for
storing additional bits of information.  In fact, we already do this for
slab pages, where the last bit indicates that a pointer has an attached
vector of objcg pointers instead of a regular memcg pointer.

This commits uses 2 existing helpers and introduces a new helper to
converts all read sides to calls of these helpers:
  struct mem_cgroup *page_memcg(struct page *page);
  struct mem_cgroup *page_memcg_rcu(struct page *page);
  struct mem_cgroup *page_memcg_check(struct page *page);

page_memcg_check() is intended to be used in cases when the page can be a
slab page and have a memcg pointer pointing at objcg vector.  It does
check the lowest bit, and if set, returns NULL.  page_memcg() contains a
VM_BUG_ON_PAGE() check for the page not being a slab page.

To make sure nobody uses a direct access, struct page's
mem_cgroup/obj_cgroups is converted to unsigned long memcg_data.

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Link: https://lkml.kernel.org/r/20201027001657.3398190-1-guro@fb.com
Link: https://lkml.kernel.org/r/20201027001657.3398190-2-guro@fb.com
Link: https://lore.kernel.org/bpf/20201201215900.3569844-2-guro@fb.com
---
 fs/buffer.c                      |   2 +-
 fs/iomap/buffered-io.c           |   2 +-
 include/linux/memcontrol.h       | 114 +++++++++++++++++++++++++++++++++---
 include/linux/mm.h               |  22 -------
 include/linux/mm_types.h         |   5 +-
 include/trace/events/writeback.h |   2 +-
 kernel/fork.c                    |   7 ++-
 mm/debug.c                       |   4 +-
 mm/huge_memory.c                 |   4 +-
 mm/memcontrol.c                  | 121 ++++++++++++++++++---------------------
 mm/page_alloc.c                  |   4 +-
 mm/page_io.c                     |   6 +-
 mm/slab.h                        |   9 ++-
 mm/workingset.c                  |   2 +-
 14 files changed, 184 insertions(+), 120 deletions(-)

(limited to 'include/linux')

diff --git a/fs/buffer.c b/fs/buffer.c
index 23f645657488..b56f99f82b5b 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -657,7 +657,7 @@ int __set_page_dirty_buffers(struct page *page)
 		} while (bh != head);
 	}
 	/*
-	 * Lock out page->mem_cgroup migration to keep PageDirty
+	 * Lock out page's memcg migration to keep PageDirty
 	 * synchronized with per-memcg dirty page counters.
 	 */
 	lock_page_memcg(page);
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 10cc7979ce38..16a1e82e3aeb 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -650,7 +650,7 @@ iomap_set_page_dirty(struct page *page)
 		return !TestSetPageDirty(page);
 
 	/*
-	 * Lock out page->mem_cgroup migration to keep PageDirty
+	 * Lock out page's memcg migration to keep PageDirty
 	 * synchronized with per-memcg dirty page counters.
 	 */
 	lock_page_memcg(page);
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index e391e3c56de5..f95c1433461c 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -343,6 +343,79 @@ struct mem_cgroup {
 
 extern struct mem_cgroup *root_mem_cgroup;
 
+/*
+ * page_memcg - get the memory cgroup associated with a page
+ * @page: a pointer to the page struct
+ *
+ * Returns a pointer to the memory cgroup associated with the page,
+ * or NULL. This function assumes that the page is known to have a
+ * proper memory cgroup pointer. It's not safe to call this function
+ * against some type of pages, e.g. slab pages or ex-slab pages.
+ *
+ * Any of the following ensures page and memcg binding stability:
+ * - the page lock
+ * - LRU isolation
+ * - lock_page_memcg()
+ * - exclusive reference
+ */
+static inline struct mem_cgroup *page_memcg(struct page *page)
+{
+	VM_BUG_ON_PAGE(PageSlab(page), page);
+	return (struct mem_cgroup *)page->memcg_data;
+}
+
+/*
+ * page_memcg_rcu - locklessly get the memory cgroup associated with a page
+ * @page: a pointer to the page struct
+ *
+ * Returns a pointer to the memory cgroup associated with the page,
+ * or NULL. This function assumes that the page is known to have a
+ * proper memory cgroup pointer. It's not safe to call this function
+ * against some type of pages, e.g. slab pages or ex-slab pages.
+ */
+static inline struct mem_cgroup *page_memcg_rcu(struct page *page)
+{
+	VM_BUG_ON_PAGE(PageSlab(page), page);
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	return (struct mem_cgroup *)READ_ONCE(page->memcg_data);
+}
+
+/*
+ * page_memcg_check - get the memory cgroup associated with a page
+ * @page: a pointer to the page struct
+ *
+ * Returns a pointer to the memory cgroup associated with the page,
+ * or NULL. This function unlike page_memcg() can take any  page
+ * as an argument. It has to be used in cases when it's not known if a page
+ * has an associated memory cgroup pointer or an object cgroups vector.
+ *
+ * Any of the following ensures page and memcg binding stability:
+ * - the page lock
+ * - LRU isolation
+ * - lock_page_memcg()
+ * - exclusive reference
+ */
+static inline struct mem_cgroup *page_memcg_check(struct page *page)
+{
+	/*
+	 * Because page->memcg_data might be changed asynchronously
+	 * for slab pages, READ_ONCE() should be used here.
+	 */
+	unsigned long memcg_data = READ_ONCE(page->memcg_data);
+
+	/*
+	 * The lowest bit set means that memcg isn't a valid
+	 * memcg pointer, but a obj_cgroups pointer.
+	 * In this case the page is shared and doesn't belong
+	 * to any specific memory cgroup.
+	 */
+	if (memcg_data & 0x1UL)
+		return NULL;
+
+	return (struct mem_cgroup *)memcg_data;
+}
+
 static __always_inline bool memcg_stat_item_in_bytes(int idx)
 {
 	if (idx == MEMCG_PERCPU_B)
@@ -743,15 +816,19 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg,
 static inline void __mod_memcg_page_state(struct page *page,
 					  int idx, int val)
 {
-	if (page->mem_cgroup)
-		__mod_memcg_state(page->mem_cgroup, idx, val);
+	struct mem_cgroup *memcg = page_memcg(page);
+
+	if (memcg)
+		__mod_memcg_state(memcg, idx, val);
 }
 
 static inline void mod_memcg_page_state(struct page *page,
 					int idx, int val)
 {
-	if (page->mem_cgroup)
-		mod_memcg_state(page->mem_cgroup, idx, val);
+	struct mem_cgroup *memcg = page_memcg(page);
+
+	if (memcg)
+		mod_memcg_state(memcg, idx, val);
 }
 
 static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
@@ -834,16 +911,17 @@ static inline void __mod_lruvec_page_state(struct page *page,
 					   enum node_stat_item idx, int val)
 {
 	struct page *head = compound_head(page); /* rmap on tail pages */
+	struct mem_cgroup *memcg = page_memcg(head);
 	pg_data_t *pgdat = page_pgdat(page);
 	struct lruvec *lruvec;
 
 	/* Untracked pages have no memcg, no lruvec. Update only the node */
-	if (!head->mem_cgroup) {
+	if (!memcg) {
 		__mod_node_page_state(pgdat, idx, val);
 		return;
 	}
 
-	lruvec = mem_cgroup_lruvec(head->mem_cgroup, pgdat);
+	lruvec = mem_cgroup_lruvec(memcg, pgdat);
 	__mod_lruvec_state(lruvec, idx, val);
 }
 
@@ -878,8 +956,10 @@ static inline void count_memcg_events(struct mem_cgroup *memcg,
 static inline void count_memcg_page_event(struct page *page,
 					  enum vm_event_item idx)
 {
-	if (page->mem_cgroup)
-		count_memcg_events(page->mem_cgroup, idx, 1);
+	struct mem_cgroup *memcg = page_memcg(page);
+
+	if (memcg)
+		count_memcg_events(memcg, idx, 1);
 }
 
 static inline void count_memcg_event_mm(struct mm_struct *mm,
@@ -941,6 +1021,22 @@ void mem_cgroup_split_huge_fixup(struct page *head);
 
 struct mem_cgroup;
 
+static inline struct mem_cgroup *page_memcg(struct page *page)
+{
+	return NULL;
+}
+
+static inline struct mem_cgroup *page_memcg_rcu(struct page *page)
+{
+	WARN_ON_ONCE(!rcu_read_lock_held());
+	return NULL;
+}
+
+static inline struct mem_cgroup *page_memcg_check(struct page *page)
+{
+	return NULL;
+}
+
 static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg)
 {
 	return true;
@@ -1430,7 +1526,7 @@ static inline void mem_cgroup_track_foreign_dirty(struct page *page,
 	if (mem_cgroup_disabled())
 		return;
 
-	if (unlikely(&page->mem_cgroup->css != wb->memcg_css))
+	if (unlikely(&page_memcg(page)->css != wb->memcg_css))
 		mem_cgroup_track_foreign_dirty_slowpath(page, wb);
 }
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index db6ae4d3fb4e..6b0c9d2c1d10 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1484,28 +1484,6 @@ static inline void set_page_links(struct page *page, enum zone_type zone,
 #endif
 }
 
-#ifdef CONFIG_MEMCG
-static inline struct mem_cgroup *page_memcg(struct page *page)
-{
-	return page->mem_cgroup;
-}
-static inline struct mem_cgroup *page_memcg_rcu(struct page *page)
-{
-	WARN_ON_ONCE(!rcu_read_lock_held());
-	return READ_ONCE(page->mem_cgroup);
-}
-#else
-static inline struct mem_cgroup *page_memcg(struct page *page)
-{
-	return NULL;
-}
-static inline struct mem_cgroup *page_memcg_rcu(struct page *page)
-{
-	WARN_ON_ONCE(!rcu_read_lock_held());
-	return NULL;
-}
-#endif
-
 /*
  * Some inline functions in vmstat.h depend on page_zone()
  */
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 5a9238f6caad..80f5d755c037 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -199,10 +199,7 @@ struct page {
 	atomic_t _refcount;
 
 #ifdef CONFIG_MEMCG
-	union {
-		struct mem_cgroup *mem_cgroup;
-		struct obj_cgroup **obj_cgroups;
-	};
+	unsigned long memcg_data;
 #endif
 
 	/*
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index e7cbccc7c14c..39a40dfb578a 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -257,7 +257,7 @@ TRACE_EVENT(track_foreign_dirty,
 		__entry->ino		= inode ? inode->i_ino : 0;
 		__entry->memcg_id	= wb->memcg_css->id;
 		__entry->cgroup_ino	= __trace_wb_assign_cgroup(wb);
-		__entry->page_cgroup_ino = cgroup_ino(page->mem_cgroup->css.cgroup);
+		__entry->page_cgroup_ino = cgroup_ino(page_memcg(page)->css.cgroup);
 	),
 
 	TP_printk("bdi %s[%llu]: ino=%lu memcg_id=%u cgroup_ino=%lu page_cgroup_ino=%lu",
diff --git a/kernel/fork.c b/kernel/fork.c
index 6d266388d380..cbd4f6f58409 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -404,9 +404,10 @@ static int memcg_charge_kernel_stack(struct task_struct *tsk)
 
 		for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) {
 			/*
-			 * If memcg_kmem_charge_page() fails, page->mem_cgroup
-			 * pointer is NULL, and memcg_kmem_uncharge_page() in
-			 * free_thread_stack() will ignore this page.
+			 * If memcg_kmem_charge_page() fails, page's
+			 * memory cgroup pointer is NULL, and
+			 * memcg_kmem_uncharge_page() in free_thread_stack()
+			 * will ignore this page.
 			 */
 			ret = memcg_kmem_charge_page(vm->pages[i], GFP_KERNEL,
 						     0);
diff --git a/mm/debug.c b/mm/debug.c
index ccca576b2899..8a40b3fefbeb 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -182,8 +182,8 @@ hex_only:
 		pr_warn("page dumped because: %s\n", reason);
 
 #ifdef CONFIG_MEMCG
-	if (!page_poisoned && page->mem_cgroup)
-		pr_warn("page->mem_cgroup:%px\n", page->mem_cgroup);
+	if (!page_poisoned && page->memcg_data)
+		pr_warn("pages's memcg:%lx\n", page->memcg_data);
 #endif
 }
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 9474dbc150ed..cedfb3503411 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -470,7 +470,7 @@ pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
 #ifdef CONFIG_MEMCG
 static inline struct deferred_split *get_deferred_split_queue(struct page *page)
 {
-	struct mem_cgroup *memcg = compound_head(page)->mem_cgroup;
+	struct mem_cgroup *memcg = page_memcg(compound_head(page));
 	struct pglist_data *pgdat = NODE_DATA(page_to_nid(page));
 
 	if (memcg)
@@ -2765,7 +2765,7 @@ void deferred_split_huge_page(struct page *page)
 {
 	struct deferred_split *ds_queue = get_deferred_split_queue(page);
 #ifdef CONFIG_MEMCG
-	struct mem_cgroup *memcg = compound_head(page)->mem_cgroup;
+	struct mem_cgroup *memcg = page_memcg(compound_head(page));
 #endif
 	unsigned long flags;
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 3dcbf24d2227..3968d68503cb 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -533,7 +533,7 @@ struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page)
 {
 	struct mem_cgroup *memcg;
 
-	memcg = page->mem_cgroup;
+	memcg = page_memcg(page);
 
 	if (!memcg || !cgroup_subsys_on_dfl(memory_cgrp_subsys))
 		memcg = root_mem_cgroup;
@@ -560,16 +560,7 @@ ino_t page_cgroup_ino(struct page *page)
 	unsigned long ino = 0;
 
 	rcu_read_lock();
-	memcg = page->mem_cgroup;
-
-	/*
-	 * The lowest bit set means that memcg isn't a valid
-	 * memcg pointer, but a obj_cgroups pointer.
-	 * In this case the page is shared and doesn't belong
-	 * to any specific memory cgroup.
-	 */
-	if ((unsigned long) memcg & 0x1UL)
-		memcg = NULL;
+	memcg = page_memcg_check(page);
 
 	while (memcg && !(memcg->css.flags & CSS_ONLINE))
 		memcg = parent_mem_cgroup(memcg);
@@ -1050,7 +1041,7 @@ EXPORT_SYMBOL(get_mem_cgroup_from_mm);
  */
 struct mem_cgroup *get_mem_cgroup_from_page(struct page *page)
 {
-	struct mem_cgroup *memcg = page->mem_cgroup;
+	struct mem_cgroup *memcg = page_memcg(page);
 
 	if (mem_cgroup_disabled())
 		return NULL;
@@ -1349,7 +1340,7 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct pglist_data *pgd
 		goto out;
 	}
 
-	memcg = page->mem_cgroup;
+	memcg = page_memcg(page);
 	/*
 	 * Swapcache readahead pages are added to the LRU - and
 	 * possibly migrated - before they are charged.
@@ -2109,7 +2100,7 @@ void mem_cgroup_print_oom_group(struct mem_cgroup *memcg)
 }
 
 /**
- * lock_page_memcg - lock a page->mem_cgroup binding
+ * lock_page_memcg - lock a page and memcg binding
  * @page: the page
  *
  * This function protects unlocked LRU pages from being moved to
@@ -2141,7 +2132,7 @@ struct mem_cgroup *lock_page_memcg(struct page *page)
 	if (mem_cgroup_disabled())
 		return NULL;
 again:
-	memcg = head->mem_cgroup;
+	memcg = page_memcg(head);
 	if (unlikely(!memcg))
 		return NULL;
 
@@ -2149,7 +2140,7 @@ again:
 		return memcg;
 
 	spin_lock_irqsave(&memcg->move_lock, flags);
-	if (memcg != head->mem_cgroup) {
+	if (memcg != page_memcg(head)) {
 		spin_unlock_irqrestore(&memcg->move_lock, flags);
 		goto again;
 	}
@@ -2187,14 +2178,14 @@ void __unlock_page_memcg(struct mem_cgroup *memcg)
 }
 
 /**
- * unlock_page_memcg - unlock a page->mem_cgroup binding
+ * unlock_page_memcg - unlock a page and memcg binding
  * @page: the page
  */
 void unlock_page_memcg(struct page *page)
 {
 	struct page *head = compound_head(page);
 
-	__unlock_page_memcg(head->mem_cgroup);
+	__unlock_page_memcg(page_memcg(head));
 }
 EXPORT_SYMBOL(unlock_page_memcg);
 
@@ -2884,7 +2875,7 @@ static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
 
 static void commit_charge(struct page *page, struct mem_cgroup *memcg)
 {
-	VM_BUG_ON_PAGE(page->mem_cgroup, page);
+	VM_BUG_ON_PAGE(page_memcg(page), page);
 	/*
 	 * Any of the following ensures page->mem_cgroup stability:
 	 *
@@ -2893,7 +2884,7 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg)
 	 * - lock_page_memcg()
 	 * - exclusive reference
 	 */
-	page->mem_cgroup = memcg;
+	page->memcg_data = (unsigned long)memcg;
 }
 
 #ifdef CONFIG_MEMCG_KMEM
@@ -2908,8 +2899,7 @@ int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
 	if (!vec)
 		return -ENOMEM;
 
-	if (cmpxchg(&page->obj_cgroups, NULL,
-		    (struct obj_cgroup **) ((unsigned long)vec | 0x1UL)))
+	if (cmpxchg(&page->memcg_data, 0, (unsigned long)vec | 0x1UL))
 		kfree(vec);
 	else
 		kmemleak_not_leak(vec);
@@ -2920,6 +2910,12 @@ int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
 /*
  * Returns a pointer to the memory cgroup to which the kernel object is charged.
  *
+ * A passed kernel object can be a slab object or a generic kernel page, so
+ * different mechanisms for getting the memory cgroup pointer should be used.
+ * In certain cases (e.g. kernel stacks or large kmallocs with SLUB) the caller
+ * can not know for sure how the kernel object is implemented.
+ * mem_cgroup_from_obj() can be safely used in such cases.
+ *
  * The caller must ensure the memcg lifetime, e.g. by taking rcu_read_lock(),
  * cgroup_mutex, etc.
  */
@@ -2932,17 +2928,6 @@ struct mem_cgroup *mem_cgroup_from_obj(void *p)
 
 	page = virt_to_head_page(p);
 
-	/*
-	 * If page->mem_cgroup is set, it's either a simple mem_cgroup pointer
-	 * or a pointer to obj_cgroup vector. In the latter case the lowest
-	 * bit of the pointer is set.
-	 * The page->mem_cgroup pointer can be asynchronously changed
-	 * from NULL to (obj_cgroup_vec | 0x1UL), but can't be changed
-	 * from a valid memcg pointer to objcg vector or back.
-	 */
-	if (!page->mem_cgroup)
-		return NULL;
-
 	/*
 	 * Slab objects are accounted individually, not per-page.
 	 * Memcg membership data for each individual object is saved in
@@ -2960,8 +2945,14 @@ struct mem_cgroup *mem_cgroup_from_obj(void *p)
 		return NULL;
 	}
 
-	/* All other pages use page->mem_cgroup */
-	return page->mem_cgroup;
+	/*
+	 * page_memcg_check() is used here, because page_has_obj_cgroups()
+	 * check above could fail because the object cgroups vector wasn't set
+	 * at that moment, but it can be set concurrently.
+	 * page_memcg_check(page) will guarantee that a proper memory
+	 * cgroup pointer or NULL will be returned.
+	 */
+	return page_memcg_check(page);
 }
 
 __always_inline struct obj_cgroup *get_obj_cgroup_from_current(void)
@@ -3099,7 +3090,7 @@ int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order)
 	if (memcg && !mem_cgroup_is_root(memcg)) {
 		ret = __memcg_kmem_charge(memcg, gfp, 1 << order);
 		if (!ret) {
-			page->mem_cgroup = memcg;
+			page->memcg_data = (unsigned long)memcg;
 			__SetPageKmemcg(page);
 			return 0;
 		}
@@ -3115,7 +3106,7 @@ int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order)
  */
 void __memcg_kmem_uncharge_page(struct page *page, int order)
 {
-	struct mem_cgroup *memcg = page->mem_cgroup;
+	struct mem_cgroup *memcg = page_memcg(page);
 	unsigned int nr_pages = 1 << order;
 
 	if (!memcg)
@@ -3123,7 +3114,7 @@ void __memcg_kmem_uncharge_page(struct page *page, int order)
 
 	VM_BUG_ON_PAGE(mem_cgroup_is_root(memcg), page);
 	__memcg_kmem_uncharge(memcg, nr_pages);
-	page->mem_cgroup = NULL;
+	page->memcg_data = 0;
 	css_put(&memcg->css);
 
 	/* slab pages do not have PageKmemcg flag set */
@@ -3274,7 +3265,7 @@ void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size)
  */
 void mem_cgroup_split_huge_fixup(struct page *head)
 {
-	struct mem_cgroup *memcg = head->mem_cgroup;
+	struct mem_cgroup *memcg = page_memcg(head);
 	int i;
 
 	if (mem_cgroup_disabled())
@@ -3282,7 +3273,7 @@ void mem_cgroup_split_huge_fixup(struct page *head)
 
 	for (i = 1; i < HPAGE_PMD_NR; i++) {
 		css_get(&memcg->css);
-		head[i].mem_cgroup = memcg;
+		head[i].memcg_data = (unsigned long)memcg;
 	}
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
@@ -4664,7 +4655,7 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
 void mem_cgroup_track_foreign_dirty_slowpath(struct page *page,
 					     struct bdi_writeback *wb)
 {
-	struct mem_cgroup *memcg = page->mem_cgroup;
+	struct mem_cgroup *memcg = page_memcg(page);
 	struct memcg_cgwb_frn *frn;
 	u64 now = get_jiffies_64();
 	u64 oldest_at = now;
@@ -5641,14 +5632,14 @@ static int mem_cgroup_move_account(struct page *page,
 
 	/*
 	 * Prevent mem_cgroup_migrate() from looking at
-	 * page->mem_cgroup of its source page while we change it.
+	 * page's memory cgroup of its source page while we change it.
 	 */
 	ret = -EBUSY;
 	if (!trylock_page(page))
 		goto out;
 
 	ret = -EINVAL;
-	if (page->mem_cgroup != from)
+	if (page_memcg(page) != from)
 		goto out_unlock;
 
 	pgdat = page_pgdat(page);
@@ -5703,13 +5694,13 @@ static int mem_cgroup_move_account(struct page *page,
 	/*
 	 * All state has been migrated, let's switch to the new memcg.
 	 *
-	 * It is safe to change page->mem_cgroup here because the page
+	 * It is safe to change page's memcg here because the page
 	 * is referenced, charged, isolated, and locked: we can't race
 	 * with (un)charging, migration, LRU putback, or anything else
-	 * that would rely on a stable page->mem_cgroup.
+	 * that would rely on a stable page's memory cgroup.
 	 *
 	 * Note that lock_page_memcg is a memcg lock, not a page lock,
-	 * to save space. As soon as we switch page->mem_cgroup to a
+	 * to save space. As soon as we switch page's memory cgroup to a
 	 * new memcg that isn't locked, the above state can change
 	 * concurrently again. Make sure we're truly done with it.
 	 */
@@ -5718,7 +5709,7 @@ static int mem_cgroup_move_account(struct page *page,
 	css_get(&to->css);
 	css_put(&from->css);
 
-	page->mem_cgroup = to;
+	page->memcg_data = (unsigned long)to;
 
 	__unlock_page_memcg(from);
 
@@ -5784,7 +5775,7 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma,
 		 * mem_cgroup_move_account() checks the page is valid or
 		 * not under LRU exclusion.
 		 */
-		if (page->mem_cgroup == mc.from) {
+		if (page_memcg(page) == mc.from) {
 			ret = MC_TARGET_PAGE;
 			if (is_device_private_page(page))
 				ret = MC_TARGET_DEVICE;
@@ -5828,7 +5819,7 @@ static enum mc_target_type get_mctgt_type_thp(struct vm_area_struct *vma,
 	VM_BUG_ON_PAGE(!page || !PageHead(page), page);
 	if (!(mc.flags & MOVE_ANON))
 		return ret;
-	if (page->mem_cgroup == mc.from) {
+	if (page_memcg(page) == mc.from) {
 		ret = MC_TARGET_PAGE;
 		if (target) {
 			get_page(page);
@@ -6774,12 +6765,12 @@ int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask)
 		/*
 		 * Every swap fault against a single page tries to charge the
 		 * page, bail as early as possible.  shmem_unuse() encounters
-		 * already charged pages, too.  page->mem_cgroup is protected
-		 * by the page lock, which serializes swap cache removal, which
-		 * in turn serializes uncharging.
+		 * already charged pages, too.  page and memcg binding is
+		 * protected by the page lock, which serializes swap cache
+		 * removal, which in turn serializes uncharging.
 		 */
 		VM_BUG_ON_PAGE(!PageLocked(page), page);
-		if (compound_head(page)->mem_cgroup)
+		if (page_memcg(compound_head(page)))
 			goto out;
 
 		id = lookup_swap_cgroup_id(ent);
@@ -6863,21 +6854,21 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug)
 
 	VM_BUG_ON_PAGE(PageLRU(page), page);
 
-	if (!page->mem_cgroup)
+	if (!page_memcg(page))
 		return;
 
 	/*
 	 * Nobody should be changing or seriously looking at
-	 * page->mem_cgroup at this point, we have fully
+	 * page_memcg(page) at this point, we have fully
 	 * exclusive access to the page.
 	 */
 
-	if (ug->memcg != page->mem_cgroup) {
+	if (ug->memcg != page_memcg(page)) {
 		if (ug->memcg) {
 			uncharge_batch(ug);
 			uncharge_gather_clear(ug);
 		}
-		ug->memcg = page->mem_cgroup;
+		ug->memcg = page_memcg(page);
 
 		/* pairs with css_put in uncharge_batch */
 		css_get(&ug->memcg->css);
@@ -6894,7 +6885,7 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug)
 	}
 
 	ug->dummy_page = page;
-	page->mem_cgroup = NULL;
+	page->memcg_data = 0;
 	css_put(&ug->memcg->css);
 }
 
@@ -6937,7 +6928,7 @@ void mem_cgroup_uncharge(struct page *page)
 		return;
 
 	/* Don't touch page->lru of any random page, pre-check: */
-	if (!page->mem_cgroup)
+	if (!page_memcg(page))
 		return;
 
 	uncharge_gather_clear(&ug);
@@ -6987,11 +6978,11 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage)
 		return;
 
 	/* Page cache replacement: new page already charged? */
-	if (newpage->mem_cgroup)
+	if (page_memcg(newpage))
 		return;
 
 	/* Swapcache readahead pages can get replaced before being charged */
-	memcg = oldpage->mem_cgroup;
+	memcg = page_memcg(oldpage);
 	if (!memcg)
 		return;
 
@@ -7186,7 +7177,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
 	if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
 		return;
 
-	memcg = page->mem_cgroup;
+	memcg = page_memcg(page);
 
 	/* Readahead page, never charged */
 	if (!memcg)
@@ -7207,7 +7198,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
 	VM_BUG_ON_PAGE(oldid, page);
 	mod_memcg_state(swap_memcg, MEMCG_SWAP, nr_entries);
 
-	page->mem_cgroup = NULL;
+	page->memcg_data = 0;
 
 	if (!mem_cgroup_is_root(memcg))
 		page_counter_uncharge(&memcg->memory, nr_entries);
@@ -7250,7 +7241,7 @@ int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry)
 	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
 		return 0;
 
-	memcg = page->mem_cgroup;
+	memcg = page_memcg(page);
 
 	/* Readahead page, never charged */
 	if (!memcg)
@@ -7331,7 +7322,7 @@ bool mem_cgroup_swap_full(struct page *page)
 	if (cgroup_memory_noswap || !cgroup_subsys_on_dfl(memory_cgrp_subsys))
 		return false;
 
-	memcg = page->mem_cgroup;
+	memcg = page_memcg(page);
 	if (!memcg)
 		return false;
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 23f5066bd4a5..271133b8243b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1092,7 +1092,7 @@ static inline bool page_expected_state(struct page *page,
 	if (unlikely((unsigned long)page->mapping |
 			page_ref_count(page) |
 #ifdef CONFIG_MEMCG
-			(unsigned long)page->mem_cgroup |
+			(unsigned long)page_memcg(page) |
 #endif
 			(page->flags & check_flags)))
 		return false;
@@ -1117,7 +1117,7 @@ static const char *page_bad_reason(struct page *page, unsigned long flags)
 			bad_reason = "PAGE_FLAGS_CHECK_AT_FREE flag(s) set";
 	}
 #ifdef CONFIG_MEMCG
-	if (unlikely(page->mem_cgroup))
+	if (unlikely(page_memcg(page)))
 		bad_reason = "page still charged to cgroup";
 #endif
 	return bad_reason;
diff --git a/mm/page_io.c b/mm/page_io.c
index 433df1263349..9bca17ecc4df 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -291,12 +291,14 @@ static inline void count_swpout_vm_event(struct page *page)
 static void bio_associate_blkg_from_page(struct bio *bio, struct page *page)
 {
 	struct cgroup_subsys_state *css;
+	struct mem_cgroup *memcg;
 
-	if (!page->mem_cgroup)
+	memcg = page_memcg(page);
+	if (!memcg)
 		return;
 
 	rcu_read_lock();
-	css = cgroup_e_css(page->mem_cgroup->css.cgroup, &io_cgrp_subsys);
+	css = cgroup_e_css(memcg->css.cgroup, &io_cgrp_subsys);
 	bio_associate_blkg_from_css(bio, css);
 	rcu_read_unlock();
 }
diff --git a/mm/slab.h b/mm/slab.h
index 6d7c6a5056ba..e2535cee0d33 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -242,18 +242,17 @@ static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t fla
 static inline struct obj_cgroup **page_obj_cgroups(struct page *page)
 {
 	/*
-	 * page->mem_cgroup and page->obj_cgroups are sharing the same
+	 * Page's memory cgroup and obj_cgroups vector are sharing the same
 	 * space. To distinguish between them in case we don't know for sure
 	 * that the page is a slab page (e.g. page_cgroup_ino()), let's
 	 * always set the lowest bit of obj_cgroups.
 	 */
-	return (struct obj_cgroup **)
-		((unsigned long)page->obj_cgroups & ~0x1UL);
+	return (struct obj_cgroup **)(page->memcg_data & ~0x1UL);
 }
 
 static inline bool page_has_obj_cgroups(struct page *page)
 {
-	return ((unsigned long)page->obj_cgroups & 0x1UL);
+	return page->memcg_data & 0x1UL;
 }
 
 int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
@@ -262,7 +261,7 @@ int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
 static inline void memcg_free_page_obj_cgroups(struct page *page)
 {
 	kfree(page_obj_cgroups(page));
-	page->obj_cgroups = NULL;
+	page->memcg_data = 0;
 }
 
 static inline size_t obj_full_size(struct kmem_cache *s)
diff --git a/mm/workingset.c b/mm/workingset.c
index 975a4d2dd02e..130348cbf40a 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -257,7 +257,7 @@ void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg)
 	struct lruvec *lruvec;
 	int memcgid;
 
-	/* Page is fully exclusive and pins page->mem_cgroup */
+	/* Page is fully exclusive and pins page's memory cgroup pointer */
 	VM_BUG_ON_PAGE(PageLRU(page), page);
 	VM_BUG_ON_PAGE(page_count(page), page);
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
-- 
cgit v1.2.3


From 270c6a71460e12b07b1dcadf7457ff95b6c6e8f4 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Tue, 1 Dec 2020 13:58:28 -0800
Subject: mm: memcontrol/slab: Use helpers to access slab page's memcg_data

To gather all direct accesses to struct page's memcg_data field in one
place, let's introduce 3 new helpers to use in the slab accounting code:

  struct obj_cgroup **page_objcgs(struct page *page);
  struct obj_cgroup **page_objcgs_check(struct page *page);
  bool set_page_objcgs(struct page *page, struct obj_cgroup **objcgs);

They are similar to the corresponding API for generic pages, except that
the setter can return false, indicating that the value has been already
set from a different thread.

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Link: https://lkml.kernel.org/r/20201027001657.3398190-3-guro@fb.com
Link: https://lore.kernel.org/bpf/20201201215900.3569844-3-guro@fb.com
---
 include/linux/memcontrol.h | 64 ++++++++++++++++++++++++++++++++++++++++++++++
 mm/memcontrol.c            |  6 ++---
 mm/slab.h                  | 35 ++++++-------------------
 3 files changed, 75 insertions(+), 30 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index f95c1433461c..c7ac0a5b8989 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -416,6 +416,70 @@ static inline struct mem_cgroup *page_memcg_check(struct page *page)
 	return (struct mem_cgroup *)memcg_data;
 }
 
+#ifdef CONFIG_MEMCG_KMEM
+/*
+ * page_objcgs - get the object cgroups vector associated with a page
+ * @page: a pointer to the page struct
+ *
+ * Returns a pointer to the object cgroups vector associated with the page,
+ * or NULL. This function assumes that the page is known to have an
+ * associated object cgroups vector. It's not safe to call this function
+ * against pages, which might have an associated memory cgroup: e.g.
+ * kernel stack pages.
+ */
+static inline struct obj_cgroup **page_objcgs(struct page *page)
+{
+	return (struct obj_cgroup **)(READ_ONCE(page->memcg_data) & ~0x1UL);
+}
+
+/*
+ * page_objcgs_check - get the object cgroups vector associated with a page
+ * @page: a pointer to the page struct
+ *
+ * Returns a pointer to the object cgroups vector associated with the page,
+ * or NULL. This function is safe to use if the page can be directly associated
+ * with a memory cgroup.
+ */
+static inline struct obj_cgroup **page_objcgs_check(struct page *page)
+{
+	unsigned long memcg_data = READ_ONCE(page->memcg_data);
+
+	if (memcg_data && (memcg_data & 0x1UL))
+		return (struct obj_cgroup **)(memcg_data & ~0x1UL);
+
+	return NULL;
+}
+
+/*
+ * set_page_objcgs - associate a page with a object cgroups vector
+ * @page: a pointer to the page struct
+ * @objcgs: a pointer to the object cgroups vector
+ *
+ * Atomically associates a page with a vector of object cgroups.
+ */
+static inline bool set_page_objcgs(struct page *page,
+					struct obj_cgroup **objcgs)
+{
+	return !cmpxchg(&page->memcg_data, 0, (unsigned long)objcgs | 0x1UL);
+}
+#else
+static inline struct obj_cgroup **page_objcgs(struct page *page)
+{
+	return NULL;
+}
+
+static inline struct obj_cgroup **page_objcgs_check(struct page *page)
+{
+	return NULL;
+}
+
+static inline bool set_page_objcgs(struct page *page,
+					struct obj_cgroup **objcgs)
+{
+	return true;
+}
+#endif
+
 static __always_inline bool memcg_stat_item_in_bytes(int idx)
 {
 	if (idx == MEMCG_PERCPU_B)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 3968d68503cb..0054b4846770 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2899,7 +2899,7 @@ int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
 	if (!vec)
 		return -ENOMEM;
 
-	if (cmpxchg(&page->memcg_data, 0, (unsigned long)vec | 0x1UL))
+	if (!set_page_objcgs(page, vec))
 		kfree(vec);
 	else
 		kmemleak_not_leak(vec);
@@ -2933,12 +2933,12 @@ struct mem_cgroup *mem_cgroup_from_obj(void *p)
 	 * Memcg membership data for each individual object is saved in
 	 * the page->obj_cgroups.
 	 */
-	if (page_has_obj_cgroups(page)) {
+	if (page_objcgs_check(page)) {
 		struct obj_cgroup *objcg;
 		unsigned int off;
 
 		off = obj_to_index(page->slab_cache, page, p);
-		objcg = page_obj_cgroups(page)[off];
+		objcg = page_objcgs(page)[off];
 		if (objcg)
 			return obj_cgroup_memcg(objcg);
 
diff --git a/mm/slab.h b/mm/slab.h
index e2535cee0d33..9a54a0cb5cca 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -239,28 +239,12 @@ static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t fla
 }
 
 #ifdef CONFIG_MEMCG_KMEM
-static inline struct obj_cgroup **page_obj_cgroups(struct page *page)
-{
-	/*
-	 * Page's memory cgroup and obj_cgroups vector are sharing the same
-	 * space. To distinguish between them in case we don't know for sure
-	 * that the page is a slab page (e.g. page_cgroup_ino()), let's
-	 * always set the lowest bit of obj_cgroups.
-	 */
-	return (struct obj_cgroup **)(page->memcg_data & ~0x1UL);
-}
-
-static inline bool page_has_obj_cgroups(struct page *page)
-{
-	return page->memcg_data & 0x1UL;
-}
-
 int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
 				 gfp_t gfp);
 
 static inline void memcg_free_page_obj_cgroups(struct page *page)
 {
-	kfree(page_obj_cgroups(page));
+	kfree(page_objcgs(page));
 	page->memcg_data = 0;
 }
 
@@ -322,7 +306,7 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
 		if (likely(p[i])) {
 			page = virt_to_head_page(p[i]);
 
-			if (!page_has_obj_cgroups(page) &&
+			if (!page_objcgs(page) &&
 			    memcg_alloc_page_obj_cgroups(page, s, flags)) {
 				obj_cgroup_uncharge(objcg, obj_full_size(s));
 				continue;
@@ -330,7 +314,7 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
 
 			off = obj_to_index(s, page, p[i]);
 			obj_cgroup_get(objcg);
-			page_obj_cgroups(page)[off] = objcg;
+			page_objcgs(page)[off] = objcg;
 			mod_objcg_state(objcg, page_pgdat(page),
 					cache_vmstat_idx(s), obj_full_size(s));
 		} else {
@@ -344,6 +328,7 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s_orig,
 					void **p, int objects)
 {
 	struct kmem_cache *s;
+	struct obj_cgroup **objcgs;
 	struct obj_cgroup *objcg;
 	struct page *page;
 	unsigned int off;
@@ -357,7 +342,8 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s_orig,
 			continue;
 
 		page = virt_to_head_page(p[i]);
-		if (!page_has_obj_cgroups(page))
+		objcgs = page_objcgs(page);
+		if (!objcgs)
 			continue;
 
 		if (!s_orig)
@@ -366,11 +352,11 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s_orig,
 			s = s_orig;
 
 		off = obj_to_index(s, page, p[i]);
-		objcg = page_obj_cgroups(page)[off];
+		objcg = objcgs[off];
 		if (!objcg)
 			continue;
 
-		page_obj_cgroups(page)[off] = NULL;
+		objcgs[off] = NULL;
 		obj_cgroup_uncharge(objcg, obj_full_size(s));
 		mod_objcg_state(objcg, page_pgdat(page), cache_vmstat_idx(s),
 				-obj_full_size(s));
@@ -379,11 +365,6 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s_orig,
 }
 
 #else /* CONFIG_MEMCG_KMEM */
-static inline bool page_has_obj_cgroups(struct page *page)
-{
-	return false;
-}
-
 static inline struct mem_cgroup *memcg_from_slab_obj(void *ptr)
 {
 	return NULL;
-- 
cgit v1.2.3


From 87944e2992bd28098c6806086a1e96bb4d0e502b Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Tue, 1 Dec 2020 13:58:29 -0800
Subject: mm: Introduce page memcg flags

The lowest bit in page->memcg_data is used to distinguish between struct
memory_cgroup pointer and a pointer to a objcgs array.  All checks and
modifications of this bit are open-coded.

Let's formalize it using page memcg flags, defined in enum
page_memcg_data_flags.

Additional flags might be added later.

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Link: https://lkml.kernel.org/r/20201027001657.3398190-4-guro@fb.com
Link: https://lore.kernel.org/bpf/20201201215900.3569844-4-guro@fb.com
---
 include/linux/memcontrol.h | 32 ++++++++++++++++++++------------
 1 file changed, 20 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index c7ac0a5b8989..99a4841d658b 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -343,6 +343,15 @@ struct mem_cgroup {
 
 extern struct mem_cgroup *root_mem_cgroup;
 
+enum page_memcg_data_flags {
+	/* page->memcg_data is a pointer to an objcgs vector */
+	MEMCG_DATA_OBJCGS = (1UL << 0),
+	/* the next bit after the last actual flag */
+	__NR_MEMCG_DATA_FLAGS  = (1UL << 1),
+};
+
+#define MEMCG_DATA_FLAGS_MASK (__NR_MEMCG_DATA_FLAGS - 1)
+
 /*
  * page_memcg - get the memory cgroup associated with a page
  * @page: a pointer to the page struct
@@ -404,13 +413,7 @@ static inline struct mem_cgroup *page_memcg_check(struct page *page)
 	 */
 	unsigned long memcg_data = READ_ONCE(page->memcg_data);
 
-	/*
-	 * The lowest bit set means that memcg isn't a valid
-	 * memcg pointer, but a obj_cgroups pointer.
-	 * In this case the page is shared and doesn't belong
-	 * to any specific memory cgroup.
-	 */
-	if (memcg_data & 0x1UL)
+	if (memcg_data & MEMCG_DATA_OBJCGS)
 		return NULL;
 
 	return (struct mem_cgroup *)memcg_data;
@@ -429,7 +432,11 @@ static inline struct mem_cgroup *page_memcg_check(struct page *page)
  */
 static inline struct obj_cgroup **page_objcgs(struct page *page)
 {
-	return (struct obj_cgroup **)(READ_ONCE(page->memcg_data) & ~0x1UL);
+	unsigned long memcg_data = READ_ONCE(page->memcg_data);
+
+	VM_BUG_ON_PAGE(memcg_data && !(memcg_data & MEMCG_DATA_OBJCGS), page);
+
+	return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
 }
 
 /*
@@ -444,10 +451,10 @@ static inline struct obj_cgroup **page_objcgs_check(struct page *page)
 {
 	unsigned long memcg_data = READ_ONCE(page->memcg_data);
 
-	if (memcg_data && (memcg_data & 0x1UL))
-		return (struct obj_cgroup **)(memcg_data & ~0x1UL);
+	if (!memcg_data || !(memcg_data & MEMCG_DATA_OBJCGS))
+		return NULL;
 
-	return NULL;
+	return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
 }
 
 /*
@@ -460,7 +467,8 @@ static inline struct obj_cgroup **page_objcgs_check(struct page *page)
 static inline bool set_page_objcgs(struct page *page,
 					struct obj_cgroup **objcgs)
 {
-	return !cmpxchg(&page->memcg_data, 0, (unsigned long)objcgs | 0x1UL);
+	return !cmpxchg(&page->memcg_data, 0, (unsigned long)objcgs |
+			MEMCG_DATA_OBJCGS);
 }
 #else
 static inline struct obj_cgroup **page_objcgs(struct page *page)
-- 
cgit v1.2.3


From 18b2db3b0385226b71cb3288474fa5a6e4a45474 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Tue, 1 Dec 2020 13:58:30 -0800
Subject: mm: Convert page kmemcg type to a page memcg flag

PageKmemcg flag is currently defined as a page type (like buddy, offline,
table and guard).  Semantically it means that the page was accounted as a
kernel memory by the page allocator and has to be uncharged on the
release.

As a side effect of defining the flag as a page type, the accounted page
can't be mapped to userspace (look at page_has_type() and comments above).
In particular, this blocks the accounting of vmalloc-backed memory used
by some bpf maps, because these maps do map the memory to userspace.

One option is to fix it by complicating the access to page->mapcount,
which provides some free bits for page->page_type.

But it's way better to move this flag into page->memcg_data flags.
Indeed, the flag makes no sense without enabled memory cgroups and memory
cgroup pointer set in particular.

This commit replaces PageKmemcg() and __SetPageKmemcg() with
PageMemcgKmem() and an open-coded OR operation setting the memcg pointer
with the MEMCG_DATA_KMEM bit.  __ClearPageKmemcg() can be simple deleted,
as the whole memcg_data is zeroed at once.

As a bonus, on !CONFIG_MEMCG build the PageMemcgKmem() check will be
compiled out.

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Link: https://lkml.kernel.org/r/20201027001657.3398190-5-guro@fb.com
Link: https://lore.kernel.org/bpf/20201201215900.3569844-5-guro@fb.com
---
 include/linux/memcontrol.h | 37 +++++++++++++++++++++++++++++++++----
 include/linux/page-flags.h | 11 ++---------
 mm/memcontrol.c            | 16 +++++-----------
 mm/page_alloc.c            |  4 ++--
 4 files changed, 42 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 99a4841d658b..7c9d43476166 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -346,8 +346,10 @@ extern struct mem_cgroup *root_mem_cgroup;
 enum page_memcg_data_flags {
 	/* page->memcg_data is a pointer to an objcgs vector */
 	MEMCG_DATA_OBJCGS = (1UL << 0),
+	/* page has been accounted as a non-slab kernel page */
+	MEMCG_DATA_KMEM = (1UL << 1),
 	/* the next bit after the last actual flag */
-	__NR_MEMCG_DATA_FLAGS  = (1UL << 1),
+	__NR_MEMCG_DATA_FLAGS  = (1UL << 2),
 };
 
 #define MEMCG_DATA_FLAGS_MASK (__NR_MEMCG_DATA_FLAGS - 1)
@@ -369,8 +371,12 @@ enum page_memcg_data_flags {
  */
 static inline struct mem_cgroup *page_memcg(struct page *page)
 {
+	unsigned long memcg_data = page->memcg_data;
+
 	VM_BUG_ON_PAGE(PageSlab(page), page);
-	return (struct mem_cgroup *)page->memcg_data;
+	VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_OBJCGS, page);
+
+	return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
 }
 
 /*
@@ -387,7 +393,8 @@ static inline struct mem_cgroup *page_memcg_rcu(struct page *page)
 	VM_BUG_ON_PAGE(PageSlab(page), page);
 	WARN_ON_ONCE(!rcu_read_lock_held());
 
-	return (struct mem_cgroup *)READ_ONCE(page->memcg_data);
+	return (struct mem_cgroup *)(READ_ONCE(page->memcg_data) &
+				     ~MEMCG_DATA_FLAGS_MASK);
 }
 
 /*
@@ -416,7 +423,21 @@ static inline struct mem_cgroup *page_memcg_check(struct page *page)
 	if (memcg_data & MEMCG_DATA_OBJCGS)
 		return NULL;
 
-	return (struct mem_cgroup *)memcg_data;
+	return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
+}
+
+/*
+ * PageMemcgKmem - check if the page has MemcgKmem flag set
+ * @page: a pointer to the page struct
+ *
+ * Checks if the page has MemcgKmem flag set. The caller must ensure that
+ * the page has an associated memory cgroup. It's not safe to call this function
+ * against some types of pages, e.g. slab pages.
+ */
+static inline bool PageMemcgKmem(struct page *page)
+{
+	VM_BUG_ON_PAGE(page->memcg_data & MEMCG_DATA_OBJCGS, page);
+	return page->memcg_data & MEMCG_DATA_KMEM;
 }
 
 #ifdef CONFIG_MEMCG_KMEM
@@ -435,6 +456,7 @@ static inline struct obj_cgroup **page_objcgs(struct page *page)
 	unsigned long memcg_data = READ_ONCE(page->memcg_data);
 
 	VM_BUG_ON_PAGE(memcg_data && !(memcg_data & MEMCG_DATA_OBJCGS), page);
+	VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_KMEM, page);
 
 	return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
 }
@@ -454,6 +476,8 @@ static inline struct obj_cgroup **page_objcgs_check(struct page *page)
 	if (!memcg_data || !(memcg_data & MEMCG_DATA_OBJCGS))
 		return NULL;
 
+	VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_KMEM, page);
+
 	return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
 }
 
@@ -1109,6 +1133,11 @@ static inline struct mem_cgroup *page_memcg_check(struct page *page)
 	return NULL;
 }
 
+static inline bool PageMemcgKmem(struct page *page)
+{
+	return false;
+}
+
 static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg)
 {
 	return true;
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 4f6ba9379112..fc0e1bd48e73 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -715,9 +715,8 @@ PAGEFLAG_FALSE(DoubleMap)
 #define PAGE_MAPCOUNT_RESERVE	-128
 #define PG_buddy	0x00000080
 #define PG_offline	0x00000100
-#define PG_kmemcg	0x00000200
-#define PG_table	0x00000400
-#define PG_guard	0x00000800
+#define PG_table	0x00000200
+#define PG_guard	0x00000400
 
 #define PageType(page, flag)						\
 	((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE)
@@ -768,12 +767,6 @@ PAGE_TYPE_OPS(Buddy, buddy)
  */
 PAGE_TYPE_OPS(Offline, offline)
 
-/*
- * If kmemcg is enabled, the buddy allocator will set PageKmemcg() on
- * pages allocated with __GFP_ACCOUNT. It gets cleared on page free.
- */
-PAGE_TYPE_OPS(Kmemcg, kmemcg)
-
 /*
  * Marks pages in use as page tables.
  */
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 0054b4846770..e0366e306221 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3090,8 +3090,8 @@ int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order)
 	if (memcg && !mem_cgroup_is_root(memcg)) {
 		ret = __memcg_kmem_charge(memcg, gfp, 1 << order);
 		if (!ret) {
-			page->memcg_data = (unsigned long)memcg;
-			__SetPageKmemcg(page);
+			page->memcg_data = (unsigned long)memcg |
+				MEMCG_DATA_KMEM;
 			return 0;
 		}
 		css_put(&memcg->css);
@@ -3116,10 +3116,6 @@ void __memcg_kmem_uncharge_page(struct page *page, int order)
 	__memcg_kmem_uncharge(memcg, nr_pages);
 	page->memcg_data = 0;
 	css_put(&memcg->css);
-
-	/* slab pages do not have PageKmemcg flag set */
-	if (PageKmemcg(page))
-		__ClearPageKmemcg(page);
 }
 
 static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes)
@@ -6877,12 +6873,10 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug)
 	nr_pages = compound_nr(page);
 	ug->nr_pages += nr_pages;
 
-	if (!PageKmemcg(page)) {
-		ug->pgpgout++;
-	} else {
+	if (PageMemcgKmem(page))
 		ug->nr_kmem += nr_pages;
-		__ClearPageKmemcg(page);
-	}
+	else
+		ug->pgpgout++;
 
 	ug->dummy_page = page;
 	page->memcg_data = 0;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 271133b8243b..3c53018c9c61 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1214,7 +1214,7 @@ static __always_inline bool free_pages_prepare(struct page *page,
 		 * Do not let hwpoison pages hit pcplists/buddy
 		 * Untie memcg state and reset page's owner
 		 */
-		if (memcg_kmem_enabled() && PageKmemcg(page))
+		if (memcg_kmem_enabled() && PageMemcgKmem(page))
 			__memcg_kmem_uncharge_page(page, order);
 		reset_page_owner(page, order);
 		return false;
@@ -1244,7 +1244,7 @@ static __always_inline bool free_pages_prepare(struct page *page,
 	}
 	if (PageMappingFlags(page))
 		page->mapping = NULL;
-	if (memcg_kmem_enabled() && PageKmemcg(page))
+	if (memcg_kmem_enabled() && PageMemcgKmem(page))
 		__memcg_kmem_uncharge_page(page, order);
 	if (check_free)
 		bad += check_free_page(page);
-- 
cgit v1.2.3


From 48edc1f78aabeba35ed00e40c36f211de89e0090 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Tue, 1 Dec 2020 13:58:32 -0800
Subject: bpf: Prepare for memcg-based memory accounting for bpf maps

Bpf maps can be updated from an interrupt context and in such
case there is no process which can be charged. It makes the memory
accounting of bpf maps non-trivial.

Fortunately, after commit 4127c6504f25 ("mm: kmem: enable kernel
memcg accounting from interrupt contexts") and commit b87d8cefe43c
("mm, memcg: rework remote charging API to support nesting")
it's finally possible.

To make the ownership model simple and consistent, when the map
is created, the memory cgroup of the current process is recorded.
All subsequent allocations related to the bpf map are charged to
the same memory cgroup. It includes allocations made by any processes
(even if they do belong to a different cgroup) and from interrupts.

This commit introduces 3 new helpers, which will be used by following
commits to enable the accounting of bpf maps memory:
  - bpf_map_kmalloc_node()
  - bpf_map_kzalloc()
  - bpf_map_alloc_percpu()

They are wrapping popular memory allocation functions. They set
the active memory cgroup to the map's memory cgroup and add
__GFP_ACCOUNT to the passed gfp flags. Then they call into
the corresponding memory allocation function and restore
the original active memory cgroup.

These helpers are supposed to use everywhere except the map creation
path. During the map creation when the map structure is allocated by
itself, it cannot be passed to those helpers. In those cases default
memory allocation function will be used with the __GFP_ACCOUNT flag.

Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20201201215900.3569844-7-guro@fb.com
---
 include/linux/bpf.h  | 34 ++++++++++++++++++++++++++++
 kernel/bpf/syscall.c | 63 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 97 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index e1bcb6d7345c..e1f2c95c15ec 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -20,6 +20,8 @@
 #include <linux/module.h>
 #include <linux/kallsyms.h>
 #include <linux/capability.h>
+#include <linux/sched/mm.h>
+#include <linux/slab.h>
 
 struct bpf_verifier_env;
 struct bpf_verifier_log;
@@ -37,6 +39,7 @@ struct bpf_iter_aux_info;
 struct bpf_local_storage;
 struct bpf_local_storage_map;
 struct kobject;
+struct mem_cgroup;
 
 extern struct idr btf_idr;
 extern spinlock_t btf_idr_lock;
@@ -161,6 +164,9 @@ struct bpf_map {
 	u32 btf_value_type_id;
 	struct btf *btf;
 	struct bpf_map_memory memory;
+#ifdef CONFIG_MEMCG_KMEM
+	struct mem_cgroup *memcg;
+#endif
 	char name[BPF_OBJ_NAME_LEN];
 	u32 btf_vmlinux_value_type_id;
 	bool bypass_spec_v1;
@@ -1240,6 +1246,34 @@ int  generic_map_delete_batch(struct bpf_map *map,
 struct bpf_map *bpf_map_get_curr_or_next(u32 *id);
 struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id);
 
+#ifdef CONFIG_MEMCG_KMEM
+void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags,
+			   int node);
+void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags);
+void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size,
+				    size_t align, gfp_t flags);
+#else
+static inline void *
+bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags,
+		     int node)
+{
+	return kmalloc_node(size, flags, node);
+}
+
+static inline void *
+bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags)
+{
+	return kzalloc(size, flags);
+}
+
+static inline void __percpu *
+bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align,
+		     gfp_t flags)
+{
+	return __alloc_percpu_gfp(size, align, flags);
+}
+#endif
+
 extern int sysctl_unprivileged_bpf_disabled;
 
 static inline bool bpf_allow_ptr_leaks(void)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index f3fe9f53f93c..dedbf6d4cd84 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -31,6 +31,7 @@
 #include <linux/poll.h>
 #include <linux/bpf-netns.h>
 #include <linux/rcupdate_trace.h>
+#include <linux/memcontrol.h>
 
 #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
 			  (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \
@@ -456,6 +457,65 @@ void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock)
 		__release(&map_idr_lock);
 }
 
+#ifdef CONFIG_MEMCG_KMEM
+static void bpf_map_save_memcg(struct bpf_map *map)
+{
+	map->memcg = get_mem_cgroup_from_mm(current->mm);
+}
+
+static void bpf_map_release_memcg(struct bpf_map *map)
+{
+	mem_cgroup_put(map->memcg);
+}
+
+void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags,
+			   int node)
+{
+	struct mem_cgroup *old_memcg;
+	void *ptr;
+
+	old_memcg = set_active_memcg(map->memcg);
+	ptr = kmalloc_node(size, flags | __GFP_ACCOUNT, node);
+	set_active_memcg(old_memcg);
+
+	return ptr;
+}
+
+void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags)
+{
+	struct mem_cgroup *old_memcg;
+	void *ptr;
+
+	old_memcg = set_active_memcg(map->memcg);
+	ptr = kzalloc(size, flags | __GFP_ACCOUNT);
+	set_active_memcg(old_memcg);
+
+	return ptr;
+}
+
+void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size,
+				    size_t align, gfp_t flags)
+{
+	struct mem_cgroup *old_memcg;
+	void __percpu *ptr;
+
+	old_memcg = set_active_memcg(map->memcg);
+	ptr = __alloc_percpu_gfp(size, align, flags | __GFP_ACCOUNT);
+	set_active_memcg(old_memcg);
+
+	return ptr;
+}
+
+#else
+static void bpf_map_save_memcg(struct bpf_map *map)
+{
+}
+
+static void bpf_map_release_memcg(struct bpf_map *map)
+{
+}
+#endif
+
 /* called from workqueue */
 static void bpf_map_free_deferred(struct work_struct *work)
 {
@@ -464,6 +524,7 @@ static void bpf_map_free_deferred(struct work_struct *work)
 
 	bpf_map_charge_move(&mem, &map->memory);
 	security_bpf_map_free(map);
+	bpf_map_release_memcg(map);
 	/* implementation dependent freeing */
 	map->ops->map_free(map);
 	bpf_map_charge_finish(&mem);
@@ -875,6 +936,8 @@ static int map_create(union bpf_attr *attr)
 	if (err)
 		goto free_map_sec;
 
+	bpf_map_save_memcg(map);
+
 	err = bpf_map_new_fd(map, f_flags);
 	if (err < 0) {
 		/* failed to allocate fd.
-- 
cgit v1.2.3


From 80ee81e0403c48f4eb342f7c8d40477c89b8836a Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Tue, 1 Dec 2020 13:58:58 -0800
Subject: bpf: Eliminate rlimit-based memory accounting infra for bpf maps

Remove rlimit-based accounting infrastructure code, which is not used
anymore.

To provide a backward compatibility, use an approximation of the
bpf map memory footprint as a "memlock" value, available to a user
via map info. The approximation is based on the maximal number of
elements and key and value sizes.

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20201201215900.3569844-33-guro@fb.com
---
 include/linux/bpf.h                                | 12 ---
 kernel/bpf/syscall.c                               | 96 ++++------------------
 .../testing/selftests/bpf/progs/bpf_iter_bpf_map.c |  2 +-
 tools/testing/selftests/bpf/progs/map_ptr_kern.c   |  7 --
 4 files changed, 17 insertions(+), 100 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index e1f2c95c15ec..61331a148cde 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -138,11 +138,6 @@ struct bpf_map_ops {
 	const struct bpf_iter_seq_info *iter_seq_info;
 };
 
-struct bpf_map_memory {
-	u32 pages;
-	struct user_struct *user;
-};
-
 struct bpf_map {
 	/* The first two cachelines with read-mostly members of which some
 	 * are also accessed in fast-path (e.g. ops, max_entries).
@@ -163,7 +158,6 @@ struct bpf_map {
 	u32 btf_key_type_id;
 	u32 btf_value_type_id;
 	struct btf *btf;
-	struct bpf_map_memory memory;
 #ifdef CONFIG_MEMCG_KMEM
 	struct mem_cgroup *memcg;
 #endif
@@ -1224,12 +1218,6 @@ void bpf_map_inc_with_uref(struct bpf_map *map);
 struct bpf_map * __must_check bpf_map_inc_not_zero(struct bpf_map *map);
 void bpf_map_put_with_uref(struct bpf_map *map);
 void bpf_map_put(struct bpf_map *map);
-int bpf_map_charge_memlock(struct bpf_map *map, u32 pages);
-void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages);
-int bpf_map_charge_init(struct bpf_map_memory *mem, u64 size);
-void bpf_map_charge_finish(struct bpf_map_memory *mem);
-void bpf_map_charge_move(struct bpf_map_memory *dst,
-			 struct bpf_map_memory *src);
 void *bpf_map_area_alloc(u64 size, int numa_node);
 void *bpf_map_area_mmapable_alloc(u64 size, int numa_node);
 void bpf_map_area_free(void *base);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index dff3a5f62d7a..29096d96d989 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -128,7 +128,7 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
 	return map;
 }
 
-static u32 bpf_map_value_size(struct bpf_map *map)
+static u32 bpf_map_value_size(const struct bpf_map *map)
 {
 	if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
 	    map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
@@ -346,77 +346,6 @@ void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr)
 	map->numa_node = bpf_map_attr_numa_node(attr);
 }
 
-static int bpf_charge_memlock(struct user_struct *user, u32 pages)
-{
-	unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
-
-	if (atomic_long_add_return(pages, &user->locked_vm) > memlock_limit) {
-		atomic_long_sub(pages, &user->locked_vm);
-		return -EPERM;
-	}
-	return 0;
-}
-
-static void bpf_uncharge_memlock(struct user_struct *user, u32 pages)
-{
-	if (user)
-		atomic_long_sub(pages, &user->locked_vm);
-}
-
-int bpf_map_charge_init(struct bpf_map_memory *mem, u64 size)
-{
-	u32 pages = round_up(size, PAGE_SIZE) >> PAGE_SHIFT;
-	struct user_struct *user;
-	int ret;
-
-	if (size >= U32_MAX - PAGE_SIZE)
-		return -E2BIG;
-
-	user = get_current_user();
-	ret = bpf_charge_memlock(user, pages);
-	if (ret) {
-		free_uid(user);
-		return ret;
-	}
-
-	mem->pages = pages;
-	mem->user = user;
-
-	return 0;
-}
-
-void bpf_map_charge_finish(struct bpf_map_memory *mem)
-{
-	bpf_uncharge_memlock(mem->user, mem->pages);
-	free_uid(mem->user);
-}
-
-void bpf_map_charge_move(struct bpf_map_memory *dst,
-			 struct bpf_map_memory *src)
-{
-	*dst = *src;
-
-	/* Make sure src will not be used for the redundant uncharging. */
-	memset(src, 0, sizeof(struct bpf_map_memory));
-}
-
-int bpf_map_charge_memlock(struct bpf_map *map, u32 pages)
-{
-	int ret;
-
-	ret = bpf_charge_memlock(map->memory.user, pages);
-	if (ret)
-		return ret;
-	map->memory.pages += pages;
-	return ret;
-}
-
-void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages)
-{
-	bpf_uncharge_memlock(map->memory.user, pages);
-	map->memory.pages -= pages;
-}
-
 static int bpf_map_alloc_id(struct bpf_map *map)
 {
 	int id;
@@ -524,14 +453,11 @@ static void bpf_map_release_memcg(struct bpf_map *map)
 static void bpf_map_free_deferred(struct work_struct *work)
 {
 	struct bpf_map *map = container_of(work, struct bpf_map, work);
-	struct bpf_map_memory mem;
 
-	bpf_map_charge_move(&mem, &map->memory);
 	security_bpf_map_free(map);
 	bpf_map_release_memcg(map);
 	/* implementation dependent freeing */
 	map->ops->map_free(map);
-	bpf_map_charge_finish(&mem);
 }
 
 static void bpf_map_put_uref(struct bpf_map *map)
@@ -592,6 +518,19 @@ static fmode_t map_get_sys_perms(struct bpf_map *map, struct fd f)
 }
 
 #ifdef CONFIG_PROC_FS
+/* Provides an approximation of the map's memory footprint.
+ * Used only to provide a backward compatibility and display
+ * a reasonable "memlock" info.
+ */
+static unsigned long bpf_map_memory_footprint(const struct bpf_map *map)
+{
+	unsigned long size;
+
+	size = round_up(map->key_size + bpf_map_value_size(map), 8);
+
+	return round_up(map->max_entries * size, PAGE_SIZE);
+}
+
 static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
 {
 	const struct bpf_map *map = filp->private_data;
@@ -610,7 +549,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
 		   "value_size:\t%u\n"
 		   "max_entries:\t%u\n"
 		   "map_flags:\t%#x\n"
-		   "memlock:\t%llu\n"
+		   "memlock:\t%lu\n"
 		   "map_id:\t%u\n"
 		   "frozen:\t%u\n",
 		   map->map_type,
@@ -618,7 +557,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
 		   map->value_size,
 		   map->max_entries,
 		   map->map_flags,
-		   map->memory.pages * 1ULL << PAGE_SHIFT,
+		   bpf_map_memory_footprint(map),
 		   map->id,
 		   READ_ONCE(map->frozen));
 	if (type) {
@@ -861,7 +800,6 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
 static int map_create(union bpf_attr *attr)
 {
 	int numa_node = bpf_map_attr_numa_node(attr);
-	struct bpf_map_memory mem;
 	struct bpf_map *map;
 	int f_flags;
 	int err;
@@ -960,9 +898,7 @@ free_map_sec:
 	security_bpf_map_free(map);
 free_map:
 	btf_put(map->btf);
-	bpf_map_charge_move(&mem, &map->memory);
 	map->ops->map_free(map);
-	bpf_map_charge_finish(&mem);
 	return err;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c
index 08651b23edba..b83b5d2e17dc 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c
@@ -23,6 +23,6 @@ int dump_bpf_map(struct bpf_iter__bpf_map *ctx)
 
 	BPF_SEQ_PRINTF(seq, "%8u %8ld %8ld %10lu\n", map->id, map->refcnt.counter,
 		       map->usercnt.counter,
-		       map->memory.user->locked_vm.counter);
+		       0LLU);
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/map_ptr_kern.c b/tools/testing/selftests/bpf/progs/map_ptr_kern.c
index c325405751e2..d8850bc6a9f1 100644
--- a/tools/testing/selftests/bpf/progs/map_ptr_kern.c
+++ b/tools/testing/selftests/bpf/progs/map_ptr_kern.c
@@ -26,17 +26,12 @@ __u32 g_line = 0;
 		return 0;	\
 })
 
-struct bpf_map_memory {
-	__u32 pages;
-} __attribute__((preserve_access_index));
-
 struct bpf_map {
 	enum bpf_map_type map_type;
 	__u32 key_size;
 	__u32 value_size;
 	__u32 max_entries;
 	__u32 id;
-	struct bpf_map_memory memory;
 } __attribute__((preserve_access_index));
 
 static inline int check_bpf_map_fields(struct bpf_map *map, __u32 key_size,
@@ -47,7 +42,6 @@ static inline int check_bpf_map_fields(struct bpf_map *map, __u32 key_size,
 	VERIFY(map->value_size == value_size);
 	VERIFY(map->max_entries == max_entries);
 	VERIFY(map->id > 0);
-	VERIFY(map->memory.pages > 0);
 
 	return 1;
 }
@@ -60,7 +54,6 @@ static inline int check_bpf_map_ptr(struct bpf_map *indirect,
 	VERIFY(indirect->value_size == direct->value_size);
 	VERIFY(indirect->max_entries == direct->max_entries);
 	VERIFY(indirect->id == direct->id);
-	VERIFY(indirect->memory.pages == direct->memory.pages);
 
 	return 1;
 }
-- 
cgit v1.2.3


From 3ac1f01b43b6e2759cc34d3a715ba5eed04c5805 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Tue, 1 Dec 2020 13:58:59 -0800
Subject: bpf: Eliminate rlimit-based memory accounting for bpf progs

Do not use rlimit-based memory accounting for bpf progs. It has been
replaced with memcg-based memory accounting.

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20201201215900.3569844-34-guro@fb.com
---
 include/linux/bpf.h  | 11 ---------
 kernel/bpf/core.c    | 12 ++-------
 kernel/bpf/syscall.c | 69 ++++++++--------------------------------------------
 3 files changed, 12 insertions(+), 80 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 61331a148cde..a9de5711b23f 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1202,8 +1202,6 @@ void bpf_prog_sub(struct bpf_prog *prog, int i);
 void bpf_prog_inc(struct bpf_prog *prog);
 struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog);
 void bpf_prog_put(struct bpf_prog *prog);
-int __bpf_prog_charge(struct user_struct *user, u32 pages);
-void __bpf_prog_uncharge(struct user_struct *user, u32 pages);
 void __bpf_free_used_maps(struct bpf_prog_aux *aux,
 			  struct bpf_map **used_maps, u32 len);
 
@@ -1512,15 +1510,6 @@ bpf_prog_inc_not_zero(struct bpf_prog *prog)
 	return ERR_PTR(-EOPNOTSUPP);
 }
 
-static inline int __bpf_prog_charge(struct user_struct *user, u32 pages)
-{
-	return 0;
-}
-
-static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages)
-{
-}
-
 static inline void bpf_link_init(struct bpf_link *link, enum bpf_link_type type,
 				 const struct bpf_link_ops *ops,
 				 struct bpf_prog *prog)
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 2921f58c03a8..261f8692d0d2 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -221,23 +221,15 @@ struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
 {
 	gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags;
 	struct bpf_prog *fp;
-	u32 pages, delta;
-	int ret;
+	u32 pages;
 
 	size = round_up(size, PAGE_SIZE);
 	pages = size / PAGE_SIZE;
 	if (pages <= fp_old->pages)
 		return fp_old;
 
-	delta = pages - fp_old->pages;
-	ret = __bpf_prog_charge(fp_old->aux->user, delta);
-	if (ret)
-		return NULL;
-
 	fp = __vmalloc(size, gfp_flags);
-	if (fp == NULL) {
-		__bpf_prog_uncharge(fp_old->aux->user, delta);
-	} else {
+	if (fp) {
 		memcpy(fp, fp_old, fp_old->pages * PAGE_SIZE);
 		fp->pages = pages;
 		fp->aux->prog = fp;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 29096d96d989..d16dd4945100 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1632,51 +1632,6 @@ static void bpf_audit_prog(const struct bpf_prog *prog, unsigned int op)
 	audit_log_end(ab);
 }
 
-int __bpf_prog_charge(struct user_struct *user, u32 pages)
-{
-	unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
-	unsigned long user_bufs;
-
-	if (user) {
-		user_bufs = atomic_long_add_return(pages, &user->locked_vm);
-		if (user_bufs > memlock_limit) {
-			atomic_long_sub(pages, &user->locked_vm);
-			return -EPERM;
-		}
-	}
-
-	return 0;
-}
-
-void __bpf_prog_uncharge(struct user_struct *user, u32 pages)
-{
-	if (user)
-		atomic_long_sub(pages, &user->locked_vm);
-}
-
-static int bpf_prog_charge_memlock(struct bpf_prog *prog)
-{
-	struct user_struct *user = get_current_user();
-	int ret;
-
-	ret = __bpf_prog_charge(user, prog->pages);
-	if (ret) {
-		free_uid(user);
-		return ret;
-	}
-
-	prog->aux->user = user;
-	return 0;
-}
-
-static void bpf_prog_uncharge_memlock(struct bpf_prog *prog)
-{
-	struct user_struct *user = prog->aux->user;
-
-	__bpf_prog_uncharge(user, prog->pages);
-	free_uid(user);
-}
-
 static int bpf_prog_alloc_id(struct bpf_prog *prog)
 {
 	int id;
@@ -1726,7 +1681,7 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu)
 
 	kvfree(aux->func_info);
 	kfree(aux->func_info_aux);
-	bpf_prog_uncharge_memlock(aux->prog);
+	free_uid(aux->user);
 	security_bpf_prog_free(aux);
 	bpf_prog_free(aux->prog);
 }
@@ -2164,7 +2119,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 		dst_prog = bpf_prog_get(attr->attach_prog_fd);
 		if (IS_ERR(dst_prog)) {
 			err = PTR_ERR(dst_prog);
-			goto free_prog_nouncharge;
+			goto free_prog;
 		}
 		prog->aux->dst_prog = dst_prog;
 	}
@@ -2174,18 +2129,15 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 
 	err = security_bpf_prog_alloc(prog->aux);
 	if (err)
-		goto free_prog_nouncharge;
-
-	err = bpf_prog_charge_memlock(prog);
-	if (err)
-		goto free_prog_sec;
+		goto free_prog;
 
+	prog->aux->user = get_current_user();
 	prog->len = attr->insn_cnt;
 
 	err = -EFAULT;
 	if (copy_from_user(prog->insns, u64_to_user_ptr(attr->insns),
 			   bpf_prog_insn_size(prog)) != 0)
-		goto free_prog;
+		goto free_prog_sec;
 
 	prog->orig_prog = NULL;
 	prog->jited = 0;
@@ -2196,19 +2148,19 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 	if (bpf_prog_is_dev_bound(prog->aux)) {
 		err = bpf_prog_offload_init(prog, attr);
 		if (err)
-			goto free_prog;
+			goto free_prog_sec;
 	}
 
 	/* find program type: socket_filter vs tracing_filter */
 	err = find_prog_type(type, prog);
 	if (err < 0)
-		goto free_prog;
+		goto free_prog_sec;
 
 	prog->aux->load_time = ktime_get_boottime_ns();
 	err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name,
 			       sizeof(attr->prog_name));
 	if (err < 0)
-		goto free_prog;
+		goto free_prog_sec;
 
 	/* run eBPF verifier */
 	err = bpf_check(&prog, attr, uattr);
@@ -2253,11 +2205,10 @@ free_used_maps:
 	 */
 	__bpf_prog_put_noref(prog, prog->aux->func_cnt);
 	return err;
-free_prog:
-	bpf_prog_uncharge_memlock(prog);
 free_prog_sec:
+	free_uid(prog->aux->user);
 	security_bpf_prog_free(prog->aux);
-free_prog_nouncharge:
+free_prog:
 	bpf_prog_free(prog);
 	return err;
 }
-- 
cgit v1.2.3


From 608af703519a58f5a7da4273809211cac27edfb2 Mon Sep 17 00:00:00 2001
From: Daniel Rosenberg <drosen@google.com>
Date: Thu, 19 Nov 2020 06:09:02 +0000
Subject: libfs: Add generic function for setting dentry_ops

This adds a function to set dentry operations at lookup time that will
work for both encrypted filenames and casefolded filenames.

A filesystem that supports both features simultaneously can use this
function during lookup preparations to set up its dentry operations once
fscrypt no longer does that itself.

Currently the casefolding dentry operation are always set if the
filesystem defines an encoding because the features is toggleable on
empty directories. Unlike in the encryption case, the dentry operations
used come from the parent. Since we don't know what set of functions
we'll eventually need, and cannot change them later, we enable the
casefolding operations if the filesystem supports them at all.

By splitting out the various cases, we support as few dentry operations
as we can get away with, maximizing compatibility with overlayfs, which
will not function if a filesystem supports certain dentry_operations.

Signed-off-by: Daniel Rosenberg <drosen@google.com>
Reviewed-by: Theodore Ts'o <tytso@mit.edu>
Reviewed-by: Eric Biggers <ebiggers@google.com>
Reviewed-by: Gabriel Krisman Bertazi <krisman@collabora.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/libfs.c         | 70 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/fs.h |  1 +
 2 files changed, 71 insertions(+)

(limited to 'include/linux')

diff --git a/fs/libfs.c b/fs/libfs.c
index fc34361c1489..bac918699022 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -1449,4 +1449,74 @@ int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str)
 	return 0;
 }
 EXPORT_SYMBOL(generic_ci_d_hash);
+
+static const struct dentry_operations generic_ci_dentry_ops = {
+	.d_hash = generic_ci_d_hash,
+	.d_compare = generic_ci_d_compare,
+};
+#endif
+
+#ifdef CONFIG_FS_ENCRYPTION
+static const struct dentry_operations generic_encrypted_dentry_ops = {
+	.d_revalidate = fscrypt_d_revalidate,
+};
+#endif
+
+#if defined(CONFIG_FS_ENCRYPTION) && defined(CONFIG_UNICODE)
+static const struct dentry_operations generic_encrypted_ci_dentry_ops = {
+	.d_hash = generic_ci_d_hash,
+	.d_compare = generic_ci_d_compare,
+	.d_revalidate = fscrypt_d_revalidate,
+};
+#endif
+
+/**
+ * generic_set_encrypted_ci_d_ops - helper for setting d_ops for given dentry
+ * @dentry:	dentry to set ops on
+ *
+ * Casefolded directories need d_hash and d_compare set, so that the dentries
+ * contained in them are handled case-insensitively.  Note that these operations
+ * are needed on the parent directory rather than on the dentries in it, and
+ * while the casefolding flag can be toggled on and off on an empty directory,
+ * dentry_operations can't be changed later.  As a result, if the filesystem has
+ * casefolding support enabled at all, we have to give all dentries the
+ * casefolding operations even if their inode doesn't have the casefolding flag
+ * currently (and thus the casefolding ops would be no-ops for now).
+ *
+ * Encryption works differently in that the only dentry operation it needs is
+ * d_revalidate, which it only needs on dentries that have the no-key name flag.
+ * The no-key flag can't be set "later", so we don't have to worry about that.
+ *
+ * Finally, to maximize compatibility with overlayfs (which isn't compatible
+ * with certain dentry operations) and to avoid taking an unnecessary
+ * performance hit, we use custom dentry_operations for each possible
+ * combination rather than always installing all operations.
+ */
+void generic_set_encrypted_ci_d_ops(struct dentry *dentry)
+{
+#ifdef CONFIG_FS_ENCRYPTION
+	bool needs_encrypt_ops = dentry->d_flags & DCACHE_NOKEY_NAME;
+#endif
+#ifdef CONFIG_UNICODE
+	bool needs_ci_ops = dentry->d_sb->s_encoding;
+#endif
+#if defined(CONFIG_FS_ENCRYPTION) && defined(CONFIG_UNICODE)
+	if (needs_encrypt_ops && needs_ci_ops) {
+		d_set_d_op(dentry, &generic_encrypted_ci_dentry_ops);
+		return;
+	}
 #endif
+#ifdef CONFIG_FS_ENCRYPTION
+	if (needs_encrypt_ops) {
+		d_set_d_op(dentry, &generic_encrypted_dentry_ops);
+		return;
+	}
+#endif
+#ifdef CONFIG_UNICODE
+	if (needs_ci_ops) {
+		d_set_d_op(dentry, &generic_ci_dentry_ops);
+		return;
+	}
+#endif
+}
+EXPORT_SYMBOL(generic_set_encrypted_ci_d_ops);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 21cc971fd960..4a25ab4dbd3e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3186,6 +3186,7 @@ extern int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str);
 extern int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
 				const char *str, const struct qstr *name);
 #endif
+extern void generic_set_encrypted_ci_d_ops(struct dentry *dentry);
 
 #ifdef CONFIG_MIGRATION
 extern int buffer_migrate_page(struct address_space *,
-- 
cgit v1.2.3


From bb9cd9106b22b4fc5ff8d78a752be8a4ba2cbba5 Mon Sep 17 00:00:00 2001
From: Daniel Rosenberg <drosen@google.com>
Date: Thu, 19 Nov 2020 06:09:03 +0000
Subject: fscrypt: Have filesystems handle their d_ops

This shifts the responsibility of setting up dentry operations from
fscrypt to the individual filesystems, allowing them to have their own
operations while still setting fscrypt's d_revalidate as appropriate.

Most filesystems can just use generic_set_encrypted_ci_d_ops, unless
they have their own specific dentry operations as well. That operation
will set the minimal d_ops required under the circumstances.

Since the fscrypt d_ops are set later on, we must set all d_ops there,
since we cannot adjust those later on. This should not result in any
change in behavior.

Signed-off-by: Daniel Rosenberg <drosen@google.com>
Acked-by: Theodore Ts'o <tytso@mit.edu>
Acked-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/crypto/fname.c           | 4 ----
 fs/crypto/fscrypt_private.h | 1 -
 fs/crypto/hooks.c           | 1 -
 fs/ext4/dir.c               | 7 -------
 fs/ext4/ext4.h              | 4 ----
 fs/ext4/namei.c             | 1 +
 fs/ext4/super.c             | 5 -----
 fs/f2fs/dir.c               | 7 -------
 fs/f2fs/f2fs.h              | 3 ---
 fs/f2fs/namei.c             | 1 +
 fs/f2fs/super.c             | 1 -
 fs/ubifs/dir.c              | 1 +
 include/linux/fscrypt.h     | 7 +++++--
 13 files changed, 8 insertions(+), 35 deletions(-)

(limited to 'include/linux')

diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c
index 1fbe6c24d705..cb3cfa6329ba 100644
--- a/fs/crypto/fname.c
+++ b/fs/crypto/fname.c
@@ -570,7 +570,3 @@ int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
 	return valid;
 }
 EXPORT_SYMBOL_GPL(fscrypt_d_revalidate);
-
-const struct dentry_operations fscrypt_d_ops = {
-	.d_revalidate = fscrypt_d_revalidate,
-};
diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h
index 4f5806a3b73d..df9c48c1fbf7 100644
--- a/fs/crypto/fscrypt_private.h
+++ b/fs/crypto/fscrypt_private.h
@@ -294,7 +294,6 @@ int fscrypt_fname_encrypt(const struct inode *inode, const struct qstr *iname,
 bool fscrypt_fname_encrypted_size(const union fscrypt_policy *policy,
 				  u32 orig_len, u32 max_len,
 				  u32 *encrypted_len_ret);
-extern const struct dentry_operations fscrypt_d_ops;
 
 /* hkdf.c */
 
diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c
index 20b0df47fe6a..9006fa983335 100644
--- a/fs/crypto/hooks.c
+++ b/fs/crypto/hooks.c
@@ -117,7 +117,6 @@ int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry,
 		spin_lock(&dentry->d_lock);
 		dentry->d_flags |= DCACHE_NOKEY_NAME;
 		spin_unlock(&dentry->d_lock);
-		d_set_d_op(dentry, &fscrypt_d_ops);
 	}
 	return err;
 }
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index ca50c90adc4c..e757319a4472 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -667,10 +667,3 @@ const struct file_operations ext4_dir_operations = {
 	.open		= ext4_dir_open,
 	.release	= ext4_release_dir,
 };
-
-#ifdef CONFIG_UNICODE
-const struct dentry_operations ext4_dentry_ops = {
-	.d_hash = generic_ci_d_hash,
-	.d_compare = generic_ci_d_compare,
-};
-#endif
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 45fcdbf538d1..983f2b970d6a 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -3354,10 +3354,6 @@ static inline void ext4_unlock_group(struct super_block *sb,
 /* dir.c */
 extern const struct file_operations ext4_dir_operations;
 
-#ifdef CONFIG_UNICODE
-extern const struct dentry_operations ext4_dentry_ops;
-#endif
-
 /* file.c */
 extern const struct inode_operations ext4_file_inode_operations;
 extern const struct file_operations ext4_file_operations;
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index f458d1d81d96..8e2398e5d0fe 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1614,6 +1614,7 @@ static struct buffer_head *ext4_lookup_entry(struct inode *dir,
 	struct buffer_head *bh;
 
 	err = ext4_fname_prepare_lookup(dir, dentry, &fname);
+	generic_set_encrypted_ci_d_ops(dentry);
 	if (err == -ENOENT)
 		return NULL;
 	if (err)
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index ef4734b40e2a..82b365acedf8 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -4974,11 +4974,6 @@ no_journal:
 		goto failed_mount4;
 	}
 
-#ifdef CONFIG_UNICODE
-	if (sb->s_encoding)
-		sb->s_d_op = &ext4_dentry_ops;
-#endif
-
 	sb->s_root = d_make_root(root);
 	if (!sb->s_root) {
 		ext4_msg(sb, KERN_ERR, "get root dentry failed");
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 4b9ef8bbfa4a..71fdf5076461 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -1099,10 +1099,3 @@ const struct file_operations f2fs_dir_operations = {
 	.compat_ioctl   = f2fs_compat_ioctl,
 #endif
 };
-
-#ifdef CONFIG_UNICODE
-const struct dentry_operations f2fs_dentry_ops = {
-	.d_hash = generic_ci_d_hash,
-	.d_compare = generic_ci_d_compare,
-};
-#endif
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 99bcf4b44a9c..01fd42843e49 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -3688,9 +3688,6 @@ static inline void f2fs_update_sit_info(struct f2fs_sb_info *sbi) {}
 #endif
 
 extern const struct file_operations f2fs_dir_operations;
-#ifdef CONFIG_UNICODE
-extern const struct dentry_operations f2fs_dentry_ops;
-#endif
 extern const struct file_operations f2fs_file_operations;
 extern const struct inode_operations f2fs_file_inode_operations;
 extern const struct address_space_operations f2fs_dblock_aops;
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 8fa37d1434de..6edb1ab579a1 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -497,6 +497,7 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
 	}
 
 	err = f2fs_prepare_lookup(dir, dentry, &fname);
+	generic_set_encrypted_ci_d_ops(dentry);
 	if (err == -ENOENT)
 		goto out_splice;
 	if (err)
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 0ec292d7fcdb..08e63c8caa1e 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -3426,7 +3426,6 @@ static int f2fs_setup_casefold(struct f2fs_sb_info *sbi)
 
 		sbi->sb->s_encoding = encoding;
 		sbi->sb->s_encoding_flags = encoding_flags;
-		sbi->sb->s_d_op = &f2fs_dentry_ops;
 	}
 #else
 	if (f2fs_sb_has_casefold(sbi)) {
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index 155521e51ac5..7a920434d741 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -203,6 +203,7 @@ static struct dentry *ubifs_lookup(struct inode *dir, struct dentry *dentry,
 	dbg_gen("'%pd' in dir ino %lu", dentry, dir->i_ino);
 
 	err = fscrypt_prepare_lookup(dir, dentry, &nm);
+	generic_set_encrypted_ci_d_ops(dentry);
 	if (err == -ENOENT)
 		return d_splice_alias(NULL, dentry);
 	if (err)
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index a8f7a43f031b..e72f80482671 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -741,8 +741,11 @@ static inline int fscrypt_prepare_rename(struct inode *old_dir,
  * directory's encryption key is available, then the lookup is assumed to be by
  * plaintext name; otherwise, it is assumed to be by no-key name.
  *
- * This also installs a custom ->d_revalidate() method which will invalidate the
- * dentry if it was created without the key and the key is later added.
+ * This will set DCACHE_NOKEY_NAME on the dentry if the lookup is by no-key
+ * name.  In this case the filesystem must assign the dentry a dentry_operations
+ * which contains fscrypt_d_revalidate (or contains a d_revalidate method that
+ * calls fscrypt_d_revalidate), so that the dentry will be invalidated if the
+ * directory's encryption key is later added.
  *
  * Return: 0 on success; -ENOENT if the directory's key is unavailable but the
  * filename isn't a valid no-key name, so a negative dentry should be created;
-- 
cgit v1.2.3


From b28f047b28c51d0b9864c34b097bb0b221ea7247 Mon Sep 17 00:00:00 2001
From: Chao Yu <yuchao0@huawei.com>
Date: Thu, 26 Nov 2020 18:32:09 +0800
Subject: f2fs: compress: support chksum

This patch supports to store chksum value with compressed
data, and verify the integrality of compressed data while
reading the data.

The feature can be enabled through specifying mount option
'compress_chksum'.

Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 Documentation/filesystems/f2fs.rst |  1 +
 fs/f2fs/compress.c                 | 23 +++++++++++++++++++++++
 fs/f2fs/f2fs.h                     | 16 ++++++++++++++--
 fs/f2fs/inode.c                    |  3 +++
 fs/f2fs/super.c                    |  9 +++++++++
 include/linux/f2fs_fs.h            |  2 +-
 6 files changed, 51 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/f2fs.rst b/Documentation/filesystems/f2fs.rst
index b8ee761c9922..985ae7d35066 100644
--- a/Documentation/filesystems/f2fs.rst
+++ b/Documentation/filesystems/f2fs.rst
@@ -260,6 +260,7 @@ compress_extension=%s	 Support adding specified extension, so that f2fs can enab
 			 For other files, we can still enable compression via ioctl.
 			 Note that, there is one reserved special extension '*', it
 			 can be set to enable compression for all files.
+compress_chksum		 Support verifying chksum of raw data in compressed cluster.
 inlinecrypt		 When possible, encrypt/decrypt the contents of encrypted
 			 files using the blk-crypto framework rather than
 			 filesystem-layer encryption. This allows the use of
diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c
index 14262e0f1cd6..7ec1592a0973 100644
--- a/fs/f2fs/compress.c
+++ b/fs/f2fs/compress.c
@@ -602,6 +602,7 @@ static int f2fs_compress_pages(struct compress_ctx *cc)
 				f2fs_cops[fi->i_compress_algorithm];
 	unsigned int max_len, new_nr_cpages;
 	struct page **new_cpages;
+	u32 chksum = 0;
 	int i, ret;
 
 	trace_f2fs_compress_pages_start(cc->inode, cc->cluster_idx,
@@ -655,6 +656,11 @@ static int f2fs_compress_pages(struct compress_ctx *cc)
 
 	cc->cbuf->clen = cpu_to_le32(cc->clen);
 
+	if (fi->i_compress_flag & 1 << COMPRESS_CHKSUM)
+		chksum = f2fs_crc32(F2FS_I_SB(cc->inode),
+					cc->cbuf->cdata, cc->clen);
+	cc->cbuf->chksum = cpu_to_le32(chksum);
+
 	for (i = 0; i < COMPRESS_DATA_RESERVED_SIZE; i++)
 		cc->cbuf->reserved[i] = cpu_to_le32(0);
 
@@ -790,6 +796,23 @@ void f2fs_decompress_pages(struct bio *bio, struct page *page, bool verity)
 
 	ret = cops->decompress_pages(dic);
 
+	if (!ret && fi->i_compress_flag & 1 << COMPRESS_CHKSUM) {
+		u32 provided = le32_to_cpu(dic->cbuf->chksum);
+		u32 calculated = f2fs_crc32(sbi, dic->cbuf->cdata, dic->clen);
+
+		if (provided != calculated) {
+			if (!is_inode_flag_set(dic->inode, FI_COMPRESS_CORRUPT)) {
+				set_inode_flag(dic->inode, FI_COMPRESS_CORRUPT);
+				printk_ratelimited(
+					"%sF2FS-fs (%s): checksum invalid, nid = %lu, %x vs %x",
+					KERN_INFO, sbi->sb->s_id, dic->inode->i_ino,
+					provided, calculated);
+			}
+			set_sbi_flag(sbi, SBI_NEED_FSCK);
+			WARN_ON_ONCE(1);
+		}
+	}
+
 out_vunmap_cbuf:
 	vm_unmap_ram(dic->cbuf, dic->nr_cpages);
 out_vunmap_rbuf:
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 0d25f5ca5618..0b314b2034d8 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -147,7 +147,8 @@ struct f2fs_mount_info {
 
 	/* For compression */
 	unsigned char compress_algorithm;	/* algorithm type */
-	unsigned compress_log_size;		/* cluster log size */
+	unsigned char compress_log_size;	/* cluster log size */
+	bool compress_chksum;			/* compressed data chksum */
 	unsigned char compress_ext_cnt;		/* extension count */
 	unsigned char extensions[COMPRESS_EXT_NUM][F2FS_EXTENSION_LEN];	/* extensions */
 };
@@ -676,6 +677,7 @@ enum {
 	FI_ATOMIC_REVOKE_REQUEST, /* request to drop atomic data */
 	FI_VERITY_IN_PROGRESS,	/* building fs-verity Merkle tree */
 	FI_COMPRESSED_FILE,	/* indicate file's data can be compressed */
+	FI_COMPRESS_CORRUPT,	/* indicate compressed cluster is corrupted */
 	FI_MMAP_FILE,		/* indicate file was mmapped */
 	FI_MAX,			/* max flag, never be used */
 };
@@ -733,6 +735,7 @@ struct f2fs_inode_info {
 	atomic_t i_compr_blocks;		/* # of compressed blocks */
 	unsigned char i_compress_algorithm;	/* algorithm type */
 	unsigned char i_log_cluster_size;	/* log of cluster size */
+	unsigned short i_compress_flag;		/* compress flag */
 	unsigned int i_cluster_size;		/* cluster size */
 };
 
@@ -1272,9 +1275,15 @@ enum compress_algorithm_type {
 	COMPRESS_MAX,
 };
 
-#define COMPRESS_DATA_RESERVED_SIZE		5
+enum compress_flag {
+	COMPRESS_CHKSUM,
+	COMPRESS_MAX_FLAG,
+};
+
+#define COMPRESS_DATA_RESERVED_SIZE		4
 struct compress_data {
 	__le32 clen;			/* compressed data size */
+	__le32 chksum;			/* compressed data chksum */
 	__le32 reserved[COMPRESS_DATA_RESERVED_SIZE];	/* reserved */
 	u8 cdata[];			/* compressed data */
 };
@@ -3888,6 +3897,9 @@ static inline void set_compress_context(struct inode *inode)
 			F2FS_OPTION(sbi).compress_algorithm;
 	F2FS_I(inode)->i_log_cluster_size =
 			F2FS_OPTION(sbi).compress_log_size;
+	F2FS_I(inode)->i_compress_flag =
+			F2FS_OPTION(sbi).compress_chksum ?
+				1 << COMPRESS_CHKSUM : 0;
 	F2FS_I(inode)->i_cluster_size =
 			1 << F2FS_I(inode)->i_log_cluster_size;
 	F2FS_I(inode)->i_flags |= F2FS_COMPR_FL;
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 657db2fb6739..349d9cb933ee 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -456,6 +456,7 @@ static int do_read_inode(struct inode *inode)
 					le64_to_cpu(ri->i_compr_blocks));
 			fi->i_compress_algorithm = ri->i_compress_algorithm;
 			fi->i_log_cluster_size = ri->i_log_cluster_size;
+			fi->i_compress_flag = le16_to_cpu(ri->i_compress_flag);
 			fi->i_cluster_size = 1 << fi->i_log_cluster_size;
 			set_inode_flag(inode, FI_COMPRESSED_FILE);
 		}
@@ -634,6 +635,8 @@ void f2fs_update_inode(struct inode *inode, struct page *node_page)
 					&F2FS_I(inode)->i_compr_blocks));
 			ri->i_compress_algorithm =
 				F2FS_I(inode)->i_compress_algorithm;
+			ri->i_compress_flag =
+				cpu_to_le16(F2FS_I(inode)->i_compress_flag);
 			ri->i_log_cluster_size =
 				F2FS_I(inode)->i_log_cluster_size;
 		}
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 82baaa89c893..f3d919ee4dee 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -146,6 +146,7 @@ enum {
 	Opt_compress_algorithm,
 	Opt_compress_log_size,
 	Opt_compress_extension,
+	Opt_compress_chksum,
 	Opt_atgc,
 	Opt_err,
 };
@@ -214,6 +215,7 @@ static match_table_t f2fs_tokens = {
 	{Opt_compress_algorithm, "compress_algorithm=%s"},
 	{Opt_compress_log_size, "compress_log_size=%u"},
 	{Opt_compress_extension, "compress_extension=%s"},
+	{Opt_compress_chksum, "compress_chksum"},
 	{Opt_atgc, "atgc"},
 	{Opt_err, NULL},
 };
@@ -934,10 +936,14 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
 			F2FS_OPTION(sbi).compress_ext_cnt++;
 			kfree(name);
 			break;
+		case Opt_compress_chksum:
+			F2FS_OPTION(sbi).compress_chksum = true;
+			break;
 #else
 		case Opt_compress_algorithm:
 		case Opt_compress_log_size:
 		case Opt_compress_extension:
+		case Opt_compress_chksum:
 			f2fs_info(sbi, "compression options not supported");
 			break;
 #endif
@@ -1523,6 +1529,9 @@ static inline void f2fs_show_compress_options(struct seq_file *seq,
 		seq_printf(seq, ",compress_extension=%s",
 			F2FS_OPTION(sbi).extensions[i]);
 	}
+
+	if (F2FS_OPTION(sbi).compress_chksum)
+		seq_puts(seq, ",compress_chksum");
 }
 
 static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index a5dbb57a687f..7dc2a06cf19a 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -273,7 +273,7 @@ struct f2fs_inode {
 			__le64 i_compr_blocks;	/* # of compressed blocks */
 			__u8 i_compress_algorithm;	/* compress algorithm */
 			__u8 i_log_cluster_size;	/* log of cluster size */
-			__le16 i_padding;		/* padding */
+			__le16 i_compress_flag;		/* compress flag */
 			__le32 i_extra_end[0];	/* for attribute size calculation */
 		} __packed;
 		__le32 i_addr[DEF_ADDRS_PER_INODE];	/* Pointers to data blocks */
-- 
cgit v1.2.3


From 41a340941854c4606a9b71b9d68db412747e7c84 Mon Sep 17 00:00:00 2001
From: Fabio Estevam <festevam@gmail.com>
Date: Wed, 2 Dec 2020 15:13:26 +0100
Subject: media: coda: Convert the driver to DT-only

Since 5.10-rc1 i.MX is a devicetree-only platform, so simplify the code
by removing the unused non-DT support.

Signed-off-by: Fabio Estevam <festevam@gmail.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 drivers/media/platform/Kconfig            |  2 +-
 drivers/media/platform/coda/coda-common.c | 27 ++-------------------------
 include/linux/platform_data/media/coda.h  | 14 --------------
 3 files changed, 3 insertions(+), 40 deletions(-)
 delete mode 100644 include/linux/platform_data/media/coda.h

(limited to 'include/linux')

diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig
index ffffef2267f4..9fdbfea06087 100644
--- a/drivers/media/platform/Kconfig
+++ b/drivers/media/platform/Kconfig
@@ -201,7 +201,7 @@ if V4L_MEM2MEM_DRIVERS
 
 config VIDEO_CODA
 	tristate "Chips&Media Coda multi-standard codec IP"
-	depends on VIDEO_DEV && VIDEO_V4L2 && (ARCH_MXC || COMPILE_TEST)
+	depends on VIDEO_DEV && VIDEO_V4L2 && OF && (ARCH_MXC || COMPILE_TEST)
 	select SRAM
 	select VIDEOBUF2_DMA_CONTIG
 	select VIDEOBUF2_VMALLOC
diff --git a/drivers/media/platform/coda/coda-common.c b/drivers/media/platform/coda/coda-common.c
index d30eafea701d..995e95272e51 100644
--- a/drivers/media/platform/coda/coda-common.c
+++ b/drivers/media/platform/coda/coda-common.c
@@ -25,7 +25,6 @@
 #include <linux/slab.h>
 #include <linux/videodev2.h>
 #include <linux/of.h>
-#include <linux/platform_data/media/coda.h>
 #include <linux/ratelimit.h>
 #include <linux/reset.h>
 
@@ -3102,13 +3101,6 @@ static const struct coda_devtype coda_devdata[] = {
 	},
 };
 
-static const struct platform_device_id coda_platform_ids[] = {
-	{ .name = "coda-imx27", .driver_data = CODA_IMX27 },
-	{ /* sentinel */ }
-};
-MODULE_DEVICE_TABLE(platform, coda_platform_ids);
-
-#ifdef CONFIG_OF
 static const struct of_device_id coda_dt_ids[] = {
 	{ .compatible = "fsl,imx27-vpu", .data = &coda_devdata[CODA_IMX27] },
 	{ .compatible = "fsl,imx51-vpu", .data = &coda_devdata[CODA_IMX51] },
@@ -3118,14 +3110,9 @@ static const struct of_device_id coda_dt_ids[] = {
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, coda_dt_ids);
-#endif
 
 static int coda_probe(struct platform_device *pdev)
 {
-	const struct of_device_id *of_id =
-			of_match_device(of_match_ptr(coda_dt_ids), &pdev->dev);
-	const struct platform_device_id *pdev_id;
-	struct coda_platform_data *pdata = pdev->dev.platform_data;
 	struct device_node *np = pdev->dev.of_node;
 	struct gen_pool *pool;
 	struct coda_dev *dev;
@@ -3135,14 +3122,7 @@ static int coda_probe(struct platform_device *pdev)
 	if (!dev)
 		return -ENOMEM;
 
-	pdev_id = of_id ? of_id->data : platform_get_device_id(pdev);
-
-	if (of_id)
-		dev->devtype = of_id->data;
-	else if (pdev_id)
-		dev->devtype = &coda_devdata[pdev_id->driver_data];
-	else
-		return -EINVAL;
+	dev->devtype = of_device_get_match_data(&pdev->dev);
 
 	dev->dev = &pdev->dev;
 	dev->clk_per = devm_clk_get(&pdev->dev, "per");
@@ -3200,10 +3180,8 @@ static int coda_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	/* Get IRAM pool from device tree or platform data */
+	/* Get IRAM pool from device tree */
 	pool = of_gen_pool_get(np, "iram", 0);
-	if (!pool && pdata)
-		pool = gen_pool_get(pdata->iram_dev, NULL);
 	if (!pool) {
 		dev_err(&pdev->dev, "iram pool not available\n");
 		return -ENOMEM;
@@ -3342,7 +3320,6 @@ static struct platform_driver coda_driver = {
 		.of_match_table = of_match_ptr(coda_dt_ids),
 		.pm	= &coda_pm_ops,
 	},
-	.id_table = coda_platform_ids,
 };
 
 module_platform_driver(coda_driver);
diff --git a/include/linux/platform_data/media/coda.h b/include/linux/platform_data/media/coda.h
deleted file mode 100644
index 293b61b60c9d..000000000000
--- a/include/linux/platform_data/media/coda.h
+++ /dev/null
@@ -1,14 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Copyright (C) 2013 Philipp Zabel, Pengutronix
- */
-#ifndef PLATFORM_CODA_H
-#define PLATFORM_CODA_H
-
-struct device;
-
-struct coda_platform_data {
-	struct device *iram_dev;
-};
-
-#endif
-- 
cgit v1.2.3


From 2a4a06da8a4b93dd189171eed7a99fffd38f42f3 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 13 Nov 2020 11:41:40 +0100
Subject: mm/gup: Provide gup_get_pte() more generic

In order to write another lockless page-table walker, we need
gup_get_pte() exposed. While doing that, rename it to
ptep_get_lockless() to match the existing ptep_get() naming.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20201126121121.036370527@infradead.org
---
 include/linux/pgtable.h | 55 ++++++++++++++++++++++++++++++++++++++++++++++
 mm/gup.c                | 58 +------------------------------------------------
 2 files changed, 56 insertions(+), 57 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 71125a4676c4..ed9266cc115b 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -258,6 +258,61 @@ static inline pte_t ptep_get(pte_t *ptep)
 }
 #endif
 
+#ifdef CONFIG_GUP_GET_PTE_LOW_HIGH
+/*
+ * WARNING: only to be used in the get_user_pages_fast() implementation.
+ *
+ * With get_user_pages_fast(), we walk down the pagetables without taking any
+ * locks.  For this we would like to load the pointers atomically, but sometimes
+ * that is not possible (e.g. without expensive cmpxchg8b on x86_32 PAE).  What
+ * we do have is the guarantee that a PTE will only either go from not present
+ * to present, or present to not present or both -- it will not switch to a
+ * completely different present page without a TLB flush in between; something
+ * that we are blocking by holding interrupts off.
+ *
+ * Setting ptes from not present to present goes:
+ *
+ *   ptep->pte_high = h;
+ *   smp_wmb();
+ *   ptep->pte_low = l;
+ *
+ * And present to not present goes:
+ *
+ *   ptep->pte_low = 0;
+ *   smp_wmb();
+ *   ptep->pte_high = 0;
+ *
+ * We must ensure here that the load of pte_low sees 'l' IFF pte_high sees 'h'.
+ * We load pte_high *after* loading pte_low, which ensures we don't see an older
+ * value of pte_high.  *Then* we recheck pte_low, which ensures that we haven't
+ * picked up a changed pte high. We might have gotten rubbish values from
+ * pte_low and pte_high, but we are guaranteed that pte_low will not have the
+ * present bit set *unless* it is 'l'. Because get_user_pages_fast() only
+ * operates on present ptes we're safe.
+ */
+static inline pte_t ptep_get_lockless(pte_t *ptep)
+{
+	pte_t pte;
+
+	do {
+		pte.pte_low = ptep->pte_low;
+		smp_rmb();
+		pte.pte_high = ptep->pte_high;
+		smp_rmb();
+	} while (unlikely(pte.pte_low != ptep->pte_low));
+
+	return pte;
+}
+#else /* CONFIG_GUP_GET_PTE_LOW_HIGH */
+/*
+ * We require that the PTE can be read atomically.
+ */
+static inline pte_t ptep_get_lockless(pte_t *ptep)
+{
+	return ptep_get(ptep);
+}
+#endif /* CONFIG_GUP_GET_PTE_LOW_HIGH */
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
 static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
diff --git a/mm/gup.c b/mm/gup.c
index 98eb8e6d2609..44b0c6b89602 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2085,62 +2085,6 @@ static void put_compound_head(struct page *page, int refs, unsigned int flags)
 	put_page(page);
 }
 
-#ifdef CONFIG_GUP_GET_PTE_LOW_HIGH
-
-/*
- * WARNING: only to be used in the get_user_pages_fast() implementation.
- *
- * With get_user_pages_fast(), we walk down the pagetables without taking any
- * locks.  For this we would like to load the pointers atomically, but sometimes
- * that is not possible (e.g. without expensive cmpxchg8b on x86_32 PAE).  What
- * we do have is the guarantee that a PTE will only either go from not present
- * to present, or present to not present or both -- it will not switch to a
- * completely different present page without a TLB flush in between; something
- * that we are blocking by holding interrupts off.
- *
- * Setting ptes from not present to present goes:
- *
- *   ptep->pte_high = h;
- *   smp_wmb();
- *   ptep->pte_low = l;
- *
- * And present to not present goes:
- *
- *   ptep->pte_low = 0;
- *   smp_wmb();
- *   ptep->pte_high = 0;
- *
- * We must ensure here that the load of pte_low sees 'l' IFF pte_high sees 'h'.
- * We load pte_high *after* loading pte_low, which ensures we don't see an older
- * value of pte_high.  *Then* we recheck pte_low, which ensures that we haven't
- * picked up a changed pte high. We might have gotten rubbish values from
- * pte_low and pte_high, but we are guaranteed that pte_low will not have the
- * present bit set *unless* it is 'l'. Because get_user_pages_fast() only
- * operates on present ptes we're safe.
- */
-static inline pte_t gup_get_pte(pte_t *ptep)
-{
-	pte_t pte;
-
-	do {
-		pte.pte_low = ptep->pte_low;
-		smp_rmb();
-		pte.pte_high = ptep->pte_high;
-		smp_rmb();
-	} while (unlikely(pte.pte_low != ptep->pte_low));
-
-	return pte;
-}
-#else /* CONFIG_GUP_GET_PTE_LOW_HIGH */
-/*
- * We require that the PTE can be read atomically.
- */
-static inline pte_t gup_get_pte(pte_t *ptep)
-{
-	return ptep_get(ptep);
-}
-#endif /* CONFIG_GUP_GET_PTE_LOW_HIGH */
-
 static void __maybe_unused undo_dev_pagemap(int *nr, int nr_start,
 					    unsigned int flags,
 					    struct page **pages)
@@ -2166,7 +2110,7 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 
 	ptem = ptep = pte_offset_map(&pmd, addr);
 	do {
-		pte_t pte = gup_get_pte(ptep);
+		pte_t pte = ptep_get_lockless(ptep);
 		struct page *head, *page;
 
 		/*
-- 
cgit v1.2.3


From 560dabbdf68bb15f9e241af8f828b1c8c38d6c6f Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 13 Nov 2020 11:45:36 +0100
Subject: mm: Introduce pXX_leaf_size()

A number of architectures have non-pagetable aligned huge/large pages.
For such architectures a leaf can actually be part of a larger entry.

Provide generic helpers to determine the size of a page-table leaf.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Link: https://lkml.kernel.org/r/20201126121121.102580109@infradead.org
---
 include/linux/pgtable.h | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index ed9266cc115b..fefbbdbbb3f3 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1536,4 +1536,20 @@ typedef unsigned int pgtbl_mod_mask;
 #define pmd_leaf(x)	0
 #endif
 
+#ifndef pgd_leaf_size
+#define pgd_leaf_size(x) (1ULL << PGDIR_SHIFT)
+#endif
+#ifndef p4d_leaf_size
+#define p4d_leaf_size(x) P4D_SIZE
+#endif
+#ifndef pud_leaf_size
+#define pud_leaf_size(x) PUD_SIZE
+#endif
+#ifndef pmd_leaf_size
+#define pmd_leaf_size(x) PMD_SIZE
+#endif
+#ifndef pte_leaf_size
+#define pte_leaf_size(x) PAGE_SIZE
+#endif
+
 #endif /* _LINUX_PGTABLE_H */
-- 
cgit v1.2.3


From a07c45312f06e288417049208c344ad76074627d Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 26 Oct 2020 17:50:38 +0100
Subject: seqlock: avoid -Wshadow warnings

When building with W=2, there is a flood of warnings about the seqlock
macros shadowing local variables:

  19806 linux/seqlock.h:331:11: warning: declaration of 'seq' shadows a previous local [-Wshadow]
     48 linux/seqlock.h:348:11: warning: declaration of 'seq' shadows a previous local [-Wshadow]
      8 linux/seqlock.h:379:11: warning: declaration of 'seq' shadows a previous local [-Wshadow]

Prefix the local variables to make the warning useful elsewhere again.

Fixes: 52ac39e5db51 ("seqlock: seqcount_t: Implement all read APIs as statement expressions")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20201026165044.3722931-1-arnd@kernel.org
---
 include/linux/seqlock.h | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index cbfc78b92b65..8d8552474c64 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -328,13 +328,13 @@ SEQCOUNT_LOCKNAME(ww_mutex,     struct ww_mutex, true,     &s->lock->base, ww_mu
  */
 #define __read_seqcount_begin(s)					\
 ({									\
-	unsigned seq;							\
+	unsigned __seq;							\
 									\
-	while ((seq = __seqcount_sequence(s)) & 1)			\
+	while ((__seq = __seqcount_sequence(s)) & 1)			\
 		cpu_relax();						\
 									\
 	kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX);			\
-	seq;								\
+	__seq;								\
 })
 
 /**
@@ -345,10 +345,10 @@ SEQCOUNT_LOCKNAME(ww_mutex,     struct ww_mutex, true,     &s->lock->base, ww_mu
  */
 #define raw_read_seqcount_begin(s)					\
 ({									\
-	unsigned seq = __read_seqcount_begin(s);			\
+	unsigned _seq = __read_seqcount_begin(s);			\
 									\
 	smp_rmb();							\
-	seq;								\
+	_seq;								\
 })
 
 /**
@@ -376,11 +376,11 @@ SEQCOUNT_LOCKNAME(ww_mutex,     struct ww_mutex, true,     &s->lock->base, ww_mu
  */
 #define raw_read_seqcount(s)						\
 ({									\
-	unsigned seq = __seqcount_sequence(s);				\
+	unsigned __seq = __seqcount_sequence(s);			\
 									\
 	smp_rmb();							\
 	kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX);			\
-	seq;								\
+	__seq;								\
 })
 
 /**
-- 
cgit v1.2.3


From ab440b2c604b60fe90885270fcfeb5c3dd5d6fae Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 10 Nov 2020 13:44:17 +0100
Subject: seqlock: Rename __seqprop() users

More consistent naming should make it easier to untangle the _Generic
token pasting maze called __seqprop().

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20201110115358.GE2594@hirez.programming.kicks-ass.net
---
 include/linux/seqlock.h | 46 +++++++++++++++++++++++-----------------------
 1 file changed, 23 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 8d8552474c64..d89134c74fba 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -307,10 +307,10 @@ SEQCOUNT_LOCKNAME(ww_mutex,     struct ww_mutex, true,     &s->lock->base, ww_mu
 	__seqprop_case((s),	mutex,		prop),			\
 	__seqprop_case((s),	ww_mutex,	prop))
 
-#define __seqcount_ptr(s)		__seqprop(s, ptr)
-#define __seqcount_sequence(s)		__seqprop(s, sequence)
-#define __seqcount_lock_preemptible(s)	__seqprop(s, preemptible)
-#define __seqcount_assert_lock_held(s)	__seqprop(s, assert)
+#define seqprop_ptr(s)			__seqprop(s, ptr)
+#define seqprop_sequence(s)		__seqprop(s, sequence)
+#define seqprop_preemptible(s)		__seqprop(s, preemptible)
+#define seqprop_assert(s)		__seqprop(s, assert)
 
 /**
  * __read_seqcount_begin() - begin a seqcount_t read section w/o barrier
@@ -330,7 +330,7 @@ SEQCOUNT_LOCKNAME(ww_mutex,     struct ww_mutex, true,     &s->lock->base, ww_mu
 ({									\
 	unsigned __seq;							\
 									\
-	while ((__seq = __seqcount_sequence(s)) & 1)			\
+	while ((__seq = seqprop_sequence(s)) & 1)			\
 		cpu_relax();						\
 									\
 	kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX);			\
@@ -359,7 +359,7 @@ SEQCOUNT_LOCKNAME(ww_mutex,     struct ww_mutex, true,     &s->lock->base, ww_mu
  */
 #define read_seqcount_begin(s)						\
 ({									\
-	seqcount_lockdep_reader_access(__seqcount_ptr(s));		\
+	seqcount_lockdep_reader_access(seqprop_ptr(s));			\
 	raw_read_seqcount_begin(s);					\
 })
 
@@ -376,7 +376,7 @@ SEQCOUNT_LOCKNAME(ww_mutex,     struct ww_mutex, true,     &s->lock->base, ww_mu
  */
 #define raw_read_seqcount(s)						\
 ({									\
-	unsigned __seq = __seqcount_sequence(s);			\
+	unsigned __seq = seqprop_sequence(s);				\
 									\
 	smp_rmb();							\
 	kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX);			\
@@ -425,7 +425,7 @@ SEQCOUNT_LOCKNAME(ww_mutex,     struct ww_mutex, true,     &s->lock->base, ww_mu
  * Return: true if a read section retry is required, else false
  */
 #define __read_seqcount_retry(s, start)					\
-	__read_seqcount_t_retry(__seqcount_ptr(s), start)
+	__read_seqcount_t_retry(seqprop_ptr(s), start)
 
 static inline int __read_seqcount_t_retry(const seqcount_t *s, unsigned start)
 {
@@ -445,7 +445,7 @@ static inline int __read_seqcount_t_retry(const seqcount_t *s, unsigned start)
  * Return: true if a read section retry is required, else false
  */
 #define read_seqcount_retry(s, start)					\
-	read_seqcount_t_retry(__seqcount_ptr(s), start)
+	read_seqcount_t_retry(seqprop_ptr(s), start)
 
 static inline int read_seqcount_t_retry(const seqcount_t *s, unsigned start)
 {
@@ -459,10 +459,10 @@ static inline int read_seqcount_t_retry(const seqcount_t *s, unsigned start)
  */
 #define raw_write_seqcount_begin(s)					\
 do {									\
-	if (__seqcount_lock_preemptible(s))				\
+	if (seqprop_preemptible(s))					\
 		preempt_disable();					\
 									\
-	raw_write_seqcount_t_begin(__seqcount_ptr(s));			\
+	raw_write_seqcount_t_begin(seqprop_ptr(s));			\
 } while (0)
 
 static inline void raw_write_seqcount_t_begin(seqcount_t *s)
@@ -478,9 +478,9 @@ static inline void raw_write_seqcount_t_begin(seqcount_t *s)
  */
 #define raw_write_seqcount_end(s)					\
 do {									\
-	raw_write_seqcount_t_end(__seqcount_ptr(s));			\
+	raw_write_seqcount_t_end(seqprop_ptr(s));			\
 									\
-	if (__seqcount_lock_preemptible(s))				\
+	if (seqprop_preemptible(s))					\
 		preempt_enable();					\
 } while (0)
 
@@ -501,12 +501,12 @@ static inline void raw_write_seqcount_t_end(seqcount_t *s)
  */
 #define write_seqcount_begin_nested(s, subclass)			\
 do {									\
-	__seqcount_assert_lock_held(s);					\
+	seqprop_assert(s);						\
 									\
-	if (__seqcount_lock_preemptible(s))				\
+	if (seqprop_preemptible(s))					\
 		preempt_disable();					\
 									\
-	write_seqcount_t_begin_nested(__seqcount_ptr(s), subclass);	\
+	write_seqcount_t_begin_nested(seqprop_ptr(s), subclass);	\
 } while (0)
 
 static inline void write_seqcount_t_begin_nested(seqcount_t *s, int subclass)
@@ -528,12 +528,12 @@ static inline void write_seqcount_t_begin_nested(seqcount_t *s, int subclass)
  */
 #define write_seqcount_begin(s)						\
 do {									\
-	__seqcount_assert_lock_held(s);					\
+	seqprop_assert(s);						\
 									\
-	if (__seqcount_lock_preemptible(s))				\
+	if (seqprop_preemptible(s))					\
 		preempt_disable();					\
 									\
-	write_seqcount_t_begin(__seqcount_ptr(s));			\
+	write_seqcount_t_begin(seqprop_ptr(s));				\
 } while (0)
 
 static inline void write_seqcount_t_begin(seqcount_t *s)
@@ -549,9 +549,9 @@ static inline void write_seqcount_t_begin(seqcount_t *s)
  */
 #define write_seqcount_end(s)						\
 do {									\
-	write_seqcount_t_end(__seqcount_ptr(s));			\
+	write_seqcount_t_end(seqprop_ptr(s));				\
 									\
-	if (__seqcount_lock_preemptible(s))				\
+	if (seqprop_preemptible(s))					\
 		preempt_enable();					\
 } while (0)
 
@@ -603,7 +603,7 @@ static inline void write_seqcount_t_end(seqcount_t *s)
  *      }
  */
 #define raw_write_seqcount_barrier(s)					\
-	raw_write_seqcount_t_barrier(__seqcount_ptr(s))
+	raw_write_seqcount_t_barrier(seqprop_ptr(s))
 
 static inline void raw_write_seqcount_t_barrier(seqcount_t *s)
 {
@@ -623,7 +623,7 @@ static inline void raw_write_seqcount_t_barrier(seqcount_t *s)
  * will complete successfully and see data older than this.
  */
 #define write_seqcount_invalidate(s)					\
-	write_seqcount_t_invalidate(__seqcount_ptr(s))
+	write_seqcount_t_invalidate(seqprop_ptr(s))
 
 static inline void write_seqcount_t_invalidate(seqcount_t *s)
 {
-- 
cgit v1.2.3


From b6498aad59b091e5618a9f05e7636e2ad2c6732d Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Tue, 1 Dec 2020 13:09:00 +0100
Subject: completion: Drop init_completion define

Changeset cd8084f91c02 ("locking/lockdep: Apply crossrelease to completions")
added a CONFIG_LOCKDEP_COMPLETE (that was later renamed to
CONFIG_LOCKDEP_COMPLETIONS).

Such changeset renamed the init_completion, and add a macro
that would either run a modified version or the original code.

However, such code reported too many false positives. So, it
ended being dropped later on by
changeset e966eaeeb623 ("locking/lockdep: Remove the cross-release locking checks").

Yet, the define remained there as just:

	 #define init_completion(x) __init_completion(x)

Get rid of the define, and return __init_completion() function
to its original name.

Fixes: e966eaeeb623 ("locking/lockdep: Remove the cross-release locking checks")
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/e657bfc533545c185b1c3c55926a449ead56a88b.1606823973.git.mchehab+huawei@kernel.org
---
 include/linux/completion.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/completion.h b/include/linux/completion.h
index bf8e77001f18..51d9ab079629 100644
--- a/include/linux/completion.h
+++ b/include/linux/completion.h
@@ -28,8 +28,7 @@ struct completion {
 	struct swait_queue_head wait;
 };
 
-#define init_completion_map(x, m) __init_completion(x)
-#define init_completion(x) __init_completion(x)
+#define init_completion_map(x, m) init_completion(x)
 static inline void complete_acquire(struct completion *x) {}
 static inline void complete_release(struct completion *x) {}
 
@@ -82,7 +81,7 @@ static inline void complete_release(struct completion *x) {}
  * This inline function will initialize a dynamically created completion
  * structure.
  */
-static inline void __init_completion(struct completion *x)
+static inline void init_completion(struct completion *x)
 {
 	x->done = 0;
 	init_swait_queue_head(&x->wait);
-- 
cgit v1.2.3


From 97d62caa32d6d79dadae3f8d19af5c92ea9a589a Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Tue, 1 Dec 2020 13:09:08 +0100
Subject: refcount: Fix a kernel-doc markup

The kernel-doc markup is wrong: it is asking the tool to document
struct refcount_struct, instead of documenting typedef refcount_t.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Kees Cook <keescook@chromium.org>
Link: https://lkml.kernel.org/r/afb9bb1e675bf5f72a34a55d780779d7d5916b4c.1606823973.git.mchehab+huawei@kernel.org
---
 include/linux/refcount.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/refcount.h b/include/linux/refcount.h
index 497990c69b0b..b8a6e387f8f9 100644
--- a/include/linux/refcount.h
+++ b/include/linux/refcount.h
@@ -101,7 +101,7 @@
 struct mutex;
 
 /**
- * struct refcount_t - variant of atomic_t specialized for reference counts
+ * typedef refcount_t - variant of atomic_t specialized for reference counts
  * @refs: atomic_t counter field
  *
  * The counter saturates at REFCOUNT_SATURATED and will not move once
-- 
cgit v1.2.3


From 950cc0d2bef078e1f6459900ca4d4b2a2e0e3c37 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Wed, 2 Dec 2020 14:07:07 +0200
Subject: fsnotify: generalize handle_inode_event()

The handle_inode_event() interface was added as (quoting comment):
"a simple variant of handle_event() for groups that only have inode
marks and don't have ignore mask".

In other words, all backends except fanotify.  The inotify backend
also falls under this category, but because it required extra arguments
it was left out of the initial pass of backends conversion to the
simple interface.

This results in code duplication between the generic helper
fsnotify_handle_event() and the inotify_handle_event() callback
which also happen to be buggy code.

Generalize the handle_inode_event() arguments and add the check for
FS_EXCL_UNLINK flag to the generic helper, so inotify backend could
be converted to use the simple interface.

Link: https://lore.kernel.org/r/20201202120713.702387-2-amir73il@gmail.com
CC: stable@vger.kernel.org
Fixes: b9a1b9772509 ("fsnotify: create method handle_inode_event() in fsnotify_operations")
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/nfsd/filecache.c              |  2 +-
 fs/notify/dnotify/dnotify.c      |  2 +-
 fs/notify/fsnotify.c             | 31 ++++++++++++++++++++++++-------
 include/linux/fsnotify_backend.h |  3 ++-
 kernel/audit_fsnotify.c          |  2 +-
 kernel/audit_tree.c              |  2 +-
 kernel/audit_watch.c             |  2 +-
 7 files changed, 31 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index 3c6c2f7d1688..5849c1bd88f1 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -600,7 +600,7 @@ static struct notifier_block nfsd_file_lease_notifier = {
 static int
 nfsd_file_fsnotify_handle_event(struct fsnotify_mark *mark, u32 mask,
 				struct inode *inode, struct inode *dir,
-				const struct qstr *name)
+				const struct qstr *name, u32 cookie)
 {
 	trace_nfsd_file_fsnotify_handle_event(inode, mask);
 
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index 5dcda8f20c04..e45ca6ecba95 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -72,7 +72,7 @@ static void dnotify_recalc_inode_mask(struct fsnotify_mark *fsn_mark)
  */
 static int dnotify_handle_event(struct fsnotify_mark *inode_mark, u32 mask,
 				struct inode *inode, struct inode *dir,
-				const struct qstr *name)
+				const struct qstr *name, u32 cookie)
 {
 	struct dnotify_mark *dn_mark;
 	struct dnotify_struct *dn;
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 8d3ad5ef2925..c5c68bcbaadf 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -232,6 +232,26 @@ notify:
 }
 EXPORT_SYMBOL_GPL(__fsnotify_parent);
 
+static int fsnotify_handle_inode_event(struct fsnotify_group *group,
+				       struct fsnotify_mark *inode_mark,
+				       u32 mask, const void *data, int data_type,
+				       struct inode *dir, const struct qstr *name,
+				       u32 cookie)
+{
+	const struct path *path = fsnotify_data_path(data, data_type);
+	struct inode *inode = fsnotify_data_inode(data, data_type);
+	const struct fsnotify_ops *ops = group->ops;
+
+	if (WARN_ON_ONCE(!ops->handle_inode_event))
+		return 0;
+
+	if ((inode_mark->mask & FS_EXCL_UNLINK) &&
+	    path && d_unlinked(path->dentry))
+		return 0;
+
+	return ops->handle_inode_event(inode_mark, mask, inode, dir, name, cookie);
+}
+
 static int fsnotify_handle_event(struct fsnotify_group *group, __u32 mask,
 				 const void *data, int data_type,
 				 struct inode *dir, const struct qstr *name,
@@ -239,13 +259,8 @@ static int fsnotify_handle_event(struct fsnotify_group *group, __u32 mask,
 {
 	struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info);
 	struct fsnotify_mark *child_mark = fsnotify_iter_child_mark(iter_info);
-	struct inode *inode = fsnotify_data_inode(data, data_type);
-	const struct fsnotify_ops *ops = group->ops;
 	int ret;
 
-	if (WARN_ON_ONCE(!ops->handle_inode_event))
-		return 0;
-
 	if (WARN_ON_ONCE(fsnotify_iter_sb_mark(iter_info)) ||
 	    WARN_ON_ONCE(fsnotify_iter_vfsmount_mark(iter_info)))
 		return 0;
@@ -262,7 +277,8 @@ static int fsnotify_handle_event(struct fsnotify_group *group, __u32 mask,
 		name = NULL;
 	}
 
-	ret = ops->handle_inode_event(inode_mark, mask, inode, dir, name);
+	ret = fsnotify_handle_inode_event(group, inode_mark, mask, data, data_type,
+					  dir, name, cookie);
 	if (ret || !child_mark)
 		return ret;
 
@@ -272,7 +288,8 @@ static int fsnotify_handle_event(struct fsnotify_group *group, __u32 mask,
 	 * report the event once to parent dir with name and once to child
 	 * without name.
 	 */
-	return ops->handle_inode_event(child_mark, mask, inode, NULL, NULL);
+	return fsnotify_handle_inode_event(group, child_mark, mask, data, data_type,
+					   NULL, NULL, 0);
 }
 
 static int send_to_group(__u32 mask, const void *data, int data_type,
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index f8529a3a2923..4ee3044eedd0 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -137,6 +137,7 @@ struct mem_cgroup;
  *		if @file_name is not NULL, this is the directory that
  *		@file_name is relative to.
  * @file_name:	optional file name associated with event
+ * @cookie:	inotify rename cookie
  *
  * free_group_priv - called when a group refcnt hits 0 to clean up the private union
  * freeing_mark - called when a mark is being destroyed for some reason.  The group
@@ -151,7 +152,7 @@ struct fsnotify_ops {
 			    struct fsnotify_iter_info *iter_info);
 	int (*handle_inode_event)(struct fsnotify_mark *mark, u32 mask,
 			    struct inode *inode, struct inode *dir,
-			    const struct qstr *file_name);
+			    const struct qstr *file_name, u32 cookie);
 	void (*free_group_priv)(struct fsnotify_group *group);
 	void (*freeing_mark)(struct fsnotify_mark *mark, struct fsnotify_group *group);
 	void (*free_event)(struct fsnotify_event *event);
diff --git a/kernel/audit_fsnotify.c b/kernel/audit_fsnotify.c
index bfcfcd61adb6..5b3f01da172b 100644
--- a/kernel/audit_fsnotify.c
+++ b/kernel/audit_fsnotify.c
@@ -154,7 +154,7 @@ static void audit_autoremove_mark_rule(struct audit_fsnotify_mark *audit_mark)
 /* Update mark data in audit rules based on fsnotify events. */
 static int audit_mark_handle_event(struct fsnotify_mark *inode_mark, u32 mask,
 				   struct inode *inode, struct inode *dir,
-				   const struct qstr *dname)
+				   const struct qstr *dname, u32 cookie)
 {
 	struct audit_fsnotify_mark *audit_mark;
 
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 83e1c07fc99e..6c91902f4f45 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -1037,7 +1037,7 @@ static void evict_chunk(struct audit_chunk *chunk)
 
 static int audit_tree_handle_event(struct fsnotify_mark *mark, u32 mask,
 				   struct inode *inode, struct inode *dir,
-				   const struct qstr *file_name)
+				   const struct qstr *file_name, u32 cookie)
 {
 	return 0;
 }
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 246e5ba704c0..2acf7ca49154 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -466,7 +466,7 @@ void audit_remove_watch_rule(struct audit_krule *krule)
 /* Update watch data in audit rules based on fsnotify events. */
 static int audit_watch_handle_event(struct fsnotify_mark *inode_mark, u32 mask,
 				    struct inode *inode, struct inode *dir,
-				    const struct qstr *dname)
+				    const struct qstr *dname, u32 cookie)
 {
 	struct audit_parent *parent;
 
-- 
cgit v1.2.3


From 50a4952fd67b7f7f551e82ac07c51c1a7a74d474 Mon Sep 17 00:00:00 2001
From: Alexander Lochmann <alexander.lochmann@tu-dortmund.de>
Date: Thu, 15 Oct 2020 15:24:52 +0200
Subject: Updated locking documentation for transaction_t

We used LockDoc to derive locking rules for each member
of struct transaction_t.
Based on those results, we extended the existing documentation
by more members of struct transaction_t, and updated the existing
documentation.

Link: https://lore.kernel.org/r/10cfbef1-994c-c604-f8a6-b1042fcc622f@tu-dortmund.de
Signed-off-by: Alexander Lochmann <alexander.lochmann@tu-dortmund.de>
Signed-off-by: Horst Schirmeier <horst.schirmeier@tu-dortmund.de>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 include/linux/jbd2.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 578ff196b3ce..d2a4860feb72 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -538,6 +538,7 @@ struct transaction_chp_stats_s {
  * The transaction keeps track of all of the buffers modified by a
  * running transaction, and all of the buffers committed but not yet
  * flushed to home for finished transactions.
+ * (Locking Documentation improved by LockDoc)
  */
 
 /*
@@ -658,12 +659,12 @@ struct transaction_s
 	unsigned long		t_start;
 
 	/*
-	 * When commit was requested
+	 * When commit was requested [j_state_lock]
 	 */
 	unsigned long		t_requested;
 
 	/*
-	 * Checkpointing stats [j_checkpoint_sem]
+	 * Checkpointing stats [j_list_lock]
 	 */
 	struct transaction_chp_stats_s t_chp_stats;
 
-- 
cgit v1.2.3


From 14026b94ccfe626e512bc9fa01e0e72ee75c7a98 Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Tue, 18 Aug 2020 17:19:32 +0000
Subject: signal: Add unsafe_put_compat_sigset()

Implement 'unsafe' version of put_compat_sigset()

For the bigendian, use unsafe_put_user() directly
to avoid intermediate copy through the stack.

For the littleendian, use a straight unsafe_copy_to_user().

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/537c7082ee309a0bb9c67a50c5d9dd929aedb82d.1597770847.git.christophe.leroy@csgroup.eu
---
 include/linux/compat.h | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/compat.h b/include/linux/compat.h
index 14d514233e1d..400c0941c8af 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -442,6 +442,38 @@ put_compat_sigset(compat_sigset_t __user *compat, const sigset_t *set,
 #endif
 }
 
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define unsafe_put_compat_sigset(compat, set, label) do {		\
+	compat_sigset_t __user *__c = compat;				\
+	const sigset_t *__s = set;					\
+									\
+	switch (_NSIG_WORDS) {						\
+	case 4:								\
+		unsafe_put_user(__s->sig[3] >> 32, &__c->sig[7], label);	\
+		unsafe_put_user(__s->sig[3], &__c->sig[6], label);	\
+		fallthrough;						\
+	case 3:								\
+		unsafe_put_user(__s->sig[2] >> 32, &__c->sig[5], label);	\
+		unsafe_put_user(__s->sig[2], &__c->sig[4], label);	\
+		fallthrough;						\
+	case 2:								\
+		unsafe_put_user(__s->sig[1] >> 32, &__c->sig[3], label);	\
+		unsafe_put_user(__s->sig[1], &__c->sig[2], label);	\
+		fallthrough;						\
+	case 1:								\
+		unsafe_put_user(__s->sig[0] >> 32, &__c->sig[1], label);	\
+		unsafe_put_user(__s->sig[0], &__c->sig[0], label);	\
+	}								\
+} while (0)
+#else
+#define unsafe_put_compat_sigset(compat, set, label) do {		\
+	compat_sigset_t __user *__c = compat;				\
+	const sigset_t *__s = set;					\
+									\
+	unsafe_copy_to_user(__c, __s, sizeof(*__c), label);		\
+} while (0)
+#endif
+
 extern int compat_ptrace_request(struct task_struct *child,
 				 compat_long_t request,
 				 compat_ulong_t addr, compat_ulong_t data);
-- 
cgit v1.2.3


From d4bff72c8401e6f56194ecf455db70ebc22929e2 Mon Sep 17 00:00:00 2001
From: Thomas Karlsson <thomas.karlsson@paneda.se>
Date: Wed, 2 Dec 2020 19:49:58 +0100
Subject: macvlan: Support for high multicast packet rate

Background:
Broadcast and multicast packages are enqueued for later processing.
This queue was previously hardcoded to 1000.

This proved insufficient for handling very high packet rates.
This resulted in packet drops for multicast.
While at the same time unicast worked fine.

The change:
This patch make the queue length adjustable to accommodate
for environments with very high multicast packet rate.
But still keeps the default value of 1000 unless specified.

The queue length is specified as a request per macvlan
using the IFLA_MACVLAN_BC_QUEUE_LEN parameter.

The actual used queue length will then be the maximum of
any macvlan connected to the same port. The actual used
queue length for the port can be retrieved (read only)
by the IFLA_MACVLAN_BC_QUEUE_LEN_USED parameter for verification.

This will be followed up by a patch to iproute2
in order to adjust the parameter from userspace.

Signed-off-by: Thomas Karlsson <thomas.karlsson@paneda.se>
Link: https://lore.kernel.org/r/dd4673b2-7eab-edda-6815-85c67ce87f63@paneda.se
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/macvlan.c              | 40 ++++++++++++++++++++++++++++++++++++--
 include/linux/if_macvlan.h         |  1 +
 include/uapi/linux/if_link.h       |  2 ++
 tools/include/uapi/linux/if_link.h |  2 ++
 4 files changed, 43 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index d9b6c44a5911..fb51329f8964 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -35,7 +35,7 @@
 
 #define MACVLAN_HASH_BITS	8
 #define MACVLAN_HASH_SIZE	(1<<MACVLAN_HASH_BITS)
-#define MACVLAN_BC_QUEUE_LEN	1000
+#define MACVLAN_DEFAULT_BC_QUEUE_LEN	1000
 
 #define MACVLAN_F_PASSTHRU	1
 #define MACVLAN_F_ADDRCHANGE	2
@@ -46,6 +46,7 @@ struct macvlan_port {
 	struct list_head	vlans;
 	struct sk_buff_head	bc_queue;
 	struct work_struct	bc_work;
+	u32			bc_queue_len_used;
 	u32			flags;
 	int			count;
 	struct hlist_head	vlan_source_hash[MACVLAN_HASH_SIZE];
@@ -67,6 +68,7 @@ struct macvlan_skb_cb {
 #define MACVLAN_SKB_CB(__skb) ((struct macvlan_skb_cb *)&((__skb)->cb[0]))
 
 static void macvlan_port_destroy(struct net_device *dev);
+static void update_port_bc_queue_len(struct macvlan_port *port);
 
 static inline bool macvlan_passthru(const struct macvlan_port *port)
 {
@@ -354,7 +356,7 @@ static void macvlan_broadcast_enqueue(struct macvlan_port *port,
 	MACVLAN_SKB_CB(nskb)->src = src;
 
 	spin_lock(&port->bc_queue.lock);
-	if (skb_queue_len(&port->bc_queue) < MACVLAN_BC_QUEUE_LEN) {
+	if (skb_queue_len(&port->bc_queue) < port->bc_queue_len_used) {
 		if (src)
 			dev_hold(src->dev);
 		__skb_queue_tail(&port->bc_queue, nskb);
@@ -1218,6 +1220,7 @@ static int macvlan_port_create(struct net_device *dev)
 	for (i = 0; i < MACVLAN_HASH_SIZE; i++)
 		INIT_HLIST_HEAD(&port->vlan_source_hash[i]);
 
+	port->bc_queue_len_used = 0;
 	skb_queue_head_init(&port->bc_queue);
 	INIT_WORK(&port->bc_work, macvlan_process_broadcast);
 
@@ -1486,6 +1489,10 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
 			goto destroy_macvlan_port;
 	}
 
+	vlan->bc_queue_len_req = MACVLAN_DEFAULT_BC_QUEUE_LEN;
+	if (data && data[IFLA_MACVLAN_BC_QUEUE_LEN])
+		vlan->bc_queue_len_req = nla_get_u32(data[IFLA_MACVLAN_BC_QUEUE_LEN]);
+
 	err = register_netdevice(dev);
 	if (err < 0)
 		goto destroy_macvlan_port;
@@ -1496,6 +1503,7 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
 		goto unregister_netdev;
 
 	list_add_tail_rcu(&vlan->list, &port->vlans);
+	update_port_bc_queue_len(vlan->port);
 	netif_stacked_transfer_operstate(lowerdev, dev);
 	linkwatch_fire_event(dev);
 
@@ -1529,6 +1537,7 @@ void macvlan_dellink(struct net_device *dev, struct list_head *head)
 	if (vlan->mode == MACVLAN_MODE_SOURCE)
 		macvlan_flush_sources(vlan->port, vlan);
 	list_del_rcu(&vlan->list);
+	update_port_bc_queue_len(vlan->port);
 	unregister_netdevice_queue(dev, head);
 	netdev_upper_dev_unlink(vlan->lowerdev, dev);
 }
@@ -1572,6 +1581,12 @@ static int macvlan_changelink(struct net_device *dev,
 		}
 		vlan->flags = flags;
 	}
+
+	if (data && data[IFLA_MACVLAN_BC_QUEUE_LEN]) {
+		vlan->bc_queue_len_req = nla_get_u32(data[IFLA_MACVLAN_BC_QUEUE_LEN]);
+		update_port_bc_queue_len(vlan->port);
+	}
+
 	if (set_mode)
 		vlan->mode = mode;
 	if (data && data[IFLA_MACVLAN_MACADDR_MODE]) {
@@ -1602,6 +1617,8 @@ static size_t macvlan_get_size(const struct net_device *dev)
 		+ nla_total_size(2) /* IFLA_MACVLAN_FLAGS */
 		+ nla_total_size(4) /* IFLA_MACVLAN_MACADDR_COUNT */
 		+ macvlan_get_size_mac(vlan) /* IFLA_MACVLAN_MACADDR */
+		+ nla_total_size(4) /* IFLA_MACVLAN_BC_QUEUE_LEN */
+		+ nla_total_size(4) /* IFLA_MACVLAN_BC_QUEUE_LEN_USED */
 		);
 }
 
@@ -1625,6 +1642,7 @@ static int macvlan_fill_info(struct sk_buff *skb,
 				const struct net_device *dev)
 {
 	struct macvlan_dev *vlan = netdev_priv(dev);
+	struct macvlan_port *port = vlan->port;
 	int i;
 	struct nlattr *nest;
 
@@ -1645,6 +1663,10 @@ static int macvlan_fill_info(struct sk_buff *skb,
 		}
 		nla_nest_end(skb, nest);
 	}
+	if (nla_put_u32(skb, IFLA_MACVLAN_BC_QUEUE_LEN, vlan->bc_queue_len_req))
+		goto nla_put_failure;
+	if (nla_put_u32(skb, IFLA_MACVLAN_BC_QUEUE_LEN_USED, port->bc_queue_len_used))
+		goto nla_put_failure;
 	return 0;
 
 nla_put_failure:
@@ -1658,6 +1680,8 @@ static const struct nla_policy macvlan_policy[IFLA_MACVLAN_MAX + 1] = {
 	[IFLA_MACVLAN_MACADDR] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
 	[IFLA_MACVLAN_MACADDR_DATA] = { .type = NLA_NESTED },
 	[IFLA_MACVLAN_MACADDR_COUNT] = { .type = NLA_U32 },
+	[IFLA_MACVLAN_BC_QUEUE_LEN] = { .type = NLA_U32 },
+	[IFLA_MACVLAN_BC_QUEUE_LEN_USED] = { .type = NLA_REJECT },
 };
 
 int macvlan_link_register(struct rtnl_link_ops *ops)
@@ -1688,6 +1712,18 @@ static struct rtnl_link_ops macvlan_link_ops = {
 	.priv_size      = sizeof(struct macvlan_dev),
 };
 
+static void update_port_bc_queue_len(struct macvlan_port *port)
+{
+	u32 max_bc_queue_len_req = 0;
+	struct macvlan_dev *vlan;
+
+	list_for_each_entry(vlan, &port->vlans, list) {
+		if (vlan->bc_queue_len_req > max_bc_queue_len_req)
+			max_bc_queue_len_req = vlan->bc_queue_len_req;
+	}
+	port->bc_queue_len_used = max_bc_queue_len_req;
+}
+
 static int macvlan_device_event(struct notifier_block *unused,
 				unsigned long event, void *ptr)
 {
diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h
index a367ead4bf4b..96556c64c95d 100644
--- a/include/linux/if_macvlan.h
+++ b/include/linux/if_macvlan.h
@@ -30,6 +30,7 @@ struct macvlan_dev {
 	enum macvlan_mode	mode;
 	u16			flags;
 	unsigned int		macaddr_count;
+	u32			bc_queue_len_req;
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	struct netpoll		*netpoll;
 #endif
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index c4b23f06f69e..874cc12a34d9 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -588,6 +588,8 @@ enum {
 	IFLA_MACVLAN_MACADDR,
 	IFLA_MACVLAN_MACADDR_DATA,
 	IFLA_MACVLAN_MACADDR_COUNT,
+	IFLA_MACVLAN_BC_QUEUE_LEN,
+	IFLA_MACVLAN_BC_QUEUE_LEN_USED,
 	__IFLA_MACVLAN_MAX,
 };
 
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index 781e482dc499..d208b2af697f 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -409,6 +409,8 @@ enum {
 	IFLA_MACVLAN_MACADDR,
 	IFLA_MACVLAN_MACADDR_DATA,
 	IFLA_MACVLAN_MACADDR_COUNT,
+	IFLA_MACVLAN_BC_QUEUE_LEN,
+	IFLA_MACVLAN_BC_QUEUE_LEN_USED,
 	__IFLA_MACVLAN_MAX,
 };
 
-- 
cgit v1.2.3


From d421e466c2373095f165ddd25cbabd6c5b077928 Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Wed, 2 Dec 2020 20:39:46 -0800
Subject: net/mlx5: DR, Proper handling of unsupported Connect-X6DX SW steering

STEs format for Connect-X5 and Connect-X6DX different. Currently, on
Connext-X6DX the SW steering would break at some point when building STEs
w/o giving a proper error message. Fix this by checking the STE format of
the current device when initializing domain: add mlx5_ifc definitions for
Connect-X6DX SW steering, read FW capability to get the current format
version, and check this version when domain is being created.

Fixes: 26d688e33f88 ("net/mlx5: DR, Add Steering entry (STE) utilities")
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c    | 1 +
 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c | 5 +++++
 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h  | 1 +
 include/linux/mlx5/mlx5_ifc.h                                | 9 ++++++++-
 4 files changed, 15 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c
index 6bd34b293007..51bbd88ff021 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c
@@ -92,6 +92,7 @@ int mlx5dr_cmd_query_device(struct mlx5_core_dev *mdev,
 	caps->eswitch_manager	= MLX5_CAP_GEN(mdev, eswitch_manager);
 	caps->gvmi		= MLX5_CAP_GEN(mdev, vhca_id);
 	caps->flex_protocols	= MLX5_CAP_GEN(mdev, flex_parser_protocols);
+	caps->sw_format_ver	= MLX5_CAP_GEN(mdev, steering_format_version);
 
 	if (mlx5dr_matcher_supp_flex_parser_icmp_v4(caps)) {
 		caps->flex_parser_id_icmp_dw0 = MLX5_CAP_GEN(mdev, flex_parser_id_icmp_dw0);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
index 890767a2a7cb..aa2c2d6c44e6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
@@ -223,6 +223,11 @@ static int dr_domain_caps_init(struct mlx5_core_dev *mdev,
 	if (ret)
 		return ret;
 
+	if (dmn->info.caps.sw_format_ver != MLX5_STEERING_FORMAT_CONNECTX_5) {
+		mlx5dr_err(dmn, "SW steering is not supported on this device\n");
+		return -EOPNOTSUPP;
+	}
+
 	ret = dr_domain_query_fdb_caps(mdev, dmn);
 	if (ret)
 		return ret;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
index f50f3b107aa3..cf62ea4f882e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
@@ -625,6 +625,7 @@ struct mlx5dr_cmd_caps {
 	u8 max_ft_level;
 	u16 roce_min_src_udp;
 	u8 num_esw_ports;
+	u8 sw_format_ver;
 	bool eswitch_manager;
 	bool rx_sw_owner;
 	bool tx_sw_owner;
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index a092346c7b2d..233352447b1a 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1223,6 +1223,11 @@ enum mlx5_fc_bulk_alloc_bitmask {
 
 #define MLX5_FC_BULK_NUM_FCS(fc_enum) (MLX5_FC_BULK_SIZE_FACTOR * (fc_enum))
 
+enum {
+	MLX5_STEERING_FORMAT_CONNECTX_5   = 0,
+	MLX5_STEERING_FORMAT_CONNECTX_6DX = 1,
+};
+
 struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         reserved_at_0[0x30];
 	u8         vhca_id[0x10];
@@ -1521,7 +1526,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 	u8         general_obj_types[0x40];
 
-	u8         reserved_at_440[0x20];
+	u8         reserved_at_440[0x4];
+	u8         steering_format_version[0x4];
+	u8         create_qp_start_hint[0x18];
 
 	u8         reserved_at_460[0x3];
 	u8         log_max_uctx[0x5];
-- 
cgit v1.2.3


From 0fb6ee8d0b5e90b72f870f76debc8bd31a742014 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Tue, 24 Nov 2020 14:38:07 +0200
Subject: iio: ad_sigma_delta: Don't put SPI transfer buffer on the stack

Use a heap allocated memory for the SPI transfer buffer. Using stack memory
can corrupt stack memory when using DMA on some systems.

This change moves the buffer from the stack of the trigger handler call to
the heap of the buffer of the state struct. The size increases takes into
account the alignment for the timestamp, which is 8 bytes.

The 'data' buffer is split into 'tx_buf' and 'rx_buf', to make a clearer
separation of which part of the buffer should be used for TX & RX.

Fixes: af3008485ea03 ("iio:adc: Add common code for ADI Sigma Delta devices")
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Link: https://lore.kernel.org/r/20201124123807.19717-1-alexandru.ardelean@analog.com
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad_sigma_delta.c       | 18 ++++++++----------
 include/linux/iio/adc/ad_sigma_delta.h |  6 +++++-
 2 files changed, 13 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iio/adc/ad_sigma_delta.c b/drivers/iio/adc/ad_sigma_delta.c
index 86039e9ecaca..3a6f239d4acc 100644
--- a/drivers/iio/adc/ad_sigma_delta.c
+++ b/drivers/iio/adc/ad_sigma_delta.c
@@ -57,7 +57,7 @@ EXPORT_SYMBOL_GPL(ad_sd_set_comm);
 int ad_sd_write_reg(struct ad_sigma_delta *sigma_delta, unsigned int reg,
 	unsigned int size, unsigned int val)
 {
-	uint8_t *data = sigma_delta->data;
+	uint8_t *data = sigma_delta->tx_buf;
 	struct spi_transfer t = {
 		.tx_buf		= data,
 		.len		= size + 1,
@@ -99,7 +99,7 @@ EXPORT_SYMBOL_GPL(ad_sd_write_reg);
 static int ad_sd_read_reg_raw(struct ad_sigma_delta *sigma_delta,
 	unsigned int reg, unsigned int size, uint8_t *val)
 {
-	uint8_t *data = sigma_delta->data;
+	uint8_t *data = sigma_delta->tx_buf;
 	int ret;
 	struct spi_transfer t[] = {
 		{
@@ -146,22 +146,22 @@ int ad_sd_read_reg(struct ad_sigma_delta *sigma_delta,
 {
 	int ret;
 
-	ret = ad_sd_read_reg_raw(sigma_delta, reg, size, sigma_delta->data);
+	ret = ad_sd_read_reg_raw(sigma_delta, reg, size, sigma_delta->rx_buf);
 	if (ret < 0)
 		goto out;
 
 	switch (size) {
 	case 4:
-		*val = get_unaligned_be32(sigma_delta->data);
+		*val = get_unaligned_be32(sigma_delta->rx_buf);
 		break;
 	case 3:
-		*val = get_unaligned_be24(&sigma_delta->data[0]);
+		*val = get_unaligned_be24(sigma_delta->rx_buf);
 		break;
 	case 2:
-		*val = get_unaligned_be16(sigma_delta->data);
+		*val = get_unaligned_be16(sigma_delta->rx_buf);
 		break;
 	case 1:
-		*val = sigma_delta->data[0];
+		*val = sigma_delta->rx_buf[0];
 		break;
 	default:
 		ret = -EINVAL;
@@ -395,11 +395,9 @@ static irqreturn_t ad_sd_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct ad_sigma_delta *sigma_delta = iio_device_get_drvdata(indio_dev);
+	uint8_t *data = sigma_delta->rx_buf;
 	unsigned int reg_size;
 	unsigned int data_reg;
-	uint8_t data[16];
-
-	memset(data, 0x00, 16);
 
 	reg_size = indio_dev->channels[0].scan_type.realbits +
 			indio_dev->channels[0].scan_type.shift;
diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h
index a3a838dcf8e4..7199280d89ca 100644
--- a/include/linux/iio/adc/ad_sigma_delta.h
+++ b/include/linux/iio/adc/ad_sigma_delta.h
@@ -79,8 +79,12 @@ struct ad_sigma_delta {
 	/*
 	 * DMA (thus cache coherency maintenance) requires the
 	 * transfer buffers to live in their own cache lines.
+	 * 'tx_buf' is up to 32 bits.
+	 * 'rx_buf' is up to 32 bits per sample + 64 bit timestamp,
+	 * rounded to 16 bytes to take into account padding.
 	 */
-	uint8_t				data[4] ____cacheline_aligned;
+	uint8_t				tx_buf[4] ____cacheline_aligned;
+	uint8_t				rx_buf[16] __aligned(8);
 };
 
 static inline int ad_sigma_delta_set_channel(struct ad_sigma_delta *sd,
-- 
cgit v1.2.3


From eca8523a388f65cc0f515e3db4f3b027d7546532 Mon Sep 17 00:00:00 2001
From: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Date: Sun, 20 Sep 2020 14:25:48 +0100
Subject: iio:trigger: rename try_reenable() to reenable() plus return void

As we no longer support a try again if we cannot reenable the trigger
rename the function to reflect this.   Also we don't do anything with
the value returned so stop it returning anything.  For the few drivers
that didn't already print an error message in this patch, add such
a print.

Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Cc: Linus Walleij <linus.walleij@linaro.org>
Cc: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Cc: Christian Oder <me@myself5.de>
Cc: Eugen Hristev <eugen.hristev@microchip.com>
Cc: Nishant Malpani <nish.malpani25@gmail.com>
Cc: Daniel Baluta <daniel.baluta@oss.nxp.com>
Link: https://lore.kernel.org/r/20200920132548.196452-3-jic23@kernel.org
---
 drivers/iio/accel/bma180.c             |  9 ++++++---
 drivers/iio/accel/bmc150-accel-core.c  | 12 ++++--------
 drivers/iio/accel/kxcjk-1013.c         | 10 +++-------
 drivers/iio/accel/mxc4005.c            | 16 ++++++----------
 drivers/iio/adc/at91-sama5d2_adc.c     |  8 +++-----
 drivers/iio/gyro/adxrs290.c            |  6 ++----
 drivers/iio/gyro/bmg160_core.c         | 12 ++++--------
 drivers/iio/imu/kmx61.c                | 10 +++-------
 drivers/iio/industrialio-trigger.c     |  4 ++--
 drivers/iio/magnetometer/bmc150_magn.c | 10 +++++-----
 include/linux/iio/trigger.h            |  4 ++--
 11 files changed, 40 insertions(+), 61 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iio/accel/bma180.c b/drivers/iio/accel/bma180.c
index 6b74c2b04c15..71f85a3e525b 100644
--- a/drivers/iio/accel/bma180.c
+++ b/drivers/iio/accel/bma180.c
@@ -959,17 +959,20 @@ static int bma180_data_rdy_trigger_set_state(struct iio_trigger *trig,
 	return bma180_set_new_data_intr_state(data, state);
 }
 
-static int bma180_trig_try_reen(struct iio_trigger *trig)
+static void bma180_trig_reen(struct iio_trigger *trig)
 {
 	struct iio_dev *indio_dev = iio_trigger_get_drvdata(trig);
 	struct bma180_data *data = iio_priv(indio_dev);
+	int ret;
 
-	return bma180_reset_intr(data);
+	ret = bma180_reset_intr(data);
+	if (ret)
+		dev_err(&data->client->dev, "failed to reset interrupt\n");
 }
 
 static const struct iio_trigger_ops bma180_trigger_ops = {
 	.set_trigger_state = bma180_data_rdy_trigger_set_state,
-	.try_reenable = bma180_trig_try_reen,
+	.reenable = bma180_trig_reen,
 };
 
 static int bma180_probe(struct i2c_client *client,
diff --git a/drivers/iio/accel/bmc150-accel-core.c b/drivers/iio/accel/bmc150-accel-core.c
index 20dc7bc291f8..9a552d11ea27 100644
--- a/drivers/iio/accel/bmc150-accel-core.c
+++ b/drivers/iio/accel/bmc150-accel-core.c
@@ -1151,7 +1151,7 @@ err_read:
 	return IRQ_HANDLED;
 }
 
-static int bmc150_accel_trig_try_reen(struct iio_trigger *trig)
+static void bmc150_accel_trig_reen(struct iio_trigger *trig)
 {
 	struct bmc150_accel_trigger *t = iio_trigger_get_drvdata(trig);
 	struct bmc150_accel_data *data = t->data;
@@ -1160,7 +1160,7 @@ static int bmc150_accel_trig_try_reen(struct iio_trigger *trig)
 
 	/* new data interrupts don't need ack */
 	if (t == &t->data->triggers[BMC150_ACCEL_TRIGGER_DATA_READY])
-		return 0;
+		return;
 
 	mutex_lock(&data->mutex);
 	/* clear any latched interrupt */
@@ -1168,12 +1168,8 @@ static int bmc150_accel_trig_try_reen(struct iio_trigger *trig)
 			   BMC150_ACCEL_INT_MODE_LATCH_INT |
 			   BMC150_ACCEL_INT_MODE_LATCH_RESET);
 	mutex_unlock(&data->mutex);
-	if (ret < 0) {
+	if (ret < 0)
 		dev_err(dev, "Error writing reg_int_rst_latch\n");
-		return ret;
-	}
-
-	return 0;
 }
 
 static int bmc150_accel_trigger_set_state(struct iio_trigger *trig,
@@ -1213,7 +1209,7 @@ static int bmc150_accel_trigger_set_state(struct iio_trigger *trig,
 
 static const struct iio_trigger_ops bmc150_accel_trigger_ops = {
 	.set_trigger_state = bmc150_accel_trigger_set_state,
-	.try_reenable = bmc150_accel_trig_try_reen,
+	.reenable = bmc150_accel_trig_reen,
 };
 
 static int bmc150_accel_handle_roc_event(struct iio_dev *indio_dev)
diff --git a/drivers/iio/accel/kxcjk-1013.c b/drivers/iio/accel/kxcjk-1013.c
index 560a3373ff20..e92c7e6766e1 100644
--- a/drivers/iio/accel/kxcjk-1013.c
+++ b/drivers/iio/accel/kxcjk-1013.c
@@ -1105,19 +1105,15 @@ err:
 	return IRQ_HANDLED;
 }
 
-static int kxcjk1013_trig_try_reen(struct iio_trigger *trig)
+static void kxcjk1013_trig_reen(struct iio_trigger *trig)
 {
 	struct iio_dev *indio_dev = iio_trigger_get_drvdata(trig);
 	struct kxcjk1013_data *data = iio_priv(indio_dev);
 	int ret;
 
 	ret = i2c_smbus_read_byte_data(data->client, KXCJK1013_REG_INT_REL);
-	if (ret < 0) {
+	if (ret < 0)
 		dev_err(&data->client->dev, "Error reading reg_int_rel\n");
-		return ret;
-	}
-
-	return 0;
 }
 
 static int kxcjk1013_data_rdy_trigger_set_state(struct iio_trigger *trig,
@@ -1161,7 +1157,7 @@ static int kxcjk1013_data_rdy_trigger_set_state(struct iio_trigger *trig,
 
 static const struct iio_trigger_ops kxcjk1013_trigger_ops = {
 	.set_trigger_state = kxcjk1013_data_rdy_trigger_set_state,
-	.try_reenable = kxcjk1013_trig_try_reen,
+	.reenable = kxcjk1013_trig_reen,
 };
 
 static void kxcjk1013_report_motion_event(struct iio_dev *indio_dev)
diff --git a/drivers/iio/accel/mxc4005.c b/drivers/iio/accel/mxc4005.c
index f877263dc6ef..0f8fd687866d 100644
--- a/drivers/iio/accel/mxc4005.c
+++ b/drivers/iio/accel/mxc4005.c
@@ -310,19 +310,15 @@ err:
 	return IRQ_HANDLED;
 }
 
-static int mxc4005_clr_intr(struct mxc4005_data *data)
+static void mxc4005_clr_intr(struct mxc4005_data *data)
 {
 	int ret;
 
 	/* clear interrupt */
 	ret = regmap_write(data->regmap, MXC4005_REG_INT_CLR1,
 			   MXC4005_REG_INT_CLR1_BIT_DRDYC);
-	if (ret < 0) {
+	if (ret < 0)
 		dev_err(data->dev, "failed to write to reg_int_clr1\n");
-		return ret;
-	}
-
-	return 0;
 }
 
 static int mxc4005_set_trigger_state(struct iio_trigger *trig,
@@ -353,20 +349,20 @@ static int mxc4005_set_trigger_state(struct iio_trigger *trig,
 	return 0;
 }
 
-static int mxc4005_trigger_try_reen(struct iio_trigger *trig)
+static void mxc4005_trigger_reen(struct iio_trigger *trig)
 {
 	struct iio_dev *indio_dev = iio_trigger_get_drvdata(trig);
 	struct mxc4005_data *data = iio_priv(indio_dev);
 
 	if (!data->dready_trig)
-		return 0;
+		return;
 
-	return mxc4005_clr_intr(data);
+	mxc4005_clr_intr(data);
 }
 
 static const struct iio_trigger_ops mxc4005_trigger_ops = {
 	.set_trigger_state = mxc4005_set_trigger_state,
-	.try_reenable = mxc4005_trigger_try_reen,
+	.reenable = mxc4005_trigger_reen,
 };
 
 static int mxc4005_chip_init(struct mxc4005_data *data)
diff --git a/drivers/iio/adc/at91-sama5d2_adc.c b/drivers/iio/adc/at91-sama5d2_adc.c
index 6edcc99009d1..a7826f097b95 100644
--- a/drivers/iio/adc/at91-sama5d2_adc.c
+++ b/drivers/iio/adc/at91-sama5d2_adc.c
@@ -742,26 +742,24 @@ static int at91_adc_configure_trigger(struct iio_trigger *trig, bool state)
 	return 0;
 }
 
-static int at91_adc_reenable_trigger(struct iio_trigger *trig)
+static void at91_adc_reenable_trigger(struct iio_trigger *trig)
 {
 	struct iio_dev *indio = iio_trigger_get_drvdata(trig);
 	struct at91_adc_state *st = iio_priv(indio);
 
 	/* if we are using DMA, we must not reenable irq after each trigger */
 	if (st->dma_st.dma_chan)
-		return 0;
+		return;
 
 	enable_irq(st->irq);
 
 	/* Needed to ACK the DRDY interruption */
 	at91_adc_readl(st, AT91_SAMA5D2_LCDR);
-
-	return 0;
 }
 
 static const struct iio_trigger_ops at91_adc_trigger_ops = {
 	.set_trigger_state = &at91_adc_configure_trigger,
-	.try_reenable = &at91_adc_reenable_trigger,
+	.reenable = &at91_adc_reenable_trigger,
 	.validate_device = iio_trigger_validate_own_device,
 };
 
diff --git a/drivers/iio/gyro/adxrs290.c b/drivers/iio/gyro/adxrs290.c
index ca6fc234076e..c45d8226cc2b 100644
--- a/drivers/iio/gyro/adxrs290.c
+++ b/drivers/iio/gyro/adxrs290.c
@@ -478,7 +478,7 @@ static int adxrs290_data_rdy_trigger_set_state(struct iio_trigger *trig,
 	return ret;
 }
 
-static int adxrs290_reset_trig(struct iio_trigger *trig)
+static void adxrs290_reset_trig(struct iio_trigger *trig)
 {
 	struct iio_dev *indio_dev = iio_trigger_get_drvdata(trig);
 	int val;
@@ -491,14 +491,12 @@ static int adxrs290_reset_trig(struct iio_trigger *trig)
 	 */
 	adxrs290_get_rate_data(indio_dev,
 			       ADXRS290_READ_REG(ADXRS290_REG_DATAY0), &val);
-
-	return 0;
 }
 
 static const struct iio_trigger_ops adxrs290_trigger_ops = {
 	.set_trigger_state = &adxrs290_data_rdy_trigger_set_state,
 	.validate_device = &iio_trigger_validate_own_device,
-	.try_reenable = &adxrs290_reset_trig,
+	.reenable = &adxrs290_reset_trig,
 };
 
 static irqreturn_t adxrs290_trigger_handler(int irq, void *p)
diff --git a/drivers/iio/gyro/bmg160_core.c b/drivers/iio/gyro/bmg160_core.c
index 8ddda96455fc..2d5015801a75 100644
--- a/drivers/iio/gyro/bmg160_core.c
+++ b/drivers/iio/gyro/bmg160_core.c
@@ -893,7 +893,7 @@ err:
 	return IRQ_HANDLED;
 }
 
-static int bmg160_trig_try_reen(struct iio_trigger *trig)
+static void bmg160_trig_reen(struct iio_trigger *trig)
 {
 	struct iio_dev *indio_dev = iio_trigger_get_drvdata(trig);
 	struct bmg160_data *data = iio_priv(indio_dev);
@@ -902,18 +902,14 @@ static int bmg160_trig_try_reen(struct iio_trigger *trig)
 
 	/* new data interrupts don't need ack */
 	if (data->dready_trigger_on)
-		return 0;
+		return;
 
 	/* Set latched mode interrupt and clear any latched interrupt */
 	ret = regmap_write(data->regmap, BMG160_REG_INT_RST_LATCH,
 			   BMG160_INT_MODE_LATCH_INT |
 			   BMG160_INT_MODE_LATCH_RESET);
-	if (ret < 0) {
+	if (ret < 0)
 		dev_err(dev, "Error writing reg_rst_latch\n");
-		return ret;
-	}
-
-	return 0;
 }
 
 static int bmg160_data_rdy_trigger_set_state(struct iio_trigger *trig,
@@ -961,7 +957,7 @@ static int bmg160_data_rdy_trigger_set_state(struct iio_trigger *trig,
 
 static const struct iio_trigger_ops bmg160_trigger_ops = {
 	.set_trigger_state = bmg160_data_rdy_trigger_set_state,
-	.try_reenable = bmg160_trig_try_reen,
+	.reenable = bmg160_trig_reen,
 };
 
 static irqreturn_t bmg160_event_handler(int irq, void *private)
diff --git a/drivers/iio/imu/kmx61.c b/drivers/iio/imu/kmx61.c
index 61885e99d3fc..4377047d503a 100644
--- a/drivers/iio/imu/kmx61.c
+++ b/drivers/iio/imu/kmx61.c
@@ -1063,24 +1063,20 @@ err_unlock:
 	return ret;
 }
 
-static int kmx61_trig_try_reenable(struct iio_trigger *trig)
+static void kmx61_trig_reenable(struct iio_trigger *trig)
 {
 	struct iio_dev *indio_dev = iio_trigger_get_drvdata(trig);
 	struct kmx61_data *data = kmx61_get_data(indio_dev);
 	int ret;
 
 	ret = i2c_smbus_read_byte_data(data->client, KMX61_REG_INL);
-	if (ret < 0) {
+	if (ret < 0)
 		dev_err(&data->client->dev, "Error reading reg_inl\n");
-		return ret;
-	}
-
-	return 0;
 }
 
 static const struct iio_trigger_ops kmx61_trigger_ops = {
 	.set_trigger_state = kmx61_data_rdy_trigger_set_state,
-	.try_reenable = kmx61_trig_try_reenable,
+	.reenable = kmx61_trig_reenable,
 };
 
 static irqreturn_t kmx61_event_handler(int irq, void *private)
diff --git a/drivers/iio/industrialio-trigger.c b/drivers/iio/industrialio-trigger.c
index f902be90980b..ea3c9859b258 100644
--- a/drivers/iio/industrialio-trigger.c
+++ b/drivers/iio/industrialio-trigger.c
@@ -203,8 +203,8 @@ EXPORT_SYMBOL(iio_trigger_poll_chained);
 void iio_trigger_notify_done(struct iio_trigger *trig)
 {
 	if (atomic_dec_and_test(&trig->use_count) && trig->ops &&
-	    trig->ops->try_reenable)
-		trig->ops->try_reenable(trig);
+	    trig->ops->reenable)
+		trig->ops->reenable(trig);
 }
 EXPORT_SYMBOL(iio_trigger_notify_done);
 
diff --git a/drivers/iio/magnetometer/bmc150_magn.c b/drivers/iio/magnetometer/bmc150_magn.c
index 73e55ec815ec..fa09fcab620a 100644
--- a/drivers/iio/magnetometer/bmc150_magn.c
+++ b/drivers/iio/magnetometer/bmc150_magn.c
@@ -766,20 +766,20 @@ static int bmc150_magn_reset_intr(struct bmc150_magn_data *data)
 	return regmap_read(data->regmap, BMC150_MAGN_REG_X_L, &tmp);
 }
 
-static int bmc150_magn_trig_try_reen(struct iio_trigger *trig)
+static void bmc150_magn_trig_reen(struct iio_trigger *trig)
 {
 	struct iio_dev *indio_dev = iio_trigger_get_drvdata(trig);
 	struct bmc150_magn_data *data = iio_priv(indio_dev);
 	int ret;
 
 	if (!data->dready_trigger_on)
-		return 0;
+		return;
 
 	mutex_lock(&data->mutex);
 	ret = bmc150_magn_reset_intr(data);
 	mutex_unlock(&data->mutex);
-
-	return ret;
+	if (ret)
+		dev_err(data->dev, "Failed to reset interrupt\n");
 }
 
 static int bmc150_magn_data_rdy_trigger_set_state(struct iio_trigger *trig,
@@ -817,7 +817,7 @@ err_unlock:
 
 static const struct iio_trigger_ops bmc150_magn_trigger_ops = {
 	.set_trigger_state = bmc150_magn_data_rdy_trigger_set_state,
-	.try_reenable = bmc150_magn_trig_try_reen,
+	.reenable = bmc150_magn_trig_reen,
 };
 
 static int bmc150_magn_buffer_preenable(struct iio_dev *indio_dev)
diff --git a/include/linux/iio/trigger.h b/include/linux/iio/trigger.h
index f930c4ccf378..055890b6ffcf 100644
--- a/include/linux/iio/trigger.h
+++ b/include/linux/iio/trigger.h
@@ -21,7 +21,7 @@ struct iio_trigger;
 /**
  * struct iio_trigger_ops - operations structure for an iio_trigger.
  * @set_trigger_state:	switch on/off the trigger on demand
- * @try_reenable:	function to reenable the trigger when the
+ * @reenable:		function to reenable the trigger when the
  *			use count is zero (may be NULL)
  * @validate_device:	function to validate the device when the
  *			current trigger gets changed.
@@ -31,7 +31,7 @@ struct iio_trigger;
  **/
 struct iio_trigger_ops {
 	int (*set_trigger_state)(struct iio_trigger *trig, bool state);
-	int (*try_reenable)(struct iio_trigger *trig);
+	void (*reenable)(struct iio_trigger *trig);
 	int (*validate_device)(struct iio_trigger *trig,
 			       struct iio_dev *indio_dev);
 };
-- 
cgit v1.2.3


From 41dd9596d6b239a125c3d19f9d0ca90bdbfbf876 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 30 Nov 2020 16:36:29 +0100
Subject: security: add const qualifier to struct sock in various places

A followup change to tcp_request_sock_op would have to drop the 'const'
qualifier from the 'route_req' function as the
'security_inet_conn_request' call is moved there - and that function
expects a 'struct sock *'.

However, it turns out its also possible to add a const qualifier to
security_inet_conn_request instead.

Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: James Morris <jamorris@linux.microsoft.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/lsm_audit.h       | 2 +-
 include/linux/lsm_hook_defs.h   | 2 +-
 include/linux/security.h        | 4 ++--
 security/apparmor/include/net.h | 2 +-
 security/apparmor/lsm.c         | 2 +-
 security/apparmor/net.c         | 6 +++---
 security/lsm_audit.c            | 4 ++--
 security/security.c             | 2 +-
 security/selinux/hooks.c        | 2 +-
 security/smack/smack_lsm.c      | 4 ++--
 10 files changed, 15 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/lsm_audit.h b/include/linux/lsm_audit.h
index 28f23b341c1c..cd23355d2271 100644
--- a/include/linux/lsm_audit.h
+++ b/include/linux/lsm_audit.h
@@ -26,7 +26,7 @@
 
 struct lsm_network_audit {
 	int netif;
-	struct sock *sk;
+	const struct sock *sk;
 	u16 family;
 	__be16 dport;
 	__be16 sport;
diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index 32a940117e7a..acc0494cceba 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -301,7 +301,7 @@ LSM_HOOK(void, LSM_RET_VOID, sk_clone_security, const struct sock *sk,
 	 struct sock *newsk)
 LSM_HOOK(void, LSM_RET_VOID, sk_getsecid, struct sock *sk, u32 *secid)
 LSM_HOOK(void, LSM_RET_VOID, sock_graft, struct sock *sk, struct socket *parent)
-LSM_HOOK(int, 0, inet_conn_request, struct sock *sk, struct sk_buff *skb,
+LSM_HOOK(int, 0, inet_conn_request, const struct sock *sk, struct sk_buff *skb,
 	 struct request_sock *req)
 LSM_HOOK(void, LSM_RET_VOID, inet_csk_clone, struct sock *newsk,
 	 const struct request_sock *req)
diff --git a/include/linux/security.h b/include/linux/security.h
index bc2725491560..0df62735651b 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -1358,7 +1358,7 @@ void security_sk_clone(const struct sock *sk, struct sock *newsk);
 void security_sk_classify_flow(struct sock *sk, struct flowi *fl);
 void security_req_classify_flow(const struct request_sock *req, struct flowi *fl);
 void security_sock_graft(struct sock*sk, struct socket *parent);
-int security_inet_conn_request(struct sock *sk,
+int security_inet_conn_request(const struct sock *sk,
 			struct sk_buff *skb, struct request_sock *req);
 void security_inet_csk_clone(struct sock *newsk,
 			const struct request_sock *req);
@@ -1519,7 +1519,7 @@ static inline void security_sock_graft(struct sock *sk, struct socket *parent)
 {
 }
 
-static inline int security_inet_conn_request(struct sock *sk,
+static inline int security_inet_conn_request(const struct sock *sk,
 			struct sk_buff *skb, struct request_sock *req)
 {
 	return 0;
diff --git a/security/apparmor/include/net.h b/security/apparmor/include/net.h
index 2431c011800d..aadb4b29fb66 100644
--- a/security/apparmor/include/net.h
+++ b/security/apparmor/include/net.h
@@ -107,6 +107,6 @@ int aa_sock_file_perm(struct aa_label *label, const char *op, u32 request,
 		      struct socket *sock);
 
 int apparmor_secmark_check(struct aa_label *label, char *op, u32 request,
-			   u32 secid, struct sock *sk);
+			   u32 secid, const struct sock *sk);
 
 #endif /* __AA_NET_H */
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index ffeaee5ed968..1b0aba8eb723 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -1147,7 +1147,7 @@ static void apparmor_sock_graft(struct sock *sk, struct socket *parent)
 }
 
 #ifdef CONFIG_NETWORK_SECMARK
-static int apparmor_inet_conn_request(struct sock *sk, struct sk_buff *skb,
+static int apparmor_inet_conn_request(const struct sock *sk, struct sk_buff *skb,
 				      struct request_sock *req)
 {
 	struct aa_sk_ctx *ctx = SK_CTX(sk);
diff --git a/security/apparmor/net.c b/security/apparmor/net.c
index fa0e85568450..e0c1b50d6edd 100644
--- a/security/apparmor/net.c
+++ b/security/apparmor/net.c
@@ -211,7 +211,7 @@ static int apparmor_secmark_init(struct aa_secmark *secmark)
 }
 
 static int aa_secmark_perm(struct aa_profile *profile, u32 request, u32 secid,
-			   struct common_audit_data *sa, struct sock *sk)
+			   struct common_audit_data *sa)
 {
 	int i, ret;
 	struct aa_perms perms = { };
@@ -244,13 +244,13 @@ static int aa_secmark_perm(struct aa_profile *profile, u32 request, u32 secid,
 }
 
 int apparmor_secmark_check(struct aa_label *label, char *op, u32 request,
-			   u32 secid, struct sock *sk)
+			   u32 secid, const struct sock *sk)
 {
 	struct aa_profile *profile;
 	DEFINE_AUDIT_SK(sa, op, sk);
 
 	return fn_for_each_confined(label, profile,
 				    aa_secmark_perm(profile, request, secid,
-						    &sa, sk));
+						    &sa));
 }
 #endif
diff --git a/security/lsm_audit.c b/security/lsm_audit.c
index 53d0d183db8f..078f9cdcd7f5 100644
--- a/security/lsm_audit.c
+++ b/security/lsm_audit.c
@@ -183,7 +183,7 @@ int ipv6_skb_to_auditdata(struct sk_buff *skb,
 
 
 static inline void print_ipv6_addr(struct audit_buffer *ab,
-				   struct in6_addr *addr, __be16 port,
+				   const struct in6_addr *addr, __be16 port,
 				   char *name1, char *name2)
 {
 	if (!ipv6_addr_any(addr))
@@ -322,7 +322,7 @@ static void dump_common_audit_data(struct audit_buffer *ab,
 	}
 	case LSM_AUDIT_DATA_NET:
 		if (a->u.net->sk) {
-			struct sock *sk = a->u.net->sk;
+			const struct sock *sk = a->u.net->sk;
 			struct unix_sock *u;
 			struct unix_address *addr;
 			int len = 0;
diff --git a/security/security.c b/security/security.c
index a28045dc9e7f..6509f95d203f 100644
--- a/security/security.c
+++ b/security/security.c
@@ -2225,7 +2225,7 @@ void security_sock_graft(struct sock *sk, struct socket *parent)
 }
 EXPORT_SYMBOL(security_sock_graft);
 
-int security_inet_conn_request(struct sock *sk,
+int security_inet_conn_request(const struct sock *sk,
 			struct sk_buff *skb, struct request_sock *req)
 {
 	return call_int_hook(inet_conn_request, 0, sk, skb, req);
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 6b1826fc3658..6fa593006802 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -5355,7 +5355,7 @@ static void selinux_sctp_sk_clone(struct sctp_endpoint *ep, struct sock *sk,
 	selinux_netlbl_sctp_sk_clone(sk, newsk);
 }
 
-static int selinux_inet_conn_request(struct sock *sk, struct sk_buff *skb,
+static int selinux_inet_conn_request(const struct sock *sk, struct sk_buff *skb,
 				     struct request_sock *req)
 {
 	struct sk_security_struct *sksec = sk->sk_security;
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index 5c90b9fa4d40..3a62d6aa74a6 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -3864,7 +3864,7 @@ static inline struct smack_known *smack_from_skb(struct sk_buff *skb)
  *
  * Returns smack_known of the IP options or NULL if that won't work.
  */
-static struct smack_known *smack_from_netlbl(struct sock *sk, u16 family,
+static struct smack_known *smack_from_netlbl(const struct sock *sk, u16 family,
 					     struct sk_buff *skb)
 {
 	struct netlbl_lsm_secattr secattr;
@@ -4114,7 +4114,7 @@ static void smack_sock_graft(struct sock *sk, struct socket *parent)
  * Returns 0 if a task with the packet label could write to
  * the socket, otherwise an error code
  */
-static int smack_inet_conn_request(struct sock *sk, struct sk_buff *skb,
+static int smack_inet_conn_request(const struct sock *sk, struct sk_buff *skb,
 				   struct request_sock *req)
 {
 	u16 family = sk->sk_family;
-- 
cgit v1.2.3


From a15ac665b9e9c90b1557499f2a46c1e89d29154a Mon Sep 17 00:00:00 2001
From: Eric Farman <farman@linux.ibm.com>
Date: Thu, 3 Dec 2020 22:35:11 +0100
Subject: vfio-mdev: Wire in a request handler for mdev parent

While performing some destructive tests with vfio-ccw, where the
paths to a device are forcible removed and thus the device itself
is unreachable, it is rather easy to end up in an endless loop in
vfio_del_group_dev() due to the lack of a request callback for the
associated device.

In this example, one MDEV (77c) is used by a guest, while another
(77b) is not. The symptom is that the iommu is detached from the
mdev for 77b, but not 77c, until that guest is shutdown:

    [  238.794867] vfio_ccw 0.0.077b: MDEV: Unregistering
    [  238.794996] vfio_mdev 11f2d2bc-4083-431d-a023-eff72715c4f0: Removing from iommu group 2
    [  238.795001] vfio_mdev 11f2d2bc-4083-431d-a023-eff72715c4f0: MDEV: detaching iommu
    [  238.795036] vfio_ccw 0.0.077c: MDEV: Unregistering
    ...silence...

Let's wire in the request call back to the mdev device, so that a
device being physically removed from the host can be (gracefully?)
handled by the parent device at the time the device is removed.

Add a message when registering the device if a driver doesn't
provide this callback, so a clue is given that this same loop
may be encountered in a similar situation, and a message when
this occurs instead of the awkward silence noted above.

Signed-off-by: Eric Farman <farman@linux.ibm.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/mdev/mdev_core.c |  4 ++++
 drivers/vfio/mdev/vfio_mdev.c | 13 +++++++++++++
 include/linux/mdev.h          |  4 ++++
 3 files changed, 21 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/vfio/mdev/mdev_core.c b/drivers/vfio/mdev/mdev_core.c
index b558d4cfd082..6de97d25a3f8 100644
--- a/drivers/vfio/mdev/mdev_core.c
+++ b/drivers/vfio/mdev/mdev_core.c
@@ -154,6 +154,10 @@ int mdev_register_device(struct device *dev, const struct mdev_parent_ops *ops)
 	if (!dev)
 		return -EINVAL;
 
+	/* Not mandatory, but its absence could be a problem */
+	if (!ops->request)
+		dev_info(dev, "Driver cannot be asked to release device\n");
+
 	mutex_lock(&parent_list_lock);
 
 	/* Check for duplicate */
diff --git a/drivers/vfio/mdev/vfio_mdev.c b/drivers/vfio/mdev/vfio_mdev.c
index 30964a4e0a28..b52eea128549 100644
--- a/drivers/vfio/mdev/vfio_mdev.c
+++ b/drivers/vfio/mdev/vfio_mdev.c
@@ -98,6 +98,18 @@ static int vfio_mdev_mmap(void *device_data, struct vm_area_struct *vma)
 	return parent->ops->mmap(mdev, vma);
 }
 
+static void vfio_mdev_request(void *device_data, unsigned int count)
+{
+	struct mdev_device *mdev = device_data;
+	struct mdev_parent *parent = mdev->parent;
+
+	if (parent->ops->request)
+		parent->ops->request(mdev, count);
+	else if (count == 0)
+		dev_notice(mdev_dev(mdev),
+			   "No mdev vendor driver request callback support, blocked until released by user\n");
+}
+
 static const struct vfio_device_ops vfio_mdev_dev_ops = {
 	.name		= "vfio-mdev",
 	.open		= vfio_mdev_open,
@@ -106,6 +118,7 @@ static const struct vfio_device_ops vfio_mdev_dev_ops = {
 	.read		= vfio_mdev_read,
 	.write		= vfio_mdev_write,
 	.mmap		= vfio_mdev_mmap,
+	.request	= vfio_mdev_request,
 };
 
 static int vfio_mdev_probe(struct device *dev)
diff --git a/include/linux/mdev.h b/include/linux/mdev.h
index 0ce30ca78db0..9004375c462e 100644
--- a/include/linux/mdev.h
+++ b/include/linux/mdev.h
@@ -72,6 +72,9 @@ struct device *mdev_get_iommu_device(struct device *dev);
  * @mmap:		mmap callback
  *			@mdev: mediated device structure
  *			@vma: vma structure
+ * @request:		request callback to release device
+ *			@mdev: mediated device structure
+ *			@count: request sequence number
  * Parent device that support mediated device should be registered with mdev
  * module with mdev_parent_ops structure.
  **/
@@ -92,6 +95,7 @@ struct mdev_parent_ops {
 	long	(*ioctl)(struct mdev_device *mdev, unsigned int cmd,
 			 unsigned long arg);
 	int	(*mmap)(struct mdev_device *mdev, struct vm_area_struct *vma);
+	void	(*request)(struct mdev_device *mdev, unsigned int count);
 };
 
 /* interface for exporting mdev supported type attributes */
-- 
cgit v1.2.3


From 22dc4a0f5ed11b6dc8fd73a0892fa0ea1a4c3cdf Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Thu, 3 Dec 2020 12:46:29 -0800
Subject: bpf: Remove hard-coded btf_vmlinux assumption from BPF verifier

Remove a permeating assumption thoughout BPF verifier of vmlinux BTF. Instead,
wherever BTF type IDs are involved, also track the instance of struct btf that
goes along with the type ID. This allows to gradually add support for kernel
module BTFs and using/tracking module types across BPF helper calls and
registers.

This patch also renames btf_id() function to btf_obj_id() to minimize naming
clash with using btf_id to denote BTF *type* ID, rather than BTF *object*'s ID.

Also, altough btf_vmlinux can't get destructed and thus doesn't need
refcounting, module BTFs need that, so apply BTF refcounting universally when
BPF program is using BTF-powered attachment (tp_btf, fentry/fexit, etc). This
makes for simpler clean up code.

Now that BTF type ID is not enough to uniquely identify a BTF type, extend BPF
trampoline key to include BTF object ID. To differentiate that from target
program BPF ID, set 31st bit of type ID. BTF type IDs (at least currently) are
not allowed to take full 32 bits, so there is no danger of confusing that bit
with a valid BTF type ID.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20201203204634.1325171-10-andrii@kernel.org
---
 include/linux/bpf.h          | 13 +++++---
 include/linux/bpf_verifier.h | 28 ++++++++++++----
 include/linux/btf.h          |  5 ++-
 kernel/bpf/btf.c             | 65 +++++++++++++++++++++++++------------
 kernel/bpf/syscall.c         | 24 ++++++++++++--
 kernel/bpf/verifier.c        | 77 +++++++++++++++++++++++++++-----------------
 net/ipv4/bpf_tcp_ca.c        |  3 +-
 7 files changed, 148 insertions(+), 67 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index a9de5711b23f..d05e75ed8c1b 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -421,7 +421,10 @@ struct bpf_insn_access_aux {
 	enum bpf_reg_type reg_type;
 	union {
 		int ctx_field_size;
-		u32 btf_id;
+		struct {
+			struct btf *btf;
+			u32 btf_id;
+		};
 	};
 	struct bpf_verifier_log *log; /* for verbose logs */
 };
@@ -458,6 +461,7 @@ struct bpf_verifier_ops {
 				  struct bpf_insn *dst,
 				  struct bpf_prog *prog, u32 *target_size);
 	int (*btf_struct_access)(struct bpf_verifier_log *log,
+				 const struct btf *btf,
 				 const struct btf_type *t, int off, int size,
 				 enum bpf_access_type atype,
 				 u32 *next_btf_id);
@@ -771,6 +775,7 @@ struct bpf_prog_aux {
 	u32 ctx_arg_info_size;
 	u32 max_rdonly_access;
 	u32 max_rdwr_access;
+	struct btf *attach_btf;
 	const struct bpf_ctx_arg_aux *ctx_arg_info;
 	struct mutex dst_mutex; /* protects dst_* pointers below, *after* prog becomes visible */
 	struct bpf_prog *dst_prog;
@@ -1005,7 +1010,6 @@ struct bpf_event_entry {
 
 bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp);
 int bpf_prog_calc_tag(struct bpf_prog *fp);
-const char *kernel_type_name(u32 btf_type_id);
 
 const struct bpf_func_proto *bpf_get_trace_printk_proto(void);
 
@@ -1450,12 +1454,13 @@ int bpf_prog_test_run_raw_tp(struct bpf_prog *prog,
 bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 		    const struct bpf_prog *prog,
 		    struct bpf_insn_access_aux *info);
-int btf_struct_access(struct bpf_verifier_log *log,
+int btf_struct_access(struct bpf_verifier_log *log, const struct btf *btf,
 		      const struct btf_type *t, int off, int size,
 		      enum bpf_access_type atype,
 		      u32 *next_btf_id);
 bool btf_struct_ids_match(struct bpf_verifier_log *log,
-			  int off, u32 id, u32 need_type_id);
+			  const struct btf *btf, u32 id, int off,
+			  const struct btf *need_btf, u32 need_type_id);
 
 int btf_distill_func_proto(struct bpf_verifier_log *log,
 			   struct btf *btf,
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 306869d4743b..e941fe1484e5 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -5,6 +5,7 @@
 #define _LINUX_BPF_VERIFIER_H 1
 
 #include <linux/bpf.h> /* for enum bpf_reg_type */
+#include <linux/btf.h> /* for struct btf and btf_id() */
 #include <linux/filter.h> /* for MAX_BPF_STACK */
 #include <linux/tnum.h>
 
@@ -43,6 +44,8 @@ enum bpf_reg_liveness {
 struct bpf_reg_state {
 	/* Ordering of fields matters.  See states_equal() */
 	enum bpf_reg_type type;
+	/* Fixed part of pointer offset, pointer types only */
+	s32 off;
 	union {
 		/* valid when type == PTR_TO_PACKET */
 		int range;
@@ -52,15 +55,20 @@ struct bpf_reg_state {
 		 */
 		struct bpf_map *map_ptr;
 
-		u32 btf_id; /* for PTR_TO_BTF_ID */
+		/* for PTR_TO_BTF_ID */
+		struct {
+			struct btf *btf;
+			u32 btf_id;
+		};
 
 		u32 mem_size; /* for PTR_TO_MEM | PTR_TO_MEM_OR_NULL */
 
 		/* Max size from any of the above. */
-		unsigned long raw;
+		struct {
+			unsigned long raw1;
+			unsigned long raw2;
+		} raw;
 	};
-	/* Fixed part of pointer offset, pointer types only */
-	s32 off;
 	/* For PTR_TO_PACKET, used to find other pointers with the same variable
 	 * offset, so they can share range knowledge.
 	 * For PTR_TO_MAP_VALUE_OR_NULL this is used to share which map value we
@@ -311,7 +319,10 @@ struct bpf_insn_aux_data {
 		struct {
 			enum bpf_reg_type reg_type;	/* type of pseudo_btf_id */
 			union {
-				u32 btf_id;	/* btf_id for struct typed var */
+				struct {
+					struct btf *btf;
+					u32 btf_id;	/* btf_id for struct typed var */
+				};
 				u32 mem_size;	/* mem_size for non-struct typed var */
 			};
 		} btf_var;
@@ -459,9 +470,12 @@ int check_ctx_reg(struct bpf_verifier_env *env,
 
 /* this lives here instead of in bpf.h because it needs to dereference tgt_prog */
 static inline u64 bpf_trampoline_compute_key(const struct bpf_prog *tgt_prog,
-					     u32 btf_id)
+					     struct btf *btf, u32 btf_id)
 {
-        return tgt_prog ? (((u64)tgt_prog->aux->id) << 32 | btf_id) : btf_id;
+	if (tgt_prog)
+		return ((u64)tgt_prog->aux->id << 32) | btf_id;
+	else
+		return ((u64)btf_obj_id(btf) << 32) | 0x80000000 | btf_id;
 }
 
 int bpf_check_attach_target(struct bpf_verifier_log *log,
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 2bf641829664..fb608e4de076 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -18,6 +18,7 @@ struct btf_show;
 
 extern const struct file_operations btf_fops;
 
+void btf_get(struct btf *btf);
 void btf_put(struct btf *btf);
 int btf_new_fd(const union bpf_attr *attr);
 struct btf *btf_get_by_fd(int fd);
@@ -88,7 +89,7 @@ int btf_type_snprintf_show(const struct btf *btf, u32 type_id, void *obj,
 			   char *buf, int len, u64 flags);
 
 int btf_get_fd_by_id(u32 id);
-u32 btf_id(const struct btf *btf);
+u32 btf_obj_id(const struct btf *btf);
 bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
 			   const struct btf_member *m,
 			   u32 expected_offset, u32 expected_size);
@@ -206,6 +207,8 @@ static inline const struct btf_var_secinfo *btf_type_var_secinfo(
 }
 
 #ifdef CONFIG_BPF_SYSCALL
+struct bpf_prog;
+
 const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id);
 const char *btf_name_by_offset(const struct btf *btf, u32 offset);
 struct btf *btf_parse_vmlinux(void);
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 6b2d508b33d4..7a19bf5bfe97 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -1524,6 +1524,11 @@ static void btf_free_rcu(struct rcu_head *rcu)
 	btf_free(btf);
 }
 
+void btf_get(struct btf *btf)
+{
+	refcount_inc(&btf->refcnt);
+}
+
 void btf_put(struct btf *btf)
 {
 	if (btf && refcount_dec_and_test(&btf->refcnt)) {
@@ -4555,11 +4560,10 @@ struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog)
 {
 	struct bpf_prog *tgt_prog = prog->aux->dst_prog;
 
-	if (tgt_prog) {
+	if (tgt_prog)
 		return tgt_prog->aux->btf;
-	} else {
-		return btf_vmlinux;
-	}
+	else
+		return prog->aux->attach_btf;
 }
 
 static bool is_string_ptr(struct btf *btf, const struct btf_type *t)
@@ -4700,6 +4704,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 
 		if (ctx_arg_info->offset == off) {
 			info->reg_type = ctx_arg_info->reg_type;
+			info->btf = btf_vmlinux;
 			info->btf_id = ctx_arg_info->btf_id;
 			return true;
 		}
@@ -4716,6 +4721,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 
 		ret = btf_translate_to_vmlinux(log, btf, t, tgt_type, arg);
 		if (ret > 0) {
+			info->btf = btf_vmlinux;
 			info->btf_id = ret;
 			return true;
 		} else {
@@ -4723,6 +4729,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 		}
 	}
 
+	info->btf = btf;
 	info->btf_id = t->type;
 	t = btf_type_by_id(btf, t->type);
 	/* skip modifiers */
@@ -4749,7 +4756,7 @@ enum bpf_struct_walk_result {
 	WALK_STRUCT,
 };
 
-static int btf_struct_walk(struct bpf_verifier_log *log,
+static int btf_struct_walk(struct bpf_verifier_log *log, const struct btf *btf,
 			   const struct btf_type *t, int off, int size,
 			   u32 *next_btf_id)
 {
@@ -4760,7 +4767,7 @@ static int btf_struct_walk(struct bpf_verifier_log *log,
 	u32 vlen, elem_id, mid;
 
 again:
-	tname = __btf_name_by_offset(btf_vmlinux, t->name_off);
+	tname = __btf_name_by_offset(btf, t->name_off);
 	if (!btf_type_is_struct(t)) {
 		bpf_log(log, "Type '%s' is not a struct\n", tname);
 		return -EINVAL;
@@ -4777,7 +4784,7 @@ again:
 			goto error;
 
 		member = btf_type_member(t) + vlen - 1;
-		mtype = btf_type_skip_modifiers(btf_vmlinux, member->type,
+		mtype = btf_type_skip_modifiers(btf, member->type,
 						NULL);
 		if (!btf_type_is_array(mtype))
 			goto error;
@@ -4793,7 +4800,7 @@ again:
 		/* Only allow structure for now, can be relaxed for
 		 * other types later.
 		 */
-		t = btf_type_skip_modifiers(btf_vmlinux, array_elem->type,
+		t = btf_type_skip_modifiers(btf, array_elem->type,
 					    NULL);
 		if (!btf_type_is_struct(t))
 			goto error;
@@ -4851,10 +4858,10 @@ error:
 
 		/* type of the field */
 		mid = member->type;
-		mtype = btf_type_by_id(btf_vmlinux, member->type);
-		mname = __btf_name_by_offset(btf_vmlinux, member->name_off);
+		mtype = btf_type_by_id(btf, member->type);
+		mname = __btf_name_by_offset(btf, member->name_off);
 
-		mtype = __btf_resolve_size(btf_vmlinux, mtype, &msize,
+		mtype = __btf_resolve_size(btf, mtype, &msize,
 					   &elem_type, &elem_id, &total_nelems,
 					   &mid);
 		if (IS_ERR(mtype)) {
@@ -4949,7 +4956,7 @@ error:
 					mname, moff, tname, off, size);
 				return -EACCES;
 			}
-			stype = btf_type_skip_modifiers(btf_vmlinux, mtype->type, &id);
+			stype = btf_type_skip_modifiers(btf, mtype->type, &id);
 			if (btf_type_is_struct(stype)) {
 				*next_btf_id = id;
 				return WALK_PTR;
@@ -4975,7 +4982,7 @@ error:
 	return -EINVAL;
 }
 
-int btf_struct_access(struct bpf_verifier_log *log,
+int btf_struct_access(struct bpf_verifier_log *log, const struct btf *btf,
 		      const struct btf_type *t, int off, int size,
 		      enum bpf_access_type atype __maybe_unused,
 		      u32 *next_btf_id)
@@ -4984,7 +4991,7 @@ int btf_struct_access(struct bpf_verifier_log *log,
 	u32 id;
 
 	do {
-		err = btf_struct_walk(log, t, off, size, &id);
+		err = btf_struct_walk(log, btf, t, off, size, &id);
 
 		switch (err) {
 		case WALK_PTR:
@@ -5000,7 +5007,7 @@ int btf_struct_access(struct bpf_verifier_log *log,
 			 * by diving in it. At this point the offset is
 			 * aligned with the new type, so set it to 0.
 			 */
-			t = btf_type_by_id(btf_vmlinux, id);
+			t = btf_type_by_id(btf, id);
 			off = 0;
 			break;
 		default:
@@ -5016,21 +5023,37 @@ int btf_struct_access(struct bpf_verifier_log *log,
 	return -EINVAL;
 }
 
+/* Check that two BTF types, each specified as an BTF object + id, are exactly
+ * the same. Trivial ID check is not enough due to module BTFs, because we can
+ * end up with two different module BTFs, but IDs point to the common type in
+ * vmlinux BTF.
+ */
+static bool btf_types_are_same(const struct btf *btf1, u32 id1,
+			       const struct btf *btf2, u32 id2)
+{
+	if (id1 != id2)
+		return false;
+	if (btf1 == btf2)
+		return true;
+	return btf_type_by_id(btf1, id1) == btf_type_by_id(btf2, id2);
+}
+
 bool btf_struct_ids_match(struct bpf_verifier_log *log,
-			  int off, u32 id, u32 need_type_id)
+			  const struct btf *btf, u32 id, int off,
+			  const struct btf *need_btf, u32 need_type_id)
 {
 	const struct btf_type *type;
 	int err;
 
 	/* Are we already done? */
-	if (need_type_id == id && off == 0)
+	if (off == 0 && btf_types_are_same(btf, id, need_btf, need_type_id))
 		return true;
 
 again:
-	type = btf_type_by_id(btf_vmlinux, id);
+	type = btf_type_by_id(btf, id);
 	if (!type)
 		return false;
-	err = btf_struct_walk(log, type, off, 1, &id);
+	err = btf_struct_walk(log, btf, type, off, 1, &id);
 	if (err != WALK_STRUCT)
 		return false;
 
@@ -5039,7 +5062,7 @@ again:
 	 * continue the search with offset 0 in the new
 	 * type.
 	 */
-	if (need_type_id != id) {
+	if (!btf_types_are_same(btf, id, need_btf, need_type_id)) {
 		off = 0;
 		goto again;
 	}
@@ -5710,7 +5733,7 @@ int btf_get_fd_by_id(u32 id)
 	return fd;
 }
 
-u32 btf_id(const struct btf *btf)
+u32 btf_obj_id(const struct btf *btf)
 {
 	return btf->id;
 }
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index d16dd4945100..184204169949 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1691,6 +1691,8 @@ static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred)
 	bpf_prog_kallsyms_del_all(prog);
 	btf_put(prog->aux->btf);
 	bpf_prog_free_linfo(prog);
+	if (prog->aux->attach_btf)
+		btf_put(prog->aux->attach_btf);
 
 	if (deferred) {
 		if (prog->aux->sleepable)
@@ -2113,6 +2115,20 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 
 	prog->expected_attach_type = attr->expected_attach_type;
 	prog->aux->attach_btf_id = attr->attach_btf_id;
+
+	if (attr->attach_btf_id && !attr->attach_prog_fd) {
+		struct btf *btf;
+
+		btf = bpf_get_btf_vmlinux();
+		if (IS_ERR(btf))
+			return PTR_ERR(btf);
+		if (!btf)
+			return -EINVAL;
+
+		btf_get(btf);
+		prog->aux->attach_btf = btf;
+	}
+
 	if (attr->attach_prog_fd) {
 		struct bpf_prog *dst_prog;
 
@@ -2209,6 +2225,8 @@ free_prog_sec:
 	free_uid(prog->aux->user);
 	security_bpf_prog_free(prog->aux);
 free_prog:
+	if (prog->aux->attach_btf)
+		btf_put(prog->aux->attach_btf);
 	bpf_prog_free(prog);
 	return err;
 }
@@ -2566,7 +2584,7 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog,
 			goto out_put_prog;
 		}
 
-		key = bpf_trampoline_compute_key(tgt_prog, btf_id);
+		key = bpf_trampoline_compute_key(tgt_prog, NULL, btf_id);
 	}
 
 	link = kzalloc(sizeof(*link), GFP_USER);
@@ -3543,7 +3561,7 @@ static int bpf_prog_get_info_by_fd(struct file *file,
 	}
 
 	if (prog->aux->btf)
-		info.btf_id = btf_id(prog->aux->btf);
+		info.btf_id = btf_obj_id(prog->aux->btf);
 
 	ulen = info.nr_func_info;
 	info.nr_func_info = prog->aux->func_info_cnt;
@@ -3646,7 +3664,7 @@ static int bpf_map_get_info_by_fd(struct file *file,
 	memcpy(info.name, map->name, sizeof(map->name));
 
 	if (map->btf) {
-		info.btf_id = btf_id(map->btf);
+		info.btf_id = btf_obj_id(map->btf);
 		info.btf_key_type_id = map->btf_key_type_id;
 		info.btf_value_type_id = map->btf_value_type_id;
 	}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index e333ce43f281..2f3950839b85 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -238,7 +238,9 @@ struct bpf_call_arg_meta {
 	u64 msize_max_value;
 	int ref_obj_id;
 	int func_id;
+	struct btf *btf;
 	u32 btf_id;
+	struct btf *ret_btf;
 	u32 ret_btf_id;
 };
 
@@ -556,10 +558,9 @@ static struct bpf_func_state *func(struct bpf_verifier_env *env,
 	return cur->frame[reg->frameno];
 }
 
-const char *kernel_type_name(u32 id)
+static const char *kernel_type_name(const struct btf* btf, u32 id)
 {
-	return btf_name_by_offset(btf_vmlinux,
-				  btf_type_by_id(btf_vmlinux, id)->name_off);
+	return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off);
 }
 
 static void print_verifier_state(struct bpf_verifier_env *env,
@@ -589,7 +590,7 @@ static void print_verifier_state(struct bpf_verifier_env *env,
 			if (t == PTR_TO_BTF_ID ||
 			    t == PTR_TO_BTF_ID_OR_NULL ||
 			    t == PTR_TO_PERCPU_BTF_ID)
-				verbose(env, "%s", kernel_type_name(reg->btf_id));
+				verbose(env, "%s", kernel_type_name(reg->btf, reg->btf_id));
 			verbose(env, "(id=%d", reg->id);
 			if (reg_type_may_be_refcounted_or_null(t))
 				verbose(env, ",ref_obj_id=%d", reg->ref_obj_id);
@@ -1383,7 +1384,8 @@ static void mark_reg_not_init(struct bpf_verifier_env *env,
 
 static void mark_btf_ld_reg(struct bpf_verifier_env *env,
 			    struct bpf_reg_state *regs, u32 regno,
-			    enum bpf_reg_type reg_type, u32 btf_id)
+			    enum bpf_reg_type reg_type,
+			    struct btf *btf, u32 btf_id)
 {
 	if (reg_type == SCALAR_VALUE) {
 		mark_reg_unknown(env, regs, regno);
@@ -1391,6 +1393,7 @@ static void mark_btf_ld_reg(struct bpf_verifier_env *env,
 	}
 	mark_reg_known_zero(env, regs, regno);
 	regs[regno].type = PTR_TO_BTF_ID;
+	regs[regno].btf = btf;
 	regs[regno].btf_id = btf_id;
 }
 
@@ -2764,7 +2767,7 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off,
 /* check access to 'struct bpf_context' fields.  Supports fixed offsets only */
 static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, int size,
 			    enum bpf_access_type t, enum bpf_reg_type *reg_type,
-			    u32 *btf_id)
+			    struct btf **btf, u32 *btf_id)
 {
 	struct bpf_insn_access_aux info = {
 		.reg_type = *reg_type,
@@ -2782,10 +2785,12 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off,
 		 */
 		*reg_type = info.reg_type;
 
-		if (*reg_type == PTR_TO_BTF_ID || *reg_type == PTR_TO_BTF_ID_OR_NULL)
+		if (*reg_type == PTR_TO_BTF_ID || *reg_type == PTR_TO_BTF_ID_OR_NULL) {
+			*btf = info.btf;
 			*btf_id = info.btf_id;
-		else
+		} else {
 			env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size;
+		}
 		/* remember the offset of last byte accessed in ctx */
 		if (env->prog->aux->max_ctx_offset < off + size)
 			env->prog->aux->max_ctx_offset = off + size;
@@ -3297,8 +3302,8 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
 				   int value_regno)
 {
 	struct bpf_reg_state *reg = regs + regno;
-	const struct btf_type *t = btf_type_by_id(btf_vmlinux, reg->btf_id);
-	const char *tname = btf_name_by_offset(btf_vmlinux, t->name_off);
+	const struct btf_type *t = btf_type_by_id(reg->btf, reg->btf_id);
+	const char *tname = btf_name_by_offset(reg->btf, t->name_off);
 	u32 btf_id;
 	int ret;
 
@@ -3319,23 +3324,23 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
 	}
 
 	if (env->ops->btf_struct_access) {
-		ret = env->ops->btf_struct_access(&env->log, t, off, size,
-						  atype, &btf_id);
+		ret = env->ops->btf_struct_access(&env->log, reg->btf, t,
+						  off, size, atype, &btf_id);
 	} else {
 		if (atype != BPF_READ) {
 			verbose(env, "only read is supported\n");
 			return -EACCES;
 		}
 
-		ret = btf_struct_access(&env->log, t, off, size, atype,
-					&btf_id);
+		ret = btf_struct_access(&env->log, reg->btf, t, off, size,
+					atype, &btf_id);
 	}
 
 	if (ret < 0)
 		return ret;
 
 	if (atype == BPF_READ && value_regno >= 0)
-		mark_btf_ld_reg(env, regs, value_regno, ret, btf_id);
+		mark_btf_ld_reg(env, regs, value_regno, ret, reg->btf, btf_id);
 
 	return 0;
 }
@@ -3385,12 +3390,12 @@ static int check_ptr_to_map_access(struct bpf_verifier_env *env,
 		return -EACCES;
 	}
 
-	ret = btf_struct_access(&env->log, t, off, size, atype, &btf_id);
+	ret = btf_struct_access(&env->log, btf_vmlinux, t, off, size, atype, &btf_id);
 	if (ret < 0)
 		return ret;
 
 	if (value_regno >= 0)
-		mark_btf_ld_reg(env, regs, value_regno, ret, btf_id);
+		mark_btf_ld_reg(env, regs, value_regno, ret, btf_vmlinux, btf_id);
 
 	return 0;
 }
@@ -3466,6 +3471,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 			mark_reg_unknown(env, regs, value_regno);
 	} else if (reg->type == PTR_TO_CTX) {
 		enum bpf_reg_type reg_type = SCALAR_VALUE;
+		struct btf *btf = NULL;
 		u32 btf_id = 0;
 
 		if (t == BPF_WRITE && value_regno >= 0 &&
@@ -3478,7 +3484,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 		if (err < 0)
 			return err;
 
-		err = check_ctx_access(env, insn_idx, off, size, t, &reg_type, &btf_id);
+		err = check_ctx_access(env, insn_idx, off, size, t, &reg_type, &btf, &btf_id);
 		if (err)
 			verbose_linfo(env, insn_idx, "; ");
 		if (!err && t == BPF_READ && value_regno >= 0) {
@@ -3500,8 +3506,10 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 				 */
 				regs[value_regno].subreg_def = DEF_NOT_SUBREG;
 				if (reg_type == PTR_TO_BTF_ID ||
-				    reg_type == PTR_TO_BTF_ID_OR_NULL)
+				    reg_type == PTR_TO_BTF_ID_OR_NULL) {
+					regs[value_regno].btf = btf;
 					regs[value_regno].btf_id = btf_id;
+				}
 			}
 			regs[value_regno].type = reg_type;
 		}
@@ -4118,11 +4126,11 @@ found:
 			arg_btf_id = compatible->btf_id;
 		}
 
-		if (!btf_struct_ids_match(&env->log, reg->off, reg->btf_id,
-					  *arg_btf_id)) {
+		if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, reg->off,
+					  btf_vmlinux, *arg_btf_id)) {
 			verbose(env, "R%d is of type %s but %s is expected\n",
-				regno, kernel_type_name(reg->btf_id),
-				kernel_type_name(*arg_btf_id));
+				regno, kernel_type_name(reg->btf, reg->btf_id),
+				kernel_type_name(btf_vmlinux, *arg_btf_id));
 			return -EACCES;
 		}
 
@@ -4244,6 +4252,7 @@ skip_type_check:
 			verbose(env, "Helper has invalid btf_id in R%d\n", regno);
 			return -EACCES;
 		}
+		meta->ret_btf = reg->btf;
 		meta->ret_btf_id = reg->btf_id;
 	} else if (arg_type == ARG_PTR_TO_SPIN_LOCK) {
 		if (meta->func_id == BPF_FUNC_spin_lock) {
@@ -5190,16 +5199,16 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 		const struct btf_type *t;
 
 		mark_reg_known_zero(env, regs, BPF_REG_0);
-		t = btf_type_skip_modifiers(btf_vmlinux, meta.ret_btf_id, NULL);
+		t = btf_type_skip_modifiers(meta.ret_btf, meta.ret_btf_id, NULL);
 		if (!btf_type_is_struct(t)) {
 			u32 tsize;
 			const struct btf_type *ret;
 			const char *tname;
 
 			/* resolve the type size of ksym. */
-			ret = btf_resolve_size(btf_vmlinux, t, &tsize);
+			ret = btf_resolve_size(meta.ret_btf, t, &tsize);
 			if (IS_ERR(ret)) {
-				tname = btf_name_by_offset(btf_vmlinux, t->name_off);
+				tname = btf_name_by_offset(meta.ret_btf, t->name_off);
 				verbose(env, "unable to resolve the size of type '%s': %ld\n",
 					tname, PTR_ERR(ret));
 				return -EINVAL;
@@ -5212,6 +5221,7 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 			regs[BPF_REG_0].type =
 				fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID ?
 				PTR_TO_BTF_ID : PTR_TO_BTF_ID_OR_NULL;
+			regs[BPF_REG_0].btf = meta.ret_btf;
 			regs[BPF_REG_0].btf_id = meta.ret_btf_id;
 		}
 	} else if (fn->ret_type == RET_PTR_TO_BTF_ID_OR_NULL ||
@@ -5228,6 +5238,10 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 				fn->ret_type, func_id_name(func_id), func_id);
 			return -EINVAL;
 		}
+		/* current BPF helper definitions are only coming from
+		 * built-in code with type IDs from  vmlinux BTF
+		 */
+		regs[BPF_REG_0].btf = btf_vmlinux;
 		regs[BPF_REG_0].btf_id = ret_btf_id;
 	} else {
 		verbose(env, "unknown return type %d of func %s#%d\n",
@@ -5627,7 +5641,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 		if (reg_is_pkt_pointer(ptr_reg)) {
 			dst_reg->id = ++env->id_gen;
 			/* something was added to pkt_ptr, set range to zero */
-			dst_reg->raw = 0;
+			memset(&dst_reg->raw, 0, sizeof(dst_reg->raw));
 		}
 		break;
 	case BPF_SUB:
@@ -5692,7 +5706,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 			dst_reg->id = ++env->id_gen;
 			/* something was added to pkt_ptr, set range to zero */
 			if (smin_val < 0)
-				dst_reg->raw = 0;
+				memset(&dst_reg->raw, 0, sizeof(dst_reg->raw));
 		}
 		break;
 	case BPF_AND:
@@ -7744,6 +7758,7 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
 			break;
 		case PTR_TO_BTF_ID:
 		case PTR_TO_PERCPU_BTF_ID:
+			dst_reg->btf = aux->btf_var.btf;
 			dst_reg->btf_id = aux->btf_var.btf_id;
 			break;
 		default:
@@ -9739,6 +9754,7 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env,
 	t = btf_type_skip_modifiers(btf_vmlinux, type, NULL);
 	if (percpu) {
 		aux->btf_var.reg_type = PTR_TO_PERCPU_BTF_ID;
+		aux->btf_var.btf = btf_vmlinux;
 		aux->btf_var.btf_id = type;
 	} else if (!btf_type_is_struct(t)) {
 		const struct btf_type *ret;
@@ -9757,6 +9773,7 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env,
 		aux->btf_var.mem_size = tsize;
 	} else {
 		aux->btf_var.reg_type = PTR_TO_BTF_ID;
+		aux->btf_var.btf = btf_vmlinux;
 		aux->btf_var.btf_id = type;
 	}
 	return 0;
@@ -11609,7 +11626,7 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
 		bpf_log(log, "Tracing programs must provide btf_id\n");
 		return -EINVAL;
 	}
-	btf = tgt_prog ? tgt_prog->aux->btf : btf_vmlinux;
+	btf = tgt_prog ? tgt_prog->aux->btf : prog->aux->attach_btf;
 	if (!btf) {
 		bpf_log(log,
 			"FENTRY/FEXIT program can only be attached to another program annotated with BTF\n");
@@ -11885,7 +11902,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 			return ret;
 	}
 
-	key = bpf_trampoline_compute_key(tgt_prog, btf_id);
+	key = bpf_trampoline_compute_key(tgt_prog, prog->aux->attach_btf, btf_id);
 	tr = bpf_trampoline_get(key, &tgt_info);
 	if (!tr)
 		return -ENOMEM;
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index 618954f82764..d520e61649c8 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -95,6 +95,7 @@ static bool bpf_tcp_ca_is_valid_access(int off, int size,
 }
 
 static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log,
+					const struct btf *btf,
 					const struct btf_type *t, int off,
 					int size, enum bpf_access_type atype,
 					u32 *next_btf_id)
@@ -102,7 +103,7 @@ static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log,
 	size_t end;
 
 	if (atype == BPF_READ)
-		return btf_struct_access(log, t, off, size, atype, next_btf_id);
+		return btf_struct_access(log, btf, t, off, size, atype, next_btf_id);
 
 	if (t != tcp_sock_type) {
 		bpf_log(log, "only read is supported\n");
-- 
cgit v1.2.3


From 290248a5b7d829871b3ea3c62578613a580a1744 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Thu, 3 Dec 2020 12:46:30 -0800
Subject: bpf: Allow to specify kernel module BTFs when attaching BPF programs

Add ability for user-space programs to specify non-vmlinux BTF when attaching
BTF-powered BPF programs: raw_tp, fentry/fexit/fmod_ret, LSM, etc. For this,
attach_prog_fd (now with the alias name attach_btf_obj_fd) should specify FD
of a module or vmlinux BTF object. For backwards compatibility reasons,
0 denotes vmlinux BTF. Only kernel BTF (vmlinux or module) can be specified.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20201203204634.1325171-11-andrii@kernel.org
---
 include/linux/btf.h            |  1 +
 include/uapi/linux/bpf.h       |  7 +++-
 kernel/bpf/btf.c               |  5 +++
 kernel/bpf/syscall.c           | 82 ++++++++++++++++++++++++++----------------
 tools/include/uapi/linux/bpf.h |  7 +++-
 5 files changed, 69 insertions(+), 33 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/btf.h b/include/linux/btf.h
index fb608e4de076..4c200f5d242b 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -90,6 +90,7 @@ int btf_type_snprintf_show(const struct btf *btf, u32 type_id, void *obj,
 
 int btf_get_fd_by_id(u32 id);
 u32 btf_obj_id(const struct btf *btf);
+bool btf_is_kernel(const struct btf *btf);
 bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
 			   const struct btf_member *m,
 			   u32 expected_offset, u32 expected_size);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index c3458ec1f30a..1233f14f659f 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -557,7 +557,12 @@ union bpf_attr {
 		__aligned_u64	line_info;	/* line info */
 		__u32		line_info_cnt;	/* number of bpf_line_info records */
 		__u32		attach_btf_id;	/* in-kernel BTF type id to attach to */
-		__u32		attach_prog_fd; /* 0 to attach to vmlinux */
+		union {
+			/* valid prog_fd to attach to bpf prog */
+			__u32		attach_prog_fd;
+			/* or valid module BTF object fd or 0 to attach to vmlinux */
+			__u32		attach_btf_obj_fd;
+		};
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 7a19bf5bfe97..8d6bdb4f4d61 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -5738,6 +5738,11 @@ u32 btf_obj_id(const struct btf *btf)
 	return btf->id;
 }
 
+bool btf_is_kernel(const struct btf *btf)
+{
+	return btf->kernel_btf;
+}
+
 static int btf_id_cmp_func(const void *a, const void *b)
 {
 	const int *pa = a, *pb = b;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 184204169949..0cd3cc2af9c1 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1926,12 +1926,16 @@ static void bpf_prog_load_fixup_attach_type(union bpf_attr *attr)
 static int
 bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
 			   enum bpf_attach_type expected_attach_type,
-			   u32 btf_id, u32 prog_fd)
+			   struct btf *attach_btf, u32 btf_id,
+			   struct bpf_prog *dst_prog)
 {
 	if (btf_id) {
 		if (btf_id > BTF_MAX_TYPE)
 			return -EINVAL;
 
+		if (!attach_btf && !dst_prog)
+			return -EINVAL;
+
 		switch (prog_type) {
 		case BPF_PROG_TYPE_TRACING:
 		case BPF_PROG_TYPE_LSM:
@@ -1943,7 +1947,10 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
 		}
 	}
 
-	if (prog_fd && prog_type != BPF_PROG_TYPE_TRACING &&
+	if (attach_btf && (!btf_id || dst_prog))
+		return -EINVAL;
+
+	if (dst_prog && prog_type != BPF_PROG_TYPE_TRACING &&
 	    prog_type != BPF_PROG_TYPE_EXT)
 		return -EINVAL;
 
@@ -2060,7 +2067,8 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type)
 static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 {
 	enum bpf_prog_type type = attr->prog_type;
-	struct bpf_prog *prog;
+	struct bpf_prog *prog, *dst_prog = NULL;
+	struct btf *attach_btf = NULL;
 	int err;
 	char license[128];
 	bool is_gpl;
@@ -2102,44 +2110,56 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 	if (is_perfmon_prog_type(type) && !perfmon_capable())
 		return -EPERM;
 
+	/* attach_prog_fd/attach_btf_obj_fd can specify fd of either bpf_prog
+	 * or btf, we need to check which one it is
+	 */
+	if (attr->attach_prog_fd) {
+		dst_prog = bpf_prog_get(attr->attach_prog_fd);
+		if (IS_ERR(dst_prog)) {
+			dst_prog = NULL;
+			attach_btf = btf_get_by_fd(attr->attach_btf_obj_fd);
+			if (IS_ERR(attach_btf))
+				return -EINVAL;
+			if (!btf_is_kernel(attach_btf)) {
+				btf_put(attach_btf);
+				return -EINVAL;
+			}
+		}
+	} else if (attr->attach_btf_id) {
+		/* fall back to vmlinux BTF, if BTF type ID is specified */
+		attach_btf = bpf_get_btf_vmlinux();
+		if (IS_ERR(attach_btf))
+			return PTR_ERR(attach_btf);
+		if (!attach_btf)
+			return -EINVAL;
+		btf_get(attach_btf);
+	}
+
 	bpf_prog_load_fixup_attach_type(attr);
 	if (bpf_prog_load_check_attach(type, attr->expected_attach_type,
-				       attr->attach_btf_id,
-				       attr->attach_prog_fd))
+				       attach_btf, attr->attach_btf_id,
+				       dst_prog)) {
+		if (dst_prog)
+			bpf_prog_put(dst_prog);
+		if (attach_btf)
+			btf_put(attach_btf);
 		return -EINVAL;
+	}
 
 	/* plain bpf_prog allocation */
 	prog = bpf_prog_alloc(bpf_prog_size(attr->insn_cnt), GFP_USER);
-	if (!prog)
+	if (!prog) {
+		if (dst_prog)
+			bpf_prog_put(dst_prog);
+		if (attach_btf)
+			btf_put(attach_btf);
 		return -ENOMEM;
+	}
 
 	prog->expected_attach_type = attr->expected_attach_type;
+	prog->aux->attach_btf = attach_btf;
 	prog->aux->attach_btf_id = attr->attach_btf_id;
-
-	if (attr->attach_btf_id && !attr->attach_prog_fd) {
-		struct btf *btf;
-
-		btf = bpf_get_btf_vmlinux();
-		if (IS_ERR(btf))
-			return PTR_ERR(btf);
-		if (!btf)
-			return -EINVAL;
-
-		btf_get(btf);
-		prog->aux->attach_btf = btf;
-	}
-
-	if (attr->attach_prog_fd) {
-		struct bpf_prog *dst_prog;
-
-		dst_prog = bpf_prog_get(attr->attach_prog_fd);
-		if (IS_ERR(dst_prog)) {
-			err = PTR_ERR(dst_prog);
-			goto free_prog;
-		}
-		prog->aux->dst_prog = dst_prog;
-	}
-
+	prog->aux->dst_prog = dst_prog;
 	prog->aux->offload_requested = !!attr->prog_ifindex;
 	prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE;
 
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index c3458ec1f30a..1233f14f659f 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -557,7 +557,12 @@ union bpf_attr {
 		__aligned_u64	line_info;	/* line info */
 		__u32		line_info_cnt;	/* number of bpf_line_info records */
 		__u32		attach_btf_id;	/* in-kernel BTF type id to attach to */
-		__u32		attach_prog_fd; /* 0 to attach to vmlinux */
+		union {
+			/* valid prog_fd to attach to bpf prog */
+			__u32		attach_prog_fd;
+			/* or valid module BTF object fd or 0 to attach to vmlinux */
+			__u32		attach_btf_obj_fd;
+		};
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
-- 
cgit v1.2.3


From 6df3e14436f6ee254b1a4952d90ee8988be59c89 Mon Sep 17 00:00:00 2001
From: David Brazdil <dbrazdil@google.com>
Date: Wed, 2 Dec 2020 18:41:02 +0000
Subject: psci: Add accessor for psci_0_1_function_ids

Make it possible to retrieve a copy of the psci_0_1_function_ids struct.
This is useful for KVM if it is configured to intercept host's PSCI SMCs.

Signed-off-by: David Brazdil <dbrazdil@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Link: https://lore.kernel.org/r/20201202184122.26046-7-dbrazdil@google.com
---
 drivers/firmware/psci/psci.c | 12 +++++-------
 include/linux/psci.h         |  9 +++++++++
 2 files changed, 14 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/psci/psci.c b/drivers/firmware/psci/psci.c
index 593fdd0e09a2..f5fc429cae3f 100644
--- a/drivers/firmware/psci/psci.c
+++ b/drivers/firmware/psci/psci.c
@@ -58,15 +58,13 @@ typedef unsigned long (psci_fn)(unsigned long, unsigned long,
 				unsigned long, unsigned long);
 static psci_fn *invoke_psci_fn;
 
-struct psci_0_1_function_ids {
-	u32 cpu_suspend;
-	u32 cpu_on;
-	u32 cpu_off;
-	u32 migrate;
-};
-
 static struct psci_0_1_function_ids psci_0_1_function_ids;
 
+struct psci_0_1_function_ids get_psci_0_1_function_ids(void)
+{
+	return psci_0_1_function_ids;
+}
+
 #define PSCI_0_2_POWER_STATE_MASK		\
 				(PSCI_0_2_POWER_STATE_ID_MASK | \
 				PSCI_0_2_POWER_STATE_TYPE_MASK | \
diff --git a/include/linux/psci.h b/include/linux/psci.h
index 2a1bfb890e58..4ca0060a3fc4 100644
--- a/include/linux/psci.h
+++ b/include/linux/psci.h
@@ -34,6 +34,15 @@ struct psci_operations {
 
 extern struct psci_operations psci_ops;
 
+struct psci_0_1_function_ids {
+	u32 cpu_suspend;
+	u32 cpu_on;
+	u32 cpu_off;
+	u32 migrate;
+};
+
+struct psci_0_1_function_ids get_psci_0_1_function_ids(void);
+
 #if defined(CONFIG_ARM_PSCI_FW)
 int __init psci_dt_init(void);
 #else
-- 
cgit v1.2.3


From 7de3697e9cbd4bd3d62bafa249d57990e1b8f294 Mon Sep 17 00:00:00 2001
From: Dave Ertman <david.m.ertman@intel.com>
Date: Wed, 2 Dec 2020 16:54:24 -0800
Subject: Add auxiliary bus support

Add support for the Auxiliary Bus, auxiliary_device and auxiliary_driver.
It enables drivers to create an auxiliary_device and bind an
auxiliary_driver to it.

The bus supports probe/remove shutdown and suspend/resume callbacks.
Each auxiliary_device has a unique string based id; driver binds to
an auxiliary_device based on this id through the bus.

Co-developed-by: Kiran Patil <kiran.patil@intel.com>
Co-developed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Co-developed-by: Fred Oh <fred.oh@linux.intel.com>
Co-developed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Kiran Patil <kiran.patil@intel.com>
Signed-off-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Signed-off-by: Fred Oh <fred.oh@linux.intel.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Dave Ertman <david.m.ertman@intel.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Shiraz Saleem <shiraz.saleem@intel.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Martin Habets <mhabets@solarflare.com>
Link: https://lore.kernel.org/r/20201113161859.1775473-2-david.m.ertman@intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Link: https://lore.kernel.org/r/160695681289.505290.8978295443574440604.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/driver-api/auxiliary_bus.rst | 234 +++++++++++++++++++++++++
 Documentation/driver-api/index.rst         |   1 +
 drivers/base/Kconfig                       |   3 +
 drivers/base/Makefile                      |   1 +
 drivers/base/auxiliary.c                   | 268 +++++++++++++++++++++++++++++
 include/linux/auxiliary_bus.h              |  78 +++++++++
 include/linux/mod_devicetable.h            |   8 +
 scripts/mod/devicetable-offsets.c          |   3 +
 scripts/mod/file2alias.c                   |   8 +
 9 files changed, 604 insertions(+)
 create mode 100644 Documentation/driver-api/auxiliary_bus.rst
 create mode 100644 drivers/base/auxiliary.c
 create mode 100644 include/linux/auxiliary_bus.h

(limited to 'include/linux')

diff --git a/Documentation/driver-api/auxiliary_bus.rst b/Documentation/driver-api/auxiliary_bus.rst
new file mode 100644
index 000000000000..5dd7804631ef
--- /dev/null
+++ b/Documentation/driver-api/auxiliary_bus.rst
@@ -0,0 +1,234 @@
+.. SPDX-License-Identifier: GPL-2.0-only
+
+=============
+Auxiliary Bus
+=============
+
+In some subsystems, the functionality of the core device (PCI/ACPI/other) is
+too complex for a single device to be managed by a monolithic driver
+(e.g. Sound Open Firmware), multiple devices might implement a common
+intersection of functionality (e.g. NICs + RDMA), or a driver may want to
+export an interface for another subsystem to drive (e.g. SIOV Physical Function
+export Virtual Function management).  A split of the functinoality into child-
+devices representing sub-domains of functionality makes it possible to
+compartmentalize, layer, and distribute domain-specific concerns via a Linux
+device-driver model.
+
+An example for this kind of requirement is the audio subsystem where a single
+IP is handling multiple entities such as HDMI, Soundwire, local devices such as
+mics/speakers etc. The split for the core's functionality can be arbitrary or
+be defined by the DSP firmware topology and include hooks for test/debug. This
+allows for the audio core device to be minimal and focused on hardware-specific
+control and communication.
+
+Each auxiliary_device represents a part of its parent functionality. The
+generic behavior can be extended and specialized as needed by encapsulating an
+auxiliary_device within other domain-specific structures and the use of .ops
+callbacks. Devices on the auxiliary bus do not share any structures and the use
+of a communication channel with the parent is domain-specific.
+
+Note that ops are intended as a way to augment instance behavior within a class
+of auxiliary devices, it is not the mechanism for exporting common
+infrastructure from the parent. Consider EXPORT_SYMBOL_NS() to convey
+infrastructure from the parent module to the auxiliary module(s).
+
+
+When Should the Auxiliary Bus Be Used
+=====================================
+
+The auxiliary bus is to be used when a driver and one or more kernel modules,
+who share a common header file with the driver, need a mechanism to connect and
+provide access to a shared object allocated by the auxiliary_device's
+registering driver.  The registering driver for the auxiliary_device(s) and the
+kernel module(s) registering auxiliary_drivers can be from the same subsystem,
+or from multiple subsystems.
+
+The emphasis here is on a common generic interface that keeps subsystem
+customization out of the bus infrastructure.
+
+One example is a PCI network device that is RDMA-capable and exports a child
+device to be driven by an auxiliary_driver in the RDMA subsystem.  The PCI
+driver allocates and registers an auxiliary_device for each physical
+function on the NIC.  The RDMA driver registers an auxiliary_driver that claims
+each of these auxiliary_devices.  This conveys data/ops published by the parent
+PCI device/driver to the RDMA auxiliary_driver.
+
+Another use case is for the PCI device to be split out into multiple sub
+functions.  For each sub function an auxiliary_device is created.  A PCI sub
+function driver binds to such devices that creates its own one or more class
+devices.  A PCI sub function auxiliary device is likely to be contained in a
+struct with additional attributes such as user defined sub function number and
+optional attributes such as resources and a link to the parent device.  These
+attributes could be used by systemd/udev; and hence should be initialized
+before a driver binds to an auxiliary_device.
+
+A key requirement for utilizing the auxiliary bus is that there is no
+dependency on a physical bus, device, register accesses or regmap support.
+These individual devices split from the core cannot live on the platform bus as
+they are not physical devices that are controlled by DT/ACPI.  The same
+argument applies for not using MFD in this scenario as MFD relies on individual
+function devices being physical devices.
+
+Auxiliary Device
+================
+
+An auxiliary_device represents a part of its parent device's functionality. It
+is given a name that, combined with the registering drivers KBUILD_MODNAME,
+creates a match_name that is used for driver binding, and an id that combined
+with the match_name provide a unique name to register with the bus subsystem.
+
+Registering an auxiliary_device is a two-step process.  First call
+auxiliary_device_init(), which checks several aspects of the auxiliary_device
+struct and performs a device_initialize().  After this step completes, any
+error state must have a call to auxiliary_device_uninit() in its resolution path.
+The second step in registering an auxiliary_device is to perform a call to
+auxiliary_device_add(), which sets the name of the device and add the device to
+the bus.
+
+Unregistering an auxiliary_device is also a two-step process to mirror the
+register process.  First call auxiliary_device_delete(), then call
+auxiliary_device_uninit().
+
+.. code-block:: c
+
+	struct auxiliary_device {
+		struct device dev;
+                const char *name;
+		u32 id;
+	};
+
+If two auxiliary_devices both with a match_name "mod.foo" are registered onto
+the bus, they must have unique id values (e.g. "x" and "y") so that the
+registered devices names are "mod.foo.x" and "mod.foo.y".  If match_name + id
+are not unique, then the device_add fails and generates an error message.
+
+The auxiliary_device.dev.type.release or auxiliary_device.dev.release must be
+populated with a non-NULL pointer to successfully register the auxiliary_device.
+
+The auxiliary_device.dev.parent must also be populated.
+
+Auxiliary Device Memory Model and Lifespan
+------------------------------------------
+
+The registering driver is the entity that allocates memory for the
+auxiliary_device and register it on the auxiliary bus.  It is important to note
+that, as opposed to the platform bus, the registering driver is wholly
+responsible for the management for the memory used for the driver object.
+
+A parent object, defined in the shared header file, contains the
+auxiliary_device.  It also contains a pointer to the shared object(s), which
+also is defined in the shared header.  Both the parent object and the shared
+object(s) are allocated by the registering driver.  This layout allows the
+auxiliary_driver's registering module to perform a container_of() call to go
+from the pointer to the auxiliary_device, that is passed during the call to the
+auxiliary_driver's probe function, up to the parent object, and then have
+access to the shared object(s).
+
+The memory for the auxiliary_device is freed only in its release() callback
+flow as defined by its registering driver.
+
+The memory for the shared object(s) must have a lifespan equal to, or greater
+than, the lifespan of the memory for the auxiliary_device.  The auxiliary_driver
+should only consider that this shared object is valid as long as the
+auxiliary_device is still registered on the auxiliary bus.  It is up to the
+registering driver to manage (e.g. free or keep available) the memory for the
+shared object beyond the life of the auxiliary_device.
+
+The registering driver must unregister all auxiliary devices before its own
+driver.remove() is completed.
+
+Auxiliary Drivers
+=================
+
+Auxiliary drivers follow the standard driver model convention, where
+discovery/enumeration is handled by the core, and drivers
+provide probe() and remove() methods. They support power management
+and shutdown notifications using the standard conventions.
+
+.. code-block:: c
+
+	struct auxiliary_driver {
+		int (*probe)(struct auxiliary_device *,
+                             const struct auxiliary_device_id *id);
+		int (*remove)(struct auxiliary_device *);
+		void (*shutdown)(struct auxiliary_device *);
+		int (*suspend)(struct auxiliary_device *, pm_message_t);
+		int (*resume)(struct auxiliary_device *);
+		struct device_driver driver;
+		const struct auxiliary_device_id *id_table;
+	};
+
+Auxiliary drivers register themselves with the bus by calling
+auxiliary_driver_register(). The id_table contains the match_names of auxiliary
+devices that a driver can bind with.
+
+Example Usage
+=============
+
+Auxiliary devices are created and registered by a subsystem-level core device
+that needs to break up its functionality into smaller fragments. One way to
+extend the scope of an auxiliary_device is to encapsulate it within a domain-
+pecific structure defined by the parent device. This structure contains the
+auxiliary_device and any associated shared data/callbacks needed to establish
+the connection with the parent.
+
+An example is:
+
+.. code-block:: c
+
+        struct foo {
+		struct auxiliary_device auxdev;
+		void (*connect)(struct auxiliary_device *auxdev);
+		void (*disconnect)(struct auxiliary_device *auxdev);
+		void *data;
+        };
+
+The parent device then registers the auxiliary_device by calling
+auxiliary_device_init(), and then auxiliary_device_add(), with the pointer to
+the auxdev member of the above structure. The parent provides a name for the
+auxiliary_device that, combined with the parent's KBUILD_MODNAME, creates a
+match_name that is be used for matching and binding with a driver.
+
+Whenever an auxiliary_driver is registered, based on the match_name, the
+auxiliary_driver's probe() is invoked for the matching devices.  The
+auxiliary_driver can also be encapsulated inside custom drivers that make the
+core device's functionality extensible by adding additional domain-specific ops
+as follows:
+
+.. code-block:: c
+
+	struct my_ops {
+		void (*send)(struct auxiliary_device *auxdev);
+		void (*receive)(struct auxiliary_device *auxdev);
+	};
+
+
+	struct my_driver {
+		struct auxiliary_driver auxiliary_drv;
+		const struct my_ops ops;
+	};
+
+An example of this type of usage is:
+
+.. code-block:: c
+
+	const struct auxiliary_device_id my_auxiliary_id_table[] = {
+		{ .name = "foo_mod.foo_dev" },
+		{ },
+	};
+
+	const struct my_ops my_custom_ops = {
+		.send = my_tx,
+		.receive = my_rx,
+	};
+
+	const struct my_driver my_drv = {
+		.auxiliary_drv = {
+			.name = "myauxiliarydrv",
+			.id_table = my_auxiliary_id_table,
+			.probe = my_probe,
+			.remove = my_remove,
+			.shutdown = my_shutdown,
+		},
+		.ops = my_custom_ops,
+	};
diff --git a/Documentation/driver-api/index.rst b/Documentation/driver-api/index.rst
index f357f3eb400c..86759a74b7f1 100644
--- a/Documentation/driver-api/index.rst
+++ b/Documentation/driver-api/index.rst
@@ -72,6 +72,7 @@ available subsections can be seen below.
    thermal/index
    fpga/index
    acpi/index
+   auxiliary_bus
    backlight/lp855x-driver.rst
    connector
    console
diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig
index 8d7001712062..040be48ce046 100644
--- a/drivers/base/Kconfig
+++ b/drivers/base/Kconfig
@@ -1,6 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0
 menu "Generic Driver Options"
 
+config AUXILIARY_BUS
+	bool
+
 config UEVENT_HELPER
 	bool "Support for uevent helper"
 	help
diff --git a/drivers/base/Makefile b/drivers/base/Makefile
index 41369fc7004f..5e7bf9669a81 100644
--- a/drivers/base/Makefile
+++ b/drivers/base/Makefile
@@ -7,6 +7,7 @@ obj-y			:= component.o core.o bus.o dd.o syscore.o \
 			   attribute_container.o transport_class.o \
 			   topology.o container.o property.o cacheinfo.o \
 			   swnode.o
+obj-$(CONFIG_AUXILIARY_BUS) += auxiliary.o
 obj-$(CONFIG_DEVTMPFS)	+= devtmpfs.o
 obj-y			+= power/
 obj-$(CONFIG_ISA_BUS_API)	+= isa.o
diff --git a/drivers/base/auxiliary.c b/drivers/base/auxiliary.c
new file mode 100644
index 000000000000..ef2af417438b
--- /dev/null
+++ b/drivers/base/auxiliary.c
@@ -0,0 +1,268 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2019-2020 Intel Corporation
+ *
+ * Please see Documentation/driver-api/auxiliary_bus.rst for more information.
+ */
+
+#define pr_fmt(fmt) "%s:%s: " fmt, KBUILD_MODNAME, __func__
+
+#include <linux/device.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/pm_domain.h>
+#include <linux/pm_runtime.h>
+#include <linux/string.h>
+#include <linux/auxiliary_bus.h>
+
+static const struct auxiliary_device_id *auxiliary_match_id(const struct auxiliary_device_id *id,
+							    const struct auxiliary_device *auxdev)
+{
+	for (; id->name[0]; id++) {
+		const char *p = strrchr(dev_name(&auxdev->dev), '.');
+		int match_size;
+
+		if (!p)
+			continue;
+		match_size = p - dev_name(&auxdev->dev);
+
+		/* use dev_name(&auxdev->dev) prefix before last '.' char to match to */
+		if (strlen(id->name) == match_size &&
+		    !strncmp(dev_name(&auxdev->dev), id->name, match_size))
+			return id;
+	}
+	return NULL;
+}
+
+static int auxiliary_match(struct device *dev, struct device_driver *drv)
+{
+	struct auxiliary_device *auxdev = to_auxiliary_dev(dev);
+	struct auxiliary_driver *auxdrv = to_auxiliary_drv(drv);
+
+	return !!auxiliary_match_id(auxdrv->id_table, auxdev);
+}
+
+static int auxiliary_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+	const char *name, *p;
+
+	name = dev_name(dev);
+	p = strrchr(name, '.');
+
+	return add_uevent_var(env, "MODALIAS=%s%.*s", AUXILIARY_MODULE_PREFIX, (int)(p - name),
+			      name);
+}
+
+static const struct dev_pm_ops auxiliary_dev_pm_ops = {
+	SET_RUNTIME_PM_OPS(pm_generic_runtime_suspend, pm_generic_runtime_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_generic_suspend, pm_generic_resume)
+};
+
+static int auxiliary_bus_probe(struct device *dev)
+{
+	struct auxiliary_driver *auxdrv = to_auxiliary_drv(dev->driver);
+	struct auxiliary_device *auxdev = to_auxiliary_dev(dev);
+	int ret;
+
+	ret = dev_pm_domain_attach(dev, true);
+	if (ret) {
+		dev_warn(dev, "Failed to attach to PM Domain : %d\n", ret);
+		return ret;
+	}
+
+	ret = auxdrv->probe(auxdev, auxiliary_match_id(auxdrv->id_table, auxdev));
+	if (ret)
+		dev_pm_domain_detach(dev, true);
+
+	return ret;
+}
+
+static int auxiliary_bus_remove(struct device *dev)
+{
+	struct auxiliary_driver *auxdrv = to_auxiliary_drv(dev->driver);
+	struct auxiliary_device *auxdev = to_auxiliary_dev(dev);
+	int ret = 0;
+
+	if (auxdrv->remove)
+		ret = auxdrv->remove(auxdev);
+	dev_pm_domain_detach(dev, true);
+
+	return ret;
+}
+
+static void auxiliary_bus_shutdown(struct device *dev)
+{
+	struct auxiliary_driver *auxdrv = to_auxiliary_drv(dev->driver);
+	struct auxiliary_device *auxdev = to_auxiliary_dev(dev);
+
+	if (auxdrv->shutdown)
+		auxdrv->shutdown(auxdev);
+}
+
+static struct bus_type auxiliary_bus_type = {
+	.name = "auxiliary",
+	.probe = auxiliary_bus_probe,
+	.remove = auxiliary_bus_remove,
+	.shutdown = auxiliary_bus_shutdown,
+	.match = auxiliary_match,
+	.uevent = auxiliary_uevent,
+	.pm = &auxiliary_dev_pm_ops,
+};
+
+/**
+ * auxiliary_device_init - check auxiliary_device and initialize
+ * @auxdev: auxiliary device struct
+ *
+ * This is the first step in the two-step process to register an auxiliary_device.
+ *
+ * When this function returns an error code, then the device_initialize will *not* have
+ * been performed, and the caller will be responsible to free any memory allocated for the
+ * auxiliary_device in the error path directly.
+ *
+ * It returns 0 on success.  On success, the device_initialize has been performed.  After this
+ * point any error unwinding will need to include a call to auxiliary_device_uninit().
+ * In this post-initialize error scenario, a call to the device's .release callback will be
+ * triggered, and all memory clean-up is expected to be handled there.
+ */
+int auxiliary_device_init(struct auxiliary_device *auxdev)
+{
+	struct device *dev = &auxdev->dev;
+
+	if (!dev->parent) {
+		pr_err("auxiliary_device has a NULL dev->parent\n");
+		return -EINVAL;
+	}
+
+	if (!auxdev->name) {
+		pr_err("auxiliary_device has a NULL name\n");
+		return -EINVAL;
+	}
+
+	dev->bus = &auxiliary_bus_type;
+	device_initialize(&auxdev->dev);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(auxiliary_device_init);
+
+/**
+ * __auxiliary_device_add - add an auxiliary bus device
+ * @auxdev: auxiliary bus device to add to the bus
+ * @modname: name of the parent device's driver module
+ *
+ * This is the second step in the two-step process to register an auxiliary_device.
+ *
+ * This function must be called after a successful call to auxiliary_device_init(), which
+ * will perform the device_initialize.  This means that if this returns an error code, then a
+ * call to auxiliary_device_uninit() must be performed so that the .release callback will
+ * be triggered to free the memory associated with the auxiliary_device.
+ *
+ * The expectation is that users will call the "auxiliary_device_add" macro so that the caller's
+ * KBUILD_MODNAME is automatically inserted for the modname parameter.  Only if a user requires
+ * a custom name would this version be called directly.
+ */
+int __auxiliary_device_add(struct auxiliary_device *auxdev, const char *modname)
+{
+	struct device *dev = &auxdev->dev;
+	int ret;
+
+	if (!modname) {
+		pr_err("auxiliary device modname is NULL\n");
+		return -EINVAL;
+	}
+
+	ret = dev_set_name(dev, "%s.%s.%d", modname, auxdev->name, auxdev->id);
+	if (ret) {
+		pr_err("auxiliary device dev_set_name failed: %d\n", ret);
+		return ret;
+	}
+
+	ret = device_add(dev);
+	if (ret)
+		dev_err(dev, "adding auxiliary device failed!: %d\n", ret);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(__auxiliary_device_add);
+
+/**
+ * auxiliary_find_device - auxiliary device iterator for locating a particular device.
+ * @start: Device to begin with
+ * @data: Data to pass to match function
+ * @match: Callback function to check device
+ *
+ * This function returns a reference to a device that is 'found'
+ * for later use, as determined by the @match callback.
+ *
+ * The callback should return 0 if the device doesn't match and non-zero
+ * if it does.  If the callback returns non-zero, this function will
+ * return to the caller and not iterate over any more devices.
+ */
+struct auxiliary_device *
+auxiliary_find_device(struct device *start, const void *data,
+		      int (*match)(struct device *dev, const void *data))
+{
+	struct device *dev;
+
+	dev = bus_find_device(&auxiliary_bus_type, start, data, match);
+	if (!dev)
+		return NULL;
+
+	return to_auxiliary_dev(dev);
+}
+EXPORT_SYMBOL_GPL(auxiliary_find_device);
+
+/**
+ * __auxiliary_driver_register - register a driver for auxiliary bus devices
+ * @auxdrv: auxiliary_driver structure
+ * @owner: owning module/driver
+ * @modname: KBUILD_MODNAME for parent driver
+ */
+int __auxiliary_driver_register(struct auxiliary_driver *auxdrv, struct module *owner,
+				const char *modname)
+{
+	if (WARN_ON(!auxdrv->probe) || WARN_ON(!auxdrv->id_table))
+		return -EINVAL;
+
+	if (auxdrv->name)
+		auxdrv->driver.name = kasprintf(GFP_KERNEL, "%s.%s", modname, auxdrv->name);
+	else
+		auxdrv->driver.name = kasprintf(GFP_KERNEL, "%s", modname);
+	if (!auxdrv->driver.name)
+		return -ENOMEM;
+
+	auxdrv->driver.owner = owner;
+	auxdrv->driver.bus = &auxiliary_bus_type;
+	auxdrv->driver.mod_name = modname;
+
+	return driver_register(&auxdrv->driver);
+}
+EXPORT_SYMBOL_GPL(__auxiliary_driver_register);
+
+/**
+ * auxiliary_driver_unregister - unregister a driver
+ * @auxdrv: auxiliary_driver structure
+ */
+void auxiliary_driver_unregister(struct auxiliary_driver *auxdrv)
+{
+	driver_unregister(&auxdrv->driver);
+	kfree(auxdrv->driver.name);
+}
+EXPORT_SYMBOL_GPL(auxiliary_driver_unregister);
+
+static int __init auxiliary_bus_init(void)
+{
+	return bus_register(&auxiliary_bus_type);
+}
+
+static void __exit auxiliary_bus_exit(void)
+{
+	bus_unregister(&auxiliary_bus_type);
+}
+
+module_init(auxiliary_bus_init);
+module_exit(auxiliary_bus_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Auxiliary Bus");
+MODULE_AUTHOR("David Ertman <david.m.ertman@intel.com>");
+MODULE_AUTHOR("Kiran Patil <kiran.patil@intel.com>");
diff --git a/include/linux/auxiliary_bus.h b/include/linux/auxiliary_bus.h
new file mode 100644
index 000000000000..282fbf7bf9af
--- /dev/null
+++ b/include/linux/auxiliary_bus.h
@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2019-2020 Intel Corporation
+ *
+ * Please see Documentation/driver-api/auxiliary_bus.rst for more information.
+ */
+
+#ifndef _AUXILIARY_BUS_H_
+#define _AUXILIARY_BUS_H_
+
+#include <linux/device.h>
+#include <linux/mod_devicetable.h>
+#include <linux/slab.h>
+
+struct auxiliary_device {
+	struct device dev;
+	const char *name;
+	u32 id;
+};
+
+struct auxiliary_driver {
+	int (*probe)(struct auxiliary_device *auxdev, const struct auxiliary_device_id *id);
+	int (*remove)(struct auxiliary_device *auxdev);
+	void (*shutdown)(struct auxiliary_device *auxdev);
+	int (*suspend)(struct auxiliary_device *auxdev, pm_message_t state);
+	int (*resume)(struct auxiliary_device *auxdev);
+	const char *name;
+	struct device_driver driver;
+	const struct auxiliary_device_id *id_table;
+};
+
+static inline struct auxiliary_device *to_auxiliary_dev(struct device *dev)
+{
+	return container_of(dev, struct auxiliary_device, dev);
+}
+
+static inline struct auxiliary_driver *to_auxiliary_drv(struct device_driver *drv)
+{
+	return container_of(drv, struct auxiliary_driver, driver);
+}
+
+int auxiliary_device_init(struct auxiliary_device *auxdev);
+int __auxiliary_device_add(struct auxiliary_device *auxdev, const char *modname);
+#define auxiliary_device_add(auxdev) __auxiliary_device_add(auxdev, KBUILD_MODNAME)
+
+static inline void auxiliary_device_uninit(struct auxiliary_device *auxdev)
+{
+	put_device(&auxdev->dev);
+}
+
+static inline void auxiliary_device_delete(struct auxiliary_device *auxdev)
+{
+	device_del(&auxdev->dev);
+}
+
+int __auxiliary_driver_register(struct auxiliary_driver *auxdrv, struct module *owner,
+				const char *modname);
+#define auxiliary_driver_register(auxdrv) \
+	__auxiliary_driver_register(auxdrv, THIS_MODULE, KBUILD_MODNAME)
+
+void auxiliary_driver_unregister(struct auxiliary_driver *auxdrv);
+
+/**
+ * module_auxiliary_driver() - Helper macro for registering an auxiliary driver
+ * @__auxiliary_driver: auxiliary driver struct
+ *
+ * Helper macro for auxiliary drivers which do not do anything special in
+ * module init/exit. This eliminates a lot of boilerplate. Each module may only
+ * use this macro once, and calling it replaces module_init() and module_exit()
+ */
+#define module_auxiliary_driver(__auxiliary_driver) \
+	module_driver(__auxiliary_driver, auxiliary_driver_register, auxiliary_driver_unregister)
+
+struct auxiliary_device *
+auxiliary_find_device(struct device *start, const void *data,
+		      int (*match)(struct device *dev, const void *data));
+
+#endif /* _AUXILIARY_BUS_H_ */
diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index 5b08a473cdba..c425290b21e2 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -838,4 +838,12 @@ struct mhi_device_id {
 	kernel_ulong_t driver_data;
 };
 
+#define AUXILIARY_NAME_SIZE 32
+#define AUXILIARY_MODULE_PREFIX "auxiliary:"
+
+struct auxiliary_device_id {
+	char name[AUXILIARY_NAME_SIZE];
+	kernel_ulong_t driver_data;
+};
+
 #endif /* LINUX_MOD_DEVICETABLE_H */
diff --git a/scripts/mod/devicetable-offsets.c b/scripts/mod/devicetable-offsets.c
index 27007c18e754..e377f52dbfa3 100644
--- a/scripts/mod/devicetable-offsets.c
+++ b/scripts/mod/devicetable-offsets.c
@@ -243,5 +243,8 @@ int main(void)
 	DEVID(mhi_device_id);
 	DEVID_FIELD(mhi_device_id, chan);
 
+	DEVID(auxiliary_device_id);
+	DEVID_FIELD(auxiliary_device_id, name);
+
 	return 0;
 }
diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c
index 2417dd1dee33..fb4827027536 100644
--- a/scripts/mod/file2alias.c
+++ b/scripts/mod/file2alias.c
@@ -1364,6 +1364,13 @@ static int do_mhi_entry(const char *filename, void *symval, char *alias)
 {
 	DEF_FIELD_ADDR(symval, mhi_device_id, chan);
 	sprintf(alias, MHI_DEVICE_MODALIAS_FMT, *chan);
+	return 1;
+}
+
+static int do_auxiliary_entry(const char *filename, void *symval, char *alias)
+{
+	DEF_FIELD_ADDR(symval, auxiliary_device_id, name);
+	sprintf(alias, AUXILIARY_MODULE_PREFIX "%s", *name);
 
 	return 1;
 }
@@ -1442,6 +1449,7 @@ static const struct devtable devtable[] = {
 	{"tee", SIZE_tee_client_device_id, do_tee_entry},
 	{"wmi", SIZE_wmi_device_id, do_wmi_entry},
 	{"mhi", SIZE_mhi_device_id, do_mhi_entry},
+	{"auxiliary", SIZE_auxiliary_device_id, do_auxiliary_entry},
 };
 
 /* Create MODULE_ALIAS() statements.
-- 
cgit v1.2.3


From 30ae3e13caeaa47884c222ebf5711ce27ed25f19 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Wed, 25 Nov 2020 22:29:59 +0100
Subject: mmc: tmio: set max_busy_timeout

Set max_busy_timeouts for variants known to support the TOPxx bits in
the SD_OPTION register. The timeout mechanism was running in the
background but not yet properly handled in the driver. So, let the MMC
core know when to not use R1B to avoid unhandled timeouts.

My datasheets for older variants (tmio_mmc.c) suggest that they support
it, too. However, actual bit descriptions are lacking, so I chose an
opt-in approach.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Reviewed-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Tested-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Link: https://lore.kernel.org/r/20201125213001.15003-2-wsa+renesas@sang-engineering.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/renesas_sdhi_core.c |  3 +++
 drivers/mmc/host/tmio_mmc.h          |  2 ++
 drivers/mmc/host/tmio_mmc_core.c     | 15 +++++++++++++++
 drivers/mmc/host/uniphier-sd.c       |  1 +
 include/linux/mfd/tmio.h             |  7 ++++++-
 5 files changed, 27 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c
index bb937411c2ec..153767054c05 100644
--- a/drivers/mmc/host/renesas_sdhi_core.c
+++ b/drivers/mmc/host/renesas_sdhi_core.c
@@ -1041,6 +1041,9 @@ int renesas_sdhi_probe(struct platform_device *pdev,
 	/* All SDHI have SDIO status bits which must be 1 */
 	mmc_data->flags |= TMIO_MMC_SDIO_STATUS_SETBITS;
 
+	/* All SDHI support HW busy detection */
+	mmc_data->flags |= TMIO_MMC_USE_BUSY_TIMEOUT;
+
 	dev_pm_domain_start(&pdev->dev);
 
 	ret = renesas_sdhi_clk_enable(host);
diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h
index 7ff41185896a..819198af17f4 100644
--- a/drivers/mmc/host/tmio_mmc.h
+++ b/drivers/mmc/host/tmio_mmc.h
@@ -80,6 +80,8 @@
 #define	CLK_CTL_SCLKEN		BIT(8)
 
 /* Definitions for values the CTL_SD_MEM_CARD_OPT register can take */
+#define CARD_OPT_TOP_MASK	0xf0
+#define CARD_OPT_TOP_SHIFT	4
 #define CARD_OPT_WIDTH8		BIT(13)
 #define CARD_OPT_WIDTH		BIT(15)
 
diff --git a/drivers/mmc/host/tmio_mmc_core.c b/drivers/mmc/host/tmio_mmc_core.c
index a89547f5d733..7d2da5befe6b 100644
--- a/drivers/mmc/host/tmio_mmc_core.c
+++ b/drivers/mmc/host/tmio_mmc_core.c
@@ -887,6 +887,18 @@ static void tmio_mmc_set_bus_width(struct tmio_mmc_host *host,
 	sd_ctrl_write16(host, CTL_SD_MEM_CARD_OPT, reg);
 }
 
+static void tmio_mmc_max_busy_timeout(struct tmio_mmc_host *host)
+{
+	u16 val = sd_ctrl_read16(host, CTL_SD_MEM_CARD_OPT);
+	unsigned int clk_rate = host->mmc->actual_clock ?: host->mmc->f_max;
+	unsigned int cycles;
+
+	val = (val & CARD_OPT_TOP_MASK) >> CARD_OPT_TOP_SHIFT;
+	cycles = 1 << (13 + val);
+
+	host->mmc->max_busy_timeout = cycles / (clk_rate / MSEC_PER_SEC);
+}
+
 /* Set MMC clock / power.
  * Note: This controller uses a simple divider scheme therefore it cannot
  * run a MMC card at full speed (20MHz). The max clock is 24MHz on SD, but as
@@ -945,6 +957,9 @@ static void tmio_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 		break;
 	}
 
+	if (host->pdata->flags & TMIO_MMC_USE_BUSY_TIMEOUT)
+		tmio_mmc_max_busy_timeout(host);
+
 	/* Let things settle. delay taken from winCE driver */
 	usleep_range(140, 200);
 	if (PTR_ERR(host->mrq) == -EINTR)
diff --git a/drivers/mmc/host/uniphier-sd.c b/drivers/mmc/host/uniphier-sd.c
index 3092466a99ab..a6cd16771d4e 100644
--- a/drivers/mmc/host/uniphier-sd.c
+++ b/drivers/mmc/host/uniphier-sd.c
@@ -586,6 +586,7 @@ static int uniphier_sd_probe(struct platform_device *pdev)
 
 	tmio_data = &priv->tmio_data;
 	tmio_data->flags |= TMIO_MMC_32BIT_DATA_PORT;
+	tmio_data->flags |= TMIO_MMC_USE_BUSY_TIMEOUT;
 
 	host = tmio_mmc_host_alloc(pdev, tmio_data);
 	if (IS_ERR(host))
diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h
index 8ba042430d8e..27264fe4b3b9 100644
--- a/include/linux/mfd/tmio.h
+++ b/include/linux/mfd/tmio.h
@@ -55,7 +55,12 @@
  */
 #define TMIO_MMC_HAS_IDLE_WAIT		BIT(4)
 
-/* BIT(5) is unused */
+/*
+ * Use the busy timeout feature. Probably all TMIO versions support it. Yet,
+ * we don't have documentation for old variants, so we enable only known good
+ * variants with this flag. Can be removed once all variants are known good.
+ */
+#define TMIO_MMC_USE_BUSY_TIMEOUT	BIT(5)
 
 /*
  * Some controllers have CMD12 automatically
-- 
cgit v1.2.3


From 7bbb79ff5f7499e0c5d65987458410e8099207d8 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Fri, 4 Dec 2020 12:43:47 +0100
Subject: driver core: auxiliary bus: move slab.h from include file

No need to include slab.h in include/linux/auxiliary_bus.h, as it is not
needed there.  Move it to drivers/base/auxiliary.c instead.

Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Ertman <david.m.ertman@intel.com>
Cc: Fred Oh <fred.oh@linux.intel.com>
Cc: Kiran Patil <kiran.patil@intel.com>
Cc: Leon Romanovsky <leonro@nvidia.com>
Cc: Martin Habets <mhabets@solarflare.com>
Cc: Parav Pandit <parav@mellanox.com>
Cc: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Cc: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Cc: Shiraz Saleem <shiraz.saleem@intel.com>
Link: https://lore.kernel.org/r/X8og8xi3WkoYXet9@kroah.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/auxiliary.c      | 1 +
 include/linux/auxiliary_bus.h | 1 -
 2 files changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/base/auxiliary.c b/drivers/base/auxiliary.c
index ef2af417438b..eca36d6284d0 100644
--- a/drivers/base/auxiliary.c
+++ b/drivers/base/auxiliary.c
@@ -9,6 +9,7 @@
 
 #include <linux/device.h>
 #include <linux/init.h>
+#include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/pm_domain.h>
 #include <linux/pm_runtime.h>
diff --git a/include/linux/auxiliary_bus.h b/include/linux/auxiliary_bus.h
index 282fbf7bf9af..3580743d0e8d 100644
--- a/include/linux/auxiliary_bus.h
+++ b/include/linux/auxiliary_bus.h
@@ -10,7 +10,6 @@
 
 #include <linux/device.h>
 #include <linux/mod_devicetable.h>
-#include <linux/slab.h>
 
 struct auxiliary_device {
 	struct device dev;
-- 
cgit v1.2.3


From 8142a46c50d2dd8160c42284e1044eed3bec0d18 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Fri, 4 Dec 2020 12:44:07 +0100
Subject: driver core: auxiliary bus: make remove function return void

There's an effort to move the remove() callback in the driver core to
not return an int, as nothing can be done if this function fails.  To
make that effort easier, make the aux bus remove function void to start
with so that no users have to be changed sometime in the future.

Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Ertman <david.m.ertman@intel.com>
Cc: Fred Oh <fred.oh@linux.intel.com>
Cc: Kiran Patil <kiran.patil@intel.com>
Cc: Leon Romanovsky <leonro@nvidia.com>
Cc: Martin Habets <mhabets@solarflare.com>
Cc: Parav Pandit <parav@mellanox.com>
Cc: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Cc: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Cc: Shiraz Saleem <shiraz.saleem@intel.com>
Link: https://lore.kernel.org/r/X8ohB1ks1NK7kPop@kroah.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/driver-api/auxiliary_bus.rst | 2 +-
 drivers/base/auxiliary.c                   | 5 ++---
 include/linux/auxiliary_bus.h              | 2 +-
 3 files changed, 4 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/driver-api/auxiliary_bus.rst b/Documentation/driver-api/auxiliary_bus.rst
index 5dd7804631ef..2312506b0674 100644
--- a/Documentation/driver-api/auxiliary_bus.rst
+++ b/Documentation/driver-api/auxiliary_bus.rst
@@ -150,7 +150,7 @@ and shutdown notifications using the standard conventions.
 	struct auxiliary_driver {
 		int (*probe)(struct auxiliary_device *,
                              const struct auxiliary_device_id *id);
-		int (*remove)(struct auxiliary_device *);
+		void (*remove)(struct auxiliary_device *);
 		void (*shutdown)(struct auxiliary_device *);
 		int (*suspend)(struct auxiliary_device *, pm_message_t);
 		int (*resume)(struct auxiliary_device *);
diff --git a/drivers/base/auxiliary.c b/drivers/base/auxiliary.c
index eca36d6284d0..c44e85802b43 100644
--- a/drivers/base/auxiliary.c
+++ b/drivers/base/auxiliary.c
@@ -82,13 +82,12 @@ static int auxiliary_bus_remove(struct device *dev)
 {
 	struct auxiliary_driver *auxdrv = to_auxiliary_drv(dev->driver);
 	struct auxiliary_device *auxdev = to_auxiliary_dev(dev);
-	int ret = 0;
 
 	if (auxdrv->remove)
-		ret = auxdrv->remove(auxdev);
+		auxdrv->remove(auxdev);
 	dev_pm_domain_detach(dev, true);
 
-	return ret;
+	return 0;
 }
 
 static void auxiliary_bus_shutdown(struct device *dev)
diff --git a/include/linux/auxiliary_bus.h b/include/linux/auxiliary_bus.h
index 3580743d0e8d..d67b17606210 100644
--- a/include/linux/auxiliary_bus.h
+++ b/include/linux/auxiliary_bus.h
@@ -19,7 +19,7 @@ struct auxiliary_device {
 
 struct auxiliary_driver {
 	int (*probe)(struct auxiliary_device *auxdev, const struct auxiliary_device_id *id);
-	int (*remove)(struct auxiliary_device *auxdev);
+	void (*remove)(struct auxiliary_device *auxdev);
 	void (*shutdown)(struct auxiliary_device *auxdev);
 	int (*suspend)(struct auxiliary_device *auxdev, pm_message_t state);
 	int (*resume)(struct auxiliary_device *auxdev);
-- 
cgit v1.2.3


From 0d2bf11a6b3e275a526b8d42d8d4a3a6067cf953 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Fri, 4 Dec 2020 12:49:28 +0100
Subject: driver core: auxiliary bus: minor coding style tweaks

For some reason, the original aux bus patch had some really long lines
in a few places, probably due to it being a very long-lived patch in
development by many different people.  Fix that up so that the two files
all have the same length lines and function formatting styles.

Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Ertman <david.m.ertman@intel.com>
Cc: Fred Oh <fred.oh@linux.intel.com>
Cc: Kiran Patil <kiran.patil@intel.com>
Cc: Leon Romanovsky <leonro@nvidia.com>
Cc: Martin Habets <mhabets@solarflare.com>
Cc: Parav Pandit <parav@mellanox.com>
Cc: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Cc: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Cc: Shiraz Saleem <shiraz.saleem@intel.com>
Link: https://lore.kernel.org/r/X8oiSFTpYHw1xE/o@kroah.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/auxiliary.c      | 58 ++++++++++++++++++++++++-------------------
 include/linux/auxiliary_bus.h |  6 ++---
 2 files changed, 35 insertions(+), 29 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/auxiliary.c b/drivers/base/auxiliary.c
index c44e85802b43..f303daadf843 100644
--- a/drivers/base/auxiliary.c
+++ b/drivers/base/auxiliary.c
@@ -50,8 +50,8 @@ static int auxiliary_uevent(struct device *dev, struct kobj_uevent_env *env)
 	name = dev_name(dev);
 	p = strrchr(name, '.');
 
-	return add_uevent_var(env, "MODALIAS=%s%.*s", AUXILIARY_MODULE_PREFIX, (int)(p - name),
-			      name);
+	return add_uevent_var(env, "MODALIAS=%s%.*s", AUXILIARY_MODULE_PREFIX,
+			      (int)(p - name), name);
 }
 
 static const struct dev_pm_ops auxiliary_dev_pm_ops = {
@@ -113,16 +113,18 @@ static struct bus_type auxiliary_bus_type = {
  * auxiliary_device_init - check auxiliary_device and initialize
  * @auxdev: auxiliary device struct
  *
- * This is the first step in the two-step process to register an auxiliary_device.
+ * This is the first step in the two-step process to register an
+ * auxiliary_device.
  *
- * When this function returns an error code, then the device_initialize will *not* have
- * been performed, and the caller will be responsible to free any memory allocated for the
- * auxiliary_device in the error path directly.
+ * When this function returns an error code, then the device_initialize will
+ * *not* have been performed, and the caller will be responsible to free any
+ * memory allocated for the auxiliary_device in the error path directly.
  *
- * It returns 0 on success.  On success, the device_initialize has been performed.  After this
- * point any error unwinding will need to include a call to auxiliary_device_uninit().
- * In this post-initialize error scenario, a call to the device's .release callback will be
- * triggered, and all memory clean-up is expected to be handled there.
+ * It returns 0 on success.  On success, the device_initialize has been
+ * performed.  After this point any error unwinding will need to include a call
+ * to auxiliary_device_uninit().  In this post-initialize error scenario, a call
+ * to the device's .release callback will be triggered, and all memory clean-up
+ * is expected to be handled there.
  */
 int auxiliary_device_init(struct auxiliary_device *auxdev)
 {
@@ -149,16 +151,19 @@ EXPORT_SYMBOL_GPL(auxiliary_device_init);
  * @auxdev: auxiliary bus device to add to the bus
  * @modname: name of the parent device's driver module
  *
- * This is the second step in the two-step process to register an auxiliary_device.
+ * This is the second step in the two-step process to register an
+ * auxiliary_device.
  *
- * This function must be called after a successful call to auxiliary_device_init(), which
- * will perform the device_initialize.  This means that if this returns an error code, then a
- * call to auxiliary_device_uninit() must be performed so that the .release callback will
- * be triggered to free the memory associated with the auxiliary_device.
+ * This function must be called after a successful call to
+ * auxiliary_device_init(), which will perform the device_initialize.  This
+ * means that if this returns an error code, then a call to
+ * auxiliary_device_uninit() must be performed so that the .release callback
+ * will be triggered to free the memory associated with the auxiliary_device.
  *
- * The expectation is that users will call the "auxiliary_device_add" macro so that the caller's
- * KBUILD_MODNAME is automatically inserted for the modname parameter.  Only if a user requires
- * a custom name would this version be called directly.
+ * The expectation is that users will call the "auxiliary_device_add" macro so
+ * that the caller's KBUILD_MODNAME is automatically inserted for the modname
+ * parameter.  Only if a user requires a custom name would this version be
+ * called directly.
  */
 int __auxiliary_device_add(struct auxiliary_device *auxdev, const char *modname)
 {
@@ -166,13 +171,13 @@ int __auxiliary_device_add(struct auxiliary_device *auxdev, const char *modname)
 	int ret;
 
 	if (!modname) {
-		pr_err("auxiliary device modname is NULL\n");
+		dev_err(dev, "auxiliary device modname is NULL\n");
 		return -EINVAL;
 	}
 
 	ret = dev_set_name(dev, "%s.%s.%d", modname, auxdev->name, auxdev->id);
 	if (ret) {
-		pr_err("auxiliary device dev_set_name failed: %d\n", ret);
+		dev_err(dev, "auxiliary device dev_set_name failed: %d\n", ret);
 		return ret;
 	}
 
@@ -197,9 +202,9 @@ EXPORT_SYMBOL_GPL(__auxiliary_device_add);
  * if it does.  If the callback returns non-zero, this function will
  * return to the caller and not iterate over any more devices.
  */
-struct auxiliary_device *
-auxiliary_find_device(struct device *start, const void *data,
-		      int (*match)(struct device *dev, const void *data))
+struct auxiliary_device *auxiliary_find_device(struct device *start,
+					       const void *data,
+					       int (*match)(struct device *dev, const void *data))
 {
 	struct device *dev;
 
@@ -217,14 +222,15 @@ EXPORT_SYMBOL_GPL(auxiliary_find_device);
  * @owner: owning module/driver
  * @modname: KBUILD_MODNAME for parent driver
  */
-int __auxiliary_driver_register(struct auxiliary_driver *auxdrv, struct module *owner,
-				const char *modname)
+int __auxiliary_driver_register(struct auxiliary_driver *auxdrv,
+				struct module *owner, const char *modname)
 {
 	if (WARN_ON(!auxdrv->probe) || WARN_ON(!auxdrv->id_table))
 		return -EINVAL;
 
 	if (auxdrv->name)
-		auxdrv->driver.name = kasprintf(GFP_KERNEL, "%s.%s", modname, auxdrv->name);
+		auxdrv->driver.name = kasprintf(GFP_KERNEL, "%s.%s", modname,
+						auxdrv->name);
 	else
 		auxdrv->driver.name = kasprintf(GFP_KERNEL, "%s", modname);
 	if (!auxdrv->driver.name)
diff --git a/include/linux/auxiliary_bus.h b/include/linux/auxiliary_bus.h
index d67b17606210..fc51d45f106b 100644
--- a/include/linux/auxiliary_bus.h
+++ b/include/linux/auxiliary_bus.h
@@ -70,8 +70,8 @@ void auxiliary_driver_unregister(struct auxiliary_driver *auxdrv);
 #define module_auxiliary_driver(__auxiliary_driver) \
 	module_driver(__auxiliary_driver, auxiliary_driver_register, auxiliary_driver_unregister)
 
-struct auxiliary_device *
-auxiliary_find_device(struct device *start, const void *data,
-		      int (*match)(struct device *dev, const void *data));
+struct auxiliary_device *auxiliary_find_device(struct device *start,
+					       const void *data,
+					       int (*match)(struct device *dev, const void *data));
 
 #endif /* _AUXILIARY_BUS_H_ */
-- 
cgit v1.2.3


From 17a7612b99e66d2539341ab4f888f970c2c7f76d Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Sun, 4 Oct 2020 14:30:58 +0300
Subject: net/mlx5_core: Clean driver version and name

Remove exposed driver version as it was done in other drivers,
so module version will work correctly by displaying the kernel
version for which it is compiled.

And move mlx5_core module name to general include, so auxiliary drivers
will be able to use it as a basis for a name in their device ID tables.

Reviewed-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/devlink.c       |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c    |  4 +---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c        |  1 -
 drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/main.c          | 10 ++++++----
 drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h     |  3 ---
 include/linux/mlx5/driver.h                             |  2 ++
 7 files changed, 11 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index a28f95df2901..1a351e2f6ace 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -52,7 +52,7 @@ mlx5_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req,
 	u32 running_fw, stored_fw;
 	int err;
 
-	err = devlink_info_driver_name_put(req, DRIVER_NAME);
+	err = devlink_info_driver_name_put(req, KBUILD_MODNAME);
 	if (err)
 		return err;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index d25a56ec6876..bcff18a87bcd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -40,9 +40,7 @@ void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv,
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 
-	strlcpy(drvinfo->driver, DRIVER_NAME, sizeof(drvinfo->driver));
-	strlcpy(drvinfo->version, DRIVER_VERSION,
-		sizeof(drvinfo->version));
+	strlcpy(drvinfo->driver, KBUILD_MODNAME, sizeof(drvinfo->driver));
 	snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
 		 "%d.%d.%04d (%.16s)",
 		 fw_rev_maj(mdev), fw_rev_min(mdev), fw_rev_sub(mdev),
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 67247c33b9fd..ef2f8889ba0f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -64,7 +64,6 @@ static void mlx5e_rep_get_drvinfo(struct net_device *dev,
 
 	strlcpy(drvinfo->driver, mlx5e_rep_driver_name,
 		sizeof(drvinfo->driver));
-	strlcpy(drvinfo->version, UTS_RELEASE, sizeof(drvinfo->version));
 	snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
 		 "%d.%d.%04d (%.16s)",
 		 fw_rev_maj(mdev), fw_rev_min(mdev),
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
index cac8f085b16d..97d96fc38a65 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
@@ -39,7 +39,7 @@ static void mlx5i_get_drvinfo(struct net_device *dev,
 	struct mlx5e_priv *priv = mlx5i_epriv(dev);
 
 	mlx5e_ethtool_get_drvinfo(priv, drvinfo);
-	strlcpy(drvinfo->driver, DRIVER_NAME "[ib_ipoib]",
+	strlcpy(drvinfo->driver, KBUILD_MODNAME "[ib_ipoib]",
 		sizeof(drvinfo->driver));
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index e455a2f31f07..daef141931e7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -77,7 +77,6 @@
 MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
 MODULE_DESCRIPTION("Mellanox 5th generation network adapters (ConnectX series) core driver");
 MODULE_LICENSE("Dual BSD/GPL");
-MODULE_VERSION(DRIVER_VERSION);
 
 unsigned int mlx5_core_debug_mask;
 module_param_named(debug_mask, mlx5_core_debug_mask, uint, 0644);
@@ -228,7 +227,7 @@ static void mlx5_set_driver_version(struct mlx5_core_dev *dev)
 	strncat(string, ",", remaining_size);
 
 	remaining_size = max_t(int, 0, driver_ver_sz - strlen(string));
-	strncat(string, DRIVER_NAME, remaining_size);
+	strncat(string, KBUILD_MODNAME, remaining_size);
 
 	remaining_size = max_t(int, 0, driver_ver_sz - strlen(string));
 	strncat(string, ",", remaining_size);
@@ -313,7 +312,7 @@ static int request_bar(struct pci_dev *pdev)
 		return -ENODEV;
 	}
 
-	err = pci_request_regions(pdev, DRIVER_NAME);
+	err = pci_request_regions(pdev, KBUILD_MODNAME);
 	if (err)
 		dev_err(&pdev->dev, "Couldn't get PCI resources, aborting\n");
 
@@ -1617,7 +1616,7 @@ void mlx5_recover_device(struct mlx5_core_dev *dev)
 }
 
 static struct pci_driver mlx5_core_driver = {
-	.name           = DRIVER_NAME,
+	.name           = KBUILD_MODNAME,
 	.id_table       = mlx5_core_pci_table,
 	.probe          = init_one,
 	.remove         = remove_one,
@@ -1643,6 +1642,9 @@ static int __init init(void)
 {
 	int err;
 
+	WARN_ONCE(strcmp(MLX5_ADEV_NAME, KBUILD_MODNAME),
+		  "mlx5_core name not in sync with kernel module name");
+
 	get_random_bytes(&sw_owner_id, sizeof(sw_owner_id));
 
 	mlx5_core_verify_params();
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 8cec85ab419d..b285f1515e4e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -42,9 +42,6 @@
 #include <linux/mlx5/fs.h>
 #include <linux/mlx5/driver.h>
 
-#define DRIVER_NAME "mlx5_core"
-#define DRIVER_VERSION "5.0-0"
-
 extern uint mlx5_core_debug_mask;
 
 #define mlx5_core_dbg(__dev, format, ...)				\
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 0f23e1ed5e71..5f04495c33d7 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -56,6 +56,8 @@
 #include <linux/ptp_clock_kernel.h>
 #include <net/devlink.h>
 
+#define MLX5_ADEV_NAME "mlx5_core"
+
 enum {
 	MLX5_BOARD_ID_LEN = 64,
 };
-- 
cgit v1.2.3


From 0aae392bea4da1a2a9f2e22683c0fa751dc07333 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Tue, 6 Oct 2020 12:34:25 +0300
Subject: vdpa/mlx5: Make hardware definitions visible to all mlx5 devices

Move mlx5_vdpa IFC header file to the general include folder, so
mlx5_core will be able to reuse it to check if VDPA is supported
prior to creating an auxiliary device.

As part of this move, update the header file name to mlx5 general
naming scheme.

Reviewed-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/vdpa/mlx5/core/mlx5_vdpa_ifc.h | 168 ---------------------------------
 drivers/vdpa/mlx5/net/main.c           |   2 +-
 drivers/vdpa/mlx5/net/mlx5_vnet.c      |   2 +-
 include/linux/mlx5/mlx5_ifc_vdpa.h     | 166 ++++++++++++++++++++++++++++++++
 4 files changed, 168 insertions(+), 170 deletions(-)
 delete mode 100644 drivers/vdpa/mlx5/core/mlx5_vdpa_ifc.h
 create mode 100644 include/linux/mlx5/mlx5_ifc_vdpa.h

(limited to 'include/linux')

diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa_ifc.h b/drivers/vdpa/mlx5/core/mlx5_vdpa_ifc.h
deleted file mode 100644
index f6f57a29b38e..000000000000
--- a/drivers/vdpa/mlx5/core/mlx5_vdpa_ifc.h
+++ /dev/null
@@ -1,168 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
-/* Copyright (c) 2020 Mellanox Technologies Ltd. */
-
-#ifndef __MLX5_VDPA_IFC_H_
-#define __MLX5_VDPA_IFC_H_
-
-#include <linux/mlx5/mlx5_ifc.h>
-
-enum {
-	MLX5_VIRTIO_Q_EVENT_MODE_NO_MSIX_MODE  = 0x0,
-	MLX5_VIRTIO_Q_EVENT_MODE_QP_MODE       = 0x1,
-	MLX5_VIRTIO_Q_EVENT_MODE_MSIX_MODE     = 0x2,
-};
-
-enum {
-	MLX5_VIRTIO_EMULATION_CAP_VIRTIO_QUEUE_TYPE_SPLIT   = 0x1, // do I check this caps?
-	MLX5_VIRTIO_EMULATION_CAP_VIRTIO_QUEUE_TYPE_PACKED  = 0x2,
-};
-
-enum {
-	MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_SPLIT   = 0,
-	MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_PACKED  = 1,
-};
-
-struct mlx5_ifc_virtio_q_bits {
-	u8    virtio_q_type[0x8];
-	u8    reserved_at_8[0x5];
-	u8    event_mode[0x3];
-	u8    queue_index[0x10];
-
-	u8    full_emulation[0x1];
-	u8    virtio_version_1_0[0x1];
-	u8    reserved_at_22[0x2];
-	u8    offload_type[0x4];
-	u8    event_qpn_or_msix[0x18];
-
-	u8    doorbell_stride_index[0x10];
-	u8    queue_size[0x10];
-
-	u8    device_emulation_id[0x20];
-
-	u8    desc_addr[0x40];
-
-	u8    used_addr[0x40];
-
-	u8    available_addr[0x40];
-
-	u8    virtio_q_mkey[0x20];
-
-	u8    max_tunnel_desc[0x10];
-	u8    reserved_at_170[0x8];
-	u8    error_type[0x8];
-
-	u8    umem_1_id[0x20];
-
-	u8    umem_1_size[0x20];
-
-	u8    umem_1_offset[0x40];
-
-	u8    umem_2_id[0x20];
-
-	u8    umem_2_size[0x20];
-
-	u8    umem_2_offset[0x40];
-
-	u8    umem_3_id[0x20];
-
-	u8    umem_3_size[0x20];
-
-	u8    umem_3_offset[0x40];
-
-	u8    counter_set_id[0x20];
-
-	u8    reserved_at_320[0x8];
-	u8    pd[0x18];
-
-	u8    reserved_at_340[0xc0];
-};
-
-struct mlx5_ifc_virtio_net_q_object_bits {
-	u8    modify_field_select[0x40];
-
-	u8    reserved_at_40[0x20];
-
-	u8    vhca_id[0x10];
-	u8    reserved_at_70[0x10];
-
-	u8    queue_feature_bit_mask_12_3[0xa];
-	u8    dirty_bitmap_dump_enable[0x1];
-	u8    vhost_log_page[0x5];
-	u8    reserved_at_90[0xc];
-	u8    state[0x4];
-
-	u8    reserved_at_a0[0x5];
-	u8    queue_feature_bit_mask_2_0[0x3];
-	u8    tisn_or_qpn[0x18];
-
-	u8    dirty_bitmap_mkey[0x20];
-
-	u8    dirty_bitmap_size[0x20];
-
-	u8    dirty_bitmap_addr[0x40];
-
-	u8    hw_available_index[0x10];
-	u8    hw_used_index[0x10];
-
-	u8    reserved_at_160[0xa0];
-
-	struct mlx5_ifc_virtio_q_bits virtio_q_context;
-};
-
-struct mlx5_ifc_create_virtio_net_q_in_bits {
-	struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr;
-
-	struct mlx5_ifc_virtio_net_q_object_bits obj_context;
-};
-
-struct mlx5_ifc_create_virtio_net_q_out_bits {
-	struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr;
-};
-
-struct mlx5_ifc_destroy_virtio_net_q_in_bits {
-	struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_out_cmd_hdr;
-};
-
-struct mlx5_ifc_destroy_virtio_net_q_out_bits {
-	struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr;
-};
-
-struct mlx5_ifc_query_virtio_net_q_in_bits {
-	struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr;
-};
-
-struct mlx5_ifc_query_virtio_net_q_out_bits {
-	struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr;
-
-	struct mlx5_ifc_virtio_net_q_object_bits obj_context;
-};
-
-enum {
-	MLX5_VIRTQ_MODIFY_MASK_STATE                    = (u64)1 << 0,
-	MLX5_VIRTQ_MODIFY_MASK_DIRTY_BITMAP_PARAMS      = (u64)1 << 3,
-	MLX5_VIRTQ_MODIFY_MASK_DIRTY_BITMAP_DUMP_ENABLE = (u64)1 << 4,
-};
-
-enum {
-	MLX5_VIRTIO_NET_Q_OBJECT_STATE_INIT     = 0x0,
-	MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY      = 0x1,
-	MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND  = 0x2,
-	MLX5_VIRTIO_NET_Q_OBJECT_STATE_ERR      = 0x3,
-};
-
-enum {
-	MLX5_RQTC_LIST_Q_TYPE_RQ            = 0x0,
-	MLX5_RQTC_LIST_Q_TYPE_VIRTIO_NET_Q  = 0x1,
-};
-
-struct mlx5_ifc_modify_virtio_net_q_in_bits {
-	struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr;
-
-	struct mlx5_ifc_virtio_net_q_object_bits obj_context;
-};
-
-struct mlx5_ifc_modify_virtio_net_q_out_bits {
-	struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr;
-};
-
-#endif /* __MLX5_VDPA_IFC_H_ */
diff --git a/drivers/vdpa/mlx5/net/main.c b/drivers/vdpa/mlx5/net/main.c
index 838cd98386ff..4dd3f00f2306 100644
--- a/drivers/vdpa/mlx5/net/main.c
+++ b/drivers/vdpa/mlx5/net/main.c
@@ -4,7 +4,7 @@
 #include <linux/module.h>
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/device.h>
-#include "mlx5_vdpa_ifc.h"
+#include <linux/mlx5/mlx5_ifc_vdpa.h>
 #include "mlx5_vnet.h"
 
 MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 1fa6fcac8299..6c218b47b9f1 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -9,8 +9,8 @@
 #include <linux/mlx5/vport.h>
 #include <linux/mlx5/fs.h>
 #include <linux/mlx5/device.h>
+#include <linux/mlx5/mlx5_ifc_vdpa.h>
 #include "mlx5_vnet.h"
-#include "mlx5_vdpa_ifc.h"
 #include "mlx5_vdpa.h"
 
 #define to_mvdev(__vdev) container_of((__vdev), struct mlx5_vdpa_dev, vdev)
diff --git a/include/linux/mlx5/mlx5_ifc_vdpa.h b/include/linux/mlx5/mlx5_ifc_vdpa.h
new file mode 100644
index 000000000000..98b56b75c625
--- /dev/null
+++ b/include/linux/mlx5/mlx5_ifc_vdpa.h
@@ -0,0 +1,166 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2020 Mellanox Technologies Ltd. */
+
+#ifndef __MLX5_IFC_VDPA_H_
+#define __MLX5_IFC_VDPA_H_
+
+enum {
+	MLX5_VIRTIO_Q_EVENT_MODE_NO_MSIX_MODE  = 0x0,
+	MLX5_VIRTIO_Q_EVENT_MODE_QP_MODE       = 0x1,
+	MLX5_VIRTIO_Q_EVENT_MODE_MSIX_MODE     = 0x2,
+};
+
+enum {
+	MLX5_VIRTIO_EMULATION_CAP_VIRTIO_QUEUE_TYPE_SPLIT   = 0x1, // do I check this caps?
+	MLX5_VIRTIO_EMULATION_CAP_VIRTIO_QUEUE_TYPE_PACKED  = 0x2,
+};
+
+enum {
+	MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_SPLIT   = 0,
+	MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_PACKED  = 1,
+};
+
+struct mlx5_ifc_virtio_q_bits {
+	u8    virtio_q_type[0x8];
+	u8    reserved_at_8[0x5];
+	u8    event_mode[0x3];
+	u8    queue_index[0x10];
+
+	u8    full_emulation[0x1];
+	u8    virtio_version_1_0[0x1];
+	u8    reserved_at_22[0x2];
+	u8    offload_type[0x4];
+	u8    event_qpn_or_msix[0x18];
+
+	u8    doorbell_stride_index[0x10];
+	u8    queue_size[0x10];
+
+	u8    device_emulation_id[0x20];
+
+	u8    desc_addr[0x40];
+
+	u8    used_addr[0x40];
+
+	u8    available_addr[0x40];
+
+	u8    virtio_q_mkey[0x20];
+
+	u8    max_tunnel_desc[0x10];
+	u8    reserved_at_170[0x8];
+	u8    error_type[0x8];
+
+	u8    umem_1_id[0x20];
+
+	u8    umem_1_size[0x20];
+
+	u8    umem_1_offset[0x40];
+
+	u8    umem_2_id[0x20];
+
+	u8    umem_2_size[0x20];
+
+	u8    umem_2_offset[0x40];
+
+	u8    umem_3_id[0x20];
+
+	u8    umem_3_size[0x20];
+
+	u8    umem_3_offset[0x40];
+
+	u8    counter_set_id[0x20];
+
+	u8    reserved_at_320[0x8];
+	u8    pd[0x18];
+
+	u8    reserved_at_340[0xc0];
+};
+
+struct mlx5_ifc_virtio_net_q_object_bits {
+	u8    modify_field_select[0x40];
+
+	u8    reserved_at_40[0x20];
+
+	u8    vhca_id[0x10];
+	u8    reserved_at_70[0x10];
+
+	u8    queue_feature_bit_mask_12_3[0xa];
+	u8    dirty_bitmap_dump_enable[0x1];
+	u8    vhost_log_page[0x5];
+	u8    reserved_at_90[0xc];
+	u8    state[0x4];
+
+	u8    reserved_at_a0[0x5];
+	u8    queue_feature_bit_mask_2_0[0x3];
+	u8    tisn_or_qpn[0x18];
+
+	u8    dirty_bitmap_mkey[0x20];
+
+	u8    dirty_bitmap_size[0x20];
+
+	u8    dirty_bitmap_addr[0x40];
+
+	u8    hw_available_index[0x10];
+	u8    hw_used_index[0x10];
+
+	u8    reserved_at_160[0xa0];
+
+	struct mlx5_ifc_virtio_q_bits virtio_q_context;
+};
+
+struct mlx5_ifc_create_virtio_net_q_in_bits {
+	struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr;
+
+	struct mlx5_ifc_virtio_net_q_object_bits obj_context;
+};
+
+struct mlx5_ifc_create_virtio_net_q_out_bits {
+	struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr;
+};
+
+struct mlx5_ifc_destroy_virtio_net_q_in_bits {
+	struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_out_cmd_hdr;
+};
+
+struct mlx5_ifc_destroy_virtio_net_q_out_bits {
+	struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr;
+};
+
+struct mlx5_ifc_query_virtio_net_q_in_bits {
+	struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr;
+};
+
+struct mlx5_ifc_query_virtio_net_q_out_bits {
+	struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr;
+
+	struct mlx5_ifc_virtio_net_q_object_bits obj_context;
+};
+
+enum {
+	MLX5_VIRTQ_MODIFY_MASK_STATE                    = (u64)1 << 0,
+	MLX5_VIRTQ_MODIFY_MASK_DIRTY_BITMAP_PARAMS      = (u64)1 << 3,
+	MLX5_VIRTQ_MODIFY_MASK_DIRTY_BITMAP_DUMP_ENABLE = (u64)1 << 4,
+};
+
+enum {
+	MLX5_VIRTIO_NET_Q_OBJECT_STATE_INIT     = 0x0,
+	MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY      = 0x1,
+	MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND  = 0x2,
+	MLX5_VIRTIO_NET_Q_OBJECT_STATE_ERR      = 0x3,
+};
+
+enum {
+	MLX5_RQTC_LIST_Q_TYPE_RQ            = 0x0,
+	MLX5_RQTC_LIST_Q_TYPE_VIRTIO_NET_Q  = 0x1,
+};
+
+struct mlx5_ifc_modify_virtio_net_q_in_bits {
+	struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr;
+
+	struct mlx5_ifc_virtio_net_q_object_bits obj_context;
+};
+
+struct mlx5_ifc_modify_virtio_net_q_out_bits {
+	struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr;
+};
+
+#endif /* __MLX5_IFC_VDPA_H_ */
-- 
cgit v1.2.3


From a925b5e309c9b998658a6a94dbb53154ea901299 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Thu, 8 Oct 2020 16:06:37 +0300
Subject: net/mlx5: Register mlx5 devices to auxiliary virtual bus

Create auxiliary devices under new virtual bus. This will replace
the custom-made mlx5 ->add()/->remove() interfaces and next patches
will fill the missing callback and remove the old interface logic.

The attachment of auxiliary drivers to the devices is possible in
1-to-1 manner only and it requires us to create device for every protocol,
so that device (module) will be able to connect to it.

System with 2 IB and 1 RoCE cards:
[leonro@vm ~]$ lspci |grep nox
00:09.0 Ethernet controller: Mellanox Technologies MT27800 Family [ConnectX-5]
00:0a.0 Ethernet controller: Mellanox Technologies MT28908 Family [ConnectX-6]
00:0b.0 Ethernet controller: Mellanox Technologies MT2910 Family [ConnectX-7]
[leonro@vm ~]$ ls -l /sys/bus/auxiliary/devices/
 mlx5_core.eth.2 -> ../../../devices/pci0000:00/0000:00:0b.0/mlx5_core.eth.2
 mlx5_core.rdma.0 -> ../../../devices/pci0000:00/0000:00:09.0/mlx5_core.rdma.0
 mlx5_core.rdma.1 -> ../../../devices/pci0000:00/0000:00:0a.0/mlx5_core.rdma.1
 mlx5_core.rdma.2 -> ../../../devices/pci0000:00/0000:00:0b.0/mlx5_core.rdma.2
 mlx5_core.vdpa.1 -> ../../../devices/pci0000:00/0000:00:0a.0/mlx5_core.vdpa.1
 mlx5_core.vdpa.2 -> ../../../devices/pci0000:00/0000:00:0b.0/mlx5_core.vdpa.2
[leonro@vm ~]$ rdma dev
0: ibp0s9: node_type ca fw 4.6.9999 node_guid 5254:00c0:fe12:3455 sys_image_guid 5254:00c0:fe12:3455
1: ibp0s10: node_type ca fw 4.6.9999 node_guid 5254:00c0:fe12:3456 sys_image_guid 5254:00c0:fe12:3456
2: rdmap0s11: node_type ca fw 4.6.9999 node_guid 5254:00c0:fe12:3457 sys_image_guid 5254:00c0:fe12:3457

System with RoCE SR-IOV card with 4 VFs:
[leonro@vm ~]$ lspci |grep nox
01:00.0 Ethernet controller: Mellanox Technologies MT28908 Family [ConnectX-6]
01:00.1 Ethernet controller: Mellanox Technologies MT28908 Family [ConnectX-6 Virtual Function]
01:00.2 Ethernet controller: Mellanox Technologies MT28908 Family [ConnectX-6 Virtual Function]
01:00.3 Ethernet controller: Mellanox Technologies MT28908 Family [ConnectX-6 Virtual Function]
01:00.4 Ethernet controller: Mellanox Technologies MT28908 Family [ConnectX-6 Virtual Function]
[leonro@vm ~]$ ls -l /sys/bus/auxiliary/devices/
 mlx5_core.eth.0 -> ../../../devices/pci0000:00/0000:00:09.0/0000:01:00.0/mlx5_core.eth.0
 mlx5_core.eth.1 -> ../../../devices/pci0000:00/0000:00:09.0/0000:01:00.1/mlx5_core.eth.1
 mlx5_core.eth.2 -> ../../../devices/pci0000:00/0000:00:09.0/0000:01:00.2/mlx5_core.eth.2
 mlx5_core.eth.3 -> ../../../devices/pci0000:00/0000:00:09.0/0000:01:00.3/mlx5_core.eth.3
 mlx5_core.eth.4 -> ../../../devices/pci0000:00/0000:00:09.0/0000:01:00.4/mlx5_core.eth.4
 mlx5_core.rdma.0 -> ../../../devices/pci0000:00/0000:00:09.0/0000:01:00.0/mlx5_core.rdma.0
 mlx5_core.rdma.1 -> ../../../devices/pci0000:00/0000:00:09.0/0000:01:00.1/mlx5_core.rdma.1
 mlx5_core.rdma.2 -> ../../../devices/pci0000:00/0000:00:09.0/0000:01:00.2/mlx5_core.rdma.2
 mlx5_core.rdma.3 -> ../../../devices/pci0000:00/0000:00:09.0/0000:01:00.3/mlx5_core.rdma.3
 mlx5_core.rdma.4 -> ../../../devices/pci0000:00/0000:00:09.0/0000:01:00.4/mlx5_core.rdma.4
 mlx5_core.vdpa.1 -> ../../../devices/pci0000:00/0000:00:09.0/0000:01:00.1/mlx5_core.vdpa.1
 mlx5_core.vdpa.2 -> ../../../devices/pci0000:00/0000:00:09.0/0000:01:00.2/mlx5_core.vdpa.2
 mlx5_core.vdpa.3 -> ../../../devices/pci0000:00/0000:00:09.0/0000:01:00.3/mlx5_core.vdpa.3
 mlx5_core.vdpa.4 -> ../../../devices/pci0000:00/0000:00:09.0/0000:01:00.4/mlx5_core.vdpa.4
[leonro@vm ~]$ rdma dev
0: rocep1s0f0: node_type ca fw 4.6.9999 node_guid 5254:00c0:fe12:3455 sys_image_guid 5254:00c0:fe12:3455
1: rocep1s0f0v0: node_type ca fw 4.6.9999 node_guid 0000:0000:0000:0000 sys_image_guid 5254:00c0:fe12:3456
2: rocep1s0f0v1: node_type ca fw 4.6.9999 node_guid 0000:0000:0000:0000 sys_image_guid 5254:00c0:fe12:3457
3: rocep1s0f0v2: node_type ca fw 4.6.9999 node_guid 0000:0000:0000:0000 sys_image_guid 5254:00c0:fe12:3458
4: rocep1s0f0v3: node_type ca fw 4.6.9999 node_guid 0000:0000:0000:0000 sys_image_guid 5254:00c0:fe12:3459

Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Kconfig    |   1 +
 drivers/net/ethernet/mellanox/mlx5/core/dev.c      | 265 ++++++++++++++++++++-
 drivers/net/ethernet/mellanox/mlx5/core/main.c     |  24 +-
 .../net/ethernet/mellanox/mlx5/core/mlx5_core.h    |  20 +-
 include/linux/mlx5/driver.h                        |  26 +-
 5 files changed, 325 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index 99f1ec3b2575..485478979b1a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -6,6 +6,7 @@
 config MLX5_CORE
 	tristate "Mellanox 5th generation network adapters (ConnectX series) core driver"
 	depends on PCI
+	select AUXILIARY_BUS
 	select NET_DEVLINK
 	depends on VXLAN || !VXLAN
 	depends on MLXFW || !MLXFW
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index 1972ddd12704..8ddf469b2d05 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -37,6 +37,7 @@ static LIST_HEAD(intf_list);
 static LIST_HEAD(mlx5_dev_list);
 /* intf dev list mutex */
 static DEFINE_MUTEX(mlx5_intf_mutex);
+static DEFINE_IDA(mlx5_adev_ida);
 
 struct mlx5_device_context {
 	struct list_head	list;
@@ -50,6 +51,39 @@ enum {
 	MLX5_INTERFACE_ATTACHED,
 };
 
+static const struct mlx5_adev_device {
+	const char *suffix;
+	bool (*is_supported)(struct mlx5_core_dev *dev);
+} mlx5_adev_devices[1] = {};
+
+int mlx5_adev_idx_alloc(void)
+{
+	return ida_alloc(&mlx5_adev_ida, GFP_KERNEL);
+}
+
+void mlx5_adev_idx_free(int idx)
+{
+	ida_free(&mlx5_adev_ida, idx);
+}
+
+int mlx5_adev_init(struct mlx5_core_dev *dev)
+{
+	struct mlx5_priv *priv = &dev->priv;
+
+	priv->adev = kcalloc(ARRAY_SIZE(mlx5_adev_devices),
+			     sizeof(struct mlx5_adev *), GFP_KERNEL);
+	if (!priv->adev)
+		return -ENOMEM;
+
+	return 0;
+}
+
+void mlx5_adev_cleanup(struct mlx5_core_dev *dev)
+{
+	struct mlx5_priv *priv = &dev->priv;
+
+	kfree(priv->adev);
+}
 
 void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv)
 {
@@ -135,15 +169,99 @@ static void mlx5_attach_interface(struct mlx5_interface *intf, struct mlx5_priv
 	}
 }
 
-void mlx5_attach_device(struct mlx5_core_dev *dev)
+static void adev_release(struct device *dev)
+{
+	struct mlx5_adev *mlx5_adev =
+		container_of(dev, struct mlx5_adev, adev.dev);
+	struct mlx5_priv *priv = &mlx5_adev->mdev->priv;
+	int idx = mlx5_adev->idx;
+
+	kfree(mlx5_adev);
+	priv->adev[idx] = NULL;
+}
+
+static struct mlx5_adev *add_adev(struct mlx5_core_dev *dev, int idx)
+{
+	const char *suffix = mlx5_adev_devices[idx].suffix;
+	struct auxiliary_device *adev;
+	struct mlx5_adev *madev;
+	int ret;
+
+	madev = kzalloc(sizeof(*madev), GFP_KERNEL);
+	if (!madev)
+		return ERR_PTR(-ENOMEM);
+
+	adev = &madev->adev;
+	adev->id = dev->priv.adev_idx;
+	adev->name = suffix;
+	adev->dev.parent = dev->device;
+	adev->dev.release = adev_release;
+	madev->mdev = dev;
+	madev->idx = idx;
+
+	ret = auxiliary_device_init(adev);
+	if (ret) {
+		kfree(madev);
+		return ERR_PTR(ret);
+	}
+
+	ret = auxiliary_device_add(adev);
+	if (ret) {
+		auxiliary_device_uninit(adev);
+		return ERR_PTR(ret);
+	}
+	return madev;
+}
+
+static void del_adev(struct auxiliary_device *adev)
+{
+	auxiliary_device_delete(adev);
+	auxiliary_device_uninit(adev);
+}
+
+int mlx5_attach_device(struct mlx5_core_dev *dev)
 {
 	struct mlx5_priv *priv = &dev->priv;
+	struct auxiliary_device *adev;
+	struct auxiliary_driver *adrv;
 	struct mlx5_interface *intf;
+	int ret = 0, i;
 
 	mutex_lock(&mlx5_intf_mutex);
+	for (i = 0; i < ARRAY_SIZE(mlx5_adev_devices); i++) {
+		if (!priv->adev[i]) {
+			bool is_supported = false;
+
+			if (mlx5_adev_devices[i].is_supported)
+				is_supported = mlx5_adev_devices[i].is_supported(dev);
+
+			if (!is_supported)
+				continue;
+
+			priv->adev[i] = add_adev(dev, i);
+			if (IS_ERR(priv->adev[i])) {
+				ret = PTR_ERR(priv->adev[i]);
+				priv->adev[i] = NULL;
+			}
+		} else {
+			adev = &priv->adev[i]->adev;
+			adrv = to_auxiliary_drv(adev->dev.driver);
+
+			if (adrv->resume)
+				ret = adrv->resume(adev);
+		}
+		if (ret) {
+			mlx5_core_warn(dev, "Device[%d] (%s) failed to load\n",
+				       i, mlx5_adev_devices[i].suffix);
+
+			break;
+		}
+	}
+
 	list_for_each_entry(intf, &intf_list, list)
 		mlx5_attach_interface(intf, priv);
 	mutex_unlock(&mlx5_intf_mutex);
+	return ret;
 }
 
 static void mlx5_detach_interface(struct mlx5_interface *intf, struct mlx5_priv *priv)
@@ -171,9 +289,29 @@ static void mlx5_detach_interface(struct mlx5_interface *intf, struct mlx5_priv
 void mlx5_detach_device(struct mlx5_core_dev *dev)
 {
 	struct mlx5_priv *priv = &dev->priv;
+	struct auxiliary_device *adev;
+	struct auxiliary_driver *adrv;
 	struct mlx5_interface *intf;
+	pm_message_t pm = {};
+	int i;
 
 	mutex_lock(&mlx5_intf_mutex);
+	for (i = ARRAY_SIZE(mlx5_adev_devices) - 1; i >= 0; i--) {
+		if (!priv->adev[i])
+			continue;
+
+		adev = &priv->adev[i]->adev;
+		adrv = to_auxiliary_drv(adev->dev.driver);
+
+		if (adrv->suspend) {
+			adrv->suspend(adev, pm);
+			continue;
+		}
+
+		del_adev(&priv->adev[i]->adev);
+		priv->adev[i] = NULL;
+	}
+
 	list_for_each_entry(intf, &intf_list, list)
 		mlx5_detach_interface(intf, priv);
 	mutex_unlock(&mlx5_intf_mutex);
@@ -193,16 +331,30 @@ bool mlx5_device_registered(struct mlx5_core_dev *dev)
 	return found;
 }
 
-void mlx5_register_device(struct mlx5_core_dev *dev)
+int mlx5_register_device(struct mlx5_core_dev *dev)
 {
 	struct mlx5_priv *priv = &dev->priv;
 	struct mlx5_interface *intf;
+	int ret;
+
+	mutex_lock(&mlx5_intf_mutex);
+	dev->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV;
+	ret = mlx5_rescan_drivers_locked(dev);
+	mutex_unlock(&mlx5_intf_mutex);
+	if (ret)
+		goto add_err;
 
 	mutex_lock(&mlx5_intf_mutex);
 	list_add_tail(&priv->dev_list, &mlx5_dev_list);
 	list_for_each_entry(intf, &intf_list, list)
 		mlx5_add_device(intf, priv);
 	mutex_unlock(&mlx5_intf_mutex);
+
+	return 0;
+
+add_err:
+	mlx5_unregister_device(dev);
+	return ret;
 }
 
 void mlx5_unregister_device(struct mlx5_core_dev *dev)
@@ -214,6 +366,9 @@ void mlx5_unregister_device(struct mlx5_core_dev *dev)
 	list_for_each_entry_reverse(intf, &intf_list, list)
 		mlx5_remove_device(intf, priv);
 	list_del(&priv->dev_list);
+
+	dev->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV;
+	mlx5_rescan_drivers_locked(dev);
 	mutex_unlock(&mlx5_intf_mutex);
 }
 
@@ -246,6 +401,77 @@ void mlx5_unregister_interface(struct mlx5_interface *intf)
 }
 EXPORT_SYMBOL(mlx5_unregister_interface);
 
+static int add_drivers(struct mlx5_core_dev *dev)
+{
+	struct mlx5_priv *priv = &dev->priv;
+	int i, ret = 0;
+
+	for (i = 0; i < ARRAY_SIZE(mlx5_adev_devices); i++) {
+		bool is_supported = false;
+
+		if (priv->adev[i])
+			continue;
+
+		if (mlx5_adev_devices[i].is_supported)
+			is_supported = mlx5_adev_devices[i].is_supported(dev);
+
+		if (!is_supported)
+			continue;
+
+		priv->adev[i] = add_adev(dev, i);
+		if (IS_ERR(priv->adev[i])) {
+			mlx5_core_warn(dev, "Device[%d] (%s) failed to load\n",
+				       i, mlx5_adev_devices[i].suffix);
+			/* We continue to rescan drivers and leave to the caller
+			 * to make decision if to release everything or continue.
+			 */
+			ret = PTR_ERR(priv->adev[i]);
+			priv->adev[i] = NULL;
+		}
+	}
+	return ret;
+}
+
+static void delete_drivers(struct mlx5_core_dev *dev)
+{
+	struct mlx5_priv *priv = &dev->priv;
+	bool delete_all;
+	int i;
+
+	delete_all = priv->flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV;
+
+	for (i = ARRAY_SIZE(mlx5_adev_devices) - 1; i >= 0; i--) {
+		bool is_supported = false;
+
+		if (!priv->adev[i])
+			continue;
+
+		if (mlx5_adev_devices[i].is_supported && !delete_all)
+			is_supported = mlx5_adev_devices[i].is_supported(dev);
+
+		if (is_supported)
+			continue;
+
+		del_adev(&priv->adev[i]->adev);
+		priv->adev[i] = NULL;
+	}
+}
+
+/* This function is used after mlx5_core_dev is reconfigured.
+ */
+int mlx5_rescan_drivers_locked(struct mlx5_core_dev *dev)
+{
+	struct mlx5_priv *priv = &dev->priv;
+
+	lockdep_assert_held(&mlx5_intf_mutex);
+
+	delete_drivers(dev);
+	if (priv->flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV)
+		return 0;
+
+	return add_drivers(dev);
+}
+
 /* Must be called with intf_mutex held */
 static bool mlx5_has_added_dev_by_protocol(struct mlx5_core_dev *mdev, int protocol)
 {
@@ -299,24 +525,55 @@ void mlx5_remove_dev_by_protocol(struct mlx5_core_dev *dev, int protocol)
 		}
 }
 
-static u32 mlx5_gen_pci_id(struct mlx5_core_dev *dev)
+static u32 mlx5_gen_pci_id(const struct mlx5_core_dev *dev)
 {
 	return (u32)((pci_domain_nr(dev->pdev->bus) << 16) |
 		     (dev->pdev->bus->number << 8) |
 		     PCI_SLOT(dev->pdev->devfn));
 }
 
-/* Must be called with intf_mutex held */
+static int next_phys_dev(struct device *dev, const void *data)
+{
+	struct mlx5_adev *madev = container_of(dev, struct mlx5_adev, adev.dev);
+	struct mlx5_core_dev *mdev = madev->mdev;
+	const struct mlx5_core_dev *curr = data;
+
+	if (!mlx5_core_is_pf(mdev))
+		return 0;
+
+	if (mdev == curr)
+		return 0;
+
+	if (mlx5_gen_pci_id(mdev) != mlx5_gen_pci_id(curr))
+		return 0;
+
+	return 1;
+}
+
+/* This function is called with two flows:
+ * 1. During initialization of mlx5_core_dev and we don't need to lock it.
+ * 2. During LAG configure stage and caller holds &mlx5_intf_mutex.
+ */
 struct mlx5_core_dev *mlx5_get_next_phys_dev(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_dev *res = NULL;
 	struct mlx5_core_dev *tmp_dev;
+	struct auxiliary_device *adev;
+	struct mlx5_adev *madev;
 	struct mlx5_priv *priv;
 	u32 pci_id;
 
 	if (!mlx5_core_is_pf(dev))
 		return NULL;
 
+	adev = auxiliary_find_device(NULL, dev, &next_phys_dev);
+	if (adev) {
+		madev = container_of(adev, struct mlx5_adev, adev);
+
+		put_device(&adev->dev);
+		return madev->mdev;
+	}
+
 	pci_id = mlx5_gen_pci_id(dev);
 	list_for_each_entry(priv, &mlx5_dev_list, dev_list) {
 		tmp_dev = container_of(priv, struct mlx5_core_dev, priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index daef141931e7..ff68e5b17471 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1222,14 +1222,21 @@ int mlx5_load_one(struct mlx5_core_dev *dev, bool boot)
 		err = mlx5_devlink_register(priv_to_devlink(dev), dev->device);
 		if (err)
 			goto err_devlink_reg;
-		mlx5_register_device(dev);
+
+		err = mlx5_register_device(dev);
 	} else {
-		mlx5_attach_device(dev);
+		err = mlx5_attach_device(dev);
 	}
 
+	if (err)
+		goto err_register;
+
 	mutex_unlock(&dev->intf_state_mutex);
 	return 0;
 
+err_register:
+	if (boot)
+		mlx5_devlink_unregister(priv_to_devlink(dev));
 err_devlink_reg:
 	clear_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state);
 	mlx5_unload(dev);
@@ -1306,8 +1313,14 @@ static int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
 	if (err)
 		goto err_pagealloc_init;
 
+	err = mlx5_adev_init(dev);
+	if (err)
+		goto err_adev_init;
+
 	return 0;
 
+err_adev_init:
+	mlx5_pagealloc_cleanup(dev);
 err_pagealloc_init:
 	mlx5_health_cleanup(dev);
 err_health_init:
@@ -1324,6 +1337,7 @@ static void mlx5_mdev_uninit(struct mlx5_core_dev *dev)
 {
 	struct mlx5_priv *priv = &dev->priv;
 
+	mlx5_adev_cleanup(dev);
 	mlx5_pagealloc_cleanup(dev);
 	mlx5_health_cleanup(dev);
 	debugfs_remove_recursive(dev->priv.dbg_root);
@@ -1354,6 +1368,10 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	dev->coredev_type = id->driver_data & MLX5_PCI_DEV_IS_VF ?
 			 MLX5_COREDEV_VF : MLX5_COREDEV_PF;
 
+	dev->priv.adev_idx = mlx5_adev_idx_alloc();
+	if (dev->priv.adev_idx < 0)
+		return dev->priv.adev_idx;
+
 	err = mlx5_mdev_init(dev, prof_sel);
 	if (err)
 		goto mdev_init_err;
@@ -1387,6 +1405,7 @@ err_load_one:
 pci_init_err:
 	mlx5_mdev_uninit(dev);
 mdev_init_err:
+	mlx5_adev_idx_free(dev->priv.adev_idx);
 	mlx5_devlink_free(devlink);
 
 	return err;
@@ -1403,6 +1422,7 @@ static void remove_one(struct pci_dev *pdev)
 	mlx5_unload_one(dev, true);
 	mlx5_pci_close(dev);
 	mlx5_mdev_uninit(dev);
+	mlx5_adev_idx_free(dev->priv.adev_idx);
 	mlx5_devlink_free(devlink);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index b285f1515e4e..11195381a870 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -178,12 +178,17 @@ void mlx5_events_cleanup(struct mlx5_core_dev *dev);
 void mlx5_events_start(struct mlx5_core_dev *dev);
 void mlx5_events_stop(struct mlx5_core_dev *dev);
 
+int mlx5_adev_idx_alloc(void);
+void mlx5_adev_idx_free(int idx);
+void mlx5_adev_cleanup(struct mlx5_core_dev *dev);
+int mlx5_adev_init(struct mlx5_core_dev *dev);
+
 void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv);
 void mlx5_remove_device(struct mlx5_interface *intf, struct mlx5_priv *priv);
-void mlx5_attach_device(struct mlx5_core_dev *dev);
+int mlx5_attach_device(struct mlx5_core_dev *dev);
 void mlx5_detach_device(struct mlx5_core_dev *dev);
 bool mlx5_device_registered(struct mlx5_core_dev *dev);
-void mlx5_register_device(struct mlx5_core_dev *dev);
+int mlx5_register_device(struct mlx5_core_dev *dev);
 void mlx5_unregister_device(struct mlx5_core_dev *dev);
 void mlx5_add_dev_by_protocol(struct mlx5_core_dev *dev, int protocol);
 void mlx5_remove_dev_by_protocol(struct mlx5_core_dev *dev, int protocol);
@@ -232,6 +237,17 @@ static inline int mlx5_lag_is_lacp_owner(struct mlx5_core_dev *dev)
 		    MLX5_CAP_GEN(dev, lag_master);
 }
 
+int mlx5_rescan_drivers_locked(struct mlx5_core_dev *dev);
+static inline int mlx5_rescan_drivers(struct mlx5_core_dev *dev)
+{
+	int ret;
+
+	mlx5_dev_list_lock();
+	ret = mlx5_rescan_drivers_locked(dev);
+	mlx5_dev_list_unlock();
+	return ret;
+}
+
 void mlx5_reload_interface(struct mlx5_core_dev *mdev, int protocol);
 void mlx5_lag_update(struct mlx5_core_dev *dev);
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 5f04495c33d7..e31c72693bcf 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -48,6 +48,7 @@
 #include <linux/idr.h>
 #include <linux/notifier.h>
 #include <linux/refcount.h>
+#include <linux/auxiliary_bus.h>
 
 #include <linux/mlx5/device.h>
 #include <linux/mlx5/doorbell.h>
@@ -536,6 +537,17 @@ struct mlx5_core_roce {
 	struct mlx5_flow_handle *allow_rule;
 };
 
+enum {
+	MLX5_PRIV_FLAGS_DISABLE_IB_ADEV = 1 << 0,
+	MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV = 1 << 1,
+};
+
+struct mlx5_adev {
+	struct auxiliary_device adev;
+	struct mlx5_core_dev *mdev;
+	int idx;
+};
+
 struct mlx5_priv {
 	/* IRQ table valid only for real pci devices PF or VF */
 	struct mlx5_irq_table   *irq_table;
@@ -573,6 +585,8 @@ struct mlx5_priv {
 	struct list_head        dev_list;
 	struct list_head        ctx_list;
 	spinlock_t              ctx_lock;
+	struct mlx5_adev       **adev;
+	int			adev_idx;
 	struct mlx5_events      *events;
 
 	struct mlx5_flow_steering *steering;
@@ -580,6 +594,7 @@ struct mlx5_priv {
 	struct mlx5_eswitch     *eswitch;
 	struct mlx5_core_sriov	sriov;
 	struct mlx5_lag		*lag;
+	u32			flags;
 	struct mlx5_devcom	*devcom;
 	struct mlx5_fw_reset	*fw_reset;
 	struct mlx5_core_roce	roce;
@@ -1062,9 +1077,14 @@ enum {
 };
 
 enum {
-	MLX5_INTERFACE_PROTOCOL_IB  = 0,
-	MLX5_INTERFACE_PROTOCOL_ETH = 1,
-	MLX5_INTERFACE_PROTOCOL_VDPA = 2,
+	MLX5_INTERFACE_PROTOCOL_ETH_REP,
+	MLX5_INTERFACE_PROTOCOL_ETH,
+
+	MLX5_INTERFACE_PROTOCOL_IB_REP,
+	MLX5_INTERFACE_PROTOCOL_MPIB,
+	MLX5_INTERFACE_PROTOCOL_IB,
+
+	MLX5_INTERFACE_PROTOCOL_VDPA,
 };
 
 struct mlx5_interface {
-- 
cgit v1.2.3


From 62dcd9c59f324e484c1d655884e0101a988f6671 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 23 Nov 2020 11:23:13 +0100
Subject: earlycon: simplify earlycon-table implementation

Instead of using the array-of-pointers trick to avoid having gcc mess up
the earlycon array stride, specify type alignment when declaring entries
to prevent gcc from increasing alignment.

This is essentially an alternative (one-line) fix to the problem
addressed by commit dd709e72cb93 ("earlycon: Use a pointer table to fix
__earlycon_table stride").

gcc can increase the alignment of larger objects with static extent as
an optimisation, but this can be suppressed by using the aligned
attribute when declaring variables.

Note that we have been relying on this behaviour for kernel parameters
for 16 years and it indeed hasn't changed since the introduction of the
aligned attribute in gcc-3.1.

Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20201123102319.8090-3-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/of/fdt.c              |  7 ++-----
 drivers/tty/serial/earlycon.c |  6 ++----
 include/linux/serial_core.h   | 20 +++++++-------------
 3 files changed, 11 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 4602e467ca8b..feb0f2d67fc5 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -906,7 +906,7 @@ int __init early_init_dt_scan_chosen_stdout(void)
 	int offset;
 	const char *p, *q, *options = NULL;
 	int l;
-	const struct earlycon_id **p_match;
+	const struct earlycon_id *match;
 	const void *fdt = initial_boot_params;
 
 	offset = fdt_path_offset(fdt, "/chosen");
@@ -933,10 +933,7 @@ int __init early_init_dt_scan_chosen_stdout(void)
 		return 0;
 	}
 
-	for (p_match = __earlycon_table; p_match < __earlycon_table_end;
-	     p_match++) {
-		const struct earlycon_id *match = *p_match;
-
+	for (match = __earlycon_table; match < __earlycon_table_end; match++) {
 		if (!match->compatible[0])
 			continue;
 
diff --git a/drivers/tty/serial/earlycon.c b/drivers/tty/serial/earlycon.c
index b70877932d47..57c70851f22a 100644
--- a/drivers/tty/serial/earlycon.c
+++ b/drivers/tty/serial/earlycon.c
@@ -175,7 +175,7 @@ static int __init register_earlycon(char *buf, const struct earlycon_id *match)
  */
 int __init setup_earlycon(char *buf)
 {
-	const struct earlycon_id **p_match;
+	const struct earlycon_id *match;
 	bool empty_compatible = true;
 
 	if (!buf || !buf[0])
@@ -185,9 +185,7 @@ int __init setup_earlycon(char *buf)
 		return -EALREADY;
 
 again:
-	for (p_match = __earlycon_table; p_match < __earlycon_table_end;
-	     p_match++) {
-		const struct earlycon_id *match = *p_match;
+	for (match = __earlycon_table; match < __earlycon_table_end; match++) {
 		size_t len = strlen(match->name);
 
 		if (strncmp(buf, match->name, len))
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index ff63c2963359..3e32b788c28d 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -357,8 +357,8 @@ struct earlycon_id {
 	int	(*setup)(struct earlycon_device *, const char *options);
 };
 
-extern const struct earlycon_id *__earlycon_table[];
-extern const struct earlycon_id *__earlycon_table_end[];
+extern const struct earlycon_id __earlycon_table[];
+extern const struct earlycon_id __earlycon_table_end[];
 
 #if defined(CONFIG_SERIAL_EARLYCON) && !defined(MODULE)
 #define EARLYCON_USED_OR_UNUSED	__used
@@ -366,19 +366,13 @@ extern const struct earlycon_id *__earlycon_table_end[];
 #define EARLYCON_USED_OR_UNUSED	__maybe_unused
 #endif
 
-#define _OF_EARLYCON_DECLARE(_name, compat, fn, unique_id)		\
-	static const struct earlycon_id unique_id			\
-	     EARLYCON_USED_OR_UNUSED __initconst			\
+#define OF_EARLYCON_DECLARE(_name, compat, fn)				\
+	static const struct earlycon_id __UNIQUE_ID(__earlycon_##_name) \
+		EARLYCON_USED_OR_UNUSED  __section("__earlycon_table")  \
+		__aligned(__alignof__(struct earlycon_id))		\
 		= { .name = __stringify(_name),				\
 		    .compatible = compat,				\
-		    .setup = fn  };					\
-	static const struct earlycon_id EARLYCON_USED_OR_UNUSED		\
-		__section("__earlycon_table")				\
-		* const __PASTE(__p, unique_id) = &unique_id
-
-#define OF_EARLYCON_DECLARE(_name, compat, fn)				\
-	_OF_EARLYCON_DECLARE(_name, compat, fn,				\
-			     __UNIQUE_ID(__earlycon_##_name))
+		    .setup = fn };
 
 #define EARLYCON_DECLARE(_name, fn)	OF_EARLYCON_DECLARE(_name, "", fn)
 
-- 
cgit v1.2.3


From 5812b32e01c6d86ba7a84110702b46d8a8531fe9 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 23 Nov 2020 11:23:12 +0100
Subject: of: fix linker-section match-table corruption

Specify type alignment when declaring linker-section match-table entries
to prevent gcc from increasing alignment and corrupting the various
tables with padding (e.g. timers, irqchips, clocks, reserved memory).

This is specifically needed on x86 where gcc (typically) aligns larger
objects like struct of_device_id with static extent on 32-byte
boundaries which at best prevents matching on anything but the first
entry. Specifying alignment when declaring variables suppresses this
optimisation.

Here's a 64-bit example where all entries are corrupt as 16 bytes of
padding has been inserted before the first entry:

	ffffffff8266b4b0 D __clk_of_table
	ffffffff8266b4c0 d __of_table_fixed_factor_clk
	ffffffff8266b5a0 d __of_table_fixed_clk
	ffffffff8266b680 d __clk_of_table_sentinel

And here's a 32-bit example where the 8-byte-aligned table happens to be
placed on a 32-byte boundary so that all but the first entry are corrupt
due to the 28 bytes of padding inserted between entries:

	812b3ec0 D __irqchip_of_table
	812b3ec0 d __of_table_irqchip1
	812b3fa0 d __of_table_irqchip2
	812b4080 d __of_table_irqchip3
	812b4160 d irqchip_of_match_end

Verified on x86 using gcc-9.3 and gcc-4.9 (which uses 64-byte
alignment), and on arm using gcc-7.2.

Note that there are no in-tree users of these tables on x86 currently
(even if they are included in the image).

Fixes: 54196ccbe0ba ("of: consolidate linker section OF match table declarations")
Fixes: f6e916b82022 ("irqchip: add basic infrastructure")
Cc: stable <stable@vger.kernel.org>     # 3.9
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20201123102319.8090-2-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/of.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/of.h b/include/linux/of.h
index 5d51891cbf1a..af655d264f10 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -1300,6 +1300,7 @@ static inline int of_get_available_child_count(const struct device_node *np)
 #define _OF_DECLARE(table, name, compat, fn, fn_type)			\
 	static const struct of_device_id __of_table_##name		\
 		__used __section("__" #table "_of_table")		\
+		__aligned(__alignof__(struct of_device_id))		\
 		 = { .compatible = compat,				\
 		     .data = (fn == (fn_type)NULL) ? fn : fn  }
 #else
-- 
cgit v1.2.3


From e0efb3168d34dc8c8c72718672b8902e40efff8f Mon Sep 17 00:00:00 2001
From: Jann Horn <jannh@google.com>
Date: Thu, 3 Dec 2020 03:03:31 +0100
Subject: tty: Remove dead termiox code

set_termiox() and the TCGETX handler bail out with -EINVAL immediately
if ->termiox is NULL, but there are no code paths that can set
->termiox to a non-NULL pointer; and no such code paths seem to have
existed since the termiox mechanism was introduced back in
commit 1d65b4a088de ("tty: Add termiox") in v2.6.28.
Similarly, no driver actually implements .set_termiox; and it looks like
no driver ever has.

Delete this dead code; but leave the definition of struct termiox in the
UAPI headers intact.

Signed-off-by: Jann Horn <jannh@google.com>
Link: https://lore.kernel.org/r/20201203020331.2394754-1-jannh@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/tty_ioctl.c    | 61 ++--------------------------------------------
 include/linux/tty.h        |  1 -
 include/linux/tty_driver.h |  9 -------
 3 files changed, 2 insertions(+), 69 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c
index e18f318586ab..4de1c6ddb8ff 100644
--- a/drivers/tty/tty_ioctl.c
+++ b/drivers/tty/tty_ioctl.c
@@ -443,51 +443,6 @@ static int get_termio(struct tty_struct *tty, struct termio __user *termio)
 	return 0;
 }
 
-
-#ifdef TCGETX
-
-/**
- *	set_termiox	-	set termiox fields if possible
- *	@tty: terminal
- *	@arg: termiox structure from user
- *	@opt: option flags for ioctl type
- *
- *	Implement the device calling points for the SYS5 termiox ioctl
- *	interface in Linux
- */
-
-static int set_termiox(struct tty_struct *tty, void __user *arg, int opt)
-{
-	struct termiox tnew;
-	struct tty_ldisc *ld;
-
-	if (tty->termiox == NULL)
-		return -EINVAL;
-	if (copy_from_user(&tnew, arg, sizeof(struct termiox)))
-		return -EFAULT;
-
-	ld = tty_ldisc_ref(tty);
-	if (ld != NULL) {
-		if ((opt & TERMIOS_FLUSH) && ld->ops->flush_buffer)
-			ld->ops->flush_buffer(tty);
-		tty_ldisc_deref(ld);
-	}
-	if (opt & TERMIOS_WAIT) {
-		tty_wait_until_sent(tty, 0);
-		if (signal_pending(current))
-			return -ERESTARTSYS;
-	}
-
-	down_write(&tty->termios_rwsem);
-	if (tty->ops->set_termiox)
-		tty->ops->set_termiox(tty, &tnew);
-	up_write(&tty->termios_rwsem);
-	return 0;
-}
-
-#endif
-
-
 #ifdef TIOCGETP
 /*
  * These are deprecated, but there is limited support..
@@ -815,23 +770,11 @@ int tty_mode_ioctl(struct tty_struct *tty, struct file *file,
 		return ret;
 #endif
 #ifdef TCGETX
-	case TCGETX: {
-		struct termiox ktermx;
-		if (real_tty->termiox == NULL)
-			return -EINVAL;
-		down_read(&real_tty->termios_rwsem);
-		memcpy(&ktermx, real_tty->termiox, sizeof(struct termiox));
-		up_read(&real_tty->termios_rwsem);
-		if (copy_to_user(p, &ktermx, sizeof(struct termiox)))
-			ret = -EFAULT;
-		return ret;
-	}
+	case TCGETX:
 	case TCSETX:
-		return set_termiox(real_tty, p, 0);
 	case TCSETXW:
-		return set_termiox(real_tty, p, TERMIOS_WAIT);
 	case TCSETXF:
-		return set_termiox(real_tty, p, TERMIOS_FLUSH);
+		return -EINVAL;
 #endif		
 	case TIOCGSOFTCAR:
 		copy_termios(real_tty, &kterm);
diff --git a/include/linux/tty.h b/include/linux/tty.h
index 10212c6e4345..67c7a07c8083 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -303,7 +303,6 @@ struct tty_struct {
 	spinlock_t flow_lock;
 	/* Termios values are protected by the termios rwsem */
 	struct ktermios termios, termios_locked;
-	struct termiox *termiox;	/* May be NULL for unsupported */
 	char name[64];
 	struct pid *pgrp;		/* Protected by ctrl lock */
 	struct pid *session;
diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h
index 358446247ccd..61c3372d3f32 100644
--- a/include/linux/tty_driver.h
+++ b/include/linux/tty_driver.h
@@ -224,14 +224,6 @@
  *	line). See tty_do_resize() if you need to wrap the standard method
  *	in your own logic - the usual case.
  *
- * void (*set_termiox)(struct tty_struct *tty, struct termiox *new);
- *
- *	Called when the device receives a termiox based ioctl. Passes down
- *	the requested data from user space. This method will not be invoked
- *	unless the tty also has a valid tty->termiox pointer.
- *
- *	Optional: Called under the termios lock
- *
  * int (*get_icount)(struct tty_struct *tty, struct serial_icounter *icount);
  *
  *	Called when the device receives a TIOCGICOUNT ioctl. Passed a kernel
@@ -285,7 +277,6 @@ struct tty_operations {
 	int (*tiocmset)(struct tty_struct *tty,
 			unsigned int set, unsigned int clear);
 	int (*resize)(struct tty_struct *tty, struct winsize *ws);
-	int (*set_termiox)(struct tty_struct *tty, struct termiox *tnew);
 	int (*get_icount)(struct tty_struct *tty,
 				struct serial_icounter_struct *icount);
 	int  (*get_serial)(struct tty_struct *tty, struct serial_struct *p);
-- 
cgit v1.2.3


From c8bcd9c5be24fb9e6132e97da5a35e55a83e36b9 Mon Sep 17 00:00:00 2001
From: Jann Horn <jannh@google.com>
Date: Thu, 3 Dec 2020 02:25:05 +0100
Subject: tty: Fix ->session locking

Currently, locking of ->session is very inconsistent; most places
protect it using the legacy tty mutex, but disassociate_ctty(),
__do_SAK(), tiocspgrp() and tiocgsid() don't.
Two of the writers hold the ctrl_lock (because they already need it for
->pgrp), but __proc_set_tty() doesn't do that yet.

On a PREEMPT=y system, an unprivileged user can theoretically abuse
this broken locking to read 4 bytes of freed memory via TIOCGSID if
tiocgsid() is preempted long enough at the right point. (Other things
might also go wrong, especially if root-only ioctls are involved; I'm
not sure about that.)

Change the locking on ->session such that:

 - tty_lock() is held by all writers: By making disassociate_ctty()
   hold it. This should be fine because the same lock can already be
   taken through the call to tty_vhangup_session().
   The tricky part is that we need to shorten the area covered by
   siglock to be able to take tty_lock() without ugly retry logic; as
   far as I can tell, this should be fine, since nothing in the
   signal_struct is touched in the `if (tty)` branch.
 - ctrl_lock is held by all writers: By changing __proc_set_tty() to
   hold the lock a little longer.
 - All readers that aren't holding tty_lock() hold ctrl_lock: By
   adding locking to tiocgsid() and __do_SAK(), and expanding the area
   covered by ctrl_lock in tiocspgrp().

Cc: stable@kernel.org
Signed-off-by: Jann Horn <jannh@google.com>
Reviewed-by: Jiri Slaby <jirislaby@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/tty_io.c      |  7 ++++++-
 drivers/tty/tty_jobctrl.c | 44 +++++++++++++++++++++++++++++++-------------
 include/linux/tty.h       |  4 ++++
 3 files changed, 41 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 9f8b9a567b35..56ade99ef99f 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -2897,10 +2897,14 @@ void __do_SAK(struct tty_struct *tty)
 	struct task_struct *g, *p;
 	struct pid *session;
 	int		i;
+	unsigned long flags;
 
 	if (!tty)
 		return;
-	session = tty->session;
+
+	spin_lock_irqsave(&tty->ctrl_lock, flags);
+	session = get_pid(tty->session);
+	spin_unlock_irqrestore(&tty->ctrl_lock, flags);
 
 	tty_ldisc_flush(tty);
 
@@ -2932,6 +2936,7 @@ void __do_SAK(struct tty_struct *tty)
 		task_unlock(p);
 	} while_each_thread(g, p);
 	read_unlock(&tasklist_lock);
+	put_pid(session);
 #endif
 }
 
diff --git a/drivers/tty/tty_jobctrl.c b/drivers/tty/tty_jobctrl.c
index baadeea4a289..aa6d0537b379 100644
--- a/drivers/tty/tty_jobctrl.c
+++ b/drivers/tty/tty_jobctrl.c
@@ -103,8 +103,8 @@ static void __proc_set_tty(struct tty_struct *tty)
 	put_pid(tty->session);
 	put_pid(tty->pgrp);
 	tty->pgrp = get_pid(task_pgrp(current));
-	spin_unlock_irqrestore(&tty->ctrl_lock, flags);
 	tty->session = get_pid(task_session(current));
+	spin_unlock_irqrestore(&tty->ctrl_lock, flags);
 	if (current->signal->tty) {
 		tty_debug(tty, "current tty %s not NULL!!\n",
 			  current->signal->tty->name);
@@ -293,20 +293,23 @@ void disassociate_ctty(int on_exit)
 	spin_lock_irq(&current->sighand->siglock);
 	put_pid(current->signal->tty_old_pgrp);
 	current->signal->tty_old_pgrp = NULL;
-
 	tty = tty_kref_get(current->signal->tty);
+	spin_unlock_irq(&current->sighand->siglock);
+
 	if (tty) {
 		unsigned long flags;
+
+		tty_lock(tty);
 		spin_lock_irqsave(&tty->ctrl_lock, flags);
 		put_pid(tty->session);
 		put_pid(tty->pgrp);
 		tty->session = NULL;
 		tty->pgrp = NULL;
 		spin_unlock_irqrestore(&tty->ctrl_lock, flags);
+		tty_unlock(tty);
 		tty_kref_put(tty);
 	}
 
-	spin_unlock_irq(&current->sighand->siglock);
 	/* Now clear signal->tty under the lock */
 	read_lock(&tasklist_lock);
 	session_clear_tty(task_session(current));
@@ -477,14 +480,19 @@ static int tiocspgrp(struct tty_struct *tty, struct tty_struct *real_tty, pid_t
 		return -ENOTTY;
 	if (retval)
 		return retval;
-	if (!current->signal->tty ||
-	    (current->signal->tty != real_tty) ||
-	    (real_tty->session != task_session(current)))
-		return -ENOTTY;
+
 	if (get_user(pgrp_nr, p))
 		return -EFAULT;
 	if (pgrp_nr < 0)
 		return -EINVAL;
+
+	spin_lock_irq(&real_tty->ctrl_lock);
+	if (!current->signal->tty ||
+	    (current->signal->tty != real_tty) ||
+	    (real_tty->session != task_session(current))) {
+		retval = -ENOTTY;
+		goto out_unlock_ctrl;
+	}
 	rcu_read_lock();
 	pgrp = find_vpid(pgrp_nr);
 	retval = -ESRCH;
@@ -494,12 +502,12 @@ static int tiocspgrp(struct tty_struct *tty, struct tty_struct *real_tty, pid_t
 	if (session_of_pgrp(pgrp) != task_session(current))
 		goto out_unlock;
 	retval = 0;
-	spin_lock_irq(&real_tty->ctrl_lock);
 	put_pid(real_tty->pgrp);
 	real_tty->pgrp = get_pid(pgrp);
-	spin_unlock_irq(&real_tty->ctrl_lock);
 out_unlock:
 	rcu_read_unlock();
+out_unlock_ctrl:
+	spin_unlock_irq(&real_tty->ctrl_lock);
 	return retval;
 }
 
@@ -511,20 +519,30 @@ out_unlock:
  *
  *	Obtain the session id of the tty. If there is no session
  *	return an error.
- *
- *	Locking: none. Reference to current->signal->tty is safe.
  */
 static int tiocgsid(struct tty_struct *tty, struct tty_struct *real_tty, pid_t __user *p)
 {
+	unsigned long flags;
+	pid_t sid;
+
 	/*
 	 * (tty == real_tty) is a cheap way of
 	 * testing if the tty is NOT a master pty.
 	*/
 	if (tty == real_tty && current->signal->tty != real_tty)
 		return -ENOTTY;
+
+	spin_lock_irqsave(&real_tty->ctrl_lock, flags);
 	if (!real_tty->session)
-		return -ENOTTY;
-	return put_user(pid_vnr(real_tty->session), p);
+		goto err;
+	sid = pid_vnr(real_tty->session);
+	spin_unlock_irqrestore(&real_tty->ctrl_lock, flags);
+
+	return put_user(sid, p);
+
+err:
+	spin_unlock_irqrestore(&real_tty->ctrl_lock, flags);
+	return -ENOTTY;
 }
 
 /*
diff --git a/include/linux/tty.h b/include/linux/tty.h
index a99e9b8e4e31..eb33d948788c 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -306,6 +306,10 @@ struct tty_struct {
 	struct termiox *termiox;	/* May be NULL for unsupported */
 	char name[64];
 	struct pid *pgrp;		/* Protected by ctrl lock */
+	/*
+	 * Writes protected by both ctrl lock and legacy mutex, readers must use
+	 * at least one of them.
+	 */
 	struct pid *session;
 	unsigned long flags;
 	int count;
-- 
cgit v1.2.3


From a54895fa057c67700270777f7661d8d3c7fda88a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 3 Dec 2020 17:21:39 +0100
Subject: block: remove the request_queue to argument request based tracepoints

The request_queue can trivially be derived from the request.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-merge.c            |  2 +-
 block/blk-mq-sched.c         |  2 +-
 block/blk-mq.c               |  8 ++++----
 drivers/md/dm-rq.c           |  2 +-
 drivers/s390/scsi/zfcp_fsf.c |  3 +--
 include/linux/blktrace_api.h |  5 ++---
 include/trace/events/block.h | 30 ++++++++++++------------------
 kernel/trace/blktrace.c      | 44 +++++++++++++++++---------------------------
 8 files changed, 39 insertions(+), 57 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-merge.c b/block/blk-merge.c
index 4071daa88a5e..7497d86fff38 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -799,7 +799,7 @@ static struct request *attempt_merge(struct request_queue *q,
 	 */
 	blk_account_io_merge_request(next);
 
-	trace_block_rq_merge(q, next);
+	trace_block_rq_merge(next);
 
 	/*
 	 * ownership of bio passed from next to req, return 'next' for
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index d1eafe2c045c..deff4e826e23 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -386,7 +386,7 @@ EXPORT_SYMBOL_GPL(blk_mq_sched_try_insert_merge);
 
 void blk_mq_sched_request_inserted(struct request *rq)
 {
-	trace_block_rq_insert(rq->q, rq);
+	trace_block_rq_insert(rq);
 }
 EXPORT_SYMBOL_GPL(blk_mq_sched_request_inserted);
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 21e2b4b6b742..cf3916e2852f 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -733,7 +733,7 @@ void blk_mq_start_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 
-	trace_block_rq_issue(q, rq);
+	trace_block_rq_issue(rq);
 
 	if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
 		rq->io_start_time_ns = ktime_get_ns();
@@ -760,7 +760,7 @@ static void __blk_mq_requeue_request(struct request *rq)
 
 	blk_mq_put_driver_tag(rq);
 
-	trace_block_rq_requeue(q, rq);
+	trace_block_rq_requeue(rq);
 	rq_qos_requeue(q, rq);
 
 	if (blk_mq_request_started(rq)) {
@@ -1821,7 +1821,7 @@ static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx,
 
 	lockdep_assert_held(&ctx->lock);
 
-	trace_block_rq_insert(hctx->queue, rq);
+	trace_block_rq_insert(rq);
 
 	if (at_head)
 		list_add(&rq->queuelist, &ctx->rq_lists[type]);
@@ -1878,7 +1878,7 @@ void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 	 */
 	list_for_each_entry(rq, list, queuelist) {
 		BUG_ON(rq->mq_ctx != ctx);
-		trace_block_rq_insert(hctx->queue, rq);
+		trace_block_rq_insert(rq);
 	}
 
 	spin_lock(&ctx->lock);
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index 729a72ec30cc..13b4385f4d5a 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -397,7 +397,7 @@ static int map_request(struct dm_rq_target_io *tio)
 		}
 
 		/* The target has remapped the I/O so dispatch it */
-		trace_block_rq_remap(clone->q, clone, disk_devt(dm_disk(md)),
+		trace_block_rq_remap(clone, disk_devt(dm_disk(md)),
 				     blk_rq_pos(rq));
 		ret = dm_dispatch_clone_request(clone, rq);
 		if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) {
diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c
index 6cb963a06777..37d450f46952 100644
--- a/drivers/s390/scsi/zfcp_fsf.c
+++ b/drivers/s390/scsi/zfcp_fsf.c
@@ -2359,8 +2359,7 @@ static void zfcp_fsf_req_trace(struct zfcp_fsf_req *req, struct scsi_cmnd *scsi)
 		}
 	}
 
-	blk_add_driver_data(scsi->request->q, scsi->request, &blktrc,
-			    sizeof(blktrc));
+	blk_add_driver_data(scsi->request, &blktrc, sizeof(blktrc));
 }
 
 /**
diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
index 3b6ff5902edc..05556573b896 100644
--- a/include/linux/blktrace_api.h
+++ b/include/linux/blktrace_api.h
@@ -75,8 +75,7 @@ static inline bool blk_trace_note_message_enabled(struct request_queue *q)
 	return ret;
 }
 
-extern void blk_add_driver_data(struct request_queue *q, struct request *rq,
-				void *data, size_t len);
+extern void blk_add_driver_data(struct request *rq, void *data, size_t len);
 extern int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 			   struct block_device *bdev,
 			   char __user *arg);
@@ -90,7 +89,7 @@ extern struct attribute_group blk_trace_attr_group;
 #else /* !CONFIG_BLK_DEV_IO_TRACE */
 # define blk_trace_ioctl(bdev, cmd, arg)		(-ENOTTY)
 # define blk_trace_shutdown(q)				do { } while (0)
-# define blk_add_driver_data(q, rq, data, len)		do {} while (0)
+# define blk_add_driver_data(rq, data, len)		do {} while (0)
 # define blk_trace_setup(q, name, dev, bdev, arg)	(-ENOTTY)
 # define blk_trace_startstop(q, start)			(-ENOTTY)
 # define blk_trace_remove(q)				(-ENOTTY)
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index 8fb89574d867..0d782663a005 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -64,7 +64,6 @@ DEFINE_EVENT(block_buffer, block_dirty_buffer,
 
 /**
  * block_rq_requeue - place block IO request back on a queue
- * @q: queue holding operation
  * @rq: block IO operation request
  *
  * The block operation request @rq is being placed back into queue
@@ -73,9 +72,9 @@ DEFINE_EVENT(block_buffer, block_dirty_buffer,
  */
 TRACE_EVENT(block_rq_requeue,
 
-	TP_PROTO(struct request_queue *q, struct request *rq),
+	TP_PROTO(struct request *rq),
 
-	TP_ARGS(q, rq),
+	TP_ARGS(rq),
 
 	TP_STRUCT__entry(
 		__field(  dev_t,	dev			)
@@ -147,9 +146,9 @@ TRACE_EVENT(block_rq_complete,
 
 DECLARE_EVENT_CLASS(block_rq,
 
-	TP_PROTO(struct request_queue *q, struct request *rq),
+	TP_PROTO(struct request *rq),
 
-	TP_ARGS(q, rq),
+	TP_ARGS(rq),
 
 	TP_STRUCT__entry(
 		__field(  dev_t,	dev			)
@@ -181,7 +180,6 @@ DECLARE_EVENT_CLASS(block_rq,
 
 /**
  * block_rq_insert - insert block operation request into queue
- * @q: target queue
  * @rq: block IO operation request
  *
  * Called immediately before block operation request @rq is inserted
@@ -191,14 +189,13 @@ DECLARE_EVENT_CLASS(block_rq,
  */
 DEFINE_EVENT(block_rq, block_rq_insert,
 
-	TP_PROTO(struct request_queue *q, struct request *rq),
+	TP_PROTO(struct request *rq),
 
-	TP_ARGS(q, rq)
+	TP_ARGS(rq)
 );
 
 /**
  * block_rq_issue - issue pending block IO request operation to device driver
- * @q: queue holding operation
  * @rq: block IO operation operation request
  *
  * Called when block operation request @rq from queue @q is sent to a
@@ -206,14 +203,13 @@ DEFINE_EVENT(block_rq, block_rq_insert,
  */
 DEFINE_EVENT(block_rq, block_rq_issue,
 
-	TP_PROTO(struct request_queue *q, struct request *rq),
+	TP_PROTO(struct request *rq),
 
-	TP_ARGS(q, rq)
+	TP_ARGS(rq)
 );
 
 /**
  * block_rq_merge - merge request with another one in the elevator
- * @q: queue holding operation
  * @rq: block IO operation operation request
  *
  * Called when block operation request @rq from queue @q is merged to another
@@ -221,9 +217,9 @@ DEFINE_EVENT(block_rq, block_rq_issue,
  */
 DEFINE_EVENT(block_rq, block_rq_merge,
 
-	TP_PROTO(struct request_queue *q, struct request *rq),
+	TP_PROTO(struct request *rq),
 
-	TP_ARGS(q, rq)
+	TP_ARGS(rq)
 );
 
 /**
@@ -491,7 +487,6 @@ TRACE_EVENT(block_bio_remap,
 
 /**
  * block_rq_remap - map request for a block operation request
- * @q: queue holding the operation
  * @rq: block IO operation request
  * @dev: device for the operation
  * @from: original sector for the operation
@@ -502,10 +497,9 @@ TRACE_EVENT(block_bio_remap,
  */
 TRACE_EVENT(block_rq_remap,
 
-	TP_PROTO(struct request_queue *q, struct request *rq, dev_t dev,
-		 sector_t from),
+	TP_PROTO(struct request *rq, dev_t dev, sector_t from),
 
-	TP_ARGS(q, rq, dev, from),
+	TP_ARGS(rq, dev, from),
 
 	TP_STRUCT__entry(
 		__field( dev_t,		dev		)
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 405637144a03..7839a78205c2 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -795,12 +795,12 @@ static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio)
 #endif
 
 static u64
-blk_trace_request_get_cgid(struct request_queue *q, struct request *rq)
+blk_trace_request_get_cgid(struct request *rq)
 {
 	if (!rq->bio)
 		return 0;
 	/* Use the first bio */
-	return blk_trace_bio_get_cgid(q, rq->bio);
+	return blk_trace_bio_get_cgid(rq->q, rq->bio);
 }
 
 /*
@@ -841,40 +841,35 @@ static void blk_add_trace_rq(struct request *rq, int error,
 	rcu_read_unlock();
 }
 
-static void blk_add_trace_rq_insert(void *ignore,
-				    struct request_queue *q, struct request *rq)
+static void blk_add_trace_rq_insert(void *ignore, struct request *rq)
 {
 	blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_INSERT,
-			 blk_trace_request_get_cgid(q, rq));
+			 blk_trace_request_get_cgid(rq));
 }
 
-static void blk_add_trace_rq_issue(void *ignore,
-				   struct request_queue *q, struct request *rq)
+static void blk_add_trace_rq_issue(void *ignore, struct request *rq)
 {
 	blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_ISSUE,
-			 blk_trace_request_get_cgid(q, rq));
+			 blk_trace_request_get_cgid(rq));
 }
 
-static void blk_add_trace_rq_merge(void *ignore,
-				   struct request_queue *q, struct request *rq)
+static void blk_add_trace_rq_merge(void *ignore, struct request *rq)
 {
 	blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_BACKMERGE,
-			 blk_trace_request_get_cgid(q, rq));
+			 blk_trace_request_get_cgid(rq));
 }
 
-static void blk_add_trace_rq_requeue(void *ignore,
-				     struct request_queue *q,
-				     struct request *rq)
+static void blk_add_trace_rq_requeue(void *ignore, struct request *rq)
 {
 	blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_REQUEUE,
-			 blk_trace_request_get_cgid(q, rq));
+			 blk_trace_request_get_cgid(rq));
 }
 
 static void blk_add_trace_rq_complete(void *ignore, struct request *rq,
 			int error, unsigned int nr_bytes)
 {
 	blk_add_trace_rq(rq, error, nr_bytes, BLK_TA_COMPLETE,
-			 blk_trace_request_get_cgid(rq->q, rq));
+			 blk_trace_request_get_cgid(rq));
 }
 
 /**
@@ -1037,16 +1032,14 @@ static void blk_add_trace_bio_remap(void *ignore, struct bio *bio, dev_t dev,
  *     Add a trace for that action.
  *
  **/
-static void blk_add_trace_rq_remap(void *ignore,
-				   struct request_queue *q,
-				   struct request *rq, dev_t dev,
+static void blk_add_trace_rq_remap(void *ignore, struct request *rq, dev_t dev,
 				   sector_t from)
 {
 	struct blk_trace *bt;
 	struct blk_io_trace_remap r;
 
 	rcu_read_lock();
-	bt = rcu_dereference(q->blk_trace);
+	bt = rcu_dereference(rq->q->blk_trace);
 	if (likely(!bt)) {
 		rcu_read_unlock();
 		return;
@@ -1058,13 +1051,12 @@ static void blk_add_trace_rq_remap(void *ignore,
 
 	__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
 			rq_data_dir(rq), 0, BLK_TA_REMAP, 0,
-			sizeof(r), &r, blk_trace_request_get_cgid(q, rq));
+			sizeof(r), &r, blk_trace_request_get_cgid(rq));
 	rcu_read_unlock();
 }
 
 /**
  * blk_add_driver_data - Add binary message with driver-specific data
- * @q:		queue the io is for
  * @rq:		io request
  * @data:	driver-specific data
  * @len:	length of driver-specific data
@@ -1073,14 +1065,12 @@ static void blk_add_trace_rq_remap(void *ignore,
  *     Some drivers might want to write driver-specific data per request.
  *
  **/
-void blk_add_driver_data(struct request_queue *q,
-			 struct request *rq,
-			 void *data, size_t len)
+void blk_add_driver_data(struct request *rq, void *data, size_t len)
 {
 	struct blk_trace *bt;
 
 	rcu_read_lock();
-	bt = rcu_dereference(q->blk_trace);
+	bt = rcu_dereference(rq->q->blk_trace);
 	if (likely(!bt)) {
 		rcu_read_unlock();
 		return;
@@ -1088,7 +1078,7 @@ void blk_add_driver_data(struct request_queue *q,
 
 	__blk_add_trace(bt, blk_rq_trace_sector(rq), blk_rq_bytes(rq), 0, 0,
 				BLK_TA_DRV_DATA, 0, len, data,
-				blk_trace_request_get_cgid(q, rq));
+				blk_trace_request_get_cgid(rq));
 	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(blk_add_driver_data);
-- 
cgit v1.2.3


From c9d659b60770db94b898f94947192a94bbf95c5c Mon Sep 17 00:00:00 2001
From: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
Date: Fri, 20 Nov 2020 16:10:23 -0800
Subject: PCI/ERR: Bind RCEC devices to the Root Port driver

If a Root Complex Integrated Endpoint (RCiEP) is implemented, it may signal
errors through a Root Complex Event Collector (RCEC).  Each RCiEP must be
associated with no more than one RCEC.

For an RCEC (which is technically not a Bridge), error messages "received"
from associated RCiEPs must be enabled for "transmission" in order to cause
a System Error via the Root Control register or (when the Advanced Error
Reporting Capability is present) reporting via the Root Error Command
register and logging in the Root Error Status register and Error Source
Identification register.

Given the commonality with Root Ports and the need to also support AER and
PME services for RCECs, extend the Root Port driver to support RCEC devices
by adding the RCEC Class ID to the driver structure.

Co-developed-by: Sean V Kelley <sean.v.kelley@intel.com>
Link: https://lore.kernel.org/r/20201121001036.8560-3-sean.v.kelley@intel.com
Tested-by: Jonathan Cameron <Jonathan.Cameron@huawei.com> # non-native/no RCEC
Signed-off-by: Sean V Kelley <sean.v.kelley@intel.com>
Signed-off-by: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
---
 drivers/pci/pcie/portdrv_pci.c | 5 ++++-
 include/linux/pci_ids.h        | 1 +
 include/uapi/linux/pci_regs.h  | 7 +++++++
 3 files changed, 12 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/pci/pcie/portdrv_pci.c b/drivers/pci/pcie/portdrv_pci.c
index 3a3ce40ae1ab..4d880679b9b1 100644
--- a/drivers/pci/pcie/portdrv_pci.c
+++ b/drivers/pci/pcie/portdrv_pci.c
@@ -106,7 +106,8 @@ static int pcie_portdrv_probe(struct pci_dev *dev,
 	if (!pci_is_pcie(dev) ||
 	    ((pci_pcie_type(dev) != PCI_EXP_TYPE_ROOT_PORT) &&
 	     (pci_pcie_type(dev) != PCI_EXP_TYPE_UPSTREAM) &&
-	     (pci_pcie_type(dev) != PCI_EXP_TYPE_DOWNSTREAM)))
+	     (pci_pcie_type(dev) != PCI_EXP_TYPE_DOWNSTREAM) &&
+	     (pci_pcie_type(dev) != PCI_EXP_TYPE_RC_EC)))
 		return -ENODEV;
 
 	status = pcie_port_device_register(dev);
@@ -195,6 +196,8 @@ static const struct pci_device_id port_pci_ids[] = {
 	{ PCI_DEVICE_CLASS(((PCI_CLASS_BRIDGE_PCI << 8) | 0x00), ~0) },
 	/* subtractive decode PCI-to-PCI bridge, class type is 060401h */
 	{ PCI_DEVICE_CLASS(((PCI_CLASS_BRIDGE_PCI << 8) | 0x01), ~0) },
+	/* handle any Root Complex Event Collector */
+	{ PCI_DEVICE_CLASS(((PCI_CLASS_SYSTEM_RCEC << 8) | 0x00), ~0) },
 	{ },
 };
 
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 1ab1e24bcbce..d8156a5dbee8 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -81,6 +81,7 @@
 #define PCI_CLASS_SYSTEM_RTC		0x0803
 #define PCI_CLASS_SYSTEM_PCI_HOTPLUG	0x0804
 #define PCI_CLASS_SYSTEM_SDHCI		0x0805
+#define PCI_CLASS_SYSTEM_RCEC		0x0807
 #define PCI_CLASS_SYSTEM_OTHER		0x0880
 
 #define PCI_BASE_CLASS_INPUT		0x09
diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index a95d55f9f257..bccd3e35cb65 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -831,6 +831,13 @@
 #define  PCI_PWR_CAP_BUDGET(x)	((x) & 1)	/* Included in system budget */
 #define PCI_EXT_CAP_PWR_SIZEOF	16
 
+/* Root Complex Event Collector Endpoint Association  */
+#define PCI_RCEC_RCIEP_BITMAP	4	/* Associated Bitmap for RCiEPs */
+#define PCI_RCEC_BUSN		8	/* RCEC Associated Bus Numbers */
+#define  PCI_RCEC_BUSN_REG_VER	0x02	/* Least version with BUSN present */
+#define  PCI_RCEC_BUSN_NEXT(x)	(((x) >> 8) & 0xff)
+#define  PCI_RCEC_BUSN_LAST(x)	(((x) >> 16) & 0xff)
+
 /* Vendor-Specific (VSEC, PCI_EXT_CAP_ID_VNDR) */
 #define PCI_VNDR_HEADER		4	/* Vendor-Specific Header */
 #define  PCI_VNDR_HEADER_ID(x)	((x) & 0xffff)
-- 
cgit v1.2.3


From 90655631988f8f501529e6de5f13614389717ead Mon Sep 17 00:00:00 2001
From: Sean V Kelley <sean.v.kelley@intel.com>
Date: Fri, 20 Nov 2020 16:10:24 -0800
Subject: PCI/ERR: Cache RCEC EA Capability offset in pci_init_capabilities()

Extend support for Root Complex Event Collectors by decoding and caching
the RCEC Endpoint Association Extended Capabilities when enumerating. Use
that cached information for later error source reporting. See PCIe r5.0,
sec 7.9.10.

Co-developed-by: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
Link: https://lore.kernel.org/r/20201121001036.8560-4-sean.v.kelley@intel.com
Tested-by: Jonathan Cameron <Jonathan.Cameron@huawei.com> # non-native/no RCEC
Signed-off-by: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
Signed-off-by: Sean V Kelley <sean.v.kelley@intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/pci/pci.h         | 17 ++++++++++++++
 drivers/pci/pcie/Makefile |  2 +-
 drivers/pci/pcie/rcec.c   | 59 +++++++++++++++++++++++++++++++++++++++++++++++
 drivers/pci/probe.c       |  2 ++
 include/linux/pci.h       |  4 ++++
 5 files changed, 83 insertions(+), 1 deletion(-)
 create mode 100644 drivers/pci/pcie/rcec.c

(limited to 'include/linux')

diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index f86cae9aa1f4..12dcad8f3635 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -448,6 +448,15 @@ int aer_get_device_error_info(struct pci_dev *dev, struct aer_err_info *info);
 void aer_print_error(struct pci_dev *dev, struct aer_err_info *info);
 #endif	/* CONFIG_PCIEAER */
 
+#ifdef CONFIG_PCIEPORTBUS
+/* Cached RCEC Endpoint Association */
+struct rcec_ea {
+	u8		nextbusn;
+	u8		lastbusn;
+	u32		bitmap;
+};
+#endif
+
 #ifdef CONFIG_PCIE_DPC
 void pci_save_dpc_state(struct pci_dev *dev);
 void pci_restore_dpc_state(struct pci_dev *dev);
@@ -460,6 +469,14 @@ static inline void pci_restore_dpc_state(struct pci_dev *dev) {}
 static inline void pci_dpc_init(struct pci_dev *pdev) {}
 #endif
 
+#ifdef CONFIG_PCIEPORTBUS
+void pci_rcec_init(struct pci_dev *dev);
+void pci_rcec_exit(struct pci_dev *dev);
+#else
+static inline void pci_rcec_init(struct pci_dev *dev) {}
+static inline void pci_rcec_exit(struct pci_dev *dev) {}
+#endif
+
 #ifdef CONFIG_PCI_ATS
 /* Address Translation Service */
 void pci_ats_init(struct pci_dev *dev);
diff --git a/drivers/pci/pcie/Makefile b/drivers/pci/pcie/Makefile
index 68da9280ff11..d9697892fa3e 100644
--- a/drivers/pci/pcie/Makefile
+++ b/drivers/pci/pcie/Makefile
@@ -2,7 +2,7 @@
 #
 # Makefile for PCI Express features and port driver
 
-pcieportdrv-y			:= portdrv_core.o portdrv_pci.o err.o
+pcieportdrv-y			:= portdrv_core.o portdrv_pci.o err.o rcec.o
 
 obj-$(CONFIG_PCIEPORTBUS)	+= pcieportdrv.o
 
diff --git a/drivers/pci/pcie/rcec.c b/drivers/pci/pcie/rcec.c
new file mode 100644
index 000000000000..038e9d706d5f
--- /dev/null
+++ b/drivers/pci/pcie/rcec.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Root Complex Event Collector Support
+ *
+ * Authors:
+ *  Sean V Kelley <sean.v.kelley@intel.com>
+ *  Qiuxu Zhuo <qiuxu.zhuo@intel.com>
+ *
+ * Copyright (C) 2020 Intel Corp.
+ */
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/pci_regs.h>
+
+#include "../pci.h"
+
+void pci_rcec_init(struct pci_dev *dev)
+{
+	struct rcec_ea *rcec_ea;
+	u32 rcec, hdr, busn;
+	u8 ver;
+
+	/* Only for Root Complex Event Collectors */
+	if (pci_pcie_type(dev) != PCI_EXP_TYPE_RC_EC)
+		return;
+
+	rcec = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_RCEC);
+	if (!rcec)
+		return;
+
+	rcec_ea = kzalloc(sizeof(*rcec_ea), GFP_KERNEL);
+	if (!rcec_ea)
+		return;
+
+	pci_read_config_dword(dev, rcec + PCI_RCEC_RCIEP_BITMAP,
+			      &rcec_ea->bitmap);
+
+	/* Check whether RCEC BUSN register is present */
+	pci_read_config_dword(dev, rcec, &hdr);
+	ver = PCI_EXT_CAP_VER(hdr);
+	if (ver >= PCI_RCEC_BUSN_REG_VER) {
+		pci_read_config_dword(dev, rcec + PCI_RCEC_BUSN, &busn);
+		rcec_ea->nextbusn = PCI_RCEC_BUSN_NEXT(busn);
+		rcec_ea->lastbusn = PCI_RCEC_BUSN_LAST(busn);
+	} else {
+		/* Avoid later ver check by setting nextbusn */
+		rcec_ea->nextbusn = 0xff;
+		rcec_ea->lastbusn = 0x00;
+	}
+
+	dev->rcec_ea = rcec_ea;
+}
+
+void pci_rcec_exit(struct pci_dev *dev)
+{
+	kfree(dev->rcec_ea);
+	dev->rcec_ea = NULL;
+}
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 4289030b0fff..f22e1451d65d 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -2216,6 +2216,7 @@ static void pci_configure_device(struct pci_dev *dev)
 static void pci_release_capabilities(struct pci_dev *dev)
 {
 	pci_aer_exit(dev);
+	pci_rcec_exit(dev);
 	pci_vpd_release(dev);
 	pci_iov_release(dev);
 	pci_free_cap_save_buffers(dev);
@@ -2415,6 +2416,7 @@ static void pci_init_capabilities(struct pci_dev *dev)
 	pci_ptm_init(dev);		/* Precision Time Measurement */
 	pci_aer_init(dev);		/* Advanced Error Reporting */
 	pci_dpc_init(dev);		/* Downstream Port Containment */
+	pci_rcec_init(dev);		/* Root Complex Event Collector */
 
 	pcie_report_downtraining(dev);
 
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 22207a79762c..f8c927fd0602 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -304,6 +304,7 @@ struct pcie_link_state;
 struct pci_vpd;
 struct pci_sriov;
 struct pci_p2pdma;
+struct rcec_ea;
 
 /* The pci_dev structure describes PCI devices */
 struct pci_dev {
@@ -326,6 +327,9 @@ struct pci_dev {
 #ifdef CONFIG_PCIEAER
 	u16		aer_cap;	/* AER capability offset */
 	struct aer_stats *aer_stats;	/* AER stats for this device */
+#endif
+#ifdef CONFIG_PCIEPORTBUS
+	struct rcec_ea	*rcec_ea;	/* RCEC cached endpoint association */
 #endif
 	u8		pcie_cap;	/* PCIe capability offset */
 	u8		msi_cap;	/* MSI capability offset */
-- 
cgit v1.2.3


From 3ee16db390b42b8a21f2ad2ea2518f3469c6e532 Mon Sep 17 00:00:00 2001
From: Mike Snitzer <snitzer@redhat.com>
Date: Mon, 30 Nov 2020 10:57:43 -0500
Subject: dm: fix IO splitting

Commit 882ec4e609c1 ("dm table: stack 'chunk_sectors' limit to account
for target-specific splitting") caused a couple regressions:
1) Using lcm_not_zero() when stacking chunk_sectors was a bug because
   chunk_sectors must reflect the most limited of all devices in the
   IO stack.
2) DM targets that set max_io_len but that do _not_ provide an
   .iterate_devices method no longer had there IO split properly.

And commit 5091cdec56fa ("dm: change max_io_len() to use
blk_max_size_offset()") also caused a regression where DM no longer
supported varied (per target) IO splitting. The implication being the
potential for severely reduced performance for IO stacks that use a DM
target like dm-cache to hide performance limitations of a slower
device (e.g. one that requires 4K IO splitting).

Coming full circle: Fix all these issues by discontinuing stacking
chunk_sectors up using ti->max_io_len in dm_calculate_queue_limits(),
add optional chunk_sectors override argument to blk_max_size_offset()
and update DM's max_io_len() to pass ti->max_io_len to its
blk_max_size_offset() call.

Passing in an optional chunk_sectors override to blk_max_size_offset()
allows for code reuse of block's centralized calculation for max IO
size based on provided offset and split boundary.

Fixes: 882ec4e609c1 ("dm table: stack 'chunk_sectors' limit to account for target-specific splitting")
Fixes: 5091cdec56fa ("dm: change max_io_len() to use blk_max_size_offset()")
Cc: stable@vger.kernel.org
Reported-by: John Dorminy <jdorminy@redhat.com>
Reported-by: Bruce Johnston <bjohnsto@redhat.com>
Reported-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Reviewed-by: John Dorminy <jdorminy@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-merge.c      |  2 +-
 drivers/md/dm-table.c  |  5 -----
 drivers/md/dm.c        | 19 +++++++++++--------
 include/linux/blkdev.h | 11 ++++++-----
 4 files changed, 18 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-merge.c b/block/blk-merge.c
index bcf5e4580603..97b7c2821565 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -144,7 +144,7 @@ static struct bio *blk_bio_write_same_split(struct request_queue *q,
 static inline unsigned get_max_io_size(struct request_queue *q,
 				       struct bio *bio)
 {
-	unsigned sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector);
+	unsigned sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector, 0);
 	unsigned max_sectors = sectors;
 	unsigned pbs = queue_physical_block_size(q) >> SECTOR_SHIFT;
 	unsigned lbs = queue_logical_block_size(q) >> SECTOR_SHIFT;
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 2073ee8d18f4..7eeb7c4169c9 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -18,7 +18,6 @@
 #include <linux/mutex.h>
 #include <linux/delay.h>
 #include <linux/atomic.h>
-#include <linux/lcm.h>
 #include <linux/blk-mq.h>
 #include <linux/mount.h>
 #include <linux/dax.h>
@@ -1449,10 +1448,6 @@ int dm_calculate_queue_limits(struct dm_table *table,
 			zone_sectors = ti_limits.chunk_sectors;
 		}
 
-		/* Stack chunk_sectors if target-specific splitting is required */
-		if (ti->max_io_len)
-			ti_limits.chunk_sectors = lcm_not_zero(ti->max_io_len,
-							       ti_limits.chunk_sectors);
 		/* Set I/O hints portion of queue limits */
 		if (ti->type->io_hints)
 			ti->type->io_hints(ti, &ti_limits);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 98866e725f25..f7eb3d2964f3 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1039,15 +1039,18 @@ static sector_t max_io_len(struct dm_target *ti, sector_t sector)
 	sector_t max_len;
 
 	/*
-	 * Does the target need to split even further?
-	 * - q->limits.chunk_sectors reflects ti->max_io_len so
-	 *   blk_max_size_offset() provides required splitting.
-	 * - blk_max_size_offset() also respects q->limits.max_sectors
+	 * Does the target need to split IO even further?
+	 * - varied (per target) IO splitting is a tenet of DM; this
+	 *   explains why stacked chunk_sectors based splitting via
+	 *   blk_max_size_offset() isn't possible here. So pass in
+	 *   ti->max_io_len to override stacked chunk_sectors.
 	 */
-	max_len = blk_max_size_offset(ti->table->md->queue,
-				      target_offset);
-	if (len > max_len)
-		len = max_len;
+	if (ti->max_io_len) {
+		max_len = blk_max_size_offset(ti->table->md->queue,
+					      target_offset, ti->max_io_len);
+		if (len > max_len)
+			len = max_len;
+	}
 
 	return len;
 }
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 639cae2c158b..24ae504cf77d 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1073,11 +1073,12 @@ static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
  * file system requests.
  */
 static inline unsigned int blk_max_size_offset(struct request_queue *q,
-					       sector_t offset)
+					       sector_t offset,
+					       unsigned int chunk_sectors)
 {
-	unsigned int chunk_sectors = q->limits.chunk_sectors;
-
-	if (!chunk_sectors)
+	if (!chunk_sectors && q->limits.chunk_sectors)
+		chunk_sectors = q->limits.chunk_sectors;
+	else
 		return q->limits.max_sectors;
 
 	if (likely(is_power_of_2(chunk_sectors)))
@@ -1101,7 +1102,7 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq,
 	    req_op(rq) == REQ_OP_SECURE_ERASE)
 		return blk_queue_get_max_sectors(q, req_op(rq));
 
-	return min(blk_max_size_offset(q, offset),
+	return min(blk_max_size_offset(q, offset, 0),
 			blk_queue_get_max_sectors(q, req_op(rq)));
 }
 
-- 
cgit v1.2.3


From f646c2a0a6685a8a30a150509b112c911b8feff3 Mon Sep 17 00:00:00 2001
From: Puranjay Mohan <puranjay12@gmail.com>
Date: Sun, 29 Nov 2020 22:16:26 +0530
Subject: PCI: Return u8 from pci_find_capability() and similar

PCI Capabilities are linked in a list that must appear in the first 256
bytes of config space.  Each capabilities list pointer is 8 bits.

Change the return type of pci_find_capability() and supporting functions
from int to u8 to match the specification.

[bhelgaas: change other related interfaces, fix HyperTransport typos]
Link: https://lore.kernel.org/r/20201129164626.12887-1-puranjay12@gmail.com
Signed-off-by: Puranjay Mohan <puranjay12@gmail.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pci.c   | 42 +++++++++++++++++++++---------------------
 include/linux/pci.h | 12 ++++++------
 2 files changed, 27 insertions(+), 27 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index e578d34095e9..b3761e98377b 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -399,8 +399,8 @@ found:
 	return 1;
 }
 
-static int __pci_find_next_cap_ttl(struct pci_bus *bus, unsigned int devfn,
-				   u8 pos, int cap, int *ttl)
+static u8 __pci_find_next_cap_ttl(struct pci_bus *bus, unsigned int devfn,
+				  u8 pos, int cap, int *ttl)
 {
 	u8 id;
 	u16 ent;
@@ -423,22 +423,22 @@ static int __pci_find_next_cap_ttl(struct pci_bus *bus, unsigned int devfn,
 	return 0;
 }
 
-static int __pci_find_next_cap(struct pci_bus *bus, unsigned int devfn,
-			       u8 pos, int cap)
+static u8 __pci_find_next_cap(struct pci_bus *bus, unsigned int devfn,
+			      u8 pos, int cap)
 {
 	int ttl = PCI_FIND_CAP_TTL;
 
 	return __pci_find_next_cap_ttl(bus, devfn, pos, cap, &ttl);
 }
 
-int pci_find_next_capability(struct pci_dev *dev, u8 pos, int cap)
+u8 pci_find_next_capability(struct pci_dev *dev, u8 pos, int cap)
 {
 	return __pci_find_next_cap(dev->bus, dev->devfn,
 				   pos + PCI_CAP_LIST_NEXT, cap);
 }
 EXPORT_SYMBOL_GPL(pci_find_next_capability);
 
-static int __pci_bus_find_cap_start(struct pci_bus *bus,
+static u8 __pci_bus_find_cap_start(struct pci_bus *bus,
 				    unsigned int devfn, u8 hdr_type)
 {
 	u16 status;
@@ -477,9 +477,9 @@ static int __pci_bus_find_cap_start(struct pci_bus *bus,
  *  %PCI_CAP_ID_PCIX         PCI-X
  *  %PCI_CAP_ID_EXP          PCI Express
  */
-int pci_find_capability(struct pci_dev *dev, int cap)
+u8 pci_find_capability(struct pci_dev *dev, int cap)
 {
-	int pos;
+	u8 pos;
 
 	pos = __pci_bus_find_cap_start(dev->bus, dev->devfn, dev->hdr_type);
 	if (pos)
@@ -502,10 +502,9 @@ EXPORT_SYMBOL(pci_find_capability);
  * device's PCI configuration space or 0 in case the device does not
  * support it.
  */
-int pci_bus_find_capability(struct pci_bus *bus, unsigned int devfn, int cap)
+u8 pci_bus_find_capability(struct pci_bus *bus, unsigned int devfn, int cap)
 {
-	int pos;
-	u8 hdr_type;
+	u8 hdr_type, pos;
 
 	pci_bus_read_config_byte(bus, devfn, PCI_HEADER_TYPE, &hdr_type);
 
@@ -623,7 +622,7 @@ u64 pci_get_dsn(struct pci_dev *dev)
 }
 EXPORT_SYMBOL_GPL(pci_get_dsn);
 
-static int __pci_find_next_ht_cap(struct pci_dev *dev, int pos, int ht_cap)
+static u8 __pci_find_next_ht_cap(struct pci_dev *dev, u8 pos, int ht_cap)
 {
 	int rc, ttl = PCI_FIND_CAP_TTL;
 	u8 cap, mask;
@@ -650,11 +649,12 @@ static int __pci_find_next_ht_cap(struct pci_dev *dev, int pos, int ht_cap)
 
 	return 0;
 }
+
 /**
- * pci_find_next_ht_capability - query a device's Hypertransport capabilities
+ * pci_find_next_ht_capability - query a device's HyperTransport capabilities
  * @dev: PCI device to query
  * @pos: Position from which to continue searching
- * @ht_cap: Hypertransport capability code
+ * @ht_cap: HyperTransport capability code
  *
  * To be used in conjunction with pci_find_ht_capability() to search for
  * all capabilities matching @ht_cap. @pos should always be a value returned
@@ -663,26 +663,26 @@ static int __pci_find_next_ht_cap(struct pci_dev *dev, int pos, int ht_cap)
  * NB. To be 100% safe against broken PCI devices, the caller should take
  * steps to avoid an infinite loop.
  */
-int pci_find_next_ht_capability(struct pci_dev *dev, int pos, int ht_cap)
+u8 pci_find_next_ht_capability(struct pci_dev *dev, u8 pos, int ht_cap)
 {
 	return __pci_find_next_ht_cap(dev, pos + PCI_CAP_LIST_NEXT, ht_cap);
 }
 EXPORT_SYMBOL_GPL(pci_find_next_ht_capability);
 
 /**
- * pci_find_ht_capability - query a device's Hypertransport capabilities
+ * pci_find_ht_capability - query a device's HyperTransport capabilities
  * @dev: PCI device to query
- * @ht_cap: Hypertransport capability code
+ * @ht_cap: HyperTransport capability code
  *
- * Tell if a device supports a given Hypertransport capability.
+ * Tell if a device supports a given HyperTransport capability.
  * Returns an address within the device's PCI configuration space
  * or 0 in case the device does not support the request capability.
  * The address points to the PCI capability, of type PCI_CAP_ID_HT,
- * which has a Hypertransport capability matching @ht_cap.
+ * which has a HyperTransport capability matching @ht_cap.
  */
-int pci_find_ht_capability(struct pci_dev *dev, int ht_cap)
+u8 pci_find_ht_capability(struct pci_dev *dev, int ht_cap)
 {
-	int pos;
+	u8 pos;
 
 	pos = __pci_bus_find_cap_start(dev->bus, dev->devfn, dev->hdr_type);
 	if (pos)
diff --git a/include/linux/pci.h b/include/linux/pci.h
index e007bc3e8b6e..e615f8abdd79 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1064,12 +1064,13 @@ void pci_sort_breadthfirst(void);
 
 /* Generic PCI functions exported to card drivers */
 
-int pci_find_capability(struct pci_dev *dev, int cap);
-int pci_find_next_capability(struct pci_dev *dev, u8 pos, int cap);
+u8 pci_bus_find_capability(struct pci_bus *bus, unsigned int devfn, int cap);
+u8 pci_find_capability(struct pci_dev *dev, int cap);
+u8 pci_find_next_capability(struct pci_dev *dev, u8 pos, int cap);
+u8 pci_find_ht_capability(struct pci_dev *dev, int ht_cap);
+u8 pci_find_next_ht_capability(struct pci_dev *dev, u8 pos, int ht_cap);
 int pci_find_ext_capability(struct pci_dev *dev, int cap);
 int pci_find_next_ext_capability(struct pci_dev *dev, int pos, int cap);
-int pci_find_ht_capability(struct pci_dev *dev, int ht_cap);
-int pci_find_next_ht_capability(struct pci_dev *dev, int pos, int ht_cap);
 struct pci_bus *pci_find_next_bus(const struct pci_bus *from);
 
 u64 pci_get_dsn(struct pci_dev *dev);
@@ -1280,7 +1281,6 @@ void set_pcie_port_type(struct pci_dev *pdev);
 void set_pcie_hotplug_bridge(struct pci_dev *pdev);
 
 /* Functions for PCI Hotplug drivers to use */
-int pci_bus_find_capability(struct pci_bus *bus, unsigned int devfn, int cap);
 unsigned int pci_rescan_bus_bridge_resize(struct pci_dev *bridge);
 unsigned int pci_rescan_bus(struct pci_bus *bus);
 void pci_lock_rescan_remove(void);
@@ -1720,7 +1720,7 @@ static inline int __pci_register_driver(struct pci_driver *drv,
 static inline int pci_register_driver(struct pci_driver *drv)
 { return 0; }
 static inline void pci_unregister_driver(struct pci_driver *drv) { }
-static inline int pci_find_capability(struct pci_dev *dev, int cap)
+static inline u8 pci_find_capability(struct pci_dev *dev, int cap)
 { return 0; }
 static inline int pci_find_next_capability(struct pci_dev *dev, u8 post,
 					   int cap)
-- 
cgit v1.2.3


From ee8b1c478a9fbce9c64151ee561c124c4dcd66be Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Fri, 4 Dec 2020 15:14:07 -0600
Subject: PCI: Return u16 from pci_find_ext_capability() and similar

PCI Express Extended Capabilities are in config space between offsets 256
and 4K.  These offsets all fit in 16 bits.

Change the return type of pci_find_ext_capability() and supporting
functions from int to u16 to match the specification.  Many callers use
"int", which is fine, but there's no need to store more than a u16.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pci.c   | 6 +++---
 include/linux/pci.h | 6 +++---
 2 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index b3761e98377b..85cb873266d3 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -527,11 +527,11 @@ EXPORT_SYMBOL(pci_bus_find_capability);
  * not support it.  Some capabilities can occur several times, e.g., the
  * vendor-specific capability, and this provides a way to find them all.
  */
-int pci_find_next_ext_capability(struct pci_dev *dev, int start, int cap)
+u16 pci_find_next_ext_capability(struct pci_dev *dev, u16 start, int cap)
 {
 	u32 header;
 	int ttl;
-	int pos = PCI_CFG_SPACE_SIZE;
+	u16 pos = PCI_CFG_SPACE_SIZE;
 
 	/* minimum 8 bytes per capability */
 	ttl = (PCI_CFG_SPACE_EXP_SIZE - PCI_CFG_SPACE_SIZE) / 8;
@@ -582,7 +582,7 @@ EXPORT_SYMBOL_GPL(pci_find_next_ext_capability);
  *  %PCI_EXT_CAP_ID_DSN		Device Serial Number
  *  %PCI_EXT_CAP_ID_PWR		Power Budgeting
  */
-int pci_find_ext_capability(struct pci_dev *dev, int cap)
+u16 pci_find_ext_capability(struct pci_dev *dev, int cap)
 {
 	return pci_find_next_ext_capability(dev, 0, cap);
 }
diff --git a/include/linux/pci.h b/include/linux/pci.h
index e615f8abdd79..441e5753da0c 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -381,7 +381,7 @@ struct pci_dev {
 	struct pcie_link_state	*link_state;	/* ASPM link state */
 	unsigned int	ltr_path:1;	/* Latency Tolerance Reporting
 					   supported from root to here */
-	int		l1ss;		/* L1SS Capability pointer */
+	u16		l1ss;		/* L1SS Capability pointer */
 #endif
 	unsigned int	eetlp_prefix_path:1;	/* End-to-End TLP Prefix */
 
@@ -1069,8 +1069,8 @@ u8 pci_find_capability(struct pci_dev *dev, int cap);
 u8 pci_find_next_capability(struct pci_dev *dev, u8 pos, int cap);
 u8 pci_find_ht_capability(struct pci_dev *dev, int ht_cap);
 u8 pci_find_next_ht_capability(struct pci_dev *dev, u8 pos, int ht_cap);
-int pci_find_ext_capability(struct pci_dev *dev, int cap);
-int pci_find_next_ext_capability(struct pci_dev *dev, int pos, int cap);
+u16 pci_find_ext_capability(struct pci_dev *dev, int cap);
+u16 pci_find_next_ext_capability(struct pci_dev *dev, u16 pos, int cap);
 struct pci_bus *pci_find_next_bus(const struct pci_bus *from);
 
 u64 pci_get_dsn(struct pci_dev *dev);
-- 
cgit v1.2.3


From dba4a9256bb4d78ef89aaad5f49787aa27fcd5b4 Mon Sep 17 00:00:00 2001
From: Florent Revest <revest@chromium.org>
Date: Fri, 4 Dec 2020 12:36:04 +0100
Subject: net: Remove the err argument from sock_from_file

Currently, the sock_from_file prototype takes an "err" pointer that is
either not set or set to -ENOTSOCK IFF the returned socket is NULL. This
makes the error redundant and it is ignored by a few callers.

This patch simplifies the API by letting callers deduce the error based
on whether the returned socket is NULL or not.

Suggested-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Florent Revest <revest@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: KP Singh <kpsingh@google.com>
Link: https://lore.kernel.org/bpf/20201204113609.1850150-1-revest@google.com
---
 fs/eventpoll.c               |  3 +--
 fs/io_uring.c                | 16 ++++++++--------
 include/linux/net.h          |  2 +-
 net/core/netclassid_cgroup.c |  3 +--
 net/core/netprio_cgroup.c    |  3 +--
 net/core/sock.c              |  8 +-------
 net/socket.c                 | 27 ++++++++++++++++-----------
 7 files changed, 29 insertions(+), 33 deletions(-)

(limited to 'include/linux')

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 73c346e503d7..19499b7bb82c 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -416,12 +416,11 @@ static inline void ep_set_busy_poll_napi_id(struct epitem *epi)
 	unsigned int napi_id;
 	struct socket *sock;
 	struct sock *sk;
-	int err;
 
 	if (!net_busy_loop_on())
 		return;
 
-	sock = sock_from_file(epi->ffd.file, &err);
+	sock = sock_from_file(epi->ffd.file);
 	if (!sock)
 		return;
 
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 1023f7b44cea..7942a42be4c3 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -4356,9 +4356,9 @@ static int io_sendmsg(struct io_kiocb *req, bool force_nonblock,
 	unsigned flags;
 	int ret;
 
-	sock = sock_from_file(req->file, &ret);
+	sock = sock_from_file(req->file);
 	if (unlikely(!sock))
-		return ret;
+		return -ENOTSOCK;
 
 	if (req->async_data) {
 		kmsg = req->async_data;
@@ -4405,9 +4405,9 @@ static int io_send(struct io_kiocb *req, bool force_nonblock,
 	unsigned flags;
 	int ret;
 
-	sock = sock_from_file(req->file, &ret);
+	sock = sock_from_file(req->file);
 	if (unlikely(!sock))
-		return ret;
+		return -ENOTSOCK;
 
 	ret = import_single_range(WRITE, sr->buf, sr->len, &iov, &msg.msg_iter);
 	if (unlikely(ret))
@@ -4584,9 +4584,9 @@ static int io_recvmsg(struct io_kiocb *req, bool force_nonblock,
 	unsigned flags;
 	int ret, cflags = 0;
 
-	sock = sock_from_file(req->file, &ret);
+	sock = sock_from_file(req->file);
 	if (unlikely(!sock))
-		return ret;
+		return -ENOTSOCK;
 
 	if (req->async_data) {
 		kmsg = req->async_data;
@@ -4647,9 +4647,9 @@ static int io_recv(struct io_kiocb *req, bool force_nonblock,
 	unsigned flags;
 	int ret, cflags = 0;
 
-	sock = sock_from_file(req->file, &ret);
+	sock = sock_from_file(req->file);
 	if (unlikely(!sock))
-		return ret;
+		return -ENOTSOCK;
 
 	if (req->flags & REQ_F_BUFFER_SELECT) {
 		kbuf = io_recv_buffer_select(req, !force_nonblock);
diff --git a/include/linux/net.h b/include/linux/net.h
index 0dcd51feef02..9e2324efc26a 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -240,7 +240,7 @@ int sock_sendmsg(struct socket *sock, struct msghdr *msg);
 int sock_recvmsg(struct socket *sock, struct msghdr *msg, int flags);
 struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname);
 struct socket *sockfd_lookup(int fd, int *err);
-struct socket *sock_from_file(struct file *file, int *err);
+struct socket *sock_from_file(struct file *file);
 #define		     sockfd_put(sock) fput(sock->file)
 int net_ratelimit(void);
 
diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c
index 41b24cd31562..b49c57d35a88 100644
--- a/net/core/netclassid_cgroup.c
+++ b/net/core/netclassid_cgroup.c
@@ -68,9 +68,8 @@ struct update_classid_context {
 
 static int update_classid_sock(const void *v, struct file *file, unsigned n)
 {
-	int err;
 	struct update_classid_context *ctx = (void *)v;
-	struct socket *sock = sock_from_file(file, &err);
+	struct socket *sock = sock_from_file(file);
 
 	if (sock) {
 		spin_lock(&cgroup_sk_update_lock);
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index 9bd4cab7d510..99a431c56f23 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -220,8 +220,7 @@ static ssize_t write_priomap(struct kernfs_open_file *of,
 
 static int update_netprio(const void *v, struct file *file, unsigned n)
 {
-	int err;
-	struct socket *sock = sock_from_file(file, &err);
+	struct socket *sock = sock_from_file(file);
 	if (sock) {
 		spin_lock(&cgroup_sk_update_lock);
 		sock_cgroup_set_prioidx(&sock->sk->sk_cgrp_data,
diff --git a/net/core/sock.c b/net/core/sock.c
index 4fd7e785f177..bbcd4b97eddd 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2827,14 +2827,8 @@ EXPORT_SYMBOL(sock_no_mmap);
 void __receive_sock(struct file *file)
 {
 	struct socket *sock;
-	int error;
 
-	/*
-	 * The resulting value of "error" is ignored here since we only
-	 * need to take action when the file is a socket and testing
-	 * "sock" for NULL is sufficient.
-	 */
-	sock = sock_from_file(file, &error);
+	sock = sock_from_file(file);
 	if (sock) {
 		sock_update_netprioidx(&sock->sk->sk_cgrp_data);
 		sock_update_classid(&sock->sk->sk_cgrp_data);
diff --git a/net/socket.c b/net/socket.c
index bfef11ba35b8..9a240b45bdf3 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -445,17 +445,15 @@ static int sock_map_fd(struct socket *sock, int flags)
 /**
  *	sock_from_file - Return the &socket bounded to @file.
  *	@file: file
- *	@err: pointer to an error code return
  *
- *	On failure returns %NULL and assigns -ENOTSOCK to @err.
+ *	On failure returns %NULL.
  */
 
-struct socket *sock_from_file(struct file *file, int *err)
+struct socket *sock_from_file(struct file *file)
 {
 	if (file->f_op == &socket_file_ops)
 		return file->private_data;	/* set in sock_map_fd */
 
-	*err = -ENOTSOCK;
 	return NULL;
 }
 EXPORT_SYMBOL(sock_from_file);
@@ -484,9 +482,11 @@ struct socket *sockfd_lookup(int fd, int *err)
 		return NULL;
 	}
 
-	sock = sock_from_file(file, err);
-	if (!sock)
+	sock = sock_from_file(file);
+	if (!sock) {
+		*err = -ENOTSOCK;
 		fput(file);
+	}
 	return sock;
 }
 EXPORT_SYMBOL(sockfd_lookup);
@@ -498,11 +498,12 @@ static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed)
 
 	*err = -EBADF;
 	if (f.file) {
-		sock = sock_from_file(f.file, err);
+		sock = sock_from_file(f.file);
 		if (likely(sock)) {
 			*fput_needed = f.flags & FDPUT_FPUT;
 			return sock;
 		}
+		*err = -ENOTSOCK;
 		fdput(f);
 	}
 	return NULL;
@@ -1693,9 +1694,11 @@ int __sys_accept4_file(struct file *file, unsigned file_flags,
 	if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK))
 		flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK;
 
-	sock = sock_from_file(file, &err);
-	if (!sock)
+	sock = sock_from_file(file);
+	if (!sock) {
+		err = -ENOTSOCK;
 		goto out;
+	}
 
 	err = -ENFILE;
 	newsock = sock_alloc();
@@ -1818,9 +1821,11 @@ int __sys_connect_file(struct file *file, struct sockaddr_storage *address,
 	struct socket *sock;
 	int err;
 
-	sock = sock_from_file(file, &err);
-	if (!sock)
+	sock = sock_from_file(file);
+	if (!sock) {
+		err = -ENOTSOCK;
 		goto out;
+	}
 
 	err =
 	    security_socket_connect(sock, (struct sockaddr *)address, addrlen);
-- 
cgit v1.2.3


From 65f33b35722952fa076811d5686bfd8a611a80fa Mon Sep 17 00:00:00 2001
From: Mike Snitzer <snitzer@redhat.com>
Date: Fri, 4 Dec 2020 17:21:03 -0500
Subject: block: fix incorrect branching in blk_max_size_offset()

If non-zero 'chunk_sectors' is passed in to blk_max_size_offset() that
override will be incorrectly ignored.

Old blk_max_size_offset() branching, prior to commit 3ee16db390b4,
must be used only if passed 'chunk_sectors' override is zero.

Fixes: 3ee16db390b4 ("dm: fix IO splitting")
Cc: stable@vger.kernel.org # 5.9
Reported-by: John Dorminy <jdorminy@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 include/linux/blkdev.h | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 24ae504cf77d..033eb5f73b65 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1076,10 +1076,12 @@ static inline unsigned int blk_max_size_offset(struct request_queue *q,
 					       sector_t offset,
 					       unsigned int chunk_sectors)
 {
-	if (!chunk_sectors && q->limits.chunk_sectors)
-		chunk_sectors = q->limits.chunk_sectors;
-	else
-		return q->limits.max_sectors;
+	if (!chunk_sectors) {
+		if (q->limits.chunk_sectors)
+			chunk_sectors = q->limits.chunk_sectors;
+		else
+			return q->limits.max_sectors;
+	}
 
 	if (likely(is_power_of_2(chunk_sectors)))
 		chunk_sectors -= offset & (chunk_sectors - 1);
-- 
cgit v1.2.3


From 99efde6c9bb7b42eac0459876bf964fe08e5cef9 Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Wed, 25 Nov 2020 12:07:33 +0300
Subject: PCI/PM: Rename pci_wakeup_bus() to pci_resume_bus()

A "wakeup" is a signal from a device telling the system that the device or
the whole system should be awakened and made active.  PCI devices are made
active by "resuming" them.

pci_wakeup_bus() is not involved with the wakeup signal; it *resumes*
devices on a bus (possibly in response to a wakeup signal, but that's at a
higher level).

Rename pci_wakeup_bus() to pci_resume_bus() to better reflect what it does.
No functional change intended.

[bhelgaas: commit log, reorder before removal of pci_wakeup_event()]
Link: https://lore.kernel.org/r/20201125090733.77782-2-mika.westerberg@linux.intel.com
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/gpu/vga/vga_switcheroo.c |  2 +-
 drivers/pci/pci.c                | 15 +++++----------
 include/linux/pci.h              |  2 +-
 3 files changed, 7 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/vga/vga_switcheroo.c b/drivers/gpu/vga/vga_switcheroo.c
index 087304b1a5d7..8843b078ad4e 100644
--- a/drivers/gpu/vga/vga_switcheroo.c
+++ b/drivers/gpu/vga/vga_switcheroo.c
@@ -1039,7 +1039,7 @@ static int vga_switcheroo_runtime_resume(struct device *dev)
 	mutex_lock(&vgasr_mutex);
 	vga_switcheroo_power_switch(pdev, VGA_SWITCHEROO_ON);
 	mutex_unlock(&vgasr_mutex);
-	pci_wakeup_bus(pdev->bus);
+	pci_resume_bus(pdev->bus);
 	ret = dev->bus->pm->runtime_resume(dev);
 	if (ret)
 		return ret;
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index e578d34095e9..664aada79de2 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -1174,12 +1174,7 @@ int pci_platform_power_transition(struct pci_dev *dev, pci_power_t state)
 }
 EXPORT_SYMBOL_GPL(pci_platform_power_transition);
 
-/**
- * pci_wakeup - Wake up a PCI device
- * @pci_dev: Device to handle.
- * @ign: ignored parameter
- */
-static int pci_wakeup(struct pci_dev *pci_dev, void *ign)
+static int pci_resume_one(struct pci_dev *pci_dev, void *ign)
 {
 	pci_wakeup_event(pci_dev);
 	pm_request_resume(&pci_dev->dev);
@@ -1187,13 +1182,13 @@ static int pci_wakeup(struct pci_dev *pci_dev, void *ign)
 }
 
 /**
- * pci_wakeup_bus - Walk given bus and wake up devices on it
+ * pci_resume_bus - Walk given bus and runtime resume devices on it
  * @bus: Top bus of the subtree to walk.
  */
-void pci_wakeup_bus(struct pci_bus *bus)
+void pci_resume_bus(struct pci_bus *bus)
 {
 	if (bus)
-		pci_walk_bus(bus, pci_wakeup, NULL);
+		pci_walk_bus(bus, pci_resume_one, NULL);
 }
 
 static int pci_dev_wait(struct pci_dev *dev, char *reset_type, int timeout)
@@ -1256,7 +1251,7 @@ int pci_power_up(struct pci_dev *dev)
 		 * may be powered on into D0uninitialized state, resume them to
 		 * give them a chance to suspend again
 		 */
-		pci_wakeup_bus(dev->subordinate);
+		pci_resume_bus(dev->subordinate);
 	}
 
 	return pci_raw_set_power_state(dev, PCI_D0);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 22207a79762c..9256ef2e4327 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1271,7 +1271,7 @@ bool pci_dev_run_wake(struct pci_dev *dev);
 void pci_d3cold_enable(struct pci_dev *dev);
 void pci_d3cold_disable(struct pci_dev *dev);
 bool pcie_relaxed_ordering_enabled(struct pci_dev *dev);
-void pci_wakeup_bus(struct pci_bus *bus);
+void pci_resume_bus(struct pci_bus *bus);
 void pci_bus_set_current_state(struct pci_bus *bus, pci_power_t state);
 
 /* For use by arch with custom probe code */
-- 
cgit v1.2.3


From ed9b25d1970a4787ac6a39c2091e63b127ecbfc1 Mon Sep 17 00:00:00 2001
From: Serge Hallyn <shallyn@cisco.com>
Date: Sun, 15 Nov 2020 21:55:31 -0600
Subject: [SECURITY] fix namespaced fscaps when !CONFIG_SECURITY
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Namespaced file capabilities were introduced in 8db6c34f1dbc .
When userspace reads an xattr for a namespaced capability, a
virtualized representation of it is returned if the caller is
in a user namespace owned by the capability's owning rootid.
The function which performs this virtualization was not hooked
up if CONFIG_SECURITY=n.  Therefore in that case the original
xattr was shown instead of the virtualized one.

To test this using libcap-bin (*1),

$ v=$(mktemp)
$ unshare -Ur setcap cap_sys_admin-eip $v
$ unshare -Ur setcap -v cap_sys_admin-eip $v
/tmp/tmp.lSiIFRvt8Y: OK

"setcap -v" verifies the values instead of setting them, and
will check whether the rootid value is set.  Therefore, with
this bug un-fixed, and with CONFIG_SECURITY=n, setcap -v will
fail:

$ v=$(mktemp)
$ unshare -Ur setcap cap_sys_admin=eip $v
$ unshare -Ur setcap -v cap_sys_admin=eip $v
nsowner[got=1000, want=0],/tmp/tmp.HHDiOOl9fY differs in []

Fix this bug by calling cap_inode_getsecurity() in
security_inode_getsecurity() instead of returning
-EOPNOTSUPP, when CONFIG_SECURITY=n.

*1 - note, if libcap is too old for getcap to have the '-n'
option, then use verify-caps instead.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=209689
Cc: Hervé Guillemet <herve@guillemet.org>
Acked-by: Casey Schaufler <casey@schaufler-ca.com>
Signed-off-by: Serge Hallyn <shallyn@cisco.com>
Signed-off-by: Andrew G. Morgan <morgan@kernel.org>
Signed-off-by: James Morris <jamorris@linux.microsoft.com>
---
 include/linux/security.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/security.h b/include/linux/security.h
index 0a0a03b36a3b..2befc0a25eb3 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -864,7 +864,7 @@ static inline int security_inode_killpriv(struct dentry *dentry)
 
 static inline int security_inode_getsecurity(struct inode *inode, const char *name, void **buffer, bool alloc)
 {
-	return -EOPNOTSUPP;
+	return cap_inode_getsecurity(inode, name, buffer, alloc);
 }
 
 static inline int security_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags)
-- 
cgit v1.2.3


From 507b460f814458605c47b0ed03c11e49a712fc08 Mon Sep 17 00:00:00 2001
From: Sean V Kelley <sean.v.kelley@intel.com>
Date: Fri, 20 Nov 2020 16:10:32 -0800
Subject: PCI/ERR: Add pcie_link_rcec() to associate RCiEPs

A Root Complex Event Collector terminates error and PME messages from
associated RCiEPs.

Use the RCEC Endpoint Association Extended Capability to identify
associated RCiEPs. Link the associated RCiEPs as the RCECs are enumerated.

Co-developed-by: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
Link: https://lore.kernel.org/r/20201121001036.8560-12-sean.v.kelley@intel.com
Tested-by: Jonathan Cameron <Jonathan.Cameron@huawei.com> # non-native/no RCEC
Signed-off-by: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
Signed-off-by: Sean V Kelley <sean.v.kelley@intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/pci/pci.h              |  2 +
 drivers/pci/pcie/portdrv_pci.c |  3 ++
 drivers/pci/pcie/rcec.c        | 94 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/pci.h            |  1 +
 4 files changed, 100 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 3c4570a3058f..ae2ee4df1cff 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -472,9 +472,11 @@ static inline void pci_dpc_init(struct pci_dev *pdev) {}
 #ifdef CONFIG_PCIEPORTBUS
 void pci_rcec_init(struct pci_dev *dev);
 void pci_rcec_exit(struct pci_dev *dev);
+void pcie_link_rcec(struct pci_dev *rcec);
 #else
 static inline void pci_rcec_init(struct pci_dev *dev) {}
 static inline void pci_rcec_exit(struct pci_dev *dev) {}
+static inline void pcie_link_rcec(struct pci_dev *rcec) {}
 #endif
 
 #ifdef CONFIG_PCI_ATS
diff --git a/drivers/pci/pcie/portdrv_pci.c b/drivers/pci/pcie/portdrv_pci.c
index ff9517ee92b3..0b250bc5f405 100644
--- a/drivers/pci/pcie/portdrv_pci.c
+++ b/drivers/pci/pcie/portdrv_pci.c
@@ -111,6 +111,9 @@ static int pcie_portdrv_probe(struct pci_dev *dev,
 	     (type != PCI_EXP_TYPE_RC_EC)))
 		return -ENODEV;
 
+	if (type == PCI_EXP_TYPE_RC_EC)
+		pcie_link_rcec(dev);
+
 	status = pcie_port_device_register(dev);
 	if (status)
 		return status;
diff --git a/drivers/pci/pcie/rcec.c b/drivers/pci/pcie/rcec.c
index 038e9d706d5f..cdec277cbd62 100644
--- a/drivers/pci/pcie/rcec.c
+++ b/drivers/pci/pcie/rcec.c
@@ -15,6 +15,100 @@
 
 #include "../pci.h"
 
+struct walk_rcec_data {
+	struct pci_dev *rcec;
+	int (*user_callback)(struct pci_dev *dev, void *data);
+	void *user_data;
+};
+
+static bool rcec_assoc_rciep(struct pci_dev *rcec, struct pci_dev *rciep)
+{
+	unsigned long bitmap = rcec->rcec_ea->bitmap;
+	unsigned int devn;
+
+	/* An RCiEP found on a different bus in range */
+	if (rcec->bus->number != rciep->bus->number)
+		return true;
+
+	/* Same bus, so check bitmap */
+	for_each_set_bit(devn, &bitmap, 32)
+		if (devn == rciep->devfn)
+			return true;
+
+	return false;
+}
+
+static int link_rcec_helper(struct pci_dev *dev, void *data)
+{
+	struct walk_rcec_data *rcec_data = data;
+	struct pci_dev *rcec = rcec_data->rcec;
+
+	if ((pci_pcie_type(dev) == PCI_EXP_TYPE_RC_END) &&
+	    rcec_assoc_rciep(rcec, dev)) {
+		dev->rcec = rcec;
+		pci_dbg(dev, "PME & error events signaled via %s\n",
+			pci_name(rcec));
+	}
+
+	return 0;
+}
+
+static void walk_rcec(int (*cb)(struct pci_dev *dev, void *data),
+		      void *userdata)
+{
+	struct walk_rcec_data *rcec_data = userdata;
+	struct pci_dev *rcec = rcec_data->rcec;
+	u8 nextbusn, lastbusn;
+	struct pci_bus *bus;
+	unsigned int bnr;
+
+	if (!rcec->rcec_ea)
+		return;
+
+	/* Walk own bus for bitmap based association */
+	pci_walk_bus(rcec->bus, cb, rcec_data);
+
+	nextbusn = rcec->rcec_ea->nextbusn;
+	lastbusn = rcec->rcec_ea->lastbusn;
+
+	/* All RCiEP devices are on the same bus as the RCEC */
+	if (nextbusn == 0xff && lastbusn == 0x00)
+		return;
+
+	for (bnr = nextbusn; bnr <= lastbusn; bnr++) {
+		/* No association indicated (PCIe 5.0-1, 7.9.10.3) */
+		if (bnr == rcec->bus->number)
+			continue;
+
+		bus = pci_find_bus(pci_domain_nr(rcec->bus), bnr);
+		if (!bus)
+			continue;
+
+		/* Find RCiEP devices on the given bus ranges */
+		pci_walk_bus(bus, cb, rcec_data);
+	}
+}
+
+/**
+ * pcie_link_rcec - Link RCiEP devices associated with RCEC.
+ * @rcec: RCEC whose RCiEP devices should be linked.
+ *
+ * Link the given RCEC to each RCiEP device found.
+ */
+void pcie_link_rcec(struct pci_dev *rcec)
+{
+	struct walk_rcec_data rcec_data;
+
+	if (!rcec->rcec_ea)
+		return;
+
+	rcec_data.rcec = rcec;
+	rcec_data.user_callback = NULL;
+	rcec_data.user_data = NULL;
+
+	walk_rcec(link_rcec_helper, &rcec_data);
+}
+
 void pci_rcec_init(struct pci_dev *dev)
 {
 	struct rcec_ea *rcec_ea;
diff --git a/include/linux/pci.h b/include/linux/pci.h
index f8c927fd0602..7c7d2d23e8a3 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -330,6 +330,7 @@ struct pci_dev {
 #endif
 #ifdef CONFIG_PCIEPORTBUS
 	struct rcec_ea	*rcec_ea;	/* RCEC cached endpoint association */
+	struct pci_dev  *rcec;          /* Associated RCEC device */
 #endif
 	u8		pcie_cap;	/* PCIe capability offset */
 	u8		msi_cap;	/* MSI capability offset */
-- 
cgit v1.2.3


From 601c10c89cbb32b9123d8716d193e6d1a8e5300d Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Mon, 5 Oct 2020 11:13:56 +0300
Subject: net/mlx5: Delete custom device management logic

After conversion to use auxiliary bus, all custom device management is
not needed anymore, delete it.

Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/dev.c      | 288 ++-------------------
 drivers/net/ethernet/mellanox/mlx5/core/lag.c      |  18 --
 .../net/ethernet/mellanox/mlx5/core/mlx5_core.h    |   8 -
 include/linux/mlx5/driver.h                        |  22 --
 4 files changed, 18 insertions(+), 318 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index 843a8579d8c8..3a81c2f1971b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -35,24 +35,10 @@
 #include <linux/mlx5/mlx5_ifc_vdpa.h>
 #include "mlx5_core.h"
 
-static LIST_HEAD(intf_list);
-static LIST_HEAD(mlx5_dev_list);
 /* intf dev list mutex */
 static DEFINE_MUTEX(mlx5_intf_mutex);
 static DEFINE_IDA(mlx5_adev_ida);
 
-struct mlx5_device_context {
-	struct list_head	list;
-	struct mlx5_interface  *intf;
-	void		       *context;
-	unsigned long		state;
-};
-
-enum {
-	MLX5_INTERFACE_ADDED,
-	MLX5_INTERFACE_ATTACHED,
-};
-
 static bool is_eth_rep_supported(struct mlx5_core_dev *dev)
 {
 	if (!IS_ENABLED(CONFIG_MLX5_ESWITCH))
@@ -204,11 +190,22 @@ static bool is_ib_supported(struct mlx5_core_dev *dev)
 	return true;
 }
 
+enum {
+	MLX5_INTERFACE_PROTOCOL_ETH_REP,
+	MLX5_INTERFACE_PROTOCOL_ETH,
+
+	MLX5_INTERFACE_PROTOCOL_IB_REP,
+	MLX5_INTERFACE_PROTOCOL_MPIB,
+	MLX5_INTERFACE_PROTOCOL_IB,
+
+	MLX5_INTERFACE_PROTOCOL_VNET,
+};
+
 static const struct mlx5_adev_device {
 	const char *suffix;
 	bool (*is_supported)(struct mlx5_core_dev *dev);
 } mlx5_adev_devices[] = {
-	[MLX5_INTERFACE_PROTOCOL_VDPA] = { .suffix = "vnet",
+	[MLX5_INTERFACE_PROTOCOL_VNET] = { .suffix = "vnet",
 					   .is_supported = &is_vnet_supported },
 	[MLX5_INTERFACE_PROTOCOL_IB] = { .suffix = "rdma",
 					 .is_supported = &is_ib_supported },
@@ -251,90 +248,6 @@ void mlx5_adev_cleanup(struct mlx5_core_dev *dev)
 	kfree(priv->adev);
 }
 
-void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv)
-{
-	struct mlx5_device_context *dev_ctx;
-	struct mlx5_core_dev *dev = container_of(priv, struct mlx5_core_dev, priv);
-
-	if (!mlx5_lag_intf_add(intf, priv))
-		return;
-
-	dev_ctx = kzalloc(sizeof(*dev_ctx), GFP_KERNEL);
-	if (!dev_ctx)
-		return;
-
-	dev_ctx->intf = intf;
-
-	dev_ctx->context = intf->add(dev);
-	if (dev_ctx->context) {
-		set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state);
-		if (intf->attach)
-			set_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state);
-
-		spin_lock_irq(&priv->ctx_lock);
-		list_add_tail(&dev_ctx->list, &priv->ctx_list);
-		spin_unlock_irq(&priv->ctx_lock);
-	}
-
-	if (!dev_ctx->context)
-		kfree(dev_ctx);
-}
-
-static struct mlx5_device_context *mlx5_get_device(struct mlx5_interface *intf,
-						   struct mlx5_priv *priv)
-{
-	struct mlx5_device_context *dev_ctx;
-
-	list_for_each_entry(dev_ctx, &priv->ctx_list, list)
-		if (dev_ctx->intf == intf)
-			return dev_ctx;
-	return NULL;
-}
-
-void mlx5_remove_device(struct mlx5_interface *intf, struct mlx5_priv *priv)
-{
-	struct mlx5_device_context *dev_ctx;
-	struct mlx5_core_dev *dev = container_of(priv, struct mlx5_core_dev, priv);
-
-	dev_ctx = mlx5_get_device(intf, priv);
-	if (!dev_ctx)
-		return;
-
-	spin_lock_irq(&priv->ctx_lock);
-	list_del(&dev_ctx->list);
-	spin_unlock_irq(&priv->ctx_lock);
-
-	if (test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state))
-		intf->remove(dev, dev_ctx->context);
-
-	kfree(dev_ctx);
-}
-
-static void mlx5_attach_interface(struct mlx5_interface *intf, struct mlx5_priv *priv)
-{
-	struct mlx5_device_context *dev_ctx;
-	struct mlx5_core_dev *dev = container_of(priv, struct mlx5_core_dev, priv);
-
-	dev_ctx = mlx5_get_device(intf, priv);
-	if (!dev_ctx)
-		return;
-
-	if (intf->attach) {
-		if (test_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state))
-			return;
-		if (intf->attach(dev, dev_ctx->context))
-			return;
-		set_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state);
-	} else {
-		if (test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state))
-			return;
-		dev_ctx->context = intf->add(dev);
-		if (!dev_ctx->context)
-			return;
-		set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state);
-	}
-}
-
 static void adev_release(struct device *dev)
 {
 	struct mlx5_adev *mlx5_adev =
@@ -390,7 +303,6 @@ int mlx5_attach_device(struct mlx5_core_dev *dev)
 	struct mlx5_priv *priv = &dev->priv;
 	struct auxiliary_device *adev;
 	struct auxiliary_driver *adrv;
-	struct mlx5_interface *intf;
 	int ret = 0, i;
 
 	mutex_lock(&mlx5_intf_mutex);
@@ -423,41 +335,15 @@ int mlx5_attach_device(struct mlx5_core_dev *dev)
 			break;
 		}
 	}
-
-	list_for_each_entry(intf, &intf_list, list)
-		mlx5_attach_interface(intf, priv);
 	mutex_unlock(&mlx5_intf_mutex);
 	return ret;
 }
 
-static void mlx5_detach_interface(struct mlx5_interface *intf, struct mlx5_priv *priv)
-{
-	struct mlx5_device_context *dev_ctx;
-	struct mlx5_core_dev *dev = container_of(priv, struct mlx5_core_dev, priv);
-
-	dev_ctx = mlx5_get_device(intf, priv);
-	if (!dev_ctx)
-		return;
-
-	if (intf->detach) {
-		if (!test_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state))
-			return;
-		intf->detach(dev, dev_ctx->context);
-		clear_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state);
-	} else {
-		if (!test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state))
-			return;
-		intf->remove(dev, dev_ctx->context);
-		clear_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state);
-	}
-}
-
 void mlx5_detach_device(struct mlx5_core_dev *dev)
 {
 	struct mlx5_priv *priv = &dev->priv;
 	struct auxiliary_device *adev;
 	struct auxiliary_driver *adrv;
-	struct mlx5_interface *intf;
 	pm_message_t pm = {};
 	int i;
 
@@ -477,30 +363,11 @@ void mlx5_detach_device(struct mlx5_core_dev *dev)
 		del_adev(&priv->adev[i]->adev);
 		priv->adev[i] = NULL;
 	}
-
-	list_for_each_entry(intf, &intf_list, list)
-		mlx5_detach_interface(intf, priv);
 	mutex_unlock(&mlx5_intf_mutex);
 }
 
-bool mlx5_device_registered(struct mlx5_core_dev *dev)
-{
-	struct mlx5_priv *priv;
-	bool found = false;
-
-	mutex_lock(&mlx5_intf_mutex);
-	list_for_each_entry(priv, &mlx5_dev_list, dev_list)
-		if (priv == &dev->priv)
-			found = true;
-	mutex_unlock(&mlx5_intf_mutex);
-
-	return found;
-}
-
 int mlx5_register_device(struct mlx5_core_dev *dev)
 {
-	struct mlx5_priv *priv = &dev->priv;
-	struct mlx5_interface *intf;
 	int ret;
 
 	mutex_lock(&mlx5_intf_mutex);
@@ -508,65 +375,19 @@ int mlx5_register_device(struct mlx5_core_dev *dev)
 	ret = mlx5_rescan_drivers_locked(dev);
 	mutex_unlock(&mlx5_intf_mutex);
 	if (ret)
-		goto add_err;
-
-	mutex_lock(&mlx5_intf_mutex);
-	list_add_tail(&priv->dev_list, &mlx5_dev_list);
-	list_for_each_entry(intf, &intf_list, list)
-		mlx5_add_device(intf, priv);
-	mutex_unlock(&mlx5_intf_mutex);
-
-	return 0;
+		mlx5_unregister_device(dev);
 
-add_err:
-	mlx5_unregister_device(dev);
 	return ret;
 }
 
 void mlx5_unregister_device(struct mlx5_core_dev *dev)
 {
-	struct mlx5_priv *priv = &dev->priv;
-	struct mlx5_interface *intf;
-
 	mutex_lock(&mlx5_intf_mutex);
-	list_for_each_entry_reverse(intf, &intf_list, list)
-		mlx5_remove_device(intf, priv);
-	list_del(&priv->dev_list);
-
 	dev->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV;
 	mlx5_rescan_drivers_locked(dev);
 	mutex_unlock(&mlx5_intf_mutex);
 }
 
-int mlx5_register_interface(struct mlx5_interface *intf)
-{
-	struct mlx5_priv *priv;
-
-	if (!intf->add || !intf->remove)
-		return -EINVAL;
-
-	mutex_lock(&mlx5_intf_mutex);
-	list_add_tail(&intf->list, &intf_list);
-	list_for_each_entry(priv, &mlx5_dev_list, dev_list)
-		mlx5_add_device(intf, priv);
-	mutex_unlock(&mlx5_intf_mutex);
-
-	return 0;
-}
-EXPORT_SYMBOL(mlx5_register_interface);
-
-void mlx5_unregister_interface(struct mlx5_interface *intf)
-{
-	struct mlx5_priv *priv;
-
-	mutex_lock(&mlx5_intf_mutex);
-	list_for_each_entry(priv, &mlx5_dev_list, dev_list)
-		mlx5_remove_device(intf, priv);
-	list_del(&intf->list);
-	mutex_unlock(&mlx5_intf_mutex);
-}
-EXPORT_SYMBOL(mlx5_unregister_interface);
-
 static int add_drivers(struct mlx5_core_dev *dev)
 {
 	struct mlx5_priv *priv = &dev->priv;
@@ -638,59 +459,6 @@ int mlx5_rescan_drivers_locked(struct mlx5_core_dev *dev)
 	return add_drivers(dev);
 }
 
-/* Must be called with intf_mutex held */
-static bool mlx5_has_added_dev_by_protocol(struct mlx5_core_dev *mdev, int protocol)
-{
-	struct mlx5_device_context *dev_ctx;
-	struct mlx5_interface *intf;
-	bool found = false;
-
-	list_for_each_entry(intf, &intf_list, list) {
-		if (intf->protocol == protocol) {
-			dev_ctx = mlx5_get_device(intf, &mdev->priv);
-			if (dev_ctx && test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state))
-				found = true;
-			break;
-		}
-	}
-
-	return found;
-}
-
-void mlx5_reload_interface(struct mlx5_core_dev *mdev, int protocol)
-{
-	mutex_lock(&mlx5_intf_mutex);
-	if (mlx5_has_added_dev_by_protocol(mdev, protocol)) {
-		mlx5_remove_dev_by_protocol(mdev, protocol);
-		mlx5_add_dev_by_protocol(mdev, protocol);
-	}
-	mutex_unlock(&mlx5_intf_mutex);
-}
-
-/* Must be called with intf_mutex held */
-void mlx5_add_dev_by_protocol(struct mlx5_core_dev *dev, int protocol)
-{
-	struct mlx5_interface *intf;
-
-	list_for_each_entry(intf, &intf_list, list)
-		if (intf->protocol == protocol) {
-			mlx5_add_device(intf, &dev->priv);
-			break;
-		}
-}
-
-/* Must be called with intf_mutex held */
-void mlx5_remove_dev_by_protocol(struct mlx5_core_dev *dev, int protocol)
-{
-	struct mlx5_interface *intf;
-
-	list_for_each_entry(intf, &intf_list, list)
-		if (intf->protocol == protocol) {
-			mlx5_remove_device(intf, &dev->priv);
-			break;
-		}
-}
-
 static u32 mlx5_gen_pci_id(const struct mlx5_core_dev *dev)
 {
 	return (u32)((pci_domain_nr(dev->pdev->bus) << 16) |
@@ -722,45 +490,25 @@ static int next_phys_dev(struct device *dev, const void *data)
  */
 struct mlx5_core_dev *mlx5_get_next_phys_dev(struct mlx5_core_dev *dev)
 {
-	struct mlx5_core_dev *res = NULL;
-	struct mlx5_core_dev *tmp_dev;
 	struct auxiliary_device *adev;
 	struct mlx5_adev *madev;
-	struct mlx5_priv *priv;
-	u32 pci_id;
 
 	if (!mlx5_core_is_pf(dev))
 		return NULL;
 
 	adev = auxiliary_find_device(NULL, dev, &next_phys_dev);
-	if (adev) {
-		madev = container_of(adev, struct mlx5_adev, adev);
-
-		put_device(&adev->dev);
-		return madev->mdev;
-	}
-
-	pci_id = mlx5_gen_pci_id(dev);
-	list_for_each_entry(priv, &mlx5_dev_list, dev_list) {
-		tmp_dev = container_of(priv, struct mlx5_core_dev, priv);
-		if (!mlx5_core_is_pf(tmp_dev))
-			continue;
-
-		if ((dev != tmp_dev) && (mlx5_gen_pci_id(tmp_dev) == pci_id)) {
-			res = tmp_dev;
-			break;
-		}
-	}
+	if (!adev)
+		return NULL;
 
-	return res;
+	madev = container_of(adev, struct mlx5_adev, adev);
+	put_device(&adev->dev);
+	return madev->mdev;
 }
 
-
 void mlx5_dev_list_lock(void)
 {
 	mutex_lock(&mlx5_intf_mutex);
 }
-
 void mlx5_dev_list_unlock(void)
 {
 	mutex_unlock(&mlx5_intf_mutex);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index 325f32b9525c..f3d45ef082cd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -749,24 +749,6 @@ unlock:
 }
 EXPORT_SYMBOL(mlx5_lag_get_slave_port);
 
-bool mlx5_lag_intf_add(struct mlx5_interface *intf, struct mlx5_priv *priv)
-{
-	struct mlx5_core_dev *dev = container_of(priv, struct mlx5_core_dev,
-						 priv);
-	struct mlx5_lag *ldev;
-
-	if (intf->protocol != MLX5_INTERFACE_PROTOCOL_IB)
-		return true;
-
-	ldev = mlx5_lag_dev_get(dev);
-	if (!ldev || !__mlx5_lag_is_roce(ldev) ||
-	    ldev->pf[MLX5_LAG_P1].dev == dev)
-		return true;
-
-	/* If bonded, we do not add an IB device for PF1. */
-	return false;
-}
-
 int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
 				 u64 *values,
 				 int num_counters,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index f7e44e04d465..dd7312621d0d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -183,22 +183,15 @@ void mlx5_adev_idx_free(int idx);
 void mlx5_adev_cleanup(struct mlx5_core_dev *dev);
 int mlx5_adev_init(struct mlx5_core_dev *dev);
 
-void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv);
-void mlx5_remove_device(struct mlx5_interface *intf, struct mlx5_priv *priv);
 int mlx5_attach_device(struct mlx5_core_dev *dev);
 void mlx5_detach_device(struct mlx5_core_dev *dev);
-bool mlx5_device_registered(struct mlx5_core_dev *dev);
 int mlx5_register_device(struct mlx5_core_dev *dev);
 void mlx5_unregister_device(struct mlx5_core_dev *dev);
-void mlx5_add_dev_by_protocol(struct mlx5_core_dev *dev, int protocol);
-void mlx5_remove_dev_by_protocol(struct mlx5_core_dev *dev, int protocol);
 struct mlx5_core_dev *mlx5_get_next_phys_dev(struct mlx5_core_dev *dev);
 void mlx5_dev_list_lock(void);
 void mlx5_dev_list_unlock(void);
 int mlx5_dev_list_trylock(void);
 
-bool mlx5_lag_intf_add(struct mlx5_interface *intf, struct mlx5_priv *priv);
-
 int mlx5_query_mtpps(struct mlx5_core_dev *dev, u32 *mtpps, u32 mtpps_size);
 int mlx5_set_mtpps(struct mlx5_core_dev *mdev, u32 *mtpps, u32 mtpps_size);
 int mlx5_query_mtppse(struct mlx5_core_dev *mdev, u8 pin, u8 *arm, u8 *mode);
@@ -248,7 +241,6 @@ static inline int mlx5_rescan_drivers(struct mlx5_core_dev *dev)
 	return ret;
 }
 
-void mlx5_reload_interface(struct mlx5_core_dev *mdev, int protocol);
 void mlx5_lag_update(struct mlx5_core_dev *dev);
 
 enum {
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index e31c72693bcf..54299305a2c8 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1076,28 +1076,6 @@ enum {
 	MAX_MR_CACHE_ENTRIES
 };
 
-enum {
-	MLX5_INTERFACE_PROTOCOL_ETH_REP,
-	MLX5_INTERFACE_PROTOCOL_ETH,
-
-	MLX5_INTERFACE_PROTOCOL_IB_REP,
-	MLX5_INTERFACE_PROTOCOL_MPIB,
-	MLX5_INTERFACE_PROTOCOL_IB,
-
-	MLX5_INTERFACE_PROTOCOL_VDPA,
-};
-
-struct mlx5_interface {
-	void *			(*add)(struct mlx5_core_dev *dev);
-	void			(*remove)(struct mlx5_core_dev *dev, void *context);
-	int			(*attach)(struct mlx5_core_dev *dev, void *context);
-	void			(*detach)(struct mlx5_core_dev *dev, void *context);
-	int			protocol;
-	struct list_head	list;
-};
-
-int mlx5_register_interface(struct mlx5_interface *intf);
-void mlx5_unregister_interface(struct mlx5_interface *intf);
 int mlx5_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb);
 int mlx5_notifier_unregister(struct mlx5_core_dev *dev, struct notifier_block *nb);
 int mlx5_eq_notifier_register(struct mlx5_core_dev *dev, struct mlx5_nb *nb);
-- 
cgit v1.2.3


From e87114022e1de734de0552e6b4f2dc5309efa27a Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Sat, 10 Oct 2020 11:57:26 +0300
Subject: net/mlx5: Simplify eswitch mode check

Provide mlx5_core device instead of "priv" pointer while checking
eswith mode.

Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/infiniband/hw/mlx5/counters.c             | 7 -------
 drivers/infiniband/hw/mlx5/ib_rep.c               | 5 -----
 drivers/infiniband/hw/mlx5/ib_rep.h               | 6 ------
 drivers/net/ethernet/mellanox/mlx5/core/dev.c     | 4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/devlink.c | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c   | 8 +++-----
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 4 +++-
 include/linux/mlx5/eswitch.h                      | 8 ++++++--
 9 files changed, 16 insertions(+), 30 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/infiniband/hw/mlx5/counters.c b/drivers/infiniband/hw/mlx5/counters.c
index 70c8fd67ee2f..084652e2b15a 100644
--- a/drivers/infiniband/hw/mlx5/counters.c
+++ b/drivers/infiniband/hw/mlx5/counters.c
@@ -138,13 +138,6 @@ static int mlx5_ib_create_counters(struct ib_counters *counters,
 }
 
 
-static bool is_mdev_switchdev_mode(const struct mlx5_core_dev *mdev)
-{
-	return MLX5_ESWITCH_MANAGER(mdev) &&
-	       mlx5_ib_eswitch_mode(mdev->priv.eswitch) ==
-		       MLX5_ESWITCH_OFFLOADS;
-}
-
 static const struct mlx5_ib_counters *get_counters(struct mlx5_ib_dev *dev,
 						   u8 port_num)
 {
diff --git a/drivers/infiniband/hw/mlx5/ib_rep.c b/drivers/infiniband/hw/mlx5/ib_rep.c
index 3d889a70130b..571b7a0f9188 100644
--- a/drivers/infiniband/hw/mlx5/ib_rep.c
+++ b/drivers/infiniband/hw/mlx5/ib_rep.c
@@ -102,11 +102,6 @@ static const struct mlx5_eswitch_rep_ops rep_ops = {
 	.get_proto_dev = mlx5_ib_vport_get_proto_dev,
 };
 
-u8 mlx5_ib_eswitch_mode(struct mlx5_eswitch *esw)
-{
-	return mlx5_eswitch_mode(esw);
-}
-
 struct mlx5_ib_dev *mlx5_ib_get_rep_ibdev(struct mlx5_eswitch *esw,
 					  u16 vport_num)
 {
diff --git a/drivers/infiniband/hw/mlx5/ib_rep.h b/drivers/infiniband/hw/mlx5/ib_rep.h
index 94bf51ddd422..93f562735e89 100644
--- a/drivers/infiniband/hw/mlx5/ib_rep.h
+++ b/drivers/infiniband/hw/mlx5/ib_rep.h
@@ -12,7 +12,6 @@
 extern const struct mlx5_ib_profile raw_eth_profile;
 
 #ifdef CONFIG_MLX5_ESWITCH
-u8 mlx5_ib_eswitch_mode(struct mlx5_eswitch *esw);
 struct mlx5_ib_dev *mlx5_ib_get_rep_ibdev(struct mlx5_eswitch *esw,
 					  u16 vport_num);
 struct mlx5_ib_dev *mlx5_ib_get_uplink_ibdev(struct mlx5_eswitch *esw);
@@ -26,11 +25,6 @@ struct mlx5_flow_handle *create_flow_rule_vport_sq(struct mlx5_ib_dev *dev,
 struct net_device *mlx5_ib_get_rep_netdev(struct mlx5_eswitch *esw,
 					  u16 vport_num);
 #else /* CONFIG_MLX5_ESWITCH */
-static inline u8 mlx5_ib_eswitch_mode(struct mlx5_eswitch *esw)
-{
-	return MLX5_ESWITCH_NONE;
-}
-
 static inline
 struct mlx5_ib_dev *mlx5_ib_get_rep_ibdev(struct mlx5_eswitch *esw,
 					  u16 vport_num)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index 3a81c2f1971b..b051417ede67 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -47,7 +47,7 @@ static bool is_eth_rep_supported(struct mlx5_core_dev *dev)
 	if (!MLX5_ESWITCH_MANAGER(dev))
 		return false;
 
-	if (mlx5_eswitch_mode(dev->priv.eswitch) != MLX5_ESWITCH_OFFLOADS)
+	if (!is_mdev_switchdev_mode(dev))
 		return false;
 
 	return true;
@@ -144,7 +144,7 @@ static bool is_ib_rep_supported(struct mlx5_core_dev *dev)
 	if (!MLX5_ESWITCH_MANAGER(dev))
 		return false;
 
-	if (mlx5_eswitch_mode(dev->priv.eswitch) != MLX5_ESWITCH_OFFLOADS)
+	if (!is_mdev_switchdev_mode(dev))
 		return false;
 
 	if (mlx5_core_mp_enabled(dev))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index 1a351e2f6ace..aeffb6b135ee 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -221,7 +221,7 @@ static int mlx5_devlink_fs_mode_validate(struct devlink *devlink, u32 id,
 		u8 eswitch_mode;
 		bool smfs_cap;
 
-		eswitch_mode = mlx5_eswitch_mode(dev->priv.eswitch);
+		eswitch_mode = mlx5_eswitch_mode(dev);
 		smfs_cap = mlx5_fs_dr_is_supported(dev);
 
 		if (!smfs_cap) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 25490d1e3216..cd0e2f451342 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3135,7 +3135,7 @@ static void mlx5e_modify_admin_state(struct mlx5_core_dev *mdev,
 
 	mlx5_set_port_admin_status(mdev, state);
 
-	if (!MLX5_ESWITCH_MANAGER(mdev) ||  mlx5_eswitch_mode(esw) == MLX5_ESWITCH_OFFLOADS)
+	if (mlx5_eswitch_mode(mdev) != MLX5_ESWITCH_LEGACY)
 		return;
 
 	if (state == MLX5_PORT_UP)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index ce710f22b1ff..4cdf834fa74a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -271,8 +271,6 @@ mlx5e_tc_match_to_reg_set(struct mlx5_core_dev *mdev,
 	return 0;
 }
 
-#define esw_offloads_mode(esw) (mlx5_eswitch_mode(esw) == MLX5_ESWITCH_OFFLOADS)
-
 static struct mlx5_tc_ct_priv *
 get_ct_priv(struct mlx5e_priv *priv)
 {
@@ -280,7 +278,7 @@ get_ct_priv(struct mlx5e_priv *priv)
 	struct mlx5_rep_uplink_priv *uplink_priv;
 	struct mlx5e_rep_priv *uplink_rpriv;
 
-	if (esw_offloads_mode(esw)) {
+	if (is_mdev_switchdev_mode(priv->mdev)) {
 		uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
 		uplink_priv = &uplink_rpriv->uplink_priv;
 
@@ -297,7 +295,7 @@ mlx5_tc_rule_insert(struct mlx5e_priv *priv,
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 
-	if (esw_offloads_mode(esw))
+	if (is_mdev_switchdev_mode(priv->mdev))
 		return mlx5_eswitch_add_offloaded_rule(esw, spec, attr);
 
 	return	mlx5e_add_offloaded_nic_rule(priv, spec, attr);
@@ -310,7 +308,7 @@ mlx5_tc_rule_delete(struct mlx5e_priv *priv,
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 
-	if (esw_offloads_mode(esw)) {
+	if (is_mdev_switchdev_mode(priv->mdev)) {
 		mlx5_eswitch_del_offloaded_rule(esw, rule, attr);
 
 		return;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index cb06b6e53fdd..c23dd95e634d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -2436,8 +2436,10 @@ free_out:
 	return err;
 }
 
-u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw)
+u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev)
 {
+	struct mlx5_eswitch *esw = dev->priv.eswitch;
+
 	return ESW_ALLOWED(esw) ? esw->mode : MLX5_ESWITCH_NONE;
 }
 EXPORT_SYMBOL_GPL(mlx5_eswitch_mode);
diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h
index b0ae8020f13e..29fd832950e0 100644
--- a/include/linux/mlx5/eswitch.h
+++ b/include/linux/mlx5/eswitch.h
@@ -96,10 +96,10 @@ static inline u32 mlx5_eswitch_get_vport_metadata_mask(void)
 
 u32 mlx5_eswitch_get_vport_metadata_for_match(struct mlx5_eswitch *esw,
 					      u16 vport_num);
-u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw);
+u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev);
 #else  /* CONFIG_MLX5_ESWITCH */
 
-static inline u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw)
+static inline u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev)
 {
 	return MLX5_ESWITCH_NONE;
 }
@@ -136,4 +136,8 @@ mlx5_eswitch_get_vport_metadata_mask(void)
 }
 #endif /* CONFIG_MLX5_ESWITCH */
 
+static inline bool is_mdev_switchdev_mode(struct mlx5_core_dev *dev)
+{
+	return mlx5_eswitch_mode(dev) == MLX5_ESWITCH_OFFLOADS;
+}
 #endif
-- 
cgit v1.2.3


From e91d8d78237de8d7120c320b3645b7100848f24d Mon Sep 17 00:00:00 2001
From: Minchan Kim <minchan@kernel.org>
Date: Sat, 5 Dec 2020 22:14:51 -0800
Subject: mm/zsmalloc.c: drop ZSMALLOC_PGTABLE_MAPPING

While I was doing zram testing, I found sometimes decompression failed
since the compression buffer was corrupted.  With investigation, I found
below commit calls cond_resched unconditionally so it could make a
problem in atomic context if the task is reschedule.

  BUG: sleeping function called from invalid context at mm/vmalloc.c:108
  in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 946, name: memhog
  3 locks held by memhog/946:
   #0: ffff9d01d4b193e8 (&mm->mmap_lock#2){++++}-{4:4}, at: __mm_populate+0x103/0x160
   #1: ffffffffa3d53de0 (fs_reclaim){+.+.}-{0:0}, at: __alloc_pages_slowpath.constprop.0+0xa98/0x1160
   #2: ffff9d01d56b8110 (&zspage->lock){.+.+}-{3:3}, at: zs_map_object+0x8e/0x1f0
  CPU: 0 PID: 946 Comm: memhog Not tainted 5.9.3-00011-gc5bfc0287345-dirty #316
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1 04/01/2014
  Call Trace:
    unmap_kernel_range_noflush+0x2eb/0x350
    unmap_kernel_range+0x14/0x30
    zs_unmap_object+0xd5/0xe0
    zram_bvec_rw.isra.0+0x38c/0x8e0
    zram_rw_page+0x90/0x101
    bdev_write_page+0x92/0xe0
    __swap_writepage+0x94/0x4a0
    pageout+0xe3/0x3a0
    shrink_page_list+0xb94/0xd60
    shrink_inactive_list+0x158/0x460

We can fix this by removing the ZSMALLOC_PGTABLE_MAPPING feature (which
contains the offending calling code) from zsmalloc.

Even though this option showed some amount improvement(e.g., 30%) in
some arm32 platforms, it has been headache to maintain since it have
abused APIs[1](e.g., unmap_kernel_range in atomic context).

Since we are approaching to deprecate 32bit machines and already made
the config option available for only builtin build since v5.8, lastly it
has been not default option in zsmalloc, it's time to drop the option
for better maintenance.

[1] http://lore.kernel.org/linux-mm/20201105170249.387069-1-minchan@kernel.org

Fixes: e47110e90584 ("mm/vunmap: add cond_resched() in vunmap_pmd_range")
Signed-off-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Tony Lindgren <tony@atomide.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Harish Sriram <harish@linux.ibm.com>
Cc: Uladzislau Rezki <urezki@gmail.com>
Cc: <stable@vger.kernel.org>
Link: https://lkml.kernel.org/r/20201117202916.GA3856507@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arm/configs/omap2plus_defconfig |  1 -
 include/linux/zsmalloc.h             |  1 -
 mm/Kconfig                           | 13 ---------
 mm/zsmalloc.c                        | 54 ------------------------------------
 4 files changed, 69 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index 34793aabdb65..58df9fd79a76 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -81,7 +81,6 @@ CONFIG_PARTITION_ADVANCED=y
 CONFIG_BINFMT_MISC=y
 CONFIG_CMA=y
 CONFIG_ZSMALLOC=m
-CONFIG_ZSMALLOC_PGTABLE_MAPPING=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h
index 0fdbf653b173..4807ca4d52e0 100644
--- a/include/linux/zsmalloc.h
+++ b/include/linux/zsmalloc.h
@@ -20,7 +20,6 @@
  * zsmalloc mapping modes
  *
  * NOTE: These only make a difference when a mapped object spans pages.
- * They also have no effect when ZSMALLOC_PGTABLE_MAPPING is selected.
  */
 enum zs_mapmode {
 	ZS_MM_RW, /* normal read-write mapping */
diff --git a/mm/Kconfig b/mm/Kconfig
index d42423f884a7..390165ffbb0f 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -707,19 +707,6 @@ config ZSMALLOC
 	  returned by an alloc().  This handle must be mapped in order to
 	  access the allocated space.
 
-config ZSMALLOC_PGTABLE_MAPPING
-	bool "Use page table mapping to access object in zsmalloc"
-	depends on ZSMALLOC=y
-	help
-	  By default, zsmalloc uses a copy-based object mapping method to
-	  access allocations that span two pages. However, if a particular
-	  architecture (ex, ARM) performs VM mapping faster than copying,
-	  then you should select this. This causes zsmalloc to use page table
-	  mapping rather than copying for object mapping.
-
-	  You can check speed with zsmalloc benchmark:
-	  https://github.com/spartacus06/zsmapbench
-
 config ZSMALLOC_STAT
 	bool "Export zsmalloc statistics"
 	depends on ZSMALLOC
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 918c7b019b3d..cdfaaadea8ff 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -293,11 +293,7 @@ struct zspage {
 };
 
 struct mapping_area {
-#ifdef CONFIG_ZSMALLOC_PGTABLE_MAPPING
-	struct vm_struct *vm; /* vm area for mapping object that span pages */
-#else
 	char *vm_buf; /* copy buffer for objects that span pages */
-#endif
 	char *vm_addr; /* address of kmap_atomic()'ed pages */
 	enum zs_mapmode vm_mm; /* mapping mode */
 };
@@ -1113,54 +1109,6 @@ static struct zspage *find_get_zspage(struct size_class *class)
 	return zspage;
 }
 
-#ifdef CONFIG_ZSMALLOC_PGTABLE_MAPPING
-static inline int __zs_cpu_up(struct mapping_area *area)
-{
-	/*
-	 * Make sure we don't leak memory if a cpu UP notification
-	 * and zs_init() race and both call zs_cpu_up() on the same cpu
-	 */
-	if (area->vm)
-		return 0;
-	area->vm = get_vm_area(PAGE_SIZE * 2, 0);
-	if (!area->vm)
-		return -ENOMEM;
-
-	/*
-	 * Populate ptes in advance to avoid pte allocation with GFP_KERNEL
-	 * in non-preemtible context of zs_map_object.
-	 */
-	return apply_to_page_range(&init_mm, (unsigned long)area->vm->addr,
-			PAGE_SIZE * 2, NULL, NULL);
-}
-
-static inline void __zs_cpu_down(struct mapping_area *area)
-{
-	if (area->vm)
-		free_vm_area(area->vm);
-	area->vm = NULL;
-}
-
-static inline void *__zs_map_object(struct mapping_area *area,
-				struct page *pages[2], int off, int size)
-{
-	unsigned long addr = (unsigned long)area->vm->addr;
-
-	BUG_ON(map_kernel_range(addr, PAGE_SIZE * 2, PAGE_KERNEL, pages) < 0);
-	area->vm_addr = area->vm->addr;
-	return area->vm_addr + off;
-}
-
-static inline void __zs_unmap_object(struct mapping_area *area,
-				struct page *pages[2], int off, int size)
-{
-	unsigned long addr = (unsigned long)area->vm_addr;
-
-	unmap_kernel_range(addr, PAGE_SIZE * 2);
-}
-
-#else /* CONFIG_ZSMALLOC_PGTABLE_MAPPING */
-
 static inline int __zs_cpu_up(struct mapping_area *area)
 {
 	/*
@@ -1241,8 +1189,6 @@ out:
 	pagefault_enable();
 }
 
-#endif /* CONFIG_ZSMALLOC_PGTABLE_MAPPING */
-
 static int zs_cpu_prepare(unsigned int cpu)
 {
 	struct mapping_area *area;
-- 
cgit v1.2.3


From 85261c1ff156eb60fc26c378748387f2e85c6878 Mon Sep 17 00:00:00 2001
From: Alexander Usyskin <alexander.usyskin@intel.com>
Date: Mon, 16 Nov 2020 14:56:11 +0200
Subject: mei: bus: add vtag support

Add API to support vtag in communication on mei bus.

Add mei_cldev_send_vtag, mei_cldev_recv_vtag and
mei_cldev_recv_nonblock_vtag functions to allow sending a message
with vtag set and to receive vtag of an incoming message.

Cc: Sean Z Huang <sean.z.huang@intel.com>
Signed-off-by: Alexander Usyskin <alexander.usyskin@intel.com>
Signed-off-by: Tomas Winkler <tomas.winkler@intel.com>
Link: https://lore.kernel.org/r/20201116125612.1660971-1-tomas.winkler@intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/mei/bus-fixup.c |  13 +++---
 drivers/misc/mei/bus.c       | 101 +++++++++++++++++++++++++++++++++++--------
 drivers/misc/mei/client.c    |   6 ++-
 drivers/misc/mei/mei_dev.h   |   4 +-
 include/linux/mei_cl_bus.h   |   6 +++
 5 files changed, 104 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/misc/mei/bus-fixup.c b/drivers/misc/mei/bus-fixup.c
index 4e30fa98fe7d..6cc3145bb716 100644
--- a/drivers/misc/mei/bus-fixup.c
+++ b/drivers/misc/mei/bus-fixup.c
@@ -148,7 +148,7 @@ static int mei_osver(struct mei_cl_device *cldev)
 	os_ver = (struct mei_os_ver *)fwcaps->data;
 	os_ver->os_type = OSTYPE_LINUX;
 
-	return __mei_cl_send(cldev->cl, buf, size, mode);
+	return __mei_cl_send(cldev->cl, buf, size, 0, mode);
 }
 
 #define MKHI_FWVER_BUF_LEN (sizeof(struct mkhi_msg_hdr) + \
@@ -169,7 +169,7 @@ static int mei_fwver(struct mei_cl_device *cldev)
 	req.hdr.group_id = MKHI_GEN_GROUP_ID;
 	req.hdr.command = MKHI_GEN_GET_FW_VERSION_CMD;
 
-	ret = __mei_cl_send(cldev->cl, (u8 *)&req, sizeof(req),
+	ret = __mei_cl_send(cldev->cl, (u8 *)&req, sizeof(req), 0,
 			    MEI_CL_IO_TX_BLOCKING);
 	if (ret < 0) {
 		dev_err(&cldev->dev, "Could not send ReqFWVersion cmd\n");
@@ -177,7 +177,7 @@ static int mei_fwver(struct mei_cl_device *cldev)
 	}
 
 	ret = 0;
-	bytes_recv = __mei_cl_recv(cldev->cl, buf, sizeof(buf), 0,
+	bytes_recv = __mei_cl_recv(cldev->cl, buf, sizeof(buf), NULL, 0,
 				   MKHI_RCV_TIMEOUT);
 	if (bytes_recv < 0 || (size_t)bytes_recv < MKHI_FWVER_LEN(1)) {
 		/*
@@ -324,13 +324,15 @@ static int mei_nfc_if_version(struct mei_cl *cl,
 	};
 	struct mei_nfc_reply *reply = NULL;
 	size_t if_version_length;
+	u8 vtag;
 	int bytes_recv, ret;
 
 	bus = cl->dev;
 
 	WARN_ON(mutex_is_locked(&bus->device_lock));
 
-	ret = __mei_cl_send(cl, (u8 *)&cmd, sizeof(cmd), MEI_CL_IO_TX_BLOCKING);
+	ret = __mei_cl_send(cl, (u8 *)&cmd, sizeof(cmd), 0,
+			    MEI_CL_IO_TX_BLOCKING);
 	if (ret < 0) {
 		dev_err(bus->dev, "Could not send IF version cmd\n");
 		return ret;
@@ -344,7 +346,8 @@ static int mei_nfc_if_version(struct mei_cl *cl,
 		return -ENOMEM;
 
 	ret = 0;
-	bytes_recv = __mei_cl_recv(cl, (u8 *)reply, if_version_length, 0, 0);
+	bytes_recv = __mei_cl_recv(cl, (u8 *)reply, if_version_length, &vtag,
+				   0, 0);
 	if (bytes_recv < 0 || (size_t)bytes_recv < if_version_length) {
 		dev_err(bus->dev, "Could not read IF version\n");
 		ret = -EIO;
diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c
index 7fe48baa103a..2907db260fba 100644
--- a/drivers/misc/mei/bus.c
+++ b/drivers/misc/mei/bus.c
@@ -26,11 +26,12 @@
  * @cl: host client
  * @buf: buffer to send
  * @length: buffer length
+ * @vtag: virtual tag
  * @mode: sending mode
  *
  * Return: written size bytes or < 0 on error
  */
-ssize_t __mei_cl_send(struct mei_cl *cl, u8 *buf, size_t length,
+ssize_t __mei_cl_send(struct mei_cl *cl, u8 *buf, size_t length, u8 vtag,
 		      unsigned int mode)
 {
 	struct mei_device *bus;
@@ -86,6 +87,7 @@ ssize_t __mei_cl_send(struct mei_cl *cl, u8 *buf, size_t length,
 		rets = -ENOMEM;
 		goto out;
 	}
+	cb->vtag = vtag;
 
 	cb->internal = !!(mode & MEI_CL_IO_TX_INTERNAL);
 	cb->blocking = !!(mode & MEI_CL_IO_TX_BLOCKING);
@@ -106,11 +108,12 @@ out:
  * @buf: buffer to receive
  * @length: buffer length
  * @mode: io mode
+ * @vtag: virtual tag
  * @timeout: recv timeout, 0 for infinite timeout
  *
  * Return: read size in bytes of < 0 on error
  */
-ssize_t __mei_cl_recv(struct mei_cl *cl, u8 *buf, size_t length,
+ssize_t __mei_cl_recv(struct mei_cl *cl, u8 *buf, size_t length, u8 *vtag,
 		      unsigned int mode, unsigned long timeout)
 {
 	struct mei_device *bus;
@@ -196,6 +199,8 @@ copy:
 	r_length = min_t(size_t, length, cb->buf_idx);
 	memcpy(buf, cb->buf.data, r_length);
 	rets = r_length;
+	if (vtag)
+		*vtag = cb->vtag;
 
 free:
 	mei_cl_del_rd_completed(cl, cb);
@@ -206,40 +211,87 @@ out:
 }
 
 /**
- * mei_cldev_send - me device send  (write)
+ * mei_cldev_send_vtag - me device send with vtag  (write)
  *
  * @cldev: me client device
  * @buf: buffer to send
  * @length: buffer length
+ * @vtag: virtual tag
  *
- * Return: written size in bytes or < 0 on error
+ * Return:
+ *  * written size in bytes
+ *  * < 0 on error
  */
-ssize_t mei_cldev_send(struct mei_cl_device *cldev, u8 *buf, size_t length)
+
+ssize_t mei_cldev_send_vtag(struct mei_cl_device *cldev, u8 *buf, size_t length,
+			    u8 vtag)
 {
 	struct mei_cl *cl = cldev->cl;
 
-	return __mei_cl_send(cl, buf, length, MEI_CL_IO_TX_BLOCKING);
+	return __mei_cl_send(cl, buf, length, vtag, MEI_CL_IO_TX_BLOCKING);
 }
-EXPORT_SYMBOL_GPL(mei_cldev_send);
+EXPORT_SYMBOL_GPL(mei_cldev_send_vtag);
 
 /**
- * mei_cldev_recv_nonblock - non block client receive (read)
+ * mei_cldev_recv_vtag - client receive with vtag (read)
  *
  * @cldev: me client device
  * @buf: buffer to receive
  * @length: buffer length
+ * @vtag: virtual tag
  *
- * Return: read size in bytes of < 0 on error
- *         -EAGAIN if function will block.
+ * Return:
+ * * read size in bytes
+ * *  < 0 on error
  */
-ssize_t mei_cldev_recv_nonblock(struct mei_cl_device *cldev, u8 *buf,
-				size_t length)
+
+ssize_t mei_cldev_recv_vtag(struct mei_cl_device *cldev, u8 *buf, size_t length,
+			    u8 *vtag)
 {
 	struct mei_cl *cl = cldev->cl;
 
-	return __mei_cl_recv(cl, buf, length, MEI_CL_IO_RX_NONBLOCK, 0);
+	return __mei_cl_recv(cl, buf, length, vtag, 0, 0);
 }
-EXPORT_SYMBOL_GPL(mei_cldev_recv_nonblock);
+EXPORT_SYMBOL_GPL(mei_cldev_recv_vtag);
+
+/**
+ * mei_cldev_recv_nonblock_vtag - non block client receive with vtag (read)
+ *
+ * @cldev: me client device
+ * @buf: buffer to receive
+ * @length: buffer length
+ * @vtag: virtual tag
+ *
+ * Return:
+ * * read size in bytes
+ * * -EAGAIN if function will block.
+ * * < 0 on other error
+ */
+ssize_t mei_cldev_recv_nonblock_vtag(struct mei_cl_device *cldev, u8 *buf,
+				     size_t length, u8 *vtag)
+{
+	struct mei_cl *cl = cldev->cl;
+
+	return __mei_cl_recv(cl, buf, length, vtag, MEI_CL_IO_RX_NONBLOCK, 0);
+}
+EXPORT_SYMBOL_GPL(mei_cldev_recv_nonblock_vtag);
+
+/**
+ * mei_cldev_send - me device send  (write)
+ *
+ * @cldev: me client device
+ * @buf: buffer to send
+ * @length: buffer length
+ *
+ * Return:
+ *  * written size in bytes
+ *  * < 0 on error
+ */
+ssize_t mei_cldev_send(struct mei_cl_device *cldev, u8 *buf, size_t length)
+{
+	return mei_cldev_send_vtag(cldev, buf, length, 0);
+}
+EXPORT_SYMBOL_GPL(mei_cldev_send);
 
 /**
  * mei_cldev_recv - client receive (read)
@@ -252,12 +304,27 @@ EXPORT_SYMBOL_GPL(mei_cldev_recv_nonblock);
  */
 ssize_t mei_cldev_recv(struct mei_cl_device *cldev, u8 *buf, size_t length)
 {
-	struct mei_cl *cl = cldev->cl;
-
-	return __mei_cl_recv(cl, buf, length, 0, 0);
+	return mei_cldev_recv_vtag(cldev, buf, length, NULL);
 }
 EXPORT_SYMBOL_GPL(mei_cldev_recv);
 
+/**
+ * mei_cldev_recv_nonblock - non block client receive (read)
+ *
+ * @cldev: me client device
+ * @buf: buffer to receive
+ * @length: buffer length
+ *
+ * Return: read size in bytes of < 0 on error
+ *         -EAGAIN if function will block.
+ */
+ssize_t mei_cldev_recv_nonblock(struct mei_cl_device *cldev, u8 *buf,
+				size_t length)
+{
+	return mei_cldev_recv_nonblock_vtag(cldev, buf, length, NULL);
+}
+EXPORT_SYMBOL_GPL(mei_cldev_recv_nonblock);
+
 /**
  * mei_cl_bus_rx_work - dispatch rx event for a bus device
  *
diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c
index d5c3f7d54634..a56d41321f32 100644
--- a/drivers/misc/mei/client.c
+++ b/drivers/misc/mei/client.c
@@ -1306,7 +1306,7 @@ struct mei_cl_vtag *mei_cl_vtag_alloc(struct file *fp, u8 vtag)
  * mei_cl_fp_by_vtag - obtain the file pointer by vtag
  *
  * @cl: host client
- * @vtag: vm tag
+ * @vtag: virtual tag
  *
  * Return:
  * * A file pointer - on success
@@ -1317,7 +1317,9 @@ const struct file *mei_cl_fp_by_vtag(const struct mei_cl *cl, u8 vtag)
 	struct mei_cl_vtag *vtag_l;
 
 	list_for_each_entry(vtag_l, &cl->vtag_map, list)
-		if (vtag_l->vtag == vtag)
+		/* The client on bus has one fixed fp */
+		if ((cl->cldev && mei_cldev_enabled(cl->cldev)) ||
+		    vtag_l->vtag == vtag)
 			return vtag_l->fp;
 
 	return ERR_PTR(-ENOENT);
diff --git a/drivers/misc/mei/mei_dev.h b/drivers/misc/mei/mei_dev.h
index 2f4cc1a8aae8..8c395bfdf6f3 100644
--- a/drivers/misc/mei/mei_dev.h
+++ b/drivers/misc/mei/mei_dev.h
@@ -340,9 +340,9 @@ struct mei_hw_ops {
 /* MEI bus API*/
 void mei_cl_bus_rescan_work(struct work_struct *work);
 void mei_cl_bus_dev_fixup(struct mei_cl_device *dev);
-ssize_t __mei_cl_send(struct mei_cl *cl, u8 *buf, size_t length,
+ssize_t __mei_cl_send(struct mei_cl *cl, u8 *buf, size_t length, u8 vtag,
 		      unsigned int mode);
-ssize_t __mei_cl_recv(struct mei_cl *cl, u8 *buf, size_t length,
+ssize_t __mei_cl_recv(struct mei_cl *cl, u8 *buf, size_t length, u8 *vtag,
 		      unsigned int mode, unsigned long timeout);
 bool mei_cl_bus_rx_event(struct mei_cl *cl);
 bool mei_cl_bus_notify_event(struct mei_cl *cl);
diff --git a/include/linux/mei_cl_bus.h b/include/linux/mei_cl_bus.h
index 52aa4821093a..959ad7d850b4 100644
--- a/include/linux/mei_cl_bus.h
+++ b/include/linux/mei_cl_bus.h
@@ -95,6 +95,12 @@ ssize_t mei_cldev_send(struct mei_cl_device *cldev, u8 *buf, size_t length);
 ssize_t mei_cldev_recv(struct mei_cl_device *cldev, u8 *buf, size_t length);
 ssize_t mei_cldev_recv_nonblock(struct mei_cl_device *cldev, u8 *buf,
 				size_t length);
+ssize_t mei_cldev_send_vtag(struct mei_cl_device *cldev, u8 *buf, size_t length,
+			    u8 vtag);
+ssize_t mei_cldev_recv_vtag(struct mei_cl_device *cldev, u8 *buf, size_t length,
+			    u8 *vtag);
+ssize_t mei_cldev_recv_nonblock_vtag(struct mei_cl_device *cldev, u8 *buf,
+				     size_t length, u8 *vtag);
 
 int mei_cldev_register_rx_cb(struct mei_cl_device *cldev, mei_cldev_cb_t rx_cb);
 int mei_cldev_register_notif_cb(struct mei_cl_device *cldev,
-- 
cgit v1.2.3


From 76437b340b242fd21952f54ba8965d21a1ffa8c8 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 7 Dec 2020 10:16:01 +0100
Subject: earlycon: drop semicolon from earlycon macro

Drop the trailing semicolon from the OF_EARLYCON_DECLARE() macro
definition which was left when removing the array-of-pointer
indirection.

Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20201207091601.5202-1-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/serial_core.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 3e32b788c28d..e1b684e33841 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -372,7 +372,7 @@ extern const struct earlycon_id __earlycon_table_end[];
 		__aligned(__alignof__(struct earlycon_id))		\
 		= { .name = __stringify(_name),				\
 		    .compatible = compat,				\
-		    .setup = fn };
+		    .setup = fn }
 
 #define EARLYCON_DECLARE(_name, fn)	OF_EARLYCON_DECLARE(_name, "", fn)
 
-- 
cgit v1.2.3


From 2d26c716fc49f41a63e1efe8f1f772b0adeaacef Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 7 Dec 2020 10:13:08 +0100
Subject: module: drop semicolon from version macro

Drop the trailing semicolon from the MODULE_VERSION() macro definition
which was left when removing the array-of-pointer indirection.

Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: Jessica Yu <jeyu@kernel.org>
---
 include/linux/module.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/module.h b/include/linux/module.h
index 5958075ea3f4..e7a619c2457e 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -279,7 +279,7 @@ extern typeof(name) __mod_##type##__##name##_device_table		\
 			},						\
 			.module_name	= KBUILD_MODNAME,		\
 			.version	= _version,			\
-		};
+		}
 #endif
 
 /* Optional firmware file (or files) needed by the module
-- 
cgit v1.2.3


From c69942bda5152d764ee7d897d1627d64c7177ea1 Mon Sep 17 00:00:00 2001
From: Jonathan Neuschäfer <j.neuschaefer@gmx.net>
Date: Mon, 30 Nov 2020 16:24:15 +0100
Subject: mtd: spi-nor: Fix multiple typos
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There are a few typos in comments in the SPI NOR framework; fix them.

Signed-off-by: Jonathan Neuschäfer <j.neuschaefer@gmx.net>
Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com>
Reviewed-by: Tudor Ambarus <tudor.ambarus@microchip.com>
Link: https://lore.kernel.org/r/20201130152416.1283972-1-j.neuschaefer@gmx.net
---
 drivers/mtd/spi-nor/core.c  | 4 ++--
 drivers/mtd/spi-nor/sfdp.c  | 2 +-
 include/linux/mtd/spi-nor.h | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/spi-nor/core.c b/drivers/mtd/spi-nor/core.c
index 5bee7c8da4dc..7b4850f94223 100644
--- a/drivers/mtd/spi-nor/core.c
+++ b/drivers/mtd/spi-nor/core.c
@@ -1599,7 +1599,7 @@ destroy_erase_cmd_list:
 
 /*
  * Erase an address range on the nor chip.  The address range may extend
- * one or more erase sectors.  Return an error is there is a problem erasing.
+ * one or more erase sectors. Return an error if there is a problem erasing.
  */
 static int spi_nor_erase(struct mtd_info *mtd, struct erase_info *instr)
 {
@@ -2693,7 +2693,7 @@ spi_nor_select_uniform_erase(struct spi_nor_erase_map *map,
 		}
 
 		/*
-		 * Otherwise, the current erase size is still a valid canditate.
+		 * Otherwise, the current erase size is still a valid candidate.
 		 * Select the biggest valid candidate.
 		 */
 		if (!erase && tested_erase->size)
diff --git a/drivers/mtd/spi-nor/sfdp.c b/drivers/mtd/spi-nor/sfdp.c
index 22cb519efe3f..6ee7719e5903 100644
--- a/drivers/mtd/spi-nor/sfdp.c
+++ b/drivers/mtd/spi-nor/sfdp.c
@@ -65,7 +65,7 @@ struct sfdp_bfpt_read {
 
 struct sfdp_bfpt_erase {
 	/*
-	 * The half-word at offset <shift> in DWORD <dwoard> encodes the
+	 * The half-word at offset <shift> in DWORD <dword> encodes the
 	 * op code and erase sector size to be used by Sector Erase commands.
 	 */
 	u32			dword;
diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h
index 299685d15dc2..d13958de6d8a 100644
--- a/include/linux/mtd/spi-nor.h
+++ b/include/linux/mtd/spi-nor.h
@@ -433,7 +433,7 @@ static inline struct device_node *spi_nor_get_flash_node(struct spi_nor *nor)
  * @name:	the chip type name
  * @hwcaps:	the hardware capabilities supported by the controller driver
  *
- * The drivers can use this fuction to scan the SPI NOR.
+ * The drivers can use this function to scan the SPI NOR.
  * In the scanning, it will try to get all the necessary information to
  * fill the mtd_info{} and the spi_nor{}.
  *
-- 
cgit v1.2.3


From 0eba770790426553f45b8643bcd77b854e045057 Mon Sep 17 00:00:00 2001
From: Michael Walle <michael@walle.cc>
Date: Thu, 5 Nov 2020 20:27:45 +0100
Subject: clk: composite: add devm_clk_hw_register_composite_pdata()

This will simplify drivers which would only unregister the clk in their
remove() op.

Signed-off-by: Michael Walle <michael@walle.cc>
Link: https://lore.kernel.org/r/20201105192746.19564-3-michael@walle.cc
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/clk-composite.c  | 50 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/clk-provider.h |  7 +++++++
 2 files changed, 57 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/clk/clk-composite.c b/drivers/clk/clk-composite.c
index 2ddb54f7d3ab..0506046a5f4b 100644
--- a/drivers/clk/clk-composite.c
+++ b/drivers/clk/clk-composite.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/clk-provider.h>
+#include <linux/device.h>
 #include <linux/err.h>
 #include <linux/slab.h>
 
@@ -405,3 +406,52 @@ void clk_hw_unregister_composite(struct clk_hw *hw)
 	kfree(composite);
 }
 EXPORT_SYMBOL_GPL(clk_hw_unregister_composite);
+
+static void devm_clk_hw_release_composite(struct device *dev, void *res)
+{
+	clk_hw_unregister_composite(*(struct clk_hw **)res);
+}
+
+static struct clk_hw *__devm_clk_hw_register_composite(struct device *dev,
+			const char *name, const char * const *parent_names,
+			const struct clk_parent_data *pdata, int num_parents,
+			struct clk_hw *mux_hw, const struct clk_ops *mux_ops,
+			struct clk_hw *rate_hw, const struct clk_ops *rate_ops,
+			struct clk_hw *gate_hw, const struct clk_ops *gate_ops,
+			unsigned long flags)
+{
+	struct clk_hw **ptr, *hw;
+
+	ptr = devres_alloc(devm_clk_hw_release_composite, sizeof(*ptr),
+			   GFP_KERNEL);
+	if (!ptr)
+		return ERR_PTR(-ENOMEM);
+
+	hw = __clk_hw_register_composite(dev, name, parent_names, pdata,
+					 num_parents, mux_hw, mux_ops, rate_hw,
+					 rate_ops, gate_hw, gate_ops, flags);
+
+	if (!IS_ERR(hw)) {
+		*ptr = hw;
+		devres_add(dev, ptr);
+	} else {
+		devres_free(ptr);
+	}
+
+	return hw;
+}
+
+struct clk_hw *devm_clk_hw_register_composite_pdata(struct device *dev,
+			const char *name,
+			const struct clk_parent_data *parent_data,
+			int num_parents,
+			struct clk_hw *mux_hw, const struct clk_ops *mux_ops,
+			struct clk_hw *rate_hw, const struct clk_ops *rate_ops,
+			struct clk_hw *gate_hw, const struct clk_ops *gate_ops,
+			unsigned long flags)
+{
+	return __devm_clk_hw_register_composite(dev, name, NULL, parent_data,
+						num_parents, mux_hw, mux_ops,
+						rate_hw, rate_ops, gate_hw,
+						gate_ops, flags);
+}
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index 03a5de5f99f4..33db52ff83a0 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -1062,6 +1062,13 @@ struct clk_hw *clk_hw_register_composite_pdata(struct device *dev,
 		struct clk_hw *rate_hw, const struct clk_ops *rate_ops,
 		struct clk_hw *gate_hw, const struct clk_ops *gate_ops,
 		unsigned long flags);
+struct clk_hw *devm_clk_hw_register_composite_pdata(struct device *dev,
+		const char *name, const struct clk_parent_data *parent_data,
+		int num_parents,
+		struct clk_hw *mux_hw, const struct clk_ops *mux_ops,
+		struct clk_hw *rate_hw, const struct clk_ops *rate_ops,
+		struct clk_hw *gate_hw, const struct clk_ops *gate_ops,
+		unsigned long flags);
 void clk_hw_unregister_composite(struct clk_hw *hw);
 
 struct clk *clk_register(struct device *dev, struct clk_hw *hw);
-- 
cgit v1.2.3


From d9a9280a0d0ae51dc1d4142138b99242b7ec8ac6 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 26 Oct 2020 17:10:58 +0100
Subject: seq_buf: Avoid type mismatch for seq_buf_init

Building with W=2 prints a number of warnings for one function that
has a pointer type mismatch:

linux/seq_buf.h: In function 'seq_buf_init':
linux/seq_buf.h:35:12: warning: pointer targets in assignment from 'unsigned char *' to 'char *' differ in signedness [-Wpointer-sign]

Change the type in the function prototype according to the type in
the structure.

Link: https://lkml.kernel.org/r/20201026161108.3707783-1-arnd@kernel.org

Fixes: 9a7777935c34 ("tracing: Convert seq_buf fields to be like seq_file fields")
Reviewed-by: Cezary Rojewski <cezary.rojewski@intel.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/seq_buf.h   | 2 +-
 include/linux/trace_seq.h | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h
index fb0205d87d3c..9d6c28cc4d8f 100644
--- a/include/linux/seq_buf.h
+++ b/include/linux/seq_buf.h
@@ -30,7 +30,7 @@ static inline void seq_buf_clear(struct seq_buf *s)
 }
 
 static inline void
-seq_buf_init(struct seq_buf *s, unsigned char *buf, unsigned int size)
+seq_buf_init(struct seq_buf *s, char *buf, unsigned int size)
 {
 	s->buffer = buf;
 	s->size = size;
diff --git a/include/linux/trace_seq.h b/include/linux/trace_seq.h
index 6c30508fca19..5a2c650d9e1c 100644
--- a/include/linux/trace_seq.h
+++ b/include/linux/trace_seq.h
@@ -12,7 +12,7 @@
  */
 
 struct trace_seq {
-	unsigned char		buffer[PAGE_SIZE];
+	char			buffer[PAGE_SIZE];
 	struct seq_buf		seq;
 	int			full;
 };
@@ -51,7 +51,7 @@ static inline int trace_seq_used(struct trace_seq *s)
  * that is about to be written to and then return the result
  * of that write.
  */
-static inline unsigned char *
+static inline char *
 trace_seq_buffer_ptr(struct trace_seq *s)
 {
 	return s->buffer + seq_buf_used(&s->seq);
-- 
cgit v1.2.3


From 661d4f55a79483aee4970a76e3bd9d4cdc74ac79 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Sun, 22 Nov 2020 15:35:46 +0000
Subject: sbitmap: remove swap_lock

map->swap_lock protects map->cleared from concurrent modification,
however sbitmap_deferred_clear() is already atomically drains it, so
it's guaranteed to not loose bits on concurrent
sbitmap_deferred_clear().

A one threaded tag heavy test on top of nullbk showed ~1.5% t-put
increase, and 3% -> 1% cycle reduction of sbitmap_get() according to perf.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/sbitmap.h |  5 -----
 lib/sbitmap.c           | 14 +++-----------
 2 files changed, 3 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h
index e40d019c3d9d..74cc6384715e 100644
--- a/include/linux/sbitmap.h
+++ b/include/linux/sbitmap.h
@@ -32,11 +32,6 @@ struct sbitmap_word {
 	 * @cleared: word holding cleared bits
 	 */
 	unsigned long cleared ____cacheline_aligned_in_smp;
-
-	/**
-	 * @swap_lock: Held while swapping word <-> cleared
-	 */
-	spinlock_t swap_lock;
 } ____cacheline_aligned_in_smp;
 
 /**
diff --git a/lib/sbitmap.c b/lib/sbitmap.c
index c1c8a4e69325..4fd877048ba8 100644
--- a/lib/sbitmap.c
+++ b/lib/sbitmap.c
@@ -15,13 +15,9 @@
 static inline bool sbitmap_deferred_clear(struct sbitmap_word *map)
 {
 	unsigned long mask, val;
-	bool ret = false;
-	unsigned long flags;
 
-	spin_lock_irqsave(&map->swap_lock, flags);
-
-	if (!map->cleared)
-		goto out_unlock;
+	if (!READ_ONCE(map->cleared))
+		return false;
 
 	/*
 	 * First get a stable cleared mask, setting the old mask to 0.
@@ -35,10 +31,7 @@ static inline bool sbitmap_deferred_clear(struct sbitmap_word *map)
 		val = map->word;
 	} while (cmpxchg(&map->word, val, val & ~mask) != val);
 
-	ret = true;
-out_unlock:
-	spin_unlock_irqrestore(&map->swap_lock, flags);
-	return ret;
+	return true;
 }
 
 int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift,
@@ -80,7 +73,6 @@ int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift,
 	for (i = 0; i < sb->map_nr; i++) {
 		sb->map[i].depth = min(depth, bits_per_word);
 		depth -= sb->map[i].depth;
-		spin_lock_init(&sb->map[i].swap_lock);
 	}
 	return 0;
 }
-- 
cgit v1.2.3


From 26792699fe3681102aa85f4ae6d39e80a6a7e6b6 Mon Sep 17 00:00:00 2001
From: Michael Walle <michael@walle.cc>
Date: Sun, 8 Nov 2020 19:51:09 +0100
Subject: clk: divider: add devm_clk_hw_register_divider_table()

This will simplify drivers which would only unregister the clk in their
remove() op.

Signed-off-by: Michael Walle <michael@walle.cc>
Link: https://lore.kernel.org/r/20201108185113.31377-6-michael@walle.cc
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/clk-divider.c    | 34 ++++++++++++++++++++++++++++++++++
 include/linux/clk-provider.h | 27 +++++++++++++++++++++++++++
 2 files changed, 61 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/clk/clk-divider.c b/drivers/clk/clk-divider.c
index 8de12cb0c43d..c499799693cc 100644
--- a/drivers/clk/clk-divider.c
+++ b/drivers/clk/clk-divider.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/clk-provider.h>
+#include <linux/device.h>
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/io.h>
@@ -578,3 +579,36 @@ void clk_hw_unregister_divider(struct clk_hw *hw)
 	kfree(div);
 }
 EXPORT_SYMBOL_GPL(clk_hw_unregister_divider);
+
+static void devm_clk_hw_release_divider(struct device *dev, void *res)
+{
+	clk_hw_unregister_divider(*(struct clk_hw **)res);
+}
+
+struct clk_hw *__devm_clk_hw_register_divider(struct device *dev,
+		struct device_node *np, const char *name,
+		const char *parent_name, const struct clk_hw *parent_hw,
+		const struct clk_parent_data *parent_data, unsigned long flags,
+		void __iomem *reg, u8 shift, u8 width, u8 clk_divider_flags,
+		const struct clk_div_table *table, spinlock_t *lock)
+{
+	struct clk_hw **ptr, *hw;
+
+	ptr = devres_alloc(devm_clk_hw_release_divider, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr)
+		return ERR_PTR(-ENOMEM);
+
+	hw = __clk_hw_register_divider(dev, np, name, parent_name, parent_hw,
+				       parent_data, flags, reg, shift, width,
+				       clk_divider_flags, table, lock);
+
+	if (!IS_ERR(hw)) {
+		*ptr = hw;
+		devres_add(dev, ptr);
+	} else {
+		devres_free(ptr);
+	}
+
+	return hw;
+}
+EXPORT_SYMBOL_GPL(__devm_clk_hw_register_divider);
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index 33db52ff83a0..5f896df01f83 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -639,6 +639,12 @@ struct clk_hw *__clk_hw_register_divider(struct device *dev,
 		const struct clk_parent_data *parent_data, unsigned long flags,
 		void __iomem *reg, u8 shift, u8 width, u8 clk_divider_flags,
 		const struct clk_div_table *table, spinlock_t *lock);
+struct clk_hw *__devm_clk_hw_register_divider(struct device *dev,
+		struct device_node *np, const char *name,
+		const char *parent_name, const struct clk_hw *parent_hw,
+		const struct clk_parent_data *parent_data, unsigned long flags,
+		void __iomem *reg, u8 shift, u8 width, u8 clk_divider_flags,
+		const struct clk_div_table *table, spinlock_t *lock);
 struct clk *clk_register_divider_table(struct device *dev, const char *name,
 		const char *parent_name, unsigned long flags,
 		void __iomem *reg, u8 shift, u8 width,
@@ -779,6 +785,27 @@ struct clk *clk_register_divider_table(struct device *dev, const char *name,
 				  (parent_data), (flags), (reg), (shift),     \
 				  (width), (clk_divider_flags), (table),      \
 				  (lock))
+/**
+ * devm_clk_hw_register_divider_table - register a table based divider clock
+ * with the clock framework (devres variant)
+ * @dev: device registering this clock
+ * @name: name of this clock
+ * @parent_name: name of clock's parent
+ * @flags: framework-specific flags
+ * @reg: register address to adjust divider
+ * @shift: number of bits to shift the bitfield
+ * @width: width of the bitfield
+ * @clk_divider_flags: divider-specific flags for this clock
+ * @table: array of divider/value pairs ending with a div set to 0
+ * @lock: shared register lock for this clock
+ */
+#define devm_clk_hw_register_divider_table(dev, name, parent_name, flags,     \
+					   reg, shift, width,		      \
+					   clk_divider_flags, table, lock)    \
+	__devm_clk_hw_register_divider((dev), NULL, (name), (parent_name),    \
+				       NULL, NULL, (flags), (reg), (shift),   \
+				       (width), (clk_divider_flags), (table), \
+				       (lock))
 
 void clk_unregister_divider(struct clk *clk);
 void clk_hw_unregister_divider(struct clk_hw *hw);
-- 
cgit v1.2.3


From 374a96b9600ccf60083c0fec8f727e04752a7f0c Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Sun, 6 Dec 2020 11:12:54 +0200
Subject: net/mlx4: Remove unused #define MAX_MSIX_P_PORT

All usages of the definition MAX_MSIX_P_PORT were removed.
It's not in use anymore. Remove it.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Link: https://lore.kernel.org/r/20201206091254.12476-1-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/mlx4/device.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 06e066e04a4b..236a7d04f891 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -46,7 +46,6 @@
 
 #define DEFAULT_UAR_PAGE_SHIFT  12
 
-#define MAX_MSIX_P_PORT		17
 #define MAX_MSIX		128
 #define MIN_MSIX_P_PORT		5
 #define MLX4_IS_LEGACY_EQ_MODE(dev_cap) ((dev_cap).num_comp_vectors < \
-- 
cgit v1.2.3


From fb01a2932e81a1fb2273f87ff92dc8172b8880ee Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Thu, 3 Dec 2020 09:26:36 +0800
Subject: blk-mq: add new API of blk_mq_hctx_set_fq_lock_class

flush_end_io() may be called recursively from some driver, such as
nvme-loop, so lockdep may complain 'possible recursive locking'.
Commit b3c6a5997541("block: Fix a lockdep complaint triggered by
request queue flushing") tried to address this issue by assigning
dynamically allocated per-flush-queue lock class. This solution
adds synchronize_rcu() for each hctx's release handler, and causes
horrible SCSI MQ probe delay(more than half an hour on megaraid sas).

Add new API of blk_mq_hctx_set_fq_lock_class() for these drivers, so
we just need to use driver specific lock class for avoiding the
lockdep warning of 'possible recursive locking'.

Tested-by: Kashyap Desai <kashyap.desai@broadcom.com>
Reported-by: Qian Cai <cai@redhat.com>
Cc: Sumit Saxena <sumit.saxena@broadcom.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kashyap Desai <kashyap.desai@broadcom.com>
Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Hannes Reinecke <hare@suse.de>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-flush.c      | 25 +++++++++++++++++++++++++
 include/linux/blk-mq.h |  3 +++
 2 files changed, 28 insertions(+)

(limited to 'include/linux')

diff --git a/block/blk-flush.c b/block/blk-flush.c
index 9507dcdd5881..bf51588762d8 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -490,3 +490,28 @@ void blk_free_flush_queue(struct blk_flush_queue *fq)
 	kfree(fq->flush_rq);
 	kfree(fq);
 }
+
+/*
+ * Allow driver to set its own lock class to fq->mq_flush_lock for
+ * avoiding lockdep complaint.
+ *
+ * flush_end_io() may be called recursively from some driver, such as
+ * nvme-loop, so lockdep may complain 'possible recursive locking' because
+ * all 'struct blk_flush_queue' instance share same mq_flush_lock lock class
+ * key. We need to assign different lock class for these driver's
+ * fq->mq_flush_lock for avoiding the lockdep warning.
+ *
+ * Use dynamically allocated lock class key for each 'blk_flush_queue'
+ * instance is over-kill, and more worse it introduces horrible boot delay
+ * issue because synchronize_rcu() is implied in lockdep_unregister_key which
+ * is called for each hctx release. SCSI probing may synchronously create and
+ * destroy lots of MQ request_queues for non-existent devices, and some robot
+ * test kernel always enable lockdep option. It is observed that more than half
+ * an hour is taken during SCSI MQ probe with per-fq lock class.
+ */
+void blk_mq_hctx_set_fq_lock_class(struct blk_mq_hw_ctx *hctx,
+		struct lock_class_key *key)
+{
+	lockdep_set_class(&hctx->fq->mq_flush_lock, key);
+}
+EXPORT_SYMBOL_GPL(blk_mq_hctx_set_fq_lock_class);
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 794b2a33a2c3..5f639240760e 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -5,6 +5,7 @@
 #include <linux/blkdev.h>
 #include <linux/sbitmap.h>
 #include <linux/srcu.h>
+#include <linux/lockdep.h>
 
 struct blk_mq_tags;
 struct blk_flush_queue;
@@ -594,5 +595,7 @@ static inline void blk_mq_cleanup_rq(struct request *rq)
 }
 
 blk_qc_t blk_mq_submit_bio(struct bio *bio);
+void blk_mq_hctx_set_fq_lock_class(struct blk_mq_hw_ctx *hctx,
+		struct lock_class_key *key);
 
 #endif
-- 
cgit v1.2.3


From 76ea4d8eeefbfdd37e47c6fd579d0d5852457618 Mon Sep 17 00:00:00 2001
From: Lukasz Luba <lukasz.luba@arm.com>
Date: Tue, 24 Nov 2020 10:43:45 +0000
Subject: firmware: arm_scmi: Add power_scale_mw_get() interface

Add a new interface to the existing perf_ops and export the information
about the power values scale.

This would be used by the cpufreq driver and Energy Model framework to
set the performance domains scale: milli-Watts or abstract scale.

Suggested-by: Morten Rasmussen <morten.rasmussen@arm.com>
Reviewed-by: Cristian Marussi <cristian.marussi@arm.com>
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Acked-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
---
 drivers/firmware/arm_scmi/perf.c | 8 ++++++++
 include/linux/scmi_protocol.h    | 1 +
 2 files changed, 9 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/firmware/arm_scmi/perf.c b/drivers/firmware/arm_scmi/perf.c
index 82fb3babff72..e374b1125fca 100644
--- a/drivers/firmware/arm_scmi/perf.c
+++ b/drivers/firmware/arm_scmi/perf.c
@@ -750,6 +750,13 @@ static bool scmi_fast_switch_possible(const struct scmi_handle *handle,
 	return dom->fc_info && dom->fc_info->level_set_addr;
 }
 
+static bool scmi_power_scale_mw_get(const struct scmi_handle *handle)
+{
+	struct scmi_perf_info *pi = handle->perf_priv;
+
+	return pi->power_scale_mw;
+}
+
 static const struct scmi_perf_ops perf_ops = {
 	.limits_set = scmi_perf_limits_set,
 	.limits_get = scmi_perf_limits_get,
@@ -762,6 +769,7 @@ static const struct scmi_perf_ops perf_ops = {
 	.freq_get = scmi_dvfs_freq_get,
 	.est_power_get = scmi_dvfs_est_power_get,
 	.fast_switch_possible = scmi_fast_switch_possible,
+	.power_scale_mw_get = scmi_power_scale_mw_get,
 };
 
 static int scmi_perf_set_notify_enabled(const struct scmi_handle *handle,
diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h
index 9cd312a1ff92..c77e4e11e788 100644
--- a/include/linux/scmi_protocol.h
+++ b/include/linux/scmi_protocol.h
@@ -121,6 +121,7 @@ struct scmi_perf_ops {
 			     unsigned long *rate, unsigned long *power);
 	bool (*fast_switch_possible)(const struct scmi_handle *handle,
 				     struct device *dev);
+	bool (*power_scale_mw_get)(const struct scmi_handle *handle);
 };
 
 /**
-- 
cgit v1.2.3


From cc00bcaa589914096edef7fb87ca5cee4a166b5c Mon Sep 17 00:00:00 2001
From: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Date: Wed, 25 Nov 2020 11:27:22 -0700
Subject: netfilter: x_tables: Switch synchronization to RCU

When running concurrent iptables rules replacement with data, the per CPU
sequence count is checked after the assignment of the new information.
The sequence count is used to synchronize with the packet path without the
use of any explicit locking. If there are any packets in the packet path using
the table information, the sequence count is incremented to an odd value and
is incremented to an even after the packet process completion.

The new table value assignment is followed by a write memory barrier so every
CPU should see the latest value. If the packet path has started with the old
table information, the sequence counter will be odd and the iptables
replacement will wait till the sequence count is even prior to freeing the
old table info.

However, this assumes that the new table information assignment and the memory
barrier is actually executed prior to the counter check in the replacement
thread. If CPU decides to execute the assignment later as there is no user of
the table information prior to the sequence check, the packet path in another
CPU may use the old table information. The replacement thread would then free
the table information under it leading to a use after free in the packet
processing context-

Unable to handle kernel NULL pointer dereference at virtual
address 000000000000008e
pc : ip6t_do_table+0x5d0/0x89c
lr : ip6t_do_table+0x5b8/0x89c
ip6t_do_table+0x5d0/0x89c
ip6table_filter_hook+0x24/0x30
nf_hook_slow+0x84/0x120
ip6_input+0x74/0xe0
ip6_rcv_finish+0x7c/0x128
ipv6_rcv+0xac/0xe4
__netif_receive_skb+0x84/0x17c
process_backlog+0x15c/0x1b8
napi_poll+0x88/0x284
net_rx_action+0xbc/0x23c
__do_softirq+0x20c/0x48c

This could be fixed by forcing instruction order after the new table
information assignment or by switching to RCU for the synchronization.

Fixes: 80055dab5de0 ("netfilter: x_tables: make xt_replace_table wait until old rules are not used anymore")
Reported-by: Sean Tranchetti <stranche@codeaurora.org>
Reported-by: kernel test robot <lkp@intel.com>
Suggested-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/x_tables.h |  5 +++-
 net/ipv4/netfilter/arp_tables.c    | 14 +++++------
 net/ipv4/netfilter/ip_tables.c     | 14 +++++------
 net/ipv6/netfilter/ip6_tables.c    | 14 +++++------
 net/netfilter/x_tables.c           | 49 ++++++++++++--------------------------
 5 files changed, 40 insertions(+), 56 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index 5deb099d156d..8ebb64193757 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -227,7 +227,7 @@ struct xt_table {
 	unsigned int valid_hooks;
 
 	/* Man behind the curtain... */
-	struct xt_table_info *private;
+	struct xt_table_info __rcu *private;
 
 	/* Set this to THIS_MODULE if you are a module, otherwise NULL */
 	struct module *me;
@@ -448,6 +448,9 @@ xt_get_per_cpu_counter(struct xt_counters *cnt, unsigned int cpu)
 
 struct nf_hook_ops *xt_hook_ops_alloc(const struct xt_table *, nf_hookfn *);
 
+struct xt_table_info
+*xt_table_get_private_protected(const struct xt_table *table);
+
 #ifdef CONFIG_COMPAT
 #include <net/compat.h>
 
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index d1e04d2b5170..563b62b76a5f 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -203,7 +203,7 @@ unsigned int arpt_do_table(struct sk_buff *skb,
 
 	local_bh_disable();
 	addend = xt_write_recseq_begin();
-	private = READ_ONCE(table->private); /* Address dependency. */
+	private = rcu_access_pointer(table->private);
 	cpu     = smp_processor_id();
 	table_base = private->entries;
 	jumpstack  = (struct arpt_entry **)private->jumpstack[cpu];
@@ -649,7 +649,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table)
 {
 	unsigned int countersize;
 	struct xt_counters *counters;
-	const struct xt_table_info *private = table->private;
+	const struct xt_table_info *private = xt_table_get_private_protected(table);
 
 	/* We need atomic snapshot of counters: rest doesn't change
 	 * (other than comefrom, which userspace doesn't care
@@ -673,7 +673,7 @@ static int copy_entries_to_user(unsigned int total_size,
 	unsigned int off, num;
 	const struct arpt_entry *e;
 	struct xt_counters *counters;
-	struct xt_table_info *private = table->private;
+	struct xt_table_info *private = xt_table_get_private_protected(table);
 	int ret = 0;
 	void *loc_cpu_entry;
 
@@ -807,7 +807,7 @@ static int get_info(struct net *net, void __user *user, const int *len)
 	t = xt_request_find_table_lock(net, NFPROTO_ARP, name);
 	if (!IS_ERR(t)) {
 		struct arpt_getinfo info;
-		const struct xt_table_info *private = t->private;
+		const struct xt_table_info *private = xt_table_get_private_protected(t);
 #ifdef CONFIG_COMPAT
 		struct xt_table_info tmp;
 
@@ -860,7 +860,7 @@ static int get_entries(struct net *net, struct arpt_get_entries __user *uptr,
 
 	t = xt_find_table_lock(net, NFPROTO_ARP, get.name);
 	if (!IS_ERR(t)) {
-		const struct xt_table_info *private = t->private;
+		const struct xt_table_info *private = xt_table_get_private_protected(t);
 
 		if (get.size == private->size)
 			ret = copy_entries_to_user(private->size,
@@ -1017,7 +1017,7 @@ static int do_add_counters(struct net *net, sockptr_t arg, unsigned int len)
 	}
 
 	local_bh_disable();
-	private = t->private;
+	private = xt_table_get_private_protected(t);
 	if (private->number != tmp.num_counters) {
 		ret = -EINVAL;
 		goto unlock_up_free;
@@ -1330,7 +1330,7 @@ static int compat_copy_entries_to_user(unsigned int total_size,
 				       void __user *userptr)
 {
 	struct xt_counters *counters;
-	const struct xt_table_info *private = table->private;
+	const struct xt_table_info *private = xt_table_get_private_protected(table);
 	void __user *pos;
 	unsigned int size;
 	int ret = 0;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index f15bc21d7301..6e2851f8d3a3 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -258,7 +258,7 @@ ipt_do_table(struct sk_buff *skb,
 	WARN_ON(!(table->valid_hooks & (1 << hook)));
 	local_bh_disable();
 	addend = xt_write_recseq_begin();
-	private = READ_ONCE(table->private); /* Address dependency. */
+	private = rcu_access_pointer(table->private);
 	cpu        = smp_processor_id();
 	table_base = private->entries;
 	jumpstack  = (struct ipt_entry **)private->jumpstack[cpu];
@@ -791,7 +791,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table)
 {
 	unsigned int countersize;
 	struct xt_counters *counters;
-	const struct xt_table_info *private = table->private;
+	const struct xt_table_info *private = xt_table_get_private_protected(table);
 
 	/* We need atomic snapshot of counters: rest doesn't change
 	   (other than comefrom, which userspace doesn't care
@@ -815,7 +815,7 @@ copy_entries_to_user(unsigned int total_size,
 	unsigned int off, num;
 	const struct ipt_entry *e;
 	struct xt_counters *counters;
-	const struct xt_table_info *private = table->private;
+	const struct xt_table_info *private = xt_table_get_private_protected(table);
 	int ret = 0;
 	const void *loc_cpu_entry;
 
@@ -964,7 +964,7 @@ static int get_info(struct net *net, void __user *user, const int *len)
 	t = xt_request_find_table_lock(net, AF_INET, name);
 	if (!IS_ERR(t)) {
 		struct ipt_getinfo info;
-		const struct xt_table_info *private = t->private;
+		const struct xt_table_info *private = xt_table_get_private_protected(t);
 #ifdef CONFIG_COMPAT
 		struct xt_table_info tmp;
 
@@ -1018,7 +1018,7 @@ get_entries(struct net *net, struct ipt_get_entries __user *uptr,
 
 	t = xt_find_table_lock(net, AF_INET, get.name);
 	if (!IS_ERR(t)) {
-		const struct xt_table_info *private = t->private;
+		const struct xt_table_info *private = xt_table_get_private_protected(t);
 		if (get.size == private->size)
 			ret = copy_entries_to_user(private->size,
 						   t, uptr->entrytable);
@@ -1173,7 +1173,7 @@ do_add_counters(struct net *net, sockptr_t arg, unsigned int len)
 	}
 
 	local_bh_disable();
-	private = t->private;
+	private = xt_table_get_private_protected(t);
 	if (private->number != tmp.num_counters) {
 		ret = -EINVAL;
 		goto unlock_up_free;
@@ -1543,7 +1543,7 @@ compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table,
 			    void __user *userptr)
 {
 	struct xt_counters *counters;
-	const struct xt_table_info *private = table->private;
+	const struct xt_table_info *private = xt_table_get_private_protected(table);
 	void __user *pos;
 	unsigned int size;
 	int ret = 0;
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 2e2119bfcf13..c4f532f4d311 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -280,7 +280,7 @@ ip6t_do_table(struct sk_buff *skb,
 
 	local_bh_disable();
 	addend = xt_write_recseq_begin();
-	private = READ_ONCE(table->private); /* Address dependency. */
+	private = rcu_access_pointer(table->private);
 	cpu        = smp_processor_id();
 	table_base = private->entries;
 	jumpstack  = (struct ip6t_entry **)private->jumpstack[cpu];
@@ -807,7 +807,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table)
 {
 	unsigned int countersize;
 	struct xt_counters *counters;
-	const struct xt_table_info *private = table->private;
+	const struct xt_table_info *private = xt_table_get_private_protected(table);
 
 	/* We need atomic snapshot of counters: rest doesn't change
 	   (other than comefrom, which userspace doesn't care
@@ -831,7 +831,7 @@ copy_entries_to_user(unsigned int total_size,
 	unsigned int off, num;
 	const struct ip6t_entry *e;
 	struct xt_counters *counters;
-	const struct xt_table_info *private = table->private;
+	const struct xt_table_info *private = xt_table_get_private_protected(table);
 	int ret = 0;
 	const void *loc_cpu_entry;
 
@@ -980,7 +980,7 @@ static int get_info(struct net *net, void __user *user, const int *len)
 	t = xt_request_find_table_lock(net, AF_INET6, name);
 	if (!IS_ERR(t)) {
 		struct ip6t_getinfo info;
-		const struct xt_table_info *private = t->private;
+		const struct xt_table_info *private = xt_table_get_private_protected(t);
 #ifdef CONFIG_COMPAT
 		struct xt_table_info tmp;
 
@@ -1035,7 +1035,7 @@ get_entries(struct net *net, struct ip6t_get_entries __user *uptr,
 
 	t = xt_find_table_lock(net, AF_INET6, get.name);
 	if (!IS_ERR(t)) {
-		struct xt_table_info *private = t->private;
+		struct xt_table_info *private = xt_table_get_private_protected(t);
 		if (get.size == private->size)
 			ret = copy_entries_to_user(private->size,
 						   t, uptr->entrytable);
@@ -1189,7 +1189,7 @@ do_add_counters(struct net *net, sockptr_t arg, unsigned int len)
 	}
 
 	local_bh_disable();
-	private = t->private;
+	private = xt_table_get_private_protected(t);
 	if (private->number != tmp.num_counters) {
 		ret = -EINVAL;
 		goto unlock_up_free;
@@ -1552,7 +1552,7 @@ compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table,
 			    void __user *userptr)
 {
 	struct xt_counters *counters;
-	const struct xt_table_info *private = table->private;
+	const struct xt_table_info *private = xt_table_get_private_protected(table);
 	void __user *pos;
 	unsigned int size;
 	int ret = 0;
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index af22dbe85e2c..acce622582e3 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -1349,6 +1349,14 @@ struct xt_counters *xt_counters_alloc(unsigned int counters)
 }
 EXPORT_SYMBOL(xt_counters_alloc);
 
+struct xt_table_info
+*xt_table_get_private_protected(const struct xt_table *table)
+{
+	return rcu_dereference_protected(table->private,
+					 mutex_is_locked(&xt[table->af].mutex));
+}
+EXPORT_SYMBOL(xt_table_get_private_protected);
+
 struct xt_table_info *
 xt_replace_table(struct xt_table *table,
 	      unsigned int num_counters,
@@ -1356,7 +1364,6 @@ xt_replace_table(struct xt_table *table,
 	      int *error)
 {
 	struct xt_table_info *private;
-	unsigned int cpu;
 	int ret;
 
 	ret = xt_jumpstack_alloc(newinfo);
@@ -1366,47 +1373,20 @@ xt_replace_table(struct xt_table *table,
 	}
 
 	/* Do the substitution. */
-	local_bh_disable();
-	private = table->private;
+	private = xt_table_get_private_protected(table);
 
 	/* Check inside lock: is the old number correct? */
 	if (num_counters != private->number) {
 		pr_debug("num_counters != table->private->number (%u/%u)\n",
 			 num_counters, private->number);
-		local_bh_enable();
 		*error = -EAGAIN;
 		return NULL;
 	}
 
 	newinfo->initial_entries = private->initial_entries;
-	/*
-	 * Ensure contents of newinfo are visible before assigning to
-	 * private.
-	 */
-	smp_wmb();
-	table->private = newinfo;
-
-	/* make sure all cpus see new ->private value */
-	smp_wmb();
 
-	/*
-	 * Even though table entries have now been swapped, other CPU's
-	 * may still be using the old entries...
-	 */
-	local_bh_enable();
-
-	/* ... so wait for even xt_recseq on all cpus */
-	for_each_possible_cpu(cpu) {
-		seqcount_t *s = &per_cpu(xt_recseq, cpu);
-		u32 seq = raw_read_seqcount(s);
-
-		if (seq & 1) {
-			do {
-				cond_resched();
-				cpu_relax();
-			} while (seq == raw_read_seqcount(s));
-		}
-	}
+	rcu_assign_pointer(table->private, newinfo);
+	synchronize_rcu();
 
 	audit_log_nfcfg(table->name, table->af, private->number,
 			!private->number ? AUDIT_XT_OP_REGISTER :
@@ -1442,12 +1422,12 @@ struct xt_table *xt_register_table(struct net *net,
 	}
 
 	/* Simplifies replace_table code. */
-	table->private = bootstrap;
+	rcu_assign_pointer(table->private, bootstrap);
 
 	if (!xt_replace_table(table, 0, newinfo, &ret))
 		goto unlock;
 
-	private = table->private;
+	private = xt_table_get_private_protected(table);
 	pr_debug("table->private->number = %u\n", private->number);
 
 	/* save number of initial entries */
@@ -1470,7 +1450,8 @@ void *xt_unregister_table(struct xt_table *table)
 	struct xt_table_info *private;
 
 	mutex_lock(&xt[table->af].mutex);
-	private = table->private;
+	private = xt_table_get_private_protected(table);
+	RCU_INIT_POINTER(table->private, NULL);
 	list_del(&table->list);
 	mutex_unlock(&xt[table->af].mutex);
 	audit_log_nfcfg(table->name, table->af, private->number,
-- 
cgit v1.2.3


From 2f24dfb71208eeb0174f08dd56ca6d3c17b279a5 Mon Sep 17 00:00:00 2001
From: John Garry <john.garry@huawei.com>
Date: Fri, 4 Dec 2020 02:34:50 +0800
Subject: iommu: Delete split_and_remove_iova()

Function split_and_remove_iova() has not been referenced since commit
e70b081c6f37 ("iommu/vt-d: Remove IOVA handling code from the non-dma_ops
path"), so delete it.

Signed-off-by: John Garry <john.garry@huawei.com>
Link: https://lore.kernel.org/r/1607020492-189471-2-git-send-email-john.garry@huawei.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/iova.c | 41 -----------------------------------------
 include/linux/iova.h | 10 ----------
 2 files changed, 51 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index ff59d8aa3041..3331c040b2b0 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -742,47 +742,6 @@ copy_reserved_iova(struct iova_domain *from, struct iova_domain *to)
 }
 EXPORT_SYMBOL_GPL(copy_reserved_iova);
 
-struct iova *
-split_and_remove_iova(struct iova_domain *iovad, struct iova *iova,
-		      unsigned long pfn_lo, unsigned long pfn_hi)
-{
-	unsigned long flags;
-	struct iova *prev = NULL, *next = NULL;
-
-	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
-	if (iova->pfn_lo < pfn_lo) {
-		prev = alloc_and_init_iova(iova->pfn_lo, pfn_lo - 1);
-		if (prev == NULL)
-			goto error;
-	}
-	if (iova->pfn_hi > pfn_hi) {
-		next = alloc_and_init_iova(pfn_hi + 1, iova->pfn_hi);
-		if (next == NULL)
-			goto error;
-	}
-
-	__cached_rbnode_delete_update(iovad, iova);
-	rb_erase(&iova->node, &iovad->rbroot);
-
-	if (prev) {
-		iova_insert_rbtree(&iovad->rbroot, prev, NULL);
-		iova->pfn_lo = pfn_lo;
-	}
-	if (next) {
-		iova_insert_rbtree(&iovad->rbroot, next, NULL);
-		iova->pfn_hi = pfn_hi;
-	}
-	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
-
-	return iova;
-
-error:
-	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
-	if (prev)
-		free_iova_mem(prev);
-	return NULL;
-}
-
 /*
  * Magazine caches for IOVA ranges.  For an introduction to magazines,
  * see the USENIX 2001 paper "Magazines and Vmem: Extending the Slab
diff --git a/include/linux/iova.h b/include/linux/iova.h
index a0637abffee8..a77add571c50 100644
--- a/include/linux/iova.h
+++ b/include/linux/iova.h
@@ -160,8 +160,6 @@ int init_iova_flush_queue(struct iova_domain *iovad,
 			  iova_flush_cb flush_cb, iova_entry_dtor entry_dtor);
 struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn);
 void put_iova_domain(struct iova_domain *iovad);
-struct iova *split_and_remove_iova(struct iova_domain *iovad,
-	struct iova *iova, unsigned long pfn_lo, unsigned long pfn_hi);
 void free_cpu_cached_iovas(unsigned int cpu, struct iova_domain *iovad);
 #else
 static inline int iova_cache_get(void)
@@ -258,14 +256,6 @@ static inline void put_iova_domain(struct iova_domain *iovad)
 {
 }
 
-static inline struct iova *split_and_remove_iova(struct iova_domain *iovad,
-						 struct iova *iova,
-						 unsigned long pfn_lo,
-						 unsigned long pfn_hi)
-{
-	return NULL;
-}
-
 static inline void free_cpu_cached_iovas(unsigned int cpu,
 					 struct iova_domain *iovad)
 {
-- 
cgit v1.2.3


From 51b70b817b187e48155fc492adb9ce80bdb21b70 Mon Sep 17 00:00:00 2001
From: John Garry <john.garry@huawei.com>
Date: Fri, 4 Dec 2020 02:34:51 +0800
Subject: iommu: Stop exporting alloc_iova_mem()

It is not used outside iova.c

Signed-off-by: John Garry <john.garry@huawei.com>
Link: https://lore.kernel.org/r/1607020492-189471-3-git-send-email-john.garry@huawei.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/iova.c | 3 +--
 include/linux/iova.h | 6 ------
 2 files changed, 1 insertion(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index 3331c040b2b0..bb5cb67ee311 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -243,11 +243,10 @@ static struct kmem_cache *iova_cache;
 static unsigned int iova_cache_users;
 static DEFINE_MUTEX(iova_cache_mutex);
 
-struct iova *alloc_iova_mem(void)
+static struct iova *alloc_iova_mem(void)
 {
 	return kmem_cache_zalloc(iova_cache, GFP_ATOMIC | __GFP_NOWARN);
 }
-EXPORT_SYMBOL(alloc_iova_mem);
 
 void free_iova_mem(struct iova *iova)
 {
diff --git a/include/linux/iova.h b/include/linux/iova.h
index a77add571c50..d8c011b6d4ed 100644
--- a/include/linux/iova.h
+++ b/include/linux/iova.h
@@ -136,7 +136,6 @@ static inline unsigned long iova_pfn(struct iova_domain *iovad, dma_addr_t iova)
 int iova_cache_get(void);
 void iova_cache_put(void);
 
-struct iova *alloc_iova_mem(void);
 void free_iova_mem(struct iova *iova);
 void free_iova(struct iova_domain *iovad, unsigned long pfn);
 void __free_iova(struct iova_domain *iovad, struct iova *iova);
@@ -171,11 +170,6 @@ static inline void iova_cache_put(void)
 {
 }
 
-static inline struct iova *alloc_iova_mem(void)
-{
-	return NULL;
-}
-
 static inline void free_iova_mem(struct iova *iova)
 {
 }
-- 
cgit v1.2.3


From 176cfc187c24287a363e7612cd2385ba40c2042b Mon Sep 17 00:00:00 2001
From: John Garry <john.garry@huawei.com>
Date: Fri, 4 Dec 2020 02:34:52 +0800
Subject: iommu: Stop exporting free_iova_mem()

It has no user outside iova.c

Signed-off-by: John Garry <john.garry@huawei.com>
Link: https://lore.kernel.org/r/1607020492-189471-4-git-send-email-john.garry@huawei.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/iova.c | 3 +--
 include/linux/iova.h | 5 -----
 2 files changed, 1 insertion(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index bb5cb67ee311..4bb3293ae4d7 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -248,12 +248,11 @@ static struct iova *alloc_iova_mem(void)
 	return kmem_cache_zalloc(iova_cache, GFP_ATOMIC | __GFP_NOWARN);
 }
 
-void free_iova_mem(struct iova *iova)
+static void free_iova_mem(struct iova *iova)
 {
 	if (iova->pfn_lo != IOVA_ANCHOR)
 		kmem_cache_free(iova_cache, iova);
 }
-EXPORT_SYMBOL(free_iova_mem);
 
 int iova_cache_get(void)
 {
diff --git a/include/linux/iova.h b/include/linux/iova.h
index d8c011b6d4ed..76e16ae20729 100644
--- a/include/linux/iova.h
+++ b/include/linux/iova.h
@@ -136,7 +136,6 @@ static inline unsigned long iova_pfn(struct iova_domain *iovad, dma_addr_t iova)
 int iova_cache_get(void);
 void iova_cache_put(void);
 
-void free_iova_mem(struct iova *iova);
 void free_iova(struct iova_domain *iovad, unsigned long pfn);
 void __free_iova(struct iova_domain *iovad, struct iova *iova);
 struct iova *alloc_iova(struct iova_domain *iovad, unsigned long size,
@@ -170,10 +169,6 @@ static inline void iova_cache_put(void)
 {
 }
 
-static inline void free_iova_mem(struct iova *iova)
-{
-}
-
 static inline void free_iova(struct iova_domain *iovad, unsigned long pfn)
 {
 }
-- 
cgit v1.2.3


From fefe8527a1e0e0014946c6b5b3b2e40cb32bb5d3 Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Wed, 25 Nov 2020 17:29:39 +0000
Subject: iommu/io-pgtable: Remove tlb_flush_leaf

The only user of tlb_flush_leaf is a particularly hairy corner of the
Arm short-descriptor code, which wants a synchronous invalidation to
minimise the races inherent in trying to split a large page mapping.
This is already far enough into "here be dragons" territory that no
sensible caller should ever hit it, and thus it really doesn't need
optimising. Although using tlb_flush_walk there may technically be
more heavyweight than needed, it does the job and saves everyone else
having to carry around useless baggage.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Reviewed-by: Steven Price <steven.price@arm.com>
Link: https://lore.kernel.org/r/9844ab0c5cb3da8b2f89c6c2da16941910702b41.1606324115.git.robin.murphy@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/gpu/drm/msm/msm_iommu.c             |  1 -
 drivers/gpu/drm/panfrost/panfrost_mmu.c     |  7 -------
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c |  7 -------
 drivers/iommu/arm/arm-smmu/arm-smmu.c       | 25 +++----------------------
 drivers/iommu/arm/arm-smmu/qcom_iommu.c     |  8 --------
 drivers/iommu/io-pgtable-arm-v7s.c          |  3 +--
 drivers/iommu/io-pgtable-arm.c              |  1 -
 drivers/iommu/ipmmu-vmsa.c                  |  1 -
 drivers/iommu/msm_iommu.c                   |  7 -------
 drivers/iommu/mtk_iommu.c                   |  1 -
 include/linux/io-pgtable.h                  | 11 -----------
 11 files changed, 4 insertions(+), 68 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c
index 22ac7c692a81..50d881794758 100644
--- a/drivers/gpu/drm/msm/msm_iommu.c
+++ b/drivers/gpu/drm/msm/msm_iommu.c
@@ -139,7 +139,6 @@ static void msm_iommu_tlb_add_page(struct iommu_iotlb_gather *gather,
 static const struct iommu_flush_ops null_tlb_ops = {
 	.tlb_flush_all = msm_iommu_tlb_flush_all,
 	.tlb_flush_walk = msm_iommu_tlb_flush_walk,
-	.tlb_flush_leaf = msm_iommu_tlb_flush_walk,
 	.tlb_add_page = msm_iommu_tlb_add_page,
 };
 
diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c
index 776448c527ea..c186914cc4f9 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c
@@ -347,16 +347,9 @@ static void mmu_tlb_flush_walk(unsigned long iova, size_t size, size_t granule,
 	mmu_tlb_sync_context(cookie);
 }
 
-static void mmu_tlb_flush_leaf(unsigned long iova, size_t size, size_t granule,
-			       void *cookie)
-{
-	mmu_tlb_sync_context(cookie);
-}
-
 static const struct iommu_flush_ops mmu_tlb_ops = {
 	.tlb_flush_all	= mmu_tlb_inv_context_s1,
 	.tlb_flush_walk = mmu_tlb_flush_walk,
-	.tlb_flush_leaf = mmu_tlb_flush_leaf,
 };
 
 int panfrost_mmu_pgtable_alloc(struct panfrost_file_priv *priv)
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index 2ddf5ecc75f8..8ca7415d785d 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -1760,16 +1760,9 @@ static void arm_smmu_tlb_inv_walk(unsigned long iova, size_t size,
 	arm_smmu_tlb_inv_range(iova, size, granule, false, cookie);
 }
 
-static void arm_smmu_tlb_inv_leaf(unsigned long iova, size_t size,
-				  size_t granule, void *cookie)
-{
-	arm_smmu_tlb_inv_range(iova, size, granule, true, cookie);
-}
-
 static const struct iommu_flush_ops arm_smmu_flush_ops = {
 	.tlb_flush_all	= arm_smmu_tlb_inv_context,
 	.tlb_flush_walk = arm_smmu_tlb_inv_walk,
-	.tlb_flush_leaf = arm_smmu_tlb_inv_leaf,
 	.tlb_add_page	= arm_smmu_tlb_inv_page_nosync,
 };
 
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
index d8979bb71fc0..d8c6bfde6a61 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -333,14 +333,6 @@ static void arm_smmu_tlb_inv_walk_s1(unsigned long iova, size_t size,
 	arm_smmu_tlb_sync_context(cookie);
 }
 
-static void arm_smmu_tlb_inv_leaf_s1(unsigned long iova, size_t size,
-				     size_t granule, void *cookie)
-{
-	arm_smmu_tlb_inv_range_s1(iova, size, granule, cookie,
-				  ARM_SMMU_CB_S1_TLBIVAL);
-	arm_smmu_tlb_sync_context(cookie);
-}
-
 static void arm_smmu_tlb_add_page_s1(struct iommu_iotlb_gather *gather,
 				     unsigned long iova, size_t granule,
 				     void *cookie)
@@ -357,14 +349,6 @@ static void arm_smmu_tlb_inv_walk_s2(unsigned long iova, size_t size,
 	arm_smmu_tlb_sync_context(cookie);
 }
 
-static void arm_smmu_tlb_inv_leaf_s2(unsigned long iova, size_t size,
-				     size_t granule, void *cookie)
-{
-	arm_smmu_tlb_inv_range_s2(iova, size, granule, cookie,
-				  ARM_SMMU_CB_S2_TLBIIPAS2L);
-	arm_smmu_tlb_sync_context(cookie);
-}
-
 static void arm_smmu_tlb_add_page_s2(struct iommu_iotlb_gather *gather,
 				     unsigned long iova, size_t granule,
 				     void *cookie)
@@ -373,8 +357,8 @@ static void arm_smmu_tlb_add_page_s2(struct iommu_iotlb_gather *gather,
 				  ARM_SMMU_CB_S2_TLBIIPAS2L);
 }
 
-static void arm_smmu_tlb_inv_any_s2_v1(unsigned long iova, size_t size,
-				       size_t granule, void *cookie)
+static void arm_smmu_tlb_inv_walk_s2_v1(unsigned long iova, size_t size,
+					size_t granule, void *cookie)
 {
 	arm_smmu_tlb_inv_context_s2(cookie);
 }
@@ -401,21 +385,18 @@ static void arm_smmu_tlb_add_page_s2_v1(struct iommu_iotlb_gather *gather,
 static const struct iommu_flush_ops arm_smmu_s1_tlb_ops = {
 	.tlb_flush_all	= arm_smmu_tlb_inv_context_s1,
 	.tlb_flush_walk	= arm_smmu_tlb_inv_walk_s1,
-	.tlb_flush_leaf	= arm_smmu_tlb_inv_leaf_s1,
 	.tlb_add_page	= arm_smmu_tlb_add_page_s1,
 };
 
 static const struct iommu_flush_ops arm_smmu_s2_tlb_ops_v2 = {
 	.tlb_flush_all	= arm_smmu_tlb_inv_context_s2,
 	.tlb_flush_walk	= arm_smmu_tlb_inv_walk_s2,
-	.tlb_flush_leaf	= arm_smmu_tlb_inv_leaf_s2,
 	.tlb_add_page	= arm_smmu_tlb_add_page_s2,
 };
 
 static const struct iommu_flush_ops arm_smmu_s2_tlb_ops_v1 = {
 	.tlb_flush_all	= arm_smmu_tlb_inv_context_s2,
-	.tlb_flush_walk	= arm_smmu_tlb_inv_any_s2_v1,
-	.tlb_flush_leaf	= arm_smmu_tlb_inv_any_s2_v1,
+	.tlb_flush_walk	= arm_smmu_tlb_inv_walk_s2_v1,
 	.tlb_add_page	= arm_smmu_tlb_add_page_s2_v1,
 };
 
diff --git a/drivers/iommu/arm/arm-smmu/qcom_iommu.c b/drivers/iommu/arm/arm-smmu/qcom_iommu.c
index b30d6c966e2c..7f280c8d5c53 100644
--- a/drivers/iommu/arm/arm-smmu/qcom_iommu.c
+++ b/drivers/iommu/arm/arm-smmu/qcom_iommu.c
@@ -185,13 +185,6 @@ static void qcom_iommu_tlb_flush_walk(unsigned long iova, size_t size,
 	qcom_iommu_tlb_sync(cookie);
 }
 
-static void qcom_iommu_tlb_flush_leaf(unsigned long iova, size_t size,
-				      size_t granule, void *cookie)
-{
-	qcom_iommu_tlb_inv_range_nosync(iova, size, granule, true, cookie);
-	qcom_iommu_tlb_sync(cookie);
-}
-
 static void qcom_iommu_tlb_add_page(struct iommu_iotlb_gather *gather,
 				    unsigned long iova, size_t granule,
 				    void *cookie)
@@ -202,7 +195,6 @@ static void qcom_iommu_tlb_add_page(struct iommu_iotlb_gather *gather,
 static const struct iommu_flush_ops qcom_flush_ops = {
 	.tlb_flush_all	= qcom_iommu_tlb_inv_context,
 	.tlb_flush_walk = qcom_iommu_tlb_flush_walk,
-	.tlb_flush_leaf = qcom_iommu_tlb_flush_leaf,
 	.tlb_add_page	= qcom_iommu_tlb_add_page,
 };
 
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index 359b96b0fa3e..1d92ac948db7 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -584,7 +584,7 @@ static arm_v7s_iopte arm_v7s_split_cont(struct arm_v7s_io_pgtable *data,
 	__arm_v7s_pte_sync(ptep, ARM_V7S_CONT_PAGES, &iop->cfg);
 
 	size *= ARM_V7S_CONT_PAGES;
-	io_pgtable_tlb_flush_leaf(iop, iova, size, size);
+	io_pgtable_tlb_flush_walk(iop, iova, size, size);
 	return pte;
 }
 
@@ -866,7 +866,6 @@ static void __init dummy_tlb_add_page(struct iommu_iotlb_gather *gather,
 static const struct iommu_flush_ops dummy_tlb_ops __initconst = {
 	.tlb_flush_all	= dummy_tlb_flush_all,
 	.tlb_flush_walk	= dummy_tlb_flush,
-	.tlb_flush_leaf	= dummy_tlb_flush,
 	.tlb_add_page	= dummy_tlb_add_page,
 };
 
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 135f57b37bbd..49ad8d2a82df 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -1085,7 +1085,6 @@ static void __init dummy_tlb_add_page(struct iommu_iotlb_gather *gather,
 static const struct iommu_flush_ops dummy_tlb_ops __initconst = {
 	.tlb_flush_all	= dummy_tlb_flush_all,
 	.tlb_flush_walk	= dummy_tlb_flush,
-	.tlb_flush_leaf	= dummy_tlb_flush,
 	.tlb_add_page	= dummy_tlb_add_page,
 };
 
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index 0f18abda0e20..d71f10257f15 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -325,7 +325,6 @@ static void ipmmu_tlb_flush(unsigned long iova, size_t size,
 static const struct iommu_flush_ops ipmmu_flush_ops = {
 	.tlb_flush_all = ipmmu_tlb_flush_all,
 	.tlb_flush_walk = ipmmu_tlb_flush,
-	.tlb_flush_leaf = ipmmu_tlb_flush,
 };
 
 /* -----------------------------------------------------------------------------
diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c
index 3615cd6241c4..040e85f70861 100644
--- a/drivers/iommu/msm_iommu.c
+++ b/drivers/iommu/msm_iommu.c
@@ -174,12 +174,6 @@ static void __flush_iotlb_walk(unsigned long iova, size_t size,
 	__flush_iotlb_range(iova, size, granule, false, cookie);
 }
 
-static void __flush_iotlb_leaf(unsigned long iova, size_t size,
-			       size_t granule, void *cookie)
-{
-	__flush_iotlb_range(iova, size, granule, true, cookie);
-}
-
 static void __flush_iotlb_page(struct iommu_iotlb_gather *gather,
 			       unsigned long iova, size_t granule, void *cookie)
 {
@@ -189,7 +183,6 @@ static void __flush_iotlb_page(struct iommu_iotlb_gather *gather,
 static const struct iommu_flush_ops msm_iommu_flush_ops = {
 	.tlb_flush_all = __flush_iotlb,
 	.tlb_flush_walk = __flush_iotlb_walk,
-	.tlb_flush_leaf = __flush_iotlb_leaf,
 	.tlb_add_page = __flush_iotlb_page,
 };
 
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index c072cee532c2..8e56cec532e7 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -240,7 +240,6 @@ static void mtk_iommu_tlb_flush_page_nosync(struct iommu_iotlb_gather *gather,
 static const struct iommu_flush_ops mtk_iommu_flush_ops = {
 	.tlb_flush_all = mtk_iommu_tlb_flush_all,
 	.tlb_flush_walk = mtk_iommu_tlb_flush_range_sync,
-	.tlb_flush_leaf = mtk_iommu_tlb_flush_range_sync,
 	.tlb_add_page = mtk_iommu_tlb_flush_page_nosync,
 };
 
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index fb4d5a763e0c..ea727eb1a1a9 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -25,8 +25,6 @@ enum io_pgtable_fmt {
  * @tlb_flush_walk: Synchronously invalidate all intermediate TLB state
  *                  (sometimes referred to as the "walk cache") for a virtual
  *                  address range.
- * @tlb_flush_leaf: Synchronously invalidate all leaf TLB state for a virtual
- *                  address range.
  * @tlb_add_page:   Optional callback to queue up leaf TLB invalidation for a
  *                  single page.  IOMMUs that cannot batch TLB invalidation
  *                  operations efficiently will typically issue them here, but
@@ -40,8 +38,6 @@ struct iommu_flush_ops {
 	void (*tlb_flush_all)(void *cookie);
 	void (*tlb_flush_walk)(unsigned long iova, size_t size, size_t granule,
 			       void *cookie);
-	void (*tlb_flush_leaf)(unsigned long iova, size_t size, size_t granule,
-			       void *cookie);
 	void (*tlb_add_page)(struct iommu_iotlb_gather *gather,
 			     unsigned long iova, size_t granule, void *cookie);
 };
@@ -228,13 +224,6 @@ io_pgtable_tlb_flush_walk(struct io_pgtable *iop, unsigned long iova,
 	iop->cfg.tlb->tlb_flush_walk(iova, size, granule, iop->cookie);
 }
 
-static inline void
-io_pgtable_tlb_flush_leaf(struct io_pgtable *iop, unsigned long iova,
-			  size_t size, size_t granule)
-{
-	iop->cfg.tlb->tlb_flush_leaf(iova, size, granule, iop->cookie);
-}
-
 static inline void
 io_pgtable_tlb_add_page(struct io_pgtable *iop,
 			struct iommu_iotlb_gather * gather, unsigned long iova,
-- 
cgit v1.2.3


From 1080399542075bb0e9d46ea80418d76784d1ece8 Mon Sep 17 00:00:00 2001
From: Pavankumar Kondeti <pkondeti@codeaurora.org>
Date: Sat, 28 Nov 2020 07:09:23 +0530
Subject: PM / EM: Micro optimization in em_cpu_energy

When the sum of the utilization of CPUs in a power domain is zero,
return the energy as 0 without doing any computations.

Acked-by: Quentin Perret <qperret@google.com>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/energy_model.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h
index 9618c0a46ef4..757fc60658fa 100644
--- a/include/linux/energy_model.h
+++ b/include/linux/energy_model.h
@@ -106,6 +106,9 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd,
 	struct em_perf_state *ps;
 	int i, cpu;
 
+	if (!sum_util)
+		return 0;
+
 	/*
 	 * In order to predict the performance state, map the utilization of
 	 * the most utilized CPU of the performance domain to a requested
-- 
cgit v1.2.3


From b577562ccc072ab4b09243740ebeca52309eecd2 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 8 Dec 2020 13:16:22 +0100
Subject: PCI: Remove unused HAVE_PCI_SET_MWI

Remove unused HAVE_PCI_SET_MWI.

Link: https://lore.kernel.org/r/03f20cac-708d-7897-c7c7-cb4e63cfd991@gmail.com
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 include/linux/pci.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/pci.h b/include/linux/pci.h
index 22207a79762c..fe824afc0e91 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1190,7 +1190,6 @@ void pci_clear_master(struct pci_dev *dev);
 
 int pci_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state state);
 int pci_set_cacheline_size(struct pci_dev *dev);
-#define HAVE_PCI_SET_MWI
 int __must_check pci_set_mwi(struct pci_dev *dev);
 int __must_check pcim_set_mwi(struct pci_dev *dev);
 int pci_try_set_mwi(struct pci_dev *dev);
-- 
cgit v1.2.3


From f119cc9818eb33b66e977ad3af75aef6500bbdc3 Mon Sep 17 00:00:00 2001
From: Fugang Duan <fugang.duan@nxp.com>
Date: Mon, 7 Dec 2020 18:51:41 +0800
Subject: net: stmmac: overwrite the dma_cap.addr64 according to HW design

The current IP register MAC_HW_Feature1[ADDR64] only defines
32/40/64 bit width, but some SOCs support others like i.MX8MP
support 34 bits but it maps to 40 bits width in MAC_HW_Feature1[ADDR64].
So overwrite dma_cap.addr64 according to HW real design.

Fixes: 94abdad6974a ("net: ethernet: dwmac: add ethernet glue logic for NXP imx8 chip")
Signed-off-by: Fugang Duan <fugang.duan@nxp.com>
Signed-off-by: Joakim Zhang <qiangqing.zhang@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c   | 9 +--------
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 8 ++++++++
 include/linux/stmmac.h                            | 1 +
 3 files changed, 10 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
index efef5476a577..223f69da7e95 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
@@ -246,13 +246,7 @@ static int imx_dwmac_probe(struct platform_device *pdev)
 		goto err_parse_dt;
 	}
 
-	ret = dma_set_mask_and_coherent(&pdev->dev,
-					DMA_BIT_MASK(dwmac->ops->addr_width));
-	if (ret) {
-		dev_err(&pdev->dev, "DMA mask set failed\n");
-		goto err_dma_mask;
-	}
-
+	plat_dat->addr64 = dwmac->ops->addr_width;
 	plat_dat->init = imx_dwmac_init;
 	plat_dat->exit = imx_dwmac_exit;
 	plat_dat->fix_mac_speed = imx_dwmac_fix_speed;
@@ -272,7 +266,6 @@ static int imx_dwmac_probe(struct platform_device *pdev)
 err_dwmac_init:
 err_drv_probe:
 	imx_dwmac_exit(pdev, plat_dat->bsp_priv);
-err_dma_mask:
 err_parse_dt:
 err_match_data:
 	stmmac_remove_config_dt(pdev, plat_dat);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index d2521ebb8217..c33db79cdd0a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -4945,6 +4945,14 @@ int stmmac_dvr_probe(struct device *device,
 		dev_info(priv->device, "SPH feature enabled\n");
 	}
 
+	/* The current IP register MAC_HW_Feature1[ADDR64] only define
+	 * 32/40/64 bit width, but some SOC support others like i.MX8MP
+	 * support 34 bits but it map to 40 bits width in MAC_HW_Feature1[ADDR64].
+	 * So overwrite dma_cap.addr64 according to HW real design.
+	 */
+	if (priv->plat->addr64)
+		priv->dma_cap.addr64 = priv->plat->addr64;
+
 	if (priv->dma_cap.addr64) {
 		ret = dma_set_mask_and_coherent(device,
 				DMA_BIT_MASK(priv->dma_cap.addr64));
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 628e28903b8b..15ca6b4167cc 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -170,6 +170,7 @@ struct plat_stmmacenet_data {
 	int unicast_filter_entries;
 	int tx_fifo_size;
 	int rx_fifo_size;
+	u32 addr64;
 	u32 rx_queues_to_use;
 	u32 tx_queues_to_use;
 	u8 rx_sched_algorithm;
-- 
cgit v1.2.3


From b60da4955f53d1f50e44351a9c3a37a92503079e Mon Sep 17 00:00:00 2001
From: Florent Revest <revest@chromium.org>
Date: Tue, 8 Dec 2020 18:36:23 +0100
Subject: bpf: Only provide bpf_sock_from_file with CONFIG_NET

This moves the bpf_sock_from_file definition into net/core/filter.c
which only gets compiled with CONFIG_NET and also moves the helper proto
usage next to other tracing helpers that are conditional on CONFIG_NET.

This avoids
  ld: kernel/trace/bpf_trace.o: in function `bpf_sock_from_file':
  bpf_trace.c:(.text+0xe23): undefined reference to `sock_from_file'
When compiling a kernel with BPF and without NET.

Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Florent Revest <revest@chromium.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: KP Singh <kpsingh@kernel.org>
Link: https://lore.kernel.org/bpf/20201208173623.1136863-1-revest@chromium.org
---
 include/linux/bpf.h      |  1 +
 kernel/trace/bpf_trace.c | 22 ++--------------------
 net/core/filter.c        | 18 ++++++++++++++++++
 3 files changed, 21 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index d05e75ed8c1b..07cb5d15e743 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1859,6 +1859,7 @@ extern const struct bpf_func_proto bpf_snprintf_btf_proto;
 extern const struct bpf_func_proto bpf_per_cpu_ptr_proto;
 extern const struct bpf_func_proto bpf_this_cpu_ptr_proto;
 extern const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto;
+extern const struct bpf_func_proto bpf_sock_from_file_proto;
 
 const struct bpf_func_proto *bpf_tracing_func_proto(
 	enum bpf_func_id func_id, const struct bpf_prog *prog);
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 0cf0a6331482..52ddd217d6a1 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1270,24 +1270,6 @@ const struct bpf_func_proto bpf_snprintf_btf_proto = {
 	.arg5_type	= ARG_ANYTHING,
 };
 
-BPF_CALL_1(bpf_sock_from_file, struct file *, file)
-{
-	return (unsigned long) sock_from_file(file);
-}
-
-BTF_ID_LIST(bpf_sock_from_file_btf_ids)
-BTF_ID(struct, socket)
-BTF_ID(struct, file)
-
-static const struct bpf_func_proto bpf_sock_from_file_proto = {
-	.func		= bpf_sock_from_file,
-	.gpl_only	= false,
-	.ret_type	= RET_PTR_TO_BTF_ID_OR_NULL,
-	.ret_btf_id	= &bpf_sock_from_file_btf_ids[0],
-	.arg1_type	= ARG_PTR_TO_BTF_ID,
-	.arg1_btf_id	= &bpf_sock_from_file_btf_ids[1],
-};
-
 const struct bpf_func_proto *
 bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
@@ -1384,8 +1366,6 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_per_cpu_ptr_proto;
 	case BPF_FUNC_bpf_this_cpu_ptr:
 		return &bpf_this_cpu_ptr_proto;
-	case BPF_FUNC_sock_from_file:
-		return &bpf_sock_from_file_proto;
 	default:
 		return NULL;
 	}
@@ -1778,6 +1758,8 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sk_storage_get_tracing_proto;
 	case BPF_FUNC_sk_storage_delete:
 		return &bpf_sk_storage_delete_tracing_proto;
+	case BPF_FUNC_sock_from_file:
+		return &bpf_sock_from_file_proto;
 #endif
 	case BPF_FUNC_seq_printf:
 		return prog->expected_attach_type == BPF_TRACE_ITER ?
diff --git a/net/core/filter.c b/net/core/filter.c
index 77001a35768f..255aeee72402 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -10413,6 +10413,24 @@ const struct bpf_func_proto bpf_skc_to_udp6_sock_proto = {
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_UDP6],
 };
 
+BPF_CALL_1(bpf_sock_from_file, struct file *, file)
+{
+	return (unsigned long)sock_from_file(file);
+}
+
+BTF_ID_LIST(bpf_sock_from_file_btf_ids)
+BTF_ID(struct, socket)
+BTF_ID(struct, file)
+
+const struct bpf_func_proto bpf_sock_from_file_proto = {
+	.func		= bpf_sock_from_file,
+	.gpl_only	= false,
+	.ret_type	= RET_PTR_TO_BTF_ID_OR_NULL,
+	.ret_btf_id	= &bpf_sock_from_file_btf_ids[0],
+	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &bpf_sock_from_file_btf_ids[1],
+};
+
 static const struct bpf_func_proto *
 bpf_sk_base_func_proto(enum bpf_func_id func_id)
 {
-- 
cgit v1.2.3


From e77dcb0b732dd355ca594909f6c2085dfc46cde2 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Fri, 6 Nov 2020 10:37:16 +0530
Subject: opp: Don't create an OPP table from dev_pm_opp_get_opp_table()

It has been found that some users (like cpufreq-dt and others on LKML)
have abused the helper dev_pm_opp_get_opp_table() to create the OPP
table instead of just finding it, which is the wrong thing to do. This
routine was meant for OPP core's internal working and exposed the whole
functionality by mistake.

Change the scope of dev_pm_opp_get_opp_table() to only finding the
table. The internal helpers _opp_get_opp_table*() are thus renamed to
_add_opp_table*(), dev_pm_opp_get_opp_table_indexed() is removed (as we
don't need the index field for finding the OPP table) and so the only
user, genpd, is updated.

Note that the prototype of _add_opp_table() was already left in opp.h by
mistake when it was removed earlier and so we weren't required to add it
now.

Acked-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
---
 drivers/base/power/domain.c |  2 +-
 drivers/opp/core.c          | 27 +++++++++++++--------------
 drivers/opp/of.c            |  4 ++--
 drivers/opp/opp.h           |  1 +
 include/linux/pm_opp.h      |  1 -
 5 files changed, 17 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 743268996336..92b750b865d5 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -2249,7 +2249,7 @@ int of_genpd_add_provider_onecell(struct device_node *np,
 			 * Save table for faster processing while setting
 			 * performance state.
 			 */
-			genpd->opp_table = dev_pm_opp_get_opp_table_indexed(&genpd->dev, i);
+			genpd->opp_table = dev_pm_opp_get_opp_table(&genpd->dev);
 			WARN_ON(IS_ERR(genpd->opp_table));
 		}
 
diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index 27a0e49b24ab..8f53c1b48911 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -1138,7 +1138,7 @@ void _get_opp_table_kref(struct opp_table *opp_table)
  * uses the opp_tables_busy flag to indicate if another creator is in the middle
  * of adding an OPP table and others should wait for it to finish.
  */
-static struct opp_table *_opp_get_opp_table(struct device *dev, int index)
+struct opp_table *_add_opp_table_indexed(struct device *dev, int index)
 {
 	struct opp_table *opp_table;
 
@@ -1188,17 +1188,16 @@ unlock:
 	return opp_table;
 }
 
-struct opp_table *dev_pm_opp_get_opp_table(struct device *dev)
+struct opp_table *_add_opp_table(struct device *dev)
 {
-	return _opp_get_opp_table(dev, 0);
+	return _add_opp_table_indexed(dev, 0);
 }
-EXPORT_SYMBOL_GPL(dev_pm_opp_get_opp_table);
 
-struct opp_table *dev_pm_opp_get_opp_table_indexed(struct device *dev,
-						   int index)
+struct opp_table *dev_pm_opp_get_opp_table(struct device *dev)
 {
-	return _opp_get_opp_table(dev, index);
+	return _find_opp_table(dev);
 }
+EXPORT_SYMBOL_GPL(dev_pm_opp_get_opp_table);
 
 static void _opp_table_kref_release(struct kref *kref)
 {
@@ -1627,7 +1626,7 @@ struct opp_table *dev_pm_opp_set_supported_hw(struct device *dev,
 {
 	struct opp_table *opp_table;
 
-	opp_table = dev_pm_opp_get_opp_table(dev);
+	opp_table = _add_opp_table(dev);
 	if (IS_ERR(opp_table))
 		return opp_table;
 
@@ -1686,7 +1685,7 @@ struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name)
 {
 	struct opp_table *opp_table;
 
-	opp_table = dev_pm_opp_get_opp_table(dev);
+	opp_table = _add_opp_table(dev);
 	if (IS_ERR(opp_table))
 		return opp_table;
 
@@ -1779,7 +1778,7 @@ struct opp_table *dev_pm_opp_set_regulators(struct device *dev,
 	struct regulator *reg;
 	int ret, i;
 
-	opp_table = dev_pm_opp_get_opp_table(dev);
+	opp_table = _add_opp_table(dev);
 	if (IS_ERR(opp_table))
 		return opp_table;
 
@@ -1887,7 +1886,7 @@ struct opp_table *dev_pm_opp_set_clkname(struct device *dev, const char *name)
 	struct opp_table *opp_table;
 	int ret;
 
-	opp_table = dev_pm_opp_get_opp_table(dev);
+	opp_table = _add_opp_table(dev);
 	if (IS_ERR(opp_table))
 		return opp_table;
 
@@ -1955,7 +1954,7 @@ struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev,
 	if (!set_opp)
 		return ERR_PTR(-EINVAL);
 
-	opp_table = dev_pm_opp_get_opp_table(dev);
+	opp_table = _add_opp_table(dev);
 	if (IS_ERR(opp_table))
 		return opp_table;
 
@@ -2039,7 +2038,7 @@ struct opp_table *dev_pm_opp_attach_genpd(struct device *dev,
 	int index = 0, ret = -EINVAL;
 	const char **name = names;
 
-	opp_table = dev_pm_opp_get_opp_table(dev);
+	opp_table = _add_opp_table(dev);
 	if (IS_ERR(opp_table))
 		return opp_table;
 
@@ -2204,7 +2203,7 @@ int dev_pm_opp_add(struct device *dev, unsigned long freq, unsigned long u_volt)
 	struct opp_table *opp_table;
 	int ret;
 
-	opp_table = dev_pm_opp_get_opp_table(dev);
+	opp_table = _add_opp_table(dev);
 	if (IS_ERR(opp_table))
 		return PTR_ERR(opp_table);
 
diff --git a/drivers/opp/of.c b/drivers/opp/of.c
index aa0ac5d4e479..6b7f0066942d 100644
--- a/drivers/opp/of.c
+++ b/drivers/opp/of.c
@@ -975,7 +975,7 @@ int dev_pm_opp_of_add_table(struct device *dev)
 	struct opp_table *opp_table;
 	int ret;
 
-	opp_table = dev_pm_opp_get_opp_table_indexed(dev, 0);
+	opp_table = _add_opp_table_indexed(dev, 0);
 	if (IS_ERR(opp_table))
 		return PTR_ERR(opp_table);
 
@@ -1030,7 +1030,7 @@ int dev_pm_opp_of_add_table_indexed(struct device *dev, int index)
 			index = 0;
 	}
 
-	opp_table = dev_pm_opp_get_opp_table_indexed(dev, index);
+	opp_table = _add_opp_table_indexed(dev, index);
 	if (IS_ERR(opp_table))
 		return PTR_ERR(opp_table);
 
diff --git a/drivers/opp/opp.h b/drivers/opp/opp.h
index ebd930e0b3ca..4ced7ffa8158 100644
--- a/drivers/opp/opp.h
+++ b/drivers/opp/opp.h
@@ -224,6 +224,7 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, struct opp_table *o
 int _opp_add_v1(struct opp_table *opp_table, struct device *dev, unsigned long freq, long u_volt, bool dynamic);
 void _dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask, int last_cpu);
 struct opp_table *_add_opp_table(struct device *dev);
+struct opp_table *_add_opp_table_indexed(struct device *dev, int index);
 void _put_opp_list_kref(struct opp_table *opp_table);
 
 #ifdef CONFIG_OF
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
index dbb484524f82..1435c054016a 100644
--- a/include/linux/pm_opp.h
+++ b/include/linux/pm_opp.h
@@ -90,7 +90,6 @@ struct dev_pm_set_opp_data {
 #if defined(CONFIG_PM_OPP)
 
 struct opp_table *dev_pm_opp_get_opp_table(struct device *dev);
-struct opp_table *dev_pm_opp_get_opp_table_indexed(struct device *dev, int index);
 void dev_pm_opp_put_opp_table(struct opp_table *opp_table);
 
 unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp);
-- 
cgit v1.2.3


From e4a9378083c57a22624cda8b780ff5f5da4de7ef Mon Sep 17 00:00:00 2001
From: Badhri Jagan Sridharan <badhri@google.com>
Date: Tue, 1 Dec 2020 19:17:33 -0800
Subject: usb: typec: tcpm: Pass down negotiated rev to update retry count

nRetryCount was updated from 3 to 2 between PD2.0 and PD3.0 spec.
nRetryCount in "Table 6-34 Counter parameters" of the PD 2.0
spec is set to 3, whereas, nRetryCount in "Table 6-59 Counter
parameters" is set to 2.

Pass down negotiated rev in pd_transmit so that low level chip
drivers can update the retry count accordingly before attempting
packet transmission.

This helps in passing "TEST.PD.PORT.ALL.02" of the
"Power Delivery Merged" test suite which was initially failing
with "The UUT did not retransmit the message nReryCount times"

In fusb302 & tcpci drivers, by default the driver sets the retry
count to 3 (Default for PD 2.0). Update this to 2,
if the negotiated rev is PD 3.0.

In wcove, since the retry count is intentionally set to max, leaving
it as is.

Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Acked-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Signed-off-by: Badhri Jagan Sridharan <badhri@google.com>
Link: https://lore.kernel.org/r/20201202031733.647808-1-badhri@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/fusb302.c | 16 +++++++++++-----
 drivers/usb/typec/tcpm/tcpci.c   | 12 +++++++-----
 drivers/usb/typec/tcpm/tcpm.c    |  2 +-
 drivers/usb/typec/tcpm/wcove.c   |  3 ++-
 include/linux/usb/tcpm.h         |  2 +-
 5 files changed, 22 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/usb/typec/tcpm/fusb302.c b/drivers/usb/typec/tcpm/fusb302.c
index 99562cc65ca6..ebc46b9f776c 100644
--- a/drivers/usb/typec/tcpm/fusb302.c
+++ b/drivers/usb/typec/tcpm/fusb302.c
@@ -343,12 +343,11 @@ static int fusb302_sw_reset(struct fusb302_chip *chip)
 	return ret;
 }
 
-static int fusb302_enable_tx_auto_retries(struct fusb302_chip *chip)
+static int fusb302_enable_tx_auto_retries(struct fusb302_chip *chip, u8 retry_count)
 {
 	int ret = 0;
 
-	ret = fusb302_i2c_set_bits(chip, FUSB_REG_CONTROL3,
-				   FUSB_REG_CONTROL3_N_RETRIES_3 |
+	ret = fusb302_i2c_set_bits(chip, FUSB_REG_CONTROL3, retry_count |
 				   FUSB_REG_CONTROL3_AUTO_RETRY);
 
 	return ret;
@@ -399,7 +398,7 @@ static int tcpm_init(struct tcpc_dev *dev)
 	ret = fusb302_sw_reset(chip);
 	if (ret < 0)
 		return ret;
-	ret = fusb302_enable_tx_auto_retries(chip);
+	ret = fusb302_enable_tx_auto_retries(chip, FUSB_REG_CONTROL3_N_RETRIES_3);
 	if (ret < 0)
 		return ret;
 	ret = fusb302_init_interrupt(chip);
@@ -1017,7 +1016,7 @@ static const char * const transmit_type_name[] = {
 };
 
 static int tcpm_pd_transmit(struct tcpc_dev *dev, enum tcpm_transmit_type type,
-			    const struct pd_message *msg)
+			    const struct pd_message *msg, unsigned int negotiated_rev)
 {
 	struct fusb302_chip *chip = container_of(dev, struct fusb302_chip,
 						 tcpc_dev);
@@ -1026,6 +1025,13 @@ static int tcpm_pd_transmit(struct tcpc_dev *dev, enum tcpm_transmit_type type,
 	mutex_lock(&chip->lock);
 	switch (type) {
 	case TCPC_TX_SOP:
+		/* nRetryCount 3 in P2.0 spec, whereas 2 in PD3.0 spec */
+		ret = fusb302_enable_tx_auto_retries(chip, negotiated_rev > PD_REV20 ?
+						     FUSB_REG_CONTROL3_N_RETRIES_2 :
+						     FUSB_REG_CONTROL3_N_RETRIES_3);
+		if (ret < 0)
+			fusb302_log(chip, "Cannot update retry count ret=%d", ret);
+
 		ret = fusb302_pd_send_message(chip, msg);
 		if (ret < 0)
 			fusb302_log(chip,
diff --git a/drivers/usb/typec/tcpm/tcpci.c b/drivers/usb/typec/tcpm/tcpci.c
index 12d983a75510..98a2455f779f 100644
--- a/drivers/usb/typec/tcpm/tcpci.c
+++ b/drivers/usb/typec/tcpm/tcpci.c
@@ -18,7 +18,8 @@
 
 #include "tcpci.h"
 
-#define	PD_RETRY_COUNT				3
+#define	PD_RETRY_COUNT_DEFAULT			3
+#define	PD_RETRY_COUNT_3_0_OR_HIGHER		2
 #define	AUTO_DISCHARGE_DEFAULT_THRESHOLD_MV	3500
 #define	AUTO_DISCHARGE_PD_HEADROOM_MV		850
 #define	AUTO_DISCHARGE_PPS_HEADROOM_MV		1250
@@ -447,9 +448,8 @@ static int tcpci_set_vbus(struct tcpc_dev *tcpc, bool source, bool sink)
 	return 0;
 }
 
-static int tcpci_pd_transmit(struct tcpc_dev *tcpc,
-			     enum tcpm_transmit_type type,
-			     const struct pd_message *msg)
+static int tcpci_pd_transmit(struct tcpc_dev *tcpc, enum tcpm_transmit_type type,
+			     const struct pd_message *msg, unsigned int negotiated_rev)
 {
 	struct tcpci *tcpci = tcpc_to_tcpci(tcpc);
 	u16 header = msg ? le16_to_cpu(msg->header) : 0;
@@ -497,7 +497,9 @@ static int tcpci_pd_transmit(struct tcpc_dev *tcpc,
 		}
 	}
 
-	reg = (PD_RETRY_COUNT << TCPC_TRANSMIT_RETRY_SHIFT) | (type << TCPC_TRANSMIT_TYPE_SHIFT);
+	/* nRetryCount is 3 in PD2.0 spec where 2 in PD3.0 spec */
+	reg = ((negotiated_rev > PD_REV20 ? PD_RETRY_COUNT_3_0_OR_HIGHER : PD_RETRY_COUNT_DEFAULT)
+	       << TCPC_TRANSMIT_RETRY_SHIFT) | (type << TCPC_TRANSMIT_TYPE_SHIFT);
 	ret = regmap_write(tcpci->regmap, TCPC_TRANSMIT, reg);
 	if (ret < 0)
 		return ret;
diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 3bbc1f10af49..c73bc3a8356a 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -667,7 +667,7 @@ static int tcpm_pd_transmit(struct tcpm_port *port,
 		tcpm_log(port, "PD TX, type: %#x", type);
 
 	reinit_completion(&port->tx_complete);
-	ret = port->tcpc->pd_transmit(port->tcpc, type, msg);
+	ret = port->tcpc->pd_transmit(port->tcpc, type, msg, port->negotiated_rev);
 	if (ret < 0)
 		return ret;
 
diff --git a/drivers/usb/typec/tcpm/wcove.c b/drivers/usb/typec/tcpm/wcove.c
index 9b745f432c91..79ae63950050 100644
--- a/drivers/usb/typec/tcpm/wcove.c
+++ b/drivers/usb/typec/tcpm/wcove.c
@@ -356,7 +356,8 @@ static int wcove_set_pd_rx(struct tcpc_dev *tcpc, bool on)
 
 static int wcove_pd_transmit(struct tcpc_dev *tcpc,
 			     enum tcpm_transmit_type type,
-			     const struct pd_message *msg)
+			     const struct pd_message *msg,
+			     unsigned int negotiated_rev)
 {
 	struct wcove_typec *wcove = tcpc_to_wcove(tcpc);
 	unsigned int info = 0;
diff --git a/include/linux/usb/tcpm.h b/include/linux/usb/tcpm.h
index e68aaa12886f..efaedd7e8a18 100644
--- a/include/linux/usb/tcpm.h
+++ b/include/linux/usb/tcpm.h
@@ -121,7 +121,7 @@ struct tcpc_dev {
 			      enum typec_cc_status cc);
 	int (*try_role)(struct tcpc_dev *dev, int role);
 	int (*pd_transmit)(struct tcpc_dev *dev, enum tcpm_transmit_type type,
-			   const struct pd_message *msg);
+			   const struct pd_message *msg, unsigned int negotiated_rev);
 	int (*set_bist_data)(struct tcpc_dev *dev, bool on);
 	int (*enable_frs)(struct tcpc_dev *dev, bool enable);
 	void (*frs_sourcing_vbus)(struct tcpc_dev *dev);
-- 
cgit v1.2.3


From 28b43d3d746b89fc112fe681e018b39b43495dad Mon Sep 17 00:00:00 2001
From: Badhri Jagan Sridharan <badhri@google.com>
Date: Tue, 1 Dec 2020 20:08:38 -0800
Subject: usb: typec: tcpm: Introduce vsafe0v for vbus
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

TCPM at present lacks the notion of VSAFE0V. There
are three vbus threshold levels that are critical to track:
a. vSafe5V         - VBUS “5 volts” as defined by the USB
                     PD specification.
b. vSinkDisconnect - Threshold used for transition from
                     Attached.SNK to Unattached.SNK.
c. vSafe0V         - VBUS “0 volts” as defined by the USB
                     PD specification.

Tracking vSafe0V is crucial for entry into Try.SNK and
Attached.SRC and turning vbus back on by the source in
response to hard reset.

>From "4.5.2.2.8.2 Exiting from AttachWait.SRC State" section
in the Type-C spec:

"The port shall transition to Attached.SRC when VBUS is at
vSafe0V and the SRC.Rd state is detected on exactly one of
the CC1 or CC2 pins for at least tCCDebounce."

"A DRP that strongly prefers the Sink role may optionally
transition to Try.SNK instead of Attached.SRC when VBUS
is at vSafe0V and the SRC.Rd state is detected on exactly
one of the CC1 or CC2 pins for at least tCCDebounce."

>From "7.1.5 Response to Hard Resets" section in the PD spec:

"After establishing the vSafe0V voltage condition on VBUS,
the Source Shall wait tSrcRecover before re-applying VCONN
and restoring VBUS to vSafe5V."

vbus_present in the TCPM code tracks vSafe5V(vbus_present is true)
and vSinkDisconnect(vbus_present is false).

This change adds is_vbus_vsafe0v callback which when set makes
TCPM query for vSafe0V voltage level when needed.

Since not all TCPC controllers might have the capability
to report vSafe0V, TCPM assumes that vSafe0V is same as
vSinkDisconnect when is_vbus_vsafe0v callback is not set.
This allows TCPM to continue to support controllers which don't
have the support for reporting vSafe0V.

Introducing vSafe0V helps fix the failure reported at
"Step 15. CVS verifies PUT remains in AttachWait.SRC for 500ms"
of "TD 4.7.2 Try. SNK DRP Connect DRP Test" of
"Universal Serial Bus Type-C (USB Type-C) Functional Test
Specification Chapters 4 and 5". Here the compliance tester
intentionally maintains vbus at greater than vSafe0V and expects
the Product under test to stay in AttachWait.SRC till vbus drops
to vSafe0V.

Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Acked-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Signed-off-by: Badhri Jagan Sridharan <badhri@google.com>
Link: https://lore.kernel.org/r/20201202040840.663578-1-badhri@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/tcpm.c | 63 +++++++++++++++++++++++++++++++++++--------
 include/linux/usb/tcpm.h      |  7 +++++
 2 files changed, 59 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 1c64b831bbb5..cedc6cf82d61 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -258,7 +258,19 @@ struct tcpm_port {
 	bool attached;
 	bool connected;
 	enum typec_port_type port_type;
+
+	/*
+	 * Set to true when vbus is greater than VSAFE5V min.
+	 * Set to false when vbus falls below vSinkDisconnect max threshold.
+	 */
 	bool vbus_present;
+
+	/*
+	 * Set to true when vbus is less than VSAFE0V max.
+	 * Set to false when vbus is greater than VSAFE0V max.
+	 */
+	bool vbus_vsafe0v;
+
 	bool vbus_never_low;
 	bool vbus_source;
 	bool vbus_charge;
@@ -3093,7 +3105,7 @@ static void run_state_machine(struct tcpm_port *port)
 		else if (tcpm_port_is_audio(port))
 			tcpm_set_state(port, AUDIO_ACC_ATTACHED,
 				       PD_T_CC_DEBOUNCE);
-		else if (tcpm_port_is_source(port))
+		else if (tcpm_port_is_source(port) && port->vbus_vsafe0v)
 			tcpm_set_state(port,
 				       tcpm_try_snk(port) ? SNK_TRY
 							  : SRC_ATTACHED,
@@ -4096,6 +4108,12 @@ static void _tcpm_pd_vbus_on(struct tcpm_port *port)
 {
 	tcpm_log_force(port, "VBUS on");
 	port->vbus_present = true;
+	/*
+	 * When vbus_present is true i.e. Voltage at VBUS is greater than VSAFE5V implicitly
+	 * states that vbus is not at VSAFE0V, hence clear the vbus_vsafe0v flag here.
+	 */
+	port->vbus_vsafe0v = false;
+
 	switch (port->state) {
 	case SNK_TRANSITION_SINK_VBUS:
 		port->explicit_contract = true;
@@ -4185,16 +4203,8 @@ static void _tcpm_pd_vbus_off(struct tcpm_port *port)
 	case SNK_HARD_RESET_SINK_OFF:
 		tcpm_set_state(port, SNK_HARD_RESET_WAIT_VBUS, 0);
 		break;
-	case SRC_HARD_RESET_VBUS_OFF:
-		/*
-		 * After establishing the vSafe0V voltage condition on VBUS, the Source Shall wait
-		 * tSrcRecover before re-applying VCONN and restoring VBUS to vSafe5V.
-		 */
-		tcpm_set_state(port, SRC_HARD_RESET_VBUS_ON, PD_T_SRC_RECOVER);
-		break;
 	case HARD_RESET_SEND:
 		break;
-
 	case SNK_TRY:
 		/* Do nothing, waiting for timeout */
 		break;
@@ -4265,6 +4275,28 @@ static void _tcpm_pd_vbus_off(struct tcpm_port *port)
 	}
 }
 
+static void _tcpm_pd_vbus_vsafe0v(struct tcpm_port *port)
+{
+	tcpm_log_force(port, "VBUS VSAFE0V");
+	port->vbus_vsafe0v = true;
+	switch (port->state) {
+	case SRC_HARD_RESET_VBUS_OFF:
+		/*
+		 * After establishing the vSafe0V voltage condition on VBUS, the Source Shall wait
+		 * tSrcRecover before re-applying VCONN and restoring VBUS to vSafe5V.
+		 */
+		tcpm_set_state(port, SRC_HARD_RESET_VBUS_ON, PD_T_SRC_RECOVER);
+		break;
+	case SRC_ATTACH_WAIT:
+		if (tcpm_port_is_source(port))
+			tcpm_set_state(port, tcpm_try_snk(port) ? SNK_TRY : SRC_ATTACHED,
+				       PD_T_CC_DEBOUNCE);
+		break;
+	default:
+		break;
+	}
+}
+
 static void _tcpm_pd_hard_reset(struct tcpm_port *port)
 {
 	tcpm_log_force(port, "Received hard reset");
@@ -4300,10 +4332,19 @@ static void tcpm_pd_event_handler(struct kthread_work *work)
 			bool vbus;
 
 			vbus = port->tcpc->get_vbus(port->tcpc);
-			if (vbus)
+			if (vbus) {
 				_tcpm_pd_vbus_on(port);
-			else
+			} else {
 				_tcpm_pd_vbus_off(port);
+				/*
+				 * When TCPC does not support detecting vsafe0v voltage level,
+				 * treat vbus absent as vsafe0v. Else invoke is_vbus_vsafe0v
+				 * to see if vbus has discharge to VSAFE0V.
+				 */
+				if (!port->tcpc->is_vbus_vsafe0v ||
+				    port->tcpc->is_vbus_vsafe0v(port->tcpc))
+					_tcpm_pd_vbus_vsafe0v(port);
+			}
 		}
 		if (events & TCPM_CC_EVENT) {
 			enum typec_cc_status cc1, cc2;
diff --git a/include/linux/usb/tcpm.h b/include/linux/usb/tcpm.h
index efaedd7e8a18..f4a18427f5c4 100644
--- a/include/linux/usb/tcpm.h
+++ b/include/linux/usb/tcpm.h
@@ -98,6 +98,12 @@ enum tcpm_transmit_type {
  *		will be turned on. requested_vbus_voltage is set to 0 when vbus
  *		is going to disappear knowingly i.e. during PR_SWAP and
  *		HARD_RESET etc.
+ * @is_vbus_vsafe0v:
+ *		Optional; TCPCI spec based TCPC implementations are expected to
+ *		detect VSAFE0V voltage level at vbus. When detection of VSAFE0V
+ *		is supported by TCPC, set this callback for TCPM to query
+ *		whether vbus is at VSAFE0V when needed.
+ *		Returns true when vbus is at VSAFE0V, false otherwise.
  */
 struct tcpc_dev {
 	struct fwnode_handle *fwnode;
@@ -128,6 +134,7 @@ struct tcpc_dev {
 	int (*enable_auto_vbus_discharge)(struct tcpc_dev *dev, bool enable);
 	int (*set_auto_vbus_discharge_threshold)(struct tcpc_dev *dev, enum typec_pwr_opmode mode,
 						 bool pps_active, u32 requested_vbus_voltage);
+	bool (*is_vbus_vsafe0v)(struct tcpc_dev *dev);
 };
 
 struct tcpm_port;
-- 
cgit v1.2.3


From af633212c4aac1dbd3a48615a834646ce072346d Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Wed, 2 Dec 2020 12:39:36 +0100
Subject: tty: use assign_bit() in port-flag accessors

Use the new assign_bit() wrapper in the port-flag accessors instead of
open coding.

Suggested-by: Jiri Slaby <jirislaby@kernel.org>
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20201202113942.27024-2-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/tty.h | 30 ++++++------------------------
 1 file changed, 6 insertions(+), 24 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/tty.h b/include/linux/tty.h
index 0c2f97ba8018..9b8e7d5bf2fc 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -615,10 +615,7 @@ static inline bool tty_port_cts_enabled(struct tty_port *port)
 
 static inline void tty_port_set_cts_flow(struct tty_port *port, bool val)
 {
-	if (val)
-		set_bit(TTY_PORT_CTS_FLOW, &port->iflags);
-	else
-		clear_bit(TTY_PORT_CTS_FLOW, &port->iflags);
+	assign_bit(TTY_PORT_CTS_FLOW, &port->iflags, val);
 }
 
 static inline bool tty_port_active(struct tty_port *port)
@@ -628,10 +625,7 @@ static inline bool tty_port_active(struct tty_port *port)
 
 static inline void tty_port_set_active(struct tty_port *port, bool val)
 {
-	if (val)
-		set_bit(TTY_PORT_ACTIVE, &port->iflags);
-	else
-		clear_bit(TTY_PORT_ACTIVE, &port->iflags);
+	assign_bit(TTY_PORT_ACTIVE, &port->iflags, val);
 }
 
 static inline bool tty_port_check_carrier(struct tty_port *port)
@@ -641,10 +635,7 @@ static inline bool tty_port_check_carrier(struct tty_port *port)
 
 static inline void tty_port_set_check_carrier(struct tty_port *port, bool val)
 {
-	if (val)
-		set_bit(TTY_PORT_CHECK_CD, &port->iflags);
-	else
-		clear_bit(TTY_PORT_CHECK_CD, &port->iflags);
+	assign_bit(TTY_PORT_CHECK_CD, &port->iflags, val);
 }
 
 static inline bool tty_port_suspended(struct tty_port *port)
@@ -654,10 +645,7 @@ static inline bool tty_port_suspended(struct tty_port *port)
 
 static inline void tty_port_set_suspended(struct tty_port *port, bool val)
 {
-	if (val)
-		set_bit(TTY_PORT_SUSPENDED, &port->iflags);
-	else
-		clear_bit(TTY_PORT_SUSPENDED, &port->iflags);
+	assign_bit(TTY_PORT_SUSPENDED, &port->iflags, val);
 }
 
 static inline bool tty_port_initialized(struct tty_port *port)
@@ -667,10 +655,7 @@ static inline bool tty_port_initialized(struct tty_port *port)
 
 static inline void tty_port_set_initialized(struct tty_port *port, bool val)
 {
-	if (val)
-		set_bit(TTY_PORT_INITIALIZED, &port->iflags);
-	else
-		clear_bit(TTY_PORT_INITIALIZED, &port->iflags);
+	assign_bit(TTY_PORT_INITIALIZED, &port->iflags, val);
 }
 
 static inline bool tty_port_kopened(struct tty_port *port)
@@ -680,10 +665,7 @@ static inline bool tty_port_kopened(struct tty_port *port)
 
 static inline void tty_port_set_kopened(struct tty_port *port, bool val)
 {
-	if (val)
-		set_bit(TTY_PORT_KOPENED, &port->iflags);
-	else
-		clear_bit(TTY_PORT_KOPENED, &port->iflags);
+	assign_bit(TTY_PORT_KOPENED, &port->iflags, val);
 }
 
 extern struct tty_struct *tty_port_tty_get(struct tty_port *port);
-- 
cgit v1.2.3


From 9e1792727ead477f49958578d0dbd466a7deea48 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Wed, 2 Dec 2020 12:39:37 +0100
Subject: tty: use const parameters in port-flag accessors

Declare the port parameter to the flag-test accessors as const.

This is currently mostly cosmetic as the accessors are already inlined.

Suggested-by: Jiri Slaby <jirislaby@kernel.org>
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20201202113942.27024-3-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/tty.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/tty.h b/include/linux/tty.h
index 9b8e7d5bf2fc..c873f475f0a7 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -608,7 +608,7 @@ static inline struct tty_port *tty_port_get(struct tty_port *port)
 }
 
 /* If the cts flow control is enabled, return true. */
-static inline bool tty_port_cts_enabled(struct tty_port *port)
+static inline bool tty_port_cts_enabled(const struct tty_port *port)
 {
 	return test_bit(TTY_PORT_CTS_FLOW, &port->iflags);
 }
@@ -618,7 +618,7 @@ static inline void tty_port_set_cts_flow(struct tty_port *port, bool val)
 	assign_bit(TTY_PORT_CTS_FLOW, &port->iflags, val);
 }
 
-static inline bool tty_port_active(struct tty_port *port)
+static inline bool tty_port_active(const struct tty_port *port)
 {
 	return test_bit(TTY_PORT_ACTIVE, &port->iflags);
 }
@@ -628,7 +628,7 @@ static inline void tty_port_set_active(struct tty_port *port, bool val)
 	assign_bit(TTY_PORT_ACTIVE, &port->iflags, val);
 }
 
-static inline bool tty_port_check_carrier(struct tty_port *port)
+static inline bool tty_port_check_carrier(const struct tty_port *port)
 {
 	return test_bit(TTY_PORT_CHECK_CD, &port->iflags);
 }
@@ -638,7 +638,7 @@ static inline void tty_port_set_check_carrier(struct tty_port *port, bool val)
 	assign_bit(TTY_PORT_CHECK_CD, &port->iflags, val);
 }
 
-static inline bool tty_port_suspended(struct tty_port *port)
+static inline bool tty_port_suspended(const struct tty_port *port)
 {
 	return test_bit(TTY_PORT_SUSPENDED, &port->iflags);
 }
@@ -648,7 +648,7 @@ static inline void tty_port_set_suspended(struct tty_port *port, bool val)
 	assign_bit(TTY_PORT_SUSPENDED, &port->iflags, val);
 }
 
-static inline bool tty_port_initialized(struct tty_port *port)
+static inline bool tty_port_initialized(const struct tty_port *port)
 {
 	return test_bit(TTY_PORT_INITIALIZED, &port->iflags);
 }
@@ -658,7 +658,7 @@ static inline void tty_port_set_initialized(struct tty_port *port, bool val)
 	assign_bit(TTY_PORT_INITIALIZED, &port->iflags, val);
 }
 
-static inline bool tty_port_kopened(struct tty_port *port)
+static inline bool tty_port_kopened(const struct tty_port *port)
 {
 	return test_bit(TTY_PORT_KOPENED, &port->iflags);
 }
-- 
cgit v1.2.3


From 4b03d99794eeed27650597a886247c6427ce1055 Mon Sep 17 00:00:00 2001
From: "J. Bruce Fields" <bfields@redhat.com>
Date: Mon, 30 Nov 2020 17:46:16 -0500
Subject: nfsd: minor nfsd4_change_attribute cleanup

Minor cleanup, no change in behavior.

Also pull out a common helper that'll be useful elsewhere.

Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfsfh.h          | 13 +++++--------
 include/linux/iversion.h | 13 +++++++++++++
 2 files changed, 18 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h
index 39d764b129fa..45bd776290d5 100644
--- a/fs/nfsd/nfsfh.h
+++ b/fs/nfsd/nfsfh.h
@@ -259,19 +259,16 @@ fh_clear_wcc(struct svc_fh *fhp)
 static inline u64 nfsd4_change_attribute(struct kstat *stat,
 					 struct inode *inode)
 {
-	u64 chattr;
-
 	if (IS_I_VERSION(inode)) {
+		u64 chattr;
+
 		chattr =  stat->ctime.tv_sec;
 		chattr <<= 30;
 		chattr += stat->ctime.tv_nsec;
 		chattr += inode_query_iversion(inode);
-	} else {
-		chattr = stat->ctime.tv_sec;
-		chattr <<= 32;
-		chattr += stat->ctime.tv_nsec;
-	}
-	return chattr;
+		return chattr;
+	} else
+		return time_to_chattr(&stat->ctime);
 }
 
 extern void fill_pre_wcc(struct svc_fh *fhp);
diff --git a/include/linux/iversion.h b/include/linux/iversion.h
index 2917ef990d43..3bfebde5a1a6 100644
--- a/include/linux/iversion.h
+++ b/include/linux/iversion.h
@@ -328,6 +328,19 @@ inode_query_iversion(struct inode *inode)
 	return cur >> I_VERSION_QUERIED_SHIFT;
 }
 
+/*
+ * For filesystems without any sort of change attribute, the best we can
+ * do is fake one up from the ctime:
+ */
+static inline u64 time_to_chattr(struct timespec64 *t)
+{
+	u64 chattr = t->tv_sec;
+
+	chattr <<= 32;
+	chattr += t->tv_nsec;
+	return chattr;
+}
+
 /**
  * inode_eq_iversion_raw - check whether the raw i_version counter has changed
  * @inode: inode to check
-- 
cgit v1.2.3


From 1631087ba8727db03c0ab2815dc06dc25d962b80 Mon Sep 17 00:00:00 2001
From: "J. Bruce Fields" <bfields@redhat.com>
Date: Mon, 30 Nov 2020 17:46:18 -0500
Subject: Revert "nfsd4: support change_attr_type attribute"

This reverts commit a85857633b04d57f4524cca0a2bfaf87b2543f9f.

We're still factoring ctime into our change attribute even in the
IS_I_VERSION case.  If someone sets the system time backwards, a client
could see the change attribute go backwards.  Maybe we can just say
"well, don't do that", but there's some question whether that's good
enough, or whether we need a better guarantee.

Also, the client still isn't actually using the attribute.

While we're still figuring this out, let's just stop returning this
attribute.

Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4xdr.c    | 10 ----------
 fs/nfsd/nfsd.h       |  1 -
 include/linux/nfs4.h |  8 --------
 3 files changed, 19 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 7f650fa47006..45ee6b12ce5b 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -3311,16 +3311,6 @@ out_acl:
 			goto out;
 	}
 
-	if (bmval2 & FATTR4_WORD2_CHANGE_ATTR_TYPE) {
-		p = xdr_reserve_space(xdr, 4);
-		if (!p)
-			goto out_resource;
-		if (IS_I_VERSION(d_inode(dentry)))
-			*p++ = cpu_to_be32(NFS4_CHANGE_TYPE_IS_MONOTONIC_INCR);
-		else
-			*p++ = cpu_to_be32(NFS4_CHANGE_TYPE_IS_TIME_METADATA);
-	}
-
 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
 	if (bmval2 & FATTR4_WORD2_SECURITY_LABEL) {
 		status = nfsd4_encode_security_label(xdr, rqstp, context,
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 7907de3f2ee6..d63cf8196fed 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -395,7 +395,6 @@ void		nfsd_lockd_shutdown(void);
 
 #define NFSD4_2_SUPPORTED_ATTRS_WORD2 \
 	(NFSD4_1_SUPPORTED_ATTRS_WORD2 | \
-	FATTR4_WORD2_CHANGE_ATTR_TYPE | \
 	FATTR4_WORD2_MODE_UMASK | \
 	NFSD4_2_SECURITY_ATTRS | \
 	FATTR4_WORD2_XATTR_SUPPORT)
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 9dc7eeac924f..5b4c67c91f56 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -385,13 +385,6 @@ enum lock_type4 {
 	NFS4_WRITEW_LT = 4
 };
 
-enum change_attr_type4 {
-	NFS4_CHANGE_TYPE_IS_MONOTONIC_INCR = 0,
-	NFS4_CHANGE_TYPE_IS_VERSION_COUNTER = 1,
-	NFS4_CHANGE_TYPE_IS_VERSION_COUNTER_NOPNFS = 2,
-	NFS4_CHANGE_TYPE_IS_TIME_METADATA = 3,
-	NFS4_CHANGE_TYPE_IS_UNDEFINED = 4
-};
 
 /* Mandatory Attributes */
 #define FATTR4_WORD0_SUPPORTED_ATTRS    (1UL << 0)
@@ -459,7 +452,6 @@ enum change_attr_type4 {
 #define FATTR4_WORD2_LAYOUT_BLKSIZE     (1UL << 1)
 #define FATTR4_WORD2_MDSTHRESHOLD       (1UL << 4)
 #define FATTR4_WORD2_CLONE_BLKSIZE	(1UL << 13)
-#define FATTR4_WORD2_CHANGE_ATTR_TYPE	(1UL << 15)
 #define FATTR4_WORD2_SECURITY_LABEL     (1UL << 16)
 #define FATTR4_WORD2_MODE_UMASK		(1UL << 17)
 #define FATTR4_WORD2_XATTR_SUPPORT	(1UL << 18)
-- 
cgit v1.2.3


From daab110e47f8d7aa6da66923e3ac1a8dbd2b2a72 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jeff.layton@primarydata.com>
Date: Mon, 30 Nov 2020 17:03:14 -0500
Subject: nfsd: add a new EXPORT_OP_NOWCC flag to struct export_operations

With NFSv3 nfsd will always attempt to send along WCC data to the
client. This generally involves saving off the in-core inode information
prior to doing the operation on the given filehandle, and then issuing a
vfs_getattr to it after the op.

Some filesystems (particularly clustered or networked ones) have an
expensive ->getattr inode operation. Atomicity is also often difficult
or impossible to guarantee on such filesystems. For those, we're best
off not trying to provide WCC information to the client at all, and to
simply allow it to poll for that information as needed with a GETATTR
RPC.

This patch adds a new flags field to struct export_operations, and
defines a new EXPORT_OP_NOWCC flag that filesystems can use to indicate
that nfsd should not attempt to provide WCC info in NFSv3 replies. It
also adds a blurb about the new flags field and flag to the exporting
documentation.

The server will also now skip collecting this information for NFSv2 as
well, since that info is never used there anyway.

Note that this patch does not add this flag to any filesystem
export_operations structures. This was originally developed to allow
reexporting nfs via nfsd.

Other filesystems may want to consider enabling this flag too. It's hard
to tell however which ones have export operations to enable export via
knfsd and which ones mostly rely on them for open-by-filehandle support,
so I'm leaving that up to the individual maintainers to decide. I am
cc'ing the relevant lists for those filesystems that I think may want to
consider adding this though.

Cc: HPDD-discuss@lists.01.org
Cc: ceph-devel@vger.kernel.org
Cc: cluster-devel@redhat.com
Cc: fuse-devel@lists.sourceforge.net
Cc: ocfs2-devel@oss.oracle.com
Signed-off-by: Jeff Layton <jeff.layton@primarydata.com>
Signed-off-by: Lance Shelton <lance.shelton@hammerspace.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 Documentation/filesystems/nfs/exporting.rst | 27 +++++++++++++++++++++++++++
 fs/nfs/export.c                             |  1 +
 fs/nfsd/nfs3xdr.c                           |  7 +++++--
 fs/nfsd/nfsfh.c                             | 14 ++++++++++++++
 fs/nfsd/nfsfh.h                             |  2 +-
 include/linux/exportfs.h                    |  2 ++
 6 files changed, 50 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/nfs/exporting.rst b/Documentation/filesystems/nfs/exporting.rst
index 33d588a01ace..cbe542ad5233 100644
--- a/Documentation/filesystems/nfs/exporting.rst
+++ b/Documentation/filesystems/nfs/exporting.rst
@@ -154,6 +154,11 @@ struct which has the following members:
     to find potential names, and matches inode numbers to find the correct
     match.
 
+  flags
+    Some filesystems may need to be handled differently than others. The
+    export_operations struct also includes a flags field that allows the
+    filesystem to communicate such information to nfsd. See the Export
+    Operations Flags section below for more explanation.
 
 A filehandle fragment consists of an array of 1 or more 4byte words,
 together with a one byte "type".
@@ -163,3 +168,25 @@ generated by encode_fh, in which case it will have been padded with
 nuls.  Rather, the encode_fh routine should choose a "type" which
 indicates the decode_fh how much of the filehandle is valid, and how
 it should be interpreted.
+
+Export Operations Flags
+-----------------------
+In addition to the operation vector pointers, struct export_operations also
+contains a "flags" field that allows the filesystem to communicate to nfsd
+that it may want to do things differently when dealing with it. The
+following flags are defined:
+
+  EXPORT_OP_NOWCC - disable NFSv3 WCC attributes on this filesystem
+    RFC 1813 recommends that servers always send weak cache consistency
+    (WCC) data to the client after each operation. The server should
+    atomically collect attributes about the inode, do an operation on it,
+    and then collect the attributes afterward. This allows the client to
+    skip issuing GETATTRs in some situations but means that the server
+    is calling vfs_getattr for almost all RPCs. On some filesystems
+    (particularly those that are clustered or networked) this is expensive
+    and atomicity is difficult to guarantee. This flag indicates to nfsd
+    that it should skip providing WCC attributes to the client in NFSv3
+    replies when doing operations on this filesystem. Consider enabling
+    this on filesystems that have an expensive ->getattr inode operation,
+    or when atomicity between pre and post operation attribute collection
+    is impossible to guarantee.
diff --git a/fs/nfs/export.c b/fs/nfs/export.c
index 3430d6891e89..8f4c528865c5 100644
--- a/fs/nfs/export.c
+++ b/fs/nfs/export.c
@@ -171,4 +171,5 @@ const struct export_operations nfs_export_ops = {
 	.encode_fh = nfs_encode_fh,
 	.fh_to_dentry = nfs_fh_to_dentry,
 	.get_parent = nfs_get_parent,
+	.flags = EXPORT_OP_NOWCC,
 };
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index b0a53c857706..821db21ba072 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -206,7 +206,7 @@ static __be32 *
 encode_post_op_attr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp)
 {
 	struct dentry *dentry = fhp->fh_dentry;
-	if (dentry && d_really_is_positive(dentry)) {
+	if (!fhp->fh_no_wcc && dentry && d_really_is_positive(dentry)) {
 	        __be32 err;
 		struct kstat stat;
 
@@ -262,7 +262,7 @@ void fill_pre_wcc(struct svc_fh *fhp)
 	bool v4 = (fhp->fh_maxsize == NFS4_FHSIZE);
 	__be32 err;
 
-	if (fhp->fh_pre_saved)
+	if (fhp->fh_no_wcc || fhp->fh_pre_saved)
 		return;
 	inode = d_inode(fhp->fh_dentry);
 	err = fh_getattr(fhp, &stat);
@@ -290,6 +290,9 @@ void fill_post_wcc(struct svc_fh *fhp)
 	struct inode *inode = d_inode(fhp->fh_dentry);
 	__be32 err;
 
+	if (fhp->fh_no_wcc)
+		return;
+
 	if (fhp->fh_post_saved)
 		printk("nfsd: inode locked twice during operation.\n");
 
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index c81dbbad8792..9c29a523f484 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -291,6 +291,16 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
 
 	fhp->fh_dentry = dentry;
 	fhp->fh_export = exp;
+
+	switch (rqstp->rq_vers) {
+	case 3:
+		if (dentry->d_sb->s_export_op->flags & EXPORT_OP_NOWCC)
+			fhp->fh_no_wcc = true;
+		break;
+	case 2:
+		fhp->fh_no_wcc = true;
+	}
+
 	return 0;
 out:
 	exp_put(exp);
@@ -559,6 +569,9 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry,
 	 */
 	set_version_and_fsid_type(fhp, exp, ref_fh);
 
+	/* If we have a ref_fh, then copy the fh_no_wcc setting from it. */
+	fhp->fh_no_wcc = ref_fh ? ref_fh->fh_no_wcc : false;
+
 	if (ref_fh == fhp)
 		fh_put(ref_fh);
 
@@ -662,6 +675,7 @@ fh_put(struct svc_fh *fhp)
 		exp_put(exp);
 		fhp->fh_export = NULL;
 	}
+	fhp->fh_no_wcc = false;
 	return;
 }
 
diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h
index 45bd776290d5..347d10aa6265 100644
--- a/fs/nfsd/nfsfh.h
+++ b/fs/nfsd/nfsfh.h
@@ -35,6 +35,7 @@ typedef struct svc_fh {
 
 	bool			fh_locked;	/* inode locked by us */
 	bool			fh_want_write;	/* remount protection taken */
+	bool			fh_no_wcc;	/* no wcc data needed */
 	int			fh_flags;	/* FH flags */
 #ifdef CONFIG_NFSD_V3
 	bool			fh_post_saved;	/* post-op attrs saved */
@@ -54,7 +55,6 @@ typedef struct svc_fh {
 	struct kstat		fh_post_attr;	/* full attrs after operation */
 	u64			fh_post_change; /* nfsv4 change; see above */
 #endif /* CONFIG_NFSD_V3 */
-
 } svc_fh;
 #define NFSD4_FH_FOREIGN (1<<0)
 #define SET_FH_FLAG(c, f) ((c)->fh_flags |= (f))
diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index 3ceb72b67a7a..e7de0103a32e 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -213,6 +213,8 @@ struct export_operations {
 			  bool write, u32 *device_generation);
 	int (*commit_blocks)(struct inode *inode, struct iomap *iomaps,
 			     int nr_iomaps, struct iattr *iattr);
+#define	EXPORT_OP_NOWCC		(0x1)	/* Don't collect wcc data for NFSv3 replies */
+	unsigned long	flags;
 };
 
 extern int exportfs_encode_inode_fh(struct inode *inode, struct fid *fid,
-- 
cgit v1.2.3


From ba5e8187c55555519ae0b63c0fb681391bc42af9 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jeff.layton@primarydata.com>
Date: Mon, 30 Nov 2020 17:03:15 -0500
Subject: nfsd: allow filesystems to opt out of subtree checking

When we start allowing NFS to be reexported, then we have some problems
when it comes to subtree checking. In principle, we could allow it, but
it would mean encoding parent info in the filehandles and there may not
be enough space for that in a NFSv3 filehandle.

To enforce this at export upcall time, we add a new export_ops flag
that declares the filesystem ineligible for subtree checking.

Signed-off-by: Jeff Layton <jeff.layton@primarydata.com>
Signed-off-by: Lance Shelton <lance.shelton@hammerspace.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 Documentation/filesystems/nfs/exporting.rst | 12 ++++++++++++
 fs/nfs/export.c                             |  2 +-
 fs/nfsd/export.c                            |  6 ++++++
 include/linux/exportfs.h                    |  1 +
 4 files changed, 20 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/nfs/exporting.rst b/Documentation/filesystems/nfs/exporting.rst
index cbe542ad5233..960be64446cb 100644
--- a/Documentation/filesystems/nfs/exporting.rst
+++ b/Documentation/filesystems/nfs/exporting.rst
@@ -190,3 +190,15 @@ following flags are defined:
     this on filesystems that have an expensive ->getattr inode operation,
     or when atomicity between pre and post operation attribute collection
     is impossible to guarantee.
+
+  EXPORT_OP_NOSUBTREECHK - disallow subtree checking on this fs
+    Many NFS operations deal with filehandles, which the server must then
+    vet to ensure that they live inside of an exported tree. When the
+    export consists of an entire filesystem, this is trivial. nfsd can just
+    ensure that the filehandle live on the filesystem. When only part of a
+    filesystem is exported however, then nfsd must walk the ancestors of the
+    inode to ensure that it's within an exported subtree. This is an
+    expensive operation and not all filesystems can support it properly.
+    This flag exempts the filesystem from subtree checking and causes
+    exportfs to get back an error if it tries to enable subtree checking
+    on it.
diff --git a/fs/nfs/export.c b/fs/nfs/export.c
index 8f4c528865c5..b9ba306bf912 100644
--- a/fs/nfs/export.c
+++ b/fs/nfs/export.c
@@ -171,5 +171,5 @@ const struct export_operations nfs_export_ops = {
 	.encode_fh = nfs_encode_fh,
 	.fh_to_dentry = nfs_fh_to_dentry,
 	.get_parent = nfs_get_parent,
-	.flags = EXPORT_OP_NOWCC,
+	.flags = EXPORT_OP_NOWCC|EXPORT_OP_NOSUBTREECHK,
 };
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index 21e404e7cb68..81e7bb12aca6 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -408,6 +408,12 @@ static int check_export(struct inode *inode, int *flags, unsigned char *uuid)
 		return -EINVAL;
 	}
 
+	if (inode->i_sb->s_export_op->flags & EXPORT_OP_NOSUBTREECHK &&
+	    !(*flags & NFSEXP_NOSUBTREECHECK)) {
+		dprintk("%s: %s does not support subtree checking!\n",
+			__func__, inode->i_sb->s_type->name);
+		return -EINVAL;
+	}
 	return 0;
 
 }
diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index e7de0103a32e..2fcbab0f6b61 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -214,6 +214,7 @@ struct export_operations {
 	int (*commit_blocks)(struct inode *inode, struct iomap *iomaps,
 			     int nr_iomaps, struct iattr *iattr);
 #define	EXPORT_OP_NOWCC		(0x1)	/* Don't collect wcc data for NFSv3 replies */
+#define	EXPORT_OP_NOSUBTREECHK	(0x2)	/* Subtree checking is not supported! */
 	unsigned long	flags;
 };
 
-- 
cgit v1.2.3


From 7f84b488f9add1d5cca3e6197c95914c7bd3c1cf Mon Sep 17 00:00:00 2001
From: Jeff Layton <jeff.layton@primarydata.com>
Date: Mon, 30 Nov 2020 17:03:16 -0500
Subject: nfsd: close cached files prior to a REMOVE or RENAME that would
 replace target

It's not uncommon for some workloads to do a bunch of I/O to a file and
delete it just afterward. If knfsd has a cached open file however, then
the file may still be open when the dentry is unlinked. If the
underlying filesystem is nfs, then that could trigger it to do a
sillyrename.

On a REMOVE or RENAME scan the nfsd_file cache for open files that
correspond to the inode, and proactively unhash and put their
references. This should prevent any delete-on-last-close activity from
occurring, solely due to knfsd's open file cache.

This must be done synchronously though so we use the variants that call
flush_delayed_fput. There are deadlock possibilities if you call
flush_delayed_fput while holding locks, however. In the case of
nfsd_rename, we don't even do the lookups of the dentries to be renamed
until we've locked for rename.

Once we've figured out what the target dentry is for a rename, check to
see whether there are cached open files associated with it. If there
are, then unwind all of the locking, close them all, and then reattempt
the rename.

None of this is really necessary for "typical" filesystems though. It's
mostly of use for NFS, so declare a new export op flag and use that to
determine whether to close the files beforehand.

Signed-off-by: Jeff Layton <jeff.layton@primarydata.com>
Signed-off-by: Lance Shelton <lance.shelton@hammerspace.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 Documentation/filesystems/nfs/exporting.rst | 13 +++++++++++++
 fs/nfs/export.c                             |  2 +-
 fs/nfsd/vfs.c                               | 16 +++++++++-------
 include/linux/exportfs.h                    |  5 +++--
 4 files changed, 26 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/nfs/exporting.rst b/Documentation/filesystems/nfs/exporting.rst
index 960be64446cb..0e98edd353b5 100644
--- a/Documentation/filesystems/nfs/exporting.rst
+++ b/Documentation/filesystems/nfs/exporting.rst
@@ -202,3 +202,16 @@ following flags are defined:
     This flag exempts the filesystem from subtree checking and causes
     exportfs to get back an error if it tries to enable subtree checking
     on it.
+
+  EXPORT_OP_CLOSE_BEFORE_UNLINK - always close cached files before unlinking
+    On some exportable filesystems (such as NFS) unlinking a file that
+    is still open can cause a fair bit of extra work. For instance,
+    the NFS client will do a "sillyrename" to ensure that the file
+    sticks around while it's still open. When reexporting, that open
+    file is held by nfsd so we usually end up doing a sillyrename, and
+    then immediately deleting the sillyrenamed file just afterward when
+    the link count actually goes to zero. Sometimes this delete can race
+    with other operations (for instance an rmdir of the parent directory).
+    This flag causes nfsd to close any open files for this inode _before_
+    calling into the vfs to do an unlink or a rename that would replace
+    an existing file.
diff --git a/fs/nfs/export.c b/fs/nfs/export.c
index b9ba306bf912..5428713af5fe 100644
--- a/fs/nfs/export.c
+++ b/fs/nfs/export.c
@@ -171,5 +171,5 @@ const struct export_operations nfs_export_ops = {
 	.encode_fh = nfs_encode_fh,
 	.fh_to_dentry = nfs_fh_to_dentry,
 	.get_parent = nfs_get_parent,
-	.flags = EXPORT_OP_NOWCC|EXPORT_OP_NOSUBTREECHK,
+	.flags = EXPORT_OP_NOWCC|EXPORT_OP_NOSUBTREECHK|EXPORT_OP_CLOSE_BEFORE_UNLINK,
 };
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 1ecaceebee13..79cba942087e 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1724,7 +1724,7 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
 	struct inode	*fdir, *tdir;
 	__be32		err;
 	int		host_err;
-	bool		has_cached = false;
+	bool		close_cached = false;
 
 	err = fh_verify(rqstp, ffhp, S_IFDIR, NFSD_MAY_REMOVE);
 	if (err)
@@ -1783,8 +1783,9 @@ retry:
 	if (ffhp->fh_export->ex_path.dentry != tfhp->fh_export->ex_path.dentry)
 		goto out_dput_new;
 
-	if (nfsd_has_cached_files(ndentry)) {
-		has_cached = true;
+	if ((ndentry->d_sb->s_export_op->flags & EXPORT_OP_CLOSE_BEFORE_UNLINK) &&
+	    nfsd_has_cached_files(ndentry)) {
+		close_cached = true;
 		goto out_dput_old;
 	} else {
 		host_err = vfs_rename(fdir, odentry, tdir, ndentry, NULL, 0);
@@ -1805,7 +1806,7 @@ retry:
 	 * as that would do the wrong thing if the two directories
 	 * were the same, so again we do it by hand.
 	 */
-	if (!has_cached) {
+	if (!close_cached) {
 		fill_post_wcc(ffhp);
 		fill_post_wcc(tfhp);
 	}
@@ -1819,8 +1820,8 @@ retry:
 	 * shouldn't be done with locks held however, so we delay it until this
 	 * point and then reattempt the whole shebang.
 	 */
-	if (has_cached) {
-		has_cached = false;
+	if (close_cached) {
+		close_cached = false;
 		nfsd_close_cached_files(ndentry);
 		dput(ndentry);
 		goto retry;
@@ -1872,7 +1873,8 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
 		type = d_inode(rdentry)->i_mode & S_IFMT;
 
 	if (type != S_IFDIR) {
-		nfsd_close_cached_files(rdentry);
+		if (rdentry->d_sb->s_export_op->flags & EXPORT_OP_CLOSE_BEFORE_UNLINK)
+			nfsd_close_cached_files(rdentry);
 		host_err = vfs_unlink(dirp, rdentry, NULL);
 	} else {
 		host_err = vfs_rmdir(dirp, rdentry);
diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index 2fcbab0f6b61..d829403ffd3b 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -213,8 +213,9 @@ struct export_operations {
 			  bool write, u32 *device_generation);
 	int (*commit_blocks)(struct inode *inode, struct iomap *iomaps,
 			     int nr_iomaps, struct iattr *iattr);
-#define	EXPORT_OP_NOWCC		(0x1)	/* Don't collect wcc data for NFSv3 replies */
-#define	EXPORT_OP_NOSUBTREECHK	(0x2)	/* Subtree checking is not supported! */
+#define	EXPORT_OP_NOWCC			(0x1) /* don't collect v3 wcc data */
+#define	EXPORT_OP_NOSUBTREECHK		(0x2) /* no subtree checking */
+#define	EXPORT_OP_CLOSE_BEFORE_UNLINK	(0x4) /* close files before unlink */
 	unsigned long	flags;
 };
 
-- 
cgit v1.2.3


From d045465fc6cbfa4acfb5a7d817a7c1a57a078109 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Mon, 30 Nov 2020 17:03:17 -0500
Subject: exportfs: Add a function to return the raw output from fh_to_dentry()

In order to allow nfsd to accept return values that are not
acceptable to overlayfs and others, add a new function.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/exportfs/expfs.c      | 32 ++++++++++++++++++++++++--------
 include/linux/exportfs.h |  5 +++++
 2 files changed, 29 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index 2dd55b172d57..0106eba46d5a 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -417,9 +417,11 @@ int exportfs_encode_fh(struct dentry *dentry, struct fid *fid, int *max_len,
 }
 EXPORT_SYMBOL_GPL(exportfs_encode_fh);
 
-struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid,
-		int fh_len, int fileid_type,
-		int (*acceptable)(void *, struct dentry *), void *context)
+struct dentry *
+exportfs_decode_fh_raw(struct vfsmount *mnt, struct fid *fid, int fh_len,
+		       int fileid_type,
+		       int (*acceptable)(void *, struct dentry *),
+		       void *context)
 {
 	const struct export_operations *nop = mnt->mnt_sb->s_export_op;
 	struct dentry *result, *alias;
@@ -432,10 +434,8 @@ struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid,
 	if (!nop || !nop->fh_to_dentry)
 		return ERR_PTR(-ESTALE);
 	result = nop->fh_to_dentry(mnt->mnt_sb, fid, fh_len, fileid_type);
-	if (PTR_ERR(result) == -ENOMEM)
-		return ERR_CAST(result);
 	if (IS_ERR_OR_NULL(result))
-		return ERR_PTR(-ESTALE);
+		return result;
 
 	/*
 	 * If no acceptance criteria was specified by caller, a disconnected
@@ -561,10 +561,26 @@ struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid,
 
  err_result:
 	dput(result);
-	if (err != -ENOMEM)
-		err = -ESTALE;
 	return ERR_PTR(err);
 }
+EXPORT_SYMBOL_GPL(exportfs_decode_fh_raw);
+
+struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid,
+				  int fh_len, int fileid_type,
+				  int (*acceptable)(void *, struct dentry *),
+				  void *context)
+{
+	struct dentry *ret;
+
+	ret = exportfs_decode_fh_raw(mnt, fid, fh_len, fileid_type,
+				     acceptable, context);
+	if (IS_ERR_OR_NULL(ret)) {
+		if (ret == ERR_PTR(-ENOMEM))
+			return ret;
+		return ERR_PTR(-ESTALE);
+	}
+	return ret;
+}
 EXPORT_SYMBOL_GPL(exportfs_decode_fh);
 
 MODULE_LICENSE("GPL");
diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index d829403ffd3b..846df3c96730 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -223,6 +223,11 @@ extern int exportfs_encode_inode_fh(struct inode *inode, struct fid *fid,
 				    int *max_len, struct inode *parent);
 extern int exportfs_encode_fh(struct dentry *dentry, struct fid *fid,
 	int *max_len, int connectable);
+extern struct dentry *exportfs_decode_fh_raw(struct vfsmount *mnt,
+					     struct fid *fid, int fh_len,
+					     int fileid_type,
+					     int (*acceptable)(void *, struct dentry *),
+					     void *context);
 extern struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid,
 	int fh_len, int fileid_type, int (*acceptable)(void *, struct dentry *),
 	void *context);
-- 
cgit v1.2.3


From 01cbf3853959feec40ec9b9a399e12a021cd4d81 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Mon, 30 Nov 2020 17:03:19 -0500
Subject: nfsd: Set PF_LOCAL_THROTTLE on local filesystems only

Don't set PF_LOCAL_THROTTLE on remote filesystems like NFS, since they
aren't expected to ever be subject to double buffering.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfs/export.c          |  3 ++-
 fs/nfsd/vfs.c            | 13 +++++++++++--
 include/linux/exportfs.h |  1 +
 3 files changed, 14 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/export.c b/fs/nfs/export.c
index 5428713af5fe..48b879cfe6e3 100644
--- a/fs/nfs/export.c
+++ b/fs/nfs/export.c
@@ -171,5 +171,6 @@ const struct export_operations nfs_export_ops = {
 	.encode_fh = nfs_encode_fh,
 	.fh_to_dentry = nfs_fh_to_dentry,
 	.get_parent = nfs_get_parent,
-	.flags = EXPORT_OP_NOWCC|EXPORT_OP_NOSUBTREECHK|EXPORT_OP_CLOSE_BEFORE_UNLINK,
+	.flags = EXPORT_OP_NOWCC|EXPORT_OP_NOSUBTREECHK|
+		EXPORT_OP_CLOSE_BEFORE_UNLINK|EXPORT_OP_REMOTE_FS,
 };
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 79cba942087e..04937e51de56 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -978,18 +978,25 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf,
 				__be32 *verf)
 {
 	struct file		*file = nf->nf_file;
+	struct super_block	*sb = file_inode(file)->i_sb;
 	struct svc_export	*exp;
 	struct iov_iter		iter;
 	__be32			nfserr;
 	int			host_err;
 	int			use_wgather;
 	loff_t			pos = offset;
+	unsigned long		exp_op_flags = 0;
 	unsigned int		pflags = current->flags;
 	rwf_t			flags = 0;
+	bool			restore_flags = false;
 
 	trace_nfsd_write_opened(rqstp, fhp, offset, *cnt);
 
-	if (test_bit(RQ_LOCAL, &rqstp->rq_flags))
+	if (sb->s_export_op)
+		exp_op_flags = sb->s_export_op->flags;
+
+	if (test_bit(RQ_LOCAL, &rqstp->rq_flags) &&
+	    !(exp_op_flags & EXPORT_OP_REMOTE_FS)) {
 		/*
 		 * We want throttling in balance_dirty_pages()
 		 * and shrink_inactive_list() to only consider
@@ -998,6 +1005,8 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf,
 		 * the client's dirty pages or its congested queue.
 		 */
 		current->flags |= PF_LOCAL_THROTTLE;
+		restore_flags = true;
+	}
 
 	exp = fhp->fh_export;
 	use_wgather = (rqstp->rq_vers == 2) && EX_WGATHER(exp);
@@ -1049,7 +1058,7 @@ out_nfserr:
 		trace_nfsd_write_err(rqstp, fhp, offset, host_err);
 		nfserr = nfserrno(host_err);
 	}
-	if (test_bit(RQ_LOCAL, &rqstp->rq_flags))
+	if (restore_flags)
 		current_restore_flags(pflags, PF_LOCAL_THROTTLE);
 	return nfserr;
 }
diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index 846df3c96730..d93e8a6737bb 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -216,6 +216,7 @@ struct export_operations {
 #define	EXPORT_OP_NOWCC			(0x1) /* don't collect v3 wcc data */
 #define	EXPORT_OP_NOSUBTREECHK		(0x2) /* no subtree checking */
 #define	EXPORT_OP_CLOSE_BEFORE_UNLINK	(0x4) /* close files before unlink */
+#define EXPORT_OP_REMOTE_FS		(0x8) /* Filesystem is remote */
 	unsigned long	flags;
 };
 
-- 
cgit v1.2.3


From 716a8bc7f706eeef80ab42c99d9f210eda845c81 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Mon, 30 Nov 2020 23:14:27 -0500
Subject: nfsd: Record NFSv4 pre/post-op attributes as non-atomic

For the case of NFSv4, specify to the client that the pre/post-op
attributes were not recorded atomically with the main operation.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfs/export.c          | 3 ++-
 fs/nfsd/nfsfh.c          | 4 ++++
 fs/nfsd/nfsfh.h          | 5 +++++
 fs/nfsd/xdr4.h           | 2 +-
 include/linux/exportfs.h | 3 +++
 5 files changed, 15 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/export.c b/fs/nfs/export.c
index 48b879cfe6e3..7412bb164fa7 100644
--- a/fs/nfs/export.c
+++ b/fs/nfs/export.c
@@ -172,5 +172,6 @@ const struct export_operations nfs_export_ops = {
 	.fh_to_dentry = nfs_fh_to_dentry,
 	.get_parent = nfs_get_parent,
 	.flags = EXPORT_OP_NOWCC|EXPORT_OP_NOSUBTREECHK|
-		EXPORT_OP_CLOSE_BEFORE_UNLINK|EXPORT_OP_REMOTE_FS,
+		EXPORT_OP_CLOSE_BEFORE_UNLINK|EXPORT_OP_REMOTE_FS|
+		EXPORT_OP_NOATOMIC_ATTR,
 };
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index e80a7525561d..66f2ef67792a 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -301,6 +301,10 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
 	fhp->fh_export = exp;
 
 	switch (rqstp->rq_vers) {
+	case 4:
+		if (dentry->d_sb->s_export_op->flags & EXPORT_OP_NOATOMIC_ATTR)
+			fhp->fh_no_atomic_attr = true;
+		break;
 	case 3:
 		if (dentry->d_sb->s_export_op->flags & EXPORT_OP_NOWCC)
 			fhp->fh_no_wcc = true;
diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h
index 347d10aa6265..cb20c2cd3469 100644
--- a/fs/nfsd/nfsfh.h
+++ b/fs/nfsd/nfsfh.h
@@ -36,6 +36,11 @@ typedef struct svc_fh {
 	bool			fh_locked;	/* inode locked by us */
 	bool			fh_want_write;	/* remount protection taken */
 	bool			fh_no_wcc;	/* no wcc data needed */
+	bool			fh_no_atomic_attr;
+						/*
+						 * wcc data is not atomic with
+						 * operation
+						 */
 	int			fh_flags;	/* FH flags */
 #ifdef CONFIG_NFSD_V3
 	bool			fh_post_saved;	/* post-op attrs saved */
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index b4556e86e97c..a60ff5ce1a37 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -748,7 +748,7 @@ static inline void
 set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp)
 {
 	BUG_ON(!fhp->fh_pre_saved);
-	cinfo->atomic = (u32)fhp->fh_post_saved;
+	cinfo->atomic = (u32)(fhp->fh_post_saved && !fhp->fh_no_atomic_attr);
 
 	cinfo->before_change = fhp->fh_pre_change;
 	cinfo->after_change = fhp->fh_post_change;
diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index d93e8a6737bb..9f4d4bcbf251 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -217,6 +217,9 @@ struct export_operations {
 #define	EXPORT_OP_NOSUBTREECHK		(0x2) /* no subtree checking */
 #define	EXPORT_OP_CLOSE_BEFORE_UNLINK	(0x4) /* close files before unlink */
 #define EXPORT_OP_REMOTE_FS		(0x8) /* Filesystem is remote */
+#define EXPORT_OP_NOATOMIC_ATTR		(0x10) /* Filesystem cannot supply
+						  atomic attribute updates
+						*/
 	unsigned long	flags;
 };
 
-- 
cgit v1.2.3


From 0f9368b5bf6db0c04afc5454b1be79022a681615 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Thu, 3 Dec 2020 14:10:32 -0600
Subject: rwsem: Implement down_read_killable_nested

In preparation for converting exec_update_mutex to a rwsem so that
multiple readers can execute in parallel and not deadlock, add
down_read_killable_nested.  This is needed so that kcmp_lock
can be converted from working on a mutexes to working on rw_semaphores.

Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/87o8jabqh3.fsf@x220.int.ebiederm.org
---
 include/linux/rwsem.h  |  2 ++
 kernel/locking/rwsem.c | 14 ++++++++++++++
 2 files changed, 16 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index 25e3fde85617..13021b08b2ed 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -171,6 +171,7 @@ extern void downgrade_write(struct rw_semaphore *sem);
  * See Documentation/locking/lockdep-design.rst for more details.)
  */
 extern void down_read_nested(struct rw_semaphore *sem, int subclass);
+extern int __must_check down_read_killable_nested(struct rw_semaphore *sem, int subclass);
 extern void down_write_nested(struct rw_semaphore *sem, int subclass);
 extern int down_write_killable_nested(struct rw_semaphore *sem, int subclass);
 extern void _down_write_nest_lock(struct rw_semaphore *sem, struct lockdep_map *nest_lock);
@@ -191,6 +192,7 @@ extern void down_read_non_owner(struct rw_semaphore *sem);
 extern void up_read_non_owner(struct rw_semaphore *sem);
 #else
 # define down_read_nested(sem, subclass)		down_read(sem)
+# define down_read_killable_nested(sem, subclass)	down_read_killable(sem)
 # define down_write_nest_lock(sem, nest_lock)	down_write(sem)
 # define down_write_nested(sem, subclass)	down_write(sem)
 # define down_write_killable_nested(sem, subclass)	down_write_killable(sem)
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index f11b9bd3431d..54d11cb97551 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -1605,6 +1605,20 @@ void down_read_nested(struct rw_semaphore *sem, int subclass)
 }
 EXPORT_SYMBOL(down_read_nested);
 
+int down_read_killable_nested(struct rw_semaphore *sem, int subclass)
+{
+	might_sleep();
+	rwsem_acquire_read(&sem->dep_map, subclass, 0, _RET_IP_);
+
+	if (LOCK_CONTENDED_RETURN(sem, __down_read_trylock, __down_read_killable)) {
+		rwsem_release(&sem->dep_map, _RET_IP_);
+		return -EINTR;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(down_read_killable_nested);
+
 void _down_write_nest_lock(struct rw_semaphore *sem, struct lockdep_map *nest)
 {
 	might_sleep();
-- 
cgit v1.2.3


From 31784cff7ee073b34d6eddabb95e3be2880a425c Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Thu, 3 Dec 2020 14:11:13 -0600
Subject: rwsem: Implement down_read_interruptible

In preparation for converting exec_update_mutex to a rwsem so that
multiple readers can execute in parallel and not deadlock, add
down_read_interruptible.  This is needed for perf_event_open to be
converted (with no semantic changes) from working on a mutex to
wroking on a rwsem.

Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/87k0tybqfy.fsf@x220.int.ebiederm.org
---
 include/linux/rwsem.h  |  1 +
 kernel/locking/rwsem.c | 26 ++++++++++++++++++++++++++
 2 files changed, 27 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index 13021b08b2ed..4c715be48717 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -123,6 +123,7 @@ static inline int rwsem_is_contended(struct rw_semaphore *sem)
  * lock for reading
  */
 extern void down_read(struct rw_semaphore *sem);
+extern int __must_check down_read_interruptible(struct rw_semaphore *sem);
 extern int __must_check down_read_killable(struct rw_semaphore *sem);
 
 /*
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 54d11cb97551..a163542d178e 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -1345,6 +1345,18 @@ static inline void __down_read(struct rw_semaphore *sem)
 	}
 }
 
+static inline int __down_read_interruptible(struct rw_semaphore *sem)
+{
+	if (!rwsem_read_trylock(sem)) {
+		if (IS_ERR(rwsem_down_read_slowpath(sem, TASK_INTERRUPTIBLE)))
+			return -EINTR;
+		DEBUG_RWSEMS_WARN_ON(!is_rwsem_reader_owned(sem), sem);
+	} else {
+		rwsem_set_reader_owned(sem);
+	}
+	return 0;
+}
+
 static inline int __down_read_killable(struct rw_semaphore *sem)
 {
 	if (!rwsem_read_trylock(sem)) {
@@ -1495,6 +1507,20 @@ void __sched down_read(struct rw_semaphore *sem)
 }
 EXPORT_SYMBOL(down_read);
 
+int __sched down_read_interruptible(struct rw_semaphore *sem)
+{
+	might_sleep();
+	rwsem_acquire_read(&sem->dep_map, 0, 0, _RET_IP_);
+
+	if (LOCK_CONTENDED_RETURN(sem, __down_read_trylock, __down_read_interruptible)) {
+		rwsem_release(&sem->dep_map, _RET_IP_);
+		return -EINTR;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(down_read_interruptible);
+
 int __sched down_read_killable(struct rw_semaphore *sem)
 {
 	might_sleep();
-- 
cgit v1.2.3


From 66bcfcdf89d00f2409f4b5da0f8c20c08318dc72 Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Sun, 6 Dec 2020 17:21:42 +0100
Subject: seqlock: Prefix internal seqcount_t-only macros with a "do_"

When the seqcount_LOCKNAME_t group of data types were introduced, two
classes of seqlock.h sequence counter macros were added:

  - An external public API which can either take a plain seqcount_t or
    any of the seqcount_LOCKNAME_t variants.

  - An internal API which takes only a plain seqcount_t.

To distinguish between the two groups, the "*_seqcount_t_*" pattern was
used for the latter. This confused a number of mm/ call-site developers,
and Linus also commented that it was not a standard practice for marking
seqlock.h internal APIs.

Distinguish the latter group of macros by prefixing a "do_".

Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/CAHk-=wikhGExmprXgaW+MVXG1zsGpztBbVwOb23vetk41EtTBQ@mail.gmail.com
---
 include/linux/seqlock.h | 66 ++++++++++++++++++++++++-------------------------
 1 file changed, 33 insertions(+), 33 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index d89134c74fba..235cbc65fd71 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -425,9 +425,9 @@ SEQCOUNT_LOCKNAME(ww_mutex,     struct ww_mutex, true,     &s->lock->base, ww_mu
  * Return: true if a read section retry is required, else false
  */
 #define __read_seqcount_retry(s, start)					\
-	__read_seqcount_t_retry(seqprop_ptr(s), start)
+	do___read_seqcount_retry(seqprop_ptr(s), start)
 
-static inline int __read_seqcount_t_retry(const seqcount_t *s, unsigned start)
+static inline int do___read_seqcount_retry(const seqcount_t *s, unsigned start)
 {
 	kcsan_atomic_next(0);
 	return unlikely(READ_ONCE(s->sequence) != start);
@@ -445,12 +445,12 @@ static inline int __read_seqcount_t_retry(const seqcount_t *s, unsigned start)
  * Return: true if a read section retry is required, else false
  */
 #define read_seqcount_retry(s, start)					\
-	read_seqcount_t_retry(seqprop_ptr(s), start)
+	do_read_seqcount_retry(seqprop_ptr(s), start)
 
-static inline int read_seqcount_t_retry(const seqcount_t *s, unsigned start)
+static inline int do_read_seqcount_retry(const seqcount_t *s, unsigned start)
 {
 	smp_rmb();
-	return __read_seqcount_t_retry(s, start);
+	return do___read_seqcount_retry(s, start);
 }
 
 /**
@@ -462,10 +462,10 @@ do {									\
 	if (seqprop_preemptible(s))					\
 		preempt_disable();					\
 									\
-	raw_write_seqcount_t_begin(seqprop_ptr(s));			\
+	do_raw_write_seqcount_begin(seqprop_ptr(s));			\
 } while (0)
 
-static inline void raw_write_seqcount_t_begin(seqcount_t *s)
+static inline void do_raw_write_seqcount_begin(seqcount_t *s)
 {
 	kcsan_nestable_atomic_begin();
 	s->sequence++;
@@ -478,13 +478,13 @@ static inline void raw_write_seqcount_t_begin(seqcount_t *s)
  */
 #define raw_write_seqcount_end(s)					\
 do {									\
-	raw_write_seqcount_t_end(seqprop_ptr(s));			\
+	do_raw_write_seqcount_end(seqprop_ptr(s));			\
 									\
 	if (seqprop_preemptible(s))					\
 		preempt_enable();					\
 } while (0)
 
-static inline void raw_write_seqcount_t_end(seqcount_t *s)
+static inline void do_raw_write_seqcount_end(seqcount_t *s)
 {
 	smp_wmb();
 	s->sequence++;
@@ -506,12 +506,12 @@ do {									\
 	if (seqprop_preemptible(s))					\
 		preempt_disable();					\
 									\
-	write_seqcount_t_begin_nested(seqprop_ptr(s), subclass);	\
+	do_write_seqcount_begin_nested(seqprop_ptr(s), subclass);	\
 } while (0)
 
-static inline void write_seqcount_t_begin_nested(seqcount_t *s, int subclass)
+static inline void do_write_seqcount_begin_nested(seqcount_t *s, int subclass)
 {
-	raw_write_seqcount_t_begin(s);
+	do_raw_write_seqcount_begin(s);
 	seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_);
 }
 
@@ -533,12 +533,12 @@ do {									\
 	if (seqprop_preemptible(s))					\
 		preempt_disable();					\
 									\
-	write_seqcount_t_begin(seqprop_ptr(s));				\
+	do_write_seqcount_begin(seqprop_ptr(s));			\
 } while (0)
 
-static inline void write_seqcount_t_begin(seqcount_t *s)
+static inline void do_write_seqcount_begin(seqcount_t *s)
 {
-	write_seqcount_t_begin_nested(s, 0);
+	do_write_seqcount_begin_nested(s, 0);
 }
 
 /**
@@ -549,16 +549,16 @@ static inline void write_seqcount_t_begin(seqcount_t *s)
  */
 #define write_seqcount_end(s)						\
 do {									\
-	write_seqcount_t_end(seqprop_ptr(s));				\
+	do_write_seqcount_end(seqprop_ptr(s));				\
 									\
 	if (seqprop_preemptible(s))					\
 		preempt_enable();					\
 } while (0)
 
-static inline void write_seqcount_t_end(seqcount_t *s)
+static inline void do_write_seqcount_end(seqcount_t *s)
 {
 	seqcount_release(&s->dep_map, _RET_IP_);
-	raw_write_seqcount_t_end(s);
+	do_raw_write_seqcount_end(s);
 }
 
 /**
@@ -603,9 +603,9 @@ static inline void write_seqcount_t_end(seqcount_t *s)
  *      }
  */
 #define raw_write_seqcount_barrier(s)					\
-	raw_write_seqcount_t_barrier(seqprop_ptr(s))
+	do_raw_write_seqcount_barrier(seqprop_ptr(s))
 
-static inline void raw_write_seqcount_t_barrier(seqcount_t *s)
+static inline void do_raw_write_seqcount_barrier(seqcount_t *s)
 {
 	kcsan_nestable_atomic_begin();
 	s->sequence++;
@@ -623,9 +623,9 @@ static inline void raw_write_seqcount_t_barrier(seqcount_t *s)
  * will complete successfully and see data older than this.
  */
 #define write_seqcount_invalidate(s)					\
-	write_seqcount_t_invalidate(seqprop_ptr(s))
+	do_write_seqcount_invalidate(seqprop_ptr(s))
 
-static inline void write_seqcount_t_invalidate(seqcount_t *s)
+static inline void do_write_seqcount_invalidate(seqcount_t *s)
 {
 	smp_wmb();
 	kcsan_nestable_atomic_begin();
@@ -865,9 +865,9 @@ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start)
 }
 
 /*
- * For all seqlock_t write side functions, use write_seqcount_*t*_begin()
- * instead of the generic write_seqcount_begin(). This way, no redundant
- * lockdep_assert_held() checks are added.
+ * For all seqlock_t write side functions, use the the internal
+ * do_write_seqcount_begin() instead of generic write_seqcount_begin().
+ * This way, no redundant lockdep_assert_held() checks are added.
  */
 
 /**
@@ -886,7 +886,7 @@ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start)
 static inline void write_seqlock(seqlock_t *sl)
 {
 	spin_lock(&sl->lock);
-	write_seqcount_t_begin(&sl->seqcount.seqcount);
+	do_write_seqcount_begin(&sl->seqcount.seqcount);
 }
 
 /**
@@ -898,7 +898,7 @@ static inline void write_seqlock(seqlock_t *sl)
  */
 static inline void write_sequnlock(seqlock_t *sl)
 {
-	write_seqcount_t_end(&sl->seqcount.seqcount);
+	do_write_seqcount_end(&sl->seqcount.seqcount);
 	spin_unlock(&sl->lock);
 }
 
@@ -912,7 +912,7 @@ static inline void write_sequnlock(seqlock_t *sl)
 static inline void write_seqlock_bh(seqlock_t *sl)
 {
 	spin_lock_bh(&sl->lock);
-	write_seqcount_t_begin(&sl->seqcount.seqcount);
+	do_write_seqcount_begin(&sl->seqcount.seqcount);
 }
 
 /**
@@ -925,7 +925,7 @@ static inline void write_seqlock_bh(seqlock_t *sl)
  */
 static inline void write_sequnlock_bh(seqlock_t *sl)
 {
-	write_seqcount_t_end(&sl->seqcount.seqcount);
+	do_write_seqcount_end(&sl->seqcount.seqcount);
 	spin_unlock_bh(&sl->lock);
 }
 
@@ -939,7 +939,7 @@ static inline void write_sequnlock_bh(seqlock_t *sl)
 static inline void write_seqlock_irq(seqlock_t *sl)
 {
 	spin_lock_irq(&sl->lock);
-	write_seqcount_t_begin(&sl->seqcount.seqcount);
+	do_write_seqcount_begin(&sl->seqcount.seqcount);
 }
 
 /**
@@ -951,7 +951,7 @@ static inline void write_seqlock_irq(seqlock_t *sl)
  */
 static inline void write_sequnlock_irq(seqlock_t *sl)
 {
-	write_seqcount_t_end(&sl->seqcount.seqcount);
+	do_write_seqcount_end(&sl->seqcount.seqcount);
 	spin_unlock_irq(&sl->lock);
 }
 
@@ -960,7 +960,7 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl)
 	unsigned long flags;
 
 	spin_lock_irqsave(&sl->lock, flags);
-	write_seqcount_t_begin(&sl->seqcount.seqcount);
+	do_write_seqcount_begin(&sl->seqcount.seqcount);
 	return flags;
 }
 
@@ -989,7 +989,7 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl)
 static inline void
 write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags)
 {
-	write_seqcount_t_end(&sl->seqcount.seqcount);
+	do_write_seqcount_end(&sl->seqcount.seqcount);
 	spin_unlock_irqrestore(&sl->lock, flags);
 }
 
-- 
cgit v1.2.3


From cb262935a166bdef0ccfe6e2adffa00c0f2d038a Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Sun, 6 Dec 2020 17:21:43 +0100
Subject: seqlock: kernel-doc: Specify when preemption is automatically altered

The kernel-doc annotations for sequence counters write side functions
are incomplete: they do not specify when preemption is automatically
disabled and re-enabled.

This has confused a number of call-site developers. Fix it.

Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/CAHk-=wikhGExmprXgaW+MVXG1zsGpztBbVwOb23vetk41EtTBQ@mail.gmail.com
---
 include/linux/seqlock.h | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 235cbc65fd71..2f7bb92b4c9e 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -456,6 +456,8 @@ static inline int do_read_seqcount_retry(const seqcount_t *s, unsigned start)
 /**
  * raw_write_seqcount_begin() - start a seqcount_t write section w/o lockdep
  * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
+ *
+ * Context: check write_seqcount_begin()
  */
 #define raw_write_seqcount_begin(s)					\
 do {									\
@@ -475,6 +477,8 @@ static inline void do_raw_write_seqcount_begin(seqcount_t *s)
 /**
  * raw_write_seqcount_end() - end a seqcount_t write section w/o lockdep
  * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
+ *
+ * Context: check write_seqcount_end()
  */
 #define raw_write_seqcount_end(s)					\
 do {									\
@@ -498,6 +502,7 @@ static inline void do_raw_write_seqcount_end(seqcount_t *s)
  * @subclass: lockdep nesting level
  *
  * See Documentation/locking/lockdep-design.rst
+ * Context: check write_seqcount_begin()
  */
 #define write_seqcount_begin_nested(s, subclass)			\
 do {									\
@@ -519,11 +524,10 @@ static inline void do_write_seqcount_begin_nested(seqcount_t *s, int subclass)
  * write_seqcount_begin() - start a seqcount_t write side critical section
  * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
  *
- * write_seqcount_begin opens a write side critical section of the given
- * seqcount_t.
- *
- * Context: seqcount_t write side critical sections must be serialized and
- * non-preemptible. If readers can be invoked from hardirq or softirq
+ * Context: sequence counter write side sections must be serialized and
+ * non-preemptible. Preemption will be automatically disabled if and
+ * only if the seqcount write serialization lock is associated, and
+ * preemptible.  If readers can be invoked from hardirq or softirq
  * context, interrupts or bottom halves must be respectively disabled.
  */
 #define write_seqcount_begin(s)						\
@@ -545,7 +549,8 @@ static inline void do_write_seqcount_begin(seqcount_t *s)
  * write_seqcount_end() - end a seqcount_t write side critical section
  * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
  *
- * The write section must've been opened with write_seqcount_begin().
+ * Context: Preemption will be automatically re-enabled if and only if
+ * the seqcount write serialization lock is associated, and preemptible.
  */
 #define write_seqcount_end(s)						\
 do {									\
-- 
cgit v1.2.3


From 0854bcdcdec26aecdc92c303816f349ee1fba2bc Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Tue, 8 Dec 2020 21:29:45 -0800
Subject: scsi: block: Introduce BLK_MQ_REQ_PM

Introduce the BLK_MQ_REQ_PM flag. This flag makes the request allocation
functions set RQF_PM. This is the first step towards removing
BLK_MQ_REQ_PREEMPT.

Link: https://lore.kernel.org/r/20201209052951.16136-3-bvanassche@acm.org
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Stanley Chu <stanley.chu@mediatek.com>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Can Guo <cang@codeaurora.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Reviewed-by: Can Guo <cang@codeaurora.org>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 block/blk-core.c       | 7 ++++---
 block/blk-mq.c         | 2 ++
 include/linux/blk-mq.h | 2 ++
 3 files changed, 8 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-core.c b/block/blk-core.c
index 2db8bda43b6e..10696f9fb6ac 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -424,11 +424,11 @@ EXPORT_SYMBOL(blk_cleanup_queue);
 /**
  * blk_queue_enter() - try to increase q->q_usage_counter
  * @q: request queue pointer
- * @flags: BLK_MQ_REQ_NOWAIT and/or BLK_MQ_REQ_PREEMPT
+ * @flags: BLK_MQ_REQ_NOWAIT, BLK_MQ_REQ_PM and/or BLK_MQ_REQ_PREEMPT
  */
 int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags)
 {
-	const bool pm = flags & BLK_MQ_REQ_PREEMPT;
+	const bool pm = flags & (BLK_MQ_REQ_PM | BLK_MQ_REQ_PREEMPT);
 
 	while (true) {
 		bool success = false;
@@ -630,7 +630,8 @@ struct request *blk_get_request(struct request_queue *q, unsigned int op,
 	struct request *req;
 
 	WARN_ON_ONCE(op & REQ_NOWAIT);
-	WARN_ON_ONCE(flags & ~(BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_PREEMPT));
+	WARN_ON_ONCE(flags & ~(BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_PM |
+			       BLK_MQ_REQ_PREEMPT));
 
 	req = blk_mq_alloc_request(q, op, flags);
 	if (!IS_ERR(req) && q->mq_ops->initialize_rq_fn)
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 1b25ec2fe9be..b5880a1fb38d 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -292,6 +292,8 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 	rq->mq_hctx = data->hctx;
 	rq->rq_flags = 0;
 	rq->cmd_flags = data->cmd_flags;
+	if (data->flags & BLK_MQ_REQ_PM)
+		rq->rq_flags |= RQF_PM;
 	if (data->flags & BLK_MQ_REQ_PREEMPT)
 		rq->rq_flags |= RQF_PREEMPT;
 	if (blk_queue_io_stat(data->q))
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index b23eeca4d677..c00e856c6fb1 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -444,6 +444,8 @@ enum {
 	BLK_MQ_REQ_NOWAIT	= (__force blk_mq_req_flags_t)(1 << 0),
 	/* allocate from reserved pool */
 	BLK_MQ_REQ_RESERVED	= (__force blk_mq_req_flags_t)(1 << 1),
+	/* set RQF_PM */
+	BLK_MQ_REQ_PM		= (__force blk_mq_req_flags_t)(1 << 2),
 	/* set RQF_PREEMPT */
 	BLK_MQ_REQ_PREEMPT	= (__force blk_mq_req_flags_t)(1 << 3),
 };
-- 
cgit v1.2.3


From a4d34da715e3cb7e0741fe603dcd511bed067e00 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Tue, 8 Dec 2020 21:29:50 -0800
Subject: scsi: block: Remove RQF_PREEMPT and BLK_MQ_REQ_PREEMPT

Remove flag RQF_PREEMPT and BLK_MQ_REQ_PREEMPT since these are no longer
used by any kernel code.

Link: https://lore.kernel.org/r/20201209052951.16136-8-bvanassche@acm.org
Cc: Can Guo <cang@codeaurora.org>
Cc: Stanley Chu <stanley.chu@mediatek.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Martin Kepplinger <martin.kepplinger@puri.sm>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Reviewed-by: Can Guo <cang@codeaurora.org>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 block/blk-core.c       | 7 +++----
 block/blk-mq-debugfs.c | 1 -
 block/blk-mq.c         | 2 --
 include/linux/blk-mq.h | 2 --
 include/linux/blkdev.h | 6 +-----
 5 files changed, 4 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-core.c b/block/blk-core.c
index 10696f9fb6ac..a00bce9f46d8 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -424,11 +424,11 @@ EXPORT_SYMBOL(blk_cleanup_queue);
 /**
  * blk_queue_enter() - try to increase q->q_usage_counter
  * @q: request queue pointer
- * @flags: BLK_MQ_REQ_NOWAIT, BLK_MQ_REQ_PM and/or BLK_MQ_REQ_PREEMPT
+ * @flags: BLK_MQ_REQ_NOWAIT and/or BLK_MQ_REQ_PM
  */
 int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags)
 {
-	const bool pm = flags & (BLK_MQ_REQ_PM | BLK_MQ_REQ_PREEMPT);
+	const bool pm = flags & BLK_MQ_REQ_PM;
 
 	while (true) {
 		bool success = false;
@@ -630,8 +630,7 @@ struct request *blk_get_request(struct request_queue *q, unsigned int op,
 	struct request *req;
 
 	WARN_ON_ONCE(op & REQ_NOWAIT);
-	WARN_ON_ONCE(flags & ~(BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_PM |
-			       BLK_MQ_REQ_PREEMPT));
+	WARN_ON_ONCE(flags & ~(BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_PM));
 
 	req = blk_mq_alloc_request(q, op, flags);
 	if (!IS_ERR(req) && q->mq_ops->initialize_rq_fn)
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 3094542e12ae..9336a6f8d6ef 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -297,7 +297,6 @@ static const char *const rqf_name[] = {
 	RQF_NAME(MIXED_MERGE),
 	RQF_NAME(MQ_INFLIGHT),
 	RQF_NAME(DONTPREP),
-	RQF_NAME(PREEMPT),
 	RQF_NAME(FAILED),
 	RQF_NAME(QUIET),
 	RQF_NAME(ELVPRIV),
diff --git a/block/blk-mq.c b/block/blk-mq.c
index b5880a1fb38d..d50504888b68 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -294,8 +294,6 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 	rq->cmd_flags = data->cmd_flags;
 	if (data->flags & BLK_MQ_REQ_PM)
 		rq->rq_flags |= RQF_PM;
-	if (data->flags & BLK_MQ_REQ_PREEMPT)
-		rq->rq_flags |= RQF_PREEMPT;
 	if (blk_queue_io_stat(data->q))
 		rq->rq_flags |= RQF_IO_STAT;
 	INIT_LIST_HEAD(&rq->queuelist);
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index c00e856c6fb1..88af1df94308 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -446,8 +446,6 @@ enum {
 	BLK_MQ_REQ_RESERVED	= (__force blk_mq_req_flags_t)(1 << 1),
 	/* set RQF_PM */
 	BLK_MQ_REQ_PM		= (__force blk_mq_req_flags_t)(1 << 2),
-	/* set RQF_PREEMPT */
-	BLK_MQ_REQ_PREEMPT	= (__force blk_mq_req_flags_t)(1 << 3),
 };
 
 struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 639cae2c158b..7d4b746f7e6a 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -79,9 +79,6 @@ typedef __u32 __bitwise req_flags_t;
 #define RQF_MQ_INFLIGHT		((__force req_flags_t)(1 << 6))
 /* don't call prep for this one */
 #define RQF_DONTPREP		((__force req_flags_t)(1 << 7))
-/* set for "ide_preempt" requests and also for requests for which the SCSI
-   "quiesce" state must be ignored. */
-#define RQF_PREEMPT		((__force req_flags_t)(1 << 8))
 /* vaguely specified driver internal error.  Ignored by the block layer */
 #define RQF_FAILED		((__force req_flags_t)(1 << 10))
 /* don't warn about errors */
@@ -430,8 +427,7 @@ struct request_queue {
 	unsigned long		queue_flags;
 	/*
 	 * Number of contexts that have called blk_set_pm_only(). If this
-	 * counter is above zero then only RQF_PM and RQF_PREEMPT requests are
-	 * processed.
+	 * counter is above zero then only RQF_PM requests are processed.
 	 */
 	atomic_t		pm_only;
 
-- 
cgit v1.2.3


From 52abca64fd9410ea6c9a3a74eab25663b403d7da Mon Sep 17 00:00:00 2001
From: Alan Stern <stern@rowland.harvard.edu>
Date: Tue, 8 Dec 2020 21:29:51 -0800
Subject: scsi: block: Do not accept any requests while suspended

blk_queue_enter() accepts BLK_MQ_REQ_PM requests independent of the runtime
power management state. Now that SCSI domain validation no longer depends
on this behavior, modify the behavior of blk_queue_enter() as follows:

   - Do not accept any requests while suspended.

   - Only process power management requests while suspending or resuming.

Submitting BLK_MQ_REQ_PM requests to a device that is runtime suspended
causes runtime-suspended devices not to resume as they should. The request
which should cause a runtime resume instead gets issued directly, without
resuming the device first. Of course the device can't handle it properly,
the I/O fails, and the device remains suspended.

The problem is fixed by checking that the queue's runtime-PM status isn't
RPM_SUSPENDED before allowing a request to be issued, and queuing a
runtime-resume request if it is.  In particular, the inline
blk_pm_request_resume() routine is renamed blk_pm_resume_queue() and the
code is unified by merging the surrounding checks into the routine.  If the
queue isn't set up for runtime PM, or there currently is no restriction on
allowed requests, the request is allowed.  Likewise if the BLK_MQ_REQ_PM
flag is set and the status isn't RPM_SUSPENDED.  Otherwise a runtime resume
is queued and the request is blocked until conditions are more suitable.

[ bvanassche: modified commit message and removed Cc: stable because
  without the previous patches from this series this patch would break
  parallel SCSI domain validation + introduced queue_rpm_status() ]

Link: https://lore.kernel.org/r/20201209052951.16136-9-bvanassche@acm.org
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Can Guo <cang@codeaurora.org>
Cc: Stanley Chu <stanley.chu@mediatek.com>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reported-and-tested-by: Martin Kepplinger <martin.kepplinger@puri.sm>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Can Guo <cang@codeaurora.org>
Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 block/blk-core.c       |  7 ++++---
 block/blk-pm.h         | 14 +++++++++-----
 include/linux/blkdev.h | 12 ++++++++++++
 3 files changed, 25 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-core.c b/block/blk-core.c
index a00bce9f46d8..2d53e2ff48ff 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -18,6 +18,7 @@
 #include <linux/bio.h>
 #include <linux/blkdev.h>
 #include <linux/blk-mq.h>
+#include <linux/blk-pm.h>
 #include <linux/highmem.h>
 #include <linux/mm.h>
 #include <linux/pagemap.h>
@@ -440,7 +441,8 @@ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags)
 			 * responsible for ensuring that that counter is
 			 * globally visible before the queue is unfrozen.
 			 */
-			if (pm || !blk_queue_pm_only(q)) {
+			if ((pm && queue_rpm_status(q) != RPM_SUSPENDED) ||
+			    !blk_queue_pm_only(q)) {
 				success = true;
 			} else {
 				percpu_ref_put(&q->q_usage_counter);
@@ -465,8 +467,7 @@ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags)
 
 		wait_event(q->mq_freeze_wq,
 			   (!q->mq_freeze_depth &&
-			    (pm || (blk_pm_request_resume(q),
-				    !blk_queue_pm_only(q)))) ||
+			    blk_pm_resume_queue(pm, q)) ||
 			   blk_queue_dying(q));
 		if (blk_queue_dying(q))
 			return -ENODEV;
diff --git a/block/blk-pm.h b/block/blk-pm.h
index ea5507d23e75..a2283cc9f716 100644
--- a/block/blk-pm.h
+++ b/block/blk-pm.h
@@ -6,11 +6,14 @@
 #include <linux/pm_runtime.h>
 
 #ifdef CONFIG_PM
-static inline void blk_pm_request_resume(struct request_queue *q)
+static inline int blk_pm_resume_queue(const bool pm, struct request_queue *q)
 {
-	if (q->dev && (q->rpm_status == RPM_SUSPENDED ||
-		       q->rpm_status == RPM_SUSPENDING))
-		pm_request_resume(q->dev);
+	if (!q->dev || !blk_queue_pm_only(q))
+		return 1;	/* Nothing to do */
+	if (pm && q->rpm_status != RPM_SUSPENDED)
+		return 1;	/* Request allowed */
+	pm_request_resume(q->dev);
+	return 0;
 }
 
 static inline void blk_pm_mark_last_busy(struct request *rq)
@@ -44,8 +47,9 @@ static inline void blk_pm_put_request(struct request *rq)
 		--rq->q->nr_pending;
 }
 #else
-static inline void blk_pm_request_resume(struct request_queue *q)
+static inline int blk_pm_resume_queue(const bool pm, struct request_queue *q)
 {
+	return 1;
 }
 
 static inline void blk_pm_mark_last_busy(struct request *rq)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 7d4b746f7e6a..2b6fc3fb3a99 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -692,6 +692,18 @@ static inline bool queue_is_mq(struct request_queue *q)
 	return q->mq_ops;
 }
 
+#ifdef CONFIG_PM
+static inline enum rpm_status queue_rpm_status(struct request_queue *q)
+{
+	return q->rpm_status;
+}
+#else
+static inline enum rpm_status queue_rpm_status(struct request_queue *q)
+{
+	return RPM_ACTIVE;
+}
+#endif
+
 static inline enum blk_zoned_model
 blk_queue_zoned_model(struct request_queue *q)
 {
-- 
cgit v1.2.3


From c95d64012ad7de2747923b0caf80e195e940606c Mon Sep 17 00:00:00 2001
From: Saravana Kannan <saravanak@google.com>
Date: Fri, 20 Nov 2020 18:02:16 -0800
Subject: Revert "driver core: Avoid deferred probe due to
 fw_devlink_pause/resume()"

This reverts commit 2451e746478a6a6e981cfa66b62b791ca93b90c8.

fw_devlink_pause/resume() was an incomplete attempt at boot time
optimization. That's going to get replaced by a much better optimization
at the end of the series. Since fw_devlink_pause/resume() is going away,
changes made for that can also go away.

Signed-off-by: Saravana Kannan <saravanak@google.com>
Link: https://lore.kernel.org/r/20201121020232.908850-2-saravanak@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/core.c    | 21 ---------------------
 include/linux/device.h |  3 +--
 2 files changed, 1 insertion(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/core.c b/drivers/base/core.c
index ba5a3cac6571..58c7d17820a7 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -51,7 +51,6 @@ static DEFINE_MUTEX(wfs_lock);
 static LIST_HEAD(deferred_sync);
 static unsigned int defer_sync_state_count = 1;
 static unsigned int defer_fw_devlink_count;
-static LIST_HEAD(deferred_fw_devlink);
 static DEFINE_MUTEX(defer_fw_devlink_lock);
 static bool fw_devlink_is_permissive(void);
 
@@ -1468,12 +1467,6 @@ static void fw_devlink_link_device(struct device *dev)
 			fw_ret = -EAGAIN;
 	} else {
 		fw_ret = -ENODEV;
-		/*
-		 * defer_hook is not used to add device to deferred_sync list
-		 * until device is bound. Since deferred fw devlink also blocks
-		 * probing, same list hook can be used for deferred_fw_devlink.
-		 */
-		list_add_tail(&dev->links.defer_hook, &deferred_fw_devlink);
 	}
 
 	if (fw_ret == -ENODEV)
@@ -1542,9 +1535,6 @@ void fw_devlink_pause(void)
  */
 void fw_devlink_resume(void)
 {
-	struct device *dev, *tmp;
-	LIST_HEAD(probe_list);
-
 	mutex_lock(&defer_fw_devlink_lock);
 	if (!defer_fw_devlink_count) {
 		WARN(true, "Unmatched fw_devlink pause/resume!");
@@ -1556,19 +1546,8 @@ void fw_devlink_resume(void)
 		goto out;
 
 	device_link_add_missing_supplier_links();
-	list_splice_tail_init(&deferred_fw_devlink, &probe_list);
 out:
 	mutex_unlock(&defer_fw_devlink_lock);
-
-	/*
-	 * bus_probe_device() can cause new devices to get added and they'll
-	 * try to grab defer_fw_devlink_lock. So, this needs to be done outside
-	 * the defer_fw_devlink_lock.
-	 */
-	list_for_each_entry_safe(dev, tmp, &probe_list, links.defer_hook) {
-		list_del_init(&dev->links.defer_hook);
-		bus_probe_device(dev);
-	}
 }
 /* Device links support end. */
 
diff --git a/include/linux/device.h b/include/linux/device.h
index 5ed101be7b2e..da00f8e449bb 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -352,8 +352,7 @@ enum dl_dev_state {
  * @suppliers: List of links to supplier devices.
  * @consumers: List of links to consumer devices.
  * @needs_suppliers: Hook to global list of devices waiting for suppliers.
- * @defer_hook: Hook to global list of devices that have deferred sync_state or
- *		deferred fw_devlink.
+ * @defer_hook: Hook to global list of devices that have deferred sync_state.
  * @need_for_probe: If needs_suppliers is on a list, this indicates if the
  *		    suppliers are needed for probe or not.
  * @status: Driver status information.
-- 
cgit v1.2.3


From 3b052a3e30f2eb92dcae9fd89af48d5a13045737 Mon Sep 17 00:00:00 2001
From: Saravana Kannan <saravanak@google.com>
Date: Fri, 20 Nov 2020 18:02:17 -0800
Subject: Revert "driver core: Rename dev_links_info.defer_sync to defer_hook"

This reverts commit ec7bd78498f29680f536451fbdf9464e851273ed.

This field rename was done to reuse defer_syc list head for multiple
lists. That's not needed anymore and this list head will only be used
for defer sync. So revert this patch to avoid conflicts with the other
reverts coming after this.

Signed-off-by: Saravana Kannan <saravanak@google.com>
Link: https://lore.kernel.org/r/20201121020232.908850-3-saravanak@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/core.c    | 22 +++++++++++-----------
 include/linux/device.h |  4 ++--
 2 files changed, 13 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/core.c b/drivers/base/core.c
index 58c7d17820a7..fc4b0bc59935 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -959,11 +959,11 @@ static void __device_links_queue_sync_state(struct device *dev,
 	 */
 	dev->state_synced = true;
 
-	if (WARN_ON(!list_empty(&dev->links.defer_hook)))
+	if (WARN_ON(!list_empty(&dev->links.defer_sync)))
 		return;
 
 	get_device(dev);
-	list_add_tail(&dev->links.defer_hook, list);
+	list_add_tail(&dev->links.defer_sync, list);
 }
 
 /**
@@ -981,8 +981,8 @@ static void device_links_flush_sync_list(struct list_head *list,
 {
 	struct device *dev, *tmp;
 
-	list_for_each_entry_safe(dev, tmp, list, links.defer_hook) {
-		list_del_init(&dev->links.defer_hook);
+	list_for_each_entry_safe(dev, tmp, list, links.defer_sync) {
+		list_del_init(&dev->links.defer_sync);
 
 		if (dev != dont_lock_dev)
 			device_lock(dev);
@@ -1020,12 +1020,12 @@ void device_links_supplier_sync_state_resume(void)
 	if (defer_sync_state_count)
 		goto out;
 
-	list_for_each_entry_safe(dev, tmp, &deferred_sync, links.defer_hook) {
+	list_for_each_entry_safe(dev, tmp, &deferred_sync, links.defer_sync) {
 		/*
 		 * Delete from deferred_sync list before queuing it to
-		 * sync_list because defer_hook is used for both lists.
+		 * sync_list because defer_sync is used for both lists.
 		 */
-		list_del_init(&dev->links.defer_hook);
+		list_del_init(&dev->links.defer_sync);
 		__device_links_queue_sync_state(dev, &sync_list);
 	}
 out:
@@ -1043,8 +1043,8 @@ late_initcall(sync_state_resume_initcall);
 
 static void __device_links_supplier_defer_sync(struct device *sup)
 {
-	if (list_empty(&sup->links.defer_hook) && dev_has_sync_state(sup))
-		list_add_tail(&sup->links.defer_hook, &deferred_sync);
+	if (list_empty(&sup->links.defer_sync) && dev_has_sync_state(sup))
+		list_add_tail(&sup->links.defer_sync, &deferred_sync);
 }
 
 static void device_link_drop_managed(struct device_link *link)
@@ -1272,7 +1272,7 @@ void device_links_driver_cleanup(struct device *dev)
 		WRITE_ONCE(link->status, DL_STATE_DORMANT);
 	}
 
-	list_del_init(&dev->links.defer_hook);
+	list_del_init(&dev->links.defer_sync);
 	__device_links_no_driver(dev);
 
 	device_links_write_unlock();
@@ -2405,7 +2405,7 @@ void device_initialize(struct device *dev)
 	INIT_LIST_HEAD(&dev->links.consumers);
 	INIT_LIST_HEAD(&dev->links.suppliers);
 	INIT_LIST_HEAD(&dev->links.needs_suppliers);
-	INIT_LIST_HEAD(&dev->links.defer_hook);
+	INIT_LIST_HEAD(&dev->links.defer_sync);
 	dev->links.status = DL_DEV_NO_DRIVER;
 }
 EXPORT_SYMBOL_GPL(device_initialize);
diff --git a/include/linux/device.h b/include/linux/device.h
index da00f8e449bb..1e771ea4dca6 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -352,7 +352,7 @@ enum dl_dev_state {
  * @suppliers: List of links to supplier devices.
  * @consumers: List of links to consumer devices.
  * @needs_suppliers: Hook to global list of devices waiting for suppliers.
- * @defer_hook: Hook to global list of devices that have deferred sync_state.
+ * @defer_sync: Hook to global list of devices that have deferred sync_state.
  * @need_for_probe: If needs_suppliers is on a list, this indicates if the
  *		    suppliers are needed for probe or not.
  * @status: Driver status information.
@@ -361,7 +361,7 @@ struct dev_links_info {
 	struct list_head suppliers;
 	struct list_head consumers;
 	struct list_head needs_suppliers;
-	struct list_head defer_hook;
+	struct list_head defer_sync;
 	bool need_for_probe;
 	enum dl_dev_state status;
 };
-- 
cgit v1.2.3


From c84b90909e475a2eb4934b4d92fdd10e73e75805 Mon Sep 17 00:00:00 2001
From: Saravana Kannan <saravanak@google.com>
Date: Fri, 20 Nov 2020 18:02:21 -0800
Subject: Revert "driver core: fw_devlink: Add support for batching fwnode
 parsing"

This reverts commit 716a7a25969003d82ab738179c3f1068a120ed11.

The fw_devlink_pause/resume() APIs added by the commit being reverted
were a first cut attempt at optimizing boot time. But these APIs don't
fully solve the problem and are very fragile (can only be used for the
top level devices being added). This series replaces them with a much
better optimization that works for all device additions and also has the
benefit of reducing the complexity of the firmware (DT, EFI) specific
code and abstracting out common code to driver core.

Signed-off-by: Saravana Kannan <saravanak@google.com>
Link: https://lore.kernel.org/r/20201121020232.908850-7-saravanak@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/base.h    |   1 -
 drivers/base/core.c    | 116 +++----------------------------------------------
 drivers/base/dd.c      |   8 ----
 include/linux/fwnode.h |   2 -
 4 files changed, 7 insertions(+), 120 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/base.h b/drivers/base/base.h
index c3562adf4789..91cfb8405abd 100644
--- a/drivers/base/base.h
+++ b/drivers/base/base.h
@@ -156,7 +156,6 @@ extern char *make_class_name(const char *name, struct kobject *kobj);
 extern int devres_release_all(struct device *dev);
 extern void device_block_probing(void);
 extern void device_unblock_probing(void);
-extern void driver_deferred_probe_force_trigger(void);
 
 /* /sys/devices directory */
 extern struct kset *devices_kset;
diff --git a/drivers/base/core.c b/drivers/base/core.c
index b1189697c29b..670aa452bfe7 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -50,9 +50,6 @@ static LIST_HEAD(wait_for_suppliers);
 static DEFINE_MUTEX(wfs_lock);
 static LIST_HEAD(deferred_sync);
 static unsigned int defer_sync_state_count = 1;
-static unsigned int defer_fw_devlink_count;
-static DEFINE_MUTEX(defer_fw_devlink_lock);
-static bool fw_devlink_is_permissive(void);
 
 #ifdef CONFIG_SRCU
 static DEFINE_MUTEX(device_links_lock);
@@ -758,7 +755,7 @@ static void device_link_add_missing_supplier_links(void)
 		int ret = fwnode_call_int_op(dev->fwnode, add_links, dev);
 		if (!ret)
 			list_del_init(&dev->links.needs_suppliers);
-		else if (ret != -ENODEV || fw_devlink_is_permissive())
+		else if (ret != -ENODEV)
 			dev->links.need_for_probe = false;
 	}
 	mutex_unlock(&wfs_lock);
@@ -1440,116 +1437,17 @@ static void fw_devlink_link_device(struct device *dev)
 {
 	int fw_ret;
 
-	if (!fw_devlink_flags)
-		return;
-
-	mutex_lock(&defer_fw_devlink_lock);
-	if (!defer_fw_devlink_count)
-		device_link_add_missing_supplier_links();
-
-	/*
-	 * The device's fwnode not having add_links() doesn't affect if other
-	 * consumers can find this device as a supplier.  So, this check is
-	 * intentionally placed after device_link_add_missing_supplier_links().
-	 */
-	if (!fwnode_has_op(dev->fwnode, add_links))
-		goto out;
+	device_link_add_missing_supplier_links();
 
-	/*
-	 * If fw_devlink is being deferred, assume all devices have mandatory
-	 * suppliers they need to link to later. Then, when the fw_devlink is
-	 * resumed, all these devices will get a chance to try and link to any
-	 * suppliers they have.
-	 */
-	if (!defer_fw_devlink_count) {
+	if (fw_devlink_flags && fwnode_has_op(dev->fwnode, add_links)) {
 		fw_ret = fwnode_call_int_op(dev->fwnode, add_links, dev);
-		if (fw_ret == -ENODEV && fw_devlink_is_permissive())
-			fw_ret = -EAGAIN;
-	} else {
-		fw_ret = -ENODEV;
+		if (fw_ret == -ENODEV && !fw_devlink_is_permissive())
+			device_link_wait_for_mandatory_supplier(dev);
+		else if (fw_ret)
+			device_link_wait_for_optional_supplier(dev);
 	}
-
-	if (fw_ret == -ENODEV)
-		device_link_wait_for_mandatory_supplier(dev);
-	else if (fw_ret)
-		device_link_wait_for_optional_supplier(dev);
-
-out:
-	mutex_unlock(&defer_fw_devlink_lock);
 }
 
-/**
- * fw_devlink_pause - Pause parsing of fwnode to create device links
- *
- * Calling this function defers any fwnode parsing to create device links until
- * fw_devlink_resume() is called. Both these functions are ref counted and the
- * caller needs to match the calls.
- *
- * While fw_devlink is paused:
- * - Any device that is added won't have its fwnode parsed to create device
- *   links.
- * - The probe of the device will also be deferred during this period.
- * - Any devices that were already added, but waiting for suppliers won't be
- *   able to link to newly added devices.
- *
- * Once fw_devlink_resume():
- * - All the fwnodes that was not parsed will be parsed.
- * - All the devices that were deferred probing will be reattempted if they
- *   aren't waiting for any more suppliers.
- *
- * This pair of functions, is mainly meant to optimize the parsing of fwnodes
- * when a lot of devices that need to link to each other are added in a short
- * interval of time. For example, adding all the top level devices in a system.
- *
- * For example, if N devices are added and:
- * - All the consumers are added before their suppliers
- * - All the suppliers of the N devices are part of the N devices
- *
- * Then:
- *
- * - With the use of fw_devlink_pause() and fw_devlink_resume(), each device
- *   will only need one parsing of its fwnode because it is guaranteed to find
- *   all the supplier devices already registered and ready to link to. It won't
- *   have to do another pass later to find one or more suppliers it couldn't
- *   find in the first parse of the fwnode. So, we'll only need O(N) fwnode
- *   parses.
- *
- * - Without the use of fw_devlink_pause() and fw_devlink_resume(), we would
- *   end up doing O(N^2) parses of fwnodes because every device that's added is
- *   guaranteed to trigger a parse of the fwnode of every device added before
- *   it. This O(N^2) parse is made worse by the fact that when a fwnode of a
- *   device is parsed, all it descendant devices might need to have their
- *   fwnodes parsed too (even if the devices themselves aren't added).
- */
-void fw_devlink_pause(void)
-{
-	mutex_lock(&defer_fw_devlink_lock);
-	defer_fw_devlink_count++;
-	mutex_unlock(&defer_fw_devlink_lock);
-}
-
-/** fw_devlink_resume - Resume parsing of fwnode to create device links
- *
- * This function is used in conjunction with fw_devlink_pause() and is ref
- * counted. See documentation for fw_devlink_pause() for more details.
- */
-void fw_devlink_resume(void)
-{
-	mutex_lock(&defer_fw_devlink_lock);
-	if (!defer_fw_devlink_count) {
-		WARN(true, "Unmatched fw_devlink pause/resume!");
-		goto out;
-	}
-
-	defer_fw_devlink_count--;
-	if (defer_fw_devlink_count)
-		goto out;
-
-	device_link_add_missing_supplier_links();
-	driver_deferred_probe_force_trigger();
-out:
-	mutex_unlock(&defer_fw_devlink_lock);
-}
 /* Device links support end. */
 
 int (*platform_notify)(struct device *dev) = NULL;
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index b4be35fa7fda..148e81969e04 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -163,14 +163,6 @@ static bool driver_deferred_probe_enable = false;
  * again.
  */
 static void driver_deferred_probe_trigger(void)
-{
-	if (!driver_deferred_probe_enable)
-		return;
-
-	driver_deferred_probe_force_trigger();
-}
-
-void driver_deferred_probe_force_trigger(void)
 {
 	if (!driver_deferred_probe_enable)
 		return;
diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h
index 9506f8ec0974..e0abafbb17f8 100644
--- a/include/linux/fwnode.h
+++ b/include/linux/fwnode.h
@@ -171,7 +171,5 @@ struct fwnode_operations {
 #define get_dev_from_fwnode(fwnode)	get_device((fwnode)->dev)
 
 extern u32 fw_devlink_get_flags(void);
-void fw_devlink_pause(void);
-void fw_devlink_resume(void);
 
 #endif
-- 
cgit v1.2.3


From 01bb86b380a306bd937c96da36f66429f3362137 Mon Sep 17 00:00:00 2001
From: Saravana Kannan <saravanak@google.com>
Date: Fri, 20 Nov 2020 18:02:22 -0800
Subject: driver core: Add fwnode_init()

There are multiple locations in the kernel where a struct fwnode_handle
is initialized. Add fwnode_init() so that we have one way of
initializing a fwnode_handle.

Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Saravana Kannan <saravanak@google.com>
Link: https://lore.kernel.org/r/20201121020232.908850-8-saravanak@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/acpi/property.c         | 2 +-
 drivers/acpi/scan.c             | 2 +-
 drivers/base/swnode.c           | 2 +-
 drivers/firmware/efi/efi-init.c | 8 ++++----
 include/linux/fwnode.h          | 6 ++++++
 include/linux/of.h              | 2 +-
 kernel/irq/irqdomain.c          | 2 +-
 7 files changed, 15 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index d04de10a63e4..24e87b630573 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -76,7 +76,7 @@ static bool acpi_nondev_subnode_extract(const union acpi_object *desc,
 		return false;
 
 	dn->name = link->package.elements[0].string.pointer;
-	dn->fwnode.ops = &acpi_data_fwnode_ops;
+	fwnode_init(&dn->fwnode, &acpi_data_fwnode_ops);
 	dn->parent = parent;
 	INIT_LIST_HEAD(&dn->data.properties);
 	INIT_LIST_HEAD(&dn->data.subnodes);
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index a896e5e87c93..0ac19f9274b8 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1589,7 +1589,7 @@ void acpi_init_device_object(struct acpi_device *device, acpi_handle handle,
 	device->device_type = type;
 	device->handle = handle;
 	device->parent = acpi_bus_get_parent(handle);
-	device->fwnode.ops = &acpi_device_fwnode_ops;
+	fwnode_init(&device->fwnode, &acpi_device_fwnode_ops);
 	acpi_set_device_status(device, sta);
 	acpi_device_get_busid(device);
 	acpi_set_pnp_ids(handle, &device->pnp, type);
diff --git a/drivers/base/swnode.c b/drivers/base/swnode.c
index 010828fc785b..4a4b2008fbc2 100644
--- a/drivers/base/swnode.c
+++ b/drivers/base/swnode.c
@@ -653,7 +653,7 @@ swnode_register(const struct software_node *node, struct swnode *parent,
 	swnode->parent = parent;
 	swnode->allocated = allocated;
 	swnode->kobj.kset = swnode_kset;
-	swnode->fwnode.ops = &software_node_ops;
+	fwnode_init(&swnode->fwnode, &software_node_ops);
 
 	ida_init(&swnode->child_ids);
 	INIT_LIST_HEAD(&swnode->entry);
diff --git a/drivers/firmware/efi/efi-init.c b/drivers/firmware/efi/efi-init.c
index f55a92ff12c0..b148f1459fb3 100644
--- a/drivers/firmware/efi/efi-init.c
+++ b/drivers/firmware/efi/efi-init.c
@@ -359,9 +359,7 @@ static const struct fwnode_operations efifb_fwnode_ops = {
 	.add_links = efifb_add_links,
 };
 
-static struct fwnode_handle efifb_fwnode = {
-	.ops = &efifb_fwnode_ops,
-};
+static struct fwnode_handle efifb_fwnode;
 
 static int __init register_gop_device(void)
 {
@@ -375,8 +373,10 @@ static int __init register_gop_device(void)
 	if (!pd)
 		return -ENOMEM;
 
-	if (IS_ENABLED(CONFIG_PCI))
+	if (IS_ENABLED(CONFIG_PCI)) {
+		fwnode_init(&efifb_fwnode, &efifb_fwnode_ops);
 		pd->dev.fwnode = &efifb_fwnode;
+	}
 
 	err = platform_device_add_data(pd, &screen_info, sizeof(screen_info));
 	if (err)
diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h
index e0abafbb17f8..5589799708b5 100644
--- a/include/linux/fwnode.h
+++ b/include/linux/fwnode.h
@@ -170,6 +170,12 @@ struct fwnode_operations {
 	} while (false)
 #define get_dev_from_fwnode(fwnode)	get_device((fwnode)->dev)
 
+static inline void fwnode_init(struct fwnode_handle *fwnode,
+			       const struct fwnode_operations *ops)
+{
+	fwnode->ops = ops;
+}
+
 extern u32 fw_devlink_get_flags(void);
 
 #endif
diff --git a/include/linux/of.h b/include/linux/of.h
index af655d264f10..df71a3a1bb8d 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -108,7 +108,7 @@ static inline void of_node_init(struct device_node *node)
 #if defined(CONFIG_OF_KOBJ)
 	kobject_init(&node->kobj, &of_node_ktype);
 #endif
-	node->fwnode.ops = &of_fwnode_ops;
+	fwnode_init(&node->fwnode, &of_fwnode_ops);
 }
 
 #if defined(CONFIG_OF_KOBJ)
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index cf8b374b892d..06fce7e39033 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -91,7 +91,7 @@ struct fwnode_handle *__irq_domain_alloc_fwnode(unsigned int type, int id,
 	fwid->type = type;
 	fwid->name = n;
 	fwid->pa = pa;
-	fwid->fwnode.ops = &irqchip_fwnode_ops;
+	fwnode_init(&fwid->fwnode, &irqchip_fwnode_ops);
 	return &fwid->fwnode;
 }
 EXPORT_SYMBOL_GPL(__irq_domain_alloc_fwnode);
-- 
cgit v1.2.3


From 7b337cb3ebde384cba7405b61dfb84200bf623bf Mon Sep 17 00:00:00 2001
From: Saravana Kannan <saravanak@google.com>
Date: Fri, 20 Nov 2020 18:02:23 -0800
Subject: driver core: Add fwnode link support

Add support for creating supplier-consumer links between fwnodes.  It is
intended for internal use the driver core and generic firmware support
code (eg. Device Tree, ACPI), so it is simple by design and the API
provided is limited.

Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Saravana Kannan <saravanak@google.com>
Link: https://lore.kernel.org/r/20201121020232.908850-9-saravanak@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/core.c    | 98 ++++++++++++++++++++++++++++++++++++++++++++++++++
 drivers/of/dynamic.c   |  1 +
 include/linux/fwnode.h | 14 ++++++++
 3 files changed, 113 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/base/core.c b/drivers/base/core.c
index 670aa452bfe7..972d42dedfc8 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -50,6 +50,104 @@ static LIST_HEAD(wait_for_suppliers);
 static DEFINE_MUTEX(wfs_lock);
 static LIST_HEAD(deferred_sync);
 static unsigned int defer_sync_state_count = 1;
+static DEFINE_MUTEX(fwnode_link_lock);
+
+/**
+ * fwnode_link_add - Create a link between two fwnode_handles.
+ * @con: Consumer end of the link.
+ * @sup: Supplier end of the link.
+ *
+ * Create a fwnode link between fwnode handles @con and @sup. The fwnode link
+ * represents the detail that the firmware lists @sup fwnode as supplying a
+ * resource to @con.
+ *
+ * The driver core will use the fwnode link to create a device link between the
+ * two device objects corresponding to @con and @sup when they are created. The
+ * driver core will automatically delete the fwnode link between @con and @sup
+ * after doing that.
+ *
+ * Attempts to create duplicate links between the same pair of fwnode handles
+ * are ignored and there is no reference counting.
+ */
+int fwnode_link_add(struct fwnode_handle *con, struct fwnode_handle *sup)
+{
+	struct fwnode_link *link;
+	int ret = 0;
+
+	mutex_lock(&fwnode_link_lock);
+
+	list_for_each_entry(link, &sup->consumers, s_hook)
+		if (link->consumer == con)
+			goto out;
+
+	link = kzalloc(sizeof(*link), GFP_KERNEL);
+	if (!link) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	link->supplier = sup;
+	INIT_LIST_HEAD(&link->s_hook);
+	link->consumer = con;
+	INIT_LIST_HEAD(&link->c_hook);
+
+	list_add(&link->s_hook, &sup->consumers);
+	list_add(&link->c_hook, &con->suppliers);
+out:
+	mutex_unlock(&fwnode_link_lock);
+
+	return ret;
+}
+
+/**
+ * fwnode_links_purge_suppliers - Delete all supplier links of fwnode_handle.
+ * @fwnode: fwnode whose supplier links need to be deleted
+ *
+ * Deletes all supplier links connecting directly to @fwnode.
+ */
+static void fwnode_links_purge_suppliers(struct fwnode_handle *fwnode)
+{
+	struct fwnode_link *link, *tmp;
+
+	mutex_lock(&fwnode_link_lock);
+	list_for_each_entry_safe(link, tmp, &fwnode->suppliers, c_hook) {
+		list_del(&link->s_hook);
+		list_del(&link->c_hook);
+		kfree(link);
+	}
+	mutex_unlock(&fwnode_link_lock);
+}
+
+/**
+ * fwnode_links_purge_consumers - Delete all consumer links of fwnode_handle.
+ * @fwnode: fwnode whose consumer links need to be deleted
+ *
+ * Deletes all consumer links connecting directly to @fwnode.
+ */
+static void fwnode_links_purge_consumers(struct fwnode_handle *fwnode)
+{
+	struct fwnode_link *link, *tmp;
+
+	mutex_lock(&fwnode_link_lock);
+	list_for_each_entry_safe(link, tmp, &fwnode->consumers, s_hook) {
+		list_del(&link->s_hook);
+		list_del(&link->c_hook);
+		kfree(link);
+	}
+	mutex_unlock(&fwnode_link_lock);
+}
+
+/**
+ * fwnode_links_purge - Delete all links connected to a fwnode_handle.
+ * @fwnode: fwnode whose links needs to be deleted
+ *
+ * Deletes all links connecting directly to a fwnode.
+ */
+void fwnode_links_purge(struct fwnode_handle *fwnode)
+{
+	fwnode_links_purge_suppliers(fwnode);
+	fwnode_links_purge_consumers(fwnode);
+}
 
 #ifdef CONFIG_SRCU
 static DEFINE_MUTEX(device_links_lock);
diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c
index fe64430b438a..9a824decf61f 100644
--- a/drivers/of/dynamic.c
+++ b/drivers/of/dynamic.c
@@ -356,6 +356,7 @@ void of_node_release(struct kobject *kobj)
 
 	property_list_free(node->properties);
 	property_list_free(node->deadprops);
+	fwnode_links_purge(of_fwnode_handle(node));
 
 	kfree(node->full_name);
 	kfree(node->data);
diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h
index 5589799708b5..b88365187347 100644
--- a/include/linux/fwnode.h
+++ b/include/linux/fwnode.h
@@ -10,6 +10,7 @@
 #define _LINUX_FWNODE_H_
 
 #include <linux/types.h>
+#include <linux/list.h>
 
 struct fwnode_operations;
 struct device;
@@ -18,6 +19,15 @@ struct fwnode_handle {
 	struct fwnode_handle *secondary;
 	const struct fwnode_operations *ops;
 	struct device *dev;
+	struct list_head suppliers;
+	struct list_head consumers;
+};
+
+struct fwnode_link {
+	struct fwnode_handle *supplier;
+	struct list_head s_hook;
+	struct fwnode_handle *consumer;
+	struct list_head c_hook;
 };
 
 /**
@@ -174,8 +184,12 @@ static inline void fwnode_init(struct fwnode_handle *fwnode,
 			       const struct fwnode_operations *ops)
 {
 	fwnode->ops = ops;
+	INIT_LIST_HEAD(&fwnode->consumers);
+	INIT_LIST_HEAD(&fwnode->suppliers);
 }
 
 extern u32 fw_devlink_get_flags(void);
+int fwnode_link_add(struct fwnode_handle *con, struct fwnode_handle *sup);
+void fwnode_links_purge(struct fwnode_handle *fwnode);
 
 #endif
-- 
cgit v1.2.3


From b5d3e2fbcb10957521af14c4256cd0e5f68b9234 Mon Sep 17 00:00:00 2001
From: Saravana Kannan <saravanak@google.com>
Date: Fri, 20 Nov 2020 18:02:25 -0800
Subject: device property: Add fwnode_is_ancestor_of() and
 fwnode_get_next_parent_dev()

Add fwnode_is_ancestor_of() helper function to check if a fwnode is an
ancestor of another fwnode.

Add fwnode_get_next_parent_dev() helper function that take as input a
fwnode and finds the closest ancestor fwnode that has a corresponding
struct device and returns that struct device.

Signed-off-by: Saravana Kannan <saravanak@google.com>
Link: https://lore.kernel.org/r/20201121020232.908850-11-saravanak@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/property.c  | 52 ++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/property.h |  3 +++
 2 files changed, 55 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/base/property.c b/drivers/base/property.c
index 4c43d30145c6..35b95c6ac0c6 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -614,6 +614,31 @@ struct fwnode_handle *fwnode_get_next_parent(struct fwnode_handle *fwnode)
 }
 EXPORT_SYMBOL_GPL(fwnode_get_next_parent);
 
+/**
+ * fwnode_get_next_parent_dev - Find device of closest ancestor fwnode
+ * @fwnode: firmware node
+ *
+ * Given a firmware node (@fwnode), this function finds its closest ancestor
+ * firmware node that has a corresponding struct device and returns that struct
+ * device.
+ *
+ * The caller of this function is expected to call put_device() on the returned
+ * device when they are done.
+ */
+struct device *fwnode_get_next_parent_dev(struct fwnode_handle *fwnode)
+{
+	struct device *dev = NULL;
+
+	fwnode_handle_get(fwnode);
+	do {
+		fwnode = fwnode_get_next_parent(fwnode);
+		if (fwnode)
+			dev = get_dev_from_fwnode(fwnode);
+	} while (fwnode && !dev);
+	fwnode_handle_put(fwnode);
+	return dev;
+}
+
 /**
  * fwnode_count_parents - Return the number of parents a node has
  * @fwnode: The node the parents of which are to be counted
@@ -660,6 +685,33 @@ struct fwnode_handle *fwnode_get_nth_parent(struct fwnode_handle *fwnode,
 }
 EXPORT_SYMBOL_GPL(fwnode_get_nth_parent);
 
+/**
+ * fwnode_is_ancestor_of - Test if @test_ancestor is ancestor of @test_child
+ * @test_ancestor: Firmware which is tested for being an ancestor
+ * @test_child: Firmware which is tested for being the child
+ *
+ * A node is considered an ancestor of itself too.
+ *
+ * Returns true if @test_ancestor is an ancestor of @test_child.
+ * Otherwise, returns false.
+ */
+bool fwnode_is_ancestor_of(struct fwnode_handle *test_ancestor,
+				  struct fwnode_handle *test_child)
+{
+	if (!test_ancestor)
+		return false;
+
+	fwnode_handle_get(test_child);
+	while (test_child) {
+		if (test_child == test_ancestor) {
+			fwnode_handle_put(test_child);
+			return true;
+		}
+		test_child = fwnode_get_next_parent(test_child);
+	}
+	return false;
+}
+
 /**
  * fwnode_get_next_child_node - Return the next child node handle for a node
  * @fwnode: Firmware node to find the next child node for.
diff --git a/include/linux/property.h b/include/linux/property.h
index 2d4542629d80..0a9001fe7aea 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -85,9 +85,12 @@ const char *fwnode_get_name_prefix(const struct fwnode_handle *fwnode);
 struct fwnode_handle *fwnode_get_parent(const struct fwnode_handle *fwnode);
 struct fwnode_handle *fwnode_get_next_parent(
 	struct fwnode_handle *fwnode);
+struct device *fwnode_get_next_parent_dev(struct fwnode_handle *fwnode);
 unsigned int fwnode_count_parents(const struct fwnode_handle *fwn);
 struct fwnode_handle *fwnode_get_nth_parent(struct fwnode_handle *fwn,
 					    unsigned int depth);
+bool fwnode_is_ancestor_of(struct fwnode_handle *test_ancestor,
+				  struct fwnode_handle *test_child);
 struct fwnode_handle *fwnode_get_next_child_node(
 	const struct fwnode_handle *fwnode, struct fwnode_handle *child);
 struct fwnode_handle *fwnode_get_next_available_child_node(
-- 
cgit v1.2.3


From 04f63c213b671d89db35f4239f57fa1edeb736a8 Mon Sep 17 00:00:00 2001
From: Saravana Kannan <saravanak@google.com>
Date: Fri, 20 Nov 2020 18:02:26 -0800
Subject: driver core: Redefine the meaning of fwnode_operations.add_links()

Change the meaning of fwnode_operations.add_links() to just create
fwnode links by parsing the properties of a given fwnode.

This patch doesn't actually make any code changes. To keeps things more
digestable, the actual functional changes come in later patches in this
series.

Signed-off-by: Saravana Kannan <saravanak@google.com>
Link: https://lore.kernel.org/r/20201121020232.908850-12-saravanak@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/efi/efi-init.c |  2 +-
 include/linux/fwnode.h          | 42 +++--------------------------------------
 2 files changed, 4 insertions(+), 40 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/efi/efi-init.c b/drivers/firmware/efi/efi-init.c
index b148f1459fb3..65bb97c391b0 100644
--- a/drivers/firmware/efi/efi-init.c
+++ b/drivers/firmware/efi/efi-init.c
@@ -316,7 +316,7 @@ static struct device_node *find_pci_overlap_node(void)
  * resource reservation conflict on the memory window that the efifb
  * framebuffer steals from the PCIe host bridge.
  */
-static int efifb_add_links(const struct fwnode_handle *fwnode,
+static int efifb_add_links(struct fwnode_handle *fwnode,
 			   struct device *dev)
 {
 	struct device_node *sup_np;
diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h
index b88365187347..942a6bb18201 100644
--- a/include/linux/fwnode.h
+++ b/include/linux/fwnode.h
@@ -78,44 +78,8 @@ struct fwnode_reference_args {
  *			       endpoint node.
  * @graph_get_port_parent: Return the parent node of a port node.
  * @graph_parse_endpoint: Parse endpoint for port and endpoint id.
- * @add_links:	Called after the device corresponding to the fwnode is added
- *		using device_add(). The function is expected to create device
- *		links to all the suppliers of the device that are available at
- *		the time this function is called.  The function must NOT stop
- *		at the first failed device link if other unlinked supplier
- *		devices are present in the system.  This is necessary for the
- *		driver/bus sync_state() callbacks to work correctly.
- *
- *		For example, say Device-C depends on suppliers Device-S1 and
- *		Device-S2 and the dependency is listed in that order in the
- *		firmware.  Say, S1 gets populated from the firmware after
- *		late_initcall_sync().  Say S2 is populated and probed way
- *		before that in device_initcall(). When C is populated, if this
- *		add_links() function doesn't continue past a "failed linking to
- *		S1" and continue linking C to S2, then S2 will get a
- *		sync_state() callback before C is probed. This is because from
- *		the perspective of S2, C was never a consumer when its
- *		sync_state() evaluation is done. To avoid this, the add_links()
- *		function has to go through all available suppliers of the
- *		device (that corresponds to this fwnode) and link to them
- *		before returning.
- *
- *		If some suppliers are not yet available (indicated by an error
- *		return value), this function will be called again when other
- *		devices are added to allow creating device links to any newly
- *		available suppliers.
- *
- *		Return 0 if device links have been successfully created to all
- *		the known suppliers of this device or if the supplier
- *		information is not known.
- *
- *		Return -ENODEV if the suppliers needed for probing this device
- *		have not been registered yet (because device links can only be
- *		created to devices registered with the driver core).
- *
- *		Return -EAGAIN if some of the suppliers of this device have not
- *		been registered yet, but none of those suppliers are necessary
- *		for probing the device.
+ * @add_links:	Create fwnode links to all the suppliers of the fwnode. Return
+ *		zero on success, a negative error code otherwise.
  */
 struct fwnode_operations {
 	struct fwnode_handle *(*get)(struct fwnode_handle *fwnode);
@@ -155,7 +119,7 @@ struct fwnode_operations {
 	(*graph_get_port_parent)(struct fwnode_handle *fwnode);
 	int (*graph_parse_endpoint)(const struct fwnode_handle *fwnode,
 				    struct fwnode_endpoint *endpoint);
-	int (*add_links)(const struct fwnode_handle *fwnode,
+	int (*add_links)(struct fwnode_handle *fwnode,
 			 struct device *dev);
 };
 
-- 
cgit v1.2.3


From c2c724c868c42c5166bf7aa644dd0a0c8d30b47a Mon Sep 17 00:00:00 2001
From: Saravana Kannan <saravanak@google.com>
Date: Fri, 20 Nov 2020 18:02:27 -0800
Subject: driver core: Add fw_devlink_parse_fwtree()

This function is a wrapper around fwnode_operations.add_links().

This function parses each node in a fwnode tree and create fwnode links
for each of those nodes. The information for creating the fwnode links
(the supplier and consumer fwnode) is obtained by parsing the properties
in each of the fwnodes.

This function also ensures that no fwnode is parsed more than once by
marking the fwnodes as parsed.

Signed-off-by: Saravana Kannan <saravanak@google.com>
Link: https://lore.kernel.org/r/20201121020232.908850-13-saravanak@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/core.c    | 19 +++++++++++++++++++
 include/linux/fwnode.h |  8 ++++++++
 2 files changed, 27 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/base/core.c b/drivers/base/core.c
index edde79fc3d33..92a2dc355d13 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -1542,6 +1542,25 @@ static bool fw_devlink_is_permissive(void)
 	return fw_devlink_flags == DL_FLAG_SYNC_STATE_ONLY;
 }
 
+static void fw_devlink_parse_fwnode(struct fwnode_handle *fwnode)
+{
+	if (fwnode->flags & FWNODE_FLAG_LINKS_ADDED)
+		return;
+
+	fwnode_call_int_op(fwnode, add_links, NULL);
+	fwnode->flags |= FWNODE_FLAG_LINKS_ADDED;
+}
+
+static void fw_devlink_parse_fwtree(struct fwnode_handle *fwnode)
+{
+	struct fwnode_handle *child = NULL;
+
+	fw_devlink_parse_fwnode(fwnode);
+
+	while ((child = fwnode_get_next_available_child_node(fwnode, child)))
+		fw_devlink_parse_fwtree(child);
+}
+
 static void fw_devlink_link_device(struct device *dev)
 {
 	int fw_ret;
diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h
index 942a6bb18201..ffa9129182a6 100644
--- a/include/linux/fwnode.h
+++ b/include/linux/fwnode.h
@@ -15,12 +15,20 @@
 struct fwnode_operations;
 struct device;
 
+/*
+ * fwnode link flags
+ *
+ * LINKS_ADDED: The fwnode has already be parsed to add fwnode links.
+ */
+#define FWNODE_FLAG_LINKS_ADDED		BIT(0)
+
 struct fwnode_handle {
 	struct fwnode_handle *secondary;
 	const struct fwnode_operations *ops;
 	struct device *dev;
 	struct list_head suppliers;
 	struct list_head consumers;
+	u8 flags;
 };
 
 struct fwnode_link {
-- 
cgit v1.2.3


From f9aa460672c9c56896cdc12a521159e3e67000ba Mon Sep 17 00:00:00 2001
From: Saravana Kannan <saravanak@google.com>
Date: Fri, 20 Nov 2020 18:02:31 -0800
Subject: driver core: Refactor fw_devlink feature

The current implementation of fw_devlink is very inefficient because it
tries to get away without creating fwnode links in the name of saving
memory usage. Past attempts to optimize runtime at the cost of memory
usage were blocked with request for data showing that the optimization
made significant improvement for real world scenarios.

We have those scenarios now. There have been several reports of boot
time increase in the order of seconds in this thread [1]. Several OEMs
and SoC manufacturers have also privately reported significant
(350-400ms) increase in boot time due to all the parsing done by
fw_devlink.

So this patch uses all the setup done by the previous patches in this
series to refactor fw_devlink to be more efficient. Most of the code has
been moved out of firmware specific (DT mostly) code into driver core.

This brings the following benefits:
- Instead of parsing the device tree multiple times during bootup,
  fw_devlink parses each fwnode node/property only once and creates
  fwnode links. The rest of the fw_devlink code then just looks at these
  fwnode links to do rest of the work.

- Makes it much easier to debug probe issue due to fw_devlink in the
  future. fw_devlink=on blocks the probing of devices if they depend on
  a device that hasn't been added yet. With this refactor, it'll be very
  easy to tell what that device is because we now have a reference to
  the fwnode of the device.

- Much easier to add fw_devlink support to ACPI and other firmware
  types. A refactor to move the common bits from DT specific code to
  driver core was in my TODO list as a prerequisite to adding ACPI
  support to fw_devlink. This series gets that done.

[1] - https://lore.kernel.org/linux-omap/ea02f57e-871d-cd16-4418-c1da4bbc4696@ti.com/

Tested-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Tested-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Saravana Kannan <saravanak@google.com>
Link: https://lore.kernel.org/r/20201121020232.908850-17-saravanak@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/core.c    | 325 ++++++++++++++++++++++++++++++++++++-------------
 include/linux/device.h |   5 -
 2 files changed, 238 insertions(+), 92 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/core.c b/drivers/base/core.c
index 8a973d9601d3..9edf9084fc98 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -46,8 +46,6 @@ early_param("sysfs.deprecated", sysfs_deprecated_setup);
 #endif
 
 /* Device links support. */
-static LIST_HEAD(wait_for_suppliers);
-static DEFINE_MUTEX(wfs_lock);
 static LIST_HEAD(deferred_sync);
 static unsigned int defer_sync_state_count = 1;
 static DEFINE_MUTEX(fwnode_link_lock);
@@ -803,74 +801,6 @@ out:
 }
 EXPORT_SYMBOL_GPL(device_link_add);
 
-/**
- * device_link_wait_for_supplier - Add device to wait_for_suppliers list
- * @consumer: Consumer device
- *
- * Marks the @consumer device as waiting for suppliers to become available by
- * adding it to the wait_for_suppliers list. The consumer device will never be
- * probed until it's removed from the wait_for_suppliers list.
- *
- * The caller is responsible for adding the links to the supplier devices once
- * they are available and removing the @consumer device from the
- * wait_for_suppliers list once links to all the suppliers have been created.
- *
- * This function is NOT meant to be called from the probe function of the
- * consumer but rather from code that creates/adds the consumer device.
- */
-static void device_link_wait_for_supplier(struct device *consumer,
-					  bool need_for_probe)
-{
-	mutex_lock(&wfs_lock);
-	list_add_tail(&consumer->links.needs_suppliers, &wait_for_suppliers);
-	consumer->links.need_for_probe = need_for_probe;
-	mutex_unlock(&wfs_lock);
-}
-
-static void device_link_wait_for_mandatory_supplier(struct device *consumer)
-{
-	device_link_wait_for_supplier(consumer, true);
-}
-
-static void device_link_wait_for_optional_supplier(struct device *consumer)
-{
-	device_link_wait_for_supplier(consumer, false);
-}
-
-/**
- * device_link_add_missing_supplier_links - Add links from consumer devices to
- *					    supplier devices, leaving any
- *					    consumer with inactive suppliers on
- *					    the wait_for_suppliers list
- *
- * Loops through all consumers waiting on suppliers and tries to add all their
- * supplier links. If that succeeds, the consumer device is removed from
- * wait_for_suppliers list. Otherwise, they are left in the wait_for_suppliers
- * list.  Devices left on the wait_for_suppliers list will not be probed.
- *
- * The fwnode add_links callback is expected to return 0 if it has found and
- * added all the supplier links for the consumer device. It should return an
- * error if it isn't able to do so.
- *
- * The caller of device_link_wait_for_supplier() is expected to call this once
- * it's aware of potential suppliers becoming available.
- */
-static void device_link_add_missing_supplier_links(void)
-{
-	struct device *dev, *tmp;
-
-	mutex_lock(&wfs_lock);
-	list_for_each_entry_safe(dev, tmp, &wait_for_suppliers,
-				 links.needs_suppliers) {
-		int ret = fwnode_call_int_op(dev->fwnode, add_links, dev);
-		if (!ret)
-			list_del_init(&dev->links.needs_suppliers);
-		else if (ret != -ENODEV)
-			dev->links.need_for_probe = false;
-	}
-	mutex_unlock(&wfs_lock);
-}
-
 #ifdef CONFIG_SRCU
 static void __device_link_del(struct kref *kref)
 {
@@ -1195,9 +1125,8 @@ void device_links_driver_bound(struct device *dev)
 	 * the device links it needs to or make new device links as it needs
 	 * them. So, it no longer needs to wait on any suppliers.
 	 */
-	mutex_lock(&wfs_lock);
-	list_del_init(&dev->links.needs_suppliers);
-	mutex_unlock(&wfs_lock);
+	if (dev->fwnode && dev->fwnode->dev == dev)
+		fwnode_links_purge_suppliers(dev->fwnode);
 	device_remove_file(dev, &dev_attr_waiting_for_supplier);
 
 	device_links_write_lock();
@@ -1488,10 +1417,6 @@ static void device_links_purge(struct device *dev)
 	if (dev->class == &devlink_class)
 		return;
 
-	mutex_lock(&wfs_lock);
-	list_del_init(&dev->links.needs_suppliers);
-	mutex_unlock(&wfs_lock);
-
 	/*
 	 * Delete all of the remaining links from this device to any other
 	 * devices (either consumers or suppliers).
@@ -1561,19 +1486,246 @@ static void fw_devlink_parse_fwtree(struct fwnode_handle *fwnode)
 		fw_devlink_parse_fwtree(child);
 }
 
-static void fw_devlink_link_device(struct device *dev)
+/**
+ * fw_devlink_create_devlink - Create a device link from a consumer to fwnode
+ * @con - Consumer device for the device link
+ * @sup_handle - fwnode handle of supplier
+ *
+ * This function will try to create a device link between the consumer device
+ * @con and the supplier device represented by @sup_handle.
+ *
+ * The supplier has to be provided as a fwnode because incorrect cycles in
+ * fwnode links can sometimes cause the supplier device to never be created.
+ * This function detects such cases and returns an error if it cannot create a
+ * device link from the consumer to a missing supplier.
+ *
+ * Returns,
+ * 0 on successfully creating a device link
+ * -EINVAL if the device link cannot be created as expected
+ * -EAGAIN if the device link cannot be created right now, but it may be
+ *  possible to do that in the future
+ */
+static int fw_devlink_create_devlink(struct device *con,
+				     struct fwnode_handle *sup_handle, u32 flags)
+{
+	struct device *sup_dev;
+	int ret = 0;
+
+	sup_dev = get_dev_from_fwnode(sup_handle);
+	if (sup_dev) {
+		/*
+		 * If this fails, it is due to cycles in device links.  Just
+		 * give up on this link and treat it as invalid.
+		 */
+		if (!device_link_add(con, sup_dev, flags))
+			ret = -EINVAL;
+
+		goto out;
+	}
+
+	/*
+	 * DL_FLAG_SYNC_STATE_ONLY doesn't block probing and supports
+	 * cycles. So cycle detection isn't necessary and shouldn't be
+	 * done.
+	 */
+	if (flags & DL_FLAG_SYNC_STATE_ONLY)
+		return -EAGAIN;
+
+	/*
+	 * If we can't find the supplier device from its fwnode, it might be
+	 * due to a cyclic dependency between fwnodes. Some of these cycles can
+	 * be broken by applying logic. Check for these types of cycles and
+	 * break them so that devices in the cycle probe properly.
+	 *
+	 * If the supplier's parent is dependent on the consumer, then
+	 * the consumer-supplier dependency is a false dependency. So,
+	 * treat it as an invalid link.
+	 */
+	sup_dev = fwnode_get_next_parent_dev(sup_handle);
+	if (sup_dev && device_is_dependent(con, sup_dev)) {
+		dev_dbg(con, "Not linking to %pfwP - False link\n",
+			sup_handle);
+		ret = -EINVAL;
+	} else {
+		/*
+		 * Can't check for cycles or no cycles. So let's try
+		 * again later.
+		 */
+		ret = -EAGAIN;
+	}
+
+out:
+	put_device(sup_dev);
+	return ret;
+}
+
+/**
+ * __fw_devlink_link_to_consumers - Create device links to consumers of a device
+ * @dev - Device that needs to be linked to its consumers
+ *
+ * This function looks at all the consumer fwnodes of @dev and creates device
+ * links between the consumer device and @dev (supplier).
+ *
+ * If the consumer device has not been added yet, then this function creates a
+ * SYNC_STATE_ONLY link between @dev (supplier) and the closest ancestor device
+ * of the consumer fwnode. This is necessary to make sure @dev doesn't get a
+ * sync_state() callback before the real consumer device gets to be added and
+ * then probed.
+ *
+ * Once device links are created from the real consumer to @dev (supplier), the
+ * fwnode links are deleted.
+ */
+static void __fw_devlink_link_to_consumers(struct device *dev)
+{
+	struct fwnode_handle *fwnode = dev->fwnode;
+	struct fwnode_link *link, *tmp;
+
+	list_for_each_entry_safe(link, tmp, &fwnode->consumers, s_hook) {
+		u32 dl_flags = fw_devlink_get_flags();
+		struct device *con_dev;
+		bool own_link = true;
+		int ret;
+
+		con_dev = get_dev_from_fwnode(link->consumer);
+		/*
+		 * If consumer device is not available yet, make a "proxy"
+		 * SYNC_STATE_ONLY link from the consumer's parent device to
+		 * the supplier device. This is necessary to make sure the
+		 * supplier doesn't get a sync_state() callback before the real
+		 * consumer can create a device link to the supplier.
+		 *
+		 * This proxy link step is needed to handle the case where the
+		 * consumer's parent device is added before the supplier.
+		 */
+		if (!con_dev) {
+			con_dev = fwnode_get_next_parent_dev(link->consumer);
+			/*
+			 * However, if the consumer's parent device is also the
+			 * parent of the supplier, don't create a
+			 * consumer-supplier link from the parent to its child
+			 * device. Such a dependency is impossible.
+			 */
+			if (con_dev &&
+			    fwnode_is_ancestor_of(con_dev->fwnode, fwnode)) {
+				put_device(con_dev);
+				con_dev = NULL;
+			} else {
+				own_link = false;
+				dl_flags = DL_FLAG_SYNC_STATE_ONLY;
+			}
+		}
+
+		if (!con_dev)
+			continue;
+
+		ret = fw_devlink_create_devlink(con_dev, fwnode, dl_flags);
+		put_device(con_dev);
+		if (!own_link || ret == -EAGAIN)
+			continue;
+
+		list_del(&link->s_hook);
+		list_del(&link->c_hook);
+		kfree(link);
+	}
+}
+
+/**
+ * __fw_devlink_link_to_suppliers - Create device links to suppliers of a device
+ * @dev - The consumer device that needs to be linked to its suppliers
+ * @fwnode - Root of the fwnode tree that is used to create device links
+ *
+ * This function looks at all the supplier fwnodes of fwnode tree rooted at
+ * @fwnode and creates device links between @dev (consumer) and all the
+ * supplier devices of the entire fwnode tree at @fwnode.
+ *
+ * The function creates normal (non-SYNC_STATE_ONLY) device links between @dev
+ * and the real suppliers of @dev. Once these device links are created, the
+ * fwnode links are deleted. When such device links are successfully created,
+ * this function is called recursively on those supplier devices. This is
+ * needed to detect and break some invalid cycles in fwnode links.  See
+ * fw_devlink_create_devlink() for more details.
+ *
+ * In addition, it also looks at all the suppliers of the entire fwnode tree
+ * because some of the child devices of @dev that have not been added yet
+ * (because @dev hasn't probed) might already have their suppliers added to
+ * driver core. So, this function creates SYNC_STATE_ONLY device links between
+ * @dev (consumer) and these suppliers to make sure they don't execute their
+ * sync_state() callbacks before these child devices have a chance to create
+ * their device links. The fwnode links that correspond to the child devices
+ * aren't delete because they are needed later to create the device links
+ * between the real consumer and supplier devices.
+ */
+static void __fw_devlink_link_to_suppliers(struct device *dev,
+					   struct fwnode_handle *fwnode)
 {
-	int fw_ret;
+	bool own_link = (dev->fwnode == fwnode);
+	struct fwnode_link *link, *tmp;
+	struct fwnode_handle *child = NULL;
+	u32 dl_flags;
+
+	if (own_link)
+		dl_flags = fw_devlink_get_flags();
+	else
+		dl_flags = DL_FLAG_SYNC_STATE_ONLY;
 
-	device_link_add_missing_supplier_links();
+	list_for_each_entry_safe(link, tmp, &fwnode->suppliers, c_hook) {
+		int ret;
+		struct device *sup_dev;
+		struct fwnode_handle *sup = link->supplier;
+
+		ret = fw_devlink_create_devlink(dev, sup, dl_flags);
+		if (!own_link || ret == -EAGAIN)
+			continue;
 
-	if (fw_devlink_flags && fwnode_has_op(dev->fwnode, add_links)) {
-		fw_ret = fwnode_call_int_op(dev->fwnode, add_links, dev);
-		if (fw_ret == -ENODEV && !fw_devlink_is_permissive())
-			device_link_wait_for_mandatory_supplier(dev);
-		else if (fw_ret)
-			device_link_wait_for_optional_supplier(dev);
+		list_del(&link->s_hook);
+		list_del(&link->c_hook);
+		kfree(link);
+
+		/* If no device link was created, nothing more to do. */
+		if (ret)
+			continue;
+
+		/*
+		 * If a device link was successfully created to a supplier, we
+		 * now need to try and link the supplier to all its suppliers.
+		 *
+		 * This is needed to detect and delete false dependencies in
+		 * fwnode links that haven't been converted to a device link
+		 * yet. See comments in fw_devlink_create_devlink() for more
+		 * details on the false dependency.
+		 *
+		 * Without deleting these false dependencies, some devices will
+		 * never probe because they'll keep waiting for their false
+		 * dependency fwnode links to be converted to device links.
+		 */
+		sup_dev = get_dev_from_fwnode(sup);
+		__fw_devlink_link_to_suppliers(sup_dev, sup_dev->fwnode);
+		put_device(sup_dev);
 	}
+
+	/*
+	 * Make "proxy" SYNC_STATE_ONLY device links to represent the needs of
+	 * all the descendants. This proxy link step is needed to handle the
+	 * case where the supplier is added before the consumer's parent device
+	 * (@dev).
+	 */
+	while ((child = fwnode_get_next_available_child_node(fwnode, child)))
+		__fw_devlink_link_to_suppliers(dev, child);
+}
+
+static void fw_devlink_link_device(struct device *dev)
+{
+	struct fwnode_handle *fwnode = dev->fwnode;
+
+	if (!fw_devlink_flags)
+		return;
+
+	fw_devlink_parse_fwtree(fwnode);
+
+	mutex_lock(&fwnode_link_lock);
+	__fw_devlink_link_to_consumers(dev);
+	__fw_devlink_link_to_suppliers(dev, fwnode);
+	mutex_unlock(&fwnode_link_lock);
 }
 
 /* Device links support end. */
@@ -2431,7 +2583,6 @@ void device_initialize(struct device *dev)
 #endif
 	INIT_LIST_HEAD(&dev->links.consumers);
 	INIT_LIST_HEAD(&dev->links.suppliers);
-	INIT_LIST_HEAD(&dev->links.needs_suppliers);
 	INIT_LIST_HEAD(&dev->links.defer_sync);
 	dev->links.status = DL_DEV_NO_DRIVER;
 }
diff --git a/include/linux/device.h b/include/linux/device.h
index 1e771ea4dca6..89bb8b84173e 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -351,18 +351,13 @@ enum dl_dev_state {
  * struct dev_links_info - Device data related to device links.
  * @suppliers: List of links to supplier devices.
  * @consumers: List of links to consumer devices.
- * @needs_suppliers: Hook to global list of devices waiting for suppliers.
  * @defer_sync: Hook to global list of devices that have deferred sync_state.
- * @need_for_probe: If needs_suppliers is on a list, this indicates if the
- *		    suppliers are needed for probe or not.
  * @status: Driver status information.
  */
 struct dev_links_info {
 	struct list_head suppliers;
 	struct list_head consumers;
-	struct list_head needs_suppliers;
 	struct list_head defer_sync;
-	bool need_for_probe;
 	enum dl_dev_state status;
 };
 
-- 
cgit v1.2.3


From 2d09e6eb4a6f20273959f4905ccf009da8c64c7a Mon Sep 17 00:00:00 2001
From: Saravana Kannan <saravanak@google.com>
Date: Fri, 20 Nov 2020 18:02:32 -0800
Subject: driver core: Delete pointless parameter in
 fwnode_operations.add_links

The struct device input to add_links() is not used for anything. So
delete it.

Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Saravana Kannan <saravanak@google.com>
Link: https://lore.kernel.org/r/20201121020232.908850-18-saravanak@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/core.c             | 2 +-
 drivers/firmware/efi/efi-init.c | 3 +--
 drivers/of/property.c           | 3 +--
 include/linux/fwnode.h          | 3 +--
 4 files changed, 4 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/core.c b/drivers/base/core.c
index 9edf9084fc98..63edb8bd9d7d 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -1472,7 +1472,7 @@ static void fw_devlink_parse_fwnode(struct fwnode_handle *fwnode)
 	if (fwnode->flags & FWNODE_FLAG_LINKS_ADDED)
 		return;
 
-	fwnode_call_int_op(fwnode, add_links, NULL);
+	fwnode_call_int_op(fwnode, add_links);
 	fwnode->flags |= FWNODE_FLAG_LINKS_ADDED;
 }
 
diff --git a/drivers/firmware/efi/efi-init.c b/drivers/firmware/efi/efi-init.c
index c0c3d4c3837a..a552a08a1741 100644
--- a/drivers/firmware/efi/efi-init.c
+++ b/drivers/firmware/efi/efi-init.c
@@ -316,8 +316,7 @@ static struct device_node *find_pci_overlap_node(void)
  * resource reservation conflict on the memory window that the efifb
  * framebuffer steals from the PCIe host bridge.
  */
-static int efifb_add_links(struct fwnode_handle *fwnode,
-			   struct device *dev)
+static int efifb_add_links(struct fwnode_handle *fwnode)
 {
 	struct device_node *sup_np;
 
diff --git a/drivers/of/property.c b/drivers/of/property.c
index 620d29fdace8..5f9eed79a8aa 100644
--- a/drivers/of/property.c
+++ b/drivers/of/property.c
@@ -1343,8 +1343,7 @@ static int of_link_property(struct device_node *con_np, const char *prop_name)
 	return ret;
 }
 
-static int of_fwnode_add_links(struct fwnode_handle *fwnode,
-			       struct device *dev)
+static int of_fwnode_add_links(struct fwnode_handle *fwnode)
 {
 	struct property *p;
 	struct device_node *con_np = to_of_node(fwnode);
diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h
index ffa9129182a6..fde4ad97564c 100644
--- a/include/linux/fwnode.h
+++ b/include/linux/fwnode.h
@@ -127,8 +127,7 @@ struct fwnode_operations {
 	(*graph_get_port_parent)(struct fwnode_handle *fwnode);
 	int (*graph_parse_endpoint)(const struct fwnode_handle *fwnode,
 				    struct fwnode_endpoint *endpoint);
-	int (*add_links)(struct fwnode_handle *fwnode,
-			 struct device *dev);
+	int (*add_links)(struct fwnode_handle *fwnode);
 };
 
 #define fwnode_has_op(fwnode, op)				\
-- 
cgit v1.2.3


From 30b79eb1f92ed5974885d374a4107c94e2dd3e03 Mon Sep 17 00:00:00 2001
From: Michael Tretter <m.tretter@pengutronix.de>
Date: Mon, 9 Nov 2020 14:48:17 +0100
Subject: soc: xilinx: vcu: use vcu-settings syscon registers

Switch the "logicoreip" registers to the new xlnx,vcu-settings binding
to be able to read the settings if the settings are specified in a
separate device tree node that is shared with other drivers.

If the driver is not able to find a node with the new binding, fall back
to check for the logicore register bank to be backwards compatible.

Signed-off-by: Michael Tretter <m.tretter@pengutronix.de>
Reviewed-by: Hyun Kwon <hyun.kwon@xilinx.com>
Link: https://lore.kernel.org/r/20201109134818.4159342-4-m.tretter@pengutronix.de
Signed-off-by: Michal Simek <michal.simek@xilinx.com>
---
 drivers/soc/xilinx/Kconfig          |  1 +
 drivers/soc/xilinx/xlnx_vcu.c       | 94 ++++++++++++++++++-------------------
 include/linux/mfd/syscon/xlnx-vcu.h | 38 +++++++++++++++
 3 files changed, 86 insertions(+), 47 deletions(-)
 create mode 100644 include/linux/mfd/syscon/xlnx-vcu.h

(limited to 'include/linux')

diff --git a/drivers/soc/xilinx/Kconfig b/drivers/soc/xilinx/Kconfig
index 646512d7276f..0b1708dae361 100644
--- a/drivers/soc/xilinx/Kconfig
+++ b/drivers/soc/xilinx/Kconfig
@@ -4,6 +4,7 @@ menu "Xilinx SoC drivers"
 config XILINX_VCU
 	tristate "Xilinx VCU logicoreIP Init"
 	depends on HAS_IOMEM
+	select REGMAP_MMIO
 	help
 	  Provides the driver to enable and disable the isolation between the
 	  processing system and programmable logic part by using the logicoreIP
diff --git a/drivers/soc/xilinx/xlnx_vcu.c b/drivers/soc/xilinx/xlnx_vcu.c
index dcd8e7824b06..14daad4efc58 100644
--- a/drivers/soc/xilinx/xlnx_vcu.c
+++ b/drivers/soc/xilinx/xlnx_vcu.c
@@ -10,39 +10,12 @@
 #include <linux/device.h>
 #include <linux/errno.h>
 #include <linux/io.h>
+#include <linux/mfd/syscon.h>
+#include <linux/mfd/syscon/xlnx-vcu.h>
 #include <linux/module.h>
 #include <linux/of_platform.h>
 #include <linux/platform_device.h>
-
-/* Address map for different registers implemented in the VCU LogiCORE IP. */
-#define VCU_ECODER_ENABLE		0x00
-#define VCU_DECODER_ENABLE		0x04
-#define VCU_MEMORY_DEPTH		0x08
-#define VCU_ENC_COLOR_DEPTH		0x0c
-#define VCU_ENC_VERTICAL_RANGE		0x10
-#define VCU_ENC_FRAME_SIZE_X		0x14
-#define VCU_ENC_FRAME_SIZE_Y		0x18
-#define VCU_ENC_COLOR_FORMAT		0x1c
-#define VCU_ENC_FPS			0x20
-#define VCU_MCU_CLK			0x24
-#define VCU_CORE_CLK			0x28
-#define VCU_PLL_BYPASS			0x2c
-#define VCU_ENC_CLK			0x30
-#define VCU_PLL_CLK			0x34
-#define VCU_ENC_VIDEO_STANDARD		0x38
-#define VCU_STATUS			0x3c
-#define VCU_AXI_ENC_CLK			0x40
-#define VCU_AXI_DEC_CLK			0x44
-#define VCU_AXI_MCU_CLK			0x48
-#define VCU_DEC_VIDEO_STANDARD		0x4c
-#define VCU_DEC_FRAME_SIZE_X		0x50
-#define VCU_DEC_FRAME_SIZE_Y		0x54
-#define VCU_DEC_FPS			0x58
-#define VCU_BUFFER_B_FRAME		0x5c
-#define VCU_WPP_EN			0x60
-#define VCU_PLL_CLK_DEC			0x64
-#define VCU_GASKET_INIT			0x74
-#define VCU_GASKET_VALUE		0x03
+#include <linux/regmap.h>
 
 /* vcu slcr registers, bitmask and shift */
 #define VCU_PLL_CTRL			0x24
@@ -106,11 +79,20 @@ struct xvcu_device {
 	struct device *dev;
 	struct clk *pll_ref;
 	struct clk *aclk;
-	void __iomem *logicore_reg_ba;
+	struct regmap *logicore_reg_ba;
 	void __iomem *vcu_slcr_ba;
 	u32 coreclk;
 };
 
+static struct regmap_config vcu_settings_regmap_config = {
+	.name = "regmap",
+	.reg_bits = 32,
+	.val_bits = 32,
+	.reg_stride = 4,
+	.max_register = 0xfff,
+	.cache_type = REGCACHE_NONE,
+};
+
 /**
  * struct xvcu_pll_cfg - Helper data
  * @fbdiv: The integer portion of the feedback divider to the PLL
@@ -300,10 +282,12 @@ static int xvcu_set_vcu_pll_info(struct xvcu_device *xvcu)
 	int ret, i;
 	const struct xvcu_pll_cfg *found = NULL;
 
-	inte = xvcu_read(xvcu->logicore_reg_ba, VCU_PLL_CLK);
-	deci = xvcu_read(xvcu->logicore_reg_ba, VCU_PLL_CLK_DEC);
-	coreclk = xvcu_read(xvcu->logicore_reg_ba, VCU_CORE_CLK) * MHZ;
-	mcuclk = xvcu_read(xvcu->logicore_reg_ba, VCU_MCU_CLK) * MHZ;
+	regmap_read(xvcu->logicore_reg_ba, VCU_PLL_CLK, &inte);
+	regmap_read(xvcu->logicore_reg_ba, VCU_PLL_CLK_DEC, &deci);
+	regmap_read(xvcu->logicore_reg_ba, VCU_CORE_CLK, &coreclk);
+	coreclk *= MHZ;
+	regmap_read(xvcu->logicore_reg_ba, VCU_MCU_CLK, &mcuclk);
+	mcuclk *= MHZ;
 	if (!mcuclk || !coreclk) {
 		dev_err(xvcu->dev, "Invalid mcu and core clock data\n");
 		return -EINVAL;
@@ -498,6 +482,7 @@ static int xvcu_probe(struct platform_device *pdev)
 {
 	struct resource *res;
 	struct xvcu_device *xvcu;
+	void __iomem *regs;
 	int ret;
 
 	xvcu = devm_kzalloc(&pdev->dev, sizeof(*xvcu), GFP_KERNEL);
@@ -518,17 +503,32 @@ static int xvcu_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 
-	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "logicore");
-	if (!res) {
-		dev_err(&pdev->dev, "get logicore memory resource failed.\n");
-		return -ENODEV;
-	}
+	xvcu->logicore_reg_ba =
+		syscon_regmap_lookup_by_compatible("xlnx,vcu-settings");
+	if (IS_ERR(xvcu->logicore_reg_ba)) {
+		dev_info(&pdev->dev,
+			 "could not find xlnx,vcu-settings: trying direct register access\n");
+
+		res = platform_get_resource_byname(pdev,
+						   IORESOURCE_MEM, "logicore");
+		if (!res) {
+			dev_err(&pdev->dev, "get logicore memory resource failed.\n");
+			return -ENODEV;
+		}
 
-	xvcu->logicore_reg_ba = devm_ioremap(&pdev->dev, res->start,
-						     resource_size(res));
-	if (!xvcu->logicore_reg_ba) {
-		dev_err(&pdev->dev, "logicore register mapping failed.\n");
-		return -ENOMEM;
+		regs = devm_ioremap(&pdev->dev, res->start, resource_size(res));
+		if (!regs) {
+			dev_err(&pdev->dev, "logicore register mapping failed.\n");
+			return -ENOMEM;
+		}
+
+		xvcu->logicore_reg_ba =
+			devm_regmap_init_mmio(&pdev->dev, regs,
+					      &vcu_settings_regmap_config);
+		if (IS_ERR(xvcu->logicore_reg_ba)) {
+			dev_err(&pdev->dev, "failed to init regmap\n");
+			return PTR_ERR(xvcu->logicore_reg_ba);
+		}
 	}
 
 	xvcu->aclk = devm_clk_get(&pdev->dev, "aclk");
@@ -560,7 +560,7 @@ static int xvcu_probe(struct platform_device *pdev)
 	 * Bit 0 : Gasket isolation
 	 * Bit 1 : put VCU out of reset
 	 */
-	xvcu_write(xvcu->logicore_reg_ba, VCU_GASKET_INIT, VCU_GASKET_VALUE);
+	regmap_write(xvcu->logicore_reg_ba, VCU_GASKET_INIT, VCU_GASKET_VALUE);
 
 	/* Do the PLL Settings based on the ref clk,core and mcu clk freq */
 	ret = xvcu_set_pll(xvcu);
@@ -597,7 +597,7 @@ static int xvcu_remove(struct platform_device *pdev)
 		return -ENODEV;
 
 	/* Add the the Gasket isolation and put the VCU in reset. */
-	xvcu_write(xvcu->logicore_reg_ba, VCU_GASKET_INIT, 0);
+	regmap_write(xvcu->logicore_reg_ba, VCU_GASKET_INIT, 0);
 
 	clk_disable_unprepare(xvcu->pll_ref);
 	clk_disable_unprepare(xvcu->aclk);
diff --git a/include/linux/mfd/syscon/xlnx-vcu.h b/include/linux/mfd/syscon/xlnx-vcu.h
new file mode 100644
index 000000000000..d3edec4b7b1d
--- /dev/null
+++ b/include/linux/mfd/syscon/xlnx-vcu.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 Pengutronix, Michael Tretter <kernel@pengutronix.de>
+ */
+
+#ifndef __XLNX_VCU_H
+#define __XLNX_VCU_H
+
+#define VCU_ECODER_ENABLE		0x00
+#define VCU_DECODER_ENABLE		0x04
+#define VCU_MEMORY_DEPTH		0x08
+#define VCU_ENC_COLOR_DEPTH		0x0c
+#define VCU_ENC_VERTICAL_RANGE		0x10
+#define VCU_ENC_FRAME_SIZE_X		0x14
+#define VCU_ENC_FRAME_SIZE_Y		0x18
+#define VCU_ENC_COLOR_FORMAT		0x1c
+#define VCU_ENC_FPS			0x20
+#define VCU_MCU_CLK			0x24
+#define VCU_CORE_CLK			0x28
+#define VCU_PLL_BYPASS			0x2c
+#define VCU_ENC_CLK			0x30
+#define VCU_PLL_CLK			0x34
+#define VCU_ENC_VIDEO_STANDARD		0x38
+#define VCU_STATUS			0x3c
+#define VCU_AXI_ENC_CLK			0x40
+#define VCU_AXI_DEC_CLK			0x44
+#define VCU_AXI_MCU_CLK			0x48
+#define VCU_DEC_VIDEO_STANDARD		0x4c
+#define VCU_DEC_FRAME_SIZE_X		0x50
+#define VCU_DEC_FRAME_SIZE_Y		0x54
+#define VCU_DEC_FPS			0x58
+#define VCU_BUFFER_B_FRAME		0x5c
+#define VCU_WPP_EN			0x60
+#define VCU_PLL_CLK_DEC			0x64
+#define VCU_GASKET_INIT			0x74
+#define VCU_GASKET_VALUE		0x03
+
+#endif /* __XLNX_VCU_H */
-- 
cgit v1.2.3


From 7b1c9b8441aa94a549a90fa3d42687ccbad3eade Mon Sep 17 00:00:00 2001
From: Michael Tretter <m.tretter@pengutronix.de>
Date: Mon, 9 Nov 2020 14:48:18 +0100
Subject: soc: xilinx: vcu: add missing register NUM_CORE

The H.264/H.265 Video Codec Unit v1.2 documentation describes this
register as follows:

	Number of encoders core used for the provided configuration

This is required for configuring the VCU encoder buffer.

Signed-off-by: Michael Tretter <m.tretter@pengutronix.de>
Reviewed-by: Hyun Kwon <hyun.kwon@xilinx.com>
Link: https://lore.kernel.org/r/20201109134818.4159342-5-m.tretter@pengutronix.de
Signed-off-by: Michal Simek <michal.simek@xilinx.com>
---
 include/linux/mfd/syscon/xlnx-vcu.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/mfd/syscon/xlnx-vcu.h b/include/linux/mfd/syscon/xlnx-vcu.h
index d3edec4b7b1d..ff7bc3656f6e 100644
--- a/include/linux/mfd/syscon/xlnx-vcu.h
+++ b/include/linux/mfd/syscon/xlnx-vcu.h
@@ -32,6 +32,7 @@
 #define VCU_BUFFER_B_FRAME		0x5c
 #define VCU_WPP_EN			0x60
 #define VCU_PLL_CLK_DEC			0x64
+#define VCU_NUM_CORE			0x6c
 #define VCU_GASKET_INIT			0x74
 #define VCU_GASKET_VALUE		0x03
 
-- 
cgit v1.2.3


From 463edf5a59fd8f0fe0135101d67bfca81d1e3771 Mon Sep 17 00:00:00 2001
From: Wendy Liang <wendy.liang@xilinx.com>
Date: Tue, 24 Nov 2020 00:18:18 -0800
Subject: firmware: xlnx-zynqmp: fix compilation warning

Fix compilation warning when ZYNQMP_FIRMWARE is not defined.

include/linux/firmware/xlnx-zynqmp.h: In function
'zynqmp_pm_get_eemi_ops':
 include/linux/firmware/xlnx-zynqmp.h:363:9: error: implicit
 declaration of function 'ERR_PTR'
 [-Werror=implicit-function-declaration]
     363 |  return ERR_PTR(-ENODEV);

include/linux/firmware/xlnx-zynqmp.h:363:18: note: each undeclared
identifier is reported only once for each function it appears in
   include/linux/firmware/xlnx-zynqmp.h: In function
'zynqmp_pm_get_api_version':
   include/linux/firmware/xlnx-zynqmp.h:367:10: error: 'ENODEV'
undeclared (first use in this function)
     367 |  return -ENODEV;
         |          ^~~~~~

Signed-off-by: Wendy Liang <wendy.liang@xilinx.com>
Link: https://lore.kernel.org/r/1606205898-12642-1-git-send-email-wendy.liang@xilinx.com
Signed-off-by: Michal Simek <michal.simek@xilinx.com>
---
 include/linux/firmware/xlnx-zynqmp.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h
index 5968df82b991..f84244ea633b 100644
--- a/include/linux/firmware/xlnx-zynqmp.h
+++ b/include/linux/firmware/xlnx-zynqmp.h
@@ -13,6 +13,8 @@
 #ifndef __FIRMWARE_ZYNQMP_H__
 #define __FIRMWARE_ZYNQMP_H__
 
+#include <linux/err.h>
+
 #define ZYNQMP_PM_VERSION_MAJOR	1
 #define ZYNQMP_PM_VERSION_MINOR	0
 
-- 
cgit v1.2.3


From 1f6a11a01059f9c65f8461987cc0bab4c0b58338 Mon Sep 17 00:00:00 2001
From: Michal Simek <michal.simek@xilinx.com>
Date: Wed, 2 Dec 2020 08:38:48 +0100
Subject: firmware: xilinx: Remove additional newline

This additional newline is useless and also reported by checkpatch
--strict.

Signed-off-by: Michal Simek <michal.simek@xilinx.com>
Link: https://lore.kernel.org/r/d927f3f2c97910958dd77a22828cd0bf8d89c9de.1606894725.git.michal.simek@xilinx.com
---
 include/linux/firmware/xlnx-zynqmp.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h
index f84244ea633b..0db9005782d6 100644
--- a/include/linux/firmware/xlnx-zynqmp.h
+++ b/include/linux/firmware/xlnx-zynqmp.h
@@ -316,7 +316,6 @@ struct zynqmp_pm_query_data {
 	u32 arg3;
 };
 
-
 int zynqmp_pm_invoke_fn(u32 pm_api_id, u32 arg0, u32 arg1,
 			u32 arg2, u32 arg3, u32 *ret_payload);
 
-- 
cgit v1.2.3


From a80cefec2c2783166727324bde724c39aa8a12df Mon Sep 17 00:00:00 2001
From: Michal Simek <michal.simek@xilinx.com>
Date: Wed, 2 Dec 2020 08:38:49 +0100
Subject: firmware: xilinx: Add a blank line after function declaration

Fix all these issues which are also reported by checkpatch --strict.

Signed-off-by: Michal Simek <michal.simek@xilinx.com>
Link: https://lore.kernel.org/r/7b6007e05f6c01214861a37f198cd5bee62a4d3e.1606894725.git.michal.simek@xilinx.com
---
 include/linux/firmware/xlnx-zynqmp.h | 34 ++++++++++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h
index 0db9005782d6..0e7e72650ed3 100644
--- a/include/linux/firmware/xlnx-zynqmp.h
+++ b/include/linux/firmware/xlnx-zynqmp.h
@@ -363,107 +363,132 @@ static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void)
 {
 	return ERR_PTR(-ENODEV);
 }
+
 static inline int zynqmp_pm_get_api_version(u32 *version)
 {
 	return -ENODEV;
 }
+
 static inline int zynqmp_pm_get_chipid(u32 *idcode, u32 *version)
 {
 	return -ENODEV;
 }
+
 static inline int zynqmp_pm_query_data(struct zynqmp_pm_query_data qdata,
 				       u32 *out)
 {
 	return -ENODEV;
 }
+
 static inline int zynqmp_pm_clock_enable(u32 clock_id)
 {
 	return -ENODEV;
 }
+
 static inline int zynqmp_pm_clock_disable(u32 clock_id)
 {
 	return -ENODEV;
 }
+
 static inline int zynqmp_pm_clock_getstate(u32 clock_id, u32 *state)
 {
 	return -ENODEV;
 }
+
 static inline int zynqmp_pm_clock_setdivider(u32 clock_id, u32 divider)
 {
 	return -ENODEV;
 }
+
 static inline int zynqmp_pm_clock_getdivider(u32 clock_id, u32 *divider)
 {
 	return -ENODEV;
 }
+
 static inline int zynqmp_pm_clock_setrate(u32 clock_id, u64 rate)
 {
 	return -ENODEV;
 }
+
 static inline int zynqmp_pm_clock_getrate(u32 clock_id, u64 *rate)
 {
 	return -ENODEV;
 }
+
 static inline int zynqmp_pm_clock_setparent(u32 clock_id, u32 parent_id)
 {
 	return -ENODEV;
 }
+
 static inline int zynqmp_pm_clock_getparent(u32 clock_id, u32 *parent_id)
 {
 	return -ENODEV;
 }
+
 static inline int zynqmp_pm_set_pll_frac_mode(u32 clk_id, u32 mode)
 {
 	return -ENODEV;
 }
+
 static inline int zynqmp_pm_get_pll_frac_mode(u32 clk_id, u32 *mode)
 {
 	return -ENODEV;
 }
+
 static inline int zynqmp_pm_set_pll_frac_data(u32 clk_id, u32 data)
 {
 	return -ENODEV;
 }
+
 static inline int zynqmp_pm_get_pll_frac_data(u32 clk_id, u32 *data)
 {
 	return -ENODEV;
 }
+
 static inline int zynqmp_pm_set_sd_tapdelay(u32 node_id, u32 type, u32 value)
 {
 	return -ENODEV;
 }
+
 static inline int zynqmp_pm_sd_dll_reset(u32 node_id, u32 type)
 {
 	return -ENODEV;
 }
+
 static inline int zynqmp_pm_reset_assert(const enum zynqmp_pm_reset reset,
 			   const enum zynqmp_pm_reset_action assert_flag)
 {
 	return -ENODEV;
 }
+
 static inline int zynqmp_pm_reset_get_status(const enum zynqmp_pm_reset reset,
 					     u32 *status)
 {
 	return -ENODEV;
 }
+
 static inline int zynqmp_pm_init_finalize(void)
 {
 	return -ENODEV;
 }
+
 static inline int zynqmp_pm_set_suspend_mode(u32 mode)
 {
 	return -ENODEV;
 }
+
 static inline int zynqmp_pm_request_node(const u32 node, const u32 capabilities,
 					 const u32 qos,
 					 const enum zynqmp_pm_request_ack ack)
 {
 	return -ENODEV;
 }
+
 static inline int zynqmp_pm_release_node(const u32 node)
 {
 	return -ENODEV;
 }
+
 static inline int zynqmp_pm_set_requirement(const u32 node,
 					const u32 capabilities,
 					const u32 qos,
@@ -471,39 +496,48 @@ static inline int zynqmp_pm_set_requirement(const u32 node,
 {
 	return -ENODEV;
 }
+
 static inline int zynqmp_pm_aes_engine(const u64 address, u32 *out)
 {
 	return -ENODEV;
 }
+
 static inline int zynqmp_pm_fpga_load(const u64 address, const u32 size,
 				      const u32 flags)
 {
 	return -ENODEV;
 }
+
 static inline int zynqmp_pm_fpga_get_status(u32 *value)
 {
 	return -ENODEV;
 }
+
 static inline int zynqmp_pm_write_ggs(u32 index, u32 value)
 {
 	return -ENODEV;
 }
+
 static inline int zynqmp_pm_read_ggs(u32 index, u32 *value)
 {
 	return -ENODEV;
 }
+
 static inline int zynqmp_pm_write_pggs(u32 index, u32 value)
 {
 	return -ENODEV;
 }
+
 static inline int zynqmp_pm_read_pggs(u32 index, u32 *value)
 {
 	return -ENODEV;
 }
+
 static inline int zynqmp_pm_system_shutdown(const u32 type, const u32 subtype)
 {
 	return -ENODEV;
 }
+
 static inline int zynqmp_pm_set_boot_health_status(u32 value)
 {
 	return -ENODEV;
-- 
cgit v1.2.3


From 311c2520de21cb2f44291ad3d984b42191126628 Mon Sep 17 00:00:00 2001
From: Michal Simek <michal.simek@xilinx.com>
Date: Wed, 2 Dec 2020 08:38:50 +0100
Subject: firmware: xilinx: Properly align function parameter

Fix parameters alignment reported by checkpatch --strict.

Signed-off-by: Michal Simek <michal.simek@xilinx.com>
Link: https://lore.kernel.org/r/00ed9fcb94a6c22eff1fe8afdea46b2764a8687d.1606894725.git.michal.simek@xilinx.com
---
 include/linux/firmware/xlnx-zynqmp.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h
index 0e7e72650ed3..edc2977b26d9 100644
--- a/include/linux/firmware/xlnx-zynqmp.h
+++ b/include/linux/firmware/xlnx-zynqmp.h
@@ -456,7 +456,7 @@ static inline int zynqmp_pm_sd_dll_reset(u32 node_id, u32 type)
 }
 
 static inline int zynqmp_pm_reset_assert(const enum zynqmp_pm_reset reset,
-			   const enum zynqmp_pm_reset_action assert_flag)
+					 const enum zynqmp_pm_reset_action assert_flag)
 {
 	return -ENODEV;
 }
@@ -490,9 +490,9 @@ static inline int zynqmp_pm_release_node(const u32 node)
 }
 
 static inline int zynqmp_pm_set_requirement(const u32 node,
-					const u32 capabilities,
-					const u32 qos,
-					const enum zynqmp_pm_request_ack ack)
+					    const u32 capabilities,
+					    const u32 qos,
+					    const enum zynqmp_pm_request_ack ack)
 {
 	return -ENODEV;
 }
-- 
cgit v1.2.3


From 5b4258f6721f41b092c63f6ee71be76e9616718b Mon Sep 17 00:00:00 2001
From: Ricky Wu <ricky_wu@realtek.com>
Date: Wed, 2 Dec 2020 14:58:57 +0800
Subject: misc: rtsx: rts5249 support runtime PM

rtsx_pcr:
add callback functions to support runtime PM
add delay_work to put device to D3 after idle
over 10 sec

rts5249:
add extra init flow for rtd3 and set rtd3_en from
config setting

rtsx_pci_sdmmc:
child device support autosuspend

Signed-off-by: Ricky Wu <ricky_wu@realtek.com>
Link: https://lore.kernel.org/r/20201202065857.19412-1-ricky_wu@realtek.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/cardreader/rts5249.c  |  26 +++++++--
 drivers/misc/cardreader/rtsx_pcr.c | 106 ++++++++++++++++++++++++++++++++++++-
 drivers/misc/cardreader/rtsx_pcr.h |   1 +
 drivers/mmc/host/rtsx_pci_sdmmc.c  |  16 ++++++
 include/linux/rtsx_pci.h           |   2 +
 5 files changed, 145 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/misc/cardreader/rts5249.c b/drivers/misc/cardreader/rts5249.c
index b85279f1fc5e..b2676e7f5027 100644
--- a/drivers/misc/cardreader/rts5249.c
+++ b/drivers/misc/cardreader/rts5249.c
@@ -73,6 +73,9 @@ static void rtsx_base_fetch_vendor_settings(struct rtsx_pcr *pcr)
 
 	pci_read_config_dword(pdev, PCR_SETTING_REG2, &reg);
 	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", PCR_SETTING_REG2, reg);
+
+	pcr->rtd3_en = rtsx_reg_to_rtd3_uhsii(reg);
+
 	if (rtsx_check_mmc_support(reg))
 		pcr->extra_caps |= EXTRA_CAPS_NO_MMC;
 	pcr->sd30_drive_sel_3v3 = rtsx_reg_to_sd30_drive_sel_3v3(reg);
@@ -278,15 +281,28 @@ static int rts5249_extra_init_hw(struct rtsx_pcr *pcr)
 
 	rtsx_pci_send_cmd(pcr, CMD_TIMEOUT_DEF);
 
-	if (CHK_PCI_PID(pcr, PID_524A) || CHK_PCI_PID(pcr, PID_525A)) {
+	if (CHK_PCI_PID(pcr, PID_524A) || CHK_PCI_PID(pcr, PID_525A))
 		rtsx_pci_write_register(pcr, REG_VREF, PWD_SUSPND_EN, PWD_SUSPND_EN);
-		rtsx_pci_write_register(pcr, RTS524A_PM_CTRL3, 0x01, 0x00);
-		rtsx_pci_write_register(pcr, RTS524A_PME_FORCE_CTL, 0x30, 0x20);
+
+	if (pcr->rtd3_en) {
+		if (CHK_PCI_PID(pcr, PID_524A) || CHK_PCI_PID(pcr, PID_525A)) {
+			rtsx_pci_write_register(pcr, RTS524A_PM_CTRL3, 0x01, 0x01);
+			rtsx_pci_write_register(pcr, RTS524A_PME_FORCE_CTL, 0x30, 0x30);
+		} else {
+			rtsx_pci_write_register(pcr, PM_CTRL3, 0x01, 0x01);
+			rtsx_pci_write_register(pcr, PME_FORCE_CTL, 0xFF, 0x33);
+		}
 	} else {
-		rtsx_pci_write_register(pcr, PME_FORCE_CTL, 0xFF, 0x30);
-		rtsx_pci_write_register(pcr, PM_CTRL3, 0x01, 0x00);
+		if (CHK_PCI_PID(pcr, PID_524A) || CHK_PCI_PID(pcr, PID_525A)) {
+			rtsx_pci_write_register(pcr, RTS524A_PM_CTRL3, 0x01, 0x00);
+			rtsx_pci_write_register(pcr, RTS524A_PME_FORCE_CTL, 0x30, 0x20);
+		} else {
+			rtsx_pci_write_register(pcr, PME_FORCE_CTL, 0xFF, 0x30);
+			rtsx_pci_write_register(pcr, PM_CTRL3, 0x01, 0x00);
+		}
 	}
 
+
 	/*
 	 * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced
 	 * to drive low, and we forcibly request clock.
diff --git a/drivers/misc/cardreader/rtsx_pcr.c b/drivers/misc/cardreader/rtsx_pcr.c
index 3612063cab09..2700d1997750 100644
--- a/drivers/misc/cardreader/rtsx_pcr.c
+++ b/drivers/misc/cardreader/rtsx_pcr.c
@@ -20,6 +20,8 @@
 #include <linux/rtsx_pci.h>
 #include <linux/mmc/card.h>
 #include <asm/unaligned.h>
+#include <linux/pm.h>
+#include <linux/pm_runtime.h>
 
 #include "rtsx_pcr.h"
 #include "rts5261.h"
@@ -150,6 +152,12 @@ void rtsx_pci_start_run(struct rtsx_pcr *pcr)
 	if (pcr->remove_pci)
 		return;
 
+	if (pcr->rtd3_en)
+		if (pcr->is_runtime_suspended) {
+			pm_runtime_get(&(pcr->pci->dev));
+			pcr->is_runtime_suspended = false;
+		}
+
 	if (pcr->state != PDEV_STAT_RUN) {
 		pcr->state = PDEV_STAT_RUN;
 		if (pcr->ops->enable_auto_blink)
@@ -1081,6 +1089,16 @@ static void rtsx_pm_power_saving(struct rtsx_pcr *pcr)
 	rtsx_comm_pm_power_saving(pcr);
 }
 
+static void rtsx_pci_rtd3_work(struct work_struct *work)
+{
+	struct delayed_work *dwork = to_delayed_work(work);
+	struct rtsx_pcr *pcr = container_of(dwork, struct rtsx_pcr, rtd3_work);
+
+	pcr_dbg(pcr, "--> %s\n", __func__);
+	if (!pcr->is_runtime_suspended)
+		pm_runtime_put(&(pcr->pci->dev));
+}
+
 static void rtsx_pci_idle_work(struct work_struct *work)
 {
 	struct delayed_work *dwork = to_delayed_work(work);
@@ -1100,6 +1118,9 @@ static void rtsx_pci_idle_work(struct work_struct *work)
 	rtsx_pm_power_saving(pcr);
 
 	mutex_unlock(&pcr->pcr_mutex);
+
+	if (pcr->rtd3_en)
+		mod_delayed_work(system_wq, &pcr->rtd3_work, msecs_to_jiffies(10000));
 }
 
 static void rtsx_base_force_power_down(struct rtsx_pcr *pcr, u8 pm_state)
@@ -1579,6 +1600,15 @@ static int rtsx_pci_probe(struct pci_dev *pcidev,
 		rtsx_pcr_cells[i].platform_data = handle;
 		rtsx_pcr_cells[i].pdata_size = sizeof(*handle);
 	}
+
+	if (pcr->rtd3_en) {
+		INIT_DELAYED_WORK(&pcr->rtd3_work, rtsx_pci_rtd3_work);
+		pm_runtime_allow(&pcidev->dev);
+		pm_runtime_enable(&pcidev->dev);
+		pcr->is_runtime_suspended = false;
+	}
+
+
 	ret = mfd_add_devices(&pcidev->dev, pcr->id, rtsx_pcr_cells,
 			ARRAY_SIZE(rtsx_pcr_cells), NULL, 0, NULL);
 	if (ret < 0)
@@ -1616,6 +1646,9 @@ static void rtsx_pci_remove(struct pci_dev *pcidev)
 	struct pcr_handle *handle = pci_get_drvdata(pcidev);
 	struct rtsx_pcr *pcr = handle->pcr;
 
+	if (pcr->rtd3_en)
+		pm_runtime_get_noresume(&pcr->pci->dev);
+
 	pcr->remove_pci = true;
 
 	/* Disable interrupts at the pcr level */
@@ -1626,6 +1659,8 @@ static void rtsx_pci_remove(struct pci_dev *pcidev)
 
 	cancel_delayed_work_sync(&pcr->carddet_work);
 	cancel_delayed_work_sync(&pcr->idle_work);
+	if (pcr->rtd3_en)
+		cancel_delayed_work_sync(&pcr->rtd3_work);
 
 	mfd_remove_devices(&pcidev->dev);
 
@@ -1643,6 +1678,11 @@ static void rtsx_pci_remove(struct pci_dev *pcidev)
 	idr_remove(&rtsx_pci_idr, pcr->id);
 	spin_unlock(&rtsx_pci_lock);
 
+	if (pcr->rtd3_en) {
+		pm_runtime_disable(&pcr->pci->dev);
+		pm_runtime_put_noidle(&pcr->pci->dev);
+	}
+
 	kfree(pcr->slots);
 	kfree(pcr);
 	kfree(handle);
@@ -1724,13 +1764,77 @@ static void rtsx_pci_shutdown(struct pci_dev *pcidev)
 		pci_disable_msi(pcr->pci);
 }
 
+static int rtsx_pci_runtime_suspend(struct device *device)
+{
+	struct pci_dev *pcidev = to_pci_dev(device);
+	struct pcr_handle *handle;
+	struct rtsx_pcr *pcr;
+
+	handle = pci_get_drvdata(pcidev);
+	pcr = handle->pcr;
+	dev_dbg(&(pcidev->dev), "--> %s\n", __func__);
+
+	cancel_delayed_work(&pcr->carddet_work);
+	cancel_delayed_work(&pcr->rtd3_work);
+	cancel_delayed_work(&pcr->idle_work);
+
+	mutex_lock(&pcr->pcr_mutex);
+	rtsx_pci_power_off(pcr, HOST_ENTER_S3);
+
+	free_irq(pcr->irq, (void *)pcr);
+
+	mutex_unlock(&pcr->pcr_mutex);
+
+	pcr->is_runtime_suspended = true;
+
+	return 0;
+}
+
+static int rtsx_pci_runtime_resume(struct device *device)
+{
+	struct pci_dev *pcidev = to_pci_dev(device);
+	struct pcr_handle *handle;
+	struct rtsx_pcr *pcr;
+	int ret = 0;
+
+	handle = pci_get_drvdata(pcidev);
+	pcr = handle->pcr;
+	dev_dbg(&(pcidev->dev), "--> %s\n", __func__);
+
+	mutex_lock(&pcr->pcr_mutex);
+
+	rtsx_pci_write_register(pcr, HOST_SLEEP_STATE, 0x03, 0x00);
+	rtsx_pci_acquire_irq(pcr);
+	synchronize_irq(pcr->irq);
+
+	if (pcr->ops->fetch_vendor_settings)
+		pcr->ops->fetch_vendor_settings(pcr);
+
+	rtsx_pci_init_hw(pcr);
+
+	if (pcr->slots[RTSX_SD_CARD].p_dev != NULL) {
+		pcr->slots[RTSX_SD_CARD].card_event(
+				pcr->slots[RTSX_SD_CARD].p_dev);
+	}
+
+	schedule_delayed_work(&pcr->idle_work, msecs_to_jiffies(200));
+
+	mutex_unlock(&pcr->pcr_mutex);
+	return ret;
+}
+
 #else /* CONFIG_PM */
 
 #define rtsx_pci_shutdown NULL
+#define rtsx_pci_runtime_suspend NULL
+#define rtsx_pic_runtime_resume NULL
 
 #endif /* CONFIG_PM */
 
-static SIMPLE_DEV_PM_OPS(rtsx_pci_pm_ops, rtsx_pci_suspend, rtsx_pci_resume);
+static const struct dev_pm_ops rtsx_pci_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(rtsx_pci_suspend, rtsx_pci_resume)
+	SET_RUNTIME_PM_OPS(rtsx_pci_runtime_suspend, rtsx_pci_runtime_resume, NULL)
+};
 
 static struct pci_driver rtsx_pci_driver = {
 	.name = DRV_NAME_RTSX_PCI,
diff --git a/drivers/misc/cardreader/rtsx_pcr.h b/drivers/misc/cardreader/rtsx_pcr.h
index fe5f4ca0f937..daf057c4eea6 100644
--- a/drivers/misc/cardreader/rtsx_pcr.h
+++ b/drivers/misc/cardreader/rtsx_pcr.h
@@ -90,6 +90,7 @@ static inline u8 map_sd_drive(int idx)
 
 #define rtsx_check_mmc_support(reg)		((reg) & 0x10)
 #define rtsx_reg_to_rtd3(reg)				((reg) & 0x02)
+#define rtsx_reg_to_rtd3_uhsii(reg)				((reg) & 0x04)
 #define rtsx_reg_to_aspm(reg)			(((reg) >> 28) & 0x03)
 #define rtsx_reg_to_sd30_drive_sel_1v8(reg)	(((reg) >> 26) & 0x03)
 #define rtsx_reg_to_sd30_drive_sel_3v3(reg)	(((reg) >> 5) & 0x03)
diff --git a/drivers/mmc/host/rtsx_pci_sdmmc.c b/drivers/mmc/host/rtsx_pci_sdmmc.c
index eb395e144207..a7b5ad17bcf5 100644
--- a/drivers/mmc/host/rtsx_pci_sdmmc.c
+++ b/drivers/mmc/host/rtsx_pci_sdmmc.c
@@ -20,6 +20,7 @@
 #include <linux/mmc/card.h>
 #include <linux/rtsx_pci.h>
 #include <asm/unaligned.h>
+#include <linux/pm_runtime.h>
 
 struct realtek_pci_sdmmc {
 	struct platform_device	*pdev;
@@ -1343,6 +1344,7 @@ static void init_extra_caps(struct realtek_pci_sdmmc *host)
 static void realtek_init_host(struct realtek_pci_sdmmc *host)
 {
 	struct mmc_host *mmc = host->mmc;
+	struct rtsx_pcr *pcr = host->pcr;
 
 	mmc->f_min = 250000;
 	mmc->f_max = 208000000;
@@ -1350,6 +1352,8 @@ static void realtek_init_host(struct realtek_pci_sdmmc *host)
 	mmc->caps = MMC_CAP_4_BIT_DATA | MMC_CAP_SD_HIGHSPEED |
 		MMC_CAP_MMC_HIGHSPEED | MMC_CAP_BUS_WIDTH_TEST |
 		MMC_CAP_UHS_SDR12 | MMC_CAP_UHS_SDR25;
+	if (pcr->rtd3_en)
+		mmc->caps = mmc->caps | MMC_CAP_AGGRESSIVE_PM;
 	mmc->caps2 = MMC_CAP2_NO_PRESCAN_POWERUP | MMC_CAP2_FULL_PWR_CYCLE;
 	mmc->max_current_330 = 400;
 	mmc->max_current_180 = 800;
@@ -1407,6 +1411,13 @@ static int rtsx_pci_sdmmc_drv_probe(struct platform_device *pdev)
 
 	realtek_init_host(host);
 
+	if (pcr->rtd3_en) {
+		pm_runtime_set_autosuspend_delay(&pdev->dev, 5000);
+		pm_runtime_use_autosuspend(&pdev->dev);
+		pm_runtime_enable(&pdev->dev);
+	}
+
+
 	mmc_add_host(mmc);
 
 	return 0;
@@ -1426,6 +1437,11 @@ static int rtsx_pci_sdmmc_drv_remove(struct platform_device *pdev)
 	pcr->slots[RTSX_SD_CARD].card_event = NULL;
 	mmc = host->mmc;
 
+	if (pcr->rtd3_en) {
+		pm_runtime_dont_use_autosuspend(&pdev->dev);
+		pm_runtime_disable(&pdev->dev);
+	}
+
 	cancel_work_sync(&host->work);
 
 	mutex_lock(&host->host_mutex);
diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h
index 745f5e73f99a..f895ccabbe29 100644
--- a/include/linux/rtsx_pci.h
+++ b/include/linux/rtsx_pci.h
@@ -1174,6 +1174,7 @@ struct rtsx_pcr {
 
 	struct delayed_work		carddet_work;
 	struct delayed_work		idle_work;
+	struct delayed_work		rtd3_work;
 
 	spinlock_t			lock;
 	struct mutex			pcr_mutex;
@@ -1183,6 +1184,7 @@ struct rtsx_pcr {
 	unsigned int			cur_clock;
 	bool				remove_pci;
 	bool				msi_en;
+	bool				is_runtime_suspended;
 
 #define EXTRA_CAPS_SD_SDR50		(1 << 0)
 #define EXTRA_CAPS_SD_SDR104		(1 << 1)
-- 
cgit v1.2.3


From 8010622c86ca5bb44bc98492f5968726fc7c7a21 Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Wed, 9 Dec 2020 16:26:39 +0100
Subject: USB: UAS: introduce a quirk to set no_write_same

UAS does not share the pessimistic assumption storage is making that
devices cannot deal with WRITE_SAME.  A few devices supported by UAS,
are reported to not deal well with WRITE_SAME. Those need a quirk.

Add it to the device that needs it.

Reported-by: David C. Partridge <david.partridge@perdrix.co.uk>
Signed-off-by: Oliver Neukum <oneukum@suse.com>
Cc: stable <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20201209152639.9195-1-oneukum@suse.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/admin-guide/kernel-parameters.txt | 1 +
 drivers/usb/storage/uas.c                       | 3 +++
 drivers/usb/storage/unusual_uas.h               | 7 +++++--
 drivers/usb/storage/usb.c                       | 3 +++
 include/linux/usb_usual.h                       | 2 ++
 5 files changed, 14 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 44fde25bb221..f6a1513dfb76 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -5663,6 +5663,7 @@
 					device);
 				j = NO_REPORT_LUNS (don't use report luns
 					command, uas only);
+				k = NO_SAME (do not use WRITE_SAME, uas only)
 				l = NOT_LOCKABLE (don't try to lock and
 					unlock ejectable media, not on uas);
 				m = MAX_SECTORS_64 (don't transfer more
diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
index 56422c4b4ff3..bef89c6bd1d7 100644
--- a/drivers/usb/storage/uas.c
+++ b/drivers/usb/storage/uas.c
@@ -868,6 +868,9 @@ static int uas_slave_configure(struct scsi_device *sdev)
 	if (devinfo->flags & US_FL_NO_READ_CAPACITY_16)
 		sdev->no_read_capacity_16 = 1;
 
+	/* Some disks cannot handle WRITE_SAME */
+	if (devinfo->flags & US_FL_NO_SAME)
+		sdev->no_write_same = 1;
 	/*
 	 * Some disks return the total number of blocks in response
 	 * to READ CAPACITY rather than the highest block number.
diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h
index 711ab240058c..870e9cf3d5dc 100644
--- a/drivers/usb/storage/unusual_uas.h
+++ b/drivers/usb/storage/unusual_uas.h
@@ -35,12 +35,15 @@ UNUSUAL_DEV(0x054c, 0x087d, 0x0000, 0x9999,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_NO_REPORT_OPCODES),
 
-/* Reported-by: Julian Groß <julian.g@posteo.de> */
+/*
+ *  Initially Reported-by: Julian Groß <julian.g@posteo.de>
+ *  Further reports David C. Partridge <david.partridge@perdrix.co.uk>
+ */
 UNUSUAL_DEV(0x059f, 0x105f, 0x0000, 0x9999,
 		"LaCie",
 		"2Big Quadra USB3",
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
-		US_FL_NO_REPORT_OPCODES),
+		US_FL_NO_REPORT_OPCODES | US_FL_NO_SAME),
 
 /*
  * Apricorn USB3 dongle sometimes returns "USBSUSBSUSBS" in response to SCSI
diff --git a/drivers/usb/storage/usb.c b/drivers/usb/storage/usb.c
index 94a64729dc27..90aa9c12ffac 100644
--- a/drivers/usb/storage/usb.c
+++ b/drivers/usb/storage/usb.c
@@ -541,6 +541,9 @@ void usb_stor_adjust_quirks(struct usb_device *udev, unsigned long *fflags)
 		case 'j':
 			f |= US_FL_NO_REPORT_LUNS;
 			break;
+		case 'k':
+			f |= US_FL_NO_SAME;
+			break;
 		case 'l':
 			f |= US_FL_NOT_LOCKABLE;
 			break;
diff --git a/include/linux/usb_usual.h b/include/linux/usb_usual.h
index 4a19ac3f24d0..6b03fdd69d27 100644
--- a/include/linux/usb_usual.h
+++ b/include/linux/usb_usual.h
@@ -84,6 +84,8 @@
 		/* Cannot handle REPORT_LUNS */			\
 	US_FLAG(ALWAYS_SYNC, 0x20000000)			\
 		/* lies about caching, so always sync */	\
+	US_FLAG(NO_SAME, 0x40000000)				\
+		/* Cannot handle WRITE_SAME */			\
 
 #define US_FLAG(name, value)	US_FL_##name = value ,
 enum { US_DO_ALL_FLAGS };
-- 
cgit v1.2.3


From c73ebb685fb6dfb513d394cbea64fb81ba3d994f Mon Sep 17 00:00:00 2001
From: Hao Xu <haoxu@linux.alibaba.com>
Date: Tue, 3 Nov 2020 10:54:37 +0800
Subject: io_uring: add timeout support for io_uring_enter()

Now users who want to get woken when waiting for events should submit a
timeout command first. It is not safe for applications that split SQ and
CQ handling between two threads, such as mysql. Users should synchronize
the two threads explicitly to protect SQ and that will impact the
performance.

This patch adds support for timeout to existing io_uring_enter(). To
avoid overloading arguments, it introduces a new parameter structure
which contains sigmask and timeout.

I have tested the workloads with one thread submiting nop requests
while the other reaping the cqe with timeout. It shows 1.8~2x faster
when the iodepth is 16.

Signed-off-by: Jiufei Xue <jiufei.xue@linux.alibaba.com>
Signed-off-by: Hao Xu <haoxu@linux.alibaba.com>
[axboe: various cleanups/fixes, and name change to SIG_IS_DATA]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c                 | 69 ++++++++++++++++++++++++++++++++++++++-----
 include/linux/syscalls.h      |  2 +-
 include/uapi/linux/io_uring.h |  9 ++++++
 3 files changed, 72 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 11ce97d6259c..ee25c70527aa 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -7118,7 +7118,8 @@ static int io_run_task_work_sig(void)
  * application must reap them itself, as they reside on the shared cq ring.
  */
 static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
-			  const sigset_t __user *sig, size_t sigsz)
+			  const sigset_t __user *sig, size_t sigsz,
+			  struct __kernel_timespec __user *uts)
 {
 	struct io_wait_queue iowq = {
 		.wq = {
@@ -7130,6 +7131,8 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 		.to_wait	= min_events,
 	};
 	struct io_rings *rings = ctx->rings;
+	struct timespec64 ts;
+	signed long timeout = 0;
 	int ret = 0;
 
 	do {
@@ -7152,6 +7155,12 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 			return ret;
 	}
 
+	if (uts) {
+		if (get_timespec64(&ts, uts))
+			return -EFAULT;
+		timeout = timespec64_to_jiffies(&ts);
+	}
+
 	iowq.nr_timeouts = atomic_read(&ctx->cq_timeouts);
 	trace_io_uring_cqring_wait(ctx, min_events);
 	do {
@@ -7165,7 +7174,15 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 			break;
 		if (io_should_wake(&iowq, false))
 			break;
-		schedule();
+		if (uts) {
+			timeout = schedule_timeout(timeout);
+			if (timeout == 0) {
+				ret = -ETIME;
+				break;
+			}
+		} else {
+			schedule();
+		}
 	} while (1);
 	finish_wait(&ctx->wait, &iowq.wq);
 
@@ -9167,9 +9184,39 @@ static void io_sqpoll_wait_sq(struct io_ring_ctx *ctx)
 	finish_wait(&ctx->sqo_sq_wait, &wait);
 }
 
+static int io_get_ext_arg(unsigned flags, const void __user *argp, size_t *argsz,
+			  struct __kernel_timespec __user **ts,
+			  const sigset_t __user **sig)
+{
+	struct io_uring_getevents_arg arg;
+
+	/*
+	 * If EXT_ARG isn't set, then we have no timespec and the argp pointer
+	 * is just a pointer to the sigset_t.
+	 */
+	if (!(flags & IORING_ENTER_EXT_ARG)) {
+		*sig = (const sigset_t __user *) argp;
+		*ts = NULL;
+		return 0;
+	}
+
+	/*
+	 * EXT_ARG is set - ensure we agree on the size of it and copy in our
+	 * timespec and sigset_t pointers if good.
+	 */
+	if (*argsz != sizeof(arg))
+		return -EINVAL;
+	if (copy_from_user(&arg, argp, sizeof(arg)))
+		return -EFAULT;
+	*sig = u64_to_user_ptr(arg.sigmask);
+	*argsz = arg.sigmask_sz;
+	*ts = u64_to_user_ptr(arg.ts);
+	return 0;
+}
+
 SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
-		u32, min_complete, u32, flags, const sigset_t __user *, sig,
-		size_t, sigsz)
+		u32, min_complete, u32, flags, const void __user *, argp,
+		size_t, argsz)
 {
 	struct io_ring_ctx *ctx;
 	long ret = -EBADF;
@@ -9179,7 +9226,7 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 	io_run_task_work();
 
 	if (flags & ~(IORING_ENTER_GETEVENTS | IORING_ENTER_SQ_WAKEUP |
-			IORING_ENTER_SQ_WAIT))
+			IORING_ENTER_SQ_WAIT | IORING_ENTER_EXT_ARG))
 		return -EINVAL;
 
 	f = fdget(fd);
@@ -9225,6 +9272,13 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 			goto out;
 	}
 	if (flags & IORING_ENTER_GETEVENTS) {
+		const sigset_t __user *sig;
+		struct __kernel_timespec __user *ts;
+
+		ret = io_get_ext_arg(flags, argp, &argsz, &ts, &sig);
+		if (unlikely(ret))
+			goto out;
+
 		min_complete = min(min_complete, ctx->cq_entries);
 
 		/*
@@ -9237,7 +9291,7 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 		    !(ctx->flags & IORING_SETUP_SQPOLL)) {
 			ret = io_iopoll_check(ctx, min_complete);
 		} else {
-			ret = io_cqring_wait(ctx, min_complete, sig, sigsz);
+			ret = io_cqring_wait(ctx, min_complete, sig, argsz, ts);
 		}
 	}
 
@@ -9600,7 +9654,8 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p,
 	p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP |
 			IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS |
 			IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL |
-			IORING_FEAT_POLL_32BITS | IORING_FEAT_SQPOLL_NONFIXED;
+			IORING_FEAT_POLL_32BITS | IORING_FEAT_SQPOLL_NONFIXED |
+			IORING_FEAT_EXT_ARG;
 
 	if (copy_to_user(params, p, sizeof(*p))) {
 		ret = -EFAULT;
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 37bea07c12f2..8576e8bf92fe 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -317,7 +317,7 @@ asmlinkage long sys_io_uring_setup(u32 entries,
 				struct io_uring_params __user *p);
 asmlinkage long sys_io_uring_enter(unsigned int fd, u32 to_submit,
 				u32 min_complete, u32 flags,
-				const sigset_t __user *sig, size_t sigsz);
+				const void __user *argp, size_t argsz);
 asmlinkage long sys_io_uring_register(unsigned int fd, unsigned int op,
 				void __user *arg, unsigned int nr_args);
 
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 557e7eae497f..6bb8229de892 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -231,6 +231,7 @@ struct io_cqring_offsets {
 #define IORING_ENTER_GETEVENTS	(1U << 0)
 #define IORING_ENTER_SQ_WAKEUP	(1U << 1)
 #define IORING_ENTER_SQ_WAIT	(1U << 2)
+#define IORING_ENTER_EXT_ARG	(1U << 3)
 
 /*
  * Passed in for io_uring_setup(2). Copied back with updated info on success
@@ -259,6 +260,7 @@ struct io_uring_params {
 #define IORING_FEAT_FAST_POLL		(1U << 5)
 #define IORING_FEAT_POLL_32BITS 	(1U << 6)
 #define IORING_FEAT_SQPOLL_NONFIXED	(1U << 7)
+#define IORING_FEAT_EXT_ARG		(1U << 8)
 
 /*
  * io_uring_register(2) opcodes and arguments
@@ -335,4 +337,11 @@ enum {
 	IORING_RESTRICTION_LAST
 };
 
+struct io_uring_getevents_arg {
+	__u64	sigmask;
+	__u32	sigmask_sz;
+	__u32	pad;
+	__u64	ts;
+};
+
 #endif
-- 
cgit v1.2.3


From 5a6338cce9f4133c478d3b10b300f96dd644379a Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Tue, 17 Nov 2020 15:32:06 +0530
Subject: mailbox: arm_mhuv2: Add driver

This adds driver for the ARM MHUv2 (Message Handling Unit) mailbox
controller.

This is based on the accepted DT bindings of the controller and supports
combination of both transport protocols, i.e. doorbell and data-transfer.

Transmitting and receiving data through the mailbox framework is done
through struct arm_mhuv2_mbox_msg.

Based on the initial work done by Morten Borup Petersen from ARM.

Co-developed-by: Tushar Khandelwal <tushar.khandelwal@arm.com>
Signed-off-by: Tushar Khandelwal <tushar.khandelwal@arm.com>
Tested-by: Usama Arif <usama.arif@arm.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 MAINTAINERS                               |    9 +
 drivers/mailbox/Kconfig                   |    7 +
 drivers/mailbox/Makefile                  |    2 +
 drivers/mailbox/arm_mhuv2.c               | 1136 +++++++++++++++++++++++++++++
 include/linux/mailbox/arm_mhuv2_message.h |   20 +
 5 files changed, 1174 insertions(+)
 create mode 100644 drivers/mailbox/arm_mhuv2.c
 create mode 100644 include/linux/mailbox/arm_mhuv2_message.h

(limited to 'include/linux')

diff --git a/MAINTAINERS b/MAINTAINERS
index 2daa6ee673f7..3917b7ef1da6 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10418,6 +10418,15 @@ F:	drivers/mailbox/
 F:	include/linux/mailbox_client.h
 F:	include/linux/mailbox_controller.h
 
+MAILBOX ARM MHUv2
+M:	Viresh Kumar <viresh.kumar@linaro.org>
+M:	Tushar Khandelwal <Tushar.Khandelwal@arm.com>
+L:	linux-kernel@vger.kernel.org
+S:	Maintained
+F:	drivers/mailbox/arm_mhuv2.c
+F:	include/linux/mailbox/arm_mhuv2_message.h
+F:	Documentation/devicetree/bindings/mailbox/arm,mhuv2.yaml
+
 MAN-PAGES: MANUAL PAGES FOR LINUX -- Sections 2, 3, 4, 5, and 7
 M:	Michael Kerrisk <mtk.manpages@gmail.com>
 L:	linux-man@vger.kernel.org
diff --git a/drivers/mailbox/Kconfig b/drivers/mailbox/Kconfig
index abbf5d67ffa2..f4abe3529acd 100644
--- a/drivers/mailbox/Kconfig
+++ b/drivers/mailbox/Kconfig
@@ -16,6 +16,13 @@ config ARM_MHU
 	  The controller has 3 mailbox channels, the last of which can be
 	  used in Secure mode only.
 
+config ARM_MHU_V2
+	tristate "ARM MHUv2 Mailbox"
+	depends on ARM_AMBA
+	help
+	  Say Y here if you want to build the ARM MHUv2 controller driver,
+	  which provides unidirectional mailboxes between processing elements.
+
 config IMX_MBOX
 	tristate "i.MX Mailbox"
 	depends on ARCH_MXC || COMPILE_TEST
diff --git a/drivers/mailbox/Makefile b/drivers/mailbox/Makefile
index 2e06e02b2e03..7194fa92c787 100644
--- a/drivers/mailbox/Makefile
+++ b/drivers/mailbox/Makefile
@@ -7,6 +7,8 @@ obj-$(CONFIG_MAILBOX_TEST)	+= mailbox-test.o
 
 obj-$(CONFIG_ARM_MHU)	+= arm_mhu.o arm_mhu_db.o
 
+obj-$(CONFIG_ARM_MHU_V2)	+= arm_mhuv2.o
+
 obj-$(CONFIG_IMX_MBOX)	+= imx-mailbox.o
 
 obj-$(CONFIG_ARMADA_37XX_RWTM_MBOX)	+= armada-37xx-rwtm-mailbox.o
diff --git a/drivers/mailbox/arm_mhuv2.c b/drivers/mailbox/arm_mhuv2.c
new file mode 100644
index 000000000000..67fb10885bb4
--- /dev/null
+++ b/drivers/mailbox/arm_mhuv2.c
@@ -0,0 +1,1136 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ARM Message Handling Unit Version 2 (MHUv2) driver.
+ *
+ * Copyright (C) 2020 ARM Ltd.
+ * Copyright (C) 2020 Linaro Ltd.
+ *
+ * An MHUv2 mailbox controller can provide up to 124 channel windows (each 32
+ * bit long) and the driver allows any combination of both the transport
+ * protocol modes: data-transfer and doorbell, to be used on those channel
+ * windows.
+ *
+ * The transport protocols should be specified in the device tree entry for the
+ * device. The transport protocols determine how the underlying hardware
+ * resources of the device are utilized when transmitting data. Refer to the
+ * device tree bindings of the ARM MHUv2 controller for more details.
+ *
+ * The number of registered mailbox channels is dependent on both the underlying
+ * hardware - mainly the number of channel windows implemented by the platform,
+ * as well as the selected transport protocols.
+ *
+ * The MHUv2 controller can work both as a sender and receiver, but the driver
+ * and the DT bindings support unidirectional transfers for better allocation of
+ * the channels. That is, this driver will be probed for two separate devices
+ * for each mailbox controller, a sender device and a receiver device.
+ */
+
+#include <linux/amba/bus.h>
+#include <linux/interrupt.h>
+#include <linux/mailbox_controller.h>
+#include <linux/mailbox/arm_mhuv2_message.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/spinlock.h>
+
+/* ====== MHUv2 Registers ====== */
+
+/* Maximum number of channel windows */
+#define MHUV2_CH_WN_MAX			124
+/* Number of combined interrupt status registers */
+#define MHUV2_CMB_INT_ST_REG_CNT	4
+#define MHUV2_STAT_BYTES		(sizeof(u32))
+#define MHUV2_STAT_BITS			(MHUV2_STAT_BYTES * __CHAR_BIT__)
+
+#define LSB_MASK(n)			((1 << (n * __CHAR_BIT__)) - 1)
+#define MHUV2_PROTOCOL_PROP		"arm,mhuv2-protocols"
+
+/* Register Message Handling Unit Configuration fields */
+struct mhu_cfg_t {
+	u32 num_ch : 7;
+	u32 pad : 25;
+} __packed;
+
+/* register Interrupt Status fields */
+struct int_st_t {
+	u32 nr2r : 1;
+	u32 r2nr : 1;
+	u32 pad : 30;
+} __packed;
+
+/* Register Interrupt Clear fields */
+struct int_clr_t {
+	u32 nr2r : 1;
+	u32 r2nr : 1;
+	u32 pad : 30;
+} __packed;
+
+/* Register Interrupt Enable fields */
+struct int_en_t {
+	u32 r2nr : 1;
+	u32 nr2r : 1;
+	u32 chcomb : 1;
+	u32 pad : 29;
+} __packed;
+
+/* Register Implementer Identification fields */
+struct iidr_t {
+	u32 implementer : 12;
+	u32 revision : 4;
+	u32 variant : 4;
+	u32 product_id : 12;
+} __packed;
+
+/* Register Architecture Identification Register fields */
+struct aidr_t {
+	u32 arch_minor_rev : 4;
+	u32 arch_major_rev : 4;
+	u32 pad : 24;
+} __packed;
+
+/* Sender Channel Window fields */
+struct mhu2_send_ch_wn_reg {
+	u32 stat;
+	u8 pad1[0x0C - 0x04];
+	u32 stat_set;
+	u32 int_st;
+	u32 int_clr;
+	u32 int_en;
+	u8 pad2[0x20 - 0x1C];
+} __packed;
+
+/* Sender frame register fields */
+struct mhu2_send_frame_reg {
+	struct mhu2_send_ch_wn_reg ch_wn[MHUV2_CH_WN_MAX];
+	struct mhu_cfg_t mhu_cfg;
+	u32 resp_cfg;
+	u32 access_request;
+	u32 access_ready;
+	struct int_st_t int_st;
+	struct int_clr_t int_clr;
+	struct int_en_t int_en;
+	u32 reserved0;
+	u32 chcomb_int_st[MHUV2_CMB_INT_ST_REG_CNT];
+	u8 pad[0xFC8 - 0xFB0];
+	struct iidr_t iidr;
+	struct aidr_t aidr;
+} __packed;
+
+/* Receiver Channel Window fields */
+struct mhu2_recv_ch_wn_reg {
+	u32 stat;
+	u32 stat_masked;
+	u32 stat_clear;
+	u8 reserved0[0x10 - 0x0C];
+	u32 mask;
+	u32 mask_set;
+	u32 mask_clear;
+	u8 pad[0x20 - 0x1C];
+} __packed;
+
+/* Receiver frame register fields */
+struct mhu2_recv_frame_reg {
+	struct mhu2_recv_ch_wn_reg ch_wn[MHUV2_CH_WN_MAX];
+	struct mhu_cfg_t mhu_cfg;
+	u8 reserved0[0xF90 - 0xF84];
+	struct int_st_t int_st;
+	struct int_clr_t int_clr;
+	struct int_en_t int_en;
+	u32 pad;
+	u32 chcomb_int_st[MHUV2_CMB_INT_ST_REG_CNT];
+	u8 reserved2[0xFC8 - 0xFB0];
+	struct iidr_t iidr;
+	struct aidr_t aidr;
+} __packed;
+
+
+/* ====== MHUv2 data structures ====== */
+
+enum mhuv2_transport_protocol {
+	DOORBELL = 0,
+	DATA_TRANSFER = 1
+};
+
+enum mhuv2_frame {
+	RECEIVER_FRAME,
+	SENDER_FRAME
+};
+
+/**
+ * struct mhuv2 - MHUv2 mailbox controller data
+ *
+ * @mbox:	Mailbox controller belonging to the MHU frame.
+ * @send/recv:	Base address of the register mapping region.
+ * @frame:	Frame type: RECEIVER_FRAME or SENDER_FRAME.
+ * @irq:	Interrupt.
+ * @windows:	Channel windows implemented by the platform.
+ * @minor:	Minor version of the controller.
+ * @length:	Length of the protocols array in bytes.
+ * @protocols:	Raw protocol information, derived from device tree.
+ * @doorbell_pending_lock: spinlock required for correct operation of Tx
+ *		interrupt for doorbells.
+ */
+struct mhuv2 {
+	struct mbox_controller mbox;
+	union {
+		struct mhu2_send_frame_reg __iomem *send;
+		struct mhu2_recv_frame_reg __iomem *recv;
+	};
+	enum mhuv2_frame frame;
+	unsigned int irq;
+	unsigned int windows;
+	unsigned int minor;
+	unsigned int length;
+	u32 *protocols;
+
+	spinlock_t doorbell_pending_lock;
+};
+
+#define mhu_from_mbox(_mbox) container_of(_mbox, struct mhuv2, mbox)
+
+/**
+ * struct mhuv2_protocol_ops - MHUv2 operations
+ *
+ * Each transport protocol must provide an implementation of the operations
+ * provided here.
+ *
+ * @rx_startup: Startup callback for receiver.
+ * @rx_shutdown: Shutdown callback for receiver.
+ * @read_data: Reads and clears newly available data.
+ * @tx_startup: Startup callback for receiver.
+ * @tx_shutdown: Shutdown callback for receiver.
+ * @last_tx_done: Report back if the last tx is completed or not.
+ * @send_data: Send data to the receiver.
+ */
+struct mhuv2_protocol_ops {
+	int (*rx_startup)(struct mhuv2 *mhu, struct mbox_chan *chan);
+	void (*rx_shutdown)(struct mhuv2 *mhu, struct mbox_chan *chan);
+	void *(*read_data)(struct mhuv2 *mhu, struct mbox_chan *chan);
+
+	void (*tx_startup)(struct mhuv2 *mhu, struct mbox_chan *chan);
+	void (*tx_shutdown)(struct mhuv2 *mhu, struct mbox_chan *chan);
+	int (*last_tx_done)(struct mhuv2 *mhu, struct mbox_chan *chan);
+	int (*send_data)(struct mhuv2 *mhu, struct mbox_chan *chan, void *arg);
+};
+
+/*
+ * MHUv2 mailbox channel's private information
+ *
+ * @ops:	protocol specific ops for the channel.
+ * @ch_wn_idx:	Channel window index allocated to the channel.
+ * @windows:	Total number of windows consumed by the channel, only relevant
+ *		in DATA_TRANSFER protocol.
+ * @doorbell:	Doorbell bit number within the ch_wn_idx window, only relevant
+ *		in DOORBELL protocol.
+ * @pending:	Flag indicating pending doorbell interrupt, only relevant in
+ *		DOORBELL protocol.
+ */
+struct mhuv2_mbox_chan_priv {
+	const struct mhuv2_protocol_ops *ops;
+	u32 ch_wn_idx;
+	union {
+		u32 windows;
+		struct {
+			u32 doorbell;
+			u32 pending;
+		};
+	};
+};
+
+/* Macro for reading a bitfield within a physically mapped packed struct */
+#define readl_relaxed_bitfield(_regptr, _field)				\
+	({								\
+		u32 _regval;						\
+		_regval = readl_relaxed((_regptr));			\
+		(*(typeof((_regptr)))(&_regval))._field;		\
+	})
+
+/* Macro for writing a bitfield within a physically mapped packed struct */
+#define writel_relaxed_bitfield(_value, _regptr, _field)		\
+	({								\
+		u32 _regval;						\
+		_regval = readl_relaxed(_regptr);			\
+		(*(typeof(_regptr))(&_regval))._field = _value;		\
+		writel_relaxed(_regval, _regptr);			\
+	})
+
+
+/* =================== Doorbell transport protocol operations =============== */
+
+static int mhuv2_doorbell_rx_startup(struct mhuv2 *mhu, struct mbox_chan *chan)
+{
+	struct mhuv2_mbox_chan_priv *priv = chan->con_priv;
+
+	writel_relaxed(BIT(priv->doorbell),
+		       &mhu->recv->ch_wn[priv->ch_wn_idx].mask_clear);
+	return 0;
+}
+
+static void mhuv2_doorbell_rx_shutdown(struct mhuv2 *mhu,
+				       struct mbox_chan *chan)
+{
+	struct mhuv2_mbox_chan_priv *priv = chan->con_priv;
+
+	writel_relaxed(BIT(priv->doorbell),
+		       &mhu->recv->ch_wn[priv->ch_wn_idx].mask_set);
+}
+
+static void *mhuv2_doorbell_read_data(struct mhuv2 *mhu, struct mbox_chan *chan)
+{
+	struct mhuv2_mbox_chan_priv *priv = chan->con_priv;
+
+	writel_relaxed(BIT(priv->doorbell),
+		       &mhu->recv->ch_wn[priv->ch_wn_idx].stat_clear);
+	return NULL;
+}
+
+static int mhuv2_doorbell_last_tx_done(struct mhuv2 *mhu,
+				       struct mbox_chan *chan)
+{
+	struct mhuv2_mbox_chan_priv *priv = chan->con_priv;
+
+	return !(readl_relaxed(&mhu->send->ch_wn[priv->ch_wn_idx].stat) &
+		 BIT(priv->doorbell));
+}
+
+static int mhuv2_doorbell_send_data(struct mhuv2 *mhu, struct mbox_chan *chan,
+				    void *arg)
+{
+	struct mhuv2_mbox_chan_priv *priv = chan->con_priv;
+	unsigned long flags;
+
+	spin_lock_irqsave(&mhu->doorbell_pending_lock, flags);
+
+	priv->pending = 1;
+	writel_relaxed(BIT(priv->doorbell),
+		       &mhu->send->ch_wn[priv->ch_wn_idx].stat_set);
+
+	spin_unlock_irqrestore(&mhu->doorbell_pending_lock, flags);
+
+	return 0;
+}
+
+static const struct mhuv2_protocol_ops mhuv2_doorbell_ops = {
+	.rx_startup = mhuv2_doorbell_rx_startup,
+	.rx_shutdown = mhuv2_doorbell_rx_shutdown,
+	.read_data = mhuv2_doorbell_read_data,
+	.last_tx_done = mhuv2_doorbell_last_tx_done,
+	.send_data = mhuv2_doorbell_send_data,
+};
+#define IS_PROTOCOL_DOORBELL(_priv) (_priv->ops == &mhuv2_doorbell_ops)
+
+/* ============= Data transfer transport protocol operations ================ */
+
+static int mhuv2_data_transfer_rx_startup(struct mhuv2 *mhu,
+					  struct mbox_chan *chan)
+{
+	struct mhuv2_mbox_chan_priv *priv = chan->con_priv;
+	int i = priv->ch_wn_idx + priv->windows - 1;
+
+	/*
+	 * The protocol mandates that all but the last status register must be
+	 * masked.
+	 */
+	writel_relaxed(0xFFFFFFFF, &mhu->recv->ch_wn[i].mask_clear);
+	return 0;
+}
+
+static void mhuv2_data_transfer_rx_shutdown(struct mhuv2 *mhu,
+					    struct mbox_chan *chan)
+{
+	struct mhuv2_mbox_chan_priv *priv = chan->con_priv;
+	int i = priv->ch_wn_idx + priv->windows - 1;
+
+	writel_relaxed(0xFFFFFFFF, &mhu->recv->ch_wn[i].mask_set);
+}
+
+static void *mhuv2_data_transfer_read_data(struct mhuv2 *mhu,
+					   struct mbox_chan *chan)
+{
+	struct mhuv2_mbox_chan_priv *priv = chan->con_priv;
+	const int windows = priv->windows;
+	struct arm_mhuv2_mbox_msg *msg;
+	u32 *data;
+	int i, idx;
+
+	msg = kzalloc(sizeof(*msg) + windows * MHUV2_STAT_BYTES, GFP_KERNEL);
+	if (!msg)
+		return ERR_PTR(-ENOMEM);
+
+	data = msg->data = msg + 1;
+	msg->len = windows * MHUV2_STAT_BYTES;
+
+	/*
+	 * Messages are expected in order of most significant word to least
+	 * significant word. Refer mhuv2_data_transfer_send_data() for more
+	 * details.
+	 *
+	 * We also need to read the stat register instead of stat_masked, as we
+	 * masked all but the last window.
+	 *
+	 * Last channel window must be cleared as the final operation. Upon
+	 * clearing the last channel window register, which is unmasked in
+	 * data-transfer protocol, the interrupt is de-asserted.
+	 */
+	for (i = 0; i < windows; i++) {
+		idx = priv->ch_wn_idx + i;
+		data[windows - 1 - i] = readl_relaxed(&mhu->recv->ch_wn[idx].stat);
+		writel_relaxed(0xFFFFFFFF, &mhu->recv->ch_wn[idx].stat_clear);
+	}
+
+	return msg;
+}
+
+static void mhuv2_data_transfer_tx_startup(struct mhuv2 *mhu,
+					   struct mbox_chan *chan)
+{
+	struct mhuv2_mbox_chan_priv *priv = chan->con_priv;
+	int i = priv->ch_wn_idx + priv->windows - 1;
+
+	/* Enable interrupts only for the last window */
+	if (mhu->minor) {
+		writel_relaxed(0x1, &mhu->send->ch_wn[i].int_clr);
+		writel_relaxed(0x1, &mhu->send->ch_wn[i].int_en);
+	}
+}
+
+static void mhuv2_data_transfer_tx_shutdown(struct mhuv2 *mhu,
+					    struct mbox_chan *chan)
+{
+	struct mhuv2_mbox_chan_priv *priv = chan->con_priv;
+	int i = priv->ch_wn_idx + priv->windows - 1;
+
+	if (mhu->minor)
+		writel_relaxed(0x0, &mhu->send->ch_wn[i].int_en);
+}
+
+static int mhuv2_data_transfer_last_tx_done(struct mhuv2 *mhu,
+					    struct mbox_chan *chan)
+{
+	struct mhuv2_mbox_chan_priv *priv = chan->con_priv;
+	int i = priv->ch_wn_idx + priv->windows - 1;
+
+	/* Just checking the last channel window should be enough */
+	return !readl_relaxed(&mhu->send->ch_wn[i].stat);
+}
+
+/*
+ * Message will be transmitted from most significant to least significant word.
+ * This is to allow for messages shorter than channel windows to still trigger
+ * the receiver interrupt which gets activated when the last stat register is
+ * written. As an example, a 6-word message is to be written on a 4-channel MHU
+ * connection: Registers marked with '*' are masked, and will not generate an
+ * interrupt on the receiver side once written.
+ *
+ * u32 *data =	[0x00000001], [0x00000002], [0x00000003], [0x00000004],
+ *		[0x00000005], [0x00000006]
+ *
+ * ROUND 1:
+ * stat reg		To write	Write sequence
+ * [ stat 3 ]	<-	[0x00000001]	4 <- triggers interrupt on receiver
+ * [ stat 2 ]	<-	[0x00000002]	3
+ * [ stat 1 ]	<-	[0x00000003]	2
+ * [ stat 0 ]	<-	[0x00000004]	1
+ *
+ * data += 4 // Increment data pointer by number of stat regs
+ *
+ * ROUND 2:
+ * stat reg		To write	Write sequence
+ * [ stat 3 ]	<-	[0x00000005]	2 <- triggers interrupt on receiver
+ * [ stat 2 ]	<-	[0x00000006]	1
+ * [ stat 1 ]	<-	[0x00000000]
+ * [ stat 0 ]	<-	[0x00000000]
+ */
+static int mhuv2_data_transfer_send_data(struct mhuv2 *mhu,
+					 struct mbox_chan *chan, void *arg)
+{
+	const struct arm_mhuv2_mbox_msg *msg = arg;
+	int bytes_left = msg->len, bytes_to_send, bytes_in_round, i;
+	struct mhuv2_mbox_chan_priv *priv = chan->con_priv;
+	int windows = priv->windows;
+	u32 *data = msg->data, word;
+
+	while (bytes_left) {
+		if (!data[0]) {
+			dev_err(mhu->mbox.dev, "Data aligned at first window can't be zero to guarantee interrupt generation at receiver");
+			return -EINVAL;
+		}
+
+		while(!mhuv2_data_transfer_last_tx_done(mhu, chan))
+			continue;
+
+		bytes_in_round = min(bytes_left, (int)(windows * MHUV2_STAT_BYTES));
+
+		for (i = windows - 1; i >= 0; i--) {
+			/* Data less than windows can transfer ? */
+			if (unlikely(bytes_in_round <= i * MHUV2_STAT_BYTES))
+				continue;
+
+			word = data[i];
+			bytes_to_send = bytes_in_round & (MHUV2_STAT_BYTES - 1);
+			if (unlikely(bytes_to_send))
+				word &= LSB_MASK(bytes_to_send);
+			else
+				bytes_to_send = MHUV2_STAT_BYTES;
+
+			writel_relaxed(word, &mhu->send->ch_wn[priv->ch_wn_idx + windows - 1 - i].stat_set);
+			bytes_left -= bytes_to_send;
+			bytes_in_round -= bytes_to_send;
+		}
+
+		data += windows;
+	}
+
+	return 0;
+}
+
+static const struct mhuv2_protocol_ops mhuv2_data_transfer_ops = {
+	.rx_startup = mhuv2_data_transfer_rx_startup,
+	.rx_shutdown = mhuv2_data_transfer_rx_shutdown,
+	.read_data = mhuv2_data_transfer_read_data,
+	.tx_startup = mhuv2_data_transfer_tx_startup,
+	.tx_shutdown = mhuv2_data_transfer_tx_shutdown,
+	.last_tx_done = mhuv2_data_transfer_last_tx_done,
+	.send_data = mhuv2_data_transfer_send_data,
+};
+
+/* Interrupt handlers */
+
+static struct mbox_chan *get_irq_chan_comb(struct mhuv2 *mhu, u32 *reg)
+{
+	struct mbox_chan *chans = mhu->mbox.chans;
+	int channel = 0, i, offset = 0, windows, protocol, ch_wn;
+	u32 stat;
+
+	for (i = 0; i < MHUV2_CMB_INT_ST_REG_CNT; i++) {
+		stat = readl_relaxed(reg + i);
+		if (!stat)
+			continue;
+
+		ch_wn = i * MHUV2_STAT_BITS + __builtin_ctz(stat);
+
+		for (i = 0; i < mhu->length; i += 2) {
+			protocol = mhu->protocols[i];
+			windows = mhu->protocols[i + 1];
+
+			if (ch_wn >= offset + windows) {
+				if (protocol == DOORBELL)
+					channel += MHUV2_STAT_BITS * windows;
+				else
+					channel++;
+
+				offset += windows;
+				continue;
+			}
+
+			/* Return first chan of the window in doorbell mode */
+			if (protocol == DOORBELL)
+				channel += MHUV2_STAT_BITS * (ch_wn - offset);
+
+			return &chans[channel];
+		}
+	}
+
+	return ERR_PTR(-EIO);
+}
+
+static irqreturn_t mhuv2_sender_interrupt(int irq, void *data)
+{
+	struct mhuv2 *mhu = data;
+	struct device *dev = mhu->mbox.dev;
+	struct mhuv2_mbox_chan_priv *priv;
+	struct mbox_chan *chan;
+	unsigned long flags;
+	int i, found = 0;
+	u32 stat;
+
+	chan = get_irq_chan_comb(mhu, mhu->send->chcomb_int_st);
+	if (IS_ERR(chan)) {
+		dev_warn(dev, "Failed to find channel for the Tx interrupt\n");
+		return IRQ_NONE;
+	}
+	priv = chan->con_priv;
+
+	if (!IS_PROTOCOL_DOORBELL(priv)) {
+		writel_relaxed(1, &mhu->send->ch_wn[priv->ch_wn_idx + priv->windows - 1].int_clr);
+
+		if (chan->cl) {
+			mbox_chan_txdone(chan, 0);
+			return IRQ_HANDLED;
+		}
+
+		dev_warn(dev, "Tx interrupt Received on channel (%u) not currently attached to a mailbox client\n",
+			 priv->ch_wn_idx);
+		return IRQ_NONE;
+	}
+
+	/* Clear the interrupt first, so we don't miss any doorbell later */
+	writel_relaxed(1, &mhu->send->ch_wn[priv->ch_wn_idx].int_clr);
+
+	/*
+	 * In Doorbell mode, make sure no new transitions happen while the
+	 * interrupt handler is trying to find the finished doorbell tx
+	 * operations, else we may think few of the transfers were complete
+	 * before they actually were.
+	 */
+	spin_lock_irqsave(&mhu->doorbell_pending_lock, flags);
+
+	/*
+	 * In case of doorbell mode, the first channel of the window is returned
+	 * by get_irq_chan_comb(). Find all the pending channels here.
+	 */
+	stat = readl_relaxed(&mhu->send->ch_wn[priv->ch_wn_idx].stat);
+
+	for (i = 0; i < MHUV2_STAT_BITS; i++) {
+		priv = chan[i].con_priv;
+
+		/* Find cases where pending was 1, but stat's bit is cleared */
+		if (priv->pending ^ ((stat >> i) & 0x1)) {
+			BUG_ON(!priv->pending);
+
+			if (!chan->cl) {
+				dev_warn(dev, "Tx interrupt received on doorbell (%u : %u) channel not currently attached to a mailbox client\n",
+					 priv->ch_wn_idx, i);
+				continue;
+			}
+
+			mbox_chan_txdone(&chan[i], 0);
+			priv->pending = 0;
+			found++;
+		}
+	}
+
+	spin_unlock_irqrestore(&mhu->doorbell_pending_lock, flags);
+
+	if (!found) {
+		/*
+		 * We may have already processed the doorbell in the previous
+		 * iteration if the interrupt came right after we cleared it but
+		 * before we read the stat register.
+		 */
+		dev_dbg(dev, "Couldn't find the doorbell (%u) for the Tx interrupt interrupt\n",
+			priv->ch_wn_idx);
+		return IRQ_NONE;
+	}
+
+	return IRQ_HANDLED;
+}
+
+static struct mbox_chan *get_irq_chan_comb_rx(struct mhuv2 *mhu)
+{
+	struct mhuv2_mbox_chan_priv *priv;
+	struct mbox_chan *chan;
+	u32 stat;
+
+	chan = get_irq_chan_comb(mhu, mhu->recv->chcomb_int_st);
+	if (IS_ERR(chan))
+		return chan;
+
+	priv = chan->con_priv;
+	if (!IS_PROTOCOL_DOORBELL(priv))
+		return chan;
+
+	/*
+	 * In case of doorbell mode, the first channel of the window is returned
+	 * by the routine. Find the exact channel here.
+	 */
+	stat = readl_relaxed(&mhu->recv->ch_wn[priv->ch_wn_idx].stat_masked);
+	BUG_ON(!stat);
+
+	return chan + __builtin_ctz(stat);
+}
+
+static struct mbox_chan *get_irq_chan_stat_rx(struct mhuv2 *mhu)
+{
+	struct mbox_chan *chans = mhu->mbox.chans;
+	struct mhuv2_mbox_chan_priv *priv;
+	u32 stat;
+	int i = 0;
+
+	while (i < mhu->mbox.num_chans) {
+		priv = chans[i].con_priv;
+		stat = readl_relaxed(&mhu->recv->ch_wn[priv->ch_wn_idx].stat_masked);
+
+		if (stat) {
+			if (IS_PROTOCOL_DOORBELL(priv))
+				i += __builtin_ctz(stat);
+			return &chans[i];
+		}
+
+		i += IS_PROTOCOL_DOORBELL(priv) ? MHUV2_STAT_BITS : 1;
+	}
+
+	return ERR_PTR(-EIO);
+}
+
+static struct mbox_chan *get_irq_chan_rx(struct mhuv2 *mhu)
+{
+	if (!mhu->minor)
+		return get_irq_chan_stat_rx(mhu);
+
+	return get_irq_chan_comb_rx(mhu);
+}
+
+static irqreturn_t mhuv2_receiver_interrupt(int irq, void *arg)
+{
+	struct mhuv2 *mhu = arg;
+	struct mbox_chan *chan = get_irq_chan_rx(mhu);
+	struct device *dev = mhu->mbox.dev;
+	struct mhuv2_mbox_chan_priv *priv;
+	int ret = IRQ_NONE;
+	void *data;
+
+	if (IS_ERR(chan)) {
+		dev_warn(dev, "Failed to find channel for the rx interrupt\n");
+		return IRQ_NONE;
+	}
+	priv = chan->con_priv;
+
+	/* Read and clear the data first */
+	data = priv->ops->read_data(mhu, chan);
+
+	if (!chan->cl) {
+		dev_warn(dev, "Received data on channel (%u) not currently attached to a mailbox client\n",
+			 priv->ch_wn_idx);
+	} else if (IS_ERR(data)) {
+		dev_err(dev, "Failed to read data: %lu\n", PTR_ERR(data));
+	} else {
+		mbox_chan_received_data(chan, data);
+		ret = IRQ_HANDLED;
+	}
+
+	kfree(data);
+	return ret;
+}
+
+/* Sender and receiver ops */
+static bool mhuv2_sender_last_tx_done(struct mbox_chan *chan)
+{
+	struct mhuv2 *mhu = mhu_from_mbox(chan->mbox);
+	struct mhuv2_mbox_chan_priv *priv = chan->con_priv;
+
+	return priv->ops->last_tx_done(mhu, chan);
+}
+
+static int mhuv2_sender_send_data(struct mbox_chan *chan, void *data)
+{
+	struct mhuv2 *mhu = mhu_from_mbox(chan->mbox);
+	struct mhuv2_mbox_chan_priv *priv = chan->con_priv;
+
+	if (!priv->ops->last_tx_done(mhu, chan))
+		return -EBUSY;
+
+	return priv->ops->send_data(mhu, chan, data);
+}
+
+static int mhuv2_sender_startup(struct mbox_chan *chan)
+{
+	struct mhuv2 *mhu = mhu_from_mbox(chan->mbox);
+	struct mhuv2_mbox_chan_priv *priv = chan->con_priv;
+
+	if (priv->ops->tx_startup)
+		priv->ops->tx_startup(mhu, chan);
+	return 0;
+}
+
+static void mhuv2_sender_shutdown(struct mbox_chan *chan)
+{
+	struct mhuv2 *mhu = mhu_from_mbox(chan->mbox);
+	struct mhuv2_mbox_chan_priv *priv = chan->con_priv;
+
+	if (priv->ops->tx_shutdown)
+		priv->ops->tx_shutdown(mhu, chan);
+}
+
+static const struct mbox_chan_ops mhuv2_sender_ops = {
+	.send_data = mhuv2_sender_send_data,
+	.startup = mhuv2_sender_startup,
+	.shutdown = mhuv2_sender_shutdown,
+	.last_tx_done = mhuv2_sender_last_tx_done,
+};
+
+static int mhuv2_receiver_startup(struct mbox_chan *chan)
+{
+	struct mhuv2 *mhu = mhu_from_mbox(chan->mbox);
+	struct mhuv2_mbox_chan_priv *priv = chan->con_priv;
+
+	return priv->ops->rx_startup(mhu, chan);
+}
+
+static void mhuv2_receiver_shutdown(struct mbox_chan *chan)
+{
+	struct mhuv2 *mhu = mhu_from_mbox(chan->mbox);
+	struct mhuv2_mbox_chan_priv *priv = chan->con_priv;
+
+	priv->ops->rx_shutdown(mhu, chan);
+}
+
+static int mhuv2_receiver_send_data(struct mbox_chan *chan, void *data)
+{
+	dev_err(chan->mbox->dev,
+		"Trying to transmit on a receiver MHU frame\n");
+	return -EIO;
+}
+
+static bool mhuv2_receiver_last_tx_done(struct mbox_chan *chan)
+{
+	dev_err(chan->mbox->dev, "Trying to Tx poll on a receiver MHU frame\n");
+	return true;
+}
+
+static const struct mbox_chan_ops mhuv2_receiver_ops = {
+	.send_data = mhuv2_receiver_send_data,
+	.startup = mhuv2_receiver_startup,
+	.shutdown = mhuv2_receiver_shutdown,
+	.last_tx_done = mhuv2_receiver_last_tx_done,
+};
+
+static struct mbox_chan *mhuv2_mbox_of_xlate(struct mbox_controller *mbox,
+					     const struct of_phandle_args *pa)
+{
+	struct mhuv2 *mhu = mhu_from_mbox(mbox);
+	struct mbox_chan *chans = mbox->chans;
+	int channel = 0, i, offset, doorbell, protocol, windows;
+
+	if (pa->args_count != 2)
+		return ERR_PTR(-EINVAL);
+
+	offset = pa->args[0];
+	doorbell = pa->args[1];
+	if (doorbell >= MHUV2_STAT_BITS)
+		goto out;
+
+	for (i = 0; i < mhu->length; i += 2) {
+		protocol = mhu->protocols[i];
+		windows = mhu->protocols[i + 1];
+
+		if (protocol == DOORBELL) {
+			if (offset < windows)
+				return &chans[channel + MHUV2_STAT_BITS * offset + doorbell];
+
+			channel += MHUV2_STAT_BITS * windows;
+			offset -= windows;
+		} else {
+			if (offset == 0) {
+				if (doorbell)
+					goto out;
+
+				return &chans[channel];
+			}
+
+			channel++;
+			offset--;
+		}
+	}
+
+out:
+	dev_err(mbox->dev, "Couldn't xlate to a valid channel (%d: %d)\n",
+		pa->args[0], doorbell);
+	return ERR_PTR(-ENODEV);
+}
+
+static int mhuv2_verify_protocol(struct mhuv2 *mhu)
+{
+	struct device *dev = mhu->mbox.dev;
+	int protocol, windows, channels = 0, total_windows = 0, i;
+
+	for (i = 0; i < mhu->length; i += 2) {
+		protocol = mhu->protocols[i];
+		windows = mhu->protocols[i + 1];
+
+		if (!windows) {
+			dev_err(dev, "Window size can't be zero (%d)\n", i);
+			return -EINVAL;
+		}
+		total_windows += windows;
+
+		if (protocol == DOORBELL) {
+			channels += MHUV2_STAT_BITS * windows;
+		} else if (protocol == DATA_TRANSFER) {
+			channels++;
+		} else {
+			dev_err(dev, "Invalid protocol (%d) present in %s property at index %d\n",
+				protocol, MHUV2_PROTOCOL_PROP, i);
+			return -EINVAL;
+		}
+	}
+
+	if (total_windows > mhu->windows) {
+		dev_err(dev, "Channel windows can't be more than what's implemented by the hardware ( %d: %d)\n",
+			total_windows, mhu->windows);
+		return -EINVAL;
+	}
+
+	mhu->mbox.num_chans = channels;
+	return 0;
+}
+
+static int mhuv2_allocate_channels(struct mhuv2 *mhu)
+{
+	struct mbox_controller *mbox = &mhu->mbox;
+	struct mhuv2_mbox_chan_priv *priv;
+	struct device *dev = mbox->dev;
+	struct mbox_chan *chans;
+	int protocol, windows = 0, next_window = 0, i, j, k;
+
+	chans = devm_kcalloc(dev, mbox->num_chans, sizeof(*chans), GFP_KERNEL);
+	if (!chans)
+		return -ENOMEM;
+
+	mbox->chans = chans;
+
+	for (i = 0; i < mhu->length; i += 2) {
+		next_window += windows;
+
+		protocol = mhu->protocols[i];
+		windows = mhu->protocols[i + 1];
+
+		if (protocol == DATA_TRANSFER) {
+			priv = devm_kmalloc(dev, sizeof(*priv), GFP_KERNEL);
+			if (!priv)
+				return -ENOMEM;
+
+			priv->ch_wn_idx = next_window;
+			priv->ops = &mhuv2_data_transfer_ops;
+			priv->windows = windows;
+			chans++->con_priv = priv;
+			continue;
+		}
+
+		for (j = 0; j < windows; j++) {
+			for (k = 0; k < MHUV2_STAT_BITS; k++) {
+				priv = devm_kmalloc(dev, sizeof(*priv), GFP_KERNEL);
+				if (!priv)
+					return -ENOMEM;
+
+				priv->ch_wn_idx = next_window + j;
+				priv->ops = &mhuv2_doorbell_ops;
+				priv->doorbell = k;
+				chans++->con_priv = priv;
+			}
+
+			/*
+			 * Permanently enable interrupt as we can't
+			 * control it per doorbell.
+			 */
+			if (mhu->frame == SENDER_FRAME && mhu->minor)
+				writel_relaxed(0x1, &mhu->send->ch_wn[priv->ch_wn_idx].int_en);
+		}
+	}
+
+	/* Make sure we have initialized all channels */
+	BUG_ON(chans - mbox->chans != mbox->num_chans);
+
+	return 0;
+}
+
+static int mhuv2_parse_channels(struct mhuv2 *mhu)
+{
+	struct device *dev = mhu->mbox.dev;
+	const struct device_node *np = dev->of_node;
+	int ret, count;
+	u32 *protocols;
+
+	count = of_property_count_u32_elems(np, MHUV2_PROTOCOL_PROP);
+	if (count <= 0 || count % 2) {
+		dev_err(dev, "Invalid %s property (%d)\n", MHUV2_PROTOCOL_PROP,
+			count);
+		return -EINVAL;
+	}
+
+	protocols = devm_kmalloc_array(dev, count, sizeof(*protocols), GFP_KERNEL);
+	if (!protocols)
+		return -ENOMEM;
+
+	ret = of_property_read_u32_array(np, MHUV2_PROTOCOL_PROP, protocols, count);
+	if (ret) {
+		dev_err(dev, "Failed to read %s property: %d\n",
+			MHUV2_PROTOCOL_PROP, ret);
+		return ret;
+	}
+
+	mhu->protocols = protocols;
+	mhu->length = count;
+
+	ret = mhuv2_verify_protocol(mhu);
+	if (ret)
+		return ret;
+
+	return mhuv2_allocate_channels(mhu);
+}
+
+static int mhuv2_tx_init(struct amba_device *adev, struct mhuv2 *mhu,
+			 void __iomem *reg)
+{
+	struct device *dev = mhu->mbox.dev;
+	int ret, i;
+
+	mhu->frame = SENDER_FRAME;
+	mhu->mbox.ops = &mhuv2_sender_ops;
+	mhu->send = reg;
+
+	mhu->windows = readl_relaxed_bitfield(&mhu->send->mhu_cfg, num_ch);
+	mhu->minor = readl_relaxed_bitfield(&mhu->send->aidr, arch_minor_rev);
+
+	spin_lock_init(&mhu->doorbell_pending_lock);
+
+	/*
+	 * For minor version 1 and forward, tx interrupt is provided by
+	 * the controller.
+	 */
+	if (mhu->minor && adev->irq[0]) {
+		ret = devm_request_threaded_irq(dev, adev->irq[0], NULL,
+						mhuv2_sender_interrupt,
+						IRQF_ONESHOT, "mhuv2-tx", mhu);
+		if (ret) {
+			dev_err(dev, "Failed to request tx IRQ, fallback to polling mode: %d\n",
+				ret);
+		} else {
+			mhu->mbox.txdone_irq = true;
+			mhu->mbox.txdone_poll = false;
+			mhu->irq = adev->irq[0];
+
+			writel_relaxed_bitfield(1, &mhu->send->int_en, chcomb);
+
+			/* Disable all channel interrupts */
+			for (i = 0; i < mhu->windows; i++)
+				writel_relaxed(0x0, &mhu->send->ch_wn[i].int_en);
+
+			goto out;
+		}
+	}
+
+	mhu->mbox.txdone_irq = false;
+	mhu->mbox.txdone_poll = true;
+	mhu->mbox.txpoll_period = 1;
+
+out:
+	/* Wait for receiver to be ready */
+	writel_relaxed(0x1, &mhu->send->access_request);
+	while (!readl_relaxed(&mhu->send->access_ready))
+		continue;
+
+	return 0;
+}
+
+static int mhuv2_rx_init(struct amba_device *adev, struct mhuv2 *mhu,
+			 void __iomem *reg)
+{
+	struct device *dev = mhu->mbox.dev;
+	int ret, i;
+
+	mhu->frame = RECEIVER_FRAME;
+	mhu->mbox.ops = &mhuv2_receiver_ops;
+	mhu->recv = reg;
+
+	mhu->windows = readl_relaxed_bitfield(&mhu->recv->mhu_cfg, num_ch);
+	mhu->minor = readl_relaxed_bitfield(&mhu->recv->aidr, arch_minor_rev);
+
+	mhu->irq = adev->irq[0];
+	if (!mhu->irq) {
+		dev_err(dev, "Missing receiver IRQ\n");
+		return -EINVAL;
+	}
+
+	ret = devm_request_threaded_irq(dev, mhu->irq, NULL,
+					mhuv2_receiver_interrupt, IRQF_ONESHOT,
+					"mhuv2-rx", mhu);
+	if (ret) {
+		dev_err(dev, "Failed to request rx IRQ\n");
+		return ret;
+	}
+
+	/* Mask all the channel windows */
+	for (i = 0; i < mhu->windows; i++)
+		writel_relaxed(0xFFFFFFFF, &mhu->recv->ch_wn[i].mask_set);
+
+	if (mhu->minor)
+		writel_relaxed_bitfield(1, &mhu->recv->int_en, chcomb);
+
+	return 0;
+}
+
+static int mhuv2_probe(struct amba_device *adev, const struct amba_id *id)
+{
+	struct device *dev = &adev->dev;
+	const struct device_node *np = dev->of_node;
+	struct mhuv2 *mhu;
+	void __iomem *reg;
+	int ret = -EINVAL;
+
+	reg = devm_of_iomap(dev, dev->of_node, 0, NULL);
+	if (!reg)
+		return -ENOMEM;
+
+	mhu = devm_kzalloc(dev, sizeof(*mhu), GFP_KERNEL);
+	if (!mhu)
+		return -ENOMEM;
+
+	mhu->mbox.dev = dev;
+	mhu->mbox.of_xlate = mhuv2_mbox_of_xlate;
+
+	if (of_device_is_compatible(np, "arm,mhuv2-tx"))
+		ret = mhuv2_tx_init(adev, mhu, reg);
+	else if (of_device_is_compatible(np, "arm,mhuv2-rx"))
+		ret = mhuv2_rx_init(adev, mhu, reg);
+	else
+		dev_err(dev, "Invalid compatible property\n");
+
+	if (ret)
+		return ret;
+
+	/* Channel windows can't be 0 */
+	BUG_ON(!mhu->windows);
+
+	ret = mhuv2_parse_channels(mhu);
+	if (ret)
+		return ret;
+
+	amba_set_drvdata(adev, mhu);
+
+	ret = devm_mbox_controller_register(dev, &mhu->mbox);
+	if (ret)
+		dev_err(dev, "failed to register ARM MHUv2 driver %d\n", ret);
+
+	return ret;
+}
+
+static int mhuv2_remove(struct amba_device *adev)
+{
+	struct mhuv2 *mhu = amba_get_drvdata(adev);
+
+	if (mhu->frame == SENDER_FRAME)
+		writel_relaxed(0x0, &mhu->send->access_request);
+
+	return 0;
+}
+
+static struct amba_id mhuv2_ids[] = {
+	{
+		/* 2.0 */
+		.id = 0xbb0d1,
+		.mask = 0xfffff,
+	},
+	{
+		/* 2.1 */
+		.id = 0xbb076,
+		.mask = 0xfffff,
+	},
+	{ 0, 0 },
+};
+MODULE_DEVICE_TABLE(amba, mhuv2_ids);
+
+static struct amba_driver mhuv2_driver = {
+	.drv = {
+		.name	= "arm-mhuv2",
+	},
+	.id_table	= mhuv2_ids,
+	.probe		= mhuv2_probe,
+	.remove		= mhuv2_remove,
+};
+module_amba_driver(mhuv2_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("ARM MHUv2 Driver");
+MODULE_AUTHOR("Viresh Kumar <viresh.kumar@linaro.org>");
+MODULE_AUTHOR("Tushar Khandelwal <tushar.khandelwal@arm.com>");
diff --git a/include/linux/mailbox/arm_mhuv2_message.h b/include/linux/mailbox/arm_mhuv2_message.h
new file mode 100644
index 000000000000..821b9d96daa4
--- /dev/null
+++ b/include/linux/mailbox/arm_mhuv2_message.h
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ARM MHUv2 Mailbox Message
+ *
+ * Copyright (C) 2020 Arm Ltd.
+ * Copyright (C) 2020 Linaro Ltd.
+ */
+
+#ifndef _LINUX_ARM_MHUV2_MESSAGE_H_
+#define _LINUX_ARM_MHUV2_MESSAGE_H_
+
+#include <linux/types.h>
+
+/* Data structure for data-transfer protocol */
+struct arm_mhuv2_mbox_msg {
+	void *data;
+	size_t len;
+};
+
+#endif /* _LINUX_ARM_MHUV2_MESSAGE_H_ */
-- 
cgit v1.2.3


From d40c2d4ed62df64ce603c208bceff25245380157 Mon Sep 17 00:00:00 2001
From: Hsin-Hsiung Wang <hsin-hsiung.wang@mediatek.com>
Date: Wed, 9 Dec 2020 18:33:43 -0800
Subject: spmi: Add driver shutdown support

Add new shutdown() method.  Use it in the standard driver model style.

Link: https://lore.kernel.org/r/1603187810-30481-2-git-send-email-hsin-hsiung.wang@mediatek.com
Signed-off-by: Hsin-Hsiung Wang <hsin-hsiung.wang@mediatek.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
Link: https://lore.kernel.org/r/20201210023344.2838141-4-sboyd@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/spmi/spmi.c  | 9 +++++++++
 include/linux/spmi.h | 1 +
 2 files changed, 10 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/spmi/spmi.c b/drivers/spmi/spmi.c
index 253340e10dab..51f5aeb65b3b 100644
--- a/drivers/spmi/spmi.c
+++ b/drivers/spmi/spmi.c
@@ -359,6 +359,14 @@ static int spmi_drv_remove(struct device *dev)
 	return 0;
 }
 
+static void spmi_drv_shutdown(struct device *dev)
+{
+	const struct spmi_driver *sdrv = to_spmi_driver(dev->driver);
+
+	if (sdrv && sdrv->shutdown)
+		sdrv->shutdown(to_spmi_device(dev));
+}
+
 static int spmi_drv_uevent(struct device *dev, struct kobj_uevent_env *env)
 {
 	int ret;
@@ -375,6 +383,7 @@ static struct bus_type spmi_bus_type = {
 	.match		= spmi_device_match,
 	.probe		= spmi_drv_probe,
 	.remove		= spmi_drv_remove,
+	.shutdown	= spmi_drv_shutdown,
 	.uevent		= spmi_drv_uevent,
 };
 
diff --git a/include/linux/spmi.h b/include/linux/spmi.h
index 394a3f68bad5..729bcbf9f5ad 100644
--- a/include/linux/spmi.h
+++ b/include/linux/spmi.h
@@ -138,6 +138,7 @@ struct spmi_driver {
 	struct device_driver driver;
 	int	(*probe)(struct spmi_device *sdev);
 	void	(*remove)(struct spmi_device *sdev);
+	void	(*shutdown)(struct spmi_device *sdev);
 };
 
 static inline struct spmi_driver *to_spmi_driver(struct device_driver *d)
-- 
cgit v1.2.3


From 1c12c27086dcef853832a7cbebcb48bdac8104b6 Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Date: Wed, 25 Nov 2020 10:31:06 +0100
Subject: siox: Make remove callback return void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The driver core ignores the return value of the remove callback, so
don't give siox drivers the chance to provide a value.

All siox drivers only allocate devm-managed resources in
.probe, so there is no .remove callback to fix.

Tested-by: Thorsten Scherer <t.scherer@eckelmann.de>
Acked-by: Thorsten Scherer <t.scherer@eckelmann.de>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20201125093106.240643-3-u.kleine-koenig@pengutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/siox/siox-core.c | 5 ++---
 include/linux/siox.h     | 2 +-
 2 files changed, 3 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/siox/siox-core.c b/drivers/siox/siox-core.c
index b56cdcb52967..1794ff0106bc 100644
--- a/drivers/siox/siox-core.c
+++ b/drivers/siox/siox-core.c
@@ -525,12 +525,11 @@ static int siox_remove(struct device *dev)
 	struct siox_driver *sdriver =
 		container_of(dev->driver, struct siox_driver, driver);
 	struct siox_device *sdevice = to_siox_device(dev);
-	int ret = 0;
 
 	if (sdriver->remove)
-		ret = sdriver->remove(sdevice);
+		sdriver->remove(sdevice);
 
-	return ret;
+	return 0;
 }
 
 static void siox_shutdown(struct device *dev)
diff --git a/include/linux/siox.h b/include/linux/siox.h
index da7225bf1877..6bfbda3f634c 100644
--- a/include/linux/siox.h
+++ b/include/linux/siox.h
@@ -36,7 +36,7 @@ bool siox_device_connected(struct siox_device *sdevice);
 
 struct siox_driver {
 	int (*probe)(struct siox_device *sdevice);
-	int (*remove)(struct siox_device *sdevice);
+	void (*remove)(struct siox_device *sdevice);
 	void (*shutdown)(struct siox_device *sdevice);
 
 	/*
-- 
cgit v1.2.3


From 0aec2da436623abe19b80b21dd9fc5ec9300a152 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 9 Dec 2020 22:36:38 +0200
Subject: driver core: platform: Introduce platform_get_mem_or_io()

There are at least few existing users of the proposed API which
retrieves either MEM or IO resource from platform device.

Make it common to utilize in the existing and new users.

Cc: Eric Auger <eric.auger@redhat.com>
Cc: Alex Williamson <alex.williamson@redhat.com>
Cc: kvm@vger.kernel.org
Cc: linux-usb@vger.kernel.org
Cc: Peng Hao <peng.hao2@zte.com.cn>
Cc: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20201209203642.27648-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/platform.c         | 15 +++++++++++++++
 include/linux/platform_device.h |  3 +++
 2 files changed, 18 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index 8ad06daa2eaa..0358dc3ea3ad 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -63,6 +63,21 @@ struct resource *platform_get_resource(struct platform_device *dev,
 }
 EXPORT_SYMBOL_GPL(platform_get_resource);
 
+struct resource *platform_get_mem_or_io(struct platform_device *dev,
+					unsigned int num)
+{
+	u32 i;
+
+	for (i = 0; i < dev->num_resources; i++) {
+		struct resource *r = &dev->resource[i];
+
+		if ((resource_type(r) & (IORESOURCE_MEM|IORESOURCE_IO)) && num-- == 0)
+			return r;
+	}
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(platform_get_mem_or_io);
+
 #ifdef CONFIG_HAS_IOMEM
 /**
  * devm_platform_get_and_ioremap_resource - call devm_ioremap_resource() for a
diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h
index 77a2aada106d..ee6a9f10c2c7 100644
--- a/include/linux/platform_device.h
+++ b/include/linux/platform_device.h
@@ -52,6 +52,9 @@ extern struct device platform_bus;
 
 extern struct resource *platform_get_resource(struct platform_device *,
 					      unsigned int, unsigned int);
+extern struct resource *platform_get_mem_or_io(struct platform_device *,
+					       unsigned int);
+
 extern struct device *
 platform_find_device_by_driver(struct device *start,
 			       const struct device_driver *drv);
-- 
cgit v1.2.3


From 1f702603e7125a390b5cdf5ce00539781cfcc86a Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 20 Nov 2020 17:14:19 -0600
Subject: exec: Simplify unshare_files

Now that exec no longer needs to return the unshared files to their
previous value there is no reason to return displaced.

Instead when unshare_fd creates a copy of the file table, call
put_files_struct before returning from unshare_files.

Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
v1: https://lkml.kernel.org/r/20200817220425.9389-2-ebiederm@xmission.com
Link: https://lkml.kernel.org/r/20201120231441.29911-2-ebiederm@xmission.com
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
---
 fs/coredump.c           |  5 +----
 fs/exec.c               |  5 +----
 include/linux/fdtable.h |  2 +-
 kernel/fork.c           | 12 ++++++------
 4 files changed, 9 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/fs/coredump.c b/fs/coredump.c
index 0cd9056d79cc..abf807235262 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -585,7 +585,6 @@ void do_coredump(const kernel_siginfo_t *siginfo)
 	int ispipe;
 	size_t *argv = NULL;
 	int argc = 0;
-	struct files_struct *displaced;
 	/* require nonrelative corefile path and be extra careful */
 	bool need_suid_safe = false;
 	bool core_dumped = false;
@@ -791,11 +790,9 @@ void do_coredump(const kernel_siginfo_t *siginfo)
 	}
 
 	/* get us an unshared descriptor table; almost always a no-op */
-	retval = unshare_files(&displaced);
+	retval = unshare_files();
 	if (retval)
 		goto close_fail;
-	if (displaced)
-		put_files_struct(displaced);
 	if (!dump_interrupted()) {
 		/*
 		 * umh disabled with CONFIG_STATIC_USERMODEHELPER_PATH="" would
diff --git a/fs/exec.c b/fs/exec.c
index 0d6533ab1c97..48fa4fc1b116 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1238,7 +1238,6 @@ void __set_task_comm(struct task_struct *tsk, const char *buf, bool exec)
 int begin_new_exec(struct linux_binprm * bprm)
 {
 	struct task_struct *me = current;
-	struct files_struct *displaced;
 	int retval;
 
 	/* Once we are committed compute the creds */
@@ -1259,11 +1258,9 @@ int begin_new_exec(struct linux_binprm * bprm)
 		goto out;
 
 	/* Ensure the files table is not shared. */
-	retval = unshare_files(&displaced);
+	retval = unshare_files();
 	if (retval)
 		goto out;
-	if (displaced)
-		put_files_struct(displaced);
 
 	/*
 	 * Must be called _before_ exec_mmap() as bprm->mm is
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index a32bf47c593e..f46a084b60b2 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -109,7 +109,7 @@ struct task_struct;
 struct files_struct *get_files_struct(struct task_struct *);
 void put_files_struct(struct files_struct *fs);
 void reset_files_struct(struct files_struct *);
-int unshare_files(struct files_struct **);
+int unshare_files(void);
 struct files_struct *dup_fd(struct files_struct *, unsigned, int *) __latent_entropy;
 void do_close_on_exec(struct files_struct *);
 int iterate_fd(struct files_struct *, unsigned,
diff --git a/kernel/fork.c b/kernel/fork.c
index 32083db7a2a2..837b546528c8 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -3023,21 +3023,21 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
  *	the exec layer of the kernel.
  */
 
-int unshare_files(struct files_struct **displaced)
+int unshare_files(void)
 {
 	struct task_struct *task = current;
-	struct files_struct *copy = NULL;
+	struct files_struct *old, *copy = NULL;
 	int error;
 
 	error = unshare_fd(CLONE_FILES, NR_OPEN_MAX, &copy);
-	if (error || !copy) {
-		*displaced = NULL;
+	if (error || !copy)
 		return error;
-	}
-	*displaced = task->files;
+
+	old = task->files;
 	task_lock(task);
 	task->files = copy;
 	task_unlock(task);
+	put_files_struct(old);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 950db38ff2c01b7aabbd7ab4a50b7992750fa63d Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 20 Nov 2020 17:14:20 -0600
Subject: exec: Remove reset_files_struct

Now that exec no longer needs to restore the previous value of current->files
on error there are no more callers of reset_files_struct so remove it.

Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
v1: https://lkml.kernel.org/r/20200817220425.9389-3-ebiederm@xmission.com
Link: https://lkml.kernel.org/r/20201120231441.29911-3-ebiederm@xmission.com
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
---
 fs/file.c               | 12 ------------
 include/linux/fdtable.h |  1 -
 2 files changed, 13 deletions(-)

(limited to 'include/linux')

diff --git a/fs/file.c b/fs/file.c
index 4559b5fec3bd..beae7c55c84c 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -436,18 +436,6 @@ void put_files_struct(struct files_struct *files)
 	}
 }
 
-void reset_files_struct(struct files_struct *files)
-{
-	struct task_struct *tsk = current;
-	struct files_struct *old;
-
-	old = tsk->files;
-	task_lock(tsk);
-	tsk->files = files;
-	task_unlock(tsk);
-	put_files_struct(old);
-}
-
 void exit_files(struct task_struct *tsk)
 {
 	struct files_struct * files = tsk->files;
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index f46a084b60b2..7cc9885044d9 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -108,7 +108,6 @@ struct task_struct;
 
 struct files_struct *get_files_struct(struct task_struct *);
 void put_files_struct(struct files_struct *fs);
-void reset_files_struct(struct files_struct *);
 int unshare_files(void);
 struct files_struct *dup_fd(struct files_struct *, unsigned, int *) __latent_entropy;
 void do_close_on_exec(struct files_struct *);
-- 
cgit v1.2.3


From bebf684bf330915e6c96313ad7db89a5480fc9c2 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 20 Nov 2020 17:14:24 -0600
Subject: file: Rename __fcheck_files to files_lookup_fd_raw

The function fcheck despite it's comment is poorly named
as it has no callers that only check it's return value.
All of fcheck's callers use the returned file descriptor.
The same is true for fcheck_files and __fcheck_files.

A new less confusing name is needed.  In addition the names
of these functions are confusing as they do not report
the kind of locks that are needed to be held when these
functions are called making error prone to use them.

To remedy this I am making the base functio name lookup_fd
and will and prefixes and sufficies to indicate the rest
of the context.

Name the function (previously called __fcheck_files) that proceeds
from a struct files_struct, looks up the struct file of a file
descriptor, and requires it's callers to verify all of the appropriate
locks are held files_lookup_fd_raw.

The need for better names became apparent in the last round of
discussion of this set of changes[1].

[1] https://lkml.kernel.org/r/CAHk-=wj8BQbgJFLa+J0e=iT-1qpmCRTbPAJ8gd6MJQ=kbRPqyQ@mail.gmail.com
Link: https://lkml.kernel.org/r/20201120231441.29911-7-ebiederm@xmission.com
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
---
 fs/file.c               | 2 +-
 include/linux/fdtable.h | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/fs/file.c b/fs/file.c
index beae7c55c84c..b5591efb87f5 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -887,7 +887,7 @@ static unsigned long __fget_light(unsigned int fd, fmode_t mask)
 	struct file *file;
 
 	if (atomic_read(&files->count) == 1) {
-		file = __fcheck_files(files, fd);
+		file = files_lookup_fd_raw(files, fd);
 		if (!file || unlikely(file->f_mode & mask))
 			return 0;
 		return (unsigned long)file;
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index 7cc9885044d9..639933f37da9 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -80,7 +80,7 @@ struct dentry;
 /*
  * The caller must ensure that fd table isn't shared or hold rcu or file lock
  */
-static inline struct file *__fcheck_files(struct files_struct *files, unsigned int fd)
+static inline struct file *files_lookup_fd_raw(struct files_struct *files, unsigned int fd)
 {
 	struct fdtable *fdt = rcu_dereference_raw(files->fdt);
 
@@ -96,7 +96,7 @@ static inline struct file *fcheck_files(struct files_struct *files, unsigned int
 	RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&
 			   !lockdep_is_held(&files->file_lock),
 			   "suspicious rcu_dereference_check() usage");
-	return __fcheck_files(files, fd);
+	return files_lookup_fd_raw(files, fd);
 }
 
 /*
-- 
cgit v1.2.3


From 120ce2b0cd52abe73e8b16c23461eb14df5a87d8 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 20 Nov 2020 17:14:25 -0600
Subject: file: Factor files_lookup_fd_locked out of fcheck_files

To make it easy to tell where files->file_lock protection is being
used when looking up a file create files_lookup_fd_locked.  Only allow
this function to be called with the file_lock held.

Update the callers of fcheck and fcheck_files that are called with the
files->file_lock held to call files_lookup_fd_locked instead.

Hopefully this makes it easier to quickly understand what is going on.

The need for better names became apparent in the last round of
discussion of this set of changes[1].

[1] https://lkml.kernel.org/r/CAHk-=wj8BQbgJFLa+J0e=iT-1qpmCRTbPAJ8gd6MJQ=kbRPqyQ@mail.gmail.com
Link: https://lkml.kernel.org/r/20201120231441.29911-8-ebiederm@xmission.com
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
---
 fs/file.c               |  2 +-
 fs/locks.c              | 14 ++++++++------
 fs/proc/fd.c            |  2 +-
 include/linux/fdtable.h |  7 +++++++
 4 files changed, 17 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/fs/file.c b/fs/file.c
index b5591efb87f5..9d0e91168be1 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -1098,7 +1098,7 @@ static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags)
 
 	spin_lock(&files->file_lock);
 	err = expand_files(files, newfd);
-	file = fcheck(oldfd);
+	file = files_lookup_fd_locked(files, oldfd);
 	if (unlikely(!file))
 		goto Ebadf;
 	if (unlikely(err < 0)) {
diff --git a/fs/locks.c b/fs/locks.c
index 1f84a03601fe..148197c1b547 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -2539,14 +2539,15 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd,
 	 */
 	if (!error && file_lock->fl_type != F_UNLCK &&
 	    !(file_lock->fl_flags & FL_OFDLCK)) {
+		struct files_struct *files = current->files;
 		/*
 		 * We need that spin_lock here - it prevents reordering between
 		 * update of i_flctx->flc_posix and check for it done in
 		 * close(). rcu_read_lock() wouldn't do.
 		 */
-		spin_lock(&current->files->file_lock);
-		f = fcheck(fd);
-		spin_unlock(&current->files->file_lock);
+		spin_lock(&files->file_lock);
+		f = files_lookup_fd_locked(files, fd);
+		spin_unlock(&files->file_lock);
 		if (f != filp) {
 			file_lock->fl_type = F_UNLCK;
 			error = do_lock_file_wait(filp, cmd, file_lock);
@@ -2670,14 +2671,15 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd,
 	 */
 	if (!error && file_lock->fl_type != F_UNLCK &&
 	    !(file_lock->fl_flags & FL_OFDLCK)) {
+		struct files_struct *files = current->files;
 		/*
 		 * We need that spin_lock here - it prevents reordering between
 		 * update of i_flctx->flc_posix and check for it done in
 		 * close(). rcu_read_lock() wouldn't do.
 		 */
-		spin_lock(&current->files->file_lock);
-		f = fcheck(fd);
-		spin_unlock(&current->files->file_lock);
+		spin_lock(&files->file_lock);
+		f = files_lookup_fd_locked(files, fd);
+		spin_unlock(&files->file_lock);
 		if (f != filp) {
 			file_lock->fl_type = F_UNLCK;
 			error = do_lock_file_wait(filp, cmd, file_lock);
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index d58960f6ee52..2cca9bca3b3a 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -35,7 +35,7 @@ static int seq_show(struct seq_file *m, void *v)
 		unsigned int fd = proc_fd(m->private);
 
 		spin_lock(&files->file_lock);
-		file = fcheck_files(files, fd);
+		file = files_lookup_fd_locked(files, fd);
 		if (file) {
 			struct fdtable *fdt = files_fdtable(files);
 
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index 639933f37da9..fda4b81dd735 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -91,6 +91,13 @@ static inline struct file *files_lookup_fd_raw(struct files_struct *files, unsig
 	return NULL;
 }
 
+static inline struct file *files_lookup_fd_locked(struct files_struct *files, unsigned int fd)
+{
+	RCU_LOCKDEP_WARN(!lockdep_is_held(&files->file_lock),
+			   "suspicious rcu_dereference_check() usage");
+	return files_lookup_fd_raw(files, fd);
+}
+
 static inline struct file *fcheck_files(struct files_struct *files, unsigned int fd)
 {
 	RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&
-- 
cgit v1.2.3


From f36c2943274199cb8aef32ac96531ffb7c4b43d0 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 20 Nov 2020 17:14:26 -0600
Subject: file: Replace fcheck_files with files_lookup_fd_rcu

This change renames fcheck_files to files_lookup_fd_rcu.  All of the
remaining callers take the rcu_read_lock before calling this function
so the _rcu suffix is appropriate.  This change also tightens up the
debug check to verify that all callers hold the rcu_read_lock.

All callers that used to call files_check with the files->file_lock
held have now been changed to call files_lookup_fd_locked.

This change of name has helped remind me of which locks and which
guarantees are in place helping me to catch bugs later in the
patchset.

The need for better names became apparent in the last round of
discussion of this set of changes[1].

[1] https://lkml.kernel.org/r/CAHk-=wj8BQbgJFLa+J0e=iT-1qpmCRTbPAJ8gd6MJQ=kbRPqyQ@mail.gmail.com
Link: https://lkml.kernel.org/r/20201120231441.29911-9-ebiederm@xmission.com
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
---
 Documentation/filesystems/files.rst | 6 +++---
 fs/file.c                           | 4 ++--
 fs/proc/fd.c                        | 4 ++--
 include/linux/fdtable.h             | 7 +++----
 kernel/bpf/task_iter.c              | 2 +-
 kernel/kcmp.c                       | 2 +-
 6 files changed, 12 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/files.rst b/Documentation/filesystems/files.rst
index cbf8e57376bf..ea75acdb632c 100644
--- a/Documentation/filesystems/files.rst
+++ b/Documentation/filesystems/files.rst
@@ -62,7 +62,7 @@ the fdtable structure -
    be held.
 
 4. To look up the file structure given an fd, a reader
-   must use either fcheck() or fcheck_files() APIs. These
+   must use either fcheck() or files_lookup_fd_rcu() APIs. These
    take care of barrier requirements due to lock-free lookup.
 
    An example::
@@ -84,7 +84,7 @@ the fdtable structure -
    on ->f_count::
 
 	rcu_read_lock();
-	file = fcheck_files(files, fd);
+	file = files_lookup_fd_rcu(files, fd);
 	if (file) {
 		if (atomic_long_inc_not_zero(&file->f_count))
 			*fput_needed = 1;
@@ -104,7 +104,7 @@ the fdtable structure -
    lock-free, they must be installed using rcu_assign_pointer()
    API. If they are looked up lock-free, rcu_dereference()
    must be used. However it is advisable to use files_fdtable()
-   and fcheck()/fcheck_files() which take care of these issues.
+   and fcheck()/files_lookup_fd_rcu() which take care of these issues.
 
 7. While updating, the fdtable pointer must be looked up while
    holding files->file_lock. If ->file_lock is dropped, then
diff --git a/fs/file.c b/fs/file.c
index 9d0e91168be1..5861c4f89419 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -814,7 +814,7 @@ static struct file *__fget_files(struct files_struct *files, unsigned int fd,
 
 	rcu_read_lock();
 loop:
-	file = fcheck_files(files, fd);
+	file = files_lookup_fd_rcu(files, fd);
 	if (file) {
 		/* File object ref couldn't be taken.
 		 * dup2() atomicity guarantee is the reason
@@ -1127,7 +1127,7 @@ SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd)
 		int retval = oldfd;
 
 		rcu_read_lock();
-		if (!fcheck_files(files, oldfd))
+		if (!files_lookup_fd_rcu(files, oldfd))
 			retval = -EBADF;
 		rcu_read_unlock();
 		return retval;
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 2cca9bca3b3a..3dec44d7c5c5 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -90,7 +90,7 @@ static bool tid_fd_mode(struct task_struct *task, unsigned fd, fmode_t *mode)
 		return false;
 
 	rcu_read_lock();
-	file = fcheck_files(files, fd);
+	file = files_lookup_fd_rcu(files, fd);
 	if (file)
 		*mode = file->f_mode;
 	rcu_read_unlock();
@@ -243,7 +243,7 @@ static int proc_readfd_common(struct file *file, struct dir_context *ctx,
 		char name[10 + 1];
 		unsigned int len;
 
-		f = fcheck_files(files, fd);
+		f = files_lookup_fd_rcu(files, fd);
 		if (!f)
 			continue;
 		data.mode = f->f_mode;
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index fda4b81dd735..fa8c402a7790 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -98,10 +98,9 @@ static inline struct file *files_lookup_fd_locked(struct files_struct *files, un
 	return files_lookup_fd_raw(files, fd);
 }
 
-static inline struct file *fcheck_files(struct files_struct *files, unsigned int fd)
+static inline struct file *files_lookup_fd_rcu(struct files_struct *files, unsigned int fd)
 {
-	RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&
-			   !lockdep_is_held(&files->file_lock),
+	RCU_LOCKDEP_WARN(!rcu_read_lock_held(),
 			   "suspicious rcu_dereference_check() usage");
 	return files_lookup_fd_raw(files, fd);
 }
@@ -109,7 +108,7 @@ static inline struct file *fcheck_files(struct files_struct *files, unsigned int
 /*
  * Check whether the specified fd has an open file.
  */
-#define fcheck(fd)	fcheck_files(current->files, fd)
+#define fcheck(fd)	files_lookup_fd_rcu(current->files, fd)
 
 struct task_struct;
 
diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index 5b6af30bfbcd..5ab2ccfb96cb 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -183,7 +183,7 @@ again:
 	for (; curr_fd < max_fds; curr_fd++) {
 		struct file *f;
 
-		f = fcheck_files(curr_files, curr_fd);
+		f = files_lookup_fd_rcu(curr_files, curr_fd);
 		if (!f)
 			continue;
 		if (!get_file_rcu(f))
diff --git a/kernel/kcmp.c b/kernel/kcmp.c
index 87c48c0104ad..990717c1aed3 100644
--- a/kernel/kcmp.c
+++ b/kernel/kcmp.c
@@ -67,7 +67,7 @@ get_file_raw_ptr(struct task_struct *task, unsigned int idx)
 	rcu_read_lock();
 
 	if (task->files)
-		file = fcheck_files(task->files, idx);
+		file = files_lookup_fd_rcu(task->files, idx);
 
 	rcu_read_unlock();
 	task_unlock(task);
-- 
cgit v1.2.3


From 460b4f812a9d473d4b39d87d37844f9fc30a9eb3 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 20 Nov 2020 17:14:27 -0600
Subject: file: Rename fcheck lookup_fd_rcu

Also remove the confusing comment about checking if a fd exists.  I
could not find one instance in the entire kernel that still matches
the description or the reason for the name fcheck.

The need for better names became apparent in the last round of
discussion of this set of changes[1].

[1] https://lkml.kernel.org/r/CAHk-=wj8BQbgJFLa+J0e=iT-1qpmCRTbPAJ8gd6MJQ=kbRPqyQ@mail.gmail.com
Link: https://lkml.kernel.org/r/20201120231441.29911-10-ebiederm@xmission.com
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
---
 Documentation/filesystems/files.rst          | 6 +++---
 arch/powerpc/platforms/cell/spufs/coredump.c | 2 +-
 fs/notify/dnotify/dnotify.c                  | 2 +-
 include/linux/fdtable.h                      | 8 ++++----
 4 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/files.rst b/Documentation/filesystems/files.rst
index ea75acdb632c..bcf84459917f 100644
--- a/Documentation/filesystems/files.rst
+++ b/Documentation/filesystems/files.rst
@@ -62,7 +62,7 @@ the fdtable structure -
    be held.
 
 4. To look up the file structure given an fd, a reader
-   must use either fcheck() or files_lookup_fd_rcu() APIs. These
+   must use either lookup_fd_rcu() or files_lookup_fd_rcu() APIs. These
    take care of barrier requirements due to lock-free lookup.
 
    An example::
@@ -70,7 +70,7 @@ the fdtable structure -
 	struct file *file;
 
 	rcu_read_lock();
-	file = fcheck(fd);
+	file = lookup_fd_rcu(fd);
 	if (file) {
 		...
 	}
@@ -104,7 +104,7 @@ the fdtable structure -
    lock-free, they must be installed using rcu_assign_pointer()
    API. If they are looked up lock-free, rcu_dereference()
    must be used. However it is advisable to use files_fdtable()
-   and fcheck()/files_lookup_fd_rcu() which take care of these issues.
+   and lookup_fd_rcu()/files_lookup_fd_rcu() which take care of these issues.
 
 7. While updating, the fdtable pointer must be looked up while
    holding files->file_lock. If ->file_lock is dropped, then
diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c
index 026c181a98c5..60b5583e9eaf 100644
--- a/arch/powerpc/platforms/cell/spufs/coredump.c
+++ b/arch/powerpc/platforms/cell/spufs/coredump.c
@@ -74,7 +74,7 @@ static struct spu_context *coredump_next_context(int *fd)
 	*fd = n - 1;
 
 	rcu_read_lock();
-	file = fcheck(*fd);
+	file = lookup_fd_rcu(*fd);
 	ctx = SPUFS_I(file_inode(file))->i_ctx;
 	get_spu_context(ctx);
 	rcu_read_unlock();
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index 5dcda8f20c04..5486aaca60b0 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -327,7 +327,7 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned long arg)
 	}
 
 	rcu_read_lock();
-	f = fcheck(fd);
+	f = lookup_fd_rcu(fd);
 	rcu_read_unlock();
 
 	/* if (f != filp) means that we lost a race and another task/thread
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index fa8c402a7790..2a4a8fed536e 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -105,10 +105,10 @@ static inline struct file *files_lookup_fd_rcu(struct files_struct *files, unsig
 	return files_lookup_fd_raw(files, fd);
 }
 
-/*
- * Check whether the specified fd has an open file.
- */
-#define fcheck(fd)	files_lookup_fd_rcu(current->files, fd)
+static inline struct file *lookup_fd_rcu(unsigned int fd)
+{
+	return files_lookup_fd_rcu(current->files, fd);
+}
 
 struct task_struct;
 
-- 
cgit v1.2.3


From 3a879fb38082125cc0d8aa89b70c7f3a7cdf584b Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 20 Nov 2020 17:14:28 -0600
Subject: file: Implement task_lookup_fd_rcu

As a companion to lookup_fd_rcu implement task_lookup_fd_rcu for
querying an arbitrary process about a specific file.

Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
v1: https://lkml.kernel.org/r/20200818103713.aw46m7vprsy4vlve@wittgenstein
Link: https://lkml.kernel.org/r/20201120231441.29911-11-ebiederm@xmission.com
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
---
 fs/file.c               | 15 +++++++++++++++
 include/linux/fdtable.h |  2 ++
 2 files changed, 17 insertions(+)

(limited to 'include/linux')

diff --git a/fs/file.c b/fs/file.c
index 5861c4f89419..6448523ca29e 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -865,6 +865,21 @@ struct file *fget_task(struct task_struct *task, unsigned int fd)
 	return file;
 }
 
+struct file *task_lookup_fd_rcu(struct task_struct *task, unsigned int fd)
+{
+	/* Must be called with rcu_read_lock held */
+	struct files_struct *files;
+	struct file *file = NULL;
+
+	task_lock(task);
+	files = task->files;
+	if (files)
+		file = files_lookup_fd_rcu(files, fd);
+	task_unlock(task);
+
+	return file;
+}
+
 /*
  * Lightweight file lookup - no refcnt increment if fd table isn't shared.
  *
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index 2a4a8fed536e..a0558ae9b40c 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -110,6 +110,8 @@ static inline struct file *lookup_fd_rcu(unsigned int fd)
 	return files_lookup_fd_rcu(current->files, fd);
 }
 
+struct file *task_lookup_fd_rcu(struct task_struct *task, unsigned int fd);
+
 struct task_struct;
 
 struct files_struct *get_files_struct(struct task_struct *);
-- 
cgit v1.2.3


From e9a53aeb5e0a838f10fcea74235664e7ad5e6e1a Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 20 Nov 2020 17:14:31 -0600
Subject: file: Implement task_lookup_next_fd_rcu

As a companion to fget_task and task_lookup_fd_rcu implement
task_lookup_next_fd_rcu that will return the struct file for the first
file descriptor number that is equal or greater than the fd argument
value, or NULL if there is no such struct file.

This allows file descriptors of foreign processes to be iterated
through safely, without needed to increment the count on files_struct.

Some concern[1] has been expressed that this function takes the task_lock
for each iteration and thus for each file descriptor.  This place
where this function will be called in a commonly used code path is for
listing /proc/<pid>/fd.  I did some small benchmarks and did not see
any measurable performance differences.  For ordinary users ls is
likely to stat each of the directory entries and tid_fd_mode called
from tid_fd_revalidae has always taken the task lock for each file
descriptor.  So this does not look like it will be a big change in
practice.

At some point is will probably be worth changing put_files_struct to
free files_struct after an rcu grace period so that task_lock won't be
needed at all.

[1] https://lkml.kernel.org/r/20200817220425.9389-10-ebiederm@xmission.com
v1: https://lkml.kernel.org/r/20200817220425.9389-9-ebiederm@xmission.com
Link: https://lkml.kernel.org/r/20201120231441.29911-14-ebiederm@xmission.com
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
---
 fs/file.c               | 21 +++++++++++++++++++++
 include/linux/fdtable.h |  1 +
 2 files changed, 22 insertions(+)

(limited to 'include/linux')

diff --git a/fs/file.c b/fs/file.c
index 6448523ca29e..23b888a4acbe 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -880,6 +880,27 @@ struct file *task_lookup_fd_rcu(struct task_struct *task, unsigned int fd)
 	return file;
 }
 
+struct file *task_lookup_next_fd_rcu(struct task_struct *task, unsigned int *ret_fd)
+{
+	/* Must be called with rcu_read_lock held */
+	struct files_struct *files;
+	unsigned int fd = *ret_fd;
+	struct file *file = NULL;
+
+	task_lock(task);
+	files = task->files;
+	if (files) {
+		for (; fd < files_fdtable(files)->max_fds; fd++) {
+			file = files_lookup_fd_rcu(files, fd);
+			if (file)
+				break;
+		}
+	}
+	task_unlock(task);
+	*ret_fd = fd;
+	return file;
+}
+
 /*
  * Lightweight file lookup - no refcnt increment if fd table isn't shared.
  *
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index a0558ae9b40c..cf6c52dae3a1 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -111,6 +111,7 @@ static inline struct file *lookup_fd_rcu(unsigned int fd)
 }
 
 struct file *task_lookup_fd_rcu(struct task_struct *task, unsigned int fd);
+struct file *task_lookup_next_fd_rcu(struct task_struct *task, unsigned int *fd);
 
 struct task_struct;
 
-- 
cgit v1.2.3


From d74ba04d919ebe30bf47406819c18c6b50003d92 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 20 Nov 2020 17:14:35 -0600
Subject: file: Merge __fd_install into fd_install

The function __fd_install was added to support binder[1].  With binder
fixed[2] there are no more users.

As fd_install just calls __fd_install with "files=current->files",
merge them together by transforming the files parameter into a
local variable initialized to current->files.

[1] f869e8a7f753 ("expose a low-level variant of fd_install() for binder")
[2] 44d8047f1d87 ("binder: use standard functions to allocate fds")
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
v1:https://lkml.kernel.org/r/20200817220425.9389-14-ebiederm@xmission.com
Link: https://lkml.kernel.org/r/20201120231441.29911-18-ebiederm@xmission.com
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
---
 fs/file.c               | 25 ++++++-------------------
 include/linux/fdtable.h |  2 --
 2 files changed, 6 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/fs/file.c b/fs/file.c
index 23b888a4acbe..0d4ec0fa23b3 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -158,7 +158,7 @@ static int expand_fdtable(struct files_struct *files, unsigned int nr)
 	spin_unlock(&files->file_lock);
 	new_fdt = alloc_fdtable(nr);
 
-	/* make sure all __fd_install() have seen resize_in_progress
+	/* make sure all fd_install() have seen resize_in_progress
 	 * or have finished their rcu_read_lock_sched() section.
 	 */
 	if (atomic_read(&files->count) > 1)
@@ -181,7 +181,7 @@ static int expand_fdtable(struct files_struct *files, unsigned int nr)
 	rcu_assign_pointer(files->fdt, new_fdt);
 	if (cur_fdt != &files->fdtab)
 		call_rcu(&cur_fdt->rcu, free_fdtable_rcu);
-	/* coupled with smp_rmb() in __fd_install() */
+	/* coupled with smp_rmb() in fd_install() */
 	smp_wmb();
 	return 1;
 }
@@ -584,17 +584,13 @@ EXPORT_SYMBOL(put_unused_fd);
  * It should never happen - if we allow dup2() do it, _really_ bad things
  * will follow.
  *
- * NOTE: __fd_install() variant is really, really low-level; don't
- * use it unless you are forced to by truly lousy API shoved down
- * your throat.  'files' *MUST* be either current->files or obtained
- * by get_files_struct(current) done by whoever had given it to you,
- * or really bad things will happen.  Normally you want to use
- * fd_install() instead.
+ * This consumes the "file" refcount, so callers should treat it
+ * as if they had called fput(file).
  */
 
-void __fd_install(struct files_struct *files, unsigned int fd,
-		struct file *file)
+void fd_install(unsigned int fd, struct file *file)
 {
+	struct files_struct *files = current->files;
 	struct fdtable *fdt;
 
 	rcu_read_lock_sched();
@@ -616,15 +612,6 @@ void __fd_install(struct files_struct *files, unsigned int fd,
 	rcu_read_unlock_sched();
 }
 
-/*
- * This consumes the "file" refcount, so callers should treat it
- * as if they had called fput(file).
- */
-void fd_install(unsigned int fd, struct file *file)
-{
-	__fd_install(current->files, fd, file);
-}
-
 EXPORT_SYMBOL(fd_install);
 
 static struct file *pick_file(struct files_struct *files, unsigned fd)
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index cf6c52dae3a1..a5ec736d74a5 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -126,8 +126,6 @@ int iterate_fd(struct files_struct *, unsigned,
 
 extern int __alloc_fd(struct files_struct *files,
 		      unsigned start, unsigned end, unsigned flags);
-extern void __fd_install(struct files_struct *files,
-		      unsigned int fd, struct file *file);
 extern int __close_fd(struct files_struct *files,
 		      unsigned int fd);
 extern int __close_range(unsigned int fd, unsigned int max_fd, unsigned int flags);
-- 
cgit v1.2.3


From aa384d10f3d06d4b85597ff5df41551262220e16 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 20 Nov 2020 17:14:37 -0600
Subject: file: Merge __alloc_fd into alloc_fd

The function __alloc_fd was added to support binder[1].  With binder
fixed[2] there are no more users.

As alloc_fd just calls __alloc_fd with "files=current->files",
merge them together by transforming the files parameter into a
local variable initialized to current->files.

[1] dcfadfa4ec5a ("new helper: __alloc_fd()")
[2] 44d8047f1d87 ("binder: use standard functions to allocate fds")
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
v1: https://lkml.kernel.org/r/20200817220425.9389-16-ebiederm@xmission.com
Link: https://lkml.kernel.org/r/20201120231441.29911-20-ebiederm@xmission.com
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
---
 fs/file.c               | 11 +++--------
 include/linux/fdtable.h |  2 --
 2 files changed, 3 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/fs/file.c b/fs/file.c
index 07e25f1b9dfd..621563701bd9 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -480,9 +480,9 @@ static unsigned int find_next_fd(struct fdtable *fdt, unsigned int start)
 /*
  * allocate a file descriptor, mark it busy.
  */
-int __alloc_fd(struct files_struct *files,
-	       unsigned start, unsigned end, unsigned flags)
+static int alloc_fd(unsigned start, unsigned end, unsigned flags)
 {
+	struct files_struct *files = current->files;
 	unsigned int fd;
 	int error;
 	struct fdtable *fdt;
@@ -538,14 +538,9 @@ out:
 	return error;
 }
 
-static int alloc_fd(unsigned start, unsigned end, unsigned flags)
-{
-	return __alloc_fd(current->files, start, end, flags);
-}
-
 int __get_unused_fd_flags(unsigned flags, unsigned long nofile)
 {
-	return __alloc_fd(current->files, 0, nofile, flags);
+	return alloc_fd(0, nofile, flags);
 }
 
 int get_unused_fd_flags(unsigned flags)
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index a5ec736d74a5..dc476ae92f56 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -124,8 +124,6 @@ int iterate_fd(struct files_struct *, unsigned,
 		int (*)(const void *, struct file *, unsigned),
 		const void *);
 
-extern int __alloc_fd(struct files_struct *files,
-		      unsigned start, unsigned end, unsigned flags);
 extern int __close_fd(struct files_struct *files,
 		      unsigned int fd);
 extern int __close_range(unsigned int fd, unsigned int max_fd, unsigned int flags);
-- 
cgit v1.2.3


From 8760c909f54a82aaa6e76da19afe798a0c77c3c3 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 20 Nov 2020 17:14:38 -0600
Subject: file: Rename __close_fd to close_fd and remove the files parameter

The function __close_fd was added to support binder[1].  Now that
binder has been fixed to no longer need __close_fd[2] all calls
to __close_fd pass current->files.

Therefore transform the files parameter into a local variable
initialized to current->files, and rename __close_fd to close_fd to
reflect this change, and keep it in sync with the similar changes to
__alloc_fd, and __fd_install.

This removes the need for callers to care about the extra care that
needs to be take if anything except current->files is passed, by
limiting the callers to only operation on current->files.

[1] 483ce1d4b8c3 ("take descriptor-related part of close() to file.c")
[2] 44d8047f1d87 ("binder: use standard functions to allocate fds")
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
v1: https://lkml.kernel.org/r/20200817220425.9389-17-ebiederm@xmission.com
Link: https://lkml.kernel.org/r/20201120231441.29911-21-ebiederm@xmission.com
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
---
 fs/file.c                | 10 ++++------
 fs/open.c                |  2 +-
 include/linux/fdtable.h  |  3 +--
 include/linux/syscalls.h |  6 +++---
 4 files changed, 9 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/fs/file.c b/fs/file.c
index 621563701bd9..987ea51630b4 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -629,11 +629,9 @@ out_unlock:
 	return file;
 }
 
-/*
- * The same warnings as for __alloc_fd()/__fd_install() apply here...
- */
-int __close_fd(struct files_struct *files, unsigned fd)
+int close_fd(unsigned fd)
 {
+	struct files_struct *files = current->files;
 	struct file *file;
 
 	file = pick_file(files, fd);
@@ -642,7 +640,7 @@ int __close_fd(struct files_struct *files, unsigned fd)
 
 	return filp_close(file, files);
 }
-EXPORT_SYMBOL(__close_fd); /* for ksys_close() */
+EXPORT_SYMBOL(close_fd); /* for ksys_close() */
 
 /**
  * __close_range() - Close all file descriptors in a given range.
@@ -1027,7 +1025,7 @@ int replace_fd(unsigned fd, struct file *file, unsigned flags)
 	struct files_struct *files = current->files;
 
 	if (!file)
-		return __close_fd(files, fd);
+		return close_fd(fd);
 
 	if (fd >= rlimit(RLIMIT_NOFILE))
 		return -EBADF;
diff --git a/fs/open.c b/fs/open.c
index 9af548fb841b..581a674d7eee 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -1292,7 +1292,7 @@ EXPORT_SYMBOL(filp_close);
  */
 SYSCALL_DEFINE1(close, unsigned int, fd)
 {
-	int retval = __close_fd(current->files, fd);
+	int retval = close_fd(fd);
 
 	/* can't restart close syscall because file table entry was cleared */
 	if (unlikely(retval == -ERESTARTSYS ||
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index dc476ae92f56..dad4a488ce60 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -124,8 +124,7 @@ int iterate_fd(struct files_struct *, unsigned,
 		int (*)(const void *, struct file *, unsigned),
 		const void *);
 
-extern int __close_fd(struct files_struct *files,
-		      unsigned int fd);
+extern int close_fd(unsigned int fd);
 extern int __close_range(unsigned int fd, unsigned int max_fd, unsigned int flags);
 extern int __close_fd_get_file(unsigned int fd, struct file **res);
 extern int unshare_fd(unsigned long unshare_flags, unsigned int max_fds,
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 37bea07c12f2..9e055a0579f8 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1295,16 +1295,16 @@ static inline long ksys_ftruncate(unsigned int fd, loff_t length)
 	return do_sys_ftruncate(fd, length, 1);
 }
 
-extern int __close_fd(struct files_struct *files, unsigned int fd);
+extern int close_fd(unsigned int fd);
 
 /*
  * In contrast to sys_close(), this stub does not check whether the syscall
  * should or should not be restarted, but returns the raw error codes from
- * __close_fd().
+ * close_fd().
  */
 static inline int ksys_close(unsigned int fd)
 {
-	return __close_fd(current->files, fd);
+	return close_fd(fd);
 }
 
 extern long do_sys_truncate(const char __user *pathname, loff_t length);
-- 
cgit v1.2.3


From 1572bfdf21d4d50e51941498ffe0b56c2289f783 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 20 Nov 2020 17:14:39 -0600
Subject: file: Replace ksys_close with close_fd

Now that ksys_close is exactly identical to close_fd replace
the one caller of ksys_close with close_fd.

[1] https://lkml.kernel.org/r/20200818112020.GA17080@infradead.org
Suggested-by: Christoph Hellwig <hch@infradead.org>
Link: https://lkml.kernel.org/r/20201120231441.29911-22-ebiederm@xmission.com
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
---
 fs/autofs/dev-ioctl.c    |  5 +++--
 include/linux/syscalls.h | 12 ------------
 2 files changed, 3 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/fs/autofs/dev-ioctl.c b/fs/autofs/dev-ioctl.c
index 322b7dfb4ea0..5bf781ea6d67 100644
--- a/fs/autofs/dev-ioctl.c
+++ b/fs/autofs/dev-ioctl.c
@@ -4,9 +4,10 @@
  * Copyright 2008 Ian Kent <raven@themaw.net>
  */
 
+#include <linux/module.h>
 #include <linux/miscdevice.h>
 #include <linux/compat.h>
-#include <linux/syscalls.h>
+#include <linux/fdtable.h>
 #include <linux/magic.h>
 #include <linux/nospec.h>
 
@@ -289,7 +290,7 @@ static int autofs_dev_ioctl_closemount(struct file *fp,
 				       struct autofs_sb_info *sbi,
 				       struct autofs_dev_ioctl *param)
 {
-	return ksys_close(param->ioctlfd);
+	return close_fd(param->ioctlfd);
 }
 
 /*
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 9e055a0579f8..0f72f380db72 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1295,18 +1295,6 @@ static inline long ksys_ftruncate(unsigned int fd, loff_t length)
 	return do_sys_ftruncate(fd, length, 1);
 }
 
-extern int close_fd(unsigned int fd);
-
-/*
- * In contrast to sys_close(), this stub does not check whether the syscall
- * should or should not be restarted, but returns the raw error codes from
- * close_fd().
- */
-static inline int ksys_close(unsigned int fd)
-{
-	return close_fd(fd);
-}
-
 extern long do_sys_truncate(const char __user *pathname, loff_t length);
 
 static inline long ksys_truncate(const char __user *pathname, loff_t length)
-- 
cgit v1.2.3


From 9fe83c43e71cdb8e5b9520bcb98706a2b3c680c8 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 20 Nov 2020 17:14:40 -0600
Subject: file: Rename __close_fd_get_file close_fd_get_file

The function close_fd_get_file is explicitly a variant of
__close_fd[1].  Now that __close_fd has been renamed close_fd, rename
close_fd_get_file to be consistent with close_fd.

When __alloc_fd, __close_fd and __fd_install were introduced the
double underscore indicated that the function took a struct
files_struct parameter.  The function __close_fd_get_file never has so
the naming has always been inconsistent.  This just cleans things up
so there are not any lingering mentions or references __close_fd left
in the code.

[1] 80cd795630d6 ("binder: fix use-after-free due to ksys_close() during fdget()")
Link: https://lkml.kernel.org/r/20201120231441.29911-23-ebiederm@xmission.com
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
---
 drivers/android/binder.c | 2 +-
 fs/file.c                | 4 ++--
 fs/io_uring.c            | 2 +-
 include/linux/fdtable.h  | 2 +-
 4 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index b5117576792b..5b2e3721ac27 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -2226,7 +2226,7 @@ static void binder_deferred_fd_close(int fd)
 	if (!twcb)
 		return;
 	init_task_work(&twcb->twork, binder_do_fd_close);
-	__close_fd_get_file(fd, &twcb->file);
+	close_fd_get_file(fd, &twcb->file);
 	if (twcb->file) {
 		filp_close(twcb->file, current->files);
 		task_work_add(current, &twcb->twork, TWA_RESUME);
diff --git a/fs/file.c b/fs/file.c
index 987ea51630b4..947ac6d5602f 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -721,11 +721,11 @@ int __close_range(unsigned fd, unsigned max_fd, unsigned int flags)
 }
 
 /*
- * variant of __close_fd that gets a ref on the file for later fput.
+ * variant of close_fd that gets a ref on the file for later fput.
  * The caller must ensure that filp_close() called on the file, and then
  * an fput().
  */
-int __close_fd_get_file(unsigned int fd, struct file **res)
+int close_fd_get_file(unsigned int fd, struct file **res)
 {
 	struct files_struct *files = current->files;
 	struct file *file;
diff --git a/fs/io_uring.c b/fs/io_uring.c
index b42dfa0243bf..2e6e51292eff 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -4206,7 +4206,7 @@ static int io_close(struct io_kiocb *req, bool force_nonblock,
 
 	/* might be already done during nonblock submission */
 	if (!close->put_file) {
-		ret = __close_fd_get_file(close->fd, &close->put_file);
+		ret = close_fd_get_file(close->fd, &close->put_file);
 		if (ret < 0)
 			return (ret == -ENOENT) ? -EBADF : ret;
 	}
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index dad4a488ce60..4ed3589f9294 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -126,7 +126,7 @@ int iterate_fd(struct files_struct *, unsigned,
 
 extern int close_fd(unsigned int fd);
 extern int __close_range(unsigned int fd, unsigned int max_fd, unsigned int flags);
-extern int __close_fd_get_file(unsigned int fd, struct file **res);
+extern int close_fd_get_file(unsigned int fd, struct file **res);
 extern int unshare_fd(unsigned long unshare_flags, unsigned int max_fds,
 		      struct files_struct **new_fdp);
 
-- 
cgit v1.2.3


From fa67bf885e5211c7dce9514ef2877212c0a5e09e Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 20 Nov 2020 17:14:41 -0600
Subject: file: Remove get_files_struct

When discussing[1] exec and posix file locks it was realized that none
of the callers of get_files_struct fundamentally needed to call
get_files_struct, and that by switching them to helper functions
instead it will both simplify their code and remove unnecessary
increments of files_struct.count.  Those unnecessary increments can
result in exec unnecessarily unsharing files_struct which breaking
posix locks, and it can result in fget_light having to fallback to
fget reducing system performance.

Now that get_files_struct has no more users and can not cause the
problems for posix file locking and fget_light remove get_files_struct
so that it does not gain any new users.

[1] https://lkml.kernel.org/r/20180915160423.GA31461@redhat.com
Suggested-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
v1: https://lkml.kernel.org/r/20200817220425.9389-13-ebiederm@xmission.com
Link: https://lkml.kernel.org/r/20201120231441.29911-24-ebiederm@xmission.com
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
---
 fs/file.c               | 13 -------------
 include/linux/fdtable.h |  1 -
 2 files changed, 14 deletions(-)

(limited to 'include/linux')

diff --git a/fs/file.c b/fs/file.c
index 947ac6d5602f..412033d8cfdf 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -411,19 +411,6 @@ static struct fdtable *close_files(struct files_struct * files)
 	return fdt;
 }
 
-struct files_struct *get_files_struct(struct task_struct *task)
-{
-	struct files_struct *files;
-
-	task_lock(task);
-	files = task->files;
-	if (files)
-		atomic_inc(&files->count);
-	task_unlock(task);
-
-	return files;
-}
-
 void put_files_struct(struct files_struct *files)
 {
 	if (atomic_dec_and_test(&files->count)) {
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index 4ed3589f9294..d0e78174874a 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -115,7 +115,6 @@ struct file *task_lookup_next_fd_rcu(struct task_struct *task, unsigned int *fd)
 
 struct task_struct;
 
-struct files_struct *get_files_struct(struct task_struct *);
 void put_files_struct(struct files_struct *fs);
 int unshare_files(void);
 struct files_struct *dup_fd(struct files_struct *, unsigned, int *) __latent_entropy;
-- 
cgit v1.2.3


From f7cfd871ae0c5008d94b6f66834e7845caa93c15 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Thu, 3 Dec 2020 14:12:00 -0600
Subject: exec: Transform exec_update_mutex into a rw_semaphore

Recently syzbot reported[0] that there is a deadlock amongst the users
of exec_update_mutex.  The problematic lock ordering found by lockdep
was:

   perf_event_open  (exec_update_mutex -> ovl_i_mutex)
   chown            (ovl_i_mutex       -> sb_writes)
   sendfile         (sb_writes         -> p->lock)
     by reading from a proc file and writing to overlayfs
   proc_pid_syscall (p->lock           -> exec_update_mutex)

While looking at possible solutions it occured to me that all of the
users and possible users involved only wanted to state of the given
process to remain the same.  They are all readers.  The only writer is
exec.

There is no reason for readers to block on each other.  So fix
this deadlock by transforming exec_update_mutex into a rw_semaphore
named exec_update_lock that only exec takes for writing.

Cc: Jann Horn <jannh@google.com>
Cc: Vasiliy Kulikov <segoon@openwall.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Bernd Edlinger <bernd.edlinger@hotmail.de>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Christopher Yeoh <cyeoh@au1.ibm.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Sargun Dhillon <sargun@sargun.me>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Fixes: eea9673250db ("exec: Add exec_update_mutex to replace cred_guard_mutex")
[0] https://lkml.kernel.org/r/00000000000063640c05ade8e3de@google.com
Reported-by: syzbot+db9cdf3dd1f64252c6ef@syzkaller.appspotmail.com
Link: https://lkml.kernel.org/r/87ft4mbqen.fsf@x220.int.ebiederm.org
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
---
 fs/exec.c                    | 12 ++++++------
 fs/proc/base.c               | 10 +++++-----
 include/linux/sched/signal.h | 11 ++++++-----
 init/init_task.c             |  2 +-
 kernel/events/core.c         | 12 ++++++------
 kernel/fork.c                |  6 +++---
 kernel/kcmp.c                | 30 +++++++++++++++---------------
 kernel/pid.c                 |  4 ++--
 8 files changed, 44 insertions(+), 43 deletions(-)

(limited to 'include/linux')

diff --git a/fs/exec.c b/fs/exec.c
index 547a2390baf5..ca89e0e3ef10 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -965,8 +965,8 @@ EXPORT_SYMBOL(read_code);
 
 /*
  * Maps the mm_struct mm into the current task struct.
- * On success, this function returns with the mutex
- * exec_update_mutex locked.
+ * On success, this function returns with exec_update_lock
+ * held for writing.
  */
 static int exec_mmap(struct mm_struct *mm)
 {
@@ -981,7 +981,7 @@ static int exec_mmap(struct mm_struct *mm)
 	if (old_mm)
 		sync_mm_rss(old_mm);
 
-	ret = mutex_lock_killable(&tsk->signal->exec_update_mutex);
+	ret = down_write_killable(&tsk->signal->exec_update_lock);
 	if (ret)
 		return ret;
 
@@ -995,7 +995,7 @@ static int exec_mmap(struct mm_struct *mm)
 		mmap_read_lock(old_mm);
 		if (unlikely(old_mm->core_state)) {
 			mmap_read_unlock(old_mm);
-			mutex_unlock(&tsk->signal->exec_update_mutex);
+			up_write(&tsk->signal->exec_update_lock);
 			return -EINTR;
 		}
 	}
@@ -1382,7 +1382,7 @@ int begin_new_exec(struct linux_binprm * bprm)
 	return 0;
 
 out_unlock:
-	mutex_unlock(&me->signal->exec_update_mutex);
+	up_write(&me->signal->exec_update_lock);
 out:
 	return retval;
 }
@@ -1423,7 +1423,7 @@ void setup_new_exec(struct linux_binprm * bprm)
 	 * some architectures like powerpc
 	 */
 	me->mm->task_size = TASK_SIZE;
-	mutex_unlock(&me->signal->exec_update_mutex);
+	up_write(&me->signal->exec_update_lock);
 	mutex_unlock(&me->signal->cred_guard_mutex);
 }
 EXPORT_SYMBOL(setup_new_exec);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index b362523a9829..55ce0ee9c5c7 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -405,11 +405,11 @@ print0:
 
 static int lock_trace(struct task_struct *task)
 {
-	int err = mutex_lock_killable(&task->signal->exec_update_mutex);
+	int err = down_read_killable(&task->signal->exec_update_lock);
 	if (err)
 		return err;
 	if (!ptrace_may_access(task, PTRACE_MODE_ATTACH_FSCREDS)) {
-		mutex_unlock(&task->signal->exec_update_mutex);
+		up_read(&task->signal->exec_update_lock);
 		return -EPERM;
 	}
 	return 0;
@@ -417,7 +417,7 @@ static int lock_trace(struct task_struct *task)
 
 static void unlock_trace(struct task_struct *task)
 {
-	mutex_unlock(&task->signal->exec_update_mutex);
+	up_read(&task->signal->exec_update_lock);
 }
 
 #ifdef CONFIG_STACKTRACE
@@ -2930,7 +2930,7 @@ static int do_io_accounting(struct task_struct *task, struct seq_file *m, int wh
 	unsigned long flags;
 	int result;
 
-	result = mutex_lock_killable(&task->signal->exec_update_mutex);
+	result = down_read_killable(&task->signal->exec_update_lock);
 	if (result)
 		return result;
 
@@ -2966,7 +2966,7 @@ static int do_io_accounting(struct task_struct *task, struct seq_file *m, int wh
 	result = 0;
 
 out_unlock:
-	mutex_unlock(&task->signal->exec_update_mutex);
+	up_read(&task->signal->exec_update_lock);
 	return result;
 }
 
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 1bad18a1d8ba..4b6a8234d7fc 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -228,12 +228,13 @@ struct signal_struct {
 					 * credential calculations
 					 * (notably. ptrace)
 					 * Deprecated do not use in new code.
-					 * Use exec_update_mutex instead.
-					 */
-	struct mutex exec_update_mutex;	/* Held while task_struct is being
-					 * updated during exec, and may have
-					 * inconsistent permissions.
+					 * Use exec_update_lock instead.
 					 */
+	struct rw_semaphore exec_update_lock;	/* Held while task_struct is
+						 * being updated during exec,
+						 * and may have inconsistent
+						 * permissions.
+						 */
 } __randomize_layout;
 
 /*
diff --git a/init/init_task.c b/init/init_task.c
index a56f0abb63e9..15f6eb93a04f 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -26,7 +26,7 @@ static struct signal_struct init_signals = {
 	.multiprocess	= HLIST_HEAD_INIT,
 	.rlim		= INIT_RLIMITS,
 	.cred_guard_mutex = __MUTEX_INITIALIZER(init_signals.cred_guard_mutex),
-	.exec_update_mutex = __MUTEX_INITIALIZER(init_signals.exec_update_mutex),
+	.exec_update_lock = __RWSEM_INITIALIZER(init_signals.exec_update_lock),
 #ifdef CONFIG_POSIX_TIMERS
 	.posix_timers = LIST_HEAD_INIT(init_signals.posix_timers),
 	.cputimer	= {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index dc568ca295bd..55b2330b556c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1325,7 +1325,7 @@ static void put_ctx(struct perf_event_context *ctx)
  * function.
  *
  * Lock order:
- *    exec_update_mutex
+ *    exec_update_lock
  *	task_struct::perf_event_mutex
  *	  perf_event_context::mutex
  *	    perf_event::child_mutex;
@@ -11721,14 +11721,14 @@ SYSCALL_DEFINE5(perf_event_open,
 	}
 
 	if (task) {
-		err = mutex_lock_interruptible(&task->signal->exec_update_mutex);
+		err = down_read_interruptible(&task->signal->exec_update_lock);
 		if (err)
 			goto err_task;
 
 		/*
 		 * Preserve ptrace permission check for backwards compatibility.
 		 *
-		 * We must hold exec_update_mutex across this and any potential
+		 * We must hold exec_update_lock across this and any potential
 		 * perf_install_in_context() call for this new event to
 		 * serialize against exec() altering our credentials (and the
 		 * perf_event_exit_task() that could imply).
@@ -12017,7 +12017,7 @@ SYSCALL_DEFINE5(perf_event_open,
 	mutex_unlock(&ctx->mutex);
 
 	if (task) {
-		mutex_unlock(&task->signal->exec_update_mutex);
+		up_read(&task->signal->exec_update_lock);
 		put_task_struct(task);
 	}
 
@@ -12053,7 +12053,7 @@ err_alloc:
 		free_event(event);
 err_cred:
 	if (task)
-		mutex_unlock(&task->signal->exec_update_mutex);
+		up_read(&task->signal->exec_update_lock);
 err_task:
 	if (task)
 		put_task_struct(task);
@@ -12358,7 +12358,7 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 /*
  * When a child task exits, feed back event values to parent events.
  *
- * Can be called with exec_update_mutex held when called from
+ * Can be called with exec_update_lock held when called from
  * setup_new_exec().
  */
 void perf_event_exit_task(struct task_struct *child)
diff --git a/kernel/fork.c b/kernel/fork.c
index 6d266388d380..e8cb80b266d2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1221,7 +1221,7 @@ struct mm_struct *mm_access(struct task_struct *task, unsigned int mode)
 	struct mm_struct *mm;
 	int err;
 
-	err =  mutex_lock_killable(&task->signal->exec_update_mutex);
+	err =  down_read_killable(&task->signal->exec_update_lock);
 	if (err)
 		return ERR_PTR(err);
 
@@ -1231,7 +1231,7 @@ struct mm_struct *mm_access(struct task_struct *task, unsigned int mode)
 		mmput(mm);
 		mm = ERR_PTR(-EACCES);
 	}
-	mutex_unlock(&task->signal->exec_update_mutex);
+	up_read(&task->signal->exec_update_lock);
 
 	return mm;
 }
@@ -1591,7 +1591,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	sig->oom_score_adj_min = current->signal->oom_score_adj_min;
 
 	mutex_init(&sig->cred_guard_mutex);
-	mutex_init(&sig->exec_update_mutex);
+	init_rwsem(&sig->exec_update_lock);
 
 	return 0;
 }
diff --git a/kernel/kcmp.c b/kernel/kcmp.c
index b3ff9288c6cc..c0d2ad9b4705 100644
--- a/kernel/kcmp.c
+++ b/kernel/kcmp.c
@@ -75,25 +75,25 @@ get_file_raw_ptr(struct task_struct *task, unsigned int idx)
 	return file;
 }
 
-static void kcmp_unlock(struct mutex *m1, struct mutex *m2)
+static void kcmp_unlock(struct rw_semaphore *l1, struct rw_semaphore *l2)
 {
-	if (likely(m2 != m1))
-		mutex_unlock(m2);
-	mutex_unlock(m1);
+	if (likely(l2 != l1))
+		up_read(l2);
+	up_read(l1);
 }
 
-static int kcmp_lock(struct mutex *m1, struct mutex *m2)
+static int kcmp_lock(struct rw_semaphore *l1, struct rw_semaphore *l2)
 {
 	int err;
 
-	if (m2 > m1)
-		swap(m1, m2);
+	if (l2 > l1)
+		swap(l1, l2);
 
-	err = mutex_lock_killable(m1);
-	if (!err && likely(m1 != m2)) {
-		err = mutex_lock_killable_nested(m2, SINGLE_DEPTH_NESTING);
+	err = down_read_killable(l1);
+	if (!err && likely(l1 != l2)) {
+		err = down_read_killable_nested(l2, SINGLE_DEPTH_NESTING);
 		if (err)
-			mutex_unlock(m1);
+			up_read(l1);
 	}
 
 	return err;
@@ -173,8 +173,8 @@ SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type,
 	/*
 	 * One should have enough rights to inspect task details.
 	 */
-	ret = kcmp_lock(&task1->signal->exec_update_mutex,
-			&task2->signal->exec_update_mutex);
+	ret = kcmp_lock(&task1->signal->exec_update_lock,
+			&task2->signal->exec_update_lock);
 	if (ret)
 		goto err;
 	if (!ptrace_may_access(task1, PTRACE_MODE_READ_REALCREDS) ||
@@ -229,8 +229,8 @@ SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type,
 	}
 
 err_unlock:
-	kcmp_unlock(&task1->signal->exec_update_mutex,
-		    &task2->signal->exec_update_mutex);
+	kcmp_unlock(&task1->signal->exec_update_lock,
+		    &task2->signal->exec_update_lock);
 err:
 	put_task_struct(task1);
 	put_task_struct(task2);
diff --git a/kernel/pid.c b/kernel/pid.c
index a96bc4bf4f86..4856818c9de1 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -628,7 +628,7 @@ static struct file *__pidfd_fget(struct task_struct *task, int fd)
 	struct file *file;
 	int ret;
 
-	ret = mutex_lock_killable(&task->signal->exec_update_mutex);
+	ret = down_read_killable(&task->signal->exec_update_lock);
 	if (ret)
 		return ERR_PTR(ret);
 
@@ -637,7 +637,7 @@ static struct file *__pidfd_fget(struct task_struct *task, int fd)
 	else
 		file = ERR_PTR(-EPERM);
 
-	mutex_unlock(&task->signal->exec_update_mutex);
+	up_read(&task->signal->exec_update_lock);
 
 	return file ?: ERR_PTR(-EBADF);
 }
-- 
cgit v1.2.3


From adf60a870e9130c7883ec2ab798484e05f24db39 Mon Sep 17 00:00:00 2001
From: Siddharth Gupta <sidgup@codeaurora.org>
Date: Thu, 19 Nov 2020 13:05:32 -0800
Subject: remoteproc: core: Add ops to enable custom coredump functionality

Each remoteproc might have different requirements for coredumps and might
want to choose the type of dumps it wants to collect. This change allows
remoteproc drivers to specify their own custom dump function to be executed
in place of rproc_coredump. If the coredump op is not specified by the
remoteproc driver it will be set to rproc_coredump by default.

Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: Siddharth Gupta <sidgup@codeaurora.org>
Link: https://lore.kernel.org/r/1605819935-10726-2-git-send-email-sidgup@codeaurora.org
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 drivers/remoteproc/remoteproc_core.c | 6 +++++-
 include/linux/remoteproc.h           | 2 ++
 2 files changed, 7 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c
index 46c2937ebea9..2394eef383e3 100644
--- a/drivers/remoteproc/remoteproc_core.c
+++ b/drivers/remoteproc/remoteproc_core.c
@@ -1704,7 +1704,7 @@ int rproc_trigger_recovery(struct rproc *rproc)
 		goto unlock_mutex;
 
 	/* generate coredump */
-	rproc_coredump(rproc);
+	rproc->ops->coredump(rproc);
 
 	/* load firmware */
 	ret = request_firmware(&firmware_p, rproc->firmware, dev);
@@ -2189,6 +2189,10 @@ static int rproc_alloc_ops(struct rproc *rproc, const struct rproc_ops *ops)
 	if (!rproc->ops)
 		return -ENOMEM;
 
+	/* Default to rproc_coredump if no coredump function is specified */
+	if (!rproc->ops->coredump)
+		rproc->ops->coredump = rproc_coredump;
+
 	if (rproc->ops->load)
 		return 0;
 
diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h
index e8ac041c64d9..121c55eff3d2 100644
--- a/include/linux/remoteproc.h
+++ b/include/linux/remoteproc.h
@@ -375,6 +375,7 @@ enum rsc_handling_status {
  * @get_boot_addr:	get boot address to entry point specified in firmware
  * @panic:	optional callback to react to system panic, core will delay
  *		panic at least the returned number of milliseconds
+ * @coredump:	  collect firmware dump after the subsystem is shutdown
  */
 struct rproc_ops {
 	int (*prepare)(struct rproc *rproc);
@@ -393,6 +394,7 @@ struct rproc_ops {
 	int (*sanity_check)(struct rproc *rproc, const struct firmware *fw);
 	u64 (*get_boot_addr)(struct rproc *rproc, const struct firmware *fw);
 	unsigned long (*panic)(struct rproc *rproc);
+	void (*coredump)(struct rproc *rproc);
 };
 
 /**
-- 
cgit v1.2.3


From abc72b646066075acf9121a2a68aad39f550813d Mon Sep 17 00:00:00 2001
From: Siddharth Gupta <sidgup@codeaurora.org>
Date: Thu, 19 Nov 2020 13:05:33 -0800
Subject: remoteproc: coredump: Add minidump functionality

This change adds a new kind of core dump mechanism which instead of dumping
entire program segments of the firmware, dumps sections of the remoteproc
memory which are sufficient to allow debugging the firmware. This function
thus uses section headers instead of program headers during creation of the
core dump elf.

Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Co-developed-by: Rishabh Bhatnagar <rishabhb@codeaurora.org>
Signed-off-by: Rishabh Bhatnagar <rishabhb@codeaurora.org>
Signed-off-by: Siddharth Gupta <sidgup@codeaurora.org>
Link: https://lore.kernel.org/r/1605819935-10726-3-git-send-email-sidgup@codeaurora.org
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 drivers/remoteproc/remoteproc_coredump.c    | 140 ++++++++++++++++++++++++++++
 drivers/remoteproc/remoteproc_elf_helpers.h |  26 ++++++
 include/linux/remoteproc.h                  |   1 +
 3 files changed, 167 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/remoteproc/remoteproc_coredump.c b/drivers/remoteproc/remoteproc_coredump.c
index 34530dc20cb4..81ec154a6a5e 100644
--- a/drivers/remoteproc/remoteproc_coredump.c
+++ b/drivers/remoteproc/remoteproc_coredump.c
@@ -323,3 +323,143 @@ void rproc_coredump(struct rproc *rproc)
 	 */
 	wait_for_completion(&dump_state.dump_done);
 }
+
+/**
+ * rproc_coredump_using_sections() - perform coredump using section headers
+ * @rproc:	rproc handle
+ *
+ * This function will generate an ELF header for the registered sections of
+ * segments and create a devcoredump device associated with rproc. Based on
+ * the coredump configuration this function will directly copy the segments
+ * from device memory to userspace or copy segments from device memory to
+ * a separate buffer, which can then be read by userspace.
+ * The first approach avoids using extra vmalloc memory. But it will stall
+ * recovery flow until dump is read by userspace.
+ */
+void rproc_coredump_using_sections(struct rproc *rproc)
+{
+	struct rproc_dump_segment *segment;
+	void *shdr;
+	void *ehdr;
+	size_t data_size;
+	size_t strtbl_size = 0;
+	size_t strtbl_index = 1;
+	size_t offset;
+	void *data;
+	u8 class = rproc->elf_class;
+	int shnum;
+	struct rproc_coredump_state dump_state;
+	unsigned int dump_conf = rproc->dump_conf;
+	char *str_tbl = "STR_TBL";
+
+	if (list_empty(&rproc->dump_segments) ||
+	    dump_conf == RPROC_COREDUMP_DISABLED)
+		return;
+
+	if (class == ELFCLASSNONE) {
+		dev_err(&rproc->dev, "Elf class is not set\n");
+		return;
+	}
+
+	/*
+	 * We allocate two extra section headers. The first one is null.
+	 * Second section header is for the string table. Also space is
+	 * allocated for string table.
+	 */
+	data_size = elf_size_of_hdr(class) + 2 * elf_size_of_shdr(class);
+	shnum = 2;
+
+	/* the extra byte is for the null character at index 0 */
+	strtbl_size += strlen(str_tbl) + 2;
+
+	list_for_each_entry(segment, &rproc->dump_segments, node) {
+		data_size += elf_size_of_shdr(class);
+		strtbl_size += strlen(segment->priv) + 1;
+		if (dump_conf == RPROC_COREDUMP_ENABLED)
+			data_size += segment->size;
+		shnum++;
+	}
+
+	data_size += strtbl_size;
+
+	data = vmalloc(data_size);
+	if (!data)
+		return;
+
+	ehdr = data;
+	memset(ehdr, 0, elf_size_of_hdr(class));
+	/* e_ident field is common for both elf32 and elf64 */
+	elf_hdr_init_ident(ehdr, class);
+
+	elf_hdr_set_e_type(class, ehdr, ET_CORE);
+	elf_hdr_set_e_machine(class, ehdr, rproc->elf_machine);
+	elf_hdr_set_e_version(class, ehdr, EV_CURRENT);
+	elf_hdr_set_e_entry(class, ehdr, rproc->bootaddr);
+	elf_hdr_set_e_shoff(class, ehdr, elf_size_of_hdr(class));
+	elf_hdr_set_e_ehsize(class, ehdr, elf_size_of_hdr(class));
+	elf_hdr_set_e_shentsize(class, ehdr, elf_size_of_shdr(class));
+	elf_hdr_set_e_shnum(class, ehdr, shnum);
+	elf_hdr_set_e_shstrndx(class, ehdr, 1);
+
+	/*
+	 * The zeroth index of the section header is reserved and is rarely used.
+	 * Set the section header as null (SHN_UNDEF) and move to the next one.
+	 */
+	shdr = data + elf_hdr_get_e_shoff(class, ehdr);
+	memset(shdr, 0, elf_size_of_shdr(class));
+	shdr += elf_size_of_shdr(class);
+
+	/* Initialize the string table. */
+	offset = elf_hdr_get_e_shoff(class, ehdr) +
+		 elf_size_of_shdr(class) * elf_hdr_get_e_shnum(class, ehdr);
+	memset(data + offset, 0, strtbl_size);
+
+	/* Fill in the string table section header. */
+	memset(shdr, 0, elf_size_of_shdr(class));
+	elf_shdr_set_sh_type(class, shdr, SHT_STRTAB);
+	elf_shdr_set_sh_offset(class, shdr, offset);
+	elf_shdr_set_sh_size(class, shdr, strtbl_size);
+	elf_shdr_set_sh_entsize(class, shdr, 0);
+	elf_shdr_set_sh_flags(class, shdr, 0);
+	elf_shdr_set_sh_name(class, shdr, elf_strtbl_add(str_tbl, ehdr, class, &strtbl_index));
+	offset += elf_shdr_get_sh_size(class, shdr);
+	shdr += elf_size_of_shdr(class);
+
+	list_for_each_entry(segment, &rproc->dump_segments, node) {
+		memset(shdr, 0, elf_size_of_shdr(class));
+		elf_shdr_set_sh_type(class, shdr, SHT_PROGBITS);
+		elf_shdr_set_sh_offset(class, shdr, offset);
+		elf_shdr_set_sh_addr(class, shdr, segment->da);
+		elf_shdr_set_sh_size(class, shdr, segment->size);
+		elf_shdr_set_sh_entsize(class, shdr, 0);
+		elf_shdr_set_sh_flags(class, shdr, SHF_WRITE);
+		elf_shdr_set_sh_name(class, shdr,
+				     elf_strtbl_add(segment->priv, ehdr, class, &strtbl_index));
+
+		/* No need to copy segments for inline dumps */
+		if (dump_conf == RPROC_COREDUMP_ENABLED)
+			rproc_copy_segment(rproc, data + offset, segment, 0,
+					   segment->size);
+		offset += elf_shdr_get_sh_size(class, shdr);
+		shdr += elf_size_of_shdr(class);
+	}
+
+	if (dump_conf == RPROC_COREDUMP_ENABLED) {
+		dev_coredumpv(&rproc->dev, data, data_size, GFP_KERNEL);
+		return;
+	}
+
+	/* Initialize the dump state struct to be used by rproc_coredump_read */
+	dump_state.rproc = rproc;
+	dump_state.header = data;
+	init_completion(&dump_state.dump_done);
+
+	dev_coredumpm(&rproc->dev, NULL, &dump_state, data_size, GFP_KERNEL,
+		      rproc_coredump_read, rproc_coredump_free);
+
+	/* Wait until the dump is read and free is called. Data is freed
+	 * by devcoredump framework automatically after 5 minutes.
+	 */
+	wait_for_completion(&dump_state.dump_done);
+}
+EXPORT_SYMBOL(rproc_coredump_using_sections);
diff --git a/drivers/remoteproc/remoteproc_elf_helpers.h b/drivers/remoteproc/remoteproc_elf_helpers.h
index 4b6be7b6bf4d..26404e68e17a 100644
--- a/drivers/remoteproc/remoteproc_elf_helpers.h
+++ b/drivers/remoteproc/remoteproc_elf_helpers.h
@@ -65,6 +65,7 @@ ELF_GEN_FIELD_GET_SET(hdr, e_type, u16)
 ELF_GEN_FIELD_GET_SET(hdr, e_version, u32)
 ELF_GEN_FIELD_GET_SET(hdr, e_ehsize, u32)
 ELF_GEN_FIELD_GET_SET(hdr, e_phentsize, u16)
+ELF_GEN_FIELD_GET_SET(hdr, e_shentsize, u16)
 
 ELF_GEN_FIELD_GET_SET(phdr, p_paddr, u64)
 ELF_GEN_FIELD_GET_SET(phdr, p_vaddr, u64)
@@ -75,6 +76,9 @@ ELF_GEN_FIELD_GET_SET(phdr, p_offset, u64)
 ELF_GEN_FIELD_GET_SET(phdr, p_flags, u32)
 ELF_GEN_FIELD_GET_SET(phdr, p_align, u64)
 
+ELF_GEN_FIELD_GET_SET(shdr, sh_type, u32)
+ELF_GEN_FIELD_GET_SET(shdr, sh_flags, u32)
+ELF_GEN_FIELD_GET_SET(shdr, sh_entsize, u16)
 ELF_GEN_FIELD_GET_SET(shdr, sh_size, u64)
 ELF_GEN_FIELD_GET_SET(shdr, sh_offset, u64)
 ELF_GEN_FIELD_GET_SET(shdr, sh_name, u32)
@@ -93,4 +97,26 @@ ELF_STRUCT_SIZE(shdr)
 ELF_STRUCT_SIZE(phdr)
 ELF_STRUCT_SIZE(hdr)
 
+static inline unsigned int elf_strtbl_add(const char *name, void *ehdr, u8 class, size_t *index)
+{
+	u16 shstrndx = elf_hdr_get_e_shstrndx(class, ehdr);
+	void *shdr;
+	char *strtab;
+	size_t idx, ret;
+
+	shdr = ehdr + elf_size_of_hdr(class) + shstrndx * elf_size_of_shdr(class);
+	strtab = ehdr + elf_shdr_get_sh_offset(class, shdr);
+	idx = index ? *index : 0;
+	if (!strtab || !name)
+		return 0;
+
+	ret = idx;
+	strcpy((strtab + idx), name);
+	idx += strlen(name) + 1;
+	if (index)
+		*index = idx;
+
+	return ret;
+}
+
 #endif /* REMOTEPROC_ELF_LOADER_H */
diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h
index 121c55eff3d2..f28ee75d1005 100644
--- a/include/linux/remoteproc.h
+++ b/include/linux/remoteproc.h
@@ -657,6 +657,7 @@ int rproc_boot(struct rproc *rproc);
 void rproc_shutdown(struct rproc *rproc);
 int rproc_set_firmware(struct rproc *rproc, const char *fw_name);
 void rproc_report_crash(struct rproc *rproc, enum rproc_crash_type type);
+void rproc_coredump_using_sections(struct rproc *rproc);
 int rproc_coredump_add_segment(struct rproc *rproc, dma_addr_t da, size_t size);
 int rproc_coredump_add_custom_segment(struct rproc *rproc,
 				      dma_addr_t da, size_t size,
-- 
cgit v1.2.3


From e7708f5b10e205d6291bb495e645a03553b9768b Mon Sep 17 00:00:00 2001
From: Krzysztof Wilczyński <kw@linux.com>
Date: Sun, 29 Nov 2020 23:07:39 +0000
Subject: PCI: Unify ECAM constants in native PCI Express drivers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add ECAM-related constants to provide a set of standard constants
defining memory address shift values to the byte-level address that can
be used to access the PCI Express Configuration Space, and then move
native PCI Express controller drivers to use the newly introduced
definitions retiring driver-specific ones.

Refactor pci_ecam_map_bus() function to use newly added constants so
that limits to the bus, device function and offset (now limited to 4K as
per the specification) are in place to prevent the defective or
malicious caller from supplying incorrect configuration offset and thus
targeting the wrong device when accessing extended configuration space.

This refactor also allows for the ".bus_shift" initialisers to be
dropped when the user is not using a custom value as a default value
will be used as per the PCI Express Specification.

Thanks to Qian Cai <qcai@redhat.com>, Michael Walle <michael@walle.cc>,
and Vladimir Oltean <olteanv@gmail.com> for reporting a pci_ecam_create()
issue with .bus_shift and to Vladimir for proposing the fix.

[bhelgaas: incorporate Vladimir's fix, update commit log]
Suggested-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://lore.kernel.org/r/20201129230743.3006978-2-kw@linux.com
Tested-by: Michael Walle <michael@walle.cc>
Signed-off-by: Krzysztof Wilczyński <kw@linux.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jon Derrick <jonathan.derrick@intel.com>
Reviewed-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/controller/dwc/pcie-al.c        | 12 ++---------
 drivers/pci/controller/dwc/pcie-hisi.c      |  2 --
 drivers/pci/controller/pci-aardvark.c       | 13 +++---------
 drivers/pci/controller/pci-host-generic.c   |  1 -
 drivers/pci/controller/pci-thunder-ecam.c   |  1 -
 drivers/pci/controller/pcie-brcmstb.c       | 16 ++-------------
 drivers/pci/controller/pcie-rockchip-host.c | 27 ++++++++++++------------
 drivers/pci/controller/pcie-rockchip.h      |  8 +-------
 drivers/pci/controller/pcie-tango.c         |  1 -
 drivers/pci/controller/pcie-xilinx-nwl.c    |  9 ++------
 drivers/pci/controller/pcie-xilinx.c        | 11 ++--------
 drivers/pci/controller/vmd.c                | 11 +++++-----
 drivers/pci/ecam.c                          | 32 +++++++++++++++++++++--------
 include/linux/pci-ecam.h                    | 27 ++++++++++++++++++++++++
 14 files changed, 80 insertions(+), 91 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/pci/controller/dwc/pcie-al.c b/drivers/pci/controller/dwc/pcie-al.c
index f973fbca90cf..af9e51ab1af8 100644
--- a/drivers/pci/controller/dwc/pcie-al.c
+++ b/drivers/pci/controller/dwc/pcie-al.c
@@ -76,7 +76,6 @@ static int al_pcie_init(struct pci_config_window *cfg)
 }
 
 const struct pci_ecam_ops al_pcie_ops = {
-	.bus_shift    = 20,
 	.init         =  al_pcie_init,
 	.pci_ops      = {
 		.map_bus    = al_pcie_map_bus,
@@ -138,8 +137,6 @@ struct al_pcie {
 	struct al_pcie_target_bus_cfg target_bus_cfg;
 };
 
-#define PCIE_ECAM_DEVFN(x)		(((x) & 0xff) << 12)
-
 #define to_al_pcie(x)		dev_get_drvdata((x)->dev)
 
 static inline u32 al_pcie_controller_readl(struct al_pcie *pcie, u32 offset)
@@ -226,11 +223,6 @@ static void __iomem *al_pcie_conf_addr_map_bus(struct pci_bus *bus,
 	struct al_pcie_target_bus_cfg *target_bus_cfg = &pcie->target_bus_cfg;
 	unsigned int busnr_ecam = busnr & target_bus_cfg->ecam_mask;
 	unsigned int busnr_reg = busnr & target_bus_cfg->reg_mask;
-	void __iomem *pci_base_addr;
-
-	pci_base_addr = (void __iomem *)((uintptr_t)pp->va_cfg0_base +
-					 (busnr_ecam << 20) +
-					 PCIE_ECAM_DEVFN(devfn));
 
 	if (busnr_reg != target_bus_cfg->reg_val) {
 		dev_dbg(pcie->pci->dev, "Changing target bus busnum val from 0x%x to 0x%x\n",
@@ -241,7 +233,7 @@ static void __iomem *al_pcie_conf_addr_map_bus(struct pci_bus *bus,
 				       target_bus_cfg->reg_mask);
 	}
 
-	return pci_base_addr + where;
+	return pp->va_cfg0_base + PCIE_ECAM_OFFSET(busnr_ecam, devfn, where);
 }
 
 static struct pci_ops al_child_pci_ops = {
@@ -264,7 +256,7 @@ static void al_pcie_config_prepare(struct al_pcie *pcie)
 
 	target_bus_cfg = &pcie->target_bus_cfg;
 
-	ecam_bus_mask = (pcie->ecam_size >> 20) - 1;
+	ecam_bus_mask = (pcie->ecam_size >> PCIE_ECAM_BUS_SHIFT) - 1;
 	if (ecam_bus_mask > 255) {
 		dev_warn(pcie->dev, "ECAM window size is larger than 256MB. Cutting off at 256\n");
 		ecam_bus_mask = 255;
diff --git a/drivers/pci/controller/dwc/pcie-hisi.c b/drivers/pci/controller/dwc/pcie-hisi.c
index 5ca86796d43a..8fc5960faf28 100644
--- a/drivers/pci/controller/dwc/pcie-hisi.c
+++ b/drivers/pci/controller/dwc/pcie-hisi.c
@@ -100,7 +100,6 @@ static int hisi_pcie_init(struct pci_config_window *cfg)
 }
 
 const struct pci_ecam_ops hisi_pcie_ops = {
-	.bus_shift    = 20,
 	.init         =  hisi_pcie_init,
 	.pci_ops      = {
 		.map_bus    = hisi_pcie_map_bus,
@@ -135,7 +134,6 @@ static int hisi_pcie_platform_init(struct pci_config_window *cfg)
 }
 
 static const struct pci_ecam_ops hisi_pcie_platform_ops = {
-	.bus_shift    = 20,
 	.init         =  hisi_pcie_platform_init,
 	.pci_ops      = {
 		.map_bus    = hisi_pcie_map_bus,
diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c
index 0be485a25327..1043e54c73bd 100644
--- a/drivers/pci/controller/pci-aardvark.c
+++ b/drivers/pci/controller/pci-aardvark.c
@@ -16,6 +16,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
+#include <linux/pci-ecam.h>
 #include <linux/init.h>
 #include <linux/phy/phy.h>
 #include <linux/platform_device.h>
@@ -164,14 +165,6 @@
 #define PCIE_CONFIG_WR_TYPE0			0xa
 #define PCIE_CONFIG_WR_TYPE1			0xb
 
-#define PCIE_CONF_BUS(bus)			(((bus) & 0xff) << 20)
-#define PCIE_CONF_DEV(dev)			(((dev) & 0x1f) << 15)
-#define PCIE_CONF_FUNC(fun)			(((fun) & 0x7)	<< 12)
-#define PCIE_CONF_REG(reg)			((reg) & 0xffc)
-#define PCIE_CONF_ADDR(bus, devfn, where)	\
-	(PCIE_CONF_BUS(bus) | PCIE_CONF_DEV(PCI_SLOT(devfn))	| \
-	 PCIE_CONF_FUNC(PCI_FUNC(devfn)) | PCIE_CONF_REG(where))
-
 #define PIO_RETRY_CNT			500
 #define PIO_RETRY_DELAY			2 /* 2 us*/
 
@@ -687,7 +680,7 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn,
 	advk_writel(pcie, reg, PIO_CTRL);
 
 	/* Program the address registers */
-	reg = PCIE_CONF_ADDR(bus->number, devfn, where);
+	reg = ALIGN_DOWN(PCIE_ECAM_OFFSET(bus->number, devfn, where), 4);
 	advk_writel(pcie, reg, PIO_ADDR_LS);
 	advk_writel(pcie, 0, PIO_ADDR_MS);
 
@@ -748,7 +741,7 @@ static int advk_pcie_wr_conf(struct pci_bus *bus, u32 devfn,
 	advk_writel(pcie, reg, PIO_CTRL);
 
 	/* Program the address registers */
-	reg = PCIE_CONF_ADDR(bus->number, devfn, where);
+	reg = ALIGN_DOWN(PCIE_ECAM_OFFSET(bus->number, devfn, where), 4);
 	advk_writel(pcie, reg, PIO_ADDR_LS);
 	advk_writel(pcie, 0, PIO_ADDR_MS);
 
diff --git a/drivers/pci/controller/pci-host-generic.c b/drivers/pci/controller/pci-host-generic.c
index b51977abfdf1..63865aeb636b 100644
--- a/drivers/pci/controller/pci-host-generic.c
+++ b/drivers/pci/controller/pci-host-generic.c
@@ -49,7 +49,6 @@ static void __iomem *pci_dw_ecam_map_bus(struct pci_bus *bus,
 }
 
 static const struct pci_ecam_ops pci_dw_ecam_bus_ops = {
-	.bus_shift	= 20,
 	.pci_ops	= {
 		.map_bus	= pci_dw_ecam_map_bus,
 		.read		= pci_generic_config_read,
diff --git a/drivers/pci/controller/pci-thunder-ecam.c b/drivers/pci/controller/pci-thunder-ecam.c
index 7e8835fee5f7..f964fd26f7e0 100644
--- a/drivers/pci/controller/pci-thunder-ecam.c
+++ b/drivers/pci/controller/pci-thunder-ecam.c
@@ -346,7 +346,6 @@ static int thunder_ecam_config_write(struct pci_bus *bus, unsigned int devfn,
 }
 
 const struct pci_ecam_ops pci_thunder_ecam_ops = {
-	.bus_shift	= 20,
 	.pci_ops	= {
 		.map_bus        = pci_ecam_map_bus,
 		.read           = thunder_ecam_config_read,
diff --git a/drivers/pci/controller/pcie-brcmstb.c b/drivers/pci/controller/pcie-brcmstb.c
index bea86899bd5d..7fc80fd6f13f 100644
--- a/drivers/pci/controller/pcie-brcmstb.c
+++ b/drivers/pci/controller/pcie-brcmstb.c
@@ -22,6 +22,7 @@
 #include <linux/of_pci.h>
 #include <linux/of_platform.h>
 #include <linux/pci.h>
+#include <linux/pci-ecam.h>
 #include <linux/printk.h>
 #include <linux/reset.h>
 #include <linux/sizes.h>
@@ -127,11 +128,7 @@
 #define  MSI_INT_MASK_CLR		0x14
 
 #define PCIE_EXT_CFG_DATA				0x8000
-
 #define PCIE_EXT_CFG_INDEX				0x9000
-#define  PCIE_EXT_BUSNUM_SHIFT				20
-#define  PCIE_EXT_SLOT_SHIFT				15
-#define  PCIE_EXT_FUNC_SHIFT				12
 
 #define  PCIE_RGR1_SW_INIT_1_PERST_MASK			0x1
 #define  PCIE_RGR1_SW_INIT_1_PERST_SHIFT		0x0
@@ -695,15 +692,6 @@ static bool brcm_pcie_link_up(struct brcm_pcie *pcie)
 	return dla && plu;
 }
 
-/* Configuration space read/write support */
-static inline int brcm_pcie_cfg_index(int busnr, int devfn, int reg)
-{
-	return ((PCI_SLOT(devfn) & 0x1f) << PCIE_EXT_SLOT_SHIFT)
-		| ((PCI_FUNC(devfn) & 0x07) << PCIE_EXT_FUNC_SHIFT)
-		| (busnr << PCIE_EXT_BUSNUM_SHIFT)
-		| (reg & ~3);
-}
-
 static void __iomem *brcm_pcie_map_conf(struct pci_bus *bus, unsigned int devfn,
 					int where)
 {
@@ -716,7 +704,7 @@ static void __iomem *brcm_pcie_map_conf(struct pci_bus *bus, unsigned int devfn,
 		return PCI_SLOT(devfn) ? NULL : base + where;
 
 	/* For devices, write to the config space index register */
-	idx = brcm_pcie_cfg_index(bus->number, devfn, 0);
+	idx = PCIE_ECAM_OFFSET(bus->number, devfn, 0);
 	writel(idx, pcie->base + PCIE_EXT_CFG_INDEX);
 	return base + PCIE_EXT_CFG_DATA + where;
 }
diff --git a/drivers/pci/controller/pcie-rockchip-host.c b/drivers/pci/controller/pcie-rockchip-host.c
index 9705059523a6..f1d08a1b1591 100644
--- a/drivers/pci/controller/pcie-rockchip-host.c
+++ b/drivers/pci/controller/pcie-rockchip-host.c
@@ -157,12 +157,11 @@ static int rockchip_pcie_rd_other_conf(struct rockchip_pcie *rockchip,
 				       struct pci_bus *bus, u32 devfn,
 				       int where, int size, u32 *val)
 {
-	u32 busdev;
+	void __iomem *addr;
 
-	busdev = PCIE_ECAM_ADDR(bus->number, PCI_SLOT(devfn),
-				PCI_FUNC(devfn), where);
+	addr = rockchip->reg_base + PCIE_ECAM_OFFSET(bus->number, devfn, where);
 
-	if (!IS_ALIGNED(busdev, size)) {
+	if (!IS_ALIGNED((uintptr_t)addr, size)) {
 		*val = 0;
 		return PCIBIOS_BAD_REGISTER_NUMBER;
 	}
@@ -175,11 +174,11 @@ static int rockchip_pcie_rd_other_conf(struct rockchip_pcie *rockchip,
 						AXI_WRAPPER_TYPE1_CFG);
 
 	if (size == 4) {
-		*val = readl(rockchip->reg_base + busdev);
+		*val = readl(addr);
 	} else if (size == 2) {
-		*val = readw(rockchip->reg_base + busdev);
+		*val = readw(addr);
 	} else if (size == 1) {
-		*val = readb(rockchip->reg_base + busdev);
+		*val = readb(addr);
 	} else {
 		*val = 0;
 		return PCIBIOS_BAD_REGISTER_NUMBER;
@@ -191,11 +190,11 @@ static int rockchip_pcie_wr_other_conf(struct rockchip_pcie *rockchip,
 				       struct pci_bus *bus, u32 devfn,
 				       int where, int size, u32 val)
 {
-	u32 busdev;
+	void __iomem *addr;
 
-	busdev = PCIE_ECAM_ADDR(bus->number, PCI_SLOT(devfn),
-				PCI_FUNC(devfn), where);
-	if (!IS_ALIGNED(busdev, size))
+	addr = rockchip->reg_base + PCIE_ECAM_OFFSET(bus->number, devfn, where);
+
+	if (!IS_ALIGNED((uintptr_t)addr, size))
 		return PCIBIOS_BAD_REGISTER_NUMBER;
 
 	if (pci_is_root_bus(bus->parent))
@@ -206,11 +205,11 @@ static int rockchip_pcie_wr_other_conf(struct rockchip_pcie *rockchip,
 						AXI_WRAPPER_TYPE1_CFG);
 
 	if (size == 4)
-		writel(val, rockchip->reg_base + busdev);
+		writel(val, addr);
 	else if (size == 2)
-		writew(val, rockchip->reg_base + busdev);
+		writew(val, addr);
 	else if (size == 1)
-		writeb(val, rockchip->reg_base + busdev);
+		writeb(val, addr);
 	else
 		return PCIBIOS_BAD_REGISTER_NUMBER;
 
diff --git a/drivers/pci/controller/pcie-rockchip.h b/drivers/pci/controller/pcie-rockchip.h
index c7d0178fc8c2..1650a5087450 100644
--- a/drivers/pci/controller/pcie-rockchip.h
+++ b/drivers/pci/controller/pcie-rockchip.h
@@ -13,6 +13,7 @@
 
 #include <linux/kernel.h>
 #include <linux/pci.h>
+#include <linux/pci-ecam.h>
 
 /*
  * The upper 16 bits of PCIE_CLIENT_CONFIG are a write mask for the lower 16
@@ -178,13 +179,6 @@
 #define MIN_AXI_ADDR_BITS_PASSED		8
 #define PCIE_RC_SEND_PME_OFF			0x11960
 #define ROCKCHIP_VENDOR_ID			0x1d87
-#define PCIE_ECAM_BUS(x)			(((x) & 0xff) << 20)
-#define PCIE_ECAM_DEV(x)			(((x) & 0x1f) << 15)
-#define PCIE_ECAM_FUNC(x)			(((x) & 0x7) << 12)
-#define PCIE_ECAM_REG(x)			(((x) & 0xfff) << 0)
-#define PCIE_ECAM_ADDR(bus, dev, func, reg) \
-	  (PCIE_ECAM_BUS(bus) | PCIE_ECAM_DEV(dev) | \
-	   PCIE_ECAM_FUNC(func) | PCIE_ECAM_REG(reg))
 #define PCIE_LINK_IS_L2(x) \
 	(((x) & PCIE_CLIENT_DEBUG_LTSSM_MASK) == PCIE_CLIENT_DEBUG_LTSSM_L2)
 #define PCIE_LINK_UP(x) \
diff --git a/drivers/pci/controller/pcie-tango.c b/drivers/pci/controller/pcie-tango.c
index d093a8ce4bb1..62a061f1d62e 100644
--- a/drivers/pci/controller/pcie-tango.c
+++ b/drivers/pci/controller/pcie-tango.c
@@ -208,7 +208,6 @@ static int smp8759_config_write(struct pci_bus *bus, unsigned int devfn,
 }
 
 static const struct pci_ecam_ops smp8759_ecam_ops = {
-	.bus_shift	= 20,
 	.pci_ops	= {
 		.map_bus	= pci_ecam_map_bus,
 		.read		= smp8759_config_read,
diff --git a/drivers/pci/controller/pcie-xilinx-nwl.c b/drivers/pci/controller/pcie-xilinx-nwl.c
index f3cf7d61924f..7f29c2fdcd51 100644
--- a/drivers/pci/controller/pcie-xilinx-nwl.c
+++ b/drivers/pci/controller/pcie-xilinx-nwl.c
@@ -18,6 +18,7 @@
 #include <linux/of_platform.h>
 #include <linux/of_irq.h>
 #include <linux/pci.h>
+#include <linux/pci-ecam.h>
 #include <linux/platform_device.h>
 #include <linux/irqchip/chained_irq.h>
 
@@ -124,8 +125,6 @@
 #define E_ECAM_CR_ENABLE		BIT(0)
 #define E_ECAM_SIZE_LOC			GENMASK(20, 16)
 #define E_ECAM_SIZE_SHIFT		16
-#define ECAM_BUS_LOC_SHIFT		20
-#define ECAM_DEV_LOC_SHIFT		12
 #define NWL_ECAM_VALUE_DEFAULT		12
 
 #define CFG_DMA_REG_BAR			GENMASK(2, 0)
@@ -240,15 +239,11 @@ static void __iomem *nwl_pcie_map_bus(struct pci_bus *bus, unsigned int devfn,
 				      int where)
 {
 	struct nwl_pcie *pcie = bus->sysdata;
-	int relbus;
 
 	if (!nwl_pcie_valid_device(bus, devfn))
 		return NULL;
 
-	relbus = (bus->number << ECAM_BUS_LOC_SHIFT) |
-			(devfn << ECAM_DEV_LOC_SHIFT);
-
-	return pcie->ecam_base + relbus + where;
+	return pcie->ecam_base + PCIE_ECAM_OFFSET(bus->number, devfn, where);
 }
 
 /* PCIe operations */
diff --git a/drivers/pci/controller/pcie-xilinx.c b/drivers/pci/controller/pcie-xilinx.c
index 8523be61bba5..fa5baeb82653 100644
--- a/drivers/pci/controller/pcie-xilinx.c
+++ b/drivers/pci/controller/pcie-xilinx.c
@@ -21,6 +21,7 @@
 #include <linux/of_platform.h>
 #include <linux/of_irq.h>
 #include <linux/pci.h>
+#include <linux/pci-ecam.h>
 #include <linux/platform_device.h>
 
 #include "../pci.h"
@@ -86,10 +87,6 @@
 /* Phy Status/Control Register definitions */
 #define XILINX_PCIE_REG_PSCR_LNKUP	BIT(11)
 
-/* ECAM definitions */
-#define ECAM_BUS_NUM_SHIFT		20
-#define ECAM_DEV_NUM_SHIFT		12
-
 /* Number of MSI IRQs */
 #define XILINX_NUM_MSI_IRQS		128
 
@@ -183,15 +180,11 @@ static void __iomem *xilinx_pcie_map_bus(struct pci_bus *bus,
 					 unsigned int devfn, int where)
 {
 	struct xilinx_pcie_port *port = bus->sysdata;
-	int relbus;
 
 	if (!xilinx_pcie_valid_device(bus, devfn))
 		return NULL;
 
-	relbus = (bus->number << ECAM_BUS_NUM_SHIFT) |
-		 (devfn << ECAM_DEV_NUM_SHIFT);
-
-	return port->reg_base + relbus + where;
+	return port->reg_base + PCIE_ECAM_OFFSET(bus->number, devfn, where);
 }
 
 /* PCIe operations */
diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index f375c21ceeb1..1361a79bd1e7 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <linux/msi.h>
 #include <linux/pci.h>
+#include <linux/pci-ecam.h>
 #include <linux/srcu.h>
 #include <linux/rculist.h>
 #include <linux/rcupdate.h>
@@ -328,15 +329,13 @@ static void vmd_remove_irq_domain(struct vmd_dev *vmd)
 static char __iomem *vmd_cfg_addr(struct vmd_dev *vmd, struct pci_bus *bus,
 				  unsigned int devfn, int reg, int len)
 {
-	char __iomem *addr = vmd->cfgbar +
-			     ((bus->number - vmd->busn_start) << 20) +
-			     (devfn << 12) + reg;
+	unsigned int busnr_ecam = bus->number - vmd->busn_start;
+	u32 offset = PCIE_ECAM_OFFSET(busnr_ecam, devfn, reg);
 
-	if ((addr - vmd->cfgbar) + len >=
-	    resource_size(&vmd->dev->resource[VMD_CFGBAR]))
+	if (offset + len >= resource_size(&vmd->dev->resource[VMD_CFGBAR]))
 		return NULL;
 
-	return addr;
+	return vmd->cfgbar + offset;
 }
 
 /*
diff --git a/drivers/pci/ecam.c b/drivers/pci/ecam.c
index b54d32a31669..d2a1920bb055 100644
--- a/drivers/pci/ecam.c
+++ b/drivers/pci/ecam.c
@@ -28,6 +28,7 @@ struct pci_config_window *pci_ecam_create(struct device *dev,
 		struct resource *cfgres, struct resource *busr,
 		const struct pci_ecam_ops *ops)
 {
+	unsigned int bus_shift = ops->bus_shift;
 	struct pci_config_window *cfg;
 	unsigned int bus_range, bus_range_max, bsz;
 	struct resource *conflict;
@@ -40,20 +41,24 @@ struct pci_config_window *pci_ecam_create(struct device *dev,
 	if (!cfg)
 		return ERR_PTR(-ENOMEM);
 
+	/* ECAM-compliant platforms need not supply ops->bus_shift */
+	if (!bus_shift)
+		bus_shift = PCIE_ECAM_BUS_SHIFT;
+
 	cfg->parent = dev;
 	cfg->ops = ops;
 	cfg->busr.start = busr->start;
 	cfg->busr.end = busr->end;
 	cfg->busr.flags = IORESOURCE_BUS;
 	bus_range = resource_size(&cfg->busr);
-	bus_range_max = resource_size(cfgres) >> ops->bus_shift;
+	bus_range_max = resource_size(cfgres) >> bus_shift;
 	if (bus_range > bus_range_max) {
 		bus_range = bus_range_max;
 		cfg->busr.end = busr->start + bus_range - 1;
 		dev_warn(dev, "ECAM area %pR can only accommodate %pR (reduced from %pR desired)\n",
 			 cfgres, &cfg->busr, busr);
 	}
-	bsz = 1 << ops->bus_shift;
+	bsz = 1 << bus_shift;
 
 	cfg->res.start = cfgres->start;
 	cfg->res.end = cfgres->end;
@@ -131,25 +136,36 @@ void __iomem *pci_ecam_map_bus(struct pci_bus *bus, unsigned int devfn,
 			       int where)
 {
 	struct pci_config_window *cfg = bus->sysdata;
+	unsigned int bus_shift = cfg->ops->bus_shift;
 	unsigned int devfn_shift = cfg->ops->bus_shift - 8;
 	unsigned int busn = bus->number;
 	void __iomem *base;
+	u32 bus_offset, devfn_offset;
 
 	if (busn < cfg->busr.start || busn > cfg->busr.end)
 		return NULL;
 
 	busn -= cfg->busr.start;
-	if (per_bus_mapping)
+	if (per_bus_mapping) {
 		base = cfg->winp[busn];
-	else
-		base = cfg->win + (busn << cfg->ops->bus_shift);
-	return base + (devfn << devfn_shift) + where;
+		busn = 0;
+	} else
+		base = cfg->win;
+
+	if (cfg->ops->bus_shift) {
+		bus_offset = (busn & PCIE_ECAM_BUS_MASK) << bus_shift;
+		devfn_offset = (devfn & PCIE_ECAM_DEVFN_MASK) << devfn_shift;
+		where &= PCIE_ECAM_REG_MASK;
+
+		return base + (bus_offset | devfn_offset | where);
+	}
+
+	return base + PCIE_ECAM_OFFSET(busn, devfn, where);
 }
 EXPORT_SYMBOL_GPL(pci_ecam_map_bus);
 
 /* ECAM ops */
 const struct pci_ecam_ops pci_generic_ecam_ops = {
-	.bus_shift	= 20,
 	.pci_ops	= {
 		.map_bus	= pci_ecam_map_bus,
 		.read		= pci_generic_config_read,
@@ -161,7 +177,6 @@ EXPORT_SYMBOL_GPL(pci_generic_ecam_ops);
 #if defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS)
 /* ECAM ops for 32-bit access only (non-compliant) */
 const struct pci_ecam_ops pci_32b_ops = {
-	.bus_shift	= 20,
 	.pci_ops	= {
 		.map_bus	= pci_ecam_map_bus,
 		.read		= pci_generic_config_read32,
@@ -171,7 +186,6 @@ const struct pci_ecam_ops pci_32b_ops = {
 
 /* ECAM ops for 32-bit read only (non-compliant) */
 const struct pci_ecam_ops pci_32b_read_ops = {
-	.bus_shift	= 20,
 	.pci_ops	= {
 		.map_bus	= pci_ecam_map_bus,
 		.read		= pci_generic_config_read32,
diff --git a/include/linux/pci-ecam.h b/include/linux/pci-ecam.h
index 033ce74f02e8..65d3d83015c3 100644
--- a/include/linux/pci-ecam.h
+++ b/include/linux/pci-ecam.h
@@ -9,6 +9,33 @@
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
 
+/*
+ * Memory address shift values for the byte-level address that
+ * can be used when accessing the PCI Express Configuration Space.
+ */
+
+/*
+ * Enhanced Configuration Access Mechanism (ECAM)
+ *
+ * See PCI Express Base Specification, Revision 5.0, Version 1.0,
+ * Section 7.2.2, Table 7-1, p. 677.
+ */
+#define PCIE_ECAM_BUS_SHIFT	20 /* Bus number */
+#define PCIE_ECAM_DEVFN_SHIFT	12 /* Device and Function number */
+
+#define PCIE_ECAM_BUS_MASK	0xff
+#define PCIE_ECAM_DEVFN_MASK	0xff
+#define PCIE_ECAM_REG_MASK	0xfff /* Limit offset to a maximum of 4K */
+
+#define PCIE_ECAM_BUS(x)	(((x) & PCIE_ECAM_BUS_MASK) << PCIE_ECAM_BUS_SHIFT)
+#define PCIE_ECAM_DEVFN(x)	(((x) & PCIE_ECAM_DEVFN_MASK) << PCIE_ECAM_DEVFN_SHIFT)
+#define PCIE_ECAM_REG(x)	((x) & PCIE_ECAM_REG_MASK)
+
+#define PCIE_ECAM_OFFSET(bus, devfn, where) \
+	(PCIE_ECAM_BUS(bus) | \
+	 PCIE_ECAM_DEVFN(devfn) | \
+	 PCIE_ECAM_REG(where))
+
 /*
  * struct to hold pci ops and bus shift of the config window
  * for a PCI controller.
-- 
cgit v1.2.3


From 9994bb3f36e3d181d9f0a078609038080cfd7a3d Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 30 Sep 2020 01:01:13 +0200
Subject: mtd: nand: ecc-bch: Create the software BCH engine

Let's continue introducing the generic ECC engine abstraction in the
NAND subsystem by instantiating a first ECC engine: the software
BCH one.

While at it, make a very tidy ecc_sw_bch_init() function and move all
the sanity checks and user input management in
nand_ecc_sw_bch_init_ctx(). This second helper will be called from the
raw RAND core.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200929230124.31491-10-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/ecc-sw-bch.c       | 333 +++++++++++++++++++++++++++++-------
 drivers/mtd/nand/raw/nand_base.c    |  62 +------
 include/linux/mtd/nand-ecc-sw-bch.h |  16 +-
 include/linux/mtd/nand.h            |   9 +
 4 files changed, 296 insertions(+), 124 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/ecc-sw-bch.c b/drivers/mtd/nand/ecc-sw-bch.c
index 16a54bd2ca31..0a0ac11d5725 100644
--- a/drivers/mtd/nand/ecc-sw-bch.c
+++ b/drivers/mtd/nand/ecc-sw-bch.c
@@ -75,6 +75,19 @@ int nand_ecc_sw_bch_correct(struct nand_device *nand, unsigned char *buf,
 }
 EXPORT_SYMBOL(nand_ecc_sw_bch_correct);
 
+/**
+ * nand_ecc_sw_bch_cleanup - Cleanup software BCH ECC resources
+ * @nand: NAND device
+ */
+static void nand_ecc_sw_bch_cleanup(struct nand_device *nand)
+{
+	struct nand_ecc_sw_bch_conf *engine_conf = nand->ecc.ctx.priv;
+
+	bch_free(engine_conf->bch);
+	kfree(engine_conf->errloc);
+	kfree(engine_conf->eccmask);
+}
+
 /**
  * nand_ecc_sw_bch_init - Initialize software BCH ECC engine
  * @nand: NAND device
@@ -92,107 +105,301 @@ EXPORT_SYMBOL(nand_ecc_sw_bch_correct);
  * step_size = 512 (thus, m = 13 is the smallest integer such that 2^m - 1 > 512 * 8)
  * bytes = 7 (7 bytes are required to store m * t = 13 * 4 = 52 bits)
  */
-int nand_ecc_sw_bch_init(struct nand_device *nand)
+static int nand_ecc_sw_bch_init(struct nand_device *nand)
 {
-	struct mtd_info *mtd = nanddev_to_mtd(nand);
-	unsigned int m, t, eccsteps, i;
 	struct nand_ecc_sw_bch_conf *engine_conf = nand->ecc.ctx.priv;
-	unsigned char *erased_page;
 	unsigned int eccsize = nand->ecc.ctx.conf.step_size;
 	unsigned int eccbytes = engine_conf->code_size;
-	unsigned int eccstrength = nand->ecc.ctx.conf.strength;
-
-	if (!eccbytes && eccstrength) {
-		eccbytes = DIV_ROUND_UP(eccstrength * fls(8 * eccsize), 8);
-		engine_conf->code_size = eccbytes;
-	}
-
-	if (!eccsize || !eccbytes) {
-		pr_warn("ecc parameters not supplied\n");
-		return -EINVAL;
-	}
+	unsigned int m, t, i;
+	unsigned char *erased_page;
+	int ret;
 
-	m = fls(1+8*eccsize);
-	t = (eccbytes*8)/m;
+	m = fls(1 + (8 * eccsize));
+	t = (eccbytes * 8) / m;
 
 	engine_conf->bch = bch_init(m, t, 0, false);
 	if (!engine_conf->bch)
 		return -EINVAL;
 
-	/* verify that eccbytes has the expected value */
-	if (engine_conf->bch->ecc_bytes != eccbytes) {
-		pr_warn("invalid eccbytes %u, should be %u\n",
-			eccbytes, engine_conf->bch->ecc_bytes);
-		goto fail;
+	engine_conf->eccmask = kzalloc(eccbytes, GFP_KERNEL);
+	engine_conf->errloc = kmalloc_array(t, sizeof(*engine_conf->errloc),
+					    GFP_KERNEL);
+	if (!engine_conf->eccmask || !engine_conf->errloc) {
+		ret = -ENOMEM;
+		goto cleanup;
+	}
+
+	/* Compute and store the inverted ECC of an erased step */
+	erased_page = kmalloc(eccsize, GFP_KERNEL);
+	if (!erased_page) {
+		ret = -ENOMEM;
+		goto cleanup;
 	}
 
-	eccsteps = mtd->writesize/eccsize;
+	memset(erased_page, 0xff, eccsize);
+	bch_encode(engine_conf->bch, erased_page, eccsize,
+		   engine_conf->eccmask);
+	kfree(erased_page);
+
+	for (i = 0; i < eccbytes; i++)
+		engine_conf->eccmask[i] ^= 0xff;
 
-	/* Check that we have an oob layout description. */
-	if (!mtd->ooblayout) {
-		pr_warn("missing oob scheme");
-		goto fail;
+	/* Verify that the number of code bytes has the expected value */
+	if (engine_conf->bch->ecc_bytes != eccbytes) {
+		pr_err("Invalid number of ECC bytes: %u, expected: %u\n",
+		       eccbytes, engine_conf->bch->ecc_bytes);
+		ret = -EINVAL;
+		goto cleanup;
 	}
 
-	/* sanity checks */
-	if (8*(eccsize+eccbytes) >= (1 << m)) {
-		pr_warn("eccsize %u is too large\n", eccsize);
-		goto fail;
+	/* Sanity checks */
+	if (8 * (eccsize + eccbytes) >= (1 << m)) {
+		pr_err("ECC step size is too large (%u)\n", eccsize);
+		ret = -EINVAL;
+		goto cleanup;
 	}
 
-	if (mtd_ooblayout_count_eccbytes(mtd) != (eccsteps*eccbytes)) {
-		pr_warn("invalid ecc layout\n");
-		goto fail;
+	return 0;
+
+cleanup:
+	nand_ecc_sw_bch_cleanup(nand);
+
+	return ret;
+}
+
+int nand_ecc_sw_bch_init_ctx(struct nand_device *nand)
+{
+	struct nand_ecc_props *conf = &nand->ecc.ctx.conf;
+	struct mtd_info *mtd = nanddev_to_mtd(nand);
+	struct nand_ecc_sw_bch_conf *engine_conf;
+	unsigned int code_size = 0, nsteps;
+	int ret;
+
+	/* Only large page NAND chips may use BCH */
+	if (mtd->oobsize < 64) {
+		pr_err("BCH cannot be used with small page NAND chips\n");
+		return -EINVAL;
 	}
 
-	engine_conf->eccmask = kzalloc(eccbytes, GFP_KERNEL);
-	engine_conf->errloc = kmalloc_array(t, sizeof(*engine_conf->errloc),
-					    GFP_KERNEL);
-	if (!engine_conf->eccmask || !engine_conf->errloc)
-		goto fail;
+	if (!mtd->ooblayout)
+		mtd_set_ooblayout(mtd, nand_get_large_page_ooblayout());
+
+	conf->engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
+	conf->algo = NAND_ECC_ALGO_BCH;
+	conf->step_size = nand->ecc.user_conf.step_size;
+	conf->strength = nand->ecc.user_conf.strength;
 
 	/*
-	 * compute and store the inverted ecc of an erased ecc block
+	 * Board driver should supply ECC size and ECC strength
+	 * values to select how many bits are correctable.
+	 * Otherwise, default to 512 bytes for large page devices and 256 for
+	 * small page devices.
 	 */
-	erased_page = kmalloc(eccsize, GFP_KERNEL);
-	if (!erased_page)
-		goto fail;
+	if (!conf->step_size) {
+		if (mtd->oobsize >= 64)
+			conf->step_size = 512;
+		else
+			conf->step_size = 256;
 
-	memset(erased_page, 0xff, eccsize);
-	bch_encode(engine_conf->bch, erased_page, eccsize,
-		   engine_conf->eccmask);
-	kfree(erased_page);
+		conf->strength = 4;
+	}
 
-	for (i = 0; i < eccbytes; i++)
-		engine_conf->eccmask[i] ^= 0xff;
+	nsteps = mtd->writesize / conf->step_size;
+
+	/* Maximize */
+	if (nand->ecc.user_conf.flags & NAND_ECC_MAXIMIZE_STRENGTH) {
+		conf->step_size = 1024;
+		nsteps = mtd->writesize / conf->step_size;
+		/* Reserve 2 bytes for the BBM */
+		code_size = (mtd->oobsize - 2) / nsteps;
+		conf->strength = code_size * 8 / fls(8 * conf->step_size);
+	}
+
+	if (!code_size)
+		code_size = DIV_ROUND_UP(conf->strength *
+					 fls(8 * conf->step_size), 8);
+
+	if (!conf->strength)
+		conf->strength = (code_size * 8) / fls(8 * conf->step_size);
+
+	if (!code_size && !conf->strength) {
+		pr_err("Missing ECC parameters\n");
+		return -EINVAL;
+	}
+
+	engine_conf = kzalloc(sizeof(*engine_conf), GFP_KERNEL);
+	if (!engine_conf)
+		return -ENOMEM;
+
+	ret = nand_ecc_init_req_tweaking(&engine_conf->req_ctx, nand);
+	if (ret)
+		goto free_engine_conf;
+
+	engine_conf->code_size = code_size;
+	engine_conf->nsteps = nsteps;
+	engine_conf->calc_buf = kzalloc(mtd->oobsize, GFP_KERNEL);
+	engine_conf->code_buf = kzalloc(mtd->oobsize, GFP_KERNEL);
+	if (!engine_conf->calc_buf || !engine_conf->code_buf) {
+		ret = -ENOMEM;
+		goto free_bufs;
+	}
 
-	if (!eccstrength)
-		nand->ecc.ctx.conf.strength = (eccbytes * 8) / fls(8 * eccsize);
+	nand->ecc.ctx.priv = engine_conf;
+	nand->ecc.ctx.total = nsteps * code_size;
+
+	ret = nand_ecc_sw_bch_init(nand);
+	if (ret)
+		goto free_bufs;
+
+	/* Verify the layout validity */
+	if (mtd_ooblayout_count_eccbytes(mtd) !=
+	    engine_conf->nsteps * engine_conf->code_size) {
+		pr_err("Invalid ECC layout\n");
+		ret = -EINVAL;
+		goto cleanup_bch_ctx;
+	}
 
 	return 0;
 
-fail:
+cleanup_bch_ctx:
 	nand_ecc_sw_bch_cleanup(nand);
+free_bufs:
+	nand_ecc_cleanup_req_tweaking(&engine_conf->req_ctx);
+	kfree(engine_conf->calc_buf);
+	kfree(engine_conf->code_buf);
+free_engine_conf:
+	kfree(engine_conf);
 
-	return -EINVAL;
+	return ret;
 }
-EXPORT_SYMBOL(nand_ecc_sw_bch_init);
+EXPORT_SYMBOL(nand_ecc_sw_bch_init_ctx);
 
-/**
- * nand_ecc_sw_bch_cleanup - Cleanup software BCH ECC resources
- * @nand: NAND device
- */
-void nand_ecc_sw_bch_cleanup(struct nand_device *nand)
+void nand_ecc_sw_bch_cleanup_ctx(struct nand_device *nand)
 {
 	struct nand_ecc_sw_bch_conf *engine_conf = nand->ecc.ctx.priv;
 
 	if (engine_conf) {
-		bch_free(engine_conf->bch);
-		kfree(engine_conf->errloc);
-		kfree(engine_conf->eccmask);
+		nand_ecc_sw_bch_cleanup(nand);
+		nand_ecc_cleanup_req_tweaking(&engine_conf->req_ctx);
+		kfree(engine_conf->calc_buf);
+		kfree(engine_conf->code_buf);
+		kfree(engine_conf);
+	}
+}
+EXPORT_SYMBOL(nand_ecc_sw_bch_cleanup_ctx);
+
+static int nand_ecc_sw_bch_prepare_io_req(struct nand_device *nand,
+					  struct nand_page_io_req *req)
+{
+	struct nand_ecc_sw_bch_conf *engine_conf = nand->ecc.ctx.priv;
+	struct mtd_info *mtd = nanddev_to_mtd(nand);
+	int eccsize = nand->ecc.ctx.conf.step_size;
+	int eccbytes = engine_conf->code_size;
+	int eccsteps = engine_conf->nsteps;
+	int total = nand->ecc.ctx.total;
+	u8 *ecccalc = engine_conf->calc_buf;
+	const u8 *data;
+	int i;
+
+	/* Nothing to do for a raw operation */
+	if (req->mode == MTD_OPS_RAW)
+		return 0;
+
+	/* This engine does not provide BBM/free OOB bytes protection */
+	if (!req->datalen)
+		return 0;
+
+	nand_ecc_tweak_req(&engine_conf->req_ctx, req);
+
+	/* No more preparation for page read */
+	if (req->type == NAND_PAGE_READ)
+		return 0;
+
+	/* Preparation for page write: derive the ECC bytes and place them */
+	for (i = 0, data = req->databuf.out;
+	     eccsteps;
+	     eccsteps--, i += eccbytes, data += eccsize)
+		nand_ecc_sw_bch_calculate(nand, data, &ecccalc[i]);
+
+	return mtd_ooblayout_set_eccbytes(mtd, ecccalc, (void *)req->oobbuf.out,
+					  0, total);
+}
+
+static int nand_ecc_sw_bch_finish_io_req(struct nand_device *nand,
+					 struct nand_page_io_req *req)
+{
+	struct nand_ecc_sw_bch_conf *engine_conf = nand->ecc.ctx.priv;
+	struct mtd_info *mtd = nanddev_to_mtd(nand);
+	int eccsize = nand->ecc.ctx.conf.step_size;
+	int total = nand->ecc.ctx.total;
+	int eccbytes = engine_conf->code_size;
+	int eccsteps = engine_conf->nsteps;
+	u8 *ecccalc = engine_conf->calc_buf;
+	u8 *ecccode = engine_conf->code_buf;
+	unsigned int max_bitflips = 0;
+	u8 *data = req->databuf.in;
+	int i, ret;
+
+	/* Nothing to do for a raw operation */
+	if (req->mode == MTD_OPS_RAW)
+		return 0;
+
+	/* This engine does not provide BBM/free OOB bytes protection */
+	if (!req->datalen)
+		return 0;
+
+	/* No more preparation for page write */
+	if (req->type == NAND_PAGE_WRITE) {
+		nand_ecc_restore_req(&engine_conf->req_ctx, req);
+		return 0;
 	}
+
+	/* Finish a page read: retrieve the (raw) ECC bytes*/
+	ret = mtd_ooblayout_get_eccbytes(mtd, ecccode, req->oobbuf.in, 0,
+					 total);
+	if (ret)
+		return ret;
+
+	/* Calculate the ECC bytes */
+	for (i = 0; eccsteps; eccsteps--, i += eccbytes, data += eccsize)
+		nand_ecc_sw_bch_calculate(nand, data, &ecccalc[i]);
+
+	/* Finish a page read: compare and correct */
+	for (eccsteps = engine_conf->nsteps, i = 0, data = req->databuf.in;
+	     eccsteps;
+	     eccsteps--, i += eccbytes, data += eccsize) {
+		int stat =  nand_ecc_sw_bch_correct(nand, data,
+						    &ecccode[i],
+						    &ecccalc[i]);
+		if (stat < 0) {
+			mtd->ecc_stats.failed++;
+		} else {
+			mtd->ecc_stats.corrected += stat;
+			max_bitflips = max_t(unsigned int, max_bitflips, stat);
+		}
+	}
+
+	nand_ecc_restore_req(&engine_conf->req_ctx, req);
+
+	return max_bitflips;
+}
+
+static struct nand_ecc_engine_ops nand_ecc_sw_bch_engine_ops = {
+	.init_ctx = nand_ecc_sw_bch_init_ctx,
+	.cleanup_ctx = nand_ecc_sw_bch_cleanup_ctx,
+	.prepare_io_req = nand_ecc_sw_bch_prepare_io_req,
+	.finish_io_req = nand_ecc_sw_bch_finish_io_req,
+};
+
+static struct nand_ecc_engine nand_ecc_sw_bch_engine = {
+	.ops = &nand_ecc_sw_bch_engine_ops,
+};
+
+struct nand_ecc_engine *nand_ecc_sw_bch_get_engine(void)
+{
+	return &nand_ecc_sw_bch_engine;
 }
-EXPORT_SYMBOL(nand_ecc_sw_bch_cleanup);
+EXPORT_SYMBOL(nand_ecc_sw_bch_get_engine);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Ivan Djelic <ivan.djelic@parrot.com>");
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 03106bf629dd..ebaf3bbfc1b2 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -5150,17 +5150,11 @@ int rawnand_sw_bch_init(struct nand_chip *chip)
 	base->ecc.user_conf.step_size = chip->ecc.size;
 	base->ecc.user_conf.strength = chip->ecc.strength;
 
-	engine_conf = kzalloc(sizeof(*engine_conf), GFP_KERNEL);
-	if (!engine_conf)
-		return -ENOMEM;
-
-	engine_conf->code_size = chip->ecc.bytes;
-
-	base->ecc.ctx.priv = engine_conf;
-
-	ret = nand_ecc_sw_bch_init(base);
+	ret = nand_ecc_sw_bch_init_ctx(base);
 	if (ret)
-		kfree(base->ecc.ctx.priv);
+		return ret;
+
+	engine_conf = base->ecc.ctx.priv;
 
 	chip->ecc.size = base->ecc.ctx.conf.step_size;
 	chip->ecc.strength = base->ecc.ctx.conf.strength;
@@ -5168,7 +5162,7 @@ int rawnand_sw_bch_init(struct nand_chip *chip)
 	chip->ecc.steps = engine_conf->nsteps;
 	chip->ecc.bytes = engine_conf->code_size;
 
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL(rawnand_sw_bch_init);
 
@@ -5194,9 +5188,7 @@ void rawnand_sw_bch_cleanup(struct nand_chip *chip)
 {
 	struct nand_device *base = &chip->base;
 
-	nand_ecc_sw_bch_cleanup(base);
-
-	kfree(base->ecc.ctx.priv);
+	nand_ecc_sw_bch_cleanup_ctx(base);
 }
 EXPORT_SYMBOL(rawnand_sw_bch_cleanup);
 
@@ -5308,51 +5300,15 @@ static int nand_set_ecc_soft_ops(struct nand_chip *chip)
 		ecc->read_oob = nand_read_oob_std;
 		ecc->write_oob = nand_write_oob_std;
 
-		/*
-		* Board driver should supply ecc.size and ecc.strength
-		* values to select how many bits are correctable.
-		* Otherwise, default to 4 bits for large page devices.
-		*/
-		if (!ecc->size && (mtd->oobsize >= 64)) {
-			ecc->size = 512;
-			ecc->strength = 4;
-		}
-
-		/*
-		 * if no ecc placement scheme was provided pickup the default
-		 * large page one.
-		 */
-		if (!mtd->ooblayout) {
-			/* handle large page devices only */
-			if (mtd->oobsize < 64) {
-				WARN(1, "OOB layout is required when using software BCH on small pages\n");
-				return -EINVAL;
-			}
-
-			mtd_set_ooblayout(mtd, nand_get_large_page_ooblayout());
-
-		}
-
 		/*
 		 * We can only maximize ECC config when the default layout is
 		 * used, otherwise we don't know how many bytes can really be
 		 * used.
 		 */
-		if (mtd->ooblayout == nand_get_large_page_ooblayout() &&
-		    nanddev->ecc.user_conf.flags & NAND_ECC_MAXIMIZE_STRENGTH) {
-			int steps, bytes;
-
-			/* Always prefer 1k blocks over 512bytes ones */
-			ecc->size = 1024;
-			steps = mtd->writesize / ecc->size;
+		if (nanddev->ecc.user_conf.flags & NAND_ECC_MAXIMIZE_STRENGTH &&
+		    mtd->ooblayout != nand_get_large_page_ooblayout())
+			nanddev->ecc.user_conf.flags &= ~NAND_ECC_MAXIMIZE_STRENGTH;
 
-			/* Reserve 2 bytes for the BBM */
-			bytes = (mtd->oobsize - 2) / steps;
-			ecc->strength = bytes * 8 / fls(8 * ecc->size);
-		}
-
-		/* See the software BCH ECC initialization for details */
-		ecc->bytes = 0;
 		ret = rawnand_sw_bch_init(chip);
 		if (ret) {
 			WARN(1, "BCH ECC initialization failed!\n");
diff --git a/include/linux/mtd/nand-ecc-sw-bch.h b/include/linux/mtd/nand-ecc-sw-bch.h
index ce005528e55f..22c92073b3dd 100644
--- a/include/linux/mtd/nand-ecc-sw-bch.h
+++ b/include/linux/mtd/nand-ecc-sw-bch.h
@@ -13,8 +13,8 @@
 
 /**
  * struct nand_ecc_sw_bch_conf - private software BCH ECC engine structure
- * @reqooblen: Save the actual user OOB length requested before overwriting it
- * @spare_oobbuf: Spare OOB buffer if none is provided
+ * @req_ctx: Save request context and tweak the original request to fit the
+ *           engine needs
  * @code_size: Number of bytes needed to store a code (one code per step)
  * @nsteps: Number of steps
  * @calc_buf: Buffer to use when calculating ECC bytes
@@ -24,8 +24,7 @@
  * @eccmask: XOR ecc mask, allows erased pages to be decoded as valid
  */
 struct nand_ecc_sw_bch_conf {
-	unsigned int reqooblen;
-	void *spare_oobbuf;
+	struct nand_ecc_req_tweak_ctx req_ctx;
 	unsigned int code_size;
 	unsigned int nsteps;
 	u8 *calc_buf;
@@ -41,8 +40,9 @@ int nand_ecc_sw_bch_calculate(struct nand_device *nand,
 			      const unsigned char *buf, unsigned char *code);
 int nand_ecc_sw_bch_correct(struct nand_device *nand, unsigned char *buf,
 			    unsigned char *read_ecc, unsigned char *calc_ecc);
-int nand_ecc_sw_bch_init(struct nand_device *nand);
-void nand_ecc_sw_bch_cleanup(struct nand_device *nand);
+int nand_ecc_sw_bch_init_ctx(struct nand_device *nand);
+void nand_ecc_sw_bch_cleanup_ctx(struct nand_device *nand);
+struct nand_ecc_engine *nand_ecc_sw_bch_get_engine(void);
 
 #else /* !CONFIG_MTD_NAND_ECC_SW_BCH */
 
@@ -61,12 +61,12 @@ static inline int nand_ecc_sw_bch_correct(struct nand_device *nand,
 	return -ENOTSUPP;
 }
 
-static inline int nand_ecc_sw_bch_init(struct nand_device *nand)
+static inline int nand_ecc_sw_bch_init_ctx(struct nand_device *nand)
 {
 	return -ENOTSUPP;
 }
 
-static inline void nand_ecc_sw_bch_cleanup(struct nand_device *nand) {}
+static inline void nand_ecc_sw_bch_cleanup_ctx(struct nand_device *nand) {}
 
 #endif /* CONFIG_MTD_NAND_ECC_SW_BCH */
 
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 36e4fe08d0ea..df8548187713 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -278,6 +278,15 @@ int nand_ecc_finish_io_req(struct nand_device *nand,
 			   struct nand_page_io_req *req);
 bool nand_ecc_is_strong_enough(struct nand_device *nand);
 
+#if IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_BCH)
+struct nand_ecc_engine *nand_ecc_sw_bch_get_engine(void);
+#else
+static inline struct nand_ecc_engine *nand_ecc_sw_bch_get_engine(void)
+{
+	return NULL;
+}
+#endif /* CONFIG_MTD_NAND_ECC_SW_BCH */
+
 /**
  * struct nand_ecc_req_tweak_ctx - Help for automatically tweaking requests
  * @orig_req: Pointer to the original IO request
-- 
cgit v1.2.3


From cbd87780bed580b585d2992f29077ac44950cb66 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 30 Sep 2020 01:01:14 +0200
Subject: mtd: rawnand: Get rid of chip->ecc.priv

nand_ecc_ctrl embeds a private pointer which only has a meaning in the
sunxi driver. This structure will soon be deprecated, but as this
field is actually not needed, let's just drop it.

Cc: Maxime Ripard <mripard@kernel.org>
Cc: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Acked-by: Maxime Ripard <mripard@kernel.org>
Link: https://lore.kernel.org/linux-mtd/20200929230124.31491-11-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/raw/sunxi_nand.c | 31 +++++++++++++++++--------------
 include/linux/mtd/rawnand.h       |  2 --
 2 files changed, 17 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/raw/sunxi_nand.c b/drivers/mtd/nand/raw/sunxi_nand.c
index 2a7ca3072f35..540529540ade 100644
--- a/drivers/mtd/nand/raw/sunxi_nand.c
+++ b/drivers/mtd/nand/raw/sunxi_nand.c
@@ -182,6 +182,7 @@ struct sunxi_nand_hw_ecc {
  *
  * @node: used to store NAND chips into a list
  * @nand: base NAND chip structure
+ * @ecc: ECC controller structure
  * @clk_rate: clk_rate required for this NAND chip
  * @timing_cfg: TIMING_CFG register value for this NAND chip
  * @timing_ctl: TIMING_CTL register value for this NAND chip
@@ -191,6 +192,7 @@ struct sunxi_nand_hw_ecc {
 struct sunxi_nand_chip {
 	struct list_head node;
 	struct nand_chip nand;
+	struct sunxi_nand_hw_ecc *ecc;
 	unsigned long clk_rate;
 	u32 timing_cfg;
 	u32 timing_ctl;
@@ -676,15 +678,15 @@ static void sunxi_nfc_randomizer_read_buf(struct nand_chip *nand, uint8_t *buf,
 
 static void sunxi_nfc_hw_ecc_enable(struct nand_chip *nand)
 {
+	struct sunxi_nand_chip *sunxi_nand = to_sunxi_nand(nand);
 	struct sunxi_nfc *nfc = to_sunxi_nfc(nand->controller);
-	struct sunxi_nand_hw_ecc *data = nand->ecc.priv;
 	u32 ecc_ctl;
 
 	ecc_ctl = readl(nfc->regs + NFC_REG_ECC_CTL);
 	ecc_ctl &= ~(NFC_ECC_MODE_MSK | NFC_ECC_PIPELINE |
 		     NFC_ECC_BLOCK_SIZE_MSK);
-	ecc_ctl |= NFC_ECC_EN | NFC_ECC_MODE(data->mode) | NFC_ECC_EXCEPTION |
-		   NFC_ECC_PIPELINE;
+	ecc_ctl |= NFC_ECC_EN | NFC_ECC_MODE(sunxi_nand->ecc->mode) |
+		   NFC_ECC_EXCEPTION | NFC_ECC_PIPELINE;
 
 	if (nand->ecc.size == 512)
 		ecc_ctl |= NFC_ECC_BLOCK_512;
@@ -1597,9 +1599,9 @@ static const struct mtd_ooblayout_ops sunxi_nand_ooblayout_ops = {
 	.free = sunxi_nand_ooblayout_free,
 };
 
-static void sunxi_nand_hw_ecc_ctrl_cleanup(struct nand_ecc_ctrl *ecc)
+static void sunxi_nand_hw_ecc_ctrl_cleanup(struct sunxi_nand_chip *sunxi_nand)
 {
-	kfree(ecc->priv);
+	kfree(sunxi_nand->ecc);
 }
 
 static int sunxi_nand_hw_ecc_ctrl_init(struct nand_chip *nand,
@@ -1607,10 +1609,10 @@ static int sunxi_nand_hw_ecc_ctrl_init(struct nand_chip *nand,
 				       struct device_node *np)
 {
 	static const u8 strengths[] = { 16, 24, 28, 32, 40, 48, 56, 60, 64 };
+	struct sunxi_nand_chip *sunxi_nand = to_sunxi_nand(nand);
 	struct sunxi_nfc *nfc = to_sunxi_nfc(nand->controller);
 	struct mtd_info *mtd = nand_to_mtd(nand);
 	struct nand_device *nanddev = mtd_to_nanddev(mtd);
-	struct sunxi_nand_hw_ecc *data;
 	int nsectors;
 	int ret;
 	int i;
@@ -1647,8 +1649,8 @@ static int sunxi_nand_hw_ecc_ctrl_init(struct nand_chip *nand,
 	if (ecc->size != 512 && ecc->size != 1024)
 		return -EINVAL;
 
-	data = kzalloc(sizeof(*data), GFP_KERNEL);
-	if (!data)
+	sunxi_nand->ecc = kzalloc(sizeof(*sunxi_nand->ecc), GFP_KERNEL);
+	if (!sunxi_nand->ecc)
 		return -ENOMEM;
 
 	/* Prefer 1k ECC chunk over 512 ones */
@@ -1675,7 +1677,7 @@ static int sunxi_nand_hw_ecc_ctrl_init(struct nand_chip *nand,
 		goto err;
 	}
 
-	data->mode = i;
+	sunxi_nand->ecc->mode = i;
 
 	/* HW ECC always request ECC bytes for 1024 bytes blocks */
 	ecc->bytes = DIV_ROUND_UP(ecc->strength * fls(8 * 1024), 8);
@@ -1693,7 +1695,6 @@ static int sunxi_nand_hw_ecc_ctrl_init(struct nand_chip *nand,
 	ecc->read_oob = sunxi_nfc_hw_ecc_read_oob;
 	ecc->write_oob = sunxi_nfc_hw_ecc_write_oob;
 	mtd_set_ooblayout(mtd, &sunxi_nand_ooblayout_ops);
-	ecc->priv = data;
 
 	if (nfc->dmac) {
 		ecc->read_page = sunxi_nfc_hw_ecc_read_page_dma;
@@ -1714,16 +1715,18 @@ static int sunxi_nand_hw_ecc_ctrl_init(struct nand_chip *nand,
 	return 0;
 
 err:
-	kfree(data);
+	kfree(sunxi_nand->ecc);
 
 	return ret;
 }
 
-static void sunxi_nand_ecc_cleanup(struct nand_ecc_ctrl *ecc)
+static void sunxi_nand_ecc_cleanup(struct sunxi_nand_chip *sunxi_nand)
 {
+	struct nand_ecc_ctrl *ecc = &sunxi_nand->nand.ecc;
+
 	switch (ecc->engine_type) {
 	case NAND_ECC_ENGINE_TYPE_ON_HOST:
-		sunxi_nand_hw_ecc_ctrl_cleanup(ecc);
+		sunxi_nand_hw_ecc_ctrl_cleanup(sunxi_nand);
 		break;
 	case NAND_ECC_ENGINE_TYPE_NONE:
 	default:
@@ -2053,7 +2056,7 @@ static void sunxi_nand_chips_cleanup(struct sunxi_nfc *nfc)
 		ret = mtd_device_unregister(nand_to_mtd(chip));
 		WARN_ON(ret);
 		nand_cleanup(chip);
-		sunxi_nand_ecc_cleanup(&chip->ecc);
+		sunxi_nand_ecc_cleanup(sunxi_nand);
 		list_del(&sunxi_nand->node);
 	}
 }
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 23623beaad1d..15743c2c2cab 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -302,7 +302,6 @@ static const struct nand_ecc_caps __name = {			\
  * @prepad:	padding information for syndrome based ECC generators
  * @postpad:	padding information for syndrome based ECC generators
  * @options:	ECC specific options (see NAND_ECC_XXX flags defined above)
- * @priv:	pointer to private ECC control data
  * @calc_buf:	buffer for calculated ECC, size is oobsize.
  * @code_buf:	buffer for ECC read from flash, size is oobsize.
  * @hwctl:	function to control hardware ECC generator. Must only
@@ -355,7 +354,6 @@ struct nand_ecc_ctrl {
 	int prepad;
 	int postpad;
 	unsigned int options;
-	void *priv;
 	u8 *calc_buf;
 	u8 *code_buf;
 	void (*hwctl)(struct nand_chip *chip, int mode);
-- 
cgit v1.2.3


From e5acf9c862974041f7b2f581d1a40ccd29769add Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 30 Sep 2020 01:01:15 +0200
Subject: mtd: nand: ecc-hamming: Move Hamming code to the generic NAND layer

Hamming ECC code might be later re-used by the SPI NAND layer.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200929230124.31491-12-miquel.raynal@bootlin.com
---
 arch/arm/mach-s3c/common-smdk-s3c24xx.c |   2 +-
 arch/arm/mach-s3c/mach-anubis.c         |   2 +-
 arch/arm/mach-s3c/mach-at2440evb.c      |   2 +-
 arch/arm/mach-s3c/mach-bast.c           |   2 +-
 arch/arm/mach-s3c/mach-gta02.c          |   2 +-
 arch/arm/mach-s3c/mach-jive.c           |   2 +-
 arch/arm/mach-s3c/mach-mini2440.c       |   2 +-
 arch/arm/mach-s3c/mach-osiris.c         |   2 +-
 arch/arm/mach-s3c/mach-qt2410.c         |   2 +-
 arch/arm/mach-s3c/mach-rx3715.c         |   2 +-
 arch/arm/mach-s3c/mach-vstms.c          |   2 +-
 drivers/mtd/Kconfig                     |   1 +
 drivers/mtd/nand/Kconfig                |  11 +
 drivers/mtd/nand/Makefile               |   1 +
 drivers/mtd/nand/ecc-sw-hamming.c       | 484 ++++++++++++++++++++++++++++++++
 drivers/mtd/nand/raw/Kconfig            |  11 -
 drivers/mtd/nand/raw/Makefile           |   1 -
 drivers/mtd/nand/raw/cs553x_nand.c      |   2 +-
 drivers/mtd/nand/raw/fsl_elbc_nand.c    |   2 +-
 drivers/mtd/nand/raw/fsl_ifc_nand.c     |   2 +-
 drivers/mtd/nand/raw/fsl_upm.c          |   2 +-
 drivers/mtd/nand/raw/fsmc_nand.c        |   2 +-
 drivers/mtd/nand/raw/lpc32xx_mlc.c      |   2 +-
 drivers/mtd/nand/raw/lpc32xx_slc.c      |   2 +-
 drivers/mtd/nand/raw/mxic_nand.c        |   2 +-
 drivers/mtd/nand/raw/nand_base.c        |   2 +-
 drivers/mtd/nand/raw/nand_ecc.c         | 484 --------------------------------
 drivers/mtd/nand/raw/ndfc.c             |   2 +-
 drivers/mtd/nand/raw/pasemi_nand.c      |   2 +-
 drivers/mtd/nand/raw/s3c2410.c          |   2 +-
 drivers/mtd/nand/raw/sharpsl.c          |   2 +-
 drivers/mtd/nand/raw/tmio_nand.c        |   2 +-
 drivers/mtd/nand/raw/txx9ndfmc.c        |   2 +-
 drivers/mtd/sm_ftl.c                    |   2 +-
 drivers/mtd/tests/mtd_nandecctest.c     |   2 +-
 include/linux/mtd/nand-ecc-sw-hamming.h |  39 +++
 include/linux/mtd/nand_ecc.h            |  39 ---
 include/linux/mtd/sharpsl.h             |   2 +-
 38 files changed, 565 insertions(+), 564 deletions(-)
 create mode 100644 drivers/mtd/nand/ecc-sw-hamming.c
 delete mode 100644 drivers/mtd/nand/raw/nand_ecc.c
 create mode 100644 include/linux/mtd/nand-ecc-sw-hamming.h
 delete mode 100644 include/linux/mtd/nand_ecc.h

(limited to 'include/linux')

diff --git a/arch/arm/mach-s3c/common-smdk-s3c24xx.c b/arch/arm/mach-s3c/common-smdk-s3c24xx.c
index f860d8bcba0e..6d124bbd384c 100644
--- a/arch/arm/mach-s3c/common-smdk-s3c24xx.c
+++ b/arch/arm/mach-s3c/common-smdk-s3c24xx.c
@@ -20,7 +20,7 @@
 
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand_ecc.h>
+#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/mtd/partitions.h>
 #include <linux/io.h>
 
diff --git a/arch/arm/mach-s3c/mach-anubis.c b/arch/arm/mach-s3c/mach-anubis.c
index 90e3fd98a3ac..04147cc0adcc 100644
--- a/arch/arm/mach-s3c/mach-anubis.c
+++ b/arch/arm/mach-s3c/mach-anubis.c
@@ -34,7 +34,7 @@
 
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand_ecc.h>
+#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/mtd/partitions.h>
 
 #include <net/ax88796.h>
diff --git a/arch/arm/mach-s3c/mach-at2440evb.c b/arch/arm/mach-s3c/mach-at2440evb.c
index 5fa49d4e2650..c6a5a51d84aa 100644
--- a/arch/arm/mach-s3c/mach-at2440evb.c
+++ b/arch/arm/mach-s3c/mach-at2440evb.c
@@ -35,7 +35,7 @@
 
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand_ecc.h>
+#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/mtd/partitions.h>
 
 #include "devs.h"
diff --git a/arch/arm/mach-s3c/mach-bast.c b/arch/arm/mach-s3c/mach-bast.c
index 328f5d9ae9f9..27e8d5950228 100644
--- a/arch/arm/mach-s3c/mach-bast.c
+++ b/arch/arm/mach-s3c/mach-bast.c
@@ -24,7 +24,7 @@
 
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand_ecc.h>
+#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/mtd/partitions.h>
 
 #include <linux/platform_data/asoc-s3c24xx_simtec.h>
diff --git a/arch/arm/mach-s3c/mach-gta02.c b/arch/arm/mach-s3c/mach-gta02.c
index 3c75c7d112ea..aec8b451c016 100644
--- a/arch/arm/mach-s3c/mach-gta02.c
+++ b/arch/arm/mach-s3c/mach-gta02.c
@@ -37,7 +37,7 @@
 
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand_ecc.h>
+#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/mtd/partitions.h>
 #include <linux/mtd/physmap.h>
 
diff --git a/arch/arm/mach-s3c/mach-jive.c b/arch/arm/mach-s3c/mach-jive.c
index 2a29c3eca559..0785638a9069 100644
--- a/arch/arm/mach-s3c/mach-jive.c
+++ b/arch/arm/mach-s3c/mach-jive.c
@@ -40,7 +40,7 @@
 
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand_ecc.h>
+#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/mtd/partitions.h>
 
 #include "gpio-cfg.h"
diff --git a/arch/arm/mach-s3c/mach-mini2440.c b/arch/arm/mach-s3c/mach-mini2440.c
index dc22ab839b95..4100905dfbd0 100644
--- a/arch/arm/mach-s3c/mach-mini2440.c
+++ b/arch/arm/mach-s3c/mach-mini2440.c
@@ -44,7 +44,7 @@
 
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand_ecc.h>
+#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/mtd/partitions.h>
 
 #include "gpio-cfg.h"
diff --git a/arch/arm/mach-s3c/mach-osiris.c b/arch/arm/mach-s3c/mach-osiris.c
index 81744ca67d1d..3aefb9d22340 100644
--- a/arch/arm/mach-s3c/mach-osiris.c
+++ b/arch/arm/mach-s3c/mach-osiris.c
@@ -33,7 +33,7 @@
 
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand_ecc.h>
+#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/mtd/partitions.h>
 
 #include "cpu.h"
diff --git a/arch/arm/mach-s3c/mach-qt2410.c b/arch/arm/mach-s3c/mach-qt2410.c
index 151e8e373d40..f88b961798fd 100644
--- a/arch/arm/mach-s3c/mach-qt2410.c
+++ b/arch/arm/mach-s3c/mach-qt2410.c
@@ -21,7 +21,7 @@
 #include <linux/io.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand_ecc.h>
+#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/mtd/partitions.h>
 
 #include <asm/mach/arch.h>
diff --git a/arch/arm/mach-s3c/mach-rx3715.c b/arch/arm/mach-s3c/mach-rx3715.c
index a03662a47b38..9fd2d9dc3689 100644
--- a/arch/arm/mach-s3c/mach-rx3715.c
+++ b/arch/arm/mach-s3c/mach-rx3715.c
@@ -22,7 +22,7 @@
 #include <linux/io.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand_ecc.h>
+#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/mtd/partitions.h>
 
 #include <asm/mach/arch.h>
diff --git a/arch/arm/mach-s3c/mach-vstms.c b/arch/arm/mach-s3c/mach-vstms.c
index 05f19f5ffabb..ec024af7b0ce 100644
--- a/arch/arm/mach-s3c/mach-vstms.c
+++ b/arch/arm/mach-s3c/mach-vstms.c
@@ -16,7 +16,7 @@
 #include <linux/io.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand_ecc.h>
+#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/mtd/partitions.h>
 #include <linux/memblock.h>
 
diff --git a/drivers/mtd/Kconfig b/drivers/mtd/Kconfig
index 6ddab796216d..8bab6f8718a9 100644
--- a/drivers/mtd/Kconfig
+++ b/drivers/mtd/Kconfig
@@ -152,6 +152,7 @@ config SM_FTL
 	tristate "SmartMedia/xD new translation layer"
 	depends on BLOCK
 	select MTD_BLKDEVS
+	select MTD_NAND_CORE
 	select MTD_NAND_ECC_SW_HAMMING
 	help
 	  This enables EXPERIMENTAL R/W support for SmartMedia/xD
diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig
index 55c17fb0dee1..306c33ca3448 100644
--- a/drivers/mtd/nand/Kconfig
+++ b/drivers/mtd/nand/Kconfig
@@ -15,6 +15,17 @@ config MTD_NAND_ECC
        bool
        depends on MTD_NAND_CORE
 
+config MTD_NAND_ECC_SW_HAMMING
+	bool
+
+config MTD_NAND_ECC_SW_HAMMING_SMC
+	bool "NAND ECC Smart Media byte order"
+	depends on MTD_NAND_ECC_SW_HAMMING
+	default n
+	help
+	  Software ECC according to the Smart Media Specification.
+	  The original Linux implementation had byte 0 and 1 swapped.
+
 config MTD_NAND_ECC_SW_BCH
 	bool "Software BCH ECC engine"
 	select BCH
diff --git a/drivers/mtd/nand/Makefile b/drivers/mtd/nand/Makefile
index c7179ff23753..1c0b46960eb1 100644
--- a/drivers/mtd/nand/Makefile
+++ b/drivers/mtd/nand/Makefile
@@ -8,4 +8,5 @@ obj-y	+= raw/
 obj-y	+= spi/
 
 nandcore-$(CONFIG_MTD_NAND_ECC) += ecc.o
+nandcore-$(CONFIG_MTD_NAND_ECC_SW_HAMMING) += ecc-sw-hamming.o
 nandcore-$(CONFIG_MTD_NAND_ECC_SW_BCH) += ecc-sw-bch.o
diff --git a/drivers/mtd/nand/ecc-sw-hamming.c b/drivers/mtd/nand/ecc-sw-hamming.c
new file mode 100644
index 000000000000..76966f5ff13f
--- /dev/null
+++ b/drivers/mtd/nand/ecc-sw-hamming.c
@@ -0,0 +1,484 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * This file contains an ECC algorithm that detects and corrects 1 bit
+ * errors in a 256 byte block of data.
+ *
+ * Copyright © 2008 Koninklijke Philips Electronics NV.
+ *                  Author: Frans Meulenbroeks
+ *
+ * Completely replaces the previous ECC implementation which was written by:
+ *   Steven J. Hill (sjhill@realitydiluted.com)
+ *   Thomas Gleixner (tglx@linutronix.de)
+ *
+ * Information on how this algorithm works and how it was developed
+ * can be found in Documentation/driver-api/mtd/nand_ecc.rst
+ */
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/rawnand.h>
+#include <linux/mtd/nand-ecc-sw-hamming.h>
+#include <asm/byteorder.h>
+
+/*
+ * invparity is a 256 byte table that contains the odd parity
+ * for each byte. So if the number of bits in a byte is even,
+ * the array element is 1, and when the number of bits is odd
+ * the array eleemnt is 0.
+ */
+static const char invparity[256] = {
+	1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1,
+	0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0,
+	0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0,
+	1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1,
+	0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0,
+	1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1,
+	1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1,
+	0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0,
+	0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0,
+	1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1,
+	1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1,
+	0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0,
+	1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1,
+	0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0,
+	0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0,
+	1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1
+};
+
+/*
+ * bitsperbyte contains the number of bits per byte
+ * this is only used for testing and repairing parity
+ * (a precalculated value slightly improves performance)
+ */
+static const char bitsperbyte[256] = {
+	0, 1, 1, 2, 1, 2, 2, 3, 1, 2, 2, 3, 2, 3, 3, 4,
+	1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
+	1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
+	2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
+	1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
+	2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
+	2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
+	3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
+	1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
+	2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
+	2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
+	3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
+	2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
+	3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
+	3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
+	4, 5, 5, 6, 5, 6, 6, 7, 5, 6, 6, 7, 6, 7, 7, 8,
+};
+
+/*
+ * addressbits is a lookup table to filter out the bits from the xor-ed
+ * ECC data that identify the faulty location.
+ * this is only used for repairing parity
+ * see the comments in nand_correct_data for more details
+ */
+static const char addressbits[256] = {
+	0x00, 0x00, 0x01, 0x01, 0x00, 0x00, 0x01, 0x01,
+	0x02, 0x02, 0x03, 0x03, 0x02, 0x02, 0x03, 0x03,
+	0x00, 0x00, 0x01, 0x01, 0x00, 0x00, 0x01, 0x01,
+	0x02, 0x02, 0x03, 0x03, 0x02, 0x02, 0x03, 0x03,
+	0x04, 0x04, 0x05, 0x05, 0x04, 0x04, 0x05, 0x05,
+	0x06, 0x06, 0x07, 0x07, 0x06, 0x06, 0x07, 0x07,
+	0x04, 0x04, 0x05, 0x05, 0x04, 0x04, 0x05, 0x05,
+	0x06, 0x06, 0x07, 0x07, 0x06, 0x06, 0x07, 0x07,
+	0x00, 0x00, 0x01, 0x01, 0x00, 0x00, 0x01, 0x01,
+	0x02, 0x02, 0x03, 0x03, 0x02, 0x02, 0x03, 0x03,
+	0x00, 0x00, 0x01, 0x01, 0x00, 0x00, 0x01, 0x01,
+	0x02, 0x02, 0x03, 0x03, 0x02, 0x02, 0x03, 0x03,
+	0x04, 0x04, 0x05, 0x05, 0x04, 0x04, 0x05, 0x05,
+	0x06, 0x06, 0x07, 0x07, 0x06, 0x06, 0x07, 0x07,
+	0x04, 0x04, 0x05, 0x05, 0x04, 0x04, 0x05, 0x05,
+	0x06, 0x06, 0x07, 0x07, 0x06, 0x06, 0x07, 0x07,
+	0x08, 0x08, 0x09, 0x09, 0x08, 0x08, 0x09, 0x09,
+	0x0a, 0x0a, 0x0b, 0x0b, 0x0a, 0x0a, 0x0b, 0x0b,
+	0x08, 0x08, 0x09, 0x09, 0x08, 0x08, 0x09, 0x09,
+	0x0a, 0x0a, 0x0b, 0x0b, 0x0a, 0x0a, 0x0b, 0x0b,
+	0x0c, 0x0c, 0x0d, 0x0d, 0x0c, 0x0c, 0x0d, 0x0d,
+	0x0e, 0x0e, 0x0f, 0x0f, 0x0e, 0x0e, 0x0f, 0x0f,
+	0x0c, 0x0c, 0x0d, 0x0d, 0x0c, 0x0c, 0x0d, 0x0d,
+	0x0e, 0x0e, 0x0f, 0x0f, 0x0e, 0x0e, 0x0f, 0x0f,
+	0x08, 0x08, 0x09, 0x09, 0x08, 0x08, 0x09, 0x09,
+	0x0a, 0x0a, 0x0b, 0x0b, 0x0a, 0x0a, 0x0b, 0x0b,
+	0x08, 0x08, 0x09, 0x09, 0x08, 0x08, 0x09, 0x09,
+	0x0a, 0x0a, 0x0b, 0x0b, 0x0a, 0x0a, 0x0b, 0x0b,
+	0x0c, 0x0c, 0x0d, 0x0d, 0x0c, 0x0c, 0x0d, 0x0d,
+	0x0e, 0x0e, 0x0f, 0x0f, 0x0e, 0x0e, 0x0f, 0x0f,
+	0x0c, 0x0c, 0x0d, 0x0d, 0x0c, 0x0c, 0x0d, 0x0d,
+	0x0e, 0x0e, 0x0f, 0x0f, 0x0e, 0x0e, 0x0f, 0x0f
+};
+
+/**
+ * __nand_calculate_ecc - [NAND Interface] Calculate 3-byte ECC for 256/512-byte
+ *			 block
+ * @buf:	input buffer with raw data
+ * @eccsize:	data bytes per ECC step (256 or 512)
+ * @code:	output buffer with ECC
+ * @sm_order:	Smart Media byte ordering
+ */
+void __nand_calculate_ecc(const unsigned char *buf, unsigned int eccsize,
+			  unsigned char *code, bool sm_order)
+{
+	int i;
+	const uint32_t *bp = (uint32_t *)buf;
+	/* 256 or 512 bytes/ecc  */
+	const uint32_t eccsize_mult = eccsize >> 8;
+	uint32_t cur;		/* current value in buffer */
+	/* rp0..rp15..rp17 are the various accumulated parities (per byte) */
+	uint32_t rp0, rp1, rp2, rp3, rp4, rp5, rp6, rp7;
+	uint32_t rp8, rp9, rp10, rp11, rp12, rp13, rp14, rp15, rp16;
+	uint32_t rp17;
+	uint32_t par;		/* the cumulative parity for all data */
+	uint32_t tmppar;	/* the cumulative parity for this iteration;
+				   for rp12, rp14 and rp16 at the end of the
+				   loop */
+
+	par = 0;
+	rp4 = 0;
+	rp6 = 0;
+	rp8 = 0;
+	rp10 = 0;
+	rp12 = 0;
+	rp14 = 0;
+	rp16 = 0;
+
+	/*
+	 * The loop is unrolled a number of times;
+	 * This avoids if statements to decide on which rp value to update
+	 * Also we process the data by longwords.
+	 * Note: passing unaligned data might give a performance penalty.
+	 * It is assumed that the buffers are aligned.
+	 * tmppar is the cumulative sum of this iteration.
+	 * needed for calculating rp12, rp14, rp16 and par
+	 * also used as a performance improvement for rp6, rp8 and rp10
+	 */
+	for (i = 0; i < eccsize_mult << 2; i++) {
+		cur = *bp++;
+		tmppar = cur;
+		rp4 ^= cur;
+		cur = *bp++;
+		tmppar ^= cur;
+		rp6 ^= tmppar;
+		cur = *bp++;
+		tmppar ^= cur;
+		rp4 ^= cur;
+		cur = *bp++;
+		tmppar ^= cur;
+		rp8 ^= tmppar;
+
+		cur = *bp++;
+		tmppar ^= cur;
+		rp4 ^= cur;
+		rp6 ^= cur;
+		cur = *bp++;
+		tmppar ^= cur;
+		rp6 ^= cur;
+		cur = *bp++;
+		tmppar ^= cur;
+		rp4 ^= cur;
+		cur = *bp++;
+		tmppar ^= cur;
+		rp10 ^= tmppar;
+
+		cur = *bp++;
+		tmppar ^= cur;
+		rp4 ^= cur;
+		rp6 ^= cur;
+		rp8 ^= cur;
+		cur = *bp++;
+		tmppar ^= cur;
+		rp6 ^= cur;
+		rp8 ^= cur;
+		cur = *bp++;
+		tmppar ^= cur;
+		rp4 ^= cur;
+		rp8 ^= cur;
+		cur = *bp++;
+		tmppar ^= cur;
+		rp8 ^= cur;
+
+		cur = *bp++;
+		tmppar ^= cur;
+		rp4 ^= cur;
+		rp6 ^= cur;
+		cur = *bp++;
+		tmppar ^= cur;
+		rp6 ^= cur;
+		cur = *bp++;
+		tmppar ^= cur;
+		rp4 ^= cur;
+		cur = *bp++;
+		tmppar ^= cur;
+
+		par ^= tmppar;
+		if ((i & 0x1) == 0)
+			rp12 ^= tmppar;
+		if ((i & 0x2) == 0)
+			rp14 ^= tmppar;
+		if (eccsize_mult == 2 && (i & 0x4) == 0)
+			rp16 ^= tmppar;
+	}
+
+	/*
+	 * handle the fact that we use longword operations
+	 * we'll bring rp4..rp14..rp16 back to single byte entities by
+	 * shifting and xoring first fold the upper and lower 16 bits,
+	 * then the upper and lower 8 bits.
+	 */
+	rp4 ^= (rp4 >> 16);
+	rp4 ^= (rp4 >> 8);
+	rp4 &= 0xff;
+	rp6 ^= (rp6 >> 16);
+	rp6 ^= (rp6 >> 8);
+	rp6 &= 0xff;
+	rp8 ^= (rp8 >> 16);
+	rp8 ^= (rp8 >> 8);
+	rp8 &= 0xff;
+	rp10 ^= (rp10 >> 16);
+	rp10 ^= (rp10 >> 8);
+	rp10 &= 0xff;
+	rp12 ^= (rp12 >> 16);
+	rp12 ^= (rp12 >> 8);
+	rp12 &= 0xff;
+	rp14 ^= (rp14 >> 16);
+	rp14 ^= (rp14 >> 8);
+	rp14 &= 0xff;
+	if (eccsize_mult == 2) {
+		rp16 ^= (rp16 >> 16);
+		rp16 ^= (rp16 >> 8);
+		rp16 &= 0xff;
+	}
+
+	/*
+	 * we also need to calculate the row parity for rp0..rp3
+	 * This is present in par, because par is now
+	 * rp3 rp3 rp2 rp2 in little endian and
+	 * rp2 rp2 rp3 rp3 in big endian
+	 * as well as
+	 * rp1 rp0 rp1 rp0 in little endian and
+	 * rp0 rp1 rp0 rp1 in big endian
+	 * First calculate rp2 and rp3
+	 */
+#ifdef __BIG_ENDIAN
+	rp2 = (par >> 16);
+	rp2 ^= (rp2 >> 8);
+	rp2 &= 0xff;
+	rp3 = par & 0xffff;
+	rp3 ^= (rp3 >> 8);
+	rp3 &= 0xff;
+#else
+	rp3 = (par >> 16);
+	rp3 ^= (rp3 >> 8);
+	rp3 &= 0xff;
+	rp2 = par & 0xffff;
+	rp2 ^= (rp2 >> 8);
+	rp2 &= 0xff;
+#endif
+
+	/* reduce par to 16 bits then calculate rp1 and rp0 */
+	par ^= (par >> 16);
+#ifdef __BIG_ENDIAN
+	rp0 = (par >> 8) & 0xff;
+	rp1 = (par & 0xff);
+#else
+	rp1 = (par >> 8) & 0xff;
+	rp0 = (par & 0xff);
+#endif
+
+	/* finally reduce par to 8 bits */
+	par ^= (par >> 8);
+	par &= 0xff;
+
+	/*
+	 * and calculate rp5..rp15..rp17
+	 * note that par = rp4 ^ rp5 and due to the commutative property
+	 * of the ^ operator we can say:
+	 * rp5 = (par ^ rp4);
+	 * The & 0xff seems superfluous, but benchmarking learned that
+	 * leaving it out gives slightly worse results. No idea why, probably
+	 * it has to do with the way the pipeline in pentium is organized.
+	 */
+	rp5 = (par ^ rp4) & 0xff;
+	rp7 = (par ^ rp6) & 0xff;
+	rp9 = (par ^ rp8) & 0xff;
+	rp11 = (par ^ rp10) & 0xff;
+	rp13 = (par ^ rp12) & 0xff;
+	rp15 = (par ^ rp14) & 0xff;
+	if (eccsize_mult == 2)
+		rp17 = (par ^ rp16) & 0xff;
+
+	/*
+	 * Finally calculate the ECC bits.
+	 * Again here it might seem that there are performance optimisations
+	 * possible, but benchmarks showed that on the system this is developed
+	 * the code below is the fastest
+	 */
+	if (sm_order) {
+		code[0] = (invparity[rp7] << 7) | (invparity[rp6] << 6) |
+			  (invparity[rp5] << 5) | (invparity[rp4] << 4) |
+			  (invparity[rp3] << 3) | (invparity[rp2] << 2) |
+			  (invparity[rp1] << 1) | (invparity[rp0]);
+		code[1] = (invparity[rp15] << 7) | (invparity[rp14] << 6) |
+			  (invparity[rp13] << 5) | (invparity[rp12] << 4) |
+			  (invparity[rp11] << 3) | (invparity[rp10] << 2) |
+			  (invparity[rp9] << 1) | (invparity[rp8]);
+	} else {
+		code[1] = (invparity[rp7] << 7) | (invparity[rp6] << 6) |
+			  (invparity[rp5] << 5) | (invparity[rp4] << 4) |
+			  (invparity[rp3] << 3) | (invparity[rp2] << 2) |
+			  (invparity[rp1] << 1) | (invparity[rp0]);
+		code[0] = (invparity[rp15] << 7) | (invparity[rp14] << 6) |
+			  (invparity[rp13] << 5) | (invparity[rp12] << 4) |
+			  (invparity[rp11] << 3) | (invparity[rp10] << 2) |
+			  (invparity[rp9] << 1) | (invparity[rp8]);
+	}
+
+	if (eccsize_mult == 1)
+		code[2] =
+		    (invparity[par & 0xf0] << 7) |
+		    (invparity[par & 0x0f] << 6) |
+		    (invparity[par & 0xcc] << 5) |
+		    (invparity[par & 0x33] << 4) |
+		    (invparity[par & 0xaa] << 3) |
+		    (invparity[par & 0x55] << 2) |
+		    3;
+	else
+		code[2] =
+		    (invparity[par & 0xf0] << 7) |
+		    (invparity[par & 0x0f] << 6) |
+		    (invparity[par & 0xcc] << 5) |
+		    (invparity[par & 0x33] << 4) |
+		    (invparity[par & 0xaa] << 3) |
+		    (invparity[par & 0x55] << 2) |
+		    (invparity[rp17] << 1) |
+		    (invparity[rp16] << 0);
+}
+EXPORT_SYMBOL(__nand_calculate_ecc);
+
+/**
+ * nand_calculate_ecc - [NAND Interface] Calculate 3-byte ECC for 256/512-byte
+ *			 block
+ * @chip:	NAND chip object
+ * @buf:	input buffer with raw data
+ * @code:	output buffer with ECC
+ */
+int nand_calculate_ecc(struct nand_chip *chip, const unsigned char *buf,
+		       unsigned char *code)
+{
+	bool sm_order = chip->ecc.options & NAND_ECC_SOFT_HAMMING_SM_ORDER;
+
+	__nand_calculate_ecc(buf, chip->ecc.size, code, sm_order);
+
+	return 0;
+}
+EXPORT_SYMBOL(nand_calculate_ecc);
+
+/**
+ * __nand_correct_data - [NAND Interface] Detect and correct bit error(s)
+ * @buf:	raw data read from the chip
+ * @read_ecc:	ECC from the chip
+ * @calc_ecc:	the ECC calculated from raw data
+ * @eccsize:	data bytes per ECC step (256 or 512)
+ * @sm_order:	Smart Media byte order
+ *
+ * Detect and correct a 1 bit error for eccsize byte block
+ */
+int __nand_correct_data(unsigned char *buf,
+			unsigned char *read_ecc, unsigned char *calc_ecc,
+			unsigned int eccsize, bool sm_order)
+{
+	unsigned char b0, b1, b2, bit_addr;
+	unsigned int byte_addr;
+	/* 256 or 512 bytes/ecc  */
+	const uint32_t eccsize_mult = eccsize >> 8;
+
+	/*
+	 * b0 to b2 indicate which bit is faulty (if any)
+	 * we might need the xor result  more than once,
+	 * so keep them in a local var
+	*/
+	if (sm_order) {
+		b0 = read_ecc[0] ^ calc_ecc[0];
+		b1 = read_ecc[1] ^ calc_ecc[1];
+	} else {
+		b0 = read_ecc[1] ^ calc_ecc[1];
+		b1 = read_ecc[0] ^ calc_ecc[0];
+	}
+
+	b2 = read_ecc[2] ^ calc_ecc[2];
+
+	/* check if there are any bitfaults */
+
+	/* repeated if statements are slightly more efficient than switch ... */
+	/* ordered in order of likelihood */
+
+	if ((b0 | b1 | b2) == 0)
+		return 0;	/* no error */
+
+	if ((((b0 ^ (b0 >> 1)) & 0x55) == 0x55) &&
+	    (((b1 ^ (b1 >> 1)) & 0x55) == 0x55) &&
+	    ((eccsize_mult == 1 && ((b2 ^ (b2 >> 1)) & 0x54) == 0x54) ||
+	     (eccsize_mult == 2 && ((b2 ^ (b2 >> 1)) & 0x55) == 0x55))) {
+	/* single bit error */
+		/*
+		 * rp17/rp15/13/11/9/7/5/3/1 indicate which byte is the faulty
+		 * byte, cp 5/3/1 indicate the faulty bit.
+		 * A lookup table (called addressbits) is used to filter
+		 * the bits from the byte they are in.
+		 * A marginal optimisation is possible by having three
+		 * different lookup tables.
+		 * One as we have now (for b0), one for b2
+		 * (that would avoid the >> 1), and one for b1 (with all values
+		 * << 4). However it was felt that introducing two more tables
+		 * hardly justify the gain.
+		 *
+		 * The b2 shift is there to get rid of the lowest two bits.
+		 * We could also do addressbits[b2] >> 1 but for the
+		 * performance it does not make any difference
+		 */
+		if (eccsize_mult == 1)
+			byte_addr = (addressbits[b1] << 4) + addressbits[b0];
+		else
+			byte_addr = (addressbits[b2 & 0x3] << 8) +
+				    (addressbits[b1] << 4) + addressbits[b0];
+		bit_addr = addressbits[b2 >> 2];
+		/* flip the bit */
+		buf[byte_addr] ^= (1 << bit_addr);
+		return 1;
+
+	}
+	/* count nr of bits; use table lookup, faster than calculating it */
+	if ((bitsperbyte[b0] + bitsperbyte[b1] + bitsperbyte[b2]) == 1)
+		return 1;	/* error in ECC data; no action needed */
+
+	pr_err("%s: uncorrectable ECC error\n", __func__);
+	return -EBADMSG;
+}
+EXPORT_SYMBOL(__nand_correct_data);
+
+/**
+ * nand_correct_data - [NAND Interface] Detect and correct bit error(s)
+ * @chip:	NAND chip object
+ * @buf:	raw data read from the chip
+ * @read_ecc:	ECC from the chip
+ * @calc_ecc:	the ECC calculated from raw data
+ *
+ * Detect and correct a 1 bit error for 256/512 byte block
+ */
+int nand_correct_data(struct nand_chip *chip, unsigned char *buf,
+		      unsigned char *read_ecc, unsigned char *calc_ecc)
+{
+	bool sm_order = chip->ecc.options & NAND_ECC_SOFT_HAMMING_SM_ORDER;
+
+	return __nand_correct_data(buf, read_ecc, calc_ecc, chip->ecc.size,
+				   sm_order);
+}
+EXPORT_SYMBOL(nand_correct_data);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Frans Meulenbroeks <fransmeulenbroeks@gmail.com>");
+MODULE_DESCRIPTION("Generic NAND ECC support");
diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
index b73860aa77c6..6149096e32cb 100644
--- a/drivers/mtd/nand/raw/Kconfig
+++ b/drivers/mtd/nand/raw/Kconfig
@@ -1,15 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
-config MTD_NAND_ECC_SW_HAMMING
-	tristate
-
-config MTD_NAND_ECC_SW_HAMMING_SMC
-	bool "NAND ECC Smart Media byte order"
-	depends on MTD_NAND_ECC_SW_HAMMING
-	default n
-	help
-	  Software ECC according to the Smart Media Specification.
-	  The original Linux implementation had byte 0 and 1 swapped.
-
 menuconfig MTD_RAW_NAND
 	tristate "Raw/Parallel NAND Device Support"
 	select MTD_NAND_CORE
diff --git a/drivers/mtd/nand/raw/Makefile b/drivers/mtd/nand/raw/Makefile
index 76904305d091..dc38c087c693 100644
--- a/drivers/mtd/nand/raw/Makefile
+++ b/drivers/mtd/nand/raw/Makefile
@@ -1,7 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 
 obj-$(CONFIG_MTD_RAW_NAND)		+= nand.o
-obj-$(CONFIG_MTD_NAND_ECC_SW_HAMMING)	+= nand_ecc.o
 obj-$(CONFIG_MTD_SM_COMMON) 		+= sm_common.o
 
 obj-$(CONFIG_MTD_NAND_CAFE)		+= cafe_nand.o
diff --git a/drivers/mtd/nand/raw/cs553x_nand.c b/drivers/mtd/nand/raw/cs553x_nand.c
index 282203debd0c..9a2bdb45a771 100644
--- a/drivers/mtd/nand/raw/cs553x_nand.c
+++ b/drivers/mtd/nand/raw/cs553x_nand.c
@@ -19,7 +19,7 @@
 #include <linux/delay.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand_ecc.h>
+#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/mtd/partitions.h>
 #include <linux/iopoll.h>
 
diff --git a/drivers/mtd/nand/raw/fsl_elbc_nand.c b/drivers/mtd/nand/raw/fsl_elbc_nand.c
index b2af7f81fdf8..eb255cf83e32 100644
--- a/drivers/mtd/nand/raw/fsl_elbc_nand.c
+++ b/drivers/mtd/nand/raw/fsl_elbc_nand.c
@@ -22,7 +22,7 @@
 
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand_ecc.h>
+#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/mtd/partitions.h>
 
 #include <asm/io.h>
diff --git a/drivers/mtd/nand/raw/fsl_ifc_nand.c b/drivers/mtd/nand/raw/fsl_ifc_nand.c
index e345f9d9f8e8..d2f84917fa8b 100644
--- a/drivers/mtd/nand/raw/fsl_ifc_nand.c
+++ b/drivers/mtd/nand/raw/fsl_ifc_nand.c
@@ -15,7 +15,7 @@
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
 #include <linux/mtd/partitions.h>
-#include <linux/mtd/nand_ecc.h>
+#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/fsl_ifc.h>
 #include <linux/iopoll.h>
 
diff --git a/drivers/mtd/nand/raw/fsl_upm.c b/drivers/mtd/nand/raw/fsl_upm.c
index d5813b9abc8e..3824361928a1 100644
--- a/drivers/mtd/nand/raw/fsl_upm.c
+++ b/drivers/mtd/nand/raw/fsl_upm.c
@@ -11,7 +11,7 @@
 #include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand_ecc.h>
+#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/mtd/partitions.h>
 #include <linux/mtd/mtd.h>
 #include <linux/of_platform.h>
diff --git a/drivers/mtd/nand/raw/fsmc_nand.c b/drivers/mtd/nand/raw/fsmc_nand.c
index 984b05e6bd38..e880db5852d8 100644
--- a/drivers/mtd/nand/raw/fsmc_nand.c
+++ b/drivers/mtd/nand/raw/fsmc_nand.c
@@ -26,7 +26,7 @@
 #include <linux/types.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand_ecc.h>
+#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/platform_device.h>
 #include <linux/of.h>
 #include <linux/mtd/partitions.h>
diff --git a/drivers/mtd/nand/raw/lpc32xx_mlc.c b/drivers/mtd/nand/raw/lpc32xx_mlc.c
index 9e728c731795..885b03b7af52 100644
--- a/drivers/mtd/nand/raw/lpc32xx_mlc.c
+++ b/drivers/mtd/nand/raw/lpc32xx_mlc.c
@@ -31,7 +31,7 @@
 #include <linux/mm.h>
 #include <linux/dma-mapping.h>
 #include <linux/dmaengine.h>
-#include <linux/mtd/nand_ecc.h>
+#include <linux/mtd/nand-ecc-sw-hamming.h>
 
 #define DRV_NAME "lpc32xx_mlc"
 
diff --git a/drivers/mtd/nand/raw/lpc32xx_slc.c b/drivers/mtd/nand/raw/lpc32xx_slc.c
index dc7785e30d2f..0bf9c3fbcd82 100644
--- a/drivers/mtd/nand/raw/lpc32xx_slc.c
+++ b/drivers/mtd/nand/raw/lpc32xx_slc.c
@@ -23,7 +23,7 @@
 #include <linux/mm.h>
 #include <linux/dma-mapping.h>
 #include <linux/dmaengine.h>
-#include <linux/mtd/nand_ecc.h>
+#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/gpio.h>
 #include <linux/of.h>
 #include <linux/of_gpio.h>
diff --git a/drivers/mtd/nand/raw/mxic_nand.c b/drivers/mtd/nand/raw/mxic_nand.c
index d66b5b0971fa..da1070993994 100644
--- a/drivers/mtd/nand/raw/mxic_nand.c
+++ b/drivers/mtd/nand/raw/mxic_nand.c
@@ -12,8 +12,8 @@
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/mtd/mtd.h>
+#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand_ecc.h>
 #include <linux/platform_device.h>
 
 #include "internals.h"
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index ebaf3bbfc1b2..bee7c64a0a4e 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -35,7 +35,7 @@
 #include <linux/types.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/nand.h>
-#include <linux/mtd/nand_ecc.h>
+#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/mtd/nand-ecc-sw-bch.h>
 #include <linux/interrupt.h>
 #include <linux/bitops.h>
diff --git a/drivers/mtd/nand/raw/nand_ecc.c b/drivers/mtd/nand/raw/nand_ecc.c
deleted file mode 100644
index b6a46b1b7781..000000000000
--- a/drivers/mtd/nand/raw/nand_ecc.c
+++ /dev/null
@@ -1,484 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * This file contains an ECC algorithm that detects and corrects 1 bit
- * errors in a 256 byte block of data.
- *
- * Copyright © 2008 Koninklijke Philips Electronics NV.
- *                  Author: Frans Meulenbroeks
- *
- * Completely replaces the previous ECC implementation which was written by:
- *   Steven J. Hill (sjhill@realitydiluted.com)
- *   Thomas Gleixner (tglx@linutronix.de)
- *
- * Information on how this algorithm works and how it was developed
- * can be found in Documentation/driver-api/mtd/nand_ecc.rst
- */
-
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/mtd/mtd.h>
-#include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand_ecc.h>
-#include <asm/byteorder.h>
-
-/*
- * invparity is a 256 byte table that contains the odd parity
- * for each byte. So if the number of bits in a byte is even,
- * the array element is 1, and when the number of bits is odd
- * the array eleemnt is 0.
- */
-static const char invparity[256] = {
-	1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1,
-	0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0,
-	0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0,
-	1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1,
-	0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0,
-	1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1,
-	1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1,
-	0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0,
-	0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0,
-	1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1,
-	1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1,
-	0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0,
-	1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1,
-	0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0,
-	0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0,
-	1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1
-};
-
-/*
- * bitsperbyte contains the number of bits per byte
- * this is only used for testing and repairing parity
- * (a precalculated value slightly improves performance)
- */
-static const char bitsperbyte[256] = {
-	0, 1, 1, 2, 1, 2, 2, 3, 1, 2, 2, 3, 2, 3, 3, 4,
-	1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
-	1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
-	2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
-	1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
-	2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
-	2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
-	3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
-	1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
-	2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
-	2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
-	3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
-	2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
-	3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
-	3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
-	4, 5, 5, 6, 5, 6, 6, 7, 5, 6, 6, 7, 6, 7, 7, 8,
-};
-
-/*
- * addressbits is a lookup table to filter out the bits from the xor-ed
- * ECC data that identify the faulty location.
- * this is only used for repairing parity
- * see the comments in nand_correct_data for more details
- */
-static const char addressbits[256] = {
-	0x00, 0x00, 0x01, 0x01, 0x00, 0x00, 0x01, 0x01,
-	0x02, 0x02, 0x03, 0x03, 0x02, 0x02, 0x03, 0x03,
-	0x00, 0x00, 0x01, 0x01, 0x00, 0x00, 0x01, 0x01,
-	0x02, 0x02, 0x03, 0x03, 0x02, 0x02, 0x03, 0x03,
-	0x04, 0x04, 0x05, 0x05, 0x04, 0x04, 0x05, 0x05,
-	0x06, 0x06, 0x07, 0x07, 0x06, 0x06, 0x07, 0x07,
-	0x04, 0x04, 0x05, 0x05, 0x04, 0x04, 0x05, 0x05,
-	0x06, 0x06, 0x07, 0x07, 0x06, 0x06, 0x07, 0x07,
-	0x00, 0x00, 0x01, 0x01, 0x00, 0x00, 0x01, 0x01,
-	0x02, 0x02, 0x03, 0x03, 0x02, 0x02, 0x03, 0x03,
-	0x00, 0x00, 0x01, 0x01, 0x00, 0x00, 0x01, 0x01,
-	0x02, 0x02, 0x03, 0x03, 0x02, 0x02, 0x03, 0x03,
-	0x04, 0x04, 0x05, 0x05, 0x04, 0x04, 0x05, 0x05,
-	0x06, 0x06, 0x07, 0x07, 0x06, 0x06, 0x07, 0x07,
-	0x04, 0x04, 0x05, 0x05, 0x04, 0x04, 0x05, 0x05,
-	0x06, 0x06, 0x07, 0x07, 0x06, 0x06, 0x07, 0x07,
-	0x08, 0x08, 0x09, 0x09, 0x08, 0x08, 0x09, 0x09,
-	0x0a, 0x0a, 0x0b, 0x0b, 0x0a, 0x0a, 0x0b, 0x0b,
-	0x08, 0x08, 0x09, 0x09, 0x08, 0x08, 0x09, 0x09,
-	0x0a, 0x0a, 0x0b, 0x0b, 0x0a, 0x0a, 0x0b, 0x0b,
-	0x0c, 0x0c, 0x0d, 0x0d, 0x0c, 0x0c, 0x0d, 0x0d,
-	0x0e, 0x0e, 0x0f, 0x0f, 0x0e, 0x0e, 0x0f, 0x0f,
-	0x0c, 0x0c, 0x0d, 0x0d, 0x0c, 0x0c, 0x0d, 0x0d,
-	0x0e, 0x0e, 0x0f, 0x0f, 0x0e, 0x0e, 0x0f, 0x0f,
-	0x08, 0x08, 0x09, 0x09, 0x08, 0x08, 0x09, 0x09,
-	0x0a, 0x0a, 0x0b, 0x0b, 0x0a, 0x0a, 0x0b, 0x0b,
-	0x08, 0x08, 0x09, 0x09, 0x08, 0x08, 0x09, 0x09,
-	0x0a, 0x0a, 0x0b, 0x0b, 0x0a, 0x0a, 0x0b, 0x0b,
-	0x0c, 0x0c, 0x0d, 0x0d, 0x0c, 0x0c, 0x0d, 0x0d,
-	0x0e, 0x0e, 0x0f, 0x0f, 0x0e, 0x0e, 0x0f, 0x0f,
-	0x0c, 0x0c, 0x0d, 0x0d, 0x0c, 0x0c, 0x0d, 0x0d,
-	0x0e, 0x0e, 0x0f, 0x0f, 0x0e, 0x0e, 0x0f, 0x0f
-};
-
-/**
- * __nand_calculate_ecc - [NAND Interface] Calculate 3-byte ECC for 256/512-byte
- *			 block
- * @buf:	input buffer with raw data
- * @eccsize:	data bytes per ECC step (256 or 512)
- * @code:	output buffer with ECC
- * @sm_order:	Smart Media byte ordering
- */
-void __nand_calculate_ecc(const unsigned char *buf, unsigned int eccsize,
-			  unsigned char *code, bool sm_order)
-{
-	int i;
-	const uint32_t *bp = (uint32_t *)buf;
-	/* 256 or 512 bytes/ecc  */
-	const uint32_t eccsize_mult = eccsize >> 8;
-	uint32_t cur;		/* current value in buffer */
-	/* rp0..rp15..rp17 are the various accumulated parities (per byte) */
-	uint32_t rp0, rp1, rp2, rp3, rp4, rp5, rp6, rp7;
-	uint32_t rp8, rp9, rp10, rp11, rp12, rp13, rp14, rp15, rp16;
-	uint32_t rp17;
-	uint32_t par;		/* the cumulative parity for all data */
-	uint32_t tmppar;	/* the cumulative parity for this iteration;
-				   for rp12, rp14 and rp16 at the end of the
-				   loop */
-
-	par = 0;
-	rp4 = 0;
-	rp6 = 0;
-	rp8 = 0;
-	rp10 = 0;
-	rp12 = 0;
-	rp14 = 0;
-	rp16 = 0;
-
-	/*
-	 * The loop is unrolled a number of times;
-	 * This avoids if statements to decide on which rp value to update
-	 * Also we process the data by longwords.
-	 * Note: passing unaligned data might give a performance penalty.
-	 * It is assumed that the buffers are aligned.
-	 * tmppar is the cumulative sum of this iteration.
-	 * needed for calculating rp12, rp14, rp16 and par
-	 * also used as a performance improvement for rp6, rp8 and rp10
-	 */
-	for (i = 0; i < eccsize_mult << 2; i++) {
-		cur = *bp++;
-		tmppar = cur;
-		rp4 ^= cur;
-		cur = *bp++;
-		tmppar ^= cur;
-		rp6 ^= tmppar;
-		cur = *bp++;
-		tmppar ^= cur;
-		rp4 ^= cur;
-		cur = *bp++;
-		tmppar ^= cur;
-		rp8 ^= tmppar;
-
-		cur = *bp++;
-		tmppar ^= cur;
-		rp4 ^= cur;
-		rp6 ^= cur;
-		cur = *bp++;
-		tmppar ^= cur;
-		rp6 ^= cur;
-		cur = *bp++;
-		tmppar ^= cur;
-		rp4 ^= cur;
-		cur = *bp++;
-		tmppar ^= cur;
-		rp10 ^= tmppar;
-
-		cur = *bp++;
-		tmppar ^= cur;
-		rp4 ^= cur;
-		rp6 ^= cur;
-		rp8 ^= cur;
-		cur = *bp++;
-		tmppar ^= cur;
-		rp6 ^= cur;
-		rp8 ^= cur;
-		cur = *bp++;
-		tmppar ^= cur;
-		rp4 ^= cur;
-		rp8 ^= cur;
-		cur = *bp++;
-		tmppar ^= cur;
-		rp8 ^= cur;
-
-		cur = *bp++;
-		tmppar ^= cur;
-		rp4 ^= cur;
-		rp6 ^= cur;
-		cur = *bp++;
-		tmppar ^= cur;
-		rp6 ^= cur;
-		cur = *bp++;
-		tmppar ^= cur;
-		rp4 ^= cur;
-		cur = *bp++;
-		tmppar ^= cur;
-
-		par ^= tmppar;
-		if ((i & 0x1) == 0)
-			rp12 ^= tmppar;
-		if ((i & 0x2) == 0)
-			rp14 ^= tmppar;
-		if (eccsize_mult == 2 && (i & 0x4) == 0)
-			rp16 ^= tmppar;
-	}
-
-	/*
-	 * handle the fact that we use longword operations
-	 * we'll bring rp4..rp14..rp16 back to single byte entities by
-	 * shifting and xoring first fold the upper and lower 16 bits,
-	 * then the upper and lower 8 bits.
-	 */
-	rp4 ^= (rp4 >> 16);
-	rp4 ^= (rp4 >> 8);
-	rp4 &= 0xff;
-	rp6 ^= (rp6 >> 16);
-	rp6 ^= (rp6 >> 8);
-	rp6 &= 0xff;
-	rp8 ^= (rp8 >> 16);
-	rp8 ^= (rp8 >> 8);
-	rp8 &= 0xff;
-	rp10 ^= (rp10 >> 16);
-	rp10 ^= (rp10 >> 8);
-	rp10 &= 0xff;
-	rp12 ^= (rp12 >> 16);
-	rp12 ^= (rp12 >> 8);
-	rp12 &= 0xff;
-	rp14 ^= (rp14 >> 16);
-	rp14 ^= (rp14 >> 8);
-	rp14 &= 0xff;
-	if (eccsize_mult == 2) {
-		rp16 ^= (rp16 >> 16);
-		rp16 ^= (rp16 >> 8);
-		rp16 &= 0xff;
-	}
-
-	/*
-	 * we also need to calculate the row parity for rp0..rp3
-	 * This is present in par, because par is now
-	 * rp3 rp3 rp2 rp2 in little endian and
-	 * rp2 rp2 rp3 rp3 in big endian
-	 * as well as
-	 * rp1 rp0 rp1 rp0 in little endian and
-	 * rp0 rp1 rp0 rp1 in big endian
-	 * First calculate rp2 and rp3
-	 */
-#ifdef __BIG_ENDIAN
-	rp2 = (par >> 16);
-	rp2 ^= (rp2 >> 8);
-	rp2 &= 0xff;
-	rp3 = par & 0xffff;
-	rp3 ^= (rp3 >> 8);
-	rp3 &= 0xff;
-#else
-	rp3 = (par >> 16);
-	rp3 ^= (rp3 >> 8);
-	rp3 &= 0xff;
-	rp2 = par & 0xffff;
-	rp2 ^= (rp2 >> 8);
-	rp2 &= 0xff;
-#endif
-
-	/* reduce par to 16 bits then calculate rp1 and rp0 */
-	par ^= (par >> 16);
-#ifdef __BIG_ENDIAN
-	rp0 = (par >> 8) & 0xff;
-	rp1 = (par & 0xff);
-#else
-	rp1 = (par >> 8) & 0xff;
-	rp0 = (par & 0xff);
-#endif
-
-	/* finally reduce par to 8 bits */
-	par ^= (par >> 8);
-	par &= 0xff;
-
-	/*
-	 * and calculate rp5..rp15..rp17
-	 * note that par = rp4 ^ rp5 and due to the commutative property
-	 * of the ^ operator we can say:
-	 * rp5 = (par ^ rp4);
-	 * The & 0xff seems superfluous, but benchmarking learned that
-	 * leaving it out gives slightly worse results. No idea why, probably
-	 * it has to do with the way the pipeline in pentium is organized.
-	 */
-	rp5 = (par ^ rp4) & 0xff;
-	rp7 = (par ^ rp6) & 0xff;
-	rp9 = (par ^ rp8) & 0xff;
-	rp11 = (par ^ rp10) & 0xff;
-	rp13 = (par ^ rp12) & 0xff;
-	rp15 = (par ^ rp14) & 0xff;
-	if (eccsize_mult == 2)
-		rp17 = (par ^ rp16) & 0xff;
-
-	/*
-	 * Finally calculate the ECC bits.
-	 * Again here it might seem that there are performance optimisations
-	 * possible, but benchmarks showed that on the system this is developed
-	 * the code below is the fastest
-	 */
-	if (sm_order) {
-		code[0] = (invparity[rp7] << 7) | (invparity[rp6] << 6) |
-			  (invparity[rp5] << 5) | (invparity[rp4] << 4) |
-			  (invparity[rp3] << 3) | (invparity[rp2] << 2) |
-			  (invparity[rp1] << 1) | (invparity[rp0]);
-		code[1] = (invparity[rp15] << 7) | (invparity[rp14] << 6) |
-			  (invparity[rp13] << 5) | (invparity[rp12] << 4) |
-			  (invparity[rp11] << 3) | (invparity[rp10] << 2) |
-			  (invparity[rp9] << 1) | (invparity[rp8]);
-	} else {
-		code[1] = (invparity[rp7] << 7) | (invparity[rp6] << 6) |
-			  (invparity[rp5] << 5) | (invparity[rp4] << 4) |
-			  (invparity[rp3] << 3) | (invparity[rp2] << 2) |
-			  (invparity[rp1] << 1) | (invparity[rp0]);
-		code[0] = (invparity[rp15] << 7) | (invparity[rp14] << 6) |
-			  (invparity[rp13] << 5) | (invparity[rp12] << 4) |
-			  (invparity[rp11] << 3) | (invparity[rp10] << 2) |
-			  (invparity[rp9] << 1) | (invparity[rp8]);
-	}
-
-	if (eccsize_mult == 1)
-		code[2] =
-		    (invparity[par & 0xf0] << 7) |
-		    (invparity[par & 0x0f] << 6) |
-		    (invparity[par & 0xcc] << 5) |
-		    (invparity[par & 0x33] << 4) |
-		    (invparity[par & 0xaa] << 3) |
-		    (invparity[par & 0x55] << 2) |
-		    3;
-	else
-		code[2] =
-		    (invparity[par & 0xf0] << 7) |
-		    (invparity[par & 0x0f] << 6) |
-		    (invparity[par & 0xcc] << 5) |
-		    (invparity[par & 0x33] << 4) |
-		    (invparity[par & 0xaa] << 3) |
-		    (invparity[par & 0x55] << 2) |
-		    (invparity[rp17] << 1) |
-		    (invparity[rp16] << 0);
-}
-EXPORT_SYMBOL(__nand_calculate_ecc);
-
-/**
- * nand_calculate_ecc - [NAND Interface] Calculate 3-byte ECC for 256/512-byte
- *			 block
- * @chip:	NAND chip object
- * @buf:	input buffer with raw data
- * @code:	output buffer with ECC
- */
-int nand_calculate_ecc(struct nand_chip *chip, const unsigned char *buf,
-		       unsigned char *code)
-{
-	bool sm_order = chip->ecc.options & NAND_ECC_SOFT_HAMMING_SM_ORDER;
-
-	__nand_calculate_ecc(buf, chip->ecc.size, code, sm_order);
-
-	return 0;
-}
-EXPORT_SYMBOL(nand_calculate_ecc);
-
-/**
- * __nand_correct_data - [NAND Interface] Detect and correct bit error(s)
- * @buf:	raw data read from the chip
- * @read_ecc:	ECC from the chip
- * @calc_ecc:	the ECC calculated from raw data
- * @eccsize:	data bytes per ECC step (256 or 512)
- * @sm_order:	Smart Media byte order
- *
- * Detect and correct a 1 bit error for eccsize byte block
- */
-int __nand_correct_data(unsigned char *buf,
-			unsigned char *read_ecc, unsigned char *calc_ecc,
-			unsigned int eccsize, bool sm_order)
-{
-	unsigned char b0, b1, b2, bit_addr;
-	unsigned int byte_addr;
-	/* 256 or 512 bytes/ecc  */
-	const uint32_t eccsize_mult = eccsize >> 8;
-
-	/*
-	 * b0 to b2 indicate which bit is faulty (if any)
-	 * we might need the xor result  more than once,
-	 * so keep them in a local var
-	*/
-	if (sm_order) {
-		b0 = read_ecc[0] ^ calc_ecc[0];
-		b1 = read_ecc[1] ^ calc_ecc[1];
-	} else {
-		b0 = read_ecc[1] ^ calc_ecc[1];
-		b1 = read_ecc[0] ^ calc_ecc[0];
-	}
-
-	b2 = read_ecc[2] ^ calc_ecc[2];
-
-	/* check if there are any bitfaults */
-
-	/* repeated if statements are slightly more efficient than switch ... */
-	/* ordered in order of likelihood */
-
-	if ((b0 | b1 | b2) == 0)
-		return 0;	/* no error */
-
-	if ((((b0 ^ (b0 >> 1)) & 0x55) == 0x55) &&
-	    (((b1 ^ (b1 >> 1)) & 0x55) == 0x55) &&
-	    ((eccsize_mult == 1 && ((b2 ^ (b2 >> 1)) & 0x54) == 0x54) ||
-	     (eccsize_mult == 2 && ((b2 ^ (b2 >> 1)) & 0x55) == 0x55))) {
-	/* single bit error */
-		/*
-		 * rp17/rp15/13/11/9/7/5/3/1 indicate which byte is the faulty
-		 * byte, cp 5/3/1 indicate the faulty bit.
-		 * A lookup table (called addressbits) is used to filter
-		 * the bits from the byte they are in.
-		 * A marginal optimisation is possible by having three
-		 * different lookup tables.
-		 * One as we have now (for b0), one for b2
-		 * (that would avoid the >> 1), and one for b1 (with all values
-		 * << 4). However it was felt that introducing two more tables
-		 * hardly justify the gain.
-		 *
-		 * The b2 shift is there to get rid of the lowest two bits.
-		 * We could also do addressbits[b2] >> 1 but for the
-		 * performance it does not make any difference
-		 */
-		if (eccsize_mult == 1)
-			byte_addr = (addressbits[b1] << 4) + addressbits[b0];
-		else
-			byte_addr = (addressbits[b2 & 0x3] << 8) +
-				    (addressbits[b1] << 4) + addressbits[b0];
-		bit_addr = addressbits[b2 >> 2];
-		/* flip the bit */
-		buf[byte_addr] ^= (1 << bit_addr);
-		return 1;
-
-	}
-	/* count nr of bits; use table lookup, faster than calculating it */
-	if ((bitsperbyte[b0] + bitsperbyte[b1] + bitsperbyte[b2]) == 1)
-		return 1;	/* error in ECC data; no action needed */
-
-	pr_err("%s: uncorrectable ECC error\n", __func__);
-	return -EBADMSG;
-}
-EXPORT_SYMBOL(__nand_correct_data);
-
-/**
- * nand_correct_data - [NAND Interface] Detect and correct bit error(s)
- * @chip:	NAND chip object
- * @buf:	raw data read from the chip
- * @read_ecc:	ECC from the chip
- * @calc_ecc:	the ECC calculated from raw data
- *
- * Detect and correct a 1 bit error for 256/512 byte block
- */
-int nand_correct_data(struct nand_chip *chip, unsigned char *buf,
-		      unsigned char *read_ecc, unsigned char *calc_ecc)
-{
-	bool sm_order = chip->ecc.options & NAND_ECC_SOFT_HAMMING_SM_ORDER;
-
-	return __nand_correct_data(buf, read_ecc, calc_ecc, chip->ecc.size,
-				   sm_order);
-}
-EXPORT_SYMBOL(nand_correct_data);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Frans Meulenbroeks <fransmeulenbroeks@gmail.com>");
-MODULE_DESCRIPTION("Generic NAND ECC support");
diff --git a/drivers/mtd/nand/raw/ndfc.c b/drivers/mtd/nand/raw/ndfc.c
index 0fb4ba93c41e..8cda6633280b 100644
--- a/drivers/mtd/nand/raw/ndfc.c
+++ b/drivers/mtd/nand/raw/ndfc.c
@@ -18,7 +18,7 @@
  */
 #include <linux/module.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand_ecc.h>
+#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/mtd/partitions.h>
 #include <linux/mtd/ndfc.h>
 #include <linux/slab.h>
diff --git a/drivers/mtd/nand/raw/pasemi_nand.c b/drivers/mtd/nand/raw/pasemi_nand.c
index 4dfff34800f4..2dddbdca9e94 100644
--- a/drivers/mtd/nand/raw/pasemi_nand.c
+++ b/drivers/mtd/nand/raw/pasemi_nand.c
@@ -14,7 +14,7 @@
 #include <linux/module.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand_ecc.h>
+#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
diff --git a/drivers/mtd/nand/raw/s3c2410.c b/drivers/mtd/nand/raw/s3c2410.c
index fbd0fa48e063..f7eb3b5fa792 100644
--- a/drivers/mtd/nand/raw/s3c2410.c
+++ b/drivers/mtd/nand/raw/s3c2410.c
@@ -30,7 +30,7 @@
 
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand_ecc.h>
+#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/mtd/partitions.h>
 
 #include <linux/platform_data/mtd-nand-s3c2410.h>
diff --git a/drivers/mtd/nand/raw/sharpsl.c b/drivers/mtd/nand/raw/sharpsl.c
index af98bcc9d689..2fae6ade8b13 100644
--- a/drivers/mtd/nand/raw/sharpsl.c
+++ b/drivers/mtd/nand/raw/sharpsl.c
@@ -12,7 +12,7 @@
 #include <linux/delay.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand_ecc.h>
+#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/mtd/partitions.h>
 #include <linux/mtd/sharpsl.h>
 #include <linux/interrupt.h>
diff --git a/drivers/mtd/nand/raw/tmio_nand.c b/drivers/mtd/nand/raw/tmio_nand.c
index aa6c7e7bbf1b..fadca0b9e21f 100644
--- a/drivers/mtd/nand/raw/tmio_nand.c
+++ b/drivers/mtd/nand/raw/tmio_nand.c
@@ -35,7 +35,7 @@
 #include <linux/ioport.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand_ecc.h>
+#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/mtd/partitions.h>
 #include <linux/slab.h>
 
diff --git a/drivers/mtd/nand/raw/txx9ndfmc.c b/drivers/mtd/nand/raw/txx9ndfmc.c
index fe8ed2441588..68b920eab6c8 100644
--- a/drivers/mtd/nand/raw/txx9ndfmc.c
+++ b/drivers/mtd/nand/raw/txx9ndfmc.c
@@ -14,7 +14,7 @@
 #include <linux/delay.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand_ecc.h>
+#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/mtd/partitions.h>
 #include <linux/io.h>
 #include <linux/platform_data/txx9/ndfmc.h>
diff --git a/drivers/mtd/sm_ftl.c b/drivers/mtd/sm_ftl.c
index b9f272408c4d..db430ae6a1a2 100644
--- a/drivers/mtd/sm_ftl.c
+++ b/drivers/mtd/sm_ftl.c
@@ -13,7 +13,7 @@
 #include <linux/sysfs.h>
 #include <linux/bitops.h>
 #include <linux/slab.h>
-#include <linux/mtd/nand_ecc.h>
+#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include "nand/raw/sm_common.h"
 #include "sm_ftl.h"
 
diff --git a/drivers/mtd/tests/mtd_nandecctest.c b/drivers/mtd/tests/mtd_nandecctest.c
index 13bca9ea0cae..e92e3fb287b6 100644
--- a/drivers/mtd/tests/mtd_nandecctest.c
+++ b/drivers/mtd/tests/mtd_nandecctest.c
@@ -8,7 +8,7 @@
 #include <linux/string.h>
 #include <linux/bitops.h>
 #include <linux/slab.h>
-#include <linux/mtd/nand_ecc.h>
+#include <linux/mtd/nand-ecc-sw-hamming.h>
 
 #include "mtd_test.h"
 
diff --git a/include/linux/mtd/nand-ecc-sw-hamming.h b/include/linux/mtd/nand-ecc-sw-hamming.h
new file mode 100644
index 000000000000..30a0cfa50eed
--- /dev/null
+++ b/include/linux/mtd/nand-ecc-sw-hamming.h
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *  Copyright (C) 2000-2010 Steven J. Hill <sjhill@realitydiluted.com>
+ *			    David Woodhouse <dwmw2@infradead.org>
+ *			    Thomas Gleixner <tglx@linutronix.de>
+ *
+ * This file is the header for the ECC algorithm.
+ */
+
+#ifndef __MTD_NAND_ECC_SW_HAMMING_H__
+#define __MTD_NAND_ECC_SW_HAMMING_H__
+
+struct nand_chip;
+
+/*
+ * Calculate 3 byte ECC code for eccsize byte block
+ */
+void __nand_calculate_ecc(const u_char *dat, unsigned int eccsize,
+			  u_char *ecc_code, bool sm_order);
+
+/*
+ * Calculate 3 byte ECC code for 256/512 byte block
+ */
+int nand_calculate_ecc(struct nand_chip *chip, const u_char *dat,
+		       u_char *ecc_code);
+
+/*
+ * Detect and correct a 1 bit error for eccsize byte block
+ */
+int __nand_correct_data(u_char *dat, u_char *read_ecc, u_char *calc_ecc,
+			unsigned int eccsize, bool sm_order);
+
+/*
+ * Detect and correct a 1 bit error for 256/512 byte block
+ */
+int nand_correct_data(struct nand_chip *chip, u_char *dat, u_char *read_ecc,
+		      u_char *calc_ecc);
+
+#endif /* __MTD_NAND_ECC_SW_HAMMING_H__ */
diff --git a/include/linux/mtd/nand_ecc.h b/include/linux/mtd/nand_ecc.h
deleted file mode 100644
index d423916b94f0..000000000000
--- a/include/linux/mtd/nand_ecc.h
+++ /dev/null
@@ -1,39 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- *  Copyright (C) 2000-2010 Steven J. Hill <sjhill@realitydiluted.com>
- *			    David Woodhouse <dwmw2@infradead.org>
- *			    Thomas Gleixner <tglx@linutronix.de>
- *
- * This file is the header for the ECC algorithm.
- */
-
-#ifndef __MTD_NAND_ECC_H__
-#define __MTD_NAND_ECC_H__
-
-struct nand_chip;
-
-/*
- * Calculate 3 byte ECC code for eccsize byte block
- */
-void __nand_calculate_ecc(const u_char *dat, unsigned int eccsize,
-			  u_char *ecc_code, bool sm_order);
-
-/*
- * Calculate 3 byte ECC code for 256/512 byte block
- */
-int nand_calculate_ecc(struct nand_chip *chip, const u_char *dat,
-		       u_char *ecc_code);
-
-/*
- * Detect and correct a 1 bit error for eccsize byte block
- */
-int __nand_correct_data(u_char *dat, u_char *read_ecc, u_char *calc_ecc,
-			unsigned int eccsize, bool sm_order);
-
-/*
- * Detect and correct a 1 bit error for 256/512 byte block
- */
-int nand_correct_data(struct nand_chip *chip, u_char *dat, u_char *read_ecc,
-		      u_char *calc_ecc);
-
-#endif /* __MTD_NAND_ECC_H__ */
diff --git a/include/linux/mtd/sharpsl.h b/include/linux/mtd/sharpsl.h
index d2c3cf29e0d1..3762a90077d6 100644
--- a/include/linux/mtd/sharpsl.h
+++ b/include/linux/mtd/sharpsl.h
@@ -9,7 +9,7 @@
 #define _MTD_SHARPSL_H
 
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand_ecc.h>
+#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/mtd/partitions.h>
 
 struct sharpsl_nand_platform_data {
-- 
cgit v1.2.3


From 2dbe0192efa02f2f405e193f4de84bf07c7f91fb Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 30 Sep 2020 01:01:16 +0200
Subject: mtd: nand: ecc-hamming: Clarify the driver descriptions

The include file pretends being the header for "ECC algorithm", while
it is just the header for the Hamming implementation. Make this clear
by rewording the sentence.

Do the same with the module description.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200929230124.31491-13-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/ecc-sw-hamming.c       | 2 +-
 include/linux/mtd/nand-ecc-sw-hamming.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/ecc-sw-hamming.c b/drivers/mtd/nand/ecc-sw-hamming.c
index 76966f5ff13f..a17faed374a8 100644
--- a/drivers/mtd/nand/ecc-sw-hamming.c
+++ b/drivers/mtd/nand/ecc-sw-hamming.c
@@ -481,4 +481,4 @@ EXPORT_SYMBOL(nand_correct_data);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Frans Meulenbroeks <fransmeulenbroeks@gmail.com>");
-MODULE_DESCRIPTION("Generic NAND ECC support");
+MODULE_DESCRIPTION("NAND software Hamming ECC support");
diff --git a/include/linux/mtd/nand-ecc-sw-hamming.h b/include/linux/mtd/nand-ecc-sw-hamming.h
index 30a0cfa50eed..85e9a929b5f9 100644
--- a/include/linux/mtd/nand-ecc-sw-hamming.h
+++ b/include/linux/mtd/nand-ecc-sw-hamming.h
@@ -4,7 +4,7 @@
  *			    David Woodhouse <dwmw2@infradead.org>
  *			    Thomas Gleixner <tglx@linutronix.de>
  *
- * This file is the header for the ECC algorithm.
+ * This file is the header for the NAND Hamming ECC implementation.
  */
 
 #ifndef __MTD_NAND_ECC_SW_HAMMING_H__
-- 
cgit v1.2.3


From 90ccf0a0192f7fa06e52de80cb528c5217e3e297 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 30 Sep 2020 01:01:19 +0200
Subject: mtd: nand: ecc-hamming: Rename the exported functions

Prefix by ecc_sw_hamming_ the functions which should be internal only
but are exported for "raw" operations.

Prefix by nand_ecc_sw_hamming_ the other functions which will be used
in the context of the declaration of an Hamming proper ECC engine
object.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200929230124.31491-16-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/ecc-sw-hamming.c       | 53 +++++++++++++++++----------------
 drivers/mtd/nand/raw/cs553x_nand.c      |  3 +-
 drivers/mtd/nand/raw/fsmc_nand.c        |  2 +-
 drivers/mtd/nand/raw/lpc32xx_slc.c      |  2 +-
 drivers/mtd/nand/raw/nand_base.c        | 25 ++++++++++++++--
 drivers/mtd/nand/raw/ndfc.c             |  3 +-
 drivers/mtd/nand/raw/sharpsl.c          |  2 +-
 drivers/mtd/nand/raw/tmio_nand.c        |  6 ++--
 drivers/mtd/nand/raw/txx9ndfmc.c        |  4 +--
 drivers/mtd/sm_ftl.c                    | 28 ++++++++---------
 drivers/mtd/tests/mtd_nandecctest.c     | 29 +++++++++---------
 include/linux/mtd/nand-ecc-sw-hamming.h | 36 ++++++++--------------
 include/linux/mtd/rawnand.h             |  7 +++++
 13 files changed, 108 insertions(+), 92 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/ecc-sw-hamming.c b/drivers/mtd/nand/ecc-sw-hamming.c
index 771e27ed8883..7ee0387ecb29 100644
--- a/drivers/mtd/nand/ecc-sw-hamming.c
+++ b/drivers/mtd/nand/ecc-sw-hamming.c
@@ -75,7 +75,7 @@ static const char bitsperbyte[256] = {
  * addressbits is a lookup table to filter out the bits from the xor-ed
  * ECC data that identify the faulty location.
  * this is only used for repairing parity
- * see the comments in nand_correct_data for more details
+ * see the comments in nand_ecc_sw_hamming_correct for more details
  */
 static const char addressbits[256] = {
 	0x00, 0x00, 0x01, 0x01, 0x00, 0x00, 0x01, 0x01,
@@ -112,11 +112,11 @@ static const char addressbits[256] = {
 	0x0e, 0x0e, 0x0f, 0x0f, 0x0e, 0x0e, 0x0f, 0x0f
 };
 
-void __nand_calculate_ecc(const unsigned char *buf, unsigned int eccsize,
-			  unsigned char *code, bool sm_order)
+int ecc_sw_hamming_calculate(const unsigned char *buf, unsigned int step_size,
+			     unsigned char *code, bool sm_order)
 {
 	const u32 *bp = (uint32_t *)buf;
-	const u32 eccsize_mult = eccsize >> 8;
+	const u32 eccsize_mult = step_size >> 8;
 	/* current value in buffer */
 	u32 cur;
 	/* rp0..rp17 are the various accumulated parities (per byte) */
@@ -347,31 +347,32 @@ void __nand_calculate_ecc(const unsigned char *buf, unsigned int eccsize,
 		    (invparity[par & 0x55] << 2) |
 		    (invparity[rp17] << 1) |
 		    (invparity[rp16] << 0);
+
+	return 0;
 }
-EXPORT_SYMBOL(__nand_calculate_ecc);
+EXPORT_SYMBOL(ecc_sw_hamming_calculate);
 
 /**
- * nand_calculate_ecc - Calculate 3-byte ECC for 256/512-byte block
- * @chip: NAND chip object
+ * nand_ecc_sw_hamming_calculate - Calculate 3-byte ECC for 256/512-byte block
+ * @nand: NAND device
  * @buf: Input buffer with raw data
  * @code: Output buffer with ECC
  */
-int nand_calculate_ecc(struct nand_chip *chip, const unsigned char *buf,
-		       unsigned char *code)
+int nand_ecc_sw_hamming_calculate(struct nand_device *nand,
+				  const unsigned char *buf, unsigned char *code)
 {
+	struct nand_chip *chip = mtd_to_nand(nanddev_to_mtd(nand));
 	bool sm_order = chip->ecc.options & NAND_ECC_SOFT_HAMMING_SM_ORDER;
 
-	__nand_calculate_ecc(buf, chip->ecc.size, code, sm_order);
-
-	return 0;
+	return ecc_sw_hamming_calculate(buf, chip->ecc.size, code, sm_order);
 }
-EXPORT_SYMBOL(nand_calculate_ecc);
+EXPORT_SYMBOL(nand_ecc_sw_hamming_calculate);
 
-int __nand_correct_data(unsigned char *buf,
-			unsigned char *read_ecc, unsigned char *calc_ecc,
-			unsigned int eccsize, bool sm_order)
+int ecc_sw_hamming_correct(unsigned char *buf, unsigned char *read_ecc,
+			   unsigned char *calc_ecc, unsigned int step_size,
+			   bool sm_order)
 {
-	const u32 eccsize_mult = eccsize >> 8;
+	const u32 eccsize_mult = step_size >> 8;
 	unsigned char b0, b1, b2, bit_addr;
 	unsigned int byte_addr;
 
@@ -437,26 +438,28 @@ int __nand_correct_data(unsigned char *buf,
 	pr_err("%s: uncorrectable ECC error\n", __func__);
 	return -EBADMSG;
 }
-EXPORT_SYMBOL(__nand_correct_data);
+EXPORT_SYMBOL(ecc_sw_hamming_correct);
 
 /**
- * nand_correct_data - Detect and correct bit error(s)
- * @chip: NAND chip object
+ * nand_ecc_sw_hamming_correct - Detect and correct bit error(s)
+ * @nand: NAND device
  * @buf: Raw data read from the chip
  * @read_ecc: ECC bytes read from the chip
  * @calc_ecc: ECC calculated from the raw data
  *
  * Detect and correct up to 1 bit error per 256/512-byte block.
  */
-int nand_correct_data(struct nand_chip *chip, unsigned char *buf,
-		      unsigned char *read_ecc, unsigned char *calc_ecc)
+int nand_ecc_sw_hamming_correct(struct nand_device *nand, unsigned char *buf,
+				unsigned char *read_ecc,
+				unsigned char *calc_ecc)
 {
+	struct nand_chip *chip = mtd_to_nand(nanddev_to_mtd(nand));
 	bool sm_order = chip->ecc.options & NAND_ECC_SOFT_HAMMING_SM_ORDER;
 
-	return __nand_correct_data(buf, read_ecc, calc_ecc, chip->ecc.size,
-				   sm_order);
+	return ecc_sw_hamming_correct(buf, read_ecc, calc_ecc, chip->ecc.size,
+				      sm_order);
 }
-EXPORT_SYMBOL(nand_correct_data);
+EXPORT_SYMBOL(nand_ecc_sw_hamming_correct);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Frans Meulenbroeks <fransmeulenbroeks@gmail.com>");
diff --git a/drivers/mtd/nand/raw/cs553x_nand.c b/drivers/mtd/nand/raw/cs553x_nand.c
index 9a2bdb45a771..6edf78c16fc8 100644
--- a/drivers/mtd/nand/raw/cs553x_nand.c
+++ b/drivers/mtd/nand/raw/cs553x_nand.c
@@ -19,7 +19,6 @@
 #include <linux/delay.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/mtd/partitions.h>
 #include <linux/iopoll.h>
 
@@ -252,7 +251,7 @@ static int cs553x_attach_chip(struct nand_chip *chip)
 	chip->ecc.bytes = 3;
 	chip->ecc.hwctl  = cs_enable_hwecc;
 	chip->ecc.calculate = cs_calculate_ecc;
-	chip->ecc.correct  = nand_correct_data;
+	chip->ecc.correct  = rawnand_sw_hamming_correct;
 	chip->ecc.strength = 1;
 
 	return 0;
diff --git a/drivers/mtd/nand/raw/fsmc_nand.c b/drivers/mtd/nand/raw/fsmc_nand.c
index e880db5852d8..1e2ed45be2f1 100644
--- a/drivers/mtd/nand/raw/fsmc_nand.c
+++ b/drivers/mtd/nand/raw/fsmc_nand.c
@@ -918,7 +918,7 @@ static int fsmc_nand_attach_chip(struct nand_chip *nand)
 	case NAND_ECC_ENGINE_TYPE_ON_HOST:
 		dev_info(host->dev, "Using 1-bit HW ECC scheme\n");
 		nand->ecc.calculate = fsmc_read_hwecc_ecc1;
-		nand->ecc.correct = nand_correct_data;
+		nand->ecc.correct = rawnand_sw_hamming_correct;
 		nand->ecc.hwctl = fsmc_enable_hwecc;
 		nand->ecc.bytes = 3;
 		nand->ecc.strength = 1;
diff --git a/drivers/mtd/nand/raw/lpc32xx_slc.c b/drivers/mtd/nand/raw/lpc32xx_slc.c
index 0bf9c3fbcd82..beecabfa5181 100644
--- a/drivers/mtd/nand/raw/lpc32xx_slc.c
+++ b/drivers/mtd/nand/raw/lpc32xx_slc.c
@@ -803,7 +803,7 @@ static int lpc32xx_nand_attach_chip(struct nand_chip *chip)
 	chip->ecc.write_oob = lpc32xx_nand_write_oob_syndrome;
 	chip->ecc.read_oob = lpc32xx_nand_read_oob_syndrome;
 	chip->ecc.calculate = lpc32xx_nand_ecc_calculate;
-	chip->ecc.correct = nand_correct_data;
+	chip->ecc.correct = rawnand_sw_hamming_correct;
 	chip->ecc.hwctl = lpc32xx_nand_ecc_enable;
 
 	/*
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index bee7c64a0a4e..32e9870a2cf8 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -5139,6 +5139,27 @@ static void nand_scan_ident_cleanup(struct nand_chip *chip)
 	kfree(chip->parameters.onfi);
 }
 
+int rawnand_sw_hamming_calculate(struct nand_chip *chip,
+				 const unsigned char *buf,
+				 unsigned char *code)
+{
+	struct nand_device *base = &chip->base;
+
+	return nand_ecc_sw_hamming_calculate(base, buf, code);
+}
+EXPORT_SYMBOL(rawnand_sw_hamming_calculate);
+
+int rawnand_sw_hamming_correct(struct nand_chip *chip,
+			       unsigned char *buf,
+			       unsigned char *read_ecc,
+			       unsigned char *calc_ecc)
+{
+	struct nand_device *base = &chip->base;
+
+	return nand_ecc_sw_hamming_correct(base, buf, read_ecc, calc_ecc);
+}
+EXPORT_SYMBOL(rawnand_sw_hamming_correct);
+
 int rawnand_sw_bch_init(struct nand_chip *chip)
 {
 	struct nand_device *base = &chip->base;
@@ -5263,8 +5284,8 @@ static int nand_set_ecc_soft_ops(struct nand_chip *chip)
 
 	switch (ecc->algo) {
 	case NAND_ECC_ALGO_HAMMING:
-		ecc->calculate = nand_calculate_ecc;
-		ecc->correct = nand_correct_data;
+		ecc->calculate = rawnand_sw_hamming_calculate;
+		ecc->correct = rawnand_sw_hamming_correct;
 		ecc->read_page = nand_read_page_swecc;
 		ecc->read_subpage = nand_read_subpage;
 		ecc->write_page = nand_write_page_swecc;
diff --git a/drivers/mtd/nand/raw/ndfc.c b/drivers/mtd/nand/raw/ndfc.c
index 8cda6633280b..338d6b1a189e 100644
--- a/drivers/mtd/nand/raw/ndfc.c
+++ b/drivers/mtd/nand/raw/ndfc.c
@@ -18,7 +18,6 @@
  */
 #include <linux/module.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/mtd/partitions.h>
 #include <linux/mtd/ndfc.h>
 #include <linux/slab.h>
@@ -146,7 +145,7 @@ static int ndfc_chip_init(struct ndfc_controller *ndfc,
 	chip->controller = &ndfc->ndfc_control;
 	chip->legacy.read_buf = ndfc_read_buf;
 	chip->legacy.write_buf = ndfc_write_buf;
-	chip->ecc.correct = nand_correct_data;
+	chip->ecc.correct = rawnand_sw_hamming_correct;
 	chip->ecc.hwctl = ndfc_enable_hwecc;
 	chip->ecc.calculate = ndfc_calculate_ecc;
 	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
diff --git a/drivers/mtd/nand/raw/sharpsl.c b/drivers/mtd/nand/raw/sharpsl.c
index 2fae6ade8b13..3f55b523aead 100644
--- a/drivers/mtd/nand/raw/sharpsl.c
+++ b/drivers/mtd/nand/raw/sharpsl.c
@@ -107,7 +107,7 @@ static int sharpsl_attach_chip(struct nand_chip *chip)
 	chip->ecc.strength = 1;
 	chip->ecc.hwctl = sharpsl_nand_enable_hwecc;
 	chip->ecc.calculate = sharpsl_nand_calculate_ecc;
-	chip->ecc.correct = nand_correct_data;
+	chip->ecc.correct = rawnand_sw_hamming_correct;
 
 	return 0;
 }
diff --git a/drivers/mtd/nand/raw/tmio_nand.c b/drivers/mtd/nand/raw/tmio_nand.c
index fadca0b9e21f..29edacbec826 100644
--- a/drivers/mtd/nand/raw/tmio_nand.c
+++ b/drivers/mtd/nand/raw/tmio_nand.c
@@ -293,11 +293,11 @@ static int tmio_nand_correct_data(struct nand_chip *chip, unsigned char *buf,
 	int r0, r1;
 
 	/* assume ecc.size = 512 and ecc.bytes = 6 */
-	r0 = __nand_correct_data(buf, read_ecc, calc_ecc, 256, false);
+	r0 = rawnand_sw_hamming_correct(chip, buf, read_ecc, calc_ecc);
 	if (r0 < 0)
 		return r0;
-	r1 = __nand_correct_data(buf + 256, read_ecc + 3, calc_ecc + 3, 256,
-				 false);
+	r1 = rawnand_sw_hamming_correct(chip, buf + 256, read_ecc + 3,
+					calc_ecc + 3);
 	if (r1 < 0)
 		return r1;
 	return r0 + r1;
diff --git a/drivers/mtd/nand/raw/txx9ndfmc.c b/drivers/mtd/nand/raw/txx9ndfmc.c
index 68b920eab6c8..a705523eb916 100644
--- a/drivers/mtd/nand/raw/txx9ndfmc.c
+++ b/drivers/mtd/nand/raw/txx9ndfmc.c
@@ -194,8 +194,8 @@ static int txx9ndfmc_correct_data(struct nand_chip *chip, unsigned char *buf,
 	int stat;
 
 	for (eccsize = chip->ecc.size; eccsize > 0; eccsize -= 256) {
-		stat = __nand_correct_data(buf, read_ecc, calc_ecc, 256,
-					   false);
+		stat = rawnand_sw_hamming_correct(chip, buf, read_ecc,
+						  calc_ecc);
 		if (stat < 0)
 			return stat;
 		corrected += stat;
diff --git a/drivers/mtd/sm_ftl.c b/drivers/mtd/sm_ftl.c
index db430ae6a1a2..4d1ae25507ab 100644
--- a/drivers/mtd/sm_ftl.c
+++ b/drivers/mtd/sm_ftl.c
@@ -216,20 +216,19 @@ static void sm_break_offset(struct sm_ftl *ftl, loff_t loffset,
 
 static int sm_correct_sector(uint8_t *buffer, struct sm_oob *oob)
 {
+	bool sm_order = IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_HAMMING_SMC);
 	uint8_t ecc[3];
 
-	__nand_calculate_ecc(buffer, SM_SMALL_PAGE, ecc,
-			     IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_HAMMING_SMC));
-	if (__nand_correct_data(buffer, ecc, oob->ecc1, SM_SMALL_PAGE,
-				IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_HAMMING_SMC)) < 0)
+	ecc_sw_hamming_calculate(buffer, SM_SMALL_PAGE, ecc, sm_order);
+	if (ecc_sw_hamming_correct(buffer, ecc, oob->ecc1, SM_SMALL_PAGE,
+				   sm_order) < 0)
 		return -EIO;
 
 	buffer += SM_SMALL_PAGE;
 
-	__nand_calculate_ecc(buffer, SM_SMALL_PAGE, ecc,
-			     IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_HAMMING_SMC));
-	if (__nand_correct_data(buffer, ecc, oob->ecc2, SM_SMALL_PAGE,
-				IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_HAMMING_SMC)) < 0)
+	ecc_sw_hamming_calculate(buffer, SM_SMALL_PAGE, ecc, sm_order);
+	if (ecc_sw_hamming_correct(buffer, ecc, oob->ecc2, SM_SMALL_PAGE,
+				   sm_order) < 0)
 		return -EIO;
 	return 0;
 }
@@ -369,6 +368,7 @@ static int sm_write_block(struct sm_ftl *ftl, uint8_t *buf,
 			  int zone, int block, int lba,
 			  unsigned long invalid_bitmap)
 {
+	bool sm_order = IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_HAMMING_SMC);
 	struct sm_oob oob;
 	int boffset;
 	int retry = 0;
@@ -395,13 +395,13 @@ restart:
 		}
 
 		if (ftl->smallpagenand) {
-			__nand_calculate_ecc(buf + boffset, SM_SMALL_PAGE,
-					oob.ecc1,
-					IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_HAMMING_SMC));
+			ecc_sw_hamming_calculate(buf + boffset,
+						 SM_SMALL_PAGE, oob.ecc1,
+						 sm_order);
 
-			__nand_calculate_ecc(buf + boffset + SM_SMALL_PAGE,
-					SM_SMALL_PAGE, oob.ecc2,
-					IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_HAMMING_SMC));
+			ecc_sw_hamming_calculate(buf + boffset + SM_SMALL_PAGE,
+						 SM_SMALL_PAGE, oob.ecc2,
+						 sm_order);
 		}
 		if (!sm_write_sector(ftl, zone, block, boffset,
 							buf + boffset, &oob))
diff --git a/drivers/mtd/tests/mtd_nandecctest.c b/drivers/mtd/tests/mtd_nandecctest.c
index e92e3fb287b6..c4f271314f52 100644
--- a/drivers/mtd/tests/mtd_nandecctest.c
+++ b/drivers/mtd/tests/mtd_nandecctest.c
@@ -119,13 +119,13 @@ static void no_bit_error(void *error_data, void *error_ecc,
 static int no_bit_error_verify(void *error_data, void *error_ecc,
 				void *correct_data, const size_t size)
 {
+	bool sm_order = IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_HAMMING_SMC);
 	unsigned char calc_ecc[3];
 	int ret;
 
-	__nand_calculate_ecc(error_data, size, calc_ecc,
-			     IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_HAMMING_SMC));
-	ret = __nand_correct_data(error_data, error_ecc, calc_ecc, size,
-				  IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_HAMMING_SMC));
+	ecc_sw_hamming_calculate(error_data, size, calc_ecc, sm_order);
+	ret = ecc_sw_hamming_correct(error_data, error_ecc, calc_ecc, size,
+				     sm_order);
 	if (ret == 0 && !memcmp(correct_data, error_data, size))
 		return 0;
 
@@ -149,13 +149,13 @@ static void single_bit_error_in_ecc(void *error_data, void *error_ecc,
 static int single_bit_error_correct(void *error_data, void *error_ecc,
 				void *correct_data, const size_t size)
 {
+	bool sm_order = IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_HAMMING_SMC);
 	unsigned char calc_ecc[3];
 	int ret;
 
-	__nand_calculate_ecc(error_data, size, calc_ecc,
-			     IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_HAMMING_SMC));
-	ret = __nand_correct_data(error_data, error_ecc, calc_ecc, size,
-				  IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_HAMMING_SMC));
+	ecc_sw_hamming_calculate(error_data, size, calc_ecc, sm_order);
+	ret = ecc_sw_hamming_correct(error_data, error_ecc, calc_ecc, size,
+				     sm_order);
 	if (ret == 1 && !memcmp(correct_data, error_data, size))
 		return 0;
 
@@ -186,13 +186,13 @@ static void double_bit_error_in_ecc(void *error_data, void *error_ecc,
 static int double_bit_error_detect(void *error_data, void *error_ecc,
 				void *correct_data, const size_t size)
 {
+	bool sm_order = IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_HAMMING_SMC);
 	unsigned char calc_ecc[3];
 	int ret;
 
-	__nand_calculate_ecc(error_data, size, calc_ecc,
-			     IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_HAMMING_SMC));
-	ret = __nand_correct_data(error_data, error_ecc, calc_ecc, size,
-				  IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_HAMMING_SMC));
+	ecc_sw_hamming_calculate(error_data, size, calc_ecc, sm_order);
+	ret = ecc_sw_hamming_correct(error_data, error_ecc, calc_ecc, size,
+				     sm_order);
 
 	return (ret == -EBADMSG) ? 0 : -EINVAL;
 }
@@ -248,6 +248,7 @@ static void dump_data_ecc(void *error_data, void *error_ecc, void *correct_data,
 
 static int nand_ecc_test_run(const size_t size)
 {
+	bool sm_order = IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_HAMMING_SMC);
 	int i;
 	int err = 0;
 	void *error_data;
@@ -266,9 +267,7 @@ static int nand_ecc_test_run(const size_t size)
 	}
 
 	prandom_bytes(correct_data, size);
-	__nand_calculate_ecc(correct_data, size, correct_ecc,
-			     IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_HAMMING_SMC));
-
+	ecc_sw_hamming_calculate(correct_data, size, correct_ecc, sm_order);
 	for (i = 0; i < ARRAY_SIZE(nand_ecc_test); i++) {
 		nand_ecc_test[i].prepare(error_data, error_ecc,
 				correct_data, correct_ecc, size);
diff --git a/include/linux/mtd/nand-ecc-sw-hamming.h b/include/linux/mtd/nand-ecc-sw-hamming.h
index 85e9a929b5f9..84a123bf45f3 100644
--- a/include/linux/mtd/nand-ecc-sw-hamming.h
+++ b/include/linux/mtd/nand-ecc-sw-hamming.h
@@ -10,30 +10,18 @@
 #ifndef __MTD_NAND_ECC_SW_HAMMING_H__
 #define __MTD_NAND_ECC_SW_HAMMING_H__
 
-struct nand_chip;
+#include <linux/mtd/nand.h>
 
-/*
- * Calculate 3 byte ECC code for eccsize byte block
- */
-void __nand_calculate_ecc(const u_char *dat, unsigned int eccsize,
-			  u_char *ecc_code, bool sm_order);
-
-/*
- * Calculate 3 byte ECC code for 256/512 byte block
- */
-int nand_calculate_ecc(struct nand_chip *chip, const u_char *dat,
-		       u_char *ecc_code);
-
-/*
- * Detect and correct a 1 bit error for eccsize byte block
- */
-int __nand_correct_data(u_char *dat, u_char *read_ecc, u_char *calc_ecc,
-			unsigned int eccsize, bool sm_order);
-
-/*
- * Detect and correct a 1 bit error for 256/512 byte block
- */
-int nand_correct_data(struct nand_chip *chip, u_char *dat, u_char *read_ecc,
-		      u_char *calc_ecc);
+int ecc_sw_hamming_calculate(const unsigned char *buf, unsigned int step_size,
+			     unsigned char *code, bool sm_order);
+int nand_ecc_sw_hamming_calculate(struct nand_device *nand,
+				  const unsigned char *buf,
+				  unsigned char *code);
+int ecc_sw_hamming_correct(unsigned char *buf, unsigned char *read_ecc,
+			   unsigned char *calc_ecc, unsigned int step_size,
+			   bool sm_order);
+int nand_ecc_sw_hamming_correct(struct nand_device *nand, unsigned char *buf,
+				unsigned char *read_ecc,
+				unsigned char *calc_ecc);
 
 #endif /* __MTD_NAND_ECC_SW_HAMMING_H__ */
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 15743c2c2cab..685d24557e95 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -1301,6 +1301,13 @@ static inline int nand_opcode_8bits(unsigned int command)
 	return 0;
 }
 
+int rawnand_sw_hamming_calculate(struct nand_chip *chip,
+				 const unsigned char *buf,
+				 unsigned char *code);
+int rawnand_sw_hamming_correct(struct nand_chip *chip,
+			       unsigned char *buf,
+			       unsigned char *read_ecc,
+			       unsigned char *calc_ecc);
 int rawnand_sw_bch_init(struct nand_chip *chip);
 int rawnand_sw_bch_correct(struct nand_chip *chip, unsigned char *buf,
 			   unsigned char *read_ecc, unsigned char *calc_ecc);
-- 
cgit v1.2.3


From 19b2ce184b9f404d6620adf667a9019e6abcae51 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 30 Sep 2020 01:01:20 +0200
Subject: mtd: nand: ecc-hamming: Stop using raw NAND structures

This code is meant to be reused by the SPI-NAND core. Now that the
driver has been cleaned and reorganized, use a generic ECC engine
object to store the driver's data instead of accessing members of the
nand_chip structure. This means adding proper init/cleanup helpers.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200929230124.31491-17-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/ecc-sw-hamming.c       | 17 +++++----
 drivers/mtd/nand/raw/nand_base.c        | 63 +++++++++++++++++++++++++++++++--
 include/linux/mtd/nand-ecc-sw-hamming.h | 20 +++++++++++
 include/linux/mtd/rawnand.h             |  2 ++
 4 files changed, 90 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/ecc-sw-hamming.c b/drivers/mtd/nand/ecc-sw-hamming.c
index 7ee0387ecb29..9cd70b4637c1 100644
--- a/drivers/mtd/nand/ecc-sw-hamming.c
+++ b/drivers/mtd/nand/ecc-sw-hamming.c
@@ -17,8 +17,6 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/mtd/mtd.h>
-#include <linux/mtd/rawnand.h>
 #include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <asm/byteorder.h>
 
@@ -361,10 +359,11 @@ EXPORT_SYMBOL(ecc_sw_hamming_calculate);
 int nand_ecc_sw_hamming_calculate(struct nand_device *nand,
 				  const unsigned char *buf, unsigned char *code)
 {
-	struct nand_chip *chip = mtd_to_nand(nanddev_to_mtd(nand));
-	bool sm_order = chip->ecc.options & NAND_ECC_SOFT_HAMMING_SM_ORDER;
+	struct nand_ecc_sw_hamming_conf *engine_conf = nand->ecc.ctx.priv;
+	unsigned int step_size = nand->ecc.ctx.conf.step_size;
 
-	return ecc_sw_hamming_calculate(buf, chip->ecc.size, code, sm_order);
+	return ecc_sw_hamming_calculate(buf, step_size, code,
+					engine_conf->sm_order);
 }
 EXPORT_SYMBOL(nand_ecc_sw_hamming_calculate);
 
@@ -453,11 +452,11 @@ int nand_ecc_sw_hamming_correct(struct nand_device *nand, unsigned char *buf,
 				unsigned char *read_ecc,
 				unsigned char *calc_ecc)
 {
-	struct nand_chip *chip = mtd_to_nand(nanddev_to_mtd(nand));
-	bool sm_order = chip->ecc.options & NAND_ECC_SOFT_HAMMING_SM_ORDER;
+	struct nand_ecc_sw_hamming_conf *engine_conf = nand->ecc.ctx.priv;
+	unsigned int step_size = nand->ecc.ctx.conf.step_size;
 
-	return ecc_sw_hamming_correct(buf, read_ecc, calc_ecc, chip->ecc.size,
-				      sm_order);
+	return ecc_sw_hamming_correct(buf, read_ecc, calc_ecc, step_size,
+				      engine_conf->sm_order);
 }
 EXPORT_SYMBOL(nand_ecc_sw_hamming_correct);
 
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 32e9870a2cf8..c36d2d4a72d5 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -5139,6 +5139,46 @@ static void nand_scan_ident_cleanup(struct nand_chip *chip)
 	kfree(chip->parameters.onfi);
 }
 
+int rawnand_sw_hamming_init(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct nand_ecc_sw_hamming_conf *engine_conf;
+	struct nand_device *base = &chip->base;
+
+	base->ecc.user_conf.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
+	base->ecc.user_conf.algo = NAND_ECC_ALGO_HAMMING;
+	base->ecc.user_conf.strength = chip->ecc.strength;
+	base->ecc.user_conf.step_size = chip->ecc.size;
+
+	if (base->ecc.user_conf.strength != 1 ||
+	    (base->ecc.user_conf.step_size != 256 &&
+	     base->ecc.user_conf.step_size != 512)) {
+		pr_err("%s: unsupported strength or step size\n", __func__);
+		return -EINVAL;
+	}
+
+	engine_conf = kzalloc(sizeof(*engine_conf), GFP_KERNEL);
+	if (!engine_conf)
+		return -ENOMEM;
+
+	engine_conf->code_size = 3;
+	engine_conf->nsteps = mtd->writesize / base->ecc.user_conf.step_size;
+
+	if (chip->ecc.options & NAND_ECC_SOFT_HAMMING_SM_ORDER)
+		engine_conf->sm_order = true;
+
+	base->ecc.ctx.priv = engine_conf;
+
+	chip->ecc.size = base->ecc.ctx.conf.step_size;
+	chip->ecc.strength = base->ecc.ctx.conf.strength;
+	chip->ecc.total = base->ecc.ctx.total;
+	chip->ecc.steps = engine_conf->nsteps;
+	chip->ecc.bytes = engine_conf->code_size;
+
+	return 0;
+}
+EXPORT_SYMBOL(rawnand_sw_hamming_init);
+
 int rawnand_sw_hamming_calculate(struct nand_chip *chip,
 				 const unsigned char *buf,
 				 unsigned char *code)
@@ -5160,6 +5200,14 @@ int rawnand_sw_hamming_correct(struct nand_chip *chip,
 }
 EXPORT_SYMBOL(rawnand_sw_hamming_correct);
 
+void rawnand_sw_hamming_cleanup(struct nand_chip *chip)
+{
+	struct nand_device *base = &chip->base;
+
+	kfree(base->ecc.ctx.priv);
+}
+EXPORT_SYMBOL(rawnand_sw_hamming_cleanup);
+
 int rawnand_sw_bch_init(struct nand_chip *chip)
 {
 	struct nand_device *base = &chip->base;
@@ -5303,6 +5351,12 @@ static int nand_set_ecc_soft_ops(struct nand_chip *chip)
 		if (IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_HAMMING_SMC))
 			ecc->options |= NAND_ECC_SOFT_HAMMING_SM_ORDER;
 
+		ret = rawnand_sw_hamming_init(chip);
+		if (ret) {
+			WARN(1, "Hamming ECC initialization failed!\n");
+			return ret;
+		}
+
 		return 0;
 	case NAND_ECC_ALGO_BCH:
 		if (!IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_BCH)) {
@@ -5996,9 +6050,12 @@ EXPORT_SYMBOL(nand_scan_with_ids);
  */
 void nand_cleanup(struct nand_chip *chip)
 {
-	if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_SOFT &&
-	    chip->ecc.algo == NAND_ECC_ALGO_BCH)
-		rawnand_sw_bch_cleanup(chip);
+	if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_SOFT) {
+		if (chip->ecc.algo == NAND_ECC_ALGO_HAMMING)
+			rawnand_sw_hamming_cleanup(chip);
+		else if (chip->ecc.algo == NAND_ECC_ALGO_BCH)
+			rawnand_sw_bch_cleanup(chip);
+	}
 
 	nanddev_cleanup(&chip->base);
 
diff --git a/include/linux/mtd/nand-ecc-sw-hamming.h b/include/linux/mtd/nand-ecc-sw-hamming.h
index 84a123bf45f3..9d4b4d623741 100644
--- a/include/linux/mtd/nand-ecc-sw-hamming.h
+++ b/include/linux/mtd/nand-ecc-sw-hamming.h
@@ -12,6 +12,26 @@
 
 #include <linux/mtd/nand.h>
 
+/**
+ * struct nand_ecc_sw_hamming_conf - private software Hamming ECC engine structure
+ * @reqooblen: Save the actual user OOB length requested before overwriting it
+ * @spare_oobbuf: Spare OOB buffer if none is provided
+ * @code_size: Number of bytes needed to store a code (one code per step)
+ * @nsteps: Number of steps
+ * @calc_buf: Buffer to use when calculating ECC bytes
+ * @code_buf: Buffer to use when reading (raw) ECC bytes from the chip
+ * @sm_order: Smart Media special ordering
+ */
+struct nand_ecc_sw_hamming_conf {
+	unsigned int reqooblen;
+	void *spare_oobbuf;
+	unsigned int code_size;
+	unsigned int nsteps;
+	u8 *calc_buf;
+	u8 *code_buf;
+	unsigned int sm_order;
+};
+
 int ecc_sw_hamming_calculate(const unsigned char *buf, unsigned int step_size,
 			     unsigned char *code, bool sm_order);
 int nand_ecc_sw_hamming_calculate(struct nand_device *nand,
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 685d24557e95..0a90a8792d18 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -1301,6 +1301,7 @@ static inline int nand_opcode_8bits(unsigned int command)
 	return 0;
 }
 
+int rawnand_sw_hamming_init(struct nand_chip *chip);
 int rawnand_sw_hamming_calculate(struct nand_chip *chip,
 				 const unsigned char *buf,
 				 unsigned char *code);
@@ -1308,6 +1309,7 @@ int rawnand_sw_hamming_correct(struct nand_chip *chip,
 			       unsigned char *buf,
 			       unsigned char *read_ecc,
 			       unsigned char *calc_ecc);
+void rawnand_sw_hamming_cleanup(struct nand_chip *chip);
 int rawnand_sw_bch_init(struct nand_chip *chip);
 int rawnand_sw_bch_correct(struct nand_chip *chip, unsigned char *buf,
 			   unsigned char *read_ecc, unsigned char *calc_ecc);
-- 
cgit v1.2.3


From eb08376a5dd943cf2a7360f236fe20bbd709fa95 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 30 Sep 2020 01:01:21 +0200
Subject: mtd: nand: ecc-hamming: Remove useless includes

Most of the includes are simply useless, drop them.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200929230124.31491-18-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/raw/fsl_elbc_nand.c | 1 -
 drivers/mtd/nand/raw/fsl_ifc_nand.c  | 1 -
 drivers/mtd/nand/raw/fsl_upm.c       | 1 -
 drivers/mtd/nand/raw/fsmc_nand.c     | 1 -
 drivers/mtd/nand/raw/lpc32xx_mlc.c   | 1 -
 drivers/mtd/nand/raw/lpc32xx_slc.c   | 1 -
 drivers/mtd/nand/raw/pasemi_nand.c   | 1 -
 drivers/mtd/nand/raw/s3c2410.c       | 1 -
 drivers/mtd/nand/raw/sharpsl.c       | 1 -
 drivers/mtd/nand/raw/tmio_nand.c     | 1 -
 drivers/mtd/nand/raw/txx9ndfmc.c     | 1 -
 include/linux/mtd/sharpsl.h          | 1 -
 12 files changed, 12 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/raw/fsl_elbc_nand.c b/drivers/mtd/nand/raw/fsl_elbc_nand.c
index eb255cf83e32..aab93b9e6052 100644
--- a/drivers/mtd/nand/raw/fsl_elbc_nand.c
+++ b/drivers/mtd/nand/raw/fsl_elbc_nand.c
@@ -22,7 +22,6 @@
 
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/mtd/partitions.h>
 
 #include <asm/io.h>
diff --git a/drivers/mtd/nand/raw/fsl_ifc_nand.c b/drivers/mtd/nand/raw/fsl_ifc_nand.c
index d2f84917fa8b..02d500176838 100644
--- a/drivers/mtd/nand/raw/fsl_ifc_nand.c
+++ b/drivers/mtd/nand/raw/fsl_ifc_nand.c
@@ -15,7 +15,6 @@
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
 #include <linux/mtd/partitions.h>
-#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/fsl_ifc.h>
 #include <linux/iopoll.h>
 
diff --git a/drivers/mtd/nand/raw/fsl_upm.c b/drivers/mtd/nand/raw/fsl_upm.c
index 3824361928a1..b3cc427100a2 100644
--- a/drivers/mtd/nand/raw/fsl_upm.c
+++ b/drivers/mtd/nand/raw/fsl_upm.c
@@ -11,7 +11,6 @@
 #include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/mtd/partitions.h>
 #include <linux/mtd/mtd.h>
 #include <linux/of_platform.h>
diff --git a/drivers/mtd/nand/raw/fsmc_nand.c b/drivers/mtd/nand/raw/fsmc_nand.c
index 1e2ed45be2f1..0101c0fab50a 100644
--- a/drivers/mtd/nand/raw/fsmc_nand.c
+++ b/drivers/mtd/nand/raw/fsmc_nand.c
@@ -26,7 +26,6 @@
 #include <linux/types.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/platform_device.h>
 #include <linux/of.h>
 #include <linux/mtd/partitions.h>
diff --git a/drivers/mtd/nand/raw/lpc32xx_mlc.c b/drivers/mtd/nand/raw/lpc32xx_mlc.c
index 885b03b7af52..452ecaf7775a 100644
--- a/drivers/mtd/nand/raw/lpc32xx_mlc.c
+++ b/drivers/mtd/nand/raw/lpc32xx_mlc.c
@@ -31,7 +31,6 @@
 #include <linux/mm.h>
 #include <linux/dma-mapping.h>
 #include <linux/dmaengine.h>
-#include <linux/mtd/nand-ecc-sw-hamming.h>
 
 #define DRV_NAME "lpc32xx_mlc"
 
diff --git a/drivers/mtd/nand/raw/lpc32xx_slc.c b/drivers/mtd/nand/raw/lpc32xx_slc.c
index beecabfa5181..6b7269cfb7d8 100644
--- a/drivers/mtd/nand/raw/lpc32xx_slc.c
+++ b/drivers/mtd/nand/raw/lpc32xx_slc.c
@@ -23,7 +23,6 @@
 #include <linux/mm.h>
 #include <linux/dma-mapping.h>
 #include <linux/dmaengine.h>
-#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/gpio.h>
 #include <linux/of.h>
 #include <linux/of_gpio.h>
diff --git a/drivers/mtd/nand/raw/pasemi_nand.c b/drivers/mtd/nand/raw/pasemi_nand.c
index 2dddbdca9e94..5741887d7a24 100644
--- a/drivers/mtd/nand/raw/pasemi_nand.c
+++ b/drivers/mtd/nand/raw/pasemi_nand.c
@@ -14,7 +14,6 @@
 #include <linux/module.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
diff --git a/drivers/mtd/nand/raw/s3c2410.c b/drivers/mtd/nand/raw/s3c2410.c
index f7eb3b5fa792..cb2d1b4e278c 100644
--- a/drivers/mtd/nand/raw/s3c2410.c
+++ b/drivers/mtd/nand/raw/s3c2410.c
@@ -30,7 +30,6 @@
 
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/mtd/partitions.h>
 
 #include <linux/platform_data/mtd-nand-s3c2410.h>
diff --git a/drivers/mtd/nand/raw/sharpsl.c b/drivers/mtd/nand/raw/sharpsl.c
index 3f55b523aead..5612ee628425 100644
--- a/drivers/mtd/nand/raw/sharpsl.c
+++ b/drivers/mtd/nand/raw/sharpsl.c
@@ -12,7 +12,6 @@
 #include <linux/delay.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/mtd/partitions.h>
 #include <linux/mtd/sharpsl.h>
 #include <linux/interrupt.h>
diff --git a/drivers/mtd/nand/raw/tmio_nand.c b/drivers/mtd/nand/raw/tmio_nand.c
index 29edacbec826..de8e919d0ebe 100644
--- a/drivers/mtd/nand/raw/tmio_nand.c
+++ b/drivers/mtd/nand/raw/tmio_nand.c
@@ -35,7 +35,6 @@
 #include <linux/ioport.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/mtd/partitions.h>
 #include <linux/slab.h>
 
diff --git a/drivers/mtd/nand/raw/txx9ndfmc.c b/drivers/mtd/nand/raw/txx9ndfmc.c
index a705523eb916..1a9449e53bf9 100644
--- a/drivers/mtd/nand/raw/txx9ndfmc.c
+++ b/drivers/mtd/nand/raw/txx9ndfmc.c
@@ -14,7 +14,6 @@
 #include <linux/delay.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/mtd/partitions.h>
 #include <linux/io.h>
 #include <linux/platform_data/txx9/ndfmc.h>
diff --git a/include/linux/mtd/sharpsl.h b/include/linux/mtd/sharpsl.h
index 3762a90077d6..231bd1c3f408 100644
--- a/include/linux/mtd/sharpsl.h
+++ b/include/linux/mtd/sharpsl.h
@@ -9,7 +9,6 @@
 #define _MTD_SHARPSL_H
 
 #include <linux/mtd/rawnand.h>
-#include <linux/mtd/nand-ecc-sw-hamming.h>
 #include <linux/mtd/partitions.h>
 
 struct sharpsl_nand_platform_data {
-- 
cgit v1.2.3


From 5180a62c12497aa491a7c79c062a9e3a884c9762 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 30 Sep 2020 01:01:22 +0200
Subject: mtd: nand: ecc-hamming: Let the software Hamming ECC engine be
 unselected

There is no reason to always embed the software Hamming ECC engine
implementation. By default it is (with raw NAND), but we can let the
user decide.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200929230124.31491-19-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/Kconfig                | 11 +++++++++-
 drivers/mtd/nand/raw/Kconfig            |  2 +-
 include/linux/mtd/nand-ecc-sw-hamming.h | 36 +++++++++++++++++++++++++++++++++
 3 files changed, 47 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig
index 306c33ca3448..15ffe1a1b863 100644
--- a/drivers/mtd/nand/Kconfig
+++ b/drivers/mtd/nand/Kconfig
@@ -16,7 +16,16 @@ config MTD_NAND_ECC
        depends on MTD_NAND_CORE
 
 config MTD_NAND_ECC_SW_HAMMING
-	bool
+	bool "Software Hamming ECC engine"
+	default y if MTD_RAW_NAND
+	select MTD_NAND_ECC
+	help
+	  This enables support for software Hamming error
+	  correction. This correction can correct up to 1 bit error
+	  per chunk and detect up to 2 bit errors. While it used to be
+	  widely used with old parts, newer NAND chips usually require
+	  more strength correction and in this case BCH or RS will be
+	  preferred.
 
 config MTD_NAND_ECC_SW_HAMMING_SMC
 	bool "NAND ECC Smart Media byte order"
diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
index 6149096e32cb..cc86d6e4e042 100644
--- a/drivers/mtd/nand/raw/Kconfig
+++ b/drivers/mtd/nand/raw/Kconfig
@@ -3,7 +3,6 @@ menuconfig MTD_RAW_NAND
 	tristate "Raw/Parallel NAND Device Support"
 	select MTD_NAND_CORE
 	select MTD_NAND_ECC
-	select MTD_NAND_ECC_SW_HAMMING
 	help
 	  This enables support for accessing all type of raw/parallel
 	  NAND flash devices. For further information see
@@ -72,6 +71,7 @@ config MTD_NAND_AU1550
 config MTD_NAND_NDFC
 	tristate "IBM/MCC 4xx NAND controller"
 	depends on 4xx
+	select MTD_NAND_ECC_SW_HAMMING
 	select MTD_NAND_ECC_SW_HAMMING_SMC
 	help
 	  NDFC Nand Flash Controllers are integrated in IBM/AMCC's 4xx SoCs
diff --git a/include/linux/mtd/nand-ecc-sw-hamming.h b/include/linux/mtd/nand-ecc-sw-hamming.h
index 9d4b4d623741..5a39e96c3546 100644
--- a/include/linux/mtd/nand-ecc-sw-hamming.h
+++ b/include/linux/mtd/nand-ecc-sw-hamming.h
@@ -32,6 +32,8 @@ struct nand_ecc_sw_hamming_conf {
 	unsigned int sm_order;
 };
 
+#if IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_HAMMING)
+
 int ecc_sw_hamming_calculate(const unsigned char *buf, unsigned int step_size,
 			     unsigned char *code, bool sm_order);
 int nand_ecc_sw_hamming_calculate(struct nand_device *nand,
@@ -44,4 +46,38 @@ int nand_ecc_sw_hamming_correct(struct nand_device *nand, unsigned char *buf,
 				unsigned char *read_ecc,
 				unsigned char *calc_ecc);
 
+#else /* !CONFIG_MTD_NAND_ECC_SW_HAMMING */
+
+static inline int ecc_sw_hamming_calculate(const unsigned char *buf,
+					   unsigned int step_size,
+					   unsigned char *code, bool sm_order)
+{
+	return -ENOTSUPP;
+}
+
+static inline int nand_ecc_sw_hamming_calculate(struct nand_device *nand,
+						const unsigned char *buf,
+						unsigned char *code)
+{
+	return -ENOTSUPP;
+}
+
+static inline int ecc_sw_hamming_correct(unsigned char *buf,
+					 unsigned char *read_ecc,
+					 unsigned char *calc_ecc,
+					 unsigned int step_size, bool sm_order)
+{
+	return -ENOTSUPP;
+}
+
+static inline int nand_ecc_sw_hamming_correct(struct nand_device *nand,
+					      unsigned char *buf,
+					      unsigned char *read_ecc,
+					      unsigned char *calc_ecc)
+{
+	return -ENOTSUPP;
+}
+
+#endif /* CONFIG_MTD_NAND_ECC_SW_HAMMING */
+
 #endif /* __MTD_NAND_ECC_SW_HAMMING_H__ */
-- 
cgit v1.2.3


From 35fe1b98a0082ad3f576bcc420c74dab435da307 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 30 Sep 2020 01:01:23 +0200
Subject: mtd: nand: ecc-hamming: Create the software Hamming engine

Let's continue introducing the generic ECC engine abstraction in the
NAND subsystem by instantiating a second ECC engine: software
Hamming.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200929230124.31491-20-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/ecc-sw-hamming.c       | 193 ++++++++++++++++++++++++++++++++
 drivers/mtd/nand/raw/nand_base.c        |  26 ++---
 include/linux/mtd/nand-ecc-sw-hamming.h |  16 ++-
 include/linux/mtd/nand.h                |   9 ++
 4 files changed, 223 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/ecc-sw-hamming.c b/drivers/mtd/nand/ecc-sw-hamming.c
index 9cd70b4637c1..c95aadf1eb43 100644
--- a/drivers/mtd/nand/ecc-sw-hamming.c
+++ b/drivers/mtd/nand/ecc-sw-hamming.c
@@ -17,7 +17,9 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/mtd/nand.h>
 #include <linux/mtd/nand-ecc-sw-hamming.h>
+#include <linux/slab.h>
 #include <asm/byteorder.h>
 
 /*
@@ -460,6 +462,197 @@ int nand_ecc_sw_hamming_correct(struct nand_device *nand, unsigned char *buf,
 }
 EXPORT_SYMBOL(nand_ecc_sw_hamming_correct);
 
+int nand_ecc_sw_hamming_init_ctx(struct nand_device *nand)
+{
+	struct nand_ecc_props *conf = &nand->ecc.ctx.conf;
+	struct nand_ecc_sw_hamming_conf *engine_conf;
+	struct mtd_info *mtd = nanddev_to_mtd(nand);
+	int ret;
+
+	if (!mtd->ooblayout) {
+		switch (mtd->oobsize) {
+		case 8:
+		case 16:
+			mtd_set_ooblayout(mtd, nand_get_small_page_ooblayout());
+			break;
+		case 64:
+		case 128:
+			mtd_set_ooblayout(mtd,
+					  nand_get_large_page_hamming_ooblayout());
+			break;
+		default:
+			return -ENOTSUPP;
+		}
+	}
+
+	conf->engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
+	conf->algo = NAND_ECC_ALGO_HAMMING;
+	conf->step_size = nand->ecc.user_conf.step_size;
+	conf->strength = 1;
+
+	/* Use the strongest configuration by default */
+	if (conf->step_size != 256 && conf->step_size != 512)
+		conf->step_size = 256;
+
+	engine_conf = kzalloc(sizeof(*engine_conf), GFP_KERNEL);
+	if (!engine_conf)
+		return -ENOMEM;
+
+	ret = nand_ecc_init_req_tweaking(&engine_conf->req_ctx, nand);
+	if (ret)
+		goto free_engine_conf;
+
+	engine_conf->code_size = 3;
+	engine_conf->nsteps = mtd->writesize / conf->step_size;
+	engine_conf->calc_buf = kzalloc(mtd->oobsize, GFP_KERNEL);
+	engine_conf->code_buf = kzalloc(mtd->oobsize, GFP_KERNEL);
+	if (!engine_conf->calc_buf || !engine_conf->code_buf) {
+		ret = -ENOMEM;
+		goto free_bufs;
+	}
+
+	nand->ecc.ctx.priv = engine_conf;
+	nand->ecc.ctx.total = engine_conf->nsteps * engine_conf->code_size;
+
+	return 0;
+
+free_bufs:
+	nand_ecc_cleanup_req_tweaking(&engine_conf->req_ctx);
+	kfree(engine_conf->calc_buf);
+	kfree(engine_conf->code_buf);
+free_engine_conf:
+	kfree(engine_conf);
+
+	return ret;
+}
+EXPORT_SYMBOL(nand_ecc_sw_hamming_init_ctx);
+
+void nand_ecc_sw_hamming_cleanup_ctx(struct nand_device *nand)
+{
+	struct nand_ecc_sw_hamming_conf *engine_conf = nand->ecc.ctx.priv;
+
+	if (engine_conf) {
+		nand_ecc_cleanup_req_tweaking(&engine_conf->req_ctx);
+		kfree(engine_conf->calc_buf);
+		kfree(engine_conf->code_buf);
+		kfree(engine_conf);
+	}
+}
+EXPORT_SYMBOL(nand_ecc_sw_hamming_cleanup_ctx);
+
+static int nand_ecc_sw_hamming_prepare_io_req(struct nand_device *nand,
+					      struct nand_page_io_req *req)
+{
+	struct nand_ecc_sw_hamming_conf *engine_conf = nand->ecc.ctx.priv;
+	struct mtd_info *mtd = nanddev_to_mtd(nand);
+	int eccsize = nand->ecc.ctx.conf.step_size;
+	int eccbytes = engine_conf->code_size;
+	int eccsteps = engine_conf->nsteps;
+	int total = nand->ecc.ctx.total;
+	u8 *ecccalc = engine_conf->calc_buf;
+	const u8 *data;
+	int i;
+
+	/* Nothing to do for a raw operation */
+	if (req->mode == MTD_OPS_RAW)
+		return 0;
+
+	/* This engine does not provide BBM/free OOB bytes protection */
+	if (!req->datalen)
+		return 0;
+
+	nand_ecc_tweak_req(&engine_conf->req_ctx, req);
+
+	/* No more preparation for page read */
+	if (req->type == NAND_PAGE_READ)
+		return 0;
+
+	/* Preparation for page write: derive the ECC bytes and place them */
+	for (i = 0, data = req->databuf.out;
+	     eccsteps;
+	     eccsteps--, i += eccbytes, data += eccsize)
+		nand_ecc_sw_hamming_calculate(nand, data, &ecccalc[i]);
+
+	return mtd_ooblayout_set_eccbytes(mtd, ecccalc, (void *)req->oobbuf.out,
+					  0, total);
+}
+
+static int nand_ecc_sw_hamming_finish_io_req(struct nand_device *nand,
+					     struct nand_page_io_req *req)
+{
+	struct nand_ecc_sw_hamming_conf *engine_conf = nand->ecc.ctx.priv;
+	struct mtd_info *mtd = nanddev_to_mtd(nand);
+	int eccsize = nand->ecc.ctx.conf.step_size;
+	int total = nand->ecc.ctx.total;
+	int eccbytes = engine_conf->code_size;
+	int eccsteps = engine_conf->nsteps;
+	u8 *ecccalc = engine_conf->calc_buf;
+	u8 *ecccode = engine_conf->code_buf;
+	unsigned int max_bitflips = 0;
+	u8 *data = req->databuf.in;
+	int i, ret;
+
+	/* Nothing to do for a raw operation */
+	if (req->mode == MTD_OPS_RAW)
+		return 0;
+
+	/* This engine does not provide BBM/free OOB bytes protection */
+	if (!req->datalen)
+		return 0;
+
+	/* No more preparation for page write */
+	if (req->type == NAND_PAGE_WRITE) {
+		nand_ecc_restore_req(&engine_conf->req_ctx, req);
+		return 0;
+	}
+
+	/* Finish a page read: retrieve the (raw) ECC bytes*/
+	ret = mtd_ooblayout_get_eccbytes(mtd, ecccode, req->oobbuf.in, 0,
+					 total);
+	if (ret)
+		return ret;
+
+	/* Calculate the ECC bytes */
+	for (i = 0; eccsteps; eccsteps--, i += eccbytes, data += eccsize)
+		nand_ecc_sw_hamming_calculate(nand, data, &ecccalc[i]);
+
+	/* Finish a page read: compare and correct */
+	for (eccsteps = engine_conf->nsteps, i = 0, data = req->databuf.in;
+	     eccsteps;
+	     eccsteps--, i += eccbytes, data += eccsize) {
+		int stat =  nand_ecc_sw_hamming_correct(nand, data,
+							&ecccode[i],
+							&ecccalc[i]);
+		if (stat < 0) {
+			mtd->ecc_stats.failed++;
+		} else {
+			mtd->ecc_stats.corrected += stat;
+			max_bitflips = max_t(unsigned int, max_bitflips, stat);
+		}
+	}
+
+	nand_ecc_restore_req(&engine_conf->req_ctx, req);
+
+	return max_bitflips;
+}
+
+static struct nand_ecc_engine_ops nand_ecc_sw_hamming_engine_ops = {
+	.init_ctx = nand_ecc_sw_hamming_init_ctx,
+	.cleanup_ctx = nand_ecc_sw_hamming_cleanup_ctx,
+	.prepare_io_req = nand_ecc_sw_hamming_prepare_io_req,
+	.finish_io_req = nand_ecc_sw_hamming_finish_io_req,
+};
+
+static struct nand_ecc_engine nand_ecc_sw_hamming_engine = {
+	.ops = &nand_ecc_sw_hamming_engine_ops,
+};
+
+struct nand_ecc_engine *nand_ecc_sw_hamming_get_engine(void)
+{
+	return &nand_ecc_sw_hamming_engine;
+}
+EXPORT_SYMBOL(nand_ecc_sw_hamming_get_engine);
+
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Frans Meulenbroeks <fransmeulenbroeks@gmail.com>");
 MODULE_DESCRIPTION("NAND software Hamming ECC support");
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index c36d2d4a72d5..c33fa1b1847f 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -5141,34 +5141,24 @@ static void nand_scan_ident_cleanup(struct nand_chip *chip)
 
 int rawnand_sw_hamming_init(struct nand_chip *chip)
 {
-	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct nand_ecc_sw_hamming_conf *engine_conf;
 	struct nand_device *base = &chip->base;
+	int ret;
 
 	base->ecc.user_conf.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 	base->ecc.user_conf.algo = NAND_ECC_ALGO_HAMMING;
 	base->ecc.user_conf.strength = chip->ecc.strength;
 	base->ecc.user_conf.step_size = chip->ecc.size;
 
-	if (base->ecc.user_conf.strength != 1 ||
-	    (base->ecc.user_conf.step_size != 256 &&
-	     base->ecc.user_conf.step_size != 512)) {
-		pr_err("%s: unsupported strength or step size\n", __func__);
-		return -EINVAL;
-	}
-
-	engine_conf = kzalloc(sizeof(*engine_conf), GFP_KERNEL);
-	if (!engine_conf)
-		return -ENOMEM;
+	ret = nand_ecc_sw_hamming_init_ctx(base);
+	if (ret)
+		return ret;
 
-	engine_conf->code_size = 3;
-	engine_conf->nsteps = mtd->writesize / base->ecc.user_conf.step_size;
+	engine_conf = base->ecc.ctx.priv;
 
 	if (chip->ecc.options & NAND_ECC_SOFT_HAMMING_SM_ORDER)
 		engine_conf->sm_order = true;
 
-	base->ecc.ctx.priv = engine_conf;
-
 	chip->ecc.size = base->ecc.ctx.conf.step_size;
 	chip->ecc.strength = base->ecc.ctx.conf.strength;
 	chip->ecc.total = base->ecc.ctx.total;
@@ -5204,7 +5194,7 @@ void rawnand_sw_hamming_cleanup(struct nand_chip *chip)
 {
 	struct nand_device *base = &chip->base;
 
-	kfree(base->ecc.ctx.priv);
+	nand_ecc_sw_hamming_cleanup_ctx(base);
 }
 EXPORT_SYMBOL(rawnand_sw_hamming_cleanup);
 
@@ -5733,7 +5723,9 @@ static int nand_scan_tail(struct nand_chip *chip)
 	 */
 	if (!mtd->ooblayout &&
 	    !(ecc->engine_type == NAND_ECC_ENGINE_TYPE_SOFT &&
-	      ecc->algo == NAND_ECC_ALGO_BCH)) {
+	      ecc->algo == NAND_ECC_ALGO_BCH) &&
+	    !(ecc->engine_type == NAND_ECC_ENGINE_TYPE_SOFT &&
+	      ecc->algo == NAND_ECC_ALGO_HAMMING)) {
 		switch (mtd->oobsize) {
 		case 8:
 		case 16:
diff --git a/include/linux/mtd/nand-ecc-sw-hamming.h b/include/linux/mtd/nand-ecc-sw-hamming.h
index 5a39e96c3546..9f9073d86ff3 100644
--- a/include/linux/mtd/nand-ecc-sw-hamming.h
+++ b/include/linux/mtd/nand-ecc-sw-hamming.h
@@ -14,8 +14,8 @@
 
 /**
  * struct nand_ecc_sw_hamming_conf - private software Hamming ECC engine structure
- * @reqooblen: Save the actual user OOB length requested before overwriting it
- * @spare_oobbuf: Spare OOB buffer if none is provided
+ * @req_ctx: Save request context and tweak the original request to fit the
+ *           engine needs
  * @code_size: Number of bytes needed to store a code (one code per step)
  * @nsteps: Number of steps
  * @calc_buf: Buffer to use when calculating ECC bytes
@@ -23,8 +23,7 @@
  * @sm_order: Smart Media special ordering
  */
 struct nand_ecc_sw_hamming_conf {
-	unsigned int reqooblen;
-	void *spare_oobbuf;
+	struct nand_ecc_req_tweak_ctx req_ctx;
 	unsigned int code_size;
 	unsigned int nsteps;
 	u8 *calc_buf;
@@ -34,6 +33,8 @@ struct nand_ecc_sw_hamming_conf {
 
 #if IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_HAMMING)
 
+int nand_ecc_sw_hamming_init_ctx(struct nand_device *nand);
+void nand_ecc_sw_hamming_cleanup_ctx(struct nand_device *nand);
 int ecc_sw_hamming_calculate(const unsigned char *buf, unsigned int step_size,
 			     unsigned char *code, bool sm_order);
 int nand_ecc_sw_hamming_calculate(struct nand_device *nand,
@@ -48,6 +49,13 @@ int nand_ecc_sw_hamming_correct(struct nand_device *nand, unsigned char *buf,
 
 #else /* !CONFIG_MTD_NAND_ECC_SW_HAMMING */
 
+static inline int nand_ecc_sw_hamming_init_ctx(struct nand_device *nand)
+{
+	return -ENOTSUPP;
+}
+
+static inline void nand_ecc_sw_hamming_cleanup_ctx(struct nand_device *nand) {}
+
 static inline int ecc_sw_hamming_calculate(const unsigned char *buf,
 					   unsigned int step_size,
 					   unsigned char *code, bool sm_order)
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index df8548187713..3616fa27eaa1 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -278,6 +278,15 @@ int nand_ecc_finish_io_req(struct nand_device *nand,
 			   struct nand_page_io_req *req);
 bool nand_ecc_is_strong_enough(struct nand_device *nand);
 
+#if IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_HAMMING)
+struct nand_ecc_engine *nand_ecc_sw_hamming_get_engine(void);
+#else
+static inline struct nand_ecc_engine *nand_ecc_sw_hamming_get_engine(void)
+{
+	return NULL;
+}
+#endif /* CONFIG_MTD_NAND_ECC_SW_HAMMING */
+
 #if IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_BCH)
 struct nand_ecc_engine *nand_ecc_sw_bch_get_engine(void);
 #else
-- 
cgit v1.2.3


From 53fbdeeb57a0168a88547e22f8d433810c531169 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 30 Sep 2020 01:01:24 +0200
Subject: mtd: nand: Let software ECC engines be retrieved from the NAND core

Before making use of the ECC engines, we must retrieve them. Add the
boilerplate for the ones already available: software engines (Hamming
and BCH).

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200929230124.31491-21-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/ecc.c   | 20 ++++++++++++++++++++
 include/linux/mtd/nand.h |  1 +
 2 files changed, 21 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/ecc.c b/drivers/mtd/nand/ecc.c
index 541137736fd3..57bc8c5ef08c 100644
--- a/drivers/mtd/nand/ecc.c
+++ b/drivers/mtd/nand/ecc.c
@@ -585,6 +585,26 @@ void nand_ecc_restore_req(struct nand_ecc_req_tweak_ctx *ctx,
 }
 EXPORT_SYMBOL_GPL(nand_ecc_restore_req);
 
+struct nand_ecc_engine *nand_ecc_get_sw_engine(struct nand_device *nand)
+{
+	unsigned int algo = nand->ecc.user_conf.algo;
+
+	if (algo == NAND_ECC_ALGO_UNKNOWN)
+		algo = nand->ecc.defaults.algo;
+
+	switch (algo) {
+	case NAND_ECC_ALGO_HAMMING:
+		return nand_ecc_sw_hamming_get_engine();
+	case NAND_ECC_ALGO_BCH:
+		return nand_ecc_sw_bch_get_engine();
+	default:
+		break;
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL(nand_ecc_get_sw_engine);
+
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Miquel Raynal <miquel.raynal@bootlin.com>");
 MODULE_DESCRIPTION("Generic ECC engine");
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 3616fa27eaa1..f78f61c9a9ee 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -277,6 +277,7 @@ int nand_ecc_prepare_io_req(struct nand_device *nand,
 int nand_ecc_finish_io_req(struct nand_device *nand,
 			   struct nand_page_io_req *req);
 bool nand_ecc_is_strong_enough(struct nand_device *nand);
+struct nand_ecc_engine *nand_ecc_get_sw_engine(struct nand_device *nand);
 
 #if IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_HAMMING)
 struct nand_ecc_engine *nand_ecc_sw_hamming_get_engine(void);
-- 
cgit v1.2.3


From 945845b54c9cf61809d1963492bb728ce8937964 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 30 Sep 2020 17:41:07 +0200
Subject: mtd: spinand: Instantiate a SPI-NAND on-die ECC engine

Make use of the existing functions taken from the SPI-NAND core to
instantiate an on-die ECC engine specific to the SPI-NAND core. The
next step will be to tweak the core to use this object instead of
calling the helpers directly.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200930154109.3922-4-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/spi/core.c | 67 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/mtd/spinand.h |  9 ++++++
 2 files changed, 76 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c
index b2830e19a7f6..069ebf85dd3f 100644
--- a/drivers/mtd/nand/spi/core.c
+++ b/drivers/mtd/nand/spi/core.c
@@ -246,6 +246,73 @@ static const struct mtd_ooblayout_ops spinand_noecc_ooblayout = {
 	.free = spinand_noecc_ooblayout_free,
 };
 
+static int spinand_ondie_ecc_init_ctx(struct nand_device *nand)
+{
+	struct spinand_device *spinand = nand_to_spinand(nand);
+	struct mtd_info *mtd = nanddev_to_mtd(nand);
+	struct spinand_ondie_ecc_conf *engine_conf;
+
+	nand->ecc.ctx.conf.engine_type = NAND_ECC_ENGINE_TYPE_ON_DIE;
+	nand->ecc.ctx.conf.step_size = nand->ecc.requirements.step_size;
+	nand->ecc.ctx.conf.strength = nand->ecc.requirements.strength;
+
+	engine_conf = kzalloc(sizeof(*engine_conf), GFP_KERNEL);
+	if (!engine_conf)
+		return -ENOMEM;
+
+	nand->ecc.ctx.priv = engine_conf;
+
+	if (spinand->eccinfo.ooblayout)
+		mtd_set_ooblayout(mtd, spinand->eccinfo.ooblayout);
+	else
+		mtd_set_ooblayout(mtd, &spinand_noecc_ooblayout);
+
+	return 0;
+}
+
+static void spinand_ondie_ecc_cleanup_ctx(struct nand_device *nand)
+{
+	kfree(nand->ecc.ctx.priv);
+}
+
+static int spinand_ondie_ecc_prepare_io_req(struct nand_device *nand,
+					    struct nand_page_io_req *req)
+{
+	struct spinand_device *spinand = nand_to_spinand(nand);
+	bool enable = (req->mode != MTD_OPS_RAW);
+
+	/* Only enable or disable the engine */
+	return spinand_ecc_enable(spinand, enable);
+}
+
+static int spinand_ondie_ecc_finish_io_req(struct nand_device *nand,
+					   struct nand_page_io_req *req)
+{
+	struct spinand_ondie_ecc_conf *engine_conf = nand->ecc.ctx.priv;
+	struct spinand_device *spinand = nand_to_spinand(nand);
+
+	if (req->mode == MTD_OPS_RAW)
+		return 0;
+
+	/* Nothing to do when finishing a page write */
+	if (req->type == NAND_PAGE_WRITE)
+		return 0;
+
+	/* Finish a page write: check the status, report errors/bitflips */
+	return spinand_check_ecc_status(spinand, engine_conf->status);
+}
+
+static struct nand_ecc_engine_ops spinand_ondie_ecc_engine_ops = {
+	.init_ctx = spinand_ondie_ecc_init_ctx,
+	.cleanup_ctx = spinand_ondie_ecc_cleanup_ctx,
+	.prepare_io_req = spinand_ondie_ecc_prepare_io_req,
+	.finish_io_req = spinand_ondie_ecc_finish_io_req,
+};
+
+static __maybe_unused struct nand_ecc_engine spinand_ondie_ecc_engine = {
+	.ops = &spinand_ondie_ecc_engine_ops,
+};
+
 static int spinand_write_enable_op(struct spinand_device *spinand)
 {
 	struct spi_mem_op op = SPINAND_WR_EN_DIS_OP(true);
diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h
index 7b78c4ba9b3e..6bb92f26833e 100644
--- a/include/linux/mtd/spinand.h
+++ b/include/linux/mtd/spinand.h
@@ -286,6 +286,15 @@ struct spinand_ecc_info {
 #define SPINAND_HAS_QE_BIT		BIT(0)
 #define SPINAND_HAS_CR_FEAT_BIT		BIT(1)
 
+/**
+ * struct spinand_ondie_ecc_conf - private SPI-NAND on-die ECC engine structure
+ * @status: status of the last wait operation that will be used in case
+ *          ->get_status() is not populated by the spinand device.
+ */
+struct spinand_ondie_ecc_conf {
+	u8 status;
+};
+
 /**
  * struct spinand_info - Structure used to describe SPI NAND chips
  * @model: model name
-- 
cgit v1.2.3


From da429b9615803b6f19e5734c4c4d99136e1e3bfd Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 30 Sep 2020 17:41:08 +0200
Subject: mtd: nand: Let on-die ECC engines be retrieved from the NAND core

Before making use of the ECC engines, we must retrieve them. Add the
necessary boilerplate.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200930154109.3922-5-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/ecc.c   | 6 ++++++
 include/linux/mtd/nand.h | 1 +
 2 files changed, 7 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/ecc.c b/drivers/mtd/nand/ecc.c
index 57bc8c5ef08c..9afdde70824a 100644
--- a/drivers/mtd/nand/ecc.c
+++ b/drivers/mtd/nand/ecc.c
@@ -605,6 +605,12 @@ struct nand_ecc_engine *nand_ecc_get_sw_engine(struct nand_device *nand)
 }
 EXPORT_SYMBOL(nand_ecc_get_sw_engine);
 
+struct nand_ecc_engine *nand_ecc_get_on_die_hw_engine(struct nand_device *nand)
+{
+	return nand->ecc.ondie_engine;
+}
+EXPORT_SYMBOL(nand_ecc_get_on_die_hw_engine);
+
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Miquel Raynal <miquel.raynal@bootlin.com>");
 MODULE_DESCRIPTION("Generic ECC engine");
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index f78f61c9a9ee..6c6f91c03c42 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -278,6 +278,7 @@ int nand_ecc_finish_io_req(struct nand_device *nand,
 			   struct nand_page_io_req *req);
 bool nand_ecc_is_strong_enough(struct nand_device *nand);
 struct nand_ecc_engine *nand_ecc_get_sw_engine(struct nand_device *nand);
+struct nand_ecc_engine *nand_ecc_get_on_die_hw_engine(struct nand_device *nand);
 
 #if IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_HAMMING)
 struct nand_ecc_engine *nand_ecc_sw_hamming_get_engine(void);
-- 
cgit v1.2.3


From 6b0c3b84156125e029956e46d2b44e72f513a9fa Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Thu, 1 Oct 2020 12:20:09 +0200
Subject: mtd: nand: Add helpers to manage ECC engines and configurations

Add the logic in the NAND core to find the right ECC engine depending
on the NAND chip requirements and the user desires. Right now, the
choice may be made between (more will come):
* software Hamming
* software BCH
* on-die (SPI-NAND devices only)

Once the ECC engine has been found, the ECC engine must be
configured.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20201001102014.20100-2-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/core.c  | 124 +++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/mtd/nand.h |   4 ++
 2 files changed, 128 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/core.c b/drivers/mtd/nand/core.c
index b6de955ac8bf..5e13a03d2b32 100644
--- a/drivers/mtd/nand/core.c
+++ b/drivers/mtd/nand/core.c
@@ -207,6 +207,130 @@ int nanddev_mtd_max_bad_blocks(struct mtd_info *mtd, loff_t offs, size_t len)
 }
 EXPORT_SYMBOL_GPL(nanddev_mtd_max_bad_blocks);
 
+/**
+ * nanddev_get_ecc_engine() - Find and get a suitable ECC engine
+ * @nand: NAND device
+ */
+static int nanddev_get_ecc_engine(struct nand_device *nand)
+{
+	int engine_type;
+
+	/* Read the user desires in terms of ECC engine/configuration */
+	of_get_nand_ecc_user_config(nand);
+
+	engine_type = nand->ecc.user_conf.engine_type;
+	if (engine_type == NAND_ECC_ENGINE_TYPE_INVALID)
+		engine_type = nand->ecc.defaults.engine_type;
+
+	switch (engine_type) {
+	case NAND_ECC_ENGINE_TYPE_NONE:
+		return 0;
+	case NAND_ECC_ENGINE_TYPE_SOFT:
+		nand->ecc.engine = nand_ecc_get_sw_engine(nand);
+		break;
+	case NAND_ECC_ENGINE_TYPE_ON_DIE:
+		nand->ecc.engine = nand_ecc_get_on_die_hw_engine(nand);
+		break;
+	case NAND_ECC_ENGINE_TYPE_ON_HOST:
+		pr_err("On-host hardware ECC engines not supported yet\n");
+		break;
+	default:
+		pr_err("Missing ECC engine type\n");
+	}
+
+	if (!nand->ecc.engine)
+		return  -EINVAL;
+
+	return 0;
+}
+
+/**
+ * nanddev_put_ecc_engine() - Dettach and put the in-use ECC engine
+ * @nand: NAND device
+ */
+static int nanddev_put_ecc_engine(struct nand_device *nand)
+{
+	switch (nand->ecc.ctx.conf.engine_type) {
+	case NAND_ECC_ENGINE_TYPE_ON_HOST:
+		pr_err("On-host hardware ECC engines not supported yet\n");
+		break;
+	case NAND_ECC_ENGINE_TYPE_NONE:
+	case NAND_ECC_ENGINE_TYPE_SOFT:
+	case NAND_ECC_ENGINE_TYPE_ON_DIE:
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+/**
+ * nanddev_find_ecc_configuration() - Find a suitable ECC configuration
+ * @nand: NAND device
+ */
+static int nanddev_find_ecc_configuration(struct nand_device *nand)
+{
+	int ret;
+
+	if (!nand->ecc.engine)
+		return -ENOTSUPP;
+
+	ret = nand_ecc_init_ctx(nand);
+	if (ret)
+		return ret;
+
+	if (!nand_ecc_is_strong_enough(nand))
+		pr_warn("WARNING: %s: the ECC used on your system is too weak compared to the one required by the NAND chip\n",
+			nand->mtd.name);
+
+	return 0;
+}
+
+/**
+ * nanddev_ecc_engine_init() - Initialize an ECC engine for the chip
+ * @nand: NAND device
+ */
+int nanddev_ecc_engine_init(struct nand_device *nand)
+{
+	int ret;
+
+	/* Look for the ECC engine to use */
+	ret = nanddev_get_ecc_engine(nand);
+	if (ret) {
+		pr_err("No ECC engine found\n");
+		return ret;
+	}
+
+	/* No ECC engine requested */
+	if (!nand->ecc.engine)
+		return 0;
+
+	/* Configure the engine: balance user input and chip requirements */
+	ret = nanddev_find_ecc_configuration(nand);
+	if (ret) {
+		pr_err("No suitable ECC configuration\n");
+		nanddev_put_ecc_engine(nand);
+
+		return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nanddev_ecc_engine_init);
+
+/**
+ * nanddev_ecc_engine_cleanup() - Cleanup ECC engine initializations
+ * @nand: NAND device
+ */
+void nanddev_ecc_engine_cleanup(struct nand_device *nand)
+{
+	if (nand->ecc.engine)
+		nand_ecc_cleanup_ctx(nand);
+
+	nanddev_put_ecc_engine(nand);
+}
+EXPORT_SYMBOL_GPL(nanddev_ecc_engine_cleanup);
+
 /**
  * nanddev_init() - Initialize a NAND device
  * @nand: NAND device
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 6c6f91c03c42..414f8a4d2853 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -936,6 +936,10 @@ bool nanddev_isreserved(struct nand_device *nand, const struct nand_pos *pos);
 int nanddev_erase(struct nand_device *nand, const struct nand_pos *pos);
 int nanddev_markbad(struct nand_device *nand, const struct nand_pos *pos);
 
+/* ECC related functions */
+int nanddev_ecc_engine_init(struct nand_device *nand);
+void nanddev_ecc_engine_cleanup(struct nand_device *nand);
+
 /* BBT related functions */
 enum nand_bbt_block_status {
 	NAND_BBT_BLOCK_STATUS_UNKNOWN,
-- 
cgit v1.2.3


From 7998d89875177a5fac9f963e230dbb828c218cb9 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Fri, 23 Oct 2020 18:33:04 +0200
Subject: mtd: rawnand: fix a kernel-doc markup

Some identifiers have different names between their prototypes
and the kernel-doc markup.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/9ed47a57d12c40e73a9b01612ee119d39baa6236.1603469755.git.mchehab+huawei@kernel.org
---
 drivers/mtd/nand/raw/nand_bbt.c | 2 +-
 include/linux/mtd/rawnand.h     | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/raw/nand_bbt.c b/drivers/mtd/nand/raw/nand_bbt.c
index 344a24fd2ca8..dced32a126d9 100644
--- a/drivers/mtd/nand/raw/nand_bbt.c
+++ b/drivers/mtd/nand/raw/nand_bbt.c
@@ -1087,7 +1087,7 @@ static int nand_update_bbt(struct nand_chip *this, loff_t offs)
 }
 
 /**
- * mark_bbt_regions - [GENERIC] mark the bad block table regions
+ * mark_bbt_region - [GENERIC] mark the bad block table regions
  * @this: the NAND device
  * @td: bad block table descriptor
  *
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 0a90a8792d18..6b3240e44310 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -1284,7 +1284,8 @@ static inline bool nand_is_slc(struct nand_chip *chip)
 }
 
 /**
- * Check if the opcode's address should be sent only on the lower 8 bits
+ * nand_opcode_8bits - Check if the opcode's address should be sent only on the
+ *	lower 8 bits
  * @command: opcode to check
  */
 static inline int nand_opcode_8bits(unsigned int command)
-- 
cgit v1.2.3


From 0f6b791955a6365b5ebe8b6a5b01de69a47ee92e Mon Sep 17 00:00:00 2001
From: Fabio Estevam <festevam@gmail.com>
Date: Tue, 10 Nov 2020 09:19:08 -0300
Subject: mtd: rawnand: mxc: Remove platform data support

i.MX is a devicetree-only platform now and the existing platform data
support in this driver was only useful for old non-devicetree platforms.

Get rid of the platform data support since it is no longer used.

Signed-off-by: Fabio Estevam <festevam@gmail.com>
Reviewed-by: Sascha Hauer <s.hauer@pengutronix.de>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20201110121908.19400-1-festevam@gmail.com
---
 drivers/mtd/nand/raw/Kconfig               |  2 +-
 drivers/mtd/nand/raw/mxc_nand.c            | 75 ++----------------------------
 include/linux/platform_data/mtd-mxc_nand.h | 19 --------
 3 files changed, 5 insertions(+), 91 deletions(-)
 delete mode 100644 include/linux/platform_data/mtd-mxc_nand.h

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
index cc86d6e4e042..b93e6cd23259 100644
--- a/drivers/mtd/nand/raw/Kconfig
+++ b/drivers/mtd/nand/raw/Kconfig
@@ -292,7 +292,7 @@ config MTD_NAND_VF610_NFC
 config MTD_NAND_MXC
 	tristate "Freescale MXC NAND controller"
 	depends on ARCH_MXC || COMPILE_TEST
-	depends on HAS_IOMEM
+	depends on HAS_IOMEM && OF
 	help
 	  This enables the driver for the NAND flash controller on the
 	  MXC processors.
diff --git a/drivers/mtd/nand/raw/mxc_nand.c b/drivers/mtd/nand/raw/mxc_nand.c
index 684c51e5e60d..f896364968d8 100644
--- a/drivers/mtd/nand/raw/mxc_nand.c
+++ b/drivers/mtd/nand/raw/mxc_nand.c
@@ -21,7 +21,6 @@
 #include <linux/completion.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
-#include <linux/platform_data/mtd-mxc_nand.h>
 
 #define DRIVER_NAME "mxc_nand"
 
@@ -184,7 +183,6 @@ struct mxc_nand_host {
 	unsigned int		buf_start;
 
 	const struct mxc_nand_devtype_data *devtype_data;
-	struct mxc_nand_platform_data pdata;
 };
 
 static const char * const part_probes[] = {
@@ -1611,29 +1609,6 @@ static inline int is_imx53_nfc(struct mxc_nand_host *host)
 	return host->devtype_data == &imx53_nand_devtype_data;
 }
 
-static const struct platform_device_id mxcnd_devtype[] = {
-	{
-		.name = "imx21-nand",
-		.driver_data = (kernel_ulong_t) &imx21_nand_devtype_data,
-	}, {
-		.name = "imx27-nand",
-		.driver_data = (kernel_ulong_t) &imx27_nand_devtype_data,
-	}, {
-		.name = "imx25-nand",
-		.driver_data = (kernel_ulong_t) &imx25_nand_devtype_data,
-	}, {
-		.name = "imx51-nand",
-		.driver_data = (kernel_ulong_t) &imx51_nand_devtype_data,
-	}, {
-		.name = "imx53-nand",
-		.driver_data = (kernel_ulong_t) &imx53_nand_devtype_data,
-	}, {
-		/* sentinel */
-	}
-};
-MODULE_DEVICE_TABLE(platform, mxcnd_devtype);
-
-#ifdef CONFIG_OF
 static const struct of_device_id mxcnd_dt_ids[] = {
 	{
 		.compatible = "fsl,imx21-nand",
@@ -1655,26 +1630,6 @@ static const struct of_device_id mxcnd_dt_ids[] = {
 };
 MODULE_DEVICE_TABLE(of, mxcnd_dt_ids);
 
-static int mxcnd_probe_dt(struct mxc_nand_host *host)
-{
-	struct device_node *np = host->dev->of_node;
-	const struct of_device_id *of_id =
-		of_match_device(mxcnd_dt_ids, host->dev);
-
-	if (!np)
-		return 1;
-
-	host->devtype_data = of_id->data;
-
-	return 0;
-}
-#else
-static int mxcnd_probe_dt(struct mxc_nand_host *host)
-{
-	return 1;
-}
-#endif
-
 static int mxcnd_attach_chip(struct nand_chip *chip)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
@@ -1759,6 +1714,7 @@ static const struct nand_controller_ops mxcnd_controller_ops = {
 
 static int mxcnd_probe(struct platform_device *pdev)
 {
+	const struct of_device_id *of_id;
 	struct nand_chip *this;
 	struct mtd_info *mtd;
 	struct mxc_nand_host *host;
@@ -1800,20 +1756,8 @@ static int mxcnd_probe(struct platform_device *pdev)
 	if (IS_ERR(host->clk))
 		return PTR_ERR(host->clk);
 
-	err = mxcnd_probe_dt(host);
-	if (err > 0) {
-		struct mxc_nand_platform_data *pdata =
-					dev_get_platdata(&pdev->dev);
-		if (pdata) {
-			host->pdata = *pdata;
-			host->devtype_data = (struct mxc_nand_devtype_data *)
-						pdev->id_entry->driver_data;
-		} else {
-			err = -ENODEV;
-		}
-	}
-	if (err < 0)
-		return err;
+	of_id = of_match_device(mxcnd_dt_ids, host->dev);
+	host->devtype_data = of_id->data;
 
 	if (!host->devtype_data->setup_interface)
 		this->options |= NAND_KEEP_TIMINGS;
@@ -1843,14 +1787,6 @@ static int mxcnd_probe(struct platform_device *pdev)
 
 	this->legacy.select_chip = host->devtype_data->select_chip;
 
-	/* NAND bus width determines access functions used by upper layer */
-	if (host->pdata.width == 2)
-		this->options |= NAND_BUSWIDTH_16;
-
-	/* update flash based bbt */
-	if (host->pdata.flash_bbt)
-		this->bbt_options |= NAND_BBT_USE_FLASH;
-
 	init_completion(&host->op_completion);
 
 	host->irq = platform_get_irq(pdev, 0);
@@ -1891,9 +1827,7 @@ static int mxcnd_probe(struct platform_device *pdev)
 		goto escan;
 
 	/* Register the partitions */
-	err = mtd_device_parse_register(mtd, part_probes, NULL,
-					host->pdata.parts,
-					host->pdata.nr_parts);
+	err = mtd_device_parse_register(mtd, part_probes, NULL, NULL, 0);
 	if (err)
 		goto cleanup_nand;
 
@@ -1930,7 +1864,6 @@ static struct platform_driver mxcnd_driver = {
 		   .name = DRIVER_NAME,
 		   .of_match_table = of_match_ptr(mxcnd_dt_ids),
 	},
-	.id_table = mxcnd_devtype,
 	.probe = mxcnd_probe,
 	.remove = mxcnd_remove,
 };
diff --git a/include/linux/platform_data/mtd-mxc_nand.h b/include/linux/platform_data/mtd-mxc_nand.h
deleted file mode 100644
index d1230030c6db..000000000000
--- a/include/linux/platform_data/mtd-mxc_nand.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Copyright 2004-2007 Freescale Semiconductor, Inc. All Rights Reserved.
- * Copyright 2008 Sascha Hauer, kernel@pengutronix.de
- */
-
-#ifndef __ASM_ARCH_NAND_H
-#define __ASM_ARCH_NAND_H
-
-#include <linux/mtd/partitions.h>
-
-struct mxc_nand_platform_data {
-	unsigned int width;	/* data bus width in bytes */
-	unsigned int hw_ecc:1;	/* 0 if suppress hardware ECC */
-	unsigned int flash_bbt:1; /* set to 1 to use a flash based bbt */
-	struct mtd_partition *parts;	/* partition table */
-	int nr_parts;			/* size of parts */
-};
-#endif /* __ASM_ARCH_NAND_H */
-- 
cgit v1.2.3


From bdfae1c9a913930eae5ea506733aa7c285e12a06 Mon Sep 17 00:00:00 2001
From: Lu Baolu <baolu.lu@linux.intel.com>
Date: Wed, 9 Dec 2020 09:44:44 +0800
Subject: vfio/type1: Add vfio_group_iommu_domain()

Add the API for getting the domain from a vfio group. This could be used
by the physical device drivers which rely on the vfio/mdev framework for
mediated device user level access. The typical use case like below:

	unsigned int pasid;
	struct vfio_group *vfio_group;
	struct iommu_domain *iommu_domain;
	struct device *dev = mdev_dev(mdev);
	struct device *iommu_device = mdev_get_iommu_device(dev);

	if (!iommu_device ||
	    !iommu_dev_feature_enabled(iommu_device, IOMMU_DEV_FEAT_AUX))
		return -EINVAL;

	vfio_group = vfio_group_get_external_user_from_dev(dev);
	if (IS_ERR_OR_NULL(vfio_group))
		return -EFAULT;

	iommu_domain = vfio_group_iommu_domain(vfio_group);
	if (IS_ERR_OR_NULL(iommu_domain)) {
		vfio_group_put_external_user(vfio_group);
		return -EFAULT;
	}

	pasid = iommu_aux_get_pasid(iommu_domain, iommu_device);
	if (pasid < 0) {
		vfio_group_put_external_user(vfio_group);
		return -EFAULT;
	}

	/* Program device context with pasid value. */
	...

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/vfio.c             | 18 ++++++++++++++++++
 drivers/vfio/vfio_iommu_type1.c | 24 ++++++++++++++++++++++++
 include/linux/vfio.h            |  4 ++++
 3 files changed, 46 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 2151bc7f87ab..4ad8a35667a7 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -2331,6 +2331,24 @@ int vfio_unregister_notifier(struct device *dev, enum vfio_notify_type type,
 }
 EXPORT_SYMBOL(vfio_unregister_notifier);
 
+struct iommu_domain *vfio_group_iommu_domain(struct vfio_group *group)
+{
+	struct vfio_container *container;
+	struct vfio_iommu_driver *driver;
+
+	if (!group)
+		return ERR_PTR(-EINVAL);
+
+	container = group->container;
+	driver = container->iommu_driver;
+	if (likely(driver && driver->ops->group_iommu_domain))
+		return driver->ops->group_iommu_domain(container->iommu_data,
+						       group->iommu_group);
+
+	return ERR_PTR(-ENOTTY);
+}
+EXPORT_SYMBOL_GPL(vfio_group_iommu_domain);
+
 /**
  * Module/class support
  */
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 67e827638995..0b4dedaa9128 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -2980,6 +2980,29 @@ static int vfio_iommu_type1_dma_rw(void *iommu_data, dma_addr_t user_iova,
 	return ret;
 }
 
+static struct iommu_domain *
+vfio_iommu_type1_group_iommu_domain(void *iommu_data,
+				    struct iommu_group *iommu_group)
+{
+	struct iommu_domain *domain = ERR_PTR(-ENODEV);
+	struct vfio_iommu *iommu = iommu_data;
+	struct vfio_domain *d;
+
+	if (!iommu || !iommu_group)
+		return ERR_PTR(-EINVAL);
+
+	mutex_lock(&iommu->lock);
+	list_for_each_entry(d, &iommu->domain_list, next) {
+		if (find_iommu_group(d, iommu_group)) {
+			domain = d->domain;
+			break;
+		}
+	}
+	mutex_unlock(&iommu->lock);
+
+	return domain;
+}
+
 static const struct vfio_iommu_driver_ops vfio_iommu_driver_ops_type1 = {
 	.name			= "vfio-iommu-type1",
 	.owner			= THIS_MODULE,
@@ -2993,6 +3016,7 @@ static const struct vfio_iommu_driver_ops vfio_iommu_driver_ops_type1 = {
 	.register_notifier	= vfio_iommu_type1_register_notifier,
 	.unregister_notifier	= vfio_iommu_type1_unregister_notifier,
 	.dma_rw			= vfio_iommu_type1_dma_rw,
+	.group_iommu_domain	= vfio_iommu_type1_group_iommu_domain,
 };
 
 static int __init vfio_iommu_type1_init(void)
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index 38d3c6a8dc7e..f45940b38a02 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -90,6 +90,8 @@ struct vfio_iommu_driver_ops {
 					       struct notifier_block *nb);
 	int		(*dma_rw)(void *iommu_data, dma_addr_t user_iova,
 				  void *data, size_t count, bool write);
+	struct iommu_domain *(*group_iommu_domain)(void *iommu_data,
+						   struct iommu_group *group);
 };
 
 extern int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops);
@@ -126,6 +128,8 @@ extern int vfio_group_unpin_pages(struct vfio_group *group,
 extern int vfio_dma_rw(struct vfio_group *group, dma_addr_t user_iova,
 		       void *data, size_t len, bool write);
 
+extern struct iommu_domain *vfio_group_iommu_domain(struct vfio_group *group);
+
 /* each type has independent events */
 enum vfio_notify_type {
 	VFIO_IOMMU_NOTIFY = 0,
-- 
cgit v1.2.3


From 88149082bb8ef31b289673669e080ec6a00c2e59 Mon Sep 17 00:00:00 2001
From: Hao Li <lihao2018.fnst@cn.fujitsu.com>
Date: Tue, 8 Dec 2020 10:08:43 +0800
Subject: fs: Handle I_DONTCACHE in iput_final() instead of
 generic_drop_inode()

If generic_drop_inode() returns true, it means iput_final() can evict
this inode regardless of whether it is dirty or not. If we check
I_DONTCACHE in generic_drop_inode(), any inode with this bit set will be
evicted unconditionally. This is not the desired behavior because
I_DONTCACHE only means the inode shouldn't be cached on the LRU list.
As for whether we need to evict this inode, this is what
generic_drop_inode() should do. This patch corrects the usage of
I_DONTCACHE.

This patch was proposed in [1].

[1]: https://lore.kernel.org/linux-fsdevel/20200831003407.GE12096@dread.disaster.area/

Fixes: dae2f8ed7992 ("fs: Lift XFS_IDONTCACHE to the VFS layer")
Signed-off-by: Hao Li <lihao2018.fnst@cn.fujitsu.com>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/inode.c         | 4 +++-
 include/linux/fs.h | 3 +--
 2 files changed, 4 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/fs/inode.c b/fs/inode.c
index 9d78c37b00b8..5eea9912a0b9 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1627,7 +1627,9 @@ static void iput_final(struct inode *inode)
 	else
 		drop = generic_drop_inode(inode);
 
-	if (!drop && (sb->s_flags & SB_ACTIVE)) {
+	if (!drop &&
+	    !(inode->i_state & I_DONTCACHE) &&
+	    (sb->s_flags & SB_ACTIVE)) {
 		inode_add_lru(inode);
 		spin_unlock(&inode->i_lock);
 		return;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 8667d0cdc71e..8bde32cf9711 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2878,8 +2878,7 @@ extern int inode_needs_sync(struct inode *inode);
 extern int generic_delete_inode(struct inode *inode);
 static inline int generic_drop_inode(struct inode *inode)
 {
-	return !inode->i_nlink || inode_unhashed(inode) ||
-		(inode->i_state & I_DONTCACHE);
+	return !inode->i_nlink || inode_unhashed(inode);
 }
 extern void d_mark_dontcache(struct inode *inode);
 
-- 
cgit v1.2.3


From c9e6189fb03123a7dfb93589280347b46f30b161 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sun, 6 Dec 2020 22:46:18 +0100
Subject: ntp: Make the RTC synchronization more reliable

Miroslav reported that the periodic RTC synchronization in the NTP code
fails more often than not to hit the specified update window.

The reason is that the code uses delayed_work to schedule the update which
needs to be in thread context as the underlying RTC might be connected via
a slow bus, e.g. I2C. In the update function it verifies whether the
current time is correct vs. the requirements of the underlying RTC.

But delayed_work is using the timer wheel for scheduling which is
inaccurate by design. Depending on the distance to the expiry the wheel
gets less granular to allow batching and to avoid the cascading of the
original timer wheel. See 500462a9de65 ("timers: Switch to a non-cascading
wheel") and the code for further details.

The code already deals with this by splitting the 660 seconds period into a
long 659 seconds timer and then retrying with a smaller delta.

But looking at the actual granularities of the timer wheel (which depend on
the HZ configuration) the 659 seconds timer ends up in an outer wheel level
and is affected by a worst case granularity of:

HZ          Granularity
1000        32s
 250        16s
 100        40s

So the initial timer can be already off by max 12.5% which is not a big
issue as the period of the sync is defined as ~11 minutes.

The fine grained second attempt schedules to the desired update point with
a timer expiring less than a second from now. Depending on the actual delta
and the HZ setting even the second attempt can end up in outer wheel levels
which have a large enough granularity to make the correctness check fail.

As this is a fundamental property of the timer wheel there is no way to
make this more accurate short of iterating in one jiffies steps towards the
update point.

Switch it to an hrtimer instead which schedules the actual update work. The
hrtimer will expire precisely (max 1 jiffie delay when high resolution
timers are not available). The actual scheduling delay of the work is the
same as before.

The update is triggered from do_adjtimex() which is a bit racy but not much
more racy than it was before:

     if (ntp_synced())
     	queue_delayed_work(system_power_efficient_wq, &sync_work, 0);

which is racy when the work is currently executed and has not managed to
reschedule itself.

This becomes now:

     if (ntp_synced() && !hrtimer_is_queued(&sync_hrtimer))
     	queue_work(system_power_efficient_wq, &sync_work, 0);

which is racy when the hrtimer has expired and the work is currently
executed and has not yet managed to rearm the hrtimer.

Not a big problem as it just schedules work for nothing.

The new implementation has a safe guard in place to catch the case where
the hrtimer is queued on entry to the work function and avoids an extra
update attempt of the RTC that way.

Reported-by: Miroslav Lichvar <mlichvar@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Miroslav Lichvar <mlichvar@redhat.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Acked-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Link: https://lore.kernel.org/r/20201206220542.062910520@linutronix.de
---
 include/linux/timex.h      |  1 -
 kernel/time/ntp.c          | 90 ++++++++++++++++++++++++----------------------
 kernel/time/ntp_internal.h |  7 ++++
 3 files changed, 55 insertions(+), 43 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/timex.h b/include/linux/timex.h
index ce0859763670..9c2e54faf9b7 100644
--- a/include/linux/timex.h
+++ b/include/linux/timex.h
@@ -157,7 +157,6 @@ extern int do_clock_adjtime(const clockid_t which_clock, struct __kernel_timex *
 extern void hardpps(const struct timespec64 *, const struct timespec64 *);
 
 int read_current_timer(unsigned long *timer_val);
-void ntp_notify_cmos_timer(void);
 
 /* The clock frequency of the i8253/i8254 PIT */
 #define PIT_TICK_RATE 1193182ul
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 069ca78fb0bf..ff1a7b8ec4ef 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -494,65 +494,55 @@ out:
 	return leap;
 }
 
+#if defined(CONFIG_GENERIC_CMOS_UPDATE) || defined(CONFIG_RTC_SYSTOHC)
 static void sync_hw_clock(struct work_struct *work);
-static DECLARE_DELAYED_WORK(sync_work, sync_hw_clock);
-
-static void sched_sync_hw_clock(struct timespec64 now,
-				unsigned long target_nsec, bool fail)
+static DECLARE_WORK(sync_work, sync_hw_clock);
+static struct hrtimer sync_hrtimer;
+#define SYNC_PERIOD_NS (11UL * 60 * NSEC_PER_SEC)
 
+static enum hrtimer_restart sync_timer_callback(struct hrtimer *timer)
 {
-	struct timespec64 next;
+	queue_work(system_power_efficient_wq, &sync_work);
 
-	ktime_get_real_ts64(&next);
-	if (!fail)
-		next.tv_sec = 659;
-	else {
-		/*
-		 * Try again as soon as possible. Delaying long periods
-		 * decreases the accuracy of the work queue timer. Due to this
-		 * the algorithm is very likely to require a short-sleep retry
-		 * after the above long sleep to synchronize ts_nsec.
-		 */
-		next.tv_sec = 0;
-	}
+	return HRTIMER_NORESTART;
+}
 
-	/* Compute the needed delay that will get to tv_nsec == target_nsec */
-	next.tv_nsec = target_nsec - next.tv_nsec;
-	if (next.tv_nsec <= 0)
-		next.tv_nsec += NSEC_PER_SEC;
-	if (next.tv_nsec >= NSEC_PER_SEC) {
-		next.tv_sec++;
-		next.tv_nsec -= NSEC_PER_SEC;
-	}
+static void sched_sync_hw_clock(unsigned long offset_nsec, bool retry)
+{
+	ktime_t exp = ktime_set(ktime_get_real_seconds(), 0);
+
+	if (retry)
+		exp = ktime_add_ns(exp, 2 * NSEC_PER_SEC - offset_nsec);
+	else
+		exp = ktime_add_ns(exp, SYNC_PERIOD_NS - offset_nsec);
 
-	queue_delayed_work(system_power_efficient_wq, &sync_work,
-			   timespec64_to_jiffies(&next));
+	hrtimer_start(&sync_hrtimer, exp, HRTIMER_MODE_ABS);
 }
 
 static void sync_rtc_clock(void)
 {
-	unsigned long target_nsec;
-	struct timespec64 adjust, now;
+	unsigned long offset_nsec;
+	struct timespec64 adjust;
 	int rc;
 
 	if (!IS_ENABLED(CONFIG_RTC_SYSTOHC))
 		return;
 
-	ktime_get_real_ts64(&now);
+	ktime_get_real_ts64(&adjust);
 
-	adjust = now;
 	if (persistent_clock_is_local)
 		adjust.tv_sec -= (sys_tz.tz_minuteswest * 60);
 
 	/*
-	 * The current RTC in use will provide the target_nsec it wants to be
-	 * called at, and does rtc_tv_nsec_ok internally.
+	 * The current RTC in use will provide the nanoseconds offset prior
+	 * to a full second it wants to be called at, and invokes
+	 * rtc_tv_nsec_ok() internally.
 	 */
-	rc = rtc_set_ntp_time(adjust, &target_nsec);
+	rc = rtc_set_ntp_time(adjust, &offset_nsec);
 	if (rc == -ENODEV)
 		return;
 
-	sched_sync_hw_clock(now, target_nsec, rc);
+	sched_sync_hw_clock(offset_nsec, rc != 0);
 }
 
 #ifdef CONFIG_GENERIC_CMOS_UPDATE
@@ -599,7 +589,7 @@ static bool sync_cmos_clock(void)
 		}
 	}
 
-	sched_sync_hw_clock(now, target_nsec, rc);
+	sched_sync_hw_clock(target_nsec, rc != 0);
 	return true;
 }
 
@@ -613,7 +603,12 @@ static bool sync_cmos_clock(void)
  */
 static void sync_hw_clock(struct work_struct *work)
 {
-	if (!ntp_synced())
+	/*
+	 * Don't update if STA_UNSYNC is set and if ntp_notify_cmos_timer()
+	 * managed to schedule the work between the timer firing and the
+	 * work being able to rearm the timer. Wait for the timer to expire.
+	 */
+	if (!ntp_synced() || hrtimer_is_queued(&sync_hrtimer))
 		return;
 
 	if (sync_cmos_clock())
@@ -624,13 +619,23 @@ static void sync_hw_clock(struct work_struct *work)
 
 void ntp_notify_cmos_timer(void)
 {
-	if (!ntp_synced())
-		return;
+	/*
+	 * When the work is currently executed but has not yet the timer
+	 * rearmed this queues the work immediately again. No big issue,
+	 * just a pointless work scheduled.
+	 */
+	if (ntp_synced() && !hrtimer_is_queued(&sync_hrtimer))
+		queue_work(system_power_efficient_wq, &sync_work);
+}
 
-	if (IS_ENABLED(CONFIG_GENERIC_CMOS_UPDATE) ||
-	    IS_ENABLED(CONFIG_RTC_SYSTOHC))
-		queue_delayed_work(system_power_efficient_wq, &sync_work, 0);
+static void __init ntp_init_cmos_sync(void)
+{
+	hrtimer_init(&sync_hrtimer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
+	sync_hrtimer.function = sync_timer_callback;
 }
+#else /* CONFIG_GENERIC_CMOS_UPDATE) || defined(CONFIG_RTC_SYSTOHC) */
+static inline void __init ntp_init_cmos_sync(void) { }
+#endif /* !CONFIG_GENERIC_CMOS_UPDATE) || defined(CONFIG_RTC_SYSTOHC) */
 
 /*
  * Propagate a new txc->status value into the NTP state:
@@ -1044,4 +1049,5 @@ __setup("ntp_tick_adj=", ntp_tick_adj_setup);
 void __init ntp_init(void)
 {
 	ntp_clear();
+	ntp_init_cmos_sync();
 }
diff --git a/kernel/time/ntp_internal.h b/kernel/time/ntp_internal.h
index 908ecaa65fc3..23d1b74c3065 100644
--- a/kernel/time/ntp_internal.h
+++ b/kernel/time/ntp_internal.h
@@ -12,4 +12,11 @@ extern int __do_adjtimex(struct __kernel_timex *txc,
 			 const struct timespec64 *ts,
 			 s32 *time_tai, struct audit_ntp_data *ad);
 extern void __hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts);
+
+#if defined(CONFIG_GENERIC_CMOS_UPDATE) || defined(CONFIG_RTC_SYSTOHC)
+extern void ntp_notify_cmos_timer(void);
+#else
+static inline void ntp_notify_cmos_timer(void) { }
+#endif
+
 #endif /* _LINUX_NTP_INTERNAL_H */
-- 
cgit v1.2.3


From 33e62e832384c8cb523044e0e9d99d7133f98e93 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sun, 6 Dec 2020 22:46:19 +0100
Subject: ntp, rtc: Move rtc_set_ntp_time() to ntp code

rtc_set_ntp_time() is not really RTC functionality as the code is just a
user of RTC. Move it into the NTP code which allows further cleanups.

Requested-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Acked-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Link: https://lore.kernel.org/r/20201206220542.166871172@linutronix.de
---
 drivers/rtc/Makefile  |  1 -
 drivers/rtc/systohc.c | 61 -----------------------------------
 include/linux/rtc.h   | 34 --------------------
 kernel/time/ntp.c     | 88 +++++++++++++++++++++++++++++++++++++++++++++++++--
 4 files changed, 85 insertions(+), 99 deletions(-)
 delete mode 100644 drivers/rtc/systohc.c

(limited to 'include/linux')

diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile
index bfb57464118d..bb8f319b09fb 100644
--- a/drivers/rtc/Makefile
+++ b/drivers/rtc/Makefile
@@ -6,7 +6,6 @@
 ccflags-$(CONFIG_RTC_DEBUG)	:= -DDEBUG
 
 obj-$(CONFIG_RTC_LIB)		+= lib.o
-obj-$(CONFIG_RTC_SYSTOHC)	+= systohc.o
 obj-$(CONFIG_RTC_CLASS)		+= rtc-core.o
 obj-$(CONFIG_RTC_MC146818_LIB)	+= rtc-mc146818-lib.o
 rtc-core-y			:= class.o interface.o
diff --git a/drivers/rtc/systohc.c b/drivers/rtc/systohc.c
deleted file mode 100644
index 8b70f0520e13..000000000000
--- a/drivers/rtc/systohc.c
+++ /dev/null
@@ -1,61 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/rtc.h>
-#include <linux/time.h>
-
-/**
- * rtc_set_ntp_time - Save NTP synchronized time to the RTC
- * @now: Current time of day
- * @target_nsec: pointer for desired now->tv_nsec value
- *
- * Replacement for the NTP platform function update_persistent_clock64
- * that stores time for later retrieval by rtc_hctosys.
- *
- * Returns 0 on successful RTC update, -ENODEV if a RTC update is not
- * possible at all, and various other -errno for specific temporary failure
- * cases.
- *
- * -EPROTO is returned if now.tv_nsec is not close enough to *target_nsec.
- *
- * If temporary failure is indicated the caller should try again 'soon'
- */
-int rtc_set_ntp_time(struct timespec64 now, unsigned long *target_nsec)
-{
-	struct rtc_device *rtc;
-	struct rtc_time tm;
-	struct timespec64 to_set;
-	int err = -ENODEV;
-	bool ok;
-
-	rtc = rtc_class_open(CONFIG_RTC_SYSTOHC_DEVICE);
-	if (!rtc)
-		goto out_err;
-
-	if (!rtc->ops || !rtc->ops->set_time)
-		goto out_close;
-
-	/* Compute the value of tv_nsec we require the caller to supply in
-	 * now.tv_nsec.  This is the value such that (now +
-	 * set_offset_nsec).tv_nsec == 0.
-	 */
-	set_normalized_timespec64(&to_set, 0, -rtc->set_offset_nsec);
-	*target_nsec = to_set.tv_nsec;
-
-	/* The ntp code must call this with the correct value in tv_nsec, if
-	 * it does not we update target_nsec and return EPROTO to make the ntp
-	 * code try again later.
-	 */
-	ok = rtc_tv_nsec_ok(rtc->set_offset_nsec, &to_set, &now);
-	if (!ok) {
-		err = -EPROTO;
-		goto out_close;
-	}
-
-	rtc_time64_to_tm(to_set.tv_sec, &tm);
-
-	err = rtc_set_time(rtc, &tm);
-
-out_close:
-	rtc_class_close(rtc);
-out_err:
-	return err;
-}
diff --git a/include/linux/rtc.h b/include/linux/rtc.h
index 22d1575e4991..ff62680b48ca 100644
--- a/include/linux/rtc.h
+++ b/include/linux/rtc.h
@@ -165,7 +165,6 @@ int __rtc_register_device(struct module *owner, struct rtc_device *rtc);
 
 extern int rtc_read_time(struct rtc_device *rtc, struct rtc_time *tm);
 extern int rtc_set_time(struct rtc_device *rtc, struct rtc_time *tm);
-extern int rtc_set_ntp_time(struct timespec64 now, unsigned long *target_nsec);
 int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm);
 extern int rtc_read_alarm(struct rtc_device *rtc,
 			struct rtc_wkalrm *alrm);
@@ -205,39 +204,6 @@ static inline bool is_leap_year(unsigned int year)
 	return (!(year % 4) && (year % 100)) || !(year % 400);
 }
 
-/* Determine if we can call to driver to set the time. Drivers can only be
- * called to set a second aligned time value, and the field set_offset_nsec
- * specifies how far away from the second aligned time to call the driver.
- *
- * This also computes 'to_set' which is the time we are trying to set, and has
- * a zero in tv_nsecs, such that:
- *    to_set - set_delay_nsec == now +/- FUZZ
- *
- */
-static inline bool rtc_tv_nsec_ok(s64 set_offset_nsec,
-				  struct timespec64 *to_set,
-				  const struct timespec64 *now)
-{
-	/* Allowed error in tv_nsec, arbitarily set to 5 jiffies in ns. */
-	const unsigned long TIME_SET_NSEC_FUZZ = TICK_NSEC * 5;
-	struct timespec64 delay = {.tv_sec = 0,
-				   .tv_nsec = set_offset_nsec};
-
-	*to_set = timespec64_add(*now, delay);
-
-	if (to_set->tv_nsec < TIME_SET_NSEC_FUZZ) {
-		to_set->tv_nsec = 0;
-		return true;
-	}
-
-	if (to_set->tv_nsec > NSEC_PER_SEC - TIME_SET_NSEC_FUZZ) {
-		to_set->tv_sec++;
-		to_set->tv_nsec = 0;
-		return true;
-	}
-	return false;
-}
-
 #define rtc_register_device(device) \
 	__rtc_register_device(THIS_MODULE, device)
 
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index ff1a7b8ec4ef..84a554622cee 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -519,15 +519,94 @@ static void sched_sync_hw_clock(unsigned long offset_nsec, bool retry)
 	hrtimer_start(&sync_hrtimer, exp, HRTIMER_MODE_ABS);
 }
 
+/*
+ * Determine if we can call to driver to set the time. Drivers can only be
+ * called to set a second aligned time value, and the field set_offset_nsec
+ * specifies how far away from the second aligned time to call the driver.
+ *
+ * This also computes 'to_set' which is the time we are trying to set, and has
+ * a zero in tv_nsecs, such that:
+ *    to_set - set_delay_nsec == now +/- FUZZ
+ *
+ */
+static inline bool rtc_tv_nsec_ok(long set_offset_nsec,
+				  struct timespec64 *to_set,
+				  const struct timespec64 *now)
+{
+	/* Allowed error in tv_nsec, arbitarily set to 5 jiffies in ns. */
+	const unsigned long TIME_SET_NSEC_FUZZ = TICK_NSEC * 5;
+	struct timespec64 delay = {.tv_sec = 0,
+				   .tv_nsec = set_offset_nsec};
+
+	*to_set = timespec64_add(*now, delay);
+
+	if (to_set->tv_nsec < TIME_SET_NSEC_FUZZ) {
+		to_set->tv_nsec = 0;
+		return true;
+	}
+
+	if (to_set->tv_nsec > NSEC_PER_SEC - TIME_SET_NSEC_FUZZ) {
+		to_set->tv_sec++;
+		to_set->tv_nsec = 0;
+		return true;
+	}
+	return false;
+}
+
+#ifdef CONFIG_RTC_SYSTOHC
+/*
+ * rtc_set_ntp_time - Save NTP synchronized time to the RTC
+ */
+static int rtc_set_ntp_time(struct timespec64 now, unsigned long *target_nsec)
+{
+	struct rtc_device *rtc;
+	struct rtc_time tm;
+	struct timespec64 to_set;
+	int err = -ENODEV;
+	bool ok;
+
+	rtc = rtc_class_open(CONFIG_RTC_SYSTOHC_DEVICE);
+	if (!rtc)
+		goto out_err;
+
+	if (!rtc->ops || !rtc->ops->set_time)
+		goto out_close;
+
+	/*
+	 * Compute the value of tv_nsec we require the caller to supply in
+	 * now.tv_nsec.  This is the value such that (now +
+	 * set_offset_nsec).tv_nsec == 0.
+	 */
+	set_normalized_timespec64(&to_set, 0, -rtc->set_offset_nsec);
+	*target_nsec = to_set.tv_nsec;
+
+	/*
+	 * The ntp code must call this with the correct value in tv_nsec, if
+	 * it does not we update target_nsec and return EPROTO to make the ntp
+	 * code try again later.
+	 */
+	ok = rtc_tv_nsec_ok(rtc->set_offset_nsec, &to_set, &now);
+	if (!ok) {
+		err = -EPROTO;
+		goto out_close;
+	}
+
+	rtc_time64_to_tm(to_set.tv_sec, &tm);
+
+	err = rtc_set_time(rtc, &tm);
+
+out_close:
+	rtc_class_close(rtc);
+out_err:
+	return err;
+}
+
 static void sync_rtc_clock(void)
 {
 	unsigned long offset_nsec;
 	struct timespec64 adjust;
 	int rc;
 
-	if (!IS_ENABLED(CONFIG_RTC_SYSTOHC))
-		return;
-
 	ktime_get_real_ts64(&adjust);
 
 	if (persistent_clock_is_local)
@@ -544,6 +623,9 @@ static void sync_rtc_clock(void)
 
 	sched_sync_hw_clock(offset_nsec, rc != 0);
 }
+#else
+static inline void sync_rtc_clock(void) { }
+#endif
 
 #ifdef CONFIG_GENERIC_CMOS_UPDATE
 int __weak update_persistent_clock64(struct timespec64 now64)
-- 
cgit v1.2.3


From 69eca258c85000564577642ba28335eb4e1df8f0 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sun, 6 Dec 2020 22:46:20 +0100
Subject: ntp: Make the RTC sync offset less obscure

The current RTC set_offset_nsec value is not really intuitive to
understand.

  tsched       twrite(t2.tv_sec - 1) 	 t2 (seconds increment)

The offset is calculated from twrite based on the assumption that t2 -
twrite == 1s. That means for the MC146818 RTC the offset needs to be
negative so that the write happens 500ms before t2.

It's easier to understand when the whole calculation is based on t2. That
avoids negative offsets and the meaning is obvious:

 t2 - twrite:     The time defined by the chip when seconds increment
      		  after the write.

 twrite - tsched: The time for the transport to the point where the chip
 	  	  is updated.

==> set_offset_nsec =  t2 - tsched
    ttransport      =  twrite - tsched
    tRTCinc         =  t2 - twrite
==> set_offset_nsec =  ttransport + tRTCinc

tRTCinc is a chip property and can be obtained from the data sheet.

ttransport depends on how the RTC is connected. It is close to 0 for
directly accessible RTCs. For RTCs behind a slow bus, e.g. i2c, it's the
time required to send the update over the bus. This can be estimated or
even calibrated, but that's a different problem.

Adjust the implementation and update comments accordingly.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Link: https://lore.kernel.org/r/20201206220542.263204937@linutronix.de
---
 drivers/rtc/class.c    |  9 +++++++--
 drivers/rtc/rtc-cmos.c |  2 +-
 include/linux/rtc.h    | 35 +++++++++++++++++++++++++++++------
 kernel/time/ntp.c      | 47 ++++++++++++++++++++++++-----------------------
 4 files changed, 61 insertions(+), 32 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c
index d7957376eb96..5855aa2eef62 100644
--- a/drivers/rtc/class.c
+++ b/drivers/rtc/class.c
@@ -200,8 +200,13 @@ static struct rtc_device *rtc_allocate_device(void)
 
 	device_initialize(&rtc->dev);
 
-	/* Drivers can revise this default after allocating the device. */
-	rtc->set_offset_nsec =  5 * NSEC_PER_MSEC;
+	/*
+	 * Drivers can revise this default after allocating the device.
+	 * The default is what most RTCs do: Increment seconds exactly one
+	 * second after the write happened. This adds a default transport
+	 * time of 5ms which is at least halfways close to reality.
+	 */
+	rtc->set_offset_nsec = NSEC_PER_SEC + 5 * NSEC_PER_MSEC;
 
 	rtc->irq_freq = 1;
 	rtc->max_user_freq = 64;
diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index 7728faca01b4..c5bcd2adc9fe 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -869,7 +869,7 @@ cmos_do_probe(struct device *dev, struct resource *ports, int rtc_irq)
 		goto cleanup2;
 
 	/* Set the sync offset for the periodic 11min update correct */
-	cmos_rtc.rtc->set_offset_nsec = -(NSEC_PER_SEC / 2);
+	cmos_rtc.rtc->set_offset_nsec = NSEC_PER_SEC / 2;
 
 	/* export at least the first block of NVRAM */
 	nvmem_cfg.size = address_space - NVRAM_OFFSET;
diff --git a/include/linux/rtc.h b/include/linux/rtc.h
index ff62680b48ca..b829382de6c3 100644
--- a/include/linux/rtc.h
+++ b/include/linux/rtc.h
@@ -110,13 +110,36 @@ struct rtc_device {
 	/* Some hardware can't support UIE mode */
 	int uie_unsupported;
 
-	/* Number of nsec it takes to set the RTC clock. This influences when
-	 * the set ops are called. An offset:
-	 *   - of 0.5 s will call RTC set for wall clock time 10.0 s at 9.5 s
-	 *   - of 1.5 s will call RTC set for wall clock time 10.0 s at 8.5 s
-	 *   - of -0.5 s will call RTC set for wall clock time 10.0 s at 10.5 s
+	/*
+	 * This offset specifies the update timing of the RTC.
+	 *
+	 * tsched     t1 write(t2.tv_sec - 1sec))  t2 RTC increments seconds
+	 *
+	 * The offset defines how tsched is computed so that the write to
+	 * the RTC (t2.tv_sec - 1sec) is correct versus the time required
+	 * for the transport of the write and the time which the RTC needs
+	 * to increment seconds the first time after the write (t2).
+	 *
+	 * For direct accessible RTCs tsched ~= t1 because the write time
+	 * is negligible. For RTCs behind slow busses the transport time is
+	 * significant and has to be taken into account.
+	 *
+	 * The time between the write (t1) and the first increment after
+	 * the write (t2) is RTC specific. For a MC146818 RTC it's 500ms,
+	 * for many others it's exactly 1 second. Consult the datasheet.
+	 *
+	 * The value of this offset is also used to calculate the to be
+	 * written value (t2.tv_sec - 1sec) at tsched.
+	 *
+	 * The default value for this is NSEC_PER_SEC + 10 msec default
+	 * transport time. The offset can be adjusted by drivers so the
+	 * calculation for the to be written value at tsched becomes
+	 * correct:
+	 *
+	 *	newval = tsched + set_offset_nsec - NSEC_PER_SEC
+	 * and  (tsched + set_offset_nsec) % NSEC_PER_SEC == 0
 	 */
-	long set_offset_nsec;
+	unsigned long set_offset_nsec;
 
 	bool registered;
 
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 84a554622cee..a34ac069335f 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -520,22 +520,33 @@ static void sched_sync_hw_clock(unsigned long offset_nsec, bool retry)
 }
 
 /*
- * Determine if we can call to driver to set the time. Drivers can only be
- * called to set a second aligned time value, and the field set_offset_nsec
- * specifies how far away from the second aligned time to call the driver.
+ * Check whether @now is correct versus the required time to update the RTC
+ * and calculate the value which needs to be written to the RTC so that the
+ * next seconds increment of the RTC after the write is aligned with the next
+ * seconds increment of clock REALTIME.
  *
- * This also computes 'to_set' which is the time we are trying to set, and has
- * a zero in tv_nsecs, such that:
- *    to_set - set_delay_nsec == now +/- FUZZ
+ * tsched     t1 write(t2.tv_sec - 1sec))	t2 RTC increments seconds
  *
+ * t2.tv_nsec == 0
+ * tsched = t2 - set_offset_nsec
+ * newval = t2 - NSEC_PER_SEC
+ *
+ * ==> neval = tsched + set_offset_nsec - NSEC_PER_SEC
+ *
+ * As the execution of this code is not guaranteed to happen exactly at
+ * tsched this allows it to happen within a fuzzy region:
+ *
+ *	abs(now - tsched) < FUZZ
+ *
+ * If @now is not inside the allowed window the function returns false.
  */
-static inline bool rtc_tv_nsec_ok(long set_offset_nsec,
+static inline bool rtc_tv_nsec_ok(unsigned long set_offset_nsec,
 				  struct timespec64 *to_set,
 				  const struct timespec64 *now)
 {
 	/* Allowed error in tv_nsec, arbitarily set to 5 jiffies in ns. */
 	const unsigned long TIME_SET_NSEC_FUZZ = TICK_NSEC * 5;
-	struct timespec64 delay = {.tv_sec = 0,
+	struct timespec64 delay = {.tv_sec = -1,
 				   .tv_nsec = set_offset_nsec};
 
 	*to_set = timespec64_add(*now, delay);
@@ -557,11 +568,11 @@ static inline bool rtc_tv_nsec_ok(long set_offset_nsec,
 /*
  * rtc_set_ntp_time - Save NTP synchronized time to the RTC
  */
-static int rtc_set_ntp_time(struct timespec64 now, unsigned long *target_nsec)
+static int rtc_set_ntp_time(struct timespec64 now, unsigned long *offset_nsec)
 {
+	struct timespec64 to_set;
 	struct rtc_device *rtc;
 	struct rtc_time tm;
-	struct timespec64 to_set;
 	int err = -ENODEV;
 	bool ok;
 
@@ -572,19 +583,9 @@ static int rtc_set_ntp_time(struct timespec64 now, unsigned long *target_nsec)
 	if (!rtc->ops || !rtc->ops->set_time)
 		goto out_close;
 
-	/*
-	 * Compute the value of tv_nsec we require the caller to supply in
-	 * now.tv_nsec.  This is the value such that (now +
-	 * set_offset_nsec).tv_nsec == 0.
-	 */
-	set_normalized_timespec64(&to_set, 0, -rtc->set_offset_nsec);
-	*target_nsec = to_set.tv_nsec;
+	/* Store the update offset for this RTC */
+	*offset_nsec = rtc->set_offset_nsec;
 
-	/*
-	 * The ntp code must call this with the correct value in tv_nsec, if
-	 * it does not we update target_nsec and return EPROTO to make the ntp
-	 * code try again later.
-	 */
 	ok = rtc_tv_nsec_ok(rtc->set_offset_nsec, &to_set, &now);
 	if (!ok) {
 		err = -EPROTO;
@@ -657,7 +658,7 @@ static bool sync_cmos_clock(void)
 	 * implement this legacy API.
 	 */
 	ktime_get_real_ts64(&now);
-	if (rtc_tv_nsec_ok(-1 * target_nsec, &adjust, &now)) {
+	if (rtc_tv_nsec_ok(target_nsec, &adjust, &now)) {
 		if (persistent_clock_is_local)
 			adjust.tv_sec -= (sys_tz.tz_minuteswest * 60);
 		rc = update_persistent_clock64(adjust);
-- 
cgit v1.2.3


From fe79d5de77204dd946cfad76a9bec23354b1a500 Mon Sep 17 00:00:00 2001
From: Kyle Tso <kyletso@google.com>
Date: Thu, 10 Dec 2020 17:05:20 +0100
Subject: USB: typec: tcpm: Add a 30ms room for tPSSourceOn in PR_SWAP

TCPM state machine needs 20-25ms to enter the ErrorRecovery state after
tPSSourceOn timer timeouts. Change the timer from max 480ms to 450ms to
ensure that the timer complies with the Spec. In order to keep the
flexibility for other usecases using tPSSourceOn, add another timer only
for PR_SWAP.

Cc: Guenter Roeck <linux@roeck-us.net>
Cc: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Cc: Badhri Jagan Sridharan <badhri@google.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Acked-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Signed-off-by: Kyle Tso <kyletso@google.com>
Signed-off-by: Will McVicker <willmcvicker@google.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/20201210160521.3417426-5-gregkh@linuxfoundation.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/tcpm.c | 2 +-
 include/linux/usb/pd.h        | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 3f9edc8a9a57..36b6ce85093f 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -3738,7 +3738,7 @@ static void run_state_machine(struct tcpm_port *port)
 			tcpm_set_state(port, ERROR_RECOVERY, 0);
 			break;
 		}
-		tcpm_set_state(port, ERROR_RECOVERY, PD_T_PS_SOURCE_ON);
+		tcpm_set_state(port, ERROR_RECOVERY, PD_T_PS_SOURCE_ON_PRS);
 		break;
 	case PR_SWAP_SRC_SNK_SINK_ON:
 		/* Set the vbus disconnect threshold for implicit contract */
diff --git a/include/linux/usb/pd.h b/include/linux/usb/pd.h
index 63a66dd5d832..bb9a782e1411 100644
--- a/include/linux/usb/pd.h
+++ b/include/linux/usb/pd.h
@@ -466,6 +466,7 @@ static inline unsigned int rdo_max_power(u32 rdo)
 #define PD_T_DRP_SRC		30
 #define PD_T_PS_SOURCE_OFF	920
 #define PD_T_PS_SOURCE_ON	480
+#define PD_T_PS_SOURCE_ON_PRS	450	/* 390 - 480ms */
 #define PD_T_PS_HARD_RESET	30
 #define PD_T_SRC_RECOVER	760
 #define PD_T_SRC_RECOVER_MAX	1000
-- 
cgit v1.2.3


From fecc4559780d52d174ea05e3bf543669165389c3 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Wed, 2 Dec 2020 14:07:09 +0200
Subject: fsnotify: fix events reported to watching parent and child

fsnotify_parent() used to send two separate events to backends when a
parent inode is watching children and the child inode is also watching.
In an attempt to avoid duplicate events in fanotify, we unified the two
backend callbacks to a single callback and handled the reporting of the
two separate events for the relevant backends (inotify and dnotify).
However the handling is buggy and can result in inotify and dnotify
listeners receiving events of the type they never asked for or spurious
events.

The problem is the unified event callback with two inode marks (parent and
child) is called when any of the parent and child inodes are watched and
interested in the event, but the parent inode's mark that is interested
in the event on the child is not necessarily the one we are currently
reporting to (it could belong to a different group).

So before reporting the parent or child event flavor to backend we need
to check that the mark is really interested in that event flavor.

The semantics of INODE and CHILD marks were hard to follow and made the
logic more complicated than it should have been.  Replace it with INODE
and PARENT marks semantics to hopefully make the logic more clear.

Thanks to Hugh Dickins for spotting a bug in the earlier version of this
patch.

Fixes: 497b0c5a7c06 ("fsnotify: send event to parent and child with single callback")
CC: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20201202120713.702387-4-amir73il@gmail.com
Reported-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/notify/fanotify/fanotify.c    |  7 ++--
 fs/notify/fsnotify.c             | 84 ++++++++++++++++++++++++----------------
 include/linux/fsnotify_backend.h |  6 +--
 3 files changed, 57 insertions(+), 40 deletions(-)

(limited to 'include/linux')

diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 9167884a61ec..1192c9953620 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -268,12 +268,11 @@ static u32 fanotify_group_event_mask(struct fsnotify_group *group,
 			continue;
 
 		/*
-		 * If the event is for a child and this mark is on a parent not
+		 * If the event is on a child and this mark is on a parent not
 		 * watching children, don't send it!
 		 */
-		if (event_mask & FS_EVENT_ON_CHILD &&
-		    type == FSNOTIFY_OBJ_TYPE_INODE &&
-		     !(mark->mask & FS_EVENT_ON_CHILD))
+		if (type == FSNOTIFY_OBJ_TYPE_PARENT &&
+		    !(mark->mask & FS_EVENT_ON_CHILD))
 			continue;
 
 		marks_mask |= mark->mask;
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index c5c68bcbaadf..30d422b8c0fc 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -152,6 +152,13 @@ static bool fsnotify_event_needs_parent(struct inode *inode, struct mount *mnt,
 	if (mask & FS_ISDIR)
 		return false;
 
+	/*
+	 * All events that are possible on child can also may be reported with
+	 * parent/name info to inode/sb/mount.  Otherwise, a watching parent
+	 * could result in events reported with unexpected name info to sb/mount.
+	 */
+	BUILD_BUG_ON(FS_EVENTS_POSS_ON_CHILD & ~FS_EVENTS_POSS_TO_PARENT);
+
 	/* Did either inode/sb/mount subscribe for events with parent/name? */
 	marks_mask |= fsnotify_parent_needed_mask(inode->i_fsnotify_mask);
 	marks_mask |= fsnotify_parent_needed_mask(inode->i_sb->s_fsnotify_mask);
@@ -249,6 +256,10 @@ static int fsnotify_handle_inode_event(struct fsnotify_group *group,
 	    path && d_unlinked(path->dentry))
 		return 0;
 
+	/* Check interest of this mark in case event was sent with two marks */
+	if (!(mask & inode_mark->mask & ALL_FSNOTIFY_EVENTS))
+		return 0;
+
 	return ops->handle_inode_event(inode_mark, mask, inode, dir, name, cookie);
 }
 
@@ -258,38 +269,46 @@ static int fsnotify_handle_event(struct fsnotify_group *group, __u32 mask,
 				 u32 cookie, struct fsnotify_iter_info *iter_info)
 {
 	struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info);
-	struct fsnotify_mark *child_mark = fsnotify_iter_child_mark(iter_info);
+	struct fsnotify_mark *parent_mark = fsnotify_iter_parent_mark(iter_info);
 	int ret;
 
 	if (WARN_ON_ONCE(fsnotify_iter_sb_mark(iter_info)) ||
 	    WARN_ON_ONCE(fsnotify_iter_vfsmount_mark(iter_info)))
 		return 0;
 
-	/*
-	 * An event can be sent on child mark iterator instead of inode mark
-	 * iterator because of other groups that have interest of this inode
-	 * and have marks on both parent and child.  We can simplify this case.
-	 */
-	if (!inode_mark) {
-		inode_mark = child_mark;
-		child_mark = NULL;
+	if (parent_mark) {
+		/*
+		 * parent_mark indicates that the parent inode is watching
+		 * children and interested in this event, which is an event
+		 * possible on child. But is *this mark* watching children and
+		 * interested in this event?
+		 */
+		if (parent_mark->mask & FS_EVENT_ON_CHILD) {
+			ret = fsnotify_handle_inode_event(group, parent_mark, mask,
+							  data, data_type, dir, name, 0);
+			if (ret)
+				return ret;
+		}
+		if (!inode_mark)
+			return 0;
+	}
+
+	if (mask & FS_EVENT_ON_CHILD) {
+		/*
+		 * Some events can be sent on both parent dir and child marks
+		 * (e.g. FS_ATTRIB).  If both parent dir and child are
+		 * watching, report the event once to parent dir with name (if
+		 * interested) and once to child without name (if interested).
+		 * The child watcher is expecting an event without a file name
+		 * and without the FS_EVENT_ON_CHILD flag.
+		 */
+		mask &= ~FS_EVENT_ON_CHILD;
 		dir = NULL;
 		name = NULL;
 	}
 
-	ret = fsnotify_handle_inode_event(group, inode_mark, mask, data, data_type,
-					  dir, name, cookie);
-	if (ret || !child_mark)
-		return ret;
-
-	/*
-	 * Some events can be sent on both parent dir and child marks
-	 * (e.g. FS_ATTRIB).  If both parent dir and child are watching,
-	 * report the event once to parent dir with name and once to child
-	 * without name.
-	 */
-	return fsnotify_handle_inode_event(group, child_mark, mask, data, data_type,
-					   NULL, NULL, 0);
+	return fsnotify_handle_inode_event(group, inode_mark, mask, data, data_type,
+					   dir, name, cookie);
 }
 
 static int send_to_group(__u32 mask, const void *data, int data_type,
@@ -447,7 +466,7 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir,
 	struct fsnotify_iter_info iter_info = {};
 	struct super_block *sb;
 	struct mount *mnt = NULL;
-	struct inode *child = NULL;
+	struct inode *parent = NULL;
 	int ret = 0;
 	__u32 test_mask, marks_mask;
 
@@ -459,11 +478,10 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir,
 		inode = dir;
 	} else if (mask & FS_EVENT_ON_CHILD) {
 		/*
-		 * Event on child - report on TYPE_INODE to dir if it is
-		 * watching children and on TYPE_CHILD to child.
+		 * Event on child - report on TYPE_PARENT to dir if it is
+		 * watching children and on TYPE_INODE to child.
 		 */
-		child = inode;
-		inode = dir;
+		parent = dir;
 	}
 	sb = inode->i_sb;
 
@@ -477,7 +495,7 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir,
 	if (!sb->s_fsnotify_marks &&
 	    (!mnt || !mnt->mnt_fsnotify_marks) &&
 	    (!inode || !inode->i_fsnotify_marks) &&
-	    (!child || !child->i_fsnotify_marks))
+	    (!parent || !parent->i_fsnotify_marks))
 		return 0;
 
 	marks_mask = sb->s_fsnotify_mask;
@@ -485,8 +503,8 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir,
 		marks_mask |= mnt->mnt_fsnotify_mask;
 	if (inode)
 		marks_mask |= inode->i_fsnotify_mask;
-	if (child)
-		marks_mask |= child->i_fsnotify_mask;
+	if (parent)
+		marks_mask |= parent->i_fsnotify_mask;
 
 
 	/*
@@ -509,9 +527,9 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir,
 		iter_info.marks[FSNOTIFY_OBJ_TYPE_INODE] =
 			fsnotify_first_mark(&inode->i_fsnotify_marks);
 	}
-	if (child) {
-		iter_info.marks[FSNOTIFY_OBJ_TYPE_CHILD] =
-			fsnotify_first_mark(&child->i_fsnotify_marks);
+	if (parent) {
+		iter_info.marks[FSNOTIFY_OBJ_TYPE_PARENT] =
+			fsnotify_first_mark(&parent->i_fsnotify_marks);
 	}
 
 	/*
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 4ee3044eedd0..a2e42d3cd87c 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -278,7 +278,7 @@ static inline const struct path *fsnotify_data_path(const void *data,
 
 enum fsnotify_obj_type {
 	FSNOTIFY_OBJ_TYPE_INODE,
-	FSNOTIFY_OBJ_TYPE_CHILD,
+	FSNOTIFY_OBJ_TYPE_PARENT,
 	FSNOTIFY_OBJ_TYPE_VFSMOUNT,
 	FSNOTIFY_OBJ_TYPE_SB,
 	FSNOTIFY_OBJ_TYPE_COUNT,
@@ -286,7 +286,7 @@ enum fsnotify_obj_type {
 };
 
 #define FSNOTIFY_OBJ_TYPE_INODE_FL	(1U << FSNOTIFY_OBJ_TYPE_INODE)
-#define FSNOTIFY_OBJ_TYPE_CHILD_FL	(1U << FSNOTIFY_OBJ_TYPE_CHILD)
+#define FSNOTIFY_OBJ_TYPE_PARENT_FL	(1U << FSNOTIFY_OBJ_TYPE_PARENT)
 #define FSNOTIFY_OBJ_TYPE_VFSMOUNT_FL	(1U << FSNOTIFY_OBJ_TYPE_VFSMOUNT)
 #define FSNOTIFY_OBJ_TYPE_SB_FL		(1U << FSNOTIFY_OBJ_TYPE_SB)
 #define FSNOTIFY_OBJ_ALL_TYPES_MASK	((1U << FSNOTIFY_OBJ_TYPE_COUNT) - 1)
@@ -331,7 +331,7 @@ static inline struct fsnotify_mark *fsnotify_iter_##name##_mark( \
 }
 
 FSNOTIFY_ITER_FUNCS(inode, INODE)
-FSNOTIFY_ITER_FUNCS(child, CHILD)
+FSNOTIFY_ITER_FUNCS(parent, PARENT)
 FSNOTIFY_ITER_FUNCS(vfsmount, VFSMOUNT)
 FSNOTIFY_ITER_FUNCS(sb, SB)
 
-- 
cgit v1.2.3


From 14486c82612a177cb910980c70ba900827ca0894 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Wed, 4 Nov 2020 15:46:41 +0200
Subject: rfkill: add a reason to the HW rfkill state

The WLAN device may exist yet not be usable. This can happen
when the WLAN device is controllable by both the host and
some platform internal component.
We need some arbritration that is vendor specific, but when
the device is not available for the host, we need to reflect
this state towards the user space.

Add a reason field to the rfkill object (and event) so that
userspace can know why the device is in rfkill: because some
other platform component currently owns the device, or
because the actual hw rfkill signal is asserted.

Capable userspace can now determine the reason for the rfkill
and possibly do some negotiation on a side band channel using
a proprietary protocol to gain ownership on the device in case
the device is owned by some other component. When the host
gains ownership on the device, the kernel can remove the
RFKILL_HARD_BLOCK_NOT_OWNER reason and the hw rfkill state
will be off. Then, the userspace can bring the device up and
start normal operation.

The rfkill_event structure is enlarged to include the additional
byte, it is now 9 bytes long. Old user space will ask to read
only 8 bytes so that the kernel can know not to feed them with
more data. When the user space writes 8 bytes, new kernels will
just read what is present in the file descriptor. This new byte
is read only from the userspace standpoint anyway.

If a new user space uses an old kernel, it'll ask to read 9 bytes
but will get only 8, and it'll know that it didn't get the new
state. When it'll write 9 bytes, the kernel will again ignore
this new byte which is read only from the userspace standpoint.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Link: https://lore.kernel.org/r/20201104134641.28816-1-emmanuel.grumbach@intel.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/rfkill.h      | 24 +++++++++++++++++++++++-
 include/uapi/linux/rfkill.h | 16 +++++++++++++++-
 net/rfkill/core.c           | 41 ++++++++++++++++++++++++++++++++++-------
 3 files changed, 72 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/rfkill.h b/include/linux/rfkill.h
index 8ad2487a86d5..231e06b74b50 100644
--- a/include/linux/rfkill.h
+++ b/include/linux/rfkill.h
@@ -137,6 +137,17 @@ void rfkill_unregister(struct rfkill *rfkill);
  */
 void rfkill_destroy(struct rfkill *rfkill);
 
+/**
+ * rfkill_set_hw_state_reason - Set the internal rfkill hardware block state
+ *	with a reason
+ * @rfkill: pointer to the rfkill class to modify.
+ * @blocked: the current hardware block state to set
+ * @reason: one of &enum rfkill_hard_block_reasons
+ *
+ * Prefer to use rfkill_set_hw_state if you don't need any special reason.
+ */
+bool rfkill_set_hw_state_reason(struct rfkill *rfkill,
+				bool blocked, unsigned long reason);
 /**
  * rfkill_set_hw_state - Set the internal rfkill hardware block state
  * @rfkill: pointer to the rfkill class to modify.
@@ -156,7 +167,11 @@ void rfkill_destroy(struct rfkill *rfkill);
  * should be blocked) so that drivers need not keep track of the soft
  * block state -- which they might not be able to.
  */
-bool rfkill_set_hw_state(struct rfkill *rfkill, bool blocked);
+static inline bool rfkill_set_hw_state(struct rfkill *rfkill, bool blocked)
+{
+	return rfkill_set_hw_state_reason(rfkill, blocked,
+					  RFKILL_HARD_BLOCK_SIGNAL);
+}
 
 /**
  * rfkill_set_sw_state - Set the internal rfkill software block state
@@ -256,6 +271,13 @@ static inline void rfkill_destroy(struct rfkill *rfkill)
 {
 }
 
+static inline bool rfkill_set_hw_state_reason(struct rfkill *rfkill,
+					      bool blocked,
+					      unsigned long reason)
+{
+	return blocked;
+}
+
 static inline bool rfkill_set_hw_state(struct rfkill *rfkill, bool blocked)
 {
 	return blocked;
diff --git a/include/uapi/linux/rfkill.h b/include/uapi/linux/rfkill.h
index 2e00dcebebd0..03e8af87b364 100644
--- a/include/uapi/linux/rfkill.h
+++ b/include/uapi/linux/rfkill.h
@@ -69,6 +69,16 @@ enum rfkill_operation {
 	RFKILL_OP_CHANGE_ALL,
 };
 
+/**
+ * enum rfkill_hard_block_reasons - hard block reasons
+ * @RFKILL_HARD_BLOCK_SIGNAL: the hardware rfkill signal is active
+ * @RFKILL_HARD_BLOCK_NOT_OWNER: the NIC is not owned by the host
+ */
+enum rfkill_hard_block_reasons {
+	RFKILL_HARD_BLOCK_SIGNAL	= 1 << 0,
+	RFKILL_HARD_BLOCK_NOT_OWNER	= 1 << 1,
+};
+
 /**
  * struct rfkill_event - events for userspace on /dev/rfkill
  * @idx: index of dev rfkill
@@ -76,6 +86,8 @@ enum rfkill_operation {
  * @op: operation code
  * @hard: hard state (0/1)
  * @soft: soft state (0/1)
+ * @hard_block_reasons: valid if hard is set. One or several reasons from
+ *	&enum rfkill_hard_block_reasons.
  *
  * Structure used for userspace communication on /dev/rfkill,
  * used for events from the kernel and control to the kernel.
@@ -84,7 +96,9 @@ struct rfkill_event {
 	__u32 idx;
 	__u8  type;
 	__u8  op;
-	__u8  soft, hard;
+	__u8  soft;
+	__u8  hard;
+	__u8  hard_block_reasons;
 } __attribute__((packed));
 
 /*
diff --git a/net/rfkill/core.c b/net/rfkill/core.c
index 97101c55763d..68d6ef9e59fc 100644
--- a/net/rfkill/core.c
+++ b/net/rfkill/core.c
@@ -40,6 +40,7 @@ struct rfkill {
 	enum rfkill_type	type;
 
 	unsigned long		state;
+	unsigned long		hard_block_reasons;
 
 	u32			idx;
 
@@ -265,6 +266,7 @@ static void rfkill_fill_event(struct rfkill_event *ev, struct rfkill *rfkill,
 	ev->hard = !!(rfkill->state & RFKILL_BLOCK_HW);
 	ev->soft = !!(rfkill->state & (RFKILL_BLOCK_SW |
 					RFKILL_BLOCK_SW_PREV));
+	ev->hard_block_reasons = rfkill->hard_block_reasons;
 	spin_unlock_irqrestore(&rfkill->lock, flags);
 }
 
@@ -522,19 +524,29 @@ bool rfkill_get_global_sw_state(const enum rfkill_type type)
 }
 #endif
 
-bool rfkill_set_hw_state(struct rfkill *rfkill, bool blocked)
+bool rfkill_set_hw_state_reason(struct rfkill *rfkill,
+				bool blocked, unsigned long reason)
 {
 	unsigned long flags;
 	bool ret, prev;
 
 	BUG_ON(!rfkill);
 
+	if (WARN(reason &
+	    ~(RFKILL_HARD_BLOCK_SIGNAL | RFKILL_HARD_BLOCK_NOT_OWNER),
+	    "hw_state reason not supported: 0x%lx", reason))
+		return blocked;
+
 	spin_lock_irqsave(&rfkill->lock, flags);
-	prev = !!(rfkill->state & RFKILL_BLOCK_HW);
-	if (blocked)
+	prev = !!(rfkill->hard_block_reasons & reason);
+	if (blocked) {
 		rfkill->state |= RFKILL_BLOCK_HW;
-	else
-		rfkill->state &= ~RFKILL_BLOCK_HW;
+		rfkill->hard_block_reasons |= reason;
+	} else {
+		rfkill->hard_block_reasons &= ~reason;
+		if (!rfkill->hard_block_reasons)
+			rfkill->state &= ~RFKILL_BLOCK_HW;
+	}
 	ret = !!(rfkill->state & RFKILL_BLOCK_ANY);
 	spin_unlock_irqrestore(&rfkill->lock, flags);
 
@@ -546,7 +558,7 @@ bool rfkill_set_hw_state(struct rfkill *rfkill, bool blocked)
 
 	return ret;
 }
-EXPORT_SYMBOL(rfkill_set_hw_state);
+EXPORT_SYMBOL(rfkill_set_hw_state_reason);
 
 static void __rfkill_set_sw_state(struct rfkill *rfkill, bool blocked)
 {
@@ -744,6 +756,16 @@ static ssize_t soft_store(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_RW(soft);
 
+static ssize_t hard_block_reasons_show(struct device *dev,
+				       struct device_attribute *attr,
+				       char *buf)
+{
+	struct rfkill *rfkill = to_rfkill(dev);
+
+	return sprintf(buf, "0x%lx\n", rfkill->hard_block_reasons);
+}
+static DEVICE_ATTR_RO(hard_block_reasons);
+
 static u8 user_state_from_blocked(unsigned long state)
 {
 	if (state & RFKILL_BLOCK_HW)
@@ -796,6 +818,7 @@ static struct attribute *rfkill_dev_attrs[] = {
 	&dev_attr_state.attr,
 	&dev_attr_soft.attr,
 	&dev_attr_hard.attr,
+	&dev_attr_hard_block_reasons.attr,
 	NULL,
 };
 ATTRIBUTE_GROUPS(rfkill_dev);
@@ -811,6 +834,7 @@ static int rfkill_dev_uevent(struct device *dev, struct kobj_uevent_env *env)
 {
 	struct rfkill *rfkill = to_rfkill(dev);
 	unsigned long flags;
+	unsigned long reasons;
 	u32 state;
 	int error;
 
@@ -823,10 +847,13 @@ static int rfkill_dev_uevent(struct device *dev, struct kobj_uevent_env *env)
 		return error;
 	spin_lock_irqsave(&rfkill->lock, flags);
 	state = rfkill->state;
+	reasons = rfkill->hard_block_reasons;
 	spin_unlock_irqrestore(&rfkill->lock, flags);
 	error = add_uevent_var(env, "RFKILL_STATE=%d",
 			       user_state_from_blocked(state));
-	return error;
+	if (error)
+		return error;
+	return add_uevent_var(env, "RFKILL_HW_BLOCK_REASON=0x%lx", reasons);
 }
 
 void rfkill_pause_polling(struct rfkill *rfkill)
-- 
cgit v1.2.3


From d6587602c59974a2eda35e8ed70a4f5970380be8 Mon Sep 17 00:00:00 2001
From: Ilan Peer <ilan.peer@intel.com>
Date: Sun, 29 Nov 2020 17:30:46 +0200
Subject: cfg80211: Parse SAE H2E only membership selector

This extends the support for drivers that rebuild IEs in the
FW (same as with HT/VHT/HE).

Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20201129172929.4012647275f3.I1a93ae71c57ef0b6f58f99d47fce919d19d65ff0@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 1 +
 include/net/cfg80211.h    | 3 ++-
 net/wireless/nl80211.c    | 2 ++
 3 files changed, 5 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 5e8cc9c3d45a..cbd294239430 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1261,6 +1261,7 @@ struct ieee80211_mgmt {
 #define BSS_MEMBERSHIP_SELECTOR_HT_PHY	127
 #define BSS_MEMBERSHIP_SELECTOR_VHT_PHY	126
 #define BSS_MEMBERSHIP_SELECTOR_HE_PHY	122
+#define BSS_MEMBERSHIP_SELECTOR_SAE_H2E 123
 
 /* mgmt header + 1 byte category code */
 #define IEEE80211_MIN_ACTION_SIZE offsetof(struct ieee80211_mgmt, u.action.u)
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 78c763dfc99a..f3dfb26b50b9 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1187,6 +1187,7 @@ enum cfg80211_ap_settings_flags {
  * @vht_required: stations must support VHT
  * @twt_responder: Enable Target Wait Time
  * @he_required: stations must support HE
+ * @sae_h2e_required: stations must support direct H2E technique in SAE
  * @flags: flags, as defined in enum cfg80211_ap_settings_flags
  * @he_obss_pd: OBSS Packet Detection settings
  * @he_bss_color: BSS Color settings
@@ -1218,7 +1219,7 @@ struct cfg80211_ap_settings {
 	const struct ieee80211_vht_cap *vht_cap;
 	const struct ieee80211_he_cap_elem *he_cap;
 	const struct ieee80211_he_operation *he_oper;
-	bool ht_required, vht_required, he_required;
+	bool ht_required, vht_required, he_required, sae_h2e_required;
 	bool twt_responder;
 	u32 flags;
 	struct ieee80211_he_obss_pd he_obss_pd;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 57f615a6d2f3..8e7320a868d3 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -5017,6 +5017,8 @@ static void nl80211_check_ap_rate_selectors(struct cfg80211_ap_settings *params,
 			params->vht_required = true;
 		if (rates[2 + i] == BSS_MEMBERSHIP_SELECTOR_HE_PHY)
 			params->he_required = true;
+		if (rates[2 + i] == BSS_MEMBERSHIP_SELECTOR_SAE_H2E)
+			params->sae_h2e_required = true;
 	}
 }
 
-- 
cgit v1.2.3


From 9850742470804b2cc6a6543bd8f5822eeb5fdbc0 Mon Sep 17 00:00:00 2001
From: Avraham Stern <avraham.stern@intel.com>
Date: Sun, 29 Nov 2020 17:30:52 +0200
Subject: ieee80211: update reduced neighbor report TBTT info length

A new field (20MHz PSD - 1 byte) was added to the RNR TBTT info field.
Adjust the expected TBTT info length accordingly.

Signed-off-by: Avraham Stern <avraham.stern@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/iwlwifi.20201129172929.b503adccce6a.Ie684e1d3039c111bf2d521bf762aaec3f7a24d2e@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index cbd294239430..72ff75fb1971 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -3836,15 +3836,15 @@ static inline bool for_each_element_completed(const struct element *element,
 #define WLAN_RSNX_CAPA_SAE_H2E BIT(5)
 
 /*
- * reduced neighbor report, based on Draft P802.11ax_D5.0,
- * section 9.4.2.170
+ * reduced neighbor report, based on Draft P802.11ax_D6.1,
+ * section 9.4.2.170 and accepted contributions.
  */
 #define IEEE80211_AP_INFO_TBTT_HDR_TYPE				0x03
 #define IEEE80211_AP_INFO_TBTT_HDR_FILTERED			0x04
 #define IEEE80211_AP_INFO_TBTT_HDR_COLOC			0x08
 #define IEEE80211_AP_INFO_TBTT_HDR_COUNT			0xF0
-#define IEEE80211_TBTT_INFO_OFFSET_BSSID_BSS_PARAM		8
-#define IEEE80211_TBTT_INFO_OFFSET_BSSID_SSSID_BSS_PARAM	12
+#define IEEE80211_TBTT_INFO_OFFSET_BSSID_BSS_PARAM		9
+#define IEEE80211_TBTT_INFO_OFFSET_BSSID_SSSID_BSS_PARAM	13
 
 #define IEEE80211_RNR_TBTT_PARAMS_OCT_RECOMMENDED		0x01
 #define IEEE80211_RNR_TBTT_PARAMS_SAME_SSID			0x02
-- 
cgit v1.2.3


From 84e0d87c9944eb36ae6037af5cb6905f67c074c5 Mon Sep 17 00:00:00 2001
From: Lukasz Luba <lukasz.luba@arm.com>
Date: Thu, 10 Dec 2020 14:30:12 +0000
Subject: thermal: devfreq_cooling: add new registration functions with Energy
 Model

The Energy Model (EM) framework supports devices such as Devfreq. Create
new registration function which automatically register EM for the thermal
devfreq_cooling devices. This patch prepares the code for coming changes
which are going to replace old power model with the new EM.

Reviewed-by: Ionela Voinescu <ionela.voinescu@arm.com>
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Link: https://lore.kernel.org/r/20201210143014.24685-4-lukasz.luba@arm.com
---
 drivers/thermal/devfreq_cooling.c | 54 ++++++++++++++++++++++++++++++++++++++-
 include/linux/devfreq_cooling.h   | 10 ++++++++
 2 files changed, 63 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/thermal/devfreq_cooling.c b/drivers/thermal/devfreq_cooling.c
index afcebadbad24..6cea027d89a3 100644
--- a/drivers/thermal/devfreq_cooling.c
+++ b/drivers/thermal/devfreq_cooling.c
@@ -12,6 +12,7 @@
 
 #include <linux/devfreq.h>
 #include <linux/devfreq_cooling.h>
+#include <linux/energy_model.h>
 #include <linux/export.h>
 #include <linux/idr.h>
 #include <linux/slab.h>
@@ -576,22 +577,73 @@ struct thermal_cooling_device *devfreq_cooling_register(struct devfreq *df)
 }
 EXPORT_SYMBOL_GPL(devfreq_cooling_register);
 
+/**
+ * devfreq_cooling_em_register_power() - Register devfreq cooling device with
+ *		power information and automatically register Energy Model (EM)
+ * @df:		Pointer to devfreq device.
+ * @dfc_power:	Pointer to devfreq_cooling_power.
+ *
+ * Register a devfreq cooling device and automatically register EM. The
+ * available OPPs must be registered for the device.
+ *
+ * If @dfc_power is provided, the cooling device is registered with the
+ * power extensions. It is using the simple Energy Model which requires
+ * "dynamic-power-coefficient" a devicetree property. To not break drivers
+ * which miss that DT property, the function won't bail out when the EM
+ * registration failed. The cooling device will be registered if everything
+ * else is OK.
+ */
+struct thermal_cooling_device *
+devfreq_cooling_em_register(struct devfreq *df,
+			    struct devfreq_cooling_power *dfc_power)
+{
+	struct thermal_cooling_device *cdev;
+	struct device *dev;
+	int ret;
+
+	if (IS_ERR_OR_NULL(df))
+		return ERR_PTR(-EINVAL);
+
+	dev = df->dev.parent;
+
+	ret = dev_pm_opp_of_register_em(dev, NULL);
+	if (ret)
+		dev_dbg(dev, "Unable to register EM for devfreq cooling device (%d)\n",
+			ret);
+
+	cdev = of_devfreq_cooling_register_power(dev->of_node, df, dfc_power);
+
+	if (IS_ERR_OR_NULL(cdev))
+		em_dev_unregister_perf_domain(dev);
+
+	return cdev;
+}
+EXPORT_SYMBOL_GPL(devfreq_cooling_em_register);
+
 /**
  * devfreq_cooling_unregister() - Unregister devfreq cooling device.
  * @cdev: Pointer to devfreq cooling device to unregister.
+ *
+ * Unregisters devfreq cooling device and related Energy Model if it was
+ * present.
  */
 void devfreq_cooling_unregister(struct thermal_cooling_device *cdev)
 {
 	struct devfreq_cooling_device *dfc;
+	struct device *dev;
 
-	if (!cdev)
+	if (IS_ERR_OR_NULL(cdev))
 		return;
 
 	dfc = cdev->devdata;
+	dev = dfc->devfreq->dev.parent;
 
 	thermal_cooling_device_unregister(dfc->cdev);
 	ida_simple_remove(&devfreq_ida, dfc->id);
 	dev_pm_qos_remove_request(&dfc->req_max_freq);
+
+	em_dev_unregister_perf_domain(dev);
+
 	kfree(dfc->power_table);
 	kfree(dfc->freq_table);
 
diff --git a/include/linux/devfreq_cooling.h b/include/linux/devfreq_cooling.h
index 9df2dfca68dd..7a9fbcc7b265 100644
--- a/include/linux/devfreq_cooling.h
+++ b/include/linux/devfreq_cooling.h
@@ -65,6 +65,9 @@ struct thermal_cooling_device *
 of_devfreq_cooling_register(struct device_node *np, struct devfreq *df);
 struct thermal_cooling_device *devfreq_cooling_register(struct devfreq *df);
 void devfreq_cooling_unregister(struct thermal_cooling_device *dfc);
+struct thermal_cooling_device *
+devfreq_cooling_em_register(struct devfreq *df,
+			    struct devfreq_cooling_power *dfc_power);
 
 #else /* !CONFIG_DEVFREQ_THERMAL */
 
@@ -87,6 +90,13 @@ devfreq_cooling_register(struct devfreq *df)
 	return ERR_PTR(-EINVAL);
 }
 
+static inline struct thermal_cooling_device *
+devfreq_cooling_em_register(struct devfreq *df,
+			    struct devfreq_cooling_power *dfc_power)
+{
+	return ERR_PTR(-EINVAL);
+}
+
 static inline void
 devfreq_cooling_unregister(struct thermal_cooling_device *dfc)
 {
-- 
cgit v1.2.3


From 615510fe13bd2434610193f1acab53027d5146d6 Mon Sep 17 00:00:00 2001
From: Lukasz Luba <lukasz.luba@arm.com>
Date: Thu, 10 Dec 2020 14:30:13 +0000
Subject: thermal: devfreq_cooling: remove old power model and use EM

Remove old power model and use new Energy Model to calculate the power
budget. It drops static + dynamic power calculations and power table
in order to use Energy Model performance domain data. This model
should be easy to use and could find more users. It is also less
complicated to setup the needed structures.

Reviewed-by: Ionela Voinescu <ionela.voinescu@arm.com>
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Link: https://lore.kernel.org/r/20201210143014.24685-5-lukasz.luba@arm.com
---
 drivers/thermal/devfreq_cooling.c | 307 ++++++++++++--------------------------
 include/linux/devfreq_cooling.h   |  17 ---
 2 files changed, 97 insertions(+), 227 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/thermal/devfreq_cooling.c b/drivers/thermal/devfreq_cooling.c
index 6cea027d89a3..df1049a34777 100644
--- a/drivers/thermal/devfreq_cooling.c
+++ b/drivers/thermal/devfreq_cooling.c
@@ -34,20 +34,17 @@ static DEFINE_IDA(devfreq_ida);
  * @cdev:	Pointer to associated thermal cooling device.
  * @devfreq:	Pointer to associated devfreq device.
  * @cooling_state:	Current cooling state.
- * @power_table:	Pointer to table with maximum power draw for each
- *			cooling state. State is the index into the table, and
- *			the power is in mW.
  * @freq_table:	Pointer to a table with the frequencies sorted in descending
  *		order.  You can index the table by cooling device state
- * @freq_table_size:	Size of the @freq_table and @power_table
- * @power_ops:	Pointer to devfreq_cooling_power, used to generate the
- *		@power_table.
+ * @max_state:	It is the last index, that is, one less than the number of the
+ *		OPPs
+ * @power_ops:	Pointer to devfreq_cooling_power, a more precised model.
  * @res_util:	Resource utilization scaling factor for the power.
  *		It is multiplied by 100 to minimize the error. It is used
  *		for estimation of the power budget instead of using
- *		'utilization' (which is	'busy_time / 'total_time').
- *		The 'res_util' range is from 100 to (power_table[state] * 100)
- *		for the corresponding 'state'.
+ *		'utilization' (which is	'busy_time' / 'total_time').
+ *		The 'res_util' range is from 100 to power * 100	for the
+ *		corresponding 'state'.
  * @capped_state:	index to cooling state with in dynamic power budget
  * @req_max_freq:	PM QoS request for limiting the maximum frequency
  *			of the devfreq device.
@@ -57,9 +54,8 @@ struct devfreq_cooling_device {
 	struct thermal_cooling_device *cdev;
 	struct devfreq *devfreq;
 	unsigned long cooling_state;
-	u32 *power_table;
 	u32 *freq_table;
-	size_t freq_table_size;
+	size_t max_state;
 	struct devfreq_cooling_power *power_ops;
 	u32 res_util;
 	int capped_state;
@@ -71,7 +67,7 @@ static int devfreq_cooling_get_max_state(struct thermal_cooling_device *cdev,
 {
 	struct devfreq_cooling_device *dfc = cdev->devdata;
 
-	*state = dfc->freq_table_size - 1;
+	*state = dfc->max_state;
 
 	return 0;
 }
@@ -93,16 +89,22 @@ static int devfreq_cooling_set_cur_state(struct thermal_cooling_device *cdev,
 	struct devfreq *df = dfc->devfreq;
 	struct device *dev = df->dev.parent;
 	unsigned long freq;
+	int perf_idx;
 
 	if (state == dfc->cooling_state)
 		return 0;
 
 	dev_dbg(dev, "Setting cooling state %lu\n", state);
 
-	if (state >= dfc->freq_table_size)
+	if (state > dfc->max_state)
 		return -EINVAL;
 
-	freq = dfc->freq_table[state];
+	if (dev->em_pd) {
+		perf_idx = dfc->max_state - state;
+		freq = dev->em_pd->table[perf_idx].frequency * 1000;
+	} else {
+		freq = dfc->freq_table[state];
+	}
 
 	dev_pm_qos_update_request(&dfc->req_max_freq,
 				  DIV_ROUND_UP(freq, HZ_PER_KHZ));
@@ -113,24 +115,23 @@ static int devfreq_cooling_set_cur_state(struct thermal_cooling_device *cdev,
 }
 
 /**
- * freq_get_state() - get the cooling state corresponding to a frequency
- * @dfc:	Pointer to devfreq cooling device
- * @freq:	frequency in Hz
+ * get_perf_idx() - get the performance index corresponding to a frequency
+ * @em_pd:	Pointer to device's Energy Model
+ * @freq:	frequency in kHz
  *
- * Return: the cooling state associated with the @freq, or
- * THERMAL_CSTATE_INVALID if it wasn't found.
+ * Return: the performance index associated with the @freq, or
+ * -EINVAL if it wasn't found.
  */
-static unsigned long
-freq_get_state(struct devfreq_cooling_device *dfc, unsigned long freq)
+static int get_perf_idx(struct em_perf_domain *em_pd, unsigned long freq)
 {
 	int i;
 
-	for (i = 0; i < dfc->freq_table_size; i++) {
-		if (dfc->freq_table[i] == freq)
+	for (i = 0; i < em_pd->nr_perf_states; i++) {
+		if (em_pd->table[i].frequency == freq)
 			return i;
 	}
 
-	return THERMAL_CSTATE_INVALID;
+	return -EINVAL;
 }
 
 static unsigned long get_voltage(struct devfreq *df, unsigned long freq)
@@ -161,73 +162,6 @@ static unsigned long get_voltage(struct devfreq *df, unsigned long freq)
 	return voltage;
 }
 
-/**
- * get_static_power() - calculate the static power
- * @dfc:	Pointer to devfreq cooling device
- * @freq:	Frequency in Hz
- *
- * Calculate the static power in milliwatts using the supplied
- * get_static_power().  The current voltage is calculated using the
- * OPP library.  If no get_static_power() was supplied, assume the
- * static power is negligible.
- */
-static unsigned long
-get_static_power(struct devfreq_cooling_device *dfc, unsigned long freq)
-{
-	struct devfreq *df = dfc->devfreq;
-	unsigned long voltage;
-
-	if (!dfc->power_ops->get_static_power)
-		return 0;
-
-	voltage = get_voltage(df, freq);
-
-	if (voltage == 0)
-		return 0;
-
-	return dfc->power_ops->get_static_power(df, voltage);
-}
-
-/**
- * get_dynamic_power - calculate the dynamic power
- * @dfc:	Pointer to devfreq cooling device
- * @freq:	Frequency in Hz
- * @voltage:	Voltage in millivolts
- *
- * Calculate the dynamic power in milliwatts consumed by the device at
- * frequency @freq and voltage @voltage.  If the get_dynamic_power()
- * was supplied as part of the devfreq_cooling_power struct, then that
- * function is used.  Otherwise, a simple power model (Pdyn = Coeff *
- * Voltage^2 * Frequency) is used.
- */
-static unsigned long
-get_dynamic_power(struct devfreq_cooling_device *dfc, unsigned long freq,
-		  unsigned long voltage)
-{
-	u64 power;
-	u32 freq_mhz;
-	struct devfreq_cooling_power *dfc_power = dfc->power_ops;
-
-	if (dfc_power->get_dynamic_power)
-		return dfc_power->get_dynamic_power(dfc->devfreq, freq,
-						    voltage);
-
-	freq_mhz = freq / 1000000;
-	power = (u64)dfc_power->dyn_power_coeff * freq_mhz * voltage * voltage;
-	do_div(power, 1000000000);
-
-	return power;
-}
-
-
-static inline unsigned long get_total_power(struct devfreq_cooling_device *dfc,
-					    unsigned long freq,
-					    unsigned long voltage)
-{
-	return get_static_power(dfc, freq) + get_dynamic_power(dfc, freq,
-							       voltage);
-}
-
 static void _normalize_load(struct devfreq_dev_status *status)
 {
 	if (status->total_time > 0xfffff) {
@@ -247,13 +181,12 @@ static int devfreq_cooling_get_requested_power(struct thermal_cooling_device *cd
 {
 	struct devfreq_cooling_device *dfc = cdev->devdata;
 	struct devfreq *df = dfc->devfreq;
+	struct device *dev = df->dev.parent;
 	struct devfreq_dev_status status;
 	unsigned long state;
 	unsigned long freq;
 	unsigned long voltage;
-	u32 dyn_power = 0;
-	u32 static_power = 0;
-	int res;
+	int res, perf_idx;
 
 	mutex_lock(&df->lock);
 	status = df->last_status;
@@ -261,13 +194,7 @@ static int devfreq_cooling_get_requested_power(struct thermal_cooling_device *cd
 
 	freq = status.current_frequency;
 
-	state = freq_get_state(dfc, freq);
-	if (state == THERMAL_CSTATE_INVALID) {
-		res = -EAGAIN;
-		goto fail;
-	}
-
-	if (dfc->power_ops->get_real_power) {
+	if (dfc->power_ops && dfc->power_ops->get_real_power) {
 		voltage = get_voltage(df, freq);
 		if (voltage == 0) {
 			res = -EINVAL;
@@ -277,7 +204,7 @@ static int devfreq_cooling_get_requested_power(struct thermal_cooling_device *cd
 		res = dfc->power_ops->get_real_power(df, power, freq, voltage);
 		if (!res) {
 			state = dfc->capped_state;
-			dfc->res_util = dfc->power_table[state];
+			dfc->res_util = dev->em_pd->table[state].power;
 			dfc->res_util *= SCALE_ERROR_MITIGATION;
 
 			if (*power > 1)
@@ -286,17 +213,19 @@ static int devfreq_cooling_get_requested_power(struct thermal_cooling_device *cd
 			goto fail;
 		}
 	} else {
-		dyn_power = dfc->power_table[state];
+		/* Energy Model frequencies are in kHz */
+		perf_idx = get_perf_idx(dev->em_pd, freq / 1000);
+		if (perf_idx < 0) {
+			res = -EAGAIN;
+			goto fail;
+		}
 
 		_normalize_load(&status);
 
-		/* Scale dynamic power for utilization */
-		dyn_power *= status.busy_time;
-		dyn_power >>= 10;
-		/* Get static power */
-		static_power = get_static_power(dfc, freq);
-
-		*power = dyn_power + static_power;
+		/* Scale power for utilization */
+		*power = dev->em_pd->table[perf_idx].power;
+		*power *= status.busy_time;
+		*power >>= 10;
 	}
 
 	trace_thermal_power_devfreq_get_power(cdev, &status, freq, *power);
@@ -309,20 +238,19 @@ fail:
 }
 
 static int devfreq_cooling_state2power(struct thermal_cooling_device *cdev,
-				       unsigned long state,
-				       u32 *power)
+				       unsigned long state, u32 *power)
 {
 	struct devfreq_cooling_device *dfc = cdev->devdata;
-	unsigned long freq;
-	u32 static_power;
+	struct devfreq *df = dfc->devfreq;
+	struct device *dev = df->dev.parent;
+	int perf_idx;
 
-	if (state >= dfc->freq_table_size)
+	if (state > dfc->max_state)
 		return -EINVAL;
 
-	freq = dfc->freq_table[state];
-	static_power = get_static_power(dfc, freq);
+	perf_idx = dfc->max_state - state;
+	*power = dev->em_pd->table[perf_idx].power;
 
-	*power = dfc->power_table[state] + static_power;
 	return 0;
 }
 
@@ -331,10 +259,9 @@ static int devfreq_cooling_power2state(struct thermal_cooling_device *cdev,
 {
 	struct devfreq_cooling_device *dfc = cdev->devdata;
 	struct devfreq *df = dfc->devfreq;
+	struct device *dev = df->dev.parent;
 	struct devfreq_dev_status status;
 	unsigned long freq;
-	s32 dyn_power;
-	u32 static_power;
 	s32 est_power;
 	int i;
 
@@ -344,32 +271,28 @@ static int devfreq_cooling_power2state(struct thermal_cooling_device *cdev,
 
 	freq = status.current_frequency;
 
-	if (dfc->power_ops->get_real_power) {
+	if (dfc->power_ops && dfc->power_ops->get_real_power) {
 		/* Scale for resource utilization */
 		est_power = power * dfc->res_util;
 		est_power /= SCALE_ERROR_MITIGATION;
 	} else {
-		static_power = get_static_power(dfc, freq);
-
-		dyn_power = power - static_power;
-		dyn_power = dyn_power > 0 ? dyn_power : 0;
-
 		/* Scale dynamic power for utilization */
 		_normalize_load(&status);
-		dyn_power <<= 10;
-		est_power = dyn_power / status.busy_time;
+		est_power = power << 10;
+		est_power /= status.busy_time;
 	}
 
 	/*
 	 * Find the first cooling state that is within the power
-	 * budget for dynamic power.
+	 * budget. The EM power table is sorted ascending.
 	 */
-	for (i = 0; i < dfc->freq_table_size - 1; i++)
-		if (est_power >= dfc->power_table[i])
+	for (i = dfc->max_state; i > 0; i--)
+		if (est_power >= dev->em_pd->table[i].power)
 			break;
 
-	*state = i;
-	dfc->capped_state = i;
+	*state = dfc->max_state - i;
+	dfc->capped_state = *state;
+
 	trace_thermal_power_devfreq_limit(cdev, freq, *state, power);
 	return 0;
 }
@@ -381,91 +304,43 @@ static struct thermal_cooling_device_ops devfreq_cooling_ops = {
 };
 
 /**
- * devfreq_cooling_gen_tables() - Generate power and freq tables.
- * @dfc: Pointer to devfreq cooling device.
- *
- * Generate power and frequency tables: the power table hold the
- * device's maximum power usage at each cooling state (OPP).  The
- * static and dynamic power using the appropriate voltage and
- * frequency for the state, is acquired from the struct
- * devfreq_cooling_power, and summed to make the maximum power draw.
- *
- * The frequency table holds the frequencies in descending order.
- * That way its indexed by cooling device state.
+ * devfreq_cooling_gen_tables() - Generate frequency table.
+ * @dfc:	Pointer to devfreq cooling device.
+ * @num_opps:	Number of OPPs
  *
- * The tables are malloced, and pointers put in dfc.  They must be
- * freed when unregistering the devfreq cooling device.
+ * Generate frequency table which holds the frequencies in descending
+ * order. That way its indexed by cooling device state. This is for
+ * compatibility with drivers which do not register Energy Model.
  *
  * Return: 0 on success, negative error code on failure.
  */
-static int devfreq_cooling_gen_tables(struct devfreq_cooling_device *dfc)
+static int devfreq_cooling_gen_tables(struct devfreq_cooling_device *dfc,
+				      int num_opps)
 {
 	struct devfreq *df = dfc->devfreq;
 	struct device *dev = df->dev.parent;
-	int ret, num_opps;
 	unsigned long freq;
-	u32 *power_table = NULL;
-	u32 *freq_table;
 	int i;
 
-	num_opps = dev_pm_opp_get_opp_count(dev);
-
-	if (dfc->power_ops) {
-		power_table = kcalloc(num_opps, sizeof(*power_table),
-				      GFP_KERNEL);
-		if (!power_table)
-			return -ENOMEM;
-	}
-
-	freq_table = kcalloc(num_opps, sizeof(*freq_table),
+	dfc->freq_table = kcalloc(num_opps, sizeof(*dfc->freq_table),
 			     GFP_KERNEL);
-	if (!freq_table) {
-		ret = -ENOMEM;
-		goto free_power_table;
-	}
+	if (!dfc->freq_table)
+		return -ENOMEM;
 
 	for (i = 0, freq = ULONG_MAX; i < num_opps; i++, freq--) {
-		unsigned long power, voltage;
 		struct dev_pm_opp *opp;
 
 		opp = dev_pm_opp_find_freq_floor(dev, &freq);
 		if (IS_ERR(opp)) {
-			ret = PTR_ERR(opp);
-			goto free_tables;
+			kfree(dfc->freq_table);
+			return PTR_ERR(opp);
 		}
 
-		voltage = dev_pm_opp_get_voltage(opp) / 1000; /* mV */
 		dev_pm_opp_put(opp);
-
-		if (dfc->power_ops) {
-			if (dfc->power_ops->get_real_power)
-				power = get_total_power(dfc, freq, voltage);
-			else
-				power = get_dynamic_power(dfc, freq, voltage);
-
-			dev_dbg(dev, "Power table: %lu MHz @ %lu mV: %lu = %lu mW\n",
-				freq / 1000000, voltage, power, power);
-
-			power_table[i] = power;
-		}
-
-		freq_table[i] = freq;
+		dfc->freq_table[i] = freq;
 	}
 
-	if (dfc->power_ops)
-		dfc->power_table = power_table;
-
-	dfc->freq_table = freq_table;
-	dfc->freq_table_size = num_opps;
-
 	return 0;
-
-free_tables:
-	kfree(freq_table);
-free_power_table:
-	kfree(power_table);
-
-	return ret;
 }
 
 /**
@@ -488,9 +363,10 @@ of_devfreq_cooling_register_power(struct device_node *np, struct devfreq *df,
 				  struct devfreq_cooling_power *dfc_power)
 {
 	struct thermal_cooling_device *cdev;
+	struct device *dev = df->dev.parent;
 	struct devfreq_cooling_device *dfc;
 	char dev_name[THERMAL_NAME_LENGTH];
-	int err;
+	int err, num_opps;
 
 	dfc = kzalloc(sizeof(*dfc), GFP_KERNEL);
 	if (!dfc)
@@ -498,28 +374,44 @@ of_devfreq_cooling_register_power(struct device_node *np, struct devfreq *df,
 
 	dfc->devfreq = df;
 
-	if (dfc_power) {
-		dfc->power_ops = dfc_power;
-
+	if (dev->em_pd) {
 		devfreq_cooling_ops.get_requested_power =
 			devfreq_cooling_get_requested_power;
 		devfreq_cooling_ops.state2power = devfreq_cooling_state2power;
 		devfreq_cooling_ops.power2state = devfreq_cooling_power2state;
+
+		dfc->power_ops = dfc_power;
+
+		num_opps = em_pd_nr_perf_states(dev->em_pd);
+	} else {
+		/* Backward compatibility for drivers which do not use IPA */
+		dev_dbg(dev, "missing EM for cooling device\n");
+
+		num_opps = dev_pm_opp_get_opp_count(dev);
+
+		err = devfreq_cooling_gen_tables(dfc, num_opps);
+		if (err)
+			goto free_dfc;
 	}
 
-	err = devfreq_cooling_gen_tables(dfc);
-	if (err)
+	if (num_opps <= 0) {
+		err = -EINVAL;
 		goto free_dfc;
+	}
+
+	/* max_state is an index, not a counter */
+	dfc->max_state = num_opps - 1;
 
-	err = dev_pm_qos_add_request(df->dev.parent, &dfc->req_max_freq,
+	err = dev_pm_qos_add_request(dev, &dfc->req_max_freq,
 				     DEV_PM_QOS_MAX_FREQUENCY,
 				     PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE);
 	if (err < 0)
-		goto free_tables;
+		goto free_table;
 
 	err = ida_simple_get(&devfreq_ida, 0, 0, GFP_KERNEL);
 	if (err < 0)
 		goto remove_qos_req;
+
 	dfc->id = err;
 
 	snprintf(dev_name, sizeof(dev_name), "thermal-devfreq-%d", dfc->id);
@@ -528,7 +420,7 @@ of_devfreq_cooling_register_power(struct device_node *np, struct devfreq *df,
 						  &devfreq_cooling_ops);
 	if (IS_ERR(cdev)) {
 		err = PTR_ERR(cdev);
-		dev_err(df->dev.parent,
+		dev_err(dev,
 			"Failed to register devfreq cooling device (%d)\n",
 			err);
 		goto release_ida;
@@ -540,12 +432,9 @@ of_devfreq_cooling_register_power(struct device_node *np, struct devfreq *df,
 
 release_ida:
 	ida_simple_remove(&devfreq_ida, dfc->id);
-
 remove_qos_req:
 	dev_pm_qos_remove_request(&dfc->req_max_freq);
-
-free_tables:
-	kfree(dfc->power_table);
+free_table:
 	kfree(dfc->freq_table);
 free_dfc:
 	kfree(dfc);
@@ -644,9 +533,7 @@ void devfreq_cooling_unregister(struct thermal_cooling_device *cdev)
 
 	em_dev_unregister_perf_domain(dev);
 
-	kfree(dfc->power_table);
 	kfree(dfc->freq_table);
-
 	kfree(dfc);
 }
 EXPORT_SYMBOL_GPL(devfreq_cooling_unregister);
diff --git a/include/linux/devfreq_cooling.h b/include/linux/devfreq_cooling.h
index 7a9fbcc7b265..14baa73fc2de 100644
--- a/include/linux/devfreq_cooling.h
+++ b/include/linux/devfreq_cooling.h
@@ -16,17 +16,6 @@
 
 /**
  * struct devfreq_cooling_power - Devfreq cooling power ops
- * @get_static_power:	Take voltage, in mV, and return the static power
- *			in mW.  If NULL, the static power is assumed
- *			to be 0.
- * @get_dynamic_power:	Take voltage, in mV, and frequency, in HZ, and
- *			return the dynamic power draw in mW.  If NULL,
- *			a simple power model is used.
- * @dyn_power_coeff:	Coefficient for the simple dynamic power model in
- *			mW/(MHz mV mV).
- *			If get_dynamic_power() is NULL, then the
- *			dynamic power is calculated as
- *			@dyn_power_coeff * frequency * voltage^2
  * @get_real_power:	When this is set, the framework uses it to ask the
  *			device driver for the actual power.
  *			Some devices have more sophisticated methods
@@ -46,14 +35,8 @@
  *			max total (static + dynamic) power value for each OPP.
  */
 struct devfreq_cooling_power {
-	unsigned long (*get_static_power)(struct devfreq *devfreq,
-					  unsigned long voltage);
-	unsigned long (*get_dynamic_power)(struct devfreq *devfreq,
-					   unsigned long freq,
-					   unsigned long voltage);
 	int (*get_real_power)(struct devfreq *df, u32 *power,
 			      unsigned long freq, unsigned long voltage);
-	unsigned long dyn_power_coeff;
 };
 
 #ifdef CONFIG_DEVFREQ_THERMAL
-- 
cgit v1.2.3


From d7203eedf4f68e9909fd489453168a9d26bf0c3d Mon Sep 17 00:00:00 2001
From: Daniel Lezcano <daniel.lezcano@linaro.org>
Date: Thu, 10 Dec 2020 13:15:11 +0100
Subject: thermal/core: Add critical and hot ops

Currently there is no way to the sensors to directly call an ops in
interrupt mode without calling thermal_zone_device_update assuming all
the trip points are defined.

A sensor may want to do something special if a trip point is hot or
critical.

This patch adds the critical and hot ops to the thermal zone device,
so a sensor can directly invoke them or let the thermal framework to
call the sensor specific ones.

Tested-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
Link: https://lore.kernel.org/r/20201210121514.25760-2-daniel.lezcano@linaro.org
---
 drivers/thermal/thermal_core.c | 43 ++++++++++++++++++++++++++----------------
 include/linux/thermal.h        |  3 +++
 2 files changed, 30 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 64de09861c05..4a291d205d5c 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -380,6 +380,25 @@ static void thermal_emergency_poweroff(void)
 			      msecs_to_jiffies(poweroff_delay_ms));
 }
 
+void thermal_zone_device_critical(struct thermal_zone_device *tz)
+{
+	dev_emerg(&tz->device, "%s: critical temperature reached, "
+		  "shutting down\n", tz->type);
+
+	mutex_lock(&poweroff_lock);
+	if (!power_off_triggered) {
+		/*
+		 * Queue a backup emergency shutdown in the event of
+		 * orderly_poweroff failure
+		 */
+		thermal_emergency_poweroff();
+		orderly_poweroff(true);
+		power_off_triggered = true;
+	}
+	mutex_unlock(&poweroff_lock);
+}
+EXPORT_SYMBOL(thermal_zone_device_critical);
+
 static void handle_critical_trips(struct thermal_zone_device *tz,
 				  int trip, enum thermal_trip_type trip_type)
 {
@@ -396,22 +415,10 @@ static void handle_critical_trips(struct thermal_zone_device *tz,
 	if (tz->ops->notify)
 		tz->ops->notify(tz, trip, trip_type);
 
-	if (trip_type == THERMAL_TRIP_CRITICAL) {
-		dev_emerg(&tz->device,
-			  "critical temperature reached (%d C), shutting down\n",
-			  tz->temperature / 1000);
-		mutex_lock(&poweroff_lock);
-		if (!power_off_triggered) {
-			/*
-			 * Queue a backup emergency shutdown in the event of
-			 * orderly_poweroff failure
-			 */
-			thermal_emergency_poweroff();
-			orderly_poweroff(true);
-			power_off_triggered = true;
-		}
-		mutex_unlock(&poweroff_lock);
-	}
+	if (trip_type == THERMAL_TRIP_HOT && tz->ops->hot)
+		tz->ops->hot(tz);
+	else if (trip_type == THERMAL_TRIP_CRITICAL)
+		tz->ops->critical(tz);
 }
 
 static void handle_thermal_trip(struct thermal_zone_device *tz, int trip)
@@ -1336,6 +1343,10 @@ thermal_zone_device_register(const char *type, int trips, int mask,
 
 	tz->id = id;
 	strlcpy(tz->type, type, sizeof(tz->type));
+
+	if (!ops->critical)
+		ops->critical = thermal_zone_device_critical;
+
 	tz->ops = ops;
 	tz->tzp = tzp;
 	tz->device.class = &thermal_class;
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index d07ea27e72a9..31b84404f047 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -79,6 +79,8 @@ struct thermal_zone_device_ops {
 			  enum thermal_trend *);
 	int (*notify) (struct thermal_zone_device *, int,
 		       enum thermal_trip_type);
+	void (*hot)(struct thermal_zone_device *);
+	void (*critical)(struct thermal_zone_device *);
 };
 
 struct thermal_cooling_device_ops {
@@ -399,6 +401,7 @@ void thermal_cdev_update(struct thermal_cooling_device *);
 void thermal_notify_framework(struct thermal_zone_device *, int);
 int thermal_zone_device_enable(struct thermal_zone_device *tz);
 int thermal_zone_device_disable(struct thermal_zone_device *tz);
+void thermal_zone_device_critical(struct thermal_zone_device *tz);
 #else
 static inline struct thermal_zone_device *thermal_zone_device_register(
 	const char *type, int trips, int mask, void *devdata,
-- 
cgit v1.2.3


From 6a6939d5f588b40db32b82ebcec20ee5189c8376 Mon Sep 17 00:00:00 2001
From: Fabio Estevam <festevam@gmail.com>
Date: Thu, 10 Dec 2020 18:27:48 -0300
Subject: regulator: pfuze100: Convert the driver to DT-only

Since 5.10-rc1 i.MX is a devicetree-only platform, so simplify the code
by removing the unused non-DT support.

Signed-off-by: Fabio Estevam <festevam@gmail.com>
Link: https://lore.kernel.org/r/20201210212748.5849-1-festevam@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/Kconfig              |  2 +-
 drivers/regulator/pfuze100-regulator.c | 34 +---------------------------------
 include/linux/regulator/pfuze100.h     |  6 ------
 3 files changed, 2 insertions(+), 40 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index 7faedb05b7a6..cb9333d4c0fd 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -830,7 +830,7 @@ config REGULATOR_PF8X00
 
 config REGULATOR_PFUZE100
 	tristate "Freescale PFUZE100/200/3000/3001 regulator driver"
-	depends on I2C
+	depends on I2C && OF
 	select REGMAP_I2C
 	help
 	  Say y here to support the regulators found on the Freescale
diff --git a/drivers/regulator/pfuze100-regulator.c b/drivers/regulator/pfuze100-regulator.c
index 7e8ba9246167..09bab0b45f90 100644
--- a/drivers/regulator/pfuze100-regulator.c
+++ b/drivers/regulator/pfuze100-regulator.c
@@ -105,15 +105,6 @@ static const int pfuze3000_sw2hi[] = {
 	2500000, 2800000, 2850000, 3000000, 3100000, 3150000, 3200000, 3300000,
 };
 
-static const struct i2c_device_id pfuze_device_id[] = {
-	{.name = "pfuze100", .driver_data = PFUZE100},
-	{.name = "pfuze200", .driver_data = PFUZE200},
-	{.name = "pfuze3000", .driver_data = PFUZE3000},
-	{.name = "pfuze3001", .driver_data = PFUZE3001},
-	{ }
-};
-MODULE_DEVICE_TABLE(i2c, pfuze_device_id);
-
 static const struct of_device_id pfuze_dt_ids[] = {
 	{ .compatible = "fsl,pfuze100", .data = (void *)PFUZE100},
 	{ .compatible = "fsl,pfuze200", .data = (void *)PFUZE200},
@@ -440,7 +431,6 @@ static struct pfuze_regulator pfuze3001_regulators[] = {
 	PFUZE100_VGEN_REG(PFUZE3001, VLDO4, PFUZE100_VGEN6VOL, 1800000, 3300000, 100000),
 };
 
-#ifdef CONFIG_OF
 /* PFUZE100 */
 static struct of_regulator_match pfuze100_matches[] = {
 	{ .name = "sw1ab",	},
@@ -578,22 +568,6 @@ static inline struct device_node *match_of_node(int index)
 {
 	return pfuze_matches[index].of_node;
 }
-#else
-static int pfuze_parse_regulators_dt(struct pfuze_chip *chip)
-{
-	return 0;
-}
-
-static inline struct regulator_init_data *match_init_data(int index)
-{
-	return NULL;
-}
-
-static inline struct device_node *match_of_node(int index)
-{
-	return NULL;
-}
-#endif
 
 static struct pfuze_chip *syspm_pfuze_chip;
 
@@ -708,8 +682,6 @@ static int pfuze100_regulator_probe(struct i2c_client *client,
 				    const struct i2c_device_id *id)
 {
 	struct pfuze_chip *pfuze_chip;
-	struct pfuze_regulator_platform_data *pdata =
-	    dev_get_platdata(&client->dev);
 	struct regulator_config config = { };
 	int i, ret;
 	const struct of_device_id *match;
@@ -802,10 +774,7 @@ static int pfuze100_regulator_probe(struct i2c_client *client,
 
 		desc = &pfuze_chip->regulator_descs[i].desc;
 
-		if (pdata)
-			init_data = pdata->init_data[i];
-		else
-			init_data = match_init_data(i);
+		init_data = match_init_data(i);
 
 		/* SW2~SW4 high bit check and modify the voltage value table */
 		if (i >= sw_check_start && i <= sw_check_end) {
@@ -876,7 +845,6 @@ static int pfuze100_regulator_remove(struct i2c_client *client)
 }
 
 static struct i2c_driver pfuze_driver = {
-	.id_table = pfuze_device_id,
 	.driver = {
 		.name = "pfuze100-regulator",
 		.of_match_table = pfuze_dt_ids,
diff --git a/include/linux/regulator/pfuze100.h b/include/linux/regulator/pfuze100.h
index d47e668d9ca8..c964fe8ab698 100644
--- a/include/linux/regulator/pfuze100.h
+++ b/include/linux/regulator/pfuze100.h
@@ -63,10 +63,4 @@
 #define PFUZE3001_VLDO3		8
 #define PFUZE3001_VLDO4		9
 
-struct regulator_init_data;
-
-struct pfuze_regulator_platform_data {
-	struct regulator_init_data *init_data[PFUZE100_MAX_REGULATOR];
-};
-
 #endif /* __LINUX_REG_PFUZE100_H */
-- 
cgit v1.2.3


From b388fa50142510fb6477f130bb1b3f05a0a263a1 Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Mon, 9 Nov 2020 09:41:21 +0000
Subject: Revert "genirq: Add fasteoi IPI flow"

handle_percpu_devid_fasteoi_ipi() has no more users, and
handle_percpu_devid_irq() can do all that it was supposed to do. Get rid of
it.

This reverts commit c5e5ec033c4ab25c53f1fd217849e75deb0bf7bf.

Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20201109094121.29975-6-valentin.schneider@arm.com
---
 include/linux/irq.h |  1 -
 kernel/irq/chip.c   | 27 ---------------------------
 2 files changed, 28 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index c54365309e97..ca26bec51cec 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -647,7 +647,6 @@ static inline int irq_set_parent(int irq, int parent_irq)
  */
 extern void handle_level_irq(struct irq_desc *desc);
 extern void handle_fasteoi_irq(struct irq_desc *desc);
-extern void handle_percpu_devid_fasteoi_ipi(struct irq_desc *desc);
 extern void handle_edge_irq(struct irq_desc *desc);
 extern void handle_edge_eoi_irq(struct irq_desc *desc);
 extern void handle_simple_irq(struct irq_desc *desc);
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index b9b9618e1aca..0ae308efa604 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -944,33 +944,6 @@ void handle_percpu_devid_irq(struct irq_desc *desc)
 		chip->irq_eoi(&desc->irq_data);
 }
 
-/**
- * handle_percpu_devid_fasteoi_ipi - Per CPU local IPI handler with per cpu
- *				     dev ids
- * @desc:	the interrupt description structure for this irq
- *
- * The biggest difference with the IRQ version is that the interrupt is
- * EOIed early, as the IPI could result in a context switch, and we need to
- * make sure the IPI can fire again. We also assume that the arch code has
- * registered an action. If not, we are positively doomed.
- */
-void handle_percpu_devid_fasteoi_ipi(struct irq_desc *desc)
-{
-	struct irq_chip *chip = irq_desc_get_chip(desc);
-	struct irqaction *action = desc->action;
-	unsigned int irq = irq_desc_get_irq(desc);
-	irqreturn_t res;
-
-	__kstat_incr_irqs_this_cpu(desc);
-
-	if (chip->irq_eoi)
-		chip->irq_eoi(&desc->irq_data);
-
-	trace_irq_handler_entry(irq, action);
-	res = action->handler(irq, raw_cpu_ptr(action->percpu_dev_id));
-	trace_irq_handler_exit(irq, action, res);
-}
-
 /**
  * handle_percpu_devid_fasteoi_nmi - Per CPU local NMI handler with per cpu
  *				     dev ids
-- 
cgit v1.2.3


From 1d3aec89286254487df7641c30f1b14ad1d127a5 Mon Sep 17 00:00:00 2001
From: John Garry <john.garry@huawei.com>
Date: Wed, 2 Dec 2020 18:36:53 +0800
Subject: genirq/affinity: Add irq_update_affinity_desc()

Add a function to allow the affinity of an interrupt be switched to
managed, such that interrupts allocated for platform devices may be
managed.

This new interface has certain limitations, and attempts to use it in the
following circumstances will fail:
- For when the kernel is configured for generic IRQ reservation mode (in
  config GENERIC_IRQ_RESERVATION_MODE). The reason being that it could
  conflict with managed vs. non-managed interrupt accounting.
- The interrupt is already started, which should not be the case during
  init
- The interrupt is already configured as managed, which means double init

Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: John Garry <john.garry@huawei.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/1606905417-183214-2-git-send-email-john.garry@huawei.com
---
 include/linux/interrupt.h |  8 ++++++
 kernel/irq/manage.c       | 70 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 78 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index ee8299eb1f52..870b3251e174 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -352,6 +352,8 @@ extern int irq_can_set_affinity(unsigned int irq);
 extern int irq_select_affinity(unsigned int irq);
 
 extern int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m);
+extern int irq_update_affinity_desc(unsigned int irq,
+				    struct irq_affinity_desc *affinity);
 
 extern int
 irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify);
@@ -387,6 +389,12 @@ static inline int irq_set_affinity_hint(unsigned int irq,
 	return -EINVAL;
 }
 
+static inline int irq_update_affinity_desc(unsigned int irq,
+					   struct irq_affinity_desc *affinity)
+{
+	return -EINVAL;
+}
+
 static inline int
 irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify)
 {
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index c460e0496006..c826ba4141fe 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -371,6 +371,76 @@ int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask,
 	return ret;
 }
 
+/**
+ * irq_update_affinity_desc - Update affinity management for an interrupt
+ * @irq:	The interrupt number to update
+ * @affinity:	Pointer to the affinity descriptor
+ *
+ * This interface can be used to configure the affinity management of
+ * interrupts which have been allocated already.
+ *
+ * There are certain limitations on when it may be used - attempts to use it
+ * for when the kernel is configured for generic IRQ reservation mode (in
+ * config GENERIC_IRQ_RESERVATION_MODE) will fail, as it may conflict with
+ * managed/non-managed interrupt accounting. In addition, attempts to use it on
+ * an interrupt which is already started or which has already been configured
+ * as managed will also fail, as these mean invalid init state or double init.
+ */
+int irq_update_affinity_desc(unsigned int irq,
+			     struct irq_affinity_desc *affinity)
+{
+	struct irq_desc *desc;
+	unsigned long flags;
+	bool activated;
+	int ret = 0;
+
+	/*
+	 * Supporting this with the reservation scheme used by x86 needs
+	 * some more thought. Fail it for now.
+	 */
+	if (IS_ENABLED(CONFIG_GENERIC_IRQ_RESERVATION_MODE))
+		return -EOPNOTSUPP;
+
+	desc = irq_get_desc_buslock(irq, &flags, 0);
+	if (!desc)
+		return -EINVAL;
+
+	/* Requires the interrupt to be shut down */
+	if (irqd_is_started(&desc->irq_data)) {
+		ret = -EBUSY;
+		goto out_unlock;
+	}
+
+	/* Interrupts which are already managed cannot be modified */
+	if (irqd_affinity_is_managed(&desc->irq_data)) {
+		ret = -EBUSY;
+		goto out_unlock;
+	}
+
+	/*
+	 * Deactivate the interrupt. That's required to undo
+	 * anything an earlier activation has established.
+	 */
+	activated = irqd_is_activated(&desc->irq_data);
+	if (activated)
+		irq_domain_deactivate_irq(&desc->irq_data);
+
+	if (affinity->is_managed) {
+		irqd_set(&desc->irq_data, IRQD_AFFINITY_MANAGED);
+		irqd_set(&desc->irq_data, IRQD_MANAGED_SHUTDOWN);
+	}
+
+	cpumask_copy(desc->irq_common_data.affinity, &affinity->mask);
+
+	/* Restore the activation state */
+	if (activated)
+		irq_domain_activate_irq(&desc->irq_data, false);
+
+out_unlock:
+	irq_put_desc_busunlock(desc, flags);
+	return ret;
+}
+
 int __irq_set_affinity(unsigned int irq, const struct cpumask *mask, bool force)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
-- 
cgit v1.2.3


From 9806731db684a475ade1e95d166089b9edbd9da3 Mon Sep 17 00:00:00 2001
From: John Garry <john.garry@huawei.com>
Date: Wed, 2 Dec 2020 18:36:54 +0800
Subject: resource: Add irqresource_disabled()

Add a common function to set the fields for a irq resource to disabled,
which mimics what is done in acpi_dev_irqresource_disabled(), with a view
to replace that function.

Signed-off-by: John Garry <john.garry@huawei.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lore.kernel.org/r/1606905417-183214-3-git-send-email-john.garry@huawei.com
---
 include/linux/ioport.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index 5135d4b86cd6..f9bf374f9633 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -307,6 +307,13 @@ struct resource *devm_request_free_mem_region(struct device *dev,
 struct resource *request_free_mem_region(struct resource *base,
 		unsigned long size, const char *name);
 
+static inline void irqresource_disabled(struct resource *res, u32 irq)
+{
+	res->start = irq;
+	res->end = irq;
+	res->flags = IORESOURCE_IRQ | IORESOURCE_DISABLED | IORESOURCE_UNSET;
+}
+
 #ifdef CONFIG_IO_STRICT_DEVMEM
 void revoke_devmem(struct resource *res);
 #else
-- 
cgit v1.2.3


From e15f2fa959f2cce8a05e8e3a596e75d068cd42c5 Mon Sep 17 00:00:00 2001
From: John Garry <john.garry@huawei.com>
Date: Wed, 2 Dec 2020 18:36:56 +0800
Subject: driver core: platform: Add devm_platform_get_irqs_affinity()

Drivers for multi-queue platform devices may also want managed interrupts
for handling HW queue completion interrupts, so add support.

The function accepts an affinity descriptor pointer, which covers all IRQs
expected for the device.

The function is devm class as the only current in-tree user will also use
devm method for requesting the interrupts; as such, the function is made
as devm as it can ensure ordering of freeing the irq and disposing of the
mapping.

Signed-off-by: John Garry <john.garry@huawei.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Acked-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/1606905417-183214-5-git-send-email-john.garry@huawei.com
---
 drivers/base/platform.c         | 121 ++++++++++++++++++++++++++++++++++++++++
 include/linux/platform_device.h |   6 ++
 2 files changed, 127 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index 88aef93eb4dd..ea8add164b89 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -15,6 +15,8 @@
 #include <linux/of_irq.h>
 #include <linux/module.h>
 #include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/ioport.h>
 #include <linux/dma-mapping.h>
 #include <linux/memblock.h>
 #include <linux/err.h>
@@ -289,6 +291,125 @@ int platform_irq_count(struct platform_device *dev)
 }
 EXPORT_SYMBOL_GPL(platform_irq_count);
 
+struct irq_affinity_devres {
+	unsigned int count;
+	unsigned int irq[];
+};
+
+static void platform_disable_acpi_irq(struct platform_device *pdev, int index)
+{
+	struct resource *r;
+
+	r = platform_get_resource(pdev, IORESOURCE_IRQ, index);
+	if (r)
+		irqresource_disabled(r, 0);
+}
+
+static void devm_platform_get_irqs_affinity_release(struct device *dev,
+						    void *res)
+{
+	struct irq_affinity_devres *ptr = res;
+	int i;
+
+	for (i = 0; i < ptr->count; i++) {
+		irq_dispose_mapping(ptr->irq[i]);
+
+		if (has_acpi_companion(dev))
+			platform_disable_acpi_irq(to_platform_device(dev), i);
+	}
+}
+
+/**
+ * devm_platform_get_irqs_affinity - devm method to get a set of IRQs for a
+ *				device using an interrupt affinity descriptor
+ * @dev: platform device pointer
+ * @affd: affinity descriptor
+ * @minvec: minimum count of interrupt vectors
+ * @maxvec: maximum count of interrupt vectors
+ * @irqs: pointer holder for IRQ numbers
+ *
+ * Gets a set of IRQs for a platform device, and updates IRQ afffinty according
+ * to the passed affinity descriptor
+ *
+ * Return: Number of vectors on success, negative error number on failure.
+ */
+int devm_platform_get_irqs_affinity(struct platform_device *dev,
+				    struct irq_affinity *affd,
+				    unsigned int minvec,
+				    unsigned int maxvec,
+				    int **irqs)
+{
+	struct irq_affinity_devres *ptr;
+	struct irq_affinity_desc *desc;
+	size_t size;
+	int i, ret, nvec;
+
+	if (!affd)
+		return -EPERM;
+
+	if (maxvec < minvec)
+		return -ERANGE;
+
+	nvec = platform_irq_count(dev);
+
+	if (nvec < minvec)
+		return -ENOSPC;
+
+	nvec = irq_calc_affinity_vectors(minvec, nvec, affd);
+	if (nvec < minvec)
+		return -ENOSPC;
+
+	if (nvec > maxvec)
+		nvec = maxvec;
+
+	size = sizeof(*ptr) + sizeof(unsigned int) * nvec;
+	ptr = devres_alloc(devm_platform_get_irqs_affinity_release, size,
+			   GFP_KERNEL);
+	if (!ptr)
+		return -ENOMEM;
+
+	ptr->count = nvec;
+
+	for (i = 0; i < nvec; i++) {
+		int irq = platform_get_irq(dev, i);
+		if (irq < 0) {
+			ret = irq;
+			goto err_free_devres;
+		}
+		ptr->irq[i] = irq;
+	}
+
+	desc = irq_create_affinity_masks(nvec, affd);
+	if (!desc) {
+		ret = -ENOMEM;
+		goto err_free_devres;
+	}
+
+	for (i = 0; i < nvec; i++) {
+		ret = irq_update_affinity_desc(ptr->irq[i], &desc[i]);
+		if (ret) {
+			dev_err(&dev->dev, "failed to update irq%d affinity descriptor (%d)\n",
+				ptr->irq[i], ret);
+			goto err_free_desc;
+		}
+	}
+
+	devres_add(&dev->dev, ptr);
+
+	kfree(desc);
+
+	*irqs = ptr->irq;
+
+	return nvec;
+
+err_free_desc:
+	kfree(desc);
+err_free_devres:
+	devres_free(ptr);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(devm_platform_get_irqs_affinity);
+
 /**
  * platform_get_resource_byname - get a resource for a device by name
  * @dev: platform device
diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h
index 77a2aada106d..4d75633e6735 100644
--- a/include/linux/platform_device.h
+++ b/include/linux/platform_device.h
@@ -15,6 +15,7 @@
 #define PLATFORM_DEVID_NONE	(-1)
 #define PLATFORM_DEVID_AUTO	(-2)
 
+struct irq_affinity;
 struct mfd_cell;
 struct property_entry;
 struct platform_device_id;
@@ -70,6 +71,11 @@ devm_platform_ioremap_resource_byname(struct platform_device *pdev,
 extern int platform_get_irq(struct platform_device *, unsigned int);
 extern int platform_get_irq_optional(struct platform_device *, unsigned int);
 extern int platform_irq_count(struct platform_device *);
+extern int devm_platform_get_irqs_affinity(struct platform_device *dev,
+					   struct irq_affinity *affd,
+					   unsigned int minvec,
+					   unsigned int maxvec,
+					   int **irqs);
 extern struct resource *platform_get_resource_byname(struct platform_device *,
 						     unsigned int,
 						     const char *);
-- 
cgit v1.2.3


From 426506a7e0f1902268c3edbdc7e5475624a9d18b Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@ti.com>
Date: Tue, 8 Dec 2020 11:04:24 +0200
Subject: dmaengine: ti: k3-udma-glue: Add function to get device pointer for
 DMA API

Glue layer users should use the device of the DMA for DMA mapping and
allocations as it is the DMA which accesses to descriptors and buffers,
not the clients

Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com>
Link: https://lore.kernel.org/r/20201208090440.31792-5-peter.ujfalusi@ti.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/ti/k3-udma-glue.c    | 14 ++++++++++++++
 drivers/dma/ti/k3-udma-private.c |  6 ++++++
 drivers/dma/ti/k3-udma.h         |  1 +
 include/linux/dma/k3-udma-glue.h |  4 ++++
 4 files changed, 25 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/dma/ti/k3-udma-glue.c b/drivers/dma/ti/k3-udma-glue.c
index dfb65e382ab9..29d1524d1916 100644
--- a/drivers/dma/ti/k3-udma-glue.c
+++ b/drivers/dma/ti/k3-udma-glue.c
@@ -493,6 +493,13 @@ int k3_udma_glue_tx_get_irq(struct k3_udma_glue_tx_channel *tx_chn)
 }
 EXPORT_SYMBOL_GPL(k3_udma_glue_tx_get_irq);
 
+struct device *
+	k3_udma_glue_tx_get_dma_device(struct k3_udma_glue_tx_channel *tx_chn)
+{
+	return xudma_get_device(tx_chn->common.udmax);
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_tx_get_dma_device);
+
 static int k3_udma_glue_cfg_rx_chn(struct k3_udma_glue_rx_channel *rx_chn)
 {
 	const struct udma_tisci_rm *tisci_rm = rx_chn->common.tisci_rm;
@@ -1201,3 +1208,10 @@ int k3_udma_glue_rx_get_irq(struct k3_udma_glue_rx_channel *rx_chn,
 	return flow->virq;
 }
 EXPORT_SYMBOL_GPL(k3_udma_glue_rx_get_irq);
+
+struct device *
+	k3_udma_glue_rx_get_dma_device(struct k3_udma_glue_rx_channel *rx_chn)
+{
+	return xudma_get_device(rx_chn->common.udmax);
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_rx_get_dma_device);
diff --git a/drivers/dma/ti/k3-udma-private.c b/drivers/dma/ti/k3-udma-private.c
index aa24e554f7b4..8ff7a264be03 100644
--- a/drivers/dma/ti/k3-udma-private.c
+++ b/drivers/dma/ti/k3-udma-private.c
@@ -50,6 +50,12 @@ struct udma_dev *of_xudma_dev_get(struct device_node *np, const char *property)
 }
 EXPORT_SYMBOL(of_xudma_dev_get);
 
+struct device *xudma_get_device(struct udma_dev *ud)
+{
+	return ud->dev;
+}
+EXPORT_SYMBOL(xudma_get_device);
+
 u32 xudma_dev_get_psil_base(struct udma_dev *ud)
 {
 	return ud->psil_base;
diff --git a/drivers/dma/ti/k3-udma.h b/drivers/dma/ti/k3-udma.h
index 09c4529e013d..d1cace0cb43b 100644
--- a/drivers/dma/ti/k3-udma.h
+++ b/drivers/dma/ti/k3-udma.h
@@ -112,6 +112,7 @@ int xudma_navss_psil_unpair(struct udma_dev *ud, u32 src_thread,
 			    u32 dst_thread);
 
 struct udma_dev *of_xudma_dev_get(struct device_node *np, const char *property);
+struct device *xudma_get_device(struct udma_dev *ud);
 void xudma_dev_put(struct udma_dev *ud);
 u32 xudma_dev_get_psil_base(struct udma_dev *ud);
 struct udma_tisci_rm *xudma_dev_get_tisci_rm(struct udma_dev *ud);
diff --git a/include/linux/dma/k3-udma-glue.h b/include/linux/dma/k3-udma-glue.h
index 5eb34ad973a7..d7c12f31377c 100644
--- a/include/linux/dma/k3-udma-glue.h
+++ b/include/linux/dma/k3-udma-glue.h
@@ -41,6 +41,8 @@ void k3_udma_glue_reset_tx_chn(struct k3_udma_glue_tx_channel *tx_chn,
 u32 k3_udma_glue_tx_get_hdesc_size(struct k3_udma_glue_tx_channel *tx_chn);
 u32 k3_udma_glue_tx_get_txcq_id(struct k3_udma_glue_tx_channel *tx_chn);
 int k3_udma_glue_tx_get_irq(struct k3_udma_glue_tx_channel *tx_chn);
+struct device *
+	k3_udma_glue_tx_get_dma_device(struct k3_udma_glue_tx_channel *tx_chn);
 
 enum {
 	K3_UDMA_GLUE_SRC_TAG_LO_KEEP = 0,
@@ -130,5 +132,7 @@ int k3_udma_glue_rx_flow_enable(struct k3_udma_glue_rx_channel *rx_chn,
 				u32 flow_idx);
 int k3_udma_glue_rx_flow_disable(struct k3_udma_glue_rx_channel *rx_chn,
 				 u32 flow_idx);
+struct device *
+	k3_udma_glue_rx_get_dma_device(struct k3_udma_glue_rx_channel *rx_chn);
 
 #endif /* K3_UDMA_GLUE_H_ */
-- 
cgit v1.2.3


From 4f910c035f38053ac8eb63a672c78862c535cd0f Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@ti.com>
Date: Tue, 8 Dec 2020 11:04:27 +0200
Subject: dmaengine: of-dma: Add support for optional router configuration
 callback

Additional configuration for the DMA event router might be needed for a
channel which can not be done during device_alloc_chan_resources callback
since the router information is not yet present for the drivers.

If there is a need for additional configuration for the channel if DMA
router is in use, then the driver can implement the device_router_config
callback.

Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Link: https://lore.kernel.org/r/20201208090440.31792-8-peter.ujfalusi@ti.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/of-dma.c      | 10 ++++++++++
 include/linux/dmaengine.h |  2 ++
 2 files changed, 12 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/dma/of-dma.c b/drivers/dma/of-dma.c
index 8a4f608904b9..ec00b20ae8e4 100644
--- a/drivers/dma/of-dma.c
+++ b/drivers/dma/of-dma.c
@@ -75,8 +75,18 @@ static struct dma_chan *of_dma_router_xlate(struct of_phandle_args *dma_spec,
 		ofdma->dma_router->route_free(ofdma->dma_router->dev,
 					      route_data);
 	} else {
+		int ret = 0;
+
 		chan->router = ofdma->dma_router;
 		chan->route_data = route_data;
+
+		if (chan->device->device_router_config)
+			ret = chan->device->device_router_config(chan);
+
+		if (ret) {
+			dma_release_channel(chan);
+			chan = ERR_PTR(ret);
+		}
 	}
 
 	/*
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 493a047ed0a2..aed44888cad3 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -805,6 +805,7 @@ struct dma_filter {
  *	by tx_status
  * @device_alloc_chan_resources: allocate resources and return the
  *	number of allocated descriptors
+ * @device_router_config: optional callback for DMA router configuration
  * @device_free_chan_resources: release DMA channel's resources
  * @device_prep_dma_memcpy: prepares a memcpy operation
  * @device_prep_dma_xor: prepares a xor operation
@@ -879,6 +880,7 @@ struct dma_device {
 	enum dma_residue_granularity residue_granularity;
 
 	int (*device_alloc_chan_resources)(struct dma_chan *chan);
+	int (*device_router_config)(struct dma_chan *chan);
 	void (*device_free_chan_resources)(struct dma_chan *chan);
 
 	struct dma_async_tx_descriptor *(*device_prep_dma_memcpy)(
-- 
cgit v1.2.3


From ab650ef6d548153862119e1bf3bf267510707f48 Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@ti.com>
Date: Tue, 8 Dec 2020 11:04:28 +0200
Subject: dmaengine: Add support for per channel coherency handling

If the DMA device supports per channel coherency configuration (a channel
can be configured to have coherent or not coherent view) then a single
device (the DMA controller's device) can not be used for dma_api for all
channels as channels can have different coherency.

Introduce custom_dma_mapping flag for the dma_chan and a new helper to get
the device pointer to be used for dma_api for the given channel.

Client drivers should be updated to be able to support per channel
coherency by:

- dma_map_single(chan->device->dev, ptr, size, DMA_TO_DEVICE);
+ struct device *dma_dev = dmaengine_get_dma_device(chan);
+
+ dma_map_single(dma_dev, ptr, size, DMA_TO_DEVICE);

Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Link: https://lore.kernel.org/r/20201208090440.31792-9-peter.ujfalusi@ti.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/dmaengine.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index aed44888cad3..68130f5f599e 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -357,11 +357,14 @@ struct dma_chan {
  * @chan: driver channel device
  * @device: sysfs device
  * @dev_id: parent dma_device dev_id
+ * @chan_dma_dev: The channel is using custom/different dma-mapping
+ * compared to the parent dma_device
  */
 struct dma_chan_dev {
 	struct dma_chan *chan;
 	struct device device;
 	int dev_id;
+	bool chan_dma_dev;
 };
 
 /**
@@ -1618,4 +1621,13 @@ dmaengine_get_direction_text(enum dma_transfer_direction dir)
 		return "invalid";
 	}
 }
+
+static inline struct device *dmaengine_get_dma_device(struct dma_chan *chan)
+{
+	if (chan->dev->chan_dma_dev)
+		return &chan->dev->device;
+
+	return chan->device->dev;
+}
+
 #endif /* DMAENGINE_H */
-- 
cgit v1.2.3


From b9366e2577a38ca5322f326cff9752c2008597c6 Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@ti.com>
Date: Tue, 8 Dec 2020 11:04:33 +0200
Subject: dmaengine: ti: k3-psil: Extend psil_endpoint_config for K3 PKTDMA

Additional fields needed for K3 PKTDMA to be able to handle the mapped
channels (channels are locked to handle specific threads) and flow ranges
for these mapped threads.
PKTDMA also introduces tflow for tx channels which can not be found in
K3 UDMA architecture.

Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com>
Link: https://lore.kernel.org/r/20201208090440.31792-14-peter.ujfalusi@ti.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/dma/k3-psil.h | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/dma/k3-psil.h b/include/linux/dma/k3-psil.h
index 1962f75fa2d3..36e22c5a0f29 100644
--- a/include/linux/dma/k3-psil.h
+++ b/include/linux/dma/k3-psil.h
@@ -50,6 +50,15 @@ enum psil_endpoint_type {
  * @channel_tpl:	Desired throughput level for the channel
  * @pdma_acc32:		ACC32 must be enabled on the PDMA side
  * @pdma_burst:		BURST must be enabled on the PDMA side
+ * @mapped_channel_id:	PKTDMA thread to channel mapping for mapped channels.
+ *			The thread must be serviced by the specified channel if
+ *			mapped_channel_id is >= 0 in case of PKTDMA
+ * @flow_start:		PKDMA flow range start of mapped channel. Unmapped
+ *			channels use flow_id == chan_id
+ * @flow_num:		PKDMA flow count of mapped channel. Unmapped channels
+ *			use flow_id == chan_id
+ * @default_flow_id:	PKDMA default (r)flow index of mapped channel.
+ *			Must be within the flow range of the mapped channel.
  */
 struct psil_endpoint_config {
 	enum psil_endpoint_type ep_type;
@@ -63,6 +72,13 @@ struct psil_endpoint_config {
 	/* PDMA properties, valid for PSIL_EP_PDMA_* */
 	unsigned pdma_acc32:1;
 	unsigned pdma_burst:1;
+
+	/* PKDMA mapped channel */
+	int mapped_channel_id;
+	/* PKTDMA tflow and rflow ranges for mapped channel */
+	u16 flow_start;
+	u16 flow_num;
+	u16 default_flow_id;
 };
 
 int psil_set_new_ep_config(struct device *dev, const char *name,
-- 
cgit v1.2.3


From fc373e47d72605cc3f5012ddda49d2dca430d51f Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@ti.com>
Date: Tue, 8 Dec 2020 11:04:35 +0200
Subject: dmaengine: ti: Add support for k3 event routers

In k3 architecture a DMA channel (in TR momde) can be triggered by global
events, origination from different modules.

The events for triggers can be sent from any module which is connected to
PSI-L fabric, but the event number to be sent is DMA channel specific, it
is only known after the channel itself is requested.

The router operation needs to be split up:
- route_allocate: configure the dma_spec for the DMA and store the
  configuration which is needed for the router's input
- set_event: callback used by the DMA driver to set the event number for
  the channel and enable the routing

Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Link: https://lore.kernel.org/r/20201208090440.31792-16-peter.ujfalusi@ti.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/dma/k3-event-router.h | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)
 create mode 100644 include/linux/dma/k3-event-router.h

(limited to 'include/linux')

diff --git a/include/linux/dma/k3-event-router.h b/include/linux/dma/k3-event-router.h
new file mode 100644
index 000000000000..e3f88b2f87be
--- /dev/null
+++ b/include/linux/dma/k3-event-router.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *  Copyright (C) 2020 Texas Instruments Incorporated - https://www.ti.com
+ */
+
+#ifndef K3_EVENT_ROUTER_
+#define K3_EVENT_ROUTER_
+
+#include <linux/types.h>
+
+struct k3_event_route_data {
+	void *priv;
+	int (*set_event)(void *priv, u32 event);
+};
+
+#endif /* K3_EVENT_ROUTER_ */
-- 
cgit v1.2.3


From d782298c6f6b854452965b56d91616dfb60490c5 Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Tue, 8 Dec 2020 11:04:36 +0200
Subject: soc: ti: k3-ringacc: add AM64 DMA rings support.

The DMAs in AM64 have built in rings compared to AM654/J721e/J7200 where a
separate and generic ringacc is used.

The ring SW interface is similar to ringacc with some major architectural
differences, like

They are part of the DMA (BCDMA or PKTDMA).

They are dual mode rings are modeled as pair of Rings objects which has
common configuration and memory buffer, but separate real-time control
register sets for each direction mem2dev (forward) and dev2mem (reverse).

The ringacc driver must be initialized for DMA rings use with
k3_ringacc_dmarings_init() as it is not an independent device as ringacc
is.

AM64 rings must be requested only using k3_ringacc_request_rings_pair(),
and forward ring must always be initialized/configured. After this any
other Ringacc APIs can be used without any callers changes.

Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Link: https://lore.kernel.org/r/20201208090440.31792-17-peter.ujfalusi@ti.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soc/ti/k3-ringacc.c       | 325 +++++++++++++++++++++++++++++++++++++-
 include/linux/soc/ti/k3-ringacc.h |  17 ++
 2 files changed, 335 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/soc/ti/k3-ringacc.c b/drivers/soc/ti/k3-ringacc.c
index 119164abcb41..c88c305ba367 100644
--- a/drivers/soc/ti/k3-ringacc.c
+++ b/drivers/soc/ti/k3-ringacc.c
@@ -11,6 +11,7 @@
 #include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/sys_soc.h>
+#include <linux/dma/ti-cppi5.h>
 #include <linux/soc/ti/k3-ringacc.h>
 #include <linux/soc/ti/ti_sci_protocol.h>
 #include <linux/soc/ti/ti_sci_inta_msi.h>
@@ -21,6 +22,7 @@ static LIST_HEAD(k3_ringacc_list);
 static DEFINE_MUTEX(k3_ringacc_list_lock);
 
 #define K3_RINGACC_CFG_RING_SIZE_ELCNT_MASK		GENMASK(19, 0)
+#define K3_DMARING_CFG_RING_SIZE_ELCNT_MASK		GENMASK(15, 0)
 
 /**
  * struct k3_ring_rt_regs - The RA realtime Control/Status Registers region
@@ -43,7 +45,13 @@ struct k3_ring_rt_regs {
 	u32	hwindx;
 };
 
-#define K3_RINGACC_RT_REGS_STEP	0x1000
+#define K3_RINGACC_RT_REGS_STEP			0x1000
+#define K3_DMARING_RT_REGS_STEP			0x2000
+#define K3_DMARING_RT_REGS_REVERSE_OFS		0x1000
+#define K3_RINGACC_RT_OCC_MASK			GENMASK(20, 0)
+#define K3_DMARING_RT_OCC_TDOWN_COMPLETE	BIT(31)
+#define K3_DMARING_RT_DB_ENTRY_MASK		GENMASK(7, 0)
+#define K3_DMARING_RT_DB_TDOWN_ACK		BIT(31)
 
 /**
  * struct k3_ring_fifo_regs - The Ring Accelerator Queues Registers region
@@ -122,6 +130,7 @@ struct k3_ring_state {
 	u32 occ;
 	u32 windex;
 	u32 rindex;
+	u32 tdown_complete:1;
 };
 
 /**
@@ -143,6 +152,7 @@ struct k3_ring_state {
  * @use_count: Use count for shared rings
  * @proxy_id: RA Ring Proxy Id (only if @K3_RINGACC_RING_USE_PROXY)
  * @dma_dev: device to be used for DMA API (allocation, mapping)
+ * @asel: Address Space Select value for physical addresses
  */
 struct k3_ring {
 	struct k3_ring_rt_regs __iomem *rt;
@@ -157,12 +167,15 @@ struct k3_ring {
 	u32		flags;
 #define K3_RING_FLAG_BUSY	BIT(1)
 #define K3_RING_FLAG_SHARED	BIT(2)
+#define K3_RING_FLAG_REVERSE	BIT(3)
 	struct k3_ring_state state;
 	u32		ring_id;
 	struct k3_ringacc	*parent;
 	u32		use_count;
 	int		proxy_id;
 	struct device	*dma_dev;
+	u32		asel;
+#define K3_ADDRESS_ASEL_SHIFT	48
 };
 
 struct k3_ringacc_ops {
@@ -188,6 +201,7 @@ struct k3_ringacc_ops {
  * @tisci_ring_ops: ti-sci rings ops
  * @tisci_dev_id: ti-sci device id
  * @ops: SoC specific ringacc operation
+ * @dma_rings: indicate DMA ring (dual ring within BCDMA/PKTDMA)
  */
 struct k3_ringacc {
 	struct device *dev;
@@ -210,6 +224,7 @@ struct k3_ringacc {
 	u32 tisci_dev_id;
 
 	const struct k3_ringacc_ops *ops;
+	bool dma_rings;
 };
 
 /**
@@ -221,6 +236,21 @@ struct k3_ringacc_soc_data {
 	unsigned dma_ring_reset_quirk:1;
 };
 
+static int k3_ringacc_ring_read_occ(struct k3_ring *ring)
+{
+	return readl(&ring->rt->occ) & K3_RINGACC_RT_OCC_MASK;
+}
+
+static void k3_ringacc_ring_update_occ(struct k3_ring *ring)
+{
+	u32 val;
+
+	val = readl(&ring->rt->occ);
+
+	ring->state.occ = val & K3_RINGACC_RT_OCC_MASK;
+	ring->state.tdown_complete = !!(val & K3_DMARING_RT_OCC_TDOWN_COMPLETE);
+}
+
 static long k3_ringacc_ring_get_fifo_pos(struct k3_ring *ring)
 {
 	return K3_RINGACC_FIFO_WINDOW_SIZE_BYTES -
@@ -234,12 +264,24 @@ static void *k3_ringacc_get_elm_addr(struct k3_ring *ring, u32 idx)
 
 static int k3_ringacc_ring_push_mem(struct k3_ring *ring, void *elem);
 static int k3_ringacc_ring_pop_mem(struct k3_ring *ring, void *elem);
+static int k3_dmaring_fwd_pop(struct k3_ring *ring, void *elem);
+static int k3_dmaring_reverse_pop(struct k3_ring *ring, void *elem);
 
 static struct k3_ring_ops k3_ring_mode_ring_ops = {
 		.push_tail = k3_ringacc_ring_push_mem,
 		.pop_head = k3_ringacc_ring_pop_mem,
 };
 
+static struct k3_ring_ops k3_dmaring_fwd_ops = {
+		.push_tail = k3_ringacc_ring_push_mem,
+		.pop_head = k3_dmaring_fwd_pop,
+};
+
+static struct k3_ring_ops k3_dmaring_reverse_ops = {
+		/* Reverse side of the DMA ring can only be popped by SW */
+		.pop_head = k3_dmaring_reverse_pop,
+};
+
 static int k3_ringacc_ring_push_io(struct k3_ring *ring, void *elem);
 static int k3_ringacc_ring_pop_io(struct k3_ring *ring, void *elem);
 static int k3_ringacc_ring_push_head_io(struct k3_ring *ring, void *elem);
@@ -342,6 +384,40 @@ error:
 }
 EXPORT_SYMBOL_GPL(k3_ringacc_request_ring);
 
+static int k3_dmaring_request_dual_ring(struct k3_ringacc *ringacc, int fwd_id,
+					struct k3_ring **fwd_ring,
+					struct k3_ring **compl_ring)
+{
+	int ret = 0;
+
+	/*
+	 * DMA rings must be requested by ID, completion ring is the reverse
+	 * side of the forward ring
+	 */
+	if (fwd_id < 0)
+		return -EINVAL;
+
+	mutex_lock(&ringacc->req_lock);
+
+	if (test_bit(fwd_id, ringacc->rings_inuse)) {
+		ret = -EBUSY;
+		goto error;
+	}
+
+	*fwd_ring = &ringacc->rings[fwd_id];
+	*compl_ring = &ringacc->rings[fwd_id + ringacc->num_rings];
+	set_bit(fwd_id, ringacc->rings_inuse);
+	ringacc->rings[fwd_id].use_count++;
+	dev_dbg(ringacc->dev, "Giving ring#%d\n", fwd_id);
+
+	mutex_unlock(&ringacc->req_lock);
+	return 0;
+
+error:
+	mutex_unlock(&ringacc->req_lock);
+	return ret;
+}
+
 int k3_ringacc_request_rings_pair(struct k3_ringacc *ringacc,
 				  int fwd_id, int compl_id,
 				  struct k3_ring **fwd_ring,
@@ -352,6 +428,10 @@ int k3_ringacc_request_rings_pair(struct k3_ringacc *ringacc,
 	if (!fwd_ring || !compl_ring)
 		return -EINVAL;
 
+	if (ringacc->dma_rings)
+		return k3_dmaring_request_dual_ring(ringacc, fwd_id,
+						    fwd_ring, compl_ring);
+
 	*fwd_ring = k3_ringacc_request_ring(ringacc, fwd_id, 0);
 	if (!(*fwd_ring))
 		return -ENODEV;
@@ -421,7 +501,7 @@ void k3_ringacc_ring_reset_dma(struct k3_ring *ring, u32 occ)
 		goto reset;
 
 	if (!occ)
-		occ = readl(&ring->rt->occ);
+		occ = k3_ringacc_ring_read_occ(ring);
 
 	if (occ) {
 		u32 db_ring_cnt, db_ring_cnt_cur;
@@ -496,6 +576,13 @@ int k3_ringacc_ring_free(struct k3_ring *ring)
 
 	ringacc = ring->parent;
 
+	/*
+	 * DMA rings: rings shared memory and configuration, only forward ring
+	 * is configured and reverse ring considered as slave.
+	 */
+	if (ringacc->dma_rings && (ring->flags & K3_RING_FLAG_REVERSE))
+		return 0;
+
 	dev_dbg(ring->parent->dev, "flags: 0x%08x\n", ring->flags);
 
 	if (!test_bit(ring->ring_id, ringacc->rings_inuse))
@@ -517,6 +604,8 @@ int k3_ringacc_ring_free(struct k3_ring *ring)
 	ring->flags = 0;
 	ring->ops = NULL;
 	ring->dma_dev = NULL;
+	ring->asel = 0;
+
 	if (ring->proxy_id != K3_RINGACC_PROXY_NOT_USED) {
 		clear_bit(ring->proxy_id, ringacc->proxy_inuse);
 		ring->proxy = NULL;
@@ -581,6 +670,7 @@ static int k3_ringacc_ring_cfg_sci(struct k3_ring *ring)
 	ring_cfg.count = ring->size;
 	ring_cfg.mode = ring->mode;
 	ring_cfg.size = ring->elm_size;
+	ring_cfg.asel = ring->asel;
 
 	ret = ringacc->tisci_ring_ops->set_cfg(ringacc->tisci, &ring_cfg);
 	if (ret)
@@ -590,6 +680,90 @@ static int k3_ringacc_ring_cfg_sci(struct k3_ring *ring)
 	return ret;
 }
 
+static int k3_dmaring_cfg(struct k3_ring *ring, struct k3_ring_cfg *cfg)
+{
+	struct k3_ringacc *ringacc;
+	struct k3_ring *reverse_ring;
+	int ret = 0;
+
+	if (cfg->elm_size != K3_RINGACC_RING_ELSIZE_8 ||
+	    cfg->mode != K3_RINGACC_RING_MODE_RING ||
+	    cfg->size & ~K3_DMARING_CFG_RING_SIZE_ELCNT_MASK)
+		return -EINVAL;
+
+	ringacc = ring->parent;
+
+	/*
+	 * DMA rings: rings shared memory and configuration, only forward ring
+	 * is configured and reverse ring considered as slave.
+	 */
+	if (ringacc->dma_rings && (ring->flags & K3_RING_FLAG_REVERSE))
+		return 0;
+
+	if (!test_bit(ring->ring_id, ringacc->rings_inuse))
+		return -EINVAL;
+
+	ring->size = cfg->size;
+	ring->elm_size = cfg->elm_size;
+	ring->mode = cfg->mode;
+	ring->asel = cfg->asel;
+	ring->dma_dev = cfg->dma_dev;
+	if (!ring->dma_dev) {
+		dev_warn(ringacc->dev, "dma_dev is not provided for ring%d\n",
+			 ring->ring_id);
+		ring->dma_dev = ringacc->dev;
+	}
+
+	memset(&ring->state, 0, sizeof(ring->state));
+
+	ring->ops = &k3_dmaring_fwd_ops;
+
+	ring->ring_mem_virt = dma_alloc_coherent(ring->dma_dev,
+						 ring->size * (4 << ring->elm_size),
+						 &ring->ring_mem_dma, GFP_KERNEL);
+	if (!ring->ring_mem_virt) {
+		dev_err(ringacc->dev, "Failed to alloc ring mem\n");
+		ret = -ENOMEM;
+		goto err_free_ops;
+	}
+
+	ret = k3_ringacc_ring_cfg_sci(ring);
+	if (ret)
+		goto err_free_mem;
+
+	ring->flags |= K3_RING_FLAG_BUSY;
+
+	k3_ringacc_ring_dump(ring);
+
+	/* DMA rings: configure reverse ring */
+	reverse_ring = &ringacc->rings[ring->ring_id + ringacc->num_rings];
+	reverse_ring->size = cfg->size;
+	reverse_ring->elm_size = cfg->elm_size;
+	reverse_ring->mode = cfg->mode;
+	reverse_ring->asel = cfg->asel;
+	memset(&reverse_ring->state, 0, sizeof(reverse_ring->state));
+	reverse_ring->ops = &k3_dmaring_reverse_ops;
+
+	reverse_ring->ring_mem_virt = ring->ring_mem_virt;
+	reverse_ring->ring_mem_dma = ring->ring_mem_dma;
+	reverse_ring->flags |= K3_RING_FLAG_BUSY;
+	k3_ringacc_ring_dump(reverse_ring);
+
+	return 0;
+
+err_free_mem:
+	dma_free_coherent(ring->dma_dev,
+			  ring->size * (4 << ring->elm_size),
+			  ring->ring_mem_virt,
+			  ring->ring_mem_dma);
+err_free_ops:
+	ring->ops = NULL;
+	ring->proxy = NULL;
+	ring->dma_dev = NULL;
+	ring->asel = 0;
+	return ret;
+}
+
 int k3_ringacc_ring_cfg(struct k3_ring *ring, struct k3_ring_cfg *cfg)
 {
 	struct k3_ringacc *ringacc;
@@ -597,8 +771,12 @@ int k3_ringacc_ring_cfg(struct k3_ring *ring, struct k3_ring_cfg *cfg)
 
 	if (!ring || !cfg)
 		return -EINVAL;
+
 	ringacc = ring->parent;
 
+	if (ringacc->dma_rings)
+		return k3_dmaring_cfg(ring, cfg);
+
 	if (cfg->elm_size > K3_RINGACC_RING_ELSIZE_256 ||
 	    cfg->mode >= K3_RINGACC_RING_MODE_INVALID ||
 	    cfg->size & ~K3_RINGACC_CFG_RING_SIZE_ELCNT_MASK ||
@@ -705,7 +883,7 @@ u32 k3_ringacc_ring_get_free(struct k3_ring *ring)
 		return -EINVAL;
 
 	if (!ring->state.free)
-		ring->state.free = ring->size - readl(&ring->rt->occ);
+		ring->state.free = ring->size - k3_ringacc_ring_read_occ(ring);
 
 	return ring->state.free;
 }
@@ -716,7 +894,7 @@ u32 k3_ringacc_ring_get_occ(struct k3_ring *ring)
 	if (!ring || !(ring->flags & K3_RING_FLAG_BUSY))
 		return -EINVAL;
 
-	return readl(&ring->rt->occ);
+	return k3_ringacc_ring_read_occ(ring);
 }
 EXPORT_SYMBOL_GPL(k3_ringacc_ring_get_occ);
 
@@ -892,6 +1070,72 @@ static int k3_ringacc_ring_pop_tail_io(struct k3_ring *ring, void *elem)
 					 K3_RINGACC_ACCESS_MODE_POP_HEAD);
 }
 
+/*
+ * The element is 48 bits of address + ASEL bits in the ring.
+ * ASEL is used by the DMAs and should be removed for the kernel as it is not
+ * part of the physical memory address.
+ */
+static void k3_dmaring_remove_asel_from_elem(u64 *elem)
+{
+	*elem &= GENMASK_ULL(K3_ADDRESS_ASEL_SHIFT - 1, 0);
+}
+
+static int k3_dmaring_fwd_pop(struct k3_ring *ring, void *elem)
+{
+	void *elem_ptr;
+	u32 elem_idx;
+
+	/*
+	 * DMA rings: forward ring is always tied DMA channel and HW does not
+	 * maintain any state data required for POP operation and its unknown
+	 * how much elements were consumed by HW. So, to actually
+	 * do POP, the read pointer has to be recalculated every time.
+	 */
+	ring->state.occ = k3_ringacc_ring_read_occ(ring);
+	if (ring->state.windex >= ring->state.occ)
+		elem_idx = ring->state.windex - ring->state.occ;
+	else
+		elem_idx = ring->size - (ring->state.occ - ring->state.windex);
+
+	elem_ptr = k3_ringacc_get_elm_addr(ring, elem_idx);
+	memcpy(elem, elem_ptr, (4 << ring->elm_size));
+	k3_dmaring_remove_asel_from_elem(elem);
+
+	ring->state.occ--;
+	writel(-1, &ring->rt->db);
+
+	dev_dbg(ring->parent->dev, "%s: occ%d Windex%d Rindex%d pos_ptr%px\n",
+		__func__, ring->state.occ, ring->state.windex, elem_idx,
+		elem_ptr);
+	return 0;
+}
+
+static int k3_dmaring_reverse_pop(struct k3_ring *ring, void *elem)
+{
+	void *elem_ptr;
+
+	elem_ptr = k3_ringacc_get_elm_addr(ring, ring->state.rindex);
+
+	if (ring->state.occ) {
+		memcpy(elem, elem_ptr, (4 << ring->elm_size));
+		k3_dmaring_remove_asel_from_elem(elem);
+
+		ring->state.rindex = (ring->state.rindex + 1) % ring->size;
+		ring->state.occ--;
+		writel(-1 & K3_DMARING_RT_DB_ENTRY_MASK, &ring->rt->db);
+	} else if (ring->state.tdown_complete) {
+		dma_addr_t *value = elem;
+
+		*value = CPPI5_TDCM_MARKER;
+		writel(K3_DMARING_RT_DB_TDOWN_ACK, &ring->rt->db);
+		ring->state.tdown_complete = false;
+	}
+
+	dev_dbg(ring->parent->dev, "%s: occ%d index%d pos_ptr%px\n",
+		__func__, ring->state.occ, ring->state.rindex, elem_ptr);
+	return 0;
+}
+
 static int k3_ringacc_ring_push_mem(struct k3_ring *ring, void *elem)
 {
 	void *elem_ptr;
@@ -899,6 +1143,11 @@ static int k3_ringacc_ring_push_mem(struct k3_ring *ring, void *elem)
 	elem_ptr = k3_ringacc_get_elm_addr(ring, ring->state.windex);
 
 	memcpy(elem_ptr, elem, (4 << ring->elm_size));
+	if (ring->parent->dma_rings) {
+		u64 *addr = elem_ptr;
+
+		*addr |= ((u64)ring->asel << K3_ADDRESS_ASEL_SHIFT);
+	}
 
 	ring->state.windex = (ring->state.windex + 1) % ring->size;
 	ring->state.free--;
@@ -975,12 +1224,12 @@ int k3_ringacc_ring_pop(struct k3_ring *ring, void *elem)
 		return -EINVAL;
 
 	if (!ring->state.occ)
-		ring->state.occ = k3_ringacc_ring_get_occ(ring);
+		k3_ringacc_ring_update_occ(ring);
 
 	dev_dbg(ring->parent->dev, "ring_pop: occ%d index%d\n", ring->state.occ,
 		ring->state.rindex);
 
-	if (!ring->state.occ)
+	if (!ring->state.occ && !ring->state.tdown_complete)
 		return -ENODATA;
 
 	if (ring->ops && ring->ops->pop_head)
@@ -998,7 +1247,7 @@ int k3_ringacc_ring_pop_tail(struct k3_ring *ring, void *elem)
 		return -EINVAL;
 
 	if (!ring->state.occ)
-		ring->state.occ = k3_ringacc_ring_get_occ(ring);
+		k3_ringacc_ring_update_occ(ring);
 
 	dev_dbg(ring->parent->dev, "ring_pop_tail: occ%d index%d\n",
 		ring->state.occ, ring->state.rindex);
@@ -1203,6 +1452,68 @@ static const struct of_device_id k3_ringacc_of_match[] = {
 	{},
 };
 
+struct k3_ringacc *k3_ringacc_dmarings_init(struct platform_device *pdev,
+					    struct k3_ringacc_init_data *data)
+{
+	struct device *dev = &pdev->dev;
+	struct k3_ringacc *ringacc;
+	void __iomem *base_rt;
+	struct resource *res;
+	int i;
+
+	ringacc = devm_kzalloc(dev, sizeof(*ringacc), GFP_KERNEL);
+	if (!ringacc)
+		return ERR_PTR(-ENOMEM);
+
+	ringacc->dev = dev;
+	ringacc->dma_rings = true;
+	ringacc->num_rings = data->num_rings;
+	ringacc->tisci = data->tisci;
+	ringacc->tisci_dev_id = data->tisci_dev_id;
+
+	mutex_init(&ringacc->req_lock);
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "ringrt");
+	base_rt = devm_ioremap_resource(dev, res);
+	if (IS_ERR(base_rt))
+		return base_rt;
+
+	ringacc->rings = devm_kzalloc(dev,
+				      sizeof(*ringacc->rings) *
+				      ringacc->num_rings * 2,
+				      GFP_KERNEL);
+	ringacc->rings_inuse = devm_kcalloc(dev,
+					    BITS_TO_LONGS(ringacc->num_rings),
+					    sizeof(unsigned long), GFP_KERNEL);
+
+	if (!ringacc->rings || !ringacc->rings_inuse)
+		return ERR_PTR(-ENOMEM);
+
+	for (i = 0; i < ringacc->num_rings; i++) {
+		struct k3_ring *ring = &ringacc->rings[i];
+
+		ring->rt = base_rt + K3_DMARING_RT_REGS_STEP * i;
+		ring->parent = ringacc;
+		ring->ring_id = i;
+		ring->proxy_id = K3_RINGACC_PROXY_NOT_USED;
+
+		ring = &ringacc->rings[ringacc->num_rings + i];
+		ring->rt = base_rt + K3_DMARING_RT_REGS_STEP * i +
+			   K3_DMARING_RT_REGS_REVERSE_OFS;
+		ring->parent = ringacc;
+		ring->ring_id = i;
+		ring->proxy_id = K3_RINGACC_PROXY_NOT_USED;
+		ring->flags = K3_RING_FLAG_REVERSE;
+	}
+
+	ringacc->tisci_ring_ops = &ringacc->tisci->ops.rm_ring_ops;
+
+	dev_info(dev, "Number of rings: %u\n", ringacc->num_rings);
+
+	return ringacc;
+}
+EXPORT_SYMBOL_GPL(k3_ringacc_dmarings_init);
+
 static int k3_ringacc_probe(struct platform_device *pdev)
 {
 	const struct ringacc_match_data *match_data;
diff --git a/include/linux/soc/ti/k3-ringacc.h b/include/linux/soc/ti/k3-ringacc.h
index 658dc71d2901..39b022b92598 100644
--- a/include/linux/soc/ti/k3-ringacc.h
+++ b/include/linux/soc/ti/k3-ringacc.h
@@ -70,6 +70,7 @@ struct k3_ring;
  * @dma_dev: Master device which is using and accessing to the ring
  *	memory when the mode is K3_RINGACC_RING_MODE_RING. Memory allocations
  *	should be done using this device.
+ * @asel: Address Space Select value for physical addresses
  */
 struct k3_ring_cfg {
 	u32 size;
@@ -79,6 +80,7 @@ struct k3_ring_cfg {
 	u32 flags;
 
 	struct device *dma_dev;
+	u32 asel;
 };
 
 #define K3_RINGACC_RING_ID_ANY (-1)
@@ -250,4 +252,19 @@ int k3_ringacc_ring_pop_tail(struct k3_ring *ring, void *elem);
 
 u32 k3_ringacc_get_tisci_dev_id(struct k3_ring *ring);
 
+/* DMA ring support */
+struct ti_sci_handle;
+
+/**
+ * struct struct k3_ringacc_init_data - Initialization data for DMA rings
+ */
+struct k3_ringacc_init_data {
+	const struct ti_sci_handle *tisci;
+	u32 tisci_dev_id;
+	u32 num_rings;
+};
+
+struct k3_ringacc *k3_ringacc_dmarings_init(struct platform_device *pdev,
+					    struct k3_ringacc_init_data *data);
+
 #endif /* __SOC_TI_K3_RINGACC_API_H_ */
-- 
cgit v1.2.3


From 5b65781d06ea90ef2f8e51a13352c43c3daa8cdc Mon Sep 17 00:00:00 2001
From: Vignesh Raghavendra <vigneshr@ti.com>
Date: Tue, 8 Dec 2020 11:04:40 +0200
Subject: dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA

This commit adds support for PKTDMA in k3-udma glue driver. Use new
psil_endpoint_config struct to get static data for a given channel or a
flow during setup.  Make sure that the RX flows being mapped to a RX
channel is within the range of flows that is been allocated to that RX
channel.

Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com>
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Link: https://lore.kernel.org/r/20201208090440.31792-21-peter.ujfalusi@ti.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/ti/k3-udma-glue.c    | 291 ++++++++++++++++++++++++++++++++++-----
 drivers/dma/ti/k3-udma-private.c |  24 ++++
 drivers/dma/ti/k3-udma.h         |   4 +
 include/linux/dma/k3-udma-glue.h |   8 ++
 4 files changed, 289 insertions(+), 38 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/dma/ti/k3-udma-glue.c b/drivers/dma/ti/k3-udma-glue.c
index e6ebcd98c02a..4fdd9f06b723 100644
--- a/drivers/dma/ti/k3-udma-glue.c
+++ b/drivers/dma/ti/k3-udma-glue.c
@@ -22,6 +22,7 @@
 
 struct k3_udma_glue_common {
 	struct device *dev;
+	struct device chan_dev;
 	struct udma_dev *udmax;
 	const struct udma_tisci_rm *tisci_rm;
 	struct k3_ringacc *ringacc;
@@ -32,7 +33,8 @@ struct k3_udma_glue_common {
 	bool epib;
 	u32  psdata_size;
 	u32  swdata_size;
-	u32  atype;
+	u32  atype_asel;
+	struct psil_endpoint_config *ep_config;
 };
 
 struct k3_udma_glue_tx_channel {
@@ -53,6 +55,8 @@ struct k3_udma_glue_tx_channel {
 	bool tx_filt_einfo;
 	bool tx_filt_pswords;
 	bool tx_supr_tdpkt;
+
+	int udma_tflow_id;
 };
 
 struct k3_udma_glue_rx_flow {
@@ -81,6 +85,16 @@ struct k3_udma_glue_rx_channel {
 	u32 flows_ready;
 };
 
+static void k3_udma_chan_dev_release(struct device *dev)
+{
+	/* The struct containing the device is devm managed */
+}
+
+static struct class k3_udma_glue_devclass = {
+	.name		= "k3_udma_glue_chan",
+	.dev_release	= k3_udma_chan_dev_release,
+};
+
 #define K3_UDMAX_TDOWN_TIMEOUT_US 1000
 
 static int of_k3_udma_glue_parse(struct device_node *udmax_np,
@@ -100,7 +114,6 @@ static int of_k3_udma_glue_parse_chn(struct device_node *chn_np,
 		const char *name, struct k3_udma_glue_common *common,
 		bool tx_chn)
 {
-	struct psil_endpoint_config *ep_config;
 	struct of_phandle_args dma_spec;
 	u32 thread_id;
 	int ret = 0;
@@ -117,15 +130,26 @@ static int of_k3_udma_glue_parse_chn(struct device_node *chn_np,
 				       &dma_spec))
 		return -ENOENT;
 
+	ret = of_k3_udma_glue_parse(dma_spec.np, common);
+	if (ret)
+		goto out_put_spec;
+
 	thread_id = dma_spec.args[0];
 	if (dma_spec.args_count == 2) {
-		if (dma_spec.args[1] > 2) {
+		if (dma_spec.args[1] > 2 && !xudma_is_pktdma(common->udmax)) {
 			dev_err(common->dev, "Invalid channel atype: %u\n",
 				dma_spec.args[1]);
 			ret = -EINVAL;
 			goto out_put_spec;
 		}
-		common->atype = dma_spec.args[1];
+		if (dma_spec.args[1] > 15 && xudma_is_pktdma(common->udmax)) {
+			dev_err(common->dev, "Invalid channel asel: %u\n",
+				dma_spec.args[1]);
+			ret = -EINVAL;
+			goto out_put_spec;
+		}
+
+		common->atype_asel = dma_spec.args[1];
 	}
 
 	if (tx_chn && !(thread_id & K3_PSIL_DST_THREAD_ID_OFFSET)) {
@@ -139,25 +163,23 @@ static int of_k3_udma_glue_parse_chn(struct device_node *chn_np,
 	}
 
 	/* get psil endpoint config */
-	ep_config = psil_get_ep_config(thread_id);
-	if (IS_ERR(ep_config)) {
+	common->ep_config = psil_get_ep_config(thread_id);
+	if (IS_ERR(common->ep_config)) {
 		dev_err(common->dev,
 			"No configuration for psi-l thread 0x%04x\n",
 			thread_id);
-		ret = PTR_ERR(ep_config);
+		ret = PTR_ERR(common->ep_config);
 		goto out_put_spec;
 	}
 
-	common->epib = ep_config->needs_epib;
-	common->psdata_size = ep_config->psd_size;
+	common->epib = common->ep_config->needs_epib;
+	common->psdata_size = common->ep_config->psd_size;
 
 	if (tx_chn)
 		common->dst_thread = thread_id;
 	else
 		common->src_thread = thread_id;
 
-	ret = of_k3_udma_glue_parse(dma_spec.np, common);
-
 out_put_spec:
 	of_node_put(dma_spec.np);
 	return ret;
@@ -223,7 +245,7 @@ static int k3_udma_glue_cfg_tx_chn(struct k3_udma_glue_tx_channel *tx_chn)
 		req.tx_supr_tdpkt = 1;
 	req.tx_fetch_size = tx_chn->common.hdesc_size >> 2;
 	req.txcq_qnum = k3_ringacc_get_ring_id(tx_chn->ringtxcq);
-	req.tx_atype = tx_chn->common.atype;
+	req.tx_atype = tx_chn->common.atype_asel;
 
 	return tisci_rm->tisci_udmap_ops->tx_ch_cfg(tisci_rm->tisci, &req);
 }
@@ -255,8 +277,14 @@ struct k3_udma_glue_tx_channel *k3_udma_glue_request_tx_chn(struct device *dev,
 						tx_chn->common.psdata_size,
 						tx_chn->common.swdata_size);
 
+	if (xudma_is_pktdma(tx_chn->common.udmax))
+		tx_chn->udma_tchan_id = tx_chn->common.ep_config->mapped_channel_id;
+	else
+		tx_chn->udma_tchan_id = -1;
+
 	/* request and cfg UDMAP TX channel */
-	tx_chn->udma_tchanx = xudma_tchan_get(tx_chn->common.udmax, -1);
+	tx_chn->udma_tchanx = xudma_tchan_get(tx_chn->common.udmax,
+					      tx_chn->udma_tchan_id);
 	if (IS_ERR(tx_chn->udma_tchanx)) {
 		ret = PTR_ERR(tx_chn->udma_tchanx);
 		dev_err(dev, "UDMAX tchanx get err %d\n", ret);
@@ -264,11 +292,34 @@ struct k3_udma_glue_tx_channel *k3_udma_glue_request_tx_chn(struct device *dev,
 	}
 	tx_chn->udma_tchan_id = xudma_tchan_get_id(tx_chn->udma_tchanx);
 
+	tx_chn->common.chan_dev.class = &k3_udma_glue_devclass;
+	tx_chn->common.chan_dev.parent = xudma_get_device(tx_chn->common.udmax);
+	dev_set_name(&tx_chn->common.chan_dev, "tchan%d-0x%04x",
+		     tx_chn->udma_tchan_id, tx_chn->common.dst_thread);
+	ret = device_register(&tx_chn->common.chan_dev);
+	if (ret) {
+		dev_err(dev, "Channel Device registration failed %d\n", ret);
+		tx_chn->common.chan_dev.parent = NULL;
+		goto err;
+	}
+
+	if (xudma_is_pktdma(tx_chn->common.udmax)) {
+		/* prepare the channel device as coherent */
+		tx_chn->common.chan_dev.dma_coherent = true;
+		dma_coerce_mask_and_coherent(&tx_chn->common.chan_dev,
+					     DMA_BIT_MASK(48));
+	}
+
 	atomic_set(&tx_chn->free_pkts, cfg->txcq_cfg.size);
 
+	if (xudma_is_pktdma(tx_chn->common.udmax))
+		tx_chn->udma_tflow_id = tx_chn->common.ep_config->default_flow_id;
+	else
+		tx_chn->udma_tflow_id = tx_chn->udma_tchan_id;
+
 	/* request and cfg rings */
 	ret =  k3_ringacc_request_rings_pair(tx_chn->common.ringacc,
-					     tx_chn->udma_tchan_id, -1,
+					     tx_chn->udma_tflow_id, -1,
 					     &tx_chn->ringtx,
 					     &tx_chn->ringtxcq);
 	if (ret) {
@@ -280,6 +331,12 @@ struct k3_udma_glue_tx_channel *k3_udma_glue_request_tx_chn(struct device *dev,
 	cfg->tx_cfg.dma_dev = k3_udma_glue_tx_get_dma_device(tx_chn);
 	cfg->txcq_cfg.dma_dev = cfg->tx_cfg.dma_dev;
 
+	/* Set the ASEL value for DMA rings of PKTDMA */
+	if (xudma_is_pktdma(tx_chn->common.udmax)) {
+		cfg->tx_cfg.asel = tx_chn->common.atype_asel;
+		cfg->txcq_cfg.asel = tx_chn->common.atype_asel;
+	}
+
 	ret = k3_ringacc_ring_cfg(tx_chn->ringtx, &cfg->tx_cfg);
 	if (ret) {
 		dev_err(dev, "Failed to cfg ringtx %d\n", ret);
@@ -331,6 +388,11 @@ void k3_udma_glue_release_tx_chn(struct k3_udma_glue_tx_channel *tx_chn)
 
 	if (tx_chn->ringtx)
 		k3_ringacc_ring_free(tx_chn->ringtx);
+
+	if (tx_chn->common.chan_dev.parent) {
+		device_unregister(&tx_chn->common.chan_dev);
+		tx_chn->common.chan_dev.parent = NULL;
+	}
 }
 EXPORT_SYMBOL_GPL(k3_udma_glue_release_tx_chn);
 
@@ -443,13 +505,10 @@ void k3_udma_glue_reset_tx_chn(struct k3_udma_glue_tx_channel *tx_chn,
 			       void *data,
 			       void (*cleanup)(void *data, dma_addr_t desc_dma))
 {
+	struct device *dev = tx_chn->common.dev;
 	dma_addr_t desc_dma;
 	int occ_tx, i, ret;
 
-	/* reset TXCQ as it is not input for udma - expected to be empty */
-	if (tx_chn->ringtxcq)
-		k3_ringacc_ring_reset(tx_chn->ringtxcq);
-
 	/*
 	 * TXQ reset need to be special way as it is input for udma and its
 	 * state cached by udma, so:
@@ -458,17 +517,20 @@ void k3_udma_glue_reset_tx_chn(struct k3_udma_glue_tx_channel *tx_chn,
 	 * 3) reset TXQ in a special way
 	 */
 	occ_tx = k3_ringacc_ring_get_occ(tx_chn->ringtx);
-	dev_dbg(tx_chn->common.dev, "TX reset occ_tx %u\n", occ_tx);
+	dev_dbg(dev, "TX reset occ_tx %u\n", occ_tx);
 
 	for (i = 0; i < occ_tx; i++) {
 		ret = k3_ringacc_ring_pop(tx_chn->ringtx, &desc_dma);
 		if (ret) {
-			dev_err(tx_chn->common.dev, "TX reset pop %d\n", ret);
+			if (ret != -ENODATA)
+				dev_err(dev, "TX reset pop %d\n", ret);
 			break;
 		}
 		cleanup(data, desc_dma);
 	}
 
+	/* reset TXCQ as it is not input for udma - expected to be empty */
+	k3_ringacc_ring_reset(tx_chn->ringtxcq);
 	k3_ringacc_ring_reset_dma(tx_chn->ringtx, occ_tx);
 }
 EXPORT_SYMBOL_GPL(k3_udma_glue_reset_tx_chn);
@@ -487,7 +549,12 @@ EXPORT_SYMBOL_GPL(k3_udma_glue_tx_get_txcq_id);
 
 int k3_udma_glue_tx_get_irq(struct k3_udma_glue_tx_channel *tx_chn)
 {
-	tx_chn->virq = k3_ringacc_get_ring_irq_num(tx_chn->ringtxcq);
+	if (xudma_is_pktdma(tx_chn->common.udmax)) {
+		tx_chn->virq = xudma_pktdma_tflow_get_irq(tx_chn->common.udmax,
+							  tx_chn->udma_tflow_id);
+	} else {
+		tx_chn->virq = k3_ringacc_get_ring_irq_num(tx_chn->ringtxcq);
+	}
 
 	return tx_chn->virq;
 }
@@ -496,10 +563,36 @@ EXPORT_SYMBOL_GPL(k3_udma_glue_tx_get_irq);
 struct device *
 	k3_udma_glue_tx_get_dma_device(struct k3_udma_glue_tx_channel *tx_chn)
 {
+	if (xudma_is_pktdma(tx_chn->common.udmax) &&
+	    (tx_chn->common.atype_asel == 14 || tx_chn->common.atype_asel == 15))
+		return &tx_chn->common.chan_dev;
+
 	return xudma_get_device(tx_chn->common.udmax);
 }
 EXPORT_SYMBOL_GPL(k3_udma_glue_tx_get_dma_device);
 
+void k3_udma_glue_tx_dma_to_cppi5_addr(struct k3_udma_glue_tx_channel *tx_chn,
+				       dma_addr_t *addr)
+{
+	if (!xudma_is_pktdma(tx_chn->common.udmax) ||
+	    !tx_chn->common.atype_asel)
+		return;
+
+	*addr |= (u64)tx_chn->common.atype_asel << K3_ADDRESS_ASEL_SHIFT;
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_tx_dma_to_cppi5_addr);
+
+void k3_udma_glue_tx_cppi5_to_dma_addr(struct k3_udma_glue_tx_channel *tx_chn,
+				       dma_addr_t *addr)
+{
+	if (!xudma_is_pktdma(tx_chn->common.udmax) ||
+	    !tx_chn->common.atype_asel)
+		return;
+
+	*addr &= (u64)GENMASK(K3_ADDRESS_ASEL_SHIFT - 1, 0);
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_tx_cppi5_to_dma_addr);
+
 static int k3_udma_glue_cfg_rx_chn(struct k3_udma_glue_rx_channel *rx_chn)
 {
 	const struct udma_tisci_rm *tisci_rm = rx_chn->common.tisci_rm;
@@ -511,8 +604,6 @@ static int k3_udma_glue_cfg_rx_chn(struct k3_udma_glue_rx_channel *rx_chn)
 	req.valid_params = TI_SCI_MSG_VALUE_RM_UDMAP_CH_FETCH_SIZE_VALID |
 			   TI_SCI_MSG_VALUE_RM_UDMAP_CH_CQ_QNUM_VALID |
 			   TI_SCI_MSG_VALUE_RM_UDMAP_CH_CHAN_TYPE_VALID |
-			   TI_SCI_MSG_VALUE_RM_UDMAP_CH_RX_FLOWID_START_VALID |
-			   TI_SCI_MSG_VALUE_RM_UDMAP_CH_RX_FLOWID_CNT_VALID |
 			   TI_SCI_MSG_VALUE_RM_UDMAP_CH_ATYPE_VALID;
 
 	req.nav_id = tisci_rm->tisci_dev_id;
@@ -524,13 +615,16 @@ static int k3_udma_glue_cfg_rx_chn(struct k3_udma_glue_rx_channel *rx_chn)
 	 * req.rxcq_qnum = k3_ringacc_get_ring_id(rx_chn->flows[0].ringrx);
 	 */
 	req.rxcq_qnum = 0xFFFF;
-	if (rx_chn->flow_num && rx_chn->flow_id_base != rx_chn->udma_rchan_id) {
+	if (!xudma_is_pktdma(rx_chn->common.udmax) && rx_chn->flow_num &&
+	    rx_chn->flow_id_base != rx_chn->udma_rchan_id) {
 		/* Default flow + extra ones */
+		req.valid_params |= TI_SCI_MSG_VALUE_RM_UDMAP_CH_RX_FLOWID_START_VALID |
+				    TI_SCI_MSG_VALUE_RM_UDMAP_CH_RX_FLOWID_CNT_VALID;
 		req.flowid_start = rx_chn->flow_id_base;
 		req.flowid_cnt = rx_chn->flow_num;
 	}
 	req.rx_chan_type = TI_SCI_RM_UDMAP_CHAN_TYPE_PKT_PBRR;
-	req.rx_atype = rx_chn->common.atype;
+	req.rx_atype = rx_chn->common.atype_asel;
 
 	ret = tisci_rm->tisci_udmap_ops->rx_ch_cfg(tisci_rm->tisci, &req);
 	if (ret)
@@ -584,10 +678,18 @@ static int k3_udma_glue_cfg_rx_flow(struct k3_udma_glue_rx_channel *rx_chn,
 		goto err_rflow_put;
 	}
 
+	if (xudma_is_pktdma(rx_chn->common.udmax)) {
+		rx_ringfdq_id = flow->udma_rflow_id +
+				xudma_get_rflow_ring_offset(rx_chn->common.udmax);
+		rx_ring_id = 0;
+	} else {
+		rx_ring_id = flow_cfg->ring_rxq_id;
+		rx_ringfdq_id = flow_cfg->ring_rxfdq0_id;
+	}
+
 	/* request and cfg rings */
 	ret =  k3_ringacc_request_rings_pair(rx_chn->common.ringacc,
-					     flow_cfg->ring_rxfdq0_id,
-					     flow_cfg->ring_rxq_id,
+					     rx_ringfdq_id, rx_ring_id,
 					     &flow->ringrxfdq,
 					     &flow->ringrx);
 	if (ret) {
@@ -599,6 +701,12 @@ static int k3_udma_glue_cfg_rx_flow(struct k3_udma_glue_rx_channel *rx_chn,
 	flow_cfg->rx_cfg.dma_dev = k3_udma_glue_rx_get_dma_device(rx_chn);
 	flow_cfg->rxfdq_cfg.dma_dev = flow_cfg->rx_cfg.dma_dev;
 
+	/* Set the ASEL value for DMA rings of PKTDMA */
+	if (xudma_is_pktdma(rx_chn->common.udmax)) {
+		flow_cfg->rx_cfg.asel = rx_chn->common.atype_asel;
+		flow_cfg->rxfdq_cfg.asel = rx_chn->common.atype_asel;
+	}
+
 	ret = k3_ringacc_ring_cfg(flow->ringrx, &flow_cfg->rx_cfg);
 	if (ret) {
 		dev_err(dev, "Failed to cfg ringrx %d\n", ret);
@@ -757,6 +865,7 @@ k3_udma_glue_request_rx_chn_priv(struct device *dev, const char *name,
 				 struct k3_udma_glue_rx_channel_cfg *cfg)
 {
 	struct k3_udma_glue_rx_channel *rx_chn;
+	struct psil_endpoint_config *ep_cfg;
 	int ret, i;
 
 	if (cfg->flow_id_num <= 0)
@@ -784,8 +893,16 @@ k3_udma_glue_request_rx_chn_priv(struct device *dev, const char *name,
 						rx_chn->common.psdata_size,
 						rx_chn->common.swdata_size);
 
+	ep_cfg = rx_chn->common.ep_config;
+
+	if (xudma_is_pktdma(rx_chn->common.udmax))
+		rx_chn->udma_rchan_id = ep_cfg->mapped_channel_id;
+	else
+		rx_chn->udma_rchan_id = -1;
+
 	/* request and cfg UDMAP RX channel */
-	rx_chn->udma_rchanx = xudma_rchan_get(rx_chn->common.udmax, -1);
+	rx_chn->udma_rchanx = xudma_rchan_get(rx_chn->common.udmax,
+					      rx_chn->udma_rchan_id);
 	if (IS_ERR(rx_chn->udma_rchanx)) {
 		ret = PTR_ERR(rx_chn->udma_rchanx);
 		dev_err(dev, "UDMAX rchanx get err %d\n", ret);
@@ -793,12 +910,48 @@ k3_udma_glue_request_rx_chn_priv(struct device *dev, const char *name,
 	}
 	rx_chn->udma_rchan_id = xudma_rchan_get_id(rx_chn->udma_rchanx);
 
-	rx_chn->flow_num = cfg->flow_id_num;
-	rx_chn->flow_id_base = cfg->flow_id_base;
+	rx_chn->common.chan_dev.class = &k3_udma_glue_devclass;
+	rx_chn->common.chan_dev.parent = xudma_get_device(rx_chn->common.udmax);
+	dev_set_name(&rx_chn->common.chan_dev, "rchan%d-0x%04x",
+		     rx_chn->udma_rchan_id, rx_chn->common.src_thread);
+	ret = device_register(&rx_chn->common.chan_dev);
+	if (ret) {
+		dev_err(dev, "Channel Device registration failed %d\n", ret);
+		rx_chn->common.chan_dev.parent = NULL;
+		goto err;
+	}
 
-	/* Use RX channel id as flow id: target dev can't generate flow_id */
-	if (cfg->flow_id_use_rxchan_id)
-		rx_chn->flow_id_base = rx_chn->udma_rchan_id;
+	if (xudma_is_pktdma(rx_chn->common.udmax)) {
+		/* prepare the channel device as coherent */
+		rx_chn->common.chan_dev.dma_coherent = true;
+		dma_coerce_mask_and_coherent(&rx_chn->common.chan_dev,
+					     DMA_BIT_MASK(48));
+	}
+
+	if (xudma_is_pktdma(rx_chn->common.udmax)) {
+		int flow_start = cfg->flow_id_base;
+		int flow_end;
+
+		if (flow_start == -1)
+			flow_start = ep_cfg->flow_start;
+
+		flow_end = flow_start + cfg->flow_id_num - 1;
+		if (flow_start < ep_cfg->flow_start ||
+		    flow_end > (ep_cfg->flow_start + ep_cfg->flow_num - 1)) {
+			dev_err(dev, "Invalid flow range requested\n");
+			ret = -EINVAL;
+			goto err;
+		}
+		rx_chn->flow_id_base = flow_start;
+	} else {
+		rx_chn->flow_id_base = cfg->flow_id_base;
+
+		/* Use RX channel id as flow id: target dev can't generate flow_id */
+		if (cfg->flow_id_use_rxchan_id)
+			rx_chn->flow_id_base = rx_chn->udma_rchan_id;
+	}
+
+	rx_chn->flow_num = cfg->flow_id_num;
 
 	rx_chn->flows = devm_kcalloc(dev, rx_chn->flow_num,
 				     sizeof(*rx_chn->flows), GFP_KERNEL);
@@ -888,6 +1041,24 @@ k3_udma_glue_request_remote_rx_chn(struct device *dev, const char *name,
 		goto err;
 	}
 
+	rx_chn->common.chan_dev.class = &k3_udma_glue_devclass;
+	rx_chn->common.chan_dev.parent = xudma_get_device(rx_chn->common.udmax);
+	dev_set_name(&rx_chn->common.chan_dev, "rchan_remote-0x%04x",
+		     rx_chn->common.src_thread);
+	ret = device_register(&rx_chn->common.chan_dev);
+	if (ret) {
+		dev_err(dev, "Channel Device registration failed %d\n", ret);
+		rx_chn->common.chan_dev.parent = NULL;
+		goto err;
+	}
+
+	if (xudma_is_pktdma(rx_chn->common.udmax)) {
+		/* prepare the channel device as coherent */
+		rx_chn->common.chan_dev.dma_coherent = true;
+		dma_coerce_mask_and_coherent(&rx_chn->common.chan_dev,
+					     DMA_BIT_MASK(48));
+	}
+
 	ret = k3_udma_glue_allocate_rx_flows(rx_chn, cfg);
 	if (ret)
 		goto err;
@@ -940,6 +1111,11 @@ void k3_udma_glue_release_rx_chn(struct k3_udma_glue_rx_channel *rx_chn)
 	if (!IS_ERR_OR_NULL(rx_chn->udma_rchanx))
 		xudma_rchan_put(rx_chn->common.udmax,
 				rx_chn->udma_rchanx);
+
+	if (rx_chn->common.chan_dev.parent) {
+		device_unregister(&rx_chn->common.chan_dev);
+		rx_chn->common.chan_dev.parent = NULL;
+	}
 }
 EXPORT_SYMBOL_GPL(k3_udma_glue_release_rx_chn);
 
@@ -1151,12 +1327,10 @@ void k3_udma_glue_reset_rx_chn(struct k3_udma_glue_rx_channel *rx_chn,
 	/* reset RXCQ as it is not input for udma - expected to be empty */
 	occ_rx = k3_ringacc_ring_get_occ(flow->ringrx);
 	dev_dbg(dev, "RX reset flow %u occ_rx %u\n", flow_num, occ_rx);
-	if (flow->ringrx)
-		k3_ringacc_ring_reset(flow->ringrx);
 
 	/* Skip RX FDQ in case one FDQ is used for the set of flows */
 	if (skip_fdq)
-		return;
+		goto do_reset;
 
 	/*
 	 * RX FDQ reset need to be special way as it is input for udma and its
@@ -1171,13 +1345,17 @@ void k3_udma_glue_reset_rx_chn(struct k3_udma_glue_rx_channel *rx_chn,
 	for (i = 0; i < occ_rx; i++) {
 		ret = k3_ringacc_ring_pop(flow->ringrxfdq, &desc_dma);
 		if (ret) {
-			dev_err(dev, "RX reset pop %d\n", ret);
+			if (ret != -ENODATA)
+				dev_err(dev, "RX reset pop %d\n", ret);
 			break;
 		}
 		cleanup(data, desc_dma);
 	}
 
 	k3_ringacc_ring_reset_dma(flow->ringrxfdq, occ_rx);
+
+do_reset:
+	k3_ringacc_ring_reset(flow->ringrx);
 }
 EXPORT_SYMBOL_GPL(k3_udma_glue_reset_rx_chn);
 
@@ -1207,7 +1385,12 @@ int k3_udma_glue_rx_get_irq(struct k3_udma_glue_rx_channel *rx_chn,
 
 	flow = &rx_chn->flows[flow_num];
 
-	flow->virq = k3_ringacc_get_ring_irq_num(flow->ringrx);
+	if (xudma_is_pktdma(rx_chn->common.udmax)) {
+		flow->virq = xudma_pktdma_rflow_get_irq(rx_chn->common.udmax,
+							flow->udma_rflow_id);
+	} else {
+		flow->virq = k3_ringacc_get_ring_irq_num(flow->ringrx);
+	}
 
 	return flow->virq;
 }
@@ -1216,6 +1399,38 @@ EXPORT_SYMBOL_GPL(k3_udma_glue_rx_get_irq);
 struct device *
 	k3_udma_glue_rx_get_dma_device(struct k3_udma_glue_rx_channel *rx_chn)
 {
+	if (xudma_is_pktdma(rx_chn->common.udmax) &&
+	    (rx_chn->common.atype_asel == 14 || rx_chn->common.atype_asel == 15))
+		return &rx_chn->common.chan_dev;
+
 	return xudma_get_device(rx_chn->common.udmax);
 }
 EXPORT_SYMBOL_GPL(k3_udma_glue_rx_get_dma_device);
+
+void k3_udma_glue_rx_dma_to_cppi5_addr(struct k3_udma_glue_rx_channel *rx_chn,
+				       dma_addr_t *addr)
+{
+	if (!xudma_is_pktdma(rx_chn->common.udmax) ||
+	    !rx_chn->common.atype_asel)
+		return;
+
+	*addr |= (u64)rx_chn->common.atype_asel << K3_ADDRESS_ASEL_SHIFT;
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_rx_dma_to_cppi5_addr);
+
+void k3_udma_glue_rx_cppi5_to_dma_addr(struct k3_udma_glue_rx_channel *rx_chn,
+				       dma_addr_t *addr)
+{
+	if (!xudma_is_pktdma(rx_chn->common.udmax) ||
+	    !rx_chn->common.atype_asel)
+		return;
+
+	*addr &= (u64)GENMASK(K3_ADDRESS_ASEL_SHIFT - 1, 0);
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_rx_cppi5_to_dma_addr);
+
+static int __init k3_udma_glue_class_init(void)
+{
+	return class_register(&k3_udma_glue_devclass);
+}
+arch_initcall(k3_udma_glue_class_init);
diff --git a/drivers/dma/ti/k3-udma-private.c b/drivers/dma/ti/k3-udma-private.c
index 5436b19d656e..eb4795c089bd 100644
--- a/drivers/dma/ti/k3-udma-private.c
+++ b/drivers/dma/ti/k3-udma-private.c
@@ -157,3 +157,27 @@ void xudma_##res##rt_write(struct udma_##res *p, int reg, u32 val)	\
 EXPORT_SYMBOL(xudma_##res##rt_write)
 XUDMA_RT_IO_FUNCTIONS(tchan);
 XUDMA_RT_IO_FUNCTIONS(rchan);
+
+int xudma_is_pktdma(struct udma_dev *ud)
+{
+	return ud->match_data->type == DMA_TYPE_PKTDMA;
+}
+EXPORT_SYMBOL(xudma_is_pktdma);
+
+int xudma_pktdma_tflow_get_irq(struct udma_dev *ud, int udma_tflow_id)
+{
+	const struct udma_oes_offsets *oes = &ud->soc_data->oes;
+
+	return ti_sci_inta_msi_get_virq(ud->dev, udma_tflow_id +
+					oes->pktdma_tchan_flow);
+}
+EXPORT_SYMBOL(xudma_pktdma_tflow_get_irq);
+
+int xudma_pktdma_rflow_get_irq(struct udma_dev *ud, int udma_rflow_id)
+{
+	const struct udma_oes_offsets *oes = &ud->soc_data->oes;
+
+	return ti_sci_inta_msi_get_virq(ud->dev, udma_rflow_id +
+					oes->pktdma_rchan_flow);
+}
+EXPORT_SYMBOL(xudma_pktdma_rflow_get_irq);
diff --git a/drivers/dma/ti/k3-udma.h b/drivers/dma/ti/k3-udma.h
index ccb19f286daf..d349c6d482ae 100644
--- a/drivers/dma/ti/k3-udma.h
+++ b/drivers/dma/ti/k3-udma.h
@@ -157,4 +157,8 @@ void xudma_rchanrt_write(struct udma_rchan *rchan, int reg, u32 val);
 bool xudma_rflow_is_gp(struct udma_dev *ud, int id);
 int xudma_get_rflow_ring_offset(struct udma_dev *ud);
 
+int xudma_is_pktdma(struct udma_dev *ud);
+
+int xudma_pktdma_tflow_get_irq(struct udma_dev *ud, int udma_tflow_id);
+int xudma_pktdma_rflow_get_irq(struct udma_dev *ud, int udma_rflow_id);
 #endif /* K3_UDMA_H_ */
diff --git a/include/linux/dma/k3-udma-glue.h b/include/linux/dma/k3-udma-glue.h
index d7c12f31377c..e443be4d3b4b 100644
--- a/include/linux/dma/k3-udma-glue.h
+++ b/include/linux/dma/k3-udma-glue.h
@@ -43,6 +43,10 @@ u32 k3_udma_glue_tx_get_txcq_id(struct k3_udma_glue_tx_channel *tx_chn);
 int k3_udma_glue_tx_get_irq(struct k3_udma_glue_tx_channel *tx_chn);
 struct device *
 	k3_udma_glue_tx_get_dma_device(struct k3_udma_glue_tx_channel *tx_chn);
+void k3_udma_glue_tx_dma_to_cppi5_addr(struct k3_udma_glue_tx_channel *tx_chn,
+				       dma_addr_t *addr);
+void k3_udma_glue_tx_cppi5_to_dma_addr(struct k3_udma_glue_tx_channel *tx_chn,
+				       dma_addr_t *addr);
 
 enum {
 	K3_UDMA_GLUE_SRC_TAG_LO_KEEP = 0,
@@ -134,5 +138,9 @@ int k3_udma_glue_rx_flow_disable(struct k3_udma_glue_rx_channel *rx_chn,
 				 u32 flow_idx);
 struct device *
 	k3_udma_glue_rx_get_dma_device(struct k3_udma_glue_rx_channel *rx_chn);
+void k3_udma_glue_rx_dma_to_cppi5_addr(struct k3_udma_glue_rx_channel *rx_chn,
+				       dma_addr_t *addr);
+void k3_udma_glue_rx_cppi5_to_dma_addr(struct k3_udma_glue_rx_channel *rx_chn,
+				       dma_addr_t *addr);
 
 #endif /* K3_UDMA_GLUE_H_ */
-- 
cgit v1.2.3


From e998879d4fb7991856916972168cf27c0d86ed12 Mon Sep 17 00:00:00 2001
From: Ashish Kalra <ashish.kalra@amd.com>
Date: Thu, 10 Dec 2020 01:25:15 +0000
Subject: x86,swiotlb: Adjust SWIOTLB bounce buffer size for SEV guests

For SEV, all DMA to and from guest has to use shared (un-encrypted) pages.
SEV uses SWIOTLB to make this happen without requiring changes to device
drivers.  However, depending on the workload being run, the default 64MB
of it might not be enough and it may run out of buffers to use for DMA,
resulting in I/O errors and/or performance degradation for high
I/O workloads.

Adjust the default size of SWIOTLB for SEV guests using a
percentage of the total memory available to guest for the SWIOTLB buffers.

Adds a new sev_setup_arch() function which is invoked from setup_arch()
and it calls into a new swiotlb generic code function swiotlb_adjust_size()
to do the SWIOTLB buffer adjustment.

v5 fixed build errors and warnings as
Reported-by: kbuild test robot <lkp@intel.com>

Signed-off-by: Ashish Kalra <ashish.kalra@amd.com>
Co-developed-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 arch/x86/include/asm/mem_encrypt.h |  2 ++
 arch/x86/kernel/setup.c            |  6 ++++++
 arch/x86/mm/mem_encrypt.c          | 31 +++++++++++++++++++++++++++++++
 include/linux/swiotlb.h            |  8 ++++++++
 kernel/dma/swiotlb.c               | 20 ++++++++++++++++++--
 5 files changed, 65 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index 2f62bbdd9d12..31c4df123aa0 100644
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -37,6 +37,7 @@ void __init sme_map_bootdata(char *real_mode_data);
 void __init sme_unmap_bootdata(char *real_mode_data);
 
 void __init sme_early_init(void);
+void __init sev_setup_arch(void);
 
 void __init sme_encrypt_kernel(struct boot_params *bp);
 void __init sme_enable(struct boot_params *bp);
@@ -69,6 +70,7 @@ static inline void __init sme_map_bootdata(char *real_mode_data) { }
 static inline void __init sme_unmap_bootdata(char *real_mode_data) { }
 
 static inline void __init sme_early_init(void) { }
+static inline void __init sev_setup_arch(void) { }
 
 static inline void __init sme_encrypt_kernel(struct boot_params *bp) { }
 static inline void __init sme_enable(struct boot_params *bp) { }
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 84f581c91db4..874b2c17af41 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1054,6 +1054,12 @@ void __init setup_arch(char **cmdline_p)
 	memblock_set_current_limit(ISA_END_ADDRESS);
 	e820__memblock_setup();
 
+	/*
+	 * Needs to run after memblock setup because it needs the physical
+	 * memory size.
+	 */
+	sev_setup_arch();
+
 	reserve_bios_regions();
 
 	efi_fake_memmap();
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index bc0833713be9..c79e5736ab2b 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -198,6 +198,37 @@ void __init sme_early_init(void)
 		swiotlb_force = SWIOTLB_FORCE;
 }
 
+void __init sev_setup_arch(void)
+{
+	phys_addr_t total_mem = memblock_phys_mem_size();
+	unsigned long size;
+
+	if (!sev_active())
+		return;
+
+	/*
+	 * For SEV, all DMA has to occur via shared/unencrypted pages.
+	 * SEV uses SWIOTLB to make this happen without changing device
+	 * drivers. However, depending on the workload being run, the
+	 * default 64MB of SWIOTLB may not be enough and SWIOTLB may
+	 * run out of buffers for DMA, resulting in I/O errors and/or
+	 * performance degradation especially with high I/O workloads.
+	 *
+	 * Adjust the default size of SWIOTLB for SEV guests using
+	 * a percentage of guest memory for SWIOTLB buffers.
+	 * Also, as the SWIOTLB bounce buffer memory is allocated
+	 * from low memory, ensure that the adjusted size is within
+	 * the limits of low available memory.
+	 *
+	 * The percentage of guest memory used here for SWIOTLB buffers
+	 * is more of an approximation of the static adjustment which
+	 * 64MB for <1G, and ~128M to 256M for 1G-to-4G, i.e., the 6%
+	 */
+	size = total_mem * 6 / 100;
+	size = clamp_val(size, IO_TLB_DEFAULT_SIZE, SZ_1G);
+	swiotlb_adjust_size(size);
+}
+
 static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc)
 {
 	pgprot_t old_prot, new_prot;
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index fbdc65782195..d9c9fc9ca5d2 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -30,6 +30,9 @@ enum swiotlb_force {
  */
 #define IO_TLB_SHIFT 11
 
+/* default to 64MB */
+#define IO_TLB_DEFAULT_SIZE (64UL<<20)
+
 extern void swiotlb_init(int verbose);
 int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose);
 extern unsigned long swiotlb_nr_tbl(void);
@@ -78,6 +81,7 @@ void __init swiotlb_exit(void);
 unsigned int swiotlb_max_segment(void);
 size_t swiotlb_max_mapping_size(struct device *dev);
 bool is_swiotlb_active(void);
+void __init swiotlb_adjust_size(unsigned long new_size);
 #else
 #define swiotlb_force SWIOTLB_NO_FORCE
 static inline bool is_swiotlb_buffer(phys_addr_t paddr)
@@ -100,6 +104,10 @@ static inline bool is_swiotlb_active(void)
 {
 	return false;
 }
+
+static inline void swiotlb_adjust_size(unsigned long new_size)
+{
+}
 #endif /* CONFIG_SWIOTLB */
 
 extern void swiotlb_print_info(void);
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 781b9dca197c..7c42df6e6100 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -152,8 +152,6 @@ void swiotlb_set_max_segment(unsigned int val)
 		max_segment = rounddown(val, PAGE_SIZE);
 }
 
-/* default to 64MB */
-#define IO_TLB_DEFAULT_SIZE (64UL<<20)
 unsigned long swiotlb_size_or_default(void)
 {
 	unsigned long size;
@@ -163,6 +161,24 @@ unsigned long swiotlb_size_or_default(void)
 	return size ? size : (IO_TLB_DEFAULT_SIZE);
 }
 
+void __init swiotlb_adjust_size(unsigned long new_size)
+{
+	unsigned long size;
+
+	/*
+	 * If swiotlb parameter has not been specified, give a chance to
+	 * architectures such as those supporting memory encryption to
+	 * adjust/expand SWIOTLB size for their use.
+	 */
+	if (!io_tlb_nslabs) {
+		size = ALIGN(new_size, 1 << IO_TLB_SHIFT);
+		io_tlb_nslabs = size >> IO_TLB_SHIFT;
+		io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
+
+		pr_info("SWIOTLB bounce buffer size adjusted to %luMB", size >> 20);
+	}
+}
+
 void swiotlb_print_info(void)
 {
 	unsigned long bytes = io_tlb_nslabs << IO_TLB_SHIFT;
-- 
cgit v1.2.3


From 14dc3983b5dff513a90bd5a8cc90acaf7867c3d0 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 11 Dec 2020 13:36:38 -0800
Subject: kbuild: avoid static_assert for genksyms

genksyms does not know or care about the _Static_assert() built-in, and
sometimes falls back to ignoring the later symbols, which causes
undefined behavior such as

  WARNING: modpost: EXPORT symbol "ethtool_set_ethtool_phy_ops" [vmlinux] version generation failed, symbol will not be versioned.
  ld: net/ethtool/common.o: relocation R_AARCH64_ABS32 against `__crc_ethtool_set_ethtool_phy_ops' can not be used when making a shared object
  net/ethtool/common.o:(_ftrace_annotated_branch+0x0): dangerous relocation: unsupported relocation

Redefine static_assert for genksyms to avoid that.

Link: https://lkml.kernel.org/r/20201203230955.1482058-1-arnd@kernel.org
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Suggested-by: Ard Biesheuvel <ardb@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Michal Marek <michal.lkml@markovi.net>
Cc: Kees Cook <keescook@chromium.org>
Cc: Rikard Falkeborn <rikard.falkeborn@gmail.com>
Cc: Marco Elver <elver@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/build_bug.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/build_bug.h b/include/linux/build_bug.h
index e3a0be2c90ad..7bb66e15b481 100644
--- a/include/linux/build_bug.h
+++ b/include/linux/build_bug.h
@@ -77,4 +77,9 @@
 #define static_assert(expr, ...) __static_assert(expr, ##__VA_ARGS__, #expr)
 #define __static_assert(expr, msg, ...) _Static_assert(expr, msg)
 
+#ifdef __GENKSYMS__
+/* genksyms gets confused by _Static_assert */
+#define _Static_assert(expr, ...)
+#endif
+
 #endif	/* _LINUX_BUILD_BUG_H */
-- 
cgit v1.2.3


From 6e7b64b9dd6d96537d816ea07ec26b7dedd397b9 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 11 Dec 2020 13:36:46 -0800
Subject: elfcore: fix building with clang

kernel/elfcore.c only contains weak symbols, which triggers a bug with
clang in combination with recordmcount:

  Cannot find symbol for section 2: .text.
  kernel/elfcore.o: failed

Move the empty stubs into linux/elfcore.h as inline functions.  As only
two architectures use these, just use the architecture specific Kconfig
symbols to key off the declaration.

Link: https://lkml.kernel.org/r/20201204165742.3815221-2-arnd@kernel.org
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Nathan Chancellor <natechancellor@gmail.com>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Barret Rhoden <brho@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/elfcore.h | 22 ++++++++++++++++++++++
 kernel/Makefile         |  1 -
 kernel/elfcore.c        | 26 --------------------------
 3 files changed, 22 insertions(+), 27 deletions(-)
 delete mode 100644 kernel/elfcore.c

(limited to 'include/linux')

diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h
index 46c3d691f677..de51c1bef27d 100644
--- a/include/linux/elfcore.h
+++ b/include/linux/elfcore.h
@@ -104,6 +104,7 @@ static inline int elf_core_copy_task_fpregs(struct task_struct *t, struct pt_reg
 #endif
 }
 
+#if defined(CONFIG_UM) || defined(CONFIG_IA64)
 /*
  * These functions parameterize elf_core_dump in fs/binfmt_elf.c to write out
  * extra segments containing the gate DSO contents.  Dumping its
@@ -118,5 +119,26 @@ elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset);
 extern int
 elf_core_write_extra_data(struct coredump_params *cprm);
 extern size_t elf_core_extra_data_size(void);
+#else
+static inline Elf_Half elf_core_extra_phdrs(void)
+{
+	return 0;
+}
+
+static inline int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset)
+{
+	return 1;
+}
+
+static inline int elf_core_write_extra_data(struct coredump_params *cprm)
+{
+	return 1;
+}
+
+static inline size_t elf_core_extra_data_size(void)
+{
+	return 0;
+}
+#endif
 
 #endif /* _LINUX_ELFCORE_H */
diff --git a/kernel/Makefile b/kernel/Makefile
index af601b9bda0e..6c9f19911be0 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -97,7 +97,6 @@ obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
 obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o
 obj-$(CONFIG_TRACEPOINTS) += tracepoint.o
 obj-$(CONFIG_LATENCYTOP) += latencytop.o
-obj-$(CONFIG_ELFCORE) += elfcore.o
 obj-$(CONFIG_FUNCTION_TRACER) += trace/
 obj-$(CONFIG_TRACING) += trace/
 obj-$(CONFIG_TRACE_CLOCK) += trace/
diff --git a/kernel/elfcore.c b/kernel/elfcore.c
deleted file mode 100644
index 57fb4dcff434..000000000000
--- a/kernel/elfcore.c
+++ /dev/null
@@ -1,26 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/elf.h>
-#include <linux/fs.h>
-#include <linux/mm.h>
-#include <linux/binfmts.h>
-#include <linux/elfcore.h>
-
-Elf_Half __weak elf_core_extra_phdrs(void)
-{
-	return 0;
-}
-
-int __weak elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset)
-{
-	return 1;
-}
-
-int __weak elf_core_write_extra_data(struct coredump_params *cprm)
-{
-	return 1;
-}
-
-size_t __weak elf_core_extra_data_size(void)
-{
-	return 0;
-}
-- 
cgit v1.2.3


From 2ab695aa8eb8f3226f68a2b91fc6103b56fcb57d Mon Sep 17 00:00:00 2001
From: Saravana Kannan <saravanak@google.com>
Date: Fri, 11 Dec 2020 12:26:29 -0800
Subject: ACPI: Use fwnode_init() to set up fwnode

Commit 01bb86b380a3 ("driver core: Add fwnode_init()") was supposed to
fix up all instances of fwnode creation to use fwnode_init(). But looks
like this instance was missed. This causes a NULL pointer dereference
during device_add() [1]. So, fix it.

[   60.792324][    T1] Call trace:
[   60.795495][    T1]  device_add+0xf60/0x16b0
__fw_devlink_link_to_consumers at drivers/base/core.c:1583
(inlined by) fw_devlink_link_device at drivers/base/core.c:1726
(inlined by) device_add at drivers/base/core.c:3088
[   60.799813][    T1]  platform_device_add+0x274/0x628
[   60.804833][    T1]  acpi_iort_init+0x9d8/0xc50
[   60.809415][    T1]  acpi_init+0x45c/0x4e8
[   60.813556][    T1]  do_one_initcall+0x170/0xb70
[   60.818224][    T1]  kernel_init_freeable+0x6a8/0x734
[   60.823332][    T1]  kernel_init+0x18/0x12c
[   60.827566][    T1]  ret_from_fork+0x10/0x1c
[   60.838756][    T1] ---[ end trace fa5c8ce17a226d83 ]---

[1] - https://lore.kernel.org/linux-arm-kernel/02e7047071f0b54b046ac472adeeb3fafabc643c.camel@redhat.com/

Fixes: 01bb86b380a3 ("driver core: Add fwnode_init()")
Reported-by: Qian Cai <qcai@redhat.com>
Suggested-by: Robin Murphy <robin.murphy@arm.com>
Tested-by: Marc Zyngier <maz@kernel.org>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Saravana Kannan <saravanak@google.com>
Link: https://lore.kernel.org/r/20201211202629.2164655-1-saravanak@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/acpi.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 39263c6b52e1..2630c2e953f7 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -55,7 +55,7 @@ static inline struct fwnode_handle *acpi_alloc_fwnode_static(void)
 	if (!fwnode)
 		return NULL;
 
-	fwnode->ops = &acpi_static_fwnode_ops;
+	fwnode_init(fwnode, &acpi_static_fwnode_ops);
 
 	return fwnode;
 }
-- 
cgit v1.2.3


From 98b89b649fce39dacb9dc036d6d0fdb8caff73f7 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Fri, 9 Oct 2020 16:03:01 -0600
Subject: signal: kill JOBCTL_TASK_WORK

It's no longer used, get rid of it.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/sched/jobctl.h |  4 +---
 kernel/signal.c              | 20 --------------------
 2 files changed, 1 insertion(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/jobctl.h b/include/linux/sched/jobctl.h
index d2b4204ba4d3..fa067de9f1a9 100644
--- a/include/linux/sched/jobctl.h
+++ b/include/linux/sched/jobctl.h
@@ -19,7 +19,6 @@ struct task_struct;
 #define JOBCTL_TRAPPING_BIT	21	/* switching to TRACED */
 #define JOBCTL_LISTENING_BIT	22	/* ptracer is listening for events */
 #define JOBCTL_TRAP_FREEZE_BIT	23	/* trap for cgroup freezer */
-#define JOBCTL_TASK_WORK_BIT	24	/* set by TWA_SIGNAL */
 
 #define JOBCTL_STOP_DEQUEUED	(1UL << JOBCTL_STOP_DEQUEUED_BIT)
 #define JOBCTL_STOP_PENDING	(1UL << JOBCTL_STOP_PENDING_BIT)
@@ -29,10 +28,9 @@ struct task_struct;
 #define JOBCTL_TRAPPING		(1UL << JOBCTL_TRAPPING_BIT)
 #define JOBCTL_LISTENING	(1UL << JOBCTL_LISTENING_BIT)
 #define JOBCTL_TRAP_FREEZE	(1UL << JOBCTL_TRAP_FREEZE_BIT)
-#define JOBCTL_TASK_WORK	(1UL << JOBCTL_TASK_WORK_BIT)
 
 #define JOBCTL_TRAP_MASK	(JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY)
-#define JOBCTL_PENDING_MASK	(JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK | JOBCTL_TASK_WORK)
+#define JOBCTL_PENDING_MASK	(JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK)
 
 extern bool task_set_jobctl_pending(struct task_struct *task, unsigned long mask);
 extern void task_clear_jobctl_trapping(struct task_struct *task);
diff --git a/kernel/signal.c b/kernel/signal.c
index 923230ff6cfc..cf8b057ca2ac 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2556,26 +2556,6 @@ bool get_signal(struct ksignal *ksig)
 
 relock:
 	spin_lock_irq(&sighand->siglock);
-	/*
-	 * Make sure we can safely read ->jobctl() in task_work add. As Oleg
-	 * states:
-	 *
-	 * It pairs with mb (implied by cmpxchg) before READ_ONCE. So we
-	 * roughly have
-	 *
-	 *	task_work_add:				get_signal:
-	 *	STORE(task->task_works, new_work);	STORE(task->jobctl);
-	 *	mb();					mb();
-	 *	LOAD(task->jobctl);			LOAD(task->task_works);
-	 *
-	 * and we can rely on STORE-MB-LOAD [ in task_work_add].
-	 */
-	smp_store_mb(current->jobctl, current->jobctl & ~JOBCTL_TASK_WORK);
-	if (unlikely(current->task_works)) {
-		spin_unlock_irq(&sighand->siglock);
-		task_work_run();
-		goto relock;
-	}
 
 	/*
 	 * Every stopped thread goes here after wakeup. Check to see if
-- 
cgit v1.2.3


From e296dc4996b8094ccde45d19090d804c4103513e Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Fri, 9 Oct 2020 16:04:39 -0600
Subject: kernel: remove checking for TIF_NOTIFY_SIGNAL

It's available everywhere now, no need to check or add dummy defines.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/entry-common.h | 4 ----
 include/linux/sched/signal.h | 2 --
 include/linux/tracehook.h    | 4 ----
 kernel/signal.c              | 2 --
 4 files changed, 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index b9711e813ec2..abec3a5ae799 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -37,10 +37,6 @@
 # define _TIF_UPROBE			(0)
 #endif
 
-#ifndef _TIF_NOTIFY_SIGNAL
-# define _TIF_NOTIFY_SIGNAL		(0)
-#endif
-
 /*
  * TIF flags handled in syscall_enter_from_user_mode()
  */
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index bd5afa076189..24b7b862e043 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -360,7 +360,6 @@ static inline int task_sigpending(struct task_struct *p)
 
 static inline int signal_pending(struct task_struct *p)
 {
-#if defined(TIF_NOTIFY_SIGNAL)
 	/*
 	 * TIF_NOTIFY_SIGNAL isn't really a signal, but it requires the same
 	 * behavior in terms of ensuring that we break out of wait loops
@@ -368,7 +367,6 @@ static inline int signal_pending(struct task_struct *p)
 	 */
 	if (unlikely(test_tsk_thread_flag(p, TIF_NOTIFY_SIGNAL)))
 		return 1;
-#endif
 	return task_sigpending(p);
 }
 
diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h
index f7d82e4fafd6..ee9ab7dbc8c3 100644
--- a/include/linux/tracehook.h
+++ b/include/linux/tracehook.h
@@ -205,12 +205,10 @@ static inline void tracehook_notify_resume(struct pt_regs *regs)
  */
 static inline void tracehook_notify_signal(void)
 {
-#if defined(TIF_NOTIFY_SIGNAL)
 	clear_thread_flag(TIF_NOTIFY_SIGNAL);
 	smp_mb__after_atomic();
 	if (current->task_works)
 		task_work_run();
-#endif
 }
 
 /*
@@ -218,11 +216,9 @@ static inline void tracehook_notify_signal(void)
  */
 static inline void set_notify_signal(struct task_struct *task)
 {
-#if defined(TIF_NOTIFY_SIGNAL)
 	if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) &&
 	    !wake_up_state(task, TASK_INTERRUPTIBLE))
 		kick_process(task);
-#endif
 }
 
 #endif	/* <linux/tracehook.h> */
diff --git a/kernel/signal.c b/kernel/signal.c
index cf8b057ca2ac..ccd530509201 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2535,14 +2535,12 @@ bool get_signal(struct ksignal *ksig)
 	 * that the arch handlers don't all have to do it. If we get here
 	 * without TIF_SIGPENDING, just exit after running signal work.
 	 */
-#ifdef TIF_NOTIFY_SIGNAL
 	if (!IS_ENABLED(CONFIG_GENERIC_ENTRY)) {
 		if (test_thread_flag(TIF_NOTIFY_SIGNAL))
 			tracehook_notify_signal();
 		if (!task_sigpending(current))
 			return false;
 	}
-#endif
 
 	if (unlikely(uprobe_deny_signal()))
 		return false;
-- 
cgit v1.2.3


From 3cabca87b329cbcbdf295be0094adbd72c7b1f67 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sat, 12 Dec 2020 18:29:20 +0100
Subject: ntp: Fix prototype in the !CONFIG_GENERIC_CMOS_UPDATE case

In the !CONFIG_GENERIC_CMOS_UPDATE case the update_persistent_clock64() function
gets defined as a stub in ntp.c - make the prototype in <linux/timekeeping.h>
conditional on CONFIG_GENERIC_CMOS_UPDATE as well.

Fixes: 76e87d96b30b5 ("ntp: Consolidate the RTC update implementation")
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/timekeeping.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 7f7e4a3f4394..929d3f3937c0 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -303,6 +303,8 @@ extern int persistent_clock_is_local;
 extern void read_persistent_clock64(struct timespec64 *ts);
 void read_persistent_wall_and_boot_offset(struct timespec64 *wall_clock,
 					  struct timespec64 *boot_offset);
+#ifdef CONFIG_GENERIC_CMOS_UPDATE
 extern int update_persistent_clock64(struct timespec64 now);
+#endif
 
 #endif
-- 
cgit v1.2.3


From 9a20f6f4e6ba9713605fbf7e7426ca22f1181545 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Fri, 4 Dec 2020 15:16:46 -0500
Subject: SUNRPC: Fixes for xdr_align_data()

The main use case right now for xdr_align_data() is to shift the page
data to the left, and in practice shrink the total XDR data buffer.
This patch ensures that we fix up the accounting for the buffer length
as we shift that data around.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 include/linux/sunrpc/xdr.h |   2 +-
 net/sunrpc/xdr.c           | 174 ++++++++++++++++++++++++++++++++++-----------
 2 files changed, 133 insertions(+), 43 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 9548d075e06d..2b4e44bb0654 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -252,7 +252,7 @@ extern __be32 *xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes);
 extern unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len);
 extern void xdr_enter_page(struct xdr_stream *xdr, unsigned int len);
 extern int xdr_process_buf(struct xdr_buf *buf, unsigned int offset, unsigned int len, int (*actor)(struct scatterlist *, void *), void *data);
-extern uint64_t xdr_align_data(struct xdr_stream *, uint64_t, uint32_t);
+extern unsigned int xdr_align_data(struct xdr_stream *, unsigned int offset, unsigned int length);
 extern uint64_t xdr_expand_hole(struct xdr_stream *, uint64_t, uint64_t);
 
 /**
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 5833329c132c..c474339ba9ac 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -266,26 +266,6 @@ _shift_data_left_pages(struct page **pages, size_t pgto_base,
 	} while ((len -= copy) != 0);
 }
 
-static void
-_shift_data_left_tail(struct xdr_buf *buf, unsigned int pgto, size_t len)
-{
-	struct kvec *tail = buf->tail;
-
-	if (len > tail->iov_len)
-		len = tail->iov_len;
-
-	_copy_to_pages(buf->pages,
-		       buf->page_base + pgto,
-		       (char *)tail->iov_base,
-		       len);
-	tail->iov_len -= len;
-
-	if (tail->iov_len > 0)
-		memmove((char *)tail->iov_base,
-				tail->iov_base + len,
-				tail->iov_len);
-}
-
 /**
  * _shift_data_right_pages
  * @pages: vector of pages containing both the source and dest memory area.
@@ -516,6 +496,109 @@ _zero_pages(struct page **pages, size_t pgbase, size_t len)
 	} while ((len -= zero) != 0);
 }
 
+static void xdr_buf_tail_copy_left(const struct xdr_buf *buf, unsigned int base,
+				   unsigned int len, unsigned int shift)
+{
+	const struct kvec *tail = buf->tail;
+
+	if (base >= tail->iov_len)
+		return;
+	if (len > tail->iov_len - base)
+		len = tail->iov_len - base;
+	/* Shift data into head */
+	if (shift > buf->page_len + base) {
+		const struct kvec *head = buf->head;
+		unsigned int hdto =
+			head->iov_len + buf->page_len + base - shift;
+		unsigned int hdlen = len;
+
+		if (WARN_ONCE(shift > head->iov_len + buf->page_len + base,
+			      "SUNRPC: Misaligned data.\n"))
+			return;
+		if (hdto + hdlen > head->iov_len)
+			hdlen = head->iov_len - hdto;
+		memcpy(head->iov_base + hdto, tail->iov_base + base, hdlen);
+		base += hdlen;
+		len -= hdlen;
+		if (!len)
+			return;
+	}
+	/* Shift data into pages */
+	if (shift > base) {
+		unsigned int pgto = buf->page_len + base - shift;
+		unsigned int pglen = len;
+
+		if (pgto + pglen > buf->page_len)
+			pglen = buf->page_len - pgto;
+		_copy_to_pages(buf->pages, buf->page_base + pgto,
+			       tail->iov_base + base, pglen);
+		base += pglen;
+		len -= pglen;
+		if (!len)
+			return;
+	}
+	memmove(tail->iov_base + base - shift, tail->iov_base + base, len);
+}
+
+static void xdr_buf_pages_copy_left(const struct xdr_buf *buf,
+				    unsigned int base, unsigned int len,
+				    unsigned int shift)
+{
+	unsigned int pgto;
+
+	if (base >= buf->page_len)
+		return;
+	if (len > buf->page_len - base)
+		len = buf->page_len - base;
+	/* Shift data into head */
+	if (shift > base) {
+		const struct kvec *head = buf->head;
+		unsigned int hdto = head->iov_len + base - shift;
+		unsigned int hdlen = len;
+
+		if (WARN_ONCE(shift > head->iov_len + base,
+			      "SUNRPC: Misaligned data.\n"))
+			return;
+		if (hdto + hdlen > head->iov_len)
+			hdlen = head->iov_len - hdto;
+		_copy_from_pages(head->iov_base + hdto, buf->pages,
+				 buf->page_base + base, hdlen);
+		base += hdlen;
+		len -= hdlen;
+		if (!len)
+			return;
+	}
+	pgto = base - shift;
+	_shift_data_left_pages(buf->pages, buf->page_base + pgto,
+			       buf->page_base + base, len);
+}
+
+static void xdr_buf_tail_shift_left(const struct xdr_buf *buf,
+				    unsigned int base, unsigned int len,
+				    unsigned int shift)
+{
+	if (!shift || !len)
+		return;
+	xdr_buf_tail_copy_left(buf, base, len, shift);
+}
+
+static void xdr_buf_pages_shift_left(const struct xdr_buf *buf,
+				     unsigned int base, unsigned int len,
+				     unsigned int shift)
+{
+	if (!shift || !len)
+		return;
+	if (base >= buf->page_len) {
+		xdr_buf_tail_shift_left(buf, base - buf->page_len, len, shift);
+		return;
+	}
+	xdr_buf_pages_copy_left(buf, base, len, shift);
+	len += base;
+	if (len <= buf->page_len)
+		return;
+	xdr_buf_tail_copy_left(buf, 0, len - buf->page_len, shift);
+}
+
 /**
  * xdr_shrink_bufhead
  * @buf: xdr_buf
@@ -1261,38 +1344,45 @@ unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len)
 }
 EXPORT_SYMBOL_GPL(xdr_read_pages);
 
-uint64_t xdr_align_data(struct xdr_stream *xdr, uint64_t offset, uint32_t length)
+unsigned int xdr_align_data(struct xdr_stream *xdr, unsigned int offset,
+			    unsigned int length)
 {
 	struct xdr_buf *buf = xdr->buf;
-	unsigned int from, bytes;
-	unsigned int shift = 0;
-
-	if ((offset + length) < offset ||
-	    (offset + length) > buf->page_len)
-		length = buf->page_len - offset;
+	unsigned int from, bytes, len;
+	unsigned int shift;
 
 	xdr_realign_pages(xdr);
 	from = xdr_page_pos(xdr);
-	bytes = xdr_stream_remaining(xdr);
-	if (length < bytes)
-		bytes = length;
+
+	if (from >= buf->page_len + buf->tail->iov_len)
+		return 0;
+	if (from + buf->head->iov_len >= buf->len)
+		return 0;
+
+	len = buf->len - buf->head->iov_len;
+
+	/* We only shift data left! */
+	if (WARN_ONCE(from < offset, "SUNRPC: misaligned data src=%u dst=%u\n",
+		      from, offset))
+		return 0;
+	if (WARN_ONCE(offset > buf->page_len,
+		      "SUNRPC: buffer overflow. offset=%u, page_len=%u\n",
+		      offset, buf->page_len))
+		return 0;
 
 	/* Move page data to the left */
-	if (from > offset) {
-		shift = min_t(unsigned int, bytes, buf->page_len - from);
-		_shift_data_left_pages(buf->pages,
-				       buf->page_base + offset,
-				       buf->page_base + from,
-				       shift);
-		bytes -= shift;
+	shift = from - offset;
+	xdr_buf_pages_shift_left(buf, from, len, shift);
+	xdr->buf->len -= shift;
+	xdr->nwords -= XDR_QUADLEN(shift);
 
-		/* Move tail data into the pages, if necessary */
-		if (bytes > 0)
-			_shift_data_left_tail(buf, offset + shift, bytes);
-	}
+	bytes = xdr_stream_remaining(xdr);
+	if (length > bytes)
+		length = bytes;
+	bytes -= length;
 
 	xdr->nwords -= XDR_QUADLEN(length);
-	xdr_set_page(xdr, from + length, xdr_stream_remaining(xdr));
+	xdr_set_page(xdr, offset + length, bytes);
 	return length;
 }
 EXPORT_SYMBOL_GPL(xdr_align_data);
-- 
cgit v1.2.3


From c4f2f591f02c392ea7de018d2733748bf4c7b5f5 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Fri, 4 Dec 2020 17:15:09 -0500
Subject: SUNRPC: Fix xdr_expand_hole()

We do want to try to grow the buffer if possible, but if that attempt
fails, we still want to move the data and truncate the XDR message.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 include/linux/sunrpc/xdr.h |   2 +-
 net/sunrpc/xdr.c           | 274 +++++++++++++++++++++++++++++----------------
 2 files changed, 180 insertions(+), 96 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 2b4e44bb0654..178f499e2283 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -253,7 +253,7 @@ extern unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len);
 extern void xdr_enter_page(struct xdr_stream *xdr, unsigned int len);
 extern int xdr_process_buf(struct xdr_buf *buf, unsigned int offset, unsigned int len, int (*actor)(struct scatterlist *, void *), void *data);
 extern unsigned int xdr_align_data(struct xdr_stream *, unsigned int offset, unsigned int length);
-extern uint64_t xdr_expand_hole(struct xdr_stream *, uint64_t, uint64_t);
+extern unsigned int xdr_expand_hole(struct xdr_stream *, unsigned int offset, unsigned int length);
 
 /**
  * xdr_stream_remaining - Return the number of bytes remaining in the stream
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index c474339ba9ac..e0906ed24374 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -334,46 +334,6 @@ _shift_data_right_pages(struct page **pages, size_t pgto_base,
 	} while ((len -= copy) != 0);
 }
 
-static unsigned int
-_shift_data_right_tail(struct xdr_buf *buf, unsigned int pgfrom, size_t len)
-{
-	struct kvec *tail = buf->tail;
-	unsigned int tailbuf_len;
-	unsigned int result = 0;
-	size_t copy;
-
-	tailbuf_len = buf->buflen - buf->head->iov_len - buf->page_len;
-
-	/* Shift the tail first */
-	if (tailbuf_len != 0) {
-		unsigned int free_space = tailbuf_len - tail->iov_len;
-
-		if (len < free_space)
-			free_space = len;
-		if (len > free_space)
-			len = free_space;
-
-		tail->iov_len += free_space;
-		copy = len;
-
-		if (tail->iov_len > len) {
-			char *p = (char *)tail->iov_base + len;
-			memmove(p, tail->iov_base, tail->iov_len - free_space);
-			result += tail->iov_len - free_space;
-		} else
-			copy = tail->iov_len;
-
-		/* Copy from the inlined pages into the tail */
-		_copy_from_pages((char *)tail->iov_base,
-					 buf->pages,
-					 buf->page_base + pgfrom,
-					 copy);
-		result += copy;
-	}
-
-	return result;
-}
-
 /**
  * _copy_to_pages
  * @pages: array of pages
@@ -464,18 +424,42 @@ _copy_from_pages(char *p, struct page **pages, size_t pgbase, size_t len)
 }
 EXPORT_SYMBOL_GPL(_copy_from_pages);
 
+static void xdr_buf_iov_zero(const struct kvec *iov, unsigned int base,
+			     unsigned int len)
+{
+	if (base >= iov->iov_len)
+		return;
+	if (len > iov->iov_len - base)
+		len = iov->iov_len - base;
+	memset(iov->iov_base + base, 0, len);
+}
+
 /**
- * _zero_pages
- * @pages: array of pages
- * @pgbase: beginning page vector address
+ * xdr_buf_pages_zero
+ * @buf: xdr_buf
+ * @pgbase: beginning offset
  * @len: length
  */
-static void
-_zero_pages(struct page **pages, size_t pgbase, size_t len)
+static void xdr_buf_pages_zero(const struct xdr_buf *buf, unsigned int pgbase,
+			       unsigned int len)
 {
+	struct page **pages = buf->pages;
 	struct page **page;
 	char *vpage;
-	size_t zero;
+	unsigned int zero;
+
+	if (!len)
+		return;
+	if (pgbase >= buf->page_len) {
+		xdr_buf_iov_zero(buf->tail, pgbase - buf->page_len, len);
+		return;
+	}
+	if (pgbase + len > buf->page_len) {
+		xdr_buf_iov_zero(buf->tail, 0, pgbase + len - buf->page_len);
+		len = buf->page_len - pgbase;
+	}
+
+	pgbase += buf->page_base;
 
 	page = pages + (pgbase >> PAGE_SHIFT);
 	pgbase &= ~PAGE_MASK;
@@ -496,6 +480,103 @@ _zero_pages(struct page **pages, size_t pgbase, size_t len)
 	} while ((len -= zero) != 0);
 }
 
+static void xdr_buf_try_expand(struct xdr_buf *buf, unsigned int len)
+{
+	struct kvec *head = buf->head;
+	struct kvec *tail = buf->tail;
+	unsigned int sum = head->iov_len + buf->page_len + tail->iov_len;
+	unsigned int free_space;
+
+	if (sum > buf->len) {
+		free_space = min_t(unsigned int, sum - buf->len, len);
+		buf->len += free_space;
+		len -= free_space;
+		if (!len)
+			return;
+	}
+
+	if (buf->buflen > sum) {
+		/* Expand the tail buffer */
+		free_space = min_t(unsigned int, buf->buflen - sum, len);
+		tail->iov_len += free_space;
+		buf->len += free_space;
+	}
+}
+
+static void xdr_buf_tail_copy_right(const struct xdr_buf *buf,
+				    unsigned int base, unsigned int len,
+				    unsigned int shift)
+{
+	const struct kvec *tail = buf->tail;
+	unsigned int to = base + shift;
+
+	if (to >= tail->iov_len)
+		return;
+	if (len + to > tail->iov_len)
+		len = tail->iov_len - to;
+	memmove(tail->iov_base + to, tail->iov_base + base, len);
+}
+
+static void xdr_buf_pages_copy_right(const struct xdr_buf *buf,
+				     unsigned int base, unsigned int len,
+				     unsigned int shift)
+{
+	const struct kvec *tail = buf->tail;
+	unsigned int to = base + shift;
+	unsigned int pglen = 0;
+	unsigned int talen = 0, tato = 0;
+
+	if (base >= buf->page_len)
+		return;
+	if (len > buf->page_len - base)
+		len = buf->page_len - base;
+	if (to >= buf->page_len) {
+		tato = to - buf->page_len;
+		if (tail->iov_len >= len + tato)
+			talen = len;
+		else if (tail->iov_len > tato)
+			talen = tail->iov_len - tato;
+	} else if (len + to >= buf->page_len) {
+		pglen = buf->page_len - to;
+		talen = len - pglen;
+		if (talen > tail->iov_len)
+			talen = tail->iov_len;
+	} else
+		pglen = len;
+
+	_copy_from_pages(tail->iov_base + tato, buf->pages,
+			 buf->page_base + base + pglen, talen);
+	_shift_data_right_pages(buf->pages, buf->page_base + to,
+				buf->page_base + base, pglen);
+}
+
+static void xdr_buf_tail_shift_right(const struct xdr_buf *buf,
+				     unsigned int base, unsigned int len,
+				     unsigned int shift)
+{
+	const struct kvec *tail = buf->tail;
+
+	if (base >= tail->iov_len || !shift || !len)
+		return;
+	xdr_buf_tail_copy_right(buf, base, len, shift);
+}
+
+static void xdr_buf_pages_shift_right(const struct xdr_buf *buf,
+				      unsigned int base, unsigned int len,
+				      unsigned int shift)
+{
+	if (!shift || !len)
+		return;
+	if (base >= buf->page_len) {
+		xdr_buf_tail_shift_right(buf, base - buf->page_len, len, shift);
+		return;
+	}
+	if (base + len > buf->page_len)
+		xdr_buf_tail_shift_right(buf, 0, base + len - buf->page_len,
+					 shift);
+	xdr_buf_pages_copy_right(buf, base, len, shift);
+}
+
 static void xdr_buf_tail_copy_left(const struct xdr_buf *buf, unsigned int base,
 				   unsigned int len, unsigned int shift)
 {
@@ -685,30 +766,33 @@ xdr_shrink_bufhead(struct xdr_buf *buf, size_t len)
 }
 
 /**
- * xdr_shrink_pagelen - shrinks buf->pages by up to @len bytes
+ * xdr_shrink_pagelen - shrinks buf->pages to @len bytes
  * @buf: xdr_buf
- * @len: bytes to remove from buf->pages
+ * @len: new page buffer length
  *
  * The extra data is not lost, but is instead moved into buf->tail.
  * Returns the actual number of bytes moved.
  */
-static unsigned int
-xdr_shrink_pagelen(struct xdr_buf *buf, size_t len)
+static unsigned int xdr_shrink_pagelen(struct xdr_buf *buf, unsigned int len)
 {
-	unsigned int pglen = buf->page_len;
-	unsigned int result;
-
-	if (len > buf->page_len)
-		len = buf-> page_len;
-
-	result = _shift_data_right_tail(buf, pglen - len, len);
-	buf->page_len -= len;
-	buf->buflen -= len;
-	/* Have we truncated the message? */
-	if (buf->len > buf->buflen)
-		buf->len = buf->buflen;
+	unsigned int shift, buflen = buf->len - buf->head->iov_len;
 
-	return result;
+	WARN_ON_ONCE(len > buf->page_len);
+	if (buf->head->iov_len >= buf->len || len > buflen)
+		buflen = len;
+	if (buf->page_len > buflen) {
+		buf->buflen -= buf->page_len - buflen;
+		buf->page_len = buflen;
+	}
+	if (len >= buf->page_len)
+		return 0;
+	shift = buf->page_len - len;
+	xdr_buf_try_expand(buf, shift);
+	xdr_buf_pages_shift_right(buf, len, buflen - len, shift);
+	buf->page_len = len;
+	buf->len -= shift;
+	buf->buflen -= shift;
+	return shift;
 }
 
 void
@@ -728,6 +812,18 @@ unsigned int xdr_stream_pos(const struct xdr_stream *xdr)
 }
 EXPORT_SYMBOL_GPL(xdr_stream_pos);
 
+static void xdr_stream_set_pos(struct xdr_stream *xdr, unsigned int pos)
+{
+	unsigned int blen = xdr->buf->len;
+
+	xdr->nwords = blen > pos ? XDR_QUADLEN(blen) - XDR_QUADLEN(pos) : 0;
+}
+
+static void xdr_stream_page_set_pos(struct xdr_stream *xdr, unsigned int pos)
+{
+	xdr_stream_set_pos(xdr, pos + xdr->buf->head[0].iov_len);
+}
+
 /**
  * xdr_page_pos - Return the current offset from the start of the xdr pages
  * @xdr: pointer to struct xdr_stream
@@ -1291,7 +1387,7 @@ static unsigned int xdr_align_pages(struct xdr_stream *xdr, unsigned int len)
 	struct xdr_buf *buf = xdr->buf;
 	unsigned int nwords = XDR_QUADLEN(len);
 	unsigned int cur = xdr_stream_pos(xdr);
-	unsigned int copied, offset;
+	unsigned int copied;
 
 	if (xdr->nwords == 0)
 		return 0;
@@ -1305,9 +1401,8 @@ static unsigned int xdr_align_pages(struct xdr_stream *xdr, unsigned int len)
 		len = buf->page_len;
 	else if (nwords < xdr->nwords) {
 		/* Truncate page data and move it into the tail */
-		offset = buf->page_len - len;
-		copied = xdr_shrink_pagelen(buf, offset);
-		trace_rpc_xdr_alignment(xdr, offset, copied);
+		copied = xdr_shrink_pagelen(buf, len);
+		trace_rpc_xdr_alignment(xdr, len, copied);
 		xdr->nwords = XDR_QUADLEN(buf->len - cur);
 	}
 	return len;
@@ -1387,39 +1482,28 @@ unsigned int xdr_align_data(struct xdr_stream *xdr, unsigned int offset,
 }
 EXPORT_SYMBOL_GPL(xdr_align_data);
 
-uint64_t xdr_expand_hole(struct xdr_stream *xdr, uint64_t offset, uint64_t length)
+unsigned int xdr_expand_hole(struct xdr_stream *xdr, unsigned int offset,
+			     unsigned int length)
 {
 	struct xdr_buf *buf = xdr->buf;
-	unsigned int bytes;
-	unsigned int from;
-	unsigned int truncated = 0;
-
-	if ((offset + length) < offset ||
-	    (offset + length) > buf->page_len)
-		length = buf->page_len - offset;
+	unsigned int from, to, shift;
 
 	xdr_realign_pages(xdr);
 	from = xdr_page_pos(xdr);
-	bytes = xdr_stream_remaining(xdr);
-
-	if (offset + length + bytes > buf->page_len) {
-		unsigned int shift = (offset + length + bytes) - buf->page_len;
-		unsigned int res = _shift_data_right_tail(buf, from + bytes - shift, shift);
-		truncated = shift - res;
-		xdr->nwords -= XDR_QUADLEN(truncated);
-		bytes -= shift;
-	}
-
-	/* Now move the page data over and zero pages */
-	if (bytes > 0)
-		_shift_data_right_pages(buf->pages,
-					buf->page_base + offset + length,
-					buf->page_base + from,
-					bytes);
-	_zero_pages(buf->pages, buf->page_base + offset, length);
-
-	buf->len += length - (from - offset) - truncated;
-	xdr_set_page(xdr, offset + length, xdr_stream_remaining(xdr));
+	to = xdr_align_size(offset + length);
+
+	/* Could the hole be behind us? */
+	if (to > from) {
+		unsigned int buflen = buf->len - buf->head->iov_len;
+		shift = to - from;
+		xdr_buf_try_expand(buf, shift);
+		xdr_buf_pages_shift_right(buf, from, buflen, shift);
+		xdr_stream_page_set_pos(xdr, to);
+	} else if (to != from)
+		xdr_align_data(xdr, to, 0);
+	xdr_buf_pages_zero(buf, offset, length);
+
+	xdr_set_page(xdr, to, xdr_stream_remaining(xdr));
 	return length;
 }
 EXPORT_SYMBOL_GPL(xdr_expand_hole);
-- 
cgit v1.2.3


From f8d0e60f1056687826abc1eded98f0ea067dfc4c Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Tue, 8 Dec 2020 22:56:18 -0500
Subject: SUNRPC: Cleanup - constify a number of xdr_buf helpers

There are a number of xdr helpers for struct xdr_buf that do not change
the structure itself. Mark those as taking const pointers for
documentation purposes.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 include/linux/sunrpc/xdr.h | 22 +++++++++----------
 net/sunrpc/xdr.c           | 53 +++++++++++++++++++++-------------------------
 2 files changed, 35 insertions(+), 40 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 178f499e2283..68d49fdc4ee9 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -128,8 +128,8 @@ __be32 *xdr_decode_netobj(__be32 *p, struct xdr_netobj *);
 
 void	xdr_inline_pages(struct xdr_buf *, unsigned int,
 			 struct page **, unsigned int, unsigned int);
-void	xdr_terminate_string(struct xdr_buf *, const u32);
-size_t	xdr_buf_pagecount(struct xdr_buf *buf);
+void	xdr_terminate_string(const struct xdr_buf *, const u32);
+size_t	xdr_buf_pagecount(const struct xdr_buf *buf);
 int	xdr_alloc_bvec(struct xdr_buf *buf, gfp_t gfp);
 void	xdr_free_bvec(struct xdr_buf *buf);
 
@@ -182,14 +182,14 @@ xdr_adjust_iovec(struct kvec *iov, __be32 *p)
  * XDR buffer helper functions
  */
 extern void xdr_shift_buf(struct xdr_buf *, size_t);
-extern void xdr_buf_from_iov(struct kvec *, struct xdr_buf *);
-extern int xdr_buf_subsegment(struct xdr_buf *, struct xdr_buf *, unsigned int, unsigned int);
+extern void xdr_buf_from_iov(const struct kvec *, struct xdr_buf *);
+extern int xdr_buf_subsegment(const struct xdr_buf *, struct xdr_buf *, unsigned int, unsigned int);
 extern void xdr_buf_trim(struct xdr_buf *, unsigned int);
-extern int read_bytes_from_xdr_buf(struct xdr_buf *, unsigned int, void *, unsigned int);
-extern int write_bytes_to_xdr_buf(struct xdr_buf *, unsigned int, void *, unsigned int);
+extern int read_bytes_from_xdr_buf(const struct xdr_buf *, unsigned int, void *, unsigned int);
+extern int write_bytes_to_xdr_buf(const struct xdr_buf *, unsigned int, void *, unsigned int);
 
-extern int xdr_encode_word(struct xdr_buf *, unsigned int, u32);
-extern int xdr_decode_word(struct xdr_buf *, unsigned int, u32 *);
+extern int xdr_encode_word(const struct xdr_buf *, unsigned int, u32);
+extern int xdr_decode_word(const struct xdr_buf *, unsigned int, u32 *);
 
 struct xdr_array2_desc;
 typedef int (*xdr_xcode_elem_t)(struct xdr_array2_desc *desc, void *elem);
@@ -200,9 +200,9 @@ struct xdr_array2_desc {
 	xdr_xcode_elem_t xcode;
 };
 
-extern int xdr_decode_array2(struct xdr_buf *buf, unsigned int base,
+extern int xdr_decode_array2(const struct xdr_buf *buf, unsigned int base,
 			     struct xdr_array2_desc *desc);
-extern int xdr_encode_array2(struct xdr_buf *buf, unsigned int base,
+extern int xdr_encode_array2(const struct xdr_buf *buf, unsigned int base,
 			     struct xdr_array2_desc *desc);
 extern void _copy_from_pages(char *p, struct page **pages, size_t pgbase,
 			     size_t len);
@@ -251,7 +251,7 @@ extern void xdr_set_scratch_buffer(struct xdr_stream *xdr, void *buf, size_t buf
 extern __be32 *xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes);
 extern unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len);
 extern void xdr_enter_page(struct xdr_stream *xdr, unsigned int len);
-extern int xdr_process_buf(struct xdr_buf *buf, unsigned int offset, unsigned int len, int (*actor)(struct scatterlist *, void *), void *data);
+extern int xdr_process_buf(const struct xdr_buf *buf, unsigned int offset, unsigned int len, int (*actor)(struct scatterlist *, void *), void *data);
 extern unsigned int xdr_align_data(struct xdr_stream *, unsigned int offset, unsigned int length);
 extern unsigned int xdr_expand_hole(struct xdr_stream *, unsigned int offset, unsigned int length);
 
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index f0444bf5617c..2e91fbd70f11 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -123,8 +123,7 @@ EXPORT_SYMBOL_GPL(xdr_decode_string_inplace);
  * @len: length of string, in bytes
  *
  */
-void
-xdr_terminate_string(struct xdr_buf *buf, const u32 len)
+void xdr_terminate_string(const struct xdr_buf *buf, const u32 len)
 {
 	char *kaddr;
 
@@ -134,8 +133,7 @@ xdr_terminate_string(struct xdr_buf *buf, const u32 len)
 }
 EXPORT_SYMBOL_GPL(xdr_terminate_string);
 
-size_t
-xdr_buf_pagecount(struct xdr_buf *buf)
+size_t xdr_buf_pagecount(const struct xdr_buf *buf)
 {
 	if (!buf->page_len)
 		return 0;
@@ -1545,8 +1543,7 @@ EXPORT_SYMBOL_GPL(xdr_enter_page);
 
 static const struct kvec empty_iov = {.iov_base = NULL, .iov_len = 0};
 
-void
-xdr_buf_from_iov(struct kvec *iov, struct xdr_buf *buf)
+void xdr_buf_from_iov(const struct kvec *iov, struct xdr_buf *buf)
 {
 	buf->head[0] = *iov;
 	buf->tail[0] = empty_iov;
@@ -1569,9 +1566,8 @@ EXPORT_SYMBOL_GPL(xdr_buf_from_iov);
  *
  * Returns -1 if base of length are out of bounds.
  */
-int
-xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf,
-			unsigned int base, unsigned int len)
+int xdr_buf_subsegment(const struct xdr_buf *buf, struct xdr_buf *subbuf,
+		       unsigned int base, unsigned int len)
 {
 	subbuf->buflen = subbuf->len = len;
 	if (base < buf->head[0].iov_len) {
@@ -1659,7 +1655,8 @@ fix_len:
 }
 EXPORT_SYMBOL_GPL(xdr_buf_trim);
 
-static void __read_bytes_from_xdr_buf(struct xdr_buf *subbuf, void *obj, unsigned int len)
+static void __read_bytes_from_xdr_buf(const struct xdr_buf *subbuf,
+				      void *obj, unsigned int len)
 {
 	unsigned int this_len;
 
@@ -1676,7 +1673,8 @@ static void __read_bytes_from_xdr_buf(struct xdr_buf *subbuf, void *obj, unsigne
 }
 
 /* obj is assumed to point to allocated memory of size at least len: */
-int read_bytes_from_xdr_buf(struct xdr_buf *buf, unsigned int base, void *obj, unsigned int len)
+int read_bytes_from_xdr_buf(const struct xdr_buf *buf, unsigned int base,
+			    void *obj, unsigned int len)
 {
 	struct xdr_buf subbuf;
 	int status;
@@ -1689,7 +1687,8 @@ int read_bytes_from_xdr_buf(struct xdr_buf *buf, unsigned int base, void *obj, u
 }
 EXPORT_SYMBOL_GPL(read_bytes_from_xdr_buf);
 
-static void __write_bytes_to_xdr_buf(struct xdr_buf *subbuf, void *obj, unsigned int len)
+static void __write_bytes_to_xdr_buf(const struct xdr_buf *subbuf,
+				     void *obj, unsigned int len)
 {
 	unsigned int this_len;
 
@@ -1706,7 +1705,8 @@ static void __write_bytes_to_xdr_buf(struct xdr_buf *subbuf, void *obj, unsigned
 }
 
 /* obj is assumed to point to allocated memory of size at least len: */
-int write_bytes_to_xdr_buf(struct xdr_buf *buf, unsigned int base, void *obj, unsigned int len)
+int write_bytes_to_xdr_buf(const struct xdr_buf *buf, unsigned int base,
+			   void *obj, unsigned int len)
 {
 	struct xdr_buf subbuf;
 	int status;
@@ -1719,8 +1719,7 @@ int write_bytes_to_xdr_buf(struct xdr_buf *buf, unsigned int base, void *obj, un
 }
 EXPORT_SYMBOL_GPL(write_bytes_to_xdr_buf);
 
-int
-xdr_decode_word(struct xdr_buf *buf, unsigned int base, u32 *obj)
+int xdr_decode_word(const struct xdr_buf *buf, unsigned int base, u32 *obj)
 {
 	__be32	raw;
 	int	status;
@@ -1733,8 +1732,7 @@ xdr_decode_word(struct xdr_buf *buf, unsigned int base, u32 *obj)
 }
 EXPORT_SYMBOL_GPL(xdr_decode_word);
 
-int
-xdr_encode_word(struct xdr_buf *buf, unsigned int base, u32 obj)
+int xdr_encode_word(const struct xdr_buf *buf, unsigned int base, u32 obj)
 {
 	__be32	raw = cpu_to_be32(obj);
 
@@ -1743,9 +1741,8 @@ xdr_encode_word(struct xdr_buf *buf, unsigned int base, u32 obj)
 EXPORT_SYMBOL_GPL(xdr_encode_word);
 
 /* Returns 0 on success, or else a negative error code. */
-static int
-xdr_xcode_array2(struct xdr_buf *buf, unsigned int base,
-		 struct xdr_array2_desc *desc, int encode)
+static int xdr_xcode_array2(const struct xdr_buf *buf, unsigned int base,
+			    struct xdr_array2_desc *desc, int encode)
 {
 	char *elem = NULL, *c;
 	unsigned int copied = 0, todo, avail_here;
@@ -1937,9 +1934,8 @@ out:
 	return err;
 }
 
-int
-xdr_decode_array2(struct xdr_buf *buf, unsigned int base,
-		  struct xdr_array2_desc *desc)
+int xdr_decode_array2(const struct xdr_buf *buf, unsigned int base,
+		      struct xdr_array2_desc *desc)
 {
 	if (base >= buf->len)
 		return -EINVAL;
@@ -1948,9 +1944,8 @@ xdr_decode_array2(struct xdr_buf *buf, unsigned int base,
 }
 EXPORT_SYMBOL_GPL(xdr_decode_array2);
 
-int
-xdr_encode_array2(struct xdr_buf *buf, unsigned int base,
-		  struct xdr_array2_desc *desc)
+int xdr_encode_array2(const struct xdr_buf *buf, unsigned int base,
+		      struct xdr_array2_desc *desc)
 {
 	if ((unsigned long) base + 4 + desc->array_len * desc->elem_size >
 	    buf->head->iov_len + buf->page_len + buf->tail->iov_len)
@@ -1960,9 +1955,9 @@ xdr_encode_array2(struct xdr_buf *buf, unsigned int base,
 }
 EXPORT_SYMBOL_GPL(xdr_encode_array2);
 
-int
-xdr_process_buf(struct xdr_buf *buf, unsigned int offset, unsigned int len,
-		int (*actor)(struct scatterlist *, void *), void *data)
+int xdr_process_buf(const struct xdr_buf *buf, unsigned int offset,
+		    unsigned int len,
+		    int (*actor)(struct scatterlist *, void *), void *data)
 {
 	int i, ret = 0;
 	unsigned int page_len, thislen, page_offset;
-- 
cgit v1.2.3


From 7c03e2cda4a584cadc398e8f6641ca9988a39d52 Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@redhat.com>
Date: Mon, 14 Dec 2020 15:26:13 +0100
Subject: vfs: move cap_convert_nscap() call into vfs_setxattr()

cap_convert_nscap() does permission checking as well as conversion of the
xattr value conditionally based on fs's user-ns.

This is needed by overlayfs and probably other layered fs (ecryptfs) and is
what vfs_foo() is supposed to do anyway.

Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Acked-by: James Morris <jamorris@linux.microsoft.com>
---
 fs/xattr.c                 | 17 +++++++++++------
 include/linux/capability.h |  2 +-
 security/commoncap.c       |  3 +--
 3 files changed, 13 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/fs/xattr.c b/fs/xattr.c
index cd7a563e8bcd..fd57153b1f61 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -276,8 +276,16 @@ vfs_setxattr(struct dentry *dentry, const char *name, const void *value,
 {
 	struct inode *inode = dentry->d_inode;
 	struct inode *delegated_inode = NULL;
+	const void  *orig_value = value;
 	int error;
 
+	if (size && strcmp(name, XATTR_NAME_CAPS) == 0) {
+		error = cap_convert_nscap(dentry, &value, size);
+		if (error < 0)
+			return error;
+		size = error;
+	}
+
 retry_deleg:
 	inode_lock(inode);
 	error = __vfs_setxattr_locked(dentry, name, value, size, flags,
@@ -289,6 +297,9 @@ retry_deleg:
 		if (!error)
 			goto retry_deleg;
 	}
+	if (value != orig_value)
+		kfree(value);
+
 	return error;
 }
 EXPORT_SYMBOL_GPL(vfs_setxattr);
@@ -537,12 +548,6 @@ setxattr(struct dentry *d, const char __user *name, const void __user *value,
 		if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) ||
 		    (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0))
 			posix_acl_fix_xattr_from_user(kvalue, size);
-		else if (strcmp(kname, XATTR_NAME_CAPS) == 0) {
-			error = cap_convert_nscap(d, &kvalue, size);
-			if (error < 0)
-				goto out;
-			size = error;
-		}
 	}
 
 	error = vfs_setxattr(d, kname, kvalue, size, flags);
diff --git a/include/linux/capability.h b/include/linux/capability.h
index 1e7fe311cabe..b2f698915c0f 100644
--- a/include/linux/capability.h
+++ b/include/linux/capability.h
@@ -270,6 +270,6 @@ static inline bool checkpoint_restore_ns_capable(struct user_namespace *ns)
 /* audit system wants to get cap info from files as well */
 extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps);
 
-extern int cap_convert_nscap(struct dentry *dentry, void **ivalue, size_t size);
+extern int cap_convert_nscap(struct dentry *dentry, const void **ivalue, size_t size);
 
 #endif /* !_LINUX_CAPABILITY_H */
diff --git a/security/commoncap.c b/security/commoncap.c
index 59bf3c1674c8..bacc1111d871 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -473,7 +473,7 @@ static bool validheader(size_t size, const struct vfs_cap_data *cap)
  *
  * If all is ok, we return the new size, on error return < 0.
  */
-int cap_convert_nscap(struct dentry *dentry, void **ivalue, size_t size)
+int cap_convert_nscap(struct dentry *dentry, const void **ivalue, size_t size)
 {
 	struct vfs_ns_cap_data *nscap;
 	uid_t nsrootid;
@@ -516,7 +516,6 @@ int cap_convert_nscap(struct dentry *dentry, void **ivalue, size_t size)
 	nscap->magic_etc = cpu_to_le32(nsmagic);
 	memcpy(&nscap->data, &cap->data, sizeof(__le32) * 2 * VFS_CAP_U32);
 
-	kvfree(*ivalue);
 	*ivalue = nscap;
 	return newsize;
 }
-- 
cgit v1.2.3


From e0a6aa30504cb8179d07609fb6386705e8f00663 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Sun, 13 Dec 2020 09:39:40 +0100
Subject: efi: ia64: disable the capsule loader

EFI capsule loading is a feature that was introduced into EFI long after
its initial introduction on Itanium, and it is highly unlikely that IA64
systems are receiving firmware updates in the first place, let alone
using EFI capsules.

So let's disable capsule support altogether on IA64. This fixes a build
error on IA64 due to a recent change that added an unconditional
include of asm/efi.h, which IA64 does not provide.

While at it, tweak the make rules a bit so that the EFI capsule
component that is always builtin (even if the EFI capsule loader itself
is built as a module) is omitted for all architectures if the module is
not enabled in the build.

Cc: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/linux-efi/20201214152200.38353-1-ardb@kernel.org
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/Kconfig  |  2 +-
 drivers/firmware/efi/Makefile |  5 ++++-
 include/linux/efi.h           | 10 ++++------
 3 files changed, 9 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig
index b452cfa2100b..5ac2a37ed025 100644
--- a/drivers/firmware/efi/Kconfig
+++ b/drivers/firmware/efi/Kconfig
@@ -147,7 +147,7 @@ config EFI_BOOTLOADER_CONTROL
 
 config EFI_CAPSULE_LOADER
 	tristate "EFI capsule loader"
-	depends on EFI
+	depends on EFI && !IA64
 	help
 	  This option exposes a loader interface "/dev/efi_capsule_loader" for
 	  users to load EFI capsules. This driver requires working runtime
diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile
index d6ca2da19339..467e94259679 100644
--- a/drivers/firmware/efi/Makefile
+++ b/drivers/firmware/efi/Makefile
@@ -12,7 +12,10 @@ KASAN_SANITIZE_runtime-wrappers.o	:= n
 
 obj-$(CONFIG_ACPI_BGRT) 		+= efi-bgrt.o
 obj-$(CONFIG_EFI)			+= efi.o vars.o reboot.o memattr.o tpm.o
-obj-$(CONFIG_EFI)			+= capsule.o memmap.o
+obj-$(CONFIG_EFI)			+= memmap.o
+ifneq ($(CONFIG_EFI_CAPSULE_LOADER),)
+obj-$(CONFIG_EFI)			+= capsule.o
+endif
 obj-$(CONFIG_EFI_PARAMS_FROM_FDT)	+= fdtparams.o
 obj-$(CONFIG_EFI_VARS)			+= efivars.o
 obj-$(CONFIG_EFI_ESRT)			+= esrt.o
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 1cd5d91d8ca1..763b816ba19c 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -817,12 +817,6 @@ static inline bool efi_enabled(int feature)
 static inline void
 efi_reboot(enum reboot_mode reboot_mode, const char *__unused) {}
 
-static inline bool
-efi_capsule_pending(int *reset_type)
-{
-	return false;
-}
-
 static inline bool efi_soft_reserve_enabled(void)
 {
 	return false;
@@ -1038,6 +1032,7 @@ bool efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data,
 bool efivar_variable_is_removable(efi_guid_t vendor, const char *name,
 				  size_t len);
 
+#if IS_ENABLED(CONFIG_EFI_CAPSULE_LOADER)
 extern bool efi_capsule_pending(int *reset_type);
 
 extern int efi_capsule_supported(efi_guid_t guid, u32 flags,
@@ -1045,6 +1040,9 @@ extern int efi_capsule_supported(efi_guid_t guid, u32 flags,
 
 extern int efi_capsule_update(efi_capsule_header_t *capsule,
 			      phys_addr_t *pages);
+#else
+static inline bool efi_capsule_pending(int *reset_type) { return false; }
+#endif
 
 #ifdef CONFIG_EFI_RUNTIME_MAP
 int efi_runtime_map_init(struct kobject *);
-- 
cgit v1.2.3


From 50c9132ddfb2024e96900407beeec660cf9848bd Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Fri, 25 Sep 2020 07:55:39 -0400
Subject: ceph: add new RECOVER mount_state when recovering session

When recovering a session (a'la recover_session=clean), we want to do
all of the operations that we do on a forced umount, but changing the
mount state to SHUTDOWN is can cause queued MDS requests to fail when
the session comes back. Most of those can idle until the session is
recovered in this situation.

Reserve SHUTDOWN state for forced umount, and make a new RECOVER state
for the forced reconnect situation. Change several tests for equality with
SHUTDOWN to test for that or RECOVER.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: "Yan, Zheng" <zyan@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/addr.c               |  4 ++--
 fs/ceph/caps.c               |  2 +-
 fs/ceph/inode.c              |  2 +-
 fs/ceph/mds_client.c         |  4 ++--
 fs/ceph/super.c              | 14 ++++++++++----
 include/linux/ceph/libceph.h |  1 +
 6 files changed, 17 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 35c83f65475b..e10b07edc95c 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -840,7 +840,7 @@ static int ceph_writepages_start(struct address_space *mapping,
 	     wbc->sync_mode == WB_SYNC_NONE ? "NONE" :
 	     (wbc->sync_mode == WB_SYNC_ALL ? "ALL" : "HOLD"));
 
-	if (READ_ONCE(fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) {
+	if (READ_ONCE(fsc->mount_state) >= CEPH_MOUNT_SHUTDOWN) {
 		if (ci->i_wrbuffer_ref > 0) {
 			pr_warn_ratelimited(
 				"writepage_start %p %lld forced umount\n",
@@ -1264,7 +1264,7 @@ ceph_find_incompatible(struct page *page)
 	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 
-	if (READ_ONCE(fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) {
+	if (READ_ONCE(fsc->mount_state) >= CEPH_MOUNT_SHUTDOWN) {
 		dout(" page %p forced umount\n", page);
 		return ERR_PTR(-EIO);
 	}
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 8552d1082b0e..c74d8182fb48 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -2747,7 +2747,7 @@ again:
 			goto out_unlock;
 		}
 
-		if (READ_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) {
+		if (READ_ONCE(mdsc->fsc->mount_state) >= CEPH_MOUNT_SHUTDOWN) {
 			dout("get_cap_refs %p forced umount\n", inode);
 			ret = -EIO;
 			goto out_unlock;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 526faf4778ce..02b11a4a4d39 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1888,7 +1888,7 @@ static void ceph_do_invalidate_pages(struct inode *inode)
 
 	mutex_lock(&ci->i_truncate_mutex);
 
-	if (READ_ONCE(fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) {
+	if (READ_ONCE(fsc->mount_state) >= CEPH_MOUNT_SHUTDOWN) {
 		pr_warn_ratelimited("invalidate_pages %p %lld forced umount\n",
 				    inode, ceph_ino(inode));
 		mapping_set_error(inode->i_mapping, -EIO);
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 8f1d7500a7ec..a2d6ef808f70 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1595,7 +1595,7 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
 		struct ceph_cap_flush *cf;
 		struct ceph_mds_client *mdsc = fsc->mdsc;
 
-		if (READ_ONCE(fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) {
+		if (READ_ONCE(fsc->mount_state) >= CEPH_MOUNT_SHUTDOWN) {
 			if (inode->i_data.nrpages > 0)
 				invalidate = true;
 			if (ci->i_wrbuffer_ref > 0)
@@ -4678,7 +4678,7 @@ void ceph_mdsc_sync(struct ceph_mds_client *mdsc)
 {
 	u64 want_tid, want_flush;
 
-	if (READ_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_SHUTDOWN)
+	if (READ_ONCE(mdsc->fsc->mount_state) >= CEPH_MOUNT_SHUTDOWN)
 		return;
 
 	dout("sync\n");
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 33ba6f0aa55c..9b1b7f4cfdd4 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -831,6 +831,13 @@ static void destroy_caches(void)
 	ceph_fscache_unregister();
 }
 
+static void __ceph_umount_begin(struct ceph_fs_client *fsc)
+{
+	ceph_osdc_abort_requests(&fsc->client->osdc, -EIO);
+	ceph_mdsc_force_umount(fsc->mdsc);
+	fsc->filp_gen++; // invalidate open files
+}
+
 /*
  * ceph_umount_begin - initiate forced umount.  Tear down the
  * mount, skipping steps that may hang while waiting for server(s).
@@ -843,9 +850,7 @@ static void ceph_umount_begin(struct super_block *sb)
 	if (!fsc)
 		return;
 	fsc->mount_state = CEPH_MOUNT_SHUTDOWN;
-	ceph_osdc_abort_requests(&fsc->client->osdc, -EIO);
-	ceph_mdsc_force_umount(fsc->mdsc);
-	fsc->filp_gen++; // invalidate open files
+	__ceph_umount_begin(fsc);
 }
 
 static const struct super_operations ceph_super_ops = {
@@ -1234,7 +1239,8 @@ int ceph_force_reconnect(struct super_block *sb)
 	struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
 	int err = 0;
 
-	ceph_umount_begin(sb);
+	fsc->mount_state = CEPH_MOUNT_RECOVER;
+	__ceph_umount_begin(fsc);
 
 	/* Make sure all page caches get invalidated.
 	 * see remove_session_caps_cb() */
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index c8645f0b797d..eb5a7ca13f9c 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -104,6 +104,7 @@ enum {
 	CEPH_MOUNT_UNMOUNTING,
 	CEPH_MOUNT_UNMOUNTED,
 	CEPH_MOUNT_SHUTDOWN,
+	CEPH_MOUNT_RECOVER,
 };
 
 static inline unsigned long ceph_timeout_jiffies(unsigned long timeout)
-- 
cgit v1.2.3


From 36c9478d6069994848c8897755b4380aa0a29dd3 Mon Sep 17 00:00:00 2001
From: "Liu, Changcheng" <changcheng.liu@aliyun.com>
Date: Tue, 10 Nov 2020 21:20:08 +0800
Subject: libceph: remove unused port macros

1. monitor's default port is defined by CEPH_MON_PORT
2. CEPH_PORT_START and CEPH_PORT_LAST are not needed.

Signed-off-by: Changcheng Liu <changcheng.liu@aliyun.com>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/msgr.h | 9 ---------
 1 file changed, 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ceph/msgr.h b/include/linux/ceph/msgr.h
index 9e50aede46c8..46939485f2c3 100644
--- a/include/linux/ceph/msgr.h
+++ b/include/linux/ceph/msgr.h
@@ -8,15 +8,6 @@
 
 #define CEPH_MON_PORT    6789  /* default monitor port */
 
-/*
- * client-side processes will try to bind to ports in this
- * range, simply for the benefit of tools like nmap or wireshark
- * that would like to identify the protocol.
- */
-#define CEPH_PORT_FIRST  6789
-#define CEPH_PORT_START  6800  /* non-monitors start here */
-#define CEPH_PORT_LAST   6900
-
 /*
  * tcp connection banner.  include a protocol version. and adjust
  * whenever the wire protocol changes.  try to keep this string length
-- 
cgit v1.2.3


From 968cd14edc3acff251f98bdc1eb15f13f05dd5fb Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Wed, 9 Dec 2020 10:52:20 +0800
Subject: ceph: set osdmap epoch for setxattr

When setting the file/dir layout, it may need data pool info. So
in mds server, it needs to check the osdmap. At present, if mds
doesn't find the data pool specified, it will try to get the latest
osdmap. Now if pass the osd epoch for setxattr, the mds server can
only check this epoch of osdmap.

URL: https://tracker.ceph.com/issues/48504
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/mds_client.c         | 2 +-
 fs/ceph/xattr.c              | 3 +++
 include/linux/ceph/ceph_fs.h | 1 +
 3 files changed, 5 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 70d347989603..75034f7d8f46 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2533,7 +2533,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
 		goto out_free2;
 	}
 
-	msg->hdr.version = cpu_to_le16(2);
+	msg->hdr.version = cpu_to_le16(3);
 	msg->hdr.tid = cpu_to_le64(req->r_tid);
 
 	head = msg->front.iov_base;
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index cd8c7aaa23a0..24997982de01 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -1022,6 +1022,7 @@ static int ceph_sync_setxattr(struct inode *inode, const char *name,
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_mds_request *req;
 	struct ceph_mds_client *mdsc = fsc->mdsc;
+	struct ceph_osd_client *osdc = &fsc->client->osdc;
 	struct ceph_pagelist *pagelist = NULL;
 	int op = CEPH_MDS_OP_SETXATTR;
 	int err;
@@ -1060,6 +1061,8 @@ static int ceph_sync_setxattr(struct inode *inode, const char *name,
 
 	if (op == CEPH_MDS_OP_SETXATTR) {
 		req->r_args.setxattr.flags = cpu_to_le32(flags);
+		req->r_args.setxattr.osdmap_epoch =
+			cpu_to_le32(osdc->osdmap->epoch);
 		req->r_pagelist = pagelist;
 		pagelist = NULL;
 	}
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index 455e9b9e2adf..c0f1b921ec69 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -424,6 +424,7 @@ union ceph_mds_request_args {
 	} __attribute__ ((packed)) open;
 	struct {
 		__le32 flags;
+		__le32 osdmap_epoch; /* used for setting file/dir layouts */
 	} __attribute__ ((packed)) setxattr;
 	struct {
 		struct ceph_file_layout_legacy layout;
-- 
cgit v1.2.3


From 4f1ddb1ea874c7703528a8c21b77b7f2462ee247 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Wed, 9 Dec 2020 10:12:59 -0500
Subject: ceph: implement updated ceph_mds_request_head structure

When we added the btime feature in mainline ceph, we had to extend
struct ceph_mds_request_args so that it could be set. Implement the same
in the kernel client.

Rename ceph_mds_request_head with a _old extension, and a union
ceph_mds_request_args_ext to allow for the extended size of the new
header format.

Add the appropriate code to handle both formats in struct
create_request_message and key the behavior on whether the peer supports
CEPH_FEATURE_FS_BTIME.

The gid_list field in the payload is now populated from the saved
credential. For now, we don't add any support for setting the btime via
setattr, but this does enable us to add that in the future.

[ idryomov: break unnecessarily long lines ]

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/mds_client.c         | 75 ++++++++++++++++++++++++++++++++++++--------
 include/linux/ceph/ceph_fs.h | 32 ++++++++++++++++++-
 2 files changed, 93 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 14d0a11b7d88..a256d95ec99a 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2478,21 +2478,24 @@ static int set_request_path_attr(struct inode *rinode, struct dentry *rdentry,
 /*
  * called under mdsc->mutex
  */
-static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
+static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 					       struct ceph_mds_request *req,
-					       int mds, bool drop_cap_releases)
+					       bool drop_cap_releases)
 {
+	int mds = session->s_mds;
+	struct ceph_mds_client *mdsc = session->s_mdsc;
 	struct ceph_msg *msg;
-	struct ceph_mds_request_head *head;
+	struct ceph_mds_request_head_old *head;
 	const char *path1 = NULL;
 	const char *path2 = NULL;
 	u64 ino1 = 0, ino2 = 0;
 	int pathlen1 = 0, pathlen2 = 0;
 	bool freepath1 = false, freepath2 = false;
-	int len;
+	int len, i;
 	u16 releases;
 	void *p, *end;
 	int ret;
+	bool legacy = !(session->s_con.peer_features & CEPH_FEATURE_FS_BTIME);
 
 	ret = set_request_path_attr(req->r_inode, req->r_dentry,
 			      req->r_parent, req->r_path1, req->r_ino1.ino,
@@ -2514,14 +2517,23 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
 		goto out_free1;
 	}
 
-	len = sizeof(*head) +
-		pathlen1 + pathlen2 + 2*(1 + sizeof(u32) + sizeof(u64)) +
+	if (legacy) {
+		/* Old style */
+		len = sizeof(*head);
+	} else {
+		/* New style: add gid_list and any later fields */
+		len = sizeof(struct ceph_mds_request_head) + sizeof(u32) +
+		      (sizeof(u64) * req->r_cred->group_info->ngroups);
+	}
+
+	len += pathlen1 + pathlen2 + 2*(1 + sizeof(u32) + sizeof(u64)) +
 		sizeof(struct ceph_timespec);
 
 	/* calculate (max) length for cap releases */
 	len += sizeof(struct ceph_mds_request_release) *
 		(!!req->r_inode_drop + !!req->r_dentry_drop +
 		 !!req->r_old_inode_drop + !!req->r_old_dentry_drop);
+
 	if (req->r_dentry_drop)
 		len += pathlen1;
 	if (req->r_old_dentry_drop)
@@ -2533,11 +2545,25 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
 		goto out_free2;
 	}
 
-	msg->hdr.version = cpu_to_le16(3);
 	msg->hdr.tid = cpu_to_le64(req->r_tid);
 
-	head = msg->front.iov_base;
-	p = msg->front.iov_base + sizeof(*head);
+	/*
+	 * The old ceph_mds_request_header didn't contain a version field, and
+	 * one was added when we moved the message version from 3->4.
+	 */
+	if (legacy) {
+		msg->hdr.version = cpu_to_le16(3);
+		head = msg->front.iov_base;
+		p = msg->front.iov_base + sizeof(*head);
+	} else {
+		struct ceph_mds_request_head *new_head = msg->front.iov_base;
+
+		msg->hdr.version = cpu_to_le16(4);
+		new_head->version = cpu_to_le16(CEPH_MDS_REQUEST_HEAD_VERSION);
+		head = (struct ceph_mds_request_head_old *)&new_head->oldest_client_tid;
+		p = msg->front.iov_base + sizeof(*new_head);
+	}
+
 	end = msg->front.iov_base + msg->front.iov_len;
 
 	head->mdsmap_epoch = cpu_to_le32(mdsc->mdsmap->m_epoch);
@@ -2590,6 +2616,14 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
 		ceph_encode_copy(&p, &ts, sizeof(ts));
 	}
 
+	/* gid list */
+	if (!legacy) {
+		ceph_encode_32(&p, req->r_cred->group_info->ngroups);
+		for (i = 0; i < req->r_cred->group_info->ngroups; i++)
+			ceph_encode_64(&p, from_kgid(&init_user_ns,
+				       req->r_cred->group_info->gid[i]));
+	}
+
 	if (WARN_ON_ONCE(p > end)) {
 		ceph_msg_put(msg);
 		msg = ERR_PTR(-ERANGE);
@@ -2633,6 +2667,18 @@ static void complete_request(struct ceph_mds_client *mdsc,
 	complete_all(&req->r_completion);
 }
 
+static struct ceph_mds_request_head_old *
+find_old_request_head(void *p, u64 features)
+{
+	bool legacy = !(features & CEPH_FEATURE_FS_BTIME);
+	struct ceph_mds_request_head *new_head;
+
+	if (legacy)
+		return (struct ceph_mds_request_head_old *)p;
+	new_head = (struct ceph_mds_request_head *)p;
+	return (struct ceph_mds_request_head_old *)&new_head->oldest_client_tid;
+}
+
 /*
  * called under mdsc->mutex
  */
@@ -2642,7 +2688,7 @@ static int __prepare_send_request(struct ceph_mds_session *session,
 {
 	int mds = session->s_mds;
 	struct ceph_mds_client *mdsc = session->s_mdsc;
-	struct ceph_mds_request_head *rhead;
+	struct ceph_mds_request_head_old *rhead;
 	struct ceph_msg *msg;
 	int flags = 0;
 
@@ -2661,6 +2707,7 @@ static int __prepare_send_request(struct ceph_mds_session *session,
 
 	if (test_bit(CEPH_MDS_R_GOT_UNSAFE, &req->r_req_flags)) {
 		void *p;
+
 		/*
 		 * Replay.  Do not regenerate message (and rebuild
 		 * paths, etc.); just use the original message.
@@ -2668,7 +2715,8 @@ static int __prepare_send_request(struct ceph_mds_session *session,
 		 * d_move mangles the src name.
 		 */
 		msg = req->r_request;
-		rhead = msg->front.iov_base;
+		rhead = find_old_request_head(msg->front.iov_base,
+					      session->s_con.peer_features);
 
 		flags = le32_to_cpu(rhead->flags);
 		flags |= CEPH_MDS_FLAG_REPLAY;
@@ -2699,14 +2747,15 @@ static int __prepare_send_request(struct ceph_mds_session *session,
 		ceph_msg_put(req->r_request);
 		req->r_request = NULL;
 	}
-	msg = create_request_message(mdsc, req, mds, drop_cap_releases);
+	msg = create_request_message(session, req, drop_cap_releases);
 	if (IS_ERR(msg)) {
 		req->r_err = PTR_ERR(msg);
 		return PTR_ERR(msg);
 	}
 	req->r_request = msg;
 
-	rhead = msg->front.iov_base;
+	rhead = find_old_request_head(msg->front.iov_base,
+				      session->s_con.peer_features);
 	rhead->oldest_client_tid = cpu_to_le64(__get_oldest_tid(mdsc));
 	if (test_bit(CEPH_MDS_R_GOT_UNSAFE, &req->r_req_flags))
 		flags |= CEPH_MDS_FLAG_REPLAY;
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index c0f1b921ec69..d44d98033d58 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -446,11 +446,25 @@ union ceph_mds_request_args {
 	} __attribute__ ((packed)) lookupino;
 } __attribute__ ((packed));
 
+union ceph_mds_request_args_ext {
+	union ceph_mds_request_args old;
+	struct {
+		__le32 mode;
+		__le32 uid;
+		__le32 gid;
+		struct ceph_timespec mtime;
+		struct ceph_timespec atime;
+		__le64 size, old_size;       /* old_size needed by truncate */
+		__le32 mask;                 /* CEPH_SETATTR_* */
+		struct ceph_timespec btime;
+	} __attribute__ ((packed)) setattr_ext;
+};
+
 #define CEPH_MDS_FLAG_REPLAY		1 /* this is a replayed op */
 #define CEPH_MDS_FLAG_WANT_DENTRY	2 /* want dentry in reply */
 #define CEPH_MDS_FLAG_ASYNC		4 /* request is asynchronous */
 
-struct ceph_mds_request_head {
+struct ceph_mds_request_head_old {
 	__le64 oldest_client_tid;
 	__le32 mdsmap_epoch;           /* on client */
 	__le32 flags;                  /* CEPH_MDS_FLAG_* */
@@ -463,6 +477,22 @@ struct ceph_mds_request_head {
 	union ceph_mds_request_args args;
 } __attribute__ ((packed));
 
+#define CEPH_MDS_REQUEST_HEAD_VERSION  1
+
+struct ceph_mds_request_head {
+	__le16 version;                /* struct version */
+	__le64 oldest_client_tid;
+	__le32 mdsmap_epoch;           /* on client */
+	__le32 flags;                  /* CEPH_MDS_FLAG_* */
+	__u8 num_retry, num_fwd;       /* count retry, fwd attempts */
+	__le16 num_releases;           /* # include cap/lease release records */
+	__le32 op;                     /* mds op code */
+	__le32 caller_uid, caller_gid;
+	__le64 ino;                    /* use this ino for openc, mkdir, mknod,
+					  etc. (if replaying) */
+	union ceph_mds_request_args_ext args;
+} __attribute__ ((packed));
+
 /* cap/lease release record */
 struct ceph_mds_request_release {
 	__le64 ino, cap_id;            /* ino and unique cap id */
-- 
cgit v1.2.3


From 418af5b3bfc4f1ef4854e83c5be8a0bdce51e95c Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Thu, 29 Oct 2020 14:49:10 +0100
Subject: libceph: lower exponential backoff delay

The current setting allows the backoff to climb up to 5 minutes.  This
is too high -- it becomes hard to tell whether the client is stuck on
something or just in backoff.

In userspace, ms_max_backoff is defaulted to 15 seconds.  Let's do the
same.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/messenger.h |  4 ++--
 net/ceph/messenger.c           | 12 +++++++++---
 2 files changed, 11 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index 60b324efd1c4..b47c7cc4c90a 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -241,8 +241,8 @@ struct ceph_msg {
 };
 
 /* ceph connection fault delay defaults, for exponential backoff */
-#define BASE_DELAY_INTERVAL	(HZ/2)
-#define MAX_DELAY_INTERVAL	(5 * 60 * HZ)
+#define BASE_DELAY_INTERVAL	(HZ / 4)
+#define MAX_DELAY_INTERVAL	(15 * HZ)
 
 /*
  * A single connection with another host.
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 214ae2d17a90..f3eb66bab988 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -2812,6 +2812,9 @@ static int queue_con_delay(struct ceph_connection *con, unsigned long delay)
 		return -ENOENT;
 	}
 
+	if (delay >= HZ)
+		delay = round_jiffies_relative(delay);
+
 	dout("%s %p %lu\n", __func__, con, delay);
 	if (!queue_delayed_work(ceph_msgr_wq, &con->work, delay)) {
 		dout("%s %p - already queued\n", __func__, con);
@@ -2871,7 +2874,7 @@ static bool con_backoff(struct ceph_connection *con)
 	if (!con_flag_test_and_clear(con, CON_FLAG_BACKOFF))
 		return false;
 
-	ret = queue_con_delay(con, round_jiffies_relative(con->delay));
+	ret = queue_con_delay(con, con->delay);
 	if (ret) {
 		dout("%s: con %p FAILED to back off %lu\n", __func__,
 			con, con->delay);
@@ -3018,10 +3021,13 @@ static void con_fault(struct ceph_connection *con)
 	} else {
 		/* retry after a delay. */
 		con->state = CON_STATE_PREOPEN;
-		if (con->delay == 0)
+		if (!con->delay) {
 			con->delay = BASE_DELAY_INTERVAL;
-		else if (con->delay < MAX_DELAY_INTERVAL)
+		} else if (con->delay < MAX_DELAY_INTERVAL) {
 			con->delay *= 2;
+			if (con->delay > MAX_DELAY_INTERVAL)
+				con->delay = MAX_DELAY_INTERVAL;
+		}
 		con_flag_set(con, CON_FLAG_BACKOFF);
 		queue_con(con);
 	}
-- 
cgit v1.2.3


From 5cd8da3a1ca2160b8f9c2ff6a96762e66410ea38 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Tue, 13 Oct 2020 17:23:22 +0200
Subject: libceph: drop msg->ack_stamp field

It is set in process_ack() but never used.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/messenger.h | 1 -
 net/ceph/messenger.c           | 1 -
 2 files changed, 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index b47c7cc4c90a..6f77e70db855 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -235,7 +235,6 @@ struct ceph_msg {
 	bool more_to_follow;
 	bool needs_out_seq;
 	int front_alloc_len;
-	unsigned long ack_stamp;        /* tx: when we were acked */
 
 	struct ceph_msgpool *pool;
 };
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index a6d93280d3e9..29b00b2cecac 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -2279,7 +2279,6 @@ static void process_ack(struct ceph_connection *con)
 			break;
 		dout("got ack for seq %llu type %d at %p\n", seq,
 		     le16_to_cpu(m->hdr.type), m);
-		m->ack_stamp = jiffies;
 		ceph_msg_remove(m);
 	}
 
-- 
cgit v1.2.3


From 30be780a87211de75b93935c20a0913e46744a3f Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Mon, 9 Nov 2020 14:11:26 +0100
Subject: libceph: make con->state an int

unsigned long is a leftover from when con->state used to be a set of
bits managed with set_bit(), clear_bit(), etc.  Save a bit of memory.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/messenger.h |  2 +-
 net/ceph/messenger.c           | 16 ++++++----------
 2 files changed, 7 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index 6f77e70db855..f053de4f46dd 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -257,13 +257,13 @@ struct ceph_connection {
 
 	struct ceph_messenger *msgr;
 
+	int state;
 	atomic_t sock_state;
 	struct socket *sock;
 	struct ceph_entity_addr peer_addr; /* peer address */
 	struct ceph_entity_addr peer_addr_for_me;
 
 	unsigned long flags;
-	unsigned long state;
 	const char *error_msg;  /* error message, if any */
 
 	struct ceph_entity_name peer_name; /* peer name */
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index bb79a59daf42..9c92f101aa88 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -372,7 +372,7 @@ static void ceph_sock_data_ready(struct sock *sk)
 	}
 
 	if (sk->sk_state != TCP_CLOSE_WAIT) {
-		dout("%s on %p state = %lu, queueing work\n", __func__,
+		dout("%s %p state = %d, queueing work\n", __func__,
 		     con, con->state);
 		queue_con(con);
 	}
@@ -406,7 +406,7 @@ static void ceph_sock_state_change(struct sock *sk)
 {
 	struct ceph_connection *con = sk->sk_user_data;
 
-	dout("%s %p state = %lu sk_state = %u\n", __func__,
+	dout("%s %p state = %d sk_state = %u\n", __func__,
 	     con, con->state, sk->sk_state);
 
 	switch (sk->sk_state) {
@@ -2582,7 +2582,7 @@ static int try_write(struct ceph_connection *con)
 {
 	int ret = 1;
 
-	dout("try_write start %p state %lu\n", con, con->state);
+	dout("try_write start %p state %d\n", con, con->state);
 	if (con->state != CON_STATE_PREOPEN &&
 	    con->state != CON_STATE_CONNECTING &&
 	    con->state != CON_STATE_NEGOTIATING &&
@@ -2600,7 +2600,7 @@ static int try_write(struct ceph_connection *con)
 
 		BUG_ON(con->in_msg);
 		con->in_tag = CEPH_MSGR_TAG_READY;
-		dout("try_write initiating connect on %p new state %lu\n",
+		dout("try_write initiating connect on %p new state %d\n",
 		     con, con->state);
 		ret = ceph_tcp_connect(con);
 		if (ret < 0) {
@@ -2679,7 +2679,7 @@ static int try_read(struct ceph_connection *con)
 	int ret = -1;
 
 more:
-	dout("try_read start on %p state %lu\n", con, con->state);
+	dout("try_read start %p state %d\n", con, con->state);
 	if (con->state != CON_STATE_CONNECTING &&
 	    con->state != CON_STATE_NEGOTIATING &&
 	    con->state != CON_STATE_OPEN)
@@ -2876,11 +2876,7 @@ static bool con_sock_closed(struct ceph_connection *con)
 	CASE(OPEN);
 	CASE(STANDBY);
 	default:
-		pr_warn("%s con %p unrecognized state %lu\n",
-			__func__, con, con->state);
-		con->error_msg = "unrecognized con state";
 		BUG();
-		break;
 	}
 #undef CASE
 
@@ -2998,7 +2994,7 @@ static void ceph_con_workfn(struct work_struct *work)
  */
 static void con_fault(struct ceph_connection *con)
 {
-	dout("fault %p state %lu to peer %s\n",
+	dout("fault %p state %d to peer %s\n",
 	     con, con->state, ceph_pr_addr(&con->peer_addr));
 
 	pr_warn("%s%lld %s %s\n", ENTITY_NAME(con->peer_name),
-- 
cgit v1.2.3


From 6d7f62bfb5b5da6b0b37174c1fd32545f3b5b90d Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Mon, 9 Nov 2020 14:59:02 +0100
Subject: libceph: rename and export con->state states

In preparation for msgr2, rename msgr1 specific states and move the
defines to the header file.

Also drop state transition comments.  They don't cover all possible
transitions (e.g. NEGOTIATING -> STANDBY, etc) and currently do more
harm than good.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/messenger.h | 12 +++++-
 net/ceph/messenger.c           | 90 ++++++++++++++++++------------------------
 2 files changed, 50 insertions(+), 52 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index f053de4f46dd..e6be85b67c6c 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -239,6 +239,16 @@ struct ceph_msg {
 	struct ceph_msgpool *pool;
 };
 
+/*
+ * connection states
+ */
+#define CEPH_CON_S_CLOSED		1
+#define CEPH_CON_S_PREOPEN		2
+#define CEPH_CON_S_V1_BANNER		3
+#define CEPH_CON_S_V1_CONNECT_MSG	4
+#define CEPH_CON_S_OPEN			5
+#define CEPH_CON_S_STANDBY		6
+
 /* ceph connection fault delay defaults, for exponential backoff */
 #define BASE_DELAY_INTERVAL	(HZ / 4)
 #define MAX_DELAY_INTERVAL	(15 * HZ)
@@ -257,7 +267,7 @@ struct ceph_connection {
 
 	struct ceph_messenger *msgr;
 
-	int state;
+	int state;  /* CEPH_CON_S_* */
 	atomic_t sock_state;
 	struct socket *sock;
 	struct ceph_entity_addr peer_addr; /* peer address */
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 9c92f101aa88..adeb69ba6747 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -82,16 +82,6 @@
 #define CON_SOCK_STATE_CONNECTED	3	/* -> CLOSING or -> CLOSED */
 #define CON_SOCK_STATE_CLOSING		4	/* -> CLOSED */
 
-/*
- * connection states
- */
-#define CON_STATE_CLOSED        1  /* -> PREOPEN */
-#define CON_STATE_PREOPEN       2  /* -> CONNECTING, CLOSED */
-#define CON_STATE_CONNECTING    3  /* -> NEGOTIATING, CLOSED */
-#define CON_STATE_NEGOTIATING   4  /* -> OPEN, CLOSED */
-#define CON_STATE_OPEN          5  /* -> STANDBY, CLOSED */
-#define CON_STATE_STANDBY       6  /* -> PREOPEN, CLOSED */
-
 /*
  * ceph_connection flag bits
  */
@@ -674,7 +664,7 @@ void ceph_con_close(struct ceph_connection *con)
 {
 	mutex_lock(&con->mutex);
 	dout("con_close %p peer %s\n", con, ceph_pr_addr(&con->peer_addr));
-	con->state = CON_STATE_CLOSED;
+	con->state = CEPH_CON_S_CLOSED;
 
 	con_flag_clear(con, CON_FLAG_LOSSYTX);	/* so we retry next connect */
 	con_flag_clear(con, CON_FLAG_KEEPALIVE_PENDING);
@@ -698,8 +688,8 @@ void ceph_con_open(struct ceph_connection *con,
 	mutex_lock(&con->mutex);
 	dout("con_open %p %s\n", con, ceph_pr_addr(addr));
 
-	WARN_ON(con->state != CON_STATE_CLOSED);
-	con->state = CON_STATE_PREOPEN;
+	WARN_ON(con->state != CEPH_CON_S_CLOSED);
+	con->state = CEPH_CON_S_PREOPEN;
 
 	con->peer_name.type = (__u8) entity_type;
 	con->peer_name.num = cpu_to_le64(entity_num);
@@ -739,7 +729,7 @@ void ceph_con_init(struct ceph_connection *con, void *private,
 	INIT_LIST_HEAD(&con->out_sent);
 	INIT_DELAYED_WORK(&con->work, ceph_con_workfn);
 
-	con->state = CON_STATE_CLOSED;
+	con->state = CEPH_CON_S_CLOSED;
 }
 EXPORT_SYMBOL(ceph_con_init);
 
@@ -2183,7 +2173,7 @@ static int process_connect(struct ceph_connection *con)
 		if (con->ops->peer_reset)
 			con->ops->peer_reset(con);
 		mutex_lock(&con->mutex);
-		if (con->state != CON_STATE_NEGOTIATING)
+		if (con->state != CEPH_CON_S_V1_CONNECT_MSG)
 			return -EAGAIN;
 		break;
 
@@ -2232,8 +2222,8 @@ static int process_connect(struct ceph_connection *con)
 			return -1;
 		}
 
-		WARN_ON(con->state != CON_STATE_NEGOTIATING);
-		con->state = CON_STATE_OPEN;
+		WARN_ON(con->state != CEPH_CON_S_V1_CONNECT_MSG);
+		con->state = CEPH_CON_S_OPEN;
 		con->auth_retry = 0;    /* we authenticated; clear flag */
 		con->peer_global_seq = le32_to_cpu(con->in_reply.global_seq);
 		con->connect_seq++;
@@ -2583,16 +2573,16 @@ static int try_write(struct ceph_connection *con)
 	int ret = 1;
 
 	dout("try_write start %p state %d\n", con, con->state);
-	if (con->state != CON_STATE_PREOPEN &&
-	    con->state != CON_STATE_CONNECTING &&
-	    con->state != CON_STATE_NEGOTIATING &&
-	    con->state != CON_STATE_OPEN)
+	if (con->state != CEPH_CON_S_PREOPEN &&
+	    con->state != CEPH_CON_S_V1_BANNER &&
+	    con->state != CEPH_CON_S_V1_CONNECT_MSG &&
+	    con->state != CEPH_CON_S_OPEN)
 		return 0;
 
 	/* open the socket first? */
-	if (con->state == CON_STATE_PREOPEN) {
+	if (con->state == CEPH_CON_S_PREOPEN) {
 		BUG_ON(con->sock);
-		con->state = CON_STATE_CONNECTING;
+		con->state = CEPH_CON_S_V1_BANNER;
 
 		con_out_kvec_reset(con);
 		prepare_write_banner(con);
@@ -2646,7 +2636,7 @@ more:
 	}
 
 do_next:
-	if (con->state == CON_STATE_OPEN) {
+	if (con->state == CEPH_CON_S_OPEN) {
 		if (con_flag_test_and_clear(con, CON_FLAG_KEEPALIVE_PENDING)) {
 			prepare_write_keepalive(con);
 			goto more;
@@ -2680,9 +2670,9 @@ static int try_read(struct ceph_connection *con)
 
 more:
 	dout("try_read start %p state %d\n", con, con->state);
-	if (con->state != CON_STATE_CONNECTING &&
-	    con->state != CON_STATE_NEGOTIATING &&
-	    con->state != CON_STATE_OPEN)
+	if (con->state != CEPH_CON_S_V1_BANNER &&
+	    con->state != CEPH_CON_S_V1_CONNECT_MSG &&
+	    con->state != CEPH_CON_S_OPEN)
 		return 0;
 
 	BUG_ON(!con->sock);
@@ -2690,8 +2680,7 @@ more:
 	dout("try_read tag %d in_base_pos %d\n", (int)con->in_tag,
 	     con->in_base_pos);
 
-	if (con->state == CON_STATE_CONNECTING) {
-		dout("try_read connecting\n");
+	if (con->state == CEPH_CON_S_V1_BANNER) {
 		ret = read_partial_banner(con);
 		if (ret <= 0)
 			goto out;
@@ -2699,7 +2688,7 @@ more:
 		if (ret < 0)
 			goto out;
 
-		con->state = CON_STATE_NEGOTIATING;
+		con->state = CEPH_CON_S_V1_CONNECT_MSG;
 
 		/*
 		 * Received banner is good, exchange connection info.
@@ -2715,8 +2704,7 @@ more:
 		goto out;
 	}
 
-	if (con->state == CON_STATE_NEGOTIATING) {
-		dout("try_read negotiating\n");
+	if (con->state == CEPH_CON_S_V1_CONNECT_MSG) {
 		ret = read_partial_connect(con);
 		if (ret <= 0)
 			goto out;
@@ -2726,7 +2714,7 @@ more:
 		goto more;
 	}
 
-	WARN_ON(con->state != CON_STATE_OPEN);
+	WARN_ON(con->state != CEPH_CON_S_OPEN);
 
 	if (con->in_base_pos < 0) {
 		/*
@@ -2760,7 +2748,7 @@ more:
 			break;
 		case CEPH_MSGR_TAG_CLOSE:
 			con_close_socket(con);
-			con->state = CON_STATE_CLOSED;
+			con->state = CEPH_CON_S_CLOSED;
 			goto out;
 		default:
 			goto bad_tag;
@@ -2785,7 +2773,7 @@ more:
 		if (con->in_tag == CEPH_MSGR_TAG_READY)
 			goto more;
 		process_message(con);
-		if (con->state == CON_STATE_OPEN)
+		if (con->state == CEPH_CON_S_OPEN)
 			prepare_read_tag(con);
 		goto more;
 	}
@@ -2864,15 +2852,15 @@ static bool con_sock_closed(struct ceph_connection *con)
 		return false;
 
 #define CASE(x)								\
-	case CON_STATE_ ## x:						\
+	case CEPH_CON_S_ ## x:						\
 		con->error_msg = "socket closed (con state " #x ")";	\
 		break;
 
 	switch (con->state) {
 	CASE(CLOSED);
 	CASE(PREOPEN);
-	CASE(CONNECTING);
-	CASE(NEGOTIATING);
+	CASE(V1_BANNER);
+	CASE(V1_CONNECT_MSG);
 	CASE(OPEN);
 	CASE(STANDBY);
 	default:
@@ -2943,16 +2931,16 @@ static void ceph_con_workfn(struct work_struct *work)
 			dout("%s: con %p BACKOFF\n", __func__, con);
 			break;
 		}
-		if (con->state == CON_STATE_STANDBY) {
+		if (con->state == CEPH_CON_S_STANDBY) {
 			dout("%s: con %p STANDBY\n", __func__, con);
 			break;
 		}
-		if (con->state == CON_STATE_CLOSED) {
+		if (con->state == CEPH_CON_S_CLOSED) {
 			dout("%s: con %p CLOSED\n", __func__, con);
 			BUG_ON(con->sock);
 			break;
 		}
-		if (con->state == CON_STATE_PREOPEN) {
+		if (con->state == CEPH_CON_S_PREOPEN) {
 			dout("%s: con %p PREOPEN\n", __func__, con);
 			BUG_ON(con->sock);
 		}
@@ -3001,15 +2989,15 @@ static void con_fault(struct ceph_connection *con)
 		ceph_pr_addr(&con->peer_addr), con->error_msg);
 	con->error_msg = NULL;
 
-	WARN_ON(con->state != CON_STATE_CONNECTING &&
-	       con->state != CON_STATE_NEGOTIATING &&
-	       con->state != CON_STATE_OPEN);
+	WARN_ON(con->state != CEPH_CON_S_V1_BANNER &&
+	       con->state != CEPH_CON_S_V1_CONNECT_MSG &&
+	       con->state != CEPH_CON_S_OPEN);
 
 	ceph_con_reset_protocol(con);
 
 	if (con_flag_test(con, CON_FLAG_LOSSYTX)) {
 		dout("fault on LOSSYTX channel, marking CLOSED\n");
-		con->state = CON_STATE_CLOSED;
+		con->state = CEPH_CON_S_CLOSED;
 		return;
 	}
 
@@ -3022,10 +3010,10 @@ static void con_fault(struct ceph_connection *con)
 	    !con_flag_test(con, CON_FLAG_KEEPALIVE_PENDING)) {
 		dout("fault %p setting STANDBY clearing WRITE_PENDING\n", con);
 		con_flag_clear(con, CON_FLAG_WRITE_PENDING);
-		con->state = CON_STATE_STANDBY;
+		con->state = CEPH_CON_S_STANDBY;
 	} else {
 		/* retry after a delay. */
-		con->state = CON_STATE_PREOPEN;
+		con->state = CEPH_CON_S_PREOPEN;
 		if (!con->delay) {
 			con->delay = BASE_DELAY_INTERVAL;
 		} else if (con->delay < MAX_DELAY_INTERVAL) {
@@ -3092,9 +3080,9 @@ static void msg_con_set(struct ceph_msg *msg, struct ceph_connection *con)
 static void clear_standby(struct ceph_connection *con)
 {
 	/* come back from STANDBY? */
-	if (con->state == CON_STATE_STANDBY) {
+	if (con->state == CEPH_CON_S_STANDBY) {
 		dout("clear_standby %p and ++connect_seq\n", con);
-		con->state = CON_STATE_PREOPEN;
+		con->state = CEPH_CON_S_PREOPEN;
 		con->connect_seq++;
 		WARN_ON(con_flag_test(con, CON_FLAG_WRITE_PENDING));
 		WARN_ON(con_flag_test(con, CON_FLAG_KEEPALIVE_PENDING));
@@ -3115,7 +3103,7 @@ void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg)
 
 	mutex_lock(&con->mutex);
 
-	if (con->state == CON_STATE_CLOSED) {
+	if (con->state == CEPH_CON_S_CLOSED) {
 		dout("con_send %p closed, dropping %p\n", con, msg);
 		ceph_msg_put(msg);
 		mutex_unlock(&con->mutex);
@@ -3456,7 +3444,7 @@ static int ceph_con_in_msg_alloc(struct ceph_connection *con,
 	mutex_unlock(&con->mutex);
 	msg = con->ops->alloc_msg(con, hdr, skip);
 	mutex_lock(&con->mutex);
-	if (con->state != CON_STATE_OPEN) {
+	if (con->state != CEPH_CON_S_OPEN) {
 		if (msg)
 			ceph_msg_put(msg);
 		return -EAGAIN;
-- 
cgit v1.2.3


From 3fefd43e741a5b8d55aeb9115ff488ad2cad439b Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Mon, 9 Nov 2020 14:56:36 +0100
Subject: libceph: rename and export con->flags bits

In preparation for msgr2, move the defines to the header file.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/messenger.h | 13 ++++++-
 net/ceph/messenger.c           | 77 +++++++++++++++++++-----------------------
 2 files changed, 46 insertions(+), 44 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index e6be85b67c6c..b6962a0fd76f 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -249,6 +249,17 @@ struct ceph_msg {
 #define CEPH_CON_S_OPEN			5
 #define CEPH_CON_S_STANDBY		6
 
+/*
+ * ceph_connection flag bits
+ */
+#define CEPH_CON_F_LOSSYTX		0  /* we can close channel or drop
+					      messages on errors */
+#define CEPH_CON_F_KEEPALIVE_PENDING	1  /* we need to send a keepalive */
+#define CEPH_CON_F_WRITE_PENDING	2  /* we have data ready to send */
+#define CEPH_CON_F_SOCK_CLOSED		3  /* socket state changed to closed */
+#define CEPH_CON_F_BACKOFF		4  /* need to retry queuing delayed
+					      work */
+
 /* ceph connection fault delay defaults, for exponential backoff */
 #define BASE_DELAY_INTERVAL	(HZ / 4)
 #define MAX_DELAY_INTERVAL	(15 * HZ)
@@ -273,7 +284,7 @@ struct ceph_connection {
 	struct ceph_entity_addr peer_addr; /* peer address */
 	struct ceph_entity_addr peer_addr_for_me;
 
-	unsigned long flags;
+	unsigned long flags;  /* CEPH_CON_F_* */
 	const char *error_msg;  /* error message, if any */
 
 	struct ceph_entity_name peer_name; /* peer name */
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index adeb69ba6747..ee87dc3af959 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -82,24 +82,14 @@
 #define CON_SOCK_STATE_CONNECTED	3	/* -> CLOSING or -> CLOSED */
 #define CON_SOCK_STATE_CLOSING		4	/* -> CLOSED */
 
-/*
- * ceph_connection flag bits
- */
-#define CON_FLAG_LOSSYTX           0  /* we can close channel or drop
-				       * messages on errors */
-#define CON_FLAG_KEEPALIVE_PENDING 1  /* we need to send a keepalive */
-#define CON_FLAG_WRITE_PENDING	   2  /* we have data ready to send */
-#define CON_FLAG_SOCK_CLOSED	   3  /* socket state changed to closed */
-#define CON_FLAG_BACKOFF           4  /* need to retry queuing delayed work */
-
 static bool con_flag_valid(unsigned long con_flag)
 {
 	switch (con_flag) {
-	case CON_FLAG_LOSSYTX:
-	case CON_FLAG_KEEPALIVE_PENDING:
-	case CON_FLAG_WRITE_PENDING:
-	case CON_FLAG_SOCK_CLOSED:
-	case CON_FLAG_BACKOFF:
+	case CEPH_CON_F_LOSSYTX:
+	case CEPH_CON_F_KEEPALIVE_PENDING:
+	case CEPH_CON_F_WRITE_PENDING:
+	case CEPH_CON_F_SOCK_CLOSED:
+	case CEPH_CON_F_BACKOFF:
 		return true;
 	default:
 		return false;
@@ -380,7 +370,7 @@ static void ceph_sock_write_space(struct sock *sk)
 	 * buffer. See net/ipv4/tcp_input.c:tcp_check_space()
 	 * and net/core/stream.c:sk_stream_write_space().
 	 */
-	if (con_flag_test(con, CON_FLAG_WRITE_PENDING)) {
+	if (con_flag_test(con, CEPH_CON_F_WRITE_PENDING)) {
 		if (sk_stream_is_writeable(sk)) {
 			dout("%s %p queueing write work\n", __func__, con);
 			clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
@@ -406,7 +396,7 @@ static void ceph_sock_state_change(struct sock *sk)
 	case TCP_CLOSE_WAIT:
 		dout("%s TCP_CLOSE_WAIT\n", __func__);
 		con_sock_state_closing(con);
-		con_flag_set(con, CON_FLAG_SOCK_CLOSED);
+		con_flag_set(con, CEPH_CON_F_SOCK_CLOSED);
 		queue_con(con);
 		break;
 	case TCP_ESTABLISHED:
@@ -597,7 +587,7 @@ static int con_close_socket(struct ceph_connection *con)
 	 * received a socket close event before we had the chance to
 	 * shut the socket down.
 	 */
-	con_flag_clear(con, CON_FLAG_SOCK_CLOSED);
+	con_flag_clear(con, CEPH_CON_F_SOCK_CLOSED);
 
 	con_sock_state_closed(con);
 	return rc;
@@ -666,10 +656,10 @@ void ceph_con_close(struct ceph_connection *con)
 	dout("con_close %p peer %s\n", con, ceph_pr_addr(&con->peer_addr));
 	con->state = CEPH_CON_S_CLOSED;
 
-	con_flag_clear(con, CON_FLAG_LOSSYTX);	/* so we retry next connect */
-	con_flag_clear(con, CON_FLAG_KEEPALIVE_PENDING);
-	con_flag_clear(con, CON_FLAG_WRITE_PENDING);
-	con_flag_clear(con, CON_FLAG_BACKOFF);
+	con_flag_clear(con, CEPH_CON_F_LOSSYTX);  /* so we retry next connect */
+	con_flag_clear(con, CEPH_CON_F_KEEPALIVE_PENDING);
+	con_flag_clear(con, CEPH_CON_F_WRITE_PENDING);
+	con_flag_clear(con, CEPH_CON_F_BACKOFF);
 
 	ceph_con_reset_protocol(con);
 	ceph_con_reset_session(con);
@@ -1365,7 +1355,7 @@ static void prepare_write_message(struct ceph_connection *con)
 		prepare_write_message_footer(con);
 	}
 
-	con_flag_set(con, CON_FLAG_WRITE_PENDING);
+	con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
 }
 
 /*
@@ -1386,7 +1376,7 @@ static void prepare_write_ack(struct ceph_connection *con)
 				&con->out_temp_ack);
 
 	con->out_more = 1;  /* more will follow.. eventually.. */
-	con_flag_set(con, CON_FLAG_WRITE_PENDING);
+	con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
 }
 
 /*
@@ -1404,7 +1394,7 @@ static void prepare_write_seq(struct ceph_connection *con)
 	con_out_kvec_add(con, sizeof (con->out_temp_ack),
 			 &con->out_temp_ack);
 
-	con_flag_set(con, CON_FLAG_WRITE_PENDING);
+	con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
 }
 
 /*
@@ -1425,7 +1415,7 @@ static void prepare_write_keepalive(struct ceph_connection *con)
 	} else {
 		con_out_kvec_add(con, sizeof(tag_keepalive), &tag_keepalive);
 	}
-	con_flag_set(con, CON_FLAG_WRITE_PENDING);
+	con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
 }
 
 /*
@@ -1464,7 +1454,7 @@ static void prepare_write_banner(struct ceph_connection *con)
 					&con->msgr->my_enc_addr);
 
 	con->out_more = 0;
-	con_flag_set(con, CON_FLAG_WRITE_PENDING);
+	con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
 }
 
 static void __prepare_write_connect(struct ceph_connection *con)
@@ -1475,7 +1465,7 @@ static void __prepare_write_connect(struct ceph_connection *con)
 				 con->auth->authorizer_buf);
 
 	con->out_more = 0;
-	con_flag_set(con, CON_FLAG_WRITE_PENDING);
+	con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
 }
 
 static int prepare_write_connect(struct ceph_connection *con)
@@ -2236,7 +2226,7 @@ static int process_connect(struct ceph_connection *con)
 			le32_to_cpu(con->in_reply.connect_seq));
 
 		if (con->in_reply.flags & CEPH_MSG_CONNECT_LOSSY)
-			con_flag_set(con, CON_FLAG_LOSSYTX);
+			con_flag_set(con, CEPH_CON_F_LOSSYTX);
 
 		con->delay = 0;      /* reset backoff memory */
 
@@ -2637,7 +2627,8 @@ more:
 
 do_next:
 	if (con->state == CEPH_CON_S_OPEN) {
-		if (con_flag_test_and_clear(con, CON_FLAG_KEEPALIVE_PENDING)) {
+		if (con_flag_test_and_clear(con,
+				CEPH_CON_F_KEEPALIVE_PENDING)) {
 			prepare_write_keepalive(con);
 			goto more;
 		}
@@ -2653,7 +2644,7 @@ do_next:
 	}
 
 	/* Nothing to do! */
-	con_flag_clear(con, CON_FLAG_WRITE_PENDING);
+	con_flag_clear(con, CEPH_CON_F_WRITE_PENDING);
 	dout("try_write nothing else to write.\n");
 	ret = 0;
 out:
@@ -2848,7 +2839,7 @@ static void cancel_con(struct ceph_connection *con)
 
 static bool con_sock_closed(struct ceph_connection *con)
 {
-	if (!con_flag_test_and_clear(con, CON_FLAG_SOCK_CLOSED))
+	if (!con_flag_test_and_clear(con, CEPH_CON_F_SOCK_CLOSED))
 		return false;
 
 #define CASE(x)								\
@@ -2875,7 +2866,7 @@ static bool con_backoff(struct ceph_connection *con)
 {
 	int ret;
 
-	if (!con_flag_test_and_clear(con, CON_FLAG_BACKOFF))
+	if (!con_flag_test_and_clear(con, CEPH_CON_F_BACKOFF))
 		return false;
 
 	ret = queue_con_delay(con, con->delay);
@@ -2883,7 +2874,7 @@ static bool con_backoff(struct ceph_connection *con)
 		dout("%s: con %p FAILED to back off %lu\n", __func__,
 			con, con->delay);
 		BUG_ON(ret == -ENOENT);
-		con_flag_set(con, CON_FLAG_BACKOFF);
+		con_flag_set(con, CEPH_CON_F_BACKOFF);
 	}
 
 	return true;
@@ -2995,7 +2986,7 @@ static void con_fault(struct ceph_connection *con)
 
 	ceph_con_reset_protocol(con);
 
-	if (con_flag_test(con, CON_FLAG_LOSSYTX)) {
+	if (con_flag_test(con, CEPH_CON_F_LOSSYTX)) {
 		dout("fault on LOSSYTX channel, marking CLOSED\n");
 		con->state = CEPH_CON_S_CLOSED;
 		return;
@@ -3007,9 +2998,9 @@ static void con_fault(struct ceph_connection *con)
 	/* If there are no messages queued or keepalive pending, place
 	 * the connection in a STANDBY state */
 	if (list_empty(&con->out_queue) &&
-	    !con_flag_test(con, CON_FLAG_KEEPALIVE_PENDING)) {
+	    !con_flag_test(con, CEPH_CON_F_KEEPALIVE_PENDING)) {
 		dout("fault %p setting STANDBY clearing WRITE_PENDING\n", con);
-		con_flag_clear(con, CON_FLAG_WRITE_PENDING);
+		con_flag_clear(con, CEPH_CON_F_WRITE_PENDING);
 		con->state = CEPH_CON_S_STANDBY;
 	} else {
 		/* retry after a delay. */
@@ -3021,7 +3012,7 @@ static void con_fault(struct ceph_connection *con)
 			if (con->delay > MAX_DELAY_INTERVAL)
 				con->delay = MAX_DELAY_INTERVAL;
 		}
-		con_flag_set(con, CON_FLAG_BACKOFF);
+		con_flag_set(con, CEPH_CON_F_BACKOFF);
 		queue_con(con);
 	}
 }
@@ -3084,8 +3075,8 @@ static void clear_standby(struct ceph_connection *con)
 		dout("clear_standby %p and ++connect_seq\n", con);
 		con->state = CEPH_CON_S_PREOPEN;
 		con->connect_seq++;
-		WARN_ON(con_flag_test(con, CON_FLAG_WRITE_PENDING));
-		WARN_ON(con_flag_test(con, CON_FLAG_KEEPALIVE_PENDING));
+		WARN_ON(con_flag_test(con, CEPH_CON_F_WRITE_PENDING));
+		WARN_ON(con_flag_test(con, CEPH_CON_F_KEEPALIVE_PENDING));
 	}
 }
 
@@ -3126,7 +3117,7 @@ void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg)
 
 	/* if there wasn't anything waiting to send before, queue
 	 * new work */
-	if (con_flag_test_and_set(con, CON_FLAG_WRITE_PENDING) == 0)
+	if (con_flag_test_and_set(con, CEPH_CON_F_WRITE_PENDING) == 0)
 		queue_con(con);
 }
 EXPORT_SYMBOL(ceph_con_send);
@@ -3222,10 +3213,10 @@ void ceph_con_keepalive(struct ceph_connection *con)
 	dout("con_keepalive %p\n", con);
 	mutex_lock(&con->mutex);
 	clear_standby(con);
-	con_flag_set(con, CON_FLAG_KEEPALIVE_PENDING);
+	con_flag_set(con, CEPH_CON_F_KEEPALIVE_PENDING);
 	mutex_unlock(&con->mutex);
 
-	if (con_flag_test_and_set(con, CON_FLAG_WRITE_PENDING) == 0)
+	if (con_flag_test_and_set(con, CEPH_CON_F_WRITE_PENDING) == 0)
 		queue_con(con);
 }
 EXPORT_SYMBOL(ceph_con_keepalive);
-- 
cgit v1.2.3


From 699921d9e68ff3d9f8645488c12f4689c6533d70 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Mon, 9 Nov 2020 14:37:06 +0100
Subject: libceph: export zero_page

In preparation for msgr2, make zero_page global.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/messenger.h |  1 +
 net/ceph/messenger.c           | 17 +++++++++--------
 2 files changed, 10 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index b6962a0fd76f..513ed5f90bff 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -343,6 +343,7 @@ struct ceph_connection {
 	unsigned long       delay;          /* current delay interval */
 };
 
+extern struct page *ceph_zero_page;
 
 extern const char *ceph_pr_addr(const struct ceph_entity_addr *addr);
 
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index ee87dc3af959..d3880fbe8424 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -164,7 +164,7 @@ static void con_fault(struct ceph_connection *con);
 static char addr_str[ADDR_STR_COUNT][MAX_ADDR_STR_LEN];
 static atomic_t addr_str_seq = ATOMIC_INIT(0);
 
-static struct page *zero_page;		/* used in certain error cases */
+struct page *ceph_zero_page;		/* used in certain error cases */
 
 const char *ceph_pr_addr(const struct ceph_entity_addr *addr)
 {
@@ -234,9 +234,9 @@ static void _ceph_msgr_exit(void)
 		ceph_msgr_wq = NULL;
 	}
 
-	BUG_ON(zero_page == NULL);
-	put_page(zero_page);
-	zero_page = NULL;
+	BUG_ON(!ceph_zero_page);
+	put_page(ceph_zero_page);
+	ceph_zero_page = NULL;
 
 	ceph_msgr_slab_exit();
 }
@@ -246,9 +246,9 @@ int __init ceph_msgr_init(void)
 	if (ceph_msgr_slab_init())
 		return -ENOMEM;
 
-	BUG_ON(zero_page != NULL);
-	zero_page = ZERO_PAGE(0);
-	get_page(zero_page);
+	BUG_ON(ceph_zero_page);
+	ceph_zero_page = ZERO_PAGE(0);
+	get_page(ceph_zero_page);
 
 	/*
 	 * The number of active work items is limited by the number of
@@ -1645,7 +1645,8 @@ static int write_partial_skip(struct ceph_connection *con)
 
 		if (size == con->out_skip)
 			more = MSG_MORE;
-		ret = ceph_tcp_sendpage(con->sock, zero_page, 0, size, more);
+		ret = ceph_tcp_sendpage(con->sock, ceph_zero_page, 0, size,
+					more);
 		if (ret <= 0)
 			goto out;
 		con->out_skip -= ret;
-- 
cgit v1.2.3


From 6503e0b69c9d4d78b5450db01e79328f8ed4ef21 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Mon, 9 Nov 2020 16:29:47 +0100
Subject: libceph: export remaining protocol independent infrastructure

In preparation for msgr2, make all protocol independent functions
in messenger.c global.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/messenger.h |  39 +++++++++-
 net/ceph/messenger.c           | 157 ++++++++++++++++++++---------------------
 2 files changed, 113 insertions(+), 83 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index 513ed5f90bff..93815f1a42b5 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -345,13 +345,50 @@ struct ceph_connection {
 
 extern struct page *ceph_zero_page;
 
+void ceph_con_flag_clear(struct ceph_connection *con, unsigned long con_flag);
+void ceph_con_flag_set(struct ceph_connection *con, unsigned long con_flag);
+bool ceph_con_flag_test(struct ceph_connection *con, unsigned long con_flag);
+bool ceph_con_flag_test_and_clear(struct ceph_connection *con,
+				  unsigned long con_flag);
+bool ceph_con_flag_test_and_set(struct ceph_connection *con,
+				unsigned long con_flag);
+
+void ceph_encode_my_addr(struct ceph_messenger *msgr);
+
+int ceph_tcp_connect(struct ceph_connection *con);
+int ceph_con_close_socket(struct ceph_connection *con);
+void ceph_con_reset_session(struct ceph_connection *con);
+
+u32 ceph_get_global_seq(struct ceph_messenger *msgr, u32 gt);
+void ceph_con_discard_sent(struct ceph_connection *con, u64 ack_seq);
+void ceph_con_discard_requeued(struct ceph_connection *con, u64 reconnect_seq);
+
+void ceph_msg_data_cursor_init(struct ceph_msg_data_cursor *cursor,
+			       struct ceph_msg *msg, size_t length);
+struct page *ceph_msg_data_next(struct ceph_msg_data_cursor *cursor,
+				size_t *page_offset, size_t *length,
+				bool *last_piece);
+void ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor, size_t bytes);
+
+u32 ceph_crc32c_page(u32 crc, struct page *page, unsigned int page_offset,
+		     unsigned int length);
+
+bool ceph_addr_is_blank(const struct ceph_entity_addr *addr);
+int ceph_addr_port(const struct ceph_entity_addr *addr);
+void ceph_addr_set_port(struct ceph_entity_addr *addr, int p);
+
+void ceph_con_process_message(struct ceph_connection *con);
+int ceph_con_in_msg_alloc(struct ceph_connection *con,
+			  struct ceph_msg_header *hdr, int *skip);
+void ceph_con_get_out_msg(struct ceph_connection *con);
+
+
 extern const char *ceph_pr_addr(const struct ceph_entity_addr *addr);
 
 extern int ceph_parse_ips(const char *c, const char *end,
 			  struct ceph_entity_addr *addr,
 			  int max_count, int *count);
 
-
 extern int ceph_msgr_init(void);
 extern void ceph_msgr_exit(void);
 extern void ceph_msgr_flush(void);
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index d3880fbe8424..85d20372f923 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -96,37 +96,37 @@ static bool con_flag_valid(unsigned long con_flag)
 	}
 }
 
-static void con_flag_clear(struct ceph_connection *con, unsigned long con_flag)
+void ceph_con_flag_clear(struct ceph_connection *con, unsigned long con_flag)
 {
 	BUG_ON(!con_flag_valid(con_flag));
 
 	clear_bit(con_flag, &con->flags);
 }
 
-static void con_flag_set(struct ceph_connection *con, unsigned long con_flag)
+void ceph_con_flag_set(struct ceph_connection *con, unsigned long con_flag)
 {
 	BUG_ON(!con_flag_valid(con_flag));
 
 	set_bit(con_flag, &con->flags);
 }
 
-static bool con_flag_test(struct ceph_connection *con, unsigned long con_flag)
+bool ceph_con_flag_test(struct ceph_connection *con, unsigned long con_flag)
 {
 	BUG_ON(!con_flag_valid(con_flag));
 
 	return test_bit(con_flag, &con->flags);
 }
 
-static bool con_flag_test_and_clear(struct ceph_connection *con,
-					unsigned long con_flag)
+bool ceph_con_flag_test_and_clear(struct ceph_connection *con,
+				  unsigned long con_flag)
 {
 	BUG_ON(!con_flag_valid(con_flag));
 
 	return test_and_clear_bit(con_flag, &con->flags);
 }
 
-static bool con_flag_test_and_set(struct ceph_connection *con,
-					unsigned long con_flag)
+bool ceph_con_flag_test_and_set(struct ceph_connection *con,
+				unsigned long con_flag)
 {
 	BUG_ON(!con_flag_valid(con_flag));
 
@@ -199,7 +199,7 @@ const char *ceph_pr_addr(const struct ceph_entity_addr *addr)
 }
 EXPORT_SYMBOL(ceph_pr_addr);
 
-static void encode_my_addr(struct ceph_messenger *msgr)
+void ceph_encode_my_addr(struct ceph_messenger *msgr)
 {
 	memcpy(&msgr->my_enc_addr, &msgr->inst.addr, sizeof(msgr->my_enc_addr));
 	ceph_encode_banner_addr(&msgr->my_enc_addr);
@@ -370,7 +370,7 @@ static void ceph_sock_write_space(struct sock *sk)
 	 * buffer. See net/ipv4/tcp_input.c:tcp_check_space()
 	 * and net/core/stream.c:sk_stream_write_space().
 	 */
-	if (con_flag_test(con, CEPH_CON_F_WRITE_PENDING)) {
+	if (ceph_con_flag_test(con, CEPH_CON_F_WRITE_PENDING)) {
 		if (sk_stream_is_writeable(sk)) {
 			dout("%s %p queueing write work\n", __func__, con);
 			clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
@@ -396,7 +396,7 @@ static void ceph_sock_state_change(struct sock *sk)
 	case TCP_CLOSE_WAIT:
 		dout("%s TCP_CLOSE_WAIT\n", __func__);
 		con_sock_state_closing(con);
-		con_flag_set(con, CEPH_CON_F_SOCK_CLOSED);
+		ceph_con_flag_set(con, CEPH_CON_F_SOCK_CLOSED);
 		queue_con(con);
 		break;
 	case TCP_ESTABLISHED:
@@ -430,13 +430,15 @@ static void set_sock_callbacks(struct socket *sock,
 /*
  * initiate connection to a remote socket.
  */
-static int ceph_tcp_connect(struct ceph_connection *con)
+int ceph_tcp_connect(struct ceph_connection *con)
 {
 	struct sockaddr_storage ss = con->peer_addr.in_addr; /* align */
 	struct socket *sock;
 	unsigned int noio_flag;
 	int ret;
 
+	dout("%s con %p peer_addr %s\n", __func__, con,
+	     ceph_pr_addr(&con->peer_addr));
 	BUG_ON(con->sock);
 
 	/* sock_create_kern() allocates with GFP_KERNEL */
@@ -454,8 +456,6 @@ static int ceph_tcp_connect(struct ceph_connection *con)
 
 	set_sock_callbacks(sock, con);
 
-	dout("connect %s\n", ceph_pr_addr(&con->peer_addr));
-
 	con_sock_state_connecting(con);
 	ret = sock->ops->connect(sock, (struct sockaddr *)&ss, sizeof(ss),
 				 O_NONBLOCK);
@@ -570,11 +570,11 @@ static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
 /*
  * Shutdown/close the socket for the given connection.
  */
-static int con_close_socket(struct ceph_connection *con)
+int ceph_con_close_socket(struct ceph_connection *con)
 {
 	int rc = 0;
 
-	dout("con_close_socket on %p sock %p\n", con, con->sock);
+	dout("%s con %p sock %p\n", __func__, con, con->sock);
 	if (con->sock) {
 		rc = con->sock->ops->shutdown(con->sock, SHUT_RDWR);
 		sock_release(con->sock);
@@ -587,7 +587,7 @@ static int con_close_socket(struct ceph_connection *con)
 	 * received a socket close event before we had the chance to
 	 * shut the socket down.
 	 */
-	con_flag_clear(con, CEPH_CON_F_SOCK_CLOSED);
+	ceph_con_flag_clear(con, CEPH_CON_F_SOCK_CLOSED);
 
 	con_sock_state_closed(con);
 	return rc;
@@ -597,7 +597,7 @@ static void ceph_con_reset_protocol(struct ceph_connection *con)
 {
 	dout("%s con %p\n", __func__, con);
 
-	con_close_socket(con);
+	ceph_con_close_socket(con);
 	if (con->in_msg) {
 		WARN_ON(con->in_msg->con != con);
 		ceph_msg_put(con->in_msg);
@@ -631,7 +631,7 @@ static void ceph_msg_remove_list(struct list_head *head)
 	}
 }
 
-static void ceph_con_reset_session(struct ceph_connection *con)
+void ceph_con_reset_session(struct ceph_connection *con)
 {
 	dout("%s con %p\n", __func__, con);
 
@@ -656,10 +656,11 @@ void ceph_con_close(struct ceph_connection *con)
 	dout("con_close %p peer %s\n", con, ceph_pr_addr(&con->peer_addr));
 	con->state = CEPH_CON_S_CLOSED;
 
-	con_flag_clear(con, CEPH_CON_F_LOSSYTX);  /* so we retry next connect */
-	con_flag_clear(con, CEPH_CON_F_KEEPALIVE_PENDING);
-	con_flag_clear(con, CEPH_CON_F_WRITE_PENDING);
-	con_flag_clear(con, CEPH_CON_F_BACKOFF);
+	ceph_con_flag_clear(con, CEPH_CON_F_LOSSYTX);  /* so we retry next
+							  connect */
+	ceph_con_flag_clear(con, CEPH_CON_F_KEEPALIVE_PENDING);
+	ceph_con_flag_clear(con, CEPH_CON_F_WRITE_PENDING);
+	ceph_con_flag_clear(con, CEPH_CON_F_BACKOFF);
 
 	ceph_con_reset_protocol(con);
 	ceph_con_reset_session(con);
@@ -728,7 +729,7 @@ EXPORT_SYMBOL(ceph_con_init);
  * We maintain a global counter to order connection attempts.  Get
  * a unique seq greater than @gt.
  */
-static u32 get_global_seq(struct ceph_messenger *msgr, u32 gt)
+u32 ceph_get_global_seq(struct ceph_messenger *msgr, u32 gt)
 {
 	u32 ret;
 
@@ -743,7 +744,7 @@ static u32 get_global_seq(struct ceph_messenger *msgr, u32 gt)
 /*
  * Discard messages that have been acked by the server.
  */
-static void ceph_con_discard_sent(struct ceph_connection *con, u64 ack_seq)
+void ceph_con_discard_sent(struct ceph_connection *con, u64 ack_seq)
 {
 	struct ceph_msg *msg;
 	u64 seq;
@@ -768,8 +769,7 @@ static void ceph_con_discard_sent(struct ceph_connection *con, u64 ack_seq)
  * reconnect_seq.  This avoids gratuitously resending messages that
  * the server had received and handled prior to reconnect.
  */
-static void ceph_con_discard_requeued(struct ceph_connection *con,
-				      u64 reconnect_seq)
+void ceph_con_discard_requeued(struct ceph_connection *con, u64 reconnect_seq)
 {
 	struct ceph_msg *msg;
 	u64 seq;
@@ -1150,8 +1150,8 @@ static void __ceph_msg_data_cursor_init(struct ceph_msg_data_cursor *cursor)
 	cursor->need_crc = true;
 }
 
-static void ceph_msg_data_cursor_init(struct ceph_msg_data_cursor *cursor,
-				      struct ceph_msg *msg, size_t length)
+void ceph_msg_data_cursor_init(struct ceph_msg_data_cursor *cursor,
+			       struct ceph_msg *msg, size_t length)
 {
 	BUG_ON(!length);
 	BUG_ON(length > msg->data_length);
@@ -1168,9 +1168,9 @@ static void ceph_msg_data_cursor_init(struct ceph_msg_data_cursor *cursor,
  * data item, and supply the page offset and length of that piece.
  * Indicate whether this is the last piece in this data item.
  */
-static struct page *ceph_msg_data_next(struct ceph_msg_data_cursor *cursor,
-					size_t *page_offset, size_t *length,
-					bool *last_piece)
+struct page *ceph_msg_data_next(struct ceph_msg_data_cursor *cursor,
+				size_t *page_offset, size_t *length,
+				bool *last_piece)
 {
 	struct page *page;
 
@@ -1209,8 +1209,7 @@ static struct page *ceph_msg_data_next(struct ceph_msg_data_cursor *cursor,
  * Returns true if the result moves the cursor on to the next piece
  * of the data item.
  */
-static void ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor,
-				  size_t bytes)
+void ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor, size_t bytes)
 {
 	bool new_piece;
 
@@ -1284,8 +1283,6 @@ static void prepare_write_message_footer(struct ceph_connection *con)
 	con->out_msg_done = true;
 }
 
-static void ceph_con_get_out_msg(struct ceph_connection *con);
-
 /*
  * Prepare headers for the next outgoing message.
  */
@@ -1355,7 +1352,7 @@ static void prepare_write_message(struct ceph_connection *con)
 		prepare_write_message_footer(con);
 	}
 
-	con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
+	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
 }
 
 /*
@@ -1376,7 +1373,7 @@ static void prepare_write_ack(struct ceph_connection *con)
 				&con->out_temp_ack);
 
 	con->out_more = 1;  /* more will follow.. eventually.. */
-	con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
+	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
 }
 
 /*
@@ -1394,7 +1391,7 @@ static void prepare_write_seq(struct ceph_connection *con)
 	con_out_kvec_add(con, sizeof (con->out_temp_ack),
 			 &con->out_temp_ack);
 
-	con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
+	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
 }
 
 /*
@@ -1415,7 +1412,7 @@ static void prepare_write_keepalive(struct ceph_connection *con)
 	} else {
 		con_out_kvec_add(con, sizeof(tag_keepalive), &tag_keepalive);
 	}
-	con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
+	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
 }
 
 /*
@@ -1454,7 +1451,7 @@ static void prepare_write_banner(struct ceph_connection *con)
 					&con->msgr->my_enc_addr);
 
 	con->out_more = 0;
-	con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
+	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
 }
 
 static void __prepare_write_connect(struct ceph_connection *con)
@@ -1465,12 +1462,12 @@ static void __prepare_write_connect(struct ceph_connection *con)
 				 con->auth->authorizer_buf);
 
 	con->out_more = 0;
-	con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
+	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
 }
 
 static int prepare_write_connect(struct ceph_connection *con)
 {
-	unsigned int global_seq = get_global_seq(con->msgr, 0);
+	unsigned int global_seq = ceph_get_global_seq(con->msgr, 0);
 	int proto;
 	int ret;
 
@@ -1549,9 +1546,8 @@ out:
 	return ret;  /* done! */
 }
 
-static u32 ceph_crc32c_page(u32 crc, struct page *page,
-				unsigned int page_offset,
-				unsigned int length)
+u32 ceph_crc32c_page(u32 crc, struct page *page, unsigned int page_offset,
+		     unsigned int length)
 {
 	char *kaddr;
 
@@ -1813,7 +1809,7 @@ static int verify_hello(struct ceph_connection *con)
 	return 0;
 }
 
-static bool addr_is_blank(struct ceph_entity_addr *addr)
+bool ceph_addr_is_blank(const struct ceph_entity_addr *addr)
 {
 	struct sockaddr_storage ss = addr->in_addr; /* align */
 	struct in_addr *addr4 = &((struct sockaddr_in *)&ss)->sin_addr;
@@ -1829,7 +1825,7 @@ static bool addr_is_blank(struct ceph_entity_addr *addr)
 	}
 }
 
-static int addr_port(struct ceph_entity_addr *addr)
+int ceph_addr_port(const struct ceph_entity_addr *addr)
 {
 	switch (get_unaligned(&addr->in_addr.ss_family)) {
 	case AF_INET:
@@ -1840,7 +1836,7 @@ static int addr_port(struct ceph_entity_addr *addr)
 	return 0;
 }
 
-static void addr_set_port(struct ceph_entity_addr *addr, int p)
+void ceph_addr_set_port(struct ceph_entity_addr *addr, int p)
 {
 	switch (get_unaligned(&addr->in_addr.ss_family)) {
 	case AF_INET:
@@ -1998,7 +1994,7 @@ int ceph_parse_ips(const char *c, const char *end,
 			port = CEPH_MON_PORT;
 		}
 
-		addr_set_port(&addr[i], port);
+		ceph_addr_set_port(&addr[i], port);
 		addr[i].type = CEPH_ENTITY_ADDR_TYPE_LEGACY;
 
 		dout("parse_ips got %s\n", ceph_pr_addr(&addr[i]));
@@ -2037,7 +2033,7 @@ static int process_banner(struct ceph_connection *con)
 	 */
 	if (memcmp(&con->peer_addr, &con->actual_peer_addr,
 		   sizeof(con->peer_addr)) != 0 &&
-	    !(addr_is_blank(&con->actual_peer_addr) &&
+	    !(ceph_addr_is_blank(&con->actual_peer_addr) &&
 	      con->actual_peer_addr.nonce == con->peer_addr.nonce)) {
 		pr_warn("wrong peer, want %s/%u, got %s/%u\n",
 			ceph_pr_addr(&con->peer_addr),
@@ -2051,12 +2047,12 @@ static int process_banner(struct ceph_connection *con)
 	/*
 	 * did we learn our address?
 	 */
-	if (addr_is_blank(my_addr)) {
+	if (ceph_addr_is_blank(my_addr)) {
 		memcpy(&my_addr->in_addr,
 		       &con->peer_addr_for_me.in_addr,
 		       sizeof(con->peer_addr_for_me.in_addr));
-		addr_set_port(my_addr, 0);
-		encode_my_addr(con->msgr);
+		ceph_addr_set_port(my_addr, 0);
+		ceph_encode_my_addr(con->msgr);
 		dout("process_banner learned my addr is %s\n",
 		     ceph_pr_addr(my_addr));
 	}
@@ -2192,8 +2188,8 @@ static int process_connect(struct ceph_connection *con)
 		dout("process_connect got RETRY_GLOBAL my %u peer_gseq %u\n",
 		     con->peer_global_seq,
 		     le32_to_cpu(con->in_reply.global_seq));
-		get_global_seq(con->msgr,
-			       le32_to_cpu(con->in_reply.global_seq));
+		ceph_get_global_seq(con->msgr,
+				    le32_to_cpu(con->in_reply.global_seq));
 		con_out_kvec_reset(con);
 		ret = prepare_write_connect(con);
 		if (ret < 0)
@@ -2227,7 +2223,7 @@ static int process_connect(struct ceph_connection *con)
 			le32_to_cpu(con->in_reply.connect_seq));
 
 		if (con->in_reply.flags & CEPH_MSG_CONNECT_LOSSY)
-			con_flag_set(con, CEPH_CON_F_LOSSYTX);
+			ceph_con_flag_set(con, CEPH_CON_F_LOSSYTX);
 
 		con->delay = 0;      /* reset backoff memory */
 
@@ -2351,9 +2347,6 @@ static int read_partial_msg_data(struct ceph_connection *con)
 /*
  * read (part of) a message.
  */
-static int ceph_con_in_msg_alloc(struct ceph_connection *con,
-				 struct ceph_msg_header *hdr, int *skip);
-
 static int read_partial_message(struct ceph_connection *con)
 {
 	struct ceph_msg *m = con->in_msg;
@@ -2515,7 +2508,7 @@ static int read_partial_message(struct ceph_connection *con)
  * be careful not to do anything that waits on other incoming messages or it
  * may deadlock.
  */
-static void process_message(struct ceph_connection *con)
+void ceph_con_process_message(struct ceph_connection *con)
 {
 	struct ceph_msg *msg = con->in_msg;
 
@@ -2628,7 +2621,7 @@ more:
 
 do_next:
 	if (con->state == CEPH_CON_S_OPEN) {
-		if (con_flag_test_and_clear(con,
+		if (ceph_con_flag_test_and_clear(con,
 				CEPH_CON_F_KEEPALIVE_PENDING)) {
 			prepare_write_keepalive(con);
 			goto more;
@@ -2645,7 +2638,7 @@ do_next:
 	}
 
 	/* Nothing to do! */
-	con_flag_clear(con, CEPH_CON_F_WRITE_PENDING);
+	ceph_con_flag_clear(con, CEPH_CON_F_WRITE_PENDING);
 	dout("try_write nothing else to write.\n");
 	ret = 0;
 out:
@@ -2739,7 +2732,7 @@ more:
 			prepare_read_keepalive_ack(con);
 			break;
 		case CEPH_MSGR_TAG_CLOSE:
-			con_close_socket(con);
+			ceph_con_close_socket(con);
 			con->state = CEPH_CON_S_CLOSED;
 			goto out;
 		default:
@@ -2764,7 +2757,7 @@ more:
 		}
 		if (con->in_tag == CEPH_MSGR_TAG_READY)
 			goto more;
-		process_message(con);
+		ceph_con_process_message(con);
 		if (con->state == CEPH_CON_S_OPEN)
 			prepare_read_tag(con);
 		goto more;
@@ -2840,7 +2833,7 @@ static void cancel_con(struct ceph_connection *con)
 
 static bool con_sock_closed(struct ceph_connection *con)
 {
-	if (!con_flag_test_and_clear(con, CEPH_CON_F_SOCK_CLOSED))
+	if (!ceph_con_flag_test_and_clear(con, CEPH_CON_F_SOCK_CLOSED))
 		return false;
 
 #define CASE(x)								\
@@ -2867,7 +2860,7 @@ static bool con_backoff(struct ceph_connection *con)
 {
 	int ret;
 
-	if (!con_flag_test_and_clear(con, CEPH_CON_F_BACKOFF))
+	if (!ceph_con_flag_test_and_clear(con, CEPH_CON_F_BACKOFF))
 		return false;
 
 	ret = queue_con_delay(con, con->delay);
@@ -2875,7 +2868,7 @@ static bool con_backoff(struct ceph_connection *con)
 		dout("%s: con %p FAILED to back off %lu\n", __func__,
 			con, con->delay);
 		BUG_ON(ret == -ENOENT);
-		con_flag_set(con, CEPH_CON_F_BACKOFF);
+		ceph_con_flag_set(con, CEPH_CON_F_BACKOFF);
 	}
 
 	return true;
@@ -2987,7 +2980,7 @@ static void con_fault(struct ceph_connection *con)
 
 	ceph_con_reset_protocol(con);
 
-	if (con_flag_test(con, CEPH_CON_F_LOSSYTX)) {
+	if (ceph_con_flag_test(con, CEPH_CON_F_LOSSYTX)) {
 		dout("fault on LOSSYTX channel, marking CLOSED\n");
 		con->state = CEPH_CON_S_CLOSED;
 		return;
@@ -2999,9 +2992,9 @@ static void con_fault(struct ceph_connection *con)
 	/* If there are no messages queued or keepalive pending, place
 	 * the connection in a STANDBY state */
 	if (list_empty(&con->out_queue) &&
-	    !con_flag_test(con, CEPH_CON_F_KEEPALIVE_PENDING)) {
+	    !ceph_con_flag_test(con, CEPH_CON_F_KEEPALIVE_PENDING)) {
 		dout("fault %p setting STANDBY clearing WRITE_PENDING\n", con);
-		con_flag_clear(con, CEPH_CON_F_WRITE_PENDING);
+		ceph_con_flag_clear(con, CEPH_CON_F_WRITE_PENDING);
 		con->state = CEPH_CON_S_STANDBY;
 	} else {
 		/* retry after a delay. */
@@ -3013,7 +3006,7 @@ static void con_fault(struct ceph_connection *con)
 			if (con->delay > MAX_DELAY_INTERVAL)
 				con->delay = MAX_DELAY_INTERVAL;
 		}
-		con_flag_set(con, CEPH_CON_F_BACKOFF);
+		ceph_con_flag_set(con, CEPH_CON_F_BACKOFF);
 		queue_con(con);
 	}
 }
@@ -3023,7 +3016,7 @@ void ceph_messenger_reset_nonce(struct ceph_messenger *msgr)
 {
 	u32 nonce = le32_to_cpu(msgr->inst.addr.nonce) + 1000000;
 	msgr->inst.addr.nonce = cpu_to_le32(nonce);
-	encode_my_addr(msgr);
+	ceph_encode_my_addr(msgr);
 }
 
 /*
@@ -3037,7 +3030,7 @@ void ceph_messenger_init(struct ceph_messenger *msgr,
 	if (myaddr) {
 		memcpy(&msgr->inst.addr.in_addr, &myaddr->in_addr,
 		       sizeof(msgr->inst.addr.in_addr));
-		addr_set_port(&msgr->inst.addr, 0);
+		ceph_addr_set_port(&msgr->inst.addr, 0);
 	}
 
 	msgr->inst.addr.type = 0;
@@ -3047,7 +3040,7 @@ void ceph_messenger_init(struct ceph_messenger *msgr,
 		get_random_bytes(&msgr->inst.addr.nonce,
 				 sizeof(msgr->inst.addr.nonce));
 	} while (!msgr->inst.addr.nonce);
-	encode_my_addr(msgr);
+	ceph_encode_my_addr(msgr);
 
 	atomic_set(&msgr->stopping, 0);
 	write_pnet(&msgr->net, get_net(current->nsproxy->net_ns));
@@ -3076,8 +3069,8 @@ static void clear_standby(struct ceph_connection *con)
 		dout("clear_standby %p and ++connect_seq\n", con);
 		con->state = CEPH_CON_S_PREOPEN;
 		con->connect_seq++;
-		WARN_ON(con_flag_test(con, CEPH_CON_F_WRITE_PENDING));
-		WARN_ON(con_flag_test(con, CEPH_CON_F_KEEPALIVE_PENDING));
+		WARN_ON(ceph_con_flag_test(con, CEPH_CON_F_WRITE_PENDING));
+		WARN_ON(ceph_con_flag_test(con, CEPH_CON_F_KEEPALIVE_PENDING));
 	}
 }
 
@@ -3118,7 +3111,7 @@ void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg)
 
 	/* if there wasn't anything waiting to send before, queue
 	 * new work */
-	if (con_flag_test_and_set(con, CEPH_CON_F_WRITE_PENDING) == 0)
+	if (!ceph_con_flag_test_and_set(con, CEPH_CON_F_WRITE_PENDING))
 		queue_con(con);
 }
 EXPORT_SYMBOL(ceph_con_send);
@@ -3214,10 +3207,10 @@ void ceph_con_keepalive(struct ceph_connection *con)
 	dout("con_keepalive %p\n", con);
 	mutex_lock(&con->mutex);
 	clear_standby(con);
-	con_flag_set(con, CEPH_CON_F_KEEPALIVE_PENDING);
+	ceph_con_flag_set(con, CEPH_CON_F_KEEPALIVE_PENDING);
 	mutex_unlock(&con->mutex);
 
-	if (con_flag_test_and_set(con, CEPH_CON_F_WRITE_PENDING) == 0)
+	if (!ceph_con_flag_test_and_set(con, CEPH_CON_F_WRITE_PENDING))
 		queue_con(con);
 }
 EXPORT_SYMBOL(ceph_con_keepalive);
@@ -3423,8 +3416,8 @@ static int ceph_alloc_middle(struct ceph_connection *con, struct ceph_msg *msg)
  * On error (ENOMEM, EAGAIN, ...),
  *  - con->in_msg == NULL
  */
-static int ceph_con_in_msg_alloc(struct ceph_connection *con,
-				 struct ceph_msg_header *hdr, int *skip)
+int ceph_con_in_msg_alloc(struct ceph_connection *con,
+			  struct ceph_msg_header *hdr, int *skip)
 {
 	int middle_len = le32_to_cpu(hdr->middle_len);
 	struct ceph_msg *msg;
@@ -3470,7 +3463,7 @@ static int ceph_con_in_msg_alloc(struct ceph_connection *con,
 	return ret;
 }
 
-static void ceph_con_get_out_msg(struct ceph_connection *con)
+void ceph_con_get_out_msg(struct ceph_connection *con)
 {
 	struct ceph_msg *msg;
 
-- 
cgit v1.2.3


From 566050e17e53db283d4e26b73b4b50556f97ce7b Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Thu, 12 Nov 2020 12:55:39 +0100
Subject: libceph: separate msgr1 protocol implementation

In preparation for msgr2, define internal messenger <-> protocol
interface (as opposed to external messenger <-> client interface, which
is struct ceph_connection_operations) consisting of try_read(),
try_write(), revoke(), revoke_incoming(), opened(), reset_session() and
reset_protocol() ops.  The semantics are exactly the same as they are
now.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/messenger.h |   8 +++
 net/ceph/messenger.c           | 138 ++++++++++++++++++++++++++---------------
 2 files changed, 96 insertions(+), 50 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index 93815f1a42b5..8cc8b08eb3dd 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -382,6 +382,14 @@ int ceph_con_in_msg_alloc(struct ceph_connection *con,
 			  struct ceph_msg_header *hdr, int *skip);
 void ceph_con_get_out_msg(struct ceph_connection *con);
 
+int ceph_con_v1_try_read(struct ceph_connection *con);
+int ceph_con_v1_try_write(struct ceph_connection *con);
+void ceph_con_v1_revoke(struct ceph_connection *con);
+void ceph_con_v1_revoke_incoming(struct ceph_connection *con);
+bool ceph_con_v1_opened(struct ceph_connection *con);
+void ceph_con_v1_reset_session(struct ceph_connection *con);
+void ceph_con_v1_reset_protocol(struct ceph_connection *con);
+
 
 extern const char *ceph_pr_addr(const struct ceph_entity_addr *addr);
 
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 85d20372f923..4ca7d9b594c7 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -593,6 +593,11 @@ int ceph_con_close_socket(struct ceph_connection *con)
 	return rc;
 }
 
+void ceph_con_v1_reset_protocol(struct ceph_connection *con)
+{
+	con->out_skip = 0;
+}
+
 static void ceph_con_reset_protocol(struct ceph_connection *con)
 {
 	dout("%s con %p\n", __func__, con);
@@ -609,7 +614,7 @@ static void ceph_con_reset_protocol(struct ceph_connection *con)
 		con->out_msg = NULL;
 	}
 
-	con->out_skip = 0;
+	ceph_con_v1_reset_protocol(con);
 }
 
 /*
@@ -631,6 +636,12 @@ static void ceph_msg_remove_list(struct list_head *head)
 	}
 }
 
+void ceph_con_v1_reset_session(struct ceph_connection *con)
+{
+	con->connect_seq = 0;
+	con->peer_global_seq = 0;
+}
+
 void ceph_con_reset_session(struct ceph_connection *con)
 {
 	dout("%s con %p\n", __func__, con);
@@ -643,8 +654,7 @@ void ceph_con_reset_session(struct ceph_connection *con)
 	con->in_seq = 0;
 	con->in_seq_acked = 0;
 
-	con->connect_seq = 0;
-	con->peer_global_seq = 0;
+	ceph_con_v1_reset_session(con);
 }
 
 /*
@@ -692,12 +702,17 @@ void ceph_con_open(struct ceph_connection *con,
 }
 EXPORT_SYMBOL(ceph_con_open);
 
+bool ceph_con_v1_opened(struct ceph_connection *con)
+{
+	return con->connect_seq;
+}
+
 /*
  * return true if this connection ever successfully opened
  */
 bool ceph_con_opened(struct ceph_connection *con)
 {
-	return con->connect_seq > 0;
+	return ceph_con_v1_opened(con);
 }
 
 /*
@@ -2552,7 +2567,7 @@ static int read_keepalive_ack(struct ceph_connection *con)
  * Write something to the socket.  Called in a worker thread when the
  * socket appears to be writeable and we have something ready to send.
  */
-static int try_write(struct ceph_connection *con)
+int ceph_con_v1_try_write(struct ceph_connection *con)
 {
 	int ret = 1;
 
@@ -2649,7 +2664,7 @@ out:
 /*
  * Read what we can from the socket.
  */
-static int try_read(struct ceph_connection *con)
+int ceph_con_v1_try_read(struct ceph_connection *con)
 {
 	int ret = -1;
 
@@ -2930,7 +2945,7 @@ static void ceph_con_workfn(struct work_struct *work)
 			BUG_ON(con->sock);
 		}
 
-		ret = try_read(con);
+		ret = ceph_con_v1_try_read(con);
 		if (ret < 0) {
 			if (ret == -EAGAIN)
 				continue;
@@ -2940,7 +2955,7 @@ static void ceph_con_workfn(struct work_struct *work)
 			break;
 		}
 
-		ret = try_write(con);
+		ret = ceph_con_v1_try_write(con);
 		if (ret < 0) {
 			if (ret == -EAGAIN)
 				continue;
@@ -3116,6 +3131,29 @@ void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg)
 }
 EXPORT_SYMBOL(ceph_con_send);
 
+void ceph_con_v1_revoke(struct ceph_connection *con)
+{
+	struct ceph_msg *msg = con->out_msg;
+
+	WARN_ON(con->out_skip);
+	/* footer */
+	if (con->out_msg_done) {
+		con->out_skip += con_out_kvec_skip(con);
+	} else {
+		WARN_ON(!msg->data_length);
+		con->out_skip += sizeof_footer(con);
+	}
+	/* data, middle, front */
+	if (msg->data_length)
+		con->out_skip += msg->cursor.total_resid;
+	if (msg->middle)
+		con->out_skip += con_out_kvec_skip(con);
+	con->out_skip += con_out_kvec_skip(con);
+
+	dout("%s con %p out_kvec_bytes %d out_skip %d\n", __func__, con,
+	     con->out_kvec_bytes, con->out_skip);
+}
+
 /*
  * Revoke a message that was previously queued for send
  */
@@ -3129,39 +3167,50 @@ void ceph_msg_revoke(struct ceph_msg *msg)
 	}
 
 	mutex_lock(&con->mutex);
-	if (!list_empty(&msg->list_head)) {
-		dout("%s %p msg %p - was on queue\n", __func__, con, msg);
-		list_del_init(&msg->list_head);
-		msg->hdr.seq = 0;
-
-		ceph_msg_put(msg);
+	if (list_empty(&msg->list_head)) {
+		WARN_ON(con->out_msg == msg);
+		dout("%s con %p msg %p not linked\n", __func__, con, msg);
+		mutex_unlock(&con->mutex);
+		return;
 	}
-	if (con->out_msg == msg) {
-		BUG_ON(con->out_skip);
-		/* footer */
-		if (con->out_msg_done) {
-			con->out_skip += con_out_kvec_skip(con);
-		} else {
-			BUG_ON(!msg->data_length);
-			con->out_skip += sizeof_footer(con);
-		}
-		/* data, middle, front */
-		if (msg->data_length)
-			con->out_skip += msg->cursor.total_resid;
-		if (msg->middle)
-			con->out_skip += con_out_kvec_skip(con);
-		con->out_skip += con_out_kvec_skip(con);
 
-		dout("%s %p msg %p - was sending, will write %d skip %d\n",
-		     __func__, con, msg, con->out_kvec_bytes, con->out_skip);
-		msg->hdr.seq = 0;
+	dout("%s con %p msg %p was linked\n", __func__, con, msg);
+	msg->hdr.seq = 0;
+	ceph_msg_remove(msg);
+
+	if (con->out_msg == msg) {
+		WARN_ON(con->state != CEPH_CON_S_OPEN);
+		dout("%s con %p msg %p was sending\n", __func__, con, msg);
+		ceph_con_v1_revoke(con);
+		ceph_msg_put(con->out_msg);
 		con->out_msg = NULL;
-		ceph_msg_put(msg);
+	} else {
+		dout("%s con %p msg %p not current, out_msg %p\n", __func__,
+		     con, msg, con->out_msg);
 	}
-
 	mutex_unlock(&con->mutex);
 }
 
+void ceph_con_v1_revoke_incoming(struct ceph_connection *con)
+{
+	unsigned int front_len = le32_to_cpu(con->in_hdr.front_len);
+	unsigned int middle_len = le32_to_cpu(con->in_hdr.middle_len);
+	unsigned int data_len = le32_to_cpu(con->in_hdr.data_len);
+
+	/* skip rest of message */
+	con->in_base_pos = con->in_base_pos -
+			sizeof(struct ceph_msg_header) -
+			front_len -
+			middle_len -
+			data_len -
+			sizeof(struct ceph_msg_footer);
+
+	con->in_tag = CEPH_MSGR_TAG_READY;
+	con->in_seq++;
+
+	dout("%s con %p in_base_pos %d\n", __func__, con, con->in_base_pos);
+}
+
 /*
  * Revoke a message that we may be reading data into
  */
@@ -3176,25 +3225,14 @@ void ceph_msg_revoke_incoming(struct ceph_msg *msg)
 
 	mutex_lock(&con->mutex);
 	if (con->in_msg == msg) {
-		unsigned int front_len = le32_to_cpu(con->in_hdr.front_len);
-		unsigned int middle_len = le32_to_cpu(con->in_hdr.middle_len);
-		unsigned int data_len = le32_to_cpu(con->in_hdr.data_len);
-
-		/* skip rest of message */
-		dout("%s %p msg %p revoked\n", __func__, con, msg);
-		con->in_base_pos = con->in_base_pos -
-				sizeof(struct ceph_msg_header) -
-				front_len -
-				middle_len -
-				data_len -
-				sizeof(struct ceph_msg_footer);
+		WARN_ON(con->state != CEPH_CON_S_OPEN);
+		dout("%s con %p msg %p was recving\n", __func__, con, msg);
+		ceph_con_v1_revoke_incoming(con);
 		ceph_msg_put(con->in_msg);
 		con->in_msg = NULL;
-		con->in_tag = CEPH_MSGR_TAG_READY;
-		con->in_seq++;
 	} else {
-		dout("%s %p in_msg %p msg %p no-op\n",
-		     __func__, con, con->in_msg, msg);
+		dout("%s con %p msg %p not current, in_msg %p\n", __func__,
+		     con, msg, con->in_msg);
 	}
 	mutex_unlock(&con->mutex);
 }
-- 
cgit v1.2.3


From 2f713615ddd9d805b6c5e79c52e0e11af99d2bf1 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Thu, 12 Nov 2020 15:48:06 +0100
Subject: libceph: move msgr1 protocol implementation to its own file

A pure move, no other changes.

Note that ceph_tcp_recv{msg,page}() and ceph_tcp_send{msg,page}()
helpers are also moved.  msgr2 will bring its own, more efficient,
variants based on iov_iter.  Switching msgr1 to them was considered
but decided against to avoid subtle regressions.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/messenger.h |    1 +
 net/ceph/Makefile              |    3 +-
 net/ceph/messenger.c           | 1495 ---------------------------------------
 net/ceph/messenger_v1.c        | 1502 ++++++++++++++++++++++++++++++++++++++++
 4 files changed, 1505 insertions(+), 1496 deletions(-)
 create mode 100644 net/ceph/messenger_v1.c

(limited to 'include/linux')

diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index 8cc8b08eb3dd..b5268127c55e 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -382,6 +382,7 @@ int ceph_con_in_msg_alloc(struct ceph_connection *con,
 			  struct ceph_msg_header *hdr, int *skip);
 void ceph_con_get_out_msg(struct ceph_connection *con);
 
+/* messenger_v1.c */
 int ceph_con_v1_try_read(struct ceph_connection *con);
 int ceph_con_v1_try_write(struct ceph_connection *con);
 void ceph_con_v1_revoke(struct ceph_connection *con);
diff --git a/net/ceph/Makefile b/net/ceph/Makefile
index ce09bb4fb249..df02bd8d6c7b 100644
--- a/net/ceph/Makefile
+++ b/net/ceph/Makefile
@@ -14,4 +14,5 @@ libceph-y := ceph_common.o messenger.o msgpool.o buffer.o pagelist.o \
 	crypto.o armor.o \
 	auth_x.o \
 	ceph_strings.o ceph_hash.o \
-	pagevec.o snapshot.o string_table.o
+	pagevec.o snapshot.o string_table.o \
+	messenger_v1.o
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 4ca7d9b594c7..544cfdbe52d6 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -137,12 +137,6 @@ bool ceph_con_flag_test_and_set(struct ceph_connection *con,
 
 static struct kmem_cache	*ceph_msg_cache;
 
-/* static tag bytes (protocol control messages) */
-static char tag_msg = CEPH_MSGR_TAG_MSG;
-static char tag_ack = CEPH_MSGR_TAG_ACK;
-static char tag_keepalive = CEPH_MSGR_TAG_KEEPALIVE;
-static char tag_keepalive2 = CEPH_MSGR_TAG_KEEPALIVE2;
-
 #ifdef CONFIG_LOCKDEP
 static struct lock_class_key socket_class;
 #endif
@@ -477,96 +471,6 @@ int ceph_tcp_connect(struct ceph_connection *con)
 	return 0;
 }
 
-/*
- * If @buf is NULL, discard up to @len bytes.
- */
-static int ceph_tcp_recvmsg(struct socket *sock, void *buf, size_t len)
-{
-	struct kvec iov = {buf, len};
-	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL };
-	int r;
-
-	if (!buf)
-		msg.msg_flags |= MSG_TRUNC;
-
-	iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, len);
-	r = sock_recvmsg(sock, &msg, msg.msg_flags);
-	if (r == -EAGAIN)
-		r = 0;
-	return r;
-}
-
-static int ceph_tcp_recvpage(struct socket *sock, struct page *page,
-		     int page_offset, size_t length)
-{
-	struct bio_vec bvec = {
-		.bv_page = page,
-		.bv_offset = page_offset,
-		.bv_len = length
-	};
-	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL };
-	int r;
-
-	BUG_ON(page_offset + length > PAGE_SIZE);
-	iov_iter_bvec(&msg.msg_iter, READ, &bvec, 1, length);
-	r = sock_recvmsg(sock, &msg, msg.msg_flags);
-	if (r == -EAGAIN)
-		r = 0;
-	return r;
-}
-
-/*
- * write something.  @more is true if caller will be sending more data
- * shortly.
- */
-static int ceph_tcp_sendmsg(struct socket *sock, struct kvec *iov,
-			    size_t kvlen, size_t len, bool more)
-{
-	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL };
-	int r;
-
-	if (more)
-		msg.msg_flags |= MSG_MORE;
-	else
-		msg.msg_flags |= MSG_EOR;  /* superfluous, but what the hell */
-
-	r = kernel_sendmsg(sock, &msg, iov, kvlen, len);
-	if (r == -EAGAIN)
-		r = 0;
-	return r;
-}
-
-/*
- * @more: either or both of MSG_MORE and MSG_SENDPAGE_NOTLAST
- */
-static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
-			     int offset, size_t size, int more)
-{
-	ssize_t (*sendpage)(struct socket *sock, struct page *page,
-			    int offset, size_t size, int flags);
-	int flags = MSG_DONTWAIT | MSG_NOSIGNAL | more;
-	int ret;
-
-	/*
-	 * sendpage cannot properly handle pages with page_count == 0,
-	 * we need to fall back to sendmsg if that's the case.
-	 *
-	 * Same goes for slab pages: skb_can_coalesce() allows
-	 * coalescing neighboring slab objects into a single frag which
-	 * triggers one of hardened usercopy checks.
-	 */
-	if (sendpage_ok(page))
-		sendpage = sock->ops->sendpage;
-	else
-		sendpage = sock_no_sendpage;
-
-	ret = sendpage(sock, page, offset, size, flags);
-	if (ret == -EAGAIN)
-		ret = 0;
-
-	return ret;
-}
-
 /*
  * Shutdown/close the socket for the given connection.
  */
@@ -593,11 +497,6 @@ int ceph_con_close_socket(struct ceph_connection *con)
 	return rc;
 }
 
-void ceph_con_v1_reset_protocol(struct ceph_connection *con)
-{
-	con->out_skip = 0;
-}
-
 static void ceph_con_reset_protocol(struct ceph_connection *con)
 {
 	dout("%s con %p\n", __func__, con);
@@ -636,12 +535,6 @@ static void ceph_msg_remove_list(struct list_head *head)
 	}
 }
 
-void ceph_con_v1_reset_session(struct ceph_connection *con)
-{
-	con->connect_seq = 0;
-	con->peer_global_seq = 0;
-}
-
 void ceph_con_reset_session(struct ceph_connection *con)
 {
 	dout("%s con %p\n", __func__, con);
@@ -702,11 +595,6 @@ void ceph_con_open(struct ceph_connection *con,
 }
 EXPORT_SYMBOL(ceph_con_open);
 
-bool ceph_con_v1_opened(struct ceph_connection *con)
-{
-	return con->connect_seq;
-}
-
 /*
  * return true if this connection ever successfully opened
  */
@@ -739,7 +627,6 @@ void ceph_con_init(struct ceph_connection *con, void *private,
 }
 EXPORT_SYMBOL(ceph_con_init);
 
-
 /*
  * We maintain a global counter to order connection attempts.  Get
  * a unique seq greater than @gt.
@@ -805,50 +692,6 @@ void ceph_con_discard_requeued(struct ceph_connection *con, u64 reconnect_seq)
 	}
 }
 
-static void con_out_kvec_reset(struct ceph_connection *con)
-{
-	BUG_ON(con->out_skip);
-
-	con->out_kvec_left = 0;
-	con->out_kvec_bytes = 0;
-	con->out_kvec_cur = &con->out_kvec[0];
-}
-
-static void con_out_kvec_add(struct ceph_connection *con,
-				size_t size, void *data)
-{
-	int index = con->out_kvec_left;
-
-	BUG_ON(con->out_skip);
-	BUG_ON(index >= ARRAY_SIZE(con->out_kvec));
-
-	con->out_kvec[index].iov_len = size;
-	con->out_kvec[index].iov_base = data;
-	con->out_kvec_left++;
-	con->out_kvec_bytes += size;
-}
-
-/*
- * Chop off a kvec from the end.  Return residual number of bytes for
- * that kvec, i.e. how many bytes would have been written if the kvec
- * hadn't been nuked.
- */
-static int con_out_kvec_skip(struct ceph_connection *con)
-{
-	int off = con->out_kvec_cur - con->out_kvec;
-	int skip = 0;
-
-	if (con->out_kvec_bytes > 0) {
-		skip = con->out_kvec[off + con->out_kvec_left - 1].iov_len;
-		BUG_ON(con->out_kvec_bytes < skip);
-		BUG_ON(!con->out_kvec_left);
-		con->out_kvec_bytes -= skip;
-		con->out_kvec_left--;
-	}
-
-	return skip;
-}
-
 #ifdef CONFIG_BLOCK
 
 /*
@@ -1260,307 +1103,6 @@ void ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor, size_t bytes)
 	cursor->need_crc = new_piece;
 }
 
-static size_t sizeof_footer(struct ceph_connection *con)
-{
-	return (con->peer_features & CEPH_FEATURE_MSG_AUTH) ?
-	    sizeof(struct ceph_msg_footer) :
-	    sizeof(struct ceph_msg_footer_old);
-}
-
-static void prepare_message_data(struct ceph_msg *msg, u32 data_len)
-{
-	/* Initialize data cursor */
-
-	ceph_msg_data_cursor_init(&msg->cursor, msg, data_len);
-}
-
-/*
- * Prepare footer for currently outgoing message, and finish things
- * off.  Assumes out_kvec* are already valid.. we just add on to the end.
- */
-static void prepare_write_message_footer(struct ceph_connection *con)
-{
-	struct ceph_msg *m = con->out_msg;
-
-	m->footer.flags |= CEPH_MSG_FOOTER_COMPLETE;
-
-	dout("prepare_write_message_footer %p\n", con);
-	con_out_kvec_add(con, sizeof_footer(con), &m->footer);
-	if (con->peer_features & CEPH_FEATURE_MSG_AUTH) {
-		if (con->ops->sign_message)
-			con->ops->sign_message(m);
-		else
-			m->footer.sig = 0;
-	} else {
-		m->old_footer.flags = m->footer.flags;
-	}
-	con->out_more = m->more_to_follow;
-	con->out_msg_done = true;
-}
-
-/*
- * Prepare headers for the next outgoing message.
- */
-static void prepare_write_message(struct ceph_connection *con)
-{
-	struct ceph_msg *m;
-	u32 crc;
-
-	con_out_kvec_reset(con);
-	con->out_msg_done = false;
-
-	/* Sneak an ack in there first?  If we can get it into the same
-	 * TCP packet that's a good thing. */
-	if (con->in_seq > con->in_seq_acked) {
-		con->in_seq_acked = con->in_seq;
-		con_out_kvec_add(con, sizeof (tag_ack), &tag_ack);
-		con->out_temp_ack = cpu_to_le64(con->in_seq_acked);
-		con_out_kvec_add(con, sizeof (con->out_temp_ack),
-			&con->out_temp_ack);
-	}
-
-	ceph_con_get_out_msg(con);
-	m = con->out_msg;
-
-	dout("prepare_write_message %p seq %lld type %d len %d+%d+%zd\n",
-	     m, con->out_seq, le16_to_cpu(m->hdr.type),
-	     le32_to_cpu(m->hdr.front_len), le32_to_cpu(m->hdr.middle_len),
-	     m->data_length);
-	WARN_ON(m->front.iov_len != le32_to_cpu(m->hdr.front_len));
-	WARN_ON(m->data_length != le32_to_cpu(m->hdr.data_len));
-
-	/* tag + hdr + front + middle */
-	con_out_kvec_add(con, sizeof (tag_msg), &tag_msg);
-	con_out_kvec_add(con, sizeof(con->out_hdr), &con->out_hdr);
-	con_out_kvec_add(con, m->front.iov_len, m->front.iov_base);
-
-	if (m->middle)
-		con_out_kvec_add(con, m->middle->vec.iov_len,
-			m->middle->vec.iov_base);
-
-	/* fill in hdr crc and finalize hdr */
-	crc = crc32c(0, &m->hdr, offsetof(struct ceph_msg_header, crc));
-	con->out_msg->hdr.crc = cpu_to_le32(crc);
-	memcpy(&con->out_hdr, &con->out_msg->hdr, sizeof(con->out_hdr));
-
-	/* fill in front and middle crc, footer */
-	crc = crc32c(0, m->front.iov_base, m->front.iov_len);
-	con->out_msg->footer.front_crc = cpu_to_le32(crc);
-	if (m->middle) {
-		crc = crc32c(0, m->middle->vec.iov_base,
-				m->middle->vec.iov_len);
-		con->out_msg->footer.middle_crc = cpu_to_le32(crc);
-	} else
-		con->out_msg->footer.middle_crc = 0;
-	dout("%s front_crc %u middle_crc %u\n", __func__,
-	     le32_to_cpu(con->out_msg->footer.front_crc),
-	     le32_to_cpu(con->out_msg->footer.middle_crc));
-	con->out_msg->footer.flags = 0;
-
-	/* is there a data payload? */
-	con->out_msg->footer.data_crc = 0;
-	if (m->data_length) {
-		prepare_message_data(con->out_msg, m->data_length);
-		con->out_more = 1;  /* data + footer will follow */
-	} else {
-		/* no, queue up footer too and be done */
-		prepare_write_message_footer(con);
-	}
-
-	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
-}
-
-/*
- * Prepare an ack.
- */
-static void prepare_write_ack(struct ceph_connection *con)
-{
-	dout("prepare_write_ack %p %llu -> %llu\n", con,
-	     con->in_seq_acked, con->in_seq);
-	con->in_seq_acked = con->in_seq;
-
-	con_out_kvec_reset(con);
-
-	con_out_kvec_add(con, sizeof (tag_ack), &tag_ack);
-
-	con->out_temp_ack = cpu_to_le64(con->in_seq_acked);
-	con_out_kvec_add(con, sizeof (con->out_temp_ack),
-				&con->out_temp_ack);
-
-	con->out_more = 1;  /* more will follow.. eventually.. */
-	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
-}
-
-/*
- * Prepare to share the seq during handshake
- */
-static void prepare_write_seq(struct ceph_connection *con)
-{
-	dout("prepare_write_seq %p %llu -> %llu\n", con,
-	     con->in_seq_acked, con->in_seq);
-	con->in_seq_acked = con->in_seq;
-
-	con_out_kvec_reset(con);
-
-	con->out_temp_ack = cpu_to_le64(con->in_seq_acked);
-	con_out_kvec_add(con, sizeof (con->out_temp_ack),
-			 &con->out_temp_ack);
-
-	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
-}
-
-/*
- * Prepare to write keepalive byte.
- */
-static void prepare_write_keepalive(struct ceph_connection *con)
-{
-	dout("prepare_write_keepalive %p\n", con);
-	con_out_kvec_reset(con);
-	if (con->peer_features & CEPH_FEATURE_MSGR_KEEPALIVE2) {
-		struct timespec64 now;
-
-		ktime_get_real_ts64(&now);
-		con_out_kvec_add(con, sizeof(tag_keepalive2), &tag_keepalive2);
-		ceph_encode_timespec64(&con->out_temp_keepalive2, &now);
-		con_out_kvec_add(con, sizeof(con->out_temp_keepalive2),
-				 &con->out_temp_keepalive2);
-	} else {
-		con_out_kvec_add(con, sizeof(tag_keepalive), &tag_keepalive);
-	}
-	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
-}
-
-/*
- * Connection negotiation.
- */
-
-static int get_connect_authorizer(struct ceph_connection *con)
-{
-	struct ceph_auth_handshake *auth;
-	int auth_proto;
-
-	if (!con->ops->get_authorizer) {
-		con->auth = NULL;
-		con->out_connect.authorizer_protocol = CEPH_AUTH_UNKNOWN;
-		con->out_connect.authorizer_len = 0;
-		return 0;
-	}
-
-	auth = con->ops->get_authorizer(con, &auth_proto, con->auth_retry);
-	if (IS_ERR(auth))
-		return PTR_ERR(auth);
-
-	con->auth = auth;
-	con->out_connect.authorizer_protocol = cpu_to_le32(auth_proto);
-	con->out_connect.authorizer_len = cpu_to_le32(auth->authorizer_buf_len);
-	return 0;
-}
-
-/*
- * We connected to a peer and are saying hello.
- */
-static void prepare_write_banner(struct ceph_connection *con)
-{
-	con_out_kvec_add(con, strlen(CEPH_BANNER), CEPH_BANNER);
-	con_out_kvec_add(con, sizeof (con->msgr->my_enc_addr),
-					&con->msgr->my_enc_addr);
-
-	con->out_more = 0;
-	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
-}
-
-static void __prepare_write_connect(struct ceph_connection *con)
-{
-	con_out_kvec_add(con, sizeof(con->out_connect), &con->out_connect);
-	if (con->auth)
-		con_out_kvec_add(con, con->auth->authorizer_buf_len,
-				 con->auth->authorizer_buf);
-
-	con->out_more = 0;
-	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
-}
-
-static int prepare_write_connect(struct ceph_connection *con)
-{
-	unsigned int global_seq = ceph_get_global_seq(con->msgr, 0);
-	int proto;
-	int ret;
-
-	switch (con->peer_name.type) {
-	case CEPH_ENTITY_TYPE_MON:
-		proto = CEPH_MONC_PROTOCOL;
-		break;
-	case CEPH_ENTITY_TYPE_OSD:
-		proto = CEPH_OSDC_PROTOCOL;
-		break;
-	case CEPH_ENTITY_TYPE_MDS:
-		proto = CEPH_MDSC_PROTOCOL;
-		break;
-	default:
-		BUG();
-	}
-
-	dout("prepare_write_connect %p cseq=%d gseq=%d proto=%d\n", con,
-	     con->connect_seq, global_seq, proto);
-
-	con->out_connect.features =
-	    cpu_to_le64(from_msgr(con->msgr)->supported_features);
-	con->out_connect.host_type = cpu_to_le32(CEPH_ENTITY_TYPE_CLIENT);
-	con->out_connect.connect_seq = cpu_to_le32(con->connect_seq);
-	con->out_connect.global_seq = cpu_to_le32(global_seq);
-	con->out_connect.protocol_version = cpu_to_le32(proto);
-	con->out_connect.flags = 0;
-
-	ret = get_connect_authorizer(con);
-	if (ret)
-		return ret;
-
-	__prepare_write_connect(con);
-	return 0;
-}
-
-/*
- * write as much of pending kvecs to the socket as we can.
- *  1 -> done
- *  0 -> socket full, but more to do
- * <0 -> error
- */
-static int write_partial_kvec(struct ceph_connection *con)
-{
-	int ret;
-
-	dout("write_partial_kvec %p %d left\n", con, con->out_kvec_bytes);
-	while (con->out_kvec_bytes > 0) {
-		ret = ceph_tcp_sendmsg(con->sock, con->out_kvec_cur,
-				       con->out_kvec_left, con->out_kvec_bytes,
-				       con->out_more);
-		if (ret <= 0)
-			goto out;
-		con->out_kvec_bytes -= ret;
-		if (con->out_kvec_bytes == 0)
-			break;            /* done */
-
-		/* account for full iov entries consumed */
-		while (ret >= con->out_kvec_cur->iov_len) {
-			BUG_ON(!con->out_kvec_left);
-			ret -= con->out_kvec_cur->iov_len;
-			con->out_kvec_cur++;
-			con->out_kvec_left--;
-		}
-		/* and for a partially-consumed entry */
-		if (ret) {
-			con->out_kvec_cur->iov_len -= ret;
-			con->out_kvec_cur->iov_base += ret;
-		}
-	}
-	con->out_kvec_left = 0;
-	ret = 1;
-out:
-	dout("write_partial_kvec %p %d left in %d kvecs ret = %d\n", con,
-	     con->out_kvec_bytes, con->out_kvec_left, ret);
-	return ret;  /* done! */
-}
-
 u32 ceph_crc32c_page(u32 crc, struct page *page, unsigned int page_offset,
 		     unsigned int length)
 {
@@ -1573,256 +1115,6 @@ u32 ceph_crc32c_page(u32 crc, struct page *page, unsigned int page_offset,
 
 	return crc;
 }
-/*
- * Write as much message data payload as we can.  If we finish, queue
- * up the footer.
- *  1 -> done, footer is now queued in out_kvec[].
- *  0 -> socket full, but more to do
- * <0 -> error
- */
-static int write_partial_message_data(struct ceph_connection *con)
-{
-	struct ceph_msg *msg = con->out_msg;
-	struct ceph_msg_data_cursor *cursor = &msg->cursor;
-	bool do_datacrc = !ceph_test_opt(from_msgr(con->msgr), NOCRC);
-	int more = MSG_MORE | MSG_SENDPAGE_NOTLAST;
-	u32 crc;
-
-	dout("%s %p msg %p\n", __func__, con, msg);
-
-	if (!msg->num_data_items)
-		return -EINVAL;
-
-	/*
-	 * Iterate through each page that contains data to be
-	 * written, and send as much as possible for each.
-	 *
-	 * If we are calculating the data crc (the default), we will
-	 * need to map the page.  If we have no pages, they have
-	 * been revoked, so use the zero page.
-	 */
-	crc = do_datacrc ? le32_to_cpu(msg->footer.data_crc) : 0;
-	while (cursor->total_resid) {
-		struct page *page;
-		size_t page_offset;
-		size_t length;
-		int ret;
-
-		if (!cursor->resid) {
-			ceph_msg_data_advance(cursor, 0);
-			continue;
-		}
-
-		page = ceph_msg_data_next(cursor, &page_offset, &length, NULL);
-		if (length == cursor->total_resid)
-			more = MSG_MORE;
-		ret = ceph_tcp_sendpage(con->sock, page, page_offset, length,
-					more);
-		if (ret <= 0) {
-			if (do_datacrc)
-				msg->footer.data_crc = cpu_to_le32(crc);
-
-			return ret;
-		}
-		if (do_datacrc && cursor->need_crc)
-			crc = ceph_crc32c_page(crc, page, page_offset, length);
-		ceph_msg_data_advance(cursor, (size_t)ret);
-	}
-
-	dout("%s %p msg %p done\n", __func__, con, msg);
-
-	/* prepare and queue up footer, too */
-	if (do_datacrc)
-		msg->footer.data_crc = cpu_to_le32(crc);
-	else
-		msg->footer.flags |= CEPH_MSG_FOOTER_NOCRC;
-	con_out_kvec_reset(con);
-	prepare_write_message_footer(con);
-
-	return 1;	/* must return > 0 to indicate success */
-}
-
-/*
- * write some zeros
- */
-static int write_partial_skip(struct ceph_connection *con)
-{
-	int more = MSG_MORE | MSG_SENDPAGE_NOTLAST;
-	int ret;
-
-	dout("%s %p %d left\n", __func__, con, con->out_skip);
-	while (con->out_skip > 0) {
-		size_t size = min(con->out_skip, (int) PAGE_SIZE);
-
-		if (size == con->out_skip)
-			more = MSG_MORE;
-		ret = ceph_tcp_sendpage(con->sock, ceph_zero_page, 0, size,
-					more);
-		if (ret <= 0)
-			goto out;
-		con->out_skip -= ret;
-	}
-	ret = 1;
-out:
-	return ret;
-}
-
-/*
- * Prepare to read connection handshake, or an ack.
- */
-static void prepare_read_banner(struct ceph_connection *con)
-{
-	dout("prepare_read_banner %p\n", con);
-	con->in_base_pos = 0;
-}
-
-static void prepare_read_connect(struct ceph_connection *con)
-{
-	dout("prepare_read_connect %p\n", con);
-	con->in_base_pos = 0;
-}
-
-static void prepare_read_ack(struct ceph_connection *con)
-{
-	dout("prepare_read_ack %p\n", con);
-	con->in_base_pos = 0;
-}
-
-static void prepare_read_seq(struct ceph_connection *con)
-{
-	dout("prepare_read_seq %p\n", con);
-	con->in_base_pos = 0;
-	con->in_tag = CEPH_MSGR_TAG_SEQ;
-}
-
-static void prepare_read_tag(struct ceph_connection *con)
-{
-	dout("prepare_read_tag %p\n", con);
-	con->in_base_pos = 0;
-	con->in_tag = CEPH_MSGR_TAG_READY;
-}
-
-static void prepare_read_keepalive_ack(struct ceph_connection *con)
-{
-	dout("prepare_read_keepalive_ack %p\n", con);
-	con->in_base_pos = 0;
-}
-
-/*
- * Prepare to read a message.
- */
-static int prepare_read_message(struct ceph_connection *con)
-{
-	dout("prepare_read_message %p\n", con);
-	BUG_ON(con->in_msg != NULL);
-	con->in_base_pos = 0;
-	con->in_front_crc = con->in_middle_crc = con->in_data_crc = 0;
-	return 0;
-}
-
-
-static int read_partial(struct ceph_connection *con,
-			int end, int size, void *object)
-{
-	while (con->in_base_pos < end) {
-		int left = end - con->in_base_pos;
-		int have = size - left;
-		int ret = ceph_tcp_recvmsg(con->sock, object + have, left);
-		if (ret <= 0)
-			return ret;
-		con->in_base_pos += ret;
-	}
-	return 1;
-}
-
-
-/*
- * Read all or part of the connect-side handshake on a new connection
- */
-static int read_partial_banner(struct ceph_connection *con)
-{
-	int size;
-	int end;
-	int ret;
-
-	dout("read_partial_banner %p at %d\n", con, con->in_base_pos);
-
-	/* peer's banner */
-	size = strlen(CEPH_BANNER);
-	end = size;
-	ret = read_partial(con, end, size, con->in_banner);
-	if (ret <= 0)
-		goto out;
-
-	size = sizeof (con->actual_peer_addr);
-	end += size;
-	ret = read_partial(con, end, size, &con->actual_peer_addr);
-	if (ret <= 0)
-		goto out;
-	ceph_decode_banner_addr(&con->actual_peer_addr);
-
-	size = sizeof (con->peer_addr_for_me);
-	end += size;
-	ret = read_partial(con, end, size, &con->peer_addr_for_me);
-	if (ret <= 0)
-		goto out;
-	ceph_decode_banner_addr(&con->peer_addr_for_me);
-
-out:
-	return ret;
-}
-
-static int read_partial_connect(struct ceph_connection *con)
-{
-	int size;
-	int end;
-	int ret;
-
-	dout("read_partial_connect %p at %d\n", con, con->in_base_pos);
-
-	size = sizeof (con->in_reply);
-	end = size;
-	ret = read_partial(con, end, size, &con->in_reply);
-	if (ret <= 0)
-		goto out;
-
-	if (con->auth) {
-		size = le32_to_cpu(con->in_reply.authorizer_len);
-		if (size > con->auth->authorizer_reply_buf_len) {
-			pr_err("authorizer reply too big: %d > %zu\n", size,
-			       con->auth->authorizer_reply_buf_len);
-			ret = -EINVAL;
-			goto out;
-		}
-
-		end += size;
-		ret = read_partial(con, end, size,
-				   con->auth->authorizer_reply_buf);
-		if (ret <= 0)
-			goto out;
-	}
-
-	dout("read_partial_connect %p tag %d, con_seq = %u, g_seq = %u\n",
-	     con, (int)con->in_reply.tag,
-	     le32_to_cpu(con->in_reply.connect_seq),
-	     le32_to_cpu(con->in_reply.global_seq));
-out:
-	return ret;
-}
-
-/*
- * Verify the hello banner looks okay.
- */
-static int verify_hello(struct ceph_connection *con)
-{
-	if (memcmp(con->in_banner, CEPH_BANNER, strlen(CEPH_BANNER))) {
-		pr_err("connect to %s got bad banner\n",
-		       ceph_pr_addr(&con->peer_addr));
-		con->error_msg = "protocol error, bad banner";
-		return -1;
-	}
-	return 0;
-}
 
 bool ceph_addr_is_blank(const struct ceph_entity_addr *addr)
 {
@@ -2032,492 +1324,6 @@ bad:
 	return ret;
 }
 
-static int process_banner(struct ceph_connection *con)
-{
-	struct ceph_entity_addr *my_addr = &con->msgr->inst.addr;
-
-	dout("process_banner on %p\n", con);
-
-	if (verify_hello(con) < 0)
-		return -1;
-
-	/*
-	 * Make sure the other end is who we wanted.  note that the other
-	 * end may not yet know their ip address, so if it's 0.0.0.0, give
-	 * them the benefit of the doubt.
-	 */
-	if (memcmp(&con->peer_addr, &con->actual_peer_addr,
-		   sizeof(con->peer_addr)) != 0 &&
-	    !(ceph_addr_is_blank(&con->actual_peer_addr) &&
-	      con->actual_peer_addr.nonce == con->peer_addr.nonce)) {
-		pr_warn("wrong peer, want %s/%u, got %s/%u\n",
-			ceph_pr_addr(&con->peer_addr),
-			le32_to_cpu(con->peer_addr.nonce),
-			ceph_pr_addr(&con->actual_peer_addr),
-			le32_to_cpu(con->actual_peer_addr.nonce));
-		con->error_msg = "wrong peer at address";
-		return -1;
-	}
-
-	/*
-	 * did we learn our address?
-	 */
-	if (ceph_addr_is_blank(my_addr)) {
-		memcpy(&my_addr->in_addr,
-		       &con->peer_addr_for_me.in_addr,
-		       sizeof(con->peer_addr_for_me.in_addr));
-		ceph_addr_set_port(my_addr, 0);
-		ceph_encode_my_addr(con->msgr);
-		dout("process_banner learned my addr is %s\n",
-		     ceph_pr_addr(my_addr));
-	}
-
-	return 0;
-}
-
-static int process_connect(struct ceph_connection *con)
-{
-	u64 sup_feat = from_msgr(con->msgr)->supported_features;
-	u64 req_feat = from_msgr(con->msgr)->required_features;
-	u64 server_feat = le64_to_cpu(con->in_reply.features);
-	int ret;
-
-	dout("process_connect on %p tag %d\n", con, (int)con->in_tag);
-
-	if (con->auth) {
-		int len = le32_to_cpu(con->in_reply.authorizer_len);
-
-		/*
-		 * Any connection that defines ->get_authorizer()
-		 * should also define ->add_authorizer_challenge() and
-		 * ->verify_authorizer_reply().
-		 *
-		 * See get_connect_authorizer().
-		 */
-		if (con->in_reply.tag == CEPH_MSGR_TAG_CHALLENGE_AUTHORIZER) {
-			ret = con->ops->add_authorizer_challenge(
-				    con, con->auth->authorizer_reply_buf, len);
-			if (ret < 0)
-				return ret;
-
-			con_out_kvec_reset(con);
-			__prepare_write_connect(con);
-			prepare_read_connect(con);
-			return 0;
-		}
-
-		if (len) {
-			ret = con->ops->verify_authorizer_reply(con);
-			if (ret < 0) {
-				con->error_msg = "bad authorize reply";
-				return ret;
-			}
-		}
-	}
-
-	switch (con->in_reply.tag) {
-	case CEPH_MSGR_TAG_FEATURES:
-		pr_err("%s%lld %s feature set mismatch,"
-		       " my %llx < server's %llx, missing %llx\n",
-		       ENTITY_NAME(con->peer_name),
-		       ceph_pr_addr(&con->peer_addr),
-		       sup_feat, server_feat, server_feat & ~sup_feat);
-		con->error_msg = "missing required protocol features";
-		return -1;
-
-	case CEPH_MSGR_TAG_BADPROTOVER:
-		pr_err("%s%lld %s protocol version mismatch,"
-		       " my %d != server's %d\n",
-		       ENTITY_NAME(con->peer_name),
-		       ceph_pr_addr(&con->peer_addr),
-		       le32_to_cpu(con->out_connect.protocol_version),
-		       le32_to_cpu(con->in_reply.protocol_version));
-		con->error_msg = "protocol version mismatch";
-		return -1;
-
-	case CEPH_MSGR_TAG_BADAUTHORIZER:
-		con->auth_retry++;
-		dout("process_connect %p got BADAUTHORIZER attempt %d\n", con,
-		     con->auth_retry);
-		if (con->auth_retry == 2) {
-			con->error_msg = "connect authorization failure";
-			return -1;
-		}
-		con_out_kvec_reset(con);
-		ret = prepare_write_connect(con);
-		if (ret < 0)
-			return ret;
-		prepare_read_connect(con);
-		break;
-
-	case CEPH_MSGR_TAG_RESETSESSION:
-		/*
-		 * If we connected with a large connect_seq but the peer
-		 * has no record of a session with us (no connection, or
-		 * connect_seq == 0), they will send RESETSESION to indicate
-		 * that they must have reset their session, and may have
-		 * dropped messages.
-		 */
-		dout("process_connect got RESET peer seq %u\n",
-		     le32_to_cpu(con->in_reply.connect_seq));
-		pr_info("%s%lld %s session reset\n",
-			ENTITY_NAME(con->peer_name),
-			ceph_pr_addr(&con->peer_addr));
-		ceph_con_reset_session(con);
-		con_out_kvec_reset(con);
-		ret = prepare_write_connect(con);
-		if (ret < 0)
-			return ret;
-		prepare_read_connect(con);
-
-		/* Tell ceph about it. */
-		mutex_unlock(&con->mutex);
-		if (con->ops->peer_reset)
-			con->ops->peer_reset(con);
-		mutex_lock(&con->mutex);
-		if (con->state != CEPH_CON_S_V1_CONNECT_MSG)
-			return -EAGAIN;
-		break;
-
-	case CEPH_MSGR_TAG_RETRY_SESSION:
-		/*
-		 * If we sent a smaller connect_seq than the peer has, try
-		 * again with a larger value.
-		 */
-		dout("process_connect got RETRY_SESSION my seq %u, peer %u\n",
-		     le32_to_cpu(con->out_connect.connect_seq),
-		     le32_to_cpu(con->in_reply.connect_seq));
-		con->connect_seq = le32_to_cpu(con->in_reply.connect_seq);
-		con_out_kvec_reset(con);
-		ret = prepare_write_connect(con);
-		if (ret < 0)
-			return ret;
-		prepare_read_connect(con);
-		break;
-
-	case CEPH_MSGR_TAG_RETRY_GLOBAL:
-		/*
-		 * If we sent a smaller global_seq than the peer has, try
-		 * again with a larger value.
-		 */
-		dout("process_connect got RETRY_GLOBAL my %u peer_gseq %u\n",
-		     con->peer_global_seq,
-		     le32_to_cpu(con->in_reply.global_seq));
-		ceph_get_global_seq(con->msgr,
-				    le32_to_cpu(con->in_reply.global_seq));
-		con_out_kvec_reset(con);
-		ret = prepare_write_connect(con);
-		if (ret < 0)
-			return ret;
-		prepare_read_connect(con);
-		break;
-
-	case CEPH_MSGR_TAG_SEQ:
-	case CEPH_MSGR_TAG_READY:
-		if (req_feat & ~server_feat) {
-			pr_err("%s%lld %s protocol feature mismatch,"
-			       " my required %llx > server's %llx, need %llx\n",
-			       ENTITY_NAME(con->peer_name),
-			       ceph_pr_addr(&con->peer_addr),
-			       req_feat, server_feat, req_feat & ~server_feat);
-			con->error_msg = "missing required protocol features";
-			return -1;
-		}
-
-		WARN_ON(con->state != CEPH_CON_S_V1_CONNECT_MSG);
-		con->state = CEPH_CON_S_OPEN;
-		con->auth_retry = 0;    /* we authenticated; clear flag */
-		con->peer_global_seq = le32_to_cpu(con->in_reply.global_seq);
-		con->connect_seq++;
-		con->peer_features = server_feat;
-		dout("process_connect got READY gseq %d cseq %d (%d)\n",
-		     con->peer_global_seq,
-		     le32_to_cpu(con->in_reply.connect_seq),
-		     con->connect_seq);
-		WARN_ON(con->connect_seq !=
-			le32_to_cpu(con->in_reply.connect_seq));
-
-		if (con->in_reply.flags & CEPH_MSG_CONNECT_LOSSY)
-			ceph_con_flag_set(con, CEPH_CON_F_LOSSYTX);
-
-		con->delay = 0;      /* reset backoff memory */
-
-		if (con->in_reply.tag == CEPH_MSGR_TAG_SEQ) {
-			prepare_write_seq(con);
-			prepare_read_seq(con);
-		} else {
-			prepare_read_tag(con);
-		}
-		break;
-
-	case CEPH_MSGR_TAG_WAIT:
-		/*
-		 * If there is a connection race (we are opening
-		 * connections to each other), one of us may just have
-		 * to WAIT.  This shouldn't happen if we are the
-		 * client.
-		 */
-		con->error_msg = "protocol error, got WAIT as client";
-		return -1;
-
-	default:
-		con->error_msg = "protocol error, garbage tag during connect";
-		return -1;
-	}
-	return 0;
-}
-
-
-/*
- * read (part of) an ack
- */
-static int read_partial_ack(struct ceph_connection *con)
-{
-	int size = sizeof (con->in_temp_ack);
-	int end = size;
-
-	return read_partial(con, end, size, &con->in_temp_ack);
-}
-
-/*
- * We can finally discard anything that's been acked.
- */
-static void process_ack(struct ceph_connection *con)
-{
-	u64 ack = le64_to_cpu(con->in_temp_ack);
-
-	if (con->in_tag == CEPH_MSGR_TAG_ACK)
-		ceph_con_discard_sent(con, ack);
-	else
-		ceph_con_discard_requeued(con, ack);
-
-	prepare_read_tag(con);
-}
-
-
-static int read_partial_message_section(struct ceph_connection *con,
-					struct kvec *section,
-					unsigned int sec_len, u32 *crc)
-{
-	int ret, left;
-
-	BUG_ON(!section);
-
-	while (section->iov_len < sec_len) {
-		BUG_ON(section->iov_base == NULL);
-		left = sec_len - section->iov_len;
-		ret = ceph_tcp_recvmsg(con->sock, (char *)section->iov_base +
-				       section->iov_len, left);
-		if (ret <= 0)
-			return ret;
-		section->iov_len += ret;
-	}
-	if (section->iov_len == sec_len)
-		*crc = crc32c(0, section->iov_base, section->iov_len);
-
-	return 1;
-}
-
-static int read_partial_msg_data(struct ceph_connection *con)
-{
-	struct ceph_msg *msg = con->in_msg;
-	struct ceph_msg_data_cursor *cursor = &msg->cursor;
-	bool do_datacrc = !ceph_test_opt(from_msgr(con->msgr), NOCRC);
-	struct page *page;
-	size_t page_offset;
-	size_t length;
-	u32 crc = 0;
-	int ret;
-
-	if (!msg->num_data_items)
-		return -EIO;
-
-	if (do_datacrc)
-		crc = con->in_data_crc;
-	while (cursor->total_resid) {
-		if (!cursor->resid) {
-			ceph_msg_data_advance(cursor, 0);
-			continue;
-		}
-
-		page = ceph_msg_data_next(cursor, &page_offset, &length, NULL);
-		ret = ceph_tcp_recvpage(con->sock, page, page_offset, length);
-		if (ret <= 0) {
-			if (do_datacrc)
-				con->in_data_crc = crc;
-
-			return ret;
-		}
-
-		if (do_datacrc)
-			crc = ceph_crc32c_page(crc, page, page_offset, ret);
-		ceph_msg_data_advance(cursor, (size_t)ret);
-	}
-	if (do_datacrc)
-		con->in_data_crc = crc;
-
-	return 1;	/* must return > 0 to indicate success */
-}
-
-/*
- * read (part of) a message.
- */
-static int read_partial_message(struct ceph_connection *con)
-{
-	struct ceph_msg *m = con->in_msg;
-	int size;
-	int end;
-	int ret;
-	unsigned int front_len, middle_len, data_len;
-	bool do_datacrc = !ceph_test_opt(from_msgr(con->msgr), NOCRC);
-	bool need_sign = (con->peer_features & CEPH_FEATURE_MSG_AUTH);
-	u64 seq;
-	u32 crc;
-
-	dout("read_partial_message con %p msg %p\n", con, m);
-
-	/* header */
-	size = sizeof (con->in_hdr);
-	end = size;
-	ret = read_partial(con, end, size, &con->in_hdr);
-	if (ret <= 0)
-		return ret;
-
-	crc = crc32c(0, &con->in_hdr, offsetof(struct ceph_msg_header, crc));
-	if (cpu_to_le32(crc) != con->in_hdr.crc) {
-		pr_err("read_partial_message bad hdr crc %u != expected %u\n",
-		       crc, con->in_hdr.crc);
-		return -EBADMSG;
-	}
-
-	front_len = le32_to_cpu(con->in_hdr.front_len);
-	if (front_len > CEPH_MSG_MAX_FRONT_LEN)
-		return -EIO;
-	middle_len = le32_to_cpu(con->in_hdr.middle_len);
-	if (middle_len > CEPH_MSG_MAX_MIDDLE_LEN)
-		return -EIO;
-	data_len = le32_to_cpu(con->in_hdr.data_len);
-	if (data_len > CEPH_MSG_MAX_DATA_LEN)
-		return -EIO;
-
-	/* verify seq# */
-	seq = le64_to_cpu(con->in_hdr.seq);
-	if ((s64)seq - (s64)con->in_seq < 1) {
-		pr_info("skipping %s%lld %s seq %lld expected %lld\n",
-			ENTITY_NAME(con->peer_name),
-			ceph_pr_addr(&con->peer_addr),
-			seq, con->in_seq + 1);
-		con->in_base_pos = -front_len - middle_len - data_len -
-			sizeof_footer(con);
-		con->in_tag = CEPH_MSGR_TAG_READY;
-		return 1;
-	} else if ((s64)seq - (s64)con->in_seq > 1) {
-		pr_err("read_partial_message bad seq %lld expected %lld\n",
-		       seq, con->in_seq + 1);
-		con->error_msg = "bad message sequence # for incoming message";
-		return -EBADE;
-	}
-
-	/* allocate message? */
-	if (!con->in_msg) {
-		int skip = 0;
-
-		dout("got hdr type %d front %d data %d\n", con->in_hdr.type,
-		     front_len, data_len);
-		ret = ceph_con_in_msg_alloc(con, &con->in_hdr, &skip);
-		if (ret < 0)
-			return ret;
-
-		BUG_ON(!con->in_msg ^ skip);
-		if (skip) {
-			/* skip this message */
-			dout("alloc_msg said skip message\n");
-			con->in_base_pos = -front_len - middle_len - data_len -
-				sizeof_footer(con);
-			con->in_tag = CEPH_MSGR_TAG_READY;
-			con->in_seq++;
-			return 1;
-		}
-
-		BUG_ON(!con->in_msg);
-		BUG_ON(con->in_msg->con != con);
-		m = con->in_msg;
-		m->front.iov_len = 0;    /* haven't read it yet */
-		if (m->middle)
-			m->middle->vec.iov_len = 0;
-
-		/* prepare for data payload, if any */
-
-		if (data_len)
-			prepare_message_data(con->in_msg, data_len);
-	}
-
-	/* front */
-	ret = read_partial_message_section(con, &m->front, front_len,
-					   &con->in_front_crc);
-	if (ret <= 0)
-		return ret;
-
-	/* middle */
-	if (m->middle) {
-		ret = read_partial_message_section(con, &m->middle->vec,
-						   middle_len,
-						   &con->in_middle_crc);
-		if (ret <= 0)
-			return ret;
-	}
-
-	/* (page) data */
-	if (data_len) {
-		ret = read_partial_msg_data(con);
-		if (ret <= 0)
-			return ret;
-	}
-
-	/* footer */
-	size = sizeof_footer(con);
-	end += size;
-	ret = read_partial(con, end, size, &m->footer);
-	if (ret <= 0)
-		return ret;
-
-	if (!need_sign) {
-		m->footer.flags = m->old_footer.flags;
-		m->footer.sig = 0;
-	}
-
-	dout("read_partial_message got msg %p %d (%u) + %d (%u) + %d (%u)\n",
-	     m, front_len, m->footer.front_crc, middle_len,
-	     m->footer.middle_crc, data_len, m->footer.data_crc);
-
-	/* crc ok? */
-	if (con->in_front_crc != le32_to_cpu(m->footer.front_crc)) {
-		pr_err("read_partial_message %p front crc %u != exp. %u\n",
-		       m, con->in_front_crc, m->footer.front_crc);
-		return -EBADMSG;
-	}
-	if (con->in_middle_crc != le32_to_cpu(m->footer.middle_crc)) {
-		pr_err("read_partial_message %p middle crc %u != exp %u\n",
-		       m, con->in_middle_crc, m->footer.middle_crc);
-		return -EBADMSG;
-	}
-	if (do_datacrc &&
-	    (m->footer.flags & CEPH_MSG_FOOTER_NOCRC) == 0 &&
-	    con->in_data_crc != le32_to_cpu(m->footer.data_crc)) {
-		pr_err("read_partial_message %p data crc %u != exp. %u\n", m,
-		       con->in_data_crc, le32_to_cpu(m->footer.data_crc));
-		return -EBADMSG;
-	}
-
-	if (need_sign && con->ops->check_message_signature &&
-	    con->ops->check_message_signature(m)) {
-		pr_err("read_partial_message %p signature check failed\n", m);
-		return -EBADMSG;
-	}
-
-	return 1; /* done! */
-}
-
 /*
  * Process message.  This happens in the worker thread.  The callback should
  * be careful not to do anything that waits on other incoming messages or it
@@ -2551,263 +1357,6 @@ void ceph_con_process_message(struct ceph_connection *con)
 	mutex_lock(&con->mutex);
 }
 
-static int read_keepalive_ack(struct ceph_connection *con)
-{
-	struct ceph_timespec ceph_ts;
-	size_t size = sizeof(ceph_ts);
-	int ret = read_partial(con, size, size, &ceph_ts);
-	if (ret <= 0)
-		return ret;
-	ceph_decode_timespec64(&con->last_keepalive_ack, &ceph_ts);
-	prepare_read_tag(con);
-	return 1;
-}
-
-/*
- * Write something to the socket.  Called in a worker thread when the
- * socket appears to be writeable and we have something ready to send.
- */
-int ceph_con_v1_try_write(struct ceph_connection *con)
-{
-	int ret = 1;
-
-	dout("try_write start %p state %d\n", con, con->state);
-	if (con->state != CEPH_CON_S_PREOPEN &&
-	    con->state != CEPH_CON_S_V1_BANNER &&
-	    con->state != CEPH_CON_S_V1_CONNECT_MSG &&
-	    con->state != CEPH_CON_S_OPEN)
-		return 0;
-
-	/* open the socket first? */
-	if (con->state == CEPH_CON_S_PREOPEN) {
-		BUG_ON(con->sock);
-		con->state = CEPH_CON_S_V1_BANNER;
-
-		con_out_kvec_reset(con);
-		prepare_write_banner(con);
-		prepare_read_banner(con);
-
-		BUG_ON(con->in_msg);
-		con->in_tag = CEPH_MSGR_TAG_READY;
-		dout("try_write initiating connect on %p new state %d\n",
-		     con, con->state);
-		ret = ceph_tcp_connect(con);
-		if (ret < 0) {
-			con->error_msg = "connect error";
-			goto out;
-		}
-	}
-
-more:
-	dout("try_write out_kvec_bytes %d\n", con->out_kvec_bytes);
-	BUG_ON(!con->sock);
-
-	/* kvec data queued? */
-	if (con->out_kvec_left) {
-		ret = write_partial_kvec(con);
-		if (ret <= 0)
-			goto out;
-	}
-	if (con->out_skip) {
-		ret = write_partial_skip(con);
-		if (ret <= 0)
-			goto out;
-	}
-
-	/* msg pages? */
-	if (con->out_msg) {
-		if (con->out_msg_done) {
-			ceph_msg_put(con->out_msg);
-			con->out_msg = NULL;   /* we're done with this one */
-			goto do_next;
-		}
-
-		ret = write_partial_message_data(con);
-		if (ret == 1)
-			goto more;  /* we need to send the footer, too! */
-		if (ret == 0)
-			goto out;
-		if (ret < 0) {
-			dout("try_write write_partial_message_data err %d\n",
-			     ret);
-			goto out;
-		}
-	}
-
-do_next:
-	if (con->state == CEPH_CON_S_OPEN) {
-		if (ceph_con_flag_test_and_clear(con,
-				CEPH_CON_F_KEEPALIVE_PENDING)) {
-			prepare_write_keepalive(con);
-			goto more;
-		}
-		/* is anything else pending? */
-		if (!list_empty(&con->out_queue)) {
-			prepare_write_message(con);
-			goto more;
-		}
-		if (con->in_seq > con->in_seq_acked) {
-			prepare_write_ack(con);
-			goto more;
-		}
-	}
-
-	/* Nothing to do! */
-	ceph_con_flag_clear(con, CEPH_CON_F_WRITE_PENDING);
-	dout("try_write nothing else to write.\n");
-	ret = 0;
-out:
-	dout("try_write done on %p ret %d\n", con, ret);
-	return ret;
-}
-
-/*
- * Read what we can from the socket.
- */
-int ceph_con_v1_try_read(struct ceph_connection *con)
-{
-	int ret = -1;
-
-more:
-	dout("try_read start %p state %d\n", con, con->state);
-	if (con->state != CEPH_CON_S_V1_BANNER &&
-	    con->state != CEPH_CON_S_V1_CONNECT_MSG &&
-	    con->state != CEPH_CON_S_OPEN)
-		return 0;
-
-	BUG_ON(!con->sock);
-
-	dout("try_read tag %d in_base_pos %d\n", (int)con->in_tag,
-	     con->in_base_pos);
-
-	if (con->state == CEPH_CON_S_V1_BANNER) {
-		ret = read_partial_banner(con);
-		if (ret <= 0)
-			goto out;
-		ret = process_banner(con);
-		if (ret < 0)
-			goto out;
-
-		con->state = CEPH_CON_S_V1_CONNECT_MSG;
-
-		/*
-		 * Received banner is good, exchange connection info.
-		 * Do not reset out_kvec, as sending our banner raced
-		 * with receiving peer banner after connect completed.
-		 */
-		ret = prepare_write_connect(con);
-		if (ret < 0)
-			goto out;
-		prepare_read_connect(con);
-
-		/* Send connection info before awaiting response */
-		goto out;
-	}
-
-	if (con->state == CEPH_CON_S_V1_CONNECT_MSG) {
-		ret = read_partial_connect(con);
-		if (ret <= 0)
-			goto out;
-		ret = process_connect(con);
-		if (ret < 0)
-			goto out;
-		goto more;
-	}
-
-	WARN_ON(con->state != CEPH_CON_S_OPEN);
-
-	if (con->in_base_pos < 0) {
-		/*
-		 * skipping + discarding content.
-		 */
-		ret = ceph_tcp_recvmsg(con->sock, NULL, -con->in_base_pos);
-		if (ret <= 0)
-			goto out;
-		dout("skipped %d / %d bytes\n", ret, -con->in_base_pos);
-		con->in_base_pos += ret;
-		if (con->in_base_pos)
-			goto more;
-	}
-	if (con->in_tag == CEPH_MSGR_TAG_READY) {
-		/*
-		 * what's next?
-		 */
-		ret = ceph_tcp_recvmsg(con->sock, &con->in_tag, 1);
-		if (ret <= 0)
-			goto out;
-		dout("try_read got tag %d\n", (int)con->in_tag);
-		switch (con->in_tag) {
-		case CEPH_MSGR_TAG_MSG:
-			prepare_read_message(con);
-			break;
-		case CEPH_MSGR_TAG_ACK:
-			prepare_read_ack(con);
-			break;
-		case CEPH_MSGR_TAG_KEEPALIVE2_ACK:
-			prepare_read_keepalive_ack(con);
-			break;
-		case CEPH_MSGR_TAG_CLOSE:
-			ceph_con_close_socket(con);
-			con->state = CEPH_CON_S_CLOSED;
-			goto out;
-		default:
-			goto bad_tag;
-		}
-	}
-	if (con->in_tag == CEPH_MSGR_TAG_MSG) {
-		ret = read_partial_message(con);
-		if (ret <= 0) {
-			switch (ret) {
-			case -EBADMSG:
-				con->error_msg = "bad crc/signature";
-				fallthrough;
-			case -EBADE:
-				ret = -EIO;
-				break;
-			case -EIO:
-				con->error_msg = "io error";
-				break;
-			}
-			goto out;
-		}
-		if (con->in_tag == CEPH_MSGR_TAG_READY)
-			goto more;
-		ceph_con_process_message(con);
-		if (con->state == CEPH_CON_S_OPEN)
-			prepare_read_tag(con);
-		goto more;
-	}
-	if (con->in_tag == CEPH_MSGR_TAG_ACK ||
-	    con->in_tag == CEPH_MSGR_TAG_SEQ) {
-		/*
-		 * the final handshake seq exchange is semantically
-		 * equivalent to an ACK
-		 */
-		ret = read_partial_ack(con);
-		if (ret <= 0)
-			goto out;
-		process_ack(con);
-		goto more;
-	}
-	if (con->in_tag == CEPH_MSGR_TAG_KEEPALIVE2_ACK) {
-		ret = read_keepalive_ack(con);
-		if (ret <= 0)
-			goto out;
-		goto more;
-	}
-
-out:
-	dout("try_read done on %p ret %d\n", con, ret);
-	return ret;
-
-bad_tag:
-	pr_err("try_read bad con->in_tag = %d\n", (int)con->in_tag);
-	con->error_msg = "protocol error, garbage tag";
-	ret = -1;
-	goto out;
-}
-
-
 /*
  * Atomically queue work on a connection after the specified delay.
  * Bump @con reference to avoid races with connection teardown.
@@ -3026,7 +1575,6 @@ static void con_fault(struct ceph_connection *con)
 	}
 }
 
-
 void ceph_messenger_reset_nonce(struct ceph_messenger *msgr)
 {
 	u32 nonce = le32_to_cpu(msgr->inst.addr.nonce) + 1000000;
@@ -3131,29 +1679,6 @@ void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg)
 }
 EXPORT_SYMBOL(ceph_con_send);
 
-void ceph_con_v1_revoke(struct ceph_connection *con)
-{
-	struct ceph_msg *msg = con->out_msg;
-
-	WARN_ON(con->out_skip);
-	/* footer */
-	if (con->out_msg_done) {
-		con->out_skip += con_out_kvec_skip(con);
-	} else {
-		WARN_ON(!msg->data_length);
-		con->out_skip += sizeof_footer(con);
-	}
-	/* data, middle, front */
-	if (msg->data_length)
-		con->out_skip += msg->cursor.total_resid;
-	if (msg->middle)
-		con->out_skip += con_out_kvec_skip(con);
-	con->out_skip += con_out_kvec_skip(con);
-
-	dout("%s con %p out_kvec_bytes %d out_skip %d\n", __func__, con,
-	     con->out_kvec_bytes, con->out_skip);
-}
-
 /*
  * Revoke a message that was previously queued for send
  */
@@ -3191,26 +1716,6 @@ void ceph_msg_revoke(struct ceph_msg *msg)
 	mutex_unlock(&con->mutex);
 }
 
-void ceph_con_v1_revoke_incoming(struct ceph_connection *con)
-{
-	unsigned int front_len = le32_to_cpu(con->in_hdr.front_len);
-	unsigned int middle_len = le32_to_cpu(con->in_hdr.middle_len);
-	unsigned int data_len = le32_to_cpu(con->in_hdr.data_len);
-
-	/* skip rest of message */
-	con->in_base_pos = con->in_base_pos -
-			sizeof(struct ceph_msg_header) -
-			front_len -
-			middle_len -
-			data_len -
-			sizeof(struct ceph_msg_footer);
-
-	con->in_tag = CEPH_MSGR_TAG_READY;
-	con->in_seq++;
-
-	dout("%s con %p in_base_pos %d\n", __func__, con, con->in_base_pos);
-}
-
 /*
  * Revoke a message that we may be reading data into
  */
diff --git a/net/ceph/messenger_v1.c b/net/ceph/messenger_v1.c
new file mode 100644
index 000000000000..899038a9678e
--- /dev/null
+++ b/net/ceph/messenger_v1.c
@@ -0,0 +1,1502 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/bvec.h>
+#include <linux/crc32c.h>
+#include <linux/net.h>
+#include <linux/socket.h>
+#include <net/sock.h>
+
+#include <linux/ceph/ceph_features.h>
+#include <linux/ceph/decode.h>
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/messenger.h>
+
+/* static tag bytes (protocol control messages) */
+static char tag_msg = CEPH_MSGR_TAG_MSG;
+static char tag_ack = CEPH_MSGR_TAG_ACK;
+static char tag_keepalive = CEPH_MSGR_TAG_KEEPALIVE;
+static char tag_keepalive2 = CEPH_MSGR_TAG_KEEPALIVE2;
+
+/*
+ * If @buf is NULL, discard up to @len bytes.
+ */
+static int ceph_tcp_recvmsg(struct socket *sock, void *buf, size_t len)
+{
+	struct kvec iov = {buf, len};
+	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL };
+	int r;
+
+	if (!buf)
+		msg.msg_flags |= MSG_TRUNC;
+
+	iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, len);
+	r = sock_recvmsg(sock, &msg, msg.msg_flags);
+	if (r == -EAGAIN)
+		r = 0;
+	return r;
+}
+
+static int ceph_tcp_recvpage(struct socket *sock, struct page *page,
+		     int page_offset, size_t length)
+{
+	struct bio_vec bvec = {
+		.bv_page = page,
+		.bv_offset = page_offset,
+		.bv_len = length
+	};
+	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL };
+	int r;
+
+	BUG_ON(page_offset + length > PAGE_SIZE);
+	iov_iter_bvec(&msg.msg_iter, READ, &bvec, 1, length);
+	r = sock_recvmsg(sock, &msg, msg.msg_flags);
+	if (r == -EAGAIN)
+		r = 0;
+	return r;
+}
+
+/*
+ * write something.  @more is true if caller will be sending more data
+ * shortly.
+ */
+static int ceph_tcp_sendmsg(struct socket *sock, struct kvec *iov,
+			    size_t kvlen, size_t len, bool more)
+{
+	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL };
+	int r;
+
+	if (more)
+		msg.msg_flags |= MSG_MORE;
+	else
+		msg.msg_flags |= MSG_EOR;  /* superfluous, but what the hell */
+
+	r = kernel_sendmsg(sock, &msg, iov, kvlen, len);
+	if (r == -EAGAIN)
+		r = 0;
+	return r;
+}
+
+/*
+ * @more: either or both of MSG_MORE and MSG_SENDPAGE_NOTLAST
+ */
+static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
+			     int offset, size_t size, int more)
+{
+	ssize_t (*sendpage)(struct socket *sock, struct page *page,
+			    int offset, size_t size, int flags);
+	int flags = MSG_DONTWAIT | MSG_NOSIGNAL | more;
+	int ret;
+
+	/*
+	 * sendpage cannot properly handle pages with page_count == 0,
+	 * we need to fall back to sendmsg if that's the case.
+	 *
+	 * Same goes for slab pages: skb_can_coalesce() allows
+	 * coalescing neighboring slab objects into a single frag which
+	 * triggers one of hardened usercopy checks.
+	 */
+	if (sendpage_ok(page))
+		sendpage = sock->ops->sendpage;
+	else
+		sendpage = sock_no_sendpage;
+
+	ret = sendpage(sock, page, offset, size, flags);
+	if (ret == -EAGAIN)
+		ret = 0;
+
+	return ret;
+}
+
+static void con_out_kvec_reset(struct ceph_connection *con)
+{
+	BUG_ON(con->out_skip);
+
+	con->out_kvec_left = 0;
+	con->out_kvec_bytes = 0;
+	con->out_kvec_cur = &con->out_kvec[0];
+}
+
+static void con_out_kvec_add(struct ceph_connection *con,
+				size_t size, void *data)
+{
+	int index = con->out_kvec_left;
+
+	BUG_ON(con->out_skip);
+	BUG_ON(index >= ARRAY_SIZE(con->out_kvec));
+
+	con->out_kvec[index].iov_len = size;
+	con->out_kvec[index].iov_base = data;
+	con->out_kvec_left++;
+	con->out_kvec_bytes += size;
+}
+
+/*
+ * Chop off a kvec from the end.  Return residual number of bytes for
+ * that kvec, i.e. how many bytes would have been written if the kvec
+ * hadn't been nuked.
+ */
+static int con_out_kvec_skip(struct ceph_connection *con)
+{
+	int off = con->out_kvec_cur - con->out_kvec;
+	int skip = 0;
+
+	if (con->out_kvec_bytes > 0) {
+		skip = con->out_kvec[off + con->out_kvec_left - 1].iov_len;
+		BUG_ON(con->out_kvec_bytes < skip);
+		BUG_ON(!con->out_kvec_left);
+		con->out_kvec_bytes -= skip;
+		con->out_kvec_left--;
+	}
+
+	return skip;
+}
+
+static size_t sizeof_footer(struct ceph_connection *con)
+{
+	return (con->peer_features & CEPH_FEATURE_MSG_AUTH) ?
+	    sizeof(struct ceph_msg_footer) :
+	    sizeof(struct ceph_msg_footer_old);
+}
+
+static void prepare_message_data(struct ceph_msg *msg, u32 data_len)
+{
+	/* Initialize data cursor */
+
+	ceph_msg_data_cursor_init(&msg->cursor, msg, data_len);
+}
+
+/*
+ * Prepare footer for currently outgoing message, and finish things
+ * off.  Assumes out_kvec* are already valid.. we just add on to the end.
+ */
+static void prepare_write_message_footer(struct ceph_connection *con)
+{
+	struct ceph_msg *m = con->out_msg;
+
+	m->footer.flags |= CEPH_MSG_FOOTER_COMPLETE;
+
+	dout("prepare_write_message_footer %p\n", con);
+	con_out_kvec_add(con, sizeof_footer(con), &m->footer);
+	if (con->peer_features & CEPH_FEATURE_MSG_AUTH) {
+		if (con->ops->sign_message)
+			con->ops->sign_message(m);
+		else
+			m->footer.sig = 0;
+	} else {
+		m->old_footer.flags = m->footer.flags;
+	}
+	con->out_more = m->more_to_follow;
+	con->out_msg_done = true;
+}
+
+/*
+ * Prepare headers for the next outgoing message.
+ */
+static void prepare_write_message(struct ceph_connection *con)
+{
+	struct ceph_msg *m;
+	u32 crc;
+
+	con_out_kvec_reset(con);
+	con->out_msg_done = false;
+
+	/* Sneak an ack in there first?  If we can get it into the same
+	 * TCP packet that's a good thing. */
+	if (con->in_seq > con->in_seq_acked) {
+		con->in_seq_acked = con->in_seq;
+		con_out_kvec_add(con, sizeof (tag_ack), &tag_ack);
+		con->out_temp_ack = cpu_to_le64(con->in_seq_acked);
+		con_out_kvec_add(con, sizeof (con->out_temp_ack),
+			&con->out_temp_ack);
+	}
+
+	ceph_con_get_out_msg(con);
+	m = con->out_msg;
+
+	dout("prepare_write_message %p seq %lld type %d len %d+%d+%zd\n",
+	     m, con->out_seq, le16_to_cpu(m->hdr.type),
+	     le32_to_cpu(m->hdr.front_len), le32_to_cpu(m->hdr.middle_len),
+	     m->data_length);
+	WARN_ON(m->front.iov_len != le32_to_cpu(m->hdr.front_len));
+	WARN_ON(m->data_length != le32_to_cpu(m->hdr.data_len));
+
+	/* tag + hdr + front + middle */
+	con_out_kvec_add(con, sizeof (tag_msg), &tag_msg);
+	con_out_kvec_add(con, sizeof(con->out_hdr), &con->out_hdr);
+	con_out_kvec_add(con, m->front.iov_len, m->front.iov_base);
+
+	if (m->middle)
+		con_out_kvec_add(con, m->middle->vec.iov_len,
+			m->middle->vec.iov_base);
+
+	/* fill in hdr crc and finalize hdr */
+	crc = crc32c(0, &m->hdr, offsetof(struct ceph_msg_header, crc));
+	con->out_msg->hdr.crc = cpu_to_le32(crc);
+	memcpy(&con->out_hdr, &con->out_msg->hdr, sizeof(con->out_hdr));
+
+	/* fill in front and middle crc, footer */
+	crc = crc32c(0, m->front.iov_base, m->front.iov_len);
+	con->out_msg->footer.front_crc = cpu_to_le32(crc);
+	if (m->middle) {
+		crc = crc32c(0, m->middle->vec.iov_base,
+				m->middle->vec.iov_len);
+		con->out_msg->footer.middle_crc = cpu_to_le32(crc);
+	} else
+		con->out_msg->footer.middle_crc = 0;
+	dout("%s front_crc %u middle_crc %u\n", __func__,
+	     le32_to_cpu(con->out_msg->footer.front_crc),
+	     le32_to_cpu(con->out_msg->footer.middle_crc));
+	con->out_msg->footer.flags = 0;
+
+	/* is there a data payload? */
+	con->out_msg->footer.data_crc = 0;
+	if (m->data_length) {
+		prepare_message_data(con->out_msg, m->data_length);
+		con->out_more = 1;  /* data + footer will follow */
+	} else {
+		/* no, queue up footer too and be done */
+		prepare_write_message_footer(con);
+	}
+
+	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
+}
+
+/*
+ * Prepare an ack.
+ */
+static void prepare_write_ack(struct ceph_connection *con)
+{
+	dout("prepare_write_ack %p %llu -> %llu\n", con,
+	     con->in_seq_acked, con->in_seq);
+	con->in_seq_acked = con->in_seq;
+
+	con_out_kvec_reset(con);
+
+	con_out_kvec_add(con, sizeof (tag_ack), &tag_ack);
+
+	con->out_temp_ack = cpu_to_le64(con->in_seq_acked);
+	con_out_kvec_add(con, sizeof (con->out_temp_ack),
+				&con->out_temp_ack);
+
+	con->out_more = 1;  /* more will follow.. eventually.. */
+	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
+}
+
+/*
+ * Prepare to share the seq during handshake
+ */
+static void prepare_write_seq(struct ceph_connection *con)
+{
+	dout("prepare_write_seq %p %llu -> %llu\n", con,
+	     con->in_seq_acked, con->in_seq);
+	con->in_seq_acked = con->in_seq;
+
+	con_out_kvec_reset(con);
+
+	con->out_temp_ack = cpu_to_le64(con->in_seq_acked);
+	con_out_kvec_add(con, sizeof (con->out_temp_ack),
+			 &con->out_temp_ack);
+
+	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
+}
+
+/*
+ * Prepare to write keepalive byte.
+ */
+static void prepare_write_keepalive(struct ceph_connection *con)
+{
+	dout("prepare_write_keepalive %p\n", con);
+	con_out_kvec_reset(con);
+	if (con->peer_features & CEPH_FEATURE_MSGR_KEEPALIVE2) {
+		struct timespec64 now;
+
+		ktime_get_real_ts64(&now);
+		con_out_kvec_add(con, sizeof(tag_keepalive2), &tag_keepalive2);
+		ceph_encode_timespec64(&con->out_temp_keepalive2, &now);
+		con_out_kvec_add(con, sizeof(con->out_temp_keepalive2),
+				 &con->out_temp_keepalive2);
+	} else {
+		con_out_kvec_add(con, sizeof(tag_keepalive), &tag_keepalive);
+	}
+	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
+}
+
+/*
+ * Connection negotiation.
+ */
+
+static int get_connect_authorizer(struct ceph_connection *con)
+{
+	struct ceph_auth_handshake *auth;
+	int auth_proto;
+
+	if (!con->ops->get_authorizer) {
+		con->auth = NULL;
+		con->out_connect.authorizer_protocol = CEPH_AUTH_UNKNOWN;
+		con->out_connect.authorizer_len = 0;
+		return 0;
+	}
+
+	auth = con->ops->get_authorizer(con, &auth_proto, con->auth_retry);
+	if (IS_ERR(auth))
+		return PTR_ERR(auth);
+
+	con->auth = auth;
+	con->out_connect.authorizer_protocol = cpu_to_le32(auth_proto);
+	con->out_connect.authorizer_len = cpu_to_le32(auth->authorizer_buf_len);
+	return 0;
+}
+
+/*
+ * We connected to a peer and are saying hello.
+ */
+static void prepare_write_banner(struct ceph_connection *con)
+{
+	con_out_kvec_add(con, strlen(CEPH_BANNER), CEPH_BANNER);
+	con_out_kvec_add(con, sizeof (con->msgr->my_enc_addr),
+					&con->msgr->my_enc_addr);
+
+	con->out_more = 0;
+	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
+}
+
+static void __prepare_write_connect(struct ceph_connection *con)
+{
+	con_out_kvec_add(con, sizeof(con->out_connect), &con->out_connect);
+	if (con->auth)
+		con_out_kvec_add(con, con->auth->authorizer_buf_len,
+				 con->auth->authorizer_buf);
+
+	con->out_more = 0;
+	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
+}
+
+static int prepare_write_connect(struct ceph_connection *con)
+{
+	unsigned int global_seq = ceph_get_global_seq(con->msgr, 0);
+	int proto;
+	int ret;
+
+	switch (con->peer_name.type) {
+	case CEPH_ENTITY_TYPE_MON:
+		proto = CEPH_MONC_PROTOCOL;
+		break;
+	case CEPH_ENTITY_TYPE_OSD:
+		proto = CEPH_OSDC_PROTOCOL;
+		break;
+	case CEPH_ENTITY_TYPE_MDS:
+		proto = CEPH_MDSC_PROTOCOL;
+		break;
+	default:
+		BUG();
+	}
+
+	dout("prepare_write_connect %p cseq=%d gseq=%d proto=%d\n", con,
+	     con->connect_seq, global_seq, proto);
+
+	con->out_connect.features =
+	    cpu_to_le64(from_msgr(con->msgr)->supported_features);
+	con->out_connect.host_type = cpu_to_le32(CEPH_ENTITY_TYPE_CLIENT);
+	con->out_connect.connect_seq = cpu_to_le32(con->connect_seq);
+	con->out_connect.global_seq = cpu_to_le32(global_seq);
+	con->out_connect.protocol_version = cpu_to_le32(proto);
+	con->out_connect.flags = 0;
+
+	ret = get_connect_authorizer(con);
+	if (ret)
+		return ret;
+
+	__prepare_write_connect(con);
+	return 0;
+}
+
+/*
+ * write as much of pending kvecs to the socket as we can.
+ *  1 -> done
+ *  0 -> socket full, but more to do
+ * <0 -> error
+ */
+static int write_partial_kvec(struct ceph_connection *con)
+{
+	int ret;
+
+	dout("write_partial_kvec %p %d left\n", con, con->out_kvec_bytes);
+	while (con->out_kvec_bytes > 0) {
+		ret = ceph_tcp_sendmsg(con->sock, con->out_kvec_cur,
+				       con->out_kvec_left, con->out_kvec_bytes,
+				       con->out_more);
+		if (ret <= 0)
+			goto out;
+		con->out_kvec_bytes -= ret;
+		if (con->out_kvec_bytes == 0)
+			break;            /* done */
+
+		/* account for full iov entries consumed */
+		while (ret >= con->out_kvec_cur->iov_len) {
+			BUG_ON(!con->out_kvec_left);
+			ret -= con->out_kvec_cur->iov_len;
+			con->out_kvec_cur++;
+			con->out_kvec_left--;
+		}
+		/* and for a partially-consumed entry */
+		if (ret) {
+			con->out_kvec_cur->iov_len -= ret;
+			con->out_kvec_cur->iov_base += ret;
+		}
+	}
+	con->out_kvec_left = 0;
+	ret = 1;
+out:
+	dout("write_partial_kvec %p %d left in %d kvecs ret = %d\n", con,
+	     con->out_kvec_bytes, con->out_kvec_left, ret);
+	return ret;  /* done! */
+}
+
+/*
+ * Write as much message data payload as we can.  If we finish, queue
+ * up the footer.
+ *  1 -> done, footer is now queued in out_kvec[].
+ *  0 -> socket full, but more to do
+ * <0 -> error
+ */
+static int write_partial_message_data(struct ceph_connection *con)
+{
+	struct ceph_msg *msg = con->out_msg;
+	struct ceph_msg_data_cursor *cursor = &msg->cursor;
+	bool do_datacrc = !ceph_test_opt(from_msgr(con->msgr), NOCRC);
+	int more = MSG_MORE | MSG_SENDPAGE_NOTLAST;
+	u32 crc;
+
+	dout("%s %p msg %p\n", __func__, con, msg);
+
+	if (!msg->num_data_items)
+		return -EINVAL;
+
+	/*
+	 * Iterate through each page that contains data to be
+	 * written, and send as much as possible for each.
+	 *
+	 * If we are calculating the data crc (the default), we will
+	 * need to map the page.  If we have no pages, they have
+	 * been revoked, so use the zero page.
+	 */
+	crc = do_datacrc ? le32_to_cpu(msg->footer.data_crc) : 0;
+	while (cursor->total_resid) {
+		struct page *page;
+		size_t page_offset;
+		size_t length;
+		int ret;
+
+		if (!cursor->resid) {
+			ceph_msg_data_advance(cursor, 0);
+			continue;
+		}
+
+		page = ceph_msg_data_next(cursor, &page_offset, &length, NULL);
+		if (length == cursor->total_resid)
+			more = MSG_MORE;
+		ret = ceph_tcp_sendpage(con->sock, page, page_offset, length,
+					more);
+		if (ret <= 0) {
+			if (do_datacrc)
+				msg->footer.data_crc = cpu_to_le32(crc);
+
+			return ret;
+		}
+		if (do_datacrc && cursor->need_crc)
+			crc = ceph_crc32c_page(crc, page, page_offset, length);
+		ceph_msg_data_advance(cursor, (size_t)ret);
+	}
+
+	dout("%s %p msg %p done\n", __func__, con, msg);
+
+	/* prepare and queue up footer, too */
+	if (do_datacrc)
+		msg->footer.data_crc = cpu_to_le32(crc);
+	else
+		msg->footer.flags |= CEPH_MSG_FOOTER_NOCRC;
+	con_out_kvec_reset(con);
+	prepare_write_message_footer(con);
+
+	return 1;	/* must return > 0 to indicate success */
+}
+
+/*
+ * write some zeros
+ */
+static int write_partial_skip(struct ceph_connection *con)
+{
+	int more = MSG_MORE | MSG_SENDPAGE_NOTLAST;
+	int ret;
+
+	dout("%s %p %d left\n", __func__, con, con->out_skip);
+	while (con->out_skip > 0) {
+		size_t size = min(con->out_skip, (int) PAGE_SIZE);
+
+		if (size == con->out_skip)
+			more = MSG_MORE;
+		ret = ceph_tcp_sendpage(con->sock, ceph_zero_page, 0, size,
+					more);
+		if (ret <= 0)
+			goto out;
+		con->out_skip -= ret;
+	}
+	ret = 1;
+out:
+	return ret;
+}
+
+/*
+ * Prepare to read connection handshake, or an ack.
+ */
+static void prepare_read_banner(struct ceph_connection *con)
+{
+	dout("prepare_read_banner %p\n", con);
+	con->in_base_pos = 0;
+}
+
+static void prepare_read_connect(struct ceph_connection *con)
+{
+	dout("prepare_read_connect %p\n", con);
+	con->in_base_pos = 0;
+}
+
+static void prepare_read_ack(struct ceph_connection *con)
+{
+	dout("prepare_read_ack %p\n", con);
+	con->in_base_pos = 0;
+}
+
+static void prepare_read_seq(struct ceph_connection *con)
+{
+	dout("prepare_read_seq %p\n", con);
+	con->in_base_pos = 0;
+	con->in_tag = CEPH_MSGR_TAG_SEQ;
+}
+
+static void prepare_read_tag(struct ceph_connection *con)
+{
+	dout("prepare_read_tag %p\n", con);
+	con->in_base_pos = 0;
+	con->in_tag = CEPH_MSGR_TAG_READY;
+}
+
+static void prepare_read_keepalive_ack(struct ceph_connection *con)
+{
+	dout("prepare_read_keepalive_ack %p\n", con);
+	con->in_base_pos = 0;
+}
+
+/*
+ * Prepare to read a message.
+ */
+static int prepare_read_message(struct ceph_connection *con)
+{
+	dout("prepare_read_message %p\n", con);
+	BUG_ON(con->in_msg != NULL);
+	con->in_base_pos = 0;
+	con->in_front_crc = con->in_middle_crc = con->in_data_crc = 0;
+	return 0;
+}
+
+static int read_partial(struct ceph_connection *con,
+			int end, int size, void *object)
+{
+	while (con->in_base_pos < end) {
+		int left = end - con->in_base_pos;
+		int have = size - left;
+		int ret = ceph_tcp_recvmsg(con->sock, object + have, left);
+		if (ret <= 0)
+			return ret;
+		con->in_base_pos += ret;
+	}
+	return 1;
+}
+
+/*
+ * Read all or part of the connect-side handshake on a new connection
+ */
+static int read_partial_banner(struct ceph_connection *con)
+{
+	int size;
+	int end;
+	int ret;
+
+	dout("read_partial_banner %p at %d\n", con, con->in_base_pos);
+
+	/* peer's banner */
+	size = strlen(CEPH_BANNER);
+	end = size;
+	ret = read_partial(con, end, size, con->in_banner);
+	if (ret <= 0)
+		goto out;
+
+	size = sizeof (con->actual_peer_addr);
+	end += size;
+	ret = read_partial(con, end, size, &con->actual_peer_addr);
+	if (ret <= 0)
+		goto out;
+	ceph_decode_banner_addr(&con->actual_peer_addr);
+
+	size = sizeof (con->peer_addr_for_me);
+	end += size;
+	ret = read_partial(con, end, size, &con->peer_addr_for_me);
+	if (ret <= 0)
+		goto out;
+	ceph_decode_banner_addr(&con->peer_addr_for_me);
+
+out:
+	return ret;
+}
+
+static int read_partial_connect(struct ceph_connection *con)
+{
+	int size;
+	int end;
+	int ret;
+
+	dout("read_partial_connect %p at %d\n", con, con->in_base_pos);
+
+	size = sizeof (con->in_reply);
+	end = size;
+	ret = read_partial(con, end, size, &con->in_reply);
+	if (ret <= 0)
+		goto out;
+
+	if (con->auth) {
+		size = le32_to_cpu(con->in_reply.authorizer_len);
+		if (size > con->auth->authorizer_reply_buf_len) {
+			pr_err("authorizer reply too big: %d > %zu\n", size,
+			       con->auth->authorizer_reply_buf_len);
+			ret = -EINVAL;
+			goto out;
+		}
+
+		end += size;
+		ret = read_partial(con, end, size,
+				   con->auth->authorizer_reply_buf);
+		if (ret <= 0)
+			goto out;
+	}
+
+	dout("read_partial_connect %p tag %d, con_seq = %u, g_seq = %u\n",
+	     con, (int)con->in_reply.tag,
+	     le32_to_cpu(con->in_reply.connect_seq),
+	     le32_to_cpu(con->in_reply.global_seq));
+out:
+	return ret;
+}
+
+/*
+ * Verify the hello banner looks okay.
+ */
+static int verify_hello(struct ceph_connection *con)
+{
+	if (memcmp(con->in_banner, CEPH_BANNER, strlen(CEPH_BANNER))) {
+		pr_err("connect to %s got bad banner\n",
+		       ceph_pr_addr(&con->peer_addr));
+		con->error_msg = "protocol error, bad banner";
+		return -1;
+	}
+	return 0;
+}
+
+static int process_banner(struct ceph_connection *con)
+{
+	struct ceph_entity_addr *my_addr = &con->msgr->inst.addr;
+
+	dout("process_banner on %p\n", con);
+
+	if (verify_hello(con) < 0)
+		return -1;
+
+	/*
+	 * Make sure the other end is who we wanted.  note that the other
+	 * end may not yet know their ip address, so if it's 0.0.0.0, give
+	 * them the benefit of the doubt.
+	 */
+	if (memcmp(&con->peer_addr, &con->actual_peer_addr,
+		   sizeof(con->peer_addr)) != 0 &&
+	    !(ceph_addr_is_blank(&con->actual_peer_addr) &&
+	      con->actual_peer_addr.nonce == con->peer_addr.nonce)) {
+		pr_warn("wrong peer, want %s/%u, got %s/%u\n",
+			ceph_pr_addr(&con->peer_addr),
+			le32_to_cpu(con->peer_addr.nonce),
+			ceph_pr_addr(&con->actual_peer_addr),
+			le32_to_cpu(con->actual_peer_addr.nonce));
+		con->error_msg = "wrong peer at address";
+		return -1;
+	}
+
+	/*
+	 * did we learn our address?
+	 */
+	if (ceph_addr_is_blank(my_addr)) {
+		memcpy(&my_addr->in_addr,
+		       &con->peer_addr_for_me.in_addr,
+		       sizeof(con->peer_addr_for_me.in_addr));
+		ceph_addr_set_port(my_addr, 0);
+		ceph_encode_my_addr(con->msgr);
+		dout("process_banner learned my addr is %s\n",
+		     ceph_pr_addr(my_addr));
+	}
+
+	return 0;
+}
+
+static int process_connect(struct ceph_connection *con)
+{
+	u64 sup_feat = from_msgr(con->msgr)->supported_features;
+	u64 req_feat = from_msgr(con->msgr)->required_features;
+	u64 server_feat = le64_to_cpu(con->in_reply.features);
+	int ret;
+
+	dout("process_connect on %p tag %d\n", con, (int)con->in_tag);
+
+	if (con->auth) {
+		int len = le32_to_cpu(con->in_reply.authorizer_len);
+
+		/*
+		 * Any connection that defines ->get_authorizer()
+		 * should also define ->add_authorizer_challenge() and
+		 * ->verify_authorizer_reply().
+		 *
+		 * See get_connect_authorizer().
+		 */
+		if (con->in_reply.tag == CEPH_MSGR_TAG_CHALLENGE_AUTHORIZER) {
+			ret = con->ops->add_authorizer_challenge(
+				    con, con->auth->authorizer_reply_buf, len);
+			if (ret < 0)
+				return ret;
+
+			con_out_kvec_reset(con);
+			__prepare_write_connect(con);
+			prepare_read_connect(con);
+			return 0;
+		}
+
+		if (len) {
+			ret = con->ops->verify_authorizer_reply(con);
+			if (ret < 0) {
+				con->error_msg = "bad authorize reply";
+				return ret;
+			}
+		}
+	}
+
+	switch (con->in_reply.tag) {
+	case CEPH_MSGR_TAG_FEATURES:
+		pr_err("%s%lld %s feature set mismatch,"
+		       " my %llx < server's %llx, missing %llx\n",
+		       ENTITY_NAME(con->peer_name),
+		       ceph_pr_addr(&con->peer_addr),
+		       sup_feat, server_feat, server_feat & ~sup_feat);
+		con->error_msg = "missing required protocol features";
+		return -1;
+
+	case CEPH_MSGR_TAG_BADPROTOVER:
+		pr_err("%s%lld %s protocol version mismatch,"
+		       " my %d != server's %d\n",
+		       ENTITY_NAME(con->peer_name),
+		       ceph_pr_addr(&con->peer_addr),
+		       le32_to_cpu(con->out_connect.protocol_version),
+		       le32_to_cpu(con->in_reply.protocol_version));
+		con->error_msg = "protocol version mismatch";
+		return -1;
+
+	case CEPH_MSGR_TAG_BADAUTHORIZER:
+		con->auth_retry++;
+		dout("process_connect %p got BADAUTHORIZER attempt %d\n", con,
+		     con->auth_retry);
+		if (con->auth_retry == 2) {
+			con->error_msg = "connect authorization failure";
+			return -1;
+		}
+		con_out_kvec_reset(con);
+		ret = prepare_write_connect(con);
+		if (ret < 0)
+			return ret;
+		prepare_read_connect(con);
+		break;
+
+	case CEPH_MSGR_TAG_RESETSESSION:
+		/*
+		 * If we connected with a large connect_seq but the peer
+		 * has no record of a session with us (no connection, or
+		 * connect_seq == 0), they will send RESETSESION to indicate
+		 * that they must have reset their session, and may have
+		 * dropped messages.
+		 */
+		dout("process_connect got RESET peer seq %u\n",
+		     le32_to_cpu(con->in_reply.connect_seq));
+		pr_info("%s%lld %s session reset\n",
+			ENTITY_NAME(con->peer_name),
+			ceph_pr_addr(&con->peer_addr));
+		ceph_con_reset_session(con);
+		con_out_kvec_reset(con);
+		ret = prepare_write_connect(con);
+		if (ret < 0)
+			return ret;
+		prepare_read_connect(con);
+
+		/* Tell ceph about it. */
+		mutex_unlock(&con->mutex);
+		if (con->ops->peer_reset)
+			con->ops->peer_reset(con);
+		mutex_lock(&con->mutex);
+		if (con->state != CEPH_CON_S_V1_CONNECT_MSG)
+			return -EAGAIN;
+		break;
+
+	case CEPH_MSGR_TAG_RETRY_SESSION:
+		/*
+		 * If we sent a smaller connect_seq than the peer has, try
+		 * again with a larger value.
+		 */
+		dout("process_connect got RETRY_SESSION my seq %u, peer %u\n",
+		     le32_to_cpu(con->out_connect.connect_seq),
+		     le32_to_cpu(con->in_reply.connect_seq));
+		con->connect_seq = le32_to_cpu(con->in_reply.connect_seq);
+		con_out_kvec_reset(con);
+		ret = prepare_write_connect(con);
+		if (ret < 0)
+			return ret;
+		prepare_read_connect(con);
+		break;
+
+	case CEPH_MSGR_TAG_RETRY_GLOBAL:
+		/*
+		 * If we sent a smaller global_seq than the peer has, try
+		 * again with a larger value.
+		 */
+		dout("process_connect got RETRY_GLOBAL my %u peer_gseq %u\n",
+		     con->peer_global_seq,
+		     le32_to_cpu(con->in_reply.global_seq));
+		ceph_get_global_seq(con->msgr,
+				    le32_to_cpu(con->in_reply.global_seq));
+		con_out_kvec_reset(con);
+		ret = prepare_write_connect(con);
+		if (ret < 0)
+			return ret;
+		prepare_read_connect(con);
+		break;
+
+	case CEPH_MSGR_TAG_SEQ:
+	case CEPH_MSGR_TAG_READY:
+		if (req_feat & ~server_feat) {
+			pr_err("%s%lld %s protocol feature mismatch,"
+			       " my required %llx > server's %llx, need %llx\n",
+			       ENTITY_NAME(con->peer_name),
+			       ceph_pr_addr(&con->peer_addr),
+			       req_feat, server_feat, req_feat & ~server_feat);
+			con->error_msg = "missing required protocol features";
+			return -1;
+		}
+
+		WARN_ON(con->state != CEPH_CON_S_V1_CONNECT_MSG);
+		con->state = CEPH_CON_S_OPEN;
+		con->auth_retry = 0;    /* we authenticated; clear flag */
+		con->peer_global_seq = le32_to_cpu(con->in_reply.global_seq);
+		con->connect_seq++;
+		con->peer_features = server_feat;
+		dout("process_connect got READY gseq %d cseq %d (%d)\n",
+		     con->peer_global_seq,
+		     le32_to_cpu(con->in_reply.connect_seq),
+		     con->connect_seq);
+		WARN_ON(con->connect_seq !=
+			le32_to_cpu(con->in_reply.connect_seq));
+
+		if (con->in_reply.flags & CEPH_MSG_CONNECT_LOSSY)
+			ceph_con_flag_set(con, CEPH_CON_F_LOSSYTX);
+
+		con->delay = 0;      /* reset backoff memory */
+
+		if (con->in_reply.tag == CEPH_MSGR_TAG_SEQ) {
+			prepare_write_seq(con);
+			prepare_read_seq(con);
+		} else {
+			prepare_read_tag(con);
+		}
+		break;
+
+	case CEPH_MSGR_TAG_WAIT:
+		/*
+		 * If there is a connection race (we are opening
+		 * connections to each other), one of us may just have
+		 * to WAIT.  This shouldn't happen if we are the
+		 * client.
+		 */
+		con->error_msg = "protocol error, got WAIT as client";
+		return -1;
+
+	default:
+		con->error_msg = "protocol error, garbage tag during connect";
+		return -1;
+	}
+	return 0;
+}
+
+/*
+ * read (part of) an ack
+ */
+static int read_partial_ack(struct ceph_connection *con)
+{
+	int size = sizeof (con->in_temp_ack);
+	int end = size;
+
+	return read_partial(con, end, size, &con->in_temp_ack);
+}
+
+/*
+ * We can finally discard anything that's been acked.
+ */
+static void process_ack(struct ceph_connection *con)
+{
+	u64 ack = le64_to_cpu(con->in_temp_ack);
+
+	if (con->in_tag == CEPH_MSGR_TAG_ACK)
+		ceph_con_discard_sent(con, ack);
+	else
+		ceph_con_discard_requeued(con, ack);
+
+	prepare_read_tag(con);
+}
+
+static int read_partial_message_section(struct ceph_connection *con,
+					struct kvec *section,
+					unsigned int sec_len, u32 *crc)
+{
+	int ret, left;
+
+	BUG_ON(!section);
+
+	while (section->iov_len < sec_len) {
+		BUG_ON(section->iov_base == NULL);
+		left = sec_len - section->iov_len;
+		ret = ceph_tcp_recvmsg(con->sock, (char *)section->iov_base +
+				       section->iov_len, left);
+		if (ret <= 0)
+			return ret;
+		section->iov_len += ret;
+	}
+	if (section->iov_len == sec_len)
+		*crc = crc32c(0, section->iov_base, section->iov_len);
+
+	return 1;
+}
+
+static int read_partial_msg_data(struct ceph_connection *con)
+{
+	struct ceph_msg *msg = con->in_msg;
+	struct ceph_msg_data_cursor *cursor = &msg->cursor;
+	bool do_datacrc = !ceph_test_opt(from_msgr(con->msgr), NOCRC);
+	struct page *page;
+	size_t page_offset;
+	size_t length;
+	u32 crc = 0;
+	int ret;
+
+	if (!msg->num_data_items)
+		return -EIO;
+
+	if (do_datacrc)
+		crc = con->in_data_crc;
+	while (cursor->total_resid) {
+		if (!cursor->resid) {
+			ceph_msg_data_advance(cursor, 0);
+			continue;
+		}
+
+		page = ceph_msg_data_next(cursor, &page_offset, &length, NULL);
+		ret = ceph_tcp_recvpage(con->sock, page, page_offset, length);
+		if (ret <= 0) {
+			if (do_datacrc)
+				con->in_data_crc = crc;
+
+			return ret;
+		}
+
+		if (do_datacrc)
+			crc = ceph_crc32c_page(crc, page, page_offset, ret);
+		ceph_msg_data_advance(cursor, (size_t)ret);
+	}
+	if (do_datacrc)
+		con->in_data_crc = crc;
+
+	return 1;	/* must return > 0 to indicate success */
+}
+
+/*
+ * read (part of) a message.
+ */
+static int read_partial_message(struct ceph_connection *con)
+{
+	struct ceph_msg *m = con->in_msg;
+	int size;
+	int end;
+	int ret;
+	unsigned int front_len, middle_len, data_len;
+	bool do_datacrc = !ceph_test_opt(from_msgr(con->msgr), NOCRC);
+	bool need_sign = (con->peer_features & CEPH_FEATURE_MSG_AUTH);
+	u64 seq;
+	u32 crc;
+
+	dout("read_partial_message con %p msg %p\n", con, m);
+
+	/* header */
+	size = sizeof (con->in_hdr);
+	end = size;
+	ret = read_partial(con, end, size, &con->in_hdr);
+	if (ret <= 0)
+		return ret;
+
+	crc = crc32c(0, &con->in_hdr, offsetof(struct ceph_msg_header, crc));
+	if (cpu_to_le32(crc) != con->in_hdr.crc) {
+		pr_err("read_partial_message bad hdr crc %u != expected %u\n",
+		       crc, con->in_hdr.crc);
+		return -EBADMSG;
+	}
+
+	front_len = le32_to_cpu(con->in_hdr.front_len);
+	if (front_len > CEPH_MSG_MAX_FRONT_LEN)
+		return -EIO;
+	middle_len = le32_to_cpu(con->in_hdr.middle_len);
+	if (middle_len > CEPH_MSG_MAX_MIDDLE_LEN)
+		return -EIO;
+	data_len = le32_to_cpu(con->in_hdr.data_len);
+	if (data_len > CEPH_MSG_MAX_DATA_LEN)
+		return -EIO;
+
+	/* verify seq# */
+	seq = le64_to_cpu(con->in_hdr.seq);
+	if ((s64)seq - (s64)con->in_seq < 1) {
+		pr_info("skipping %s%lld %s seq %lld expected %lld\n",
+			ENTITY_NAME(con->peer_name),
+			ceph_pr_addr(&con->peer_addr),
+			seq, con->in_seq + 1);
+		con->in_base_pos = -front_len - middle_len - data_len -
+			sizeof_footer(con);
+		con->in_tag = CEPH_MSGR_TAG_READY;
+		return 1;
+	} else if ((s64)seq - (s64)con->in_seq > 1) {
+		pr_err("read_partial_message bad seq %lld expected %lld\n",
+		       seq, con->in_seq + 1);
+		con->error_msg = "bad message sequence # for incoming message";
+		return -EBADE;
+	}
+
+	/* allocate message? */
+	if (!con->in_msg) {
+		int skip = 0;
+
+		dout("got hdr type %d front %d data %d\n", con->in_hdr.type,
+		     front_len, data_len);
+		ret = ceph_con_in_msg_alloc(con, &con->in_hdr, &skip);
+		if (ret < 0)
+			return ret;
+
+		BUG_ON(!con->in_msg ^ skip);
+		if (skip) {
+			/* skip this message */
+			dout("alloc_msg said skip message\n");
+			con->in_base_pos = -front_len - middle_len - data_len -
+				sizeof_footer(con);
+			con->in_tag = CEPH_MSGR_TAG_READY;
+			con->in_seq++;
+			return 1;
+		}
+
+		BUG_ON(!con->in_msg);
+		BUG_ON(con->in_msg->con != con);
+		m = con->in_msg;
+		m->front.iov_len = 0;    /* haven't read it yet */
+		if (m->middle)
+			m->middle->vec.iov_len = 0;
+
+		/* prepare for data payload, if any */
+
+		if (data_len)
+			prepare_message_data(con->in_msg, data_len);
+	}
+
+	/* front */
+	ret = read_partial_message_section(con, &m->front, front_len,
+					   &con->in_front_crc);
+	if (ret <= 0)
+		return ret;
+
+	/* middle */
+	if (m->middle) {
+		ret = read_partial_message_section(con, &m->middle->vec,
+						   middle_len,
+						   &con->in_middle_crc);
+		if (ret <= 0)
+			return ret;
+	}
+
+	/* (page) data */
+	if (data_len) {
+		ret = read_partial_msg_data(con);
+		if (ret <= 0)
+			return ret;
+	}
+
+	/* footer */
+	size = sizeof_footer(con);
+	end += size;
+	ret = read_partial(con, end, size, &m->footer);
+	if (ret <= 0)
+		return ret;
+
+	if (!need_sign) {
+		m->footer.flags = m->old_footer.flags;
+		m->footer.sig = 0;
+	}
+
+	dout("read_partial_message got msg %p %d (%u) + %d (%u) + %d (%u)\n",
+	     m, front_len, m->footer.front_crc, middle_len,
+	     m->footer.middle_crc, data_len, m->footer.data_crc);
+
+	/* crc ok? */
+	if (con->in_front_crc != le32_to_cpu(m->footer.front_crc)) {
+		pr_err("read_partial_message %p front crc %u != exp. %u\n",
+		       m, con->in_front_crc, m->footer.front_crc);
+		return -EBADMSG;
+	}
+	if (con->in_middle_crc != le32_to_cpu(m->footer.middle_crc)) {
+		pr_err("read_partial_message %p middle crc %u != exp %u\n",
+		       m, con->in_middle_crc, m->footer.middle_crc);
+		return -EBADMSG;
+	}
+	if (do_datacrc &&
+	    (m->footer.flags & CEPH_MSG_FOOTER_NOCRC) == 0 &&
+	    con->in_data_crc != le32_to_cpu(m->footer.data_crc)) {
+		pr_err("read_partial_message %p data crc %u != exp. %u\n", m,
+		       con->in_data_crc, le32_to_cpu(m->footer.data_crc));
+		return -EBADMSG;
+	}
+
+	if (need_sign && con->ops->check_message_signature &&
+	    con->ops->check_message_signature(m)) {
+		pr_err("read_partial_message %p signature check failed\n", m);
+		return -EBADMSG;
+	}
+
+	return 1; /* done! */
+}
+
+static int read_keepalive_ack(struct ceph_connection *con)
+{
+	struct ceph_timespec ceph_ts;
+	size_t size = sizeof(ceph_ts);
+	int ret = read_partial(con, size, size, &ceph_ts);
+	if (ret <= 0)
+		return ret;
+	ceph_decode_timespec64(&con->last_keepalive_ack, &ceph_ts);
+	prepare_read_tag(con);
+	return 1;
+}
+
+/*
+ * Read what we can from the socket.
+ */
+int ceph_con_v1_try_read(struct ceph_connection *con)
+{
+	int ret = -1;
+
+more:
+	dout("try_read start %p state %d\n", con, con->state);
+	if (con->state != CEPH_CON_S_V1_BANNER &&
+	    con->state != CEPH_CON_S_V1_CONNECT_MSG &&
+	    con->state != CEPH_CON_S_OPEN)
+		return 0;
+
+	BUG_ON(!con->sock);
+
+	dout("try_read tag %d in_base_pos %d\n", (int)con->in_tag,
+	     con->in_base_pos);
+
+	if (con->state == CEPH_CON_S_V1_BANNER) {
+		ret = read_partial_banner(con);
+		if (ret <= 0)
+			goto out;
+		ret = process_banner(con);
+		if (ret < 0)
+			goto out;
+
+		con->state = CEPH_CON_S_V1_CONNECT_MSG;
+
+		/*
+		 * Received banner is good, exchange connection info.
+		 * Do not reset out_kvec, as sending our banner raced
+		 * with receiving peer banner after connect completed.
+		 */
+		ret = prepare_write_connect(con);
+		if (ret < 0)
+			goto out;
+		prepare_read_connect(con);
+
+		/* Send connection info before awaiting response */
+		goto out;
+	}
+
+	if (con->state == CEPH_CON_S_V1_CONNECT_MSG) {
+		ret = read_partial_connect(con);
+		if (ret <= 0)
+			goto out;
+		ret = process_connect(con);
+		if (ret < 0)
+			goto out;
+		goto more;
+	}
+
+	WARN_ON(con->state != CEPH_CON_S_OPEN);
+
+	if (con->in_base_pos < 0) {
+		/*
+		 * skipping + discarding content.
+		 */
+		ret = ceph_tcp_recvmsg(con->sock, NULL, -con->in_base_pos);
+		if (ret <= 0)
+			goto out;
+		dout("skipped %d / %d bytes\n", ret, -con->in_base_pos);
+		con->in_base_pos += ret;
+		if (con->in_base_pos)
+			goto more;
+	}
+	if (con->in_tag == CEPH_MSGR_TAG_READY) {
+		/*
+		 * what's next?
+		 */
+		ret = ceph_tcp_recvmsg(con->sock, &con->in_tag, 1);
+		if (ret <= 0)
+			goto out;
+		dout("try_read got tag %d\n", (int)con->in_tag);
+		switch (con->in_tag) {
+		case CEPH_MSGR_TAG_MSG:
+			prepare_read_message(con);
+			break;
+		case CEPH_MSGR_TAG_ACK:
+			prepare_read_ack(con);
+			break;
+		case CEPH_MSGR_TAG_KEEPALIVE2_ACK:
+			prepare_read_keepalive_ack(con);
+			break;
+		case CEPH_MSGR_TAG_CLOSE:
+			ceph_con_close_socket(con);
+			con->state = CEPH_CON_S_CLOSED;
+			goto out;
+		default:
+			goto bad_tag;
+		}
+	}
+	if (con->in_tag == CEPH_MSGR_TAG_MSG) {
+		ret = read_partial_message(con);
+		if (ret <= 0) {
+			switch (ret) {
+			case -EBADMSG:
+				con->error_msg = "bad crc/signature";
+				fallthrough;
+			case -EBADE:
+				ret = -EIO;
+				break;
+			case -EIO:
+				con->error_msg = "io error";
+				break;
+			}
+			goto out;
+		}
+		if (con->in_tag == CEPH_MSGR_TAG_READY)
+			goto more;
+		ceph_con_process_message(con);
+		if (con->state == CEPH_CON_S_OPEN)
+			prepare_read_tag(con);
+		goto more;
+	}
+	if (con->in_tag == CEPH_MSGR_TAG_ACK ||
+	    con->in_tag == CEPH_MSGR_TAG_SEQ) {
+		/*
+		 * the final handshake seq exchange is semantically
+		 * equivalent to an ACK
+		 */
+		ret = read_partial_ack(con);
+		if (ret <= 0)
+			goto out;
+		process_ack(con);
+		goto more;
+	}
+	if (con->in_tag == CEPH_MSGR_TAG_KEEPALIVE2_ACK) {
+		ret = read_keepalive_ack(con);
+		if (ret <= 0)
+			goto out;
+		goto more;
+	}
+
+out:
+	dout("try_read done on %p ret %d\n", con, ret);
+	return ret;
+
+bad_tag:
+	pr_err("try_read bad con->in_tag = %d\n", (int)con->in_tag);
+	con->error_msg = "protocol error, garbage tag";
+	ret = -1;
+	goto out;
+}
+
+/*
+ * Write something to the socket.  Called in a worker thread when the
+ * socket appears to be writeable and we have something ready to send.
+ */
+int ceph_con_v1_try_write(struct ceph_connection *con)
+{
+	int ret = 1;
+
+	dout("try_write start %p state %d\n", con, con->state);
+	if (con->state != CEPH_CON_S_PREOPEN &&
+	    con->state != CEPH_CON_S_V1_BANNER &&
+	    con->state != CEPH_CON_S_V1_CONNECT_MSG &&
+	    con->state != CEPH_CON_S_OPEN)
+		return 0;
+
+	/* open the socket first? */
+	if (con->state == CEPH_CON_S_PREOPEN) {
+		BUG_ON(con->sock);
+		con->state = CEPH_CON_S_V1_BANNER;
+
+		con_out_kvec_reset(con);
+		prepare_write_banner(con);
+		prepare_read_banner(con);
+
+		BUG_ON(con->in_msg);
+		con->in_tag = CEPH_MSGR_TAG_READY;
+		dout("try_write initiating connect on %p new state %d\n",
+		     con, con->state);
+		ret = ceph_tcp_connect(con);
+		if (ret < 0) {
+			con->error_msg = "connect error";
+			goto out;
+		}
+	}
+
+more:
+	dout("try_write out_kvec_bytes %d\n", con->out_kvec_bytes);
+	BUG_ON(!con->sock);
+
+	/* kvec data queued? */
+	if (con->out_kvec_left) {
+		ret = write_partial_kvec(con);
+		if (ret <= 0)
+			goto out;
+	}
+	if (con->out_skip) {
+		ret = write_partial_skip(con);
+		if (ret <= 0)
+			goto out;
+	}
+
+	/* msg pages? */
+	if (con->out_msg) {
+		if (con->out_msg_done) {
+			ceph_msg_put(con->out_msg);
+			con->out_msg = NULL;   /* we're done with this one */
+			goto do_next;
+		}
+
+		ret = write_partial_message_data(con);
+		if (ret == 1)
+			goto more;  /* we need to send the footer, too! */
+		if (ret == 0)
+			goto out;
+		if (ret < 0) {
+			dout("try_write write_partial_message_data err %d\n",
+			     ret);
+			goto out;
+		}
+	}
+
+do_next:
+	if (con->state == CEPH_CON_S_OPEN) {
+		if (ceph_con_flag_test_and_clear(con,
+				CEPH_CON_F_KEEPALIVE_PENDING)) {
+			prepare_write_keepalive(con);
+			goto more;
+		}
+		/* is anything else pending? */
+		if (!list_empty(&con->out_queue)) {
+			prepare_write_message(con);
+			goto more;
+		}
+		if (con->in_seq > con->in_seq_acked) {
+			prepare_write_ack(con);
+			goto more;
+		}
+	}
+
+	/* Nothing to do! */
+	ceph_con_flag_clear(con, CEPH_CON_F_WRITE_PENDING);
+	dout("try_write nothing else to write.\n");
+	ret = 0;
+out:
+	dout("try_write done on %p ret %d\n", con, ret);
+	return ret;
+}
+
+void ceph_con_v1_revoke(struct ceph_connection *con)
+{
+	struct ceph_msg *msg = con->out_msg;
+
+	WARN_ON(con->out_skip);
+	/* footer */
+	if (con->out_msg_done) {
+		con->out_skip += con_out_kvec_skip(con);
+	} else {
+		WARN_ON(!msg->data_length);
+		con->out_skip += sizeof_footer(con);
+	}
+	/* data, middle, front */
+	if (msg->data_length)
+		con->out_skip += msg->cursor.total_resid;
+	if (msg->middle)
+		con->out_skip += con_out_kvec_skip(con);
+	con->out_skip += con_out_kvec_skip(con);
+
+	dout("%s con %p out_kvec_bytes %d out_skip %d\n", __func__, con,
+	     con->out_kvec_bytes, con->out_skip);
+}
+
+void ceph_con_v1_revoke_incoming(struct ceph_connection *con)
+{
+	unsigned int front_len = le32_to_cpu(con->in_hdr.front_len);
+	unsigned int middle_len = le32_to_cpu(con->in_hdr.middle_len);
+	unsigned int data_len = le32_to_cpu(con->in_hdr.data_len);
+
+	/* skip rest of message */
+	con->in_base_pos = con->in_base_pos -
+			sizeof(struct ceph_msg_header) -
+			front_len -
+			middle_len -
+			data_len -
+			sizeof(struct ceph_msg_footer);
+
+	con->in_tag = CEPH_MSGR_TAG_READY;
+	con->in_seq++;
+
+	dout("%s con %p in_base_pos %d\n", __func__, con, con->in_base_pos);
+}
+
+bool ceph_con_v1_opened(struct ceph_connection *con)
+{
+	return con->connect_seq;
+}
+
+void ceph_con_v1_reset_session(struct ceph_connection *con)
+{
+	con->connect_seq = 0;
+	con->peer_global_seq = 0;
+}
+
+void ceph_con_v1_reset_protocol(struct ceph_connection *con)
+{
+	con->out_skip = 0;
+}
-- 
cgit v1.2.3


From a56dd9bf47220c3206f27075af8bdfb219a2a3cf Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Thu, 12 Nov 2020 16:31:41 +0100
Subject: libceph: move msgr1 protocol specific fields to its own struct

A couple whitespace fixups, no functional changes.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/messenger.h |  76 ++++----
 net/ceph/messenger.c           |   8 +-
 net/ceph/messenger_v1.c        | 420 +++++++++++++++++++++--------------------
 3 files changed, 257 insertions(+), 247 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index b5268127c55e..54a64e8dfce6 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -264,6 +264,43 @@ struct ceph_msg {
 #define BASE_DELAY_INTERVAL	(HZ / 4)
 #define MAX_DELAY_INTERVAL	(15 * HZ)
 
+struct ceph_connection_v1_info {
+	struct kvec out_kvec[8],         /* sending header/footer data */
+		*out_kvec_cur;
+	int out_kvec_left;   /* kvec's left in out_kvec */
+	int out_skip;        /* skip this many bytes */
+	int out_kvec_bytes;  /* total bytes left */
+	bool out_more;       /* there is more data after the kvecs */
+	bool out_msg_done;
+
+	struct ceph_auth_handshake *auth;
+	int auth_retry;       /* true if we need a newer authorizer */
+
+	/* connection negotiation temps */
+	u8 in_banner[CEPH_BANNER_MAX_LEN];
+	struct ceph_entity_addr actual_peer_addr;
+	struct ceph_entity_addr peer_addr_for_me;
+	struct ceph_msg_connect out_connect;
+	struct ceph_msg_connect_reply in_reply;
+
+	int in_base_pos;     /* bytes read */
+
+	/* message in temps */
+	u8 in_tag;           /* protocol control byte */
+	struct ceph_msg_header in_hdr;
+	__le64 in_temp_ack;  /* for reading an ack */
+
+	/* message out temps */
+	struct ceph_msg_header out_hdr;
+	__le64 out_temp_ack;  /* for writing an ack */
+	struct ceph_timespec out_temp_keepalive2;  /* for writing keepalive2
+						      stamp */
+
+	u32 connect_seq;      /* identify the most recent connection
+				 attempt for this session */
+	u32 peer_global_seq;  /* peer's global seq for this connection */
+};
+
 /*
  * A single connection with another host.
  *
@@ -281,21 +318,13 @@ struct ceph_connection {
 	int state;  /* CEPH_CON_S_* */
 	atomic_t sock_state;
 	struct socket *sock;
-	struct ceph_entity_addr peer_addr; /* peer address */
-	struct ceph_entity_addr peer_addr_for_me;
 
 	unsigned long flags;  /* CEPH_CON_F_* */
 	const char *error_msg;  /* error message, if any */
 
 	struct ceph_entity_name peer_name; /* peer name */
-
+	struct ceph_entity_addr peer_addr; /* peer address */
 	u64 peer_features;
-	u32 connect_seq;      /* identify the most recent connection
-				 attempt for this connection, client */
-	u32 peer_global_seq;  /* peer's global seq for this connection */
-
-	struct ceph_auth_handshake *auth;
-	int auth_retry;       /* true if we need a newer authorizer */
 
 	struct mutex mutex;
 
@@ -306,41 +335,18 @@ struct ceph_connection {
 
 	u64 in_seq, in_seq_acked;  /* last message received, acked */
 
-	/* connection negotiation temps */
-	char in_banner[CEPH_BANNER_MAX_LEN];
-	struct ceph_msg_connect out_connect;
-	struct ceph_msg_connect_reply in_reply;
-	struct ceph_entity_addr actual_peer_addr;
-
-	/* message out temps */
-	struct ceph_msg_header out_hdr;
+	struct ceph_msg *in_msg;
 	struct ceph_msg *out_msg;        /* sending message (== tail of
 					    out_sent) */
-	bool out_msg_done;
-
-	struct kvec out_kvec[8],         /* sending header/footer data */
-		*out_kvec_cur;
-	int out_kvec_left;   /* kvec's left in out_kvec */
-	int out_skip;        /* skip this many bytes */
-	int out_kvec_bytes;  /* total bytes left */
-	int out_more;        /* there is more data after the kvecs */
-	__le64 out_temp_ack; /* for writing an ack */
-	struct ceph_timespec out_temp_keepalive2; /* for writing keepalive2
-						     stamp */
 
-	/* message in temps */
-	struct ceph_msg_header in_hdr;
-	struct ceph_msg *in_msg;
 	u32 in_front_crc, in_middle_crc, in_data_crc;  /* calculated crc */
 
-	char in_tag;         /* protocol control byte */
-	int in_base_pos;     /* bytes read */
-	__le64 in_temp_ack;  /* for reading an ack */
-
 	struct timespec64 last_keepalive_ack; /* keepalive2 ack stamp */
 
 	struct delayed_work work;	    /* send|recv work */
 	unsigned long       delay;          /* current delay interval */
+
+	struct ceph_connection_v1_info v1;
 };
 
 extern struct page *ceph_zero_page;
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 544cfdbe52d6..4fb3c33a7b03 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -1448,11 +1448,11 @@ static void con_fault_finish(struct ceph_connection *con)
 	 * in case we faulted due to authentication, invalidate our
 	 * current tickets so that we can get new ones.
 	 */
-	if (con->auth_retry) {
-		dout("auth_retry %d, invalidating\n", con->auth_retry);
+	if (con->v1.auth_retry) {
+		dout("auth_retry %d, invalidating\n", con->v1.auth_retry);
 		if (con->ops->invalidate_authorizer)
 			con->ops->invalidate_authorizer(con);
-		con->auth_retry = 0;
+		con->v1.auth_retry = 0;
 	}
 
 	if (con->ops->fault)
@@ -1631,7 +1631,7 @@ static void clear_standby(struct ceph_connection *con)
 	if (con->state == CEPH_CON_S_STANDBY) {
 		dout("clear_standby %p and ++connect_seq\n", con);
 		con->state = CEPH_CON_S_PREOPEN;
-		con->connect_seq++;
+		con->v1.connect_seq++;
 		WARN_ON(ceph_con_flag_test(con, CEPH_CON_F_WRITE_PENDING));
 		WARN_ON(ceph_con_flag_test(con, CEPH_CON_F_KEEPALIVE_PENDING));
 	}
diff --git a/net/ceph/messenger_v1.c b/net/ceph/messenger_v1.c
index 899038a9678e..04f653b3c897 100644
--- a/net/ceph/messenger_v1.c
+++ b/net/ceph/messenger_v1.c
@@ -110,25 +110,25 @@ static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
 
 static void con_out_kvec_reset(struct ceph_connection *con)
 {
-	BUG_ON(con->out_skip);
+	BUG_ON(con->v1.out_skip);
 
-	con->out_kvec_left = 0;
-	con->out_kvec_bytes = 0;
-	con->out_kvec_cur = &con->out_kvec[0];
+	con->v1.out_kvec_left = 0;
+	con->v1.out_kvec_bytes = 0;
+	con->v1.out_kvec_cur = &con->v1.out_kvec[0];
 }
 
 static void con_out_kvec_add(struct ceph_connection *con,
 				size_t size, void *data)
 {
-	int index = con->out_kvec_left;
+	int index = con->v1.out_kvec_left;
 
-	BUG_ON(con->out_skip);
-	BUG_ON(index >= ARRAY_SIZE(con->out_kvec));
+	BUG_ON(con->v1.out_skip);
+	BUG_ON(index >= ARRAY_SIZE(con->v1.out_kvec));
 
-	con->out_kvec[index].iov_len = size;
-	con->out_kvec[index].iov_base = data;
-	con->out_kvec_left++;
-	con->out_kvec_bytes += size;
+	con->v1.out_kvec[index].iov_len = size;
+	con->v1.out_kvec[index].iov_base = data;
+	con->v1.out_kvec_left++;
+	con->v1.out_kvec_bytes += size;
 }
 
 /*
@@ -138,15 +138,14 @@ static void con_out_kvec_add(struct ceph_connection *con,
  */
 static int con_out_kvec_skip(struct ceph_connection *con)
 {
-	int off = con->out_kvec_cur - con->out_kvec;
 	int skip = 0;
 
-	if (con->out_kvec_bytes > 0) {
-		skip = con->out_kvec[off + con->out_kvec_left - 1].iov_len;
-		BUG_ON(con->out_kvec_bytes < skip);
-		BUG_ON(!con->out_kvec_left);
-		con->out_kvec_bytes -= skip;
-		con->out_kvec_left--;
+	if (con->v1.out_kvec_bytes > 0) {
+		skip = con->v1.out_kvec_cur[con->v1.out_kvec_left - 1].iov_len;
+		BUG_ON(con->v1.out_kvec_bytes < skip);
+		BUG_ON(!con->v1.out_kvec_left);
+		con->v1.out_kvec_bytes -= skip;
+		con->v1.out_kvec_left--;
 	}
 
 	return skip;
@@ -186,8 +185,8 @@ static void prepare_write_message_footer(struct ceph_connection *con)
 	} else {
 		m->old_footer.flags = m->footer.flags;
 	}
-	con->out_more = m->more_to_follow;
-	con->out_msg_done = true;
+	con->v1.out_more = m->more_to_follow;
+	con->v1.out_msg_done = true;
 }
 
 /*
@@ -199,16 +198,16 @@ static void prepare_write_message(struct ceph_connection *con)
 	u32 crc;
 
 	con_out_kvec_reset(con);
-	con->out_msg_done = false;
+	con->v1.out_msg_done = false;
 
 	/* Sneak an ack in there first?  If we can get it into the same
 	 * TCP packet that's a good thing. */
 	if (con->in_seq > con->in_seq_acked) {
 		con->in_seq_acked = con->in_seq;
 		con_out_kvec_add(con, sizeof (tag_ack), &tag_ack);
-		con->out_temp_ack = cpu_to_le64(con->in_seq_acked);
-		con_out_kvec_add(con, sizeof (con->out_temp_ack),
-			&con->out_temp_ack);
+		con->v1.out_temp_ack = cpu_to_le64(con->in_seq_acked);
+		con_out_kvec_add(con, sizeof(con->v1.out_temp_ack),
+			&con->v1.out_temp_ack);
 	}
 
 	ceph_con_get_out_msg(con);
@@ -223,7 +222,7 @@ static void prepare_write_message(struct ceph_connection *con)
 
 	/* tag + hdr + front + middle */
 	con_out_kvec_add(con, sizeof (tag_msg), &tag_msg);
-	con_out_kvec_add(con, sizeof(con->out_hdr), &con->out_hdr);
+	con_out_kvec_add(con, sizeof(con->v1.out_hdr), &con->v1.out_hdr);
 	con_out_kvec_add(con, m->front.iov_len, m->front.iov_base);
 
 	if (m->middle)
@@ -233,7 +232,7 @@ static void prepare_write_message(struct ceph_connection *con)
 	/* fill in hdr crc and finalize hdr */
 	crc = crc32c(0, &m->hdr, offsetof(struct ceph_msg_header, crc));
 	con->out_msg->hdr.crc = cpu_to_le32(crc);
-	memcpy(&con->out_hdr, &con->out_msg->hdr, sizeof(con->out_hdr));
+	memcpy(&con->v1.out_hdr, &con->out_msg->hdr, sizeof(con->v1.out_hdr));
 
 	/* fill in front and middle crc, footer */
 	crc = crc32c(0, m->front.iov_base, m->front.iov_len);
@@ -253,7 +252,7 @@ static void prepare_write_message(struct ceph_connection *con)
 	con->out_msg->footer.data_crc = 0;
 	if (m->data_length) {
 		prepare_message_data(con->out_msg, m->data_length);
-		con->out_more = 1;  /* data + footer will follow */
+		con->v1.out_more = 1;  /* data + footer will follow */
 	} else {
 		/* no, queue up footer too and be done */
 		prepare_write_message_footer(con);
@@ -275,11 +274,11 @@ static void prepare_write_ack(struct ceph_connection *con)
 
 	con_out_kvec_add(con, sizeof (tag_ack), &tag_ack);
 
-	con->out_temp_ack = cpu_to_le64(con->in_seq_acked);
-	con_out_kvec_add(con, sizeof (con->out_temp_ack),
-				&con->out_temp_ack);
+	con->v1.out_temp_ack = cpu_to_le64(con->in_seq_acked);
+	con_out_kvec_add(con, sizeof(con->v1.out_temp_ack),
+			 &con->v1.out_temp_ack);
 
-	con->out_more = 1;  /* more will follow.. eventually.. */
+	con->v1.out_more = 1;  /* more will follow.. eventually.. */
 	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
 }
 
@@ -294,9 +293,9 @@ static void prepare_write_seq(struct ceph_connection *con)
 
 	con_out_kvec_reset(con);
 
-	con->out_temp_ack = cpu_to_le64(con->in_seq_acked);
-	con_out_kvec_add(con, sizeof (con->out_temp_ack),
-			 &con->out_temp_ack);
+	con->v1.out_temp_ack = cpu_to_le64(con->in_seq_acked);
+	con_out_kvec_add(con, sizeof(con->v1.out_temp_ack),
+			 &con->v1.out_temp_ack);
 
 	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
 }
@@ -313,9 +312,9 @@ static void prepare_write_keepalive(struct ceph_connection *con)
 
 		ktime_get_real_ts64(&now);
 		con_out_kvec_add(con, sizeof(tag_keepalive2), &tag_keepalive2);
-		ceph_encode_timespec64(&con->out_temp_keepalive2, &now);
-		con_out_kvec_add(con, sizeof(con->out_temp_keepalive2),
-				 &con->out_temp_keepalive2);
+		ceph_encode_timespec64(&con->v1.out_temp_keepalive2, &now);
+		con_out_kvec_add(con, sizeof(con->v1.out_temp_keepalive2),
+				 &con->v1.out_temp_keepalive2);
 	} else {
 		con_out_kvec_add(con, sizeof(tag_keepalive), &tag_keepalive);
 	}
@@ -332,19 +331,20 @@ static int get_connect_authorizer(struct ceph_connection *con)
 	int auth_proto;
 
 	if (!con->ops->get_authorizer) {
-		con->auth = NULL;
-		con->out_connect.authorizer_protocol = CEPH_AUTH_UNKNOWN;
-		con->out_connect.authorizer_len = 0;
+		con->v1.auth = NULL;
+		con->v1.out_connect.authorizer_protocol = CEPH_AUTH_UNKNOWN;
+		con->v1.out_connect.authorizer_len = 0;
 		return 0;
 	}
 
-	auth = con->ops->get_authorizer(con, &auth_proto, con->auth_retry);
+	auth = con->ops->get_authorizer(con, &auth_proto, con->v1.auth_retry);
 	if (IS_ERR(auth))
 		return PTR_ERR(auth);
 
-	con->auth = auth;
-	con->out_connect.authorizer_protocol = cpu_to_le32(auth_proto);
-	con->out_connect.authorizer_len = cpu_to_le32(auth->authorizer_buf_len);
+	con->v1.auth = auth;
+	con->v1.out_connect.authorizer_protocol = cpu_to_le32(auth_proto);
+	con->v1.out_connect.authorizer_len =
+		cpu_to_le32(auth->authorizer_buf_len);
 	return 0;
 }
 
@@ -357,18 +357,19 @@ static void prepare_write_banner(struct ceph_connection *con)
 	con_out_kvec_add(con, sizeof (con->msgr->my_enc_addr),
 					&con->msgr->my_enc_addr);
 
-	con->out_more = 0;
+	con->v1.out_more = 0;
 	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
 }
 
 static void __prepare_write_connect(struct ceph_connection *con)
 {
-	con_out_kvec_add(con, sizeof(con->out_connect), &con->out_connect);
-	if (con->auth)
-		con_out_kvec_add(con, con->auth->authorizer_buf_len,
-				 con->auth->authorizer_buf);
+	con_out_kvec_add(con, sizeof(con->v1.out_connect),
+			 &con->v1.out_connect);
+	if (con->v1.auth)
+		con_out_kvec_add(con, con->v1.auth->authorizer_buf_len,
+				 con->v1.auth->authorizer_buf);
 
-	con->out_more = 0;
+	con->v1.out_more = 0;
 	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
 }
 
@@ -393,15 +394,15 @@ static int prepare_write_connect(struct ceph_connection *con)
 	}
 
 	dout("prepare_write_connect %p cseq=%d gseq=%d proto=%d\n", con,
-	     con->connect_seq, global_seq, proto);
+	     con->v1.connect_seq, global_seq, proto);
 
-	con->out_connect.features =
-	    cpu_to_le64(from_msgr(con->msgr)->supported_features);
-	con->out_connect.host_type = cpu_to_le32(CEPH_ENTITY_TYPE_CLIENT);
-	con->out_connect.connect_seq = cpu_to_le32(con->connect_seq);
-	con->out_connect.global_seq = cpu_to_le32(global_seq);
-	con->out_connect.protocol_version = cpu_to_le32(proto);
-	con->out_connect.flags = 0;
+	con->v1.out_connect.features =
+		cpu_to_le64(from_msgr(con->msgr)->supported_features);
+	con->v1.out_connect.host_type = cpu_to_le32(CEPH_ENTITY_TYPE_CLIENT);
+	con->v1.out_connect.connect_seq = cpu_to_le32(con->v1.connect_seq);
+	con->v1.out_connect.global_seq = cpu_to_le32(global_seq);
+	con->v1.out_connect.protocol_version = cpu_to_le32(proto);
+	con->v1.out_connect.flags = 0;
 
 	ret = get_connect_authorizer(con);
 	if (ret)
@@ -421,35 +422,36 @@ static int write_partial_kvec(struct ceph_connection *con)
 {
 	int ret;
 
-	dout("write_partial_kvec %p %d left\n", con, con->out_kvec_bytes);
-	while (con->out_kvec_bytes > 0) {
-		ret = ceph_tcp_sendmsg(con->sock, con->out_kvec_cur,
-				       con->out_kvec_left, con->out_kvec_bytes,
-				       con->out_more);
+	dout("write_partial_kvec %p %d left\n", con, con->v1.out_kvec_bytes);
+	while (con->v1.out_kvec_bytes > 0) {
+		ret = ceph_tcp_sendmsg(con->sock, con->v1.out_kvec_cur,
+				       con->v1.out_kvec_left,
+				       con->v1.out_kvec_bytes,
+				       con->v1.out_more);
 		if (ret <= 0)
 			goto out;
-		con->out_kvec_bytes -= ret;
-		if (con->out_kvec_bytes == 0)
+		con->v1.out_kvec_bytes -= ret;
+		if (!con->v1.out_kvec_bytes)
 			break;            /* done */
 
 		/* account for full iov entries consumed */
-		while (ret >= con->out_kvec_cur->iov_len) {
-			BUG_ON(!con->out_kvec_left);
-			ret -= con->out_kvec_cur->iov_len;
-			con->out_kvec_cur++;
-			con->out_kvec_left--;
+		while (ret >= con->v1.out_kvec_cur->iov_len) {
+			BUG_ON(!con->v1.out_kvec_left);
+			ret -= con->v1.out_kvec_cur->iov_len;
+			con->v1.out_kvec_cur++;
+			con->v1.out_kvec_left--;
 		}
 		/* and for a partially-consumed entry */
 		if (ret) {
-			con->out_kvec_cur->iov_len -= ret;
-			con->out_kvec_cur->iov_base += ret;
+			con->v1.out_kvec_cur->iov_len -= ret;
+			con->v1.out_kvec_cur->iov_base += ret;
 		}
 	}
-	con->out_kvec_left = 0;
+	con->v1.out_kvec_left = 0;
 	ret = 1;
 out:
 	dout("write_partial_kvec %p %d left in %d kvecs ret = %d\n", con,
-	     con->out_kvec_bytes, con->out_kvec_left, ret);
+	     con->v1.out_kvec_bytes, con->v1.out_kvec_left, ret);
 	return ret;  /* done! */
 }
 
@@ -530,17 +532,17 @@ static int write_partial_skip(struct ceph_connection *con)
 	int more = MSG_MORE | MSG_SENDPAGE_NOTLAST;
 	int ret;
 
-	dout("%s %p %d left\n", __func__, con, con->out_skip);
-	while (con->out_skip > 0) {
-		size_t size = min(con->out_skip, (int) PAGE_SIZE);
+	dout("%s %p %d left\n", __func__, con, con->v1.out_skip);
+	while (con->v1.out_skip > 0) {
+		size_t size = min(con->v1.out_skip, (int)PAGE_SIZE);
 
-		if (size == con->out_skip)
+		if (size == con->v1.out_skip)
 			more = MSG_MORE;
 		ret = ceph_tcp_sendpage(con->sock, ceph_zero_page, 0, size,
 					more);
 		if (ret <= 0)
 			goto out;
-		con->out_skip -= ret;
+		con->v1.out_skip -= ret;
 	}
 	ret = 1;
 out:
@@ -553,39 +555,39 @@ out:
 static void prepare_read_banner(struct ceph_connection *con)
 {
 	dout("prepare_read_banner %p\n", con);
-	con->in_base_pos = 0;
+	con->v1.in_base_pos = 0;
 }
 
 static void prepare_read_connect(struct ceph_connection *con)
 {
 	dout("prepare_read_connect %p\n", con);
-	con->in_base_pos = 0;
+	con->v1.in_base_pos = 0;
 }
 
 static void prepare_read_ack(struct ceph_connection *con)
 {
 	dout("prepare_read_ack %p\n", con);
-	con->in_base_pos = 0;
+	con->v1.in_base_pos = 0;
 }
 
 static void prepare_read_seq(struct ceph_connection *con)
 {
 	dout("prepare_read_seq %p\n", con);
-	con->in_base_pos = 0;
-	con->in_tag = CEPH_MSGR_TAG_SEQ;
+	con->v1.in_base_pos = 0;
+	con->v1.in_tag = CEPH_MSGR_TAG_SEQ;
 }
 
 static void prepare_read_tag(struct ceph_connection *con)
 {
 	dout("prepare_read_tag %p\n", con);
-	con->in_base_pos = 0;
-	con->in_tag = CEPH_MSGR_TAG_READY;
+	con->v1.in_base_pos = 0;
+	con->v1.in_tag = CEPH_MSGR_TAG_READY;
 }
 
 static void prepare_read_keepalive_ack(struct ceph_connection *con)
 {
 	dout("prepare_read_keepalive_ack %p\n", con);
-	con->in_base_pos = 0;
+	con->v1.in_base_pos = 0;
 }
 
 /*
@@ -595,7 +597,7 @@ static int prepare_read_message(struct ceph_connection *con)
 {
 	dout("prepare_read_message %p\n", con);
 	BUG_ON(con->in_msg != NULL);
-	con->in_base_pos = 0;
+	con->v1.in_base_pos = 0;
 	con->in_front_crc = con->in_middle_crc = con->in_data_crc = 0;
 	return 0;
 }
@@ -603,13 +605,13 @@ static int prepare_read_message(struct ceph_connection *con)
 static int read_partial(struct ceph_connection *con,
 			int end, int size, void *object)
 {
-	while (con->in_base_pos < end) {
-		int left = end - con->in_base_pos;
+	while (con->v1.in_base_pos < end) {
+		int left = end - con->v1.in_base_pos;
 		int have = size - left;
 		int ret = ceph_tcp_recvmsg(con->sock, object + have, left);
 		if (ret <= 0)
 			return ret;
-		con->in_base_pos += ret;
+		con->v1.in_base_pos += ret;
 	}
 	return 1;
 }
@@ -623,28 +625,28 @@ static int read_partial_banner(struct ceph_connection *con)
 	int end;
 	int ret;
 
-	dout("read_partial_banner %p at %d\n", con, con->in_base_pos);
+	dout("read_partial_banner %p at %d\n", con, con->v1.in_base_pos);
 
 	/* peer's banner */
 	size = strlen(CEPH_BANNER);
 	end = size;
-	ret = read_partial(con, end, size, con->in_banner);
+	ret = read_partial(con, end, size, con->v1.in_banner);
 	if (ret <= 0)
 		goto out;
 
-	size = sizeof (con->actual_peer_addr);
+	size = sizeof(con->v1.actual_peer_addr);
 	end += size;
-	ret = read_partial(con, end, size, &con->actual_peer_addr);
+	ret = read_partial(con, end, size, &con->v1.actual_peer_addr);
 	if (ret <= 0)
 		goto out;
-	ceph_decode_banner_addr(&con->actual_peer_addr);
+	ceph_decode_banner_addr(&con->v1.actual_peer_addr);
 
-	size = sizeof (con->peer_addr_for_me);
+	size = sizeof(con->v1.peer_addr_for_me);
 	end += size;
-	ret = read_partial(con, end, size, &con->peer_addr_for_me);
+	ret = read_partial(con, end, size, &con->v1.peer_addr_for_me);
 	if (ret <= 0)
 		goto out;
-	ceph_decode_banner_addr(&con->peer_addr_for_me);
+	ceph_decode_banner_addr(&con->v1.peer_addr_for_me);
 
 out:
 	return ret;
@@ -656,34 +658,34 @@ static int read_partial_connect(struct ceph_connection *con)
 	int end;
 	int ret;
 
-	dout("read_partial_connect %p at %d\n", con, con->in_base_pos);
+	dout("read_partial_connect %p at %d\n", con, con->v1.in_base_pos);
 
-	size = sizeof (con->in_reply);
+	size = sizeof(con->v1.in_reply);
 	end = size;
-	ret = read_partial(con, end, size, &con->in_reply);
+	ret = read_partial(con, end, size, &con->v1.in_reply);
 	if (ret <= 0)
 		goto out;
 
-	if (con->auth) {
-		size = le32_to_cpu(con->in_reply.authorizer_len);
-		if (size > con->auth->authorizer_reply_buf_len) {
+	if (con->v1.auth) {
+		size = le32_to_cpu(con->v1.in_reply.authorizer_len);
+		if (size > con->v1.auth->authorizer_reply_buf_len) {
 			pr_err("authorizer reply too big: %d > %zu\n", size,
-			       con->auth->authorizer_reply_buf_len);
+			       con->v1.auth->authorizer_reply_buf_len);
 			ret = -EINVAL;
 			goto out;
 		}
 
 		end += size;
 		ret = read_partial(con, end, size,
-				   con->auth->authorizer_reply_buf);
+				   con->v1.auth->authorizer_reply_buf);
 		if (ret <= 0)
 			goto out;
 	}
 
 	dout("read_partial_connect %p tag %d, con_seq = %u, g_seq = %u\n",
-	     con, (int)con->in_reply.tag,
-	     le32_to_cpu(con->in_reply.connect_seq),
-	     le32_to_cpu(con->in_reply.global_seq));
+	     con, con->v1.in_reply.tag,
+	     le32_to_cpu(con->v1.in_reply.connect_seq),
+	     le32_to_cpu(con->v1.in_reply.global_seq));
 out:
 	return ret;
 }
@@ -693,7 +695,7 @@ out:
  */
 static int verify_hello(struct ceph_connection *con)
 {
-	if (memcmp(con->in_banner, CEPH_BANNER, strlen(CEPH_BANNER))) {
+	if (memcmp(con->v1.in_banner, CEPH_BANNER, strlen(CEPH_BANNER))) {
 		pr_err("connect to %s got bad banner\n",
 		       ceph_pr_addr(&con->peer_addr));
 		con->error_msg = "protocol error, bad banner";
@@ -716,15 +718,15 @@ static int process_banner(struct ceph_connection *con)
 	 * end may not yet know their ip address, so if it's 0.0.0.0, give
 	 * them the benefit of the doubt.
 	 */
-	if (memcmp(&con->peer_addr, &con->actual_peer_addr,
+	if (memcmp(&con->peer_addr, &con->v1.actual_peer_addr,
 		   sizeof(con->peer_addr)) != 0 &&
-	    !(ceph_addr_is_blank(&con->actual_peer_addr) &&
-	      con->actual_peer_addr.nonce == con->peer_addr.nonce)) {
+	    !(ceph_addr_is_blank(&con->v1.actual_peer_addr) &&
+	      con->v1.actual_peer_addr.nonce == con->peer_addr.nonce)) {
 		pr_warn("wrong peer, want %s/%u, got %s/%u\n",
 			ceph_pr_addr(&con->peer_addr),
 			le32_to_cpu(con->peer_addr.nonce),
-			ceph_pr_addr(&con->actual_peer_addr),
-			le32_to_cpu(con->actual_peer_addr.nonce));
+			ceph_pr_addr(&con->v1.actual_peer_addr),
+			le32_to_cpu(con->v1.actual_peer_addr.nonce));
 		con->error_msg = "wrong peer at address";
 		return -1;
 	}
@@ -734,8 +736,8 @@ static int process_banner(struct ceph_connection *con)
 	 */
 	if (ceph_addr_is_blank(my_addr)) {
 		memcpy(&my_addr->in_addr,
-		       &con->peer_addr_for_me.in_addr,
-		       sizeof(con->peer_addr_for_me.in_addr));
+		       &con->v1.peer_addr_for_me.in_addr,
+		       sizeof(con->v1.peer_addr_for_me.in_addr));
 		ceph_addr_set_port(my_addr, 0);
 		ceph_encode_my_addr(con->msgr);
 		dout("process_banner learned my addr is %s\n",
@@ -749,13 +751,13 @@ static int process_connect(struct ceph_connection *con)
 {
 	u64 sup_feat = from_msgr(con->msgr)->supported_features;
 	u64 req_feat = from_msgr(con->msgr)->required_features;
-	u64 server_feat = le64_to_cpu(con->in_reply.features);
+	u64 server_feat = le64_to_cpu(con->v1.in_reply.features);
 	int ret;
 
-	dout("process_connect on %p tag %d\n", con, (int)con->in_tag);
+	dout("process_connect on %p tag %d\n", con, con->v1.in_tag);
 
-	if (con->auth) {
-		int len = le32_to_cpu(con->in_reply.authorizer_len);
+	if (con->v1.auth) {
+		int len = le32_to_cpu(con->v1.in_reply.authorizer_len);
 
 		/*
 		 * Any connection that defines ->get_authorizer()
@@ -764,9 +766,10 @@ static int process_connect(struct ceph_connection *con)
 		 *
 		 * See get_connect_authorizer().
 		 */
-		if (con->in_reply.tag == CEPH_MSGR_TAG_CHALLENGE_AUTHORIZER) {
+		if (con->v1.in_reply.tag ==
+				CEPH_MSGR_TAG_CHALLENGE_AUTHORIZER) {
 			ret = con->ops->add_authorizer_challenge(
-				    con, con->auth->authorizer_reply_buf, len);
+				con, con->v1.auth->authorizer_reply_buf, len);
 			if (ret < 0)
 				return ret;
 
@@ -785,7 +788,7 @@ static int process_connect(struct ceph_connection *con)
 		}
 	}
 
-	switch (con->in_reply.tag) {
+	switch (con->v1.in_reply.tag) {
 	case CEPH_MSGR_TAG_FEATURES:
 		pr_err("%s%lld %s feature set mismatch,"
 		       " my %llx < server's %llx, missing %llx\n",
@@ -800,16 +803,16 @@ static int process_connect(struct ceph_connection *con)
 		       " my %d != server's %d\n",
 		       ENTITY_NAME(con->peer_name),
 		       ceph_pr_addr(&con->peer_addr),
-		       le32_to_cpu(con->out_connect.protocol_version),
-		       le32_to_cpu(con->in_reply.protocol_version));
+		       le32_to_cpu(con->v1.out_connect.protocol_version),
+		       le32_to_cpu(con->v1.in_reply.protocol_version));
 		con->error_msg = "protocol version mismatch";
 		return -1;
 
 	case CEPH_MSGR_TAG_BADAUTHORIZER:
-		con->auth_retry++;
+		con->v1.auth_retry++;
 		dout("process_connect %p got BADAUTHORIZER attempt %d\n", con,
-		     con->auth_retry);
-		if (con->auth_retry == 2) {
+		     con->v1.auth_retry);
+		if (con->v1.auth_retry == 2) {
 			con->error_msg = "connect authorization failure";
 			return -1;
 		}
@@ -829,7 +832,7 @@ static int process_connect(struct ceph_connection *con)
 		 * dropped messages.
 		 */
 		dout("process_connect got RESET peer seq %u\n",
-		     le32_to_cpu(con->in_reply.connect_seq));
+		     le32_to_cpu(con->v1.in_reply.connect_seq));
 		pr_info("%s%lld %s session reset\n",
 			ENTITY_NAME(con->peer_name),
 			ceph_pr_addr(&con->peer_addr));
@@ -855,9 +858,9 @@ static int process_connect(struct ceph_connection *con)
 		 * again with a larger value.
 		 */
 		dout("process_connect got RETRY_SESSION my seq %u, peer %u\n",
-		     le32_to_cpu(con->out_connect.connect_seq),
-		     le32_to_cpu(con->in_reply.connect_seq));
-		con->connect_seq = le32_to_cpu(con->in_reply.connect_seq);
+		     le32_to_cpu(con->v1.out_connect.connect_seq),
+		     le32_to_cpu(con->v1.in_reply.connect_seq));
+		con->v1.connect_seq = le32_to_cpu(con->v1.in_reply.connect_seq);
 		con_out_kvec_reset(con);
 		ret = prepare_write_connect(con);
 		if (ret < 0)
@@ -871,10 +874,10 @@ static int process_connect(struct ceph_connection *con)
 		 * again with a larger value.
 		 */
 		dout("process_connect got RETRY_GLOBAL my %u peer_gseq %u\n",
-		     con->peer_global_seq,
-		     le32_to_cpu(con->in_reply.global_seq));
+		     con->v1.peer_global_seq,
+		     le32_to_cpu(con->v1.in_reply.global_seq));
 		ceph_get_global_seq(con->msgr,
-				    le32_to_cpu(con->in_reply.global_seq));
+				    le32_to_cpu(con->v1.in_reply.global_seq));
 		con_out_kvec_reset(con);
 		ret = prepare_write_connect(con);
 		if (ret < 0)
@@ -896,23 +899,24 @@ static int process_connect(struct ceph_connection *con)
 
 		WARN_ON(con->state != CEPH_CON_S_V1_CONNECT_MSG);
 		con->state = CEPH_CON_S_OPEN;
-		con->auth_retry = 0;    /* we authenticated; clear flag */
-		con->peer_global_seq = le32_to_cpu(con->in_reply.global_seq);
-		con->connect_seq++;
+		con->v1.auth_retry = 0;    /* we authenticated; clear flag */
+		con->v1.peer_global_seq =
+			le32_to_cpu(con->v1.in_reply.global_seq);
+		con->v1.connect_seq++;
 		con->peer_features = server_feat;
 		dout("process_connect got READY gseq %d cseq %d (%d)\n",
-		     con->peer_global_seq,
-		     le32_to_cpu(con->in_reply.connect_seq),
-		     con->connect_seq);
-		WARN_ON(con->connect_seq !=
-			le32_to_cpu(con->in_reply.connect_seq));
+		     con->v1.peer_global_seq,
+		     le32_to_cpu(con->v1.in_reply.connect_seq),
+		     con->v1.connect_seq);
+		WARN_ON(con->v1.connect_seq !=
+			le32_to_cpu(con->v1.in_reply.connect_seq));
 
-		if (con->in_reply.flags & CEPH_MSG_CONNECT_LOSSY)
+		if (con->v1.in_reply.flags & CEPH_MSG_CONNECT_LOSSY)
 			ceph_con_flag_set(con, CEPH_CON_F_LOSSYTX);
 
 		con->delay = 0;      /* reset backoff memory */
 
-		if (con->in_reply.tag == CEPH_MSGR_TAG_SEQ) {
+		if (con->v1.in_reply.tag == CEPH_MSGR_TAG_SEQ) {
 			prepare_write_seq(con);
 			prepare_read_seq(con);
 		} else {
@@ -942,10 +946,10 @@ static int process_connect(struct ceph_connection *con)
  */
 static int read_partial_ack(struct ceph_connection *con)
 {
-	int size = sizeof (con->in_temp_ack);
+	int size = sizeof(con->v1.in_temp_ack);
 	int end = size;
 
-	return read_partial(con, end, size, &con->in_temp_ack);
+	return read_partial(con, end, size, &con->v1.in_temp_ack);
 }
 
 /*
@@ -953,9 +957,9 @@ static int read_partial_ack(struct ceph_connection *con)
  */
 static void process_ack(struct ceph_connection *con)
 {
-	u64 ack = le64_to_cpu(con->in_temp_ack);
+	u64 ack = le64_to_cpu(con->v1.in_temp_ack);
 
-	if (con->in_tag == CEPH_MSGR_TAG_ACK)
+	if (con->v1.in_tag == CEPH_MSGR_TAG_ACK)
 		ceph_con_discard_sent(con, ack);
 	else
 		ceph_con_discard_requeued(con, ack);
@@ -1045,39 +1049,39 @@ static int read_partial_message(struct ceph_connection *con)
 	dout("read_partial_message con %p msg %p\n", con, m);
 
 	/* header */
-	size = sizeof (con->in_hdr);
+	size = sizeof(con->v1.in_hdr);
 	end = size;
-	ret = read_partial(con, end, size, &con->in_hdr);
+	ret = read_partial(con, end, size, &con->v1.in_hdr);
 	if (ret <= 0)
 		return ret;
 
-	crc = crc32c(0, &con->in_hdr, offsetof(struct ceph_msg_header, crc));
-	if (cpu_to_le32(crc) != con->in_hdr.crc) {
+	crc = crc32c(0, &con->v1.in_hdr, offsetof(struct ceph_msg_header, crc));
+	if (cpu_to_le32(crc) != con->v1.in_hdr.crc) {
 		pr_err("read_partial_message bad hdr crc %u != expected %u\n",
-		       crc, con->in_hdr.crc);
+		       crc, con->v1.in_hdr.crc);
 		return -EBADMSG;
 	}
 
-	front_len = le32_to_cpu(con->in_hdr.front_len);
+	front_len = le32_to_cpu(con->v1.in_hdr.front_len);
 	if (front_len > CEPH_MSG_MAX_FRONT_LEN)
 		return -EIO;
-	middle_len = le32_to_cpu(con->in_hdr.middle_len);
+	middle_len = le32_to_cpu(con->v1.in_hdr.middle_len);
 	if (middle_len > CEPH_MSG_MAX_MIDDLE_LEN)
 		return -EIO;
-	data_len = le32_to_cpu(con->in_hdr.data_len);
+	data_len = le32_to_cpu(con->v1.in_hdr.data_len);
 	if (data_len > CEPH_MSG_MAX_DATA_LEN)
 		return -EIO;
 
 	/* verify seq# */
-	seq = le64_to_cpu(con->in_hdr.seq);
+	seq = le64_to_cpu(con->v1.in_hdr.seq);
 	if ((s64)seq - (s64)con->in_seq < 1) {
 		pr_info("skipping %s%lld %s seq %lld expected %lld\n",
 			ENTITY_NAME(con->peer_name),
 			ceph_pr_addr(&con->peer_addr),
 			seq, con->in_seq + 1);
-		con->in_base_pos = -front_len - middle_len - data_len -
-			sizeof_footer(con);
-		con->in_tag = CEPH_MSGR_TAG_READY;
+		con->v1.in_base_pos = -front_len - middle_len - data_len -
+				      sizeof_footer(con);
+		con->v1.in_tag = CEPH_MSGR_TAG_READY;
 		return 1;
 	} else if ((s64)seq - (s64)con->in_seq > 1) {
 		pr_err("read_partial_message bad seq %lld expected %lld\n",
@@ -1090,9 +1094,9 @@ static int read_partial_message(struct ceph_connection *con)
 	if (!con->in_msg) {
 		int skip = 0;
 
-		dout("got hdr type %d front %d data %d\n", con->in_hdr.type,
+		dout("got hdr type %d front %d data %d\n", con->v1.in_hdr.type,
 		     front_len, data_len);
-		ret = ceph_con_in_msg_alloc(con, &con->in_hdr, &skip);
+		ret = ceph_con_in_msg_alloc(con, &con->v1.in_hdr, &skip);
 		if (ret < 0)
 			return ret;
 
@@ -1100,9 +1104,9 @@ static int read_partial_message(struct ceph_connection *con)
 		if (skip) {
 			/* skip this message */
 			dout("alloc_msg said skip message\n");
-			con->in_base_pos = -front_len - middle_len - data_len -
-				sizeof_footer(con);
-			con->in_tag = CEPH_MSGR_TAG_READY;
+			con->v1.in_base_pos = -front_len - middle_len -
+					      data_len - sizeof_footer(con);
+			con->v1.in_tag = CEPH_MSGR_TAG_READY;
 			con->in_seq++;
 			return 1;
 		}
@@ -1214,8 +1218,8 @@ more:
 
 	BUG_ON(!con->sock);
 
-	dout("try_read tag %d in_base_pos %d\n", (int)con->in_tag,
-	     con->in_base_pos);
+	dout("try_read tag %d in_base_pos %d\n", con->v1.in_tag,
+	     con->v1.in_base_pos);
 
 	if (con->state == CEPH_CON_S_V1_BANNER) {
 		ret = read_partial_banner(con);
@@ -1253,27 +1257,27 @@ more:
 
 	WARN_ON(con->state != CEPH_CON_S_OPEN);
 
-	if (con->in_base_pos < 0) {
+	if (con->v1.in_base_pos < 0) {
 		/*
 		 * skipping + discarding content.
 		 */
-		ret = ceph_tcp_recvmsg(con->sock, NULL, -con->in_base_pos);
+		ret = ceph_tcp_recvmsg(con->sock, NULL, -con->v1.in_base_pos);
 		if (ret <= 0)
 			goto out;
-		dout("skipped %d / %d bytes\n", ret, -con->in_base_pos);
-		con->in_base_pos += ret;
-		if (con->in_base_pos)
+		dout("skipped %d / %d bytes\n", ret, -con->v1.in_base_pos);
+		con->v1.in_base_pos += ret;
+		if (con->v1.in_base_pos)
 			goto more;
 	}
-	if (con->in_tag == CEPH_MSGR_TAG_READY) {
+	if (con->v1.in_tag == CEPH_MSGR_TAG_READY) {
 		/*
 		 * what's next?
 		 */
-		ret = ceph_tcp_recvmsg(con->sock, &con->in_tag, 1);
+		ret = ceph_tcp_recvmsg(con->sock, &con->v1.in_tag, 1);
 		if (ret <= 0)
 			goto out;
-		dout("try_read got tag %d\n", (int)con->in_tag);
-		switch (con->in_tag) {
+		dout("try_read got tag %d\n", con->v1.in_tag);
+		switch (con->v1.in_tag) {
 		case CEPH_MSGR_TAG_MSG:
 			prepare_read_message(con);
 			break;
@@ -1291,7 +1295,7 @@ more:
 			goto bad_tag;
 		}
 	}
-	if (con->in_tag == CEPH_MSGR_TAG_MSG) {
+	if (con->v1.in_tag == CEPH_MSGR_TAG_MSG) {
 		ret = read_partial_message(con);
 		if (ret <= 0) {
 			switch (ret) {
@@ -1307,15 +1311,15 @@ more:
 			}
 			goto out;
 		}
-		if (con->in_tag == CEPH_MSGR_TAG_READY)
+		if (con->v1.in_tag == CEPH_MSGR_TAG_READY)
 			goto more;
 		ceph_con_process_message(con);
 		if (con->state == CEPH_CON_S_OPEN)
 			prepare_read_tag(con);
 		goto more;
 	}
-	if (con->in_tag == CEPH_MSGR_TAG_ACK ||
-	    con->in_tag == CEPH_MSGR_TAG_SEQ) {
+	if (con->v1.in_tag == CEPH_MSGR_TAG_ACK ||
+	    con->v1.in_tag == CEPH_MSGR_TAG_SEQ) {
 		/*
 		 * the final handshake seq exchange is semantically
 		 * equivalent to an ACK
@@ -1326,7 +1330,7 @@ more:
 		process_ack(con);
 		goto more;
 	}
-	if (con->in_tag == CEPH_MSGR_TAG_KEEPALIVE2_ACK) {
+	if (con->v1.in_tag == CEPH_MSGR_TAG_KEEPALIVE2_ACK) {
 		ret = read_keepalive_ack(con);
 		if (ret <= 0)
 			goto out;
@@ -1338,7 +1342,7 @@ out:
 	return ret;
 
 bad_tag:
-	pr_err("try_read bad con->in_tag = %d\n", (int)con->in_tag);
+	pr_err("try_read bad tag %d\n", con->v1.in_tag);
 	con->error_msg = "protocol error, garbage tag";
 	ret = -1;
 	goto out;
@@ -1369,7 +1373,7 @@ int ceph_con_v1_try_write(struct ceph_connection *con)
 		prepare_read_banner(con);
 
 		BUG_ON(con->in_msg);
-		con->in_tag = CEPH_MSGR_TAG_READY;
+		con->v1.in_tag = CEPH_MSGR_TAG_READY;
 		dout("try_write initiating connect on %p new state %d\n",
 		     con, con->state);
 		ret = ceph_tcp_connect(con);
@@ -1380,16 +1384,16 @@ int ceph_con_v1_try_write(struct ceph_connection *con)
 	}
 
 more:
-	dout("try_write out_kvec_bytes %d\n", con->out_kvec_bytes);
+	dout("try_write out_kvec_bytes %d\n", con->v1.out_kvec_bytes);
 	BUG_ON(!con->sock);
 
 	/* kvec data queued? */
-	if (con->out_kvec_left) {
+	if (con->v1.out_kvec_left) {
 		ret = write_partial_kvec(con);
 		if (ret <= 0)
 			goto out;
 	}
-	if (con->out_skip) {
+	if (con->v1.out_skip) {
 		ret = write_partial_skip(con);
 		if (ret <= 0)
 			goto out;
@@ -1397,7 +1401,7 @@ more:
 
 	/* msg pages? */
 	if (con->out_msg) {
-		if (con->out_msg_done) {
+		if (con->v1.out_msg_done) {
 			ceph_msg_put(con->out_msg);
 			con->out_msg = NULL;   /* we're done with this one */
 			goto do_next;
@@ -1446,57 +1450,57 @@ void ceph_con_v1_revoke(struct ceph_connection *con)
 {
 	struct ceph_msg *msg = con->out_msg;
 
-	WARN_ON(con->out_skip);
+	WARN_ON(con->v1.out_skip);
 	/* footer */
-	if (con->out_msg_done) {
-		con->out_skip += con_out_kvec_skip(con);
+	if (con->v1.out_msg_done) {
+		con->v1.out_skip += con_out_kvec_skip(con);
 	} else {
 		WARN_ON(!msg->data_length);
-		con->out_skip += sizeof_footer(con);
+		con->v1.out_skip += sizeof_footer(con);
 	}
 	/* data, middle, front */
 	if (msg->data_length)
-		con->out_skip += msg->cursor.total_resid;
+		con->v1.out_skip += msg->cursor.total_resid;
 	if (msg->middle)
-		con->out_skip += con_out_kvec_skip(con);
-	con->out_skip += con_out_kvec_skip(con);
+		con->v1.out_skip += con_out_kvec_skip(con);
+	con->v1.out_skip += con_out_kvec_skip(con);
 
 	dout("%s con %p out_kvec_bytes %d out_skip %d\n", __func__, con,
-	     con->out_kvec_bytes, con->out_skip);
+	     con->v1.out_kvec_bytes, con->v1.out_skip);
 }
 
 void ceph_con_v1_revoke_incoming(struct ceph_connection *con)
 {
-	unsigned int front_len = le32_to_cpu(con->in_hdr.front_len);
-	unsigned int middle_len = le32_to_cpu(con->in_hdr.middle_len);
-	unsigned int data_len = le32_to_cpu(con->in_hdr.data_len);
+	unsigned int front_len = le32_to_cpu(con->v1.in_hdr.front_len);
+	unsigned int middle_len = le32_to_cpu(con->v1.in_hdr.middle_len);
+	unsigned int data_len = le32_to_cpu(con->v1.in_hdr.data_len);
 
 	/* skip rest of message */
-	con->in_base_pos = con->in_base_pos -
+	con->v1.in_base_pos = con->v1.in_base_pos -
 			sizeof(struct ceph_msg_header) -
 			front_len -
 			middle_len -
 			data_len -
 			sizeof(struct ceph_msg_footer);
 
-	con->in_tag = CEPH_MSGR_TAG_READY;
+	con->v1.in_tag = CEPH_MSGR_TAG_READY;
 	con->in_seq++;
 
-	dout("%s con %p in_base_pos %d\n", __func__, con, con->in_base_pos);
+	dout("%s con %p in_base_pos %d\n", __func__, con, con->v1.in_base_pos);
 }
 
 bool ceph_con_v1_opened(struct ceph_connection *con)
 {
-	return con->connect_seq;
+	return con->v1.connect_seq;
 }
 
 void ceph_con_v1_reset_session(struct ceph_connection *con)
 {
-	con->connect_seq = 0;
-	con->peer_global_seq = 0;
+	con->v1.connect_seq = 0;
+	con->v1.peer_global_seq = 0;
 }
 
 void ceph_con_v1_reset_protocol(struct ceph_connection *con)
 {
-	con->out_skip = 0;
+	con->v1.out_skip = 0;
 }
-- 
cgit v1.2.3


From 285ea34fc876aa0a2c5e65d310c4a41269e2e5f2 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Mon, 26 Oct 2020 16:47:20 +0100
Subject: libceph, ceph: incorporate nautilus cephx changes

- request service tickets together with auth ticket.  Currently we get
  auth ticket via CEPHX_GET_AUTH_SESSION_KEY op and then request service
  tickets via CEPHX_GET_PRINCIPAL_SESSION_KEY op in a separate message.
  Since nautilus, desired service tickets are shared togther with auth
  ticket in CEPHX_GET_AUTH_SESSION_KEY reply.

- propagate session key and connection secret, if any.  In preparation
  for msgr2, update handle_reply() and verify_authorizer_reply() auth
  ops to propagate session key and connection secret.  Since nautilus,
  if secure mode is negotiated, connection secret is shared either in
  CEPHX_GET_AUTH_SESSION_KEY reply (for mons) or in a final authorizer
  reply (for osds and mdses).

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/mds_client.c       |   5 +-
 include/linux/ceph/auth.h  |  16 +++-
 net/ceph/auth.c            |  12 ++-
 net/ceph/auth_none.c       |   4 +-
 net/ceph/auth_x.c          | 215 ++++++++++++++++++++++++++++++++++++---------
 net/ceph/auth_x_protocol.h |   3 +-
 net/ceph/crypto.h          |   3 +
 net/ceph/osd_client.c      |   5 +-
 8 files changed, 210 insertions(+), 53 deletions(-)

(limited to 'include/linux')

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index a256d95ec99a..278fe67e2617 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -5178,8 +5178,11 @@ static int verify_authorizer_reply(struct ceph_connection *con)
 	struct ceph_mds_session *s = con->private;
 	struct ceph_mds_client *mdsc = s->s_mdsc;
 	struct ceph_auth_client *ac = mdsc->fsc->client->monc.auth;
+	struct ceph_auth_handshake *auth = &s->s_auth;
 
-	return ceph_auth_verify_authorizer_reply(ac, s->s_auth.authorizer);
+	return ceph_auth_verify_authorizer_reply(ac, auth->authorizer,
+		auth->authorizer_reply_buf, auth->authorizer_reply_buf_len,
+		NULL, NULL, NULL, NULL);
 }
 
 static int invalidate_authorizer(struct ceph_connection *con)
diff --git a/include/linux/ceph/auth.h b/include/linux/ceph/auth.h
index 6728c2ee0205..d9e7d0bcdaf1 100644
--- a/include/linux/ceph/auth.h
+++ b/include/linux/ceph/auth.h
@@ -53,7 +53,9 @@ struct ceph_auth_client_ops {
 	 */
 	int (*build_request)(struct ceph_auth_client *ac, void *buf, void *end);
 	int (*handle_reply)(struct ceph_auth_client *ac, int result,
-			    void *buf, void *end);
+			    void *buf, void *end, u8 *session_key,
+			    int *session_key_len, u8 *con_secret,
+			    int *con_secret_len);
 
 	/*
 	 * Create authorizer for connecting to a service, and verify
@@ -69,7 +71,10 @@ struct ceph_auth_client_ops {
 					void *challenge_buf,
 					int challenge_buf_len);
 	int (*verify_authorizer_reply)(struct ceph_auth_client *ac,
-				       struct ceph_authorizer *a);
+				       struct ceph_authorizer *a,
+				       void *reply, int reply_len,
+				       u8 *session_key, int *session_key_len,
+				       u8 *con_secret, int *con_secret_len);
 	void (*invalidate_authorizer)(struct ceph_auth_client *ac,
 				      int peer_type);
 
@@ -126,8 +131,11 @@ int ceph_auth_add_authorizer_challenge(struct ceph_auth_client *ac,
 				       struct ceph_authorizer *a,
 				       void *challenge_buf,
 				       int challenge_buf_len);
-extern int ceph_auth_verify_authorizer_reply(struct ceph_auth_client *ac,
-					     struct ceph_authorizer *a);
+int ceph_auth_verify_authorizer_reply(struct ceph_auth_client *ac,
+				      struct ceph_authorizer *a,
+				      void *reply, int reply_len,
+				      u8 *session_key, int *session_key_len,
+				      u8 *con_secret, int *con_secret_len);
 extern void ceph_auth_invalidate_authorizer(struct ceph_auth_client *ac,
 					    int peer_type);
 
diff --git a/net/ceph/auth.c b/net/ceph/auth.c
index fbeee068ea14..40d3d95344d9 100644
--- a/net/ceph/auth.c
+++ b/net/ceph/auth.c
@@ -240,7 +240,8 @@ int ceph_handle_auth_reply(struct ceph_auth_client *ac,
 		ac->negotiating = false;
 	}
 
-	ret = ac->ops->handle_reply(ac, result, payload, payload_end);
+	ret = ac->ops->handle_reply(ac, result, payload, payload_end,
+				    NULL, NULL, NULL, NULL);
 	if (ret == -EAGAIN) {
 		ret = ceph_build_auth_request(ac, reply_buf, reply_len);
 	} else if (ret) {
@@ -332,13 +333,18 @@ int ceph_auth_add_authorizer_challenge(struct ceph_auth_client *ac,
 EXPORT_SYMBOL(ceph_auth_add_authorizer_challenge);
 
 int ceph_auth_verify_authorizer_reply(struct ceph_auth_client *ac,
-				      struct ceph_authorizer *a)
+				      struct ceph_authorizer *a,
+				      void *reply, int reply_len,
+				      u8 *session_key, int *session_key_len,
+				      u8 *con_secret, int *con_secret_len)
 {
 	int ret = 0;
 
 	mutex_lock(&ac->mutex);
 	if (ac->ops && ac->ops->verify_authorizer_reply)
-		ret = ac->ops->verify_authorizer_reply(ac, a);
+		ret = ac->ops->verify_authorizer_reply(ac, a,
+			reply, reply_len, session_key, session_key_len,
+			con_secret, con_secret_len);
 	mutex_unlock(&ac->mutex);
 	return ret;
 }
diff --git a/net/ceph/auth_none.c b/net/ceph/auth_none.c
index edb7042479ed..af8ae507e861 100644
--- a/net/ceph/auth_none.c
+++ b/net/ceph/auth_none.c
@@ -70,7 +70,9 @@ static int build_request(struct ceph_auth_client *ac, void *buf, void *end)
  * authenticate state, so nothing happens here.
  */
 static int handle_reply(struct ceph_auth_client *ac, int result,
-			void *buf, void *end)
+			void *buf, void *end, u8 *session_key,
+			int *session_key_len, u8 *con_secret,
+			int *con_secret_len)
 {
 	struct ceph_auth_none_info *xi = ac->private;
 
diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c
index 425508d4dafd..a265792642dc 100644
--- a/net/ceph/auth_x.c
+++ b/net/ceph/auth_x.c
@@ -269,22 +269,21 @@ out:
 
 static int ceph_x_proc_ticket_reply(struct ceph_auth_client *ac,
 				    struct ceph_crypto_key *secret,
-				    void *buf, void *end)
+				    void **p, void *end)
 {
-	void *p = buf;
 	u8 reply_struct_v;
 	u32 num;
 	int ret;
 
-	ceph_decode_8_safe(&p, end, reply_struct_v, bad);
+	ceph_decode_8_safe(p, end, reply_struct_v, bad);
 	if (reply_struct_v != 1)
 		return -EINVAL;
 
-	ceph_decode_32_safe(&p, end, num, bad);
+	ceph_decode_32_safe(p, end, num, bad);
 	dout("%d tickets\n", num);
 
 	while (num--) {
-		ret = process_one_ticket(ac, secret, &p, end);
+		ret = process_one_ticket(ac, secret, p, end);
 		if (ret)
 			return ret;
 	}
@@ -527,7 +526,7 @@ static int ceph_x_build_request(struct ceph_auth_client *ac,
 		if (ret < 0)
 			return ret;
 
-		auth->struct_v = 1;
+		auth->struct_v = 2;  /* nautilus+ */
 		auth->key = 0;
 		for (u = (u64 *)enc_buf; u + 1 <= (u64 *)(enc_buf + ret); u++)
 			auth->key ^= *(__le64 *)u;
@@ -540,6 +539,10 @@ static int ceph_x_build_request(struct ceph_auth_client *ac,
 		if (ret < 0)
 			return ret;
 
+		/* nautilus+: request service tickets at the same time */
+		need = ac->want_keys & ~CEPH_ENTITY_TYPE_AUTH;
+		WARN_ON(!need);
+		ceph_encode_32_safe(&p, end, need, e_range);
 		return p - buf;
 	}
 
@@ -566,8 +569,82 @@ e_range:
 	return -ERANGE;
 }
 
+static int handle_auth_session_key(struct ceph_auth_client *ac,
+				   void **p, void *end,
+				   u8 *session_key, int *session_key_len,
+				   u8 *con_secret, int *con_secret_len)
+{
+	struct ceph_x_info *xi = ac->private;
+	struct ceph_x_ticket_handler *th;
+	void *dp, *dend;
+	int len;
+	int ret;
+
+	/* AUTH ticket */
+	ret = ceph_x_proc_ticket_reply(ac, &xi->secret, p, end);
+	if (ret)
+		return ret;
+
+	if (*p == end) {
+		/* pre-nautilus (or didn't request service tickets!) */
+		WARN_ON(session_key || con_secret);
+		return 0;
+	}
+
+	th = get_ticket_handler(ac, CEPH_ENTITY_TYPE_AUTH);
+	if (IS_ERR(th))
+		return PTR_ERR(th);
+
+	if (session_key) {
+		memcpy(session_key, th->session_key.key, th->session_key.len);
+		*session_key_len = th->session_key.len;
+	}
+
+	/* connection secret */
+	ceph_decode_32_safe(p, end, len, e_inval);
+	dout("%s connection secret blob len %d\n", __func__, len);
+	if (len > 0) {
+		dp = *p + ceph_x_encrypt_offset();
+		ret = ceph_x_decrypt(&th->session_key, p, *p + len);
+		if (ret < 0)
+			return ret;
+
+		dout("%s decrypted %d bytes\n", __func__, ret);
+		dend = dp + ret;
+
+		ceph_decode_32_safe(&dp, dend, len, e_inval);
+		if (len > CEPH_MAX_CON_SECRET_LEN) {
+			pr_err("connection secret too big %d\n", len);
+			return -EINVAL;
+		}
+
+		dout("%s connection secret len %d\n", __func__, len);
+		if (con_secret) {
+			memcpy(con_secret, dp, len);
+			*con_secret_len = len;
+		}
+	}
+
+	/* service tickets */
+	ceph_decode_32_safe(p, end, len, e_inval);
+	dout("%s service tickets blob len %d\n", __func__, len);
+	if (len > 0) {
+		ret = ceph_x_proc_ticket_reply(ac, &th->session_key,
+					       p, *p + len);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+
+e_inval:
+	return -EINVAL;
+}
+
 static int ceph_x_handle_reply(struct ceph_auth_client *ac, int result,
-			       void *buf, void *end)
+			       void *buf, void *end,
+			       u8 *session_key, int *session_key_len,
+			       u8 *con_secret, int *con_secret_len)
 {
 	struct ceph_x_info *xi = ac->private;
 	struct ceph_x_ticket_handler *th;
@@ -599,8 +676,10 @@ static int ceph_x_handle_reply(struct ceph_auth_client *ac, int result,
 	dout("handle_reply op %d result %d\n", op, result);
 	switch (op) {
 	case CEPHX_GET_AUTH_SESSION_KEY:
-		/* verify auth key */
-		ret = ceph_x_proc_ticket_reply(ac, &xi->secret, p, end);
+		/* AUTH ticket + [connection secret] + service tickets */
+		ret = handle_auth_session_key(ac, &p, end, session_key,
+					      session_key_len, con_secret,
+					      con_secret_len);
 		break;
 
 	case CEPHX_GET_PRINCIPAL_SESSION_KEY:
@@ -608,7 +687,8 @@ static int ceph_x_handle_reply(struct ceph_auth_client *ac, int result,
 		if (IS_ERR(th))
 			return PTR_ERR(th);
 
-		ret = ceph_x_proc_ticket_reply(ac, &th->session_key, p, end);
+		/* service tickets */
+		ret = ceph_x_proc_ticket_reply(ac, &th->session_key, &p, end);
 		break;
 
 	default:
@@ -687,40 +767,44 @@ static int ceph_x_update_authorizer(
 	return 0;
 }
 
-static int decrypt_authorize_challenge(struct ceph_x_authorizer *au,
-				       void *challenge_buf,
-				       int challenge_buf_len,
-				       u64 *server_challenge)
+/*
+ * CephXAuthorizeChallenge
+ */
+static int decrypt_authorizer_challenge(struct ceph_crypto_key *secret,
+					void *challenge, int challenge_len,
+					u64 *server_challenge)
 {
-	struct ceph_x_authorize_challenge *ch =
-	    challenge_buf + sizeof(struct ceph_x_encrypt_header);
+	void *dp, *dend;
 	int ret;
 
 	/* no leading len */
-	ret = __ceph_x_decrypt(&au->session_key, challenge_buf,
-			       challenge_buf_len);
+	ret = __ceph_x_decrypt(secret, challenge, challenge_len);
 	if (ret < 0)
 		return ret;
-	if (ret < sizeof(*ch)) {
-		pr_err("bad size %d for ceph_x_authorize_challenge\n", ret);
-		return -EINVAL;
-	}
 
-	*server_challenge = le64_to_cpu(ch->server_challenge);
+	dout("%s decrypted %d bytes\n", __func__, ret);
+	dp = challenge + sizeof(struct ceph_x_encrypt_header);
+	dend = dp + ret;
+
+	ceph_decode_skip_8(&dp, dend, e_inval);  /* struct_v */
+	ceph_decode_64_safe(&dp, dend, *server_challenge, e_inval);
+	dout("%s server_challenge %llu\n", __func__, *server_challenge);
 	return 0;
+
+e_inval:
+	return -EINVAL;
 }
 
 static int ceph_x_add_authorizer_challenge(struct ceph_auth_client *ac,
 					   struct ceph_authorizer *a,
-					   void *challenge_buf,
-					   int challenge_buf_len)
+					   void *challenge, int challenge_len)
 {
 	struct ceph_x_authorizer *au = (void *)a;
 	u64 server_challenge;
 	int ret;
 
-	ret = decrypt_authorize_challenge(au, challenge_buf, challenge_buf_len,
-					  &server_challenge);
+	ret = decrypt_authorizer_challenge(&au->session_key, challenge,
+					   challenge_len, &server_challenge);
 	if (ret) {
 		pr_err("failed to decrypt authorize challenge: %d", ret);
 		return ret;
@@ -735,29 +819,76 @@ static int ceph_x_add_authorizer_challenge(struct ceph_auth_client *ac,
 	return 0;
 }
 
+/*
+ * CephXAuthorizeReply
+ */
+static int decrypt_authorizer_reply(struct ceph_crypto_key *secret,
+				    void **p, void *end, u64 *nonce_plus_one,
+				    u8 *con_secret, int *con_secret_len)
+{
+	void *dp, *dend;
+	u8 struct_v;
+	int len;
+	int ret;
+
+	dp = *p + ceph_x_encrypt_offset();
+	ret = ceph_x_decrypt(secret, p, end);
+	if (ret < 0)
+		return ret;
+
+	dout("%s decrypted %d bytes\n", __func__, ret);
+	dend = dp + ret;
+
+	ceph_decode_8_safe(&dp, dend, struct_v, e_inval);
+	ceph_decode_64_safe(&dp, dend, *nonce_plus_one, e_inval);
+	dout("%s nonce_plus_one %llu\n", __func__, *nonce_plus_one);
+	if (struct_v >= 2) {
+		ceph_decode_32_safe(&dp, dend, len, e_inval);
+		if (len > CEPH_MAX_CON_SECRET_LEN) {
+			pr_err("connection secret too big %d\n", len);
+			return -EINVAL;
+		}
+
+		dout("%s connection secret len %d\n", __func__, len);
+		if (con_secret) {
+			memcpy(con_secret, dp, len);
+			*con_secret_len = len;
+		}
+	}
+
+	return 0;
+
+e_inval:
+	return -EINVAL;
+}
+
 static int ceph_x_verify_authorizer_reply(struct ceph_auth_client *ac,
-					  struct ceph_authorizer *a)
+					  struct ceph_authorizer *a,
+					  void *reply, int reply_len,
+					  u8 *session_key, int *session_key_len,
+					  u8 *con_secret, int *con_secret_len)
 {
 	struct ceph_x_authorizer *au = (void *)a;
-	void *p = au->enc_buf;
-	struct ceph_x_authorize_reply *reply = p + ceph_x_encrypt_offset();
+	u64 nonce_plus_one;
 	int ret;
 
-	ret = ceph_x_decrypt(&au->session_key, &p, p + CEPHX_AU_ENC_BUF_LEN);
-	if (ret < 0)
+	if (session_key) {
+		memcpy(session_key, au->session_key.key, au->session_key.len);
+		*session_key_len = au->session_key.len;
+	}
+
+	ret = decrypt_authorizer_reply(&au->session_key, &reply,
+				       reply + reply_len, &nonce_plus_one,
+				       con_secret, con_secret_len);
+	if (ret)
 		return ret;
-	if (ret < sizeof(*reply)) {
-		pr_err("bad size %d for ceph_x_authorize_reply\n", ret);
-		return -EINVAL;
+
+	if (nonce_plus_one != au->nonce + 1) {
+		pr_err("failed to authenticate server\n");
+		return -EPERM;
 	}
 
-	if (au->nonce + 1 != le64_to_cpu(reply->nonce_plus_one))
-		ret = -EPERM;
-	else
-		ret = 0;
-	dout("verify_authorizer_reply nonce %llx got %llx ret %d\n",
-	     au->nonce, le64_to_cpu(reply->nonce_plus_one), ret);
-	return ret;
+	return 0;
 }
 
 static void ceph_x_reset(struct ceph_auth_client *ac)
diff --git a/net/ceph/auth_x_protocol.h b/net/ceph/auth_x_protocol.h
index 24b0b74564d0..792fcb974dc3 100644
--- a/net/ceph/auth_x_protocol.h
+++ b/net/ceph/auth_x_protocol.h
@@ -38,7 +38,8 @@ struct ceph_x_authenticate {
 	__u8 struct_v;
 	__le64 client_challenge;
 	__le64 key;
-	/* ticket blob */
+	/* old_ticket blob */
+	/* nautilus+: other_keys */
 } __attribute__ ((packed));
 
 struct ceph_x_service_ticket_request {
diff --git a/net/ceph/crypto.h b/net/ceph/crypto.h
index 96ef4d860bc9..13bd526349fa 100644
--- a/net/ceph/crypto.h
+++ b/net/ceph/crypto.h
@@ -5,6 +5,9 @@
 #include <linux/ceph/types.h>
 #include <linux/ceph/buffer.h>
 
+#define CEPH_KEY_LEN			16
+#define CEPH_MAX_CON_SECRET_LEN		64
+
 /*
  * cryptographic secret
  */
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 7901ab6c79fd..8966eae543d3 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -5623,8 +5623,11 @@ static int verify_authorizer_reply(struct ceph_connection *con)
 	struct ceph_osd *o = con->private;
 	struct ceph_osd_client *osdc = o->o_osdc;
 	struct ceph_auth_client *ac = osdc->client->monc.auth;
+	struct ceph_auth_handshake *auth = &o->o_auth;
 
-	return ceph_auth_verify_authorizer_reply(ac, o->o_auth.authorizer);
+	return ceph_auth_verify_authorizer_reply(ac, auth->authorizer,
+		auth->authorizer_reply_buf, auth->authorizer_reply_buf_len,
+		NULL, NULL, NULL, NULL);
 }
 
 static int invalidate_authorizer(struct ceph_connection *con)
-- 
cgit v1.2.3


From 59711f9ec219bf5245a8e95989803fb503adc52d Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Mon, 26 Oct 2020 17:01:53 +0100
Subject: libceph: amend cephx init_protocol() and build_request()

In msgr2, initial authentication happens with an exchange of msgr2
control frames -- MAuth message and struct ceph_mon_request_header
aren't used.  Make that optional.

Stop reporting cephx protocol as "x".  Use "cephx" instead.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/ceph_fs.h |  1 +
 net/ceph/auth.c              | 63 ++++++++++++++++++++++++--------------------
 net/ceph/ceph_strings.c      | 14 ++++++++++
 3 files changed, 50 insertions(+), 28 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index d44d98033d58..6d986e52000b 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -95,6 +95,7 @@ struct ceph_dir_layout {
 
 #define CEPH_AUTH_UID_DEFAULT ((__u64) -1)
 
+const char *ceph_auth_proto_name(int proto);
 
 /*********************************************
  * message layer
diff --git a/net/ceph/auth.c b/net/ceph/auth.c
index 40d3d95344d9..deaf267f8942 100644
--- a/net/ceph/auth.c
+++ b/net/ceph/auth.c
@@ -21,15 +21,18 @@ static u32 supported_protocols[] = {
 	CEPH_AUTH_CEPHX
 };
 
-static int ceph_auth_init_protocol(struct ceph_auth_client *ac, int protocol)
+static int init_protocol(struct ceph_auth_client *ac, int proto)
 {
-	switch (protocol) {
+	dout("%s proto %d\n", __func__, proto);
+
+	switch (proto) {
 	case CEPH_AUTH_NONE:
 		return ceph_auth_none_init(ac);
 	case CEPH_AUTH_CEPHX:
 		return ceph_x_init(ac);
 	default:
-		return -ENOENT;
+		pr_err("bad auth protocol %d\n", proto);
+		return -EINVAL;
 	}
 }
 
@@ -145,31 +148,35 @@ bad:
 	goto out;
 }
 
-static int ceph_build_auth_request(struct ceph_auth_client *ac,
-				   void *msg_buf, size_t msg_len)
+static int build_request(struct ceph_auth_client *ac, bool add_header,
+			 void *buf, int buf_len)
 {
-	struct ceph_mon_request_header *monhdr = msg_buf;
-	void *p = monhdr + 1;
-	void *end = msg_buf + msg_len;
+	void *end = buf + buf_len;
+	void *p;
 	int ret;
 
-	monhdr->have_version = 0;
-	monhdr->session_mon = cpu_to_le16(-1);
-	monhdr->session_mon_tid = 0;
-
-	ceph_encode_32(&p, ac->protocol);
+	p = buf;
+	if (add_header) {
+		/* struct ceph_mon_request_header + protocol */
+		ceph_encode_64_safe(&p, end, 0, e_range);
+		ceph_encode_16_safe(&p, end, -1, e_range);
+		ceph_encode_64_safe(&p, end, 0, e_range);
+		ceph_encode_32_safe(&p, end, ac->protocol, e_range);
+	}
 
+	ceph_encode_need(&p, end, sizeof(u32), e_range);
 	ret = ac->ops->build_request(ac, p + sizeof(u32), end);
 	if (ret < 0) {
-		pr_err("error %d building auth method %s request\n", ret,
-		       ac->ops->name);
-		goto out;
+		pr_err("auth protocol '%s' building request failed: %d\n",
+		       ceph_auth_proto_name(ac->protocol), ret);
+		return ret;
 	}
 	dout(" built request %d bytes\n", ret);
 	ceph_encode_32(&p, ret);
-	ret = p + ret - msg_buf;
-out:
-	return ret;
+	return p + ret - buf;
+
+e_range:
+	return -ERANGE;
 }
 
 /*
@@ -229,10 +236,10 @@ int ceph_handle_auth_reply(struct ceph_auth_client *ac,
 			ac->ops = NULL;
 		}
 		if (ac->protocol != protocol) {
-			ret = ceph_auth_init_protocol(ac, protocol);
+			ret = init_protocol(ac, protocol);
 			if (ret) {
-				pr_err("error %d on auth protocol %d init\n",
-				       ret, protocol);
+				pr_err("auth protocol '%s' init failed: %d\n",
+				       ceph_auth_proto_name(protocol), ret);
 				goto out;
 			}
 		}
@@ -242,11 +249,11 @@ int ceph_handle_auth_reply(struct ceph_auth_client *ac,
 
 	ret = ac->ops->handle_reply(ac, result, payload, payload_end,
 				    NULL, NULL, NULL, NULL);
-	if (ret == -EAGAIN) {
-		ret = ceph_build_auth_request(ac, reply_buf, reply_len);
-	} else if (ret) {
-		pr_err("auth method '%s' error %d\n", ac->ops->name, ret);
-	}
+	if (ret == -EAGAIN)
+		ret = build_request(ac, true, reply_buf, reply_len);
+	else if (ret)
+		pr_err("auth protocol '%s' mauth authentication failed: %d\n",
+		       ceph_auth_proto_name(ac->protocol), result);
 
 out:
 	mutex_unlock(&ac->mutex);
@@ -265,7 +272,7 @@ int ceph_build_auth(struct ceph_auth_client *ac,
 
 	mutex_lock(&ac->mutex);
 	if (ac->ops->should_authenticate(ac))
-		ret = ceph_build_auth_request(ac, msg_buf, msg_len);
+		ret = build_request(ac, true, msg_buf, msg_len);
 	mutex_unlock(&ac->mutex);
 	return ret;
 }
diff --git a/net/ceph/ceph_strings.c b/net/ceph/ceph_strings.c
index 10e01494993c..69cd391e02a6 100644
--- a/net/ceph/ceph_strings.c
+++ b/net/ceph/ceph_strings.c
@@ -18,6 +18,20 @@ const char *ceph_entity_type_name(int type)
 }
 EXPORT_SYMBOL(ceph_entity_type_name);
 
+const char *ceph_auth_proto_name(int proto)
+{
+	switch (proto) {
+	case CEPH_AUTH_UNKNOWN:
+		return "unknown";
+	case CEPH_AUTH_NONE:
+		return "none";
+	case CEPH_AUTH_CEPHX:
+		return "cephx";
+	default:
+		return "???";
+	}
+}
+
 const char *ceph_osd_op_name(int op)
 {
 	switch (op) {
-- 
cgit v1.2.3


From c1c0ce78f479cf4d7dfe72c4c1cabbf0bc0730c9 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Mon, 26 Oct 2020 17:05:44 +0100
Subject: libceph: drop ac->ops->name field

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/auth.h | 2 --
 net/ceph/auth_none.c      | 1 -
 net/ceph/auth_x.c         | 1 -
 3 files changed, 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ceph/auth.h b/include/linux/ceph/auth.h
index d9e7d0bcdaf1..5f64f66309fa 100644
--- a/include/linux/ceph/auth.h
+++ b/include/linux/ceph/auth.h
@@ -32,8 +32,6 @@ struct ceph_auth_handshake {
 };
 
 struct ceph_auth_client_ops {
-	const char *name;
-
 	/*
 	 * true if we are authenticated and can connect to
 	 * services.
diff --git a/net/ceph/auth_none.c b/net/ceph/auth_none.c
index af8ae507e861..70e86e462250 100644
--- a/net/ceph/auth_none.c
+++ b/net/ceph/auth_none.c
@@ -118,7 +118,6 @@ static int ceph_auth_none_create_authorizer(
 }
 
 static const struct ceph_auth_client_ops ceph_auth_none_ops = {
-	.name = "none",
 	.reset = reset,
 	.destroy = destroy,
 	.is_authenticated = is_authenticated,
diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c
index a265792642dc..9815cfe42af0 100644
--- a/net/ceph/auth_x.c
+++ b/net/ceph/auth_x.c
@@ -1058,7 +1058,6 @@ static int ceph_x_check_message_signature(struct ceph_auth_handshake *auth,
 }
 
 static const struct ceph_auth_client_ops ceph_x_ops = {
-	.name = "x",
 	.is_authenticated = ceph_x_is_authenticated,
 	.should_authenticate = ceph_x_should_authenticate,
 	.build_request = ceph_x_build_request,
-- 
cgit v1.2.3


From a5cbd5fc22d5043a8a76e15d75d031fe24d1f69c Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Fri, 30 Oct 2020 13:30:51 +0100
Subject: libceph, ceph: get and handle cluster maps with addrvecs

In preparation for msgr2, make the cluster send us maps with addrvecs
including both LEGACY and MSGR2 addrs instead of a single LEGACY addr.
This means advertising support for SERVER_NAUTILUS and also some older
features: SERVER_MIMIC, MONENC and MONNAMES.

MONNAMES and MONENC are actually pre-argonaut, we just never updated
ceph_monmap_decode() for them.  Decoding is unconditional, see commit
23c625ce3065 ("libceph: assume argonaut on the server side").

SERVER_MIMIC doesn't bear any meaning for the kernel client.

Since ceph_decode_entity_addrvec() is guarded by encoding version
checks (and in msgr2 case it is guarded implicitly by the fact that
server is speaking msgr2), we assume MSG_ADDR2 for it.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/mds_client.c               |   2 +-
 fs/ceph/mdsmap.c                   |  21 +++---
 include/linux/ceph/ceph_features.h |  11 ++-
 include/linux/ceph/decode.h        |   4 +
 include/linux/ceph/mdsmap.h        |   2 +-
 include/linux/ceph/osdmap.h        |   4 +-
 net/ceph/decode.c                  |  56 ++++++++++++++
 net/ceph/mon_client.c              | 145 +++++++++++++++++++++++++++----------
 net/ceph/osd_client.c              |   4 +-
 net/ceph/osdmap.c                  |  45 ++++++++----
 10 files changed, 222 insertions(+), 72 deletions(-)

(limited to 'include/linux')

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 278fe67e2617..afd22815fbda 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -5014,7 +5014,7 @@ void ceph_mdsc_handle_mdsmap(struct ceph_mds_client *mdsc, struct ceph_msg *msg)
 		return;
 	}
 
-	newmap = ceph_mdsmap_decode(&p, end);
+	newmap = ceph_mdsmap_decode(&p, end, false);
 	if (IS_ERR(newmap)) {
 		err = PTR_ERR(newmap);
 		goto bad_unlock;
diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c
index 1096d1d3a84c..abd9af7727ad 100644
--- a/fs/ceph/mdsmap.c
+++ b/fs/ceph/mdsmap.c
@@ -114,7 +114,7 @@ bad:
  * Ignore any fields we don't care about (there are quite a few of
  * them).
  */
-struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
+struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end, bool msgr2)
 {
 	struct ceph_mdsmap *m;
 	const void *start = *p;
@@ -201,18 +201,19 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
 		namelen = ceph_decode_32(p);  /* skip mds name */
 		*p += namelen;
 
-		ceph_decode_need(p, end,
-				 4*sizeof(u32) + sizeof(u64) +
-				 sizeof(addr) + sizeof(struct ceph_timespec),
-				 bad);
-		mds = ceph_decode_32(p);
-		inc = ceph_decode_32(p);
-		state = ceph_decode_32(p);
+		ceph_decode_32_safe(p, end, mds, bad);
+		ceph_decode_32_safe(p, end, inc, bad);
+		ceph_decode_32_safe(p, end, state, bad);
 		*p += sizeof(u64);		/* state_seq */
-		err = ceph_decode_entity_addr(p, end, &addr);
+		if (info_v >= 8)
+			err = ceph_decode_entity_addrvec(p, end, msgr2, &addr);
+		else
+			err = ceph_decode_entity_addr(p, end, &addr);
 		if (err)
 			goto corrupt;
-		ceph_decode_copy(p, &laggy_since, sizeof(laggy_since));
+
+		ceph_decode_copy_safe(p, end, &laggy_since, sizeof(laggy_since),
+				      bad);
 		laggy = laggy_since.tv_sec != 0 || laggy_since.tv_nsec != 0;
 		*p += sizeof(u32);
 		ceph_decode_32_safe(p, end, namelen, bad);
diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h
index 999636d53cf2..3a47acd9cc14 100644
--- a/include/linux/ceph/ceph_features.h
+++ b/include/linux/ceph/ceph_features.h
@@ -8,7 +8,8 @@
  * feature.  Base case is 1 (first use).
  */
 #define CEPH_FEATURE_INCARNATION_1 (0ull)
-#define CEPH_FEATURE_INCARNATION_2 (1ull<<57) // CEPH_FEATURE_SERVER_JEWEL
+#define CEPH_FEATURE_INCARNATION_2 (1ull<<57)              // SERVER_JEWEL
+#define CEPH_FEATURE_INCARNATION_3 ((1ull<<57)|(1ull<<28)) // SERVER_MIMIC
 
 #define DEFINE_CEPH_FEATURE(bit, incarnation, name)			\
 	static const uint64_t __maybe_unused CEPH_FEATURE_##name = (1ULL<<bit);		\
@@ -75,7 +76,7 @@
 DEFINE_CEPH_FEATURE( 0, 1, UID)
 DEFINE_CEPH_FEATURE( 1, 1, NOSRCADDR)
 DEFINE_CEPH_FEATURE_RETIRED( 2, 1, MONCLOCKCHECK, JEWEL, LUMINOUS)
-
+DEFINE_CEPH_FEATURE( 2, 3, SERVER_NAUTILUS)
 DEFINE_CEPH_FEATURE( 3, 1, FLOCK)
 DEFINE_CEPH_FEATURE( 4, 1, SUBSCRIBE2)
 DEFINE_CEPH_FEATURE( 5, 1, MONNAMES)
@@ -114,7 +115,7 @@ DEFINE_CEPH_FEATURE(25, 1, CRUSH_TUNABLES2)
 DEFINE_CEPH_FEATURE(26, 1, CREATEPOOLID)
 DEFINE_CEPH_FEATURE(27, 1, REPLY_CREATE_INODE)
 DEFINE_CEPH_FEATURE_RETIRED(28, 1, OSD_HBMSGS, HAMMER, JEWEL)
-DEFINE_CEPH_FEATURE(28, 2, SERVER_M)
+DEFINE_CEPH_FEATURE(28, 2, SERVER_MIMIC)
 DEFINE_CEPH_FEATURE(29, 1, MDSENC)
 DEFINE_CEPH_FEATURE(30, 1, OSDHASHPSPOOL)
 DEFINE_CEPH_FEATURE(31, 1, MON_SINGLE_PAXOS)  // deprecate me
@@ -177,13 +178,16 @@ DEFINE_CEPH_FEATURE_DEPRECATED(63, 1, RESERVED_BROKEN, LUMINOUS) // client-facin
  */
 #define CEPH_FEATURES_SUPPORTED_DEFAULT		\
 	(CEPH_FEATURE_NOSRCADDR |		\
+	 CEPH_FEATURE_SERVER_NAUTILUS |		\
 	 CEPH_FEATURE_FLOCK |			\
 	 CEPH_FEATURE_SUBSCRIBE2 |		\
+	 CEPH_FEATURE_MONNAMES |		\
 	 CEPH_FEATURE_RECONNECT_SEQ |		\
 	 CEPH_FEATURE_DIRLAYOUTHASH |		\
 	 CEPH_FEATURE_PGID64 |			\
 	 CEPH_FEATURE_PGPOOL3 |			\
 	 CEPH_FEATURE_OSDENC |			\
+	 CEPH_FEATURE_MONENC |			\
 	 CEPH_FEATURE_CRUSH_TUNABLES |		\
 	 CEPH_FEATURE_SERVER_LUMINOUS |		\
 	 CEPH_FEATURE_RESEND_ON_SPLIT |		\
@@ -193,6 +197,7 @@ DEFINE_CEPH_FEATURE_DEPRECATED(63, 1, RESERVED_BROKEN, LUMINOUS) // client-facin
 	 CEPH_FEATURE_MSG_AUTH |		\
 	 CEPH_FEATURE_CRUSH_TUNABLES2 |		\
 	 CEPH_FEATURE_REPLY_CREATE_INODE |	\
+	 CEPH_FEATURE_SERVER_MIMIC |		\
 	 CEPH_FEATURE_MDSENC |			\
 	 CEPH_FEATURE_OSDHASHPSPOOL |		\
 	 CEPH_FEATURE_OSD_CACHEPOOL |		\
diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h
index 450384fe487c..9a934e04f841 100644
--- a/include/linux/ceph/decode.h
+++ b/include/linux/ceph/decode.h
@@ -220,6 +220,7 @@ static inline void ceph_encode_timespec64(struct ceph_timespec *tv,
  */
 #define CEPH_ENTITY_ADDR_TYPE_NONE	0
 #define CEPH_ENTITY_ADDR_TYPE_LEGACY	__cpu_to_le32(1)
+#define CEPH_ENTITY_ADDR_TYPE_MSGR2	__cpu_to_le32(2)
 
 static inline void ceph_encode_banner_addr(struct ceph_entity_addr *a)
 {
@@ -239,6 +240,9 @@ static inline void ceph_decode_banner_addr(struct ceph_entity_addr *a)
 
 extern int ceph_decode_entity_addr(void **p, void *end,
 				   struct ceph_entity_addr *addr);
+int ceph_decode_entity_addrvec(void **p, void *end, bool msgr2,
+			       struct ceph_entity_addr *addr);
+
 /*
  * encoders
  */
diff --git a/include/linux/ceph/mdsmap.h b/include/linux/ceph/mdsmap.h
index 35d385296fbb..523fd0452856 100644
--- a/include/linux/ceph/mdsmap.h
+++ b/include/linux/ceph/mdsmap.h
@@ -64,7 +64,7 @@ static inline bool ceph_mdsmap_is_laggy(struct ceph_mdsmap *m, int w)
 }
 
 extern int ceph_mdsmap_get_random_mds(struct ceph_mdsmap *m);
-extern struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end);
+struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end, bool msgr2);
 extern void ceph_mdsmap_destroy(struct ceph_mdsmap *m);
 extern bool ceph_mdsmap_is_cluster_available(struct ceph_mdsmap *m);
 
diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index cad9acfbc320..5553019c3f07 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -251,8 +251,8 @@ static inline int ceph_decode_pgid(void **p, void *end, struct ceph_pg *pgid)
 }
 
 struct ceph_osdmap *ceph_osdmap_alloc(void);
-extern struct ceph_osdmap *ceph_osdmap_decode(void **p, void *end);
-struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
+struct ceph_osdmap *ceph_osdmap_decode(void **p, void *end, bool msgr2);
+struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, bool msgr2,
 					     struct ceph_osdmap *map);
 extern void ceph_osdmap_destroy(struct ceph_osdmap *map);
 
diff --git a/net/ceph/decode.c b/net/ceph/decode.c
index eea529595a7a..6429b6713507 100644
--- a/net/ceph/decode.c
+++ b/net/ceph/decode.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/ceph/decode.h>
 
@@ -82,3 +83,58 @@ bad:
 }
 EXPORT_SYMBOL(ceph_decode_entity_addr);
 
+/*
+ * Return addr of desired type (MSGR2 or LEGACY) or error.
+ * Make sure there is only one match.
+ *
+ * Assume encoding with MSG_ADDR2.
+ */
+int ceph_decode_entity_addrvec(void **p, void *end, bool msgr2,
+			       struct ceph_entity_addr *addr)
+{
+	__le32 my_type = msgr2 ? CEPH_ENTITY_ADDR_TYPE_MSGR2 :
+				 CEPH_ENTITY_ADDR_TYPE_LEGACY;
+	struct ceph_entity_addr tmp_addr;
+	int addr_cnt;
+	bool found;
+	u8 marker;
+	int ret;
+	int i;
+
+	ceph_decode_8_safe(p, end, marker, e_inval);
+	if (marker != 2) {
+		pr_err("bad addrvec marker %d\n", marker);
+		return -EINVAL;
+	}
+
+	ceph_decode_32_safe(p, end, addr_cnt, e_inval);
+
+	found = false;
+	for (i = 0; i < addr_cnt; i++) {
+		ret = ceph_decode_entity_addr(p, end, &tmp_addr);
+		if (ret)
+			return ret;
+
+		if (tmp_addr.type == my_type) {
+			if (found) {
+				pr_err("another match of type %d in addrvec\n",
+				       le32_to_cpu(my_type));
+				return -EINVAL;
+			}
+
+			memcpy(addr, &tmp_addr, sizeof(*addr));
+			found = true;
+		}
+	}
+	if (!found && addr_cnt != 0) {
+		pr_err("no match of type %d in addrvec\n",
+		       le32_to_cpu(my_type));
+		return -ENOENT;
+	}
+
+	return 0;
+
+e_inval:
+	return -EINVAL;
+}
+EXPORT_SYMBOL(ceph_decode_entity_addrvec);
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index ebfecf8d0918..a9754a7fa78c 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -36,57 +36,122 @@ static const struct ceph_connection_operations mon_con_ops;
 
 static int __validate_auth(struct ceph_mon_client *monc);
 
+static int decode_mon_info(void **p, void *end, bool msgr2,
+			   struct ceph_entity_addr *addr)
+{
+	void *mon_info_end;
+	u32 struct_len;
+	u8 struct_v;
+	int ret;
+
+	ret = ceph_start_decoding(p, end, 1, "mon_info_t", &struct_v,
+				  &struct_len);
+	if (ret)
+		return ret;
+
+	mon_info_end = *p + struct_len;
+	ceph_decode_skip_string(p, end, e_inval);  /* skip mon name */
+	ret = ceph_decode_entity_addrvec(p, end, msgr2, addr);
+	if (ret)
+		return ret;
+
+	*p = mon_info_end;
+	return 0;
+
+e_inval:
+	return -EINVAL;
+}
+
 /*
  * Decode a monmap blob (e.g., during mount).
+ *
+ * Assume MonMap v3 (i.e. encoding with MONNAMES and MONENC).
  */
-static struct ceph_monmap *ceph_monmap_decode(void *p, void *end)
+static struct ceph_monmap *ceph_monmap_decode(void **p, void *end, bool msgr2)
 {
-	struct ceph_monmap *m = NULL;
-	int i, err = -EINVAL;
+	struct ceph_monmap *monmap = NULL;
 	struct ceph_fsid fsid;
-	u32 epoch, num_mon;
-	u32 len;
+	u32 struct_len;
+	int blob_len;
+	int num_mon;
+	u8 struct_v;
+	u32 epoch;
+	int ret;
+	int i;
+
+	ceph_decode_32_safe(p, end, blob_len, e_inval);
+	ceph_decode_need(p, end, blob_len, e_inval);
+
+	ret = ceph_start_decoding(p, end, 6, "monmap", &struct_v, &struct_len);
+	if (ret)
+		goto fail;
+
+	dout("%s struct_v %d\n", __func__, struct_v);
+	ceph_decode_copy_safe(p, end, &fsid, sizeof(fsid), e_inval);
+	ceph_decode_32_safe(p, end, epoch, e_inval);
+	if (struct_v >= 6) {
+		u32 feat_struct_len;
+		u8 feat_struct_v;
 
-	ceph_decode_32_safe(&p, end, len, bad);
-	ceph_decode_need(&p, end, len, bad);
+		*p += sizeof(struct ceph_timespec);  /* skip last_changed */
+		*p += sizeof(struct ceph_timespec);  /* skip created */
 
-	dout("monmap_decode %p %p len %d (%d)\n", p, end, len, (int)(end-p));
-	p += sizeof(u16);  /* skip version */
+		ret = ceph_start_decoding(p, end, 1, "mon_feature_t",
+					  &feat_struct_v, &feat_struct_len);
+		if (ret)
+			goto fail;
 
-	ceph_decode_need(&p, end, sizeof(fsid) + 2*sizeof(u32), bad);
-	ceph_decode_copy(&p, &fsid, sizeof(fsid));
-	epoch = ceph_decode_32(&p);
+		*p += feat_struct_len;  /* skip persistent_features */
 
-	num_mon = ceph_decode_32(&p);
+		ret = ceph_start_decoding(p, end, 1, "mon_feature_t",
+					  &feat_struct_v, &feat_struct_len);
+		if (ret)
+			goto fail;
 
+		*p += feat_struct_len;  /* skip optional_features */
+	}
+	ceph_decode_32_safe(p, end, num_mon, e_inval);
+
+	dout("%s fsid %pU epoch %u num_mon %d\n", __func__, &fsid, epoch,
+	     num_mon);
 	if (num_mon > CEPH_MAX_MON)
-		goto bad;
-	m = kmalloc(struct_size(m, mon_inst, num_mon), GFP_NOFS);
-	if (m == NULL)
-		return ERR_PTR(-ENOMEM);
-	m->fsid = fsid;
-	m->epoch = epoch;
-	m->num_mon = num_mon;
-	for (i = 0; i < num_mon; ++i) {
-		struct ceph_entity_inst *inst = &m->mon_inst[i];
-
-		/* copy name portion */
-		ceph_decode_copy_safe(&p, end, &inst->name,
-					sizeof(inst->name), bad);
-		err = ceph_decode_entity_addr(&p, end, &inst->addr);
-		if (err)
-			goto bad;
+		goto e_inval;
+
+	monmap = kmalloc(struct_size(monmap, mon_inst, num_mon), GFP_NOIO);
+	if (!monmap) {
+		ret = -ENOMEM;
+		goto fail;
 	}
-	dout("monmap_decode epoch %d, num_mon %d\n", m->epoch,
-	     m->num_mon);
-	for (i = 0; i < m->num_mon; i++)
-		dout("monmap_decode  mon%d is %s\n", i,
-		     ceph_pr_addr(&m->mon_inst[i].addr));
-	return m;
-bad:
-	dout("monmap_decode failed with %d\n", err);
-	kfree(m);
-	return ERR_PTR(err);
+	monmap->fsid = fsid;
+	monmap->epoch = epoch;
+	monmap->num_mon = num_mon;
+
+	/* legacy_mon_addr map or mon_info map */
+	for (i = 0; i < num_mon; i++) {
+		struct ceph_entity_inst *inst = &monmap->mon_inst[i];
+
+		ceph_decode_skip_string(p, end, e_inval);  /* skip mon name */
+		inst->name.type = CEPH_ENTITY_TYPE_MON;
+		inst->name.num = cpu_to_le64(i);
+
+		if (struct_v >= 6)
+			ret = decode_mon_info(p, end, msgr2, &inst->addr);
+		else
+			ret = ceph_decode_entity_addr(p, end, &inst->addr);
+		if (ret)
+			goto fail;
+
+		dout("%s mon%d addr %s\n", __func__, i,
+		     ceph_pr_addr(&inst->addr));
+	}
+
+	return monmap;
+
+e_inval:
+	ret = -EINVAL;
+fail:
+	kfree(monmap);
+	return ERR_PTR(ret);
 }
 
 /*
@@ -476,7 +541,7 @@ static void ceph_monc_handle_map(struct ceph_mon_client *monc,
 	p = msg->front.iov_base;
 	end = p + msg->front.iov_len;
 
-	monmap = ceph_monmap_decode(p, end);
+	monmap = ceph_monmap_decode(&p, end, false);
 	if (IS_ERR(monmap)) {
 		pr_err("problem decoding monmap, %d\n",
 		       (int)PTR_ERR(monmap));
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 8966eae543d3..51be5a7482fc 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -3918,9 +3918,9 @@ static int handle_one_map(struct ceph_osd_client *osdc,
 	set_pool_was_full(osdc);
 
 	if (incremental)
-		newmap = osdmap_apply_incremental(&p, end, osdc->osdmap);
+		newmap = osdmap_apply_incremental(&p, end, false, osdc->osdmap);
 	else
-		newmap = ceph_osdmap_decode(&p, end);
+		newmap = ceph_osdmap_decode(&p, end, false);
 	if (IS_ERR(newmap))
 		return PTR_ERR(newmap);
 
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index fa08c15be0c0..2b1dd252f231 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -1647,7 +1647,8 @@ static int decode_old_pg_upmap_items(void **p, void *end,
 /*
  * decode a full map.
  */
-static int osdmap_decode(void **p, void *end, struct ceph_osdmap *map)
+static int osdmap_decode(void **p, void *end, bool msgr2,
+			 struct ceph_osdmap *map)
 {
 	u8 struct_v;
 	u32 epoch = 0;
@@ -1718,9 +1719,16 @@ static int osdmap_decode(void **p, void *end, struct ceph_osdmap *map)
 		goto e_inval;
 
 	for (i = 0; i < map->max_osd; i++) {
-		err = ceph_decode_entity_addr(p, end, &map->osd_addr[i]);
+		struct ceph_entity_addr *addr = &map->osd_addr[i];
+
+		if (struct_v >= 8)
+			err = ceph_decode_entity_addrvec(p, end, msgr2, addr);
+		else
+			err = ceph_decode_entity_addr(p, end, addr);
 		if (err)
 			goto bad;
+
+		dout("%s osd%d addr %s\n", __func__, i, ceph_pr_addr(addr));
 	}
 
 	/* pg_temp */
@@ -1790,7 +1798,7 @@ bad:
 /*
  * Allocate and decode a full map.
  */
-struct ceph_osdmap *ceph_osdmap_decode(void **p, void *end)
+struct ceph_osdmap *ceph_osdmap_decode(void **p, void *end, bool msgr2)
 {
 	struct ceph_osdmap *map;
 	int ret;
@@ -1799,7 +1807,7 @@ struct ceph_osdmap *ceph_osdmap_decode(void **p, void *end)
 	if (!map)
 		return ERR_PTR(-ENOMEM);
 
-	ret = osdmap_decode(p, end, map);
+	ret = osdmap_decode(p, end, msgr2, map);
 	if (ret) {
 		ceph_osdmap_destroy(map);
 		return ERR_PTR(ret);
@@ -1817,12 +1825,13 @@ struct ceph_osdmap *ceph_osdmap_decode(void **p, void *end)
  *     new_state: { osd=6, xorstate=EXISTS } # clear osd_state
  */
 static int decode_new_up_state_weight(void **p, void *end, u8 struct_v,
-				      struct ceph_osdmap *map)
+				      bool msgr2, struct ceph_osdmap *map)
 {
 	void *new_up_client;
 	void *new_state;
 	void *new_weight_end;
 	u32 len;
+	int ret;
 	int i;
 
 	new_up_client = *p;
@@ -1831,8 +1840,12 @@ static int decode_new_up_state_weight(void **p, void *end, u8 struct_v,
 		struct ceph_entity_addr addr;
 
 		ceph_decode_skip_32(p, end, e_inval);
-		if (ceph_decode_entity_addr(p, end, &addr))
-			goto e_inval;
+		if (struct_v >= 7)
+			ret = ceph_decode_entity_addrvec(p, end, msgr2, &addr);
+		else
+			ret = ceph_decode_entity_addr(p, end, &addr);
+		if (ret)
+			return ret;
 	}
 
 	new_state = *p;
@@ -1874,7 +1887,6 @@ static int decode_new_up_state_weight(void **p, void *end, u8 struct_v,
 	while (len--) {
 		s32 osd;
 		u32 xorstate;
-		int ret;
 
 		osd = ceph_decode_32(p);
 		if (struct_v >= 5)
@@ -1910,8 +1922,15 @@ static int decode_new_up_state_weight(void **p, void *end, u8 struct_v,
 
 		osd = ceph_decode_32(p);
 		BUG_ON(osd >= map->max_osd);
-		if (ceph_decode_entity_addr(p, end, &addr))
-			goto e_inval;
+		if (struct_v >= 7)
+			ret = ceph_decode_entity_addrvec(p, end, msgr2, &addr);
+		else
+			ret = ceph_decode_entity_addr(p, end, &addr);
+		if (ret)
+			return ret;
+
+		dout("%s osd%d addr %s\n", __func__, osd, ceph_pr_addr(&addr));
+
 		pr_info("osd%d up\n", osd);
 		map->osd_state[osd] |= CEPH_OSD_EXISTS | CEPH_OSD_UP;
 		map->osd_addr[osd] = addr;
@@ -1927,7 +1946,7 @@ e_inval:
 /*
  * decode and apply an incremental map update.
  */
-struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
+struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, bool msgr2,
 					     struct ceph_osdmap *map)
 {
 	struct ceph_fsid fsid;
@@ -1962,7 +1981,7 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 	if (len > 0) {
 		dout("apply_incremental full map len %d, %p to %p\n",
 		     len, *p, end);
-		return ceph_osdmap_decode(p, min(*p+len, end));
+		return ceph_osdmap_decode(p, min(*p+len, end), msgr2);
 	}
 
 	/* new crush? */
@@ -2014,7 +2033,7 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 	}
 
 	/* new_up_client, new_state, new_weight */
-	err = decode_new_up_state_weight(p, end, struct_v, map);
+	err = decode_new_up_state_weight(p, end, struct_v, msgr2, map);
 	if (err)
 		goto bad;
 
-- 
cgit v1.2.3


From 313771e80fd253d4b5472e61a2d12b03c5293aa9 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Wed, 25 Nov 2020 14:41:59 +0100
Subject: libceph, rbd: ignore addr->type while comparing in some cases

For libceph, this ensures that libceph instance sharing (share option)
continues to work.  For rbd, this avoids blocklisting alive lock owners
(locker addr is always LEGACY, while watcher addr is ANY in nautilus).

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 drivers/block/rbd.c       | 8 ++++++--
 include/linux/ceph/msgr.h | 9 ++++++++-
 net/ceph/mon_client.c     | 6 ++++--
 3 files changed, 18 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index f84128abade3..bec85c054522 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -3957,8 +3957,12 @@ static int find_watcher(struct rbd_device *rbd_dev,
 
 	sscanf(locker->id.cookie, RBD_LOCK_COOKIE_PREFIX " %llu", &cookie);
 	for (i = 0; i < num_watchers; i++) {
-		if (!memcmp(&watchers[i].addr, &locker->info.addr,
-			    sizeof(locker->info.addr)) &&
+		/*
+		 * Ignore addr->type while comparing.  This mimics
+		 * entity_addr_t::get_legacy_str() + strcmp().
+		 */
+		if (ceph_addr_equal_no_type(&watchers[i].addr,
+					    &locker->info.addr) &&
 		    watchers[i].cookie == cookie) {
 			struct rbd_client_id cid = {
 				.gid = le64_to_cpu(watchers[i].name.num),
diff --git a/include/linux/ceph/msgr.h b/include/linux/ceph/msgr.h
index 46939485f2c3..9a897a60f20b 100644
--- a/include/linux/ceph/msgr.h
+++ b/include/linux/ceph/msgr.h
@@ -52,11 +52,18 @@ extern const char *ceph_entity_type_name(int type);
  * entity_addr -- network address
  */
 struct ceph_entity_addr {
-	__le32 type;
+	__le32 type;  /* CEPH_ENTITY_ADDR_TYPE_* */
 	__le32 nonce;  /* unique id for process (e.g. pid) */
 	struct sockaddr_storage in_addr;
 } __attribute__ ((packed));
 
+static inline bool ceph_addr_equal_no_type(const struct ceph_entity_addr *lhs,
+					   const struct ceph_entity_addr *rhs)
+{
+	return !memcmp(&lhs->in_addr, &rhs->in_addr, sizeof(lhs->in_addr)) &&
+	       lhs->nonce == rhs->nonce;
+}
+
 struct ceph_entity_inst {
 	struct ceph_entity_name name;
 	struct ceph_entity_addr addr;
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index a9754a7fa78c..f5f090b4e409 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -161,9 +161,11 @@ int ceph_monmap_contains(struct ceph_monmap *m, struct ceph_entity_addr *addr)
 {
 	int i;
 
-	for (i = 0; i < m->num_mon; i++)
-		if (memcmp(addr, &m->mon_inst[i].addr, sizeof(*addr)) == 0)
+	for (i = 0; i < m->num_mon; i++) {
+		if (ceph_addr_equal_no_type(addr, &m->mon_inst[i].addr))
 			return 1;
+	}
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From 00498b994113a871a556f7ff24a4cf8a00611700 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Thu, 19 Nov 2020 16:04:58 +0100
Subject: libceph: introduce connection modes and ms_mode option

msgr2 supports two connection modes: crc (plain) and secure (on-wire
encryption).  Connection mode is picked by server based on input from
client.

Introduce ms_mode option:

  ms_mode=legacy        - msgr1 (default)
  ms_mode=crc           - crc mode, if denied fail
  ms_mode=secure        - secure mode, if denied fail
  ms_mode=prefer-crc    - crc mode, if denied agree to secure mode
  ms_mode=prefer-secure - secure mode, if denied agree to crc mode

ms_mode affects all connections, we don't separate connections to mons
like it's done in userspace with ms_client_mode vs ms_mon_client_mode.

For now the default is legacy, to be flipped to prefer-crc after some
time.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/auth.h    |  8 ++++--
 include/linux/ceph/ceph_fs.h |  6 +++++
 include/linux/ceph/libceph.h |  1 +
 net/ceph/auth.c              | 12 ++++++---
 net/ceph/ceph_common.c       | 63 ++++++++++++++++++++++++++++++++++++++++++++
 net/ceph/ceph_strings.c      | 14 ++++++++++
 net/ceph/mon_client.c        |  4 +--
 7 files changed, 100 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ceph/auth.h b/include/linux/ceph/auth.h
index 5f64f66309fa..6fc058fe9efa 100644
--- a/include/linux/ceph/auth.h
+++ b/include/linux/ceph/auth.h
@@ -98,11 +98,15 @@ struct ceph_auth_client {
 	const struct ceph_crypto_key *key;     /* our secret key */
 	unsigned want_keys;     /* which services we want */
 
+	int preferred_mode;	/* CEPH_CON_MODE_* */
+	int fallback_mode;	/* ditto */
+
 	struct mutex mutex;
 };
 
-extern struct ceph_auth_client *ceph_auth_init(const char *name,
-					       const struct ceph_crypto_key *key);
+struct ceph_auth_client *ceph_auth_init(const char *name,
+					const struct ceph_crypto_key *key,
+					const int *con_modes);
 extern void ceph_auth_destroy(struct ceph_auth_client *ac);
 
 extern void ceph_auth_reset(struct ceph_auth_client *ac);
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index 6d986e52000b..ce22d5469670 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -93,9 +93,15 @@ struct ceph_dir_layout {
 #define CEPH_AUTH_NONE	 	0x1
 #define CEPH_AUTH_CEPHX	 	0x2
 
+/* msgr2 protocol modes */
+#define CEPH_CON_MODE_UNKNOWN	0x0
+#define CEPH_CON_MODE_CRC	0x1
+#define CEPH_CON_MODE_SECURE	0x2
+
 #define CEPH_AUTH_UID_DEFAULT ((__u64) -1)
 
 const char *ceph_auth_proto_name(int proto);
+const char *ceph_con_mode_name(int mode);
 
 /*********************************************
  * message layer
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index eb5a7ca13f9c..8765a5ad267a 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -53,6 +53,7 @@ struct ceph_options {
 	unsigned long osd_keepalive_timeout;	/* jiffies */
 	unsigned long osd_request_timeout;	/* jiffies */
 	u32 read_from_replica;  /* CEPH_OSD_FLAG_BALANCE/LOCALIZE_READS */
+	int con_modes[2];  /* CEPH_CON_MODE_* */
 
 	/*
 	 * any type that can't be simply compared or doesn't need
diff --git a/net/ceph/auth.c b/net/ceph/auth.c
index deaf267f8942..4a0f32b32cc6 100644
--- a/net/ceph/auth.c
+++ b/net/ceph/auth.c
@@ -39,13 +39,13 @@ static int init_protocol(struct ceph_auth_client *ac, int proto)
 /*
  * setup, teardown.
  */
-struct ceph_auth_client *ceph_auth_init(const char *name, const struct ceph_crypto_key *key)
+struct ceph_auth_client *ceph_auth_init(const char *name,
+					const struct ceph_crypto_key *key,
+					const int *con_modes)
 {
 	struct ceph_auth_client *ac;
 	int ret;
 
-	dout("auth_init name '%s'\n", name);
-
 	ret = -ENOMEM;
 	ac = kzalloc(sizeof(*ac), GFP_NOFS);
 	if (!ac)
@@ -57,8 +57,12 @@ struct ceph_auth_client *ceph_auth_init(const char *name, const struct ceph_cryp
 		ac->name = name;
 	else
 		ac->name = CEPH_AUTH_NAME_DEFAULT;
-	dout("auth_init name %s\n", ac->name);
 	ac->key = key;
+	ac->preferred_mode = con_modes[0];
+	ac->fallback_mode = con_modes[1];
+
+	dout("%s name '%s' preferred_mode %d fallback_mode %d\n", __func__,
+	     ac->name, ac->preferred_mode, ac->fallback_mode);
 	return ac;
 
 out:
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index 4e7edd707a14..271287c5ec12 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -265,6 +265,7 @@ enum {
 	Opt_ip,
 	Opt_crush_location,
 	Opt_read_from_replica,
+	Opt_ms_mode,
 	/* string args above */
 	Opt_share,
 	Opt_crc,
@@ -287,6 +288,23 @@ static const struct constant_table ceph_param_read_from_replica[] = {
 	{}
 };
 
+enum ceph_ms_mode {
+	Opt_ms_mode_legacy,
+	Opt_ms_mode_crc,
+	Opt_ms_mode_secure,
+	Opt_ms_mode_prefer_crc,
+	Opt_ms_mode_prefer_secure
+};
+
+static const struct constant_table ceph_param_ms_mode[] = {
+	{"legacy",		Opt_ms_mode_legacy},
+	{"crc",			Opt_ms_mode_crc},
+	{"secure",		Opt_ms_mode_secure},
+	{"prefer-crc",		Opt_ms_mode_prefer_crc},
+	{"prefer-secure",	Opt_ms_mode_prefer_secure},
+	{}
+};
+
 static const struct fs_parameter_spec ceph_parameters[] = {
 	fsparam_flag	("abort_on_full",		Opt_abort_on_full),
 	fsparam_flag_no ("cephx_require_signatures",	Opt_cephx_require_signatures),
@@ -305,6 +323,8 @@ static const struct fs_parameter_spec ceph_parameters[] = {
 			 fs_param_deprecated, NULL),
 	fsparam_enum	("read_from_replica",		Opt_read_from_replica,
 			 ceph_param_read_from_replica),
+	fsparam_enum	("ms_mode",			Opt_ms_mode,
+			 ceph_param_ms_mode),
 	fsparam_string	("secret",			Opt_secret),
 	fsparam_flag_no ("share",			Opt_share),
 	fsparam_flag_no ("tcp_nodelay",			Opt_tcp_nodelay),
@@ -333,6 +353,8 @@ struct ceph_options *ceph_alloc_options(void)
 	opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT;
 	opt->osd_request_timeout = CEPH_OSD_REQUEST_TIMEOUT_DEFAULT;
 	opt->read_from_replica = CEPH_READ_FROM_REPLICA_DEFAULT;
+	opt->con_modes[0] = CEPH_CON_MODE_UNKNOWN;
+	opt->con_modes[1] = CEPH_CON_MODE_UNKNOWN;
 	return opt;
 }
 EXPORT_SYMBOL(ceph_alloc_options);
@@ -503,6 +525,32 @@ int ceph_parse_param(struct fs_parameter *param, struct ceph_options *opt,
 			BUG();
 		}
 		break;
+	case Opt_ms_mode:
+		switch (result.uint_32) {
+		case Opt_ms_mode_legacy:
+			opt->con_modes[0] = CEPH_CON_MODE_UNKNOWN;
+			opt->con_modes[1] = CEPH_CON_MODE_UNKNOWN;
+			break;
+		case Opt_ms_mode_crc:
+			opt->con_modes[0] = CEPH_CON_MODE_CRC;
+			opt->con_modes[1] = CEPH_CON_MODE_UNKNOWN;
+			break;
+		case Opt_ms_mode_secure:
+			opt->con_modes[0] = CEPH_CON_MODE_SECURE;
+			opt->con_modes[1] = CEPH_CON_MODE_UNKNOWN;
+			break;
+		case Opt_ms_mode_prefer_crc:
+			opt->con_modes[0] = CEPH_CON_MODE_CRC;
+			opt->con_modes[1] = CEPH_CON_MODE_SECURE;
+			break;
+		case Opt_ms_mode_prefer_secure:
+			opt->con_modes[0] = CEPH_CON_MODE_SECURE;
+			opt->con_modes[1] = CEPH_CON_MODE_CRC;
+			break;
+		default:
+			BUG();
+		}
+		break;
 
 	case Opt_osdtimeout:
 		warn_plog(&log, "Ignoring osdtimeout");
@@ -616,6 +664,21 @@ int ceph_print_client_options(struct seq_file *m, struct ceph_client *client,
 	} else if (opt->read_from_replica == CEPH_OSD_FLAG_LOCALIZE_READS) {
 		seq_puts(m, "read_from_replica=localize,");
 	}
+	if (opt->con_modes[0] != CEPH_CON_MODE_UNKNOWN) {
+		if (opt->con_modes[0] == CEPH_CON_MODE_CRC &&
+		    opt->con_modes[1] == CEPH_CON_MODE_UNKNOWN) {
+			seq_puts(m, "ms_mode=crc,");
+		} else if (opt->con_modes[0] == CEPH_CON_MODE_SECURE &&
+			   opt->con_modes[1] == CEPH_CON_MODE_UNKNOWN) {
+			seq_puts(m, "ms_mode=secure,");
+		} else if (opt->con_modes[0] == CEPH_CON_MODE_CRC &&
+			   opt->con_modes[1] == CEPH_CON_MODE_SECURE) {
+			seq_puts(m, "ms_mode=prefer-crc,");
+		} else if (opt->con_modes[0] == CEPH_CON_MODE_SECURE &&
+			   opt->con_modes[1] == CEPH_CON_MODE_CRC) {
+			seq_puts(m, "ms_mode=prefer-secure,");
+		}
+	}
 
 	if (opt->flags & CEPH_OPT_FSID)
 		seq_printf(m, "fsid=%pU,", &opt->fsid);
diff --git a/net/ceph/ceph_strings.c b/net/ceph/ceph_strings.c
index 69cd391e02a6..355fea272120 100644
--- a/net/ceph/ceph_strings.c
+++ b/net/ceph/ceph_strings.c
@@ -32,6 +32,20 @@ const char *ceph_auth_proto_name(int proto)
 	}
 }
 
+const char *ceph_con_mode_name(int mode)
+{
+	switch (mode) {
+	case CEPH_CON_MODE_UNKNOWN:
+		return "unknown";
+	case CEPH_CON_MODE_CRC:
+		return "crc";
+	case CEPH_CON_MODE_SECURE:
+		return "secure";
+	default:
+		return "???";
+	}
+}
+
 const char *ceph_osd_op_name(int op)
 {
 	switch (op) {
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index f5f090b4e409..792a8c4164d7 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -1156,8 +1156,8 @@ int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl)
 
 	/* connection */
 	/* authentication */
-	monc->auth = ceph_auth_init(cl->options->name,
-				    cl->options->key);
+	monc->auth = ceph_auth_init(cl->options->name, cl->options->key,
+				    cl->options->con_modes);
 	if (IS_ERR(monc->auth)) {
 		err = PTR_ERR(monc->auth);
 		goto out_monmap;
-- 
cgit v1.2.3


From cd1a677cad994021b19665ed476aea63f5d54f31 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Thu, 19 Nov 2020 16:59:08 +0100
Subject: libceph, ceph: implement msgr2.1 protocol (crc and secure modes)

Implement msgr2.1 wire protocol, available since nautilus 14.2.11
and octopus 15.2.5.  msgr2.0 wire protocol is not implemented -- it
has several security, integrity and robustness issues and therefore
considered deprecated.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/mds_client.c           |   80 +-
 include/linux/ceph/auth.h      |   36 +-
 include/linux/ceph/ceph_fs.h   |    4 +
 include/linux/ceph/decode.h    |    4 +
 include/linux/ceph/libceph.h   |    9 +-
 include/linux/ceph/messenger.h |  136 +-
 include/linux/ceph/msgr.h      |   48 +
 net/ceph/Kconfig               |    3 +
 net/ceph/Makefile              |    2 +-
 net/ceph/auth.c                |  309 ++++
 net/ceph/decode.c              |   45 +
 net/ceph/messenger.c           |   68 +-
 net/ceph/messenger_v2.c        | 3443 ++++++++++++++++++++++++++++++++++++++++
 net/ceph/mon_client.c          |  115 +-
 net/ceph/osd_client.c          |   85 +-
 15 files changed, 4356 insertions(+), 31 deletions(-)
 create mode 100644 net/ceph/messenger_v2.c

(limited to 'include/linux')

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index afd22815fbda..740d63d0fc50 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -5014,7 +5014,7 @@ void ceph_mdsc_handle_mdsmap(struct ceph_mds_client *mdsc, struct ceph_msg *msg)
 		return;
 	}
 
-	newmap = ceph_mdsmap_decode(&p, end, false);
+	newmap = ceph_mdsmap_decode(&p, end, ceph_msgr2(mdsc->fsc->client));
 	if (IS_ERR(newmap)) {
 		err = PTR_ERR(newmap);
 		goto bad_unlock;
@@ -5196,6 +5196,80 @@ static int invalidate_authorizer(struct ceph_connection *con)
 	return ceph_monc_validate_auth(&mdsc->fsc->client->monc);
 }
 
+static int mds_get_auth_request(struct ceph_connection *con,
+				void *buf, int *buf_len,
+				void **authorizer, int *authorizer_len)
+{
+	struct ceph_mds_session *s = con->private;
+	struct ceph_auth_client *ac = s->s_mdsc->fsc->client->monc.auth;
+	struct ceph_auth_handshake *auth = &s->s_auth;
+	int ret;
+
+	ret = ceph_auth_get_authorizer(ac, auth, CEPH_ENTITY_TYPE_MDS,
+				       buf, buf_len);
+	if (ret)
+		return ret;
+
+	*authorizer = auth->authorizer_buf;
+	*authorizer_len = auth->authorizer_buf_len;
+	return 0;
+}
+
+static int mds_handle_auth_reply_more(struct ceph_connection *con,
+				      void *reply, int reply_len,
+				      void *buf, int *buf_len,
+				      void **authorizer, int *authorizer_len)
+{
+	struct ceph_mds_session *s = con->private;
+	struct ceph_auth_client *ac = s->s_mdsc->fsc->client->monc.auth;
+	struct ceph_auth_handshake *auth = &s->s_auth;
+	int ret;
+
+	ret = ceph_auth_handle_svc_reply_more(ac, auth, reply, reply_len,
+					      buf, buf_len);
+	if (ret)
+		return ret;
+
+	*authorizer = auth->authorizer_buf;
+	*authorizer_len = auth->authorizer_buf_len;
+	return 0;
+}
+
+static int mds_handle_auth_done(struct ceph_connection *con,
+				u64 global_id, void *reply, int reply_len,
+				u8 *session_key, int *session_key_len,
+				u8 *con_secret, int *con_secret_len)
+{
+	struct ceph_mds_session *s = con->private;
+	struct ceph_auth_client *ac = s->s_mdsc->fsc->client->monc.auth;
+	struct ceph_auth_handshake *auth = &s->s_auth;
+
+	return ceph_auth_handle_svc_reply_done(ac, auth, reply, reply_len,
+					       session_key, session_key_len,
+					       con_secret, con_secret_len);
+}
+
+static int mds_handle_auth_bad_method(struct ceph_connection *con,
+				      int used_proto, int result,
+				      const int *allowed_protos, int proto_cnt,
+				      const int *allowed_modes, int mode_cnt)
+{
+	struct ceph_mds_session *s = con->private;
+	struct ceph_mon_client *monc = &s->s_mdsc->fsc->client->monc;
+	int ret;
+
+	if (ceph_auth_handle_bad_authorizer(monc->auth, CEPH_ENTITY_TYPE_MDS,
+					    used_proto, result,
+					    allowed_protos, proto_cnt,
+					    allowed_modes, mode_cnt)) {
+		ret = ceph_monc_validate_auth(monc);
+		if (ret)
+			return ret;
+	}
+
+	return -EACCES;
+}
+
 static struct ceph_msg *mds_alloc_msg(struct ceph_connection *con,
 				struct ceph_msg_header *hdr, int *skip)
 {
@@ -5245,6 +5319,10 @@ static const struct ceph_connection_operations mds_con_ops = {
 	.alloc_msg = mds_alloc_msg,
 	.sign_message = mds_sign_message,
 	.check_message_signature = mds_check_message_signature,
+	.get_auth_request = mds_get_auth_request,
+	.handle_auth_reply_more = mds_handle_auth_reply_more,
+	.handle_auth_done = mds_handle_auth_done,
+	.handle_auth_bad_method = mds_handle_auth_bad_method,
 };
 
 /* eof */
diff --git a/include/linux/ceph/auth.h b/include/linux/ceph/auth.h
index 6fc058fe9efa..3fbe72ebd779 100644
--- a/include/linux/ceph/auth.h
+++ b/include/linux/ceph/auth.h
@@ -120,8 +120,12 @@ int ceph_auth_entity_name_encode(const char *name, void **p, void *end);
 
 extern int ceph_build_auth(struct ceph_auth_client *ac,
 		    void *msg_buf, size_t msg_len);
-
 extern int ceph_auth_is_authenticated(struct ceph_auth_client *ac);
+
+int __ceph_auth_get_authorizer(struct ceph_auth_client *ac,
+			       struct ceph_auth_handshake *auth,
+			       int peer_type, bool force_new,
+			       int *proto, int *pref_mode, int *fallb_mode);
 extern int ceph_auth_create_authorizer(struct ceph_auth_client *ac,
 				       int peer_type,
 				       struct ceph_auth_handshake *auth);
@@ -157,4 +161,34 @@ int ceph_auth_check_message_signature(struct ceph_auth_handshake *auth,
 		return auth->check_message_signature(auth, msg);
 	return 0;
 }
+
+int ceph_auth_get_request(struct ceph_auth_client *ac, void *buf, int buf_len);
+int ceph_auth_handle_reply_more(struct ceph_auth_client *ac, void *reply,
+				int reply_len, void *buf, int buf_len);
+int ceph_auth_handle_reply_done(struct ceph_auth_client *ac,
+				u64 global_id, void *reply, int reply_len,
+				u8 *session_key, int *session_key_len,
+				u8 *con_secret, int *con_secret_len);
+bool ceph_auth_handle_bad_method(struct ceph_auth_client *ac,
+				 int used_proto, int result,
+				 const int *allowed_protos, int proto_cnt,
+				 const int *allowed_modes, int mode_cnt);
+
+int ceph_auth_get_authorizer(struct ceph_auth_client *ac,
+			     struct ceph_auth_handshake *auth,
+			     int peer_type, void *buf, int *buf_len);
+int ceph_auth_handle_svc_reply_more(struct ceph_auth_client *ac,
+				    struct ceph_auth_handshake *auth,
+				    void *reply, int reply_len,
+				    void *buf, int *buf_len);
+int ceph_auth_handle_svc_reply_done(struct ceph_auth_client *ac,
+				    struct ceph_auth_handshake *auth,
+				    void *reply, int reply_len,
+				    u8 *session_key, int *session_key_len,
+				    u8 *con_secret, int *con_secret_len);
+bool ceph_auth_handle_bad_authorizer(struct ceph_auth_client *ac,
+				     int peer_type, int used_proto, int result,
+				     const int *allowed_protos, int proto_cnt,
+				     const int *allowed_modes, int mode_cnt);
+
 #endif
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index ce22d5469670..e41a811026f6 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -93,6 +93,10 @@ struct ceph_dir_layout {
 #define CEPH_AUTH_NONE	 	0x1
 #define CEPH_AUTH_CEPHX	 	0x2
 
+#define CEPH_AUTH_MODE_NONE		0
+#define CEPH_AUTH_MODE_AUTHORIZER	1
+#define CEPH_AUTH_MODE_MON		10
+
 /* msgr2 protocol modes */
 #define CEPH_CON_MODE_UNKNOWN	0x0
 #define CEPH_CON_MODE_CRC	0x1
diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h
index 9a934e04f841..04f3ace5787b 100644
--- a/include/linux/ceph/decode.h
+++ b/include/linux/ceph/decode.h
@@ -221,6 +221,7 @@ static inline void ceph_encode_timespec64(struct ceph_timespec *tv,
 #define CEPH_ENTITY_ADDR_TYPE_NONE	0
 #define CEPH_ENTITY_ADDR_TYPE_LEGACY	__cpu_to_le32(1)
 #define CEPH_ENTITY_ADDR_TYPE_MSGR2	__cpu_to_le32(2)
+#define CEPH_ENTITY_ADDR_TYPE_ANY	__cpu_to_le32(3)
 
 static inline void ceph_encode_banner_addr(struct ceph_entity_addr *a)
 {
@@ -243,6 +244,9 @@ extern int ceph_decode_entity_addr(void **p, void *end,
 int ceph_decode_entity_addrvec(void **p, void *end, bool msgr2,
 			       struct ceph_entity_addr *addr);
 
+int ceph_entity_addr_encoding_len(const struct ceph_entity_addr *addr);
+void ceph_encode_entity_addr(void **p, const struct ceph_entity_addr *addr);
+
 /*
  * encoders
  */
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index 8765a5ad267a..eb9008bb3992 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -31,10 +31,10 @@
 #define CEPH_OPT_FSID             (1<<0)
 #define CEPH_OPT_NOSHARE          (1<<1) /* don't share client with other sbs */
 #define CEPH_OPT_MYIP             (1<<2) /* specified my ip */
-#define CEPH_OPT_NOCRC            (1<<3) /* no data crc on writes */
+#define CEPH_OPT_NOCRC            (1<<3) /* no data crc on writes (msgr1) */
 #define CEPH_OPT_NOMSGAUTH	  (1<<4) /* don't require msg signing feat */
 #define CEPH_OPT_TCP_NODELAY	  (1<<5) /* TCP_NODELAY on TCP sockets */
-#define CEPH_OPT_NOMSGSIGN	  (1<<6) /* don't sign msgs */
+#define CEPH_OPT_NOMSGSIGN	  (1<<6) /* don't sign msgs (msgr1) */
 #define CEPH_OPT_ABORT_ON_FULL	  (1<<7) /* abort w/ ENOSPC when full */
 
 #define CEPH_OPT_DEFAULT   (CEPH_OPT_TCP_NODELAY)
@@ -84,6 +84,7 @@ struct ceph_options {
 #define CEPH_MONC_HUNT_BACKOFF		2
 #define CEPH_MONC_HUNT_MAX_MULT		10
 
+#define CEPH_MSG_MAX_CONTROL_LEN (16*1024*1024)
 #define CEPH_MSG_MAX_FRONT_LEN	(16*1024*1024)
 #define CEPH_MSG_MAX_MIDDLE_LEN	(16*1024*1024)
 
@@ -152,6 +153,10 @@ struct ceph_client {
 
 #define from_msgr(ms)	container_of(ms, struct ceph_client, msgr)
 
+static inline bool ceph_msgr2(struct ceph_client *client)
+{
+	return client->options->con_modes[0] != CEPH_CON_MODE_UNKNOWN;
+}
 
 /*
  * snapshots
diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index 54a64e8dfce6..0e6e9ad3c3bf 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -3,6 +3,7 @@
 #define __FS_CEPH_MESSENGER_H
 
 #include <linux/bvec.h>
+#include <linux/crypto.h>
 #include <linux/kref.h>
 #include <linux/mutex.h>
 #include <linux/net.h>
@@ -52,6 +53,23 @@ struct ceph_connection_operations {
 
 	int (*sign_message) (struct ceph_msg *msg);
 	int (*check_message_signature) (struct ceph_msg *msg);
+
+	/* msgr2 authentication exchange */
+	int (*get_auth_request)(struct ceph_connection *con,
+				void *buf, int *buf_len,
+				void **authorizer, int *authorizer_len);
+	int (*handle_auth_reply_more)(struct ceph_connection *con,
+				      void *reply, int reply_len,
+				      void *buf, int *buf_len,
+				      void **authorizer, int *authorizer_len);
+	int (*handle_auth_done)(struct ceph_connection *con,
+				u64 global_id, void *reply, int reply_len,
+				u8 *session_key, int *session_key_len,
+				u8 *con_secret, int *con_secret_len);
+	int (*handle_auth_bad_method)(struct ceph_connection *con,
+				      int used_proto, int result,
+				      const int *allowed_protos, int proto_cnt,
+				      const int *allowed_modes, int mode_cnt);
 };
 
 /* use format string %s%lld */
@@ -246,8 +264,15 @@ struct ceph_msg {
 #define CEPH_CON_S_PREOPEN		2
 #define CEPH_CON_S_V1_BANNER		3
 #define CEPH_CON_S_V1_CONNECT_MSG	4
-#define CEPH_CON_S_OPEN			5
-#define CEPH_CON_S_STANDBY		6
+#define CEPH_CON_S_V2_BANNER_PREFIX	5
+#define CEPH_CON_S_V2_BANNER_PAYLOAD	6
+#define CEPH_CON_S_V2_HELLO		7
+#define CEPH_CON_S_V2_AUTH		8
+#define CEPH_CON_S_V2_AUTH_SIGNATURE	9
+#define CEPH_CON_S_V2_SESSION_CONNECT	10
+#define CEPH_CON_S_V2_SESSION_RECONNECT	11
+#define CEPH_CON_S_OPEN			12
+#define CEPH_CON_S_STANDBY		13
 
 /*
  * ceph_connection flag bits
@@ -301,6 +326,99 @@ struct ceph_connection_v1_info {
 	u32 peer_global_seq;  /* peer's global seq for this connection */
 };
 
+#define CEPH_CRC_LEN			4
+#define CEPH_GCM_KEY_LEN		16
+#define CEPH_GCM_IV_LEN			sizeof(struct ceph_gcm_nonce)
+#define CEPH_GCM_BLOCK_LEN		16
+#define CEPH_GCM_TAG_LEN		16
+
+#define CEPH_PREAMBLE_LEN		32
+#define CEPH_PREAMBLE_INLINE_LEN	48
+#define CEPH_PREAMBLE_PLAIN_LEN		CEPH_PREAMBLE_LEN
+#define CEPH_PREAMBLE_SECURE_LEN	(CEPH_PREAMBLE_LEN +		\
+					 CEPH_PREAMBLE_INLINE_LEN +	\
+					 CEPH_GCM_TAG_LEN)
+#define CEPH_EPILOGUE_PLAIN_LEN		(1 + 3 * CEPH_CRC_LEN)
+#define CEPH_EPILOGUE_SECURE_LEN	(CEPH_GCM_BLOCK_LEN + CEPH_GCM_TAG_LEN)
+
+#define CEPH_FRAME_MAX_SEGMENT_COUNT	4
+
+struct ceph_frame_desc {
+	int fd_tag;  /* FRAME_TAG_* */
+	int fd_seg_cnt;
+	int fd_lens[CEPH_FRAME_MAX_SEGMENT_COUNT];  /* logical */
+	int fd_aligns[CEPH_FRAME_MAX_SEGMENT_COUNT];
+};
+
+struct ceph_gcm_nonce {
+	__le32 fixed;
+	__le64 counter __packed;
+};
+
+struct ceph_connection_v2_info {
+	struct iov_iter in_iter;
+	struct kvec in_kvecs[5];  /* recvmsg */
+	struct bio_vec in_bvec;  /* recvmsg (in_cursor) */
+	int in_kvec_cnt;
+	int in_state;  /* IN_S_* */
+
+	struct iov_iter out_iter;
+	struct kvec out_kvecs[8];  /* sendmsg */
+	struct bio_vec out_bvec;  /* sendpage (out_cursor, out_zero),
+				     sendmsg (out_enc_pages) */
+	int out_kvec_cnt;
+	int out_state;  /* OUT_S_* */
+
+	int out_zero;  /* # of zero bytes to send */
+	bool out_iter_sendpage;  /* use sendpage if possible */
+
+	struct ceph_frame_desc in_desc;
+	struct ceph_msg_data_cursor in_cursor;
+	struct ceph_msg_data_cursor out_cursor;
+
+	struct crypto_shash *hmac_tfm;  /* post-auth signature */
+	struct crypto_aead *gcm_tfm;  /* on-wire encryption */
+	struct aead_request *gcm_req;
+	struct crypto_wait gcm_wait;
+	struct ceph_gcm_nonce in_gcm_nonce;
+	struct ceph_gcm_nonce out_gcm_nonce;
+
+	struct page **out_enc_pages;
+	int out_enc_page_cnt;
+	int out_enc_resid;
+	int out_enc_i;
+
+	int con_mode;  /* CEPH_CON_MODE_* */
+
+	void *conn_bufs[16];
+	int conn_buf_cnt;
+
+	struct kvec in_sign_kvecs[8];
+	struct kvec out_sign_kvecs[8];
+	int in_sign_kvec_cnt;
+	int out_sign_kvec_cnt;
+
+	u64 client_cookie;
+	u64 server_cookie;
+	u64 global_seq;
+	u64 connect_seq;
+	u64 peer_global_seq;
+
+	u8 in_buf[CEPH_PREAMBLE_SECURE_LEN];
+	u8 out_buf[CEPH_PREAMBLE_SECURE_LEN];
+	struct {
+		u8 late_status;  /* FRAME_LATE_STATUS_* */
+		union {
+			struct {
+				u32 front_crc;
+				u32 middle_crc;
+				u32 data_crc;
+			} __packed;
+			u8 pad[CEPH_GCM_BLOCK_LEN - 1];
+		};
+	} out_epil;
+};
+
 /*
  * A single connection with another host.
  *
@@ -346,7 +464,10 @@ struct ceph_connection {
 	struct delayed_work work;	    /* send|recv work */
 	unsigned long       delay;          /* current delay interval */
 
-	struct ceph_connection_v1_info v1;
+	union {
+		struct ceph_connection_v1_info v1;
+		struct ceph_connection_v2_info v2;
+	};
 };
 
 extern struct page *ceph_zero_page;
@@ -397,6 +518,15 @@ bool ceph_con_v1_opened(struct ceph_connection *con);
 void ceph_con_v1_reset_session(struct ceph_connection *con);
 void ceph_con_v1_reset_protocol(struct ceph_connection *con);
 
+/* messenger_v2.c */
+int ceph_con_v2_try_read(struct ceph_connection *con);
+int ceph_con_v2_try_write(struct ceph_connection *con);
+void ceph_con_v2_revoke(struct ceph_connection *con);
+void ceph_con_v2_revoke_incoming(struct ceph_connection *con);
+bool ceph_con_v2_opened(struct ceph_connection *con);
+void ceph_con_v2_reset_session(struct ceph_connection *con);
+void ceph_con_v2_reset_protocol(struct ceph_connection *con);
+
 
 extern const char *ceph_pr_addr(const struct ceph_entity_addr *addr);
 
diff --git a/include/linux/ceph/msgr.h b/include/linux/ceph/msgr.h
index 9a897a60f20b..f5e02f6c0655 100644
--- a/include/linux/ceph/msgr.h
+++ b/include/linux/ceph/msgr.h
@@ -14,9 +14,39 @@
  * constant.
  */
 #define CEPH_BANNER "ceph v027"
+#define CEPH_BANNER_LEN 9
 #define CEPH_BANNER_MAX_LEN 30
 
 
+/*
+ * messenger V2 connection banner prefix.
+ * The full banner string should have the form: "ceph v2\n<le16>"
+ * the 2 bytes are the length of the remaining banner.
+ */
+#define CEPH_BANNER_V2 "ceph v2\n"
+#define CEPH_BANNER_V2_LEN 8
+#define CEPH_BANNER_V2_PREFIX_LEN (CEPH_BANNER_V2_LEN + sizeof(__le16))
+
+/*
+ * messenger V2 features
+ */
+#define CEPH_MSGR2_INCARNATION_1 (0ull)
+
+#define DEFINE_MSGR2_FEATURE(bit, incarnation, name)               \
+	static const uint64_t CEPH_MSGR2_FEATURE_##name = (1ULL << bit); \
+	static const uint64_t CEPH_MSGR2_FEATUREMASK_##name =            \
+			(1ULL << bit | CEPH_MSGR2_INCARNATION_##incarnation);
+
+#define HAVE_MSGR2_FEATURE(x, name) \
+	(((x) & (CEPH_MSGR2_FEATUREMASK_##name)) == (CEPH_MSGR2_FEATUREMASK_##name))
+
+DEFINE_MSGR2_FEATURE( 0, 1, REVISION_1)   // msgr2.1
+
+#define CEPH_MSGR2_SUPPORTED_FEATURES (CEPH_MSGR2_FEATURE_REVISION_1)
+
+#define CEPH_MSGR2_REQUIRED_FEATURES  (CEPH_MSGR2_FEATURE_REVISION_1)
+
+
 /*
  * Rollover-safe type and comparator for 32-bit sequence numbers.
  * Comparator returns -1, 0, or 1.
@@ -158,6 +188,24 @@ struct ceph_msg_header {
 	__le32 crc;       /* header crc32c */
 } __attribute__ ((packed));
 
+struct ceph_msg_header2 {
+	__le64 seq;       /* message seq# for this session */
+	__le64 tid;       /* transaction id */
+	__le16 type;      /* message type */
+	__le16 priority;  /* priority.  higher value == higher priority */
+	__le16 version;   /* version of message encoding */
+
+	__le32 data_pre_padding_len;
+	__le16 data_off;  /* sender: include full offset;
+			     receiver: mask against ~PAGE_MASK */
+
+	__le64 ack_seq;
+	__u8 flags;
+	/* oldest code we think can decode this.  unknown if zero. */
+	__le16 compat_version;
+	__le16 reserved;
+} __attribute__ ((packed));
+
 #define CEPH_MSG_PRIO_LOW     64
 #define CEPH_MSG_PRIO_DEFAULT 127
 #define CEPH_MSG_PRIO_HIGH    196
diff --git a/net/ceph/Kconfig b/net/ceph/Kconfig
index f36f9a3a4e20..c5c4eef3a9ff 100644
--- a/net/ceph/Kconfig
+++ b/net/ceph/Kconfig
@@ -5,6 +5,9 @@ config CEPH_LIB
 	select LIBCRC32C
 	select CRYPTO_AES
 	select CRYPTO_CBC
+	select CRYPTO_GCM
+	select CRYPTO_HMAC
+	select CRYPTO_SHA256
 	select CRYPTO
 	select KEYS
 	default n
diff --git a/net/ceph/Makefile b/net/ceph/Makefile
index df02bd8d6c7b..8802a0c0155d 100644
--- a/net/ceph/Makefile
+++ b/net/ceph/Makefile
@@ -15,4 +15,4 @@ libceph-y := ceph_common.o messenger.o msgpool.o buffer.o pagelist.o \
 	auth_x.o \
 	ceph_strings.o ceph_hash.o \
 	pagevec.o snapshot.o string_table.o \
-	messenger_v1.o
+	messenger_v1.o messenger_v2.o
diff --git a/net/ceph/auth.c b/net/ceph/auth.c
index 4a0f32b32cc6..6b315c8212b1 100644
--- a/net/ceph/auth.c
+++ b/net/ceph/auth.c
@@ -293,6 +293,39 @@ int ceph_auth_is_authenticated(struct ceph_auth_client *ac)
 }
 EXPORT_SYMBOL(ceph_auth_is_authenticated);
 
+int __ceph_auth_get_authorizer(struct ceph_auth_client *ac,
+			       struct ceph_auth_handshake *auth,
+			       int peer_type, bool force_new,
+			       int *proto, int *pref_mode, int *fallb_mode)
+{
+	int ret;
+
+	mutex_lock(&ac->mutex);
+	if (force_new && auth->authorizer) {
+		ceph_auth_destroy_authorizer(auth->authorizer);
+		auth->authorizer = NULL;
+	}
+	if (!auth->authorizer)
+		ret = ac->ops->create_authorizer(ac, peer_type, auth);
+	else if (ac->ops->update_authorizer)
+		ret = ac->ops->update_authorizer(ac, peer_type, auth);
+	else
+		ret = 0;
+	if (ret)
+		goto out;
+
+	*proto = ac->protocol;
+	if (pref_mode && fallb_mode) {
+		*pref_mode = ac->preferred_mode;
+		*fallb_mode = ac->fallback_mode;
+	}
+
+out:
+	mutex_unlock(&ac->mutex);
+	return ret;
+}
+EXPORT_SYMBOL(__ceph_auth_get_authorizer);
+
 int ceph_auth_create_authorizer(struct ceph_auth_client *ac,
 				int peer_type,
 				struct ceph_auth_handshake *auth)
@@ -369,3 +402,279 @@ void ceph_auth_invalidate_authorizer(struct ceph_auth_client *ac, int peer_type)
 	mutex_unlock(&ac->mutex);
 }
 EXPORT_SYMBOL(ceph_auth_invalidate_authorizer);
+
+/*
+ * msgr2 authentication
+ */
+
+static bool contains(const int *arr, int cnt, int val)
+{
+	int i;
+
+	for (i = 0; i < cnt; i++) {
+		if (arr[i] == val)
+			return true;
+	}
+
+	return false;
+}
+
+static int encode_con_modes(void **p, void *end, int pref_mode, int fallb_mode)
+{
+	WARN_ON(pref_mode == CEPH_CON_MODE_UNKNOWN);
+	if (fallb_mode != CEPH_CON_MODE_UNKNOWN) {
+		ceph_encode_32_safe(p, end, 2, e_range);
+		ceph_encode_32_safe(p, end, pref_mode, e_range);
+		ceph_encode_32_safe(p, end, fallb_mode, e_range);
+	} else {
+		ceph_encode_32_safe(p, end, 1, e_range);
+		ceph_encode_32_safe(p, end, pref_mode, e_range);
+	}
+
+	return 0;
+
+e_range:
+	return -ERANGE;
+}
+
+/*
+ * Similar to ceph_auth_build_hello().
+ */
+int ceph_auth_get_request(struct ceph_auth_client *ac, void *buf, int buf_len)
+{
+	int proto = ac->key ? CEPH_AUTH_CEPHX : CEPH_AUTH_NONE;
+	void *end = buf + buf_len;
+	void *lenp;
+	void *p;
+	int ret;
+
+	mutex_lock(&ac->mutex);
+	if (ac->protocol == CEPH_AUTH_UNKNOWN) {
+		ret = init_protocol(ac, proto);
+		if (ret) {
+			pr_err("auth protocol '%s' init failed: %d\n",
+			       ceph_auth_proto_name(proto), ret);
+			goto out;
+		}
+	} else {
+		WARN_ON(ac->protocol != proto);
+		ac->ops->reset(ac);
+	}
+
+	p = buf;
+	ceph_encode_32_safe(&p, end, ac->protocol, e_range);
+	ret = encode_con_modes(&p, end, ac->preferred_mode, ac->fallback_mode);
+	if (ret)
+		goto out;
+
+	lenp = p;
+	p += 4;  /* space for len */
+
+	ceph_encode_8_safe(&p, end, CEPH_AUTH_MODE_MON, e_range);
+	ret = ceph_auth_entity_name_encode(ac->name, &p, end);
+	if (ret)
+		goto out;
+
+	ceph_encode_64_safe(&p, end, ac->global_id, e_range);
+	ceph_encode_32(&lenp, p - lenp - 4);
+	ret = p - buf;
+
+out:
+	mutex_unlock(&ac->mutex);
+	return ret;
+
+e_range:
+	ret = -ERANGE;
+	goto out;
+}
+
+int ceph_auth_handle_reply_more(struct ceph_auth_client *ac, void *reply,
+				int reply_len, void *buf, int buf_len)
+{
+	int ret;
+
+	mutex_lock(&ac->mutex);
+	ret = ac->ops->handle_reply(ac, 0, reply, reply + reply_len,
+				    NULL, NULL, NULL, NULL);
+	if (ret == -EAGAIN)
+		ret = build_request(ac, false, buf, buf_len);
+	else
+		WARN_ON(ret >= 0);
+	mutex_unlock(&ac->mutex);
+	return ret;
+}
+
+int ceph_auth_handle_reply_done(struct ceph_auth_client *ac,
+				u64 global_id, void *reply, int reply_len,
+				u8 *session_key, int *session_key_len,
+				u8 *con_secret, int *con_secret_len)
+{
+	int ret;
+
+	mutex_lock(&ac->mutex);
+	if (global_id && ac->global_id != global_id) {
+		dout("%s global_id %llu -> %llu\n", __func__, ac->global_id,
+		     global_id);
+		ac->global_id = global_id;
+	}
+
+	ret = ac->ops->handle_reply(ac, 0, reply, reply + reply_len,
+				    session_key, session_key_len,
+				    con_secret, con_secret_len);
+	mutex_unlock(&ac->mutex);
+	return ret;
+}
+
+bool ceph_auth_handle_bad_method(struct ceph_auth_client *ac,
+				 int used_proto, int result,
+				 const int *allowed_protos, int proto_cnt,
+				 const int *allowed_modes, int mode_cnt)
+{
+	mutex_lock(&ac->mutex);
+	WARN_ON(used_proto != ac->protocol);
+
+	if (result == -EOPNOTSUPP) {
+		if (!contains(allowed_protos, proto_cnt, ac->protocol)) {
+			pr_err("auth protocol '%s' not allowed\n",
+			       ceph_auth_proto_name(ac->protocol));
+			goto not_allowed;
+		}
+		if (!contains(allowed_modes, mode_cnt, ac->preferred_mode) &&
+		    (ac->fallback_mode == CEPH_CON_MODE_UNKNOWN ||
+		     !contains(allowed_modes, mode_cnt, ac->fallback_mode))) {
+			pr_err("preferred mode '%s' not allowed\n",
+			       ceph_con_mode_name(ac->preferred_mode));
+			if (ac->fallback_mode == CEPH_CON_MODE_UNKNOWN)
+				pr_err("no fallback mode\n");
+			else
+				pr_err("fallback mode '%s' not allowed\n",
+				       ceph_con_mode_name(ac->fallback_mode));
+			goto not_allowed;
+		}
+	}
+
+	WARN_ON(result == -EOPNOTSUPP || result >= 0);
+	pr_err("auth protocol '%s' msgr authentication failed: %d\n",
+	       ceph_auth_proto_name(ac->protocol), result);
+
+	mutex_unlock(&ac->mutex);
+	return true;
+
+not_allowed:
+	mutex_unlock(&ac->mutex);
+	return false;
+}
+
+int ceph_auth_get_authorizer(struct ceph_auth_client *ac,
+			     struct ceph_auth_handshake *auth,
+			     int peer_type, void *buf, int *buf_len)
+{
+	void *end = buf + *buf_len;
+	int pref_mode, fallb_mode;
+	int proto;
+	void *p;
+	int ret;
+
+	ret = __ceph_auth_get_authorizer(ac, auth, peer_type, true, &proto,
+					 &pref_mode, &fallb_mode);
+	if (ret)
+		return ret;
+
+	p = buf;
+	ceph_encode_32_safe(&p, end, proto, e_range);
+	ret = encode_con_modes(&p, end, pref_mode, fallb_mode);
+	if (ret)
+		return ret;
+
+	ceph_encode_32_safe(&p, end, auth->authorizer_buf_len, e_range);
+	*buf_len = p - buf;
+	return 0;
+
+e_range:
+	return -ERANGE;
+}
+EXPORT_SYMBOL(ceph_auth_get_authorizer);
+
+int ceph_auth_handle_svc_reply_more(struct ceph_auth_client *ac,
+				    struct ceph_auth_handshake *auth,
+				    void *reply, int reply_len,
+				    void *buf, int *buf_len)
+{
+	void *end = buf + *buf_len;
+	void *p;
+	int ret;
+
+	ret = ceph_auth_add_authorizer_challenge(ac, auth->authorizer,
+						 reply, reply_len);
+	if (ret)
+		return ret;
+
+	p = buf;
+	ceph_encode_32_safe(&p, end, auth->authorizer_buf_len, e_range);
+	*buf_len = p - buf;
+	return 0;
+
+e_range:
+	return -ERANGE;
+}
+EXPORT_SYMBOL(ceph_auth_handle_svc_reply_more);
+
+int ceph_auth_handle_svc_reply_done(struct ceph_auth_client *ac,
+				    struct ceph_auth_handshake *auth,
+				    void *reply, int reply_len,
+				    u8 *session_key, int *session_key_len,
+				    u8 *con_secret, int *con_secret_len)
+{
+	return ceph_auth_verify_authorizer_reply(ac, auth->authorizer,
+		reply, reply_len, session_key, session_key_len,
+		con_secret, con_secret_len);
+}
+EXPORT_SYMBOL(ceph_auth_handle_svc_reply_done);
+
+bool ceph_auth_handle_bad_authorizer(struct ceph_auth_client *ac,
+				     int peer_type, int used_proto, int result,
+				     const int *allowed_protos, int proto_cnt,
+				     const int *allowed_modes, int mode_cnt)
+{
+	mutex_lock(&ac->mutex);
+	WARN_ON(used_proto != ac->protocol);
+
+	if (result == -EOPNOTSUPP) {
+		if (!contains(allowed_protos, proto_cnt, ac->protocol)) {
+			pr_err("auth protocol '%s' not allowed by %s\n",
+			       ceph_auth_proto_name(ac->protocol),
+			       ceph_entity_type_name(peer_type));
+			goto not_allowed;
+		}
+		if (!contains(allowed_modes, mode_cnt, ac->preferred_mode) &&
+		    (ac->fallback_mode == CEPH_CON_MODE_UNKNOWN ||
+		     !contains(allowed_modes, mode_cnt, ac->fallback_mode))) {
+			pr_err("preferred mode '%s' not allowed by %s\n",
+			       ceph_con_mode_name(ac->preferred_mode),
+			       ceph_entity_type_name(peer_type));
+			if (ac->fallback_mode == CEPH_CON_MODE_UNKNOWN)
+				pr_err("no fallback mode\n");
+			else
+				pr_err("fallback mode '%s' not allowed by %s\n",
+				       ceph_con_mode_name(ac->fallback_mode),
+				       ceph_entity_type_name(peer_type));
+			goto not_allowed;
+		}
+	}
+
+	WARN_ON(result == -EOPNOTSUPP || result >= 0);
+	pr_err("auth protocol '%s' authorization to %s failed: %d\n",
+	       ceph_auth_proto_name(ac->protocol),
+	       ceph_entity_type_name(peer_type), result);
+
+	if (ac->ops->invalidate_authorizer)
+		ac->ops->invalidate_authorizer(ac, peer_type);
+
+	mutex_unlock(&ac->mutex);
+	return true;
+
+not_allowed:
+	mutex_unlock(&ac->mutex);
+	return false;
+}
+EXPORT_SYMBOL(ceph_auth_handle_bad_authorizer);
diff --git a/net/ceph/decode.c b/net/ceph/decode.c
index 6429b6713507..b44f7651be04 100644
--- a/net/ceph/decode.c
+++ b/net/ceph/decode.c
@@ -1,6 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/ceph/ceph_debug.h>
 
+#include <linux/inet.h>
+
 #include <linux/ceph/decode.h>
 
 static int
@@ -138,3 +140,46 @@ e_inval:
 	return -EINVAL;
 }
 EXPORT_SYMBOL(ceph_decode_entity_addrvec);
+
+static int get_sockaddr_encoding_len(sa_family_t family)
+{
+	union {
+		struct sockaddr sa;
+		struct sockaddr_in sin;
+		struct sockaddr_in6 sin6;
+	} u;
+
+	switch (family) {
+	case AF_INET:
+		return sizeof(u.sin);
+	case AF_INET6:
+		return sizeof(u.sin6);
+	default:
+		return sizeof(u);
+	}
+}
+
+int ceph_entity_addr_encoding_len(const struct ceph_entity_addr *addr)
+{
+	sa_family_t family = get_unaligned(&addr->in_addr.ss_family);
+	int addr_len = get_sockaddr_encoding_len(family);
+
+	return 1 + CEPH_ENCODING_START_BLK_LEN + 4 + 4 + 4 + addr_len;
+}
+
+void ceph_encode_entity_addr(void **p, const struct ceph_entity_addr *addr)
+{
+	sa_family_t family = get_unaligned(&addr->in_addr.ss_family);
+	int addr_len = get_sockaddr_encoding_len(family);
+
+	ceph_encode_8(p, 1);  /* marker */
+	ceph_start_encoding(p, 1, 1, sizeof(addr->type) +
+				     sizeof(addr->nonce) +
+				     sizeof(u32) + addr_len);
+	ceph_encode_copy(p, &addr->type, sizeof(addr->type));
+	ceph_encode_copy(p, &addr->nonce, sizeof(addr->nonce));
+
+	ceph_encode_32(p, addr_len);
+	ceph_encode_16(p, family);
+	ceph_encode_copy(p, addr->in_addr.__data, addr_len - sizeof(family));
+}
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 4fb3c33a7b03..57d043b382ed 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -195,8 +195,11 @@ EXPORT_SYMBOL(ceph_pr_addr);
 
 void ceph_encode_my_addr(struct ceph_messenger *msgr)
 {
-	memcpy(&msgr->my_enc_addr, &msgr->inst.addr, sizeof(msgr->my_enc_addr));
-	ceph_encode_banner_addr(&msgr->my_enc_addr);
+	if (!ceph_msgr2(from_msgr(msgr))) {
+		memcpy(&msgr->my_enc_addr, &msgr->inst.addr,
+		       sizeof(msgr->my_enc_addr));
+		ceph_encode_banner_addr(&msgr->my_enc_addr);
+	}
 }
 
 /*
@@ -513,7 +516,10 @@ static void ceph_con_reset_protocol(struct ceph_connection *con)
 		con->out_msg = NULL;
 	}
 
-	ceph_con_v1_reset_protocol(con);
+	if (ceph_msgr2(from_msgr(con->msgr)))
+		ceph_con_v2_reset_protocol(con);
+	else
+		ceph_con_v1_reset_protocol(con);
 }
 
 /*
@@ -526,6 +532,7 @@ static void ceph_msg_remove(struct ceph_msg *msg)
 
 	ceph_msg_put(msg);
 }
+
 static void ceph_msg_remove_list(struct list_head *head)
 {
 	while (!list_empty(head)) {
@@ -547,7 +554,10 @@ void ceph_con_reset_session(struct ceph_connection *con)
 	con->in_seq = 0;
 	con->in_seq_acked = 0;
 
-	ceph_con_v1_reset_session(con);
+	if (ceph_msgr2(from_msgr(con->msgr)))
+		ceph_con_v2_reset_session(con);
+	else
+		ceph_con_v1_reset_session(con);
 }
 
 /*
@@ -600,6 +610,9 @@ EXPORT_SYMBOL(ceph_con_open);
  */
 bool ceph_con_opened(struct ceph_connection *con)
 {
+	if (ceph_msgr2(from_msgr(con->msgr)))
+		return ceph_con_v2_opened(con);
+
 	return ceph_con_v1_opened(con);
 }
 
@@ -1302,7 +1315,16 @@ int ceph_parse_ips(const char *c, const char *end,
 		}
 
 		ceph_addr_set_port(&addr[i], port);
+		/*
+		 * We want the type to be set according to ms_mode
+		 * option, but options are normally parsed after mon
+		 * addresses.  Rather than complicating parsing, set
+		 * to LEGACY and override in build_initial_monmap()
+		 * for mon addresses and ceph_messenger_init() for
+		 * ip option.
+		 */
 		addr[i].type = CEPH_ENTITY_ADDR_TYPE_LEGACY;
+		addr[i].nonce = 0;
 
 		dout("parse_ips got %s\n", ceph_pr_addr(&addr[i]));
 
@@ -1410,6 +1432,13 @@ static bool con_sock_closed(struct ceph_connection *con)
 	CASE(PREOPEN);
 	CASE(V1_BANNER);
 	CASE(V1_CONNECT_MSG);
+	CASE(V2_BANNER_PREFIX);
+	CASE(V2_BANNER_PAYLOAD);
+	CASE(V2_HELLO);
+	CASE(V2_AUTH);
+	CASE(V2_AUTH_SIGNATURE);
+	CASE(V2_SESSION_CONNECT);
+	CASE(V2_SESSION_RECONNECT);
 	CASE(OPEN);
 	CASE(STANDBY);
 	default:
@@ -1494,7 +1523,10 @@ static void ceph_con_workfn(struct work_struct *work)
 			BUG_ON(con->sock);
 		}
 
-		ret = ceph_con_v1_try_read(con);
+		if (ceph_msgr2(from_msgr(con->msgr)))
+			ret = ceph_con_v2_try_read(con);
+		else
+			ret = ceph_con_v1_try_read(con);
 		if (ret < 0) {
 			if (ret == -EAGAIN)
 				continue;
@@ -1504,7 +1536,10 @@ static void ceph_con_workfn(struct work_struct *work)
 			break;
 		}
 
-		ret = ceph_con_v1_try_write(con);
+		if (ceph_msgr2(from_msgr(con->msgr)))
+			ret = ceph_con_v2_try_write(con);
+		else
+			ret = ceph_con_v1_try_write(con);
 		if (ret < 0) {
 			if (ret == -EAGAIN)
 				continue;
@@ -1538,9 +1573,8 @@ static void con_fault(struct ceph_connection *con)
 		ceph_pr_addr(&con->peer_addr), con->error_msg);
 	con->error_msg = NULL;
 
-	WARN_ON(con->state != CEPH_CON_S_V1_BANNER &&
-	       con->state != CEPH_CON_S_V1_CONNECT_MSG &&
-	       con->state != CEPH_CON_S_OPEN);
+	WARN_ON(con->state == CEPH_CON_S_STANDBY ||
+		con->state == CEPH_CON_S_CLOSED);
 
 	ceph_con_reset_protocol(con);
 
@@ -1596,7 +1630,11 @@ void ceph_messenger_init(struct ceph_messenger *msgr,
 		ceph_addr_set_port(&msgr->inst.addr, 0);
 	}
 
-	msgr->inst.addr.type = 0;
+	/*
+	 * Since nautilus, clients are identified using type ANY.
+	 * For msgr1, ceph_encode_banner_addr() munges it to NONE.
+	 */
+	msgr->inst.addr.type = CEPH_ENTITY_ADDR_TYPE_ANY;
 
 	/* generate a random non-zero nonce */
 	do {
@@ -1706,7 +1744,10 @@ void ceph_msg_revoke(struct ceph_msg *msg)
 	if (con->out_msg == msg) {
 		WARN_ON(con->state != CEPH_CON_S_OPEN);
 		dout("%s con %p msg %p was sending\n", __func__, con, msg);
-		ceph_con_v1_revoke(con);
+		if (ceph_msgr2(from_msgr(con->msgr)))
+			ceph_con_v2_revoke(con);
+		else
+			ceph_con_v1_revoke(con);
 		ceph_msg_put(con->out_msg);
 		con->out_msg = NULL;
 	} else {
@@ -1732,7 +1773,10 @@ void ceph_msg_revoke_incoming(struct ceph_msg *msg)
 	if (con->in_msg == msg) {
 		WARN_ON(con->state != CEPH_CON_S_OPEN);
 		dout("%s con %p msg %p was recving\n", __func__, con, msg);
-		ceph_con_v1_revoke_incoming(con);
+		if (ceph_msgr2(from_msgr(con->msgr)))
+			ceph_con_v2_revoke_incoming(con);
+		else
+			ceph_con_v1_revoke_incoming(con);
 		ceph_msg_put(con->in_msg);
 		con->in_msg = NULL;
 	} else {
diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c
new file mode 100644
index 000000000000..5e38c847317b
--- /dev/null
+++ b/net/ceph/messenger_v2.c
@@ -0,0 +1,3443 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Ceph msgr2 protocol implementation
+ *
+ * Copyright (C) 2020 Ilya Dryomov <idryomov@gmail.com>
+ */
+
+#include <linux/ceph/ceph_debug.h>
+
+#include <crypto/aead.h>
+#include <crypto/algapi.h>  /* for crypto_memneq() */
+#include <crypto/hash.h>
+#include <crypto/sha.h>
+#include <linux/bvec.h>
+#include <linux/crc32c.h>
+#include <linux/net.h>
+#include <linux/scatterlist.h>
+#include <linux/socket.h>
+#include <linux/sched/mm.h>
+#include <net/sock.h>
+#include <net/tcp.h>
+
+#include <linux/ceph/ceph_features.h>
+#include <linux/ceph/decode.h>
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/messenger.h>
+
+#include "crypto.h"  /* for CEPH_KEY_LEN and CEPH_MAX_CON_SECRET_LEN */
+
+#define FRAME_TAG_HELLO			1
+#define FRAME_TAG_AUTH_REQUEST		2
+#define FRAME_TAG_AUTH_BAD_METHOD	3
+#define FRAME_TAG_AUTH_REPLY_MORE	4
+#define FRAME_TAG_AUTH_REQUEST_MORE	5
+#define FRAME_TAG_AUTH_DONE		6
+#define FRAME_TAG_AUTH_SIGNATURE	7
+#define FRAME_TAG_CLIENT_IDENT		8
+#define FRAME_TAG_SERVER_IDENT		9
+#define FRAME_TAG_IDENT_MISSING_FEATURES 10
+#define FRAME_TAG_SESSION_RECONNECT	11
+#define FRAME_TAG_SESSION_RESET		12
+#define FRAME_TAG_SESSION_RETRY		13
+#define FRAME_TAG_SESSION_RETRY_GLOBAL	14
+#define FRAME_TAG_SESSION_RECONNECT_OK	15
+#define FRAME_TAG_WAIT			16
+#define FRAME_TAG_MESSAGE		17
+#define FRAME_TAG_KEEPALIVE2		18
+#define FRAME_TAG_KEEPALIVE2_ACK	19
+#define FRAME_TAG_ACK			20
+
+#define FRAME_LATE_STATUS_ABORTED	0x1
+#define FRAME_LATE_STATUS_COMPLETE	0xe
+#define FRAME_LATE_STATUS_ABORTED_MASK	0xf
+
+#define IN_S_HANDLE_PREAMBLE		1
+#define IN_S_HANDLE_CONTROL		2
+#define IN_S_HANDLE_CONTROL_REMAINDER	3
+#define IN_S_PREPARE_READ_DATA		4
+#define IN_S_PREPARE_READ_DATA_CONT	5
+#define IN_S_HANDLE_EPILOGUE		6
+#define IN_S_FINISH_SKIP		7
+
+#define OUT_S_QUEUE_DATA		1
+#define OUT_S_QUEUE_DATA_CONT		2
+#define OUT_S_QUEUE_ENC_PAGE		3
+#define OUT_S_QUEUE_ZEROS		4
+#define OUT_S_FINISH_MESSAGE		5
+#define OUT_S_GET_NEXT			6
+
+#define CTRL_BODY(p)	((void *)(p) + CEPH_PREAMBLE_LEN)
+#define FRONT_PAD(p)	((void *)(p) + CEPH_EPILOGUE_SECURE_LEN)
+#define MIDDLE_PAD(p)	(FRONT_PAD(p) + CEPH_GCM_BLOCK_LEN)
+#define DATA_PAD(p)	(MIDDLE_PAD(p) + CEPH_GCM_BLOCK_LEN)
+
+#define CEPH_MSG_FLAGS (MSG_DONTWAIT | MSG_NOSIGNAL)
+
+static int do_recvmsg(struct socket *sock, struct iov_iter *it)
+{
+	struct msghdr msg = { .msg_flags = CEPH_MSG_FLAGS };
+	int ret;
+
+	msg.msg_iter = *it;
+	while (iov_iter_count(it)) {
+		ret = sock_recvmsg(sock, &msg, msg.msg_flags);
+		if (ret <= 0) {
+			if (ret == -EAGAIN)
+				ret = 0;
+			return ret;
+		}
+
+		iov_iter_advance(it, ret);
+	}
+
+	WARN_ON(msg_data_left(&msg));
+	return 1;
+}
+
+/*
+ * Read as much as possible.
+ *
+ * Return:
+ *   1 - done, nothing (else) to read
+ *   0 - socket is empty, need to wait
+ *  <0 - error
+ */
+static int ceph_tcp_recv(struct ceph_connection *con)
+{
+	int ret;
+
+	dout("%s con %p %s %zu\n", __func__, con,
+	     iov_iter_is_discard(&con->v2.in_iter) ? "discard" : "need",
+	     iov_iter_count(&con->v2.in_iter));
+	ret = do_recvmsg(con->sock, &con->v2.in_iter);
+	dout("%s con %p ret %d left %zu\n", __func__, con, ret,
+	     iov_iter_count(&con->v2.in_iter));
+	return ret;
+}
+
+static int do_sendmsg(struct socket *sock, struct iov_iter *it)
+{
+	struct msghdr msg = { .msg_flags = CEPH_MSG_FLAGS };
+	int ret;
+
+	msg.msg_iter = *it;
+	while (iov_iter_count(it)) {
+		ret = sock_sendmsg(sock, &msg);
+		if (ret <= 0) {
+			if (ret == -EAGAIN)
+				ret = 0;
+			return ret;
+		}
+
+		iov_iter_advance(it, ret);
+	}
+
+	WARN_ON(msg_data_left(&msg));
+	return 1;
+}
+
+static int do_try_sendpage(struct socket *sock, struct iov_iter *it)
+{
+	struct msghdr msg = { .msg_flags = CEPH_MSG_FLAGS };
+	struct bio_vec bv;
+	int ret;
+
+	if (WARN_ON(!iov_iter_is_bvec(it)))
+		return -EINVAL;
+
+	while (iov_iter_count(it)) {
+		/* iov_iter_iovec() for ITER_BVEC */
+		bv.bv_page = it->bvec->bv_page;
+		bv.bv_offset = it->bvec->bv_offset + it->iov_offset;
+		bv.bv_len = min(iov_iter_count(it),
+				it->bvec->bv_len - it->iov_offset);
+
+		/*
+		 * sendpage cannot properly handle pages with
+		 * page_count == 0, we need to fall back to sendmsg if
+		 * that's the case.
+		 *
+		 * Same goes for slab pages: skb_can_coalesce() allows
+		 * coalescing neighboring slab objects into a single frag
+		 * which triggers one of hardened usercopy checks.
+		 */
+		if (sendpage_ok(bv.bv_page)) {
+			ret = sock->ops->sendpage(sock, bv.bv_page,
+						  bv.bv_offset, bv.bv_len,
+						  CEPH_MSG_FLAGS);
+		} else {
+			iov_iter_bvec(&msg.msg_iter, WRITE, &bv, 1, bv.bv_len);
+			ret = sock_sendmsg(sock, &msg);
+		}
+		if (ret <= 0) {
+			if (ret == -EAGAIN)
+				ret = 0;
+			return ret;
+		}
+
+		iov_iter_advance(it, ret);
+	}
+
+	return 1;
+}
+
+/*
+ * Write as much as possible.  The socket is expected to be corked,
+ * so we don't bother with MSG_MORE/MSG_SENDPAGE_NOTLAST here.
+ *
+ * Return:
+ *   1 - done, nothing (else) to write
+ *   0 - socket is full, need to wait
+ *  <0 - error
+ */
+static int ceph_tcp_send(struct ceph_connection *con)
+{
+	int ret;
+
+	dout("%s con %p have %zu try_sendpage %d\n", __func__, con,
+	     iov_iter_count(&con->v2.out_iter), con->v2.out_iter_sendpage);
+	if (con->v2.out_iter_sendpage)
+		ret = do_try_sendpage(con->sock, &con->v2.out_iter);
+	else
+		ret = do_sendmsg(con->sock, &con->v2.out_iter);
+	dout("%s con %p ret %d left %zu\n", __func__, con, ret,
+	     iov_iter_count(&con->v2.out_iter));
+	return ret;
+}
+
+static void add_in_kvec(struct ceph_connection *con, void *buf, int len)
+{
+	BUG_ON(con->v2.in_kvec_cnt >= ARRAY_SIZE(con->v2.in_kvecs));
+	WARN_ON(!iov_iter_is_kvec(&con->v2.in_iter));
+
+	con->v2.in_kvecs[con->v2.in_kvec_cnt].iov_base = buf;
+	con->v2.in_kvecs[con->v2.in_kvec_cnt].iov_len = len;
+	con->v2.in_kvec_cnt++;
+
+	con->v2.in_iter.nr_segs++;
+	con->v2.in_iter.count += len;
+}
+
+static void reset_in_kvecs(struct ceph_connection *con)
+{
+	WARN_ON(iov_iter_count(&con->v2.in_iter));
+
+	con->v2.in_kvec_cnt = 0;
+	iov_iter_kvec(&con->v2.in_iter, READ, con->v2.in_kvecs, 0, 0);
+}
+
+static void set_in_bvec(struct ceph_connection *con, const struct bio_vec *bv)
+{
+	WARN_ON(iov_iter_count(&con->v2.in_iter));
+
+	con->v2.in_bvec = *bv;
+	iov_iter_bvec(&con->v2.in_iter, READ, &con->v2.in_bvec, 1, bv->bv_len);
+}
+
+static void set_in_skip(struct ceph_connection *con, int len)
+{
+	WARN_ON(iov_iter_count(&con->v2.in_iter));
+
+	dout("%s con %p len %d\n", __func__, con, len);
+	iov_iter_discard(&con->v2.in_iter, READ, len);
+}
+
+static void add_out_kvec(struct ceph_connection *con, void *buf, int len)
+{
+	BUG_ON(con->v2.out_kvec_cnt >= ARRAY_SIZE(con->v2.out_kvecs));
+	WARN_ON(!iov_iter_is_kvec(&con->v2.out_iter));
+	WARN_ON(con->v2.out_zero);
+
+	con->v2.out_kvecs[con->v2.out_kvec_cnt].iov_base = buf;
+	con->v2.out_kvecs[con->v2.out_kvec_cnt].iov_len = len;
+	con->v2.out_kvec_cnt++;
+
+	con->v2.out_iter.nr_segs++;
+	con->v2.out_iter.count += len;
+}
+
+static void reset_out_kvecs(struct ceph_connection *con)
+{
+	WARN_ON(iov_iter_count(&con->v2.out_iter));
+	WARN_ON(con->v2.out_zero);
+
+	con->v2.out_kvec_cnt = 0;
+
+	iov_iter_kvec(&con->v2.out_iter, WRITE, con->v2.out_kvecs, 0, 0);
+	con->v2.out_iter_sendpage = false;
+}
+
+static void set_out_bvec(struct ceph_connection *con, const struct bio_vec *bv,
+			 bool zerocopy)
+{
+	WARN_ON(iov_iter_count(&con->v2.out_iter));
+	WARN_ON(con->v2.out_zero);
+
+	con->v2.out_bvec = *bv;
+	con->v2.out_iter_sendpage = zerocopy;
+	iov_iter_bvec(&con->v2.out_iter, WRITE, &con->v2.out_bvec, 1,
+		      con->v2.out_bvec.bv_len);
+}
+
+static void set_out_bvec_zero(struct ceph_connection *con)
+{
+	WARN_ON(iov_iter_count(&con->v2.out_iter));
+	WARN_ON(!con->v2.out_zero);
+
+	con->v2.out_bvec.bv_page = ceph_zero_page;
+	con->v2.out_bvec.bv_offset = 0;
+	con->v2.out_bvec.bv_len = min(con->v2.out_zero, (int)PAGE_SIZE);
+	con->v2.out_iter_sendpage = true;
+	iov_iter_bvec(&con->v2.out_iter, WRITE, &con->v2.out_bvec, 1,
+		      con->v2.out_bvec.bv_len);
+}
+
+static void out_zero_add(struct ceph_connection *con, int len)
+{
+	dout("%s con %p len %d\n", __func__, con, len);
+	con->v2.out_zero += len;
+}
+
+static void *alloc_conn_buf(struct ceph_connection *con, int len)
+{
+	void *buf;
+
+	dout("%s con %p len %d\n", __func__, con, len);
+
+	if (WARN_ON(con->v2.conn_buf_cnt >= ARRAY_SIZE(con->v2.conn_bufs)))
+		return NULL;
+
+	buf = ceph_kvmalloc(len, GFP_NOIO);
+	if (!buf)
+		return NULL;
+
+	con->v2.conn_bufs[con->v2.conn_buf_cnt++] = buf;
+	return buf;
+}
+
+static void free_conn_bufs(struct ceph_connection *con)
+{
+	while (con->v2.conn_buf_cnt)
+		kvfree(con->v2.conn_bufs[--con->v2.conn_buf_cnt]);
+}
+
+static void add_in_sign_kvec(struct ceph_connection *con, void *buf, int len)
+{
+	BUG_ON(con->v2.in_sign_kvec_cnt >= ARRAY_SIZE(con->v2.in_sign_kvecs));
+
+	con->v2.in_sign_kvecs[con->v2.in_sign_kvec_cnt].iov_base = buf;
+	con->v2.in_sign_kvecs[con->v2.in_sign_kvec_cnt].iov_len = len;
+	con->v2.in_sign_kvec_cnt++;
+}
+
+static void clear_in_sign_kvecs(struct ceph_connection *con)
+{
+	con->v2.in_sign_kvec_cnt = 0;
+}
+
+static void add_out_sign_kvec(struct ceph_connection *con, void *buf, int len)
+{
+	BUG_ON(con->v2.out_sign_kvec_cnt >= ARRAY_SIZE(con->v2.out_sign_kvecs));
+
+	con->v2.out_sign_kvecs[con->v2.out_sign_kvec_cnt].iov_base = buf;
+	con->v2.out_sign_kvecs[con->v2.out_sign_kvec_cnt].iov_len = len;
+	con->v2.out_sign_kvec_cnt++;
+}
+
+static void clear_out_sign_kvecs(struct ceph_connection *con)
+{
+	con->v2.out_sign_kvec_cnt = 0;
+}
+
+static bool con_secure(struct ceph_connection *con)
+{
+	return con->v2.con_mode == CEPH_CON_MODE_SECURE;
+}
+
+static int front_len(const struct ceph_msg *msg)
+{
+	return le32_to_cpu(msg->hdr.front_len);
+}
+
+static int middle_len(const struct ceph_msg *msg)
+{
+	return le32_to_cpu(msg->hdr.middle_len);
+}
+
+static int data_len(const struct ceph_msg *msg)
+{
+	return le32_to_cpu(msg->hdr.data_len);
+}
+
+static bool need_padding(int len)
+{
+	return !IS_ALIGNED(len, CEPH_GCM_BLOCK_LEN);
+}
+
+static int padded_len(int len)
+{
+	return ALIGN(len, CEPH_GCM_BLOCK_LEN);
+}
+
+static int padding_len(int len)
+{
+	return padded_len(len) - len;
+}
+
+/* preamble + control segment */
+static int head_onwire_len(int ctrl_len, bool secure)
+{
+	int head_len;
+	int rem_len;
+
+	if (secure) {
+		head_len = CEPH_PREAMBLE_SECURE_LEN;
+		if (ctrl_len > CEPH_PREAMBLE_INLINE_LEN) {
+			rem_len = ctrl_len - CEPH_PREAMBLE_INLINE_LEN;
+			head_len += padded_len(rem_len) + CEPH_GCM_TAG_LEN;
+		}
+	} else {
+		head_len = CEPH_PREAMBLE_PLAIN_LEN;
+		if (ctrl_len)
+			head_len += ctrl_len + CEPH_CRC_LEN;
+	}
+	return head_len;
+}
+
+/* front, middle and data segments + epilogue */
+static int __tail_onwire_len(int front_len, int middle_len, int data_len,
+			     bool secure)
+{
+	if (!front_len && !middle_len && !data_len)
+		return 0;
+
+	if (!secure)
+		return front_len + middle_len + data_len +
+		       CEPH_EPILOGUE_PLAIN_LEN;
+
+	return padded_len(front_len) + padded_len(middle_len) +
+	       padded_len(data_len) + CEPH_EPILOGUE_SECURE_LEN;
+}
+
+static int tail_onwire_len(const struct ceph_msg *msg, bool secure)
+{
+	return __tail_onwire_len(front_len(msg), middle_len(msg),
+				 data_len(msg), secure);
+}
+
+/* head_onwire_len(sizeof(struct ceph_msg_header2), false) */
+#define MESSAGE_HEAD_PLAIN_LEN	(CEPH_PREAMBLE_PLAIN_LEN +		\
+				 sizeof(struct ceph_msg_header2) +	\
+				 CEPH_CRC_LEN)
+
+static const int frame_aligns[] = {
+	sizeof(void *),
+	sizeof(void *),
+	sizeof(void *),
+	PAGE_SIZE
+};
+
+/*
+ * Discards trailing empty segments, unless there is just one segment.
+ * A frame always has at least one (possibly empty) segment.
+ */
+static int calc_segment_count(const int *lens, int len_cnt)
+{
+	int i;
+
+	for (i = len_cnt - 1; i >= 0; i--) {
+		if (lens[i])
+			return i + 1;
+	}
+
+	return 1;
+}
+
+static void init_frame_desc(struct ceph_frame_desc *desc, int tag,
+			    const int *lens, int len_cnt)
+{
+	int i;
+
+	memset(desc, 0, sizeof(*desc));
+
+	desc->fd_tag = tag;
+	desc->fd_seg_cnt = calc_segment_count(lens, len_cnt);
+	BUG_ON(desc->fd_seg_cnt > CEPH_FRAME_MAX_SEGMENT_COUNT);
+	for (i = 0; i < desc->fd_seg_cnt; i++) {
+		desc->fd_lens[i] = lens[i];
+		desc->fd_aligns[i] = frame_aligns[i];
+	}
+}
+
+/*
+ * Preamble crc covers everything up to itself (28 bytes) and
+ * is calculated and verified irrespective of the connection mode
+ * (i.e. even if the frame is encrypted).
+ */
+static void encode_preamble(const struct ceph_frame_desc *desc, void *p)
+{
+	void *crcp = p + CEPH_PREAMBLE_LEN - CEPH_CRC_LEN;
+	void *start = p;
+	int i;
+
+	memset(p, 0, CEPH_PREAMBLE_LEN);
+
+	ceph_encode_8(&p, desc->fd_tag);
+	ceph_encode_8(&p, desc->fd_seg_cnt);
+	for (i = 0; i < desc->fd_seg_cnt; i++) {
+		ceph_encode_32(&p, desc->fd_lens[i]);
+		ceph_encode_16(&p, desc->fd_aligns[i]);
+	}
+
+	put_unaligned_le32(crc32c(0, start, crcp - start), crcp);
+}
+
+static int decode_preamble(void *p, struct ceph_frame_desc *desc)
+{
+	void *crcp = p + CEPH_PREAMBLE_LEN - CEPH_CRC_LEN;
+	u32 crc, expected_crc;
+	int i;
+
+	crc = crc32c(0, p, crcp - p);
+	expected_crc = get_unaligned_le32(crcp);
+	if (crc != expected_crc) {
+		pr_err("bad preamble crc, calculated %u, expected %u\n",
+		       crc, expected_crc);
+		return -EBADMSG;
+	}
+
+	memset(desc, 0, sizeof(*desc));
+
+	desc->fd_tag = ceph_decode_8(&p);
+	desc->fd_seg_cnt = ceph_decode_8(&p);
+	if (desc->fd_seg_cnt < 1 ||
+	    desc->fd_seg_cnt > CEPH_FRAME_MAX_SEGMENT_COUNT) {
+		pr_err("bad segment count %d\n", desc->fd_seg_cnt);
+		return -EINVAL;
+	}
+	for (i = 0; i < desc->fd_seg_cnt; i++) {
+		desc->fd_lens[i] = ceph_decode_32(&p);
+		desc->fd_aligns[i] = ceph_decode_16(&p);
+	}
+
+	/*
+	 * This would fire for FRAME_TAG_WAIT (it has one empty
+	 * segment), but we should never get it as client.
+	 */
+	if (!desc->fd_lens[desc->fd_seg_cnt - 1]) {
+		pr_err("last segment empty\n");
+		return -EINVAL;
+	}
+
+	if (desc->fd_lens[0] > CEPH_MSG_MAX_CONTROL_LEN) {
+		pr_err("control segment too big %d\n", desc->fd_lens[0]);
+		return -EINVAL;
+	}
+	if (desc->fd_lens[1] > CEPH_MSG_MAX_FRONT_LEN) {
+		pr_err("front segment too big %d\n", desc->fd_lens[1]);
+		return -EINVAL;
+	}
+	if (desc->fd_lens[2] > CEPH_MSG_MAX_MIDDLE_LEN) {
+		pr_err("middle segment too big %d\n", desc->fd_lens[2]);
+		return -EINVAL;
+	}
+	if (desc->fd_lens[3] > CEPH_MSG_MAX_DATA_LEN) {
+		pr_err("data segment too big %d\n", desc->fd_lens[3]);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void encode_epilogue_plain(struct ceph_connection *con, bool aborted)
+{
+	con->v2.out_epil.late_status = aborted ? FRAME_LATE_STATUS_ABORTED :
+						 FRAME_LATE_STATUS_COMPLETE;
+	cpu_to_le32s(&con->v2.out_epil.front_crc);
+	cpu_to_le32s(&con->v2.out_epil.middle_crc);
+	cpu_to_le32s(&con->v2.out_epil.data_crc);
+}
+
+static void encode_epilogue_secure(struct ceph_connection *con, bool aborted)
+{
+	memset(&con->v2.out_epil, 0, sizeof(con->v2.out_epil));
+	con->v2.out_epil.late_status = aborted ? FRAME_LATE_STATUS_ABORTED :
+						 FRAME_LATE_STATUS_COMPLETE;
+}
+
+static int decode_epilogue(void *p, u32 *front_crc, u32 *middle_crc,
+			   u32 *data_crc)
+{
+	u8 late_status;
+
+	late_status = ceph_decode_8(&p);
+	if ((late_status & FRAME_LATE_STATUS_ABORTED_MASK) !=
+			FRAME_LATE_STATUS_COMPLETE) {
+		/* we should never get an aborted message as client */
+		pr_err("bad late_status 0x%x\n", late_status);
+		return -EINVAL;
+	}
+
+	if (front_crc && middle_crc && data_crc) {
+		*front_crc = ceph_decode_32(&p);
+		*middle_crc = ceph_decode_32(&p);
+		*data_crc = ceph_decode_32(&p);
+	}
+
+	return 0;
+}
+
+static void fill_header(struct ceph_msg_header *hdr,
+			const struct ceph_msg_header2 *hdr2,
+			int front_len, int middle_len, int data_len,
+			const struct ceph_entity_name *peer_name)
+{
+	hdr->seq = hdr2->seq;
+	hdr->tid = hdr2->tid;
+	hdr->type = hdr2->type;
+	hdr->priority = hdr2->priority;
+	hdr->version = hdr2->version;
+	hdr->front_len = cpu_to_le32(front_len);
+	hdr->middle_len = cpu_to_le32(middle_len);
+	hdr->data_len = cpu_to_le32(data_len);
+	hdr->data_off = hdr2->data_off;
+	hdr->src = *peer_name;
+	hdr->compat_version = hdr2->compat_version;
+	hdr->reserved = 0;
+	hdr->crc = 0;
+}
+
+static void fill_header2(struct ceph_msg_header2 *hdr2,
+			 const struct ceph_msg_header *hdr, u64 ack_seq)
+{
+	hdr2->seq = hdr->seq;
+	hdr2->tid = hdr->tid;
+	hdr2->type = hdr->type;
+	hdr2->priority = hdr->priority;
+	hdr2->version = hdr->version;
+	hdr2->data_pre_padding_len = 0;
+	hdr2->data_off = hdr->data_off;
+	hdr2->ack_seq = cpu_to_le64(ack_seq);
+	hdr2->flags = 0;
+	hdr2->compat_version = hdr->compat_version;
+	hdr2->reserved = 0;
+}
+
+static int verify_control_crc(struct ceph_connection *con)
+{
+	int ctrl_len = con->v2.in_desc.fd_lens[0];
+	u32 crc, expected_crc;
+
+	WARN_ON(con->v2.in_kvecs[0].iov_len != ctrl_len);
+	WARN_ON(con->v2.in_kvecs[1].iov_len != CEPH_CRC_LEN);
+
+	crc = crc32c(-1, con->v2.in_kvecs[0].iov_base, ctrl_len);
+	expected_crc = get_unaligned_le32(con->v2.in_kvecs[1].iov_base);
+	if (crc != expected_crc) {
+		pr_err("bad control crc, calculated %u, expected %u\n",
+		       crc, expected_crc);
+		return -EBADMSG;
+	}
+
+	return 0;
+}
+
+static int verify_epilogue_crcs(struct ceph_connection *con, u32 front_crc,
+				u32 middle_crc, u32 data_crc)
+{
+	if (front_len(con->in_msg)) {
+		con->in_front_crc = crc32c(-1, con->in_msg->front.iov_base,
+					   front_len(con->in_msg));
+	} else {
+		WARN_ON(!middle_len(con->in_msg) && !data_len(con->in_msg));
+		con->in_front_crc = -1;
+	}
+
+	if (middle_len(con->in_msg))
+		con->in_middle_crc = crc32c(-1,
+					    con->in_msg->middle->vec.iov_base,
+					    middle_len(con->in_msg));
+	else if (data_len(con->in_msg))
+		con->in_middle_crc = -1;
+	else
+		con->in_middle_crc = 0;
+
+	if (!data_len(con->in_msg))
+		con->in_data_crc = 0;
+
+	dout("%s con %p msg %p crcs %u %u %u\n", __func__, con, con->in_msg,
+	     con->in_front_crc, con->in_middle_crc, con->in_data_crc);
+
+	if (con->in_front_crc != front_crc) {
+		pr_err("bad front crc, calculated %u, expected %u\n",
+		       con->in_front_crc, front_crc);
+		return -EBADMSG;
+	}
+	if (con->in_middle_crc != middle_crc) {
+		pr_err("bad middle crc, calculated %u, expected %u\n",
+		       con->in_middle_crc, middle_crc);
+		return -EBADMSG;
+	}
+	if (con->in_data_crc != data_crc) {
+		pr_err("bad data crc, calculated %u, expected %u\n",
+		       con->in_data_crc, data_crc);
+		return -EBADMSG;
+	}
+
+	return 0;
+}
+
+static int setup_crypto(struct ceph_connection *con,
+			u8 *session_key, int session_key_len,
+			u8 *con_secret, int con_secret_len)
+{
+	unsigned int noio_flag;
+	void *p;
+	int ret;
+
+	dout("%s con %p con_mode %d session_key_len %d con_secret_len %d\n",
+	     __func__, con, con->v2.con_mode, session_key_len, con_secret_len);
+	WARN_ON(con->v2.hmac_tfm || con->v2.gcm_tfm || con->v2.gcm_req);
+
+	if (con->v2.con_mode != CEPH_CON_MODE_CRC &&
+	    con->v2.con_mode != CEPH_CON_MODE_SECURE) {
+		pr_err("bad con_mode %d\n", con->v2.con_mode);
+		return -EINVAL;
+	}
+
+	if (!session_key_len) {
+		WARN_ON(con->v2.con_mode != CEPH_CON_MODE_CRC);
+		WARN_ON(con_secret_len);
+		return 0;  /* auth_none */
+	}
+
+	noio_flag = memalloc_noio_save();
+	con->v2.hmac_tfm = crypto_alloc_shash("hmac(sha256)", 0, 0);
+	memalloc_noio_restore(noio_flag);
+	if (IS_ERR(con->v2.hmac_tfm)) {
+		ret = PTR_ERR(con->v2.hmac_tfm);
+		con->v2.hmac_tfm = NULL;
+		pr_err("failed to allocate hmac tfm context: %d\n", ret);
+		return ret;
+	}
+
+	WARN_ON((unsigned long)session_key &
+		crypto_shash_alignmask(con->v2.hmac_tfm));
+	ret = crypto_shash_setkey(con->v2.hmac_tfm, session_key,
+				  session_key_len);
+	if (ret) {
+		pr_err("failed to set hmac key: %d\n", ret);
+		return ret;
+	}
+
+	if (con->v2.con_mode == CEPH_CON_MODE_CRC) {
+		WARN_ON(con_secret_len);
+		return 0;  /* auth_x, plain mode */
+	}
+
+	if (con_secret_len < CEPH_GCM_KEY_LEN + 2 * CEPH_GCM_IV_LEN) {
+		pr_err("con_secret too small %d\n", con_secret_len);
+		return -EINVAL;
+	}
+
+	noio_flag = memalloc_noio_save();
+	con->v2.gcm_tfm = crypto_alloc_aead("gcm(aes)", 0, 0);
+	memalloc_noio_restore(noio_flag);
+	if (IS_ERR(con->v2.gcm_tfm)) {
+		ret = PTR_ERR(con->v2.gcm_tfm);
+		con->v2.gcm_tfm = NULL;
+		pr_err("failed to allocate gcm tfm context: %d\n", ret);
+		return ret;
+	}
+
+	p = con_secret;
+	WARN_ON((unsigned long)p & crypto_aead_alignmask(con->v2.gcm_tfm));
+	ret = crypto_aead_setkey(con->v2.gcm_tfm, p, CEPH_GCM_KEY_LEN);
+	if (ret) {
+		pr_err("failed to set gcm key: %d\n", ret);
+		return ret;
+	}
+
+	p += CEPH_GCM_KEY_LEN;
+	WARN_ON(crypto_aead_ivsize(con->v2.gcm_tfm) != CEPH_GCM_IV_LEN);
+	ret = crypto_aead_setauthsize(con->v2.gcm_tfm, CEPH_GCM_TAG_LEN);
+	if (ret) {
+		pr_err("failed to set gcm tag size: %d\n", ret);
+		return ret;
+	}
+
+	con->v2.gcm_req = aead_request_alloc(con->v2.gcm_tfm, GFP_NOIO);
+	if (!con->v2.gcm_req) {
+		pr_err("failed to allocate gcm request\n");
+		return -ENOMEM;
+	}
+
+	crypto_init_wait(&con->v2.gcm_wait);
+	aead_request_set_callback(con->v2.gcm_req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+				  crypto_req_done, &con->v2.gcm_wait);
+
+	memcpy(&con->v2.in_gcm_nonce, p, CEPH_GCM_IV_LEN);
+	memcpy(&con->v2.out_gcm_nonce, p + CEPH_GCM_IV_LEN, CEPH_GCM_IV_LEN);
+	return 0;  /* auth_x, secure mode */
+}
+
+static int hmac_sha256(struct ceph_connection *con, const struct kvec *kvecs,
+		       int kvec_cnt, u8 *hmac)
+{
+	SHASH_DESC_ON_STACK(desc, con->v2.hmac_tfm);  /* tfm arg is ignored */
+	int ret;
+	int i;
+
+	dout("%s con %p hmac_tfm %p kvec_cnt %d\n", __func__, con,
+	     con->v2.hmac_tfm, kvec_cnt);
+
+	if (!con->v2.hmac_tfm) {
+		memset(hmac, 0, SHA256_DIGEST_SIZE);
+		return 0;  /* auth_none */
+	}
+
+	desc->tfm = con->v2.hmac_tfm;
+	ret = crypto_shash_init(desc);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < kvec_cnt; i++) {
+		WARN_ON((unsigned long)kvecs[i].iov_base &
+			crypto_shash_alignmask(con->v2.hmac_tfm));
+		ret = crypto_shash_update(desc, kvecs[i].iov_base,
+					  kvecs[i].iov_len);
+		if (ret)
+			return ret;
+	}
+
+	ret = crypto_shash_final(desc, hmac);
+	if (ret)
+		return ret;
+
+	shash_desc_zero(desc);
+	return 0;  /* auth_x, both plain and secure modes */
+}
+
+static void gcm_inc_nonce(struct ceph_gcm_nonce *nonce)
+{
+	u64 counter;
+
+	counter = le64_to_cpu(nonce->counter);
+	nonce->counter = cpu_to_le64(counter + 1);
+}
+
+static int gcm_crypt(struct ceph_connection *con, bool encrypt,
+		     struct scatterlist *src, struct scatterlist *dst,
+		     int src_len)
+{
+	struct ceph_gcm_nonce *nonce;
+	int ret;
+
+	nonce = encrypt ? &con->v2.out_gcm_nonce : &con->v2.in_gcm_nonce;
+
+	aead_request_set_ad(con->v2.gcm_req, 0);  /* no AAD */
+	aead_request_set_crypt(con->v2.gcm_req, src, dst, src_len, (u8 *)nonce);
+	ret = crypto_wait_req(encrypt ? crypto_aead_encrypt(con->v2.gcm_req) :
+					crypto_aead_decrypt(con->v2.gcm_req),
+			      &con->v2.gcm_wait);
+	if (ret)
+		return ret;
+
+	gcm_inc_nonce(nonce);
+	return 0;
+}
+
+static void get_bvec_at(struct ceph_msg_data_cursor *cursor,
+			struct bio_vec *bv)
+{
+	struct page *page;
+	size_t off, len;
+
+	WARN_ON(!cursor->total_resid);
+
+	/* skip zero-length data items */
+	while (!cursor->resid)
+		ceph_msg_data_advance(cursor, 0);
+
+	/* get a piece of data, cursor isn't advanced */
+	page = ceph_msg_data_next(cursor, &off, &len, NULL);
+
+	bv->bv_page = page;
+	bv->bv_offset = off;
+	bv->bv_len = len;
+}
+
+static int calc_sg_cnt(void *buf, int buf_len)
+{
+	int sg_cnt;
+
+	if (!buf_len)
+		return 0;
+
+	sg_cnt = need_padding(buf_len) ? 1 : 0;
+	if (is_vmalloc_addr(buf)) {
+		WARN_ON(offset_in_page(buf));
+		sg_cnt += PAGE_ALIGN(buf_len) >> PAGE_SHIFT;
+	} else {
+		sg_cnt++;
+	}
+
+	return sg_cnt;
+}
+
+static int calc_sg_cnt_cursor(struct ceph_msg_data_cursor *cursor)
+{
+	int data_len = cursor->total_resid;
+	struct bio_vec bv;
+	int sg_cnt;
+
+	if (!data_len)
+		return 0;
+
+	sg_cnt = need_padding(data_len) ? 1 : 0;
+	do {
+		get_bvec_at(cursor, &bv);
+		sg_cnt++;
+
+		ceph_msg_data_advance(cursor, bv.bv_len);
+	} while (cursor->total_resid);
+
+	return sg_cnt;
+}
+
+static void init_sgs(struct scatterlist **sg, void *buf, int buf_len, u8 *pad)
+{
+	void *end = buf + buf_len;
+	struct page *page;
+	int len;
+	void *p;
+
+	if (!buf_len)
+		return;
+
+	if (is_vmalloc_addr(buf)) {
+		p = buf;
+		do {
+			page = vmalloc_to_page(p);
+			len = min_t(int, end - p, PAGE_SIZE);
+			WARN_ON(!page || !len || offset_in_page(p));
+			sg_set_page(*sg, page, len, 0);
+			*sg = sg_next(*sg);
+			p += len;
+		} while (p != end);
+	} else {
+		sg_set_buf(*sg, buf, buf_len);
+		*sg = sg_next(*sg);
+	}
+
+	if (need_padding(buf_len)) {
+		sg_set_buf(*sg, pad, padding_len(buf_len));
+		*sg = sg_next(*sg);
+	}
+}
+
+static void init_sgs_cursor(struct scatterlist **sg,
+			    struct ceph_msg_data_cursor *cursor, u8 *pad)
+{
+	int data_len = cursor->total_resid;
+	struct bio_vec bv;
+
+	if (!data_len)
+		return;
+
+	do {
+		get_bvec_at(cursor, &bv);
+		sg_set_page(*sg, bv.bv_page, bv.bv_len, bv.bv_offset);
+		*sg = sg_next(*sg);
+
+		ceph_msg_data_advance(cursor, bv.bv_len);
+	} while (cursor->total_resid);
+
+	if (need_padding(data_len)) {
+		sg_set_buf(*sg, pad, padding_len(data_len));
+		*sg = sg_next(*sg);
+	}
+}
+
+static int setup_message_sgs(struct sg_table *sgt, struct ceph_msg *msg,
+			     u8 *front_pad, u8 *middle_pad, u8 *data_pad,
+			     void *epilogue, bool add_tag)
+{
+	struct ceph_msg_data_cursor cursor;
+	struct scatterlist *cur_sg;
+	int sg_cnt;
+	int ret;
+
+	if (!front_len(msg) && !middle_len(msg) && !data_len(msg))
+		return 0;
+
+	sg_cnt = 1;  /* epilogue + [auth tag] */
+	if (front_len(msg))
+		sg_cnt += calc_sg_cnt(msg->front.iov_base,
+				      front_len(msg));
+	if (middle_len(msg))
+		sg_cnt += calc_sg_cnt(msg->middle->vec.iov_base,
+				      middle_len(msg));
+	if (data_len(msg)) {
+		ceph_msg_data_cursor_init(&cursor, msg, data_len(msg));
+		sg_cnt += calc_sg_cnt_cursor(&cursor);
+	}
+
+	ret = sg_alloc_table(sgt, sg_cnt, GFP_NOIO);
+	if (ret)
+		return ret;
+
+	cur_sg = sgt->sgl;
+	if (front_len(msg))
+		init_sgs(&cur_sg, msg->front.iov_base, front_len(msg),
+			 front_pad);
+	if (middle_len(msg))
+		init_sgs(&cur_sg, msg->middle->vec.iov_base, middle_len(msg),
+			 middle_pad);
+	if (data_len(msg)) {
+		ceph_msg_data_cursor_init(&cursor, msg, data_len(msg));
+		init_sgs_cursor(&cur_sg, &cursor, data_pad);
+	}
+
+	WARN_ON(!sg_is_last(cur_sg));
+	sg_set_buf(cur_sg, epilogue,
+		   CEPH_GCM_BLOCK_LEN + (add_tag ? CEPH_GCM_TAG_LEN : 0));
+	return 0;
+}
+
+static int decrypt_preamble(struct ceph_connection *con)
+{
+	struct scatterlist sg;
+
+	sg_init_one(&sg, con->v2.in_buf, CEPH_PREAMBLE_SECURE_LEN);
+	return gcm_crypt(con, false, &sg, &sg, CEPH_PREAMBLE_SECURE_LEN);
+}
+
+static int decrypt_control_remainder(struct ceph_connection *con)
+{
+	int ctrl_len = con->v2.in_desc.fd_lens[0];
+	int rem_len = ctrl_len - CEPH_PREAMBLE_INLINE_LEN;
+	int pt_len = padding_len(rem_len) + CEPH_GCM_TAG_LEN;
+	struct scatterlist sgs[2];
+
+	WARN_ON(con->v2.in_kvecs[0].iov_len != rem_len);
+	WARN_ON(con->v2.in_kvecs[1].iov_len != pt_len);
+
+	sg_init_table(sgs, 2);
+	sg_set_buf(&sgs[0], con->v2.in_kvecs[0].iov_base, rem_len);
+	sg_set_buf(&sgs[1], con->v2.in_buf, pt_len);
+
+	return gcm_crypt(con, false, sgs, sgs,
+			 padded_len(rem_len) + CEPH_GCM_TAG_LEN);
+}
+
+static int decrypt_message(struct ceph_connection *con)
+{
+	struct sg_table sgt = {};
+	int ret;
+
+	ret = setup_message_sgs(&sgt, con->in_msg, FRONT_PAD(con->v2.in_buf),
+			MIDDLE_PAD(con->v2.in_buf), DATA_PAD(con->v2.in_buf),
+			con->v2.in_buf, true);
+	if (ret)
+		goto out;
+
+	ret = gcm_crypt(con, false, sgt.sgl, sgt.sgl,
+			tail_onwire_len(con->in_msg, true));
+
+out:
+	sg_free_table(&sgt);
+	return ret;
+}
+
+static int prepare_banner(struct ceph_connection *con)
+{
+	int buf_len = CEPH_BANNER_V2_LEN + 2 + 8 + 8;
+	void *buf, *p;
+
+	buf = alloc_conn_buf(con, buf_len);
+	if (!buf)
+		return -ENOMEM;
+
+	p = buf;
+	ceph_encode_copy(&p, CEPH_BANNER_V2, CEPH_BANNER_V2_LEN);
+	ceph_encode_16(&p, sizeof(u64) + sizeof(u64));
+	ceph_encode_64(&p, CEPH_MSGR2_SUPPORTED_FEATURES);
+	ceph_encode_64(&p, CEPH_MSGR2_REQUIRED_FEATURES);
+	WARN_ON(p != buf + buf_len);
+
+	add_out_kvec(con, buf, buf_len);
+	add_out_sign_kvec(con, buf, buf_len);
+	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
+	return 0;
+}
+
+/*
+ * base:
+ *   preamble
+ *   control body (ctrl_len bytes)
+ *   space for control crc
+ *
+ * extdata (optional):
+ *   control body (extdata_len bytes)
+ *
+ * Compute control crc and gather base and extdata into:
+ *
+ *   preamble
+ *   control body (ctrl_len + extdata_len bytes)
+ *   control crc
+ *
+ * Preamble should already be encoded at the start of base.
+ */
+static void prepare_head_plain(struct ceph_connection *con, void *base,
+			       int ctrl_len, void *extdata, int extdata_len,
+			       bool to_be_signed)
+{
+	int base_len = CEPH_PREAMBLE_LEN + ctrl_len + CEPH_CRC_LEN;
+	void *crcp = base + base_len - CEPH_CRC_LEN;
+	u32 crc;
+
+	crc = crc32c(-1, CTRL_BODY(base), ctrl_len);
+	if (extdata_len)
+		crc = crc32c(crc, extdata, extdata_len);
+	put_unaligned_le32(crc, crcp);
+
+	if (!extdata_len) {
+		add_out_kvec(con, base, base_len);
+		if (to_be_signed)
+			add_out_sign_kvec(con, base, base_len);
+		return;
+	}
+
+	add_out_kvec(con, base, crcp - base);
+	add_out_kvec(con, extdata, extdata_len);
+	add_out_kvec(con, crcp, CEPH_CRC_LEN);
+	if (to_be_signed) {
+		add_out_sign_kvec(con, base, crcp - base);
+		add_out_sign_kvec(con, extdata, extdata_len);
+		add_out_sign_kvec(con, crcp, CEPH_CRC_LEN);
+	}
+}
+
+static int prepare_head_secure_small(struct ceph_connection *con,
+				     void *base, int ctrl_len)
+{
+	struct scatterlist sg;
+	int ret;
+
+	/* inline buffer padding? */
+	if (ctrl_len < CEPH_PREAMBLE_INLINE_LEN)
+		memset(CTRL_BODY(base) + ctrl_len, 0,
+		       CEPH_PREAMBLE_INLINE_LEN - ctrl_len);
+
+	sg_init_one(&sg, base, CEPH_PREAMBLE_SECURE_LEN);
+	ret = gcm_crypt(con, true, &sg, &sg,
+			CEPH_PREAMBLE_SECURE_LEN - CEPH_GCM_TAG_LEN);
+	if (ret)
+		return ret;
+
+	add_out_kvec(con, base, CEPH_PREAMBLE_SECURE_LEN);
+	return 0;
+}
+
+/*
+ * base:
+ *   preamble
+ *   control body (ctrl_len bytes)
+ *   space for padding, if needed
+ *   space for control remainder auth tag
+ *   space for preamble auth tag
+ *
+ * Encrypt preamble and the inline portion, then encrypt the remainder
+ * and gather into:
+ *
+ *   preamble
+ *   control body (48 bytes)
+ *   preamble auth tag
+ *   control body (ctrl_len - 48 bytes)
+ *   zero padding, if needed
+ *   control remainder auth tag
+ *
+ * Preamble should already be encoded at the start of base.
+ */
+static int prepare_head_secure_big(struct ceph_connection *con,
+				   void *base, int ctrl_len)
+{
+	int rem_len = ctrl_len - CEPH_PREAMBLE_INLINE_LEN;
+	void *rem = CTRL_BODY(base) + CEPH_PREAMBLE_INLINE_LEN;
+	void *rem_tag = rem + padded_len(rem_len);
+	void *pmbl_tag = rem_tag + CEPH_GCM_TAG_LEN;
+	struct scatterlist sgs[2];
+	int ret;
+
+	sg_init_table(sgs, 2);
+	sg_set_buf(&sgs[0], base, rem - base);
+	sg_set_buf(&sgs[1], pmbl_tag, CEPH_GCM_TAG_LEN);
+	ret = gcm_crypt(con, true, sgs, sgs, rem - base);
+	if (ret)
+		return ret;
+
+	/* control remainder padding? */
+	if (need_padding(rem_len))
+		memset(rem + rem_len, 0, padding_len(rem_len));
+
+	sg_init_one(&sgs[0], rem, pmbl_tag - rem);
+	ret = gcm_crypt(con, true, sgs, sgs, rem_tag - rem);
+	if (ret)
+		return ret;
+
+	add_out_kvec(con, base, rem - base);
+	add_out_kvec(con, pmbl_tag, CEPH_GCM_TAG_LEN);
+	add_out_kvec(con, rem, pmbl_tag - rem);
+	return 0;
+}
+
+static int __prepare_control(struct ceph_connection *con, int tag,
+			     void *base, int ctrl_len, void *extdata,
+			     int extdata_len, bool to_be_signed)
+{
+	int total_len = ctrl_len + extdata_len;
+	struct ceph_frame_desc desc;
+	int ret;
+
+	dout("%s con %p tag %d len %d (%d+%d)\n", __func__, con, tag,
+	     total_len, ctrl_len, extdata_len);
+
+	/* extdata may be vmalloc'ed but not base */
+	if (WARN_ON(is_vmalloc_addr(base) || !ctrl_len))
+		return -EINVAL;
+
+	init_frame_desc(&desc, tag, &total_len, 1);
+	encode_preamble(&desc, base);
+
+	if (con_secure(con)) {
+		if (WARN_ON(extdata_len || to_be_signed))
+			return -EINVAL;
+
+		if (ctrl_len <= CEPH_PREAMBLE_INLINE_LEN)
+			/* fully inlined, inline buffer may need padding */
+			ret = prepare_head_secure_small(con, base, ctrl_len);
+		else
+			/* partially inlined, inline buffer is full */
+			ret = prepare_head_secure_big(con, base, ctrl_len);
+		if (ret)
+			return ret;
+	} else {
+		prepare_head_plain(con, base, ctrl_len, extdata, extdata_len,
+				   to_be_signed);
+	}
+
+	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
+	return 0;
+}
+
+static int prepare_control(struct ceph_connection *con, int tag,
+			   void *base, int ctrl_len)
+{
+	return __prepare_control(con, tag, base, ctrl_len, NULL, 0, false);
+}
+
+static int prepare_hello(struct ceph_connection *con)
+{
+	void *buf, *p;
+	int ctrl_len;
+
+	ctrl_len = 1 + ceph_entity_addr_encoding_len(&con->peer_addr);
+	buf = alloc_conn_buf(con, head_onwire_len(ctrl_len, false));
+	if (!buf)
+		return -ENOMEM;
+
+	p = CTRL_BODY(buf);
+	ceph_encode_8(&p, CEPH_ENTITY_TYPE_CLIENT);
+	ceph_encode_entity_addr(&p, &con->peer_addr);
+	WARN_ON(p != CTRL_BODY(buf) + ctrl_len);
+
+	return __prepare_control(con, FRAME_TAG_HELLO, buf, ctrl_len,
+				 NULL, 0, true);
+}
+
+/* so that head_onwire_len(AUTH_BUF_LEN, false) is 512 */
+#define AUTH_BUF_LEN	(512 - CEPH_CRC_LEN - CEPH_PREAMBLE_PLAIN_LEN)
+
+static int prepare_auth_request(struct ceph_connection *con)
+{
+	void *authorizer, *authorizer_copy;
+	int ctrl_len, authorizer_len;
+	void *buf;
+	int ret;
+
+	ctrl_len = AUTH_BUF_LEN;
+	buf = alloc_conn_buf(con, head_onwire_len(ctrl_len, false));
+	if (!buf)
+		return -ENOMEM;
+
+	mutex_unlock(&con->mutex);
+	ret = con->ops->get_auth_request(con, CTRL_BODY(buf), &ctrl_len,
+					 &authorizer, &authorizer_len);
+	mutex_lock(&con->mutex);
+	if (con->state != CEPH_CON_S_V2_HELLO) {
+		dout("%s con %p state changed to %d\n", __func__, con,
+		     con->state);
+		return -EAGAIN;
+	}
+
+	dout("%s con %p get_auth_request ret %d\n", __func__, con, ret);
+	if (ret)
+		return ret;
+
+	authorizer_copy = alloc_conn_buf(con, authorizer_len);
+	if (!authorizer_copy)
+		return -ENOMEM;
+
+	memcpy(authorizer_copy, authorizer, authorizer_len);
+
+	return __prepare_control(con, FRAME_TAG_AUTH_REQUEST, buf, ctrl_len,
+				 authorizer_copy, authorizer_len, true);
+}
+
+static int prepare_auth_request_more(struct ceph_connection *con,
+				     void *reply, int reply_len)
+{
+	int ctrl_len, authorizer_len;
+	void *authorizer;
+	void *buf;
+	int ret;
+
+	ctrl_len = AUTH_BUF_LEN;
+	buf = alloc_conn_buf(con, head_onwire_len(ctrl_len, false));
+	if (!buf)
+		return -ENOMEM;
+
+	mutex_unlock(&con->mutex);
+	ret = con->ops->handle_auth_reply_more(con, reply, reply_len,
+					       CTRL_BODY(buf), &ctrl_len,
+					       &authorizer, &authorizer_len);
+	mutex_lock(&con->mutex);
+	if (con->state != CEPH_CON_S_V2_AUTH) {
+		dout("%s con %p state changed to %d\n", __func__, con,
+		     con->state);
+		return -EAGAIN;
+	}
+
+	dout("%s con %p handle_auth_reply_more ret %d\n", __func__, con, ret);
+	if (ret)
+		return ret;
+
+	return __prepare_control(con, FRAME_TAG_AUTH_REQUEST_MORE, buf,
+				 ctrl_len, authorizer, authorizer_len, true);
+}
+
+static int prepare_auth_signature(struct ceph_connection *con)
+{
+	void *buf;
+	int ret;
+
+	buf = alloc_conn_buf(con, head_onwire_len(SHA256_DIGEST_SIZE, false));
+	if (!buf)
+		return -ENOMEM;
+
+	ret = hmac_sha256(con, con->v2.in_sign_kvecs, con->v2.in_sign_kvec_cnt,
+			  CTRL_BODY(buf));
+	if (ret)
+		return ret;
+
+	return prepare_control(con, FRAME_TAG_AUTH_SIGNATURE, buf,
+			       SHA256_DIGEST_SIZE);
+}
+
+static int prepare_client_ident(struct ceph_connection *con)
+{
+	struct ceph_entity_addr *my_addr = &con->msgr->inst.addr;
+	struct ceph_client *client = from_msgr(con->msgr);
+	u64 global_id = ceph_client_gid(client);
+	void *buf, *p;
+	int ctrl_len;
+
+	WARN_ON(con->v2.server_cookie);
+	WARN_ON(con->v2.connect_seq);
+	WARN_ON(con->v2.peer_global_seq);
+
+	if (!con->v2.client_cookie) {
+		do {
+			get_random_bytes(&con->v2.client_cookie,
+					 sizeof(con->v2.client_cookie));
+		} while (!con->v2.client_cookie);
+		dout("%s con %p generated cookie 0x%llx\n", __func__, con,
+		     con->v2.client_cookie);
+	} else {
+		dout("%s con %p cookie already set 0x%llx\n", __func__, con,
+		     con->v2.client_cookie);
+	}
+
+	dout("%s con %p my_addr %s/%u peer_addr %s/%u global_id %llu global_seq %llu features 0x%llx required_features 0x%llx cookie 0x%llx\n",
+	     __func__, con, ceph_pr_addr(my_addr), le32_to_cpu(my_addr->nonce),
+	     ceph_pr_addr(&con->peer_addr), le32_to_cpu(con->peer_addr.nonce),
+	     global_id, con->v2.global_seq, client->supported_features,
+	     client->required_features, con->v2.client_cookie);
+
+	ctrl_len = 1 + 4 + ceph_entity_addr_encoding_len(my_addr) +
+		   ceph_entity_addr_encoding_len(&con->peer_addr) + 6 * 8;
+	buf = alloc_conn_buf(con, head_onwire_len(ctrl_len, con_secure(con)));
+	if (!buf)
+		return -ENOMEM;
+
+	p = CTRL_BODY(buf);
+	ceph_encode_8(&p, 2);  /* addrvec marker */
+	ceph_encode_32(&p, 1);  /* addr_cnt */
+	ceph_encode_entity_addr(&p, my_addr);
+	ceph_encode_entity_addr(&p, &con->peer_addr);
+	ceph_encode_64(&p, global_id);
+	ceph_encode_64(&p, con->v2.global_seq);
+	ceph_encode_64(&p, client->supported_features);
+	ceph_encode_64(&p, client->required_features);
+	ceph_encode_64(&p, 0);  /* flags */
+	ceph_encode_64(&p, con->v2.client_cookie);
+	WARN_ON(p != CTRL_BODY(buf) + ctrl_len);
+
+	return prepare_control(con, FRAME_TAG_CLIENT_IDENT, buf, ctrl_len);
+}
+
+static int prepare_session_reconnect(struct ceph_connection *con)
+{
+	struct ceph_entity_addr *my_addr = &con->msgr->inst.addr;
+	void *buf, *p;
+	int ctrl_len;
+
+	WARN_ON(!con->v2.client_cookie);
+	WARN_ON(!con->v2.server_cookie);
+	WARN_ON(!con->v2.connect_seq);
+	WARN_ON(!con->v2.peer_global_seq);
+
+	dout("%s con %p my_addr %s/%u client_cookie 0x%llx server_cookie 0x%llx global_seq %llu connect_seq %llu in_seq %llu\n",
+	     __func__, con, ceph_pr_addr(my_addr), le32_to_cpu(my_addr->nonce),
+	     con->v2.client_cookie, con->v2.server_cookie, con->v2.global_seq,
+	     con->v2.connect_seq, con->in_seq);
+
+	ctrl_len = 1 + 4 + ceph_entity_addr_encoding_len(my_addr) + 5 * 8;
+	buf = alloc_conn_buf(con, head_onwire_len(ctrl_len, con_secure(con)));
+	if (!buf)
+		return -ENOMEM;
+
+	p = CTRL_BODY(buf);
+	ceph_encode_8(&p, 2);  /* entity_addrvec_t marker */
+	ceph_encode_32(&p, 1);  /* my_addrs len */
+	ceph_encode_entity_addr(&p, my_addr);
+	ceph_encode_64(&p, con->v2.client_cookie);
+	ceph_encode_64(&p, con->v2.server_cookie);
+	ceph_encode_64(&p, con->v2.global_seq);
+	ceph_encode_64(&p, con->v2.connect_seq);
+	ceph_encode_64(&p, con->in_seq);
+	WARN_ON(p != CTRL_BODY(buf) + ctrl_len);
+
+	return prepare_control(con, FRAME_TAG_SESSION_RECONNECT, buf, ctrl_len);
+}
+
+static int prepare_keepalive2(struct ceph_connection *con)
+{
+	struct ceph_timespec *ts = CTRL_BODY(con->v2.out_buf);
+	struct timespec64 now;
+
+	ktime_get_real_ts64(&now);
+	dout("%s con %p timestamp %lld.%09ld\n", __func__, con, now.tv_sec,
+	     now.tv_nsec);
+
+	ceph_encode_timespec64(ts, &now);
+
+	reset_out_kvecs(con);
+	return prepare_control(con, FRAME_TAG_KEEPALIVE2, con->v2.out_buf,
+			       sizeof(struct ceph_timespec));
+}
+
+static int prepare_ack(struct ceph_connection *con)
+{
+	void *p;
+
+	dout("%s con %p in_seq_acked %llu -> %llu\n", __func__, con,
+	     con->in_seq_acked, con->in_seq);
+	con->in_seq_acked = con->in_seq;
+
+	p = CTRL_BODY(con->v2.out_buf);
+	ceph_encode_64(&p, con->in_seq_acked);
+
+	reset_out_kvecs(con);
+	return prepare_control(con, FRAME_TAG_ACK, con->v2.out_buf, 8);
+}
+
+static void prepare_epilogue_plain(struct ceph_connection *con, bool aborted)
+{
+	dout("%s con %p msg %p aborted %d crcs %u %u %u\n", __func__, con,
+	     con->out_msg, aborted, con->v2.out_epil.front_crc,
+	     con->v2.out_epil.middle_crc, con->v2.out_epil.data_crc);
+
+	encode_epilogue_plain(con, aborted);
+	add_out_kvec(con, &con->v2.out_epil, CEPH_EPILOGUE_PLAIN_LEN);
+}
+
+/*
+ * For "used" empty segments, crc is -1.  For unused (trailing)
+ * segments, crc is 0.
+ */
+static void prepare_message_plain(struct ceph_connection *con)
+{
+	struct ceph_msg *msg = con->out_msg;
+
+	prepare_head_plain(con, con->v2.out_buf,
+			   sizeof(struct ceph_msg_header2), NULL, 0, false);
+
+	if (!front_len(msg) && !middle_len(msg)) {
+		if (!data_len(msg)) {
+			/*
+			 * Empty message: once the head is written,
+			 * we are done -- there is no epilogue.
+			 */
+			con->v2.out_state = OUT_S_FINISH_MESSAGE;
+			return;
+		}
+
+		con->v2.out_epil.front_crc = -1;
+		con->v2.out_epil.middle_crc = -1;
+		con->v2.out_state = OUT_S_QUEUE_DATA;
+		return;
+	}
+
+	if (front_len(msg)) {
+		con->v2.out_epil.front_crc = crc32c(-1, msg->front.iov_base,
+						    front_len(msg));
+		add_out_kvec(con, msg->front.iov_base, front_len(msg));
+	} else {
+		/* middle (at least) is there, checked above */
+		con->v2.out_epil.front_crc = -1;
+	}
+
+	if (middle_len(msg)) {
+		con->v2.out_epil.middle_crc =
+			crc32c(-1, msg->middle->vec.iov_base, middle_len(msg));
+		add_out_kvec(con, msg->middle->vec.iov_base, middle_len(msg));
+	} else {
+		con->v2.out_epil.middle_crc = data_len(msg) ? -1 : 0;
+	}
+
+	if (data_len(msg)) {
+		con->v2.out_state = OUT_S_QUEUE_DATA;
+	} else {
+		con->v2.out_epil.data_crc = 0;
+		prepare_epilogue_plain(con, false);
+		con->v2.out_state = OUT_S_FINISH_MESSAGE;
+	}
+}
+
+/*
+ * Unfortunately the kernel crypto API doesn't support streaming
+ * (piecewise) operation for AEAD algorithms, so we can't get away
+ * with a fixed size buffer and a couple sgs.  Instead, we have to
+ * allocate pages for the entire tail of the message (currently up
+ * to ~32M) and two sgs arrays (up to ~256K each)...
+ */
+static int prepare_message_secure(struct ceph_connection *con)
+{
+	void *zerop = page_address(ceph_zero_page);
+	struct sg_table enc_sgt = {};
+	struct sg_table sgt = {};
+	struct page **enc_pages;
+	int enc_page_cnt;
+	int tail_len;
+	int ret;
+
+	ret = prepare_head_secure_small(con, con->v2.out_buf,
+					sizeof(struct ceph_msg_header2));
+	if (ret)
+		return ret;
+
+	tail_len = tail_onwire_len(con->out_msg, true);
+	if (!tail_len) {
+		/*
+		 * Empty message: once the head is written,
+		 * we are done -- there is no epilogue.
+		 */
+		con->v2.out_state = OUT_S_FINISH_MESSAGE;
+		return 0;
+	}
+
+	encode_epilogue_secure(con, false);
+	ret = setup_message_sgs(&sgt, con->out_msg, zerop, zerop, zerop,
+				&con->v2.out_epil, false);
+	if (ret)
+		goto out;
+
+	enc_page_cnt = calc_pages_for(0, tail_len);
+	enc_pages = ceph_alloc_page_vector(enc_page_cnt, GFP_NOIO);
+	if (IS_ERR(enc_pages)) {
+		ret = PTR_ERR(enc_pages);
+		goto out;
+	}
+
+	WARN_ON(con->v2.out_enc_pages || con->v2.out_enc_page_cnt);
+	con->v2.out_enc_pages = enc_pages;
+	con->v2.out_enc_page_cnt = enc_page_cnt;
+	con->v2.out_enc_resid = tail_len;
+	con->v2.out_enc_i = 0;
+
+	ret = sg_alloc_table_from_pages(&enc_sgt, enc_pages, enc_page_cnt,
+					0, tail_len, GFP_NOIO);
+	if (ret)
+		goto out;
+
+	ret = gcm_crypt(con, true, sgt.sgl, enc_sgt.sgl,
+			tail_len - CEPH_GCM_TAG_LEN);
+	if (ret)
+		goto out;
+
+	dout("%s con %p msg %p sg_cnt %d enc_page_cnt %d\n", __func__, con,
+	     con->out_msg, sgt.orig_nents, enc_page_cnt);
+	con->v2.out_state = OUT_S_QUEUE_ENC_PAGE;
+
+out:
+	sg_free_table(&sgt);
+	sg_free_table(&enc_sgt);
+	return ret;
+}
+
+static int prepare_message(struct ceph_connection *con)
+{
+	int lens[] = {
+		sizeof(struct ceph_msg_header2),
+		front_len(con->out_msg),
+		middle_len(con->out_msg),
+		data_len(con->out_msg)
+	};
+	struct ceph_frame_desc desc;
+	int ret;
+
+	dout("%s con %p msg %p logical %d+%d+%d+%d\n", __func__, con,
+	     con->out_msg, lens[0], lens[1], lens[2], lens[3]);
+
+	if (con->in_seq > con->in_seq_acked) {
+		dout("%s con %p in_seq_acked %llu -> %llu\n", __func__, con,
+		     con->in_seq_acked, con->in_seq);
+		con->in_seq_acked = con->in_seq;
+	}
+
+	reset_out_kvecs(con);
+	init_frame_desc(&desc, FRAME_TAG_MESSAGE, lens, 4);
+	encode_preamble(&desc, con->v2.out_buf);
+	fill_header2(CTRL_BODY(con->v2.out_buf), &con->out_msg->hdr,
+		     con->in_seq_acked);
+
+	if (con_secure(con)) {
+		ret = prepare_message_secure(con);
+		if (ret)
+			return ret;
+	} else {
+		prepare_message_plain(con);
+	}
+
+	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
+	return 0;
+}
+
+static int prepare_read_banner_prefix(struct ceph_connection *con)
+{
+	void *buf;
+
+	buf = alloc_conn_buf(con, CEPH_BANNER_V2_PREFIX_LEN);
+	if (!buf)
+		return -ENOMEM;
+
+	reset_in_kvecs(con);
+	add_in_kvec(con, buf, CEPH_BANNER_V2_PREFIX_LEN);
+	add_in_sign_kvec(con, buf, CEPH_BANNER_V2_PREFIX_LEN);
+	con->state = CEPH_CON_S_V2_BANNER_PREFIX;
+	return 0;
+}
+
+static int prepare_read_banner_payload(struct ceph_connection *con,
+				       int payload_len)
+{
+	void *buf;
+
+	buf = alloc_conn_buf(con, payload_len);
+	if (!buf)
+		return -ENOMEM;
+
+	reset_in_kvecs(con);
+	add_in_kvec(con, buf, payload_len);
+	add_in_sign_kvec(con, buf, payload_len);
+	con->state = CEPH_CON_S_V2_BANNER_PAYLOAD;
+	return 0;
+}
+
+static void prepare_read_preamble(struct ceph_connection *con)
+{
+	reset_in_kvecs(con);
+	add_in_kvec(con, con->v2.in_buf,
+		    con_secure(con) ? CEPH_PREAMBLE_SECURE_LEN :
+				      CEPH_PREAMBLE_PLAIN_LEN);
+	con->v2.in_state = IN_S_HANDLE_PREAMBLE;
+}
+
+static int prepare_read_control(struct ceph_connection *con)
+{
+	int ctrl_len = con->v2.in_desc.fd_lens[0];
+	int head_len;
+	void *buf;
+
+	reset_in_kvecs(con);
+	if (con->state == CEPH_CON_S_V2_HELLO ||
+	    con->state == CEPH_CON_S_V2_AUTH) {
+		head_len = head_onwire_len(ctrl_len, false);
+		buf = alloc_conn_buf(con, head_len);
+		if (!buf)
+			return -ENOMEM;
+
+		/* preserve preamble */
+		memcpy(buf, con->v2.in_buf, CEPH_PREAMBLE_LEN);
+
+		add_in_kvec(con, CTRL_BODY(buf), ctrl_len);
+		add_in_kvec(con, CTRL_BODY(buf) + ctrl_len, CEPH_CRC_LEN);
+		add_in_sign_kvec(con, buf, head_len);
+	} else {
+		if (ctrl_len > CEPH_PREAMBLE_INLINE_LEN) {
+			buf = alloc_conn_buf(con, ctrl_len);
+			if (!buf)
+				return -ENOMEM;
+
+			add_in_kvec(con, buf, ctrl_len);
+		} else {
+			add_in_kvec(con, CTRL_BODY(con->v2.in_buf), ctrl_len);
+		}
+		add_in_kvec(con, con->v2.in_buf, CEPH_CRC_LEN);
+	}
+	con->v2.in_state = IN_S_HANDLE_CONTROL;
+	return 0;
+}
+
+static int prepare_read_control_remainder(struct ceph_connection *con)
+{
+	int ctrl_len = con->v2.in_desc.fd_lens[0];
+	int rem_len = ctrl_len - CEPH_PREAMBLE_INLINE_LEN;
+	void *buf;
+
+	buf = alloc_conn_buf(con, ctrl_len);
+	if (!buf)
+		return -ENOMEM;
+
+	memcpy(buf, CTRL_BODY(con->v2.in_buf), CEPH_PREAMBLE_INLINE_LEN);
+
+	reset_in_kvecs(con);
+	add_in_kvec(con, buf + CEPH_PREAMBLE_INLINE_LEN, rem_len);
+	add_in_kvec(con, con->v2.in_buf,
+		    padding_len(rem_len) + CEPH_GCM_TAG_LEN);
+	con->v2.in_state = IN_S_HANDLE_CONTROL_REMAINDER;
+	return 0;
+}
+
+static void prepare_read_data(struct ceph_connection *con)
+{
+	struct bio_vec bv;
+
+	if (!con_secure(con))
+		con->in_data_crc = -1;
+	ceph_msg_data_cursor_init(&con->v2.in_cursor, con->in_msg,
+				  data_len(con->in_msg));
+
+	get_bvec_at(&con->v2.in_cursor, &bv);
+	set_in_bvec(con, &bv);
+	con->v2.in_state = IN_S_PREPARE_READ_DATA_CONT;
+}
+
+static void prepare_read_data_cont(struct ceph_connection *con)
+{
+	struct bio_vec bv;
+
+	if (!con_secure(con))
+		con->in_data_crc = ceph_crc32c_page(con->in_data_crc,
+						    con->v2.in_bvec.bv_page,
+						    con->v2.in_bvec.bv_offset,
+						    con->v2.in_bvec.bv_len);
+
+	ceph_msg_data_advance(&con->v2.in_cursor, con->v2.in_bvec.bv_len);
+	if (con->v2.in_cursor.total_resid) {
+		get_bvec_at(&con->v2.in_cursor, &bv);
+		set_in_bvec(con, &bv);
+		WARN_ON(con->v2.in_state != IN_S_PREPARE_READ_DATA_CONT);
+		return;
+	}
+
+	/*
+	 * We've read all data.  Prepare to read data padding (if any)
+	 * and epilogue.
+	 */
+	reset_in_kvecs(con);
+	if (con_secure(con)) {
+		if (need_padding(data_len(con->in_msg)))
+			add_in_kvec(con, DATA_PAD(con->v2.in_buf),
+				    padding_len(data_len(con->in_msg)));
+		add_in_kvec(con, con->v2.in_buf, CEPH_EPILOGUE_SECURE_LEN);
+	} else {
+		add_in_kvec(con, con->v2.in_buf, CEPH_EPILOGUE_PLAIN_LEN);
+	}
+	con->v2.in_state = IN_S_HANDLE_EPILOGUE;
+}
+
+static void __finish_skip(struct ceph_connection *con)
+{
+	con->in_seq++;
+	prepare_read_preamble(con);
+}
+
+static void prepare_skip_message(struct ceph_connection *con)
+{
+	struct ceph_frame_desc *desc = &con->v2.in_desc;
+	int tail_len;
+
+	dout("%s con %p %d+%d+%d\n", __func__, con, desc->fd_lens[1],
+	     desc->fd_lens[2], desc->fd_lens[3]);
+
+	tail_len = __tail_onwire_len(desc->fd_lens[1], desc->fd_lens[2],
+				     desc->fd_lens[3], con_secure(con));
+	if (!tail_len) {
+		__finish_skip(con);
+	} else {
+		set_in_skip(con, tail_len);
+		con->v2.in_state = IN_S_FINISH_SKIP;
+	}
+}
+
+static int process_banner_prefix(struct ceph_connection *con)
+{
+	int payload_len;
+	void *p;
+
+	WARN_ON(con->v2.in_kvecs[0].iov_len != CEPH_BANNER_V2_PREFIX_LEN);
+
+	p = con->v2.in_kvecs[0].iov_base;
+	if (memcmp(p, CEPH_BANNER_V2, CEPH_BANNER_V2_LEN)) {
+		if (!memcmp(p, CEPH_BANNER, CEPH_BANNER_LEN))
+			con->error_msg = "server is speaking msgr1 protocol";
+		else
+			con->error_msg = "protocol error, bad banner";
+		return -EINVAL;
+	}
+
+	p += CEPH_BANNER_V2_LEN;
+	payload_len = ceph_decode_16(&p);
+	dout("%s con %p payload_len %d\n", __func__, con, payload_len);
+
+	return prepare_read_banner_payload(con, payload_len);
+}
+
+static int process_banner_payload(struct ceph_connection *con)
+{
+	void *end = con->v2.in_kvecs[0].iov_base + con->v2.in_kvecs[0].iov_len;
+	u64 feat = CEPH_MSGR2_SUPPORTED_FEATURES;
+	u64 req_feat = CEPH_MSGR2_REQUIRED_FEATURES;
+	u64 server_feat, server_req_feat;
+	void *p;
+	int ret;
+
+	p = con->v2.in_kvecs[0].iov_base;
+	ceph_decode_64_safe(&p, end, server_feat, bad);
+	ceph_decode_64_safe(&p, end, server_req_feat, bad);
+
+	dout("%s con %p server_feat 0x%llx server_req_feat 0x%llx\n",
+	     __func__, con, server_feat, server_req_feat);
+
+	if (req_feat & ~server_feat) {
+		pr_err("msgr2 feature set mismatch: my required > server's supported 0x%llx, need 0x%llx\n",
+		       server_feat, req_feat & ~server_feat);
+		con->error_msg = "missing required protocol features";
+		return -EINVAL;
+	}
+	if (server_req_feat & ~feat) {
+		pr_err("msgr2 feature set mismatch: server's required > my supported 0x%llx, missing 0x%llx\n",
+		       feat, server_req_feat & ~feat);
+		con->error_msg = "missing required protocol features";
+		return -EINVAL;
+	}
+
+	/* no reset_out_kvecs() as our banner may still be pending */
+	ret = prepare_hello(con);
+	if (ret) {
+		pr_err("prepare_hello failed: %d\n", ret);
+		return ret;
+	}
+
+	con->state = CEPH_CON_S_V2_HELLO;
+	prepare_read_preamble(con);
+	return 0;
+
+bad:
+	pr_err("failed to decode banner payload\n");
+	return -EINVAL;
+}
+
+static int process_hello(struct ceph_connection *con, void *p, void *end)
+{
+	struct ceph_entity_addr *my_addr = &con->msgr->inst.addr;
+	struct ceph_entity_addr addr_for_me;
+	u8 entity_type;
+	int ret;
+
+	if (con->state != CEPH_CON_S_V2_HELLO) {
+		con->error_msg = "protocol error, unexpected hello";
+		return -EINVAL;
+	}
+
+	ceph_decode_8_safe(&p, end, entity_type, bad);
+	ret = ceph_decode_entity_addr(&p, end, &addr_for_me);
+	if (ret) {
+		pr_err("failed to decode addr_for_me: %d\n", ret);
+		return ret;
+	}
+
+	dout("%s con %p entity_type %d addr_for_me %s\n", __func__, con,
+	     entity_type, ceph_pr_addr(&addr_for_me));
+
+	if (entity_type != con->peer_name.type) {
+		pr_err("bad peer type, want %d, got %d\n",
+		       con->peer_name.type, entity_type);
+		con->error_msg = "wrong peer at address";
+		return -EINVAL;
+	}
+
+	/*
+	 * Set our address to the address our first peer (i.e. monitor)
+	 * sees that we are connecting from.  If we are behind some sort
+	 * of NAT and want to be identified by some private (not NATed)
+	 * address, ip option should be used.
+	 */
+	if (ceph_addr_is_blank(my_addr)) {
+		memcpy(&my_addr->in_addr, &addr_for_me.in_addr,
+		       sizeof(my_addr->in_addr));
+		ceph_addr_set_port(my_addr, 0);
+		dout("%s con %p set my addr %s, as seen by peer %s\n",
+		     __func__, con, ceph_pr_addr(my_addr),
+		     ceph_pr_addr(&con->peer_addr));
+	} else {
+		dout("%s con %p my addr already set %s\n",
+		     __func__, con, ceph_pr_addr(my_addr));
+	}
+
+	WARN_ON(ceph_addr_is_blank(my_addr) || ceph_addr_port(my_addr));
+	WARN_ON(my_addr->type != CEPH_ENTITY_ADDR_TYPE_ANY);
+	WARN_ON(!my_addr->nonce);
+
+	/* no reset_out_kvecs() as our hello may still be pending */
+	ret = prepare_auth_request(con);
+	if (ret) {
+		if (ret != -EAGAIN)
+			pr_err("prepare_auth_request failed: %d\n", ret);
+		return ret;
+	}
+
+	con->state = CEPH_CON_S_V2_AUTH;
+	return 0;
+
+bad:
+	pr_err("failed to decode hello\n");
+	return -EINVAL;
+}
+
+static int process_auth_bad_method(struct ceph_connection *con,
+				   void *p, void *end)
+{
+	int allowed_protos[8], allowed_modes[8];
+	int allowed_proto_cnt, allowed_mode_cnt;
+	int used_proto, result;
+	int ret;
+	int i;
+
+	if (con->state != CEPH_CON_S_V2_AUTH) {
+		con->error_msg = "protocol error, unexpected auth_bad_method";
+		return -EINVAL;
+	}
+
+	ceph_decode_32_safe(&p, end, used_proto, bad);
+	ceph_decode_32_safe(&p, end, result, bad);
+	dout("%s con %p used_proto %d result %d\n", __func__, con, used_proto,
+	     result);
+
+	ceph_decode_32_safe(&p, end, allowed_proto_cnt, bad);
+	if (allowed_proto_cnt > ARRAY_SIZE(allowed_protos)) {
+		pr_err("allowed_protos too big %d\n", allowed_proto_cnt);
+		return -EINVAL;
+	}
+	for (i = 0; i < allowed_proto_cnt; i++) {
+		ceph_decode_32_safe(&p, end, allowed_protos[i], bad);
+		dout("%s con %p allowed_protos[%d] %d\n", __func__, con,
+		     i, allowed_protos[i]);
+	}
+
+	ceph_decode_32_safe(&p, end, allowed_mode_cnt, bad);
+	if (allowed_mode_cnt > ARRAY_SIZE(allowed_modes)) {
+		pr_err("allowed_modes too big %d\n", allowed_mode_cnt);
+		return -EINVAL;
+	}
+	for (i = 0; i < allowed_mode_cnt; i++) {
+		ceph_decode_32_safe(&p, end, allowed_modes[i], bad);
+		dout("%s con %p allowed_modes[%d] %d\n", __func__, con,
+		     i, allowed_modes[i]);
+	}
+
+	mutex_unlock(&con->mutex);
+	ret = con->ops->handle_auth_bad_method(con, used_proto, result,
+					       allowed_protos,
+					       allowed_proto_cnt,
+					       allowed_modes,
+					       allowed_mode_cnt);
+	mutex_lock(&con->mutex);
+	if (con->state != CEPH_CON_S_V2_AUTH) {
+		dout("%s con %p state changed to %d\n", __func__, con,
+		     con->state);
+		return -EAGAIN;
+	}
+
+	dout("%s con %p handle_auth_bad_method ret %d\n", __func__, con, ret);
+	return ret;
+
+bad:
+	pr_err("failed to decode auth_bad_method\n");
+	return -EINVAL;
+}
+
+static int process_auth_reply_more(struct ceph_connection *con,
+				   void *p, void *end)
+{
+	int payload_len;
+	int ret;
+
+	if (con->state != CEPH_CON_S_V2_AUTH) {
+		con->error_msg = "protocol error, unexpected auth_reply_more";
+		return -EINVAL;
+	}
+
+	ceph_decode_32_safe(&p, end, payload_len, bad);
+	ceph_decode_need(&p, end, payload_len, bad);
+
+	dout("%s con %p payload_len %d\n", __func__, con, payload_len);
+
+	reset_out_kvecs(con);
+	ret = prepare_auth_request_more(con, p, payload_len);
+	if (ret) {
+		if (ret != -EAGAIN)
+			pr_err("prepare_auth_request_more failed: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+
+bad:
+	pr_err("failed to decode auth_reply_more\n");
+	return -EINVAL;
+}
+
+static int process_auth_done(struct ceph_connection *con, void *p, void *end)
+{
+	u8 session_key[CEPH_KEY_LEN];
+	u8 con_secret[CEPH_MAX_CON_SECRET_LEN];
+	int session_key_len, con_secret_len;
+	int payload_len;
+	u64 global_id;
+	int ret;
+
+	if (con->state != CEPH_CON_S_V2_AUTH) {
+		con->error_msg = "protocol error, unexpected auth_done";
+		return -EINVAL;
+	}
+
+	ceph_decode_64_safe(&p, end, global_id, bad);
+	ceph_decode_32_safe(&p, end, con->v2.con_mode, bad);
+	ceph_decode_32_safe(&p, end, payload_len, bad);
+
+	dout("%s con %p global_id %llu con_mode %d payload_len %d\n",
+	     __func__, con, global_id, con->v2.con_mode, payload_len);
+
+	mutex_unlock(&con->mutex);
+	session_key_len = 0;
+	con_secret_len = 0;
+	ret = con->ops->handle_auth_done(con, global_id, p, payload_len,
+					 session_key, &session_key_len,
+					 con_secret, &con_secret_len);
+	mutex_lock(&con->mutex);
+	if (con->state != CEPH_CON_S_V2_AUTH) {
+		dout("%s con %p state changed to %d\n", __func__, con,
+		     con->state);
+		return -EAGAIN;
+	}
+
+	dout("%s con %p handle_auth_done ret %d\n", __func__, con, ret);
+	if (ret)
+		return ret;
+
+	ret = setup_crypto(con, session_key, session_key_len, con_secret,
+			   con_secret_len);
+	if (ret)
+		return ret;
+
+	reset_out_kvecs(con);
+	ret = prepare_auth_signature(con);
+	if (ret) {
+		pr_err("prepare_auth_signature failed: %d\n", ret);
+		return ret;
+	}
+
+	con->state = CEPH_CON_S_V2_AUTH_SIGNATURE;
+	return 0;
+
+bad:
+	pr_err("failed to decode auth_done\n");
+	return -EINVAL;
+}
+
+static int process_auth_signature(struct ceph_connection *con,
+				  void *p, void *end)
+{
+	u8 hmac[SHA256_DIGEST_SIZE];
+	int ret;
+
+	if (con->state != CEPH_CON_S_V2_AUTH_SIGNATURE) {
+		con->error_msg = "protocol error, unexpected auth_signature";
+		return -EINVAL;
+	}
+
+	ret = hmac_sha256(con, con->v2.out_sign_kvecs,
+			  con->v2.out_sign_kvec_cnt, hmac);
+	if (ret)
+		return ret;
+
+	ceph_decode_need(&p, end, SHA256_DIGEST_SIZE, bad);
+	if (crypto_memneq(p, hmac, SHA256_DIGEST_SIZE)) {
+		con->error_msg = "integrity error, bad auth signature";
+		return -EBADMSG;
+	}
+
+	dout("%s con %p auth signature ok\n", __func__, con);
+
+	/* no reset_out_kvecs() as our auth_signature may still be pending */
+	if (!con->v2.server_cookie) {
+		ret = prepare_client_ident(con);
+		if (ret) {
+			pr_err("prepare_client_ident failed: %d\n", ret);
+			return ret;
+		}
+
+		con->state = CEPH_CON_S_V2_SESSION_CONNECT;
+	} else {
+		ret = prepare_session_reconnect(con);
+		if (ret) {
+			pr_err("prepare_session_reconnect failed: %d\n", ret);
+			return ret;
+		}
+
+		con->state = CEPH_CON_S_V2_SESSION_RECONNECT;
+	}
+
+	return 0;
+
+bad:
+	pr_err("failed to decode auth_signature\n");
+	return -EINVAL;
+}
+
+static int process_server_ident(struct ceph_connection *con,
+				void *p, void *end)
+{
+	struct ceph_client *client = from_msgr(con->msgr);
+	u64 features, required_features;
+	struct ceph_entity_addr addr;
+	u64 global_seq;
+	u64 global_id;
+	u64 cookie;
+	u64 flags;
+	int ret;
+
+	if (con->state != CEPH_CON_S_V2_SESSION_CONNECT) {
+		con->error_msg = "protocol error, unexpected server_ident";
+		return -EINVAL;
+	}
+
+	ret = ceph_decode_entity_addrvec(&p, end, true, &addr);
+	if (ret) {
+		pr_err("failed to decode server addrs: %d\n", ret);
+		return ret;
+	}
+
+	ceph_decode_64_safe(&p, end, global_id, bad);
+	ceph_decode_64_safe(&p, end, global_seq, bad);
+	ceph_decode_64_safe(&p, end, features, bad);
+	ceph_decode_64_safe(&p, end, required_features, bad);
+	ceph_decode_64_safe(&p, end, flags, bad);
+	ceph_decode_64_safe(&p, end, cookie, bad);
+
+	dout("%s con %p addr %s/%u global_id %llu global_seq %llu features 0x%llx required_features 0x%llx flags 0x%llx cookie 0x%llx\n",
+	     __func__, con, ceph_pr_addr(&addr), le32_to_cpu(addr.nonce),
+	     global_id, global_seq, features, required_features, flags, cookie);
+
+	/* is this who we intended to talk to? */
+	if (memcmp(&addr, &con->peer_addr, sizeof(con->peer_addr))) {
+		pr_err("bad peer addr/nonce, want %s/%u, got %s/%u\n",
+		       ceph_pr_addr(&con->peer_addr),
+		       le32_to_cpu(con->peer_addr.nonce),
+		       ceph_pr_addr(&addr), le32_to_cpu(addr.nonce));
+		con->error_msg = "wrong peer at address";
+		return -EINVAL;
+	}
+
+	if (client->required_features & ~features) {
+		pr_err("RADOS feature set mismatch: my required > server's supported 0x%llx, need 0x%llx\n",
+		       features, client->required_features & ~features);
+		con->error_msg = "missing required protocol features";
+		return -EINVAL;
+	}
+
+	/*
+	 * Both name->type and name->num are set in ceph_con_open() but
+	 * name->num may be bogus in the initial monmap.  name->type is
+	 * verified in handle_hello().
+	 */
+	WARN_ON(!con->peer_name.type);
+	con->peer_name.num = cpu_to_le64(global_id);
+	con->v2.peer_global_seq = global_seq;
+	con->peer_features = features;
+	WARN_ON(required_features & ~client->supported_features);
+	con->v2.server_cookie = cookie;
+
+	if (flags & CEPH_MSG_CONNECT_LOSSY) {
+		ceph_con_flag_set(con, CEPH_CON_F_LOSSYTX);
+		WARN_ON(con->v2.server_cookie);
+	} else {
+		WARN_ON(!con->v2.server_cookie);
+	}
+
+	clear_in_sign_kvecs(con);
+	clear_out_sign_kvecs(con);
+	free_conn_bufs(con);
+	con->delay = 0;  /* reset backoff memory */
+
+	con->state = CEPH_CON_S_OPEN;
+	con->v2.out_state = OUT_S_GET_NEXT;
+	return 0;
+
+bad:
+	pr_err("failed to decode server_ident\n");
+	return -EINVAL;
+}
+
+static int process_ident_missing_features(struct ceph_connection *con,
+					  void *p, void *end)
+{
+	struct ceph_client *client = from_msgr(con->msgr);
+	u64 missing_features;
+
+	if (con->state != CEPH_CON_S_V2_SESSION_CONNECT) {
+		con->error_msg = "protocol error, unexpected ident_missing_features";
+		return -EINVAL;
+	}
+
+	ceph_decode_64_safe(&p, end, missing_features, bad);
+	pr_err("RADOS feature set mismatch: server's required > my supported 0x%llx, missing 0x%llx\n",
+	       client->supported_features, missing_features);
+	con->error_msg = "missing required protocol features";
+	return -EINVAL;
+
+bad:
+	pr_err("failed to decode ident_missing_features\n");
+	return -EINVAL;
+}
+
+static int process_session_reconnect_ok(struct ceph_connection *con,
+					void *p, void *end)
+{
+	u64 seq;
+
+	if (con->state != CEPH_CON_S_V2_SESSION_RECONNECT) {
+		con->error_msg = "protocol error, unexpected session_reconnect_ok";
+		return -EINVAL;
+	}
+
+	ceph_decode_64_safe(&p, end, seq, bad);
+
+	dout("%s con %p seq %llu\n", __func__, con, seq);
+	ceph_con_discard_requeued(con, seq);
+
+	clear_in_sign_kvecs(con);
+	clear_out_sign_kvecs(con);
+	free_conn_bufs(con);
+	con->delay = 0;  /* reset backoff memory */
+
+	con->state = CEPH_CON_S_OPEN;
+	con->v2.out_state = OUT_S_GET_NEXT;
+	return 0;
+
+bad:
+	pr_err("failed to decode session_reconnect_ok\n");
+	return -EINVAL;
+}
+
+static int process_session_retry(struct ceph_connection *con,
+				 void *p, void *end)
+{
+	u64 connect_seq;
+	int ret;
+
+	if (con->state != CEPH_CON_S_V2_SESSION_RECONNECT) {
+		con->error_msg = "protocol error, unexpected session_retry";
+		return -EINVAL;
+	}
+
+	ceph_decode_64_safe(&p, end, connect_seq, bad);
+
+	dout("%s con %p connect_seq %llu\n", __func__, con, connect_seq);
+	WARN_ON(connect_seq <= con->v2.connect_seq);
+	con->v2.connect_seq = connect_seq + 1;
+
+	free_conn_bufs(con);
+
+	reset_out_kvecs(con);
+	ret = prepare_session_reconnect(con);
+	if (ret) {
+		pr_err("prepare_session_reconnect (cseq) failed: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+
+bad:
+	pr_err("failed to decode session_retry\n");
+	return -EINVAL;
+}
+
+static int process_session_retry_global(struct ceph_connection *con,
+					void *p, void *end)
+{
+	u64 global_seq;
+	int ret;
+
+	if (con->state != CEPH_CON_S_V2_SESSION_RECONNECT) {
+		con->error_msg = "protocol error, unexpected session_retry_global";
+		return -EINVAL;
+	}
+
+	ceph_decode_64_safe(&p, end, global_seq, bad);
+
+	dout("%s con %p global_seq %llu\n", __func__, con, global_seq);
+	WARN_ON(global_seq <= con->v2.global_seq);
+	con->v2.global_seq = ceph_get_global_seq(con->msgr, global_seq);
+
+	free_conn_bufs(con);
+
+	reset_out_kvecs(con);
+	ret = prepare_session_reconnect(con);
+	if (ret) {
+		pr_err("prepare_session_reconnect (gseq) failed: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+
+bad:
+	pr_err("failed to decode session_retry_global\n");
+	return -EINVAL;
+}
+
+static int process_session_reset(struct ceph_connection *con,
+				 void *p, void *end)
+{
+	bool full;
+	int ret;
+
+	if (con->state != CEPH_CON_S_V2_SESSION_RECONNECT) {
+		con->error_msg = "protocol error, unexpected session_reset";
+		return -EINVAL;
+	}
+
+	ceph_decode_8_safe(&p, end, full, bad);
+	if (!full) {
+		con->error_msg = "protocol error, bad session_reset";
+		return -EINVAL;
+	}
+
+	pr_info("%s%lld %s session reset\n", ENTITY_NAME(con->peer_name),
+		ceph_pr_addr(&con->peer_addr));
+	ceph_con_reset_session(con);
+
+	mutex_unlock(&con->mutex);
+	if (con->ops->peer_reset)
+		con->ops->peer_reset(con);
+	mutex_lock(&con->mutex);
+	if (con->state != CEPH_CON_S_V2_SESSION_RECONNECT) {
+		dout("%s con %p state changed to %d\n", __func__, con,
+		     con->state);
+		return -EAGAIN;
+	}
+
+	free_conn_bufs(con);
+
+	reset_out_kvecs(con);
+	ret = prepare_client_ident(con);
+	if (ret) {
+		pr_err("prepare_client_ident (rst) failed: %d\n", ret);
+		return ret;
+	}
+
+	con->state = CEPH_CON_S_V2_SESSION_CONNECT;
+	return 0;
+
+bad:
+	pr_err("failed to decode session_reset\n");
+	return -EINVAL;
+}
+
+static int process_keepalive2_ack(struct ceph_connection *con,
+				  void *p, void *end)
+{
+	if (con->state != CEPH_CON_S_OPEN) {
+		con->error_msg = "protocol error, unexpected keepalive2_ack";
+		return -EINVAL;
+	}
+
+	ceph_decode_need(&p, end, sizeof(struct ceph_timespec), bad);
+	ceph_decode_timespec64(&con->last_keepalive_ack, p);
+
+	dout("%s con %p timestamp %lld.%09ld\n", __func__, con,
+	     con->last_keepalive_ack.tv_sec, con->last_keepalive_ack.tv_nsec);
+
+	return 0;
+
+bad:
+	pr_err("failed to decode keepalive2_ack\n");
+	return -EINVAL;
+}
+
+static int process_ack(struct ceph_connection *con, void *p, void *end)
+{
+	u64 seq;
+
+	if (con->state != CEPH_CON_S_OPEN) {
+		con->error_msg = "protocol error, unexpected ack";
+		return -EINVAL;
+	}
+
+	ceph_decode_64_safe(&p, end, seq, bad);
+
+	dout("%s con %p seq %llu\n", __func__, con, seq);
+	ceph_con_discard_sent(con, seq);
+	return 0;
+
+bad:
+	pr_err("failed to decode ack\n");
+	return -EINVAL;
+}
+
+static int process_control(struct ceph_connection *con, void *p, void *end)
+{
+	int tag = con->v2.in_desc.fd_tag;
+	int ret;
+
+	dout("%s con %p tag %d len %d\n", __func__, con, tag, (int)(end - p));
+
+	switch (tag) {
+	case FRAME_TAG_HELLO:
+		ret = process_hello(con, p, end);
+		break;
+	case FRAME_TAG_AUTH_BAD_METHOD:
+		ret = process_auth_bad_method(con, p, end);
+		break;
+	case FRAME_TAG_AUTH_REPLY_MORE:
+		ret = process_auth_reply_more(con, p, end);
+		break;
+	case FRAME_TAG_AUTH_DONE:
+		ret = process_auth_done(con, p, end);
+		break;
+	case FRAME_TAG_AUTH_SIGNATURE:
+		ret = process_auth_signature(con, p, end);
+		break;
+	case FRAME_TAG_SERVER_IDENT:
+		ret = process_server_ident(con, p, end);
+		break;
+	case FRAME_TAG_IDENT_MISSING_FEATURES:
+		ret = process_ident_missing_features(con, p, end);
+		break;
+	case FRAME_TAG_SESSION_RECONNECT_OK:
+		ret = process_session_reconnect_ok(con, p, end);
+		break;
+	case FRAME_TAG_SESSION_RETRY:
+		ret = process_session_retry(con, p, end);
+		break;
+	case FRAME_TAG_SESSION_RETRY_GLOBAL:
+		ret = process_session_retry_global(con, p, end);
+		break;
+	case FRAME_TAG_SESSION_RESET:
+		ret = process_session_reset(con, p, end);
+		break;
+	case FRAME_TAG_KEEPALIVE2_ACK:
+		ret = process_keepalive2_ack(con, p, end);
+		break;
+	case FRAME_TAG_ACK:
+		ret = process_ack(con, p, end);
+		break;
+	default:
+		pr_err("bad tag %d\n", tag);
+		con->error_msg = "protocol error, bad tag";
+		return -EINVAL;
+	}
+	if (ret) {
+		dout("%s con %p error %d\n", __func__, con, ret);
+		return ret;
+	}
+
+	prepare_read_preamble(con);
+	return 0;
+}
+
+/*
+ * Return:
+ *   1 - con->in_msg set, read message
+ *   0 - skip message
+ *  <0 - error
+ */
+static int process_message_header(struct ceph_connection *con,
+				  void *p, void *end)
+{
+	struct ceph_frame_desc *desc = &con->v2.in_desc;
+	struct ceph_msg_header2 *hdr2 = p;
+	struct ceph_msg_header hdr;
+	int skip;
+	int ret;
+	u64 seq;
+
+	/* verify seq# */
+	seq = le64_to_cpu(hdr2->seq);
+	if ((s64)seq - (s64)con->in_seq < 1) {
+		pr_info("%s%lld %s skipping old message: seq %llu, expected %llu\n",
+			ENTITY_NAME(con->peer_name),
+			ceph_pr_addr(&con->peer_addr),
+			seq, con->in_seq + 1);
+		return 0;
+	}
+	if ((s64)seq - (s64)con->in_seq > 1) {
+		pr_err("bad seq %llu, expected %llu\n", seq, con->in_seq + 1);
+		con->error_msg = "bad message sequence # for incoming message";
+		return -EBADE;
+	}
+
+	ceph_con_discard_sent(con, le64_to_cpu(hdr2->ack_seq));
+
+	fill_header(&hdr, hdr2, desc->fd_lens[1], desc->fd_lens[2],
+		    desc->fd_lens[3], &con->peer_name);
+	ret = ceph_con_in_msg_alloc(con, &hdr, &skip);
+	if (ret)
+		return ret;
+
+	WARN_ON(!con->in_msg ^ skip);
+	if (skip)
+		return 0;
+
+	WARN_ON(!con->in_msg);
+	WARN_ON(con->in_msg->con != con);
+	return 1;
+}
+
+static int process_message(struct ceph_connection *con)
+{
+	ceph_con_process_message(con);
+
+	/*
+	 * We could have been closed by ceph_con_close() because
+	 * ceph_con_process_message() temporarily drops con->mutex.
+	 */
+	if (con->state != CEPH_CON_S_OPEN) {
+		dout("%s con %p state changed to %d\n", __func__, con,
+		     con->state);
+		return -EAGAIN;
+	}
+
+	prepare_read_preamble(con);
+	return 0;
+}
+
+static int __handle_control(struct ceph_connection *con, void *p)
+{
+	void *end = p + con->v2.in_desc.fd_lens[0];
+	struct ceph_msg *msg;
+	int ret;
+
+	if (con->v2.in_desc.fd_tag != FRAME_TAG_MESSAGE)
+		return process_control(con, p, end);
+
+	ret = process_message_header(con, p, end);
+	if (ret < 0)
+		return ret;
+	if (ret == 0) {
+		prepare_skip_message(con);
+		return 0;
+	}
+
+	msg = con->in_msg;  /* set in process_message_header() */
+	if (!front_len(msg) && !middle_len(msg)) {
+		if (!data_len(msg))
+			return process_message(con);
+
+		prepare_read_data(con);
+		return 0;
+	}
+
+	reset_in_kvecs(con);
+	if (front_len(msg)) {
+		WARN_ON(front_len(msg) > msg->front_alloc_len);
+		add_in_kvec(con, msg->front.iov_base, front_len(msg));
+		msg->front.iov_len = front_len(msg);
+
+		if (con_secure(con) && need_padding(front_len(msg)))
+			add_in_kvec(con, FRONT_PAD(con->v2.in_buf),
+				    padding_len(front_len(msg)));
+	} else {
+		msg->front.iov_len = 0;
+	}
+	if (middle_len(msg)) {
+		WARN_ON(middle_len(msg) > msg->middle->alloc_len);
+		add_in_kvec(con, msg->middle->vec.iov_base, middle_len(msg));
+		msg->middle->vec.iov_len = middle_len(msg);
+
+		if (con_secure(con) && need_padding(middle_len(msg)))
+			add_in_kvec(con, MIDDLE_PAD(con->v2.in_buf),
+				    padding_len(middle_len(msg)));
+	} else if (msg->middle) {
+		msg->middle->vec.iov_len = 0;
+	}
+
+	if (data_len(msg)) {
+		con->v2.in_state = IN_S_PREPARE_READ_DATA;
+	} else {
+		add_in_kvec(con, con->v2.in_buf,
+			    con_secure(con) ? CEPH_EPILOGUE_SECURE_LEN :
+					      CEPH_EPILOGUE_PLAIN_LEN);
+		con->v2.in_state = IN_S_HANDLE_EPILOGUE;
+	}
+	return 0;
+}
+
+static int handle_preamble(struct ceph_connection *con)
+{
+	struct ceph_frame_desc *desc = &con->v2.in_desc;
+	int ret;
+
+	if (con_secure(con)) {
+		ret = decrypt_preamble(con);
+		if (ret) {
+			if (ret == -EBADMSG)
+				con->error_msg = "integrity error, bad preamble auth tag";
+			return ret;
+		}
+	}
+
+	ret = decode_preamble(con->v2.in_buf, desc);
+	if (ret) {
+		if (ret == -EBADMSG)
+			con->error_msg = "integrity error, bad crc";
+		else
+			con->error_msg = "protocol error, bad preamble";
+		return ret;
+	}
+
+	dout("%s con %p tag %d seg_cnt %d %d+%d+%d+%d\n", __func__,
+	     con, desc->fd_tag, desc->fd_seg_cnt, desc->fd_lens[0],
+	     desc->fd_lens[1], desc->fd_lens[2], desc->fd_lens[3]);
+
+	if (!con_secure(con))
+		return prepare_read_control(con);
+
+	if (desc->fd_lens[0] > CEPH_PREAMBLE_INLINE_LEN)
+		return prepare_read_control_remainder(con);
+
+	return __handle_control(con, CTRL_BODY(con->v2.in_buf));
+}
+
+static int handle_control(struct ceph_connection *con)
+{
+	int ctrl_len = con->v2.in_desc.fd_lens[0];
+	void *buf;
+	int ret;
+
+	WARN_ON(con_secure(con));
+
+	ret = verify_control_crc(con);
+	if (ret) {
+		con->error_msg = "integrity error, bad crc";
+		return ret;
+	}
+
+	if (con->state == CEPH_CON_S_V2_AUTH) {
+		buf = alloc_conn_buf(con, ctrl_len);
+		if (!buf)
+			return -ENOMEM;
+
+		memcpy(buf, con->v2.in_kvecs[0].iov_base, ctrl_len);
+		return __handle_control(con, buf);
+	}
+
+	return __handle_control(con, con->v2.in_kvecs[0].iov_base);
+}
+
+static int handle_control_remainder(struct ceph_connection *con)
+{
+	int ret;
+
+	WARN_ON(!con_secure(con));
+
+	ret = decrypt_control_remainder(con);
+	if (ret) {
+		if (ret == -EBADMSG)
+			con->error_msg = "integrity error, bad control remainder auth tag";
+		return ret;
+	}
+
+	return __handle_control(con, con->v2.in_kvecs[0].iov_base -
+				     CEPH_PREAMBLE_INLINE_LEN);
+}
+
+static int handle_epilogue(struct ceph_connection *con)
+{
+	u32 front_crc, middle_crc, data_crc;
+	int ret;
+
+	if (con_secure(con)) {
+		ret = decrypt_message(con);
+		if (ret) {
+			if (ret == -EBADMSG)
+				con->error_msg = "integrity error, bad epilogue auth tag";
+			return ret;
+		}
+
+		/* just late_status */
+		ret = decode_epilogue(con->v2.in_buf, NULL, NULL, NULL);
+		if (ret) {
+			con->error_msg = "protocol error, bad epilogue";
+			return ret;
+		}
+	} else {
+		ret = decode_epilogue(con->v2.in_buf, &front_crc,
+				      &middle_crc, &data_crc);
+		if (ret) {
+			con->error_msg = "protocol error, bad epilogue";
+			return ret;
+		}
+
+		ret = verify_epilogue_crcs(con, front_crc, middle_crc,
+					   data_crc);
+		if (ret) {
+			con->error_msg = "integrity error, bad crc";
+			return ret;
+		}
+	}
+
+	return process_message(con);
+}
+
+static void finish_skip(struct ceph_connection *con)
+{
+	dout("%s con %p\n", __func__, con);
+
+	if (con_secure(con))
+		gcm_inc_nonce(&con->v2.in_gcm_nonce);
+
+	__finish_skip(con);
+}
+
+static int populate_in_iter(struct ceph_connection *con)
+{
+	int ret;
+
+	dout("%s con %p state %d in_state %d\n", __func__, con, con->state,
+	     con->v2.in_state);
+	WARN_ON(iov_iter_count(&con->v2.in_iter));
+
+	if (con->state == CEPH_CON_S_V2_BANNER_PREFIX) {
+		ret = process_banner_prefix(con);
+	} else if (con->state == CEPH_CON_S_V2_BANNER_PAYLOAD) {
+		ret = process_banner_payload(con);
+	} else if ((con->state >= CEPH_CON_S_V2_HELLO &&
+		    con->state <= CEPH_CON_S_V2_SESSION_RECONNECT) ||
+		   con->state == CEPH_CON_S_OPEN) {
+		switch (con->v2.in_state) {
+		case IN_S_HANDLE_PREAMBLE:
+			ret = handle_preamble(con);
+			break;
+		case IN_S_HANDLE_CONTROL:
+			ret = handle_control(con);
+			break;
+		case IN_S_HANDLE_CONTROL_REMAINDER:
+			ret = handle_control_remainder(con);
+			break;
+		case IN_S_PREPARE_READ_DATA:
+			prepare_read_data(con);
+			ret = 0;
+			break;
+		case IN_S_PREPARE_READ_DATA_CONT:
+			prepare_read_data_cont(con);
+			ret = 0;
+			break;
+		case IN_S_HANDLE_EPILOGUE:
+			ret = handle_epilogue(con);
+			break;
+		case IN_S_FINISH_SKIP:
+			finish_skip(con);
+			ret = 0;
+			break;
+		default:
+			WARN(1, "bad in_state %d", con->v2.in_state);
+			return -EINVAL;
+		}
+	} else {
+		WARN(1, "bad state %d", con->state);
+		return -EINVAL;
+	}
+	if (ret) {
+		dout("%s con %p error %d\n", __func__, con, ret);
+		return ret;
+	}
+
+	if (WARN_ON(!iov_iter_count(&con->v2.in_iter)))
+		return -ENODATA;
+	dout("%s con %p populated %zu\n", __func__, con,
+	     iov_iter_count(&con->v2.in_iter));
+	return 1;
+}
+
+int ceph_con_v2_try_read(struct ceph_connection *con)
+{
+	int ret;
+
+	dout("%s con %p state %d need %zu\n", __func__, con, con->state,
+	     iov_iter_count(&con->v2.in_iter));
+
+	if (con->state == CEPH_CON_S_PREOPEN)
+		return 0;
+
+	/*
+	 * We should always have something pending here.  If not,
+	 * avoid calling populate_in_iter() as if we read something
+	 * (ceph_tcp_recv() would immediately return 1).
+	 */
+	if (WARN_ON(!iov_iter_count(&con->v2.in_iter)))
+		return -ENODATA;
+
+	for (;;) {
+		ret = ceph_tcp_recv(con);
+		if (ret <= 0)
+			return ret;
+
+		ret = populate_in_iter(con);
+		if (ret <= 0) {
+			if (ret && ret != -EAGAIN && !con->error_msg)
+				con->error_msg = "read processing error";
+			return ret;
+		}
+	}
+}
+
+static void queue_data(struct ceph_connection *con)
+{
+	struct bio_vec bv;
+
+	con->v2.out_epil.data_crc = -1;
+	ceph_msg_data_cursor_init(&con->v2.out_cursor, con->out_msg,
+				  data_len(con->out_msg));
+
+	get_bvec_at(&con->v2.out_cursor, &bv);
+	set_out_bvec(con, &bv, true);
+	con->v2.out_state = OUT_S_QUEUE_DATA_CONT;
+}
+
+static void queue_data_cont(struct ceph_connection *con)
+{
+	struct bio_vec bv;
+
+	con->v2.out_epil.data_crc = ceph_crc32c_page(
+		con->v2.out_epil.data_crc, con->v2.out_bvec.bv_page,
+		con->v2.out_bvec.bv_offset, con->v2.out_bvec.bv_len);
+
+	ceph_msg_data_advance(&con->v2.out_cursor, con->v2.out_bvec.bv_len);
+	if (con->v2.out_cursor.total_resid) {
+		get_bvec_at(&con->v2.out_cursor, &bv);
+		set_out_bvec(con, &bv, true);
+		WARN_ON(con->v2.out_state != OUT_S_QUEUE_DATA_CONT);
+		return;
+	}
+
+	/*
+	 * We've written all data.  Queue epilogue.  Once it's written,
+	 * we are done.
+	 */
+	reset_out_kvecs(con);
+	prepare_epilogue_plain(con, false);
+	con->v2.out_state = OUT_S_FINISH_MESSAGE;
+}
+
+static void queue_enc_page(struct ceph_connection *con)
+{
+	struct bio_vec bv;
+
+	dout("%s con %p i %d resid %d\n", __func__, con, con->v2.out_enc_i,
+	     con->v2.out_enc_resid);
+	WARN_ON(!con->v2.out_enc_resid);
+
+	bv.bv_page = con->v2.out_enc_pages[con->v2.out_enc_i];
+	bv.bv_offset = 0;
+	bv.bv_len = min(con->v2.out_enc_resid, (int)PAGE_SIZE);
+
+	set_out_bvec(con, &bv, false);
+	con->v2.out_enc_i++;
+	con->v2.out_enc_resid -= bv.bv_len;
+
+	if (con->v2.out_enc_resid) {
+		WARN_ON(con->v2.out_state != OUT_S_QUEUE_ENC_PAGE);
+		return;
+	}
+
+	/*
+	 * We've queued the last piece of ciphertext (ending with
+	 * epilogue) + auth tag.  Once it's written, we are done.
+	 */
+	WARN_ON(con->v2.out_enc_i != con->v2.out_enc_page_cnt);
+	con->v2.out_state = OUT_S_FINISH_MESSAGE;
+}
+
+static void queue_zeros(struct ceph_connection *con)
+{
+	dout("%s con %p out_zero %d\n", __func__, con, con->v2.out_zero);
+
+	if (con->v2.out_zero) {
+		set_out_bvec_zero(con);
+		con->v2.out_zero -= con->v2.out_bvec.bv_len;
+		con->v2.out_state = OUT_S_QUEUE_ZEROS;
+		return;
+	}
+
+	/*
+	 * We've zero-filled everything up to epilogue.  Queue epilogue
+	 * with late_status set to ABORTED and crcs adjusted for zeros.
+	 * Once it's written, we are done patching up for the revoke.
+	 */
+	reset_out_kvecs(con);
+	prepare_epilogue_plain(con, true);
+	con->v2.out_state = OUT_S_FINISH_MESSAGE;
+}
+
+static void finish_message(struct ceph_connection *con)
+{
+	dout("%s con %p msg %p\n", __func__, con, con->out_msg);
+
+	/* we end up here both plain and secure modes */
+	if (con->v2.out_enc_pages) {
+		WARN_ON(!con->v2.out_enc_page_cnt);
+		ceph_release_page_vector(con->v2.out_enc_pages,
+					 con->v2.out_enc_page_cnt);
+		con->v2.out_enc_pages = NULL;
+		con->v2.out_enc_page_cnt = 0;
+	}
+	/* message may have been revoked */
+	if (con->out_msg) {
+		ceph_msg_put(con->out_msg);
+		con->out_msg = NULL;
+	}
+
+	con->v2.out_state = OUT_S_GET_NEXT;
+}
+
+static int populate_out_iter(struct ceph_connection *con)
+{
+	int ret;
+
+	dout("%s con %p state %d out_state %d\n", __func__, con, con->state,
+	     con->v2.out_state);
+	WARN_ON(iov_iter_count(&con->v2.out_iter));
+
+	if (con->state != CEPH_CON_S_OPEN) {
+		WARN_ON(con->state < CEPH_CON_S_V2_BANNER_PREFIX ||
+			con->state > CEPH_CON_S_V2_SESSION_RECONNECT);
+		goto nothing_pending;
+	}
+
+	switch (con->v2.out_state) {
+	case OUT_S_QUEUE_DATA:
+		WARN_ON(!con->out_msg);
+		queue_data(con);
+		goto populated;
+	case OUT_S_QUEUE_DATA_CONT:
+		WARN_ON(!con->out_msg);
+		queue_data_cont(con);
+		goto populated;
+	case OUT_S_QUEUE_ENC_PAGE:
+		queue_enc_page(con);
+		goto populated;
+	case OUT_S_QUEUE_ZEROS:
+		WARN_ON(con->out_msg);  /* revoked */
+		queue_zeros(con);
+		goto populated;
+	case OUT_S_FINISH_MESSAGE:
+		finish_message(con);
+		break;
+	case OUT_S_GET_NEXT:
+		break;
+	default:
+		WARN(1, "bad out_state %d", con->v2.out_state);
+		return -EINVAL;
+	}
+
+	WARN_ON(con->v2.out_state != OUT_S_GET_NEXT);
+	if (ceph_con_flag_test_and_clear(con, CEPH_CON_F_KEEPALIVE_PENDING)) {
+		ret = prepare_keepalive2(con);
+		if (ret) {
+			pr_err("prepare_keepalive2 failed: %d\n", ret);
+			return ret;
+		}
+	} else if (!list_empty(&con->out_queue)) {
+		ceph_con_get_out_msg(con);
+		ret = prepare_message(con);
+		if (ret) {
+			pr_err("prepare_message failed: %d\n", ret);
+			return ret;
+		}
+	} else if (con->in_seq > con->in_seq_acked) {
+		ret = prepare_ack(con);
+		if (ret) {
+			pr_err("prepare_ack failed: %d\n", ret);
+			return ret;
+		}
+	} else {
+		goto nothing_pending;
+	}
+
+populated:
+	if (WARN_ON(!iov_iter_count(&con->v2.out_iter)))
+		return -ENODATA;
+	dout("%s con %p populated %zu\n", __func__, con,
+	     iov_iter_count(&con->v2.out_iter));
+	return 1;
+
+nothing_pending:
+	WARN_ON(iov_iter_count(&con->v2.out_iter));
+	dout("%s con %p nothing pending\n", __func__, con);
+	ceph_con_flag_clear(con, CEPH_CON_F_WRITE_PENDING);
+	return 0;
+}
+
+int ceph_con_v2_try_write(struct ceph_connection *con)
+{
+	int ret;
+
+	dout("%s con %p state %d have %zu\n", __func__, con, con->state,
+	     iov_iter_count(&con->v2.out_iter));
+
+	/* open the socket first? */
+	if (con->state == CEPH_CON_S_PREOPEN) {
+		WARN_ON(con->peer_addr.type != CEPH_ENTITY_ADDR_TYPE_MSGR2);
+
+		/*
+		 * Always bump global_seq.  Bump connect_seq only if
+		 * there is a session (i.e. we are reconnecting and will
+		 * send session_reconnect instead of client_ident).
+		 */
+		con->v2.global_seq = ceph_get_global_seq(con->msgr, 0);
+		if (con->v2.server_cookie)
+			con->v2.connect_seq++;
+
+		ret = prepare_read_banner_prefix(con);
+		if (ret) {
+			pr_err("prepare_read_banner_prefix failed: %d\n", ret);
+			con->error_msg = "connect error";
+			return ret;
+		}
+
+		reset_out_kvecs(con);
+		ret = prepare_banner(con);
+		if (ret) {
+			pr_err("prepare_banner failed: %d\n", ret);
+			con->error_msg = "connect error";
+			return ret;
+		}
+
+		ret = ceph_tcp_connect(con);
+		if (ret) {
+			pr_err("ceph_tcp_connect failed: %d\n", ret);
+			con->error_msg = "connect error";
+			return ret;
+		}
+	}
+
+	if (!iov_iter_count(&con->v2.out_iter)) {
+		ret = populate_out_iter(con);
+		if (ret <= 0) {
+			if (ret && ret != -EAGAIN && !con->error_msg)
+				con->error_msg = "write processing error";
+			return ret;
+		}
+	}
+
+	tcp_sock_set_cork(con->sock->sk, true);
+	for (;;) {
+		ret = ceph_tcp_send(con);
+		if (ret <= 0)
+			break;
+
+		ret = populate_out_iter(con);
+		if (ret <= 0) {
+			if (ret && ret != -EAGAIN && !con->error_msg)
+				con->error_msg = "write processing error";
+			break;
+		}
+	}
+
+	tcp_sock_set_cork(con->sock->sk, false);
+	return ret;
+}
+
+static u32 crc32c_zeros(u32 crc, int zero_len)
+{
+	int len;
+
+	while (zero_len) {
+		len = min(zero_len, (int)PAGE_SIZE);
+		crc = crc32c(crc, page_address(ceph_zero_page), len);
+		zero_len -= len;
+	}
+
+	return crc;
+}
+
+static void prepare_zero_front(struct ceph_connection *con, int resid)
+{
+	int sent;
+
+	WARN_ON(!resid || resid > front_len(con->out_msg));
+	sent = front_len(con->out_msg) - resid;
+	dout("%s con %p sent %d resid %d\n", __func__, con, sent, resid);
+
+	if (sent) {
+		con->v2.out_epil.front_crc =
+			crc32c(-1, con->out_msg->front.iov_base, sent);
+		con->v2.out_epil.front_crc =
+			crc32c_zeros(con->v2.out_epil.front_crc, resid);
+	} else {
+		con->v2.out_epil.front_crc = crc32c_zeros(-1, resid);
+	}
+
+	con->v2.out_iter.count -= resid;
+	out_zero_add(con, resid);
+}
+
+static void prepare_zero_middle(struct ceph_connection *con, int resid)
+{
+	int sent;
+
+	WARN_ON(!resid || resid > middle_len(con->out_msg));
+	sent = middle_len(con->out_msg) - resid;
+	dout("%s con %p sent %d resid %d\n", __func__, con, sent, resid);
+
+	if (sent) {
+		con->v2.out_epil.middle_crc =
+			crc32c(-1, con->out_msg->middle->vec.iov_base, sent);
+		con->v2.out_epil.middle_crc =
+			crc32c_zeros(con->v2.out_epil.middle_crc, resid);
+	} else {
+		con->v2.out_epil.middle_crc = crc32c_zeros(-1, resid);
+	}
+
+	con->v2.out_iter.count -= resid;
+	out_zero_add(con, resid);
+}
+
+static void prepare_zero_data(struct ceph_connection *con)
+{
+	dout("%s con %p\n", __func__, con);
+	con->v2.out_epil.data_crc = crc32c_zeros(-1, data_len(con->out_msg));
+	out_zero_add(con, data_len(con->out_msg));
+}
+
+static void revoke_at_queue_data(struct ceph_connection *con)
+{
+	int boundary;
+	int resid;
+
+	WARN_ON(!data_len(con->out_msg));
+	WARN_ON(!iov_iter_is_kvec(&con->v2.out_iter));
+	resid = iov_iter_count(&con->v2.out_iter);
+
+	boundary = front_len(con->out_msg) + middle_len(con->out_msg);
+	if (resid > boundary) {
+		resid -= boundary;
+		WARN_ON(resid > MESSAGE_HEAD_PLAIN_LEN);
+		dout("%s con %p was sending head\n", __func__, con);
+		if (front_len(con->out_msg))
+			prepare_zero_front(con, front_len(con->out_msg));
+		if (middle_len(con->out_msg))
+			prepare_zero_middle(con, middle_len(con->out_msg));
+		prepare_zero_data(con);
+		WARN_ON(iov_iter_count(&con->v2.out_iter) != resid);
+		con->v2.out_state = OUT_S_QUEUE_ZEROS;
+		return;
+	}
+
+	boundary = middle_len(con->out_msg);
+	if (resid > boundary) {
+		resid -= boundary;
+		dout("%s con %p was sending front\n", __func__, con);
+		prepare_zero_front(con, resid);
+		if (middle_len(con->out_msg))
+			prepare_zero_middle(con, middle_len(con->out_msg));
+		prepare_zero_data(con);
+		queue_zeros(con);
+		return;
+	}
+
+	WARN_ON(!resid);
+	dout("%s con %p was sending middle\n", __func__, con);
+	prepare_zero_middle(con, resid);
+	prepare_zero_data(con);
+	queue_zeros(con);
+}
+
+static void revoke_at_queue_data_cont(struct ceph_connection *con)
+{
+	int sent, resid;  /* current piece of data */
+
+	WARN_ON(!data_len(con->out_msg));
+	WARN_ON(!iov_iter_is_bvec(&con->v2.out_iter));
+	resid = iov_iter_count(&con->v2.out_iter);
+	WARN_ON(!resid || resid > con->v2.out_bvec.bv_len);
+	sent = con->v2.out_bvec.bv_len - resid;
+	dout("%s con %p sent %d resid %d\n", __func__, con, sent, resid);
+
+	if (sent) {
+		con->v2.out_epil.data_crc = ceph_crc32c_page(
+			con->v2.out_epil.data_crc, con->v2.out_bvec.bv_page,
+			con->v2.out_bvec.bv_offset, sent);
+		ceph_msg_data_advance(&con->v2.out_cursor, sent);
+	}
+	WARN_ON(resid > con->v2.out_cursor.total_resid);
+	con->v2.out_epil.data_crc = crc32c_zeros(con->v2.out_epil.data_crc,
+						con->v2.out_cursor.total_resid);
+
+	con->v2.out_iter.count -= resid;
+	out_zero_add(con, con->v2.out_cursor.total_resid);
+	queue_zeros(con);
+}
+
+static void revoke_at_finish_message(struct ceph_connection *con)
+{
+	int boundary;
+	int resid;
+
+	WARN_ON(!iov_iter_is_kvec(&con->v2.out_iter));
+	resid = iov_iter_count(&con->v2.out_iter);
+
+	if (!front_len(con->out_msg) && !middle_len(con->out_msg) &&
+	    !data_len(con->out_msg)) {
+		WARN_ON(!resid || resid > MESSAGE_HEAD_PLAIN_LEN);
+		dout("%s con %p was sending head (empty message) - noop\n",
+		     __func__, con);
+		return;
+	}
+
+	boundary = front_len(con->out_msg) + middle_len(con->out_msg) +
+		   CEPH_EPILOGUE_PLAIN_LEN;
+	if (resid > boundary) {
+		resid -= boundary;
+		WARN_ON(resid > MESSAGE_HEAD_PLAIN_LEN);
+		dout("%s con %p was sending head\n", __func__, con);
+		if (front_len(con->out_msg))
+			prepare_zero_front(con, front_len(con->out_msg));
+		if (middle_len(con->out_msg))
+			prepare_zero_middle(con, middle_len(con->out_msg));
+		con->v2.out_iter.count -= CEPH_EPILOGUE_PLAIN_LEN;
+		WARN_ON(iov_iter_count(&con->v2.out_iter) != resid);
+		con->v2.out_state = OUT_S_QUEUE_ZEROS;
+		return;
+	}
+
+	boundary = middle_len(con->out_msg) + CEPH_EPILOGUE_PLAIN_LEN;
+	if (resid > boundary) {
+		resid -= boundary;
+		dout("%s con %p was sending front\n", __func__, con);
+		prepare_zero_front(con, resid);
+		if (middle_len(con->out_msg))
+			prepare_zero_middle(con, middle_len(con->out_msg));
+		con->v2.out_iter.count -= CEPH_EPILOGUE_PLAIN_LEN;
+		queue_zeros(con);
+		return;
+	}
+
+	boundary = CEPH_EPILOGUE_PLAIN_LEN;
+	if (resid > boundary) {
+		resid -= boundary;
+		dout("%s con %p was sending middle\n", __func__, con);
+		prepare_zero_middle(con, resid);
+		con->v2.out_iter.count -= CEPH_EPILOGUE_PLAIN_LEN;
+		queue_zeros(con);
+		return;
+	}
+
+	WARN_ON(!resid);
+	dout("%s con %p was sending epilogue - noop\n", __func__, con);
+}
+
+void ceph_con_v2_revoke(struct ceph_connection *con)
+{
+	WARN_ON(con->v2.out_zero);
+
+	if (con_secure(con)) {
+		WARN_ON(con->v2.out_state != OUT_S_QUEUE_ENC_PAGE &&
+			con->v2.out_state != OUT_S_FINISH_MESSAGE);
+		dout("%s con %p secure - noop\n", __func__, con);
+		return;
+	}
+
+	switch (con->v2.out_state) {
+	case OUT_S_QUEUE_DATA:
+		revoke_at_queue_data(con);
+		break;
+	case OUT_S_QUEUE_DATA_CONT:
+		revoke_at_queue_data_cont(con);
+		break;
+	case OUT_S_FINISH_MESSAGE:
+		revoke_at_finish_message(con);
+		break;
+	default:
+		WARN(1, "bad out_state %d", con->v2.out_state);
+		break;
+	}
+}
+
+static void revoke_at_prepare_read_data(struct ceph_connection *con)
+{
+	int remaining;  /* data + [data padding] + epilogue */
+	int resid;
+
+	WARN_ON(!data_len(con->in_msg));
+	WARN_ON(!iov_iter_is_kvec(&con->v2.in_iter));
+	resid = iov_iter_count(&con->v2.in_iter);
+	WARN_ON(!resid);
+
+	if (con_secure(con))
+		remaining = padded_len(data_len(con->in_msg)) +
+			    CEPH_EPILOGUE_SECURE_LEN;
+	else
+		remaining = data_len(con->in_msg) + CEPH_EPILOGUE_PLAIN_LEN;
+
+	dout("%s con %p resid %d remaining %d\n", __func__, con, resid,
+	     remaining);
+	con->v2.in_iter.count -= resid;
+	set_in_skip(con, resid + remaining);
+	con->v2.in_state = IN_S_FINISH_SKIP;
+}
+
+static void revoke_at_prepare_read_data_cont(struct ceph_connection *con)
+{
+	int recved, resid;  /* current piece of data */
+	int remaining;  /* [data padding] + epilogue */
+
+	WARN_ON(!data_len(con->in_msg));
+	WARN_ON(!iov_iter_is_bvec(&con->v2.in_iter));
+	resid = iov_iter_count(&con->v2.in_iter);
+	WARN_ON(!resid || resid > con->v2.in_bvec.bv_len);
+	recved = con->v2.in_bvec.bv_len - resid;
+	dout("%s con %p recved %d resid %d\n", __func__, con, recved, resid);
+
+	if (recved)
+		ceph_msg_data_advance(&con->v2.in_cursor, recved);
+	WARN_ON(resid > con->v2.in_cursor.total_resid);
+
+	if (con_secure(con))
+		remaining = padding_len(data_len(con->in_msg)) +
+			    CEPH_EPILOGUE_SECURE_LEN;
+	else
+		remaining = CEPH_EPILOGUE_PLAIN_LEN;
+
+	dout("%s con %p total_resid %zu remaining %d\n", __func__, con,
+	     con->v2.in_cursor.total_resid, remaining);
+	con->v2.in_iter.count -= resid;
+	set_in_skip(con, con->v2.in_cursor.total_resid + remaining);
+	con->v2.in_state = IN_S_FINISH_SKIP;
+}
+
+static void revoke_at_handle_epilogue(struct ceph_connection *con)
+{
+	int resid;
+
+	WARN_ON(!iov_iter_is_kvec(&con->v2.in_iter));
+	resid = iov_iter_count(&con->v2.in_iter);
+	WARN_ON(!resid);
+
+	dout("%s con %p resid %d\n", __func__, con, resid);
+	con->v2.in_iter.count -= resid;
+	set_in_skip(con, resid);
+	con->v2.in_state = IN_S_FINISH_SKIP;
+}
+
+void ceph_con_v2_revoke_incoming(struct ceph_connection *con)
+{
+	switch (con->v2.in_state) {
+	case IN_S_PREPARE_READ_DATA:
+		revoke_at_prepare_read_data(con);
+		break;
+	case IN_S_PREPARE_READ_DATA_CONT:
+		revoke_at_prepare_read_data_cont(con);
+		break;
+	case IN_S_HANDLE_EPILOGUE:
+		revoke_at_handle_epilogue(con);
+		break;
+	default:
+		WARN(1, "bad in_state %d", con->v2.in_state);
+		break;
+	}
+}
+
+bool ceph_con_v2_opened(struct ceph_connection *con)
+{
+	return con->v2.peer_global_seq;
+}
+
+void ceph_con_v2_reset_session(struct ceph_connection *con)
+{
+	con->v2.client_cookie = 0;
+	con->v2.server_cookie = 0;
+	con->v2.global_seq = 0;
+	con->v2.connect_seq = 0;
+	con->v2.peer_global_seq = 0;
+}
+
+void ceph_con_v2_reset_protocol(struct ceph_connection *con)
+{
+	iov_iter_truncate(&con->v2.in_iter, 0);
+	iov_iter_truncate(&con->v2.out_iter, 0);
+	con->v2.out_zero = 0;
+
+	clear_in_sign_kvecs(con);
+	clear_out_sign_kvecs(con);
+	free_conn_bufs(con);
+
+	if (con->v2.out_enc_pages) {
+		WARN_ON(!con->v2.out_enc_page_cnt);
+		ceph_release_page_vector(con->v2.out_enc_pages,
+					 con->v2.out_enc_page_cnt);
+		con->v2.out_enc_pages = NULL;
+		con->v2.out_enc_page_cnt = 0;
+	}
+
+	con->v2.con_mode = CEPH_CON_MODE_UNKNOWN;
+
+	if (con->v2.hmac_tfm) {
+		crypto_free_shash(con->v2.hmac_tfm);
+		con->v2.hmac_tfm = NULL;
+	}
+	if (con->v2.gcm_req) {
+		aead_request_free(con->v2.gcm_req);
+		con->v2.gcm_req = NULL;
+	}
+	if (con->v2.gcm_tfm) {
+		crypto_free_aead(con->v2.gcm_tfm);
+		con->v2.gcm_tfm = NULL;
+	}
+}
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index 792a8c4164d7..b9d54ed9f338 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -257,10 +257,16 @@ static void __open_session(struct ceph_mon_client *monc)
 		      &monc->monmap->mon_inst[monc->cur_mon].addr);
 
 	/*
-	 * send an initial keepalive to ensure our timestamp is valid
-	 * by the time we are in an OPENED state
+	 * Queue a keepalive to ensure that in case of an early fault
+	 * the messenger doesn't put us into STANDBY state and instead
+	 * retries.  This also ensures that our timestamp is valid by
+	 * the time we finish hunting and delayed_work() checks it.
 	 */
 	ceph_con_keepalive(&monc->con);
+	if (ceph_msgr2(monc->client)) {
+		monc->pending_auth = 1;
+		return;
+	}
 
 	/* initiate authentication handshake */
 	ret = ceph_auth_build_hello(monc->auth,
@@ -543,7 +549,7 @@ static void ceph_monc_handle_map(struct ceph_mon_client *monc,
 	p = msg->front.iov_base;
 	end = p + msg->front.iov_len;
 
-	monmap = ceph_monmap_decode(&p, end, false);
+	monmap = ceph_monmap_decode(&p, end, ceph_msgr2(client));
 	if (IS_ERR(monmap)) {
 		pr_err("problem decoding monmap, %d\n",
 		       (int)PTR_ERR(monmap));
@@ -1119,8 +1125,9 @@ static void delayed_work(struct work_struct *work)
  */
 static int build_initial_monmap(struct ceph_mon_client *monc)
 {
+	__le32 my_type = ceph_msgr2(monc->client) ?
+		CEPH_ENTITY_ADDR_TYPE_MSGR2 : CEPH_ENTITY_ADDR_TYPE_LEGACY;
 	struct ceph_options *opt = monc->client->options;
-	struct ceph_entity_addr *mon_addr = opt->mon_addr;
 	int num_mon = opt->num_mon;
 	int i;
 
@@ -1129,12 +1136,16 @@ static int build_initial_monmap(struct ceph_mon_client *monc)
 			       GFP_KERNEL);
 	if (!monc->monmap)
 		return -ENOMEM;
+
 	for (i = 0; i < num_mon; i++) {
-		monc->monmap->mon_inst[i].addr = mon_addr[i];
-		monc->monmap->mon_inst[i].addr.nonce = 0;
-		monc->monmap->mon_inst[i].name.type =
-			CEPH_ENTITY_TYPE_MON;
-		monc->monmap->mon_inst[i].name.num = cpu_to_le64(i);
+		struct ceph_entity_inst *inst = &monc->monmap->mon_inst[i];
+
+		memcpy(&inst->addr.in_addr, &opt->mon_addr[i].in_addr,
+		       sizeof(inst->addr.in_addr));
+		inst->addr.type = my_type;
+		inst->addr.nonce = 0;
+		inst->name.type = CEPH_ENTITY_TYPE_MON;
+		inst->name.num = cpu_to_le64(i);
 	}
 	monc->monmap->num_mon = num_mon;
 	return 0;
@@ -1337,6 +1348,88 @@ int ceph_monc_validate_auth(struct ceph_mon_client *monc)
 }
 EXPORT_SYMBOL(ceph_monc_validate_auth);
 
+static int mon_get_auth_request(struct ceph_connection *con,
+				void *buf, int *buf_len,
+				void **authorizer, int *authorizer_len)
+{
+	struct ceph_mon_client *monc = con->private;
+	int ret;
+
+	mutex_lock(&monc->mutex);
+	ret = ceph_auth_get_request(monc->auth, buf, *buf_len);
+	mutex_unlock(&monc->mutex);
+	if (ret < 0)
+		return ret;
+
+	*buf_len = ret;
+	*authorizer = NULL;
+	*authorizer_len = 0;
+	return 0;
+}
+
+static int mon_handle_auth_reply_more(struct ceph_connection *con,
+				      void *reply, int reply_len,
+				      void *buf, int *buf_len,
+				      void **authorizer, int *authorizer_len)
+{
+	struct ceph_mon_client *monc = con->private;
+	int ret;
+
+	mutex_lock(&monc->mutex);
+	ret = ceph_auth_handle_reply_more(monc->auth, reply, reply_len,
+					  buf, *buf_len);
+	mutex_unlock(&monc->mutex);
+	if (ret < 0)
+		return ret;
+
+	*buf_len = ret;
+	*authorizer = NULL;
+	*authorizer_len = 0;
+	return 0;
+}
+
+static int mon_handle_auth_done(struct ceph_connection *con,
+				u64 global_id, void *reply, int reply_len,
+				u8 *session_key, int *session_key_len,
+				u8 *con_secret, int *con_secret_len)
+{
+	struct ceph_mon_client *monc = con->private;
+	bool was_authed;
+	int ret;
+
+	mutex_lock(&monc->mutex);
+	WARN_ON(!monc->hunting);
+	was_authed = ceph_auth_is_authenticated(monc->auth);
+	ret = ceph_auth_handle_reply_done(monc->auth, global_id,
+					  reply, reply_len,
+					  session_key, session_key_len,
+					  con_secret, con_secret_len);
+	finish_auth(monc, ret, was_authed);
+	if (!ret)
+		finish_hunting(monc);
+	mutex_unlock(&monc->mutex);
+	return 0;
+}
+
+static int mon_handle_auth_bad_method(struct ceph_connection *con,
+				      int used_proto, int result,
+				      const int *allowed_protos, int proto_cnt,
+				      const int *allowed_modes, int mode_cnt)
+{
+	struct ceph_mon_client *monc = con->private;
+	bool was_authed;
+
+	mutex_lock(&monc->mutex);
+	WARN_ON(!monc->hunting);
+	was_authed = ceph_auth_is_authenticated(monc->auth);
+	ceph_auth_handle_bad_method(monc->auth, used_proto, result,
+				    allowed_protos, proto_cnt,
+				    allowed_modes, mode_cnt);
+	finish_auth(monc, -EACCES, was_authed);
+	mutex_unlock(&monc->mutex);
+	return 0;
+}
+
 /*
  * handle incoming message
  */
@@ -1487,4 +1580,8 @@ static const struct ceph_connection_operations mon_con_ops = {
 	.dispatch = dispatch,
 	.fault = mon_fault,
 	.alloc_msg = mon_alloc_msg,
+	.get_auth_request = mon_get_auth_request,
+	.handle_auth_reply_more = mon_handle_auth_reply_more,
+	.handle_auth_done = mon_handle_auth_done,
+	.handle_auth_bad_method = mon_handle_auth_bad_method,
 };
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 51be5a7482fc..662b52e52651 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -3918,9 +3918,11 @@ static int handle_one_map(struct ceph_osd_client *osdc,
 	set_pool_was_full(osdc);
 
 	if (incremental)
-		newmap = osdmap_apply_incremental(&p, end, false, osdc->osdmap);
+		newmap = osdmap_apply_incremental(&p, end,
+						  ceph_msgr2(osdc->client),
+						  osdc->osdmap);
 	else
-		newmap = ceph_osdmap_decode(&p, end, false);
+		newmap = ceph_osdmap_decode(&p, end, ceph_msgr2(osdc->client));
 	if (IS_ERR(newmap))
 		return PTR_ERR(newmap);
 
@@ -5575,6 +5577,7 @@ static void put_osd_con(struct ceph_connection *con)
 /*
  * authentication
  */
+
 /*
  * Note: returned pointer is the address of a structure that's
  * managed separately.  Caller must *not* attempt to free it.
@@ -5640,6 +5643,80 @@ static int invalidate_authorizer(struct ceph_connection *con)
 	return ceph_monc_validate_auth(&osdc->client->monc);
 }
 
+static int osd_get_auth_request(struct ceph_connection *con,
+				void *buf, int *buf_len,
+				void **authorizer, int *authorizer_len)
+{
+	struct ceph_osd *o = con->private;
+	struct ceph_auth_client *ac = o->o_osdc->client->monc.auth;
+	struct ceph_auth_handshake *auth = &o->o_auth;
+	int ret;
+
+	ret = ceph_auth_get_authorizer(ac, auth, CEPH_ENTITY_TYPE_OSD,
+				       buf, buf_len);
+	if (ret)
+		return ret;
+
+	*authorizer = auth->authorizer_buf;
+	*authorizer_len = auth->authorizer_buf_len;
+	return 0;
+}
+
+static int osd_handle_auth_reply_more(struct ceph_connection *con,
+				      void *reply, int reply_len,
+				      void *buf, int *buf_len,
+				      void **authorizer, int *authorizer_len)
+{
+	struct ceph_osd *o = con->private;
+	struct ceph_auth_client *ac = o->o_osdc->client->monc.auth;
+	struct ceph_auth_handshake *auth = &o->o_auth;
+	int ret;
+
+	ret = ceph_auth_handle_svc_reply_more(ac, auth, reply, reply_len,
+					      buf, buf_len);
+	if (ret)
+		return ret;
+
+	*authorizer = auth->authorizer_buf;
+	*authorizer_len = auth->authorizer_buf_len;
+	return 0;
+}
+
+static int osd_handle_auth_done(struct ceph_connection *con,
+				u64 global_id, void *reply, int reply_len,
+				u8 *session_key, int *session_key_len,
+				u8 *con_secret, int *con_secret_len)
+{
+	struct ceph_osd *o = con->private;
+	struct ceph_auth_client *ac = o->o_osdc->client->monc.auth;
+	struct ceph_auth_handshake *auth = &o->o_auth;
+
+	return ceph_auth_handle_svc_reply_done(ac, auth, reply, reply_len,
+					       session_key, session_key_len,
+					       con_secret, con_secret_len);
+}
+
+static int osd_handle_auth_bad_method(struct ceph_connection *con,
+				      int used_proto, int result,
+				      const int *allowed_protos, int proto_cnt,
+				      const int *allowed_modes, int mode_cnt)
+{
+	struct ceph_osd *o = con->private;
+	struct ceph_mon_client *monc = &o->o_osdc->client->monc;
+	int ret;
+
+	if (ceph_auth_handle_bad_authorizer(monc->auth, CEPH_ENTITY_TYPE_OSD,
+					    used_proto, result,
+					    allowed_protos, proto_cnt,
+					    allowed_modes, mode_cnt)) {
+		ret = ceph_monc_validate_auth(monc);
+		if (ret)
+			return ret;
+	}
+
+	return -EACCES;
+}
+
 static void osd_reencode_message(struct ceph_msg *msg)
 {
 	int type = le16_to_cpu(msg->hdr.type);
@@ -5677,4 +5754,8 @@ static const struct ceph_connection_operations osd_con_ops = {
 	.sign_message = osd_sign_message,
 	.check_message_signature = osd_check_message_signature,
 	.fault = osd_fault,
+	.get_auth_request = osd_get_auth_request,
+	.handle_auth_reply_more = osd_handle_auth_reply_more,
+	.handle_auth_done = osd_handle_auth_done,
+	.handle_auth_bad_method = osd_handle_auth_bad_method,
 };
-- 
cgit v1.2.3


From 2f0df6cfa325d7106b8a65bc0e02db1086e3f73b Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Thu, 19 Nov 2020 20:00:10 +0100
Subject: libceph: drop ceph_auth_{create,update}_authorizer()

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/auth.h |  6 ------
 net/ceph/auth.c           | 28 ----------------------------
 2 files changed, 34 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ceph/auth.h b/include/linux/ceph/auth.h
index 3fbe72ebd779..71b5d481c653 100644
--- a/include/linux/ceph/auth.h
+++ b/include/linux/ceph/auth.h
@@ -126,13 +126,7 @@ int __ceph_auth_get_authorizer(struct ceph_auth_client *ac,
 			       struct ceph_auth_handshake *auth,
 			       int peer_type, bool force_new,
 			       int *proto, int *pref_mode, int *fallb_mode);
-extern int ceph_auth_create_authorizer(struct ceph_auth_client *ac,
-				       int peer_type,
-				       struct ceph_auth_handshake *auth);
 void ceph_auth_destroy_authorizer(struct ceph_authorizer *a);
-extern int ceph_auth_update_authorizer(struct ceph_auth_client *ac,
-				       int peer_type,
-				       struct ceph_auth_handshake *a);
 int ceph_auth_add_authorizer_challenge(struct ceph_auth_client *ac,
 				       struct ceph_authorizer *a,
 				       void *challenge_buf,
diff --git a/net/ceph/auth.c b/net/ceph/auth.c
index 6b315c8212b1..eb261aa5fe18 100644
--- a/net/ceph/auth.c
+++ b/net/ceph/auth.c
@@ -326,40 +326,12 @@ out:
 }
 EXPORT_SYMBOL(__ceph_auth_get_authorizer);
 
-int ceph_auth_create_authorizer(struct ceph_auth_client *ac,
-				int peer_type,
-				struct ceph_auth_handshake *auth)
-{
-	int ret = 0;
-
-	mutex_lock(&ac->mutex);
-	if (ac->ops && ac->ops->create_authorizer)
-		ret = ac->ops->create_authorizer(ac, peer_type, auth);
-	mutex_unlock(&ac->mutex);
-	return ret;
-}
-EXPORT_SYMBOL(ceph_auth_create_authorizer);
-
 void ceph_auth_destroy_authorizer(struct ceph_authorizer *a)
 {
 	a->destroy(a);
 }
 EXPORT_SYMBOL(ceph_auth_destroy_authorizer);
 
-int ceph_auth_update_authorizer(struct ceph_auth_client *ac,
-				int peer_type,
-				struct ceph_auth_handshake *a)
-{
-	int ret = 0;
-
-	mutex_lock(&ac->mutex);
-	if (ac->ops && ac->ops->update_authorizer)
-		ret = ac->ops->update_authorizer(ac, peer_type, a);
-	mutex_unlock(&ac->mutex);
-	return ret;
-}
-EXPORT_SYMBOL(ceph_auth_update_authorizer);
-
 int ceph_auth_add_authorizer_challenge(struct ceph_auth_client *ac,
 				       struct ceph_authorizer *a,
 				       void *challenge_buf,
-- 
cgit v1.2.3


From 1b04fa9900263b4e217ca2509fd778b32c2b4eb2 Mon Sep 17 00:00:00 2001
From: "Uladzislau Rezki (Sony)" <urezki@gmail.com>
Date: Wed, 9 Dec 2020 21:27:31 +0100
Subject: rcu-tasks: Move RCU-tasks initialization to before early_initcall()

PowerPC testing encountered boot failures due to RCU Tasks not being
fully initialized until core_initcall() time.  This commit therefore
initializes RCU Tasks (along with Rude RCU and RCU Tasks Trace) just
before early_initcall() time, thus allowing waiting on RCU Tasks grace
periods from early_initcall() handlers.

Link: https://lore.kernel.org/rcu/87eekfh80a.fsf@dja-thinkpad.axtens.net/
Fixes: 36dadef23fcc ("kprobes: Init kprobes in early_initcall")
Tested-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/rcupdate.h |  6 ++++++
 init/main.c              |  1 +
 kernel/rcu/tasks.h       | 25 +++++++++++++++++++++----
 3 files changed, 28 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 6cdd0152c253..5c119d6cecf1 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -86,6 +86,12 @@ void rcu_sched_clock_irq(int user);
 void rcu_report_dead(unsigned int cpu);
 void rcutree_migrate_callbacks(int cpu);
 
+#ifdef CONFIG_TASKS_RCU_GENERIC
+void rcu_init_tasks_generic(void);
+#else
+static inline void rcu_init_tasks_generic(void) { }
+#endif
+
 #ifdef CONFIG_RCU_STALL_COMMON
 void rcu_sysrq_start(void);
 void rcu_sysrq_end(void);
diff --git a/init/main.c b/init/main.c
index 32b2a8affafd..9d964511fe0c 100644
--- a/init/main.c
+++ b/init/main.c
@@ -1512,6 +1512,7 @@ static noinline void __init kernel_init_freeable(void)
 
 	init_mm_internals();
 
+	rcu_init_tasks_generic();
 	do_pre_smp_initcalls();
 	lockup_detector_init();
 
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index d5d9f2d03e8a..73bbe792fe1e 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -241,7 +241,7 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 	}
 }
 
-/* Spawn RCU-tasks grace-period kthread, e.g., at core_initcall() time. */
+/* Spawn RCU-tasks grace-period kthread. */
 static void __init rcu_spawn_tasks_kthread_generic(struct rcu_tasks *rtp)
 {
 	struct task_struct *t;
@@ -569,7 +569,6 @@ static int __init rcu_spawn_tasks_kthread(void)
 	rcu_spawn_tasks_kthread_generic(&rcu_tasks);
 	return 0;
 }
-core_initcall(rcu_spawn_tasks_kthread);
 
 #ifndef CONFIG_TINY_RCU
 static void show_rcu_tasks_classic_gp_kthread(void)
@@ -697,7 +696,6 @@ static int __init rcu_spawn_tasks_rude_kthread(void)
 	rcu_spawn_tasks_kthread_generic(&rcu_tasks_rude);
 	return 0;
 }
-core_initcall(rcu_spawn_tasks_rude_kthread);
 
 #ifndef CONFIG_TINY_RCU
 static void show_rcu_tasks_rude_gp_kthread(void)
@@ -975,6 +973,11 @@ static void rcu_tasks_trace_pregp_step(void)
 static void rcu_tasks_trace_pertask(struct task_struct *t,
 				    struct list_head *hop)
 {
+	// During early boot when there is only the one boot CPU, there
+	// is no idle task for the other CPUs. Just return.
+	if (unlikely(t == NULL))
+		return;
+
 	WRITE_ONCE(t->trc_reader_special.b.need_qs, false);
 	WRITE_ONCE(t->trc_reader_checked, false);
 	t->trc_ipi_to_cpu = -1;
@@ -1200,7 +1203,6 @@ static int __init rcu_spawn_tasks_trace_kthread(void)
 	rcu_spawn_tasks_kthread_generic(&rcu_tasks_trace);
 	return 0;
 }
-core_initcall(rcu_spawn_tasks_trace_kthread);
 
 #ifndef CONFIG_TINY_RCU
 static void show_rcu_tasks_trace_gp_kthread(void)
@@ -1229,6 +1231,21 @@ void show_rcu_tasks_gp_kthreads(void)
 }
 #endif /* #ifndef CONFIG_TINY_RCU */
 
+void __init rcu_init_tasks_generic(void)
+{
+#ifdef CONFIG_TASKS_RCU
+	rcu_spawn_tasks_kthread();
+#endif
+
+#ifdef CONFIG_TASKS_RUDE_RCU
+	rcu_spawn_tasks_rude_kthread();
+#endif
+
+#ifdef CONFIG_TASKS_TRACE_RCU
+	rcu_spawn_tasks_trace_kthread();
+#endif
+}
+
 #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */
 static inline void rcu_tasks_bootup_oddness(void) {}
 void show_rcu_tasks_gp_kthreads(void) {}
-- 
cgit v1.2.3


From be98e05a67f05ff4c8349a51fcec993a28be718c Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Fri, 4 Dec 2020 21:02:42 +0100
Subject: dma-buf: Fix kerneldoc formatting

I wanted to look up something and noticed the hyperlink doesn't work.
While fixing that also noticed a trivial kerneldoc comment typo in the
same section, fix that too.

Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Reviewed-by: Simon Ser <contact@emersion.fr>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20201204200242.2671481-1-daniel.vetter@ffwll.ch
---
 Documentation/driver-api/dma-buf.rst | 2 +-
 include/linux/dma-buf-map.h          | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/driver-api/dma-buf.rst b/Documentation/driver-api/dma-buf.rst
index d6b2a195dbed..a2133d69872c 100644
--- a/Documentation/driver-api/dma-buf.rst
+++ b/Documentation/driver-api/dma-buf.rst
@@ -190,7 +190,7 @@ DMA Fence uABI/Sync File
 Indefinite DMA Fences
 ~~~~~~~~~~~~~~~~~~~~~
 
-At various times &dma_fence with an indefinite time until dma_fence_wait()
+At various times struct dma_fence with an indefinite time until dma_fence_wait()
 finishes have been proposed. Examples include:
 
 * Future fences, used in HWC1 to signal when a buffer isn't used by the display
diff --git a/include/linux/dma-buf-map.h b/include/linux/dma-buf-map.h
index 583a3a1f9447..278d489e4bdd 100644
--- a/include/linux/dma-buf-map.h
+++ b/include/linux/dma-buf-map.h
@@ -122,7 +122,7 @@ struct dma_buf_map {
 
 /**
  * DMA_BUF_MAP_INIT_VADDR - Initializes struct dma_buf_map to an address in system memory
- * @vaddr:	A system-memory address
+ * @vaddr_:	A system-memory address
  */
 #define DMA_BUF_MAP_INIT_VADDR(vaddr_) \
 	{ \
-- 
cgit v1.2.3


From a313357e704f2617f298333e3e617a38b1719760 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 10 Dec 2020 20:25:37 +0100
Subject: genirq: Move irq_has_action() into core code

This function uses irq_to_desc() and is going to be used by modules to
replace the open coded irq_to_desc() (ab)usage. The final goal is to remove
the export of irq_to_desc() so driver cannot fiddle with it anymore.

Move it into the core code and fixup the usage sites to include the proper
header.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20201210194042.548936472@linutronix.de
---
 arch/alpha/kernel/sys_jensen.c |  2 +-
 arch/x86/kernel/topology.c     |  1 +
 include/linux/interrupt.h      |  1 +
 include/linux/irqdesc.h        |  7 +------
 kernel/irq/manage.c            | 17 +++++++++++++++++
 5 files changed, 21 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/arch/alpha/kernel/sys_jensen.c b/arch/alpha/kernel/sys_jensen.c
index 0a2ab6cb18db..e5d870ff225f 100644
--- a/arch/alpha/kernel/sys_jensen.c
+++ b/arch/alpha/kernel/sys_jensen.c
@@ -7,7 +7,7 @@
  *
  * Code supporting the Jensen.
  */
-
+#include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/mm.h>
diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c
index 0a2ec801b63f..f5477eab5692 100644
--- a/arch/x86/kernel/topology.c
+++ b/arch/x86/kernel/topology.c
@@ -25,6 +25,7 @@
  *
  * Send feedback to <colpatch@us.ibm.com>
  */
+#include <linux/interrupt.h>
 #include <linux/nodemask.h>
 #include <linux/export.h>
 #include <linux/mmzone.h>
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 870b3251e174..bb8ff9083e7d 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -232,6 +232,7 @@ extern void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id);
 # define local_irq_enable_in_hardirq()	local_irq_enable()
 #endif
 
+bool irq_has_action(unsigned int irq);
 extern void disable_irq_nosync(unsigned int irq);
 extern bool disable_hardirq(unsigned int irq);
 extern void disable_irq(unsigned int irq);
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index 5745491303e0..385a4fafe631 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -179,12 +179,7 @@ int handle_domain_nmi(struct irq_domain *domain, unsigned int hwirq,
 /* Test to see if a driver has successfully requested an irq */
 static inline int irq_desc_has_action(struct irq_desc *desc)
 {
-	return desc->action != NULL;
-}
-
-static inline int irq_has_action(unsigned int irq)
-{
-	return irq_desc_has_action(irq_to_desc(irq));
+	return desc && desc->action != NULL;
 }
 
 /**
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index c826ba4141fe..a5a1cde5c1a2 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -2822,3 +2822,20 @@ out_unlock:
 	return err;
 }
 EXPORT_SYMBOL_GPL(irq_set_irqchip_state);
+
+/**
+ * irq_has_action - Check whether an interrupt is requested
+ * @irq:	The linux irq number
+ *
+ * Returns: A snapshot of the current state
+ */
+bool irq_has_action(unsigned int irq)
+{
+	bool res;
+
+	rcu_read_lock();
+	res = irq_desc_has_action(irq_to_desc(irq));
+	rcu_read_unlock();
+	return res;
+}
+EXPORT_SYMBOL_GPL(irq_has_action);
-- 
cgit v1.2.3


From fdd029630434b434b127efc7fba337da28f45658 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 10 Dec 2020 20:25:38 +0100
Subject: genirq: Move status flag checks to core

These checks are used by modules and prevent the removal of the export of
irq_to_desc(). Move the accessor into the core.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20201210194042.703779349@linutronix.de
---
 include/linux/irqdesc.h | 17 +++++------------
 kernel/irq/manage.c     | 20 ++++++++++++++++++++
 2 files changed, 25 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index 385a4fafe631..308d7db8991f 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -223,28 +223,21 @@ irq_set_chip_handler_name_locked(struct irq_data *data, struct irq_chip *chip,
 	data->chip = chip;
 }
 
+bool irq_check_status_bit(unsigned int irq, unsigned int bitmask);
+
 static inline bool irq_balancing_disabled(unsigned int irq)
 {
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-	return desc->status_use_accessors & IRQ_NO_BALANCING_MASK;
+	return irq_check_status_bit(irq, IRQ_NO_BALANCING_MASK);
 }
 
 static inline bool irq_is_percpu(unsigned int irq)
 {
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-	return desc->status_use_accessors & IRQ_PER_CPU;
+	return irq_check_status_bit(irq, IRQ_PER_CPU);
 }
 
 static inline bool irq_is_percpu_devid(unsigned int irq)
 {
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-	return desc->status_use_accessors & IRQ_PER_CPU_DEVID;
+	return irq_check_status_bit(irq, IRQ_PER_CPU_DEVID);
 }
 
 static inline void
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index a5a1cde5c1a2..ab8567f32501 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -2839,3 +2839,23 @@ bool irq_has_action(unsigned int irq)
 	return res;
 }
 EXPORT_SYMBOL_GPL(irq_has_action);
+
+/**
+ * irq_check_status_bit - Check whether bits in the irq descriptor status are set
+ * @irq:	The linux irq number
+ * @bitmask:	The bitmask to evaluate
+ *
+ * Returns: True if one of the bits in @bitmask is set
+ */
+bool irq_check_status_bit(unsigned int irq, unsigned int bitmask)
+{
+	struct irq_desc *desc;
+	bool res = false;
+
+	rcu_read_lock();
+	desc = irq_to_desc(irq);
+	if (desc)
+		res = !!(desc->status_use_accessors & bitmask);
+	rcu_read_unlock();
+	return res;
+}
-- 
cgit v1.2.3


From f1c6306c0d6b50844ba02c8a53e35405e9c0db05 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 10 Dec 2020 20:25:39 +0100
Subject: genirq: Move irq_set_lockdep_class() to core

irq_set_lockdep_class() is used from modules and requires irq_to_desc() to
be exported. Move it into the core code which lifts another requirement for
the export.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20201210194042.860029489@linutronix.de
---
 include/linux/irqdesc.h | 10 ++++------
 kernel/irq/irqdesc.c    | 14 ++++++++++++++
 2 files changed, 18 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index 308d7db8991f..4a1d016716f4 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -240,16 +240,14 @@ static inline bool irq_is_percpu_devid(unsigned int irq)
 	return irq_check_status_bit(irq, IRQ_PER_CPU_DEVID);
 }
 
+void __irq_set_lockdep_class(unsigned int irq, struct lock_class_key *lock_class,
+			     struct lock_class_key *request_class);
 static inline void
 irq_set_lockdep_class(unsigned int irq, struct lock_class_key *lock_class,
 		      struct lock_class_key *request_class)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-
-	if (desc) {
-		lockdep_set_class(&desc->lock, lock_class);
-		lockdep_set_class(&desc->request_mutex, request_class);
-	}
+	if (IS_ENABLED(CONFIG_LOCKDEP))
+		__irq_set_lockdep_class(irq, lock_class, request_class);
 }
 
 #endif
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index e810eb9906ea..20a54fa7cd30 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -968,3 +968,17 @@ unsigned int kstat_irqs_usr(unsigned int irq)
 	rcu_read_unlock();
 	return sum;
 }
+
+#ifdef CONFIG_LOCKDEP
+void __irq_set_lockdep_class(unsigned int irq, struct lock_class_key *lock_class,
+			     struct lock_class_key *request_class)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	if (desc) {
+		lockdep_set_class(&desc->lock, lock_class);
+		lockdep_set_class(&desc->request_mutex, request_class);
+	}
+}
+EXPORT_SYMBOL_GPL(__irq_set_lockdep_class);
+#endif
-- 
cgit v1.2.3


From 3e2380123fb96987ce958f623207010c667ffa7c Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 10 Dec 2020 20:25:40 +0100
Subject: genirq: Provide irq_get_effective_affinity()

Provide an accessor to the effective interrupt affinity mask. Going to be
used to replace open coded fiddling with the irq descriptor.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20201210194042.967177918@linutronix.de
---
 include/linux/irq.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index c332871d59da..4aeb1c4c7e07 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -906,6 +906,13 @@ struct cpumask *irq_data_get_effective_affinity_mask(struct irq_data *d)
 }
 #endif
 
+static inline struct cpumask *irq_get_effective_affinity_mask(unsigned int irq)
+{
+	struct irq_data *d = irq_get_irq_data(irq);
+
+	return d ? irq_data_get_effective_affinity_mask(d) : NULL;
+}
+
 unsigned int arch_dynirq_lower_bound(unsigned int from);
 
 int __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
-- 
cgit v1.2.3


From 26c19d0a8610fb233b31730fe26a31145f2d9796 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 10 Dec 2020 20:25:43 +0100
Subject: genirq: Make kstat_irqs() static

No more users outside the core code.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20201210194043.268774449@linutronix.de
---
 include/linux/kernel_stat.h |  1 -
 kernel/irq/irqdesc.c        | 19 ++++++-------------
 2 files changed, 6 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index 89f0745c096d..44ae1a7eb9e3 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -67,7 +67,6 @@ static inline unsigned int kstat_softirqs_cpu(unsigned int irq, int cpu)
 /*
  * Number of interrupts per specific IRQ source, since bootup
  */
-extern unsigned int kstat_irqs(unsigned int irq);
 extern unsigned int kstat_irqs_usr(unsigned int irq);
 
 /*
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 02b446a21ce6..2eb076f4a566 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -924,15 +924,7 @@ static bool irq_is_nmi(struct irq_desc *desc)
 	return desc->istate & IRQS_NMI;
 }
 
-/**
- * kstat_irqs - Get the statistics for an interrupt
- * @irq:	The interrupt number
- *
- * Returns the sum of interrupt counts on all cpus since boot for
- * @irq. The caller must ensure that the interrupt is not removed
- * concurrently.
- */
-unsigned int kstat_irqs(unsigned int irq)
+static unsigned int kstat_irqs(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned int sum = 0;
@@ -951,13 +943,14 @@ unsigned int kstat_irqs(unsigned int irq)
 }
 
 /**
- * kstat_irqs_usr - Get the statistics for an interrupt
+ * kstat_irqs_usr - Get the statistics for an interrupt from thread context
  * @irq:	The interrupt number
  *
  * Returns the sum of interrupt counts on all cpus since boot for @irq.
- * Contrary to kstat_irqs() this can be called from any context.
- * It uses rcu since a concurrent removal of an interrupt descriptor is
- * observing an rcu grace period before delayed_free_desc()/irq_kobj_release().
+ *
+ * It uses rcu to protect the access since a concurrent removal of an
+ * interrupt descriptor is observing an rcu grace period before
+ * delayed_free_desc()/irq_kobj_release().
  */
 unsigned int kstat_irqs_usr(unsigned int irq)
 {
-- 
cgit v1.2.3


From 501e2db67fa4264b517de5c7934e94cca89b3a1e Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 10 Dec 2020 20:25:44 +0100
Subject: genirq: Provide kstat_irqdesc_cpu()

Most users of kstat_irqs_cpu() have the irq descriptor already. No point in
calling into the core code and looking it up once more.

Use it in per_cpu_count_show() to start with.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20201210194043.362094758@linutronix.de
---
 include/linux/irqdesc.h | 6 ++++++
 kernel/irq/irqdesc.c    | 4 ++--
 2 files changed, 8 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index 4a1d016716f4..891b323266df 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -113,6 +113,12 @@ static inline void irq_unlock_sparse(void) { }
 extern struct irq_desc irq_desc[NR_IRQS];
 #endif
 
+static inline unsigned int irq_desc_kstat_cpu(struct irq_desc *desc,
+					      unsigned int cpu)
+{
+	return desc->kstat_irqs ? *per_cpu_ptr(desc->kstat_irqs, cpu) : 0;
+}
+
 static inline struct irq_desc *irq_data_to_desc(struct irq_data *data)
 {
 	return container_of(data->common, struct irq_desc, irq_common_data);
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 2eb076f4a566..f509c4db2029 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -147,12 +147,12 @@ static ssize_t per_cpu_count_show(struct kobject *kobj,
 				  struct kobj_attribute *attr, char *buf)
 {
 	struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj);
-	int cpu, irq = desc->irq_data.irq;
 	ssize_t ret = 0;
 	char *p = "";
+	int cpu;
 
 	for_each_possible_cpu(cpu) {
-		unsigned int c = kstat_irqs_cpu(irq, cpu);
+		unsigned int c = irq_desc_kstat_cpu(desc, cpu);
 
 		ret += scnprintf(buf + ret, PAGE_SIZE - ret, "%s%u", p, c);
 		p = ",";
-- 
cgit v1.2.3


From ee2cc4276ba4909438f5894a218877660e1536d9 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Mon, 14 Dec 2020 21:08:00 +0100
Subject: cpufreq: Add special-purpose fast-switching callback for drivers

First off, some cpufreq drivers (eg. intel_pstate) can pass hints
beyond the current target frequency to the hardware and there are no
provisions for doing that in the cpufreq framework.  In particular,
today the driver has to assume that it should not allow the frequency
to fall below the one requested by the governor (or the required
capacity may not be provided) which may not be the case and which may
lead to excessive energy usage in some scenarios.

Second, the hints passed by these drivers to the hardware need not be
in terms of the frequency, so representing the utilization numbers
coming from the scheduler as frequency before passing them to those
drivers is not really useful.

Address the two points above by adding a special-purpose replacement
for the ->fast_switch callback, called ->adjust_perf, allowing the
governor to pass abstract performance level (rather than frequency)
values for the minimum (required) and target (desired) performance
along with the CPU capacity to compare them to.

Also update the schedutil governor to use the new callback instead
of ->fast_switch if present and if the utilization mertics are
frequency-invariant (that is requisite for the direct mapping
between the utilization and the CPU performance levels to be a
reasonable approximation).

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
---
 drivers/cpufreq/cpufreq.c        | 40 +++++++++++++++++++++++
 include/linux/cpufreq.h          | 14 +++++++++
 include/linux/sched/cpufreq.h    |  5 +++
 kernel/sched/cpufreq_schedutil.c | 68 ++++++++++++++++++++++++++++++++++------
 4 files changed, 117 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index c17aa2973c44..d0a3525ce27f 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -2097,6 +2097,46 @@ unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy,
 }
 EXPORT_SYMBOL_GPL(cpufreq_driver_fast_switch);
 
+/**
+ * cpufreq_driver_adjust_perf - Adjust CPU performance level in one go.
+ * @cpu: Target CPU.
+ * @min_perf: Minimum (required) performance level (units of @capacity).
+ * @target_perf: Terget (desired) performance level (units of @capacity).
+ * @capacity: Capacity of the target CPU.
+ *
+ * Carry out a fast performance level switch of @cpu without sleeping.
+ *
+ * The driver's ->adjust_perf() callback invoked by this function must be
+ * suitable for being called from within RCU-sched read-side critical sections
+ * and it is expected to select a suitable performance level equal to or above
+ * @min_perf and preferably equal to or below @target_perf.
+ *
+ * This function must not be called if policy->fast_switch_enabled is unset.
+ *
+ * Governors calling this function must guarantee that it will never be invoked
+ * twice in parallel for the same CPU and that it will never be called in
+ * parallel with either ->target() or ->target_index() or ->fast_switch() for
+ * the same CPU.
+ */
+void cpufreq_driver_adjust_perf(unsigned int cpu,
+				 unsigned long min_perf,
+				 unsigned long target_perf,
+				 unsigned long capacity)
+{
+	cpufreq_driver->adjust_perf(cpu, min_perf, target_perf, capacity);
+}
+
+/**
+ * cpufreq_driver_has_adjust_perf - Check "direct fast switch" callback.
+ *
+ * Return 'true' if the ->adjust_perf callback is present for the
+ * current driver or 'false' otherwise.
+ */
+bool cpufreq_driver_has_adjust_perf(void)
+{
+	return !!cpufreq_driver->adjust_perf;
+}
+
 /* Must set freqs->new to intermediate frequency */
 static int __target_intermediate(struct cpufreq_policy *policy,
 				 struct cpufreq_freqs *freqs, int index)
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 584fccd4fcab..9c8b7437b6cd 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -320,6 +320,15 @@ struct cpufreq_driver {
 					unsigned int index);
 	unsigned int	(*fast_switch)(struct cpufreq_policy *policy,
 				       unsigned int target_freq);
+	/*
+	 * ->fast_switch() replacement for drivers that use an internal
+	 * representation of performance levels and can pass hints other than
+	 * the target performance level to the hardware.
+	 */
+	void		(*adjust_perf)(unsigned int cpu,
+				       unsigned long min_perf,
+				       unsigned long target_perf,
+				       unsigned long capacity);
 
 	/*
 	 * Caches and returns the lowest driver-supported frequency greater than
@@ -588,6 +597,11 @@ struct cpufreq_governor {
 /* Pass a target to the cpufreq driver */
 unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy,
 					unsigned int target_freq);
+void cpufreq_driver_adjust_perf(unsigned int cpu,
+				unsigned long min_perf,
+				unsigned long target_perf,
+				unsigned long capacity);
+bool cpufreq_driver_has_adjust_perf(void);
 int cpufreq_driver_target(struct cpufreq_policy *policy,
 				 unsigned int target_freq,
 				 unsigned int relation);
diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h
index 3ed5aa18593f..6205578ab6ee 100644
--- a/include/linux/sched/cpufreq.h
+++ b/include/linux/sched/cpufreq.h
@@ -28,6 +28,11 @@ static inline unsigned long map_util_freq(unsigned long util,
 {
 	return (freq + (freq >> 2)) * util / cap;
 }
+
+static inline unsigned long map_util_perf(unsigned long util)
+{
+	return util + (util >> 2);
+}
 #endif /* CONFIG_CPU_FREQ */
 
 #endif /* _LINUX_SCHED_CPUFREQ_H */
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 319a270d13c1..803bcb30db27 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -432,13 +432,10 @@ static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu, struct sugov_p
 		sg_policy->limits_changed = true;
 }
 
-static void sugov_update_single(struct update_util_data *hook, u64 time,
-				unsigned int flags)
+static inline bool sugov_update_single_common(struct sugov_cpu *sg_cpu,
+					      u64 time, unsigned int flags)
 {
-	struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util);
 	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
-	unsigned int cached_freq = sg_policy->cached_raw_freq;
-	unsigned int next_f;
 
 	sugov_iowait_boost(sg_cpu, time, flags);
 	sg_cpu->last_update = time;
@@ -446,11 +443,25 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
 	ignore_dl_rate_limit(sg_cpu, sg_policy);
 
 	if (!sugov_should_update_freq(sg_policy, time))
-		return;
+		return false;
 
 	sugov_get_util(sg_cpu);
 	sugov_iowait_apply(sg_cpu, time);
 
+	return true;
+}
+
+static void sugov_update_single_freq(struct update_util_data *hook, u64 time,
+				     unsigned int flags)
+{
+	struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util);
+	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
+	unsigned int cached_freq = sg_policy->cached_raw_freq;
+	unsigned int next_f;
+
+	if (!sugov_update_single_common(sg_cpu, time, flags))
+		return;
+
 	next_f = get_next_freq(sg_policy, sg_cpu->util, sg_cpu->max);
 	/*
 	 * Do not reduce the frequency if the CPU has not been idle
@@ -477,6 +488,38 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
 	}
 }
 
+static void sugov_update_single_perf(struct update_util_data *hook, u64 time,
+				     unsigned int flags)
+{
+	struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util);
+	unsigned long prev_util = sg_cpu->util;
+
+	/*
+	 * Fall back to the "frequency" path if frequency invariance is not
+	 * supported, because the direct mapping between the utilization and
+	 * the performance levels depends on the frequency invariance.
+	 */
+	if (!arch_scale_freq_invariant()) {
+		sugov_update_single_freq(hook, time, flags);
+		return;
+	}
+
+	if (!sugov_update_single_common(sg_cpu, time, flags))
+		return;
+
+	/*
+	 * Do not reduce the target performance level if the CPU has not been
+	 * idle recently, as the reduction is likely to be premature then.
+	 */
+	if (sugov_cpu_is_busy(sg_cpu) && sg_cpu->util < prev_util)
+		sg_cpu->util = prev_util;
+
+	cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl),
+				   map_util_perf(sg_cpu->util), sg_cpu->max);
+
+	sg_cpu->sg_policy->last_freq_update_time = time;
+}
+
 static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
 {
 	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
@@ -815,6 +858,7 @@ static void sugov_exit(struct cpufreq_policy *policy)
 static int sugov_start(struct cpufreq_policy *policy)
 {
 	struct sugov_policy *sg_policy = policy->governor_data;
+	void (*uu)(struct update_util_data *data, u64 time, unsigned int flags);
 	unsigned int cpu;
 
 	sg_policy->freq_update_delay_ns	= sg_policy->tunables->rate_limit_us * NSEC_PER_USEC;
@@ -834,13 +878,17 @@ static int sugov_start(struct cpufreq_policy *policy)
 		sg_cpu->sg_policy		= sg_policy;
 	}
 
+	if (policy_is_shared(policy))
+		uu = sugov_update_shared;
+	else if (policy->fast_switch_enabled && cpufreq_driver_has_adjust_perf())
+		uu = sugov_update_single_perf;
+	else
+		uu = sugov_update_single_freq;
+
 	for_each_cpu(cpu, policy->cpus) {
 		struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu);
 
-		cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util,
-					     policy_is_shared(policy) ?
-							sugov_update_shared :
-							sugov_update_single);
+		cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util, uu);
 	}
 	return 0;
 }
-- 
cgit v1.2.3


From f0dbd2bd1c22c6670e83ddcd46a9beb8b575e86d Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Mon, 14 Dec 2020 19:03:55 -0800
Subject: mm: slab: provide krealloc_array()

When allocating an array of elements, users should check for
multiplication overflow or preferably use one of the provided helpers
like: kmalloc_array().

There's no krealloc_array() counterpart but there are many users who use
regular krealloc() to reallocate arrays.  Let's provide an actual
krealloc_array() implementation.

While at it: add some documentation regarding krealloc.

Link: https://lkml.kernel.org/r/20201109110654.12547-3-brgl@bgdev.pl
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Borislav Petkov <bp@suse.de>
Cc: Christian Knig <christian.koenig@amd.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: David Airlie <airlied@linux.ie>
Cc: David Rientjes <rientjes@google.com>
Cc: Gustavo Padovan <gustavo@padovan.org>
Cc: James Morse <james.morse@arm.com>
Cc: Jaroslav Kysela <perex@perex.cz>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Linus Walleij <linus.walleij@linaro.org>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Mauro Carvalho Chehab <mchehab@kernel.org>
Cc: Maxime Ripard <mripard@kernel.org>
Cc: "Michael S . Tsirkin" <mst@redhat.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Robert Richter <rric@kernel.org>
Cc: Sumit Semwal <sumit.semwal@linaro.org>
Cc: Takashi Iwai <tiwai@suse.com>
Cc: Takashi Iwai <tiwai@suse.de>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/core-api/memory-allocation.rst |  4 ++++
 include/linux/slab.h                         | 18 ++++++++++++++++++
 2 files changed, 22 insertions(+)

(limited to 'include/linux')

diff --git a/Documentation/core-api/memory-allocation.rst b/Documentation/core-api/memory-allocation.rst
index 4446a1ac36cc..5954ddf6ee13 100644
--- a/Documentation/core-api/memory-allocation.rst
+++ b/Documentation/core-api/memory-allocation.rst
@@ -147,6 +147,10 @@ The address of a chunk allocated with `kmalloc` is aligned to at least
 ARCH_KMALLOC_MINALIGN bytes.  For sizes which are a power of two, the
 alignment is also guaranteed to be at least the respective size.
 
+Chunks allocated with kmalloc() can be resized with krealloc(). Similarly
+to kmalloc_array(): a helper for resizing arrays is provided in the form of
+krealloc_array().
+
 For large allocations you can use vmalloc() and vzalloc(), or directly
 request pages from the page allocator. The memory allocated by `vmalloc`
 and related functions is not physically contiguous.
diff --git a/include/linux/slab.h b/include/linux/slab.h
index dd6897f62010..be4ba5867ac5 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -592,6 +592,24 @@ static inline void *kmalloc_array(size_t n, size_t size, gfp_t flags)
 	return __kmalloc(bytes, flags);
 }
 
+/**
+ * krealloc_array - reallocate memory for an array.
+ * @p: pointer to the memory chunk to reallocate
+ * @new_n: new number of elements to alloc
+ * @new_size: new size of a single member of the array
+ * @flags: the type of memory to allocate (see kmalloc)
+ */
+static __must_check inline void *
+krealloc_array(void *p, size_t new_n, size_t new_size, gfp_t flags)
+{
+	size_t bytes;
+
+	if (unlikely(check_mul_overflow(new_n, new_size, &bytes)))
+		return NULL;
+
+	return krealloc(p, bytes, flags);
+}
+
 /**
  * kcalloc - allocate memory for an array. The memory is set to zero.
  * @n: number of elements.
-- 
cgit v1.2.3


From 7fb7ab6d618a4dc7ea3f3eafc92388a35b4f8894 Mon Sep 17 00:00:00 2001
From: Zhenhua Huang <zhenhuah@codeaurora.org>
Date: Mon, 14 Dec 2020 19:04:46 -0800
Subject: mm: fix page_owner initializing issue for arm32

Page owner of pages used by page owner itself used is missing on arm32
targets.  The reason is dummy_handle and failure_handle is not initialized
correctly.  Buddy allocator is used to initialize these two handles.
However, buddy allocator is not ready when page owner calls it.  This
change fixed that by initializing page owner after buddy initialization.

The working flow before and after this change are:
original logic:
 1. allocated memory for page_ext(using memblock).
 2. invoke the init callback of page_ext_ops like page_owner(using buddy
    allocator).
 3. initialize buddy.

after this change:
 1. allocated memory for page_ext(using memblock).
 2. initialize buddy.
 3. invoke the init callback of page_ext_ops like page_owner(using buddy
    allocator).

with the change, failure/dummy_handle can get its correct value and page
owner output for example has the one for page owner itself:

  Page allocated via order 2, mask 0x6202c0(GFP_USER|__GFP_NOWARN), pid 1006, ts 67278156558 ns
  PFN 543776 type Unmovable Block 531 type Unmovable Flags 0x0()
    init_page_owner+0x28/0x2f8
    invoke_init_callbacks_flatmem+0x24/0x34
    start_kernel+0x33c/0x5d8

Link: https://lkml.kernel.org/r/1603104925-5888-1-git-send-email-zhenhuah@codeaurora.org
Signed-off-by: Zhenhua Huang <zhenhuah@codeaurora.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/page_ext.h |  8 ++++++++
 init/main.c              |  2 ++
 mm/page_ext.c            | 10 ++++++++--
 3 files changed, 18 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h
index cfce186f0c4e..aff81ba31bd8 100644
--- a/include/linux/page_ext.h
+++ b/include/linux/page_ext.h
@@ -44,8 +44,12 @@ static inline void page_ext_init_flatmem(void)
 {
 }
 extern void page_ext_init(void);
+static inline void page_ext_init_flatmem_late(void)
+{
+}
 #else
 extern void page_ext_init_flatmem(void);
+extern void page_ext_init_flatmem_late(void);
 static inline void page_ext_init(void)
 {
 }
@@ -76,6 +80,10 @@ static inline void page_ext_init(void)
 {
 }
 
+static inline void page_ext_init_flatmem_late(void)
+{
+}
+
 static inline void page_ext_init_flatmem(void)
 {
 }
diff --git a/init/main.c b/init/main.c
index 32b2a8affafd..82ae0d1345a0 100644
--- a/init/main.c
+++ b/init/main.c
@@ -828,6 +828,8 @@ static void __init mm_init(void)
 	init_debug_pagealloc();
 	report_meminit();
 	mem_init();
+	/* page_owner must be initialized after buddy is ready */
+	page_ext_init_flatmem_late();
 	kmem_cache_init();
 	kmemleak_init();
 	pgtable_init();
diff --git a/mm/page_ext.c b/mm/page_ext.c
index a3616f7a0e9e..16b161f28a31 100644
--- a/mm/page_ext.c
+++ b/mm/page_ext.c
@@ -99,12 +99,19 @@ static void __init invoke_init_callbacks(void)
 	}
 }
 
+#ifndef CONFIG_SPARSEMEM
+void __init page_ext_init_flatmem_late(void)
+{
+	invoke_init_callbacks();
+}
+#endif
+
 static inline struct page_ext *get_entry(void *base, unsigned long index)
 {
 	return base + page_ext_size * index;
 }
 
-#if !defined(CONFIG_SPARSEMEM)
+#ifndef CONFIG_SPARSEMEM
 
 
 void __meminit pgdat_page_ext_init(struct pglist_data *pgdat)
@@ -177,7 +184,6 @@ void __init page_ext_init_flatmem(void)
 			goto fail;
 	}
 	pr_info("allocated %ld bytes of page_ext\n", total_usage);
-	invoke_init_callbacks();
 	return;
 
 fail:
-- 
cgit v1.2.3


From 57efa1fe5957694fa541c9062de0a127f0b9acb0 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Mon, 14 Dec 2020 19:05:44 -0800
Subject: mm/gup: prevent gup_fast from racing with COW during fork

Since commit 70e806e4e645 ("mm: Do early cow for pinned pages during
fork() for ptes") pages under a FOLL_PIN will not be write protected
during COW for fork.  This means that pages returned from
pin_user_pages(FOLL_WRITE) should not become write protected while the pin
is active.

However, there is a small race where get_user_pages_fast(FOLL_PIN) can
establish a FOLL_PIN at the same time copy_present_page() is write
protecting it:

        CPU 0                             CPU 1
   get_user_pages_fast()
    internal_get_user_pages_fast()
                                       copy_page_range()
                                         pte_alloc_map_lock()
                                           copy_present_page()
                                             atomic_read(has_pinned) == 0
					     page_maybe_dma_pinned() == false
     atomic_set(has_pinned, 1);
     gup_pgd_range()
      gup_pte_range()
       pte_t pte = gup_get_pte(ptep)
       pte_access_permitted(pte)
       try_grab_compound_head()
                                             pte = pte_wrprotect(pte)
	                                     set_pte_at();
                                         pte_unmap_unlock()
      // GUP now returns with a write protected page

The first attempt to resolve this by using the write protect caused
problems (and was missing a barrrier), see commit f3c64eda3e50 ("mm: avoid
early COW write protect games during fork()")

Instead wrap copy_p4d_range() with the write side of a seqcount and check
the read side around gup_pgd_range().  If there is a collision then
get_user_pages_fast() fails and falls back to slow GUP.

Slow GUP is safe against this race because copy_page_range() is only
called while holding the exclusive side of the mmap_lock on the src
mm_struct.

[akpm@linux-foundation.org: coding style fixes]
  Link: https://lore.kernel.org/r/CAHk-=wi=iCnYCARbPGjkVJu9eyYeZ13N64tZYLdOB8CP5Q_PLw@mail.gmail.com

Link: https://lkml.kernel.org/r/2-v4-908497cf359a+4782-gup_fork_jgg@nvidia.com
Fixes: f3c64eda3e50 ("mm: avoid early COW write protect games during fork()")
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Peter Xu <peterx@redhat.com>
Acked-by: "Ahmed S. Darwish" <a.darwish@linutronix.de>	[seqcount_t parts]
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Kirill Shutemov <kirill@shutemov.name>
Cc: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: Leon Romanovsky <leonro@nvidia.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/kernel/tboot.c    |  1 +
 drivers/firmware/efi/efi.c |  1 +
 include/linux/mm_types.h   |  8 ++++++++
 kernel/fork.c              |  1 +
 mm/gup.c                   | 18 ++++++++++++++++++
 mm/init-mm.c               |  1 +
 mm/memory.c                | 13 ++++++++++++-
 7 files changed, 42 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index ae64f98ec2ab..4c09ba110204 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -93,6 +93,7 @@ static struct mm_struct tboot_mm = {
 	.pgd            = swapper_pg_dir,
 	.mm_users       = ATOMIC_INIT(2),
 	.mm_count       = ATOMIC_INIT(1),
+	.write_protect_seq = SEQCNT_ZERO(tboot_mm.write_protect_seq),
 	MMAP_LOCK_INITIALIZER(init_mm)
 	.page_table_lock =  __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock),
 	.mmlist         = LIST_HEAD_INIT(init_mm.mmlist),
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 6c6eec044a97..df3f9bcab581 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -57,6 +57,7 @@ struct mm_struct efi_mm = {
 	.mm_rb			= RB_ROOT,
 	.mm_users		= ATOMIC_INIT(2),
 	.mm_count		= ATOMIC_INIT(1),
+	.write_protect_seq      = SEQCNT_ZERO(efi_mm.write_protect_seq),
 	MMAP_LOCK_INITIALIZER(efi_mm)
 	.page_table_lock	= __SPIN_LOCK_UNLOCKED(efi_mm.page_table_lock),
 	.mmlist			= LIST_HEAD_INIT(efi_mm.mmlist),
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 5a9238f6caad..915f4f100383 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -14,6 +14,7 @@
 #include <linux/uprobes.h>
 #include <linux/page-flags-layout.h>
 #include <linux/workqueue.h>
+#include <linux/seqlock.h>
 
 #include <asm/mmu.h>
 
@@ -446,6 +447,13 @@ struct mm_struct {
 		 */
 		atomic_t has_pinned;
 
+		/**
+		 * @write_protect_seq: Locked when any thread is write
+		 * protecting pages mapped by this mm to enforce a later COW,
+		 * for instance during page table copying for fork().
+		 */
+		seqcount_t write_protect_seq;
+
 #ifdef CONFIG_MMU
 		atomic_long_t pgtables_bytes;	/* PTE page table pages */
 #endif
diff --git a/kernel/fork.c b/kernel/fork.c
index 6d266388d380..dc55f68a6ee3 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1007,6 +1007,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 	mm->vmacache_seqnum = 0;
 	atomic_set(&mm->mm_users, 1);
 	atomic_set(&mm->mm_count, 1);
+	seqcount_init(&mm->write_protect_seq);
 	mmap_init_lock(mm);
 	INIT_LIST_HEAD(&mm->mmlist);
 	mm->core_state = NULL;
diff --git a/mm/gup.c b/mm/gup.c
index c7e24301860a..9c6a2f5001c5 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2684,11 +2684,18 @@ static unsigned long lockless_pages_from_mm(unsigned long start,
 {
 	unsigned long flags;
 	int nr_pinned = 0;
+	unsigned seq;
 
 	if (!IS_ENABLED(CONFIG_HAVE_FAST_GUP) ||
 	    !gup_fast_permitted(start, end))
 		return 0;
 
+	if (gup_flags & FOLL_PIN) {
+		seq = raw_read_seqcount(&current->mm->write_protect_seq);
+		if (seq & 1)
+			return 0;
+	}
+
 	/*
 	 * Disable interrupts. The nested form is used, in order to allow full,
 	 * general purpose use of this routine.
@@ -2703,6 +2710,17 @@ static unsigned long lockless_pages_from_mm(unsigned long start,
 	local_irq_save(flags);
 	gup_pgd_range(start, end, gup_flags, pages, &nr_pinned);
 	local_irq_restore(flags);
+
+	/*
+	 * When pinning pages for DMA there could be a concurrent write protect
+	 * from fork() via copy_page_range(), in this case always fail fast GUP.
+	 */
+	if (gup_flags & FOLL_PIN) {
+		if (read_seqcount_retry(&current->mm->write_protect_seq, seq)) {
+			unpin_user_pages(pages, nr_pinned);
+			return 0;
+		}
+	}
 	return nr_pinned;
 }
 
diff --git a/mm/init-mm.c b/mm/init-mm.c
index 3a613c85f9ed..153162669f80 100644
--- a/mm/init-mm.c
+++ b/mm/init-mm.c
@@ -31,6 +31,7 @@ struct mm_struct init_mm = {
 	.pgd		= swapper_pg_dir,
 	.mm_users	= ATOMIC_INIT(2),
 	.mm_count	= ATOMIC_INIT(1),
+	.write_protect_seq = SEQCNT_ZERO(init_mm.write_protect_seq),
 	MMAP_LOCK_INITIALIZER(init_mm)
 	.page_table_lock =  __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock),
 	.arg_lock	=  __SPIN_LOCK_UNLOCKED(init_mm.arg_lock),
diff --git a/mm/memory.c b/mm/memory.c
index c48f8df6e502..50632c4366b8 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1171,6 +1171,15 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
 		mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE,
 					0, src_vma, src_mm, addr, end);
 		mmu_notifier_invalidate_range_start(&range);
+		/*
+		 * Disabling preemption is not needed for the write side, as
+		 * the read side doesn't spin, but goes to the mmap_lock.
+		 *
+		 * Use the raw variant of the seqcount_t write API to avoid
+		 * lockdep complaining about preemptibility.
+		 */
+		mmap_assert_write_locked(src_mm);
+		raw_write_seqcount_begin(&src_mm->write_protect_seq);
 	}
 
 	ret = 0;
@@ -1187,8 +1196,10 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
 		}
 	} while (dst_pgd++, src_pgd++, addr = next, addr != end);
 
-	if (is_cow)
+	if (is_cow) {
+		raw_write_seqcount_end(&src_mm->write_protect_seq);
 		mmu_notifier_invalidate_range_end(&range);
+	}
 	return ret;
 }
 
-- 
cgit v1.2.3


From 52650c8b466bac399aec213c61d74bfe6f7af1a4 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Mon, 14 Dec 2020 19:05:48 -0800
Subject: mm/gup: remove the vma allocation from gup_longterm_locked()

Long ago there wasn't a FOLL_LONGTERM flag so this DAX check was done by
post-processing the VMA list.

These days it is trivial to just check each VMA to see if it is DAX before
processing it inside __get_user_pages() and return failure if a DAX VMA is
encountered with FOLL_LONGTERM.

Removing the allocation of the VMA list is a significant speed up for many
call sites.

Add an IS_ENABLED to vma_is_fsdax so that code generation is unchanged
when DAX is compiled out.

Remove the dummy version of __gup_longterm_locked() as !CONFIG_CMA already
makes memalloc_nocma_save(), check_and_migrate_cma_pages(), and
memalloc_nocma_restore() into a NOP.

Link: https://lkml.kernel.org/r/0-v1-5551df3ed12e+b8-gup_dax_speedup_jgg@nvidia.com
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/fs.h |  2 +-
 mm/gup.c           | 83 ++++++++++--------------------------------------------
 2 files changed, 16 insertions(+), 69 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 8667d0cdc71e..1fcc2b00582b 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3230,7 +3230,7 @@ static inline bool vma_is_fsdax(struct vm_area_struct *vma)
 {
 	struct inode *inode;
 
-	if (!vma->vm_file)
+	if (!IS_ENABLED(CONFIG_FS_DAX) || !vma->vm_file)
 		return false;
 	if (!vma_is_dax(vma))
 		return false;
diff --git a/mm/gup.c b/mm/gup.c
index 9c6a2f5001c5..311a44ff41ff 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -923,6 +923,9 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
 	if (gup_flags & FOLL_ANON && !vma_is_anonymous(vma))
 		return -EFAULT;
 
+	if ((gup_flags & FOLL_LONGTERM) && vma_is_fsdax(vma))
+		return -EOPNOTSUPP;
+
 	if (write) {
 		if (!(vm_flags & VM_WRITE)) {
 			if (!(gup_flags & FOLL_FORCE))
@@ -1060,10 +1063,14 @@ static long __get_user_pages(struct mm_struct *mm,
 				goto next_page;
 			}
 
-			if (!vma || check_vma_flags(vma, gup_flags)) {
+			if (!vma) {
 				ret = -EFAULT;
 				goto out;
 			}
+			ret = check_vma_flags(vma, gup_flags);
+			if (ret)
+				goto out;
+
 			if (is_vm_hugetlb_page(vma)) {
 				i = follow_hugetlb_page(mm, vma, pages, vmas,
 						&start, &nr_pages, i,
@@ -1567,26 +1574,6 @@ struct page *get_dump_page(unsigned long addr)
 }
 #endif /* CONFIG_ELF_CORE */
 
-#if defined(CONFIG_FS_DAX) || defined (CONFIG_CMA)
-static bool check_dax_vmas(struct vm_area_struct **vmas, long nr_pages)
-{
-	long i;
-	struct vm_area_struct *vma_prev = NULL;
-
-	for (i = 0; i < nr_pages; i++) {
-		struct vm_area_struct *vma = vmas[i];
-
-		if (vma == vma_prev)
-			continue;
-
-		vma_prev = vma;
-
-		if (vma_is_fsdax(vma))
-			return true;
-	}
-	return false;
-}
-
 #ifdef CONFIG_CMA
 static long check_and_migrate_cma_pages(struct mm_struct *mm,
 					unsigned long start,
@@ -1705,63 +1692,23 @@ static long __gup_longterm_locked(struct mm_struct *mm,
 				  struct vm_area_struct **vmas,
 				  unsigned int gup_flags)
 {
-	struct vm_area_struct **vmas_tmp = vmas;
 	unsigned long flags = 0;
-	long rc, i;
+	long rc;
 
-	if (gup_flags & FOLL_LONGTERM) {
-		if (!pages)
-			return -EINVAL;
-
-		if (!vmas_tmp) {
-			vmas_tmp = kcalloc(nr_pages,
-					   sizeof(struct vm_area_struct *),
-					   GFP_KERNEL);
-			if (!vmas_tmp)
-				return -ENOMEM;
-		}
+	if (gup_flags & FOLL_LONGTERM)
 		flags = memalloc_nocma_save();
-	}
 
-	rc = __get_user_pages_locked(mm, start, nr_pages, pages,
-				     vmas_tmp, NULL, gup_flags);
+	rc = __get_user_pages_locked(mm, start, nr_pages, pages, vmas, NULL,
+				     gup_flags);
 
 	if (gup_flags & FOLL_LONGTERM) {
-		if (rc < 0)
-			goto out;
-
-		if (check_dax_vmas(vmas_tmp, rc)) {
-			if (gup_flags & FOLL_PIN)
-				unpin_user_pages(pages, rc);
-			else
-				for (i = 0; i < rc; i++)
-					put_page(pages[i]);
-			rc = -EOPNOTSUPP;
-			goto out;
-		}
-
-		rc = check_and_migrate_cma_pages(mm, start, rc, pages,
-						 vmas_tmp, gup_flags);
-out:
+		if (rc > 0)
+			rc = check_and_migrate_cma_pages(mm, start, rc, pages,
+							 vmas, gup_flags);
 		memalloc_nocma_restore(flags);
 	}
-
-	if (vmas_tmp != vmas)
-		kfree(vmas_tmp);
 	return rc;
 }
-#else /* !CONFIG_FS_DAX && !CONFIG_CMA */
-static __always_inline long __gup_longterm_locked(struct mm_struct *mm,
-						  unsigned long start,
-						  unsigned long nr_pages,
-						  struct page **pages,
-						  struct vm_area_struct **vmas,
-						  unsigned int flags)
-{
-	return __get_user_pages_locked(mm, start, nr_pages, pages, vmas,
-				       NULL, flags);
-}
-#endif /* CONFIG_FS_DAX || CONFIG_CMA */
 
 static bool is_valid_gup_flags(unsigned int gup_flags)
 {
-- 
cgit v1.2.3


From 462680946b6d982afdda3bf5f7de3c379cb8c97b Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Mon, 14 Dec 2020 19:06:11 -0800
Subject: mm: remove pagevec_lookup_range_nr_tag()

With the merge of commit 2e1692966034 ("ceph: have ceph_writepages_start
call pagevec_lookup_range_tag"), nothing calls this anymore.

Link: https://lkml.kernel.org/r/20201021193926.101474-1-jlayton@kernel.org
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/pagevec.h | 3 ---
 mm/swap.c               | 9 ---------
 2 files changed, 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h
index 081d934eda64..ad4ddc17d403 100644
--- a/include/linux/pagevec.h
+++ b/include/linux/pagevec.h
@@ -43,9 +43,6 @@ static inline unsigned pagevec_lookup(struct pagevec *pvec,
 unsigned pagevec_lookup_range_tag(struct pagevec *pvec,
 		struct address_space *mapping, pgoff_t *index, pgoff_t end,
 		xa_mark_t tag);
-unsigned pagevec_lookup_range_nr_tag(struct pagevec *pvec,
-		struct address_space *mapping, pgoff_t *index, pgoff_t end,
-		xa_mark_t tag, unsigned max_pages);
 static inline unsigned pagevec_lookup_tag(struct pagevec *pvec,
 		struct address_space *mapping, pgoff_t *index, xa_mark_t tag)
 {
diff --git a/mm/swap.c b/mm/swap.c
index 29220174433b..16a525296960 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -1167,15 +1167,6 @@ unsigned pagevec_lookup_range_tag(struct pagevec *pvec,
 }
 EXPORT_SYMBOL(pagevec_lookup_range_tag);
 
-unsigned pagevec_lookup_range_nr_tag(struct pagevec *pvec,
-		struct address_space *mapping, pgoff_t *index, pgoff_t end,
-		xa_mark_t tag, unsigned max_pages)
-{
-	pvec->nr = find_get_pages_range_tag(mapping, index, end, tag,
-		min_t(unsigned int, max_pages, PAGEVEC_SIZE), pvec->pages);
-	return pagevec_count(pvec);
-}
-EXPORT_SYMBOL(pagevec_lookup_range_nr_tag);
 /*
  * Perform any setup for the swap system
  */
-- 
cgit v1.2.3


From 30e6a51dbb0594d79dc2a9543659c1d596e2f7d4 Mon Sep 17 00:00:00 2001
From: Hui Su <sh_def@163.com>
Date: Mon, 14 Dec 2020 19:06:14 -0800
Subject: mm/shmem.c: make shmem_mapping() inline

shmem_mapping() isn't worth an out-of-line call from any callsite.

So make it inline by
 - make shmem_aops global
 - export shmem_aops
 - inline the shmem_mapping()

and replace the direct call 'shmem_aops' with shmem_mapping()
in shmem.c.

Link: https://lkml.kernel.org/r/20201115165207.GA265355@rlk
Signed-off-by: Hui Su <sh_def@163.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/shmem_fs.h |  6 +++++-
 mm/shmem.c               | 16 ++++++----------
 2 files changed, 11 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index a5a5d1d4d7b1..d82b6f396588 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -67,7 +67,11 @@ extern unsigned long shmem_get_unmapped_area(struct file *, unsigned long addr,
 		unsigned long len, unsigned long pgoff, unsigned long flags);
 extern int shmem_lock(struct file *file, int lock, struct user_struct *user);
 #ifdef CONFIG_SHMEM
-extern bool shmem_mapping(struct address_space *mapping);
+extern const struct address_space_operations shmem_aops;
+static inline bool shmem_mapping(struct address_space *mapping)
+{
+	return mapping->a_ops == &shmem_aops;
+}
 #else
 static inline bool shmem_mapping(struct address_space *mapping)
 {
diff --git a/mm/shmem.c b/mm/shmem.c
index 537c137698f8..b7361fce50bc 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -246,7 +246,7 @@ static inline void shmem_inode_unacct_blocks(struct inode *inode, long pages)
 }
 
 static const struct super_operations shmem_ops;
-static const struct address_space_operations shmem_aops;
+const struct address_space_operations shmem_aops;
 static const struct file_operations shmem_file_operations;
 static const struct inode_operations shmem_inode_operations;
 static const struct inode_operations shmem_dir_inode_operations;
@@ -1152,7 +1152,7 @@ static void shmem_evict_inode(struct inode *inode)
 	struct shmem_inode_info *info = SHMEM_I(inode);
 	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
 
-	if (inode->i_mapping->a_ops == &shmem_aops) {
+	if (shmem_mapping(inode->i_mapping)) {
 		shmem_unacct_size(info->flags, inode->i_size);
 		inode->i_size = 0;
 		shmem_truncate_range(inode, 0, (loff_t)-1);
@@ -1858,7 +1858,7 @@ repeat:
 	}
 
 	/* shmem_symlink() */
-	if (mapping->a_ops != &shmem_aops)
+	if (!shmem_mapping(mapping))
 		goto alloc_nohuge;
 	if (shmem_huge == SHMEM_HUGE_DENY || sgp_huge == SGP_NOHUGE)
 		goto alloc_nohuge;
@@ -2352,11 +2352,6 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
 	return inode;
 }
 
-bool shmem_mapping(struct address_space *mapping)
-{
-	return mapping->a_ops == &shmem_aops;
-}
-
 static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
 				  pmd_t *dst_pmd,
 				  struct vm_area_struct *dst_vma,
@@ -3865,7 +3860,7 @@ static void shmem_destroy_inodecache(void)
 	kmem_cache_destroy(shmem_inode_cachep);
 }
 
-static const struct address_space_operations shmem_aops = {
+const struct address_space_operations shmem_aops = {
 	.writepage	= shmem_writepage,
 	.set_page_dirty	= __set_page_dirty_no_writeback,
 #ifdef CONFIG_TMPFS
@@ -3877,6 +3872,7 @@ static const struct address_space_operations shmem_aops = {
 #endif
 	.error_remove_page = generic_error_remove_page,
 };
+EXPORT_SYMBOL(shmem_aops);
 
 static const struct file_operations shmem_file_operations = {
 	.mmap		= shmem_mmap,
@@ -4312,7 +4308,7 @@ struct page *shmem_read_mapping_page_gfp(struct address_space *mapping,
 	struct page *page;
 	int error;
 
-	BUG_ON(mapping->a_ops != &shmem_aops);
+	BUG_ON(!shmem_mapping(mapping));
 	error = shmem_getpage_gfp(inode, index, &page, SGP_CACHE,
 				  gfp, NULL, NULL, NULL);
 	if (error)
-- 
cgit v1.2.3


From 1a984c4e8200e0e58bb316f14a4bebb28d32d15a Mon Sep 17 00:00:00 2001
From: Muchun Song <songmuchun@bytedance.com>
Date: Mon, 14 Dec 2020 19:06:24 -0800
Subject: mm: memcontrol: remove unused mod_memcg_obj_state()

Since commit 991e7673859e ("mm: memcontrol: account kernel stack per
node") there is no user of the mod_memcg_obj_state().  So just remove
it.

Also rework type of the idx parameter of the mod_objcg_state() from int
to enum node_stat_item.

Link: https://lkml.kernel.org/r/20201013153504.92602-1-songmuchun@bytedance.com
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Acked-by: Roman Gushchin <guro@fb.com>
Acked-by: David Rientjes <rientjes@google.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Christopher Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yafang Shao <laoar.shao@gmail.com>
Cc: Chris Down <chris@chrisdown.name>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h |  6 ------
 mm/memcontrol.c            | 11 -----------
 mm/slab.h                  |  4 ++--
 3 files changed, 2 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 922a7f600465..28bf65560084 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -798,8 +798,6 @@ void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 			int val);
 void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val);
 
-void mod_memcg_obj_state(void *p, int idx, int val);
-
 static inline void mod_lruvec_slab_state(void *p, enum node_stat_item idx,
 					 int val)
 {
@@ -1255,10 +1253,6 @@ static inline void mod_lruvec_slab_state(void *p, enum node_stat_item idx,
 	mod_node_page_state(page_pgdat(page), idx, val);
 }
 
-static inline void mod_memcg_obj_state(void *p, int idx, int val)
-{
-}
-
 static inline
 unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
 					    gfp_t gfp_mask,
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c3654510fb70..83f2e5f84bdc 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -882,17 +882,6 @@ void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val)
 	rcu_read_unlock();
 }
 
-void mod_memcg_obj_state(void *p, int idx, int val)
-{
-	struct mem_cgroup *memcg;
-
-	rcu_read_lock();
-	memcg = mem_cgroup_from_obj(p);
-	if (memcg)
-		mod_memcg_state(memcg, idx, val);
-	rcu_read_unlock();
-}
-
 /**
  * __count_memcg_events - account VM events in a cgroup
  * @memcg: the memory cgroup
diff --git a/mm/slab.h b/mm/slab.h
index f9977d6613d6..65f4647f1286 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -204,7 +204,7 @@ ssize_t slabinfo_write(struct file *file, const char __user *buffer,
 void __kmem_cache_free_bulk(struct kmem_cache *, size_t, void **);
 int __kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **);
 
-static inline int cache_vmstat_idx(struct kmem_cache *s)
+static inline enum node_stat_item cache_vmstat_idx(struct kmem_cache *s)
 {
 	return (s->flags & SLAB_RECLAIM_ACCOUNT) ?
 		NR_SLAB_RECLAIMABLE_B : NR_SLAB_UNRECLAIMABLE_B;
@@ -304,7 +304,7 @@ static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s,
 
 static inline void mod_objcg_state(struct obj_cgroup *objcg,
 				   struct pglist_data *pgdat,
-				   int idx, int nr)
+				   enum node_stat_item idx, int nr)
 {
 	struct mem_cgroup *memcg;
 	struct lruvec *lruvec;
-- 
cgit v1.2.3


From 013339df116c2ee0d796dd8bfb8f293a2030c063 Mon Sep 17 00:00:00 2001
From: Shakeel Butt <shakeelb@google.com>
Date: Mon, 14 Dec 2020 19:06:39 -0800
Subject: mm/rmap: always do TTU_IGNORE_ACCESS

Since commit 369ea8242c0f ("mm/rmap: update to new mmu_notifier semantic
v2"), the code to check the secondary MMU's page table access bit is
broken for !(TTU_IGNORE_ACCESS) because the page is unmapped from the
secondary MMU's page table before the check.  More specifically for those
secondary MMUs which unmap the memory in
mmu_notifier_invalidate_range_start() like kvm.

However memory reclaim is the only user of !(TTU_IGNORE_ACCESS) or the
absence of TTU_IGNORE_ACCESS and it explicitly performs the page table
access check before trying to unmap the page.  So, at worst the reclaim
will miss accesses in a very short window if we remove page table access
check in unmapping code.

There is an unintented consequence of !(TTU_IGNORE_ACCESS) for the memcg
reclaim.  From memcg reclaim the page_referenced() only account the
accesses from the processes which are in the same memcg of the target page
but the unmapping code is considering accesses from all the processes, so,
decreasing the effectiveness of memcg reclaim.

The simplest solution is to always assume TTU_IGNORE_ACCESS in unmapping
code.

Link: https://lkml.kernel.org/r/20201104231928.1494083-1-shakeelb@google.com
Fixes: 369ea8242c0f ("mm/rmap: update to new mmu_notifier semantic v2")
Signed-off-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/rmap.h |  1 -
 mm/huge_memory.c     |  2 +-
 mm/memory-failure.c  |  2 +-
 mm/memory_hotplug.c  |  2 +-
 mm/migrate.c         |  8 +++-----
 mm/rmap.c            |  9 ---------
 mm/vmscan.c          | 14 +++++---------
 7 files changed, 11 insertions(+), 27 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 3a6adfa70fb0..70085ca1a3fc 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -91,7 +91,6 @@ enum ttu_flags {
 
 	TTU_SPLIT_HUGE_PMD	= 0x4,	/* split huge PMD if any */
 	TTU_IGNORE_MLOCK	= 0x8,	/* ignore mlock */
-	TTU_IGNORE_ACCESS	= 0x10,	/* don't age */
 	TTU_IGNORE_HWPOISON	= 0x20,	/* corrupted page is recoverable */
 	TTU_BATCH_FLUSH		= 0x40,	/* Batch TLB flushes where possible
 					 * and caller guarantees they will
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 42b18d461086..c11c80078335 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2321,7 +2321,7 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma,
 
 static void unmap_page(struct page *page)
 {
-	enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS |
+	enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK |
 		TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD;
 	bool unmap_success;
 
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 5d880d4eb9a2..71295bb984af 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -989,7 +989,7 @@ static int get_hwpoison_page(struct page *page)
 static bool hwpoison_user_mappings(struct page *p, unsigned long pfn,
 				  int flags, struct page **hpagep)
 {
-	enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS;
+	enum ttu_flags ttu = TTU_IGNORE_MLOCK;
 	struct address_space *mapping;
 	LIST_HEAD(tokill);
 	bool unmap_success = true;
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 63b2e46b6555..0f855deea4b2 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1304,7 +1304,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 			if (WARN_ON(PageLRU(page)))
 				isolate_lru_page(page);
 			if (page_mapped(page))
-				try_to_unmap(page, TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS);
+				try_to_unmap(page, TTU_IGNORE_MLOCK);
 			continue;
 		}
 
diff --git a/mm/migrate.c b/mm/migrate.c
index 5795cb82e27c..8ea0c65f1075 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1122,8 +1122,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
 		/* Establish migration ptes */
 		VM_BUG_ON_PAGE(PageAnon(page) && !PageKsm(page) && !anon_vma,
 				page);
-		try_to_unmap(page,
-			TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS);
+		try_to_unmap(page, TTU_MIGRATION|TTU_IGNORE_MLOCK);
 		page_was_mapped = 1;
 	}
 
@@ -1329,8 +1328,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
 
 	if (page_mapped(hpage)) {
 		bool mapping_locked = false;
-		enum ttu_flags ttu = TTU_MIGRATION|TTU_IGNORE_MLOCK|
-					TTU_IGNORE_ACCESS;
+		enum ttu_flags ttu = TTU_MIGRATION|TTU_IGNORE_MLOCK;
 
 		if (!PageAnon(hpage)) {
 			/*
@@ -2688,7 +2686,7 @@ static void migrate_vma_prepare(struct migrate_vma *migrate)
  */
 static void migrate_vma_unmap(struct migrate_vma *migrate)
 {
-	int flags = TTU_MIGRATION | TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS;
+	int flags = TTU_MIGRATION | TTU_IGNORE_MLOCK;
 	const unsigned long npages = migrate->npages;
 	const unsigned long start = migrate->start;
 	unsigned long addr, i, restore = 0;
diff --git a/mm/rmap.c b/mm/rmap.c
index 31b29321adfe..6657000b18d4 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1533,15 +1533,6 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			goto discard;
 		}
 
-		if (!(flags & TTU_IGNORE_ACCESS)) {
-			if (ptep_clear_flush_young_notify(vma, address,
-						pvmw.pte)) {
-				ret = false;
-				page_vma_mapped_walk_done(&pvmw);
-				break;
-			}
-		}
-
 		/* Nuke the page table entry. */
 		flush_cache_page(vma, address, pte_pfn(*pvmw.pte));
 		if (should_defer_flush(mm, flags)) {
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 7b4e31eac2cf..0ec6321e9887 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1072,7 +1072,6 @@ static void page_check_dirty_writeback(struct page *page,
 static unsigned int shrink_page_list(struct list_head *page_list,
 				     struct pglist_data *pgdat,
 				     struct scan_control *sc,
-				     enum ttu_flags ttu_flags,
 				     struct reclaim_stat *stat,
 				     bool ignore_references)
 {
@@ -1297,7 +1296,7 @@ static unsigned int shrink_page_list(struct list_head *page_list,
 		 * processes. Try to unmap it here.
 		 */
 		if (page_mapped(page)) {
-			enum ttu_flags flags = ttu_flags | TTU_BATCH_FLUSH;
+			enum ttu_flags flags = TTU_BATCH_FLUSH;
 			bool was_swapbacked = PageSwapBacked(page);
 
 			if (unlikely(PageTransHuge(page)))
@@ -1514,7 +1513,7 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
 	}
 
 	nr_reclaimed = shrink_page_list(&clean_pages, zone->zone_pgdat, &sc,
-			TTU_IGNORE_ACCESS, &stat, true);
+					&stat, true);
 	list_splice(&clean_pages, page_list);
 	mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE,
 			    -(long)nr_reclaimed);
@@ -1958,8 +1957,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	if (nr_taken == 0)
 		return 0;
 
-	nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, 0,
-				&stat, false);
+	nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, &stat, false);
 
 	spin_lock_irq(&pgdat->lru_lock);
 
@@ -2131,8 +2129,7 @@ unsigned long reclaim_pages(struct list_head *page_list)
 
 		nr_reclaimed += shrink_page_list(&node_page_list,
 						NODE_DATA(nid),
-						&sc, 0,
-						&dummy_stat, false);
+						&sc, &dummy_stat, false);
 		while (!list_empty(&node_page_list)) {
 			page = lru_to_page(&node_page_list);
 			list_del(&page->lru);
@@ -2145,8 +2142,7 @@ unsigned long reclaim_pages(struct list_head *page_list)
 	if (!list_empty(&node_page_list)) {
 		nr_reclaimed += shrink_page_list(&node_page_list,
 						NODE_DATA(nid),
-						&sc, 0,
-						&dummy_stat, false);
+						&sc, &dummy_stat, false);
 		while (!list_empty(&node_page_list)) {
 			page = lru_to_page(&node_page_list);
 			list_del(&page->lru);
-- 
cgit v1.2.3


From a7cb874bfff785d39de6cc847673539cb3540821 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Mon, 14 Dec 2020 19:06:45 -0800
Subject: mm: memcg: fix obsolete code comments

This patch fixes/removes some obsolete comments in the code related
to the kernel memory accounting:

 - kmem_cache->memcg_params.memcg_caches has been removed by commit
   9855609bde03 ("mm: memcg/slab: use a single set of kmem_caches for
   all accounted allocations")

 - memcg->kmemcg_id is not used as a gate for kmem accounting since
   commit 0b8f73e10428 ("mm: memcontrol: clean up alloc, online,
   offline, free functions")

Link: https://lkml.kernel.org/r/20201110184615.311974-1-guro@fb.com
Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 6 ++----
 mm/memcontrol.c            | 6 ------
 2 files changed, 2 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 28bf65560084..1f0f64fa3ccd 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -296,7 +296,6 @@ struct mem_cgroup {
 	int			tcpmem_pressure;
 
 #ifdef CONFIG_MEMCG_KMEM
-        /* Index in the kmem_cache->memcg_params.memcg_caches array */
 	int kmemcg_id;
 	enum memcg_kmem_state kmem_state;
 	struct obj_cgroup __rcu *objcg;
@@ -1562,9 +1561,8 @@ static inline void memcg_kmem_uncharge(struct mem_cgroup *memcg,
 }
 
 /*
- * helper for accessing a memcg's index. It will be used as an index in the
- * child cache array in kmem_cache, and also to derive its name. This function
- * will return -1 when this is not a kmem-limited memcg.
+ * A helper for accessing memcg's kmem_id, used for getting
+ * corresponding LRU lists.
  */
 static inline int memcg_cache_id(struct mem_cgroup *memcg)
 {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 758613277286..466d9aed6cc8 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3703,12 +3703,6 @@ static int memcg_online_kmem(struct mem_cgroup *memcg)
 
 	static_branch_enable(&memcg_kmem_enabled_key);
 
-	/*
-	 * A memory cgroup is considered kmem-online as soon as it gets
-	 * kmemcg_id. Setting the id after enabling static branching will
-	 * guarantee no one starts accounting before all call sites are
-	 * patched.
-	 */
 	memcg->kmemcg_id = memcg_id;
 	memcg->kmem_state = KMEM_ONLINE;
 
-- 
cgit v1.2.3


From bef8620cd8e0a117c1a0719604052e424eb418f9 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Mon, 14 Dec 2020 19:06:49 -0800
Subject: mm: memcg: deprecate the non-hierarchical mode

Patch series "mm: memcg: deprecate cgroup v1 non-hierarchical mode", v1.

The non-hierarchical cgroup v1 mode is a legacy of early days
of the memory controller and doesn't bring any value today.
However, it complicates the code and creates many edge cases
all over the memory controller code.

It's a good time to deprecate it completely. This patchset removes
the internal logic, adjusts the user interface and updates
the documentation. The alt patch removes some bits of the cgroup
core code, which become obsolete.

Michal Hocko said:
  "All that we know today is that we have a warning in place to complain
   loudly when somebody relies on use_hierarchy=0 with a deeper
   hierarchy. For all those years we have seen _zero_ reports that would
   describe a sensible usecase.

   Moreover we (SUSE) have backported this warning into old distribution
   kernels (since 3.0 based kernels) to extend the coverage and didn't
   hear even for users who adopt new kernels only very slowly. The only
   report we have seen so far was a LTP test suite which doesn't really
   reflect any real life usecase"

This patch (of 3):

The non-hierarchical cgroup v1 mode is a legacy of early days of the
memory controller and doesn't bring any value today.  However, it
complicates the code and creates many edge cases all over the memory
controller code.

It's a good time to deprecate it completely.

Functionally this patch enabled is by default for all cgroups and forbids
switching it off.  Nothing changes if cgroup v2 is used: hierarchical mode
was enforced from scratch.

To protect the ABI memory.use_hierarchy interface is preserved with a
limited functionality: reading always returns "1", writing of "1" passes
silently, writing of any other value fails with -EINVAL and a warning to
dmesg (on the first occasion).

Link: https://lkml.kernel.org/r/20201110220800.929549-1-guro@fb.com
Link: https://lkml.kernel.org/r/20201110220800.929549-2-guro@fb.com
Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: David Rientjes <rientjes@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h |  7 ----
 kernel/cgroup/cgroup.c     |  5 ---
 mm/memcontrol.c            | 90 +++++++---------------------------------------
 3 files changed, 13 insertions(+), 89 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 1f0f64fa3ccd..dd992b81bcb7 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -234,11 +234,6 @@ struct mem_cgroup {
 	/* vmpressure notifications */
 	struct vmpressure vmpressure;
 
-	/*
-	 * Should the accounting and control be hierarchical, per subtree?
-	 */
-	bool use_hierarchy;
-
 	/*
 	 * Should the OOM killer kill all belonging tasks, had it kill one?
 	 */
@@ -588,8 +583,6 @@ static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg,
 {
 	if (root == memcg)
 		return true;
-	if (!root->use_hierarchy)
-		return false;
 	return cgroup_is_descendant(memcg->css.cgroup, root->css.cgroup);
 }
 
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index e41c21819ba0..80c5c34416e8 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -281,9 +281,6 @@ bool cgroup_ssid_enabled(int ssid)
  * - cpuset: a task can be moved into an empty cpuset, and again it takes
  *   masks of ancestors.
  *
- * - memcg: use_hierarchy is on by default and the cgroup file for the flag
- *   is not created.
- *
  * - blkcg: blk-throttle becomes properly hierarchical.
  *
  * - debug: disallowed on the default hierarchy.
@@ -5156,8 +5153,6 @@ static struct cgroup_subsys_state *css_create(struct cgroup *cgrp,
 	    cgroup_parent(parent)) {
 		pr_warn("%s (%d) created nested cgroup for controller \"%s\" which has incomplete hierarchy support. Nested cgroups may change behavior in the future.\n",
 			current->comm, current->pid, ss->name);
-		if (!strcmp(ss->name, "memory"))
-			pr_warn("\"memory\" requires setting use_hierarchy to 1 on the root\n");
 		ss->warned_broken_hierarchy = true;
 	}
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 466d9aed6cc8..fc18a2b7d25a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1141,12 +1141,6 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 	if (prev && !reclaim)
 		pos = prev;
 
-	if (!root->use_hierarchy && root != root_mem_cgroup) {
-		if (prev)
-			goto out;
-		return root;
-	}
-
 	rcu_read_lock();
 
 	if (reclaim) {
@@ -1226,7 +1220,6 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 
 out_unlock:
 	rcu_read_unlock();
-out:
 	if (prev && prev != root)
 		css_put(&prev->css);
 
@@ -3461,10 +3454,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
 }
 
 /*
- * Test whether @memcg has children, dead or alive.  Note that this
- * function doesn't care whether @memcg has use_hierarchy enabled and
- * returns %true if there are child csses according to the cgroup
- * hierarchy.  Testing use_hierarchy is the caller's responsibility.
+ * Test whether @memcg has children, dead or alive.
  */
 static inline bool memcg_has_children(struct mem_cgroup *memcg)
 {
@@ -3524,37 +3514,20 @@ static ssize_t mem_cgroup_force_empty_write(struct kernfs_open_file *of,
 static u64 mem_cgroup_hierarchy_read(struct cgroup_subsys_state *css,
 				     struct cftype *cft)
 {
-	return mem_cgroup_from_css(css)->use_hierarchy;
+	return 1;
 }
 
 static int mem_cgroup_hierarchy_write(struct cgroup_subsys_state *css,
 				      struct cftype *cft, u64 val)
 {
-	int retval = 0;
-	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
-	struct mem_cgroup *parent_memcg = mem_cgroup_from_css(memcg->css.parent);
-
-	if (memcg->use_hierarchy == val)
+	if (val == 1)
 		return 0;
 
-	/*
-	 * If parent's use_hierarchy is set, we can't make any modifications
-	 * in the child subtrees. If it is unset, then the change can
-	 * occur, provided the current cgroup has no children.
-	 *
-	 * For the root cgroup, parent_mem is NULL, we allow value to be
-	 * set if there are no children.
-	 */
-	if ((!parent_memcg || !parent_memcg->use_hierarchy) &&
-				(val == 1 || val == 0)) {
-		if (!memcg_has_children(memcg))
-			memcg->use_hierarchy = val;
-		else
-			retval = -EBUSY;
-	} else
-		retval = -EINVAL;
+	pr_warn_once("Non-hierarchical mode is deprecated. "
+		     "Please report your usecase to linux-mm@kvack.org if you "
+		     "depend on this functionality.\n");
 
-	return retval;
+	return -EINVAL;
 }
 
 static unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
@@ -3742,8 +3715,6 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg)
 		child = mem_cgroup_from_css(css);
 		BUG_ON(child->kmemcg_id != kmemcg_id);
 		child->kmemcg_id = parent->kmemcg_id;
-		if (!memcg->use_hierarchy)
-			break;
 	}
 	rcu_read_unlock();
 
@@ -5334,38 +5305,22 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 	if (parent) {
 		memcg->swappiness = mem_cgroup_swappiness(parent);
 		memcg->oom_kill_disable = parent->oom_kill_disable;
-	}
-	if (!parent) {
-		page_counter_init(&memcg->memory, NULL);
-		page_counter_init(&memcg->swap, NULL);
-		page_counter_init(&memcg->kmem, NULL);
-		page_counter_init(&memcg->tcpmem, NULL);
-	} else if (parent->use_hierarchy) {
-		memcg->use_hierarchy = true;
+
 		page_counter_init(&memcg->memory, &parent->memory);
 		page_counter_init(&memcg->swap, &parent->swap);
 		page_counter_init(&memcg->kmem, &parent->kmem);
 		page_counter_init(&memcg->tcpmem, &parent->tcpmem);
 	} else {
-		page_counter_init(&memcg->memory, &root_mem_cgroup->memory);
-		page_counter_init(&memcg->swap, &root_mem_cgroup->swap);
-		page_counter_init(&memcg->kmem, &root_mem_cgroup->kmem);
-		page_counter_init(&memcg->tcpmem, &root_mem_cgroup->tcpmem);
-		/*
-		 * Deeper hierachy with use_hierarchy == false doesn't make
-		 * much sense so let cgroup subsystem know about this
-		 * unfortunate state in our controller.
-		 */
-		if (parent != root_mem_cgroup)
-			memory_cgrp_subsys.broken_hierarchy = true;
-	}
+		page_counter_init(&memcg->memory, NULL);
+		page_counter_init(&memcg->swap, NULL);
+		page_counter_init(&memcg->kmem, NULL);
+		page_counter_init(&memcg->tcpmem, NULL);
 
-	/* The following stuff does not apply to the root */
-	if (!parent) {
 		root_mem_cgroup = memcg;
 		return &memcg->css;
 	}
 
+	/* The following stuff does not apply to the root */
 	error = memcg_online_kmem(memcg);
 	if (error)
 		goto fail;
@@ -6202,24 +6157,6 @@ static void mem_cgroup_move_task(void)
 }
 #endif
 
-/*
- * Cgroup retains root cgroups across [un]mount cycles making it necessary
- * to verify whether we're attached to the default hierarchy on each mount
- * attempt.
- */
-static void mem_cgroup_bind(struct cgroup_subsys_state *root_css)
-{
-	/*
-	 * use_hierarchy is forced on the default hierarchy.  cgroup core
-	 * guarantees that @root doesn't have any children, so turning it
-	 * on for the root memcg is enough.
-	 */
-	if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
-		root_mem_cgroup->use_hierarchy = true;
-	else
-		root_mem_cgroup->use_hierarchy = false;
-}
-
 static int seq_puts_memcg_tunable(struct seq_file *m, unsigned long value)
 {
 	if (value == PAGE_COUNTER_MAX)
@@ -6557,7 +6494,6 @@ struct cgroup_subsys memory_cgrp_subsys = {
 	.can_attach = mem_cgroup_can_attach,
 	.cancel_attach = mem_cgroup_cancel_attach,
 	.post_attach = mem_cgroup_move_task,
-	.bind = mem_cgroup_bind,
 	.dfl_cftypes = memory_files,
 	.legacy_cftypes = mem_cgroup_legacy_files,
 	.early_init = 0,
-- 
cgit v1.2.3


From 9d9d341df4d519d96e7927941d91f5785c5cea07 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Mon, 14 Dec 2020 19:06:55 -0800
Subject: cgroup: remove obsoleted broken_hierarchy and warned_broken_hierarchy

With the deprecation of the non-hierarchical mode of the memory controller
there are no more examples of broken hierarchies left.

Let's remove the cgroup core code which was supposed to print warnings
about creating of broken hierarchies.

Link: https://lkml.kernel.org/r/20201110220800.929549-4-guro@fb.com
Signed-off-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: David Rientjes <rientjes@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/cgroup-defs.h | 15 ---------------
 kernel/cgroup/cgroup.c      |  7 -------
 2 files changed, 22 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index fee0b5547cd0..559ee05f86b2 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -668,21 +668,6 @@ struct cgroup_subsys {
 	 */
 	bool threaded:1;
 
-	/*
-	 * If %false, this subsystem is properly hierarchical -
-	 * configuration, resource accounting and restriction on a parent
-	 * cgroup cover those of its children.  If %true, hierarchy support
-	 * is broken in some ways - some subsystems ignore hierarchy
-	 * completely while others are only implemented half-way.
-	 *
-	 * It's now disallowed to create nested cgroups if the subsystem is
-	 * broken and cgroup core will emit a warning message on such
-	 * cases.  Eventually, all subsystems will be made properly
-	 * hierarchical and this will go away.
-	 */
-	bool broken_hierarchy:1;
-	bool warned_broken_hierarchy:1;
-
 	/* the following two fields are initialized automtically during boot */
 	int id;
 	const char *name;
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 80c5c34416e8..16f4692dc961 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -5149,13 +5149,6 @@ static struct cgroup_subsys_state *css_create(struct cgroup *cgrp,
 	if (err)
 		goto err_list_del;
 
-	if (ss->broken_hierarchy && !ss->warned_broken_hierarchy &&
-	    cgroup_parent(parent)) {
-		pr_warn("%s (%d) created nested cgroup for controller \"%s\" which has incomplete hierarchy support. Nested cgroups may change behavior in the future.\n",
-			current->comm, current->pid, ss->name);
-		ss->warned_broken_hierarchy = true;
-	}
-
 	return css;
 
 err_list_del:
-- 
cgit v1.2.3


From da3ceeff923e3bc750a8423c840462760c463926 Mon Sep 17 00:00:00 2001
From: Muchun Song <songmuchun@bytedance.com>
Date: Mon, 14 Dec 2020 19:07:04 -0800
Subject: mm: memcg/slab: rename *_lruvec_slab_state to *_lruvec_kmem_state

The *_lruvec_slab_state is also suitable for pages allocated from buddy,
not just for the slab objects.  But the function name seems to tell us
that only slab object is applicable.  So we can rename the keyword of slab
to kmem.

Link: https://lkml.kernel.org/r/20201117085249.24319-1-songmuchun@bytedance.com
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Acked-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 18 +++++++++---------
 kernel/fork.c              |  2 +-
 mm/memcontrol.c            |  2 +-
 mm/workingset.c            |  8 ++++----
 4 files changed, 15 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index dd992b81bcb7..71c961452d9a 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -788,15 +788,15 @@ void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 			      int val);
 void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 			int val);
-void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val);
+void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val);
 
-static inline void mod_lruvec_slab_state(void *p, enum node_stat_item idx,
+static inline void mod_lruvec_kmem_state(void *p, enum node_stat_item idx,
 					 int val)
 {
 	unsigned long flags;
 
 	local_irq_save(flags);
-	__mod_lruvec_slab_state(p, idx, val);
+	__mod_lruvec_kmem_state(p, idx, val);
 	local_irq_restore(flags);
 }
 
@@ -1229,7 +1229,7 @@ static inline void mod_lruvec_page_state(struct page *page,
 	mod_node_page_state(page_pgdat(page), idx, val);
 }
 
-static inline void __mod_lruvec_slab_state(void *p, enum node_stat_item idx,
+static inline void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx,
 					   int val)
 {
 	struct page *page = virt_to_head_page(p);
@@ -1237,7 +1237,7 @@ static inline void __mod_lruvec_slab_state(void *p, enum node_stat_item idx,
 	__mod_node_page_state(page_pgdat(page), idx, val);
 }
 
-static inline void mod_lruvec_slab_state(void *p, enum node_stat_item idx,
+static inline void mod_lruvec_kmem_state(void *p, enum node_stat_item idx,
 					 int val)
 {
 	struct page *page = virt_to_head_page(p);
@@ -1332,14 +1332,14 @@ static inline void __dec_lruvec_page_state(struct page *page,
 	__mod_lruvec_page_state(page, idx, -1);
 }
 
-static inline void __inc_lruvec_slab_state(void *p, enum node_stat_item idx)
+static inline void __inc_lruvec_kmem_state(void *p, enum node_stat_item idx)
 {
-	__mod_lruvec_slab_state(p, idx, 1);
+	__mod_lruvec_kmem_state(p, idx, 1);
 }
 
-static inline void __dec_lruvec_slab_state(void *p, enum node_stat_item idx)
+static inline void __dec_lruvec_kmem_state(void *p, enum node_stat_item idx)
 {
-	__mod_lruvec_slab_state(p, idx, -1);
+	__mod_lruvec_kmem_state(p, idx, -1);
 }
 
 /* idx can be of type enum memcg_stat_item or node_stat_item */
diff --git a/kernel/fork.c b/kernel/fork.c
index dc55f68a6ee3..5e7cc88eadb5 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -385,7 +385,7 @@ static void account_kernel_stack(struct task_struct *tsk, int account)
 		mod_lruvec_page_state(vm->pages[0], NR_KERNEL_STACK_KB,
 				      account * (THREAD_SIZE / 1024));
 	else
-		mod_lruvec_slab_state(stack, NR_KERNEL_STACK_KB,
+		mod_lruvec_kmem_state(stack, NR_KERNEL_STACK_KB,
 				      account * (THREAD_SIZE / 1024));
 }
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ce19e8484c89..b50f7f336b16 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -853,7 +853,7 @@ void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 		__mod_memcg_lruvec_state(lruvec, idx, val);
 }
 
-void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val)
+void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val)
 {
 	pg_data_t *pgdat = page_pgdat(virt_to_page(p));
 	struct mem_cgroup *memcg;
diff --git a/mm/workingset.c b/mm/workingset.c
index 975a4d2dd02e..25f75bbe80e0 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -445,12 +445,12 @@ void workingset_update_node(struct xa_node *node)
 	if (node->count && node->count == node->nr_values) {
 		if (list_empty(&node->private_list)) {
 			list_lru_add(&shadow_nodes, &node->private_list);
-			__inc_lruvec_slab_state(node, WORKINGSET_NODES);
+			__inc_lruvec_kmem_state(node, WORKINGSET_NODES);
 		}
 	} else {
 		if (!list_empty(&node->private_list)) {
 			list_lru_del(&shadow_nodes, &node->private_list);
-			__dec_lruvec_slab_state(node, WORKINGSET_NODES);
+			__dec_lruvec_kmem_state(node, WORKINGSET_NODES);
 		}
 	}
 }
@@ -544,7 +544,7 @@ static enum lru_status shadow_lru_isolate(struct list_head *item,
 	}
 
 	list_lru_isolate(lru, item);
-	__dec_lruvec_slab_state(node, WORKINGSET_NODES);
+	__dec_lruvec_kmem_state(node, WORKINGSET_NODES);
 
 	spin_unlock(lru_lock);
 
@@ -559,7 +559,7 @@ static enum lru_status shadow_lru_isolate(struct list_head *item,
 		goto out_invalid;
 	mapping->nrexceptional -= node->nr_values;
 	xa_delete_node(node, workingset_update_node);
-	__inc_lruvec_slab_state(node, WORKINGSET_NODERECLAIM);
+	__inc_lruvec_kmem_state(node, WORKINGSET_NODERECLAIM);
 
 out_invalid:
 	xa_unlock_irq(&mapping->i_pages);
-- 
cgit v1.2.3


From c47d5032ed3002311a4188eae51f4641ec436beb Mon Sep 17 00:00:00 2001
From: Shakeel Butt <shakeelb@google.com>
Date: Mon, 14 Dec 2020 19:07:14 -0800
Subject: mm: move lruvec stats update functions to vmstat.h

Patch series "memcg: add pagetable comsumption to memory.stat", v2.

Many workloads consumes significant amount of memory in pagetables.  One
specific use-case is the user space network driver which mmaps the
application memory to provide zero copy transfer.  This driver can consume
a large amount memory in page tables.  This patch series exposes the
pagetable comsumption for each memory cgroup.

This patch (of 2):

This does not change any functionality and only move the functions which
update the lruvec stats to vmstat.h from memcontrol.h.  The main reason
for this patch is to be able to use these functions in the page table
contructor function which is defined in mm.h and we can not include the
memcontrol.h in that file.  Also this is a better place for this interface
in general.  The lruvec abstraction, while invented for memcg, isn't
specific to memcg at all.

Link: https://lkml.kernel.org/r/20201130212541.2781790-2-shakeelb@google.com
Signed-off-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Roman Gushchin <guro@fb.com>
Cc: Michal Hocko <mhocko@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 111 ---------------------------------------------
 include/linux/vmstat.h     | 104 ++++++++++++++++++++++++++++++++++++++++++
 mm/memcontrol.c            |  17 +++++++
 3 files changed, 121 insertions(+), 111 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 71c961452d9a..f530d634f055 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -786,8 +786,6 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
 
 void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 			      int val);
-void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
-			int val);
 void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val);
 
 static inline void mod_lruvec_kmem_state(void *p, enum node_stat_item idx,
@@ -810,43 +808,6 @@ static inline void mod_memcg_lruvec_state(struct lruvec *lruvec,
 	local_irq_restore(flags);
 }
 
-static inline void mod_lruvec_state(struct lruvec *lruvec,
-				    enum node_stat_item idx, int val)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	__mod_lruvec_state(lruvec, idx, val);
-	local_irq_restore(flags);
-}
-
-static inline void __mod_lruvec_page_state(struct page *page,
-					   enum node_stat_item idx, int val)
-{
-	struct page *head = compound_head(page); /* rmap on tail pages */
-	pg_data_t *pgdat = page_pgdat(page);
-	struct lruvec *lruvec;
-
-	/* Untracked pages have no memcg, no lruvec. Update only the node */
-	if (!head->mem_cgroup) {
-		__mod_node_page_state(pgdat, idx, val);
-		return;
-	}
-
-	lruvec = mem_cgroup_lruvec(head->mem_cgroup, pgdat);
-	__mod_lruvec_state(lruvec, idx, val);
-}
-
-static inline void mod_lruvec_page_state(struct page *page,
-					 enum node_stat_item idx, int val)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	__mod_lruvec_page_state(page, idx, val);
-	local_irq_restore(flags);
-}
-
 unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
 						gfp_t gfp_mask,
 						unsigned long *total_scanned);
@@ -1205,30 +1166,6 @@ static inline void __mod_memcg_lruvec_state(struct lruvec *lruvec,
 {
 }
 
-static inline void __mod_lruvec_state(struct lruvec *lruvec,
-				      enum node_stat_item idx, int val)
-{
-	__mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
-}
-
-static inline void mod_lruvec_state(struct lruvec *lruvec,
-				    enum node_stat_item idx, int val)
-{
-	mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
-}
-
-static inline void __mod_lruvec_page_state(struct page *page,
-					   enum node_stat_item idx, int val)
-{
-	__mod_node_page_state(page_pgdat(page), idx, val);
-}
-
-static inline void mod_lruvec_page_state(struct page *page,
-					 enum node_stat_item idx, int val)
-{
-	mod_node_page_state(page_pgdat(page), idx, val);
-}
-
 static inline void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx,
 					   int val)
 {
@@ -1308,30 +1245,6 @@ static inline void __dec_memcg_page_state(struct page *page,
 	__mod_memcg_page_state(page, idx, -1);
 }
 
-static inline void __inc_lruvec_state(struct lruvec *lruvec,
-				      enum node_stat_item idx)
-{
-	__mod_lruvec_state(lruvec, idx, 1);
-}
-
-static inline void __dec_lruvec_state(struct lruvec *lruvec,
-				      enum node_stat_item idx)
-{
-	__mod_lruvec_state(lruvec, idx, -1);
-}
-
-static inline void __inc_lruvec_page_state(struct page *page,
-					   enum node_stat_item idx)
-{
-	__mod_lruvec_page_state(page, idx, 1);
-}
-
-static inline void __dec_lruvec_page_state(struct page *page,
-					   enum node_stat_item idx)
-{
-	__mod_lruvec_page_state(page, idx, -1);
-}
-
 static inline void __inc_lruvec_kmem_state(void *p, enum node_stat_item idx)
 {
 	__mod_lruvec_kmem_state(p, idx, 1);
@@ -1370,30 +1283,6 @@ static inline void dec_memcg_page_state(struct page *page,
 	mod_memcg_page_state(page, idx, -1);
 }
 
-static inline void inc_lruvec_state(struct lruvec *lruvec,
-				    enum node_stat_item idx)
-{
-	mod_lruvec_state(lruvec, idx, 1);
-}
-
-static inline void dec_lruvec_state(struct lruvec *lruvec,
-				    enum node_stat_item idx)
-{
-	mod_lruvec_state(lruvec, idx, -1);
-}
-
-static inline void inc_lruvec_page_state(struct page *page,
-					 enum node_stat_item idx)
-{
-	mod_lruvec_page_state(page, idx, 1);
-}
-
-static inline void dec_lruvec_page_state(struct page *page,
-					 enum node_stat_item idx)
-{
-	mod_lruvec_page_state(page, idx, -1);
-}
-
 static inline struct lruvec *parent_lruvec(struct lruvec *lruvec)
 {
 	struct mem_cgroup *memcg;
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 322dcbfcc933..773135fc6e19 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -450,4 +450,108 @@ static inline const char *vm_event_name(enum vm_event_item item)
 }
 #endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */
 
+#ifdef CONFIG_MEMCG
+
+void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
+			int val);
+
+static inline void mod_lruvec_state(struct lruvec *lruvec,
+				    enum node_stat_item idx, int val)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__mod_lruvec_state(lruvec, idx, val);
+	local_irq_restore(flags);
+}
+
+void __mod_lruvec_page_state(struct page *page,
+			     enum node_stat_item idx, int val);
+
+static inline void mod_lruvec_page_state(struct page *page,
+					 enum node_stat_item idx, int val)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__mod_lruvec_page_state(page, idx, val);
+	local_irq_restore(flags);
+}
+
+#else
+
+static inline void __mod_lruvec_state(struct lruvec *lruvec,
+				      enum node_stat_item idx, int val)
+{
+	__mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
+}
+
+static inline void mod_lruvec_state(struct lruvec *lruvec,
+				    enum node_stat_item idx, int val)
+{
+	mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
+}
+
+static inline void __mod_lruvec_page_state(struct page *page,
+					   enum node_stat_item idx, int val)
+{
+	__mod_node_page_state(page_pgdat(page), idx, val);
+}
+
+static inline void mod_lruvec_page_state(struct page *page,
+					 enum node_stat_item idx, int val)
+{
+	mod_node_page_state(page_pgdat(page), idx, val);
+}
+
+#endif /* CONFIG_MEMCG */
+
+static inline void __inc_lruvec_state(struct lruvec *lruvec,
+				      enum node_stat_item idx)
+{
+	__mod_lruvec_state(lruvec, idx, 1);
+}
+
+static inline void __dec_lruvec_state(struct lruvec *lruvec,
+				      enum node_stat_item idx)
+{
+	__mod_lruvec_state(lruvec, idx, -1);
+}
+
+static inline void __inc_lruvec_page_state(struct page *page,
+					   enum node_stat_item idx)
+{
+	__mod_lruvec_page_state(page, idx, 1);
+}
+
+static inline void __dec_lruvec_page_state(struct page *page,
+					   enum node_stat_item idx)
+{
+	__mod_lruvec_page_state(page, idx, -1);
+}
+
+static inline void inc_lruvec_state(struct lruvec *lruvec,
+				    enum node_stat_item idx)
+{
+	mod_lruvec_state(lruvec, idx, 1);
+}
+
+static inline void dec_lruvec_state(struct lruvec *lruvec,
+				    enum node_stat_item idx)
+{
+	mod_lruvec_state(lruvec, idx, -1);
+}
+
+static inline void inc_lruvec_page_state(struct page *page,
+					 enum node_stat_item idx)
+{
+	mod_lruvec_page_state(page, idx, 1);
+}
+
+static inline void dec_lruvec_page_state(struct page *page,
+					 enum node_stat_item idx)
+{
+	mod_lruvec_page_state(page, idx, -1);
+}
+
 #endif /* _LINUX_VMSTAT_H */
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 0083b69b5cac..52837d68bbec 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -853,6 +853,23 @@ void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 		__mod_memcg_lruvec_state(lruvec, idx, val);
 }
 
+void __mod_lruvec_page_state(struct page *page, enum node_stat_item idx,
+			     int val)
+{
+	struct page *head = compound_head(page); /* rmap on tail pages */
+	pg_data_t *pgdat = page_pgdat(page);
+	struct lruvec *lruvec;
+
+	/* Untracked pages have no memcg, no lruvec. Update only the node */
+	if (!head->mem_cgroup) {
+		__mod_node_page_state(pgdat, idx, val);
+		return;
+	}
+
+	lruvec = mem_cgroup_lruvec(head->mem_cgroup, pgdat);
+	__mod_lruvec_state(lruvec, idx, val);
+}
+
 void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val)
 {
 	pg_data_t *pgdat = page_pgdat(virt_to_page(p));
-- 
cgit v1.2.3


From f0c0c115fb81940f4dba0644ac2a8a43b39c83f3 Mon Sep 17 00:00:00 2001
From: Shakeel Butt <shakeelb@google.com>
Date: Mon, 14 Dec 2020 19:07:17 -0800
Subject: mm: memcontrol: account pagetables per node

For many workloads, pagetable consumption is significant and it makes
sense to expose it in the memory.stat for the memory cgroups.  However at
the moment, the pagetables are accounted per-zone.  Converting them to
per-node and using the right interface will correctly account for the
memory cgroups as well.

[akpm@linux-foundation.org: export __mod_lruvec_page_state to modules for arch/mips/kvm/]

Link: https://lkml.kernel.org/r/20201130212541.2781790-3-shakeelb@google.com
Signed-off-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Roman Gushchin <guro@fb.com>
Cc: Michal Hocko <mhocko@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/admin-guide/cgroup-v2.rst | 3 +++
 arch/nds32/mm/mm-nds32.c                | 6 +++---
 drivers/base/node.c                     | 2 +-
 fs/proc/meminfo.c                       | 2 +-
 include/linux/mm.h                      | 8 ++++----
 include/linux/mmzone.h                  | 2 +-
 mm/memcontrol.c                         | 2 ++
 mm/page_alloc.c                         | 6 +++---
 mm/vmstat.c                             | 2 +-
 9 files changed, 19 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 515bb13084a0..63521cd36ce5 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1274,6 +1274,9 @@ PAGE_SIZE multiple when read back.
 	  kernel_stack
 		Amount of memory allocated to kernel stacks.
 
+	  pagetables
+                Amount of memory allocated for page tables.
+
 	  percpu(npn)
 		Amount of memory used for storing per-cpu kernel
 		data structures.
diff --git a/arch/nds32/mm/mm-nds32.c b/arch/nds32/mm/mm-nds32.c
index 55bec50ccc03..f2778f2b39f6 100644
--- a/arch/nds32/mm/mm-nds32.c
+++ b/arch/nds32/mm/mm-nds32.c
@@ -34,8 +34,8 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 	cpu_dcache_wb_range((unsigned long)new_pgd,
 			    (unsigned long)new_pgd +
 			    PTRS_PER_PGD * sizeof(pgd_t));
-	inc_zone_page_state(virt_to_page((unsigned long *)new_pgd),
-			    NR_PAGETABLE);
+	inc_lruvec_page_state(virt_to_page((unsigned long *)new_pgd),
+			      NR_PAGETABLE);
 
 	return new_pgd;
 }
@@ -59,7 +59,7 @@ void pgd_free(struct mm_struct *mm, pgd_t * pgd)
 
 	pte = pmd_page(*pmd);
 	pmd_clear(pmd);
-	dec_zone_page_state(virt_to_page((unsigned long *)pgd), NR_PAGETABLE);
+	dec_lruvec_page_state(virt_to_page((unsigned long *)pgd), NR_PAGETABLE);
 	pte_free(mm, pte);
 	mm_dec_nr_ptes(mm);
 	pmd_free(mm, pmd);
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 6ffa470e2984..04f71c7bc3f8 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -450,7 +450,7 @@ static ssize_t node_read_meminfo(struct device *dev,
 #ifdef CONFIG_SHADOW_CALL_STACK
 			     nid, node_page_state(pgdat, NR_KERNEL_SCS_KB),
 #endif
-			     nid, K(sum_zone_node_page_state(nid, NR_PAGETABLE)),
+			     nid, K(node_page_state(pgdat, NR_PAGETABLE)),
 			     nid, 0UL,
 			     nid, K(sum_zone_node_page_state(nid, NR_BOUNCE)),
 			     nid, K(node_page_state(pgdat, NR_WRITEBACK_TEMP)),
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 887a5532e449..d6fc74619625 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -107,7 +107,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 		   global_node_page_state(NR_KERNEL_SCS_KB));
 #endif
 	show_val_kb(m, "PageTables:     ",
-		    global_zone_page_state(NR_PAGETABLE));
+		    global_node_page_state(NR_PAGETABLE));
 
 	show_val_kb(m, "NFS_Unstable:   ", 0);
 	show_val_kb(m, "Bounce:         ",
diff --git a/include/linux/mm.h b/include/linux/mm.h
index db6ae4d3fb4e..5bbbf4aeee94 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2203,7 +2203,7 @@ static inline bool pgtable_pte_page_ctor(struct page *page)
 	if (!ptlock_init(page))
 		return false;
 	__SetPageTable(page);
-	inc_zone_page_state(page, NR_PAGETABLE);
+	inc_lruvec_page_state(page, NR_PAGETABLE);
 	return true;
 }
 
@@ -2211,7 +2211,7 @@ static inline void pgtable_pte_page_dtor(struct page *page)
 {
 	ptlock_free(page);
 	__ClearPageTable(page);
-	dec_zone_page_state(page, NR_PAGETABLE);
+	dec_lruvec_page_state(page, NR_PAGETABLE);
 }
 
 #define pte_offset_map_lock(mm, pmd, address, ptlp)	\
@@ -2298,7 +2298,7 @@ static inline bool pgtable_pmd_page_ctor(struct page *page)
 	if (!pmd_ptlock_init(page))
 		return false;
 	__SetPageTable(page);
-	inc_zone_page_state(page, NR_PAGETABLE);
+	inc_lruvec_page_state(page, NR_PAGETABLE);
 	return true;
 }
 
@@ -2306,7 +2306,7 @@ static inline void pgtable_pmd_page_dtor(struct page *page)
 {
 	pmd_ptlock_free(page);
 	__ClearPageTable(page);
-	dec_zone_page_state(page, NR_PAGETABLE);
+	dec_lruvec_page_state(page, NR_PAGETABLE);
 }
 
 /*
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index fb3bf696c05e..cca2a4443c9c 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -152,7 +152,6 @@ enum zone_stat_item {
 	NR_ZONE_UNEVICTABLE,
 	NR_ZONE_WRITE_PENDING,	/* Count of dirty, writeback and unstable pages */
 	NR_MLOCK,		/* mlock()ed pages found and moved off LRU */
-	NR_PAGETABLE,		/* used for pagetables */
 	/* Second 128 byte cacheline */
 	NR_BOUNCE,
 #if IS_ENABLED(CONFIG_ZSMALLOC)
@@ -207,6 +206,7 @@ enum node_stat_item {
 #if IS_ENABLED(CONFIG_SHADOW_CALL_STACK)
 	NR_KERNEL_SCS_KB,	/* measured in KiB */
 #endif
+	NR_PAGETABLE,		/* used for pagetables */
 	NR_VM_NODE_STAT_ITEMS
 };
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 52837d68bbec..b9419a3605eb 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -869,6 +869,7 @@ void __mod_lruvec_page_state(struct page *page, enum node_stat_item idx,
 	lruvec = mem_cgroup_lruvec(head->mem_cgroup, pgdat);
 	__mod_lruvec_state(lruvec, idx, val);
 }
+EXPORT_SYMBOL(__mod_lruvec_page_state);
 
 void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val)
 {
@@ -1493,6 +1494,7 @@ static struct memory_stat memory_stats[] = {
 	{ "anon", PAGE_SIZE, NR_ANON_MAPPED },
 	{ "file", PAGE_SIZE, NR_FILE_PAGES },
 	{ "kernel_stack", 1024, NR_KERNEL_STACK_KB },
+	{ "pagetables", PAGE_SIZE, NR_PAGETABLE },
 	{ "percpu", 1, MEMCG_PERCPU_B },
 	{ "sock", PAGE_SIZE, MEMCG_SOCK },
 	{ "shmem", PAGE_SIZE, NR_SHMEM },
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index eaa227a479e4..743fb2bccecc 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5465,7 +5465,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
 		global_node_page_state_pages(NR_SLAB_UNRECLAIMABLE_B),
 		global_node_page_state(NR_FILE_MAPPED),
 		global_node_page_state(NR_SHMEM),
-		global_zone_page_state(NR_PAGETABLE),
+		global_node_page_state(NR_PAGETABLE),
 		global_zone_page_state(NR_BOUNCE),
 		global_zone_page_state(NR_FREE_PAGES),
 		free_pcp,
@@ -5497,6 +5497,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
 #ifdef CONFIG_SHADOW_CALL_STACK
 			" shadow_call_stack:%lukB"
 #endif
+			" pagetables:%lukB"
 			" all_unreclaimable? %s"
 			"\n",
 			pgdat->node_id,
@@ -5522,6 +5523,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
 #ifdef CONFIG_SHADOW_CALL_STACK
 			node_page_state(pgdat, NR_KERNEL_SCS_KB),
 #endif
+			K(node_page_state(pgdat, NR_PAGETABLE)),
 			pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES ?
 				"yes" : "no");
 	}
@@ -5553,7 +5555,6 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
 			" present:%lukB"
 			" managed:%lukB"
 			" mlocked:%lukB"
-			" pagetables:%lukB"
 			" bounce:%lukB"
 			" free_pcp:%lukB"
 			" local_pcp:%ukB"
@@ -5574,7 +5575,6 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
 			K(zone->present_pages),
 			K(zone_managed_pages(zone)),
 			K(zone_page_state(zone, NR_MLOCK)),
-			K(zone_page_state(zone, NR_PAGETABLE)),
 			K(zone_page_state(zone, NR_BOUNCE)),
 			K(free_pcp),
 			K(this_cpu_read(zone->pageset->pcp.count)),
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 698bc0bc18d1..da36e3b0aab2 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1157,7 +1157,6 @@ const char * const vmstat_text[] = {
 	"nr_zone_unevictable",
 	"nr_zone_write_pending",
 	"nr_mlock",
-	"nr_page_table_pages",
 	"nr_bounce",
 #if IS_ENABLED(CONFIG_ZSMALLOC)
 	"nr_zspages",
@@ -1215,6 +1214,7 @@ const char * const vmstat_text[] = {
 #if IS_ENABLED(CONFIG_SHADOW_CALL_STACK)
 	"nr_shadow_call_stack",
 #endif
+	"nr_page_table_pages",
 
 	/* enum writeback_stat_item counters */
 	"nr_dirty_threshold",
-- 
cgit v1.2.3


From d3f5ffcacd1528736471bc78f03f06da6c4551cc Mon Sep 17 00:00:00 2001
From: John Hubbard <jhubbard@nvidia.com>
Date: Mon, 14 Dec 2020 19:07:45 -0800
Subject: mm: cleanup: remove unused tsk arg from __access_remote_vm

Despite a comment that said that page fault accounting would be charged to
whatever task_struct* was passed into __access_remote_vm(), the tsk
argument was actually unused.

Making page fault accounting actually use this task struct is quite a
project, so there is no point in keeping the tsk argument.

Delete both the comment, and the argument.

[rppt@linux.ibm.com: changelog addition]

Link: https://lkml.kernel.org/r/20201026074137.4147787-1-jhubbard@nvidia.com
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h |  4 ++--
 kernel/ptrace.c    |  2 +-
 mm/memory.c        | 11 +++++------
 mm/nommu.c         |  8 ++++----
 4 files changed, 12 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 5bbbf4aeee94..1d8e84bf718a 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1716,8 +1716,8 @@ extern int access_process_vm(struct task_struct *tsk, unsigned long addr,
 		void *buf, int len, unsigned int gup_flags);
 extern int access_remote_vm(struct mm_struct *mm, unsigned long addr,
 		void *buf, int len, unsigned int gup_flags);
-extern int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
-		unsigned long addr, void *buf, int len, unsigned int gup_flags);
+extern int __access_remote_vm(struct mm_struct *mm, unsigned long addr,
+			      void *buf, int len, unsigned int gup_flags);
 
 long get_user_pages_remote(struct mm_struct *mm,
 			    unsigned long start, unsigned long nr_pages,
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 79de1294f8eb..a77d25c641e9 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -57,7 +57,7 @@ int ptrace_access_vm(struct task_struct *tsk, unsigned long addr,
 		return 0;
 	}
 
-	ret = __access_remote_vm(tsk, mm, addr, buf, len, gup_flags);
+	ret = __access_remote_vm(mm, addr, buf, len, gup_flags);
 	mmput(mm);
 
 	return ret;
diff --git a/mm/memory.c b/mm/memory.c
index 50632c4366b8..4a42a74a2240 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4885,11 +4885,10 @@ EXPORT_SYMBOL_GPL(generic_access_phys);
 #endif
 
 /*
- * Access another process' address space as given in mm.  If non-NULL, use the
- * given task for page fault accounting.
+ * Access another process' address space as given in mm.
  */
-int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
-		unsigned long addr, void *buf, int len, unsigned int gup_flags)
+int __access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf,
+		       int len, unsigned int gup_flags)
 {
 	struct vm_area_struct *vma;
 	void *old_buf = buf;
@@ -4966,7 +4965,7 @@ int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
 int access_remote_vm(struct mm_struct *mm, unsigned long addr,
 		void *buf, int len, unsigned int gup_flags)
 {
-	return __access_remote_vm(NULL, mm, addr, buf, len, gup_flags);
+	return __access_remote_vm(mm, addr, buf, len, gup_flags);
 }
 
 /*
@@ -4984,7 +4983,7 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr,
 	if (!mm)
 		return 0;
 
-	ret = __access_remote_vm(tsk, mm, addr, buf, len, gup_flags);
+	ret = __access_remote_vm(mm, addr, buf, len, gup_flags);
 
 	mmput(mm);
 
diff --git a/mm/nommu.c b/mm/nommu.c
index 0faf39b32cdb..870fea12823e 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1675,8 +1675,8 @@ void filemap_map_pages(struct vm_fault *vmf,
 }
 EXPORT_SYMBOL(filemap_map_pages);
 
-int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
-		unsigned long addr, void *buf, int len, unsigned int gup_flags)
+int __access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf,
+		       int len, unsigned int gup_flags)
 {
 	struct vm_area_struct *vma;
 	int write = gup_flags & FOLL_WRITE;
@@ -1722,7 +1722,7 @@ int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
 int access_remote_vm(struct mm_struct *mm, unsigned long addr,
 		void *buf, int len, unsigned int gup_flags)
 {
-	return __access_remote_vm(NULL, mm, addr, buf, len, gup_flags);
+	return __access_remote_vm(mm, addr, buf, len, gup_flags);
 }
 
 /*
@@ -1741,7 +1741,7 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, in
 	if (!mm)
 		return 0;
 
-	len = __access_remote_vm(tsk, mm, addr, buf, len, gup_flags);
+	len = __access_remote_vm(mm, addr, buf, len, gup_flags);
 
 	mmput(mm);
 	return len;
-- 
cgit v1.2.3


From 2b5067a8143e34aa3fa57a20fb8a3c40d905f942 Mon Sep 17 00:00:00 2001
From: Axel Rasmussen <axelrasmussen@google.com>
Date: Mon, 14 Dec 2020 19:07:55 -0800
Subject: mm: mmap_lock: add tracepoints around lock acquisition

The goal of these tracepoints is to be able to debug lock contention
issues.  This lock is acquired on most (all?) mmap / munmap / page fault
operations, so a multi-threaded process which does a lot of these can
experience significant contention.

We trace just before we start acquisition, when the acquisition returns
(whether it succeeded or not), and when the lock is released (or
downgraded).  The events are broken out by lock type (read / write).

The events are also broken out by memcg path.  For container-based
workloads, users often think of several processes in a memcg as a single
logical "task", so collecting statistics at this level is useful.

The end goal is to get latency information.  This isn't directly included
in the trace events.  Instead, users are expected to compute the time
between "start locking" and "acquire returned", using e.g.  synthetic
events or BPF.  The benefit we get from this is simpler code.

Because we use tracepoint_enabled() to decide whether or not to trace,
this patch has effectively no overhead unless tracepoints are enabled at
runtime.  If tracepoints are enabled, there is a performance impact, but
how much depends on exactly what e.g.  the BPF program does.

[axelrasmussen@google.com: fix use-after-free race and css ref leak in tracepoints]
  Link: https://lkml.kernel.org/r/20201130233504.3725241-1-axelrasmussen@google.com
[axelrasmussen@google.com: v3]
  Link: https://lkml.kernel.org/r/20201207213358.573750-1-axelrasmussen@google.com
[rostedt@goodmis.org: in-depth examples of tracepoint_enabled() usage, and per-cpu-per-context buffer design]

Link: https://lkml.kernel.org/r/20201105211739.568279-2-axelrasmussen@google.com
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: Jann Horn <jannh@google.com>
Cc: Chinwen Chang <chinwen.chang@mediatek.com>
Cc: Davidlohr Bueso <dbueso@suse.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Laurent Dufour <ldufour@linux.ibm.com>
Cc: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmap_lock.h        |  94 +++++++++++++++-
 include/trace/events/mmap_lock.h | 107 ++++++++++++++++++
 mm/Makefile                      |   2 +-
 mm/mmap_lock.c                   | 230 +++++++++++++++++++++++++++++++++++++++
 4 files changed, 427 insertions(+), 6 deletions(-)
 create mode 100644 include/trace/events/mmap_lock.h
 create mode 100644 mm/mmap_lock.c

(limited to 'include/linux')

diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h
index 18e7eae9b5ba..0540f0156f58 100644
--- a/include/linux/mmap_lock.h
+++ b/include/linux/mmap_lock.h
@@ -1,11 +1,65 @@
 #ifndef _LINUX_MMAP_LOCK_H
 #define _LINUX_MMAP_LOCK_H
 
+#include <linux/lockdep.h>
+#include <linux/mm_types.h>
 #include <linux/mmdebug.h>
+#include <linux/rwsem.h>
+#include <linux/tracepoint-defs.h>
+#include <linux/types.h>
 
 #define MMAP_LOCK_INITIALIZER(name) \
 	.mmap_lock = __RWSEM_INITIALIZER((name).mmap_lock),
 
+DECLARE_TRACEPOINT(mmap_lock_start_locking);
+DECLARE_TRACEPOINT(mmap_lock_acquire_returned);
+DECLARE_TRACEPOINT(mmap_lock_released);
+
+#ifdef CONFIG_TRACING
+
+void __mmap_lock_do_trace_start_locking(struct mm_struct *mm, bool write);
+void __mmap_lock_do_trace_acquire_returned(struct mm_struct *mm, bool write,
+					   bool success);
+void __mmap_lock_do_trace_released(struct mm_struct *mm, bool write);
+
+static inline void __mmap_lock_trace_start_locking(struct mm_struct *mm,
+						   bool write)
+{
+	if (tracepoint_enabled(mmap_lock_start_locking))
+		__mmap_lock_do_trace_start_locking(mm, write);
+}
+
+static inline void __mmap_lock_trace_acquire_returned(struct mm_struct *mm,
+						      bool write, bool success)
+{
+	if (tracepoint_enabled(mmap_lock_acquire_returned))
+		__mmap_lock_do_trace_acquire_returned(mm, write, success);
+}
+
+static inline void __mmap_lock_trace_released(struct mm_struct *mm, bool write)
+{
+	if (tracepoint_enabled(mmap_lock_released))
+		__mmap_lock_do_trace_released(mm, write);
+}
+
+#else /* !CONFIG_TRACING */
+
+static inline void __mmap_lock_trace_start_locking(struct mm_struct *mm,
+						   bool write)
+{
+}
+
+static inline void __mmap_lock_trace_acquire_returned(struct mm_struct *mm,
+						      bool write, bool success)
+{
+}
+
+static inline void __mmap_lock_trace_released(struct mm_struct *mm, bool write)
+{
+}
+
+#endif /* CONFIG_TRACING */
+
 static inline void mmap_init_lock(struct mm_struct *mm)
 {
 	init_rwsem(&mm->mmap_lock);
@@ -13,57 +67,86 @@ static inline void mmap_init_lock(struct mm_struct *mm)
 
 static inline void mmap_write_lock(struct mm_struct *mm)
 {
+	__mmap_lock_trace_start_locking(mm, true);
 	down_write(&mm->mmap_lock);
+	__mmap_lock_trace_acquire_returned(mm, true, true);
 }
 
 static inline void mmap_write_lock_nested(struct mm_struct *mm, int subclass)
 {
+	__mmap_lock_trace_start_locking(mm, true);
 	down_write_nested(&mm->mmap_lock, subclass);
+	__mmap_lock_trace_acquire_returned(mm, true, true);
 }
 
 static inline int mmap_write_lock_killable(struct mm_struct *mm)
 {
-	return down_write_killable(&mm->mmap_lock);
+	int ret;
+
+	__mmap_lock_trace_start_locking(mm, true);
+	ret = down_write_killable(&mm->mmap_lock);
+	__mmap_lock_trace_acquire_returned(mm, true, ret == 0);
+	return ret;
 }
 
 static inline bool mmap_write_trylock(struct mm_struct *mm)
 {
-	return down_write_trylock(&mm->mmap_lock) != 0;
+	bool ret;
+
+	__mmap_lock_trace_start_locking(mm, true);
+	ret = down_write_trylock(&mm->mmap_lock) != 0;
+	__mmap_lock_trace_acquire_returned(mm, true, ret);
+	return ret;
 }
 
 static inline void mmap_write_unlock(struct mm_struct *mm)
 {
 	up_write(&mm->mmap_lock);
+	__mmap_lock_trace_released(mm, true);
 }
 
 static inline void mmap_write_downgrade(struct mm_struct *mm)
 {
 	downgrade_write(&mm->mmap_lock);
+	__mmap_lock_trace_acquire_returned(mm, false, true);
 }
 
 static inline void mmap_read_lock(struct mm_struct *mm)
 {
+	__mmap_lock_trace_start_locking(mm, false);
 	down_read(&mm->mmap_lock);
+	__mmap_lock_trace_acquire_returned(mm, false, true);
 }
 
 static inline int mmap_read_lock_killable(struct mm_struct *mm)
 {
-	return down_read_killable(&mm->mmap_lock);
+	int ret;
+
+	__mmap_lock_trace_start_locking(mm, false);
+	ret = down_read_killable(&mm->mmap_lock);
+	__mmap_lock_trace_acquire_returned(mm, false, ret == 0);
+	return ret;
 }
 
 static inline bool mmap_read_trylock(struct mm_struct *mm)
 {
-	return down_read_trylock(&mm->mmap_lock) != 0;
+	bool ret;
+
+	__mmap_lock_trace_start_locking(mm, false);
+	ret = down_read_trylock(&mm->mmap_lock) != 0;
+	__mmap_lock_trace_acquire_returned(mm, false, ret);
+	return ret;
 }
 
 static inline void mmap_read_unlock(struct mm_struct *mm)
 {
 	up_read(&mm->mmap_lock);
+	__mmap_lock_trace_released(mm, false);
 }
 
 static inline bool mmap_read_trylock_non_owner(struct mm_struct *mm)
 {
-	if (down_read_trylock(&mm->mmap_lock)) {
+	if (mmap_read_trylock(mm)) {
 		rwsem_release(&mm->mmap_lock.dep_map, _RET_IP_);
 		return true;
 	}
@@ -73,6 +156,7 @@ static inline bool mmap_read_trylock_non_owner(struct mm_struct *mm)
 static inline void mmap_read_unlock_non_owner(struct mm_struct *mm)
 {
 	up_read_non_owner(&mm->mmap_lock);
+	__mmap_lock_trace_released(mm, false);
 }
 
 static inline void mmap_assert_locked(struct mm_struct *mm)
diff --git a/include/trace/events/mmap_lock.h b/include/trace/events/mmap_lock.h
new file mode 100644
index 000000000000..0abff67b96f0
--- /dev/null
+++ b/include/trace/events/mmap_lock.h
@@ -0,0 +1,107 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM mmap_lock
+
+#if !defined(_TRACE_MMAP_LOCK_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_MMAP_LOCK_H
+
+#include <linux/tracepoint.h>
+#include <linux/types.h>
+
+struct mm_struct;
+
+extern int trace_mmap_lock_reg(void);
+extern void trace_mmap_lock_unreg(void);
+
+TRACE_EVENT_FN(mmap_lock_start_locking,
+
+	TP_PROTO(struct mm_struct *mm, const char *memcg_path, bool write),
+
+	TP_ARGS(mm, memcg_path, write),
+
+	TP_STRUCT__entry(
+		__field(struct mm_struct *, mm)
+		__string(memcg_path, memcg_path)
+		__field(bool, write)
+	),
+
+	TP_fast_assign(
+		__entry->mm = mm;
+		__assign_str(memcg_path, memcg_path);
+		__entry->write = write;
+	),
+
+	TP_printk(
+		"mm=%p memcg_path=%s write=%s\n",
+		__entry->mm,
+		__get_str(memcg_path),
+		__entry->write ? "true" : "false"
+	),
+
+	trace_mmap_lock_reg, trace_mmap_lock_unreg
+);
+
+TRACE_EVENT_FN(mmap_lock_acquire_returned,
+
+	TP_PROTO(struct mm_struct *mm, const char *memcg_path, bool write,
+		bool success),
+
+	TP_ARGS(mm, memcg_path, write, success),
+
+	TP_STRUCT__entry(
+		__field(struct mm_struct *, mm)
+		__string(memcg_path, memcg_path)
+		__field(bool, write)
+		__field(bool, success)
+	),
+
+	TP_fast_assign(
+		__entry->mm = mm;
+		__assign_str(memcg_path, memcg_path);
+		__entry->write = write;
+		__entry->success = success;
+	),
+
+	TP_printk(
+		"mm=%p memcg_path=%s write=%s success=%s\n",
+		__entry->mm,
+		__get_str(memcg_path),
+		__entry->write ? "true" : "false",
+		__entry->success ? "true" : "false"
+	),
+
+	trace_mmap_lock_reg, trace_mmap_lock_unreg
+);
+
+TRACE_EVENT_FN(mmap_lock_released,
+
+	TP_PROTO(struct mm_struct *mm, const char *memcg_path, bool write),
+
+	TP_ARGS(mm, memcg_path, write),
+
+	TP_STRUCT__entry(
+		__field(struct mm_struct *, mm)
+		__string(memcg_path, memcg_path)
+		__field(bool, write)
+	),
+
+	TP_fast_assign(
+		__entry->mm = mm;
+		__assign_str(memcg_path, memcg_path);
+		__entry->write = write;
+	),
+
+	TP_printk(
+		"mm=%p memcg_path=%s write=%s\n",
+		__entry->mm,
+		__get_str(memcg_path),
+		__entry->write ? "true" : "false"
+	),
+
+	trace_mmap_lock_reg, trace_mmap_lock_unreg
+);
+
+#endif /* _TRACE_MMAP_LOCK_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/mm/Makefile b/mm/Makefile
index 069f216e109e..b6cd2fffa492 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -52,7 +52,7 @@ obj-y			:= filemap.o mempool.o oom_kill.o fadvise.o \
 			   mm_init.o percpu.o slab_common.o \
 			   compaction.o vmacache.o \
 			   interval_tree.o list_lru.o workingset.o \
-			   debug.o gup.o $(mmu-y)
+			   debug.o gup.o mmap_lock.o $(mmu-y)
 
 # Give 'page_alloc' its own module-parameter namespace
 page-alloc-y := page_alloc.o
diff --git a/mm/mmap_lock.c b/mm/mmap_lock.c
new file mode 100644
index 000000000000..dcdde4f722a4
--- /dev/null
+++ b/mm/mmap_lock.c
@@ -0,0 +1,230 @@
+// SPDX-License-Identifier: GPL-2.0
+#define CREATE_TRACE_POINTS
+#include <trace/events/mmap_lock.h>
+
+#include <linux/mm.h>
+#include <linux/cgroup.h>
+#include <linux/memcontrol.h>
+#include <linux/mmap_lock.h>
+#include <linux/mutex.h>
+#include <linux/percpu.h>
+#include <linux/rcupdate.h>
+#include <linux/smp.h>
+#include <linux/trace_events.h>
+
+EXPORT_TRACEPOINT_SYMBOL(mmap_lock_start_locking);
+EXPORT_TRACEPOINT_SYMBOL(mmap_lock_acquire_returned);
+EXPORT_TRACEPOINT_SYMBOL(mmap_lock_released);
+
+#ifdef CONFIG_MEMCG
+
+/*
+ * Our various events all share the same buffer (because we don't want or need
+ * to allocate a set of buffers *per event type*), so we need to protect against
+ * concurrent _reg() and _unreg() calls, and count how many _reg() calls have
+ * been made.
+ */
+static DEFINE_MUTEX(reg_lock);
+static int reg_refcount; /* Protected by reg_lock. */
+
+/*
+ * Size of the buffer for memcg path names. Ignoring stack trace support,
+ * trace_events_hist.c uses MAX_FILTER_STR_VAL for this, so we also use it.
+ */
+#define MEMCG_PATH_BUF_SIZE MAX_FILTER_STR_VAL
+
+/*
+ * How many contexts our trace events might be called in: normal, softirq, irq,
+ * and NMI.
+ */
+#define CONTEXT_COUNT 4
+
+static DEFINE_PER_CPU(char __rcu *, memcg_path_buf);
+static char **tmp_bufs;
+static DEFINE_PER_CPU(int, memcg_path_buf_idx);
+
+/* Called with reg_lock held. */
+static void free_memcg_path_bufs(void)
+{
+	int cpu;
+	char **old = tmp_bufs;
+
+	for_each_possible_cpu(cpu) {
+		*(old++) = rcu_dereference_protected(
+			per_cpu(memcg_path_buf, cpu),
+			lockdep_is_held(&reg_lock));
+		rcu_assign_pointer(per_cpu(memcg_path_buf, cpu), NULL);
+	}
+
+	/* Wait for inflight memcg_path_buf users to finish. */
+	synchronize_rcu();
+
+	old = tmp_bufs;
+	for_each_possible_cpu(cpu) {
+		kfree(*(old++));
+	}
+
+	kfree(tmp_bufs);
+	tmp_bufs = NULL;
+}
+
+int trace_mmap_lock_reg(void)
+{
+	int cpu;
+	char *new;
+
+	mutex_lock(&reg_lock);
+
+	/* If the refcount is going 0->1, proceed with allocating buffers. */
+	if (reg_refcount++)
+		goto out;
+
+	tmp_bufs = kmalloc_array(num_possible_cpus(), sizeof(*tmp_bufs),
+				 GFP_KERNEL);
+	if (tmp_bufs == NULL)
+		goto out_fail;
+
+	for_each_possible_cpu(cpu) {
+		new = kmalloc(MEMCG_PATH_BUF_SIZE * CONTEXT_COUNT, GFP_KERNEL);
+		if (new == NULL)
+			goto out_fail_free;
+		rcu_assign_pointer(per_cpu(memcg_path_buf, cpu), new);
+		/* Don't need to wait for inflights, they'd have gotten NULL. */
+	}
+
+out:
+	mutex_unlock(&reg_lock);
+	return 0;
+
+out_fail_free:
+	free_memcg_path_bufs();
+out_fail:
+	/* Since we failed, undo the earlier ref increment. */
+	--reg_refcount;
+
+	mutex_unlock(&reg_lock);
+	return -ENOMEM;
+}
+
+void trace_mmap_lock_unreg(void)
+{
+	mutex_lock(&reg_lock);
+
+	/* If the refcount is going 1->0, proceed with freeing buffers. */
+	if (--reg_refcount)
+		goto out;
+
+	free_memcg_path_bufs();
+
+out:
+	mutex_unlock(&reg_lock);
+}
+
+static inline char *get_memcg_path_buf(void)
+{
+	char *buf;
+	int idx;
+
+	rcu_read_lock();
+	buf = rcu_dereference(*this_cpu_ptr(&memcg_path_buf));
+	if (buf == NULL) {
+		rcu_read_unlock();
+		return NULL;
+	}
+	idx = this_cpu_add_return(memcg_path_buf_idx, MEMCG_PATH_BUF_SIZE) -
+	      MEMCG_PATH_BUF_SIZE;
+	return &buf[idx];
+}
+
+static inline void put_memcg_path_buf(void)
+{
+	this_cpu_sub(memcg_path_buf_idx, MEMCG_PATH_BUF_SIZE);
+	rcu_read_unlock();
+}
+
+/*
+ * Write the given mm_struct's memcg path to a percpu buffer, and return a
+ * pointer to it. If the path cannot be determined, or no buffer was available
+ * (because the trace event is being unregistered), NULL is returned.
+ *
+ * Note: buffers are allocated per-cpu to avoid locking, so preemption must be
+ * disabled by the caller before calling us, and re-enabled only after the
+ * caller is done with the pointer.
+ *
+ * The caller must call put_memcg_path_buf() once the buffer is no longer
+ * needed. This must be done while preemption is still disabled.
+ */
+static const char *get_mm_memcg_path(struct mm_struct *mm)
+{
+	char *buf = NULL;
+	struct mem_cgroup *memcg = get_mem_cgroup_from_mm(mm);
+
+	if (memcg == NULL)
+		goto out;
+	if (unlikely(memcg->css.cgroup == NULL))
+		goto out_put;
+
+	buf = get_memcg_path_buf();
+	if (buf == NULL)
+		goto out_put;
+
+	cgroup_path(memcg->css.cgroup, buf, MEMCG_PATH_BUF_SIZE);
+
+out_put:
+	css_put(&memcg->css);
+out:
+	return buf;
+}
+
+#define TRACE_MMAP_LOCK_EVENT(type, mm, ...)                                   \
+	do {                                                                   \
+		const char *memcg_path;                                        \
+		preempt_disable();                                             \
+		memcg_path = get_mm_memcg_path(mm);                            \
+		trace_mmap_lock_##type(mm,                                     \
+				       memcg_path != NULL ? memcg_path : "",   \
+				       ##__VA_ARGS__);                         \
+		if (likely(memcg_path != NULL))                                \
+			put_memcg_path_buf();                                  \
+		preempt_enable();                                              \
+	} while (0)
+
+#else /* !CONFIG_MEMCG */
+
+int trace_mmap_lock_reg(void)
+{
+	return 0;
+}
+
+void trace_mmap_lock_unreg(void)
+{
+}
+
+#define TRACE_MMAP_LOCK_EVENT(type, mm, ...)                                   \
+	trace_mmap_lock_##type(mm, "", ##__VA_ARGS__)
+
+#endif /* CONFIG_MEMCG */
+
+/*
+ * Trace calls must be in a separate file, as otherwise there's a circular
+ * dependency between linux/mmap_lock.h and trace/events/mmap_lock.h.
+ */
+
+void __mmap_lock_do_trace_start_locking(struct mm_struct *mm, bool write)
+{
+	TRACE_MMAP_LOCK_EVENT(start_locking, mm, write);
+}
+EXPORT_SYMBOL(__mmap_lock_do_trace_start_locking);
+
+void __mmap_lock_do_trace_acquire_returned(struct mm_struct *mm, bool write,
+					   bool success)
+{
+	TRACE_MMAP_LOCK_EVENT(acquire_returned, mm, write, success);
+}
+EXPORT_SYMBOL(__mmap_lock_do_trace_acquire_returned);
+
+void __mmap_lock_do_trace_released(struct mm_struct *mm, bool write)
+{
+	TRACE_MMAP_LOCK_EVENT(released, mm, write);
+}
+EXPORT_SYMBOL(__mmap_lock_do_trace_released);
-- 
cgit v1.2.3


From 0966aeb404e854e3377a10fcd01be46f19055bc6 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Mon, 14 Dec 2020 19:08:02 -0800
Subject: mm: move free_unref_page to mm/internal.h

Code outside mm/ should not be calling free_unref_page().  Also move
free_unref_page_list().

Link: https://lkml.kernel.org/r/20201125034655.27687-2-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/gfp.h | 2 --
 mm/internal.h       | 3 +++
 2 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index c603237e006c..6e479e9c48ce 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -580,8 +580,6 @@ void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask);
 
 extern void __free_pages(struct page *page, unsigned int order);
 extern void free_pages(unsigned long addr, unsigned int order);
-extern void free_unref_page(struct page *page);
-extern void free_unref_page_list(struct list_head *list);
 
 struct page_frag_cache;
 extern void __page_frag_cache_drain(struct page *page, unsigned int count);
diff --git a/mm/internal.h b/mm/internal.h
index c43ccdddb0f6..fd6734be9c85 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -199,6 +199,9 @@ extern void post_alloc_hook(struct page *page, unsigned int order,
 					gfp_t gfp_flags);
 extern int user_min_free_kbytes;
 
+extern void free_unref_page(struct page *page);
+extern void free_unref_page_list(struct list_head *list);
+
 extern void zone_pcp_update(struct zone *zone);
 extern void zone_pcp_reset(struct zone *zone);
 
-- 
cgit v1.2.3


From cd544fd1dc9293c6702fab6effa63dac1cc67e99 Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <dima@arista.com>
Date: Mon, 14 Dec 2020 19:08:13 -0800
Subject: mremap: don't allow MREMAP_DONTUNMAP on special_mappings and aio

As kernel expect to see only one of such mappings, any further operations
on the VMA-copy may be unexpected by the kernel.  Maybe it's being on the
safe side, but there doesn't seem to be any expected use-case for this, so
restrict it now.

Link: https://lkml.kernel.org/r/20201013013416.390574-4-dima@arista.com
Fixes: commit e346b3813067 ("mm/mremap: add MREMAP_DONTUNMAP to mremap()")
Signed-off-by: Dmitry Safonov <dima@arista.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Brian Geffon <bgeffon@google.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dan Carpenter <dan.carpenter@oracle.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c | 2 +-
 fs/aio.c                                  | 5 ++++-
 include/linux/mm.h                        | 2 +-
 mm/mmap.c                                 | 6 +++++-
 mm/mremap.c                               | 2 +-
 5 files changed, 12 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
index 0daf2f1cf7a8..e916646adc69 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
@@ -1458,7 +1458,7 @@ static int pseudo_lock_dev_release(struct inode *inode, struct file *filp)
 	return 0;
 }
 
-static int pseudo_lock_dev_mremap(struct vm_area_struct *area)
+static int pseudo_lock_dev_mremap(struct vm_area_struct *area, unsigned long flags)
 {
 	/* Not supported */
 	return -EINVAL;
diff --git a/fs/aio.c b/fs/aio.c
index 6a21d8919409..fd2d68532506 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -324,13 +324,16 @@ static void aio_free_ring(struct kioctx *ctx)
 	}
 }
 
-static int aio_ring_mremap(struct vm_area_struct *vma)
+static int aio_ring_mremap(struct vm_area_struct *vma, unsigned long flags)
 {
 	struct file *file = vma->vm_file;
 	struct mm_struct *mm = vma->vm_mm;
 	struct kioctx_table *table;
 	int i, res = -EINVAL;
 
+	if (flags & MREMAP_DONTUNMAP)
+		return -EINVAL;
+
 	spin_lock(&mm->ioctx_lock);
 	rcu_read_lock();
 	table = rcu_dereference(mm->ioctx_table);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 1d8e84bf718a..dacc889744b1 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -558,7 +558,7 @@ struct vm_operations_struct {
 	void (*open)(struct vm_area_struct * area);
 	void (*close)(struct vm_area_struct * area);
 	int (*split)(struct vm_area_struct * area, unsigned long addr);
-	int (*mremap)(struct vm_area_struct * area);
+	int (*mremap)(struct vm_area_struct *area, unsigned long flags);
 	vm_fault_t (*fault)(struct vm_fault *vmf);
 	vm_fault_t (*huge_fault)(struct vm_fault *vmf,
 			enum page_entry_size pe_size);
diff --git a/mm/mmap.c b/mm/mmap.c
index 5c8b4485860d..8950c20239a0 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -3405,10 +3405,14 @@ static const char *special_mapping_name(struct vm_area_struct *vma)
 	return ((struct vm_special_mapping *)vma->vm_private_data)->name;
 }
 
-static int special_mapping_mremap(struct vm_area_struct *new_vma)
+static int special_mapping_mremap(struct vm_area_struct *new_vma,
+				  unsigned long flags)
 {
 	struct vm_special_mapping *sm = new_vma->vm_private_data;
 
+	if (flags & MREMAP_DONTUNMAP)
+		return -EINVAL;
+
 	if (WARN_ON_ONCE(current->mm != new_vma->vm_mm))
 		return -EFAULT;
 
diff --git a/mm/mremap.c b/mm/mremap.c
index 90ff09c09e84..366b3dea992c 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -534,7 +534,7 @@ static unsigned long move_vma(struct vm_area_struct *vma,
 	if (moved_len < old_len) {
 		err = -ENOMEM;
 	} else if (vma->vm_ops && vma->vm_ops->mremap) {
-		err = vma->vm_ops->mremap(new_vma);
+		err = vma->vm_ops->mremap(new_vma, flags);
 	}
 
 	if (unlikely(err)) {
-- 
cgit v1.2.3


From dd3b614f858d88f33e0cf8b7353e2ad937e71da3 Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <dima@arista.com>
Date: Mon, 14 Dec 2020 19:08:17 -0800
Subject: vm_ops: rename .split() callback to .may_split()

Rename the callback to reflect that it's not called *on* or *after* split,
but rather some time before the splitting to check if it's possible.

Link: https://lkml.kernel.org/r/20201013013416.390574-5-dima@arista.com
Signed-off-by: Dmitry Safonov <dima@arista.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Brian Geffon <bgeffon@google.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dan Carpenter <dan.carpenter@oracle.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/dax/device.c | 4 ++--
 include/linux/mm.h   | 3 ++-
 ipc/shm.c            | 8 ++++----
 mm/hugetlb.c         | 2 +-
 mm/mmap.c            | 4 ++--
 5 files changed, 11 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/dax/device.c b/drivers/dax/device.c
index 25e0b84a4296..5da2980bb16b 100644
--- a/drivers/dax/device.c
+++ b/drivers/dax/device.c
@@ -256,7 +256,7 @@ static vm_fault_t dev_dax_fault(struct vm_fault *vmf)
 	return dev_dax_huge_fault(vmf, PE_SIZE_PTE);
 }
 
-static int dev_dax_split(struct vm_area_struct *vma, unsigned long addr)
+static int dev_dax_may_split(struct vm_area_struct *vma, unsigned long addr)
 {
 	struct file *filp = vma->vm_file;
 	struct dev_dax *dev_dax = filp->private_data;
@@ -277,7 +277,7 @@ static unsigned long dev_dax_pagesize(struct vm_area_struct *vma)
 static const struct vm_operations_struct dax_vm_ops = {
 	.fault = dev_dax_fault,
 	.huge_fault = dev_dax_huge_fault,
-	.split = dev_dax_split,
+	.may_split = dev_dax_may_split,
 	.pagesize = dev_dax_pagesize,
 };
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index dacc889744b1..5d188b8611dc 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -557,7 +557,8 @@ enum page_entry_size {
 struct vm_operations_struct {
 	void (*open)(struct vm_area_struct * area);
 	void (*close)(struct vm_area_struct * area);
-	int (*split)(struct vm_area_struct * area, unsigned long addr);
+	/* Called any time before splitting to check if it's allowed */
+	int (*may_split)(struct vm_area_struct *area, unsigned long addr);
 	int (*mremap)(struct vm_area_struct *area, unsigned long flags);
 	vm_fault_t (*fault)(struct vm_fault *vmf);
 	vm_fault_t (*huge_fault)(struct vm_fault *vmf,
diff --git a/ipc/shm.c b/ipc/shm.c
index e25c7c6106bc..febd88daba8c 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -434,13 +434,13 @@ static vm_fault_t shm_fault(struct vm_fault *vmf)
 	return sfd->vm_ops->fault(vmf);
 }
 
-static int shm_split(struct vm_area_struct *vma, unsigned long addr)
+static int shm_may_split(struct vm_area_struct *vma, unsigned long addr)
 {
 	struct file *file = vma->vm_file;
 	struct shm_file_data *sfd = shm_file_data(file);
 
-	if (sfd->vm_ops->split)
-		return sfd->vm_ops->split(vma, addr);
+	if (sfd->vm_ops->may_split)
+		return sfd->vm_ops->may_split(vma, addr);
 
 	return 0;
 }
@@ -582,7 +582,7 @@ static const struct vm_operations_struct shm_vm_ops = {
 	.open	= shm_open,	/* callback for a new vm-area open */
 	.close	= shm_close,	/* callback for when the vm-area is released */
 	.fault	= shm_fault,
-	.split	= shm_split,
+	.may_split = shm_may_split,
 	.pagesize = shm_pagesize,
 #if defined(CONFIG_NUMA)
 	.set_policy = shm_set_policy,
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index d029d938d26d..4b809cc7a3fd 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3673,7 +3673,7 @@ const struct vm_operations_struct hugetlb_vm_ops = {
 	.fault = hugetlb_vm_op_fault,
 	.open = hugetlb_vm_op_open,
 	.close = hugetlb_vm_op_close,
-	.split = hugetlb_vm_op_split,
+	.may_split = hugetlb_vm_op_split,
 	.pagesize = hugetlb_vm_op_pagesize,
 };
 
diff --git a/mm/mmap.c b/mm/mmap.c
index 8950c20239a0..886de799e7d2 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2731,8 +2731,8 @@ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
 	struct vm_area_struct *new;
 	int err;
 
-	if (vma->vm_ops && vma->vm_ops->split) {
-		err = vma->vm_ops->split(vma, addr);
+	if (vma->vm_ops && vma->vm_ops->may_split) {
+		err = vma->vm_ops->may_split(vma, addr);
 		if (err)
 			return err;
 	}
-- 
cgit v1.2.3


From 95d6c701f4ca7c44dc148d664f604541266a2333 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Mon, 14 Dec 2020 19:08:34 -0800
Subject: mm: extract might_alloc() debug check
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Extracted from slab.h, which seems to have the most complete version
including the correct might_sleep() check.  Roll it out to slob.c.

Motivated by a discussion with Paul about possibly changing call_rcu
behaviour to allocate memory, but only roughly every 500th call.

There are a lot fewer places in the kernel that care about whether
allocating memory is allowed or not (due to deadlocks with reclaim code)
than places that care whether sleeping is allowed.  But debugging these
also tends to be a lot harder, so nice descriptive checks could come in
handy.  I might have some use eventually for annotations in drivers/gpu.

Note that unlike fs_reclaim_acquire/release gfpflags_allow_blocking does
not consult the PF_MEMALLOC flags.  But there is no flag equivalent for
GFP_NOWAIT, hence this check can't go wrong due to
memalloc_no*_save/restore contexts.  Willy is working on a patch series
which might change this:

https://lore.kernel.org/linux-mm/20200625113122.7540-7-willy@infradead.org/

I think best would be if that updates gfpflags_allow_blocking(), since
there's a ton of callers all over the place for that already.

Link: https://lkml.kernel.org/r/20201125162532.1299794-3-daniel.vetter@ffwll.ch
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Paul E. McKenney <paulmck@kernel.org>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Paul E. McKenney <paulmck@kernel.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Michel Lespinasse <walken@google.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Waiman Long <longman@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Qian Cai <cai@lca.pw>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Christian König <christian.koenig@amd.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Thomas Hellström (Intel) <thomas_os@shipmail.org>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/sched/mm.h | 16 ++++++++++++++++
 mm/slab.h                |  5 +----
 mm/slob.c                |  6 ++----
 3 files changed, 19 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index d5ece7a9a403..a11a61b5226f 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -180,6 +180,22 @@ static inline void fs_reclaim_acquire(gfp_t gfp_mask) { }
 static inline void fs_reclaim_release(gfp_t gfp_mask) { }
 #endif
 
+/**
+ * might_alloc - Mark possible allocation sites
+ * @gfp_mask: gfp_t flags that would be used to allocate
+ *
+ * Similar to might_sleep() and other annotations, this can be used in functions
+ * that might allocate, but often don't. Compiles to nothing without
+ * CONFIG_LOCKDEP. Includes a conditional might_sleep() if @gfp allows blocking.
+ */
+static inline void might_alloc(gfp_t gfp_mask)
+{
+	fs_reclaim_acquire(gfp_mask);
+	fs_reclaim_release(gfp_mask);
+
+	might_sleep_if(gfpflags_allow_blocking(gfp_mask));
+}
+
 /**
  * memalloc_noio_save - Marks implicit GFP_NOIO allocation scope.
  *
diff --git a/mm/slab.h b/mm/slab.h
index 65f4647f1286..54faf9a623f9 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -510,10 +510,7 @@ static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s,
 {
 	flags &= gfp_allowed_mask;
 
-	fs_reclaim_acquire(flags);
-	fs_reclaim_release(flags);
-
-	might_sleep_if(gfpflags_allow_blocking(flags));
+	might_alloc(flags);
 
 	if (should_failslab(s, flags))
 		return NULL;
diff --git a/mm/slob.c b/mm/slob.c
index 7cc9805c8091..8d4bfa46247f 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -474,8 +474,7 @@ __do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller)
 
 	gfp &= gfp_allowed_mask;
 
-	fs_reclaim_acquire(gfp);
-	fs_reclaim_release(gfp);
+	might_alloc(gfp);
 
 	if (size < PAGE_SIZE - minalign) {
 		int align = minalign;
@@ -597,8 +596,7 @@ static void *slob_alloc_node(struct kmem_cache *c, gfp_t flags, int node)
 
 	flags &= gfp_allowed_mask;
 
-	fs_reclaim_acquire(flags);
-	fs_reclaim_release(flags);
+	might_alloc(flags);
 
 	if (c->size < PAGE_SIZE) {
 		b = slob_alloc(c->size, flags, c->align, node, 0);
-- 
cgit v1.2.3


From 96e2db456135db0cf2476b6890f1e8b2fdcf21eb Mon Sep 17 00:00:00 2001
From: "Uladzislau Rezki (Sony)" <urezki@gmail.com>
Date: Mon, 14 Dec 2020 19:08:49 -0800
Subject: mm/vmalloc: rework the drain logic

A current "lazy drain" model suffers from at least two issues.

First one is related to the unsorted list of vmap areas, thus in order to
identify the [min:max] range of areas to be drained, it requires a full
list scan.  What is a time consuming if the list is too long.

Second one and as a next step is about merging all fragments with a free
space.  What is also a time consuming because it has to iterate over
entire list which holds outstanding lazy areas.

See below the "preemptirqsoff" tracer that illustrates a high latency.  It
is ~24676us.  Our workloads like audio and video are effected by such long
latency:

<snip>
  tracer: preemptirqsoff

  preemptirqsoff latency trace v1.1.5 on 4.9.186-perf+
  --------------------------------------------------------------------
  latency: 24676 us, #4/4, CPU#1 | (M:preempt VP:0, KP:0, SP:0 HP:0 P:8)
     -----------------
     | task: crtc_commit:112-261 (uid:0 nice:0 policy:1 rt_prio:16)
     -----------------
   => started at: __purge_vmap_area_lazy
   => ended at:   __purge_vmap_area_lazy

                   _------=> CPU#
                  / _-----=> irqs-off
                 | / _----=> need-resched
                 || / _---=> hardirq/softirq
                 ||| / _--=> preempt-depth
                 |||| /     delay
   cmd     pid   ||||| time  |   caller
      \   /      |||||  \    |   /
crtc_com-261     1...1    1us*: _raw_spin_lock <-__purge_vmap_area_lazy
[...]
crtc_com-261     1...1 24675us : _raw_spin_unlock <-__purge_vmap_area_lazy
crtc_com-261     1...1 24677us : trace_preempt_on <-__purge_vmap_area_lazy
crtc_com-261     1...1 24683us : <stack trace>
 => free_vmap_area_noflush
 => remove_vm_area
 => __vunmap
 => vfree
 => drm_property_free_blob
 => drm_mode_object_unreference
 => drm_property_unreference_blob
 => __drm_atomic_helper_crtc_destroy_state
 => sde_crtc_destroy_state
 => drm_atomic_state_default_clear
 => drm_atomic_state_clear
 => drm_atomic_state_free
 => complete_commit
 => _msm_drm_commit_work_cb
 => kthread_worker_fn
 => kthread
 => ret_from_fork
<snip>

To address those two issues we can redesign a purging of the outstanding
lazy areas.  Instead of queuing vmap areas to the list, we replace it by
the separate rb-tree.  In hat case an area is located in the tree/list in
ascending order.  It will give us below advantages:

a) Outstanding vmap areas are merged creating bigger coalesced blocks,
   thus it becomes less fragmented.

b) It is possible to calculate a flush range [min:max] without scanning
   all elements.  It is O(1) access time or complexity;

c) The final merge of areas with the rb-tree that represents a free
   space is faster because of (a).  As a result the lock contention is
   also reduced.

Link: https://lkml.kernel.org/r/20201116220033.1837-2-urezki@gmail.com
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Cc: Hillf Danton <hdanton@sina.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: huang ying <huang.ying.caritas@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/vmalloc.h |  8 ++---
 mm/vmalloc.c            | 90 +++++++++++++++++++++++++++----------------------
 2 files changed, 53 insertions(+), 45 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 938eaf9517e2..80c0181c411d 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -72,16 +72,14 @@ struct vmap_area {
 	struct list_head list;          /* address sorted list */
 
 	/*
-	 * The following three variables can be packed, because
-	 * a vmap_area object is always one of the three states:
+	 * The following two variables can be packed, because
+	 * a vmap_area object can be either:
 	 *    1) in "free" tree (root is vmap_area_root)
-	 *    2) in "busy" tree (root is free_vmap_area_root)
-	 *    3) in purge list  (head is vmap_purge_list)
+	 *    2) or "busy" tree (root is free_vmap_area_root)
 	 */
 	union {
 		unsigned long subtree_max_size; /* in "free" tree */
 		struct vm_struct *vm;           /* in "busy" tree */
-		struct llist_node purge_list;   /* in purge list */
 	};
 };
 
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index da833c66d625..9bd3298f8c69 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -413,10 +413,13 @@ static DEFINE_SPINLOCK(vmap_area_lock);
 static DEFINE_SPINLOCK(free_vmap_area_lock);
 /* Export for kexec only */
 LIST_HEAD(vmap_area_list);
-static LLIST_HEAD(vmap_purge_list);
 static struct rb_root vmap_area_root = RB_ROOT;
 static bool vmap_initialized __read_mostly;
 
+static struct rb_root purge_vmap_area_root = RB_ROOT;
+static LIST_HEAD(purge_vmap_area_list);
+static DEFINE_SPINLOCK(purge_vmap_area_lock);
+
 /*
  * This kmem_cache is used for vmap_area objects. Instead of
  * allocating from slab we reuse an object from this cache to
@@ -820,10 +823,17 @@ insert:
 	if (!merged)
 		link_va(va, root, parent, link, head);
 
-	/*
-	 * Last step is to check and update the tree.
-	 */
-	augment_tree_propagate_from(va);
+	return va;
+}
+
+static __always_inline struct vmap_area *
+merge_or_add_vmap_area_augment(struct vmap_area *va,
+	struct rb_root *root, struct list_head *head)
+{
+	va = merge_or_add_vmap_area(va, root, head);
+	if (va)
+		augment_tree_propagate_from(va);
+
 	return va;
 }
 
@@ -1138,7 +1148,7 @@ static void free_vmap_area(struct vmap_area *va)
 	 * Insert/Merge it back to the free tree/list.
 	 */
 	spin_lock(&free_vmap_area_lock);
-	merge_or_add_vmap_area(va, &free_vmap_area_root, &free_vmap_area_list);
+	merge_or_add_vmap_area_augment(va, &free_vmap_area_root, &free_vmap_area_list);
 	spin_unlock(&free_vmap_area_lock);
 }
 
@@ -1326,32 +1336,32 @@ void set_iounmap_nonlazy(void)
 static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end)
 {
 	unsigned long resched_threshold;
-	struct llist_node *valist;
-	struct vmap_area *va;
-	struct vmap_area *n_va;
+	struct list_head local_pure_list;
+	struct vmap_area *va, *n_va;
 
 	lockdep_assert_held(&vmap_purge_lock);
 
-	valist = llist_del_all(&vmap_purge_list);
-	if (unlikely(valist == NULL))
+	spin_lock(&purge_vmap_area_lock);
+	purge_vmap_area_root = RB_ROOT;
+	list_replace_init(&purge_vmap_area_list, &local_pure_list);
+	spin_unlock(&purge_vmap_area_lock);
+
+	if (unlikely(list_empty(&local_pure_list)))
 		return false;
 
-	/*
-	 * TODO: to calculate a flush range without looping.
-	 * The list can be up to lazy_max_pages() elements.
-	 */
-	llist_for_each_entry(va, valist, purge_list) {
-		if (va->va_start < start)
-			start = va->va_start;
-		if (va->va_end > end)
-			end = va->va_end;
-	}
+	start = min(start,
+		list_first_entry(&local_pure_list,
+			struct vmap_area, list)->va_start);
+
+	end = max(end,
+		list_last_entry(&local_pure_list,
+			struct vmap_area, list)->va_end);
 
 	flush_tlb_kernel_range(start, end);
 	resched_threshold = lazy_max_pages() << 1;
 
 	spin_lock(&free_vmap_area_lock);
-	llist_for_each_entry_safe(va, n_va, valist, purge_list) {
+	list_for_each_entry_safe(va, n_va, &local_pure_list, list) {
 		unsigned long nr = (va->va_end - va->va_start) >> PAGE_SHIFT;
 		unsigned long orig_start = va->va_start;
 		unsigned long orig_end = va->va_end;
@@ -1361,8 +1371,8 @@ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end)
 		 * detached and there is no need to "unlink" it from
 		 * anything.
 		 */
-		va = merge_or_add_vmap_area(va, &free_vmap_area_root,
-					    &free_vmap_area_list);
+		va = merge_or_add_vmap_area_augment(va, &free_vmap_area_root,
+				&free_vmap_area_list);
 
 		if (!va)
 			continue;
@@ -1419,9 +1429,15 @@ static void free_vmap_area_noflush(struct vmap_area *va)
 	nr_lazy = atomic_long_add_return((va->va_end - va->va_start) >>
 				PAGE_SHIFT, &vmap_lazy_nr);
 
-	/* After this point, we may free va at any time */
-	llist_add(&va->purge_list, &vmap_purge_list);
+	/*
+	 * Merge or place it to the purge tree/list.
+	 */
+	spin_lock(&purge_vmap_area_lock);
+	merge_or_add_vmap_area(va,
+		&purge_vmap_area_root, &purge_vmap_area_list);
+	spin_unlock(&purge_vmap_area_lock);
 
+	/* After this point, we may free va at any time */
 	if (unlikely(nr_lazy > lazy_max_pages()))
 		try_purge_vmap_area_lazy();
 }
@@ -3351,8 +3367,8 @@ recovery:
 	while (area--) {
 		orig_start = vas[area]->va_start;
 		orig_end = vas[area]->va_end;
-		va = merge_or_add_vmap_area(vas[area], &free_vmap_area_root,
-					    &free_vmap_area_list);
+		va = merge_or_add_vmap_area_augment(vas[area], &free_vmap_area_root,
+				&free_vmap_area_list);
 		if (va)
 			kasan_release_vmalloc(orig_start, orig_end,
 				va->va_start, va->va_end);
@@ -3401,8 +3417,8 @@ err_free_shadow:
 	for (area = 0; area < nr_vms; area++) {
 		orig_start = vas[area]->va_start;
 		orig_end = vas[area]->va_end;
-		va = merge_or_add_vmap_area(vas[area], &free_vmap_area_root,
-					    &free_vmap_area_list);
+		va = merge_or_add_vmap_area_augment(vas[area], &free_vmap_area_root,
+				&free_vmap_area_list);
 		if (va)
 			kasan_release_vmalloc(orig_start, orig_end,
 				va->va_start, va->va_end);
@@ -3482,18 +3498,15 @@ static void show_numa_info(struct seq_file *m, struct vm_struct *v)
 
 static void show_purge_info(struct seq_file *m)
 {
-	struct llist_node *head;
 	struct vmap_area *va;
 
-	head = READ_ONCE(vmap_purge_list.first);
-	if (head == NULL)
-		return;
-
-	llist_for_each_entry(va, head, purge_list) {
+	spin_lock(&purge_vmap_area_lock);
+	list_for_each_entry(va, &purge_vmap_area_list, list) {
 		seq_printf(m, "0x%pK-0x%pK %7ld unpurged vm_area\n",
 			(void *)va->va_start, (void *)va->va_end,
 			va->va_end - va->va_start);
 	}
+	spin_unlock(&purge_vmap_area_lock);
 }
 
 static int s_show(struct seq_file *m, void *p)
@@ -3551,10 +3564,7 @@ static int s_show(struct seq_file *m, void *p)
 	seq_putc(m, '\n');
 
 	/*
-	 * As a final step, dump "unpurged" areas. Note,
-	 * that entire "/proc/vmallocinfo" output will not
-	 * be address sorted, because the purge list is not
-	 * sorted.
+	 * As a final step, dump "unpurged" areas.
 	 */
 	if (list_is_last(&va->list, &vmap_area_list))
 		show_purge_info(m);
-- 
cgit v1.2.3


From 03e92a5e097d679acbd1fb4d2ae238a38158aa0b Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.ibm.com>
Date: Mon, 14 Dec 2020 19:09:32 -0800
Subject: ia64: remove custom __early_pfn_to_nid()

The ia64 implementation of __early_pfn_to_nid() essentially relies on the
same data as the generic implementation.

The correspondence between memory ranges and nodes is set in memblock
during early memory initialization in register_active_ranges() function.

The initialization of sparsemem that requires early_pfn_to_nid() happens
later and it can use the memblock information like the other architectures.

Link: https://lkml.kernel.org/r/20201101170454.9567-3-rppt@kernel.org
Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Greg Ungerer <gerg@linux-m68k.org>
Cc: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Meelis Roos <mroos@linux.ee>
Cc: Michael Schmitz <schmitzmic@gmail.com>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Vineet Gupta <vgupta@synopsys.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/ia64/Kconfig      |  3 ---
 arch/ia64/mm/numa.c    | 30 ------------------------------
 include/linux/mm.h     |  3 ---
 include/linux/mmzone.h | 11 -----------
 mm/page_alloc.c        | 16 ++++++++++++----
 5 files changed, 12 insertions(+), 51 deletions(-)

(limited to 'include/linux')

diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 39b25a5a591b..12aae706cb27 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -342,9 +342,6 @@ config HOLES_IN_ZONE
 	bool
 	default y if VIRTUAL_MEM_MAP
 
-config HAVE_ARCH_EARLY_PFN_TO_NID
-	def_bool NUMA && SPARSEMEM
-
 config HAVE_ARCH_NODEDATA_EXTENSION
 	def_bool y
 	depends on NUMA
diff --git a/arch/ia64/mm/numa.c b/arch/ia64/mm/numa.c
index f34964271101..46b6e5f3a40f 100644
--- a/arch/ia64/mm/numa.c
+++ b/arch/ia64/mm/numa.c
@@ -58,36 +58,6 @@ paddr_to_nid(unsigned long paddr)
 EXPORT_SYMBOL(paddr_to_nid);
 
 #if defined(CONFIG_SPARSEMEM) && defined(CONFIG_NUMA)
-/*
- * Because of holes evaluate on section limits.
- * If the section of memory exists, then return the node where the section
- * resides.  Otherwise return node 0 as the default.  This is used by
- * SPARSEMEM to allocate the SPARSEMEM sectionmap on the NUMA node where
- * the section resides.
- */
-int __meminit __early_pfn_to_nid(unsigned long pfn,
-					struct mminit_pfnnid_cache *state)
-{
-	int i, section = pfn >> PFN_SECTION_SHIFT, ssec, esec;
-
-	if (section >= state->last_start && section < state->last_end)
-		return state->last_nid;
-
-	for (i = 0; i < num_node_memblks; i++) {
-		ssec = node_memblk[i].start_paddr >> PA_SECTION_SHIFT;
-		esec = (node_memblk[i].start_paddr + node_memblk[i].size +
-			((1L << PA_SECTION_SHIFT) - 1)) >> PA_SECTION_SHIFT;
-		if (section >= ssec && section < esec) {
-			state->last_start = ssec;
-			state->last_end = esec;
-			state->last_nid = node_memblk[i].nid;
-			return node_memblk[i].nid;
-		}
-	}
-
-	return -1;
-}
-
 void numa_clear_node(int cpu)
 {
 	unmap_cpu_from_node(cpu, NUMA_NO_NODE);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 5d188b8611dc..48fa3e71be1a 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2434,9 +2434,6 @@ static inline int early_pfn_to_nid(unsigned long pfn)
 #else
 /* please see mm/page_alloc.c */
 extern int __meminit early_pfn_to_nid(unsigned long pfn);
-/* there is a per-arch backend function. */
-extern int __meminit __early_pfn_to_nid(unsigned long pfn,
-					struct mminit_pfnnid_cache *state);
 #endif
 
 extern void set_dma_reserve(unsigned long new_dma_reserve);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index cca2a4443c9c..16fb5522a74f 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1428,17 +1428,6 @@ void sparse_init(void);
 #define subsection_map_init(_pfn, _nr_pages) do {} while (0)
 #endif /* CONFIG_SPARSEMEM */
 
-/*
- * During memory init memblocks map pfns to nids. The search is expensive and
- * this caches recent lookups. The implementation of __early_pfn_to_nid
- * may treat start/end as pfns or sections.
- */
-struct mminit_pfnnid_cache {
-	unsigned long last_start;
-	unsigned long last_end;
-	int last_nid;
-};
-
 /*
  * If it is possible to have holes within a MAX_ORDER_NR_PAGES, then we
  * need to check pfn validity within that MAX_ORDER_NR_PAGES block.
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 2e240d3cda05..484d5582f88c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1559,14 +1559,23 @@ void __free_pages_core(struct page *page, unsigned int order)
 
 #ifdef CONFIG_NEED_MULTIPLE_NODES
 
-static struct mminit_pfnnid_cache early_pfnnid_cache __meminitdata;
+/*
+ * During memory init memblocks map pfns to nids. The search is expensive and
+ * this caches recent lookups. The implementation of __early_pfn_to_nid
+ * treats start/end as pfns.
+ */
+struct mminit_pfnnid_cache {
+	unsigned long last_start;
+	unsigned long last_end;
+	int last_nid;
+};
 
-#ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID
+static struct mminit_pfnnid_cache early_pfnnid_cache __meminitdata;
 
 /*
  * Required by SPARSEMEM. Given a PFN, return what node the PFN is on.
  */
-int __meminit __early_pfn_to_nid(unsigned long pfn,
+static int __meminit __early_pfn_to_nid(unsigned long pfn,
 					struct mminit_pfnnid_cache *state)
 {
 	unsigned long start_pfn, end_pfn;
@@ -1584,7 +1593,6 @@ int __meminit __early_pfn_to_nid(unsigned long pfn,
 
 	return nid;
 }
-#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */
 
 int __meminit early_pfn_to_nid(unsigned long pfn)
 {
-- 
cgit v1.2.3


From 5e545df3292fbd3d5963c68980f1527ead2a2b3f Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.ibm.com>
Date: Mon, 14 Dec 2020 19:09:55 -0800
Subject: arm: remove CONFIG_ARCH_HAS_HOLES_MEMORYMODEL

ARM is the only architecture that defines CONFIG_ARCH_HAS_HOLES_MEMORYMODEL
which in turn enables memmap_valid_within() function that is intended to
verify existence  of struct page associated with a pfn when there are holes
in the memory map.

However, the ARCH_HAS_HOLES_MEMORYMODEL also enables HAVE_ARCH_PFN_VALID
and arch-specific pfn_valid() implementation that also deals with the holes
in the memory map.

The only two users of memmap_valid_within() call this function after
a call to pfn_valid() so the memmap_valid_within() check becomes redundant.

Remove CONFIG_ARCH_HAS_HOLES_MEMORYMODEL and memmap_valid_within() and rely
entirely on ARM's implementation of pfn_valid() that is now enabled
unconditionally.

Link: https://lkml.kernel.org/r/20201101170454.9567-9-rppt@kernel.org
Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Greg Ungerer <gerg@linux-m68k.org>
Cc: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Meelis Roos <mroos@linux.ee>
Cc: Michael Schmitz <schmitzmic@gmail.com>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Vineet Gupta <vgupta@synopsys.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/vm/memory-model.rst |  3 +--
 arch/arm/Kconfig                  |  8 ++------
 arch/arm/mach-bcm/Kconfig         |  1 -
 arch/arm/mach-davinci/Kconfig     |  1 -
 arch/arm/mach-exynos/Kconfig      |  1 -
 arch/arm/mach-highbank/Kconfig    |  1 -
 arch/arm/mach-omap2/Kconfig       |  1 -
 arch/arm/mach-s5pv210/Kconfig     |  1 -
 arch/arm/mach-tango/Kconfig       |  1 -
 fs/proc/kcore.c                   |  2 --
 include/linux/mmzone.h            | 31 -------------------------------
 mm/mmzone.c                       | 14 --------------
 mm/vmstat.c                       |  4 ----
 13 files changed, 3 insertions(+), 66 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/vm/memory-model.rst b/Documentation/vm/memory-model.rst
index 9daadf9faba1..ce398a7dc6cd 100644
--- a/Documentation/vm/memory-model.rst
+++ b/Documentation/vm/memory-model.rst
@@ -51,8 +51,7 @@ call :c:func:`free_area_init` function. Yet, the mappings array is not
 usable until the call to :c:func:`memblock_free_all` that hands all the
 memory to the page allocator.
 
-If an architecture enables `CONFIG_ARCH_HAS_HOLES_MEMORYMODEL` option,
-it may free parts of the `mem_map` array that do not cover the
+An architecture may free parts of the `mem_map` array that do not cover the
 actual physical pages. In such case, the architecture specific
 :c:func:`pfn_valid` implementation should take the holes in the
 `mem_map` into account.
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 002e0cf025f5..353c3979a2d5 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -25,7 +25,7 @@ config ARM
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAVE_CUSTOM_GPIO_H
 	select ARCH_HAS_GCOV_PROFILE_ALL
-	select ARCH_KEEP_MEMBLOCK if HAVE_ARCH_PFN_VALID || KEXEC
+	select ARCH_KEEP_MEMBLOCK
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_NO_SG_CHAIN if !ARM_HAS_SG_CHAIN
 	select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX
@@ -520,7 +520,6 @@ config ARCH_S3C24XX
 config ARCH_OMAP1
 	bool "TI OMAP1"
 	depends on MMU
-	select ARCH_HAS_HOLES_MEMORYMODEL
 	select ARCH_OMAP
 	select CLKDEV_LOOKUP
 	select CLKSRC_MMIO
@@ -1480,9 +1479,6 @@ config OABI_COMPAT
 	  UNPREDICTABLE (in fact it can be predicted that it won't work
 	  at all). If in doubt say N.
 
-config ARCH_HAS_HOLES_MEMORYMODEL
-	bool
-
 config ARCH_SELECT_MEMORY_MODEL
 	bool
 
@@ -1494,7 +1490,7 @@ config ARCH_SPARSEMEM_ENABLE
 	select SPARSEMEM_STATIC if SPARSEMEM
 
 config HAVE_ARCH_PFN_VALID
-	def_bool ARCH_HAS_HOLES_MEMORYMODEL || !SPARSEMEM
+	def_bool y
 
 config HIGHMEM
 	bool "High Memory Support"
diff --git a/arch/arm/mach-bcm/Kconfig b/arch/arm/mach-bcm/Kconfig
index ae790908fc74..9b594ae98153 100644
--- a/arch/arm/mach-bcm/Kconfig
+++ b/arch/arm/mach-bcm/Kconfig
@@ -211,7 +211,6 @@ config ARCH_BRCMSTB
 	select BCM7038_L1_IRQ
 	select BRCMSTB_L2_IRQ
 	select BCM7120_L2_IRQ
-	select ARCH_HAS_HOLES_MEMORYMODEL
 	select ZONE_DMA if ARM_LPAE
 	select SOC_BRCMSTB
 	select SOC_BUS
diff --git a/arch/arm/mach-davinci/Kconfig b/arch/arm/mach-davinci/Kconfig
index f56ff8c24043..de11030748d0 100644
--- a/arch/arm/mach-davinci/Kconfig
+++ b/arch/arm/mach-davinci/Kconfig
@@ -5,7 +5,6 @@ menuconfig ARCH_DAVINCI
 	depends on ARCH_MULTI_V5
 	select DAVINCI_TIMER
 	select ZONE_DMA
-	select ARCH_HAS_HOLES_MEMORYMODEL
 	select PM_GENERIC_DOMAINS if PM
 	select PM_GENERIC_DOMAINS_OF if PM && OF
 	select REGMAP_MMIO
diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig
index d2d249706ebb..56d272967fc0 100644
--- a/arch/arm/mach-exynos/Kconfig
+++ b/arch/arm/mach-exynos/Kconfig
@@ -8,7 +8,6 @@
 menuconfig ARCH_EXYNOS
 	bool "Samsung Exynos"
 	depends on ARCH_MULTI_V7
-	select ARCH_HAS_HOLES_MEMORYMODEL
 	select ARCH_SUPPORTS_BIG_ENDIAN
 	select ARM_AMBA
 	select ARM_GIC
diff --git a/arch/arm/mach-highbank/Kconfig b/arch/arm/mach-highbank/Kconfig
index 1bc68913d62c..9de38ce8124f 100644
--- a/arch/arm/mach-highbank/Kconfig
+++ b/arch/arm/mach-highbank/Kconfig
@@ -2,7 +2,6 @@
 config ARCH_HIGHBANK
 	bool "Calxeda ECX-1000/2000 (Highbank/Midway)"
 	depends on ARCH_MULTI_V7
-	select ARCH_HAS_HOLES_MEMORYMODEL
 	select ARCH_SUPPORTS_BIG_ENDIAN
 	select ARM_AMBA
 	select ARM_ERRATA_764369 if SMP
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index 3f62a0c9450d..164985505f9e 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -93,7 +93,6 @@ config SOC_DRA7XX
 config ARCH_OMAP2PLUS
 	bool
 	select ARCH_HAS_BANDGAP
-	select ARCH_HAS_HOLES_MEMORYMODEL
 	select ARCH_HAS_RESET_CONTROLLER
 	select ARCH_OMAP
 	select CLKSRC_MMIO
diff --git a/arch/arm/mach-s5pv210/Kconfig b/arch/arm/mach-s5pv210/Kconfig
index 95d4e8284866..d644b45bc29d 100644
--- a/arch/arm/mach-s5pv210/Kconfig
+++ b/arch/arm/mach-s5pv210/Kconfig
@@ -8,7 +8,6 @@
 config ARCH_S5PV210
 	bool "Samsung S5PV210/S5PC110"
 	depends on ARCH_MULTI_V7
-	select ARCH_HAS_HOLES_MEMORYMODEL
 	select ARM_VIC
 	select CLKSRC_SAMSUNG_PWM
 	select COMMON_CLK_SAMSUNG
diff --git a/arch/arm/mach-tango/Kconfig b/arch/arm/mach-tango/Kconfig
index 25b2fd434861..a9eeda36aeb1 100644
--- a/arch/arm/mach-tango/Kconfig
+++ b/arch/arm/mach-tango/Kconfig
@@ -3,7 +3,6 @@ config ARCH_TANGO
 	bool "Sigma Designs Tango4 (SMP87xx)"
 	depends on ARCH_MULTI_V7
 	# Cortex-A9 MPCore r3p0, PL310 r3p2
-	select ARCH_HAS_HOLES_MEMORYMODEL
 	select ARM_ERRATA_754322
 	select ARM_ERRATA_764369 if SMP
 	select ARM_ERRATA_775420
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index e502414b3556..4d2e64e9016c 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -193,8 +193,6 @@ kclist_add_private(unsigned long pfn, unsigned long nr_pages, void *arg)
 		return 1;
 
 	p = pfn_to_page(pfn);
-	if (!memmap_valid_within(pfn, p, page_zone(p)))
-		return 1;
 
 	ent = kmalloc(sizeof(*ent), GFP_KERNEL);
 	if (!ent)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 16fb5522a74f..6e0025b5a88f 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1440,37 +1440,6 @@ void sparse_init(void);
 #define pfn_valid_within(pfn) (1)
 #endif
 
-#ifdef CONFIG_ARCH_HAS_HOLES_MEMORYMODEL
-/*
- * pfn_valid() is meant to be able to tell if a given PFN has valid memmap
- * associated with it or not. This means that a struct page exists for this
- * pfn. The caller cannot assume the page is fully initialized in general.
- * Hotplugable pages might not have been onlined yet. pfn_to_online_page()
- * will ensure the struct page is fully online and initialized. Special pages
- * (e.g. ZONE_DEVICE) are never onlined and should be treated accordingly.
- *
- * In FLATMEM, it is expected that holes always have valid memmap as long as
- * there is valid PFNs either side of the hole. In SPARSEMEM, it is assumed
- * that a valid section has a memmap for the entire section.
- *
- * However, an ARM, and maybe other embedded architectures in the future
- * free memmap backing holes to save memory on the assumption the memmap is
- * never used. The page_zone linkages are then broken even though pfn_valid()
- * returns true. A walker of the full memmap must then do this additional
- * check to ensure the memmap they are looking at is sane by making sure
- * the zone and PFN linkages are still valid. This is expensive, but walkers
- * of the full memmap are extremely rare.
- */
-bool memmap_valid_within(unsigned long pfn,
-					struct page *page, struct zone *zone);
-#else
-static inline bool memmap_valid_within(unsigned long pfn,
-					struct page *page, struct zone *zone)
-{
-	return true;
-}
-#endif /* CONFIG_ARCH_HAS_HOLES_MEMORYMODEL */
-
 #endif /* !__GENERATING_BOUNDS.H */
 #endif /* !__ASSEMBLY__ */
 #endif /* _LINUX_MMZONE_H */
diff --git a/mm/mmzone.c b/mm/mmzone.c
index 4686fdc23bb9..f337831affc2 100644
--- a/mm/mmzone.c
+++ b/mm/mmzone.c
@@ -72,20 +72,6 @@ struct zoneref *__next_zones_zonelist(struct zoneref *z,
 	return z;
 }
 
-#ifdef CONFIG_ARCH_HAS_HOLES_MEMORYMODEL
-bool memmap_valid_within(unsigned long pfn,
-					struct page *page, struct zone *zone)
-{
-	if (page_to_pfn(page) != pfn)
-		return false;
-
-	if (page_zone(page) != zone)
-		return false;
-
-	return true;
-}
-#endif /* CONFIG_ARCH_HAS_HOLES_MEMORYMODEL */
-
 void lruvec_init(struct lruvec *lruvec)
 {
 	enum lru_list lru;
diff --git a/mm/vmstat.c b/mm/vmstat.c
index da36e3b0aab2..f8942160fc95 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1503,10 +1503,6 @@ static void pagetypeinfo_showblockcount_print(struct seq_file *m,
 		if (!page)
 			continue;
 
-		/* Watch for unexpected holes punched in the memmap */
-		if (!memmap_valid_within(pfn, page, zone))
-			continue;
-
 		if (page_zone(page) != zone)
 			continue;
 
-- 
cgit v1.2.3


From 77bc7fd607dee2ffb28daff6d0dd8ae42af61ea8 Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.ibm.com>
Date: Mon, 14 Dec 2020 19:10:20 -0800
Subject: mm: introduce debug_pagealloc_{map,unmap}_pages() helpers

Patch series "arch, mm: improve robustness of direct map manipulation", v7.

During recent discussion about KVM protected memory, David raised a
concern about usage of __kernel_map_pages() outside of DEBUG_PAGEALLOC
scope [1].

Indeed, for architectures that define CONFIG_ARCH_HAS_SET_DIRECT_MAP it is
possible that __kernel_map_pages() would fail, but since this function is
void, the failure will go unnoticed.

Moreover, there's lack of consistency of __kernel_map_pages() semantics
across architectures as some guard this function with #ifdef
DEBUG_PAGEALLOC, some refuse to update the direct map if page allocation
debugging is disabled at run time and some allow modifying the direct map
regardless of DEBUG_PAGEALLOC settings.

This set straightens this out by restoring dependency of
__kernel_map_pages() on DEBUG_PAGEALLOC and updating the call sites
accordingly.

Since currently the only user of __kernel_map_pages() outside
DEBUG_PAGEALLOC is hibernation, it is updated to make direct map accesses
there more explicit.

[1] https://lore.kernel.org/lkml/2759b4bf-e1e3-d006-7d86-78a40348269d@redhat.com

This patch (of 4):

When CONFIG_DEBUG_PAGEALLOC is enabled, it unmaps pages from the kernel
direct mapping after free_pages().  The pages than need to be mapped back
before they could be used.  Theese mapping operations use
__kernel_map_pages() guarded with with debug_pagealloc_enabled().

The only place that calls __kernel_map_pages() without checking whether
DEBUG_PAGEALLOC is enabled is the hibernation code that presumes
availability of this function when ARCH_HAS_SET_DIRECT_MAP is set.  Still,
on arm64, __kernel_map_pages() will bail out when DEBUG_PAGEALLOC is not
enabled but set_direct_map_invalid_noflush() may render some pages not
present in the direct map and hibernation code won't be able to save such
pages.

To make page allocation debugging and hibernation interaction more robust,
the dependency on DEBUG_PAGEALLOC or ARCH_HAS_SET_DIRECT_MAP has to be
made more explicit.

Start with combining the guard condition and the call to
__kernel_map_pages() into debug_pagealloc_map_pages() and
debug_pagealloc_unmap_pages() functions to emphasize that
__kernel_map_pages() should not be called without DEBUG_PAGEALLOC and use
these new functions to map/unmap pages when page allocation debugging is
enabled.

Link: https://lkml.kernel.org/r/20201109192128.960-1-rppt@kernel.org
Link: https://lkml.kernel.org/r/20201109192128.960-2-rppt@kernel.org
Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Rientjes <rientjes@google.com>
Cc: "Edgecombe, Rick P" <rick.p.edgecombe@intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Len Brown <len.brown@intel.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h  | 15 +++++++++++++++
 mm/memory_hotplug.c |  3 +--
 mm/page_alloc.c     |  6 ++----
 mm/slab.c           |  2 +-
 4 files changed, 19 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 48fa3e71be1a..0f4c34672a13 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2943,12 +2943,27 @@ kernel_map_pages(struct page *page, int numpages, int enable)
 {
 	__kernel_map_pages(page, numpages, enable);
 }
+
+static inline void debug_pagealloc_map_pages(struct page *page, int numpages)
+{
+	if (debug_pagealloc_enabled_static())
+		__kernel_map_pages(page, numpages, 1);
+}
+
+static inline void debug_pagealloc_unmap_pages(struct page *page, int numpages)
+{
+	if (debug_pagealloc_enabled_static())
+		__kernel_map_pages(page, numpages, 0);
+}
+
 #ifdef CONFIG_HIBERNATION
 extern bool kernel_page_present(struct page *page);
 #endif	/* CONFIG_HIBERNATION */
 #else	/* CONFIG_DEBUG_PAGEALLOC || CONFIG_ARCH_HAS_SET_DIRECT_MAP */
 static inline void
 kernel_map_pages(struct page *page, int numpages, int enable) {}
+static inline void debug_pagealloc_map_pages(struct page *page, int numpages) {}
+static inline void debug_pagealloc_unmap_pages(struct page *page, int numpages) {}
 #ifdef CONFIG_HIBERNATION
 static inline bool kernel_page_present(struct page *page) { return true; }
 #endif	/* CONFIG_HIBERNATION */
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 0f855deea4b2..41c62295292b 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -596,8 +596,7 @@ void generic_online_page(struct page *page, unsigned int order)
 	 * so we should map it first. This is better than introducing a special
 	 * case in page freeing fast path.
 	 */
-	if (debug_pagealloc_enabled_static())
-		kernel_map_pages(page, 1 << order, 1);
+	debug_pagealloc_map_pages(page, 1 << order);
 	__free_pages_core(page, order);
 	totalram_pages_add(1UL << order);
 #ifdef CONFIG_HIGHMEM
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 484d5582f88c..2b5410dac827 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1273,8 +1273,7 @@ static __always_inline bool free_pages_prepare(struct page *page,
 	 */
 	arch_free_page(page, order);
 
-	if (debug_pagealloc_enabled_static())
-		kernel_map_pages(page, 1 << order, 0);
+	debug_pagealloc_unmap_pages(page, 1 << order);
 
 	kasan_free_nondeferred_pages(page, order);
 
@@ -2279,8 +2278,7 @@ inline void post_alloc_hook(struct page *page, unsigned int order,
 	set_page_refcounted(page);
 
 	arch_alloc_page(page, order);
-	if (debug_pagealloc_enabled_static())
-		kernel_map_pages(page, 1 << order, 1);
+	debug_pagealloc_map_pages(page, 1 << order);
 	kasan_alloc_pages(page, order);
 	kernel_poison_pages(page, 1 << order, 1);
 	set_page_owner(page, order, gfp_flags);
diff --git a/mm/slab.c b/mm/slab.c
index 176b65e2157d..d7c8da9319c7 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1435,7 +1435,7 @@ static void slab_kernel_map(struct kmem_cache *cachep, void *objp, int map)
 	if (!is_debug_pagealloc_cache(cachep))
 		return;
 
-	kernel_map_pages(virt_to_page(objp), cachep->size / PAGE_SIZE, map);
+	__kernel_map_pages(virt_to_page(objp), cachep->size / PAGE_SIZE, map);
 }
 
 #else
-- 
cgit v1.2.3


From 2abf962a8d42b32f5ffeb827826290b799c85f86 Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.ibm.com>
Date: Mon, 14 Dec 2020 19:10:25 -0800
Subject: PM: hibernate: make direct map manipulations more explicit

When DEBUG_PAGEALLOC or ARCH_HAS_SET_DIRECT_MAP is enabled a page may be
not present in the direct map and has to be explicitly mapped before it
could be copied.

Introduce hibernate_map_page() and hibernation_unmap_page() that will
explicitly use set_direct_map_{default,invalid}_noflush() for
ARCH_HAS_SET_DIRECT_MAP case and debug_pagealloc_{map,unmap}_pages() for
DEBUG_PAGEALLOC case.

The remapping of the pages in safe_copy_page() presumes that it only
changes protection bits in an existing PTE and so it is safe to ignore
return value of set_direct_map_{default,invalid}_noflush().

Still, add a pr_warn() so that future changes in set_memory APIs will not
silently break hibernation.

Link: https://lkml.kernel.org/r/20201109192128.960-3-rppt@kernel.org
Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Rientjes <rientjes@google.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: "Edgecombe, Rick P" <rick.p.edgecombe@intel.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Len Brown <len.brown@intel.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h      | 12 ------------
 kernel/power/snapshot.c | 38 ++++++++++++++++++++++++++++++++++++--
 2 files changed, 36 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0f4c34672a13..6b5df31387b5 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2934,16 +2934,6 @@ static inline bool debug_pagealloc_enabled_static(void)
 #if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_ARCH_HAS_SET_DIRECT_MAP)
 extern void __kernel_map_pages(struct page *page, int numpages, int enable);
 
-/*
- * When called in DEBUG_PAGEALLOC context, the call should most likely be
- * guarded by debug_pagealloc_enabled() or debug_pagealloc_enabled_static()
- */
-static inline void
-kernel_map_pages(struct page *page, int numpages, int enable)
-{
-	__kernel_map_pages(page, numpages, enable);
-}
-
 static inline void debug_pagealloc_map_pages(struct page *page, int numpages)
 {
 	if (debug_pagealloc_enabled_static())
@@ -2960,8 +2950,6 @@ static inline void debug_pagealloc_unmap_pages(struct page *page, int numpages)
 extern bool kernel_page_present(struct page *page);
 #endif	/* CONFIG_HIBERNATION */
 #else	/* CONFIG_DEBUG_PAGEALLOC || CONFIG_ARCH_HAS_SET_DIRECT_MAP */
-static inline void
-kernel_map_pages(struct page *page, int numpages, int enable) {}
 static inline void debug_pagealloc_map_pages(struct page *page, int numpages) {}
 static inline void debug_pagealloc_unmap_pages(struct page *page, int numpages) {}
 #ifdef CONFIG_HIBERNATION
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 46b1804c1ddf..d848377dd8dc 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -76,6 +76,40 @@ static inline void hibernate_restore_protect_page(void *page_address) {}
 static inline void hibernate_restore_unprotect_page(void *page_address) {}
 #endif /* CONFIG_STRICT_KERNEL_RWX  && CONFIG_ARCH_HAS_SET_MEMORY */
 
+
+/*
+ * The calls to set_direct_map_*() should not fail because remapping a page
+ * here means that we only update protection bits in an existing PTE.
+ * It is still worth to have a warning here if something changes and this
+ * will no longer be the case.
+ */
+static inline void hibernate_map_page(struct page *page)
+{
+	if (IS_ENABLED(CONFIG_ARCH_HAS_SET_DIRECT_MAP)) {
+		int ret = set_direct_map_default_noflush(page);
+
+		if (ret)
+			pr_warn_once("Failed to remap page\n");
+	} else {
+		debug_pagealloc_map_pages(page, 1);
+	}
+}
+
+static inline void hibernate_unmap_page(struct page *page)
+{
+	if (IS_ENABLED(CONFIG_ARCH_HAS_SET_DIRECT_MAP)) {
+		unsigned long addr = (unsigned long)page_address(page);
+		int ret  = set_direct_map_invalid_noflush(page);
+
+		if (ret)
+			pr_warn_once("Failed to remap page\n");
+
+		flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+	} else {
+		debug_pagealloc_unmap_pages(page, 1);
+	}
+}
+
 static int swsusp_page_is_free(struct page *);
 static void swsusp_set_page_forbidden(struct page *);
 static void swsusp_unset_page_forbidden(struct page *);
@@ -1355,9 +1389,9 @@ static void safe_copy_page(void *dst, struct page *s_page)
 	if (kernel_page_present(s_page)) {
 		do_copy_page(dst, page_address(s_page));
 	} else {
-		kernel_map_pages(s_page, 1, 1);
+		hibernate_map_page(s_page);
 		do_copy_page(dst, page_address(s_page));
-		kernel_map_pages(s_page, 1, 0);
+		hibernate_unmap_page(s_page);
 	}
 }
 
-- 
cgit v1.2.3


From 5d6ad668f31625c6aa9ed8dc3bdb29561d2b1144 Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.ibm.com>
Date: Mon, 14 Dec 2020 19:10:30 -0800
Subject: arch, mm: restore dependency of __kernel_map_pages() on
 DEBUG_PAGEALLOC

The design of DEBUG_PAGEALLOC presumes that __kernel_map_pages() must
never fail.  With this assumption is wouldn't be safe to allow general
usage of this function.

Moreover, some architectures that implement __kernel_map_pages() have this
function guarded by #ifdef DEBUG_PAGEALLOC and some refuse to map/unmap
pages when page allocation debugging is disabled at runtime.

As all the users of __kernel_map_pages() were converted to use
debug_pagealloc_map_pages() it is safe to make it available only when
DEBUG_PAGEALLOC is set.

Link: https://lkml.kernel.org/r/20201109192128.960-4-rppt@kernel.org
Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Rientjes <rientjes@google.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: "Edgecombe, Rick P" <rick.p.edgecombe@intel.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Len Brown <len.brown@intel.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/Kconfig                     |  3 +++
 arch/arm64/Kconfig               |  4 +---
 arch/arm64/mm/pageattr.c         |  8 ++++++--
 arch/powerpc/Kconfig             |  5 +----
 arch/riscv/Kconfig               |  4 +---
 arch/riscv/include/asm/pgtable.h |  2 --
 arch/riscv/mm/pageattr.c         |  2 ++
 arch/s390/Kconfig                |  4 +---
 arch/sparc/Kconfig               |  4 +---
 arch/x86/Kconfig                 |  4 +---
 arch/x86/mm/pat/set_memory.c     |  2 ++
 include/linux/mm.h               | 10 +++++++---
 12 files changed, 26 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/arch/Kconfig b/arch/Kconfig
index 8d5efff59cd8..cd4172a80123 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -1047,6 +1047,9 @@ config ARCH_WANT_LD_ORPHAN_WARN
 config HAVE_ARCH_PFN_VALID
 	bool
 
+config ARCH_SUPPORTS_DEBUG_PAGEALLOC
+	bool
+
 source "kernel/gcov/Kconfig"
 
 source "scripts/gcc-plugins/Kconfig"
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 6f0751631ef1..f2dee598a921 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -71,6 +71,7 @@ config ARM64
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USE_QUEUED_SPINLOCKS
 	select ARCH_USE_SYM_ANNOTATIONS
+	select ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	select ARCH_SUPPORTS_MEMORY_FAILURE
 	select ARCH_SUPPORTS_SHADOW_CALL_STACK if CC_HAVE_SHADOW_CALL_STACK
 	select ARCH_SUPPORTS_ATOMIC_RMW
@@ -1028,9 +1029,6 @@ config HOLES_IN_ZONE
 
 source "kernel/Kconfig.hz"
 
-config ARCH_SUPPORTS_DEBUG_PAGEALLOC
-	def_bool y
-
 config ARCH_SPARSEMEM_ENABLE
 	def_bool y
 	select SPARSEMEM_VMEMMAP_ENABLE
diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c
index 1b94f5b82654..439325532be1 100644
--- a/arch/arm64/mm/pageattr.c
+++ b/arch/arm64/mm/pageattr.c
@@ -155,7 +155,7 @@ int set_direct_map_invalid_noflush(struct page *page)
 		.clear_mask = __pgprot(PTE_VALID),
 	};
 
-	if (!rodata_full)
+	if (!debug_pagealloc_enabled() && !rodata_full)
 		return 0;
 
 	return apply_to_page_range(&init_mm,
@@ -170,7 +170,7 @@ int set_direct_map_default_noflush(struct page *page)
 		.clear_mask = __pgprot(PTE_RDONLY),
 	};
 
-	if (!rodata_full)
+	if (!debug_pagealloc_enabled() && !rodata_full)
 		return 0;
 
 	return apply_to_page_range(&init_mm,
@@ -178,6 +178,7 @@ int set_direct_map_default_noflush(struct page *page)
 				   PAGE_SIZE, change_page_range, &data);
 }
 
+#ifdef CONFIG_DEBUG_PAGEALLOC
 void __kernel_map_pages(struct page *page, int numpages, int enable)
 {
 	if (!debug_pagealloc_enabled() && !rodata_full)
@@ -186,6 +187,7 @@ void __kernel_map_pages(struct page *page, int numpages, int enable)
 	set_memory_valid((unsigned long)page_address(page), numpages, enable);
 }
 
+#ifdef CONFIG_HIBERNATION
 /*
  * This function is used to determine if a linear map page has been marked as
  * not-valid. Walk the page table and check the PTE_VALID bit. This is based
@@ -232,3 +234,5 @@ bool kernel_page_present(struct page *page)
 	ptep = pte_offset_kernel(pmdp, addr);
 	return pte_valid(READ_ONCE(*ptep));
 }
+#endif /* CONFIG_HIBERNATION */
+#endif /* CONFIG_DEBUG_PAGEALLOC */
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 5181872f9452..8e8f46bbd39c 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -146,6 +146,7 @@ config PPC
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select ARCH_OPTIONAL_KERNEL_RWX		if ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_SUPPORTS_ATOMIC_RMW
+	select ARCH_SUPPORTS_DEBUG_PAGEALLOC	if PPC32 || PPC_BOOK3S_64
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF		if PPC64
 	select ARCH_USE_QUEUED_RWLOCKS		if PPC_QUEUED_SPINLOCKS
@@ -356,10 +357,6 @@ config PPC_OF_PLATFORM_PCI
 	depends on PCI
 	depends on PPC64 # not supported on 32 bits yet
 
-config ARCH_SUPPORTS_DEBUG_PAGEALLOC
-	depends on PPC32 || PPC_BOOK3S_64
-	def_bool y
-
 config ARCH_SUPPORTS_UPROBES
 	def_bool y
 
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 44377fd7860e..9283c6f9ae2a 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -14,6 +14,7 @@ config RISCV
 	def_bool y
 	select ARCH_CLOCKSOURCE_INIT
 	select ARCH_SUPPORTS_ATOMIC_RMW
+	select ARCH_SUPPORTS_DEBUG_PAGEALLOC if MMU
 	select ARCH_HAS_BINFMT_FLAT
 	select ARCH_HAS_DEBUG_VM_PGTABLE
 	select ARCH_HAS_DEBUG_VIRTUAL if MMU
@@ -153,9 +154,6 @@ config ARCH_SELECT_MEMORY_MODEL
 config ARCH_WANT_GENERAL_HUGETLB
 	def_bool y
 
-config ARCH_SUPPORTS_DEBUG_PAGEALLOC
-	def_bool y
-
 config SYS_SUPPORTS_HUGETLBFS
 	depends on MMU
 	def_bool y
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 183f1f4b2ae6..41a72861987c 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -461,8 +461,6 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
 #define VMALLOC_START		0
 #define VMALLOC_END		TASK_SIZE
 
-static inline void __kernel_map_pages(struct page *page, int numpages, int enable) {}
-
 #endif /* !CONFIG_MMU */
 
 #define kern_addr_valid(addr)   (1) /* FIXME */
diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c
index 19fecb362d81..321b09d2e2ea 100644
--- a/arch/riscv/mm/pageattr.c
+++ b/arch/riscv/mm/pageattr.c
@@ -184,6 +184,7 @@ int set_direct_map_default_noflush(struct page *page)
 	return ret;
 }
 
+#ifdef CONFIG_DEBUG_PAGEALLOC
 void __kernel_map_pages(struct page *page, int numpages, int enable)
 {
 	if (!debug_pagealloc_enabled())
@@ -196,3 +197,4 @@ void __kernel_map_pages(struct page *page, int numpages, int enable)
 		__set_memory((unsigned long)page_address(page), numpages,
 			     __pgprot(0), __pgprot(_PAGE_PRESENT));
 }
+#endif
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 4a2a12be04c9..991a850a6c0b 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -35,9 +35,6 @@ config GENERIC_LOCKBREAK
 config PGSTE
 	def_bool y if KVM
 
-config ARCH_SUPPORTS_DEBUG_PAGEALLOC
-	def_bool y
-
 config AUDIT_ARCH
 	def_bool y
 
@@ -106,6 +103,7 @@ config S390
 	select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
 	select ARCH_STACKWALK
 	select ARCH_SUPPORTS_ATOMIC_RMW
+	select ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	select ARCH_SUPPORTS_NUMA_BALANCING
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index a6ca135442f9..2c729b8d097a 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -88,6 +88,7 @@ config SPARC64
 	select HAVE_C_RECORDMCOUNT
 	select HAVE_ARCH_AUDITSYSCALL
 	select ARCH_SUPPORTS_ATOMIC_RMW
+	select ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	select HAVE_NMI
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select ARCH_USE_QUEUED_RWLOCKS
@@ -148,9 +149,6 @@ config GENERIC_ISA_DMA
 	bool
 	default y if SPARC32
 
-config ARCH_SUPPORTS_DEBUG_PAGEALLOC
-	def_bool y if SPARC64
-
 config PGTABLE_LEVELS
 	default 4 if 64BIT
 	default 3
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 46393177ce73..384c91b057c5 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -91,6 +91,7 @@ config X86
 	select ARCH_STACKWALK
 	select ARCH_SUPPORTS_ACPI
 	select ARCH_SUPPORTS_ATOMIC_RMW
+	select ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	select ARCH_SUPPORTS_NUMA_BALANCING	if X86_64
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_QUEUED_RWLOCKS
@@ -331,9 +332,6 @@ config ZONE_DMA32
 config AUDIT_ARCH
 	def_bool y if X86_64
 
-config ARCH_SUPPORTS_DEBUG_PAGEALLOC
-	def_bool y
-
 config KASAN_SHADOW_OFFSET
 	hex
 	depends on KASAN
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index 40baa90e74f4..bc9be96b777f 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -2194,6 +2194,7 @@ int set_direct_map_default_noflush(struct page *page)
 	return __set_pages_p(page, 1);
 }
 
+#ifdef CONFIG_DEBUG_PAGEALLOC
 void __kernel_map_pages(struct page *page, int numpages, int enable)
 {
 	if (PageHighMem(page))
@@ -2239,6 +2240,7 @@ bool kernel_page_present(struct page *page)
 	return (pte_val(*pte) & _PAGE_PRESENT);
 }
 #endif /* CONFIG_HIBERNATION */
+#endif /* CONFIG_DEBUG_PAGEALLOC */
 
 int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
 				   unsigned numpages, unsigned long page_flags)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 6b5df31387b5..7a67bdf3df5e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2931,7 +2931,11 @@ static inline bool debug_pagealloc_enabled_static(void)
 	return static_branch_unlikely(&_debug_pagealloc_enabled);
 }
 
-#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_ARCH_HAS_SET_DIRECT_MAP)
+#ifdef CONFIG_DEBUG_PAGEALLOC
+/*
+ * To support DEBUG_PAGEALLOC architecture must ensure that
+ * __kernel_map_pages() never fails
+ */
 extern void __kernel_map_pages(struct page *page, int numpages, int enable);
 
 static inline void debug_pagealloc_map_pages(struct page *page, int numpages)
@@ -2949,13 +2953,13 @@ static inline void debug_pagealloc_unmap_pages(struct page *page, int numpages)
 #ifdef CONFIG_HIBERNATION
 extern bool kernel_page_present(struct page *page);
 #endif	/* CONFIG_HIBERNATION */
-#else	/* CONFIG_DEBUG_PAGEALLOC || CONFIG_ARCH_HAS_SET_DIRECT_MAP */
+#else	/* CONFIG_DEBUG_PAGEALLOC */
 static inline void debug_pagealloc_map_pages(struct page *page, int numpages) {}
 static inline void debug_pagealloc_unmap_pages(struct page *page, int numpages) {}
 #ifdef CONFIG_HIBERNATION
 static inline bool kernel_page_present(struct page *page) { return true; }
 #endif	/* CONFIG_HIBERNATION */
-#endif	/* CONFIG_DEBUG_PAGEALLOC || CONFIG_ARCH_HAS_SET_DIRECT_MAP */
+#endif	/* CONFIG_DEBUG_PAGEALLOC */
 
 #ifdef __HAVE_ARCH_GATE_AREA
 extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm);
-- 
cgit v1.2.3


From 32a0de886eb3cb7e6990da27a9cdfa50baa8be64 Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.ibm.com>
Date: Mon, 14 Dec 2020 19:10:35 -0800
Subject: arch, mm: make kernel_page_present() always available

For architectures that enable ARCH_HAS_SET_MEMORY having the ability to
verify that a page is mapped in the kernel direct map can be useful
regardless of hibernation.

Add RISC-V implementation of kernel_page_present(), update its forward
declarations and stubs to be a part of set_memory API and remove ugly
ifdefery in inlcude/linux/mm.h around current declarations of
kernel_page_present().

Link: https://lkml.kernel.org/r/20201109192128.960-5-rppt@kernel.org
Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: "Edgecombe, Rick P" <rick.p.edgecombe@intel.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Len Brown <len.brown@intel.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arm64/include/asm/cacheflush.h |  1 +
 arch/arm64/mm/pageattr.c            |  4 +---
 arch/riscv/include/asm/set_memory.h |  1 +
 arch/riscv/mm/pageattr.c            | 29 +++++++++++++++++++++++++++++
 arch/x86/include/asm/set_memory.h   |  1 +
 arch/x86/mm/pat/set_memory.c        |  4 +---
 include/linux/mm.h                  |  7 -------
 include/linux/set_memory.h          |  5 +++++
 8 files changed, 39 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index 9384fd8fc13c..45217f21f1fe 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -140,6 +140,7 @@ int set_memory_valid(unsigned long addr, int numpages, int enable);
 
 int set_direct_map_invalid_noflush(struct page *page);
 int set_direct_map_default_noflush(struct page *page);
+bool kernel_page_present(struct page *page);
 
 #include <asm-generic/cacheflush.h>
 
diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c
index 439325532be1..92eccaf595c8 100644
--- a/arch/arm64/mm/pageattr.c
+++ b/arch/arm64/mm/pageattr.c
@@ -186,8 +186,8 @@ void __kernel_map_pages(struct page *page, int numpages, int enable)
 
 	set_memory_valid((unsigned long)page_address(page), numpages, enable);
 }
+#endif /* CONFIG_DEBUG_PAGEALLOC */
 
-#ifdef CONFIG_HIBERNATION
 /*
  * This function is used to determine if a linear map page has been marked as
  * not-valid. Walk the page table and check the PTE_VALID bit. This is based
@@ -234,5 +234,3 @@ bool kernel_page_present(struct page *page)
 	ptep = pte_offset_kernel(pmdp, addr);
 	return pte_valid(READ_ONCE(*ptep));
 }
-#endif /* CONFIG_HIBERNATION */
-#endif /* CONFIG_DEBUG_PAGEALLOC */
diff --git a/arch/riscv/include/asm/set_memory.h b/arch/riscv/include/asm/set_memory.h
index 4c5bae7ca01c..d690b08dff2a 100644
--- a/arch/riscv/include/asm/set_memory.h
+++ b/arch/riscv/include/asm/set_memory.h
@@ -24,6 +24,7 @@ static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; }
 
 int set_direct_map_invalid_noflush(struct page *page);
 int set_direct_map_default_noflush(struct page *page);
+bool kernel_page_present(struct page *page);
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c
index 321b09d2e2ea..87ba5a68bbb8 100644
--- a/arch/riscv/mm/pageattr.c
+++ b/arch/riscv/mm/pageattr.c
@@ -198,3 +198,32 @@ void __kernel_map_pages(struct page *page, int numpages, int enable)
 			     __pgprot(0), __pgprot(_PAGE_PRESENT));
 }
 #endif
+
+bool kernel_page_present(struct page *page)
+{
+	unsigned long addr = (unsigned long)page_address(page);
+	pgd_t *pgd;
+	pud_t *pud;
+	p4d_t *p4d;
+	pmd_t *pmd;
+	pte_t *pte;
+
+	pgd = pgd_offset_k(addr);
+	if (!pgd_present(*pgd))
+		return false;
+
+	p4d = p4d_offset(pgd, addr);
+	if (!p4d_present(*p4d))
+		return false;
+
+	pud = pud_offset(p4d, addr);
+	if (!pud_present(*pud))
+		return false;
+
+	pmd = pmd_offset(pud, addr);
+	if (!pmd_present(*pmd))
+		return false;
+
+	pte = pte_offset_kernel(pmd, addr);
+	return pte_present(*pte);
+}
diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h
index 5948218f35c5..4352f08bfbb5 100644
--- a/arch/x86/include/asm/set_memory.h
+++ b/arch/x86/include/asm/set_memory.h
@@ -82,6 +82,7 @@ int set_pages_rw(struct page *page, int numpages);
 
 int set_direct_map_invalid_noflush(struct page *page);
 int set_direct_map_default_noflush(struct page *page);
+bool kernel_page_present(struct page *page);
 
 extern int kernel_set_to_readonly;
 
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index bc9be96b777f..16f878c26667 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -2226,8 +2226,8 @@ void __kernel_map_pages(struct page *page, int numpages, int enable)
 
 	arch_flush_lazy_mmu_mode();
 }
+#endif /* CONFIG_DEBUG_PAGEALLOC */
 
-#ifdef CONFIG_HIBERNATION
 bool kernel_page_present(struct page *page)
 {
 	unsigned int level;
@@ -2239,8 +2239,6 @@ bool kernel_page_present(struct page *page)
 	pte = lookup_address((unsigned long)page_address(page), &level);
 	return (pte_val(*pte) & _PAGE_PRESENT);
 }
-#endif /* CONFIG_HIBERNATION */
-#endif /* CONFIG_DEBUG_PAGEALLOC */
 
 int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
 				   unsigned numpages, unsigned long page_flags)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 7a67bdf3df5e..5ec79757eeae 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2949,16 +2949,9 @@ static inline void debug_pagealloc_unmap_pages(struct page *page, int numpages)
 	if (debug_pagealloc_enabled_static())
 		__kernel_map_pages(page, numpages, 0);
 }
-
-#ifdef CONFIG_HIBERNATION
-extern bool kernel_page_present(struct page *page);
-#endif	/* CONFIG_HIBERNATION */
 #else	/* CONFIG_DEBUG_PAGEALLOC */
 static inline void debug_pagealloc_map_pages(struct page *page, int numpages) {}
 static inline void debug_pagealloc_unmap_pages(struct page *page, int numpages) {}
-#ifdef CONFIG_HIBERNATION
-static inline bool kernel_page_present(struct page *page) { return true; }
-#endif	/* CONFIG_HIBERNATION */
 #endif	/* CONFIG_DEBUG_PAGEALLOC */
 
 #ifdef __HAVE_ARCH_GATE_AREA
diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h
index 860e0f843c12..fe1aa4e54680 100644
--- a/include/linux/set_memory.h
+++ b/include/linux/set_memory.h
@@ -23,6 +23,11 @@ static inline int set_direct_map_default_noflush(struct page *page)
 {
 	return 0;
 }
+
+static inline bool kernel_page_present(struct page *page)
+{
+	return true;
+}
 #endif
 
 #ifndef set_mce_nospec
-- 
cgit v1.2.3


From 952eaf815925f106eb6b68346b3458a68bb18ec1 Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Mon, 14 Dec 2020 19:10:53 -0800
Subject: mm, page_alloc: cache pageset high and batch in struct zone

All per-cpu pagesets for a zone use the same high and batch values, that
are duplicated there just for performance (locality) reasons.  This patch
adds the same variables also to struct zone as a shared copy.

This will be useful later for making possible to disable pcplists
temporarily by setting high value to 0, while remembering the values for
restoring them later.  But we can also immediately benefit from not
updating pagesets of all possible cpus in case the newly recalculated
values (after sysctl change or memory online/offline) are actually
unchanged from the previous ones.

Link: https://lkml.kernel.org/r/20201111092812.11329-6-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmzone.h |  6 ++++++
 mm/page_alloc.c        | 16 ++++++++++++++--
 2 files changed, 20 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 6e0025b5a88f..4eee08b0062b 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -470,6 +470,12 @@ struct zone {
 #endif
 	struct pglist_data	*zone_pgdat;
 	struct per_cpu_pageset __percpu *pageset;
+	/*
+	 * the high and batch values are copied to individual pagesets for
+	 * faster access
+	 */
+	int pageset_high;
+	int pageset_batch;
 
 #ifndef CONFIG_SPARSEMEM
 	/*
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 0c47af9e97c6..c3d1752b57dc 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5920,6 +5920,9 @@ static void build_zonelists(pg_data_t *pgdat)
  * Other parts of the kernel may not check if the zone is available.
  */
 static void pageset_init(struct per_cpu_pageset *p);
+/* These effectively disable the pcplists in the boot pageset completely */
+#define BOOT_PAGESET_HIGH	0
+#define BOOT_PAGESET_BATCH	1
 static DEFINE_PER_CPU(struct per_cpu_pageset, boot_pageset);
 static DEFINE_PER_CPU(struct per_cpu_nodestat, boot_nodestats);
 
@@ -6309,8 +6312,8 @@ static void pageset_init(struct per_cpu_pageset *p)
 	 * need to be as careful as pageset_update() as nobody can access the
 	 * pageset yet.
 	 */
-	pcp->high = 0;
-	pcp->batch = 1;
+	pcp->high = BOOT_PAGESET_HIGH;
+	pcp->batch = BOOT_PAGESET_BATCH;
 }
 
 /*
@@ -6334,6 +6337,13 @@ static void zone_set_pageset_high_and_batch(struct zone *zone)
 		new_batch = max(1UL, 1 * new_batch);
 	}
 
+	if (zone->pageset_high == new_high &&
+	    zone->pageset_batch == new_batch)
+		return;
+
+	zone->pageset_high = new_high;
+	zone->pageset_batch = new_batch;
+
 	for_each_possible_cpu(cpu) {
 		p = per_cpu_ptr(zone->pageset, cpu);
 		pageset_update(&p->pcp, new_high, new_batch);
@@ -6394,6 +6404,8 @@ static __meminit void zone_pcp_init(struct zone *zone)
 	 * offset of a (static) per cpu variable into the per cpu area.
 	 */
 	zone->pageset = &boot_pageset;
+	zone->pageset_high = BOOT_PAGESET_HIGH;
+	zone->pageset_batch = BOOT_PAGESET_BATCH;
 
 	if (populated_zone(zone))
 		printk(KERN_DEBUG "  %s zone: %lu pages, LIFO batch:%u\n",
-- 
cgit v1.2.3


From 2ee08717da50160c20056f6d6b76afdf65db33ab Mon Sep 17 00:00:00 2001
From: Miaohe Lin <linmiaohe@huawei.com>
Date: Mon, 14 Dec 2020 19:11:02 -0800
Subject: include/linux/page-flags.h: remove unused __[Set|Clear]PagePrivate

They are not used anymore.

Link: https://lkml.kernel.org/r/20201009135914.64826-1-linmiaohe@huawei.com
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/page-flags.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 4f6ba9379112..50cbf5e931bc 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -363,8 +363,7 @@ PAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL)
  * for its own purposes.
  * - PG_private and PG_private_2 cause releasepage() and co to be invoked
  */
-PAGEFLAG(Private, private, PF_ANY) __SETPAGEFLAG(Private, private, PF_ANY)
-	__CLEARPAGEFLAG(Private, private, PF_ANY)
+PAGEFLAG(Private, private, PF_ANY)
 PAGEFLAG(Private2, private_2, PF_ANY) TESTSCFLAG(Private2, private_2, PF_ANY)
 PAGEFLAG(OwnerPriv1, owner_priv_1, PF_ANY)
 	TESTCLEARFLAG(OwnerPriv1, owner_priv_1, PF_ANY)
-- 
cgit v1.2.3


From 3b12da6d1d4adff087939c071e0d74a7857439a0 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Mon, 14 Dec 2020 19:11:05 -0800
Subject: mm/page-flags: fix comment

We haven't had 'dontuse' flags since 2002.  Replace this obsolete warning
with a hopefully more useful one.

Link: https://lkml.kernel.org/r/20201027025823.3704-1-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: William Kucharski <william.kucharski@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/page-flags.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 50cbf5e931bc..c1368af622c7 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -86,8 +86,7 @@
  */
 
 /*
- * Don't use the *_dontuse flags.  Use the macros.  Otherwise you'll break
- * locked- and dirty-page accounting.
+ * Don't use the pageflags directly.  Use the PageFoo macros.
  *
  * The page flags field is split into two parts, the main flags area
  * which extends from the low bits upwards, and the fields area which
-- 
cgit v1.2.3


From ebfe1b8f6ea5d83d8c1aa18ddd8ede432a7414e7 Mon Sep 17 00:00:00 2001
From: Ralph Campbell <rcampbell@nvidia.com>
Date: Mon, 14 Dec 2020 19:11:58 -0800
Subject: include/linux/huge_mm.h: remove extern keyword

The external function definitions don't need the "extern" keyword.  Remove
them so future changes don't copy the function definition style.

Link: https://lkml.kernel.org/r/20201106235135.32109-1-rcampbell@nvidia.com
Signed-off-by: Ralph Campbell <rcampbell@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/huge_mm.h | 93 ++++++++++++++++++++++---------------------------
 1 file changed, 41 insertions(+), 52 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 0365aa97f8e7..6a19f35f836b 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -7,43 +7,37 @@
 
 #include <linux/fs.h> /* only for vma_is_dax() */
 
-extern vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf);
-extern int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-			 pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
-			 struct vm_area_struct *vma);
-extern void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd);
-extern int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-			 pud_t *dst_pud, pud_t *src_pud, unsigned long addr,
-			 struct vm_area_struct *vma);
+vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf);
+int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+		  pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
+		  struct vm_area_struct *vma);
+void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd);
+int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+		  pud_t *dst_pud, pud_t *src_pud, unsigned long addr,
+		  struct vm_area_struct *vma);
 
 #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
-extern void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud);
+void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud);
 #else
 static inline void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud)
 {
 }
 #endif
 
-extern vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd);
-extern struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
-					  unsigned long addr,
-					  pmd_t *pmd,
-					  unsigned int flags);
-extern bool madvise_free_huge_pmd(struct mmu_gather *tlb,
-			struct vm_area_struct *vma,
-			pmd_t *pmd, unsigned long addr, unsigned long next);
-extern int zap_huge_pmd(struct mmu_gather *tlb,
-			struct vm_area_struct *vma,
-			pmd_t *pmd, unsigned long addr);
-extern int zap_huge_pud(struct mmu_gather *tlb,
-			struct vm_area_struct *vma,
-			pud_t *pud, unsigned long addr);
-extern bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
-			 unsigned long new_addr,
-			 pmd_t *old_pmd, pmd_t *new_pmd);
-extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
-			unsigned long addr, pgprot_t newprot,
-			unsigned long cp_flags);
+vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd);
+struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
+				   unsigned long addr, pmd_t *pmd,
+				   unsigned int flags);
+bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
+			   pmd_t *pmd, unsigned long addr, unsigned long next);
+int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd,
+		 unsigned long addr);
+int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud,
+		 unsigned long addr);
+bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
+		   unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd);
+int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr,
+		    pgprot_t newprot, unsigned long cp_flags);
 vm_fault_t vmf_insert_pfn_pmd_prot(struct vm_fault *vmf, pfn_t pfn,
 				   pgprot_t pgprot, bool write);
 
@@ -100,13 +94,13 @@ enum transparent_hugepage_flag {
 struct kobject;
 struct kobj_attribute;
 
-extern ssize_t single_hugepage_flag_store(struct kobject *kobj,
-				 struct kobj_attribute *attr,
-				 const char *buf, size_t count,
-				 enum transparent_hugepage_flag flag);
-extern ssize_t single_hugepage_flag_show(struct kobject *kobj,
-				struct kobj_attribute *attr, char *buf,
-				enum transparent_hugepage_flag flag);
+ssize_t single_hugepage_flag_store(struct kobject *kobj,
+				   struct kobj_attribute *attr,
+				   const char *buf, size_t count,
+				   enum transparent_hugepage_flag flag);
+ssize_t single_hugepage_flag_show(struct kobject *kobj,
+				  struct kobj_attribute *attr, char *buf,
+				  enum transparent_hugepage_flag flag);
 extern struct kobj_attribute shmem_enabled_attr;
 
 #define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT)
@@ -179,12 +173,11 @@ static inline bool transhuge_vma_suitable(struct vm_area_struct *vma,
 	(transparent_hugepage_flags &					\
 	 (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG))
 
-extern unsigned long thp_get_unmapped_area(struct file *filp,
-		unsigned long addr, unsigned long len, unsigned long pgoff,
-		unsigned long flags);
+unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr,
+		unsigned long len, unsigned long pgoff, unsigned long flags);
 
-extern void prep_transhuge_page(struct page *page);
-extern void free_transhuge_page(struct page *page);
+void prep_transhuge_page(struct page *page);
+void free_transhuge_page(struct page *page);
 bool is_transparent_hugepage(struct page *page);
 
 bool can_split_huge_page(struct page *page, int *pextra_pins);
@@ -222,16 +215,12 @@ void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud,
 			__split_huge_pud(__vma, __pud, __address);	\
 	}  while (0)
 
-extern int hugepage_madvise(struct vm_area_struct *vma,
-			    unsigned long *vm_flags, int advice);
-extern void vma_adjust_trans_huge(struct vm_area_struct *vma,
-				    unsigned long start,
-				    unsigned long end,
-				    long adjust_next);
-extern spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd,
-		struct vm_area_struct *vma);
-extern spinlock_t *__pud_trans_huge_lock(pud_t *pud,
-		struct vm_area_struct *vma);
+int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags,
+		     int advice);
+void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start,
+			   unsigned long end, long adjust_next);
+spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma);
+spinlock_t *__pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma);
 
 static inline int is_swap_pmd(pmd_t pmd)
 {
@@ -294,7 +283,7 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
 struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,
 		pud_t *pud, int flags, struct dev_pagemap **pgmap);
 
-extern vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd);
+vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd);
 
 extern struct page *huge_zero_page;
 
-- 
cgit v1.2.3


From 2271b016bf368d19d60531dd5ddd4375b4dae0ab Mon Sep 17 00:00:00 2001
From: Hui Su <sh_def@163.com>
Date: Mon, 14 Dec 2020 19:12:46 -0800
Subject: mm/compaction: make defer_compaction and compaction_deferred static

defer_compaction() and compaction_deferred() and compaction_restarting()
in mm/compaction.c won't be used in other files, so make them static, and
remove the declaration in the header file.

Take the chance to fix a typo.

Link: https://lkml.kernel.org/r/20201123170801.GA9625@rlk
Signed-off-by: Hui Su <sh_def@163.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Nitin Gupta <nigupta@nvidia.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Mateusz Nosek <mateusznosek0@gmail.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/compaction.h | 12 ------------
 mm/compaction.c            |  8 ++++----
 2 files changed, 4 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 1de5a1151ee7..ed4070ed41ef 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -98,11 +98,8 @@ extern void reset_isolation_suitable(pg_data_t *pgdat);
 extern enum compact_result compaction_suitable(struct zone *zone, int order,
 		unsigned int alloc_flags, int highest_zoneidx);
 
-extern void defer_compaction(struct zone *zone, int order);
-extern bool compaction_deferred(struct zone *zone, int order);
 extern void compaction_defer_reset(struct zone *zone, int order,
 				bool alloc_success);
-extern bool compaction_restarting(struct zone *zone, int order);
 
 /* Compaction has made some progress and retrying makes sense */
 static inline bool compaction_made_progress(enum compact_result result)
@@ -194,15 +191,6 @@ static inline enum compact_result compaction_suitable(struct zone *zone, int ord
 	return COMPACT_SKIPPED;
 }
 
-static inline void defer_compaction(struct zone *zone, int order)
-{
-}
-
-static inline bool compaction_deferred(struct zone *zone, int order)
-{
-	return true;
-}
-
 static inline bool compaction_made_progress(enum compact_result result)
 {
 	return false;
diff --git a/mm/compaction.c b/mm/compaction.c
index c1370828acee..dbcfdfce1b82 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -157,7 +157,7 @@ EXPORT_SYMBOL(__ClearPageMovable);
  * allocation success. 1 << compact_defer_shift, compactions are skipped up
  * to a limit of 1 << COMPACT_MAX_DEFER_SHIFT
  */
-void defer_compaction(struct zone *zone, int order)
+static void defer_compaction(struct zone *zone, int order)
 {
 	zone->compact_considered = 0;
 	zone->compact_defer_shift++;
@@ -172,7 +172,7 @@ void defer_compaction(struct zone *zone, int order)
 }
 
 /* Returns true if compaction should be skipped this time */
-bool compaction_deferred(struct zone *zone, int order)
+static bool compaction_deferred(struct zone *zone, int order)
 {
 	unsigned long defer_limit = 1UL << zone->compact_defer_shift;
 
@@ -209,7 +209,7 @@ void compaction_defer_reset(struct zone *zone, int order,
 }
 
 /* Returns true if restarting compaction after many failures */
-bool compaction_restarting(struct zone *zone, int order)
+static bool compaction_restarting(struct zone *zone, int order)
 {
 	if (order < zone->compact_order_failed)
 		return false;
@@ -237,7 +237,7 @@ static void reset_cached_positions(struct zone *zone)
 }
 
 /*
- * Compound pages of >= pageblock_order should consistenly be skipped until
+ * Compound pages of >= pageblock_order should consistently be skipped until
  * released. It is always pointless to compact pages of such order (if they are
  * migratable), and the pageblocks they occupy cannot contain any free pages.
  */
-- 
cgit v1.2.3


From 0060ef3b4e6dd1410da164d48a595eadb2fb02f7 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Mon, 14 Dec 2020 19:12:59 -0800
Subject: mm: support THPs in zero_user_segments

We can only kmap() one subpage of a THP at a time, so loop over all
relevant subpages, skipping ones which don't need to be zeroed.  This is
too large to inline when THPs are enabled and we actually need highmem, so
put it in highmem.c.

[willy@infradead.org: start1 was allowed to be less than start2]

Link: https://lkml.kernel.org/r/20201124041507.28996-1-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: Song Liu <songliubraving@fb.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Naresh Kamboju <naresh.kamboju@linaro.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/highmem.h | 19 ++++++++++++++----
 mm/highmem.c            | 52 +++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 67 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 14e6202ce47f..8e21fe82b3a3 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -284,13 +284,22 @@ static inline void clear_highpage(struct page *page)
 	kunmap_atomic(kaddr);
 }
 
+/*
+ * If we pass in a base or tail page, we can zero up to PAGE_SIZE.
+ * If we pass in a head page, we can zero up to the size of the compound page.
+ */
+#if defined(CONFIG_HIGHMEM) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
+void zero_user_segments(struct page *page, unsigned start1, unsigned end1,
+		unsigned start2, unsigned end2);
+#else /* !HIGHMEM || !TRANSPARENT_HUGEPAGE */
 static inline void zero_user_segments(struct page *page,
-	unsigned start1, unsigned end1,
-	unsigned start2, unsigned end2)
+		unsigned start1, unsigned end1,
+		unsigned start2, unsigned end2)
 {
 	void *kaddr = kmap_atomic(page);
+	unsigned int i;
 
-	BUG_ON(end1 > PAGE_SIZE || end2 > PAGE_SIZE);
+	BUG_ON(end1 > page_size(page) || end2 > page_size(page));
 
 	if (end1 > start1)
 		memset(kaddr + start1, 0, end1 - start1);
@@ -299,8 +308,10 @@ static inline void zero_user_segments(struct page *page,
 		memset(kaddr + start2, 0, end2 - start2);
 
 	kunmap_atomic(kaddr);
-	flush_dcache_page(page);
+	for (i = 0; i < compound_nr(page); i++)
+		flush_dcache_page(page + i);
 }
+#endif /* !HIGHMEM || !TRANSPARENT_HUGEPAGE */
 
 static inline void zero_user_segment(struct page *page,
 	unsigned start, unsigned end)
diff --git a/mm/highmem.c b/mm/highmem.c
index 1352a27951e3..0ee87a9e0cbf 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -369,6 +369,58 @@ void kunmap_high(struct page *page)
 }
 
 EXPORT_SYMBOL(kunmap_high);
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+void zero_user_segments(struct page *page, unsigned start1, unsigned end1,
+		unsigned start2, unsigned end2)
+{
+	unsigned int i;
+
+	BUG_ON(end1 > page_size(page) || end2 > page_size(page));
+
+	for (i = 0; i < compound_nr(page); i++) {
+		void *kaddr = NULL;
+
+		if (start1 < PAGE_SIZE || start2 < PAGE_SIZE)
+			kaddr = kmap_atomic(page + i);
+
+		if (start1 >= PAGE_SIZE) {
+			start1 -= PAGE_SIZE;
+			end1 -= PAGE_SIZE;
+		} else {
+			unsigned this_end = min_t(unsigned, end1, PAGE_SIZE);
+
+			if (end1 > start1)
+				memset(kaddr + start1, 0, this_end - start1);
+			end1 -= this_end;
+			start1 = 0;
+		}
+
+		if (start2 >= PAGE_SIZE) {
+			start2 -= PAGE_SIZE;
+			end2 -= PAGE_SIZE;
+		} else {
+			unsigned this_end = min_t(unsigned, end2, PAGE_SIZE);
+
+			if (end2 > start2)
+				memset(kaddr + start2, 0, this_end - start2);
+			end2 -= this_end;
+			start2 = 0;
+		}
+
+		if (kaddr) {
+			kunmap_atomic(kaddr);
+			flush_dcache_page(page + i);
+		}
+
+		if (!end1 && !end2)
+			break;
+	}
+
+	BUG_ON((start1 | start2 | end1 | end2) != 0);
+}
+EXPORT_SYMBOL(zero_user_segments);
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif	/* CONFIG_HIGHMEM */
 
 #if defined(HASHED_PAGE_VIRTUAL)
-- 
cgit v1.2.3


From 236c32eb109696590b7428957eda50cc05e22af8 Mon Sep 17 00:00:00 2001
From: Yang Shi <shy828301@gmail.com>
Date: Mon, 14 Dec 2020 19:13:13 -0800
Subject: mm: migrate: clean up migrate_prep{_local}

The migrate_prep{_local} never fails, so it is pointless to have return
value and check the return value.

Link: https://lkml.kernel.org/r/20201113205359.556831-5-shy828301@gmail.com
Signed-off-by: Yang Shi <shy828301@gmail.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Song Liu <songliubraving@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/migrate.h | 4 ++--
 mm/mempolicy.c          | 8 ++------
 mm/migrate.c            | 8 ++------
 3 files changed, 6 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 0f8d1583fa8e..4594838a0f7c 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -45,8 +45,8 @@ extern struct page *alloc_migration_target(struct page *page, unsigned long priv
 extern int isolate_movable_page(struct page *page, isolate_mode_t mode);
 extern void putback_movable_page(struct page *page);
 
-extern int migrate_prep(void);
-extern int migrate_prep_local(void);
+extern void migrate_prep(void);
+extern void migrate_prep_local(void);
 extern void migrate_page_states(struct page *newpage, struct page *page);
 extern void migrate_page_copy(struct page *newpage, struct page *page);
 extern int migrate_huge_page_move_mapping(struct address_space *mapping,
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 3ca4898f3f24..8cf96bd21341 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1114,9 +1114,7 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
 	int err;
 	nodemask_t tmp;
 
-	err = migrate_prep();
-	if (err)
-		return err;
+	migrate_prep();
 
 	mmap_read_lock(mm);
 
@@ -1315,9 +1313,7 @@ static long do_mbind(unsigned long start, unsigned long len,
 
 	if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
 
-		err = migrate_prep();
-		if (err)
-			goto mpol_out;
+		migrate_prep();
 	}
 	{
 		NODEMASK_SCRATCH(scratch);
diff --git a/mm/migrate.c b/mm/migrate.c
index a7ccda55ca82..76e2a6f3749f 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -62,7 +62,7 @@
  * to be migrated using isolate_lru_page(). If scheduling work on other CPUs is
  * undesirable, use migrate_prep_local()
  */
-int migrate_prep(void)
+void migrate_prep(void)
 {
 	/*
 	 * Clear the LRU lists so pages can be isolated.
@@ -71,16 +71,12 @@ int migrate_prep(void)
 	 * pages that may be busy.
 	 */
 	lru_add_drain_all();
-
-	return 0;
 }
 
 /* Do the necessary work of migrate_prep but not if it involves other CPUs */
-int migrate_prep_local(void)
+void migrate_prep_local(void)
 {
 	lru_add_drain();
-
-	return 0;
 }
 
 int isolate_movable_page(struct page *page, isolate_mode_t mode)
-- 
cgit v1.2.3


From 04013513cc84c401c7de9023ff3eda7863fc4add Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Mon, 14 Dec 2020 19:13:30 -0800
Subject: mm, page_alloc: do not rely on the order of page_poison and
 init_on_alloc/free parameters

Patch series "cleanup page poisoning", v3.

I have identified a number of issues and opportunities for cleanup with
CONFIG_PAGE_POISON and friends:

 - interaction with init_on_alloc and init_on_free parameters depends on
   the order of parameters (Patch 1)

 - the boot time enabling uses static key, but inefficienty (Patch 2)

 - sanity checking is incompatible with hibernation (Patch 3)

 - CONFIG_PAGE_POISONING_NO_SANITY can be removed now that we have
   init_on_free (Patch 4)

 - CONFIG_PAGE_POISONING_ZERO can be most likely removed now that we
   have init_on_free (Patch 5)

This patch (of 5):

Enabling page_poison=1 together with init_on_alloc=1 or init_on_free=1
produces a warning in dmesg that page_poison takes precedence.  However,
as these warnings are printed in early_param handlers for
init_on_alloc/free, they are not printed if page_poison is enabled later
on the command line (handlers are called in the order of their
parameters), or when init_on_alloc/free is always enabled by the
respective config option - before the page_poison early param handler is
called, it is not considered to be enabled.  This is inconsistent.

We can remove the dependency on order by making the init_on_* parameters
only set a boolean variable, and postponing the evaluation after all early
params have been processed.  Introduce a new
init_mem_debugging_and_hardening() function for that, and move the related
debug_pagealloc processing there as well.

As a result init_mem_debugging_and_hardening() knows always accurately if
init_on_* and/or page_poison options were enabled.  Thus we can also
optimize want_init_on_alloc() and want_init_on_free().  We don't need to
check page_poisoning_enabled() there, we can instead not enable the
init_on_* static keys at all, if page poisoning is enabled.  This results
in a simpler and more effective code.

Link: https://lkml.kernel.org/r/20201113104033.22907-1-vbabka@suse.cz
Link: https://lkml.kernel.org/r/20201113104033.22907-2-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mateusz Nosek <mateusznosek0@gmail.com>
Cc: Laura Abbott <labbott@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h | 20 ++-----------
 init/main.c        |  2 +-
 mm/page_alloc.c    | 88 ++++++++++++++++++++++++++----------------------------
 3 files changed, 46 insertions(+), 64 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 5ec79757eeae..591c784277ea 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2872,6 +2872,7 @@ extern int apply_to_existing_page_range(struct mm_struct *mm,
 				   unsigned long address, unsigned long size,
 				   pte_fn_t fn, void *data);
 
+extern void init_mem_debugging_and_hardening(void);
 #ifdef CONFIG_PAGE_POISONING
 extern bool page_poisoning_enabled(void);
 extern void kernel_poison_pages(struct page *page, int numpages, int enable);
@@ -2881,35 +2882,20 @@ static inline void kernel_poison_pages(struct page *page, int numpages,
 					int enable) { }
 #endif
 
-#ifdef CONFIG_INIT_ON_ALLOC_DEFAULT_ON
-DECLARE_STATIC_KEY_TRUE(init_on_alloc);
-#else
 DECLARE_STATIC_KEY_FALSE(init_on_alloc);
-#endif
 static inline bool want_init_on_alloc(gfp_t flags)
 {
-	if (static_branch_unlikely(&init_on_alloc) &&
-	    !page_poisoning_enabled())
+	if (static_branch_unlikely(&init_on_alloc))
 		return true;
 	return flags & __GFP_ZERO;
 }
 
-#ifdef CONFIG_INIT_ON_FREE_DEFAULT_ON
-DECLARE_STATIC_KEY_TRUE(init_on_free);
-#else
 DECLARE_STATIC_KEY_FALSE(init_on_free);
-#endif
 static inline bool want_init_on_free(void)
 {
-	return static_branch_unlikely(&init_on_free) &&
-	       !page_poisoning_enabled();
+	return static_branch_unlikely(&init_on_free);
 }
 
-#ifdef CONFIG_DEBUG_PAGEALLOC
-extern void init_debug_pagealloc(void);
-#else
-static inline void init_debug_pagealloc(void) {}
-#endif
 extern bool _debug_pagealloc_enabled_early;
 DECLARE_STATIC_KEY_FALSE(_debug_pagealloc_enabled);
 
diff --git a/init/main.c b/init/main.c
index 404366e1a64d..3024c4db17a9 100644
--- a/init/main.c
+++ b/init/main.c
@@ -824,7 +824,7 @@ static void __init mm_init(void)
 	 * bigger than MAX_ORDER unless SPARSEMEM.
 	 */
 	page_ext_init_flatmem();
-	init_debug_pagealloc();
+	init_mem_debugging_and_hardening();
 	report_meminit();
 	mem_init();
 	/* page_owner must be initialized after buddy is ready */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 521d29718c9e..3fd0c8d5745f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -167,53 +167,26 @@ unsigned long totalcma_pages __read_mostly;
 
 int percpu_pagelist_fraction;
 gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK;
-#ifdef CONFIG_INIT_ON_ALLOC_DEFAULT_ON
-DEFINE_STATIC_KEY_TRUE(init_on_alloc);
-#else
 DEFINE_STATIC_KEY_FALSE(init_on_alloc);
-#endif
 EXPORT_SYMBOL(init_on_alloc);
 
-#ifdef CONFIG_INIT_ON_FREE_DEFAULT_ON
-DEFINE_STATIC_KEY_TRUE(init_on_free);
-#else
 DEFINE_STATIC_KEY_FALSE(init_on_free);
-#endif
 EXPORT_SYMBOL(init_on_free);
 
+static bool _init_on_alloc_enabled_early __read_mostly
+				= IS_ENABLED(CONFIG_INIT_ON_ALLOC_DEFAULT_ON);
 static int __init early_init_on_alloc(char *buf)
 {
-	int ret;
-	bool bool_result;
 
-	ret = kstrtobool(buf, &bool_result);
-	if (ret)
-		return ret;
-	if (bool_result && page_poisoning_enabled())
-		pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, will take precedence over init_on_alloc\n");
-	if (bool_result)
-		static_branch_enable(&init_on_alloc);
-	else
-		static_branch_disable(&init_on_alloc);
-	return 0;
+	return kstrtobool(buf, &_init_on_alloc_enabled_early);
 }
 early_param("init_on_alloc", early_init_on_alloc);
 
+static bool _init_on_free_enabled_early __read_mostly
+				= IS_ENABLED(CONFIG_INIT_ON_FREE_DEFAULT_ON);
 static int __init early_init_on_free(char *buf)
 {
-	int ret;
-	bool bool_result;
-
-	ret = kstrtobool(buf, &bool_result);
-	if (ret)
-		return ret;
-	if (bool_result && page_poisoning_enabled())
-		pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, will take precedence over init_on_free\n");
-	if (bool_result)
-		static_branch_enable(&init_on_free);
-	else
-		static_branch_disable(&init_on_free);
-	return 0;
+	return kstrtobool(buf, &_init_on_free_enabled_early);
 }
 early_param("init_on_free", early_init_on_free);
 
@@ -730,19 +703,6 @@ static int __init early_debug_pagealloc(char *buf)
 }
 early_param("debug_pagealloc", early_debug_pagealloc);
 
-void init_debug_pagealloc(void)
-{
-	if (!debug_pagealloc_enabled())
-		return;
-
-	static_branch_enable(&_debug_pagealloc_enabled);
-
-	if (!debug_guardpage_minorder())
-		return;
-
-	static_branch_enable(&_debug_guardpage_enabled);
-}
-
 static int __init debug_guardpage_minorder_setup(char *buf)
 {
 	unsigned long res;
@@ -794,6 +754,42 @@ static inline void clear_page_guard(struct zone *zone, struct page *page,
 				unsigned int order, int migratetype) {}
 #endif
 
+/*
+ * Enable static keys related to various memory debugging and hardening options.
+ * Some override others, and depend on early params that are evaluated in the
+ * order of appearance. So we need to first gather the full picture of what was
+ * enabled, and then make decisions.
+ */
+void init_mem_debugging_and_hardening(void)
+{
+	if (_init_on_alloc_enabled_early) {
+		if (page_poisoning_enabled())
+			pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, "
+				"will take precedence over init_on_alloc\n");
+		else
+			static_branch_enable(&init_on_alloc);
+	}
+	if (_init_on_free_enabled_early) {
+		if (page_poisoning_enabled())
+			pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, "
+				"will take precedence over init_on_free\n");
+		else
+			static_branch_enable(&init_on_free);
+	}
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+	if (!debug_pagealloc_enabled())
+		return;
+
+	static_branch_enable(&_debug_pagealloc_enabled);
+
+	if (!debug_guardpage_minorder())
+		return;
+
+	static_branch_enable(&_debug_guardpage_enabled);
+#endif
+}
+
 static inline void set_buddy_order(struct page *page, unsigned int order)
 {
 	set_page_private(page, order);
-- 
cgit v1.2.3


From 8db26a3d47354ce7271a8cab03cd65b9d3d610b9 Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Mon, 14 Dec 2020 19:13:34 -0800
Subject: mm, page_poison: use static key more efficiently

Commit 11c9c7edae06 ("mm/page_poison.c: replace bool variable with static
key") changed page_poisoning_enabled() to a static key check.  However,
the function is not inlined, so each check still involves a function call
with overhead not eliminated when page poisoning is disabled.

Analogically to how debug_pagealloc is handled, this patch converts
page_poisoning_enabled() back to boolean check, and introduces
page_poisoning_enabled_static() for fast paths.  Both functions are
inlined.

The function kernel_poison_pages() is also called unconditionally and does
the static key check inside.  Remove it from there and put it to callers.
Also split it to two functions kernel_poison_pages() and
kernel_unpoison_pages() instead of the confusing bool parameter.

Also optimize the check that enables page poisoning instead of
debug_pagealloc for architectures without proper debug_pagealloc support.
Move the check to init_mem_debugging_and_hardening() to enable a single
static key instead of having two static branches in
page_poisoning_enabled_static().

Link: https://lkml.kernel.org/r/20201113104033.22907-3-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: David Hildenbrand <david@redhat.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Laura Abbott <labbott@kernel.org>
Cc: Mateusz Nosek <mateusznosek0@gmail.com>
Cc: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/virtio/virtio_balloon.c |  2 +-
 include/linux/mm.h              | 33 +++++++++++++++++++++----
 mm/page_alloc.c                 | 18 +++++++++++---
 mm/page_poison.c                | 53 ++++++-----------------------------------
 4 files changed, 52 insertions(+), 54 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 481611c09dae..e53faed6ba93 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -1116,7 +1116,7 @@ static int virtballoon_validate(struct virtio_device *vdev)
 	 */
 	if (!want_init_on_free() &&
 	    (IS_ENABLED(CONFIG_PAGE_POISONING_NO_SANITY) ||
-	     !page_poisoning_enabled()))
+	     !page_poisoning_enabled_static()))
 		__virtio_clear_bit(vdev, VIRTIO_BALLOON_F_PAGE_POISON);
 	else if (!virtio_has_feature(vdev, VIRTIO_BALLOON_F_PAGE_POISON))
 		__virtio_clear_bit(vdev, VIRTIO_BALLOON_F_REPORTING);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 591c784277ea..026707a58159 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2874,12 +2874,37 @@ extern int apply_to_existing_page_range(struct mm_struct *mm,
 
 extern void init_mem_debugging_and_hardening(void);
 #ifdef CONFIG_PAGE_POISONING
-extern bool page_poisoning_enabled(void);
-extern void kernel_poison_pages(struct page *page, int numpages, int enable);
+extern void __kernel_poison_pages(struct page *page, int numpages);
+extern void __kernel_unpoison_pages(struct page *page, int numpages);
+extern bool _page_poisoning_enabled_early;
+DECLARE_STATIC_KEY_FALSE(_page_poisoning_enabled);
+static inline bool page_poisoning_enabled(void)
+{
+	return _page_poisoning_enabled_early;
+}
+/*
+ * For use in fast paths after init_mem_debugging() has run, or when a
+ * false negative result is not harmful when called too early.
+ */
+static inline bool page_poisoning_enabled_static(void)
+{
+	return static_branch_unlikely(&_page_poisoning_enabled);
+}
+static inline void kernel_poison_pages(struct page *page, int numpages)
+{
+	if (page_poisoning_enabled_static())
+		__kernel_poison_pages(page, numpages);
+}
+static inline void kernel_unpoison_pages(struct page *page, int numpages)
+{
+	if (page_poisoning_enabled_static())
+		__kernel_unpoison_pages(page, numpages);
+}
 #else
 static inline bool page_poisoning_enabled(void) { return false; }
-static inline void kernel_poison_pages(struct page *page, int numpages,
-					int enable) { }
+static inline bool page_poisoning_enabled_static(void) { return false; }
+static inline void kernel_poison_pages(struct page *page, int numpages) { }
+static inline void kernel_unpoison_pages(struct page *page, int numpages) { }
 #endif
 
 DECLARE_STATIC_KEY_FALSE(init_on_alloc);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3fd0c8d5745f..efcd1baa35e4 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -777,6 +777,17 @@ void init_mem_debugging_and_hardening(void)
 			static_branch_enable(&init_on_free);
 	}
 
+#ifdef CONFIG_PAGE_POISONING
+	/*
+	 * Page poisoning is debug page alloc for some arches. If
+	 * either of those options are enabled, enable poisoning.
+	 */
+	if (page_poisoning_enabled() ||
+	     (!IS_ENABLED(CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC) &&
+	      debug_pagealloc_enabled()))
+		static_branch_enable(&_page_poisoning_enabled);
+#endif
+
 #ifdef CONFIG_DEBUG_PAGEALLOC
 	if (!debug_pagealloc_enabled())
 		return;
@@ -1262,7 +1273,8 @@ static __always_inline bool free_pages_prepare(struct page *page,
 	if (want_init_on_free())
 		kernel_init_free_pages(page, 1 << order);
 
-	kernel_poison_pages(page, 1 << order, 0);
+	kernel_poison_pages(page, 1 << order);
+
 	/*
 	 * arch_free_page() can make the page's contents inaccessible.  s390
 	 * does this.  So nothing which can access the page's contents should
@@ -2219,7 +2231,7 @@ static inline int check_new_page(struct page *page)
 static inline bool free_pages_prezeroed(void)
 {
 	return (IS_ENABLED(CONFIG_PAGE_POISONING_ZERO) &&
-		page_poisoning_enabled()) || want_init_on_free();
+		page_poisoning_enabled_static()) || want_init_on_free();
 }
 
 #ifdef CONFIG_DEBUG_VM
@@ -2281,7 +2293,7 @@ inline void post_alloc_hook(struct page *page, unsigned int order,
 	arch_alloc_page(page, order);
 	debug_pagealloc_map_pages(page, 1 << order);
 	kasan_alloc_pages(page, order);
-	kernel_poison_pages(page, 1 << order, 1);
+	kernel_unpoison_pages(page, 1 << order);
 	set_page_owner(page, order, gfp_flags);
 
 	if (!free_pages_prezeroed() && want_init_on_alloc(gfp_flags))
diff --git a/mm/page_poison.c b/mm/page_poison.c
index ae0482cded87..4d75fc9ccc7a 100644
--- a/mm/page_poison.c
+++ b/mm/page_poison.c
@@ -8,45 +8,17 @@
 #include <linux/ratelimit.h>
 #include <linux/kasan.h>
 
-static DEFINE_STATIC_KEY_FALSE_RO(want_page_poisoning);
+bool _page_poisoning_enabled_early;
+EXPORT_SYMBOL(_page_poisoning_enabled_early);
+DEFINE_STATIC_KEY_FALSE(_page_poisoning_enabled);
+EXPORT_SYMBOL(_page_poisoning_enabled);
 
 static int __init early_page_poison_param(char *buf)
 {
-	int ret;
-	bool tmp;
-
-	ret = strtobool(buf, &tmp);
-	if (ret)
-		return ret;
-
-	if (tmp)
-		static_branch_enable(&want_page_poisoning);
-	else
-		static_branch_disable(&want_page_poisoning);
-
-	return 0;
+	return kstrtobool(buf, &_page_poisoning_enabled_early);
 }
 early_param("page_poison", early_page_poison_param);
 
-/**
- * page_poisoning_enabled - check if page poisoning is enabled
- *
- * Return true if page poisoning is enabled, or false if not.
- */
-bool page_poisoning_enabled(void)
-{
-	/*
-	 * Assumes that debug_pagealloc_enabled is set before
-	 * memblock_free_all.
-	 * Page poisoning is debug page alloc for some arches. If
-	 * either of those options are enabled, enable poisoning.
-	 */
-	return (static_branch_unlikely(&want_page_poisoning) ||
-		(!IS_ENABLED(CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC) &&
-		debug_pagealloc_enabled()));
-}
-EXPORT_SYMBOL_GPL(page_poisoning_enabled);
-
 static void poison_page(struct page *page)
 {
 	void *addr = kmap_atomic(page);
@@ -58,7 +30,7 @@ static void poison_page(struct page *page)
 	kunmap_atomic(addr);
 }
 
-static void poison_pages(struct page *page, int n)
+void __kernel_poison_pages(struct page *page, int n)
 {
 	int i;
 
@@ -117,7 +89,7 @@ static void unpoison_page(struct page *page)
 	kunmap_atomic(addr);
 }
 
-static void unpoison_pages(struct page *page, int n)
+void __kernel_unpoison_pages(struct page *page, int n)
 {
 	int i;
 
@@ -125,17 +97,6 @@ static void unpoison_pages(struct page *page, int n)
 		unpoison_page(page + i);
 }
 
-void kernel_poison_pages(struct page *page, int numpages, int enable)
-{
-	if (!page_poisoning_enabled())
-		return;
-
-	if (enable)
-		unpoison_pages(page, numpages);
-	else
-		poison_pages(page, numpages);
-}
-
 #ifndef CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC
 void __kernel_map_pages(struct page *page, int numpages, int enable)
 {
-- 
cgit v1.2.3


From 03b6c9a3e8805606c0bb4ad41855fac3bf85c3b9 Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Mon, 14 Dec 2020 19:13:38 -0800
Subject: kernel/power: allow hibernation with page_poison sanity checking

Page poisoning used to be incompatible with hibernation, as the state of
poisoned pages was lost after resume, thus enabling CONFIG_HIBERNATION
forces CONFIG_PAGE_POISONING_NO_SANITY.  For the same reason, the
poisoning with zeroes variant CONFIG_PAGE_POISONING_ZERO used to disable
hibernation.  The latter restriction was removed by commit 1ad1410f632d
("PM / Hibernate: allow hibernation with PAGE_POISONING_ZERO") and
similarly for init_on_free by commit 18451f9f9e58 ("PM: hibernate: fix
crashes with init_on_free=1") by making sure free pages are cleared after
resume.

We can use the same mechanism to instead poison free pages with
PAGE_POISON after resume.  This covers both zero and 0xAA patterns.  Thus
we can remove the Kconfig restriction that disables page poison sanity
checking when hibernation is enabled.

Link: https://lkml.kernel.org/r/20201113104033.22907-4-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>	[hibernation]
Reviewed-by: David Hildenbrand <david@redhat.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Laura Abbott <labbott@kernel.org>
Cc: Mateusz Nosek <mateusznosek0@gmail.com>
Cc: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h       |  1 +
 kernel/power/hibernate.c |  2 +-
 kernel/power/power.h     |  2 +-
 kernel/power/snapshot.c  | 14 +++++++++++---
 mm/Kconfig.debug         |  1 -
 5 files changed, 14 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 026707a58159..3e1fe8ca9720 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2903,6 +2903,7 @@ static inline void kernel_unpoison_pages(struct page *page, int numpages)
 #else
 static inline bool page_poisoning_enabled(void) { return false; }
 static inline bool page_poisoning_enabled_static(void) { return false; }
+static inline void __kernel_poison_pages(struct page *page, int nunmpages) { }
 static inline void kernel_poison_pages(struct page *page, int numpages) { }
 static inline void kernel_unpoison_pages(struct page *page, int numpages) { }
 #endif
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 2fc7d509a34f..da0b41914177 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -326,7 +326,7 @@ static int create_image(int platform_mode)
 
 	if (!in_suspend) {
 		events_check_enabled = false;
-		clear_free_pages();
+		clear_or_poison_free_pages();
 	}
 
 	platform_leave(platform_mode);
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 24f12d534515..778bf431ec02 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -106,7 +106,7 @@ extern int create_basic_memory_bitmaps(void);
 extern void free_basic_memory_bitmaps(void);
 extern int hibernate_preallocate_memory(void);
 
-extern void clear_free_pages(void);
+extern void clear_or_poison_free_pages(void);
 
 /**
  *	Auxiliary structure used for reading the snapshot image data and
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index d848377dd8dc..d63560e1cf87 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1178,7 +1178,15 @@ void free_basic_memory_bitmaps(void)
 	pr_debug("Basic memory bitmaps freed\n");
 }
 
-void clear_free_pages(void)
+static void clear_or_poison_free_page(struct page *page)
+{
+	if (page_poisoning_enabled_static())
+		__kernel_poison_pages(page, 1);
+	else if (want_init_on_free())
+		clear_highpage(page);
+}
+
+void clear_or_poison_free_pages(void)
 {
 	struct memory_bitmap *bm = free_pages_map;
 	unsigned long pfn;
@@ -1186,12 +1194,12 @@ void clear_free_pages(void)
 	if (WARN_ON(!(free_pages_map)))
 		return;
 
-	if (IS_ENABLED(CONFIG_PAGE_POISONING_ZERO) || want_init_on_free()) {
+	if (page_poisoning_enabled() || want_init_on_free()) {
 		memory_bm_position_reset(bm);
 		pfn = memory_bm_next_pfn(bm);
 		while (pfn != BM_END_OF_MAP) {
 			if (pfn_valid(pfn))
-				clear_highpage(pfn_to_page(pfn));
+				clear_or_poison_free_page(pfn_to_page(pfn));
 
 			pfn = memory_bm_next_pfn(bm);
 		}
diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug
index 864f129f1937..c57786ad5be9 100644
--- a/mm/Kconfig.debug
+++ b/mm/Kconfig.debug
@@ -64,7 +64,6 @@ config PAGE_OWNER
 
 config PAGE_POISONING
 	bool "Poison pages after freeing"
-	select PAGE_POISONING_NO_SANITY if HIBERNATION
 	help
 	  Fill the pages with poison patterns after free_pages() and verify
 	  the patterns before alloc_pages. The filling of the memory helps
-- 
cgit v1.2.3


From f289041ed4cf9a3f6e8a32068fef9ffb2acc5662 Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Mon, 14 Dec 2020 19:13:45 -0800
Subject: mm, page_poison: remove CONFIG_PAGE_POISONING_ZERO

CONFIG_PAGE_POISONING_ZERO uses the zero pattern instead of 0xAA.  It was
introduced by commit 1414c7f4f7d7 ("mm/page_poisoning.c: allow for zero
poisoning"), noting that using zeroes retains the benefit of sanitizing
content of freed pages, with the benefit of not having to zero them again
on alloc, and the downside of making some forms of corruption (stray
writes of NULLs) harder to detect than with the 0xAA pattern.  Together
with CONFIG_PAGE_POISONING_NO_SANITY it made possible to sanitize the
contents on free without checking it back on alloc.

These days we have the init_on_free() option to achieve sanitization with
zeroes and to save clearing on alloc (and without checking on alloc).
Arguably if someone does choose to check the poison for corruption on
alloc, the savings of not clearing the page are secondary, and it makes
sense to always use the 0xAA poison pattern.  Thus, remove the
CONFIG_PAGE_POISONING_ZERO option for being redundant.

Link: https://lkml.kernel.org/r/20201113104033.22907-6-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Laura Abbott <labbott@kernel.org>
Cc: Mateusz Nosek <mateusznosek0@gmail.com>
Cc: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/poison.h       |  4 ----
 mm/Kconfig.debug             | 12 ------------
 mm/page_alloc.c              |  8 +-------
 tools/include/linux/poison.h |  6 +-----
 4 files changed, 2 insertions(+), 28 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/poison.h b/include/linux/poison.h
index dc8ae5d8db03..aff1c9250c82 100644
--- a/include/linux/poison.h
+++ b/include/linux/poison.h
@@ -27,11 +27,7 @@
 #define TIMER_ENTRY_STATIC	((void *) 0x300 + POISON_POINTER_DELTA)
 
 /********** mm/page_poison.c **********/
-#ifdef CONFIG_PAGE_POISONING_ZERO
-#define PAGE_POISON 0x00
-#else
 #define PAGE_POISON 0xaa
-#endif
 
 /********** mm/page_alloc.c ************/
 
diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug
index 14e29fe5bfa6..1e73717802f8 100644
--- a/mm/Kconfig.debug
+++ b/mm/Kconfig.debug
@@ -80,18 +80,6 @@ config PAGE_POISONING
 
 	  If unsure, say N
 
-config PAGE_POISONING_ZERO
-	bool "Use zero for poisoning instead of debugging value"
-	depends on PAGE_POISONING
-	help
-	   Instead of using the existing poison value, fill the pages with
-	   zeros. This makes it harder to detect when errors are occurring
-	   due to sanitization but the zeroing at free means that it is
-	   no longer necessary to write zeros when GFP_ZERO is used on
-	   allocation.
-
-	   If unsure, say N
-
 config DEBUG_PAGE_REF
 	bool "Enable tracepoint to track down page reference manipulation"
 	depends on DEBUG_KERNEL
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index efcd1baa35e4..918647ff6eef 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2228,12 +2228,6 @@ static inline int check_new_page(struct page *page)
 	return 1;
 }
 
-static inline bool free_pages_prezeroed(void)
-{
-	return (IS_ENABLED(CONFIG_PAGE_POISONING_ZERO) &&
-		page_poisoning_enabled_static()) || want_init_on_free();
-}
-
 #ifdef CONFIG_DEBUG_VM
 /*
  * With DEBUG_VM enabled, order-0 pages are checked for expected state when
@@ -2296,7 +2290,7 @@ inline void post_alloc_hook(struct page *page, unsigned int order,
 	kernel_unpoison_pages(page, 1 << order);
 	set_page_owner(page, order, gfp_flags);
 
-	if (!free_pages_prezeroed() && want_init_on_alloc(gfp_flags))
+	if (!want_init_on_free() && want_init_on_alloc(gfp_flags))
 		kernel_init_free_pages(page, 1 << order);
 }
 
diff --git a/tools/include/linux/poison.h b/tools/include/linux/poison.h
index d29725769107..2e6338ac5eed 100644
--- a/tools/include/linux/poison.h
+++ b/tools/include/linux/poison.h
@@ -35,12 +35,8 @@
  */
 #define TIMER_ENTRY_STATIC	((void *) 0x300 + POISON_POINTER_DELTA)
 
-/********** mm/debug-pagealloc.c **********/
-#ifdef CONFIG_PAGE_POISONING_ZERO
-#define PAGE_POISON 0x00
-#else
+/********** mm/page_poison.c **********/
 #define PAGE_POISON 0xaa
-#endif
 
 /********** mm/page_alloc.c ************/
 
-- 
cgit v1.2.3


From 88dcb9a3fb48c67ec345f1cdbc2a26119d3cb57d Mon Sep 17 00:00:00 2001
From: Alex Shi <alex.shi@linux.alibaba.com>
Date: Tue, 15 Dec 2020 12:33:20 -0800
Subject: mm/thp: move lru_add_page_tail() to huge_memory.c
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Patch series "per memcg lru lock", v21.

This patchset includes 3 parts:

 1) some code cleanup and minimum optimization as preparation

 2) use TestCleanPageLRU as page isolation's precondition

 3) replace per node lru_lock with per memcg per node lru_lock

Current lru_lock is one for each of node, pgdat->lru_lock, that guard
for lru lists, but now we had moved the lru lists into memcg for long
time.  Still using per node lru_lock is clearly unscalable, pages on
each of memcgs have to compete each others for a whole lru_lock.  This
patchset try to use per lruvec/memcg lru_lock to repleace per node lru
lock to guard lru lists, make it scalable for memcgs and get performance
gain.

Currently lru_lock still guards both lru list and page's lru bit, that's
ok.  but if we want to use specific lruvec lock on the page, we need to
pin down the page's lruvec/memcg during locking.  Just taking lruvec
lock first may be undermined by the page's memcg charge/migration.  To
fix this problem, we could take out the page's lru bit clear and use it
as pin down action to block the memcg changes.  That's the reason for
new atomic func TestClearPageLRU.  So now isolating a page need both
actions: TestClearPageLRU and hold the lru_lock.

The typical usage of this is isolate_migratepages_block() in
compaction.c we have to take lru bit before lru lock, that serialized
the page isolation in memcg page charge/migration which will change
page's lruvec and new lru_lock in it.

The above solution suggested by Johannes Weiner, and based on his new
memcg charge path, then have this patchset.  (Hugh Dickins tested and
contributed much code from compaction fix to general code polish, thanks
a lot!).

Daniel Jordan's testing show 62% improvement on modified readtwice case
on his 2P * 10 core * 2 HT broadwell box on v18, which has no much
different with this v20.

 https://lore.kernel.org/lkml/20200915165807.kpp7uhiw7l3loofu@ca-dmjordan1.us.oracle.com/

Thanks to Hugh Dickins and Konstantin Khlebnikov, they both brought this
idea 8 years ago, and others who gave comments as well: Daniel Jordan,
Mel Gorman, Shakeel Butt, Matthew Wilcox, Alexander Duyck etc.

Thanks for Testing support from Intel 0day and Rong Chen, Fengguang Wu,
and Yun Wang.  Hugh Dickins also shared his kbuild-swap case.

This patch (of 19):

lru_add_page_tail() is only used in huge_memory.c, defining it in other
file with a CONFIG_TRANSPARENT_HUGEPAGE macro restrict just looks weird.

Let's move it THP. And make it static as Hugh Dickins suggested.

Link: https://lkml.kernel.org/r/1604566549-62481-1-git-send-email-alex.shi@linux.alibaba.com
Link: https://lkml.kernel.org/r/1604566549-62481-2-git-send-email-alex.shi@linux.alibaba.com
Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Hugh Dickins <hughd@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Tejun Heo <tj@kernel.org>
Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Cc: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Wei Yang <richard.weiyang@gmail.com>
Cc: Alexander Duyck <alexander.duyck@gmail.com>
Cc: "Chen, Rong A" <rong.a.chen@intel.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Jann Horn <jannh@google.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mika Penttilä <mika.penttila@nextfour.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yang Shi <yang.shi@linux.alibaba.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/swap.h |  2 --
 mm/huge_memory.c     | 30 ++++++++++++++++++++++++++++++
 mm/swap.c            | 33 ---------------------------------
 3 files changed, 30 insertions(+), 35 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 667935c0dbd4..5e1e967c225f 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -338,8 +338,6 @@ extern void lru_note_cost(struct lruvec *lruvec, bool file,
 			  unsigned int nr_pages);
 extern void lru_note_cost_page(struct page *);
 extern void lru_cache_add(struct page *);
-extern void lru_add_page_tail(struct page *page, struct page *page_tail,
-			 struct lruvec *lruvec, struct list_head *head);
 extern void mark_page_accessed(struct page *);
 extern void lru_add_drain(void);
 extern void lru_add_drain_cpu(int cpu);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 57d08156acb1..85b50baa7c7e 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2359,6 +2359,36 @@ static void remap_page(struct page *page, unsigned int nr)
 	}
 }
 
+static void lru_add_page_tail(struct page *page, struct page *page_tail,
+		struct lruvec *lruvec, struct list_head *list)
+{
+	VM_BUG_ON_PAGE(!PageHead(page), page);
+	VM_BUG_ON_PAGE(PageCompound(page_tail), page);
+	VM_BUG_ON_PAGE(PageLRU(page_tail), page);
+	lockdep_assert_held(&lruvec_pgdat(lruvec)->lru_lock);
+
+	if (!list)
+		SetPageLRU(page_tail);
+
+	if (likely(PageLRU(page)))
+		list_add_tail(&page_tail->lru, &page->lru);
+	else if (list) {
+		/* page reclaim is reclaiming a huge page */
+		get_page(page_tail);
+		list_add_tail(&page_tail->lru, list);
+	} else {
+		/*
+		 * Head page has not yet been counted, as an hpage,
+		 * so we must account for each subpage individually.
+		 *
+		 * Put page_tail on the list at the correct position
+		 * so they all end up in order.
+		 */
+		add_page_to_lru_list_tail(page_tail, lruvec,
+					  page_lru(page_tail));
+	}
+}
+
 static void __split_huge_page_tail(struct page *head, int tail,
 		struct lruvec *lruvec, struct list_head *list)
 {
diff --git a/mm/swap.c b/mm/swap.c
index 16a525296960..6e3121dd6e07 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -977,39 +977,6 @@ void __pagevec_release(struct pagevec *pvec)
 }
 EXPORT_SYMBOL(__pagevec_release);
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-/* used by __split_huge_page_refcount() */
-void lru_add_page_tail(struct page *page, struct page *page_tail,
-		       struct lruvec *lruvec, struct list_head *list)
-{
-	VM_BUG_ON_PAGE(!PageHead(page), page);
-	VM_BUG_ON_PAGE(PageCompound(page_tail), page);
-	VM_BUG_ON_PAGE(PageLRU(page_tail), page);
-	lockdep_assert_held(&lruvec_pgdat(lruvec)->lru_lock);
-
-	if (!list)
-		SetPageLRU(page_tail);
-
-	if (likely(PageLRU(page)))
-		list_add_tail(&page_tail->lru, &page->lru);
-	else if (list) {
-		/* page reclaim is reclaiming a huge page */
-		get_page(page_tail);
-		list_add_tail(&page_tail->lru, list);
-	} else {
-		/*
-		 * Head page has not yet been counted, as an hpage,
-		 * so we must account for each subpage individually.
-		 *
-		 * Put page_tail on the list at the correct position
-		 * so they all end up in order.
-		 */
-		add_page_to_lru_list_tail(page_tail, lruvec,
-					  page_lru(page_tail));
-	}
-}
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-
 static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec,
 				 void *arg)
 {
-- 
cgit v1.2.3


From d25b5bd8a8f420b15517c19c4626c0c009f72a63 Mon Sep 17 00:00:00 2001
From: Alex Shi <alex.shi@linux.alibaba.com>
Date: Tue, 15 Dec 2020 12:34:16 -0800
Subject: mm/lru: introduce TestClearPageLRU()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently lru_lock still guards both lru list and page's lru bit, that's
ok.  but if we want to use specific lruvec lock on the page, we need to
pin down the page's lruvec/memcg during locking.  Just taking lruvec lock
first may be undermined by the page's memcg charge/migration.  To fix this
problem, we will clear the lru bit out of locking and use it as pin down
action to block the page isolation in memcg changing.

So now a standard steps of page isolation is following:
	1, get_page(); 	       #pin the page avoid to be free
	2, TestClearPageLRU(); #block other isolation like memcg change
	3, spin_lock on lru_lock; #serialize lru list access
	4, delete page from lru list;

This patch start with the first part: TestClearPageLRU, which combines
PageLRU check and ClearPageLRU into a macro func TestClearPageLRU.  This
function will be used as page isolation precondition to prevent other
isolations some where else.  Then there are may !PageLRU page on lru list,
need to remove BUG() checking accordingly.

There 2 rules for lru bit now:
1, the lru bit still indicate if a page on lru list, just in some
   temporary moment(isolating), the page may have no lru bit when
   it's on lru list.  but the page still must be on lru list when the
   lru bit set.
2, have to remove lru bit before delete it from lru list.

As Andrew Morton mentioned this change would dirty cacheline for a page
which isn't on the LRU.  But the loss would be acceptable in Rong Chen
<rong.a.chen@intel.com> report:
https://lore.kernel.org/lkml/20200304090301.GB5972@shao2-debian/

Link: https://lkml.kernel.org/r/1604566549-62481-15-git-send-email-alex.shi@linux.alibaba.com
Suggested-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
Acked-by: Hugh Dickins <hughd@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Alexander Duyck <alexander.duyck@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Jann Horn <jannh@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mika Penttilä <mika.penttila@nextfour.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Wei Yang <richard.weiyang@gmail.com>
Cc: Yang Shi <yang.shi@linux.alibaba.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/page-flags.h |  1 +
 mm/mlock.c                 |  3 +--
 mm/vmscan.c                | 39 +++++++++++++++++++--------------------
 3 files changed, 21 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index c1368af622c7..f8b4375ce1b3 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -334,6 +334,7 @@ PAGEFLAG(Referenced, referenced, PF_HEAD)
 PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD)
 	__CLEARPAGEFLAG(Dirty, dirty, PF_HEAD)
 PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD)
+	TESTCLEARFLAG(LRU, lru, PF_HEAD)
 PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD)
 	TESTCLEARFLAG(Active, active, PF_HEAD)
 PAGEFLAG(Workingset, workingset, PF_HEAD)
diff --git a/mm/mlock.c b/mm/mlock.c
index d487aa864e86..7b0e6334be6f 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -276,10 +276,9 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 			 * We already have pin from follow_page_mask()
 			 * so we can spare the get_page() here.
 			 */
-			if (PageLRU(page)) {
+			if (TestClearPageLRU(page)) {
 				struct lruvec *lruvec;
 
-				ClearPageLRU(page);
 				lruvec = mem_cgroup_page_lruvec(page,
 							page_pgdat(page));
 				del_page_from_lru_list(page, lruvec,
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 397f89accdb6..54ab9cbb631a 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1541,7 +1541,7 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
  */
 int __isolate_lru_page(struct page *page, isolate_mode_t mode)
 {
-	int ret = -EINVAL;
+	int ret = -EBUSY;
 
 	/* Only take pages on the LRU. */
 	if (!PageLRU(page))
@@ -1551,8 +1551,6 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode)
 	if (PageUnevictable(page) && !(mode & ISOLATE_UNEVICTABLE))
 		return ret;
 
-	ret = -EBUSY;
-
 	/*
 	 * To minimise LRU disruption, the caller can indicate that it only
 	 * wants to isolate pages it will be able to operate on without
@@ -1599,8 +1597,10 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode)
 		 * sure the page is not being freed elsewhere -- the
 		 * page release code relies on it.
 		 */
-		ClearPageLRU(page);
-		ret = 0;
+		if (TestClearPageLRU(page))
+			ret = 0;
+		else
+			put_page(page);
 	}
 
 	return ret;
@@ -1666,8 +1666,6 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 		page = lru_to_page(src);
 		prefetchw_prev_lru_page(page, src, flags);
 
-		VM_BUG_ON_PAGE(!PageLRU(page), page);
-
 		nr_pages = compound_nr(page);
 		total_scan += nr_pages;
 
@@ -1764,21 +1762,18 @@ int isolate_lru_page(struct page *page)
 	VM_BUG_ON_PAGE(!page_count(page), page);
 	WARN_RATELIMIT(PageTail(page), "trying to isolate tail page");
 
-	if (PageLRU(page)) {
+	if (TestClearPageLRU(page)) {
 		pg_data_t *pgdat = page_pgdat(page);
 		struct lruvec *lruvec;
 
-		spin_lock_irq(&pgdat->lru_lock);
+		get_page(page);
 		lruvec = mem_cgroup_page_lruvec(page, pgdat);
-		if (PageLRU(page)) {
-			int lru = page_lru(page);
-			get_page(page);
-			ClearPageLRU(page);
-			del_page_from_lru_list(page, lruvec, lru);
-			ret = 0;
-		}
+		spin_lock_irq(&pgdat->lru_lock);
+		del_page_from_lru_list(page, lruvec, page_lru(page));
 		spin_unlock_irq(&pgdat->lru_lock);
+		ret = 0;
 	}
+
 	return ret;
 }
 
@@ -4289,6 +4284,10 @@ void check_move_unevictable_pages(struct pagevec *pvec)
 		nr_pages = thp_nr_pages(page);
 		pgscanned += nr_pages;
 
+		/* block memcg migration during page moving between lru */
+		if (!TestClearPageLRU(page))
+			continue;
+
 		if (pagepgdat != pgdat) {
 			if (pgdat)
 				spin_unlock_irq(&pgdat->lru_lock);
@@ -4297,10 +4296,7 @@ void check_move_unevictable_pages(struct pagevec *pvec)
 		}
 		lruvec = mem_cgroup_page_lruvec(page, pgdat);
 
-		if (!PageLRU(page) || !PageUnevictable(page))
-			continue;
-
-		if (page_evictable(page)) {
+		if (page_evictable(page) && PageUnevictable(page)) {
 			enum lru_list lru = page_lru_base_type(page);
 
 			VM_BUG_ON_PAGE(PageActive(page), page);
@@ -4309,12 +4305,15 @@ void check_move_unevictable_pages(struct pagevec *pvec)
 			add_page_to_lru_list(page, lruvec, lru);
 			pgrescued += nr_pages;
 		}
+		SetPageLRU(page);
 	}
 
 	if (pgdat) {
 		__count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued);
 		__count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned);
 		spin_unlock_irq(&pgdat->lru_lock);
+	} else if (pgscanned) {
+		count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned);
 	}
 }
 EXPORT_SYMBOL_GPL(check_move_unevictable_pages);
-- 
cgit v1.2.3


From 9df41314390b81a541ca6e84c8340bad0959e4b5 Mon Sep 17 00:00:00 2001
From: Alex Shi <alex.shi@linux.alibaba.com>
Date: Tue, 15 Dec 2020 12:34:20 -0800
Subject: mm/compaction: do page isolation first in compaction
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, compaction would get the lru_lock and then do page isolation
which works fine with pgdat->lru_lock, since any page isoltion would
compete for the lru_lock.  If we want to change to memcg lru_lock, we have
to isolate the page before getting lru_lock, thus isoltion would block
page's memcg change which relay on page isoltion too.  Then we could
safely use per memcg lru_lock later.

The new page isolation use previous introduced TestClearPageLRU() + pgdat
lru locking which will be changed to memcg lru lock later.

Hugh Dickins <hughd@google.com> fixed following bugs in this patch's early
version:

Fix lots of crashes under compaction load: isolate_migratepages_block()
must clean up appropriately when rejecting a page, setting PageLRU again
if it had been cleared; and a put_page() after get_page_unless_zero()
cannot safely be done while holding locked_lruvec - it may turn out to be
the final put_page(), which will take an lruvec lock when PageLRU.

And move __isolate_lru_page_prepare back after get_page_unless_zero to
make trylock_page() safe: trylock_page() is not safe to use at this time:
its setting PG_locked can race with the page being freed or allocated
("Bad page"), and can also erase flags being set by one of those "sole
owners" of a freshly allocated page who use non-atomic __SetPageFlag().

Link: https://lkml.kernel.org/r/1604566549-62481-16-git-send-email-alex.shi@linux.alibaba.com
Suggested-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
Acked-by: Hugh Dickins <hughd@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Alexander Duyck <alexander.duyck@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: "Chen, Rong A" <rong.a.chen@intel.com>
Cc: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Jann Horn <jannh@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mika Penttilä <mika.penttila@nextfour.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Wei Yang <richard.weiyang@gmail.com>
Cc: Yang Shi <yang.shi@linux.alibaba.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/swap.h |  2 +-
 mm/compaction.c      | 42 +++++++++++++++++++++++++++++++++---------
 mm/vmscan.c          | 43 ++++++++++++++++++++++---------------------
 3 files changed, 56 insertions(+), 31 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 5e1e967c225f..596bc2f4d9b0 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -356,7 +356,7 @@ extern void lru_cache_add_inactive_or_unevictable(struct page *page,
 extern unsigned long zone_reclaimable_pages(struct zone *zone);
 extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 					gfp_t gfp_mask, nodemask_t *mask);
-extern int __isolate_lru_page(struct page *page, isolate_mode_t mode);
+extern int __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode);
 extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 						  unsigned long nr_pages,
 						  gfp_t gfp_mask,
diff --git a/mm/compaction.c b/mm/compaction.c
index dbcfdfce1b82..50938e66083c 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -890,6 +890,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		if (!valid_page && IS_ALIGNED(low_pfn, pageblock_nr_pages)) {
 			if (!cc->ignore_skip_hint && get_pageblock_skip(page)) {
 				low_pfn = end_pfn;
+				page = NULL;
 				goto isolate_abort;
 			}
 			valid_page = page;
@@ -971,6 +972,21 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		if (!(cc->gfp_mask & __GFP_FS) && page_mapping(page))
 			goto isolate_fail;
 
+		/*
+		 * Be careful not to clear PageLRU until after we're
+		 * sure the page is not being freed elsewhere -- the
+		 * page release code relies on it.
+		 */
+		if (unlikely(!get_page_unless_zero(page)))
+			goto isolate_fail;
+
+		if (__isolate_lru_page_prepare(page, isolate_mode) != 0)
+			goto isolate_fail_put;
+
+		/* Try isolate the page */
+		if (!TestClearPageLRU(page))
+			goto isolate_fail_put;
+
 		/* If we already hold the lock, we can skip some rechecking */
 		if (!locked) {
 			locked = compact_lock_irqsave(&pgdat->lru_lock,
@@ -983,10 +999,6 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 					goto isolate_abort;
 			}
 
-			/* Recheck PageLRU and PageCompound under lock */
-			if (!PageLRU(page))
-				goto isolate_fail;
-
 			/*
 			 * Page become compound since the non-locked check,
 			 * and it's on LRU. It can only be a THP so the order
@@ -994,16 +1006,13 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 			 */
 			if (unlikely(PageCompound(page) && !cc->alloc_contig)) {
 				low_pfn += compound_nr(page) - 1;
-				goto isolate_fail;
+				SetPageLRU(page);
+				goto isolate_fail_put;
 			}
 		}
 
 		lruvec = mem_cgroup_page_lruvec(page, pgdat);
 
-		/* Try isolate the page */
-		if (__isolate_lru_page(page, isolate_mode) != 0)
-			goto isolate_fail;
-
 		/* The whole page is taken off the LRU; skip the tail pages. */
 		if (PageCompound(page))
 			low_pfn += compound_nr(page) - 1;
@@ -1032,6 +1041,15 @@ isolate_success:
 		}
 
 		continue;
+
+isolate_fail_put:
+		/* Avoid potential deadlock in freeing page under lru_lock */
+		if (locked) {
+			spin_unlock_irqrestore(&pgdat->lru_lock, flags);
+			locked = false;
+		}
+		put_page(page);
+
 isolate_fail:
 		if (!skip_on_failure)
 			continue;
@@ -1068,9 +1086,15 @@ isolate_fail:
 	if (unlikely(low_pfn > end_pfn))
 		low_pfn = end_pfn;
 
+	page = NULL;
+
 isolate_abort:
 	if (locked)
 		spin_unlock_irqrestore(&pgdat->lru_lock, flags);
+	if (page) {
+		SetPageLRU(page);
+		put_page(page);
+	}
 
 	/*
 	 * Updated the cached scanner pfn once the pageblock has been scanned
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 54ab9cbb631a..cf99e66e7f33 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1539,7 +1539,7 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
  *
  * returns 0 on success, -ve errno on failure.
  */
-int __isolate_lru_page(struct page *page, isolate_mode_t mode)
+int __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode)
 {
 	int ret = -EBUSY;
 
@@ -1591,22 +1591,9 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode)
 	if ((mode & ISOLATE_UNMAPPED) && page_mapped(page))
 		return ret;
 
-	if (likely(get_page_unless_zero(page))) {
-		/*
-		 * Be careful not to clear PageLRU until after we're
-		 * sure the page is not being freed elsewhere -- the
-		 * page release code relies on it.
-		 */
-		if (TestClearPageLRU(page))
-			ret = 0;
-		else
-			put_page(page);
-	}
-
-	return ret;
+	return 0;
 }
 
-
 /*
  * Update LRU sizes after isolating pages. The LRU size updates must
  * be complete before mem_cgroup_update_lru_size due to a sanity check.
@@ -1686,20 +1673,34 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 		 * only when the page is being freed somewhere else.
 		 */
 		scan += nr_pages;
-		switch (__isolate_lru_page(page, mode)) {
+		switch (__isolate_lru_page_prepare(page, mode)) {
 		case 0:
+			/*
+			 * Be careful not to clear PageLRU until after we're
+			 * sure the page is not being freed elsewhere -- the
+			 * page release code relies on it.
+			 */
+			if (unlikely(!get_page_unless_zero(page)))
+				goto busy;
+
+			if (!TestClearPageLRU(page)) {
+				/*
+				 * This page may in other isolation path,
+				 * but we still hold lru_lock.
+				 */
+				put_page(page);
+				goto busy;
+			}
+
 			nr_taken += nr_pages;
 			nr_zone_taken[page_zonenum(page)] += nr_pages;
 			list_move(&page->lru, dst);
 			break;
 
-		case -EBUSY:
+		default:
+busy:
 			/* else it is being freed elsewhere */
 			list_move(&page->lru, src);
-			continue;
-
-		default:
-			BUG();
 		}
 	}
 
-- 
cgit v1.2.3


From 6168d0da2b479ce25a4647de194045de1bdd1f1d Mon Sep 17 00:00:00 2001
From: Alex Shi <alex.shi@linux.alibaba.com>
Date: Tue, 15 Dec 2020 12:34:29 -0800
Subject: mm/lru: replace pgdat lru_lock with lruvec lock
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch moves per node lru_lock into lruvec, thus bring a lru_lock for
each of memcg per node.  So on a large machine, each of memcg don't have
to suffer from per node pgdat->lru_lock competition.  They could go fast
with their self lru_lock.

After move memcg charge before lru inserting, page isolation could
serialize page's memcg, then per memcg lruvec lock is stable and could
replace per node lru lock.

In isolate_migratepages_block(), compact_unlock_should_abort and
lock_page_lruvec_irqsave are open coded to work with compact_control.
Also add a debug func in locking which may give some clues if there are
sth out of hands.

Daniel Jordan's testing show 62% improvement on modified readtwice case on
his 2P * 10 core * 2 HT broadwell box.
https://lore.kernel.org/lkml/20200915165807.kpp7uhiw7l3loofu@ca-dmjordan1.us.oracle.com/

Hugh Dickins helped on the patch polish, thanks!

[alex.shi@linux.alibaba.com: fix comment typo]
  Link: https://lkml.kernel.org/r/5b085715-292a-4b43-50b3-d73dc90d1de5@linux.alibaba.com
[alex.shi@linux.alibaba.com: use page_memcg()]
  Link: https://lkml.kernel.org/r/5a4c2b72-7ee8-2478-fc0e-85eb83aafec4@linux.alibaba.com

Link: https://lkml.kernel.org/r/1604566549-62481-18-git-send-email-alex.shi@linux.alibaba.com
Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
Acked-by: Hugh Dickins <hughd@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Rong Chen <rong.a.chen@intel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Yang Shi <yang.shi@linux.alibaba.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Cc: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: Alexander Duyck <alexander.duyck@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Jann Horn <jannh@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mika Penttilä <mika.penttila@nextfour.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Wei Yang <richard.weiyang@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h |  58 +++++++++++++++++++++++
 include/linux/mmzone.h     |   3 +-
 mm/compaction.c            |  56 ++++++++++++++--------
 mm/huge_memory.c           |  11 ++---
 mm/memcontrol.c            |  78 ++++++++++++++++++++++++++++--
 mm/mlock.c                 |  22 ++++++---
 mm/mmzone.c                |   1 +
 mm/page_alloc.c            |   1 -
 mm/swap.c                  | 116 ++++++++++++++++++++++-----------------------
 mm/vmscan.c                |  55 ++++++++++-----------
 10 files changed, 275 insertions(+), 126 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index f530d634f055..aa5d559853c2 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -491,6 +491,19 @@ struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm);
 
 struct mem_cgroup *get_mem_cgroup_from_page(struct page *page);
 
+struct lruvec *lock_page_lruvec(struct page *page);
+struct lruvec *lock_page_lruvec_irq(struct page *page);
+struct lruvec *lock_page_lruvec_irqsave(struct page *page,
+						unsigned long *flags);
+
+#ifdef CONFIG_DEBUG_VM
+void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page);
+#else
+static inline void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page)
+{
+}
+#endif
+
 static inline
 struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){
 	return css ? container_of(css, struct mem_cgroup, css) : NULL;
@@ -996,6 +1009,31 @@ static inline void mem_cgroup_put(struct mem_cgroup *memcg)
 {
 }
 
+static inline struct lruvec *lock_page_lruvec(struct page *page)
+{
+	struct pglist_data *pgdat = page_pgdat(page);
+
+	spin_lock(&pgdat->__lruvec.lru_lock);
+	return &pgdat->__lruvec;
+}
+
+static inline struct lruvec *lock_page_lruvec_irq(struct page *page)
+{
+	struct pglist_data *pgdat = page_pgdat(page);
+
+	spin_lock_irq(&pgdat->__lruvec.lru_lock);
+	return &pgdat->__lruvec;
+}
+
+static inline struct lruvec *lock_page_lruvec_irqsave(struct page *page,
+		unsigned long *flagsp)
+{
+	struct pglist_data *pgdat = page_pgdat(page);
+
+	spin_lock_irqsave(&pgdat->__lruvec.lru_lock, *flagsp);
+	return &pgdat->__lruvec;
+}
+
 static inline struct mem_cgroup *
 mem_cgroup_iter(struct mem_cgroup *root,
 		struct mem_cgroup *prev,
@@ -1215,6 +1253,10 @@ static inline
 void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx)
 {
 }
+
+static inline void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page)
+{
+}
 #endif /* CONFIG_MEMCG */
 
 /* idx can be of type enum memcg_stat_item or node_stat_item */
@@ -1296,6 +1338,22 @@ static inline struct lruvec *parent_lruvec(struct lruvec *lruvec)
 	return mem_cgroup_lruvec(memcg, lruvec_pgdat(lruvec));
 }
 
+static inline void unlock_page_lruvec(struct lruvec *lruvec)
+{
+	spin_unlock(&lruvec->lru_lock);
+}
+
+static inline void unlock_page_lruvec_irq(struct lruvec *lruvec)
+{
+	spin_unlock_irq(&lruvec->lru_lock);
+}
+
+static inline void unlock_page_lruvec_irqrestore(struct lruvec *lruvec,
+		unsigned long flags)
+{
+	spin_unlock_irqrestore(&lruvec->lru_lock, flags);
+}
+
 #ifdef CONFIG_CGROUP_WRITEBACK
 
 struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 98a80c01d150..9da23c019dc5 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -276,6 +276,8 @@ enum lruvec_flags {
 
 struct lruvec {
 	struct list_head		lists[NR_LRU_LISTS];
+	/* per lruvec lru_lock for memcg */
+	spinlock_t			lru_lock;
 	/*
 	 * These track the cost of reclaiming one LRU - file or anon -
 	 * over the other. As the observed cost of reclaiming one LRU
@@ -782,7 +784,6 @@ typedef struct pglist_data {
 
 	/* Write-intensive fields used by page reclaim */
 	ZONE_PADDING(_pad1_)
-	spinlock_t		lru_lock;
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
 	/*
diff --git a/mm/compaction.c b/mm/compaction.c
index 50938e66083c..e5acb9714436 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -804,7 +804,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 	unsigned long nr_scanned = 0, nr_isolated = 0;
 	struct lruvec *lruvec;
 	unsigned long flags = 0;
-	bool locked = false;
+	struct lruvec *locked = NULL;
 	struct page *page = NULL, *valid_page = NULL;
 	unsigned long start_pfn = low_pfn;
 	bool skip_on_failure = false;
@@ -868,11 +868,20 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		 * contention, to give chance to IRQs. Abort completely if
 		 * a fatal signal is pending.
 		 */
-		if (!(low_pfn % SWAP_CLUSTER_MAX)
-		    && compact_unlock_should_abort(&pgdat->lru_lock,
-					    flags, &locked, cc)) {
-			low_pfn = 0;
-			goto fatal_pending;
+		if (!(low_pfn % SWAP_CLUSTER_MAX)) {
+			if (locked) {
+				unlock_page_lruvec_irqrestore(locked, flags);
+				locked = NULL;
+			}
+
+			if (fatal_signal_pending(current)) {
+				cc->contended = true;
+
+				low_pfn = 0;
+				goto fatal_pending;
+			}
+
+			cond_resched();
 		}
 
 		if (!pfn_valid_within(low_pfn))
@@ -944,9 +953,8 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 			if (unlikely(__PageMovable(page)) &&
 					!PageIsolated(page)) {
 				if (locked) {
-					spin_unlock_irqrestore(&pgdat->lru_lock,
-									flags);
-					locked = false;
+					unlock_page_lruvec_irqrestore(locked, flags);
+					locked = NULL;
 				}
 
 				if (!isolate_movable_page(page, isolate_mode))
@@ -987,10 +995,19 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		if (!TestClearPageLRU(page))
 			goto isolate_fail_put;
 
+		rcu_read_lock();
+		lruvec = mem_cgroup_page_lruvec(page, pgdat);
+
 		/* If we already hold the lock, we can skip some rechecking */
-		if (!locked) {
-			locked = compact_lock_irqsave(&pgdat->lru_lock,
-								&flags, cc);
+		if (lruvec != locked) {
+			if (locked)
+				unlock_page_lruvec_irqrestore(locked, flags);
+
+			compact_lock_irqsave(&lruvec->lru_lock, &flags, cc);
+			locked = lruvec;
+			rcu_read_unlock();
+
+			lruvec_memcg_debug(lruvec, page);
 
 			/* Try get exclusive access under lock */
 			if (!skip_updated) {
@@ -1009,9 +1026,8 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 				SetPageLRU(page);
 				goto isolate_fail_put;
 			}
-		}
-
-		lruvec = mem_cgroup_page_lruvec(page, pgdat);
+		} else
+			rcu_read_unlock();
 
 		/* The whole page is taken off the LRU; skip the tail pages. */
 		if (PageCompound(page))
@@ -1045,8 +1061,8 @@ isolate_success:
 isolate_fail_put:
 		/* Avoid potential deadlock in freeing page under lru_lock */
 		if (locked) {
-			spin_unlock_irqrestore(&pgdat->lru_lock, flags);
-			locked = false;
+			unlock_page_lruvec_irqrestore(locked, flags);
+			locked = NULL;
 		}
 		put_page(page);
 
@@ -1061,8 +1077,8 @@ isolate_fail:
 		 */
 		if (nr_isolated) {
 			if (locked) {
-				spin_unlock_irqrestore(&pgdat->lru_lock, flags);
-				locked = false;
+				unlock_page_lruvec_irqrestore(locked, flags);
+				locked = NULL;
 			}
 			putback_movable_pages(&cc->migratepages);
 			cc->nr_migratepages = 0;
@@ -1090,7 +1106,7 @@ isolate_fail:
 
 isolate_abort:
 	if (locked)
-		spin_unlock_irqrestore(&pgdat->lru_lock, flags);
+		unlock_page_lruvec_irqrestore(locked, flags);
 	if (page) {
 		SetPageLRU(page);
 		put_page(page);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index a59333aa4020..3c4a8fc9102f 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2365,7 +2365,7 @@ static void lru_add_page_tail(struct page *head, struct page *tail,
 	VM_BUG_ON_PAGE(!PageHead(head), head);
 	VM_BUG_ON_PAGE(PageCompound(tail), head);
 	VM_BUG_ON_PAGE(PageLRU(tail), head);
-	lockdep_assert_held(&lruvec_pgdat(lruvec)->lru_lock);
+	lockdep_assert_held(&lruvec->lru_lock);
 
 	if (list) {
 		/* page reclaim is reclaiming a huge page */
@@ -2449,7 +2449,6 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 		pgoff_t end)
 {
 	struct page *head = compound_head(page);
-	pg_data_t *pgdat = page_pgdat(head);
 	struct lruvec *lruvec;
 	struct address_space *swap_cache = NULL;
 	unsigned long offset = 0;
@@ -2467,10 +2466,8 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 		xa_lock(&swap_cache->i_pages);
 	}
 
-	/* prevent PageLRU to go away from under us, and freeze lru stats */
-	spin_lock(&pgdat->lru_lock);
-
-	lruvec = mem_cgroup_page_lruvec(head, pgdat);
+	/* lock lru list/PageCompound, ref freezed by page_ref_freeze */
+	lruvec = lock_page_lruvec(head);
 
 	for (i = nr - 1; i >= 1; i--) {
 		__split_huge_page_tail(head, i, lruvec, list);
@@ -2491,7 +2488,7 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 	}
 
 	ClearPageCompound(head);
-	spin_unlock(&pgdat->lru_lock);
+	unlock_page_lruvec(lruvec);
 	/* Caller disabled irqs, so they are still disabled here */
 
 	split_page_owner(head, nr);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 827879d8d447..2f7824d0c897 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -20,6 +20,9 @@
  * Lockless page tracking & accounting
  * Unified hierarchy configuration model
  * Copyright (C) 2015 Red Hat, Inc., Johannes Weiner
+ *
+ * Per memcg lru locking
+ * Copyright (C) 2020 Alibaba, Inc, Alex Shi
  */
 
 #include <linux/page_counter.h>
@@ -1330,6 +1333,23 @@ int mem_cgroup_scan_tasks(struct mem_cgroup *memcg,
 	return ret;
 }
 
+#ifdef CONFIG_DEBUG_VM
+void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page)
+{
+	struct mem_cgroup *memcg;
+
+	if (mem_cgroup_disabled())
+		return;
+
+	memcg = page_memcg(page);
+
+	if (!memcg)
+		VM_BUG_ON_PAGE(lruvec_memcg(lruvec) != root_mem_cgroup, page);
+	else
+		VM_BUG_ON_PAGE(lruvec_memcg(lruvec) != memcg, page);
+}
+#endif
+
 /**
  * mem_cgroup_page_lruvec - return lruvec for isolating/putting an LRU page
  * @page: the page
@@ -1370,6 +1390,60 @@ out:
 	return lruvec;
 }
 
+/**
+ * lock_page_lruvec - lock and return lruvec for a given page.
+ * @page: the page
+ *
+ * This series functions should be used in either conditions:
+ * PageLRU is cleared or unset
+ * or page->_refcount is zero
+ * or page is locked.
+ */
+struct lruvec *lock_page_lruvec(struct page *page)
+{
+	struct lruvec *lruvec;
+	struct pglist_data *pgdat = page_pgdat(page);
+
+	rcu_read_lock();
+	lruvec = mem_cgroup_page_lruvec(page, pgdat);
+	spin_lock(&lruvec->lru_lock);
+	rcu_read_unlock();
+
+	lruvec_memcg_debug(lruvec, page);
+
+	return lruvec;
+}
+
+struct lruvec *lock_page_lruvec_irq(struct page *page)
+{
+	struct lruvec *lruvec;
+	struct pglist_data *pgdat = page_pgdat(page);
+
+	rcu_read_lock();
+	lruvec = mem_cgroup_page_lruvec(page, pgdat);
+	spin_lock_irq(&lruvec->lru_lock);
+	rcu_read_unlock();
+
+	lruvec_memcg_debug(lruvec, page);
+
+	return lruvec;
+}
+
+struct lruvec *lock_page_lruvec_irqsave(struct page *page, unsigned long *flags)
+{
+	struct lruvec *lruvec;
+	struct pglist_data *pgdat = page_pgdat(page);
+
+	rcu_read_lock();
+	lruvec = mem_cgroup_page_lruvec(page, pgdat);
+	spin_lock_irqsave(&lruvec->lru_lock, *flags);
+	rcu_read_unlock();
+
+	lruvec_memcg_debug(lruvec, page);
+
+	return lruvec;
+}
+
 /**
  * mem_cgroup_update_lru_size - account for adding or removing an lru page
  * @lruvec: mem_cgroup per zone lru vector
@@ -3281,10 +3355,8 @@ void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size)
 #endif /* CONFIG_MEMCG_KMEM */
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-
 /*
- * Because tail pages are not marked as "used", set it. We're under
- * pgdat->lru_lock and migration entries setup in all page mappings.
+ * Because page_memcg(head) is not set on compound tails, set it now.
  */
 void mem_cgroup_split_huge_fixup(struct page *head)
 {
diff --git a/mm/mlock.c b/mm/mlock.c
index 7b0e6334be6f..ab164a675c25 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -262,12 +262,12 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 	int nr = pagevec_count(pvec);
 	int delta_munlocked = -nr;
 	struct pagevec pvec_putback;
+	struct lruvec *lruvec = NULL;
 	int pgrescued = 0;
 
 	pagevec_init(&pvec_putback);
 
 	/* Phase 1: page isolation */
-	spin_lock_irq(&zone->zone_pgdat->lru_lock);
 	for (i = 0; i < nr; i++) {
 		struct page *page = pvec->pages[i];
 
@@ -277,10 +277,16 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 			 * so we can spare the get_page() here.
 			 */
 			if (TestClearPageLRU(page)) {
-				struct lruvec *lruvec;
+				struct lruvec *new_lruvec;
+
+				new_lruvec = mem_cgroup_page_lruvec(page,
+						page_pgdat(page));
+				if (new_lruvec != lruvec) {
+					if (lruvec)
+						unlock_page_lruvec_irq(lruvec);
+					lruvec = lock_page_lruvec_irq(page);
+				}
 
-				lruvec = mem_cgroup_page_lruvec(page,
-							page_pgdat(page));
 				del_page_from_lru_list(page, lruvec,
 							page_lru(page));
 				continue;
@@ -299,8 +305,12 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 		pagevec_add(&pvec_putback, pvec->pages[i]);
 		pvec->pages[i] = NULL;
 	}
-	__mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
-	spin_unlock_irq(&zone->zone_pgdat->lru_lock);
+	if (lruvec) {
+		__mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
+		unlock_page_lruvec_irq(lruvec);
+	} else if (delta_munlocked) {
+		mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
+	}
 
 	/* Now we can release pins of pages that we are not munlocking */
 	pagevec_release(&pvec_putback);
diff --git a/mm/mmzone.c b/mm/mmzone.c
index f337831affc2..eb89d6e018e2 100644
--- a/mm/mmzone.c
+++ b/mm/mmzone.c
@@ -77,6 +77,7 @@ void lruvec_init(struct lruvec *lruvec)
 	enum lru_list lru;
 
 	memset(lruvec, 0, sizeof(struct lruvec));
+	spin_lock_init(&lruvec->lru_lock);
 
 	for_each_lru(lru)
 		INIT_LIST_HEAD(&lruvec->lists[lru]);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index b63294517e04..b1cc2b7483a1 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6870,7 +6870,6 @@ static void __meminit pgdat_init_internals(struct pglist_data *pgdat)
 	init_waitqueue_head(&pgdat->pfmemalloc_wait);
 
 	pgdat_page_ext_init(pgdat);
-	spin_lock_init(&pgdat->lru_lock);
 	lruvec_init(&pgdat->__lruvec);
 }
 
diff --git a/mm/swap.c b/mm/swap.c
index d952af770053..ba9fc21b24ea 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -79,16 +79,14 @@ static DEFINE_PER_CPU(struct lru_pvecs, lru_pvecs) = {
 static void __page_cache_release(struct page *page)
 {
 	if (PageLRU(page)) {
-		pg_data_t *pgdat = page_pgdat(page);
 		struct lruvec *lruvec;
 		unsigned long flags;
 
-		spin_lock_irqsave(&pgdat->lru_lock, flags);
-		lruvec = mem_cgroup_page_lruvec(page, pgdat);
+		lruvec = lock_page_lruvec_irqsave(page, &flags);
 		VM_BUG_ON_PAGE(!PageLRU(page), page);
 		__ClearPageLRU(page);
 		del_page_from_lru_list(page, lruvec, page_off_lru(page));
-		spin_unlock_irqrestore(&pgdat->lru_lock, flags);
+		unlock_page_lruvec_irqrestore(lruvec, flags);
 	}
 	__ClearPageWaiters(page);
 }
@@ -207,32 +205,30 @@ static void pagevec_lru_move_fn(struct pagevec *pvec,
 	void (*move_fn)(struct page *page, struct lruvec *lruvec))
 {
 	int i;
-	struct pglist_data *pgdat = NULL;
-	struct lruvec *lruvec;
+	struct lruvec *lruvec = NULL;
 	unsigned long flags = 0;
 
 	for (i = 0; i < pagevec_count(pvec); i++) {
 		struct page *page = pvec->pages[i];
-		struct pglist_data *pagepgdat = page_pgdat(page);
-
-		if (pagepgdat != pgdat) {
-			if (pgdat)
-				spin_unlock_irqrestore(&pgdat->lru_lock, flags);
-			pgdat = pagepgdat;
-			spin_lock_irqsave(&pgdat->lru_lock, flags);
-		}
+		struct lruvec *new_lruvec;
 
 		/* block memcg migration during page moving between lru */
 		if (!TestClearPageLRU(page))
 			continue;
 
-		lruvec = mem_cgroup_page_lruvec(page, pgdat);
+		new_lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page));
+		if (lruvec != new_lruvec) {
+			if (lruvec)
+				unlock_page_lruvec_irqrestore(lruvec, flags);
+			lruvec = lock_page_lruvec_irqsave(page, &flags);
+		}
+
 		(*move_fn)(page, lruvec);
 
 		SetPageLRU(page);
 	}
-	if (pgdat)
-		spin_unlock_irqrestore(&pgdat->lru_lock, flags);
+	if (lruvec)
+		unlock_page_lruvec_irqrestore(lruvec, flags);
 	release_pages(pvec->pages, pvec->nr);
 	pagevec_reinit(pvec);
 }
@@ -274,9 +270,15 @@ void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages)
 {
 	do {
 		unsigned long lrusize;
-		struct pglist_data *pgdat = lruvec_pgdat(lruvec);
 
-		spin_lock_irq(&pgdat->lru_lock);
+		/*
+		 * Hold lruvec->lru_lock is safe here, since
+		 * 1) The pinned lruvec in reclaim, or
+		 * 2) From a pre-LRU page during refault (which also holds the
+		 *    rcu lock, so would be safe even if the page was on the LRU
+		 *    and could move simultaneously to a new lruvec).
+		 */
+		spin_lock_irq(&lruvec->lru_lock);
 		/* Record cost event */
 		if (file)
 			lruvec->file_cost += nr_pages;
@@ -300,7 +302,7 @@ void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages)
 			lruvec->file_cost /= 2;
 			lruvec->anon_cost /= 2;
 		}
-		spin_unlock_irq(&pgdat->lru_lock);
+		spin_unlock_irq(&lruvec->lru_lock);
 	} while ((lruvec = parent_lruvec(lruvec)));
 }
 
@@ -364,13 +366,15 @@ static inline void activate_page_drain(int cpu)
 
 static void activate_page(struct page *page)
 {
-	pg_data_t *pgdat = page_pgdat(page);
+	struct lruvec *lruvec;
 
 	page = compound_head(page);
-	spin_lock_irq(&pgdat->lru_lock);
-	if (PageLRU(page))
-		__activate_page(page, mem_cgroup_page_lruvec(page, pgdat));
-	spin_unlock_irq(&pgdat->lru_lock);
+	if (TestClearPageLRU(page)) {
+		lruvec = lock_page_lruvec_irq(page);
+		__activate_page(page, lruvec);
+		unlock_page_lruvec_irq(lruvec);
+		SetPageLRU(page);
+	}
 }
 #endif
 
@@ -860,8 +864,7 @@ void release_pages(struct page **pages, int nr)
 {
 	int i;
 	LIST_HEAD(pages_to_free);
-	struct pglist_data *locked_pgdat = NULL;
-	struct lruvec *lruvec;
+	struct lruvec *lruvec = NULL;
 	unsigned long flags;
 	unsigned int lock_batch;
 
@@ -871,11 +874,11 @@ void release_pages(struct page **pages, int nr)
 		/*
 		 * Make sure the IRQ-safe lock-holding time does not get
 		 * excessive with a continuous string of pages from the
-		 * same pgdat. The lock is held only if pgdat != NULL.
+		 * same lruvec. The lock is held only if lruvec != NULL.
 		 */
-		if (locked_pgdat && ++lock_batch == SWAP_CLUSTER_MAX) {
-			spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags);
-			locked_pgdat = NULL;
+		if (lruvec && ++lock_batch == SWAP_CLUSTER_MAX) {
+			unlock_page_lruvec_irqrestore(lruvec, flags);
+			lruvec = NULL;
 		}
 
 		page = compound_head(page);
@@ -883,10 +886,9 @@ void release_pages(struct page **pages, int nr)
 			continue;
 
 		if (is_zone_device_page(page)) {
-			if (locked_pgdat) {
-				spin_unlock_irqrestore(&locked_pgdat->lru_lock,
-						       flags);
-				locked_pgdat = NULL;
+			if (lruvec) {
+				unlock_page_lruvec_irqrestore(lruvec, flags);
+				lruvec = NULL;
 			}
 			/*
 			 * ZONE_DEVICE pages that return 'false' from
@@ -907,27 +909,27 @@ void release_pages(struct page **pages, int nr)
 			continue;
 
 		if (PageCompound(page)) {
-			if (locked_pgdat) {
-				spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags);
-				locked_pgdat = NULL;
+			if (lruvec) {
+				unlock_page_lruvec_irqrestore(lruvec, flags);
+				lruvec = NULL;
 			}
 			__put_compound_page(page);
 			continue;
 		}
 
 		if (PageLRU(page)) {
-			struct pglist_data *pgdat = page_pgdat(page);
+			struct lruvec *new_lruvec;
 
-			if (pgdat != locked_pgdat) {
-				if (locked_pgdat)
-					spin_unlock_irqrestore(&locked_pgdat->lru_lock,
+			new_lruvec = mem_cgroup_page_lruvec(page,
+							page_pgdat(page));
+			if (new_lruvec != lruvec) {
+				if (lruvec)
+					unlock_page_lruvec_irqrestore(lruvec,
 									flags);
 				lock_batch = 0;
-				locked_pgdat = pgdat;
-				spin_lock_irqsave(&locked_pgdat->lru_lock, flags);
+				lruvec = lock_page_lruvec_irqsave(page, &flags);
 			}
 
-			lruvec = mem_cgroup_page_lruvec(page, locked_pgdat);
 			VM_BUG_ON_PAGE(!PageLRU(page), page);
 			__ClearPageLRU(page);
 			del_page_from_lru_list(page, lruvec, page_off_lru(page));
@@ -937,8 +939,8 @@ void release_pages(struct page **pages, int nr)
 
 		list_add(&page->lru, &pages_to_free);
 	}
-	if (locked_pgdat)
-		spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags);
+	if (lruvec)
+		unlock_page_lruvec_irqrestore(lruvec, flags);
 
 	mem_cgroup_uncharge_list(&pages_to_free);
 	free_unref_page_list(&pages_to_free);
@@ -1026,26 +1028,24 @@ static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec)
 void __pagevec_lru_add(struct pagevec *pvec)
 {
 	int i;
-	struct pglist_data *pgdat = NULL;
-	struct lruvec *lruvec;
+	struct lruvec *lruvec = NULL;
 	unsigned long flags = 0;
 
 	for (i = 0; i < pagevec_count(pvec); i++) {
 		struct page *page = pvec->pages[i];
-		struct pglist_data *pagepgdat = page_pgdat(page);
+		struct lruvec *new_lruvec;
 
-		if (pagepgdat != pgdat) {
-			if (pgdat)
-				spin_unlock_irqrestore(&pgdat->lru_lock, flags);
-			pgdat = pagepgdat;
-			spin_lock_irqsave(&pgdat->lru_lock, flags);
+		new_lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page));
+		if (lruvec != new_lruvec) {
+			if (lruvec)
+				unlock_page_lruvec_irqrestore(lruvec, flags);
+			lruvec = lock_page_lruvec_irqsave(page, &flags);
 		}
 
-		lruvec = mem_cgroup_page_lruvec(page, pgdat);
 		__pagevec_lru_add_fn(page, lruvec);
 	}
-	if (pgdat)
-		spin_unlock_irqrestore(&pgdat->lru_lock, flags);
+	if (lruvec)
+		unlock_page_lruvec_irqrestore(lruvec, flags);
 	release_pages(pvec->pages, pvec->nr);
 	pagevec_reinit(pvec);
 }
diff --git a/mm/vmscan.c b/mm/vmscan.c
index cf99e66e7f33..b27b5dba3fdd 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1764,14 +1764,12 @@ int isolate_lru_page(struct page *page)
 	WARN_RATELIMIT(PageTail(page), "trying to isolate tail page");
 
 	if (TestClearPageLRU(page)) {
-		pg_data_t *pgdat = page_pgdat(page);
 		struct lruvec *lruvec;
 
 		get_page(page);
-		lruvec = mem_cgroup_page_lruvec(page, pgdat);
-		spin_lock_irq(&pgdat->lru_lock);
+		lruvec = lock_page_lruvec_irq(page);
 		del_page_from_lru_list(page, lruvec, page_lru(page));
-		spin_unlock_irq(&pgdat->lru_lock);
+		unlock_page_lruvec_irq(lruvec);
 		ret = 0;
 	}
 
@@ -1838,7 +1836,6 @@ static int too_many_isolated(struct pglist_data *pgdat, int file,
 static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec,
 						     struct list_head *list)
 {
-	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
 	int nr_pages, nr_moved = 0;
 	LIST_HEAD(pages_to_free);
 	struct page *page;
@@ -1849,9 +1846,9 @@ static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec,
 		VM_BUG_ON_PAGE(PageLRU(page), page);
 		list_del(&page->lru);
 		if (unlikely(!page_evictable(page))) {
-			spin_unlock_irq(&pgdat->lru_lock);
+			spin_unlock_irq(&lruvec->lru_lock);
 			putback_lru_page(page);
-			spin_lock_irq(&pgdat->lru_lock);
+			spin_lock_irq(&lruvec->lru_lock);
 			continue;
 		}
 
@@ -1873,9 +1870,9 @@ static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec,
 			__ClearPageActive(page);
 
 			if (unlikely(PageCompound(page))) {
-				spin_unlock_irq(&pgdat->lru_lock);
+				spin_unlock_irq(&lruvec->lru_lock);
 				destroy_compound_page(page);
-				spin_lock_irq(&pgdat->lru_lock);
+				spin_lock_irq(&lruvec->lru_lock);
 			} else
 				list_add(&page->lru, &pages_to_free);
 
@@ -1952,7 +1949,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 
 	lru_add_drain();
 
-	spin_lock_irq(&pgdat->lru_lock);
+	spin_lock_irq(&lruvec->lru_lock);
 
 	nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &page_list,
 				     &nr_scanned, sc, lru);
@@ -1964,14 +1961,14 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	__count_memcg_events(lruvec_memcg(lruvec), item, nr_scanned);
 	__count_vm_events(PGSCAN_ANON + file, nr_scanned);
 
-	spin_unlock_irq(&pgdat->lru_lock);
+	spin_unlock_irq(&lruvec->lru_lock);
 
 	if (nr_taken == 0)
 		return 0;
 
 	nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, &stat, false);
 
-	spin_lock_irq(&pgdat->lru_lock);
+	spin_lock_irq(&lruvec->lru_lock);
 	move_pages_to_lru(lruvec, &page_list);
 
 	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
@@ -1980,7 +1977,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 		__count_vm_events(item, nr_reclaimed);
 	__count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed);
 	__count_vm_events(PGSTEAL_ANON + file, nr_reclaimed);
-	spin_unlock_irq(&pgdat->lru_lock);
+	spin_unlock_irq(&lruvec->lru_lock);
 
 	lru_note_cost(lruvec, file, stat.nr_pageout);
 	mem_cgroup_uncharge_list(&page_list);
@@ -2033,7 +2030,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 
 	lru_add_drain();
 
-	spin_lock_irq(&pgdat->lru_lock);
+	spin_lock_irq(&lruvec->lru_lock);
 
 	nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &l_hold,
 				     &nr_scanned, sc, lru);
@@ -2044,7 +2041,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 		__count_vm_events(PGREFILL, nr_scanned);
 	__count_memcg_events(lruvec_memcg(lruvec), PGREFILL, nr_scanned);
 
-	spin_unlock_irq(&pgdat->lru_lock);
+	spin_unlock_irq(&lruvec->lru_lock);
 
 	while (!list_empty(&l_hold)) {
 		cond_resched();
@@ -2090,7 +2087,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 	/*
 	 * Move pages back to the lru list.
 	 */
-	spin_lock_irq(&pgdat->lru_lock);
+	spin_lock_irq(&lruvec->lru_lock);
 
 	nr_activate = move_pages_to_lru(lruvec, &l_active);
 	nr_deactivate = move_pages_to_lru(lruvec, &l_inactive);
@@ -2101,7 +2098,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 	__count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_deactivate);
 
 	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
-	spin_unlock_irq(&pgdat->lru_lock);
+	spin_unlock_irq(&lruvec->lru_lock);
 
 	mem_cgroup_uncharge_list(&l_active);
 	free_unref_page_list(&l_active);
@@ -2689,10 +2686,10 @@ again:
 	/*
 	 * Determine the scan balance between anon and file LRUs.
 	 */
-	spin_lock_irq(&pgdat->lru_lock);
+	spin_lock_irq(&target_lruvec->lru_lock);
 	sc->anon_cost = target_lruvec->anon_cost;
 	sc->file_cost = target_lruvec->file_cost;
-	spin_unlock_irq(&pgdat->lru_lock);
+	spin_unlock_irq(&target_lruvec->lru_lock);
 
 	/*
 	 * Target desirable inactive:active list ratios for the anon
@@ -4268,16 +4265,15 @@ int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order)
  */
 void check_move_unevictable_pages(struct pagevec *pvec)
 {
-	struct lruvec *lruvec;
-	struct pglist_data *pgdat = NULL;
+	struct lruvec *lruvec = NULL;
 	int pgscanned = 0;
 	int pgrescued = 0;
 	int i;
 
 	for (i = 0; i < pvec->nr; i++) {
 		struct page *page = pvec->pages[i];
-		struct pglist_data *pagepgdat = page_pgdat(page);
 		int nr_pages;
+		struct lruvec *new_lruvec;
 
 		if (PageTransTail(page))
 			continue;
@@ -4289,13 +4285,12 @@ void check_move_unevictable_pages(struct pagevec *pvec)
 		if (!TestClearPageLRU(page))
 			continue;
 
-		if (pagepgdat != pgdat) {
-			if (pgdat)
-				spin_unlock_irq(&pgdat->lru_lock);
-			pgdat = pagepgdat;
-			spin_lock_irq(&pgdat->lru_lock);
+		new_lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page));
+		if (lruvec != new_lruvec) {
+			if (lruvec)
+				unlock_page_lruvec_irq(lruvec);
+			lruvec = lock_page_lruvec_irq(page);
 		}
-		lruvec = mem_cgroup_page_lruvec(page, pgdat);
 
 		if (page_evictable(page) && PageUnevictable(page)) {
 			enum lru_list lru = page_lru_base_type(page);
@@ -4309,10 +4304,10 @@ void check_move_unevictable_pages(struct pagevec *pvec)
 		SetPageLRU(page);
 	}
 
-	if (pgdat) {
+	if (lruvec) {
 		__count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued);
 		__count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned);
-		spin_unlock_irq(&pgdat->lru_lock);
+		unlock_page_lruvec_irq(lruvec);
 	} else if (pgscanned) {
 		count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned);
 	}
-- 
cgit v1.2.3


From 2a5e4e340b0fe0f8d402196a466887db6a270b9b Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Date: Tue, 15 Dec 2020 12:34:33 -0800
Subject: mm/lru: introduce relock_page_lruvec()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add relock_page_lruvec() to replace repeated same code, no functional
change.

When testing for relock we can avoid the need for RCU locking if we simply
compare the page pgdat and memcg pointers versus those that the lruvec is
holding.  By doing this we can avoid the extra pointer walks and accesses
of the memory cgroup.

In addition we can avoid the checks entirely if lruvec is currently NULL.

[alex.shi@linux.alibaba.com: use page_memcg()]
  Link: https://lkml.kernel.org/r/66d8e79d-7ec6-bfbc-1c82-bf32db3ae5b7@linux.alibaba.com

Link: https://lkml.kernel.org/r/1604566549-62481-19-git-send-email-alex.shi@linux.alibaba.com
Signed-off-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
Acked-by: Hugh Dickins <hughd@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Cc: Tejun Heo <tj@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Chen, Rong A" <rong.a.chen@intel.com>
Cc: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Jann Horn <jannh@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mika Penttilä <mika.penttila@nextfour.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Wei Yang <richard.weiyang@gmail.com>
Cc: Yang Shi <yang.shi@linux.alibaba.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 52 ++++++++++++++++++++++++++++++++++++++++++++++
 mm/mlock.c                 | 11 +---------
 mm/swap.c                  | 33 +++++++----------------------
 mm/vmscan.c                | 12 ++---------
 4 files changed, 62 insertions(+), 46 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index aa5d559853c2..ff02f831e7e1 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -485,6 +485,22 @@ out:
 
 struct lruvec *mem_cgroup_page_lruvec(struct page *, struct pglist_data *);
 
+static inline bool lruvec_holds_page_lru_lock(struct page *page,
+					      struct lruvec *lruvec)
+{
+	pg_data_t *pgdat = page_pgdat(page);
+	const struct mem_cgroup *memcg;
+	struct mem_cgroup_per_node *mz;
+
+	if (mem_cgroup_disabled())
+		return lruvec == &pgdat->__lruvec;
+
+	mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
+	memcg = page_memcg(page) ? : root_mem_cgroup;
+
+	return lruvec->pgdat == pgdat && mz->memcg == memcg;
+}
+
 struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
 
 struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm);
@@ -984,6 +1000,14 @@ static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page,
 	return &pgdat->__lruvec;
 }
 
+static inline bool lruvec_holds_page_lru_lock(struct page *page,
+					      struct lruvec *lruvec)
+{
+	pg_data_t *pgdat = page_pgdat(page);
+
+	return lruvec == &pgdat->__lruvec;
+}
+
 static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
 {
 	return NULL;
@@ -1354,6 +1378,34 @@ static inline void unlock_page_lruvec_irqrestore(struct lruvec *lruvec,
 	spin_unlock_irqrestore(&lruvec->lru_lock, flags);
 }
 
+/* Don't lock again iff page's lruvec locked */
+static inline struct lruvec *relock_page_lruvec_irq(struct page *page,
+		struct lruvec *locked_lruvec)
+{
+	if (locked_lruvec) {
+		if (lruvec_holds_page_lru_lock(page, locked_lruvec))
+			return locked_lruvec;
+
+		unlock_page_lruvec_irq(locked_lruvec);
+	}
+
+	return lock_page_lruvec_irq(page);
+}
+
+/* Don't lock again iff page's lruvec locked */
+static inline struct lruvec *relock_page_lruvec_irqsave(struct page *page,
+		struct lruvec *locked_lruvec, unsigned long *flags)
+{
+	if (locked_lruvec) {
+		if (lruvec_holds_page_lru_lock(page, locked_lruvec))
+			return locked_lruvec;
+
+		unlock_page_lruvec_irqrestore(locked_lruvec, *flags);
+	}
+
+	return lock_page_lruvec_irqsave(page, flags);
+}
+
 #ifdef CONFIG_CGROUP_WRITEBACK
 
 struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb);
diff --git a/mm/mlock.c b/mm/mlock.c
index ab164a675c25..55b3b3672977 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -277,16 +277,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 			 * so we can spare the get_page() here.
 			 */
 			if (TestClearPageLRU(page)) {
-				struct lruvec *new_lruvec;
-
-				new_lruvec = mem_cgroup_page_lruvec(page,
-						page_pgdat(page));
-				if (new_lruvec != lruvec) {
-					if (lruvec)
-						unlock_page_lruvec_irq(lruvec);
-					lruvec = lock_page_lruvec_irq(page);
-				}
-
+				lruvec = relock_page_lruvec_irq(page, lruvec);
 				del_page_from_lru_list(page, lruvec,
 							page_lru(page));
 				continue;
diff --git a/mm/swap.c b/mm/swap.c
index ba9fc21b24ea..2cca7141470c 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -210,19 +210,12 @@ static void pagevec_lru_move_fn(struct pagevec *pvec,
 
 	for (i = 0; i < pagevec_count(pvec); i++) {
 		struct page *page = pvec->pages[i];
-		struct lruvec *new_lruvec;
 
 		/* block memcg migration during page moving between lru */
 		if (!TestClearPageLRU(page))
 			continue;
 
-		new_lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page));
-		if (lruvec != new_lruvec) {
-			if (lruvec)
-				unlock_page_lruvec_irqrestore(lruvec, flags);
-			lruvec = lock_page_lruvec_irqsave(page, &flags);
-		}
-
+		lruvec = relock_page_lruvec_irqsave(page, lruvec, &flags);
 		(*move_fn)(page, lruvec);
 
 		SetPageLRU(page);
@@ -918,17 +911,12 @@ void release_pages(struct page **pages, int nr)
 		}
 
 		if (PageLRU(page)) {
-			struct lruvec *new_lruvec;
-
-			new_lruvec = mem_cgroup_page_lruvec(page,
-							page_pgdat(page));
-			if (new_lruvec != lruvec) {
-				if (lruvec)
-					unlock_page_lruvec_irqrestore(lruvec,
-									flags);
+			struct lruvec *prev_lruvec = lruvec;
+
+			lruvec = relock_page_lruvec_irqsave(page, lruvec,
+									&flags);
+			if (prev_lruvec != lruvec)
 				lock_batch = 0;
-				lruvec = lock_page_lruvec_irqsave(page, &flags);
-			}
 
 			VM_BUG_ON_PAGE(!PageLRU(page), page);
 			__ClearPageLRU(page);
@@ -1033,15 +1021,8 @@ void __pagevec_lru_add(struct pagevec *pvec)
 
 	for (i = 0; i < pagevec_count(pvec); i++) {
 		struct page *page = pvec->pages[i];
-		struct lruvec *new_lruvec;
-
-		new_lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page));
-		if (lruvec != new_lruvec) {
-			if (lruvec)
-				unlock_page_lruvec_irqrestore(lruvec, flags);
-			lruvec = lock_page_lruvec_irqsave(page, &flags);
-		}
 
+		lruvec = relock_page_lruvec_irqsave(page, lruvec, &flags);
 		__pagevec_lru_add_fn(page, lruvec);
 	}
 	if (lruvec)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b27b5dba3fdd..60705ea598ee 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1883,8 +1883,7 @@ static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec,
 		 * All pages were isolated from the same lruvec (and isolation
 		 * inhibits memcg migration).
 		 */
-		VM_BUG_ON_PAGE(mem_cgroup_page_lruvec(page, page_pgdat(page))
-							!= lruvec, page);
+		VM_BUG_ON_PAGE(!lruvec_holds_page_lru_lock(page, lruvec), page);
 		lru = page_lru(page);
 		nr_pages = thp_nr_pages(page);
 
@@ -4273,7 +4272,6 @@ void check_move_unevictable_pages(struct pagevec *pvec)
 	for (i = 0; i < pvec->nr; i++) {
 		struct page *page = pvec->pages[i];
 		int nr_pages;
-		struct lruvec *new_lruvec;
 
 		if (PageTransTail(page))
 			continue;
@@ -4285,13 +4283,7 @@ void check_move_unevictable_pages(struct pagevec *pvec)
 		if (!TestClearPageLRU(page))
 			continue;
 
-		new_lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page));
-		if (lruvec != new_lruvec) {
-			if (lruvec)
-				unlock_page_lruvec_irq(lruvec);
-			lruvec = lock_page_lruvec_irq(page);
-		}
-
+		lruvec = relock_page_lruvec_irq(page, lruvec);
 		if (page_evictable(page) && PageUnevictable(page)) {
 			enum lru_list lru = page_lru_base_type(page);
 
-- 
cgit v1.2.3


From 15b447361794271f4d03c04d82276a841fe06328 Mon Sep 17 00:00:00 2001
From: Hugh Dickins <hughd@google.com>
Date: Tue, 15 Dec 2020 14:21:31 -0800
Subject: mm/lru: revise the comments of lru_lock
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since we changed the pgdat->lru_lock to lruvec->lru_lock, it's time to fix
the incorrect comments in code.  Also fixed some zone->lru_lock comment
error from ancient time.  etc.

I struggled to understand the comment above move_pages_to_lru() (surely
it never calls page_referenced()), and eventually realized that most of
it had got separated from shrink_active_list(): move that comment back.

Link: https://lkml.kernel.org/r/1604566549-62481-20-git-send-email-alex.shi@linux.alibaba.com
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Tejun Heo <tj@kernel.org>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Jann Horn <jannh@google.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Alexander Duyck <alexander.duyck@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Chen, Rong A" <rong.a.chen@intel.com>
Cc: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mika Penttilä <mika.penttila@nextfour.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Wei Yang <richard.weiyang@gmail.com>
Cc: Yang Shi <yang.shi@linux.alibaba.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/admin-guide/cgroup-v1/memcg_test.rst | 15 ++------
 Documentation/admin-guide/cgroup-v1/memory.rst     | 21 +++++------
 Documentation/trace/events-kmem.rst                |  2 +-
 Documentation/vm/unevictable-lru.rst               | 22 +++++-------
 include/linux/mm_types.h                           |  2 +-
 include/linux/mmzone.h                             |  3 +-
 mm/filemap.c                                       |  4 +--
 mm/rmap.c                                          |  4 +--
 mm/vmscan.c                                        | 41 ++++++++++++----------
 9 files changed, 50 insertions(+), 64 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/admin-guide/cgroup-v1/memcg_test.rst b/Documentation/admin-guide/cgroup-v1/memcg_test.rst
index 4f83de2dab6e..45b94f7b3beb 100644
--- a/Documentation/admin-guide/cgroup-v1/memcg_test.rst
+++ b/Documentation/admin-guide/cgroup-v1/memcg_test.rst
@@ -133,18 +133,9 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
 
 8. LRU
 ======
-        Each memcg has its own private LRU. Now, its handling is under global
-	VM's control (means that it's handled under global pgdat->lru_lock).
-	Almost all routines around memcg's LRU is called by global LRU's
-	list management functions under pgdat->lru_lock.
-
-	A special function is mem_cgroup_isolate_pages(). This scans
-	memcg's private LRU and call __isolate_lru_page() to extract a page
-	from LRU.
-
-	(By __isolate_lru_page(), the page is removed from both of global and
-	private LRU.)
-
+	Each memcg has its own vector of LRUs (inactive anon, active anon,
+	inactive file, active file, unevictable) of pages from each node,
+	each LRU handled under a single lru_lock for that memcg and node.
 
 9. Typical Tests.
 =================
diff --git a/Documentation/admin-guide/cgroup-v1/memory.rst b/Documentation/admin-guide/cgroup-v1/memory.rst
index a44cd467d218..52688ae34461 100644
--- a/Documentation/admin-guide/cgroup-v1/memory.rst
+++ b/Documentation/admin-guide/cgroup-v1/memory.rst
@@ -287,20 +287,17 @@ When oom event notifier is registered, event will be delivered.
 2.6 Locking
 -----------
 
-   lock_page_cgroup()/unlock_page_cgroup() should not be called under
-   the i_pages lock.
+Lock order is as follows:
 
-   Other lock order is following:
+  Page lock (PG_locked bit of page->flags)
+    mm->page_table_lock or split pte_lock
+      lock_page_memcg (memcg->move_lock)
+        mapping->i_pages lock
+          lruvec->lru_lock.
 
-   PG_locked.
-     mm->page_table_lock
-         pgdat->lru_lock
-	   lock_page_cgroup.
-
-  In many cases, just lock_page_cgroup() is called.
-
-  per-zone-per-cgroup LRU (cgroup's private LRU) is just guarded by
-  pgdat->lru_lock, it has no lock of its own.
+Per-node-per-memcgroup LRU (cgroup's private LRU) is guarded by
+lruvec->lru_lock; PG_lru bit of page->flags is cleared before
+isolating a page from its LRU under lruvec->lru_lock.
 
 2.7 Kernel Memory Extension (CONFIG_MEMCG_KMEM)
 -----------------------------------------------
diff --git a/Documentation/trace/events-kmem.rst b/Documentation/trace/events-kmem.rst
index 555484110e36..68fa75247488 100644
--- a/Documentation/trace/events-kmem.rst
+++ b/Documentation/trace/events-kmem.rst
@@ -69,7 +69,7 @@ When pages are freed in batch, the also mm_page_free_batched is triggered.
 Broadly speaking, pages are taken off the LRU lock in bulk and
 freed in batch with a page list. Significant amounts of activity here could
 indicate that the system is under memory pressure and can also indicate
-contention on the zone->lru_lock.
+contention on the lruvec->lru_lock.
 
 4. Per-CPU Allocator Activity
 =============================
diff --git a/Documentation/vm/unevictable-lru.rst b/Documentation/vm/unevictable-lru.rst
index 17d0861b0f1d..0e1490524f53 100644
--- a/Documentation/vm/unevictable-lru.rst
+++ b/Documentation/vm/unevictable-lru.rst
@@ -33,7 +33,7 @@ reclaim in Linux.  The problems have been observed at customer sites on large
 memory x86_64 systems.
 
 To illustrate this with an example, a non-NUMA x86_64 platform with 128GB of
-main memory will have over 32 million 4k pages in a single zone.  When a large
+main memory will have over 32 million 4k pages in a single node.  When a large
 fraction of these pages are not evictable for any reason [see below], vmscan
 will spend a lot of time scanning the LRU lists looking for the small fraction
 of pages that are evictable.  This can result in a situation where all CPUs are
@@ -55,7 +55,7 @@ unevictable, either by definition or by circumstance, in the future.
 The Unevictable Page List
 -------------------------
 
-The Unevictable LRU infrastructure consists of an additional, per-zone, LRU list
+The Unevictable LRU infrastructure consists of an additional, per-node, LRU list
 called the "unevictable" list and an associated page flag, PG_unevictable, to
 indicate that the page is being managed on the unevictable list.
 
@@ -84,15 +84,9 @@ The unevictable list does not differentiate between file-backed and anonymous,
 swap-backed pages.  This differentiation is only important while the pages are,
 in fact, evictable.
 
-The unevictable list benefits from the "arrayification" of the per-zone LRU
+The unevictable list benefits from the "arrayification" of the per-node LRU
 lists and statistics originally proposed and posted by Christoph Lameter.
 
-The unevictable list does not use the LRU pagevec mechanism. Rather,
-unevictable pages are placed directly on the page's zone's unevictable list
-under the zone lru_lock.  This allows us to prevent the stranding of pages on
-the unevictable list when one task has the page isolated from the LRU and other
-tasks are changing the "evictability" state of the page.
-
 
 Memory Control Group Interaction
 --------------------------------
@@ -101,8 +95,8 @@ The unevictable LRU facility interacts with the memory control group [aka
 memory controller; see Documentation/admin-guide/cgroup-v1/memory.rst] by extending the
 lru_list enum.
 
-The memory controller data structure automatically gets a per-zone unevictable
-list as a result of the "arrayification" of the per-zone LRU lists (one per
+The memory controller data structure automatically gets a per-node unevictable
+list as a result of the "arrayification" of the per-node LRU lists (one per
 lru_list enum element).  The memory controller tracks the movement of pages to
 and from the unevictable list.
 
@@ -196,7 +190,7 @@ for the sake of expediency, to leave a unevictable page on one of the regular
 active/inactive LRU lists for vmscan to deal with.  vmscan checks for such
 pages in all of the shrink_{active|inactive|page}_list() functions and will
 "cull" such pages that it encounters: that is, it diverts those pages to the
-unevictable list for the zone being scanned.
+unevictable list for the node being scanned.
 
 There may be situations where a page is mapped into a VM_LOCKED VMA, but the
 page is not marked as PG_mlocked.  Such pages will make it all the way to
@@ -328,7 +322,7 @@ If the page was NOT already mlocked, mlock_vma_page() attempts to isolate the
 page from the LRU, as it is likely on the appropriate active or inactive list
 at that time.  If the isolate_lru_page() succeeds, mlock_vma_page() will put
 back the page - by calling putback_lru_page() - which will notice that the page
-is now mlocked and divert the page to the zone's unevictable list.  If
+is now mlocked and divert the page to the node's unevictable list.  If
 mlock_vma_page() is unable to isolate the page from the LRU, vmscan will handle
 it later if and when it attempts to reclaim the page.
 
@@ -603,7 +597,7 @@ Some examples of these unevictable pages on the LRU lists are:
      unevictable list in mlock_vma_page().
 
 shrink_inactive_list() also diverts any unevictable pages that it finds on the
-inactive lists to the appropriate zone's unevictable list.
+inactive lists to the appropriate node's unevictable list.
 
 shrink_inactive_list() should only see SHM_LOCK'd pages that became SHM_LOCK'd
 after shrink_active_list() had moved them to the inactive list, or pages mapped
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 915f4f100383..a9688cc55964 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -79,7 +79,7 @@ struct page {
 		struct {	/* Page cache and anonymous pages */
 			/**
 			 * @lru: Pageout list, eg. active_list protected by
-			 * pgdat->lru_lock.  Sometimes used as a generic list
+			 * lruvec->lru_lock.  Sometimes used as a generic list
 			 * by the page owner.
 			 */
 			struct list_head lru;
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 9da23c019dc5..b593316bff3d 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -113,8 +113,7 @@ static inline bool free_area_empty(struct free_area *area, int migratetype)
 struct pglist_data;
 
 /*
- * zone->lock and the zone lru_lock are two of the hottest locks in the kernel.
- * So add a wild amount of padding here to ensure that they fall into separate
+ * Add a wild amount of padding here to ensure datas fall into separate
  * cachelines.  There are very few zone structures in the machine, so space
  * consumption is not a concern here.
  */
diff --git a/mm/filemap.c b/mm/filemap.c
index 39bb88140680..c178022d7893 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -102,8 +102,8 @@
  *    ->swap_lock		(try_to_unmap_one)
  *    ->private_lock		(try_to_unmap_one)
  *    ->i_pages lock		(try_to_unmap_one)
- *    ->pgdat->lru_lock		(follow_page->mark_page_accessed)
- *    ->pgdat->lru_lock		(check_pte_range->isolate_lru_page)
+ *    ->lruvec->lru_lock	(follow_page->mark_page_accessed)
+ *    ->lruvec->lru_lock	(check_pte_range->isolate_lru_page)
  *    ->private_lock		(page_remove_rmap->set_page_dirty)
  *    ->i_pages lock		(page_remove_rmap->set_page_dirty)
  *    bdi.wb->list_lock		(page_remove_rmap->set_page_dirty)
diff --git a/mm/rmap.c b/mm/rmap.c
index ab16c96efdfb..08c56aaf72eb 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -28,12 +28,12 @@
  *           hugetlb_fault_mutex (hugetlbfs specific page fault mutex)
  *           anon_vma->rwsem
  *             mm->page_table_lock or pte_lock
- *               pgdat->lru_lock (in mark_page_accessed, isolate_lru_page)
  *               swap_lock (in swap_duplicate, swap_info_get)
  *                 mmlist_lock (in mmput, drain_mmlist and others)
  *                 mapping->private_lock (in __set_page_dirty_buffers)
- *                   mem_cgroup_{begin,end}_page_stat (memcg->move_lock)
+ *                   lock_page_memcg move_lock (in __set_page_dirty_buffers)
  *                     i_pages lock (widely used)
+ *                       lruvec->lru_lock (in lock_page_lruvec_irq)
  *                 inode->i_lock (in set_page_dirty's __mark_inode_dirty)
  *                 bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty)
  *                   sb_lock (within inode_lock in fs/fs-writeback.c)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 60705ea598ee..257cba79a96d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1613,14 +1613,16 @@ static __always_inline void update_lru_sizes(struct lruvec *lruvec,
 }
 
 /**
- * pgdat->lru_lock is heavily contended.  Some of the functions that
+ * Isolating page from the lruvec to fill in @dst list by nr_to_scan times.
+ *
+ * lruvec->lru_lock is heavily contended.  Some of the functions that
  * shrink the lists perform better by taking out a batch of pages
  * and working on them outside the LRU lock.
  *
  * For pagecache intensive workloads, this function is the hottest
  * spot in the kernel (apart from copy_*_user functions).
  *
- * Appropriate locks must be held before calling this function.
+ * Lru_lock must be held before calling this function.
  *
  * @nr_to_scan:	The number of eligible pages to look through on the list.
  * @lruvec:	The LRU vector to pull pages from.
@@ -1814,25 +1816,11 @@ static int too_many_isolated(struct pglist_data *pgdat, int file,
 }
 
 /*
- * This moves pages from @list to corresponding LRU list.
- *
- * We move them the other way if the page is referenced by one or more
- * processes, from rmap.
- *
- * If the pages are mostly unmapped, the processing is fast and it is
- * appropriate to hold zone_lru_lock across the whole operation.  But if
- * the pages are mapped, the processing is slow (page_referenced()) so we
- * should drop zone_lru_lock around each page.  It's impossible to balance
- * this, so instead we remove the pages from the LRU while processing them.
- * It is safe to rely on PG_active against the non-LRU pages in here because
- * nobody will play with that bit on a non-LRU page.
- *
- * The downside is that we have to touch page->_refcount against each page.
- * But we had to alter page->flags anyway.
+ * move_pages_to_lru() moves pages from private @list to appropriate LRU list.
+ * On return, @list is reused as a list of pages to be freed by the caller.
  *
  * Returns the number of pages moved to the given lruvec.
  */
-
 static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec,
 						     struct list_head *list)
 {
@@ -2010,6 +1998,23 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	return nr_reclaimed;
 }
 
+/*
+ * shrink_active_list() moves pages from the active LRU to the inactive LRU.
+ *
+ * We move them the other way if the page is referenced by one or more
+ * processes.
+ *
+ * If the pages are mostly unmapped, the processing is fast and it is
+ * appropriate to hold lru_lock across the whole operation.  But if
+ * the pages are mapped, the processing is slow (page_referenced()), so
+ * we should drop lru_lock around each page.  It's impossible to balance
+ * this, so instead we remove the pages from the LRU while processing them.
+ * It is safe to rely on PG_active against the non-LRU pages in here because
+ * nobody will play with that bit on a non-LRU page.
+ *
+ * The downside is that we have to touch page->_refcount against each page.
+ * But we had to alter page->flags anyway.
+ */
 static void shrink_active_list(unsigned long nr_to_scan,
 			       struct lruvec *lruvec,
 			       struct scan_control *sc,
-- 
cgit v1.2.3


From c6c75deda81344c3a95d1d1f606d5cee109e5d54 Mon Sep 17 00:00:00 2001
From: Alexey Dobriyan <adobriyan@gmail.com>
Date: Tue, 15 Dec 2020 20:42:39 -0800
Subject: proc: fix lookup in /proc/net subdirectories after setns(2)

Commit 1fde6f21d90f ("proc: fix /proc/net/* after setns(2)") only forced
revalidation of regular files under /proc/net/

However, /proc/net/ is unusual in the sense of /proc/net/foo handlers
take netns pointer from parent directory which is old netns.

Steps to reproduce:

	(void)open("/proc/net/sctp/snmp", O_RDONLY);
	unshare(CLONE_NEWNET);

	int fd = open("/proc/net/sctp/snmp", O_RDONLY);
	read(fd, &c, 1);

Read will read wrong data from original netns.

Patch forces lookup on every directory under /proc/net .

Link: https://lkml.kernel.org/r/20201205160916.GA109739@localhost.localdomain
Fixes: 1da4d377f943 ("proc: revalidate misc dentries")
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Reported-by: "Rantala, Tommi T. (Nokia - FI/Espoo)" <tommi.t.rantala@nokia.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/proc/generic.c       | 24 ++++++++++++++++++++++--
 fs/proc/internal.h      |  7 +++++++
 fs/proc/proc_net.c      | 16 ----------------
 include/linux/proc_fs.h |  8 +++++++-
 4 files changed, 36 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index b84663252add..6c0a05f55d6b 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -349,6 +349,16 @@ static const struct file_operations proc_dir_operations = {
 	.iterate_shared		= proc_readdir,
 };
 
+static int proc_net_d_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	return 0;
+}
+
+const struct dentry_operations proc_net_dentry_ops = {
+	.d_revalidate	= proc_net_d_revalidate,
+	.d_delete	= always_delete_dentry,
+};
+
 /*
  * proc directories can do almost nothing..
  */
@@ -471,8 +481,8 @@ struct proc_dir_entry *proc_symlink(const char *name,
 }
 EXPORT_SYMBOL(proc_symlink);
 
-struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode,
-		struct proc_dir_entry *parent, void *data)
+struct proc_dir_entry *_proc_mkdir(const char *name, umode_t mode,
+		struct proc_dir_entry *parent, void *data, bool force_lookup)
 {
 	struct proc_dir_entry *ent;
 
@@ -484,10 +494,20 @@ struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode,
 		ent->data = data;
 		ent->proc_dir_ops = &proc_dir_operations;
 		ent->proc_iops = &proc_dir_inode_operations;
+		if (force_lookup) {
+			pde_force_lookup(ent);
+		}
 		ent = proc_register(parent, ent);
 	}
 	return ent;
 }
+EXPORT_SYMBOL_GPL(_proc_mkdir);
+
+struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode,
+		struct proc_dir_entry *parent, void *data)
+{
+	return _proc_mkdir(name, mode, parent, data, false);
+}
 EXPORT_SYMBOL_GPL(proc_mkdir_data);
 
 struct proc_dir_entry *proc_mkdir_mode(const char *name, umode_t mode,
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 917cc85e3466..afbe96b6bf77 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -310,3 +310,10 @@ extern unsigned long task_statm(struct mm_struct *,
 				unsigned long *, unsigned long *,
 				unsigned long *, unsigned long *);
 extern void task_mem(struct seq_file *, struct mm_struct *);
+
+extern const struct dentry_operations proc_net_dentry_ops;
+static inline void pde_force_lookup(struct proc_dir_entry *pde)
+{
+	/* /proc/net/ entries can be changed under us by setns(CLONE_NEWNET) */
+	pde->proc_dops = &proc_net_dentry_ops;
+}
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index 45c7318a2ce5..18601042af99 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -39,22 +39,6 @@ static struct net *get_proc_net(const struct inode *inode)
 	return maybe_get_net(PDE_NET(PDE(inode)));
 }
 
-static int proc_net_d_revalidate(struct dentry *dentry, unsigned int flags)
-{
-	return 0;
-}
-
-static const struct dentry_operations proc_net_dentry_ops = {
-	.d_revalidate	= proc_net_d_revalidate,
-	.d_delete	= always_delete_dentry,
-};
-
-static void pde_force_lookup(struct proc_dir_entry *pde)
-{
-	/* /proc/net/ entries can be changed under us by setns(CLONE_NEWNET) */
-	pde->proc_dops = &proc_net_dentry_ops;
-}
-
 static int seq_open_net(struct inode *inode, struct file *file)
 {
 	unsigned int state_size = PDE(inode)->state_size;
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index 270cab43ca3d..000cc0533c33 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -80,6 +80,7 @@ extern void proc_flush_pid(struct pid *);
 
 extern struct proc_dir_entry *proc_symlink(const char *,
 		struct proc_dir_entry *, const char *);
+struct proc_dir_entry *_proc_mkdir(const char *, umode_t, struct proc_dir_entry *, void *, bool);
 extern struct proc_dir_entry *proc_mkdir(const char *, struct proc_dir_entry *);
 extern struct proc_dir_entry *proc_mkdir_data(const char *, umode_t,
 					      struct proc_dir_entry *, void *);
@@ -162,6 +163,11 @@ static inline struct proc_dir_entry *proc_symlink(const char *name,
 static inline struct proc_dir_entry *proc_mkdir(const char *name,
 	struct proc_dir_entry *parent) {return NULL;}
 static inline struct proc_dir_entry *proc_create_mount_point(const char *name) { return NULL; }
+static inline struct proc_dir_entry *_proc_mkdir(const char *name, umode_t mode,
+		struct proc_dir_entry *parent, void *data, bool force_lookup)
+{
+	return NULL;
+}
 static inline struct proc_dir_entry *proc_mkdir_data(const char *name,
 	umode_t mode, struct proc_dir_entry *parent, void *data) { return NULL; }
 static inline struct proc_dir_entry *proc_mkdir_mode(const char *name,
@@ -199,7 +205,7 @@ struct net;
 static inline struct proc_dir_entry *proc_net_mkdir(
 	struct net *net, const char *name, struct proc_dir_entry *parent)
 {
-	return proc_mkdir_data(name, 0, parent, net);
+	return _proc_mkdir(name, 0, parent, net, true);
 }
 
 struct ns_common;
-- 
cgit v1.2.3


From aa6159ab99a9ab5df835b4750b66cf132a5aa292 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 15 Dec 2020 20:42:48 -0800
Subject: kernel.h: split out mathematical helpers

kernel.h is being used as a dump for all kinds of stuff for a long time.
Here is the attempt to start cleaning it up by splitting out
mathematical helpers.

At the same time convert users in header and lib folder to use new
header.  Though for time being include new header back to kernel.h to
avoid twisted indirected includes for existing users.

[sfr@canb.auug.org.au: fix powerpc build]
  Link: https://lkml.kernel.org/r/20201029150809.13059608@canb.auug.org.au

Link: https://lkml.kernel.org/r/20201028173212.41768-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: "Paul E. McKenney" <paulmck@kernel.org>
Cc: Trond Myklebust <trond.myklebust@hammerspace.com>
Cc: Jeff Layton <jlayton@kernel.org>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/nfs/callback_proc.c        |   5 ++
 include/linux/bitops.h        |  11 ++-
 include/linux/dcache.h        |   1 +
 include/linux/iommu-helper.h  |   4 +-
 include/linux/kernel.h        | 173 +----------------------------------------
 include/linux/math.h          | 177 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/rcu_node_tree.h |   2 +
 include/linux/units.h         |   2 +-
 lib/errname.c                 |   1 +
 lib/errseq.c                  |   1 +
 lib/find_bit.c                |   3 +-
 lib/math/div64.c              |   4 +-
 lib/math/int_pow.c            |   2 +-
 lib/math/int_sqrt.c           |   3 +-
 lib/math/reciprocal_div.c     |   9 ++-
 15 files changed, 215 insertions(+), 183 deletions(-)
 create mode 100644 include/linux/math.h

(limited to 'include/linux')

diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index e61dbc9b86ae..f7786e00a6a7 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -6,10 +6,15 @@
  *
  * NFSv4 callback procedures
  */
+
+#include <linux/errno.h>
+#include <linux/math.h>
 #include <linux/nfs4.h>
 #include <linux/nfs_fs.h>
 #include <linux/slab.h>
 #include <linux/rcupdate.h>
+#include <linux/types.h>
+
 #include "nfs4_fs.h"
 #include "callback.h"
 #include "delegation.h"
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index 5b74bdf159d6..a61f192c096b 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -1,9 +1,12 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LINUX_BITOPS_H
 #define _LINUX_BITOPS_H
+
 #include <asm/types.h>
 #include <linux/bits.h>
 
+#include <uapi/linux/kernel.h>
+
 /* Set bits in the first 'n' bytes when loaded from memory */
 #ifdef __LITTLE_ENDIAN
 #  define aligned_byte_mask(n) ((1UL << 8*(n))-1)
@@ -12,10 +15,10 @@
 #endif
 
 #define BITS_PER_TYPE(type)	(sizeof(type) * BITS_PER_BYTE)
-#define BITS_TO_LONGS(nr)	DIV_ROUND_UP(nr, BITS_PER_TYPE(long))
-#define BITS_TO_U64(nr)		DIV_ROUND_UP(nr, BITS_PER_TYPE(u64))
-#define BITS_TO_U32(nr)		DIV_ROUND_UP(nr, BITS_PER_TYPE(u32))
-#define BITS_TO_BYTES(nr)	DIV_ROUND_UP(nr, BITS_PER_TYPE(char))
+#define BITS_TO_LONGS(nr)	__KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(long))
+#define BITS_TO_U64(nr)		__KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(u64))
+#define BITS_TO_U32(nr)		__KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(u32))
+#define BITS_TO_BYTES(nr)	__KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(char))
 
 extern unsigned int __sw_hweight8(unsigned int w);
 extern unsigned int __sw_hweight16(unsigned int w);
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 6f95c3300cbb..d7b369fc15d3 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -4,6 +4,7 @@
 
 #include <linux/atomic.h>
 #include <linux/list.h>
+#include <linux/math.h>
 #include <linux/rculist.h>
 #include <linux/rculist_bl.h>
 #include <linux/spinlock.h>
diff --git a/include/linux/iommu-helper.h b/include/linux/iommu-helper.h
index 70d01edcbf8b..74be34f3a20a 100644
--- a/include/linux/iommu-helper.h
+++ b/include/linux/iommu-helper.h
@@ -3,7 +3,9 @@
 #define _LINUX_IOMMU_HELPER_H
 
 #include <linux/bug.h>
-#include <linux/kernel.h>
+#include <linux/log2.h>
+#include <linux/math.h>
+#include <linux/types.h>
 
 static inline unsigned long iommu_device_max_index(unsigned long size,
 						   unsigned long offset,
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index dbf6018fc312..f7902d8c1048 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -2,7 +2,6 @@
 #ifndef _LINUX_KERNEL_H
 #define _LINUX_KERNEL_H
 
-
 #include <stdarg.h>
 #include <linux/limits.h>
 #include <linux/linkage.h>
@@ -11,12 +10,14 @@
 #include <linux/compiler.h>
 #include <linux/bitops.h>
 #include <linux/log2.h>
+#include <linux/math.h>
 #include <linux/minmax.h>
 #include <linux/typecheck.h>
 #include <linux/printk.h>
 #include <linux/build_bug.h>
+
 #include <asm/byteorder.h>
-#include <asm/div64.h>
+
 #include <uapi/linux/kernel.h>
 
 #define STACK_MAGIC	0xdeadbeef
@@ -54,125 +55,11 @@
 }					\
 )
 
-/*
- * This looks more complex than it should be. But we need to
- * get the type for the ~ right in round_down (it needs to be
- * as wide as the result!), and we want to evaluate the macro
- * arguments just once each.
- */
-#define __round_mask(x, y) ((__typeof__(x))((y)-1))
-/**
- * round_up - round up to next specified power of 2
- * @x: the value to round
- * @y: multiple to round up to (must be a power of 2)
- *
- * Rounds @x up to next multiple of @y (which must be a power of 2).
- * To perform arbitrary rounding up, use roundup() below.
- */
-#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1)
-/**
- * round_down - round down to next specified power of 2
- * @x: the value to round
- * @y: multiple to round down to (must be a power of 2)
- *
- * Rounds @x down to next multiple of @y (which must be a power of 2).
- * To perform arbitrary rounding down, use rounddown() below.
- */
-#define round_down(x, y) ((x) & ~__round_mask(x, y))
-
 #define typeof_member(T, m)	typeof(((T*)0)->m)
 
-#define DIV_ROUND_UP __KERNEL_DIV_ROUND_UP
-
-#define DIV_ROUND_DOWN_ULL(ll, d) \
-	({ unsigned long long _tmp = (ll); do_div(_tmp, d); _tmp; })
-
-#define DIV_ROUND_UP_ULL(ll, d) \
-	DIV_ROUND_DOWN_ULL((unsigned long long)(ll) + (d) - 1, (d))
-
-#if BITS_PER_LONG == 32
-# define DIV_ROUND_UP_SECTOR_T(ll,d) DIV_ROUND_UP_ULL(ll, d)
-#else
-# define DIV_ROUND_UP_SECTOR_T(ll,d) DIV_ROUND_UP(ll,d)
-#endif
-
-/**
- * roundup - round up to the next specified multiple
- * @x: the value to up
- * @y: multiple to round up to
- *
- * Rounds @x up to next multiple of @y. If @y will always be a power
- * of 2, consider using the faster round_up().
- */
-#define roundup(x, y) (					\
-{							\
-	typeof(y) __y = y;				\
-	(((x) + (__y - 1)) / __y) * __y;		\
-}							\
-)
-/**
- * rounddown - round down to next specified multiple
- * @x: the value to round
- * @y: multiple to round down to
- *
- * Rounds @x down to next multiple of @y. If @y will always be a power
- * of 2, consider using the faster round_down().
- */
-#define rounddown(x, y) (				\
-{							\
-	typeof(x) __x = (x);				\
-	__x - (__x % (y));				\
-}							\
-)
-
-/*
- * Divide positive or negative dividend by positive or negative divisor
- * and round to closest integer. Result is undefined for negative
- * divisors if the dividend variable type is unsigned and for negative
- * dividends if the divisor variable type is unsigned.
- */
-#define DIV_ROUND_CLOSEST(x, divisor)(			\
-{							\
-	typeof(x) __x = x;				\
-	typeof(divisor) __d = divisor;			\
-	(((typeof(x))-1) > 0 ||				\
-	 ((typeof(divisor))-1) > 0 ||			\
-	 (((__x) > 0) == ((__d) > 0))) ?		\
-		(((__x) + ((__d) / 2)) / (__d)) :	\
-		(((__x) - ((__d) / 2)) / (__d));	\
-}							\
-)
-/*
- * Same as above but for u64 dividends. divisor must be a 32-bit
- * number.
- */
-#define DIV_ROUND_CLOSEST_ULL(x, divisor)(		\
-{							\
-	typeof(divisor) __d = divisor;			\
-	unsigned long long _tmp = (x) + (__d) / 2;	\
-	do_div(_tmp, __d);				\
-	_tmp;						\
-}							\
-)
-
-/*
- * Multiplies an integer by a fraction, while avoiding unnecessary
- * overflow or loss of precision.
- */
-#define mult_frac(x, numer, denom)(			\
-{							\
-	typeof(x) quot = (x) / (denom);			\
-	typeof(x) rem  = (x) % (denom);			\
-	(quot * (numer)) + ((rem * (numer)) / (denom));	\
-}							\
-)
-
-
 #define _RET_IP_		(unsigned long)__builtin_return_address(0)
 #define _THIS_IP_  ({ __label__ __here; __here: (unsigned long)&&__here; })
 
-#define sector_div(a, b) do_div(a, b)
-
 /**
  * upper_32_bits - return bits 32-63 of a number
  * @n: the number we're accessing
@@ -272,48 +159,6 @@ extern void __cant_migrate(const char *file, int line);
 
 #define might_sleep_if(cond) do { if (cond) might_sleep(); } while (0)
 
-/**
- * abs - return absolute value of an argument
- * @x: the value.  If it is unsigned type, it is converted to signed type first.
- *     char is treated as if it was signed (regardless of whether it really is)
- *     but the macro's return type is preserved as char.
- *
- * Return: an absolute value of x.
- */
-#define abs(x)	__abs_choose_expr(x, long long,				\
-		__abs_choose_expr(x, long,				\
-		__abs_choose_expr(x, int,				\
-		__abs_choose_expr(x, short,				\
-		__abs_choose_expr(x, char,				\
-		__builtin_choose_expr(					\
-			__builtin_types_compatible_p(typeof(x), char),	\
-			(char)({ signed char __x = (x); __x<0?-__x:__x; }), \
-			((void)0)))))))
-
-#define __abs_choose_expr(x, type, other) __builtin_choose_expr(	\
-	__builtin_types_compatible_p(typeof(x),   signed type) ||	\
-	__builtin_types_compatible_p(typeof(x), unsigned type),		\
-	({ signed type __x = (x); __x < 0 ? -__x : __x; }), other)
-
-/**
- * reciprocal_scale - "scale" a value into range [0, ep_ro)
- * @val: value
- * @ep_ro: right open interval endpoint
- *
- * Perform a "reciprocal multiplication" in order to "scale" a value into
- * range [0, @ep_ro), where the upper interval endpoint is right-open.
- * This is useful, e.g. for accessing a index of an array containing
- * @ep_ro elements, for example. Think of it as sort of modulus, only that
- * the result isn't that of modulo. ;) Note that if initial input is a
- * small value, then result will return 0.
- *
- * Return: a result based on @val in interval [0, @ep_ro).
- */
-static inline u32 reciprocal_scale(u32 val, u32 ep_ro)
-{
-	return (u32)(((u64) val * ep_ro) >> 32);
-}
-
 #if defined(CONFIG_MMU) && \
 	(defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP))
 #define might_fault() __might_fault(__FILE__, __LINE__)
@@ -515,18 +360,6 @@ extern int __kernel_text_address(unsigned long addr);
 extern int kernel_text_address(unsigned long addr);
 extern int func_ptr_is_kernel_text(void *ptr);
 
-u64 int_pow(u64 base, unsigned int exp);
-unsigned long int_sqrt(unsigned long);
-
-#if BITS_PER_LONG < 64
-u32 int_sqrt64(u64 x);
-#else
-static inline u32 int_sqrt64(u64 x)
-{
-	return (u32)int_sqrt(x);
-}
-#endif
-
 #ifdef CONFIG_SMP
 extern unsigned int sysctl_oops_all_cpu_backtrace;
 #else
diff --git a/include/linux/math.h b/include/linux/math.h
new file mode 100644
index 000000000000..53674a327e39
--- /dev/null
+++ b/include/linux/math.h
@@ -0,0 +1,177 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_MATH_H
+#define _LINUX_MATH_H
+
+#include <asm/div64.h>
+#include <uapi/linux/kernel.h>
+
+/*
+ * This looks more complex than it should be. But we need to
+ * get the type for the ~ right in round_down (it needs to be
+ * as wide as the result!), and we want to evaluate the macro
+ * arguments just once each.
+ */
+#define __round_mask(x, y) ((__typeof__(x))((y)-1))
+
+/**
+ * round_up - round up to next specified power of 2
+ * @x: the value to round
+ * @y: multiple to round up to (must be a power of 2)
+ *
+ * Rounds @x up to next multiple of @y (which must be a power of 2).
+ * To perform arbitrary rounding up, use roundup() below.
+ */
+#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1)
+
+/**
+ * round_down - round down to next specified power of 2
+ * @x: the value to round
+ * @y: multiple to round down to (must be a power of 2)
+ *
+ * Rounds @x down to next multiple of @y (which must be a power of 2).
+ * To perform arbitrary rounding down, use rounddown() below.
+ */
+#define round_down(x, y) ((x) & ~__round_mask(x, y))
+
+#define DIV_ROUND_UP __KERNEL_DIV_ROUND_UP
+
+#define DIV_ROUND_DOWN_ULL(ll, d) \
+	({ unsigned long long _tmp = (ll); do_div(_tmp, d); _tmp; })
+
+#define DIV_ROUND_UP_ULL(ll, d) \
+	DIV_ROUND_DOWN_ULL((unsigned long long)(ll) + (d) - 1, (d))
+
+#if BITS_PER_LONG == 32
+# define DIV_ROUND_UP_SECTOR_T(ll,d) DIV_ROUND_UP_ULL(ll, d)
+#else
+# define DIV_ROUND_UP_SECTOR_T(ll,d) DIV_ROUND_UP(ll,d)
+#endif
+
+/**
+ * roundup - round up to the next specified multiple
+ * @x: the value to up
+ * @y: multiple to round up to
+ *
+ * Rounds @x up to next multiple of @y. If @y will always be a power
+ * of 2, consider using the faster round_up().
+ */
+#define roundup(x, y) (					\
+{							\
+	typeof(y) __y = y;				\
+	(((x) + (__y - 1)) / __y) * __y;		\
+}							\
+)
+/**
+ * rounddown - round down to next specified multiple
+ * @x: the value to round
+ * @y: multiple to round down to
+ *
+ * Rounds @x down to next multiple of @y. If @y will always be a power
+ * of 2, consider using the faster round_down().
+ */
+#define rounddown(x, y) (				\
+{							\
+	typeof(x) __x = (x);				\
+	__x - (__x % (y));				\
+}							\
+)
+
+/*
+ * Divide positive or negative dividend by positive or negative divisor
+ * and round to closest integer. Result is undefined for negative
+ * divisors if the dividend variable type is unsigned and for negative
+ * dividends if the divisor variable type is unsigned.
+ */
+#define DIV_ROUND_CLOSEST(x, divisor)(			\
+{							\
+	typeof(x) __x = x;				\
+	typeof(divisor) __d = divisor;			\
+	(((typeof(x))-1) > 0 ||				\
+	 ((typeof(divisor))-1) > 0 ||			\
+	 (((__x) > 0) == ((__d) > 0))) ?		\
+		(((__x) + ((__d) / 2)) / (__d)) :	\
+		(((__x) - ((__d) / 2)) / (__d));	\
+}							\
+)
+/*
+ * Same as above but for u64 dividends. divisor must be a 32-bit
+ * number.
+ */
+#define DIV_ROUND_CLOSEST_ULL(x, divisor)(		\
+{							\
+	typeof(divisor) __d = divisor;			\
+	unsigned long long _tmp = (x) + (__d) / 2;	\
+	do_div(_tmp, __d);				\
+	_tmp;						\
+}							\
+)
+
+/*
+ * Multiplies an integer by a fraction, while avoiding unnecessary
+ * overflow or loss of precision.
+ */
+#define mult_frac(x, numer, denom)(			\
+{							\
+	typeof(x) quot = (x) / (denom);			\
+	typeof(x) rem  = (x) % (denom);			\
+	(quot * (numer)) + ((rem * (numer)) / (denom));	\
+}							\
+)
+
+#define sector_div(a, b) do_div(a, b)
+
+/**
+ * abs - return absolute value of an argument
+ * @x: the value.  If it is unsigned type, it is converted to signed type first.
+ *     char is treated as if it was signed (regardless of whether it really is)
+ *     but the macro's return type is preserved as char.
+ *
+ * Return: an absolute value of x.
+ */
+#define abs(x)	__abs_choose_expr(x, long long,				\
+		__abs_choose_expr(x, long,				\
+		__abs_choose_expr(x, int,				\
+		__abs_choose_expr(x, short,				\
+		__abs_choose_expr(x, char,				\
+		__builtin_choose_expr(					\
+			__builtin_types_compatible_p(typeof(x), char),	\
+			(char)({ signed char __x = (x); __x<0?-__x:__x; }), \
+			((void)0)))))))
+
+#define __abs_choose_expr(x, type, other) __builtin_choose_expr(	\
+	__builtin_types_compatible_p(typeof(x),   signed type) ||	\
+	__builtin_types_compatible_p(typeof(x), unsigned type),		\
+	({ signed type __x = (x); __x < 0 ? -__x : __x; }), other)
+
+/**
+ * reciprocal_scale - "scale" a value into range [0, ep_ro)
+ * @val: value
+ * @ep_ro: right open interval endpoint
+ *
+ * Perform a "reciprocal multiplication" in order to "scale" a value into
+ * range [0, @ep_ro), where the upper interval endpoint is right-open.
+ * This is useful, e.g. for accessing a index of an array containing
+ * @ep_ro elements, for example. Think of it as sort of modulus, only that
+ * the result isn't that of modulo. ;) Note that if initial input is a
+ * small value, then result will return 0.
+ *
+ * Return: a result based on @val in interval [0, @ep_ro).
+ */
+static inline u32 reciprocal_scale(u32 val, u32 ep_ro)
+{
+	return (u32)(((u64) val * ep_ro) >> 32);
+}
+
+u64 int_pow(u64 base, unsigned int exp);
+unsigned long int_sqrt(unsigned long);
+
+#if BITS_PER_LONG < 64
+u32 int_sqrt64(u64 x);
+#else
+static inline u32 int_sqrt64(u64 x)
+{
+	return (u32)int_sqrt(x);
+}
+#endif
+
+#endif	/* _LINUX_MATH_H */
diff --git a/include/linux/rcu_node_tree.h b/include/linux/rcu_node_tree.h
index b8e094b125ee..78feb8ba7358 100644
--- a/include/linux/rcu_node_tree.h
+++ b/include/linux/rcu_node_tree.h
@@ -20,6 +20,8 @@
 #ifndef __LINUX_RCU_NODE_TREE_H
 #define __LINUX_RCU_NODE_TREE_H
 
+#include <linux/math.h>
+
 /*
  * Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and
  * CONFIG_RCU_FANOUT_LEAF.
diff --git a/include/linux/units.h b/include/linux/units.h
index aaf716364ec3..5c115c809507 100644
--- a/include/linux/units.h
+++ b/include/linux/units.h
@@ -2,7 +2,7 @@
 #ifndef _LINUX_UNITS_H
 #define _LINUX_UNITS_H
 
-#include <linux/kernel.h>
+#include <linux/math.h>
 
 #define ABSOLUTE_ZERO_MILLICELSIUS -273150
 
diff --git a/lib/errname.c b/lib/errname.c
index 0c4d3e66170e..05cbf731545f 100644
--- a/lib/errname.c
+++ b/lib/errname.c
@@ -3,6 +3,7 @@
 #include <linux/errno.h>
 #include <linux/errname.h>
 #include <linux/kernel.h>
+#include <linux/math.h>
 
 /*
  * Ensure these tables do not accidentally become gigantic if some
diff --git a/lib/errseq.c b/lib/errseq.c
index 81f9e33aa7e7..93e9b94358dc 100644
--- a/lib/errseq.c
+++ b/lib/errseq.c
@@ -3,6 +3,7 @@
 #include <linux/bug.h>
 #include <linux/atomic.h>
 #include <linux/errseq.h>
+#include <linux/log2.h>
 
 /*
  * An errseq_t is a way of recording errors in one place, and allowing any
diff --git a/lib/find_bit.c b/lib/find_bit.c
index 4a8751010d59..f67f86fd2f62 100644
--- a/lib/find_bit.c
+++ b/lib/find_bit.c
@@ -15,8 +15,9 @@
 #include <linux/bitops.h>
 #include <linux/bitmap.h>
 #include <linux/export.h>
-#include <linux/kernel.h>
+#include <linux/math.h>
 #include <linux/minmax.h>
+#include <linux/swab.h>
 
 #if !defined(find_next_bit) || !defined(find_next_zero_bit) ||			\
 	!defined(find_next_bit_le) || !defined(find_next_zero_bit_le) ||	\
diff --git a/lib/math/div64.c b/lib/math/div64.c
index 3952a07130d8..064d68a5391a 100644
--- a/lib/math/div64.c
+++ b/lib/math/div64.c
@@ -18,9 +18,11 @@
  * or by defining a preprocessor macro in arch/include/asm/div64.h.
  */
 
+#include <linux/bitops.h>
 #include <linux/export.h>
-#include <linux/kernel.h>
+#include <linux/math.h>
 #include <linux/math64.h>
+#include <linux/log2.h>
 
 /* Not needed on 64bit architectures */
 #if BITS_PER_LONG == 32
diff --git a/lib/math/int_pow.c b/lib/math/int_pow.c
index 622fc1ab3c74..0cf426e69bda 100644
--- a/lib/math/int_pow.c
+++ b/lib/math/int_pow.c
@@ -6,7 +6,7 @@
  */
 
 #include <linux/export.h>
-#include <linux/kernel.h>
+#include <linux/math.h>
 #include <linux/types.h>
 
 /**
diff --git a/lib/math/int_sqrt.c b/lib/math/int_sqrt.c
index 30e0f9770f88..a8170bb9142f 100644
--- a/lib/math/int_sqrt.c
+++ b/lib/math/int_sqrt.c
@@ -6,9 +6,10 @@
  *  square root from Guy L. Steele.
  */
 
-#include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/bitops.h>
+#include <linux/limits.h>
+#include <linux/math.h>
 
 /**
  * int_sqrt - computes the integer square root
diff --git a/lib/math/reciprocal_div.c b/lib/math/reciprocal_div.c
index 32436dd4171e..6cb4adbb81d2 100644
--- a/lib/math/reciprocal_div.c
+++ b/lib/math/reciprocal_div.c
@@ -1,10 +1,13 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/bitops.h>
 #include <linux/bug.h>
-#include <linux/kernel.h>
-#include <asm/div64.h>
-#include <linux/reciprocal_div.h>
 #include <linux/export.h>
+#include <linux/limits.h>
+#include <linux/math.h>
 #include <linux/minmax.h>
+#include <linux/types.h>
+
+#include <linux/reciprocal_div.h>
 
 /*
  * For a description of the algorithm please have a look at
-- 
cgit v1.2.3


From 0bb867795540a9223d44ddcdf478330cba5917f8 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 15 Dec 2020 20:42:55 -0800
Subject: include/linux/bitmap.h: convert bitmap_empty() / bitmap_full() to
 return boolean

There is no need to return int type out of boolean expression.

Link: https://lkml.kernel.org/r/20201027180936.20806-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Yury Norov <yury.norov@gmail.com>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/bitmap.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 99058eb81042..719fe036f567 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -379,7 +379,7 @@ static inline int bitmap_subset(const unsigned long *src1,
 		return __bitmap_subset(src1, src2, nbits);
 }
 
-static inline int bitmap_empty(const unsigned long *src, unsigned nbits)
+static inline bool bitmap_empty(const unsigned long *src, unsigned nbits)
 {
 	if (small_const_nbits(nbits))
 		return ! (*src & BITMAP_LAST_WORD_MASK(nbits));
@@ -387,7 +387,7 @@ static inline int bitmap_empty(const unsigned long *src, unsigned nbits)
 	return find_first_bit(src, nbits) == nbits;
 }
 
-static inline int bitmap_full(const unsigned long *src, unsigned int nbits)
+static inline bool bitmap_full(const unsigned long *src, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return ! (~(*src) & BITMAP_LAST_WORD_MASK(nbits));
-- 
cgit v1.2.3


From ab7d7798dad5aae23bb502f1a6fc0d637b07dc47 Mon Sep 17 00:00:00 2001
From: "Ma, Jianpeng" <jianpeng.ma@intel.com>
Date: Tue, 15 Dec 2020 20:42:57 -0800
Subject: bitmap: remove unused function declaration

Link: https://lkml.kernel.org/r/BN7PR11MB26097166B6B46387D8A1ABA4FDE30@BN7PR11MB2609.namprd11.prod.outlook.com
Fixes: 2afe27c718b6 ("lib/bitmap.c: bitmap_[empty,full]: remove code duplication")
Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
Acked-by: Yury Norov <yury.norov@gmail.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/bitmap.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 719fe036f567..70a932470b2d 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -126,8 +126,6 @@ extern void bitmap_free(const unsigned long *bitmap);
  * lib/bitmap.c provides these functions:
  */
 
-extern int __bitmap_empty(const unsigned long *bitmap, unsigned int nbits);
-extern int __bitmap_full(const unsigned long *bitmap, unsigned int nbits);
 extern int __bitmap_equal(const unsigned long *bitmap1,
 			  const unsigned long *bitmap2, unsigned int nbits);
 extern bool __pure __bitmap_or_equal(const unsigned long *src1,
-- 
cgit v1.2.3


From 2f78788b55baa3410b1ec91a576286abe1ad4d6a Mon Sep 17 00:00:00 2001
From: Jakub Jelinek <jakub@redhat.com>
Date: Tue, 15 Dec 2020 20:43:37 -0800
Subject: ilog2: improve ilog2 for constant arguments

As discussed in https://gcc.gnu.org/bugzilla/show_bug.cgi?id=97445 the
const_ilog2 macro generates a lot of code which interferes badly with GCC
inlining heuristics, until it can be proven that the ilog2 argument can or
can't be simplified into a constant.

It can be expressed using __builtin_clzll builtin which is supported by
GCC 3.4 and later and when used only in the __builtin_constant_p guarded
code it ought to always fold back to a constant.  Other compilers support
the same builtin for many years too.

Other option would be to change the const_ilog2 macro, though as the
description says it is meant to be used also in C constant expressions,
and while GCC will fold it to constant with constant argument even in
those, perhaps it is better to avoid using extensions in that case.

[akpm@linux-foundation.org: coding style fixes]

Link: https://lkml.kernel.org/r/20201120125154.GB3040@hirez.programming.kicks-ass.net
Link: https://lkml.kernel.org/r/20201021132718.GB2176@tucnak
Signed-off-by: Jakub Jelinek <jakub@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/log2.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/log2.h b/include/linux/log2.h
index c619ec6eff4a..df0b155c2141 100644
--- a/include/linux/log2.h
+++ b/include/linux/log2.h
@@ -156,7 +156,8 @@ unsigned long __rounddown_pow_of_two(unsigned long n)
 #define ilog2(n) \
 ( \
 	__builtin_constant_p(n) ?	\
-	const_ilog2(n) :		\
+	((n) < 2 ? 0 :			\
+	 63 - __builtin_clzll(n)) :	\
 	(sizeof(n) <= 4) ?		\
 	__ilog2_u32(n) :		\
 	__ilog2_u64(n)			\
-- 
cgit v1.2.3


From 6a39e62abbafd1d58d1722f40c7d26ef379c6a2f Mon Sep 17 00:00:00 2001
From: Daniel Axtens <dja@axtens.net>
Date: Tue, 15 Dec 2020 20:43:44 -0800
Subject: lib: string.h: detect intra-object overflow in fortified string
 functions

Patch series "Fortify strscpy()", v7.

This patch implements a fortified version of strscpy() enabled by setting
CONFIG_FORTIFY_SOURCE=y.  The new version ensures the following before
calling vanilla strscpy():

1. There is no read overflow because either size is smaller than src
   length or we shrink size to src length by calling fortified strnlen().

2. There is no write overflow because we either failed during
   compilation or at runtime by checking that size is smaller than dest
   size.  Note that, if src and dst size cannot be got, the patch defaults
   to call vanilla strscpy().

The patches adds the following:

1. Implement the fortified version of strscpy().

2. Add a new LKDTM test to ensures the fortified version still returns
   the same value as the vanilla one while panic'ing when there is a write
   overflow.

3. Correct some typos in LKDTM related file.

I based my modifications on top of two patches from Daniel Axtens which
modify calls to __builtin_object_size, in fortified string functions, to
ensure the true size of char * are returned and not the surrounding
structure size.

About performance, I measured the slow down of fortified strscpy(), using
the vanilla one as baseline.  The hardware I used is an Intel i3 2130 CPU
clocked at 3.4 GHz.  I ran "Linux 5.10.0-rc4+ SMP PREEMPT" inside qemu
3.10 with 4 CPU cores.  The following code, called through LKDTM, was used
as a benchmark:

#define TIMES 10000
	char *src;
	char dst[7];
	int i;
	ktime_t begin;

	src = kstrdup("foobar", GFP_KERNEL);

	if (src == NULL)
		return;

	begin = ktime_get();
	for (i = 0; i < TIMES; i++)
		strscpy(dst, src, strlen(src));
	pr_info("%d fortified strscpy() tooks %lld", TIMES, ktime_get() - begin);

	begin = ktime_get();
	for (i = 0; i < TIMES; i++)
		__real_strscpy(dst, src, strlen(src));
	pr_info("%d vanilla strscpy() tooks %lld", TIMES, ktime_get() - begin);

	kfree(src);

I called the above code 30 times to compute stats for each version (in ns,
round to int):

| version   | mean    | std    | median  | 95th    |
| --------- | ------- | ------ | ------- | ------- |
| fortified | 245_069 | 54_657 | 216_230 | 331_122 |
| vanilla   | 172_501 | 70_281 | 143_539 | 219_553 |

On average, fortified strscpy() is approximately 1.42 times slower than
vanilla strscpy().  For the 95th percentile, the fortified version is
about 1.50 times slower.

So, clearly the stats are not in favor of fortified strscpy().  But, the
fortified version loops the string twice (one in strnlen() and another in
vanilla strscpy()) while the vanilla one only loops once.  This can
explain why fortified strscpy() is slower than the vanilla one.

This patch (of 5):

When the fortify feature was first introduced in commit 6974f0c4555e
("include/linux/string.h: add the option of fortified string.h
functions"), Daniel Micay observed:

  * It should be possible to optionally use __builtin_object_size(x, 1) for
    some functions (C strings) to detect intra-object overflows (like
    glibc's _FORTIFY_SOURCE=2), but for now this takes the conservative
    approach to avoid likely compatibility issues.

This is a case that often cannot be caught by KASAN. Consider:

struct foo {
    char a[10];
    char b[10];
}

void test() {
    char *msg;
    struct foo foo;

    msg = kmalloc(16, GFP_KERNEL);
    strcpy(msg, "Hello world!!");
    // this copy overwrites foo.b
    strcpy(foo.a, msg);
}

The questionable copy overflows foo.a and writes to foo.b as well.  It
cannot be detected by KASAN.  Currently it is also not detected by
fortify, because strcpy considers __builtin_object_size(x, 0), which
considers the size of the surrounding object (here, struct foo).  However,
if we switch the string functions over to use __builtin_object_size(x, 1),
the compiler will measure the size of the closest surrounding subobject
(here, foo.a), rather than the size of the surrounding object as a whole.
See https://gcc.gnu.org/onlinedocs/gcc/Object-Size-Checking.html for more
info.

Only do this for string functions: we cannot use it on things like memcpy,
memmove, memcmp and memchr_inv due to code like this which purposefully
operates on multiple structure members: (arch/x86/kernel/traps.c)

	/*
	 * regs->sp points to the failing IRET frame on the
	 * ESPFIX64 stack.  Copy it to the entry stack.  This fills
	 * in gpregs->ss through gpregs->ip.
	 *
	 */
	memmove(&gpregs->ip, (void *)regs->sp, 5*8);

This change passes an allyesconfig on powerpc and x86, and an x86 kernel
built with it survives running with syz-stress from syzkaller, so it seems
safe so far.

Link: https://lkml.kernel.org/r/20201122162451.27551-1-laniel_francis@privacyrequired.com
Link: https://lkml.kernel.org/r/20201122162451.27551-2-laniel_francis@privacyrequired.com
Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Francis Laniel <laniel_francis@privacyrequired.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Cc: Daniel Micay <danielmicay@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/string.h | 27 ++++++++++++++++-----------
 1 file changed, 16 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/string.h b/include/linux/string.h
index b1f3894a0a3e..46e91d684c47 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -292,7 +292,7 @@ extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size)
 
 __FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size)
 {
-	size_t p_size = __builtin_object_size(p, 0);
+	size_t p_size = __builtin_object_size(p, 1);
 	if (__builtin_constant_p(size) && p_size < size)
 		__write_overflow();
 	if (p_size < size)
@@ -302,7 +302,7 @@ __FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size)
 
 __FORTIFY_INLINE char *strcat(char *p, const char *q)
 {
-	size_t p_size = __builtin_object_size(p, 0);
+	size_t p_size = __builtin_object_size(p, 1);
 	if (p_size == (size_t)-1)
 		return __underlying_strcat(p, q);
 	if (strlcat(p, q, p_size) >= p_size)
@@ -313,7 +313,7 @@ __FORTIFY_INLINE char *strcat(char *p, const char *q)
 __FORTIFY_INLINE __kernel_size_t strlen(const char *p)
 {
 	__kernel_size_t ret;
-	size_t p_size = __builtin_object_size(p, 0);
+	size_t p_size = __builtin_object_size(p, 1);
 
 	/* Work around gcc excess stack consumption issue */
 	if (p_size == (size_t)-1 ||
@@ -328,7 +328,7 @@ __FORTIFY_INLINE __kernel_size_t strlen(const char *p)
 extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(strnlen);
 __FORTIFY_INLINE __kernel_size_t strnlen(const char *p, __kernel_size_t maxlen)
 {
-	size_t p_size = __builtin_object_size(p, 0);
+	size_t p_size = __builtin_object_size(p, 1);
 	__kernel_size_t ret = __real_strnlen(p, maxlen < p_size ? maxlen : p_size);
 	if (p_size <= ret && maxlen != ret)
 		fortify_panic(__func__);
@@ -340,8 +340,8 @@ extern size_t __real_strlcpy(char *, const char *, size_t) __RENAME(strlcpy);
 __FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size)
 {
 	size_t ret;
-	size_t p_size = __builtin_object_size(p, 0);
-	size_t q_size = __builtin_object_size(q, 0);
+	size_t p_size = __builtin_object_size(p, 1);
+	size_t q_size = __builtin_object_size(q, 1);
 	if (p_size == (size_t)-1 && q_size == (size_t)-1)
 		return __real_strlcpy(p, q, size);
 	ret = strlen(q);
@@ -361,8 +361,8 @@ __FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size)
 __FORTIFY_INLINE char *strncat(char *p, const char *q, __kernel_size_t count)
 {
 	size_t p_len, copy_len;
-	size_t p_size = __builtin_object_size(p, 0);
-	size_t q_size = __builtin_object_size(q, 0);
+	size_t p_size = __builtin_object_size(p, 1);
+	size_t q_size = __builtin_object_size(q, 1);
 	if (p_size == (size_t)-1 && q_size == (size_t)-1)
 		return __underlying_strncat(p, q, count);
 	p_len = strlen(p);
@@ -475,11 +475,16 @@ __FORTIFY_INLINE void *kmemdup(const void *p, size_t size, gfp_t gfp)
 /* defined after fortified strlen and memcpy to reuse them */
 __FORTIFY_INLINE char *strcpy(char *p, const char *q)
 {
-	size_t p_size = __builtin_object_size(p, 0);
-	size_t q_size = __builtin_object_size(q, 0);
+	size_t p_size = __builtin_object_size(p, 1);
+	size_t q_size = __builtin_object_size(q, 1);
+	size_t size;
 	if (p_size == (size_t)-1 && q_size == (size_t)-1)
 		return __underlying_strcpy(p, q);
-	memcpy(p, q, strlen(q) + 1);
+	size = strlen(q) + 1;
+	/* test here to use the more stringent object size */
+	if (p_size < size)
+		fortify_panic(__func__);
+	memcpy(p, q, size);
 	return p;
 }
 
-- 
cgit v1.2.3


From 33e56a59e64dfb68778e5da0be13f0c47dc5d445 Mon Sep 17 00:00:00 2001
From: Francis Laniel <laniel_francis@privacyrequired.com>
Date: Tue, 15 Dec 2020 20:43:50 -0800
Subject: string.h: add FORTIFY coverage for strscpy()

The fortified version of strscpy ensures the following before vanilla strscpy
is called:

1. There is no read overflow because we either size is smaller than
   src length or we shrink size to src length by calling fortified
   strnlen.

2. There is no write overflow because we either failed during
   compilation or at runtime by checking that size is smaller than dest
   size.

Link: https://lkml.kernel.org/r/20201122162451.27551-4-laniel_francis@privacyrequired.com
Signed-off-by: Francis Laniel <laniel_francis@privacyrequired.com>
Acked-by: Kees Cook <keescook@chromium.org>
Cc: Daniel Axtens <dja@axtens.net>
Cc: Daniel Micay <danielmicay@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/string.h | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/string.h b/include/linux/string.h
index 46e91d684c47..1cd63a8a23ab 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -6,6 +6,7 @@
 #include <linux/compiler.h>	/* for inline */
 #include <linux/types.h>	/* for size_t */
 #include <linux/stddef.h>	/* for NULL */
+#include <linux/errno.h>	/* for E2BIG */
 #include <stdarg.h>
 #include <uapi/linux/string.h>
 
@@ -357,6 +358,53 @@ __FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size)
 	return ret;
 }
 
+/* defined after fortified strnlen to reuse it */
+extern ssize_t __real_strscpy(char *, const char *, size_t) __RENAME(strscpy);
+__FORTIFY_INLINE ssize_t strscpy(char *p, const char *q, size_t size)
+{
+	size_t len;
+	/* Use string size rather than possible enclosing struct size. */
+	size_t p_size = __builtin_object_size(p, 1);
+	size_t q_size = __builtin_object_size(q, 1);
+
+	/* If we cannot get size of p and q default to call strscpy. */
+	if (p_size == (size_t) -1 && q_size == (size_t) -1)
+		return __real_strscpy(p, q, size);
+
+	/*
+	 * If size can be known at compile time and is greater than
+	 * p_size, generate a compile time write overflow error.
+	 */
+	if (__builtin_constant_p(size) && size > p_size)
+		__write_overflow();
+
+	/*
+	 * This call protects from read overflow, because len will default to q
+	 * length if it smaller than size.
+	 */
+	len = strnlen(q, size);
+	/*
+	 * If len equals size, we will copy only size bytes which leads to
+	 * -E2BIG being returned.
+	 * Otherwise we will copy len + 1 because of the final '\O'.
+	 */
+	len = len == size ? size : len + 1;
+
+	/*
+	 * Generate a runtime write overflow error if len is greater than
+	 * p_size.
+	 */
+	if (len > p_size)
+		fortify_panic(__func__);
+
+	/*
+	 * We can now safely call vanilla strscpy because we are protected from:
+	 * 1. Read overflow thanks to call to strnlen().
+	 * 2. Write overflow thanks to above ifs.
+	 */
+	return __real_strscpy(p, q, len);
+}
+
 /* defined after fortified strlen and strnlen to reuse them */
 __FORTIFY_INLINE char *strncat(char *p, const char *q, __kernel_size_t count)
 {
-- 
cgit v1.2.3


From 5c7b3280d221b84a675b85cb2727df7d82b65c3a Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Tue, 15 Dec 2020 20:45:34 -0800
Subject: rapidio: remove unused rio_get_asm() and rio_get_device()

The functions rio_get_asm() and rio_get_device() are globally exported
but have almost no users in tree. The only user is rio_init_mports()
which invokes it via rio_init().

rio_init() iterates over every registered device and invokes
rio_fixup_device().  It looks like a fixup function which should perform a
"change" to the device but does nothing.  It has been like this since its
introduction in commit 394b701ce4fbf ("[PATCH] RapidIO support: core
base") which was merged into v2.6.15-rc1.

Remove rio_init() because the performed fixup function
(rio_fixup_device()) does nothing.  Remove rio_get_asm() and
rio_get_device() which have no callers now.

Link: https://lkml.kernel.org/r/20201116170004.420143-1-bigeasy@linutronix.de
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Matt Porter <mporter@kernel.crashing.org>
Cc: Alexandre Bounine <alex.bou9@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/rapidio/rio.c   | 81 -------------------------------------------------
 include/linux/rio_drv.h |  3 --
 2 files changed, 84 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/rapidio/rio.c b/drivers/rapidio/rio.c
index 606986c5ba2c..c2b79736a92b 100644
--- a/drivers/rapidio/rio.c
+++ b/drivers/rapidio/rio.c
@@ -1412,71 +1412,6 @@ rio_mport_get_feature(struct rio_mport * port, int local, u16 destid,
 }
 EXPORT_SYMBOL_GPL(rio_mport_get_feature);
 
-/**
- * rio_get_asm - Begin or continue searching for a RIO device by vid/did/asm_vid/asm_did
- * @vid: RIO vid to match or %RIO_ANY_ID to match all vids
- * @did: RIO did to match or %RIO_ANY_ID to match all dids
- * @asm_vid: RIO asm_vid to match or %RIO_ANY_ID to match all asm_vids
- * @asm_did: RIO asm_did to match or %RIO_ANY_ID to match all asm_dids
- * @from: Previous RIO device found in search, or %NULL for new search
- *
- * Iterates through the list of known RIO devices. If a RIO device is
- * found with a matching @vid, @did, @asm_vid, @asm_did, the reference
- * count to the device is incrememted and a pointer to its device
- * structure is returned. Otherwise, %NULL is returned. A new search
- * is initiated by passing %NULL to the @from argument. Otherwise, if
- * @from is not %NULL, searches continue from next device on the global
- * list. The reference count for @from is always decremented if it is
- * not %NULL.
- */
-struct rio_dev *rio_get_asm(u16 vid, u16 did,
-			    u16 asm_vid, u16 asm_did, struct rio_dev *from)
-{
-	struct list_head *n;
-	struct rio_dev *rdev;
-
-	WARN_ON(in_interrupt());
-	spin_lock(&rio_global_list_lock);
-	n = from ? from->global_list.next : rio_devices.next;
-
-	while (n && (n != &rio_devices)) {
-		rdev = rio_dev_g(n);
-		if ((vid == RIO_ANY_ID || rdev->vid == vid) &&
-		    (did == RIO_ANY_ID || rdev->did == did) &&
-		    (asm_vid == RIO_ANY_ID || rdev->asm_vid == asm_vid) &&
-		    (asm_did == RIO_ANY_ID || rdev->asm_did == asm_did))
-			goto exit;
-		n = n->next;
-	}
-	rdev = NULL;
-      exit:
-	rio_dev_put(from);
-	rdev = rio_dev_get(rdev);
-	spin_unlock(&rio_global_list_lock);
-	return rdev;
-}
-EXPORT_SYMBOL_GPL(rio_get_asm);
-
-/**
- * rio_get_device - Begin or continue searching for a RIO device by vid/did
- * @vid: RIO vid to match or %RIO_ANY_ID to match all vids
- * @did: RIO did to match or %RIO_ANY_ID to match all dids
- * @from: Previous RIO device found in search, or %NULL for new search
- *
- * Iterates through the list of known RIO devices. If a RIO device is
- * found with a matching @vid and @did, the reference count to the
- * device is incrememted and a pointer to its device structure is returned.
- * Otherwise, %NULL is returned. A new search is initiated by passing %NULL
- * to the @from argument. Otherwise, if @from is not %NULL, searches
- * continue from next device on the global list. The reference count for
- * @from is always decremented if it is not %NULL.
- */
-struct rio_dev *rio_get_device(u16 vid, u16 did, struct rio_dev *from)
-{
-	return rio_get_asm(vid, did, RIO_ANY_ID, RIO_ANY_ID, from);
-}
-EXPORT_SYMBOL_GPL(rio_get_device);
-
 /**
  * rio_std_route_add_entry - Add switch route table entry using standard
  *   registers defined in RIO specification rev.1.3
@@ -2106,20 +2041,6 @@ found:
 	return rc;
 }
 
-static void rio_fixup_device(struct rio_dev *dev)
-{
-}
-
-static int rio_init(void)
-{
-	struct rio_dev *dev = NULL;
-
-	while ((dev = rio_get_device(RIO_ANY_ID, RIO_ANY_ID, dev)) != NULL) {
-		rio_fixup_device(dev);
-	}
-	return 0;
-}
-
 static struct workqueue_struct *rio_wq;
 
 struct rio_disc_work {
@@ -2206,8 +2127,6 @@ int rio_init_mports(void)
 	kfree(work);
 
 no_disc:
-	rio_init();
-
 	return 0;
 }
 EXPORT_SYMBOL_GPL(rio_init_mports);
diff --git a/include/linux/rio_drv.h b/include/linux/rio_drv.h
index d637742e5039..e49c32b0f394 100644
--- a/include/linux/rio_drv.h
+++ b/include/linux/rio_drv.h
@@ -444,9 +444,6 @@ static inline void rio_set_drvdata(struct rio_dev *rdev, void *data)
 /* Misc driver helpers */
 extern u16 rio_local_get_device_id(struct rio_mport *port);
 extern void rio_local_set_device_id(struct rio_mport *port, u16 did);
-extern struct rio_dev *rio_get_device(u16 vid, u16 did, struct rio_dev *from);
-extern struct rio_dev *rio_get_asm(u16 vid, u16 did, u16 asm_vid, u16 asm_did,
-				   struct rio_dev *from);
 extern int rio_init_mports(void);
 
 #endif				/* LINUX_RIO_DRV_H */
-- 
cgit v1.2.3


From 3d03295a7e9194c2318977b44999972ce3609664 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Tue, 15 Dec 2020 20:45:47 -0800
Subject: relay: remove unused buf_mapped and buf_unmapped callbacks

Patch series "relay: cleanup and const callbacks", v2.

None of the relay users require the use of mutable structs for callbacks,
however the relay code does.  Instead of assigning default callbacks when
there is none, add callback wrappers to conditionally call the client
callbacks if available, and fall back to default behaviour (typically
no-op) otherwise.

This lets all relay users make their struct rchan_callbacks const data.

This series starts with a number of cleanups first based on Christoph's
feedback.

This patch (of 9):

No relay client uses the buf_mapped or buf_unmapped callbacks.  Remove
them.  This makes relay's vm_operations_struct close callback a dummy,
remove it as well.

Link: https://lkml.kernel.org/r/cover.1606153547.git.jani.nikula@intel.com
Link: https://lkml.kernel.org/r/c69fff6e0cd485563604240bbfcc028434983bec.1606153547.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Suggested-by: Christoph Hellwig <hch@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Kalle Valo <kvalo@codeaurora.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/relay.h | 19 -------------------
 kernel/relay.c        | 34 ----------------------------------
 2 files changed, 53 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/relay.h b/include/linux/relay.h
index e13a333e7c37..b3c4f49f6951 100644
--- a/include/linux/relay.h
+++ b/include/linux/relay.h
@@ -101,25 +101,6 @@ struct rchan_callbacks
 			     void *prev_subbuf,
 			     size_t prev_padding);
 
-	/*
-	 * buf_mapped - relay buffer mmap notification
-	 * @buf: the channel buffer
-	 * @filp: relay file pointer
-	 *
-	 * Called when a relay file is successfully mmapped
-	 */
-        void (*buf_mapped)(struct rchan_buf *buf,
-			   struct file *filp);
-
-	/*
-	 * buf_unmapped - relay buffer unmap notification
-	 * @buf: the channel buffer
-	 * @filp: relay file pointer
-	 *
-	 * Called when a relay file is successfully unmapped
-	 */
-        void (*buf_unmapped)(struct rchan_buf *buf,
-			     struct file *filp);
 	/*
 	 * create_buf_file - create file to represent a relay channel buffer
 	 * @filename: the name of the file to create
diff --git a/kernel/relay.c b/kernel/relay.c
index b08d936d5fa7..b51343642bf4 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -27,15 +27,6 @@
 static DEFINE_MUTEX(relay_channels_mutex);
 static LIST_HEAD(relay_channels);
 
-/*
- * close() vm_op implementation for relay file mapping.
- */
-static void relay_file_mmap_close(struct vm_area_struct *vma)
-{
-	struct rchan_buf *buf = vma->vm_private_data;
-	buf->chan->cb->buf_unmapped(buf, vma->vm_file);
-}
-
 /*
  * fault() vm_op implementation for relay file mapping.
  */
@@ -62,7 +53,6 @@ static vm_fault_t relay_buf_fault(struct vm_fault *vmf)
  */
 static const struct vm_operations_struct relay_file_mmap_ops = {
 	.fault = relay_buf_fault,
-	.close = relay_file_mmap_close,
 };
 
 /*
@@ -96,7 +86,6 @@ static void relay_free_page_array(struct page **array)
 static int relay_mmap_buf(struct rchan_buf *buf, struct vm_area_struct *vma)
 {
 	unsigned long length = vma->vm_end - vma->vm_start;
-	struct file *filp = vma->vm_file;
 
 	if (!buf)
 		return -EBADF;
@@ -107,7 +96,6 @@ static int relay_mmap_buf(struct rchan_buf *buf, struct vm_area_struct *vma)
 	vma->vm_ops = &relay_file_mmap_ops;
 	vma->vm_flags |= VM_DONTEXPAND;
 	vma->vm_private_data = buf;
-	buf->chan->cb->buf_mapped(buf, filp);
 
 	return 0;
 }
@@ -283,22 +271,6 @@ static int subbuf_start_default_callback (struct rchan_buf *buf,
 	return 1;
 }
 
-/*
- * buf_mapped() default callback.  Does nothing.
- */
-static void buf_mapped_default_callback(struct rchan_buf *buf,
-					struct file *filp)
-{
-}
-
-/*
- * buf_unmapped() default callback.  Does nothing.
- */
-static void buf_unmapped_default_callback(struct rchan_buf *buf,
-					  struct file *filp)
-{
-}
-
 /*
  * create_buf_file_create() default callback.  Does nothing.
  */
@@ -322,8 +294,6 @@ static int remove_buf_file_default_callback(struct dentry *dentry)
 /* relay channel default callbacks */
 static struct rchan_callbacks default_channel_callbacks = {
 	.subbuf_start = subbuf_start_default_callback,
-	.buf_mapped = buf_mapped_default_callback,
-	.buf_unmapped = buf_unmapped_default_callback,
 	.create_buf_file = create_buf_file_default_callback,
 	.remove_buf_file = remove_buf_file_default_callback,
 };
@@ -509,10 +479,6 @@ static void setup_callbacks(struct rchan *chan,
 
 	if (!cb->subbuf_start)
 		cb->subbuf_start = subbuf_start_default_callback;
-	if (!cb->buf_mapped)
-		cb->buf_mapped = buf_mapped_default_callback;
-	if (!cb->buf_unmapped)
-		cb->buf_unmapped = buf_unmapped_default_callback;
 	if (!cb->create_buf_file)
 		cb->create_buf_file = create_buf_file_default_callback;
 	if (!cb->remove_buf_file)
-- 
cgit v1.2.3


From 371e03880d9d34534d3eafd2a7581042be598e39 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Tue, 15 Dec 2020 20:45:53 -0800
Subject: relay: make create_buf_file and remove_buf_file callbacks mandatory

All clients provide create_buf_file and remove_buf_file callbacks, and
they're required for relay to make sense.  There is no point in them being
optional.

Also document whether each callback is mandatory/optional.

Link: https://lkml.kernel.org/r/88003c1527386b93036e286e7917f1e33aec84ac.1606153547.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Suggested-by: Christoph Hellwig <hch@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Kalle Valo <kvalo@codeaurora.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/relay.h |  6 ++++++
 kernel/relay.c        | 26 +-------------------------
 2 files changed, 7 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/relay.h b/include/linux/relay.h
index b3c4f49f6951..99d024475ba5 100644
--- a/include/linux/relay.h
+++ b/include/linux/relay.h
@@ -89,6 +89,8 @@ struct rchan_callbacks
 	 * The client should return 1 to continue logging, 0 to stop
 	 * logging.
 	 *
+	 * This callback is optional.
+	 *
 	 * NOTE: subbuf_start will also be invoked when the buffer is
 	 *       created, so that the first sub-buffer can be initialized
 	 *       if necessary.  In this case, prev_subbuf will be NULL.
@@ -122,6 +124,8 @@ struct rchan_callbacks
 	 * cause relay_open() to create a single global buffer rather
 	 * than the default set of per-cpu buffers.
 	 *
+	 * This callback is mandatory.
+	 *
 	 * See Documentation/filesystems/relay.rst for more info.
 	 */
 	struct dentry *(*create_buf_file)(const char *filename,
@@ -139,6 +143,8 @@ struct rchan_callbacks
 	 * channel buffer.
 	 *
 	 * The callback should return 0 if successful, negative if not.
+	 *
+	 * This callback is mandatory.
 	 */
 	int (*remove_buf_file)(struct dentry *dentry);
 };
diff --git a/kernel/relay.c b/kernel/relay.c
index d9b8185161a8..dd4ec4ec07f3 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -271,26 +271,6 @@ static int subbuf_start_default_callback (struct rchan_buf *buf,
 	return 1;
 }
 
-/*
- * create_buf_file_create() default callback.  Does nothing.
- */
-static struct dentry *create_buf_file_default_callback(const char *filename,
-						       struct dentry *parent,
-						       umode_t mode,
-						       struct rchan_buf *buf,
-						       int *is_global)
-{
-	return NULL;
-}
-
-/*
- * remove_buf_file() default callback.  Does nothing.
- */
-static int remove_buf_file_default_callback(struct dentry *dentry)
-{
-	return -EINVAL;
-}
-
 /**
  *	wakeup_readers - wake up readers waiting on a channel
  *	@work: contains the channel buffer
@@ -467,10 +447,6 @@ static void setup_callbacks(struct rchan *chan,
 {
 	if (!cb->subbuf_start)
 		cb->subbuf_start = subbuf_start_default_callback;
-	if (!cb->create_buf_file)
-		cb->create_buf_file = create_buf_file_default_callback;
-	if (!cb->remove_buf_file)
-		cb->remove_buf_file = remove_buf_file_default_callback;
 	chan->cb = cb;
 }
 
@@ -530,7 +506,7 @@ struct rchan *relay_open(const char *base_filename,
 		return NULL;
 	if (subbuf_size > UINT_MAX / n_subbufs)
 		return NULL;
-	if (!cb)
+	if (!cb || !cb->create_buf_file || !cb->remove_buf_file)
 		return NULL;
 
 	chan = kzalloc(sizeof(struct rchan), GFP_KERNEL);
-- 
cgit v1.2.3


From 023542f48b57d6b785fcadb86ac336ae80653e58 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Tue, 15 Dec 2020 20:45:57 -0800
Subject: relay: allow the use of const callback structs

None of the relay users require the use of mutable structs for callbacks,
however the relay code does.  Instead of assigning the default callback
for subbuf_start, add a wrapper to conditionally call the client callback
if available, and fall back to default behaviour otherwise.

This lets all relay users make their struct rchan_callbacks const data.

[jani.nikula@intel.com: cleanups, per Christoph]
  Link: https://lkml.kernel.org/r/20201124115412.32402-1-jani.nikula@intel.com

Link: https://lkml.kernel.org/r/cc3ff292e4eb4fdc56bee3d690c7b8e39209cd37.1606153547.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Kalle Valo <kvalo@codeaurora.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/relay.h |  4 ++--
 kernel/relay.c        | 37 ++++++++++---------------------------
 2 files changed, 12 insertions(+), 29 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/relay.h b/include/linux/relay.h
index 99d024475ba5..72b876dd5cb8 100644
--- a/include/linux/relay.h
+++ b/include/linux/relay.h
@@ -62,7 +62,7 @@ struct rchan
 	size_t subbuf_size;		/* sub-buffer size */
 	size_t n_subbufs;		/* number of sub-buffers per buffer */
 	size_t alloc_size;		/* total buffer size allocated */
-	struct rchan_callbacks *cb;	/* client callbacks */
+	const struct rchan_callbacks *cb; /* client callbacks */
 	struct kref kref;		/* channel refcount */
 	void *private_data;		/* for user-defined data */
 	size_t last_toobig;		/* tried to log event > subbuf size */
@@ -157,7 +157,7 @@ struct rchan *relay_open(const char *base_filename,
 			 struct dentry *parent,
 			 size_t subbuf_size,
 			 size_t n_subbufs,
-			 struct rchan_callbacks *cb,
+			 const struct rchan_callbacks *cb,
 			 void *private_data);
 extern int relay_late_setup_files(struct rchan *chan,
 				  const char *base_filename,
diff --git a/kernel/relay.c b/kernel/relay.c
index dd4ec4ec07f3..d1a67fbb819d 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -252,23 +252,14 @@ EXPORT_SYMBOL_GPL(relay_buf_full);
  * High-level relay kernel API and associated functions.
  */
 
-/*
- * rchan_callback implementations defining default channel behavior.  Used
- * in place of corresponding NULL values in client callback struct.
- */
-
-/*
- * subbuf_start() default callback.  Does nothing.
- */
-static int subbuf_start_default_callback (struct rchan_buf *buf,
-					  void *subbuf,
-					  void *prev_subbuf,
-					  size_t prev_padding)
+static int relay_subbuf_start(struct rchan_buf *buf, void *subbuf,
+			      void *prev_subbuf, size_t prev_padding)
 {
-	if (relay_buf_full(buf))
-		return 0;
+	if (!buf->chan->cb->subbuf_start)
+		return !relay_buf_full(buf);
 
-	return 1;
+	return buf->chan->cb->subbuf_start(buf, subbuf,
+					   prev_subbuf, prev_padding);
 }
 
 /**
@@ -314,7 +305,7 @@ static void __relay_reset(struct rchan_buf *buf, unsigned int init)
 	for (i = 0; i < buf->chan->n_subbufs; i++)
 		buf->padding[i] = 0;
 
-	buf->chan->cb->subbuf_start(buf, buf->data, NULL, 0);
+	relay_subbuf_start(buf, buf->data, NULL, 0);
 }
 
 /**
@@ -442,14 +433,6 @@ static void relay_close_buf(struct rchan_buf *buf)
 	kref_put(&buf->kref, relay_remove_buf);
 }
 
-static void setup_callbacks(struct rchan *chan,
-				   struct rchan_callbacks *cb)
-{
-	if (!cb->subbuf_start)
-		cb->subbuf_start = subbuf_start_default_callback;
-	chan->cb = cb;
-}
-
 int relay_prepare_cpu(unsigned int cpu)
 {
 	struct rchan *chan;
@@ -495,7 +478,7 @@ struct rchan *relay_open(const char *base_filename,
 			 struct dentry *parent,
 			 size_t subbuf_size,
 			 size_t n_subbufs,
-			 struct rchan_callbacks *cb,
+			 const struct rchan_callbacks *cb,
 			 void *private_data)
 {
 	unsigned int i;
@@ -529,7 +512,7 @@ struct rchan *relay_open(const char *base_filename,
 		chan->has_base_filename = 1;
 		strlcpy(chan->base_filename, base_filename, NAME_MAX);
 	}
-	setup_callbacks(chan, cb);
+	chan->cb = cb;
 	kref_init(&chan->kref);
 
 	mutex_lock(&relay_channels_mutex);
@@ -712,7 +695,7 @@ size_t relay_switch_subbuf(struct rchan_buf *buf, size_t length)
 	new_subbuf = buf->subbufs_produced % buf->chan->n_subbufs;
 	new = buf->start + new_subbuf * buf->chan->subbuf_size;
 	buf->offset = 0;
-	if (!buf->chan->cb->subbuf_start(buf, new, old, buf->prev_padding)) {
+	if (!relay_subbuf_start(buf, new, old, buf->prev_padding)) {
 		buf->offset = buf->chan->subbuf_size + 1;
 		return 0;
 	}
-- 
cgit v1.2.3


From ff5c19ed4b087073cea38ff0edc80c23d7256943 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 15 Dec 2020 20:47:23 -0800
Subject: mm: simplify follow_pte{,pmd}

Merge __follow_pte_pmd, follow_pte_pmd and follow_pte into a single
follow_pte function and just pass two additional NULL arguments for the
two previous follow_pte callers.

[sfr@canb.auug.org.au: merge fix for "s390/pci: remove races against pte updates"]
  Link: https://lkml.kernel.org/r/20201111221254.7f6a3658@canb.auug.org.au

Link: https://lkml.kernel.org/r/20201029101432.47011-3-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/s390/pci/pci_mmio.c |  4 ++--
 fs/dax.c                 |  9 ++++-----
 include/linux/mm.h       |  6 +++---
 mm/memory.c              | 35 +++++------------------------------
 4 files changed, 14 insertions(+), 40 deletions(-)

(limited to 'include/linux')

diff --git a/arch/s390/pci/pci_mmio.c b/arch/s390/pci/pci_mmio.c
index de3bdbed8881..18f2d10c3176 100644
--- a/arch/s390/pci/pci_mmio.c
+++ b/arch/s390/pci/pci_mmio.c
@@ -170,7 +170,7 @@ SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr,
 	if (!(vma->vm_flags & VM_WRITE))
 		goto out_unlock_mmap;
 
-	ret = follow_pte_pmd(vma->vm_mm, mmio_addr, NULL, &ptep, NULL, &ptl);
+	ret = follow_pte(vma->vm_mm, mmio_addr, NULL, &ptep, NULL, &ptl);
 	if (ret)
 		goto out_unlock_mmap;
 
@@ -311,7 +311,7 @@ SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr,
 	if (!(vma->vm_flags & VM_WRITE))
 		goto out_unlock_mmap;
 
-	ret = follow_pte_pmd(vma->vm_mm, mmio_addr, NULL, &ptep, NULL, &ptl);
+	ret = follow_pte(vma->vm_mm, mmio_addr, NULL, &ptep, NULL, &ptl);
 	if (ret)
 		goto out_unlock_mmap;
 
diff --git a/fs/dax.c b/fs/dax.c
index 5b47834f2e1b..26d5dcd2d69e 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -810,12 +810,11 @@ static void dax_entry_mkclean(struct address_space *mapping, pgoff_t index,
 		address = pgoff_address(index, vma);
 
 		/*
-		 * Note because we provide range to follow_pte_pmd it will
-		 * call mmu_notifier_invalidate_range_start() on our behalf
-		 * before taking any lock.
+		 * Note because we provide range to follow_pte it will call
+		 * mmu_notifier_invalidate_range_start() on our behalf before
+		 * taking any lock.
 		 */
-		if (follow_pte_pmd(vma->vm_mm, address, &range,
-				   &ptep, &pmdp, &ptl))
+		if (follow_pte(vma->vm_mm, address, &range, &ptep, &pmdp, &ptl))
 			continue;
 
 		/*
diff --git a/include/linux/mm.h b/include/linux/mm.h
index abc7b3154298..855161080f18 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1641,9 +1641,9 @@ void free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
 		unsigned long end, unsigned long floor, unsigned long ceiling);
 int
 copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma);
-int follow_pte_pmd(struct mm_struct *mm, unsigned long address,
-		   struct mmu_notifier_range *range,
-		   pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp);
+int follow_pte(struct mm_struct *mm, unsigned long address,
+		struct mmu_notifier_range *range, pte_t **ptepp, pmd_t **pmdpp,
+		spinlock_t **ptlp);
 int follow_pfn(struct vm_area_struct *vma, unsigned long address,
 	unsigned long *pfn);
 int follow_phys(struct vm_area_struct *vma, unsigned long address,
diff --git a/mm/memory.c b/mm/memory.c
index 126e140baf73..7d608765932b 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4707,9 +4707,9 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
 }
 #endif /* __PAGETABLE_PMD_FOLDED */
 
-static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address,
-			    struct mmu_notifier_range *range,
-			    pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp)
+int follow_pte(struct mm_struct *mm, unsigned long address,
+	       struct mmu_notifier_range *range, pte_t **ptepp, pmd_t **pmdpp,
+	       spinlock_t **ptlp)
 {
 	pgd_t *pgd;
 	p4d_t *p4d;
@@ -4774,31 +4774,6 @@ out:
 	return -EINVAL;
 }
 
-static inline int follow_pte(struct mm_struct *mm, unsigned long address,
-			     pte_t **ptepp, spinlock_t **ptlp)
-{
-	int res;
-
-	/* (void) is needed to make gcc happy */
-	(void) __cond_lock(*ptlp,
-			   !(res = __follow_pte_pmd(mm, address, NULL,
-						    ptepp, NULL, ptlp)));
-	return res;
-}
-
-int follow_pte_pmd(struct mm_struct *mm, unsigned long address,
-		   struct mmu_notifier_range *range,
-		   pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp)
-{
-	int res;
-
-	/* (void) is needed to make gcc happy */
-	(void) __cond_lock(*ptlp,
-			   !(res = __follow_pte_pmd(mm, address, range,
-						    ptepp, pmdpp, ptlp)));
-	return res;
-}
-
 /**
  * follow_pfn - look up PFN at a user virtual address
  * @vma: memory mapping
@@ -4819,7 +4794,7 @@ int follow_pfn(struct vm_area_struct *vma, unsigned long address,
 	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
 		return ret;
 
-	ret = follow_pte(vma->vm_mm, address, &ptep, &ptl);
+	ret = follow_pte(vma->vm_mm, address, NULL, &ptep, NULL, &ptl);
 	if (ret)
 		return ret;
 	*pfn = pte_pfn(*ptep);
@@ -4840,7 +4815,7 @@ int follow_phys(struct vm_area_struct *vma,
 	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
 		goto out;
 
-	if (follow_pte(vma->vm_mm, address, &ptep, &ptl))
+	if (follow_pte(vma->vm_mm, address, NULL, &ptep, NULL, &ptl))
 		goto out;
 	pte = *ptep;
 
-- 
cgit v1.2.3


From c18e68696fdd9fd293f051030bce5aaff3c9b185 Mon Sep 17 00:00:00 2001
From: Geoff Levand <geoff@infradead.org>
Date: Mon, 14 Dec 2020 21:15:47 -0800
Subject: net/connector: Add const qualifier to cb_id
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The connector driver never modifies any cb_id passed to it, so add a const
qualifier to those arguments so callers can declare their struct cb_id as a
constant object.

Fixes build warnings like these when passing a constant struct cb_id:

  warning: passing argument 1 of ‘cn_add_callback’ discards ‘const’ qualifier from pointer target

Signed-off-by: Geoff Levand <geoff@infradead.org>
Link: https://lore.kernel.org/r/a9e49c9e-67fa-16e7-0a6b-72f6bd30c58a@infradead.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/driver-api/connector.rst |  2 +-
 drivers/connector/cn_queue.c           |  8 ++++----
 drivers/connector/connector.c          |  4 ++--
 include/linux/connector.h              | 10 +++++-----
 4 files changed, 12 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/driver-api/connector.rst b/Documentation/driver-api/connector.rst
index 23d068191fb1..631b84a48aa5 100644
--- a/Documentation/driver-api/connector.rst
+++ b/Documentation/driver-api/connector.rst
@@ -25,7 +25,7 @@ handling, etc...  The Connector driver allows any kernelspace agents to use
 netlink based networking for inter-process communication in a significantly
 easier way::
 
-  int cn_add_callback(struct cb_id *id, char *name, void (*callback) (struct cn_msg *, struct netlink_skb_parms *));
+  int cn_add_callback(const struct cb_id *id, char *name, void (*callback) (struct cn_msg *, struct netlink_skb_parms *));
   void cn_netlink_send_mult(struct cn_msg *msg, u16 len, u32 portid, u32 __group, int gfp_mask);
   void cn_netlink_send(struct cn_msg *msg, u32 portid, u32 __group, int gfp_mask);
 
diff --git a/drivers/connector/cn_queue.c b/drivers/connector/cn_queue.c
index 49295052ba8b..996f025eb63c 100644
--- a/drivers/connector/cn_queue.c
+++ b/drivers/connector/cn_queue.c
@@ -19,7 +19,7 @@
 
 static struct cn_callback_entry *
 cn_queue_alloc_callback_entry(struct cn_queue_dev *dev, const char *name,
-			      struct cb_id *id,
+			      const struct cb_id *id,
 			      void (*callback)(struct cn_msg *,
 					       struct netlink_skb_parms *))
 {
@@ -51,13 +51,13 @@ void cn_queue_release_callback(struct cn_callback_entry *cbq)
 	kfree(cbq);
 }
 
-int cn_cb_equal(struct cb_id *i1, struct cb_id *i2)
+int cn_cb_equal(const struct cb_id *i1, const struct cb_id *i2)
 {
 	return ((i1->idx == i2->idx) && (i1->val == i2->val));
 }
 
 int cn_queue_add_callback(struct cn_queue_dev *dev, const char *name,
-			  struct cb_id *id,
+			  const struct cb_id *id,
 			  void (*callback)(struct cn_msg *,
 					   struct netlink_skb_parms *))
 {
@@ -90,7 +90,7 @@ int cn_queue_add_callback(struct cn_queue_dev *dev, const char *name,
 	return 0;
 }
 
-void cn_queue_del_callback(struct cn_queue_dev *dev, struct cb_id *id)
+void cn_queue_del_callback(struct cn_queue_dev *dev, const struct cb_id *id)
 {
 	struct cn_callback_entry *cbq, *n;
 	int found = 0;
diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c
index 7d59d18c6f26..48ec7ce6ecac 100644
--- a/drivers/connector/connector.c
+++ b/drivers/connector/connector.c
@@ -193,7 +193,7 @@ static void cn_rx_skb(struct sk_buff *skb)
  *
  * May sleep.
  */
-int cn_add_callback(struct cb_id *id, const char *name,
+int cn_add_callback(const struct cb_id *id, const char *name,
 		    void (*callback)(struct cn_msg *,
 				     struct netlink_skb_parms *))
 {
@@ -214,7 +214,7 @@ EXPORT_SYMBOL_GPL(cn_add_callback);
  *
  * May sleep while waiting for reference counter to become zero.
  */
-void cn_del_callback(struct cb_id *id)
+void cn_del_callback(const struct cb_id *id)
 {
 	struct cn_dev *dev = &cdev;
 
diff --git a/include/linux/connector.h b/include/linux/connector.h
index cb732643471b..8ea860efea37 100644
--- a/include/linux/connector.h
+++ b/include/linux/connector.h
@@ -64,14 +64,14 @@ struct cn_dev {
  * @callback:	connector's callback.
  * 		parameters are %cn_msg and the sender's credentials
  */
-int cn_add_callback(struct cb_id *id, const char *name,
+int cn_add_callback(const struct cb_id *id, const char *name,
 		    void (*callback)(struct cn_msg *, struct netlink_skb_parms *));
 /**
  * cn_del_callback() - Unregisters new callback with connector core.
  *
  * @id:		unique connector's user identifier.
  */
-void cn_del_callback(struct cb_id *id);
+void cn_del_callback(const struct cb_id *id);
 
 
 /**
@@ -122,14 +122,14 @@ int cn_netlink_send_mult(struct cn_msg *msg, u16 len, u32 portid, u32 group, gfp
 int cn_netlink_send(struct cn_msg *msg, u32 portid, u32 group, gfp_t gfp_mask);
 
 int cn_queue_add_callback(struct cn_queue_dev *dev, const char *name,
-			  struct cb_id *id,
+			  const struct cb_id *id,
 			  void (*callback)(struct cn_msg *, struct netlink_skb_parms *));
-void cn_queue_del_callback(struct cn_queue_dev *dev, struct cb_id *id);
+void cn_queue_del_callback(struct cn_queue_dev *dev, const struct cb_id *id);
 void cn_queue_release_callback(struct cn_callback_entry *);
 
 struct cn_queue_dev *cn_queue_alloc_dev(const char *name, struct sock *);
 void cn_queue_free_dev(struct cn_queue_dev *dev);
 
-int cn_cb_equal(struct cb_id *, struct cb_id *);
+int cn_cb_equal(const struct cb_id *, const struct cb_id *);
 
 #endif				/* __CONNECTOR_H */
-- 
cgit v1.2.3


From 7061eb8cfa902daa1ec71d23b5cddb8b4391e72b Mon Sep 17 00:00:00 2001
From: Lijun Pan <ljp@linux.ibm.com>
Date: Mon, 14 Dec 2020 15:19:28 -0600
Subject: net: core: introduce __netdev_notify_peers

There are some use cases for netdev_notify_peers in the context
when rtnl lock is already held. Introduce lockless version
of netdev_notify_peers call to save the extra code to call
	call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, dev);
	call_netdevice_notifiers(NETDEV_RESEND_IGMP, dev);
After that, convert netdev_notify_peers to call the new helper.

Suggested-by: Nathan Lynch <nathanl@linux.ibm.com>
Signed-off-by: Lijun Pan <ljp@linux.ibm.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h |  1 +
 net/core/dev.c            | 22 ++++++++++++++++++++--
 2 files changed, 21 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7bf167993c05..259be67644e3 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4547,6 +4547,7 @@ void __dev_set_rx_mode(struct net_device *dev);
 int dev_set_promiscuity(struct net_device *dev, int inc);
 int dev_set_allmulti(struct net_device *dev, int inc);
 void netdev_state_change(struct net_device *dev);
+void __netdev_notify_peers(struct net_device *dev);
 void netdev_notify_peers(struct net_device *dev);
 void netdev_features_change(struct net_device *dev);
 /* Load a device via the kmod */
diff --git a/net/core/dev.c b/net/core/dev.c
index a46334906c94..8fa739259041 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1456,6 +1456,25 @@ void netdev_state_change(struct net_device *dev)
 }
 EXPORT_SYMBOL(netdev_state_change);
 
+/**
+ * __netdev_notify_peers - notify network peers about existence of @dev,
+ * to be called when rtnl lock is already held.
+ * @dev: network device
+ *
+ * Generate traffic such that interested network peers are aware of
+ * @dev, such as by generating a gratuitous ARP. This may be used when
+ * a device wants to inform the rest of the network about some sort of
+ * reconfiguration such as a failover event or virtual machine
+ * migration.
+ */
+void __netdev_notify_peers(struct net_device *dev)
+{
+	ASSERT_RTNL();
+	call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, dev);
+	call_netdevice_notifiers(NETDEV_RESEND_IGMP, dev);
+}
+EXPORT_SYMBOL(__netdev_notify_peers);
+
 /**
  * netdev_notify_peers - notify network peers about existence of @dev
  * @dev: network device
@@ -1469,8 +1488,7 @@ EXPORT_SYMBOL(netdev_state_change);
 void netdev_notify_peers(struct net_device *dev)
 {
 	rtnl_lock();
-	call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, dev);
-	call_netdevice_notifiers(NETDEV_RESEND_IGMP, dev);
+	__netdev_notify_peers(dev);
 	rtnl_unlock();
 }
 EXPORT_SYMBOL(netdev_notify_peers);
-- 
cgit v1.2.3


From 767143a18d6d743d4254de5cf55b1bd87bb2af18 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 14 Dec 2020 22:37:50 -0800
Subject: phy: fix kdoc warning

Kdoc does not like it when multiline comment follows the networking
style of starting right on the first line:

include/linux/phy.h:869: warning: Function parameter or member 'config_intr' not described in 'phy_driver'

Link: https://lore.kernel.org/r/20201215063750.3120976-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/phy.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/phy.h b/include/linux/phy.h
index 381a95732b6a..9effb511acde 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -743,7 +743,8 @@ struct phy_driver {
 	/** @read_status: Determines the negotiated speed and duplex */
 	int (*read_status)(struct phy_device *phydev);
 
-	/** @config_intr: Enables or disables interrupts.
+	/**
+	 * @config_intr: Enables or disables interrupts.
 	 * It should also clear any pending interrupts prior to enabling the
 	 * IRQs and after disabling them.
 	 */
-- 
cgit v1.2.3


From 3df23a316c4a5d1764b034c71c29d67a17d5299f Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <uwe@kleine-koenig.org>
Date: Sat, 5 Dec 2020 17:19:24 +0100
Subject: pwm: Remove unused function pwmchip_add_inversed()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This is only defined with CONFIG_PWM unset and was introduced together
with pwmchip_add_with_polarity() (which is only defined with CONFIG_PWM
enabled). I guess the series that introduced pwmchip_add_with_polarity()
had a different concept in earlier revisions and the !CONFIG_PWM part
was just not updated accordingly.

Given that there is no implementation for pwmchip_add_with_polarity()
without CONFIG_PWM, just drop pwmchip_add_inversed() instead of renaming
it to pwmchip_add_with_polarity().

Signed-off-by: Uwe Kleine-König <uwe@kleine-koenig.org>
Acked-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 include/linux/pwm.h | 5 -----
 1 file changed, 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index a13ff383fa1d..e4d84d4db293 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -473,11 +473,6 @@ static inline int pwmchip_add(struct pwm_chip *chip)
 	return -EINVAL;
 }
 
-static inline int pwmchip_add_inversed(struct pwm_chip *chip)
-{
-	return -EINVAL;
-}
-
 static inline int pwmchip_remove(struct pwm_chip *chip)
 {
 	return -EINVAL;
-- 
cgit v1.2.3


From 49e27134f6e9ebcd08c04a98ab7f0574b5a81a35 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@nvidia.com>
Date: Sun, 13 Dec 2020 14:06:41 +0200
Subject: net/mlx5: Fix compilation warning for 32-bit platform
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

MLX5_GENERAL_OBJECT_TYPES types bitfield is 64-bit field.

Defining an enum for such bit fields on 32-bit platform results in below
warning.

./include/vdso/bits.h:7:26: warning: left shift count >= width of type [-Wshift-count-overflow]
                         ^
./include/linux/mlx5/mlx5_ifc.h:10716:46: note: in expansion of macro ‘BIT’
 MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_SAMPLER = BIT(0x20),
                                             ^~~

Use 32-bit friendly BIT_ULL macro.

Fixes: 2a2970891647 ("net/mlx5: Add sample offload hardware bits and structures")
Signed-off-by: Parav Pandit <parav@nvidia.com>
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/20201213120641.216032-1-leon@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/mlx5/mlx5_ifc.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 0d6e287d614f..8fbddec26eb8 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -10711,9 +10711,9 @@ struct mlx5_ifc_affiliated_event_header_bits {
 };
 
 enum {
-	MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY = BIT(0xc),
-	MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_IPSEC = BIT(0x13),
-	MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_SAMPLER = BIT(0x20),
+	MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY = BIT_ULL(0xc),
+	MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_IPSEC = BIT_ULL(0x13),
+	MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_SAMPLER = BIT_ULL(0x20),
 };
 
 enum {
-- 
cgit v1.2.3


From 9bd23c31f392bda88618008f27fd52ee9e0fac38 Mon Sep 17 00:00:00 2001
From: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Date: Fri, 20 Nov 2020 12:22:32 -0800
Subject: jbd2: add a helper to find out number of fast commit blocks

Add a helper to read number of fast commit blocks from jbd2 superblock
and also rename the JBD2_MIN_FC_BLKS to
JBD2_DEFAULT_FAST_COMMIT_BLOCKS since this constant is just the
default number of fast commit blocks to use in case number of fast
commit blocks isn't set in jbd2 superblock.

Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Link: https://lore.kernel.org/r/20201120202232.2240293-2-harshadshirwadkar@gmail.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/jbd2/journal.c    | 8 ++------
 include/linux/jbd2.h | 9 ++++++++-
 2 files changed, 10 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 188f79d76988..2dc944442802 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1869,9 +1869,7 @@ static int load_superblock(journal_t *journal)
 
 	if (jbd2_has_feature_fast_commit(journal)) {
 		journal->j_fc_last = be32_to_cpu(sb->s_maxlen);
-		num_fc_blocks = be32_to_cpu(sb->s_num_fc_blks);
-		if (!num_fc_blocks)
-			num_fc_blocks = JBD2_MIN_FC_BLOCKS;
+		num_fc_blocks = jbd2_journal_get_num_fc_blks(sb);
 		if (journal->j_last - num_fc_blocks >= JBD2_MIN_JOURNAL_BLOCKS)
 			journal->j_last = journal->j_fc_last - num_fc_blocks;
 		journal->j_fc_first = journal->j_last + 1;
@@ -2102,9 +2100,7 @@ jbd2_journal_initialize_fast_commit(journal_t *journal)
 	journal_superblock_t *sb = journal->j_superblock;
 	unsigned long long num_fc_blks;
 
-	num_fc_blks = be32_to_cpu(sb->s_num_fc_blks);
-	if (num_fc_blks == 0)
-		num_fc_blks = JBD2_MIN_FC_BLOCKS;
+	num_fc_blks = jbd2_journal_get_num_fc_blks(sb);
 	if (journal->j_last - num_fc_blks < JBD2_MIN_JOURNAL_BLOCKS)
 		return -ENOSPC;
 
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index d2a4860feb72..99d3cd051ac3 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -68,7 +68,7 @@ extern void *jbd2_alloc(size_t size, gfp_t flags);
 extern void jbd2_free(void *ptr, size_t size);
 
 #define JBD2_MIN_JOURNAL_BLOCKS 1024
-#define JBD2_MIN_FC_BLOCKS	256
+#define JBD2_DEFAULT_FAST_COMMIT_BLOCKS 256
 
 #ifdef __KERNEL__
 
@@ -1692,6 +1692,13 @@ static inline int jbd2_journal_has_csum_v2or3(journal_t *journal)
 	return journal->j_chksum_driver != NULL;
 }
 
+static inline int jbd2_journal_get_num_fc_blks(journal_superblock_t *jsb)
+{
+	int num_fc_blocks = be32_to_cpu(jsb->s_num_fc_blks);
+
+	return num_fc_blocks ? num_fc_blocks : JBD2_DEFAULT_FAST_COMMIT_BLOCKS;
+}
+
 /*
  * Return number of free blocks in the log. Must be called under j_state_lock.
  */
-- 
cgit v1.2.3


From 476c135e321716ad7a8a5d4a19a636e2dcc50526 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@nvidia.com>
Date: Thu, 12 Nov 2020 08:39:59 +0200
Subject: vdpa: Add missing comment for virtqueue count

Add missing comment for number of virtqueue.

Signed-off-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Eli Cohen <elic@nvidia.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Link: https://lore.kernel.org/r/20201112064005.349268-2-parav@nvidia.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/linux/vdpa.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
index 30bc7a7223bb..0fefeb976877 100644
--- a/include/linux/vdpa.h
+++ b/include/linux/vdpa.h
@@ -42,6 +42,7 @@ struct vdpa_vq_state {
  * @config: the configuration ops for this device.
  * @index: device index
  * @features_valid: were features initialized? for legacy guests
+ * @nvqs: maximum number of supported virtqueues
  */
 struct vdpa_device {
 	struct device dev;
-- 
cgit v1.2.3


From a4055888629bc0467d12d912cd7c90acdf3d9b12 Mon Sep 17 00:00:00 2001
From: Alex Shi <alex.shi@linux.alibaba.com>
Date: Fri, 18 Dec 2020 14:01:31 -0800
Subject: mm/memcg: warning on !memcg after readahead page charged

Add VM_WARN_ON_ONCE_PAGE() macro.

Since readahead page is charged on memcg too, in theory we don't have to
check this exception now.  Before safely remove them all, add a warning
for the unexpected !memcg.

Link: https://lkml.kernel.org/r/1604283436-18880-3-git-send-email-alex.shi@linux.alibaba.com
Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Hugh Dickins <hughd@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmdebug.h | 13 +++++++++++++
 mm/memcontrol.c         | 10 ++++------
 2 files changed, 17 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h
index 2ad72d2c8cc5..5d0767cb424a 100644
--- a/include/linux/mmdebug.h
+++ b/include/linux/mmdebug.h
@@ -37,6 +37,18 @@ void dump_mm(const struct mm_struct *mm);
 			BUG();						\
 		}							\
 	} while (0)
+#define VM_WARN_ON_ONCE_PAGE(cond, page)	({			\
+	static bool __section(".data.once") __warned;			\
+	int __ret_warn_once = !!(cond);					\
+									\
+	if (unlikely(__ret_warn_once && !__warned)) {			\
+		dump_page(page, "VM_WARN_ON_ONCE_PAGE(" __stringify(cond)")");\
+		__warned = true;					\
+		WARN_ON(1);						\
+	}								\
+	unlikely(__ret_warn_once);					\
+})
+
 #define VM_WARN_ON(cond) (void)WARN_ON(cond)
 #define VM_WARN_ON_ONCE(cond) (void)WARN_ON_ONCE(cond)
 #define VM_WARN_ONCE(cond, format...) (void)WARN_ONCE(cond, format)
@@ -48,6 +60,7 @@ void dump_mm(const struct mm_struct *mm);
 #define VM_BUG_ON_MM(cond, mm) VM_BUG_ON(cond)
 #define VM_WARN_ON(cond) BUILD_BUG_ON_INVALID(cond)
 #define VM_WARN_ON_ONCE(cond) BUILD_BUG_ON_INVALID(cond)
+#define VM_WARN_ON_ONCE_PAGE(cond, page)  BUILD_BUG_ON_INVALID(cond)
 #define VM_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond)
 #define VM_WARN(cond, format...) BUILD_BUG_ON_INVALID(cond)
 #endif
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 5c3b054066f5..7b9766789a27 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1362,10 +1362,7 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct pglist_data *pgd
 	}
 
 	memcg = page_memcg(page);
-	/*
-	 * Swapcache readahead pages are added to the LRU - and
-	 * possibly migrated - before they are charged.
-	 */
+	VM_WARN_ON_ONCE_PAGE(!memcg, page);
 	if (!memcg)
 		memcg = root_mem_cgroup;
 
@@ -6987,6 +6984,7 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage)
 		return;
 
 	memcg = page_memcg(oldpage);
+	VM_WARN_ON_ONCE_PAGE(!memcg, oldpage);
 	if (!memcg)
 		return;
 
@@ -7186,7 +7184,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
 
 	memcg = page_memcg(page);
 
-	/* Readahead page, never charged */
+	VM_WARN_ON_ONCE_PAGE(!memcg, page);
 	if (!memcg)
 		return;
 
@@ -7253,7 +7251,7 @@ int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry)
 
 	memcg = page_memcg(page);
 
-	/* Readahead page, never charged */
+	VM_WARN_ON_ONCE_PAGE(!memcg, page);
 	if (!memcg)
 		return 0;
 
-- 
cgit v1.2.3


From bec78efd0061365a76f88e498affd7106b256823 Mon Sep 17 00:00:00 2001
From: Wei Yang <richard.weiyang@gmail.com>
Date: Fri, 18 Dec 2020 14:01:35 -0800
Subject: mm/memcg: remove unused definitions

Some definitions are left unused, just clean them.

Link: https://lkml.kernel.org/r/20201108003834.12669-1-richard.weiyang@gmail.com
Signed-off-by: Wei Yang <richard.weiyang@gmail.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Reviewed-by: Roman Gushchin <guro@fb.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 118 ---------------------------------------------
 1 file changed, 118 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 08ed57e02b73..196441f5dc99 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -913,41 +913,6 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg,
 	local_irq_restore(flags);
 }
 
-/**
- * mod_memcg_page_state - update page state statistics
- * @page: the page
- * @idx: page state item to account
- * @val: number of pages (positive or negative)
- *
- * The @page must be locked or the caller must use lock_page_memcg()
- * to prevent double accounting when the page is concurrently being
- * moved to another memcg:
- *
- *   lock_page(page) or lock_page_memcg(page)
- *   if (TestClearPageState(page))
- *     mod_memcg_page_state(page, state, -1);
- *   unlock_page(page) or unlock_page_memcg(page)
- *
- * Kernel pages are an exception to this, since they'll never move.
- */
-static inline void __mod_memcg_page_state(struct page *page,
-					  int idx, int val)
-{
-	struct mem_cgroup *memcg = page_memcg(page);
-
-	if (memcg)
-		__mod_memcg_state(memcg, idx, val);
-}
-
-static inline void mod_memcg_page_state(struct page *page,
-					int idx, int val)
-{
-	struct mem_cgroup *memcg = page_memcg(page);
-
-	if (memcg)
-		mod_memcg_state(memcg, idx, val);
-}
-
 static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
 					      enum node_stat_item idx)
 {
@@ -1395,18 +1360,6 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg,
 {
 }
 
-static inline void __mod_memcg_page_state(struct page *page,
-					  int idx,
-					  int nr)
-{
-}
-
-static inline void mod_memcg_page_state(struct page *page,
-					int idx,
-					int nr)
-{
-}
-
 static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
 					      enum node_stat_item idx)
 {
@@ -1479,34 +1432,6 @@ static inline void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page)
 }
 #endif /* CONFIG_MEMCG */
 
-/* idx can be of type enum memcg_stat_item or node_stat_item */
-static inline void __inc_memcg_state(struct mem_cgroup *memcg,
-				     int idx)
-{
-	__mod_memcg_state(memcg, idx, 1);
-}
-
-/* idx can be of type enum memcg_stat_item or node_stat_item */
-static inline void __dec_memcg_state(struct mem_cgroup *memcg,
-				     int idx)
-{
-	__mod_memcg_state(memcg, idx, -1);
-}
-
-/* idx can be of type enum memcg_stat_item or node_stat_item */
-static inline void __inc_memcg_page_state(struct page *page,
-					  int idx)
-{
-	__mod_memcg_page_state(page, idx, 1);
-}
-
-/* idx can be of type enum memcg_stat_item or node_stat_item */
-static inline void __dec_memcg_page_state(struct page *page,
-					  int idx)
-{
-	__mod_memcg_page_state(page, idx, -1);
-}
-
 static inline void __inc_lruvec_kmem_state(void *p, enum node_stat_item idx)
 {
 	__mod_lruvec_kmem_state(p, idx, 1);
@@ -1517,34 +1442,6 @@ static inline void __dec_lruvec_kmem_state(void *p, enum node_stat_item idx)
 	__mod_lruvec_kmem_state(p, idx, -1);
 }
 
-/* idx can be of type enum memcg_stat_item or node_stat_item */
-static inline void inc_memcg_state(struct mem_cgroup *memcg,
-				   int idx)
-{
-	mod_memcg_state(memcg, idx, 1);
-}
-
-/* idx can be of type enum memcg_stat_item or node_stat_item */
-static inline void dec_memcg_state(struct mem_cgroup *memcg,
-				   int idx)
-{
-	mod_memcg_state(memcg, idx, -1);
-}
-
-/* idx can be of type enum memcg_stat_item or node_stat_item */
-static inline void inc_memcg_page_state(struct page *page,
-					int idx)
-{
-	mod_memcg_page_state(page, idx, 1);
-}
-
-/* idx can be of type enum memcg_stat_item or node_stat_item */
-static inline void dec_memcg_page_state(struct page *page,
-					int idx)
-{
-	mod_memcg_page_state(page, idx, -1);
-}
-
 static inline struct lruvec *parent_lruvec(struct lruvec *lruvec)
 {
 	struct mem_cgroup *memcg;
@@ -1733,21 +1630,6 @@ static inline void memcg_kmem_uncharge_page(struct page *page, int order)
 		__memcg_kmem_uncharge_page(page, order);
 }
 
-static inline int memcg_kmem_charge(struct mem_cgroup *memcg, gfp_t gfp,
-				    unsigned int nr_pages)
-{
-	if (memcg_kmem_enabled())
-		return __memcg_kmem_charge(memcg, gfp, nr_pages);
-	return 0;
-}
-
-static inline void memcg_kmem_uncharge(struct mem_cgroup *memcg,
-				       unsigned int nr_pages)
-{
-	if (memcg_kmem_enabled())
-		__memcg_kmem_uncharge(memcg, nr_pages);
-}
-
 /*
  * A helper for accessing memcg's kmem_id, used for getting
  * corresponding LRU lists.
-- 
cgit v1.2.3


From 9a1ac2288cf16f9406ca54ef221bfcf262393b15 Mon Sep 17 00:00:00 2001
From: Hui Su <sh_def@163.com>
Date: Fri, 18 Dec 2020 14:01:41 -0800
Subject: mm/memcontrol:rewrite mem_cgroup_page_lruvec()

mem_cgroup_page_lruvec() in memcontrol.c and mem_cgroup_lruvec() in
memcontrol.h is very similar except for the param(page and memcg) which
also can be convert to each other.

So rewrite mem_cgroup_page_lruvec() with mem_cgroup_lruvec().

[alex.shi@linux.alibaba.com: add missed warning in mem_cgroup_lruvec]
  Link: https://lkml.kernel.org/r/94f17bb7-ec61-5b72-3555-fabeb5a4d73b@linux.alibaba.com
[lstoakes@gmail.com: warn on missing memcg on mem_cgroup_page_lruvec()]
  Link: https://lkml.kernel.org/r/20201125112202.387009-1-lstoakes@gmail.com

Link: https://lkml.kernel.org/r/20201108143731.GA74138@rlk
Signed-off-by: Hui Su <sh_def@163.com>
Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
Signed-off-by: Lorenzo Stoakes <lstoakes@gmail.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Roman Gushchin <guro@fb.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Yafang Shao <laoar.shao@gmail.com>
Cc: Chris Down <chris@chrisdown.name>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 19 +++++++++++++++++--
 mm/memcontrol.c            | 37 -------------------------------------
 2 files changed, 17 insertions(+), 39 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 196441f5dc99..d827bd7f3bfe 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -620,9 +620,10 @@ mem_cgroup_nodeinfo(struct mem_cgroup *memcg, int nid)
 /**
  * mem_cgroup_lruvec - get the lru list vector for a memcg & node
  * @memcg: memcg of the wanted lruvec
+ * @pgdat: pglist_data
  *
  * Returns the lru list vector holding pages for a given @memcg &
- * @node combination. This can be the node lruvec, if the memory
+ * @pgdat combination. This can be the node lruvec, if the memory
  * controller is disabled.
  */
 static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg,
@@ -652,7 +653,21 @@ out:
 	return lruvec;
 }
 
-struct lruvec *mem_cgroup_page_lruvec(struct page *, struct pglist_data *);
+/**
+ * mem_cgroup_page_lruvec - return lruvec for isolating/putting an LRU page
+ * @page: the page
+ * @pgdat: pgdat of the page
+ *
+ * This function relies on page->mem_cgroup being stable.
+ */
+static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page,
+						struct pglist_data *pgdat)
+{
+	struct mem_cgroup *memcg = page_memcg(page);
+
+	VM_WARN_ON_ONCE_PAGE(!memcg, page);
+	return mem_cgroup_lruvec(memcg, pgdat);
+}
 
 static inline bool lruvec_holds_page_lru_lock(struct page *page,
 					      struct lruvec *lruvec)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 7b9766789a27..605f671203ef 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1342,43 +1342,6 @@ void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page)
 }
 #endif
 
-/**
- * mem_cgroup_page_lruvec - return lruvec for isolating/putting an LRU page
- * @page: the page
- * @pgdat: pgdat of the page
- *
- * This function relies on page's memcg being stable - see the
- * access rules in commit_charge().
- */
-struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct pglist_data *pgdat)
-{
-	struct mem_cgroup_per_node *mz;
-	struct mem_cgroup *memcg;
-	struct lruvec *lruvec;
-
-	if (mem_cgroup_disabled()) {
-		lruvec = &pgdat->__lruvec;
-		goto out;
-	}
-
-	memcg = page_memcg(page);
-	VM_WARN_ON_ONCE_PAGE(!memcg, page);
-	if (!memcg)
-		memcg = root_mem_cgroup;
-
-	mz = mem_cgroup_page_nodeinfo(memcg, page);
-	lruvec = &mz->lruvec;
-out:
-	/*
-	 * Since a node can be onlined after the mem_cgroup was created,
-	 * we have to be prepared to initialize lruvec->zone here;
-	 * and if offlined then reonlined, we need to reinitialize it.
-	 */
-	if (unlikely(lruvec->pgdat != pgdat))
-		lruvec->pgdat = pgdat;
-	return lruvec;
-}
-
 /**
  * lock_page_lruvec - lock and return lruvec for a given page.
  * @page: the page
-- 
cgit v1.2.3


From b0a0c2615f6f199a656ed8549d7dce625d77aa77 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 18 Dec 2020 14:05:41 -0800
Subject: epoll: wire up syscall epoll_pwait2

Split off from prev patch in the series that implements the syscall.

Link: https://lkml.kernel.org/r/20201121144401.3727659-4-willemdebruijn.kernel@gmail.com
Signed-off-by: Willem de Bruijn <willemb@google.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/alpha/kernel/syscalls/syscall.tbl      | 1 +
 arch/arm/tools/syscall.tbl                  | 1 +
 arch/arm64/include/asm/unistd.h             | 2 +-
 arch/arm64/include/asm/unistd32.h           | 2 ++
 arch/ia64/kernel/syscalls/syscall.tbl       | 1 +
 arch/m68k/kernel/syscalls/syscall.tbl       | 1 +
 arch/microblaze/kernel/syscalls/syscall.tbl | 1 +
 arch/mips/kernel/syscalls/syscall_n32.tbl   | 1 +
 arch/mips/kernel/syscalls/syscall_n64.tbl   | 1 +
 arch/mips/kernel/syscalls/syscall_o32.tbl   | 1 +
 arch/parisc/kernel/syscalls/syscall.tbl     | 1 +
 arch/powerpc/kernel/syscalls/syscall.tbl    | 1 +
 arch/s390/kernel/syscalls/syscall.tbl       | 1 +
 arch/sh/kernel/syscalls/syscall.tbl         | 1 +
 arch/sparc/kernel/syscalls/syscall.tbl      | 1 +
 arch/x86/entry/syscalls/syscall_32.tbl      | 1 +
 arch/x86/entry/syscalls/syscall_64.tbl      | 1 +
 arch/xtensa/kernel/syscalls/syscall.tbl     | 1 +
 include/linux/compat.h                      | 6 ++++++
 include/linux/syscalls.h                    | 5 +++++
 include/uapi/asm-generic/unistd.h           | 4 +++-
 kernel/sys_ni.c                             | 2 ++
 22 files changed, 35 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index ee7b01bb7346..a6617067dbe6 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -480,3 +480,4 @@
 548	common	pidfd_getfd			sys_pidfd_getfd
 549	common	faccessat2			sys_faccessat2
 550	common	process_madvise			sys_process_madvise
+551	common	epoll_pwait2			sys_epoll_pwait2
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index d056a548358e..20e1170e2e0a 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -454,3 +454,4 @@
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	faccessat2			sys_faccessat2
 440	common	process_madvise			sys_process_madvise
+441	common	epoll_pwait2			sys_epoll_pwait2
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index b3b2019f8d16..86a9d7b3eabe 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -38,7 +38,7 @@
 #define __ARM_NR_compat_set_tls		(__ARM_NR_COMPAT_BASE + 5)
 #define __ARM_NR_COMPAT_END		(__ARM_NR_COMPAT_BASE + 0x800)
 
-#define __NR_compat_syscalls		441
+#define __NR_compat_syscalls		442
 #endif
 
 #define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 107f08e03b9f..f4bca2b90218 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -889,6 +889,8 @@ __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
 __SYSCALL(__NR_faccessat2, sys_faccessat2)
 #define __NR_process_madvise 440
 __SYSCALL(__NR_process_madvise, sys_process_madvise)
+#define __NR_epoll_pwait2 441
+__SYSCALL(__NR_epoll_pwait2, sys_epoll_pwait2)
 
 /*
  * Please add new compat syscalls above this comment and update
diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl
index b96ed8b8a508..bfc00f2bd437 100644
--- a/arch/ia64/kernel/syscalls/syscall.tbl
+++ b/arch/ia64/kernel/syscalls/syscall.tbl
@@ -361,3 +361,4 @@
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	faccessat2			sys_faccessat2
 440	common	process_madvise			sys_process_madvise
+441	common	epoll_pwait2			sys_epoll_pwait2
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index 625fb6d32842..7fe4e45c864c 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -440,3 +440,4 @@
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	faccessat2			sys_faccessat2
 440	common	process_madvise			sys_process_madvise
+441	common	epoll_pwait2			sys_epoll_pwait2
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index aae729c95cf9..a522adf194ab 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -446,3 +446,4 @@
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	faccessat2			sys_faccessat2
 440	common	process_madvise			sys_process_madvise
+441	common	epoll_pwait2			sys_epoll_pwait2
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index 32817c954435..ad9c3dd0ab1f 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -379,3 +379,4 @@
 438	n32	pidfd_getfd			sys_pidfd_getfd
 439	n32	faccessat2			sys_faccessat2
 440	n32	process_madvise			sys_process_madvise
+441	n32	epoll_pwait2			sys_epoll_pwait2
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index 9e4ea3c31b1c..91649690b52f 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -355,3 +355,4 @@
 438	n64	pidfd_getfd			sys_pidfd_getfd
 439	n64	faccessat2			sys_faccessat2
 440	n64	process_madvise			sys_process_madvise
+441	n64	epoll_pwait2			sys_epoll_pwait2
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 29f5f28cf5ce..4bad0c40aed6 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -428,3 +428,4 @@
 438	o32	pidfd_getfd			sys_pidfd_getfd
 439	o32	faccessat2			sys_faccessat2
 440	o32	process_madvise			sys_process_madvise
+441	o32	epoll_pwait2			sys_epoll_pwait2		compat_sys_epoll_pwait2
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index f375ea528e59..6bcc31966b44 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -438,3 +438,4 @@
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	faccessat2			sys_faccessat2
 440	common	process_madvise			sys_process_madvise
+441	common	epoll_pwait2			sys_epoll_pwait2		compat_sys_epoll_pwait2
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index 1275daec7fec..f744eb5cba88 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -530,3 +530,4 @@
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	faccessat2			sys_faccessat2
 440	common	process_madvise			sys_process_madvise
+441	common	epoll_pwait2			sys_epoll_pwait2		compat_sys_epoll_pwait2
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 28c168000483..14f6525886a8 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -443,3 +443,4 @@
 438  common	pidfd_getfd		sys_pidfd_getfd			sys_pidfd_getfd
 439  common	faccessat2		sys_faccessat2			sys_faccessat2
 440  common	process_madvise		sys_process_madvise		sys_process_madvise
+441  common	epoll_pwait2		sys_epoll_pwait2		sys_epoll_pwait2
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index 783738448ff5..9df40ac0ebc0 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -443,3 +443,4 @@
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	faccessat2			sys_faccessat2
 440	common	process_madvise			sys_process_madvise
+441	common	epoll_pwait2			sys_epoll_pwait2
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index 78160260991b..c7da4c3271e6 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -486,3 +486,4 @@
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	faccessat2			sys_faccessat2
 440	common	process_madvise			sys_process_madvise
+441	common	epoll_pwait2			sys_epoll_pwait2
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 0d0667a9fbd7..874aeacde2dd 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -445,3 +445,4 @@
 438	i386	pidfd_getfd		sys_pidfd_getfd
 439	i386	faccessat2		sys_faccessat2
 440	i386	process_madvise		sys_process_madvise
+441	i386	epoll_pwait2		sys_epoll_pwait2		compat_sys_epoll_pwait2
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 379819244b91..78672124d28b 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -362,6 +362,7 @@
 438	common	pidfd_getfd		sys_pidfd_getfd
 439	common	faccessat2		sys_faccessat2
 440	common	process_madvise		sys_process_madvise
+441	common	epoll_pwait2		sys_epoll_pwait2
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index b070f272995d..46116a28eeed 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -411,3 +411,4 @@
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	faccessat2			sys_faccessat2
 440	common	process_madvise			sys_process_madvise
+441	common	epoll_pwait2			sys_epoll_pwait2
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 400c0941c8af..6e65be753603 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -537,6 +537,12 @@ asmlinkage long compat_sys_epoll_pwait(int epfd,
 			int maxevents, int timeout,
 			const compat_sigset_t __user *sigmask,
 			compat_size_t sigsetsize);
+asmlinkage long compat_sys_epoll_pwait2(int epfd,
+			struct epoll_event __user *events,
+			int maxevents,
+			const struct __kernel_timespec __user *timeout,
+			const compat_sigset_t __user *sigmask,
+			compat_size_t sigsetsize);
 
 /* fs/fcntl.c */
 asmlinkage long compat_sys_fcntl(unsigned int fd, unsigned int cmd,
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index df0c3c74609e..f3929aff39cf 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -362,6 +362,11 @@ asmlinkage long sys_epoll_pwait(int epfd, struct epoll_event __user *events,
 				int maxevents, int timeout,
 				const sigset_t __user *sigmask,
 				size_t sigsetsize);
+asmlinkage long sys_epoll_pwait2(int epfd, struct epoll_event __user *events,
+				 int maxevents,
+				 const struct __kernel_timespec __user *timeout,
+				 const sigset_t __user *sigmask,
+				 size_t sigsetsize);
 
 /* fs/fcntl.c */
 asmlinkage long sys_dup(unsigned int fildes);
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index fc48c64700eb..728752917785 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -859,9 +859,11 @@ __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
 __SYSCALL(__NR_faccessat2, sys_faccessat2)
 #define __NR_process_madvise 440
 __SYSCALL(__NR_process_madvise, sys_process_madvise)
+#define __NR_epoll_pwait2 441
+__SC_COMP(__NR_epoll_pwait2, sys_epoll_pwait2, compat_sys_epoll_pwait2)
 
 #undef __NR_syscalls
-#define __NR_syscalls 441
+#define __NR_syscalls 442
 
 /*
  * 32 bit systems traditionally used different
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index f27ac94d5fa7..19aa806890d5 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -68,6 +68,8 @@ COND_SYSCALL(epoll_create1);
 COND_SYSCALL(epoll_ctl);
 COND_SYSCALL(epoll_pwait);
 COND_SYSCALL_COMPAT(epoll_pwait);
+COND_SYSCALL(epoll_pwait2);
+COND_SYSCALL_COMPAT(epoll_pwait2);
 
 /* fs/fcntl.c */
 
-- 
cgit v1.2.3


From 3b1a4a8640876a966ab68ab4f561642e19674671 Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Tue, 22 Dec 2020 12:00:14 -0800
Subject: kasan: group vmalloc code

This is a preparatory commit for the upcoming addition of a new hardware
tag-based (MTE-based) KASAN mode.

Group all vmalloc-related function declarations in include/linux/kasan.h,
and their implementations in mm/kasan/common.c.

No functional changes.

Link: https://lkml.kernel.org/r/80a6fdd29b039962843bd6cf22ce2643a7c8904e.1606161801.git.andreyknvl@google.com
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Reviewed-by: Marco Elver <elver@google.com>
Reviewed-by: Alexander Potapenko <glider@google.com>
Tested-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Branislav Rankov <Branislav.Rankov@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Kevin Brodsky <kevin.brodsky@arm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kasan.h | 41 +++++++++++++++------------
 mm/kasan/common.c     | 78 ++++++++++++++++++++++++++-------------------------
 2 files changed, 63 insertions(+), 56 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 30d343b4a40a..59538e795df4 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -75,19 +75,6 @@ struct kasan_cache {
 	int free_meta_offset;
 };
 
-/*
- * These functions provide a special case to support backing module
- * allocations with real shadow memory. With KASAN vmalloc, the special
- * case is unnecessary, as the work is handled in the generic case.
- */
-#ifndef CONFIG_KASAN_VMALLOC
-int kasan_module_alloc(void *addr, size_t size);
-void kasan_free_shadow(const struct vm_struct *vm);
-#else
-static inline int kasan_module_alloc(void *addr, size_t size) { return 0; }
-static inline void kasan_free_shadow(const struct vm_struct *vm) {}
-#endif
-
 int kasan_add_zero_shadow(void *start, unsigned long size);
 void kasan_remove_zero_shadow(void *start, unsigned long size);
 
@@ -156,9 +143,6 @@ static inline bool kasan_slab_free(struct kmem_cache *s, void *object,
 	return false;
 }
 
-static inline int kasan_module_alloc(void *addr, size_t size) { return 0; }
-static inline void kasan_free_shadow(const struct vm_struct *vm) {}
-
 static inline int kasan_add_zero_shadow(void *start, unsigned long size)
 {
 	return 0;
@@ -211,13 +195,16 @@ static inline void *kasan_reset_tag(const void *addr)
 #endif /* CONFIG_KASAN_SW_TAGS */
 
 #ifdef CONFIG_KASAN_VMALLOC
+
 int kasan_populate_vmalloc(unsigned long addr, unsigned long size);
 void kasan_poison_vmalloc(const void *start, unsigned long size);
 void kasan_unpoison_vmalloc(const void *start, unsigned long size);
 void kasan_release_vmalloc(unsigned long start, unsigned long end,
 			   unsigned long free_region_start,
 			   unsigned long free_region_end);
-#else
+
+#else /* CONFIG_KASAN_VMALLOC */
+
 static inline int kasan_populate_vmalloc(unsigned long start,
 					unsigned long size)
 {
@@ -232,7 +219,25 @@ static inline void kasan_release_vmalloc(unsigned long start,
 					 unsigned long end,
 					 unsigned long free_region_start,
 					 unsigned long free_region_end) {}
-#endif
+
+#endif /* CONFIG_KASAN_VMALLOC */
+
+#if defined(CONFIG_KASAN) && !defined(CONFIG_KASAN_VMALLOC)
+
+/*
+ * These functions provide a special case to support backing module
+ * allocations with real shadow memory. With KASAN vmalloc, the special
+ * case is unnecessary, as the work is handled in the generic case.
+ */
+int kasan_module_alloc(void *addr, size_t size);
+void kasan_free_shadow(const struct vm_struct *vm);
+
+#else /* CONFIG_KASAN && !CONFIG_KASAN_VMALLOC */
+
+static inline int kasan_module_alloc(void *addr, size_t size) { return 0; }
+static inline void kasan_free_shadow(const struct vm_struct *vm) {}
+
+#endif /* CONFIG_KASAN && !CONFIG_KASAN_VMALLOC */
 
 #ifdef CONFIG_KASAN_INLINE
 void kasan_non_canonical_hook(unsigned long addr);
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index 33d863f55db1..89e5ef9417a7 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -536,44 +536,6 @@ void kasan_kfree_large(void *ptr, unsigned long ip)
 	/* The object will be poisoned by page_alloc. */
 }
 
-#ifndef CONFIG_KASAN_VMALLOC
-int kasan_module_alloc(void *addr, size_t size)
-{
-	void *ret;
-	size_t scaled_size;
-	size_t shadow_size;
-	unsigned long shadow_start;
-
-	shadow_start = (unsigned long)kasan_mem_to_shadow(addr);
-	scaled_size = (size + KASAN_SHADOW_MASK) >> KASAN_SHADOW_SCALE_SHIFT;
-	shadow_size = round_up(scaled_size, PAGE_SIZE);
-
-	if (WARN_ON(!PAGE_ALIGNED(shadow_start)))
-		return -EINVAL;
-
-	ret = __vmalloc_node_range(shadow_size, 1, shadow_start,
-			shadow_start + shadow_size,
-			GFP_KERNEL,
-			PAGE_KERNEL, VM_NO_GUARD, NUMA_NO_NODE,
-			__builtin_return_address(0));
-
-	if (ret) {
-		__memset(ret, KASAN_SHADOW_INIT, shadow_size);
-		find_vm_area(addr)->flags |= VM_KASAN;
-		kmemleak_ignore(ret);
-		return 0;
-	}
-
-	return -ENOMEM;
-}
-
-void kasan_free_shadow(const struct vm_struct *vm)
-{
-	if (vm->flags & VM_KASAN)
-		vfree(kasan_mem_to_shadow(vm->addr));
-}
-#endif
-
 #ifdef CONFIG_MEMORY_HOTPLUG
 static bool shadow_mapped(unsigned long addr)
 {
@@ -685,6 +647,7 @@ core_initcall(kasan_memhotplug_init);
 #endif
 
 #ifdef CONFIG_KASAN_VMALLOC
+
 static int kasan_populate_vmalloc_pte(pte_t *ptep, unsigned long addr,
 				      void *unused)
 {
@@ -923,4 +886,43 @@ void kasan_release_vmalloc(unsigned long start, unsigned long end,
 				       (unsigned long)shadow_end);
 	}
 }
+
+#else /* CONFIG_KASAN_VMALLOC */
+
+int kasan_module_alloc(void *addr, size_t size)
+{
+	void *ret;
+	size_t scaled_size;
+	size_t shadow_size;
+	unsigned long shadow_start;
+
+	shadow_start = (unsigned long)kasan_mem_to_shadow(addr);
+	scaled_size = (size + KASAN_SHADOW_MASK) >> KASAN_SHADOW_SCALE_SHIFT;
+	shadow_size = round_up(scaled_size, PAGE_SIZE);
+
+	if (WARN_ON(!PAGE_ALIGNED(shadow_start)))
+		return -EINVAL;
+
+	ret = __vmalloc_node_range(shadow_size, 1, shadow_start,
+			shadow_start + shadow_size,
+			GFP_KERNEL,
+			PAGE_KERNEL, VM_NO_GUARD, NUMA_NO_NODE,
+			__builtin_return_address(0));
+
+	if (ret) {
+		__memset(ret, KASAN_SHADOW_INIT, shadow_size);
+		find_vm_area(addr)->flags |= VM_KASAN;
+		kmemleak_ignore(ret);
+		return 0;
+	}
+
+	return -ENOMEM;
+}
+
+void kasan_free_shadow(const struct vm_struct *vm)
+{
+	if (vm->flags & VM_KASAN)
+		vfree(kasan_mem_to_shadow(vm->addr));
+}
+
 #endif
-- 
cgit v1.2.3


From d5750edf6da759576f91ec2b57d5553985815b40 Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Tue, 22 Dec 2020 12:00:17 -0800
Subject: kasan: shadow declarations only for software modes

This is a preparatory commit for the upcoming addition of a new hardware
tag-based (MTE-based) KASAN mode.

Group shadow-related KASAN function declarations and only define them for
the two existing software modes.

No functional changes for software modes.

  Link: https://lkml.kernel.org/r/35126.1606402815@turing-police
  Link: https://lore.kernel.org/linux-arm-kernel/24105.1606397102@turing-police/

Link: https://lkml.kernel.org/r/e88d94eff94db883a65dca52e1736d80d28dd9bc.1606161801.git.andreyknvl@google.com
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Signed-off-by: Valdis Kletnieks <valdis.kletnieks@vt.edu>
Reviewed-by: Marco Elver <elver@google.com>
Reviewed-by: Alexander Potapenko <glider@google.com>
Tested-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Branislav Rankov <Branislav.Rankov@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Kevin Brodsky <kevin.brodsky@arm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Will Deacon <will.deacon@arm.com>
[valdis.kletnieks@vt.edu: fix build issue with asmlinkage]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kasan.h | 48 ++++++++++++++++++++++++++++++++----------------
 1 file changed, 32 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 59538e795df4..7828436a3a99 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -11,7 +11,7 @@ struct task_struct;
 
 #ifdef CONFIG_KASAN
 
-#include <linux/pgtable.h>
+#include <linux/linkage.h>
 #include <asm/kasan.h>
 
 /* kasan_data struct is used in KUnit tests for KASAN expected failures */
@@ -20,6 +20,20 @@ struct kunit_kasan_expectation {
 	bool report_found;
 };
 
+#endif
+
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
+
+#include <linux/pgtable.h>
+
+/* Software KASAN implementations use shadow memory. */
+
+#ifdef CONFIG_KASAN_SW_TAGS
+#define KASAN_SHADOW_INIT 0xFF
+#else
+#define KASAN_SHADOW_INIT 0
+#endif
+
 extern unsigned char kasan_early_shadow_page[PAGE_SIZE];
 extern pte_t kasan_early_shadow_pte[PTRS_PER_PTE];
 extern pmd_t kasan_early_shadow_pmd[PTRS_PER_PMD];
@@ -35,6 +49,23 @@ static inline void *kasan_mem_to_shadow(const void *addr)
 		+ KASAN_SHADOW_OFFSET;
 }
 
+int kasan_add_zero_shadow(void *start, unsigned long size);
+void kasan_remove_zero_shadow(void *start, unsigned long size);
+
+#else /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
+
+static inline int kasan_add_zero_shadow(void *start, unsigned long size)
+{
+	return 0;
+}
+static inline void kasan_remove_zero_shadow(void *start,
+					unsigned long size)
+{}
+
+#endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
+
+#ifdef CONFIG_KASAN
+
 /* Enable reporting bugs after kasan_disable_current() */
 extern void kasan_enable_current(void);
 
@@ -75,9 +106,6 @@ struct kasan_cache {
 	int free_meta_offset;
 };
 
-int kasan_add_zero_shadow(void *start, unsigned long size);
-void kasan_remove_zero_shadow(void *start, unsigned long size);
-
 size_t __ksize(const void *);
 static inline void kasan_unpoison_slab(const void *ptr)
 {
@@ -143,14 +171,6 @@ static inline bool kasan_slab_free(struct kmem_cache *s, void *object,
 	return false;
 }
 
-static inline int kasan_add_zero_shadow(void *start, unsigned long size)
-{
-	return 0;
-}
-static inline void kasan_remove_zero_shadow(void *start,
-					unsigned long size)
-{}
-
 static inline void kasan_unpoison_slab(const void *ptr) { }
 static inline size_t kasan_metadata_size(struct kmem_cache *cache) { return 0; }
 
@@ -158,8 +178,6 @@ static inline size_t kasan_metadata_size(struct kmem_cache *cache) { return 0; }
 
 #ifdef CONFIG_KASAN_GENERIC
 
-#define KASAN_SHADOW_INIT 0
-
 void kasan_cache_shrink(struct kmem_cache *cache);
 void kasan_cache_shutdown(struct kmem_cache *cache);
 void kasan_record_aux_stack(void *ptr);
@@ -174,8 +192,6 @@ static inline void kasan_record_aux_stack(void *ptr) {}
 
 #ifdef CONFIG_KASAN_SW_TAGS
 
-#define KASAN_SHADOW_INIT 0xFF
-
 void kasan_init_tags(void);
 
 void *kasan_reset_tag(const void *addr);
-- 
cgit v1.2.3


From cebd0eb29acdfc2f5e44e5f356ffcd0c44f16b4a Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Tue, 22 Dec 2020 12:00:21 -0800
Subject: kasan: rename (un)poison_shadow to (un)poison_range

This is a preparatory commit for the upcoming addition of a new hardware
tag-based (MTE-based) KASAN mode.

The new mode won't be using shadow memory.  Rename external annotation
kasan_unpoison_shadow() to kasan_unpoison_range(), and introduce internal
functions (un)poison_range() (without kasan_ prefix).

Co-developed-by: Marco Elver <elver@google.com>
Link: https://lkml.kernel.org/r/fccdcaa13dc6b2211bf363d6c6d499279a54fe3a.1606161801.git.andreyknvl@google.com
Signed-off-by: Marco Elver <elver@google.com>
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Reviewed-by: Alexander Potapenko <glider@google.com>
Tested-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Branislav Rankov <Branislav.Rankov@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Kevin Brodsky <kevin.brodsky@arm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kasan.h |  6 +++---
 kernel/fork.c         |  4 ++--
 mm/kasan/common.c     | 49 +++++++++++++++++++++++++++----------------------
 mm/kasan/generic.c    | 23 +++++++++++------------
 mm/kasan/kasan.h      |  3 ++-
 mm/kasan/tags.c       |  2 +-
 mm/slab_common.c      |  2 +-
 7 files changed, 47 insertions(+), 42 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 7828436a3a99..9740c06a04a1 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -72,7 +72,7 @@ extern void kasan_enable_current(void);
 /* Disable reporting bugs for current task */
 extern void kasan_disable_current(void);
 
-void kasan_unpoison_shadow(const void *address, size_t size);
+void kasan_unpoison_range(const void *address, size_t size);
 
 void kasan_unpoison_task_stack(struct task_struct *task);
 
@@ -109,7 +109,7 @@ struct kasan_cache {
 size_t __ksize(const void *);
 static inline void kasan_unpoison_slab(const void *ptr)
 {
-	kasan_unpoison_shadow(ptr, __ksize(ptr));
+	kasan_unpoison_range(ptr, __ksize(ptr));
 }
 size_t kasan_metadata_size(struct kmem_cache *cache);
 
@@ -118,7 +118,7 @@ void kasan_restore_multi_shot(bool enabled);
 
 #else /* CONFIG_KASAN */
 
-static inline void kasan_unpoison_shadow(const void *address, size_t size) {}
+static inline void kasan_unpoison_range(const void *address, size_t size) {}
 
 static inline void kasan_unpoison_task_stack(struct task_struct *task) {}
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 41906a52a764..37720a6d04ea 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -225,8 +225,8 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
 		if (!s)
 			continue;
 
-		/* Clear the KASAN shadow of the stack. */
-		kasan_unpoison_shadow(s->addr, THREAD_SIZE);
+		/* Mark stack accessible for KASAN. */
+		kasan_unpoison_range(s->addr, THREAD_SIZE);
 
 		/* Clear stale pointers from reused stack. */
 		memset(s->addr, 0, THREAD_SIZE);
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index 89e5ef9417a7..73e79a34671b 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -108,7 +108,7 @@ void *memcpy(void *dest, const void *src, size_t len)
  * Poisons the shadow memory for 'size' bytes starting from 'addr'.
  * Memory addresses should be aligned to KASAN_SHADOW_SCALE_SIZE.
  */
-void kasan_poison_shadow(const void *address, size_t size, u8 value)
+void poison_range(const void *address, size_t size, u8 value)
 {
 	void *shadow_start, *shadow_end;
 
@@ -125,7 +125,7 @@ void kasan_poison_shadow(const void *address, size_t size, u8 value)
 	__memset(shadow_start, value, shadow_end - shadow_start);
 }
 
-void kasan_unpoison_shadow(const void *address, size_t size)
+void unpoison_range(const void *address, size_t size)
 {
 	u8 tag = get_tag(address);
 
@@ -136,7 +136,7 @@ void kasan_unpoison_shadow(const void *address, size_t size)
 	 */
 	address = reset_tag(address);
 
-	kasan_poison_shadow(address, size, tag);
+	poison_range(address, size, tag);
 
 	if (size & KASAN_SHADOW_MASK) {
 		u8 *shadow = (u8 *)kasan_mem_to_shadow(address + size);
@@ -148,12 +148,17 @@ void kasan_unpoison_shadow(const void *address, size_t size)
 	}
 }
 
+void kasan_unpoison_range(const void *address, size_t size)
+{
+	unpoison_range(address, size);
+}
+
 static void __kasan_unpoison_stack(struct task_struct *task, const void *sp)
 {
 	void *base = task_stack_page(task);
 	size_t size = sp - base;
 
-	kasan_unpoison_shadow(base, size);
+	unpoison_range(base, size);
 }
 
 /* Unpoison the entire stack for a task. */
@@ -172,7 +177,7 @@ asmlinkage void kasan_unpoison_task_stack_below(const void *watermark)
 	 */
 	void *base = (void *)((unsigned long)watermark & ~(THREAD_SIZE - 1));
 
-	kasan_unpoison_shadow(base, watermark - base);
+	unpoison_range(base, watermark - base);
 }
 
 void kasan_alloc_pages(struct page *page, unsigned int order)
@@ -186,13 +191,13 @@ void kasan_alloc_pages(struct page *page, unsigned int order)
 	tag = random_tag();
 	for (i = 0; i < (1 << order); i++)
 		page_kasan_tag_set(page + i, tag);
-	kasan_unpoison_shadow(page_address(page), PAGE_SIZE << order);
+	unpoison_range(page_address(page), PAGE_SIZE << order);
 }
 
 void kasan_free_pages(struct page *page, unsigned int order)
 {
 	if (likely(!PageHighMem(page)))
-		kasan_poison_shadow(page_address(page),
+		poison_range(page_address(page),
 				PAGE_SIZE << order,
 				KASAN_FREE_PAGE);
 }
@@ -284,18 +289,18 @@ void kasan_poison_slab(struct page *page)
 
 	for (i = 0; i < compound_nr(page); i++)
 		page_kasan_tag_reset(page + i);
-	kasan_poison_shadow(page_address(page), page_size(page),
-			KASAN_KMALLOC_REDZONE);
+	poison_range(page_address(page), page_size(page),
+		     KASAN_KMALLOC_REDZONE);
 }
 
 void kasan_unpoison_object_data(struct kmem_cache *cache, void *object)
 {
-	kasan_unpoison_shadow(object, cache->object_size);
+	unpoison_range(object, cache->object_size);
 }
 
 void kasan_poison_object_data(struct kmem_cache *cache, void *object)
 {
-	kasan_poison_shadow(object,
+	poison_range(object,
 			round_up(cache->object_size, KASAN_SHADOW_SCALE_SIZE),
 			KASAN_KMALLOC_REDZONE);
 }
@@ -408,7 +413,7 @@ static bool __kasan_slab_free(struct kmem_cache *cache, void *object,
 	}
 
 	rounded_up_size = round_up(cache->object_size, KASAN_SHADOW_SCALE_SIZE);
-	kasan_poison_shadow(object, rounded_up_size, KASAN_KMALLOC_FREE);
+	poison_range(object, rounded_up_size, KASAN_KMALLOC_FREE);
 
 	if ((IS_ENABLED(CONFIG_KASAN_GENERIC) && !quarantine) ||
 			unlikely(!(cache->flags & SLAB_KASAN)))
@@ -448,9 +453,9 @@ static void *__kasan_kmalloc(struct kmem_cache *cache, const void *object,
 		tag = assign_tag(cache, object, false, keep_tag);
 
 	/* Tag is ignored in set_tag without CONFIG_KASAN_SW_TAGS */
-	kasan_unpoison_shadow(set_tag(object, tag), size);
-	kasan_poison_shadow((void *)redzone_start, redzone_end - redzone_start,
-		KASAN_KMALLOC_REDZONE);
+	unpoison_range(set_tag(object, tag), size);
+	poison_range((void *)redzone_start, redzone_end - redzone_start,
+		     KASAN_KMALLOC_REDZONE);
 
 	if (cache->flags & SLAB_KASAN)
 		kasan_set_track(&get_alloc_info(cache, object)->alloc_track, flags);
@@ -489,9 +494,9 @@ void * __must_check kasan_kmalloc_large(const void *ptr, size_t size,
 				KASAN_SHADOW_SCALE_SIZE);
 	redzone_end = (unsigned long)ptr + page_size(page);
 
-	kasan_unpoison_shadow(ptr, size);
-	kasan_poison_shadow((void *)redzone_start, redzone_end - redzone_start,
-		KASAN_PAGE_REDZONE);
+	unpoison_range(ptr, size);
+	poison_range((void *)redzone_start, redzone_end - redzone_start,
+		     KASAN_PAGE_REDZONE);
 
 	return (void *)ptr;
 }
@@ -523,7 +528,7 @@ void kasan_poison_kfree(void *ptr, unsigned long ip)
 			kasan_report_invalid_free(ptr, ip);
 			return;
 		}
-		kasan_poison_shadow(ptr, page_size(page), KASAN_FREE_PAGE);
+		poison_range(ptr, page_size(page), KASAN_FREE_PAGE);
 	} else {
 		__kasan_slab_free(page->slab_cache, ptr, ip, false);
 	}
@@ -709,7 +714,7 @@ int kasan_populate_vmalloc(unsigned long addr, unsigned long size)
 	 * // vmalloc() allocates memory
 	 * // let a = area->addr
 	 * // we reach kasan_populate_vmalloc
-	 * // and call kasan_unpoison_shadow:
+	 * // and call unpoison_range:
 	 * STORE shadow(a), unpoison_val
 	 * ...
 	 * STORE shadow(a+99), unpoison_val	x = LOAD p
@@ -744,7 +749,7 @@ void kasan_poison_vmalloc(const void *start, unsigned long size)
 		return;
 
 	size = round_up(size, KASAN_SHADOW_SCALE_SIZE);
-	kasan_poison_shadow(start, size, KASAN_VMALLOC_INVALID);
+	poison_range(start, size, KASAN_VMALLOC_INVALID);
 }
 
 void kasan_unpoison_vmalloc(const void *start, unsigned long size)
@@ -752,7 +757,7 @@ void kasan_unpoison_vmalloc(const void *start, unsigned long size)
 	if (!is_vmalloc_or_module_addr(start))
 		return;
 
-	kasan_unpoison_shadow(start, size);
+	unpoison_range(start, size);
 }
 
 static int kasan_depopulate_vmalloc_pte(pte_t *ptep, unsigned long addr,
diff --git a/mm/kasan/generic.c b/mm/kasan/generic.c
index d341859a1b95..9fe44f9b3b30 100644
--- a/mm/kasan/generic.c
+++ b/mm/kasan/generic.c
@@ -202,11 +202,11 @@ static void register_global(struct kasan_global *global)
 {
 	size_t aligned_size = round_up(global->size, KASAN_SHADOW_SCALE_SIZE);
 
-	kasan_unpoison_shadow(global->beg, global->size);
+	unpoison_range(global->beg, global->size);
 
-	kasan_poison_shadow(global->beg + aligned_size,
-		global->size_with_redzone - aligned_size,
-		KASAN_GLOBAL_REDZONE);
+	poison_range(global->beg + aligned_size,
+		     global->size_with_redzone - aligned_size,
+		     KASAN_GLOBAL_REDZONE);
 }
 
 void __asan_register_globals(struct kasan_global *globals, size_t size)
@@ -285,13 +285,12 @@ void __asan_alloca_poison(unsigned long addr, size_t size)
 
 	WARN_ON(!IS_ALIGNED(addr, KASAN_ALLOCA_REDZONE_SIZE));
 
-	kasan_unpoison_shadow((const void *)(addr + rounded_down_size),
-			      size - rounded_down_size);
-	kasan_poison_shadow(left_redzone, KASAN_ALLOCA_REDZONE_SIZE,
-			KASAN_ALLOCA_LEFT);
-	kasan_poison_shadow(right_redzone,
-			padding_size + KASAN_ALLOCA_REDZONE_SIZE,
-			KASAN_ALLOCA_RIGHT);
+	unpoison_range((const void *)(addr + rounded_down_size),
+		       size - rounded_down_size);
+	poison_range(left_redzone, KASAN_ALLOCA_REDZONE_SIZE,
+		     KASAN_ALLOCA_LEFT);
+	poison_range(right_redzone, padding_size + KASAN_ALLOCA_REDZONE_SIZE,
+		     KASAN_ALLOCA_RIGHT);
 }
 EXPORT_SYMBOL(__asan_alloca_poison);
 
@@ -301,7 +300,7 @@ void __asan_allocas_unpoison(const void *stack_top, const void *stack_bottom)
 	if (unlikely(!stack_top || stack_top > stack_bottom))
 		return;
 
-	kasan_unpoison_shadow(stack_top, stack_bottom - stack_top);
+	unpoison_range(stack_top, stack_bottom - stack_top);
 }
 EXPORT_SYMBOL(__asan_allocas_unpoison);
 
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index ac499456740f..42ab02c61331 100644
--- a/mm/kasan/kasan.h
+++ b/mm/kasan/kasan.h
@@ -150,7 +150,8 @@ static inline bool addr_has_shadow(const void *addr)
 	return (addr >= kasan_shadow_to_mem((void *)KASAN_SHADOW_START));
 }
 
-void kasan_poison_shadow(const void *address, size_t size, u8 value);
+void poison_range(const void *address, size_t size, u8 value);
+void unpoison_range(const void *address, size_t size);
 
 /**
  * check_memory_region - Check memory region, and report if invalid access.
diff --git a/mm/kasan/tags.c b/mm/kasan/tags.c
index 5c8b08a25715..c0b3f327812b 100644
--- a/mm/kasan/tags.c
+++ b/mm/kasan/tags.c
@@ -153,7 +153,7 @@ EXPORT_SYMBOL(__hwasan_storeN_noabort);
 
 void __hwasan_tag_memory(unsigned long addr, u8 tag, unsigned long size)
 {
-	kasan_poison_shadow((void *)addr, size, tag);
+	poison_range((void *)addr, size, tag);
 }
 EXPORT_SYMBOL(__hwasan_tag_memory);
 
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 2f2b55c2798e..573fbacd9ef5 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -1176,7 +1176,7 @@ size_t ksize(const void *objp)
 	 * We assume that ksize callers could use whole allocated area,
 	 * so we need to unpoison this area.
 	 */
-	kasan_unpoison_shadow(objp, size);
+	kasan_unpoison_range(objp, size);
 	return size;
 }
 EXPORT_SYMBOL(ksize);
-- 
cgit v1.2.3


From d73b49365ee65ac48074bdb5aa717bb4644dbbb7 Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Tue, 22 Dec 2020 12:00:56 -0800
Subject: kasan, arm64: only use kasan_depth for software modes

This is a preparatory commit for the upcoming addition of a new hardware
tag-based (MTE-based) KASAN mode.

Hardware tag-based KASAN won't use kasan_depth.  Only define and use it
when one of the software KASAN modes are enabled.

No functional changes for software modes.

Link: https://lkml.kernel.org/r/e16f15aeda90bc7fb4dfc2e243a14b74cc5c8219.1606161801.git.andreyknvl@google.com
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Alexander Potapenko <glider@google.com>
Tested-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Branislav Rankov <Branislav.Rankov@arm.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Kevin Brodsky <kevin.brodsky@arm.com>
Cc: Marco Elver <elver@google.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arm64/mm/kasan_init.c | 11 ++++++++---
 include/linux/kasan.h      | 18 +++++++++---------
 include/linux/sched.h      |  2 +-
 init/init_task.c           |  2 +-
 mm/kasan/common.c          |  2 ++
 mm/kasan/report.c          |  2 ++
 6 files changed, 23 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c
index ffeb80d5aa8d..5172799f831f 100644
--- a/arch/arm64/mm/kasan_init.c
+++ b/arch/arm64/mm/kasan_init.c
@@ -273,17 +273,22 @@ static void __init kasan_init_shadow(void)
 	cpu_replace_ttbr1(lm_alias(swapper_pg_dir));
 }
 
+static void __init kasan_init_depth(void)
+{
+	init_task.kasan_depth = 0;
+}
+
 #else /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS) */
 
 static inline void __init kasan_init_shadow(void) { }
 
+static inline void __init kasan_init_depth(void) { }
+
 #endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
 
 void __init kasan_init(void)
 {
 	kasan_init_shadow();
-
-	/* At this point kasan is fully initialized. Enable error messages */
-	init_task.kasan_depth = 0;
+	kasan_init_depth();
 	pr_info("KernelAddressSanitizer initialized\n");
 }
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 9740c06a04a1..b272960e8396 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -52,6 +52,12 @@ static inline void *kasan_mem_to_shadow(const void *addr)
 int kasan_add_zero_shadow(void *start, unsigned long size);
 void kasan_remove_zero_shadow(void *start, unsigned long size);
 
+/* Enable reporting bugs after kasan_disable_current() */
+extern void kasan_enable_current(void);
+
+/* Disable reporting bugs for current task */
+extern void kasan_disable_current(void);
+
 #else /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
 
 static inline int kasan_add_zero_shadow(void *start, unsigned long size)
@@ -62,16 +68,13 @@ static inline void kasan_remove_zero_shadow(void *start,
 					unsigned long size)
 {}
 
+static inline void kasan_enable_current(void) {}
+static inline void kasan_disable_current(void) {}
+
 #endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
 
 #ifdef CONFIG_KASAN
 
-/* Enable reporting bugs after kasan_disable_current() */
-extern void kasan_enable_current(void);
-
-/* Disable reporting bugs for current task */
-extern void kasan_disable_current(void);
-
 void kasan_unpoison_range(const void *address, size_t size);
 
 void kasan_unpoison_task_stack(struct task_struct *task);
@@ -122,9 +125,6 @@ static inline void kasan_unpoison_range(const void *address, size_t size) {}
 
 static inline void kasan_unpoison_task_stack(struct task_struct *task) {}
 
-static inline void kasan_enable_current(void) {}
-static inline void kasan_disable_current(void) {}
-
 static inline void kasan_alloc_pages(struct page *page, unsigned int order) {}
 static inline void kasan_free_pages(struct page *page, unsigned int order) {}
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 51d535b69bd6..6e3a5eeec509 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1234,7 +1234,7 @@ struct task_struct {
 	u64				timer_slack_ns;
 	u64				default_timer_slack_ns;
 
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 	unsigned int			kasan_depth;
 #endif
 
diff --git a/init/init_task.c b/init/init_task.c
index 15f6eb93a04f..8a992d73e6fb 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -176,7 +176,7 @@ struct task_struct init_task
 	.numa_group	= NULL,
 	.numa_faults	= NULL,
 #endif
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 	.kasan_depth	= 1,
 #endif
 #ifdef CONFIG_KCSAN
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index 663ffa71cd20..d5f23b2f170a 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -46,6 +46,7 @@ void kasan_set_track(struct kasan_track *track, gfp_t flags)
 	track->stack = kasan_save_stack(flags);
 }
 
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 void kasan_enable_current(void)
 {
 	current->kasan_depth++;
@@ -55,6 +56,7 @@ void kasan_disable_current(void)
 {
 	current->kasan_depth--;
 }
+#endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
 
 void kasan_unpoison_range(const void *address, size_t size)
 {
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index d140d26cfb31..914ab5cfc3ea 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -292,8 +292,10 @@ static void print_shadow_for_address(const void *addr)
 
 static bool report_enabled(void)
 {
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 	if (current->kasan_depth)
 		return false;
+#endif
 	if (test_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags))
 		return true;
 	return !test_and_set_bit(KASAN_BIT_REPORTED, &kasan_flags);
-- 
cgit v1.2.3


From 60a3a5fe950f4e6c02e9fc6676dc96de043ed743 Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Tue, 22 Dec 2020 12:01:03 -0800
Subject: kasan, arm64: rename kasan_init_tags and mark as __init

Rename kasan_init_tags() to kasan_init_sw_tags() as the upcoming hardware
tag-based KASAN mode will have its own initialization routine.  Also
similarly to kasan_init() mark kasan_init_tags() as __init.

Link: https://lkml.kernel.org/r/71e52af72a09f4b50c8042f16101c60e50649fbb.1606161801.git.andreyknvl@google.com
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Alexander Potapenko <glider@google.com>
Tested-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Branislav Rankov <Branislav.Rankov@arm.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Kevin Brodsky <kevin.brodsky@arm.com>
Cc: Marco Elver <elver@google.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arm64/kernel/setup.c  | 2 +-
 arch/arm64/mm/kasan_init.c | 2 +-
 include/linux/kasan.h      | 4 ++--
 mm/kasan/sw_tags.c         | 2 +-
 4 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index c44eb4b80163..c18aacde8bb0 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -358,7 +358,7 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p)
 	smp_build_mpidr_hash();
 
 	/* Init percpu seeds for random tags after cpus are set up. */
-	kasan_init_tags();
+	kasan_init_sw_tags();
 
 #ifdef CONFIG_ARM64_SW_TTBR0_PAN
 	/*
diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c
index e35ce04beed1..d8e66c78440e 100644
--- a/arch/arm64/mm/kasan_init.c
+++ b/arch/arm64/mm/kasan_init.c
@@ -283,7 +283,7 @@ void __init kasan_init(void)
 	kasan_init_shadow();
 	kasan_init_depth();
 #if defined(CONFIG_KASAN_GENERIC)
-	/* CONFIG_KASAN_SW_TAGS also requires kasan_init_tags(). */
+	/* CONFIG_KASAN_SW_TAGS also requires kasan_init_sw_tags(). */
 	pr_info("KernelAddressSanitizer initialized\n");
 #endif
 }
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index b272960e8396..d7042d129dc1 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -192,7 +192,7 @@ static inline void kasan_record_aux_stack(void *ptr) {}
 
 #ifdef CONFIG_KASAN_SW_TAGS
 
-void kasan_init_tags(void);
+void __init kasan_init_sw_tags(void);
 
 void *kasan_reset_tag(const void *addr);
 
@@ -201,7 +201,7 @@ bool kasan_report(unsigned long addr, size_t size,
 
 #else /* CONFIG_KASAN_SW_TAGS */
 
-static inline void kasan_init_tags(void) { }
+static inline void kasan_init_sw_tags(void) { }
 
 static inline void *kasan_reset_tag(const void *addr)
 {
diff --git a/mm/kasan/sw_tags.c b/mm/kasan/sw_tags.c
index 9445cf4ccdc8..7317d5229b2b 100644
--- a/mm/kasan/sw_tags.c
+++ b/mm/kasan/sw_tags.c
@@ -35,7 +35,7 @@
 
 static DEFINE_PER_CPU(u32, prng_state);
 
-void kasan_init_tags(void)
+void __init kasan_init_sw_tags(void)
 {
 	int cpu;
 
-- 
cgit v1.2.3


From 0fea6e9af889f1a4e072f5de999e07fe6859fc88 Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Tue, 22 Dec 2020 12:02:06 -0800
Subject: kasan, arm64: expand CONFIG_KASAN checks

Some #ifdef CONFIG_KASAN checks are only relevant for software KASAN modes
(either related to shadow memory or compiler instrumentation).  Expand
those into CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS.

Link: https://lkml.kernel.org/r/e6971e432dbd72bb897ff14134ebb7e169bdcf0c.1606161801.git.andreyknvl@google.com
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Alexander Potapenko <glider@google.com>
Tested-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Branislav Rankov <Branislav.Rankov@arm.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Kevin Brodsky <kevin.brodsky@arm.com>
Cc: Marco Elver <elver@google.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arm64/Kconfig                 |  2 +-
 arch/arm64/Makefile                |  2 +-
 arch/arm64/include/asm/assembler.h |  2 +-
 arch/arm64/include/asm/memory.h    |  2 +-
 arch/arm64/include/asm/string.h    |  5 +++--
 arch/arm64/kernel/head.S           |  2 +-
 arch/arm64/kernel/image-vars.h     |  2 +-
 arch/arm64/kernel/kaslr.c          |  3 ++-
 arch/arm64/kernel/module.c         |  6 ++++--
 arch/arm64/mm/ptdump.c             |  6 +++---
 include/linux/kasan-checks.h       |  2 +-
 include/linux/kasan.h              |  7 ++++---
 include/linux/moduleloader.h       |  3 ++-
 include/linux/string.h             |  2 +-
 mm/ptdump.c                        | 13 ++++++++-----
 scripts/Makefile.lib               |  2 ++
 16 files changed, 36 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index a33718f8b62f..9386b108b132 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -334,7 +334,7 @@ config BROKEN_GAS_INST
 
 config KASAN_SHADOW_OFFSET
 	hex
-	depends on KASAN
+	depends on KASAN_GENERIC || KASAN_SW_TAGS
 	default 0xdfff800000000000 if (ARM64_VA_BITS_48 || ARM64_VA_BITS_52) && !KASAN_SW_TAGS
 	default 0xdfffc00000000000 if ARM64_VA_BITS_47 && !KASAN_SW_TAGS
 	default 0xdffffe0000000000 if ARM64_VA_BITS_42 && !KASAN_SW_TAGS
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 05f46a60b245..6be9b3750250 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -137,7 +137,7 @@ head-y		:= arch/arm64/kernel/head.o
 
 ifeq ($(CONFIG_KASAN_SW_TAGS), y)
 KASAN_SHADOW_SCALE_SHIFT := 4
-else
+else ifeq ($(CONFIG_KASAN_GENERIC), y)
 KASAN_SHADOW_SCALE_SHIFT := 3
 endif
 
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index ddbe6bf00e33..bf125c591116 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -473,7 +473,7 @@ USER(\label, ic	ivau, \tmp2)			// invalidate I line PoU
 #define NOKPROBE(x)
 #endif
 
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 #define EXPORT_SYMBOL_NOKASAN(name)
 #else
 #define EXPORT_SYMBOL_NOKASAN(name)	EXPORT_SYMBOL(name)
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 3bc08e6cf82e..cd671fb6707c 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -72,7 +72,7 @@
  * address space for the shadow region respectively. They can bloat the stack
  * significantly, so double the (minimum) stack size when they are in use.
  */
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 #define KASAN_SHADOW_OFFSET	_AC(CONFIG_KASAN_SHADOW_OFFSET, UL)
 #define KASAN_SHADOW_END	((UL(1) << (64 - KASAN_SHADOW_SCALE_SHIFT)) \
 					+ KASAN_SHADOW_OFFSET)
diff --git a/arch/arm64/include/asm/string.h b/arch/arm64/include/asm/string.h
index b31e8e87a0db..3a3264ff47b9 100644
--- a/arch/arm64/include/asm/string.h
+++ b/arch/arm64/include/asm/string.h
@@ -5,7 +5,7 @@
 #ifndef __ASM_STRING_H
 #define __ASM_STRING_H
 
-#ifndef CONFIG_KASAN
+#if !(defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS))
 #define __HAVE_ARCH_STRRCHR
 extern char *strrchr(const char *, int c);
 
@@ -48,7 +48,8 @@ extern void *__memset(void *, int, __kernel_size_t);
 void memcpy_flushcache(void *dst, const void *src, size_t cnt);
 #endif
 
-#if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__)
+#if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \
+	!defined(__SANITIZE_ADDRESS__)
 
 /*
  * For files that are not instrumented (e.g. mm/slub.c) we
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 42b23ce679dc..a0dc987724ed 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -433,7 +433,7 @@ SYM_FUNC_START_LOCAL(__primary_switched)
 	bl	__pi_memset
 	dsb	ishst				// Make zero page visible to PTW
 
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 	bl	kasan_early_init
 #endif
 #ifdef CONFIG_RANDOMIZE_BASE
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index 39289d75118d..f676243abac6 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -37,7 +37,7 @@ __efistub_strncmp		= __pi_strncmp;
 __efistub_strrchr		= __pi_strrchr;
 __efistub___clean_dcache_area_poc = __pi___clean_dcache_area_poc;
 
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 __efistub___memcpy		= __pi_memcpy;
 __efistub___memmove		= __pi_memmove;
 __efistub___memset		= __pi_memset;
diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c
index 0921aa1520b0..1c74c45b9494 100644
--- a/arch/arm64/kernel/kaslr.c
+++ b/arch/arm64/kernel/kaslr.c
@@ -161,7 +161,8 @@ u64 __init kaslr_early_init(u64 dt_phys)
 	/* use the top 16 bits to randomize the linear region */
 	memstart_offset_seed = seed >> 48;
 
-	if (IS_ENABLED(CONFIG_KASAN))
+	if (IS_ENABLED(CONFIG_KASAN_GENERIC) ||
+	    IS_ENABLED(CONFIG_KASAN_SW_TAGS))
 		/*
 		 * KASAN does not expect the module region to intersect the
 		 * vmalloc region, since shadow memory is allocated for each
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index 2a1ad95d9b2c..fe21e0f06492 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -30,7 +30,8 @@ void *module_alloc(unsigned long size)
 	if (IS_ENABLED(CONFIG_ARM64_MODULE_PLTS))
 		gfp_mask |= __GFP_NOWARN;
 
-	if (IS_ENABLED(CONFIG_KASAN))
+	if (IS_ENABLED(CONFIG_KASAN_GENERIC) ||
+	    IS_ENABLED(CONFIG_KASAN_SW_TAGS))
 		/* don't exceed the static module region - see below */
 		module_alloc_end = MODULES_END;
 
@@ -39,7 +40,8 @@ void *module_alloc(unsigned long size)
 				NUMA_NO_NODE, __builtin_return_address(0));
 
 	if (!p && IS_ENABLED(CONFIG_ARM64_MODULE_PLTS) &&
-	    !IS_ENABLED(CONFIG_KASAN))
+	    !IS_ENABLED(CONFIG_KASAN_GENERIC) &&
+	    !IS_ENABLED(CONFIG_KASAN_SW_TAGS))
 		/*
 		 * KASAN can only deal with module allocations being served
 		 * from the reserved module region, since the remainder of
diff --git a/arch/arm64/mm/ptdump.c b/arch/arm64/mm/ptdump.c
index 807dc634bbd2..04137a8f3d2d 100644
--- a/arch/arm64/mm/ptdump.c
+++ b/arch/arm64/mm/ptdump.c
@@ -29,7 +29,7 @@
 enum address_markers_idx {
 	PAGE_OFFSET_NR = 0,
 	PAGE_END_NR,
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 	KASAN_START_NR,
 #endif
 };
@@ -37,7 +37,7 @@ enum address_markers_idx {
 static struct addr_marker address_markers[] = {
 	{ PAGE_OFFSET,			"Linear Mapping start" },
 	{ 0 /* PAGE_END */,		"Linear Mapping end" },
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 	{ 0 /* KASAN_SHADOW_START */,	"Kasan shadow start" },
 	{ KASAN_SHADOW_END,		"Kasan shadow end" },
 #endif
@@ -383,7 +383,7 @@ void ptdump_check_wx(void)
 static int ptdump_init(void)
 {
 	address_markers[PAGE_END_NR].start_address = PAGE_END;
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 	address_markers[KASAN_START_NR].start_address = KASAN_SHADOW_START;
 #endif
 	ptdump_initialize();
diff --git a/include/linux/kasan-checks.h b/include/linux/kasan-checks.h
index ac6aba632f2d..ca5e89fb10d3 100644
--- a/include/linux/kasan-checks.h
+++ b/include/linux/kasan-checks.h
@@ -9,7 +9,7 @@
  * even in compilation units that selectively disable KASAN, but must use KASAN
  * to validate access to an address.   Never use these in header files!
  */
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 bool __kasan_check_read(const volatile void *p, unsigned int size);
 bool __kasan_check_write(const volatile void *p, unsigned int size);
 #else
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index d7042d129dc1..b1381ee6922a 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -238,7 +238,8 @@ static inline void kasan_release_vmalloc(unsigned long start,
 
 #endif /* CONFIG_KASAN_VMALLOC */
 
-#if defined(CONFIG_KASAN) && !defined(CONFIG_KASAN_VMALLOC)
+#if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \
+		!defined(CONFIG_KASAN_VMALLOC)
 
 /*
  * These functions provide a special case to support backing module
@@ -248,12 +249,12 @@ static inline void kasan_release_vmalloc(unsigned long start,
 int kasan_module_alloc(void *addr, size_t size);
 void kasan_free_shadow(const struct vm_struct *vm);
 
-#else /* CONFIG_KASAN && !CONFIG_KASAN_VMALLOC */
+#else /* (CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS) && !CONFIG_KASAN_VMALLOC */
 
 static inline int kasan_module_alloc(void *addr, size_t size) { return 0; }
 static inline void kasan_free_shadow(const struct vm_struct *vm) {}
 
-#endif /* CONFIG_KASAN && !CONFIG_KASAN_VMALLOC */
+#endif /* (CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS) && !CONFIG_KASAN_VMALLOC */
 
 #ifdef CONFIG_KASAN_INLINE
 void kasan_non_canonical_hook(unsigned long addr);
diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h
index 4fa67a8b2265..9e09d11ffe5b 100644
--- a/include/linux/moduleloader.h
+++ b/include/linux/moduleloader.h
@@ -96,7 +96,8 @@ void module_arch_cleanup(struct module *mod);
 /* Any cleanup before freeing mod->module_init */
 void module_arch_freeing_init(struct module *mod);
 
-#if defined(CONFIG_KASAN) && !defined(CONFIG_KASAN_VMALLOC)
+#if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \
+		!defined(CONFIG_KASAN_VMALLOC)
 #include <linux/kasan.h>
 #define MODULE_ALIGN (PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT)
 #else
diff --git a/include/linux/string.h b/include/linux/string.h
index 1cd63a8a23ab..4fcfb56abcf5 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -267,7 +267,7 @@ void __write_overflow(void) __compiletime_error("detected write beyond size of o
 
 #if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE)
 
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 extern void *__underlying_memchr(const void *p, int c, __kernel_size_t size) __RENAME(memchr);
 extern int __underlying_memcmp(const void *p, const void *q, __kernel_size_t size) __RENAME(memcmp);
 extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy);
diff --git a/mm/ptdump.c b/mm/ptdump.c
index ba88ec43ff21..4354c1422d57 100644
--- a/mm/ptdump.c
+++ b/mm/ptdump.c
@@ -4,7 +4,7 @@
 #include <linux/ptdump.h>
 #include <linux/kasan.h>
 
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 /*
  * This is an optimization for KASAN=y case. Since all kasan page tables
  * eventually point to the kasan_early_shadow_page we could call note_page()
@@ -31,7 +31,8 @@ static int ptdump_pgd_entry(pgd_t *pgd, unsigned long addr,
 	struct ptdump_state *st = walk->private;
 	pgd_t val = READ_ONCE(*pgd);
 
-#if CONFIG_PGTABLE_LEVELS > 4 && defined(CONFIG_KASAN)
+#if CONFIG_PGTABLE_LEVELS > 4 && \
+		(defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS))
 	if (pgd_page(val) == virt_to_page(lm_alias(kasan_early_shadow_p4d)))
 		return note_kasan_page_table(walk, addr);
 #endif
@@ -51,7 +52,8 @@ static int ptdump_p4d_entry(p4d_t *p4d, unsigned long addr,
 	struct ptdump_state *st = walk->private;
 	p4d_t val = READ_ONCE(*p4d);
 
-#if CONFIG_PGTABLE_LEVELS > 3 && defined(CONFIG_KASAN)
+#if CONFIG_PGTABLE_LEVELS > 3 && \
+		(defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS))
 	if (p4d_page(val) == virt_to_page(lm_alias(kasan_early_shadow_pud)))
 		return note_kasan_page_table(walk, addr);
 #endif
@@ -71,7 +73,8 @@ static int ptdump_pud_entry(pud_t *pud, unsigned long addr,
 	struct ptdump_state *st = walk->private;
 	pud_t val = READ_ONCE(*pud);
 
-#if CONFIG_PGTABLE_LEVELS > 2 && defined(CONFIG_KASAN)
+#if CONFIG_PGTABLE_LEVELS > 2 && \
+		(defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS))
 	if (pud_page(val) == virt_to_page(lm_alias(kasan_early_shadow_pmd)))
 		return note_kasan_page_table(walk, addr);
 #endif
@@ -91,7 +94,7 @@ static int ptdump_pmd_entry(pmd_t *pmd, unsigned long addr,
 	struct ptdump_state *st = walk->private;
 	pmd_t val = READ_ONCE(*pmd);
 
-#if defined(CONFIG_KASAN)
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 	if (pmd_page(val) == virt_to_page(lm_alias(kasan_early_shadow_pte)))
 		return note_kasan_page_table(walk, addr);
 #endif
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 94133708889d..213677a5ed33 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -148,10 +148,12 @@ endif
 # we don't want to check (depends on variables KASAN_SANITIZE_obj.o, KASAN_SANITIZE)
 #
 ifeq ($(CONFIG_KASAN),y)
+ifneq ($(CONFIG_KASAN_HW_TAGS),y)
 _c_flags += $(if $(patsubst n%,, \
 		$(KASAN_SANITIZE_$(basetarget).o)$(KASAN_SANITIZE)y), \
 		$(CFLAGS_KASAN), $(CFLAGS_KASAN_NOSANITIZE))
 endif
+endif
 
 ifeq ($(CONFIG_UBSAN),y)
 _c_flags += $(if $(patsubst n%,, \
-- 
cgit v1.2.3


From 2e903b91479782b7dedd869603423d77e079d3de Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Tue, 22 Dec 2020 12:02:10 -0800
Subject: kasan, arm64: implement HW_TAGS runtime

Provide implementation of KASAN functions required for the hardware
tag-based mode.  Those include core functions for memory and pointer
tagging (tags_hw.c) and bug reporting (report_tags_hw.c).  Also adapt
common KASAN code to support the new mode.

Link: https://lkml.kernel.org/r/cfd0fbede579a6b66755c98c88c108e54f9c56bf.1606161801.git.andreyknvl@google.com
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Alexander Potapenko <glider@google.com>
Tested-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Branislav Rankov <Branislav.Rankov@arm.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Kevin Brodsky <kevin.brodsky@arm.com>
Cc: Marco Elver <elver@google.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arm64/include/asm/memory.h   |  4 +-
 arch/arm64/kernel/cpufeature.c    |  3 ++
 arch/arm64/kernel/smp.c           |  2 +
 include/linux/kasan.h             | 24 ++++++++----
 include/linux/mm.h                |  2 +-
 include/linux/page-flags-layout.h |  2 +-
 mm/kasan/Makefile                 |  5 +++
 mm/kasan/common.c                 | 15 ++++----
 mm/kasan/hw_tags.c                | 80 +++++++++++++++++++++++++++++++++++++++
 mm/kasan/kasan.h                  | 19 ++++++++--
 mm/kasan/report_hw_tags.c         | 42 ++++++++++++++++++++
 mm/kasan/report_sw_tags.c         |  2 +-
 mm/kasan/shadow.c                 |  2 +-
 mm/kasan/sw_tags.c                |  2 +-
 14 files changed, 178 insertions(+), 26 deletions(-)
 create mode 100644 mm/kasan/hw_tags.c
 create mode 100644 mm/kasan/report_hw_tags.c

(limited to 'include/linux')

diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index cd671fb6707c..18fce223b67b 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -214,7 +214,7 @@ static inline unsigned long kaslr_offset(void)
 	(__force __typeof__(addr))__addr;				\
 })
 
-#ifdef CONFIG_KASAN_SW_TAGS
+#if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS)
 #define __tag_shifted(tag)	((u64)(tag) << 56)
 #define __tag_reset(addr)	__untagged_addr(addr)
 #define __tag_get(addr)		(__u8)((u64)(addr) >> 56)
@@ -222,7 +222,7 @@ static inline unsigned long kaslr_offset(void)
 #define __tag_shifted(tag)	0UL
 #define __tag_reset(addr)	(addr)
 #define __tag_get(addr)		0
-#endif /* CONFIG_KASAN_SW_TAGS */
+#endif /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */
 
 static inline const void *__tag_set(const void *addr, u8 tag)
 {
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index d87cfc6246e0..7ffb5f1d8b68 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -70,6 +70,7 @@
 #include <linux/types.h>
 #include <linux/mm.h>
 #include <linux/cpu.h>
+#include <linux/kasan.h>
 #include <asm/cpu.h>
 #include <asm/cpufeature.h>
 #include <asm/cpu_ops.h>
@@ -1710,6 +1711,8 @@ static void cpu_enable_mte(struct arm64_cpu_capabilities const *cap)
 		cleared_zero_page = true;
 		mte_clear_page_tags(lm_alias(empty_zero_page));
 	}
+
+	kasan_init_hw_tags_cpu();
 }
 #endif /* CONFIG_ARM64_MTE */
 
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 2499b895efea..19b1705ae5cb 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -462,6 +462,8 @@ void __init smp_prepare_boot_cpu(void)
 	/* Conditionally switch to GIC PMR for interrupt masking */
 	if (system_uses_irq_prio_masking())
 		init_gic_priority_masking();
+
+	kasan_init_hw_tags();
 }
 
 static u64 __init of_get_cpu_mpidr(struct device_node *dn)
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index b1381ee6922a..d22ec4c9c1bd 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -190,25 +190,35 @@ static inline void kasan_record_aux_stack(void *ptr) {}
 
 #endif /* CONFIG_KASAN_GENERIC */
 
-#ifdef CONFIG_KASAN_SW_TAGS
-
-void __init kasan_init_sw_tags(void);
+#if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS)
 
 void *kasan_reset_tag(const void *addr);
 
 bool kasan_report(unsigned long addr, size_t size,
 		bool is_write, unsigned long ip);
 
-#else /* CONFIG_KASAN_SW_TAGS */
-
-static inline void kasan_init_sw_tags(void) { }
+#else /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */
 
 static inline void *kasan_reset_tag(const void *addr)
 {
 	return (void *)addr;
 }
 
-#endif /* CONFIG_KASAN_SW_TAGS */
+#endif /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS*/
+
+#ifdef CONFIG_KASAN_SW_TAGS
+void __init kasan_init_sw_tags(void);
+#else
+static inline void kasan_init_sw_tags(void) { }
+#endif
+
+#ifdef CONFIG_KASAN_HW_TAGS
+void kasan_init_hw_tags_cpu(void);
+void __init kasan_init_hw_tags(void);
+#else
+static inline void kasan_init_hw_tags_cpu(void) { }
+static inline void kasan_init_hw_tags(void) { }
+#endif
 
 #ifdef CONFIG_KASAN_VMALLOC
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 362579ad0758..024ec0a00c72 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1421,7 +1421,7 @@ static inline bool cpupid_match_pid(struct task_struct *task, int cpupid)
 }
 #endif /* CONFIG_NUMA_BALANCING */
 
-#ifdef CONFIG_KASAN_SW_TAGS
+#if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS)
 static inline u8 page_kasan_tag(const struct page *page)
 {
 	return (page->flags >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK;
diff --git a/include/linux/page-flags-layout.h b/include/linux/page-flags-layout.h
index e200eef6a7fd..7d4ec26d8a3e 100644
--- a/include/linux/page-flags-layout.h
+++ b/include/linux/page-flags-layout.h
@@ -77,7 +77,7 @@
 #define LAST_CPUPID_SHIFT 0
 #endif
 
-#ifdef CONFIG_KASAN_SW_TAGS
+#if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS)
 #define KASAN_TAG_WIDTH 8
 #else
 #define KASAN_TAG_WIDTH 0
diff --git a/mm/kasan/Makefile b/mm/kasan/Makefile
index f1d68a34f3c9..9fe39a66388a 100644
--- a/mm/kasan/Makefile
+++ b/mm/kasan/Makefile
@@ -10,8 +10,10 @@ CFLAGS_REMOVE_init.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_quarantine.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_report.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_report_generic.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_report_hw_tags.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_report_sw_tags.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_shadow.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_hw_tags.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_sw_tags.o = $(CC_FLAGS_FTRACE)
 
 # Function splitter causes unnecessary splits in __asan_load1/__asan_store1
@@ -27,10 +29,13 @@ CFLAGS_init.o := $(CC_FLAGS_KASAN_RUNTIME)
 CFLAGS_quarantine.o := $(CC_FLAGS_KASAN_RUNTIME)
 CFLAGS_report.o := $(CC_FLAGS_KASAN_RUNTIME)
 CFLAGS_report_generic.o := $(CC_FLAGS_KASAN_RUNTIME)
+CFLAGS_report_hw_tags.o := $(CC_FLAGS_KASAN_RUNTIME)
 CFLAGS_report_sw_tags.o := $(CC_FLAGS_KASAN_RUNTIME)
 CFLAGS_shadow.o := $(CC_FLAGS_KASAN_RUNTIME)
+CFLAGS_hw_tags.o := $(CC_FLAGS_KASAN_RUNTIME)
 CFLAGS_sw_tags.o := $(CC_FLAGS_KASAN_RUNTIME)
 
 obj-$(CONFIG_KASAN) := common.o report.o
 obj-$(CONFIG_KASAN_GENERIC) += init.o generic.o report_generic.o shadow.o quarantine.o
+obj-$(CONFIG_KASAN_HW_TAGS) += hw_tags.o report_hw_tags.o
 obj-$(CONFIG_KASAN_SW_TAGS) += init.o report_sw_tags.o shadow.o sw_tags.o
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index d5f23b2f170a..02613883846e 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -118,7 +118,7 @@ void kasan_free_pages(struct page *page, unsigned int order)
  */
 static inline unsigned int optimal_redzone(unsigned int object_size)
 {
-	if (IS_ENABLED(CONFIG_KASAN_SW_TAGS))
+	if (!IS_ENABLED(CONFIG_KASAN_GENERIC))
 		return 0;
 
 	return
@@ -183,14 +183,14 @@ size_t kasan_metadata_size(struct kmem_cache *cache)
 struct kasan_alloc_meta *get_alloc_info(struct kmem_cache *cache,
 					const void *object)
 {
-	return (void *)object + cache->kasan_info.alloc_meta_offset;
+	return (void *)reset_tag(object) + cache->kasan_info.alloc_meta_offset;
 }
 
 struct kasan_free_meta *get_free_info(struct kmem_cache *cache,
 				      const void *object)
 {
 	BUILD_BUG_ON(sizeof(struct kasan_free_meta) > 32);
-	return (void *)object + cache->kasan_info.free_meta_offset;
+	return (void *)reset_tag(object) + cache->kasan_info.free_meta_offset;
 }
 
 void kasan_poison_slab(struct page *page)
@@ -272,9 +272,8 @@ void * __must_check kasan_init_slab_obj(struct kmem_cache *cache,
 	alloc_info = get_alloc_info(cache, object);
 	__memset(alloc_info, 0, sizeof(*alloc_info));
 
-	if (IS_ENABLED(CONFIG_KASAN_SW_TAGS))
-		object = set_tag(object,
-				assign_tag(cache, object, true, false));
+	if (IS_ENABLED(CONFIG_KASAN_SW_TAGS) || IS_ENABLED(CONFIG_KASAN_HW_TAGS))
+		object = set_tag(object, assign_tag(cache, object, true, false));
 
 	return (void *)object;
 }
@@ -342,10 +341,10 @@ static void *__kasan_kmalloc(struct kmem_cache *cache, const void *object,
 	redzone_end = round_up((unsigned long)object + cache->object_size,
 				KASAN_GRANULE_SIZE);
 
-	if (IS_ENABLED(CONFIG_KASAN_SW_TAGS))
+	if (IS_ENABLED(CONFIG_KASAN_SW_TAGS) || IS_ENABLED(CONFIG_KASAN_HW_TAGS))
 		tag = assign_tag(cache, object, false, keep_tag);
 
-	/* Tag is ignored in set_tag without CONFIG_KASAN_SW_TAGS */
+	/* Tag is ignored in set_tag without CONFIG_KASAN_SW/HW_TAGS */
 	unpoison_range(set_tag(object, tag), size);
 	poison_range((void *)redzone_start, redzone_end - redzone_start,
 		     KASAN_KMALLOC_REDZONE);
diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c
new file mode 100644
index 000000000000..66419e908e21
--- /dev/null
+++ b/mm/kasan/hw_tags.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This file contains core hardware tag-based KASAN code.
+ *
+ * Copyright (c) 2020 Google, Inc.
+ * Author: Andrey Konovalov <andreyknvl@google.com>
+ */
+
+#define pr_fmt(fmt) "kasan: " fmt
+
+#include <linux/kasan.h>
+#include <linux/kernel.h>
+#include <linux/memory.h>
+#include <linux/mm.h>
+#include <linux/string.h>
+#include <linux/types.h>
+
+#include "kasan.h"
+
+/* kasan_init_hw_tags_cpu() is called for each CPU. */
+void kasan_init_hw_tags_cpu(void)
+{
+	hw_init_tags(KASAN_TAG_MAX);
+	hw_enable_tagging();
+}
+
+/* kasan_init_hw_tags() is called once on boot CPU. */
+void __init kasan_init_hw_tags(void)
+{
+	pr_info("KernelAddressSanitizer initialized\n");
+}
+
+void *kasan_reset_tag(const void *addr)
+{
+	return reset_tag(addr);
+}
+
+void poison_range(const void *address, size_t size, u8 value)
+{
+	hw_set_mem_tag_range(reset_tag(address),
+			round_up(size, KASAN_GRANULE_SIZE), value);
+}
+
+void unpoison_range(const void *address, size_t size)
+{
+	hw_set_mem_tag_range(reset_tag(address),
+			round_up(size, KASAN_GRANULE_SIZE), get_tag(address));
+}
+
+u8 random_tag(void)
+{
+	return hw_get_random_tag();
+}
+
+bool check_invalid_free(void *addr)
+{
+	u8 ptr_tag = get_tag(addr);
+	u8 mem_tag = hw_get_mem_tag(addr);
+
+	return (mem_tag == KASAN_TAG_INVALID) ||
+		(ptr_tag != KASAN_TAG_KERNEL && ptr_tag != mem_tag);
+}
+
+void kasan_set_free_info(struct kmem_cache *cache,
+				void *object, u8 tag)
+{
+	struct kasan_alloc_meta *alloc_meta;
+
+	alloc_meta = get_alloc_info(cache, object);
+	kasan_set_track(&alloc_meta->free_track[0], GFP_NOWAIT);
+}
+
+struct kasan_track *kasan_get_free_track(struct kmem_cache *cache,
+				void *object, u8 tag)
+{
+	struct kasan_alloc_meta *alloc_meta;
+
+	alloc_meta = get_alloc_info(cache, object);
+	return &alloc_meta->free_track[0];
+}
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index 92cb2c16e314..64560cc71191 100644
--- a/mm/kasan/kasan.h
+++ b/mm/kasan/kasan.h
@@ -154,6 +154,11 @@ struct kasan_alloc_meta *get_alloc_info(struct kmem_cache *cache,
 struct kasan_free_meta *get_free_info(struct kmem_cache *cache,
 					const void *object);
 
+void poison_range(const void *address, size_t size, u8 value);
+void unpoison_range(const void *address, size_t size);
+
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
+
 static inline const void *kasan_shadow_to_mem(const void *shadow_addr)
 {
 	return (void *)(((unsigned long)shadow_addr - KASAN_SHADOW_OFFSET)
@@ -165,9 +170,6 @@ static inline bool addr_has_metadata(const void *addr)
 	return (addr >= kasan_shadow_to_mem((void *)KASAN_SHADOW_START));
 }
 
-void poison_range(const void *address, size_t size, u8 value);
-void unpoison_range(const void *address, size_t size);
-
 /**
  * check_memory_region - Check memory region, and report if invalid access.
  * @addr: the accessed address
@@ -179,6 +181,15 @@ void unpoison_range(const void *address, size_t size);
 bool check_memory_region(unsigned long addr, size_t size, bool write,
 				unsigned long ret_ip);
 
+#else /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
+
+static inline bool addr_has_metadata(const void *addr)
+{
+	return true;
+}
+
+#endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
+
 bool check_invalid_free(void *addr);
 
 void *find_first_bad_addr(void *addr, size_t size);
@@ -215,7 +226,7 @@ static inline void quarantine_reduce(void) { }
 static inline void quarantine_remove_cache(struct kmem_cache *cache) { }
 #endif
 
-#ifdef CONFIG_KASAN_SW_TAGS
+#if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS)
 
 void print_tags(u8 addr_tag, const void *addr);
 
diff --git a/mm/kasan/report_hw_tags.c b/mm/kasan/report_hw_tags.c
new file mode 100644
index 000000000000..da543eb832cd
--- /dev/null
+++ b/mm/kasan/report_hw_tags.c
@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This file contains hardware tag-based KASAN specific error reporting code.
+ *
+ * Copyright (c) 2020 Google, Inc.
+ * Author: Andrey Konovalov <andreyknvl@google.com>
+ */
+
+#include <linux/kasan.h>
+#include <linux/kernel.h>
+#include <linux/memory.h>
+#include <linux/mm.h>
+#include <linux/string.h>
+#include <linux/types.h>
+
+#include "kasan.h"
+
+const char *get_bug_type(struct kasan_access_info *info)
+{
+	return "invalid-access";
+}
+
+void *find_first_bad_addr(void *addr, size_t size)
+{
+	return reset_tag(addr);
+}
+
+void metadata_fetch_row(char *buffer, void *row)
+{
+	int i;
+
+	for (i = 0; i < META_BYTES_PER_ROW; i++)
+		buffer[i] = hw_get_mem_tag(row + i * KASAN_GRANULE_SIZE);
+}
+
+void print_tags(u8 addr_tag, const void *addr)
+{
+	u8 memory_tag = hw_get_mem_tag((void *)addr);
+
+	pr_err("Pointer tag: [%02x], memory tag: [%02x]\n",
+		addr_tag, memory_tag);
+}
diff --git a/mm/kasan/report_sw_tags.c b/mm/kasan/report_sw_tags.c
index add2dfe6169c..aebc44a29e83 100644
--- a/mm/kasan/report_sw_tags.c
+++ b/mm/kasan/report_sw_tags.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * This file contains tag-based KASAN specific error reporting code.
+ * This file contains software tag-based KASAN specific error reporting code.
  *
  * Copyright (c) 2014 Samsung Electronics Co., Ltd.
  * Author: Andrey Ryabinin <ryabinin.a.a@gmail.com>
diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c
index ba84e5106585..ac6a5f57df33 100644
--- a/mm/kasan/shadow.c
+++ b/mm/kasan/shadow.c
@@ -107,7 +107,7 @@ void unpoison_range(const void *address, size_t size)
 
 		if (IS_ENABLED(CONFIG_KASAN_SW_TAGS))
 			*shadow = tag;
-		else
+		else /* CONFIG_KASAN_GENERIC */
 			*shadow = size & KASAN_GRANULE_MASK;
 	}
 }
diff --git a/mm/kasan/sw_tags.c b/mm/kasan/sw_tags.c
index 7317d5229b2b..a518483f3965 100644
--- a/mm/kasan/sw_tags.c
+++ b/mm/kasan/sw_tags.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * This file contains core tag-based KASAN code.
+ * This file contains core software tag-based KASAN code.
  *
  * Copyright (c) 2018 Google, Inc.
  * Author: Andrey Konovalov <andreyknvl@google.com>
-- 
cgit v1.2.3


From d56a9ef84bd0e1e8fba7a837ab12a4ec8476579f Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Tue, 22 Dec 2020 12:02:42 -0800
Subject: kasan, arm64: unpoison stack only with CONFIG_KASAN_STACK

There's a config option CONFIG_KASAN_STACK that has to be enabled for
KASAN to use stack instrumentation and perform validity checks for
stack variables.

There's no need to unpoison stack when CONFIG_KASAN_STACK is not enabled.
Only call kasan_unpoison_task_stack[_below]() when CONFIG_KASAN_STACK is
enabled.

Note, that CONFIG_KASAN_STACK is an option that is currently always
defined when CONFIG_KASAN is enabled, and therefore has to be tested
with #if instead of #ifdef.

Link: https://lkml.kernel.org/r/d09dd3f8abb388da397fd11598c5edeaa83fe559.1606162397.git.andreyknvl@google.com
Link: https://linux-review.googlesource.com/id/If8a891e9fe01ea543e00b576852685afec0887e3
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Reviewed-by: Marco Elver <elver@google.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Dmitry Vyukov <dvyukov@google.com>
Tested-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Branislav Rankov <Branislav.Rankov@arm.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Kevin Brodsky <kevin.brodsky@arm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arm64/kernel/sleep.S        |  2 +-
 arch/x86/kernel/acpi/wakeup_64.S |  2 +-
 include/linux/kasan.h            | 10 ++++++----
 mm/kasan/common.c                |  2 ++
 4 files changed, 10 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index 4be7f7eed875..6bdef7362c0e 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -133,7 +133,7 @@ SYM_FUNC_START(_cpu_resume)
 	 */
 	bl	cpu_do_resume
 
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN) && CONFIG_KASAN_STACK
 	mov	x0, sp
 	bl	kasan_unpoison_task_stack_below
 #endif
diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index c8daa92f38dc..5d3a0b8fd379 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -112,7 +112,7 @@ SYM_FUNC_START(do_suspend_lowlevel)
 	movq	pt_regs_r14(%rax), %r14
 	movq	pt_regs_r15(%rax), %r15
 
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN) && CONFIG_KASAN_STACK
 	/*
 	 * The suspend path may have poisoned some areas deeper in the stack,
 	 * which we now need to unpoison.
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index d22ec4c9c1bd..e638255ce906 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -77,8 +77,6 @@ static inline void kasan_disable_current(void) {}
 
 void kasan_unpoison_range(const void *address, size_t size);
 
-void kasan_unpoison_task_stack(struct task_struct *task);
-
 void kasan_alloc_pages(struct page *page, unsigned int order);
 void kasan_free_pages(struct page *page, unsigned int order);
 
@@ -123,8 +121,6 @@ void kasan_restore_multi_shot(bool enabled);
 
 static inline void kasan_unpoison_range(const void *address, size_t size) {}
 
-static inline void kasan_unpoison_task_stack(struct task_struct *task) {}
-
 static inline void kasan_alloc_pages(struct page *page, unsigned int order) {}
 static inline void kasan_free_pages(struct page *page, unsigned int order) {}
 
@@ -176,6 +172,12 @@ static inline size_t kasan_metadata_size(struct kmem_cache *cache) { return 0; }
 
 #endif /* CONFIG_KASAN */
 
+#if defined(CONFIG_KASAN) && CONFIG_KASAN_STACK
+void kasan_unpoison_task_stack(struct task_struct *task);
+#else
+static inline void kasan_unpoison_task_stack(struct task_struct *task) {}
+#endif
+
 #ifdef CONFIG_KASAN_GENERIC
 
 void kasan_cache_shrink(struct kmem_cache *cache);
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index 6c38fd0a9e5c..2754ce0c8334 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -63,6 +63,7 @@ void kasan_unpoison_range(const void *address, size_t size)
 	unpoison_range(address, size);
 }
 
+#if CONFIG_KASAN_STACK
 static void __kasan_unpoison_stack(struct task_struct *task, const void *sp)
 {
 	void *base = task_stack_page(task);
@@ -89,6 +90,7 @@ asmlinkage void kasan_unpoison_task_stack_below(const void *watermark)
 
 	unpoison_range(base, watermark - base);
 }
+#endif /* CONFIG_KASAN_STACK */
 
 void kasan_alloc_pages(struct page *page, unsigned int order)
 {
-- 
cgit v1.2.3


From c0054c565ae598073d6c27762c7d4f7de49a45d9 Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Tue, 22 Dec 2020 12:02:52 -0800
Subject: kasan: inline kasan_reset_tag for tag-based modes

Using kasan_reset_tag() currently results in a function call. As it's
called quite often from the allocator code, this leads to a noticeable
slowdown. Move it to include/linux/kasan.h and turn it into a static
inline function. Also remove the now unneeded reset_tag() internal KASAN
macro and use kasan_reset_tag() instead.

Link: https://lkml.kernel.org/r/6940383a3a9dfb416134d338d8fac97a9ebb8686.1606162397.git.andreyknvl@google.com
Link: https://linux-review.googlesource.com/id/I4d2061acfe91d480a75df00b07c22d8494ef14b5
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Reviewed-by: Marco Elver <elver@google.com>
Reviewed-by: Dmitry Vyukov <dvyukov@google.com>
Tested-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Branislav Rankov <Branislav.Rankov@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Kevin Brodsky <kevin.brodsky@arm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kasan.h     | 5 ++++-
 mm/kasan/common.c         | 6 +++---
 mm/kasan/hw_tags.c        | 9 ++-------
 mm/kasan/kasan.h          | 4 ----
 mm/kasan/report.c         | 4 ++--
 mm/kasan/report_hw_tags.c | 2 +-
 mm/kasan/report_sw_tags.c | 4 ++--
 mm/kasan/shadow.c         | 4 ++--
 mm/kasan/sw_tags.c        | 9 ++-------
 9 files changed, 18 insertions(+), 29 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index e638255ce906..3bb72de94f90 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -194,7 +194,10 @@ static inline void kasan_record_aux_stack(void *ptr) {}
 
 #if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS)
 
-void *kasan_reset_tag(const void *addr);
+static inline void *kasan_reset_tag(const void *addr)
+{
+	return (void *)arch_kasan_reset_tag(addr);
+}
 
 bool kasan_report(unsigned long addr, size_t size,
 		bool is_write, unsigned long ip);
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index b71dfe7c5059..780ec27459ab 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -179,14 +179,14 @@ size_t kasan_metadata_size(struct kmem_cache *cache)
 struct kasan_alloc_meta *kasan_get_alloc_meta(struct kmem_cache *cache,
 					      const void *object)
 {
-	return (void *)reset_tag(object) + cache->kasan_info.alloc_meta_offset;
+	return kasan_reset_tag(object) + cache->kasan_info.alloc_meta_offset;
 }
 
 struct kasan_free_meta *kasan_get_free_meta(struct kmem_cache *cache,
 					    const void *object)
 {
 	BUILD_BUG_ON(sizeof(struct kasan_free_meta) > 32);
-	return (void *)reset_tag(object) + cache->kasan_info.free_meta_offset;
+	return kasan_reset_tag(object) + cache->kasan_info.free_meta_offset;
 }
 
 void kasan_poison_slab(struct page *page)
@@ -283,7 +283,7 @@ static bool __kasan_slab_free(struct kmem_cache *cache, void *object,
 
 	tag = get_tag(object);
 	tagged_object = object;
-	object = reset_tag(object);
+	object = kasan_reset_tag(object);
 
 	if (unlikely(nearest_obj(cache, virt_to_head_page(object), object) !=
 	    object)) {
diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c
index cb849c8da978..227599e54e8e 100644
--- a/mm/kasan/hw_tags.c
+++ b/mm/kasan/hw_tags.c
@@ -30,20 +30,15 @@ void __init kasan_init_hw_tags(void)
 	pr_info("KernelAddressSanitizer initialized\n");
 }
 
-void *kasan_reset_tag(const void *addr)
-{
-	return reset_tag(addr);
-}
-
 void poison_range(const void *address, size_t size, u8 value)
 {
-	hw_set_mem_tag_range(reset_tag(address),
+	hw_set_mem_tag_range(kasan_reset_tag(address),
 			round_up(size, KASAN_GRANULE_SIZE), value);
 }
 
 void unpoison_range(const void *address, size_t size)
 {
-	hw_set_mem_tag_range(reset_tag(address),
+	hw_set_mem_tag_range(kasan_reset_tag(address),
 			round_up(size, KASAN_GRANULE_SIZE), get_tag(address));
 }
 
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index 0eab7e4cecb8..5e8cd2080369 100644
--- a/mm/kasan/kasan.h
+++ b/mm/kasan/kasan.h
@@ -248,15 +248,11 @@ static inline const void *arch_kasan_set_tag(const void *addr, u8 tag)
 	return addr;
 }
 #endif
-#ifndef arch_kasan_reset_tag
-#define arch_kasan_reset_tag(addr)	((void *)(addr))
-#endif
 #ifndef arch_kasan_get_tag
 #define arch_kasan_get_tag(addr)	0
 #endif
 
 #define set_tag(addr, tag)	((void *)arch_kasan_set_tag((addr), (tag)))
-#define reset_tag(addr)		((void *)arch_kasan_reset_tag(addr))
 #define get_tag(addr)		arch_kasan_get_tag(addr)
 
 #ifdef CONFIG_KASAN_HW_TAGS
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index 85ce2cb2cd2b..00c590efdaea 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -328,7 +328,7 @@ void kasan_report_invalid_free(void *object, unsigned long ip)
 	unsigned long flags;
 	u8 tag = get_tag(object);
 
-	object = reset_tag(object);
+	object = kasan_reset_tag(object);
 
 #if IS_ENABLED(CONFIG_KUNIT)
 	if (current->kunit_test)
@@ -361,7 +361,7 @@ static void __kasan_report(unsigned long addr, size_t size, bool is_write,
 	disable_trace_on_warning();
 
 	tagged_addr = (void *)addr;
-	untagged_addr = reset_tag(tagged_addr);
+	untagged_addr = kasan_reset_tag(tagged_addr);
 
 	info.access_addr = tagged_addr;
 	if (addr_has_metadata(untagged_addr))
diff --git a/mm/kasan/report_hw_tags.c b/mm/kasan/report_hw_tags.c
index da543eb832cd..57114f0e14d1 100644
--- a/mm/kasan/report_hw_tags.c
+++ b/mm/kasan/report_hw_tags.c
@@ -22,7 +22,7 @@ const char *get_bug_type(struct kasan_access_info *info)
 
 void *find_first_bad_addr(void *addr, size_t size)
 {
-	return reset_tag(addr);
+	return kasan_reset_tag(addr);
 }
 
 void metadata_fetch_row(char *buffer, void *row)
diff --git a/mm/kasan/report_sw_tags.c b/mm/kasan/report_sw_tags.c
index 317100fd95b9..7604b46239d4 100644
--- a/mm/kasan/report_sw_tags.c
+++ b/mm/kasan/report_sw_tags.c
@@ -41,7 +41,7 @@ const char *get_bug_type(struct kasan_access_info *info)
 	int i;
 
 	tag = get_tag(info->access_addr);
-	addr = reset_tag(info->access_addr);
+	addr = kasan_reset_tag(info->access_addr);
 	page = kasan_addr_to_page(addr);
 	if (page && PageSlab(page)) {
 		cache = page->slab_cache;
@@ -72,7 +72,7 @@ const char *get_bug_type(struct kasan_access_info *info)
 void *find_first_bad_addr(void *addr, size_t size)
 {
 	u8 tag = get_tag(addr);
-	void *p = reset_tag(addr);
+	void *p = kasan_reset_tag(addr);
 	void *end = p + size;
 
 	while (p < end && tag == *(u8 *)kasan_mem_to_shadow(p))
diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c
index ac6a5f57df33..44a2b748f9d3 100644
--- a/mm/kasan/shadow.c
+++ b/mm/kasan/shadow.c
@@ -81,7 +81,7 @@ void poison_range(const void *address, size_t size, u8 value)
 	 * some of the callers (e.g. kasan_poison_object_data) pass tagged
 	 * addresses to this function.
 	 */
-	address = reset_tag(address);
+	address = kasan_reset_tag(address);
 
 	shadow_start = kasan_mem_to_shadow(address);
 	shadow_end = kasan_mem_to_shadow(address + size);
@@ -98,7 +98,7 @@ void unpoison_range(const void *address, size_t size)
 	 * some of the callers (e.g. kasan_unpoison_object_data) pass tagged
 	 * addresses to this function.
 	 */
-	address = reset_tag(address);
+	address = kasan_reset_tag(address);
 
 	poison_range(address, size, tag);
 
diff --git a/mm/kasan/sw_tags.c b/mm/kasan/sw_tags.c
index 6d7648cc3b98..e17de2619bbf 100644
--- a/mm/kasan/sw_tags.c
+++ b/mm/kasan/sw_tags.c
@@ -67,11 +67,6 @@ u8 random_tag(void)
 	return (u8)(state % (KASAN_TAG_MAX + 1));
 }
 
-void *kasan_reset_tag(const void *addr)
-{
-	return reset_tag(addr);
-}
-
 bool check_memory_region(unsigned long addr, size_t size, bool write,
 				unsigned long ret_ip)
 {
@@ -107,7 +102,7 @@ bool check_memory_region(unsigned long addr, size_t size, bool write,
 	if (tag == KASAN_TAG_KERNEL)
 		return true;
 
-	untagged_addr = reset_tag((const void *)addr);
+	untagged_addr = kasan_reset_tag((const void *)addr);
 	if (unlikely(untagged_addr <
 			kasan_shadow_to_mem((void *)KASAN_SHADOW_START))) {
 		return !kasan_report(addr, size, write, ret_ip);
@@ -126,7 +121,7 @@ bool check_memory_region(unsigned long addr, size_t size, bool write,
 bool check_invalid_free(void *addr)
 {
 	u8 tag = get_tag(addr);
-	u8 shadow_byte = READ_ONCE(*(u8 *)kasan_mem_to_shadow(reset_tag(addr)));
+	u8 shadow_byte = READ_ONCE(*(u8 *)kasan_mem_to_shadow(kasan_reset_tag(addr)));
 
 	return (shadow_byte == KASAN_TAG_INVALID) ||
 		(tag != KASAN_TAG_KERNEL && tag != shadow_byte);
-- 
cgit v1.2.3


From bffe690708c8b4fdb8f0bff8ff22b347fc6c709a Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Tue, 22 Dec 2020 12:02:59 -0800
Subject: kasan: open-code kasan_unpoison_slab

There's the external annotation kasan_unpoison_slab() that is currently
defined as static inline and uses kasan_unpoison_range(). Open-code this
function in mempool.c. Otherwise with an upcoming change this function
will result in an unnecessary function call.

Link: https://lkml.kernel.org/r/131a6694a978a9a8b150187e539eecc8bcbf759b.1606162397.git.andreyknvl@google.com
Link: https://linux-review.googlesource.com/id/Ia7c8b659f79209935cbaab3913bf7f082cc43a0e
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Reviewed-by: Marco Elver <elver@google.com>
Tested-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Branislav Rankov <Branislav.Rankov@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Kevin Brodsky <kevin.brodsky@arm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kasan.h | 6 ------
 mm/mempool.c          | 2 +-
 2 files changed, 1 insertion(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 3bb72de94f90..7350de3e9fe4 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -107,11 +107,6 @@ struct kasan_cache {
 	int free_meta_offset;
 };
 
-size_t __ksize(const void *);
-static inline void kasan_unpoison_slab(const void *ptr)
-{
-	kasan_unpoison_range(ptr, __ksize(ptr));
-}
 size_t kasan_metadata_size(struct kmem_cache *cache);
 
 bool kasan_save_enable_multi_shot(void);
@@ -167,7 +162,6 @@ static inline bool kasan_slab_free(struct kmem_cache *s, void *object,
 	return false;
 }
 
-static inline void kasan_unpoison_slab(const void *ptr) { }
 static inline size_t kasan_metadata_size(struct kmem_cache *cache) { return 0; }
 
 #endif /* CONFIG_KASAN */
diff --git a/mm/mempool.c b/mm/mempool.c
index f473cdddaff0..583a9865b181 100644
--- a/mm/mempool.c
+++ b/mm/mempool.c
@@ -112,7 +112,7 @@ static __always_inline void kasan_poison_element(mempool_t *pool, void *element)
 static void kasan_unpoison_element(mempool_t *pool, void *element)
 {
 	if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc)
-		kasan_unpoison_slab(element);
+		kasan_unpoison_range(element, __ksize(element));
 	else if (pool->alloc == mempool_alloc_pages)
 		kasan_alloc_pages(element, (unsigned long)pool->pool_data);
 }
-- 
cgit v1.2.3


From 34303244f2615add92076a4bf2d4f39323bde4f2 Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Tue, 22 Dec 2020 12:03:10 -0800
Subject: kasan, mm: check kasan_enabled in annotations

Declare the kasan_enabled static key in include/linux/kasan.h and in
include/linux/mm.h and check it in all kasan annotations. This allows to
avoid any slowdown caused by function calls when kasan_enabled is
disabled.

Link: https://lkml.kernel.org/r/9f90e3c0aa840dbb4833367c2335193299f69023.1606162397.git.andreyknvl@google.com
Link: https://linux-review.googlesource.com/id/I2589451d3c96c97abbcbf714baabe6161c6f153e
Co-developed-by: Vincenzo Frascino <Vincenzo.Frascino@arm.com>
Signed-off-by: Vincenzo Frascino <Vincenzo.Frascino@arm.com>
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Reviewed-by: Marco Elver <elver@google.com>
Reviewed-by: Dmitry Vyukov <dvyukov@google.com>
Tested-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Branislav Rankov <Branislav.Rankov@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Kevin Brodsky <kevin.brodsky@arm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kasan.h | 213 +++++++++++++++++++++++++++++++++++++++-----------
 include/linux/mm.h    |  22 ++++--
 mm/kasan/common.c     |  56 ++++++-------
 3 files changed, 210 insertions(+), 81 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 7350de3e9fe4..9176849c4934 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -2,6 +2,7 @@
 #ifndef _LINUX_KASAN_H
 #define _LINUX_KASAN_H
 
+#include <linux/static_key.h>
 #include <linux/types.h>
 
 struct kmem_cache;
@@ -75,54 +76,176 @@ static inline void kasan_disable_current(void) {}
 
 #ifdef CONFIG_KASAN
 
-void kasan_unpoison_range(const void *address, size_t size);
+struct kasan_cache {
+	int alloc_meta_offset;
+	int free_meta_offset;
+};
 
-void kasan_alloc_pages(struct page *page, unsigned int order);
-void kasan_free_pages(struct page *page, unsigned int order);
+#ifdef CONFIG_KASAN_HW_TAGS
+DECLARE_STATIC_KEY_FALSE(kasan_flag_enabled);
+static __always_inline bool kasan_enabled(void)
+{
+	return static_branch_likely(&kasan_flag_enabled);
+}
+#else
+static inline bool kasan_enabled(void)
+{
+	return true;
+}
+#endif
 
-void kasan_cache_create(struct kmem_cache *cache, unsigned int *size,
-			slab_flags_t *flags);
+void __kasan_unpoison_range(const void *addr, size_t size);
+static __always_inline void kasan_unpoison_range(const void *addr, size_t size)
+{
+	if (kasan_enabled())
+		__kasan_unpoison_range(addr, size);
+}
 
-void kasan_poison_slab(struct page *page);
-void kasan_unpoison_object_data(struct kmem_cache *cache, void *object);
-void kasan_poison_object_data(struct kmem_cache *cache, void *object);
-void * __must_check kasan_init_slab_obj(struct kmem_cache *cache,
-					const void *object);
+void __kasan_alloc_pages(struct page *page, unsigned int order);
+static __always_inline void kasan_alloc_pages(struct page *page,
+						unsigned int order)
+{
+	if (kasan_enabled())
+		__kasan_alloc_pages(page, order);
+}
 
-void * __must_check kasan_kmalloc_large(const void *ptr, size_t size,
-						gfp_t flags);
-void kasan_kfree_large(void *ptr, unsigned long ip);
-void kasan_poison_kfree(void *ptr, unsigned long ip);
-void * __must_check kasan_kmalloc(struct kmem_cache *s, const void *object,
-					size_t size, gfp_t flags);
-void * __must_check kasan_krealloc(const void *object, size_t new_size,
-					gfp_t flags);
+void __kasan_free_pages(struct page *page, unsigned int order);
+static __always_inline void kasan_free_pages(struct page *page,
+						unsigned int order)
+{
+	if (kasan_enabled())
+		__kasan_free_pages(page, order);
+}
 
-void * __must_check kasan_slab_alloc(struct kmem_cache *s, void *object,
-					gfp_t flags);
-bool kasan_slab_free(struct kmem_cache *s, void *object, unsigned long ip);
+void __kasan_cache_create(struct kmem_cache *cache, unsigned int *size,
+				slab_flags_t *flags);
+static __always_inline void kasan_cache_create(struct kmem_cache *cache,
+				unsigned int *size, slab_flags_t *flags)
+{
+	if (kasan_enabled())
+		__kasan_cache_create(cache, size, flags);
+}
 
-struct kasan_cache {
-	int alloc_meta_offset;
-	int free_meta_offset;
-};
+size_t __kasan_metadata_size(struct kmem_cache *cache);
+static __always_inline size_t kasan_metadata_size(struct kmem_cache *cache)
+{
+	if (kasan_enabled())
+		return __kasan_metadata_size(cache);
+	return 0;
+}
+
+void __kasan_poison_slab(struct page *page);
+static __always_inline void kasan_poison_slab(struct page *page)
+{
+	if (kasan_enabled())
+		__kasan_poison_slab(page);
+}
+
+void __kasan_unpoison_object_data(struct kmem_cache *cache, void *object);
+static __always_inline void kasan_unpoison_object_data(struct kmem_cache *cache,
+							void *object)
+{
+	if (kasan_enabled())
+		__kasan_unpoison_object_data(cache, object);
+}
+
+void __kasan_poison_object_data(struct kmem_cache *cache, void *object);
+static __always_inline void kasan_poison_object_data(struct kmem_cache *cache,
+							void *object)
+{
+	if (kasan_enabled())
+		__kasan_poison_object_data(cache, object);
+}
+
+void * __must_check __kasan_init_slab_obj(struct kmem_cache *cache,
+					  const void *object);
+static __always_inline void * __must_check kasan_init_slab_obj(
+				struct kmem_cache *cache, const void *object)
+{
+	if (kasan_enabled())
+		return __kasan_init_slab_obj(cache, object);
+	return (void *)object;
+}
+
+bool __kasan_slab_free(struct kmem_cache *s, void *object, unsigned long ip);
+static __always_inline bool kasan_slab_free(struct kmem_cache *s, void *object,
+						unsigned long ip)
+{
+	if (kasan_enabled())
+		return __kasan_slab_free(s, object, ip);
+	return false;
+}
+
+void * __must_check __kasan_slab_alloc(struct kmem_cache *s,
+				       void *object, gfp_t flags);
+static __always_inline void * __must_check kasan_slab_alloc(
+				struct kmem_cache *s, void *object, gfp_t flags)
+{
+	if (kasan_enabled())
+		return __kasan_slab_alloc(s, object, flags);
+	return object;
+}
+
+void * __must_check __kasan_kmalloc(struct kmem_cache *s, const void *object,
+				    size_t size, gfp_t flags);
+static __always_inline void * __must_check kasan_kmalloc(struct kmem_cache *s,
+				const void *object, size_t size, gfp_t flags)
+{
+	if (kasan_enabled())
+		return __kasan_kmalloc(s, object, size, flags);
+	return (void *)object;
+}
 
-size_t kasan_metadata_size(struct kmem_cache *cache);
+void * __must_check __kasan_kmalloc_large(const void *ptr,
+					  size_t size, gfp_t flags);
+static __always_inline void * __must_check kasan_kmalloc_large(const void *ptr,
+						      size_t size, gfp_t flags)
+{
+	if (kasan_enabled())
+		return __kasan_kmalloc_large(ptr, size, flags);
+	return (void *)ptr;
+}
+
+void * __must_check __kasan_krealloc(const void *object,
+				     size_t new_size, gfp_t flags);
+static __always_inline void * __must_check kasan_krealloc(const void *object,
+						 size_t new_size, gfp_t flags)
+{
+	if (kasan_enabled())
+		return __kasan_krealloc(object, new_size, flags);
+	return (void *)object;
+}
+
+void __kasan_poison_kfree(void *ptr, unsigned long ip);
+static __always_inline void kasan_poison_kfree(void *ptr, unsigned long ip)
+{
+	if (kasan_enabled())
+		__kasan_poison_kfree(ptr, ip);
+}
+
+void __kasan_kfree_large(void *ptr, unsigned long ip);
+static __always_inline void kasan_kfree_large(void *ptr, unsigned long ip)
+{
+	if (kasan_enabled())
+		__kasan_kfree_large(ptr, ip);
+}
 
 bool kasan_save_enable_multi_shot(void);
 void kasan_restore_multi_shot(bool enabled);
 
 #else /* CONFIG_KASAN */
 
+static inline bool kasan_enabled(void)
+{
+	return false;
+}
 static inline void kasan_unpoison_range(const void *address, size_t size) {}
-
 static inline void kasan_alloc_pages(struct page *page, unsigned int order) {}
 static inline void kasan_free_pages(struct page *page, unsigned int order) {}
-
 static inline void kasan_cache_create(struct kmem_cache *cache,
 				      unsigned int *size,
 				      slab_flags_t *flags) {}
-
+static inline size_t kasan_metadata_size(struct kmem_cache *cache) { return 0; }
 static inline void kasan_poison_slab(struct page *page) {}
 static inline void kasan_unpoison_object_data(struct kmem_cache *cache,
 					void *object) {}
@@ -133,36 +256,32 @@ static inline void *kasan_init_slab_obj(struct kmem_cache *cache,
 {
 	return (void *)object;
 }
-
-static inline void *kasan_kmalloc_large(void *ptr, size_t size, gfp_t flags)
+static inline bool kasan_slab_free(struct kmem_cache *s, void *object,
+				   unsigned long ip)
 {
-	return ptr;
+	return false;
+}
+static inline void *kasan_slab_alloc(struct kmem_cache *s, void *object,
+				   gfp_t flags)
+{
+	return object;
 }
-static inline void kasan_kfree_large(void *ptr, unsigned long ip) {}
-static inline void kasan_poison_kfree(void *ptr, unsigned long ip) {}
 static inline void *kasan_kmalloc(struct kmem_cache *s, const void *object,
 				size_t size, gfp_t flags)
 {
 	return (void *)object;
 }
+static inline void *kasan_kmalloc_large(const void *ptr, size_t size, gfp_t flags)
+{
+	return (void *)ptr;
+}
 static inline void *kasan_krealloc(const void *object, size_t new_size,
 				 gfp_t flags)
 {
 	return (void *)object;
 }
-
-static inline void *kasan_slab_alloc(struct kmem_cache *s, void *object,
-				   gfp_t flags)
-{
-	return object;
-}
-static inline bool kasan_slab_free(struct kmem_cache *s, void *object,
-				   unsigned long ip)
-{
-	return false;
-}
-
-static inline size_t kasan_metadata_size(struct kmem_cache *cache) { return 0; }
+static inline void kasan_poison_kfree(void *ptr, unsigned long ip) {}
+static inline void kasan_kfree_large(void *ptr, unsigned long ip) {}
 
 #endif /* CONFIG_KASAN */
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 024ec0a00c72..5299b90a6c40 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -31,6 +31,7 @@
 #include <linux/sizes.h>
 #include <linux/sched.h>
 #include <linux/pgtable.h>
+#include <linux/kasan.h>
 
 struct mempolicy;
 struct anon_vma;
@@ -1422,22 +1423,30 @@ static inline bool cpupid_match_pid(struct task_struct *task, int cpupid)
 #endif /* CONFIG_NUMA_BALANCING */
 
 #if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS)
+
 static inline u8 page_kasan_tag(const struct page *page)
 {
-	return (page->flags >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK;
+	if (kasan_enabled())
+		return (page->flags >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK;
+	return 0xff;
 }
 
 static inline void page_kasan_tag_set(struct page *page, u8 tag)
 {
-	page->flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT);
-	page->flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT;
+	if (kasan_enabled()) {
+		page->flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT);
+		page->flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT;
+	}
 }
 
 static inline void page_kasan_tag_reset(struct page *page)
 {
-	page_kasan_tag_set(page, 0xff);
+	if (kasan_enabled())
+		page_kasan_tag_set(page, 0xff);
 }
-#else
+
+#else /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */
+
 static inline u8 page_kasan_tag(const struct page *page)
 {
 	return 0xff;
@@ -1445,7 +1454,8 @@ static inline u8 page_kasan_tag(const struct page *page)
 
 static inline void page_kasan_tag_set(struct page *page, u8 tag) { }
 static inline void page_kasan_tag_reset(struct page *page) { }
-#endif
+
+#endif /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */
 
 static inline struct zone *page_zone(const struct page *page)
 {
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index 219c2979bd3e..ae0130cf9de3 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -58,7 +58,7 @@ void kasan_disable_current(void)
 }
 #endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
 
-void kasan_unpoison_range(const void *address, size_t size)
+void __kasan_unpoison_range(const void *address, size_t size)
 {
 	unpoison_range(address, size);
 }
@@ -86,7 +86,7 @@ asmlinkage void kasan_unpoison_task_stack_below(const void *watermark)
 }
 #endif /* CONFIG_KASAN_STACK */
 
-void kasan_alloc_pages(struct page *page, unsigned int order)
+void __kasan_alloc_pages(struct page *page, unsigned int order)
 {
 	u8 tag;
 	unsigned long i;
@@ -100,7 +100,7 @@ void kasan_alloc_pages(struct page *page, unsigned int order)
 	unpoison_range(page_address(page), PAGE_SIZE << order);
 }
 
-void kasan_free_pages(struct page *page, unsigned int order)
+void __kasan_free_pages(struct page *page, unsigned int order)
 {
 	if (likely(!PageHighMem(page)))
 		poison_range(page_address(page),
@@ -127,8 +127,8 @@ static inline unsigned int optimal_redzone(unsigned int object_size)
 		object_size <= (1 << 16) - 1024 ? 1024 : 2048;
 }
 
-void kasan_cache_create(struct kmem_cache *cache, unsigned int *size,
-			slab_flags_t *flags)
+void __kasan_cache_create(struct kmem_cache *cache, unsigned int *size,
+			  slab_flags_t *flags)
 {
 	unsigned int orig_size = *size;
 	unsigned int redzone_size;
@@ -173,7 +173,7 @@ void kasan_cache_create(struct kmem_cache *cache, unsigned int *size,
 	*flags |= SLAB_KASAN;
 }
 
-size_t kasan_metadata_size(struct kmem_cache *cache)
+size_t __kasan_metadata_size(struct kmem_cache *cache)
 {
 	if (!kasan_stack_collection_enabled())
 		return 0;
@@ -196,7 +196,7 @@ struct kasan_free_meta *kasan_get_free_meta(struct kmem_cache *cache,
 	return kasan_reset_tag(object) + cache->kasan_info.free_meta_offset;
 }
 
-void kasan_poison_slab(struct page *page)
+void __kasan_poison_slab(struct page *page)
 {
 	unsigned long i;
 
@@ -206,12 +206,12 @@ void kasan_poison_slab(struct page *page)
 		     KASAN_KMALLOC_REDZONE);
 }
 
-void kasan_unpoison_object_data(struct kmem_cache *cache, void *object)
+void __kasan_unpoison_object_data(struct kmem_cache *cache, void *object)
 {
 	unpoison_range(object, cache->object_size);
 }
 
-void kasan_poison_object_data(struct kmem_cache *cache, void *object)
+void __kasan_poison_object_data(struct kmem_cache *cache, void *object)
 {
 	poison_range(object,
 			round_up(cache->object_size, KASAN_GRANULE_SIZE),
@@ -264,7 +264,7 @@ static u8 assign_tag(struct kmem_cache *cache, const void *object,
 #endif
 }
 
-void * __must_check kasan_init_slab_obj(struct kmem_cache *cache,
+void * __must_check __kasan_init_slab_obj(struct kmem_cache *cache,
 						const void *object)
 {
 	struct kasan_alloc_meta *alloc_meta;
@@ -283,7 +283,7 @@ void * __must_check kasan_init_slab_obj(struct kmem_cache *cache,
 	return (void *)object;
 }
 
-static bool __kasan_slab_free(struct kmem_cache *cache, void *object,
+static bool ____kasan_slab_free(struct kmem_cache *cache, void *object,
 			      unsigned long ip, bool quarantine)
 {
 	u8 tag;
@@ -326,9 +326,9 @@ static bool __kasan_slab_free(struct kmem_cache *cache, void *object,
 	return IS_ENABLED(CONFIG_KASAN_GENERIC);
 }
 
-bool kasan_slab_free(struct kmem_cache *cache, void *object, unsigned long ip)
+bool __kasan_slab_free(struct kmem_cache *cache, void *object, unsigned long ip)
 {
-	return __kasan_slab_free(cache, object, ip, true);
+	return ____kasan_slab_free(cache, object, ip, true);
 }
 
 static void set_alloc_info(struct kmem_cache *cache, void *object, gfp_t flags)
@@ -336,7 +336,7 @@ static void set_alloc_info(struct kmem_cache *cache, void *object, gfp_t flags)
 	kasan_set_track(&kasan_get_alloc_meta(cache, object)->alloc_track, flags);
 }
 
-static void *__kasan_kmalloc(struct kmem_cache *cache, const void *object,
+static void *____kasan_kmalloc(struct kmem_cache *cache, const void *object,
 				size_t size, gfp_t flags, bool keep_tag)
 {
 	unsigned long redzone_start;
@@ -368,20 +368,20 @@ static void *__kasan_kmalloc(struct kmem_cache *cache, const void *object,
 	return set_tag(object, tag);
 }
 
-void * __must_check kasan_slab_alloc(struct kmem_cache *cache, void *object,
-					gfp_t flags)
+void * __must_check __kasan_slab_alloc(struct kmem_cache *cache,
+					void *object, gfp_t flags)
 {
-	return __kasan_kmalloc(cache, object, cache->object_size, flags, false);
+	return ____kasan_kmalloc(cache, object, cache->object_size, flags, false);
 }
 
-void * __must_check kasan_kmalloc(struct kmem_cache *cache, const void *object,
-				size_t size, gfp_t flags)
+void * __must_check __kasan_kmalloc(struct kmem_cache *cache, const void *object,
+					size_t size, gfp_t flags)
 {
-	return __kasan_kmalloc(cache, object, size, flags, true);
+	return ____kasan_kmalloc(cache, object, size, flags, true);
 }
-EXPORT_SYMBOL(kasan_kmalloc);
+EXPORT_SYMBOL(__kasan_kmalloc);
 
-void * __must_check kasan_kmalloc_large(const void *ptr, size_t size,
+void * __must_check __kasan_kmalloc_large(const void *ptr, size_t size,
 						gfp_t flags)
 {
 	struct page *page;
@@ -406,7 +406,7 @@ void * __must_check kasan_kmalloc_large(const void *ptr, size_t size,
 	return (void *)ptr;
 }
 
-void * __must_check kasan_krealloc(const void *object, size_t size, gfp_t flags)
+void * __must_check __kasan_krealloc(const void *object, size_t size, gfp_t flags)
 {
 	struct page *page;
 
@@ -416,13 +416,13 @@ void * __must_check kasan_krealloc(const void *object, size_t size, gfp_t flags)
 	page = virt_to_head_page(object);
 
 	if (unlikely(!PageSlab(page)))
-		return kasan_kmalloc_large(object, size, flags);
+		return __kasan_kmalloc_large(object, size, flags);
 	else
-		return __kasan_kmalloc(page->slab_cache, object, size,
+		return ____kasan_kmalloc(page->slab_cache, object, size,
 						flags, true);
 }
 
-void kasan_poison_kfree(void *ptr, unsigned long ip)
+void __kasan_poison_kfree(void *ptr, unsigned long ip)
 {
 	struct page *page;
 
@@ -435,11 +435,11 @@ void kasan_poison_kfree(void *ptr, unsigned long ip)
 		}
 		poison_range(ptr, page_size(page), KASAN_FREE_PAGE);
 	} else {
-		__kasan_slab_free(page->slab_cache, ptr, ip, false);
+		____kasan_slab_free(page->slab_cache, ptr, ip, false);
 	}
 }
 
-void kasan_kfree_large(void *ptr, unsigned long ip)
+void __kasan_kfree_large(void *ptr, unsigned long ip)
 {
 	if (ptr != page_address(virt_to_head_page(ptr)))
 		kasan_report_invalid_free(ptr, ip);
-- 
cgit v1.2.3


From eeb3160c2419e0f1045537acac7b19cba64112f4 Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Tue, 22 Dec 2020 12:03:13 -0800
Subject: kasan, mm: rename kasan_poison_kfree

Rename kasan_poison_kfree() to kasan_slab_free_mempool() as it better
reflects what this annotation does. Also add a comment that explains the
PageSlab() check.

No functional changes.

Link: https://lkml.kernel.org/r/141675fb493555e984c5dca555e9d9f768c7bbaa.1606162397.git.andreyknvl@google.com
Link: https://linux-review.googlesource.com/id/I5026f87364e556b506ef1baee725144bb04b8810
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Reviewed-by: Marco Elver <elver@google.com>
Tested-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Branislav Rankov <Branislav.Rankov@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Kevin Brodsky <kevin.brodsky@arm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kasan.h | 16 ++++++++--------
 mm/kasan/common.c     | 40 +++++++++++++++++++++++-----------------
 mm/mempool.c          |  2 +-
 3 files changed, 32 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 9176849c4934..6f0c5d9aa43f 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -176,6 +176,13 @@ static __always_inline bool kasan_slab_free(struct kmem_cache *s, void *object,
 	return false;
 }
 
+void __kasan_slab_free_mempool(void *ptr, unsigned long ip);
+static __always_inline void kasan_slab_free_mempool(void *ptr, unsigned long ip)
+{
+	if (kasan_enabled())
+		__kasan_slab_free_mempool(ptr, ip);
+}
+
 void * __must_check __kasan_slab_alloc(struct kmem_cache *s,
 				       void *object, gfp_t flags);
 static __always_inline void * __must_check kasan_slab_alloc(
@@ -216,13 +223,6 @@ static __always_inline void * __must_check kasan_krealloc(const void *object,
 	return (void *)object;
 }
 
-void __kasan_poison_kfree(void *ptr, unsigned long ip);
-static __always_inline void kasan_poison_kfree(void *ptr, unsigned long ip)
-{
-	if (kasan_enabled())
-		__kasan_poison_kfree(ptr, ip);
-}
-
 void __kasan_kfree_large(void *ptr, unsigned long ip);
 static __always_inline void kasan_kfree_large(void *ptr, unsigned long ip)
 {
@@ -261,6 +261,7 @@ static inline bool kasan_slab_free(struct kmem_cache *s, void *object,
 {
 	return false;
 }
+static inline void kasan_slab_free_mempool(void *ptr, unsigned long ip) {}
 static inline void *kasan_slab_alloc(struct kmem_cache *s, void *object,
 				   gfp_t flags)
 {
@@ -280,7 +281,6 @@ static inline void *kasan_krealloc(const void *object, size_t new_size,
 {
 	return (void *)object;
 }
-static inline void kasan_poison_kfree(void *ptr, unsigned long ip) {}
 static inline void kasan_kfree_large(void *ptr, unsigned long ip) {}
 
 #endif /* CONFIG_KASAN */
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index ae0130cf9de3..d0f8d7a955cd 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -331,6 +331,29 @@ bool __kasan_slab_free(struct kmem_cache *cache, void *object, unsigned long ip)
 	return ____kasan_slab_free(cache, object, ip, true);
 }
 
+void __kasan_slab_free_mempool(void *ptr, unsigned long ip)
+{
+	struct page *page;
+
+	page = virt_to_head_page(ptr);
+
+	/*
+	 * Even though this function is only called for kmem_cache_alloc and
+	 * kmalloc backed mempool allocations, those allocations can still be
+	 * !PageSlab() when the size provided to kmalloc is larger than
+	 * KMALLOC_MAX_SIZE, and kmalloc falls back onto page_alloc.
+	 */
+	if (unlikely(!PageSlab(page))) {
+		if (ptr != page_address(page)) {
+			kasan_report_invalid_free(ptr, ip);
+			return;
+		}
+		poison_range(ptr, page_size(page), KASAN_FREE_PAGE);
+	} else {
+		____kasan_slab_free(page->slab_cache, ptr, ip, false);
+	}
+}
+
 static void set_alloc_info(struct kmem_cache *cache, void *object, gfp_t flags)
 {
 	kasan_set_track(&kasan_get_alloc_meta(cache, object)->alloc_track, flags);
@@ -422,23 +445,6 @@ void * __must_check __kasan_krealloc(const void *object, size_t size, gfp_t flag
 						flags, true);
 }
 
-void __kasan_poison_kfree(void *ptr, unsigned long ip)
-{
-	struct page *page;
-
-	page = virt_to_head_page(ptr);
-
-	if (unlikely(!PageSlab(page))) {
-		if (ptr != page_address(page)) {
-			kasan_report_invalid_free(ptr, ip);
-			return;
-		}
-		poison_range(ptr, page_size(page), KASAN_FREE_PAGE);
-	} else {
-		____kasan_slab_free(page->slab_cache, ptr, ip, false);
-	}
-}
-
 void __kasan_kfree_large(void *ptr, unsigned long ip)
 {
 	if (ptr != page_address(virt_to_head_page(ptr)))
diff --git a/mm/mempool.c b/mm/mempool.c
index 583a9865b181..624ed51b060f 100644
--- a/mm/mempool.c
+++ b/mm/mempool.c
@@ -104,7 +104,7 @@ static inline void poison_element(mempool_t *pool, void *element)
 static __always_inline void kasan_poison_element(mempool_t *pool, void *element)
 {
 	if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc)
-		kasan_poison_kfree(element, _RET_IP_);
+		kasan_slab_free_mempool(element, _RET_IP_);
 	else if (pool->alloc == mempool_alloc_pages)
 		kasan_free_pages(element, (unsigned long)pool->pool_data);
 }
-- 
cgit v1.2.3


From e86f8b09f215e3755cd2d56930487dec2de02433 Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Tue, 22 Dec 2020 12:03:31 -0800
Subject: kasan, mm: allow cache merging with no metadata

The reason cache merging is disabled with KASAN is because KASAN puts its
metadata right after the allocated object. When the merged caches have
slightly different sizes, the metadata ends up in different places, which
KASAN doesn't support.

It might be possible to adjust the metadata allocation algorithm and make
it friendly to the cache merging code. Instead this change takes a simpler
approach and allows merging caches when no metadata is present. Which is
the case for hardware tag-based KASAN with kasan.mode=prod.

Link: https://lkml.kernel.org/r/37497e940bfd4b32c0a93a702a9ae4cf061d5392.1606162397.git.andreyknvl@google.com
Link: https://linux-review.googlesource.com/id/Ia114847dfb2244f297d2cb82d592bf6a07455dba
Co-developed-by: Vincenzo Frascino <Vincenzo.Frascino@arm.com>
Signed-off-by: Vincenzo Frascino <Vincenzo.Frascino@arm.com>
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Reviewed-by: Dmitry Vyukov <dvyukov@google.com>
Reviewed-by: Marco Elver <elver@google.com>
Tested-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Branislav Rankov <Branislav.Rankov@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Kevin Brodsky <kevin.brodsky@arm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kasan.h | 21 +++++++++++++++++++--
 mm/kasan/common.c     | 11 +++++++++++
 mm/slab_common.c      |  3 ++-
 3 files changed, 32 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 6f0c5d9aa43f..5e0655fb2a6f 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -82,17 +82,30 @@ struct kasan_cache {
 };
 
 #ifdef CONFIG_KASAN_HW_TAGS
+
 DECLARE_STATIC_KEY_FALSE(kasan_flag_enabled);
+
 static __always_inline bool kasan_enabled(void)
 {
 	return static_branch_likely(&kasan_flag_enabled);
 }
-#else
+
+#else /* CONFIG_KASAN_HW_TAGS */
+
 static inline bool kasan_enabled(void)
 {
 	return true;
 }
-#endif
+
+#endif /* CONFIG_KASAN_HW_TAGS */
+
+slab_flags_t __kasan_never_merge(void);
+static __always_inline slab_flags_t kasan_never_merge(void)
+{
+	if (kasan_enabled())
+		return __kasan_never_merge();
+	return 0;
+}
 
 void __kasan_unpoison_range(const void *addr, size_t size);
 static __always_inline void kasan_unpoison_range(const void *addr, size_t size)
@@ -239,6 +252,10 @@ static inline bool kasan_enabled(void)
 {
 	return false;
 }
+static inline slab_flags_t kasan_never_merge(void)
+{
+	return 0;
+}
 static inline void kasan_unpoison_range(const void *address, size_t size) {}
 static inline void kasan_alloc_pages(struct page *page, unsigned int order) {}
 static inline void kasan_free_pages(struct page *page, unsigned int order) {}
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index 0cd583d2fe1c..b25167664ead 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -86,6 +86,17 @@ asmlinkage void kasan_unpoison_task_stack_below(const void *watermark)
 }
 #endif /* CONFIG_KASAN_STACK */
 
+/*
+ * Only allow cache merging when stack collection is disabled and no metadata
+ * is present.
+ */
+slab_flags_t __kasan_never_merge(void)
+{
+	if (kasan_stack_collection_enabled())
+		return SLAB_KASAN;
+	return 0;
+}
+
 void __kasan_alloc_pages(struct page *page, unsigned int order)
 {
 	u8 tag;
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 573fbacd9ef5..e981c80d216c 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -18,6 +18,7 @@
 #include <linux/seq_file.h>
 #include <linux/proc_fs.h>
 #include <linux/debugfs.h>
+#include <linux/kasan.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 #include <asm/page.h>
@@ -53,7 +54,7 @@ static DECLARE_WORK(slab_caches_to_rcu_destroy_work,
  */
 #define SLAB_NEVER_MERGE (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \
 		SLAB_TRACE | SLAB_TYPESAFE_BY_RCU | SLAB_NOLEAKTRACE | \
-		SLAB_FAILSLAB | SLAB_KASAN)
+		SLAB_FAILSLAB | kasan_never_merge())
 
 #define SLAB_MERGE_SAME (SLAB_RECLAIM_ACCOUNT | SLAB_CACHE_DMA | \
 			 SLAB_CACHE_DMA32 | SLAB_ACCOUNT)
-- 
cgit v1.2.3


From 2ca408d9c749c32288bc28725f9f12ba30299e8f Mon Sep 17 00:00:00 2001
From: Brian Gerst <brgerst@gmail.com>
Date: Mon, 30 Nov 2020 17:30:59 -0500
Subject: fanotify: Fix sys_fanotify_mark() on native x86-32
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit

  121b32a58a3a ("x86/entry/32: Use IA32-specific wrappers for syscalls taking 64-bit arguments")

converted native x86-32 which take 64-bit arguments to use the
compat handlers to allow conversion to passing args via pt_regs.
sys_fanotify_mark() was however missed, as it has a general compat
handler. Add a config option that will use the syscall wrapper that
takes the split args for native 32-bit.

 [ bp: Fix typo in Kconfig help text. ]

Fixes: 121b32a58a3a ("x86/entry/32: Use IA32-specific wrappers for syscalls taking 64-bit arguments")
Reported-by: Paweł Jasiak <pawel@jasiak.xyz>
Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Jan Kara <jack@suse.cz>
Acked-by: Andy Lutomirski <luto@kernel.org>
Link: https://lkml.kernel.org/r/20201130223059.101286-1-brgerst@gmail.com
---
 arch/Kconfig                       |  6 ++++++
 arch/x86/Kconfig                   |  1 +
 fs/notify/fanotify/fanotify_user.c | 17 +++++++----------
 include/linux/syscalls.h           | 24 ++++++++++++++++++++++++
 4 files changed, 38 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/arch/Kconfig b/arch/Kconfig
index 78c6f05b10f9..24862d15f3a3 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -1105,6 +1105,12 @@ config HAVE_ARCH_PFN_VALID
 config ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	bool
 
+config ARCH_SPLIT_ARG64
+	bool
+	help
+	   If a 32-bit architecture requires 64-bit arguments to be split into
+	   pairs of 32-bit arguments, select this option.
+
 source "kernel/gcov/Kconfig"
 
 source "scripts/gcc-plugins/Kconfig"
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 7b6dd10b162a..21f851179ff0 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -19,6 +19,7 @@ config X86_32
 	select KMAP_LOCAL
 	select MODULES_USE_ELF_REL
 	select OLD_SIGACTION
+	select ARCH_SPLIT_ARG64
 
 config X86_64
 	def_bool y
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 3e01d8f2ab90..dcab112e1f00 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -1285,26 +1285,23 @@ fput_and_out:
 	return ret;
 }
 
+#ifndef CONFIG_ARCH_SPLIT_ARG64
 SYSCALL_DEFINE5(fanotify_mark, int, fanotify_fd, unsigned int, flags,
 			      __u64, mask, int, dfd,
 			      const char  __user *, pathname)
 {
 	return do_fanotify_mark(fanotify_fd, flags, mask, dfd, pathname);
 }
+#endif
 
-#ifdef CONFIG_COMPAT
-COMPAT_SYSCALL_DEFINE6(fanotify_mark,
+#if defined(CONFIG_ARCH_SPLIT_ARG64) || defined(CONFIG_COMPAT)
+SYSCALL32_DEFINE6(fanotify_mark,
 				int, fanotify_fd, unsigned int, flags,
-				__u32, mask0, __u32, mask1, int, dfd,
+				SC_ARG64(mask), int, dfd,
 				const char  __user *, pathname)
 {
-	return do_fanotify_mark(fanotify_fd, flags,
-#ifdef __BIG_ENDIAN
-				((__u64)mask0 << 32) | mask1,
-#else
-				((__u64)mask1 << 32) | mask0,
-#endif
-				 dfd, pathname);
+	return do_fanotify_mark(fanotify_fd, flags, SC_VAL64(__u64, mask),
+				dfd, pathname);
 }
 #endif
 
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index f3929aff39cf..7688bc983de5 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -251,6 +251,30 @@ static inline int is_syscall_trace_event(struct trace_event_call *tp_event)
 	static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
 #endif /* __SYSCALL_DEFINEx */
 
+/* For split 64-bit arguments on 32-bit architectures */
+#ifdef __LITTLE_ENDIAN
+#define SC_ARG64(name) u32, name##_lo, u32, name##_hi
+#else
+#define SC_ARG64(name) u32, name##_hi, u32, name##_lo
+#endif
+#define SC_VAL64(type, name) ((type) name##_hi << 32 | name##_lo)
+
+#ifdef CONFIG_COMPAT
+#define SYSCALL32_DEFINE1 COMPAT_SYSCALL_DEFINE1
+#define SYSCALL32_DEFINE2 COMPAT_SYSCALL_DEFINE2
+#define SYSCALL32_DEFINE3 COMPAT_SYSCALL_DEFINE3
+#define SYSCALL32_DEFINE4 COMPAT_SYSCALL_DEFINE4
+#define SYSCALL32_DEFINE5 COMPAT_SYSCALL_DEFINE5
+#define SYSCALL32_DEFINE6 COMPAT_SYSCALL_DEFINE6
+#else
+#define SYSCALL32_DEFINE1 SYSCALL_DEFINE1
+#define SYSCALL32_DEFINE2 SYSCALL_DEFINE2
+#define SYSCALL32_DEFINE3 SYSCALL_DEFINE3
+#define SYSCALL32_DEFINE4 SYSCALL_DEFINE4
+#define SYSCALL32_DEFINE5 SYSCALL_DEFINE5
+#define SYSCALL32_DEFINE6 SYSCALL_DEFINE6
+#endif
+
 /*
  * Called before coming back to user-mode. Returning to user-mode with an
  * address limit different than USER_DS can allow to overwrite kernel memory.
-- 
cgit v1.2.3


From 664f1e259a982bf213f0cd8eea7616c89546585c Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Wed, 16 Dec 2020 18:40:05 +0100
Subject: libceph: add __maybe_unused to DEFINE_MSGR2_FEATURE

Avoid -Wunused-const-variable warnings for "make W=1".

Reported-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/msgr.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ceph/msgr.h b/include/linux/ceph/msgr.h
index f5e02f6c0655..3989dcb94d3d 100644
--- a/include/linux/ceph/msgr.h
+++ b/include/linux/ceph/msgr.h
@@ -33,8 +33,8 @@
 #define CEPH_MSGR2_INCARNATION_1 (0ull)
 
 #define DEFINE_MSGR2_FEATURE(bit, incarnation, name)               \
-	static const uint64_t CEPH_MSGR2_FEATURE_##name = (1ULL << bit); \
-	static const uint64_t CEPH_MSGR2_FEATUREMASK_##name =            \
+	static const uint64_t __maybe_unused CEPH_MSGR2_FEATURE_##name = (1ULL << bit); \
+	static const uint64_t __maybe_unused CEPH_MSGR2_FEATUREMASK_##name =            \
 			(1ULL << bit | CEPH_MSGR2_INCARNATION_##incarnation);
 
 #define HAVE_MSGR2_FEATURE(x, name) \
-- 
cgit v1.2.3


From 3a176b94609a18f5f8bac7ddbf8923bd737262db Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Tue, 29 Dec 2020 15:14:28 -0800
Subject: Revert "kbuild: avoid static_assert for genksyms"

This reverts commit 14dc3983b5dff513a90bd5a8cc90acaf7867c3d0.

Macro Elver had sent a fix proper fix earlier, and also pointed out
corner cases:
 "I guess what you propose is simpler, but might still have corner cases
  where we still get warnings. In particular, if some file (for whatever
  reason) does not include build_bug.h and uses a raw _Static_assert(),
  then we still get warnings. E.g. I see 1 user of raw _Static_assert()
  (drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h )."

I believe the raw use of _Static_assert() should be allowed, so this
should be fixed in genksyms.

Even after commit 14dc3983b5df ("kbuild: avoid static_assert for
genksyms"), I confirmed the following test code emits the warning.

  ---------------->8----------------
  #include <linux/export.h>

  _Static_assert((1 ?: 0), "");

  void foo(void) { }
  EXPORT_SYMBOL(foo);
  ---------------->8----------------

  WARNING: modpost: EXPORT symbol "foo" [vmlinux] version generation failed, symbol will not be versioned.

Now that commit 869b91992bce ("genksyms: Ignore module scoped
_Static_assert()") fixed this issue properly, the workaround should
be reverted.

Link: https://lkml.org/lkml/2020/12/10/845
Link: https://lkml.kernel.org/r/20201219183911.181442-1-masahiroy@kernel.org
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Cc: Marco Elver <elver@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/build_bug.h | 5 -----
 1 file changed, 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/build_bug.h b/include/linux/build_bug.h
index 7bb66e15b481..e3a0be2c90ad 100644
--- a/include/linux/build_bug.h
+++ b/include/linux/build_bug.h
@@ -77,9 +77,4 @@
 #define static_assert(expr, ...) __static_assert(expr, ##__VA_ARGS__, #expr)
 #define __static_assert(expr, msg, ...) _Static_assert(expr, msg)
 
-#ifdef __GENKSYMS__
-/* genksyms gets confused by _Static_assert */
-#define _Static_assert(expr, ...)
-#endif
-
 #endif	/* _LINUX_BUILD_BUG_H */
-- 
cgit v1.2.3


From 6d87d0ece58bc0022ca5247721a8eb06ef66b673 Mon Sep 17 00:00:00 2001
From: Souptick Joarder <jrdr.linux@gmail.com>
Date: Tue, 29 Dec 2020 15:14:34 -0800
Subject: mm: add prototype for __add_to_page_cache_locked()

Otherwise it causes a gcc warning:

  mm/filemap.c:830:14: warning: no previous prototype for `__add_to_page_cache_locked' [-Wmissing-prototypes]

A previous attempt to make this function static led to compilation
errors when CONFIG_DEBUG_INFO_BTF is enabled because
__add_to_page_cache_locked() is referred to by BPF code.

Adding a prototype will silence the warning.

Link: https://lkml.kernel.org/r/1608693702-4665-1-git-send-email-jrdr.linux@gmail.com
Signed-off-by: Souptick Joarder <jrdr.linux@gmail.com>
Cc: Alex Shi <alex.shi@linux.alibaba.com>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 5299b90a6c40..c1e908184442 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -216,6 +216,13 @@ int overcommit_kbytes_handler(struct ctl_table *, int, void *, size_t *,
 		loff_t *);
 int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *,
 		loff_t *);
+/*
+ * Any attempt to mark this function as static leads to build failure
+ * when CONFIG_DEBUG_INFO_BTF is enabled because __add_to_page_cache_locked()
+ * is referred to by BPF code. This must be visible for error injection.
+ */
+int __add_to_page_cache_locked(struct page *page, struct address_space *mapping,
+		pgoff_t index, gfp_t gfp, void **shadowp);
 
 #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n))
 
-- 
cgit v1.2.3


From dc2da7b45ffe954a0090f5d0310ed7b0b37d2bd2 Mon Sep 17 00:00:00 2001
From: Baoquan He <bhe@redhat.com>
Date: Tue, 29 Dec 2020 15:14:37 -0800
Subject: mm: memmap defer init doesn't work as expected

VMware observed a performance regression during memmap init on their
platform, and bisected to commit 73a6e474cb376 ("mm: memmap_init:
iterate over memblock regions rather that check each PFN") causing it.

Before the commit:

  [0.033176] Normal zone: 1445888 pages used for memmap
  [0.033176] Normal zone: 89391104 pages, LIFO batch:63
  [0.035851] ACPI: PM-Timer IO Port: 0x448

With commit

  [0.026874] Normal zone: 1445888 pages used for memmap
  [0.026875] Normal zone: 89391104 pages, LIFO batch:63
  [2.028450] ACPI: PM-Timer IO Port: 0x448

The root cause is the current memmap defer init doesn't work as expected.

Before, memmap_init_zone() was used to do memmap init of one whole zone,
to initialize all low zones of one numa node, but defer memmap init of
the last zone in that numa node.  However, since commit 73a6e474cb376,
function memmap_init() is adapted to iterater over memblock regions
inside one zone, then call memmap_init_zone() to do memmap init for each
region.

E.g, on VMware's system, the memory layout is as below, there are two
memory regions in node 2.  The current code will mistakenly initialize the
whole 1st region [mem 0xab00000000-0xfcffffffff], then do memmap defer to
iniatialize only one memmory section on the 2nd region [mem
0x10000000000-0x1033fffffff].  In fact, we only expect to see that there's
only one memory section's memmap initialized.  That's why more time is
costed at the time.

[    0.008842] ACPI: SRAT: Node 0 PXM 0 [mem 0x00000000-0x0009ffff]
[    0.008842] ACPI: SRAT: Node 0 PXM 0 [mem 0x00100000-0xbfffffff]
[    0.008843] ACPI: SRAT: Node 0 PXM 0 [mem 0x100000000-0x55ffffffff]
[    0.008844] ACPI: SRAT: Node 1 PXM 1 [mem 0x5600000000-0xaaffffffff]
[    0.008844] ACPI: SRAT: Node 2 PXM 2 [mem 0xab00000000-0xfcffffffff]
[    0.008845] ACPI: SRAT: Node 2 PXM 2 [mem 0x10000000000-0x1033fffffff]

Now, let's add a parameter 'zone_end_pfn' to memmap_init_zone() to pass
down the real zone end pfn so that defer_init() can use it to judge
whether defer need be taken in zone wide.

Link: https://lkml.kernel.org/r/20201223080811.16211-1-bhe@redhat.com
Link: https://lkml.kernel.org/r/20201223080811.16211-2-bhe@redhat.com
Fixes: commit 73a6e474cb376 ("mm: memmap_init: iterate over memblock regions rather that check each PFN")
Signed-off-by: Baoquan He <bhe@redhat.com>
Reported-by: Rahul Gopakumar <gopakumarr@vmware.com>
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/ia64/mm/init.c | 4 ++--
 include/linux/mm.h  | 5 +++--
 mm/memory_hotplug.c | 2 +-
 mm/page_alloc.c     | 8 +++++---
 4 files changed, 11 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 9b5acf8fb092..e76386a3479e 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -536,7 +536,7 @@ virtual_memmap_init(u64 start, u64 end, void *arg)
 
 	if (map_start < map_end)
 		memmap_init_zone((unsigned long)(map_end - map_start),
-				 args->nid, args->zone, page_to_pfn(map_start),
+				 args->nid, args->zone, page_to_pfn(map_start), page_to_pfn(map_end),
 				 MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
 	return 0;
 }
@@ -546,7 +546,7 @@ memmap_init (unsigned long size, int nid, unsigned long zone,
 	     unsigned long start_pfn)
 {
 	if (!vmem_map) {
-		memmap_init_zone(size, nid, zone, start_pfn,
+		memmap_init_zone(size, nid, zone, start_pfn, start_pfn + size,
 				 MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
 	} else {
 		struct page *start;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index c1e908184442..ecdf8a8cd6ae 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2439,8 +2439,9 @@ extern int __meminit early_pfn_to_nid(unsigned long pfn);
 #endif
 
 extern void set_dma_reserve(unsigned long new_dma_reserve);
-extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long,
-		enum meminit_context, struct vmem_altmap *, int migratetype);
+extern void memmap_init_zone(unsigned long, int, unsigned long,
+		unsigned long, unsigned long, enum meminit_context,
+		struct vmem_altmap *, int migratetype);
 extern void setup_per_zone_wmarks(void);
 extern int __meminit init_per_zone_wmark_min(void);
 extern void mem_init(void);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index af41fb990820..f9d57b9be8c7 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -713,7 +713,7 @@ void __ref move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
 	 * expects the zone spans the pfn range. All the pages in the range
 	 * are reserved so nobody should be touching them so we should be safe
 	 */
-	memmap_init_zone(nr_pages, nid, zone_idx(zone), start_pfn,
+	memmap_init_zone(nr_pages, nid, zone_idx(zone), start_pfn, 0,
 			 MEMINIT_HOTPLUG, altmap, migratetype);
 
 	set_zone_contiguous(zone);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 7a2c89b21115..bdbec4c98173 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -423,6 +423,8 @@ defer_init(int nid, unsigned long pfn, unsigned long end_pfn)
 	if (end_pfn < pgdat_end_pfn(NODE_DATA(nid)))
 		return false;
 
+	if (NODE_DATA(nid)->first_deferred_pfn != ULONG_MAX)
+		return true;
 	/*
 	 * We start only with one section of pages, more pages are added as
 	 * needed until the rest of deferred pages are initialized.
@@ -6116,7 +6118,7 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn)
  * zone stats (e.g., nr_isolate_pageblock) are touched.
  */
 void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
-		unsigned long start_pfn,
+		unsigned long start_pfn, unsigned long zone_end_pfn,
 		enum meminit_context context,
 		struct vmem_altmap *altmap, int migratetype)
 {
@@ -6152,7 +6154,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 		if (context == MEMINIT_EARLY) {
 			if (overlap_memmap_init(zone, &pfn))
 				continue;
-			if (defer_init(nid, pfn, end_pfn))
+			if (defer_init(nid, pfn, zone_end_pfn))
 				break;
 		}
 
@@ -6266,7 +6268,7 @@ void __meminit __weak memmap_init(unsigned long size, int nid,
 
 		if (end_pfn > start_pfn) {
 			size = end_pfn - start_pfn;
-			memmap_init_zone(size, nid, zone, start_pfn,
+			memmap_init_zone(size, nid, zone, start_pfn, range_end_pfn,
 					 MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
 		}
 	}
-- 
cgit v1.2.3


From 8b0fac44bd1ff17016502b3c3533f5abb8456c65 Mon Sep 17 00:00:00 2001
From: Huang Shijie <sjhuang@iluvatar.ai>
Date: Tue, 29 Dec 2020 15:14:52 -0800
Subject: sizes.h: add SZ_8G/SZ_16G/SZ_32G macros

Add these macros, since we can use them in drivers.

Link: https://lkml.kernel.org/r/20201229072819.11183-1-sjhuang@iluvatar.ai
Signed-off-by: Huang Shijie <sjhuang@iluvatar.ai>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/sizes.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/sizes.h b/include/linux/sizes.h
index 9874f6f67537..1ac79bcee2bb 100644
--- a/include/linux/sizes.h
+++ b/include/linux/sizes.h
@@ -44,6 +44,9 @@
 #define SZ_2G				0x80000000
 
 #define SZ_4G				_AC(0x100000000, ULL)
+#define SZ_8G				_AC(0x200000000, ULL)
+#define SZ_16G				_AC(0x400000000, ULL)
+#define SZ_32G				_AC(0x800000000, ULL)
 #define SZ_64T				_AC(0x400000000000, ULL)
 
 #endif /* __LINUX_SIZES_H__ */
-- 
cgit v1.2.3


From aa8c7db494d0a83ecae583aa193f1134ef25d506 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Tue, 29 Dec 2020 15:14:55 -0800
Subject: kdev_t: always inline major/minor helper functions

Silly GCC doesn't always inline these trivial functions.

Fixes the following warning:

  arch/x86/kernel/sys_ia32.o: warning: objtool: cp_stat64()+0xd8: call to new_encode_dev() with UACCESS enabled

Link: https://lkml.kernel.org/r/984353b44a4484d86ba9f73884b7306232e25e30.1608737428.git.jpoimboe@redhat.com
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Acked-by: Randy Dunlap <rdunlap@infradead.org>	[build-tested]
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kdev_t.h | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kdev_t.h b/include/linux/kdev_t.h
index 85b5151911cf..4856706fbfeb 100644
--- a/include/linux/kdev_t.h
+++ b/include/linux/kdev_t.h
@@ -21,61 +21,61 @@
 	})
 
 /* acceptable for old filesystems */
-static inline bool old_valid_dev(dev_t dev)
+static __always_inline bool old_valid_dev(dev_t dev)
 {
 	return MAJOR(dev) < 256 && MINOR(dev) < 256;
 }
 
-static inline u16 old_encode_dev(dev_t dev)
+static __always_inline u16 old_encode_dev(dev_t dev)
 {
 	return (MAJOR(dev) << 8) | MINOR(dev);
 }
 
-static inline dev_t old_decode_dev(u16 val)
+static __always_inline dev_t old_decode_dev(u16 val)
 {
 	return MKDEV((val >> 8) & 255, val & 255);
 }
 
-static inline u32 new_encode_dev(dev_t dev)
+static __always_inline u32 new_encode_dev(dev_t dev)
 {
 	unsigned major = MAJOR(dev);
 	unsigned minor = MINOR(dev);
 	return (minor & 0xff) | (major << 8) | ((minor & ~0xff) << 12);
 }
 
-static inline dev_t new_decode_dev(u32 dev)
+static __always_inline dev_t new_decode_dev(u32 dev)
 {
 	unsigned major = (dev & 0xfff00) >> 8;
 	unsigned minor = (dev & 0xff) | ((dev >> 12) & 0xfff00);
 	return MKDEV(major, minor);
 }
 
-static inline u64 huge_encode_dev(dev_t dev)
+static __always_inline u64 huge_encode_dev(dev_t dev)
 {
 	return new_encode_dev(dev);
 }
 
-static inline dev_t huge_decode_dev(u64 dev)
+static __always_inline dev_t huge_decode_dev(u64 dev)
 {
 	return new_decode_dev(dev);
 }
 
-static inline int sysv_valid_dev(dev_t dev)
+static __always_inline int sysv_valid_dev(dev_t dev)
 {
 	return MAJOR(dev) < (1<<14) && MINOR(dev) < (1<<18);
 }
 
-static inline u32 sysv_encode_dev(dev_t dev)
+static __always_inline u32 sysv_encode_dev(dev_t dev)
 {
 	return MINOR(dev) | (MAJOR(dev) << 18);
 }
 
-static inline unsigned sysv_major(u32 dev)
+static __always_inline unsigned sysv_major(u32 dev)
 {
 	return (dev >> 18) & 0x3fff;
 }
 
-static inline unsigned sysv_minor(u32 dev)
+static __always_inline unsigned sysv_minor(u32 dev)
 {
 	return dev & 0x3ffff;
 }
-- 
cgit v1.2.3


From e89eed02a5f1b864fa5abafc8e8e71bd9fd66d1f Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Tue, 5 Jan 2021 20:53:42 +0100
Subject: kcov, usb: hide in_serving_softirq checks in __usb_hcd_giveback_urb

Done opencode in_serving_softirq() checks in in_serving_softirq() to avoid
cluttering the code, hide them in kcov helpers instead.

Fixes: aee9ddb1d371 ("kcov, usb: only collect coverage from __usb_hcd_giveback_urb in softirq")
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Link: https://lore.kernel.org/r/aeb430c5bb90b0ccdf1ec302c70831c1a47b9c45.1609876340.git.andreyknvl@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/hcd.c |  8 +++-----
 include/linux/kcov.h   | 21 +++++++++++++++++++++
 2 files changed, 24 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 60886a7464c3..ad5a0f405a75 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -1649,14 +1649,12 @@ static void __usb_hcd_giveback_urb(struct urb *urb)
 	urb->status = status;
 	/*
 	 * This function can be called in task context inside another remote
-	 * coverage collection section, but KCOV doesn't support that kind of
+	 * coverage collection section, but kcov doesn't support that kind of
 	 * recursion yet. Only collect coverage in softirq context for now.
 	 */
-	if (in_serving_softirq())
-		kcov_remote_start_usb((u64)urb->dev->bus->busnum);
+	kcov_remote_start_usb_softirq((u64)urb->dev->bus->busnum);
 	urb->complete(urb);
-	if (in_serving_softirq())
-		kcov_remote_stop();
+	kcov_remote_stop_softirq();
 
 	usb_anchor_resume_wakeups(anchor);
 	atomic_dec(&urb->use_count);
diff --git a/include/linux/kcov.h b/include/linux/kcov.h
index a10e84707d82..4e3037dc1204 100644
--- a/include/linux/kcov.h
+++ b/include/linux/kcov.h
@@ -52,6 +52,25 @@ static inline void kcov_remote_start_usb(u64 id)
 	kcov_remote_start(kcov_remote_handle(KCOV_SUBSYSTEM_USB, id));
 }
 
+/*
+ * The softirq flavor of kcov_remote_*() functions is introduced as a temporary
+ * work around for kcov's lack of nested remote coverage sections support in
+ * task context. Adding suport for nested sections is tracked in:
+ * https://bugzilla.kernel.org/show_bug.cgi?id=210337
+ */
+
+static inline void kcov_remote_start_usb_softirq(u64 id)
+{
+	if (in_serving_softirq())
+		kcov_remote_start_usb(id);
+}
+
+static inline void kcov_remote_stop_softirq(void)
+{
+	if (in_serving_softirq())
+		kcov_remote_stop();
+}
+
 #else
 
 static inline void kcov_task_init(struct task_struct *t) {}
@@ -66,6 +85,8 @@ static inline u64 kcov_common_handle(void)
 }
 static inline void kcov_remote_start_common(u64 id) {}
 static inline void kcov_remote_start_usb(u64 id) {}
+static inline void kcov_remote_start_usb_softirq(u64 id) {}
+static inline void kcov_remote_stop_softirq(void) {}
 
 #endif /* CONFIG_KCOV */
 #endif /* _LINUX_KCOV_H */
-- 
cgit v1.2.3


From 9ad9f45b3b91162b33abfe175ae75ab65718dbf5 Mon Sep 17 00:00:00 2001
From: Liu Yi L <yi.l.liu@intel.com>
Date: Thu, 7 Jan 2021 00:03:55 +0800
Subject: iommu/vt-d: Move intel_iommu info from struct intel_svm to struct
 intel_svm_dev

'struct intel_svm' is shared by all devices bound to a give process,
but records only a single pointer to a 'struct intel_iommu'. Consequently,
cache invalidations may only be applied to a single DMAR unit, and are
erroneously skipped for the other devices.

In preparation for fixing this, rework the structures so that the iommu
pointer resides in 'struct intel_svm_dev', allowing 'struct intel_svm'
to track them in its device list.

Fixes: 1c4f88b7f1f9 ("iommu/vt-d: Shared virtual address in scalable mode")
Cc: Lu Baolu <baolu.lu@linux.intel.com>
Cc: Jacob Pan <jacob.jun.pan@linux.intel.com>
Cc: Raj Ashok <ashok.raj@intel.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Reported-by: Guo Kaijie <Kaijie.Guo@intel.com>
Reported-by: Xin Zeng <xin.zeng@intel.com>
Signed-off-by: Guo Kaijie <Kaijie.Guo@intel.com>
Signed-off-by: Xin Zeng <xin.zeng@intel.com>
Signed-off-by: Liu Yi L <yi.l.liu@intel.com>
Tested-by: Guo Kaijie <Kaijie.Guo@intel.com>
Cc: stable@vger.kernel.org # v5.0+
Acked-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/1609949037-25291-2-git-send-email-yi.l.liu@intel.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/intel/svm.c   | 9 +++++----
 include/linux/intel-iommu.h | 2 +-
 2 files changed, 6 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index 9bcedd360235..790ef3497e7e 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -142,7 +142,7 @@ static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_d
 	}
 	desc.qw2 = 0;
 	desc.qw3 = 0;
-	qi_submit_sync(svm->iommu, &desc, 1, 0);
+	qi_submit_sync(sdev->iommu, &desc, 1, 0);
 
 	if (sdev->dev_iotlb) {
 		desc.qw0 = QI_DEV_EIOTLB_PASID(svm->pasid) |
@@ -166,7 +166,7 @@ static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_d
 		}
 		desc.qw2 = 0;
 		desc.qw3 = 0;
-		qi_submit_sync(svm->iommu, &desc, 1, 0);
+		qi_submit_sync(sdev->iommu, &desc, 1, 0);
 	}
 }
 
@@ -211,7 +211,7 @@ static void intel_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)
 	 */
 	rcu_read_lock();
 	list_for_each_entry_rcu(sdev, &svm->devs, list)
-		intel_pasid_tear_down_entry(svm->iommu, sdev->dev,
+		intel_pasid_tear_down_entry(sdev->iommu, sdev->dev,
 					    svm->pasid, true);
 	rcu_read_unlock();
 
@@ -364,6 +364,7 @@ int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev,
 	}
 	sdev->dev = dev;
 	sdev->sid = PCI_DEVID(info->bus, info->devfn);
+	sdev->iommu = iommu;
 
 	/* Only count users if device has aux domains */
 	if (iommu_dev_feature_enabled(dev, IOMMU_DEV_FEAT_AUX))
@@ -548,6 +549,7 @@ intel_svm_bind_mm(struct device *dev, unsigned int flags,
 		goto out;
 	}
 	sdev->dev = dev;
+	sdev->iommu = iommu;
 
 	ret = intel_iommu_enable_pasid(iommu, dev);
 	if (ret) {
@@ -577,7 +579,6 @@ intel_svm_bind_mm(struct device *dev, unsigned int flags,
 			kfree(sdev);
 			goto out;
 		}
-		svm->iommu = iommu;
 
 		if (pasid_max > intel_pasid_max_id)
 			pasid_max = intel_pasid_max_id;
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index d956987ed032..94522685a0d9 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -758,6 +758,7 @@ struct intel_svm_dev {
 	struct list_head list;
 	struct rcu_head rcu;
 	struct device *dev;
+	struct intel_iommu *iommu;
 	struct svm_dev_ops *ops;
 	struct iommu_sva sva;
 	u32 pasid;
@@ -771,7 +772,6 @@ struct intel_svm {
 	struct mmu_notifier notifier;
 	struct mm_struct *mm;
 
-	struct intel_iommu *iommu;
 	unsigned int flags;
 	u32 pasid;
 	int gpasid; /* In case that guest PASID is different from host PASID */
-- 
cgit v1.2.3


From 18abda7a2d555783d28ea1701f3ec95e96237a86 Mon Sep 17 00:00:00 2001
From: Liu Yi L <yi.l.liu@intel.com>
Date: Thu, 7 Jan 2021 00:03:56 +0800
Subject: iommu/vt-d: Fix general protection fault in aux_detach_device()

The aux-domain attach/detach are not tracked, some data structures might
be used after free. This causes general protection faults when multiple
subdevices are created and assigned to a same guest machine:

  | general protection fault, probably for non-canonical address 0xdead000000000100: 0000 [#1] SMP NOPTI
  | RIP: 0010:intel_iommu_aux_detach_device+0x12a/0x1f0
  | [...]
  | Call Trace:
  |  iommu_aux_detach_device+0x24/0x70
  |  vfio_mdev_detach_domain+0x3b/0x60
  |  ? vfio_mdev_set_domain+0x50/0x50
  |  iommu_group_for_each_dev+0x4f/0x80
  |  vfio_iommu_detach_group.isra.0+0x22/0x30
  |  vfio_iommu_type1_detach_group.cold+0x71/0x211
  |  ? find_exported_symbol_in_section+0x4a/0xd0
  |  ? each_symbol_section+0x28/0x50
  |  __vfio_group_unset_container+0x4d/0x150
  |  vfio_group_try_dissolve_container+0x25/0x30
  |  vfio_group_put_external_user+0x13/0x20
  |  kvm_vfio_group_put_external_user+0x27/0x40 [kvm]
  |  kvm_vfio_destroy+0x45/0xb0 [kvm]
  |  kvm_put_kvm+0x1bb/0x2e0 [kvm]
  |  kvm_vm_release+0x22/0x30 [kvm]
  |  __fput+0xcc/0x260
  |  ____fput+0xe/0x10
  |  task_work_run+0x8f/0xb0
  |  do_exit+0x358/0xaf0
  |  ? wake_up_state+0x10/0x20
  |  ? signal_wake_up_state+0x1a/0x30
  |  do_group_exit+0x47/0xb0
  |  __x64_sys_exit_group+0x18/0x20
  |  do_syscall_64+0x57/0x1d0
  |  entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fix the crash by tracking the subdevices when attaching and detaching
aux-domains.

Fixes: 67b8e02b5e76 ("iommu/vt-d: Aux-domain specific domain attach/detach")
Co-developed-by: Xin Zeng <xin.zeng@intel.com>
Signed-off-by: Xin Zeng <xin.zeng@intel.com>
Signed-off-by: Liu Yi L <yi.l.liu@intel.com>
Acked-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/1609949037-25291-3-git-send-email-yi.l.liu@intel.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/intel/iommu.c | 95 +++++++++++++++++++++++++++++++++------------
 include/linux/intel-iommu.h | 16 +++++---
 2 files changed, 82 insertions(+), 29 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 788119c5b021..d7720a836268 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -1877,6 +1877,7 @@ static struct dmar_domain *alloc_domain(int flags)
 		domain->flags |= DOMAIN_FLAG_USE_FIRST_LEVEL;
 	domain->has_iotlb_device = false;
 	INIT_LIST_HEAD(&domain->devices);
+	INIT_LIST_HEAD(&domain->subdevices);
 
 	return domain;
 }
@@ -2547,7 +2548,7 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu,
 	info->iommu = iommu;
 	info->pasid_table = NULL;
 	info->auxd_enabled = 0;
-	INIT_LIST_HEAD(&info->auxiliary_domains);
+	INIT_LIST_HEAD(&info->subdevices);
 
 	if (dev && dev_is_pci(dev)) {
 		struct pci_dev *pdev = to_pci_dev(info->dev);
@@ -4475,33 +4476,61 @@ is_aux_domain(struct device *dev, struct iommu_domain *domain)
 			domain->type == IOMMU_DOMAIN_UNMANAGED;
 }
 
-static void auxiliary_link_device(struct dmar_domain *domain,
-				  struct device *dev)
+static inline struct subdev_domain_info *
+lookup_subdev_info(struct dmar_domain *domain, struct device *dev)
+{
+	struct subdev_domain_info *sinfo;
+
+	if (!list_empty(&domain->subdevices)) {
+		list_for_each_entry(sinfo, &domain->subdevices, link_domain) {
+			if (sinfo->pdev == dev)
+				return sinfo;
+		}
+	}
+
+	return NULL;
+}
+
+static int auxiliary_link_device(struct dmar_domain *domain,
+				 struct device *dev)
 {
 	struct device_domain_info *info = get_domain_info(dev);
+	struct subdev_domain_info *sinfo = lookup_subdev_info(domain, dev);
 
 	assert_spin_locked(&device_domain_lock);
 	if (WARN_ON(!info))
-		return;
+		return -EINVAL;
+
+	if (!sinfo) {
+		sinfo = kzalloc(sizeof(*sinfo), GFP_ATOMIC);
+		sinfo->domain = domain;
+		sinfo->pdev = dev;
+		list_add(&sinfo->link_phys, &info->subdevices);
+		list_add(&sinfo->link_domain, &domain->subdevices);
+	}
 
-	domain->auxd_refcnt++;
-	list_add(&domain->auxd, &info->auxiliary_domains);
+	return ++sinfo->users;
 }
 
-static void auxiliary_unlink_device(struct dmar_domain *domain,
-				    struct device *dev)
+static int auxiliary_unlink_device(struct dmar_domain *domain,
+				   struct device *dev)
 {
 	struct device_domain_info *info = get_domain_info(dev);
+	struct subdev_domain_info *sinfo = lookup_subdev_info(domain, dev);
+	int ret;
 
 	assert_spin_locked(&device_domain_lock);
-	if (WARN_ON(!info))
-		return;
+	if (WARN_ON(!info || !sinfo || sinfo->users <= 0))
+		return -EINVAL;
 
-	list_del(&domain->auxd);
-	domain->auxd_refcnt--;
+	ret = --sinfo->users;
+	if (!ret) {
+		list_del(&sinfo->link_phys);
+		list_del(&sinfo->link_domain);
+		kfree(sinfo);
+	}
 
-	if (!domain->auxd_refcnt && domain->default_pasid > 0)
-		ioasid_put(domain->default_pasid);
+	return ret;
 }
 
 static int aux_domain_add_dev(struct dmar_domain *domain,
@@ -4530,6 +4559,19 @@ static int aux_domain_add_dev(struct dmar_domain *domain,
 	}
 
 	spin_lock_irqsave(&device_domain_lock, flags);
+	ret = auxiliary_link_device(domain, dev);
+	if (ret <= 0)
+		goto link_failed;
+
+	/*
+	 * Subdevices from the same physical device can be attached to the
+	 * same domain. For such cases, only the first subdevice attachment
+	 * needs to go through the full steps in this function. So if ret >
+	 * 1, just goto out.
+	 */
+	if (ret > 1)
+		goto out;
+
 	/*
 	 * iommu->lock must be held to attach domain to iommu and setup the
 	 * pasid entry for second level translation.
@@ -4548,10 +4590,9 @@ static int aux_domain_add_dev(struct dmar_domain *domain,
 						     domain->default_pasid);
 	if (ret)
 		goto table_failed;
-	spin_unlock(&iommu->lock);
-
-	auxiliary_link_device(domain, dev);
 
+	spin_unlock(&iommu->lock);
+out:
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 
 	return 0;
@@ -4560,8 +4601,10 @@ table_failed:
 	domain_detach_iommu(domain, iommu);
 attach_failed:
 	spin_unlock(&iommu->lock);
+	auxiliary_unlink_device(domain, dev);
+link_failed:
 	spin_unlock_irqrestore(&device_domain_lock, flags);
-	if (!domain->auxd_refcnt && domain->default_pasid > 0)
+	if (list_empty(&domain->subdevices) && domain->default_pasid > 0)
 		ioasid_put(domain->default_pasid);
 
 	return ret;
@@ -4581,14 +4624,18 @@ static void aux_domain_remove_dev(struct dmar_domain *domain,
 	info = get_domain_info(dev);
 	iommu = info->iommu;
 
-	auxiliary_unlink_device(domain, dev);
-
-	spin_lock(&iommu->lock);
-	intel_pasid_tear_down_entry(iommu, dev, domain->default_pasid, false);
-	domain_detach_iommu(domain, iommu);
-	spin_unlock(&iommu->lock);
+	if (!auxiliary_unlink_device(domain, dev)) {
+		spin_lock(&iommu->lock);
+		intel_pasid_tear_down_entry(iommu, dev,
+					    domain->default_pasid, false);
+		domain_detach_iommu(domain, iommu);
+		spin_unlock(&iommu->lock);
+	}
 
 	spin_unlock_irqrestore(&device_domain_lock, flags);
+
+	if (list_empty(&domain->subdevices) && domain->default_pasid > 0)
+		ioasid_put(domain->default_pasid);
 }
 
 static int prepare_domain_attach_device(struct iommu_domain *domain,
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 94522685a0d9..09c6a0bf3892 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -533,11 +533,10 @@ struct dmar_domain {
 					/* Domain ids per IOMMU. Use u16 since
 					 * domain ids are 16 bit wide according
 					 * to VT-d spec, section 9.3 */
-	unsigned int	auxd_refcnt;	/* Refcount of auxiliary attaching */
 
 	bool has_iotlb_device;
 	struct list_head devices;	/* all devices' list */
-	struct list_head auxd;		/* link to device's auxiliary list */
+	struct list_head subdevices;	/* all subdevices' list */
 	struct iova_domain iovad;	/* iova's that belong to this domain */
 
 	struct dma_pte	*pgd;		/* virtual address */
@@ -610,14 +609,21 @@ struct intel_iommu {
 	struct dmar_drhd_unit *drhd;
 };
 
+/* Per subdevice private data */
+struct subdev_domain_info {
+	struct list_head link_phys;	/* link to phys device siblings */
+	struct list_head link_domain;	/* link to domain siblings */
+	struct device *pdev;		/* physical device derived from */
+	struct dmar_domain *domain;	/* aux-domain */
+	int users;			/* user count */
+};
+
 /* PCI domain-device relationship */
 struct device_domain_info {
 	struct list_head link;	/* link to domain siblings */
 	struct list_head global; /* link to global list */
 	struct list_head table;	/* link to pasid table */
-	struct list_head auxiliary_domains; /* auxiliary domains
-					     * attached to this device
-					     */
+	struct list_head subdevices; /* subdevices sibling */
 	u32 segment;		/* PCI segment number */
 	u8 bus;			/* PCI bus number */
 	u8 devfn;		/* PCI devfn number */
-- 
cgit v1.2.3


From ee61cfd955a64a58ed35cbcfc54068fcbd486945 Mon Sep 17 00:00:00 2001
From: Shawn Guo <shawn.guo@linaro.org>
Date: Thu, 31 Dec 2020 19:35:25 +0800
Subject: ACPI: scan: add stub acpi_create_platform_device() for !CONFIG_ACPI

It adds a stub acpi_create_platform_device() for !CONFIG_ACPI build, so
that caller doesn't have to deal with !CONFIG_ACPI build issue.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Shawn Guo <shawn.guo@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/acpi.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 2630c2e953f7..053bf05fb1f7 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -885,6 +885,13 @@ static inline int acpi_device_modalias(struct device *dev,
 	return -ENODEV;
 }
 
+static inline struct platform_device *
+acpi_create_platform_device(struct acpi_device *adev,
+			    struct property_entry *properties)
+{
+	return NULL;
+}
+
 static inline bool acpi_dma_supported(struct acpi_device *adev)
 {
 	return false;
-- 
cgit v1.2.3


From 9c9be85f6b59d80efe4705109c0396df18d4e11d Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@nvidia.com>
Date: Tue, 24 Nov 2020 22:16:23 +0200
Subject: net/mlx5e: Add missing capability check for uplink follow

Expose firmware indication that it supports setting eswitch uplink state
to follow (follow the physical link). Condition setting the eswitch
uplink admin-state with this capability bit. Older FW may not support
the uplink state setting.

Fixes: 7d0314b11cdd ("net/mlx5e: Modify uplink state on interface up/down")
Signed-off-by: Aya Levin <ayal@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 3 ++-
 include/linux/mlx5/mlx5_ifc.h                     | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 7a79d330c075..6a852b4901aa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3161,7 +3161,8 @@ static void mlx5e_modify_admin_state(struct mlx5_core_dev *mdev,
 
 	mlx5_set_port_admin_status(mdev, state);
 
-	if (mlx5_eswitch_mode(mdev) != MLX5_ESWITCH_LEGACY)
+	if (mlx5_eswitch_mode(mdev) == MLX5_ESWITCH_OFFLOADS ||
+	    !MLX5_CAP_GEN(mdev, uplink_follow))
 		return;
 
 	if (state == MLX5_PORT_UP)
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 8fbddec26eb8..442c0160caab 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1280,7 +1280,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8	   ece_support[0x1];
 	u8	   reserved_at_a4[0x7];
 	u8         log_max_srq[0x5];
-	u8         reserved_at_b0[0x2];
+	u8         reserved_at_b0[0x1];
+	u8         uplink_follow[0x1];
 	u8         ts_cqe_to_dest_cqn[0x1];
 	u8         reserved_at_b3[0xd];
 
-- 
cgit v1.2.3


From a91bd6223ecd46addc71ee6fcd432206d39365d2 Mon Sep 17 00:00:00 2001
From: Petr Mladek <pmladek@suse.com>
Date: Fri, 8 Jan 2021 12:48:47 +0100
Subject: Revert "init/console: Use ttynull as a fallback when there is no
 console"

This reverts commit 757055ae8dedf5333af17b3b5b4b70ba9bc9da4e.

The commit caused that ttynull was used as the default console
on several systems[1][2][3]. As a result, the console was
blank even when a better alternative existed.

It happened when there was no console configured
on the command line and ttynull_init() was the first initcall
calling register_console().

Or it happened when /dev/ did not exist when console_on_rootfs()
was called. It was not able to open /dev/console even though
a console driver was registered. It tried to add ttynull console
but it obviously did not help. But ttynull became the preferred
console and was used by /dev/console when it was available later.

The commit tried to fix a historical problem that have been there
for ages. The primary motivation was the commit 3cffa06aeef7ece30f6
("printk/console: Allow to disable console output by using console=""
 or console=null"). It provided a clean solution for a workaround
 that was widely used and worked only by chance.

This revert causes that the console="" or console=null command line
options will again work only by chance. These options will cause that
a particular console will be preferred and the default (tty) ones
will not get enabled. There will be no console registered at
all. As a result there won't be stdin, stdout, and stderr for
the init process. But it worked exactly this way even before.

The proper solution has to fulfill many conditions:

  + Register ttynull only when explicitly required or as
    the ultimate fallback.

  + ttynull should get associated with /dev/console but it must
    not become preferred console when used as a fallback.
    Especially, it must still be possible to replace it
    by a better console later.

Such a change requires clean up of the register_console() code.
Otherwise, it would be even harder to follow. Especially, the use
of has_preferred_console and CON_CONSDEV flag is tricky. The clean
up is risky. The ordering of consoles is not well defined. And
any changes tend to break existing user settings.

Do the revert at the least risky solution for now.

[1] https://lore.kernel.org/linux-kselftest/20201221144302.GR4077@smile.fi.intel.com/
[2] https://lore.kernel.org/lkml/d2a3b3c0-e548-7dd1-730f-59bc5c04e191@synopsys.com/
[3] https://patchwork.ozlabs.org/project/linux-um/patch/20210105120128.10854-1-thomas@m3y3r.de/

Reported-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reported-by: Vineet Gupta <vgupta@synopsys.com>
Reported-by: Thomas Meyer <thomas@m3y3r.de>
Signed-off-by: Petr Mladek <pmladek@suse.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/tty/Kconfig     | 14 ++++++++++++++
 drivers/tty/Makefile    |  3 ++-
 drivers/tty/ttynull.c   | 18 ------------------
 include/linux/console.h |  3 ---
 init/main.c             | 10 ++--------
 5 files changed, 18 insertions(+), 30 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/Kconfig b/drivers/tty/Kconfig
index 47a6e42f0d04..e15cd6b5bb99 100644
--- a/drivers/tty/Kconfig
+++ b/drivers/tty/Kconfig
@@ -401,6 +401,20 @@ config MIPS_EJTAG_FDC_KGDB_CHAN
 	help
 	  FDC channel number to use for KGDB.
 
+config NULL_TTY
+	tristate "NULL TTY driver"
+	help
+	  Say Y here if you want a NULL TTY which simply discards messages.
+
+	  This is useful to allow userspace applications which expect a console
+	  device to work without modifications even when no console is
+	  available or desired.
+
+	  In order to use this driver, you should redirect the console to this
+	  TTY, or boot the kernel with console=ttynull.
+
+	  If unsure, say N.
+
 config TRACE_ROUTER
 	tristate "Trace data router for MIPI P1149.7 cJTAG standard"
 	depends on TRACE_SINK
diff --git a/drivers/tty/Makefile b/drivers/tty/Makefile
index 3c1c5a9240a7..b3ccae932660 100644
--- a/drivers/tty/Makefile
+++ b/drivers/tty/Makefile
@@ -2,7 +2,7 @@
 obj-$(CONFIG_TTY)		+= tty_io.o n_tty.o tty_ioctl.o tty_ldisc.o \
 				   tty_buffer.o tty_port.o tty_mutex.o \
 				   tty_ldsem.o tty_baudrate.o tty_jobctrl.o \
-				   n_null.o ttynull.o
+				   n_null.o
 obj-$(CONFIG_LEGACY_PTYS)	+= pty.o
 obj-$(CONFIG_UNIX98_PTYS)	+= pty.o
 obj-$(CONFIG_AUDIT)		+= tty_audit.o
@@ -25,6 +25,7 @@ obj-$(CONFIG_ISI)		+= isicom.o
 obj-$(CONFIG_MOXA_INTELLIO)	+= moxa.o
 obj-$(CONFIG_MOXA_SMARTIO)	+= mxser.o
 obj-$(CONFIG_NOZOMI)		+= nozomi.o
+obj-$(CONFIG_NULL_TTY)	        += ttynull.o
 obj-$(CONFIG_ROCKETPORT)	+= rocket.o
 obj-$(CONFIG_SYNCLINK_GT)	+= synclink_gt.o
 obj-$(CONFIG_PPC_EPAPR_HV_BYTECHAN) += ehv_bytechan.o
diff --git a/drivers/tty/ttynull.c b/drivers/tty/ttynull.c
index eced70ec54e1..17f05b7eb6d3 100644
--- a/drivers/tty/ttynull.c
+++ b/drivers/tty/ttynull.c
@@ -2,13 +2,6 @@
 /*
  * Copyright (C) 2019 Axis Communications AB
  *
- * The console is useful for userspace applications which expect a console
- * device to work without modifications even when no console is available
- * or desired.
- *
- * In order to use this driver, you should redirect the console to this
- * TTY, or boot the kernel with console=ttynull.
- *
  * Based on ttyprintk.c:
  *  Copyright (C) 2010 Samo Pogacnik
  */
@@ -66,17 +59,6 @@ static struct console ttynull_console = {
 	.device = ttynull_device,
 };
 
-void __init register_ttynull_console(void)
-{
-	if (!ttynull_driver)
-		return;
-
-	if (add_preferred_console(ttynull_console.name, 0, NULL))
-		return;
-
-	register_console(&ttynull_console);
-}
-
 static int __init ttynull_init(void)
 {
 	struct tty_driver *driver;
diff --git a/include/linux/console.h b/include/linux/console.h
index dbe78e8e2602..20874db50bc8 100644
--- a/include/linux/console.h
+++ b/include/linux/console.h
@@ -186,12 +186,9 @@ extern int braille_register_console(struct console *, int index,
 extern int braille_unregister_console(struct console *);
 #ifdef CONFIG_TTY
 extern void console_sysfs_notify(void);
-extern void register_ttynull_console(void);
 #else
 static inline void console_sysfs_notify(void)
 { }
-static inline void register_ttynull_console(void)
-{ }
 #endif
 extern bool console_suspend_enabled;
 
diff --git a/init/main.c b/init/main.c
index 421640fca375..c68d784376ca 100644
--- a/init/main.c
+++ b/init/main.c
@@ -1480,14 +1480,8 @@ void __init console_on_rootfs(void)
 	struct file *file = filp_open("/dev/console", O_RDWR, 0);
 
 	if (IS_ERR(file)) {
-		pr_err("Warning: unable to open an initial console. Fallback to ttynull.\n");
-		register_ttynull_console();
-
-		file = filp_open("/dev/console", O_RDWR, 0);
-		if (IS_ERR(file)) {
-			pr_err("Warning: Failed to add ttynull console. No stdin, stdout, and stderr for the init process!\n");
-			return;
-		}
+		pr_err("Warning: unable to open an initial console.\n");
+		return;
 	}
 	init_dup(file);
 	init_dup(file);
-- 
cgit v1.2.3


From 9b5948267adc9e689da609eb61cf7ed49cae5fa8 Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Fri, 8 Jan 2021 11:15:56 -0500
Subject: dm integrity: fix flush with external metadata device

With external metadata device, flush requests are not passed down to the
data device.

Fix this by submitting the flush request in dm_integrity_flush_buffers. In
order to not degrade performance, we overlap the data device flush with
the metadata device flush.

Reported-by: Lukas Straub <lukasstraub2@web.de>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/dm-bufio.c     |  6 +++++
 drivers/md/dm-integrity.c | 60 ++++++++++++++++++++++++++++++++++++++---------
 include/linux/dm-bufio.h  |  1 +
 3 files changed, 56 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 9c1a86bde658..fce4cbf9529d 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -1534,6 +1534,12 @@ sector_t dm_bufio_get_device_size(struct dm_bufio_client *c)
 }
 EXPORT_SYMBOL_GPL(dm_bufio_get_device_size);
 
+struct dm_io_client *dm_bufio_get_dm_io_client(struct dm_bufio_client *c)
+{
+	return c->dm_io;
+}
+EXPORT_SYMBOL_GPL(dm_bufio_get_dm_io_client);
+
 sector_t dm_bufio_get_block_number(struct dm_buffer *b)
 {
 	return b->block;
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 5a7a1b90e671..11c7c538f7a9 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -1379,12 +1379,52 @@ thorough_test:
 #undef MAY_BE_HASH
 }
 
-static void dm_integrity_flush_buffers(struct dm_integrity_c *ic)
+struct flush_request {
+	struct dm_io_request io_req;
+	struct dm_io_region io_reg;
+	struct dm_integrity_c *ic;
+	struct completion comp;
+};
+
+static void flush_notify(unsigned long error, void *fr_)
+{
+	struct flush_request *fr = fr_;
+	if (unlikely(error != 0))
+		dm_integrity_io_error(fr->ic, "flusing disk cache", -EIO);
+	complete(&fr->comp);
+}
+
+static void dm_integrity_flush_buffers(struct dm_integrity_c *ic, bool flush_data)
 {
 	int r;
+
+	struct flush_request fr;
+
+	if (!ic->meta_dev)
+		flush_data = false;
+	if (flush_data) {
+		fr.io_req.bi_op = REQ_OP_WRITE,
+		fr.io_req.bi_op_flags = REQ_PREFLUSH | REQ_SYNC,
+		fr.io_req.mem.type = DM_IO_KMEM,
+		fr.io_req.mem.ptr.addr = NULL,
+		fr.io_req.notify.fn = flush_notify,
+		fr.io_req.notify.context = &fr;
+		fr.io_req.client = dm_bufio_get_dm_io_client(ic->bufio),
+		fr.io_reg.bdev = ic->dev->bdev,
+		fr.io_reg.sector = 0,
+		fr.io_reg.count = 0,
+		fr.ic = ic;
+		init_completion(&fr.comp);
+		r = dm_io(&fr.io_req, 1, &fr.io_reg, NULL);
+		BUG_ON(r);
+	}
+
 	r = dm_bufio_write_dirty_buffers(ic->bufio);
 	if (unlikely(r))
 		dm_integrity_io_error(ic, "writing tags", r);
+
+	if (flush_data)
+		wait_for_completion(&fr.comp);
 }
 
 static void sleep_on_endio_wait(struct dm_integrity_c *ic)
@@ -2110,7 +2150,7 @@ offload_to_thread:
 
 	if (unlikely(dio->op == REQ_OP_DISCARD) && likely(ic->mode != 'D')) {
 		integrity_metadata(&dio->work);
-		dm_integrity_flush_buffers(ic);
+		dm_integrity_flush_buffers(ic, false);
 
 		dio->in_flight = (atomic_t)ATOMIC_INIT(1);
 		dio->completion = NULL;
@@ -2195,7 +2235,7 @@ static void integrity_commit(struct work_struct *w)
 	flushes = bio_list_get(&ic->flush_bio_list);
 	if (unlikely(ic->mode != 'J')) {
 		spin_unlock_irq(&ic->endio_wait.lock);
-		dm_integrity_flush_buffers(ic);
+		dm_integrity_flush_buffers(ic, true);
 		goto release_flush_bios;
 	}
 
@@ -2409,7 +2449,7 @@ skip_io:
 	complete_journal_op(&comp);
 	wait_for_completion_io(&comp.comp);
 
-	dm_integrity_flush_buffers(ic);
+	dm_integrity_flush_buffers(ic, true);
 }
 
 static void integrity_writer(struct work_struct *w)
@@ -2451,7 +2491,7 @@ static void recalc_write_super(struct dm_integrity_c *ic)
 {
 	int r;
 
-	dm_integrity_flush_buffers(ic);
+	dm_integrity_flush_buffers(ic, false);
 	if (dm_integrity_failed(ic))
 		return;
 
@@ -2654,7 +2694,7 @@ static void bitmap_flush_work(struct work_struct *work)
 	unsigned long limit;
 	struct bio *bio;
 
-	dm_integrity_flush_buffers(ic);
+	dm_integrity_flush_buffers(ic, false);
 
 	range.logical_sector = 0;
 	range.n_sectors = ic->provided_data_sectors;
@@ -2663,9 +2703,7 @@ static void bitmap_flush_work(struct work_struct *work)
 	add_new_range_and_wait(ic, &range);
 	spin_unlock_irq(&ic->endio_wait.lock);
 
-	dm_integrity_flush_buffers(ic);
-	if (ic->meta_dev)
-		blkdev_issue_flush(ic->dev->bdev, GFP_NOIO);
+	dm_integrity_flush_buffers(ic, true);
 
 	limit = ic->provided_data_sectors;
 	if (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING)) {
@@ -2934,11 +2972,11 @@ static void dm_integrity_postsuspend(struct dm_target *ti)
 		if (ic->meta_dev)
 			queue_work(ic->writer_wq, &ic->writer_work);
 		drain_workqueue(ic->writer_wq);
-		dm_integrity_flush_buffers(ic);
+		dm_integrity_flush_buffers(ic, true);
 	}
 
 	if (ic->mode == 'B') {
-		dm_integrity_flush_buffers(ic);
+		dm_integrity_flush_buffers(ic, true);
 #if 1
 		/* set to 0 to test bitmap replay code */
 		init_journal(ic, 0, ic->journal_sections, 0);
diff --git a/include/linux/dm-bufio.h b/include/linux/dm-bufio.h
index 29d255fdd5d6..90bd558a17f5 100644
--- a/include/linux/dm-bufio.h
+++ b/include/linux/dm-bufio.h
@@ -150,6 +150,7 @@ void dm_bufio_set_minimum_buffers(struct dm_bufio_client *c, unsigned n);
 
 unsigned dm_bufio_get_block_size(struct dm_bufio_client *c);
 sector_t dm_bufio_get_device_size(struct dm_bufio_client *c);
+struct dm_io_client *dm_bufio_get_dm_io_client(struct dm_bufio_client *c);
 sector_t dm_bufio_get_block_number(struct dm_buffer *b);
 void *dm_bufio_get_block_data(struct dm_buffer *b);
 void *dm_bufio_get_aux_data(struct dm_buffer *b);
-- 
cgit v1.2.3


From 29766bcffad03da66892bef82674883e31f78fec Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Sat, 9 Jan 2021 17:18:32 -0500
Subject: net: support kmap_local forced debugging in skb_frag_foreach

Skb frags may be backed by highmem and/or compound pages. Highmem
pages need kmap_atomic mappings to access. But kmap_atomic maps a
single page, not the entire compound page.

skb_foreach_page iterates over an skb frag, in one step in the common
case, page by page only if kmap_atomic must be called for each page.
The decision logic is captured in skb_frag_must_loop.

CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP extends kmap from highmem to all
pages, to increase code coverage.

Extend skb_frag_must_loop to this new condition.

Link: https://lore.kernel.org/linux-mm/20210106180132.41dc249d@gandalf.local.home/
Fixes: 0e91a0c6984c ("mm/highmem: Provide CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP")
Reported-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Tested-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/skbuff.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 333bcdc39635..c858adfb5a82 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -366,7 +366,7 @@ static inline void skb_frag_size_sub(skb_frag_t *frag, int delta)
 static inline bool skb_frag_must_loop(struct page *p)
 {
 #if defined(CONFIG_HIGHMEM)
-	if (PageHighMem(p))
+	if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP) || PageHighMem(p))
 		return true;
 #endif
 	return false;
-- 
cgit v1.2.3


From 97550f6fa59254435d864b92603de3ca4b5a99f8 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Sat, 9 Jan 2021 17:18:33 -0500
Subject: net: compound page support in skb_seq_read

skb_seq_read iterates over an skb, returning pointer and length of
the next data range with each call.

It relies on kmap_atomic to access highmem pages when needed.

An skb frag may be backed by a compound page, but kmap_atomic maps
only a single page. There are not enough kmap slots to always map all
pages concurrently.

Instead, if kmap_atomic is needed, iterate over each page.

As this increases the number of calls, avoid this unless needed.
The necessary condition is captured in skb_frag_must_loop.

I tried to make the change as obvious as possible. It should be easy
to verify that nothing changes if skb_frag_must_loop returns false.

Tested:
  On an x86 platform with
    CONFIG_HIGHMEM=y
    CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP=y
    CONFIG_NETFILTER_XT_MATCH_STRING=y

  Run
    ip link set dev lo mtu 1500
    iptables -A OUTPUT -m string --string 'badstring' -algo bm -j ACCEPT
    dd if=/dev/urandom of=in bs=1M count=20
    nc -l -p 8000 > /dev/null &
    nc -w 1 -q 0 localhost 8000 < in

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/skbuff.h |  1 +
 net/core/skbuff.c      | 28 +++++++++++++++++++++++-----
 2 files changed, 24 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index c858adfb5a82..5f60c9e907c9 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1203,6 +1203,7 @@ struct skb_seq_state {
 	struct sk_buff	*root_skb;
 	struct sk_buff	*cur_skb;
 	__u8		*frag_data;
+	__u32		frag_off;
 };
 
 void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from,
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index b6f2b520a9b7..0da035c1e53f 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3442,6 +3442,7 @@ void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from,
 	st->root_skb = st->cur_skb = skb;
 	st->frag_idx = st->stepped_offset = 0;
 	st->frag_data = NULL;
+	st->frag_off = 0;
 }
 EXPORT_SYMBOL(skb_prepare_seq_read);
 
@@ -3496,14 +3497,27 @@ next_skb:
 		st->stepped_offset += skb_headlen(st->cur_skb);
 
 	while (st->frag_idx < skb_shinfo(st->cur_skb)->nr_frags) {
+		unsigned int pg_idx, pg_off, pg_sz;
+
 		frag = &skb_shinfo(st->cur_skb)->frags[st->frag_idx];
-		block_limit = skb_frag_size(frag) + st->stepped_offset;
 
+		pg_idx = 0;
+		pg_off = skb_frag_off(frag);
+		pg_sz = skb_frag_size(frag);
+
+		if (skb_frag_must_loop(skb_frag_page(frag))) {
+			pg_idx = (pg_off + st->frag_off) >> PAGE_SHIFT;
+			pg_off = offset_in_page(pg_off + st->frag_off);
+			pg_sz = min_t(unsigned int, pg_sz - st->frag_off,
+						    PAGE_SIZE - pg_off);
+		}
+
+		block_limit = pg_sz + st->stepped_offset;
 		if (abs_offset < block_limit) {
 			if (!st->frag_data)
-				st->frag_data = kmap_atomic(skb_frag_page(frag));
+				st->frag_data = kmap_atomic(skb_frag_page(frag) + pg_idx);
 
-			*data = (u8 *) st->frag_data + skb_frag_off(frag) +
+			*data = (u8 *)st->frag_data + pg_off +
 				(abs_offset - st->stepped_offset);
 
 			return block_limit - abs_offset;
@@ -3514,8 +3528,12 @@ next_skb:
 			st->frag_data = NULL;
 		}
 
-		st->frag_idx++;
-		st->stepped_offset += skb_frag_size(frag);
+		st->stepped_offset += pg_sz;
+		st->frag_off += pg_sz;
+		if (st->frag_off == skb_frag_size(frag)) {
+			st->frag_off = 0;
+			st->frag_idx++;
+		}
 	}
 
 	if (st->frag_data) {
-- 
cgit v1.2.3


From aba428a0c612bb259891307da12e22efd0fab14c Mon Sep 17 00:00:00 2001
From: Chunguang Xu <brookxu@tencent.com>
Date: Tue, 1 Dec 2020 17:52:31 +0800
Subject: timekeeping: Remove unused get_seconds()

The get_seconds() cleanup seems to have been completed, now it is
time to delete the legacy interface to avoid misuse later.

Signed-off-by: Chunguang Xu <brookxu@tencent.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/1606816351-26900-1-git-send-email-brookxu@tencent.com
---
 include/linux/ktime.h         |  1 -
 include/linux/timekeeping32.h | 14 --------------
 kernel/time/timekeeping.c     |  3 +--
 3 files changed, 1 insertion(+), 17 deletions(-)
 delete mode 100644 include/linux/timekeeping32.h

(limited to 'include/linux')

diff --git a/include/linux/ktime.h b/include/linux/ktime.h
index a12b5523cc18..73f20deb497d 100644
--- a/include/linux/ktime.h
+++ b/include/linux/ktime.h
@@ -230,6 +230,5 @@ static inline ktime_t ms_to_ktime(u64 ms)
 }
 
 # include <linux/timekeeping.h>
-# include <linux/timekeeping32.h>
 
 #endif
diff --git a/include/linux/timekeeping32.h b/include/linux/timekeeping32.h
deleted file mode 100644
index 266017fc9ee9..000000000000
--- a/include/linux/timekeeping32.h
+++ /dev/null
@@ -1,14 +0,0 @@
-#ifndef _LINUX_TIMEKEEPING32_H
-#define _LINUX_TIMEKEEPING32_H
-/*
- * These interfaces are all based on the old timespec type
- * and should get replaced with the timespec64 based versions
- * over time so we can remove the file here.
- */
-
-static inline unsigned long get_seconds(void)
-{
-	return ktime_get_real_seconds();
-}
-
-#endif
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index a45cedda93a7..6aee5768c86f 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -991,8 +991,7 @@ EXPORT_SYMBOL_GPL(ktime_get_seconds);
 /**
  * ktime_get_real_seconds - Get the seconds portion of CLOCK_REALTIME
  *
- * Returns the wall clock seconds since 1970. This replaces the
- * get_seconds() interface which is not y2038 safe on 32bit systems.
+ * Returns the wall clock seconds since 1970.
  *
  * For 64bit systems the fast access to tk->xtime_sec is preserved. On
  * 32bit systems the access must be protected with the sequence
-- 
cgit v1.2.3


From 7ea510b92c7c9b4eb5ff72e6b4bbad4b0407a914 Mon Sep 17 00:00:00 2001
From: Hugh Dickins <hughd@google.com>
Date: Tue, 12 Jan 2021 15:49:11 -0800
Subject: mm/memcontrol: fix warning in mem_cgroup_page_lruvec()

Boot a CONFIG_MEMCG=y kernel with "cgroup_disabled=memory" and you are
met by a series of warnings from the VM_WARN_ON_ONCE_PAGE(!memcg, page)
recently added to the inline mem_cgroup_page_lruvec().

An earlier attempt to place that warning, in mem_cgroup_lruvec(), had
been careful to do so after weeding out the mem_cgroup_disabled() case;
but was itself invalid because of the mem_cgroup_lruvec(NULL, pgdat) in
clear_pgdat_congested() and age_active_anon().

Warning in mem_cgroup_page_lruvec() was once useful in detecting a KSM
charge bug, so may be worth keeping: but skip if mem_cgroup_disabled().

Link: https://lkml.kernel.org/r/alpine.LSU.2.11.2101032056260.1093@eggly.anvils
Fixes: 9a1ac2288cf1 ("mm/memcontrol:rewrite mem_cgroup_page_lruvec()")
Signed-off-by: Hugh Dickins <hughd@google.com>
Reviewed-by: Alex Shi <alex.shi@linux.alibaba.com>
Acked-by: Roman Gushchin <guro@fb.com>
Acked-by: Chris Down <chris@chrisdown.name>
Reviewed-by: Baoquan He <bhe@redhat.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Hui Su <sh_def@163.com>
Cc: Lorenzo Stoakes <lstoakes@gmail.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Shakeel Butt <shakeelb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index d827bd7f3bfe..eeb0b52203e9 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -665,7 +665,7 @@ static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page,
 {
 	struct mem_cgroup *memcg = page_memcg(page);
 
-	VM_WARN_ON_ONCE_PAGE(!memcg, page);
+	VM_WARN_ON_ONCE_PAGE(!memcg && !mem_cgroup_disabled(), page);
 	return mem_cgroup_lruvec(memcg, pgdat);
 }
 
-- 
cgit v1.2.3


From 29970dc24faf0078beb4efab5455b4f504d2198d Mon Sep 17 00:00:00 2001
From: Hailong Liu <liu.hailong6@zte.com.cn>
Date: Tue, 12 Jan 2021 15:49:14 -0800
Subject: arm/kasan: fix the array size of kasan_early_shadow_pte[]
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The size of kasan_early_shadow_pte[] now is PTRS_PER_PTE which defined
to 512 for arm.  This means that it only covers the prev Linux pte
entries, but not the HWTABLE pte entries for arm.

The reason it currently works is that the symbol kasan_early_shadow_page
immediately following kasan_early_shadow_pte in memory is page aligned,
which makes kasan_early_shadow_pte look like a 4KB size array.  But we
can't ensure the order is always right with different compiler/linker,
or if more bss symbols are introduced.

We had a test with QEMU + vexpress：put a 512KB-size symbol with
attribute __section(".bss..page_aligned") after kasan_early_shadow_pte,
and poisoned it after kasan_early_init().  Then enabled CONFIG_KASAN, it
failed to boot up.

Link: https://lkml.kernel.org/r/20210109044622.8312-1-hailongliiu@yeah.net
Signed-off-by: Hailong Liu <liu.hailong6@zte.com.cn>
Signed-off-by: Ziliang Guo <guo.ziliang@zte.com.cn>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Alexander Potapenko <glider@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kasan.h | 6 +++++-
 mm/kasan/init.c       | 3 ++-
 2 files changed, 7 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 5e0655fb2a6f..fe1ae73ff8b5 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -35,8 +35,12 @@ struct kunit_kasan_expectation {
 #define KASAN_SHADOW_INIT 0
 #endif
 
+#ifndef PTE_HWTABLE_PTRS
+#define PTE_HWTABLE_PTRS 0
+#endif
+
 extern unsigned char kasan_early_shadow_page[PAGE_SIZE];
-extern pte_t kasan_early_shadow_pte[PTRS_PER_PTE];
+extern pte_t kasan_early_shadow_pte[PTRS_PER_PTE + PTE_HWTABLE_PTRS];
 extern pmd_t kasan_early_shadow_pmd[PTRS_PER_PMD];
 extern pud_t kasan_early_shadow_pud[PTRS_PER_PUD];
 extern p4d_t kasan_early_shadow_p4d[MAX_PTRS_PER_P4D];
diff --git a/mm/kasan/init.c b/mm/kasan/init.c
index bc0ad208b3a7..7ca0b92d5886 100644
--- a/mm/kasan/init.c
+++ b/mm/kasan/init.c
@@ -64,7 +64,8 @@ static inline bool kasan_pmd_table(pud_t pud)
 	return false;
 }
 #endif
-pte_t kasan_early_shadow_pte[PTRS_PER_PTE] __page_aligned_bss;
+pte_t kasan_early_shadow_pte[PTRS_PER_PTE + PTE_HWTABLE_PTRS]
+	__page_aligned_bss;
 
 static inline bool kasan_pte_table(pmd_t pmd)
 {
-- 
cgit v1.2.3


From b90d72a6bfdb5e5c62cd223a8cdf4045bfbcb94d Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Tue, 12 Jan 2021 22:18:55 +0000
Subject: Revert "arm64: Enable perf events based hard lockup detector"

This reverts commit 367c820ef08082e68df8a3bc12e62393af21e4b5.

lockup_detector_init() makes heavy use of per-cpu variables and must be
called with preemption disabled. Usually, it's handled early during boot
in kernel_init_freeable(), before SMP has been initialised.

Since we do not know whether or not our PMU interrupt can be signalled
as an NMI until considerably later in the boot process, the Arm PMU
driver attempts to re-initialise the lockup detector off the back of a
device_initcall(). Unfortunately, this is called from preemptible
context and results in the following splat:

  | BUG: using smp_processor_id() in preemptible [00000000] code: swapper/0/1
  | caller is debug_smp_processor_id+0x20/0x2c
  | CPU: 2 PID: 1 Comm: swapper/0 Not tainted 5.10.0+ #276
  | Hardware name: linux,dummy-virt (DT)
  | Call trace:
  |   dump_backtrace+0x0/0x3c0
  |   show_stack+0x20/0x6c
  |   dump_stack+0x2f0/0x42c
  |   check_preemption_disabled+0x1cc/0x1dc
  |   debug_smp_processor_id+0x20/0x2c
  |   hardlockup_detector_event_create+0x34/0x18c
  |   hardlockup_detector_perf_init+0x2c/0x134
  |   watchdog_nmi_probe+0x18/0x24
  |   lockup_detector_init+0x44/0xa8
  |   armv8_pmu_driver_init+0x54/0x78
  |   do_one_initcall+0x184/0x43c
  |   kernel_init_freeable+0x368/0x380
  |   kernel_init+0x1c/0x1cc
  |   ret_from_fork+0x10/0x30

Rather than bodge this with raw_smp_processor_id() or randomly disabling
preemption, simply revert the culprit for now until we figure out how to
do this properly.

Reported-by: Lecopzer Chen <lecopzer.chen@mediatek.com>
Signed-off-by: Will Deacon <will@kernel.org>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Cc: Sumit Garg <sumit.garg@linaro.org>
Cc: Alexandru Elisei <alexandru.elisei@arm.com>
Link: https://lore.kernel.org/r/20201221162249.3119-1-lecopzer.chen@mediatek.com
Link: https://lore.kernel.org/r/20210112221855.10666-1-will@kernel.org
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/Kconfig             |  2 --
 arch/arm64/kernel/perf_event.c | 41 ++---------------------------------------
 drivers/perf/arm_pmu.c         |  5 -----
 include/linux/perf/arm_pmu.h   |  2 --
 4 files changed, 2 insertions(+), 48 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 05e17351e4f3..f39568b28ec1 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -174,8 +174,6 @@ config ARM64
 	select HAVE_NMI
 	select HAVE_PATA_PLATFORM
 	select HAVE_PERF_EVENTS
-	select HAVE_PERF_EVENTS_NMI if ARM64_PSEUDO_NMI && HW_PERF_EVENTS
-	select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_REGS_AND_STACK_ACCESS_API
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 38bb07eff872..3605f77ad4df 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -23,8 +23,6 @@
 #include <linux/platform_device.h>
 #include <linux/sched_clock.h>
 #include <linux/smp.h>
-#include <linux/nmi.h>
-#include <linux/cpufreq.h>
 
 /* ARMv8 Cortex-A53 specific event types. */
 #define ARMV8_A53_PERFCTR_PREF_LINEFILL				0xC2
@@ -1250,21 +1248,10 @@ static struct platform_driver armv8_pmu_driver = {
 
 static int __init armv8_pmu_driver_init(void)
 {
-	int ret;
-
 	if (acpi_disabled)
-		ret = platform_driver_register(&armv8_pmu_driver);
+		return platform_driver_register(&armv8_pmu_driver);
 	else
-		ret = arm_pmu_acpi_probe(armv8_pmuv3_init);
-
-	/*
-	 * Try to re-initialize lockup detector after PMU init in
-	 * case PMU events are triggered via NMIs.
-	 */
-	if (ret == 0 && arm_pmu_irq_is_nmi())
-		lockup_detector_init();
-
-	return ret;
+		return arm_pmu_acpi_probe(armv8_pmuv3_init);
 }
 device_initcall(armv8_pmu_driver_init)
 
@@ -1322,27 +1309,3 @@ void arch_perf_update_userpage(struct perf_event *event,
 	userpg->cap_user_time_zero = 1;
 	userpg->cap_user_time_short = 1;
 }
-
-#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF
-/*
- * Safe maximum CPU frequency in case a particular platform doesn't implement
- * cpufreq driver. Although, architecture doesn't put any restrictions on
- * maximum frequency but 5 GHz seems to be safe maximum given the available
- * Arm CPUs in the market which are clocked much less than 5 GHz. On the other
- * hand, we can't make it much higher as it would lead to a large hard-lockup
- * detection timeout on parts which are running slower (eg. 1GHz on
- * Developerbox) and doesn't possess a cpufreq driver.
- */
-#define SAFE_MAX_CPU_FREQ	5000000000UL // 5 GHz
-u64 hw_nmi_get_sample_period(int watchdog_thresh)
-{
-	unsigned int cpu = smp_processor_id();
-	unsigned long max_cpu_freq;
-
-	max_cpu_freq = cpufreq_get_hw_max_freq(cpu) * 1000UL;
-	if (!max_cpu_freq)
-		max_cpu_freq = SAFE_MAX_CPU_FREQ;
-
-	return (u64)max_cpu_freq * watchdog_thresh;
-}
-#endif
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index 794a37d50853..cb2f55f450e4 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -726,11 +726,6 @@ static int armpmu_get_cpu_irq(struct arm_pmu *pmu, int cpu)
 	return per_cpu(hw_events->irq, cpu);
 }
 
-bool arm_pmu_irq_is_nmi(void)
-{
-	return has_nmi;
-}
-
 /*
  * PMU hardware loses all context when a CPU goes offline.
  * When a CPU is hotplugged back in, since some hardware registers are
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index bf7966776c55..505480217cf1 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -163,8 +163,6 @@ int arm_pmu_acpi_probe(armpmu_init_fn init_fn);
 static inline int arm_pmu_acpi_probe(armpmu_init_fn init_fn) { return 0; }
 #endif
 
-bool arm_pmu_irq_is_nmi(void);
-
 /* Internal functions only for core arm_pmu code */
 struct arm_pmu *armpmu_alloc(void);
 struct arm_pmu *armpmu_alloc_atomic(void);
-- 
cgit v1.2.3


From 5e6dca82bcaa49348f9e5fcb48df4881f6d6c4ae Mon Sep 17 00:00:00 2001
From: Nick Desaulniers <ndesaulniers@google.com>
Date: Tue, 12 Jan 2021 11:46:24 -0800
Subject: x86/entry: Emit a symbol for register restoring thunk

Arnd found a randconfig that produces the warning:

  arch/x86/entry/thunk_64.o: warning: objtool: missing symbol for insn at
  offset 0x3e

when building with LLVM_IAS=1 (Clang's integrated assembler). Josh
notes:

  With the LLVM assembler not generating section symbols, objtool has no
  way to reference this code when it generates ORC unwinder entries,
  because this code is outside of any ELF function.

  The limitation now being imposed by objtool is that all code must be
  contained in an ELF symbol.  And .L symbols don't create such symbols.

  So basically, you can use an .L symbol *inside* a function or a code
  segment, you just can't use the .L symbol to contain the code using a
  SYM_*_START/END annotation pair.

Fangrui notes that this optimization is helpful for reducing image size
when compiling with -ffunction-sections and -fdata-sections. I have
observed on the order of tens of thousands of symbols for the kernel
images built with those flags.

A patch has been authored against GNU binutils to match this behavior
of not generating unused section symbols ([1]), so this will
also become a problem for users of GNU binutils once they upgrade to 2.36.

Omit the .L prefix on a label so that the assembler will emit an entry
into the symbol table for the label, with STB_LOCAL binding. This
enables objtool to generate proper unwind info here with LLVM_IAS=1 or
GNU binutils 2.36+.

 [ bp: Massage commit message. ]

Reported-by: Arnd Bergmann <arnd@arndb.de>
Suggested-by: Josh Poimboeuf <jpoimboe@redhat.com>
Suggested-by: Borislav Petkov <bp@alien8.de>
Suggested-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lkml.kernel.org/r/20210112194625.4181814-1-ndesaulniers@google.com
Link: https://github.com/ClangBuiltLinux/linux/issues/1209
Link: https://reviews.llvm.org/D93783
Link: https://sourceware.org/binutils/docs/as/Symbol-Names.html
Link: https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=d1bcae833b32f1408485ce69f844dcd7ded093a8 [1]
---
 Documentation/asm-annotations.rst | 5 +++++
 arch/x86/entry/thunk_64.S         | 8 ++++----
 include/linux/linkage.h           | 5 +++++
 3 files changed, 14 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/asm-annotations.rst b/Documentation/asm-annotations.rst
index 32ea57483378..76424e0431f4 100644
--- a/Documentation/asm-annotations.rst
+++ b/Documentation/asm-annotations.rst
@@ -100,6 +100,11 @@ Instruction Macros
 ~~~~~~~~~~~~~~~~~~
 This section covers ``SYM_FUNC_*`` and ``SYM_CODE_*`` enumerated above.
 
+``objtool`` requires that all code must be contained in an ELF symbol. Symbol
+names that have a ``.L`` prefix do not emit symbol table entries. ``.L``
+prefixed symbols can be used within a code region, but should be avoided for
+denoting a range of code via ``SYM_*_START/END`` annotations.
+
 * ``SYM_FUNC_START`` and ``SYM_FUNC_START_LOCAL`` are supposed to be **the
   most frequent markings**. They are used for functions with standard calling
   conventions -- global and local. Like in C, they both align the functions to
diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S
index ccd32877a3c4..c9a9fbf1655f 100644
--- a/arch/x86/entry/thunk_64.S
+++ b/arch/x86/entry/thunk_64.S
@@ -31,7 +31,7 @@ SYM_FUNC_START_NOALIGN(\name)
 	.endif
 
 	call \func
-	jmp  .L_restore
+	jmp  __thunk_restore
 SYM_FUNC_END(\name)
 	_ASM_NOKPROBE(\name)
 	.endm
@@ -44,7 +44,7 @@ SYM_FUNC_END(\name)
 #endif
 
 #ifdef CONFIG_PREEMPTION
-SYM_CODE_START_LOCAL_NOALIGN(.L_restore)
+SYM_CODE_START_LOCAL_NOALIGN(__thunk_restore)
 	popq %r11
 	popq %r10
 	popq %r9
@@ -56,6 +56,6 @@ SYM_CODE_START_LOCAL_NOALIGN(.L_restore)
 	popq %rdi
 	popq %rbp
 	ret
-	_ASM_NOKPROBE(.L_restore)
-SYM_CODE_END(.L_restore)
+	_ASM_NOKPROBE(__thunk_restore)
+SYM_CODE_END(__thunk_restore)
 #endif
diff --git a/include/linux/linkage.h b/include/linux/linkage.h
index 5bcfbd972e97..dbf8506decca 100644
--- a/include/linux/linkage.h
+++ b/include/linux/linkage.h
@@ -178,6 +178,11 @@
  * Objtool generates debug info for both FUNC & CODE, but needs special
  * annotations for each CODE's start (to describe the actual stack frame).
  *
+ * Objtool requires that all code must be contained in an ELF symbol. Symbol
+ * names that have a  .L prefix do not emit symbol table entries. .L
+ * prefixed symbols can be used within a code region, but should be avoided for
+ * denoting a range of code via ``SYM_*_START/END`` annotations.
+ *
  * ALIAS -- does not generate debug info -- the aliased function will
  */
 
-- 
cgit v1.2.3


From dca5244d2f5b94f1809f0c02a549edf41ccd5493 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Tue, 12 Jan 2021 22:48:32 +0000
Subject: compiler.h: Raise minimum version of GCC to 5.1 for arm64

GCC versions >= 4.9 and < 5.1 have been shown to emit memory references
beyond the stack pointer, resulting in memory corruption if an interrupt
is taken after the stack pointer has been adjusted but before the
reference has been executed. This leads to subtle, infrequent data
corruption such as the EXT4 problems reported by Russell King at the
link below.

Life is too short for buggy compilers, so raise the minimum GCC version
required by arm64 to 5.1.

Reported-by: Russell King <linux@armlinux.org.uk>
Suggested-by: Arnd Bergmann <arnd@kernel.org>
Signed-off-by: Will Deacon <will@kernel.org>
Tested-by: Nathan Chancellor <natechancellor@gmail.com>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Reviewed-by: Nathan Chancellor <natechancellor@gmail.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: <stable@vger.kernel.org>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: Florian Weimer <fweimer@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Link: https://lore.kernel.org/r/20210105154726.GD1551@shell.armlinux.org.uk
Link: https://lore.kernel.org/r/20210112224832.10980-1-will@kernel.org
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 include/linux/compiler-gcc.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index 74c6c0486eed..555ab0fddbef 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -13,6 +13,12 @@
 /* https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 */
 #if GCC_VERSION < 40900
 # error Sorry, your version of GCC is too old - please use 4.9 or newer.
+#elif defined(CONFIG_ARM64) && GCC_VERSION < 50100
+/*
+ * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63293
+ * https://lore.kernel.org/r/20210107111841.GN1551@shell.armlinux.org.uk
+ */
+# error Sorry, your version of GCC is too old - please use 5.1 or newer.
 #endif
 
 /*
-- 
cgit v1.2.3


From 20d3bb92e84d417b0494a3b6867f0c86713db257 Mon Sep 17 00:00:00 2001
From: Klaus Jensen <k.jensen@samsung.com>
Date: Fri, 15 Jan 2021 07:30:46 +0100
Subject: nvme-pci: allow use of cmb on v1.4 controllers

Since NVMe v1.4 the Controller Memory Buffer must be explicitly enabled
by the host.

Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
[hch: avoid a local variable and add a comment]
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/pci.c | 14 ++++++++++++++
 include/linux/nvme.h    |  6 ++++++
 2 files changed, 20 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 50d9a20568a2..25456d02eddb 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -23,6 +23,7 @@
 #include <linux/t10-pi.h>
 #include <linux/types.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
+#include <linux/io-64-nonatomic-hi-lo.h>
 #include <linux/sed-opal.h>
 #include <linux/pci-p2pdma.h>
 
@@ -1795,6 +1796,9 @@ static void nvme_map_cmb(struct nvme_dev *dev)
 	if (dev->cmb_size)
 		return;
 
+	if (NVME_CAP_CMBS(dev->ctrl.cap))
+		writel(NVME_CMBMSC_CRE, dev->bar + NVME_REG_CMBMSC);
+
 	dev->cmbsz = readl(dev->bar + NVME_REG_CMBSZ);
 	if (!dev->cmbsz)
 		return;
@@ -1808,6 +1812,16 @@ static void nvme_map_cmb(struct nvme_dev *dev)
 	if (offset > bar_size)
 		return;
 
+	/*
+	 * Tell the controller about the host side address mapping the CMB,
+	 * and enable CMB decoding for the NVMe 1.4+ scheme:
+	 */
+	if (NVME_CAP_CMBS(dev->ctrl.cap)) {
+		hi_lo_writeq(NVME_CMBMSC_CRE | NVME_CMBMSC_CMSE |
+			     (pci_bus_address(pdev, bar) + offset),
+			     dev->bar + NVME_REG_CMBMSC);
+	}
+
 	/*
 	 * Controllers may support a CMB size larger than their BAR,
 	 * for example, due to being behind a bridge. Reduce the CMB to
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index d92535997687..bfed36e342cc 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -116,6 +116,9 @@ enum {
 	NVME_REG_BPMBL	= 0x0048,	/* Boot Partition Memory Buffer
 					 * Location
 					 */
+	NVME_REG_CMBMSC = 0x0050,	/* Controller Memory Buffer Memory
+					 * Space Control
+					 */
 	NVME_REG_PMRCAP	= 0x0e00,	/* Persistent Memory Capabilities */
 	NVME_REG_PMRCTL	= 0x0e04,	/* Persistent Memory Region Control */
 	NVME_REG_PMRSTS	= 0x0e08,	/* Persistent Memory Region Status */
@@ -135,6 +138,7 @@ enum {
 #define NVME_CAP_CSS(cap)	(((cap) >> 37) & 0xff)
 #define NVME_CAP_MPSMIN(cap)	(((cap) >> 48) & 0xf)
 #define NVME_CAP_MPSMAX(cap)	(((cap) >> 52) & 0xf)
+#define NVME_CAP_CMBS(cap)	(((cap) >> 57) & 0x1)
 
 #define NVME_CMB_BIR(cmbloc)	((cmbloc) & 0x7)
 #define NVME_CMB_OFST(cmbloc)	(((cmbloc) >> 12) & 0xfffff)
@@ -192,6 +196,8 @@ enum {
 	NVME_CSTS_SHST_OCCUR	= 1 << 2,
 	NVME_CSTS_SHST_CMPLT	= 2 << 2,
 	NVME_CSTS_SHST_MASK	= 3 << 2,
+	NVME_CMBMSC_CRE		= 1 << 0,
+	NVME_CMBMSC_CMSE	= 1 << 1,
 };
 
 struct nvme_id_power_state {
-- 
cgit v1.2.3


From 8eed01b5ca9c1deff329ad44f08e2041ca14842c Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Mon, 18 Jan 2021 16:06:55 +0100
Subject: mdio-bitbang: Export mdiobb_{read,write}()

Export mdiobb_read() and mdiobb_write(), so Ethernet controller drivers
can call them from their MDIO read/write wrappers.

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Tested-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/mdio/mdio-bitbang.c | 6 ++++--
 include/linux/mdio-bitbang.h    | 3 +++
 2 files changed, 7 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/mdio/mdio-bitbang.c b/drivers/net/mdio/mdio-bitbang.c
index 5136275c8e73..d3915f831854 100644
--- a/drivers/net/mdio/mdio-bitbang.c
+++ b/drivers/net/mdio/mdio-bitbang.c
@@ -149,7 +149,7 @@ static int mdiobb_cmd_addr(struct mdiobb_ctrl *ctrl, int phy, u32 addr)
 	return dev_addr;
 }
 
-static int mdiobb_read(struct mii_bus *bus, int phy, int reg)
+int mdiobb_read(struct mii_bus *bus, int phy, int reg)
 {
 	struct mdiobb_ctrl *ctrl = bus->priv;
 	int ret, i;
@@ -180,8 +180,9 @@ static int mdiobb_read(struct mii_bus *bus, int phy, int reg)
 	mdiobb_get_bit(ctrl);
 	return ret;
 }
+EXPORT_SYMBOL(mdiobb_read);
 
-static int mdiobb_write(struct mii_bus *bus, int phy, int reg, u16 val)
+int mdiobb_write(struct mii_bus *bus, int phy, int reg, u16 val)
 {
 	struct mdiobb_ctrl *ctrl = bus->priv;
 
@@ -201,6 +202,7 @@ static int mdiobb_write(struct mii_bus *bus, int phy, int reg, u16 val)
 	mdiobb_get_bit(ctrl);
 	return 0;
 }
+EXPORT_SYMBOL(mdiobb_write);
 
 struct mii_bus *alloc_mdio_bitbang(struct mdiobb_ctrl *ctrl)
 {
diff --git a/include/linux/mdio-bitbang.h b/include/linux/mdio-bitbang.h
index 5d71e8a8500f..aca4dc037b70 100644
--- a/include/linux/mdio-bitbang.h
+++ b/include/linux/mdio-bitbang.h
@@ -35,6 +35,9 @@ struct mdiobb_ctrl {
 	const struct mdiobb_ops *ops;
 };
 
+int mdiobb_read(struct mii_bus *bus, int phy, int reg);
+int mdiobb_write(struct mii_bus *bus, int phy, int reg, u16 val);
+
 /* The returned bus is not yet registered with the phy layer. */
 struct mii_bus *alloc_mdio_bitbang(struct mdiobb_ctrl *ctrl);
 
-- 
cgit v1.2.3


From de641d74fb00f5b32f054ee154e31fb037e0db88 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@nvidia.com>
Date: Sun, 17 Jan 2021 11:26:33 +0200
Subject: Revert "RDMA/mlx5: Fix devlink deadlock on net namespace deletion"

This reverts commit fbdd0049d98d44914fc57d4b91f867f4996c787b.

Due to commit in fixes tag, netdevice events were received only in one net
namespace of mlx5_core_dev. Due to this when netdevice events arrive in
net namespace other than net namespace of mlx5_core_dev, they are missed.

This results in empty GID table due to RDMA device being detached from its
net device.

Hence, revert back to receive netdevice events in all net namespaces to
restore back RDMA functionality in non init_net net namespace. The
deadlock will have to be addressed in another patch.

Fixes: fbdd0049d98d ("RDMA/mlx5: Fix devlink deadlock on net namespace deletion")
Link: https://lore.kernel.org/r/20210117092633.10690-1-leon@kernel.org
Signed-off-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/hw/mlx5/main.c                  |  6 ++----
 drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h |  5 +++++
 include/linux/mlx5/driver.h                        | 18 ------------------
 3 files changed, 7 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index d26f3f3e0462..aabdc07e4753 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -3311,8 +3311,7 @@ static int mlx5_add_netdev_notifier(struct mlx5_ib_dev *dev, u8 port_num)
 	int err;
 
 	dev->port[port_num].roce.nb.notifier_call = mlx5_netdev_event;
-	err = register_netdevice_notifier_net(mlx5_core_net(dev->mdev),
-					      &dev->port[port_num].roce.nb);
+	err = register_netdevice_notifier(&dev->port[port_num].roce.nb);
 	if (err) {
 		dev->port[port_num].roce.nb.notifier_call = NULL;
 		return err;
@@ -3324,8 +3323,7 @@ static int mlx5_add_netdev_notifier(struct mlx5_ib_dev *dev, u8 port_num)
 static void mlx5_remove_netdev_notifier(struct mlx5_ib_dev *dev, u8 port_num)
 {
 	if (dev->port[port_num].roce.nb.notifier_call) {
-		unregister_netdevice_notifier_net(mlx5_core_net(dev->mdev),
-						  &dev->port[port_num].roce.nb);
+		unregister_netdevice_notifier(&dev->port[port_num].roce.nb);
 		dev->port[port_num].roce.nb.notifier_call = NULL;
 	}
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
index 3a9fa629503f..d046db7bb047 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
@@ -90,4 +90,9 @@ int mlx5_create_encryption_key(struct mlx5_core_dev *mdev,
 			       u32 key_type, u32 *p_key_id);
 void mlx5_destroy_encryption_key(struct mlx5_core_dev *mdev, u32 key_id);
 
+static inline struct net *mlx5_core_net(struct mlx5_core_dev *dev)
+{
+	return devlink_net(priv_to_devlink(dev));
+}
+
 #endif
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index f93bfe7473aa..4672e12f1aa5 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1209,22 +1209,4 @@ static inline bool mlx5_is_roce_enabled(struct mlx5_core_dev *dev)
 	return val.vbool;
 }
 
-/**
- * mlx5_core_net - Provide net namespace of the mlx5_core_dev
- * @dev: mlx5 core device
- *
- * mlx5_core_net() returns the net namespace of mlx5 core device.
- * This can be called only in below described limited context.
- * (a) When a devlink instance for mlx5_core is registered and
- *     when devlink reload operation is disabled.
- *     or
- * (b) during devlink reload reload_down() and reload_up callbacks
- *     where it is ensured that devlink instance's net namespace is
- *     stable.
- */
-static inline struct net *mlx5_core_net(struct mlx5_core_dev *dev)
-{
-	return devlink_net(priv_to_devlink(dev));
-}
-
 #endif /* MLX5_DRIVER_H */
-- 
cgit v1.2.3


From de658a195ee23ca6aaffe197d1d2ea040beea0a2 Mon Sep 17 00:00:00 2001
From: Grant Grundler <grundler@chromium.org>
Date: Tue, 19 Jan 2021 17:12:08 -0800
Subject: net: usb: cdc_ncm: don't spew notifications

RTL8156 sends notifications about every 32ms.
Only display/log notifications when something changes.

This issue has been reported by others:
	https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1832472
	https://lkml.org/lkml/2020/8/27/1083

...
[785962.779840] usb 1-1: new high-speed USB device number 5 using xhci_hcd
[785962.929944] usb 1-1: New USB device found, idVendor=0bda, idProduct=8156, bcdDevice=30.00
[785962.929949] usb 1-1: New USB device strings: Mfr=1, Product=2, SerialNumber=6
[785962.929952] usb 1-1: Product: USB 10/100/1G/2.5G LAN
[785962.929954] usb 1-1: Manufacturer: Realtek
[785962.929956] usb 1-1: SerialNumber: 000000001
[785962.991755] usbcore: registered new interface driver cdc_ether
[785963.017068] cdc_ncm 1-1:2.0: MAC-Address: 00:24:27:88:08:15
[785963.017072] cdc_ncm 1-1:2.0: setting rx_max = 16384
[785963.017169] cdc_ncm 1-1:2.0: setting tx_max = 16384
[785963.017682] cdc_ncm 1-1:2.0 usb0: register 'cdc_ncm' at usb-0000:00:14.0-1, CDC NCM, 00:24:27:88:08:15
[785963.019211] usbcore: registered new interface driver cdc_ncm
[785963.023856] usbcore: registered new interface driver cdc_wdm
[785963.025461] usbcore: registered new interface driver cdc_mbim
[785963.038824] cdc_ncm 1-1:2.0 enx002427880815: renamed from usb0
[785963.089586] cdc_ncm 1-1:2.0 enx002427880815: network connection: disconnected
[785963.121673] cdc_ncm 1-1:2.0 enx002427880815: network connection: disconnected
[785963.153682] cdc_ncm 1-1:2.0 enx002427880815: network connection: disconnected
...

This is about 2KB per second and will overwrite all contents of a 1MB
dmesg buffer in under 10 minutes rendering them useless for debugging
many kernel problems.

This is also an extra 180 MB/day in /var/logs (or 1GB per week) rendering
the majority of those logs useless too.

When the link is up (expected state), spew amount is >2x higher:
...
[786139.600992] cdc_ncm 2-1:2.0 enx002427880815: network connection: connected
[786139.632997] cdc_ncm 2-1:2.0 enx002427880815: 2500 mbit/s downlink 2500 mbit/s uplink
[786139.665097] cdc_ncm 2-1:2.0 enx002427880815: network connection: connected
[786139.697100] cdc_ncm 2-1:2.0 enx002427880815: 2500 mbit/s downlink 2500 mbit/s uplink
[786139.729094] cdc_ncm 2-1:2.0 enx002427880815: network connection: connected
[786139.761108] cdc_ncm 2-1:2.0 enx002427880815: 2500 mbit/s downlink 2500 mbit/s uplink
...

Chrome OS cannot support RTL8156 until this is fixed.

Signed-off-by: Grant Grundler <grundler@chromium.org>
Reviewed-by: Hayes Wang <hayeswang@realtek.com>
Link: https://lore.kernel.org/r/20210120011208.3768105-1-grundler@chromium.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/cdc_ncm.c  | 12 +++++++++++-
 include/linux/usb/usbnet.h |  2 ++
 2 files changed, 13 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 5a78848db93f..291e76d32abe 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -1827,6 +1827,15 @@ cdc_ncm_speed_change(struct usbnet *dev,
 	uint32_t rx_speed = le32_to_cpu(data->DLBitRRate);
 	uint32_t tx_speed = le32_to_cpu(data->ULBitRate);
 
+	/* if the speed hasn't changed, don't report it.
+	 * RTL8156 shipped before 2021 sends notification about every 32ms.
+	 */
+	if (dev->rx_speed == rx_speed && dev->tx_speed == tx_speed)
+		return;
+
+	dev->rx_speed = rx_speed;
+	dev->tx_speed = tx_speed;
+
 	/*
 	 * Currently the USB-NET API does not support reporting the actual
 	 * device speed. Do print it instead.
@@ -1867,7 +1876,8 @@ static void cdc_ncm_status(struct usbnet *dev, struct urb *urb)
 		 * USB_CDC_NOTIFY_NETWORK_CONNECTION notification shall be
 		 * sent by device after USB_CDC_NOTIFY_SPEED_CHANGE.
 		 */
-		usbnet_link_change(dev, !!event->wValue, 0);
+		if (netif_carrier_ok(dev->net) != !!event->wValue)
+			usbnet_link_change(dev, !!event->wValue, 0);
 		break;
 
 	case USB_CDC_NOTIFY_SPEED_CHANGE:
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index 88a7673894d5..cfbfd6fe01df 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -81,6 +81,8 @@ struct usbnet {
 #		define EVENT_LINK_CHANGE	11
 #		define EVENT_SET_RX_MODE	12
 #		define EVENT_NO_IP_ALIGN	13
+	u32			rx_speed;	/* in bps - NOT Mbps */
+	u32			tx_speed;	/* in bps - NOT Mbps */
 };
 
 static inline struct usb_driver *driver_of(struct usb_interface *intf)
-- 
cgit v1.2.3


From 51dfb6ca3728bd0a0a3c23776a12d2a15a1d2457 Mon Sep 17 00:00:00 2001
From: Dmitry Osipenko <digetx@gmail.com>
Date: Wed, 20 Jan 2021 23:58:44 +0300
Subject: regulator: consumer: Add missing stubs to regulator/consumer.h

Add missing stubs to regulator/consumer.h in order to fix COMPILE_TEST
of the kernel. In particular this should fix compile-testing of OPP core
because of a missing stub for regulator_sync_voltage().

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Link: https://lore.kernel.org/r/20210120205844.12658-1-digetx@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/regulator/consumer.h | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h
index 2024944fd2f7..20e84a84fb77 100644
--- a/include/linux/regulator/consumer.h
+++ b/include/linux/regulator/consumer.h
@@ -331,6 +331,12 @@ regulator_get_exclusive(struct device *dev, const char *id)
 	return ERR_PTR(-ENODEV);
 }
 
+static inline struct regulator *__must_check
+devm_regulator_get_exclusive(struct device *dev, const char *id)
+{
+	return ERR_PTR(-ENODEV);
+}
+
 static inline struct regulator *__must_check
 regulator_get_optional(struct device *dev, const char *id)
 {
@@ -486,6 +492,11 @@ static inline int regulator_get_voltage(struct regulator *regulator)
 	return -EINVAL;
 }
 
+static inline int regulator_sync_voltage(struct regulator *regulator)
+{
+	return -EINVAL;
+}
+
 static inline int regulator_is_supported_voltage(struct regulator *regulator,
 				   int min_uV, int max_uV)
 {
@@ -578,6 +589,25 @@ static inline int devm_regulator_unregister_notifier(struct regulator *regulator
 	return 0;
 }
 
+static inline int regulator_suspend_enable(struct regulator_dev *rdev,
+					   suspend_state_t state)
+{
+	return -EINVAL;
+}
+
+static inline int regulator_suspend_disable(struct regulator_dev *rdev,
+					    suspend_state_t state)
+{
+	return -EINVAL;
+}
+
+static inline int regulator_set_suspend_voltage(struct regulator *regulator,
+						int min_uV, int max_uV,
+						suspend_state_t state)
+{
+	return -EINVAL;
+}
+
 static inline void *regulator_get_drvdata(struct regulator *regulator)
 {
 	return NULL;
-- 
cgit v1.2.3


From e020ff611ba9be54e959e6b548038f8a020da1c9 Mon Sep 17 00:00:00 2001
From: Saravana Kannan <saravanak@google.com>
Date: Sun, 10 Jan 2021 09:54:07 -0800
Subject: driver core: Fix device link device name collision

The device link device's name was of the form:
<supplier-dev-name>--<consumer-dev-name>

This can cause name collision as reported here [1] as device names are
not globally unique. Since device names have to be unique within the
bus/class, add the bus/class name as a prefix to the device names used to
construct the device link device name.

So the devuce link device's name will be of the form:
<supplier-bus-name>:<supplier-dev-name>--<consumer-bus-name>:<consumer-dev-name>

[1] - https://lore.kernel.org/lkml/20201229033440.32142-1-michael@walle.cc/

Fixes: 287905e68dd2 ("driver core: Expose device link details in sysfs")
Cc: stable@vger.kernel.org
Reported-by: Michael Walle <michael@walle.cc>
Tested-by: Michael Walle <michael@walle.cc>
Signed-off-by: Saravana Kannan <saravanak@google.com>
Link: https://lore.kernel.org/r/20210110175408.1465657-1-saravanak@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/ABI/testing/sysfs-class-devlink    |  4 ++--
 Documentation/ABI/testing/sysfs-devices-consumer |  5 +++--
 Documentation/ABI/testing/sysfs-devices-supplier |  5 +++--
 drivers/base/core.c                              | 27 +++++++++++++-----------
 include/linux/device.h                           | 12 +++++++++++
 5 files changed, 35 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/ABI/testing/sysfs-class-devlink b/Documentation/ABI/testing/sysfs-class-devlink
index b662f747c83e..8a21ce515f61 100644
--- a/Documentation/ABI/testing/sysfs-class-devlink
+++ b/Documentation/ABI/testing/sysfs-class-devlink
@@ -5,8 +5,8 @@ Description:
 		Provide a place in sysfs for the device link objects in the
 		kernel at any given time.  The name of a device link directory,
 		denoted as ... above, is of the form <supplier>--<consumer>
-		where <supplier> is the supplier device name and <consumer> is
-		the consumer device name.
+		where <supplier> is the supplier bus:device name and <consumer>
+		is the consumer bus:device name.
 
 What:		/sys/class/devlink/.../auto_remove_on
 Date:		May 2020
diff --git a/Documentation/ABI/testing/sysfs-devices-consumer b/Documentation/ABI/testing/sysfs-devices-consumer
index 1f06d74d1c3c..0809fda092e6 100644
--- a/Documentation/ABI/testing/sysfs-devices-consumer
+++ b/Documentation/ABI/testing/sysfs-devices-consumer
@@ -4,5 +4,6 @@ Contact:	Saravana Kannan <saravanak@google.com>
 Description:
 		The /sys/devices/.../consumer:<consumer> are symlinks to device
 		links where this device is the supplier. <consumer> denotes the
-		name of the consumer in that device link. There can be zero or
-		more of these symlinks for a given device.
+		name of the consumer in that device link and is of the form
+		bus:device name. There can be zero or more of these symlinks
+		for a given device.
diff --git a/Documentation/ABI/testing/sysfs-devices-supplier b/Documentation/ABI/testing/sysfs-devices-supplier
index a919e0db5e90..207f5972e98d 100644
--- a/Documentation/ABI/testing/sysfs-devices-supplier
+++ b/Documentation/ABI/testing/sysfs-devices-supplier
@@ -4,5 +4,6 @@ Contact:	Saravana Kannan <saravanak@google.com>
 Description:
 		The /sys/devices/.../supplier:<supplier> are symlinks to device
 		links where this device is the consumer. <supplier> denotes the
-		name of the supplier in that device link. There can be zero or
-		more of these symlinks for a given device.
+		name of the supplier in that device link and is of the form
+		bus:device name. There can be zero or more of these symlinks
+		for a given device.
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 3819fd012e27..78f6db169d47 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -471,7 +471,9 @@ static int devlink_add_symlinks(struct device *dev,
 	struct device *con = link->consumer;
 	char *buf;
 
-	len = max(strlen(dev_name(sup)), strlen(dev_name(con)));
+	len = max(strlen(dev_bus_name(sup)) + strlen(dev_name(sup)),
+		  strlen(dev_bus_name(con)) + strlen(dev_name(con)));
+	len += strlen(":");
 	len += strlen("supplier:") + 1;
 	buf = kzalloc(len, GFP_KERNEL);
 	if (!buf)
@@ -485,12 +487,12 @@ static int devlink_add_symlinks(struct device *dev,
 	if (ret)
 		goto err_con;
 
-	snprintf(buf, len, "consumer:%s", dev_name(con));
+	snprintf(buf, len, "consumer:%s:%s", dev_bus_name(con), dev_name(con));
 	ret = sysfs_create_link(&sup->kobj, &link->link_dev.kobj, buf);
 	if (ret)
 		goto err_con_dev;
 
-	snprintf(buf, len, "supplier:%s", dev_name(sup));
+	snprintf(buf, len, "supplier:%s:%s", dev_bus_name(sup), dev_name(sup));
 	ret = sysfs_create_link(&con->kobj, &link->link_dev.kobj, buf);
 	if (ret)
 		goto err_sup_dev;
@@ -498,7 +500,7 @@ static int devlink_add_symlinks(struct device *dev,
 	goto out;
 
 err_sup_dev:
-	snprintf(buf, len, "consumer:%s", dev_name(con));
+	snprintf(buf, len, "consumer:%s:%s", dev_bus_name(con), dev_name(con));
 	sysfs_remove_link(&sup->kobj, buf);
 err_con_dev:
 	sysfs_remove_link(&link->link_dev.kobj, "consumer");
@@ -521,7 +523,9 @@ static void devlink_remove_symlinks(struct device *dev,
 	sysfs_remove_link(&link->link_dev.kobj, "consumer");
 	sysfs_remove_link(&link->link_dev.kobj, "supplier");
 
-	len = max(strlen(dev_name(sup)), strlen(dev_name(con)));
+	len = max(strlen(dev_bus_name(sup)) + strlen(dev_name(sup)),
+		  strlen(dev_bus_name(con)) + strlen(dev_name(con)));
+	len += strlen(":");
 	len += strlen("supplier:") + 1;
 	buf = kzalloc(len, GFP_KERNEL);
 	if (!buf) {
@@ -529,9 +533,9 @@ static void devlink_remove_symlinks(struct device *dev,
 		return;
 	}
 
-	snprintf(buf, len, "supplier:%s", dev_name(sup));
+	snprintf(buf, len, "supplier:%s:%s", dev_bus_name(sup), dev_name(sup));
 	sysfs_remove_link(&con->kobj, buf);
-	snprintf(buf, len, "consumer:%s", dev_name(con));
+	snprintf(buf, len, "consumer:%s:%s", dev_bus_name(con), dev_name(con));
 	sysfs_remove_link(&sup->kobj, buf);
 	kfree(buf);
 }
@@ -752,8 +756,9 @@ struct device_link *device_link_add(struct device *consumer,
 
 	link->link_dev.class = &devlink_class;
 	device_set_pm_not_required(&link->link_dev);
-	dev_set_name(&link->link_dev, "%s--%s",
-		     dev_name(supplier), dev_name(consumer));
+	dev_set_name(&link->link_dev, "%s:%s--%s:%s",
+		     dev_bus_name(supplier), dev_name(supplier),
+		     dev_bus_name(consumer), dev_name(consumer));
 	if (device_register(&link->link_dev)) {
 		put_device(consumer);
 		put_device(supplier);
@@ -1823,9 +1828,7 @@ const char *dev_driver_string(const struct device *dev)
 	 * never change once they are set, so they don't need special care.
 	 */
 	drv = READ_ONCE(dev->driver);
-	return drv ? drv->name :
-			(dev->bus ? dev->bus->name :
-			(dev->class ? dev->class->name : ""));
+	return drv ? drv->name : dev_bus_name(dev);
 }
 EXPORT_SYMBOL(dev_driver_string);
 
diff --git a/include/linux/device.h b/include/linux/device.h
index 89bb8b84173e..1779f90eeb4c 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -609,6 +609,18 @@ static inline const char *dev_name(const struct device *dev)
 	return kobject_name(&dev->kobj);
 }
 
+/**
+ * dev_bus_name - Return a device's bus/class name, if at all possible
+ * @dev: struct device to get the bus/class name of
+ *
+ * Will return the name of the bus/class the device is attached to.  If it is
+ * not attached to a bus/class, an empty string will be returned.
+ */
+static inline const char *dev_bus_name(const struct device *dev)
+{
+	return dev->bus ? dev->bus->name : (dev->class ? dev->class->name : "");
+}
+
 __printf(2, 3) int dev_set_name(struct device *dev, const char *name, ...);
 
 #ifdef CONFIG_NUMA
-- 
cgit v1.2.3


From ac687e6e8c26181a33270efd1a2e2241377924b0 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 12 Jan 2021 11:24:04 +0100
Subject: kthread: Extract KTHREAD_IS_PER_CPU

There is a need to distinguish geniune per-cpu kthreads from kthreads
that happen to have a single CPU affinity.

Geniune per-cpu kthreads are kthreads that are CPU affine for
correctness, these will obviously have PF_KTHREAD set, but must also
have PF_NO_SETAFFINITY set, lest userspace modify their affinity and
ruins things.

However, these two things are not sufficient, PF_NO_SETAFFINITY is
also set on other tasks that have their affinities controlled through
other means, like for instance workqueues.

Therefore another bit is needed; it turns out kthread_create_per_cpu()
already has such a bit: KTHREAD_IS_PER_CPU, which is used to make
kthread_park()/kthread_unpark() work correctly.

Expose this flag and remove the implicit setting of it from
kthread_create_on_cpu(); the io_uring usage of it seems dubious at
best.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Tested-by: Valentin Schneider <valentin.schneider@arm.com>
Link: https://lkml.kernel.org/r/20210121103506.557620262@infradead.org
---
 include/linux/kthread.h |  3 +++
 kernel/kthread.c        | 27 ++++++++++++++++++++++++++-
 kernel/smpboot.c        |  1 +
 3 files changed, 30 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/kthread.h b/include/linux/kthread.h
index 65b81e0c494d..2484ed97e72f 100644
--- a/include/linux/kthread.h
+++ b/include/linux/kthread.h
@@ -33,6 +33,9 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data),
 					  unsigned int cpu,
 					  const char *namefmt);
 
+void kthread_set_per_cpu(struct task_struct *k, int cpu);
+bool kthread_is_per_cpu(struct task_struct *k);
+
 /**
  * kthread_run - create and wake a thread.
  * @threadfn: the function to run until signal_pending(current).
diff --git a/kernel/kthread.c b/kernel/kthread.c
index a5eceecd4513..e0e4a423f184 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -493,11 +493,36 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data),
 		return p;
 	kthread_bind(p, cpu);
 	/* CPU hotplug need to bind once again when unparking the thread. */
-	set_bit(KTHREAD_IS_PER_CPU, &to_kthread(p)->flags);
 	to_kthread(p)->cpu = cpu;
 	return p;
 }
 
+void kthread_set_per_cpu(struct task_struct *k, int cpu)
+{
+	struct kthread *kthread = to_kthread(k);
+	if (!kthread)
+		return;
+
+	WARN_ON_ONCE(!(k->flags & PF_NO_SETAFFINITY));
+
+	if (cpu < 0) {
+		clear_bit(KTHREAD_IS_PER_CPU, &kthread->flags);
+		return;
+	}
+
+	kthread->cpu = cpu;
+	set_bit(KTHREAD_IS_PER_CPU, &kthread->flags);
+}
+
+bool kthread_is_per_cpu(struct task_struct *k)
+{
+	struct kthread *kthread = to_kthread(k);
+	if (!kthread)
+		return false;
+
+	return test_bit(KTHREAD_IS_PER_CPU, &kthread->flags);
+}
+
 /**
  * kthread_unpark - unpark a thread created by kthread_create().
  * @k:		thread created by kthread_create().
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index 2efe1e206167..f25208e8df83 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -188,6 +188,7 @@ __smpboot_create_thread(struct smp_hotplug_thread *ht, unsigned int cpu)
 		kfree(td);
 		return PTR_ERR(tsk);
 	}
+	kthread_set_per_cpu(tsk, cpu);
 	/*
 	 * Park the thread so that it could start right on the CPU
 	 * when it is available.
-- 
cgit v1.2.3


From 9f12e37cae44a96132fc3031535a0b165486941a Mon Sep 17 00:00:00 2001
From: Sami Tolvanen <samitolvanen@google.com>
Date: Mon, 25 Jan 2021 11:09:25 -0800
Subject: Commit 9bb48c82aced ("tty: implement write_iter") converted the tty
 layer to use write_iter. Fix the redirected_tty_write declaration also in
 n_tty and change the comparisons to use write_iter instead of write.

[ Also moved the declaration of redirected_tty_write() to the proper
  location in a header file. The reason for the bug was the bogus extern
  declaration in n_tty.c silently not matching the changed definition in
  tty_io.c, and because it wasn't in a shared header file, there was no
  cross-checking of the declaration.

  Sami noticed because Clang's Control Flow Integrity checking ended up
  incidentally noticing the inconsistent declaration.    - Linus ]

Fixes: 9bb48c82aced ("tty: implement write_iter")
Signed-off-by: Sami Tolvanen <samitolvanen@google.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/tty/n_tty.c  | 7 ++-----
 drivers/tty/tty_io.c | 2 --
 include/linux/tty.h  | 1 +
 3 files changed, 3 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index 319d68c8a5df..219e85756171 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -2081,9 +2081,6 @@ static int canon_copy_from_read_buf(struct tty_struct *tty,
 	return 0;
 }
 
-extern ssize_t redirected_tty_write(struct file *, const char __user *,
-							size_t, loff_t *);
-
 /**
  *	job_control		-	check job control
  *	@tty: tty
@@ -2105,7 +2102,7 @@ static int job_control(struct tty_struct *tty, struct file *file)
 	/* NOTE: not yet done after every sleep pending a thorough
 	   check of the logic of this change. -- jlc */
 	/* don't stop on /dev/console */
-	if (file->f_op->write == redirected_tty_write)
+	if (file->f_op->write_iter == redirected_tty_write)
 		return 0;
 
 	return __tty_check_change(tty, SIGTTIN);
@@ -2309,7 +2306,7 @@ static ssize_t n_tty_write(struct tty_struct *tty, struct file *file,
 	ssize_t retval = 0;
 
 	/* Job control check -- must be done at start (POSIX.1 7.1.1.4). */
-	if (L_TOSTOP(tty) && file->f_op->write != redirected_tty_write) {
+	if (L_TOSTOP(tty) && file->f_op->write_iter != redirected_tty_write) {
 		retval = tty_check_change(tty);
 		if (retval)
 			return retval;
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 4a208a95e921..48de20916ca7 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -144,10 +144,8 @@ DEFINE_MUTEX(tty_mutex);
 
 static ssize_t tty_read(struct file *, char __user *, size_t, loff_t *);
 static ssize_t tty_write(struct kiocb *, struct iov_iter *);
-ssize_t redirected_tty_write(struct kiocb *, struct iov_iter *);
 static __poll_t tty_poll(struct file *, poll_table *);
 static int tty_open(struct inode *, struct file *);
-long tty_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 #ifdef CONFIG_COMPAT
 static long tty_compat_ioctl(struct file *file, unsigned int cmd,
 				unsigned long arg);
diff --git a/include/linux/tty.h b/include/linux/tty.h
index c873f475f0a7..37803f3e6d49 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -421,6 +421,7 @@ extern void tty_kclose(struct tty_struct *tty);
 extern int tty_dev_name_to_number(const char *name, dev_t *number);
 extern int tty_ldisc_lock(struct tty_struct *tty, unsigned long timeout);
 extern void tty_ldisc_unlock(struct tty_struct *tty);
+extern ssize_t redirected_tty_write(struct kiocb *, struct iov_iter *);
 #else
 static inline void tty_kref_put(struct tty_struct *tty)
 { }
-- 
cgit v1.2.3


From ba6dfce47c4d002d96cd02a304132fca76981172 Mon Sep 17 00:00:00 2001
From: Dave Wysochanski <dwysocha@redhat.com>
Date: Thu, 21 Jan 2021 16:17:23 -0500
Subject: SUNRPC: Move simple_get_bytes and simple_get_netobj into private
 header

Remove duplicated helper functions to parse opaque XDR objects
and place inside new file net/sunrpc/auth_gss/auth_gss_internal.h.
In the new file carry the license and copyright from the source file
net/sunrpc/auth_gss/auth_gss.c.  Finally, update the comment inside
include/linux/sunrpc/xdr.h since lockd is not the only user of
struct xdr_netobj.

Signed-off-by: Dave Wysochanski <dwysocha@redhat.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 include/linux/sunrpc/xdr.h              |  3 +--
 net/sunrpc/auth_gss/auth_gss.c          | 30 +----------------------
 net/sunrpc/auth_gss/auth_gss_internal.h | 42 +++++++++++++++++++++++++++++++++
 net/sunrpc/auth_gss/gss_krb5_mech.c     | 31 ++----------------------
 4 files changed, 46 insertions(+), 60 deletions(-)
 create mode 100644 net/sunrpc/auth_gss/auth_gss_internal.h

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 19b6dea27367..b26213ae8c1a 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -25,8 +25,7 @@ struct rpc_rqst;
 #define XDR_QUADLEN(l)		(((l) + 3) >> 2)
 
 /*
- * Generic opaque `network object.' At the kernel level, this type
- * is used only by lockd.
+ * Generic opaque `network object.'
  */
 #define XDR_MAX_NETOBJ		1024
 struct xdr_netobj {
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 4ecc2a959567..5f42aa5fc612 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -29,6 +29,7 @@
 #include <linux/uaccess.h>
 #include <linux/hashtable.h>
 
+#include "auth_gss_internal.h"
 #include "../netns.h"
 
 #include <trace/events/rpcgss.h>
@@ -125,35 +126,6 @@ gss_cred_set_ctx(struct rpc_cred *cred, struct gss_cl_ctx *ctx)
 	clear_bit(RPCAUTH_CRED_NEW, &cred->cr_flags);
 }
 
-static const void *
-simple_get_bytes(const void *p, const void *end, void *res, size_t len)
-{
-	const void *q = (const void *)((const char *)p + len);
-	if (unlikely(q > end || q < p))
-		return ERR_PTR(-EFAULT);
-	memcpy(res, p, len);
-	return q;
-}
-
-static inline const void *
-simple_get_netobj(const void *p, const void *end, struct xdr_netobj *dest)
-{
-	const void *q;
-	unsigned int len;
-
-	p = simple_get_bytes(p, end, &len, sizeof(len));
-	if (IS_ERR(p))
-		return p;
-	q = (const void *)((const char *)p + len);
-	if (unlikely(q > end || q < p))
-		return ERR_PTR(-EFAULT);
-	dest->data = kmemdup(p, len, GFP_NOFS);
-	if (unlikely(dest->data == NULL))
-		return ERR_PTR(-ENOMEM);
-	dest->len = len;
-	return q;
-}
-
 static struct gss_cl_ctx *
 gss_cred_get_ctx(struct rpc_cred *cred)
 {
diff --git a/net/sunrpc/auth_gss/auth_gss_internal.h b/net/sunrpc/auth_gss/auth_gss_internal.h
new file mode 100644
index 000000000000..c5603242b54b
--- /dev/null
+++ b/net/sunrpc/auth_gss/auth_gss_internal.h
@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: BSD-3-Clause
+/*
+ * linux/net/sunrpc/auth_gss/auth_gss_internal.h
+ *
+ * Internal definitions for RPCSEC_GSS client authentication
+ *
+ * Copyright (c) 2000 The Regents of the University of Michigan.
+ * All rights reserved.
+ *
+ */
+#include <linux/err.h>
+#include <linux/string.h>
+#include <linux/sunrpc/xdr.h>
+
+static inline const void *
+simple_get_bytes(const void *p, const void *end, void *res, size_t len)
+{
+	const void *q = (const void *)((const char *)p + len);
+	if (unlikely(q > end || q < p))
+		return ERR_PTR(-EFAULT);
+	memcpy(res, p, len);
+	return q;
+}
+
+static inline const void *
+simple_get_netobj(const void *p, const void *end, struct xdr_netobj *dest)
+{
+	const void *q;
+	unsigned int len;
+
+	p = simple_get_bytes(p, end, &len, sizeof(len));
+	if (IS_ERR(p))
+		return p;
+	q = (const void *)((const char *)p + len);
+	if (unlikely(q > end || q < p))
+		return ERR_PTR(-EFAULT);
+	dest->data = kmemdup(p, len, GFP_NOFS);
+	if (unlikely(dest->data == NULL))
+		return ERR_PTR(-ENOMEM);
+	dest->len = len;
+	return q;
+}
diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c
index ae9acf3a7389..1c092b05c2bb 100644
--- a/net/sunrpc/auth_gss/gss_krb5_mech.c
+++ b/net/sunrpc/auth_gss/gss_krb5_mech.c
@@ -21,6 +21,8 @@
 #include <linux/sunrpc/xdr.h>
 #include <linux/sunrpc/gss_krb5_enctypes.h>
 
+#include "auth_gss_internal.h"
+
 #if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_AUTH
 #endif
@@ -143,35 +145,6 @@ get_gss_krb5_enctype(int etype)
 	return NULL;
 }
 
-static const void *
-simple_get_bytes(const void *p, const void *end, void *res, int len)
-{
-	const void *q = (const void *)((const char *)p + len);
-	if (unlikely(q > end || q < p))
-		return ERR_PTR(-EFAULT);
-	memcpy(res, p, len);
-	return q;
-}
-
-static const void *
-simple_get_netobj(const void *p, const void *end, struct xdr_netobj *res)
-{
-	const void *q;
-	unsigned int len;
-
-	p = simple_get_bytes(p, end, &len, sizeof(len));
-	if (IS_ERR(p))
-		return p;
-	q = (const void *)((const char *)p + len);
-	if (unlikely(q > end || q < p))
-		return ERR_PTR(-EFAULT);
-	res->data = kmemdup(p, len, GFP_NOFS);
-	if (unlikely(res->data == NULL))
-		return ERR_PTR(-ENOMEM);
-	res->len = len;
-	return q;
-}
-
 static inline const void *
 get_key(const void *p, const void *end,
 	struct krb5_ctx *ctx, struct crypto_sync_skcipher **res)
-- 
cgit v1.2.3


From 97c753e62e6c31a404183898d950d8c08d752dbd Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 28 Jan 2021 00:37:51 +0900
Subject: tracing/kprobe: Fix to support kretprobe events on unloaded modules

Fix kprobe_on_func_entry() returns error code instead of false so that
register_kretprobe() can return an appropriate error code.

append_trace_kprobe() expects the kprobe registration returns -ENOENT
when the target symbol is not found, and it checks whether the target
module is unloaded or not. If the target module doesn't exist, it
defers to probe the target symbol until the module is loaded.

However, since register_kretprobe() returns -EINVAL instead of -ENOENT
in that case, it always fail on putting the kretprobe event on unloaded
modules. e.g.

Kprobe event:
/sys/kernel/debug/tracing # echo p xfs:xfs_end_io >> kprobe_events
[   16.515574] trace_kprobe: This probe might be able to register after target module is loaded. Continue.

Kretprobe event: (p -> r)
/sys/kernel/debug/tracing # echo r xfs:xfs_end_io >> kprobe_events
sh: write error: Invalid argument
/sys/kernel/debug/tracing # cat error_log
[   41.122514] trace_kprobe: error: Failed to register probe event
  Command: r xfs:xfs_end_io
             ^

To fix this bug, change kprobe_on_func_entry() to detect symbol lookup
failure and return -ENOENT in that case. Otherwise it returns -EINVAL
or 0 (succeeded, given address is on the entry).

Link: https://lkml.kernel.org/r/161176187132.1067016.8118042342894378981.stgit@devnote2

Cc: stable@vger.kernel.org
Fixes: 59158ec4aef7 ("tracing/kprobes: Check the probe on unloaded module correctly")
Reported-by: Jianlin Lv <Jianlin.Lv@arm.com>
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/kprobes.h     |  2 +-
 kernel/kprobes.c            | 34 +++++++++++++++++++++++++---------
 kernel/trace/trace_kprobe.c | 10 ++++++----
 3 files changed, 32 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index b3a36b0cfc81..1883a4a9f16a 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -266,7 +266,7 @@ extern void kprobes_inc_nmissed_count(struct kprobe *p);
 extern bool arch_within_kprobe_blacklist(unsigned long addr);
 extern int arch_populate_kprobe_blacklist(void);
 extern bool arch_kprobe_on_func_entry(unsigned long offset);
-extern bool kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset);
+extern int kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset);
 
 extern bool within_kprobe_blacklist(unsigned long addr);
 extern int kprobe_add_ksym_blacklist(unsigned long entry);
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index f7fb5d135930..1a5bc321e0a5 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1954,29 +1954,45 @@ bool __weak arch_kprobe_on_func_entry(unsigned long offset)
 	return !offset;
 }
 
-bool kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset)
+/**
+ * kprobe_on_func_entry() -- check whether given address is function entry
+ * @addr: Target address
+ * @sym:  Target symbol name
+ * @offset: The offset from the symbol or the address
+ *
+ * This checks whether the given @addr+@offset or @sym+@offset is on the
+ * function entry address or not.
+ * This returns 0 if it is the function entry, or -EINVAL if it is not.
+ * And also it returns -ENOENT if it fails the symbol or address lookup.
+ * Caller must pass @addr or @sym (either one must be NULL), or this
+ * returns -EINVAL.
+ */
+int kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset)
 {
 	kprobe_opcode_t *kp_addr = _kprobe_addr(addr, sym, offset);
 
 	if (IS_ERR(kp_addr))
-		return false;
+		return PTR_ERR(kp_addr);
 
-	if (!kallsyms_lookup_size_offset((unsigned long)kp_addr, NULL, &offset) ||
-						!arch_kprobe_on_func_entry(offset))
-		return false;
+	if (!kallsyms_lookup_size_offset((unsigned long)kp_addr, NULL, &offset))
+		return -ENOENT;
 
-	return true;
+	if (!arch_kprobe_on_func_entry(offset))
+		return -EINVAL;
+
+	return 0;
 }
 
 int register_kretprobe(struct kretprobe *rp)
 {
-	int ret = 0;
+	int ret;
 	struct kretprobe_instance *inst;
 	int i;
 	void *addr;
 
-	if (!kprobe_on_func_entry(rp->kp.addr, rp->kp.symbol_name, rp->kp.offset))
-		return -EINVAL;
+	ret = kprobe_on_func_entry(rp->kp.addr, rp->kp.symbol_name, rp->kp.offset);
+	if (ret)
+		return ret;
 
 	if (kretprobe_blacklist_size) {
 		addr = kprobe_addr(&rp->kp);
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index e6fba1798771..56c7fbff7bd7 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -221,9 +221,9 @@ bool trace_kprobe_on_func_entry(struct trace_event_call *call)
 {
 	struct trace_kprobe *tk = trace_kprobe_primary_from_call(call);
 
-	return tk ? kprobe_on_func_entry(tk->rp.kp.addr,
+	return tk ? (kprobe_on_func_entry(tk->rp.kp.addr,
 			tk->rp.kp.addr ? NULL : tk->rp.kp.symbol_name,
-			tk->rp.kp.addr ? 0 : tk->rp.kp.offset) : false;
+			tk->rp.kp.addr ? 0 : tk->rp.kp.offset) == 0) : false;
 }
 
 bool trace_kprobe_error_injectable(struct trace_event_call *call)
@@ -828,9 +828,11 @@ static int trace_kprobe_create(int argc, const char *argv[])
 		}
 		if (is_return)
 			flags |= TPARG_FL_RETURN;
-		if (kprobe_on_func_entry(NULL, symbol, offset))
+		ret = kprobe_on_func_entry(NULL, symbol, offset);
+		if (ret == 0)
 			flags |= TPARG_FL_FENTRY;
-		if (offset && is_return && !(flags & TPARG_FL_FENTRY)) {
+		/* Defer the ENOENT case until register kprobe */
+		if (ret == -EINVAL && is_return) {
 			trace_probe_log_err(0, BAD_RETPROBE);
 			goto parse_error;
 		}
-- 
cgit v1.2.3


From 4c457e8cb75eda91906a4f89fc39bde3f9a43922 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sat, 23 Jan 2021 12:27:59 +0000
Subject: genirq/msi: Activate Multi-MSI early when MSI_FLAG_ACTIVATE_EARLY is
 set

When MSI_FLAG_ACTIVATE_EARLY is set (which is the case for PCI),
__msi_domain_alloc_irqs() performs the activation of the interrupt (which
in the case of PCI results in the endpoint being programmed) as soon as the
interrupt is allocated.

But it appears that this is only done for the first vector, introducing an
inconsistent behaviour for PCI Multi-MSI.

Fix it by iterating over the number of vectors allocated to each MSI
descriptor. This is easily achieved by introducing a new
"for_each_msi_vector" iterator, together with a tiny bit of refactoring.

Fixes: f3b0946d629c ("genirq/msi: Make sure PCI MSIs are activated early")
Reported-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20210123122759.1781359-1-maz@kernel.org
---
 include/linux/msi.h |  6 ++++++
 kernel/irq/msi.c    | 44 ++++++++++++++++++++------------------------
 2 files changed, 26 insertions(+), 24 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/msi.h b/include/linux/msi.h
index 360a0a7e7341..aef35fd1cf11 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -178,6 +178,12 @@ struct msi_desc {
 	list_for_each_entry((desc), dev_to_msi_list((dev)), list)
 #define for_each_msi_entry_safe(desc, tmp, dev)	\
 	list_for_each_entry_safe((desc), (tmp), dev_to_msi_list((dev)), list)
+#define for_each_msi_vector(desc, __irq, dev)				\
+	for_each_msi_entry((desc), (dev))				\
+		if ((desc)->irq)					\
+			for (__irq = (desc)->irq;			\
+			     __irq < ((desc)->irq + (desc)->nvec_used);	\
+			     __irq++)
 
 #ifdef CONFIG_IRQ_MSI_IOMMU
 static inline const void *msi_desc_get_iommu_cookie(struct msi_desc *desc)
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index dc0e2d7fbdfd..b338d622f26e 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -436,22 +436,22 @@ int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
 
 	can_reserve = msi_check_reservation_mode(domain, info, dev);
 
-	for_each_msi_entry(desc, dev) {
-		virq = desc->irq;
-		if (desc->nvec_used == 1)
-			dev_dbg(dev, "irq %d for MSI\n", virq);
-		else
+	/*
+	 * This flag is set by the PCI layer as we need to activate
+	 * the MSI entries before the PCI layer enables MSI in the
+	 * card. Otherwise the card latches a random msi message.
+	 */
+	if (!(info->flags & MSI_FLAG_ACTIVATE_EARLY))
+		goto skip_activate;
+
+	for_each_msi_vector(desc, i, dev) {
+		if (desc->irq == i) {
+			virq = desc->irq;
 			dev_dbg(dev, "irq [%d-%d] for MSI\n",
 				virq, virq + desc->nvec_used - 1);
-		/*
-		 * This flag is set by the PCI layer as we need to activate
-		 * the MSI entries before the PCI layer enables MSI in the
-		 * card. Otherwise the card latches a random msi message.
-		 */
-		if (!(info->flags & MSI_FLAG_ACTIVATE_EARLY))
-			continue;
+		}
 
-		irq_data = irq_domain_get_irq_data(domain, desc->irq);
+		irq_data = irq_domain_get_irq_data(domain, i);
 		if (!can_reserve) {
 			irqd_clr_can_reserve(irq_data);
 			if (domain->flags & IRQ_DOMAIN_MSI_NOMASK_QUIRK)
@@ -462,28 +462,24 @@ int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
 			goto cleanup;
 	}
 
+skip_activate:
 	/*
 	 * If these interrupts use reservation mode, clear the activated bit
 	 * so request_irq() will assign the final vector.
 	 */
 	if (can_reserve) {
-		for_each_msi_entry(desc, dev) {
-			irq_data = irq_domain_get_irq_data(domain, desc->irq);
+		for_each_msi_vector(desc, i, dev) {
+			irq_data = irq_domain_get_irq_data(domain, i);
 			irqd_clr_activated(irq_data);
 		}
 	}
 	return 0;
 
 cleanup:
-	for_each_msi_entry(desc, dev) {
-		struct irq_data *irqd;
-
-		if (desc->irq == virq)
-			break;
-
-		irqd = irq_domain_get_irq_data(domain, desc->irq);
-		if (irqd_is_activated(irqd))
-			irq_domain_deactivate_irq(irqd);
+	for_each_msi_vector(desc, i, dev) {
+		irq_data = irq_domain_get_irq_data(domain, i);
+		if (irqd_is_activated(irq_data))
+			irq_domain_deactivate_irq(irq_data);
 	}
 	msi_domain_free_irqs(domain, dev);
 	return ret;
-- 
cgit v1.2.3


From c8b186a8d54d7e12d28e9f9686cb00ff18fc2ab2 Mon Sep 17 00:00:00 2001
From: Alexey Kardashevskiy <aik@ozlabs.ru>
Date: Tue, 2 Feb 2021 18:23:26 +1100
Subject: tracepoint: Fix race between tracing and removing tracepoint

When executing a tracepoint, the tracepoint's func is dereferenced twice -
in __DO_TRACE() (where the returned pointer is checked) and later on in
__traceiter_##_name where the returned pointer is dereferenced without
checking which leads to races against tracepoint_removal_sync() and
crashes.

This adds a check before referencing the pointer in tracepoint_ptr_deref.

Link: https://lkml.kernel.org/r/20210202072326.120557-1-aik@ozlabs.ru

Cc: stable@vger.kernel.org
Fixes: d25e37d89dd2f ("tracepoint: Optimize using static_call()")
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/tracepoint.h | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 0f21617f1a66..966ed8980327 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -307,11 +307,13 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 									\
 		it_func_ptr =						\
 			rcu_dereference_raw((&__tracepoint_##_name)->funcs); \
-		do {							\
-			it_func = (it_func_ptr)->func;			\
-			__data = (it_func_ptr)->data;			\
-			((void(*)(void *, proto))(it_func))(__data, args); \
-		} while ((++it_func_ptr)->func);			\
+		if (it_func_ptr) {					\
+			do {						\
+				it_func = (it_func_ptr)->func;		\
+				__data = (it_func_ptr)->data;		\
+				((void(*)(void *, proto))(it_func))(__data, args); \
+			} while ((++it_func_ptr)->func);		\
+		}							\
 		return 0;						\
 	}								\
 	DEFINE_STATIC_CALL(tp_func_##_name, __traceiter_##_name);
-- 
cgit v1.2.3


From 4c9fb5d9140802db4db9f66c23887f43174e113c Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Tue, 2 Feb 2021 15:54:19 +0100
Subject: iommu: Check dev->iommu in dev_iommu_priv_get() before dereferencing
 it

The dev_iommu_priv_get() needs a similar check to
dev_iommu_fwspec_get() to make sure no NULL-ptr is dereferenced.

Fixes: 05a0542b456e1 ("iommu/amd: Store dev_data as device iommu private data")
Cc: stable@vger.kernel.org	# v5.8+
Link: https://lore.kernel.org/r/20210202145419.29143-1-joro@8bytes.org
Reference: https://bugzilla.kernel.org/show_bug.cgi?id=211241
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 include/linux/iommu.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index b3f0e2018c62..efa96263b81b 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -616,7 +616,10 @@ static inline void dev_iommu_fwspec_set(struct device *dev,
 
 static inline void *dev_iommu_priv_get(struct device *dev)
 {
-	return dev->iommu->priv;
+	if (dev->iommu)
+		return dev->iommu->priv;
+	else
+		return NULL;
 }
 
 static inline void dev_iommu_priv_set(struct device *dev, void *priv)
-- 
cgit v1.2.3


From 52cbd23a119c6ebf40a527e53f3402d2ea38eccb Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 3 Feb 2021 14:29:52 -0500
Subject: udp: fix skb_copy_and_csum_datagram with odd segment sizes

When iteratively computing a checksum with csum_block_add, track the
offset "pos" to correctly rotate in csum_block_add when offset is odd.

The open coded implementation of skb_copy_and_csum_datagram did this.
With the switch to __skb_datagram_iter calling csum_and_copy_to_iter,
pos was reinitialized to 0 on each call.

Bring back the pos by passing it along with the csum to the callback.

Changes v1->v2
  - pass csum value, instead of csump pointer (Alexander Duyck)

Link: https://lore.kernel.org/netdev/20210128152353.GB27281@optiplex/
Fixes: 950fcaecd5cc ("datagram: consolidate datagram copy to iter helpers")
Reported-by: Oliver Graute <oliver.graute@gmail.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20210203192952.1849843-1-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/uio.h |  8 +++++++-
 lib/iov_iter.c      | 24 ++++++++++++++----------
 net/core/datagram.c | 12 ++++++++++--
 3 files changed, 31 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/uio.h b/include/linux/uio.h
index 72d88566694e..27ff8eb786dc 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -260,7 +260,13 @@ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count)
 {
 	i->count = count;
 }
-size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *csump, struct iov_iter *i);
+
+struct csum_state {
+	__wsum csum;
+	size_t off;
+};
+
+size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *csstate, struct iov_iter *i);
 size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i);
 bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i);
 size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp,
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index a21e6a5792c5..f0b2ccb1bb01 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -592,14 +592,15 @@ static __wsum csum_and_memcpy(void *to, const void *from, size_t len,
 }
 
 static size_t csum_and_copy_to_pipe_iter(const void *addr, size_t bytes,
-				__wsum *csum, struct iov_iter *i)
+					 struct csum_state *csstate,
+					 struct iov_iter *i)
 {
 	struct pipe_inode_info *pipe = i->pipe;
 	unsigned int p_mask = pipe->ring_size - 1;
+	__wsum sum = csstate->csum;
+	size_t off = csstate->off;
 	unsigned int i_head;
 	size_t n, r;
-	size_t off = 0;
-	__wsum sum = *csum;
 
 	if (!sanity(i))
 		return 0;
@@ -621,7 +622,8 @@ static size_t csum_and_copy_to_pipe_iter(const void *addr, size_t bytes,
 		i_head++;
 	} while (n);
 	i->count -= bytes;
-	*csum = sum;
+	csstate->csum = sum;
+	csstate->off = off;
 	return bytes;
 }
 
@@ -1522,18 +1524,19 @@ bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum,
 }
 EXPORT_SYMBOL(csum_and_copy_from_iter_full);
 
-size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *csump,
+size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *_csstate,
 			     struct iov_iter *i)
 {
+	struct csum_state *csstate = _csstate;
 	const char *from = addr;
-	__wsum *csum = csump;
 	__wsum sum, next;
-	size_t off = 0;
+	size_t off;
 
 	if (unlikely(iov_iter_is_pipe(i)))
-		return csum_and_copy_to_pipe_iter(addr, bytes, csum, i);
+		return csum_and_copy_to_pipe_iter(addr, bytes, _csstate, i);
 
-	sum = *csum;
+	sum = csstate->csum;
+	off = csstate->off;
 	if (unlikely(iov_iter_is_discard(i))) {
 		WARN_ON(1);	/* for now */
 		return 0;
@@ -1561,7 +1564,8 @@ size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *csump,
 		off += v.iov_len;
 	})
 	)
-	*csum = sum;
+	csstate->csum = sum;
+	csstate->off = off;
 	return bytes;
 }
 EXPORT_SYMBOL(csum_and_copy_to_iter);
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 81809fa735a7..15ab9ffb27fe 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -721,8 +721,16 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset,
 				      struct iov_iter *to, int len,
 				      __wsum *csump)
 {
-	return __skb_datagram_iter(skb, offset, to, len, true,
-			csum_and_copy_to_iter, csump);
+	struct csum_state csdata = { .csum = *csump };
+	int ret;
+
+	ret = __skb_datagram_iter(skb, offset, to, len, true,
+				  csum_and_copy_to_iter, &csdata);
+	if (ret)
+		return ret;
+
+	*csump = csdata.csum;
+	return 0;
 }
 
 /**
-- 
cgit v1.2.3


From 585fc0d2871c9318c949fbf45b1f081edd489e96 Mon Sep 17 00:00:00 2001
From: Muchun Song <songmuchun@bytedance.com>
Date: Thu, 4 Feb 2021 18:32:03 -0800
Subject: mm: hugetlbfs: fix cannot migrate the fallocated HugeTLB page

If a new hugetlb page is allocated during fallocate it will not be
marked as active (set_page_huge_active) which will result in a later
isolate_huge_page failure when the page migration code would like to
move that page.  Such a failure would be unexpected and wrong.

Only export set_page_huge_active, just leave clear_page_huge_active as
static.  Because there are no external users.

Link: https://lkml.kernel.org/r/20210115124942.46403-3-songmuchun@bytedance.com
Fixes: 70c3547e36f5 (hugetlbfs: add hugetlbfs_fallocate())
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Cc: David Hildenbrand <david@redhat.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/hugetlbfs/inode.c    | 3 ++-
 include/linux/hugetlb.h | 2 ++
 mm/hugetlb.c            | 2 +-
 3 files changed, 5 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index b5c109703daa..21c20fd5f9ee 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -735,9 +735,10 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 
 		mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 
+		set_page_huge_active(page);
 		/*
 		 * unlock_page because locked by add_to_page_cache()
-		 * page_put due to reference from alloc_huge_page()
+		 * put_page() due to reference from alloc_huge_page()
 		 */
 		unlock_page(page);
 		put_page(page);
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index ebca2ef02212..b5807f23caf8 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -770,6 +770,8 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
 }
 #endif
 
+void set_page_huge_active(struct page *page);
+
 #else	/* CONFIG_HUGETLB_PAGE */
 struct hstate {};
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 18f6ee317900..6f0e242d38ca 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1349,7 +1349,7 @@ bool page_huge_active(struct page *page)
 }
 
 /* never called for tail page */
-static void set_page_huge_active(struct page *page)
+void set_page_huge_active(struct page *page)
 {
 	VM_BUG_ON_PAGE(!PageHeadHuge(page), page);
 	SetPagePrivate(&page[1]);
-- 
cgit v1.2.3


From 4f6ec8602341e97b364e4e0d41a1ed08148f5e98 Mon Sep 17 00:00:00 2001
From: Rick Edgecombe <rick.p.edgecombe@intel.com>
Date: Thu, 4 Feb 2021 18:32:24 -0800
Subject: mm/vmalloc: separate put pages and flush VM flags

When VM_MAP_PUT_PAGES was added, it was defined with the same value as
VM_FLUSH_RESET_PERMS.  This doesn't seem like it will cause any big
functional problems other than some excess flushing for VM_MAP_PUT_PAGES
allocations.

Redefine VM_MAP_PUT_PAGES to have its own value.  Also, rearrange things
so flags are less likely to be missed in the future.

Link: https://lkml.kernel.org/r/20210122233706.9304-1-rick.p.edgecombe@intel.com
Fixes: b944afc9d64d ("mm: add a VM_MAP_PUT_PAGES flag for vmap")
Signed-off-by: Rick Edgecombe <rick.p.edgecombe@intel.com>
Suggested-by: Matthew Wilcox <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Daniel Axtens <dja@axtens.net>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/vmalloc.h | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 80c0181c411d..cedcda6593f6 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -24,7 +24,8 @@ struct notifier_block;		/* in notifier.h */
 #define VM_UNINITIALIZED	0x00000020	/* vm_struct is not fully initialized */
 #define VM_NO_GUARD		0x00000040      /* don't add guard page */
 #define VM_KASAN		0x00000080      /* has allocated kasan shadow memory */
-#define VM_MAP_PUT_PAGES	0x00000100	/* put pages and free array in vfree */
+#define VM_FLUSH_RESET_PERMS	0x00000100	/* reset direct map and flush TLB on unmap, can't be freed in atomic context */
+#define VM_MAP_PUT_PAGES	0x00000200	/* put pages and free array in vfree */
 
 /*
  * VM_KASAN is used slighly differently depending on CONFIG_KASAN_VMALLOC.
@@ -37,12 +38,6 @@ struct notifier_block;		/* in notifier.h */
  * determine which allocations need the module shadow freed.
  */
 
-/*
- * Memory with VM_FLUSH_RESET_PERMS cannot be freed in an interrupt or with
- * vfree_atomic().
- */
-#define VM_FLUSH_RESET_PERMS	0x00000100      /* Reset direct map and flush TLB on unmap */
-
 /* bits [20..32] reserved for arch specific ioremap internals */
 
 /*
-- 
cgit v1.2.3


From 49c6631d3b4f61a7b5bb0453a885a12bfa06ffd8 Mon Sep 17 00:00:00 2001
From: Vincenzo Frascino <vincenzo.frascino@arm.com>
Date: Thu, 4 Feb 2021 18:32:49 -0800
Subject: kasan: add explicit preconditions to kasan_report()

Patch series "kasan: Fix metadata detection for KASAN_HW_TAGS", v5.

With the introduction of KASAN_HW_TAGS, kasan_report() currently assumes
that every location in memory has valid metadata associated.  This is
due to the fact that addr_has_metadata() returns always true.

As a consequence of this, an invalid address (e.g.  NULL pointer
address) passed to kasan_report() when KASAN_HW_TAGS is enabled, leads
to a kernel panic.

Example below, based on arm64:

   BUG: KASAN: invalid-access in 0x0
   Read at addr 0000000000000000 by task swapper/0/1
   Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000
   Mem abort info:
     ESR = 0x96000004
     EC = 0x25: DABT (current EL), IL = 32 bits
     SET = 0, FnV = 0
     EA = 0, S1PTW = 0
   Data abort info:
     ISV = 0, ISS = 0x00000004
     CM = 0, WnR = 0

  ...

   Call trace:
    mte_get_mem_tag+0x24/0x40
    kasan_report+0x1a4/0x410
    alsa_sound_last_init+0x8c/0xa4
    do_one_initcall+0x50/0x1b0
    kernel_init_freeable+0x1d4/0x23c
    kernel_init+0x14/0x118
    ret_from_fork+0x10/0x34
   Code: d65f03c0 9000f021 f9428021 b6cfff61 (d9600000)
   ---[ end trace 377c8bb45bdd3a1a ]---
   hrtimer: interrupt took 48694256 ns
   note: swapper/0[1] exited with preempt_count 1
   Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b
   SMP: stopping secondary CPUs
   Kernel Offset: 0x35abaf140000 from 0xffff800010000000
   PHYS_OFFSET: 0x40000000
   CPU features: 0x0a7e0152,61c0a030
   Memory Limit: none
   ---[ end Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b ]---

This series fixes the behavior of addr_has_metadata() that now returns
true only when the address is valid.

This patch (of 2):

With the introduction of KASAN_HW_TAGS, kasan_report() accesses the
metadata only when addr_has_metadata() succeeds.

Add a comment to make sure that the preconditions to the function are
explicitly clarified.

Link: https://lkml.kernel.org/r/20210126134409.47894-1-vincenzo.frascino@arm.com
Link: https://lkml.kernel.org/r/20210126134409.47894-2-vincenzo.frascino@arm.com
Signed-off-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Reviewed-by: Andrey Konovalov <andreyknvl@google.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Leon Romanovsky <leonro@mellanox.com>
Cc: Andrey Konovalov <andreyknvl@google.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: "Paul E . McKenney" <paulmck@kernel.org>
Cc: Naresh Kamboju <naresh.kamboju@linaro.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kasan.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index fe1ae73ff8b5..0aea9e2a2a01 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -333,6 +333,13 @@ static inline void *kasan_reset_tag(const void *addr)
 	return (void *)arch_kasan_reset_tag(addr);
 }
 
+/**
+ * kasan_report - print a report about a bad memory access detected by KASAN
+ * @addr: address of the bad access
+ * @size: size of the bad access
+ * @is_write: whether the bad access is a write or a read
+ * @ip: instruction pointer for the accessibility check or the bad access itself
+ */
 bool kasan_report(unsigned long addr, size_t size,
 		bool is_write, unsigned long ip);
 
-- 
cgit v1.2.3


From 4c7bcb51ae25f79e3733982e5d0cd8ce8640ddfc Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Mon, 21 Dec 2020 19:56:47 +0100
Subject: genirq: Prevent [devm_]irq_alloc_desc from returning irq 0

Since commit a85a6c86c25b ("driver core: platform: Clarify that IRQ 0
is invalid"), having a linux-irq with number 0 will trigger a WARN()
when calling platform_get_irq*() to retrieve that linux-irq.

Since [devm_]irq_alloc_desc allocs a single irq and since irq 0 is not used
on some systems, it can return 0, triggering that WARN(). This happens
e.g. on Intel Bay Trail and Cherry Trail devices using the LPE audio engine
for HDMI audio:

 0 is an invalid IRQ number
 WARNING: CPU: 3 PID: 472 at drivers/base/platform.c:238 platform_get_irq_optional+0x108/0x180
 Modules linked in: snd_hdmi_lpe_audio(+) ...

 Call Trace:
  platform_get_irq+0x17/0x30
  hdmi_lpe_audio_probe+0x4a/0x6c0 [snd_hdmi_lpe_audio]

 ---[ end trace ceece38854223a0b ]---

Change the 'from' parameter passed to __[devm_]irq_alloc_descs() by the
[devm_]irq_alloc_desc macros from 0 to 1, so that these macros will no
longer return 0.

Fixes: a85a6c86c25b ("driver core: platform: Clarify that IRQ 0 is invalid")
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20201221185647.226146-1-hdegoede@redhat.com
---
 include/linux/irq.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 4aeb1c4c7e07..2efde6a79b7e 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -928,7 +928,7 @@ int __devm_irq_alloc_descs(struct device *dev, int irq, unsigned int from,
 	__irq_alloc_descs(irq, from, cnt, node, THIS_MODULE, NULL)
 
 #define irq_alloc_desc(node)			\
-	irq_alloc_descs(-1, 0, 1, node)
+	irq_alloc_descs(-1, 1, 1, node)
 
 #define irq_alloc_desc_at(at, node)		\
 	irq_alloc_descs(at, at, 1, node)
@@ -943,7 +943,7 @@ int __devm_irq_alloc_descs(struct device *dev, int irq, unsigned int from,
 	__devm_irq_alloc_descs(dev, irq, from, cnt, node, THIS_MODULE, NULL)
 
 #define devm_irq_alloc_desc(dev, node)				\
-	devm_irq_alloc_descs(dev, -1, 0, 1, node)
+	devm_irq_alloc_descs(dev, -1, 1, 1, node)
 
 #define devm_irq_alloc_desc_at(dev, at, node)			\
 	devm_irq_alloc_descs(dev, at, at, 1, node)
-- 
cgit v1.2.3


From 6342adcaa683c2b705c24ed201dc11b35854c88d Mon Sep 17 00:00:00 2001
From: Gabriel Krisman Bertazi <krisman@collabora.com>
Date: Wed, 3 Feb 2021 13:00:48 -0500
Subject: entry: Ensure trap after single-step on system call return

Commit 299155244770 ("entry: Drop usage of TIF flags in the generic syscall
code") introduced a bug on architectures using the generic syscall entry
code, in which processes stopped by PTRACE_SYSCALL do not trap on syscall
return after receiving a TIF_SINGLESTEP.

The reason is that the meaning of TIF_SINGLESTEP flag is overloaded to
cause the trap after a system call is executed, but since the above commit,
the syscall call handler only checks for the SYSCALL_WORK flags on the exit
work.

Split the meaning of TIF_SINGLESTEP such that it only means single-step
mode, and create a new type of SYSCALL_WORK to request a trap immediately
after a syscall in single-step mode.  In the current implementation, the
SYSCALL_WORK flag shadows the TIF_SINGLESTEP flag for simplicity.

Update x86 to flip this bit when a tracer enables single stepping.

Fixes: 299155244770 ("entry: Drop usage of TIF flags in the generic syscall code")
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Kyle Huey <me@kylehuey.com>
Link: https://lore.kernel.org/r/87h7mtc9pr.fsf_-_@collabora.com
---
 arch/x86/include/asm/entry-common.h |  2 --
 arch/x86/kernel/step.c              | 10 ++++++++--
 include/linux/entry-common.h        |  1 +
 include/linux/thread_info.h         |  2 ++
 kernel/entry/common.c               | 12 ++----------
 5 files changed, 13 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h
index 6fe54b2813c1..2b87b191b3b8 100644
--- a/arch/x86/include/asm/entry-common.h
+++ b/arch/x86/include/asm/entry-common.h
@@ -43,8 +43,6 @@ static __always_inline void arch_check_user_regs(struct pt_regs *regs)
 }
 #define arch_check_user_regs arch_check_user_regs
 
-#define ARCH_SYSCALL_EXIT_WORK		(_TIF_SINGLESTEP)
-
 static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
 						  unsigned long ti_work)
 {
diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c
index 60d2c3798ba2..0f3c307b37b3 100644
--- a/arch/x86/kernel/step.c
+++ b/arch/x86/kernel/step.c
@@ -127,12 +127,17 @@ static int enable_single_step(struct task_struct *child)
 		regs->flags |= X86_EFLAGS_TF;
 
 	/*
-	 * Always set TIF_SINGLESTEP - this guarantees that
-	 * we single-step system calls etc..  This will also
+	 * Always set TIF_SINGLESTEP.  This will also
 	 * cause us to set TF when returning to user mode.
 	 */
 	set_tsk_thread_flag(child, TIF_SINGLESTEP);
 
+	/*
+	 * Ensure that a trap is triggered once stepping out of a system
+	 * call prior to executing any user instruction.
+	 */
+	set_task_syscall_work(child, SYSCALL_EXIT_TRAP);
+
 	oflags = regs->flags;
 
 	/* Set TF on the kernel stack.. */
@@ -230,6 +235,7 @@ void user_disable_single_step(struct task_struct *child)
 
 	/* Always clear TIF_SINGLESTEP... */
 	clear_tsk_thread_flag(child, TIF_SINGLESTEP);
+	clear_task_syscall_work(child, SYSCALL_EXIT_TRAP);
 
 	/* But touch TF only if it was set by us.. */
 	if (test_and_clear_tsk_thread_flag(child, TIF_FORCED_TF))
diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index ca86a00abe86..a104b298019a 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -46,6 +46,7 @@
 				 SYSCALL_WORK_SYSCALL_TRACE |		\
 				 SYSCALL_WORK_SYSCALL_AUDIT |		\
 				 SYSCALL_WORK_SYSCALL_USER_DISPATCH |	\
+				 SYSCALL_WORK_SYSCALL_EXIT_TRAP	|	\
 				 ARCH_SYSCALL_WORK_EXIT)
 
 /*
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index c8a974cead73..9b2158c69275 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -43,6 +43,7 @@ enum syscall_work_bit {
 	SYSCALL_WORK_BIT_SYSCALL_EMU,
 	SYSCALL_WORK_BIT_SYSCALL_AUDIT,
 	SYSCALL_WORK_BIT_SYSCALL_USER_DISPATCH,
+	SYSCALL_WORK_BIT_SYSCALL_EXIT_TRAP,
 };
 
 #define SYSCALL_WORK_SECCOMP		BIT(SYSCALL_WORK_BIT_SECCOMP)
@@ -51,6 +52,7 @@ enum syscall_work_bit {
 #define SYSCALL_WORK_SYSCALL_EMU	BIT(SYSCALL_WORK_BIT_SYSCALL_EMU)
 #define SYSCALL_WORK_SYSCALL_AUDIT	BIT(SYSCALL_WORK_BIT_SYSCALL_AUDIT)
 #define SYSCALL_WORK_SYSCALL_USER_DISPATCH BIT(SYSCALL_WORK_BIT_SYSCALL_USER_DISPATCH)
+#define SYSCALL_WORK_SYSCALL_EXIT_TRAP	BIT(SYSCALL_WORK_BIT_SYSCALL_EXIT_TRAP)
 #endif
 
 #include <asm/thread_info.h>
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 6dd82be60df8..f9d491b17b78 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -209,15 +209,9 @@ static void exit_to_user_mode_prepare(struct pt_regs *regs)
 	lockdep_sys_exit();
 }
 
-#ifndef _TIF_SINGLESTEP
-static inline bool report_single_step(unsigned long work)
-{
-	return false;
-}
-#else
 /*
  * If SYSCALL_EMU is set, then the only reason to report is when
- * TIF_SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP).  This syscall
+ * SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP).  This syscall
  * instruction has been already reported in syscall_enter_from_user_mode().
  */
 static inline bool report_single_step(unsigned long work)
@@ -225,10 +219,8 @@ static inline bool report_single_step(unsigned long work)
 	if (work & SYSCALL_WORK_SYSCALL_EMU)
 		return false;
 
-	return !!(current_thread_info()->flags & _TIF_SINGLESTEP);
+	return work & SYSCALL_WORK_SYSCALL_EXIT_TRAP;
 }
-#endif
-
 
 static void syscall_exit_work(struct pt_regs *regs, unsigned long work)
 {
-- 
cgit v1.2.3


From 3aa6bce9af0e25b735c9c1263739a5639a336ae8 Mon Sep 17 00:00:00 2001
From: Edwin Peer <edwin.peer@broadcom.com>
Date: Fri, 5 Feb 2021 17:37:32 -0800
Subject: net: watchdog: hold device global xmit lock during tx disable

Prevent netif_tx_disable() running concurrently with dev_watchdog() by
taking the device global xmit lock. Otherwise, the recommended:

	netif_carrier_off(dev);
	netif_tx_disable(dev);

driver shutdown sequence can happen after the watchdog has already
checked carrier, resulting in possible false alarms. This is because
netif_tx_lock() only sets the frozen bit without maintaining the locks
on the individual queues.

Fixes: c3f26a269c24 ("netdev: Fix lockdep warnings in multiqueue configurations.")
Signed-off-by: Edwin Peer <edwin.peer@broadcom.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 259be67644e3..5ff27c12ce68 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4352,6 +4352,7 @@ static inline void netif_tx_disable(struct net_device *dev)
 
 	local_bh_disable();
 	cpu = smp_processor_id();
+	spin_lock(&dev->tx_global_lock);
 	for (i = 0; i < dev->num_tx_queues; i++) {
 		struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
 
@@ -4359,6 +4360,7 @@ static inline void netif_tx_disable(struct net_device *dev)
 		netif_tx_stop_queue(txq);
 		__netif_tx_unlock(txq);
 	}
+	spin_unlock(&dev->tx_global_lock);
 	local_bh_enable();
 }
 
-- 
cgit v1.2.3